Merge tag 'wireless-drivers-next-for-davem-2016-06-21' of git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/wireless-drivers-next

Kalle Valo says:

====================
wireless-drivers patches for 4.8

Major changes:

ath10k

* enable btcoex support without restarting firmware
* enable ipq4019 support using AHB bus
* add QCA9887 chipset support
* retrieve calibration data from EEPROM, currently only for QCA9887

wil6210

* add pm_notify handling

brcmfmac

* add support for the PCIE devices 43525 and 43465
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/Documentation/DocBook/80211.tmpl b/Documentation/DocBook/80211.tmpl
index 5f7c559..800fe7a 100644
--- a/Documentation/DocBook/80211.tmpl
+++ b/Documentation/DocBook/80211.tmpl
@@ -136,6 +136,7 @@
 !Finclude/net/cfg80211.h cfg80211_ibss_joined
 !Finclude/net/cfg80211.h cfg80211_connect_result
 !Finclude/net/cfg80211.h cfg80211_connect_bss
+!Finclude/net/cfg80211.h cfg80211_connect_timeout
 !Finclude/net/cfg80211.h cfg80211_roamed
 !Finclude/net/cfg80211.h cfg80211_disconnected
 !Finclude/net/cfg80211.h cfg80211_ready_on_channel
diff --git a/Documentation/DocBook/device-drivers.tmpl b/Documentation/DocBook/device-drivers.tmpl
index de79efd..8c68768 100644
--- a/Documentation/DocBook/device-drivers.tmpl
+++ b/Documentation/DocBook/device-drivers.tmpl
@@ -128,16 +128,44 @@
 !Edrivers/base/platform.c
 !Edrivers/base/bus.c
      </sect1>
-     <sect1><title>Device Drivers DMA Management</title>
+     <sect1>
+       <title>Buffer Sharing and Synchronization</title>
+       <para>
+         The dma-buf subsystem provides the framework for sharing buffers
+         for hardware (DMA) access across multiple device drivers and
+         subsystems, and for synchronizing asynchronous hardware access.
+       </para>
+       <para>
+         This is used, for example, by drm "prime" multi-GPU support, but
+         is of course not limited to GPU use cases.
+       </para>
+       <para>
+         The three main components of this are: (1) dma-buf, representing
+         a sg_table and exposed to userspace as a file descriptor to allow
+         passing between devices, (2) fence, which provides a mechanism
+         to signal when one device as finished access, and (3) reservation,
+         which manages the shared or exclusive fence(s) associated with
+         the buffer.
+       </para>
+       <sect2><title>dma-buf</title>
 !Edrivers/dma-buf/dma-buf.c
-!Edrivers/dma-buf/fence.c
-!Edrivers/dma-buf/seqno-fence.c
-!Iinclude/linux/fence.h
-!Iinclude/linux/seqno-fence.h
+!Iinclude/linux/dma-buf.h
+       </sect2>
+       <sect2><title>reservation</title>
+!Pdrivers/dma-buf/reservation.c Reservation Object Overview
 !Edrivers/dma-buf/reservation.c
 !Iinclude/linux/reservation.h
+       </sect2>
+       <sect2><title>fence</title>
+!Edrivers/dma-buf/fence.c
+!Iinclude/linux/fence.h
+!Edrivers/dma-buf/seqno-fence.c
+!Iinclude/linux/seqno-fence.h
 !Edrivers/dma-buf/sync_file.c
 !Iinclude/linux/sync_file.h
+       </sect2>
+     </sect1>
+     <sect1><title>Device Drivers DMA Management</title>
 !Edrivers/base/dma-coherent.c
 !Edrivers/base/dma-mapping.c
      </sect1>
diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt
index c6938e5..4da60b4 100644
--- a/Documentation/arm64/silicon-errata.txt
+++ b/Documentation/arm64/silicon-errata.txt
@@ -56,6 +56,7 @@
 | ARM            | MMU-500         | #841119,#826419 | N/A                     |
 |                |                 |                 |                         |
 | Cavium         | ThunderX ITS    | #22375, #24313  | CAVIUM_ERRATUM_22375    |
+| Cavium         | ThunderX ITS    | #23144          | CAVIUM_ERRATUM_23144    |
 | Cavium         | ThunderX GICv3  | #23154          | CAVIUM_ERRATUM_23154    |
 | Cavium         | ThunderX Core   | #27456          | CAVIUM_ERRATUM_27456    |
 | Cavium         | ThunderX SMMUv2 | #27704          | N/A		       |
diff --git a/Documentation/devicetree/bindings/display/imx/ldb.txt b/Documentation/devicetree/bindings/display/imx/ldb.txt
index 0a175d9..a407462 100644
--- a/Documentation/devicetree/bindings/display/imx/ldb.txt
+++ b/Documentation/devicetree/bindings/display/imx/ldb.txt
@@ -62,6 +62,7 @@
    display-timings are used instead.
 
 Optional properties (required if display-timings are used):
+ - ddc-i2c-bus: phandle of an I2C controller used for DDC EDID probing
  - display-timings : A node that describes the display timings as defined in
    Documentation/devicetree/bindings/display/display-timing.txt.
  - fsl,data-mapping : should be "spwg" or "jeida"
diff --git a/Documentation/devicetree/bindings/net/brcm,mdio-mux-iproc.txt b/Documentation/devicetree/bindings/net/brcm,mdio-mux-iproc.txt
new file mode 100644
index 0000000..dfe287a
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/brcm,mdio-mux-iproc.txt
@@ -0,0 +1,59 @@
+Properties for an MDIO bus multiplexer found in Broadcom iProc based SoCs.
+
+This MDIO bus multiplexer defines buses that could be internal as well as
+external to SoCs and could accept MDIO transaction compatible to C-22 or
+C-45 Clause. When child bus is selected, one needs to select these two
+properties as well to generate desired MDIO transaction on appropriate bus.
+
+Required properties in addition to the generic multiplexer properties:
+
+MDIO multiplexer node:
+- compatible: brcm,mdio-mux-iproc.
+
+Every non-ethernet PHY requires a compatible so that it could be probed based
+on this compatible string.
+
+Additional information regarding generic multiplexer properties can be found
+at- Documentation/devicetree/bindings/net/mdio-mux.txt
+
+
+for example:
+		mdio_mux_iproc: mdio-mux@6602023c {
+			compatible = "brcm,mdio-mux-iproc";
+			reg = <0x6602023c 0x14>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			mdio@0 {
+				reg = <0x0>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				pci_phy0: pci-phy@0 {
+					compatible = "brcm,ns2-pcie-phy";
+					reg = <0x0>;
+					#phy-cells = <0>;
+				};
+			};
+
+			mdio@7 {
+				reg = <0x7>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				pci_phy1: pci-phy@0 {
+					compatible = "brcm,ns2-pcie-phy";
+					reg = <0x0>;
+					#phy-cells = <0>;
+				};
+			};
+			mdio@10 {
+				reg = <0x10>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				gphy0: eth-phy@10 {
+					reg = <0x10>;
+				};
+			};
+		};
diff --git a/Documentation/devicetree/bindings/net/can/rcar_canfd.txt b/Documentation/devicetree/bindings/net/can/rcar_canfd.txt
new file mode 100644
index 0000000..d45182b
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/can/rcar_canfd.txt
@@ -0,0 +1,89 @@
+Renesas R-Car CAN FD controller Device Tree Bindings
+----------------------------------------------------
+
+Required properties:
+- compatible: Must contain one or more of the following:
+  - "renesas,rcar-gen3-canfd" for R-Car Gen3 compatible controller.
+  - "renesas,r8a7795-canfd" for R8A7795 (R-Car H3) compatible controller.
+
+  When compatible with the generic version, nodes must list the
+  SoC-specific version corresponding to the platform first, followed by the
+  family-specific and/or generic versions.
+
+- reg: physical base address and size of the R-Car CAN FD register map.
+- interrupts: interrupt specifier for the Global & Channel interrupts
+- clocks: phandles and clock specifiers for 3 clock inputs.
+- clock-names: 3 clock input name strings: "fck", "canfd", "can_clk".
+- pinctrl-0: pin control group to be used for this controller.
+- pinctrl-names: must be "default".
+
+Required child nodes:
+The controller supports two channels and each is represented as a child node.
+The name of the child nodes are "channel0" and "channel1" respectively. Each
+child node supports the "status" property only, which is used to
+enable/disable the respective channel.
+
+Required properties for "renesas,r8a7795-canfd" compatible:
+In R8A7795 SoC, canfd clock is a div6 clock and can be used by both CAN
+and CAN FD controller at the same time. It needs to be scaled to maximum
+frequency if any of these controllers use it. This is done using the
+below properties.
+
+- assigned-clocks: phandle of canfd clock.
+- assigned-clock-rates: maximum frequency of this clock.
+
+Example
+-------
+
+SoC common .dtsi file:
+
+		canfd: can@e66c0000 {
+			compatible = "renesas,r8a7795-canfd",
+				     "renesas,rcar-gen3-canfd";
+			reg = <0 0xe66c0000 0 0x8000>;
+			interrupts = <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>,
+				   <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD 914>,
+			       <&cpg CPG_CORE R8A7795_CLK_CANFD>,
+			       <&can_clk>;
+			clock-names = "fck", "canfd", "can_clk";
+			assigned-clocks = <&cpg CPG_CORE R8A7795_CLK_CANFD>;
+			assigned-clock-rates = <40000000>;
+			power-domains = <&cpg>;
+			status = "disabled";
+
+			channel0 {
+				status = "disabled";
+			};
+
+			channel1 {
+				status = "disabled";
+			};
+		};
+
+Board specific .dts file:
+
+E.g. below enables Channel 1 alone in the board.
+
+&canfd {
+        pinctrl-0 = <&canfd1_pins>;
+        pinctrl-names = "default";
+        status = "okay";
+
+	channel1 {
+		status = "okay";
+	};
+};
+
+E.g. below enables Channel 0 alone in the board using External clock
+as fCAN clock.
+
+&canfd {
+        pinctrl-0 = <&canfd0_pins &can_clk_pins>;
+        pinctrl-names = "default";
+        status = "okay";
+
+	channel0 {
+		status = "okay";
+	};
+};
diff --git a/Documentation/devicetree/bindings/net/cirrus,cs89x0.txt b/Documentation/devicetree/bindings/net/cirrus,cs89x0.txt
new file mode 100644
index 0000000..c070076
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/cirrus,cs89x0.txt
@@ -0,0 +1,13 @@
+* Cirrus Logic CS8900/CS8920 Network Controller
+
+Required properties:
+- compatible	: Should be "cirrus,cs8900" or "cirrus,cs8920".
+- reg		: Address and length of the IO space.
+- interrupts	: Should contain the controller interrupt line.
+
+Examples:
+	eth0: eth@10000000 {
+		compatible = "cirrus,cs8900";
+		reg = <0x10000000 0x400>;
+		interrupts = <10>;
+	};
diff --git a/Documentation/devicetree/bindings/net/cpsw.txt b/Documentation/devicetree/bindings/net/cpsw.txt
index 0ae0649..5ad439f 100644
--- a/Documentation/devicetree/bindings/net/cpsw.txt
+++ b/Documentation/devicetree/bindings/net/cpsw.txt
@@ -15,7 +15,6 @@
 - cpdma_channels 	: Specifies number of channels in CPDMA
 - ale_entries		: Specifies No of entries ALE can hold
 - bd_ram_size		: Specifies internal descriptor RAM size
-- rx_descs		: Specifies number of Rx descriptors
 - mac_control		: Specifies Default MAC control register content
 			  for the specific platform
 - slaves		: Specifies number for slaves
diff --git a/Documentation/devicetree/bindings/net/dsa/b53.txt b/Documentation/devicetree/bindings/net/dsa/b53.txt
new file mode 100644
index 0000000..ca752db
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/dsa/b53.txt
@@ -0,0 +1,88 @@
+Broadcom BCM53xx Ethernet switches
+==================================
+
+Required properties:
+
+- compatible: For external switch chips, compatible string must be exactly one
+  of: "brcm,bcm5325"
+      "brcm,bcm53115"
+      "brcm,bcm53125"
+      "brcm,bcm53128"
+      "brcm,bcm5365"
+      "brcm,bcm5395"
+      "brcm,bcm5397"
+      "brcm,bcm5398"
+
+  For the BCM5310x SoCs with an integrated switch, must be one of:
+      "brcm,bcm53010-srab"
+      "brcm,bcm53011-srab"
+      "brcm,bcm53012-srab"
+      "brcm,bcm53018-srab"
+      "brcm,bcm53019-srab" and the mandatory "brcm,bcm5301x-srab" string
+
+  For the BCM63xx/33xx SoCs with an integrated switch, must be one of:
+      "brcm,bcm3384-switch"
+      "brcm,bcm6328-switch"
+      "brcm,bcm6368-switch" and the mandatory "brcm,bcm63xx-switch"
+
+See Documentation/devicetree/bindings/dsa/dsa.txt for a list of additional
+required and optional properties.
+
+Examples:
+
+Ethernet switch connected via MDIO to the host, CPU port wired to eth0:
+
+	eth0: ethernet@10001000 {
+		compatible = "brcm,unimac";
+		reg = <0x10001000 0x1000>;
+
+		fixed-link {
+			speed = <1000>;
+			duplex-full;
+		};
+	};
+
+	mdio0: mdio@10000000 {
+		compatible = "brcm,unimac-mdio";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		switch0: ethernet-switch@30 {
+			compatible = "brcm,bcm53125";
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			ports {
+				port0@0 {
+					reg = <0>;
+					label = "lan1";
+				};
+
+				port1@1 {
+					reg = <1>;
+					label = "lan2";
+				};
+
+				port5@5 {
+					reg = <5>;
+					label = "cable-modem";
+					fixed-link {
+						speed = <1000>;
+						duplex-full;
+					};
+					phy-mode = "rgmii-txid";
+				};
+
+				port8@8 {
+					reg = <8>;
+					label = "cpu";
+					fixed-link {
+						speed = <1000>;
+						duplex-full;
+					};
+					phy-mode = "rgmii-txid";
+					ethernet = <&eth0>;
+				};
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/net/dsa/dsa.txt b/Documentation/devicetree/bindings/net/dsa/dsa.txt
index 9f4807f..9bbbe7f 100644
--- a/Documentation/devicetree/bindings/net/dsa/dsa.txt
+++ b/Documentation/devicetree/bindings/net/dsa/dsa.txt
@@ -1,5 +1,279 @@
-Marvell Distributed Switch Architecture Device Tree Bindings
-------------------------------------------------------------
+Distributed Switch Architecture Device Tree Bindings
+----------------------------------------------------
+
+Two bindings exist, one of which has been deprecated due to
+limitations.
+
+Current Binding
+---------------
+
+Switches are true Linux devices and can be probes by any means. Once
+probed, they register to the DSA framework, passing a node
+pointer. This node is expected to fulfil the following binding, and
+may contain additional properties as required by the device it is
+embedded within.
+
+Required properties:
+
+- ports		: A container for child nodes representing switch ports.
+
+Optional properties:
+
+- dsa,member	: A two element list indicates which DSA cluster, and position
+		  within the cluster a switch takes. <0 0> is cluster 0,
+		  switch 0. <0 1> is cluster 0, switch 1. <1 0> is cluster 1,
+		  switch 0. A switch not part of any cluster (single device
+		  hanging off a CPU port) must not specify this property
+
+The ports container has the following properties
+
+Required properties:
+
+- #address-cells	: Must be 1
+- #size-cells		: Must be 0
+
+Each port children node must have the following mandatory properties:
+- reg			: Describes the port address in the switch
+- label			: Describes the label associated with this port, which
+                          will become the netdev name. Special labels are
+			  "cpu" to indicate a CPU port and "dsa" to
+			  indicate an uplink/downlink port between switches in
+			  the cluster.
+
+A port labelled "dsa" has the following mandatory property:
+
+- link			: Should be a list of phandles to other switch's DSA
+			  port. This port is used as the outgoing port
+			  towards the phandle ports. The full routing
+			  information must be given, not just the one hop
+			  routes to neighbouring switches.
+
+A port labelled "cpu" has the following mandatory property:
+
+- ethernet		: Should be a phandle to a valid Ethernet device node.
+                          This host device is what the switch port is
+			  connected to.
+
+Port child nodes may also contain the following optional standardised
+properties, described in binding documents:
+
+- phy-handle		: Phandle to a PHY on an MDIO bus. See
+			  Documentation/devicetree/bindings/net/ethernet.txt
+			  for details.
+
+- phy-mode		: See
+			  Documentation/devicetree/bindings/net/ethernet.txt
+			  for details.
+
+- fixed-link		: Fixed-link subnode describing a link to a non-MDIO
+			  managed entity. See
+			  Documentation/devicetree/bindings/net/fixed-link.txt
+			  for details.
+
+Example
+
+The following example shows three switches on three MDIO busses,
+linked into one DSA cluster.
+
+&mdio1 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	switch0: switch0@0 {
+		compatible = "marvell,mv88e6085";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		reg = <0>;
+
+		dsa,member = <0 0>;
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			port@0 {
+				reg = <0>;
+				label = "lan0";
+			};
+
+			port@1 {
+				reg = <1>;
+				label = "lan1";
+			};
+
+			port@2 {
+				reg = <2>;
+				label = "lan2";
+			};
+
+			switch0port5: port@5 {
+				reg = <5>;
+				label = "dsa";
+				phy-mode = "rgmii-txid";
+				link = <&switch1port6
+					&switch2port9>;
+				fixed-link {
+					speed = <1000>;
+					full-duplex;
+				};
+			};
+
+			port@6 {
+				reg = <6>;
+				label = "cpu";
+				ethernet = <&fec1>;
+				fixed-link {
+					speed = <100>;
+					full-duplex;
+				};
+			};
+		};
+	};
+};
+
+&mdio2 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	switch1: switch1@0 {
+		compatible = "marvell,mv88e6085";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		reg = <0>;
+
+		dsa,member = <0 1>;
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			port@0 {
+				reg = <0>;
+				label = "lan3";
+				phy-handle = <&switch1phy0>;
+			};
+
+			port@1 {
+				reg = <1>;
+				label = "lan4";
+				phy-handle = <&switch1phy1>;
+			};
+
+			port@2 {
+				reg = <2>;
+				label = "lan5";
+				phy-handle = <&switch1phy2>;
+			};
+
+			switch1port5: port@5 {
+				reg = <5>;
+				label = "dsa";
+				link = <&switch2port9>;
+				phy-mode = "rgmii-txid";
+				fixed-link {
+					speed = <1000>;
+					full-duplex;
+				};
+			};
+
+			switch1port6: port@6 {
+				reg = <6>;
+				label = "dsa";
+				phy-mode = "rgmii-txid";
+				link = <&switch0port5>;
+				fixed-link {
+					speed = <1000>;
+					full-duplex;
+				};
+			};
+		};
+		mdio-bus {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			switch1phy0: switch1phy0@0 {
+				reg = <0>;
+			};
+			switch1phy1: switch1phy0@1 {
+				reg = <1>;
+			};
+			switch1phy2: switch1phy0@2 {
+				reg = <2>;
+			};
+		};
+	 };
+};
+
+&mdio4 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	switch2: switch2@0 {
+		compatible = "marvell,mv88e6085";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		reg = <0>;
+
+		dsa,member = <0 2>;
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			port@0 {
+				reg = <0>;
+				label = "lan6";
+			};
+
+			port@1 {
+				reg = <1>;
+				label = "lan7";
+			};
+
+			port@2 {
+				reg = <2>;
+				label = "lan8";
+			};
+
+			port@3 {
+				reg = <3>;
+				label = "optical3";
+				fixed-link {
+					speed = <1000>;
+					full-duplex;
+					link-gpios = <&gpio6 2
+					      GPIO_ACTIVE_HIGH>;
+				};
+			};
+
+			port@4 {
+				reg = <4>;
+				label = "optical4";
+				fixed-link {
+					speed = <1000>;
+					full-duplex;
+					link-gpios = <&gpio6 3
+					      GPIO_ACTIVE_HIGH>;
+				};
+			};
+
+			switch2port9: port@9 {
+				reg = <9>;
+				label = "dsa";
+				phy-mode = "rgmii-txid";
+				link = <&switch1port5
+					&switch0port5>;
+				fixed-link {
+					speed = <1000>;
+					full-duplex;
+				};
+			};
+		};
+	};
+};
+
+Deprecated Binding
+------------------
+
+The deprecated binding makes use of a platform device to represent the
+switches. The switches themselves are not Linux devices, and make use
+of an MDIO bus for management.
 
 Required properties:
 - compatible		: Should be "marvell,dsa"
diff --git a/Documentation/devicetree/bindings/net/mdio-mux.txt b/Documentation/devicetree/bindings/net/mdio-mux.txt
index 491f5bd..f58571f 100644
--- a/Documentation/devicetree/bindings/net/mdio-mux.txt
+++ b/Documentation/devicetree/bindings/net/mdio-mux.txt
@@ -5,11 +5,12 @@
 bus multiplexer/switch will have one child node for each child bus.
 
 Required properties:
-- mdio-parent-bus : phandle to the parent MDIO bus.
 - #address-cells = <1>;
 - #size-cells = <0>;
 
 Optional properties:
+- mdio-parent-bus : phandle to the parent MDIO bus.
+
 - Other properties specific to the multiplexer/switch hardware.
 
 Required properties for child nodes:
diff --git a/Documentation/devicetree/bindings/phy/brcm,mdio-mux-bus-pci.txt b/Documentation/devicetree/bindings/phy/brcm,mdio-mux-bus-pci.txt
new file mode 100644
index 0000000..5b51007
--- /dev/null
+++ b/Documentation/devicetree/bindings/phy/brcm,mdio-mux-bus-pci.txt
@@ -0,0 +1,27 @@
+* Broadcom NS2 PCIe PHY binding document
+
+Required bus properties:
+- reg: MDIO Bus number for the MDIO interface
+- #address-cells: must be 1
+- #size-cells: must be 0
+
+Required PHY properties:
+- compatible: should be "brcm,ns2-pcie-phy"
+- reg: MDIO Phy ID for the MDIO interface
+- #phy-cells: must be 0
+
+This is a child bus node of "brcm,mdio-mux-iproc" node.
+
+Example:
+
+mdio@0 {
+	reg = <0x0>;
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	pci_phy0: pci-phy@0 {
+		compatible = "brcm,ns2-pcie-phy";
+		reg = <0x0>;
+		#phy-cells = <0>;
+	};
+};
diff --git a/Documentation/filesystems/devpts.txt b/Documentation/filesystems/devpts.txt
index 30d2fcb..9f94fe27 100644
--- a/Documentation/filesystems/devpts.txt
+++ b/Documentation/filesystems/devpts.txt
@@ -1,141 +1,26 @@
+Each mount of the devpts filesystem is now distinct such that ptys
+and their indicies allocated in one mount are independent from ptys
+and their indicies in all other mounts.
 
-To support containers, we now allow multiple instances of devpts filesystem,
-such that indices of ptys allocated in one instance are independent of indices
-allocated in other instances of devpts.
+All mounts of the devpts filesystem now create a /dev/pts/ptmx node
+with permissions 0000.
 
-To preserve backward compatibility, this support for multiple instances is
-enabled only if:
+To retain backwards compatibility the a ptmx device node (aka any node
+created with "mknod name c 5 2") when opened will look for an instance
+of devpts under the name "pts" in the same directory as the ptmx device
+node.
 
-	- CONFIG_DEVPTS_MULTIPLE_INSTANCES=y, and
-	- '-o newinstance' mount option is specified while mounting devpts
-
-IOW, devpts now supports both single-instance and multi-instance semantics.
-
-If CONFIG_DEVPTS_MULTIPLE_INSTANCES=n, there is no change in behavior and
-this referred to as the "legacy" mode. In this mode, the new mount options
-(-o newinstance and -o ptmxmode) will be ignored with a 'bogus option' message
-on console.
-
-If CONFIG_DEVPTS_MULTIPLE_INSTANCES=y and devpts is mounted without the
-'newinstance' option (as in current start-up scripts) the new mount binds
-to the initial kernel mount of devpts. This mode is referred to as the
-'single-instance' mode and the current, single-instance semantics are
-preserved, i.e PTYs are common across the system.
-
-The only difference between this single-instance mode and the legacy mode
-is the presence of new, '/dev/pts/ptmx' node with permissions 0000, which
-can safely be ignored.
-
-If CONFIG_DEVPTS_MULTIPLE_INSTANCES=y and 'newinstance' option is specified,
-the mount is considered to be in the multi-instance mode and a new instance
-of the devpts fs is created. Any ptys created in this instance are independent
-of ptys in other instances of devpts. Like in the single-instance mode, the
-/dev/pts/ptmx node is present. To effectively use the multi-instance mode,
-open of /dev/ptmx must be a redirected to '/dev/pts/ptmx' using a symlink or
-bind-mount.
-
-Eg: A container startup script could do the following:
-
-	$ chmod 0666 /dev/pts/ptmx
-	$ rm /dev/ptmx
-	$ ln -s pts/ptmx /dev/ptmx
-	$ ns_exec -cm /bin/bash
-
-	# We are now in new container
-
-	$ umount /dev/pts
-	$ mount -t devpts -o newinstance lxcpts /dev/pts
-	$ sshd -p 1234
-
-where 'ns_exec -cm /bin/bash' calls clone() with CLONE_NEWNS flag and execs
-/bin/bash in the child process.  A pty created by the sshd is not visible in
-the original mount of /dev/pts.
+As an option instead of placing a /dev/ptmx device node at /dev/ptmx
+it is possible to place a symlink to /dev/pts/ptmx at /dev/ptmx or
+to bind mount /dev/ptx/ptmx to /dev/ptmx.  If you opt for using
+the devpts filesystem in this manner devpts should be mounted with
+the ptmxmode=0666, or chmod 0666 /dev/pts/ptmx should be called.
 
 Total count of pty pairs in all instances is limited by sysctls:
 kernel.pty.max = 4096		- global limit
-kernel.pty.reserve = 1024	- reserve for initial instance
+kernel.pty.reserve = 1024	- reserved for filesystems mounted from the initial mount namespace
 kernel.pty.nr			- current count of ptys
 
 Per-instance limit could be set by adding mount option "max=<count>".
 This feature was added in kernel 3.4 together with sysctl kernel.pty.reserve.
 In kernels older than 3.4 sysctl kernel.pty.max works as per-instance limit.
-
-User-space changes
-------------------
-
-In multi-instance mode (i.e '-o newinstance' mount option is specified at least
-once), following user-space issues should be noted.
-
-1. If -o newinstance mount option is never used, /dev/pts/ptmx can be ignored
-   and no change is needed to system-startup scripts.
-
-2. To effectively use multi-instance mode (i.e -o newinstance is specified)
-   administrators or startup scripts should "redirect" open of /dev/ptmx to
-   /dev/pts/ptmx using either a bind mount or symlink.
-
-	$ mount -t devpts -o newinstance devpts /dev/pts
-
-   followed by either
-
-	$ rm /dev/ptmx
-	$ ln -s pts/ptmx /dev/ptmx
-	$ chmod 666 /dev/pts/ptmx
-   or
-	$ mount -o bind /dev/pts/ptmx /dev/ptmx
-
-3. The '/dev/ptmx -> pts/ptmx' symlink is the preferred method since it
-   enables better error-reporting and treats both single-instance and
-   multi-instance mounts similarly.
-
-   But this method requires that system-startup scripts set the mode of
-   /dev/pts/ptmx correctly (default mode is 0000). The scripts can set the
-   mode by, either
-
-   	- adding ptmxmode mount option to devpts entry in /etc/fstab, or
-	- using 'chmod 0666 /dev/pts/ptmx'
-
-4. If multi-instance mode mount is needed for containers, but the system
-   startup scripts have not yet been updated, container-startup scripts
-   should bind mount /dev/ptmx to /dev/pts/ptmx to avoid breaking single-
-   instance mounts.
-
-   Or, in general, container-startup scripts should use:
-
-	mount -t devpts -o newinstance -o ptmxmode=0666 devpts /dev/pts
-	if [ ! -L /dev/ptmx ]; then
-		mount -o bind /dev/pts/ptmx /dev/ptmx
-	fi
-
-   When all devpts mounts are multi-instance, /dev/ptmx can permanently be
-   a symlink to pts/ptmx and the bind mount can be ignored.
-
-5. A multi-instance mount that is not accompanied by the /dev/ptmx to
-   /dev/pts/ptmx redirection would result in an unusable/unreachable pty.
-
-	mount -t devpts -o newinstance lxcpts /dev/pts
-
-   immediately followed by:
-
-	open("/dev/ptmx")
-
-    would create a pty, say /dev/pts/7, in the initial kernel mount.
-    But /dev/pts/7 would be invisible in the new mount.
-
-6. The permissions for /dev/pts/ptmx node should be specified when mounting
-   /dev/pts, using the '-o ptmxmode=%o' mount option (default is 0000).
-
-	mount -t devpts -o newinstance -o ptmxmode=0644 devpts /dev/pts
-
-   The permissions can be later be changed as usual with 'chmod'.
-
-	chmod 666 /dev/pts/ptmx
-
-7. A mount of devpts without the 'newinstance' option results in binding to
-   initial kernel mount.  This behavior while preserving legacy semantics,
-   does not provide strict isolation in a container environment. i.e by
-   mounting devpts without the 'newinstance' option, a container could
-   get visibility into the 'host' or root container's devpts.
-   
-   To workaround this and have strict isolation, all mounts of devpts,
-   including the mount in the root container, should use the newinstance
-   option.
diff --git a/Documentation/kdump/gdbmacros.txt b/Documentation/kdump/gdbmacros.txt
index 35f6a98..220d0a8 100644
--- a/Documentation/kdump/gdbmacros.txt
+++ b/Documentation/kdump/gdbmacros.txt
@@ -170,21 +170,92 @@
 	address the kernel panicked.
 end
 
+define dump_log_idx
+	set $idx = $arg0
+	if ($argc > 1)
+		set $prev_flags = $arg1
+	else
+		set $prev_flags = 0
+	end
+	set $msg = ((struct printk_log *) (log_buf + $idx))
+	set $prefix = 1
+	set $newline = 1
+	set $log = log_buf + $idx + sizeof(*$msg)
+
+	# prev & LOG_CONT && !(msg->flags & LOG_PREIX)
+	if (($prev_flags & 8) && !($msg->flags & 4))
+		set $prefix = 0
+	end
+
+	# msg->flags & LOG_CONT
+	if ($msg->flags & 8)
+		# (prev & LOG_CONT && !(prev & LOG_NEWLINE))
+		if (($prev_flags & 8) && !($prev_flags & 2))
+			set $prefix = 0
+		end
+		# (!(msg->flags & LOG_NEWLINE))
+		if (!($msg->flags & 2))
+			set $newline = 0
+		end
+	end
+
+	if ($prefix)
+		printf "[%5lu.%06lu] ", $msg->ts_nsec / 1000000000, $msg->ts_nsec % 1000000000
+	end
+	if ($msg->text_len != 0)
+		eval "printf \"%%%d.%ds\", $log", $msg->text_len, $msg->text_len
+	end
+	if ($newline)
+		printf "\n"
+	end
+	if ($msg->dict_len > 0)
+		set $dict = $log + $msg->text_len
+		set $idx = 0
+		set $line = 1
+		while ($idx < $msg->dict_len)
+			if ($line)
+				printf " "
+				set $line = 0
+			end
+			set $c = $dict[$idx]
+			if ($c == '\0')
+				printf "\n"
+				set $line = 1
+			else
+				if ($c < ' ' || $c >= 127 || $c == '\\')
+					printf "\\x%02x", $c
+				else
+					printf "%c", $c
+				end
+			end
+			set $idx = $idx + 1
+		end
+		printf "\n"
+	end
+end
+document dump_log_idx
+	Dump a single log given its index in the log buffer.  The first
+	parameter is the index into log_buf, the second is optional and
+	specified the previous log buffer's flags, used for properly
+	formatting continued lines.
+end
 
 define dmesg
-	set $i = 0
-	set $end_idx = (log_end - 1) & (log_buf_len - 1)
+	set $i = log_first_idx
+	set $end_idx = log_first_idx
+	set $prev_flags = 0
 
-	while ($i < logged_chars)
-		set $idx = (log_end - 1 - logged_chars + $i) & (log_buf_len - 1)
-
-		if ($idx + 100 <= $end_idx) || \
-		   ($end_idx <= $idx && $idx + 100 < log_buf_len)
-			printf "%.100s", &log_buf[$idx]
-			set $i = $i + 100
+	while (1)
+		set $msg = ((struct printk_log *) (log_buf + $i))
+		if ($msg->len == 0)
+			set $i = 0
 		else
-			printf "%c", log_buf[$idx]
-			set $i = $i + 1
+			dump_log_idx $i $prev_flags
+			set $i = $i + $msg->len
+			set $prev_flags = $msg->flags
+		end
+		if ($i == $end_idx)
+			loop_break
 		end
 	end
 end
diff --git a/Documentation/networking/can.txt b/Documentation/networking/can.txt
index d58ff84..aa15b9e 100644
--- a/Documentation/networking/can.txt
+++ b/Documentation/networking/can.txt
@@ -31,6 +31,7 @@
       4.2.4 Broadcast Manager message sequence transmission
       4.2.5 Broadcast Manager receive filter timers
       4.2.6 Broadcast Manager multiplex message receive filter
+      4.2.7 Broadcast Manager CAN FD support
     4.3 connected transport protocols (SOCK_SEQPACKET)
     4.4 unconnected transport protocols (SOCK_DGRAM)
 
@@ -799,7 +800,7 @@
     } mytxmsg;
 
     (..)
-    mytxmsg.nframes = 4;
+    mytxmsg.msg_head.nframes = 4;
     (..)
 
     write(s, &mytxmsg, sizeof(mytxmsg));
@@ -852,6 +853,28 @@
 
     write(s, &msg, sizeof(msg));
 
+  4.2.7 Broadcast Manager CAN FD support
+
+  The programming API of the CAN_BCM depends on struct can_frame which is
+  given as array directly behind the bcm_msg_head structure. To follow this
+  schema for the CAN FD frames a new flag 'CAN_FD_FRAME' in the bcm_msg_head
+  flags indicates that the concatenated CAN frame structures behind the
+  bcm_msg_head are defined as struct canfd_frame.
+
+    struct {
+            struct bcm_msg_head msg_head;
+            struct canfd_frame frame[5];
+    } msg;
+
+    msg.msg_head.opcode  = RX_SETUP;
+    msg.msg_head.can_id  = 0x42;
+    msg.msg_head.flags   = CAN_FD_FRAME;
+    msg.msg_head.nframes = 5;
+    (..)
+
+  When using CAN FD frames for multiplex filtering the MUX mask is still
+  expected in the first 64 bit of the struct canfd_frame data section.
+
   4.3 connected transport protocols (SOCK_SEQPACKET)
   4.4 unconnected transport protocols (SOCK_DGRAM)
 
diff --git a/Documentation/networking/gen_stats.txt b/Documentation/networking/gen_stats.txt
index ff630a8..179b18c 100644
--- a/Documentation/networking/gen_stats.txt
+++ b/Documentation/networking/gen_stats.txt
@@ -21,7 +21,7 @@
 	...
 };
 
-Update statistics:
+Update statistics, in dequeue() methods only, (while owning qdisc->running)
 mystruct->tstats.packet++;
 mystruct->qstats.backlog += skb->pkt_len;
 
diff --git a/Documentation/security/keys.txt b/Documentation/security/keys.txt
index 20d0571..3849814 100644
--- a/Documentation/security/keys.txt
+++ b/Documentation/security/keys.txt
@@ -826,7 +826,8 @@
  (*) Compute a Diffie-Hellman shared secret or public key
 
        long keyctl(KEYCTL_DH_COMPUTE, struct keyctl_dh_params *params,
-		   char *buffer, size_t buflen);
+		   char *buffer, size_t buflen,
+		   void *reserved);
 
      The params struct contains serial numbers for three keys:
 
@@ -843,6 +844,8 @@
      public key.  If the base is the remote public key, the result is
      the shared secret.
 
+     The reserved argument must be set to NULL.
+
      The buffer length must be at least the length of the prime, or zero.
 
      If the buffer length is nonzero, the length of the result is
diff --git a/MAINTAINERS b/MAINTAINERS
index 56934b5..c9544f5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2454,6 +2454,14 @@
 S:	Supported
 F:	drivers/net/ethernet/broadcom/b44.*
 
+BROADCOM B53 ETHERNET SWITCH DRIVER
+M:	Florian Fainelli <f.fainelli@gmail.com>
+L:	netdev@vger.kernel.org
+L:	openwrt-devel@lists.openwrt.org (subscribers-only)
+S:	Supported
+F:	drivers/net/dsa/b53/*
+F:	include/linux/platform_data/b53.h
+
 BROADCOM GENET ETHERNET DRIVER
 M:	Florian Fainelli <f.fainelli@gmail.com>
 L:	netdev@vger.kernel.org
@@ -2805,6 +2813,7 @@
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can.git
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can-next.git
 S:	Maintained
+F:	Documentation/devicetree/bindings/net/can/
 F:	drivers/net/can/
 F:	include/linux/can/dev.h
 F:	include/linux/can/platform/
@@ -3085,6 +3094,7 @@
 L:	linux-clk@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/clk/linux.git
 S:	Maintained
+F:	Documentation/devicetree/bindings/clock/
 F:	drivers/clk/
 X:	drivers/clk/clkdev.c
 F:	include/linux/clk-pr*
@@ -4869,6 +4879,13 @@
 X:	drivers/net/ethernet/freescale/gianfar_ptp.c
 F:	Documentation/devicetree/bindings/net/fsl-tsec-phy.txt
 
+FREESCALE QUICC ENGINE UCC HDLC DRIVER
+M:	Zhao Qiang <qiang.zhao@nxp.com>
+L:	netdev@vger.kernel.org
+L:	linuxppc-dev@lists.ozlabs.org
+S:	Maintained
+F:	drivers/net/wan/fsl_ucc_hdlc*
+
 FREESCALE QUICC ENGINE UCC UART DRIVER
 M:	Timur Tabi <timur@tabi.org>
 L:	linuxppc-dev@lists.ozlabs.org
@@ -8007,6 +8024,7 @@
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/wireless-drivers.git
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/wireless-drivers-next.git
 S:	Maintained
+F:	Documentation/devicetree/bindings/net/wireless/
 F:	drivers/net/wireless/
 
 NETXEN (1/10) GbE SUPPORT
@@ -8944,6 +8962,7 @@
 L:	linux-gpio@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-pinctrl.git
 S:	Maintained
+F:	Documentation/devicetree/bindings/pinctrl/
 F:	drivers/pinctrl/
 F:	include/linux/pinctrl/
 
diff --git a/Makefile b/Makefile
index 0f70de6..8d1301a 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 7
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
 NAME = Psychotic Stoned Sheep
 
 # *DOCUMENTATION*
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 0dcbacf..0d3e59f 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -61,7 +61,7 @@
 	def_bool y
 
 config ARCH_DISCONTIGMEM_ENABLE
-	def_bool y
+	def_bool n
 
 config ARCH_FLATMEM_ENABLE
 	def_bool y
@@ -186,9 +186,6 @@
 config ARC_HAS_COH_CACHES
 	def_bool n
 
-config ARC_HAS_REENTRANT_IRQ_LV2
-	def_bool n
-
 config ARC_MCIP
 	bool "ARConnect Multicore IP (MCIP) Support "
 	depends on ISA_ARCV2
@@ -366,25 +363,10 @@
 if ISA_ARCOMPACT
 
 config ARC_COMPACT_IRQ_LEVELS
-	bool "ARCompact IRQ Priorities: High(2)/Low(1)"
+	bool "Setup Timer IRQ as high Priority"
 	default n
-	# Timer HAS to be high priority, for any other high priority config
-	select ARC_IRQ3_LV2
 	# if SMP, LV2 enabled ONLY if ARC implementation has LV2 re-entrancy
-	depends on !SMP || ARC_HAS_REENTRANT_IRQ_LV2
-
-if ARC_COMPACT_IRQ_LEVELS
-
-config ARC_IRQ3_LV2
-	bool
-
-config ARC_IRQ5_LV2
-	bool
-
-config ARC_IRQ6_LV2
-	bool
-
-endif	#ARC_COMPACT_IRQ_LEVELS
+	depends on !SMP
 
 config ARC_FPU_SAVE_RESTORE
 	bool "Enable FPU state persistence across context switch"
@@ -407,11 +389,6 @@
 	default y
 	depends on !ARC_CANT_LLSC
 
-config ARC_STAR_9000923308
-	bool "Workaround for llock/scond livelock"
-	default n
-	depends on ISA_ARCV2 && SMP && ARC_HAS_LLSC
-
 config ARC_HAS_SWAPE
 	bool "Insn: SWAPE (endian-swap)"
 	default y
@@ -471,7 +448,7 @@
 
 config HIGHMEM
 	bool "High Memory Support"
-	select DISCONTIGMEM
+	select ARCH_DISCONTIGMEM_ENABLE
 	help
 	  With ARC 2G:2G address split, only upper 2G is directly addressable by
 	  kernel. Enable this to potentially allow access to rest of 2G and PAE
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index 02fabef..d4df6be 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -127,7 +127,7 @@
 
 boot		:= arch/arc/boot
 
-#default target for make without any arguements.
+#default target for make without any arguments.
 KBUILD_IMAGE	:= bootpImage
 
 all:	$(KBUILD_IMAGE)
diff --git a/arch/arc/boot/dts/abilis_tb100.dtsi b/arch/arc/boot/dts/abilis_tb100.dtsi
index 3942634..02410b2 100644
--- a/arch/arc/boot/dts/abilis_tb100.dtsi
+++ b/arch/arc/boot/dts/abilis_tb100.dtsi
@@ -23,8 +23,6 @@
 
 
 / {
-	clock-frequency		= <500000000>;	/* 500 MHZ */
-
 	soc100 {
 		bus-frequency	= <166666666>;
 
diff --git a/arch/arc/boot/dts/abilis_tb101.dtsi b/arch/arc/boot/dts/abilis_tb101.dtsi
index b046722..f9e7686 100644
--- a/arch/arc/boot/dts/abilis_tb101.dtsi
+++ b/arch/arc/boot/dts/abilis_tb101.dtsi
@@ -23,8 +23,6 @@
 
 
 / {
-	clock-frequency		= <500000000>;	/* 500 MHZ */
-
 	soc100 {
 		bus-frequency	= <166666666>;
 
diff --git a/arch/arc/boot/dts/axc001.dtsi b/arch/arc/boot/dts/axc001.dtsi
index 3e02f15..6ae2c47 100644
--- a/arch/arc/boot/dts/axc001.dtsi
+++ b/arch/arc/boot/dts/axc001.dtsi
@@ -15,7 +15,6 @@
 
 / {
 	compatible = "snps,arc";
-	clock-frequency = <750000000>;	/* 750 MHZ */
 	#address-cells = <1>;
 	#size-cells = <1>;
 
diff --git a/arch/arc/boot/dts/axc003.dtsi b/arch/arc/boot/dts/axc003.dtsi
index 378e455..14df46f 100644
--- a/arch/arc/boot/dts/axc003.dtsi
+++ b/arch/arc/boot/dts/axc003.dtsi
@@ -14,7 +14,6 @@
 
 / {
 	compatible = "snps,arc";
-	clock-frequency = <90000000>;
 	#address-cells = <1>;
 	#size-cells = <1>;
 
diff --git a/arch/arc/boot/dts/axc003_idu.dtsi b/arch/arc/boot/dts/axc003_idu.dtsi
index 64c94b2..3d6cfa3 100644
--- a/arch/arc/boot/dts/axc003_idu.dtsi
+++ b/arch/arc/boot/dts/axc003_idu.dtsi
@@ -14,7 +14,6 @@
 
 / {
 	compatible = "snps,arc";
-	clock-frequency = <90000000>;
 	#address-cells = <1>;
 	#size-cells = <1>;
 
diff --git a/arch/arc/boot/dts/eznps.dts b/arch/arc/boot/dts/eznps.dts
index b89f6c3..1e0d225 100644
--- a/arch/arc/boot/dts/eznps.dts
+++ b/arch/arc/boot/dts/eznps.dts
@@ -18,7 +18,6 @@
 
 / {
 	compatible = "ezchip,arc-nps";
-	clock-frequency = <83333333>;	/* 83.333333 MHZ */
 	#address-cells = <1>;
 	#size-cells = <1>;
 	interrupt-parent = <&intc>;
diff --git a/arch/arc/boot/dts/nsim_700.dts b/arch/arc/boot/dts/nsim_700.dts
index 5d5e373..6397051 100644
--- a/arch/arc/boot/dts/nsim_700.dts
+++ b/arch/arc/boot/dts/nsim_700.dts
@@ -11,7 +11,6 @@
 
 / {
 	compatible = "snps,nsim";
-	clock-frequency = <80000000>;	/* 80 MHZ */
 	#address-cells = <1>;
 	#size-cells = <1>;
 	interrupt-parent = <&core_intc>;
diff --git a/arch/arc/boot/dts/nsimosci.dts b/arch/arc/boot/dts/nsimosci.dts
index b5b060a..763d66c 100644
--- a/arch/arc/boot/dts/nsimosci.dts
+++ b/arch/arc/boot/dts/nsimosci.dts
@@ -11,7 +11,6 @@
 
 / {
 	compatible = "snps,nsimosci";
-	clock-frequency = <20000000>;	/* 20 MHZ */
 	#address-cells = <1>;
 	#size-cells = <1>;
 	interrupt-parent = <&core_intc>;
diff --git a/arch/arc/boot/dts/nsimosci_hs.dts b/arch/arc/boot/dts/nsimosci_hs.dts
index 325e730..4eb97c5 100644
--- a/arch/arc/boot/dts/nsimosci_hs.dts
+++ b/arch/arc/boot/dts/nsimosci_hs.dts
@@ -11,7 +11,6 @@
 
 / {
 	compatible = "snps,nsimosci_hs";
-	clock-frequency = <20000000>;	/* 20 MHZ */
 	#address-cells = <1>;
 	#size-cells = <1>;
 	interrupt-parent = <&core_intc>;
diff --git a/arch/arc/boot/dts/nsimosci_hs_idu.dts b/arch/arc/boot/dts/nsimosci_hs_idu.dts
index ee03d71..853f897 100644
--- a/arch/arc/boot/dts/nsimosci_hs_idu.dts
+++ b/arch/arc/boot/dts/nsimosci_hs_idu.dts
@@ -11,7 +11,6 @@
 
 / {
 	compatible = "snps,nsimosci_hs";
-	clock-frequency = <5000000>;	/* 5 MHZ */
 	#address-cells = <1>;
 	#size-cells = <1>;
 	interrupt-parent = <&core_intc>;
diff --git a/arch/arc/boot/dts/skeleton.dtsi b/arch/arc/boot/dts/skeleton.dtsi
index 3a10cc6..65808fe 100644
--- a/arch/arc/boot/dts/skeleton.dtsi
+++ b/arch/arc/boot/dts/skeleton.dtsi
@@ -13,7 +13,6 @@
 
 / {
 	compatible = "snps,arc";
-	clock-frequency = <80000000>;	/* 80 MHZ */
 	#address-cells = <1>;
 	#size-cells = <1>;
 	chosen { };
diff --git a/arch/arc/boot/dts/skeleton_hs.dtsi b/arch/arc/boot/dts/skeleton_hs.dtsi
index 71fd308..2dfe803 100644
--- a/arch/arc/boot/dts/skeleton_hs.dtsi
+++ b/arch/arc/boot/dts/skeleton_hs.dtsi
@@ -8,7 +8,6 @@
 
 / {
 	compatible = "snps,arc";
-	clock-frequency = <80000000>;	/* 80 MHZ */
 	#address-cells = <1>;
 	#size-cells = <1>;
 	chosen { };
diff --git a/arch/arc/boot/dts/skeleton_hs_idu.dtsi b/arch/arc/boot/dts/skeleton_hs_idu.dtsi
index d1cb25a..4c11079 100644
--- a/arch/arc/boot/dts/skeleton_hs_idu.dtsi
+++ b/arch/arc/boot/dts/skeleton_hs_idu.dtsi
@@ -8,7 +8,6 @@
 
 / {
 	compatible = "snps,arc";
-	clock-frequency = <80000000>;	/* 80 MHZ */
 	#address-cells = <1>;
 	#size-cells = <1>;
 	chosen { };
diff --git a/arch/arc/boot/dts/vdk_axc003.dtsi b/arch/arc/boot/dts/vdk_axc003.dtsi
index ad4ee43..0fd6ba9 100644
--- a/arch/arc/boot/dts/vdk_axc003.dtsi
+++ b/arch/arc/boot/dts/vdk_axc003.dtsi
@@ -14,7 +14,6 @@
 
 / {
 	compatible = "snps,arc";
-	clock-frequency = <50000000>;
 	#address-cells = <1>;
 	#size-cells = <1>;
 
diff --git a/arch/arc/boot/dts/vdk_axc003_idu.dtsi b/arch/arc/boot/dts/vdk_axc003_idu.dtsi
index a3cb626..82214cd 100644
--- a/arch/arc/boot/dts/vdk_axc003_idu.dtsi
+++ b/arch/arc/boot/dts/vdk_axc003_idu.dtsi
@@ -15,7 +15,6 @@
 
 / {
 	compatible = "snps,arc";
-	clock-frequency = <50000000>;
 	#address-cells = <1>;
 	#size-cells = <1>;
 
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 5f3dcbb..dd68399 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -25,50 +25,17 @@
 
 #define atomic_set(v, i) WRITE_ONCE(((v)->counter), (i))
 
-#ifdef CONFIG_ARC_STAR_9000923308
-
-#define SCOND_FAIL_RETRY_VAR_DEF						\
-	unsigned int delay = 1, tmp;						\
-
-#define SCOND_FAIL_RETRY_ASM							\
-	"	bz	4f			\n"				\
-	"   ; --- scond fail delay ---		\n"				\
-	"	mov	%[tmp], %[delay]	\n"	/* tmp = delay */	\
-	"2: 	brne.d	%[tmp], 0, 2b		\n"	/* while (tmp != 0) */	\
-	"	sub	%[tmp], %[tmp], 1	\n"	/* tmp-- */		\
-	"	rol	%[delay], %[delay]	\n"	/* delay *= 2 */	\
-	"	b	1b			\n"	/* start over */	\
-	"4: ; --- success ---			\n"				\
-
-#define SCOND_FAIL_RETRY_VARS							\
-	  ,[delay] "+&r" (delay),[tmp] "=&r"	(tmp)				\
-
-#else	/* !CONFIG_ARC_STAR_9000923308 */
-
-#define SCOND_FAIL_RETRY_VAR_DEF
-
-#define SCOND_FAIL_RETRY_ASM							\
-	"	bnz     1b			\n"				\
-
-#define SCOND_FAIL_RETRY_VARS
-
-#endif
-
 #define ATOMIC_OP(op, c_op, asm_op)					\
 static inline void atomic_##op(int i, atomic_t *v)			\
 {									\
-	unsigned int val;				                \
-	SCOND_FAIL_RETRY_VAR_DEF                                        \
+	unsigned int val;						\
 									\
 	__asm__ __volatile__(						\
 	"1:	llock   %[val], [%[ctr]]		\n"		\
 	"	" #asm_op " %[val], %[val], %[i]	\n"		\
 	"	scond   %[val], [%[ctr]]		\n"		\
-	"						\n"		\
-	SCOND_FAIL_RETRY_ASM						\
-									\
+	"	bnz     1b				\n"		\
 	: [val]	"=&r"	(val) /* Early clobber to prevent reg reuse */	\
-	  SCOND_FAIL_RETRY_VARS						\
 	: [ctr]	"r"	(&v->counter), /* Not "m": llock only supports reg direct addr mode */	\
 	  [i]	"ir"	(i)						\
 	: "cc");							\
@@ -77,8 +44,7 @@
 #define ATOMIC_OP_RETURN(op, c_op, asm_op)				\
 static inline int atomic_##op##_return(int i, atomic_t *v)		\
 {									\
-	unsigned int val;				                \
-	SCOND_FAIL_RETRY_VAR_DEF                                        \
+	unsigned int val;						\
 									\
 	/*								\
 	 * Explicit full memory barrier needed before/after as		\
@@ -90,11 +56,8 @@
 	"1:	llock   %[val], [%[ctr]]		\n"		\
 	"	" #asm_op " %[val], %[val], %[i]	\n"		\
 	"	scond   %[val], [%[ctr]]		\n"		\
-	"						\n"		\
-	SCOND_FAIL_RETRY_ASM						\
-									\
+	"	bnz     1b				\n"		\
 	: [val]	"=&r"	(val)						\
-	  SCOND_FAIL_RETRY_VARS						\
 	: [ctr]	"r"	(&v->counter),					\
 	  [i]	"ir"	(i)						\
 	: "cc");							\
diff --git a/arch/arc/include/asm/entry-compact.h b/arch/arc/include/asm/entry-compact.h
index e0e1faf..14c310f 100644
--- a/arch/arc/include/asm/entry-compact.h
+++ b/arch/arc/include/asm/entry-compact.h
@@ -76,8 +76,8 @@
 	 * We need to be a bit more cautious here. What if a kernel bug in
 	 * L1 ISR, caused SP to go whaco (some small value which looks like
 	 * USER stk) and then we take L2 ISR.
-	 * Above brlo alone would treat it as a valid L1-L2 sceanrio
-	 * instead of shouting alound
+	 * Above brlo alone would treat it as a valid L1-L2 scenario
+	 * instead of shouting around
 	 * The only feasible way is to make sure this L2 happened in
 	 * L1 prelogue ONLY i.e. ilink2 is less than a pre-set marker in
 	 * L1 ISR before it switches stack
diff --git a/arch/arc/include/asm/mmu_context.h b/arch/arc/include/asm/mmu_context.h
index 1fd467e..b0b87f2 100644
--- a/arch/arc/include/asm/mmu_context.h
+++ b/arch/arc/include/asm/mmu_context.h
@@ -83,7 +83,7 @@
 		local_flush_tlb_all();
 
 		/*
-		 * Above checke for rollover of 8 bit ASID in 32 bit container.
+		 * Above check for rollover of 8 bit ASID in 32 bit container.
 		 * If the container itself wrapped around, set it to a non zero
 		 * "generation" to distinguish from no context
 		 */
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index 034bbdc..858f98e 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -47,7 +47,7 @@
  * Page Tables are purely for Linux VM's consumption and the bits below are
  * suited to that (uniqueness). Hence some are not implemented in the TLB and
  * some have different value in TLB.
- * e.g. MMU v2: K_READ bit is 8 and so is GLOBAL (possible becoz they live in
+ * e.g. MMU v2: K_READ bit is 8 and so is GLOBAL (possible because they live in
  *      seperate PD0 and PD1, which combined forms a translation entry)
  *      while for PTE perspective, they are 8 and 9 respectively
  * with MMU v3: Most bits (except SHARED) represent the exact hardware pos
diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h
index f9048994..16b630f 100644
--- a/arch/arc/include/asm/processor.h
+++ b/arch/arc/include/asm/processor.h
@@ -78,7 +78,7 @@
 #define KSTK_ESP(tsk)   (task_pt_regs(tsk)->sp)
 
 /*
- * Where abouts of Task's sp, fp, blink when it was last seen in kernel mode.
+ * Where about of Task's sp, fp, blink when it was last seen in kernel mode.
  * Look in process.c for details of kernel stack layout
  */
 #define TSK_K_ESP(tsk)		(tsk->thread.ksp)
diff --git a/arch/arc/include/asm/smp.h b/arch/arc/include/asm/smp.h
index 9913804..89fdd1b 100644
--- a/arch/arc/include/asm/smp.h
+++ b/arch/arc/include/asm/smp.h
@@ -86,7 +86,7 @@
  * (1) These insn were introduced only in 4.10 release. So for older released
  *	support needed.
  *
- * (2) In a SMP setup, the LLOCK/SCOND atomiticity across CPUs needs to be
+ * (2) In a SMP setup, the LLOCK/SCOND atomicity across CPUs needs to be
  *	gaurantted by the platform (not something which core handles).
  *	Assuming a platform won't, SMP Linux needs to use spinlocks + local IRQ
  *	disabling for atomicity.
diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h
index 800e7c4..cded4a9 100644
--- a/arch/arc/include/asm/spinlock.h
+++ b/arch/arc/include/asm/spinlock.h
@@ -20,11 +20,6 @@
 
 #ifdef CONFIG_ARC_HAS_LLSC
 
-/*
- * A normal LLOCK/SCOND based system, w/o need for livelock workaround
- */
-#ifndef CONFIG_ARC_STAR_9000923308
-
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
 	unsigned int val;
@@ -238,293 +233,6 @@
 	smp_mb();
 }
 
-#else	/* CONFIG_ARC_STAR_9000923308 */
-
-/*
- * HS38x4 could get into a LLOCK/SCOND livelock in case of multiple overlapping
- * coherency transactions in the SCU. The exclusive line state keeps rotating
- * among contenting cores leading to a never ending cycle. So break the cycle
- * by deferring the retry of failed exclusive access (SCOND). The actual delay
- * needed is function of number of contending cores as well as the unrelated
- * coherency traffic from other cores. To keep the code simple, start off with
- * small delay of 1 which would suffice most cases and in case of contention
- * double the delay. Eventually the delay is sufficient such that the coherency
- * pipeline is drained, thus a subsequent exclusive access would succeed.
- */
-
-#define SCOND_FAIL_RETRY_VAR_DEF						\
-	unsigned int delay, tmp;						\
-
-#define SCOND_FAIL_RETRY_ASM							\
-	"   ; --- scond fail delay ---		\n"				\
-	"	mov	%[tmp], %[delay]	\n"	/* tmp = delay */	\
-	"2: 	brne.d	%[tmp], 0, 2b		\n"	/* while (tmp != 0) */	\
-	"	sub	%[tmp], %[tmp], 1	\n"	/* tmp-- */		\
-	"	rol	%[delay], %[delay]	\n"	/* delay *= 2 */	\
-	"	b	1b			\n"	/* start over */	\
-	"					\n"				\
-	"4: ; --- done ---			\n"				\
-
-#define SCOND_FAIL_RETRY_VARS							\
-	  ,[delay] "=&r" (delay), [tmp] "=&r"	(tmp)				\
-
-static inline void arch_spin_lock(arch_spinlock_t *lock)
-{
-	unsigned int val;
-	SCOND_FAIL_RETRY_VAR_DEF;
-
-	smp_mb();
-
-	__asm__ __volatile__(
-	"0:	mov	%[delay], 1		\n"
-	"1:	llock	%[val], [%[slock]]	\n"
-	"	breq	%[val], %[LOCKED], 0b	\n"	/* spin while LOCKED */
-	"	scond	%[LOCKED], [%[slock]]	\n"	/* acquire */
-	"	bz	4f			\n"	/* done */
-	"					\n"
-	SCOND_FAIL_RETRY_ASM
-
-	: [val]		"=&r"	(val)
-	  SCOND_FAIL_RETRY_VARS
-	: [slock]	"r"	(&(lock->slock)),
-	  [LOCKED]	"r"	(__ARCH_SPIN_LOCK_LOCKED__)
-	: "memory", "cc");
-
-	smp_mb();
-}
-
-/* 1 - lock taken successfully */
-static inline int arch_spin_trylock(arch_spinlock_t *lock)
-{
-	unsigned int val, got_it = 0;
-	SCOND_FAIL_RETRY_VAR_DEF;
-
-	smp_mb();
-
-	__asm__ __volatile__(
-	"0:	mov	%[delay], 1		\n"
-	"1:	llock	%[val], [%[slock]]	\n"
-	"	breq	%[val], %[LOCKED], 4f	\n"	/* already LOCKED, just bail */
-	"	scond	%[LOCKED], [%[slock]]	\n"	/* acquire */
-	"	bz.d	4f			\n"
-	"	mov.z	%[got_it], 1		\n"	/* got it */
-	"					\n"
-	SCOND_FAIL_RETRY_ASM
-
-	: [val]		"=&r"	(val),
-	  [got_it]	"+&r"	(got_it)
-	  SCOND_FAIL_RETRY_VARS
-	: [slock]	"r"	(&(lock->slock)),
-	  [LOCKED]	"r"	(__ARCH_SPIN_LOCK_LOCKED__)
-	: "memory", "cc");
-
-	smp_mb();
-
-	return got_it;
-}
-
-static inline void arch_spin_unlock(arch_spinlock_t *lock)
-{
-	smp_mb();
-
-	lock->slock = __ARCH_SPIN_LOCK_UNLOCKED__;
-
-	smp_mb();
-}
-
-/*
- * Read-write spinlocks, allowing multiple readers but only one writer.
- * Unfair locking as Writers could be starved indefinitely by Reader(s)
- */
-
-static inline void arch_read_lock(arch_rwlock_t *rw)
-{
-	unsigned int val;
-	SCOND_FAIL_RETRY_VAR_DEF;
-
-	smp_mb();
-
-	/*
-	 * zero means writer holds the lock exclusively, deny Reader.
-	 * Otherwise grant lock to first/subseq reader
-	 *
-	 * 	if (rw->counter > 0) {
-	 *		rw->counter--;
-	 *		ret = 1;
-	 *	}
-	 */
-
-	__asm__ __volatile__(
-	"0:	mov	%[delay], 1		\n"
-	"1:	llock	%[val], [%[rwlock]]	\n"
-	"	brls	%[val], %[WR_LOCKED], 0b\n"	/* <= 0: spin while write locked */
-	"	sub	%[val], %[val], 1	\n"	/* reader lock */
-	"	scond	%[val], [%[rwlock]]	\n"
-	"	bz	4f			\n"	/* done */
-	"					\n"
-	SCOND_FAIL_RETRY_ASM
-
-	: [val]		"=&r"	(val)
-	  SCOND_FAIL_RETRY_VARS
-	: [rwlock]	"r"	(&(rw->counter)),
-	  [WR_LOCKED]	"ir"	(0)
-	: "memory", "cc");
-
-	smp_mb();
-}
-
-/* 1 - lock taken successfully */
-static inline int arch_read_trylock(arch_rwlock_t *rw)
-{
-	unsigned int val, got_it = 0;
-	SCOND_FAIL_RETRY_VAR_DEF;
-
-	smp_mb();
-
-	__asm__ __volatile__(
-	"0:	mov	%[delay], 1		\n"
-	"1:	llock	%[val], [%[rwlock]]	\n"
-	"	brls	%[val], %[WR_LOCKED], 4f\n"	/* <= 0: already write locked, bail */
-	"	sub	%[val], %[val], 1	\n"	/* counter-- */
-	"	scond	%[val], [%[rwlock]]	\n"
-	"	bz.d	4f			\n"
-	"	mov.z	%[got_it], 1		\n"	/* got it */
-	"					\n"
-	SCOND_FAIL_RETRY_ASM
-
-	: [val]		"=&r"	(val),
-	  [got_it]	"+&r"	(got_it)
-	  SCOND_FAIL_RETRY_VARS
-	: [rwlock]	"r"	(&(rw->counter)),
-	  [WR_LOCKED]	"ir"	(0)
-	: "memory", "cc");
-
-	smp_mb();
-
-	return got_it;
-}
-
-static inline void arch_write_lock(arch_rwlock_t *rw)
-{
-	unsigned int val;
-	SCOND_FAIL_RETRY_VAR_DEF;
-
-	smp_mb();
-
-	/*
-	 * If reader(s) hold lock (lock < __ARCH_RW_LOCK_UNLOCKED__),
-	 * deny writer. Otherwise if unlocked grant to writer
-	 * Hence the claim that Linux rwlocks are unfair to writers.
-	 * (can be starved for an indefinite time by readers).
-	 *
-	 *	if (rw->counter == __ARCH_RW_LOCK_UNLOCKED__) {
-	 *		rw->counter = 0;
-	 *		ret = 1;
-	 *	}
-	 */
-
-	__asm__ __volatile__(
-	"0:	mov	%[delay], 1		\n"
-	"1:	llock	%[val], [%[rwlock]]	\n"
-	"	brne	%[val], %[UNLOCKED], 0b	\n"	/* while !UNLOCKED spin */
-	"	mov	%[val], %[WR_LOCKED]	\n"
-	"	scond	%[val], [%[rwlock]]	\n"
-	"	bz	4f			\n"
-	"					\n"
-	SCOND_FAIL_RETRY_ASM
-
-	: [val]		"=&r"	(val)
-	  SCOND_FAIL_RETRY_VARS
-	: [rwlock]	"r"	(&(rw->counter)),
-	  [UNLOCKED]	"ir"	(__ARCH_RW_LOCK_UNLOCKED__),
-	  [WR_LOCKED]	"ir"	(0)
-	: "memory", "cc");
-
-	smp_mb();
-}
-
-/* 1 - lock taken successfully */
-static inline int arch_write_trylock(arch_rwlock_t *rw)
-{
-	unsigned int val, got_it = 0;
-	SCOND_FAIL_RETRY_VAR_DEF;
-
-	smp_mb();
-
-	__asm__ __volatile__(
-	"0:	mov	%[delay], 1		\n"
-	"1:	llock	%[val], [%[rwlock]]	\n"
-	"	brne	%[val], %[UNLOCKED], 4f	\n"	/* !UNLOCKED, bail */
-	"	mov	%[val], %[WR_LOCKED]	\n"
-	"	scond	%[val], [%[rwlock]]	\n"
-	"	bz.d	4f			\n"
-	"	mov.z	%[got_it], 1		\n"	/* got it */
-	"					\n"
-	SCOND_FAIL_RETRY_ASM
-
-	: [val]		"=&r"	(val),
-	  [got_it]	"+&r"	(got_it)
-	  SCOND_FAIL_RETRY_VARS
-	: [rwlock]	"r"	(&(rw->counter)),
-	  [UNLOCKED]	"ir"	(__ARCH_RW_LOCK_UNLOCKED__),
-	  [WR_LOCKED]	"ir"	(0)
-	: "memory", "cc");
-
-	smp_mb();
-
-	return got_it;
-}
-
-static inline void arch_read_unlock(arch_rwlock_t *rw)
-{
-	unsigned int val;
-
-	smp_mb();
-
-	/*
-	 * rw->counter++;
-	 */
-	__asm__ __volatile__(
-	"1:	llock	%[val], [%[rwlock]]	\n"
-	"	add	%[val], %[val], 1	\n"
-	"	scond	%[val], [%[rwlock]]	\n"
-	"	bnz	1b			\n"
-	"					\n"
-	: [val]		"=&r"	(val)
-	: [rwlock]	"r"	(&(rw->counter))
-	: "memory", "cc");
-
-	smp_mb();
-}
-
-static inline void arch_write_unlock(arch_rwlock_t *rw)
-{
-	unsigned int val;
-
-	smp_mb();
-
-	/*
-	 * rw->counter = __ARCH_RW_LOCK_UNLOCKED__;
-	 */
-	__asm__ __volatile__(
-	"1:	llock	%[val], [%[rwlock]]	\n"
-	"	scond	%[UNLOCKED], [%[rwlock]]\n"
-	"	bnz	1b			\n"
-	"					\n"
-	: [val]		"=&r"	(val)
-	: [rwlock]	"r"	(&(rw->counter)),
-	  [UNLOCKED]	"r"	(__ARCH_RW_LOCK_UNLOCKED__)
-	: "memory", "cc");
-
-	smp_mb();
-}
-
-#undef SCOND_FAIL_RETRY_VAR_DEF
-#undef SCOND_FAIL_RETRY_ASM
-#undef SCOND_FAIL_RETRY_VARS
-
-#endif	/* CONFIG_ARC_STAR_9000923308 */
-
 #else	/* !CONFIG_ARC_HAS_LLSC */
 
 static inline void arch_spin_lock(arch_spinlock_t *lock)
diff --git a/arch/arc/include/asm/thread_info.h b/arch/arc/include/asm/thread_info.h
index 3af6745..2d79e52 100644
--- a/arch/arc/include/asm/thread_info.h
+++ b/arch/arc/include/asm/thread_info.h
@@ -103,7 +103,7 @@
 
 /*
  * _TIF_ALLWORK_MASK includes SYSCALL_TRACE, but we don't need it.
- * SYSCALL_TRACE is anways seperately/unconditionally tested right after a
+ * SYSCALL_TRACE is anyway seperately/unconditionally tested right after a
  * syscall, so all that reamins to be tested is _TIF_WORK_MASK
  */
 
diff --git a/arch/arc/include/asm/uaccess.h b/arch/arc/include/asm/uaccess.h
index d1da603..a78d567 100644
--- a/arch/arc/include/asm/uaccess.h
+++ b/arch/arc/include/asm/uaccess.h
@@ -32,7 +32,7 @@
 #define __kernel_ok		(segment_eq(get_fs(), KERNEL_DS))
 
 /*
- * Algorthmically, for __user_ok() we want do:
+ * Algorithmically, for __user_ok() we want do:
  * 	(start < TASK_SIZE) && (start+len < TASK_SIZE)
  * where TASK_SIZE could either be retrieved from thread_info->addr_limit or
  * emitted directly in code.
diff --git a/arch/arc/include/uapi/asm/swab.h b/arch/arc/include/uapi/asm/swab.h
index 095599a..71f3918 100644
--- a/arch/arc/include/uapi/asm/swab.h
+++ b/arch/arc/include/uapi/asm/swab.h
@@ -74,7 +74,7 @@
 	__tmp ^ __in;						\
 })
 
-#elif (ARC_BSWAP_TYPE == 2)	/* Custom single cycle bwap instruction */
+#elif (ARC_BSWAP_TYPE == 2)	/* Custom single cycle bswap instruction */
 
 #define __arch_swab32(x)						\
 ({									\
diff --git a/arch/arc/kernel/entry-compact.S b/arch/arc/kernel/entry-compact.S
index 0cb0aba..98812c1 100644
--- a/arch/arc/kernel/entry-compact.S
+++ b/arch/arc/kernel/entry-compact.S
@@ -91,27 +91,13 @@
 VECTOR   instr_service           ; 0x10, Instrn Error   (0x2)
 
 ; ******************** Device ISRs **********************
-#ifdef CONFIG_ARC_IRQ3_LV2
+#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS
 VECTOR   handle_interrupt_level2
 #else
 VECTOR   handle_interrupt_level1
 #endif
 
-VECTOR   handle_interrupt_level1
-
-#ifdef CONFIG_ARC_IRQ5_LV2
-VECTOR   handle_interrupt_level2
-#else
-VECTOR   handle_interrupt_level1
-#endif
-
-#ifdef CONFIG_ARC_IRQ6_LV2
-VECTOR   handle_interrupt_level2
-#else
-VECTOR   handle_interrupt_level1
-#endif
-
-.rept   25
+.rept   28
 VECTOR   handle_interrupt_level1 ; Other devices
 .endr
 
diff --git a/arch/arc/kernel/intc-compact.c b/arch/arc/kernel/intc-compact.c
index c5cceca..ce9deb9 100644
--- a/arch/arc/kernel/intc-compact.c
+++ b/arch/arc/kernel/intc-compact.c
@@ -28,10 +28,8 @@
 {
 	int level_mask = 0;
 
-       /* setup any high priority Interrupts (Level2 in ARCompact jargon) */
-	level_mask |= IS_ENABLED(CONFIG_ARC_IRQ3_LV2) << 3;
-	level_mask |= IS_ENABLED(CONFIG_ARC_IRQ5_LV2) << 5;
-	level_mask |= IS_ENABLED(CONFIG_ARC_IRQ6_LV2) << 6;
+       /* Is timer high priority Interrupt (Level2 in ARCompact jargon) */
+	level_mask |= IS_ENABLED(CONFIG_ARC_COMPACT_IRQ_LEVELS) << TIMER0_IRQ;
 
 	/*
 	 * Write to register, even if no LV2 IRQs configured to reset it
diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c
index 6fd4802..08f03d9 100644
--- a/arch/arc/kernel/perf_event.c
+++ b/arch/arc/kernel/perf_event.c
@@ -108,7 +108,7 @@
 	int64_t delta = new_raw_count - prev_raw_count;
 
 	/*
-	 * We don't afaraid of hwc->prev_count changing beneath our feet
+	 * We aren't afraid of hwc->prev_count changing beneath our feet
 	 * because there's no way for us to re-enter this function anytime.
 	 */
 	local64_set(&hwc->prev_count, new_raw_count);
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index f63b8bf..2ee7a4d 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -392,7 +392,7 @@
 		/*
 		 * If we are here, it is established that @uboot_arg didn't
 		 * point to DT blob. Instead if u-boot says it is cmdline,
-		 * Appent to embedded DT cmdline.
+		 * append to embedded DT cmdline.
 		 * setup_machine_fdt() would have populated @boot_command_line
 		 */
 		if (uboot_tag == 1) {
diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c
index 004b7f0..6cb3736 100644
--- a/arch/arc/kernel/signal.c
+++ b/arch/arc/kernel/signal.c
@@ -34,7 +34,7 @@
  *  -ViXS were still seeing crashes when using insmod to load drivers.
  *   It turned out that the code to change Execute permssions for TLB entries
  *   of user was not guarded for interrupts (mod_tlb_permission)
- *   This was cauing TLB entries to be overwritten on unrelated indexes
+ *   This was causing TLB entries to be overwritten on unrelated indexes
  *
  * Vineetg: July 15th 2008: Bug #94183
  *  -Exception happens in Delay slot of a JMP, and before user space resumes,
diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c
index a6f91e8..934150e 100644
--- a/arch/arc/kernel/troubleshoot.c
+++ b/arch/arc/kernel/troubleshoot.c
@@ -276,7 +276,7 @@
 	return 0;
 }
 
-/* called on user read(): display the couters */
+/* called on user read(): display the counters */
 static ssize_t tlb_stats_output(struct file *file,	/* file descriptor */
 				char __user *user_buf,	/* user buffer */
 				size_t len,		/* length of buffer */
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index 9e5eddb..5a294b2 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -215,7 +215,7 @@
  * ------------------
  * This ver of MMU supports variable page sizes (1k-16k): although Linux will
  * only support 8k (default), 16k and 4k.
- * However from hardware perspective, smaller page sizes aggrevate aliasing
+ * However from hardware perspective, smaller page sizes aggravate aliasing
  * meaning more vaddr bits needed to disambiguate the cache-line-op ;
  * the existing scheme of piggybacking won't work for certain configurations.
  * Two new registers IC_PTAG and DC_PTAG inttoduced.
@@ -302,7 +302,7 @@
 
 	/*
 	 * This is technically for MMU v4, using the MMU v3 programming model
-	 * Special work for HS38 aliasing I-cache configuratino with PAE40
+	 * Special work for HS38 aliasing I-cache configuration with PAE40
 	 *   - upper 8 bits of paddr need to be written into PTAG_HI
 	 *   - (and needs to be written before the lower 32 bits)
 	 * Note that PTAG_HI is hoisted outside the line loop
@@ -936,7 +936,7 @@
 			      ic->ver, CONFIG_ARC_MMU_VER);
 
 		/*
-		 * In MMU v4 (HS38x) the alising icache config uses IVIL/PTAG
+		 * In MMU v4 (HS38x) the aliasing icache config uses IVIL/PTAG
 		 * pair to provide vaddr/paddr respectively, just as in MMU v3
 		 */
 		if (is_isa_arcv2() && ic->alias)
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index 8c8e36f..73d7e4c 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -10,7 +10,7 @@
  * DMA Coherent API Notes
  *
  * I/O is inherently non-coherent on ARC. So a coherent DMA buffer is
- * implemented by accessintg it using a kernel virtual address, with
+ * implemented by accessing it using a kernel virtual address, with
  * Cache bit off in the TLB entry.
  *
  * The default DMA address == Phy address which is 0x8000_0000 based.
diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi
index 52be48b..702126f 100644
--- a/arch/arm/boot/dts/am33xx.dtsi
+++ b/arch/arm/boot/dts/am33xx.dtsi
@@ -766,7 +766,6 @@
 			ale_entries = <1024>;
 			bd_ram_size = <0x2000>;
 			no_bd_ram = <0>;
-			rx_descs = <64>;
 			mac_control = <0x20>;
 			slaves = <2>;
 			active_slave = <0>;
diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi
index 12fcde4..a10fa7f 100644
--- a/arch/arm/boot/dts/am4372.dtsi
+++ b/arch/arm/boot/dts/am4372.dtsi
@@ -626,7 +626,6 @@
 			ale_entries = <1024>;
 			bd_ram_size = <0x2000>;
 			no_bd_ram = <0>;
-			rx_descs = <64>;
 			mac_control = <0x20>;
 			slaves = <2>;
 			active_slave = <0>;
diff --git a/arch/arm/boot/dts/dm814x.dtsi b/arch/arm/boot/dts/dm814x.dtsi
index d4537dc..f23cae0c 100644
--- a/arch/arm/boot/dts/dm814x.dtsi
+++ b/arch/arm/boot/dts/dm814x.dtsi
@@ -509,7 +509,6 @@
 			ale_entries = <1024>;
 			bd_ram_size = <0x2000>;
 			no_bd_ram = <0>;
-			rx_descs = <64>;
 			mac_control = <0x20>;
 			slaves = <2>;
 			active_slave = <0>;
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index e007401..b7ddc64 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -1626,7 +1626,6 @@
 			ale_entries = <1024>;
 			bd_ram_size = <0x2000>;
 			no_bd_ram = <0>;
-			rx_descs = <64>;
 			mac_control = <0x20>;
 			slaves = <2>;
 			active_slave = <0>;
diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi
index 3b44ef3..3ebee53 100644
--- a/arch/arm/boot/dts/rk3288.dtsi
+++ b/arch/arm/boot/dts/rk3288.dtsi
@@ -539,8 +539,9 @@
 	gmac: ethernet@ff290000 {
 		compatible = "rockchip,rk3288-gmac";
 		reg = <0xff290000 0x10000>;
-		interrupts = <GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>;
-		interrupt-names = "macirq";
+		interrupts = <GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>,
+				<GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "macirq", "eth_wake_irq";
 		rockchip,grf = <&grf>;
 		clocks = <&cru SCLK_MAC>,
 			<&cru SCLK_MAC_RX>, <&cru SCLK_MAC_TX>,
diff --git a/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts b/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts
index 6c60b7f..5c1fcab 100644
--- a/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts
+++ b/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts
@@ -85,18 +85,193 @@
 			reg = <1>;
 			#address-cells = <1>;
 			#size-cells = <0>;
+
+			switch0: switch0@0 {
+				compatible = "marvell,mv88e6085";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				reg = <0>;
+				dsa,member = <0 0>;
+
+				ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					port@0 {
+						reg = <0>;
+						label = "lan0";
+					};
+
+					port@1 {
+						reg = <1>;
+						label = "lan1";
+					};
+
+					port@2 {
+						reg = <2>;
+						label = "lan2";
+					};
+
+					switch0port5: port@5 {
+						reg = <5>;
+						label = "dsa";
+						phy-mode = "rgmii-txid";
+						link = <&switch1port6
+							&switch2port9>;
+						fixed-link {
+							speed = <1000>;
+							full-duplex;
+						};
+					};
+
+					port@6 {
+						reg = <6>;
+						label = "cpu";
+						ethernet = <&fec1>;
+						fixed-link {
+							speed = <100>;
+							full-duplex;
+						};
+					};
+				};
+			};
 		};
 
 		mdio_mux_2: mdio@2 {
 			reg = <2>;
 			#address-cells = <1>;
 			#size-cells = <0>;
+
+			switch1: switch1@0 {
+				compatible = "marvell,mv88e6085";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				reg = <0>;
+				dsa,member = <0 1>;
+
+				ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					port@0 {
+						reg = <0>;
+						label = "lan3";
+						phy-handle = <&switch1phy0>;
+					};
+
+					port@1 {
+						reg = <1>;
+						label = "lan4";
+						phy-handle = <&switch1phy1>;
+					};
+
+					port@2 {
+						reg = <2>;
+						label = "lan5";
+						phy-handle = <&switch1phy2>;
+					};
+
+					switch1port5: port@5 {
+						reg = <5>;
+						label = "dsa";
+						link = <&switch2port9>;
+						phy-mode = "rgmii-txid";
+						fixed-link {
+							speed = <1000>;
+							full-duplex;
+						};
+					};
+
+					switch1port6: port@6 {
+						reg = <6>;
+						label = "dsa";
+						phy-mode = "rgmii-txid";
+						link = <&switch0port5>;
+						fixed-link {
+							speed = <1000>;
+							full-duplex;
+						};
+					};
+				};
+				mdio {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					switch1phy0: switch1phy0@0 {
+						reg = <0>;
+					};
+					switch1phy1: switch1phy0@1 {
+						reg = <1>;
+					};
+					switch1phy2: switch1phy0@2 {
+						reg = <2>;
+					};
+				};
+			};
 		};
 
 		mdio_mux_4: mdio@4 {
-			reg = <4>;
 			#address-cells = <1>;
 			#size-cells = <0>;
+			reg = <4>;
+
+			switch2: switch2@0 {
+				compatible = "marvell,mv88e6085";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				reg = <0>;
+				dsa,member = <0 2>;
+
+				ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					port@0 {
+						reg = <0>;
+						label = "lan6";
+					};
+
+					port@1 {
+						reg = <1>;
+						label = "lan7";
+					};
+
+					port@2 {
+						reg = <2>;
+						label = "lan8";
+					};
+
+					port@3 {
+						reg = <3>;
+						label = "optical3";
+						fixed-link {
+							speed = <1000>;
+							full-duplex;
+							link-gpios = <&gpio6 2
+							      GPIO_ACTIVE_HIGH>;
+						};
+					};
+
+					port@4 {
+						reg = <4>;
+						label = "optical4";
+						fixed-link {
+							speed = <1000>;
+							full-duplex;
+							link-gpios = <&gpio6 3
+							      GPIO_ACTIVE_HIGH>;
+						};
+					};
+
+					switch2port9: port@9 {
+						reg = <9>;
+						label = "dsa";
+						phy-mode = "rgmii-txid";
+						link = <&switch1port5
+							&switch0port5>;
+						fixed-link {
+							speed = <1000>;
+							full-duplex;
+						};
+					};
+				};
+			};
 		};
 
 		mdio_mux_8: mdio@8 {
@@ -106,169 +281,6 @@
 		};
 	};
 
-	dsa {
-		compatible = "marvell,dsa";
-		#address-cells = <2>;
-		#size-cells = <0>;
-		dsa,ethernet = <&fec1>;
-		dsa,mii-bus = <&mdio_mux_1>;
-
-		/* 6352 - Primary - 7 ports */
-		switch0: switch@0-0 {
-			#address-cells = <1>;
-			#size-cells = <0>;
-			reg = <0x00 0>;
-			eeprom-length = <512>;
-
-			port@0 {
-				reg = <0>;
-				label = "lan0";
-			};
-
-			port@1 {
-				reg = <1>;
-				label = "lan1";
-			};
-
-			port@2 {
-				reg = <2>;
-				label = "lan2";
-			};
-
-			switch0port5: port@5 {
-				reg = <5>;
-				label = "dsa";
-				phy-mode = "rgmii-txid";
-				link = <&switch1port6
-					&switch2port9>;
-
-				fixed-link {
-					speed = <1000>;
-					full-duplex;
-				};
-			};
-
-			port@6 {
-				reg = <6>;
-				label = "cpu";
-
-				fixed-link {
-					speed = <100>;
-					full-duplex;
-				};
-			};
-
-		};
-
-		/* 6352 - Secondary - 7 ports */
-		switch1: switch@0-1 {
-			#address-cells = <1>;
-			#size-cells = <0>;
-			reg = <0x00 1>;
-			eeprom-length = <512>;
-			mii-bus = <&mdio_mux_2>;
-
-			port@0 {
-				reg = <0>;
-				label = "lan3";
-			};
-
-			port@1 {
-				reg = <1>;
-				label = "lan4";
-			};
-
-			port@2 {
-				reg = <2>;
-				label = "lan5";
-			};
-
-			switch1port5: port@5 {
-				reg = <5>;
-				label = "dsa";
-				link = <&switch2port9>;
-				phy-mode = "rgmii-txid";
-
-				fixed-link {
-					speed = <1000>;
-					full-duplex;
-				};
-			};
-
-			switch1port6: port@6 {
-				reg = <6>;
-				label = "dsa";
-				phy-mode = "rgmii-txid";
-				link = <&switch0port5>;
-
-				fixed-link {
-					speed = <1000>;
-					full-duplex;
-				};
-			};
-		};
-
-		/* 6185 - 10 ports */
-		switch2: switch@0-2 {
-			#address-cells = <1>;
-			#size-cells = <0>;
-			reg = <0x00 2>;
-			mii-bus = <&mdio_mux_4>;
-
-			port@0 {
-				reg = <0>;
-				label = "lan6";
-			};
-
-			port@1 {
-				reg = <1>;
-				label = "lan7";
-			};
-
-			port@2 {
-				reg = <2>;
-				label = "lan8";
-			};
-
-			port@3 {
-				reg = <3>;
-				label = "optical3";
-
-				fixed-link {
-					speed = <1000>;
-					full-duplex;
-					link-gpios = <&gpio6 2
-						      GPIO_ACTIVE_HIGH>;
-				};
-			};
-
-			port@4 {
-				reg = <4>;
-				label = "optical4";
-
-				fixed-link {
-					speed = <1000>;
-					full-duplex;
-					link-gpios = <&gpio6 3
-						      GPIO_ACTIVE_HIGH>;
-				};
-			};
-
-			switch2port9: port@9 {
-				reg = <9>;
-				label = "dsa";
-				phy-mode = "rgmii-txid";
-				link = <&switch1port5
-					&switch0port5>;
-
-				fixed-link {
-					speed = <1000>;
-					full-duplex;
-				};
-			};
-		};
-	};
-
 	reg_vcc_3v3_mcu: regulator-vcc-3v3-mcu {
 		compatible = "regulator-fixed";
 		regulator-name = "vcc_3v3_mcu";
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index ef9119f..4d93758 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -733,8 +733,8 @@
 	if (ret)
 		return ret;
 
-	vfp_flush_hwstate(thread);
 	thread->vfpstate.hard = new_vfp;
+	vfp_flush_hwstate(thread);
 
 	return 0;
 }
diff --git a/arch/arm/mach-vexpress/spc.c b/arch/arm/mach-vexpress/spc.c
index 5766ce2..8409cab 100644
--- a/arch/arm/mach-vexpress/spc.c
+++ b/arch/arm/mach-vexpress/spc.c
@@ -547,7 +547,7 @@
 
 	init.name = dev_name(cpu_dev);
 	init.ops = &clk_spc_ops;
-	init.flags = CLK_IS_ROOT | CLK_GET_RATE_NOCACHE;
+	init.flags = CLK_GET_RATE_NOCACHE;
 	init.num_parents = 0;
 
 	return devm_clk_register(cpu_dev, &spc->hw);
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 76747d9..5a0a691 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -113,6 +113,18 @@
 config MMU
 	def_bool y
 
+config ARM64_PAGE_SHIFT
+	int
+	default 16 if ARM64_64K_PAGES
+	default 14 if ARM64_16K_PAGES
+	default 12
+
+config ARM64_CONT_SHIFT
+	int
+	default 5 if ARM64_64K_PAGES
+	default 7 if ARM64_16K_PAGES
+	default 4
+
 config ARCH_MMAP_RND_BITS_MIN
        default 14 if ARM64_64K_PAGES
        default 16 if ARM64_16K_PAGES
@@ -426,6 +438,15 @@
 
 	  If unsure, say Y.
 
+config CAVIUM_ERRATUM_23144
+	bool "Cavium erratum 23144: ITS SYNC hang on dual socket system"
+	depends on NUMA
+	default y
+	help
+	  ITS SYNC command hang for cross node io and collections/cpu mapping.
+
+	  If unsure, say Y.
+
 config CAVIUM_ERRATUM_23154
 	bool "Cavium erratum 23154: Access to ICC_IAR1_EL1 is not sync'ed"
 	default y
diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug
index 710fde4..0cc758c 100644
--- a/arch/arm64/Kconfig.debug
+++ b/arch/arm64/Kconfig.debug
@@ -12,7 +12,8 @@
 	  who are working in architecture specific areas of the kernel.
 	  It is probably not a good idea to enable this feature in a production
 	  kernel.
-	  If in doubt, say "N"
+
+	  If in doubt, say N.
 
 config PID_IN_CONTEXTIDR
 	bool "Write the current PID to the CONTEXTIDR register"
@@ -38,15 +39,15 @@
 	  value.
 
 config DEBUG_SET_MODULE_RONX
-        bool "Set loadable kernel module data as NX and text as RO"
-        depends on MODULES
-        help
-          This option helps catch unintended modifications to loadable
-          kernel module's text and read-only data. It also prevents execution
-          of module data. Such protection may interfere with run-time code
-          patching and dynamic kernel tracing - and they might also protect
-          against certain classes of kernel exploits.
-          If in doubt, say "N".
+	bool "Set loadable kernel module data as NX and text as RO"
+	depends on MODULES
+	default y
+	help
+	  Is this is set, kernel module text and rodata will be made read-only.
+	  This is to help catch accidental or malicious attempts to change the
+	  kernel's executable code.
+
+	  If in doubt, say Y.
 
 config DEBUG_RODATA
 	bool "Make kernel text and rodata read-only"
@@ -56,7 +57,7 @@
 	  is to help catch accidental or malicious attempts to change the
 	  kernel's executable code.
 
-	  If in doubt, say Y
+	  If in doubt, say Y.
 
 config DEBUG_ALIGN_RODATA
 	depends on DEBUG_RODATA
@@ -69,7 +70,7 @@
 	  alignment and potentially wasted space. Turn on this option if
 	  performance is more important than memory pressure.
 
-	  If in doubt, say N
+	  If in doubt, say N.
 
 source "drivers/hwtracing/coresight/Kconfig"
 
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 354d754..7085e32 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -60,7 +60,9 @@
 
 # The byte offset of the kernel image in RAM from the start of RAM.
 ifeq ($(CONFIG_ARM64_RANDOMIZE_TEXT_OFFSET), y)
-TEXT_OFFSET := $(shell awk 'BEGIN {srand(); printf "0x%03x000\n", int(512 * rand())}')
+TEXT_OFFSET := $(shell awk "BEGIN {srand(); printf \"0x%06x\n\", \
+		 int(2 * 1024 * 1024 / (2 ^ $(CONFIG_ARM64_PAGE_SHIFT)) * \
+		 rand()) * (2 ^ $(CONFIG_ARM64_PAGE_SHIFT))}")
 else
 TEXT_OFFSET := 0x00080000
 endif
diff --git a/arch/arm64/boot/dts/broadcom/ns2-svk.dts b/arch/arm64/boot/dts/broadcom/ns2-svk.dts
index 54ca40c..ea5603f 100644
--- a/arch/arm64/boot/dts/broadcom/ns2-svk.dts
+++ b/arch/arm64/boot/dts/broadcom/ns2-svk.dts
@@ -52,6 +52,14 @@
 	};
 };
 
+&pci_phy0 {
+	status = "ok";
+};
+
+&pci_phy1 {
+	status = "ok";
+};
+
 &pcie0 {
 	status = "ok";
 };
@@ -132,3 +140,11 @@
 		#size-cells = <1>;
 	};
 };
+
+&mdio_mux_iproc {
+	mdio@10 {
+		gphy0: eth-phy@10 {
+			reg = <0x10>;
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/broadcom/ns2.dtsi b/arch/arm64/boot/dts/broadcom/ns2.dtsi
index ec68ec1..46b78fa 100644
--- a/arch/arm64/boot/dts/broadcom/ns2.dtsi
+++ b/arch/arm64/boot/dts/broadcom/ns2.dtsi
@@ -263,6 +263,45 @@
 				      IRQ_TYPE_LEVEL_HIGH)>;
 		};
 
+		mdio_mux_iproc: mdio-mux@6602023c {
+			compatible = "brcm,mdio-mux-iproc";
+			reg = <0x6602023c 0x14>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			mdio@0 {
+				reg = <0x0>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				pci_phy0: pci-phy@0 {
+					compatible = "brcm,ns2-pcie-phy";
+					reg = <0x0>;
+					#phy-cells = <0>;
+					status = "disabled";
+				};
+			};
+
+			mdio@7 {
+				reg = <0x7>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				pci_phy1: pci-phy@0 {
+					compatible = "brcm,ns2-pcie-phy";
+					reg = <0x0>;
+					#phy-cells = <0>;
+					status = "disabled";
+				};
+			};
+
+			mdio@10 {
+				reg = <0x10>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+			};
+		};
+
 		timer0: timer@66030000 {
 			compatible = "arm,sp804", "arm,primecell";
 			reg = <0x66030000 0x1000>;
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index 7a09c48..579b6e6 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -160,14 +160,14 @@
 #define STACK_RND_MASK			(0x3ffff >> (PAGE_SHIFT - 12))
 #endif
 
-#ifdef CONFIG_COMPAT
-
 #ifdef __AARCH64EB__
 #define COMPAT_ELF_PLATFORM		("v8b")
 #else
 #define COMPAT_ELF_PLATFORM		("v8l")
 #endif
 
+#ifdef CONFIG_COMPAT
+
 #define COMPAT_ELF_ET_DYN_BASE		(2 * TASK_SIZE_32 / 3)
 
 /* AArch32 registers. */
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 72a3025..31b7322 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -55,8 +55,9 @@
 #define VMEMMAP_SIZE (UL(1) << (VA_BITS - PAGE_SHIFT - 1 + STRUCT_PAGE_MAX_SHIFT))
 
 /*
- * PAGE_OFFSET - the virtual address of the start of the kernel image (top
+ * PAGE_OFFSET - the virtual address of the start of the linear map (top
  *		 (VA_BITS - 1))
+ * KIMAGE_VADDR - the virtual address of the start of the kernel image
  * VA_BITS - the maximum number of bits for virtual addresses.
  * VA_START - the first kernel virtual address.
  * TASK_SIZE - the maximum size of a user space task.
diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h
index 17b45f7..8472c6d 100644
--- a/arch/arm64/include/asm/page.h
+++ b/arch/arm64/include/asm/page.h
@@ -23,16 +23,8 @@
 
 /* PAGE_SHIFT determines the page size */
 /* CONT_SHIFT determines the number of pages which can be tracked together  */
-#ifdef CONFIG_ARM64_64K_PAGES
-#define PAGE_SHIFT		16
-#define CONT_SHIFT		5
-#elif defined(CONFIG_ARM64_16K_PAGES)
-#define PAGE_SHIFT		14
-#define CONT_SHIFT		7
-#else
-#define PAGE_SHIFT		12
-#define CONT_SHIFT		4
-#endif
+#define PAGE_SHIFT		CONFIG_ARM64_PAGE_SHIFT
+#define CONT_SHIFT		CONFIG_ARM64_CONT_SHIFT
 #define PAGE_SIZE		(_AC(1, UL) << PAGE_SHIFT)
 #define PAGE_MASK		(~(PAGE_SIZE-1))
 
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 0685d74..9e397a5 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -81,19 +81,6 @@
 #define segment_eq(a, b)	((a) == (b))
 
 /*
- * Return 1 if addr < current->addr_limit, 0 otherwise.
- */
-#define __addr_ok(addr)							\
-({									\
-	unsigned long flag;						\
-	asm("cmp %1, %0; cset %0, lo"					\
-		: "=&r" (flag)						\
-		: "r" (addr), "0" (current_thread_info()->addr_limit)	\
-		: "cc");						\
-	flag;								\
-})
-
-/*
  * Test whether a block of memory is a valid user space address.
  * Returns 1 if the range is valid, 0 otherwise.
  *
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 41e58fe..e78ac26 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -44,7 +44,7 @@
 #define __ARM_NR_compat_cacheflush	(__ARM_NR_COMPAT_BASE+2)
 #define __ARM_NR_compat_set_tls		(__ARM_NR_COMPAT_BASE+5)
 
-#define __NR_compat_syscalls		390
+#define __NR_compat_syscalls		394
 #endif
 
 #define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 5b925b7..b7e8ef1 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -801,6 +801,14 @@
 __SYSCALL(__NR_userfaultfd, sys_userfaultfd)
 #define __NR_membarrier 389
 __SYSCALL(__NR_membarrier, sys_membarrier)
+#define __NR_mlock2 390
+__SYSCALL(__NR_mlock2, sys_mlock2)
+#define __NR_copy_file_range 391
+__SYSCALL(__NR_copy_file_range, sys_copy_file_range)
+#define __NR_preadv2 392
+__SYSCALL(__NR_preadv2, compat_sys_preadv2)
+#define __NR_pwritev2 393
+__SYSCALL(__NR_pwritev2, compat_sys_pwritev2)
 
 /*
  * Please add new compat syscalls above this comment and update
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 3808470..c173d32 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -22,6 +22,8 @@
 
 #include <linux/bitops.h>
 #include <linux/bug.h>
+#include <linux/compat.h>
+#include <linux/elf.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/personality.h>
@@ -104,6 +106,7 @@
 static int c_show(struct seq_file *m, void *v)
 {
 	int i, j;
+	bool compat = personality(current->personality) == PER_LINUX32;
 
 	for_each_online_cpu(i) {
 		struct cpuinfo_arm64 *cpuinfo = &per_cpu(cpu_data, i);
@@ -115,6 +118,9 @@
 		 * "processor".  Give glibc what it expects.
 		 */
 		seq_printf(m, "processor\t: %d\n", i);
+		if (compat)
+			seq_printf(m, "model name\t: ARMv8 Processor rev %d (%s)\n",
+				   MIDR_REVISION(midr), COMPAT_ELF_PLATFORM);
 
 		seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
 			   loops_per_jiffy / (500000UL/HZ),
@@ -127,7 +133,7 @@
 		 * software which does already (at least for 32-bit).
 		 */
 		seq_puts(m, "Features\t:");
-		if (personality(current->personality) == PER_LINUX32) {
+		if (compat) {
 #ifdef CONFIG_COMPAT
 			for (j = 0; compat_hwcap_str[j]; j++)
 				if (compat_elf_hwcap & (1 << j))
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index c539208..f7cf463 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -477,8 +477,9 @@
 	void __user *pc = (void __user *)instruction_pointer(regs);
 	console_verbose();
 
-	pr_crit("Bad mode in %s handler detected, code 0x%08x -- %s\n",
-		handler[reason], esr, esr_get_class_string(esr));
+	pr_crit("Bad mode in %s handler detected on CPU%d, code 0x%08x -- %s\n",
+		handler[reason], smp_processor_id(), esr,
+		esr_get_class_string(esr));
 	__show_regs(regs);
 
 	info.si_signo = SIGILL;
diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
index fff7cd4..5f8f80b 100644
--- a/arch/arm64/kvm/hyp/vgic-v3-sr.c
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -169,7 +169,8 @@
 	 * Make sure stores to the GIC via the memory mapped interface
 	 * are now visible to the system register interface.
 	 */
-	dsb(st);
+	if (!cpu_if->vgic_sre)
+		dsb(st);
 
 	cpu_if->vgic_vmcr  = read_gicreg(ICH_VMCR_EL2);
 
@@ -190,12 +191,11 @@
 			if (!(vcpu->arch.vgic_cpu.live_lrs & (1UL << i)))
 				continue;
 
-			if (cpu_if->vgic_elrsr & (1 << i)) {
+			if (cpu_if->vgic_elrsr & (1 << i))
 				cpu_if->vgic_lr[i] &= ~ICH_LR_STATE;
-				continue;
-			}
+			else
+				cpu_if->vgic_lr[i] = __gic_v3_get_lr(i);
 
-			cpu_if->vgic_lr[i] = __gic_v3_get_lr(i);
 			__gic_v3_set_lr(0, i);
 		}
 
@@ -236,8 +236,12 @@
 
 	val = read_gicreg(ICC_SRE_EL2);
 	write_gicreg(val | ICC_SRE_EL2_ENABLE, ICC_SRE_EL2);
-	isb(); /* Make sure ENABLE is set at EL2 before setting SRE at EL1 */
-	write_gicreg(1, ICC_SRE_EL1);
+
+	if (!cpu_if->vgic_sre) {
+		/* Make sure ENABLE is set at EL2 before setting SRE at EL1 */
+		isb();
+		write_gicreg(1, ICC_SRE_EL1);
+	}
 }
 
 void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
@@ -256,8 +260,10 @@
 	 * been actually programmed with the value we want before
 	 * starting to mess with the rest of the GIC.
 	 */
-	write_gicreg(cpu_if->vgic_sre, ICC_SRE_EL1);
-	isb();
+	if (!cpu_if->vgic_sre) {
+		write_gicreg(0, ICC_SRE_EL1);
+		isb();
+	}
 
 	val = read_gicreg(ICH_VTR_EL2);
 	max_lr_idx = vtr_to_max_lr_idx(val);
@@ -306,18 +312,18 @@
 	 * (re)distributors. This ensure the guest will read the
 	 * correct values from the memory-mapped interface.
 	 */
-	isb();
-	dsb(sy);
+	if (!cpu_if->vgic_sre) {
+		isb();
+		dsb(sy);
+	}
 	vcpu->arch.vgic_cpu.live_lrs = live_lrs;
 
 	/*
 	 * Prevent the guest from touching the GIC system registers if
 	 * SRE isn't enabled for GICv3 emulation.
 	 */
-	if (!cpu_if->vgic_sre) {
-		write_gicreg(read_gicreg(ICC_SRE_EL2) & ~ICC_SRE_EL2_ENABLE,
-			     ICC_SRE_EL2);
-	}
+	write_gicreg(read_gicreg(ICC_SRE_EL2) & ~ICC_SRE_EL2_ENABLE,
+		     ICC_SRE_EL2);
 }
 
 void __hyp_text __vgic_v3_init_lrs(void)
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 7bbe3ff..a57d650 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -134,6 +134,17 @@
 	return true;
 }
 
+static bool access_gic_sre(struct kvm_vcpu *vcpu,
+			   struct sys_reg_params *p,
+			   const struct sys_reg_desc *r)
+{
+	if (p->is_write)
+		return ignore_write(vcpu, p);
+
+	p->regval = vcpu->arch.vgic_cpu.vgic_v3.vgic_sre;
+	return true;
+}
+
 static bool trap_raz_wi(struct kvm_vcpu *vcpu,
 			struct sys_reg_params *p,
 			const struct sys_reg_desc *r)
@@ -958,7 +969,7 @@
 	  access_gic_sgi },
 	/* ICC_SRE_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1100), CRm(0b1100), Op2(0b101),
-	  trap_raz_wi },
+	  access_gic_sre },
 
 	/* CONTEXTIDR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1101), CRm(0b0000), Op2(0b001),
diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c
index 8404190..ccfde23 100644
--- a/arch/arm64/mm/dump.c
+++ b/arch/arm64/mm/dump.c
@@ -150,6 +150,7 @@
 
 struct pg_level {
 	const struct prot_bits *bits;
+	const char *name;
 	size_t num;
 	u64 mask;
 };
@@ -157,15 +158,19 @@
 static struct pg_level pg_level[] = {
 	{
 	}, { /* pgd */
+		.name	= "PGD",
 		.bits	= pte_bits,
 		.num	= ARRAY_SIZE(pte_bits),
 	}, { /* pud */
+		.name	= (CONFIG_PGTABLE_LEVELS > 3) ? "PUD" : "PGD",
 		.bits	= pte_bits,
 		.num	= ARRAY_SIZE(pte_bits),
 	}, { /* pmd */
+		.name	= (CONFIG_PGTABLE_LEVELS > 2) ? "PMD" : "PGD",
 		.bits	= pte_bits,
 		.num	= ARRAY_SIZE(pte_bits),
 	}, { /* pte */
+		.name	= "PTE",
 		.bits	= pte_bits,
 		.num	= ARRAY_SIZE(pte_bits),
 	},
@@ -214,7 +219,8 @@
 				delta >>= 10;
 				unit++;
 			}
-			seq_printf(st->seq, "%9lu%c", delta, *unit);
+			seq_printf(st->seq, "%9lu%c %s", delta, *unit,
+				   pg_level[st->level].name);
 			if (pg_level[st->level].bits)
 				dump_prot(st, pg_level[st->level].bits,
 					  pg_level[st->level].num);
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index aa8aee7..2e49bd2 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -306,6 +306,10 @@
 		hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
 	} else if (ps == PUD_SIZE) {
 		hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
+	} else if (ps == (PAGE_SIZE * CONT_PTES)) {
+		hugetlb_add_hstate(CONT_PTE_SHIFT);
+	} else if (ps == (PMD_SIZE * CONT_PMDS)) {
+		hugetlb_add_hstate((PMD_SHIFT + CONT_PMD_SHIFT) - PAGE_SHIFT);
 	} else {
 		hugetlb_bad_size();
 		pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10);
@@ -314,3 +318,13 @@
 	return 1;
 }
 __setup("hugepagesz=", setup_hugepagesz);
+
+#ifdef CONFIG_ARM64_64K_PAGES
+static __init int add_default_hugepagesz(void)
+{
+	if (size_to_hstate(CONT_PTES * PAGE_SIZE) == NULL)
+		hugetlb_add_hstate(CONT_PMD_SHIFT);
+	return 0;
+}
+arch_initcall(add_default_hugepagesz);
+#endif
diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h
index aee5637..7c16e54 100644
--- a/arch/arm64/net/bpf_jit.h
+++ b/arch/arm64/net/bpf_jit.h
@@ -1,7 +1,7 @@
 /*
  * BPF JIT compiler for ARM64
  *
- * Copyright (C) 2014-2015 Zi Shen Lim <zlim.lnx@gmail.com>
+ * Copyright (C) 2014-2016 Zi Shen Lim <zlim.lnx@gmail.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
@@ -55,6 +55,7 @@
 #define A64_BL(imm26) A64_BRANCH((imm26) << 2, LINK)
 
 /* Unconditional branch (register) */
+#define A64_BR(Rn)  aarch64_insn_gen_branch_reg(Rn, AARCH64_INSN_BRANCH_NOLINK)
 #define A64_BLR(Rn) aarch64_insn_gen_branch_reg(Rn, AARCH64_INSN_BRANCH_LINK)
 #define A64_RET(Rn) aarch64_insn_gen_branch_reg(Rn, AARCH64_INSN_BRANCH_RETURN)
 
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 49ba37e..b2fc97a 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -18,6 +18,7 @@
 
 #define pr_fmt(fmt) "bpf_jit: " fmt
 
+#include <linux/bpf.h>
 #include <linux/filter.h>
 #include <linux/printk.h>
 #include <linux/skbuff.h>
@@ -33,6 +34,7 @@
 
 #define TMP_REG_1 (MAX_BPF_JIT_REG + 0)
 #define TMP_REG_2 (MAX_BPF_JIT_REG + 1)
+#define TCALL_CNT (MAX_BPF_JIT_REG + 2)
 
 /* Map BPF registers to A64 registers */
 static const int bpf2a64[] = {
@@ -54,6 +56,8 @@
 	/* temporary registers for internal BPF JIT */
 	[TMP_REG_1] = A64_R(10),
 	[TMP_REG_2] = A64_R(11),
+	/* tail_call_cnt */
+	[TCALL_CNT] = A64_R(26),
 	/* temporary register for blinding constants */
 	[BPF_REG_AX] = A64_R(9),
 };
@@ -146,13 +150,18 @@
 
 #define STACK_SIZE STACK_ALIGN(_STACK_SIZE)
 
-static void build_prologue(struct jit_ctx *ctx)
+#define PROLOGUE_OFFSET 8
+
+static int build_prologue(struct jit_ctx *ctx)
 {
 	const u8 r6 = bpf2a64[BPF_REG_6];
 	const u8 r7 = bpf2a64[BPF_REG_7];
 	const u8 r8 = bpf2a64[BPF_REG_8];
 	const u8 r9 = bpf2a64[BPF_REG_9];
 	const u8 fp = bpf2a64[BPF_REG_FP];
+	const u8 tcc = bpf2a64[TCALL_CNT];
+	const int idx0 = ctx->idx;
+	int cur_offset;
 
 	/*
 	 * BPF prog stack layout
@@ -162,8 +171,6 @@
 	 *                        |FP/LR|
 	 * current A64_FP =>  -16:+-----+
 	 *                        | ... | callee saved registers
-	 *                        +-----+
-	 *                        |     | x25/x26
 	 * BPF fp register => -64:+-----+ <= (BPF_FP)
 	 *                        |     |
 	 *                        | ... | BPF prog stack
@@ -183,18 +190,90 @@
 	emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx);
 	emit(A64_MOV(1, A64_FP, A64_SP), ctx);
 
-	/* Save callee-saved register */
+	/* Save callee-saved registers */
 	emit(A64_PUSH(r6, r7, A64_SP), ctx);
 	emit(A64_PUSH(r8, r9, A64_SP), ctx);
+	emit(A64_PUSH(fp, tcc, A64_SP), ctx);
 
-	/* Save fp (x25) and x26. SP requires 16 bytes alignment */
-	emit(A64_PUSH(fp, A64_R(26), A64_SP), ctx);
-
-	/* Set up BPF prog stack base register (x25) */
+	/* Set up BPF prog stack base register */
 	emit(A64_MOV(1, fp, A64_SP), ctx);
 
+	/* Initialize tail_call_cnt */
+	emit(A64_MOVZ(1, tcc, 0, 0), ctx);
+
 	/* Set up function call stack */
 	emit(A64_SUB_I(1, A64_SP, A64_SP, STACK_SIZE), ctx);
+
+	cur_offset = ctx->idx - idx0;
+	if (cur_offset != PROLOGUE_OFFSET) {
+		pr_err_once("PROLOGUE_OFFSET = %d, expected %d!\n",
+			    cur_offset, PROLOGUE_OFFSET);
+		return -1;
+	}
+	return 0;
+}
+
+static int out_offset = -1; /* initialized on the first pass of build_body() */
+static int emit_bpf_tail_call(struct jit_ctx *ctx)
+{
+	/* bpf_tail_call(void *prog_ctx, struct bpf_array *array, u64 index) */
+	const u8 r2 = bpf2a64[BPF_REG_2];
+	const u8 r3 = bpf2a64[BPF_REG_3];
+
+	const u8 tmp = bpf2a64[TMP_REG_1];
+	const u8 prg = bpf2a64[TMP_REG_2];
+	const u8 tcc = bpf2a64[TCALL_CNT];
+	const int idx0 = ctx->idx;
+#define cur_offset (ctx->idx - idx0)
+#define jmp_offset (out_offset - (cur_offset))
+	size_t off;
+
+	/* if (index >= array->map.max_entries)
+	 *     goto out;
+	 */
+	off = offsetof(struct bpf_array, map.max_entries);
+	emit_a64_mov_i64(tmp, off, ctx);
+	emit(A64_LDR32(tmp, r2, tmp), ctx);
+	emit(A64_CMP(0, r3, tmp), ctx);
+	emit(A64_B_(A64_COND_GE, jmp_offset), ctx);
+
+	/* if (tail_call_cnt > MAX_TAIL_CALL_CNT)
+	 *     goto out;
+	 * tail_call_cnt++;
+	 */
+	emit_a64_mov_i64(tmp, MAX_TAIL_CALL_CNT, ctx);
+	emit(A64_CMP(1, tcc, tmp), ctx);
+	emit(A64_B_(A64_COND_GT, jmp_offset), ctx);
+	emit(A64_ADD_I(1, tcc, tcc, 1), ctx);
+
+	/* prog = array->ptrs[index];
+	 * if (prog == NULL)
+	 *     goto out;
+	 */
+	off = offsetof(struct bpf_array, ptrs);
+	emit_a64_mov_i64(tmp, off, ctx);
+	emit(A64_LDR64(tmp, r2, tmp), ctx);
+	emit(A64_LDR64(prg, tmp, r3), ctx);
+	emit(A64_CBZ(1, prg, jmp_offset), ctx);
+
+	/* goto *(prog->bpf_func + prologue_size); */
+	off = offsetof(struct bpf_prog, bpf_func);
+	emit_a64_mov_i64(tmp, off, ctx);
+	emit(A64_LDR64(tmp, prg, tmp), ctx);
+	emit(A64_ADD_I(1, tmp, tmp, sizeof(u32) * PROLOGUE_OFFSET), ctx);
+	emit(A64_BR(tmp), ctx);
+
+	/* out: */
+	if (out_offset == -1)
+		out_offset = cur_offset;
+	if (cur_offset != out_offset) {
+		pr_err_once("tail_call out_offset = %d, expected %d!\n",
+			    cur_offset, out_offset);
+		return -1;
+	}
+	return 0;
+#undef cur_offset
+#undef jmp_offset
 }
 
 static void build_epilogue(struct jit_ctx *ctx)
@@ -499,13 +578,15 @@
 		const u64 func = (u64)__bpf_call_base + imm;
 
 		emit_a64_mov_i64(tmp, func, ctx);
-		emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx);
-		emit(A64_MOV(1, A64_FP, A64_SP), ctx);
 		emit(A64_BLR(tmp), ctx);
 		emit(A64_MOV(1, r0, A64_R(0)), ctx);
-		emit(A64_POP(A64_FP, A64_LR, A64_SP), ctx);
 		break;
 	}
+	/* tail call */
+	case BPF_JMP | BPF_CALL | BPF_X:
+		if (emit_bpf_tail_call(ctx))
+			return -EFAULT;
+		break;
 	/* function return */
 	case BPF_JMP | BPF_EXIT:
 		/* Optimization: when last instruction is EXIT,
@@ -650,11 +731,8 @@
 		emit_a64_mov_i64(r3, size, ctx);
 		emit(A64_SUB_I(1, r4, fp, STACK_SIZE), ctx);
 		emit_a64_mov_i64(r5, (unsigned long)bpf_load_pointer, ctx);
-		emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx);
-		emit(A64_MOV(1, A64_FP, A64_SP), ctx);
 		emit(A64_BLR(r5), ctx);
 		emit(A64_MOV(1, r0, A64_R(0)), ctx);
-		emit(A64_POP(A64_FP, A64_LR, A64_SP), ctx);
 
 		jmp_offset = epilogue_offset(ctx);
 		check_imm19(jmp_offset);
@@ -780,7 +858,10 @@
 		goto out_off;
 	}
 
-	build_prologue(&ctx);
+	if (build_prologue(&ctx)) {
+		prog = orig_prog;
+		goto out_off;
+	}
 
 	ctx.epilogue_offset = ctx.idx;
 	build_epilogue(&ctx);
diff --git a/arch/parisc/include/asm/traps.h b/arch/parisc/include/asm/traps.h
index 4736020..5e953ab 100644
--- a/arch/parisc/include/asm/traps.h
+++ b/arch/parisc/include/asm/traps.h
@@ -8,6 +8,8 @@
 void parisc_terminate(char *msg, struct pt_regs *regs,
 		int code, unsigned long offset) __noreturn __cold;
 
+void die_if_kernel(char *str, struct pt_regs *regs, long err);
+
 /* mm/fault.c */
 void do_page_fault(struct pt_regs *regs, unsigned long code,
 		unsigned long address);
diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c
index e81ccf1..5adc339 100644
--- a/arch/parisc/kernel/processor.c
+++ b/arch/parisc/kernel/processor.c
@@ -324,8 +324,9 @@
 		per_cpu(cpu_data, cpunum).fp_rev = coproc_cfg.revision;
 		per_cpu(cpu_data, cpunum).fp_model = coproc_cfg.model;
 
-		printk(KERN_INFO  "FP[%d] enabled: Rev %ld Model %ld\n",
-			cpunum, coproc_cfg.revision, coproc_cfg.model);
+		if (cpunum == 0)
+			printk(KERN_INFO  "FP[%d] enabled: Rev %ld Model %ld\n",
+				cpunum, coproc_cfg.revision, coproc_cfg.model);
 
 		/*
 		** store status register to stack (hopefully aligned)
diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c
index 58dd680..31ec99a 100644
--- a/arch/parisc/kernel/time.c
+++ b/arch/parisc/kernel/time.c
@@ -309,11 +309,6 @@
 	clocks_calc_mult_shift(&cyc2ns_mul, &cyc2ns_shift, current_cr16_khz,
 				NSEC_PER_MSEC, 0);
 
-#if defined(CONFIG_HAVE_UNSTABLE_SCHED_CLOCK) && defined(CONFIG_64BIT)
-	/* At bootup only one 64bit CPU is online and cr16 is "stable" */
-	set_sched_clock_stable();
-#endif
-
 	start_cpu_itimer();	/* get CPU 0 started */
 
 	/* register at clocksource framework */
diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c
index d7c0acb..2b65c01 100644
--- a/arch/parisc/kernel/unaligned.c
+++ b/arch/parisc/kernel/unaligned.c
@@ -28,6 +28,7 @@
 #include <linux/ratelimit.h>
 #include <asm/uaccess.h>
 #include <asm/hardirq.h>
+#include <asm/traps.h>
 
 /* #define DEBUG_UNALIGNED 1 */
 
@@ -130,8 +131,6 @@
 
 int unaligned_enabled __read_mostly = 1;
 
-void die_if_kernel (char *str, struct pt_regs *regs, long err);
-
 static int emulate_ldh(struct pt_regs *regs, int toreg)
 {
 	unsigned long saddr = regs->ior;
@@ -666,7 +665,7 @@
 		break;
 	}
 
-	if (modify && R1(regs->iir))
+	if (ret == 0 && modify && R1(regs->iir))
 		regs->gr[R1(regs->iir)] = newbase;
 
 
@@ -677,6 +676,14 @@
 
 	if (ret)
 	{
+		/*
+		 * The unaligned handler failed.
+		 * If we were called by __get_user() or __put_user() jump
+		 * to it's exception fixup handler instead of crashing.
+		 */
+		if (!user_mode(regs) && fixup_exception(regs))
+			return;
+
 		printk(KERN_CRIT "Unaligned handler failed, ret = %d\n", ret);
 		die_if_kernel("Unaligned data reference", regs, 28);
 
diff --git a/arch/parisc/kernel/unwind.c b/arch/parisc/kernel/unwind.c
index ddd988b..e278a87 100644
--- a/arch/parisc/kernel/unwind.c
+++ b/arch/parisc/kernel/unwind.c
@@ -75,7 +75,10 @@
 	if (addr >= kernel_unwind_table.start && 
 	    addr <= kernel_unwind_table.end)
 		e = find_unwind_entry_in_table(&kernel_unwind_table, addr);
-	else 
+	else {
+		unsigned long flags;
+
+		spin_lock_irqsave(&unwind_lock, flags);
 		list_for_each_entry(table, &unwind_tables, list) {
 			if (addr >= table->start && 
 			    addr <= table->end)
@@ -86,6 +89,8 @@
 				break;
 			}
 		}
+		spin_unlock_irqrestore(&unwind_lock, flags);
+	}
 
 	return e;
 }
@@ -303,18 +308,16 @@
 
 			insn = *(unsigned int *)npc;
 
-			if ((insn & 0xffffc000) == 0x37de0000 ||
-			    (insn & 0xffe00000) == 0x6fc00000) {
+			if ((insn & 0xffffc001) == 0x37de0000 ||
+			    (insn & 0xffe00001) == 0x6fc00000) {
 				/* ldo X(sp), sp, or stwm X,D(sp) */
-				frame_size += (insn & 0x1 ? -1 << 13 : 0) | 
-					((insn & 0x3fff) >> 1);
+				frame_size += (insn & 0x3fff) >> 1;
 				dbg("analyzing func @ %lx, insn=%08x @ "
 				    "%lx, frame_size = %ld\n", info->ip,
 				    insn, npc, frame_size);
-			} else if ((insn & 0xffe00008) == 0x73c00008) {
+			} else if ((insn & 0xffe00009) == 0x73c00008) {
 				/* std,ma X,D(sp) */
-				frame_size += (insn & 0x1 ? -1 << 13 : 0) | 
-					(((insn >> 4) & 0x3ff) << 3);
+				frame_size += ((insn >> 4) & 0x3ff) << 3;
 				dbg("analyzing func @ %lx, insn=%08x @ "
 				    "%lx, frame_size = %ld\n", info->ip,
 				    insn, npc, frame_size);
@@ -333,6 +336,9 @@
 			}
 		}
 
+		if (frame_size > e->Total_frame_size << 3)
+			frame_size = e->Total_frame_size << 3;
+
 		if (!unwind_special(info, e->region_start, frame_size)) {
 			info->prev_sp = info->sp - frame_size;
 			if (e->Millicode)
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index c1e82e9..a0948f4 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -717,7 +717,7 @@
 #define   MMCR0_FCWAIT	0x00000002UL /* freeze counter in WAIT state */
 #define   MMCR0_FCHV	0x00000001UL /* freeze conditions in hypervisor mode */
 #define SPRN_MMCR1	798
-#define SPRN_MMCR2	769
+#define SPRN_MMCR2	785
 #define SPRN_MMCRA	0x312
 #define   MMCRA_SDSYNC	0x80000000UL /* SDAR synced with SIAR */
 #define   MMCRA_SDAR_DCACHE_MISS 0x40000000UL
@@ -754,13 +754,13 @@
 #define SPRN_PMC6	792
 #define SPRN_PMC7	793
 #define SPRN_PMC8	794
-#define SPRN_SIAR	780
-#define SPRN_SDAR	781
 #define SPRN_SIER	784
 #define   SIER_SIPR		0x2000000	/* Sampled MSR_PR */
 #define   SIER_SIHV		0x1000000	/* Sampled MSR_HV */
 #define   SIER_SIAR_VALID	0x0400000	/* SIAR contents valid */
 #define   SIER_SDAR_VALID	0x0200000	/* SDAR contents valid */
+#define SPRN_SIAR	796
+#define SPRN_SDAR	797
 #define SPRN_TACR	888
 #define SPRN_TCSCR	889
 #define SPRN_CSIGR	890
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index da51925..ccd2037 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -656,6 +656,7 @@
 	W(0xffff0000), W(0x003e0000),	/* POWER6 */
 	W(0xffff0000), W(0x003f0000),	/* POWER7 */
 	W(0xffff0000), W(0x004b0000),	/* POWER8E */
+	W(0xffff0000), W(0x004c0000),   /* POWER8NVL */
 	W(0xffff0000), W(0x004d0000),	/* POWER8 */
 	W(0xffffffff), W(0x0f000004),	/* all 2.07-compliant */
 	W(0xffffffff), W(0x0f000003),	/* all 2.06-compliant */
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 5926896..b2740c6 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -159,6 +159,19 @@
 	},
 };
 
+/*
+ * 'R' and 'C' update notes:
+ *  - Under pHyp or KVM, the updatepp path will not set C, thus it *will*
+ *     create writeable HPTEs without C set, because the hcall H_PROTECT
+ *     that we use in that case will not update C
+ *  - The above is however not a problem, because we also don't do that
+ *     fancy "no flush" variant of eviction and we use H_REMOVE which will
+ *     do the right thing and thus we don't have the race I described earlier
+ *
+ *    - Under bare metal,  we do have the race, so we need R and C set
+ *    - We make sure R is always set and never lost
+ *    - C is _PAGE_DIRTY, and *should* always be set for a writeable mapping
+ */
 unsigned long htab_convert_pte_flags(unsigned long pteflags)
 {
 	unsigned long rflags = 0;
@@ -186,9 +199,14 @@
 			rflags |= 0x1;
 	}
 	/*
-	 * Always add "C" bit for perf. Memory coherence is always enabled
+	 * We can't allow hardware to update hpte bits. Hence always
+	 * set 'R' bit and set 'C' if it is a write fault
+	 * Memory coherence is always enabled
 	 */
-	rflags |=  HPTE_R_C | HPTE_R_M;
+	rflags |=  HPTE_R_R | HPTE_R_M;
+
+	if (pteflags & _PAGE_DIRTY)
+		rflags |= HPTE_R_C;
 	/*
 	 * Add in WIG bits
 	 */
diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c
index eb44511..6703187 100644
--- a/arch/powerpc/mm/pgtable-book3s64.c
+++ b/arch/powerpc/mm/pgtable-book3s64.c
@@ -33,10 +33,7 @@
 	changed = !pmd_same(*(pmdp), entry);
 	if (changed) {
 		__ptep_set_access_flags(pmdp_ptep(pmdp), pmd_pte(entry));
-		/*
-		 * Since we are not supporting SW TLB systems, we don't
-		 * have any thing similar to flush_tlb_page_nohash()
-		 */
+		flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 	}
 	return changed;
 }
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index 18b2c11..c939e6e 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -296,11 +296,6 @@
 void __init radix__early_init_mmu(void)
 {
 	unsigned long lpcr;
-	/*
-	 * setup LPCR UPRT based on mmu_features
-	 */
-	lpcr = mfspr(SPRN_LPCR);
-	mtspr(SPRN_LPCR, lpcr | LPCR_UPRT);
 
 #ifdef CONFIG_PPC_64K_PAGES
 	/* PAGE_SIZE mappings */
@@ -343,8 +338,11 @@
 	__pte_frag_size_shift = H_PTE_FRAG_SIZE_SHIFT;
 
 	radix_init_page_sizes();
-	if (!firmware_has_feature(FW_FEATURE_LPAR))
+	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
+		lpcr = mfspr(SPRN_LPCR);
+		mtspr(SPRN_LPCR, lpcr | LPCR_UPRT);
 		radix_init_partition_table();
+	}
 
 	radix_init_pgtable();
 }
@@ -353,16 +351,15 @@
 {
 	unsigned long lpcr;
 	/*
-	 * setup LPCR UPRT based on mmu_features
+	 * update partition table control register and UPRT
 	 */
-	lpcr = mfspr(SPRN_LPCR);
-	mtspr(SPRN_LPCR, lpcr | LPCR_UPRT);
-	/*
-	 * update partition table control register, 64 K size.
-	 */
-	if (!firmware_has_feature(FW_FEATURE_LPAR))
+	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
+		lpcr = mfspr(SPRN_LPCR);
+		mtspr(SPRN_LPCR, lpcr | LPCR_UPRT);
+
 		mtspr(SPRN_PTCR,
 		      __pa(partition_tb) | (PATB_SIZE_SHIFT - 12));
+	}
 }
 
 void radix__setup_initial_memory_limit(phys_addr_t first_memblock_base,
diff --git a/arch/powerpc/platforms/512x/clock-commonclk.c b/arch/powerpc/platforms/512x/clock-commonclk.c
index c50ea76..6081fbd 100644
--- a/arch/powerpc/platforms/512x/clock-commonclk.c
+++ b/arch/powerpc/platforms/512x/clock-commonclk.c
@@ -221,7 +221,7 @@
 /* convenience wrappers around the common clk API */
 static inline struct clk *mpc512x_clk_fixed(const char *name, int rate)
 {
-	return clk_register_fixed_rate(NULL, name, NULL, CLK_IS_ROOT, rate);
+	return clk_register_fixed_rate(NULL, name, NULL, 0, rate);
 }
 
 static inline struct clk *mpc512x_clk_factor(
diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c
index 84fb984..85c85eb 100644
--- a/arch/powerpc/platforms/cell/spufs/coredump.c
+++ b/arch/powerpc/platforms/cell/spufs/coredump.c
@@ -172,7 +172,7 @@
 	if (rc < 0)
 		goto out;
 
-	skip = roundup(cprm->file->f_pos - total + sz, 4) - cprm->file->f_pos;
+	skip = roundup(cprm->pos - total + sz, 4) - cprm->pos;
 	if (!dump_skip(cprm, skip))
 		goto Eio;
 out:
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index ac3ffd9..3998e0f 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -53,7 +53,6 @@
 static int ibm_slot_error_detail;
 static int ibm_get_config_addr_info;
 static int ibm_get_config_addr_info2;
-static int ibm_configure_bridge;
 static int ibm_configure_pe;
 
 /*
@@ -81,7 +80,14 @@
 	ibm_get_config_addr_info2	= rtas_token("ibm,get-config-addr-info2");
 	ibm_get_config_addr_info	= rtas_token("ibm,get-config-addr-info");
 	ibm_configure_pe		= rtas_token("ibm,configure-pe");
-	ibm_configure_bridge		= rtas_token("ibm,configure-bridge");
+
+	/*
+	 * ibm,configure-pe and ibm,configure-bridge have the same semantics,
+	 * however ibm,configure-pe can be faster.  If we can't find
+	 * ibm,configure-pe then fall back to using ibm,configure-bridge.
+	 */
+	if (ibm_configure_pe == RTAS_UNKNOWN_SERVICE)
+		ibm_configure_pe 	= rtas_token("ibm,configure-bridge");
 
 	/*
 	 * Necessary sanity check. We needn't check "get-config-addr-info"
@@ -93,8 +99,7 @@
 	    (ibm_read_slot_reset_state2 == RTAS_UNKNOWN_SERVICE &&
 	     ibm_read_slot_reset_state == RTAS_UNKNOWN_SERVICE)	||
 	    ibm_slot_error_detail == RTAS_UNKNOWN_SERVICE	||
-	    (ibm_configure_pe == RTAS_UNKNOWN_SERVICE		&&
-	     ibm_configure_bridge == RTAS_UNKNOWN_SERVICE)) {
+	    ibm_configure_pe == RTAS_UNKNOWN_SERVICE) {
 		pr_info("EEH functionality not supported\n");
 		return -EINVAL;
 	}
@@ -615,29 +620,41 @@
 {
 	int config_addr;
 	int ret;
+	/* Waiting 0.2s maximum before skipping configuration */
+	int max_wait = 200;
 
 	/* Figure out the PE address */
 	config_addr = pe->config_addr;
 	if (pe->addr)
 		config_addr = pe->addr;
 
-	/* Use new configure-pe function, if supported */
-	if (ibm_configure_pe != RTAS_UNKNOWN_SERVICE) {
+	while (max_wait > 0) {
 		ret = rtas_call(ibm_configure_pe, 3, 1, NULL,
 				config_addr, BUID_HI(pe->phb->buid),
 				BUID_LO(pe->phb->buid));
-	} else if (ibm_configure_bridge != RTAS_UNKNOWN_SERVICE) {
-		ret = rtas_call(ibm_configure_bridge, 3, 1, NULL,
-				config_addr, BUID_HI(pe->phb->buid),
-				BUID_LO(pe->phb->buid));
-	} else {
-		return -EFAULT;
+
+		if (!ret)
+			return ret;
+
+		/*
+		 * If RTAS returns a delay value that's above 100ms, cut it
+		 * down to 100ms in case firmware made a mistake.  For more
+		 * on how these delay values work see rtas_busy_delay_time
+		 */
+		if (ret > RTAS_EXTENDED_DELAY_MIN+2 &&
+		    ret <= RTAS_EXTENDED_DELAY_MAX)
+			ret = RTAS_EXTENDED_DELAY_MIN+2;
+
+		max_wait -= rtas_busy_delay_time(ret);
+
+		if (max_wait < 0)
+			break;
+
+		rtas_busy_delay(ret);
 	}
 
-	if (ret)
-		pr_warn("%s: Unable to configure bridge PHB#%d-PE#%x (%d)\n",
-			__func__, pe->phb->global_number, pe->addr, ret);
-
+	pr_warn("%s: Unable to configure bridge PHB#%d-PE#%x (%d)\n",
+		__func__, pe->phb->global_number, pe->addr, ret);
 	return ret;
 }
 
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 769af90..7597b42 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -181,19 +181,22 @@
 			     struct kvm_cpuid_entry __user *entries)
 {
 	int r, i;
-	struct kvm_cpuid_entry *cpuid_entries;
+	struct kvm_cpuid_entry *cpuid_entries = NULL;
 
 	r = -E2BIG;
 	if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
 		goto out;
 	r = -ENOMEM;
-	cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry) * cpuid->nent);
-	if (!cpuid_entries)
-		goto out;
-	r = -EFAULT;
-	if (copy_from_user(cpuid_entries, entries,
-			   cpuid->nent * sizeof(struct kvm_cpuid_entry)))
-		goto out_free;
+	if (cpuid->nent) {
+		cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry) *
+					cpuid->nent);
+		if (!cpuid_entries)
+			goto out;
+		r = -EFAULT;
+		if (copy_from_user(cpuid_entries, entries,
+				   cpuid->nent * sizeof(struct kvm_cpuid_entry)))
+			goto out;
+	}
 	for (i = 0; i < cpuid->nent; i++) {
 		vcpu->arch.cpuid_entries[i].function = cpuid_entries[i].function;
 		vcpu->arch.cpuid_entries[i].eax = cpuid_entries[i].eax;
@@ -212,9 +215,8 @@
 	kvm_x86_ops->cpuid_update(vcpu);
 	r = kvm_update_cpuid(vcpu);
 
-out_free:
-	vfree(cpuid_entries);
 out:
+	vfree(cpuid_entries);
 	return r;
 }
 
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 24e8001..def97b3 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -336,12 +336,12 @@
 #ifdef CONFIG_X86_64
 static void __set_spte(u64 *sptep, u64 spte)
 {
-	*sptep = spte;
+	WRITE_ONCE(*sptep, spte);
 }
 
 static void __update_clear_spte_fast(u64 *sptep, u64 spte)
 {
-	*sptep = spte;
+	WRITE_ONCE(*sptep, spte);
 }
 
 static u64 __update_clear_spte_slow(u64 *sptep, u64 spte)
@@ -390,7 +390,7 @@
 	 */
 	smp_wmb();
 
-	ssptep->spte_low = sspte.spte_low;
+	WRITE_ONCE(ssptep->spte_low, sspte.spte_low);
 }
 
 static void __update_clear_spte_fast(u64 *sptep, u64 spte)
@@ -400,7 +400,7 @@
 	ssptep = (union split_spte *)sptep;
 	sspte = (union split_spte)spte;
 
-	ssptep->spte_low = sspte.spte_low;
+	WRITE_ONCE(ssptep->spte_low, sspte.spte_low);
 
 	/*
 	 * If we map the spte from present to nonpresent, we should clear
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c805cf4..902d9da 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2314,6 +2314,7 @@
 	case MSR_AMD64_NB_CFG:
 	case MSR_FAM10H_MMIO_CONF_BASE:
 	case MSR_AMD64_BU_CFG2:
+	case MSR_IA32_PERF_CTL:
 		msr_info->data = 0;
 		break;
 	case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3:
@@ -2972,6 +2973,10 @@
 			      | KVM_VCPUEVENT_VALID_SMM))
 		return -EINVAL;
 
+	if (events->exception.injected &&
+	    (events->exception.nr > 31 || events->exception.nr == NMI_VECTOR))
+		return -EINVAL;
+
 	process_nmi(vcpu);
 	vcpu->arch.exception.pending = events->exception.injected;
 	vcpu->arch.exception.nr = events->exception.nr;
@@ -3036,6 +3041,11 @@
 	if (dbgregs->flags)
 		return -EINVAL;
 
+	if (dbgregs->dr6 & ~0xffffffffull)
+		return -EINVAL;
+	if (dbgregs->dr7 & ~0xffffffffull)
+		return -EINVAL;
+
 	memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db));
 	kvm_update_dr0123(vcpu);
 	vcpu->arch.dr6 = dbgregs->dr6;
@@ -7815,7 +7825,7 @@
 
 	slot = id_to_memslot(slots, id);
 	if (size) {
-		if (WARN_ON(slot->npages))
+		if (slot->npages)
 			return -EEXIST;
 
 		/*
diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
index 0d92d0f..c7ba948 100644
--- a/drivers/acpi/acpi_processor.c
+++ b/drivers/acpi/acpi_processor.c
@@ -331,15 +331,6 @@
 		pr->throttling.duty_width = acpi_gbl_FADT.duty_width;
 
 		pr->pblk = object.processor.pblk_address;
-
-		/*
-		 * We don't care about error returns - we just try to mark
-		 * these reserved so that nobody else is confused into thinking
-		 * that this region might be unused..
-		 *
-		 * (In particular, allocating the IO range for Cardbus)
-		 */
-		request_region(pr->throttling.address, 6, "ACPI CPU throttle");
 	}
 
 	/*
diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c
index 3d5b8a0..c1d138e 100644
--- a/drivers/acpi/acpi_video.c
+++ b/drivers/acpi/acpi_video.c
@@ -754,7 +754,8 @@
 }
 
 int acpi_video_get_levels(struct acpi_device *device,
-			  struct acpi_video_device_brightness **dev_br)
+			  struct acpi_video_device_brightness **dev_br,
+			  int *pmax_level)
 {
 	union acpi_object *obj = NULL;
 	int i, max_level = 0, count = 0, level_ac_battery = 0;
@@ -841,6 +842,8 @@
 
 	br->count = count;
 	*dev_br = br;
+	if (pmax_level)
+		*pmax_level = max_level;
 
 out:
 	kfree(obj);
@@ -869,7 +872,7 @@
 	struct acpi_video_device_brightness *br = NULL;
 	int result = -EINVAL;
 
-	result = acpi_video_get_levels(device->dev, &br);
+	result = acpi_video_get_levels(device->dev, &br, &max_level);
 	if (result)
 		return result;
 	device->brightness = br;
@@ -1737,7 +1740,7 @@
 
 	mutex_lock(&video->device_list_lock);
 	list_for_each_entry(dev, &video->video_device_list, entry) {
-		if (!acpi_video_device_lcd_query_levels(dev, &levels))
+		if (!acpi_video_device_lcd_query_levels(dev->dev->handle, &levels))
 			kfree(levels);
 	}
 	mutex_unlock(&video->device_list_lock);
diff --git a/drivers/acpi/acpica/hwregs.c b/drivers/acpi/acpica/hwregs.c
index 0f18dbc..daceb80 100644
--- a/drivers/acpi/acpica/hwregs.c
+++ b/drivers/acpi/acpica/hwregs.c
@@ -83,27 +83,22 @@
 static u8
 acpi_hw_get_access_bit_width(struct acpi_generic_address *reg, u8 max_bit_width)
 {
-	u64 address;
-
 	if (!reg->access_width) {
+		if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_IO) {
+			max_bit_width = 32;
+		}
+
 		/*
 		 * Detect old register descriptors where only the bit_width field
-		 * makes senses. The target address is copied to handle possible
-		 * alignment issues.
+		 * makes senses.
 		 */
-		ACPI_MOVE_64_TO_64(&address, &reg->address);
-		if (!reg->bit_offset && reg->bit_width &&
+		if (reg->bit_width < max_bit_width &&
+		    !reg->bit_offset && reg->bit_width &&
 		    ACPI_IS_POWER_OF_TWO(reg->bit_width) &&
-		    ACPI_IS_ALIGNED(reg->bit_width, 8) &&
-		    ACPI_IS_ALIGNED(address, reg->bit_width)) {
+		    ACPI_IS_ALIGNED(reg->bit_width, 8)) {
 			return (reg->bit_width);
-		} else {
-			if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_IO) {
-				return (32);
-			} else {
-				return (max_bit_width);
-			}
 		}
+		return (max_bit_width);
 	} else {
 		return (1 << (reg->access_width + 2));
 	}
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 31e8da6..262ca31 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -1051,7 +1051,7 @@
 	 * Maybe EC region is required at bus_scan/acpi_get_devices. So it
 	 * is necessary to enable it as early as possible.
 	 */
-	acpi_boot_ec_enable();
+	acpi_ec_dsdt_probe();
 
 	printk(KERN_INFO PREFIX "Interpreter enabled\n");
 
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 0e70181..73c76d6 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -1446,10 +1446,30 @@
 	return AE_OK;
 }
 
-int __init acpi_boot_ec_enable(void)
+static const struct acpi_device_id ec_device_ids[] = {
+	{"PNP0C09", 0},
+	{"", 0},
+};
+
+int __init acpi_ec_dsdt_probe(void)
 {
-	if (!boot_ec)
+	acpi_status status;
+
+	if (boot_ec)
 		return 0;
+
+	/*
+	 * Finding EC from DSDT if there is no ECDT EC available. When this
+	 * function is invoked, ACPI tables have been fully loaded, we can
+	 * walk namespace now.
+	 */
+	boot_ec = make_acpi_ec();
+	if (!boot_ec)
+		return -ENOMEM;
+	status = acpi_get_devices(ec_device_ids[0].id,
+				  ec_parse_device, boot_ec, NULL);
+	if (ACPI_FAILURE(status) || !boot_ec->handle)
+		return -ENODEV;
 	if (!ec_install_handlers(boot_ec)) {
 		first_ec = boot_ec;
 		return 0;
@@ -1457,11 +1477,6 @@
 	return -EFAULT;
 }
 
-static const struct acpi_device_id ec_device_ids[] = {
-	{"PNP0C09", 0},
-	{"", 0},
-};
-
 #if 0
 /*
  * Some EC firmware variations refuses to respond QR_EC when SCI_EVT is not
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 9bb0773..27cc7fe 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -181,7 +181,7 @@
 
 int acpi_ec_init(void);
 int acpi_ec_ecdt_probe(void);
-int acpi_boot_ec_enable(void);
+int acpi_ec_dsdt_probe(void);
 void acpi_ec_block_transactions(void);
 void acpi_ec_unblock_transactions(void);
 void acpi_ec_unblock_transactions_early(void);
diff --git a/drivers/acpi/processor_throttling.c b/drivers/acpi/processor_throttling.c
index f170d74..c72e648 100644
--- a/drivers/acpi/processor_throttling.c
+++ b/drivers/acpi/processor_throttling.c
@@ -676,6 +676,15 @@
 	if (!pr->flags.throttling)
 		return -ENODEV;
 
+	/*
+	 * We don't care about error returns - we just try to mark
+	 * these reserved so that nobody else is confused into thinking
+	 * that this region might be unused..
+	 *
+	 * (In particular, allocating the IO range for Cardbus)
+	 */
+	request_region(pr->throttling.address, 6, "ACPI CPU throttle");
+
 	pr->throttling.state = 0;
 
 	duty_mask = pr->throttling.state_count - 1;
diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig
index 53ddba2..98efbfc 100644
--- a/drivers/clk/Kconfig
+++ b/drivers/clk/Kconfig
@@ -175,6 +175,7 @@
 config COMMON_CLK_NXP
 	def_bool COMMON_CLK && (ARCH_LPC18XX || ARCH_LPC32XX)
 	select REGMAP_MMIO if ARCH_LPC32XX
+	select MFD_SYSCON if ARCH_LPC18XX
 	---help---
 	  Support for clock providers on NXP platforms.
 
diff --git a/drivers/clk/microchip/clk-pic32mzda.c b/drivers/clk/microchip/clk-pic32mzda.c
index 020a29a..51f5438 100644
--- a/drivers/clk/microchip/clk-pic32mzda.c
+++ b/drivers/clk/microchip/clk-pic32mzda.c
@@ -180,15 +180,15 @@
 
 	/* register fixed rate clocks */
 	clks[POSCCLK] = clk_register_fixed_rate(&pdev->dev, "posc_clk", NULL,
-						CLK_IS_ROOT, 24000000);
+						0, 24000000);
 	clks[FRCCLK] =  clk_register_fixed_rate(&pdev->dev, "frc_clk", NULL,
-						CLK_IS_ROOT, 8000000);
+						0, 8000000);
 	clks[BFRCCLK] = clk_register_fixed_rate(&pdev->dev, "bfrc_clk", NULL,
-						CLK_IS_ROOT, 8000000);
+						0, 8000000);
 	clks[LPRCCLK] = clk_register_fixed_rate(&pdev->dev, "lprc_clk", NULL,
-						CLK_IS_ROOT, 32000);
+						0, 32000);
 	clks[UPLLCLK] = clk_register_fixed_rate(&pdev->dev, "usbphy_clk", NULL,
-						CLK_IS_ROOT, 24000000);
+						0, 24000000);
 	/* fixed rate (optional) clock */
 	if (of_find_property(np, "microchip,pic32mzda-sosc", NULL)) {
 		pr_info("pic32-clk: dt requests SOSC.\n");
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 36bc11a..9009295 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1832,7 +1832,7 @@
 unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy,
 					unsigned int target_freq)
 {
-	clamp_val(target_freq, policy->min, policy->max);
+	target_freq = clamp_val(target_freq, policy->min, policy->max);
 
 	return cpufreq_driver->fast_switch(policy, target_freq);
 }
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 3a9c432..ee367e9 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -449,7 +449,7 @@
 		cpu->acpi_perf_data.states[0].core_frequency =
 					policy->cpuinfo.max_freq / 1000;
 	cpu->valid_pss_table = true;
-	pr_info("_PPC limits will be enforced\n");
+	pr_debug("_PPC limits will be enforced\n");
 
 	return;
 
@@ -1460,6 +1460,9 @@
 
 	intel_pstate_clear_update_util_hook(policy->cpu);
 
+	pr_debug("set_policy cpuinfo.max %u policy->max %u\n",
+		 policy->cpuinfo.max_freq, policy->max);
+
 	cpu = all_cpu_data[0];
 	if (cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate &&
 	    policy->max < policy->cpuinfo.max_freq &&
@@ -1495,13 +1498,13 @@
 				   limits->max_sysfs_pct);
 	limits->max_perf_pct = max(limits->min_policy_pct,
 				   limits->max_perf_pct);
-	limits->max_perf = round_up(limits->max_perf, FRAC_BITS);
 
 	/* Make sure min_perf_pct <= max_perf_pct */
 	limits->min_perf_pct = min(limits->max_perf_pct, limits->min_perf_pct);
 
 	limits->min_perf = div_fp(limits->min_perf_pct, 100);
 	limits->max_perf = div_fp(limits->max_perf_pct, 100);
+	limits->max_perf = round_up(limits->max_perf, FRAC_BITS);
 
  out:
 	intel_pstate_set_update_util_hook(policy->cpu);
@@ -1558,8 +1561,11 @@
 
 	/* cpuinfo and default policy values */
 	policy->cpuinfo.min_freq = cpu->pstate.min_pstate * cpu->pstate.scaling;
-	policy->cpuinfo.max_freq =
-		cpu->pstate.turbo_pstate * cpu->pstate.scaling;
+	update_turbo_state();
+	policy->cpuinfo.max_freq = limits->turbo_disabled ?
+			cpu->pstate.max_pstate : cpu->pstate.turbo_pstate;
+	policy->cpuinfo.max_freq *= cpu->pstate.scaling;
+
 	intel_pstate_init_acpi_perf_limits(policy);
 	policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
 	cpumask_set_cpu(policy->cpu, policy->cpus);
diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index 4a2c07e..6355ab3 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -33,6 +33,7 @@
 #include <linux/seq_file.h>
 #include <linux/poll.h>
 #include <linux/reservation.h>
+#include <linux/mm.h>
 
 #include <uapi/linux/dma-buf.h>
 
@@ -90,7 +91,7 @@
 	dmabuf = file->private_data;
 
 	/* check for overflowing the buffer's size */
-	if (vma->vm_pgoff + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) >
+	if (vma->vm_pgoff + vma_pages(vma) >
 	    dmabuf->size >> PAGE_SHIFT)
 		return -EINVAL;
 
@@ -723,11 +724,11 @@
 		return -EINVAL;
 
 	/* check for offset overflow */
-	if (pgoff + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) < pgoff)
+	if (pgoff + vma_pages(vma) < pgoff)
 		return -EOVERFLOW;
 
 	/* check for overflowing the buffer's size */
-	if (pgoff + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) >
+	if (pgoff + vma_pages(vma) >
 	    dmabuf->size >> PAGE_SHIFT)
 		return -EINVAL;
 
diff --git a/drivers/dma-buf/reservation.c b/drivers/dma-buf/reservation.c
index c0bd572..9566a62 100644
--- a/drivers/dma-buf/reservation.c
+++ b/drivers/dma-buf/reservation.c
@@ -35,6 +35,17 @@
 #include <linux/reservation.h>
 #include <linux/export.h>
 
+/**
+ * DOC: Reservation Object Overview
+ *
+ * The reservation object provides a mechanism to manage shared and
+ * exclusive fences associated with a buffer.  A reservation object
+ * can have attached one exclusive fence (normally associated with
+ * write operations) or N shared fences (read operations).  The RCU
+ * mechanism is used to protect read access to fences from locked
+ * write-side updates.
+ */
+
 DEFINE_WW_CLASS(reservation_ww_class);
 EXPORT_SYMBOL(reservation_ww_class);
 
@@ -43,9 +54,17 @@
 
 const char reservation_seqcount_string[] = "reservation_seqcount";
 EXPORT_SYMBOL(reservation_seqcount_string);
-/*
- * Reserve space to add a shared fence to a reservation_object,
- * must be called with obj->lock held.
+
+/**
+ * reservation_object_reserve_shared - Reserve space to add a shared
+ * fence to a reservation_object.
+ * @obj: reservation object
+ *
+ * Should be called before reservation_object_add_shared_fence().  Must
+ * be called with obj->lock held.
+ *
+ * RETURNS
+ * Zero for success, or -errno
  */
 int reservation_object_reserve_shared(struct reservation_object *obj)
 {
@@ -180,7 +199,11 @@
 		fence_put(old_fence);
 }
 
-/*
+/**
+ * reservation_object_add_shared_fence - Add a fence to a shared slot
+ * @obj: the reservation object
+ * @fence: the shared fence to add
+ *
  * Add a fence to a shared slot, obj->lock must be held, and
  * reservation_object_reserve_shared_fence has been called.
  */
@@ -200,6 +223,13 @@
 }
 EXPORT_SYMBOL(reservation_object_add_shared_fence);
 
+/**
+ * reservation_object_add_excl_fence - Add an exclusive fence.
+ * @obj: the reservation object
+ * @fence: the shared fence to add
+ *
+ * Add a fence to the exclusive slot.  The obj->lock must be held.
+ */
 void reservation_object_add_excl_fence(struct reservation_object *obj,
 				       struct fence *fence)
 {
@@ -233,6 +263,18 @@
 }
 EXPORT_SYMBOL(reservation_object_add_excl_fence);
 
+/**
+ * reservation_object_get_fences_rcu - Get an object's shared and exclusive
+ * fences without update side lock held
+ * @obj: the reservation object
+ * @pfence_excl: the returned exclusive fence (or NULL)
+ * @pshared_count: the number of shared fences returned
+ * @pshared: the array of shared fence ptrs returned (array is krealloc'd to
+ * the required size, and must be freed by caller)
+ *
+ * RETURNS
+ * Zero or -errno
+ */
 int reservation_object_get_fences_rcu(struct reservation_object *obj,
 				      struct fence **pfence_excl,
 				      unsigned *pshared_count,
@@ -319,6 +361,18 @@
 }
 EXPORT_SYMBOL_GPL(reservation_object_get_fences_rcu);
 
+/**
+ * reservation_object_wait_timeout_rcu - Wait on reservation's objects
+ * shared and/or exclusive fences.
+ * @obj: the reservation object
+ * @wait_all: if true, wait on all fences, else wait on just exclusive fence
+ * @intr: if true, do interruptible wait
+ * @timeout: timeout value in jiffies or zero to return immediately
+ *
+ * RETURNS
+ * Returns -ERESTARTSYS if interrupted, 0 if the wait timed out, or
+ * greater than zer on success.
+ */
 long reservation_object_wait_timeout_rcu(struct reservation_object *obj,
 					 bool wait_all, bool intr,
 					 unsigned long timeout)
@@ -416,6 +470,16 @@
 	return ret;
 }
 
+/**
+ * reservation_object_test_signaled_rcu - Test if a reservation object's
+ * fences have been signaled.
+ * @obj: the reservation object
+ * @test_all: if true, test all fences, otherwise only test the exclusive
+ * fence
+ *
+ * RETURNS
+ * true if all fences signaled, else false
+ */
 bool reservation_object_test_signaled_rcu(struct reservation_object *obj,
 					  bool test_all)
 {
diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index 6aa256b0..c3ee3ad 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -565,7 +565,8 @@
 	list_for_each(item, &mc_devices) {
 		mci = list_entry(item, struct mem_ctl_info, link);
 
-		edac_mod_work(&mci->work, value);
+		if (mci->op_state == OP_RUNNING_POLL)
+			edac_mod_work(&mci->work, value);
 	}
 	mutex_unlock(&mem_ctls_mutex);
 }
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index b4d0bf6..6744d88 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -239,8 +239,11 @@
 	{ 0x1a0, 0x1a4, 0x1a8, 0x1ac, 0x1b0, 0x1b4, 0x1b8, 0x1bc },
 };
 
-#define RIR_RNK_TGT(reg)		GET_BITFIELD(reg, 16, 19)
-#define RIR_OFFSET(reg)		GET_BITFIELD(reg,  2, 14)
+#define RIR_RNK_TGT(type, reg) (((type) == BROADWELL) ? \
+	GET_BITFIELD(reg, 20, 23) : GET_BITFIELD(reg, 16, 19))
+
+#define RIR_OFFSET(type, reg) (((type) == HASWELL || (type) == BROADWELL) ? \
+	GET_BITFIELD(reg,  2, 15) : GET_BITFIELD(reg,  2, 14))
 
 /* Device 16, functions 2-7 */
 
@@ -326,6 +329,7 @@
 struct pci_id_table {
 	const struct pci_id_descr	*descr;
 	int				n_devs;
+	enum type			type;
 };
 
 struct sbridge_dev {
@@ -394,9 +398,14 @@
 	{ PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_BR, 0)		},
 };
 
-#define PCI_ID_TABLE_ENTRY(A) { .descr=A, .n_devs = ARRAY_SIZE(A) }
+#define PCI_ID_TABLE_ENTRY(A, T) {	\
+	.descr = A,			\
+	.n_devs = ARRAY_SIZE(A),	\
+	.type = T			\
+}
+
 static const struct pci_id_table pci_dev_descr_sbridge_table[] = {
-	PCI_ID_TABLE_ENTRY(pci_dev_descr_sbridge),
+	PCI_ID_TABLE_ENTRY(pci_dev_descr_sbridge, SANDY_BRIDGE),
 	{0,}			/* 0 terminated list. */
 };
 
@@ -463,7 +472,7 @@
 };
 
 static const struct pci_id_table pci_dev_descr_ibridge_table[] = {
-	PCI_ID_TABLE_ENTRY(pci_dev_descr_ibridge),
+	PCI_ID_TABLE_ENTRY(pci_dev_descr_ibridge, IVY_BRIDGE),
 	{0,}			/* 0 terminated list. */
 };
 
@@ -536,7 +545,7 @@
 };
 
 static const struct pci_id_table pci_dev_descr_haswell_table[] = {
-	PCI_ID_TABLE_ENTRY(pci_dev_descr_haswell),
+	PCI_ID_TABLE_ENTRY(pci_dev_descr_haswell, HASWELL),
 	{0,}			/* 0 terminated list. */
 };
 
@@ -580,7 +589,7 @@
 };
 
 static const struct pci_id_table pci_dev_descr_knl_table[] = {
-	PCI_ID_TABLE_ENTRY(pci_dev_descr_knl),
+	PCI_ID_TABLE_ENTRY(pci_dev_descr_knl, KNIGHTS_LANDING),
 	{0,}
 };
 
@@ -648,7 +657,7 @@
 };
 
 static const struct pci_id_table pci_dev_descr_broadwell_table[] = {
-	PCI_ID_TABLE_ENTRY(pci_dev_descr_broadwell),
+	PCI_ID_TABLE_ENTRY(pci_dev_descr_broadwell, BROADWELL),
 	{0,}			/* 0 terminated list. */
 };
 
@@ -1894,14 +1903,14 @@
 				pci_read_config_dword(pvt->pci_tad[i],
 						      rir_offset[j][k],
 						      &reg);
-				tmp_mb = RIR_OFFSET(reg) << 6;
+				tmp_mb = RIR_OFFSET(pvt->info.type, reg) << 6;
 
 				gb = div_u64_rem(tmp_mb, 1024, &mb);
 				edac_dbg(0, "CH#%d RIR#%d INTL#%d, offset %u.%03u GB (0x%016Lx), tgt: %d, reg=0x%08x\n",
 					 i, j, k,
 					 gb, (mb*1000)/1024,
 					 ((u64)tmp_mb) << 20L,
-					 (u32)RIR_RNK_TGT(reg),
+					 (u32)RIR_RNK_TGT(pvt->info.type, reg),
 					 reg);
 			}
 		}
@@ -2234,7 +2243,7 @@
 	pci_read_config_dword(pvt->pci_tad[ch_add + base_ch],
 			      rir_offset[n_rir][idx],
 			      &reg);
-	*rank = RIR_RNK_TGT(reg);
+	*rank = RIR_RNK_TGT(pvt->info.type, reg);
 
 	edac_dbg(0, "RIR#%d: channel address 0x%08Lx < 0x%08Lx, RIR interleave %d, index %d\n",
 		 n_rir,
@@ -3357,12 +3366,12 @@
 #define ICPU(model, table) \
 	{ X86_VENDOR_INTEL, 6, model, 0, (unsigned long)&table }
 
-/* Order here must match "enum type" */
 static const struct x86_cpu_id sbridge_cpuids[] = {
 	ICPU(0x2d, pci_dev_descr_sbridge_table),	/* SANDY_BRIDGE */
 	ICPU(0x3e, pci_dev_descr_ibridge_table),	/* IVY_BRIDGE */
 	ICPU(0x3f, pci_dev_descr_haswell_table),	/* HASWELL */
 	ICPU(0x4f, pci_dev_descr_broadwell_table),	/* BROADWELL */
+	ICPU(0x56, pci_dev_descr_broadwell_table),	/* BROADWELL-DE */
 	ICPU(0x57, pci_dev_descr_knl_table),		/* KNIGHTS_LANDING */
 	{ }
 };
@@ -3398,7 +3407,7 @@
 			 mc, mc + 1, num_mc);
 
 		sbridge_dev->mc = mc++;
-		rc = sbridge_register_mci(sbridge_dev, id - sbridge_cpuids);
+		rc = sbridge_register_mci(sbridge_dev, ptable->type);
 		if (unlikely(rc < 0))
 			goto fail1;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 992f00b..01c36b8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -799,6 +799,7 @@
 	unsigned		cond_exe_offs;
 	u64				cond_exe_gpu_addr;
 	volatile u32	*cond_exe_cpu_addr;
+	int                     vmid;
 };
 
 /*
@@ -936,7 +937,8 @@
 		    unsigned vm_id, uint64_t pd_addr,
 		    uint32_t gds_base, uint32_t gds_size,
 		    uint32_t gws_base, uint32_t gws_size,
-		    uint32_t oa_base, uint32_t oa_size);
+		    uint32_t oa_base, uint32_t oa_size,
+		    bool vmid_switch);
 void amdgpu_vm_reset_id(struct amdgpu_device *adev, unsigned vm_id);
 uint64_t amdgpu_vm_map_gart(const dma_addr_t *pages_addr, uint64_t addr);
 int amdgpu_vm_update_page_directory(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
index 199f76b..8943099 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
@@ -696,6 +696,17 @@
 	return result;
 }
 
+static int amdgpu_cgs_rel_firmware(struct cgs_device *cgs_device, enum cgs_ucode_id type)
+{
+	CGS_FUNC_ADEV;
+	if ((CGS_UCODE_ID_SMU == type) || (CGS_UCODE_ID_SMU_SK == type)) {
+		release_firmware(adev->pm.fw);
+		return 0;
+	}
+	/* cannot release other firmware because they are not created by cgs */
+	return -EINVAL;
+}
+
 static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device,
 					enum cgs_ucode_id type,
 					struct cgs_firmware_info *info)
@@ -1125,6 +1136,7 @@
 	amdgpu_cgs_pm_query_clock_limits,
 	amdgpu_cgs_set_camera_voltages,
 	amdgpu_cgs_get_firmware_info,
+	amdgpu_cgs_rel_firmware,
 	amdgpu_cgs_set_powergating_state,
 	amdgpu_cgs_set_clockgating_state,
 	amdgpu_cgs_get_active_displays_info,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index bb8b149..964f314 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -827,8 +827,10 @@
  */
 static void amdgpu_atombios_fini(struct amdgpu_device *adev)
 {
-	if (adev->mode_info.atom_context)
+	if (adev->mode_info.atom_context) {
 		kfree(adev->mode_info.atom_context->scratch);
+		kfree(adev->mode_info.atom_context->iio);
+	}
 	kfree(adev->mode_info.atom_context);
 	adev->mode_info.atom_context = NULL;
 	kfree(adev->mode_info.atom_card_info);
@@ -1325,6 +1327,11 @@
 		adev->ip_block_status[i].valid = false;
 	}
 
+	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
+		if (adev->ip_blocks[i].funcs->late_fini)
+			adev->ip_blocks[i].funcs->late_fini((void *)adev);
+	}
+
 	return 0;
 }
 
@@ -1513,8 +1520,7 @@
 		amdgpu_atombios_has_gpu_virtualization_table(adev);
 
 	/* Post card if necessary */
-	if (!amdgpu_card_posted(adev) ||
-	    adev->virtualization.supports_sr_iov) {
+	if (!amdgpu_card_posted(adev)) {
 		if (!adev->bios) {
 			dev_err(adev->dev, "Card not posted and no BIOS - ignoring\n");
 			return -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index 34e3542..7a0b1e5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -122,6 +122,7 @@
 	bool skip_preamble, need_ctx_switch;
 	unsigned patch_offset = ~0;
 	struct amdgpu_vm *vm;
+	int vmid = 0, old_vmid = ring->vmid;
 	struct fence *hwf;
 	uint64_t ctx;
 
@@ -135,9 +136,11 @@
 	if (job) {
 		vm = job->vm;
 		ctx = job->ctx;
+		vmid = job->vm_id;
 	} else {
 		vm = NULL;
 		ctx = 0;
+		vmid = 0;
 	}
 
 	if (!ring->ready) {
@@ -163,7 +166,8 @@
 		r = amdgpu_vm_flush(ring, job->vm_id, job->vm_pd_addr,
 				    job->gds_base, job->gds_size,
 				    job->gws_base, job->gws_size,
-				    job->oa_base, job->oa_size);
+				    job->oa_base, job->oa_size,
+				    (ring->current_ctx == ctx) && (old_vmid != vmid));
 		if (r) {
 			amdgpu_ring_undo(ring);
 			return r;
@@ -180,7 +184,6 @@
 	need_ctx_switch = ring->current_ctx != ctx;
 	for (i = 0; i < num_ibs; ++i) {
 		ib = &ibs[i];
-
 		/* drop preamble IBs if we don't have a context switch */
 		if ((ib->flags & AMDGPU_IB_FLAG_PREAMBLE) && skip_preamble)
 			continue;
@@ -188,6 +191,7 @@
 		amdgpu_ring_emit_ib(ring, ib, job ? job->vm_id : 0,
 				    need_ctx_switch);
 		need_ctx_switch = false;
+		ring->vmid = vmid;
 	}
 
 	if (ring->funcs->emit_hdp_invalidate)
@@ -198,6 +202,7 @@
 		dev_err(adev->dev, "failed to emit fence (%d)\n", r);
 		if (job && job->vm_id)
 			amdgpu_vm_reset_id(adev, job->vm_id);
+		ring->vmid = old_vmid;
 		amdgpu_ring_undo(ring);
 		return r;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c
index 6bd961f..8225655 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c
@@ -183,13 +183,6 @@
 	if (ret)
 		return ret;
 
-#ifdef CONFIG_DRM_AMD_POWERPLAY
-	if (adev->pp_enabled) {
-		amdgpu_pm_sysfs_fini(adev);
-		amd_powerplay_fini(adev->powerplay.pp_handle);
-	}
-#endif
-
 	return ret;
 }
 
@@ -223,6 +216,22 @@
 	return ret;
 }
 
+static void amdgpu_pp_late_fini(void *handle)
+{
+#ifdef CONFIG_DRM_AMD_POWERPLAY
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	if (adev->pp_enabled) {
+		amdgpu_pm_sysfs_fini(adev);
+		amd_powerplay_fini(adev->powerplay.pp_handle);
+	}
+
+	if (adev->powerplay.ip_funcs->late_fini)
+		adev->powerplay.ip_funcs->late_fini(
+			  adev->powerplay.pp_handle);
+#endif
+}
+
 static int amdgpu_pp_suspend(void *handle)
 {
 	int ret = 0;
@@ -311,6 +320,7 @@
 	.sw_fini = amdgpu_pp_sw_fini,
 	.hw_init = amdgpu_pp_hw_init,
 	.hw_fini = amdgpu_pp_hw_fini,
+	.late_fini = amdgpu_pp_late_fini,
 	.suspend = amdgpu_pp_suspend,
 	.resume = amdgpu_pp_resume,
 	.is_idle = amdgpu_pp_is_idle,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index 3b02272..870f949 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -343,6 +343,7 @@
 	ring->ring = NULL;
 	ring->ring_obj = NULL;
 
+	amdgpu_wb_free(ring->adev, ring->cond_exe_offs);
 	amdgpu_wb_free(ring->adev, ring->fence_offs);
 	amdgpu_wb_free(ring->adev, ring->rptr_offs);
 	amdgpu_wb_free(ring->adev, ring->wptr_offs);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
index 8bf84ef..48618ee 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
@@ -115,6 +115,7 @@
 		return r;
 	}
 	r = amdgpu_bo_kmap(sa_manager->bo, &sa_manager->cpu_ptr);
+	memset(sa_manager->cpu_ptr, 0, sa_manager->size);
 	amdgpu_bo_unreserve(sa_manager->bo);
 	return r;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index 01abfc2..e19520c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -253,19 +253,20 @@
 {
 	int r;
 
-	if (adev->uvd.vcpu_bo == NULL)
-		return 0;
+	kfree(adev->uvd.saved_bo);
 
 	amd_sched_entity_fini(&adev->uvd.ring.sched, &adev->uvd.entity);
 
-	r = amdgpu_bo_reserve(adev->uvd.vcpu_bo, false);
-	if (!r) {
-		amdgpu_bo_kunmap(adev->uvd.vcpu_bo);
-		amdgpu_bo_unpin(adev->uvd.vcpu_bo);
-		amdgpu_bo_unreserve(adev->uvd.vcpu_bo);
-	}
+	if (adev->uvd.vcpu_bo) {
+		r = amdgpu_bo_reserve(adev->uvd.vcpu_bo, false);
+		if (!r) {
+			amdgpu_bo_kunmap(adev->uvd.vcpu_bo);
+			amdgpu_bo_unpin(adev->uvd.vcpu_bo);
+			amdgpu_bo_unreserve(adev->uvd.vcpu_bo);
+		}
 
-	amdgpu_bo_unref(&adev->uvd.vcpu_bo);
+		amdgpu_bo_unref(&adev->uvd.vcpu_bo);
+	}
 
 	amdgpu_ring_fini(&adev->uvd.ring);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 9f36ed3..62a4c12 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -298,7 +298,8 @@
 		    unsigned vm_id, uint64_t pd_addr,
 		    uint32_t gds_base, uint32_t gds_size,
 		    uint32_t gws_base, uint32_t gws_size,
-		    uint32_t oa_base, uint32_t oa_size)
+		    uint32_t oa_base, uint32_t oa_size,
+		    bool vmid_switch)
 {
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_vm_id *id = &adev->vm_manager.ids[vm_id];
@@ -312,8 +313,7 @@
 	int r;
 
 	if (ring->funcs->emit_pipeline_sync && (
-	    pd_addr != AMDGPU_VM_NO_FLUSH || gds_switch_needed ||
-		    ring->type == AMDGPU_RING_TYPE_COMPUTE))
+	    pd_addr != AMDGPU_VM_NO_FLUSH || gds_switch_needed || vmid_switch))
 		amdgpu_ring_emit_pipeline_sync(ring);
 
 	if (ring->funcs->emit_vm_flush &&
diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
index ea407db..5ec1f1e 100644
--- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
@@ -6221,6 +6221,9 @@
 	ci_dpm_fini(adev);
 	mutex_unlock(&adev->pm.mutex);
 
+	release_firmware(adev->pm.fw);
+	adev->pm.fw = NULL;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
index 518dca4..9dc4e24 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
@@ -66,6 +66,16 @@
 
 u32 amdgpu_cik_gpu_check_soft_reset(struct amdgpu_device *adev);
 
+
+static void cik_sdma_free_microcode(struct amdgpu_device *adev)
+{
+	int i;
+	for (i = 0; i < adev->sdma.num_instances; i++) {
+			release_firmware(adev->sdma.instance[i].fw);
+			adev->sdma.instance[i].fw = NULL;
+	}
+}
+
 /*
  * sDMA - System DMA
  * Starting with CIK, the GPU has new asynchronous
@@ -419,6 +429,8 @@
 		/* Initialize the ring buffer's read and write pointers */
 		WREG32(mmSDMA0_GFX_RB_RPTR + sdma_offsets[i], 0);
 		WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[i], 0);
+		WREG32(mmSDMA0_GFX_IB_RPTR + sdma_offsets[i], 0);
+		WREG32(mmSDMA0_GFX_IB_OFFSET + sdma_offsets[i], 0);
 
 		/* set the wb address whether it's enabled or not */
 		WREG32(mmSDMA0_GFX_RB_RPTR_ADDR_HI + sdma_offsets[i],
@@ -446,7 +458,12 @@
 		WREG32(mmSDMA0_GFX_IB_CNTL + sdma_offsets[i], ib_cntl);
 
 		ring->ready = true;
+	}
 
+	cik_sdma_enable(adev, true);
+
+	for (i = 0; i < adev->sdma.num_instances; i++) {
+		ring = &adev->sdma.instance[i].ring;
 		r = amdgpu_ring_test_ring(ring);
 		if (r) {
 			ring->ready = false;
@@ -529,8 +546,8 @@
 	if (r)
 		return r;
 
-	/* unhalt the MEs */
-	cik_sdma_enable(adev, true);
+	/* halt the engine before programing */
+	cik_sdma_enable(adev, false);
 
 	/* start the gfx rings and rlc compute queues */
 	r = cik_sdma_gfx_resume(adev);
@@ -998,6 +1015,7 @@
 	for (i = 0; i < adev->sdma.num_instances; i++)
 		amdgpu_ring_fini(&adev->sdma.instance[i].ring);
 
+	cik_sdma_free_microcode(adev);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/fiji_dpm.c b/drivers/gpu/drm/amd/amdgpu/fiji_dpm.c
index 245cabf..ed03b75 100644
--- a/drivers/gpu/drm/amd/amdgpu/fiji_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/fiji_dpm.c
@@ -72,6 +72,11 @@
 
 static int fiji_dpm_sw_fini(void *handle)
 {
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	release_firmware(adev->pm.fw);
+	adev->pm.fw = NULL;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 7f18a53..8c6ad1e 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -991,6 +991,22 @@
 	return err;
 }
 
+static void gfx_v7_0_free_microcode(struct amdgpu_device *adev)
+{
+	release_firmware(adev->gfx.pfp_fw);
+	adev->gfx.pfp_fw = NULL;
+	release_firmware(adev->gfx.me_fw);
+	adev->gfx.me_fw = NULL;
+	release_firmware(adev->gfx.ce_fw);
+	adev->gfx.ce_fw = NULL;
+	release_firmware(adev->gfx.mec_fw);
+	adev->gfx.mec_fw = NULL;
+	release_firmware(adev->gfx.mec2_fw);
+	adev->gfx.mec2_fw = NULL;
+	release_firmware(adev->gfx.rlc_fw);
+	adev->gfx.rlc_fw = NULL;
+}
+
 /**
  * gfx_v7_0_tiling_mode_table_init - init the hw tiling table
  *
@@ -4489,6 +4505,7 @@
 	gfx_v7_0_cp_compute_fini(adev);
 	gfx_v7_0_rlc_fini(adev);
 	gfx_v7_0_mec_fini(adev);
+	gfx_v7_0_free_microcode(adev);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index f19bab6..9f6f866 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -836,6 +836,26 @@
 	return r;
 }
 
+
+static void gfx_v8_0_free_microcode(struct amdgpu_device *adev) {
+	release_firmware(adev->gfx.pfp_fw);
+	adev->gfx.pfp_fw = NULL;
+	release_firmware(adev->gfx.me_fw);
+	adev->gfx.me_fw = NULL;
+	release_firmware(adev->gfx.ce_fw);
+	adev->gfx.ce_fw = NULL;
+	release_firmware(adev->gfx.rlc_fw);
+	adev->gfx.rlc_fw = NULL;
+	release_firmware(adev->gfx.mec_fw);
+	adev->gfx.mec_fw = NULL;
+	if ((adev->asic_type != CHIP_STONEY) &&
+	    (adev->asic_type != CHIP_TOPAZ))
+		release_firmware(adev->gfx.mec2_fw);
+	adev->gfx.mec2_fw = NULL;
+
+	kfree(adev->gfx.rlc.register_list_format);
+}
+
 static int gfx_v8_0_init_microcode(struct amdgpu_device *adev)
 {
 	const char *chip_name;
@@ -1983,7 +2003,7 @@
 
 	gfx_v8_0_rlc_fini(adev);
 
-	kfree(adev->gfx.rlc.register_list_format);
+	gfx_v8_0_free_microcode(adev);
 
 	return 0;
 }
@@ -3974,11 +3994,15 @@
 		amdgpu_ring_write(ring, 0x3a00161a);
 		amdgpu_ring_write(ring, 0x0000002e);
 		break;
-	case CHIP_TOPAZ:
 	case CHIP_CARRIZO:
 		amdgpu_ring_write(ring, 0x00000002);
 		amdgpu_ring_write(ring, 0x00000000);
 		break;
+	case CHIP_TOPAZ:
+		amdgpu_ring_write(ring, adev->gfx.config.num_rbs == 1 ?
+				0x00000000 : 0x00000002);
+		amdgpu_ring_write(ring, 0x00000000);
+		break;
 	case CHIP_STONEY:
 		amdgpu_ring_write(ring, 0x00000000);
 		amdgpu_ring_write(ring, 0x00000000);
diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_dpm.c b/drivers/gpu/drm/amd/amdgpu/iceland_dpm.c
index 460bc8a..825ccd6 100644
--- a/drivers/gpu/drm/amd/amdgpu/iceland_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/iceland_dpm.c
@@ -72,6 +72,11 @@
 
 static int iceland_dpm_sw_fini(void *handle)
 {
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	release_firmware(adev->pm.fw);
+	adev->pm.fw = NULL;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
index f4c3130..b556bd0 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
@@ -105,6 +105,15 @@
 	}
 }
 
+static void sdma_v2_4_free_microcode(struct amdgpu_device *adev)
+{
+	int i;
+	for (i = 0; i < adev->sdma.num_instances; i++) {
+		release_firmware(adev->sdma.instance[i].fw);
+		adev->sdma.instance[i].fw = NULL;
+	}
+}
+
 /**
  * sdma_v2_4_init_microcode - load ucode images from disk
  *
@@ -461,6 +470,8 @@
 		/* Initialize the ring buffer's read and write pointers */
 		WREG32(mmSDMA0_GFX_RB_RPTR + sdma_offsets[i], 0);
 		WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[i], 0);
+		WREG32(mmSDMA0_GFX_IB_RPTR + sdma_offsets[i], 0);
+		WREG32(mmSDMA0_GFX_IB_OFFSET + sdma_offsets[i], 0);
 
 		/* set the wb address whether it's enabled or not */
 		WREG32(mmSDMA0_GFX_RB_RPTR_ADDR_HI + sdma_offsets[i],
@@ -489,7 +500,11 @@
 		WREG32(mmSDMA0_GFX_IB_CNTL + sdma_offsets[i], ib_cntl);
 
 		ring->ready = true;
+	}
 
+	sdma_v2_4_enable(adev, true);
+	for (i = 0; i < adev->sdma.num_instances; i++) {
+		ring = &adev->sdma.instance[i].ring;
 		r = amdgpu_ring_test_ring(ring);
 		if (r) {
 			ring->ready = false;
@@ -580,8 +595,8 @@
 			return -EINVAL;
 	}
 
-	/* unhalt the MEs */
-	sdma_v2_4_enable(adev, true);
+	/* halt the engine before programing */
+	sdma_v2_4_enable(adev, false);
 
 	/* start the gfx rings and rlc compute queues */
 	r = sdma_v2_4_gfx_resume(adev);
@@ -1012,6 +1027,7 @@
 	for (i = 0; i < adev->sdma.num_instances; i++)
 		amdgpu_ring_fini(&adev->sdma.instance[i].ring);
 
+	sdma_v2_4_free_microcode(adev);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index 31d99b00..532ea88 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -236,6 +236,15 @@
 	}
 }
 
+static void sdma_v3_0_free_microcode(struct amdgpu_device *adev)
+{
+	int i;
+	for (i = 0; i < adev->sdma.num_instances; i++) {
+		release_firmware(adev->sdma.instance[i].fw);
+		adev->sdma.instance[i].fw = NULL;
+	}
+}
+
 /**
  * sdma_v3_0_init_microcode - load ucode images from disk
  *
@@ -672,6 +681,8 @@
 		/* Initialize the ring buffer's read and write pointers */
 		WREG32(mmSDMA0_GFX_RB_RPTR + sdma_offsets[i], 0);
 		WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[i], 0);
+		WREG32(mmSDMA0_GFX_IB_RPTR + sdma_offsets[i], 0);
+		WREG32(mmSDMA0_GFX_IB_OFFSET + sdma_offsets[i], 0);
 
 		/* set the wb address whether it's enabled or not */
 		WREG32(mmSDMA0_GFX_RB_RPTR_ADDR_HI + sdma_offsets[i],
@@ -711,7 +722,15 @@
 		WREG32(mmSDMA0_GFX_IB_CNTL + sdma_offsets[i], ib_cntl);
 
 		ring->ready = true;
+	}
 
+	/* unhalt the MEs */
+	sdma_v3_0_enable(adev, true);
+	/* enable sdma ring preemption */
+	sdma_v3_0_ctx_switch_enable(adev, true);
+
+	for (i = 0; i < adev->sdma.num_instances; i++) {
+		ring = &adev->sdma.instance[i].ring;
 		r = amdgpu_ring_test_ring(ring);
 		if (r) {
 			ring->ready = false;
@@ -804,10 +823,9 @@
 		}
 	}
 
-	/* unhalt the MEs */
-	sdma_v3_0_enable(adev, true);
-	/* enable sdma ring preemption */
-	sdma_v3_0_ctx_switch_enable(adev, true);
+	/* disble sdma engine before programing it */
+	sdma_v3_0_ctx_switch_enable(adev, false);
+	sdma_v3_0_enable(adev, false);
 
 	/* start the gfx rings and rlc compute queues */
 	r = sdma_v3_0_gfx_resume(adev);
@@ -1247,6 +1265,7 @@
 	for (i = 0; i < adev->sdma.num_instances; i++)
 		amdgpu_ring_fini(&adev->sdma.instance[i].ring);
 
+	sdma_v3_0_free_microcode(adev);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c b/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c
index b7615ce..f06f6f4 100644
--- a/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c
@@ -71,6 +71,11 @@
 
 static int tonga_dpm_sw_fini(void *handle)
 {
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	release_firmware(adev->pm.fw);
+	adev->pm.fw = NULL;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index 6080951..afce1ed 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -157,6 +157,7 @@
 	int (*hw_init)(void *handle);
 	/* tears down the hw state */
 	int (*hw_fini)(void *handle);
+	void (*late_fini)(void *handle);
 	/* handles IP specific hw/sw changes for suspend */
 	int (*suspend)(void *handle);
 	/* handles IP specific hw/sw changes for resume */
diff --git a/drivers/gpu/drm/amd/include/cgs_common.h b/drivers/gpu/drm/amd/include/cgs_common.h
index a461e15..7464daf 100644
--- a/drivers/gpu/drm/amd/include/cgs_common.h
+++ b/drivers/gpu/drm/amd/include/cgs_common.h
@@ -581,6 +581,9 @@
 				     enum cgs_ucode_id type,
 				     struct cgs_firmware_info *info);
 
+typedef int (*cgs_rel_firmware)(struct cgs_device *cgs_device,
+					 enum cgs_ucode_id type);
+
 typedef int(*cgs_set_powergating_state)(struct cgs_device *cgs_device,
 				  enum amd_ip_block_type block_type,
 				  enum amd_powergating_state state);
@@ -645,6 +648,7 @@
 	cgs_set_camera_voltages_t set_camera_voltages;
 	/* Firmware Info */
 	cgs_get_firmware_info get_firmware_info;
+	cgs_rel_firmware rel_firmware;
 	/* cg pg interface*/
 	cgs_set_powergating_state set_powergating_state;
 	cgs_set_clockgating_state set_clockgating_state;
@@ -738,6 +742,8 @@
 	CGS_CALL(set_camera_voltages,dev,mask,voltages)
 #define cgs_get_firmware_info(dev, type, info)	\
 	CGS_CALL(get_firmware_info, dev, type, info)
+#define cgs_rel_firmware(dev, type)	\
+	CGS_CALL(rel_firmware, dev, type)
 #define cgs_set_powergating_state(dev, block_type, state)	\
 	CGS_CALL(set_powergating_state, dev, block_type, state)
 #define cgs_set_clockgating_state(dev, block_type, state)	\
diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
index 8e345bf..e629f8a 100644
--- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
@@ -73,11 +73,14 @@
 
 	ret = hwmgr->hwmgr_func->backend_init(hwmgr);
 	if (ret)
-		goto err;
+		goto err1;
 
 	pr_info("amdgpu: powerplay initialized\n");
 
 	return 0;
+err1:
+	if (hwmgr->pptable_func->pptable_fini)
+		hwmgr->pptable_func->pptable_fini(hwmgr);
 err:
 	pr_err("amdgpu: powerplay initialization failed\n");
 	return ret;
@@ -100,6 +103,9 @@
 	if (hwmgr->hwmgr_func->backend_fini != NULL)
 		ret = hwmgr->hwmgr_func->backend_fini(hwmgr);
 
+	if (hwmgr->pptable_func->pptable_fini)
+		hwmgr->pptable_func->pptable_fini(hwmgr);
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c b/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c
index 46410e3..fb88e4e 100644
--- a/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c
@@ -58,9 +58,6 @@
 	pem_unregister_interrupts(eventmgr);
 
 	pem_handle_event(eventmgr, AMD_PP_EVENT_UNINITIALIZE, &event_data);
-
-	if (eventmgr != NULL)
-		kfree(eventmgr);
 }
 
 int eventmgr_init(struct pp_instance *handle)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c
index 24a16e4..586f732 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c
@@ -1830,7 +1830,7 @@
 
 	PP_ASSERT_WITH_CODE(false,
 			"VDDCI is larger than max VDDCI in VDDCI Voltage Table!",
-			return vddci_table->entries[i].value);
+			return vddci_table->entries[i-1].value);
 }
 
 static int fiji_get_dependency_volt_by_clk(struct pp_hwmgr *hwmgr,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
index 1c48917..20f20e0 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
@@ -93,6 +93,13 @@
 	if (hwmgr == NULL || hwmgr->ps == NULL)
 		return -EINVAL;
 
+	/* do hwmgr finish*/
+	kfree(hwmgr->backend);
+
+	kfree(hwmgr->start_thermal_controller.function_list);
+
+	kfree(hwmgr->set_temperature_range.function_list);
+
 	kfree(hwmgr->ps);
 	kfree(hwmgr);
 	return 0;
@@ -462,7 +469,7 @@
 
 	PP_ASSERT_WITH_CODE(false,
 			"VDDCI is larger than max VDDCI in VDDCI Voltage Table!",
-			return vddci_table->entries[i].value);
+			return vddci_table->entries[i-1].value);
 }
 
 int phm_find_boot_level(void *table,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_powertune.c b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_powertune.c
index 0b99ab3..ae96f14 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_powertune.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_powertune.c
@@ -286,7 +286,7 @@
 
 		if (polaris10_copy_bytes_to_smc(hwmgr->smumgr, pm_fuse_table_offset,
 				(uint8_t *)&data->power_tune_table,
-				sizeof(struct SMU74_Discrete_PmFuses), data->sram_end))
+				(sizeof(struct SMU74_Discrete_PmFuses) - 92), data->sram_end))
 			PP_ASSERT_WITH_CODE(false,
 					"Attempt to download PmFuseTable Failed!",
 					return -EINVAL);
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c
index 16fed48..d27e8c4 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c
@@ -2847,27 +2847,6 @@
 		}
 	}
 
-	/* Initialize Vddc DPM table based on allow Vddc values.  And populate corresponding std values. */
-	for (i = 0; i < allowed_vdd_sclk_table->count; i++) {
-		data->dpm_table.vddc_table.dpm_levels[i].value = allowed_vdd_mclk_table->entries[i].vddc;
-		/* tonga_hwmgr->dpm_table.VddcTable.dpm_levels[i].param1 = stdVoltageTable->entries[i].Leakage; */
-		/* param1 is for corresponding std voltage */
-		data->dpm_table.vddc_table.dpm_levels[i].enabled = 1;
-	}
-	data->dpm_table.vddc_table.count = allowed_vdd_sclk_table->count;
-
-	if (NULL != allowed_vdd_mclk_table) {
-		/* Initialize Vddci DPM table based on allow Mclk values */
-		for (i = 0; i < allowed_vdd_mclk_table->count; i++) {
-			data->dpm_table.vdd_ci_table.dpm_levels[i].value = allowed_vdd_mclk_table->entries[i].vddci;
-			data->dpm_table.vdd_ci_table.dpm_levels[i].enabled = 1;
-			data->dpm_table.mvdd_table.dpm_levels[i].value = allowed_vdd_mclk_table->entries[i].mvdd;
-			data->dpm_table.mvdd_table.dpm_levels[i].enabled = 1;
-		}
-		data->dpm_table.vdd_ci_table.count = allowed_vdd_mclk_table->count;
-		data->dpm_table.mvdd_table.count = allowed_vdd_mclk_table->count;
-	}
-
 	/* setup PCIE gen speed levels*/
 	tonga_setup_default_pcie_tables(hwmgr);
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c
index 10e3630..296ec7e 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c
@@ -1040,48 +1040,44 @@
 	struct phm_ppt_v1_information *pp_table_information =
 		(struct phm_ppt_v1_information *)(hwmgr->pptable);
 
-	if (NULL != hwmgr->soft_pp_table) {
-		kfree(hwmgr->soft_pp_table);
+	if (NULL != hwmgr->soft_pp_table)
 		hwmgr->soft_pp_table = NULL;
-	}
 
-	if (NULL != pp_table_information->vdd_dep_on_sclk)
-		pp_table_information->vdd_dep_on_sclk = NULL;
+	kfree(pp_table_information->vdd_dep_on_sclk);
+	pp_table_information->vdd_dep_on_sclk = NULL;
 
-	if (NULL != pp_table_information->vdd_dep_on_mclk)
-		pp_table_information->vdd_dep_on_mclk = NULL;
+	kfree(pp_table_information->vdd_dep_on_mclk);
+	pp_table_information->vdd_dep_on_mclk = NULL;
 
-	if (NULL != pp_table_information->valid_mclk_values)
-		pp_table_information->valid_mclk_values = NULL;
+	kfree(pp_table_information->valid_mclk_values);
+	pp_table_information->valid_mclk_values = NULL;
 
-	if (NULL != pp_table_information->valid_sclk_values)
-		pp_table_information->valid_sclk_values = NULL;
+	kfree(pp_table_information->valid_sclk_values);
+	pp_table_information->valid_sclk_values = NULL;
 
-	if (NULL != pp_table_information->vddc_lookup_table)
-		pp_table_information->vddc_lookup_table = NULL;
+	kfree(pp_table_information->vddc_lookup_table);
+	pp_table_information->vddc_lookup_table = NULL;
 
-	if (NULL != pp_table_information->vddgfx_lookup_table)
-		pp_table_information->vddgfx_lookup_table = NULL;
+	kfree(pp_table_information->vddgfx_lookup_table);
+	pp_table_information->vddgfx_lookup_table = NULL;
 
-	if (NULL != pp_table_information->mm_dep_table)
-		pp_table_information->mm_dep_table = NULL;
+	kfree(pp_table_information->mm_dep_table);
+	pp_table_information->mm_dep_table = NULL;
 
-	if (NULL != pp_table_information->cac_dtp_table)
-		pp_table_information->cac_dtp_table = NULL;
+	kfree(pp_table_information->cac_dtp_table);
+	pp_table_information->cac_dtp_table = NULL;
 
-	if (NULL != hwmgr->dyn_state.cac_dtp_table)
-		hwmgr->dyn_state.cac_dtp_table = NULL;
+	kfree(hwmgr->dyn_state.cac_dtp_table);
+	hwmgr->dyn_state.cac_dtp_table = NULL;
 
-	if (NULL != pp_table_information->ppm_parameter_table)
-		pp_table_information->ppm_parameter_table = NULL;
+	kfree(pp_table_information->ppm_parameter_table);
+	pp_table_information->ppm_parameter_table = NULL;
 
-	if (NULL != pp_table_information->pcie_table)
-		pp_table_information->pcie_table = NULL;
+	kfree(pp_table_information->pcie_table);
+	pp_table_information->pcie_table = NULL;
 
-	if (NULL != hwmgr->pptable) {
-		kfree(hwmgr->pptable);
-		hwmgr->pptable = NULL;
-	}
+	kfree(hwmgr->pptable);
+	hwmgr->pptable = NULL;
 
 	return result;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c
index 673a75c..8e52a2e 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c
@@ -1006,10 +1006,16 @@
 
 static int fiji_smu_fini(struct pp_smumgr *smumgr)
 {
+	struct fiji_smumgr *priv = (struct fiji_smumgr *)(smumgr->backend);
+
+	smu_free_memory(smumgr->device, (void *)priv->header_buffer.handle);
+
 	if (smumgr->backend) {
 		kfree(smumgr->backend);
 		smumgr->backend = NULL;
 	}
+
+	cgs_rel_firmware(smumgr->device, CGS_UCODE_ID_SMU);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
index de618ea..043b6ac 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
@@ -469,6 +469,7 @@
 		kfree(smumgr->backend);
 		smumgr->backend = NULL;
 	}
+	cgs_rel_firmware(smumgr->device, CGS_UCODE_ID_SMU);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c
index c483baf..0728c1e3 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c
@@ -81,6 +81,7 @@
 
 int smum_fini(struct pp_smumgr *smumgr)
 {
+	kfree(smumgr->device);
 	kfree(smumgr);
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c
index 32820b6..b22722e 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c
@@ -328,10 +328,17 @@
 
 static int tonga_smu_fini(struct pp_smumgr *smumgr)
 {
+	struct tonga_smumgr *priv = (struct tonga_smumgr *)(smumgr->backend);
+
+	smu_free_memory(smumgr->device, (void *)priv->smu_buffer.handle);
+	smu_free_memory(smumgr->device, (void *)priv->header_buffer.handle);
+
 	if (smumgr->backend != NULL) {
 		kfree(smumgr->backend);
 		smumgr->backend = NULL;
 	}
+
+	cgs_rel_firmware(smumgr->device, CGS_UCODE_ID_SMU);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/arm/hdlcd_crtc.c b/drivers/gpu/drm/arm/hdlcd_crtc.c
index fef1b04..0813c2f 100644
--- a/drivers/gpu/drm/arm/hdlcd_crtc.c
+++ b/drivers/gpu/drm/arm/hdlcd_crtc.c
@@ -33,8 +33,17 @@
  *
  */
 
+static void hdlcd_crtc_cleanup(struct drm_crtc *crtc)
+{
+	struct hdlcd_drm_private *hdlcd = crtc_to_hdlcd_priv(crtc);
+
+	/* stop the controller on cleanup */
+	hdlcd_write(hdlcd, HDLCD_REG_COMMAND, 0);
+	drm_crtc_cleanup(crtc);
+}
+
 static const struct drm_crtc_funcs hdlcd_crtc_funcs = {
-	.destroy = drm_crtc_cleanup,
+	.destroy = hdlcd_crtc_cleanup,
 	.set_config = drm_atomic_helper_set_config,
 	.page_flip = drm_atomic_helper_page_flip,
 	.reset = drm_atomic_helper_crtc_reset,
@@ -97,7 +106,7 @@
 	struct hdlcd_drm_private *hdlcd = crtc_to_hdlcd_priv(crtc);
 	struct drm_display_mode *m = &crtc->state->adjusted_mode;
 	struct videomode vm;
-	unsigned int polarities, line_length, err;
+	unsigned int polarities, err;
 
 	vm.vfront_porch = m->crtc_vsync_start - m->crtc_vdisplay;
 	vm.vback_porch = m->crtc_vtotal - m->crtc_vsync_end;
@@ -113,23 +122,18 @@
 	if (m->flags & DRM_MODE_FLAG_PVSYNC)
 		polarities |= HDLCD_POLARITY_VSYNC;
 
-	line_length = crtc->primary->state->fb->pitches[0];
-
 	/* Allow max number of outstanding requests and largest burst size */
 	hdlcd_write(hdlcd, HDLCD_REG_BUS_OPTIONS,
 		    HDLCD_BUS_MAX_OUTSTAND | HDLCD_BUS_BURST_16);
 
-	hdlcd_write(hdlcd, HDLCD_REG_FB_LINE_LENGTH, line_length);
-	hdlcd_write(hdlcd, HDLCD_REG_FB_LINE_PITCH, line_length);
-	hdlcd_write(hdlcd, HDLCD_REG_FB_LINE_COUNT, m->crtc_vdisplay - 1);
 	hdlcd_write(hdlcd, HDLCD_REG_V_DATA, m->crtc_vdisplay - 1);
 	hdlcd_write(hdlcd, HDLCD_REG_V_BACK_PORCH, vm.vback_porch - 1);
 	hdlcd_write(hdlcd, HDLCD_REG_V_FRONT_PORCH, vm.vfront_porch - 1);
 	hdlcd_write(hdlcd, HDLCD_REG_V_SYNC, vm.vsync_len - 1);
+	hdlcd_write(hdlcd, HDLCD_REG_H_DATA, m->crtc_hdisplay - 1);
 	hdlcd_write(hdlcd, HDLCD_REG_H_BACK_PORCH, vm.hback_porch - 1);
 	hdlcd_write(hdlcd, HDLCD_REG_H_FRONT_PORCH, vm.hfront_porch - 1);
 	hdlcd_write(hdlcd, HDLCD_REG_H_SYNC, vm.hsync_len - 1);
-	hdlcd_write(hdlcd, HDLCD_REG_H_DATA, m->crtc_hdisplay - 1);
 	hdlcd_write(hdlcd, HDLCD_REG_POLARITIES, polarities);
 
 	err = hdlcd_set_pxl_fmt(crtc);
@@ -144,20 +148,19 @@
 	struct hdlcd_drm_private *hdlcd = crtc_to_hdlcd_priv(crtc);
 
 	clk_prepare_enable(hdlcd->clk);
+	hdlcd_crtc_mode_set_nofb(crtc);
 	hdlcd_write(hdlcd, HDLCD_REG_COMMAND, 1);
-	drm_crtc_vblank_on(crtc);
 }
 
 static void hdlcd_crtc_disable(struct drm_crtc *crtc)
 {
 	struct hdlcd_drm_private *hdlcd = crtc_to_hdlcd_priv(crtc);
 
-	if (!crtc->primary->fb)
+	if (!crtc->state->active)
 		return;
 
-	clk_disable_unprepare(hdlcd->clk);
 	hdlcd_write(hdlcd, HDLCD_REG_COMMAND, 0);
-	drm_crtc_vblank_off(crtc);
+	clk_disable_unprepare(hdlcd->clk);
 }
 
 static int hdlcd_crtc_atomic_check(struct drm_crtc *crtc,
@@ -179,20 +182,17 @@
 static void hdlcd_crtc_atomic_begin(struct drm_crtc *crtc,
 				    struct drm_crtc_state *state)
 {
-	struct hdlcd_drm_private *hdlcd = crtc_to_hdlcd_priv(crtc);
-	unsigned long flags;
+	struct drm_pending_vblank_event *event = crtc->state->event;
 
-	if (crtc->state->event) {
-		struct drm_pending_vblank_event *event = crtc->state->event;
-
+	if (event) {
 		crtc->state->event = NULL;
-		event->pipe = drm_crtc_index(crtc);
 
-		WARN_ON(drm_crtc_vblank_get(crtc) != 0);
-
-		spin_lock_irqsave(&crtc->dev->event_lock, flags);
-		list_add_tail(&event->base.link, &hdlcd->event_list);
-		spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
+		spin_lock_irq(&crtc->dev->event_lock);
+		if (drm_crtc_vblank_get(crtc) == 0)
+			drm_crtc_arm_vblank_event(crtc, event);
+		else
+			drm_crtc_send_vblank_event(crtc, event);
+		spin_unlock_irq(&crtc->dev->event_lock);
 	}
 }
 
@@ -225,6 +225,15 @@
 static int hdlcd_plane_atomic_check(struct drm_plane *plane,
 				    struct drm_plane_state *state)
 {
+	u32 src_w, src_h;
+
+	src_w = state->src_w >> 16;
+	src_h = state->src_h >> 16;
+
+	/* we can't do any scaling of the plane source */
+	if ((src_w != state->crtc_w) || (src_h != state->crtc_h))
+		return -EINVAL;
+
 	return 0;
 }
 
@@ -233,20 +242,31 @@
 {
 	struct hdlcd_drm_private *hdlcd;
 	struct drm_gem_cma_object *gem;
+	unsigned int depth, bpp;
+	u32 src_w, src_h, dest_w, dest_h;
 	dma_addr_t scanout_start;
 
-	if (!plane->state->crtc || !plane->state->fb)
+	if (!plane->state->fb)
 		return;
 
-	hdlcd = crtc_to_hdlcd_priv(plane->state->crtc);
+	drm_fb_get_bpp_depth(plane->state->fb->pixel_format, &depth, &bpp);
+	src_w = plane->state->src_w >> 16;
+	src_h = plane->state->src_h >> 16;
+	dest_w = plane->state->crtc_w;
+	dest_h = plane->state->crtc_h;
 	gem = drm_fb_cma_get_gem_obj(plane->state->fb, 0);
-	scanout_start = gem->paddr;
+	scanout_start = gem->paddr + plane->state->fb->offsets[0] +
+		plane->state->crtc_y * plane->state->fb->pitches[0] +
+		plane->state->crtc_x * bpp / 8;
+
+	hdlcd = plane->dev->dev_private;
+	hdlcd_write(hdlcd, HDLCD_REG_FB_LINE_LENGTH, plane->state->fb->pitches[0]);
+	hdlcd_write(hdlcd, HDLCD_REG_FB_LINE_PITCH, plane->state->fb->pitches[0]);
+	hdlcd_write(hdlcd, HDLCD_REG_FB_LINE_COUNT, dest_h - 1);
 	hdlcd_write(hdlcd, HDLCD_REG_FB_BASE, scanout_start);
 }
 
 static const struct drm_plane_helper_funcs hdlcd_plane_helper_funcs = {
-	.prepare_fb = NULL,
-	.cleanup_fb = NULL,
 	.atomic_check = hdlcd_plane_atomic_check,
 	.atomic_update = hdlcd_plane_atomic_update,
 };
@@ -294,16 +314,6 @@
 	return plane;
 }
 
-void hdlcd_crtc_suspend(struct drm_crtc *crtc)
-{
-	hdlcd_crtc_disable(crtc);
-}
-
-void hdlcd_crtc_resume(struct drm_crtc *crtc)
-{
-	hdlcd_crtc_enable(crtc);
-}
-
 int hdlcd_setup_crtc(struct drm_device *drm)
 {
 	struct hdlcd_drm_private *hdlcd = drm->dev_private;
diff --git a/drivers/gpu/drm/arm/hdlcd_drv.c b/drivers/gpu/drm/arm/hdlcd_drv.c
index b987c63..a6ca36f 100644
--- a/drivers/gpu/drm/arm/hdlcd_drv.c
+++ b/drivers/gpu/drm/arm/hdlcd_drv.c
@@ -49,8 +49,6 @@
 	atomic_set(&hdlcd->dma_end_count, 0);
 #endif
 
-	INIT_LIST_HEAD(&hdlcd->event_list);
-
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	hdlcd->mmio = devm_ioremap_resource(drm->dev, res);
 	if (IS_ERR(hdlcd->mmio)) {
@@ -84,11 +82,7 @@
 		goto setup_fail;
 	}
 
-	pm_runtime_enable(drm->dev);
-
-	pm_runtime_get_sync(drm->dev);
 	ret = drm_irq_install(drm, platform_get_irq(pdev, 0));
-	pm_runtime_put_sync(drm->dev);
 	if (ret < 0) {
 		DRM_ERROR("failed to install IRQ handler\n");
 		goto irq_fail;
@@ -164,24 +158,9 @@
 		atomic_inc(&hdlcd->vsync_count);
 
 #endif
-	if (irq_status & HDLCD_INTERRUPT_VSYNC) {
-		bool events_sent = false;
-		unsigned long flags;
-		struct drm_pending_vblank_event	*e, *t;
-
+	if (irq_status & HDLCD_INTERRUPT_VSYNC)
 		drm_crtc_handle_vblank(&hdlcd->crtc);
 
-		spin_lock_irqsave(&drm->event_lock, flags);
-		list_for_each_entry_safe(e, t, &hdlcd->event_list, base.link) {
-			list_del(&e->base.link);
-			drm_crtc_send_vblank_event(&hdlcd->crtc, e);
-			events_sent = true;
-		}
-		if (events_sent)
-			drm_crtc_vblank_put(&hdlcd->crtc);
-		spin_unlock_irqrestore(&drm->event_lock, flags);
-	}
-
 	/* acknowledge interrupt(s) */
 	hdlcd_write(hdlcd, HDLCD_REG_INT_CLEAR, irq_status);
 
@@ -275,6 +254,7 @@
 static struct drm_info_list hdlcd_debugfs_list[] = {
 	{ "interrupt_count", hdlcd_show_underrun_count, 0 },
 	{ "clocks", hdlcd_show_pxlclock, 0 },
+	{ "fb", drm_fb_cma_debugfs_show, 0 },
 };
 
 static int hdlcd_debugfs_init(struct drm_minor *minor)
@@ -357,6 +337,8 @@
 		return -ENOMEM;
 
 	drm->dev_private = hdlcd;
+	dev_set_drvdata(dev, drm);
+
 	hdlcd_setup_mode_config(drm);
 	ret = hdlcd_load(drm, 0);
 	if (ret)
@@ -366,14 +348,18 @@
 	if (ret)
 		goto err_unload;
 
-	dev_set_drvdata(dev, drm);
-
 	ret = component_bind_all(dev, drm);
 	if (ret) {
 		DRM_ERROR("Failed to bind all components\n");
 		goto err_unregister;
 	}
 
+	ret = pm_runtime_set_active(dev);
+	if (ret)
+		goto err_pm_active;
+
+	pm_runtime_enable(dev);
+
 	ret = drm_vblank_init(drm, drm->mode_config.num_crtc);
 	if (ret < 0) {
 		DRM_ERROR("failed to initialise vblank\n");
@@ -399,16 +385,16 @@
 	drm_mode_config_cleanup(drm);
 	drm_vblank_cleanup(drm);
 err_vblank:
+	pm_runtime_disable(drm->dev);
+err_pm_active:
 	component_unbind_all(dev, drm);
 err_unregister:
 	drm_dev_unregister(drm);
 err_unload:
-	pm_runtime_get_sync(drm->dev);
 	drm_irq_uninstall(drm);
-	pm_runtime_put_sync(drm->dev);
-	pm_runtime_disable(drm->dev);
 	of_reserved_mem_device_release(drm->dev);
 err_free:
+	dev_set_drvdata(dev, NULL);
 	drm_dev_unref(drm);
 
 	return ret;
@@ -495,30 +481,34 @@
 static int __maybe_unused hdlcd_pm_suspend(struct device *dev)
 {
 	struct drm_device *drm = dev_get_drvdata(dev);
-	struct drm_crtc *crtc;
+	struct hdlcd_drm_private *hdlcd = drm ? drm->dev_private : NULL;
 
-	if (pm_runtime_suspended(dev))
+	if (!hdlcd)
 		return 0;
 
-	drm_modeset_lock_all(drm);
-	list_for_each_entry(crtc, &drm->mode_config.crtc_list, head)
-		hdlcd_crtc_suspend(crtc);
-	drm_modeset_unlock_all(drm);
+	drm_kms_helper_poll_disable(drm);
+
+	hdlcd->state = drm_atomic_helper_suspend(drm);
+	if (IS_ERR(hdlcd->state)) {
+		drm_kms_helper_poll_enable(drm);
+		return PTR_ERR(hdlcd->state);
+	}
+
 	return 0;
 }
 
 static int __maybe_unused hdlcd_pm_resume(struct device *dev)
 {
 	struct drm_device *drm = dev_get_drvdata(dev);
-	struct drm_crtc *crtc;
+	struct hdlcd_drm_private *hdlcd = drm ? drm->dev_private : NULL;
 
-	if (!pm_runtime_suspended(dev))
+	if (!hdlcd)
 		return 0;
 
-	drm_modeset_lock_all(drm);
-	list_for_each_entry(crtc, &drm->mode_config.crtc_list, head)
-		hdlcd_crtc_resume(crtc);
-	drm_modeset_unlock_all(drm);
+	drm_atomic_helper_resume(drm, hdlcd->state);
+	drm_kms_helper_poll_enable(drm);
+	pm_runtime_set_active(dev);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/arm/hdlcd_drv.h b/drivers/gpu/drm/arm/hdlcd_drv.h
index aa23478..e3950a0 100644
--- a/drivers/gpu/drm/arm/hdlcd_drv.h
+++ b/drivers/gpu/drm/arm/hdlcd_drv.h
@@ -9,10 +9,9 @@
 	void __iomem			*mmio;
 	struct clk			*clk;
 	struct drm_fbdev_cma		*fbdev;
-	struct drm_framebuffer		*fb;
-	struct list_head		event_list;
 	struct drm_crtc			crtc;
 	struct drm_plane		*plane;
+	struct drm_atomic_state		*state;
 #ifdef CONFIG_DEBUG_FS
 	atomic_t buffer_underrun_count;
 	atomic_t bus_error_count;
@@ -36,7 +35,5 @@
 
 int hdlcd_setup_crtc(struct drm_device *dev);
 void hdlcd_set_scanout(struct hdlcd_drm_private *hdlcd);
-void hdlcd_crtc_suspend(struct drm_crtc *crtc);
-void hdlcd_crtc_resume(struct drm_crtc *crtc);
 
 #endif /* __HDLCD_DRV_H__ */
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
index cf23a75..bd12231 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
@@ -391,12 +391,11 @@
 {
 	struct atmel_hlcdc_crtc_state *state;
 
-	if (crtc->state && crtc->state->mode_blob)
-		drm_property_unreference_blob(crtc->state->mode_blob);
-
 	if (crtc->state) {
+		__drm_atomic_helper_crtc_destroy_state(crtc->state);
 		state = drm_crtc_state_to_atmel_hlcdc_crtc_state(crtc->state);
 		kfree(state);
+		crtc->state = NULL;
 	}
 
 	state = kzalloc(sizeof(*state), GFP_KERNEL);
@@ -415,8 +414,9 @@
 		return NULL;
 
 	state = kmalloc(sizeof(*state), GFP_KERNEL);
-	if (state)
-		__drm_atomic_helper_crtc_duplicate_state(crtc, &state->base);
+	if (!state)
+		return NULL;
+	__drm_atomic_helper_crtc_duplicate_state(crtc, &state->base);
 
 	cur = drm_crtc_state_to_atmel_hlcdc_crtc_state(crtc->state);
 	state->output_mode = cur->output_mode;
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 3ff1ed7..c204ef3 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -351,6 +351,8 @@
 	drm_property_unreference_blob(state->mode_blob);
 	state->mode_blob = NULL;
 
+	memset(&state->mode, 0, sizeof(state->mode));
+
 	if (blob) {
 		if (blob->length != sizeof(struct drm_mode_modeinfo) ||
 		    drm_mode_convert_umode(&state->mode,
@@ -363,7 +365,6 @@
 		DRM_DEBUG_ATOMIC("Set [MODE:%s] for CRTC state %p\n",
 				 state->mode.name, state);
 	} else {
-		memset(&state->mode, 0, sizeof(state->mode));
 		state->enable = false;
 		DRM_DEBUG_ATOMIC("Set [NOMODE] for CRTC state %p\n",
 				 state);
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index d2a6d95..0e3cc66 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -2821,8 +2821,6 @@
 			goto out;
 		}
 
-		drm_mode_set_crtcinfo(mode, CRTC_INTERLACE_HALVE_V);
-
 		/*
 		 * Check whether the primary plane supports the fb pixel format.
 		 * Drivers not implementing the universal planes API use a
@@ -4841,7 +4839,8 @@
 		if (value == 0)
 			return true;
 
-		return _object_find(property->dev, value, property->values[0]) != NULL;
+		*ref = _object_find(property->dev, value, property->values[0]);
+		return *ref != NULL;
 	}
 
 	for (i = 0; i < property->num_values; i++)
diff --git a/drivers/gpu/drm/drm_fb_cma_helper.c b/drivers/gpu/drm/drm_fb_cma_helper.c
index 172cafe..5075fae 100644
--- a/drivers/gpu/drm/drm_fb_cma_helper.c
+++ b/drivers/gpu/drm/drm_fb_cma_helper.c
@@ -445,7 +445,7 @@
 err_fb_info_destroy:
 	drm_fb_helper_release_fbi(helper);
 err_gem_free_object:
-	dev->driver->gem_free_object(&obj->base);
+	drm_gem_object_unreference_unlocked(&obj->base);
 	return ret;
 }
 EXPORT_SYMBOL(drm_fbdev_cma_create_with_funcs);
diff --git a/drivers/gpu/drm/drm_gem_cma_helper.c b/drivers/gpu/drm/drm_gem_cma_helper.c
index e1ab008..1d6c335 100644
--- a/drivers/gpu/drm/drm_gem_cma_helper.c
+++ b/drivers/gpu/drm/drm_gem_cma_helper.c
@@ -121,7 +121,7 @@
 	return cma_obj;
 
 error:
-	drm->driver->gem_free_object(&cma_obj->base);
+	drm_gem_object_unreference_unlocked(&cma_obj->base);
 	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(drm_gem_cma_create);
@@ -162,18 +162,12 @@
 	 * and handle has the id what user can see.
 	 */
 	ret = drm_gem_handle_create(file_priv, gem_obj, handle);
-	if (ret)
-		goto err_handle_create;
-
 	/* drop reference from allocate - handle holds it now. */
 	drm_gem_object_unreference_unlocked(gem_obj);
+	if (ret)
+		return ERR_PTR(ret);
 
 	return cma_obj;
-
-err_handle_create:
-	drm->driver->gem_free_object(gem_obj);
-
-	return ERR_PTR(ret);
 }
 
 /**
diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index 7def3d5..e5e6f50 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -1518,6 +1518,8 @@
 	if (out->status != MODE_OK)
 		goto out;
 
+	drm_mode_set_crtcinfo(out, CRTC_INTERLACE_HALVE_V);
+
 	ret = 0;
 
 out:
diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c
index 0ec1ad9..dc723f7 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c
@@ -42,9 +42,10 @@
 	.reg_bits = 32,
 	.reg_stride = 4,
 	.val_bits = 32,
-	.cache_type = REGCACHE_RBTREE,
+	.cache_type = REGCACHE_FLAT,
 
 	.volatile_reg = fsl_dcu_drm_is_volatile_reg,
+	.max_register = 0x11fc,
 };
 
 static int fsl_dcu_drm_irq_init(struct drm_device *dev)
diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c
index 1f14b60..8265665 100644
--- a/drivers/gpu/drm/imx/imx-drm-core.c
+++ b/drivers/gpu/drm/imx/imx-drm-core.c
@@ -97,8 +97,8 @@
 	return NULL;
 }
 
-int imx_drm_set_bus_format_pins(struct drm_encoder *encoder, u32 bus_format,
-		int hsync_pin, int vsync_pin)
+int imx_drm_set_bus_config(struct drm_encoder *encoder, u32 bus_format,
+		int hsync_pin, int vsync_pin, u32 bus_flags)
 {
 	struct imx_drm_crtc_helper_funcs *helper;
 	struct imx_drm_crtc *imx_crtc;
@@ -110,14 +110,17 @@
 	helper = &imx_crtc->imx_drm_helper_funcs;
 	if (helper->set_interface_pix_fmt)
 		return helper->set_interface_pix_fmt(encoder->crtc,
-					bus_format, hsync_pin, vsync_pin);
+					bus_format, hsync_pin, vsync_pin,
+					bus_flags);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(imx_drm_set_bus_format_pins);
+EXPORT_SYMBOL_GPL(imx_drm_set_bus_config);
 
 int imx_drm_set_bus_format(struct drm_encoder *encoder, u32 bus_format)
 {
-	return imx_drm_set_bus_format_pins(encoder, bus_format, 2, 3);
+	return imx_drm_set_bus_config(encoder, bus_format, 2, 3,
+				      DRM_BUS_FLAG_DE_HIGH |
+				      DRM_BUS_FLAG_PIXDATA_NEGEDGE);
 }
 EXPORT_SYMBOL_GPL(imx_drm_set_bus_format);
 
diff --git a/drivers/gpu/drm/imx/imx-drm.h b/drivers/gpu/drm/imx/imx-drm.h
index b0241b9..74320a1 100644
--- a/drivers/gpu/drm/imx/imx-drm.h
+++ b/drivers/gpu/drm/imx/imx-drm.h
@@ -19,7 +19,8 @@
 	int (*enable_vblank)(struct drm_crtc *crtc);
 	void (*disable_vblank)(struct drm_crtc *crtc);
 	int (*set_interface_pix_fmt)(struct drm_crtc *crtc,
-			u32 bus_format, int hsync_pin, int vsync_pin);
+			u32 bus_format, int hsync_pin, int vsync_pin,
+			u32 bus_flags);
 	const struct drm_crtc_helper_funcs *crtc_helper_funcs;
 	const struct drm_crtc_funcs *crtc_funcs;
 };
@@ -41,8 +42,8 @@
 
 struct drm_gem_cma_object *imx_drm_fb_get_obj(struct drm_framebuffer *fb);
 
-int imx_drm_set_bus_format_pins(struct drm_encoder *encoder,
-		u32 bus_format, int hsync_pin, int vsync_pin);
+int imx_drm_set_bus_config(struct drm_encoder *encoder, u32 bus_format,
+		int hsync_pin, int vsync_pin, u32 bus_flags);
 int imx_drm_set_bus_format(struct drm_encoder *encoder,
 		u32 bus_format);
 
diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c
index a58eee5..beff793 100644
--- a/drivers/gpu/drm/imx/imx-ldb.c
+++ b/drivers/gpu/drm/imx/imx-ldb.c
@@ -25,6 +25,7 @@
 #include <linux/mfd/syscon/imx6q-iomuxc-gpr.h>
 #include <linux/of_device.h>
 #include <linux/of_graph.h>
+#include <video/of_display_timing.h>
 #include <video/of_videomode.h>
 #include <linux/regmap.h>
 #include <linux/videodev2.h>
@@ -59,6 +60,7 @@
 	struct drm_encoder encoder;
 	struct drm_panel *panel;
 	struct device_node *child;
+	struct i2c_adapter *ddc;
 	int chno;
 	void *edid;
 	int edid_len;
@@ -107,6 +109,9 @@
 			return num_modes;
 	}
 
+	if (!imx_ldb_ch->edid && imx_ldb_ch->ddc)
+		imx_ldb_ch->edid = drm_get_edid(connector, imx_ldb_ch->ddc);
+
 	if (imx_ldb_ch->edid) {
 		drm_mode_connector_update_edid_property(connector,
 							imx_ldb_ch->edid);
@@ -553,7 +558,8 @@
 
 	for_each_child_of_node(np, child) {
 		struct imx_ldb_channel *channel;
-		struct device_node *port;
+		struct device_node *ddc_node;
+		struct device_node *ep;
 
 		ret = of_property_read_u32(child, "reg", &i);
 		if (ret || i < 0 || i > 1)
@@ -576,33 +582,54 @@
 		 * The output port is port@4 with an external 4-port mux or
 		 * port@2 with the internal 2-port mux.
 		 */
-		port = of_graph_get_port_by_id(child, imx_ldb->lvds_mux ? 4 : 2);
-		if (port) {
-			struct device_node *endpoint, *remote;
+		ep = of_graph_get_endpoint_by_regs(child,
+						   imx_ldb->lvds_mux ? 4 : 2,
+						   -1);
+		if (ep) {
+			struct device_node *remote;
 
-			endpoint = of_get_child_by_name(port, "endpoint");
-			if (endpoint) {
-				remote = of_graph_get_remote_port_parent(endpoint);
-				if (remote)
-					channel->panel = of_drm_find_panel(remote);
-				else
-					return -EPROBE_DEFER;
-				if (!channel->panel) {
-					dev_err(dev, "panel not found: %s\n",
-						remote->full_name);
-					return -EPROBE_DEFER;
-				}
+			remote = of_graph_get_remote_port_parent(ep);
+			of_node_put(ep);
+			if (remote)
+				channel->panel = of_drm_find_panel(remote);
+			else
+				return -EPROBE_DEFER;
+			of_node_put(remote);
+			if (!channel->panel) {
+				dev_err(dev, "panel not found: %s\n",
+					remote->full_name);
+				return -EPROBE_DEFER;
 			}
 		}
 
-		edidp = of_get_property(child, "edid", &channel->edid_len);
-		if (edidp) {
-			channel->edid = kmemdup(edidp, channel->edid_len,
-						GFP_KERNEL);
-		} else if (!channel->panel) {
-			ret = of_get_drm_display_mode(child, &channel->mode, 0);
-			if (!ret)
-				channel->mode_valid = 1;
+		ddc_node = of_parse_phandle(child, "ddc-i2c-bus", 0);
+		if (ddc_node) {
+			channel->ddc = of_find_i2c_adapter_by_node(ddc_node);
+			of_node_put(ddc_node);
+			if (!channel->ddc) {
+				dev_warn(dev, "failed to get ddc i2c adapter\n");
+				return -EPROBE_DEFER;
+			}
+		}
+
+		if (!channel->ddc) {
+			/* if no DDC available, fallback to hardcoded EDID */
+			dev_dbg(dev, "no ddc available\n");
+
+			edidp = of_get_property(child, "edid",
+						&channel->edid_len);
+			if (edidp) {
+				channel->edid = kmemdup(edidp,
+							channel->edid_len,
+							GFP_KERNEL);
+			} else if (!channel->panel) {
+				/* fallback to display-timings node */
+				ret = of_get_drm_display_mode(child,
+							      &channel->mode,
+							      OF_USE_NATIVE_MODE);
+				if (!ret)
+					channel->mode_valid = 1;
+			}
 		}
 
 		channel->bus_format = of_get_bus_format(dev, child);
@@ -647,6 +674,7 @@
 		channel->encoder.funcs->destroy(&channel->encoder);
 
 		kfree(channel->edid);
+		i2c_put_adapter(channel->ddc);
 	}
 }
 
diff --git a/drivers/gpu/drm/imx/imx-tve.c b/drivers/gpu/drm/imx/imx-tve.c
index ae7a9fb..baf7881 100644
--- a/drivers/gpu/drm/imx/imx-tve.c
+++ b/drivers/gpu/drm/imx/imx-tve.c
@@ -294,8 +294,10 @@
 
 	switch (tve->mode) {
 	case TVE_MODE_VGA:
-		imx_drm_set_bus_format_pins(encoder, MEDIA_BUS_FMT_GBR888_1X24,
-					    tve->hsync_pin, tve->vsync_pin);
+		imx_drm_set_bus_config(encoder, MEDIA_BUS_FMT_GBR888_1X24,
+				       tve->hsync_pin, tve->vsync_pin,
+				       DRM_BUS_FLAG_DE_HIGH |
+				       DRM_BUS_FLAG_PIXDATA_NEGEDGE);
 		break;
 	case TVE_MODE_TVOUT:
 		imx_drm_set_bus_format(encoder, MEDIA_BUS_FMT_YUV8_1X24);
diff --git a/drivers/gpu/drm/imx/ipuv3-crtc.c b/drivers/gpu/drm/imx/ipuv3-crtc.c
index b2c30b8..fc04041 100644
--- a/drivers/gpu/drm/imx/ipuv3-crtc.c
+++ b/drivers/gpu/drm/imx/ipuv3-crtc.c
@@ -66,6 +66,7 @@
 	struct ipu_flip_work	*flip_work;
 	int			irq;
 	u32			bus_format;
+	u32			bus_flags;
 	int			di_hsync_pin;
 	int			di_vsync_pin;
 };
@@ -271,8 +272,10 @@
 	else
 		sig_cfg.clkflags = 0;
 
-	sig_cfg.enable_pol = 1;
-	sig_cfg.clk_pol = 0;
+	sig_cfg.enable_pol = !(ipu_crtc->bus_flags & DRM_BUS_FLAG_DE_LOW);
+	/* Default to driving pixel data on negative clock edges */
+	sig_cfg.clk_pol = !!(ipu_crtc->bus_flags &
+			     DRM_BUS_FLAG_PIXDATA_POSEDGE);
 	sig_cfg.bus_format = ipu_crtc->bus_format;
 	sig_cfg.v_to_h_sync = 0;
 	sig_cfg.hsync_pin = ipu_crtc->di_hsync_pin;
@@ -396,11 +399,12 @@
 }
 
 static int ipu_set_interface_pix_fmt(struct drm_crtc *crtc,
-		u32 bus_format, int hsync_pin, int vsync_pin)
+		u32 bus_format, int hsync_pin, int vsync_pin, u32 bus_flags)
 {
 	struct ipu_crtc *ipu_crtc = to_ipu_crtc(crtc);
 
 	ipu_crtc->bus_format = bus_format;
+	ipu_crtc->bus_flags = bus_flags;
 	ipu_crtc->di_hsync_pin = hsync_pin;
 	ipu_crtc->di_vsync_pin = vsync_pin;
 
diff --git a/drivers/gpu/drm/imx/ipuv3-plane.c b/drivers/gpu/drm/imx/ipuv3-plane.c
index 681ec6e..a4bb441 100644
--- a/drivers/gpu/drm/imx/ipuv3-plane.c
+++ b/drivers/gpu/drm/imx/ipuv3-plane.c
@@ -38,6 +38,8 @@
 	DRM_FORMAT_RGBX8888,
 	DRM_FORMAT_BGRA8888,
 	DRM_FORMAT_BGRA8888,
+	DRM_FORMAT_UYVY,
+	DRM_FORMAT_VYUY,
 	DRM_FORMAT_YUYV,
 	DRM_FORMAT_YVYU,
 	DRM_FORMAT_YUV420,
@@ -428,7 +430,6 @@
 	if (crtc != plane->crtc)
 		dev_dbg(plane->dev->dev, "crtc change: %p -> %p\n",
 				plane->crtc, crtc);
-	plane->crtc = crtc;
 
 	if (!ipu_plane->enabled)
 		ipu_plane_enable(ipu_plane);
@@ -461,7 +462,7 @@
 	kfree(ipu_plane);
 }
 
-static struct drm_plane_funcs ipu_plane_funcs = {
+static const struct drm_plane_funcs ipu_plane_funcs = {
 	.update_plane	= ipu_update_plane,
 	.disable_plane	= ipu_disable_plane,
 	.destroy	= ipu_plane_destroy,
diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c
index 363e2c7..2d1fd02 100644
--- a/drivers/gpu/drm/imx/parallel-display.c
+++ b/drivers/gpu/drm/imx/parallel-display.c
@@ -35,7 +35,6 @@
 	void *edid;
 	int edid_len;
 	u32 bus_format;
-	int mode_valid;
 	struct drm_display_mode mode;
 	struct drm_panel *panel;
 };
@@ -68,17 +67,6 @@
 		num_modes = drm_add_edid_modes(connector, imxpd->edid);
 	}
 
-	if (imxpd->mode_valid) {
-		struct drm_display_mode *mode = drm_mode_create(connector->dev);
-
-		if (!mode)
-			return -EINVAL;
-		drm_mode_copy(mode, &imxpd->mode);
-		mode->type |= DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED,
-		drm_mode_probed_add(connector, mode);
-		num_modes++;
-	}
-
 	if (np) {
 		struct drm_display_mode *mode = drm_mode_create(connector->dev);
 
@@ -115,8 +103,8 @@
 static void imx_pd_encoder_prepare(struct drm_encoder *encoder)
 {
 	struct imx_parallel_display *imxpd = enc_to_imxpd(encoder);
-
-	imx_drm_set_bus_format(encoder, imxpd->bus_format);
+	imx_drm_set_bus_config(encoder, imxpd->bus_format, 2, 3,
+			       imxpd->connector.display_info.bus_flags);
 }
 
 static void imx_pd_encoder_commit(struct drm_encoder *encoder)
@@ -203,7 +191,7 @@
 {
 	struct drm_device *drm = data;
 	struct device_node *np = dev->of_node;
-	struct device_node *port;
+	struct device_node *ep;
 	const u8 *edidp;
 	struct imx_parallel_display *imxpd;
 	int ret;
@@ -230,18 +218,18 @@
 	}
 
 	/* port@1 is the output port */
-	port = of_graph_get_port_by_id(np, 1);
-	if (port) {
-		struct device_node *endpoint, *remote;
+	ep = of_graph_get_endpoint_by_regs(np, 1, -1);
+	if (ep) {
+		struct device_node *remote;
 
-		endpoint = of_get_child_by_name(port, "endpoint");
-		if (endpoint) {
-			remote = of_graph_get_remote_port_parent(endpoint);
-			if (remote)
-				imxpd->panel = of_drm_find_panel(remote);
-			if (!imxpd->panel)
-				return -EPROBE_DEFER;
+		remote = of_graph_get_remote_port_parent(ep);
+		of_node_put(ep);
+		if (remote) {
+			imxpd->panel = of_drm_find_panel(remote);
+			of_node_put(remote);
 		}
+		if (!imxpd->panel)
+			return -EPROBE_DEFER;
 	}
 
 	imxpd->dev = dev;
diff --git a/drivers/gpu/drm/mediatek/mtk_dpi.c b/drivers/gpu/drm/mediatek/mtk_dpi.c
index d05ca79..0186e50 100644
--- a/drivers/gpu/drm/mediatek/mtk_dpi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dpi.c
@@ -432,11 +432,6 @@
 	unsigned long pll_rate;
 	unsigned int factor;
 
-	if (!dpi) {
-		dev_err(dpi->dev, "invalid argument\n");
-		return -EINVAL;
-	}
-
 	pix_rate = 1000UL * mode->clock;
 	if (mode->clock <= 74000)
 		factor = 8 * 3;
diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c
index 2d808e5..7695591 100644
--- a/drivers/gpu/drm/mediatek/mtk_dsi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dsi.c
@@ -695,10 +695,8 @@
 {
 	drm_encoder_cleanup(&dsi->encoder);
 	/* Skip connector cleanup if creation was delegated to the bridge */
-	if (dsi->conn.dev) {
-		drm_connector_unregister(&dsi->conn);
+	if (dsi->conn.dev)
 		drm_connector_cleanup(&dsi->conn);
-	}
 }
 
 static void mtk_dsi_ddp_start(struct mtk_ddp_comp *comp)
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index 14e64e0..d347dca 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -182,7 +182,7 @@
 			}
 		}
 
-		fvv = pllreffreq * testn / testm;
+		fvv = pllreffreq * (n + 1) / (m + 1);
 		fvv = (fvv - 800000) / 50000;
 
 		if (fvv > 15)
@@ -202,6 +202,14 @@
 	WREG_DAC(MGA1064_PIX_PLLC_M, m);
 	WREG_DAC(MGA1064_PIX_PLLC_N, n);
 	WREG_DAC(MGA1064_PIX_PLLC_P, p);
+
+	if (mdev->unique_rev_id >= 0x04) {
+		WREG_DAC(0x1a, 0x09);
+		msleep(20);
+		WREG_DAC(0x1a, 0x01);
+
+	}
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index fbe304e..2aec27d 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -408,7 +408,7 @@
 	}
 
 	adreno_gpu->memptrs = msm_gem_vaddr(adreno_gpu->memptrs_bo);
-	if (!adreno_gpu->memptrs) {
+	if (IS_ERR(adreno_gpu->memptrs)) {
 		dev_err(drm->dev, "could not vmap memptrs\n");
 		return -ENOMEM;
 	}
diff --git a/drivers/gpu/drm/msm/msm_fbdev.c b/drivers/gpu/drm/msm/msm_fbdev.c
index d9759bf..c6cf837 100644
--- a/drivers/gpu/drm/msm/msm_fbdev.c
+++ b/drivers/gpu/drm/msm/msm_fbdev.c
@@ -159,6 +159,10 @@
 	dev->mode_config.fb_base = paddr;
 
 	fbi->screen_base = msm_gem_vaddr_locked(fbdev->bo);
+	if (IS_ERR(fbi->screen_base)) {
+		ret = PTR_ERR(fbi->screen_base);
+		goto fail_unlock;
+	}
 	fbi->screen_size = fbdev->bo->size;
 	fbi->fix.smem_start = paddr;
 	fbi->fix.smem_len = fbdev->bo->size;
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 7daf4054..69836f5 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -398,6 +398,8 @@
 			return ERR_CAST(pages);
 		msm_obj->vaddr = vmap(pages, obj->size >> PAGE_SHIFT,
 				VM_MAP, pgprot_writecombine(PAGE_KERNEL));
+		if (msm_obj->vaddr == NULL)
+			return ERR_PTR(-ENOMEM);
 	}
 	return msm_obj->vaddr;
 }
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index b89ca51..eb4bb8b 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -40,12 +40,14 @@
 
 	submit->dev = dev;
 	submit->gpu = gpu;
+	submit->fence = NULL;
 	submit->pid = get_pid(task_pid(current));
 
 	/* initially, until copy_from_user() and bo lookup succeeds: */
 	submit->nr_bos = 0;
 	submit->nr_cmds = 0;
 
+	INIT_LIST_HEAD(&submit->node);
 	INIT_LIST_HEAD(&submit->bo_list);
 	ww_acquire_init(&submit->ticket, &reservation_ww_class);
 
@@ -75,6 +77,11 @@
 		void __user *userptr =
 			u64_to_user_ptr(args->bos + (i * sizeof(submit_bo)));
 
+		/* make sure we don't have garbage flags, in case we hit
+		 * error path before flags is initialized:
+		 */
+		submit->bos[i].flags = 0;
+
 		ret = copy_from_user(&submit_bo, userptr, sizeof(submit_bo));
 		if (ret) {
 			ret = -EFAULT;
diff --git a/drivers/gpu/drm/msm/msm_rd.c b/drivers/gpu/drm/msm/msm_rd.c
index b48f73a..0857710 100644
--- a/drivers/gpu/drm/msm/msm_rd.c
+++ b/drivers/gpu/drm/msm/msm_rd.c
@@ -312,6 +312,9 @@
 		struct msm_gem_object *obj = submit->bos[idx].obj;
 		const char *buf = msm_gem_vaddr_locked(&obj->base);
 
+		if (IS_ERR(buf))
+			continue;
+
 		buf += iova - submit->bos[idx].iova;
 
 		rd_write_section(rd, RD_GPUADDR,
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c
index 1f14b90..42f5359 100644
--- a/drivers/gpu/drm/msm/msm_ringbuffer.c
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.c
@@ -40,6 +40,10 @@
 	}
 
 	ring->start = msm_gem_vaddr_locked(ring->bo);
+	if (IS_ERR(ring->start)) {
+		ret = PTR_ERR(ring->start);
+		goto fail;
+	}
 	ring->end   = ring->start + (size / 4);
 	ring->cur   = ring->start;
 
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/device.h b/drivers/gpu/drm/nouveau/include/nvkm/core/device.h
index c612dc1..126a85c 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/core/device.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/core/device.h
@@ -16,9 +16,9 @@
 	NVKM_SUBDEV_MC,
 	NVKM_SUBDEV_BUS,
 	NVKM_SUBDEV_TIMER,
+	NVKM_SUBDEV_INSTMEM,
 	NVKM_SUBDEV_FB,
 	NVKM_SUBDEV_LTC,
-	NVKM_SUBDEV_INSTMEM,
 	NVKM_SUBDEV_MMU,
 	NVKM_SUBDEV_BAR,
 	NVKM_SUBDEV_PMU,
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/bios/disp.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/bios/disp.h
index db10c11..c5a6ebd 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/bios/disp.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/bios/disp.h
@@ -25,7 +25,8 @@
 		      u8 *ver, u8 *hdr, u8 *cnt, u8 *len, struct nvbios_outp *);
 
 struct nvbios_ocfg {
-	u16 match;
+	u8  proto;
+	u8  flags;
 	u16 clkcmp[2];
 };
 
@@ -33,7 +34,7 @@
 		      u8 *ver, u8 *hdr, u8 *cnt, u8 *len);
 u16 nvbios_ocfg_parse(struct nvkm_bios *, u16 outp, u8 idx,
 		      u8 *ver, u8 *hdr, u8 *cnt, u8 *len, struct nvbios_ocfg *);
-u16 nvbios_ocfg_match(struct nvkm_bios *, u16 outp, u16 type,
+u16 nvbios_ocfg_match(struct nvkm_bios *, u16 outp, u8 proto, u8 flags,
 		      u8 *ver, u8 *hdr, u8 *cnt, u8 *len, struct nvbios_ocfg *);
 u16 nvbios_oclk_match(struct nvkm_bios *, u16 cmp, u32 khz);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
index 57aaf98..300ea03 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
@@ -552,6 +552,7 @@
 	if (ret)
 		goto fini;
 
+	fbcon->helper.fbdev->pixmap.buf_align = 4;
 	return 0;
 
 fini:
diff --git a/drivers/gpu/drm/nouveau/nv04_fbcon.c b/drivers/gpu/drm/nouveau/nv04_fbcon.c
index 0f3e4bb..7d9248b 100644
--- a/drivers/gpu/drm/nouveau/nv04_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nv04_fbcon.c
@@ -82,7 +82,6 @@
 	uint32_t fg;
 	uint32_t bg;
 	uint32_t dsize;
-	uint32_t width;
 	uint32_t *data = (uint32_t *)image->data;
 	int ret;
 
@@ -93,9 +92,6 @@
 	if (ret)
 		return ret;
 
-	width = ALIGN(image->width, 8);
-	dsize = ALIGN(width * image->height, 32) >> 5;
-
 	if (info->fix.visual == FB_VISUAL_TRUECOLOR ||
 	    info->fix.visual == FB_VISUAL_DIRECTCOLOR) {
 		fg = ((uint32_t *) info->pseudo_palette)[image->fg_color];
@@ -111,10 +107,11 @@
 			 ((image->dx + image->width) & 0xffff));
 	OUT_RING(chan, bg);
 	OUT_RING(chan, fg);
-	OUT_RING(chan, (image->height << 16) | width);
+	OUT_RING(chan, (image->height << 16) | image->width);
 	OUT_RING(chan, (image->height << 16) | image->width);
 	OUT_RING(chan, (image->dy << 16) | (image->dx & 0xffff));
 
+	dsize = ALIGN(image->width * image->height, 32) >> 5;
 	while (dsize) {
 		int iter_len = dsize > 128 ? 128 : dsize;
 
diff --git a/drivers/gpu/drm/nouveau/nv50_fbcon.c b/drivers/gpu/drm/nouveau/nv50_fbcon.c
index 33d9ee0..1aeb698 100644
--- a/drivers/gpu/drm/nouveau/nv50_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nv50_fbcon.c
@@ -95,7 +95,7 @@
 	struct nouveau_fbdev *nfbdev = info->par;
 	struct nouveau_drm *drm = nouveau_drm(nfbdev->dev);
 	struct nouveau_channel *chan = drm->channel;
-	uint32_t width, dwords, *data = (uint32_t *)image->data;
+	uint32_t dwords, *data = (uint32_t *)image->data;
 	uint32_t mask = ~(~0 >> (32 - info->var.bits_per_pixel));
 	uint32_t *palette = info->pseudo_palette;
 	int ret;
@@ -107,9 +107,6 @@
 	if (ret)
 		return ret;
 
-	width = ALIGN(image->width, 32);
-	dwords = (width * image->height) >> 5;
-
 	BEGIN_NV04(chan, NvSub2D, 0x0814, 2);
 	if (info->fix.visual == FB_VISUAL_TRUECOLOR ||
 	    info->fix.visual == FB_VISUAL_DIRECTCOLOR) {
@@ -128,6 +125,7 @@
 	OUT_RING(chan, 0);
 	OUT_RING(chan, image->dy);
 
+	dwords = ALIGN(image->width * image->height, 32) >> 5;
 	while (dwords) {
 		int push = dwords > 2047 ? 2047 : dwords;
 
diff --git a/drivers/gpu/drm/nouveau/nvc0_fbcon.c b/drivers/gpu/drm/nouveau/nvc0_fbcon.c
index a091335..839f4c8 100644
--- a/drivers/gpu/drm/nouveau/nvc0_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nvc0_fbcon.c
@@ -95,7 +95,7 @@
 	struct nouveau_fbdev *nfbdev = info->par;
 	struct nouveau_drm *drm = nouveau_drm(nfbdev->dev);
 	struct nouveau_channel *chan = drm->channel;
-	uint32_t width, dwords, *data = (uint32_t *)image->data;
+	uint32_t dwords, *data = (uint32_t *)image->data;
 	uint32_t mask = ~(~0 >> (32 - info->var.bits_per_pixel));
 	uint32_t *palette = info->pseudo_palette;
 	int ret;
@@ -107,9 +107,6 @@
 	if (ret)
 		return ret;
 
-	width = ALIGN(image->width, 32);
-	dwords = (width * image->height) >> 5;
-
 	BEGIN_NVC0(chan, NvSub2D, 0x0814, 2);
 	if (info->fix.visual == FB_VISUAL_TRUECOLOR ||
 	    info->fix.visual == FB_VISUAL_DIRECTCOLOR) {
@@ -128,6 +125,7 @@
 	OUT_RING  (chan, 0);
 	OUT_RING  (chan, image->dy);
 
+	dwords = ALIGN(image->width * image->height, 32) >> 5;
 	while (dwords) {
 		int push = dwords > 2047 ? 2047 : dwords;
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild
index a74c5dd..e2a64ed 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild
@@ -18,6 +18,7 @@
 nvkm-y += nvkm/engine/disp/sornv50.o
 nvkm-y += nvkm/engine/disp/sorg94.o
 nvkm-y += nvkm/engine/disp/sorgf119.o
+nvkm-y += nvkm/engine/disp/sorgm107.o
 nvkm-y += nvkm/engine/disp/sorgm200.o
 nvkm-y += nvkm/engine/disp/dport.o
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gf119.c
index f031466..5dd3438 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gf119.c
@@ -76,6 +76,7 @@
 	mask |= 0x0001 << or;
 	mask |= 0x0100 << head;
 
+
 	list_for_each_entry(outp, &disp->base.outp, head) {
 		if ((outp->info.hasht & 0xff) == type &&
 		    (outp->info.hashm & mask) == mask) {
@@ -155,25 +156,21 @@
 	if (!outp)
 		return NULL;
 
+	*conf = (ctrl & 0x00000f00) >> 8;
 	switch (outp->info.type) {
 	case DCB_OUTPUT_TMDS:
-		*conf = (ctrl & 0x00000f00) >> 8;
 		if (*conf == 5)
 			*conf |= 0x0100;
 		break;
 	case DCB_OUTPUT_LVDS:
-		*conf = disp->sor.lvdsconf;
+		*conf |= disp->sor.lvdsconf;
 		break;
-	case DCB_OUTPUT_DP:
-		*conf = (ctrl & 0x00000f00) >> 8;
-		break;
-	case DCB_OUTPUT_ANALOG:
 	default:
-		*conf = 0x00ff;
 		break;
 	}
 
-	data = nvbios_ocfg_match(bios, data, *conf, &ver, &hdr, &cnt, &len, &info2);
+	data = nvbios_ocfg_match(bios, data, *conf & 0xff, *conf >> 8,
+				 &ver, &hdr, &cnt, &len, &info2);
 	if (data && id < 0xff) {
 		data = nvbios_oclk_match(bios, info2.clkcmp[id], pclk);
 		if (data) {
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gm107.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gm107.c
index b694414..f4b9cf8 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gm107.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gm107.c
@@ -36,7 +36,7 @@
 	.outp.internal.crt = nv50_dac_output_new,
 	.outp.internal.tmds = nv50_sor_output_new,
 	.outp.internal.lvds = nv50_sor_output_new,
-	.outp.internal.dp = gf119_sor_dp_new,
+	.outp.internal.dp = gm107_sor_dp_new,
 	.dac.nr = 3,
 	.dac.power = nv50_dac_power,
 	.dac.sense = nv50_dac_sense,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c
index 4226d21..fcb1b0c 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c
@@ -387,22 +387,17 @@
 	if (!outp)
 		return NULL;
 
+	*conf = (ctrl & 0x00000f00) >> 8;
 	if (outp->info.location == 0) {
 		switch (outp->info.type) {
 		case DCB_OUTPUT_TMDS:
-			*conf = (ctrl & 0x00000f00) >> 8;
 			if (*conf == 5)
 				*conf |= 0x0100;
 			break;
 		case DCB_OUTPUT_LVDS:
-			*conf = disp->sor.lvdsconf;
+			*conf |= disp->sor.lvdsconf;
 			break;
-		case DCB_OUTPUT_DP:
-			*conf = (ctrl & 0x00000f00) >> 8;
-			break;
-		case DCB_OUTPUT_ANALOG:
 		default:
-			*conf = 0x00ff;
 			break;
 		}
 	} else {
@@ -410,7 +405,8 @@
 		pclk = pclk / 2;
 	}
 
-	data = nvbios_ocfg_match(bios, data, *conf, &ver, &hdr, &cnt, &len, &info2);
+	data = nvbios_ocfg_match(bios, data, *conf & 0xff, *conf >> 8,
+				 &ver, &hdr, &cnt, &len, &info2);
 	if (data && id < 0xff) {
 		data = nvbios_oclk_match(bios, info2.clkcmp[id], pclk);
 		if (data) {
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/outpdp.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/outpdp.h
index e9067ba..4e983f6 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/outpdp.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/outpdp.h
@@ -62,7 +62,12 @@
 int gf119_sor_dp_new(struct nvkm_disp *, int, struct dcb_output *,
 		     struct nvkm_output **);
 int gf119_sor_dp_lnk_ctl(struct nvkm_output_dp *, int, int, bool);
+int gf119_sor_dp_drv_ctl(struct nvkm_output_dp *, int, int, int, int);
 
-int  gm200_sor_dp_new(struct nvkm_disp *, int, struct dcb_output *,
-		      struct nvkm_output **);
+int gm107_sor_dp_new(struct nvkm_disp *, int, struct dcb_output *,
+		     struct nvkm_output **);
+int gm107_sor_dp_pattern(struct nvkm_output_dp *, int);
+
+int gm200_sor_dp_new(struct nvkm_disp *, int, struct dcb_output *,
+		     struct nvkm_output **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c
index b4b41b1..22706c0 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c
@@ -40,8 +40,7 @@
 gf119_sor_dp_pattern(struct nvkm_output_dp *outp, int pattern)
 {
 	struct nvkm_device *device = outp->base.disp->engine.subdev.device;
-	const u32 loff = gf119_sor_loff(outp);
-	nvkm_mask(device, 0x61c110 + loff, 0x0f0f0f0f, 0x01010101 * pattern);
+	nvkm_mask(device, 0x61c110, 0x0f0f0f0f, 0x01010101 * pattern);
 	return 0;
 }
 
@@ -64,7 +63,7 @@
 	return 0;
 }
 
-static int
+int
 gf119_sor_dp_drv_ctl(struct nvkm_output_dp *outp,
 		     int ln, int vs, int pe, int pc)
 {
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgm107.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgm107.c
new file mode 100644
index 0000000..37790b2
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgm107.c
@@ -0,0 +1,53 @@
+/*
+ * Copyright 2016 Red Hat Inc.
+ *
+ * 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: Ben Skeggs <bskeggs@redhat.com>
+ */
+#include "nv50.h"
+#include "outpdp.h"
+
+int
+gm107_sor_dp_pattern(struct nvkm_output_dp *outp, int pattern)
+{
+	struct nvkm_device *device = outp->base.disp->engine.subdev.device;
+	const u32 soff = outp->base.or * 0x800;
+	const u32 data = 0x01010101 * pattern;
+	if (outp->base.info.sorconf.link & 1)
+		nvkm_mask(device, 0x61c110 + soff, 0x0f0f0f0f, data);
+	else
+		nvkm_mask(device, 0x61c12c + soff, 0x0f0f0f0f, data);
+	return 0;
+}
+
+static const struct nvkm_output_dp_func
+gm107_sor_dp_func = {
+	.pattern = gm107_sor_dp_pattern,
+	.lnk_pwr = g94_sor_dp_lnk_pwr,
+	.lnk_ctl = gf119_sor_dp_lnk_ctl,
+	.drv_ctl = gf119_sor_dp_drv_ctl,
+};
+
+int
+gm107_sor_dp_new(struct nvkm_disp *disp, int index,
+		 struct dcb_output *dcbE, struct nvkm_output **poutp)
+{
+	return nvkm_output_dp_new_(&gm107_sor_dp_func, disp, index, dcbE, poutp);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgm200.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgm200.c
index 2cfbef9..c44fa7e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgm200.c
@@ -57,19 +57,6 @@
 }
 
 static int
-gm200_sor_dp_pattern(struct nvkm_output_dp *outp, int pattern)
-{
-	struct nvkm_device *device = outp->base.disp->engine.subdev.device;
-	const u32 soff = gm200_sor_soff(outp);
-	const u32 data = 0x01010101 * pattern;
-	if (outp->base.info.sorconf.link & 1)
-		nvkm_mask(device, 0x61c110 + soff, 0x0f0f0f0f, data);
-	else
-		nvkm_mask(device, 0x61c12c + soff, 0x0f0f0f0f, data);
-	return 0;
-}
-
-static int
 gm200_sor_dp_lnk_pwr(struct nvkm_output_dp *outp, int nr)
 {
 	struct nvkm_device *device = outp->base.disp->engine.subdev.device;
@@ -129,7 +116,7 @@
 
 static const struct nvkm_output_dp_func
 gm200_sor_dp_func = {
-	.pattern = gm200_sor_dp_pattern,
+	.pattern = gm107_sor_dp_pattern,
 	.lnk_pwr = gm200_sor_dp_lnk_pwr,
 	.lnk_ctl = gf119_sor_dp_lnk_ctl,
 	.drv_ctl = gm200_sor_dp_drv_ctl,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
index 9513bad..ae9ab5b 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
@@ -949,22 +949,41 @@
 }
 
 static const struct nvkm_enum gf100_mp_warp_error[] = {
-	{ 0x00, "NO_ERROR" },
-	{ 0x01, "STACK_MISMATCH" },
+	{ 0x01, "STACK_ERROR" },
+	{ 0x02, "API_STACK_ERROR" },
+	{ 0x03, "RET_EMPTY_STACK_ERROR" },
+	{ 0x04, "PC_WRAP" },
 	{ 0x05, "MISALIGNED_PC" },
-	{ 0x08, "MISALIGNED_GPR" },
-	{ 0x09, "INVALID_OPCODE" },
-	{ 0x0d, "GPR_OUT_OF_BOUNDS" },
-	{ 0x0e, "MEM_OUT_OF_BOUNDS" },
-	{ 0x0f, "UNALIGNED_MEM_ACCESS" },
+	{ 0x06, "PC_OVERFLOW" },
+	{ 0x07, "MISALIGNED_IMMC_ADDR" },
+	{ 0x08, "MISALIGNED_REG" },
+	{ 0x09, "ILLEGAL_INSTR_ENCODING" },
+	{ 0x0a, "ILLEGAL_SPH_INSTR_COMBO" },
+	{ 0x0b, "ILLEGAL_INSTR_PARAM" },
+	{ 0x0c, "INVALID_CONST_ADDR" },
+	{ 0x0d, "OOR_REG" },
+	{ 0x0e, "OOR_ADDR" },
+	{ 0x0f, "MISALIGNED_ADDR" },
 	{ 0x10, "INVALID_ADDR_SPACE" },
-	{ 0x11, "INVALID_PARAM" },
+	{ 0x11, "ILLEGAL_INSTR_PARAM2" },
+	{ 0x12, "INVALID_CONST_ADDR_LDC" },
+	{ 0x13, "GEOMETRY_SM_ERROR" },
+	{ 0x14, "DIVERGENT" },
+	{ 0x15, "WARP_EXIT" },
 	{}
 };
 
 static const struct nvkm_bitfield gf100_mp_global_error[] = {
+	{ 0x00000001, "SM_TO_SM_FAULT" },
+	{ 0x00000002, "L1_ERROR" },
 	{ 0x00000004, "MULTIPLE_WARP_ERRORS" },
-	{ 0x00000008, "OUT_OF_STACK_SPACE" },
+	{ 0x00000008, "PHYSICAL_STACK_OVERFLOW" },
+	{ 0x00000010, "BPT_INT" },
+	{ 0x00000020, "BPT_PAUSE" },
+	{ 0x00000040, "SINGLE_STEP_COMPLETE" },
+	{ 0x20000000, "ECC_SEC_ERROR" },
+	{ 0x40000000, "ECC_DED_ERROR" },
+	{ 0x80000000, "TIMEOUT" },
 	{}
 };
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/disp.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/disp.c
index a5e9213..9efb1b4 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/disp.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/disp.c
@@ -141,7 +141,8 @@
 {
 	u16 data = nvbios_ocfg_entry(bios, outp, idx, ver, hdr, cnt, len);
 	if (data) {
-		info->match     = nvbios_rd16(bios, data + 0x00);
+		info->proto     = nvbios_rd08(bios, data + 0x00);
+		info->flags     = nvbios_rd16(bios, data + 0x01);
 		info->clkcmp[0] = nvbios_rd16(bios, data + 0x02);
 		info->clkcmp[1] = nvbios_rd16(bios, data + 0x04);
 	}
@@ -149,12 +150,13 @@
 }
 
 u16
-nvbios_ocfg_match(struct nvkm_bios *bios, u16 outp, u16 type,
+nvbios_ocfg_match(struct nvkm_bios *bios, u16 outp, u8 proto, u8 flags,
 		  u8 *ver, u8 *hdr, u8 *cnt, u8 *len, struct nvbios_ocfg *info)
 {
 	u16 data, idx = 0;
 	while ((data = nvbios_ocfg_parse(bios, outp, idx++, ver, hdr, cnt, len, info))) {
-		if (info->match == type)
+		if ((info->proto == proto || info->proto == 0xff) &&
+		    (info->flags == flags))
 			break;
 	}
 	return data;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gm107.c b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gm107.c
index e292f56..389fb13 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gm107.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gm107.c
@@ -69,11 +69,11 @@
 }
 
 static void
-gm107_ltc_lts_isr(struct nvkm_ltc *ltc, int c, int s)
+gm107_ltc_intr_lts(struct nvkm_ltc *ltc, int c, int s)
 {
 	struct nvkm_subdev *subdev = &ltc->subdev;
 	struct nvkm_device *device = subdev->device;
-	u32 base = 0x140000 + (c * 0x2000) + (s * 0x200);
+	u32 base = 0x140400 + (c * 0x2000) + (s * 0x200);
 	u32 stat = nvkm_rd32(device, base + 0x00c);
 
 	if (stat) {
@@ -92,7 +92,7 @@
 	while (mask) {
 		u32 s, c = __ffs(mask);
 		for (s = 0; s < ltc->lts_nr; s++)
-			gm107_ltc_lts_isr(ltc, c, s);
+			gm107_ltc_intr_lts(ltc, c, s);
 		mask &= ~(1 << c);
 	}
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gm200.c b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gm200.c
index 2a29bfd..e18e0dc 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gm200.c
@@ -46,7 +46,7 @@
 gm200_ltc = {
 	.oneinit = gm200_ltc_oneinit,
 	.init = gm200_ltc_init,
-	.intr = gm107_ltc_intr, /*XXX: not validated */
+	.intr = gm107_ltc_intr,
 	.cbc_clear = gm107_ltc_cbc_clear,
 	.cbc_wait = gm107_ltc_cbc_wait,
 	.zbc = 16,
diff --git a/drivers/gpu/drm/omapdrm/Kconfig b/drivers/gpu/drm/omapdrm/Kconfig
index 73241c4..336ad4d 100644
--- a/drivers/gpu/drm/omapdrm/Kconfig
+++ b/drivers/gpu/drm/omapdrm/Kconfig
@@ -2,6 +2,7 @@
 	tristate "OMAP DRM"
 	depends on DRM
 	depends on ARCH_OMAP2PLUS || ARCH_MULTIPLATFORM
+	select OMAP2_DSS
 	select DRM_KMS_HELPER
 	select DRM_KMS_FB_HELPER
 	select FB_SYS_FILLRECT
diff --git a/drivers/gpu/drm/omapdrm/displays/connector-hdmi.c b/drivers/gpu/drm/omapdrm/displays/connector-hdmi.c
index 225fd8d..667ca4a 100644
--- a/drivers/gpu/drm/omapdrm/displays/connector-hdmi.c
+++ b/drivers/gpu/drm/omapdrm/displays/connector-hdmi.c
@@ -9,6 +9,7 @@
  * the Free Software Foundation.
  */
 
+#include <linux/gpio/consumer.h>
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
diff --git a/drivers/gpu/drm/omapdrm/displays/encoder-opa362.c b/drivers/gpu/drm/omapdrm/displays/encoder-opa362.c
index 8c246c2..9594ff7 100644
--- a/drivers/gpu/drm/omapdrm/displays/encoder-opa362.c
+++ b/drivers/gpu/drm/omapdrm/displays/encoder-opa362.c
@@ -14,7 +14,7 @@
  * the Free Software Foundation.
  */
 
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
diff --git a/drivers/gpu/drm/omapdrm/displays/encoder-tfp410.c b/drivers/gpu/drm/omapdrm/displays/encoder-tfp410.c
index 2fd5602..671806c 100644
--- a/drivers/gpu/drm/omapdrm/displays/encoder-tfp410.c
+++ b/drivers/gpu/drm/omapdrm/displays/encoder-tfp410.c
@@ -9,7 +9,7 @@
  * the Free Software Foundation.
  */
 
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
diff --git a/drivers/gpu/drm/omapdrm/displays/panel-dpi.c b/drivers/gpu/drm/omapdrm/displays/panel-dpi.c
index e780fd4..7c2331b 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-dpi.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-dpi.c
@@ -9,7 +9,7 @@
  * the Free Software Foundation.
  */
 
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
diff --git a/drivers/gpu/drm/omapdrm/displays/panel-dsi-cm.c b/drivers/gpu/drm/omapdrm/displays/panel-dsi-cm.c
index 36485c2..2b11807 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-dsi-cm.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-dsi-cm.c
@@ -14,7 +14,7 @@
 #include <linux/backlight.h>
 #include <linux/delay.h>
 #include <linux/fb.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/interrupt.h>
 #include <linux/jiffies.h>
 #include <linux/module.h>
diff --git a/drivers/gpu/drm/omapdrm/displays/panel-lgphilips-lb035q02.c b/drivers/gpu/drm/omapdrm/displays/panel-lgphilips-lb035q02.c
index 458f77b..ac680e1 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-lgphilips-lb035q02.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-lgphilips-lb035q02.c
@@ -15,6 +15,7 @@
 #include <linux/spi/spi.h>
 #include <linux/mutex.h>
 #include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 
 #include <video/omapdss.h>
 #include <video/omap-panel-data.h>
diff --git a/drivers/gpu/drm/omapdrm/displays/panel-nec-nl8048hl11.c b/drivers/gpu/drm/omapdrm/displays/panel-nec-nl8048hl11.c
index 780cb26..38d2920 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-nec-nl8048hl11.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-nec-nl8048hl11.c
@@ -15,7 +15,7 @@
 #include <linux/delay.h>
 #include <linux/spi/spi.h>
 #include <linux/fb.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/of_gpio.h>
 
 #include <video/omapdss.h>
diff --git a/drivers/gpu/drm/omapdrm/displays/panel-sharp-ls037v7dw01.c b/drivers/gpu/drm/omapdrm/displays/panel-sharp-ls037v7dw01.c
index 529a017..4363fff 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-sharp-ls037v7dw01.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-sharp-ls037v7dw01.c
@@ -10,7 +10,7 @@
  */
 
 #include <linux/delay.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_gpio.h>
diff --git a/drivers/gpu/drm/omapdrm/displays/panel-sony-acx565akm.c b/drivers/gpu/drm/omapdrm/displays/panel-sony-acx565akm.c
index 31efcca..deb4167 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-sony-acx565akm.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-sony-acx565akm.c
@@ -29,7 +29,7 @@
 #include <linux/sched.h>
 #include <linux/backlight.h>
 #include <linux/fb.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/of.h>
 #include <linux/of_gpio.h>
 
diff --git a/drivers/gpu/drm/omapdrm/displays/panel-tpo-td043mtea1.c b/drivers/gpu/drm/omapdrm/displays/panel-tpo-td043mtea1.c
index 03e2beb..d93175b 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-tpo-td043mtea1.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-tpo-td043mtea1.c
@@ -14,7 +14,7 @@
 #include <linux/delay.h>
 #include <linux/spi/spi.h>
 #include <linux/regulator/consumer.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/of_gpio.h>
diff --git a/drivers/gpu/drm/omapdrm/dss/dsi.c b/drivers/gpu/drm/omapdrm/dss/dsi.c
index 8730646..56c43f3 100644
--- a/drivers/gpu/drm/omapdrm/dss/dsi.c
+++ b/drivers/gpu/drm/omapdrm/dss/dsi.c
@@ -1167,7 +1167,6 @@
 {
 	struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
 	struct regulator *vdds_dsi;
-	int r;
 
 	if (dsi->vdds_dsi_reg != NULL)
 		return 0;
@@ -1180,15 +1179,6 @@
 		return PTR_ERR(vdds_dsi);
 	}
 
-	if (regulator_can_change_voltage(vdds_dsi)) {
-		r = regulator_set_voltage(vdds_dsi, 1800000, 1800000);
-		if (r) {
-			devm_regulator_put(vdds_dsi);
-			DSSERR("can't set the DSI regulator voltage\n");
-			return r;
-		}
-	}
-
 	dsi->vdds_dsi_reg = vdds_dsi;
 
 	return 0;
diff --git a/drivers/gpu/drm/omapdrm/dss/dss.c b/drivers/gpu/drm/omapdrm/dss/dss.c
index f95ff31..3303cfa 100644
--- a/drivers/gpu/drm/omapdrm/dss/dss.c
+++ b/drivers/gpu/drm/omapdrm/dss/dss.c
@@ -30,6 +30,7 @@
 #include <linux/delay.h>
 #include <linux/seq_file.h>
 #include <linux/clk.h>
+#include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/gfp.h>
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi4.c b/drivers/gpu/drm/omapdrm/dss/hdmi4.c
index f892ae15..4d46cdf 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi4.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi4.c
@@ -33,6 +33,7 @@
 #include <linux/gpio.h>
 #include <linux/regulator/consumer.h>
 #include <linux/component.h>
+#include <linux/of.h>
 #include <video/omapdss.h>
 #include <sound/omap-hdmi-audio.h>
 
@@ -100,7 +101,6 @@
 
 static int hdmi_init_regulator(void)
 {
-	int r;
 	struct regulator *reg;
 
 	if (hdmi.vdda_reg != NULL)
@@ -114,15 +114,6 @@
 		return PTR_ERR(reg);
 	}
 
-	if (regulator_can_change_voltage(reg)) {
-		r = regulator_set_voltage(reg, 1800000, 1800000);
-		if (r) {
-			devm_regulator_put(reg);
-			DSSWARN("can't set the regulator voltage\n");
-			return r;
-		}
-	}
-
 	hdmi.vdda_reg = reg;
 
 	return 0;
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi4_core.c b/drivers/gpu/drm/omapdrm/dss/hdmi4_core.c
index fa72e73..ef3afe9 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi4_core.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi4_core.c
@@ -211,7 +211,7 @@
 static void hdmi_core_powerdown_disable(struct hdmi_core_data *core)
 {
 	DSSDBG("Enter hdmi_core_powerdown_disable\n");
-	REG_FLD_MOD(core->base, HDMI_CORE_SYS_SYS_CTRL1, 0x0, 0, 0);
+	REG_FLD_MOD(core->base, HDMI_CORE_SYS_SYS_CTRL1, 0x1, 0, 0);
 }
 
 static void hdmi_core_swreset_release(struct hdmi_core_data *core)
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi5.c b/drivers/gpu/drm/omapdrm/dss/hdmi5.c
index a43f7b1..9255c0e1 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi5.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi5.c
@@ -38,6 +38,7 @@
 #include <linux/gpio.h>
 #include <linux/regulator/consumer.h>
 #include <linux/component.h>
+#include <linux/of.h>
 #include <video/omapdss.h>
 #include <sound/omap-hdmi-audio.h>
 
@@ -119,7 +120,6 @@
 
 static int hdmi_init_regulator(void)
 {
-	int r;
 	struct regulator *reg;
 
 	if (hdmi.vdda_reg != NULL)
@@ -131,15 +131,6 @@
 		return PTR_ERR(reg);
 	}
 
-	if (regulator_can_change_voltage(reg)) {
-		r = regulator_set_voltage(reg, 1800000, 1800000);
-		if (r) {
-			devm_regulator_put(reg);
-			DSSWARN("can't set the regulator voltage\n");
-			return r;
-		}
-	}
-
 	hdmi.vdda_reg = reg;
 
 	return 0;
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi5_core.c b/drivers/gpu/drm/omapdrm/dss/hdmi5_core.c
index 6a39752..8ab2093 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi5_core.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi5_core.c
@@ -51,8 +51,8 @@
 {
 	void __iomem *base = core->base;
 	const unsigned long long iclk = 266000000;	/* DSS L3 ICLK */
-	const unsigned ss_scl_high = 4000;		/* ns */
-	const unsigned ss_scl_low = 4700;		/* ns */
+	const unsigned ss_scl_high = 4600;		/* ns */
+	const unsigned ss_scl_low = 5400;		/* ns */
 	const unsigned fs_scl_high = 600;		/* ns */
 	const unsigned fs_scl_low = 1300;		/* ns */
 	const unsigned sda_hold = 1000;			/* ns */
@@ -458,7 +458,7 @@
 
 	c = (ptr[1] >> 6) & 0x3;
 	m = (ptr[1] >> 4) & 0x3;
-	r = (ptr[1] >> 0) & 0x3;
+	r = (ptr[1] >> 0) & 0xf;
 
 	itc = (ptr[2] >> 7) & 0x1;
 	ec = (ptr[2] >> 4) & 0x7;
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi_phy.c b/drivers/gpu/drm/omapdrm/dss/hdmi_phy.c
index 1f5d19c..f98b750 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi_phy.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi_phy.c
@@ -13,6 +13,7 @@
 #include <linux/io.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
+#include <linux/seq_file.h>
 #include <video/omapdss.h>
 
 #include "dss.h"
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi_pll.c b/drivers/gpu/drm/omapdrm/dss/hdmi_pll.c
index 06e23a7..f1015e8 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi_pll.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi_pll.c
@@ -16,6 +16,7 @@
 #include <linux/io.h>
 #include <linux/platform_device.h>
 #include <linux/clk.h>
+#include <linux/seq_file.h>
 
 #include <video/omapdss.h>
 
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi_wp.c b/drivers/gpu/drm/omapdrm/dss/hdmi_wp.c
index 13442b9..055f62f 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi_wp.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi_wp.c
@@ -14,6 +14,7 @@
 #include <linux/err.h>
 #include <linux/io.h>
 #include <linux/platform_device.h>
+#include <linux/seq_file.h>
 #include <video/omapdss.h>
 
 #include "dss.h"
diff --git a/drivers/gpu/drm/omapdrm/omap_debugfs.c b/drivers/gpu/drm/omapdrm/omap_debugfs.c
index 6f5fc14..479bf24 100644
--- a/drivers/gpu/drm/omapdrm/omap_debugfs.c
+++ b/drivers/gpu/drm/omapdrm/omap_debugfs.c
@@ -17,6 +17,8 @@
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/seq_file.h>
+
 #include <drm/drm_crtc.h>
 #include <drm/drm_fb_helper.h>
 
diff --git a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
index de275a5..4ceed7a9 100644
--- a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
+++ b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
@@ -27,6 +27,7 @@
 #include <linux/module.h>
 #include <linux/platform_device.h> /* platform_device() */
 #include <linux/sched.h>
+#include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/time.h>
 #include <linux/vmalloc.h>
diff --git a/drivers/gpu/drm/omapdrm/omap_fb.c b/drivers/gpu/drm/omapdrm/omap_fb.c
index 94ec06d..f84570d 100644
--- a/drivers/gpu/drm/omapdrm/omap_fb.c
+++ b/drivers/gpu/drm/omapdrm/omap_fb.c
@@ -17,6 +17,8 @@
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/seq_file.h>
+
 #include <drm/drm_crtc.h>
 #include <drm/drm_crtc_helper.h>
 
diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index b97afc2..03698b6 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem.c
@@ -17,6 +17,7 @@
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/seq_file.h>
 #include <linux/shmem_fs.h>
 #include <linux/spinlock.h>
 #include <linux/pfn_t.h>
diff --git a/drivers/gpu/drm/sti/sti_crtc.c b/drivers/gpu/drm/sti/sti_crtc.c
index 505620c..e04deed 100644
--- a/drivers/gpu/drm/sti/sti_crtc.c
+++ b/drivers/gpu/drm/sti/sti_crtc.c
@@ -51,15 +51,6 @@
 	mixer->status = STI_MIXER_DISABLING;
 }
 
-static bool sti_crtc_mode_fixup(struct drm_crtc *crtc,
-				const struct drm_display_mode *mode,
-				struct drm_display_mode *adjusted_mode)
-{
-	/* accept the provided drm_display_mode, do not fix it up */
-	drm_mode_set_crtcinfo(adjusted_mode, CRTC_INTERLACE_HALVE_V);
-	return true;
-}
-
 static int
 sti_crtc_mode_set(struct drm_crtc *crtc, struct drm_display_mode *mode)
 {
@@ -230,7 +221,6 @@
 static const struct drm_crtc_helper_funcs sti_crtc_helper_funcs = {
 	.enable = sti_crtc_enable,
 	.disable = sti_crtc_disabling,
-	.mode_fixup = sti_crtc_mode_fixup,
 	.mode_set = drm_helper_crtc_mode_set,
 	.mode_set_nofb = sti_crtc_mode_set_nofb,
 	.mode_set_base = drm_helper_crtc_mode_set_base,
diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c
index 904d075..0f18b76 100644
--- a/drivers/gpu/drm/vc4/vc4_crtc.c
+++ b/drivers/gpu/drm/vc4/vc4_crtc.c
@@ -456,14 +456,6 @@
 
 	WARN_ON_ONCE(dlist_next - dlist_start != vc4_state->mm.size);
 
-	HVS_WRITE(SCALER_DISPLISTX(vc4_crtc->channel),
-		  vc4_state->mm.start);
-
-	if (debug_dump_regs) {
-		DRM_INFO("CRTC %d HVS after:\n", drm_crtc_index(crtc));
-		vc4_hvs_dump_state(dev);
-	}
-
 	if (crtc->state->event) {
 		unsigned long flags;
 
@@ -473,8 +465,20 @@
 
 		spin_lock_irqsave(&dev->event_lock, flags);
 		vc4_crtc->event = crtc->state->event;
-		spin_unlock_irqrestore(&dev->event_lock, flags);
 		crtc->state->event = NULL;
+
+		HVS_WRITE(SCALER_DISPLISTX(vc4_crtc->channel),
+			  vc4_state->mm.start);
+
+		spin_unlock_irqrestore(&dev->event_lock, flags);
+	} else {
+		HVS_WRITE(SCALER_DISPLISTX(vc4_crtc->channel),
+			  vc4_state->mm.start);
+	}
+
+	if (debug_dump_regs) {
+		DRM_INFO("CRTC %d HVS after:\n", drm_crtc_index(crtc));
+		vc4_hvs_dump_state(dev);
 	}
 }
 
@@ -500,12 +504,17 @@
 {
 	struct drm_crtc *crtc = &vc4_crtc->base;
 	struct drm_device *dev = crtc->dev;
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(crtc->state);
+	u32 chan = vc4_crtc->channel;
 	unsigned long flags;
 
 	spin_lock_irqsave(&dev->event_lock, flags);
-	if (vc4_crtc->event) {
+	if (vc4_crtc->event &&
+	    (vc4_state->mm.start == HVS_READ(SCALER_DISPLACTX(chan)))) {
 		drm_crtc_send_vblank_event(crtc, vc4_crtc->event);
 		vc4_crtc->event = NULL;
+		drm_crtc_vblank_put(crtc);
 	}
 	spin_unlock_irqrestore(&dev->event_lock, flags);
 }
@@ -556,6 +565,7 @@
 		spin_unlock_irqrestore(&dev->event_lock, flags);
 	}
 
+	drm_crtc_vblank_put(crtc);
 	drm_framebuffer_unreference(flip_state->fb);
 	kfree(flip_state);
 
@@ -598,6 +608,8 @@
 		return ret;
 	}
 
+	WARN_ON(drm_crtc_vblank_get(crtc) != 0);
+
 	/* Immediately update the plane's legacy fb pointer, so that later
 	 * modeset prep sees the state that will be present when the semaphore
 	 * is released.
diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c
index 3446ece..250ed7e 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.c
+++ b/drivers/gpu/drm/vc4/vc4_drv.c
@@ -66,12 +66,12 @@
 };
 
 static const struct drm_ioctl_desc vc4_drm_ioctls[] = {
-	DRM_IOCTL_DEF_DRV(VC4_SUBMIT_CL, vc4_submit_cl_ioctl, 0),
-	DRM_IOCTL_DEF_DRV(VC4_WAIT_SEQNO, vc4_wait_seqno_ioctl, 0),
-	DRM_IOCTL_DEF_DRV(VC4_WAIT_BO, vc4_wait_bo_ioctl, 0),
-	DRM_IOCTL_DEF_DRV(VC4_CREATE_BO, vc4_create_bo_ioctl, 0),
-	DRM_IOCTL_DEF_DRV(VC4_MMAP_BO, vc4_mmap_bo_ioctl, 0),
-	DRM_IOCTL_DEF_DRV(VC4_CREATE_SHADER_BO, vc4_create_shader_bo_ioctl, 0),
+	DRM_IOCTL_DEF_DRV(VC4_SUBMIT_CL, vc4_submit_cl_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VC4_WAIT_SEQNO, vc4_wait_seqno_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VC4_WAIT_BO, vc4_wait_bo_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VC4_CREATE_BO, vc4_create_bo_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VC4_MMAP_BO, vc4_mmap_bo_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VC4_CREATE_SHADER_BO, vc4_create_shader_bo_ioctl, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(VC4_GET_HANG_STATE, vc4_get_hang_state_ioctl,
 			  DRM_ROOT_ONLY),
 };
@@ -91,7 +91,7 @@
 
 	.enable_vblank = vc4_enable_vblank,
 	.disable_vblank = vc4_disable_vblank,
-	.get_vblank_counter = drm_vblank_count,
+	.get_vblank_counter = drm_vblank_no_hw_counter,
 
 #if defined(CONFIG_DEBUG_FS)
 	.debugfs_init = vc4_debugfs_init,
diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c
index cb37751..861a623 100644
--- a/drivers/gpu/drm/vc4/vc4_kms.c
+++ b/drivers/gpu/drm/vc4/vc4_kms.c
@@ -117,10 +117,18 @@
 		return -ENOMEM;
 
 	/* Make sure that any outstanding modesets have finished. */
-	ret = down_interruptible(&vc4->async_modeset);
-	if (ret) {
-		kfree(c);
-		return ret;
+	if (nonblock) {
+		ret = down_trylock(&vc4->async_modeset);
+		if (ret) {
+			kfree(c);
+			return -EBUSY;
+		}
+	} else {
+		ret = down_interruptible(&vc4->async_modeset);
+		if (ret) {
+			kfree(c);
+			return ret;
+		}
 	}
 
 	ret = drm_atomic_helper_prepare_planes(dev, state);
diff --git a/drivers/gpu/drm/vc4/vc4_regs.h b/drivers/gpu/drm/vc4/vc4_regs.h
index 6163b95..f99eece 100644
--- a/drivers/gpu/drm/vc4/vc4_regs.h
+++ b/drivers/gpu/drm/vc4/vc4_regs.h
@@ -341,6 +341,10 @@
 #define SCALER_DISPLACT0                        0x00000030
 #define SCALER_DISPLACT1                        0x00000034
 #define SCALER_DISPLACT2                        0x00000038
+#define SCALER_DISPLACTX(x)			(SCALER_DISPLACT0 +	\
+						 (x) * (SCALER_DISPLACT1 - \
+							SCALER_DISPLACT0))
+
 #define SCALER_DISPCTRL0                        0x00000040
 # define SCALER_DISPCTRLX_ENABLE		BIT(31)
 # define SCALER_DISPCTRLX_RESET			BIT(30)
diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c
index c2e257d..0409667 100644
--- a/drivers/infiniband/core/cache.c
+++ b/drivers/infiniband/core/cache.c
@@ -178,6 +178,7 @@
 {
 	int ret = 0;
 	struct net_device *old_net_dev;
+	enum ib_gid_type old_gid_type;
 
 	/* in rdma_cap_roce_gid_table, this funciton should be protected by a
 	 * sleep-able lock.
@@ -199,6 +200,7 @@
 	}
 
 	old_net_dev = table->data_vec[ix].attr.ndev;
+	old_gid_type = table->data_vec[ix].attr.gid_type;
 	if (old_net_dev && old_net_dev != attr->ndev)
 		dev_put(old_net_dev);
 	/* if modify_gid failed, just delete the old gid */
@@ -207,10 +209,14 @@
 		attr = &zattr;
 		table->data_vec[ix].context = NULL;
 	}
-	if (default_gid)
-		table->data_vec[ix].props |= GID_TABLE_ENTRY_DEFAULT;
+
 	memcpy(&table->data_vec[ix].gid, gid, sizeof(*gid));
 	memcpy(&table->data_vec[ix].attr, attr, sizeof(*attr));
+	if (default_gid) {
+		table->data_vec[ix].props |= GID_TABLE_ENTRY_DEFAULT;
+		if (action == GID_TABLE_WRITE_ACTION_DEL)
+			table->data_vec[ix].attr.gid_type = old_gid_type;
+	}
 	if (table->data_vec[ix].attr.ndev &&
 	    table->data_vec[ix].attr.ndev != old_net_dev)
 		dev_hold(table->data_vec[ix].attr.ndev);
diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index 1d92e09..c995255 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -3452,14 +3452,14 @@
 	work->cm_event.event = IB_CM_USER_ESTABLISHED;
 
 	/* Check if the device started its remove_one */
-	spin_lock_irq(&cm.lock);
+	spin_lock_irqsave(&cm.lock, flags);
 	if (!cm_dev->going_down) {
 		queue_delayed_work(cm.wq, &work->work, 0);
 	} else {
 		kfree(work);
 		ret = -ENODEV;
 	}
-	spin_unlock_irq(&cm.lock);
+	spin_unlock_irqrestore(&cm.lock, flags);
 
 out:
 	return ret;
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 5516fb0..5c155fa 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -661,6 +661,9 @@
 	if (err || port_attr->subnet_prefix)
 		return err;
 
+	if (rdma_port_get_link_layer(device, port_num) != IB_LINK_LAYER_INFINIBAND)
+		return 0;
+
 	err = ib_query_gid(device, port_num, 0, &gid, NULL);
 	if (err)
 		return err;
@@ -1024,7 +1027,8 @@
 		goto err_mad;
 	}
 
-	if (ib_add_ibnl_clients()) {
+	ret = ib_add_ibnl_clients();
+	if (ret) {
 		pr_warn("Couldn't register ibnl clients\n");
 		goto err_sa;
 	}
diff --git a/drivers/infiniband/core/iwpm_msg.c b/drivers/infiniband/core/iwpm_msg.c
index 43e3fa2..1c41b95 100644
--- a/drivers/infiniband/core/iwpm_msg.c
+++ b/drivers/infiniband/core/iwpm_msg.c
@@ -506,7 +506,7 @@
 	if (!nlmsg_request) {
 		pr_info("%s: Could not find a matching request (seq = %u)\n",
 				 __func__, msg_seq);
-			return -EINVAL;
+		return -EINVAL;
 	}
 	pm_msg = nlmsg_request->req_buffer;
 	local_sockaddr = (struct sockaddr_storage *)
diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c
index 82fb511..2d49228 100644
--- a/drivers/infiniband/core/mad.c
+++ b/drivers/infiniband/core/mad.c
@@ -1638,9 +1638,9 @@
 		/* Now, check to see if there are any methods still in use */
 		if (!check_method_table(method)) {
 			/* If not, release management method table */
-			 kfree(method);
-			 class->method_table[mgmt_class] = NULL;
-			 /* Any management classes left ? */
+			kfree(method);
+			class->method_table[mgmt_class] = NULL;
+			/* Any management classes left ? */
 			if (!check_class_table(class)) {
 				/* If not, release management class table */
 				kfree(class);
diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c
index 5e573bb..a5793c8 100644
--- a/drivers/infiniband/core/sysfs.c
+++ b/drivers/infiniband/core/sysfs.c
@@ -889,9 +889,9 @@
 static void setup_hw_stats(struct ib_device *device, struct ib_port *port,
 			   u8 port_num)
 {
-	struct attribute_group *hsag = NULL;
+	struct attribute_group *hsag;
 	struct rdma_hw_stats *stats;
-	int i = 0, ret;
+	int i, ret;
 
 	stats = device->alloc_hw_stats(device, port_num);
 
@@ -899,19 +899,22 @@
 		return;
 
 	if (!stats->names || stats->num_counters <= 0)
-		goto err;
+		goto err_free_stats;
 
+	/*
+	 * Two extra attribue elements here, one for the lifespan entry and
+	 * one to NULL terminate the list for the sysfs core code
+	 */
 	hsag = kzalloc(sizeof(*hsag) +
-		       // 1 extra for the lifespan config entry
-		       sizeof(void *) * (stats->num_counters + 1),
+		       sizeof(void *) * (stats->num_counters + 2),
 		       GFP_KERNEL);
 	if (!hsag)
-		return;
+		goto err_free_stats;
 
 	ret = device->get_hw_stats(device, stats, port_num,
 				   stats->num_counters);
 	if (ret != stats->num_counters)
-		goto err;
+		goto err_free_hsag;
 
 	stats->timestamp = jiffies;
 
@@ -922,10 +925,13 @@
 		hsag->attrs[i] = alloc_hsa(i, port_num, stats->names[i]);
 		if (!hsag->attrs[i])
 			goto err;
+		sysfs_attr_init(hsag->attrs[i]);
 	}
 
 	/* treat an error here as non-fatal */
 	hsag->attrs[i] = alloc_hsa_lifespan("lifespan", port_num);
+	if (hsag->attrs[i])
+		sysfs_attr_init(hsag->attrs[i]);
 
 	if (port) {
 		struct kobject *kobj = &port->kobj;
@@ -946,10 +952,12 @@
 	return;
 
 err:
-	kfree(stats);
 	for (; i >= 0; i--)
 		kfree(hsag->attrs[i]);
+err_free_hsag:
 	kfree(hsag);
+err_free_stats:
+	kfree(stats);
 	return;
 }
 
diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c
index 6e7050a..14d7eeb 100644
--- a/drivers/infiniband/hw/hfi1/affinity.c
+++ b/drivers/infiniband/hw/hfi1/affinity.c
@@ -300,16 +300,15 @@
 	const struct cpumask *node_mask,
 		*proc_mask = tsk_cpus_allowed(current);
 	struct cpu_mask_set *set = &dd->affinity->proc;
-	char buf[1024];
 
 	/*
 	 * check whether process/context affinity has already
 	 * been set
 	 */
 	if (cpumask_weight(proc_mask) == 1) {
-		scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(proc_mask));
-		hfi1_cdbg(PROC, "PID %u %s affinity set to CPU %s",
-			  current->pid, current->comm, buf);
+		hfi1_cdbg(PROC, "PID %u %s affinity set to CPU %*pbl",
+			  current->pid, current->comm,
+			  cpumask_pr_args(proc_mask));
 		/*
 		 * Mark the pre-set CPU as used. This is atomic so we don't
 		 * need the lock
@@ -318,9 +317,9 @@
 		cpumask_set_cpu(cpu, &set->used);
 		goto done;
 	} else if (cpumask_weight(proc_mask) < cpumask_weight(&set->mask)) {
-		scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(proc_mask));
-		hfi1_cdbg(PROC, "PID %u %s affinity set to CPU set(s) %s",
-			  current->pid, current->comm, buf);
+		hfi1_cdbg(PROC, "PID %u %s affinity set to CPU set(s) %*pbl",
+			  current->pid, current->comm,
+			  cpumask_pr_args(proc_mask));
 		goto done;
 	}
 
@@ -356,8 +355,8 @@
 	cpumask_or(intrs, intrs, (dd->affinity->rcv_intr.gen ?
 				  &dd->affinity->rcv_intr.mask :
 				  &dd->affinity->rcv_intr.used));
-	scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(intrs));
-	hfi1_cdbg(PROC, "CPUs used by interrupts: %s", buf);
+	hfi1_cdbg(PROC, "CPUs used by interrupts: %*pbl",
+		  cpumask_pr_args(intrs));
 
 	/*
 	 * If we don't have a NUMA node requested, preference is towards
@@ -366,18 +365,16 @@
 	if (node == -1)
 		node = dd->node;
 	node_mask = cpumask_of_node(node);
-	scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(node_mask));
-	hfi1_cdbg(PROC, "device on NUMA %u, CPUs %s", node, buf);
+	hfi1_cdbg(PROC, "device on NUMA %u, CPUs %*pbl", node,
+		  cpumask_pr_args(node_mask));
 
 	/* diff will hold all unused cpus */
 	cpumask_andnot(diff, &set->mask, &set->used);
-	scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(diff));
-	hfi1_cdbg(PROC, "unused CPUs (all) %s", buf);
+	hfi1_cdbg(PROC, "unused CPUs (all) %*pbl", cpumask_pr_args(diff));
 
 	/* get cpumask of available CPUs on preferred NUMA */
 	cpumask_and(mask, diff, node_mask);
-	scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(mask));
-	hfi1_cdbg(PROC, "available cpus on NUMA %s", buf);
+	hfi1_cdbg(PROC, "available cpus on NUMA %*pbl", cpumask_pr_args(mask));
 
 	/*
 	 * At first, we don't want to place processes on the same
@@ -395,8 +392,8 @@
 		cpumask_andnot(diff, &set->mask, &set->used);
 		cpumask_andnot(mask, diff, node_mask);
 	}
-	scnprintf(buf, 1024, "%*pbl", cpumask_pr_args(mask));
-	hfi1_cdbg(PROC, "possible CPUs for process %s", buf);
+	hfi1_cdbg(PROC, "possible CPUs for process %*pbl",
+		  cpumask_pr_args(mask));
 
 	cpu = cpumask_first(mask);
 	if (cpu >= nr_cpu_ids) /* empty */
diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index 3b876da..81619fb 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -7832,8 +7832,8 @@
 			 * save first 2 flits in the packet that caused
 			 * the error
 			 */
-			 dd->err_info_rcvport.packet_flit1 = hdr0;
-			 dd->err_info_rcvport.packet_flit2 = hdr1;
+			dd->err_info_rcvport.packet_flit1 = hdr0;
+			dd->err_info_rcvport.packet_flit2 = hdr1;
 		}
 		switch (info) {
 		case 1:
@@ -11906,7 +11906,7 @@
 		hfi1_cdbg(CNTR, "[%d] No update necessary", dd->unit);
 	}
 
-mod_timer(&dd->synth_stats_timer, jiffies + HZ * SYNTH_CNT_TIME);
+	mod_timer(&dd->synth_stats_timer, jiffies + HZ * SYNTH_CNT_TIME);
 }
 
 #define C_MAX_NAME 13 /* 12 chars + one for /0 */
diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index 5cc492e..0d28a5a 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -1337,7 +1337,7 @@
 		dma_free_coherent(&dd->pcidev->dev, sizeof(u64),
 				  (void *)dd->rcvhdrtail_dummy_kvaddr,
 				  dd->rcvhdrtail_dummy_physaddr);
-				  dd->rcvhdrtail_dummy_kvaddr = NULL;
+		dd->rcvhdrtail_dummy_kvaddr = NULL;
 	}
 
 	for (ctxt = 0; tmp && ctxt < dd->num_rcv_contexts; ctxt++) {
diff --git a/drivers/infiniband/hw/hfi1/trace.c b/drivers/infiniband/hw/hfi1/trace.c
index 79b2952..4cfb137 100644
--- a/drivers/infiniband/hw/hfi1/trace.c
+++ b/drivers/infiniband/hw/hfi1/trace.c
@@ -214,19 +214,6 @@
 	return ret;
 }
 
-const char *print_u64_array(
-	struct trace_seq *p,
-	u64 *arr, int len)
-{
-	int i;
-	const char *ret = trace_seq_buffer_ptr(p);
-
-	for (i = 0; i < len; i++)
-		trace_seq_printf(p, "%s0x%016llx", i == 0 ? "" : " ", arr[i]);
-	trace_seq_putc(p, 0);
-	return ret;
-}
-
 __hfi1_trace_fn(PKT);
 __hfi1_trace_fn(PROC);
 __hfi1_trace_fn(SDMA);
diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c
index 29f4795..47ffd27 100644
--- a/drivers/infiniband/hw/hfi1/user_sdma.c
+++ b/drivers/infiniband/hw/hfi1/user_sdma.c
@@ -183,7 +183,7 @@
 	struct sdma_mmu_node *node;
 };
 
-#define SDMA_CACHE_NODE_EVICT BIT(0)
+#define SDMA_CACHE_NODE_EVICT 0
 
 struct sdma_mmu_node {
 	struct mmu_rb_node rb;
@@ -1355,11 +1355,11 @@
 		 */
 		SDMA_DBG(req, "TID offset %ubytes %uunits om%u",
 			 req->tidoffset, req->tidoffset / req->omfactor,
-			 !!(req->omfactor - KDETH_OM_SMALL));
+			 req->omfactor != KDETH_OM_SMALL);
 		KDETH_SET(hdr->kdeth.ver_tid_offset, OFFSET,
 			  req->tidoffset / req->omfactor);
 		KDETH_SET(hdr->kdeth.ver_tid_offset, OM,
-			  !!(req->omfactor - KDETH_OM_SMALL));
+			  req->omfactor != KDETH_OM_SMALL);
 	}
 done:
 	trace_hfi1_sdma_user_header(pq->dd, pq->ctxt, pq->subctxt,
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index b01ef6e..0eb09e1 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -505,9 +505,9 @@
 			props->device_cap_flags |= IB_DEVICE_MEM_WINDOW_TYPE_2B;
 		else
 			props->device_cap_flags |= IB_DEVICE_MEM_WINDOW_TYPE_2A;
-	if (dev->steering_support ==  MLX4_STEERING_MODE_DEVICE_MANAGED)
-		props->device_cap_flags |= IB_DEVICE_MANAGED_FLOW_STEERING;
 	}
+	if (dev->steering_support == MLX4_STEERING_MODE_DEVICE_MANAGED)
+		props->device_cap_flags |= IB_DEVICE_MANAGED_FLOW_STEERING;
 
 	props->device_cap_flags |= IB_DEVICE_RAW_IP_CSUM;
 
diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index dabcc65..9c0e67b 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -822,7 +822,8 @@
 	int eqn;
 	int err;
 
-	if (entries < 0)
+	if (entries < 0 ||
+	    (entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz))))
 		return ERR_PTR(-EINVAL);
 
 	if (check_cq_create_flags(attr->flags))
@@ -1168,11 +1169,16 @@
 		return -ENOSYS;
 	}
 
-	if (entries < 1)
+	if (entries < 1 ||
+	    entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz))) {
+		mlx5_ib_warn(dev, "wrong entries number %d, max %d\n",
+			     entries,
+			     1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz));
 		return -EINVAL;
+	}
 
 	entries = roundup_pow_of_two(entries + 1);
-	if (entries >  (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz)) + 1)
+	if (entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz)) + 1)
 		return -EINVAL;
 
 	if (entries == ibcq->cqe + 1)
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index c72797c..b48ad85 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -524,6 +524,9 @@
 	    MLX5_CAP_ETH(dev->mdev, scatter_fcs))
 		props->device_cap_flags |= IB_DEVICE_RAW_SCATTER_FCS;
 
+	if (mlx5_get_flow_namespace(dev->mdev, MLX5_FLOW_NAMESPACE_BYPASS))
+		props->device_cap_flags |= IB_DEVICE_MANAGED_FLOW_STEERING;
+
 	props->vendor_part_id	   = mdev->pdev->device;
 	props->hw_ver		   = mdev->pdev->revision;
 
@@ -915,7 +918,8 @@
 	num_uars = req.total_num_uuars / MLX5_NON_FP_BF_REGS_PER_PAGE;
 	gross_uuars = num_uars * MLX5_BF_REGS_PER_PAGE;
 	resp.qp_tab_size = 1 << MLX5_CAP_GEN(dev->mdev, log_max_qp);
-	resp.bf_reg_size = 1 << MLX5_CAP_GEN(dev->mdev, log_bf_reg_size);
+	if (mlx5_core_is_pf(dev->mdev) && MLX5_CAP_GEN(dev->mdev, bf))
+		resp.bf_reg_size = 1 << MLX5_CAP_GEN(dev->mdev, log_bf_reg_size);
 	resp.cache_line_size = L1_CACHE_BYTES;
 	resp.max_sq_desc_sz = MLX5_CAP_GEN(dev->mdev, max_wqe_sz_sq);
 	resp.max_rq_desc_sz = MLX5_CAP_GEN(dev->mdev, max_wqe_sz_rq);
@@ -988,7 +992,14 @@
 	if (field_avail(typeof(resp), cqe_version, udata->outlen))
 		resp.response_length += sizeof(resp.cqe_version);
 
-	if (field_avail(typeof(resp), hca_core_clock_offset, udata->outlen)) {
+	/*
+	 * We don't want to expose information from the PCI bar that is located
+	 * after 4096 bytes, so if the arch only supports larger pages, let's
+	 * pretend we don't support reading the HCA's core clock. This is also
+	 * forced by mmap function.
+	 */
+	if (PAGE_SIZE <= 4096 &&
+	    field_avail(typeof(resp), hca_core_clock_offset, udata->outlen)) {
 		resp.comp_mask |=
 			MLX5_IB_ALLOC_UCONTEXT_RESP_MASK_CORE_CLOCK_OFFSET;
 		resp.hca_core_clock_offset =
@@ -1798,7 +1809,7 @@
 {
 	struct mlx5_ib_dev *dev =
 		container_of(device, struct mlx5_ib_dev, ib_dev.dev);
-	return sprintf(buf, "%d.%d.%d\n", fw_rev_maj(dev->mdev),
+	return sprintf(buf, "%d.%d.%04d\n", fw_rev_maj(dev->mdev),
 		       fw_rev_min(dev->mdev), fw_rev_sub(dev->mdev));
 }
 
@@ -1866,14 +1877,11 @@
 		break;
 
 	case MLX5_DEV_EVENT_PORT_DOWN:
+	case MLX5_DEV_EVENT_PORT_INITIALIZED:
 		ibev.event = IB_EVENT_PORT_ERR;
 		port = (u8)param;
 		break;
 
-	case MLX5_DEV_EVENT_PORT_INITIALIZED:
-		/* not used by ULPs */
-		return;
-
 	case MLX5_DEV_EVENT_LID_CHANGE:
 		ibev.event = IB_EVENT_LID_CHANGE;
 		port = (u8)param;
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 5041176..ce43422 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -235,6 +235,8 @@
 		qp->rq.max_gs = 0;
 		qp->rq.wqe_cnt = 0;
 		qp->rq.wqe_shift = 0;
+		cap->max_recv_wr = 0;
+		cap->max_recv_sge = 0;
 	} else {
 		if (ucmd) {
 			qp->rq.wqe_cnt = ucmd->rq_wqe_count;
@@ -1851,13 +1853,15 @@
 static int mlx5_set_path(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 			 const struct ib_ah_attr *ah,
 			 struct mlx5_qp_path *path, u8 port, int attr_mask,
-			 u32 path_flags, const struct ib_qp_attr *attr)
+			 u32 path_flags, const struct ib_qp_attr *attr,
+			 bool alt)
 {
 	enum rdma_link_layer ll = rdma_port_get_link_layer(&dev->ib_dev, port);
 	int err;
 
 	if (attr_mask & IB_QP_PKEY_INDEX)
-		path->pkey_index = attr->pkey_index;
+		path->pkey_index = cpu_to_be16(alt ? attr->alt_pkey_index :
+						     attr->pkey_index);
 
 	if (ah->ah_flags & IB_AH_GRH) {
 		if (ah->grh.sgid_index >=
@@ -1877,9 +1881,9 @@
 							  ah->grh.sgid_index);
 		path->dci_cfi_prio_sl = (ah->sl & 0x7) << 4;
 	} else {
-		path->fl = (path_flags & MLX5_PATH_FLAG_FL) ? 0x80 : 0;
-		path->free_ar = (path_flags & MLX5_PATH_FLAG_FREE_AR) ? 0x80 :
-									0;
+		path->fl_free_ar = (path_flags & MLX5_PATH_FLAG_FL) ? 0x80 : 0;
+		path->fl_free_ar |=
+			(path_flags & MLX5_PATH_FLAG_FREE_AR) ? 0x40 : 0;
 		path->rlid = cpu_to_be16(ah->dlid);
 		path->grh_mlid = ah->src_path_bits & 0x7f;
 		if (ah->ah_flags & IB_AH_GRH)
@@ -1903,7 +1907,7 @@
 	path->port = port;
 
 	if (attr_mask & IB_QP_TIMEOUT)
-		path->ackto_lt = attr->timeout << 3;
+		path->ackto_lt = (alt ? attr->alt_timeout : attr->timeout) << 3;
 
 	if ((qp->ibqp.qp_type == IB_QPT_RAW_PACKET) && qp->sq.wqe_cnt)
 		return modify_raw_packet_eth_prio(dev->mdev,
@@ -2264,7 +2268,7 @@
 		context->log_pg_sz_remote_qpn = cpu_to_be32(attr->dest_qp_num);
 
 	if (attr_mask & IB_QP_PKEY_INDEX)
-		context->pri_path.pkey_index = attr->pkey_index;
+		context->pri_path.pkey_index = cpu_to_be16(attr->pkey_index);
 
 	/* todo implement counter_index functionality */
 
@@ -2277,7 +2281,7 @@
 	if (attr_mask & IB_QP_AV) {
 		err = mlx5_set_path(dev, qp, &attr->ah_attr, &context->pri_path,
 				    attr_mask & IB_QP_PORT ? attr->port_num : qp->port,
-				    attr_mask, 0, attr);
+				    attr_mask, 0, attr, false);
 		if (err)
 			goto out;
 	}
@@ -2288,7 +2292,9 @@
 	if (attr_mask & IB_QP_ALT_PATH) {
 		err = mlx5_set_path(dev, qp, &attr->alt_ah_attr,
 				    &context->alt_path,
-				    attr->alt_port_num, attr_mask, 0, attr);
+				    attr->alt_port_num,
+				    attr_mask | IB_QP_PKEY_INDEX | IB_QP_TIMEOUT,
+				    0, attr, true);
 		if (err)
 			goto out;
 	}
@@ -4013,11 +4019,12 @@
 	if (qp->ibqp.qp_type == IB_QPT_RC || qp->ibqp.qp_type == IB_QPT_UC) {
 		to_ib_ah_attr(dev, &qp_attr->ah_attr, &context->pri_path);
 		to_ib_ah_attr(dev, &qp_attr->alt_ah_attr, &context->alt_path);
-		qp_attr->alt_pkey_index = context->alt_path.pkey_index & 0x7f;
+		qp_attr->alt_pkey_index =
+			be16_to_cpu(context->alt_path.pkey_index);
 		qp_attr->alt_port_num	= qp_attr->alt_ah_attr.port_num;
 	}
 
-	qp_attr->pkey_index = context->pri_path.pkey_index & 0x7f;
+	qp_attr->pkey_index = be16_to_cpu(context->pri_path.pkey_index);
 	qp_attr->port_num = context->pri_path.port;
 
 	/* qp_attr->en_sqd_async_notify is only applicable in modify qp */
@@ -4079,17 +4086,19 @@
 	qp_attr->cap.max_recv_sge    = qp->rq.max_gs;
 
 	if (!ibqp->uobject) {
-		qp_attr->cap.max_send_wr  = qp->sq.wqe_cnt;
+		qp_attr->cap.max_send_wr  = qp->sq.max_post;
 		qp_attr->cap.max_send_sge = qp->sq.max_gs;
+		qp_init_attr->qp_context = ibqp->qp_context;
 	} else {
 		qp_attr->cap.max_send_wr  = 0;
 		qp_attr->cap.max_send_sge = 0;
 	}
 
-	/* We don't support inline sends for kernel QPs (yet), and we
-	 * don't know what userspace's value should be.
-	 */
-	qp_attr->cap.max_inline_data = 0;
+	qp_init_attr->qp_type = ibqp->qp_type;
+	qp_init_attr->recv_cq = ibqp->recv_cq;
+	qp_init_attr->send_cq = ibqp->send_cq;
+	qp_init_attr->srq = ibqp->srq;
+	qp_attr->cap.max_inline_data = qp->max_inline_data;
 
 	qp_init_attr->cap	     = qp_attr->cap;
 
diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.c b/drivers/infiniband/hw/usnic/usnic_uiom.c
index 7209fbc..a0b6ebe 100644
--- a/drivers/infiniband/hw/usnic/usnic_uiom.c
+++ b/drivers/infiniband/hw/usnic/usnic_uiom.c
@@ -36,7 +36,6 @@
 #include <linux/dma-mapping.h>
 #include <linux/sched.h>
 #include <linux/hugetlb.h>
-#include <linux/dma-attrs.h>
 #include <linux/iommu.h>
 #include <linux/workqueue.h>
 #include <linux/list.h>
@@ -112,10 +111,6 @@
 	int i;
 	int flags;
 	dma_addr_t pa;
-	DEFINE_DMA_ATTRS(attrs);
-
-	if (dmasync)
-		dma_set_attr(DMA_ATTR_WRITE_BARRIER, &attrs);
 
 	if (!can_do_mlock())
 		return -EPERM;
diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c
index 5fa4d4d..7de5134 100644
--- a/drivers/infiniband/sw/rdmavt/qp.c
+++ b/drivers/infiniband/sw/rdmavt/qp.c
@@ -502,6 +502,12 @@
  */
 static void rvt_reset_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp,
 		  enum ib_qp_type type)
+	__releases(&qp->s_lock)
+	__releases(&qp->s_hlock)
+	__releases(&qp->r_lock)
+	__acquires(&qp->r_lock)
+	__acquires(&qp->s_hlock)
+	__acquires(&qp->s_lock)
 {
 	if (qp->state != IB_QPS_RESET) {
 		qp->state = IB_QPS_RESET;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index bab7db6..4f7d9b4 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -94,6 +94,7 @@
 	IPOIB_NEIGH_TBL_FLUSH	  = 12,
 	IPOIB_FLAG_DEV_ADDR_SET	  = 13,
 	IPOIB_FLAG_DEV_ADDR_CTRL  = 14,
+	IPOIB_FLAG_GOING_DOWN	  = 15,
 
 	IPOIB_MAX_BACKOFF_SECONDS = 16,
 
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index b2f4283..951d9ab 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -1486,6 +1486,10 @@
 {
 	struct net_device *dev = to_net_dev(d);
 	int ret;
+	struct ipoib_dev_priv *priv = netdev_priv(dev);
+
+	if (test_bit(IPOIB_FLAG_GOING_DOWN, &priv->flags))
+		return -EPERM;
 
 	if (!rtnl_trylock())
 		return restart_syscall();
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index 45c40a1..dc6d241 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -1015,7 +1015,7 @@
 	if (ib_query_gid(priv->ca, priv->port, 0, &gid0, NULL))
 		return false;
 
-	netif_addr_lock(priv->dev);
+	netif_addr_lock_bh(priv->dev);
 
 	/* The subnet prefix may have changed, update it now so we won't have
 	 * to do it later
@@ -1026,12 +1026,12 @@
 
 	search_gid.global.interface_id = priv->local_gid.global.interface_id;
 
-	netif_addr_unlock(priv->dev);
+	netif_addr_unlock_bh(priv->dev);
 
 	err = ib_find_gid(priv->ca, &search_gid, IB_GID_TYPE_IB,
 			  priv->dev, &port, &index);
 
-	netif_addr_lock(priv->dev);
+	netif_addr_lock_bh(priv->dev);
 
 	if (search_gid.global.interface_id !=
 	    priv->local_gid.global.interface_id)
@@ -1092,7 +1092,7 @@
 	}
 
 out:
-	netif_addr_unlock(priv->dev);
+	netif_addr_unlock_bh(priv->dev);
 
 	return ret;
 }
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 2d7c163..5f58c41 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -1206,7 +1206,9 @@
 				neigh = NULL;
 				goto out_unlock;
 			}
-			neigh->alive = jiffies;
+
+			if (likely(skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE))
+				neigh->alive = jiffies;
 			goto out_unlock;
 		}
 	}
@@ -1851,7 +1853,7 @@
 	struct ipoib_dev_priv *child_priv;
 	struct net_device *netdev = priv->dev;
 
-	netif_addr_lock(netdev);
+	netif_addr_lock_bh(netdev);
 
 	memcpy(&priv->local_gid.global.interface_id,
 	       &gid->global.interface_id,
@@ -1859,7 +1861,7 @@
 	memcpy(netdev->dev_addr + 4, &priv->local_gid, sizeof(priv->local_gid));
 	clear_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags);
 
-	netif_addr_unlock(netdev);
+	netif_addr_unlock_bh(netdev);
 
 	if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) {
 		down_read(&priv->vlan_rwsem);
@@ -1875,7 +1877,7 @@
 	union ib_gid *gid = (union ib_gid *)(ss->__data + 4);
 	int ret = 0;
 
-	netif_addr_lock(dev);
+	netif_addr_lock_bh(dev);
 
 	/* Make sure the QPN, reserved and subnet prefix match the current
 	 * lladdr, it also makes sure the lladdr is unicast.
@@ -1885,7 +1887,7 @@
 	    gid->global.interface_id == 0)
 		ret = -EINVAL;
 
-	netif_addr_unlock(dev);
+	netif_addr_unlock_bh(dev);
 
 	return ret;
 }
@@ -2141,6 +2143,9 @@
 		ib_unregister_event_handler(&priv->event_handler);
 		flush_workqueue(ipoib_workqueue);
 
+		/* mark interface in the middle of destruction */
+		set_bit(IPOIB_FLAG_GOING_DOWN, &priv->flags);
+
 		rtnl_lock();
 		dev_change_flags(priv->dev, priv->dev->flags & ~IFF_UP);
 		rtnl_unlock();
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index 82fbc94..d3394b6 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -582,13 +582,13 @@
 		return;
 	}
 	priv->local_lid = port_attr.lid;
-	netif_addr_lock(dev);
+	netif_addr_lock_bh(dev);
 
 	if (!test_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags)) {
-		netif_addr_unlock(dev);
+		netif_addr_unlock_bh(dev);
 		return;
 	}
-	netif_addr_unlock(dev);
+	netif_addr_unlock_bh(dev);
 
 	spin_lock_irq(&priv->lock);
 	if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags))
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
index 64a3559..a2f9f29 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
@@ -131,6 +131,9 @@
 
 	ppriv = netdev_priv(pdev);
 
+	if (test_bit(IPOIB_FLAG_GOING_DOWN, &ppriv->flags))
+		return -EPERM;
+
 	snprintf(intf_name, sizeof intf_name, "%s.%04x",
 		 ppriv->dev->name, pkey);
 	priv = ipoib_intf_alloc(intf_name);
@@ -183,6 +186,9 @@
 
 	ppriv = netdev_priv(pdev);
 
+	if (test_bit(IPOIB_FLAG_GOING_DOWN, &ppriv->flags))
+		return -EPERM;
+
 	if (!rtnl_trylock())
 		return restart_syscall();
 
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 646de17..3322ed7 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -1457,7 +1457,6 @@
 {
 	unsigned int sg_offset = 0;
 
-	state->desc = req->indirect_desc;
 	state->fr.next = req->fr_list;
 	state->fr.end = req->fr_list + ch->target->mr_per_cmd;
 	state->sg = scat;
@@ -1489,7 +1488,6 @@
 	struct scatterlist *sg;
 	int i;
 
-	state->desc = req->indirect_desc;
 	for_each_sg(scat, sg, count, i) {
 		srp_map_desc(state, ib_sg_dma_address(dev->dev, sg),
 			     ib_sg_dma_len(dev->dev, sg),
@@ -1655,6 +1653,7 @@
 				   target->indirect_size, DMA_TO_DEVICE);
 
 	memset(&state, 0, sizeof(state));
+	state.desc = req->indirect_desc;
 	if (dev->use_fast_reg)
 		ret = srp_map_sg_fr(&state, ch, req, scat, count);
 	else if (dev->use_fmr)
@@ -3526,7 +3525,7 @@
 	int mr_page_shift, p;
 	u64 max_pages_per_mr;
 
-	srp_dev = kmalloc(sizeof *srp_dev, GFP_KERNEL);
+	srp_dev = kzalloc(sizeof(*srp_dev), GFP_KERNEL);
 	if (!srp_dev)
 		return;
 
@@ -3586,8 +3585,6 @@
 						   IB_ACCESS_REMOTE_WRITE);
 		if (IS_ERR(srp_dev->global_mr))
 			goto err_pd;
-	} else {
-		srp_dev->global_mr = NULL;
 	}
 
 	for (p = rdma_start_port(device); p <= rdma_end_port(device); ++p) {
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 6bd881b..5eb1f9e 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -41,6 +41,7 @@
 
 #define ITS_FLAGS_CMDQ_NEEDS_FLUSHING		(1ULL << 0)
 #define ITS_FLAGS_WORKAROUND_CAVIUM_22375	(1ULL << 1)
+#define ITS_FLAGS_WORKAROUND_CAVIUM_23144	(1ULL << 2)
 
 #define RDIST_FLAGS_PROPBASE_NEEDS_FLUSHING	(1 << 0)
 
@@ -82,6 +83,7 @@
 	u64			flags;
 	u32			ite_size;
 	u32			device_ids;
+	int			numa_node;
 };
 
 #define ITS_ITT_ALIGN		SZ_256
@@ -613,11 +615,23 @@
 static int its_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 			    bool force)
 {
-	unsigned int cpu = cpumask_any_and(mask_val, cpu_online_mask);
+	unsigned int cpu;
+	const struct cpumask *cpu_mask = cpu_online_mask;
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
 	struct its_collection *target_col;
 	u32 id = its_get_event_id(d);
 
+       /* lpi cannot be routed to a redistributor that is on a foreign node */
+	if (its_dev->its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144) {
+		if (its_dev->its->numa_node >= 0) {
+			cpu_mask = cpumask_of_node(its_dev->its->numa_node);
+			if (!cpumask_intersects(mask_val, cpu_mask))
+				return -EINVAL;
+		}
+	}
+
+	cpu = cpumask_any_and(mask_val, cpu_mask);
+
 	if (cpu >= nr_cpu_ids)
 		return -EINVAL;
 
@@ -1101,6 +1115,16 @@
 	list_for_each_entry(its, &its_nodes, entry) {
 		u64 target;
 
+		/* avoid cross node collections and its mapping */
+		if (its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144) {
+			struct device_node *cpu_node;
+
+			cpu_node = of_get_cpu_node(cpu, NULL);
+			if (its->numa_node != NUMA_NO_NODE &&
+				its->numa_node != of_node_to_nid(cpu_node))
+				continue;
+		}
+
 		/*
 		 * We now have to bind each collection to its target
 		 * redistributor.
@@ -1351,9 +1375,14 @@
 {
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
 	u32 event = its_get_event_id(d);
+	const struct cpumask *cpu_mask = cpu_online_mask;
+
+	/* get the cpu_mask of local node */
+	if (its_dev->its->numa_node >= 0)
+		cpu_mask = cpumask_of_node(its_dev->its->numa_node);
 
 	/* Bind the LPI to the first possible CPU */
-	its_dev->event_map.col_map[event] = cpumask_first(cpu_online_mask);
+	its_dev->event_map.col_map[event] = cpumask_first(cpu_mask);
 
 	/* Map the GIC IRQ and event to the device */
 	its_send_mapvi(its_dev, d->hwirq, event);
@@ -1443,6 +1472,13 @@
 	its->flags |= ITS_FLAGS_WORKAROUND_CAVIUM_22375;
 }
 
+static void __maybe_unused its_enable_quirk_cavium_23144(void *data)
+{
+	struct its_node *its = data;
+
+	its->flags |= ITS_FLAGS_WORKAROUND_CAVIUM_23144;
+}
+
 static const struct gic_quirk its_quirks[] = {
 #ifdef CONFIG_CAVIUM_ERRATUM_22375
 	{
@@ -1452,6 +1488,14 @@
 		.init	= its_enable_quirk_cavium_22375,
 	},
 #endif
+#ifdef CONFIG_CAVIUM_ERRATUM_23144
+	{
+		.desc	= "ITS: Cavium erratum 23144",
+		.iidr	= 0xa100034c,	/* ThunderX pass 1.x */
+		.mask	= 0xffff0fff,
+		.init	= its_enable_quirk_cavium_23144,
+	},
+#endif
 	{
 	}
 };
@@ -1514,6 +1558,7 @@
 	its->base = its_base;
 	its->phys_base = res.start;
 	its->ite_size = ((readl_relaxed(its_base + GITS_TYPER) >> 4) & 0xf) + 1;
+	its->numa_node = of_node_to_nid(node);
 
 	its->cmd_base = kzalloc(ITS_CMD_QUEUE_SZ, GFP_KERNEL);
 	if (!its->cmd_base) {
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index fb042ba..2c5ba0e 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -155,7 +155,7 @@
 
 	while (count--) {
 		val = readl_relaxed(rbase + GICR_WAKER);
-		if (enable ^ (val & GICR_WAKER_ChildrenAsleep))
+		if (enable ^ (bool)(val & GICR_WAKER_ChildrenAsleep))
 			break;
 		cpu_relax();
 		udelay(1);
diff --git a/drivers/irqchip/irq-pic32-evic.c b/drivers/irqchip/irq-pic32-evic.c
index e7155db..73addb4 100644
--- a/drivers/irqchip/irq-pic32-evic.c
+++ b/drivers/irqchip/irq-pic32-evic.c
@@ -91,7 +91,7 @@
 	/* set polarity for external interrupts only */
 	for (i = 0; i < ARRAY_SIZE(priv->ext_irqs); i++) {
 		if (priv->ext_irqs[i] == data->hwirq) {
-			ret = pic32_set_ext_polarity(i + 1, flow_type);
+			ret = pic32_set_ext_polarity(i, flow_type);
 			if (ret)
 				return ret;
 		}
diff --git a/drivers/isdn/hardware/eicon/divasmain.c b/drivers/isdn/hardware/eicon/divasmain.c
index a2e0ed6..32f3451 100644
--- a/drivers/isdn/hardware/eicon/divasmain.c
+++ b/drivers/isdn/hardware/eicon/divasmain.c
@@ -445,32 +445,32 @@
 /*********************************************************
  ** I/O port access
  *********************************************************/
-byte __inline__ inpp(void __iomem *addr)
+inline byte inpp(void __iomem *addr)
 {
 	return (inb((unsigned long) addr));
 }
 
-word __inline__ inppw(void __iomem *addr)
+inline word inppw(void __iomem *addr)
 {
 	return (inw((unsigned long) addr));
 }
 
-void __inline__ inppw_buffer(void __iomem *addr, void *P, int length)
+inline void inppw_buffer(void __iomem *addr, void *P, int length)
 {
 	insw((unsigned long) addr, (word *) P, length >> 1);
 }
 
-void __inline__ outppw_buffer(void __iomem *addr, void *P, int length)
+inline void outppw_buffer(void __iomem *addr, void *P, int length)
 {
 	outsw((unsigned long) addr, (word *) P, length >> 1);
 }
 
-void __inline__ outppw(void __iomem *addr, word w)
+inline void outppw(void __iomem *addr, word w)
 {
 	outw(w, (unsigned long) addr);
 }
 
-void __inline__ outpp(void __iomem *addr, word p)
+inline void outpp(void __iomem *addr, word p)
 {
 	outb(p, (unsigned long) addr);
 }
diff --git a/drivers/isdn/hardware/eicon/platform.h b/drivers/isdn/hardware/eicon/platform.h
index b2edb75..62e2073 100644
--- a/drivers/isdn/hardware/eicon/platform.h
+++ b/drivers/isdn/hardware/eicon/platform.h
@@ -203,7 +203,7 @@
 /*
 **  I/O Port utilities
 */
-int diva_os_register_io_port(void *adapter, int register, unsigned long port,
+int diva_os_register_io_port(void *adapter, int reg, unsigned long port,
 			     unsigned long length, const char *name, int id);
 /*
 **  I/O port access abstraction
@@ -271,13 +271,13 @@
 **  atomic operation, fake because we use threads
 */
 typedef int diva_os_atomic_t;
-static diva_os_atomic_t __inline__
+static inline diva_os_atomic_t
 diva_os_atomic_increment(diva_os_atomic_t *pv)
 {
 	*pv += 1;
 	return (*pv);
 }
-static diva_os_atomic_t __inline__
+static inline diva_os_atomic_t
 diva_os_atomic_decrement(diva_os_atomic_t *pv)
 {
 	*pv -= 1;
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index c984321..5d438ad 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -1276,7 +1276,7 @@
 	 * switch to HS200 mode if bus width is set successfully.
 	 */
 	err = mmc_select_bus_width(card);
-	if (!err) {
+	if (err >= 0) {
 		val = EXT_CSD_TIMING_HS200 |
 		      card->drive_strength << EXT_CSD_DRV_STR_SHIFT;
 		err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
@@ -1583,7 +1583,7 @@
 	} else if (mmc_card_hs(card)) {
 		/* Select the desired bus width optionally */
 		err = mmc_select_bus_width(card);
-		if (!err) {
+		if (err >= 0) {
 			err = mmc_select_hs_ddr(card);
 			if (err)
 				goto free_card;
diff --git a/drivers/mmc/host/sunxi-mmc.c b/drivers/mmc/host/sunxi-mmc.c
index 7fc8b7a..2ee4c21 100644
--- a/drivers/mmc/host/sunxi-mmc.c
+++ b/drivers/mmc/host/sunxi-mmc.c
@@ -970,8 +970,8 @@
 	[SDXC_CLK_400K]		= { .output = 180, .sample = 180 },
 	[SDXC_CLK_25M]		= { .output = 180, .sample =  75 },
 	[SDXC_CLK_50M]		= { .output = 150, .sample = 120 },
-	[SDXC_CLK_50M_DDR]	= { .output =  90, .sample = 120 },
-	[SDXC_CLK_50M_DDR_8BIT]	= { .output =  90, .sample = 120 },
+	[SDXC_CLK_50M_DDR]	= { .output =  54, .sample =  36 },
+	[SDXC_CLK_50M_DDR_8BIT]	= { .output =  72, .sample =  72 },
 };
 
 static int sunxi_mmc_resource_request(struct sunxi_mmc_host *host,
@@ -1129,11 +1129,6 @@
 				  MMC_CAP_1_8V_DDR |
 				  MMC_CAP_ERASE | MMC_CAP_SDIO_IRQ;
 
-	/* TODO MMC DDR is not working on A80 */
-	if (of_device_is_compatible(pdev->dev.of_node,
-				    "allwinner,sun9i-a80-mmc"))
-		mmc->caps &= ~MMC_CAP_1_8V_DDR;
-
 	ret = mmc_of_parse(mmc);
 	if (ret)
 		goto error_free_dma;
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 941ec99..90157e2 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -4607,26 +4607,6 @@
 	return 0;
 }
 
-static struct lock_class_key bonding_netdev_xmit_lock_key;
-static struct lock_class_key bonding_netdev_addr_lock_key;
-static struct lock_class_key bonding_tx_busylock_key;
-
-static void bond_set_lockdep_class_one(struct net_device *dev,
-				       struct netdev_queue *txq,
-				       void *_unused)
-{
-	lockdep_set_class(&txq->_xmit_lock,
-			  &bonding_netdev_xmit_lock_key);
-}
-
-static void bond_set_lockdep_class(struct net_device *dev)
-{
-	lockdep_set_class(&dev->addr_list_lock,
-			  &bonding_netdev_addr_lock_key);
-	netdev_for_each_tx_queue(dev, bond_set_lockdep_class_one, NULL);
-	dev->qdisc_tx_busylock = &bonding_tx_busylock_key;
-}
-
 /* Called from registration process */
 static int bond_init(struct net_device *bond_dev)
 {
@@ -4639,7 +4619,7 @@
 	if (!bond->wq)
 		return -ENOMEM;
 
-	bond_set_lockdep_class(bond_dev);
+	netdev_lockdep_set_classes(bond_dev);
 
 	list_add_tail(&bond->bond_list, &bn->dev_list);
 
diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig
index 0d40aef..22570ea 100644
--- a/drivers/net/can/Kconfig
+++ b/drivers/net/can/Kconfig
@@ -104,16 +104,6 @@
 	  This driver can also be built as a module. If so, the module will be
 	  called janz-ican3.ko.
 
-config CAN_RCAR
-	tristate "Renesas R-Car CAN controller"
-	depends on ARCH_RENESAS || ARM
-	---help---
-	  Say Y here if you want to use CAN controller found on Renesas R-Car
-	  SoCs.
-
-	  To compile this driver as a module, choose M here: the module will
-	  be called rcar_can.
-
 config CAN_SUN4I
 	tristate "Allwinner A10 CAN controller"
 	depends on MACH_SUN4I || MACH_SUN7I || COMPILE_TEST
@@ -152,6 +142,7 @@
 source "drivers/net/can/ifi_canfd/Kconfig"
 source "drivers/net/can/m_can/Kconfig"
 source "drivers/net/can/mscan/Kconfig"
+source "drivers/net/can/rcar/Kconfig"
 source "drivers/net/can/sja1000/Kconfig"
 source "drivers/net/can/softing/Kconfig"
 source "drivers/net/can/spi/Kconfig"
diff --git a/drivers/net/can/Makefile b/drivers/net/can/Makefile
index e3db0c8..26ba4b7 100644
--- a/drivers/net/can/Makefile
+++ b/drivers/net/can/Makefile
@@ -10,6 +10,7 @@
 
 can-dev-$(CONFIG_CAN_LEDS)	+= led.o
 
+obj-y				+= rcar/
 obj-y				+= spi/
 obj-y				+= usb/
 obj-y				+= softing/
@@ -24,7 +25,6 @@
 obj-$(CONFIG_CAN_JANZ_ICAN3)	+= janz-ican3.o
 obj-$(CONFIG_CAN_MSCAN)		+= mscan/
 obj-$(CONFIG_CAN_M_CAN)		+= m_can/
-obj-$(CONFIG_CAN_RCAR)		+= rcar_can.o
 obj-$(CONFIG_CAN_SJA1000)	+= sja1000/
 obj-$(CONFIG_CAN_SUN4I)		+= sun4i_can.o
 obj-$(CONFIG_CAN_TI_HECC)	+= ti_hecc.o
diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index 910c12e..7188137 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -69,6 +69,7 @@
 
 #ifdef CONFIG_CAN_CALC_BITTIMING
 #define CAN_CALC_MAX_ERROR 50 /* in one-tenth of a percent */
+#define CAN_CALC_SYNC_SEG 1
 
 /*
  * Bit-timing calculation derived from:
@@ -83,98 +84,126 @@
  * registers of the CAN controller. You can find more information
  * in the header file linux/can/netlink.h.
  */
-static int can_update_spt(const struct can_bittiming_const *btc,
-			  int sampl_pt, int tseg, int *tseg1, int *tseg2)
+static int can_update_sample_point(const struct can_bittiming_const *btc,
+			  unsigned int sample_point_nominal, unsigned int tseg,
+			  unsigned int *tseg1_ptr, unsigned int *tseg2_ptr,
+			  unsigned int *sample_point_error_ptr)
 {
-	*tseg2 = tseg + 1 - (sampl_pt * (tseg + 1)) / 1000;
-	if (*tseg2 < btc->tseg2_min)
-		*tseg2 = btc->tseg2_min;
-	if (*tseg2 > btc->tseg2_max)
-		*tseg2 = btc->tseg2_max;
-	*tseg1 = tseg - *tseg2;
-	if (*tseg1 > btc->tseg1_max) {
-		*tseg1 = btc->tseg1_max;
-		*tseg2 = tseg - *tseg1;
+	unsigned int sample_point_error, best_sample_point_error = UINT_MAX;
+	unsigned int sample_point, best_sample_point = 0;
+	unsigned int tseg1, tseg2;
+	int i;
+
+	for (i = 0; i <= 1; i++) {
+		tseg2 = tseg + CAN_CALC_SYNC_SEG - (sample_point_nominal * (tseg + CAN_CALC_SYNC_SEG)) / 1000 - i;
+		tseg2 = clamp(tseg2, btc->tseg2_min, btc->tseg2_max);
+		tseg1 = tseg - tseg2;
+		if (tseg1 > btc->tseg1_max) {
+			tseg1 = btc->tseg1_max;
+			tseg2 = tseg - tseg1;
+		}
+
+		sample_point = 1000 * (tseg + CAN_CALC_SYNC_SEG - tseg2) / (tseg + CAN_CALC_SYNC_SEG);
+		sample_point_error = abs(sample_point_nominal - sample_point);
+
+		if ((sample_point <= sample_point_nominal) && (sample_point_error < best_sample_point_error)) {
+			best_sample_point = sample_point;
+			best_sample_point_error = sample_point_error;
+			*tseg1_ptr = tseg1;
+			*tseg2_ptr = tseg2;
+		}
 	}
-	return 1000 * (tseg + 1 - *tseg2) / (tseg + 1);
+
+	if (sample_point_error_ptr)
+		*sample_point_error_ptr = best_sample_point_error;
+
+	return best_sample_point;
 }
 
 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);
-	long best_error = 1000000000, error = 0;
-	int best_tseg = 0, best_brp = 0, brp = 0;
-	int tsegall, tseg = 0, tseg1 = 0, tseg2 = 0;
-	int spt_error = 1000, spt = 0, sampl_pt;
-	long rate;
+	unsigned int bitrate;			/* current bitrate */
+	unsigned int bitrate_error;		/* difference between current and nominal value */
+	unsigned int best_bitrate_error = UINT_MAX;
+	unsigned int sample_point_error;	/* difference between current and nominal value */
+	unsigned int best_sample_point_error = UINT_MAX;
+	unsigned int sample_point_nominal;	/* nominal sample point */
+	unsigned int best_tseg = 0;		/* current best value for tseg */
+	unsigned int best_brp = 0;		/* current best value for brp */
+	unsigned int brp, tsegall, tseg, tseg1 = 0, tseg2 = 0;
 	u64 v64;
 
 	/* Use CiA recommended sample points */
 	if (bt->sample_point) {
-		sampl_pt = bt->sample_point;
+		sample_point_nominal = bt->sample_point;
 	} else {
 		if (bt->bitrate > 800000)
-			sampl_pt = 750;
+			sample_point_nominal = 750;
 		else if (bt->bitrate > 500000)
-			sampl_pt = 800;
+			sample_point_nominal = 800;
 		else
-			sampl_pt = 875;
+			sample_point_nominal = 875;
 	}
 
 	/* tseg even = round down, odd = round up */
 	for (tseg = (btc->tseg1_max + btc->tseg2_max) * 2 + 1;
 	     tseg >= (btc->tseg1_min + btc->tseg2_min) * 2; tseg--) {
-		tsegall = 1 + tseg / 2;
+		tsegall = CAN_CALC_SYNC_SEG + tseg / 2;
+
 		/* Compute all possible tseg choices (tseg=tseg1+tseg2) */
 		brp = priv->clock.freq / (tsegall * bt->bitrate) + tseg % 2;
-		/* chose brp step which is possible in system */
+
+		/* choose brp step which is possible in system */
 		brp = (brp / btc->brp_inc) * btc->brp_inc;
 		if ((brp < btc->brp_min) || (brp > btc->brp_max))
 			continue;
-		rate = priv->clock.freq / (brp * tsegall);
-		error = bt->bitrate - rate;
+
+		bitrate = priv->clock.freq / (brp * tsegall);
+		bitrate_error = abs(bt->bitrate - bitrate);
+
 		/* tseg brp biterror */
-		if (error < 0)
-			error = -error;
-		if (error > best_error)
+		if (bitrate_error > best_bitrate_error)
 			continue;
-		best_error = error;
-		if (error == 0) {
-			spt = can_update_spt(btc, sampl_pt, tseg / 2,
-					     &tseg1, &tseg2);
-			error = sampl_pt - spt;
-			if (error < 0)
-				error = -error;
-			if (error > spt_error)
-				continue;
-			spt_error = error;
-		}
+
+		/* reset sample point error if we have a better bitrate */
+		if (bitrate_error < best_bitrate_error)
+			best_sample_point_error = UINT_MAX;
+
+		can_update_sample_point(btc, sample_point_nominal, tseg / 2, &tseg1, &tseg2, &sample_point_error);
+		if (sample_point_error > best_sample_point_error)
+			continue;
+
+		best_sample_point_error = sample_point_error;
+		best_bitrate_error = bitrate_error;
 		best_tseg = tseg / 2;
 		best_brp = brp;
-		if (error == 0)
+
+		if (bitrate_error == 0 && sample_point_error == 0)
 			break;
 	}
 
-	if (best_error) {
+	if (best_bitrate_error) {
 		/* Error in one-tenth of a percent */
-		error = (best_error * 1000) / bt->bitrate;
-		if (error > CAN_CALC_MAX_ERROR) {
+		v64 = (u64)best_bitrate_error * 1000;
+		do_div(v64, bt->bitrate);
+		bitrate_error = (u32)v64;
+		if (bitrate_error > CAN_CALC_MAX_ERROR) {
 			netdev_err(dev,
-				   "bitrate error %ld.%ld%% too high\n",
-				   error / 10, error % 10);
+				   "bitrate error %d.%d%% too high\n",
+				   bitrate_error / 10, bitrate_error % 10);
 			return -EDOM;
-		} else {
-			netdev_warn(dev, "bitrate error %ld.%ld%%\n",
-				    error / 10, error % 10);
 		}
+		netdev_warn(dev, "bitrate error %d.%d%%\n",
+			    bitrate_error / 10, bitrate_error % 10);
 	}
 
 	/* real sample point */
-	bt->sample_point = can_update_spt(btc, sampl_pt, best_tseg,
-					  &tseg1, &tseg2);
+	bt->sample_point = can_update_sample_point(btc, sample_point_nominal, best_tseg,
+					  &tseg1, &tseg2, NULL);
 
-	v64 = (u64)best_brp * 1000000000UL;
+	v64 = (u64)best_brp * 1000 * 1000 * 1000;
 	do_div(v64, priv->clock.freq);
 	bt->tq = (u32)v64;
 	bt->prop_seg = tseg1 / 2;
@@ -182,9 +211,9 @@
 	bt->phase_seg2 = tseg2;
 
 	/* check for sjw user settings */
-	if (!bt->sjw || !btc->sjw_max)
+	if (!bt->sjw || !btc->sjw_max) {
 		bt->sjw = 1;
-	else {
+	} else {
 		/* bt->sjw is at least 1 -> sanitize upper bound to sjw_max */
 		if (bt->sjw > btc->sjw_max)
 			bt->sjw = btc->sjw_max;
@@ -194,8 +223,9 @@
 	}
 
 	bt->brp = best_brp;
-	/* real bit-rate */
-	bt->bitrate = priv->clock.freq / (bt->brp * (tseg1 + tseg2 + 1));
+
+	/* real bitrate */
+	bt->bitrate = priv->clock.freq / (bt->brp * (CAN_CALC_SYNC_SEG + tseg1 + tseg2));
 
 	return 0;
 }
diff --git a/drivers/net/can/rcar/Kconfig b/drivers/net/can/rcar/Kconfig
new file mode 100644
index 0000000..7b03a3a
--- /dev/null
+++ b/drivers/net/can/rcar/Kconfig
@@ -0,0 +1,21 @@
+config CAN_RCAR
+	tristate "Renesas R-Car CAN controller"
+	depends on ARCH_RENESAS || ARM
+	---help---
+	  Say Y here if you want to use CAN controller found on Renesas R-Car
+	  SoCs.
+
+	  To compile this driver as a module, choose M here: the module will
+	  be called rcar_can.
+
+config CAN_RCAR_CANFD
+	tristate "Renesas R-Car CAN FD controller"
+	depends on ARCH_RENESAS || ARM
+	---help---
+	  Say Y here if you want to use CAN FD controller found on
+	  Renesas R-Car SoCs. The driver puts the controller in CAN FD only
+	  mode, which can interoperate with CAN2.0 nodes but does not support
+	  dedicated CAN 2.0 mode.
+
+	  To compile this driver as a module, choose M here: the module will
+	  be called rcar_canfd.
diff --git a/drivers/net/can/rcar/Makefile b/drivers/net/can/rcar/Makefile
new file mode 100644
index 0000000..08de36a
--- /dev/null
+++ b/drivers/net/can/rcar/Makefile
@@ -0,0 +1,6 @@
+#
+#  Makefile for the Renesas R-Car CAN & CAN FD controller drivers
+#
+
+obj-$(CONFIG_CAN_RCAR)		+= rcar_can.o
+obj-$(CONFIG_CAN_RCAR_CANFD)	+= rcar_canfd.o
diff --git a/drivers/net/can/rcar_can.c b/drivers/net/can/rcar/rcar_can.c
similarity index 100%
rename from drivers/net/can/rcar_can.c
rename to drivers/net/can/rcar/rcar_can.c
diff --git a/drivers/net/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c
new file mode 100644
index 0000000..a39d922
--- /dev/null
+++ b/drivers/net/can/rcar/rcar_canfd.c
@@ -0,0 +1,1695 @@
+/* Renesas R-Car CAN FD device driver
+ *
+ * Copyright (C) 2015 Renesas Electronics Corp.
+ *
+ * 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.
+ */
+
+/* The R-Car CAN FD controller can operate in either one of the below two modes
+ *  - CAN FD only mode
+ *  - Classical CAN (CAN 2.0) only mode
+ *
+ * This driver puts the controller in CAN FD only mode by default. In this
+ * mode, the controller acts as a CAN FD node that can also interoperate with
+ * CAN 2.0 nodes.
+ *
+ * As of now, this driver does not support the Classical CAN (CAN 2.0) mode,
+ * which is handled by a different register map compared to CAN FD only mode.
+ *
+ * Note: The h/w manual register naming convention is clumsy and not acceptable
+ * to use as it is in the driver. However, those names are added as comments
+ * wherever it is modified to a readable name.
+ */
+
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/interrupt.h>
+#include <linux/errno.h>
+#include <linux/netdevice.h>
+#include <linux/platform_device.h>
+#include <linux/can/led.h>
+#include <linux/can/dev.h>
+#include <linux/clk.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+#include <linux/iopoll.h>
+
+#define RCANFD_DRV_NAME			"rcar_canfd"
+
+/* Global register bits */
+
+/* RSCFDnCFDGRMCFG */
+#define RCANFD_GRMCFG_RCMC		BIT(0)
+
+/* RSCFDnCFDGCFG */
+#define RCANFD_GCFG_CMPOC		BIT(5)
+#define RCANFD_GCFG_DCS			BIT(4)
+#define RCANFD_GCFG_DCE			BIT(1)
+#define RCANFD_GCFG_TPRI		BIT(0)
+
+/* RSCFDnCFDGCTR */
+#define RCANFD_GCTR_TSRST		BIT(16)
+#define RCANFD_GCTR_CFMPOFIE		BIT(11)
+#define RCANFD_GCTR_THLEIE		BIT(10)
+#define RCANFD_GCTR_MEIE		BIT(9)
+#define RCANFD_GCTR_DEIE		BIT(8)
+#define RCANFD_GCTR_GSLPR		BIT(2)
+#define RCANFD_GCTR_GMDC_MASK		(0x3)
+#define RCANFD_GCTR_GMDC_GOPM		(0x0)
+#define RCANFD_GCTR_GMDC_GRESET		(0x1)
+#define RCANFD_GCTR_GMDC_GTEST		(0x2)
+
+/* RSCFDnCFDGSTS */
+#define RCANFD_GSTS_GRAMINIT		BIT(3)
+#define RCANFD_GSTS_GSLPSTS		BIT(2)
+#define RCANFD_GSTS_GHLTSTS		BIT(1)
+#define RCANFD_GSTS_GRSTSTS		BIT(0)
+/* Non-operational status */
+#define RCANFD_GSTS_GNOPM		(BIT(0) | BIT(1) | BIT(2) | BIT(3))
+
+/* RSCFDnCFDGERFL */
+#define RCANFD_GERFL_EEF1		BIT(17)
+#define RCANFD_GERFL_EEF0		BIT(16)
+#define RCANFD_GERFL_CMPOF		BIT(3)
+#define RCANFD_GERFL_THLES		BIT(2)
+#define RCANFD_GERFL_MES		BIT(1)
+#define RCANFD_GERFL_DEF		BIT(0)
+
+#define RCANFD_GERFL_ERR(x)		((x) & (RCANFD_GERFL_EEF1 |\
+						RCANFD_GERFL_EEF0 |\
+						RCANFD_GERFL_MES |\
+						RCANFD_GERFL_CMPOF))
+
+/* AFL Rx rules registers */
+
+/* RSCFDnCFDGAFLCFG0 */
+#define RCANFD_GAFLCFG_SETRNC(n, x)	(((x) & 0xff) << (24 - n * 8))
+#define RCANFD_GAFLCFG_GETRNC(n, x)	(((x) >> (24 - n * 8)) & 0xff)
+
+/* RSCFDnCFDGAFLECTR */
+#define RCANFD_GAFLECTR_AFLDAE		BIT(8)
+#define RCANFD_GAFLECTR_AFLPN(x)	((x) & 0x1f)
+
+/* RSCFDnCFDGAFLIDj */
+#define RCANFD_GAFLID_GAFLLB		BIT(29)
+
+/* RSCFDnCFDGAFLP1_j */
+#define RCANFD_GAFLP1_GAFLFDP(x)	(1 << (x))
+
+/* Channel register bits */
+
+/* RSCFDnCFDCmNCFG */
+#define RCANFD_NCFG_NTSEG2(x)		(((x) & 0x1f) << 24)
+#define RCANFD_NCFG_NTSEG1(x)		(((x) & 0x7f) << 16)
+#define RCANFD_NCFG_NSJW(x)		(((x) & 0x1f) << 11)
+#define RCANFD_NCFG_NBRP(x)		(((x) & 0x3ff) << 0)
+
+/* RSCFDnCFDCmCTR */
+#define RCANFD_CCTR_CTME		BIT(24)
+#define RCANFD_CCTR_ERRD		BIT(23)
+#define RCANFD_CCTR_BOM_MASK		(0x3 << 21)
+#define RCANFD_CCTR_BOM_ISO		(0x0 << 21)
+#define RCANFD_CCTR_BOM_BENTRY		(0x1 << 21)
+#define RCANFD_CCTR_BOM_BEND		(0x2 << 21)
+#define RCANFD_CCTR_TDCVFIE		BIT(19)
+#define RCANFD_CCTR_SOCOIE		BIT(18)
+#define RCANFD_CCTR_EOCOIE		BIT(17)
+#define RCANFD_CCTR_TAIE		BIT(16)
+#define RCANFD_CCTR_ALIE		BIT(15)
+#define RCANFD_CCTR_BLIE		BIT(14)
+#define RCANFD_CCTR_OLIE		BIT(13)
+#define RCANFD_CCTR_BORIE		BIT(12)
+#define RCANFD_CCTR_BOEIE		BIT(11)
+#define RCANFD_CCTR_EPIE		BIT(10)
+#define RCANFD_CCTR_EWIE		BIT(9)
+#define RCANFD_CCTR_BEIE		BIT(8)
+#define RCANFD_CCTR_CSLPR		BIT(2)
+#define RCANFD_CCTR_CHMDC_MASK		(0x3)
+#define RCANFD_CCTR_CHDMC_COPM		(0x0)
+#define RCANFD_CCTR_CHDMC_CRESET	(0x1)
+#define RCANFD_CCTR_CHDMC_CHLT		(0x2)
+
+/* RSCFDnCFDCmSTS */
+#define RCANFD_CSTS_COMSTS		BIT(7)
+#define RCANFD_CSTS_RECSTS		BIT(6)
+#define RCANFD_CSTS_TRMSTS		BIT(5)
+#define RCANFD_CSTS_BOSTS		BIT(4)
+#define RCANFD_CSTS_EPSTS		BIT(3)
+#define RCANFD_CSTS_SLPSTS		BIT(2)
+#define RCANFD_CSTS_HLTSTS		BIT(1)
+#define RCANFD_CSTS_CRSTSTS		BIT(0)
+
+#define RCANFD_CSTS_TECCNT(x)		(((x) >> 24) & 0xff)
+#define RCANFD_CSTS_RECCNT(x)		(((x) >> 16) & 0xff)
+
+/* RSCFDnCFDCmERFL */
+#define RCANFD_CERFL_ADERR		BIT(14)
+#define RCANFD_CERFL_B0ERR		BIT(13)
+#define RCANFD_CERFL_B1ERR		BIT(12)
+#define RCANFD_CERFL_CERR		BIT(11)
+#define RCANFD_CERFL_AERR		BIT(10)
+#define RCANFD_CERFL_FERR		BIT(9)
+#define RCANFD_CERFL_SERR		BIT(8)
+#define RCANFD_CERFL_ALF		BIT(7)
+#define RCANFD_CERFL_BLF		BIT(6)
+#define RCANFD_CERFL_OVLF		BIT(5)
+#define RCANFD_CERFL_BORF		BIT(4)
+#define RCANFD_CERFL_BOEF		BIT(3)
+#define RCANFD_CERFL_EPF		BIT(2)
+#define RCANFD_CERFL_EWF		BIT(1)
+#define RCANFD_CERFL_BEF		BIT(0)
+
+#define RCANFD_CERFL_ERR(x)		((x) & (0x7fff)) /* above bits 14:0 */
+
+/* RSCFDnCFDCmDCFG */
+#define RCANFD_DCFG_DSJW(x)		(((x) & 0x7) << 24)
+#define RCANFD_DCFG_DTSEG2(x)		(((x) & 0x7) << 20)
+#define RCANFD_DCFG_DTSEG1(x)		(((x) & 0xf) << 16)
+#define RCANFD_DCFG_DBRP(x)		(((x) & 0xff) << 0)
+
+/* RSCFDnCFDCmFDCFG */
+#define RCANFD_FDCFG_TDCE		BIT(9)
+#define RCANFD_FDCFG_TDCOC		BIT(8)
+#define RCANFD_FDCFG_TDCO(x)		(((x) & 0x7f) >> 16)
+
+/* RSCFDnCFDRFCCx */
+#define RCANFD_RFCC_RFIM		BIT(12)
+#define RCANFD_RFCC_RFDC(x)		(((x) & 0x7) << 8)
+#define RCANFD_RFCC_RFPLS(x)		(((x) & 0x7) << 4)
+#define RCANFD_RFCC_RFIE		BIT(1)
+#define RCANFD_RFCC_RFE			BIT(0)
+
+/* RSCFDnCFDRFSTSx */
+#define RCANFD_RFSTS_RFIF		BIT(3)
+#define RCANFD_RFSTS_RFMLT		BIT(2)
+#define RCANFD_RFSTS_RFFLL		BIT(1)
+#define RCANFD_RFSTS_RFEMP		BIT(0)
+
+/* RSCFDnCFDRFIDx */
+#define RCANFD_RFID_RFIDE		BIT(31)
+#define RCANFD_RFID_RFRTR		BIT(30)
+
+/* RSCFDnCFDRFPTRx */
+#define RCANFD_RFPTR_RFDLC(x)		(((x) >> 28) & 0xf)
+#define RCANFD_RFPTR_RFPTR(x)		(((x) >> 16) & 0xfff)
+#define RCANFD_RFPTR_RFTS(x)		(((x) >> 0) & 0xffff)
+
+/* RSCFDnCFDRFFDSTSx */
+#define RCANFD_RFFDSTS_RFFDF		BIT(2)
+#define RCANFD_RFFDSTS_RFBRS		BIT(1)
+#define RCANFD_RFFDSTS_RFESI		BIT(0)
+
+/* Common FIFO bits */
+
+/* RSCFDnCFDCFCCk */
+#define RCANFD_CFCC_CFTML(x)		(((x) & 0xf) << 20)
+#define RCANFD_CFCC_CFM(x)		(((x) & 0x3) << 16)
+#define RCANFD_CFCC_CFIM		BIT(12)
+#define RCANFD_CFCC_CFDC(x)		(((x) & 0x7) << 8)
+#define RCANFD_CFCC_CFPLS(x)		(((x) & 0x7) << 4)
+#define RCANFD_CFCC_CFTXIE		BIT(2)
+#define RCANFD_CFCC_CFE			BIT(0)
+
+/* RSCFDnCFDCFSTSk */
+#define RCANFD_CFSTS_CFMC(x)		(((x) >> 8) & 0xff)
+#define RCANFD_CFSTS_CFTXIF		BIT(4)
+#define RCANFD_CFSTS_CFMLT		BIT(2)
+#define RCANFD_CFSTS_CFFLL		BIT(1)
+#define RCANFD_CFSTS_CFEMP		BIT(0)
+
+/* RSCFDnCFDCFIDk */
+#define RCANFD_CFID_CFIDE		BIT(31)
+#define RCANFD_CFID_CFRTR		BIT(30)
+#define RCANFD_CFID_CFID_MASK(x)	((x) & 0x1fffffff)
+
+/* RSCFDnCFDCFPTRk */
+#define RCANFD_CFPTR_CFDLC(x)		(((x) & 0xf) << 28)
+#define RCANFD_CFPTR_CFPTR(x)		(((x) & 0xfff) << 16)
+#define RCANFD_CFPTR_CFTS(x)		(((x) & 0xff) << 0)
+
+/* RSCFDnCFDCFFDCSTSk */
+#define RCANFD_CFFDCSTS_CFFDF		BIT(2)
+#define RCANFD_CFFDCSTS_CFBRS		BIT(1)
+#define RCANFD_CFFDCSTS_CFESI		BIT(0)
+
+/* This controller supports classical CAN only mode or CAN FD only mode. These
+ * modes are supported in two separate set of register maps & names. However,
+ * some of the register offsets are common for both modes. Those offsets are
+ * listed below as Common registers.
+ *
+ * The CAN FD only specific registers are listed separately and their names
+ * starts with RCANFD_F_xxx names. When classical CAN only specific registers
+ * are added, those specific registers can be prefixed as RCANFD_C_xxx.
+ */
+
+/* Common registers */
+
+/* RSCFDnCFDCmNCFG / RSCFDnCmCFG */
+#define RCANFD_CCFG(m)			(0x0000 + (0x10 * (m)))
+/* RSCFDnCFDCmCTR / RSCFDnCmCTR */
+#define RCANFD_CCTR(m)			(0x0004 + (0x10 * (m)))
+/* RSCFDnCFDCmSTS / RSCFDnCmSTS */
+#define RCANFD_CSTS(m)			(0x0008 + (0x10 * (m)))
+/* RSCFDnCFDCmERFL / RSCFDnCmERFL */
+#define RCANFD_CERFL(m)			(0x000C + (0x10 * (m)))
+
+/* RSCFDnCFDGCFG / RSCFDnGCFG */
+#define RCANFD_GCFG			(0x0084)
+/* RSCFDnCFDGCTR / RSCFDnGCTR */
+#define RCANFD_GCTR			(0x0088)
+/* RSCFDnCFDGCTS / RSCFDnGCTS */
+#define RCANFD_GSTS			(0x008c)
+/* RSCFDnCFDGERFL / RSCFDnGERFL */
+#define RCANFD_GERFL			(0x0090)
+/* RSCFDnCFDGTSC / RSCFDnGTSC */
+#define RCANFD_GTSC			(0x0094)
+/* RSCFDnCFDGAFLECTR / RSCFDnGAFLECTR */
+#define RCANFD_GAFLECTR			(0x0098)
+/* RSCFDnCFDGAFLCFG0 / RSCFDnGAFLCFG0 */
+#define RCANFD_GAFLCFG0			(0x009c)
+/* RSCFDnCFDGAFLCFG1 / RSCFDnGAFLCFG1 */
+#define RCANFD_GAFLCFG1			(0x00a0)
+/* RSCFDnCFDRMNB / RSCFDnRMNB */
+#define RCANFD_RMNB			(0x00a4)
+/* RSCFDnCFDRMND / RSCFDnRMND */
+#define RCANFD_RMND(y)			(0x00a8 + (0x04 * (y)))
+
+/* RSCFDnCFDRFCCx / RSCFDnRFCCx */
+#define RCANFD_RFCC(x)			(0x00b8 + (0x04 * (x)))
+/* RSCFDnCFDRFSTSx / RSCFDnRFSTSx */
+#define RCANFD_RFSTS(x)			(0x00d8 + (0x04 * (x)))
+/* RSCFDnCFDRFPCTRx / RSCFDnRFPCTRx */
+#define RCANFD_RFPCTR(x)		(0x00f8 + (0x04 * (x)))
+
+/* Common FIFO Control registers */
+
+/* RSCFDnCFDCFCCx / RSCFDnCFCCx */
+#define RCANFD_CFCC(ch, idx)		(0x0118 + (0x0c * (ch)) + \
+					 (0x04 * (idx)))
+/* RSCFDnCFDCFSTSx / RSCFDnCFSTSx */
+#define RCANFD_CFSTS(ch, idx)		(0x0178 + (0x0c * (ch)) + \
+					 (0x04 * (idx)))
+/* RSCFDnCFDCFPCTRx / RSCFDnCFPCTRx */
+#define RCANFD_CFPCTR(ch, idx)		(0x01d8 + (0x0c * (ch)) + \
+					 (0x04 * (idx)))
+
+/* RSCFDnCFDFESTS / RSCFDnFESTS */
+#define RCANFD_FESTS			(0x0238)
+/* RSCFDnCFDFFSTS / RSCFDnFFSTS */
+#define RCANFD_FFSTS			(0x023c)
+/* RSCFDnCFDFMSTS / RSCFDnFMSTS */
+#define RCANFD_FMSTS			(0x0240)
+/* RSCFDnCFDRFISTS / RSCFDnRFISTS */
+#define RCANFD_RFISTS			(0x0244)
+/* RSCFDnCFDCFRISTS / RSCFDnCFRISTS */
+#define RCANFD_CFRISTS			(0x0248)
+/* RSCFDnCFDCFTISTS / RSCFDnCFTISTS */
+#define RCANFD_CFTISTS			(0x024c)
+
+/* RSCFDnCFDTMCp / RSCFDnTMCp */
+#define RCANFD_TMC(p)			(0x0250 + (0x01 * (p)))
+/* RSCFDnCFDTMSTSp / RSCFDnTMSTSp */
+#define RCANFD_TMSTS(p)			(0x02d0 + (0x01 * (p)))
+
+/* RSCFDnCFDTMTRSTSp / RSCFDnTMTRSTSp */
+#define RCANFD_TMTRSTS(y)		(0x0350 + (0x04 * (y)))
+/* RSCFDnCFDTMTARSTSp / RSCFDnTMTARSTSp */
+#define RCANFD_TMTARSTS(y)		(0x0360 + (0x04 * (y)))
+/* RSCFDnCFDTMTCSTSp / RSCFDnTMTCSTSp */
+#define RCANFD_TMTCSTS(y)		(0x0370 + (0x04 * (y)))
+/* RSCFDnCFDTMTASTSp / RSCFDnTMTASTSp */
+#define RCANFD_TMTASTS(y)		(0x0380 + (0x04 * (y)))
+/* RSCFDnCFDTMIECy / RSCFDnTMIECy */
+#define RCANFD_TMIEC(y)			(0x0390 + (0x04 * (y)))
+
+/* RSCFDnCFDTXQCCm / RSCFDnTXQCCm */
+#define RCANFD_TXQCC(m)			(0x03a0 + (0x04 * (m)))
+/* RSCFDnCFDTXQSTSm / RSCFDnTXQSTSm */
+#define RCANFD_TXQSTS(m)		(0x03c0 + (0x04 * (m)))
+/* RSCFDnCFDTXQPCTRm / RSCFDnTXQPCTRm */
+#define RCANFD_TXQPCTR(m)		(0x03e0 + (0x04 * (m)))
+
+/* RSCFDnCFDTHLCCm / RSCFDnTHLCCm */
+#define RCANFD_THLCC(m)			(0x0400 + (0x04 * (m)))
+/* RSCFDnCFDTHLSTSm / RSCFDnTHLSTSm */
+#define RCANFD_THLSTS(m)		(0x0420 + (0x04 * (m)))
+/* RSCFDnCFDTHLPCTRm / RSCFDnTHLPCTRm */
+#define RCANFD_THLPCTR(m)		(0x0440 + (0x04 * (m)))
+
+/* RSCFDnCFDGTINTSTS0 / RSCFDnGTINTSTS0 */
+#define RCANFD_GTINTSTS0		(0x0460)
+/* RSCFDnCFDGTINTSTS1 / RSCFDnGTINTSTS1 */
+#define RCANFD_GTINTSTS1		(0x0464)
+/* RSCFDnCFDGTSTCFG / RSCFDnGTSTCFG */
+#define RCANFD_GTSTCFG			(0x0468)
+/* RSCFDnCFDGTSTCTR / RSCFDnGTSTCTR */
+#define RCANFD_GTSTCTR			(0x046c)
+/* RSCFDnCFDGLOCKK / RSCFDnGLOCKK */
+#define RCANFD_GLOCKK			(0x047c)
+/* RSCFDnCFDGRMCFG / RSCFDnGRMCFG */
+#define RCANFD_GRMCFG			(0x04fc)
+
+/* RSCFDnCFDGAFLIDj / RSCFDnGAFLIDj */
+#define RCANFD_GAFLID(offset, j)	((offset) + (0x10 * (j)))
+/* RSCFDnCFDGAFLMj / RSCFDnGAFLMj */
+#define RCANFD_GAFLM(offset, j)		((offset) + 0x04 + (0x10 * (j)))
+/* RSCFDnCFDGAFLP0j / RSCFDnGAFLP0j */
+#define RCANFD_GAFLP0(offset, j)	((offset) + 0x08 + (0x10 * (j)))
+/* RSCFDnCFDGAFLP1j / RSCFDnGAFLP1j */
+#define RCANFD_GAFLP1(offset, j)	((offset) + 0x0c + (0x10 * (j)))
+
+/* CAN FD mode specific regsiter map */
+
+/* RSCFDnCFDCmXXX -> RCANFD_F_XXX(m) */
+#define RCANFD_F_DCFG(m)		(0x0500 + (0x20 * (m)))
+#define RCANFD_F_CFDCFG(m)		(0x0504 + (0x20 * (m)))
+#define RCANFD_F_CFDCTR(m)		(0x0508 + (0x20 * (m)))
+#define RCANFD_F_CFDSTS(m)		(0x050c + (0x20 * (m)))
+#define RCANFD_F_CFDCRC(m)		(0x0510 + (0x20 * (m)))
+
+/* RSCFDnCFDGAFLXXXj offset */
+#define RCANFD_F_GAFL_OFFSET		(0x1000)
+
+/* RSCFDnCFDRMXXXq -> RCANFD_F_RMXXX(q) */
+#define RCANFD_F_RMID(q)		(0x2000 + (0x20 * (q)))
+#define RCANFD_F_RMPTR(q)		(0x2004 + (0x20 * (q)))
+#define RCANFD_F_RMFDSTS(q)		(0x2008 + (0x20 * (q)))
+#define RCANFD_F_RMDF(q, b)		(0x200c + (0x04 * (b)) + (0x20 * (q)))
+
+/* RSCFDnCFDRFXXx -> RCANFD_F_RFXX(x) */
+#define RCANFD_F_RFOFFSET		(0x3000)
+#define RCANFD_F_RFID(x)		(RCANFD_F_RFOFFSET + (0x80 * (x)))
+#define RCANFD_F_RFPTR(x)		(RCANFD_F_RFOFFSET + 0x04 + \
+					 (0x80 * (x)))
+#define RCANFD_F_RFFDSTS(x)		(RCANFD_F_RFOFFSET + 0x08 + \
+					 (0x80 * (x)))
+#define RCANFD_F_RFDF(x, df)		(RCANFD_F_RFOFFSET + 0x0c + \
+					 (0x80 * (x)) + (0x04 * (df)))
+
+/* RSCFDnCFDCFXXk -> RCANFD_F_CFXX(ch, k) */
+#define RCANFD_F_CFOFFSET		(0x3400)
+#define RCANFD_F_CFID(ch, idx)		(RCANFD_F_CFOFFSET + (0x180 * (ch)) + \
+					 (0x80 * (idx)))
+#define RCANFD_F_CFPTR(ch, idx)		(RCANFD_F_CFOFFSET + 0x04 + \
+					 (0x180 * (ch)) + (0x80 * (idx)))
+#define RCANFD_F_CFFDCSTS(ch, idx)	(RCANFD_F_CFOFFSET + 0x08 + \
+					 (0x180 * (ch)) + (0x80 * (idx)))
+#define RCANFD_F_CFDF(ch, idx, df)	(RCANFD_F_CFOFFSET + 0x0c + \
+					 (0x180 * (ch)) + (0x80 * (idx)) + \
+					 (0x04 * (df)))
+
+/* RSCFDnCFDTMXXp -> RCANFD_F_TMXX(p) */
+#define RCANFD_F_TMID(p)		(0x4000 + (0x20 * (p)))
+#define RCANFD_F_TMPTR(p)		(0x4004 + (0x20 * (p)))
+#define RCANFD_F_TMFDCTR(p)		(0x4008 + (0x20 * (p)))
+#define RCANFD_F_TMDF(p, b)		(0x400c + (0x20 * (p)) + (0x04 * (b)))
+
+/* RSCFDnCFDTHLACCm */
+#define RCANFD_F_THLACC(m)		(0x6000 + (0x04 * (m)))
+/* RSCFDnCFDRPGACCr */
+#define RCANFD_F_RPGACC(r)		(0x6400 + (0x04 * (r)))
+
+/* Constants */
+#define RCANFD_FIFO_DEPTH		8	/* Tx FIFO depth */
+#define RCANFD_NAPI_WEIGHT		8	/* Rx poll quota */
+
+#define RCANFD_NUM_CHANNELS		2	/* Two channels max */
+#define RCANFD_CHANNELS_MASK		BIT((RCANFD_NUM_CHANNELS) - 1)
+
+#define RCANFD_GAFL_PAGENUM(entry)	((entry) / 16)
+#define RCANFD_CHANNEL_NUMRULES		1	/* only one rule per channel */
+
+/* Rx FIFO is a global resource of the controller. There are 8 such FIFOs
+ * available. Each channel gets a dedicated Rx FIFO (i.e.) the channel
+ * number is added to RFFIFO index.
+ */
+#define RCANFD_RFFIFO_IDX		0
+
+/* Tx/Rx or Common FIFO is a per channel resource. Each channel has 3 Common
+ * FIFOs dedicated to them. Use the first (index 0) FIFO out of the 3 for Tx.
+ */
+#define RCANFD_CFFIFO_IDX		0
+
+/* fCAN clock select register settings */
+enum rcar_canfd_fcanclk {
+	RCANFD_CANFDCLK = 0,		/* CANFD clock */
+	RCANFD_EXTCLK,			/* Externally input clock */
+};
+
+struct rcar_canfd_global;
+
+/* Channel priv data */
+struct rcar_canfd_channel {
+	struct can_priv can;			/* Must be the first member */
+	struct net_device *ndev;
+	struct rcar_canfd_global *gpriv;	/* Controller reference */
+	void __iomem *base;			/* Register base address */
+	struct napi_struct napi;
+	u8  tx_len[RCANFD_FIFO_DEPTH];		/* For net stats */
+	u32 tx_head;				/* Incremented on xmit */
+	u32 tx_tail;				/* Incremented on xmit done */
+	u32 channel;				/* Channel number */
+	spinlock_t tx_lock;			/* To protect tx path */
+};
+
+/* Global priv data */
+struct rcar_canfd_global {
+	struct rcar_canfd_channel *ch[RCANFD_NUM_CHANNELS];
+	void __iomem *base;		/* Register base address */
+	struct platform_device *pdev;	/* Respective platform device */
+	struct clk *clkp;		/* Peripheral clock */
+	struct clk *can_clk;		/* fCAN clock */
+	enum rcar_canfd_fcanclk fcan;	/* CANFD or Ext clock */
+	unsigned long channels_mask;	/* Enabled channels mask */
+};
+
+/* CAN FD mode nominal rate constants */
+static const struct can_bittiming_const rcar_canfd_nom_bittiming_const = {
+	.name = RCANFD_DRV_NAME,
+	.tseg1_min = 2,
+	.tseg1_max = 128,
+	.tseg2_min = 2,
+	.tseg2_max = 32,
+	.sjw_max = 32,
+	.brp_min = 1,
+	.brp_max = 1024,
+	.brp_inc = 1,
+};
+
+/* CAN FD mode data rate constants */
+static const struct can_bittiming_const rcar_canfd_data_bittiming_const = {
+	.name = RCANFD_DRV_NAME,
+	.tseg1_min = 2,
+	.tseg1_max = 16,
+	.tseg2_min = 2,
+	.tseg2_max = 8,
+	.sjw_max = 8,
+	.brp_min = 1,
+	.brp_max = 256,
+	.brp_inc = 1,
+};
+
+/* Helper functions */
+static inline void rcar_canfd_update(u32 mask, u32 val, u32 __iomem *reg)
+{
+	u32 data = readl(reg);
+
+	data &= ~mask;
+	data |= (val & mask);
+	writel(data, reg);
+}
+
+static inline u32 rcar_canfd_read(void __iomem *base, u32 offset)
+{
+	return readl(base + (offset));
+}
+
+static inline void rcar_canfd_write(void __iomem *base, u32 offset, u32 val)
+{
+	writel(val, base + (offset));
+}
+
+static void rcar_canfd_set_bit(void __iomem *base, u32 reg, u32 val)
+{
+	rcar_canfd_update(val, val, base + (reg));
+}
+
+static void rcar_canfd_clear_bit(void __iomem *base, u32 reg, u32 val)
+{
+	rcar_canfd_update(val, 0, base + (reg));
+}
+
+static void rcar_canfd_update_bit(void __iomem *base, u32 reg,
+				  u32 mask, u32 val)
+{
+	rcar_canfd_update(mask, val, base + (reg));
+}
+
+static void rcar_canfd_get_data(struct rcar_canfd_channel *priv,
+				struct canfd_frame *cf, u32 off)
+{
+	u32 i, lwords;
+
+	lwords = DIV_ROUND_UP(cf->len, sizeof(u32));
+	for (i = 0; i < lwords; i++)
+		*((u32 *)cf->data + i) =
+			rcar_canfd_read(priv->base, off + (i * sizeof(u32)));
+}
+
+static void rcar_canfd_put_data(struct rcar_canfd_channel *priv,
+				struct canfd_frame *cf, u32 off)
+{
+	u32 i, lwords;
+
+	lwords = DIV_ROUND_UP(cf->len, sizeof(u32));
+	for (i = 0; i < lwords; i++)
+		rcar_canfd_write(priv->base, off + (i * sizeof(u32)),
+				 *((u32 *)cf->data + i));
+}
+
+static void rcar_canfd_tx_failure_cleanup(struct net_device *ndev)
+{
+	u32 i;
+
+	for (i = 0; i < RCANFD_FIFO_DEPTH; i++)
+		can_free_echo_skb(ndev, i);
+}
+
+static int rcar_canfd_reset_controller(struct rcar_canfd_global *gpriv)
+{
+	u32 sts, ch;
+	int err;
+
+	/* Check RAMINIT flag as CAN RAM initialization takes place
+	 * after the MCU reset
+	 */
+	err = readl_poll_timeout((gpriv->base + RCANFD_GSTS), sts,
+				 !(sts & RCANFD_GSTS_GRAMINIT), 2, 500000);
+	if (err) {
+		dev_dbg(&gpriv->pdev->dev, "global raminit failed\n");
+		return err;
+	}
+
+	/* Transition to Global Reset mode */
+	rcar_canfd_clear_bit(gpriv->base, RCANFD_GCTR, RCANFD_GCTR_GSLPR);
+	rcar_canfd_update_bit(gpriv->base, RCANFD_GCTR,
+			      RCANFD_GCTR_GMDC_MASK, RCANFD_GCTR_GMDC_GRESET);
+
+	/* Ensure Global reset mode */
+	err = readl_poll_timeout((gpriv->base + RCANFD_GSTS), sts,
+				 (sts & RCANFD_GSTS_GRSTSTS), 2, 500000);
+	if (err) {
+		dev_dbg(&gpriv->pdev->dev, "global reset failed\n");
+		return err;
+	}
+
+	/* Reset Global error flags */
+	rcar_canfd_write(gpriv->base, RCANFD_GERFL, 0x0);
+
+	/* Set the controller into FD mode */
+	rcar_canfd_set_bit(gpriv->base, RCANFD_GRMCFG, RCANFD_GRMCFG_RCMC);
+
+	/* Transition all Channels to reset mode */
+	for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS) {
+		rcar_canfd_clear_bit(gpriv->base,
+				     RCANFD_CCTR(ch), RCANFD_CCTR_CSLPR);
+
+		rcar_canfd_update_bit(gpriv->base, RCANFD_CCTR(ch),
+				      RCANFD_CCTR_CHMDC_MASK,
+				      RCANFD_CCTR_CHDMC_CRESET);
+
+		/* Ensure Channel reset mode */
+		err = readl_poll_timeout((gpriv->base + RCANFD_CSTS(ch)), sts,
+					 (sts & RCANFD_CSTS_CRSTSTS),
+					 2, 500000);
+		if (err) {
+			dev_dbg(&gpriv->pdev->dev,
+				"channel %u reset failed\n", ch);
+			return err;
+		}
+	}
+	return 0;
+}
+
+static void rcar_canfd_configure_controller(struct rcar_canfd_global *gpriv)
+{
+	u32 cfg, ch;
+
+	/* Global configuration settings */
+
+	/* Truncate payload to configured message size RFPLS */
+	cfg = RCANFD_GCFG_CMPOC;
+
+	/* Set External Clock if selected */
+	if (gpriv->fcan != RCANFD_CANFDCLK)
+		cfg |= RCANFD_GCFG_DCS;
+
+	rcar_canfd_set_bit(gpriv->base, RCANFD_GCFG, cfg);
+
+	/* Channel configuration settings */
+	for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS) {
+		rcar_canfd_set_bit(gpriv->base, RCANFD_CCTR(ch),
+				   RCANFD_CCTR_ERRD);
+		rcar_canfd_update_bit(gpriv->base, RCANFD_CCTR(ch),
+				      RCANFD_CCTR_BOM_MASK,
+				      RCANFD_CCTR_BOM_BENTRY);
+	}
+}
+
+static void rcar_canfd_configure_afl_rules(struct rcar_canfd_global *gpriv,
+					   u32 ch)
+{
+	u32 cfg;
+	int start, page, num_rules = RCANFD_CHANNEL_NUMRULES;
+	u32 ridx = ch + RCANFD_RFFIFO_IDX;
+
+	if (ch == 0) {
+		start = 0; /* Channel 0 always starts from 0th rule */
+	} else {
+		/* Get number of Channel 0 rules and adjust */
+		cfg = rcar_canfd_read(gpriv->base, RCANFD_GAFLCFG0);
+		start = RCANFD_GAFLCFG_GETRNC(0, cfg);
+	}
+
+	/* Enable write access to entry */
+	page = RCANFD_GAFL_PAGENUM(start);
+	rcar_canfd_set_bit(gpriv->base, RCANFD_GAFLECTR,
+			   (RCANFD_GAFLECTR_AFLPN(page) |
+			    RCANFD_GAFLECTR_AFLDAE));
+
+	/* Write number of rules for channel */
+	rcar_canfd_set_bit(gpriv->base, RCANFD_GAFLCFG0,
+			   RCANFD_GAFLCFG_SETRNC(ch, num_rules));
+
+	/* Accept all IDs */
+	rcar_canfd_write(gpriv->base,
+			 RCANFD_GAFLID(RCANFD_F_GAFL_OFFSET, start), 0);
+	/* IDE or RTR is not considered for matching */
+	rcar_canfd_write(gpriv->base,
+			 RCANFD_GAFLM(RCANFD_F_GAFL_OFFSET, start), 0);
+	/* Any data length accepted */
+	rcar_canfd_write(gpriv->base,
+			 RCANFD_GAFLP0(RCANFD_F_GAFL_OFFSET, start), 0);
+	/* Place the msg in corresponding Rx FIFO entry */
+	rcar_canfd_write(gpriv->base,
+			 RCANFD_GAFLP1(RCANFD_F_GAFL_OFFSET, start),
+			 RCANFD_GAFLP1_GAFLFDP(ridx));
+
+	/* Disable write access to page */
+	rcar_canfd_clear_bit(gpriv->base,
+			     RCANFD_GAFLECTR, RCANFD_GAFLECTR_AFLDAE);
+}
+
+static void rcar_canfd_configure_rx(struct rcar_canfd_global *gpriv, u32 ch)
+{
+	/* Rx FIFO is used for reception */
+	u32 cfg;
+	u16 rfdc, rfpls;
+
+	/* Select Rx FIFO based on channel */
+	u32 ridx = ch + RCANFD_RFFIFO_IDX;
+
+	rfdc = 2;		/* b010 - 8 messages Rx FIFO depth */
+	rfpls = 7;		/* b111 - Max 64 bytes payload */
+
+	cfg = (RCANFD_RFCC_RFIM | RCANFD_RFCC_RFDC(rfdc) |
+		RCANFD_RFCC_RFPLS(rfpls) | RCANFD_RFCC_RFIE);
+	rcar_canfd_write(gpriv->base, RCANFD_RFCC(ridx), cfg);
+}
+
+static void rcar_canfd_configure_tx(struct rcar_canfd_global *gpriv, u32 ch)
+{
+	/* Tx/Rx(Common) FIFO configured in Tx mode is
+	 * used for transmission
+	 *
+	 * Each channel has 3 Common FIFO dedicated to them.
+	 * Use the 1st (index 0) out of 3
+	 */
+	u32 cfg;
+	u16 cftml, cfm, cfdc, cfpls;
+
+	cftml = 0;		/* 0th buffer */
+	cfm = 1;		/* b01 - Transmit mode */
+	cfdc = 2;		/* b010 - 8 messages Tx FIFO depth */
+	cfpls = 7;		/* b111 - Max 64 bytes payload */
+
+	cfg = (RCANFD_CFCC_CFTML(cftml) | RCANFD_CFCC_CFM(cfm) |
+		RCANFD_CFCC_CFIM | RCANFD_CFCC_CFDC(cfdc) |
+		RCANFD_CFCC_CFPLS(cfpls) | RCANFD_CFCC_CFTXIE);
+	rcar_canfd_write(gpriv->base, RCANFD_CFCC(ch, RCANFD_CFFIFO_IDX), cfg);
+
+	/* Clear FD mode specific control/status register */
+	rcar_canfd_write(gpriv->base,
+			 RCANFD_F_CFFDCSTS(ch, RCANFD_CFFIFO_IDX), 0);
+}
+
+static void rcar_canfd_enable_global_interrupts(struct rcar_canfd_global *gpriv)
+{
+	u32 ctr;
+
+	/* Clear any stray error interrupt flags */
+	rcar_canfd_write(gpriv->base, RCANFD_GERFL, 0);
+
+	/* Global interrupts setup */
+	ctr = RCANFD_GCTR_MEIE;
+	ctr |= RCANFD_GCTR_CFMPOFIE;
+
+	rcar_canfd_set_bit(gpriv->base, RCANFD_GCTR, ctr);
+}
+
+static void rcar_canfd_disable_global_interrupts(struct rcar_canfd_global
+						 *gpriv)
+{
+	/* Disable all interrupts */
+	rcar_canfd_write(gpriv->base, RCANFD_GCTR, 0);
+
+	/* Clear any stray error interrupt flags */
+	rcar_canfd_write(gpriv->base, RCANFD_GERFL, 0);
+}
+
+static void rcar_canfd_enable_channel_interrupts(struct rcar_canfd_channel
+						 *priv)
+{
+	u32 ctr, ch = priv->channel;
+
+	/* Clear any stray error flags */
+	rcar_canfd_write(priv->base, RCANFD_CERFL(ch), 0);
+
+	/* Channel interrupts setup */
+	ctr = (RCANFD_CCTR_TAIE |
+	       RCANFD_CCTR_ALIE | RCANFD_CCTR_BLIE |
+	       RCANFD_CCTR_OLIE | RCANFD_CCTR_BORIE |
+	       RCANFD_CCTR_BOEIE | RCANFD_CCTR_EPIE |
+	       RCANFD_CCTR_EWIE | RCANFD_CCTR_BEIE);
+	rcar_canfd_set_bit(priv->base, RCANFD_CCTR(ch), ctr);
+}
+
+static void rcar_canfd_disable_channel_interrupts(struct rcar_canfd_channel
+						  *priv)
+{
+	u32 ctr, ch = priv->channel;
+
+	ctr = (RCANFD_CCTR_TAIE |
+	       RCANFD_CCTR_ALIE | RCANFD_CCTR_BLIE |
+	       RCANFD_CCTR_OLIE | RCANFD_CCTR_BORIE |
+	       RCANFD_CCTR_BOEIE | RCANFD_CCTR_EPIE |
+	       RCANFD_CCTR_EWIE | RCANFD_CCTR_BEIE);
+	rcar_canfd_clear_bit(priv->base, RCANFD_CCTR(ch), ctr);
+
+	/* Clear any stray error flags */
+	rcar_canfd_write(priv->base, RCANFD_CERFL(ch), 0);
+}
+
+static void rcar_canfd_global_error(struct net_device *ndev)
+{
+	struct rcar_canfd_channel *priv = netdev_priv(ndev);
+	struct net_device_stats *stats = &ndev->stats;
+	u32 ch = priv->channel;
+	u32 gerfl, sts;
+	u32 ridx = ch + RCANFD_RFFIFO_IDX;
+
+	gerfl = rcar_canfd_read(priv->base, RCANFD_GERFL);
+	if ((gerfl & RCANFD_GERFL_EEF0) && (ch == 0)) {
+		netdev_dbg(ndev, "Ch0: ECC Error flag\n");
+		stats->tx_dropped++;
+	}
+	if ((gerfl & RCANFD_GERFL_EEF1) && (ch == 1)) {
+		netdev_dbg(ndev, "Ch1: ECC Error flag\n");
+		stats->tx_dropped++;
+	}
+	if (gerfl & RCANFD_GERFL_MES) {
+		sts = rcar_canfd_read(priv->base,
+				      RCANFD_CFSTS(ch, RCANFD_CFFIFO_IDX));
+		if (sts & RCANFD_CFSTS_CFMLT) {
+			netdev_dbg(ndev, "Tx Message Lost flag\n");
+			stats->tx_dropped++;
+			rcar_canfd_write(priv->base,
+					 RCANFD_CFSTS(ch, RCANFD_CFFIFO_IDX),
+					 sts & ~RCANFD_CFSTS_CFMLT);
+		}
+
+		sts = rcar_canfd_read(priv->base, RCANFD_RFSTS(ridx));
+		if (sts & RCANFD_RFSTS_RFMLT) {
+			netdev_dbg(ndev, "Rx Message Lost flag\n");
+			stats->rx_dropped++;
+			rcar_canfd_write(priv->base, RCANFD_RFSTS(ridx),
+					 sts & ~RCANFD_RFSTS_RFMLT);
+		}
+	}
+	if (gerfl & RCANFD_GERFL_CMPOF) {
+		/* Message Lost flag will be set for respective channel
+		 * when this condition happens with counters and flags
+		 * already updated.
+		 */
+		netdev_dbg(ndev, "global payload overflow interrupt\n");
+	}
+
+	/* Clear all global error interrupts. Only affected channels bits
+	 * get cleared
+	 */
+	rcar_canfd_write(priv->base, RCANFD_GERFL, 0);
+}
+
+static void rcar_canfd_error(struct net_device *ndev)
+{
+	struct rcar_canfd_channel *priv = netdev_priv(ndev);
+	struct net_device_stats *stats = &ndev->stats;
+	struct can_frame *cf;
+	struct sk_buff *skb;
+	u32 cerfl, csts;
+	u32 txerr = 0, rxerr = 0;
+	u32 ch = priv->channel;
+
+	/* Propagate the error condition to the CAN stack */
+	skb = alloc_can_err_skb(ndev, &cf);
+	if (!skb) {
+		stats->rx_dropped++;
+		return;
+	}
+
+	/* Channel error interrupt */
+	cerfl = rcar_canfd_read(priv->base, RCANFD_CERFL(ch));
+	csts = rcar_canfd_read(priv->base, RCANFD_CSTS(ch));
+	txerr = RCANFD_CSTS_TECCNT(csts);
+	rxerr = RCANFD_CSTS_RECCNT(csts);
+
+	netdev_dbg(ndev, "ch erfl %x sts %x txerr %u rxerr %u\n",
+		   cerfl, csts, txerr, rxerr);
+
+	if (cerfl & RCANFD_CERFL_BEF) {
+		netdev_dbg(ndev, "Bus error\n");
+		cf->can_id |= CAN_ERR_BUSERROR | CAN_ERR_PROT;
+		cf->data[2] = CAN_ERR_PROT_UNSPEC;
+		priv->can.can_stats.bus_error++;
+	}
+	if (cerfl & RCANFD_CERFL_ADERR) {
+		netdev_dbg(ndev, "ACK Delimiter Error\n");
+		stats->tx_errors++;
+		cf->data[3] |= CAN_ERR_PROT_LOC_ACK_DEL;
+	}
+	if (cerfl & RCANFD_CERFL_B0ERR) {
+		netdev_dbg(ndev, "Bit Error (dominant)\n");
+		stats->tx_errors++;
+		cf->data[2] |= CAN_ERR_PROT_BIT0;
+	}
+	if (cerfl & RCANFD_CERFL_B1ERR) {
+		netdev_dbg(ndev, "Bit Error (recessive)\n");
+		stats->tx_errors++;
+		cf->data[2] |= CAN_ERR_PROT_BIT1;
+	}
+	if (cerfl & RCANFD_CERFL_CERR) {
+		netdev_dbg(ndev, "CRC Error\n");
+		stats->rx_errors++;
+		cf->data[3] |= CAN_ERR_PROT_LOC_CRC_SEQ;
+	}
+	if (cerfl & RCANFD_CERFL_AERR) {
+		netdev_dbg(ndev, "ACK Error\n");
+		stats->tx_errors++;
+		cf->can_id |= CAN_ERR_ACK;
+		cf->data[3] |= CAN_ERR_PROT_LOC_ACK;
+	}
+	if (cerfl & RCANFD_CERFL_FERR) {
+		netdev_dbg(ndev, "Form Error\n");
+		stats->rx_errors++;
+		cf->data[2] |= CAN_ERR_PROT_FORM;
+	}
+	if (cerfl & RCANFD_CERFL_SERR) {
+		netdev_dbg(ndev, "Stuff Error\n");
+		stats->rx_errors++;
+		cf->data[2] |= CAN_ERR_PROT_STUFF;
+	}
+	if (cerfl & RCANFD_CERFL_ALF) {
+		netdev_dbg(ndev, "Arbitration lost Error\n");
+		priv->can.can_stats.arbitration_lost++;
+		cf->can_id |= CAN_ERR_LOSTARB;
+		cf->data[0] |= CAN_ERR_LOSTARB_UNSPEC;
+	}
+	if (cerfl & RCANFD_CERFL_BLF) {
+		netdev_dbg(ndev, "Bus Lock Error\n");
+		stats->rx_errors++;
+		cf->can_id |= CAN_ERR_BUSERROR;
+	}
+	if (cerfl & RCANFD_CERFL_EWF) {
+		netdev_dbg(ndev, "Error warning interrupt\n");
+		priv->can.state = CAN_STATE_ERROR_WARNING;
+		priv->can.can_stats.error_warning++;
+		cf->can_id |= CAN_ERR_CRTL;
+		cf->data[1] = txerr > rxerr ? CAN_ERR_CRTL_TX_WARNING :
+			CAN_ERR_CRTL_RX_WARNING;
+		cf->data[6] = txerr;
+		cf->data[7] = rxerr;
+	}
+	if (cerfl & RCANFD_CERFL_EPF) {
+		netdev_dbg(ndev, "Error passive interrupt\n");
+		priv->can.state = CAN_STATE_ERROR_PASSIVE;
+		priv->can.can_stats.error_passive++;
+		cf->can_id |= CAN_ERR_CRTL;
+		cf->data[1] = txerr > rxerr ? CAN_ERR_CRTL_TX_PASSIVE :
+			CAN_ERR_CRTL_RX_PASSIVE;
+		cf->data[6] = txerr;
+		cf->data[7] = rxerr;
+	}
+	if (cerfl & RCANFD_CERFL_BOEF) {
+		netdev_dbg(ndev, "Bus-off entry interrupt\n");
+		rcar_canfd_tx_failure_cleanup(ndev);
+		priv->can.state = CAN_STATE_BUS_OFF;
+		priv->can.can_stats.bus_off++;
+		can_bus_off(ndev);
+		cf->can_id |= CAN_ERR_BUSOFF;
+	}
+	if (cerfl & RCANFD_CERFL_OVLF) {
+		netdev_dbg(ndev,
+			   "Overload Frame Transmission error interrupt\n");
+		stats->tx_errors++;
+		cf->can_id |= CAN_ERR_PROT;
+		cf->data[2] |= CAN_ERR_PROT_OVERLOAD;
+	}
+
+	/* Clear all channel error interrupts */
+	rcar_canfd_write(priv->base, RCANFD_CERFL(ch), 0);
+	stats->rx_packets++;
+	stats->rx_bytes += cf->can_dlc;
+	netif_rx(skb);
+}
+
+static void rcar_canfd_tx_done(struct net_device *ndev)
+{
+	struct rcar_canfd_channel *priv = netdev_priv(ndev);
+	struct net_device_stats *stats = &ndev->stats;
+	u32 sts;
+	unsigned long flags;
+	u32 ch = priv->channel;
+
+	do {
+		u8 unsent, sent;
+
+		sent = priv->tx_tail % RCANFD_FIFO_DEPTH;
+		stats->tx_packets++;
+		stats->tx_bytes += priv->tx_len[sent];
+		priv->tx_len[sent] = 0;
+		can_get_echo_skb(ndev, sent);
+
+		spin_lock_irqsave(&priv->tx_lock, flags);
+		priv->tx_tail++;
+		sts = rcar_canfd_read(priv->base,
+				      RCANFD_CFSTS(ch, RCANFD_CFFIFO_IDX));
+		unsent = RCANFD_CFSTS_CFMC(sts);
+
+		/* Wake producer only when there is room */
+		if (unsent != RCANFD_FIFO_DEPTH)
+			netif_wake_queue(ndev);
+
+		if (priv->tx_head - priv->tx_tail <= unsent) {
+			spin_unlock_irqrestore(&priv->tx_lock, flags);
+			break;
+		}
+		spin_unlock_irqrestore(&priv->tx_lock, flags);
+
+	} while (1);
+
+	/* Clear interrupt */
+	rcar_canfd_write(priv->base, RCANFD_CFSTS(ch, RCANFD_CFFIFO_IDX),
+			 sts & ~RCANFD_CFSTS_CFTXIF);
+	can_led_event(ndev, CAN_LED_EVENT_TX);
+}
+
+static irqreturn_t rcar_canfd_global_interrupt(int irq, void *dev_id)
+{
+	struct rcar_canfd_global *gpriv = dev_id;
+	struct net_device *ndev;
+	struct rcar_canfd_channel *priv;
+	u32 sts, gerfl;
+	u32 ch, ridx;
+
+	/* Global error interrupts still indicate a condition specific
+	 * to a channel. RxFIFO interrupt is a global interrupt.
+	 */
+	for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS) {
+		priv = gpriv->ch[ch];
+		ndev = priv->ndev;
+		ridx = ch + RCANFD_RFFIFO_IDX;
+
+		/* Global error interrupts */
+		gerfl = rcar_canfd_read(priv->base, RCANFD_GERFL);
+		if (RCANFD_GERFL_ERR(gerfl))
+			rcar_canfd_global_error(ndev);
+
+		/* Handle Rx interrupts */
+		sts = rcar_canfd_read(priv->base, RCANFD_RFSTS(ridx));
+		if (sts & RCANFD_RFSTS_RFIF) {
+			if (napi_schedule_prep(&priv->napi)) {
+				/* Disable Rx FIFO interrupts */
+				rcar_canfd_clear_bit(priv->base,
+						     RCANFD_RFCC(ridx),
+						     RCANFD_RFCC_RFIE);
+				__napi_schedule(&priv->napi);
+			}
+		}
+	}
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t rcar_canfd_channel_interrupt(int irq, void *dev_id)
+{
+	struct rcar_canfd_global *gpriv = dev_id;
+	struct net_device *ndev;
+	struct rcar_canfd_channel *priv;
+	u32 sts, cerfl, ch;
+
+	/* Common FIFO is a per channel resource */
+	for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS) {
+		priv = gpriv->ch[ch];
+		ndev = priv->ndev;
+
+		/* Channel error interrupts */
+		cerfl = rcar_canfd_read(priv->base, RCANFD_CERFL(ch));
+		if (RCANFD_CERFL_ERR(cerfl))
+			rcar_canfd_error(ndev);
+
+		/* Handle Tx interrupts */
+		sts = rcar_canfd_read(priv->base,
+				      RCANFD_CFSTS(ch, RCANFD_CFFIFO_IDX));
+		if (sts & RCANFD_CFSTS_CFTXIF)
+			rcar_canfd_tx_done(ndev);
+	}
+	return IRQ_HANDLED;
+}
+
+static void rcar_canfd_set_bittiming(struct net_device *dev)
+{
+	struct rcar_canfd_channel *priv = netdev_priv(dev);
+	const struct can_bittiming *bt = &priv->can.bittiming;
+	const struct can_bittiming *dbt = &priv->can.data_bittiming;
+	u16 brp, sjw, tseg1, tseg2;
+	u32 cfg;
+	u32 ch = priv->channel;
+
+	/* Nominal bit timing settings */
+	brp = bt->brp - 1;
+	sjw = bt->sjw - 1;
+	tseg1 = bt->prop_seg + bt->phase_seg1 - 1;
+	tseg2 = bt->phase_seg2 - 1;
+
+	cfg = (RCANFD_NCFG_NTSEG1(tseg1) | RCANFD_NCFG_NBRP(brp) |
+	       RCANFD_NCFG_NSJW(sjw) | RCANFD_NCFG_NTSEG2(tseg2));
+
+	rcar_canfd_write(priv->base, RCANFD_CCFG(ch), cfg);
+	netdev_dbg(priv->ndev, "nrate: brp %u, sjw %u, tseg1 %u, tseg2 %u\n",
+		   brp, sjw, tseg1, tseg2);
+
+	/* Data bit timing settings */
+	brp = dbt->brp - 1;
+	sjw = dbt->sjw - 1;
+	tseg1 = dbt->prop_seg + dbt->phase_seg1 - 1;
+	tseg2 = dbt->phase_seg2 - 1;
+
+	cfg = (RCANFD_DCFG_DTSEG1(tseg1) | RCANFD_DCFG_DBRP(brp) |
+	       RCANFD_DCFG_DSJW(sjw) | RCANFD_DCFG_DTSEG2(tseg2));
+
+	rcar_canfd_write(priv->base, RCANFD_F_DCFG(ch), cfg);
+	netdev_dbg(priv->ndev, "drate: brp %u, sjw %u, tseg1 %u, tseg2 %u\n",
+		   brp, sjw, tseg1, tseg2);
+}
+
+static int rcar_canfd_start(struct net_device *ndev)
+{
+	struct rcar_canfd_channel *priv = netdev_priv(ndev);
+	int err = -EOPNOTSUPP;
+	u32 sts, ch = priv->channel;
+	u32 ridx = ch + RCANFD_RFFIFO_IDX;
+
+	rcar_canfd_set_bittiming(ndev);
+
+	rcar_canfd_enable_channel_interrupts(priv);
+
+	/* Set channel to Operational mode */
+	rcar_canfd_update_bit(priv->base, RCANFD_CCTR(ch),
+			      RCANFD_CCTR_CHMDC_MASK, RCANFD_CCTR_CHDMC_COPM);
+
+	/* Verify channel mode change */
+	err = readl_poll_timeout((priv->base + RCANFD_CSTS(ch)), sts,
+				 (sts & RCANFD_CSTS_COMSTS), 2, 500000);
+	if (err) {
+		netdev_err(ndev, "channel %u communication state failed\n", ch);
+		goto fail_mode_change;
+	}
+
+	/* Enable Common & Rx FIFO */
+	rcar_canfd_set_bit(priv->base, RCANFD_CFCC(ch, RCANFD_CFFIFO_IDX),
+			   RCANFD_CFCC_CFE);
+	rcar_canfd_set_bit(priv->base, RCANFD_RFCC(ridx), RCANFD_RFCC_RFE);
+
+	priv->can.state = CAN_STATE_ERROR_ACTIVE;
+	return 0;
+
+fail_mode_change:
+	rcar_canfd_disable_channel_interrupts(priv);
+	return err;
+}
+
+static int rcar_canfd_open(struct net_device *ndev)
+{
+	struct rcar_canfd_channel *priv = netdev_priv(ndev);
+	struct rcar_canfd_global *gpriv = priv->gpriv;
+	int err;
+
+	/* Peripheral clock is already enabled in probe */
+	err = clk_prepare_enable(gpriv->can_clk);
+	if (err) {
+		netdev_err(ndev, "failed to enable CAN clock, error %d\n", err);
+		goto out_clock;
+	}
+
+	err = open_candev(ndev);
+	if (err) {
+		netdev_err(ndev, "open_candev() failed, error %d\n", err);
+		goto out_can_clock;
+	}
+
+	napi_enable(&priv->napi);
+	err = rcar_canfd_start(ndev);
+	if (err)
+		goto out_close;
+	netif_start_queue(ndev);
+	can_led_event(ndev, CAN_LED_EVENT_OPEN);
+	return 0;
+out_close:
+	napi_disable(&priv->napi);
+	close_candev(ndev);
+out_can_clock:
+	clk_disable_unprepare(gpriv->can_clk);
+out_clock:
+	return err;
+}
+
+static void rcar_canfd_stop(struct net_device *ndev)
+{
+	struct rcar_canfd_channel *priv = netdev_priv(ndev);
+	int err;
+	u32 sts, ch = priv->channel;
+	u32 ridx = ch + RCANFD_RFFIFO_IDX;
+
+	/* Transition to channel reset mode  */
+	rcar_canfd_update_bit(priv->base, RCANFD_CCTR(ch),
+			      RCANFD_CCTR_CHMDC_MASK, RCANFD_CCTR_CHDMC_CRESET);
+
+	/* Check Channel reset mode */
+	err = readl_poll_timeout((priv->base + RCANFD_CSTS(ch)), sts,
+				 (sts & RCANFD_CSTS_CRSTSTS), 2, 500000);
+	if (err)
+		netdev_err(ndev, "channel %u reset failed\n", ch);
+
+	rcar_canfd_disable_channel_interrupts(priv);
+
+	/* Disable Common & Rx FIFO */
+	rcar_canfd_clear_bit(priv->base, RCANFD_CFCC(ch, RCANFD_CFFIFO_IDX),
+			     RCANFD_CFCC_CFE);
+	rcar_canfd_clear_bit(priv->base, RCANFD_RFCC(ridx), RCANFD_RFCC_RFE);
+
+	/* Set the state as STOPPED */
+	priv->can.state = CAN_STATE_STOPPED;
+}
+
+static int rcar_canfd_close(struct net_device *ndev)
+{
+	struct rcar_canfd_channel *priv = netdev_priv(ndev);
+	struct rcar_canfd_global *gpriv = priv->gpriv;
+
+	netif_stop_queue(ndev);
+	rcar_canfd_stop(ndev);
+	napi_disable(&priv->napi);
+	clk_disable_unprepare(gpriv->can_clk);
+	close_candev(ndev);
+	can_led_event(ndev, CAN_LED_EVENT_STOP);
+	return 0;
+}
+
+static netdev_tx_t rcar_canfd_start_xmit(struct sk_buff *skb,
+					 struct net_device *ndev)
+{
+	struct rcar_canfd_channel *priv = netdev_priv(ndev);
+	struct canfd_frame *cf = (struct canfd_frame *)skb->data;
+	u32 sts = 0, id, dlc;
+	unsigned long flags;
+	u32 ch = priv->channel;
+
+	if (can_dropped_invalid_skb(ndev, skb))
+		return NETDEV_TX_OK;
+
+	if (cf->can_id & CAN_EFF_FLAG) {
+		id = cf->can_id & CAN_EFF_MASK;
+		id |= RCANFD_CFID_CFIDE;
+	} else {
+		id = cf->can_id & CAN_SFF_MASK;
+	}
+
+	if (cf->can_id & CAN_RTR_FLAG)
+		id |= RCANFD_CFID_CFRTR;
+
+	rcar_canfd_write(priv->base,
+			 RCANFD_F_CFID(ch, RCANFD_CFFIFO_IDX), id);
+	dlc = RCANFD_CFPTR_CFDLC(can_len2dlc(cf->len));
+	rcar_canfd_write(priv->base,
+			 RCANFD_F_CFPTR(ch, RCANFD_CFFIFO_IDX), dlc);
+
+	if (can_is_canfd_skb(skb)) {
+		/* CAN FD frame format */
+		sts |= RCANFD_CFFDCSTS_CFFDF;
+		if (cf->flags & CANFD_BRS)
+			sts |= RCANFD_CFFDCSTS_CFBRS;
+
+		if (priv->can.state == CAN_STATE_ERROR_PASSIVE)
+			sts |= RCANFD_CFFDCSTS_CFESI;
+	}
+
+	rcar_canfd_write(priv->base, RCANFD_F_CFFDCSTS(ch, RCANFD_CFFIFO_IDX),
+			 sts);
+
+	rcar_canfd_put_data(priv, cf,
+			    RCANFD_F_CFDF(ch, RCANFD_CFFIFO_IDX, 0));
+
+	priv->tx_len[priv->tx_head % RCANFD_FIFO_DEPTH] = cf->len;
+	can_put_echo_skb(skb, ndev, priv->tx_head % RCANFD_FIFO_DEPTH);
+
+	spin_lock_irqsave(&priv->tx_lock, flags);
+	priv->tx_head++;
+
+	/* Stop the queue if we've filled all FIFO entries */
+	if (priv->tx_head - priv->tx_tail >= RCANFD_FIFO_DEPTH)
+		netif_stop_queue(ndev);
+
+	/* Start Tx: Write 0xff to CFPC to increment the CPU-side
+	 * pointer for the Common FIFO
+	 */
+	rcar_canfd_write(priv->base,
+			 RCANFD_CFPCTR(ch, RCANFD_CFFIFO_IDX), 0xff);
+
+	spin_unlock_irqrestore(&priv->tx_lock, flags);
+	return NETDEV_TX_OK;
+}
+
+static void rcar_canfd_rx_pkt(struct rcar_canfd_channel *priv)
+{
+	struct net_device_stats *stats = &priv->ndev->stats;
+	struct canfd_frame *cf;
+	struct sk_buff *skb;
+	u32 sts = 0, id, ptr;
+	u32 ch = priv->channel;
+	u32 ridx = ch + RCANFD_RFFIFO_IDX;
+
+	id = rcar_canfd_read(priv->base, RCANFD_F_RFID(ridx));
+	ptr = rcar_canfd_read(priv->base, RCANFD_F_RFPTR(ridx));
+
+	sts = rcar_canfd_read(priv->base, RCANFD_F_RFFDSTS(ridx));
+	if (sts & RCANFD_RFFDSTS_RFFDF)
+		skb = alloc_canfd_skb(priv->ndev, &cf);
+	else
+		skb = alloc_can_skb(priv->ndev,
+				    (struct can_frame **)&cf);
+
+	if (!skb) {
+		stats->rx_dropped++;
+		return;
+	}
+
+	if (sts & RCANFD_RFFDSTS_RFFDF)
+		cf->len = can_dlc2len(RCANFD_RFPTR_RFDLC(ptr));
+	else
+		cf->len = get_can_dlc(RCANFD_RFPTR_RFDLC(ptr));
+
+	if (sts & RCANFD_RFFDSTS_RFESI) {
+		cf->flags |= CANFD_ESI;
+		netdev_dbg(priv->ndev, "ESI Error\n");
+	}
+
+	if (id & RCANFD_RFID_RFIDE)
+		cf->can_id = (id & CAN_EFF_MASK) | CAN_EFF_FLAG;
+	else
+		cf->can_id = id & CAN_SFF_MASK;
+
+	if (!(sts & RCANFD_RFFDSTS_RFFDF) && (id & RCANFD_RFID_RFRTR)) {
+		cf->can_id |= CAN_RTR_FLAG;
+	} else {
+		if (sts & RCANFD_RFFDSTS_RFBRS)
+			cf->flags |= CANFD_BRS;
+
+		rcar_canfd_get_data(priv, cf, RCANFD_F_RFDF(ridx, 0));
+	}
+
+	/* Write 0xff to RFPC to increment the CPU-side
+	 * pointer of the Rx FIFO
+	 */
+	rcar_canfd_write(priv->base, RCANFD_RFPCTR(ridx), 0xff);
+
+	can_led_event(priv->ndev, CAN_LED_EVENT_RX);
+
+	stats->rx_bytes += cf->len;
+	stats->rx_packets++;
+	netif_receive_skb(skb);
+}
+
+static int rcar_canfd_rx_poll(struct napi_struct *napi, int quota)
+{
+	struct rcar_canfd_channel *priv =
+		container_of(napi, struct rcar_canfd_channel, napi);
+	int num_pkts;
+	u32 sts;
+	u32 ch = priv->channel;
+	u32 ridx = ch + RCANFD_RFFIFO_IDX;
+
+	for (num_pkts = 0; num_pkts < quota; num_pkts++) {
+		sts = rcar_canfd_read(priv->base, RCANFD_RFSTS(ridx));
+		/* Check FIFO empty condition */
+		if (sts & RCANFD_RFSTS_RFEMP)
+			break;
+
+		rcar_canfd_rx_pkt(priv);
+
+		/* Clear interrupt bit */
+		if (sts & RCANFD_RFSTS_RFIF)
+			rcar_canfd_write(priv->base, RCANFD_RFSTS(ridx),
+					 sts & ~RCANFD_RFSTS_RFIF);
+	}
+
+	/* All packets processed */
+	if (num_pkts < quota) {
+		napi_complete(napi);
+		/* Enable Rx FIFO interrupts */
+		rcar_canfd_set_bit(priv->base, RCANFD_RFCC(ridx),
+				   RCANFD_RFCC_RFIE);
+	}
+	return num_pkts;
+}
+
+static int rcar_canfd_do_set_mode(struct net_device *ndev, enum can_mode mode)
+{
+	int err;
+
+	switch (mode) {
+	case CAN_MODE_START:
+		err = rcar_canfd_start(ndev);
+		if (err)
+			return err;
+		netif_wake_queue(ndev);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int rcar_canfd_get_berr_counter(const struct net_device *dev,
+				       struct can_berr_counter *bec)
+{
+	struct rcar_canfd_channel *priv = netdev_priv(dev);
+	u32 val, ch = priv->channel;
+
+	/* Peripheral clock is already enabled in probe */
+	val = rcar_canfd_read(priv->base, RCANFD_CSTS(ch));
+	bec->txerr = RCANFD_CSTS_TECCNT(val);
+	bec->rxerr = RCANFD_CSTS_RECCNT(val);
+	return 0;
+}
+
+static const struct net_device_ops rcar_canfd_netdev_ops = {
+	.ndo_open = rcar_canfd_open,
+	.ndo_stop = rcar_canfd_close,
+	.ndo_start_xmit = rcar_canfd_start_xmit,
+	.ndo_change_mtu = can_change_mtu,
+};
+
+static int rcar_canfd_channel_probe(struct rcar_canfd_global *gpriv, u32 ch,
+				    u32 fcan_freq)
+{
+	struct platform_device *pdev = gpriv->pdev;
+	struct rcar_canfd_channel *priv;
+	struct net_device *ndev;
+	int err = -ENODEV;
+
+	ndev = alloc_candev(sizeof(*priv), RCANFD_FIFO_DEPTH);
+	if (!ndev) {
+		dev_err(&pdev->dev, "alloc_candev() failed\n");
+		err = -ENOMEM;
+		goto fail;
+	}
+	priv = netdev_priv(ndev);
+
+	ndev->netdev_ops = &rcar_canfd_netdev_ops;
+	ndev->flags |= IFF_ECHO;
+	priv->ndev = ndev;
+	priv->base = gpriv->base;
+	priv->channel = ch;
+	priv->can.clock.freq = fcan_freq;
+	dev_info(&pdev->dev, "can_clk rate is %u\n", priv->can.clock.freq);
+
+	priv->can.bittiming_const = &rcar_canfd_nom_bittiming_const;
+	priv->can.data_bittiming_const =
+		&rcar_canfd_data_bittiming_const;
+
+	/* Controller starts in CAN FD only mode */
+	can_set_static_ctrlmode(ndev, CAN_CTRLMODE_FD);
+	priv->can.ctrlmode_supported = CAN_CTRLMODE_BERR_REPORTING;
+
+	priv->can.do_set_mode = rcar_canfd_do_set_mode;
+	priv->can.do_get_berr_counter = rcar_canfd_get_berr_counter;
+	priv->gpriv = gpriv;
+	SET_NETDEV_DEV(ndev, &pdev->dev);
+
+	netif_napi_add(ndev, &priv->napi, rcar_canfd_rx_poll,
+		       RCANFD_NAPI_WEIGHT);
+	err = register_candev(ndev);
+	if (err) {
+		dev_err(&pdev->dev,
+			"register_candev() failed, error %d\n", err);
+		goto fail_candev;
+	}
+	spin_lock_init(&priv->tx_lock);
+	devm_can_led_init(ndev);
+	gpriv->ch[priv->channel] = priv;
+	dev_info(&pdev->dev, "device registered (channel %u)\n", priv->channel);
+	return 0;
+
+fail_candev:
+	netif_napi_del(&priv->napi);
+	free_candev(ndev);
+fail:
+	return err;
+}
+
+static void rcar_canfd_channel_remove(struct rcar_canfd_global *gpriv, u32 ch)
+{
+	struct rcar_canfd_channel *priv = gpriv->ch[ch];
+
+	if (priv) {
+		unregister_candev(priv->ndev);
+		netif_napi_del(&priv->napi);
+		free_candev(priv->ndev);
+	}
+}
+
+static int rcar_canfd_probe(struct platform_device *pdev)
+{
+	struct resource *mem;
+	void __iomem *addr;
+	u32 sts, ch, fcan_freq;
+	struct rcar_canfd_global *gpriv;
+	struct device_node *of_child;
+	unsigned long channels_mask = 0;
+	int err, ch_irq, g_irq;
+
+	of_child = of_get_child_by_name(pdev->dev.of_node, "channel0");
+	if (of_child && of_device_is_available(of_child))
+		channels_mask |= BIT(0);	/* Channel 0 */
+
+	of_child = of_get_child_by_name(pdev->dev.of_node, "channel1");
+	if (of_child && of_device_is_available(of_child))
+		channels_mask |= BIT(1);	/* Channel 1 */
+
+	ch_irq = platform_get_irq(pdev, 0);
+	if (ch_irq < 0) {
+		dev_err(&pdev->dev, "no Channel IRQ resource\n");
+		err = ch_irq;
+		goto fail_dev;
+	}
+
+	g_irq = platform_get_irq(pdev, 1);
+	if (g_irq < 0) {
+		dev_err(&pdev->dev, "no Global IRQ resource\n");
+		err = g_irq;
+		goto fail_dev;
+	}
+
+	/* Global controller context */
+	gpriv = devm_kzalloc(&pdev->dev, sizeof(*gpriv), GFP_KERNEL);
+	if (!gpriv) {
+		err = -ENOMEM;
+		goto fail_dev;
+	}
+	gpriv->pdev = pdev;
+	gpriv->channels_mask = channels_mask;
+
+	/* Peripheral clock */
+	gpriv->clkp = devm_clk_get(&pdev->dev, "fck");
+	if (IS_ERR(gpriv->clkp)) {
+		err = PTR_ERR(gpriv->clkp);
+		dev_err(&pdev->dev, "cannot get peripheral clock, error %d\n",
+			err);
+		goto fail_dev;
+	}
+
+	/* fCAN clock: Pick External clock. If not available fallback to
+	 * CANFD clock
+	 */
+	gpriv->can_clk = devm_clk_get(&pdev->dev, "can_clk");
+	if (IS_ERR(gpriv->can_clk) || (clk_get_rate(gpriv->can_clk) == 0)) {
+		gpriv->can_clk = devm_clk_get(&pdev->dev, "canfd");
+		if (IS_ERR(gpriv->can_clk)) {
+			err = PTR_ERR(gpriv->can_clk);
+			dev_err(&pdev->dev,
+				"cannot get canfd clock, error %d\n", err);
+			goto fail_dev;
+		}
+		gpriv->fcan = RCANFD_CANFDCLK;
+
+	} else {
+		gpriv->fcan = RCANFD_EXTCLK;
+	}
+	fcan_freq = clk_get_rate(gpriv->can_clk);
+
+	if (gpriv->fcan == RCANFD_CANFDCLK)
+		/* CANFD clock is further divided by (1/2) within the IP */
+		fcan_freq /= 2;
+
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	addr = devm_ioremap_resource(&pdev->dev, mem);
+	if (IS_ERR(addr)) {
+		err = PTR_ERR(addr);
+		goto fail_dev;
+	}
+	gpriv->base = addr;
+
+	/* Request IRQ that's common for both channels */
+	err = devm_request_irq(&pdev->dev, ch_irq,
+			       rcar_canfd_channel_interrupt, 0,
+			       "canfd.chn", gpriv);
+	if (err) {
+		dev_err(&pdev->dev, "devm_request_irq(%d) failed, error %d\n",
+			ch_irq, err);
+		goto fail_dev;
+	}
+	err = devm_request_irq(&pdev->dev, g_irq,
+			       rcar_canfd_global_interrupt, 0,
+			       "canfd.gbl", gpriv);
+	if (err) {
+		dev_err(&pdev->dev, "devm_request_irq(%d) failed, error %d\n",
+			g_irq, err);
+		goto fail_dev;
+	}
+
+	/* Enable peripheral clock for register access */
+	err = clk_prepare_enable(gpriv->clkp);
+	if (err) {
+		dev_err(&pdev->dev,
+			"failed to enable peripheral clock, error %d\n", err);
+		goto fail_dev;
+	}
+
+	err = rcar_canfd_reset_controller(gpriv);
+	if (err) {
+		dev_err(&pdev->dev, "reset controller failed\n");
+		goto fail_clk;
+	}
+
+	/* Controller in Global reset & Channel reset mode */
+	rcar_canfd_configure_controller(gpriv);
+
+	/* Configure per channel attributes */
+	for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS) {
+		/* Configure Channel's Rx fifo */
+		rcar_canfd_configure_rx(gpriv, ch);
+
+		/* Configure Channel's Tx (Common) fifo */
+		rcar_canfd_configure_tx(gpriv, ch);
+
+		/* Configure receive rules */
+		rcar_canfd_configure_afl_rules(gpriv, ch);
+	}
+
+	/* Configure common interrupts */
+	rcar_canfd_enable_global_interrupts(gpriv);
+
+	/* Start Global operation mode */
+	rcar_canfd_update_bit(gpriv->base, RCANFD_GCTR, RCANFD_GCTR_GMDC_MASK,
+			      RCANFD_GCTR_GMDC_GOPM);
+
+	/* Verify mode change */
+	err = readl_poll_timeout((gpriv->base + RCANFD_GSTS), sts,
+				 !(sts & RCANFD_GSTS_GNOPM), 2, 500000);
+	if (err) {
+		dev_err(&pdev->dev, "global operational mode failed\n");
+		goto fail_mode;
+	}
+
+	for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS) {
+		err = rcar_canfd_channel_probe(gpriv, ch, fcan_freq);
+		if (err)
+			goto fail_channel;
+	}
+
+	platform_set_drvdata(pdev, gpriv);
+	dev_info(&pdev->dev, "global operational state (clk %d)\n",
+		 gpriv->fcan);
+	return 0;
+
+fail_channel:
+	for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS)
+		rcar_canfd_channel_remove(gpriv, ch);
+fail_mode:
+	rcar_canfd_disable_global_interrupts(gpriv);
+fail_clk:
+	clk_disable_unprepare(gpriv->clkp);
+fail_dev:
+	return err;
+}
+
+static int rcar_canfd_remove(struct platform_device *pdev)
+{
+	struct rcar_canfd_global *gpriv = platform_get_drvdata(pdev);
+	u32 ch;
+
+	rcar_canfd_reset_controller(gpriv);
+	rcar_canfd_disable_global_interrupts(gpriv);
+
+	for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS) {
+		rcar_canfd_disable_channel_interrupts(gpriv->ch[ch]);
+		rcar_canfd_channel_remove(gpriv, ch);
+	}
+
+	/* Enter global sleep mode */
+	rcar_canfd_set_bit(gpriv->base, RCANFD_GCTR, RCANFD_GCTR_GSLPR);
+	clk_disable_unprepare(gpriv->clkp);
+	return 0;
+}
+
+static int __maybe_unused rcar_canfd_suspend(struct device *dev)
+{
+	return 0;
+}
+
+static int __maybe_unused rcar_canfd_resume(struct device *dev)
+{
+	return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(rcar_canfd_pm_ops, rcar_canfd_suspend,
+			 rcar_canfd_resume);
+
+static const struct of_device_id rcar_canfd_of_table[] = {
+	{ .compatible = "renesas,rcar-gen3-canfd" },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(of, rcar_canfd_of_table);
+
+static struct platform_driver rcar_canfd_driver = {
+	.driver = {
+		.name = RCANFD_DRV_NAME,
+		.of_match_table = of_match_ptr(rcar_canfd_of_table),
+		.pm = &rcar_canfd_pm_ops,
+	},
+	.probe = rcar_canfd_probe,
+	.remove = rcar_canfd_remove,
+};
+
+module_platform_driver(rcar_canfd_driver);
+
+MODULE_AUTHOR("Ramesh Shanmugasundaram <ramesh.shanmugasundaram@bp.renesas.com>");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("CAN FD driver for Renesas R-Car SoC");
+MODULE_ALIAS("platform:" RCANFD_DRV_NAME);
diff --git a/drivers/net/can/sja1000/tscan1.c b/drivers/net/can/sja1000/tscan1.c
index 76513dd..79572457 100644
--- a/drivers/net/can/sja1000/tscan1.c
+++ b/drivers/net/can/sja1000/tscan1.c
@@ -203,14 +203,4 @@
 	},
 };
 
-static int __init tscan1_init(void)
-{
-	return isa_register_driver(&tscan1_isa_driver, TSCAN1_MAXDEV);
-}
-module_init(tscan1_init);
-
-static void __exit tscan1_exit(void)
-{
-	isa_unregister_driver(&tscan1_isa_driver);
-}
-module_exit(tscan1_exit);
+module_isa_driver(tscan1_isa_driver, TSCAN1_MAXDEV);
diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c
index 9a3f15c..eb71737 100644
--- a/drivers/net/can/slcan.c
+++ b/drivers/net/can/slcan.c
@@ -354,7 +354,7 @@
 {
 	struct slcan *sl = netdev_priv(dev);
 
-	if (skb->len != sizeof(struct can_frame))
+	if (skb->len != CAN_MTU)
 		goto out;
 
 	spin_lock(&sl->lock);
@@ -442,7 +442,7 @@
 	dev->addr_len		= 0;
 	dev->tx_queue_len	= 10;
 
-	dev->mtu		= sizeof(struct can_frame);
+	dev->mtu		= CAN_MTU;
 	dev->type		= ARPHRD_CAN;
 
 	/* New-style flags. */
diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index 1556d42..3607643 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -39,7 +39,9 @@
 	GS_USB_BREQ_MODE,
 	GS_USB_BREQ_BERR,
 	GS_USB_BREQ_BT_CONST,
-	GS_USB_BREQ_DEVICE_CONFIG
+	GS_USB_BREQ_DEVICE_CONFIG,
+	GS_USB_BREQ_TIMESTAMP,
+	GS_USB_BREQ_IDENTIFY,
 };
 
 enum gs_can_mode {
@@ -58,6 +60,11 @@
 	GS_CAN_STATE_SLEEPING
 };
 
+enum gs_can_identify_mode {
+	GS_CAN_IDENTIFY_OFF = 0,
+	GS_CAN_IDENTIFY_ON
+};
+
 /* data types passed between host and device */
 struct gs_host_config {
 	u32 byte_order;
@@ -77,10 +84,10 @@
 } __packed;
 
 #define GS_CAN_MODE_NORMAL               0
-#define GS_CAN_MODE_LISTEN_ONLY          (1<<0)
-#define GS_CAN_MODE_LOOP_BACK            (1<<1)
-#define GS_CAN_MODE_TRIPLE_SAMPLE        (1<<2)
-#define GS_CAN_MODE_ONE_SHOT             (1<<3)
+#define GS_CAN_MODE_LISTEN_ONLY          BIT(0)
+#define GS_CAN_MODE_LOOP_BACK            BIT(1)
+#define GS_CAN_MODE_TRIPLE_SAMPLE        BIT(2)
+#define GS_CAN_MODE_ONE_SHOT             BIT(3)
 
 struct gs_device_mode {
 	u32 mode;
@@ -101,10 +108,16 @@
 	u32 brp;
 } __packed;
 
-#define GS_CAN_FEATURE_LISTEN_ONLY      (1<<0)
-#define GS_CAN_FEATURE_LOOP_BACK        (1<<1)
-#define GS_CAN_FEATURE_TRIPLE_SAMPLE    (1<<2)
-#define GS_CAN_FEATURE_ONE_SHOT         (1<<3)
+struct gs_identify_mode {
+	u32 mode;
+} __packed;
+
+#define GS_CAN_FEATURE_LISTEN_ONLY      BIT(0)
+#define GS_CAN_FEATURE_LOOP_BACK        BIT(1)
+#define GS_CAN_FEATURE_TRIPLE_SAMPLE    BIT(2)
+#define GS_CAN_FEATURE_ONE_SHOT         BIT(3)
+#define GS_CAN_FEATURE_HW_TIMESTAMP     BIT(4)
+#define GS_CAN_FEATURE_IDENTIFY         BIT(5)
 
 struct gs_device_bt_const {
 	u32 feature;
@@ -209,7 +222,8 @@
 
 /* Get a tx context by id.
  */
-static struct gs_tx_context *gs_get_tx_context(struct gs_can *dev, unsigned int id)
+static struct gs_tx_context *gs_get_tx_context(struct gs_can *dev,
+					       unsigned int id)
 {
 	unsigned long flags;
 
@@ -452,7 +466,8 @@
 		netif_wake_queue(netdev);
 }
 
-static netdev_tx_t gs_can_start_xmit(struct sk_buff *skb, struct net_device *netdev)
+static netdev_tx_t gs_can_start_xmit(struct sk_buff *skb,
+				     struct net_device *netdev)
 {
 	struct gs_can *dev = netdev_priv(netdev);
 	struct net_device_stats *stats = &dev->netdev->stats;
@@ -658,7 +673,8 @@
 	rc = usb_control_msg(interface_to_usbdev(dev->iface),
 			     usb_sndctrlpipe(interface_to_usbdev(dev->iface), 0),
 			     GS_USB_BREQ_MODE,
-			     USB_DIR_OUT|USB_TYPE_VENDOR|USB_RECIP_INTERFACE,
+			     USB_DIR_OUT | USB_TYPE_VENDOR |
+			     USB_RECIP_INTERFACE,
 			     dev->channel,
 			     0,
 			     dm,
@@ -721,7 +737,59 @@
 	.ndo_change_mtu = can_change_mtu,
 };
 
-static struct gs_can *gs_make_candev(unsigned int channel, struct usb_interface *intf)
+static int gs_usb_set_identify(struct net_device *netdev, bool do_identify)
+{
+	struct gs_can *dev = netdev_priv(netdev);
+	struct gs_identify_mode imode;
+	int rc;
+
+	if (do_identify)
+		imode.mode = GS_CAN_IDENTIFY_ON;
+	else
+		imode.mode = GS_CAN_IDENTIFY_OFF;
+
+	rc = usb_control_msg(interface_to_usbdev(dev->iface),
+			     usb_sndctrlpipe(interface_to_usbdev(dev->iface),
+					     0),
+			     GS_USB_BREQ_IDENTIFY,
+			     USB_DIR_OUT | USB_TYPE_VENDOR |
+			     USB_RECIP_INTERFACE,
+			     dev->channel,
+			     0,
+			     &imode,
+			     sizeof(imode),
+			     100);
+
+	return (rc > 0) ? 0 : rc;
+}
+
+/* blink LED's for finding the this interface */
+static int gs_usb_set_phys_id(struct net_device *dev,
+			      enum ethtool_phys_id_state state)
+{
+	int rc = 0;
+
+	switch (state) {
+	case ETHTOOL_ID_ACTIVE:
+		rc = gs_usb_set_identify(dev, GS_CAN_IDENTIFY_ON);
+		break;
+	case ETHTOOL_ID_INACTIVE:
+		rc = gs_usb_set_identify(dev, GS_CAN_IDENTIFY_OFF);
+		break;
+	default:
+		break;
+	}
+
+	return rc;
+}
+
+static const struct ethtool_ops gs_usb_ethtool_ops = {
+	.set_phys_id = gs_usb_set_phys_id,
+};
+
+static struct gs_can *gs_make_candev(unsigned int channel,
+				     struct usb_interface *intf,
+				     struct gs_device_config *dconf)
 {
 	struct gs_can *dev;
 	struct net_device *netdev;
@@ -809,10 +877,14 @@
 	if (bt_const->feature & GS_CAN_FEATURE_ONE_SHOT)
 		dev->can.ctrlmode_supported |= CAN_CTRLMODE_ONE_SHOT;
 
-	kfree(bt_const);
-
 	SET_NETDEV_DEV(netdev, &intf->dev);
 
+	if (dconf->sw_version > 1)
+		if (bt_const->feature & GS_CAN_FEATURE_IDENTIFY)
+			netdev->ethtool_ops = &gs_usb_ethtool_ops;
+
+	kfree(bt_const);
+
 	rc = register_candev(dev->netdev);
 	if (rc) {
 		free_candev(dev->netdev);
@@ -830,19 +902,16 @@
 	free_candev(dev->netdev);
 }
 
-static int gs_usb_probe(struct usb_interface *intf, const struct usb_device_id *id)
+static int gs_usb_probe(struct usb_interface *intf,
+			const struct usb_device_id *id)
 {
 	struct gs_usb *dev;
 	int rc = -ENOMEM;
 	unsigned int icount, i;
-	struct gs_host_config *hconf;
-	struct gs_device_config *dconf;
-
-	hconf = kmalloc(sizeof(*hconf), GFP_KERNEL);
-	if (!hconf)
-		return -ENOMEM;
-
-	hconf->byte_order = 0x0000beef;
+	struct gs_host_config hconf = {
+		.byte_order = 0x0000beef,
+	};
+	struct gs_device_config dconf;
 
 	/* send host config */
 	rc = usb_control_msg(interface_to_usbdev(intf),
@@ -851,22 +920,16 @@
 			     USB_DIR_OUT|USB_TYPE_VENDOR|USB_RECIP_INTERFACE,
 			     1,
 			     intf->altsetting[0].desc.bInterfaceNumber,
-			     hconf,
-			     sizeof(*hconf),
+			     &hconf,
+			     sizeof(hconf),
 			     1000);
 
-	kfree(hconf);
-
 	if (rc < 0) {
 		dev_err(&intf->dev, "Couldn't send data format (err=%d)\n",
 			rc);
 		return rc;
 	}
 
-	dconf = kmalloc(sizeof(*dconf), GFP_KERNEL);
-	if (!dconf)
-		return -ENOMEM;
-
 	/* read device config */
 	rc = usb_control_msg(interface_to_usbdev(intf),
 			     usb_rcvctrlpipe(interface_to_usbdev(intf), 0),
@@ -874,22 +937,16 @@
 			     USB_DIR_IN|USB_TYPE_VENDOR|USB_RECIP_INTERFACE,
 			     1,
 			     intf->altsetting[0].desc.bInterfaceNumber,
-			     dconf,
-			     sizeof(*dconf),
+			     &dconf,
+			     sizeof(dconf),
 			     1000);
 	if (rc < 0) {
 		dev_err(&intf->dev, "Couldn't get device config: (err=%d)\n",
 			rc);
-
-		kfree(dconf);
-
 		return rc;
 	}
 
-	icount = dconf->icount+1;
-
-	kfree(dconf);
-
+	icount = dconf.icount + 1;
 	dev_info(&intf->dev, "Configuring for %d interfaces\n", icount);
 
 	if (icount > GS_MAX_INTF) {
@@ -910,7 +967,7 @@
 	dev->udev = interface_to_usbdev(intf);
 
 	for (i = 0; i < icount; i++) {
-		dev->canch[i] = gs_make_candev(i, intf);
+		dev->canch[i] = gs_make_candev(i, intf, &dconf);
 		if (IS_ERR_OR_NULL(dev->canch[i])) {
 			/* save error code to return later */
 			rc = PTR_ERR(dev->canch[i]);
diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig
index 200663c..be481e1 100644
--- a/drivers/net/dsa/Kconfig
+++ b/drivers/net/dsa/Kconfig
@@ -28,4 +28,6 @@
 	  This enables support for the Broadcom Starfighter 2 Ethernet
 	  switch chips.
 
+source "drivers/net/dsa/b53/Kconfig"
+
 endmenu
diff --git a/drivers/net/dsa/Makefile b/drivers/net/dsa/Makefile
index 76b751d..97bc70a 100644
--- a/drivers/net/dsa/Makefile
+++ b/drivers/net/dsa/Makefile
@@ -1,3 +1,5 @@
 obj-$(CONFIG_NET_DSA_MV88E6060) += mv88e6060.o
 obj-$(CONFIG_NET_DSA_MV88E6XXX) += mv88e6xxx.o
 obj-$(CONFIG_NET_DSA_BCM_SF2)	+= bcm_sf2.o
+
+obj-y				+= b53/
diff --git a/drivers/net/dsa/b53/Kconfig b/drivers/net/dsa/b53/Kconfig
new file mode 100644
index 0000000..27f32a5
--- /dev/null
+++ b/drivers/net/dsa/b53/Kconfig
@@ -0,0 +1,33 @@
+menuconfig B53
+	tristate "Broadcom BCM53xx managed switch support"
+	depends on NET_DSA
+	help
+	  This driver adds support for Broadcom managed switch chips. It supports
+	  BCM5325E, BCM5365, BCM539x, BCM53115 and BCM53125 as well as BCM63XX
+	  integrated switches.
+
+config B53_SPI_DRIVER
+	tristate "B53 SPI connected switch driver"
+	depends on B53 && SPI
+	help
+	  Select to enable support for registering switches configured through SPI.
+
+config B53_MDIO_DRIVER
+	tristate "B53 MDIO connected switch driver"
+	depends on B53
+	help
+	  Select to enable support for registering switches configured through MDIO.
+
+config B53_MMAP_DRIVER
+	tristate "B53 MMAP connected switch driver"
+	depends on B53 && HAS_IOMEM
+	help
+	  Select to enable support for memory-mapped switches like the BCM63XX
+	  integrated switches.
+
+config B53_SRAB_DRIVER
+	tristate "B53 SRAB connected switch driver"
+	depends on B53 && HAS_IOMEM
+	help
+	  Select to enable support for memory-mapped Switch Register Access
+	  Bridge Registers (SRAB) like it is found on the BCM53010
diff --git a/drivers/net/dsa/b53/Makefile b/drivers/net/dsa/b53/Makefile
new file mode 100644
index 0000000..7e6f9a8
--- /dev/null
+++ b/drivers/net/dsa/b53/Makefile
@@ -0,0 +1,6 @@
+obj-$(CONFIG_B53)		+= b53_common.o
+
+obj-$(CONFIG_B53_SPI_DRIVER)	+= b53_spi.o
+obj-$(CONFIG_B53_MDIO_DRIVER)	+= b53_mdio.o
+obj-$(CONFIG_B53_MMAP_DRIVER)	+= b53_mmap.o
+obj-$(CONFIG_B53_SRAB_DRIVER)	+= b53_srab.o
diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
new file mode 100644
index 0000000..444de66
--- /dev/null
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -0,0 +1,1787 @@
+/*
+ * B53 switch driver main logic
+ *
+ * Copyright (C) 2011-2013 Jonas Gorski <jogo@openwrt.org>
+ * Copyright (C) 2016 Florian Fainelli <f.fainelli@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/delay.h>
+#include <linux/export.h>
+#include <linux/gpio.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_data/b53.h>
+#include <linux/phy.h>
+#include <linux/etherdevice.h>
+#include <linux/if_bridge.h>
+#include <net/dsa.h>
+#include <net/switchdev.h>
+
+#include "b53_regs.h"
+#include "b53_priv.h"
+
+struct b53_mib_desc {
+	u8 size;
+	u8 offset;
+	const char *name;
+};
+
+/* BCM5365 MIB counters */
+static const struct b53_mib_desc b53_mibs_65[] = {
+	{ 8, 0x00, "TxOctets" },
+	{ 4, 0x08, "TxDropPkts" },
+	{ 4, 0x10, "TxBroadcastPkts" },
+	{ 4, 0x14, "TxMulticastPkts" },
+	{ 4, 0x18, "TxUnicastPkts" },
+	{ 4, 0x1c, "TxCollisions" },
+	{ 4, 0x20, "TxSingleCollision" },
+	{ 4, 0x24, "TxMultipleCollision" },
+	{ 4, 0x28, "TxDeferredTransmit" },
+	{ 4, 0x2c, "TxLateCollision" },
+	{ 4, 0x30, "TxExcessiveCollision" },
+	{ 4, 0x38, "TxPausePkts" },
+	{ 8, 0x44, "RxOctets" },
+	{ 4, 0x4c, "RxUndersizePkts" },
+	{ 4, 0x50, "RxPausePkts" },
+	{ 4, 0x54, "Pkts64Octets" },
+	{ 4, 0x58, "Pkts65to127Octets" },
+	{ 4, 0x5c, "Pkts128to255Octets" },
+	{ 4, 0x60, "Pkts256to511Octets" },
+	{ 4, 0x64, "Pkts512to1023Octets" },
+	{ 4, 0x68, "Pkts1024to1522Octets" },
+	{ 4, 0x6c, "RxOversizePkts" },
+	{ 4, 0x70, "RxJabbers" },
+	{ 4, 0x74, "RxAlignmentErrors" },
+	{ 4, 0x78, "RxFCSErrors" },
+	{ 8, 0x7c, "RxGoodOctets" },
+	{ 4, 0x84, "RxDropPkts" },
+	{ 4, 0x88, "RxUnicastPkts" },
+	{ 4, 0x8c, "RxMulticastPkts" },
+	{ 4, 0x90, "RxBroadcastPkts" },
+	{ 4, 0x94, "RxSAChanges" },
+	{ 4, 0x98, "RxFragments" },
+};
+
+#define B53_MIBS_65_SIZE	ARRAY_SIZE(b53_mibs_65)
+
+/* BCM63xx MIB counters */
+static const struct b53_mib_desc b53_mibs_63xx[] = {
+	{ 8, 0x00, "TxOctets" },
+	{ 4, 0x08, "TxDropPkts" },
+	{ 4, 0x0c, "TxQoSPkts" },
+	{ 4, 0x10, "TxBroadcastPkts" },
+	{ 4, 0x14, "TxMulticastPkts" },
+	{ 4, 0x18, "TxUnicastPkts" },
+	{ 4, 0x1c, "TxCollisions" },
+	{ 4, 0x20, "TxSingleCollision" },
+	{ 4, 0x24, "TxMultipleCollision" },
+	{ 4, 0x28, "TxDeferredTransmit" },
+	{ 4, 0x2c, "TxLateCollision" },
+	{ 4, 0x30, "TxExcessiveCollision" },
+	{ 4, 0x38, "TxPausePkts" },
+	{ 8, 0x3c, "TxQoSOctets" },
+	{ 8, 0x44, "RxOctets" },
+	{ 4, 0x4c, "RxUndersizePkts" },
+	{ 4, 0x50, "RxPausePkts" },
+	{ 4, 0x54, "Pkts64Octets" },
+	{ 4, 0x58, "Pkts65to127Octets" },
+	{ 4, 0x5c, "Pkts128to255Octets" },
+	{ 4, 0x60, "Pkts256to511Octets" },
+	{ 4, 0x64, "Pkts512to1023Octets" },
+	{ 4, 0x68, "Pkts1024to1522Octets" },
+	{ 4, 0x6c, "RxOversizePkts" },
+	{ 4, 0x70, "RxJabbers" },
+	{ 4, 0x74, "RxAlignmentErrors" },
+	{ 4, 0x78, "RxFCSErrors" },
+	{ 8, 0x7c, "RxGoodOctets" },
+	{ 4, 0x84, "RxDropPkts" },
+	{ 4, 0x88, "RxUnicastPkts" },
+	{ 4, 0x8c, "RxMulticastPkts" },
+	{ 4, 0x90, "RxBroadcastPkts" },
+	{ 4, 0x94, "RxSAChanges" },
+	{ 4, 0x98, "RxFragments" },
+	{ 4, 0xa0, "RxSymbolErrors" },
+	{ 4, 0xa4, "RxQoSPkts" },
+	{ 8, 0xa8, "RxQoSOctets" },
+	{ 4, 0xb0, "Pkts1523to2047Octets" },
+	{ 4, 0xb4, "Pkts2048to4095Octets" },
+	{ 4, 0xb8, "Pkts4096to8191Octets" },
+	{ 4, 0xbc, "Pkts8192to9728Octets" },
+	{ 4, 0xc0, "RxDiscarded" },
+};
+
+#define B53_MIBS_63XX_SIZE	ARRAY_SIZE(b53_mibs_63xx)
+
+/* MIB counters */
+static const struct b53_mib_desc b53_mibs[] = {
+	{ 8, 0x00, "TxOctets" },
+	{ 4, 0x08, "TxDropPkts" },
+	{ 4, 0x10, "TxBroadcastPkts" },
+	{ 4, 0x14, "TxMulticastPkts" },
+	{ 4, 0x18, "TxUnicastPkts" },
+	{ 4, 0x1c, "TxCollisions" },
+	{ 4, 0x20, "TxSingleCollision" },
+	{ 4, 0x24, "TxMultipleCollision" },
+	{ 4, 0x28, "TxDeferredTransmit" },
+	{ 4, 0x2c, "TxLateCollision" },
+	{ 4, 0x30, "TxExcessiveCollision" },
+	{ 4, 0x38, "TxPausePkts" },
+	{ 8, 0x50, "RxOctets" },
+	{ 4, 0x58, "RxUndersizePkts" },
+	{ 4, 0x5c, "RxPausePkts" },
+	{ 4, 0x60, "Pkts64Octets" },
+	{ 4, 0x64, "Pkts65to127Octets" },
+	{ 4, 0x68, "Pkts128to255Octets" },
+	{ 4, 0x6c, "Pkts256to511Octets" },
+	{ 4, 0x70, "Pkts512to1023Octets" },
+	{ 4, 0x74, "Pkts1024to1522Octets" },
+	{ 4, 0x78, "RxOversizePkts" },
+	{ 4, 0x7c, "RxJabbers" },
+	{ 4, 0x80, "RxAlignmentErrors" },
+	{ 4, 0x84, "RxFCSErrors" },
+	{ 8, 0x88, "RxGoodOctets" },
+	{ 4, 0x90, "RxDropPkts" },
+	{ 4, 0x94, "RxUnicastPkts" },
+	{ 4, 0x98, "RxMulticastPkts" },
+	{ 4, 0x9c, "RxBroadcastPkts" },
+	{ 4, 0xa0, "RxSAChanges" },
+	{ 4, 0xa4, "RxFragments" },
+	{ 4, 0xa8, "RxJumboPkts" },
+	{ 4, 0xac, "RxSymbolErrors" },
+	{ 4, 0xc0, "RxDiscarded" },
+};
+
+#define B53_MIBS_SIZE	ARRAY_SIZE(b53_mibs)
+
+static int b53_do_vlan_op(struct b53_device *dev, u8 op)
+{
+	unsigned int i;
+
+	b53_write8(dev, B53_ARLIO_PAGE, dev->vta_regs[0], VTA_START_CMD | op);
+
+	for (i = 0; i < 10; i++) {
+		u8 vta;
+
+		b53_read8(dev, B53_ARLIO_PAGE, dev->vta_regs[0], &vta);
+		if (!(vta & VTA_START_CMD))
+			return 0;
+
+		usleep_range(100, 200);
+	}
+
+	return -EIO;
+}
+
+static void b53_set_vlan_entry(struct b53_device *dev, u16 vid,
+			       struct b53_vlan *vlan)
+{
+	if (is5325(dev)) {
+		u32 entry = 0;
+
+		if (vlan->members) {
+			entry = ((vlan->untag & VA_UNTAG_MASK_25) <<
+				 VA_UNTAG_S_25) | vlan->members;
+			if (dev->core_rev >= 3)
+				entry |= VA_VALID_25_R4 | vid << VA_VID_HIGH_S;
+			else
+				entry |= VA_VALID_25;
+		}
+
+		b53_write32(dev, B53_VLAN_PAGE, B53_VLAN_WRITE_25, entry);
+		b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_TABLE_ACCESS_25, vid |
+			    VTA_RW_STATE_WR | VTA_RW_OP_EN);
+	} else if (is5365(dev)) {
+		u16 entry = 0;
+
+		if (vlan->members)
+			entry = ((vlan->untag & VA_UNTAG_MASK_65) <<
+				 VA_UNTAG_S_65) | vlan->members | VA_VALID_65;
+
+		b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_WRITE_65, entry);
+		b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_TABLE_ACCESS_65, vid |
+			    VTA_RW_STATE_WR | VTA_RW_OP_EN);
+	} else {
+		b53_write16(dev, B53_ARLIO_PAGE, dev->vta_regs[1], vid);
+		b53_write32(dev, B53_ARLIO_PAGE, dev->vta_regs[2],
+			    (vlan->untag << VTE_UNTAG_S) | vlan->members);
+
+		b53_do_vlan_op(dev, VTA_CMD_WRITE);
+	}
+
+	dev_dbg(dev->ds->dev, "VID: %d, members: 0x%04x, untag: 0x%04x\n",
+		vid, vlan->members, vlan->untag);
+}
+
+static void b53_get_vlan_entry(struct b53_device *dev, u16 vid,
+			       struct b53_vlan *vlan)
+{
+	if (is5325(dev)) {
+		u32 entry = 0;
+
+		b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_TABLE_ACCESS_25, vid |
+			    VTA_RW_STATE_RD | VTA_RW_OP_EN);
+		b53_read32(dev, B53_VLAN_PAGE, B53_VLAN_WRITE_25, &entry);
+
+		if (dev->core_rev >= 3)
+			vlan->valid = !!(entry & VA_VALID_25_R4);
+		else
+			vlan->valid = !!(entry & VA_VALID_25);
+		vlan->members = entry & VA_MEMBER_MASK;
+		vlan->untag = (entry >> VA_UNTAG_S_25) & VA_UNTAG_MASK_25;
+
+	} else if (is5365(dev)) {
+		u16 entry = 0;
+
+		b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_TABLE_ACCESS_65, vid |
+			    VTA_RW_STATE_WR | VTA_RW_OP_EN);
+		b53_read16(dev, B53_VLAN_PAGE, B53_VLAN_WRITE_65, &entry);
+
+		vlan->valid = !!(entry & VA_VALID_65);
+		vlan->members = entry & VA_MEMBER_MASK;
+		vlan->untag = (entry >> VA_UNTAG_S_65) & VA_UNTAG_MASK_65;
+	} else {
+		u32 entry = 0;
+
+		b53_write16(dev, B53_ARLIO_PAGE, dev->vta_regs[1], vid);
+		b53_do_vlan_op(dev, VTA_CMD_READ);
+		b53_read32(dev, B53_ARLIO_PAGE, dev->vta_regs[2], &entry);
+		vlan->members = entry & VTE_MEMBERS;
+		vlan->untag = (entry >> VTE_UNTAG_S) & VTE_MEMBERS;
+		vlan->valid = true;
+	}
+}
+
+static void b53_set_forwarding(struct b53_device *dev, int enable)
+{
+	u8 mgmt;
+
+	b53_read8(dev, B53_CTRL_PAGE, B53_SWITCH_MODE, &mgmt);
+
+	if (enable)
+		mgmt |= SM_SW_FWD_EN;
+	else
+		mgmt &= ~SM_SW_FWD_EN;
+
+	b53_write8(dev, B53_CTRL_PAGE, B53_SWITCH_MODE, mgmt);
+}
+
+static void b53_enable_vlan(struct b53_device *dev, bool enable)
+{
+	u8 mgmt, vc0, vc1, vc4 = 0, vc5;
+
+	b53_read8(dev, B53_CTRL_PAGE, B53_SWITCH_MODE, &mgmt);
+	b53_read8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL0, &vc0);
+	b53_read8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL1, &vc1);
+
+	if (is5325(dev) || is5365(dev)) {
+		b53_read8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL4_25, &vc4);
+		b53_read8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL5_25, &vc5);
+	} else if (is63xx(dev)) {
+		b53_read8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL4_63XX, &vc4);
+		b53_read8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL5_63XX, &vc5);
+	} else {
+		b53_read8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL4, &vc4);
+		b53_read8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL5, &vc5);
+	}
+
+	mgmt &= ~SM_SW_FWD_MODE;
+
+	if (enable) {
+		vc0 |= VC0_VLAN_EN | VC0_VID_CHK_EN | VC0_VID_HASH_VID;
+		vc1 |= VC1_RX_MCST_UNTAG_EN | VC1_RX_MCST_FWD_EN;
+		vc4 &= ~VC4_ING_VID_CHECK_MASK;
+		vc4 |= VC4_ING_VID_VIO_DROP << VC4_ING_VID_CHECK_S;
+		vc5 |= VC5_DROP_VTABLE_MISS;
+
+		if (is5325(dev))
+			vc0 &= ~VC0_RESERVED_1;
+
+		if (is5325(dev) || is5365(dev))
+			vc1 |= VC1_RX_MCST_TAG_EN;
+
+	} else {
+		vc0 &= ~(VC0_VLAN_EN | VC0_VID_CHK_EN | VC0_VID_HASH_VID);
+		vc1 &= ~(VC1_RX_MCST_UNTAG_EN | VC1_RX_MCST_FWD_EN);
+		vc4 &= ~VC4_ING_VID_CHECK_MASK;
+		vc5 &= ~VC5_DROP_VTABLE_MISS;
+
+		if (is5325(dev) || is5365(dev))
+			vc4 |= VC4_ING_VID_VIO_FWD << VC4_ING_VID_CHECK_S;
+		else
+			vc4 |= VC4_ING_VID_VIO_TO_IMP << VC4_ING_VID_CHECK_S;
+
+		if (is5325(dev) || is5365(dev))
+			vc1 &= ~VC1_RX_MCST_TAG_EN;
+	}
+
+	if (!is5325(dev) && !is5365(dev))
+		vc5 &= ~VC5_VID_FFF_EN;
+
+	b53_write8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL0, vc0);
+	b53_write8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL1, vc1);
+
+	if (is5325(dev) || is5365(dev)) {
+		/* enable the high 8 bit vid check on 5325 */
+		if (is5325(dev) && enable)
+			b53_write8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL3,
+				   VC3_HIGH_8BIT_EN);
+		else
+			b53_write8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL3, 0);
+
+		b53_write8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL4_25, vc4);
+		b53_write8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL5_25, vc5);
+	} else if (is63xx(dev)) {
+		b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_CTRL3_63XX, 0);
+		b53_write8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL4_63XX, vc4);
+		b53_write8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL5_63XX, vc5);
+	} else {
+		b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_CTRL3, 0);
+		b53_write8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL4, vc4);
+		b53_write8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL5, vc5);
+	}
+
+	b53_write8(dev, B53_CTRL_PAGE, B53_SWITCH_MODE, mgmt);
+}
+
+static int b53_set_jumbo(struct b53_device *dev, bool enable, bool allow_10_100)
+{
+	u32 port_mask = 0;
+	u16 max_size = JMS_MIN_SIZE;
+
+	if (is5325(dev) || is5365(dev))
+		return -EINVAL;
+
+	if (enable) {
+		port_mask = dev->enabled_ports;
+		max_size = JMS_MAX_SIZE;
+		if (allow_10_100)
+			port_mask |= JPM_10_100_JUMBO_EN;
+	}
+
+	b53_write32(dev, B53_JUMBO_PAGE, dev->jumbo_pm_reg, port_mask);
+	return b53_write16(dev, B53_JUMBO_PAGE, dev->jumbo_size_reg, max_size);
+}
+
+static int b53_flush_arl(struct b53_device *dev, u8 mask)
+{
+	unsigned int i;
+
+	b53_write8(dev, B53_CTRL_PAGE, B53_FAST_AGE_CTRL,
+		   FAST_AGE_DONE | FAST_AGE_DYNAMIC | mask);
+
+	for (i = 0; i < 10; i++) {
+		u8 fast_age_ctrl;
+
+		b53_read8(dev, B53_CTRL_PAGE, B53_FAST_AGE_CTRL,
+			  &fast_age_ctrl);
+
+		if (!(fast_age_ctrl & FAST_AGE_DONE))
+			goto out;
+
+		msleep(1);
+	}
+
+	return -ETIMEDOUT;
+out:
+	/* Only age dynamic entries (default behavior) */
+	b53_write8(dev, B53_CTRL_PAGE, B53_FAST_AGE_CTRL, FAST_AGE_DYNAMIC);
+	return 0;
+}
+
+static int b53_fast_age_port(struct b53_device *dev, int port)
+{
+	b53_write8(dev, B53_CTRL_PAGE, B53_FAST_AGE_PORT_CTRL, port);
+
+	return b53_flush_arl(dev, FAST_AGE_PORT);
+}
+
+static int b53_fast_age_vlan(struct b53_device *dev, u16 vid)
+{
+	b53_write16(dev, B53_CTRL_PAGE, B53_FAST_AGE_VID_CTRL, vid);
+
+	return b53_flush_arl(dev, FAST_AGE_VLAN);
+}
+
+static void b53_imp_vlan_setup(struct dsa_switch *ds, int cpu_port)
+{
+	struct b53_device *dev = ds_to_priv(ds);
+	unsigned int i;
+	u16 pvlan;
+
+	/* Enable the IMP port to be in the same VLAN as the other ports
+	 * on a per-port basis such that we only have Port i and IMP in
+	 * the same VLAN.
+	 */
+	b53_for_each_port(dev, i) {
+		b53_read16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(i), &pvlan);
+		pvlan |= BIT(cpu_port);
+		b53_write16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(i), pvlan);
+	}
+}
+
+static int b53_enable_port(struct dsa_switch *ds, int port,
+			   struct phy_device *phy)
+{
+	struct b53_device *dev = ds_to_priv(ds);
+	unsigned int cpu_port = dev->cpu_port;
+	u16 pvlan;
+
+	/* Clear the Rx and Tx disable bits and set to no spanning tree */
+	b53_write8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), 0);
+
+	/* Set this port, and only this one to be in the default VLAN,
+	 * if member of a bridge, restore its membership prior to
+	 * bringing down this port.
+	 */
+	b53_read16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(port), &pvlan);
+	pvlan &= ~0x1ff;
+	pvlan |= BIT(port);
+	pvlan |= dev->ports[port].vlan_ctl_mask;
+	b53_write16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(port), pvlan);
+
+	b53_imp_vlan_setup(ds, cpu_port);
+
+	return 0;
+}
+
+static void b53_disable_port(struct dsa_switch *ds, int port,
+			     struct phy_device *phy)
+{
+	struct b53_device *dev = ds_to_priv(ds);
+	u8 reg;
+
+	/* Disable Tx/Rx for the port */
+	b53_read8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), &reg);
+	reg |= PORT_CTRL_RX_DISABLE | PORT_CTRL_TX_DISABLE;
+	b53_write8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), reg);
+}
+
+static void b53_enable_cpu_port(struct b53_device *dev)
+{
+	unsigned int cpu_port = dev->cpu_port;
+	u8 port_ctrl;
+
+	/* BCM5325 CPU port is at 8 */
+	if ((is5325(dev) || is5365(dev)) && cpu_port == B53_CPU_PORT_25)
+		cpu_port = B53_CPU_PORT;
+
+	port_ctrl = PORT_CTRL_RX_BCST_EN |
+		    PORT_CTRL_RX_MCST_EN |
+		    PORT_CTRL_RX_UCST_EN;
+	b53_write8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(cpu_port), port_ctrl);
+}
+
+static void b53_enable_mib(struct b53_device *dev)
+{
+	u8 gc;
+
+	b53_read8(dev, B53_MGMT_PAGE, B53_GLOBAL_CONFIG, &gc);
+	gc &= ~(GC_RESET_MIB | GC_MIB_AC_EN);
+	b53_write8(dev, B53_MGMT_PAGE, B53_GLOBAL_CONFIG, gc);
+}
+
+static int b53_configure_vlan(struct b53_device *dev)
+{
+	struct b53_vlan vl = { 0 };
+	int i;
+
+	/* clear all vlan entries */
+	if (is5325(dev) || is5365(dev)) {
+		for (i = 1; i < dev->num_vlans; i++)
+			b53_set_vlan_entry(dev, i, &vl);
+	} else {
+		b53_do_vlan_op(dev, VTA_CMD_CLEAR);
+	}
+
+	b53_enable_vlan(dev, false);
+
+	b53_for_each_port(dev, i)
+		b53_write16(dev, B53_VLAN_PAGE,
+			    B53_VLAN_PORT_DEF_TAG(i), 1);
+
+	if (!is5325(dev) && !is5365(dev))
+		b53_set_jumbo(dev, dev->enable_jumbo, false);
+
+	return 0;
+}
+
+static void b53_switch_reset_gpio(struct b53_device *dev)
+{
+	int gpio = dev->reset_gpio;
+
+	if (gpio < 0)
+		return;
+
+	/* Reset sequence: RESET low(50ms)->high(20ms)
+	 */
+	gpio_set_value(gpio, 0);
+	mdelay(50);
+
+	gpio_set_value(gpio, 1);
+	mdelay(20);
+
+	dev->current_page = 0xff;
+}
+
+static int b53_switch_reset(struct b53_device *dev)
+{
+	u8 mgmt;
+
+	b53_switch_reset_gpio(dev);
+
+	if (is539x(dev)) {
+		b53_write8(dev, B53_CTRL_PAGE, B53_SOFTRESET, 0x83);
+		b53_write8(dev, B53_CTRL_PAGE, B53_SOFTRESET, 0x00);
+	}
+
+	b53_read8(dev, B53_CTRL_PAGE, B53_SWITCH_MODE, &mgmt);
+
+	if (!(mgmt & SM_SW_FWD_EN)) {
+		mgmt &= ~SM_SW_FWD_MODE;
+		mgmt |= SM_SW_FWD_EN;
+
+		b53_write8(dev, B53_CTRL_PAGE, B53_SWITCH_MODE, mgmt);
+		b53_read8(dev, B53_CTRL_PAGE, B53_SWITCH_MODE, &mgmt);
+
+		if (!(mgmt & SM_SW_FWD_EN)) {
+			dev_err(dev->dev, "Failed to enable switch!\n");
+			return -EINVAL;
+		}
+	}
+
+	b53_enable_mib(dev);
+
+	return b53_flush_arl(dev, FAST_AGE_STATIC);
+}
+
+static int b53_phy_read16(struct dsa_switch *ds, int addr, int reg)
+{
+	struct b53_device *priv = ds_to_priv(ds);
+	u16 value = 0;
+	int ret;
+
+	if (priv->ops->phy_read16)
+		ret = priv->ops->phy_read16(priv, addr, reg, &value);
+	else
+		ret = b53_read16(priv, B53_PORT_MII_PAGE(addr),
+				 reg * 2, &value);
+
+	return ret ? ret : value;
+}
+
+static int b53_phy_write16(struct dsa_switch *ds, int addr, int reg, u16 val)
+{
+	struct b53_device *priv = ds_to_priv(ds);
+
+	if (priv->ops->phy_write16)
+		return priv->ops->phy_write16(priv, addr, reg, val);
+
+	return b53_write16(priv, B53_PORT_MII_PAGE(addr), reg * 2, val);
+}
+
+static int b53_reset_switch(struct b53_device *priv)
+{
+	/* reset vlans */
+	priv->enable_jumbo = false;
+
+	memset(priv->vlans, 0, sizeof(*priv->vlans) * priv->num_vlans);
+	memset(priv->ports, 0, sizeof(*priv->ports) * priv->num_ports);
+
+	return b53_switch_reset(priv);
+}
+
+static int b53_apply_config(struct b53_device *priv)
+{
+	/* disable switching */
+	b53_set_forwarding(priv, 0);
+
+	b53_configure_vlan(priv);
+
+	/* enable switching */
+	b53_set_forwarding(priv, 1);
+
+	return 0;
+}
+
+static void b53_reset_mib(struct b53_device *priv)
+{
+	u8 gc;
+
+	b53_read8(priv, B53_MGMT_PAGE, B53_GLOBAL_CONFIG, &gc);
+
+	b53_write8(priv, B53_MGMT_PAGE, B53_GLOBAL_CONFIG, gc | GC_RESET_MIB);
+	msleep(1);
+	b53_write8(priv, B53_MGMT_PAGE, B53_GLOBAL_CONFIG, gc & ~GC_RESET_MIB);
+	msleep(1);
+}
+
+static const struct b53_mib_desc *b53_get_mib(struct b53_device *dev)
+{
+	if (is5365(dev))
+		return b53_mibs_65;
+	else if (is63xx(dev))
+		return b53_mibs_63xx;
+	else
+		return b53_mibs;
+}
+
+static unsigned int b53_get_mib_size(struct b53_device *dev)
+{
+	if (is5365(dev))
+		return B53_MIBS_65_SIZE;
+	else if (is63xx(dev))
+		return B53_MIBS_63XX_SIZE;
+	else
+		return B53_MIBS_SIZE;
+}
+
+static void b53_get_strings(struct dsa_switch *ds, int port, uint8_t *data)
+{
+	struct b53_device *dev = ds_to_priv(ds);
+	const struct b53_mib_desc *mibs = b53_get_mib(dev);
+	unsigned int mib_size = b53_get_mib_size(dev);
+	unsigned int i;
+
+	for (i = 0; i < mib_size; i++)
+		memcpy(data + i * ETH_GSTRING_LEN,
+		       mibs[i].name, ETH_GSTRING_LEN);
+}
+
+static void b53_get_ethtool_stats(struct dsa_switch *ds, int port,
+				  uint64_t *data)
+{
+	struct b53_device *dev = ds_to_priv(ds);
+	const struct b53_mib_desc *mibs = b53_get_mib(dev);
+	unsigned int mib_size = b53_get_mib_size(dev);
+	const struct b53_mib_desc *s;
+	unsigned int i;
+	u64 val = 0;
+
+	if (is5365(dev) && port == 5)
+		port = 8;
+
+	mutex_lock(&dev->stats_mutex);
+
+	for (i = 0; i < mib_size; i++) {
+		s = &mibs[i];
+
+		if (s->size == 8) {
+			b53_read64(dev, B53_MIB_PAGE(port), s->offset, &val);
+		} else {
+			u32 val32;
+
+			b53_read32(dev, B53_MIB_PAGE(port), s->offset,
+				   &val32);
+			val = val32;
+		}
+		data[i] = (u64)val;
+	}
+
+	mutex_unlock(&dev->stats_mutex);
+}
+
+static int b53_get_sset_count(struct dsa_switch *ds)
+{
+	struct b53_device *dev = ds_to_priv(ds);
+
+	return b53_get_mib_size(dev);
+}
+
+static int b53_set_addr(struct dsa_switch *ds, u8 *addr)
+{
+	return 0;
+}
+
+static int b53_setup(struct dsa_switch *ds)
+{
+	struct b53_device *dev = ds_to_priv(ds);
+	unsigned int port;
+	int ret;
+
+	ret = b53_reset_switch(dev);
+	if (ret) {
+		dev_err(ds->dev, "failed to reset switch\n");
+		return ret;
+	}
+
+	b53_reset_mib(dev);
+
+	ret = b53_apply_config(dev);
+	if (ret)
+		dev_err(ds->dev, "failed to apply configuration\n");
+
+	for (port = 0; port < dev->num_ports; port++) {
+		if (BIT(port) & ds->enabled_port_mask)
+			b53_enable_port(ds, port, NULL);
+		else if (dsa_is_cpu_port(ds, port))
+			b53_enable_cpu_port(dev);
+		else
+			b53_disable_port(ds, port, NULL);
+	}
+
+	return ret;
+}
+
+static void b53_adjust_link(struct dsa_switch *ds, int port,
+			    struct phy_device *phydev)
+{
+	struct b53_device *dev = ds_to_priv(ds);
+	u8 rgmii_ctrl = 0, reg = 0, off;
+
+	if (!phy_is_pseudo_fixed_link(phydev))
+		return;
+
+	/* Override the port settings */
+	if (port == dev->cpu_port) {
+		off = B53_PORT_OVERRIDE_CTRL;
+		reg = PORT_OVERRIDE_EN;
+	} else {
+		off = B53_GMII_PORT_OVERRIDE_CTRL(port);
+		reg = GMII_PO_EN;
+	}
+
+	/* Set the link UP */
+	if (phydev->link)
+		reg |= PORT_OVERRIDE_LINK;
+
+	if (phydev->duplex == DUPLEX_FULL)
+		reg |= PORT_OVERRIDE_FULL_DUPLEX;
+
+	switch (phydev->speed) {
+	case 2000:
+		reg |= PORT_OVERRIDE_SPEED_2000M;
+		/* fallthrough */
+	case SPEED_1000:
+		reg |= PORT_OVERRIDE_SPEED_1000M;
+		break;
+	case SPEED_100:
+		reg |= PORT_OVERRIDE_SPEED_100M;
+		break;
+	case SPEED_10:
+		reg |= PORT_OVERRIDE_SPEED_10M;
+		break;
+	default:
+		dev_err(ds->dev, "unknown speed: %d\n", phydev->speed);
+		return;
+	}
+
+	/* Enable flow control on BCM5301x's CPU port */
+	if (is5301x(dev) && port == dev->cpu_port)
+		reg |= PORT_OVERRIDE_RX_FLOW | PORT_OVERRIDE_TX_FLOW;
+
+	if (phydev->pause) {
+		if (phydev->asym_pause)
+			reg |= PORT_OVERRIDE_TX_FLOW;
+		reg |= PORT_OVERRIDE_RX_FLOW;
+	}
+
+	b53_write8(dev, B53_CTRL_PAGE, off, reg);
+
+	if (is531x5(dev) && phy_interface_is_rgmii(phydev)) {
+		if (port == 8)
+			off = B53_RGMII_CTRL_IMP;
+		else
+			off = B53_RGMII_CTRL_P(port);
+
+		/* Configure the port RGMII clock delay by DLL disabled and
+		 * tx_clk aligned timing (restoring to reset defaults)
+		 */
+		b53_read8(dev, B53_CTRL_PAGE, off, &rgmii_ctrl);
+		rgmii_ctrl &= ~(RGMII_CTRL_DLL_RXC | RGMII_CTRL_DLL_TXC |
+				RGMII_CTRL_TIMING_SEL);
+
+		/* PHY_INTERFACE_MODE_RGMII_TXID means TX internal delay, make
+		 * sure that we enable the port TX clock internal delay to
+		 * account for this internal delay that is inserted, otherwise
+		 * the switch won't be able to receive correctly.
+		 *
+		 * PHY_INTERFACE_MODE_RGMII means that we are not introducing
+		 * any delay neither on transmission nor reception, so the
+		 * BCM53125 must also be configured accordingly to account for
+		 * the lack of delay and introduce
+		 *
+		 * The BCM53125 switch has its RX clock and TX clock control
+		 * swapped, hence the reason why we modify the TX clock path in
+		 * the "RGMII" case
+		 */
+		if (phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID)
+			rgmii_ctrl |= RGMII_CTRL_DLL_TXC;
+		if (phydev->interface == PHY_INTERFACE_MODE_RGMII)
+			rgmii_ctrl |= RGMII_CTRL_DLL_TXC | RGMII_CTRL_DLL_RXC;
+		rgmii_ctrl |= RGMII_CTRL_TIMING_SEL;
+		b53_write8(dev, B53_CTRL_PAGE, off, rgmii_ctrl);
+
+		dev_info(ds->dev, "Configured port %d for %s\n", port,
+			 phy_modes(phydev->interface));
+	}
+
+	/* configure MII port if necessary */
+	if (is5325(dev)) {
+		b53_read8(dev, B53_CTRL_PAGE, B53_PORT_OVERRIDE_CTRL,
+			  &reg);
+
+		/* reverse mii needs to be enabled */
+		if (!(reg & PORT_OVERRIDE_RV_MII_25)) {
+			b53_write8(dev, B53_CTRL_PAGE, B53_PORT_OVERRIDE_CTRL,
+				   reg | PORT_OVERRIDE_RV_MII_25);
+			b53_read8(dev, B53_CTRL_PAGE, B53_PORT_OVERRIDE_CTRL,
+				  &reg);
+
+			if (!(reg & PORT_OVERRIDE_RV_MII_25)) {
+				dev_err(ds->dev,
+					"Failed to enable reverse MII mode\n");
+				return;
+			}
+		}
+	} else if (is5301x(dev)) {
+		if (port != dev->cpu_port) {
+			u8 po_reg = B53_GMII_PORT_OVERRIDE_CTRL(dev->cpu_port);
+			u8 gmii_po;
+
+			b53_read8(dev, B53_CTRL_PAGE, po_reg, &gmii_po);
+			gmii_po |= GMII_PO_LINK |
+				   GMII_PO_RX_FLOW |
+				   GMII_PO_TX_FLOW |
+				   GMII_PO_EN |
+				   GMII_PO_SPEED_2000M;
+			b53_write8(dev, B53_CTRL_PAGE, po_reg, gmii_po);
+		}
+	}
+}
+
+static int b53_vlan_filtering(struct dsa_switch *ds, int port,
+			      bool vlan_filtering)
+{
+	return 0;
+}
+
+static int b53_vlan_prepare(struct dsa_switch *ds, int port,
+			    const struct switchdev_obj_port_vlan *vlan,
+			    struct switchdev_trans *trans)
+{
+	struct b53_device *dev = ds_to_priv(ds);
+
+	if ((is5325(dev) || is5365(dev)) && vlan->vid_begin == 0)
+		return -EOPNOTSUPP;
+
+	if (vlan->vid_end > dev->num_vlans)
+		return -ERANGE;
+
+	b53_enable_vlan(dev, true);
+
+	return 0;
+}
+
+static void b53_vlan_add(struct dsa_switch *ds, int port,
+			 const struct switchdev_obj_port_vlan *vlan,
+			 struct switchdev_trans *trans)
+{
+	struct b53_device *dev = ds_to_priv(ds);
+	bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
+	bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
+	unsigned int cpu_port = dev->cpu_port;
+	struct b53_vlan *vl;
+	u16 vid;
+
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) {
+		vl = &dev->vlans[vid];
+
+		b53_get_vlan_entry(dev, vid, vl);
+
+		vl->members |= BIT(port) | BIT(cpu_port);
+		if (untagged)
+			vl->untag |= BIT(port) | BIT(cpu_port);
+		else
+			vl->untag &= ~(BIT(port) | BIT(cpu_port));
+
+		b53_set_vlan_entry(dev, vid, vl);
+		b53_fast_age_vlan(dev, vid);
+	}
+
+	if (pvid) {
+		b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port),
+			    vlan->vid_end);
+		b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(cpu_port),
+			    vlan->vid_end);
+		b53_fast_age_vlan(dev, vid);
+	}
+}
+
+static int b53_vlan_del(struct dsa_switch *ds, int port,
+			const struct switchdev_obj_port_vlan *vlan)
+{
+	struct b53_device *dev = ds_to_priv(ds);
+	bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
+	unsigned int cpu_port = dev->cpu_port;
+	struct b53_vlan *vl;
+	u16 vid;
+	u16 pvid;
+
+	b53_read16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port), &pvid);
+
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) {
+		vl = &dev->vlans[vid];
+
+		b53_get_vlan_entry(dev, vid, vl);
+
+		vl->members &= ~BIT(port);
+		if ((vl->members & BIT(cpu_port)) == BIT(cpu_port))
+			vl->members = 0;
+
+		if (pvid == vid) {
+			if (is5325(dev) || is5365(dev))
+				pvid = 1;
+			else
+				pvid = 0;
+		}
+
+		if (untagged) {
+			vl->untag &= ~(BIT(port));
+			if ((vl->untag & BIT(cpu_port)) == BIT(cpu_port))
+				vl->untag = 0;
+		}
+
+		b53_set_vlan_entry(dev, vid, vl);
+		b53_fast_age_vlan(dev, vid);
+	}
+
+	b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port), pvid);
+	b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(cpu_port), pvid);
+	b53_fast_age_vlan(dev, pvid);
+
+	return 0;
+}
+
+static int b53_vlan_dump(struct dsa_switch *ds, int port,
+			 struct switchdev_obj_port_vlan *vlan,
+			 int (*cb)(struct switchdev_obj *obj))
+{
+	struct b53_device *dev = ds_to_priv(ds);
+	u16 vid, vid_start = 0, pvid;
+	struct b53_vlan *vl;
+	int err = 0;
+
+	if (is5325(dev) || is5365(dev))
+		vid_start = 1;
+
+	b53_read16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port), &pvid);
+
+	/* Use our software cache for dumps, since we do not have any HW
+	 * operation returning only the used/valid VLANs
+	 */
+	for (vid = vid_start; vid < dev->num_vlans; vid++) {
+		vl = &dev->vlans[vid];
+
+		if (!vl->valid)
+			continue;
+
+		if (!(vl->members & BIT(port)))
+			continue;
+
+		vlan->vid_begin = vlan->vid_end = vid;
+		vlan->flags = 0;
+
+		if (vl->untag & BIT(port))
+			vlan->flags |= BRIDGE_VLAN_INFO_UNTAGGED;
+		if (pvid == vid)
+			vlan->flags |= BRIDGE_VLAN_INFO_PVID;
+
+		err = cb(&vlan->obj);
+		if (err)
+			break;
+	}
+
+	return err;
+}
+
+/* Address Resolution Logic routines */
+static int b53_arl_op_wait(struct b53_device *dev)
+{
+	unsigned int timeout = 10;
+	u8 reg;
+
+	do {
+		b53_read8(dev, B53_ARLIO_PAGE, B53_ARLTBL_RW_CTRL, &reg);
+		if (!(reg & ARLTBL_START_DONE))
+			return 0;
+
+		usleep_range(1000, 2000);
+	} while (timeout--);
+
+	dev_warn(dev->dev, "timeout waiting for ARL to finish: 0x%02x\n", reg);
+
+	return -ETIMEDOUT;
+}
+
+static int b53_arl_rw_op(struct b53_device *dev, unsigned int op)
+{
+	u8 reg;
+
+	if (op > ARLTBL_RW)
+		return -EINVAL;
+
+	b53_read8(dev, B53_ARLIO_PAGE, B53_ARLTBL_RW_CTRL, &reg);
+	reg |= ARLTBL_START_DONE;
+	if (op)
+		reg |= ARLTBL_RW;
+	else
+		reg &= ~ARLTBL_RW;
+	b53_write8(dev, B53_ARLIO_PAGE, B53_ARLTBL_RW_CTRL, reg);
+
+	return b53_arl_op_wait(dev);
+}
+
+static int b53_arl_read(struct b53_device *dev, u64 mac,
+			u16 vid, struct b53_arl_entry *ent, u8 *idx,
+			bool is_valid)
+{
+	unsigned int i;
+	int ret;
+
+	ret = b53_arl_op_wait(dev);
+	if (ret)
+		return ret;
+
+	/* Read the bins */
+	for (i = 0; i < dev->num_arl_entries; i++) {
+		u64 mac_vid;
+		u32 fwd_entry;
+
+		b53_read64(dev, B53_ARLIO_PAGE,
+			   B53_ARLTBL_MAC_VID_ENTRY(i), &mac_vid);
+		b53_read32(dev, B53_ARLIO_PAGE,
+			   B53_ARLTBL_DATA_ENTRY(i), &fwd_entry);
+		b53_arl_to_entry(ent, mac_vid, fwd_entry);
+
+		if (!(fwd_entry & ARLTBL_VALID))
+			continue;
+		if ((mac_vid & ARLTBL_MAC_MASK) != mac)
+			continue;
+		*idx = i;
+	}
+
+	return -ENOENT;
+}
+
+static int b53_arl_op(struct b53_device *dev, int op, int port,
+		      const unsigned char *addr, u16 vid, bool is_valid)
+{
+	struct b53_arl_entry ent;
+	u32 fwd_entry;
+	u64 mac, mac_vid = 0;
+	u8 idx = 0;
+	int ret;
+
+	/* Convert the array into a 64-bit MAC */
+	mac = b53_mac_to_u64(addr);
+
+	/* Perform a read for the given MAC and VID */
+	b53_write48(dev, B53_ARLIO_PAGE, B53_MAC_ADDR_IDX, mac);
+	b53_write16(dev, B53_ARLIO_PAGE, B53_VLAN_ID_IDX, vid);
+
+	/* Issue a read operation for this MAC */
+	ret = b53_arl_rw_op(dev, 1);
+	if (ret)
+		return ret;
+
+	ret = b53_arl_read(dev, mac, vid, &ent, &idx, is_valid);
+	/* If this is a read, just finish now */
+	if (op)
+		return ret;
+
+	/* We could not find a matching MAC, so reset to a new entry */
+	if (ret) {
+		fwd_entry = 0;
+		idx = 1;
+	}
+
+	memset(&ent, 0, sizeof(ent));
+	ent.port = port;
+	ent.is_valid = is_valid;
+	ent.vid = vid;
+	ent.is_static = true;
+	memcpy(ent.mac, addr, ETH_ALEN);
+	b53_arl_from_entry(&mac_vid, &fwd_entry, &ent);
+
+	b53_write64(dev, B53_ARLIO_PAGE,
+		    B53_ARLTBL_MAC_VID_ENTRY(idx), mac_vid);
+	b53_write32(dev, B53_ARLIO_PAGE,
+		    B53_ARLTBL_DATA_ENTRY(idx), fwd_entry);
+
+	return b53_arl_rw_op(dev, 0);
+}
+
+static int b53_fdb_prepare(struct dsa_switch *ds, int port,
+			   const struct switchdev_obj_port_fdb *fdb,
+			   struct switchdev_trans *trans)
+{
+	struct b53_device *priv = ds_to_priv(ds);
+
+	/* 5325 and 5365 require some more massaging, but could
+	 * be supported eventually
+	 */
+	if (is5325(priv) || is5365(priv))
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
+static void b53_fdb_add(struct dsa_switch *ds, int port,
+			const struct switchdev_obj_port_fdb *fdb,
+			struct switchdev_trans *trans)
+{
+	struct b53_device *priv = ds_to_priv(ds);
+
+	if (b53_arl_op(priv, 0, port, fdb->addr, fdb->vid, true))
+		pr_err("%s: failed to add MAC address\n", __func__);
+}
+
+static int b53_fdb_del(struct dsa_switch *ds, int port,
+		       const struct switchdev_obj_port_fdb *fdb)
+{
+	struct b53_device *priv = ds_to_priv(ds);
+
+	return b53_arl_op(priv, 0, port, fdb->addr, fdb->vid, false);
+}
+
+static int b53_arl_search_wait(struct b53_device *dev)
+{
+	unsigned int timeout = 1000;
+	u8 reg;
+
+	do {
+		b53_read8(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_CTL, &reg);
+		if (!(reg & ARL_SRCH_STDN))
+			return 0;
+
+		if (reg & ARL_SRCH_VLID)
+			return 0;
+
+		usleep_range(1000, 2000);
+	} while (timeout--);
+
+	return -ETIMEDOUT;
+}
+
+static void b53_arl_search_rd(struct b53_device *dev, u8 idx,
+			      struct b53_arl_entry *ent)
+{
+	u64 mac_vid;
+	u32 fwd_entry;
+
+	b53_read64(dev, B53_ARLIO_PAGE,
+		   B53_ARL_SRCH_RSTL_MACVID(idx), &mac_vid);
+	b53_read32(dev, B53_ARLIO_PAGE,
+		   B53_ARL_SRCH_RSTL(idx), &fwd_entry);
+	b53_arl_to_entry(ent, mac_vid, fwd_entry);
+}
+
+static int b53_fdb_copy(struct net_device *dev, int port,
+			const struct b53_arl_entry *ent,
+			struct switchdev_obj_port_fdb *fdb,
+			int (*cb)(struct switchdev_obj *obj))
+{
+	if (!ent->is_valid)
+		return 0;
+
+	if (port != ent->port)
+		return 0;
+
+	ether_addr_copy(fdb->addr, ent->mac);
+	fdb->vid = ent->vid;
+	fdb->ndm_state = ent->is_static ? NUD_NOARP : NUD_REACHABLE;
+
+	return cb(&fdb->obj);
+}
+
+static int b53_fdb_dump(struct dsa_switch *ds, int port,
+			struct switchdev_obj_port_fdb *fdb,
+			int (*cb)(struct switchdev_obj *obj))
+{
+	struct b53_device *priv = ds_to_priv(ds);
+	struct net_device *dev = ds->ports[port].netdev;
+	struct b53_arl_entry results[2];
+	unsigned int count = 0;
+	int ret;
+	u8 reg;
+
+	/* Start search operation */
+	reg = ARL_SRCH_STDN;
+	b53_write8(priv, B53_ARLIO_PAGE, B53_ARL_SRCH_CTL, reg);
+
+	do {
+		ret = b53_arl_search_wait(priv);
+		if (ret)
+			return ret;
+
+		b53_arl_search_rd(priv, 0, &results[0]);
+		ret = b53_fdb_copy(dev, port, &results[0], fdb, cb);
+		if (ret)
+			return ret;
+
+		if (priv->num_arl_entries > 2) {
+			b53_arl_search_rd(priv, 1, &results[1]);
+			ret = b53_fdb_copy(dev, port, &results[1], fdb, cb);
+			if (ret)
+				return ret;
+
+			if (!results[0].is_valid && !results[1].is_valid)
+				break;
+		}
+
+	} while (count++ < 1024);
+
+	return 0;
+}
+
+static int b53_br_join(struct dsa_switch *ds, int port,
+		       struct net_device *bridge)
+{
+	struct b53_device *dev = ds_to_priv(ds);
+	u16 pvlan, reg;
+	unsigned int i;
+
+	dev->ports[port].bridge_dev = bridge;
+	b53_read16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(port), &pvlan);
+
+	b53_for_each_port(dev, i) {
+		if (dev->ports[i].bridge_dev != bridge)
+			continue;
+
+		/* Add this local port to the remote port VLAN control
+		 * membership and update the remote port bitmask
+		 */
+		b53_read16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(i), &reg);
+		reg |= BIT(port);
+		b53_write16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(i), reg);
+		dev->ports[i].vlan_ctl_mask = reg;
+
+		pvlan |= BIT(i);
+	}
+
+	/* Configure the local port VLAN control membership to include
+	 * remote ports and update the local port bitmask
+	 */
+	b53_write16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(port), pvlan);
+	dev->ports[port].vlan_ctl_mask = pvlan;
+
+	return 0;
+}
+
+static void b53_br_leave(struct dsa_switch *ds, int port)
+{
+	struct b53_device *dev = ds_to_priv(ds);
+	struct net_device *bridge = dev->ports[port].bridge_dev;
+	struct b53_vlan *vl = &dev->vlans[0];
+	unsigned int i;
+	u16 pvlan, reg, pvid;
+
+	b53_read16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(port), &pvlan);
+
+	b53_for_each_port(dev, i) {
+		/* Don't touch the remaining ports */
+		if (dev->ports[i].bridge_dev != bridge)
+			continue;
+
+		b53_read16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(i), &reg);
+		reg &= ~BIT(port);
+		b53_write16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(i), reg);
+		dev->ports[port].vlan_ctl_mask = reg;
+
+		/* Prevent self removal to preserve isolation */
+		if (port != i)
+			pvlan &= ~BIT(i);
+	}
+
+	b53_write16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(port), pvlan);
+	dev->ports[port].vlan_ctl_mask = pvlan;
+	dev->ports[port].bridge_dev = NULL;
+
+	if (is5325(dev) || is5365(dev))
+		pvid = 1;
+	else
+		pvid = 0;
+
+	b53_get_vlan_entry(dev, pvid, vl);
+	vl->members |= BIT(port) | BIT(dev->cpu_port);
+	vl->untag |= BIT(port) | BIT(dev->cpu_port);
+	b53_set_vlan_entry(dev, pvid, vl);
+}
+
+static void b53_br_set_stp_state(struct dsa_switch *ds, int port,
+				 u8 state)
+{
+	struct b53_device *dev = ds_to_priv(ds);
+	u8 hw_state, cur_hw_state;
+	u8 reg;
+
+	b53_read8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), &reg);
+	cur_hw_state = reg & PORT_CTRL_STP_STATE_MASK;
+
+	switch (state) {
+	case BR_STATE_DISABLED:
+		hw_state = PORT_CTRL_DIS_STATE;
+		break;
+	case BR_STATE_LISTENING:
+		hw_state = PORT_CTRL_LISTEN_STATE;
+		break;
+	case BR_STATE_LEARNING:
+		hw_state = PORT_CTRL_LEARN_STATE;
+		break;
+	case BR_STATE_FORWARDING:
+		hw_state = PORT_CTRL_FWD_STATE;
+		break;
+	case BR_STATE_BLOCKING:
+		hw_state = PORT_CTRL_BLOCK_STATE;
+		break;
+	default:
+		dev_err(ds->dev, "invalid STP state: %d\n", state);
+		return;
+	}
+
+	/* Fast-age ARL entries if we are moving a port from Learning or
+	 * Forwarding (cur_hw_state) state to Disabled, Blocking or Listening
+	 * state (hw_state)
+	 */
+	if (cur_hw_state != hw_state) {
+		if (cur_hw_state >= PORT_CTRL_LEARN_STATE &&
+		    hw_state <= PORT_CTRL_LISTEN_STATE) {
+			if (b53_fast_age_port(dev, port)) {
+				dev_err(ds->dev, "fast ageing failed\n");
+				return;
+			}
+		}
+	}
+
+	b53_read8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), &reg);
+	reg &= ~PORT_CTRL_STP_STATE_MASK;
+	reg |= hw_state;
+	b53_write8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), reg);
+}
+
+static struct dsa_switch_driver b53_switch_ops = {
+	.tag_protocol		= DSA_TAG_PROTO_NONE,
+	.setup			= b53_setup,
+	.set_addr		= b53_set_addr,
+	.get_strings		= b53_get_strings,
+	.get_ethtool_stats	= b53_get_ethtool_stats,
+	.get_sset_count		= b53_get_sset_count,
+	.phy_read		= b53_phy_read16,
+	.phy_write		= b53_phy_write16,
+	.adjust_link		= b53_adjust_link,
+	.port_enable		= b53_enable_port,
+	.port_disable		= b53_disable_port,
+	.port_bridge_join	= b53_br_join,
+	.port_bridge_leave	= b53_br_leave,
+	.port_stp_state_set	= b53_br_set_stp_state,
+	.port_vlan_filtering	= b53_vlan_filtering,
+	.port_vlan_prepare	= b53_vlan_prepare,
+	.port_vlan_add		= b53_vlan_add,
+	.port_vlan_del		= b53_vlan_del,
+	.port_vlan_dump		= b53_vlan_dump,
+	.port_fdb_prepare	= b53_fdb_prepare,
+	.port_fdb_dump		= b53_fdb_dump,
+	.port_fdb_add		= b53_fdb_add,
+	.port_fdb_del		= b53_fdb_del,
+};
+
+struct b53_chip_data {
+	u32 chip_id;
+	const char *dev_name;
+	u16 vlans;
+	u16 enabled_ports;
+	u8 cpu_port;
+	u8 vta_regs[3];
+	u8 arl_entries;
+	u8 duplex_reg;
+	u8 jumbo_pm_reg;
+	u8 jumbo_size_reg;
+};
+
+#define B53_VTA_REGS	\
+	{ B53_VT_ACCESS, B53_VT_INDEX, B53_VT_ENTRY }
+#define B53_VTA_REGS_9798 \
+	{ B53_VT_ACCESS_9798, B53_VT_INDEX_9798, B53_VT_ENTRY_9798 }
+#define B53_VTA_REGS_63XX \
+	{ B53_VT_ACCESS_63XX, B53_VT_INDEX_63XX, B53_VT_ENTRY_63XX }
+
+static const struct b53_chip_data b53_switch_chips[] = {
+	{
+		.chip_id = BCM5325_DEVICE_ID,
+		.dev_name = "BCM5325",
+		.vlans = 16,
+		.enabled_ports = 0x1f,
+		.arl_entries = 2,
+		.cpu_port = B53_CPU_PORT_25,
+		.duplex_reg = B53_DUPLEX_STAT_FE,
+	},
+	{
+		.chip_id = BCM5365_DEVICE_ID,
+		.dev_name = "BCM5365",
+		.vlans = 256,
+		.enabled_ports = 0x1f,
+		.arl_entries = 2,
+		.cpu_port = B53_CPU_PORT_25,
+		.duplex_reg = B53_DUPLEX_STAT_FE,
+	},
+	{
+		.chip_id = BCM5395_DEVICE_ID,
+		.dev_name = "BCM5395",
+		.vlans = 4096,
+		.enabled_ports = 0x1f,
+		.arl_entries = 4,
+		.cpu_port = B53_CPU_PORT,
+		.vta_regs = B53_VTA_REGS,
+		.duplex_reg = B53_DUPLEX_STAT_GE,
+		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
+		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+	},
+	{
+		.chip_id = BCM5397_DEVICE_ID,
+		.dev_name = "BCM5397",
+		.vlans = 4096,
+		.enabled_ports = 0x1f,
+		.arl_entries = 4,
+		.cpu_port = B53_CPU_PORT,
+		.vta_regs = B53_VTA_REGS_9798,
+		.duplex_reg = B53_DUPLEX_STAT_GE,
+		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
+		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+	},
+	{
+		.chip_id = BCM5398_DEVICE_ID,
+		.dev_name = "BCM5398",
+		.vlans = 4096,
+		.enabled_ports = 0x7f,
+		.arl_entries = 4,
+		.cpu_port = B53_CPU_PORT,
+		.vta_regs = B53_VTA_REGS_9798,
+		.duplex_reg = B53_DUPLEX_STAT_GE,
+		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
+		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+	},
+	{
+		.chip_id = BCM53115_DEVICE_ID,
+		.dev_name = "BCM53115",
+		.vlans = 4096,
+		.enabled_ports = 0x1f,
+		.arl_entries = 4,
+		.vta_regs = B53_VTA_REGS,
+		.cpu_port = B53_CPU_PORT,
+		.duplex_reg = B53_DUPLEX_STAT_GE,
+		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
+		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+	},
+	{
+		.chip_id = BCM53125_DEVICE_ID,
+		.dev_name = "BCM53125",
+		.vlans = 4096,
+		.enabled_ports = 0xff,
+		.cpu_port = B53_CPU_PORT,
+		.vta_regs = B53_VTA_REGS,
+		.duplex_reg = B53_DUPLEX_STAT_GE,
+		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
+		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+	},
+	{
+		.chip_id = BCM53128_DEVICE_ID,
+		.dev_name = "BCM53128",
+		.vlans = 4096,
+		.enabled_ports = 0x1ff,
+		.arl_entries = 4,
+		.cpu_port = B53_CPU_PORT,
+		.vta_regs = B53_VTA_REGS,
+		.duplex_reg = B53_DUPLEX_STAT_GE,
+		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
+		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+	},
+	{
+		.chip_id = BCM63XX_DEVICE_ID,
+		.dev_name = "BCM63xx",
+		.vlans = 4096,
+		.enabled_ports = 0, /* pdata must provide them */
+		.arl_entries = 4,
+		.cpu_port = B53_CPU_PORT,
+		.vta_regs = B53_VTA_REGS_63XX,
+		.duplex_reg = B53_DUPLEX_STAT_63XX,
+		.jumbo_pm_reg = B53_JUMBO_PORT_MASK_63XX,
+		.jumbo_size_reg = B53_JUMBO_MAX_SIZE_63XX,
+	},
+	{
+		.chip_id = BCM53010_DEVICE_ID,
+		.dev_name = "BCM53010",
+		.vlans = 4096,
+		.enabled_ports = 0x1f,
+		.arl_entries = 4,
+		.cpu_port = B53_CPU_PORT_25, /* TODO: auto detect */
+		.vta_regs = B53_VTA_REGS,
+		.duplex_reg = B53_DUPLEX_STAT_GE,
+		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
+		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+	},
+	{
+		.chip_id = BCM53011_DEVICE_ID,
+		.dev_name = "BCM53011",
+		.vlans = 4096,
+		.enabled_ports = 0x1bf,
+		.arl_entries = 4,
+		.cpu_port = B53_CPU_PORT_25, /* TODO: auto detect */
+		.vta_regs = B53_VTA_REGS,
+		.duplex_reg = B53_DUPLEX_STAT_GE,
+		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
+		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+	},
+	{
+		.chip_id = BCM53012_DEVICE_ID,
+		.dev_name = "BCM53012",
+		.vlans = 4096,
+		.enabled_ports = 0x1bf,
+		.arl_entries = 4,
+		.cpu_port = B53_CPU_PORT_25, /* TODO: auto detect */
+		.vta_regs = B53_VTA_REGS,
+		.duplex_reg = B53_DUPLEX_STAT_GE,
+		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
+		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+	},
+	{
+		.chip_id = BCM53018_DEVICE_ID,
+		.dev_name = "BCM53018",
+		.vlans = 4096,
+		.enabled_ports = 0x1f,
+		.arl_entries = 4,
+		.cpu_port = B53_CPU_PORT_25, /* TODO: auto detect */
+		.vta_regs = B53_VTA_REGS,
+		.duplex_reg = B53_DUPLEX_STAT_GE,
+		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
+		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+	},
+	{
+		.chip_id = BCM53019_DEVICE_ID,
+		.dev_name = "BCM53019",
+		.vlans = 4096,
+		.enabled_ports = 0x1f,
+		.arl_entries = 4,
+		.cpu_port = B53_CPU_PORT_25, /* TODO: auto detect */
+		.vta_regs = B53_VTA_REGS,
+		.duplex_reg = B53_DUPLEX_STAT_GE,
+		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
+		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+	},
+};
+
+static int b53_switch_init(struct b53_device *dev)
+{
+	struct dsa_switch *ds = dev->ds;
+	unsigned int i;
+	int ret;
+
+	for (i = 0; i < ARRAY_SIZE(b53_switch_chips); i++) {
+		const struct b53_chip_data *chip = &b53_switch_chips[i];
+
+		if (chip->chip_id == dev->chip_id) {
+			if (!dev->enabled_ports)
+				dev->enabled_ports = chip->enabled_ports;
+			dev->name = chip->dev_name;
+			dev->duplex_reg = chip->duplex_reg;
+			dev->vta_regs[0] = chip->vta_regs[0];
+			dev->vta_regs[1] = chip->vta_regs[1];
+			dev->vta_regs[2] = chip->vta_regs[2];
+			dev->jumbo_pm_reg = chip->jumbo_pm_reg;
+			ds->drv = &b53_switch_ops;
+			dev->cpu_port = chip->cpu_port;
+			dev->num_vlans = chip->vlans;
+			dev->num_arl_entries = chip->arl_entries;
+			break;
+		}
+	}
+
+	/* check which BCM5325x version we have */
+	if (is5325(dev)) {
+		u8 vc4;
+
+		b53_read8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL4_25, &vc4);
+
+		/* check reserved bits */
+		switch (vc4 & 3) {
+		case 1:
+			/* BCM5325E */
+			break;
+		case 3:
+			/* BCM5325F - do not use port 4 */
+			dev->enabled_ports &= ~BIT(4);
+			break;
+		default:
+/* On the BCM47XX SoCs this is the supported internal switch.*/
+#ifndef CONFIG_BCM47XX
+			/* BCM5325M */
+			return -EINVAL;
+#else
+			break;
+#endif
+		}
+	} else if (dev->chip_id == BCM53115_DEVICE_ID) {
+		u64 strap_value;
+
+		b53_read48(dev, B53_STAT_PAGE, B53_STRAP_VALUE, &strap_value);
+		/* use second IMP port if GMII is enabled */
+		if (strap_value & SV_GMII_CTRL_115)
+			dev->cpu_port = 5;
+	}
+
+	/* cpu port is always last */
+	dev->num_ports = dev->cpu_port + 1;
+	dev->enabled_ports |= BIT(dev->cpu_port);
+
+	dev->ports = devm_kzalloc(dev->dev,
+				  sizeof(struct b53_port) * dev->num_ports,
+				  GFP_KERNEL);
+	if (!dev->ports)
+		return -ENOMEM;
+
+	dev->vlans = devm_kzalloc(dev->dev,
+				  sizeof(struct b53_vlan) * dev->num_vlans,
+				  GFP_KERNEL);
+	if (!dev->vlans)
+		return -ENOMEM;
+
+	dev->reset_gpio = b53_switch_get_reset_gpio(dev);
+	if (dev->reset_gpio >= 0) {
+		ret = devm_gpio_request_one(dev->dev, dev->reset_gpio,
+					    GPIOF_OUT_INIT_HIGH, "robo_reset");
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+struct b53_device *b53_switch_alloc(struct device *base, struct b53_io_ops *ops,
+				    void *priv)
+{
+	struct dsa_switch *ds;
+	struct b53_device *dev;
+
+	ds = devm_kzalloc(base, sizeof(*ds) + sizeof(*dev), GFP_KERNEL);
+	if (!ds)
+		return NULL;
+
+	dev = (struct b53_device *)(ds + 1);
+
+	ds->priv = dev;
+	ds->dev = base;
+	dev->dev = base;
+
+	dev->ds = ds;
+	dev->priv = priv;
+	dev->ops = ops;
+	mutex_init(&dev->reg_mutex);
+	mutex_init(&dev->stats_mutex);
+
+	return dev;
+}
+EXPORT_SYMBOL(b53_switch_alloc);
+
+int b53_switch_detect(struct b53_device *dev)
+{
+	u32 id32;
+	u16 tmp;
+	u8 id8;
+	int ret;
+
+	ret = b53_read8(dev, B53_MGMT_PAGE, B53_DEVICE_ID, &id8);
+	if (ret)
+		return ret;
+
+	switch (id8) {
+	case 0:
+		/* BCM5325 and BCM5365 do not have this register so reads
+		 * return 0. But the read operation did succeed, so assume this
+		 * is one of them.
+		 *
+		 * Next check if we can write to the 5325's VTA register; for
+		 * 5365 it is read only.
+		 */
+		b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_TABLE_ACCESS_25, 0xf);
+		b53_read16(dev, B53_VLAN_PAGE, B53_VLAN_TABLE_ACCESS_25, &tmp);
+
+		if (tmp == 0xf)
+			dev->chip_id = BCM5325_DEVICE_ID;
+		else
+			dev->chip_id = BCM5365_DEVICE_ID;
+		break;
+	case BCM5395_DEVICE_ID:
+	case BCM5397_DEVICE_ID:
+	case BCM5398_DEVICE_ID:
+		dev->chip_id = id8;
+		break;
+	default:
+		ret = b53_read32(dev, B53_MGMT_PAGE, B53_DEVICE_ID, &id32);
+		if (ret)
+			return ret;
+
+		switch (id32) {
+		case BCM53115_DEVICE_ID:
+		case BCM53125_DEVICE_ID:
+		case BCM53128_DEVICE_ID:
+		case BCM53010_DEVICE_ID:
+		case BCM53011_DEVICE_ID:
+		case BCM53012_DEVICE_ID:
+		case BCM53018_DEVICE_ID:
+		case BCM53019_DEVICE_ID:
+			dev->chip_id = id32;
+			break;
+		default:
+			pr_err("unsupported switch detected (BCM53%02x/BCM%x)\n",
+			       id8, id32);
+			return -ENODEV;
+		}
+	}
+
+	if (dev->chip_id == BCM5325_DEVICE_ID)
+		return b53_read8(dev, B53_STAT_PAGE, B53_REV_ID_25,
+				 &dev->core_rev);
+	else
+		return b53_read8(dev, B53_MGMT_PAGE, B53_REV_ID,
+				 &dev->core_rev);
+}
+EXPORT_SYMBOL(b53_switch_detect);
+
+int b53_switch_register(struct b53_device *dev)
+{
+	int ret;
+
+	if (dev->pdata) {
+		dev->chip_id = dev->pdata->chip_id;
+		dev->enabled_ports = dev->pdata->enabled_ports;
+	}
+
+	if (!dev->chip_id && b53_switch_detect(dev))
+		return -EINVAL;
+
+	ret = b53_switch_init(dev);
+	if (ret)
+		return ret;
+
+	pr_info("found switch: %s, rev %i\n", dev->name, dev->core_rev);
+
+	return dsa_register_switch(dev->ds, dev->ds->dev->of_node);
+}
+EXPORT_SYMBOL(b53_switch_register);
+
+MODULE_AUTHOR("Jonas Gorski <jogo@openwrt.org>");
+MODULE_DESCRIPTION("B53 switch library");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/dsa/b53/b53_mdio.c b/drivers/net/dsa/b53/b53_mdio.c
new file mode 100644
index 0000000..aa87c3f
--- /dev/null
+++ b/drivers/net/dsa/b53/b53_mdio.c
@@ -0,0 +1,392 @@
+/*
+ * B53 register access through MII registers
+ *
+ * Copyright (C) 2011-2013 Jonas Gorski <jogo@openwrt.org>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/phy.h>
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/brcmphy.h>
+#include <linux/rtnetlink.h>
+#include <net/dsa.h>
+
+#include "b53_priv.h"
+
+/* MII registers */
+#define REG_MII_PAGE    0x10    /* MII Page register */
+#define REG_MII_ADDR    0x11    /* MII Address register */
+#define REG_MII_DATA0   0x18    /* MII Data register 0 */
+#define REG_MII_DATA1   0x19    /* MII Data register 1 */
+#define REG_MII_DATA2   0x1a    /* MII Data register 2 */
+#define REG_MII_DATA3   0x1b    /* MII Data register 3 */
+
+#define REG_MII_PAGE_ENABLE     BIT(0)
+#define REG_MII_ADDR_WRITE      BIT(0)
+#define REG_MII_ADDR_READ       BIT(1)
+
+static int b53_mdio_op(struct b53_device *dev, u8 page, u8 reg, u16 op)
+{
+	int i;
+	u16 v;
+	int ret;
+	struct mii_bus *bus = dev->priv;
+
+	if (dev->current_page != page) {
+		/* set page number */
+		v = (page << 8) | REG_MII_PAGE_ENABLE;
+		ret = mdiobus_write_nested(bus, BRCM_PSEUDO_PHY_ADDR,
+					   REG_MII_PAGE, v);
+		if (ret)
+			return ret;
+		dev->current_page = page;
+	}
+
+	/* set register address */
+	v = (reg << 8) | op;
+	ret = mdiobus_write_nested(bus, BRCM_PSEUDO_PHY_ADDR, REG_MII_ADDR, v);
+	if (ret)
+		return ret;
+
+	/* check if operation completed */
+	for (i = 0; i < 5; ++i) {
+		v = mdiobus_read_nested(bus, BRCM_PSEUDO_PHY_ADDR,
+					REG_MII_ADDR);
+		if (!(v & (REG_MII_ADDR_WRITE | REG_MII_ADDR_READ)))
+			break;
+		usleep_range(10, 100);
+	}
+
+	if (WARN_ON(i == 5))
+		return -EIO;
+
+	return 0;
+}
+
+static int b53_mdio_read8(struct b53_device *dev, u8 page, u8 reg, u8 *val)
+{
+	struct mii_bus *bus = dev->priv;
+	int ret;
+
+	ret = b53_mdio_op(dev, page, reg, REG_MII_ADDR_READ);
+	if (ret)
+		return ret;
+
+	*val = mdiobus_read_nested(bus, BRCM_PSEUDO_PHY_ADDR,
+				   REG_MII_DATA0) & 0xff;
+
+	return 0;
+}
+
+static int b53_mdio_read16(struct b53_device *dev, u8 page, u8 reg, u16 *val)
+{
+	struct mii_bus *bus = dev->priv;
+	int ret;
+
+	ret = b53_mdio_op(dev, page, reg, REG_MII_ADDR_READ);
+	if (ret)
+		return ret;
+
+	*val = mdiobus_read_nested(bus, BRCM_PSEUDO_PHY_ADDR, REG_MII_DATA0);
+
+	return 0;
+}
+
+static int b53_mdio_read32(struct b53_device *dev, u8 page, u8 reg, u32 *val)
+{
+	struct mii_bus *bus = dev->priv;
+	int ret;
+
+	ret = b53_mdio_op(dev, page, reg, REG_MII_ADDR_READ);
+	if (ret)
+		return ret;
+
+	*val = mdiobus_read_nested(bus, BRCM_PSEUDO_PHY_ADDR, REG_MII_DATA0);
+	*val |= mdiobus_read_nested(bus, BRCM_PSEUDO_PHY_ADDR,
+				    REG_MII_DATA1) << 16;
+
+	return 0;
+}
+
+static int b53_mdio_read48(struct b53_device *dev, u8 page, u8 reg, u64 *val)
+{
+	struct mii_bus *bus = dev->priv;
+	u64 temp = 0;
+	int i;
+	int ret;
+
+	ret = b53_mdio_op(dev, page, reg, REG_MII_ADDR_READ);
+	if (ret)
+		return ret;
+
+	for (i = 2; i >= 0; i--) {
+		temp <<= 16;
+		temp |= mdiobus_read_nested(bus, BRCM_PSEUDO_PHY_ADDR,
+				     REG_MII_DATA0 + i);
+	}
+
+	*val = temp;
+
+	return 0;
+}
+
+static int b53_mdio_read64(struct b53_device *dev, u8 page, u8 reg, u64 *val)
+{
+	struct mii_bus *bus = dev->priv;
+	u64 temp = 0;
+	int i;
+	int ret;
+
+	ret = b53_mdio_op(dev, page, reg, REG_MII_ADDR_READ);
+	if (ret)
+		return ret;
+
+	for (i = 3; i >= 0; i--) {
+		temp <<= 16;
+		temp |= mdiobus_read_nested(bus, BRCM_PSEUDO_PHY_ADDR,
+					    REG_MII_DATA0 + i);
+	}
+
+	*val = temp;
+
+	return 0;
+}
+
+static int b53_mdio_write8(struct b53_device *dev, u8 page, u8 reg, u8 value)
+{
+	struct mii_bus *bus = dev->priv;
+	int ret;
+
+	ret = mdiobus_write_nested(bus, BRCM_PSEUDO_PHY_ADDR,
+				   REG_MII_DATA0, value);
+	if (ret)
+		return ret;
+
+	return b53_mdio_op(dev, page, reg, REG_MII_ADDR_WRITE);
+}
+
+static int b53_mdio_write16(struct b53_device *dev, u8 page, u8 reg,
+			    u16 value)
+{
+	struct mii_bus *bus = dev->priv;
+	int ret;
+
+	ret = mdiobus_write_nested(bus, BRCM_PSEUDO_PHY_ADDR,
+				   REG_MII_DATA0, value);
+	if (ret)
+		return ret;
+
+	return b53_mdio_op(dev, page, reg, REG_MII_ADDR_WRITE);
+}
+
+static int b53_mdio_write32(struct b53_device *dev, u8 page, u8 reg,
+			    u32 value)
+{
+	struct mii_bus *bus = dev->priv;
+	unsigned int i;
+	u32 temp = value;
+
+	for (i = 0; i < 2; i++) {
+		int ret = mdiobus_write_nested(bus, BRCM_PSEUDO_PHY_ADDR,
+					       REG_MII_DATA0 + i,
+					       temp & 0xffff);
+		if (ret)
+			return ret;
+		temp >>= 16;
+	}
+
+	return b53_mdio_op(dev, page, reg, REG_MII_ADDR_WRITE);
+}
+
+static int b53_mdio_write48(struct b53_device *dev, u8 page, u8 reg,
+			    u64 value)
+{
+	struct mii_bus *bus = dev->priv;
+	unsigned int i;
+	u64 temp = value;
+
+	for (i = 0; i < 3; i++) {
+		int ret = mdiobus_write_nested(bus, BRCM_PSEUDO_PHY_ADDR,
+					       REG_MII_DATA0 + i,
+					       temp & 0xffff);
+		if (ret)
+			return ret;
+		temp >>= 16;
+	}
+
+	return b53_mdio_op(dev, page, reg, REG_MII_ADDR_WRITE);
+}
+
+static int b53_mdio_write64(struct b53_device *dev, u8 page, u8 reg,
+			    u64 value)
+{
+	struct mii_bus *bus = dev->priv;
+	unsigned int i;
+	u64 temp = value;
+
+	for (i = 0; i < 4; i++) {
+		int ret = mdiobus_write_nested(bus, BRCM_PSEUDO_PHY_ADDR,
+					       REG_MII_DATA0 + i,
+					       temp & 0xffff);
+		if (ret)
+			return ret;
+		temp >>= 16;
+	}
+
+	return b53_mdio_op(dev, page, reg, REG_MII_ADDR_WRITE);
+}
+
+static int b53_mdio_phy_read16(struct b53_device *dev, int addr, int reg,
+			       u16 *value)
+{
+	struct mii_bus *bus = dev->priv;
+
+	*value = mdiobus_read_nested(bus, addr, reg);
+
+	return 0;
+}
+
+static int b53_mdio_phy_write16(struct b53_device *dev, int addr, int reg,
+				u16 value)
+{
+	struct mii_bus *bus = dev->bus;
+
+	return mdiobus_write_nested(bus, addr, reg, value);
+}
+
+static struct b53_io_ops b53_mdio_ops = {
+	.read8 = b53_mdio_read8,
+	.read16 = b53_mdio_read16,
+	.read32 = b53_mdio_read32,
+	.read48 = b53_mdio_read48,
+	.read64 = b53_mdio_read64,
+	.write8 = b53_mdio_write8,
+	.write16 = b53_mdio_write16,
+	.write32 = b53_mdio_write32,
+	.write48 = b53_mdio_write48,
+	.write64 = b53_mdio_write64,
+	.phy_read16 = b53_mdio_phy_read16,
+	.phy_write16 = b53_mdio_phy_write16,
+};
+
+#define B53_BRCM_OUI_1	0x0143bc00
+#define B53_BRCM_OUI_2	0x03625c00
+#define B53_BRCM_OUI_3	0x00406000
+
+static int b53_mdio_probe(struct mdio_device *mdiodev)
+{
+	struct b53_device *dev;
+	u32 phy_id;
+	int ret;
+
+	/* allow the generic PHY driver to take over the non-management MDIO
+	 * addresses
+	 */
+	if (mdiodev->addr != BRCM_PSEUDO_PHY_ADDR && mdiodev->addr != 0) {
+		dev_err(&mdiodev->dev, "leaving address %d to PHY\n",
+			mdiodev->addr);
+		return -ENODEV;
+	}
+
+	/* read the first port's id */
+	phy_id = mdiobus_read(mdiodev->bus, 0, 2) << 16;
+	phy_id |= mdiobus_read(mdiodev->bus, 0, 3);
+
+	/* BCM5325, BCM539x (OUI_1)
+	 * BCM53125, BCM53128 (OUI_2)
+	 * BCM5365 (OUI_3)
+	 */
+	if ((phy_id & 0xfffffc00) != B53_BRCM_OUI_1 &&
+	    (phy_id & 0xfffffc00) != B53_BRCM_OUI_2 &&
+	    (phy_id & 0xfffffc00) != B53_BRCM_OUI_3) {
+		dev_err(&mdiodev->dev, "Unsupported device: 0x%08x\n", phy_id);
+		return -ENODEV;
+	}
+
+	/* First probe will come from SWITCH_MDIO controller on the 7445D0
+	 * switch, which will conflict with the 7445 integrated switch
+	 * pseudo-phy (we end-up programming both). In that case, we return
+	 * -EPROBE_DEFER for the first time we get here, and wait until we come
+	 * back with the slave MDIO bus which has the correct indirection
+	 * layer setup
+	 */
+	if (of_machine_is_compatible("brcm,bcm7445d0") &&
+	    strcmp(mdiodev->bus->name, "sf2 slave mii"))
+		return -EPROBE_DEFER;
+
+	dev = b53_switch_alloc(&mdiodev->dev, &b53_mdio_ops, mdiodev->bus);
+	if (!dev)
+		return -ENOMEM;
+
+	/* we don't use page 0xff, so force a page set */
+	dev->current_page = 0xff;
+	dev->bus = mdiodev->bus;
+
+	dev_set_drvdata(&mdiodev->dev, dev);
+
+	ret = b53_switch_register(dev);
+	if (ret) {
+		dev_err(&mdiodev->dev, "failed to register switch: %i\n", ret);
+		return ret;
+	}
+
+	return ret;
+}
+
+static void b53_mdio_remove(struct mdio_device *mdiodev)
+{
+	struct b53_device *dev = dev_get_drvdata(&mdiodev->dev);
+	struct dsa_switch *ds = dev->ds;
+
+	dsa_unregister_switch(ds);
+}
+
+static const struct of_device_id b53_of_match[] = {
+	{ .compatible = "brcm,bcm5325" },
+	{ .compatible = "brcm,bcm53115" },
+	{ .compatible = "brcm,bcm53125" },
+	{ .compatible = "brcm,bcm53128" },
+	{ .compatible = "brcm,bcm5365" },
+	{ .compatible = "brcm,bcm5395" },
+	{ .compatible = "brcm,bcm5397" },
+	{ .compatible = "brcm,bcm5398" },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, b53_of_match);
+
+static struct mdio_driver b53_mdio_driver = {
+	.probe	= b53_mdio_probe,
+	.remove	= b53_mdio_remove,
+	.mdiodrv.driver = {
+		.name = "bcm53xx",
+		.of_match_table = b53_of_match,
+	},
+};
+
+static int __init b53_mdio_driver_register(void)
+{
+	return mdio_driver_register(&b53_mdio_driver);
+}
+module_init(b53_mdio_driver_register);
+
+static void __exit b53_mdio_driver_unregister(void)
+{
+	mdio_driver_unregister(&b53_mdio_driver);
+}
+module_exit(b53_mdio_driver_unregister);
+
+MODULE_DESCRIPTION("B53 MDIO access driver");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/dsa/b53/b53_mmap.c b/drivers/net/dsa/b53/b53_mmap.c
new file mode 100644
index 0000000..b70daf9
--- /dev/null
+++ b/drivers/net/dsa/b53/b53_mmap.c
@@ -0,0 +1,256 @@
+/*
+ * B53 register access through memory mapped registers
+ *
+ * Copyright (C) 2012-2013 Jonas Gorski <jogo@openwrt.org>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/kconfig.h>
+#include <linux/module.h>
+#include <linux/io.h>
+#include <linux/platform_device.h>
+#include <linux/platform_data/b53.h>
+
+#include "b53_priv.h"
+
+struct b53_mmap_priv {
+	void __iomem *regs;
+};
+
+static int b53_mmap_read8(struct b53_device *dev, u8 page, u8 reg, u8 *val)
+{
+	u8 __iomem *regs = dev->priv;
+
+	*val = readb(regs + (page << 8) + reg);
+
+	return 0;
+}
+
+static int b53_mmap_read16(struct b53_device *dev, u8 page, u8 reg, u16 *val)
+{
+	u8 __iomem *regs = dev->priv;
+
+	if (WARN_ON(reg % 2))
+		return -EINVAL;
+
+	if (dev->pdata && dev->pdata->big_endian)
+		*val = ioread16be(regs + (page << 8) + reg);
+	else
+		*val = readw(regs + (page << 8) + reg);
+
+	return 0;
+}
+
+static int b53_mmap_read32(struct b53_device *dev, u8 page, u8 reg, u32 *val)
+{
+	u8 __iomem *regs = dev->priv;
+
+	if (WARN_ON(reg % 4))
+		return -EINVAL;
+
+	if (dev->pdata && dev->pdata->big_endian)
+		*val = ioread32be(regs + (page << 8) + reg);
+	else
+		*val = readl(regs + (page << 8) + reg);
+
+	return 0;
+}
+
+static int b53_mmap_read48(struct b53_device *dev, u8 page, u8 reg, u64 *val)
+{
+	if (WARN_ON(reg % 2))
+		return -EINVAL;
+
+	if (reg % 4) {
+		u16 lo;
+		u32 hi;
+
+		b53_mmap_read16(dev, page, reg, &lo);
+		b53_mmap_read32(dev, page, reg + 2, &hi);
+
+		*val = ((u64)hi << 16) | lo;
+	} else {
+		u32 lo;
+		u16 hi;
+
+		b53_mmap_read32(dev, page, reg, &lo);
+		b53_mmap_read16(dev, page, reg + 4, &hi);
+
+		*val = ((u64)hi << 32) | lo;
+	}
+
+	return 0;
+}
+
+static int b53_mmap_read64(struct b53_device *dev, u8 page, u8 reg, u64 *val)
+{
+	u32 hi, lo;
+
+	if (WARN_ON(reg % 4))
+		return -EINVAL;
+
+	b53_mmap_read32(dev, page, reg, &lo);
+	b53_mmap_read32(dev, page, reg + 4, &hi);
+
+	*val = ((u64)hi << 32) | lo;
+
+	return 0;
+}
+
+static int b53_mmap_write8(struct b53_device *dev, u8 page, u8 reg, u8 value)
+{
+	u8 __iomem *regs = dev->priv;
+
+	writeb(value, regs + (page << 8) + reg);
+
+	return 0;
+}
+
+static int b53_mmap_write16(struct b53_device *dev, u8 page, u8 reg,
+			    u16 value)
+{
+	u8 __iomem *regs = dev->priv;
+
+	if (WARN_ON(reg % 2))
+		return -EINVAL;
+
+	if (dev->pdata && dev->pdata->big_endian)
+		iowrite16be(value, regs + (page << 8) + reg);
+	else
+		writew(value, regs + (page << 8) + reg);
+
+	return 0;
+}
+
+static int b53_mmap_write32(struct b53_device *dev, u8 page, u8 reg,
+			    u32 value)
+{
+	u8 __iomem *regs = dev->priv;
+
+	if (WARN_ON(reg % 4))
+		return -EINVAL;
+
+	if (dev->pdata && dev->pdata->big_endian)
+		iowrite32be(value, regs + (page << 8) + reg);
+	else
+		writel(value, regs + (page << 8) + reg);
+
+	return 0;
+}
+
+static int b53_mmap_write48(struct b53_device *dev, u8 page, u8 reg,
+			    u64 value)
+{
+	if (WARN_ON(reg % 2))
+		return -EINVAL;
+
+	if (reg % 4) {
+		u32 hi = (u32)(value >> 16);
+		u16 lo = (u16)value;
+
+		b53_mmap_write16(dev, page, reg, lo);
+		b53_mmap_write32(dev, page, reg + 2, hi);
+	} else {
+		u16 hi = (u16)(value >> 32);
+		u32 lo = (u32)value;
+
+		b53_mmap_write32(dev, page, reg, lo);
+		b53_mmap_write16(dev, page, reg + 4, hi);
+	}
+
+	return 0;
+}
+
+static int b53_mmap_write64(struct b53_device *dev, u8 page, u8 reg,
+			    u64 value)
+{
+	u32 hi, lo;
+
+	hi = upper_32_bits(value);
+	lo = lower_32_bits(value);
+
+	if (WARN_ON(reg % 4))
+		return -EINVAL;
+
+	b53_mmap_write32(dev, page, reg, lo);
+	b53_mmap_write32(dev, page, reg + 4, hi);
+
+	return 0;
+}
+
+static struct b53_io_ops b53_mmap_ops = {
+	.read8 = b53_mmap_read8,
+	.read16 = b53_mmap_read16,
+	.read32 = b53_mmap_read32,
+	.read48 = b53_mmap_read48,
+	.read64 = b53_mmap_read64,
+	.write8 = b53_mmap_write8,
+	.write16 = b53_mmap_write16,
+	.write32 = b53_mmap_write32,
+	.write48 = b53_mmap_write48,
+	.write64 = b53_mmap_write64,
+};
+
+static int b53_mmap_probe(struct platform_device *pdev)
+{
+	struct b53_platform_data *pdata = pdev->dev.platform_data;
+	struct b53_device *dev;
+
+	if (!pdata)
+		return -EINVAL;
+
+	dev = b53_switch_alloc(&pdev->dev, &b53_mmap_ops, pdata->regs);
+	if (!dev)
+		return -ENOMEM;
+
+	if (pdata)
+		dev->pdata = pdata;
+
+	platform_set_drvdata(pdev, dev);
+
+	return b53_switch_register(dev);
+}
+
+static int b53_mmap_remove(struct platform_device *pdev)
+{
+	struct b53_device *dev = platform_get_drvdata(pdev);
+
+	if (dev)
+		b53_switch_remove(dev);
+
+	return 0;
+}
+
+static const struct of_device_id b53_mmap_of_table[] = {
+	{ .compatible = "brcm,bcm3384-switch" },
+	{ .compatible = "brcm,bcm6328-switch" },
+	{ .compatible = "brcm,bcm6368-switch" },
+	{ .compatible = "brcm,bcm63xx-switch" },
+	{ /* sentinel */ },
+};
+
+static struct platform_driver b53_mmap_driver = {
+	.probe = b53_mmap_probe,
+	.remove = b53_mmap_remove,
+	.driver = {
+		.name = "b53-switch",
+		.of_match_table = b53_mmap_of_table,
+	},
+};
+
+module_platform_driver(b53_mmap_driver);
+MODULE_AUTHOR("Jonas Gorski <jogo@openwrt.org>");
+MODULE_DESCRIPTION("B53 MMAP access driver");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h
new file mode 100644
index 0000000..5d8c602
--- /dev/null
+++ b/drivers/net/dsa/b53/b53_priv.h
@@ -0,0 +1,387 @@
+/*
+ * B53 common definitions
+ *
+ * Copyright (C) 2011-2013 Jonas Gorski <jogo@openwrt.org>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#ifndef __B53_PRIV_H
+#define __B53_PRIV_H
+
+#include <linux/kernel.h>
+#include <linux/mutex.h>
+#include <linux/phy.h>
+#include <net/dsa.h>
+
+#include "b53_regs.h"
+
+struct b53_device;
+struct net_device;
+
+struct b53_io_ops {
+	int (*read8)(struct b53_device *dev, u8 page, u8 reg, u8 *value);
+	int (*read16)(struct b53_device *dev, u8 page, u8 reg, u16 *value);
+	int (*read32)(struct b53_device *dev, u8 page, u8 reg, u32 *value);
+	int (*read48)(struct b53_device *dev, u8 page, u8 reg, u64 *value);
+	int (*read64)(struct b53_device *dev, u8 page, u8 reg, u64 *value);
+	int (*write8)(struct b53_device *dev, u8 page, u8 reg, u8 value);
+	int (*write16)(struct b53_device *dev, u8 page, u8 reg, u16 value);
+	int (*write32)(struct b53_device *dev, u8 page, u8 reg, u32 value);
+	int (*write48)(struct b53_device *dev, u8 page, u8 reg, u64 value);
+	int (*write64)(struct b53_device *dev, u8 page, u8 reg, u64 value);
+	int (*phy_read16)(struct b53_device *dev, int addr, int reg, u16 *value);
+	int (*phy_write16)(struct b53_device *dev, int addr, int reg, u16 value);
+};
+
+enum {
+	BCM5325_DEVICE_ID = 0x25,
+	BCM5365_DEVICE_ID = 0x65,
+	BCM5395_DEVICE_ID = 0x95,
+	BCM5397_DEVICE_ID = 0x97,
+	BCM5398_DEVICE_ID = 0x98,
+	BCM53115_DEVICE_ID = 0x53115,
+	BCM53125_DEVICE_ID = 0x53125,
+	BCM53128_DEVICE_ID = 0x53128,
+	BCM63XX_DEVICE_ID = 0x6300,
+	BCM53010_DEVICE_ID = 0x53010,
+	BCM53011_DEVICE_ID = 0x53011,
+	BCM53012_DEVICE_ID = 0x53012,
+	BCM53018_DEVICE_ID = 0x53018,
+	BCM53019_DEVICE_ID = 0x53019,
+};
+
+#define B53_N_PORTS	9
+#define B53_N_PORTS_25	6
+
+struct b53_port {
+	u16		vlan_ctl_mask;
+	struct net_device *bridge_dev;
+};
+
+struct b53_vlan {
+	u16 members;
+	u16 untag;
+	bool valid;
+};
+
+struct b53_device {
+	struct dsa_switch *ds;
+	struct b53_platform_data *pdata;
+	const char *name;
+
+	struct mutex reg_mutex;
+	struct mutex stats_mutex;
+	const struct b53_io_ops *ops;
+
+	/* chip specific data */
+	u32 chip_id;
+	u8 core_rev;
+	u8 vta_regs[3];
+	u8 duplex_reg;
+	u8 jumbo_pm_reg;
+	u8 jumbo_size_reg;
+	int reset_gpio;
+	u8 num_arl_entries;
+
+	/* used ports mask */
+	u16 enabled_ports;
+	unsigned int cpu_port;
+
+	/* connect specific data */
+	u8 current_page;
+	struct device *dev;
+
+	/* Master MDIO bus we got probed from */
+	struct mii_bus *bus;
+
+	void *priv;
+
+	/* run time configuration */
+	bool enable_jumbo;
+
+	unsigned int num_vlans;
+	struct b53_vlan *vlans;
+	unsigned int num_ports;
+	struct b53_port *ports;
+};
+
+#define b53_for_each_port(dev, i) \
+	for (i = 0; i < B53_N_PORTS; i++) \
+		if (dev->enabled_ports & BIT(i))
+
+
+static inline int is5325(struct b53_device *dev)
+{
+	return dev->chip_id == BCM5325_DEVICE_ID;
+}
+
+static inline int is5365(struct b53_device *dev)
+{
+#ifdef CONFIG_BCM47XX
+	return dev->chip_id == BCM5365_DEVICE_ID;
+#else
+	return 0;
+#endif
+}
+
+static inline int is5397_98(struct b53_device *dev)
+{
+	return dev->chip_id == BCM5397_DEVICE_ID ||
+		dev->chip_id == BCM5398_DEVICE_ID;
+}
+
+static inline int is539x(struct b53_device *dev)
+{
+	return dev->chip_id == BCM5395_DEVICE_ID ||
+		dev->chip_id == BCM5397_DEVICE_ID ||
+		dev->chip_id == BCM5398_DEVICE_ID;
+}
+
+static inline int is531x5(struct b53_device *dev)
+{
+	return dev->chip_id == BCM53115_DEVICE_ID ||
+		dev->chip_id == BCM53125_DEVICE_ID ||
+		dev->chip_id == BCM53128_DEVICE_ID;
+}
+
+static inline int is63xx(struct b53_device *dev)
+{
+#ifdef CONFIG_BCM63XX
+	return dev->chip_id == BCM63XX_DEVICE_ID;
+#else
+	return 0;
+#endif
+}
+
+static inline int is5301x(struct b53_device *dev)
+{
+	return dev->chip_id == BCM53010_DEVICE_ID ||
+		dev->chip_id == BCM53011_DEVICE_ID ||
+		dev->chip_id == BCM53012_DEVICE_ID ||
+		dev->chip_id == BCM53018_DEVICE_ID ||
+		dev->chip_id == BCM53019_DEVICE_ID;
+}
+
+#define B53_CPU_PORT_25	5
+#define B53_CPU_PORT	8
+
+static inline int is_cpu_port(struct b53_device *dev, int port)
+{
+	return dev->cpu_port;
+}
+
+struct b53_device *b53_switch_alloc(struct device *base, struct b53_io_ops *ops,
+				    void *priv);
+
+int b53_switch_detect(struct b53_device *dev);
+
+int b53_switch_register(struct b53_device *dev);
+
+static inline void b53_switch_remove(struct b53_device *dev)
+{
+	dsa_unregister_switch(dev->ds);
+}
+
+static inline int b53_read8(struct b53_device *dev, u8 page, u8 reg, u8 *val)
+{
+	int ret;
+
+	mutex_lock(&dev->reg_mutex);
+	ret = dev->ops->read8(dev, page, reg, val);
+	mutex_unlock(&dev->reg_mutex);
+
+	return ret;
+}
+
+static inline int b53_read16(struct b53_device *dev, u8 page, u8 reg, u16 *val)
+{
+	int ret;
+
+	mutex_lock(&dev->reg_mutex);
+	ret = dev->ops->read16(dev, page, reg, val);
+	mutex_unlock(&dev->reg_mutex);
+
+	return ret;
+}
+
+static inline int b53_read32(struct b53_device *dev, u8 page, u8 reg, u32 *val)
+{
+	int ret;
+
+	mutex_lock(&dev->reg_mutex);
+	ret = dev->ops->read32(dev, page, reg, val);
+	mutex_unlock(&dev->reg_mutex);
+
+	return ret;
+}
+
+static inline int b53_read48(struct b53_device *dev, u8 page, u8 reg, u64 *val)
+{
+	int ret;
+
+	mutex_lock(&dev->reg_mutex);
+	ret = dev->ops->read48(dev, page, reg, val);
+	mutex_unlock(&dev->reg_mutex);
+
+	return ret;
+}
+
+static inline int b53_read64(struct b53_device *dev, u8 page, u8 reg, u64 *val)
+{
+	int ret;
+
+	mutex_lock(&dev->reg_mutex);
+	ret = dev->ops->read64(dev, page, reg, val);
+	mutex_unlock(&dev->reg_mutex);
+
+	return ret;
+}
+
+static inline int b53_write8(struct b53_device *dev, u8 page, u8 reg, u8 value)
+{
+	int ret;
+
+	mutex_lock(&dev->reg_mutex);
+	ret = dev->ops->write8(dev, page, reg, value);
+	mutex_unlock(&dev->reg_mutex);
+
+	return ret;
+}
+
+static inline int b53_write16(struct b53_device *dev, u8 page, u8 reg,
+			      u16 value)
+{
+	int ret;
+
+	mutex_lock(&dev->reg_mutex);
+	ret = dev->ops->write16(dev, page, reg, value);
+	mutex_unlock(&dev->reg_mutex);
+
+	return ret;
+}
+
+static inline int b53_write32(struct b53_device *dev, u8 page, u8 reg,
+			      u32 value)
+{
+	int ret;
+
+	mutex_lock(&dev->reg_mutex);
+	ret = dev->ops->write32(dev, page, reg, value);
+	mutex_unlock(&dev->reg_mutex);
+
+	return ret;
+}
+
+static inline int b53_write48(struct b53_device *dev, u8 page, u8 reg,
+			      u64 value)
+{
+	int ret;
+
+	mutex_lock(&dev->reg_mutex);
+	ret = dev->ops->write48(dev, page, reg, value);
+	mutex_unlock(&dev->reg_mutex);
+
+	return ret;
+}
+
+static inline int b53_write64(struct b53_device *dev, u8 page, u8 reg,
+			       u64 value)
+{
+	int ret;
+
+	mutex_lock(&dev->reg_mutex);
+	ret = dev->ops->write64(dev, page, reg, value);
+	mutex_unlock(&dev->reg_mutex);
+
+	return ret;
+}
+
+struct b53_arl_entry {
+	u8 port;
+	u8 mac[ETH_ALEN];
+	u16 vid;
+	u8 is_valid:1;
+	u8 is_age:1;
+	u8 is_static:1;
+};
+
+static inline void b53_mac_from_u64(u64 src, u8 *dst)
+{
+	unsigned int i;
+
+	for (i = 0; i < ETH_ALEN; i++)
+		dst[ETH_ALEN - 1 - i] = (src >> (8 * i)) & 0xff;
+}
+
+static inline u64 b53_mac_to_u64(const u8 *src)
+{
+	unsigned int i;
+	u64 dst = 0;
+
+	for (i = 0; i < ETH_ALEN; i++)
+		dst |= (u64)src[ETH_ALEN - 1 - i] << (8 * i);
+
+	return dst;
+}
+
+static inline void b53_arl_to_entry(struct b53_arl_entry *ent,
+				    u64 mac_vid, u32 fwd_entry)
+{
+	memset(ent, 0, sizeof(*ent));
+	ent->port = fwd_entry & ARLTBL_DATA_PORT_ID_MASK;
+	ent->is_valid = !!(fwd_entry & ARLTBL_VALID);
+	ent->is_age = !!(fwd_entry & ARLTBL_AGE);
+	ent->is_static = !!(fwd_entry & ARLTBL_STATIC);
+	b53_mac_from_u64(mac_vid, ent->mac);
+	ent->vid = mac_vid >> ARLTBL_VID_S;
+}
+
+static inline void b53_arl_from_entry(u64 *mac_vid, u32 *fwd_entry,
+				      const struct b53_arl_entry *ent)
+{
+	*mac_vid = b53_mac_to_u64(ent->mac);
+	*mac_vid |= (u64)(ent->vid & ARLTBL_VID_MASK) << ARLTBL_VID_S;
+	*fwd_entry = ent->port & ARLTBL_DATA_PORT_ID_MASK;
+	if (ent->is_valid)
+		*fwd_entry |= ARLTBL_VALID;
+	if (ent->is_static)
+		*fwd_entry |= ARLTBL_STATIC;
+	if (ent->is_age)
+		*fwd_entry |= ARLTBL_AGE;
+}
+
+#ifdef CONFIG_BCM47XX
+
+#include <linux/version.h>
+#include <linux/bcm47xx_nvram.h>
+#include <bcm47xx_board.h>
+static inline int b53_switch_get_reset_gpio(struct b53_device *dev)
+{
+	enum bcm47xx_board board = bcm47xx_board_get();
+
+	switch (board) {
+	case BCM47XX_BOARD_LINKSYS_WRT300NV11:
+	case BCM47XX_BOARD_LINKSYS_WRT310NV1:
+		return 8;
+	default:
+		return bcm47xx_nvram_gpio_pin("robo_reset");
+	}
+}
+#else
+static inline int b53_switch_get_reset_gpio(struct b53_device *dev)
+{
+	return -ENOENT;
+}
+#endif
+#endif
diff --git a/drivers/net/dsa/b53/b53_regs.h b/drivers/net/dsa/b53/b53_regs.h
new file mode 100644
index 0000000..8f12bdd
--- /dev/null
+++ b/drivers/net/dsa/b53/b53_regs.h
@@ -0,0 +1,434 @@
+/*
+ * B53 register definitions
+ *
+ * Copyright (C) 2004 Broadcom Corporation
+ * Copyright (C) 2011-2013 Jonas Gorski <jogo@openwrt.org>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#ifndef __B53_REGS_H
+#define __B53_REGS_H
+
+/* Management Port (SMP) Page offsets */
+#define B53_CTRL_PAGE			0x00 /* Control */
+#define B53_STAT_PAGE			0x01 /* Status */
+#define B53_MGMT_PAGE			0x02 /* Management Mode */
+#define B53_MIB_AC_PAGE			0x03 /* MIB Autocast */
+#define B53_ARLCTRL_PAGE		0x04 /* ARL Control */
+#define B53_ARLIO_PAGE			0x05 /* ARL Access */
+#define B53_FRAMEBUF_PAGE		0x06 /* Management frame access */
+#define B53_MEM_ACCESS_PAGE		0x08 /* Memory access */
+
+/* PHY Registers */
+#define B53_PORT_MII_PAGE(i)		(0x10 + (i)) /* Port i MII Registers */
+#define B53_IM_PORT_PAGE		0x18 /* Inverse MII Port (to EMAC) */
+#define B53_ALL_PORT_PAGE		0x19 /* All ports MII (broadcast) */
+
+/* MIB registers */
+#define B53_MIB_PAGE(i)			(0x20 + (i))
+
+/* Quality of Service (QoS) Registers */
+#define B53_QOS_PAGE			0x30
+
+/* Port VLAN Page */
+#define B53_PVLAN_PAGE			0x31
+
+/* VLAN Registers */
+#define B53_VLAN_PAGE			0x34
+
+/* Jumbo Frame Registers */
+#define B53_JUMBO_PAGE			0x40
+
+/* CFP Configuration Registers Page */
+#define B53_CFP_PAGE			0xa1
+
+/*************************************************************************
+ * Control Page registers
+ *************************************************************************/
+
+/* Port Control Register (8 bit) */
+#define B53_PORT_CTRL(i)		(0x00 + (i))
+#define   PORT_CTRL_RX_DISABLE		BIT(0)
+#define   PORT_CTRL_TX_DISABLE		BIT(1)
+#define   PORT_CTRL_RX_BCST_EN		BIT(2) /* Broadcast RX (P8 only) */
+#define   PORT_CTRL_RX_MCST_EN		BIT(3) /* Multicast RX (P8 only) */
+#define   PORT_CTRL_RX_UCST_EN		BIT(4) /* Unicast RX (P8 only) */
+#define	  PORT_CTRL_STP_STATE_S		5
+#define   PORT_CTRL_NO_STP		(0 << PORT_CTRL_STP_STATE_S)
+#define   PORT_CTRL_DIS_STATE		(1 << PORT_CTRL_STP_STATE_S)
+#define   PORT_CTRL_BLOCK_STATE		(2 << PORT_CTRL_STP_STATE_S)
+#define   PORT_CTRL_LISTEN_STATE	(3 << PORT_CTRL_STP_STATE_S)
+#define   PORT_CTRL_LEARN_STATE		(4 << PORT_CTRL_STP_STATE_S)
+#define   PORT_CTRL_FWD_STATE		(5 << PORT_CTRL_STP_STATE_S)
+#define   PORT_CTRL_STP_STATE_MASK	(0x7 << PORT_CTRL_STP_STATE_S)
+
+/* SMP Control Register (8 bit) */
+#define B53_SMP_CTRL			0x0a
+
+/* Switch Mode Control Register (8 bit) */
+#define B53_SWITCH_MODE			0x0b
+#define   SM_SW_FWD_MODE		BIT(0)	/* 1 = Managed Mode */
+#define   SM_SW_FWD_EN			BIT(1)	/* Forwarding Enable */
+
+/* IMP Port state override register (8 bit) */
+#define B53_PORT_OVERRIDE_CTRL		0x0e
+#define   PORT_OVERRIDE_LINK		BIT(0)
+#define   PORT_OVERRIDE_FULL_DUPLEX	BIT(1) /* 0 = Half Duplex */
+#define   PORT_OVERRIDE_SPEED_S		2
+#define   PORT_OVERRIDE_SPEED_10M	(0 << PORT_OVERRIDE_SPEED_S)
+#define   PORT_OVERRIDE_SPEED_100M	(1 << PORT_OVERRIDE_SPEED_S)
+#define   PORT_OVERRIDE_SPEED_1000M	(2 << PORT_OVERRIDE_SPEED_S)
+#define   PORT_OVERRIDE_RV_MII_25	BIT(4) /* BCM5325 only */
+#define   PORT_OVERRIDE_RX_FLOW		BIT(4)
+#define   PORT_OVERRIDE_TX_FLOW		BIT(5)
+#define   PORT_OVERRIDE_SPEED_2000M	BIT(6) /* BCM5301X only, requires setting 1000M */
+#define   PORT_OVERRIDE_EN		BIT(7) /* Use the register contents */
+
+/* Power-down mode control */
+#define B53_PD_MODE_CTRL_25		0x0f
+
+/* IP Multicast control (8 bit) */
+#define B53_IP_MULTICAST_CTRL		0x21
+#define  B53_IPMC_FWD_EN		BIT(1)
+#define  B53_UC_FWD_EN			BIT(6)
+#define  B53_MC_FWD_EN			BIT(7)
+
+/* (16 bit) */
+#define B53_UC_FLOOD_MASK		0x32
+#define B53_MC_FLOOD_MASK		0x34
+#define B53_IPMC_FLOOD_MASK		0x36
+
+/*
+ * Override Ports 0-7 State on devices with xMII interfaces (8 bit)
+ *
+ * For port 8 still use B53_PORT_OVERRIDE_CTRL
+ * Please note that not all ports are available on every hardware, e.g. BCM5301X
+ * don't include overriding port 6, BCM63xx also have some limitations.
+ */
+#define B53_GMII_PORT_OVERRIDE_CTRL(i)	(0x58 + (i))
+#define   GMII_PO_LINK			BIT(0)
+#define   GMII_PO_FULL_DUPLEX		BIT(1) /* 0 = Half Duplex */
+#define   GMII_PO_SPEED_S		2
+#define   GMII_PO_SPEED_10M		(0 << GMII_PO_SPEED_S)
+#define   GMII_PO_SPEED_100M		(1 << GMII_PO_SPEED_S)
+#define   GMII_PO_SPEED_1000M		(2 << GMII_PO_SPEED_S)
+#define   GMII_PO_RX_FLOW		BIT(4)
+#define   GMII_PO_TX_FLOW		BIT(5)
+#define   GMII_PO_EN			BIT(6) /* Use the register contents */
+#define   GMII_PO_SPEED_2000M		BIT(7) /* BCM5301X only, requires setting 1000M */
+
+#define B53_RGMII_CTRL_IMP		0x60
+#define   RGMII_CTRL_ENABLE_GMII	BIT(7)
+#define   RGMII_CTRL_TIMING_SEL		BIT(2)
+#define   RGMII_CTRL_DLL_RXC		BIT(1)
+#define   RGMII_CTRL_DLL_TXC		BIT(0)
+
+#define B53_RGMII_CTRL_P(i)		(B53_RGMII_CTRL_IMP + (i))
+
+/* Software reset register (8 bit) */
+#define B53_SOFTRESET			0x79
+#define   SW_RST			BIT(7)
+#define   EN_SW_RST			BIT(4)
+
+/* Fast Aging Control register (8 bit) */
+#define B53_FAST_AGE_CTRL		0x88
+#define   FAST_AGE_STATIC		BIT(0)
+#define   FAST_AGE_DYNAMIC		BIT(1)
+#define   FAST_AGE_PORT			BIT(2)
+#define   FAST_AGE_VLAN			BIT(3)
+#define   FAST_AGE_STP			BIT(4)
+#define   FAST_AGE_MC			BIT(5)
+#define   FAST_AGE_DONE			BIT(7)
+
+/* Fast Aging Port Control register (8 bit) */
+#define B53_FAST_AGE_PORT_CTRL		0x89
+
+/* Fast Aging VID Control register (16 bit) */
+#define B53_FAST_AGE_VID_CTRL		0x8a
+
+/*************************************************************************
+ * Status Page registers
+ *************************************************************************/
+
+/* Link Status Summary Register (16bit) */
+#define B53_LINK_STAT			0x00
+
+/* Link Status Change Register (16 bit) */
+#define B53_LINK_STAT_CHANGE		0x02
+
+/* Port Speed Summary Register (16 bit for FE, 32 bit for GE) */
+#define B53_SPEED_STAT			0x04
+#define  SPEED_PORT_FE(reg, port)	(((reg) >> (port)) & 1)
+#define  SPEED_PORT_GE(reg, port)	(((reg) >> 2 * (port)) & 3)
+#define  SPEED_STAT_10M			0
+#define  SPEED_STAT_100M		1
+#define  SPEED_STAT_1000M		2
+
+/* Duplex Status Summary (16 bit) */
+#define B53_DUPLEX_STAT_FE		0x06
+#define B53_DUPLEX_STAT_GE		0x08
+#define B53_DUPLEX_STAT_63XX		0x0c
+
+/* Revision ID register for BCM5325 */
+#define B53_REV_ID_25			0x50
+
+/* Strap Value (48 bit) */
+#define B53_STRAP_VALUE			0x70
+#define   SV_GMII_CTRL_115		BIT(27)
+
+/*************************************************************************
+ * Management Mode Page Registers
+ *************************************************************************/
+
+/* Global Management Config Register (8 bit) */
+#define B53_GLOBAL_CONFIG		0x00
+#define   GC_RESET_MIB			0x01
+#define   GC_RX_BPDU_EN			0x02
+#define   GC_MIB_AC_HDR_EN		0x10
+#define   GC_MIB_AC_EN			0x20
+#define   GC_FRM_MGMT_PORT_M		0xC0
+#define   GC_FRM_MGMT_PORT_04		0x00
+#define   GC_FRM_MGMT_PORT_MII		0x80
+
+/* Broadcom Header control register (8 bit) */
+#define B53_BRCM_HDR			0x03
+#define   BRCM_HDR_P8_EN		BIT(0) /* Enable tagging on port 8 */
+#define   BRCM_HDR_P5_EN		BIT(1) /* Enable tagging on port 5 */
+
+/* Device ID register (8 or 32 bit) */
+#define B53_DEVICE_ID			0x30
+
+/* Revision ID register (8 bit) */
+#define B53_REV_ID			0x40
+
+/*************************************************************************
+ * ARL Access Page Registers
+ *************************************************************************/
+
+/* VLAN Table Access Register (8 bit) */
+#define B53_VT_ACCESS			0x80
+#define B53_VT_ACCESS_9798		0x60 /* for BCM5397/BCM5398 */
+#define B53_VT_ACCESS_63XX		0x60 /* for BCM6328/62/68 */
+#define   VTA_CMD_WRITE			0
+#define   VTA_CMD_READ			1
+#define   VTA_CMD_CLEAR			2
+#define   VTA_START_CMD			BIT(7)
+
+/* VLAN Table Index Register (16 bit) */
+#define B53_VT_INDEX			0x81
+#define B53_VT_INDEX_9798		0x61
+#define B53_VT_INDEX_63XX		0x62
+
+/* VLAN Table Entry Register (32 bit) */
+#define B53_VT_ENTRY			0x83
+#define B53_VT_ENTRY_9798		0x63
+#define B53_VT_ENTRY_63XX		0x64
+#define   VTE_MEMBERS			0x1ff
+#define   VTE_UNTAG_S			9
+#define   VTE_UNTAG			(0x1ff << 9)
+
+/*************************************************************************
+ * ARL I/O Registers
+ *************************************************************************/
+
+/* ARL Table Read/Write Register (8 bit) */
+#define B53_ARLTBL_RW_CTRL		0x00
+#define    ARLTBL_RW			BIT(0)
+#define    ARLTBL_START_DONE		BIT(7)
+
+/* MAC Address Index Register (48 bit) */
+#define B53_MAC_ADDR_IDX		0x02
+
+/* VLAN ID Index Register (16 bit) */
+#define B53_VLAN_ID_IDX			0x08
+
+/* ARL Table MAC/VID Entry N Registers (64 bit)
+ *
+ * BCM5325 and BCM5365 share most definitions below
+ */
+#define B53_ARLTBL_MAC_VID_ENTRY(n)	(0x10 * (n))
+#define   ARLTBL_MAC_MASK		0xffffffffffff
+#define   ARLTBL_VID_S			48
+#define   ARLTBL_VID_MASK_25		0xff
+#define   ARLTBL_VID_MASK		0xfff
+#define   ARLTBL_DATA_PORT_ID_S_25	48
+#define   ARLTBL_DATA_PORT_ID_MASK_25	0xf
+#define   ARLTBL_AGE_25			BIT(61)
+#define   ARLTBL_STATIC_25		BIT(62)
+#define   ARLTBL_VALID_25		BIT(63)
+
+/* ARL Table Data Entry N Registers (32 bit) */
+#define B53_ARLTBL_DATA_ENTRY(n)	((0x10 * (n)) + 0x08)
+#define   ARLTBL_DATA_PORT_ID_MASK	0x1ff
+#define   ARLTBL_TC(tc)			((3 & tc) << 11)
+#define   ARLTBL_AGE			BIT(14)
+#define   ARLTBL_STATIC			BIT(15)
+#define   ARLTBL_VALID			BIT(16)
+
+/* ARL Search Control Register (8 bit) */
+#define B53_ARL_SRCH_CTL		0x50
+#define B53_ARL_SRCH_CTL_25		0x20
+#define   ARL_SRCH_VLID			BIT(0)
+#define   ARL_SRCH_STDN			BIT(7)
+
+/* ARL Search Address Register (16 bit) */
+#define B53_ARL_SRCH_ADDR		0x51
+#define B53_ARL_SRCH_ADDR_25		0x22
+#define B53_ARL_SRCH_ADDR_65		0x24
+#define  ARL_ADDR_MASK			GENMASK(14, 0)
+
+/* ARL Search MAC/VID Result (64 bit) */
+#define B53_ARL_SRCH_RSTL_0_MACVID	0x60
+
+/* Single register search result on 5325 */
+#define B53_ARL_SRCH_RSTL_0_MACVID_25	0x24
+/* Single register search result on 5365 */
+#define B53_ARL_SRCH_RSTL_0_MACVID_65	0x30
+
+/* ARL Search Data Result (32 bit) */
+#define B53_ARL_SRCH_RSTL_0		0x68
+
+#define B53_ARL_SRCH_RSTL_MACVID(x)	(B53_ARL_SRCH_RSTL_0_MACVID + ((x) * 0x10))
+#define B53_ARL_SRCH_RSTL(x)		(B53_ARL_SRCH_RSTL_0 + ((x) * 0x10))
+
+/*************************************************************************
+ * Port VLAN Registers
+ *************************************************************************/
+
+/* Port VLAN mask (16 bit) IMP port is always 8, also on 5325 & co */
+#define B53_PVLAN_PORT_MASK(i)		((i) * 2)
+
+/*************************************************************************
+ * 802.1Q Page Registers
+ *************************************************************************/
+
+/* Global QoS Control (8 bit) */
+#define B53_QOS_GLOBAL_CTL		0x00
+
+/* Enable 802.1Q for individual Ports (16 bit) */
+#define B53_802_1P_EN			0x04
+
+/*************************************************************************
+ * VLAN Page Registers
+ *************************************************************************/
+
+/* VLAN Control 0 (8 bit) */
+#define B53_VLAN_CTRL0			0x00
+#define   VC0_8021PF_CTRL_MASK		0x3
+#define   VC0_8021PF_CTRL_NONE		0x0
+#define   VC0_8021PF_CTRL_CHANGE_PRI	0x1
+#define   VC0_8021PF_CTRL_CHANGE_VID	0x2
+#define   VC0_8021PF_CTRL_CHANGE_BOTH	0x3
+#define   VC0_8021QF_CTRL_MASK		0xc
+#define   VC0_8021QF_CTRL_CHANGE_PRI	0x1
+#define   VC0_8021QF_CTRL_CHANGE_VID	0x2
+#define   VC0_8021QF_CTRL_CHANGE_BOTH	0x3
+#define   VC0_RESERVED_1		BIT(1)
+#define   VC0_DROP_VID_MISS		BIT(4)
+#define   VC0_VID_HASH_VID		BIT(5)
+#define   VC0_VID_CHK_EN		BIT(6)	/* Use VID,DA or VID,SA */
+#define   VC0_VLAN_EN			BIT(7)	/* 802.1Q VLAN Enabled */
+
+/* VLAN Control 1 (8 bit) */
+#define B53_VLAN_CTRL1			0x01
+#define   VC1_RX_MCST_TAG_EN		BIT(1)
+#define   VC1_RX_MCST_FWD_EN		BIT(2)
+#define   VC1_RX_MCST_UNTAG_EN		BIT(3)
+
+/* VLAN Control 2 (8 bit) */
+#define B53_VLAN_CTRL2			0x02
+
+/* VLAN Control 3 (8 bit when BCM5325, 16 bit else) */
+#define B53_VLAN_CTRL3			0x03
+#define B53_VLAN_CTRL3_63XX		0x04
+#define   VC3_MAXSIZE_1532		BIT(6) /* 5325 only */
+#define   VC3_HIGH_8BIT_EN		BIT(7) /* 5325 only */
+
+/* VLAN Control 4 (8 bit) */
+#define B53_VLAN_CTRL4			0x05
+#define B53_VLAN_CTRL4_25		0x04
+#define B53_VLAN_CTRL4_63XX		0x06
+#define   VC4_ING_VID_CHECK_S		6
+#define   VC4_ING_VID_CHECK_MASK	(0x3 << VC4_ING_VID_CHECK_S)
+#define   VC4_ING_VID_VIO_FWD		0 /* forward, but do not learn */
+#define   VC4_ING_VID_VIO_DROP		1 /* drop VID violations */
+#define   VC4_NO_ING_VID_CHK		2 /* do not check */
+#define   VC4_ING_VID_VIO_TO_IMP	3 /* redirect to MII port */
+
+/* VLAN Control 5 (8 bit) */
+#define B53_VLAN_CTRL5			0x06
+#define B53_VLAN_CTRL5_25		0x05
+#define B53_VLAN_CTRL5_63XX		0x07
+#define   VC5_VID_FFF_EN		BIT(2)
+#define   VC5_DROP_VTABLE_MISS		BIT(3)
+
+/* VLAN Control 6 (8 bit) */
+#define B53_VLAN_CTRL6			0x07
+#define B53_VLAN_CTRL6_63XX		0x08
+
+/* VLAN Table Access Register (16 bit) */
+#define B53_VLAN_TABLE_ACCESS_25	0x06	/* BCM5325E/5350 */
+#define B53_VLAN_TABLE_ACCESS_65	0x08	/* BCM5365 */
+#define   VTA_VID_LOW_MASK_25		0xf
+#define   VTA_VID_LOW_MASK_65		0xff
+#define   VTA_VID_HIGH_S_25		4
+#define   VTA_VID_HIGH_S_65		8
+#define   VTA_VID_HIGH_MASK_25		(0xff << VTA_VID_HIGH_S_25E)
+#define   VTA_VID_HIGH_MASK_65		(0xf << VTA_VID_HIGH_S_65)
+#define   VTA_RW_STATE			BIT(12)
+#define   VTA_RW_STATE_RD		0
+#define   VTA_RW_STATE_WR		BIT(12)
+#define   VTA_RW_OP_EN			BIT(13)
+
+/* VLAN Read/Write Registers for (16/32 bit) */
+#define B53_VLAN_WRITE_25		0x08
+#define B53_VLAN_WRITE_65		0x0a
+#define B53_VLAN_READ			0x0c
+#define   VA_MEMBER_MASK		0x3f
+#define   VA_UNTAG_S_25			6
+#define   VA_UNTAG_MASK_25		0x3f
+#define   VA_UNTAG_S_65			7
+#define   VA_UNTAG_MASK_65		0x1f
+#define   VA_VID_HIGH_S			12
+#define   VA_VID_HIGH_MASK		(0xffff << VA_VID_HIGH_S)
+#define   VA_VALID_25			BIT(20)
+#define   VA_VALID_25_R4		BIT(24)
+#define   VA_VALID_65			BIT(14)
+
+/* VLAN Port Default Tag (16 bit) */
+#define B53_VLAN_PORT_DEF_TAG(i)	(0x10 + 2 * (i))
+
+/*************************************************************************
+ * Jumbo Frame Page Registers
+ *************************************************************************/
+
+/* Jumbo Enable Port Mask (bit i == port i enabled) (32 bit) */
+#define B53_JUMBO_PORT_MASK		0x01
+#define B53_JUMBO_PORT_MASK_63XX	0x04
+#define   JPM_10_100_JUMBO_EN		BIT(24) /* GigE always enabled */
+
+/* Good Frame Max Size without 802.1Q TAG (16 bit) */
+#define B53_JUMBO_MAX_SIZE		0x05
+#define B53_JUMBO_MAX_SIZE_63XX		0x08
+#define   JMS_MIN_SIZE			1518
+#define   JMS_MAX_SIZE			9724
+
+/*************************************************************************
+ * CFP Configuration Page Registers
+ *************************************************************************/
+
+/* CFP Control Register with ports map (8 bit) */
+#define B53_CFP_CTRL			0x00
+
+#endif /* !__B53_REGS_H */
diff --git a/drivers/net/dsa/b53/b53_spi.c b/drivers/net/dsa/b53/b53_spi.c
new file mode 100644
index 0000000..2bda0b5
--- /dev/null
+++ b/drivers/net/dsa/b53/b53_spi.c
@@ -0,0 +1,331 @@
+/*
+ * B53 register access through SPI
+ *
+ * Copyright (C) 2011-2013 Jonas Gorski <jogo@openwrt.org>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include <asm/unaligned.h>
+
+#include <linux/delay.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/spi/spi.h>
+#include <linux/platform_data/b53.h>
+
+#include "b53_priv.h"
+
+#define B53_SPI_DATA		0xf0
+
+#define B53_SPI_STATUS		0xfe
+#define B53_SPI_CMD_SPIF	BIT(7)
+#define B53_SPI_CMD_RACK	BIT(5)
+
+#define B53_SPI_CMD_READ	0x00
+#define B53_SPI_CMD_WRITE	0x01
+#define B53_SPI_CMD_NORMAL	0x60
+#define B53_SPI_CMD_FAST	0x10
+
+#define B53_SPI_PAGE_SELECT	0xff
+
+static inline int b53_spi_read_reg(struct spi_device *spi, u8 reg, u8 *val,
+				   unsigned int len)
+{
+	u8 txbuf[2];
+
+	txbuf[0] = B53_SPI_CMD_NORMAL | B53_SPI_CMD_READ;
+	txbuf[1] = reg;
+
+	return spi_write_then_read(spi, txbuf, 2, val, len);
+}
+
+static inline int b53_spi_clear_status(struct spi_device *spi)
+{
+	unsigned int i;
+	u8 rxbuf;
+	int ret;
+
+	for (i = 0; i < 10; i++) {
+		ret = b53_spi_read_reg(spi, B53_SPI_STATUS, &rxbuf, 1);
+		if (ret)
+			return ret;
+
+		if (!(rxbuf & B53_SPI_CMD_SPIF))
+			break;
+
+		mdelay(1);
+	}
+
+	if (i == 10)
+		return -EIO;
+
+	return 0;
+}
+
+static inline int b53_spi_set_page(struct spi_device *spi, u8 page)
+{
+	u8 txbuf[3];
+
+	txbuf[0] = B53_SPI_CMD_NORMAL | B53_SPI_CMD_WRITE;
+	txbuf[1] = B53_SPI_PAGE_SELECT;
+	txbuf[2] = page;
+
+	return spi_write(spi, txbuf, sizeof(txbuf));
+}
+
+static inline int b53_prepare_reg_access(struct spi_device *spi, u8 page)
+{
+	int ret = b53_spi_clear_status(spi);
+
+	if (ret)
+		return ret;
+
+	return b53_spi_set_page(spi, page);
+}
+
+static int b53_spi_prepare_reg_read(struct spi_device *spi, u8 reg)
+{
+	u8 rxbuf;
+	int retry_count;
+	int ret;
+
+	ret = b53_spi_read_reg(spi, reg, &rxbuf, 1);
+	if (ret)
+		return ret;
+
+	for (retry_count = 0; retry_count < 10; retry_count++) {
+		ret = b53_spi_read_reg(spi, B53_SPI_STATUS, &rxbuf, 1);
+		if (ret)
+			return ret;
+
+		if (rxbuf & B53_SPI_CMD_RACK)
+			break;
+
+		mdelay(1);
+	}
+
+	if (retry_count == 10)
+		return -EIO;
+
+	return 0;
+}
+
+static int b53_spi_read(struct b53_device *dev, u8 page, u8 reg, u8 *data,
+			unsigned int len)
+{
+	struct spi_device *spi = dev->priv;
+	int ret;
+
+	ret = b53_prepare_reg_access(spi, page);
+	if (ret)
+		return ret;
+
+	ret = b53_spi_prepare_reg_read(spi, reg);
+	if (ret)
+		return ret;
+
+	return b53_spi_read_reg(spi, B53_SPI_DATA, data, len);
+}
+
+static int b53_spi_read8(struct b53_device *dev, u8 page, u8 reg, u8 *val)
+{
+	return b53_spi_read(dev, page, reg, val, 1);
+}
+
+static int b53_spi_read16(struct b53_device *dev, u8 page, u8 reg, u16 *val)
+{
+	int ret = b53_spi_read(dev, page, reg, (u8 *)val, 2);
+
+	if (!ret)
+		*val = le16_to_cpu(*val);
+
+	return ret;
+}
+
+static int b53_spi_read32(struct b53_device *dev, u8 page, u8 reg, u32 *val)
+{
+	int ret = b53_spi_read(dev, page, reg, (u8 *)val, 4);
+
+	if (!ret)
+		*val = le32_to_cpu(*val);
+
+	return ret;
+}
+
+static int b53_spi_read48(struct b53_device *dev, u8 page, u8 reg, u64 *val)
+{
+	int ret;
+
+	*val = 0;
+	ret = b53_spi_read(dev, page, reg, (u8 *)val, 6);
+	if (!ret)
+		*val = le64_to_cpu(*val);
+
+	return ret;
+}
+
+static int b53_spi_read64(struct b53_device *dev, u8 page, u8 reg, u64 *val)
+{
+	int ret = b53_spi_read(dev, page, reg, (u8 *)val, 8);
+
+	if (!ret)
+		*val = le64_to_cpu(*val);
+
+	return ret;
+}
+
+static int b53_spi_write8(struct b53_device *dev, u8 page, u8 reg, u8 value)
+{
+	struct spi_device *spi = dev->priv;
+	int ret;
+	u8 txbuf[3];
+
+	ret = b53_prepare_reg_access(spi, page);
+	if (ret)
+		return ret;
+
+	txbuf[0] = B53_SPI_CMD_NORMAL | B53_SPI_CMD_WRITE;
+	txbuf[1] = reg;
+	txbuf[2] = value;
+
+	return spi_write(spi, txbuf, sizeof(txbuf));
+}
+
+static int b53_spi_write16(struct b53_device *dev, u8 page, u8 reg, u16 value)
+{
+	struct spi_device *spi = dev->priv;
+	int ret;
+	u8 txbuf[4];
+
+	ret = b53_prepare_reg_access(spi, page);
+	if (ret)
+		return ret;
+
+	txbuf[0] = B53_SPI_CMD_NORMAL | B53_SPI_CMD_WRITE;
+	txbuf[1] = reg;
+	put_unaligned_le16(value, &txbuf[2]);
+
+	return spi_write(spi, txbuf, sizeof(txbuf));
+}
+
+static int b53_spi_write32(struct b53_device *dev, u8 page, u8 reg, u32 value)
+{
+	struct spi_device *spi = dev->priv;
+	int ret;
+	u8 txbuf[6];
+
+	ret = b53_prepare_reg_access(spi, page);
+	if (ret)
+		return ret;
+
+	txbuf[0] = B53_SPI_CMD_NORMAL | B53_SPI_CMD_WRITE;
+	txbuf[1] = reg;
+	put_unaligned_le32(value, &txbuf[2]);
+
+	return spi_write(spi, txbuf, sizeof(txbuf));
+}
+
+static int b53_spi_write48(struct b53_device *dev, u8 page, u8 reg, u64 value)
+{
+	struct spi_device *spi = dev->priv;
+	int ret;
+	u8 txbuf[10];
+
+	ret = b53_prepare_reg_access(spi, page);
+	if (ret)
+		return ret;
+
+	txbuf[0] = B53_SPI_CMD_NORMAL | B53_SPI_CMD_WRITE;
+	txbuf[1] = reg;
+	put_unaligned_le64(value, &txbuf[2]);
+
+	return spi_write(spi, txbuf, sizeof(txbuf) - 2);
+}
+
+static int b53_spi_write64(struct b53_device *dev, u8 page, u8 reg, u64 value)
+{
+	struct spi_device *spi = dev->priv;
+	int ret;
+	u8 txbuf[10];
+
+	ret = b53_prepare_reg_access(spi, page);
+	if (ret)
+		return ret;
+
+	txbuf[0] = B53_SPI_CMD_NORMAL | B53_SPI_CMD_WRITE;
+	txbuf[1] = reg;
+	put_unaligned_le64(value, &txbuf[2]);
+
+	return spi_write(spi, txbuf, sizeof(txbuf));
+}
+
+static struct b53_io_ops b53_spi_ops = {
+	.read8 = b53_spi_read8,
+	.read16 = b53_spi_read16,
+	.read32 = b53_spi_read32,
+	.read48 = b53_spi_read48,
+	.read64 = b53_spi_read64,
+	.write8 = b53_spi_write8,
+	.write16 = b53_spi_write16,
+	.write32 = b53_spi_write32,
+	.write48 = b53_spi_write48,
+	.write64 = b53_spi_write64,
+};
+
+static int b53_spi_probe(struct spi_device *spi)
+{
+	struct b53_device *dev;
+	int ret;
+
+	dev = b53_switch_alloc(&spi->dev, &b53_spi_ops, spi);
+	if (!dev)
+		return -ENOMEM;
+
+	if (spi->dev.platform_data)
+		dev->pdata = spi->dev.platform_data;
+
+	ret = b53_switch_register(dev);
+	if (ret)
+		return ret;
+
+	spi_set_drvdata(spi, dev);
+
+	return 0;
+}
+
+static int b53_spi_remove(struct spi_device *spi)
+{
+	struct b53_device *dev = spi_get_drvdata(spi);
+
+	if (dev)
+		b53_switch_remove(dev);
+
+	return 0;
+}
+
+static struct spi_driver b53_spi_driver = {
+	.driver = {
+		.name	= "b53-switch",
+		.bus	= &spi_bus_type,
+		.owner	= THIS_MODULE,
+	},
+	.probe	= b53_spi_probe,
+	.remove	= b53_spi_remove,
+};
+
+module_spi_driver(b53_spi_driver);
+
+MODULE_AUTHOR("Jonas Gorski <jogo@openwrt.org>");
+MODULE_DESCRIPTION("B53 SPI access driver");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/dsa/b53/b53_srab.c b/drivers/net/dsa/b53/b53_srab.c
new file mode 100644
index 0000000..70fd472
--- /dev/null
+++ b/drivers/net/dsa/b53/b53_srab.c
@@ -0,0 +1,415 @@
+/*
+ * B53 register access through Switch Register Access Bridge Registers
+ *
+ * Copyright (C) 2013 Hauke Mehrtens <hauke@hauke-m.de>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/platform_device.h>
+#include <linux/platform_data/b53.h>
+
+#include "b53_priv.h"
+
+/* command and status register of the SRAB */
+#define B53_SRAB_CMDSTAT		0x2c
+#define  B53_SRAB_CMDSTAT_RST		BIT(2)
+#define  B53_SRAB_CMDSTAT_WRITE		BIT(1)
+#define  B53_SRAB_CMDSTAT_GORDYN	BIT(0)
+#define  B53_SRAB_CMDSTAT_PAGE		24
+#define  B53_SRAB_CMDSTAT_REG		16
+
+/* high order word of write data to switch registe */
+#define B53_SRAB_WD_H			0x30
+
+/* low order word of write data to switch registe */
+#define B53_SRAB_WD_L			0x34
+
+/* high order word of read data from switch register */
+#define B53_SRAB_RD_H			0x38
+
+/* low order word of read data from switch register */
+#define B53_SRAB_RD_L			0x3c
+
+/* command and status register of the SRAB */
+#define B53_SRAB_CTRLS			0x40
+#define  B53_SRAB_CTRLS_RCAREQ		BIT(3)
+#define  B53_SRAB_CTRLS_RCAGNT		BIT(4)
+#define  B53_SRAB_CTRLS_SW_INIT_DONE	BIT(6)
+
+/* the register captures interrupt pulses from the switch */
+#define B53_SRAB_INTR			0x44
+#define  B53_SRAB_INTR_P(x)		BIT(x)
+#define  B53_SRAB_SWITCH_PHY		BIT(8)
+#define  B53_SRAB_1588_SYNC		BIT(9)
+#define  B53_SRAB_IMP1_SLEEP_TIMER	BIT(10)
+#define  B53_SRAB_P7_SLEEP_TIMER	BIT(11)
+#define  B53_SRAB_IMP0_SLEEP_TIMER	BIT(12)
+
+struct b53_srab_priv {
+	void __iomem *regs;
+};
+
+static int b53_srab_request_grant(struct b53_device *dev)
+{
+	struct b53_srab_priv *priv = dev->priv;
+	u8 __iomem *regs = priv->regs;
+	u32 ctrls;
+	int i;
+
+	ctrls = readl(regs + B53_SRAB_CTRLS);
+	ctrls |= B53_SRAB_CTRLS_RCAREQ;
+	writel(ctrls, regs + B53_SRAB_CTRLS);
+
+	for (i = 0; i < 20; i++) {
+		ctrls = readl(regs + B53_SRAB_CTRLS);
+		if (ctrls & B53_SRAB_CTRLS_RCAGNT)
+			break;
+		usleep_range(10, 100);
+	}
+	if (WARN_ON(i == 5))
+		return -EIO;
+
+	return 0;
+}
+
+static void b53_srab_release_grant(struct b53_device *dev)
+{
+	struct b53_srab_priv *priv = dev->priv;
+	u8 __iomem *regs = priv->regs;
+	u32 ctrls;
+
+	ctrls = readl(regs + B53_SRAB_CTRLS);
+	ctrls &= ~B53_SRAB_CTRLS_RCAREQ;
+	writel(ctrls, regs + B53_SRAB_CTRLS);
+}
+
+static int b53_srab_op(struct b53_device *dev, u8 page, u8 reg, u32 op)
+{
+	struct b53_srab_priv *priv = dev->priv;
+	u8 __iomem *regs = priv->regs;
+	int i;
+	u32 cmdstat;
+
+	/* set register address */
+	cmdstat = (page << B53_SRAB_CMDSTAT_PAGE) |
+		  (reg << B53_SRAB_CMDSTAT_REG) |
+		  B53_SRAB_CMDSTAT_GORDYN |
+		  op;
+	writel(cmdstat, regs + B53_SRAB_CMDSTAT);
+
+	/* check if operation completed */
+	for (i = 0; i < 5; ++i) {
+		cmdstat = readl(regs + B53_SRAB_CMDSTAT);
+		if (!(cmdstat & B53_SRAB_CMDSTAT_GORDYN))
+			break;
+		usleep_range(10, 100);
+	}
+
+	if (WARN_ON(i == 5))
+		return -EIO;
+
+	return 0;
+}
+
+static int b53_srab_read8(struct b53_device *dev, u8 page, u8 reg, u8 *val)
+{
+	struct b53_srab_priv *priv = dev->priv;
+	u8 __iomem *regs = priv->regs;
+	int ret = 0;
+
+	ret = b53_srab_request_grant(dev);
+	if (ret)
+		goto err;
+
+	ret = b53_srab_op(dev, page, reg, 0);
+	if (ret)
+		goto err;
+
+	*val = readl(regs + B53_SRAB_RD_L) & 0xff;
+
+err:
+	b53_srab_release_grant(dev);
+
+	return ret;
+}
+
+static int b53_srab_read16(struct b53_device *dev, u8 page, u8 reg, u16 *val)
+{
+	struct b53_srab_priv *priv = dev->priv;
+	u8 __iomem *regs = priv->regs;
+	int ret = 0;
+
+	ret = b53_srab_request_grant(dev);
+	if (ret)
+		goto err;
+
+	ret = b53_srab_op(dev, page, reg, 0);
+	if (ret)
+		goto err;
+
+	*val = readl(regs + B53_SRAB_RD_L) & 0xffff;
+
+err:
+	b53_srab_release_grant(dev);
+
+	return ret;
+}
+
+static int b53_srab_read32(struct b53_device *dev, u8 page, u8 reg, u32 *val)
+{
+	struct b53_srab_priv *priv = dev->priv;
+	u8 __iomem *regs = priv->regs;
+	int ret = 0;
+
+	ret = b53_srab_request_grant(dev);
+	if (ret)
+		goto err;
+
+	ret = b53_srab_op(dev, page, reg, 0);
+	if (ret)
+		goto err;
+
+	*val = readl(regs + B53_SRAB_RD_L);
+
+err:
+	b53_srab_release_grant(dev);
+
+	return ret;
+}
+
+static int b53_srab_read48(struct b53_device *dev, u8 page, u8 reg, u64 *val)
+{
+	struct b53_srab_priv *priv = dev->priv;
+	u8 __iomem *regs = priv->regs;
+	int ret = 0;
+
+	ret = b53_srab_request_grant(dev);
+	if (ret)
+		goto err;
+
+	ret = b53_srab_op(dev, page, reg, 0);
+	if (ret)
+		goto err;
+
+	*val = readl(regs + B53_SRAB_RD_L);
+	*val += ((u64)readl(regs + B53_SRAB_RD_H) & 0xffff) << 32;
+
+err:
+	b53_srab_release_grant(dev);
+
+	return ret;
+}
+
+static int b53_srab_read64(struct b53_device *dev, u8 page, u8 reg, u64 *val)
+{
+	struct b53_srab_priv *priv = dev->priv;
+	u8 __iomem *regs = priv->regs;
+	int ret = 0;
+
+	ret = b53_srab_request_grant(dev);
+	if (ret)
+		goto err;
+
+	ret = b53_srab_op(dev, page, reg, 0);
+	if (ret)
+		goto err;
+
+	*val = readl(regs + B53_SRAB_RD_L);
+	*val += (u64)readl(regs + B53_SRAB_RD_H) << 32;
+
+err:
+	b53_srab_release_grant(dev);
+
+	return ret;
+}
+
+static int b53_srab_write8(struct b53_device *dev, u8 page, u8 reg, u8 value)
+{
+	struct b53_srab_priv *priv = dev->priv;
+	u8 __iomem *regs = priv->regs;
+	int ret = 0;
+
+	ret = b53_srab_request_grant(dev);
+	if (ret)
+		goto err;
+
+	writel(value, regs + B53_SRAB_WD_L);
+
+	ret = b53_srab_op(dev, page, reg, B53_SRAB_CMDSTAT_WRITE);
+
+err:
+	b53_srab_release_grant(dev);
+
+	return ret;
+}
+
+static int b53_srab_write16(struct b53_device *dev, u8 page, u8 reg,
+			    u16 value)
+{
+	struct b53_srab_priv *priv = dev->priv;
+	u8 __iomem *regs = priv->regs;
+	int ret = 0;
+
+	ret = b53_srab_request_grant(dev);
+	if (ret)
+		goto err;
+
+	writel(value, regs + B53_SRAB_WD_L);
+
+	ret = b53_srab_op(dev, page, reg, B53_SRAB_CMDSTAT_WRITE);
+
+err:
+	b53_srab_release_grant(dev);
+
+	return ret;
+}
+
+static int b53_srab_write32(struct b53_device *dev, u8 page, u8 reg,
+			    u32 value)
+{
+	struct b53_srab_priv *priv = dev->priv;
+	u8 __iomem *regs = priv->regs;
+	int ret = 0;
+
+	ret = b53_srab_request_grant(dev);
+	if (ret)
+		goto err;
+
+	writel(value, regs + B53_SRAB_WD_L);
+
+	ret = b53_srab_op(dev, page, reg, B53_SRAB_CMDSTAT_WRITE);
+
+err:
+	b53_srab_release_grant(dev);
+
+	return ret;
+}
+
+static int b53_srab_write48(struct b53_device *dev, u8 page, u8 reg,
+			    u64 value)
+{
+	struct b53_srab_priv *priv = dev->priv;
+	u8 __iomem *regs = priv->regs;
+	int ret = 0;
+
+	ret = b53_srab_request_grant(dev);
+	if (ret)
+		goto err;
+
+	writel((u32)value, regs + B53_SRAB_WD_L);
+	writel((u16)(value >> 32), regs + B53_SRAB_WD_H);
+
+	ret = b53_srab_op(dev, page, reg, B53_SRAB_CMDSTAT_WRITE);
+
+err:
+	b53_srab_release_grant(dev);
+
+	return ret;
+}
+
+static int b53_srab_write64(struct b53_device *dev, u8 page, u8 reg,
+			    u64 value)
+{
+	struct b53_srab_priv *priv = dev->priv;
+	u8 __iomem *regs = priv->regs;
+	int ret = 0;
+
+	ret = b53_srab_request_grant(dev);
+	if (ret)
+		goto err;
+
+	writel((u32)value, regs + B53_SRAB_WD_L);
+	writel((u32)(value >> 32), regs + B53_SRAB_WD_H);
+
+	ret = b53_srab_op(dev, page, reg, B53_SRAB_CMDSTAT_WRITE);
+
+err:
+	b53_srab_release_grant(dev);
+
+	return ret;
+}
+
+static struct b53_io_ops b53_srab_ops = {
+	.read8 = b53_srab_read8,
+	.read16 = b53_srab_read16,
+	.read32 = b53_srab_read32,
+	.read48 = b53_srab_read48,
+	.read64 = b53_srab_read64,
+	.write8 = b53_srab_write8,
+	.write16 = b53_srab_write16,
+	.write32 = b53_srab_write32,
+	.write48 = b53_srab_write48,
+	.write64 = b53_srab_write64,
+};
+
+static int b53_srab_probe(struct platform_device *pdev)
+{
+	struct b53_srab_priv *priv;
+	struct b53_device *dev;
+	struct resource *r;
+
+	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	priv->regs = devm_ioremap_resource(&pdev->dev, r);
+	if (IS_ERR(priv->regs))
+		return -ENOMEM;
+
+	dev = b53_switch_alloc(&pdev->dev, &b53_srab_ops, priv);
+	if (!dev)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, dev);
+
+	return b53_switch_register(dev);
+}
+
+static int b53_srab_remove(struct platform_device *pdev)
+{
+	struct b53_device *dev = platform_get_drvdata(pdev);
+
+	if (dev)
+		b53_switch_remove(dev);
+
+	return 0;
+}
+
+static const struct of_device_id b53_srab_of_match[] = {
+	{ .compatible = "brcm,bcm53010-srab" },
+	{ .compatible = "brcm,bcm53011-srab" },
+	{ .compatible = "brcm,bcm53012-srab" },
+	{ .compatible = "brcm,bcm53018-srab" },
+	{ .compatible = "brcm,bcm53019-srab" },
+	{ .compatible = "brcm,bcm5301x-srab" },
+	{ /* sentinel */ },
+};
+
+static struct platform_driver b53_srab_driver = {
+	.probe = b53_srab_probe,
+	.remove = b53_srab_remove,
+	.driver = {
+		.name = "b53-srab-switch",
+		.of_match_table = b53_srab_of_match,
+	},
+};
+
+module_platform_driver(b53_srab_driver);
+MODULE_AUTHOR("Hauke Mehrtens <hauke@hauke-m.de>");
+MODULE_DESCRIPTION("B53 Switch Register Access Bridge Registers (SRAB) access driver");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 10ddd5a..cd1d630 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -22,6 +22,7 @@
 #include <linux/of_irq.h>
 #include <linux/of_address.h>
 #include <linux/of_net.h>
+#include <linux/of_mdio.h>
 #include <net/dsa.h>
 #include <linux/ethtool.h>
 #include <linux/if_bridge.h>
@@ -460,19 +461,13 @@
 	return 0;
 }
 
-/* Fast-ageing of ARL entries for a given port, equivalent to an ARL
- * flush for that port.
- */
-static int bcm_sf2_sw_fast_age_port(struct dsa_switch  *ds, int port)
+static int bcm_sf2_fast_age_op(struct bcm_sf2_priv *priv)
 {
-	struct bcm_sf2_priv *priv = ds_to_priv(ds);
 	unsigned int timeout = 1000;
 	u32 reg;
 
-	core_writel(priv, port, CORE_FAST_AGE_PORT);
-
 	reg = core_readl(priv, CORE_FAST_AGE_CTRL);
-	reg |= EN_AGE_PORT | EN_AGE_DYNAMIC | FAST_AGE_STR_DONE;
+	reg |= EN_AGE_PORT | EN_AGE_VLAN | EN_AGE_DYNAMIC | FAST_AGE_STR_DONE;
 	core_writel(priv, reg, CORE_FAST_AGE_CTRL);
 
 	do {
@@ -491,13 +486,98 @@
 	return 0;
 }
 
+/* Fast-ageing of ARL entries for a given port, equivalent to an ARL
+ * flush for that port.
+ */
+static int bcm_sf2_sw_fast_age_port(struct dsa_switch *ds, int port)
+{
+	struct bcm_sf2_priv *priv = ds_to_priv(ds);
+
+	core_writel(priv, port, CORE_FAST_AGE_PORT);
+
+	return bcm_sf2_fast_age_op(priv);
+}
+
+static int bcm_sf2_sw_fast_age_vlan(struct bcm_sf2_priv *priv, u16 vid)
+{
+	core_writel(priv, vid, CORE_FAST_AGE_VID);
+
+	return bcm_sf2_fast_age_op(priv);
+}
+
+static int bcm_sf2_vlan_op_wait(struct bcm_sf2_priv *priv)
+{
+	unsigned int timeout = 10;
+	u32 reg;
+
+	do {
+		reg = core_readl(priv, CORE_ARLA_VTBL_RWCTRL);
+		if (!(reg & ARLA_VTBL_STDN))
+			return 0;
+
+		usleep_range(1000, 2000);
+	} while (timeout--);
+
+	return -ETIMEDOUT;
+}
+
+static int bcm_sf2_vlan_op(struct bcm_sf2_priv *priv, u8 op)
+{
+	core_writel(priv, ARLA_VTBL_STDN | op, CORE_ARLA_VTBL_RWCTRL);
+
+	return bcm_sf2_vlan_op_wait(priv);
+}
+
+static void bcm_sf2_set_vlan_entry(struct bcm_sf2_priv *priv, u16 vid,
+				   struct bcm_sf2_vlan *vlan)
+{
+	int ret;
+
+	core_writel(priv, vid & VTBL_ADDR_INDEX_MASK, CORE_ARLA_VTBL_ADDR);
+	core_writel(priv, vlan->untag << UNTAG_MAP_SHIFT | vlan->members,
+		    CORE_ARLA_VTBL_ENTRY);
+
+	ret = bcm_sf2_vlan_op(priv, ARLA_VTBL_CMD_WRITE);
+	if (ret)
+		pr_err("failed to write VLAN entry\n");
+}
+
+static int bcm_sf2_get_vlan_entry(struct bcm_sf2_priv *priv, u16 vid,
+				  struct bcm_sf2_vlan *vlan)
+{
+	u32 entry;
+	int ret;
+
+	core_writel(priv, vid & VTBL_ADDR_INDEX_MASK, CORE_ARLA_VTBL_ADDR);
+
+	ret = bcm_sf2_vlan_op(priv, ARLA_VTBL_CMD_READ);
+	if (ret)
+		return ret;
+
+	entry = core_readl(priv, CORE_ARLA_VTBL_ENTRY);
+	vlan->members = entry & FWD_MAP_MASK;
+	vlan->untag = (entry >> UNTAG_MAP_SHIFT) & UNTAG_MAP_MASK;
+
+	return 0;
+}
+
 static int bcm_sf2_sw_br_join(struct dsa_switch *ds, int port,
 			      struct net_device *bridge)
 {
 	struct bcm_sf2_priv *priv = ds_to_priv(ds);
+	s8 cpu_port = ds->dst->cpu_port;
 	unsigned int i;
 	u32 reg, p_ctl;
 
+	/* Make this port leave the all VLANs join since we will have proper
+	 * VLAN entries from now on
+	 */
+	reg = core_readl(priv, CORE_JOIN_ALL_VLAN_EN);
+	reg &= ~BIT(port);
+	if ((reg & BIT(cpu_port)) == BIT(cpu_port))
+		reg &= ~BIT(cpu_port);
+	core_writel(priv, reg, CORE_JOIN_ALL_VLAN_EN);
+
 	priv->port_sts[port].bridge_dev = bridge;
 	p_ctl = core_readl(priv, CORE_PORT_VLAN_CTL_PORT(port));
 
@@ -529,6 +609,7 @@
 {
 	struct bcm_sf2_priv *priv = ds_to_priv(ds);
 	struct net_device *bridge = priv->port_sts[port].bridge_dev;
+	s8 cpu_port = ds->dst->cpu_port;
 	unsigned int i;
 	u32 reg, p_ctl;
 
@@ -552,6 +633,13 @@
 	core_writel(priv, p_ctl, CORE_PORT_VLAN_CTL_PORT(port));
 	priv->port_sts[port].vlan_ctl_mask = p_ctl;
 	priv->port_sts[port].bridge_dev = NULL;
+
+	/* Make this port join all VLANs without VLAN entries */
+	reg = core_readl(priv, CORE_JOIN_ALL_VLAN_EN);
+	reg |= BIT(port);
+	if (!(reg & BIT(cpu_port)))
+		reg |= BIT(cpu_port);
+	core_writel(priv, reg, CORE_JOIN_ALL_VLAN_EN);
 }
 
 static void bcm_sf2_sw_br_set_stp_state(struct dsa_switch *ds, int port,
@@ -804,7 +892,7 @@
 			       int (*cb)(struct switchdev_obj *obj))
 {
 	struct bcm_sf2_priv *priv = ds_to_priv(ds);
-	struct net_device *dev = ds->ports[port];
+	struct net_device *dev = ds->ports[port].netdev;
 	struct bcm_sf2_arl_entry results[2];
 	unsigned int count = 0;
 	int ret;
@@ -836,6 +924,66 @@
 	return 0;
 }
 
+static int bcm_sf2_sw_indir_rw(struct bcm_sf2_priv *priv, int op, int addr,
+			       int regnum, u16 val)
+{
+	int ret = 0;
+	u32 reg;
+
+	reg = reg_readl(priv, REG_SWITCH_CNTRL);
+	reg |= MDIO_MASTER_SEL;
+	reg_writel(priv, reg, REG_SWITCH_CNTRL);
+
+	/* Page << 8 | offset */
+	reg = 0x70;
+	reg <<= 2;
+	core_writel(priv, addr, reg);
+
+	/* Page << 8 | offset */
+	reg = 0x80 << 8 | regnum << 1;
+	reg <<= 2;
+
+	if (op)
+		ret = core_readl(priv, reg);
+	else
+		core_writel(priv, val, reg);
+
+	reg = reg_readl(priv, REG_SWITCH_CNTRL);
+	reg &= ~MDIO_MASTER_SEL;
+	reg_writel(priv, reg, REG_SWITCH_CNTRL);
+
+	return ret & 0xffff;
+}
+
+static int bcm_sf2_sw_mdio_read(struct mii_bus *bus, int addr, int regnum)
+{
+	struct bcm_sf2_priv *priv = bus->priv;
+
+	/* Intercept reads from Broadcom pseudo-PHY address, else, send
+	 * them to our master MDIO bus controller
+	 */
+	if (addr == BRCM_PSEUDO_PHY_ADDR && priv->indir_phy_mask & BIT(addr))
+		return bcm_sf2_sw_indir_rw(priv, 1, addr, regnum, 0);
+	else
+		return mdiobus_read(priv->master_mii_bus, addr, regnum);
+}
+
+static int bcm_sf2_sw_mdio_write(struct mii_bus *bus, int addr, int regnum,
+				 u16 val)
+{
+	struct bcm_sf2_priv *priv = bus->priv;
+
+	/* Intercept writes to the Broadcom pseudo-PHY address, else,
+	 * send them to our master MDIO bus controller
+	 */
+	if (addr == BRCM_PSEUDO_PHY_ADDR && priv->indir_phy_mask & BIT(addr))
+		bcm_sf2_sw_indir_rw(priv, 0, addr, regnum, val);
+	else
+		mdiobus_write(priv->master_mii_bus, addr, regnum, val);
+
+	return 0;
+}
+
 static irqreturn_t bcm_sf2_switch_0_isr(int irq, void *dev_id)
 {
 	struct bcm_sf2_priv *priv = dev_id;
@@ -932,133 +1080,70 @@
 	}
 }
 
-static int bcm_sf2_sw_setup(struct dsa_switch *ds)
+static int bcm_sf2_mdio_register(struct dsa_switch *ds)
 {
-	const char *reg_names[BCM_SF2_REGS_NUM] = BCM_SF2_REGS_NAME;
 	struct bcm_sf2_priv *priv = ds_to_priv(ds);
 	struct device_node *dn;
-	void __iomem **base;
-	unsigned int port;
-	unsigned int i;
-	u32 reg, rev;
-	int ret;
+	static int index;
+	int err;
 
-	spin_lock_init(&priv->indir_lock);
-	mutex_init(&priv->stats_mutex);
+	/* Find our integrated MDIO bus node */
+	dn = of_find_compatible_node(NULL, NULL, "brcm,unimac-mdio");
+	priv->master_mii_bus = of_mdio_find_bus(dn);
+	if (!priv->master_mii_bus)
+		return -EPROBE_DEFER;
 
-	/* All the interesting properties are at the parent device_node
-	 * level
-	 */
-	dn = ds->cd->of_node->parent;
-	bcm_sf2_identify_ports(priv, ds->cd->of_node);
+	get_device(&priv->master_mii_bus->dev);
+	priv->master_mii_dn = dn;
 
-	priv->irq0 = irq_of_parse_and_map(dn, 0);
-	priv->irq1 = irq_of_parse_and_map(dn, 1);
+	priv->slave_mii_bus = devm_mdiobus_alloc(ds->dev);
+	if (!priv->slave_mii_bus)
+		return -ENOMEM;
 
-	base = &priv->core;
-	for (i = 0; i < BCM_SF2_REGS_NUM; i++) {
-		*base = of_iomap(dn, i);
-		if (*base == NULL) {
-			pr_err("unable to find register: %s\n", reg_names[i]);
-			ret = -ENOMEM;
-			goto out_unmap;
-		}
-		base++;
-	}
+	priv->slave_mii_bus->priv = priv;
+	priv->slave_mii_bus->name = "sf2 slave mii";
+	priv->slave_mii_bus->read = bcm_sf2_sw_mdio_read;
+	priv->slave_mii_bus->write = bcm_sf2_sw_mdio_write;
+	snprintf(priv->slave_mii_bus->id, MII_BUS_ID_SIZE, "sf2-%d",
+		 index++);
+	priv->slave_mii_bus->dev.of_node = dn;
 
-	ret = bcm_sf2_sw_rst(priv);
-	if (ret) {
-		pr_err("unable to software reset switch: %d\n", ret);
-		goto out_unmap;
-	}
-
-	/* Disable all interrupts and request them */
-	bcm_sf2_intr_disable(priv);
-
-	ret = request_irq(priv->irq0, bcm_sf2_switch_0_isr, 0,
-			  "switch_0", priv);
-	if (ret < 0) {
-		pr_err("failed to request switch_0 IRQ\n");
-		goto out_unmap;
-	}
-
-	ret = request_irq(priv->irq1, bcm_sf2_switch_1_isr, 0,
-			  "switch_1", priv);
-	if (ret < 0) {
-		pr_err("failed to request switch_1 IRQ\n");
-		goto out_free_irq0;
-	}
-
-	/* Reset the MIB counters */
-	reg = core_readl(priv, CORE_GMNCFGCFG);
-	reg |= RST_MIB_CNT;
-	core_writel(priv, reg, CORE_GMNCFGCFG);
-	reg &= ~RST_MIB_CNT;
-	core_writel(priv, reg, CORE_GMNCFGCFG);
-
-	/* Get the maximum number of ports for this switch */
-	priv->hw_params.num_ports = core_readl(priv, CORE_IMP0_PRT_ID) + 1;
-	if (priv->hw_params.num_ports > DSA_MAX_PORTS)
-		priv->hw_params.num_ports = DSA_MAX_PORTS;
-
-	/* Assume a single GPHY setup if we can't read that property */
-	if (of_property_read_u32(dn, "brcm,num-gphy",
-				 &priv->hw_params.num_gphy))
-		priv->hw_params.num_gphy = 1;
-
-	/* Enable all valid ports and disable those unused */
-	for (port = 0; port < priv->hw_params.num_ports; port++) {
-		/* IMP port receives special treatment */
-		if ((1 << port) & ds->enabled_port_mask)
-			bcm_sf2_port_setup(ds, port, NULL);
-		else if (dsa_is_cpu_port(ds, port))
-			bcm_sf2_imp_setup(ds, port);
-		else
-			bcm_sf2_port_disable(ds, port, NULL);
-	}
-
-	/* Include the pseudo-PHY address and the broadcast PHY address to
-	 * divert reads towards our workaround. This is only required for
-	 * 7445D0, since 7445E0 disconnects the internal switch pseudo-PHY such
-	 * that we can use the regular SWITCH_MDIO master controller instead.
+	/* Include the pseudo-PHY address to divert reads towards our
+	 * workaround. This is only required for 7445D0, since 7445E0
+	 * disconnects the internal switch pseudo-PHY such that we can use the
+	 * regular SWITCH_MDIO master controller instead.
 	 *
-	 * By default, DSA initializes ds->phys_mii_mask to
-	 * ds->enabled_port_mask to have a 1:1 mapping between Port address
-	 * and PHY address in order to utilize the slave_mii_bus instance to
-	 * read from Port PHYs. This is not what we want here, so we
-	 * initialize phys_mii_mask 0 to always utilize the "master" MDIO
-	 * bus backed by the "mdio-unimac" driver.
+	 * Here we flag the pseudo PHY as needing special treatment and would
+	 * otherwise make all other PHY read/writes go to the master MDIO bus
+	 * controller that comes with this switch backed by the "mdio-unimac"
+	 * driver.
 	 */
 	if (of_machine_is_compatible("brcm,bcm7445d0"))
-		ds->phys_mii_mask |= ((1 << BRCM_PSEUDO_PHY_ADDR) | (1 << 0));
+		priv->indir_phy_mask |= (1 << BRCM_PSEUDO_PHY_ADDR);
 	else
-		ds->phys_mii_mask = 0;
+		priv->indir_phy_mask = 0;
 
-	rev = reg_readl(priv, REG_SWITCH_REVISION);
-	priv->hw_params.top_rev = (rev >> SWITCH_TOP_REV_SHIFT) &
-					SWITCH_TOP_REV_MASK;
-	priv->hw_params.core_rev = (rev & SF2_REV_MASK);
+	ds->phys_mii_mask = priv->indir_phy_mask;
+	ds->slave_mii_bus = priv->slave_mii_bus;
+	priv->slave_mii_bus->parent = ds->dev->parent;
+	priv->slave_mii_bus->phy_mask = ~priv->indir_phy_mask;
 
-	rev = reg_readl(priv, REG_PHY_REVISION);
-	priv->hw_params.gphy_rev = rev & PHY_REVISION_MASK;
+	if (dn)
+		err = of_mdiobus_register(priv->slave_mii_bus, dn);
+	else
+		err = mdiobus_register(priv->slave_mii_bus);
 
-	pr_info("Starfighter 2 top: %x.%02x, core: %x.%02x base: 0x%p, IRQs: %d, %d\n",
-		priv->hw_params.top_rev >> 8, priv->hw_params.top_rev & 0xff,
-		priv->hw_params.core_rev >> 8, priv->hw_params.core_rev & 0xff,
-		priv->core, priv->irq0, priv->irq1);
+	if (err)
+		of_node_put(dn);
 
-	return 0;
+	return err;
+}
 
-out_free_irq0:
-	free_irq(priv->irq0, priv);
-out_unmap:
-	base = &priv->core;
-	for (i = 0; i < BCM_SF2_REGS_NUM; i++) {
-		if (*base)
-			iounmap(*base);
-		base++;
-	}
-	return ret;
+static void bcm_sf2_mdio_unregister(struct bcm_sf2_priv *priv)
+{
+	mdiobus_unregister(priv->slave_mii_bus);
+	if (priv->master_mii_dn)
+		of_node_put(priv->master_mii_dn);
 }
 
 static int bcm_sf2_sw_set_addr(struct dsa_switch *ds, u8 *addr)
@@ -1078,68 +1163,6 @@
 	return priv->hw_params.gphy_rev;
 }
 
-static int bcm_sf2_sw_indir_rw(struct dsa_switch *ds, int op, int addr,
-			       int regnum, u16 val)
-{
-	struct bcm_sf2_priv *priv = ds_to_priv(ds);
-	int ret = 0;
-	u32 reg;
-
-	reg = reg_readl(priv, REG_SWITCH_CNTRL);
-	reg |= MDIO_MASTER_SEL;
-	reg_writel(priv, reg, REG_SWITCH_CNTRL);
-
-	/* Page << 8 | offset */
-	reg = 0x70;
-	reg <<= 2;
-	core_writel(priv, addr, reg);
-
-	/* Page << 8 | offset */
-	reg = 0x80 << 8 | regnum << 1;
-	reg <<= 2;
-
-	if (op)
-		ret = core_readl(priv, reg);
-	else
-		core_writel(priv, val, reg);
-
-	reg = reg_readl(priv, REG_SWITCH_CNTRL);
-	reg &= ~MDIO_MASTER_SEL;
-	reg_writel(priv, reg, REG_SWITCH_CNTRL);
-
-	return ret & 0xffff;
-}
-
-static int bcm_sf2_sw_phy_read(struct dsa_switch *ds, int addr, int regnum)
-{
-	/* Intercept reads from the MDIO broadcast address or Broadcom
-	 * pseudo-PHY address
-	 */
-	switch (addr) {
-	case 0:
-	case BRCM_PSEUDO_PHY_ADDR:
-		return bcm_sf2_sw_indir_rw(ds, 1, addr, regnum, 0);
-	default:
-		return 0xffff;
-	}
-}
-
-static int bcm_sf2_sw_phy_write(struct dsa_switch *ds, int addr, int regnum,
-				u16 val)
-{
-	/* Intercept writes to the MDIO broadcast address or Broadcom
-	 * pseudo-PHY address
-	 */
-	switch (addr) {
-	case 0:
-	case BRCM_PSEUDO_PHY_ADDR:
-		bcm_sf2_sw_indir_rw(ds, 0, addr, regnum, val);
-		break;
-	}
-
-	return 0;
-}
-
 static void bcm_sf2_sw_adjust_link(struct dsa_switch *ds, int port,
 				   struct phy_device *phydev)
 {
@@ -1248,7 +1271,7 @@
 		 * state machine and make it go in PHY_FORCING state instead.
 		 */
 		if (!status->link)
-			netif_carrier_off(ds->ports[port]);
+			netif_carrier_off(ds->ports[port].netdev);
 		status->duplex = 1;
 	} else {
 		status->link = 1;
@@ -1370,14 +1393,309 @@
 	return p->ethtool_ops->set_wol(p, wol);
 }
 
+static void bcm_sf2_enable_vlan(struct bcm_sf2_priv *priv, bool enable)
+{
+	u32 mgmt, vc0, vc1, vc4, vc5;
+
+	mgmt = core_readl(priv, CORE_SWMODE);
+	vc0 = core_readl(priv, CORE_VLAN_CTRL0);
+	vc1 = core_readl(priv, CORE_VLAN_CTRL1);
+	vc4 = core_readl(priv, CORE_VLAN_CTRL4);
+	vc5 = core_readl(priv, CORE_VLAN_CTRL5);
+
+	mgmt &= ~SW_FWDG_MODE;
+
+	if (enable) {
+		vc0 |= VLAN_EN | VLAN_LEARN_MODE_IVL;
+		vc1 |= EN_RSV_MCAST_UNTAG | EN_RSV_MCAST_FWDMAP;
+		vc4 &= ~(INGR_VID_CHK_MASK << INGR_VID_CHK_SHIFT);
+		vc4 |= INGR_VID_CHK_DROP;
+		vc5 |= DROP_VTABLE_MISS | EN_VID_FFF_FWD;
+	} else {
+		vc0 &= ~(VLAN_EN | VLAN_LEARN_MODE_IVL);
+		vc1 &= ~(EN_RSV_MCAST_UNTAG | EN_RSV_MCAST_FWDMAP);
+		vc4 &= ~(INGR_VID_CHK_MASK << INGR_VID_CHK_SHIFT);
+		vc5 &= ~(DROP_VTABLE_MISS | EN_VID_FFF_FWD);
+		vc4 |= INGR_VID_CHK_VID_VIOL_IMP;
+	}
+
+	core_writel(priv, vc0, CORE_VLAN_CTRL0);
+	core_writel(priv, vc1, CORE_VLAN_CTRL1);
+	core_writel(priv, 0, CORE_VLAN_CTRL3);
+	core_writel(priv, vc4, CORE_VLAN_CTRL4);
+	core_writel(priv, vc5, CORE_VLAN_CTRL5);
+	core_writel(priv, mgmt, CORE_SWMODE);
+}
+
+static void bcm_sf2_sw_configure_vlan(struct dsa_switch *ds)
+{
+	struct bcm_sf2_priv *priv = ds_to_priv(ds);
+	unsigned int port;
+
+	/* Clear all VLANs */
+	bcm_sf2_vlan_op(priv, ARLA_VTBL_CMD_CLEAR);
+
+	for (port = 0; port < priv->hw_params.num_ports; port++) {
+		if (!((1 << port) & ds->enabled_port_mask))
+			continue;
+
+		core_writel(priv, 1, CORE_DEFAULT_1Q_TAG_P(port));
+	}
+}
+
+static int bcm_sf2_sw_vlan_filtering(struct dsa_switch *ds, int port,
+				     bool vlan_filtering)
+{
+	return 0;
+}
+
+static int bcm_sf2_sw_vlan_prepare(struct dsa_switch *ds, int port,
+				   const struct switchdev_obj_port_vlan *vlan,
+				   struct switchdev_trans *trans)
+{
+	struct bcm_sf2_priv *priv = ds_to_priv(ds);
+
+	bcm_sf2_enable_vlan(priv, true);
+
+	return 0;
+}
+
+static void bcm_sf2_sw_vlan_add(struct dsa_switch *ds, int port,
+				const struct switchdev_obj_port_vlan *vlan,
+				struct switchdev_trans *trans)
+{
+	struct bcm_sf2_priv *priv = ds_to_priv(ds);
+	bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
+	bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
+	s8 cpu_port = ds->dst->cpu_port;
+	struct bcm_sf2_vlan *vl;
+	u16 vid;
+
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) {
+		vl = &priv->vlans[vid];
+
+		bcm_sf2_get_vlan_entry(priv, vid, vl);
+
+		vl->members |= BIT(port) | BIT(cpu_port);
+		if (untagged)
+			vl->untag |= BIT(port) | BIT(cpu_port);
+		else
+			vl->untag &= ~(BIT(port) | BIT(cpu_port));
+
+		bcm_sf2_set_vlan_entry(priv, vid, vl);
+		bcm_sf2_sw_fast_age_vlan(priv, vid);
+	}
+
+	if (pvid) {
+		core_writel(priv, vlan->vid_end, CORE_DEFAULT_1Q_TAG_P(port));
+		core_writel(priv, vlan->vid_end,
+			    CORE_DEFAULT_1Q_TAG_P(cpu_port));
+		bcm_sf2_sw_fast_age_vlan(priv, vid);
+	}
+}
+
+static int bcm_sf2_sw_vlan_del(struct dsa_switch *ds, int port,
+			       const struct switchdev_obj_port_vlan *vlan)
+{
+	struct bcm_sf2_priv *priv = ds_to_priv(ds);
+	bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
+	s8 cpu_port = ds->dst->cpu_port;
+	struct bcm_sf2_vlan *vl;
+	u16 vid, pvid;
+	int ret;
+
+	pvid = core_readl(priv, CORE_DEFAULT_1Q_TAG_P(port));
+
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) {
+		vl = &priv->vlans[vid];
+
+		ret = bcm_sf2_get_vlan_entry(priv, vid, vl);
+		if (ret)
+			return ret;
+
+		vl->members &= ~BIT(port);
+		if ((vl->members & BIT(cpu_port)) == BIT(cpu_port))
+			vl->members = 0;
+		if (pvid == vid)
+			pvid = 0;
+		if (untagged) {
+			vl->untag &= ~BIT(port);
+			if ((vl->untag & BIT(port)) == BIT(cpu_port))
+				vl->untag = 0;
+		}
+
+		bcm_sf2_set_vlan_entry(priv, vid, vl);
+		bcm_sf2_sw_fast_age_vlan(priv, vid);
+	}
+
+	core_writel(priv, pvid, CORE_DEFAULT_1Q_TAG_P(port));
+	core_writel(priv, pvid, CORE_DEFAULT_1Q_TAG_P(cpu_port));
+	bcm_sf2_sw_fast_age_vlan(priv, vid);
+
+	return 0;
+}
+
+static int bcm_sf2_sw_vlan_dump(struct dsa_switch *ds, int port,
+				struct switchdev_obj_port_vlan *vlan,
+				int (*cb)(struct switchdev_obj *obj))
+{
+	struct bcm_sf2_priv *priv = ds_to_priv(ds);
+	struct bcm_sf2_port_status *p = &priv->port_sts[port];
+	struct bcm_sf2_vlan *vl;
+	u16 vid, pvid;
+	int err = 0;
+
+	pvid = core_readl(priv, CORE_DEFAULT_1Q_TAG_P(port));
+
+	for (vid = 0; vid < VLAN_N_VID; vid++) {
+		vl = &priv->vlans[vid];
+
+		if (!(vl->members & BIT(port)))
+			continue;
+
+		vlan->vid_begin = vlan->vid_end = vid;
+		vlan->flags = 0;
+
+		if (vl->untag & BIT(port))
+			vlan->flags |= BRIDGE_VLAN_INFO_UNTAGGED;
+		if (p->pvid == vid)
+			vlan->flags |= BRIDGE_VLAN_INFO_PVID;
+
+		err = cb(&vlan->obj);
+		if (err)
+			break;
+	}
+
+	return err;
+}
+
+static int bcm_sf2_sw_setup(struct dsa_switch *ds)
+{
+	const char *reg_names[BCM_SF2_REGS_NUM] = BCM_SF2_REGS_NAME;
+	struct bcm_sf2_priv *priv = ds_to_priv(ds);
+	struct device_node *dn;
+	void __iomem **base;
+	unsigned int port;
+	unsigned int i;
+	u32 reg, rev;
+	int ret;
+
+	spin_lock_init(&priv->indir_lock);
+	mutex_init(&priv->stats_mutex);
+
+	/* All the interesting properties are at the parent device_node
+	 * level
+	 */
+	dn = ds->cd->of_node->parent;
+	bcm_sf2_identify_ports(priv, ds->cd->of_node);
+
+	priv->irq0 = irq_of_parse_and_map(dn, 0);
+	priv->irq1 = irq_of_parse_and_map(dn, 1);
+
+	base = &priv->core;
+	for (i = 0; i < BCM_SF2_REGS_NUM; i++) {
+		*base = of_iomap(dn, i);
+		if (*base == NULL) {
+			pr_err("unable to find register: %s\n", reg_names[i]);
+			ret = -ENOMEM;
+			goto out_unmap;
+		}
+		base++;
+	}
+
+	ret = bcm_sf2_sw_rst(priv);
+	if (ret) {
+		pr_err("unable to software reset switch: %d\n", ret);
+		goto out_unmap;
+	}
+
+	ret = bcm_sf2_mdio_register(ds);
+	if (ret) {
+		pr_err("failed to register MDIO bus\n");
+		goto out_unmap;
+	}
+
+	/* Disable all interrupts and request them */
+	bcm_sf2_intr_disable(priv);
+
+	ret = request_irq(priv->irq0, bcm_sf2_switch_0_isr, 0,
+			  "switch_0", priv);
+	if (ret < 0) {
+		pr_err("failed to request switch_0 IRQ\n");
+		goto out_unmap;
+	}
+
+	ret = request_irq(priv->irq1, bcm_sf2_switch_1_isr, 0,
+			  "switch_1", priv);
+	if (ret < 0) {
+		pr_err("failed to request switch_1 IRQ\n");
+		goto out_free_irq0;
+	}
+
+	/* Reset the MIB counters */
+	reg = core_readl(priv, CORE_GMNCFGCFG);
+	reg |= RST_MIB_CNT;
+	core_writel(priv, reg, CORE_GMNCFGCFG);
+	reg &= ~RST_MIB_CNT;
+	core_writel(priv, reg, CORE_GMNCFGCFG);
+
+	/* Get the maximum number of ports for this switch */
+	priv->hw_params.num_ports = core_readl(priv, CORE_IMP0_PRT_ID) + 1;
+	if (priv->hw_params.num_ports > DSA_MAX_PORTS)
+		priv->hw_params.num_ports = DSA_MAX_PORTS;
+
+	/* Assume a single GPHY setup if we can't read that property */
+	if (of_property_read_u32(dn, "brcm,num-gphy",
+				 &priv->hw_params.num_gphy))
+		priv->hw_params.num_gphy = 1;
+
+	/* Enable all valid ports and disable those unused */
+	for (port = 0; port < priv->hw_params.num_ports; port++) {
+		/* IMP port receives special treatment */
+		if ((1 << port) & ds->enabled_port_mask)
+			bcm_sf2_port_setup(ds, port, NULL);
+		else if (dsa_is_cpu_port(ds, port))
+			bcm_sf2_imp_setup(ds, port);
+		else
+			bcm_sf2_port_disable(ds, port, NULL);
+	}
+
+	bcm_sf2_sw_configure_vlan(ds);
+
+	rev = reg_readl(priv, REG_SWITCH_REVISION);
+	priv->hw_params.top_rev = (rev >> SWITCH_TOP_REV_SHIFT) &
+					SWITCH_TOP_REV_MASK;
+	priv->hw_params.core_rev = (rev & SF2_REV_MASK);
+
+	rev = reg_readl(priv, REG_PHY_REVISION);
+	priv->hw_params.gphy_rev = rev & PHY_REVISION_MASK;
+
+	pr_info("Starfighter 2 top: %x.%02x, core: %x.%02x base: 0x%p, IRQs: %d, %d\n",
+		priv->hw_params.top_rev >> 8, priv->hw_params.top_rev & 0xff,
+		priv->hw_params.core_rev >> 8, priv->hw_params.core_rev & 0xff,
+		priv->core, priv->irq0, priv->irq1);
+
+	return 0;
+
+out_free_irq0:
+	free_irq(priv->irq0, priv);
+out_unmap:
+	base = &priv->core;
+	for (i = 0; i < BCM_SF2_REGS_NUM; i++) {
+		if (*base)
+			iounmap(*base);
+		base++;
+	}
+	bcm_sf2_mdio_unregister(priv);
+	return ret;
+}
+
 static struct dsa_switch_driver bcm_sf2_switch_driver = {
 	.tag_protocol		= DSA_TAG_PROTO_BRCM,
 	.probe			= bcm_sf2_sw_drv_probe,
 	.setup			= bcm_sf2_sw_setup,
 	.set_addr		= bcm_sf2_sw_set_addr,
 	.get_phy_flags		= bcm_sf2_sw_get_phy_flags,
-	.phy_read		= bcm_sf2_sw_phy_read,
-	.phy_write		= bcm_sf2_sw_phy_write,
 	.get_strings		= bcm_sf2_sw_get_strings,
 	.get_ethtool_stats	= bcm_sf2_sw_get_ethtool_stats,
 	.get_sset_count		= bcm_sf2_sw_get_sset_count,
@@ -1398,6 +1716,11 @@
 	.port_fdb_add		= bcm_sf2_sw_fdb_add,
 	.port_fdb_del		= bcm_sf2_sw_fdb_del,
 	.port_fdb_dump		= bcm_sf2_sw_fdb_dump,
+	.port_vlan_filtering	= bcm_sf2_sw_vlan_filtering,
+	.port_vlan_prepare	= bcm_sf2_sw_vlan_prepare,
+	.port_vlan_add		= bcm_sf2_sw_vlan_add,
+	.port_vlan_del		= bcm_sf2_sw_vlan_del,
+	.port_vlan_dump		= bcm_sf2_sw_vlan_dump,
 };
 
 static int __init bcm_sf2_init(void)
diff --git a/drivers/net/dsa/bcm_sf2.h b/drivers/net/dsa/bcm_sf2.h
index 200b1f5..463bed8 100644
--- a/drivers/net/dsa/bcm_sf2.h
+++ b/drivers/net/dsa/bcm_sf2.h
@@ -21,6 +21,7 @@
 #include <linux/ethtool.h>
 #include <linux/types.h>
 #include <linux/bitops.h>
+#include <linux/if_vlan.h>
 
 #include <net/dsa.h>
 
@@ -50,6 +51,7 @@
 	struct ethtool_eee eee;
 
 	u32 vlan_ctl_mask;
+	u16 pvid;
 
 	struct net_device *bridge_dev;
 };
@@ -63,6 +65,11 @@
 	u8 is_static:1;
 };
 
+struct bcm_sf2_vlan {
+	u16 members;
+	u16 untag;
+};
+
 static inline void bcm_sf2_mac_from_u64(u64 src, u8 *dst)
 {
 	unsigned int i;
@@ -142,6 +149,15 @@
 
 	/* Bitmask of ports having an integrated PHY */
 	unsigned int			int_phy_mask;
+
+	/* Master and slave MDIO bus controller */
+	unsigned int			indir_phy_mask;
+	struct device_node		*master_mii_dn;
+	struct mii_bus			*slave_mii_bus;
+	struct mii_bus			*master_mii_bus;
+
+	/* Cache of programmed VLANs */
+	struct bcm_sf2_vlan		vlans[VLAN_N_VID];
 };
 
 struct bcm_sf2_hw_stats {
diff --git a/drivers/net/dsa/bcm_sf2_regs.h b/drivers/net/dsa/bcm_sf2_regs.h
index 97780d4..9f2a9cb 100644
--- a/drivers/net/dsa/bcm_sf2_regs.h
+++ b/drivers/net/dsa/bcm_sf2_regs.h
@@ -274,6 +274,23 @@
 #define CORE_ARLA_SRCH_RSLT_MACVID(x)	(CORE_ARLA_SRCH_RSLT_0_MACVID + ((x) * 0x40))
 #define CORE_ARLA_SRCH_RSLT(x)		(CORE_ARLA_SRCH_RSLT_0 + ((x) * 0x40))
 
+#define CORE_ARLA_VTBL_RWCTRL		0x1600
+#define  ARLA_VTBL_CMD_WRITE		0
+#define  ARLA_VTBL_CMD_READ		1
+#define  ARLA_VTBL_CMD_CLEAR		2
+#define  ARLA_VTBL_STDN			(1 << 7)
+
+#define CORE_ARLA_VTBL_ADDR		0x1604
+#define  VTBL_ADDR_INDEX_MASK		0xfff
+
+#define CORE_ARLA_VTBL_ENTRY		0x160c
+#define  FWD_MAP_MASK			0x1ff
+#define  UNTAG_MAP_MASK			0x1ff
+#define  UNTAG_MAP_SHIFT		9
+#define  MSTP_INDEX_MASK		0x7
+#define  MSTP_INDEX_SHIFT		18
+#define  FWD_MODE			(1 << 21)
+
 #define CORE_MEM_PSM_VDD_CTRL		0x2380
 #define  P_TXQ_PSM_VDD_SHIFT		2
 #define  P_TXQ_PSM_VDD_MASK		0x3
@@ -287,6 +304,59 @@
 #define CORE_PORT_VLAN_CTL_PORT(x)	(0xc400 + ((x) * 0x8))
 #define  PORT_VLAN_CTRL_MASK		0x1ff
 
+#define CORE_VLAN_CTRL0			0xd000
+#define  CHANGE_1P_VID_INNER		(1 << 0)
+#define  CHANGE_1P_VID_OUTER		(1 << 1)
+#define  CHANGE_1Q_VID			(1 << 3)
+#define  VLAN_LEARN_MODE_SVL		(0 << 5)
+#define  VLAN_LEARN_MODE_IVL		(3 << 5)
+#define  VLAN_EN			(1 << 7)
+
+#define CORE_VLAN_CTRL1			0xd004
+#define  EN_RSV_MCAST_FWDMAP		(1 << 2)
+#define  EN_RSV_MCAST_UNTAG		(1 << 3)
+#define  EN_IPMC_BYPASS_FWDMAP		(1 << 5)
+#define  EN_IPMC_BYPASS_UNTAG		(1 << 6)
+
+#define CORE_VLAN_CTRL2			0xd008
+#define  EN_MIIM_BYPASS_V_FWDMAP	(1 << 2)
+#define  EN_GMRP_GVRP_V_FWDMAP		(1 << 5)
+#define  EN_GMRP_GVRP_UNTAG_MAP		(1 << 6)
+
+#define CORE_VLAN_CTRL3			0xd00c
+#define  EN_DROP_NON1Q_MASK		0x1ff
+
+#define CORE_VLAN_CTRL4			0xd014
+#define  RESV_MCAST_FLOOD		(1 << 1)
+#define  EN_DOUBLE_TAG_MASK		0x3
+#define  EN_DOUBLE_TAG_SHIFT		2
+#define  EN_MGE_REV_GMRP		(1 << 4)
+#define  EN_MGE_REV_GVRP		(1 << 5)
+#define  INGR_VID_CHK_SHIFT		6
+#define  INGR_VID_CHK_MASK		0x3
+#define  INGR_VID_CHK_FWD		(0 << INGR_VID_CHK_SHIFT)
+#define  INGR_VID_CHK_DROP		(1 << INGR_VID_CHK_SHIFT)
+#define  INGR_VID_CHK_NO_CHK		(2 << INGR_VID_CHK_SHIFT)
+#define  INGR_VID_CHK_VID_VIOL_IMP	(3 << INGR_VID_CHK_SHIFT)
+
+#define CORE_VLAN_CTRL5			0xd018
+#define  EN_CPU_RX_BYP_INNER_CRCCHCK	(1 << 0)
+#define  EN_VID_FFF_FWD			(1 << 2)
+#define  DROP_VTABLE_MISS		(1 << 3)
+#define  EGRESS_DIR_FRM_BYP_TRUNK_EN	(1 << 4)
+#define  PRESV_NON1Q			(1 << 6)
+
+#define CORE_VLAN_CTRL6			0xd01c
+#define  STRICT_SFD_DETECT		(1 << 0)
+#define  DIS_ARL_BUST_LMIT		(1 << 4)
+
+#define CORE_DEFAULT_1Q_TAG_P(x)	(0xd040 + ((x) * 8))
+#define  CFI_SHIFT			12
+#define  PRI_SHIFT			13
+#define  PRI_MASK			0x7
+
+#define CORE_JOIN_ALL_VLAN_EN		0xd140
+
 #define CORE_EEE_EN_CTRL		0x24800
 #define CORE_EEE_LPI_INDICATE		0x24810
 
diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c
index ba9dfc9..9b116d8 100644
--- a/drivers/net/dsa/mv88e6xxx.c
+++ b/drivers/net/dsa/mv88e6xxx.c
@@ -21,6 +21,8 @@
 #include <linux/list.h>
 #include <linux/mdio.h>
 #include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/of_mdio.h>
 #include <linux/netdevice.h>
 #include <linux/gpio/consumer.h>
 #include <linux/phy.h>
@@ -28,29 +30,82 @@
 #include <net/switchdev.h>
 #include "mv88e6xxx.h"
 
-static void assert_smi_lock(struct mv88e6xxx_priv_state *ps)
+static void assert_reg_lock(struct mv88e6xxx_priv_state *ps)
 {
-	if (unlikely(!mutex_is_locked(&ps->smi_mutex))) {
-		dev_err(ps->dev, "SMI lock not held!\n");
+	if (unlikely(!mutex_is_locked(&ps->reg_lock))) {
+		dev_err(ps->dev, "Switch registers lock not held!\n");
 		dump_stack();
 	}
 }
 
-/* If the switch's ADDR[4:0] strap pins are strapped to zero, it will
- * use all 32 SMI bus addresses on its SMI bus, and all switch registers
- * will be directly accessible on some {device address,register address}
- * pair.  If the ADDR[4:0] pins are not strapped to zero, the switch
- * will only respond to SMI transactions to that specific address, and
- * an indirect addressing mechanism needs to be used to access its
- * registers.
+/* The switch ADDR[4:1] configuration pins define the chip SMI device address
+ * (ADDR[0] is always zero, thus only even SMI addresses can be strapped).
+ *
+ * When ADDR is all zero, the chip uses Single-chip Addressing Mode, assuming it
+ * is the only device connected to the SMI master. In this mode it responds to
+ * all 32 possible SMI addresses, and thus maps directly the internal devices.
+ *
+ * When ADDR is non-zero, the chip uses Multi-chip Addressing Mode, allowing
+ * multiple devices to share the SMI interface. In this mode it responds to only
+ * 2 registers, used to indirectly access the internal SMI devices.
  */
-static int mv88e6xxx_reg_wait_ready(struct mii_bus *bus, int sw_addr)
+
+static int mv88e6xxx_smi_read(struct mv88e6xxx_priv_state *ps,
+			      int addr, int reg, u16 *val)
+{
+	if (!ps->smi_ops)
+		return -EOPNOTSUPP;
+
+	return ps->smi_ops->read(ps, addr, reg, val);
+}
+
+static int mv88e6xxx_smi_write(struct mv88e6xxx_priv_state *ps,
+			       int addr, int reg, u16 val)
+{
+	if (!ps->smi_ops)
+		return -EOPNOTSUPP;
+
+	return ps->smi_ops->write(ps, addr, reg, val);
+}
+
+static int mv88e6xxx_smi_single_chip_read(struct mv88e6xxx_priv_state *ps,
+					  int addr, int reg, u16 *val)
+{
+	int ret;
+
+	ret = mdiobus_read_nested(ps->bus, addr, reg);
+	if (ret < 0)
+		return ret;
+
+	*val = ret & 0xffff;
+
+	return 0;
+}
+
+static int mv88e6xxx_smi_single_chip_write(struct mv88e6xxx_priv_state *ps,
+					   int addr, int reg, u16 val)
+{
+	int ret;
+
+	ret = mdiobus_write_nested(ps->bus, addr, reg, val);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static const struct mv88e6xxx_ops mv88e6xxx_smi_single_chip_ops = {
+	.read = mv88e6xxx_smi_single_chip_read,
+	.write = mv88e6xxx_smi_single_chip_write,
+};
+
+static int mv88e6xxx_smi_multi_chip_wait(struct mv88e6xxx_priv_state *ps)
 {
 	int ret;
 	int i;
 
 	for (i = 0; i < 16; i++) {
-		ret = mdiobus_read_nested(bus, sw_addr, SMI_CMD);
+		ret = mdiobus_read_nested(ps->bus, ps->sw_addr, SMI_CMD);
 		if (ret < 0)
 			return ret;
 
@@ -61,117 +116,144 @@
 	return -ETIMEDOUT;
 }
 
-static int __mv88e6xxx_reg_read(struct mii_bus *bus, int sw_addr, int addr,
-				int reg)
+static int mv88e6xxx_smi_multi_chip_read(struct mv88e6xxx_priv_state *ps,
+					 int addr, int reg, u16 *val)
 {
 	int ret;
 
-	if (sw_addr == 0)
-		return mdiobus_read_nested(bus, addr, reg);
-
 	/* Wait for the bus to become free. */
-	ret = mv88e6xxx_reg_wait_ready(bus, sw_addr);
+	ret = mv88e6xxx_smi_multi_chip_wait(ps);
 	if (ret < 0)
 		return ret;
 
 	/* Transmit the read command. */
-	ret = mdiobus_write_nested(bus, sw_addr, SMI_CMD,
+	ret = mdiobus_write_nested(ps->bus, ps->sw_addr, SMI_CMD,
 				   SMI_CMD_OP_22_READ | (addr << 5) | reg);
 	if (ret < 0)
 		return ret;
 
 	/* Wait for the read command to complete. */
-	ret = mv88e6xxx_reg_wait_ready(bus, sw_addr);
+	ret = mv88e6xxx_smi_multi_chip_wait(ps);
 	if (ret < 0)
 		return ret;
 
 	/* Read the data. */
-	ret = mdiobus_read_nested(bus, sw_addr, SMI_DATA);
+	ret = mdiobus_read_nested(ps->bus, ps->sw_addr, SMI_DATA);
 	if (ret < 0)
 		return ret;
 
-	return ret & 0xffff;
+	*val = ret & 0xffff;
+
+	return 0;
 }
 
-static int _mv88e6xxx_reg_read(struct mv88e6xxx_priv_state *ps,
-			       int addr, int reg)
+static int mv88e6xxx_smi_multi_chip_write(struct mv88e6xxx_priv_state *ps,
+					  int addr, int reg, u16 val)
 {
 	int ret;
 
-	assert_smi_lock(ps);
-
-	ret = __mv88e6xxx_reg_read(ps->bus, ps->sw_addr, addr, reg);
-	if (ret < 0)
-		return ret;
-
-	dev_dbg(ps->dev, "<- addr: 0x%.2x reg: 0x%.2x val: 0x%.4x\n",
-		addr, reg, ret);
-
-	return ret;
-}
-
-int mv88e6xxx_reg_read(struct mv88e6xxx_priv_state *ps, int addr, int reg)
-{
-	int ret;
-
-	mutex_lock(&ps->smi_mutex);
-	ret = _mv88e6xxx_reg_read(ps, addr, reg);
-	mutex_unlock(&ps->smi_mutex);
-
-	return ret;
-}
-
-static int __mv88e6xxx_reg_write(struct mii_bus *bus, int sw_addr, int addr,
-				 int reg, u16 val)
-{
-	int ret;
-
-	if (sw_addr == 0)
-		return mdiobus_write_nested(bus, addr, reg, val);
-
 	/* Wait for the bus to become free. */
-	ret = mv88e6xxx_reg_wait_ready(bus, sw_addr);
+	ret = mv88e6xxx_smi_multi_chip_wait(ps);
 	if (ret < 0)
 		return ret;
 
 	/* Transmit the data to write. */
-	ret = mdiobus_write_nested(bus, sw_addr, SMI_DATA, val);
+	ret = mdiobus_write_nested(ps->bus, ps->sw_addr, SMI_DATA, val);
 	if (ret < 0)
 		return ret;
 
 	/* Transmit the write command. */
-	ret = mdiobus_write_nested(bus, sw_addr, SMI_CMD,
+	ret = mdiobus_write_nested(ps->bus, ps->sw_addr, SMI_CMD,
 				   SMI_CMD_OP_22_WRITE | (addr << 5) | reg);
 	if (ret < 0)
 		return ret;
 
 	/* Wait for the write command to complete. */
-	ret = mv88e6xxx_reg_wait_ready(bus, sw_addr);
+	ret = mv88e6xxx_smi_multi_chip_wait(ps);
 	if (ret < 0)
 		return ret;
 
 	return 0;
 }
 
-static int _mv88e6xxx_reg_write(struct mv88e6xxx_priv_state *ps, int addr,
-				int reg, u16 val)
+static const struct mv88e6xxx_ops mv88e6xxx_smi_multi_chip_ops = {
+	.read = mv88e6xxx_smi_multi_chip_read,
+	.write = mv88e6xxx_smi_multi_chip_write,
+};
+
+static int mv88e6xxx_read(struct mv88e6xxx_priv_state *ps,
+			  int addr, int reg, u16 *val)
 {
-	assert_smi_lock(ps);
+	int err;
+
+	assert_reg_lock(ps);
+
+	err = mv88e6xxx_smi_read(ps, addr, reg, val);
+	if (err)
+		return err;
+
+	dev_dbg(ps->dev, "<- addr: 0x%.2x reg: 0x%.2x val: 0x%.4x\n",
+		addr, reg, *val);
+
+	return 0;
+}
+
+static int mv88e6xxx_write(struct mv88e6xxx_priv_state *ps,
+			   int addr, int reg, u16 val)
+{
+	int err;
+
+	assert_reg_lock(ps);
+
+	err = mv88e6xxx_smi_write(ps, addr, reg, val);
+	if (err)
+		return err;
 
 	dev_dbg(ps->dev, "-> addr: 0x%.2x reg: 0x%.2x val: 0x%.4x\n",
 		addr, reg, val);
 
-	return __mv88e6xxx_reg_write(ps->bus, ps->sw_addr, addr, reg, val);
+	return 0;
 }
 
-int mv88e6xxx_reg_write(struct mv88e6xxx_priv_state *ps, int addr,
-			int reg, u16 val)
+static int _mv88e6xxx_reg_read(struct mv88e6xxx_priv_state *ps,
+			       int addr, int reg)
+{
+	u16 val;
+	int err;
+
+	err = mv88e6xxx_read(ps, addr, reg, &val);
+	if (err)
+		return err;
+
+	return val;
+}
+
+static int mv88e6xxx_reg_read(struct mv88e6xxx_priv_state *ps, int addr,
+			      int reg)
 {
 	int ret;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&ps->reg_lock);
+	ret = _mv88e6xxx_reg_read(ps, addr, reg);
+	mutex_unlock(&ps->reg_lock);
+
+	return ret;
+}
+
+static int _mv88e6xxx_reg_write(struct mv88e6xxx_priv_state *ps, int addr,
+				int reg, u16 val)
+{
+	return mv88e6xxx_write(ps, addr, reg, val);
+}
+
+static int mv88e6xxx_reg_write(struct mv88e6xxx_priv_state *ps, int addr,
+			       int reg, u16 val)
+{
+	int ret;
+
+	mutex_lock(&ps->reg_lock);
 	ret = _mv88e6xxx_reg_write(ps, addr, reg, val);
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&ps->reg_lock);
 
 	return ret;
 }
@@ -228,7 +310,7 @@
 	return 0;
 }
 
-int mv88e6xxx_set_addr(struct dsa_switch *ds, u8 *addr)
+static int mv88e6xxx_set_addr(struct dsa_switch *ds, u8 *addr)
 {
 	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
 
@@ -238,16 +320,16 @@
 		return mv88e6xxx_set_addr_direct(ds, addr);
 }
 
-static int _mv88e6xxx_phy_read(struct mv88e6xxx_priv_state *ps, int addr,
-			       int regnum)
+static int mv88e6xxx_mdio_read_direct(struct mv88e6xxx_priv_state *ps,
+				      int addr, int regnum)
 {
 	if (addr >= 0)
 		return _mv88e6xxx_reg_read(ps, addr, regnum);
 	return 0xffff;
 }
 
-static int _mv88e6xxx_phy_write(struct mv88e6xxx_priv_state *ps, int addr,
-				int regnum, u16 val)
+static int mv88e6xxx_mdio_write_direct(struct mv88e6xxx_priv_state *ps,
+				       int addr, int regnum, u16 val)
 {
 	if (addr >= 0)
 		return _mv88e6xxx_reg_write(ps, addr, regnum, val);
@@ -288,18 +370,18 @@
 	int ret, err;
 	unsigned long timeout;
 
-	ret = mv88e6xxx_reg_read(ps, REG_GLOBAL, GLOBAL_CONTROL);
+	ret = _mv88e6xxx_reg_read(ps, REG_GLOBAL, GLOBAL_CONTROL);
 	if (ret < 0)
 		return ret;
 
-	err = mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_CONTROL,
-				  ret | GLOBAL_CONTROL_PPU_ENABLE);
+	err = _mv88e6xxx_reg_write(ps, REG_GLOBAL, GLOBAL_CONTROL,
+				   ret | GLOBAL_CONTROL_PPU_ENABLE);
 	if (err)
 		return err;
 
 	timeout = jiffies + 1 * HZ;
 	while (time_before(jiffies, timeout)) {
-		ret = mv88e6xxx_reg_read(ps, REG_GLOBAL, GLOBAL_STATUS);
+		ret = _mv88e6xxx_reg_read(ps, REG_GLOBAL, GLOBAL_STATUS);
 		if (ret < 0)
 			return ret;
 
@@ -317,11 +399,16 @@
 	struct mv88e6xxx_priv_state *ps;
 
 	ps = container_of(ugly, struct mv88e6xxx_priv_state, ppu_work);
+
+	mutex_lock(&ps->reg_lock);
+
 	if (mutex_trylock(&ps->ppu_mutex)) {
 		if (mv88e6xxx_ppu_enable(ps) == 0)
 			ps->ppu_disabled = 0;
 		mutex_unlock(&ps->ppu_mutex);
 	}
+
+	mutex_unlock(&ps->reg_lock);
 }
 
 static void mv88e6xxx_ppu_reenable_timer(unsigned long _ps)
@@ -364,7 +451,7 @@
 	mutex_unlock(&ps->ppu_mutex);
 }
 
-void mv88e6xxx_ppu_state_init(struct mv88e6xxx_priv_state *ps)
+static void mv88e6xxx_ppu_state_init(struct mv88e6xxx_priv_state *ps)
 {
 	mutex_init(&ps->ppu_mutex);
 	INIT_WORK(&ps->ppu_work, mv88e6xxx_ppu_reenable_work);
@@ -373,8 +460,8 @@
 	ps->ppu_timer.function = mv88e6xxx_ppu_reenable_timer;
 }
 
-static int mv88e6xxx_phy_read_ppu(struct mv88e6xxx_priv_state *ps, int addr,
-				  int regnum)
+static int mv88e6xxx_mdio_read_ppu(struct mv88e6xxx_priv_state *ps, int addr,
+				   int regnum)
 {
 	int ret;
 
@@ -387,8 +474,8 @@
 	return ret;
 }
 
-static int mv88e6xxx_phy_write_ppu(struct mv88e6xxx_priv_state *ps, int addr,
-				   int regnum, u16 val)
+static int mv88e6xxx_mdio_write_ppu(struct mv88e6xxx_priv_state *ps, int addr,
+				    int regnum, u16 val)
 {
 	int ret;
 
@@ -470,7 +557,7 @@
 	if (!phy_is_pseudo_fixed_link(phydev))
 		return;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&ps->reg_lock);
 
 	ret = _mv88e6xxx_reg_read(ps, REG_PORT(port), PORT_PCS_CTRL);
 	if (ret < 0)
@@ -484,7 +571,7 @@
 
 	reg |= PORT_PCS_CTRL_FORCE_LINK;
 	if (phydev->link)
-			reg |= PORT_PCS_CTRL_LINK_UP;
+		reg |= PORT_PCS_CTRL_LINK_UP;
 
 	if (mv88e6xxx_6065_family(ps) && phydev->speed > SPEED_100)
 		goto out;
@@ -521,7 +608,7 @@
 	_mv88e6xxx_reg_write(ps, REG_PORT(port), PORT_PCS_CTRL, reg);
 
 out:
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&ps->reg_lock);
 }
 
 static int _mv88e6xxx_stats_wait(struct mv88e6xxx_priv_state *ps)
@@ -746,11 +833,11 @@
 	int ret;
 	int i, j;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&ps->reg_lock);
 
 	ret = _mv88e6xxx_stats_snapshot(ps, port);
 	if (ret < 0) {
-		mutex_unlock(&ps->smi_mutex);
+		mutex_unlock(&ps->reg_lock);
 		return;
 	}
 	for (i = 0, j = 0; i < ARRAY_SIZE(mv88e6xxx_hw_stats); i++) {
@@ -761,7 +848,7 @@
 		}
 	}
 
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&ps->reg_lock);
 }
 
 static int mv88e6xxx_get_regs_len(struct dsa_switch *ds, int port)
@@ -780,7 +867,7 @@
 
 	memset(p, 0xff, 32 * sizeof(u16));
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&ps->reg_lock);
 
 	for (i = 0; i < 32; i++) {
 		int ret;
@@ -790,7 +877,7 @@
 			p[i] = ret;
 	}
 
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&ps->reg_lock);
 }
 
 static int _mv88e6xxx_wait(struct mv88e6xxx_priv_state *ps, int reg, int offset,
@@ -817,14 +904,14 @@
 {
 	int ret;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&ps->reg_lock);
 	ret = _mv88e6xxx_wait(ps, reg, offset, mask);
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&ps->reg_lock);
 
 	return ret;
 }
 
-static int _mv88e6xxx_phy_wait(struct mv88e6xxx_priv_state *ps)
+static int mv88e6xxx_mdio_wait(struct mv88e6xxx_priv_state *ps)
 {
 	return _mv88e6xxx_wait(ps, REG_GLOBAL2, GLOBAL2_SMI_OP,
 			       GLOBAL2_SMI_OP_BUSY);
@@ -1071,7 +1158,7 @@
 			       GLOBAL_ATU_OP_BUSY);
 }
 
-static int _mv88e6xxx_phy_read_indirect(struct mv88e6xxx_priv_state *ps,
+static int mv88e6xxx_mdio_read_indirect(struct mv88e6xxx_priv_state *ps,
 					int addr, int regnum)
 {
 	int ret;
@@ -1082,7 +1169,7 @@
 	if (ret < 0)
 		return ret;
 
-	ret = _mv88e6xxx_phy_wait(ps);
+	ret = mv88e6xxx_mdio_wait(ps);
 	if (ret < 0)
 		return ret;
 
@@ -1091,7 +1178,7 @@
 	return ret;
 }
 
-static int _mv88e6xxx_phy_write_indirect(struct mv88e6xxx_priv_state *ps,
+static int mv88e6xxx_mdio_write_indirect(struct mv88e6xxx_priv_state *ps,
 					 int addr, int regnum, u16 val)
 {
 	int ret;
@@ -1104,7 +1191,7 @@
 				   GLOBAL2_SMI_OP_22_WRITE | (addr << 5) |
 				   regnum);
 
-	return _mv88e6xxx_phy_wait(ps);
+	return mv88e6xxx_mdio_wait(ps);
 }
 
 static int mv88e6xxx_get_eee(struct dsa_switch *ds, int port,
@@ -1116,9 +1203,9 @@
 	if (!mv88e6xxx_has(ps, MV88E6XXX_FLAG_EEE))
 		return -EOPNOTSUPP;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&ps->reg_lock);
 
-	reg = _mv88e6xxx_phy_read_indirect(ps, port, 16);
+	reg = mv88e6xxx_mdio_read_indirect(ps, port, 16);
 	if (reg < 0)
 		goto out;
 
@@ -1133,7 +1220,7 @@
 	reg = 0;
 
 out:
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&ps->reg_lock);
 	return reg;
 }
 
@@ -1147,9 +1234,9 @@
 	if (!mv88e6xxx_has(ps, MV88E6XXX_FLAG_EEE))
 		return -EOPNOTSUPP;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&ps->reg_lock);
 
-	ret = _mv88e6xxx_phy_read_indirect(ps, port, 16);
+	ret = mv88e6xxx_mdio_read_indirect(ps, port, 16);
 	if (ret < 0)
 		goto out;
 
@@ -1159,9 +1246,9 @@
 	if (e->tx_lpi_enabled)
 		reg |= 0x0100;
 
-	ret = _mv88e6xxx_phy_write_indirect(ps, port, 16, reg);
+	ret = mv88e6xxx_mdio_write_indirect(ps, port, 16, reg);
 out:
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&ps->reg_lock);
 
 	return ret;
 }
@@ -1308,9 +1395,9 @@
 		 * Blocking or Listening state.
 		 */
 		if ((oldstate == PORT_CONTROL_STATE_LEARNING ||
-		     oldstate == PORT_CONTROL_STATE_FORWARDING)
-		    && (state == PORT_CONTROL_STATE_DISABLED ||
-			state == PORT_CONTROL_STATE_BLOCKING)) {
+		     oldstate == PORT_CONTROL_STATE_FORWARDING) &&
+		    (state == PORT_CONTROL_STATE_DISABLED ||
+		     state == PORT_CONTROL_STATE_BLOCKING)) {
 			ret = _mv88e6xxx_atu_remove(ps, 0, port, false);
 			if (ret)
 				return ret;
@@ -1322,7 +1409,7 @@
 		if (ret)
 			return ret;
 
-		netdev_dbg(ds->ports[port], "PortState %s (was %s)\n",
+		netdev_dbg(ds->ports[port].netdev, "PortState %s (was %s)\n",
 			   mv88e6xxx_port_state_names[state],
 			   mv88e6xxx_port_state_names[oldstate]);
 	}
@@ -1395,12 +1482,13 @@
 		break;
 	}
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&ps->reg_lock);
 	err = _mv88e6xxx_port_state(ps, port, stp_state);
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&ps->reg_lock);
 
 	if (err)
-		netdev_err(ds->ports[port], "failed to update state to %s\n",
+		netdev_err(ds->ports[port].netdev,
+			   "failed to update state to %s\n",
 			   mv88e6xxx_port_state_names[stp_state]);
 }
 
@@ -1426,8 +1514,8 @@
 		if (ret < 0)
 			return ret;
 
-		netdev_dbg(ds->ports[port], "DefaultVID %d (was %d)\n", *new,
-			   pvid);
+		netdev_dbg(ds->ports[port].netdev,
+			   "DefaultVID %d (was %d)\n", *new, pvid);
 	}
 
 	if (old)
@@ -1630,7 +1718,7 @@
 	if (!mv88e6xxx_has(ps, MV88E6XXX_FLAG_VTU))
 		return -EOPNOTSUPP;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&ps->reg_lock);
 
 	err = _mv88e6xxx_port_pvid_get(ps, port, &pvid);
 	if (err)
@@ -1652,7 +1740,8 @@
 			continue;
 
 		/* reinit and dump this VLAN obj */
-		vlan->vid_begin = vlan->vid_end = next.vid;
+		vlan->vid_begin = next.vid;
+		vlan->vid_end = next.vid;
 		vlan->flags = 0;
 
 		if (next.data[port] == GLOBAL_VTU_DATA_MEMBER_TAG_UNTAGGED)
@@ -1667,7 +1756,7 @@
 	} while (next.vid < GLOBAL_VTU_VID_MASK);
 
 unlock:
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&ps->reg_lock);
 
 	return err;
 }
@@ -1842,7 +1931,8 @@
 		if (ret < 0)
 			return ret;
 
-		netdev_dbg(ds->ports[port], "FID %d (was %d)\n", *new, fid);
+		netdev_dbg(ds->ports[port].netdev,
+			   "FID %d (was %d)\n", *new, fid);
 	}
 
 	if (old)
@@ -1994,7 +2084,7 @@
 	if (!vid_begin)
 		return -EOPNOTSUPP;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&ps->reg_lock);
 
 	err = _mv88e6xxx_vtu_vid_write(ps, vid_begin - 1);
 	if (err)
@@ -2023,7 +2113,7 @@
 			    ps->ports[port].bridge_dev)
 				break; /* same bridge, check next VLAN */
 
-			netdev_warn(ds->ports[port],
+			netdev_warn(ds->ports[port].netdev,
 				    "hardware VLAN %d already used by %s\n",
 				    vlan.vid,
 				    netdev_name(ps->ports[i].bridge_dev));
@@ -2033,7 +2123,7 @@
 	} while (vlan.vid < vid_end);
 
 unlock:
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&ps->reg_lock);
 
 	return err;
 }
@@ -2056,7 +2146,7 @@
 	if (!mv88e6xxx_has(ps, MV88E6XXX_FLAG_VTU))
 		return -EOPNOTSUPP;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&ps->reg_lock);
 
 	ret = _mv88e6xxx_reg_read(ps, REG_PORT(port), PORT_CONTROL_2);
 	if (ret < 0)
@@ -2073,21 +2163,22 @@
 		if (ret < 0)
 			goto unlock;
 
-		netdev_dbg(ds->ports[port], "802.1Q Mode %s (was %s)\n",
+		netdev_dbg(ds->ports[port].netdev, "802.1Q Mode %s (was %s)\n",
 			   mv88e6xxx_port_8021q_mode_names[new],
 			   mv88e6xxx_port_8021q_mode_names[old]);
 	}
 
 	ret = 0;
 unlock:
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&ps->reg_lock);
 
 	return ret;
 }
 
-static int mv88e6xxx_port_vlan_prepare(struct dsa_switch *ds, int port,
-				       const struct switchdev_obj_port_vlan *vlan,
-				       struct switchdev_trans *trans)
+static int
+mv88e6xxx_port_vlan_prepare(struct dsa_switch *ds, int port,
+			    const struct switchdev_obj_port_vlan *vlan,
+			    struct switchdev_trans *trans)
 {
 	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
 	int err;
@@ -2138,18 +2229,19 @@
 	if (!mv88e6xxx_has(ps, MV88E6XXX_FLAG_VTU))
 		return;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&ps->reg_lock);
 
 	for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid)
 		if (_mv88e6xxx_port_vlan_add(ps, port, vid, untagged))
-			netdev_err(ds->ports[port], "failed to add VLAN %d%c\n",
+			netdev_err(ds->ports[port].netdev,
+				   "failed to add VLAN %d%c\n",
 				   vid, untagged ? 'u' : 't');
 
 	if (pvid && _mv88e6xxx_port_pvid_set(ps, port, vlan->vid_end))
-		netdev_err(ds->ports[port], "failed to set PVID %d\n",
+		netdev_err(ds->ports[port].netdev, "failed to set PVID %d\n",
 			   vlan->vid_end);
 
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&ps->reg_lock);
 }
 
 static int _mv88e6xxx_port_vlan_del(struct mv88e6xxx_priv_state *ps,
@@ -2198,7 +2290,7 @@
 	if (!mv88e6xxx_has(ps, MV88E6XXX_FLAG_VTU))
 		return -EOPNOTSUPP;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&ps->reg_lock);
 
 	err = _mv88e6xxx_port_pvid_get(ps, port, &pvid);
 	if (err)
@@ -2217,7 +2309,7 @@
 	}
 
 unlock:
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&ps->reg_lock);
 
 	return err;
 }
@@ -2329,10 +2421,11 @@
 	if (!mv88e6xxx_has(ps, MV88E6XXX_FLAG_ATU))
 		return;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&ps->reg_lock);
 	if (_mv88e6xxx_port_fdb_load(ps, port, fdb->addr, fdb->vid, state))
-		netdev_err(ds->ports[port], "failed to load MAC address\n");
-	mutex_unlock(&ps->smi_mutex);
+		netdev_err(ds->ports[port].netdev,
+			   "failed to load MAC address\n");
+	mutex_unlock(&ps->reg_lock);
 }
 
 static int mv88e6xxx_port_fdb_del(struct dsa_switch *ds, int port,
@@ -2344,10 +2437,10 @@
 	if (!mv88e6xxx_has(ps, MV88E6XXX_FLAG_ATU))
 		return -EOPNOTSUPP;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&ps->reg_lock);
 	ret = _mv88e6xxx_port_fdb_load(ps, port, fdb->addr, fdb->vid,
 				       GLOBAL_ATU_DATA_STATE_UNUSED);
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&ps->reg_lock);
 
 	return ret;
 }
@@ -2452,7 +2545,7 @@
 	if (!mv88e6xxx_has(ps, MV88E6XXX_FLAG_ATU))
 		return -EOPNOTSUPP;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&ps->reg_lock);
 
 	/* Dump port's default Filtering Information Database (VLAN ID 0) */
 	err = _mv88e6xxx_port_fid_get(ps, port, &fid);
@@ -2483,7 +2576,7 @@
 	} while (vlan.vid < GLOBAL_VTU_VID_MASK);
 
 unlock:
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&ps->reg_lock);
 
 	return err;
 }
@@ -2497,7 +2590,7 @@
 	if (!mv88e6xxx_has(ps, MV88E6XXX_FLAG_VLANTABLE))
 		return -EOPNOTSUPP;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&ps->reg_lock);
 
 	/* Assign the bridge and remap each port's VLANTable */
 	ps->ports[port].bridge_dev = bridge;
@@ -2510,7 +2603,7 @@
 		}
 	}
 
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&ps->reg_lock);
 
 	return err;
 }
@@ -2524,7 +2617,7 @@
 	if (!mv88e6xxx_has(ps, MV88E6XXX_FLAG_VLANTABLE))
 		return;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&ps->reg_lock);
 
 	/* Unassign the bridge and remap each port's VLANTable */
 	ps->ports[port].bridge_dev = NULL;
@@ -2532,39 +2625,40 @@
 	for (i = 0; i < ps->info->num_ports; ++i)
 		if (i == port || ps->ports[i].bridge_dev == bridge)
 			if (_mv88e6xxx_port_based_vlan_map(ps, i))
-				netdev_warn(ds->ports[i], "failed to remap\n");
+				netdev_warn(ds->ports[i].netdev,
+					    "failed to remap\n");
 
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&ps->reg_lock);
 }
 
-static int _mv88e6xxx_phy_page_write(struct mv88e6xxx_priv_state *ps,
-				     int port, int page, int reg, int val)
+static int _mv88e6xxx_mdio_page_write(struct mv88e6xxx_priv_state *ps,
+				      int port, int page, int reg, int val)
 {
 	int ret;
 
-	ret = _mv88e6xxx_phy_write_indirect(ps, port, 0x16, page);
+	ret = mv88e6xxx_mdio_write_indirect(ps, port, 0x16, page);
 	if (ret < 0)
 		goto restore_page_0;
 
-	ret = _mv88e6xxx_phy_write_indirect(ps, port, reg, val);
+	ret = mv88e6xxx_mdio_write_indirect(ps, port, reg, val);
 restore_page_0:
-	_mv88e6xxx_phy_write_indirect(ps, port, 0x16, 0x0);
+	mv88e6xxx_mdio_write_indirect(ps, port, 0x16, 0x0);
 
 	return ret;
 }
 
-static int _mv88e6xxx_phy_page_read(struct mv88e6xxx_priv_state *ps,
-				    int port, int page, int reg)
+static int _mv88e6xxx_mdio_page_read(struct mv88e6xxx_priv_state *ps,
+				     int port, int page, int reg)
 {
 	int ret;
 
-	ret = _mv88e6xxx_phy_write_indirect(ps, port, 0x16, page);
+	ret = mv88e6xxx_mdio_write_indirect(ps, port, 0x16, page);
 	if (ret < 0)
 		goto restore_page_0;
 
-	ret = _mv88e6xxx_phy_read_indirect(ps, port, reg);
+	ret = mv88e6xxx_mdio_read_indirect(ps, port, reg);
 restore_page_0:
-	_mv88e6xxx_phy_write_indirect(ps, port, 0x16, 0x0);
+	mv88e6xxx_mdio_write_indirect(ps, port, 0x16, 0x0);
 
 	return ret;
 }
@@ -2635,16 +2729,16 @@
 {
 	int ret;
 
-	ret = _mv88e6xxx_phy_page_read(ps, REG_FIBER_SERDES, PAGE_FIBER_SERDES,
-				       MII_BMCR);
+	ret = _mv88e6xxx_mdio_page_read(ps, REG_FIBER_SERDES,
+					PAGE_FIBER_SERDES, MII_BMCR);
 	if (ret < 0)
 		return ret;
 
 	if (ret & BMCR_PDOWN) {
 		ret &= ~BMCR_PDOWN;
-		ret = _mv88e6xxx_phy_page_write(ps, REG_FIBER_SERDES,
-						PAGE_FIBER_SERDES, MII_BMCR,
-						ret);
+		ret = _mv88e6xxx_mdio_page_write(ps, REG_FIBER_SERDES,
+						 PAGE_FIBER_SERDES, MII_BMCR,
+						 ret);
 	}
 
 	return ret;
@@ -2715,11 +2809,8 @@
 		if (mv88e6xxx_6352_family(ps) || mv88e6xxx_6351_family(ps) ||
 		    mv88e6xxx_6165_family(ps) || mv88e6xxx_6097_family(ps) ||
 		    mv88e6xxx_6320_family(ps)) {
-			if (ds->dst->tag_protocol == DSA_TAG_PROTO_EDSA)
-				reg |= PORT_CONTROL_FRAME_ETHER_TYPE_DSA;
-			else
-				reg |= PORT_CONTROL_FRAME_MODE_DSA;
-			reg |= PORT_CONTROL_FORWARD_UNKNOWN |
+			reg |= PORT_CONTROL_FRAME_ETHER_TYPE_DSA |
+				PORT_CONTROL_FORWARD_UNKNOWN |
 				PORT_CONTROL_FORWARD_UNKNOWN_MC;
 		}
 
@@ -2727,8 +2818,7 @@
 		    mv88e6xxx_6165_family(ps) || mv88e6xxx_6097_family(ps) ||
 		    mv88e6xxx_6095_family(ps) || mv88e6xxx_6065_family(ps) ||
 		    mv88e6xxx_6185_family(ps) || mv88e6xxx_6320_family(ps)) {
-			if (ds->dst->tag_protocol == DSA_TAG_PROTO_EDSA)
-				reg |= PORT_CONTROL_EGRESS_ADD_TAG;
+			reg |= PORT_CONTROL_EGRESS_ADD_TAG;
 		}
 	}
 	if (dsa_is_dsa_port(ds, port)) {
@@ -3014,9 +3104,8 @@
 	for (i = 0; i < 32; i++) {
 		int nexthop = 0x1f;
 
-		if (ps->ds->cd->rtable &&
-		    i != ps->ds->index && i < ps->ds->dst->pd->nr_chips)
-			nexthop = ps->ds->cd->rtable[i] & 0x1f;
+		if (i != ds->index && i < DSA_MAX_SWITCHES)
+			nexthop = ds->rtable[i] & 0x1f;
 
 		err = _mv88e6xxx_reg_write(
 			ps, REG_GLOBAL2,
@@ -3125,14 +3214,12 @@
 	int i;
 
 	ps->ds = ds;
+	ds->slave_mii_bus = ps->mdio_bus;
 
 	if (mv88e6xxx_has(ps, MV88E6XXX_FLAG_EEPROM))
 		mutex_init(&ps->eeprom_mutex);
 
-	if (mv88e6xxx_has(ps, MV88E6XXX_FLAG_PPU))
-		mv88e6xxx_ppu_state_init(ps);
-
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&ps->reg_lock);
 
 	err = mv88e6xxx_switch_reset(ps);
 	if (err)
@@ -3149,89 +3236,150 @@
 	}
 
 unlock:
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&ps->reg_lock);
 
 	return err;
 }
 
-int mv88e6xxx_phy_page_read(struct dsa_switch *ds, int port, int page, int reg)
+static int mv88e6xxx_mdio_page_read(struct dsa_switch *ds, int port, int page,
+				    int reg)
 {
 	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
 	int ret;
 
-	mutex_lock(&ps->smi_mutex);
-	ret = _mv88e6xxx_phy_page_read(ps, port, page, reg);
-	mutex_unlock(&ps->smi_mutex);
+	mutex_lock(&ps->reg_lock);
+	ret = _mv88e6xxx_mdio_page_read(ps, port, page, reg);
+	mutex_unlock(&ps->reg_lock);
 
 	return ret;
 }
 
-int mv88e6xxx_phy_page_write(struct dsa_switch *ds, int port, int page,
-			     int reg, int val)
+static int mv88e6xxx_mdio_page_write(struct dsa_switch *ds, int port, int page,
+				     int reg, int val)
 {
 	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
 	int ret;
 
-	mutex_lock(&ps->smi_mutex);
-	ret = _mv88e6xxx_phy_page_write(ps, port, page, reg, val);
-	mutex_unlock(&ps->smi_mutex);
+	mutex_lock(&ps->reg_lock);
+	ret = _mv88e6xxx_mdio_page_write(ps, port, page, reg, val);
+	mutex_unlock(&ps->reg_lock);
 
 	return ret;
 }
 
-static int mv88e6xxx_port_to_phy_addr(struct mv88e6xxx_priv_state *ps,
-				      int port)
+static int mv88e6xxx_port_to_mdio_addr(struct mv88e6xxx_priv_state *ps,
+				       int port)
 {
 	if (port >= 0 && port < ps->info->num_ports)
 		return port;
 	return -EINVAL;
 }
 
-static int mv88e6xxx_phy_read(struct dsa_switch *ds, int port, int regnum)
+static int mv88e6xxx_mdio_read(struct mii_bus *bus, int port, int regnum)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
-	int addr = mv88e6xxx_port_to_phy_addr(ps, port);
+	struct mv88e6xxx_priv_state *ps = bus->priv;
+	int addr = mv88e6xxx_port_to_mdio_addr(ps, port);
 	int ret;
 
 	if (addr < 0)
 		return 0xffff;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&ps->reg_lock);
 
 	if (mv88e6xxx_has(ps, MV88E6XXX_FLAG_PPU))
-		ret = mv88e6xxx_phy_read_ppu(ps, addr, regnum);
+		ret = mv88e6xxx_mdio_read_ppu(ps, addr, regnum);
 	else if (mv88e6xxx_has(ps, MV88E6XXX_FLAG_SMI_PHY))
-		ret = _mv88e6xxx_phy_read_indirect(ps, addr, regnum);
+		ret = mv88e6xxx_mdio_read_indirect(ps, addr, regnum);
 	else
-		ret = _mv88e6xxx_phy_read(ps, addr, regnum);
+		ret = mv88e6xxx_mdio_read_direct(ps, addr, regnum);
 
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&ps->reg_lock);
 	return ret;
 }
 
-static int mv88e6xxx_phy_write(struct dsa_switch *ds, int port, int regnum,
-			       u16 val)
+static int mv88e6xxx_mdio_write(struct mii_bus *bus, int port, int regnum,
+				u16 val)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
-	int addr = mv88e6xxx_port_to_phy_addr(ps, port);
+	struct mv88e6xxx_priv_state *ps = bus->priv;
+	int addr = mv88e6xxx_port_to_mdio_addr(ps, port);
 	int ret;
 
 	if (addr < 0)
 		return 0xffff;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&ps->reg_lock);
 
 	if (mv88e6xxx_has(ps, MV88E6XXX_FLAG_PPU))
-		ret = mv88e6xxx_phy_write_ppu(ps, addr, regnum, val);
+		ret = mv88e6xxx_mdio_write_ppu(ps, addr, regnum, val);
 	else if (mv88e6xxx_has(ps, MV88E6XXX_FLAG_SMI_PHY))
-		ret = _mv88e6xxx_phy_write_indirect(ps, addr, regnum, val);
+		ret = mv88e6xxx_mdio_write_indirect(ps, addr, regnum, val);
 	else
-		ret = _mv88e6xxx_phy_write(ps, addr, regnum, val);
+		ret = mv88e6xxx_mdio_write_direct(ps, addr, regnum, val);
 
-	mutex_unlock(&ps->smi_mutex);
+	mutex_unlock(&ps->reg_lock);
 	return ret;
 }
 
+static int mv88e6xxx_mdio_register(struct mv88e6xxx_priv_state *ps,
+				   struct device_node *np)
+{
+	static int index;
+	struct mii_bus *bus;
+	int err;
+
+	if (mv88e6xxx_has(ps, MV88E6XXX_FLAG_PPU))
+		mv88e6xxx_ppu_state_init(ps);
+
+	if (np)
+		ps->mdio_np = of_get_child_by_name(np, "mdio");
+
+	bus = devm_mdiobus_alloc(ps->dev);
+	if (!bus)
+		return -ENOMEM;
+
+	bus->priv = (void *)ps;
+	if (np) {
+		bus->name = np->full_name;
+		snprintf(bus->id, MII_BUS_ID_SIZE, "%s", np->full_name);
+	} else {
+		bus->name = "mv88e6xxx SMI";
+		snprintf(bus->id, MII_BUS_ID_SIZE, "mv88e6xxx-%d", index++);
+	}
+
+	bus->read = mv88e6xxx_mdio_read;
+	bus->write = mv88e6xxx_mdio_write;
+	bus->parent = ps->dev;
+
+	if (ps->mdio_np)
+		err = of_mdiobus_register(bus, ps->mdio_np);
+	else
+		err = mdiobus_register(bus);
+	if (err) {
+		dev_err(ps->dev, "Cannot register MDIO bus (%d)\n", err);
+		goto out;
+	}
+	ps->mdio_bus = bus;
+
+	return 0;
+
+out:
+	if (ps->mdio_np)
+		of_node_put(ps->mdio_np);
+
+	return err;
+}
+
+static void mv88e6xxx_mdio_unregister(struct mv88e6xxx_priv_state *ps)
+
+{
+	struct mii_bus *bus = ps->mdio_bus;
+
+	mdiobus_unregister(bus);
+
+	if (ps->mdio_np)
+		of_node_put(ps->mdio_np);
+}
+
 #ifdef CONFIG_NET_DSA_HWMON
 
 static int mv88e61xx_get_temp(struct dsa_switch *ds, int *temp)
@@ -3242,40 +3390,40 @@
 
 	*temp = 0;
 
-	mutex_lock(&ps->smi_mutex);
+	mutex_lock(&ps->reg_lock);
 
-	ret = _mv88e6xxx_phy_write(ps, 0x0, 0x16, 0x6);
+	ret = mv88e6xxx_mdio_write_direct(ps, 0x0, 0x16, 0x6);
 	if (ret < 0)
 		goto error;
 
 	/* Enable temperature sensor */
-	ret = _mv88e6xxx_phy_read(ps, 0x0, 0x1a);
+	ret = mv88e6xxx_mdio_read_direct(ps, 0x0, 0x1a);
 	if (ret < 0)
 		goto error;
 
-	ret = _mv88e6xxx_phy_write(ps, 0x0, 0x1a, ret | (1 << 5));
+	ret = mv88e6xxx_mdio_write_direct(ps, 0x0, 0x1a, ret | (1 << 5));
 	if (ret < 0)
 		goto error;
 
 	/* Wait for temperature to stabilize */
 	usleep_range(10000, 12000);
 
-	val = _mv88e6xxx_phy_read(ps, 0x0, 0x1a);
+	val = mv88e6xxx_mdio_read_direct(ps, 0x0, 0x1a);
 	if (val < 0) {
 		ret = val;
 		goto error;
 	}
 
 	/* Disable temperature sensor */
-	ret = _mv88e6xxx_phy_write(ps, 0x0, 0x1a, ret & ~(1 << 5));
+	ret = mv88e6xxx_mdio_write_direct(ps, 0x0, 0x1a, ret & ~(1 << 5));
 	if (ret < 0)
 		goto error;
 
 	*temp = ((val & 0x1f) - 5) * 5;
 
 error:
-	_mv88e6xxx_phy_write(ps, 0x0, 0x16, 0x0);
-	mutex_unlock(&ps->smi_mutex);
+	mv88e6xxx_mdio_write_direct(ps, 0x0, 0x16, 0x0);
+	mutex_unlock(&ps->reg_lock);
 	return ret;
 }
 
@@ -3287,7 +3435,7 @@
 
 	*temp = 0;
 
-	ret = mv88e6xxx_phy_page_read(ds, phy, 6, 27);
+	ret = mv88e6xxx_mdio_page_read(ds, phy, 6, 27);
 	if (ret < 0)
 		return ret;
 
@@ -3320,7 +3468,7 @@
 
 	*temp = 0;
 
-	ret = mv88e6xxx_phy_page_read(ds, phy, 6, 26);
+	ret = mv88e6xxx_mdio_page_read(ds, phy, 6, 26);
 	if (ret < 0)
 		return ret;
 
@@ -3338,12 +3486,12 @@
 	if (!mv88e6xxx_has(ps, MV88E6XXX_FLAG_TEMP_LIMIT))
 		return -EOPNOTSUPP;
 
-	ret = mv88e6xxx_phy_page_read(ds, phy, 6, 26);
+	ret = mv88e6xxx_mdio_page_read(ds, phy, 6, 26);
 	if (ret < 0)
 		return ret;
 	temp = clamp_val(DIV_ROUND_CLOSEST(temp, 5) + 5, 0, 0x1f);
-	return mv88e6xxx_phy_page_write(ds, phy, 6, 26,
-					(ret & 0xe0ff) | (temp << 8));
+	return mv88e6xxx_mdio_page_write(ds, phy, 6, 26,
+					 (ret & 0xe0ff) | (temp << 8));
 }
 
 static int mv88e6xxx_get_temp_alarm(struct dsa_switch *ds, bool *alarm)
@@ -3357,7 +3505,7 @@
 
 	*alarm = false;
 
-	ret = mv88e6xxx_phy_page_read(ds, phy, 6, 26);
+	ret = mv88e6xxx_mdio_page_read(ds, phy, 6, 26);
 	if (ret < 0)
 		return ret;
 
@@ -3374,6 +3522,7 @@
 		.name = "Marvell 88E6085",
 		.num_databases = 4096,
 		.num_ports = 10,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6097,
 	},
 
@@ -3383,6 +3532,7 @@
 		.name = "Marvell 88E6095/88E6095F",
 		.num_databases = 256,
 		.num_ports = 11,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6095,
 	},
 
@@ -3392,6 +3542,7 @@
 		.name = "Marvell 88E6123",
 		.num_databases = 4096,
 		.num_ports = 3,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6165,
 	},
 
@@ -3401,6 +3552,7 @@
 		.name = "Marvell 88E6131",
 		.num_databases = 256,
 		.num_ports = 8,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6185,
 	},
 
@@ -3410,6 +3562,7 @@
 		.name = "Marvell 88E6161",
 		.num_databases = 4096,
 		.num_ports = 6,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6165,
 	},
 
@@ -3419,6 +3572,7 @@
 		.name = "Marvell 88E6165",
 		.num_databases = 4096,
 		.num_ports = 6,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6165,
 	},
 
@@ -3428,6 +3582,7 @@
 		.name = "Marvell 88E6171",
 		.num_databases = 4096,
 		.num_ports = 7,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6351,
 	},
 
@@ -3437,6 +3592,7 @@
 		.name = "Marvell 88E6172",
 		.num_databases = 4096,
 		.num_ports = 7,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6352,
 	},
 
@@ -3446,6 +3602,7 @@
 		.name = "Marvell 88E6175",
 		.num_databases = 4096,
 		.num_ports = 7,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6351,
 	},
 
@@ -3455,6 +3612,7 @@
 		.name = "Marvell 88E6176",
 		.num_databases = 4096,
 		.num_ports = 7,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6352,
 	},
 
@@ -3464,6 +3622,7 @@
 		.name = "Marvell 88E6185",
 		.num_databases = 256,
 		.num_ports = 10,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6185,
 	},
 
@@ -3473,6 +3632,7 @@
 		.name = "Marvell 88E6240",
 		.num_databases = 4096,
 		.num_ports = 7,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6352,
 	},
 
@@ -3482,6 +3642,7 @@
 		.name = "Marvell 88E6320",
 		.num_databases = 4096,
 		.num_ports = 7,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6320,
 	},
 
@@ -3491,6 +3652,7 @@
 		.name = "Marvell 88E6321",
 		.num_databases = 4096,
 		.num_ports = 7,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6320,
 	},
 
@@ -3500,6 +3662,7 @@
 		.name = "Marvell 88E6350",
 		.num_databases = 4096,
 		.num_ports = 7,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6351,
 	},
 
@@ -3509,6 +3672,7 @@
 		.name = "Marvell 88E6351",
 		.num_databases = 4096,
 		.num_ports = 7,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6351,
 	},
 
@@ -3518,75 +3682,127 @@
 		.name = "Marvell 88E6352",
 		.num_databases = 4096,
 		.num_ports = 7,
+		.port_base_addr = 0x10,
 		.flags = MV88E6XXX_FLAGS_FAMILY_6352,
 	},
 };
 
-static const struct mv88e6xxx_info *
-mv88e6xxx_lookup_info(unsigned int prod_num, const struct mv88e6xxx_info *table,
-		      unsigned int num)
+static const struct mv88e6xxx_info *mv88e6xxx_lookup_info(unsigned int prod_num)
 {
 	int i;
 
-	for (i = 0; i < num; ++i)
-		if (table[i].prod_num == prod_num)
-			return &table[i];
+	for (i = 0; i < ARRAY_SIZE(mv88e6xxx_table); ++i)
+		if (mv88e6xxx_table[i].prod_num == prod_num)
+			return &mv88e6xxx_table[i];
 
 	return NULL;
 }
 
+static int mv88e6xxx_detect(struct mv88e6xxx_priv_state *ps)
+{
+	const struct mv88e6xxx_info *info;
+	int id, prod_num, rev;
+
+	id = mv88e6xxx_reg_read(ps, ps->info->port_base_addr, PORT_SWITCH_ID);
+	if (id < 0)
+		return id;
+
+	prod_num = (id & 0xfff0) >> 4;
+	rev = id & 0x000f;
+
+	info = mv88e6xxx_lookup_info(prod_num);
+	if (!info)
+		return -ENODEV;
+
+	/* Update the compatible info with the probed one */
+	ps->info = info;
+
+	dev_info(ps->dev, "switch 0x%x detected: %s, revision %u\n",
+		 ps->info->prod_num, ps->info->name, rev);
+
+	return 0;
+}
+
+static struct mv88e6xxx_priv_state *mv88e6xxx_alloc_chip(struct device *dev)
+{
+	struct mv88e6xxx_priv_state *ps;
+
+	ps = devm_kzalloc(dev, sizeof(*ps), GFP_KERNEL);
+	if (!ps)
+		return NULL;
+
+	ps->dev = dev;
+
+	mutex_init(&ps->reg_lock);
+
+	return ps;
+}
+
+static int mv88e6xxx_smi_init(struct mv88e6xxx_priv_state *ps,
+			      struct mii_bus *bus, int sw_addr)
+{
+	/* ADDR[0] pin is unavailable externally and considered zero */
+	if (sw_addr & 0x1)
+		return -EINVAL;
+
+	if (sw_addr == 0)
+		ps->smi_ops = &mv88e6xxx_smi_single_chip_ops;
+	else if (mv88e6xxx_has(ps, MV88E6XXX_FLAG_MULTI_CHIP))
+		ps->smi_ops = &mv88e6xxx_smi_multi_chip_ops;
+	else
+		return -EINVAL;
+
+	ps->bus = bus;
+	ps->sw_addr = sw_addr;
+
+	return 0;
+}
+
 static const char *mv88e6xxx_drv_probe(struct device *dsa_dev,
 				       struct device *host_dev, int sw_addr,
 				       void **priv)
 {
-	const struct mv88e6xxx_info *info;
 	struct mv88e6xxx_priv_state *ps;
 	struct mii_bus *bus;
-	const char *name;
-	int id, prod_num, rev;
+	int err;
 
 	bus = dsa_host_dev_to_mii_bus(host_dev);
 	if (!bus)
 		return NULL;
 
-	id = __mv88e6xxx_reg_read(bus, sw_addr, REG_PORT(0), PORT_SWITCH_ID);
-	if (id < 0)
-		return NULL;
-
-	prod_num = (id & 0xfff0) >> 4;
-	rev = id & 0x000f;
-
-	info = mv88e6xxx_lookup_info(prod_num, mv88e6xxx_table,
-				     ARRAY_SIZE(mv88e6xxx_table));
-	if (!info)
-		return NULL;
-
-	name = info->name;
-
-	ps = devm_kzalloc(dsa_dev, sizeof(*ps), GFP_KERNEL);
+	ps = mv88e6xxx_alloc_chip(dsa_dev);
 	if (!ps)
 		return NULL;
 
-	ps->bus = bus;
-	ps->sw_addr = sw_addr;
-	ps->info = info;
-	mutex_init(&ps->smi_mutex);
+	/* Legacy SMI probing will only support chips similar to 88E6085 */
+	ps->info = &mv88e6xxx_table[MV88E6085];
+
+	err = mv88e6xxx_smi_init(ps, bus, sw_addr);
+	if (err)
+		goto free;
+
+	err = mv88e6xxx_detect(ps);
+	if (err)
+		goto free;
+
+	err = mv88e6xxx_mdio_register(ps, NULL);
+	if (err)
+		goto free;
 
 	*priv = ps;
 
-	dev_info(&ps->bus->dev, "switch 0x%x probed: %s, revision %u\n",
-		 prod_num, name, rev);
+	return ps->info->name;
+free:
+	devm_kfree(dsa_dev, ps);
 
-	return name;
+	return NULL;
 }
 
-struct dsa_switch_driver mv88e6xxx_switch_driver = {
+static struct dsa_switch_driver mv88e6xxx_switch_driver = {
 	.tag_protocol		= DSA_TAG_PROTO_EDSA,
 	.probe			= mv88e6xxx_drv_probe,
 	.setup			= mv88e6xxx_setup,
 	.set_addr		= mv88e6xxx_set_addr,
-	.phy_read		= mv88e6xxx_phy_read,
-	.phy_write		= mv88e6xxx_phy_write,
 	.adjust_link		= mv88e6xxx_adjust_link,
 	.get_strings		= mv88e6xxx_get_strings,
 	.get_ethtool_stats	= mv88e6xxx_get_ethtool_stats,
@@ -3618,64 +3834,74 @@
 	.port_fdb_dump          = mv88e6xxx_port_fdb_dump,
 };
 
-int mv88e6xxx_probe(struct mdio_device *mdiodev)
+static int mv88e6xxx_register_switch(struct mv88e6xxx_priv_state *ps,
+				     struct device_node *np)
 {
-	struct device *dev = &mdiodev->dev;
-	struct device_node *np = dev->of_node;
-	struct mv88e6xxx_priv_state *ps;
-	int id, prod_num, rev;
+	struct device *dev = ps->dev;
 	struct dsa_switch *ds;
-	u32 eeprom_len;
-	int err;
 
-	ds = devm_kzalloc(dev, sizeof(*ds) + sizeof(*ps), GFP_KERNEL);
+	ds = devm_kzalloc(dev, sizeof(*ds), GFP_KERNEL);
 	if (!ds)
 		return -ENOMEM;
 
-	ps = (struct mv88e6xxx_priv_state *)(ds + 1);
-	ds->priv = ps;
 	ds->dev = dev;
-	ps->dev = dev;
-	ps->ds = ds;
-	ps->bus = mdiodev->bus;
-	ps->sw_addr = mdiodev->addr;
-	mutex_init(&ps->smi_mutex);
-
-	get_device(&ps->bus->dev);
-
+	ds->priv = ps;
 	ds->drv = &mv88e6xxx_switch_driver;
 
-	id = mv88e6xxx_reg_read(ps, REG_PORT(0), PORT_SWITCH_ID);
-	if (id < 0)
-		return id;
+	dev_set_drvdata(dev, ds);
 
-	prod_num = (id & 0xfff0) >> 4;
-	rev = id & 0x000f;
+	return dsa_register_switch(ds, np);
+}
 
-	ps->info = mv88e6xxx_lookup_info(prod_num, mv88e6xxx_table,
-					 ARRAY_SIZE(mv88e6xxx_table));
-	if (!ps->info)
-		return -ENODEV;
+static void mv88e6xxx_unregister_switch(struct mv88e6xxx_priv_state *ps)
+{
+	dsa_unregister_switch(ps->ds);
+}
 
-	ps->reset = devm_gpiod_get(&mdiodev->dev, "reset", GPIOD_ASIS);
-	if (IS_ERR(ps->reset)) {
-		err = PTR_ERR(ps->reset);
-		if (err == -ENOENT) {
-			/* Optional, so not an error */
-			ps->reset = NULL;
-		} else {
-			return err;
-		}
-	}
+static int mv88e6xxx_probe(struct mdio_device *mdiodev)
+{
+	struct device *dev = &mdiodev->dev;
+	struct device_node *np = dev->of_node;
+	const struct mv88e6xxx_info *compat_info;
+	struct mv88e6xxx_priv_state *ps;
+	u32 eeprom_len;
+	int err;
+
+	compat_info = of_device_get_match_data(dev);
+	if (!compat_info)
+		return -EINVAL;
+
+	ps = mv88e6xxx_alloc_chip(dev);
+	if (!ps)
+		return -ENOMEM;
+
+	ps->info = compat_info;
+
+	err = mv88e6xxx_smi_init(ps, mdiodev->bus, mdiodev->addr);
+	if (err)
+		return err;
+
+	err = mv88e6xxx_detect(ps);
+	if (err)
+		return err;
+
+	ps->reset = devm_gpiod_get_optional(dev, "reset", GPIOD_ASIS);
+	if (IS_ERR(ps->reset))
+		return PTR_ERR(ps->reset);
 
 	if (mv88e6xxx_has(ps, MV88E6XXX_FLAG_EEPROM) &&
 	    !of_property_read_u32(np, "eeprom-length", &eeprom_len))
 		ps->eeprom_len = eeprom_len;
 
-	dev_set_drvdata(dev, ds);
+	err = mv88e6xxx_mdio_register(ps, np);
+	if (err)
+		return err;
 
-	dev_info(dev, "switch 0x%x probed: %s, revision %u\n",
-		 prod_num, ps->info->name, rev);
+	err = mv88e6xxx_register_switch(ps, np);
+	if (err) {
+		mv88e6xxx_mdio_unregister(ps);
+		return err;
+	}
 
 	return 0;
 }
@@ -3685,11 +3911,15 @@
 	struct dsa_switch *ds = dev_get_drvdata(&mdiodev->dev);
 	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
 
-	put_device(&ps->bus->dev);
+	mv88e6xxx_unregister_switch(ps);
+	mv88e6xxx_mdio_unregister(ps);
 }
 
 static const struct of_device_id mv88e6xxx_of_match[] = {
-	{ .compatible = "marvell,mv88e6085" },
+	{
+		.compatible = "marvell,mv88e6085",
+		.data = &mv88e6xxx_table[MV88E6085],
+	},
 	{ /* sentinel */ },
 };
 
diff --git a/drivers/net/dsa/mv88e6xxx.h b/drivers/net/dsa/mv88e6xxx.h
index 36d0e15..a94acd8 100644
--- a/drivers/net/dsa/mv88e6xxx.h
+++ b/drivers/net/dsa/mv88e6xxx.h
@@ -387,6 +387,12 @@
 	 */
 	MV88E6XXX_CAP_EEPROM,
 
+	/* Multi-chip Addressing Mode.
+	 * Some chips require an indirect SMI access when their SMI device
+	 * address is not zero. See SMI_CMD and SMI_DATA.
+	 */
+	MV88E6XXX_CAP_MULTI_CHIP,
+
 	/* Port State Filtering for 802.1D Spanning Tree.
 	 * See PORT_CONTROL_STATE_* values in the PORT_CONTROL register.
 	 */
@@ -439,6 +445,7 @@
 #define MV88E6XXX_FLAG_ATU		BIT(MV88E6XXX_CAP_ATU)
 #define MV88E6XXX_FLAG_EEE		BIT(MV88E6XXX_CAP_EEE)
 #define MV88E6XXX_FLAG_EEPROM		BIT(MV88E6XXX_CAP_EEPROM)
+#define MV88E6XXX_FLAG_MULTI_CHIP	BIT(MV88E6XXX_CAP_MULTI_CHIP)
 #define MV88E6XXX_FLAG_PORTSTATE	BIT(MV88E6XXX_CAP_PORTSTATE)
 #define MV88E6XXX_FLAG_PPU		BIT(MV88E6XXX_CAP_PPU)
 #define MV88E6XXX_FLAG_PPU_ACTIVE	BIT(MV88E6XXX_CAP_PPU_ACTIVE)
@@ -452,25 +459,29 @@
 
 #define MV88E6XXX_FLAGS_FAMILY_6095	\
 	(MV88E6XXX_FLAG_ATU |		\
+	 MV88E6XXX_FLAG_MULTI_CHIP |	\
 	 MV88E6XXX_FLAG_PPU |		\
 	 MV88E6XXX_FLAG_VLANTABLE |	\
 	 MV88E6XXX_FLAG_VTU)
 
 #define MV88E6XXX_FLAGS_FAMILY_6097	\
 	(MV88E6XXX_FLAG_ATU |		\
+	 MV88E6XXX_FLAG_MULTI_CHIP |	\
 	 MV88E6XXX_FLAG_PPU |		\
 	 MV88E6XXX_FLAG_STU |		\
 	 MV88E6XXX_FLAG_VLANTABLE |	\
 	 MV88E6XXX_FLAG_VTU)
 
 #define MV88E6XXX_FLAGS_FAMILY_6165	\
-	(MV88E6XXX_FLAG_STU |		\
+	(MV88E6XXX_FLAG_MULTI_CHIP |	\
+	 MV88E6XXX_FLAG_STU |		\
 	 MV88E6XXX_FLAG_SWITCH_MAC |	\
 	 MV88E6XXX_FLAG_TEMP |		\
 	 MV88E6XXX_FLAG_VTU)
 
 #define MV88E6XXX_FLAGS_FAMILY_6185	\
 	(MV88E6XXX_FLAG_ATU |		\
+	 MV88E6XXX_FLAG_MULTI_CHIP |	\
 	 MV88E6XXX_FLAG_PPU |		\
 	 MV88E6XXX_FLAG_VLANTABLE |	\
 	 MV88E6XXX_FLAG_VTU)
@@ -479,6 +490,7 @@
 	(MV88E6XXX_FLAG_ATU |		\
 	 MV88E6XXX_FLAG_EEE |		\
 	 MV88E6XXX_FLAG_EEPROM |	\
+	 MV88E6XXX_FLAG_MULTI_CHIP |	\
 	 MV88E6XXX_FLAG_PORTSTATE |	\
 	 MV88E6XXX_FLAG_PPU_ACTIVE |	\
 	 MV88E6XXX_FLAG_SMI_PHY |	\
@@ -490,6 +502,7 @@
 
 #define MV88E6XXX_FLAGS_FAMILY_6351	\
 	(MV88E6XXX_FLAG_ATU |		\
+	 MV88E6XXX_FLAG_MULTI_CHIP |	\
 	 MV88E6XXX_FLAG_PORTSTATE |	\
 	 MV88E6XXX_FLAG_PPU_ACTIVE |	\
 	 MV88E6XXX_FLAG_SMI_PHY |	\
@@ -503,6 +516,7 @@
 	(MV88E6XXX_FLAG_ATU |		\
 	 MV88E6XXX_FLAG_EEE |		\
 	 MV88E6XXX_FLAG_EEPROM |	\
+	 MV88E6XXX_FLAG_MULTI_CHIP |	\
 	 MV88E6XXX_FLAG_PORTSTATE |	\
 	 MV88E6XXX_FLAG_PPU_ACTIVE |	\
 	 MV88E6XXX_FLAG_SMI_PHY |	\
@@ -519,6 +533,7 @@
 	const char *name;
 	unsigned int num_databases;
 	unsigned int num_ports;
+	unsigned int port_base_addr;
 	unsigned long flags;
 };
 
@@ -541,6 +556,8 @@
 	u8	data[DSA_MAX_PORTS];
 };
 
+struct mv88e6xxx_ops;
+
 struct mv88e6xxx_priv_port {
 	struct net_device *bridge_dev;
 };
@@ -554,15 +571,13 @@
 	/* The device this structure is associated to */
 	struct device *dev;
 
-	/* When using multi-chip addressing, this mutex protects
-	 * access to the indirect access registers.  (In single-chip
-	 * mode, this mutex is effectively useless.)
-	 */
-	struct mutex	smi_mutex;
+	/* This mutex protects the access to the switch registers */
+	struct mutex reg_lock;
 
 	/* The MII bus and the address on the bus that is used to
 	 * communication with the switch
 	 */
+	const struct mv88e6xxx_ops *smi_ops;
 	struct mii_bus *bus;
 	int sw_addr;
 
@@ -600,6 +615,19 @@
 
 	/* set to size of eeprom if supported by the switch */
 	int		eeprom_len;
+
+	/* Device node for the MDIO bus */
+	struct device_node *mdio_np;
+
+	/* And the MDIO bus itself */
+	struct mii_bus *mdio_bus;
+};
+
+struct mv88e6xxx_ops {
+	int (*read)(struct mv88e6xxx_priv_state *ps,
+		    int addr, int reg, u16 *val);
+	int (*write)(struct mv88e6xxx_priv_state *ps,
+		     int addr, int reg, u16 val);
 };
 
 enum stat_type {
diff --git a/drivers/net/ethernet/8390/ax88796.c b/drivers/net/ethernet/8390/ax88796.c
index c89b9ae..5698f53 100644
--- a/drivers/net/ethernet/8390/ax88796.c
+++ b/drivers/net/ethernet/8390/ax88796.c
@@ -84,7 +84,6 @@
 struct ax_device {
 	struct mii_bus *mii_bus;
 	struct mdiobb_ctrl bb_ctrl;
-	struct phy_device *phy_dev;
 	void __iomem *addr_memr;
 	u8 reg_memr;
 	int link;
@@ -320,7 +319,7 @@
 static void ax_handle_link_change(struct net_device *dev)
 {
 	struct ax_device  *ax = to_ax_dev(dev);
-	struct phy_device *phy_dev = ax->phy_dev;
+	struct phy_device *phy_dev = dev->phydev;
 	int status_change = 0;
 
 	if (phy_dev->link && ((ax->speed != phy_dev->speed) ||
@@ -369,8 +368,6 @@
 	phy_dev->supported &= PHY_BASIC_FEATURES;
 	phy_dev->advertising = phy_dev->supported;
 
-	ax->phy_dev = phy_dev;
-
 	netdev_info(dev, "PHY driver [%s] (mii_bus:phy_addr=%s, irq=%d)\n",
 		    phy_dev->drv->name, phydev_name(phy_dev), phy_dev->irq);
 
@@ -410,7 +407,7 @@
 	ret = ax_mii_probe(dev);
 	if (ret)
 		goto failed_mii_probe;
-	phy_start(ax->phy_dev);
+	phy_start(dev->phydev);
 
 	ret = ax_ei_open(dev);
 	if (ret)
@@ -421,7 +418,7 @@
 	return 0;
 
  failed_ax_ei_open:
-	phy_disconnect(ax->phy_dev);
+	phy_disconnect(dev->phydev);
  failed_mii_probe:
 	ax_phy_switch(dev, 0);
 	free_irq(dev->irq, dev);
@@ -442,7 +439,7 @@
 
 	/* turn the phy off */
 	ax_phy_switch(dev, 0);
-	phy_disconnect(ax->phy_dev);
+	phy_disconnect(dev->phydev);
 
 	free_irq(dev->irq, dev);
 	return 0;
@@ -450,8 +447,7 @@
 
 static int ax_ioctl(struct net_device *dev, struct ifreq *req, int cmd)
 {
-	struct ax_device *ax = to_ax_dev(dev);
-	struct phy_device *phy_dev = ax->phy_dev;
+	struct phy_device *phy_dev = dev->phydev;
 
 	if (!netif_running(dev))
 		return -EINVAL;
@@ -474,28 +470,6 @@
 	strlcpy(info->bus_info, pdev->name, sizeof(info->bus_info));
 }
 
-static int ax_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
-{
-	struct ax_device *ax = to_ax_dev(dev);
-	struct phy_device *phy_dev = ax->phy_dev;
-
-	if (!phy_dev)
-		return -ENODEV;
-
-	return phy_ethtool_gset(phy_dev, cmd);
-}
-
-static int ax_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
-{
-	struct ax_device *ax = to_ax_dev(dev);
-	struct phy_device *phy_dev = ax->phy_dev;
-
-	if (!phy_dev)
-		return -ENODEV;
-
-	return phy_ethtool_sset(phy_dev, cmd);
-}
-
 static u32 ax_get_msglevel(struct net_device *dev)
 {
 	struct ei_device *ei_local = netdev_priv(dev);
@@ -512,12 +486,12 @@
 
 static const struct ethtool_ops ax_ethtool_ops = {
 	.get_drvinfo		= ax_get_drvinfo,
-	.get_settings		= ax_get_settings,
-	.set_settings		= ax_set_settings,
 	.get_link		= ethtool_op_get_link,
 	.get_ts_info		= ethtool_op_get_ts_info,
 	.get_msglevel		= ax_get_msglevel,
 	.set_msglevel		= ax_set_msglevel,
+	.get_link_ksettings	= phy_ethtool_get_link_ksettings,
+	.set_link_ksettings	= phy_ethtool_set_link_ksettings,
 };
 
 #ifdef CONFIG_AX88796_93CX6
diff --git a/drivers/net/ethernet/agere/et131x.c b/drivers/net/ethernet/agere/et131x.c
index 30defe6..cd7e2e5 100644
--- a/drivers/net/ethernet/agere/et131x.c
+++ b/drivers/net/ethernet/agere/et131x.c
@@ -440,7 +440,6 @@
 	struct net_device *netdev;
 	struct pci_dev *pdev;
 	struct mii_bus *mii_bus;
-	struct phy_device *phydev;
 	struct napi_struct napi;
 
 	/* Flags that indicate current state of the adapter */
@@ -864,7 +863,7 @@
 {
 	int32_t delay = 0;
 	struct mac_regs __iomem *mac = &adapter->regs->mac;
-	struct phy_device *phydev = adapter->phydev;
+	struct phy_device *phydev = adapter->netdev->phydev;
 	u32 cfg1;
 	u32 cfg2;
 	u32 ifctrl;
@@ -1035,7 +1034,7 @@
 static void et1310_config_rxmac_regs(struct et131x_adapter *adapter)
 {
 	struct rxmac_regs __iomem *rxmac = &adapter->regs->rxmac;
-	struct phy_device *phydev = adapter->phydev;
+	struct phy_device *phydev = adapter->netdev->phydev;
 	u32 sa_lo;
 	u32 sa_hi = 0;
 	u32 pf_ctrl = 0;
@@ -1230,7 +1229,7 @@
 
 static int et131x_mii_read(struct et131x_adapter *adapter, u8 reg, u16 *value)
 {
-	struct phy_device *phydev = adapter->phydev;
+	struct phy_device *phydev = adapter->netdev->phydev;
 
 	if (!phydev)
 		return -EIO;
@@ -1311,7 +1310,7 @@
 
 static void et1310_config_flow_control(struct et131x_adapter *adapter)
 {
-	struct phy_device *phydev = adapter->phydev;
+	struct phy_device *phydev = adapter->netdev->phydev;
 
 	if (phydev->duplex == DUPLEX_HALF) {
 		adapter->flow = FLOW_NONE;
@@ -1456,7 +1455,7 @@
 static void et1310_phy_power_switch(struct et131x_adapter *adapter, bool down)
 {
 	u16 data;
-	struct  phy_device *phydev = adapter->phydev;
+	struct  phy_device *phydev = adapter->netdev->phydev;
 
 	et131x_mii_read(adapter, MII_BMCR, &data);
 	data &= ~BMCR_PDOWN;
@@ -1469,7 +1468,7 @@
 static void et131x_xcvr_init(struct et131x_adapter *adapter)
 {
 	u16 lcr2;
-	struct  phy_device *phydev = adapter->phydev;
+	struct  phy_device *phydev = adapter->netdev->phydev;
 
 	/* Set the LED behavior such that LED 1 indicates speed (off =
 	 * 10Mbits, blink = 100Mbits, on = 1000Mbits) and LED 2 indicates
@@ -2111,7 +2110,7 @@
 /* et131x_set_rx_dma_timer - Set the heartbeat timer according to line rate */
 static void et131x_set_rx_dma_timer(struct et131x_adapter *adapter)
 {
-	struct phy_device *phydev = adapter->phydev;
+	struct phy_device *phydev = adapter->netdev->phydev;
 
 	/* For version B silicon, we do not use the RxDMA timer for 10 and 100
 	 * Mbits/s line rates. We do not enable and RxDMA interrupt coalescing.
@@ -2426,7 +2425,7 @@
 	struct sk_buff *skb = tcb->skb;
 	u32 nr_frags = skb_shinfo(skb)->nr_frags + 1;
 	struct skb_frag_struct *frags = &skb_shinfo(skb)->frags[0];
-	struct phy_device *phydev = adapter->phydev;
+	struct phy_device *phydev = adapter->netdev->phydev;
 	dma_addr_t dma_addr;
 	struct tx_ring *tx_ring = &adapter->tx_ring;
 
@@ -2791,22 +2790,6 @@
 	spin_unlock_irqrestore(&adapter->tcb_send_qlock, flags);
 }
 
-static int et131x_get_settings(struct net_device *netdev,
-			       struct ethtool_cmd *cmd)
-{
-	struct et131x_adapter *adapter = netdev_priv(netdev);
-
-	return phy_ethtool_gset(adapter->phydev, cmd);
-}
-
-static int et131x_set_settings(struct net_device *netdev,
-			       struct ethtool_cmd *cmd)
-{
-	struct et131x_adapter *adapter = netdev_priv(netdev);
-
-	return phy_ethtool_sset(adapter->phydev, cmd);
-}
-
 static int et131x_get_regs_len(struct net_device *netdev)
 {
 #define ET131X_REGS_LEN 256
@@ -2979,12 +2962,12 @@
 }
 
 static struct ethtool_ops et131x_ethtool_ops = {
-	.get_settings	= et131x_get_settings,
-	.set_settings	= et131x_set_settings,
 	.get_drvinfo	= et131x_get_drvinfo,
 	.get_regs_len	= et131x_get_regs_len,
 	.get_regs	= et131x_get_regs,
 	.get_link	= ethtool_op_get_link,
+	.get_link_ksettings = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings = phy_ethtool_set_link_ksettings,
 };
 
 /* et131x_hwaddr_init - set up the MAC Address */
@@ -3098,7 +3081,7 @@
 static void et131x_error_timer_handler(unsigned long data)
 {
 	struct et131x_adapter *adapter = (struct et131x_adapter *)data;
-	struct phy_device *phydev = adapter->phydev;
+	struct phy_device *phydev = adapter->netdev->phydev;
 
 	if (et1310_in_phy_coma(adapter)) {
 		/* Bring the device immediately out of coma, to
@@ -3168,7 +3151,7 @@
 static void et131x_adjust_link(struct net_device *netdev)
 {
 	struct et131x_adapter *adapter = netdev_priv(netdev);
-	struct  phy_device *phydev = adapter->phydev;
+	struct  phy_device *phydev = netdev->phydev;
 
 	if (!phydev)
 		return;
@@ -3287,7 +3270,6 @@
 
 	phydev->advertising = phydev->supported;
 	phydev->autoneg = AUTONEG_ENABLE;
-	adapter->phydev = phydev;
 
 	phy_attached_info(phydev);
 
@@ -3323,7 +3305,7 @@
 
 	unregister_netdev(netdev);
 	netif_napi_del(&adapter->napi);
-	phy_disconnect(adapter->phydev);
+	phy_disconnect(netdev->phydev);
 	mdiobus_unregister(adapter->mii_bus);
 	mdiobus_free(adapter->mii_bus);
 
@@ -3338,20 +3320,16 @@
 
 static void et131x_up(struct net_device *netdev)
 {
-	struct et131x_adapter *adapter = netdev_priv(netdev);
-
 	et131x_enable_txrx(netdev);
-	phy_start(adapter->phydev);
+	phy_start(netdev->phydev);
 }
 
 static void et131x_down(struct net_device *netdev)
 {
-	struct et131x_adapter *adapter = netdev_priv(netdev);
-
 	/* Save the timestamp for the TX watchdog, prevent a timeout */
 	netif_trans_update(netdev);
 
-	phy_stop(adapter->phydev);
+	phy_stop(netdev->phydev);
 	et131x_disable_txrx(netdev);
 }
 
@@ -3684,12 +3662,10 @@
 static int et131x_ioctl(struct net_device *netdev, struct ifreq *reqbuf,
 			int cmd)
 {
-	struct et131x_adapter *adapter = netdev_priv(netdev);
-
-	if (!adapter->phydev)
+	if (!netdev->phydev)
 		return -EINVAL;
 
-	return phy_mii_ioctl(adapter->phydev, reqbuf, cmd);
+	return phy_mii_ioctl(netdev->phydev, reqbuf, cmd);
 }
 
 /* et131x_set_packet_filter - Configures the Rx Packet filtering */
@@ -4073,7 +4049,7 @@
 	return rc;
 
 err_phy_disconnect:
-	phy_disconnect(adapter->phydev);
+	phy_disconnect(netdev->phydev);
 err_mdio_unregister:
 	mdiobus_unregister(adapter->mii_bus);
 err_mdio_free:
diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c
index de2c4bf..6ffdff6 100644
--- a/drivers/net/ethernet/allwinner/sun4i-emac.c
+++ b/drivers/net/ethernet/allwinner/sun4i-emac.c
@@ -77,7 +77,6 @@
 
 	int			emacrx_completed_flag;
 
-	struct phy_device	*phy_dev;
 	struct device_node	*phy_node;
 	unsigned int		link;
 	unsigned int		speed;
@@ -115,7 +114,7 @@
 static void emac_handle_link_change(struct net_device *dev)
 {
 	struct emac_board_info *db = netdev_priv(dev);
-	struct phy_device *phydev = db->phy_dev;
+	struct phy_device *phydev = dev->phydev;
 	unsigned long flags;
 	int status_change = 0;
 
@@ -154,21 +153,22 @@
 static int emac_mdio_probe(struct net_device *dev)
 {
 	struct emac_board_info *db = netdev_priv(dev);
+	struct phy_device *phydev;
 
 	/* to-do: PHY interrupts are currently not supported */
 
 	/* attach the mac to the phy */
-	db->phy_dev = of_phy_connect(db->ndev, db->phy_node,
-				     &emac_handle_link_change, 0,
-				     db->phy_interface);
-	if (!db->phy_dev) {
+	phydev = of_phy_connect(db->ndev, db->phy_node,
+				&emac_handle_link_change, 0,
+				db->phy_interface);
+	if (!phydev) {
 		netdev_err(db->ndev, "could not find the PHY\n");
 		return -ENODEV;
 	}
 
 	/* mask with MAC supported features */
-	db->phy_dev->supported &= PHY_BASIC_FEATURES;
-	db->phy_dev->advertising = db->phy_dev->supported;
+	phydev->supported &= PHY_BASIC_FEATURES;
+	phydev->advertising = phydev->supported;
 
 	db->link = 0;
 	db->speed = 0;
@@ -179,10 +179,7 @@
 
 static void emac_mdio_remove(struct net_device *dev)
 {
-	struct emac_board_info *db = netdev_priv(dev);
-
-	phy_disconnect(db->phy_dev);
-	db->phy_dev = NULL;
+	phy_disconnect(dev->phydev);
 }
 
 static void emac_reset(struct emac_board_info *db)
@@ -208,8 +205,7 @@
 
 static int emac_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 {
-	struct emac_board_info *dm = netdev_priv(dev);
-	struct phy_device *phydev = dm->phy_dev;
+	struct phy_device *phydev = dev->phydev;
 
 	if (!netif_running(dev))
 		return -EINVAL;
@@ -229,33 +225,11 @@
 	strlcpy(info->bus_info, dev_name(&dev->dev), sizeof(info->bus_info));
 }
 
-static int emac_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
-{
-	struct emac_board_info *dm = netdev_priv(dev);
-	struct phy_device *phydev = dm->phy_dev;
-
-	if (!phydev)
-		return -ENODEV;
-
-	return phy_ethtool_gset(phydev, cmd);
-}
-
-static int emac_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
-{
-	struct emac_board_info *dm = netdev_priv(dev);
-	struct phy_device *phydev = dm->phy_dev;
-
-	if (!phydev)
-		return -ENODEV;
-
-	return phy_ethtool_sset(phydev, cmd);
-}
-
 static const struct ethtool_ops emac_ethtool_ops = {
 	.get_drvinfo	= emac_get_drvinfo,
-	.get_settings	= emac_get_settings,
-	.set_settings	= emac_set_settings,
 	.get_link	= ethtool_op_get_link,
+	.get_link_ksettings = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings = phy_ethtool_set_link_ksettings,
 };
 
 static unsigned int emac_setup(struct net_device *ndev)
@@ -744,7 +718,7 @@
 		return ret;
 	}
 
-	phy_start(db->phy_dev);
+	phy_start(dev->phydev);
 	netif_start_queue(dev);
 
 	return 0;
@@ -781,7 +755,7 @@
 	netif_stop_queue(ndev);
 	netif_carrier_off(ndev);
 
-	phy_stop(db->phy_dev);
+	phy_stop(ndev->phydev);
 
 	emac_mdio_remove(ndev);
 
diff --git a/drivers/net/ethernet/altera/altera_tse.h b/drivers/net/ethernet/altera/altera_tse.h
index 103c30d..e005200 100644
--- a/drivers/net/ethernet/altera/altera_tse.h
+++ b/drivers/net/ethernet/altera/altera_tse.h
@@ -473,7 +473,6 @@
 	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;
diff --git a/drivers/net/ethernet/altera/altera_tse_ethtool.c b/drivers/net/ethernet/altera/altera_tse_ethtool.c
index be72e1e..7c36771 100644
--- a/drivers/net/ethernet/altera/altera_tse_ethtool.c
+++ b/drivers/net/ethernet/altera/altera_tse_ethtool.c
@@ -233,40 +233,18 @@
 		buf[i] = csrrd32(priv->mac_dev, i * 4);
 }
 
-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,
+	.get_link_ksettings = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings = phy_ethtool_set_link_ksettings,
 };
 
 void altera_tse_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c
index f749e4d..49025e9 100644
--- a/drivers/net/ethernet/altera/altera_tse_main.c
+++ b/drivers/net/ethernet/altera/altera_tse_main.c
@@ -625,7 +625,7 @@
 static void altera_tse_adjust_link(struct net_device *dev)
 {
 	struct altera_tse_private *priv = netdev_priv(dev);
-	struct phy_device *phydev = priv->phydev;
+	struct phy_device *phydev = dev->phydev;
 	int new_state = 0;
 
 	/* only change config if there is a link */
@@ -845,7 +845,6 @@
 	netdev_dbg(dev, "attached to PHY %d UID 0x%08x Link = %d\n",
 		   phydev->mdio.addr, phydev->phy_id, phydev->link);
 
-	priv->phydev = phydev;
 	return 0;
 }
 
@@ -1172,8 +1171,8 @@
 
 	spin_unlock_irqrestore(&priv->rxdma_irq_lock, flags);
 
-	if (priv->phydev)
-		phy_start(priv->phydev);
+	if (dev->phydev)
+		phy_start(dev->phydev);
 
 	napi_enable(&priv->napi);
 	netif_start_queue(dev);
@@ -1205,8 +1204,8 @@
 	unsigned long int flags;
 
 	/* Stop the PHY */
-	if (priv->phydev)
-		phy_stop(priv->phydev);
+	if (dev->phydev)
+		phy_stop(dev->phydev);
 
 	netif_stop_queue(dev);
 	napi_disable(&priv->napi);
@@ -1545,10 +1544,9 @@
 static int altera_tse_remove(struct platform_device *pdev)
 {
 	struct net_device *ndev = platform_get_drvdata(pdev);
-	struct altera_tse_private *priv = netdev_priv(ndev);
 
-	if (priv->phydev)
-		phy_disconnect(priv->phydev);
+	if (ndev->phydev)
+		phy_disconnect(ndev->phydev);
 
 	platform_set_drvdata(pdev, NULL);
 	altera_tse_mdio_destroy(ndev);
diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c
index 08a23e6..dc2c35d 100644
--- a/drivers/net/ethernet/aurora/nb8800.c
+++ b/drivers/net/ethernet/aurora/nb8800.c
@@ -631,7 +631,7 @@
 static void nb8800_pause_config(struct net_device *dev)
 {
 	struct nb8800_priv *priv = netdev_priv(dev);
-	struct phy_device *phydev = priv->phydev;
+	struct phy_device *phydev = dev->phydev;
 	u32 rxcr;
 
 	if (priv->pause_aneg) {
@@ -664,7 +664,7 @@
 static void nb8800_link_reconfigure(struct net_device *dev)
 {
 	struct nb8800_priv *priv = netdev_priv(dev);
-	struct phy_device *phydev = priv->phydev;
+	struct phy_device *phydev = dev->phydev;
 	int change = 0;
 
 	if (phydev->link) {
@@ -690,7 +690,7 @@
 	}
 
 	if (change)
-		phy_print_status(priv->phydev);
+		phy_print_status(phydev);
 }
 
 static void nb8800_update_mac_addr(struct net_device *dev)
@@ -935,9 +935,10 @@
 static void nb8800_pause_adv(struct net_device *dev)
 {
 	struct nb8800_priv *priv = netdev_priv(dev);
+	struct phy_device *phydev = dev->phydev;
 	u32 adv = 0;
 
-	if (!priv->phydev)
+	if (!phydev)
 		return;
 
 	if (priv->pause_rx)
@@ -945,13 +946,14 @@
 	if (priv->pause_tx)
 		adv ^= ADVERTISED_Asym_Pause;
 
-	priv->phydev->supported |= adv;
-	priv->phydev->advertising |= adv;
+	phydev->supported |= adv;
+	phydev->advertising |= adv;
 }
 
 static int nb8800_open(struct net_device *dev)
 {
 	struct nb8800_priv *priv = netdev_priv(dev);
+	struct phy_device *phydev;
 	int err;
 
 	/* clear any pending interrupts */
@@ -969,10 +971,10 @@
 	nb8800_mac_rx(dev, true);
 	nb8800_mac_tx(dev, true);
 
-	priv->phydev = of_phy_connect(dev, priv->phy_node,
-				      nb8800_link_reconfigure, 0,
-				      priv->phy_mode);
-	if (!priv->phydev)
+	phydev = of_phy_connect(dev, priv->phy_node,
+				nb8800_link_reconfigure, 0,
+				priv->phy_mode);
+	if (!phydev)
 		goto err_free_irq;
 
 	nb8800_pause_adv(dev);
@@ -982,7 +984,7 @@
 	netif_start_queue(dev);
 
 	nb8800_start_rx(dev);
-	phy_start(priv->phydev);
+	phy_start(phydev);
 
 	return 0;
 
@@ -997,8 +999,9 @@
 static int nb8800_stop(struct net_device *dev)
 {
 	struct nb8800_priv *priv = netdev_priv(dev);
+	struct phy_device *phydev = dev->phydev;
 
-	phy_stop(priv->phydev);
+	phy_stop(phydev);
 
 	netif_stop_queue(dev);
 	napi_disable(&priv->napi);
@@ -1007,8 +1010,7 @@
 	nb8800_mac_rx(dev, false);
 	nb8800_mac_tx(dev, false);
 
-	phy_disconnect(priv->phydev);
-	priv->phydev = NULL;
+	phy_disconnect(phydev);
 
 	free_irq(dev->irq, dev);
 
@@ -1019,9 +1021,7 @@
 
 static int nb8800_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 {
-	struct nb8800_priv *priv = netdev_priv(dev);
-
-	return phy_mii_ioctl(priv->phydev, rq, cmd);
+	return phy_mii_ioctl(dev->phydev, rq, cmd);
 }
 
 static const struct net_device_ops nb8800_netdev_ops = {
@@ -1035,34 +1035,14 @@
 	.ndo_validate_addr	= eth_validate_addr,
 };
 
-static int nb8800_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
-{
-	struct nb8800_priv *priv = netdev_priv(dev);
-
-	if (!priv->phydev)
-		return -ENODEV;
-
-	return phy_ethtool_gset(priv->phydev, cmd);
-}
-
-static int nb8800_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
-{
-	struct nb8800_priv *priv = netdev_priv(dev);
-
-	if (!priv->phydev)
-		return -ENODEV;
-
-	return phy_ethtool_sset(priv->phydev, cmd);
-}
-
 static int nb8800_nway_reset(struct net_device *dev)
 {
-	struct nb8800_priv *priv = netdev_priv(dev);
+	struct phy_device *phydev = dev->phydev;
 
-	if (!priv->phydev)
+	if (!phydev)
 		return -ENODEV;
 
-	return genphy_restart_aneg(priv->phydev);
+	return genphy_restart_aneg(phydev);
 }
 
 static void nb8800_get_pauseparam(struct net_device *dev,
@@ -1079,6 +1059,7 @@
 				 struct ethtool_pauseparam *pp)
 {
 	struct nb8800_priv *priv = netdev_priv(dev);
+	struct phy_device *phydev = dev->phydev;
 
 	priv->pause_aneg = pp->autoneg;
 	priv->pause_rx = pp->rx_pause;
@@ -1088,8 +1069,8 @@
 
 	if (!priv->pause_aneg)
 		nb8800_pause_config(dev);
-	else if (priv->phydev)
-		phy_start_aneg(priv->phydev);
+	else if (phydev)
+		phy_start_aneg(phydev);
 
 	return 0;
 }
@@ -1182,8 +1163,6 @@
 }
 
 static const struct ethtool_ops nb8800_ethtool_ops = {
-	.get_settings		= nb8800_get_settings,
-	.set_settings		= nb8800_set_settings,
 	.nway_reset		= nb8800_nway_reset,
 	.get_link		= ethtool_op_get_link,
 	.get_pauseparam		= nb8800_get_pauseparam,
@@ -1191,6 +1170,8 @@
 	.get_sset_count		= nb8800_get_sset_count,
 	.get_strings		= nb8800_get_strings,
 	.get_ethtool_stats	= nb8800_get_ethtool_stats,
+	.get_link_ksettings	= phy_ethtool_get_link_ksettings,
+	.set_link_ksettings	= phy_ethtool_set_link_ksettings,
 };
 
 static int nb8800_hw_init(struct net_device *dev)
diff --git a/drivers/net/ethernet/aurora/nb8800.h b/drivers/net/ethernet/aurora/nb8800.h
index e5adbc2..6ec4a95 100644
--- a/drivers/net/ethernet/aurora/nb8800.h
+++ b/drivers/net/ethernet/aurora/nb8800.h
@@ -284,7 +284,6 @@
 
 	struct mii_bus			*mii_bus;
 	struct device_node		*phy_node;
-	struct phy_device		*phydev;
 
 	/* PHY connection type from DT */
 	int				phy_mode;
diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index 18042c2..d74a92e 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -139,26 +139,6 @@
 	  Virtualization support in the 578xx and 57712 products. This
 	  allows for virtual function acceleration in virtual environments.
 
-config BNX2X_VXLAN
-	bool "Virtual eXtensible Local Area Network support"
-	default n
-	depends on BNX2X && VXLAN && !(BNX2X=y && VXLAN=m)
-	---help---
-	  This enables hardward offload support for VXLAN protocol over the
-	  NetXtremeII series adapters.
-	  Say Y here if you want to enable hardware offload support for
-	  Virtual eXtensible Local Area Network (VXLAN) in the driver.
-
-config BNX2X_GENEVE
-	bool "Generic Network Virtualization Encapsulation (GENEVE) support"
-	depends on BNX2X && GENEVE && !(BNX2X=y && GENEVE=m)
-	---help---
-          This allows one to create GENEVE virtual interfaces that provide
-          Layer 2 Networks over Layer 3 Networks. GENEVE is often used
-          to tunnel virtual network infrastructure in virtualized environments.
-	  Say Y here if you want to enable hardware offload support for
-	  Generic Network Virtualization Encapsulation (GENEVE) in the driver.
-
 config BGMAC
 	tristate "BCMA bus GBit core support"
 	depends on BCMA && BCMA_HOST_SOC
@@ -186,7 +166,6 @@
 config BNXT
 	tristate "Broadcom NetXtreme-C/E support"
 	depends on PCI
-	depends on VXLAN || VXLAN=n
 	select FW_LOADER
 	select LIBCRC32C
 	---help---
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 543bf38..834afbb 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -96,28 +96,6 @@
 }
 
 /* Ethtool operations */
-static int bcm_sysport_set_settings(struct net_device *dev,
-				    struct ethtool_cmd *cmd)
-{
-	struct bcm_sysport_priv *priv = netdev_priv(dev);
-
-	if (!netif_running(dev))
-		return -EINVAL;
-
-	return phy_ethtool_sset(priv->phydev, cmd);
-}
-
-static int bcm_sysport_get_settings(struct net_device *dev,
-				    struct ethtool_cmd *cmd)
-{
-	struct bcm_sysport_priv *priv = netdev_priv(dev);
-
-	if (!netif_running(dev))
-		return -EINVAL;
-
-	return phy_ethtool_gset(priv->phydev, cmd);
-}
-
 static int bcm_sysport_set_rx_csum(struct net_device *dev,
 				   netdev_features_t wanted)
 {
@@ -1127,7 +1105,7 @@
 static void bcm_sysport_adj_link(struct net_device *dev)
 {
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
-	struct phy_device *phydev = priv->phydev;
+	struct phy_device *phydev = dev->phydev;
 	unsigned int changed = 0;
 	u32 cmd_bits = 0, reg;
 
@@ -1182,7 +1160,7 @@
 		umac_writel(priv, reg, UMAC_CMD);
 	}
 
-	phy_print_status(priv->phydev);
+	phy_print_status(phydev);
 }
 
 static int bcm_sysport_init_tx_ring(struct bcm_sysport_priv *priv,
@@ -1525,7 +1503,7 @@
 	/* Enable RX interrupt and TX ring full interrupt */
 	intrl2_0_mask_clear(priv, INTRL2_0_RDMA_MBDONE | INTRL2_0_TX_RING_FULL);
 
-	phy_start(priv->phydev);
+	phy_start(dev->phydev);
 
 	/* Enable TX interrupts for the 32 TXQs */
 	intrl2_1_mask_clear(priv, 0xffffffff);
@@ -1546,6 +1524,7 @@
 static int bcm_sysport_open(struct net_device *dev)
 {
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
+	struct phy_device *phydev;
 	unsigned int i;
 	int ret;
 
@@ -1570,9 +1549,9 @@
 	/* Read CRC forward */
 	priv->crc_fwd = !!(umac_readl(priv, UMAC_CMD) & CMD_CRC_FWD);
 
-	priv->phydev = of_phy_connect(dev, priv->phy_dn, bcm_sysport_adj_link,
-					0, priv->phy_interface);
-	if (!priv->phydev) {
+	phydev = of_phy_connect(dev, priv->phy_dn, bcm_sysport_adj_link,
+				0, priv->phy_interface);
+	if (!phydev) {
 		netdev_err(dev, "could not attach to PHY\n");
 		return -ENODEV;
 	}
@@ -1650,7 +1629,7 @@
 out_free_irq0:
 	free_irq(priv->irq0, dev);
 out_phy_disconnect:
-	phy_disconnect(priv->phydev);
+	phy_disconnect(phydev);
 	return ret;
 }
 
@@ -1661,7 +1640,7 @@
 	/* stop all software from updating hardware */
 	netif_tx_stop_all_queues(dev);
 	napi_disable(&priv->napi);
-	phy_stop(priv->phydev);
+	phy_stop(dev->phydev);
 
 	/* mask all interrupts */
 	intrl2_0_mask_set(priv, 0xffffffff);
@@ -1708,14 +1687,12 @@
 	free_irq(priv->irq1, dev);
 
 	/* Disconnect from PHY */
-	phy_disconnect(priv->phydev);
+	phy_disconnect(dev->phydev);
 
 	return 0;
 }
 
 static struct ethtool_ops bcm_sysport_ethtool_ops = {
-	.get_settings		= bcm_sysport_get_settings,
-	.set_settings		= bcm_sysport_set_settings,
 	.get_drvinfo		= bcm_sysport_get_drvinfo,
 	.get_msglevel		= bcm_sysport_get_msglvl,
 	.set_msglevel		= bcm_sysport_set_msglvl,
@@ -1727,6 +1704,8 @@
 	.set_wol		= bcm_sysport_set_wol,
 	.get_coalesce		= bcm_sysport_get_coalesce,
 	.set_coalesce		= bcm_sysport_set_coalesce,
+	.get_link_ksettings     = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings     = phy_ethtool_set_link_ksettings,
 };
 
 static const struct net_device_ops bcm_sysport_netdev_ops = {
@@ -1929,7 +1908,7 @@
 
 	bcm_sysport_netif_stop(dev);
 
-	phy_suspend(priv->phydev);
+	phy_suspend(dev->phydev);
 
 	netif_device_detach(dev);
 
@@ -2055,7 +2034,7 @@
 		goto out_free_rx_ring;
 	}
 
-	phy_resume(priv->phydev);
+	phy_resume(dev->phydev);
 
 	bcm_sysport_netif_start(dev);
 
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h
index f28bf54..1c82e3d 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.h
+++ b/drivers/net/ethernet/broadcom/bcmsysport.h
@@ -670,7 +670,6 @@
 
 	/* PHY device */
 	struct device_node	*phy_dn;
-	struct phy_device	*phydev;
 	phy_interface_t		phy_interface;
 	int			old_pause;
 	int			old_link;
diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index ee5f431..e6e74ca 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -246,6 +246,8 @@
 
 err_drop:
 	dev_kfree_skb(skb);
+	net_dev->stats.tx_dropped++;
+	net_dev->stats.tx_errors++;
 	return NETDEV_TX_OK;
 }
 
@@ -284,6 +286,8 @@
 				       DMA_TO_DEVICE);
 
 		if (slot->skb) {
+			bgmac->net_dev->stats.tx_bytes += slot->skb->len;
+			bgmac->net_dev->stats.tx_packets++;
 			bytes_compl += slot->skb->len;
 			pkts_compl++;
 
@@ -464,6 +468,7 @@
 				bgmac_err(bgmac, "Found poisoned packet at slot %d, DMA issue!\n",
 					  ring->start);
 				put_page(virt_to_head_page(buf));
+				bgmac->net_dev->stats.rx_errors++;
 				break;
 			}
 
@@ -471,6 +476,8 @@
 				bgmac_err(bgmac, "Found oversized packet at slot %d, DMA issue!\n",
 					  ring->start);
 				put_page(virt_to_head_page(buf));
+				bgmac->net_dev->stats.rx_length_errors++;
+				bgmac->net_dev->stats.rx_errors++;
 				break;
 			}
 
@@ -481,6 +488,7 @@
 			if (unlikely(!skb)) {
 				bgmac_err(bgmac, "build_skb failed\n");
 				put_page(virt_to_head_page(buf));
+				bgmac->net_dev->stats.rx_errors++;
 				break;
 			}
 			skb_put(skb, BGMAC_RX_FRAME_OFFSET +
@@ -490,6 +498,8 @@
 
 			skb_checksum_none_assert(skb);
 			skb->protocol = eth_type_trans(skb, bgmac->net_dev);
+			bgmac->net_dev->stats.rx_bytes += len;
+			bgmac->net_dev->stats.rx_packets++;
 			napi_gro_receive(&bgmac->napi, skb);
 			handled++;
 		} while (0);
@@ -1310,7 +1320,7 @@
 	}
 	napi_enable(&bgmac->napi);
 
-	phy_start(bgmac->phy_dev);
+	phy_start(net_dev->phydev);
 
 	netif_carrier_on(net_dev);
 	return 0;
@@ -1322,7 +1332,7 @@
 
 	netif_carrier_off(net_dev);
 
-	phy_stop(bgmac->phy_dev);
+	phy_stop(net_dev->phydev);
 
 	napi_disable(&bgmac->napi);
 	bgmac_chip_intrs_off(bgmac);
@@ -1360,12 +1370,10 @@
 
 static int bgmac_ioctl(struct net_device *net_dev, struct ifreq *ifr, int cmd)
 {
-	struct bgmac *bgmac = netdev_priv(net_dev);
-
 	if (!netif_running(net_dev))
 		return -EINVAL;
 
-	return phy_mii_ioctl(bgmac->phy_dev, ifr, cmd);
+	return phy_mii_ioctl(net_dev->phydev, ifr, cmd);
 }
 
 static const struct net_device_ops bgmac_netdev_ops = {
@@ -1382,20 +1390,125 @@
  * ethtool_ops
  **************************************************/
 
-static int bgmac_get_settings(struct net_device *net_dev,
-			      struct ethtool_cmd *cmd)
-{
-	struct bgmac *bgmac = netdev_priv(net_dev);
+struct bgmac_stat {
+	u8 size;
+	u32 offset;
+	const char *name;
+};
 
-	return phy_ethtool_gset(bgmac->phy_dev, cmd);
+static struct bgmac_stat bgmac_get_strings_stats[] = {
+	{ 8, BGMAC_TX_GOOD_OCTETS, "tx_good_octets" },
+	{ 4, BGMAC_TX_GOOD_PKTS, "tx_good" },
+	{ 8, BGMAC_TX_OCTETS, "tx_octets" },
+	{ 4, BGMAC_TX_PKTS, "tx_pkts" },
+	{ 4, BGMAC_TX_BROADCAST_PKTS, "tx_broadcast" },
+	{ 4, BGMAC_TX_MULTICAST_PKTS, "tx_multicast" },
+	{ 4, BGMAC_TX_LEN_64, "tx_64" },
+	{ 4, BGMAC_TX_LEN_65_TO_127, "tx_65_127" },
+	{ 4, BGMAC_TX_LEN_128_TO_255, "tx_128_255" },
+	{ 4, BGMAC_TX_LEN_256_TO_511, "tx_256_511" },
+	{ 4, BGMAC_TX_LEN_512_TO_1023, "tx_512_1023" },
+	{ 4, BGMAC_TX_LEN_1024_TO_1522, "tx_1024_1522" },
+	{ 4, BGMAC_TX_LEN_1523_TO_2047, "tx_1523_2047" },
+	{ 4, BGMAC_TX_LEN_2048_TO_4095, "tx_2048_4095" },
+	{ 4, BGMAC_TX_LEN_4096_TO_8191, "tx_4096_8191" },
+	{ 4, BGMAC_TX_LEN_8192_TO_MAX, "tx_8192_max" },
+	{ 4, BGMAC_TX_JABBER_PKTS, "tx_jabber" },
+	{ 4, BGMAC_TX_OVERSIZE_PKTS, "tx_oversize" },
+	{ 4, BGMAC_TX_FRAGMENT_PKTS, "tx_fragment" },
+	{ 4, BGMAC_TX_UNDERRUNS, "tx_underruns" },
+	{ 4, BGMAC_TX_TOTAL_COLS, "tx_total_cols" },
+	{ 4, BGMAC_TX_SINGLE_COLS, "tx_single_cols" },
+	{ 4, BGMAC_TX_MULTIPLE_COLS, "tx_multiple_cols" },
+	{ 4, BGMAC_TX_EXCESSIVE_COLS, "tx_excessive_cols" },
+	{ 4, BGMAC_TX_LATE_COLS, "tx_late_cols" },
+	{ 4, BGMAC_TX_DEFERED, "tx_defered" },
+	{ 4, BGMAC_TX_CARRIER_LOST, "tx_carrier_lost" },
+	{ 4, BGMAC_TX_PAUSE_PKTS, "tx_pause" },
+	{ 4, BGMAC_TX_UNI_PKTS, "tx_unicast" },
+	{ 4, BGMAC_TX_Q0_PKTS, "tx_q0" },
+	{ 8, BGMAC_TX_Q0_OCTETS, "tx_q0_octets" },
+	{ 4, BGMAC_TX_Q1_PKTS, "tx_q1" },
+	{ 8, BGMAC_TX_Q1_OCTETS, "tx_q1_octets" },
+	{ 4, BGMAC_TX_Q2_PKTS, "tx_q2" },
+	{ 8, BGMAC_TX_Q2_OCTETS, "tx_q2_octets" },
+	{ 4, BGMAC_TX_Q3_PKTS, "tx_q3" },
+	{ 8, BGMAC_TX_Q3_OCTETS, "tx_q3_octets" },
+	{ 8, BGMAC_RX_GOOD_OCTETS, "rx_good_octets" },
+	{ 4, BGMAC_RX_GOOD_PKTS, "rx_good" },
+	{ 8, BGMAC_RX_OCTETS, "rx_octets" },
+	{ 4, BGMAC_RX_PKTS, "rx_pkts" },
+	{ 4, BGMAC_RX_BROADCAST_PKTS, "rx_broadcast" },
+	{ 4, BGMAC_RX_MULTICAST_PKTS, "rx_multicast" },
+	{ 4, BGMAC_RX_LEN_64, "rx_64" },
+	{ 4, BGMAC_RX_LEN_65_TO_127, "rx_65_127" },
+	{ 4, BGMAC_RX_LEN_128_TO_255, "rx_128_255" },
+	{ 4, BGMAC_RX_LEN_256_TO_511, "rx_256_511" },
+	{ 4, BGMAC_RX_LEN_512_TO_1023, "rx_512_1023" },
+	{ 4, BGMAC_RX_LEN_1024_TO_1522, "rx_1024_1522" },
+	{ 4, BGMAC_RX_LEN_1523_TO_2047, "rx_1523_2047" },
+	{ 4, BGMAC_RX_LEN_2048_TO_4095, "rx_2048_4095" },
+	{ 4, BGMAC_RX_LEN_4096_TO_8191, "rx_4096_8191" },
+	{ 4, BGMAC_RX_LEN_8192_TO_MAX, "rx_8192_max" },
+	{ 4, BGMAC_RX_JABBER_PKTS, "rx_jabber" },
+	{ 4, BGMAC_RX_OVERSIZE_PKTS, "rx_oversize" },
+	{ 4, BGMAC_RX_FRAGMENT_PKTS, "rx_fragment" },
+	{ 4, BGMAC_RX_MISSED_PKTS, "rx_missed" },
+	{ 4, BGMAC_RX_CRC_ALIGN_ERRS, "rx_crc_align" },
+	{ 4, BGMAC_RX_UNDERSIZE, "rx_undersize" },
+	{ 4, BGMAC_RX_CRC_ERRS, "rx_crc" },
+	{ 4, BGMAC_RX_ALIGN_ERRS, "rx_align" },
+	{ 4, BGMAC_RX_SYMBOL_ERRS, "rx_symbol" },
+	{ 4, BGMAC_RX_PAUSE_PKTS, "rx_pause" },
+	{ 4, BGMAC_RX_NONPAUSE_PKTS, "rx_nonpause" },
+	{ 4, BGMAC_RX_SACHANGES, "rx_sa_changes" },
+	{ 4, BGMAC_RX_UNI_PKTS, "rx_unicast" },
+};
+
+#define BGMAC_STATS_LEN	ARRAY_SIZE(bgmac_get_strings_stats)
+
+static int bgmac_get_sset_count(struct net_device *dev, int string_set)
+{
+	switch (string_set) {
+	case ETH_SS_STATS:
+		return BGMAC_STATS_LEN;
+	}
+
+	return -EOPNOTSUPP;
 }
 
-static int bgmac_set_settings(struct net_device *net_dev,
-			      struct ethtool_cmd *cmd)
+static void bgmac_get_strings(struct net_device *dev, u32 stringset,
+			      u8 *data)
 {
-	struct bgmac *bgmac = netdev_priv(net_dev);
+	int i;
 
-	return phy_ethtool_sset(bgmac->phy_dev, cmd);
+	if (stringset != ETH_SS_STATS)
+		return;
+
+	for (i = 0; i < BGMAC_STATS_LEN; i++)
+		strlcpy(data + i * ETH_GSTRING_LEN,
+			bgmac_get_strings_stats[i].name, ETH_GSTRING_LEN);
+}
+
+static void bgmac_get_ethtool_stats(struct net_device *dev,
+				    struct ethtool_stats *ss, uint64_t *data)
+{
+	struct bgmac *bgmac = netdev_priv(dev);
+	const struct bgmac_stat *s;
+	unsigned int i;
+	u64 val;
+
+	if (!netif_running(dev))
+		return;
+
+	for (i = 0; i < BGMAC_STATS_LEN; i++) {
+		s = &bgmac_get_strings_stats[i];
+		val = 0;
+		if (s->size == 8)
+			val = (u64)bgmac_read(bgmac, s->offset + 4) << 32;
+		val |= bgmac_read(bgmac, s->offset);
+		data[i] = val;
+	}
 }
 
 static void bgmac_get_drvinfo(struct net_device *net_dev,
@@ -1406,9 +1519,12 @@
 }
 
 static const struct ethtool_ops bgmac_ethtool_ops = {
-	.get_settings		= bgmac_get_settings,
-	.set_settings		= bgmac_set_settings,
+	.get_strings		= bgmac_get_strings,
+	.get_sset_count		= bgmac_get_sset_count,
+	.get_ethtool_stats	= bgmac_get_ethtool_stats,
 	.get_drvinfo		= bgmac_get_drvinfo,
+	.get_link_ksettings     = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings     = phy_ethtool_set_link_ksettings,
 };
 
 /**************************************************
@@ -1429,7 +1545,7 @@
 static void bgmac_adjust_link(struct net_device *net_dev)
 {
 	struct bgmac *bgmac = netdev_priv(net_dev);
-	struct phy_device *phy_dev = bgmac->phy_dev;
+	struct phy_device *phy_dev = net_dev->phydev;
 	bool update = false;
 
 	if (phy_dev->link) {
@@ -1473,8 +1589,6 @@
 		return err;
 	}
 
-	bgmac->phy_dev = phy_dev;
-
 	return err;
 }
 
@@ -1519,7 +1633,6 @@
 		err = PTR_ERR(phy_dev);
 		goto err_unregister_bus;
 	}
-	bgmac->phy_dev = phy_dev;
 
 	return err;
 
@@ -1588,6 +1701,7 @@
 	bgmac->net_dev = net_dev;
 	bgmac->core = core;
 	bcma_set_drvdata(core, bgmac);
+	SET_NETDEV_DEV(net_dev, &core->dev);
 
 	/* Defaults */
 	memcpy(bgmac->net_dev->dev_addr, mac, ETH_ALEN);
diff --git a/drivers/net/ethernet/broadcom/bgmac.h b/drivers/net/ethernet/broadcom/bgmac.h
index 9a03c14..99beb18 100644
--- a/drivers/net/ethernet/broadcom/bgmac.h
+++ b/drivers/net/ethernet/broadcom/bgmac.h
@@ -123,7 +123,7 @@
 #define BGMAC_TX_LEN_1024_TO_1522		0x334
 #define BGMAC_TX_LEN_1523_TO_2047		0x338
 #define BGMAC_TX_LEN_2048_TO_4095		0x33c
-#define BGMAC_TX_LEN_4095_TO_8191		0x340
+#define BGMAC_TX_LEN_4096_TO_8191		0x340
 #define BGMAC_TX_LEN_8192_TO_MAX		0x344
 #define BGMAC_TX_JABBER_PKTS			0x348		/* Error */
 #define BGMAC_TX_OVERSIZE_PKTS			0x34c		/* Error */
@@ -166,7 +166,7 @@
 #define BGMAC_RX_LEN_1024_TO_1522		0x3e4
 #define BGMAC_RX_LEN_1523_TO_2047		0x3e8
 #define BGMAC_RX_LEN_2048_TO_4095		0x3ec
-#define BGMAC_RX_LEN_4095_TO_8191		0x3f0
+#define BGMAC_RX_LEN_4096_TO_8191		0x3f0
 #define BGMAC_RX_LEN_8192_TO_MAX		0x3f4
 #define BGMAC_RX_JABBER_PKTS			0x3f8		/* Error */
 #define BGMAC_RX_OVERSIZE_PKTS			0x3fc		/* Error */
@@ -441,7 +441,6 @@
 	struct net_device *net_dev;
 	struct napi_struct napi;
 	struct mii_bus *mii_bus;
-	struct phy_device *phy_dev;
 
 	/* DMA */
 	struct bgmac_dma_ring tx_ring[BGMAC_MAX_TX_RINGS];
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index c5fe9158..97e8925 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -59,9 +59,6 @@
 #include <linux/semaphore.h>
 #include <linux/stringify.h>
 #include <linux/vmalloc.h>
-#if IS_ENABLED(CONFIG_BNX2X_GENEVE)
-#include <net/geneve.h>
-#endif
 #include "bnx2x.h"
 #include "bnx2x_init.h"
 #include "bnx2x_init_ops.h"
@@ -10076,7 +10073,6 @@
 	}
 }
 
-#if defined(CONFIG_BNX2X_VXLAN) || IS_ENABLED(CONFIG_BNX2X_GENEVE)
 static int bnx2x_udp_port_update(struct bnx2x *bp)
 {
 	struct bnx2x_func_switch_update_params *switch_update_params;
@@ -10177,47 +10173,42 @@
 		DP(BNX2X_MSG_SP, "Deleted UDP tunnel [%d] port %d\n",
 		   type, port);
 }
-#endif
 
-#ifdef CONFIG_BNX2X_VXLAN
-static void bnx2x_add_vxlan_port(struct net_device *netdev,
-				 sa_family_t sa_family, __be16 port)
+static void bnx2x_udp_tunnel_add(struct net_device *netdev,
+				 struct udp_tunnel_info *ti)
 {
 	struct bnx2x *bp = netdev_priv(netdev);
-	u16 t_port = ntohs(port);
+	u16 t_port = ntohs(ti->port);
 
-	__bnx2x_add_udp_port(bp, t_port, BNX2X_UDP_PORT_VXLAN);
+	switch (ti->type) {
+	case UDP_TUNNEL_TYPE_VXLAN:
+		__bnx2x_add_udp_port(bp, t_port, BNX2X_UDP_PORT_VXLAN);
+		break;
+	case UDP_TUNNEL_TYPE_GENEVE:
+		__bnx2x_add_udp_port(bp, t_port, BNX2X_UDP_PORT_GENEVE);
+		break;
+	default:
+		break;
+	}
 }
 
-static void bnx2x_del_vxlan_port(struct net_device *netdev,
-				 sa_family_t sa_family, __be16 port)
+static void bnx2x_udp_tunnel_del(struct net_device *netdev,
+				 struct udp_tunnel_info *ti)
 {
 	struct bnx2x *bp = netdev_priv(netdev);
-	u16 t_port = ntohs(port);
+	u16 t_port = ntohs(ti->port);
 
-	__bnx2x_del_udp_port(bp, t_port, BNX2X_UDP_PORT_VXLAN);
+	switch (ti->type) {
+	case UDP_TUNNEL_TYPE_VXLAN:
+		__bnx2x_del_udp_port(bp, t_port, BNX2X_UDP_PORT_VXLAN);
+		break;
+	case UDP_TUNNEL_TYPE_GENEVE:
+		__bnx2x_del_udp_port(bp, t_port, BNX2X_UDP_PORT_GENEVE);
+		break;
+	default:
+		break;
+	}
 }
-#endif
-
-#if IS_ENABLED(CONFIG_BNX2X_GENEVE)
-static void bnx2x_add_geneve_port(struct net_device *netdev,
-				  sa_family_t sa_family, __be16 port)
-{
-	struct bnx2x *bp = netdev_priv(netdev);
-	u16 t_port = ntohs(port);
-
-	__bnx2x_add_udp_port(bp, t_port, BNX2X_UDP_PORT_GENEVE);
-}
-
-static void bnx2x_del_geneve_port(struct net_device *netdev,
-				  sa_family_t sa_family, __be16 port)
-{
-	struct bnx2x *bp = netdev_priv(netdev);
-	u16 t_port = ntohs(port);
-
-	__bnx2x_del_udp_port(bp, t_port, BNX2X_UDP_PORT_GENEVE);
-}
-#endif
 
 static int bnx2x_close(struct net_device *dev);
 
@@ -10325,7 +10316,6 @@
 			       &bp->sp_rtnl_state))
 		bnx2x_update_mng_version(bp);
 
-#if defined(CONFIG_BNX2X_VXLAN) || IS_ENABLED(CONFIG_BNX2X_GENEVE)
 	if (test_and_clear_bit(BNX2X_SP_RTNL_CHANGE_UDP_PORT,
 			       &bp->sp_rtnl_state)) {
 		if (bnx2x_udp_port_update(bp)) {
@@ -10335,20 +10325,14 @@
 			       BNX2X_UDP_PORT_MAX);
 		} else {
 			/* Since we don't store additional port information,
-			 * if no port is configured for any feature ask for
+			 * if no ports are configured for any feature ask for
 			 * information about currently configured ports.
 			 */
-#ifdef CONFIG_BNX2X_VXLAN
-			if (!bp->udp_tunnel_ports[BNX2X_UDP_PORT_VXLAN].count)
-				vxlan_get_rx_port(bp->dev);
-#endif
-#if IS_ENABLED(CONFIG_BNX2X_GENEVE)
-			if (!bp->udp_tunnel_ports[BNX2X_UDP_PORT_GENEVE].count)
-				geneve_get_rx_port(bp->dev);
-#endif
+			if (!bp->udp_tunnel_ports[BNX2X_UDP_PORT_VXLAN].count &&
+			    !bp->udp_tunnel_ports[BNX2X_UDP_PORT_GENEVE].count)
+				udp_tunnel_get_rx_info(bp->dev);
 		}
 	}
-#endif
 
 	/* work which needs rtnl lock not-taken (as it takes the lock itself and
 	 * can be called from other contexts as well)
@@ -12551,14 +12535,8 @@
 	if (rc)
 		return rc;
 
-#ifdef CONFIG_BNX2X_VXLAN
 	if (IS_PF(bp))
-		vxlan_get_rx_port(dev);
-#endif
-#if IS_ENABLED(CONFIG_BNX2X_GENEVE)
-	if (IS_PF(bp))
-		geneve_get_rx_port(dev);
-#endif
+		udp_tunnel_get_rx_info(dev);
 
 	return 0;
 }
@@ -12895,52 +12873,71 @@
 	return rc;
 }
 
-int bnx2x_vlan_reconfigure_vid(struct bnx2x *bp)
+static int bnx2x_vlan_configure_vid_list(struct bnx2x *bp)
 {
 	struct bnx2x_vlan_entry *vlan;
 	int rc = 0;
 
-	if (!bp->vlan_cnt) {
-		DP(NETIF_MSG_IFUP, "No need to re-configure vlan filters\n");
-		return 0;
-	}
-
+	/* Configure all non-configured entries */
 	list_for_each_entry(vlan, &bp->vlan_reg, link) {
-		/* Prepare for cleanup in case of errors */
-		if (rc) {
-			vlan->hw = false;
-			continue;
-		}
-
-		if (!vlan->hw)
+		if (vlan->hw)
 			continue;
 
-		DP(NETIF_MSG_IFUP, "Re-configuring vlan 0x%04x\n", vlan->vid);
+		if (bp->vlan_cnt >= bp->vlan_credit)
+			return -ENOBUFS;
 
 		rc = __bnx2x_vlan_configure_vid(bp, vlan->vid, true);
 		if (rc) {
-			BNX2X_ERR("Unable to configure VLAN %d\n", vlan->vid);
-			vlan->hw = false;
-			rc = -EINVAL;
-			continue;
+			BNX2X_ERR("Unable to config VLAN %d\n", vlan->vid);
+			return rc;
 		}
+
+		DP(NETIF_MSG_IFUP, "HW configured for VLAN %d\n", vlan->vid);
+		vlan->hw = true;
+		bp->vlan_cnt++;
 	}
 
-	return rc;
+	return 0;
+}
+
+static void bnx2x_vlan_configure(struct bnx2x *bp, bool set_rx_mode)
+{
+	bool need_accept_any_vlan;
+
+	need_accept_any_vlan = !!bnx2x_vlan_configure_vid_list(bp);
+
+	if (bp->accept_any_vlan != need_accept_any_vlan) {
+		bp->accept_any_vlan = need_accept_any_vlan;
+		DP(NETIF_MSG_IFUP, "Accept all VLAN %s\n",
+		   bp->accept_any_vlan ? "raised" : "cleared");
+		if (set_rx_mode) {
+			if (IS_PF(bp))
+				bnx2x_set_rx_mode_inner(bp);
+			else
+				bnx2x_vfpf_storm_rx_mode(bp);
+		}
+	}
+}
+
+int bnx2x_vlan_reconfigure_vid(struct bnx2x *bp)
+{
+	struct bnx2x_vlan_entry *vlan;
+
+	/* The hw forgot all entries after reload */
+	list_for_each_entry(vlan, &bp->vlan_reg, link)
+		vlan->hw = false;
+	bp->vlan_cnt = 0;
+
+	/* Don't set rx mode here. Our caller will do it. */
+	bnx2x_vlan_configure(bp, false);
+
+	return 0;
 }
 
 static int bnx2x_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 	struct bnx2x_vlan_entry *vlan;
-	bool hw = false;
-	int rc = 0;
-
-	if (!netif_running(bp->dev)) {
-		DP(NETIF_MSG_IFUP,
-		   "Ignoring VLAN configuration the interface is down\n");
-		return -EFAULT;
-	}
 
 	DP(NETIF_MSG_IFUP, "Adding VLAN %d\n", vid);
 
@@ -12948,93 +12945,47 @@
 	if (!vlan)
 		return -ENOMEM;
 
-	bp->vlan_cnt++;
-	if (bp->vlan_cnt > bp->vlan_credit && !bp->accept_any_vlan) {
-		DP(NETIF_MSG_IFUP, "Accept all VLAN raised\n");
-		bp->accept_any_vlan = true;
-		if (IS_PF(bp))
-			bnx2x_set_rx_mode_inner(bp);
-		else
-			bnx2x_vfpf_storm_rx_mode(bp);
-	} else if (bp->vlan_cnt <= bp->vlan_credit) {
-		rc = __bnx2x_vlan_configure_vid(bp, vid, true);
-		hw = true;
-	}
-
 	vlan->vid = vid;
-	vlan->hw = hw;
+	vlan->hw = false;
+	list_add_tail(&vlan->link, &bp->vlan_reg);
 
-	if (!rc) {
-		list_add(&vlan->link, &bp->vlan_reg);
-	} else {
-		bp->vlan_cnt--;
-		kfree(vlan);
-	}
+	if (netif_running(dev))
+		bnx2x_vlan_configure(bp, true);
 
-	DP(NETIF_MSG_IFUP, "Adding VLAN result %d\n", rc);
-
-	return rc;
+	return 0;
 }
 
 static int bnx2x_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 	struct bnx2x_vlan_entry *vlan;
+	bool found = false;
 	int rc = 0;
 
-	if (!netif_running(bp->dev)) {
-		DP(NETIF_MSG_IFUP,
-		   "Ignoring VLAN configuration the interface is down\n");
-		return -EFAULT;
-	}
-
 	DP(NETIF_MSG_IFUP, "Removing VLAN %d\n", vid);
 
-	if (!bp->vlan_cnt) {
-		BNX2X_ERR("Unable to kill VLAN %d\n", vid);
-		return -EINVAL;
-	}
-
 	list_for_each_entry(vlan, &bp->vlan_reg, link)
-		if (vlan->vid == vid)
+		if (vlan->vid == vid) {
+			found = true;
 			break;
+		}
 
-	if (vlan->vid != vid) {
+	if (!found) {
 		BNX2X_ERR("Unable to kill VLAN %d - not found\n", vid);
 		return -EINVAL;
 	}
 
-	if (vlan->hw)
+	if (netif_running(dev) && vlan->hw) {
 		rc = __bnx2x_vlan_configure_vid(bp, vid, false);
+		DP(NETIF_MSG_IFUP, "HW deconfigured for VLAN %d\n", vid);
+		bp->vlan_cnt--;
+	}
 
 	list_del(&vlan->link);
 	kfree(vlan);
 
-	bp->vlan_cnt--;
-
-	if (bp->vlan_cnt <= bp->vlan_credit && bp->accept_any_vlan) {
-		/* Configure all non-configured entries */
-		list_for_each_entry(vlan, &bp->vlan_reg, link) {
-			if (vlan->hw)
-				continue;
-
-			rc = __bnx2x_vlan_configure_vid(bp, vlan->vid, true);
-			if (rc) {
-				BNX2X_ERR("Unable to config VLAN %d\n",
-					  vlan->vid);
-				continue;
-			}
-			DP(NETIF_MSG_IFUP, "HW configured for VLAN %d\n",
-			   vlan->vid);
-			vlan->hw = true;
-		}
-		DP(NETIF_MSG_IFUP, "Accept all VLAN Removed\n");
-		bp->accept_any_vlan = false;
-		if (IS_PF(bp))
-			bnx2x_set_rx_mode_inner(bp);
-		else
-			bnx2x_vfpf_storm_rx_mode(bp);
-	}
+	if (netif_running(dev))
+		bnx2x_vlan_configure(bp, true);
 
 	DP(NETIF_MSG_IFUP, "Removing VLAN result %d\n", rc);
 
@@ -13072,14 +13023,8 @@
 	.ndo_get_phys_port_id	= bnx2x_get_phys_port_id,
 	.ndo_set_vf_link_state	= bnx2x_set_vf_link_state,
 	.ndo_features_check	= bnx2x_features_check,
-#ifdef CONFIG_BNX2X_VXLAN
-	.ndo_add_vxlan_port	= bnx2x_add_vxlan_port,
-	.ndo_del_vxlan_port	= bnx2x_del_vxlan_port,
-#endif
-#if IS_ENABLED(CONFIG_BNX2X_GENEVE)
-	.ndo_add_geneve_port	= bnx2x_add_geneve_port,
-	.ndo_del_geneve_port	= bnx2x_del_geneve_port,
-#endif
+	.ndo_udp_tunnel_add	= bnx2x_udp_tunnel_add,
+	.ndo_udp_tunnel_del	= bnx2x_udp_tunnel_del,
 };
 
 static int bnx2x_set_coherency_mask(struct bnx2x *bp)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 72a2eff..673f4d6 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -37,9 +37,7 @@
 #include <net/udp.h>
 #include <net/checksum.h>
 #include <net/ip6_checksum.h>
-#if defined(CONFIG_VXLAN) || defined(CONFIG_VXLAN_MODULE)
-#include <net/vxlan.h>
-#endif
+#include <net/udp_tunnel.h>
 #ifdef CONFIG_NET_RX_BUSY_POLL
 #include <net/busy_poll.h>
 #endif
@@ -75,12 +73,22 @@
 	BCM57301,
 	BCM57302,
 	BCM57304,
+	BCM57311,
+	BCM57312,
 	BCM57402,
 	BCM57404,
 	BCM57406,
+	BCM57404_NPAR,
+	BCM57412,
+	BCM57414,
+	BCM57416,
+	BCM57417,
+	BCM57414_NPAR,
 	BCM57314,
 	BCM57304_VF,
 	BCM57404_VF,
+	BCM57414_VF,
+	BCM57314_VF,
 };
 
 /* indexed by enum above */
@@ -90,25 +98,45 @@
 	{ "Broadcom BCM57301 NetXtreme-C Single-port 10Gb Ethernet" },
 	{ "Broadcom BCM57302 NetXtreme-C Dual-port 10Gb/25Gb Ethernet" },
 	{ "Broadcom BCM57304 NetXtreme-C Dual-port 10Gb/25Gb/40Gb/50Gb Ethernet" },
+	{ "Broadcom BCM57311 NetXtreme-C Single-port 10Gb Ethernet" },
+	{ "Broadcom BCM57312 NetXtreme-C Dual-port 10Gb/25Gb Ethernet" },
 	{ "Broadcom BCM57402 NetXtreme-E Dual-port 10Gb Ethernet" },
 	{ "Broadcom BCM57404 NetXtreme-E Dual-port 10Gb/25Gb Ethernet" },
 	{ "Broadcom BCM57406 NetXtreme-E Dual-port 10GBase-T Ethernet" },
+	{ "Broadcom BCM57404 NetXtreme-E Ethernet Partition" },
+	{ "Broadcom BCM57412 NetXtreme-E Dual-port 10Gb Ethernet" },
+	{ "Broadcom BCM57414 NetXtreme-E Dual-port 10Gb/25Gb Ethernet" },
+	{ "Broadcom BCM57416 NetXtreme-E Dual-port 10GBase-T Ethernet" },
+	{ "Broadcom BCM57417 NetXtreme-E Dual-port 10GBase-T Ethernet" },
+	{ "Broadcom BCM57414 NetXtreme-E Ethernet Partition" },
 	{ "Broadcom BCM57314 NetXtreme-C Dual-port 10Gb/25Gb/40Gb/50Gb Ethernet" },
 	{ "Broadcom BCM57304 NetXtreme-C Ethernet Virtual Function" },
 	{ "Broadcom BCM57404 NetXtreme-E Ethernet Virtual Function" },
+	{ "Broadcom BCM57414 NetXtreme-E Ethernet Virtual Function" },
+	{ "Broadcom BCM57314 NetXtreme-E Ethernet Virtual Function" },
 };
 
 static const struct pci_device_id bnxt_pci_tbl[] = {
 	{ PCI_VDEVICE(BROADCOM, 0x16c8), .driver_data = BCM57301 },
 	{ PCI_VDEVICE(BROADCOM, 0x16c9), .driver_data = BCM57302 },
 	{ PCI_VDEVICE(BROADCOM, 0x16ca), .driver_data = BCM57304 },
+	{ PCI_VDEVICE(BROADCOM, 0x16ce), .driver_data = BCM57311 },
+	{ PCI_VDEVICE(BROADCOM, 0x16cf), .driver_data = BCM57312 },
 	{ PCI_VDEVICE(BROADCOM, 0x16d0), .driver_data = BCM57402 },
 	{ PCI_VDEVICE(BROADCOM, 0x16d1), .driver_data = BCM57404 },
 	{ PCI_VDEVICE(BROADCOM, 0x16d2), .driver_data = BCM57406 },
+	{ PCI_VDEVICE(BROADCOM, 0x16d4), .driver_data = BCM57404_NPAR },
+	{ PCI_VDEVICE(BROADCOM, 0x16d6), .driver_data = BCM57412 },
+	{ PCI_VDEVICE(BROADCOM, 0x16d7), .driver_data = BCM57414 },
+	{ PCI_VDEVICE(BROADCOM, 0x16d8), .driver_data = BCM57416 },
+	{ PCI_VDEVICE(BROADCOM, 0x16d9), .driver_data = BCM57417 },
+	{ PCI_VDEVICE(BROADCOM, 0x16de), .driver_data = BCM57414_NPAR },
 	{ PCI_VDEVICE(BROADCOM, 0x16df), .driver_data = BCM57314 },
 #ifdef CONFIG_BNXT_SRIOV
 	{ PCI_VDEVICE(BROADCOM, 0x16cb), .driver_data = BCM57304_VF },
 	{ PCI_VDEVICE(BROADCOM, 0x16d3), .driver_data = BCM57404_VF },
+	{ PCI_VDEVICE(BROADCOM, 0x16dc), .driver_data = BCM57414_VF },
+	{ PCI_VDEVICE(BROADCOM, 0x16e1), .driver_data = BCM57314_VF },
 #endif
 	{ 0 }
 };
@@ -125,12 +153,14 @@
 	HWRM_ASYNC_EVENT_CMPL_EVENT_ID_LINK_STATUS_CHANGE,
 	HWRM_ASYNC_EVENT_CMPL_EVENT_ID_PF_DRVR_UNLOAD,
 	HWRM_ASYNC_EVENT_CMPL_EVENT_ID_PORT_CONN_NOT_ALLOWED,
+	HWRM_ASYNC_EVENT_CMPL_EVENT_ID_VF_CFG_CHANGE,
 	HWRM_ASYNC_EVENT_CMPL_EVENT_ID_LINK_SPEED_CFG_CHANGE,
 };
 
 static bool bnxt_vf_pciid(enum board_idx idx)
 {
-	return (idx == BCM57304_VF || idx == BCM57404_VF);
+	return (idx == BCM57304_VF || idx == BCM57404_VF ||
+		idx == BCM57314_VF || idx == BCM57414_VF);
 }
 
 #define DB_CP_REARM_FLAGS	(DB_KEY_CP | DB_IDX_VALID)
@@ -286,7 +316,9 @@
 			cpu_to_le32(DB_KEY_TX_PUSH | DB_LONG_TX_PUSH | prod);
 		txr->tx_prod = prod;
 
+		tx_buf->is_push = 1;
 		netdev_tx_sent_queue(txq, skb->len);
+		wmb();	/* Sync is_push and byte queue before pushing data */
 
 		push_len = (length + sizeof(*tx_push) + 7) / 8;
 		if (push_len > 16) {
@@ -298,7 +330,6 @@
 					 push_len);
 		}
 
-		tx_buf->is_push = 1;
 		goto tx_done;
 	}
 
@@ -919,6 +950,7 @@
 	}
 	tpa_info->flags2 = le32_to_cpu(tpa_start1->rx_tpa_start_cmp_flags2);
 	tpa_info->metadata = le32_to_cpu(tpa_start1->rx_tpa_start_cmp_metadata);
+	tpa_info->hdr_info = le32_to_cpu(tpa_start1->rx_tpa_start_cmp_hdr_info);
 
 	rxr->rx_prod = NEXT_RX(prod);
 	cons = NEXT_RX(cons);
@@ -937,32 +969,102 @@
 		bnxt_reuse_rx_agg_bufs(bnapi, cp_cons, agg_bufs);
 }
 
-#define BNXT_IPV4_HDR_SIZE	(sizeof(struct iphdr) + sizeof(struct tcphdr))
-#define BNXT_IPV6_HDR_SIZE	(sizeof(struct ipv6hdr) + sizeof(struct tcphdr))
-
-static inline struct sk_buff *bnxt_gro_skb(struct bnxt_tpa_info *tpa_info,
-					   struct rx_tpa_end_cmp *tpa_end,
-					   struct rx_tpa_end_cmp_ext *tpa_end1,
+static struct sk_buff *bnxt_gro_func_5731x(struct bnxt_tpa_info *tpa_info,
+					   int payload_off, int tcp_ts,
 					   struct sk_buff *skb)
 {
 #ifdef CONFIG_INET
 	struct tcphdr *th;
-	int payload_off, tcp_opt_len = 0;
 	int len, nw_off;
-	u16 segs;
+	u16 outer_ip_off, inner_ip_off, inner_mac_off;
+	u32 hdr_info = tpa_info->hdr_info;
+	bool loopback = false;
 
-	segs = TPA_END_TPA_SEGS(tpa_end);
-	if (segs == 1)
-		return skb;
+	inner_ip_off = BNXT_TPA_INNER_L3_OFF(hdr_info);
+	inner_mac_off = BNXT_TPA_INNER_L2_OFF(hdr_info);
+	outer_ip_off = BNXT_TPA_OUTER_L3_OFF(hdr_info);
 
-	NAPI_GRO_CB(skb)->count = segs;
-	skb_shinfo(skb)->gso_size =
-		le32_to_cpu(tpa_end1->rx_tpa_end_cmp_seg_len);
-	skb_shinfo(skb)->gso_type = tpa_info->gso_type;
-	payload_off = (le32_to_cpu(tpa_end->rx_tpa_end_cmp_misc_v1) &
-		       RX_TPA_END_CMP_PAYLOAD_OFFSET) >>
-		      RX_TPA_END_CMP_PAYLOAD_OFFSET_SHIFT;
-	if (TPA_END_GRO_TS(tpa_end))
+	/* If the packet is an internal loopback packet, the offsets will
+	 * have an extra 4 bytes.
+	 */
+	if (inner_mac_off == 4) {
+		loopback = true;
+	} else if (inner_mac_off > 4) {
+		__be16 proto = *((__be16 *)(skb->data + inner_ip_off -
+					    ETH_HLEN - 2));
+
+		/* We only support inner iPv4/ipv6.  If we don't see the
+		 * correct protocol ID, it must be a loopback packet where
+		 * the offsets are off by 4.
+		 */
+		if (proto != htons(ETH_P_IP) && proto && htons(ETH_P_IPV6))
+			loopback = true;
+	}
+	if (loopback) {
+		/* internal loopback packet, subtract all offsets by 4 */
+		inner_ip_off -= 4;
+		inner_mac_off -= 4;
+		outer_ip_off -= 4;
+	}
+
+	nw_off = inner_ip_off - ETH_HLEN;
+	skb_set_network_header(skb, nw_off);
+	if (tpa_info->flags2 & RX_TPA_START_CMP_FLAGS2_IP_TYPE) {
+		struct ipv6hdr *iph = ipv6_hdr(skb);
+
+		skb_set_transport_header(skb, nw_off + sizeof(struct ipv6hdr));
+		len = skb->len - skb_transport_offset(skb);
+		th = tcp_hdr(skb);
+		th->check = ~tcp_v6_check(len, &iph->saddr, &iph->daddr, 0);
+	} else {
+		struct iphdr *iph = ip_hdr(skb);
+
+		skb_set_transport_header(skb, nw_off + sizeof(struct iphdr));
+		len = skb->len - skb_transport_offset(skb);
+		th = tcp_hdr(skb);
+		th->check = ~tcp_v4_check(len, iph->saddr, iph->daddr, 0);
+	}
+
+	if (inner_mac_off) { /* tunnel */
+		struct udphdr *uh = NULL;
+		__be16 proto = *((__be16 *)(skb->data + outer_ip_off -
+					    ETH_HLEN - 2));
+
+		if (proto == htons(ETH_P_IP)) {
+			struct iphdr *iph = (struct iphdr *)skb->data;
+
+			if (iph->protocol == IPPROTO_UDP)
+				uh = (struct udphdr *)(iph + 1);
+		} else {
+			struct ipv6hdr *iph = (struct ipv6hdr *)skb->data;
+
+			if (iph->nexthdr == IPPROTO_UDP)
+				uh = (struct udphdr *)(iph + 1);
+		}
+		if (uh) {
+			if (uh->check)
+				skb_shinfo(skb)->gso_type |=
+					SKB_GSO_UDP_TUNNEL_CSUM;
+			else
+				skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL;
+		}
+	}
+#endif
+	return skb;
+}
+
+#define BNXT_IPV4_HDR_SIZE	(sizeof(struct iphdr) + sizeof(struct tcphdr))
+#define BNXT_IPV6_HDR_SIZE	(sizeof(struct ipv6hdr) + sizeof(struct tcphdr))
+
+static struct sk_buff *bnxt_gro_func_5730x(struct bnxt_tpa_info *tpa_info,
+					   int payload_off, int tcp_ts,
+					   struct sk_buff *skb)
+{
+#ifdef CONFIG_INET
+	struct tcphdr *th;
+	int len, nw_off, tcp_opt_len;
+
+	if (tcp_ts)
 		tcp_opt_len = 12;
 
 	if (tpa_info->gso_type == SKB_GSO_TCPV4) {
@@ -1019,6 +1121,32 @@
 	return skb;
 }
 
+static inline struct sk_buff *bnxt_gro_skb(struct bnxt *bp,
+					   struct bnxt_tpa_info *tpa_info,
+					   struct rx_tpa_end_cmp *tpa_end,
+					   struct rx_tpa_end_cmp_ext *tpa_end1,
+					   struct sk_buff *skb)
+{
+#ifdef CONFIG_INET
+	int payload_off;
+	u16 segs;
+
+	segs = TPA_END_TPA_SEGS(tpa_end);
+	if (segs == 1)
+		return skb;
+
+	NAPI_GRO_CB(skb)->count = segs;
+	skb_shinfo(skb)->gso_size =
+		le32_to_cpu(tpa_end1->rx_tpa_end_cmp_seg_len);
+	skb_shinfo(skb)->gso_type = tpa_info->gso_type;
+	payload_off = (le32_to_cpu(tpa_end->rx_tpa_end_cmp_misc_v1) &
+		       RX_TPA_END_CMP_PAYLOAD_OFFSET) >>
+		      RX_TPA_END_CMP_PAYLOAD_OFFSET_SHIFT;
+	skb = bp->gro_func(tpa_info, payload_off, TPA_END_GRO_TS(tpa_end), skb);
+#endif
+	return skb;
+}
+
 static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
 					   struct bnxt_napi *bnapi,
 					   u32 *raw_cons,
@@ -1112,19 +1240,13 @@
 	if (tpa_info->hash_type != PKT_HASH_TYPE_NONE)
 		skb_set_hash(skb, tpa_info->rss_hash, tpa_info->hash_type);
 
-	if (tpa_info->flags2 & RX_CMP_FLAGS2_META_FORMAT_VLAN) {
-		netdev_features_t features = skb->dev->features;
+	if ((tpa_info->flags2 & RX_CMP_FLAGS2_META_FORMAT_VLAN) &&
+	    (skb->dev->features & NETIF_F_HW_VLAN_CTAG_RX)) {
 		u16 vlan_proto = tpa_info->metadata >>
 			RX_CMP_FLAGS2_METADATA_TPID_SFT;
+		u16 vtag = tpa_info->metadata & RX_CMP_FLAGS2_METADATA_VID_MASK;
 
-		if (((features & NETIF_F_HW_VLAN_CTAG_RX) &&
-		     vlan_proto == ETH_P_8021Q) ||
-		    ((features & NETIF_F_HW_VLAN_STAG_RX) &&
-		     vlan_proto == ETH_P_8021AD)) {
-			__vlan_hwaccel_put_tag(skb, htons(vlan_proto),
-					       tpa_info->metadata &
-					       RX_CMP_FLAGS2_METADATA_VID_MASK);
-		}
+		__vlan_hwaccel_put_tag(skb, htons(vlan_proto), vtag);
 	}
 
 	skb_checksum_none_assert(skb);
@@ -1135,7 +1257,7 @@
 	}
 
 	if (TPA_END_GRO(tpa_end))
-		skb = bnxt_gro_skb(tpa_info, tpa_end, tpa_end1, skb);
+		skb = bnxt_gro_skb(bp, tpa_info, tpa_end, tpa_end1, skb);
 
 	return skb;
 }
@@ -1277,19 +1399,14 @@
 
 	skb->protocol = eth_type_trans(skb, dev);
 
-	if (rxcmp1->rx_cmp_flags2 &
-	    cpu_to_le32(RX_CMP_FLAGS2_META_FORMAT_VLAN)) {
-		netdev_features_t features = skb->dev->features;
+	if ((rxcmp1->rx_cmp_flags2 &
+	     cpu_to_le32(RX_CMP_FLAGS2_META_FORMAT_VLAN)) &&
+	    (skb->dev->features & NETIF_F_HW_VLAN_CTAG_RX)) {
 		u32 meta_data = le32_to_cpu(rxcmp1->rx_cmp_meta_data);
+		u16 vtag = meta_data & RX_CMP_FLAGS2_METADATA_VID_MASK;
 		u16 vlan_proto = meta_data >> RX_CMP_FLAGS2_METADATA_TPID_SFT;
 
-		if (((features & NETIF_F_HW_VLAN_CTAG_RX) &&
-		     vlan_proto == ETH_P_8021Q) ||
-		    ((features & NETIF_F_HW_VLAN_STAG_RX) &&
-		     vlan_proto == ETH_P_8021AD))
-			__vlan_hwaccel_put_tag(skb, htons(vlan_proto),
-					       meta_data &
-					       RX_CMP_FLAGS2_METADATA_VID_MASK);
+		__vlan_hwaccel_put_tag(skb, htons(vlan_proto), vtag);
 	}
 
 	skb_checksum_none_assert(skb);
@@ -1368,6 +1485,11 @@
 		set_bit(BNXT_HWRM_PORT_MODULE_SP_EVENT, &bp->sp_event);
 		break;
 	}
+	case HWRM_ASYNC_EVENT_CMPL_EVENT_ID_VF_CFG_CHANGE:
+		if (BNXT_PF(bp))
+			goto async_event_process_exit;
+		set_bit(BNXT_RESET_TASK_SILENT_SP_EVENT, &bp->sp_event);
+		break;
 	default:
 		netdev_err(bp->dev, "unhandled ASYNC event (id 0x%x)\n",
 			   event_id);
@@ -2272,7 +2394,7 @@
 	bp->flags &= ~BNXT_FLAG_TPA;
 	if (bp->dev->features & NETIF_F_LRO)
 		bp->flags |= BNXT_FLAG_LRO;
-	if ((bp->dev->features & NETIF_F_GRO) && (bp->pdev->revision > 0))
+	if (bp->dev->features & NETIF_F_GRO)
 		bp->flags |= BNXT_FLAG_GRO;
 }
 
@@ -3287,6 +3409,7 @@
 	unsigned int ring = 0, grp_idx;
 	struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id];
 	struct hwrm_vnic_cfg_input req = {0};
+	u16 def_vlan = 0;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_VNIC_CFG, -1, -1);
 	/* Only RSS support for now TBD: COS & LB */
@@ -3307,7 +3430,11 @@
 	req.mru = cpu_to_le16(bp->dev->mtu + ETH_HLEN + ETH_FCS_LEN +
 			      VLAN_HLEN);
 
-	if (bp->flags & BNXT_FLAG_STRIP_VLAN)
+#ifdef CONFIG_BNXT_SRIOV
+	if (BNXT_VF(bp))
+		def_vlan = bp->vf.vlan;
+#endif
+	if ((bp->flags & BNXT_FLAG_STRIP_VLAN) || def_vlan)
 		req.flags |= cpu_to_le32(VNIC_CFG_REQ_FLAGS_VLAN_STRIP_MODE);
 
 	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
@@ -3846,6 +3973,39 @@
 	return 0;
 }
 
+static int bnxt_hwrm_func_qcfg(struct bnxt *bp)
+{
+	struct hwrm_func_qcfg_input req = {0};
+	struct hwrm_func_qcfg_output *resp = bp->hwrm_cmd_resp_addr;
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_QCFG, -1, -1);
+	req.fid = cpu_to_le16(0xffff);
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc)
+		goto func_qcfg_exit;
+
+#ifdef CONFIG_BNXT_SRIOV
+	if (BNXT_VF(bp)) {
+		struct bnxt_vf_info *vf = &bp->vf;
+
+		vf->vlan = le16_to_cpu(resp->vlan) & VLAN_VID_MASK;
+	}
+#endif
+	switch (resp->port_partition_type) {
+	case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_0:
+	case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_5:
+	case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR2_0:
+		bp->port_partition_type = resp->port_partition_type;
+		break;
+	}
+
+func_qcfg_exit:
+	mutex_unlock(&bp->hwrm_cmd_lock);
+	return rc;
+}
+
 int bnxt_hwrm_func_qcaps(struct bnxt *bp)
 {
 	int rc = 0;
@@ -4000,6 +4160,8 @@
 	if (resp->hwrm_intf_maj >= 1)
 		bp->hwrm_max_req_len = le16_to_cpu(resp->max_req_win_len);
 
+	bp->chip_num = le16_to_cpu(resp->chip_num);
+
 hwrm_ver_get_exit:
 	mutex_unlock(&bp->hwrm_cmd_lock);
 	return rc;
@@ -4240,6 +4402,11 @@
 		netdev_warn(bp->dev, "HWRM set coalescing failure rc: %x\n",
 			    rc);
 
+	if (BNXT_VF(bp)) {
+		bnxt_hwrm_func_qcfg(bp);
+		netdev_update_features(bp->dev);
+	}
+
 	return 0;
 
 err_out:
@@ -4654,6 +4821,7 @@
 	int rc = 0;
 	struct hwrm_port_phy_qcaps_input req = {0};
 	struct hwrm_port_phy_qcaps_output *resp = bp->hwrm_cmd_resp_addr;
+	struct bnxt_link_info *link_info = &bp->link_info;
 
 	if (bp->hwrm_spec_code < 0x10201)
 		return 0;
@@ -4676,6 +4844,8 @@
 		bp->lpi_tmr_hi = le32_to_cpu(resp->valid_tx_lpi_timer_high) &
 				 PORT_PHY_QCAPS_RESP_TX_LPI_TIMER_HIGH_MASK;
 	}
+	link_info->support_auto_speeds =
+		le16_to_cpu(resp->supported_speeds_auto_mode);
 
 hwrm_phy_qcaps_exit:
 	mutex_unlock(&bp->hwrm_cmd_lock);
@@ -4933,7 +5103,7 @@
 {
 	struct hwrm_port_phy_cfg_input req = {0};
 
-	if (BNXT_VF(bp))
+	if (!BNXT_SINGLE_PF(bp))
 		return 0;
 
 	if (pci_num_vf(bp->pdev))
@@ -5083,15 +5253,8 @@
 			netdev_warn(bp->dev, "failed to update phy settings\n");
 	}
 
-	if (irq_re_init) {
-#if defined(CONFIG_VXLAN) || defined(CONFIG_VXLAN_MODULE)
-		vxlan_get_rx_port(bp->dev);
-#endif
-		if (!bnxt_hwrm_tunnel_dst_port_alloc(
-				bp, htons(0x17c1),
-				TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE))
-			bp->nge_port_cnt = 1;
-	}
+	if (irq_re_init)
+		udp_tunnel_get_rx_info(bp->dev);
 
 	set_bit(BNXT_STATE_OPEN, &bp->state);
 	bnxt_enable_int(bp);
@@ -5466,6 +5629,27 @@
 
 	if (!bnxt_rfs_capable(bp))
 		features &= ~NETIF_F_NTUPLE;
+
+	/* Both CTAG and STAG VLAN accelaration on the RX side have to be
+	 * turned on or off together.
+	 */
+	if ((features & (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX)) !=
+	    (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX)) {
+		if (dev->features & NETIF_F_HW_VLAN_CTAG_RX)
+			features &= ~(NETIF_F_HW_VLAN_CTAG_RX |
+				      NETIF_F_HW_VLAN_STAG_RX);
+		else
+			features |= NETIF_F_HW_VLAN_CTAG_RX |
+				    NETIF_F_HW_VLAN_STAG_RX;
+	}
+#ifdef CONFIG_BNXT_SRIOV
+	if (BNXT_VF(bp)) {
+		if (bp->vf.vlan) {
+			features &= ~(NETIF_F_HW_VLAN_CTAG_RX |
+				      NETIF_F_HW_VLAN_STAG_RX);
+		}
+	}
+#endif
 	return features;
 }
 
@@ -5581,9 +5765,10 @@
 	}
 }
 
-static void bnxt_reset_task(struct bnxt *bp)
+static void bnxt_reset_task(struct bnxt *bp, bool silent)
 {
-	bnxt_dbg_dump_states(bp);
+	if (!silent)
+		bnxt_dbg_dump_states(bp);
 	if (netif_running(bp->dev)) {
 		bnxt_close_nic(bp, false, false);
 		bnxt_open_nic(bp, false, false);
@@ -5634,6 +5819,23 @@
 	mod_timer(&bp->timer, jiffies + bp->current_interval);
 }
 
+/* Only called from bnxt_sp_task() */
+static void bnxt_reset(struct bnxt *bp, bool silent)
+{
+	/* bnxt_reset_task() calls bnxt_close_nic() which waits
+	 * for BNXT_STATE_IN_SP_TASK to clear.
+	 * If there is a parallel dev_close(), bnxt_close() may be holding
+	 * rtnl() and waiting for BNXT_STATE_IN_SP_TASK to clear.  So we
+	 * must clear BNXT_STATE_IN_SP_TASK before holding rtnl().
+	 */
+	clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
+	rtnl_lock();
+	if (test_bit(BNXT_STATE_OPEN, &bp->state))
+		bnxt_reset_task(bp, silent);
+	set_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
+	rtnl_unlock();
+}
+
 static void bnxt_cfg_ntp_filters(struct bnxt *);
 
 static void bnxt_sp_task(struct work_struct *work)
@@ -5670,16 +5872,20 @@
 		bnxt_hwrm_tunnel_dst_port_free(
 			bp, TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN);
 	}
-	if (test_and_clear_bit(BNXT_RESET_TASK_SP_EVENT, &bp->sp_event)) {
-		/* bnxt_reset_task() calls bnxt_close_nic() which waits
-		 * for BNXT_STATE_IN_SP_TASK to clear.
-		 */
-		clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
-		rtnl_lock();
-		bnxt_reset_task(bp);
-		set_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
-		rtnl_unlock();
+	if (test_and_clear_bit(BNXT_GENEVE_ADD_PORT_SP_EVENT, &bp->sp_event)) {
+		bnxt_hwrm_tunnel_dst_port_alloc(
+			bp, bp->nge_port,
+			TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE);
 	}
+	if (test_and_clear_bit(BNXT_GENEVE_DEL_PORT_SP_EVENT, &bp->sp_event)) {
+		bnxt_hwrm_tunnel_dst_port_free(
+			bp, TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE);
+	}
+	if (test_and_clear_bit(BNXT_RESET_TASK_SP_EVENT, &bp->sp_event))
+		bnxt_reset(bp, false);
+
+	if (test_and_clear_bit(BNXT_RESET_TASK_SILENT_SP_EVENT, &bp->sp_event))
+		bnxt_reset(bp, true);
 
 	if (test_and_clear_bit(BNXT_HWRM_PORT_MODULE_SP_EVENT, &bp->sp_event))
 		bnxt_get_port_module_status(bp);
@@ -6044,47 +6250,83 @@
 
 #endif /* CONFIG_RFS_ACCEL */
 
-static void bnxt_add_vxlan_port(struct net_device *dev, sa_family_t sa_family,
-				__be16 port)
+static void bnxt_udp_tunnel_add(struct net_device *dev,
+				struct udp_tunnel_info *ti)
 {
 	struct bnxt *bp = netdev_priv(dev);
 
+	if (ti->sa_family != AF_INET6 && ti->sa_family != AF_INET)
+		return;
+
 	if (!netif_running(dev))
 		return;
 
-	if (sa_family != AF_INET6 && sa_family != AF_INET)
-		return;
+	switch (ti->type) {
+	case UDP_TUNNEL_TYPE_VXLAN:
+		if (bp->vxlan_port_cnt && bp->vxlan_port != ti->port)
+			return;
 
-	if (bp->vxlan_port_cnt && bp->vxlan_port != port)
-		return;
-
-	bp->vxlan_port_cnt++;
-	if (bp->vxlan_port_cnt == 1) {
-		bp->vxlan_port = port;
-		set_bit(BNXT_VXLAN_ADD_PORT_SP_EVENT, &bp->sp_event);
-		schedule_work(&bp->sp_task);
-	}
-}
-
-static void bnxt_del_vxlan_port(struct net_device *dev, sa_family_t sa_family,
-				__be16 port)
-{
-	struct bnxt *bp = netdev_priv(dev);
-
-	if (!netif_running(dev))
-		return;
-
-	if (sa_family != AF_INET6 && sa_family != AF_INET)
-		return;
-
-	if (bp->vxlan_port_cnt && bp->vxlan_port == port) {
-		bp->vxlan_port_cnt--;
-
-		if (bp->vxlan_port_cnt == 0) {
-			set_bit(BNXT_VXLAN_DEL_PORT_SP_EVENT, &bp->sp_event);
+		bp->vxlan_port_cnt++;
+		if (bp->vxlan_port_cnt == 1) {
+			bp->vxlan_port = ti->port;
+			set_bit(BNXT_VXLAN_ADD_PORT_SP_EVENT, &bp->sp_event);
 			schedule_work(&bp->sp_task);
 		}
+		break;
+	case UDP_TUNNEL_TYPE_GENEVE:
+		if (bp->nge_port_cnt && bp->nge_port != ti->port)
+			return;
+
+		bp->nge_port_cnt++;
+		if (bp->nge_port_cnt == 1) {
+			bp->nge_port = ti->port;
+			set_bit(BNXT_GENEVE_ADD_PORT_SP_EVENT, &bp->sp_event);
+		}
+		break;
+	default:
+		return;
 	}
+
+	schedule_work(&bp->sp_task);
+}
+
+static void bnxt_udp_tunnel_del(struct net_device *dev,
+				struct udp_tunnel_info *ti)
+{
+	struct bnxt *bp = netdev_priv(dev);
+
+	if (ti->sa_family != AF_INET6 && ti->sa_family != AF_INET)
+		return;
+
+	if (!netif_running(dev))
+		return;
+
+	switch (ti->type) {
+	case UDP_TUNNEL_TYPE_VXLAN:
+		if (!bp->vxlan_port_cnt || bp->vxlan_port != ti->port)
+			return;
+		bp->vxlan_port_cnt--;
+
+		if (bp->vxlan_port_cnt != 0)
+			return;
+
+		set_bit(BNXT_VXLAN_DEL_PORT_SP_EVENT, &bp->sp_event);
+		break;
+	case UDP_TUNNEL_TYPE_GENEVE:
+		if (!bp->nge_port_cnt || bp->nge_port != ti->port)
+			return;
+		bp->nge_port_cnt--;
+
+		if (bp->nge_port_cnt != 0)
+			return;
+
+		set_bit(BNXT_GENEVE_DEL_PORT_SP_EVENT, &bp->sp_event);
+		break;
+	default:
+		return;
+	}
+
+	schedule_work(&bp->sp_task);
 }
 
 static const struct net_device_ops bnxt_netdev_ops = {
@@ -6115,8 +6357,8 @@
 #ifdef CONFIG_RFS_ACCEL
 	.ndo_rx_flow_steer	= bnxt_rx_flow_steer,
 #endif
-	.ndo_add_vxlan_port	= bnxt_add_vxlan_port,
-	.ndo_del_vxlan_port	= bnxt_del_vxlan_port,
+	.ndo_udp_tunnel_add	= bnxt_udp_tunnel_add,
+	.ndo_udp_tunnel_del	= bnxt_udp_tunnel_del,
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	.ndo_busy_poll		= bnxt_busy_poll,
 #endif
@@ -6165,6 +6407,12 @@
 		return rc;
 	}
 
+	/* Older firmware does not have supported_auto_speeds, so assume
+	 * that all supported speeds can be autonegotiated.
+	 */
+	if (link_info->auto_link_speeds && !link_info->support_auto_speeds)
+		link_info->support_auto_speeds = link_info->support_speeds;
+
 	/*initialize the ethool setting copy with NVM settings */
 	if (BNXT_AUTO_MODE(link_info->auto_mode)) {
 		link_info->autoneg = BNXT_AUTONEG_SPEED;
@@ -6338,7 +6586,13 @@
 		goto init_err;
 
 	mutex_init(&bp->hwrm_cmd_lock);
-	bnxt_hwrm_ver_get(bp);
+	rc = bnxt_hwrm_ver_get(bp);
+	if (rc)
+		goto init_err;
+
+	bp->gro_func = bnxt_gro_func_5730x;
+	if (BNXT_CHIP_NUM_57X1X(bp->chip_num))
+		bp->gro_func = bnxt_gro_func_5731x;
 
 	rc = bnxt_hwrm_func_drv_rgtr(bp);
 	if (rc)
@@ -6361,6 +6615,8 @@
 		goto init_err;
 	}
 
+	bnxt_hwrm_func_qcfg(bp);
+
 	bnxt_set_tpa_flags(bp);
 	bnxt_set_ring_params(bp);
 	if (BNXT_PF(bp))
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 2824d65..927ece9 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -298,13 +298,14 @@
 	#define RX_TPA_START_CMP_FLAGS2_L4_CS_CALC		(0x1 << 1)
 	#define RX_TPA_START_CMP_FLAGS2_T_IP_CS_CALC		(0x1 << 2)
 	#define RX_TPA_START_CMP_FLAGS2_T_L4_CS_CALC		(0x1 << 3)
+	#define RX_TPA_START_CMP_FLAGS2_IP_TYPE			(0x1 << 8)
 
 	__le32 rx_tpa_start_cmp_metadata;
 	__le32 rx_tpa_start_cmp_cfa_code_v2;
 	#define RX_TPA_START_CMP_V2				(0x1 << 0)
 	#define RX_TPA_START_CMP_CFA_CODE			(0xffff << 16)
 	 #define RX_TPA_START_CMPL_CFA_CODE_SHIFT		 16
-	__le32 rx_tpa_start_cmp_unused5;
+	__le32 rx_tpa_start_cmp_hdr_info;
 };
 
 struct rx_tpa_end_cmp {
@@ -584,6 +585,19 @@
 	u32			metadata;
 	enum pkt_hash_types	hash_type;
 	u32			rss_hash;
+	u32			hdr_info;
+
+#define BNXT_TPA_L4_SIZE(hdr_info)	\
+	(((hdr_info) & 0xf8000000) ? ((hdr_info) >> 27) : 32)
+
+#define BNXT_TPA_INNER_L3_OFF(hdr_info)	\
+	(((hdr_info) >> 18) & 0x1ff)
+
+#define BNXT_TPA_INNER_L2_OFF(hdr_info)	\
+	(((hdr_info) >> 9) & 0x1ff)
+
+#define BNXT_TPA_OUTER_L3_OFF(hdr_info)	\
+	((hdr_info) & 0x1ff)
 };
 
 struct bnxt_rx_ring_info {
@@ -835,6 +849,7 @@
 #define BNXT_LINK_SPEED_MSK_25GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_25GB
 #define BNXT_LINK_SPEED_MSK_40GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_40GB
 #define BNXT_LINK_SPEED_MSK_50GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_50GB
+	u16			support_auto_speeds;
 	u16			lp_auto_link_speeds;
 	u16			force_link_speed;
 	u32			preemphasis;
@@ -873,6 +888,44 @@
 	void __iomem		*bar2;
 
 	u32			reg_base;
+	u16			chip_num;
+#define CHIP_NUM_57301		0x16c8
+#define CHIP_NUM_57302		0x16c9
+#define CHIP_NUM_57304		0x16ca
+#define CHIP_NUM_57402		0x16d0
+#define CHIP_NUM_57404		0x16d1
+#define CHIP_NUM_57406		0x16d2
+
+#define CHIP_NUM_57311		0x16ce
+#define CHIP_NUM_57312		0x16cf
+#define CHIP_NUM_57314		0x16df
+#define CHIP_NUM_57412		0x16d6
+#define CHIP_NUM_57414		0x16d7
+#define CHIP_NUM_57416		0x16d8
+#define CHIP_NUM_57417		0x16d9
+
+#define BNXT_CHIP_NUM_5730X(chip_num)		\
+	((chip_num) >= CHIP_NUM_57301 &&	\
+	 (chip_num) <= CHIP_NUM_57304)
+
+#define BNXT_CHIP_NUM_5740X(chip_num)		\
+	((chip_num) >= CHIP_NUM_57402 &&	\
+	 (chip_num) <= CHIP_NUM_57406)
+
+#define BNXT_CHIP_NUM_5731X(chip_num)		\
+	((chip_num) == CHIP_NUM_57311 ||	\
+	 (chip_num) == CHIP_NUM_57312 ||	\
+	 (chip_num) == CHIP_NUM_57314)
+
+#define BNXT_CHIP_NUM_5741X(chip_num)		\
+	((chip_num) >= CHIP_NUM_57412 &&	\
+	 (chip_num) <= CHIP_NUM_57417)
+
+#define BNXT_CHIP_NUM_57X0X(chip_num)		\
+	(BNXT_CHIP_NUM_5730X(chip_num) || BNXT_CHIP_NUM_5740X(chip_num))
+
+#define BNXT_CHIP_NUM_57X1X(chip_num)		\
+	(BNXT_CHIP_NUM_5731X(chip_num) || BNXT_CHIP_NUM_5741X(chip_num))
 
 	struct net_device	*dev;
 	struct pci_dev		*pdev;
@@ -907,12 +960,17 @@
 
 #define BNXT_PF(bp)		(!((bp)->flags & BNXT_FLAG_VF))
 #define BNXT_VF(bp)		((bp)->flags & BNXT_FLAG_VF)
+#define BNXT_NPAR(bp)		((bp)->port_partition_type)
+#define BNXT_SINGLE_PF(bp)	(BNXT_PF(bp) && !BNXT_NPAR(bp))
 
 	struct bnxt_napi	**bnapi;
 
 	struct bnxt_rx_ring_info	*rx_ring;
 	struct bnxt_tx_ring_info	*tx_ring;
 
+	struct sk_buff *	(*gro_func)(struct bnxt_tpa_info *, int, int,
+					    struct sk_buff *);
+
 	u32			rx_buf_size;
 	u32			rx_buf_use_size;	/* useable size */
 	u32			rx_ring_size;
@@ -991,8 +1049,10 @@
 	__be16			vxlan_port;
 	u8			vxlan_port_cnt;
 	__le16			vxlan_fw_dst_port_id;
+	__be16			nge_port;
 	u8			nge_port_cnt;
 	__le16			nge_fw_dst_port_id;
+	u8			port_partition_type;
 
 	u16			rx_coal_ticks;
 	u16			rx_coal_ticks_irq;
@@ -1018,6 +1078,9 @@
 #define BNXT_HWRM_PF_UNLOAD_SP_EVENT	8
 #define BNXT_PERIODIC_STATS_SP_EVENT	9
 #define BNXT_HWRM_PORT_MODULE_SP_EVENT	10
+#define BNXT_RESET_TASK_SILENT_SP_EVENT	11
+#define BNXT_GENEVE_ADD_PORT_SP_EVENT	12
+#define BNXT_GENEVE_DEL_PORT_SP_EVENT	13
 
 	struct bnxt_pf_info	pf;
 #ifdef CONFIG_BNXT_SRIOV
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index a38cb04..d7ab2d79 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -628,7 +628,66 @@
 	return speed_mask;
 }
 
-static u32 bnxt_fw_to_ethtool_advertised_spds(struct bnxt_link_info *link_info)
+#define BNXT_FW_TO_ETHTOOL_SPDS(fw_speeds, fw_pause, lk_ksettings, name)\
+{									\
+	if ((fw_speeds) & BNXT_LINK_SPEED_MSK_100MB)			\
+		ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\
+						     100baseT_Full);	\
+	if ((fw_speeds) & BNXT_LINK_SPEED_MSK_1GB)			\
+		ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\
+						     1000baseT_Full);	\
+	if ((fw_speeds) & BNXT_LINK_SPEED_MSK_10GB)			\
+		ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\
+						     10000baseT_Full);	\
+	if ((fw_speeds) & BNXT_LINK_SPEED_MSK_25GB)			\
+		ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\
+						     25000baseCR_Full);	\
+	if ((fw_speeds) & BNXT_LINK_SPEED_MSK_40GB)			\
+		ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\
+						     40000baseCR4_Full);\
+	if ((fw_speeds) & BNXT_LINK_SPEED_MSK_50GB)			\
+		ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\
+						     50000baseCR2_Full);\
+	if ((fw_pause) & BNXT_LINK_PAUSE_RX) {				\
+		ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\
+						     Pause);		\
+		if (!((fw_pause) & BNXT_LINK_PAUSE_TX))			\
+			ethtool_link_ksettings_add_link_mode(		\
+					lk_ksettings, name, Asym_Pause);\
+	} else if ((fw_pause) & BNXT_LINK_PAUSE_TX) {			\
+		ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\
+						     Asym_Pause);	\
+	}								\
+}
+
+#define BNXT_ETHTOOL_TO_FW_SPDS(fw_speeds, lk_ksettings, name)		\
+{									\
+	if (ethtool_link_ksettings_test_link_mode(lk_ksettings, name,	\
+						  100baseT_Full) ||	\
+	    ethtool_link_ksettings_test_link_mode(lk_ksettings, name,	\
+						  100baseT_Half))	\
+		(fw_speeds) |= BNXT_LINK_SPEED_MSK_100MB;		\
+	if (ethtool_link_ksettings_test_link_mode(lk_ksettings, name,	\
+						  1000baseT_Full) ||	\
+	    ethtool_link_ksettings_test_link_mode(lk_ksettings, name,	\
+						  1000baseT_Half))	\
+		(fw_speeds) |= BNXT_LINK_SPEED_MSK_1GB;			\
+	if (ethtool_link_ksettings_test_link_mode(lk_ksettings, name,	\
+						  10000baseT_Full))	\
+		(fw_speeds) |= BNXT_LINK_SPEED_MSK_10GB;		\
+	if (ethtool_link_ksettings_test_link_mode(lk_ksettings, name,	\
+						  25000baseCR_Full))	\
+		(fw_speeds) |= BNXT_LINK_SPEED_MSK_25GB;		\
+	if (ethtool_link_ksettings_test_link_mode(lk_ksettings, name,	\
+						  40000baseCR4_Full))	\
+		(fw_speeds) |= BNXT_LINK_SPEED_MSK_40GB;		\
+	if (ethtool_link_ksettings_test_link_mode(lk_ksettings, name,	\
+						  50000baseCR2_Full))	\
+		(fw_speeds) |= BNXT_LINK_SPEED_MSK_50GB;		\
+}
+
+static void bnxt_fw_to_ethtool_advertised_spds(struct bnxt_link_info *link_info,
+				struct ethtool_link_ksettings *lk_ksettings)
 {
 	u16 fw_speeds = link_info->auto_link_speeds;
 	u8 fw_pause = 0;
@@ -636,10 +695,11 @@
 	if (link_info->autoneg & BNXT_AUTONEG_FLOW_CTRL)
 		fw_pause = link_info->auto_pause_setting;
 
-	return _bnxt_fw_to_ethtool_adv_spds(fw_speeds, fw_pause);
+	BNXT_FW_TO_ETHTOOL_SPDS(fw_speeds, fw_pause, lk_ksettings, advertising);
 }
 
-static u32 bnxt_fw_to_ethtool_lp_adv(struct bnxt_link_info *link_info)
+static void bnxt_fw_to_ethtool_lp_adv(struct bnxt_link_info *link_info,
+				struct ethtool_link_ksettings *lk_ksettings)
 {
 	u16 fw_speeds = link_info->lp_auto_link_speeds;
 	u8 fw_pause = 0;
@@ -647,16 +707,24 @@
 	if (link_info->autoneg & BNXT_AUTONEG_FLOW_CTRL)
 		fw_pause = link_info->lp_pause;
 
-	return _bnxt_fw_to_ethtool_adv_spds(fw_speeds, fw_pause);
+	BNXT_FW_TO_ETHTOOL_SPDS(fw_speeds, fw_pause, lk_ksettings,
+				lp_advertising);
 }
 
-static u32 bnxt_fw_to_ethtool_support_spds(struct bnxt_link_info *link_info)
+static void bnxt_fw_to_ethtool_support_spds(struct bnxt_link_info *link_info,
+				struct ethtool_link_ksettings *lk_ksettings)
 {
 	u16 fw_speeds = link_info->support_speeds;
-	u32 supported;
 
-	supported = _bnxt_fw_to_ethtool_adv_spds(fw_speeds, 0);
-	return supported | SUPPORTED_Pause | SUPPORTED_Asym_Pause;
+	BNXT_FW_TO_ETHTOOL_SPDS(fw_speeds, 0, lk_ksettings, supported);
+
+	ethtool_link_ksettings_add_link_mode(lk_ksettings, supported, Pause);
+	ethtool_link_ksettings_add_link_mode(lk_ksettings, supported,
+					     Asym_Pause);
+
+	if (link_info->support_auto_speeds)
+		ethtool_link_ksettings_add_link_mode(lk_ksettings, supported,
+						     Autoneg);
 }
 
 u32 bnxt_fw_to_ethtool_speed(u16 fw_link_speed)
@@ -683,65 +751,62 @@
 	}
 }
 
-static int bnxt_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int bnxt_get_link_ksettings(struct net_device *dev,
+				   struct ethtool_link_ksettings *lk_ksettings)
 {
 	struct bnxt *bp = netdev_priv(dev);
 	struct bnxt_link_info *link_info = &bp->link_info;
-	u16 ethtool_speed;
+	struct ethtool_link_settings *base = &lk_ksettings->base;
+	u32 ethtool_speed;
 
-	cmd->supported = bnxt_fw_to_ethtool_support_spds(link_info);
+	ethtool_link_ksettings_zero_link_mode(lk_ksettings, supported);
+	bnxt_fw_to_ethtool_support_spds(link_info, lk_ksettings);
 
-	if (link_info->auto_link_speeds)
-		cmd->supported |= SUPPORTED_Autoneg;
-
+	ethtool_link_ksettings_zero_link_mode(lk_ksettings, advertising);
 	if (link_info->autoneg) {
-		cmd->advertising =
-			bnxt_fw_to_ethtool_advertised_spds(link_info);
-		cmd->advertising |= ADVERTISED_Autoneg;
-		cmd->autoneg = AUTONEG_ENABLE;
+		bnxt_fw_to_ethtool_advertised_spds(link_info, lk_ksettings);
+		ethtool_link_ksettings_add_link_mode(lk_ksettings,
+						     advertising, Autoneg);
+		base->autoneg = AUTONEG_ENABLE;
 		if (link_info->phy_link_status == BNXT_LINK_LINK)
-			cmd->lp_advertising =
-				bnxt_fw_to_ethtool_lp_adv(link_info);
+			bnxt_fw_to_ethtool_lp_adv(link_info, lk_ksettings);
 		ethtool_speed = bnxt_fw_to_ethtool_speed(link_info->link_speed);
 		if (!netif_carrier_ok(dev))
-			cmd->duplex = DUPLEX_UNKNOWN;
+			base->duplex = DUPLEX_UNKNOWN;
 		else if (link_info->duplex & BNXT_LINK_DUPLEX_FULL)
-			cmd->duplex = DUPLEX_FULL;
+			base->duplex = DUPLEX_FULL;
 		else
-			cmd->duplex = DUPLEX_HALF;
+			base->duplex = DUPLEX_HALF;
 	} else {
-		cmd->autoneg = AUTONEG_DISABLE;
-		cmd->advertising = 0;
+		base->autoneg = AUTONEG_DISABLE;
 		ethtool_speed =
 			bnxt_fw_to_ethtool_speed(link_info->req_link_speed);
-		cmd->duplex = DUPLEX_HALF;
+		base->duplex = DUPLEX_HALF;
 		if (link_info->req_duplex == BNXT_LINK_DUPLEX_FULL)
-			cmd->duplex = DUPLEX_FULL;
+			base->duplex = DUPLEX_FULL;
 	}
-	ethtool_cmd_speed_set(cmd, ethtool_speed);
+	base->speed = ethtool_speed;
 
-	cmd->port = PORT_NONE;
+	base->port = PORT_NONE;
 	if (link_info->media_type == PORT_PHY_QCFG_RESP_MEDIA_TYPE_TP) {
-		cmd->port = PORT_TP;
-		cmd->supported |= SUPPORTED_TP;
-		cmd->advertising |= ADVERTISED_TP;
+		base->port = PORT_TP;
+		ethtool_link_ksettings_add_link_mode(lk_ksettings, supported,
+						     TP);
+		ethtool_link_ksettings_add_link_mode(lk_ksettings, advertising,
+						     TP);
 	} else {
-		cmd->supported |= SUPPORTED_FIBRE;
-		cmd->advertising |= ADVERTISED_FIBRE;
+		ethtool_link_ksettings_add_link_mode(lk_ksettings, supported,
+						     FIBRE);
+		ethtool_link_ksettings_add_link_mode(lk_ksettings, advertising,
+						     FIBRE);
 
 		if (link_info->media_type == PORT_PHY_QCFG_RESP_MEDIA_TYPE_DAC)
-			cmd->port = PORT_DA;
+			base->port = PORT_DA;
 		else if (link_info->media_type ==
 			 PORT_PHY_QCFG_RESP_MEDIA_TYPE_FIBRE)
-			cmd->port = PORT_FIBRE;
+			base->port = PORT_FIBRE;
 	}
-
-	if (link_info->transceiver ==
-	    PORT_PHY_QCFG_RESP_XCVR_PKG_TYPE_XCVR_INTERNAL)
-		cmd->transceiver = XCVR_INTERNAL;
-	else
-		cmd->transceiver = XCVR_EXTERNAL;
-	cmd->phy_address = link_info->phy_addr;
+	base->phy_address = link_info->phy_addr;
 
 	return 0;
 }
@@ -815,37 +880,25 @@
 	return fw_speed_mask;
 }
 
-static int bnxt_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int bnxt_set_link_ksettings(struct net_device *dev,
+			   const struct ethtool_link_ksettings *lk_ksettings)
 {
-	int rc = 0;
 	struct bnxt *bp = netdev_priv(dev);
 	struct bnxt_link_info *link_info = &bp->link_info;
+	const struct ethtool_link_settings *base = &lk_ksettings->base;
 	u32 speed, fw_advertising = 0;
 	bool set_pause = false;
+	int rc = 0;
 
-	if (BNXT_VF(bp))
-		return rc;
+	if (!BNXT_SINGLE_PF(bp))
+		return -EOPNOTSUPP;
 
-	if (cmd->autoneg == AUTONEG_ENABLE) {
-		u32 supported_spds = bnxt_fw_to_ethtool_support_spds(link_info);
-
-		if (cmd->advertising & ~(supported_spds | ADVERTISED_Autoneg |
-					 ADVERTISED_TP | ADVERTISED_FIBRE)) {
-			netdev_err(dev, "Unsupported advertising mask (adv: 0x%x)\n",
-				   cmd->advertising);
-			rc = -EINVAL;
-			goto set_setting_exit;
-		}
-		fw_advertising = bnxt_get_fw_auto_link_speeds(cmd->advertising);
-		if (fw_advertising & ~link_info->support_speeds) {
-			netdev_err(dev, "Advertising parameters are not supported! (adv: 0x%x)\n",
-				   cmd->advertising);
-			rc = -EINVAL;
-			goto set_setting_exit;
-		}
+	if (base->autoneg == AUTONEG_ENABLE) {
+		BNXT_ETHTOOL_TO_FW_SPDS(fw_advertising, lk_ksettings,
+					advertising);
 		link_info->autoneg |= BNXT_AUTONEG_SPEED;
 		if (!fw_advertising)
-			link_info->advertising = link_info->support_speeds;
+			link_info->advertising = link_info->support_auto_speeds;
 		else
 			link_info->advertising = fw_advertising;
 		/* any change to autoneg will cause link change, therefore the
@@ -863,16 +916,12 @@
 			rc = -EINVAL;
 			goto set_setting_exit;
 		}
-		/* TODO: currently don't support half duplex */
-		if (cmd->duplex == DUPLEX_HALF) {
+		if (base->duplex == DUPLEX_HALF) {
 			netdev_err(dev, "HALF DUPLEX is not supported!\n");
 			rc = -EINVAL;
 			goto set_setting_exit;
 		}
-		/* If received a request for an unknown duplex, assume full*/
-		if (cmd->duplex == DUPLEX_UNKNOWN)
-			cmd->duplex = DUPLEX_FULL;
-		speed = ethtool_cmd_speed(cmd);
+		speed = base->speed;
 		fw_speed = bnxt_get_fw_speed(dev, speed);
 		if (!fw_speed) {
 			rc = -EINVAL;
@@ -911,7 +960,7 @@
 	struct bnxt *bp = netdev_priv(dev);
 	struct bnxt_link_info *link_info = &bp->link_info;
 
-	if (BNXT_VF(bp))
+	if (!BNXT_SINGLE_PF(bp))
 		return rc;
 
 	if (epause->autoneg) {
@@ -1433,7 +1482,7 @@
 		 _bnxt_fw_to_ethtool_adv_spds(link_info->advertising, 0);
 	int rc = 0;
 
-	if (BNXT_VF(bp))
+	if (!BNXT_SINGLE_PF(bp))
 		return 0;
 
 	if (!(bp->flags & BNXT_FLAG_EEE_CAP))
@@ -1618,8 +1667,8 @@
 }
 
 const struct ethtool_ops bnxt_ethtool_ops = {
-	.get_settings		= bnxt_get_settings,
-	.set_settings		= bnxt_set_settings,
+	.get_link_ksettings	= bnxt_get_link_ksettings,
+	.set_link_ksettings	= bnxt_set_link_ksettings,
 	.get_pauseparam		= bnxt_get_pauseparam,
 	.set_pauseparam		= bnxt_set_pauseparam,
 	.get_drvinfo		= bnxt_get_drvinfo,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index 363884d..50d2007 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -143,6 +143,9 @@
 	u16 vlan_tag;
 	int rc;
 
+	if (bp->hwrm_spec_code < 0x10201)
+		return -ENOTSUPP;
+
 	rc = bnxt_vf_ndo_prep(bp, vf_id);
 	if (rc)
 		return rc;
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
index 245c063..4523c86 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
@@ -127,7 +127,7 @@
 		dev_err(&oct->pci_dev->dev, "Unknown link interface reported\n");
 	}
 
-	if (linfo->link.s.status) {
+	if (linfo->link.s.link_up) {
 		ethtool_cmd_speed_set(ecmd, linfo->link.s.speed);
 		ecmd->duplex = linfo->link.s.duplex;
 	} else {
@@ -222,23 +222,20 @@
 	struct lio *lio = GET_LIO(netdev);
 	struct octeon_device *oct = lio->oct_dev;
 	struct octnic_ctrl_pkt nctrl;
-	struct octnic_ctrl_params nparams;
 	int ret = 0;
 
 	memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
 
 	nctrl.ncmd.u64 = 0;
 	nctrl.ncmd.s.cmd = OCTNET_CMD_GPIO_ACCESS;
-	nctrl.ncmd.s.param1 = lio->linfo.ifidx;
-	nctrl.ncmd.s.param2 = addr;
-	nctrl.ncmd.s.param3 = val;
+	nctrl.ncmd.s.param1 = addr;
+	nctrl.ncmd.s.param2 = val;
+	nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
 	nctrl.wait_time = 100;
 	nctrl.netpndev = (u64)netdev;
 	nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
 
-	nparams.resp_order = OCTEON_RESP_ORDERED;
-
-	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl, nparams);
+	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
 	if (ret < 0) {
 		dev_err(&oct->pci_dev->dev, "Failed to configure gpio value\n");
 		return -EINVAL;
@@ -303,9 +300,10 @@
 	mdio_cmd->mdio_addr = loc;
 	if (op)
 		mdio_cmd->value1 = *value;
-	mdio_cmd->value2 = lio->linfo.ifidx;
 	octeon_swap_8B_data((u64 *)mdio_cmd, sizeof(struct oct_mdio_cmd) / 8);
 
+	sc->iq_no = lio->linfo.txpciq[0].s.q_no;
+
 	octeon_prepare_soft_command(oct_dev, sc, OPCODE_NIC, OPCODE_NIC_MDIO45,
 				    0, 0, 0);
 
@@ -317,7 +315,7 @@
 
 	retval = octeon_send_soft_command(oct_dev, sc);
 
-	if (retval) {
+	if (retval == IQ_SEND_FAILED) {
 		dev_err(&oct_dev->pci_dev->dev,
 			"octnet_mdio45_access instruction failed status: %x\n",
 			retval);
@@ -503,10 +501,10 @@
 	if ((msglvl ^ lio->msg_enable) & NETIF_MSG_HW) {
 		if (msglvl & NETIF_MSG_HW)
 			liquidio_set_feature(netdev,
-					     OCTNET_CMD_VERBOSE_ENABLE);
+					     OCTNET_CMD_VERBOSE_ENABLE, 0);
 		else
 			liquidio_set_feature(netdev,
-					     OCTNET_CMD_VERBOSE_DISABLE);
+					     OCTNET_CMD_VERBOSE_DISABLE, 0);
 	}
 
 	lio->msg_enable = msglvl;
@@ -653,7 +651,7 @@
 				intrmod_cfg->intrmod_mincnt_trigger;
 		}
 
-		iq = oct->instr_queue[lio->linfo.txpciq[0]];
+		iq = oct->instr_queue[lio->linfo.txpciq[0].s.q_no];
 		intr_coal->tx_max_coalesced_frames = iq->fill_threshold;
 		break;
 
@@ -722,7 +720,7 @@
 	sc->wait_time = 1000;
 
 	retval = octeon_send_soft_command(oct_dev, sc);
-	if (retval) {
+	if (retval == IQ_SEND_FAILED) {
 		octeon_free_soft_command(oct_dev, sc);
 		return -EINVAL;
 	}
@@ -859,7 +857,7 @@
 	if ((intr_coal->tx_max_coalesced_frames >= CN6XXX_DB_MIN) &&
 	    (intr_coal->tx_max_coalesced_frames <= CN6XXX_DB_MAX)) {
 		for (j = 0; j < lio->linfo.num_txpciq; j++) {
-			q_no = lio->linfo.txpciq[j];
+			q_no = lio->linfo.txpciq[j].s.q_no;
 			oct->instr_queue[q_no]->fill_threshold =
 				intr_coal->tx_max_coalesced_frames;
 		}
@@ -950,7 +948,6 @@
 	struct octeon_device *oct = lio->oct_dev;
 	struct oct_link_info *linfo;
 	struct octnic_ctrl_pkt nctrl;
-	struct octnic_ctrl_params nparams;
 	int ret = 0;
 
 	/* get the link info */
@@ -978,9 +975,9 @@
 
 	nctrl.ncmd.u64 = 0;
 	nctrl.ncmd.s.cmd = OCTNET_CMD_SET_SETTINGS;
+	nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
 	nctrl.wait_time = 1000;
 	nctrl.netpndev = (u64)netdev;
-	nctrl.ncmd.s.param1 = lio->linfo.ifidx;
 	nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
 
 	/* Passing the parameters sent by ethtool like Speed, Autoneg & Duplex
@@ -990,19 +987,17 @@
 		/* Autoneg ON */
 		nctrl.ncmd.s.more = OCTNIC_NCMD_PHY_ON |
 				     OCTNIC_NCMD_AUTONEG_ON;
-		nctrl.ncmd.s.param2 = ecmd->advertising;
+		nctrl.ncmd.s.param1 = ecmd->advertising;
 	} else {
 		/* Autoneg OFF */
 		nctrl.ncmd.s.more = OCTNIC_NCMD_PHY_ON;
 
-		nctrl.ncmd.s.param3 = ecmd->duplex;
+		nctrl.ncmd.s.param2 = ecmd->duplex;
 
-		nctrl.ncmd.s.param2 = ecmd->speed;
+		nctrl.ncmd.s.param1 = ecmd->speed;
 	}
 
-	nparams.resp_order = OCTEON_RESP_ORDERED;
-
-	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl, nparams);
+	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
 	if (ret < 0) {
 		dev_err(&oct->pci_dev->dev, "Failed to set settings\n");
 		return -1;
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index 8de79ae..d0ab97c 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -84,6 +84,8 @@
 module_param(conf_type, int, 0);
 MODULE_PARM_DESC(conf_type, "select octeon configuration 0 default 1 ovs");
 
+static int ptp_enable = 1;
+
 /* Bit mask values for lio->ifstate */
 #define   LIO_IFSTATE_DROQ_OPS             0x01
 #define   LIO_IFSTATE_REGISTERED           0x02
@@ -166,6 +168,8 @@
 	 *  received from the IP layer.
 	 */
 	struct octeon_sg_entry *sg;
+
+	u64 sg_dma_ptr;
 };
 
 /** This structure is used by NIC driver to store information required
@@ -682,7 +686,8 @@
 		int i;
 
 		for (i = 0; i < netdev->num_tx_queues; i++)
-			netif_wake_subqueue(netdev, i);
+			if (__netif_subqueue_stopped(netdev, i))
+				netif_wake_subqueue(netdev, i);
 	} else {
 		netif_wake_queue(netdev);
 	}
@@ -705,7 +710,7 @@
 {
 	struct lio *lio = GET_LIO(netdev);
 
-	if (lio->linfo.link.s.status) {
+	if (lio->linfo.link.s.link_up) {
 		txqs_start(netdev);
 		return;
 	}
@@ -752,11 +757,14 @@
 
 		/* check each sub-queue state */
 		for (q = 0; q < numqs; q++) {
-			iq = lio->linfo.txpciq[q & (lio->linfo.num_txpciq - 1)];
+			iq = lio->linfo.txpciq[q %
+				(lio->linfo.num_txpciq)].s.q_no;
 			if (octnet_iq_is_full(lio->oct_dev, iq))
 				continue;
-			wake_q(lio->netdev, q);
-			ret_val++;
+			if (__netif_subqueue_stopped(lio->netdev, q)) {
+				wake_q(lio->netdev, q);
+				ret_val++;
+			}
 		}
 	} else {
 		if (octnet_iq_is_full(lio->oct_dev, lio->txq))
@@ -787,64 +795,116 @@
 }
 
 /**
- * \brief Delete gather list
+ * \brief Delete gather lists
  * @param lio per-network private data
  */
-static void delete_glist(struct lio *lio)
+static void delete_glists(struct lio *lio)
 {
 	struct octnic_gather *g;
+	int i;
 
-	do {
-		g = (struct octnic_gather *)
-		    list_delete_head(&lio->glist);
-		if (g) {
-			if (g->sg)
-				kfree((void *)((unsigned long)g->sg -
-						g->adjust));
-			kfree(g);
-		}
-	} while (g);
+	if (!lio->glist)
+		return;
+
+	for (i = 0; i < lio->linfo.num_txpciq; i++) {
+		do {
+			g = (struct octnic_gather *)
+				list_delete_head(&lio->glist[i]);
+			if (g) {
+				if (g->sg) {
+					dma_unmap_single(&lio->oct_dev->
+							 pci_dev->dev,
+							 g->sg_dma_ptr,
+							 g->sg_size,
+							 DMA_TO_DEVICE);
+					kfree((void *)((unsigned long)g->sg -
+						       g->adjust));
+				}
+				kfree(g);
+			}
+		} while (g);
+	}
+
+	kfree((void *)lio->glist);
 }
 
 /**
- * \brief Setup gather list
+ * \brief Setup gather lists
  * @param lio per-network private data
  */
-static int setup_glist(struct lio *lio)
+static int setup_glists(struct octeon_device *oct, struct lio *lio, int num_iqs)
 {
-	int i;
+	int i, j;
 	struct octnic_gather *g;
 
-	INIT_LIST_HEAD(&lio->glist);
+	lio->glist_lock = kcalloc(num_iqs, sizeof(*lio->glist_lock),
+				  GFP_KERNEL);
+	if (!lio->glist_lock)
+		return 1;
 
-	for (i = 0; i < lio->tx_qsize; i++) {
-		g = kzalloc(sizeof(*g), GFP_KERNEL);
-		if (!g)
-			break;
-
-		g->sg_size =
-			((ROUNDUP4(OCTNIC_MAX_SG) >> 2) * OCT_SG_ENTRY_SIZE);
-
-		g->sg = kmalloc(g->sg_size + 8, GFP_KERNEL);
-		if (!g->sg) {
-			kfree(g);
-			break;
-		}
-
-		/* The gather component should be aligned on 64-bit boundary */
-		if (((unsigned long)g->sg) & 7) {
-			g->adjust = 8 - (((unsigned long)g->sg) & 7);
-			g->sg = (struct octeon_sg_entry *)
-				((unsigned long)g->sg + g->adjust);
-		}
-		list_add_tail(&g->list, &lio->glist);
+	lio->glist = kcalloc(num_iqs, sizeof(*lio->glist),
+			     GFP_KERNEL);
+	if (!lio->glist) {
+		kfree((void *)lio->glist_lock);
+		return 1;
 	}
 
-	if (i == lio->tx_qsize)
-		return 0;
+	for (i = 0; i < num_iqs; i++) {
+		int numa_node = cpu_to_node(i % num_online_cpus());
 
-	delete_glist(lio);
-	return 1;
+		spin_lock_init(&lio->glist_lock[i]);
+
+		INIT_LIST_HEAD(&lio->glist[i]);
+
+		for (j = 0; j < lio->tx_qsize; j++) {
+			g = kzalloc_node(sizeof(*g), GFP_KERNEL,
+					 numa_node);
+			if (!g)
+				g = kzalloc(sizeof(*g), GFP_KERNEL);
+			if (!g)
+				break;
+
+			g->sg_size = ((ROUNDUP4(OCTNIC_MAX_SG) >> 2) *
+				      OCT_SG_ENTRY_SIZE);
+
+			g->sg = kmalloc_node(g->sg_size + 8,
+					     GFP_KERNEL, numa_node);
+			if (!g->sg)
+				g->sg = kmalloc(g->sg_size + 8, GFP_KERNEL);
+			if (!g->sg) {
+				kfree(g);
+				break;
+			}
+
+			/* The gather component should be aligned on 64-bit
+			 * boundary
+			 */
+			if (((unsigned long)g->sg) & 7) {
+				g->adjust = 8 - (((unsigned long)g->sg) & 7);
+				g->sg = (struct octeon_sg_entry *)
+					((unsigned long)g->sg + g->adjust);
+			}
+			g->sg_dma_ptr = dma_map_single(&oct->pci_dev->dev,
+						       g->sg, g->sg_size,
+						       DMA_TO_DEVICE);
+			if (dma_mapping_error(&oct->pci_dev->dev,
+					      g->sg_dma_ptr)) {
+				kfree((void *)((unsigned long)g->sg -
+					       g->adjust));
+				kfree(g);
+				break;
+			}
+
+			list_add_tail(&g->list, &lio->glist[i]);
+		}
+
+		if (j != lio->tx_qsize) {
+			delete_glists(lio);
+			return 1;
+		}
+	}
+
+	return 0;
 }
 
 /**
@@ -858,7 +918,7 @@
 	if (atomic_read(&lio->ifstate) & LIO_IFSTATE_REGISTERED) {
 		struct oct_link_info *linfo = &lio->linfo;
 
-		if (linfo->link.s.status) {
+		if (linfo->link.s.link_up) {
 			netif_info(lio, link, lio->netdev, "%d Mbps %s Duplex UP\n",
 				   linfo->link.s.speed,
 				   (linfo->link.s.duplex) ? "Full" : "Half");
@@ -880,13 +940,15 @@
 				      union oct_link_status *ls)
 {
 	struct lio *lio = GET_LIO(netdev);
+	int changed = (lio->linfo.link.u64 != ls->u64);
 
-	if ((lio->intf_open) && (lio->linfo.link.u64 != ls->u64)) {
-		lio->linfo.link.u64 = ls->u64;
+	lio->linfo.link.u64 = ls->u64;
 
+	if ((lio->intf_open) && (changed)) {
 		print_link_info(netdev);
+		lio->link_changes++;
 
-		if (lio->linfo.link.s.status) {
+		if (lio->linfo.link.s.link_up) {
 			netif_carrier_on(netdev);
 			/* start_txq(netdev); */
 			txqs_wake(netdev);
@@ -1159,18 +1221,15 @@
 static void send_rx_ctrl_cmd(struct lio *lio, int start_stop)
 {
 	struct octnic_ctrl_pkt nctrl;
-	struct octnic_ctrl_params nparams;
 
 	memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
 
 	nctrl.ncmd.s.cmd = OCTNET_CMD_RX_CTL;
-	nctrl.ncmd.s.param1 = lio->linfo.ifidx;
-	nctrl.ncmd.s.param2 = start_stop;
+	nctrl.ncmd.s.param1 = start_stop;
+	nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
 	nctrl.netpndev = (u64)lio->netdev;
 
-	nparams.resp_order = OCTEON_RESP_NORESPONSE;
-
-	if (octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl, nparams) < 0)
+	if (octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl) < 0)
 		netif_info(lio, rx_err, lio->netdev, "Failed to send RX Control message\n");
 }
 
@@ -1205,10 +1264,12 @@
 	if (atomic_read(&lio->ifstate) & LIO_IFSTATE_REGISTERED)
 		unregister_netdev(netdev);
 
-	delete_glist(lio);
+	delete_glists(lio);
 
 	free_netdev(netdev);
 
+	oct->props[ifidx].gmxport = -1;
+
 	oct->props[ifidx].netdev = NULL;
 }
 
@@ -1230,7 +1291,8 @@
 	for (i = 0; i < oct->ifcount; i++) {
 		lio = GET_LIO(oct->props[i].netdev);
 		for (j = 0; j < lio->linfo.num_rxpciq; j++)
-			octeon_unregister_droq_ops(oct, lio->linfo.rxpciq[j]);
+			octeon_unregister_droq_ops(oct,
+						   lio->linfo.rxpciq[j].s.q_no);
 	}
 
 	for (i = 0; i < oct->ifcount; i++)
@@ -1326,6 +1388,16 @@
 	return 0;
 }
 
+static inline int skb_iq(struct lio *lio, struct sk_buff *skb)
+{
+	int q = 0;
+
+	if (netif_is_multiqueue(lio->netdev))
+		q = skb->queue_mapping % lio->linfo.num_txpciq;
+
+	return q;
+}
+
 /**
  * \brief Check Tx queue state for a given network buffer
  * @param lio per-network private data
@@ -1337,14 +1409,17 @@
 
 	if (netif_is_multiqueue(lio->netdev)) {
 		q = skb->queue_mapping;
-		iq = lio->linfo.txpciq[(q & (lio->linfo.num_txpciq - 1))];
+		iq = lio->linfo.txpciq[(q % (lio->linfo.num_txpciq))].s.q_no;
 	} else {
 		iq = lio->txq;
+		q = iq;
 	}
 
 	if (octnet_iq_is_full(lio->oct_dev, iq))
 		return 0;
-	wake_q(lio->netdev, q);
+
+	if (__netif_subqueue_stopped(lio->netdev, q))
+		wake_q(lio->netdev, q);
 	return 1;
 }
 
@@ -1367,7 +1442,7 @@
 
 	check_txq_state(lio, skb);
 
-	recv_buffer_free((struct sk_buff *)skb);
+	tx_buffer_free(skb);
 }
 
 /**
@@ -1380,7 +1455,7 @@
 	struct sk_buff *skb;
 	struct lio *lio;
 	struct octnic_gather *g;
-	int i, frags;
+	int i, frags, iq;
 
 	finfo = (struct octnet_buf_free_info *)buf;
 	skb = finfo->skb;
@@ -1402,17 +1477,17 @@
 		i++;
 	}
 
-	dma_unmap_single(&lio->oct_dev->pci_dev->dev,
-			 finfo->dptr, g->sg_size,
-			 DMA_TO_DEVICE);
+	dma_sync_single_for_cpu(&lio->oct_dev->pci_dev->dev,
+				g->sg_dma_ptr, g->sg_size, DMA_TO_DEVICE);
 
-	spin_lock(&lio->lock);
-	list_add_tail(&g->list, &lio->glist);
-	spin_unlock(&lio->lock);
+	iq = skb_iq(lio, skb);
+	spin_lock(&lio->glist_lock[iq]);
+	list_add_tail(&g->list, &lio->glist[iq]);
+	spin_unlock(&lio->glist_lock[iq]);
 
 	check_txq_state(lio, skb);     /* mq support: sub-queue state check */
 
-	recv_buffer_free((struct sk_buff *)skb);
+	tx_buffer_free(skb);
 }
 
 /**
@@ -1426,7 +1501,7 @@
 	struct sk_buff *skb;
 	struct lio *lio;
 	struct octnic_gather *g;
-	int i, frags;
+	int i, frags, iq;
 
 	sc = (struct octeon_soft_command *)buf;
 	skb = (struct sk_buff *)sc->callback_arg;
@@ -1450,13 +1525,14 @@
 		i++;
 	}
 
-	dma_unmap_single(&lio->oct_dev->pci_dev->dev,
-			 finfo->dptr, g->sg_size,
-			 DMA_TO_DEVICE);
+	dma_sync_single_for_cpu(&lio->oct_dev->pci_dev->dev,
+				g->sg_dma_ptr, g->sg_size, DMA_TO_DEVICE);
 
-	spin_lock(&lio->lock);
-	list_add_tail(&g->list, &lio->glist);
-	spin_unlock(&lio->lock);
+	iq = skb_iq(lio, skb);
+
+	spin_lock(&lio->glist_lock[iq]);
+	list_add_tail(&g->list, &lio->glist[iq]);
+	spin_unlock(&lio->glist_lock[iq]);
 
 	/* Don't free the skb yet */
 
@@ -1743,14 +1819,13 @@
 static u16 select_q(struct net_device *dev, struct sk_buff *skb,
 		    void *accel_priv, select_queue_fallback_t fallback)
 {
-	int qindex;
+	u32 qindex = 0;
 	struct lio *lio;
 
 	lio = GET_LIO(dev);
-	/* select queue on chosen queue_mapping or core */
-	qindex = skb_rx_queue_recorded(skb) ?
-		 skb_get_rx_queue(skb) : smp_processor_id();
-	return (u16)(qindex & (lio->linfo.num_txpciq - 1));
+	qindex = skb_tx_hash(dev, skb);
+
+	return (u16)(qindex % (lio->linfo.num_txpciq));
 }
 
 /** Routine to push packets arriving on Octeon interface upto network layer.
@@ -1759,26 +1834,27 @@
  * @param len      - size of total data received.
  * @param rh       - Control header associated with the packet
  * @param param    - additional control data with the packet
+ * @param arg	   - farg registered in droq_ops
  */
 static void
 liquidio_push_packet(u32 octeon_id,
 		     void *skbuff,
 		     u32 len,
 		     union octeon_rh *rh,
-		     void *param)
+		     void *param,
+		     void *arg)
 {
 	struct napi_struct *napi = param;
-	struct octeon_device *oct = lio_get_device(octeon_id);
 	struct sk_buff *skb = (struct sk_buff *)skbuff;
 	struct skb_shared_hwtstamps *shhwtstamps;
 	u64 ns;
-	struct net_device *netdev =
-		(struct net_device *)oct->props[rh->r_dh.link].netdev;
+	struct net_device *netdev = (struct net_device *)arg;
 	struct octeon_droq *droq = container_of(param, struct octeon_droq,
 						napi);
 	if (netdev) {
 		int packet_was_received;
 		struct lio *lio = GET_LIO(netdev);
+		struct octeon_device *oct = lio->oct_dev;
 
 		/* Do not proceed if the interface is not in RUNNING state. */
 		if (!ifstate_check(lio, LIO_IFSTATE_RUNNING)) {
@@ -1789,21 +1865,54 @@
 
 		skb->dev = netdev;
 
-		if (rh->r_dh.has_hwtstamp) {
-			/* timestamp is included from the hardware at the
-			 * beginning of the packet.
-			 */
-			if (ifstate_check(lio,
-					  LIO_IFSTATE_RX_TIMESTAMP_ENABLED)) {
-				/* Nanoseconds are in the first 64-bits
-				 * of the packet.
-				 */
-				memcpy(&ns, (skb->data), sizeof(ns));
-				shhwtstamps = skb_hwtstamps(skb);
-				shhwtstamps->hwtstamp =
-					ns_to_ktime(ns + lio->ptp_adjust);
+		skb_record_rx_queue(skb, droq->q_no);
+		if (likely(len > MIN_SKB_SIZE)) {
+			struct octeon_skb_page_info *pg_info;
+			unsigned char *va;
+
+			pg_info = ((struct octeon_skb_page_info *)(skb->cb));
+			if (pg_info->page) {
+				/* For Paged allocation use the frags */
+				va = page_address(pg_info->page) +
+					pg_info->page_offset;
+				memcpy(skb->data, va, MIN_SKB_SIZE);
+				skb_put(skb, MIN_SKB_SIZE);
+				skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
+						pg_info->page,
+						pg_info->page_offset +
+						MIN_SKB_SIZE,
+						len - MIN_SKB_SIZE,
+						LIO_RXBUFFER_SZ);
 			}
-			skb_pull(skb, sizeof(ns));
+		} else {
+			struct octeon_skb_page_info *pg_info =
+				((struct octeon_skb_page_info *)(skb->cb));
+			skb_copy_to_linear_data(skb, page_address(pg_info->page)
+						+ pg_info->page_offset, len);
+			skb_put(skb, len);
+			put_page(pg_info->page);
+		}
+
+		if (((oct->chip_id == OCTEON_CN66XX) ||
+		     (oct->chip_id == OCTEON_CN68XX)) &&
+		    ptp_enable) {
+			if (rh->r_dh.has_hwtstamp) {
+				/* timestamp is included from the hardware at
+				 * the beginning of the packet.
+				 */
+				if (ifstate_check
+				    (lio, LIO_IFSTATE_RX_TIMESTAMP_ENABLED)) {
+					/* Nanoseconds are in the first 64-bits
+					 * of the packet.
+					 */
+					memcpy(&ns, (skb->data), sizeof(ns));
+					shhwtstamps = skb_hwtstamps(skb);
+					shhwtstamps->hwtstamp =
+						ns_to_ktime(ns +
+							    lio->ptp_adjust);
+				}
+				skb_pull(skb, sizeof(ns));
+			}
 		}
 
 		skb->protocol = eth_type_trans(skb, skb->dev);
@@ -1935,10 +2044,10 @@
  * are for ingress packets.
  */
 static inline int setup_io_queues(struct octeon_device *octeon_dev,
-				  struct net_device *net_device)
+				  int ifidx)
 {
-	static int first_time = 1;
-	static struct octeon_droq_ops droq_ops;
+	struct octeon_droq_ops droq_ops;
+	struct net_device *netdev;
 	static int cpu_id;
 	static int cpu_id_modulus;
 	struct octeon_droq *droq;
@@ -1947,23 +2056,26 @@
 	struct lio *lio;
 	int num_tx_descs;
 
-	lio = GET_LIO(net_device);
-	if (first_time) {
-		first_time = 0;
-		memset(&droq_ops, 0, sizeof(struct octeon_droq_ops));
+	netdev = octeon_dev->props[ifidx].netdev;
 
-		droq_ops.fptr = liquidio_push_packet;
+	lio = GET_LIO(netdev);
 
-		droq_ops.poll_mode = 1;
-		droq_ops.napi_fn = liquidio_napi_drv_callback;
-		cpu_id = 0;
-		cpu_id_modulus = num_present_cpus();
-	}
+	memset(&droq_ops, 0, sizeof(struct octeon_droq_ops));
+
+	droq_ops.fptr = liquidio_push_packet;
+	droq_ops.farg = (void *)netdev;
+
+	droq_ops.poll_mode = 1;
+	droq_ops.napi_fn = liquidio_napi_drv_callback;
+	cpu_id = 0;
+	cpu_id_modulus = num_present_cpus();
 
 	/* set up DROQs. */
 	for (q = 0; q < lio->linfo.num_rxpciq; q++) {
-		q_no = lio->linfo.rxpciq[q];
-
+		q_no = lio->linfo.rxpciq[q].s.q_no;
+		dev_dbg(&octeon_dev->pci_dev->dev,
+			"setup_io_queues index:%d linfo.rxpciq.s.q_no:%d\n",
+			q, q_no);
 		retval = octeon_setup_droq(octeon_dev, q_no,
 					   CFG_GET_NUM_RX_DESCS_NIC_IF
 						   (octeon_get_conf(octeon_dev),
@@ -1980,7 +2092,11 @@
 
 		droq = octeon_dev->droq[q_no];
 		napi = &droq->napi;
-		netif_napi_add(net_device, napi, liquidio_napi_poll, 64);
+		dev_dbg(&octeon_dev->pci_dev->dev,
+			"netif_napi_add netdev:%llx oct:%llx\n",
+			(u64)netdev,
+			(u64)octeon_dev);
+		netif_napi_add(netdev, napi, liquidio_napi_poll, 64);
 
 		/* designate a CPU for this droq */
 		droq->cpu_id = cpu_id;
@@ -1996,9 +2112,9 @@
 		num_tx_descs = CFG_GET_NUM_TX_DESCS_NIC_IF(octeon_get_conf
 							   (octeon_dev),
 							   lio->ifidx);
-		retval = octeon_setup_iq(octeon_dev, lio->linfo.txpciq[q],
-					 num_tx_descs,
-					 netdev_get_tx_queue(net_device, q));
+		retval = octeon_setup_iq(octeon_dev, ifidx, q,
+					 lio->linfo.txpciq[q], num_tx_descs,
+					 netdev_get_tx_queue(netdev, q));
 		if (retval) {
 			dev_err(&octeon_dev->pci_dev->dev,
 				" %s : Runtime IQ(TxQ) creation failed.\n",
@@ -2036,7 +2152,8 @@
 	struct lio *lio = GET_LIO(netdev);
 	struct octeon_device *oct = lio->oct_dev;
 
-	lio->txq_status_wq.wq = create_workqueue("txq-status");
+	lio->txq_status_wq.wq = alloc_workqueue("txq-status",
+						WQ_MEM_RECLAIM, 0);
 	if (!lio->txq_status_wq.wq) {
 		dev_err(&oct->pci_dev->dev, "unable to create cavium txq status wq\n");
 		return;
@@ -2095,7 +2212,8 @@
 	netif_info(lio, ifdown, lio->netdev, "Stopping interface!\n");
 	/* Inform that netif carrier is down */
 	lio->intf_open = 0;
-	lio->linfo.link.s.status = 0;
+	lio->linfo.link.s.link_up = 0;
+	lio->link_changes++;
 
 	netif_carrier_off(netdev);
 
@@ -2103,7 +2221,6 @@
 	send_rx_ctrl_cmd(lio, 0);
 
 	cancel_delayed_work_sync(&lio->txq_status_wq.wk.work);
-	flush_workqueue(lio->txq_status_wq.wq);
 	destroy_workqueue(lio->txq_status_wq.wq);
 
 	if (lio->ptp_clock) {
@@ -2235,7 +2352,6 @@
 	struct lio *lio = GET_LIO(netdev);
 	struct octeon_device *oct = lio->oct_dev;
 	struct octnic_ctrl_pkt nctrl;
-	struct octnic_ctrl_params nparams;
 	struct netdev_hw_addr *ha;
 	u64 *mc;
 	int ret, i;
@@ -2246,10 +2362,10 @@
 	/* Create a ctrl pkt command to be sent to core app. */
 	nctrl.ncmd.u64 = 0;
 	nctrl.ncmd.s.cmd = OCTNET_CMD_SET_MULTI_LIST;
-	nctrl.ncmd.s.param1 = lio->linfo.ifidx;
-	nctrl.ncmd.s.param2 = get_new_flags(netdev);
-	nctrl.ncmd.s.param3 = mc_count;
+	nctrl.ncmd.s.param1 = get_new_flags(netdev);
+	nctrl.ncmd.s.param2 = mc_count;
 	nctrl.ncmd.s.more = mc_count;
+	nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
 	nctrl.netpndev = (u64)netdev;
 	nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
 
@@ -2270,9 +2386,7 @@
 	 */
 	nctrl.wait_time = 0;
 
-	nparams.resp_order = OCTEON_RESP_NORESPONSE;
-
-	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl, nparams);
+	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
 	if (ret < 0) {
 		dev_err(&oct->pci_dev->dev, "DEVFLAGS change failed in core (ret: 0x%x)\n",
 			ret);
@@ -2290,19 +2404,17 @@
 	struct octeon_device *oct = lio->oct_dev;
 	struct sockaddr *addr = (struct sockaddr *)p;
 	struct octnic_ctrl_pkt nctrl;
-	struct octnic_ctrl_params nparams;
 
-	if ((!is_valid_ether_addr(addr->sa_data)) ||
-	    (ifstate_check(lio, LIO_IFSTATE_RUNNING)))
+	if (!is_valid_ether_addr(addr->sa_data))
 		return -EADDRNOTAVAIL;
 
 	memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
 
 	nctrl.ncmd.u64 = 0;
 	nctrl.ncmd.s.cmd = OCTNET_CMD_CHANGE_MACADDR;
-	nctrl.ncmd.s.param1 = lio->linfo.ifidx;
-	nctrl.ncmd.s.param2 = 0;
+	nctrl.ncmd.s.param1 = 0;
 	nctrl.ncmd.s.more = 1;
+	nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
 	nctrl.netpndev = (u64)netdev;
 	nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
 	nctrl.wait_time = 100;
@@ -2311,9 +2423,7 @@
 	/* The MAC Address is presented in network byte order. */
 	memcpy((u8 *)&nctrl.udd[0] + 2, addr->sa_data, ETH_ALEN);
 
-	nparams.resp_order = OCTEON_RESP_ORDERED;
-
-	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl, nparams);
+	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
 	if (ret < 0) {
 		dev_err(&oct->pci_dev->dev, "MAC Address change failed\n");
 		return -ENOMEM;
@@ -2341,7 +2451,7 @@
 	oct = lio->oct_dev;
 
 	for (i = 0; i < lio->linfo.num_txpciq; i++) {
-		iq_no = lio->linfo.txpciq[i];
+		iq_no = lio->linfo.txpciq[i].s.q_no;
 		iq_stats = &oct->instr_queue[iq_no]->stats;
 		pkts += iq_stats->tx_done;
 		drop += iq_stats->tx_dropped;
@@ -2357,7 +2467,7 @@
 	bytes = 0;
 
 	for (i = 0; i < lio->linfo.num_rxpciq; i++) {
-		oq_no = lio->linfo.rxpciq[i];
+		oq_no = lio->linfo.rxpciq[i].s.q_no;
 		oq_stats = &oct->droq[oq_no]->stats;
 		pkts += oq_stats->rx_pkts_received;
 		drop += (oq_stats->rx_dropped +
@@ -2383,7 +2493,6 @@
 	struct lio *lio = GET_LIO(netdev);
 	struct octeon_device *oct = lio->oct_dev;
 	struct octnic_ctrl_pkt nctrl;
-	struct octnic_ctrl_params nparams;
 	int max_frm_size = new_mtu + OCTNET_FRM_HEADER_SIZE;
 	int ret = 0;
 
@@ -2403,15 +2512,13 @@
 
 	nctrl.ncmd.u64 = 0;
 	nctrl.ncmd.s.cmd = OCTNET_CMD_CHANGE_MTU;
-	nctrl.ncmd.s.param1 = lio->linfo.ifidx;
-	nctrl.ncmd.s.param2 = new_mtu;
+	nctrl.ncmd.s.param1 = new_mtu;
+	nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
 	nctrl.wait_time = 100;
 	nctrl.netpndev = (u64)netdev;
 	nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
 
-	nparams.resp_order = OCTEON_RESP_ORDERED;
-
-	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl, nparams);
+	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
 	if (ret < 0) {
 		dev_err(&oct->pci_dev->dev, "Failed to set MTU\n");
 		return -1;
@@ -2536,7 +2643,7 @@
 	}
 
 	octeon_free_soft_command(oct, sc);
-	recv_buffer_free(skb);
+	tx_buffer_free(skb);
 }
 
 /* \brief Send a data packet that will be timestamped
@@ -2551,10 +2658,9 @@
 {
 	int retval;
 	struct octeon_soft_command *sc;
-	struct octeon_instr_ih *ih;
-	struct octeon_instr_rdp *rdp;
 	struct lio *lio;
 	int ring_doorbell;
+	u32 len;
 
 	lio = finfo->lio;
 
@@ -2576,14 +2682,13 @@
 	sc->callback_arg = finfo->skb;
 	sc->iq_no = ndata->q_no;
 
-	ih = (struct octeon_instr_ih *)&sc->cmd.ih;
-	rdp = (struct octeon_instr_rdp *)&sc->cmd.rdp;
+	len = (u32)((struct octeon_instr_ih2 *)(&sc->cmd.cmd2.ih2))->dlengsz;
 
 	ring_doorbell = !xmit_more;
 	retval = octeon_send_command(oct, sc->iq_no, ring_doorbell, &sc->cmd,
-				     sc, ih->dlengsz, ndata->reqtype);
+				     sc, len, ndata->reqtype);
 
-	if (retval) {
+	if (retval == IQ_SEND_FAILED) {
 		dev_err(&oct->pci_dev->dev, "timestamp data packet failed status: %x\n",
 			retval);
 		octeon_free_soft_command(oct, sc);
@@ -2594,68 +2699,6 @@
 	return retval;
 }
 
-static inline int is_ipv4(struct sk_buff *skb)
-{
-	return (skb->protocol == htons(ETH_P_IP)) &&
-	       (ip_hdr(skb)->version == 4);
-}
-
-static inline int is_vlan(struct sk_buff *skb)
-{
-	return skb->protocol == htons(ETH_P_8021Q);
-}
-
-static inline int is_ip_fragmented(struct sk_buff *skb)
-{
-	/* The Don't fragment and Reserved flag fields are ignored.
-	 * IP is fragmented if
-	 * -  the More fragments bit is set (indicating this IP is a fragment
-	 * with more to follow; the current offset could be 0 ).
-	 * -  ths offset field is non-zero.
-	 */
-	return (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) ? 1 : 0;
-}
-
-static inline int is_ipv6(struct sk_buff *skb)
-{
-	return (skb->protocol == htons(ETH_P_IPV6)) &&
-	       (ipv6_hdr(skb)->version == 6);
-}
-
-static inline int is_with_extn_hdr(struct sk_buff *skb)
-{
-	return (ipv6_hdr(skb)->nexthdr != IPPROTO_TCP) &&
-	       (ipv6_hdr(skb)->nexthdr != IPPROTO_UDP);
-}
-
-static inline int is_tcpudp(struct sk_buff *skb)
-{
-	return (ip_hdr(skb)->protocol == IPPROTO_TCP) ||
-	       (ip_hdr(skb)->protocol == IPPROTO_UDP);
-}
-
-static inline u32 get_ipv4_5tuple_tag(struct sk_buff *skb)
-{
-	u32 tag;
-	struct iphdr *iphdr = ip_hdr(skb);
-
-	tag = crc32(0, &iphdr->protocol, 1);
-	tag = crc32(tag, (u8 *)&iphdr->saddr, 8);
-	tag = crc32(tag, skb_transport_header(skb), 4);
-	return tag;
-}
-
-static inline u32 get_ipv6_5tuple_tag(struct sk_buff *skb)
-{
-	u32 tag;
-	struct ipv6hdr *ipv6hdr = ipv6_hdr(skb);
-
-	tag = crc32(0, &ipv6hdr->nexthdr, 1);
-	tag = crc32(tag, (u8 *)&ipv6hdr->saddr, 32);
-	tag = crc32(tag, skb_transport_header(skb), 4);
-	return tag;
-}
-
 /** \brief Transmit networks packets to the Octeon interface
  * @param skbuff   skbuff struct to be passed to network layer.
  * @param netdev    pointer to network device
@@ -2670,18 +2713,22 @@
 	struct octnic_data_pkt ndata;
 	struct octeon_device *oct;
 	struct oct_iq_stats *stats;
-	int cpu = 0, status = 0;
+	struct octeon_instr_irh *irh;
+	union tx_info *tx_info;
+	int status = 0;
 	int q_idx = 0, iq_no = 0;
-	int xmit_more;
+	int xmit_more, j;
+	u64 dptr = 0;
 	u32 tag = 0;
 
 	lio = GET_LIO(netdev);
 	oct = lio->oct_dev;
 
 	if (netif_is_multiqueue(netdev)) {
-		cpu = skb->queue_mapping;
-		q_idx = (cpu & (lio->linfo.num_txpciq - 1));
-		iq_no = lio->linfo.txpciq[q_idx];
+		q_idx = skb->queue_mapping;
+		q_idx = (q_idx % (lio->linfo.num_txpciq));
+		tag = q_idx;
+		iq_no = lio->linfo.txpciq[q_idx].s.q_no;
 	} else {
 		iq_no = lio->txq;
 	}
@@ -2692,11 +2739,11 @@
 	 * transmitted.
 	 */
 	if (!(atomic_read(&lio->ifstate) & LIO_IFSTATE_RUNNING) ||
-	    (!lio->linfo.link.s.status) ||
+	    (!lio->linfo.link.s.link_up) ||
 	    (skb->len <= 0)) {
 		netif_info(lio, tx_err, lio->netdev,
 			   "Transmit failed link_status : %d\n",
-			   lio->linfo.link.s.status);
+			   lio->linfo.link.s.link_up);
 		goto lio_xmit_failed;
 	}
 
@@ -2739,53 +2786,11 @@
 	ndata.datasize = skb->len;
 
 	cmdsetup.u64 = 0;
-	cmdsetup.s.ifidx = lio->linfo.ifidx;
+	cmdsetup.s.iq_no = iq_no;
 
-	if (skb->ip_summed == CHECKSUM_PARTIAL) {
-		if (is_ipv4(skb) && !is_ip_fragmented(skb) && is_tcpudp(skb)) {
-			tag = get_ipv4_5tuple_tag(skb);
+	if (skb->ip_summed == CHECKSUM_PARTIAL)
+		cmdsetup.s.transport_csum = 1;
 
-			cmdsetup.s.cksum_offset = sizeof(struct ethhdr) + 1;
-
-			if (ip_hdr(skb)->ihl > 5)
-				cmdsetup.s.ipv4opts_ipv6exthdr =
-						OCT_PKT_PARAM_IPV4OPTS;
-
-		} else if (is_ipv6(skb)) {
-			tag = get_ipv6_5tuple_tag(skb);
-
-			cmdsetup.s.cksum_offset = sizeof(struct ethhdr) + 1;
-
-			if (is_with_extn_hdr(skb))
-				cmdsetup.s.ipv4opts_ipv6exthdr =
-						OCT_PKT_PARAM_IPV6EXTHDR;
-
-		} else if (is_vlan(skb)) {
-			if (vlan_eth_hdr(skb)->h_vlan_encapsulated_proto
-				== htons(ETH_P_IP) &&
-				!is_ip_fragmented(skb) && is_tcpudp(skb)) {
-				tag = get_ipv4_5tuple_tag(skb);
-
-				cmdsetup.s.cksum_offset =
-					sizeof(struct vlan_ethhdr) + 1;
-
-				if (ip_hdr(skb)->ihl > 5)
-					cmdsetup.s.ipv4opts_ipv6exthdr =
-						OCT_PKT_PARAM_IPV4OPTS;
-
-			} else if (vlan_eth_hdr(skb)->h_vlan_encapsulated_proto
-				== htons(ETH_P_IPV6)) {
-				tag = get_ipv6_5tuple_tag(skb);
-
-				cmdsetup.s.cksum_offset =
-					sizeof(struct vlan_ethhdr) + 1;
-
-				if (is_with_extn_hdr(skb))
-					cmdsetup.s.ipv4opts_ipv6exthdr =
-						OCT_PKT_PARAM_IPV6EXTHDR;
-			}
-		}
-	}
 	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) {
 		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 		cmdsetup.s.timestamp = 1;
@@ -2793,20 +2798,20 @@
 
 	if (skb_shinfo(skb)->nr_frags == 0) {
 		cmdsetup.s.u.datasize = skb->len;
-		octnet_prepare_pci_cmd(&ndata.cmd, &cmdsetup, tag);
+		octnet_prepare_pci_cmd(oct, &ndata.cmd, &cmdsetup, tag);
 		/* Offload checksum calculation for TCP/UDP packets */
-		ndata.cmd.dptr = dma_map_single(&oct->pci_dev->dev,
-						skb->data,
-						skb->len,
-						DMA_TO_DEVICE);
-		if (dma_mapping_error(&oct->pci_dev->dev, ndata.cmd.dptr)) {
+		dptr = dma_map_single(&oct->pci_dev->dev,
+				      skb->data,
+				      skb->len,
+				      DMA_TO_DEVICE);
+		if (dma_mapping_error(&oct->pci_dev->dev, dptr)) {
 			dev_err(&oct->pci_dev->dev, "%s DMA mapping error 1\n",
 				__func__);
 			return NETDEV_TX_BUSY;
 		}
 
-		finfo->dptr = ndata.cmd.dptr;
-
+		ndata.cmd.cmd2.dptr = dptr;
+		finfo->dptr = dptr;
 		ndata.reqtype = REQTYPE_NORESP_NET;
 
 	} else {
@@ -2814,9 +2819,10 @@
 		struct skb_frag_struct *frag;
 		struct octnic_gather *g;
 
-		spin_lock(&lio->lock);
-		g = (struct octnic_gather *)list_delete_head(&lio->glist);
-		spin_unlock(&lio->lock);
+		spin_lock(&lio->glist_lock[q_idx]);
+		g = (struct octnic_gather *)
+			list_delete_head(&lio->glist[q_idx]);
+		spin_unlock(&lio->glist_lock[q_idx]);
 
 		if (!g) {
 			netif_info(lio, tx_err, lio->netdev,
@@ -2826,7 +2832,7 @@
 
 		cmdsetup.s.gather = 1;
 		cmdsetup.s.u.gatherptrs = (skb_shinfo(skb)->nr_frags + 1);
-		octnet_prepare_pci_cmd(&ndata.cmd, &cmdsetup, tag);
+		octnet_prepare_pci_cmd(oct, &ndata.cmd, &cmdsetup, tag);
 
 		memset(g->sg, 0, g->sg_size);
 
@@ -2853,34 +2859,43 @@
 					     frag->size,
 					     DMA_TO_DEVICE);
 
+			if (dma_mapping_error(&oct->pci_dev->dev,
+					      g->sg[i >> 2].ptr[i & 3])) {
+				dma_unmap_single(&oct->pci_dev->dev,
+						 g->sg[0].ptr[0],
+						 skb->len - skb->data_len,
+						 DMA_TO_DEVICE);
+				for (j = 1; j < i; j++) {
+					frag = &skb_shinfo(skb)->frags[j - 1];
+					dma_unmap_page(&oct->pci_dev->dev,
+						       g->sg[j >> 2].ptr[j & 3],
+						       frag->size,
+						       DMA_TO_DEVICE);
+				}
+				dev_err(&oct->pci_dev->dev, "%s DMA mapping error 3\n",
+					__func__);
+				return NETDEV_TX_BUSY;
+			}
+
 			add_sg_size(&g->sg[(i >> 2)], frag->size, (i & 3));
 			i++;
 		}
 
-		ndata.cmd.dptr = dma_map_single(&oct->pci_dev->dev,
-						g->sg, g->sg_size,
-						DMA_TO_DEVICE);
-		if (dma_mapping_error(&oct->pci_dev->dev, ndata.cmd.dptr)) {
-			dev_err(&oct->pci_dev->dev, "%s DMA mapping error 3\n",
-				__func__);
-			dma_unmap_single(&oct->pci_dev->dev, g->sg[0].ptr[0],
-					 skb->len - skb->data_len,
-					 DMA_TO_DEVICE);
-			return NETDEV_TX_BUSY;
-		}
+		dma_sync_single_for_device(&oct->pci_dev->dev, g->sg_dma_ptr,
+					   g->sg_size, DMA_TO_DEVICE);
+		dptr = g->sg_dma_ptr;
 
-		finfo->dptr = ndata.cmd.dptr;
+		ndata.cmd.cmd2.dptr = dptr;
+		finfo->dptr = dptr;
 		finfo->g = g;
 
 		ndata.reqtype = REQTYPE_NORESP_NET_SG;
 	}
 
-	if (skb_shinfo(skb)->gso_size) {
-		struct octeon_instr_irh *irh =
-			(struct octeon_instr_irh *)&ndata.cmd.irh;
-		union tx_info *tx_info = (union tx_info *)&ndata.cmd.ossp[0];
+	irh = (struct octeon_instr_irh *)&ndata.cmd.cmd2.irh;
+	tx_info = (union tx_info *)&ndata.cmd.cmd2.ossp[0];
 
-		irh->len = 1;   /* to indicate that ossp[0] contains tx_info */
+	if (skb_shinfo(skb)->gso_size) {
 		tx_info->s.gso_size = skb_shinfo(skb)->gso_size;
 		tx_info->s.gso_segs = skb_shinfo(skb)->gso_segs;
 	}
@@ -2910,9 +2925,10 @@
 	stats->tx_dropped++;
 	netif_info(lio, tx_err, lio->netdev, "IQ%d Transmit dropped:%llu\n",
 		   iq_no, stats->tx_dropped);
-	dma_unmap_single(&oct->pci_dev->dev, ndata.cmd.dptr,
-			 ndata.datasize, DMA_TO_DEVICE);
-	recv_buffer_free(skb);
+	if (dptr)
+		dma_unmap_single(&oct->pci_dev->dev, dptr,
+				 ndata.datasize, DMA_TO_DEVICE);
+	tx_buffer_free(skb);
 	return NETDEV_TX_OK;
 }
 
@@ -2932,27 +2948,24 @@
 	txqs_wake(netdev);
 }
 
-int liquidio_set_feature(struct net_device *netdev, int cmd)
+int liquidio_set_feature(struct net_device *netdev, int cmd, u16 param1)
 {
 	struct lio *lio = GET_LIO(netdev);
 	struct octeon_device *oct = lio->oct_dev;
 	struct octnic_ctrl_pkt nctrl;
-	struct octnic_ctrl_params nparams;
 	int ret = 0;
 
 	memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
 
 	nctrl.ncmd.u64 = 0;
 	nctrl.ncmd.s.cmd = cmd;
-	nctrl.ncmd.s.param1 = lio->linfo.ifidx;
-	nctrl.ncmd.s.param2 = OCTNIC_LROIPV4 | OCTNIC_LROIPV6;
+	nctrl.ncmd.s.param1 = param1;
+	nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
 	nctrl.wait_time = 100;
 	nctrl.netpndev = (u64)netdev;
 	nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
 
-	nparams.resp_order = OCTEON_RESP_NORESPONSE;
-
-	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl, nparams);
+	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
 	if (ret < 0) {
 		dev_err(&oct->pci_dev->dev, "Feature change failed in core (ret: 0x%x)\n",
 			ret);
@@ -3008,10 +3021,12 @@
 		return 0;
 
 	if ((features & NETIF_F_LRO) && (lio->dev_capability & NETIF_F_LRO))
-		liquidio_set_feature(netdev, OCTNET_CMD_LRO_ENABLE);
+		liquidio_set_feature(netdev, OCTNET_CMD_LRO_ENABLE,
+				     OCTNIC_LROIPV4 | OCTNIC_LROIPV6);
 	else if (!(features & NETIF_F_LRO) &&
 		 (lio->dev_capability & NETIF_F_LRO))
-		liquidio_set_feature(netdev, OCTNET_CMD_LRO_DISABLE);
+		liquidio_set_feature(netdev, OCTNET_CMD_LRO_DISABLE,
+				     OCTNIC_LROIPV4 | OCTNIC_LROIPV6);
 
 	return 0;
 }
@@ -3082,24 +3097,27 @@
 {
 	struct octeon_device *oct = (struct octeon_device *)buf;
 	struct octeon_recv_pkt *recv_pkt = recv_info->recv_pkt;
-	int ifidx = 0;
+	int gmxport = 0;
 	union oct_link_status *ls;
 	int i;
 
-	if ((recv_pkt->buffer_size[0] != sizeof(*ls)) ||
-	    (recv_pkt->rh.r_nic_info.ifidx > oct->ifcount)) {
+	if (recv_pkt->buffer_size[0] != sizeof(*ls)) {
 		dev_err(&oct->pci_dev->dev, "Malformed NIC_INFO, len=%d, ifidx=%d\n",
 			recv_pkt->buffer_size[0],
-			recv_pkt->rh.r_nic_info.ifidx);
+			recv_pkt->rh.r_nic_info.gmxport);
 		goto nic_info_err;
 	}
 
-	ifidx = recv_pkt->rh.r_nic_info.ifidx;
+	gmxport = recv_pkt->rh.r_nic_info.gmxport;
 	ls = (union oct_link_status *)get_rbd(recv_pkt->buffer_ptr[0]);
 
 	octeon_swap_8B_data((u64 *)ls, (sizeof(union oct_link_status)) >> 3);
-
-	update_link_status(oct->props[ifidx].netdev, ls);
+	for (i = 0; i < oct->ifcount; i++) {
+		if (oct->props[i].gmxport == gmxport) {
+			update_link_status(oct->props[i].netdev, ls);
+			break;
+		}
+	}
 
 nic_info_err:
 	for (i = 0; i < recv_pkt->buffer_count; i++)
@@ -3125,13 +3143,13 @@
 	struct liquidio_if_cfg_context *ctx;
 	struct liquidio_if_cfg_resp *resp;
 	struct octdev_props *props;
-	int retval, num_iqueues, num_oqueues, q_no;
-	u64 q_mask;
+	int retval, num_iqueues, num_oqueues;
 	int num_cpus = num_online_cpus();
 	union oct_nic_if_cfg if_cfg;
 	unsigned int base_queue;
 	unsigned int gmx_port_id;
 	u32 resp_size, ctx_size;
+	u32 ifidx_or_pfnum;
 
 	/* This is to handle link status changes */
 	octeon_register_dispatch_fn(octeon_dev, OPCODE_NIC,
@@ -3167,13 +3185,14 @@
 			CFG_GET_BASE_QUE_NIC_IF(octeon_get_conf(octeon_dev), i);
 		gmx_port_id =
 			CFG_GET_GMXID_NIC_IF(octeon_get_conf(octeon_dev), i);
+		ifidx_or_pfnum = i;
 		if (num_iqueues > num_cpus)
 			num_iqueues = num_cpus;
 		if (num_oqueues > num_cpus)
 			num_oqueues = num_cpus;
 		dev_dbg(&octeon_dev->pci_dev->dev,
 			"requesting config for interface %d, iqs %d, oqs %d\n",
-			i, num_iqueues, num_oqueues);
+			ifidx_or_pfnum, num_iqueues, num_oqueues);
 		ACCESS_ONCE(ctx->cond) = 0;
 		ctx->octeon_id = lio_get_device_id(octeon_dev);
 		init_waitqueue_head(&ctx->wc);
@@ -3183,8 +3202,11 @@
 		if_cfg.s.num_oqueues = num_oqueues;
 		if_cfg.s.base_queue = base_queue;
 		if_cfg.s.gmx_port_id = gmx_port_id;
+
+		sc->iq_no = 0;
+
 		octeon_prepare_soft_command(octeon_dev, sc, OPCODE_NIC,
-					    OPCODE_NIC_IF_CFG, i,
+					    OPCODE_NIC_IF_CFG, 0,
 					    if_cfg.u64, 0);
 
 		sc->callback = if_cfg_callback;
@@ -3192,7 +3214,7 @@
 		sc->wait_time = 1000;
 
 		retval = octeon_send_soft_command(octeon_dev, sc);
-		if (retval) {
+		if (retval == IQ_SEND_FAILED) {
 			dev_err(&octeon_dev->pci_dev->dev,
 				"iq/oq config failed status: %x\n",
 				retval);
@@ -3234,8 +3256,7 @@
 			goto setup_nic_dev_fail;
 		}
 
-		props = &octeon_dev->props[i];
-		props->netdev = netdev;
+		SET_NETDEV_DEV(netdev, &octeon_dev->pci_dev->dev);
 
 		if (num_iqueues > 1)
 			lionetdevops.ndo_select_queue = select_q;
@@ -3249,23 +3270,21 @@
 
 		memset(lio, 0, sizeof(struct lio));
 
-		lio->linfo.ifidx = resp->cfg_info.ifidx;
-		lio->ifidx = resp->cfg_info.ifidx;
+		lio->ifidx = ifidx_or_pfnum;
+
+		props = &octeon_dev->props[i];
+		props->gmxport = resp->cfg_info.linfo.gmxport;
+		props->netdev = netdev;
 
 		lio->linfo.num_rxpciq = num_oqueues;
 		lio->linfo.num_txpciq = num_iqueues;
-		q_mask = resp->cfg_info.oqmask;
-		/* q_mask is 0-based and already verified mask is nonzero */
 		for (j = 0; j < num_oqueues; j++) {
-			q_no = __ffs64(q_mask);
-			q_mask &= (~(1UL << q_no));
-			lio->linfo.rxpciq[j] = q_no;
+			lio->linfo.rxpciq[j].u64 =
+				resp->cfg_info.linfo.rxpciq[j].u64;
 		}
-		q_mask = resp->cfg_info.iqmask;
 		for (j = 0; j < num_iqueues; j++) {
-			q_no = __ffs64(q_mask);
-			q_mask &= (~(1UL << q_no));
-			lio->linfo.txpciq[j] = q_no;
+			lio->linfo.txpciq[j].u64 =
+				resp->cfg_info.linfo.txpciq[j].u64;
 		}
 		lio->linfo.hw_addr = resp->cfg_info.linfo.hw_addr;
 		lio->linfo.gmxport = resp->cfg_info.linfo.gmxport;
@@ -3274,13 +3293,15 @@
 		lio->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE);
 
 		lio->dev_capability = NETIF_F_HIGHDMA
-				      | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM
-				      | NETIF_F_SG | NETIF_F_RXCSUM
-				      | NETIF_F_TSO | NETIF_F_TSO6
-				      | NETIF_F_LRO;
+				| NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM
+				| NETIF_F_SG | NETIF_F_RXCSUM
+				| NETIF_F_GRO
+				| NETIF_F_TSO | NETIF_F_TSO6
+				| NETIF_F_LRO;
 		netif_set_gso_max_size(netdev, OCTNIC_GSO_MAX_SIZE);
 
-		netdev->features = lio->dev_capability;
+		netdev->features = (lio->dev_capability & ~NETIF_F_LRO);
+
 		netdev->vlan_features = lio->dev_capability;
 
 		netdev->hw_features = lio->dev_capability;
@@ -3291,7 +3312,6 @@
 		lio->oct_dev = octeon_dev;
 		lio->octprops = props;
 		lio->netdev = netdev;
-		spin_lock_init(&lio->lock);
 
 		dev_dbg(&octeon_dev->pci_dev->dev,
 			"if%d gmx: %d hw_addr: 0x%llx\n", i,
@@ -3306,23 +3326,22 @@
 
 		ether_addr_copy(netdev->dev_addr, mac);
 
-		if (setup_io_queues(octeon_dev, netdev)) {
+		/* By default all interfaces on a single Octeon uses the same
+		 * tx and rx queues
+		 */
+		lio->txq = lio->linfo.txpciq[0].s.q_no;
+		lio->rxq = lio->linfo.rxpciq[0].s.q_no;
+		if (setup_io_queues(octeon_dev, i)) {
 			dev_err(&octeon_dev->pci_dev->dev, "I/O queues creation failed\n");
 			goto setup_nic_dev_fail;
 		}
 
 		ifstate_set(lio, LIO_IFSTATE_DROQ_OPS);
 
-		/* By default all interfaces on a single Octeon uses the same
-		 * tx and rx queues
-		 */
-		lio->txq = lio->linfo.txpciq[0];
-		lio->rxq = lio->linfo.rxpciq[0];
-
 		lio->tx_qsize = octeon_get_tx_qsize(octeon_dev, lio->txq);
 		lio->rx_qsize = octeon_get_rx_qsize(octeon_dev, lio->rxq);
 
-		if (setup_glist(lio)) {
+		if (setup_glists(octeon_dev, lio, num_iqueues)) {
 			dev_err(&octeon_dev->pci_dev->dev,
 				"Gather list allocation failed\n");
 			goto setup_nic_dev_fail;
@@ -3331,10 +3350,13 @@
 		/* Register ethtool support */
 		liquidio_set_ethtool_ops(netdev);
 
-		liquidio_set_feature(netdev, OCTNET_CMD_LRO_ENABLE);
+		if (netdev->features & NETIF_F_LRO)
+		liquidio_set_feature(netdev, OCTNET_CMD_LRO_ENABLE,
+				     OCTNIC_LROIPV4 | OCTNIC_LROIPV6);
 
 		if ((debug != -1) && (debug & NETIF_MSG_HW))
-			liquidio_set_feature(netdev, OCTNET_CMD_VERBOSE_ENABLE);
+			liquidio_set_feature(netdev, OCTNET_CMD_VERBOSE_ENABLE,
+					     0);
 
 		/* Register the network device with the OS */
 		if (register_netdev(netdev)) {
@@ -3346,13 +3368,7 @@
 			"Setup NIC ifidx:%d mac:%02x%02x%02x%02x%02x%02x\n",
 			i, mac[0], mac[1], mac[2], mac[3], mac[4], mac[5]);
 		netif_carrier_off(netdev);
-
-		if (lio->linfo.link.s.status) {
-			netif_carrier_on(netdev);
-			start_txq(netdev);
-		} else {
-			netif_carrier_off(netdev);
-		}
+		lio->link_changes++;
 
 		ifstate_set(lio, LIO_IFSTATE_REGISTERED);
 
@@ -3386,7 +3402,7 @@
 static int liquidio_init_nic_module(struct octeon_device *oct)
 {
 	struct oct_intrmod_cfg *intrmod_cfg;
-	int retval = 0;
+	int i, retval = 0;
 	int num_nic_ports = CFG_GET_NUM_NIC_PORTS(octeon_get_conf(oct));
 
 	dev_dbg(&oct->pci_dev->dev, "Initializing network interfaces\n");
@@ -3400,6 +3416,9 @@
 	memset(oct->props, 0,
 	       sizeof(struct octdev_props) * num_nic_ports);
 
+	for (i = 0; i < MAX_OCTEON_LINKS; i++)
+		oct->props[i].gmxport = -1;
+
 	retval = setup_nic_devices(oct);
 	if (retval) {
 		dev_err(&oct->pci_dev->dev, "Setup NIC devices failed\n");
diff --git a/drivers/net/ethernet/cavium/liquidio/liquidio_common.h b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h
index 0ac347c..2179691 100644
--- a/drivers/net/ethernet/cavium/liquidio/liquidio_common.h
+++ b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h
@@ -174,9 +174,11 @@
 /*------------------------- End Scatter/Gather ---------------------------*/
 
 #define   OCTNET_FRM_PTP_HEADER_SIZE  8
-#define   OCTNET_FRM_HEADER_SIZE     30 /* PTP timestamp + VLAN + Ethernet */
 
-#define   OCTNET_MIN_FRM_SIZE        (64  + OCTNET_FRM_PTP_HEADER_SIZE)
+#define   OCTNET_FRM_HEADER_SIZE     22 /* VLAN + Ethernet */
+
+#define   OCTNET_MIN_FRM_SIZE        64
+
 #define   OCTNET_MAX_FRM_SIZE        (16000 + OCTNET_FRM_HEADER_SIZE)
 
 #define   OCTNET_DEFAULT_FRM_SIZE    (1500 + OCTNET_FRM_HEADER_SIZE)
@@ -258,19 +260,19 @@
 
 		u64 more:6; /* How many udd words follow the command */
 
-		u64 param1:29;
+		u64 reserved:29;
 
-		u64 param2:16;
+		u64 param1:16;
 
-		u64 param3:8;
+		u64 param2:8;
 
 #else
 
-		u64 param3:8;
+		u64 param2:8;
 
-		u64 param2:16;
+		u64 param1:16;
 
-		u64 param1:29;
+		u64 reserved:29;
 
 		u64 more:6;
 
@@ -283,8 +285,140 @@
 
 #define   OCTNET_CMD_SIZE     (sizeof(union octnet_cmd))
 
+/* Instruction Header (DPI - CN23xx) - for OCTEON-III models */
+struct  octeon_instr_ih3 {
+#ifdef __BIG_ENDIAN_BITFIELD
+
+	/** Reserved3 */
+	u64     reserved3:1;
+
+	/** Gather indicator 1=gather*/
+	u64     gather:1;
+
+	/** Data length OR no. of entries in gather list */
+	u64     dlengsz:14;
+
+	/** Front Data size */
+	u64     fsz:6;
+
+	/** Reserved2 */
+	u64     reserved2:4;
+
+	/** PKI port kind - PKIND */
+	u64     pkind:6;
+
+	/** Reserved1 */
+	u64     reserved1:32;
+
+#else
+	/** Reserved1 */
+	u64     reserved1:32;
+
+	/** PKI port kind - PKIND */
+	u64     pkind:6;
+
+	/** Reserved2 */
+	u64     reserved2:4;
+
+	/** Front Data size */
+	u64     fsz:6;
+
+	/** Data length OR no. of entries in gather list */
+	u64     dlengsz:14;
+
+	/** Gather indicator 1=gather*/
+	u64     gather:1;
+
+	/** Reserved3 */
+	u64     reserved3:1;
+
+#endif
+};
+
+/* Optional PKI Instruction Header(PKI IH) - for OCTEON CN23XX models */
+/** BIG ENDIAN format.   */
+struct  octeon_instr_pki_ih3 {
+#ifdef __BIG_ENDIAN_BITFIELD
+
+	/** Wider bit */
+	u64     w:1;
+
+	/** Raw mode indicator 1 = RAW */
+	u64     raw:1;
+
+	/** Use Tag */
+	u64     utag:1;
+
+	/** Use QPG */
+	u64     uqpg:1;
+
+	/** Reserved2 */
+	u64     reserved2:1;
+
+	/** Parse Mode */
+	u64     pm:3;
+
+	/** Skip Length */
+	u64     sl:8;
+
+	/** Use Tag Type */
+	u64     utt:1;
+
+	/** Tag type */
+	u64     tagtype:2;
+
+	/** Reserved1 */
+	u64     reserved1:2;
+
+	/** QPG Value */
+	u64     qpg:11;
+
+	/** Tag Value */
+	u64     tag:32;
+
+#else
+
+	/** Tag Value */
+	u64     tag:32;
+
+	/** QPG Value */
+	u64     qpg:11;
+
+	/** Reserved1 */
+	u64     reserved1:2;
+
+	/** Tag type */
+	u64     tagtype:2;
+
+	/** Use Tag Type */
+	u64     utt:1;
+
+	/** Skip Length */
+	u64     sl:8;
+
+	/** Parse Mode */
+	u64     pm:3;
+
+	/** Reserved2 */
+	u64     reserved2:1;
+
+	/** Use QPG */
+	u64     uqpg:1;
+
+	/** Use Tag */
+	u64     utag:1;
+
+	/** Raw mode indicator 1 = RAW */
+	u64     raw:1;
+
+	/** Wider bit */
+	u64     w:1;
+#endif
+
+};
+
 /** Instruction Header */
-struct octeon_instr_ih {
+struct octeon_instr_ih2 {
 #ifdef __BIG_ENDIAN_BITFIELD
 	/** Raw mode indicator 1 = RAW */
 	u64 raw:1;
@@ -412,10 +546,9 @@
 		u64 opcode:4;
 		u64 subcode:8;
 		u64 len:3;       /** additional 64-bit words */
-		u64 rid:13;
-		u64 reserved:4;
+		u64 reserved:8;
 		u64 extra:25;
-		u64 ifidx:7;
+		u64 gmxport:16;
 	} r_nic_info;
 #else
 	u64 u64;
@@ -448,10 +581,9 @@
 		u64 opcode:4;
 	} r_core_drv_init;
 	struct {
-		u64 ifidx:7;
+		u64 gmxport:16;
 		u64 extra:25;
-		u64 reserved:4;
-		u64 rid:13;
+		u64 reserved:8;
 		u64 len:3;       /** additional 64-bit words */
 		u64 subcode:8;
 		u64 opcode:4;
@@ -461,30 +593,25 @@
 
 #define  OCT_RH_SIZE   (sizeof(union  octeon_rh))
 
-#define OCT_PKT_PARAM_IPV4OPTS   1
-#define OCT_PKT_PARAM_IPV6EXTHDR 2
-
 union octnic_packet_params {
 	u32 u32;
 	struct {
 #ifdef __BIG_ENDIAN_BITFIELD
-		u32 reserved:6;
+		u32 reserved:24;
+		u32 ip_csum:1;		/* Perform IP header checksum(s) */
+		/* Perform Outer transport header checksum */
+		u32 transport_csum:1;
+		/* Find tunnel, and perform transport csum. */
 		u32 tnl_csum:1;
-		u32 ip_csum:1;
-		u32 ipv4opts_ipv6exthdr:2;
-		u32 ipsec_ops:4;
-		u32 tsflag:1;
-		u32 csoffset:9;
-		u32 ifidx:8;
+		u32 tsflag:1;		/* Timestamp this packet */
+		u32 ipsec_ops:4;	/* IPsec operation */
 #else
-		u32 ifidx:8;
-		u32 csoffset:9;
-		u32 tsflag:1;
 		u32 ipsec_ops:4;
-		u32 ipv4opts_ipv6exthdr:2;
-		u32 ip_csum:1;
+		u32 tsflag:1;
 		u32 tnl_csum:1;
-		u32 reserved:6;
+		u32 transport_csum:1;
+		u32 ip_csum:1;
+		u32 reserved:24;
 #endif
 	} s;
 };
@@ -496,53 +623,90 @@
 	struct {
 #ifdef __BIG_ENDIAN_BITFIELD
 		u64 duplex:8;
-		u64 status:8;
 		u64 mtu:16;
 		u64 speed:16;
+		u64 link_up:1;
 		u64 autoneg:1;
 		u64 interface:4;
 		u64 pause:1;
-		u64 reserved:10;
+		u64 reserved:17;
 #else
-		u64 reserved:10;
+		u64 reserved:17;
 		u64 pause:1;
 		u64 interface:4;
 		u64 autoneg:1;
+		u64 link_up:1;
 		u64 speed:16;
 		u64 mtu:16;
-		u64 status:8;
 		u64 duplex:8;
 #endif
 	} s;
 };
 
+/** The txpciq info passed to host from the firmware */
+
+union oct_txpciq {
+	u64 u64;
+
+	struct {
+#ifdef __BIG_ENDIAN_BITFIELD
+		u64 q_no:8;
+		u64 port:8;
+		u64 pkind:6;
+		u64 use_qpg:1;
+		u64 qpg:11;
+		u64 reserved:30;
+#else
+		u64 reserved:30;
+		u64 qpg:11;
+		u64 use_qpg:1;
+		u64 pkind:6;
+		u64 port:8;
+		u64 q_no:8;
+#endif
+	} s;
+};
+
+/** The rxpciq info passed to host from the firmware */
+
+union oct_rxpciq {
+	u64 u64;
+
+	struct {
+#ifdef __BIG_ENDIAN_BITFIELD
+		u64 q_no:8;
+		u64 reserved:56;
+#else
+		u64 reserved:56;
+		u64 q_no:8;
+#endif
+	} s;
+};
+
 /** Information for a OCTEON ethernet interface shared between core & host. */
 struct oct_link_info {
 	union oct_link_status link;
 	u64 hw_addr;
 
 #ifdef __BIG_ENDIAN_BITFIELD
-	u16 gmxport;
-	u8 rsvd[3];
-	u8 num_txpciq;
-	u8 num_rxpciq;
-	u8 ifidx;
+	u64 gmxport:16;
+	u64 rsvd:32;
+	u64 num_txpciq:8;
+	u64 num_rxpciq:8;
 #else
-	u8 ifidx;
-	u8 num_rxpciq;
-	u8 num_txpciq;
-	u8 rsvd[3];
-	u16 gmxport;
+	u64 num_rxpciq:8;
+	u64 num_txpciq:8;
+	u64 rsvd:32;
+	u64 gmxport:16;
 #endif
 
-	u8 txpciq[MAX_IOQS_PER_NICIF];
-	u8 rxpciq[MAX_IOQS_PER_NICIF];
+	union oct_txpciq txpciq[MAX_IOQS_PER_NICIF];
+	union oct_rxpciq rxpciq[MAX_IOQS_PER_NICIF];
 };
 
 #define OCT_LINK_INFO_SIZE   (sizeof(struct oct_link_info))
 
 struct liquidio_if_cfg_info {
-	u64 ifidx;
 	u64 iqmask; /** mask for IQs enabled for  the port */
 	u64 oqmask; /** mask for OQs enabled for the port */
 	struct oct_link_info linfo; /** initial link information */
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.c b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
index 8e23e3f..7b44b5c 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
@@ -19,7 +19,6 @@
 * This file may also be available under a different license from Cavium.
 * Contact Cavium, Inc. for more information
 **********************************************************************/
-#include <linux/version.h>
 #include <linux/types.h>
 #include <linux/list.h>
 #include <linux/interrupt.h>
@@ -741,49 +740,59 @@
 	return oct;
 }
 
+/* this function is only for setting up the first queue */
 int octeon_setup_instr_queues(struct octeon_device *oct)
 {
-	u32 i, num_iqs = 0;
+	u32 num_iqs = 0;
 	u32 num_descs = 0;
+	u32 iq_no = 0;
+	union oct_txpciq txpciq;
+	int numa_node = cpu_to_node(iq_no % num_online_cpus());
 
+	num_iqs = 1;
 	/* this causes queue 0 to be default queue */
-	if (OCTEON_CN6XXX(oct)) {
-		num_iqs = 1;
+	if (OCTEON_CN6XXX(oct))
 		num_descs =
 			CFG_GET_NUM_DEF_TX_DESCS(CHIP_FIELD(oct, cn6xxx, conf));
-	}
 
 	oct->num_iqs = 0;
 
-	for (i = 0; i < num_iqs; i++) {
-		oct->instr_queue[i] =
+	oct->instr_queue[0] = vmalloc_node(sizeof(*oct->instr_queue[0]),
+				numa_node);
+	if (!oct->instr_queue[0])
+		oct->instr_queue[0] =
 			vmalloc(sizeof(struct octeon_instr_queue));
-		if (!oct->instr_queue[i])
-			return 1;
-
-		memset(oct->instr_queue[i], 0,
-		       sizeof(struct octeon_instr_queue));
-
-		oct->instr_queue[i]->app_ctx = (void *)(size_t)i;
-		if (octeon_init_instr_queue(oct, i, num_descs))
-			return 1;
-
-		oct->num_iqs++;
+	if (!oct->instr_queue[0])
+		return 1;
+	memset(oct->instr_queue[0], 0, sizeof(struct octeon_instr_queue));
+	oct->instr_queue[0]->q_index = 0;
+	oct->instr_queue[0]->app_ctx = (void *)(size_t)0;
+	oct->instr_queue[0]->ifidx = 0;
+	txpciq.u64 = 0;
+	txpciq.s.q_no = iq_no;
+	txpciq.s.use_qpg = 0;
+	txpciq.s.qpg = 0;
+	if (octeon_init_instr_queue(oct, txpciq, num_descs)) {
+		/* prevent memory leak */
+		vfree(oct->instr_queue[0]);
+		return 1;
 	}
 
+	oct->num_iqs++;
 	return 0;
 }
 
 int octeon_setup_output_queues(struct octeon_device *oct)
 {
-	u32 i, num_oqs = 0;
+	u32 num_oqs = 0;
 	u32 num_descs = 0;
 	u32 desc_size = 0;
+	u32 oq_no = 0;
+	int numa_node = cpu_to_node(oq_no % num_online_cpus());
 
+	num_oqs = 1;
 	/* this causes queue 0 to be default queue */
 	if (OCTEON_CN6XXX(oct)) {
-		/* CFG_GET_OQ_MAX_BASE_Q(CHIP_FIELD(oct, cn6xxx, conf)); */
-		num_oqs = 1;
 		num_descs =
 			CFG_GET_NUM_DEF_RX_DESCS(CHIP_FIELD(oct, cn6xxx, conf));
 		desc_size =
@@ -791,19 +800,15 @@
 	}
 
 	oct->num_oqs = 0;
+	oct->droq[0] = vmalloc_node(sizeof(*oct->droq[0]), numa_node);
+	if (!oct->droq[0])
+		oct->droq[0] = vmalloc(sizeof(*oct->droq[0]));
+	if (!oct->droq[0])
+		return 1;
 
-	for (i = 0; i < num_oqs; i++) {
-		oct->droq[i] = vmalloc(sizeof(*oct->droq[i]));
-		if (!oct->droq[i])
-			return 1;
-
-		memset(oct->droq[i], 0, sizeof(struct octeon_droq));
-
-		if (octeon_init_droq(oct, i, num_descs, desc_size, NULL))
-			return 1;
-
-		oct->num_oqs++;
-	}
+	if (octeon_init_droq(oct, oq_no, num_descs, desc_size, NULL))
+		return 1;
+	oct->num_oqs++;
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.h b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
index 36e1f85..0950b94 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
@@ -267,6 +267,7 @@
 	/* Each interface in the Octeon device has a network
 	 * device pointer (used for OS specific calls).
 	 */
+	int    gmxport;
 	struct net_device *netdev;
 };
 
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
index 174072b..59a5293 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
@@ -151,22 +151,26 @@
 				 struct octeon_droq *droq)
 {
 	u32 i;
+	struct octeon_skb_page_info *pg_info;
 
 	for (i = 0; i < droq->max_count; i++) {
-		if (droq->recv_buf_list[i].buffer) {
-			if (droq->desc_ring) {
-				lio_unmap_ring_info(oct->pci_dev,
-						    (u64)droq->
-						    desc_ring[i].info_ptr,
-						    OCT_DROQ_INFO_SIZE);
-				lio_unmap_ring(oct->pci_dev,
-					       (u64)droq->desc_ring[i].
-					       buffer_ptr,
-					       droq->buffer_size);
-			}
-			recv_buffer_free(droq->recv_buf_list[i].buffer);
-			droq->recv_buf_list[i].buffer = NULL;
-		}
+		pg_info = &droq->recv_buf_list[i].pg_info;
+
+		if (pg_info->dma)
+			lio_unmap_ring(oct->pci_dev,
+				       (u64)pg_info->dma);
+		pg_info->dma = 0;
+
+		if (pg_info->page)
+			recv_buffer_destroy(droq->recv_buf_list[i].buffer,
+					    pg_info);
+
+		if (droq->desc_ring && droq->desc_ring[i].info_ptr)
+			lio_unmap_ring_info(oct->pci_dev,
+					    (u64)droq->
+					    desc_ring[i].info_ptr,
+					    OCT_DROQ_INFO_SIZE);
+		droq->recv_buf_list[i].buffer = NULL;
 	}
 
 	octeon_droq_reset_indices(droq);
@@ -181,11 +185,12 @@
 	struct octeon_droq_desc *desc_ring = droq->desc_ring;
 
 	for (i = 0; i < droq->max_count; i++) {
-		buf = recv_buffer_alloc(oct, droq->q_no, droq->buffer_size);
+		buf = recv_buffer_alloc(oct, &droq->recv_buf_list[i].pg_info);
 
 		if (!buf) {
 			dev_err(&oct->pci_dev->dev, "%s buffer alloc failed\n",
 				__func__);
+			droq->stats.rx_alloc_failure++;
 			return -ENOMEM;
 		}
 
@@ -197,9 +202,7 @@
 		/* map ring buffers into memory */
 		desc_ring[i].info_ptr = lio_map_ring_info(droq, i);
 		desc_ring[i].buffer_ptr =
-			lio_map_ring(oct->pci_dev,
-				     droq->recv_buf_list[i].buffer,
-				     droq->buffer_size);
+			lio_map_ring(droq->recv_buf_list[i].buffer);
 	}
 
 	octeon_droq_reset_indices(droq);
@@ -242,6 +245,8 @@
 	struct octeon_droq *droq;
 	u32 desc_ring_size = 0, c_num_descs = 0, c_buf_size = 0;
 	u32 c_pkts_per_intr = 0, c_refill_threshold = 0;
+	int orig_node = dev_to_node(&oct->pci_dev->dev);
+	int numa_node = cpu_to_node(q_no % num_online_cpus());
 
 	dev_dbg(&oct->pci_dev->dev, "%s[%d]\n", __func__, q_no);
 
@@ -261,15 +266,23 @@
 		struct octeon_config *conf6x = CHIP_FIELD(oct, cn6xxx, conf);
 
 		c_pkts_per_intr = (u32)CFG_GET_OQ_PKTS_PER_INTR(conf6x);
-		c_refill_threshold = (u32)CFG_GET_OQ_REFILL_THRESHOLD(conf6x);
+		c_refill_threshold =
+			(u32)CFG_GET_OQ_REFILL_THRESHOLD(conf6x);
+	} else {
+		return 1;
 	}
 
 	droq->max_count = c_num_descs;
 	droq->buffer_size = c_buf_size;
 
 	desc_ring_size = droq->max_count * OCT_DROQ_DESC_SIZE;
+	set_dev_node(&oct->pci_dev->dev, numa_node);
 	droq->desc_ring = lio_dma_alloc(oct, desc_ring_size,
 					(dma_addr_t *)&droq->desc_ring_dma);
+	set_dev_node(&oct->pci_dev->dev, orig_node);
+	if (!droq->desc_ring)
+		droq->desc_ring = lio_dma_alloc(oct, desc_ring_size,
+					(dma_addr_t *)&droq->desc_ring_dma);
 
 	if (!droq->desc_ring) {
 		dev_err(&oct->pci_dev->dev,
@@ -283,12 +296,11 @@
 		droq->max_count);
 
 	droq->info_list =
-		cnnic_alloc_aligned_dma(oct->pci_dev,
-					(droq->max_count * OCT_DROQ_INFO_SIZE),
-					&droq->info_alloc_size,
-					&droq->info_base_addr,
-					&droq->info_list_dma);
-
+		cnnic_numa_alloc_aligned_dma((droq->max_count *
+					      OCT_DROQ_INFO_SIZE),
+					     &droq->info_alloc_size,
+					     &droq->info_base_addr,
+					     numa_node);
 	if (!droq->info_list) {
 		dev_err(&oct->pci_dev->dev, "Cannot allocate memory for info list.\n");
 		lio_dma_free(oct, (droq->max_count * OCT_DROQ_DESC_SIZE),
@@ -297,7 +309,12 @@
 	}
 
 	droq->recv_buf_list = (struct octeon_recv_buffer *)
-			      vmalloc(droq->max_count *
+			      vmalloc_node(droq->max_count *
+						OCT_DROQ_RECVBUF_SIZE,
+						numa_node);
+	if (!droq->recv_buf_list)
+		droq->recv_buf_list = (struct octeon_recv_buffer *)
+				      vmalloc(droq->max_count *
 						OCT_DROQ_RECVBUF_SIZE);
 	if (!droq->recv_buf_list) {
 		dev_err(&oct->pci_dev->dev, "Output queue recv buf list alloc failed\n");
@@ -358,6 +375,7 @@
 	struct octeon_recv_pkt *recv_pkt;
 	struct octeon_recv_info *recv_info;
 	u32 i, bytes_left;
+	struct octeon_skb_page_info *pg_info;
 
 	info = &droq->info_list[idx];
 
@@ -375,9 +393,14 @@
 	bytes_left = (u32)info->length;
 
 	while (buf_cnt) {
-		lio_unmap_ring(octeon_dev->pci_dev,
-			       (u64)droq->desc_ring[idx].buffer_ptr,
-			       droq->buffer_size);
+		{
+			pg_info = &droq->recv_buf_list[idx].pg_info;
+
+			lio_unmap_ring(octeon_dev->pci_dev,
+				       (u64)pg_info->dma);
+			pg_info->page = NULL;
+			pg_info->dma = 0;
+		}
 
 		recv_pkt->buffer_size[i] =
 			(bytes_left >=
@@ -449,6 +472,7 @@
 	void *buf = NULL;
 	u8 *data;
 	u32 desc_refilled = 0;
+	struct octeon_skb_page_info *pg_info;
 
 	desc_ring = droq->desc_ring;
 
@@ -458,13 +482,22 @@
 		 * the buffer, else allocate.
 		 */
 		if (!droq->recv_buf_list[droq->refill_idx].buffer) {
-			buf = recv_buffer_alloc(octeon_dev, droq->q_no,
-						droq->buffer_size);
+			pg_info =
+				&droq->recv_buf_list[droq->refill_idx].pg_info;
+			/* Either recycle the existing pages or go for
+			 * new page alloc
+			 */
+			if (pg_info->page)
+				buf = recv_buffer_reuse(octeon_dev, pg_info);
+			else
+				buf = recv_buffer_alloc(octeon_dev, pg_info);
 			/* If a buffer could not be allocated, no point in
 			 * continuing
 			 */
-			if (!buf)
+			if (!buf) {
+				droq->stats.rx_alloc_failure++;
 				break;
+			}
 			droq->recv_buf_list[droq->refill_idx].buffer =
 				buf;
 			data = get_rbd(buf);
@@ -476,11 +509,8 @@
 		droq->recv_buf_list[droq->refill_idx].data = data;
 
 		desc_ring[droq->refill_idx].buffer_ptr =
-			lio_map_ring(octeon_dev->pci_dev,
-				     droq->recv_buf_list[droq->
-				     refill_idx].buffer,
-				     droq->buffer_size);
-
+			lio_map_ring(droq->recv_buf_list[droq->
+				     refill_idx].buffer);
 		/* Reset any previous values in the length field. */
 		droq->info_list[droq->refill_idx].length = 0;
 
@@ -586,6 +616,8 @@
 	for (pkt = 0; pkt < pkt_count; pkt++) {
 		u32 pkt_len = 0;
 		struct sk_buff *nicbuf = NULL;
+		struct octeon_skb_page_info *pg_info;
+		void *buf;
 
 		info = &droq->info_list[droq->read_idx];
 		octeon_swap_8B_data((u64 *)info, 2);
@@ -605,7 +637,6 @@
 		rh = &info->rh;
 
 		total_len += (u32)info->length;
-
 		if (OPCODE_SLOW_PATH(rh)) {
 			u32 buf_cnt;
 
@@ -614,50 +645,44 @@
 			droq->refill_count += buf_cnt;
 		} else {
 			if (info->length <= droq->buffer_size) {
-				lio_unmap_ring(oct->pci_dev,
-					       (u64)droq->desc_ring[
-					       droq->read_idx].buffer_ptr,
-					       droq->buffer_size);
 				pkt_len = (u32)info->length;
 				nicbuf = droq->recv_buf_list[
 					droq->read_idx].buffer;
+				pg_info = &droq->recv_buf_list[
+					droq->read_idx].pg_info;
+				if (recv_buffer_recycle(oct, pg_info))
+					pg_info->page = NULL;
 				droq->recv_buf_list[droq->read_idx].buffer =
 					NULL;
 				INCR_INDEX_BY1(droq->read_idx, droq->max_count);
-				skb_put(nicbuf, pkt_len);
 				droq->refill_count++;
 			} else {
-				nicbuf = octeon_fast_packet_alloc(oct, droq,
-								  droq->q_no,
-								  (u32)
+				nicbuf = octeon_fast_packet_alloc((u32)
 								  info->length);
 				pkt_len = 0;
 				/* nicbuf allocation can fail. We'll handle it
 				 * inside the loop.
 				 */
 				while (pkt_len < info->length) {
-					int cpy_len;
+					int cpy_len, idx = droq->read_idx;
 
-					cpy_len = ((pkt_len +
-						droq->buffer_size) >
-						info->length) ?
+					cpy_len = ((pkt_len + droq->buffer_size)
+						   > info->length) ?
 						((u32)info->length - pkt_len) :
 						droq->buffer_size;
 
 					if (nicbuf) {
-						lio_unmap_ring(oct->pci_dev,
-							       (u64)
-							       droq->desc_ring
-							       [droq->read_idx].
-							       buffer_ptr,
-							       droq->
-							       buffer_size);
 						octeon_fast_packet_next(droq,
 									nicbuf,
 									cpy_len,
-									droq->
-									read_idx
-									);
+									idx);
+						buf = droq->recv_buf_list[idx].
+							buffer;
+						recv_buffer_fast_free(buf);
+						droq->recv_buf_list[idx].buffer
+							= NULL;
+					} else {
+						droq->stats.rx_alloc_failure++;
 					}
 
 					pkt_len += cpy_len;
@@ -668,12 +693,14 @@
 			}
 
 			if (nicbuf) {
-				if (droq->ops.fptr)
+				if (droq->ops.fptr) {
 					droq->ops.fptr(oct->octeon_id,
-					nicbuf, pkt_len,
-					rh, &droq->napi);
-				else
+						       nicbuf, pkt_len,
+						       rh, &droq->napi,
+						       droq->ops.farg);
+				} else {
 					recv_buffer_free(nicbuf);
+				}
 			}
 		}
 
@@ -681,16 +708,16 @@
 			int desc_refilled = octeon_droq_refill(oct, droq);
 
 			/* Flush the droq descriptor data to memory to be sure
-			* that when we update the credits the data in memory
-			* is accurate.
-			*/
+			 * that when we update the credits the data in memory
+			 * is accurate.
+			 */
 			wmb();
 			writel((desc_refilled), droq->pkts_credit_reg);
 			/* make sure mmio write completes */
 			mmiowb();
 		}
 
-	}                       /* for ( each packet )... */
+	}                       /* for (each packet)... */
 
 	/* Increment refill_count by the number of buffers processed. */
 	droq->stats.pkts_received += pkt;
@@ -937,6 +964,7 @@
 	spin_lock_irqsave(&droq->lock, flags);
 
 	droq->ops.fptr = NULL;
+	droq->ops.farg = NULL;
 	droq->ops.drop_on_max = 0;
 
 	spin_unlock_irqrestore(&droq->lock, flags);
@@ -949,6 +977,7 @@
 		       u32 desc_size, void *app_ctx)
 {
 	struct octeon_droq *droq;
+	int numa_node = cpu_to_node(q_no % num_online_cpus());
 
 	if (oct->droq[q_no]) {
 		dev_dbg(&oct->pci_dev->dev, "Droq already in use. Cannot create droq %d again\n",
@@ -957,7 +986,9 @@
 	}
 
 	/* Allocate the DS for the new droq. */
-	droq = vmalloc(sizeof(*droq));
+	droq = vmalloc_node(sizeof(*droq), numa_node);
+	if (!droq)
+		droq = vmalloc(sizeof(*droq));
 	if (!droq)
 		goto create_droq_fail;
 	memset(droq, 0, sizeof(struct octeon_droq));
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.h b/drivers/net/ethernet/cavium/liquidio/octeon_droq.h
index 7940cce..1ca9c4f 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.h
@@ -65,6 +65,17 @@
 
 #define OCT_DROQ_INFO_SIZE   (sizeof(struct octeon_droq_info))
 
+struct octeon_skb_page_info {
+	/* DMA address for the page */
+	dma_addr_t dma;
+
+	/* Page for the rx dma  **/
+	struct page *page;
+
+	/** which offset into page */
+	unsigned int page_offset;
+};
+
 /** Pointer to data buffer.
  *  Driver keeps a pointer to the data buffer that it made available to
  *  the Octeon device. Since the descriptor ring keeps physical (bus)
@@ -77,6 +88,9 @@
 
 	/** Data in the packet buffer.  */
 	u8 *data;
+
+	/** pg_info **/
+	struct octeon_skb_page_info pg_info;
 };
 
 #define OCT_DROQ_RECVBUF_SIZE    (sizeof(struct octeon_recv_buffer))
@@ -106,6 +120,10 @@
 
 	/** Num of Packets dropped due to receive path failures. */
 	u64 rx_dropped;
+
+	/** Num of failures of recv_buffer_alloc() */
+	u64 rx_alloc_failure;
+
 };
 
 #define POLL_EVENT_INTR_ARRIVED  1
@@ -213,7 +231,8 @@
 	 *  data in the buffer. The receive header gives the port
 	 *  number to the caller.  Function pointer is set by caller.
 	 */
-	void (*fptr)(u32, void *, u32, union octeon_rh *, void *);
+	void (*fptr)(u32, void *, u32, union octeon_rh *, void *, void *);
+	void *farg;
 
 	/* This function will be called by the driver for all NAPI related
 	 * events. The first param is the octeon id. The second param is the
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
index 592fe49..513f8a0 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
@@ -75,14 +75,16 @@
  *  a Octeon device has one such structure to represent it.
 */
 struct octeon_instr_queue {
+	struct octeon_device *oct_dev;
+
 	/** A spinlock to protect access to the input ring.  */
 	spinlock_t lock;
 
 	/** Flag that indicates if the queue uses 64 byte commands. */
 	u32 iqcmd_64B:1;
 
-	/** Queue Number. */
-	u32 iq_no:5;
+	/** Queue info. */
+	union oct_txpciq txpciq;
 
 	u32 rsvd:17;
 
@@ -147,6 +149,13 @@
 
 	/** Application context */
 	void *app_ctx;
+
+	/* network stack queue index */
+	int q_index;
+
+	/*os ifidx associated with this queue */
+	int ifidx;
+
 };
 
 /*----------------------  INSTRUCTION FORMAT ----------------------------*/
@@ -176,12 +185,12 @@
 /** 64-byte instruction format.
  *  Format of instruction for a 64-byte mode input queue.
  */
-struct octeon_instr_64B {
+struct octeon_instr2_64B {
 	/** Pointer where the input data is available. */
 	u64 dptr;
 
 	/** Instruction Header. */
-	u64 ih;
+	u64 ih2;
 
 	/** Input Request Header. */
 	u64 irh;
@@ -198,10 +207,40 @@
 	u64 rptr;
 
 	u64 reserved;
+};
+
+struct octeon_instr3_64B {
+	/** Pointer where the input data is available. */
+	u64 dptr;
+
+	/** Instruction Header. */
+	u64 ih3;
+
+	/** Instruction Header. */
+	u64 pki_ih3;
+
+	/** Input Request Header. */
+	u64 irh;
+
+	/** opcode/subcode specific parameters */
+	u64 ossp[2];
+
+	/** Return Data Parameters */
+	u64 rdp;
+
+	/** Pointer where the response for a RAW mode packet will be written
+	 * by Octeon.
+	 */
+	u64 rptr;
 
 };
 
-#define OCT_64B_INSTR_SIZE     (sizeof(struct octeon_instr_64B))
+union octeon_instr_64B {
+	struct octeon_instr2_64B cmd2;
+	struct octeon_instr3_64B cmd3;
+};
+
+#define OCT_64B_INSTR_SIZE     (sizeof(union octeon_instr_64B))
 
 /** The size of each buffer in soft command buffer pool
  */
@@ -214,7 +253,8 @@
 	u32 size;
 
 	/** Command and return status */
-	struct octeon_instr_64B cmd;
+	union octeon_instr_64B cmd;
+
 #define COMPLETION_WORD_INIT    0xffffffffffffffffULL
 	u64 *status_word;
 
@@ -268,14 +308,15 @@
 /**
  *  octeon_init_instr_queue()
  *  @param octeon_dev      - pointer to the octeon device structure.
- *  @param iq_no           - queue to be initialized (0 <= q_no <= 3).
+ *  @param txpciq          - queue to be initialized (0 <= q_no <= 3).
  *
  *  Called at driver init time for each input queue. iq_conf has the
  *  configuration parameters for the queue.
  *
  *  @return  Success: 0   Failure: 1
  */
-int octeon_init_instr_queue(struct octeon_device *octeon_dev, u32 iq_no,
+int octeon_init_instr_queue(struct octeon_device *octeon_dev,
+			    union oct_txpciq txpciq,
 			    u32 num_descs);
 
 /**
@@ -313,7 +354,8 @@
 int octeon_send_soft_command(struct octeon_device *oct,
 			     struct octeon_soft_command *sc);
 
-int octeon_setup_iq(struct octeon_device *oct, u32 iq_no,
-		    u32 num_descs, void *app_ctx);
+int octeon_setup_iq(struct octeon_device *oct, int ifidx,
+		    int q_index, union oct_txpciq iq_no, u32 num_descs,
+		    void *app_ctx);
 
 #endif				/* __OCTEON_IQ_H__ */
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_main.h b/drivers/net/ethernet/cavium/liquidio/octeon_main.h
index cbd0819..0ff3efc 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_main.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_main.h
@@ -126,22 +126,27 @@
 }
 
 static inline void *
-cnnic_alloc_aligned_dma(struct pci_dev *pci_dev,
-			u32 size,
-			u32 *alloc_size,
-			size_t *orig_ptr,
-			size_t *dma_addr __attribute__((unused)))
+cnnic_numa_alloc_aligned_dma(u32 size,
+			     u32 *alloc_size,
+			     size_t *orig_ptr,
+			     int numa_node)
 {
 	int retries = 0;
 	void *ptr = NULL;
 
 #define OCTEON_MAX_ALLOC_RETRIES     1
 	do {
-		ptr =
-		    (void *)__get_free_pages(GFP_KERNEL,
-					     get_order(size));
+		struct page *page = NULL;
+
+		page = alloc_pages_node(numa_node,
+					GFP_KERNEL,
+					get_order(size));
+		if (!page)
+			page = alloc_pages(GFP_KERNEL,
+					   get_order(size));
+		ptr = (void *)page_address(page);
 		if ((unsigned long)ptr & 0x07) {
-			free_pages((unsigned long)ptr, get_order(size));
+			__free_pages(page, get_order(size));
 			ptr = NULL;
 			/* Increment the size required if the first
 			 * attempt failed.
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_network.h b/drivers/net/ethernet/cavium/liquidio/octeon_network.h
index b3abe58..9c14484 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_network.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_network.h
@@ -48,11 +48,11 @@
 	 */
 	int rxq;
 
-	/** Guards the glist */
-	spinlock_t lock;
+	/** Guards each glist */
+	spinlock_t *glist_lock;
 
-	/** Linked list of gather components */
-	struct list_head glist;
+	/** Array of gather component linked lists */
+	struct list_head *glist;
 
 	/** Pointer to the NIC properties for the Octeon device this network
 	 *  interface is associated with.
@@ -67,6 +67,9 @@
 	/** Link information sent by the core application for this interface. */
 	struct oct_link_info linfo;
 
+	/** counter of link changes */
+	u64 link_changes;
+
 	/** Size of Tx queue for this octeon device. */
 	u32 tx_qsize;
 
@@ -111,8 +114,9 @@
  * \brief Enable or disable feature
  * @param netdev    pointer to network device
  * @param cmd       Command that just requires acknowledgment
+ * @param param1    Parameter to command
  */
-int liquidio_set_feature(struct net_device *netdev, int cmd);
+int liquidio_set_feature(struct net_device *netdev, int cmd, u16 param1);
 
 /**
  * \brief Link control command completion callback
@@ -131,14 +135,30 @@
  */
 void liquidio_set_ethtool_ops(struct net_device *netdev);
 
-static inline void
-*recv_buffer_alloc(struct octeon_device *oct __attribute__((unused)),
-		   u32 q_no __attribute__((unused)), u32 size)
-{
 #define SKB_ADJ_MASK  0x3F
 #define SKB_ADJ       (SKB_ADJ_MASK + 1)
 
-	struct sk_buff *skb = dev_alloc_skb(size + SKB_ADJ);
+#define MIN_SKB_SIZE       256 /* 8 bytes and more - 8 bytes for PTP */
+#define LIO_RXBUFFER_SZ    2048
+
+static inline void
+*recv_buffer_alloc(struct octeon_device *oct,
+		   struct octeon_skb_page_info *pg_info)
+{
+	struct page *page;
+	struct sk_buff *skb;
+	struct octeon_skb_page_info *skb_pg_info;
+
+	page = alloc_page(GFP_ATOMIC | __GFP_COLD);
+	if (unlikely(!page))
+		return NULL;
+
+	skb = dev_alloc_skb(MIN_SKB_SIZE + SKB_ADJ);
+	if (unlikely(!skb)) {
+		__free_page(page);
+		pg_info->page = NULL;
+		return NULL;
+	}
 
 	if ((unsigned long)skb->data & SKB_ADJ_MASK) {
 		u32 r = SKB_ADJ - ((unsigned long)skb->data & SKB_ADJ_MASK);
@@ -146,11 +166,151 @@
 		skb_reserve(skb, r);
 	}
 
+	skb_pg_info = ((struct octeon_skb_page_info *)(skb->cb));
+	/* Get DMA info */
+	pg_info->dma = dma_map_page(&oct->pci_dev->dev, page, 0,
+				    PAGE_SIZE, DMA_FROM_DEVICE);
+
+	/* Mapping failed!! */
+	if (dma_mapping_error(&oct->pci_dev->dev, pg_info->dma)) {
+		__free_page(page);
+		dev_kfree_skb_any((struct sk_buff *)skb);
+		pg_info->page = NULL;
+		return NULL;
+	}
+
+	pg_info->page = page;
+	pg_info->page_offset = 0;
+	skb_pg_info->page = page;
+	skb_pg_info->page_offset = 0;
+	skb_pg_info->dma = pg_info->dma;
+
 	return (void *)skb;
 }
 
+static inline void
+*recv_buffer_fast_alloc(u32 size)
+{
+	struct sk_buff *skb;
+	struct octeon_skb_page_info *skb_pg_info;
+
+	skb = dev_alloc_skb(size + SKB_ADJ);
+	if (unlikely(!skb))
+		return NULL;
+
+	if ((unsigned long)skb->data & SKB_ADJ_MASK) {
+		u32 r = SKB_ADJ - ((unsigned long)skb->data & SKB_ADJ_MASK);
+
+		skb_reserve(skb, r);
+	}
+
+	skb_pg_info = ((struct octeon_skb_page_info *)(skb->cb));
+	skb_pg_info->page = NULL;
+	skb_pg_info->page_offset = 0;
+	skb_pg_info->dma = 0;
+
+	return skb;
+}
+
+static inline int
+recv_buffer_recycle(struct octeon_device *oct, void *buf)
+{
+	struct octeon_skb_page_info *pg_info = buf;
+
+	if (!pg_info->page) {
+		dev_err(&oct->pci_dev->dev, "%s: pg_info->page NULL\n",
+			__func__);
+		return -ENOMEM;
+	}
+
+	if (unlikely(page_count(pg_info->page) != 1) ||
+	    unlikely(page_to_nid(pg_info->page)	!= numa_node_id())) {
+		dma_unmap_page(&oct->pci_dev->dev,
+			       pg_info->dma, (PAGE_SIZE << 0),
+			       DMA_FROM_DEVICE);
+		pg_info->dma = 0;
+		pg_info->page = NULL;
+		pg_info->page_offset = 0;
+		return -ENOMEM;
+	}
+
+	/* Flip to other half of the buffer */
+	if (pg_info->page_offset == 0)
+		pg_info->page_offset = LIO_RXBUFFER_SZ;
+	else
+		pg_info->page_offset = 0;
+	page_ref_inc(pg_info->page);
+
+	return 0;
+}
+
+static inline void
+*recv_buffer_reuse(struct octeon_device *oct, void *buf)
+{
+	struct octeon_skb_page_info *pg_info = buf, *skb_pg_info;
+	struct sk_buff *skb;
+
+	skb = dev_alloc_skb(MIN_SKB_SIZE + SKB_ADJ);
+	if (unlikely(!skb)) {
+		dma_unmap_page(&oct->pci_dev->dev,
+			       pg_info->dma, (PAGE_SIZE << 0),
+			       DMA_FROM_DEVICE);
+		return NULL;
+	}
+
+	if ((unsigned long)skb->data & SKB_ADJ_MASK) {
+		u32 r = SKB_ADJ - ((unsigned long)skb->data & SKB_ADJ_MASK);
+
+		skb_reserve(skb, r);
+	}
+
+	skb_pg_info = ((struct octeon_skb_page_info *)(skb->cb));
+	skb_pg_info->page = pg_info->page;
+	skb_pg_info->page_offset = pg_info->page_offset;
+	skb_pg_info->dma = pg_info->dma;
+
+	return skb;
+}
+
+static inline void
+recv_buffer_destroy(void *buffer, struct octeon_skb_page_info *pg_info)
+{
+	struct sk_buff *skb = (struct sk_buff *)buffer;
+
+	put_page(pg_info->page);
+	pg_info->dma = 0;
+	pg_info->page = NULL;
+	pg_info->page_offset = 0;
+
+	if (skb)
+		dev_kfree_skb_any(skb);
+}
+
 static inline void recv_buffer_free(void *buffer)
 {
+	struct sk_buff *skb = (struct sk_buff *)buffer;
+	struct octeon_skb_page_info *pg_info;
+
+	pg_info = ((struct octeon_skb_page_info *)(skb->cb));
+
+	if (pg_info->page) {
+		put_page(pg_info->page);
+		pg_info->dma = 0;
+		pg_info->page = NULL;
+		pg_info->page_offset = 0;
+	}
+
+	dev_kfree_skb_any((struct sk_buff *)buffer);
+}
+
+static inline void
+recv_buffer_fast_free(void *buffer)
+{
+	dev_kfree_skb_any((struct sk_buff *)buffer);
+}
+
+static inline void tx_buffer_free(void *buffer)
+{
 	dev_kfree_skb_any((struct sk_buff *)buffer);
 }
 
@@ -159,7 +319,17 @@
 #define lio_dma_free(oct, size, virt_addr, dma_addr) \
 	dma_free_coherent(&oct->pci_dev->dev, size, virt_addr, dma_addr)
 
-#define   get_rbd(ptr)      (((struct sk_buff *)(ptr))->data)
+static inline
+void *get_rbd(struct sk_buff *skb)
+{
+	struct octeon_skb_page_info *pg_info;
+	unsigned char *va;
+
+	pg_info = ((struct octeon_skb_page_info *)(skb->cb));
+	va = page_address(pg_info->page) + pg_info->page_offset;
+
+	return va;
+}
 
 static inline u64
 lio_map_ring_info(struct octeon_droq *droq, u32 i)
@@ -183,33 +353,44 @@
 }
 
 static inline u64
-lio_map_ring(struct pci_dev *pci_dev,
-	     void *buf, u32 size)
+lio_map_ring(void *buf)
 {
 	dma_addr_t dma_addr;
 
-	dma_addr = dma_map_single(&pci_dev->dev, get_rbd(buf), size,
-				  DMA_FROM_DEVICE);
+	struct sk_buff *skb = (struct sk_buff *)buf;
+	struct octeon_skb_page_info *pg_info;
 
-	BUG_ON(dma_mapping_error(&pci_dev->dev, dma_addr));
+	pg_info = ((struct octeon_skb_page_info *)(skb->cb));
+	if (!pg_info->page) {
+		pr_err("%s: pg_info->page NULL\n", __func__);
+		WARN_ON(1);
+	}
+
+	/* Get DMA info */
+	dma_addr = pg_info->dma;
+	if (!pg_info->dma) {
+		pr_err("%s: ERROR it should be already available\n",
+		       __func__);
+		WARN_ON(1);
+	}
+	dma_addr += pg_info->page_offset;
 
 	return (u64)dma_addr;
 }
 
 static inline void
 lio_unmap_ring(struct pci_dev *pci_dev,
-	       u64 buf_ptr, u32 size)
+	       u64 buf_ptr)
+
 {
-	dma_unmap_single(&pci_dev->dev,
-			 buf_ptr, size,
-			 DMA_FROM_DEVICE);
+	dma_unmap_page(&pci_dev->dev,
+		       buf_ptr, (PAGE_SIZE << 0),
+		       DMA_FROM_DEVICE);
 }
 
-static inline void *octeon_fast_packet_alloc(struct octeon_device *oct,
-					     struct octeon_droq *droq,
-					     u32 q_no, u32 size)
+static inline void *octeon_fast_packet_alloc(u32 size)
 {
-	return recv_buffer_alloc(oct, q_no, size);
+	return recv_buffer_fast_alloc(size);
 }
 
 static inline void octeon_fast_packet_next(struct octeon_droq *droq,
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_nic.c b/drivers/net/ethernet/cavium/liquidio/octeon_nic.c
index 1a01915..7843b8a 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_nic.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_nic.c
@@ -44,11 +44,11 @@
 
 void *
 octeon_alloc_soft_command_resp(struct octeon_device    *oct,
-			       struct octeon_instr_64B *cmd,
-			       size_t		       rdatasize)
+			       union octeon_instr_64B *cmd,
+			       u32		       rdatasize)
 {
 	struct octeon_soft_command *sc;
-	struct octeon_instr_ih  *ih;
+	struct octeon_instr_ih2  *ih2;
 	struct octeon_instr_irh *irh;
 	struct octeon_instr_rdp *rdp;
 
@@ -59,24 +59,25 @@
 		return NULL;
 
 	/* Copy existing command structure into the soft command */
-	memcpy(&sc->cmd, cmd, sizeof(struct octeon_instr_64B));
+	memcpy(&sc->cmd, cmd, sizeof(union octeon_instr_64B));
 
 	/* Add in the response related fields. Opcode and Param are already
 	 * there.
 	 */
-	ih      = (struct octeon_instr_ih *)&sc->cmd.ih;
-	ih->fsz = 40; /* irh + ossp[0] + ossp[1] + rdp + rptr = 40 bytes */
+	ih2      = (struct octeon_instr_ih2 *)&sc->cmd.cmd2.ih2;
+	rdp     = (struct octeon_instr_rdp *)&sc->cmd.cmd2.rdp;
+	irh     = (struct octeon_instr_irh *)&sc->cmd.cmd2.irh;
+	ih2->fsz = 40; /* irh + ossp[0] + ossp[1] + rdp + rptr = 40 bytes */
 
-	irh        = (struct octeon_instr_irh *)&sc->cmd.irh;
 	irh->rflag = 1; /* a response is required */
-	irh->len   = 4; /* means four 64-bit words immediately follow irh */
 
-	rdp            = (struct octeon_instr_rdp *)&sc->cmd.rdp;
 	rdp->pcie_port = oct->pcie_port;
 	rdp->rlen      = rdatasize;
 
 	*sc->status_word = COMPLETION_WORD_INIT;
 
+	sc->cmd.cmd2.rptr =  sc->dmarptr;
+
 	sc->wait_time = 1000;
 	sc->timeout = jiffies + sc->wait_time;
 
@@ -119,12 +120,11 @@
 
 static inline struct octeon_soft_command
 *octnic_alloc_ctrl_pkt_sc(struct octeon_device *oct,
-			  struct octnic_ctrl_pkt *nctrl,
-			  struct octnic_ctrl_params nparams)
+			  struct octnic_ctrl_pkt *nctrl)
 {
 	struct octeon_soft_command *sc = NULL;
 	u8 *data;
-	size_t rdatasize;
+	u32 rdatasize;
 	u32 uddsize = 0, datasize = 0;
 
 	uddsize = (u32)(nctrl->ncmd.s.more * 8);
@@ -143,7 +143,7 @@
 
 	data = (u8 *)sc->virtdptr;
 
-	memcpy(data, &nctrl->ncmd,  OCTNET_CMD_SIZE);
+	memcpy(data, &nctrl->ncmd, OCTNET_CMD_SIZE);
 
 	octeon_swap_8B_data((u64 *)data, (OCTNET_CMD_SIZE >> 3));
 
@@ -152,6 +152,8 @@
 		memcpy(data + OCTNET_CMD_SIZE, nctrl->udd, uddsize);
 	}
 
+	sc->iq_no = (u32)nctrl->iq_no;
+
 	octeon_prepare_soft_command(oct, sc, OPCODE_NIC, OPCODE_NIC_CMD,
 				    0, 0, 0);
 
@@ -164,13 +166,12 @@
 
 int
 octnet_send_nic_ctrl_pkt(struct octeon_device *oct,
-			 struct octnic_ctrl_pkt *nctrl,
-			 struct octnic_ctrl_params nparams)
+			 struct octnic_ctrl_pkt *nctrl)
 {
 	int retval;
 	struct octeon_soft_command *sc = NULL;
 
-	sc = octnic_alloc_ctrl_pkt_sc(oct, nctrl, nparams);
+	sc = octnic_alloc_ctrl_pkt_sc(oct, nctrl);
 	if (!sc) {
 		dev_err(&oct->pci_dev->dev, "%s soft command alloc failed\n",
 			__func__);
@@ -178,7 +179,7 @@
 	}
 
 	retval = octeon_send_soft_command(oct, sc);
-	if (retval) {
+	if (retval == IQ_SEND_FAILED) {
 		octeon_free_soft_command(oct, sc);
 		dev_err(&oct->pci_dev->dev, "%s soft command send failed status: %x\n",
 			__func__, retval);
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_nic.h b/drivers/net/ethernet/cavium/liquidio/octeon_nic.h
index 0238857..b71a2bb 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_nic.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_nic.h
@@ -52,6 +52,9 @@
 	/** Additional data that may be needed by some commands. */
 	u64 udd[MAX_NCTRL_UDD];
 
+	/** Input queue to use to send this command. */
+	u64 iq_no;
+
 	/** Time to wait for Octeon software to respond to this control command.
 	 *  If wait_time is 0, OSI assumes no response is expected.
 	 */
@@ -82,7 +85,7 @@
 	u32 datasize;
 
 	/** Command to be passed to the Octeon device software. */
-	struct octeon_instr_64B cmd;
+	union octeon_instr_64B cmd;
 
 	/** Input queue to use to send this command. */
 	u32 q_no;
@@ -94,15 +97,14 @@
  */
 union octnic_cmd_setup {
 	struct {
-		u32 ifidx:8;
-		u32 cksum_offset:7;
+		u32 iq_no:8;
 		u32 gather:1;
 		u32 timestamp:1;
-		u32 ipv4opts_ipv6exthdr:2;
 		u32 ip_csum:1;
+		u32 transport_csum:1;
 		u32 tnl_csum:1;
+		u32 rsvd:19;
 
-		u32 rsvd:11;
 		union {
 			u32 datasize;
 			u32 gatherptrs;
@@ -113,16 +115,129 @@
 
 };
 
-struct octnic_ctrl_params {
-	u32 resp_order;
-};
-
 static inline int octnet_iq_is_full(struct octeon_device *oct, u32 q_no)
 {
 	return ((u32)atomic_read(&oct->instr_queue[q_no]->instr_pending)
 		>= (oct->instr_queue[q_no]->max_count - 2));
 }
 
+static inline void
+octnet_prepare_pci_cmd_o2(struct octeon_device *oct,
+			  union octeon_instr_64B *cmd,
+			  union octnic_cmd_setup *setup, u32 tag)
+{
+	struct octeon_instr_ih2 *ih2;
+	struct octeon_instr_irh *irh;
+	union octnic_packet_params packet_params;
+	int port;
+
+	memset(cmd, 0, sizeof(union octeon_instr_64B));
+
+	ih2 = (struct octeon_instr_ih2 *)&cmd->cmd2.ih2;
+
+	/* assume that rflag is cleared so therefore front data will only have
+	 * irh and ossp[0], ossp[1] for a total of 32 bytes
+	 */
+	ih2->fsz = 24;
+
+	ih2->tagtype = ORDERED_TAG;
+	ih2->grp = DEFAULT_POW_GRP;
+
+	port = (int)oct->instr_queue[setup->s.iq_no]->txpciq.s.port;
+
+	if (tag)
+		ih2->tag = tag;
+	else
+		ih2->tag = LIO_DATA(port);
+
+	ih2->raw = 1;
+	ih2->qos = (port & 3) + 4;	/* map qos based on interface */
+
+	if (!setup->s.gather) {
+		ih2->dlengsz = setup->s.u.datasize;
+	} else {
+		ih2->gather = 1;
+		ih2->dlengsz = setup->s.u.gatherptrs;
+	}
+
+	irh = (struct octeon_instr_irh *)&cmd->cmd2.irh;
+
+	irh->opcode = OPCODE_NIC;
+	irh->subcode = OPCODE_NIC_NW_DATA;
+
+	packet_params.u32 = 0;
+
+	packet_params.s.ip_csum = setup->s.ip_csum;
+	packet_params.s.transport_csum = setup->s.transport_csum;
+	packet_params.s.tnl_csum = setup->s.tnl_csum;
+	packet_params.s.tsflag = setup->s.timestamp;
+
+	irh->ossp = packet_params.u32;
+}
+
+static inline void
+octnet_prepare_pci_cmd_o3(struct octeon_device *oct,
+			  union octeon_instr_64B *cmd,
+			  union octnic_cmd_setup *setup, u32 tag)
+{
+	struct octeon_instr_irh *irh;
+	struct octeon_instr_ih3     *ih3;
+	struct octeon_instr_pki_ih3 *pki_ih3;
+	union octnic_packet_params packet_params;
+	int port;
+
+	memset(cmd, 0, sizeof(union octeon_instr_64B));
+
+	ih3 = (struct octeon_instr_ih3 *)&cmd->cmd3.ih3;
+	pki_ih3 = (struct octeon_instr_pki_ih3 *)&cmd->cmd3.pki_ih3;
+
+	/* assume that rflag is cleared so therefore front data will only have
+	 * irh and ossp[1] and ossp[2] for a total of 24 bytes
+	 */
+	ih3->pkind       = oct->instr_queue[setup->s.iq_no]->txpciq.s.pkind;
+	/*PKI IH*/
+	ih3->fsz = 24 + 8;
+
+	if (!setup->s.gather) {
+		ih3->dlengsz = setup->s.u.datasize;
+	} else {
+		ih3->gather = 1;
+		ih3->dlengsz = setup->s.u.gatherptrs;
+	}
+
+	pki_ih3->w       = 1;
+	pki_ih3->raw     = 1;
+	pki_ih3->utag    = 1;
+	pki_ih3->utt     = 1;
+	pki_ih3->uqpg    = oct->instr_queue[setup->s.iq_no]->txpciq.s.use_qpg;
+
+	port = (int)oct->instr_queue[setup->s.iq_no]->txpciq.s.port;
+
+	if (tag)
+		pki_ih3->tag = tag;
+	else
+		pki_ih3->tag     = LIO_DATA(port);
+
+	pki_ih3->tagtype = ORDERED_TAG;
+	pki_ih3->qpg     = oct->instr_queue[setup->s.iq_no]->txpciq.s.qpg;
+	pki_ih3->pm      = 0x7; /*0x7 - meant for Parse nothing, uninterpreted*/
+	pki_ih3->sl      = 8;   /* sl will be sizeof(pki_ih3)*/
+
+	irh = (struct octeon_instr_irh *)&cmd->cmd3.irh;
+
+	irh->opcode = OPCODE_NIC;
+	irh->subcode = OPCODE_NIC_NW_DATA;
+
+	packet_params.u32 = 0;
+
+	packet_params.s.ip_csum = setup->s.ip_csum;
+	packet_params.s.transport_csum = setup->s.transport_csum;
+	packet_params.s.tnl_csum = setup->s.tnl_csum;
+	packet_params.s.tsflag = setup->s.timestamp;
+
+	irh->ossp = packet_params.u32;
+}
+
 /** Utility function to prepare a 64B NIC instruction based on a setup command
  * @param cmd - pointer to instruction to be filled in.
  * @param setup - pointer to the setup structure
@@ -131,59 +246,13 @@
  * Assumes the cmd instruction is pre-allocated, but no fields are filled in.
  */
 static inline void
-octnet_prepare_pci_cmd(struct octeon_instr_64B *cmd,
+octnet_prepare_pci_cmd(struct octeon_device *oct, union octeon_instr_64B *cmd,
 		       union octnic_cmd_setup *setup, u32 tag)
 {
-	struct octeon_instr_ih *ih;
-	struct octeon_instr_irh *irh;
-	union octnic_packet_params packet_params;
-
-	memset(cmd, 0, sizeof(struct octeon_instr_64B));
-
-	ih = (struct octeon_instr_ih *)&cmd->ih;
-
-	/* assume that rflag is cleared so therefore front data will only have
-	 * irh and ossp[1] and ossp[2] for a total of 24 bytes
-	 */
-	ih->fsz = 24;
-
-	ih->tagtype = ORDERED_TAG;
-	ih->grp = DEFAULT_POW_GRP;
-
-	if (tag)
-		ih->tag = tag;
+	if (OCTEON_CN6XXX(oct))
+		octnet_prepare_pci_cmd_o2(oct, cmd, setup, tag);
 	else
-		ih->tag = LIO_DATA(setup->s.ifidx);
-
-	ih->raw = 1;
-	ih->qos = (setup->s.ifidx & 3) + 4;	/* map qos based on interface */
-
-	if (!setup->s.gather) {
-		ih->dlengsz = setup->s.u.datasize;
-	} else {
-		ih->gather = 1;
-		ih->dlengsz = setup->s.u.gatherptrs;
-	}
-
-	irh = (struct octeon_instr_irh *)&cmd->irh;
-
-	irh->opcode = OPCODE_NIC;
-	irh->subcode = OPCODE_NIC_NW_DATA;
-
-	packet_params.u32 = 0;
-
-	if (setup->s.cksum_offset) {
-		packet_params.s.csoffset = setup->s.cksum_offset;
-		packet_params.s.ipv4opts_ipv6exthdr =
-						setup->s.ipv4opts_ipv6exthdr;
-	}
-
-	packet_params.s.ip_csum = setup->s.ip_csum;
-	packet_params.s.tnl_csum = setup->s.tnl_csum;
-	packet_params.s.ifidx = setup->s.ifidx;
-	packet_params.s.tsflag = setup->s.timestamp;
-
-	irh->ossp = packet_params.u32;
+		octnet_prepare_pci_cmd_o3(oct, cmd, setup, tag);
 }
 
 /** Allocate and a soft command with space for a response immediately following
@@ -198,8 +267,8 @@
  */
 void *
 octeon_alloc_soft_command_resp(struct octeon_device    *oct,
-			       struct octeon_instr_64B *cmd,
-			       size_t		       rdatasize);
+			       union octeon_instr_64B *cmd,
+			       u32		       rdatasize);
 
 /** Send a NIC data packet to the device
  * @param oct - octeon device pointer
@@ -214,14 +283,11 @@
 /** Send a NIC control packet to the device
  * @param oct - octeon device pointer
  * @param nctrl - control structure with command, timout, and callback info
- * @param nparams - response control structure
- *
  * @returns IQ_FAILED if it failed to add to the input queue. IQ_STOP if it the
  * queue should be stopped, and IQ_SEND_OK if it sent okay.
  */
 int
 octnet_send_nic_ctrl_pkt(struct octeon_device *oct,
-			 struct octnic_ctrl_pkt *nctrl,
-			 struct octnic_ctrl_params nparams);
+			 struct octnic_ctrl_pkt *nctrl);
 
 #endif
diff --git a/drivers/net/ethernet/cavium/liquidio/request_manager.c b/drivers/net/ethernet/cavium/liquidio/request_manager.c
index a2a2465..8649677 100644
--- a/drivers/net/ethernet/cavium/liquidio/request_manager.c
+++ b/drivers/net/ethernet/cavium/liquidio/request_manager.c
@@ -69,12 +69,16 @@
 
 /* Return 0 on success, 1 on failure */
 int octeon_init_instr_queue(struct octeon_device *oct,
-			    u32 iq_no, u32 num_descs)
+			    union oct_txpciq txpciq,
+			    u32 num_descs)
 {
 	struct octeon_instr_queue *iq;
 	struct octeon_iq_config *conf = NULL;
+	u32 iq_no = (u32)txpciq.s.q_no;
 	u32 q_size;
 	struct cavium_wq *db_wq;
+	int orig_node = dev_to_node(&oct->pci_dev->dev);
+	int numa_node = cpu_to_node(iq_no % num_online_cpus());
 
 	if (OCTEON_CN6XXX(oct))
 		conf = &(CFG_GET_IQ_CFG(CHIP_FIELD(oct, cn6xxx, conf)));
@@ -95,9 +99,15 @@
 	q_size = (u32)conf->instr_type * num_descs;
 
 	iq = oct->instr_queue[iq_no];
+	iq->oct_dev = oct;
 
+	set_dev_node(&oct->pci_dev->dev, numa_node);
 	iq->base_addr = lio_dma_alloc(oct, q_size,
 				      (dma_addr_t *)&iq->base_addr_dma);
+	set_dev_node(&oct->pci_dev->dev, orig_node);
+	if (!iq->base_addr)
+		iq->base_addr = lio_dma_alloc(oct, q_size,
+					      (dma_addr_t *)&iq->base_addr_dma);
 	if (!iq->base_addr) {
 		dev_err(&oct->pci_dev->dev, "Cannot allocate memory for instr queue %d\n",
 			iq_no);
@@ -109,7 +119,11 @@
 	/* Initialize a list to holds requests that have been posted to Octeon
 	 * but has yet to be fetched by octeon
 	 */
-	iq->request_list = vmalloc(sizeof(*iq->request_list) * num_descs);
+	iq->request_list = vmalloc_node((sizeof(*iq->request_list) * num_descs),
+					       numa_node);
+	if (!iq->request_list)
+		iq->request_list = vmalloc(sizeof(*iq->request_list) *
+						  num_descs);
 	if (!iq->request_list) {
 		lio_dma_free(oct, q_size, iq->base_addr, iq->base_addr_dma);
 		dev_err(&oct->pci_dev->dev, "Alloc failed for IQ[%d] nr free list\n",
@@ -122,7 +136,7 @@
 	dev_dbg(&oct->pci_dev->dev, "IQ[%d]: base: %p basedma: %llx count: %d\n",
 		iq_no, iq->base_addr, iq->base_addr_dma, iq->max_count);
 
-	iq->iq_no = iq_no;
+	iq->txpciq.u64 = txpciq.u64;
 	iq->fill_threshold = (u32)conf->db_min;
 	iq->fill_cnt = 0;
 	iq->host_write_index = 0;
@@ -144,7 +158,9 @@
 
 	oct->fn_list.setup_iq_regs(oct, iq_no);
 
-	oct->check_db_wq[iq_no].wq = create_workqueue("check_iq_db");
+	oct->check_db_wq[iq_no].wq = alloc_workqueue("check_iq_db",
+						     WQ_MEM_RECLAIM,
+						     0);
 	if (!oct->check_db_wq[iq_no].wq) {
 		lio_dma_free(oct, q_size, iq->base_addr, iq->base_addr_dma);
 		dev_err(&oct->pci_dev->dev, "check db wq create failed for iq %d\n",
@@ -168,7 +184,6 @@
 	struct octeon_instr_queue *iq = oct->instr_queue[iq_no];
 
 	cancel_delayed_work_sync(&oct->check_db_wq[iq_no].wk.work);
-	flush_workqueue(oct->check_db_wq[iq_no].wq);
 	destroy_workqueue(oct->check_db_wq[iq_no].wq);
 
 	if (OCTEON_CN6XXX(oct))
@@ -188,26 +203,38 @@
 
 /* Return 0 on success, 1 on failure */
 int octeon_setup_iq(struct octeon_device *oct,
-		    u32 iq_no,
+		    int ifidx,
+		    int q_index,
+		    union oct_txpciq txpciq,
 		    u32 num_descs,
 		    void *app_ctx)
 {
+	u32 iq_no = (u32)txpciq.s.q_no;
+	int numa_node = cpu_to_node(iq_no % num_online_cpus());
+
 	if (oct->instr_queue[iq_no]) {
 		dev_dbg(&oct->pci_dev->dev, "IQ is in use. Cannot create the IQ: %d again\n",
 			iq_no);
+		oct->instr_queue[iq_no]->txpciq.u64 = txpciq.u64;
 		oct->instr_queue[iq_no]->app_ctx = app_ctx;
 		return 0;
 	}
 	oct->instr_queue[iq_no] =
-	    vmalloc(sizeof(struct octeon_instr_queue));
+	    vmalloc_node(sizeof(struct octeon_instr_queue), numa_node);
+	if (!oct->instr_queue[iq_no])
+		oct->instr_queue[iq_no] =
+		    vmalloc(sizeof(struct octeon_instr_queue));
 	if (!oct->instr_queue[iq_no])
 		return 1;
 
 	memset(oct->instr_queue[iq_no], 0,
 	       sizeof(struct octeon_instr_queue));
 
+	oct->instr_queue[iq_no]->q_index = q_index;
 	oct->instr_queue[iq_no]->app_ctx = app_ctx;
-	if (octeon_init_instr_queue(oct, iq_no, num_descs)) {
+	oct->instr_queue[iq_no]->ifidx = ifidx;
+
+	if (octeon_init_instr_queue(oct, txpciq, num_descs)) {
 		vfree(oct->instr_queue[iq_no]);
 		oct->instr_queue[iq_no] = NULL;
 		return 1;
@@ -394,7 +421,7 @@
 		case REQTYPE_SOFT_COMMAND:
 			sc = buf;
 
-			irh = (struct octeon_instr_irh *)&sc->cmd.irh;
+			irh = (struct octeon_instr_irh *)&sc->cmd.cmd2.irh;
 			if (irh->rflag) {
 				/* We're expecting a response from Octeon.
 				 * It's up to lio_process_ordered_list() to
@@ -557,7 +584,7 @@
 			    u64 ossp1)
 {
 	struct octeon_config *oct_cfg;
-	struct octeon_instr_ih *ih;
+	struct octeon_instr_ih2 *ih2;
 	struct octeon_instr_irh *irh;
 	struct octeon_instr_rdp *rdp;
 
@@ -566,73 +593,69 @@
 
 	oct_cfg = octeon_get_conf(oct);
 
-	ih          = (struct octeon_instr_ih *)&sc->cmd.ih;
-	ih->tagtype = ATOMIC_TAG;
-	ih->tag     = LIO_CONTROL;
-	ih->raw     = 1;
-	ih->grp     = CFG_GET_CTRL_Q_GRP(oct_cfg);
+	ih2          = (struct octeon_instr_ih2 *)&sc->cmd.cmd2.ih2;
+	ih2->tagtype = ATOMIC_TAG;
+	ih2->tag     = LIO_CONTROL;
+	ih2->raw     = 1;
+	ih2->grp     = CFG_GET_CTRL_Q_GRP(oct_cfg);
 
 	if (sc->datasize) {
-		ih->dlengsz = sc->datasize;
-		ih->rs = 1;
+		ih2->dlengsz = sc->datasize;
+		ih2->rs = 1;
 	}
 
-	irh            = (struct octeon_instr_irh *)&sc->cmd.irh;
+	irh            = (struct octeon_instr_irh *)&sc->cmd.cmd2.irh;
 	irh->opcode    = opcode;
 	irh->subcode   = subcode;
 
 	/* opcode/subcode specific parameters (ossp) */
 	irh->ossp       = irh_ossp;
-	sc->cmd.ossp[0] = ossp0;
-	sc->cmd.ossp[1] = ossp1;
+	sc->cmd.cmd2.ossp[0] = ossp0;
+	sc->cmd.cmd2.ossp[1] = ossp1;
 
 	if (sc->rdatasize) {
-		rdp            = (struct octeon_instr_rdp *)&sc->cmd.rdp;
+		rdp = (struct octeon_instr_rdp *)&sc->cmd.cmd2.rdp;
 		rdp->pcie_port = oct->pcie_port;
 		rdp->rlen      = sc->rdatasize;
 
 		irh->rflag =  1;
-		irh->len   =  4;
-		ih->fsz    = 40; /* irh+ossp[0]+ossp[1]+rdp+rptr = 40 bytes */
+		ih2->fsz   = 40; /* irh+ossp[0]+ossp[1]+rdp+rptr = 40 bytes */
 	} else {
 		irh->rflag =  0;
-		irh->len   =  2;
-		ih->fsz    = 24; /* irh + ossp[0] + ossp[1] = 24 bytes */
+		ih2->fsz   = 24; /* irh + ossp[0] + ossp[1] = 24 bytes */
 	}
-
-	while (!(oct->io_qmask.iq & (1 << sc->iq_no)))
-		sc->iq_no++;
 }
 
 int octeon_send_soft_command(struct octeon_device *oct,
 			     struct octeon_soft_command *sc)
 {
-	struct octeon_instr_ih *ih;
+	struct octeon_instr_ih2 *ih2;
 	struct octeon_instr_irh *irh;
 	struct octeon_instr_rdp *rdp;
+	u32 len;
 
-	ih = (struct octeon_instr_ih *)&sc->cmd.ih;
-	if (ih->dlengsz) {
-		BUG_ON(!sc->dmadptr);
-		sc->cmd.dptr = sc->dmadptr;
+	ih2 = (struct octeon_instr_ih2 *)&sc->cmd.cmd2.ih2;
+	if (ih2->dlengsz) {
+		WARN_ON(!sc->dmadptr);
+		sc->cmd.cmd2.dptr = sc->dmadptr;
 	}
-
-	irh = (struct octeon_instr_irh *)&sc->cmd.irh;
+	irh = (struct octeon_instr_irh *)&sc->cmd.cmd2.irh;
 	if (irh->rflag) {
 		BUG_ON(!sc->dmarptr);
 		BUG_ON(!sc->status_word);
 		*sc->status_word = COMPLETION_WORD_INIT;
 
-		rdp = (struct octeon_instr_rdp *)&sc->cmd.rdp;
+		rdp = (struct octeon_instr_rdp *)&sc->cmd.cmd2.rdp;
 
-		sc->cmd.rptr = sc->dmarptr;
+		sc->cmd.cmd2.rptr = sc->dmarptr;
 	}
+	len = (u32)ih2->dlengsz;
 
 	if (sc->wait_time)
 		sc->timeout = jiffies + sc->wait_time;
 
-	return octeon_send_command(oct, sc->iq_no, 1, &sc->cmd, sc,
-				   (u32)ih->dlengsz, REQTYPE_SOFT_COMMAND);
+	return (octeon_send_command(oct, sc->iq_no, 1, &sc->cmd, sc,
+				    len, REQTYPE_SOFT_COMMAND));
 }
 
 int octeon_setup_sc_buffer_pool(struct octeon_device *oct)
diff --git a/drivers/net/ethernet/cavium/liquidio/response_manager.c b/drivers/net/ethernet/cavium/liquidio/response_manager.c
index 091f537..e2e9103 100644
--- a/drivers/net/ethernet/cavium/liquidio/response_manager.c
+++ b/drivers/net/ethernet/cavium/liquidio/response_manager.c
@@ -55,7 +55,7 @@
 		atomic_set(&oct->response_list[i].pending_req_count, 0);
 	}
 
-	oct->dma_comp_wq.wq = create_workqueue("dma-comp");
+	oct->dma_comp_wq.wq = alloc_workqueue("dma-comp", WQ_MEM_RECLAIM, 0);
 	if (!oct->dma_comp_wq.wq) {
 		dev_err(&oct->pci_dev->dev, "failed to create wq thread\n");
 		return -ENOMEM;
@@ -72,7 +72,6 @@
 void octeon_delete_response_list(struct octeon_device *oct)
 {
 	cancel_delayed_work_sync(&oct->dma_comp_wq.wk.work);
-	flush_workqueue(oct->dma_comp_wq.wq);
 	destroy_workqueue(oct->dma_comp_wq.wq);
 }
 
@@ -86,6 +85,7 @@
 	u32 status;
 	u64 status64;
 	struct octeon_instr_rdp *rdp;
+	u64 rptr;
 
 	ordered_sc_list = &octeon_dev->response_list[OCTEON_ORDERED_SC_LIST];
 
@@ -103,7 +103,8 @@
 
 		sc = (struct octeon_soft_command *)ordered_sc_list->
 		    head.next;
-		rdp = (struct octeon_instr_rdp *)&sc->cmd.rdp;
+		rdp = (struct octeon_instr_rdp *)&sc->cmd.cmd2.rdp;
+		rptr = sc->cmd.cmd2.rptr;
 
 		status = OCTEON_REQUEST_PENDING;
 
@@ -111,7 +112,7 @@
 		 * to where rptr is pointing to
 		 */
 		dma_sync_single_for_cpu(&octeon_dev->pci_dev->dev,
-					sc->cmd.rptr, rdp->rlen,
+					rptr, rdp->rlen,
 					DMA_FROM_DEVICE);
 		status64 = *sc->status_word;
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 477db47..c45de49 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -64,6 +64,7 @@
 #include <net/bonding.h>
 #include <net/addrconf.h>
 #include <asm/uaccess.h>
+#include <linux/crash_dump.h>
 
 #include "cxgb4.h"
 #include "t4_regs.h"
@@ -206,7 +207,7 @@
 static unsigned int num_vf[NUM_OF_PF_WITH_SRIOV];
 
 module_param_array(num_vf, uint, NULL, 0644);
-MODULE_PARM_DESC(num_vf, "number of VFs for each of PFs 0-3");
+MODULE_PARM_DESC(num_vf, "number of VFs for each of PFs 0-3, deprecated parameter - please use the pci sysfs interface.");
 #endif
 
 /* TX Queue select used to determine what algorithm to use for selecting TX
@@ -460,11 +461,8 @@
 	struct port_info *pi = netdev_priv(dev);
 	struct adapter *adapter = pi->adapter;
 
-	if (!(dev->flags & IFF_PROMISC)) {
-		__dev_uc_sync(dev, cxgb4_mac_sync, cxgb4_mac_unsync);
-		if (!(dev->flags & IFF_ALLMULTI))
-			__dev_mc_sync(dev, cxgb4_mac_sync, cxgb4_mac_unsync);
-	}
+	__dev_uc_sync(dev, cxgb4_mac_sync, cxgb4_mac_unsync);
+	__dev_mc_sync(dev, cxgb4_mac_sync, cxgb4_mac_unsync);
 
 	return t4_set_rxmode(adapter, adapter->mbox, pi->viid, mtu,
 			     (dev->flags & IFF_PROMISC) ? 1 : 0,
@@ -3735,7 +3733,8 @@
 		return ret;
 
 	/* Contact FW, advertising Master capability */
-	ret = t4_fw_hello(adap, adap->mbox, adap->mbox, MASTER_MAY, &state);
+	ret = t4_fw_hello(adap, adap->mbox, adap->mbox,
+			  is_kdump_kernel() ? MASTER_MUST : MASTER_MAY, &state);
 	if (ret < 0) {
 		dev_err(adap->pdev_dev, "could not connect to FW, error %d\n",
 			ret);
@@ -4366,6 +4365,11 @@
 	if (q10g > netif_get_num_default_rss_queues())
 		q10g = netif_get_num_default_rss_queues();
 
+	/* Reduce memory usage in kdump environment, disable all offload.
+	 */
+	if (is_kdump_kernel())
+		adap->params.offload = 0;
+
 	for_each_port(adap, i) {
 		struct port_info *pi = adap2pinfo(adap, i);
 
@@ -4829,6 +4833,60 @@
 	return -EINVAL;
 }
 
+#ifdef CONFIG_PCI_IOV
+static int cxgb4_iov_configure(struct pci_dev *pdev, int num_vfs)
+{
+	int err = 0;
+	int current_vfs = pci_num_vf(pdev);
+	u32 pcie_fw;
+	void __iomem *regs;
+
+	regs = pci_ioremap_bar(pdev, 0);
+	if (!regs) {
+		dev_err(&pdev->dev, "cannot map device registers\n");
+		return -ENOMEM;
+	}
+
+	pcie_fw = readl(regs + PCIE_FW_A);
+	iounmap(regs);
+	/* Check if cxgb4 is the MASTER and fw is initialized */
+	if (!(pcie_fw & PCIE_FW_INIT_F) ||
+	    !(pcie_fw & PCIE_FW_MASTER_VLD_F) ||
+	    PCIE_FW_MASTER_G(pcie_fw) != 4) {
+		dev_warn(&pdev->dev,
+			 "cxgb4 driver needs to be MASTER to support SRIOV\n");
+		return -EOPNOTSUPP;
+	}
+
+	/* If any of the VF's is already assigned to Guest OS, then
+	 * SRIOV for the same cannot be modified
+	 */
+	if (current_vfs && pci_vfs_assigned(pdev)) {
+		dev_err(&pdev->dev,
+			"Cannot modify SR-IOV while VFs are assigned\n");
+		num_vfs = current_vfs;
+		return num_vfs;
+	}
+
+	/* Disable SRIOV when zero is passed.
+	 * One needs to disable SRIOV before modifying it, else
+	 * stack throws the below warning:
+	 * " 'n' VFs already enabled. Disable before enabling 'm' VFs."
+	 */
+	if (!num_vfs) {
+		pci_disable_sriov(pdev);
+		return num_vfs;
+	}
+
+	if (num_vfs != current_vfs) {
+		err = pci_enable_sriov(pdev, num_vfs);
+		if (err)
+			return err;
+	}
+	return num_vfs;
+}
+#endif
+
 static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	int func, i, err, s_qpp, qpp, num_seg;
@@ -5162,11 +5220,16 @@
 
 sriov:
 #ifdef CONFIG_PCI_IOV
-	if (func < ARRAY_SIZE(num_vf) && num_vf[func] > 0)
+	if (func < ARRAY_SIZE(num_vf) && num_vf[func] > 0) {
+		dev_warn(&pdev->dev,
+			 "Enabling SR-IOV VFs using the num_vf module "
+			 "parameter is deprecated - please use the pci sysfs "
+			 "interface instead.\n");
 		if (pci_enable_sriov(pdev, num_vf[func]) == 0)
 			dev_info(&pdev->dev,
 				 "instantiated %u virtual functions\n",
 				 num_vf[func]);
+	}
 #endif
 	return 0;
 
@@ -5259,6 +5322,9 @@
 	.probe    = init_one,
 	.remove   = remove_one,
 	.shutdown = remove_one,
+#ifdef CONFIG_PCI_IOV
+	.sriov_configure = cxgb4_iov_configure,
+#endif
 	.err_handler = &cxgb4_eeh,
 };
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
index a2cdfc1..50812a1 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
@@ -144,6 +144,7 @@
 	CH_PCI_ID_TABLE_FENTRY(0x5015),	/* T502-bt */
 	CH_PCI_ID_TABLE_FENTRY(0x5016),	/* T580-OCP-SO */
 	CH_PCI_ID_TABLE_FENTRY(0x5017),	/* T520-OCP-SO */
+	CH_PCI_ID_TABLE_FENTRY(0x5018),	/* T540-BT */
 	CH_PCI_ID_TABLE_FENTRY(0x5080),	/* Custom T540-cr */
 	CH_PCI_ID_TABLE_FENTRY(0x5081),	/* Custom T540-LL-cr */
 	CH_PCI_ID_TABLE_FENTRY(0x5082),	/* Custom T504-cr */
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
index 04fc6f6..8d9b2cb 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
@@ -937,12 +937,8 @@
 {
 	struct port_info *pi = netdev_priv(dev);
 
-	if (!(dev->flags & IFF_PROMISC)) {
-		__dev_uc_sync(dev, cxgb4vf_mac_sync, cxgb4vf_mac_unsync);
-		if (!(dev->flags & IFF_ALLMULTI))
-			__dev_mc_sync(dev, cxgb4vf_mac_sync,
-				      cxgb4vf_mac_unsync);
-	}
+	__dev_uc_sync(dev, cxgb4vf_mac_sync, cxgb4vf_mac_unsync);
+	__dev_mc_sync(dev, cxgb4vf_mac_sync, cxgb4vf_mac_unsync);
 	return t4vf_set_rxmode(pi->adapter, pi->viid, -1,
 			       (dev->flags & IFF_PROMISC) != 0,
 			       (dev->flags & IFF_ALLMULTI) != 0,
diff --git a/drivers/net/ethernet/cirrus/cs89x0.c b/drivers/net/ethernet/cirrus/cs89x0.c
index 6038304..c363b58 100644
--- a/drivers/net/ethernet/cirrus/cs89x0.c
+++ b/drivers/net/ethernet/cirrus/cs89x0.c
@@ -53,6 +53,8 @@
 #include <linux/errno.h>
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
@@ -1895,9 +1897,17 @@
 	return 0;
 }
 
+static const struct __maybe_unused of_device_id cs89x0_match[] = {
+	{ .compatible = "cirrus,cs8900", },
+	{ .compatible = "cirrus,cs8920", },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, cs89x0_match);
+
 static struct platform_driver cs89x0_driver = {
 	.driver	= {
-		.name	= DRV_NAME,
+		.name		= DRV_NAME,
+		.of_match_table	= of_match_ptr(cs89x0_match),
 	},
 	.remove	= cs89x0_platform_remove,
 };
diff --git a/drivers/net/ethernet/cisco/enic/enic_ethtool.c b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
index f44a39c..fd3980c 100644
--- a/drivers/net/ethernet/cisco/enic/enic_ethtool.c
+++ b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
@@ -103,25 +103,29 @@
 	}
 }
 
-static int enic_get_settings(struct net_device *netdev,
-	struct ethtool_cmd *ecmd)
+static int enic_get_ksettings(struct net_device *netdev,
+			      struct ethtool_link_ksettings *ecmd)
 {
 	struct enic *enic = netdev_priv(netdev);
+	struct ethtool_link_settings *base = &ecmd->base;
 
-	ecmd->supported = (SUPPORTED_10000baseT_Full | SUPPORTED_FIBRE);
-	ecmd->advertising = (ADVERTISED_10000baseT_Full | ADVERTISED_FIBRE);
-	ecmd->port = PORT_FIBRE;
-	ecmd->transceiver = XCVR_EXTERNAL;
+	ethtool_link_ksettings_add_link_mode(ecmd, supported,
+					     10000baseT_Full);
+	ethtool_link_ksettings_add_link_mode(ecmd, supported, FIBRE);
+	ethtool_link_ksettings_add_link_mode(ecmd, advertising,
+					     10000baseT_Full);
+	ethtool_link_ksettings_add_link_mode(ecmd, advertising, FIBRE);
+	base->port = PORT_FIBRE;
 
 	if (netif_carrier_ok(netdev)) {
-		ethtool_cmd_speed_set(ecmd, vnic_dev_port_speed(enic->vdev));
-		ecmd->duplex = DUPLEX_FULL;
+		base->speed = vnic_dev_port_speed(enic->vdev);
+		base->duplex = DUPLEX_FULL;
 	} else {
-		ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
-		ecmd->duplex = DUPLEX_UNKNOWN;
+		base->speed = SPEED_UNKNOWN;
+		base->duplex = DUPLEX_UNKNOWN;
 	}
 
-	ecmd->autoneg = AUTONEG_DISABLE;
+	base->autoneg = AUTONEG_DISABLE;
 
 	return 0;
 }
@@ -500,7 +504,6 @@
 }
 
 static const struct ethtool_ops enic_ethtool_ops = {
-	.get_settings = enic_get_settings,
 	.get_drvinfo = enic_get_drvinfo,
 	.get_msglevel = enic_get_msglevel,
 	.set_msglevel = enic_set_msglevel,
@@ -516,6 +519,7 @@
 	.get_rxfh_key_size = enic_get_rxfh_key_size,
 	.get_rxfh = enic_get_rxfh,
 	.set_rxfh = enic_set_rxfh,
+	.get_link_ksettings = enic_get_ksettings,
 };
 
 void enic_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/emulex/benet/Kconfig b/drivers/net/ethernet/emulex/benet/Kconfig
index 7108563..b4853ec 100644
--- a/drivers/net/ethernet/emulex/benet/Kconfig
+++ b/drivers/net/ethernet/emulex/benet/Kconfig
@@ -13,11 +13,3 @@
 	---help---
 	  Say Y here if you want to expose thermal sensor data on
 	  be2net network adapter.
-
-config BE2NET_VXLAN
-        bool "VXLAN offload support on be2net driver"
-        default y
-        depends on BE2NET && VXLAN && !(BE2NET=y && VXLAN=m)
-        ---help---
-	  Say Y here if you want to enable VXLAN offload support on
-	  be2net driver.
diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index fe3763d..e1e6c40 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -97,7 +97,8 @@
 					 * SURF/DPDK
 					 */
 
-#define MAX_RSS_IFACES		15
+#define MAX_PORT_RSS_TABLES	15
+#define MAX_NIC_FUNCS		16
 #define MAX_RX_QS		32
 #define MAX_EVT_QS		32
 #define MAX_TX_QS		32
@@ -444,6 +445,17 @@
 	u16 max_evt_qs;
 	u32 if_cap_flags;
 	u32 vf_if_cap_flags;	/* VF if capability flags */
+	u32 flags;
+	/* Calculated PF Pool's share of RSS Tables. This is not enforced by
+	 * the FW, but is a self-imposed driver limitation.
+	 */
+	u16 max_rss_tables;
+};
+
+/* These are port-wide values */
+struct be_port_resources {
+	u16 max_vfs;
+	u16 nic_pfs;
 };
 
 #define be_is_os2bmc_enabled(adapter) (adapter->flags & BE_FLAGS_OS2BMC)
@@ -634,6 +646,8 @@
 #define be_max_rxqs(adapter)		(adapter->res.max_rx_qs)
 #define be_max_eqs(adapter)		(adapter->res.max_evt_qs)
 #define be_if_cap_flags(adapter)	(adapter->res.if_cap_flags)
+#define be_max_pf_pool_rss_tables(adapter)	\
+				(adapter->pool_res.max_rss_tables)
 
 static inline u16 be_max_qs(struct be_adapter *adapter)
 {
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 22402db..29aeb91 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -4023,7 +4023,10 @@
 		resp = (struct be_cmd_resp_acpi_wol_magic_config_v1 *)cmd.va;
 
 		adapter->wol_cap = resp->wol_settings;
-		if (adapter->wol_cap & BE_WOL_CAP)
+
+		/* Non-zero macaddr indicates WOL is enabled */
+		if (adapter->wol_cap & BE_WOL_CAP &&
+		    !is_zero_ether_addr(resp->magic_mac))
 			adapter->wol_en = true;
 	}
 err:
@@ -4360,9 +4363,35 @@
 	return status;
 }
 
+/* This routine returns a list of all the NIC PF_nums in the adapter */
+u16 be_get_nic_pf_num_list(u8 *buf, u32 desc_count, u16 *nic_pf_nums)
+{
+	struct be_res_desc_hdr *hdr = (struct be_res_desc_hdr *)buf;
+	struct be_pcie_res_desc *pcie = NULL;
+	int i;
+	u16 nic_pf_count = 0;
+
+	for (i = 0; i < desc_count; i++) {
+		if (hdr->desc_type == PCIE_RESOURCE_DESC_TYPE_V0 ||
+		    hdr->desc_type == PCIE_RESOURCE_DESC_TYPE_V1) {
+			pcie = (struct be_pcie_res_desc *)hdr;
+			if (pcie->pf_state && (pcie->pf_type == MISSION_NIC ||
+					       pcie->pf_type == MISSION_RDMA)) {
+				nic_pf_nums[nic_pf_count++] = pcie->pf_num;
+			}
+		}
+
+		hdr->desc_len = hdr->desc_len ? : RESOURCE_DESC_SIZE_V0;
+		hdr = (void *)hdr + hdr->desc_len;
+	}
+	return nic_pf_count;
+}
+
 /* Will use MBOX only if MCCQ has not been created */
 int be_cmd_get_profile_config(struct be_adapter *adapter,
-			      struct be_resources *res, u8 query, u8 domain)
+			      struct be_resources *res,
+			      struct be_port_resources *port_res,
+			      u8 profile_type, u8 query, u8 domain)
 {
 	struct be_cmd_resp_get_profile_config *resp;
 	struct be_cmd_req_get_profile_config *req;
@@ -4389,7 +4418,7 @@
 
 	if (!lancer_chip(adapter))
 		req->hdr.version = 1;
-	req->type = ACTIVE_PROFILE_TYPE;
+	req->type = profile_type;
 	req->hdr.domain = domain;
 
 	/* When QUERY_MODIFIABLE_FIELDS_TYPE bit is set, cmd returns the
@@ -4406,6 +4435,28 @@
 	resp = cmd.va;
 	desc_count = le16_to_cpu(resp->desc_count);
 
+	if (port_res) {
+		u16 nic_pf_cnt = 0, i;
+		u16 nic_pf_num_list[MAX_NIC_FUNCS];
+
+		nic_pf_cnt = be_get_nic_pf_num_list(resp->func_param,
+						    desc_count,
+						    nic_pf_num_list);
+
+		for (i = 0; i < nic_pf_cnt; i++) {
+			nic = be_get_func_nic_desc(resp->func_param, desc_count,
+						   nic_pf_num_list[i]);
+			if (nic->link_param == adapter->port_num) {
+				port_res->nic_pfs++;
+				pcie = be_get_pcie_desc(resp->func_param,
+							desc_count,
+							nic_pf_num_list[i]);
+				port_res->max_vfs += le16_to_cpu(pcie->num_vfs);
+			}
+		}
+		return status;
+	}
+
 	pcie = be_get_pcie_desc(resp->func_param, desc_count,
 				adapter->pf_num);
 	if (pcie)
@@ -4465,7 +4516,7 @@
 }
 
 /* Mark all fields invalid */
-static void be_reset_nic_desc(struct be_nic_res_desc *nic)
+void be_reset_nic_desc(struct be_nic_res_desc *nic)
 {
 	memset(nic, 0, sizeof(*nic));
 	nic->unicast_mac_count = 0xFFFF;
@@ -4534,73 +4585,9 @@
 					 1, version, domain);
 }
 
-static void be_fill_vf_res_template(struct be_adapter *adapter,
-				    struct be_resources pool_res,
-				    u16 num_vfs, u16 num_vf_qs,
-				    struct be_nic_res_desc *nic_vft)
-{
-	u32 vf_if_cap_flags = pool_res.vf_if_cap_flags;
-	struct be_resources res_mod = {0};
-
-	/* Resource with fields set to all '1's by GET_PROFILE_CONFIG cmd,
-	 * which are modifiable using SET_PROFILE_CONFIG cmd.
-	 */
-	be_cmd_get_profile_config(adapter, &res_mod, RESOURCE_MODIFIABLE, 0);
-
-	/* If RSS IFACE capability flags are modifiable for a VF, set the
-	 * capability flag as valid and set RSS and DEFQ_RSS IFACE flags if
-	 * more than 1 RSSQ is available for a VF.
-	 * Otherwise, provision only 1 queue pair for VF.
-	 */
-	if (res_mod.vf_if_cap_flags & BE_IF_FLAGS_RSS) {
-		nic_vft->flags |= BIT(IF_CAPS_FLAGS_VALID_SHIFT);
-		if (num_vf_qs > 1) {
-			vf_if_cap_flags |= BE_IF_FLAGS_RSS;
-			if (pool_res.if_cap_flags & BE_IF_FLAGS_DEFQ_RSS)
-				vf_if_cap_flags |= BE_IF_FLAGS_DEFQ_RSS;
-		} else {
-			vf_if_cap_flags &= ~(BE_IF_FLAGS_RSS |
-					     BE_IF_FLAGS_DEFQ_RSS);
-		}
-	} else {
-		num_vf_qs = 1;
-	}
-
-	if (res_mod.vf_if_cap_flags & BE_IF_FLAGS_VLAN_PROMISCUOUS) {
-		nic_vft->flags |= BIT(IF_CAPS_FLAGS_VALID_SHIFT);
-		vf_if_cap_flags &= ~BE_IF_FLAGS_VLAN_PROMISCUOUS;
-	}
-
-	nic_vft->cap_flags = cpu_to_le32(vf_if_cap_flags);
-	nic_vft->rq_count = cpu_to_le16(num_vf_qs);
-	nic_vft->txq_count = cpu_to_le16(num_vf_qs);
-	nic_vft->rssq_count = cpu_to_le16(num_vf_qs);
-	nic_vft->cq_count = cpu_to_le16(pool_res.max_cq_count /
-					(num_vfs + 1));
-
-	/* Distribute unicast MACs, VLANs, IFACE count and MCCQ count equally
-	 * among the PF and it's VFs, if the fields are changeable
-	 */
-	if (res_mod.max_uc_mac == FIELD_MODIFIABLE)
-		nic_vft->unicast_mac_count = cpu_to_le16(pool_res.max_uc_mac /
-							 (num_vfs + 1));
-
-	if (res_mod.max_vlans == FIELD_MODIFIABLE)
-		nic_vft->vlan_count = cpu_to_le16(pool_res.max_vlans /
-						  (num_vfs + 1));
-
-	if (res_mod.max_iface_count == FIELD_MODIFIABLE)
-		nic_vft->iface_count = cpu_to_le16(pool_res.max_iface_count /
-						   (num_vfs + 1));
-
-	if (res_mod.max_mcc_count == FIELD_MODIFIABLE)
-		nic_vft->mcc_count = cpu_to_le16(pool_res.max_mcc_count /
-						 (num_vfs + 1));
-}
-
 int be_cmd_set_sriov_config(struct be_adapter *adapter,
 			    struct be_resources pool_res, u16 num_vfs,
-			    u16 num_vf_qs)
+			    struct be_resources *vft_res)
 {
 	struct {
 		struct be_pcie_res_desc pcie;
@@ -4620,12 +4607,26 @@
 	be_reset_nic_desc(&desc.nic_vft);
 	desc.nic_vft.hdr.desc_type = NIC_RESOURCE_DESC_TYPE_V1;
 	desc.nic_vft.hdr.desc_len = RESOURCE_DESC_SIZE_V1;
-	desc.nic_vft.flags = BIT(VFT_SHIFT) | BIT(IMM_SHIFT) | BIT(NOSV_SHIFT);
+	desc.nic_vft.flags = vft_res->flags | BIT(VFT_SHIFT) |
+			     BIT(IMM_SHIFT) | BIT(NOSV_SHIFT);
 	desc.nic_vft.pf_num = adapter->pdev->devfn;
 	desc.nic_vft.vf_num = 0;
+	desc.nic_vft.cap_flags = cpu_to_le32(vft_res->vf_if_cap_flags);
+	desc.nic_vft.rq_count = cpu_to_le16(vft_res->max_rx_qs);
+	desc.nic_vft.txq_count = cpu_to_le16(vft_res->max_tx_qs);
+	desc.nic_vft.rssq_count = cpu_to_le16(vft_res->max_rss_qs);
+	desc.nic_vft.cq_count = cpu_to_le16(vft_res->max_cq_count);
 
-	be_fill_vf_res_template(adapter, pool_res, num_vfs, num_vf_qs,
-				&desc.nic_vft);
+	if (vft_res->max_uc_mac)
+		desc.nic_vft.unicast_mac_count =
+					cpu_to_le16(vft_res->max_uc_mac);
+	if (vft_res->max_vlans)
+		desc.nic_vft.vlan_count = cpu_to_le16(vft_res->max_vlans);
+	if (vft_res->max_iface_count)
+		desc.nic_vft.iface_count =
+				cpu_to_le16(vft_res->max_iface_count);
+	if (vft_res->max_mcc_count)
+		desc.nic_vft.mcc_count = cpu_to_le16(vft_res->max_mcc_count);
 
 	return be_cmd_set_profile_config(adapter, &desc,
 					 2 * RESOURCE_DESC_SIZE_V1, 2, 1, 0);
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h
index d8540ae..cb96ddd 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.h
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.h
@@ -1556,7 +1556,9 @@
 	u8 rsvd0[2];
 	u8 wol_settings;
 	u8 rsvd1[5];
-	u32 rsvd2[295];
+	u32 rsvd2[288];
+	u8 magic_mac[6];
+	u8 rsvd3[22];
 } __packed;
 
 #define BE_GET_WOL_CAP			2
@@ -2128,6 +2130,9 @@
 #define IMM_SHIFT				6	/* Immediate */
 #define NOSV_SHIFT				7	/* No save */
 
+#define MISSION_NIC				1
+#define MISSION_RDMA				8
+
 struct be_res_desc_hdr {
 	u8 desc_type;
 	u8 desc_len;
@@ -2244,6 +2249,7 @@
 	struct be_cmd_req_hdr hdr;
 	u8 rsvd;
 #define ACTIVE_PROFILE_TYPE			0x2
+#define SAVED_PROFILE_TYPE			0x0
 #define QUERY_MODIFIABLE_FIELDS_TYPE		BIT(3)
 	u8 type;
 	u16 rsvd1;
@@ -2449,7 +2455,9 @@
 int be_cmd_get_func_config(struct be_adapter *adapter,
 			   struct be_resources *res);
 int be_cmd_get_profile_config(struct be_adapter *adapter,
-			      struct be_resources *res, u8 query, u8 domain);
+			      struct be_resources *res,
+			      struct be_port_resources *port_res,
+			      u8 profile_type, u8 query, 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);
@@ -2461,4 +2469,4 @@
 int be_cmd_manage_iface(struct be_adapter *adapter, u32 iface, u8 op);
 int be_cmd_set_sriov_config(struct be_adapter *adapter,
 			    struct be_resources res, u16 num_vfs,
-			    u16 num_vf_qs);
+			    struct be_resources *vft_res);
diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c
index 2ff6916..c569cd7 100644
--- a/drivers/net/ethernet/emulex/benet/be_ethtool.c
+++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c
@@ -793,6 +793,11 @@
 static int be_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
+	struct device *dev = &adapter->pdev->dev;
+	struct be_dma_mem cmd;
+	u8 mac[ETH_ALEN];
+	bool enable;
+	int status;
 
 	if (wol->wolopts & ~WAKE_MAGIC)
 		return -EOPNOTSUPP;
@@ -802,12 +807,32 @@
 		return -EOPNOTSUPP;
 	}
 
-	if (wol->wolopts & WAKE_MAGIC)
-		adapter->wol_en = true;
-	else
-		adapter->wol_en = false;
+	cmd.size = sizeof(struct be_cmd_req_acpi_wol_magic_config);
+	cmd.va = dma_zalloc_coherent(dev, cmd.size, &cmd.dma, GFP_KERNEL);
+	if (!cmd.va)
+		return -ENOMEM;
 
-	return 0;
+	eth_zero_addr(mac);
+
+	enable = wol->wolopts & WAKE_MAGIC;
+	if (enable)
+		ether_addr_copy(mac, adapter->netdev->dev_addr);
+
+	status = be_cmd_enable_magic_wol(adapter, mac, &cmd);
+	if (status) {
+		dev_err(dev, "Could not set Wake-on-lan mac address\n");
+		status = be_cmd_status(status);
+		goto err;
+	}
+
+	pci_enable_wake(adapter->pdev, PCI_D3hot, enable);
+	pci_enable_wake(adapter->pdev, PCI_D3cold, enable);
+
+	adapter->wol_en = enable ? true : false;
+
+err:
+	dma_free_coherent(dev, cmd.size, cmd.va, cmd.dma);
+	return status;
 }
 
 static int be_test_ddr_dma(struct be_adapter *adapter)
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index ed98ef1..3d94789 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -3625,10 +3625,8 @@
 		be_link_status_update(adapter, link_status);
 
 	netif_tx_start_all_queues(netdev);
-#ifdef CONFIG_BE2NET_VXLAN
 	if (skyhawk_chip(adapter))
-		vxlan_get_rx_port(netdev);
-#endif
+		udp_tunnel_get_rx_info(netdev);
 
 	return 0;
 err:
@@ -3636,40 +3634,6 @@
 	return -EIO;
 }
 
-static int be_setup_wol(struct be_adapter *adapter, bool enable)
-{
-	struct device *dev = &adapter->pdev->dev;
-	struct be_dma_mem cmd;
-	u8 mac[ETH_ALEN];
-	int status;
-
-	eth_zero_addr(mac);
-
-	cmd.size = sizeof(struct be_cmd_req_acpi_wol_magic_config);
-	cmd.va = dma_zalloc_coherent(dev, cmd.size, &cmd.dma, GFP_KERNEL);
-	if (!cmd.va)
-		return -ENOMEM;
-
-	if (enable) {
-		status = pci_write_config_dword(adapter->pdev,
-						PCICFG_PM_CONTROL_OFFSET,
-						PCICFG_PM_CONTROL_MASK);
-		if (status) {
-			dev_err(dev, "Could not enable Wake-on-lan\n");
-			goto err;
-		}
-	} else {
-		ether_addr_copy(mac, adapter->netdev->dev_addr);
-	}
-
-	status = be_cmd_enable_magic_wol(adapter, mac, &cmd);
-	pci_enable_wake(adapter->pdev, PCI_D3hot, enable);
-	pci_enable_wake(adapter->pdev, PCI_D3cold, enable);
-err:
-	dma_free_coherent(dev, cmd.size, cmd.va, cmd.dma);
-	return status;
-}
-
 static void be_vf_eth_addr_generate(struct be_adapter *adapter, u8 *mac)
 {
 	u32 addr;
@@ -3789,7 +3753,6 @@
 	}
 }
 
-#ifdef CONFIG_BE2NET_VXLAN
 static void be_disable_vxlan_offloads(struct be_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
@@ -3808,37 +3771,87 @@
 	netdev->hw_features &= ~(NETIF_F_GSO_UDP_TUNNEL);
 	netdev->features &= ~(NETIF_F_GSO_UDP_TUNNEL);
 }
-#endif
 
-static u16 be_calculate_vf_qs(struct be_adapter *adapter, u16 num_vfs)
+static void be_calculate_vf_res(struct be_adapter *adapter, u16 num_vfs,
+				struct be_resources *vft_res)
 {
 	struct be_resources res = adapter->pool_res;
+	u32 vf_if_cap_flags = res.vf_if_cap_flags;
+	struct be_resources res_mod = {0};
 	u16 num_vf_qs = 1;
 
-	/* Distribute the queue resources among the PF and it's VFs
-	 * Do not distribute queue resources in multi-channel configuration.
-	 */
-	if (num_vfs && !be_is_mc(adapter)) {
-		 /* Divide the qpairs evenly among the VFs and the PF, capped
-		  * at VF-EQ-count. Any remainder qpairs belong to the PF.
-		  */
+	/* Distribute the queue resources among the PF and it's VFs */
+	if (num_vfs) {
+		/* Divide the rx queues evenly among the VFs and the PF, capped
+		 * at VF-EQ-count. Any remainder queues belong to the PF.
+		 */
 		num_vf_qs = min(SH_VF_MAX_NIC_EQS,
 				res.max_rss_qs / (num_vfs + 1));
 
-		/* Skyhawk-R chip supports only MAX_RSS_IFACES RSS capable
-		 * interfaces per port. Provide RSS on VFs, only if number
-		 * of VFs requested is less than MAX_RSS_IFACES limit.
+		/* Skyhawk-R chip supports only MAX_PORT_RSS_TABLES
+		 * RSS Tables per port. Provide RSS on VFs, only if number of
+		 * VFs requested is less than it's PF Pool's RSS Tables limit.
 		 */
-		if (num_vfs >= MAX_RSS_IFACES)
+		if (num_vfs >= be_max_pf_pool_rss_tables(adapter))
 			num_vf_qs = 1;
 	}
-	return num_vf_qs;
+
+	/* Resource with fields set to all '1's by GET_PROFILE_CONFIG cmd,
+	 * which are modifiable using SET_PROFILE_CONFIG cmd.
+	 */
+	be_cmd_get_profile_config(adapter, &res_mod, NULL, ACTIVE_PROFILE_TYPE,
+				  RESOURCE_MODIFIABLE, 0);
+
+	/* If RSS IFACE capability flags are modifiable for a VF, set the
+	 * capability flag as valid and set RSS and DEFQ_RSS IFACE flags if
+	 * more than 1 RSSQ is available for a VF.
+	 * Otherwise, provision only 1 queue pair for VF.
+	 */
+	if (res_mod.vf_if_cap_flags & BE_IF_FLAGS_RSS) {
+		vft_res->flags |= BIT(IF_CAPS_FLAGS_VALID_SHIFT);
+		if (num_vf_qs > 1) {
+			vf_if_cap_flags |= BE_IF_FLAGS_RSS;
+			if (res.if_cap_flags & BE_IF_FLAGS_DEFQ_RSS)
+				vf_if_cap_flags |= BE_IF_FLAGS_DEFQ_RSS;
+		} else {
+			vf_if_cap_flags &= ~(BE_IF_FLAGS_RSS |
+					     BE_IF_FLAGS_DEFQ_RSS);
+		}
+	} else {
+		num_vf_qs = 1;
+	}
+
+	if (res_mod.vf_if_cap_flags & BE_IF_FLAGS_VLAN_PROMISCUOUS) {
+		vft_res->flags |= BIT(IF_CAPS_FLAGS_VALID_SHIFT);
+		vf_if_cap_flags &= ~BE_IF_FLAGS_VLAN_PROMISCUOUS;
+	}
+
+	vft_res->vf_if_cap_flags = vf_if_cap_flags;
+	vft_res->max_rx_qs = num_vf_qs;
+	vft_res->max_rss_qs = num_vf_qs;
+	vft_res->max_tx_qs = res.max_tx_qs / (num_vfs + 1);
+	vft_res->max_cq_count = res.max_cq_count / (num_vfs + 1);
+
+	/* Distribute unicast MACs, VLANs, IFACE count and MCCQ count equally
+	 * among the PF and it's VFs, if the fields are changeable
+	 */
+	if (res_mod.max_uc_mac == FIELD_MODIFIABLE)
+		vft_res->max_uc_mac = res.max_uc_mac / (num_vfs + 1);
+
+	if (res_mod.max_vlans == FIELD_MODIFIABLE)
+		vft_res->max_vlans = res.max_vlans / (num_vfs + 1);
+
+	if (res_mod.max_iface_count == FIELD_MODIFIABLE)
+		vft_res->max_iface_count = res.max_iface_count / (num_vfs + 1);
+
+	if (res_mod.max_mcc_count == FIELD_MODIFIABLE)
+		vft_res->max_mcc_count = res.max_mcc_count / (num_vfs + 1);
 }
 
 static int be_clear(struct be_adapter *adapter)
 {
 	struct pci_dev *pdev = adapter->pdev;
-	u16 num_vf_qs;
+	struct  be_resources vft_res = {0};
 
 	be_cancel_worker(adapter);
 
@@ -3850,16 +3863,15 @@
 	 */
 	if (skyhawk_chip(adapter) && be_physfn(adapter) &&
 	    !pci_vfs_assigned(pdev)) {
-		num_vf_qs = be_calculate_vf_qs(adapter,
-					       pci_sriov_get_totalvfs(pdev));
+		be_calculate_vf_res(adapter,
+				    pci_sriov_get_totalvfs(pdev),
+				    &vft_res);
 		be_cmd_set_sriov_config(adapter, adapter->pool_res,
 					pci_sriov_get_totalvfs(pdev),
-					num_vf_qs);
+					&vft_res);
 	}
 
-#ifdef CONFIG_BE2NET_VXLAN
 	be_disable_vxlan_offloads(adapter);
-#endif
 	kfree(adapter->pmac_id);
 	adapter->pmac_id = NULL;
 
@@ -3884,7 +3896,8 @@
 
 	for_all_vfs(adapter, vf_cfg, vf) {
 		if (!BE3_chip(adapter)) {
-			status = be_cmd_get_profile_config(adapter, &res,
+			status = be_cmd_get_profile_config(adapter, &res, NULL,
+							   ACTIVE_PROFILE_TYPE,
 							   RESOURCE_LIMITS,
 							   vf + 1);
 			if (!status) {
@@ -4069,8 +4082,9 @@
 		/* On a SuperNIC profile, the driver needs to use the
 		 * GET_PROFILE_CONFIG cmd to query the per-function TXQ limits
 		 */
-		be_cmd_get_profile_config(adapter, &super_nic_res,
-					  RESOURCE_LIMITS, 0);
+		be_cmd_get_profile_config(adapter, &super_nic_res, NULL,
+					  ACTIVE_PROFILE_TYPE, RESOURCE_LIMITS,
+					  0);
 		/* Some old versions of BE3 FW don't report max_tx_qs value */
 		res->max_tx_qs = super_nic_res.max_tx_qs ? : BE3_MAX_TX_QS;
 	} else {
@@ -4109,12 +4123,38 @@
 		adapter->cmd_privileges = MIN_PRIVILEGES;
 }
 
+/* HW supports only MAX_PORT_RSS_TABLES RSS Policy Tables per port.
+ * However, this HW limitation is not exposed to the host via any SLI cmd.
+ * As a result, in the case of SRIOV and in particular multi-partition configs
+ * the driver needs to calcuate a proportional share of RSS Tables per PF-pool
+ * for distribution between the VFs. This self-imposed limit will determine the
+ * no: of VFs for which RSS can be enabled.
+ */
+void be_calculate_pf_pool_rss_tables(struct be_adapter *adapter)
+{
+	struct be_port_resources port_res = {0};
+	u8 rss_tables_on_port;
+	u16 max_vfs = be_max_vfs(adapter);
+
+	be_cmd_get_profile_config(adapter, NULL, &port_res, SAVED_PROFILE_TYPE,
+				  RESOURCE_LIMITS, 0);
+
+	rss_tables_on_port = MAX_PORT_RSS_TABLES - port_res.nic_pfs;
+
+	/* Each PF Pool's RSS Tables limit =
+	 * PF's Max VFs / Total_Max_VFs on Port * RSS Tables on Port
+	 */
+	adapter->pool_res.max_rss_tables =
+		max_vfs * rss_tables_on_port / port_res.max_vfs;
+}
+
 static int be_get_sriov_config(struct be_adapter *adapter)
 {
 	struct be_resources res = {0};
 	int max_vfs, old_vfs;
 
-	be_cmd_get_profile_config(adapter, &res, RESOURCE_LIMITS, 0);
+	be_cmd_get_profile_config(adapter, &res, NULL, ACTIVE_PROFILE_TYPE,
+				  RESOURCE_LIMITS, 0);
 
 	/* Some old versions of BE3 FW don't report max_vfs value */
 	if (BE3_chip(adapter) && !res.max_vfs) {
@@ -4138,13 +4178,19 @@
 		adapter->num_vfs = old_vfs;
 	}
 
+	if (skyhawk_chip(adapter) && be_max_vfs(adapter) && !old_vfs) {
+		be_calculate_pf_pool_rss_tables(adapter);
+		dev_info(&adapter->pdev->dev,
+			 "RSS can be enabled for all VFs if num_vfs <= %d\n",
+			 be_max_pf_pool_rss_tables(adapter));
+	}
 	return 0;
 }
 
 static void be_alloc_sriov_res(struct be_adapter *adapter)
 {
 	int old_vfs = pci_num_vf(adapter->pdev);
-	u16 num_vf_qs;
+	struct  be_resources vft_res = {0};
 	int status;
 
 	be_get_sriov_config(adapter);
@@ -4158,9 +4204,9 @@
 	 * Also, this is done by FW in Lancer chip.
 	 */
 	if (skyhawk_chip(adapter) && be_max_vfs(adapter) && !old_vfs) {
-		num_vf_qs = be_calculate_vf_qs(adapter, 0);
+		be_calculate_vf_res(adapter, 0, &vft_res);
 		status = be_cmd_set_sriov_config(adapter, adapter->pool_res, 0,
-						 num_vf_qs);
+						 &vft_res);
 		if (status)
 			dev_err(&adapter->pdev->dev,
 				"Failed to optimize SRIOV resources\n");
@@ -4241,6 +4287,8 @@
 	}
 
 	be_cmd_get_acpi_wol_cap(adapter);
+	pci_enable_wake(adapter->pdev, PCI_D3hot, adapter->wol_en);
+	pci_enable_wake(adapter->pdev, PCI_D3cold, adapter->wol_en);
 
 	be_cmd_query_port_name(adapter);
 
@@ -4251,15 +4299,6 @@
 				 "Using profile 0x%x\n", profile_id);
 	}
 
-	status = be_get_resources(adapter);
-	if (status)
-		return status;
-
-	adapter->pmac_id = kcalloc(be_max_uc(adapter),
-				   sizeof(*adapter->pmac_id), GFP_KERNEL);
-	if (!adapter->pmac_id)
-		return -ENOMEM;
-
 	return 0;
 }
 
@@ -4460,13 +4499,22 @@
 			return status;
 	}
 
-	if (!BE2_chip(adapter) && be_physfn(adapter))
-		be_alloc_sriov_res(adapter);
-
 	status = be_get_config(adapter);
 	if (status)
 		goto err;
 
+	if (!BE2_chip(adapter) && be_physfn(adapter))
+		be_alloc_sriov_res(adapter);
+
+	status = be_get_resources(adapter);
+	if (status)
+		goto err;
+
+	adapter->pmac_id = kcalloc(be_max_uc(adapter),
+				   sizeof(*adapter->pmac_id), GFP_KERNEL);
+	if (!adapter->pmac_id)
+		return -ENOMEM;
+
 	status = be_msix_enable(adapter);
 	if (status)
 		goto err;
@@ -4651,7 +4699,6 @@
 				       0, 0, nlflags, filter_mask, NULL);
 }
 
-#ifdef CONFIG_BE2NET_VXLAN
 /* VxLAN offload Notes:
  *
  * The stack defines tunnel offload flags (hw_enc_features) for IP and doesn't
@@ -4666,13 +4713,17 @@
  * adds more than one port, disable offloads and don't re-enable them again
  * until after all the tunnels are removed.
  */
-static void be_add_vxlan_port(struct net_device *netdev, sa_family_t sa_family,
-			      __be16 port)
+static void be_add_vxlan_port(struct net_device *netdev,
+			      struct udp_tunnel_info *ti)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 	struct device *dev = &adapter->pdev->dev;
+	__be16 port = ti->port;
 	int status;
 
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
+		return;
+
 	if (lancer_chip(adapter) || BEx_chip(adapter) || be_is_mc(adapter))
 		return;
 
@@ -4720,10 +4771,14 @@
 	be_disable_vxlan_offloads(adapter);
 }
 
-static void be_del_vxlan_port(struct net_device *netdev, sa_family_t sa_family,
-			      __be16 port)
+static void be_del_vxlan_port(struct net_device *netdev,
+			      struct udp_tunnel_info *ti)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
+	__be16 port = ti->port;
+
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
+		return;
 
 	if (lancer_chip(adapter) || BEx_chip(adapter) || be_is_mc(adapter))
 		return;
@@ -4785,7 +4840,6 @@
 
 	return features;
 }
-#endif
 
 static int be_get_phys_port_id(struct net_device *dev,
 			       struct netdev_phys_item_id *ppid)
@@ -4833,11 +4887,9 @@
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	.ndo_busy_poll		= be_busy_poll,
 #endif
-#ifdef CONFIG_BE2NET_VXLAN
-	.ndo_add_vxlan_port	= be_add_vxlan_port,
-	.ndo_del_vxlan_port	= be_del_vxlan_port,
+	.ndo_udp_tunnel_add	= be_add_vxlan_port,
+	.ndo_udp_tunnel_del	= be_del_vxlan_port,
 	.ndo_features_check	= be_features_check,
-#endif
 	.ndo_get_phys_port_id   = be_get_phys_port_id,
 };
 
@@ -5410,9 +5462,6 @@
 {
 	struct be_adapter *adapter = pci_get_drvdata(pdev);
 
-	if (adapter->wol_en)
-		be_setup_wol(adapter, true);
-
 	be_intr_set(adapter, false);
 	be_cancel_err_detection(adapter);
 
@@ -5441,9 +5490,6 @@
 
 	be_schedule_err_detection(adapter, ERR_DETECTION_DELAY);
 
-	if (adapter->wol_en)
-		be_setup_wol(adapter, false);
-
 	return 0;
 }
 
@@ -5552,7 +5598,7 @@
 static int be_pci_sriov_configure(struct pci_dev *pdev, int num_vfs)
 {
 	struct be_adapter *adapter = pci_get_drvdata(pdev);
-	u16 num_vf_qs;
+	struct be_resources vft_res = {0};
 	int status;
 
 	if (!num_vfs)
@@ -5575,9 +5621,10 @@
 	 * Also, this is done by FW in Lancer chip.
 	 */
 	if (skyhawk_chip(adapter) && !pci_num_vf(pdev)) {
-		num_vf_qs = be_calculate_vf_qs(adapter, adapter->num_vfs);
+		be_calculate_vf_res(adapter, adapter->num_vfs,
+				    &vft_res);
 		status = be_cmd_set_sriov_config(adapter, adapter->pool_res,
-						 adapter->num_vfs, num_vf_qs);
+						 adapter->num_vfs, &vft_res);
 		if (status)
 			dev_err(&pdev->dev,
 				"Failed to optimize SR-IOV resources\n");
diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c
index 41b01064..4edb98c 100644
--- a/drivers/net/ethernet/ethoc.c
+++ b/drivers/net/ethernet/ethoc.c
@@ -1195,7 +1195,7 @@
 	priv->mdio = mdiobus_alloc();
 	if (!priv->mdio) {
 		ret = -ENOMEM;
-		goto free;
+		goto free2;
 	}
 
 	priv->mdio->name = "ethoc-mdio";
@@ -1208,7 +1208,7 @@
 	ret = mdiobus_register(priv->mdio);
 	if (ret) {
 		dev_err(&netdev->dev, "failed to register MDIO bus\n");
-		goto free;
+		goto free2;
 	}
 
 	ret = ethoc_mdio_probe(netdev);
@@ -1241,9 +1241,10 @@
 error:
 	mdiobus_unregister(priv->mdio);
 	mdiobus_free(priv->mdio);
-free:
+free2:
 	if (priv->clk)
 		clk_disable_unprepare(priv->clk);
+free:
 	free_netdev(netdev);
 out:
 	return ret;
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 3c0255e..c36401e 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -2416,24 +2416,24 @@
 		return -EOPNOTSUPP;
 
 	if (ec->rx_max_coalesced_frames > 255) {
-		pr_err("Rx coalesced frames exceed hardware limiation");
+		pr_err("Rx coalesced frames exceed hardware limitation\n");
 		return -EINVAL;
 	}
 
 	if (ec->tx_max_coalesced_frames > 255) {
-		pr_err("Tx coalesced frame exceed hardware limiation");
+		pr_err("Tx coalesced frame exceed hardware limitation\n");
 		return -EINVAL;
 	}
 
 	cycle = fec_enet_us_to_itr_clock(ndev, fep->rx_time_itr);
 	if (cycle > 0xFFFF) {
-		pr_err("Rx coalesed usec exceeed hardware limiation");
+		pr_err("Rx coalesced usec exceed hardware limitation\n");
 		return -EINVAL;
 	}
 
 	cycle = fec_enet_us_to_itr_clock(ndev, fep->tx_time_itr);
 	if (cycle > 0xFFFF) {
-		pr_err("Rx coalesed usec exceeed hardware limiation");
+		pr_err("Rx coalesced usec exceed hardware limitation\n");
 		return -EINVAL;
 	}
 
@@ -3191,7 +3191,12 @@
 		dev_err(&pdev->dev, "failed to get phy-reset-gpios: %d\n", err);
 		return;
 	}
-	msleep(msec);
+
+	if (msec > 20)
+		msleep(msec);
+	else
+		usleep_range(msec * 1000, msec * 1000 + 1000);
+
 	gpio_set_value_cansleep(phy_reset, !active_high);
 }
 #else /* CONFIG_OF */
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 7615e06..d20935d 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -2275,7 +2275,7 @@
 	fcb->flags = flags;
 }
 
-void inline gfar_tx_vlan(struct sk_buff *skb, struct txfcb *fcb)
+static inline void gfar_tx_vlan(struct sk_buff *skb, struct txfcb *fcb)
 {
 	fcb->flags |= TXFCB_VLN;
 	fcb->vlctl = cpu_to_be16(skb_vlan_tag_get(skb));
@@ -2440,7 +2440,8 @@
 						 tx_queue->tx_ring_size);
 
 	if (likely(!nr_frags)) {
-		lstatus |= BD_LFLAG(TXBD_LAST | TXBD_INTERRUPT);
+		if (likely(!do_tstamp))
+			lstatus |= BD_LFLAG(TXBD_LAST | TXBD_INTERRUPT);
 	} else {
 		u32 lstatus_start = lstatus;
 
diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig
index 4ccc032..2e25662 100644
--- a/drivers/net/ethernet/hisilicon/Kconfig
+++ b/drivers/net/ethernet/hisilicon/Kconfig
@@ -5,7 +5,7 @@
 config NET_VENDOR_HISILICON
 	bool "Hisilicon devices"
 	default y
-	depends on OF && HAS_DMA
+	depends on (OF || ACPI) && HAS_DMA
 	depends on ARM || ARM64 || COMPILE_TEST
 	---help---
 	  If you have a network (Ethernet) card belonging to this class, say Y.
diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c
index 3bfe36f..c54c6fa 100644
--- a/drivers/net/ethernet/hisilicon/hns/hnae.c
+++ b/drivers/net/ethernet/hisilicon/hns/hnae.c
@@ -96,16 +96,22 @@
 {
 	struct hnae_ae_dev *hdev = cls_to_ae_dev(dev);
 
-	return hdev->dev->of_node == data;
+	if (dev_of_node(hdev->dev))
+		return (data == &hdev->dev->of_node->fwnode);
+	else if (is_acpi_node(hdev->dev->fwnode))
+		return (data == hdev->dev->fwnode);
+
+	dev_err(dev, "__ae_match cannot read cfg data from OF or acpi\n");
+	return 0;
 }
 
-static struct hnae_ae_dev *find_ae(const struct device_node *ae_node)
+static struct hnae_ae_dev *find_ae(const struct fwnode_handle *fwnode)
 {
 	struct device *dev;
 
-	WARN_ON(!ae_node);
+	WARN_ON(!fwnode);
 
-	dev = class_find_device(hnae_class, NULL, ae_node, __ae_match);
+	dev = class_find_device(hnae_class, NULL, fwnode, __ae_match);
 
 	return dev ? cls_to_ae_dev(dev) : NULL;
 }
@@ -312,7 +318,7 @@
  * return handle ptr or ERR_PTR
  */
 struct hnae_handle *hnae_get_handle(struct device *owner_dev,
-				    const struct device_node *ae_node,
+				    const struct fwnode_handle	*fwnode,
 				    u32 port_id,
 				    struct hnae_buf_ops *bops)
 {
@@ -321,7 +327,7 @@
 	int i, j;
 	int ret;
 
-	dev = find_ae(ae_node);
+	dev = find_ae(fwnode);
 	if (!dev)
 		return ERR_PTR(-ENODEV);
 
@@ -394,7 +400,6 @@
 
 	if (!hdev->ops || !hdev->ops->get_handle ||
 	    !hdev->ops->toggle_ring_irq ||
-	    !hdev->ops->toggle_queue_status ||
 	    !hdev->ops->get_status || !hdev->ops->adjust_link)
 		return -EINVAL;
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h
index e8d36aa..3869322 100644
--- a/drivers/net/ethernet/hisilicon/hns/hnae.h
+++ b/drivers/net/ethernet/hisilicon/hns/hnae.h
@@ -27,6 +27,7 @@
  * "cb" means control block
  */
 
+#include <linux/acpi.h>
 #include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/module.h>
@@ -453,7 +454,6 @@
 	int (*get_info)(struct hnae_handle *handle,
 			u8 *auto_neg, u16 *speed, u8 *duplex);
 	void (*toggle_ring_irq)(struct hnae_ring *ring, u32 val);
-	void (*toggle_queue_status)(struct hnae_queue *queue, u32 val);
 	void (*adjust_link)(struct hnae_handle *handle, int speed, int duplex);
 	int (*set_loopback)(struct hnae_handle *handle,
 			    enum hnae_loop loop_mode, int en);
@@ -472,6 +472,11 @@
 	int (*set_coalesce_usecs)(struct hnae_handle *handle, u32 timeout);
 	int (*set_coalesce_frames)(struct hnae_handle *handle,
 				   u32 coalesce_frames);
+	void (*get_coalesce_range)(struct hnae_handle *handle,
+				   u32 *tx_frames_low, u32 *rx_frames_low,
+				   u32 *tx_frames_high, u32 *rx_frames_high,
+				   u32 *tx_usecs_low, u32 *rx_usecs_low,
+				   u32 *tx_usecs_high, u32 *rx_usecs_high);
 	void (*set_promisc_mode)(struct hnae_handle *handle, u32 en);
 	int (*get_mac_addr)(struct hnae_handle *handle, void **p);
 	int (*set_mac_addr)(struct hnae_handle *handle, void *p);
@@ -512,7 +517,7 @@
 struct hnae_handle {
 	struct device *owner_dev; /* the device which make use of this handle */
 	struct hnae_ae_dev *dev;  /* the device who provides this handle */
-	struct device_node *phy_node;
+	struct phy_device *phy_dev;
 	phy_interface_t phy_if;
 	u32 if_support;
 	int q_num;
@@ -528,7 +533,7 @@
 #define ring_to_dev(ring) ((ring)->q->dev->dev)
 
 struct hnae_handle *hnae_get_handle(struct device *owner_dev,
-				    const struct device_node *ae_node,
+				    const struct fwnode_handle	*fwnode,
 				    u32 port_id,
 				    struct hnae_buf_ops *bops);
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
index 7a757e8..835521b 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
@@ -131,7 +131,7 @@
 	vf_cb->mac_cb = dsaf_dev->mac_cb[port_id];
 
 	ae_handle->phy_if = vf_cb->mac_cb->phy_if;
-	ae_handle->phy_node = vf_cb->mac_cb->phy_node;
+	ae_handle->phy_dev = vf_cb->mac_cb->phy_dev;
 	ae_handle->if_support = vf_cb->mac_cb->if_support;
 	ae_handle->port_type = vf_cb->mac_cb->mac_type;
 	ae_handle->dport_id = port_id;
@@ -247,12 +247,21 @@
 static int hns_ae_start(struct hnae_handle *handle)
 {
 	int ret;
+	int k;
 	struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle);
 
 	ret = hns_mac_vm_config_bc_en(mac_cb, 0, true);
 	if (ret)
 		return ret;
 
+	for (k = 0; k < handle->q_num; k++) {
+		if (AE_IS_VER1(mac_cb->dsaf_dev->dsaf_ver))
+			hns_rcb_int_clr_hw(handle->qs[k],
+					   RCB_INT_FLAG_TX | RCB_INT_FLAG_RX);
+		else
+			hns_rcbv2_int_clr_hw(handle->qs[k],
+					     RCB_INT_FLAG_TX | RCB_INT_FLAG_RX);
+	}
 	hns_ae_ring_enable_all(handle, 1);
 	msleep(100);
 
@@ -313,18 +322,6 @@
 	hns_rcbv2_int_ctrl_hw(ring->q, flag, mask);
 }
 
-static void hns_ae_toggle_queue_status(struct hnae_queue *queue, u32 val)
-{
-	struct dsaf_device *dsaf_dev = hns_ae_get_dsaf_dev(queue->dev);
-
-	if (AE_IS_VER1(dsaf_dev->dsaf_ver))
-		hns_rcb_int_clr_hw(queue, RCB_INT_FLAG_TX | RCB_INT_FLAG_RX);
-	else
-		hns_rcbv2_int_clr_hw(queue, RCB_INT_FLAG_TX | RCB_INT_FLAG_RX);
-
-	hns_rcb_start(queue, val);
-}
-
 static int hns_ae_get_link_status(struct hnae_handle *handle)
 {
 	u32 link_status;
@@ -465,6 +462,30 @@
 		ring_pair->port_id_in_comm, coalesce_frames);
 }
 
+static void hns_ae_get_coalesce_range(struct hnae_handle *handle,
+				      u32 *tx_frames_low, u32 *rx_frames_low,
+				      u32 *tx_frames_high, u32 *rx_frames_high,
+				      u32 *tx_usecs_low, u32 *rx_usecs_low,
+				      u32 *tx_usecs_high, u32 *rx_usecs_high)
+{
+	struct dsaf_device *dsaf_dev;
+
+	dsaf_dev = hns_ae_get_dsaf_dev(handle->dev);
+
+	*tx_frames_low  = HNS_RCB_MIN_COALESCED_FRAMES;
+	*rx_frames_low  = HNS_RCB_MIN_COALESCED_FRAMES;
+	*tx_frames_high =
+		(dsaf_dev->desc_num - 1 > HNS_RCB_MAX_COALESCED_FRAMES) ?
+		HNS_RCB_MAX_COALESCED_FRAMES : dsaf_dev->desc_num - 1;
+	*rx_frames_high =
+		(dsaf_dev->desc_num - 1 > HNS_RCB_MAX_COALESCED_FRAMES) ?
+		 HNS_RCB_MAX_COALESCED_FRAMES : dsaf_dev->desc_num - 1;
+	*tx_usecs_low   = 0;
+	*rx_usecs_low   = 0;
+	*tx_usecs_high  = HNS_RCB_MAX_COALESCED_USECS;
+	*rx_usecs_high  = HNS_RCB_MAX_COALESCED_USECS;
+}
+
 void hns_ae_update_stats(struct hnae_handle *handle,
 			 struct net_device_stats *net_stats)
 {
@@ -587,6 +608,7 @@
 	int idx;
 	struct hns_mac_cb *mac_cb;
 	struct hns_ppe_cb *ppe_cb;
+	struct dsaf_device *dsaf_dev = hns_ae_get_dsaf_dev(handle->dev);
 	u8 *p = data;
 	struct	hnae_vf_cb *vf_cb;
 
@@ -609,13 +631,14 @@
 	p += ETH_GSTRING_LEN * hns_mac_get_sset_count(mac_cb, stringset);
 
 	if (mac_cb->mac_type == HNAE_PORT_SERVICE)
-		hns_dsaf_get_strings(stringset, p, port);
+		hns_dsaf_get_strings(stringset, p, port, dsaf_dev);
 }
 
 int hns_ae_get_sset_count(struct hnae_handle *handle, int stringset)
 {
 	u32 sset_count = 0;
 	struct hns_mac_cb *mac_cb;
+	struct dsaf_device *dsaf_dev = hns_ae_get_dsaf_dev(handle->dev);
 
 	assert(handle);
 
@@ -626,7 +649,7 @@
 	sset_count += hns_mac_get_sset_count(mac_cb, stringset);
 
 	if (mac_cb->mac_type == HNAE_PORT_SERVICE)
-		sset_count += hns_dsaf_get_sset_count(stringset);
+		sset_count += hns_dsaf_get_sset_count(dsaf_dev, stringset);
 
 	return sset_count;
 }
@@ -637,13 +660,15 @@
 	int ret;
 	struct hnae_vf_cb *vf_cb = hns_ae_get_vf_cb(handle);
 	struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle);
+	struct dsaf_device *dsaf_dev = mac_cb->dsaf_dev;
 
 	switch (loop) {
 	case MAC_INTERNALLOOP_PHY:
 		ret = 0;
 		break;
 	case MAC_INTERNALLOOP_SERDES:
-		ret = hns_mac_config_sds_loopback(vf_cb->mac_cb, en);
+		ret = dsaf_dev->misc_op->cfg_serdes_loopback(vf_cb->mac_cb,
+							     !!en);
 		break;
 	case MAC_INTERNALLOOP_MAC:
 		ret = hns_mac_config_mac_loopback(vf_cb->mac_cb, loop, en);
@@ -780,7 +805,6 @@
 	.stop = hns_ae_stop,
 	.reset = hns_ae_reset,
 	.toggle_ring_irq = hns_ae_toggle_ring_irq,
-	.toggle_queue_status = hns_ae_toggle_queue_status,
 	.get_status = hns_ae_get_link_status,
 	.get_info = hns_ae_get_mac_info,
 	.adjust_link = hns_ae_adjust_link,
@@ -794,6 +818,7 @@
 	.get_rx_max_coalesced_frames = hns_ae_get_rx_max_coalesced_frames,
 	.set_coalesce_usecs = hns_ae_set_coalesce_usecs,
 	.set_coalesce_frames = hns_ae_set_coalesce_frames,
+	.get_coalesce_range = hns_ae_get_coalesce_range,
 	.set_promisc_mode = hns_ae_set_promisc_mode,
 	.set_mac_addr = hns_ae_set_mac_address,
 	.set_mc_addr = hns_ae_set_multicast_one,
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c
index 44abb08..1235c7f 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c
@@ -110,7 +110,7 @@
 
 	u32 mac_id = drv->mac_id;
 
-	hns_dsaf_ge_srst_by_port(dsaf_dev, mac_id, 0);
+	dsaf_dev->misc_op->ge_srst(dsaf_dev, mac_id, 0);
 }
 
 static void hns_gmac_set_tx_auto_pause_frames(void *mac_drv, u16 newval)
@@ -317,9 +317,9 @@
 
 	port = drv->mac_id;
 
-	hns_dsaf_ge_srst_by_port(dsaf_dev, port, 0);
+	dsaf_dev->misc_op->ge_srst(dsaf_dev, port, 0);
 	mdelay(10);
-	hns_dsaf_ge_srst_by_port(dsaf_dev, port, 1);
+	dsaf_dev->misc_op->ge_srst(dsaf_dev, port, 1);
 	mdelay(10);
 	hns_gmac_disable(mac_drv, MAC_COMM_MODE_RX_AND_TX);
 	hns_gmac_tx_loop_pkt_dis(mac_drv);
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
index 611581f..c526558 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
@@ -7,6 +7,7 @@
  * (at your option) any later version.
  */
 
+#include <linux/acpi.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
@@ -15,7 +16,8 @@
 #include <linux/netdevice.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
-#include <linux/phy_fixed.h>
+#include <linux/of_mdio.h>
+#include <linux/phy.h>
 #include <linux/platform_device.h>
 
 #include "hns_dsaf_main.h"
@@ -94,7 +96,7 @@
 	else
 		*link_status = 0;
 
-	ret = hns_mac_get_sfp_prsnt(mac_cb, &sfp_prsnt);
+	ret = mac_cb->dsaf_dev->misc_op->get_sfp_prsnt(mac_cb, &sfp_prsnt);
 	if (!ret)
 		*link_status = *link_status && sfp_prsnt;
 
@@ -511,7 +513,7 @@
 
 	mac_ctrl_drv->mac_en_flg = 0;
 	mac_cb->link = 0;
-	cpld_led_reset(mac_cb);
+	mac_cb->dsaf_dev->misc_op->cpld_reset_led(mac_cb);
 }
 
 /**
@@ -637,6 +639,115 @@
 	return ret;
 }
 
+static int
+hns_mac_phy_parse_addr(struct device *dev, struct fwnode_handle *fwnode)
+{
+	u32 addr;
+	int ret;
+
+	ret = fwnode_property_read_u32(fwnode, "phy-addr", &addr);
+	if (ret) {
+		dev_err(dev, "has invalid PHY address ret:%d\n", ret);
+		return ret;
+	}
+
+	if (addr >= PHY_MAX_ADDR) {
+		dev_err(dev, "PHY address %i is too large\n", addr);
+		return -EINVAL;
+	}
+
+	return addr;
+}
+
+static int hns_mac_phydev_match(struct device *dev, void *fwnode)
+{
+	return dev->fwnode == fwnode;
+}
+
+static struct
+platform_device *hns_mac_find_platform_device(struct fwnode_handle *fwnode)
+{
+	struct device *dev;
+
+	dev = bus_find_device(&platform_bus_type, NULL,
+			      fwnode, hns_mac_phydev_match);
+	return dev ? to_platform_device(dev) : NULL;
+}
+
+static int
+hns_mac_register_phydev(struct mii_bus *mdio, struct hns_mac_cb *mac_cb,
+			u32 addr)
+{
+	struct phy_device *phy;
+	const char *phy_type;
+	bool is_c45;
+	int rc;
+
+	rc = fwnode_property_read_string(mac_cb->fw_port,
+					 "phy-mode", &phy_type);
+	if (rc < 0)
+		return rc;
+
+	if (!strcmp(phy_type, phy_modes(PHY_INTERFACE_MODE_XGMII)))
+		is_c45 = 1;
+	else if (!strcmp(phy_type, phy_modes(PHY_INTERFACE_MODE_SGMII)))
+		is_c45 = 0;
+	else
+		return -ENODATA;
+
+	phy = get_phy_device(mdio, addr, is_c45);
+	if (!phy || IS_ERR(phy))
+		return -EIO;
+
+	if (mdio->irq)
+		phy->irq = mdio->irq[addr];
+
+	/* All data is now stored in the phy struct;
+	 * register it
+	 */
+	rc = phy_device_register(phy);
+	if (rc) {
+		phy_device_free(phy);
+		return -ENODEV;
+	}
+
+	mac_cb->phy_dev = phy;
+
+	dev_dbg(&mdio->dev, "registered phy at address %i\n", addr);
+
+	return 0;
+}
+
+static void hns_mac_register_phy(struct hns_mac_cb *mac_cb)
+{
+	struct acpi_reference_args args;
+	struct platform_device *pdev;
+	struct mii_bus *mii_bus;
+	int rc;
+	int addr;
+
+	/* Loop over the child nodes and register a phy_device for each one */
+	if (!to_acpi_device_node(mac_cb->fw_port))
+		return;
+
+	rc = acpi_node_get_property_reference(
+			mac_cb->fw_port, "mdio-node", 0, &args);
+	if (rc)
+		return;
+
+	addr = hns_mac_phy_parse_addr(mac_cb->dev, mac_cb->fw_port);
+	if (addr < 0)
+		return;
+
+	/* dev address in adev */
+	pdev = hns_mac_find_platform_device(acpi_fwnode_handle(args.adev));
+	mii_bus = platform_get_drvdata(pdev);
+	rc = hns_mac_register_phydev(mii_bus, mac_cb, addr);
+	if (!rc)
+		dev_dbg(mac_cb->dev, "mac%d register phy addr:%d\n",
+			mac_cb->mac_id, addr);
+}
+
 /**
  *hns_mac_get_info  - get mac information from device node
  *@mac_cb: mac device
@@ -645,7 +756,7 @@
  */
 static int  hns_mac_get_info(struct hns_mac_cb *mac_cb)
 {
-	struct device_node *np = mac_cb->dev->of_node;
+	struct device_node *np;
 	struct regmap *syscon;
 	struct of_phandle_args cpld_args;
 	u32 ret;
@@ -672,63 +783,85 @@
 	 * from dsaf node
 	 */
 	if (!mac_cb->fw_port) {
-		mac_cb->phy_node = of_parse_phandle(np, "phy-handle",
-						    mac_cb->mac_id);
-		if (mac_cb->phy_node)
+		np = of_parse_phandle(mac_cb->dev->of_node, "phy-handle",
+				      mac_cb->mac_id);
+		mac_cb->phy_dev = of_phy_find_device(np);
+		if (mac_cb->phy_dev) {
+			/* refcount is held by of_phy_find_device()
+			 * if the phy_dev is found
+			 */
+			put_device(&mac_cb->phy_dev->mdio.dev);
+
 			dev_dbg(mac_cb->dev, "mac%d phy_node: %s\n",
-				mac_cb->mac_id, mac_cb->phy_node->name);
+				mac_cb->mac_id, np->name);
+		}
+
 		return 0;
 	}
-	if (!is_of_node(mac_cb->fw_port))
-		return -EINVAL;
-	/* parse property from port subnode in dsaf */
-	mac_cb->phy_node = of_parse_phandle(to_of_node(mac_cb->fw_port),
-					    "phy-handle", 0);
-	if (mac_cb->phy_node)
-		dev_dbg(mac_cb->dev, "mac%d phy_node: %s\n",
-			mac_cb->mac_id, mac_cb->phy_node->name);
-	syscon = syscon_node_to_regmap(
-			of_parse_phandle(to_of_node(mac_cb->fw_port),
-					 "serdes-syscon", 0));
-	if (IS_ERR_OR_NULL(syscon)) {
-		dev_err(mac_cb->dev, "serdes-syscon is needed!\n");
-		return -EINVAL;
-	}
-	mac_cb->serdes_ctrl = syscon;
 
-	ret = fwnode_property_read_u32(mac_cb->fw_port,
-				       "port-rst-offset",
-				       &mac_cb->port_rst_off);
-	if (ret) {
-		dev_dbg(mac_cb->dev,
-			"mac%d port-rst-offset not found, use default value.\n",
-			mac_cb->mac_id);
-	}
+	if (is_of_node(mac_cb->fw_port)) {
+		/* parse property from port subnode in dsaf */
+		np = of_parse_phandle(to_of_node(mac_cb->fw_port),
+				      "phy-handle", 0);
+		mac_cb->phy_dev = of_phy_find_device(np);
+		if (mac_cb->phy_dev) {
+			/* refcount is held by of_phy_find_device()
+			 * if the phy_dev is found
+			 */
+			put_device(&mac_cb->phy_dev->mdio.dev);
+			dev_dbg(mac_cb->dev, "mac%d phy_node: %s\n",
+				mac_cb->mac_id, np->name);
+		}
 
-	ret = fwnode_property_read_u32(mac_cb->fw_port,
-				       "port-mode-offset",
-				       &mac_cb->port_mode_off);
-	if (ret) {
-		dev_dbg(mac_cb->dev,
-			"mac%d port-mode-offset not found, use default value.\n",
-			mac_cb->mac_id);
-	}
-
-	ret = of_parse_phandle_with_fixed_args(to_of_node(mac_cb->fw_port),
-					       "cpld-syscon", 1, 0, &cpld_args);
-	if (ret) {
-		dev_dbg(mac_cb->dev, "mac%d no cpld-syscon found.\n",
-			mac_cb->mac_id);
-		mac_cb->cpld_ctrl = NULL;
-	} else {
-		syscon = syscon_node_to_regmap(cpld_args.np);
+		syscon = syscon_node_to_regmap(
+				of_parse_phandle(to_of_node(mac_cb->fw_port),
+						 "serdes-syscon", 0));
 		if (IS_ERR_OR_NULL(syscon)) {
-			dev_dbg(mac_cb->dev, "no cpld-syscon found!\n");
+			dev_err(mac_cb->dev, "serdes-syscon is needed!\n");
+			return -EINVAL;
+		}
+		mac_cb->serdes_ctrl = syscon;
+
+		ret = fwnode_property_read_u32(mac_cb->fw_port,
+					       "port-rst-offset",
+					       &mac_cb->port_rst_off);
+		if (ret) {
+			dev_dbg(mac_cb->dev,
+				"mac%d port-rst-offset not found, use default value.\n",
+				mac_cb->mac_id);
+		}
+
+		ret = fwnode_property_read_u32(mac_cb->fw_port,
+					       "port-mode-offset",
+					       &mac_cb->port_mode_off);
+		if (ret) {
+			dev_dbg(mac_cb->dev,
+				"mac%d port-mode-offset not found, use default value.\n",
+				mac_cb->mac_id);
+		}
+
+		ret = of_parse_phandle_with_fixed_args(
+			to_of_node(mac_cb->fw_port), "cpld-syscon", 1, 0,
+			&cpld_args);
+		if (ret) {
+			dev_dbg(mac_cb->dev, "mac%d no cpld-syscon found.\n",
+				mac_cb->mac_id);
 			mac_cb->cpld_ctrl = NULL;
 		} else {
-			mac_cb->cpld_ctrl = syscon;
-			mac_cb->cpld_ctrl_reg = cpld_args.args[0];
+			syscon = syscon_node_to_regmap(cpld_args.np);
+			if (IS_ERR_OR_NULL(syscon)) {
+				dev_dbg(mac_cb->dev, "no cpld-syscon found!\n");
+				mac_cb->cpld_ctrl = NULL;
+			} else {
+				mac_cb->cpld_ctrl = syscon;
+				mac_cb->cpld_ctrl_reg = cpld_args.args[0];
+			}
 		}
+	} else if (is_acpi_node(mac_cb->fw_port)) {
+		hns_mac_register_phy(mac_cb);
+	} else {
+		dev_err(mac_cb->dev, "mac%d cannot find phy node\n",
+			mac_cb->mac_id);
 	}
 
 	return 0;
@@ -790,7 +923,7 @@
 	else
 		mac_cb->mac_type = HNAE_PORT_DEBUG;
 
-	mac_cb->phy_if = hns_mac_get_phy_if(mac_cb);
+	mac_cb->phy_if = dsaf_dev->misc_op->get_phy_if(mac_cb);
 
 	ret = hns_mac_get_mode(mac_cb->phy_if);
 	if (ret < 0) {
@@ -805,7 +938,7 @@
 	if (ret)
 		return ret;
 
-	cpld_led_reset(mac_cb);
+	mac_cb->dsaf_dev->misc_op->cpld_reset_led(mac_cb);
 	mac_cb->vaddr = hns_mac_get_vaddr(dsaf_dev, mac_cb, mac_mode_idx);
 
 	return 0;
@@ -892,7 +1025,7 @@
 	int max_port_num = hns_mac_get_max_port_num(dsaf_dev);
 
 	for (i = 0; i < max_port_num; i++) {
-		cpld_led_reset(dsaf_dev->mac_cb[i]);
+		dsaf_dev->misc_op->cpld_reset_led(dsaf_dev->mac_cb[i]);
 		dsaf_dev->mac_cb[i] = NULL;
 	}
 }
@@ -975,7 +1108,7 @@
 		nic_data = 0;
 	mac_cb->txpkt_for_led = mac_cb->hw_stats.tx_good_pkts;
 	mac_cb->rxpkt_for_led = mac_cb->hw_stats.rx_good_pkts;
-	hns_cpld_set_led(mac_cb, (int)mac_cb->link,
+	mac_cb->dsaf_dev->misc_op->cpld_set_led(mac_cb, (int)mac_cb->link,
 			 mac_cb->speed, nic_data);
 }
 
@@ -985,5 +1118,5 @@
 	if (!mac_cb || !mac_cb->cpld_ctrl)
 		return 0;
 
-	return cpld_set_led_id(mac_cb, status);
+	return mac_cb->dsaf_dev->misc_op->cpld_set_led_id(mac_cb, status);
 }
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h
index 97ce9a7..05a6e8f 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h
@@ -338,7 +338,7 @@
 	phy_interface_t phy_if;
 	enum hnae_loop loop_mode;
 
-	struct device_node *phy_node;
+	struct phy_device *phy_dev;
 
 	struct mac_hw_stats hw_stats;
 };
@@ -448,8 +448,6 @@
 int hns_mac_set_mtu(struct hns_mac_cb *mac_cb, u32 new_mtu);
 int hns_mac_get_port_info(struct hns_mac_cb *mac_cb,
 			  u8 *auto_neg, u16 *speed, u8 *duplex);
-phy_interface_t hns_mac_get_phy_if(struct hns_mac_cb *mac_cb);
-int hns_mac_config_sds_loopback(struct hns_mac_cb *mac_cb, u8 en);
 int hns_mac_config_mac_loopback(struct hns_mac_cb *mac_cb,
 				enum hnae_loop loop, int en);
 void hns_mac_update_stats(struct hns_mac_cb *mac_cb);
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
index 1c2ddb2..67e8e13 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
@@ -7,6 +7,7 @@
  * (at your option) any later version.
  */
 
+#include <linux/acpi.h>
 #include <linux/device.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
@@ -24,6 +25,7 @@
 #include "hns_dsaf_main.h"
 #include "hns_dsaf_ppe.h"
 #include "hns_dsaf_rcb.h"
+#include "hns_dsaf_misc.h"
 
 const char *g_dsaf_mode_match[DSAF_MODE_MAX] = {
 	[DSAF_MODE_DISABLE_2PORT_64VM] = "2port-64vf",
@@ -32,6 +34,13 @@
 	[DSAF_MODE_DISABLE_SP] = "single-port",
 };
 
+static const struct acpi_device_id hns_dsaf_acpi_match[] = {
+	{ "HISI00B1", 0 },
+	{ "HISI00B2", 0 },
+	{ },
+};
+MODULE_DEVICE_TABLE(acpi, hns_dsaf_acpi_match);
+
 int hns_dsaf_get_cfg(struct dsaf_device *dsaf_dev)
 {
 	int ret, i;
@@ -45,12 +54,24 @@
 	struct device_node *np = dsaf_dev->dev->of_node;
 	struct platform_device *pdev = to_platform_device(dsaf_dev->dev);
 
-	if (of_device_is_compatible(np, "hisilicon,hns-dsaf-v1"))
-		dsaf_dev->dsaf_ver = AE_VERSION_1;
-	else
-		dsaf_dev->dsaf_ver = AE_VERSION_2;
+	if (dev_of_node(dsaf_dev->dev)) {
+		if (of_device_is_compatible(np, "hisilicon,hns-dsaf-v1"))
+			dsaf_dev->dsaf_ver = AE_VERSION_1;
+		else
+			dsaf_dev->dsaf_ver = AE_VERSION_2;
+	} else if (is_acpi_node(dsaf_dev->dev->fwnode)) {
+		if (acpi_dev_found(hns_dsaf_acpi_match[0].id))
+			dsaf_dev->dsaf_ver = AE_VERSION_1;
+		else if (acpi_dev_found(hns_dsaf_acpi_match[1].id))
+			dsaf_dev->dsaf_ver = AE_VERSION_2;
+		else
+			return -ENXIO;
+	} else {
+		dev_err(dsaf_dev->dev, "cannot get cfg data from of or acpi\n");
+		return -ENXIO;
+	}
 
-	ret = of_property_read_string(np, "mode", &mode_str);
+	ret = device_property_read_string(dsaf_dev->dev, "mode", &mode_str);
 	if (ret) {
 		dev_err(dsaf_dev->dev, "get dsaf mode fail, ret=%d!\n", ret);
 		return ret;
@@ -80,32 +101,40 @@
 	else
 		dsaf_dev->dsaf_tc_mode = HRD_DSAF_4TC_MODE;
 
-	syscon = syscon_node_to_regmap(
-			of_parse_phandle(np, "subctrl-syscon", 0));
-	if (IS_ERR_OR_NULL(syscon)) {
-		res = platform_get_resource(pdev, IORESOURCE_MEM, res_idx++);
-		if (!res) {
-			dev_err(dsaf_dev->dev, "subctrl info is needed!\n");
-			return -ENOMEM;
-		}
-		dsaf_dev->sc_base = devm_ioremap_resource(&pdev->dev, res);
-		if (!dsaf_dev->sc_base) {
-			dev_err(dsaf_dev->dev, "subctrl can not map!\n");
-			return -ENOMEM;
-		}
+	if (dev_of_node(dsaf_dev->dev)) {
+		syscon = syscon_node_to_regmap(
+				of_parse_phandle(np, "subctrl-syscon", 0));
+		if (IS_ERR_OR_NULL(syscon)) {
+			res = platform_get_resource(pdev, IORESOURCE_MEM,
+						    res_idx++);
+			if (!res) {
+				dev_err(dsaf_dev->dev, "subctrl info is needed!\n");
+				return -ENOMEM;
+			}
 
-		res = platform_get_resource(pdev, IORESOURCE_MEM, res_idx++);
-		if (!res) {
-			dev_err(dsaf_dev->dev, "serdes-ctrl info is needed!\n");
-			return -ENOMEM;
+			dsaf_dev->sc_base = devm_ioremap_resource(&pdev->dev,
+								  res);
+			if (!dsaf_dev->sc_base) {
+				dev_err(dsaf_dev->dev, "subctrl can not map!\n");
+				return -ENOMEM;
+			}
+
+			res = platform_get_resource(pdev, IORESOURCE_MEM,
+						    res_idx++);
+			if (!res) {
+				dev_err(dsaf_dev->dev, "serdes-ctrl info is needed!\n");
+				return -ENOMEM;
+			}
+
+			dsaf_dev->sds_base = devm_ioremap_resource(&pdev->dev,
+								   res);
+			if (!dsaf_dev->sds_base) {
+				dev_err(dsaf_dev->dev, "serdes-ctrl can not map!\n");
+				return -ENOMEM;
+			}
+		} else {
+			dsaf_dev->sub_ctrl = syscon;
 		}
-		dsaf_dev->sds_base = devm_ioremap_resource(&pdev->dev, res);
-		if (!dsaf_dev->sds_base) {
-			dev_err(dsaf_dev->dev, "serdes-ctrl can not map!\n");
-			return -ENOMEM;
-		}
-	} else {
-		dsaf_dev->sub_ctrl = syscon;
 	}
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "ppe-base");
@@ -142,27 +171,28 @@
 		}
 	}
 
-	ret = of_property_read_u32(np, "desc-num", &desc_num);
+	ret = device_property_read_u32(dsaf_dev->dev, "desc-num", &desc_num);
 	if (ret < 0 || desc_num < HNS_DSAF_MIN_DESC_CNT ||
 	    desc_num > HNS_DSAF_MAX_DESC_CNT) {
 		dev_err(dsaf_dev->dev, "get desc-num(%d) fail, ret=%d!\n",
 			desc_num, ret);
-		goto unmap_base_addr;
+		return -EINVAL;
 	}
 	dsaf_dev->desc_num = desc_num;
 
-	ret = of_property_read_u32(np, "reset-field-offset", &reset_offset);
+	ret = device_property_read_u32(dsaf_dev->dev, "reset-field-offset",
+				       &reset_offset);
 	if (ret < 0) {
 		dev_dbg(dsaf_dev->dev,
 			"get reset-field-offset fail, ret=%d!\r\n", ret);
 	}
 	dsaf_dev->reset_offset = reset_offset;
 
-	ret = of_property_read_u32(np, "buf-size", &buf_size);
+	ret = device_property_read_u32(dsaf_dev->dev, "buf-size", &buf_size);
 	if (ret < 0) {
 		dev_err(dsaf_dev->dev,
 			"get buf-size fail, ret=%d!\r\n", ret);
-		goto unmap_base_addr;
+		return ret;
 	}
 	dsaf_dev->buf_size = buf_size;
 
@@ -170,41 +200,19 @@
 	if (dsaf_dev->buf_size_type < 0) {
 		dev_err(dsaf_dev->dev,
 			"buf_size(%d) is wrong!\n", buf_size);
-		goto unmap_base_addr;
+		return -EINVAL;
 	}
 
+	dsaf_dev->misc_op = hns_misc_op_get(dsaf_dev);
+	if (!dsaf_dev->misc_op)
+		return -ENOMEM;
+
 	if (!dma_set_mask_and_coherent(dsaf_dev->dev, DMA_BIT_MASK(64ULL)))
 		dev_dbg(dsaf_dev->dev, "set mask to 64bit\n");
 	else
 		dev_err(dsaf_dev->dev, "set mask to 64bit fail!\n");
 
 	return 0;
-
-unmap_base_addr:
-	if (dsaf_dev->io_base)
-		iounmap(dsaf_dev->io_base);
-	if (dsaf_dev->ppe_base)
-		iounmap(dsaf_dev->ppe_base);
-	if (dsaf_dev->sds_base)
-		iounmap(dsaf_dev->sds_base);
-	if (dsaf_dev->sc_base)
-		iounmap(dsaf_dev->sc_base);
-	return ret;
-}
-
-static void hns_dsaf_free_cfg(struct dsaf_device *dsaf_dev)
-{
-	if (dsaf_dev->io_base)
-		iounmap(dsaf_dev->io_base);
-
-	if (dsaf_dev->ppe_base)
-		iounmap(dsaf_dev->ppe_base);
-
-	if (dsaf_dev->sds_base)
-		iounmap(dsaf_dev->sds_base);
-
-	if (dsaf_dev->sc_base)
-		iounmap(dsaf_dev->sc_base);
 }
 
 /**
@@ -508,10 +516,10 @@
 		o_sbm_bp_cfg = dsaf_read_dev(dsaf_dev, reg);
 		dsaf_set_field(o_sbm_bp_cfg,
 			       DSAFV2_SBM_CFG3_SET_BUF_NUM_NO_PFC_M,
-			       DSAFV2_SBM_CFG3_SET_BUF_NUM_NO_PFC_S, 110);
+			       DSAFV2_SBM_CFG3_SET_BUF_NUM_NO_PFC_S, 48);
 		dsaf_set_field(o_sbm_bp_cfg,
 			       DSAFV2_SBM_CFG3_RESET_BUF_NUM_NO_PFC_M,
-			       DSAFV2_SBM_CFG3_RESET_BUF_NUM_NO_PFC_S, 160);
+			       DSAFV2_SBM_CFG3_RESET_BUF_NUM_NO_PFC_S, 80);
 		dsaf_write_dev(dsaf_dev, reg, o_sbm_bp_cfg);
 
 		/* for no enable pfc mode */
@@ -519,29 +527,39 @@
 		o_sbm_bp_cfg = dsaf_read_dev(dsaf_dev, reg);
 		dsaf_set_field(o_sbm_bp_cfg,
 			       DSAFV2_SBM_CFG4_SET_BUF_NUM_NO_PFC_M,
-			       DSAFV2_SBM_CFG4_SET_BUF_NUM_NO_PFC_S, 128);
+			       DSAFV2_SBM_CFG4_SET_BUF_NUM_NO_PFC_S, 192);
 		dsaf_set_field(o_sbm_bp_cfg,
 			       DSAFV2_SBM_CFG4_RESET_BUF_NUM_NO_PFC_M,
-			       DSAFV2_SBM_CFG4_RESET_BUF_NUM_NO_PFC_S, 192);
+			       DSAFV2_SBM_CFG4_RESET_BUF_NUM_NO_PFC_S, 240);
 		dsaf_write_dev(dsaf_dev, reg, o_sbm_bp_cfg);
 	}
 
 	/* PPE */
-	reg = DSAF_SBM_BP_CFG_2_PPE_REG_0_REG + 0x80 * i;
-	o_sbm_bp_cfg = dsaf_read_dev(dsaf_dev, reg);
-	dsaf_set_field(o_sbm_bp_cfg, DSAFV2_SBM_CFG2_SET_BUF_NUM_M,
-		       DSAFV2_SBM_CFG2_SET_BUF_NUM_S, 10);
-	dsaf_set_field(o_sbm_bp_cfg, DSAFV2_SBM_CFG2_RESET_BUF_NUM_M,
-		       DSAFV2_SBM_CFG2_RESET_BUF_NUM_S, 12);
-	dsaf_write_dev(dsaf_dev, reg, o_sbm_bp_cfg);
+	for (i = 0; i < DSAFV2_SBM_PPE_CHN; i++) {
+		reg = DSAF_SBM_BP_CFG_2_PPE_REG_0_REG + 0x80 * i;
+		o_sbm_bp_cfg = dsaf_read_dev(dsaf_dev, reg);
+		dsaf_set_field(o_sbm_bp_cfg,
+			       DSAFV2_SBM_CFG2_PPE_SET_BUF_NUM_M,
+			       DSAFV2_SBM_CFG2_PPE_SET_BUF_NUM_S, 2);
+		dsaf_set_field(o_sbm_bp_cfg,
+			       DSAFV2_SBM_CFG2_PPE_RESET_BUF_NUM_M,
+			       DSAFV2_SBM_CFG2_PPE_RESET_BUF_NUM_S, 3);
+		dsaf_set_field(o_sbm_bp_cfg,
+			       DSAFV2_SBM_CFG2_PPE_CFG_USEFUL_NUM_M,
+			       DSAFV2_SBM_CFG2_PPE_CFG_USEFUL_NUM_S, 52);
+		dsaf_write_dev(dsaf_dev, reg, o_sbm_bp_cfg);
+	}
+
 	/* RoCEE */
 	for (i = 0; i < DASFV2_ROCEE_CRD_NUM; i++) {
 		reg = DSAFV2_SBM_BP_CFG_2_ROCEE_REG_0_REG + 0x80 * i;
 		o_sbm_bp_cfg = dsaf_read_dev(dsaf_dev, reg);
-		dsaf_set_field(o_sbm_bp_cfg, DSAFV2_SBM_CFG2_SET_BUF_NUM_M,
-			       DSAFV2_SBM_CFG2_SET_BUF_NUM_S, 2);
-		dsaf_set_field(o_sbm_bp_cfg, DSAFV2_SBM_CFG2_RESET_BUF_NUM_M,
-			       DSAFV2_SBM_CFG2_RESET_BUF_NUM_S, 4);
+		dsaf_set_field(o_sbm_bp_cfg,
+			       DSAFV2_SBM_CFG2_ROCEE_SET_BUF_NUM_M,
+			       DSAFV2_SBM_CFG2_ROCEE_SET_BUF_NUM_S, 2);
+		dsaf_set_field(o_sbm_bp_cfg,
+			       DSAFV2_SBM_CFG2_ROCEE_RESET_BUF_NUM_M,
+			       DSAFV2_SBM_CFG2_ROCEE_RESET_BUF_NUM_S, 4);
 		dsaf_write_dev(dsaf_dev, reg, o_sbm_bp_cfg);
 	}
 }
@@ -852,6 +870,8 @@
 	struct dsaf_device *dsaf_dev,
 	u32 address, struct dsaf_tbl_line_cfg *ptbl_line)
 {
+	spin_lock_bh(&dsaf_dev->tcam_lock);
+
 	/*Write Addr*/
 	hns_dsaf_tbl_line_addr_cfg(dsaf_dev, address);
 
@@ -860,6 +880,8 @@
 
 	/*Write Plus*/
 	hns_dsaf_tbl_line_pul(dsaf_dev);
+
+	spin_unlock_bh(&dsaf_dev->tcam_lock);
 }
 
 /**
@@ -873,6 +895,8 @@
 	struct dsaf_tbl_tcam_data *ptbl_tcam_data,
 	struct dsaf_tbl_tcam_ucast_cfg *ptbl_tcam_ucast)
 {
+	spin_lock_bh(&dsaf_dev->tcam_lock);
+
 	/*Write Addr*/
 	hns_dsaf_tbl_tcam_addr_cfg(dsaf_dev, address);
 	/*Write Tcam Data*/
@@ -881,6 +905,8 @@
 	hns_dsaf_tbl_tcam_ucast_cfg(dsaf_dev, ptbl_tcam_ucast);
 	/*Write Plus*/
 	hns_dsaf_tbl_tcam_data_ucast_pul(dsaf_dev);
+
+	spin_unlock_bh(&dsaf_dev->tcam_lock);
 }
 
 /**
@@ -895,6 +921,8 @@
 	struct dsaf_tbl_tcam_data *ptbl_tcam_data,
 	struct dsaf_tbl_tcam_mcast_cfg *ptbl_tcam_mcast)
 {
+	spin_lock_bh(&dsaf_dev->tcam_lock);
+
 	/*Write Addr*/
 	hns_dsaf_tbl_tcam_addr_cfg(dsaf_dev, address);
 	/*Write Tcam Data*/
@@ -903,6 +931,8 @@
 	hns_dsaf_tbl_tcam_mcast_cfg(dsaf_dev, ptbl_tcam_mcast);
 	/*Write Plus*/
 	hns_dsaf_tbl_tcam_data_mcast_pul(dsaf_dev);
+
+	spin_unlock_bh(&dsaf_dev->tcam_lock);
 }
 
 /**
@@ -912,6 +942,8 @@
  */
 static void hns_dsaf_tcam_mc_invld(struct dsaf_device *dsaf_dev, u32 address)
 {
+	spin_lock_bh(&dsaf_dev->tcam_lock);
+
 	/*Write Addr*/
 	hns_dsaf_tbl_tcam_addr_cfg(dsaf_dev, address);
 
@@ -924,6 +956,8 @@
 
 	/*Write Plus*/
 	hns_dsaf_tbl_tcam_mcast_pul(dsaf_dev);
+
+	spin_unlock_bh(&dsaf_dev->tcam_lock);
 }
 
 /**
@@ -941,6 +975,8 @@
 	u32 tcam_read_data0;
 	u32 tcam_read_data4;
 
+	spin_lock_bh(&dsaf_dev->tcam_lock);
+
 	/*Write Addr*/
 	hns_dsaf_tbl_tcam_addr_cfg(dsaf_dev, address);
 
@@ -949,9 +985,9 @@
 
 	/*read tcam data*/
 	ptbl_tcam_data->tbl_tcam_data_high
-		= dsaf_read_dev(dsaf_dev, DSAF_TBL_TCAM_RDATA_LOW_0_REG);
-	ptbl_tcam_data->tbl_tcam_data_low
 		= dsaf_read_dev(dsaf_dev, DSAF_TBL_TCAM_RDATA_HIGH_0_REG);
+	ptbl_tcam_data->tbl_tcam_data_low
+		= dsaf_read_dev(dsaf_dev, DSAF_TBL_TCAM_RDATA_LOW_0_REG);
 
 	/*read tcam mcast*/
 	tcam_read_data0 = dsaf_read_dev(dsaf_dev,
@@ -973,6 +1009,8 @@
 				 DSAF_TBL_UCAST_CFG1_OUT_PORT_S);
 	ptbl_tcam_ucast->tbl_ucast_dvc
 		= dsaf_get_bit(tcam_read_data0, DSAF_TBL_UCAST_CFG1_DVC_S);
+
+	spin_unlock_bh(&dsaf_dev->tcam_lock);
 }
 
 /**
@@ -989,6 +1027,8 @@
 {
 	u32 data_tmp;
 
+	spin_lock_bh(&dsaf_dev->tcam_lock);
+
 	/*Write Addr*/
 	hns_dsaf_tbl_tcam_addr_cfg(dsaf_dev, address);
 
@@ -997,9 +1037,9 @@
 
 	/*read tcam data*/
 	ptbl_tcam_data->tbl_tcam_data_high =
-		dsaf_read_dev(dsaf_dev, DSAF_TBL_TCAM_RDATA_LOW_0_REG);
-	ptbl_tcam_data->tbl_tcam_data_low =
 		dsaf_read_dev(dsaf_dev, DSAF_TBL_TCAM_RDATA_HIGH_0_REG);
+	ptbl_tcam_data->tbl_tcam_data_low =
+		dsaf_read_dev(dsaf_dev, DSAF_TBL_TCAM_RDATA_LOW_0_REG);
 
 	/*read tcam mcast*/
 	ptbl_tcam_mcast->tbl_mcast_port_msk[0] =
@@ -1019,6 +1059,8 @@
 	ptbl_tcam_mcast->tbl_mcast_port_msk[4] =
 		dsaf_get_field(data_tmp, DSAF_TBL_MCAST_CFG4_VM128_112_M,
 			       DSAF_TBL_MCAST_CFG4_VM128_112_S);
+
+	spin_unlock_bh(&dsaf_dev->tcam_lock);
 }
 
 /**
@@ -1080,10 +1122,10 @@
 				 u32 en)
 {
 	if (AE_IS_VER1(dsaf_dev->dsaf_ver)) {
-		if (!en)
+		if (!en) {
 			dev_err(dsaf_dev->dev, "dsafv1 can't close rx_pause!\n");
-
-		return -EINVAL;
+			return -EINVAL;
+		}
 	}
 
 	dsaf_set_dev_bit(dsaf_dev, DSAF_PAUSE_CFG_REG + mac_id * 4,
@@ -1295,9 +1337,9 @@
 	dev_dbg(dsaf_dev->dev,
 		"hns_dsaf_init_hw begin %s !\n", dsaf_dev->ae_dev.name);
 
-	hns_dsaf_rst(dsaf_dev, 0);
+	dsaf_dev->misc_op->dsaf_reset(dsaf_dev, 0);
 	mdelay(10);
-	hns_dsaf_rst(dsaf_dev, 1);
+	dsaf_dev->misc_op->dsaf_reset(dsaf_dev, 1);
 
 	hns_dsaf_comm_init(dsaf_dev);
 
@@ -1325,7 +1367,7 @@
 static void hns_dsaf_remove_hw(struct dsaf_device *dsaf_dev)
 {
 	/*reset*/
-	hns_dsaf_rst(dsaf_dev, 0);
+	dsaf_dev->misc_op->dsaf_reset(dsaf_dev, 0);
 }
 
 /**
@@ -1343,6 +1385,7 @@
 	if (HNS_DSAF_IS_DEBUG(dsaf_dev))
 		return 0;
 
+	spin_lock_init(&dsaf_dev->tcam_lock);
 	ret = hns_dsaf_init_hw(dsaf_dev);
 	if (ret)
 		return ret;
@@ -2088,11 +2131,24 @@
 	hns_dsaf_port_work_rate_cfg(dsaf_dev, mac_id, mode);
 }
 
+static u32 hns_dsaf_get_inode_prio_reg(int index)
+{
+	int base_index, offset;
+	u32 base_addr = DSAF_INODE_IN_PRIO_PAUSE_BASE_REG;
+
+	base_index = (index + 1) / DSAF_REG_PER_ZONE;
+	offset = (index + 1) % DSAF_REG_PER_ZONE;
+
+	return base_addr + DSAF_INODE_IN_PRIO_PAUSE_BASE_OFFSET * base_index +
+		DSAF_INODE_IN_PRIO_PAUSE_OFFSET * offset;
+}
+
 void hns_dsaf_update_stats(struct dsaf_device *dsaf_dev, u32 node_num)
 {
 	struct dsaf_hw_stats *hw_stats
 		= &dsaf_dev->hw_stats[node_num];
 	bool is_ver1 = AE_IS_VER1(dsaf_dev->dsaf_ver);
+	int i;
 	u32 reg_tmp;
 
 	hw_stats->pad_drop += dsaf_read_dev(dsaf_dev,
@@ -2127,6 +2183,18 @@
 	hw_stats->stp_drop += dsaf_read_dev(dsaf_dev,
 		DSAF_INODE_IN_DATA_STP_DISC_0_REG + 0x80 * (u64)node_num);
 
+	/* pfc pause frame statistics stored in dsaf inode*/
+	if ((node_num < DSAF_SERVICE_NW_NUM) && !is_ver1) {
+		for (i = 0; i < DSAF_PRIO_NR; i++) {
+			reg_tmp = hns_dsaf_get_inode_prio_reg(i);
+			hw_stats->rx_pfc[i] += dsaf_read_dev(dsaf_dev,
+				reg_tmp + 0x4 * (u64)node_num);
+			hw_stats->tx_pfc[i] += dsaf_read_dev(dsaf_dev,
+				DSAF_XOD_XGE_PFC_PRIO_CNT_BASE_REG +
+				DSAF_XOD_XGE_PFC_PRIO_CNT_OFFSET * i +
+				0xF0 * (u64)node_num);
+		}
+	}
 	hw_stats->tx_pkts += dsaf_read_dev(dsaf_dev,
 		DSAF_XOD_RCVPKT_CNT_0_REG + 0x90 * (u64)node_num);
 }
@@ -2464,9 +2532,12 @@
 		p[i] = 0xdddddddd;
 }
 
-static char *hns_dsaf_get_node_stats_strings(char *data, int node)
+static char *hns_dsaf_get_node_stats_strings(char *data, int node,
+					     struct dsaf_device *dsaf_dev)
 {
 	char *buff = data;
+	int i;
+	bool is_ver1 = AE_IS_VER1(dsaf_dev->dsaf_ver);
 
 	snprintf(buff, ETH_GSTRING_LEN, "innod%d_pad_drop_pkts", node);
 	buff = buff + ETH_GSTRING_LEN;
@@ -2494,6 +2565,18 @@
 	buff = buff + ETH_GSTRING_LEN;
 	snprintf(buff, ETH_GSTRING_LEN, "innod%d_stp_drop_pkts", node);
 	buff = buff + ETH_GSTRING_LEN;
+	if ((node < DSAF_SERVICE_NW_NUM) && (!is_ver1)) {
+		for (i = 0; i < DSAF_PRIO_NR; i++) {
+			snprintf(buff, ETH_GSTRING_LEN,
+				 "inod%d_pfc_prio%d_pkts", node, i);
+			buff = buff + ETH_GSTRING_LEN;
+		}
+		for (i = 0; i < DSAF_PRIO_NR; i++) {
+			snprintf(buff, ETH_GSTRING_LEN,
+				 "onod%d_pfc_prio%d_pkts", node, i);
+			buff = buff + ETH_GSTRING_LEN;
+		}
+	}
 	snprintf(buff, ETH_GSTRING_LEN, "onnod%d_tx_pkts", node);
 	buff = buff + ETH_GSTRING_LEN;
 
@@ -2504,7 +2587,9 @@
 				    int node_num)
 {
 	u64 *p = data;
+	int i;
 	struct dsaf_hw_stats *hw_stats = &ddev->hw_stats[node_num];
+	bool is_ver1 = AE_IS_VER1(ddev->dsaf_ver);
 
 	p[0] = hw_stats->pad_drop;
 	p[1] = hw_stats->man_pkts;
@@ -2519,8 +2604,16 @@
 	p[10] = hw_stats->local_addr_false;
 	p[11] = hw_stats->vlan_drop;
 	p[12] = hw_stats->stp_drop;
-	p[13] = hw_stats->tx_pkts;
+	if ((node_num < DSAF_SERVICE_NW_NUM) && (!is_ver1)) {
+		for (i = 0; i < DSAF_PRIO_NR; i++) {
+			p[13 + i] = hw_stats->rx_pfc[i];
+			p[13 + i + DSAF_PRIO_NR] = hw_stats->tx_pfc[i];
+		}
+		p[29] = hw_stats->tx_pkts;
+		return &p[30];
+	}
 
+	p[13] = hw_stats->tx_pkts;
 	return &p[14];
 }
 
@@ -2548,11 +2641,16 @@
  *@stringset: type of values in data
  *return dsaf string name count
  */
-int hns_dsaf_get_sset_count(int stringset)
+int hns_dsaf_get_sset_count(struct dsaf_device *dsaf_dev, int stringset)
 {
-	if (stringset == ETH_SS_STATS)
-		return DSAF_STATIC_NUM;
+	bool is_ver1 = AE_IS_VER1(dsaf_dev->dsaf_ver);
 
+	if (stringset == ETH_SS_STATS) {
+		if (is_ver1)
+			return DSAF_STATIC_NUM;
+		else
+			return DSAF_V2_STATIC_NUM;
+	}
 	return 0;
 }
 
@@ -2562,7 +2660,8 @@
  *@data:strings name value
  *@port:port index
  */
-void hns_dsaf_get_strings(int stringset, u8 *data, int port)
+void hns_dsaf_get_strings(int stringset, u8 *data, int port,
+			  struct dsaf_device *dsaf_dev)
 {
 	char *buff = (char *)data;
 	int node = port;
@@ -2571,11 +2670,11 @@
 		return;
 
 	/* for ge/xge node info */
-	buff = hns_dsaf_get_node_stats_strings(buff, node);
+	buff = hns_dsaf_get_node_stats_strings(buff, node, dsaf_dev);
 
 	/* for ppe node info */
 	node = port + DSAF_PPE_INODE_BASE;
-	(void)hns_dsaf_get_node_stats_strings(buff, node);
+	(void)hns_dsaf_get_node_stats_strings(buff, node, dsaf_dev);
 }
 
 /**
@@ -2611,7 +2710,7 @@
 
 	ret = hns_dsaf_init(dsaf_dev);
 	if (ret)
-		goto free_cfg;
+		goto free_dev;
 
 	ret = hns_mac_init(dsaf_dev);
 	if (ret)
@@ -2636,9 +2735,6 @@
 uninit_dsaf:
 	hns_dsaf_free(dsaf_dev);
 
-free_cfg:
-	hns_dsaf_free_cfg(dsaf_dev);
-
 free_dev:
 	hns_dsaf_free_dev(dsaf_dev);
 
@@ -2661,8 +2757,6 @@
 
 	hns_dsaf_free(dsaf_dev);
 
-	hns_dsaf_free_cfg(dsaf_dev);
-
 	hns_dsaf_free_dev(dsaf_dev);
 
 	return 0;
@@ -2680,6 +2774,7 @@
 	.driver = {
 		.name = DSAF_DRV_NAME,
 		.of_match_table = g_dsaf_match,
+		.acpi_match_table = hns_dsaf_acpi_match,
 	},
 };
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
index f0502ba..1daf018 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
@@ -39,6 +39,9 @@
 
 #define DSAF_DUMP_REGS_NUM 504
 #define DSAF_STATIC_NUM 28
+#define DSAF_V2_STATIC_NUM	44
+#define DSAF_PRIO_NR	8
+#define DSAF_REG_PER_ZONE	3
 
 #define DSAF_STATS_READ(p, offset) (*((u64 *)((u8 *)(p) + (offset))))
 #define HNS_DSAF_IS_DEBUG(dev) (dev->dsaf_mode == DSAF_MODE_DISABLE_SP)
@@ -176,6 +179,8 @@
 	u64 local_addr_false;
 	u64 vlan_drop;
 	u64 stp_drop;
+	u64 rx_pfc[DSAF_PRIO_NR];
+	u64 tx_pfc[DSAF_PRIO_NR];
 	u64 tx_pkts;
 };
 
@@ -268,6 +273,27 @@
 
 };
 
+struct dsaf_misc_op {
+	void (*cpld_set_led)(struct hns_mac_cb *mac_cb, int link_status,
+			     u16 speed, int data);
+	void (*cpld_reset_led)(struct hns_mac_cb *mac_cb);
+	int (*cpld_set_led_id)(struct hns_mac_cb *mac_cb,
+			       enum hnae_led_state status);
+	/* reset seris function, it will be reset if the dereseet is 0 */
+	void (*dsaf_reset)(struct dsaf_device *dsaf_dev, bool dereset);
+	void (*xge_srst)(struct dsaf_device *dsaf_dev, u32 port, bool dereset);
+	void (*xge_core_srst)(struct dsaf_device *dsaf_dev, u32 port,
+			      bool dereset);
+	void (*ge_srst)(struct dsaf_device *dsaf_dev, u32 port, bool dereset);
+	void (*ppe_srst)(struct dsaf_device *dsaf_dev, u32 port, bool dereset);
+	void (*ppe_comm_srst)(struct dsaf_device *dsaf_dev, bool dereset);
+
+	phy_interface_t (*get_phy_if)(struct hns_mac_cb *mac_cb);
+	int (*get_sfp_prsnt)(struct hns_mac_cb *mac_cb, int *sfp_prsnt);
+
+	int (*cfg_serdes_loopback)(struct hns_mac_cb *mac_cb, bool en);
+};
+
 /* Dsaf device struct define ,and mac ->  dsaf */
 struct dsaf_device {
 	struct device *dev;
@@ -292,9 +318,12 @@
 	struct ppe_common_cb *ppe_common[DSAF_COMM_DEV_NUM];
 	struct rcb_common_cb *rcb_common[DSAF_COMM_DEV_NUM];
 	struct hns_mac_cb *mac_cb[DSAF_MAX_PORT_NUM];
+	struct dsaf_misc_op *misc_op;
 
 	struct dsaf_hw_stats hw_stats[DSAF_NODE_NUM];
 	struct dsaf_int_stat int_stat;
+	/* make sure tcam table config spinlock */
+	spinlock_t tcam_lock;
 };
 
 static inline void *hns_dsaf_dev_priv(const struct dsaf_device *dsaf_dev)
@@ -388,27 +417,17 @@
 	u16 entry_index,
 	struct dsaf_drv_mac_multi_dest_entry *mac_entry);
 
-void hns_dsaf_rst(struct dsaf_device *dsaf_dev, u32 val);
-
-void hns_ppe_srst_by_port(struct dsaf_device *dsaf_dev, u32 port, u32 val);
-
-void hns_ppe_com_srst(struct ppe_common_cb *ppe_common, u32 val);
-
 void hns_dsaf_fix_mac_mode(struct hns_mac_cb *mac_cb);
 
 int hns_dsaf_ae_init(struct dsaf_device *dsaf_dev);
 void hns_dsaf_ae_uninit(struct dsaf_device *dsaf_dev);
 
-void hns_dsaf_xge_srst_by_port(struct dsaf_device *dsaf_dev, u32 port, u32 val);
-void hns_dsaf_ge_srst_by_port(struct dsaf_device *dsaf_dev, u32 port, u32 val);
-void hns_dsaf_xge_core_srst_by_port(struct dsaf_device *dsaf_dev,
-				    u32 port, u32 val);
-
 void hns_dsaf_update_stats(struct dsaf_device *dsaf_dev, u32 inode_num);
 
-int hns_dsaf_get_sset_count(int stringset);
+int hns_dsaf_get_sset_count(struct dsaf_device *dsaf_dev, int stringset);
 void hns_dsaf_get_stats(struct dsaf_device *ddev, u64 *data, int port);
-void hns_dsaf_get_strings(int stringset, u8 *data, int port);
+void hns_dsaf_get_strings(int stringset, u8 *data, int port,
+			  struct dsaf_device *dsaf_dev);
 
 void hns_dsaf_get_regs(struct dsaf_device *ddev, u32 port, void *data);
 int hns_dsaf_get_regs_count(void);
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
index a837bb9..8473287 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
@@ -12,6 +12,27 @@
 #include "hns_dsaf_ppe.h"
 #include "hns_dsaf_reg.h"
 
+enum _dsm_op_index {
+	HNS_OP_RESET_FUNC               = 0x1,
+	HNS_OP_SERDES_LP_FUNC           = 0x2,
+	HNS_OP_LED_SET_FUNC             = 0x3,
+	HNS_OP_GET_PORT_TYPE_FUNC       = 0x4,
+	HNS_OP_GET_SFP_STAT_FUNC        = 0x5,
+};
+
+enum _dsm_rst_type {
+	HNS_DSAF_RESET_FUNC     = 0x1,
+	HNS_PPE_RESET_FUNC      = 0x2,
+	HNS_XGE_CORE_RESET_FUNC = 0x3,
+	HNS_XGE_RESET_FUNC      = 0x4,
+	HNS_GE_RESET_FUNC       = 0x5,
+};
+
+const u8 hns_dsaf_acpi_dsm_uuid[] = {
+	0x1A, 0xAA, 0x85, 0x1A, 0x93, 0xE2, 0x5E, 0x41,
+	0x8E, 0x28, 0x8D, 0x69, 0x0A, 0x0F, 0x82, 0x0A
+};
+
 static void dsaf_write_sub(struct dsaf_device *dsaf_dev, u32 reg, u32 val)
 {
 	if (dsaf_dev->sub_ctrl)
@@ -32,8 +53,8 @@
 	return ret;
 }
 
-void hns_cpld_set_led(struct hns_mac_cb *mac_cb, int link_status,
-		      u16 speed, int data)
+static void hns_cpld_set_led(struct hns_mac_cb *mac_cb, int link_status,
+			     u16 speed, int data)
 {
 	int speed_reg = 0;
 	u8 value;
@@ -65,13 +86,14 @@
 			mac_cb->cpld_led_value = value;
 		}
 	} else {
-		dsaf_write_syscon(mac_cb->cpld_ctrl, mac_cb->cpld_ctrl_reg,
-				  CPLD_LED_DEFAULT_VALUE);
-		mac_cb->cpld_led_value = CPLD_LED_DEFAULT_VALUE;
+		value = (mac_cb->cpld_led_value) & (0x1 << DSAF_LED_ANCHOR_B);
+		dsaf_write_syscon(mac_cb->cpld_ctrl,
+				  mac_cb->cpld_ctrl_reg, value);
+		mac_cb->cpld_led_value = value;
 	}
 }
 
-void cpld_led_reset(struct hns_mac_cb *mac_cb)
+static void cpld_led_reset(struct hns_mac_cb *mac_cb)
 {
 	if (!mac_cb || !mac_cb->cpld_ctrl)
 		return;
@@ -81,8 +103,8 @@
 	mac_cb->cpld_led_value = CPLD_LED_DEFAULT_VALUE;
 }
 
-int cpld_set_led_id(struct hns_mac_cb *mac_cb,
-		    enum hnae_led_state status)
+static int cpld_set_led_id(struct hns_mac_cb *mac_cb,
+			   enum hnae_led_state status)
 {
 	switch (status) {
 	case HNAE_LED_ACTIVE:
@@ -93,7 +115,7 @@
 			     CPLD_LED_ON_VALUE);
 		dsaf_write_syscon(mac_cb->cpld_ctrl, mac_cb->cpld_ctrl_reg,
 				  mac_cb->cpld_led_value);
-		return 2;
+		break;
 	case HNAE_LED_INACTIVE:
 		dsaf_set_bit(mac_cb->cpld_led_value, DSAF_LED_ANCHOR_B,
 			     CPLD_LED_DEFAULT_VALUE);
@@ -101,7 +123,8 @@
 				  mac_cb->cpld_led_value);
 		break;
 	default:
-		break;
+		dev_err(mac_cb->dev, "invalid led state: %d!", status);
+		return -EINVAL;
 	}
 
 	return 0;
@@ -109,12 +132,40 @@
 
 #define RESET_REQ_OR_DREQ 1
 
-void hns_dsaf_rst(struct dsaf_device *dsaf_dev, u32 val)
+static void hns_dsaf_acpi_srst_by_port(struct dsaf_device *dsaf_dev, u8 op_type,
+				       u32 port_type, u32 port, u32 val)
+{
+	union acpi_object *obj;
+	union acpi_object obj_args[3], argv4;
+
+	obj_args[0].integer.type = ACPI_TYPE_INTEGER;
+	obj_args[0].integer.value = port_type;
+	obj_args[1].integer.type = ACPI_TYPE_INTEGER;
+	obj_args[1].integer.value = port;
+	obj_args[2].integer.type = ACPI_TYPE_INTEGER;
+	obj_args[2].integer.value = val;
+
+	argv4.type = ACPI_TYPE_PACKAGE;
+	argv4.package.count = 3;
+	argv4.package.elements = obj_args;
+
+	obj = acpi_evaluate_dsm(ACPI_HANDLE(dsaf_dev->dev),
+				hns_dsaf_acpi_dsm_uuid, 0, op_type, &argv4);
+	if (!obj) {
+		dev_warn(dsaf_dev->dev, "reset port_type%d port%d fail!",
+			 port_type, port);
+		return;
+	}
+
+	ACPI_FREE(obj);
+}
+
+static void hns_dsaf_rst(struct dsaf_device *dsaf_dev, bool dereset)
 {
 	u32 xbar_reg_addr;
 	u32 nt_reg_addr;
 
-	if (!val) {
+	if (!dereset) {
 		xbar_reg_addr = DSAF_SUB_SC_XBAR_RESET_REQ_REG;
 		nt_reg_addr = DSAF_SUB_SC_NT_RESET_REQ_REG;
 	} else {
@@ -126,7 +177,15 @@
 	dsaf_write_sub(dsaf_dev, nt_reg_addr, RESET_REQ_OR_DREQ);
 }
 
-void hns_dsaf_xge_srst_by_port(struct dsaf_device *dsaf_dev, u32 port, u32 val)
+static void hns_dsaf_rst_acpi(struct dsaf_device *dsaf_dev, bool dereset)
+{
+	hns_dsaf_acpi_srst_by_port(dsaf_dev, HNS_OP_RESET_FUNC,
+				   HNS_DSAF_RESET_FUNC,
+				   0, dereset);
+}
+
+static void hns_dsaf_xge_srst_by_port(struct dsaf_device *dsaf_dev, u32 port,
+				      bool dereset)
 {
 	u32 reg_val = 0;
 	u32 reg_addr;
@@ -137,7 +196,7 @@
 	reg_val |= RESET_REQ_OR_DREQ;
 	reg_val |= 0x2082082 << dsaf_dev->mac_cb[port]->port_rst_off;
 
-	if (val == 0)
+	if (!dereset)
 		reg_addr = DSAF_SUB_SC_XGE_RESET_REQ_REG;
 	else
 		reg_addr = DSAF_SUB_SC_XGE_RESET_DREQ_REG;
@@ -145,8 +204,15 @@
 	dsaf_write_sub(dsaf_dev, reg_addr, reg_val);
 }
 
-void hns_dsaf_xge_core_srst_by_port(struct dsaf_device *dsaf_dev,
-				    u32 port, u32 val)
+static void hns_dsaf_xge_srst_by_port_acpi(struct dsaf_device *dsaf_dev,
+					   u32 port, bool dereset)
+{
+	hns_dsaf_acpi_srst_by_port(dsaf_dev, HNS_OP_RESET_FUNC,
+				   HNS_XGE_RESET_FUNC, port, dereset);
+}
+
+static void hns_dsaf_xge_core_srst_by_port(struct dsaf_device *dsaf_dev,
+					   u32 port, bool dereset)
 {
 	u32 reg_val = 0;
 	u32 reg_addr;
@@ -157,7 +223,7 @@
 	reg_val |= XGMAC_TRX_CORE_SRST_M
 		<< dsaf_dev->mac_cb[port]->port_rst_off;
 
-	if (val == 0)
+	if (!dereset)
 		reg_addr = DSAF_SUB_SC_XGE_RESET_REQ_REG;
 	else
 		reg_addr = DSAF_SUB_SC_XGE_RESET_DREQ_REG;
@@ -165,7 +231,16 @@
 	dsaf_write_sub(dsaf_dev, reg_addr, reg_val);
 }
 
-void hns_dsaf_ge_srst_by_port(struct dsaf_device *dsaf_dev, u32 port, u32 val)
+static void
+hns_dsaf_xge_core_srst_by_port_acpi(struct dsaf_device *dsaf_dev,
+				    u32 port, bool dereset)
+{
+	hns_dsaf_acpi_srst_by_port(dsaf_dev, HNS_OP_RESET_FUNC,
+				   HNS_XGE_CORE_RESET_FUNC, port, dereset);
+}
+
+static void hns_dsaf_ge_srst_by_port(struct dsaf_device *dsaf_dev, u32 port,
+				     bool dereset)
 {
 	u32 reg_val_1;
 	u32 reg_val_2;
@@ -183,7 +258,7 @@
 		else
 			reg_val_2  = 0x2082082 << port_rst_off;
 
-		if (val == 0) {
+		if (!dereset) {
 			dsaf_write_sub(dsaf_dev, DSAF_SUB_SC_GE_RESET_REQ1_REG,
 				       reg_val_1);
 
@@ -198,9 +273,13 @@
 		}
 	} else {
 		reg_val_1 = 0x15540 << dsaf_dev->reset_offset;
-		reg_val_2 = 0x100 << dsaf_dev->reset_offset;
 
-		if (val == 0) {
+		if (AE_IS_VER1(dsaf_dev->dsaf_ver))
+			reg_val_2 = 0x100 << dsaf_dev->reset_offset;
+		else
+			reg_val_2 = 0x40 << dsaf_dev->reset_offset;
+
+		if (!dereset) {
 			dsaf_write_sub(dsaf_dev, DSAF_SUB_SC_GE_RESET_REQ1_REG,
 				       reg_val_1);
 
@@ -216,14 +295,22 @@
 	}
 }
 
-void hns_ppe_srst_by_port(struct dsaf_device *dsaf_dev, u32 port, u32 val)
+static void hns_dsaf_ge_srst_by_port_acpi(struct dsaf_device *dsaf_dev,
+					  u32 port, bool dereset)
+{
+	hns_dsaf_acpi_srst_by_port(dsaf_dev, HNS_OP_RESET_FUNC,
+				   HNS_GE_RESET_FUNC, port, dereset);
+}
+
+static void hns_ppe_srst_by_port(struct dsaf_device *dsaf_dev, u32 port,
+				 bool dereset)
 {
 	u32 reg_val = 0;
 	u32 reg_addr;
 
 	reg_val |= RESET_REQ_OR_DREQ <<	dsaf_dev->mac_cb[port]->port_rst_off;
 
-	if (val == 0)
+	if (!dereset)
 		reg_addr = DSAF_SUB_SC_PPE_RESET_REQ_REG;
 	else
 		reg_addr = DSAF_SUB_SC_PPE_RESET_DREQ_REG;
@@ -231,15 +318,24 @@
 	dsaf_write_sub(dsaf_dev, reg_addr, reg_val);
 }
 
-void hns_ppe_com_srst(struct ppe_common_cb *ppe_common, u32 val)
+static void
+hns_ppe_srst_by_port_acpi(struct dsaf_device *dsaf_dev, u32 port, bool dereset)
 {
-	struct dsaf_device *dsaf_dev = ppe_common->dsaf_dev;
+	hns_dsaf_acpi_srst_by_port(dsaf_dev, HNS_OP_RESET_FUNC,
+				   HNS_PPE_RESET_FUNC, port, dereset);
+}
+
+static void hns_ppe_com_srst(struct dsaf_device *dsaf_dev, bool dereset)
+{
 	u32 reg_val;
 	u32 reg_addr;
 
+	if (!(dev_of_node(dsaf_dev->dev)))
+		return;
+
 	if (!HNS_DSAF_IS_DEBUG(dsaf_dev)) {
 		reg_val = RESET_REQ_OR_DREQ;
-		if (val == 0)
+		if (!dereset)
 			reg_addr = DSAF_SUB_SC_RCB_PPE_COM_RESET_REQ_REG;
 		else
 			reg_addr = DSAF_SUB_SC_RCB_PPE_COM_RESET_DREQ_REG;
@@ -247,7 +343,7 @@
 	} else {
 		reg_val = 0x100 << dsaf_dev->reset_offset;
 
-		if (val == 0)
+		if (!dereset)
 			reg_addr = DSAF_SUB_SC_PPE_RESET_REQ_REG;
 		else
 			reg_addr = DSAF_SUB_SC_PPE_RESET_DREQ_REG;
@@ -261,7 +357,7 @@
  * @mac_cb: mac control block
  * retuen phy interface
  */
-phy_interface_t hns_mac_get_phy_if(struct hns_mac_cb *mac_cb)
+static phy_interface_t hns_mac_get_phy_if(struct hns_mac_cb *mac_cb)
 {
 	u32 mode;
 	u32 reg;
@@ -293,6 +389,36 @@
 	return phy_if;
 }
 
+static phy_interface_t hns_mac_get_phy_if_acpi(struct hns_mac_cb *mac_cb)
+{
+	phy_interface_t phy_if = PHY_INTERFACE_MODE_NA;
+	union acpi_object *obj;
+	union acpi_object obj_args, argv4;
+
+	obj_args.integer.type = ACPI_TYPE_INTEGER;
+	obj_args.integer.value = mac_cb->mac_id;
+
+	argv4.type = ACPI_TYPE_PACKAGE,
+	argv4.package.count = 1,
+	argv4.package.elements = &obj_args,
+
+	obj = acpi_evaluate_dsm(ACPI_HANDLE(mac_cb->dev),
+				hns_dsaf_acpi_dsm_uuid, 0,
+				HNS_OP_GET_PORT_TYPE_FUNC, &argv4);
+
+	if (!obj || obj->type != ACPI_TYPE_INTEGER)
+		return phy_if;
+
+	phy_if = obj->integer.value ?
+		PHY_INTERFACE_MODE_XGMII : PHY_INTERFACE_MODE_SGMII;
+
+	dev_dbg(mac_cb->dev, "mac_id=%d, phy_if=%d\n", mac_cb->mac_id, phy_if);
+
+	ACPI_FREE(obj);
+
+	return phy_if;
+}
+
 int hns_mac_get_sfp_prsnt(struct hns_mac_cb *mac_cb, int *sfp_prsnt)
 {
 	if (!mac_cb->cpld_ctrl)
@@ -309,13 +435,8 @@
  * @mac_cb: mac control block
  * retuen 0 == success
  */
-int hns_mac_config_sds_loopback(struct hns_mac_cb *mac_cb, u8 en)
+static int hns_mac_config_sds_loopback(struct hns_mac_cb *mac_cb, bool en)
 {
-	/* port 0-3 hilink4 base is serdes_vaddr + 0x00280000
-	 * port 4-7 hilink3 base is serdes_vaddr + 0x00200000
-	 */
-	u8 *base_addr = (u8 *)mac_cb->serdes_vaddr +
-		       (mac_cb->mac_id <= 3 ? 0x00280000 : 0x00200000);
 	const u8 lane_id[] = {
 		0,	/* mac 0 -> lane 0 */
 		1,	/* mac 1 -> lane 1 */
@@ -332,7 +453,7 @@
 	int sfp_prsnt;
 	int ret = hns_mac_get_sfp_prsnt(mac_cb, &sfp_prsnt);
 
-	if (!mac_cb->phy_node) {
+	if (!mac_cb->phy_dev) {
 		if (ret)
 			pr_info("please confirm sfp is present or not\n");
 		else
@@ -341,13 +462,110 @@
 	}
 
 	if (mac_cb->serdes_ctrl) {
-		u32 origin = dsaf_read_syscon(mac_cb->serdes_ctrl, reg_offset);
+		u32 origin;
 
-		dsaf_set_field(origin, 1ull << 10, 10, !!en);
+		if (!AE_IS_VER1(mac_cb->dsaf_dev->dsaf_ver)) {
+#define HILINK_ACCESS_SEL_CFG		0x40008
+			/* hilink4 & hilink3 use the same xge training and
+			 * xge u adaptor. There is a hilink access sel cfg
+			 * register to select which one to be configed
+			 */
+			if ((!HNS_DSAF_IS_DEBUG(mac_cb->dsaf_dev)) &&
+			    (mac_cb->mac_id <= 3))
+				dsaf_write_syscon(mac_cb->serdes_ctrl,
+						  HILINK_ACCESS_SEL_CFG, 0);
+			else
+				dsaf_write_syscon(mac_cb->serdes_ctrl,
+						  HILINK_ACCESS_SEL_CFG, 3);
+		}
+
+		origin = dsaf_read_syscon(mac_cb->serdes_ctrl, reg_offset);
+
+		dsaf_set_field(origin, 1ull << 10, 10, en);
 		dsaf_write_syscon(mac_cb->serdes_ctrl, reg_offset, origin);
 	} else {
-		dsaf_set_reg_field(base_addr, reg_offset, 1ull << 10, 10, !!en);
+		u8 *base_addr = (u8 *)mac_cb->serdes_vaddr +
+				(mac_cb->mac_id <= 3 ? 0x00280000 : 0x00200000);
+		dsaf_set_reg_field(base_addr, reg_offset, 1ull << 10, 10, en);
 	}
 
 	return 0;
 }
+
+static int
+hns_mac_config_sds_loopback_acpi(struct hns_mac_cb *mac_cb, bool en)
+{
+	union acpi_object *obj;
+	union acpi_object obj_args[3], argv4;
+
+	obj_args[0].integer.type = ACPI_TYPE_INTEGER;
+	obj_args[0].integer.value = mac_cb->mac_id;
+	obj_args[1].integer.type = ACPI_TYPE_INTEGER;
+	obj_args[1].integer.value = !!en;
+
+	argv4.type = ACPI_TYPE_PACKAGE;
+	argv4.package.count = 2;
+	argv4.package.elements = obj_args;
+
+	obj = acpi_evaluate_dsm(ACPI_HANDLE(mac_cb->dsaf_dev->dev),
+				hns_dsaf_acpi_dsm_uuid, 0,
+				HNS_OP_SERDES_LP_FUNC, &argv4);
+	if (!obj) {
+		dev_warn(mac_cb->dsaf_dev->dev, "set port%d serdes lp fail!",
+			 mac_cb->mac_id);
+
+		return -ENOTSUPP;
+	}
+
+	ACPI_FREE(obj);
+
+	return 0;
+}
+
+struct dsaf_misc_op *hns_misc_op_get(struct dsaf_device *dsaf_dev)
+{
+	struct dsaf_misc_op *misc_op;
+
+	misc_op = devm_kzalloc(dsaf_dev->dev, sizeof(*misc_op), GFP_KERNEL);
+	if (!misc_op)
+		return NULL;
+
+	if (dev_of_node(dsaf_dev->dev)) {
+		misc_op->cpld_set_led = hns_cpld_set_led;
+		misc_op->cpld_reset_led = cpld_led_reset;
+		misc_op->cpld_set_led_id = cpld_set_led_id;
+
+		misc_op->dsaf_reset = hns_dsaf_rst;
+		misc_op->xge_srst = hns_dsaf_xge_srst_by_port;
+		misc_op->xge_core_srst = hns_dsaf_xge_core_srst_by_port;
+		misc_op->ge_srst = hns_dsaf_ge_srst_by_port;
+		misc_op->ppe_srst = hns_ppe_srst_by_port;
+		misc_op->ppe_comm_srst = hns_ppe_com_srst;
+
+		misc_op->get_phy_if = hns_mac_get_phy_if;
+		misc_op->get_sfp_prsnt = hns_mac_get_sfp_prsnt;
+
+		misc_op->cfg_serdes_loopback = hns_mac_config_sds_loopback;
+	} else if (is_acpi_node(dsaf_dev->dev->fwnode)) {
+		misc_op->cpld_set_led = hns_cpld_set_led;
+		misc_op->cpld_reset_led = cpld_led_reset;
+		misc_op->cpld_set_led_id = cpld_set_led_id;
+
+		misc_op->dsaf_reset = hns_dsaf_rst_acpi;
+		misc_op->xge_srst = hns_dsaf_xge_srst_by_port_acpi;
+		misc_op->xge_core_srst = hns_dsaf_xge_core_srst_by_port_acpi;
+		misc_op->ge_srst = hns_dsaf_ge_srst_by_port_acpi;
+		misc_op->ppe_srst = hns_ppe_srst_by_port_acpi;
+		misc_op->ppe_comm_srst = hns_ppe_com_srst;
+
+		misc_op->get_phy_if = hns_mac_get_phy_if_acpi;
+		misc_op->get_sfp_prsnt = hns_mac_get_sfp_prsnt;
+
+		misc_op->cfg_serdes_loopback = hns_mac_config_sds_loopback_acpi;
+	} else {
+		devm_kfree(dsaf_dev->dev, (void *)misc_op);
+		misc_op = NULL;
+	}
+
+	return (void *)misc_op;
+}
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.h
index 419f07a..f06bb03 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.h
@@ -33,11 +33,6 @@
 #define DSAF_LED_DATA_B 4
 #define DSAF_LED_ANCHOR_B 5
 
-void hns_cpld_set_led(struct hns_mac_cb *mac_cb, int link_status,
-		      u16 speed, int data);
-void cpld_led_reset(struct hns_mac_cb *mac_cb);
-int cpld_set_led_id(struct hns_mac_cb *mac_cb,
-		    enum hnae_led_state status);
-int hns_mac_get_sfp_prsnt(struct hns_mac_cb *mac_cb, int *sfp_prsnt);
+struct dsaf_misc_op *hns_misc_op_get(struct dsaf_device *dsaf_dev);
 
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
index 8cd151a..ff8b6a4 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
@@ -112,7 +112,6 @@
 static void __iomem *hns_ppe_get_iobase(struct ppe_common_cb *ppe_common,
 					int ppe_idx)
 {
-
 	return ppe_common->dsaf_dev->ppe_base + ppe_idx * PPE_REG_OFFSET;
 }
 
@@ -200,11 +199,12 @@
 static int hns_ppe_common_init_hw(struct ppe_common_cb *ppe_common)
 {
 	enum ppe_qid_mode qid_mode;
-	enum dsaf_mode dsaf_mode = ppe_common->dsaf_dev->dsaf_mode;
+	struct dsaf_device *dsaf_dev = ppe_common->dsaf_dev;
+	enum dsaf_mode dsaf_mode = dsaf_dev->dsaf_mode;
 
-	hns_ppe_com_srst(ppe_common, 0);
+	dsaf_dev->misc_op->ppe_comm_srst(dsaf_dev, 0);
 	mdelay(100);
-	hns_ppe_com_srst(ppe_common, 1);
+	dsaf_dev->misc_op->ppe_comm_srst(dsaf_dev, 1);
 	mdelay(100);
 
 	if (ppe_common->ppe_mode == PPE_COMMON_MODE_SERVICE) {
@@ -288,9 +288,9 @@
 	/* get default RSS key */
 	netdev_rss_key_fill(ppe_cb->rss_key, HNS_PPEV2_RSS_KEY_SIZE);
 
-	hns_ppe_srst_by_port(dsaf_dev, port, 0);
+	dsaf_dev->misc_op->ppe_srst(dsaf_dev, port, 0);
 	mdelay(10);
-	hns_ppe_srst_by_port(dsaf_dev, port, 1);
+	dsaf_dev->misc_op->ppe_srst(dsaf_dev, port, 1);
 
 	/* clr and msk except irq*/
 	hns_ppe_exc_irq_en(ppe_cb, 0);
@@ -328,10 +328,11 @@
 static void hns_ppe_uninit_hw(struct hns_ppe_cb *ppe_cb)
 {
 	u32 port;
+	struct dsaf_device *dsaf_dev = ppe_cb->ppe_common_cb->dsaf_dev;
 
 	if (ppe_cb->ppe_common_cb) {
 		port = ppe_cb->index;
-		hns_ppe_srst_by_port(ppe_cb->ppe_common_cb->dsaf_dev, port, 0);
+		dsaf_dev->misc_op->ppe_srst(dsaf_dev, port, 0);
 	}
 }
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
index 4ef6d23..ef11077 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
@@ -458,7 +458,6 @@
 	u32 i;
 	u32 ring_num = rcb_common->ring_num;
 	int base_irq_idx = hns_rcb_get_base_irq_idx(rcb_common);
-	struct device_node *np = rcb_common->dsaf_dev->dev->of_node;
 	struct platform_device *pdev =
 		to_platform_device(rcb_common->dsaf_dev->dev);
 	bool is_ver1 = AE_IS_VER1(rcb_common->dsaf_dev->dsaf_ver);
@@ -473,10 +472,10 @@
 		ring_pair_cb->port_id_in_comm =
 			hns_rcb_get_port_in_comm(rcb_common, i);
 		ring_pair_cb->virq[HNS_RCB_IRQ_IDX_TX] =
-		is_ver1 ? irq_of_parse_and_map(np, base_irq_idx + i * 2) :
+		is_ver1 ? platform_get_irq(pdev, base_irq_idx + i * 2) :
 			  platform_get_irq(pdev, base_irq_idx + i * 3 + 1);
 		ring_pair_cb->virq[HNS_RCB_IRQ_IDX_RX] =
-		is_ver1 ? irq_of_parse_and_map(np, base_irq_idx + i * 2 + 1) :
+		is_ver1 ? platform_get_irq(pdev, base_irq_idx + i * 2 + 1) :
 			  platform_get_irq(pdev, base_irq_idx + i * 3);
 		ring_pair_cb->q.phy_base =
 			RCB_COMM_BASE_TO_RING_BASE(rcb_common->phy_base, i);
@@ -541,7 +540,7 @@
 	}
 	if (timeout > HNS_RCB_MAX_COALESCED_USECS) {
 		dev_err(rcb_common->dsaf_dev->dev,
-			"error: not support coalesce %dus!\n", timeout);
+			"error: coalesce_usecs setting supports 0~1023us\n");
 		return -EINVAL;
 	}
 	hns_rcb_set_port_timeout(rcb_common, port_idx, timeout);
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h
index bd54dac..99b4e1b 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h
@@ -40,7 +40,7 @@
 #define HNS_RCB_DEF_COALESCED_FRAMES		50
 #define HNS_RCB_CLK_FREQ_MHZ			350
 #define HNS_RCB_MAX_COALESCED_USECS		0x3ff
-#define HNS_RCB_DEF_COALESCED_USECS		3
+#define HNS_RCB_DEF_COALESCED_USECS		50
 
 #define HNS_RCB_COMMON_ENDIAN			1
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
index 7c3b510..235f744 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
@@ -32,7 +32,7 @@
 #define DSAFV2_SBM_NUM		8
 #define DSAFV2_SBM_XGE_CHN    6
 #define DSAFV2_SBM_PPE_CHN    1
-#define DASFV2_ROCEE_CRD_NUM  8
+#define DASFV2_ROCEE_CRD_NUM  1
 
 #define DSAF_VOQ_NUM		DSAF_NODE_NUM
 #define DSAF_INODE_NUM		DSAF_NODE_NUM
@@ -166,6 +166,9 @@
 #define DSAF_INODE_GE_FC_EN_0_REG		0x1B00
 #define DSAF_INODE_VC0_IN_PKT_NUM_0_REG		0x1B50
 #define DSAF_INODE_VC1_IN_PKT_NUM_0_REG		0x1C00
+#define DSAF_INODE_IN_PRIO_PAUSE_BASE_REG	0x1C00
+#define DSAF_INODE_IN_PRIO_PAUSE_BASE_OFFSET	0x100
+#define DSAF_INODE_IN_PRIO_PAUSE_OFFSET		0x50
 
 #define DSAF_SBM_CFG_REG_0_REG			0x2000
 #define DSAF_SBM_BP_CFG_0_XGE_REG_0_REG		0x2004
@@ -175,7 +178,7 @@
 #define DSAF_SBM_BP_CFG_2_XGE_REG_0_REG		0x200C
 #define DSAF_SBM_BP_CFG_2_PPE_REG_0_REG		0x230C
 #define DSAF_SBM_BP_CFG_2_ROCEE_REG_0_REG	0x260C
-#define DSAFV2_SBM_BP_CFG_2_ROCEE_REG_0_REG		 0x238C
+#define DSAFV2_SBM_BP_CFG_2_ROCEE_REG_0_REG	0x238C
 #define DSAF_SBM_FREE_CNT_0_0_REG		0x2010
 #define DSAF_SBM_FREE_CNT_1_0_REG		0x2014
 #define DSAF_SBM_BP_CNT_0_0_REG			0x2018
@@ -232,6 +235,8 @@
 #define DSAF_XOD_ROCEE_RCVIN0_CNT_0_REG		0x3074
 #define DSAF_XOD_ROCEE_RCVIN1_CNT_0_REG		0x3078
 #define DSAF_XOD_FIFO_STATUS_0_REG		0x307C
+#define DSAF_XOD_XGE_PFC_PRIO_CNT_BASE_REG	0x3A00
+#define DSAF_XOD_XGE_PFC_PRIO_CNT_OFFSET	0x4
 
 #define DSAF_VOQ_ECC_INVERT_EN_0_REG		0x4004
 #define DSAF_VOQ_SRAM_PKT_NUM_0_REG		0x4008
@@ -791,6 +796,18 @@
 #define DSAFV2_SBM_CFG4_RESET_BUF_NUM_NO_PFC_S 9
 #define DSAFV2_SBM_CFG4_RESET_BUF_NUM_NO_PFC_M (((1ULL << 9) - 1) << 9)
 
+#define DSAFV2_SBM_CFG2_ROCEE_SET_BUF_NUM_S 0
+#define DSAFV2_SBM_CFG2_ROCEE_SET_BUF_NUM_M (((1ULL << 8) - 1) << 0)
+#define DSAFV2_SBM_CFG2_ROCEE_RESET_BUF_NUM_S 8
+#define DSAFV2_SBM_CFG2_ROCEE_RESET_BUF_NUM_M (((1ULL << 8) - 1) << 8)
+
+#define DSAFV2_SBM_CFG2_PPE_SET_BUF_NUM_S (0)
+#define DSAFV2_SBM_CFG2_PPE_SET_BUF_NUM_M (((1ULL << 6) - 1) << 0)
+#define DSAFV2_SBM_CFG2_PPE_RESET_BUF_NUM_S (6)
+#define DSAFV2_SBM_CFG2_PPE_RESET_BUF_NUM_M (((1ULL << 6) - 1) << 6)
+#define DSAFV2_SBM_CFG2_PPE_CFG_USEFUL_NUM_S (12)
+#define DSAFV2_SBM_CFG2_PPE_CFG_USEFUL_NUM_M (((1ULL << 6) - 1) << 12)
+
 #define DSAF_TBL_TCAM_ADDR_S 0
 #define DSAF_TBL_TCAM_ADDR_M ((1ULL << 9) - 1)
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
index fd90f37..8f4f0e8 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
@@ -119,7 +119,7 @@
 		= (struct dsaf_device *)dev_get_drvdata(drv->dev);
 	u32 port = drv->mac_id;
 
-	hns_dsaf_xge_core_srst_by_port(dsaf_dev, port, 1);
+	dsaf_dev->misc_op->xge_core_srst(dsaf_dev, port, 1);
 	mdelay(10);
 
 	/*enable XGE rX/tX */
@@ -157,7 +157,7 @@
 	}
 
 	mdelay(10);
-	hns_dsaf_xge_core_srst_by_port(dsaf_dev, port, 0);
+	dsaf_dev->misc_op->xge_core_srst(dsaf_dev, port, 0);
 }
 
 /**
@@ -198,9 +198,9 @@
 		= (struct dsaf_device *)dev_get_drvdata(drv->dev);
 	u32 port = drv->mac_id;
 
-	hns_dsaf_xge_srst_by_port(dsaf_dev, port, 0);
+	dsaf_dev->misc_op->xge_srst(dsaf_dev, port, 0);
 	mdelay(100);
-	hns_dsaf_xge_srst_by_port(dsaf_dev, port, 1);
+	dsaf_dev->misc_op->xge_srst(dsaf_dev, port, 1);
 
 	mdelay(100);
 	hns_xgmac_exc_irq_en(drv, 0);
@@ -425,7 +425,7 @@
 
 	u32 mac_id = drv->mac_id;
 
-	hns_dsaf_xge_srst_by_port(dsaf_dev, mac_id, 0);
+	dsaf_dev->misc_op->xge_srst(dsaf_dev, mac_id, 0);
 }
 
 /**
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index e621636..d5297ec 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -132,6 +132,13 @@
 	ring_ptr_move_fw(ring, next_to_use);
 }
 
+static const struct acpi_device_id hns_enet_acpi_match[] = {
+	{ "HISI00C1", 0 },
+	{ "HISI00C2", 0 },
+	{ },
+};
+MODULE_DEVICE_TABLE(acpi, hns_enet_acpi_match);
+
 static void fill_desc(struct hnae_ring *ring, void *priv,
 		      int size, dma_addr_t dma, int frag_end,
 		      int buf_num, enum hns_desc_type type, int mtu)
@@ -593,6 +600,7 @@
 		ring->stats.sw_err_cnt++;
 		return -ENOMEM;
 	}
+	skb_reset_mac_header(skb);
 
 	prefetchw(skb->data);
 	length = le16_to_cpu(desc->rx.pkt_len);
@@ -760,10 +768,10 @@
 			clean_count = 0;
 		}
 
-		/* poll one pkg*/
+		/* poll one pkt*/
 		err = hns_nic_poll_rx_skb(ring_data, &skb, &bnum);
 		if (unlikely(!skb)) /* this fault cannot be repaired */
-			break;
+			goto out;
 
 		recv_bds += bnum;
 		clean_count += bnum;
@@ -789,6 +797,7 @@
 		}
 	}
 
+out:
 	/* make all data has been write before submit */
 	if (clean_count > 0)
 		hns_nic_alloc_rx_buffers(ring_data, clean_count);
@@ -983,8 +992,26 @@
 {
 	struct hns_nic_priv *priv = netdev_priv(ndev);
 	struct hnae_handle *h = priv->ae_handle;
+	int state = 1;
 
-	h->dev->ops->adjust_link(h, ndev->phydev->speed, ndev->phydev->duplex);
+	if (priv->phy) {
+		h->dev->ops->adjust_link(h, ndev->phydev->speed,
+					 ndev->phydev->duplex);
+		state = priv->phy->link;
+	}
+	state = state && h->dev->ops->get_status(h);
+
+	if (state != priv->link) {
+		if (state) {
+			netif_carrier_on(ndev);
+			netif_tx_wake_all_queues(ndev);
+			netdev_info(ndev, "link up\n");
+		} else {
+			netif_carrier_off(ndev);
+			netdev_info(ndev, "link down\n");
+		}
+		priv->link = state;
+	}
 }
 
 /**
@@ -996,19 +1023,22 @@
 int hns_nic_init_phy(struct net_device *ndev, struct hnae_handle *h)
 {
 	struct hns_nic_priv *priv = netdev_priv(ndev);
-	struct phy_device *phy_dev = NULL;
+	struct phy_device *phy_dev = h->phy_dev;
+	int ret;
 
-	if (!h->phy_node)
+	if (!h->phy_dev)
 		return 0;
 
-	if (h->phy_if != PHY_INTERFACE_MODE_XGMII)
-		phy_dev = of_phy_connect(ndev, h->phy_node,
-					 hns_nic_adjust_link, 0, h->phy_if);
-	else
-		phy_dev = of_phy_attach(ndev, h->phy_node, 0, h->phy_if);
+	if (h->phy_if != PHY_INTERFACE_MODE_XGMII) {
+		phy_dev->dev_flags = 0;
 
-	if (unlikely(!phy_dev) || IS_ERR(phy_dev))
-		return !phy_dev ? -ENODEV : PTR_ERR(phy_dev);
+		ret = phy_connect_direct(ndev, phy_dev, hns_nic_adjust_link,
+					 h->phy_if);
+	} else {
+		ret = phy_attach_direct(ndev, phy_dev, 0, h->phy_if);
+	}
+	if (unlikely(ret))
+		return -ENODEV;
 
 	phy_dev->supported &= h->if_support;
 	phy_dev->advertising = phy_dev->supported;
@@ -1067,13 +1097,8 @@
 static void hns_init_mac_addr(struct net_device *ndev)
 {
 	struct hns_nic_priv *priv = netdev_priv(ndev);
-	struct device_node *node = priv->dev->of_node;
-	const void *mac_addr_temp;
 
-	mac_addr_temp = of_get_mac_address(node);
-	if (mac_addr_temp && is_valid_ether_addr(mac_addr_temp)) {
-		memcpy(ndev->dev_addr, mac_addr_temp, ndev->addr_len);
-	} else {
+	if (!device_get_mac_address(priv->dev, ndev->dev_addr, ETH_ALEN)) {
 		eth_hw_addr_random(ndev);
 		dev_warn(priv->dev, "No valid mac, use random mac %pM",
 			 ndev->dev_addr);
@@ -1176,7 +1201,7 @@
 {
 	struct hns_nic_priv *priv = netdev_priv(ndev);
 	struct hnae_handle *h = priv->ae_handle;
-	int i, j, k;
+	int i, j;
 	int ret;
 
 	ret = hns_nic_init_irq(priv);
@@ -1191,9 +1216,6 @@
 			goto out_has_some_queues;
 	}
 
-	for (k = 0; k < h->q_num; k++)
-		h->dev->ops->toggle_queue_status(h->qs[k], 1);
-
 	ret = h->dev->ops->set_mac_addr(h, ndev->dev_addr);
 	if (ret)
 		goto out_set_mac_addr_err;
@@ -1213,8 +1235,6 @@
 out_start_err:
 	netif_stop_queue(ndev);
 out_set_mac_addr_err:
-	for (k = 0; k < h->q_num; k++)
-		h->dev->ops->toggle_queue_status(h->qs[k], 0);
 out_has_some_queues:
 	for (j = i - 1; j >= 0; j--)
 		hns_nic_ring_close(ndev, j);
@@ -1421,7 +1441,6 @@
 				netdev_features_t features)
 {
 	struct hns_nic_priv *priv = netdev_priv(netdev);
-	struct hnae_handle *h = priv->ae_handle;
 
 	switch (priv->enet_ver) {
 	case AE_VERSION_1:
@@ -1434,11 +1453,9 @@
 			priv->ops.maybe_stop_tx = hns_nic_maybe_stop_tso;
 			/* The chip only support 7*4096 */
 			netif_set_gso_max_size(netdev, 7 * 4096);
-			h->dev->ops->set_tso_stats(h, 1);
 		} else {
 			priv->ops.fill_desc = fill_v2_desc;
 			priv->ops.maybe_stop_tx = hns_nic_maybe_stop_tx;
-			h->dev->ops->set_tso_stats(h, 0);
 		}
 		break;
 	}
@@ -1571,27 +1588,14 @@
 	struct hns_nic_priv *priv = netdev_priv(netdev);
 
 	struct hnae_handle *h = priv->ae_handle;
-	int state = 1;
 
-	if (priv->phy) {
-		if (!genphy_update_link(priv->phy))
-			state = priv->phy->link;
-		else
-			state = 0;
-	}
-	state = state && h->dev->ops->get_status(h);
+	if (h->phy_dev) {
+		if (h->phy_if != PHY_INTERFACE_MODE_XGMII)
+			return;
 
-	if (state != priv->link) {
-		if (state) {
-			netif_carrier_on(netdev);
-			netif_tx_wake_all_queues(netdev);
-			netdev_info(netdev, "link up\n");
-		} else {
-			netif_carrier_off(netdev);
-			netdev_info(netdev, "link down\n");
-		}
-		priv->link = state;
+		(void)genphy_read_status(h->phy_dev);
 	}
+	hns_nic_adjust_link(netdev);
 }
 
 /* for dumping key regs*/
@@ -1627,7 +1631,7 @@
 	}
 }
 
-/* for resetting suntask*/
+/* for resetting subtask */
 static void hns_nic_reset_subtask(struct hns_nic_priv *priv)
 {
 	enum hnae_port_type type = priv->ae_handle->port_type;
@@ -1797,11 +1801,14 @@
 			priv->ops.maybe_stop_tx = hns_nic_maybe_stop_tso;
 			/* This chip only support 7*4096 */
 			netif_set_gso_max_size(netdev, 7 * 4096);
-			h->dev->ops->set_tso_stats(h, 1);
 		} else {
 			priv->ops.fill_desc = fill_v2_desc;
 			priv->ops.maybe_stop_tx = hns_nic_maybe_stop_tx;
 		}
+		/* enable tso when init
+		 * control tso on/off through TSE bit in bd
+		 */
+		h->dev->ops->set_tso_stats(h, 1);
 	}
 }
 
@@ -1812,7 +1819,7 @@
 	int ret;
 
 	h = hnae_get_handle(&priv->netdev->dev,
-			    priv->ae_node, priv->port_id, NULL);
+			    priv->fwnode, priv->port_id, NULL);
 	if (IS_ERR_OR_NULL(h)) {
 		ret = -ENODEV;
 		dev_dbg(priv->dev, "has not handle, register notifier!\n");
@@ -1872,7 +1879,6 @@
 	struct device *dev = &pdev->dev;
 	struct net_device *ndev;
 	struct hns_nic_priv *priv;
-	struct device_node *node = dev->of_node;
 	u32 port_id;
 	int ret;
 
@@ -1886,22 +1892,49 @@
 	priv->dev = dev;
 	priv->netdev = ndev;
 
-	if (of_device_is_compatible(node, "hisilicon,hns-nic-v1"))
-		priv->enet_ver = AE_VERSION_1;
-	else
-		priv->enet_ver = AE_VERSION_2;
+	if (dev_of_node(dev)) {
+		struct device_node *ae_node;
 
-	priv->ae_node = (void *)of_parse_phandle(node, "ae-handle", 0);
-	if (IS_ERR_OR_NULL(priv->ae_node)) {
-		ret = PTR_ERR(priv->ae_node);
-		dev_err(dev, "not find ae-handle\n");
-		goto out_read_prop_fail;
+		if (of_device_is_compatible(dev->of_node,
+					    "hisilicon,hns-nic-v1"))
+			priv->enet_ver = AE_VERSION_1;
+		else
+			priv->enet_ver = AE_VERSION_2;
+
+		ae_node = of_parse_phandle(dev->of_node, "ae-handle", 0);
+		if (IS_ERR_OR_NULL(ae_node)) {
+			ret = PTR_ERR(ae_node);
+			dev_err(dev, "not find ae-handle\n");
+			goto out_read_prop_fail;
+		}
+		priv->fwnode = &ae_node->fwnode;
+	} else if (is_acpi_node(dev->fwnode)) {
+		struct acpi_reference_args args;
+
+		if (acpi_dev_found(hns_enet_acpi_match[0].id))
+			priv->enet_ver = AE_VERSION_1;
+		else if (acpi_dev_found(hns_enet_acpi_match[1].id))
+			priv->enet_ver = AE_VERSION_2;
+		else
+			return -ENXIO;
+
+		/* try to find port-idx-in-ae first */
+		ret = acpi_node_get_property_reference(dev->fwnode,
+						       "ae-handle", 0, &args);
+		if (ret) {
+			dev_err(dev, "not find ae-handle\n");
+			goto out_read_prop_fail;
+		}
+		priv->fwnode = acpi_fwnode_handle(args.adev);
+	} else {
+		dev_err(dev, "cannot read cfg data from OF or acpi\n");
+		return -ENXIO;
 	}
-	/* try to find port-idx-in-ae first */
-	ret = of_property_read_u32(node, "port-idx-in-ae", &port_id);
+
+	ret = device_property_read_u32(dev, "port-idx-in-ae", &port_id);
 	if (ret) {
 		/* only for old code compatible */
-		ret = of_property_read_u32(node, "port-id", &port_id);
+		ret = device_property_read_u32(dev, "port-id", &port_id);
 		if (ret)
 			goto out_read_prop_fail;
 		/* for old dts, we need to caculate the port offset */
@@ -1940,7 +1973,7 @@
 	if (!dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)))
 		dev_dbg(dev, "set mask to 64bit\n");
 	else
-		dev_err(dev, "set mask to 32bit fail!\n");
+		dev_err(dev, "set mask to 64bit fail!\n");
 
 	/* carrier off reporting is important to ethtool even BEFORE open */
 	netif_carrier_off(ndev);
@@ -2014,6 +2047,7 @@
 	.driver = {
 		.name = "hns-nic",
 		.of_match_table = hns_enet_of_match,
+		.acpi_match_table = ACPI_PTR(hns_enet_acpi_match),
 	},
 	.probe = hns_nic_dev_probe,
 	.remove = hns_nic_dev_remove,
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.h b/drivers/net/ethernet/hisilicon/hns/hns_enet.h
index 337efa5..44bb301 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.h
@@ -54,7 +54,7 @@
 };
 
 struct hns_nic_priv {
-	const struct device_node *ae_node;
+	const struct fwnode_handle      *fwnode;
 	u32 enet_ver;
 	u32 port_id;
 	int phy_mode;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
index 67a648c..a395ca1 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
@@ -49,7 +49,7 @@
 	h = priv->ae_handle;
 
 	if (priv->phy) {
-		if (!genphy_update_link(priv->phy))
+		if (!genphy_read_status(priv->phy))
 			link_stat = priv->phy->link;
 		else
 			link_stat = 0;
@@ -242,6 +242,7 @@
 static int hns_nic_config_phy_loopback(struct phy_device *phy_dev, u8 en)
 {
 #define COPPER_CONTROL_REG 0
+#define PHY_POWER_DOWN BIT(11)
 #define PHY_LOOP_BACK BIT(14)
 	u16 val = 0;
 
@@ -252,33 +253,40 @@
 		/* speed : 1000M */
 		phy_write(phy_dev, HNS_PHY_PAGE_REG, 2);
 		phy_write(phy_dev, 21, 0x1046);
+
+		phy_write(phy_dev, HNS_PHY_PAGE_REG, 0);
 		/* Force Master */
 		phy_write(phy_dev, 9, 0x1F00);
+
 		/* Soft-reset */
 		phy_write(phy_dev, 0, 0x9140);
 		/* If autoneg disabled,two soft-reset operations */
 		phy_write(phy_dev, 0, 0x9140);
-		phy_write(phy_dev, 22, 0xFA);
+
+		phy_write(phy_dev, HNS_PHY_PAGE_REG, 0xFA);
 
 		/* Default is 0x0400 */
 		phy_write(phy_dev, 1, 0x418);
 
 		/* Force 1000M Link, Default is 0x0200 */
 		phy_write(phy_dev, 7, 0x20C);
-		phy_write(phy_dev, 22, 0);
+		phy_write(phy_dev, HNS_PHY_PAGE_REG, 0);
 
-		/* Enable MAC loop-back */
+		/* Enable PHY loop-back */
 		val = phy_read(phy_dev, COPPER_CONTROL_REG);
 		val |= PHY_LOOP_BACK;
+		val &= ~PHY_POWER_DOWN;
 		phy_write(phy_dev, COPPER_CONTROL_REG, val);
 	} else {
-		phy_write(phy_dev, 22, 0xFA);
+		phy_write(phy_dev, HNS_PHY_PAGE_REG, 0xFA);
 		phy_write(phy_dev, 1, 0x400);
 		phy_write(phy_dev, 7, 0x200);
-		phy_write(phy_dev, 22, 0);
+		phy_write(phy_dev, HNS_PHY_PAGE_REG, 0);
+		phy_write(phy_dev, 9, 0xF00);
 
 		val = phy_read(phy_dev, COPPER_CONTROL_REG);
 		val &= ~PHY_LOOP_BACK;
+		val |= PHY_POWER_DOWN;
 		phy_write(phy_dev, COPPER_CONTROL_REG, val);
 	}
 	return 0;
@@ -339,28 +347,16 @@
 
 	hns_nic_net_reset(ndev);
 
-	if (priv->phy) {
-		phy_disconnect(priv->phy);
-		msleep(100);
-
-		ret = hns_nic_init_phy(ndev, h);
-		if (ret)
-			return ret;
-	}
-
 	ret = __lb_setup(ndev, loop_mode);
 	if (ret)
 		return ret;
 
-	msleep(100);
+	msleep(200);
 
 	ret = h->dev->ops->start ? h->dev->ops->start(h) : 0;
 	if (ret)
 		return ret;
 
-	if (priv->phy)
-		phy_start(priv->phy);
-
 	/* link adjust duplex*/
 	if (priv->ae_handle->phy_if != PHY_INTERFACE_MODE_XGMII)
 		speed = 1000;
@@ -561,9 +557,6 @@
 			   __func__,
 			   ret);
 
-	if (priv->phy)
-		phy_stop(priv->phy);
-
 	if (h->dev->ops->stop)
 		h->dev->ops->stop(h);
 
@@ -596,7 +589,7 @@
 	st_param[1][0] = MAC_INTERNALLOOP_SERDES;
 	st_param[1][1] = 1; /*serdes must exist*/
 	st_param[2][0] = MAC_INTERNALLOOP_PHY; /* only supporte phy node*/
-	st_param[2][1] = ((!!(priv->ae_handle->phy_node)) &&
+	st_param[2][1] = ((!!(priv->ae_handle->phy_dev)) &&
 		(priv->ae_handle->phy_if != PHY_INTERFACE_MODE_XGMII));
 
 	if (eth_test->flags == ETH_TEST_FL_OFFLINE) {
@@ -758,6 +751,16 @@
 		&ec->tx_max_coalesced_frames,
 		&ec->rx_max_coalesced_frames);
 
+	ops->get_coalesce_range(priv->ae_handle,
+				&ec->tx_max_coalesced_frames_low,
+				&ec->rx_max_coalesced_frames_low,
+				&ec->tx_max_coalesced_frames_high,
+				&ec->rx_max_coalesced_frames_high,
+				&ec->tx_coalesce_usecs_low,
+				&ec->rx_coalesce_usecs_low,
+				&ec->tx_coalesce_usecs_high,
+				&ec->rx_coalesce_usecs_high);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c
index 765ddb3..761a32f 100644
--- a/drivers/net/ethernet/hisilicon/hns_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns_mdio.c
@@ -7,6 +7,7 @@
  * (at your option) any later version.
  */
 
+#include <linux/acpi.h>
 #include <linux/errno.h>
 #include <linux/etherdevice.h>
 #include <linux/init.h>
@@ -354,67 +355,64 @@
 	struct hns_mdio_device *mdio_dev = (struct hns_mdio_device *)bus->priv;
 	int ret;
 
-	if (!mdio_dev->subctrl_vbase) {
-		dev_err(&bus->dev, "mdio sys ctl reg has not maped\n");
-		return -ENODEV;
+	if (dev_of_node(bus->parent)) {
+		if (!mdio_dev->subctrl_vbase) {
+			dev_err(&bus->dev, "mdio sys ctl reg has not maped\n");
+			return -ENODEV;
+		}
+
+		/* 1. reset req, and read reset st check */
+		ret = mdio_sc_cfg_reg_write(mdio_dev, MDIO_SC_RESET_REQ, 0x1,
+					    MDIO_SC_RESET_ST, 0x1,
+					    MDIO_CHECK_SET_ST);
+		if (ret) {
+			dev_err(&bus->dev, "MDIO reset fail\n");
+			return ret;
+		}
+
+		/* 2. dis clk, and read clk st check */
+		ret = mdio_sc_cfg_reg_write(mdio_dev, MDIO_SC_CLK_DIS,
+					    0x1, MDIO_SC_CLK_ST, 0x1,
+					    MDIO_CHECK_CLR_ST);
+		if (ret) {
+			dev_err(&bus->dev, "MDIO dis clk fail\n");
+			return ret;
+		}
+
+		/* 3. reset dreq, and read reset st check */
+		ret = mdio_sc_cfg_reg_write(mdio_dev, MDIO_SC_RESET_DREQ, 0x1,
+					    MDIO_SC_RESET_ST, 0x1,
+					    MDIO_CHECK_CLR_ST);
+		if (ret) {
+			dev_err(&bus->dev, "MDIO dis clk fail\n");
+			return ret;
+		}
+
+		/* 4. en clk, and read clk st check */
+		ret = mdio_sc_cfg_reg_write(mdio_dev, MDIO_SC_CLK_EN,
+					    0x1, MDIO_SC_CLK_ST, 0x1,
+					    MDIO_CHECK_SET_ST);
+		if (ret)
+			dev_err(&bus->dev, "MDIO en clk fail\n");
+	} else if (is_acpi_node(bus->parent->fwnode)) {
+		acpi_status s;
+
+		s = acpi_evaluate_object(ACPI_HANDLE(bus->parent),
+					 "_RST", NULL, NULL);
+		if (ACPI_FAILURE(s)) {
+			dev_err(&bus->dev, "Reset failed, return:%#x\n", s);
+			ret = -EBUSY;
+		} else {
+			ret = 0;
+		}
+	} else {
+		dev_err(&bus->dev, "Can not get cfg data from DT or ACPI\n");
+		ret = -ENXIO;
 	}
-
-	/*1. reset req, and read reset st check*/
-	ret = mdio_sc_cfg_reg_write(mdio_dev, MDIO_SC_RESET_REQ, 0x1,
-				    MDIO_SC_RESET_ST, 0x1,
-				    MDIO_CHECK_SET_ST);
-	if (ret) {
-		dev_err(&bus->dev, "MDIO reset fail\n");
-		return ret;
-	}
-
-	/*2. dis clk, and read clk st check*/
-	ret = mdio_sc_cfg_reg_write(mdio_dev, MDIO_SC_CLK_DIS,
-				    0x1, MDIO_SC_CLK_ST, 0x1,
-				    MDIO_CHECK_CLR_ST);
-	if (ret) {
-		dev_err(&bus->dev, "MDIO dis clk fail\n");
-		return ret;
-	}
-
-	/*3. reset dreq, and read reset st check*/
-	ret = mdio_sc_cfg_reg_write(mdio_dev, MDIO_SC_RESET_DREQ, 0x1,
-				    MDIO_SC_RESET_ST, 0x1,
-				    MDIO_CHECK_CLR_ST);
-	if (ret) {
-		dev_err(&bus->dev, "MDIO dis clk fail\n");
-		return ret;
-	}
-
-	/*4. en clk, and read clk st check*/
-	ret = mdio_sc_cfg_reg_write(mdio_dev, MDIO_SC_CLK_EN,
-				    0x1, MDIO_SC_CLK_ST, 0x1,
-				    MDIO_CHECK_SET_ST);
-	if (ret)
-		dev_err(&bus->dev, "MDIO en clk fail\n");
-
 	return ret;
 }
 
 /**
- * hns_mdio_bus_name - get mdio bus name
- * @name: mdio bus name
- * @np: mdio device node pointer
- */
-static void hns_mdio_bus_name(char *name, struct device_node *np)
-{
-	const u32 *addr;
-	u64 taddr = OF_BAD_ADDR;
-
-	addr = of_get_address(np, 0, NULL, NULL);
-	if (addr)
-		taddr = of_translate_address(np, addr);
-
-	snprintf(name, MII_BUS_ID_SIZE, "%s@%llx", np->name,
-		 (unsigned long long)taddr);
-}
-
-/**
  * hns_mdio_probe - probe mdio device
  * @pdev: mdio platform device
  *
@@ -422,17 +420,16 @@
  */
 static int hns_mdio_probe(struct platform_device *pdev)
 {
-	struct device_node *np;
 	struct hns_mdio_device *mdio_dev;
 	struct mii_bus *new_bus;
 	struct resource *res;
-	int ret;
+	int ret = -ENODEV;
 
 	if (!pdev) {
 		dev_err(NULL, "pdev is NULL!\r\n");
 		return -ENODEV;
 	}
-	np = pdev->dev.of_node;
+
 	mdio_dev = devm_kzalloc(&pdev->dev, sizeof(*mdio_dev), GFP_KERNEL);
 	if (!mdio_dev)
 		return -ENOMEM;
@@ -448,7 +445,7 @@
 	new_bus->write = hns_mdio_write;
 	new_bus->reset = hns_mdio_reset;
 	new_bus->priv = mdio_dev;
-	hns_mdio_bus_name(new_bus->id, np);
+	new_bus->parent = &pdev->dev;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	mdio_dev->vbase = devm_ioremap_resource(&pdev->dev, res);
@@ -457,16 +454,32 @@
 		return ret;
 	}
 
-	mdio_dev->subctrl_vbase =
-		syscon_node_to_regmap(of_parse_phandle(np, "subctrl-vbase", 0));
-	if (IS_ERR(mdio_dev->subctrl_vbase)) {
-		dev_warn(&pdev->dev, "no syscon hisilicon,peri-c-subctrl\n");
-		mdio_dev->subctrl_vbase = NULL;
-	}
-	new_bus->parent = &pdev->dev;
 	platform_set_drvdata(pdev, new_bus);
+	snprintf(new_bus->id, MII_BUS_ID_SIZE, "%s-%s", "Mii",
+		 dev_name(&pdev->dev));
+	if (dev_of_node(&pdev->dev)) {
+		mdio_dev->subctrl_vbase = syscon_node_to_regmap(
+			of_parse_phandle(pdev->dev.of_node,
+					 "subctrl-vbase", 0));
+		if (IS_ERR(mdio_dev->subctrl_vbase)) {
+			dev_warn(&pdev->dev, "no syscon hisilicon,peri-c-subctrl\n");
+			mdio_dev->subctrl_vbase = NULL;
+		}
+		ret = of_mdiobus_register(new_bus, pdev->dev.of_node);
+	} else if (is_acpi_node(pdev->dev.fwnode)) {
+		/* Clear all the IRQ properties */
+		memset(new_bus->irq, PHY_POLL, 4 * PHY_MAX_ADDR);
 
-	ret = of_mdiobus_register(new_bus, np);
+		/* Mask out all PHYs from auto probing. */
+		new_bus->phy_mask = ~0;
+
+		/* Register the MDIO bus */
+		ret = mdiobus_register(new_bus);
+	} else {
+		dev_err(&pdev->dev, "Can not get cfg data from DT or ACPI\n");
+		ret = -ENXIO;
+	}
+
 	if (ret) {
 		dev_err(&pdev->dev, "Cannot register as MDIO bus!\n");
 		platform_set_drvdata(pdev, NULL);
@@ -499,12 +512,19 @@
 	{}
 };
 
+static const struct acpi_device_id hns_mdio_acpi_match[] = {
+	{ "HISI0141", 0 },
+	{ },
+};
+MODULE_DEVICE_TABLE(acpi, hns_mdio_acpi_match);
+
 static struct platform_driver hns_mdio_driver = {
 	.probe = hns_mdio_probe,
 	.remove = hns_mdio_remove,
 	.driver = {
 		   .name = MDIO_DRV_NAME,
 		   .of_match_table = hns_mdio_match,
+		   .acpi_match_table = ACPI_PTR(hns_mdio_acpi_match),
 		   },
 };
 
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig
index 714bd10..c0e1743 100644
--- a/drivers/net/ethernet/intel/Kconfig
+++ b/drivers/net/ethernet/intel/Kconfig
@@ -167,17 +167,6 @@
 	  To compile this driver as a module, choose M here. The module
 	  will be called ixgbe.
 
-config IXGBE_VXLAN
-	bool "Virtual eXtensible Local Area Network Support"
-	default n
-	depends on IXGBE && VXLAN && !(IXGBE=y && VXLAN=m)
-	---help---
-	  This allows one to create VXLAN virtual interfaces that provide
-	  Layer 2 Networks over Layer 3 Networks. VXLAN is often used
-	  to tunnel virtual network infrastructure in virtualized environments.
-	  Say Y here if you want to use Virtual eXtensible Local Area Network
-	  (VXLAN) in the driver.
-
 config IXGBE_HWMON
 	bool "Intel(R) 10GbE PCI Express adapters HWMON support"
 	default y
@@ -236,27 +225,6 @@
 	  To compile this driver as a module, choose M here. The module
 	  will be called i40e.
 
-config I40E_VXLAN
-	bool "Virtual eXtensible Local Area Network Support"
-	default n
-	depends on I40E && VXLAN && !(I40E=y && VXLAN=m)
-	---help---
-	  This allows one to create VXLAN virtual interfaces that provide
-	  Layer 2 Networks over Layer 3 Networks. VXLAN is often used
-	  to tunnel virtual network infrastructure in virtualized environments.
-	  Say Y here if you want to use Virtual eXtensible Local Area Network
-	  (VXLAN) in the driver.
-
-config I40E_GENEVE
-	bool "Generic Network Virtualization Encapsulation (GENEVE) Support"
-	depends on I40E && GENEVE && !(I40E=y && GENEVE=m)
-	default n
-	---help---
-	  This allows one to create GENEVE virtual interfaces that provide
-	  Layer 2 Networks over Layer 3 Networks. GENEVE is often used
-	  to tunnel virtual network infrastructure in virtualized environments.
-	  Say Y here if you want to use GENEVE in the driver.
-
 config I40E_DCB
 	bool "Data Center Bridging (DCB) Support"
 	default n
@@ -307,15 +275,4 @@
 	  To compile this driver as a module, choose M here. The module
 	  will be called fm10k.  MSI-X interrupt support is required
 
-config FM10K_VXLAN
-	bool "Virtual eXtensible Local Area Network Support"
-	default n
-	depends on FM10K && VXLAN && !(FM10K=y && VXLAN=m)
-	---help---
-	  This allows one to create VXLAN virtual interfaces that provide
-	  Layer 2 Networks over Layer 3 Networks. VXLAN is often used
-	  to tunnel virtual network infrastructure in virtualized environments.
-	  Say Y here if you want to use Virtual eXtensible Local Area Network
-	  (VXLAN) in the driver.
-
 endif # NET_VENDOR_INTEL
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
index 2a08d3f..d00cb19 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
@@ -20,9 +20,7 @@
 
 #include "fm10k.h"
 #include <linux/vmalloc.h>
-#ifdef CONFIG_FM10K_VXLAN
-#include <net/vxlan.h>
-#endif /* CONFIG_FM10K_VXLAN */
+#include <net/udp_tunnel.h>
 
 /**
  * fm10k_setup_tx_resources - allocate Tx resources (Descriptors)
@@ -436,6 +434,7 @@
  * @netdev: network interface device structure
  * @sa_family: Address family of new port
  * @port: port number used for VXLAN
+ * @type: Enumerated value specifying udp encapsulation type
  *
  * This function is called when a new VXLAN interface has added a new port
  * number to the range that is currently in use for VXLAN.  The new port
@@ -444,18 +443,21 @@
  * is always used as the VXLAN port number for offloads.
  **/
 static void fm10k_add_vxlan_port(struct net_device *dev,
-				 sa_family_t sa_family, __be16 port) {
+				 struct udp_tunnel_info *ti)
+{
 	struct fm10k_intfc *interface = netdev_priv(dev);
 	struct fm10k_vxlan_port *vxlan_port;
 
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
+		return;
 	/* only the PF supports configuring tunnels */
 	if (interface->hw.mac.type != fm10k_mac_pf)
 		return;
 
 	/* existing ports are pulled out so our new entry is always last */
 	fm10k_vxlan_port_for_each(vxlan_port, interface) {
-		if ((vxlan_port->port == port) &&
-		    (vxlan_port->sa_family == sa_family)) {
+		if ((vxlan_port->port == ti->port) &&
+		    (vxlan_port->sa_family == ti->sa_family)) {
 			list_del(&vxlan_port->list);
 			goto insert_tail;
 		}
@@ -465,8 +467,8 @@
 	vxlan_port = kmalloc(sizeof(*vxlan_port), GFP_ATOMIC);
 	if (!vxlan_port)
 		return;
-	vxlan_port->port = port;
-	vxlan_port->sa_family = sa_family;
+	vxlan_port->port = ti->port;
+	vxlan_port->sa_family = ti->sa_family;
 
 insert_tail:
 	/* add new port value to list */
@@ -480,6 +482,7 @@
  * @netdev: network interface device structure
  * @sa_family: Address family of freed port
  * @port: port number used for VXLAN
+ * @type: Enumerated value specifying udp encapsulation type
  *
  * This function is called when a new VXLAN interface has freed a port
  * number from the range that is currently in use for VXLAN.  The freed
@@ -487,17 +490,20 @@
  * the port number for offloads.
  **/
 static void fm10k_del_vxlan_port(struct net_device *dev,
-				 sa_family_t sa_family, __be16 port) {
+				 struct udp_tunnel_info *ti)
+{
 	struct fm10k_intfc *interface = netdev_priv(dev);
 	struct fm10k_vxlan_port *vxlan_port;
 
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
+		return;
 	if (interface->hw.mac.type != fm10k_mac_pf)
 		return;
 
 	/* find the port in the list and free it */
 	fm10k_vxlan_port_for_each(vxlan_port, interface) {
-		if ((vxlan_port->port == port) &&
-		    (vxlan_port->sa_family == sa_family)) {
+		if ((vxlan_port->port == ti->port) &&
+		    (vxlan_port->sa_family == ti->sa_family)) {
 			list_del(&vxlan_port->list);
 			kfree(vxlan_port);
 			break;
@@ -553,10 +559,8 @@
 	if (err)
 		goto err_set_queues;
 
-#ifdef CONFIG_FM10K_VXLAN
 	/* update VXLAN port configuration */
-	vxlan_get_rx_port(netdev);
-#endif
+	udp_tunnel_get_rx_info(netdev);
 
 	fm10k_up(interface);
 
@@ -1375,8 +1379,8 @@
 	.ndo_set_vf_vlan	= fm10k_ndo_set_vf_vlan,
 	.ndo_set_vf_rate	= fm10k_ndo_set_vf_bw,
 	.ndo_get_vf_config	= fm10k_ndo_get_vf_config,
-	.ndo_add_vxlan_port	= fm10k_add_vxlan_port,
-	.ndo_del_vxlan_port	= fm10k_del_vxlan_port,
+	.ndo_udp_tunnel_add	= fm10k_add_vxlan_port,
+	.ndo_udp_tunnel_del	= fm10k_del_vxlan_port,
 	.ndo_dfwd_add_station	= fm10k_dfwd_add_station,
 	.ndo_dfwd_del_station	= fm10k_dfwd_del_station,
 #ifdef CONFIG_NET_POLL_CONTROLLER
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 5ea2200..734cba6 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -31,12 +31,7 @@
 /* Local includes */
 #include "i40e.h"
 #include "i40e_diag.h"
-#if IS_ENABLED(CONFIG_VXLAN)
-#include <net/vxlan.h>
-#endif
-#if IS_ENABLED(CONFIG_GENEVE)
-#include <net/geneve.h>
-#endif
+#include <net/udp_tunnel.h>
 
 const char i40e_driver_name[] = "i40e";
 static const char i40e_driver_string[] =
@@ -5342,14 +5337,7 @@
 						       TCP_FLAG_CWR) >> 16);
 	wr32(&pf->hw, I40E_GLLAN_TSOMSK_L, be32_to_cpu(TCP_FLAG_CWR) >> 16);
 
-#ifdef CONFIG_I40E_VXLAN
-	vxlan_get_rx_port(netdev);
-#endif
-#ifdef CONFIG_I40E_GENEVE
-	if (pf->flags & I40E_FLAG_GENEVE_OFFLOAD_CAPABLE)
-		geneve_get_rx_port(netdev);
-#endif
-
+	udp_tunnel_get_rx_info(netdev);
 	i40e_notify_client_of_netdev_open(vsi);
 
 	return 0;
@@ -7057,7 +7045,6 @@
  **/
 static void i40e_sync_udp_filters_subtask(struct i40e_pf *pf)
 {
-#if IS_ENABLED(CONFIG_VXLAN) || IS_ENABLED(CONFIG_GENEVE)
 	struct i40e_hw *hw = &pf->hw;
 	i40e_status ret;
 	__be16 port;
@@ -7092,7 +7079,6 @@
 			}
 		}
 	}
-#endif
 }
 
 /**
@@ -8628,7 +8614,6 @@
 	return 0;
 }
 
-#if IS_ENABLED(CONFIG_VXLAN) || IS_ENABLED(CONFIG_GENEVE)
 /**
  * i40e_get_udp_port_idx - Lookup a possibly offloaded for Rx UDP port
  * @pf: board private structure
@@ -8648,21 +8633,18 @@
 	return i;
 }
 
-#endif
-
-#if IS_ENABLED(CONFIG_VXLAN)
 /**
- * i40e_add_vxlan_port - Get notifications about VXLAN ports that come up
+ * i40e_udp_tunnel_add - Get notifications about UDP tunnel ports that come up
  * @netdev: This physical port's netdev
- * @sa_family: Socket Family that VXLAN is notifying us about
- * @port: New UDP port number that VXLAN started listening to
+ * @ti: Tunnel endpoint information
  **/
-static void i40e_add_vxlan_port(struct net_device *netdev,
-				sa_family_t sa_family, __be16 port)
+static void i40e_udp_tunnel_add(struct net_device *netdev,
+				struct udp_tunnel_info *ti)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_pf *pf = vsi->back;
+	__be16 port = ti->port;
 	u8 next_idx;
 	u8 idx;
 
@@ -8670,7 +8652,7 @@
 
 	/* Check if port already exists */
 	if (idx < I40E_MAX_PF_UDP_OFFLOAD_PORTS) {
-		netdev_info(netdev, "vxlan port %d already offloaded\n",
+		netdev_info(netdev, "port %d already offloaded\n",
 			    ntohs(port));
 		return;
 	}
@@ -8679,132 +8661,76 @@
 	next_idx = i40e_get_udp_port_idx(pf, 0);
 
 	if (next_idx == I40E_MAX_PF_UDP_OFFLOAD_PORTS) {
-		netdev_info(netdev, "maximum number of vxlan UDP ports reached, not adding port %d\n",
+		netdev_info(netdev, "maximum number of offloaded UDP ports reached, not adding port %d\n",
 			    ntohs(port));
 		return;
 	}
 
+	switch (ti->type) {
+	case UDP_TUNNEL_TYPE_VXLAN:
+		pf->udp_ports[next_idx].type = I40E_AQC_TUNNEL_TYPE_VXLAN;
+		break;
+	case UDP_TUNNEL_TYPE_GENEVE:
+		if (!(pf->flags & I40E_FLAG_GENEVE_OFFLOAD_CAPABLE))
+			return;
+		pf->udp_ports[next_idx].type = I40E_AQC_TUNNEL_TYPE_NGE;
+		break;
+	default:
+		return;
+	}
+
 	/* New port: add it and mark its index in the bitmap */
 	pf->udp_ports[next_idx].index = port;
-	pf->udp_ports[next_idx].type = I40E_AQC_TUNNEL_TYPE_VXLAN;
 	pf->pending_udp_bitmap |= BIT_ULL(next_idx);
 	pf->flags |= I40E_FLAG_UDP_FILTER_SYNC;
 }
 
 /**
- * i40e_del_vxlan_port - Get notifications about VXLAN ports that go away
+ * i40e_udp_tunnel_del - Get notifications about UDP tunnel ports that go away
  * @netdev: This physical port's netdev
- * @sa_family: Socket Family that VXLAN is notifying us about
- * @port: UDP port number that VXLAN stopped listening to
+ * @ti: Tunnel endpoint information
  **/
-static void i40e_del_vxlan_port(struct net_device *netdev,
-				sa_family_t sa_family, __be16 port)
+static void i40e_udp_tunnel_del(struct net_device *netdev,
+				struct udp_tunnel_info *ti)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_pf *pf = vsi->back;
+	__be16 port = ti->port;
 	u8 idx;
 
 	idx = i40e_get_udp_port_idx(pf, port);
 
 	/* Check if port already exists */
-	if (idx < I40E_MAX_PF_UDP_OFFLOAD_PORTS) {
-		/* if port exists, set it to 0 (mark for deletion)
-		 * and make it pending
-		 */
-		pf->udp_ports[idx].index = 0;
-		pf->pending_udp_bitmap |= BIT_ULL(idx);
-		pf->flags |= I40E_FLAG_UDP_FILTER_SYNC;
-	} else {
-		netdev_warn(netdev, "vxlan port %d was not found, not deleting\n",
-			    ntohs(port));
-	}
-}
-#endif
+	if (idx >= I40E_MAX_PF_UDP_OFFLOAD_PORTS)
+		goto not_found;
 
-#if IS_ENABLED(CONFIG_GENEVE)
-/**
- * i40e_add_geneve_port - Get notifications about GENEVE ports that come up
- * @netdev: This physical port's netdev
- * @sa_family: Socket Family that GENEVE is notifying us about
- * @port: New UDP port number that GENEVE started listening to
- **/
-static void i40e_add_geneve_port(struct net_device *netdev,
-				 sa_family_t sa_family, __be16 port)
-{
-	struct i40e_netdev_priv *np = netdev_priv(netdev);
-	struct i40e_vsi *vsi = np->vsi;
-	struct i40e_pf *pf = vsi->back;
-	u8 next_idx;
-	u8 idx;
-
-	if (!(pf->flags & I40E_FLAG_GENEVE_OFFLOAD_CAPABLE))
-		return;
-
-	idx = i40e_get_udp_port_idx(pf, port);
-
-	/* Check if port already exists */
-	if (idx < I40E_MAX_PF_UDP_OFFLOAD_PORTS) {
-		netdev_info(netdev, "udp port %d already offloaded\n",
-			    ntohs(port));
-		return;
+	switch (ti->type) {
+	case UDP_TUNNEL_TYPE_VXLAN:
+		if (pf->udp_ports[idx].type != I40E_AQC_TUNNEL_TYPE_VXLAN)
+			goto not_found;
+		break;
+	case UDP_TUNNEL_TYPE_GENEVE:
+		if (pf->udp_ports[idx].type != I40E_AQC_TUNNEL_TYPE_NGE)
+			goto not_found;
+		break;
+	default:
+		goto not_found;
 	}
 
-	/* Now check if there is space to add the new port */
-	next_idx = i40e_get_udp_port_idx(pf, 0);
-
-	if (next_idx == I40E_MAX_PF_UDP_OFFLOAD_PORTS) {
-		netdev_info(netdev, "maximum number of UDP ports reached, not adding port %d\n",
-			    ntohs(port));
-		return;
-	}
-
-	/* New port: add it and mark its index in the bitmap */
-	pf->udp_ports[next_idx].index = port;
-	pf->udp_ports[next_idx].type = I40E_AQC_TUNNEL_TYPE_NGE;
-	pf->pending_udp_bitmap |= BIT_ULL(next_idx);
+	/* if port exists, set it to 0 (mark for deletion)
+	 * and make it pending
+	 */
+	pf->udp_ports[idx].index = 0;
+	pf->pending_udp_bitmap |= BIT_ULL(idx);
 	pf->flags |= I40E_FLAG_UDP_FILTER_SYNC;
 
-	dev_info(&pf->pdev->dev, "adding geneve port %d\n", ntohs(port));
+	return;
+not_found:
+	netdev_warn(netdev, "UDP port %d was not found, not deleting\n",
+		    ntohs(port));
 }
 
-/**
- * i40e_del_geneve_port - Get notifications about GENEVE ports that go away
- * @netdev: This physical port's netdev
- * @sa_family: Socket Family that GENEVE is notifying us about
- * @port: UDP port number that GENEVE stopped listening to
- **/
-static void i40e_del_geneve_port(struct net_device *netdev,
-				 sa_family_t sa_family, __be16 port)
-{
-	struct i40e_netdev_priv *np = netdev_priv(netdev);
-	struct i40e_vsi *vsi = np->vsi;
-	struct i40e_pf *pf = vsi->back;
-	u8 idx;
-
-	if (!(pf->flags & I40E_FLAG_GENEVE_OFFLOAD_CAPABLE))
-		return;
-
-	idx = i40e_get_udp_port_idx(pf, port);
-
-	/* Check if port already exists */
-	if (idx < I40E_MAX_PF_UDP_OFFLOAD_PORTS) {
-		/* if port exists, set it to 0 (mark for deletion)
-		 * and make it pending
-		 */
-		pf->udp_ports[idx].index = 0;
-		pf->pending_udp_bitmap |= BIT_ULL(idx);
-		pf->flags |= I40E_FLAG_UDP_FILTER_SYNC;
-
-		dev_info(&pf->pdev->dev, "deleting geneve port %d\n",
-			 ntohs(port));
-	} else {
-		netdev_warn(netdev, "geneve port %d was not found, not deleting\n",
-			    ntohs(port));
-	}
-}
-#endif
-
 static int i40e_get_phys_port_id(struct net_device *netdev,
 				 struct netdev_phys_item_id *ppid)
 {
@@ -9033,14 +8959,8 @@
 	.ndo_set_vf_link_state	= i40e_ndo_set_vf_link_state,
 	.ndo_set_vf_spoofchk	= i40e_ndo_set_vf_spoofchk,
 	.ndo_set_vf_trust	= i40e_ndo_set_vf_trust,
-#if IS_ENABLED(CONFIG_VXLAN)
-	.ndo_add_vxlan_port	= i40e_add_vxlan_port,
-	.ndo_del_vxlan_port	= i40e_del_vxlan_port,
-#endif
-#if IS_ENABLED(CONFIG_GENEVE)
-	.ndo_add_geneve_port	= i40e_add_geneve_port,
-	.ndo_del_geneve_port	= i40e_del_geneve_port,
-#endif
+	.ndo_udp_tunnel_add	= i40e_udp_tunnel_add,
+	.ndo_udp_tunnel_del	= i40e_udp_tunnel_del,
 	.ndo_get_phys_port_id	= i40e_get_phys_port_id,
 	.ndo_fdb_add		= i40e_ndo_fdb_add,
 	.ndo_features_check	= i40e_features_check,
@@ -10689,12 +10609,8 @@
 	}
 	if (pf->flags & I40E_FLAG_DCB_CAPABLE)
 		i += snprintf(&buf[i], REMAIN(i), " DCB");
-#if IS_ENABLED(CONFIG_VXLAN)
 	i += snprintf(&buf[i], REMAIN(i), " VxLAN");
-#endif
-#if IS_ENABLED(CONFIG_GENEVE)
 	i += snprintf(&buf[i], REMAIN(i), " Geneve");
-#endif
 	if (pf->flags & I40E_FLAG_PTP)
 		i += snprintf(&buf[i], REMAIN(i), " PTP");
 #ifdef I40E_FCOE
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 088c47c..468fa9d 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -50,7 +50,7 @@
 #include <linux/if_bridge.h>
 #include <linux/prefetch.h>
 #include <scsi/fc/fc_fcoe.h>
-#include <net/vxlan.h>
+#include <net/udp_tunnel.h>
 #include <net/pkt_cls.h>
 #include <net/tc_act/tc_gact.h>
 #include <net/tc_act/tc_mirred.h>
@@ -5722,9 +5722,7 @@
 #ifdef CONFIG_IXGBE_DCA
 		adapter->flags &= ~IXGBE_FLAG_DCA_CAPABLE;
 #endif
-#ifdef CONFIG_IXGBE_VXLAN
 		adapter->flags |= IXGBE_FLAG_VXLAN_OFFLOAD_CAPABLE;
-#endif
 		break;
 	default:
 		break;
@@ -6158,9 +6156,7 @@
 	ixgbe_up_complete(adapter);
 
 	ixgbe_clear_vxlan_port(adapter);
-#ifdef CONFIG_IXGBE_VXLAN
-	vxlan_get_rx_port(netdev);
-#endif
+	udp_tunnel_get_rx_info(netdev);
 
 	return 0;
 
@@ -7262,14 +7258,12 @@
 		ixgbe_service_event_complete(adapter);
 		return;
 	}
-#ifdef CONFIG_IXGBE_VXLAN
-	rtnl_lock();
 	if (adapter->flags2 & IXGBE_FLAG2_VXLAN_REREG_NEEDED) {
+		rtnl_lock();
 		adapter->flags2 &= ~IXGBE_FLAG2_VXLAN_REREG_NEEDED;
-		vxlan_get_rx_port(adapter->netdev);
+		udp_tunnel_get_rx_info(adapter->netdev);
+		rtnl_unlock();
 	}
-	rtnl_unlock();
-#endif /* CONFIG_IXGBE_VXLAN */
 	ixgbe_reset_subtask(adapter);
 	ixgbe_phy_interrupt_subtask(adapter);
 	ixgbe_sfp_detection_subtask(adapter);
@@ -7697,7 +7691,6 @@
 	/* snag network header to get L4 type and address */
 	skb = first->skb;
 	hdr.network = skb_network_header(skb);
-#ifdef CONFIG_IXGBE_VXLAN
 	if (skb->encapsulation &&
 	    first->protocol == htons(ETH_P_IP) &&
 	    hdr.ipv4->protocol != IPPROTO_UDP) {
@@ -7708,7 +7701,6 @@
 		    udp_hdr(skb)->dest == adapter->vxlan_port)
 			hdr.network = skb_inner_network_header(skb);
 	}
-#endif /* CONFIG_IXGBE_VXLAN */
 
 	/* Currently only IPv4/IPv6 with TCP is supported */
 	switch (hdr.ipv4->version) {
@@ -8770,14 +8762,12 @@
 
 	netdev->features = features;
 
-#ifdef CONFIG_IXGBE_VXLAN
 	if ((adapter->flags & IXGBE_FLAG_VXLAN_OFFLOAD_CAPABLE)) {
 		if (features & NETIF_F_RXCSUM)
 			adapter->flags2 |= IXGBE_FLAG2_VXLAN_REREG_NEEDED;
 		else
 			ixgbe_clear_vxlan_port(adapter);
 	}
-#endif /* CONFIG_IXGBE_VXLAN */
 
 	if (need_reset)
 		ixgbe_do_reset(netdev);
@@ -8788,23 +8778,27 @@
 	return 0;
 }
 
-#ifdef CONFIG_IXGBE_VXLAN
 /**
  * ixgbe_add_vxlan_port - Get notifications about VXLAN ports that come up
  * @dev: The port's netdev
  * @sa_family: Socket Family that VXLAN is notifiying us about
  * @port: New UDP port number that VXLAN started listening to
+ * @type: Enumerated type specifying UDP tunnel type
  **/
-static void ixgbe_add_vxlan_port(struct net_device *dev, sa_family_t sa_family,
-				 __be16 port)
+static void ixgbe_add_vxlan_port(struct net_device *dev,
+				 struct udp_tunnel_info *ti)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(dev);
 	struct ixgbe_hw *hw = &adapter->hw;
+	__be16 port = ti->port;
 
-	if (!(adapter->flags & IXGBE_FLAG_VXLAN_OFFLOAD_CAPABLE))
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
 		return;
 
-	if (sa_family == AF_INET6)
+	if (ti->sa_family != AF_INET)
+		return;
+
+	if (!(adapter->flags & IXGBE_FLAG_VXLAN_OFFLOAD_CAPABLE))
 		return;
 
 	if (adapter->vxlan_port == port)
@@ -8826,28 +8820,31 @@
  * @dev: The port's netdev
  * @sa_family: Socket Family that VXLAN is notifying us about
  * @port: UDP port number that VXLAN stopped listening to
+ * @type: Enumerated type specifying UDP tunnel type
  **/
-static void ixgbe_del_vxlan_port(struct net_device *dev, sa_family_t sa_family,
-				 __be16 port)
+static void ixgbe_del_vxlan_port(struct net_device *dev,
+				 struct udp_tunnel_info *ti)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(dev);
 
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
+		return;
+
+	if (ti->sa_family != AF_INET)
+		return;
+
 	if (!(adapter->flags & IXGBE_FLAG_VXLAN_OFFLOAD_CAPABLE))
 		return;
 
-	if (sa_family == AF_INET6)
-		return;
-
-	if (adapter->vxlan_port != port) {
+	if (adapter->vxlan_port != ti->port) {
 		netdev_info(dev, "Port %d was not found, not deleting\n",
-			    ntohs(port));
+			    ntohs(ti->port));
 		return;
 	}
 
 	ixgbe_clear_vxlan_port(adapter);
 	adapter->flags2 |= IXGBE_FLAG2_VXLAN_REREG_NEEDED;
 }
-#endif /* CONFIG_IXGBE_VXLAN */
 
 static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 			     struct net_device *dev,
@@ -9160,10 +9157,8 @@
 	.ndo_bridge_getlink	= ixgbe_ndo_bridge_getlink,
 	.ndo_dfwd_add_station	= ixgbe_fwd_add,
 	.ndo_dfwd_del_station	= ixgbe_fwd_del,
-#ifdef CONFIG_IXGBE_VXLAN
-	.ndo_add_vxlan_port	= ixgbe_add_vxlan_port,
-	.ndo_del_vxlan_port	= ixgbe_del_vxlan_port,
-#endif /* CONFIG_IXGBE_VXLAN */
+	.ndo_udp_tunnel_add	= ixgbe_add_vxlan_port,
+	.ndo_udp_tunnel_del	= ixgbe_del_vxlan_port,
 	.ndo_features_check	= ixgbe_features_check,
 };
 
diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c
index dc82b1b..0d2f8e9 100644
--- a/drivers/net/ethernet/lantiq_etop.c
+++ b/drivers/net/ethernet/lantiq_etop.c
@@ -411,7 +411,6 @@
 ltq_etop_mdio_init(struct net_device *dev)
 {
 	struct ltq_etop_priv *priv = netdev_priv(dev);
-	int i;
 	int err;
 
 	priv->mii_bus = mdiobus_alloc();
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index c984462..4763252 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -133,6 +133,8 @@
 static void mtk_phy_link_adjust(struct net_device *dev)
 {
 	struct mtk_mac *mac = netdev_priv(dev);
+	u16 lcl_adv = 0, rmt_adv = 0;
+	u8 flowctrl;
 	u32 mcr = MAC_MCR_MAX_RX_1536 | MAC_MCR_IPG_CFG |
 		  MAC_MCR_FORCE_MODE | MAC_MCR_TX_EN |
 		  MAC_MCR_RX_EN | MAC_MCR_BACKOFF_EN |
@@ -150,11 +152,30 @@
 	if (mac->phy_dev->link)
 		mcr |= MAC_MCR_FORCE_LINK;
 
-	if (mac->phy_dev->duplex)
+	if (mac->phy_dev->duplex) {
 		mcr |= MAC_MCR_FORCE_DPX;
 
-	if (mac->phy_dev->pause)
-		mcr |= MAC_MCR_FORCE_RX_FC | MAC_MCR_FORCE_TX_FC;
+		if (mac->phy_dev->pause)
+			rmt_adv = LPA_PAUSE_CAP;
+		if (mac->phy_dev->asym_pause)
+			rmt_adv |= LPA_PAUSE_ASYM;
+
+		if (mac->phy_dev->advertising & ADVERTISED_Pause)
+			lcl_adv |= ADVERTISE_PAUSE_CAP;
+		if (mac->phy_dev->advertising & ADVERTISED_Asym_Pause)
+			lcl_adv |= ADVERTISE_PAUSE_ASYM;
+
+		flowctrl = mii_resolve_flowctrl_fdx(lcl_adv, rmt_adv);
+
+		if (flowctrl & FLOW_CTRL_TX)
+			mcr |= MAC_MCR_FORCE_TX_FC;
+		if (flowctrl & FLOW_CTRL_RX)
+			mcr |= MAC_MCR_FORCE_RX_FC;
+
+		netif_dbg(mac->hw, link, dev, "rx pause %s, tx pause %s\n",
+			  flowctrl & FLOW_CTRL_RX ? "enabled" : "disabled",
+			  flowctrl & FLOW_CTRL_TX ? "enabled" : "disabled");
+	}
 
 	mtk_w32(mac->hw, mcr, MTK_MAC_MCR(mac->id));
 
@@ -208,10 +229,16 @@
 	u32 val, ge_mode;
 
 	np = of_parse_phandle(mac->of_node, "phy-handle", 0);
+	if (!np && of_phy_is_fixed_link(mac->of_node))
+		if (!of_phy_register_fixed_link(mac->of_node))
+			np = of_node_get(mac->of_node);
 	if (!np)
 		return -ENODEV;
 
 	switch (of_get_phy_mode(np)) {
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_ID:
 	case PHY_INTERFACE_MODE_RGMII:
 		ge_mode = 0;
 		break;
@@ -236,7 +263,8 @@
 	mac->phy_dev->autoneg = AUTONEG_ENABLE;
 	mac->phy_dev->speed = 0;
 	mac->phy_dev->duplex = 0;
-	mac->phy_dev->supported &= PHY_BASIC_FEATURES;
+	mac->phy_dev->supported &= PHY_GBIT_FEATURES | SUPPORTED_Pause |
+				   SUPPORTED_Asym_Pause;
 	mac->phy_dev->advertising = mac->phy_dev->supported |
 				    ADVERTISED_Autoneg;
 	phy_start_aneg(mac->phy_dev);
@@ -280,7 +308,7 @@
 	return 0;
 
 err_free_bus:
-	kfree(eth->mii_bus);
+	mdiobus_free(eth->mii_bus);
 
 err_put_node:
 	of_node_put(mii_np);
@@ -295,7 +323,7 @@
 
 	mdiobus_unregister(eth->mii_bus);
 	of_node_put(eth->mii_bus->dev.of_node);
-	kfree(eth->mii_bus);
+	mdiobus_free(eth->mii_bus);
 }
 
 static inline void mtk_irq_disable(struct mtk_eth *eth, u32 mask)
diff --git a/drivers/net/ethernet/mellanox/mlx4/Kconfig b/drivers/net/ethernet/mellanox/mlx4/Kconfig
index 9ca3734..5098e7f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx4/Kconfig
@@ -24,13 +24,6 @@
 
 	  If unsure, set to Y
 
-config MLX4_EN_VXLAN
-	bool "VXLAN offloads Support"
-	default y
-	depends on MLX4_EN && VXLAN && !(MLX4_EN=y && VXLAN=m)
-	---help---
-	  Say Y here if you want to use VXLAN offloads in the driver.
-
 config MLX4_CORE
 	tristate
 	depends on PCI
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
index f01918c..99c6bbd 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
@@ -37,6 +37,11 @@
 #include "mlx4_en.h"
 #include "fw_qos.h"
 
+enum {
+	MLX4_CEE_STATE_DOWN   = 0,
+	MLX4_CEE_STATE_UP     = 1,
+};
+
 /* Definitions for QCN
  */
 
@@ -80,13 +85,202 @@
 	__be32 reserved3[4];
 };
 
+static u8 mlx4_en_dcbnl_getcap(struct net_device *dev, int capid, u8 *cap)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+
+	switch (capid) {
+	case DCB_CAP_ATTR_PFC:
+		*cap = true;
+		break;
+	case DCB_CAP_ATTR_DCBX:
+		*cap = priv->cee_params.dcbx_cap;
+		break;
+	case DCB_CAP_ATTR_PFC_TCS:
+		*cap = 1 <<  mlx4_max_tc(priv->mdev->dev);
+		break;
+	default:
+		*cap = false;
+		break;
+	}
+
+	return 0;
+}
+
+static u8 mlx4_en_dcbnl_getpfcstate(struct net_device *netdev)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+
+	return priv->cee_params.dcb_cfg.pfc_state;
+}
+
+static void mlx4_en_dcbnl_setpfcstate(struct net_device *netdev, u8 state)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+
+	priv->cee_params.dcb_cfg.pfc_state = state;
+}
+
+static void mlx4_en_dcbnl_get_pfc_cfg(struct net_device *netdev, int priority,
+				      u8 *setting)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+
+	*setting = priv->cee_params.dcb_cfg.tc_config[priority].dcb_pfc;
+}
+
+static void mlx4_en_dcbnl_set_pfc_cfg(struct net_device *netdev, int priority,
+				      u8 setting)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+
+	priv->cee_params.dcb_cfg.tc_config[priority].dcb_pfc = setting;
+	priv->cee_params.dcb_cfg.pfc_state = true;
+}
+
+static int mlx4_en_dcbnl_getnumtcs(struct net_device *netdev, int tcid, u8 *num)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+
+	if (!(priv->flags & MLX4_EN_FLAG_DCB_ENABLED))
+		return -EINVAL;
+
+	if (tcid == DCB_NUMTCS_ATTR_PFC)
+		*num = mlx4_max_tc(priv->mdev->dev);
+	else
+		*num = 0;
+
+	return 0;
+}
+
+static u8 mlx4_en_dcbnl_set_all(struct net_device *netdev)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+	struct mlx4_en_dev *mdev = priv->mdev;
+	struct mlx4_en_cee_config *dcb_cfg = &priv->cee_params.dcb_cfg;
+	int err = 0;
+
+	if (!(priv->cee_params.dcbx_cap & DCB_CAP_DCBX_VER_CEE))
+		return -EINVAL;
+
+	if (dcb_cfg->pfc_state) {
+		int tc;
+
+		priv->prof->rx_pause = 0;
+		priv->prof->tx_pause = 0;
+		for (tc = 0; tc < CEE_DCBX_MAX_PRIO; tc++) {
+			u8 tc_mask = 1 << tc;
+
+			switch (dcb_cfg->tc_config[tc].dcb_pfc) {
+			case pfc_disabled:
+				priv->prof->tx_ppp &= ~tc_mask;
+				priv->prof->rx_ppp &= ~tc_mask;
+				break;
+			case pfc_enabled_full:
+				priv->prof->tx_ppp |= tc_mask;
+				priv->prof->rx_ppp |= tc_mask;
+				break;
+			case pfc_enabled_tx:
+				priv->prof->tx_ppp |= tc_mask;
+				priv->prof->rx_ppp &= ~tc_mask;
+				break;
+			case pfc_enabled_rx:
+				priv->prof->tx_ppp &= ~tc_mask;
+				priv->prof->rx_ppp |= tc_mask;
+				break;
+			default:
+				break;
+			}
+		}
+		en_dbg(DRV, priv, "Set pfc on\n");
+	} else {
+		priv->prof->rx_pause = 1;
+		priv->prof->tx_pause = 1;
+		en_dbg(DRV, priv, "Set pfc off\n");
+	}
+
+	err = mlx4_SET_PORT_general(mdev->dev, priv->port,
+				    priv->rx_skb_size + ETH_FCS_LEN,
+				    priv->prof->tx_pause,
+				    priv->prof->tx_ppp,
+				    priv->prof->rx_pause,
+				    priv->prof->rx_ppp);
+	if (err)
+		en_err(priv, "Failed setting pause params\n");
+	return err;
+}
+
+static u8 mlx4_en_dcbnl_get_state(struct net_device *dev)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+
+	if (priv->flags & MLX4_EN_FLAG_DCB_ENABLED)
+		return MLX4_CEE_STATE_UP;
+
+	return MLX4_CEE_STATE_DOWN;
+}
+
+static u8 mlx4_en_dcbnl_set_state(struct net_device *dev, u8 state)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	int num_tcs = 0;
+
+	if (!(priv->cee_params.dcbx_cap & DCB_CAP_DCBX_VER_CEE))
+		return 1;
+
+	if (!!(state) == !!(priv->flags & MLX4_EN_FLAG_DCB_ENABLED))
+		return 0;
+
+	if (state) {
+		priv->flags |= MLX4_EN_FLAG_DCB_ENABLED;
+		num_tcs = IEEE_8021QAZ_MAX_TCS;
+	} else {
+		priv->flags &= ~MLX4_EN_FLAG_DCB_ENABLED;
+	}
+
+	return mlx4_en_setup_tc(dev, num_tcs);
+}
+
+/* On success returns a non-zero 802.1p user priority bitmap
+ * otherwise returns 0 as the invalid user priority bitmap to
+ * indicate an error.
+ */
+static int mlx4_en_dcbnl_getapp(struct net_device *netdev, u8 idtype, u16 id)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+	struct dcb_app app = {
+				.selector = idtype,
+				.protocol = id,
+			     };
+	if (!(priv->cee_params.dcbx_cap & DCB_CAP_DCBX_VER_CEE))
+		return 0;
+
+	return dcb_getapp(netdev, &app);
+}
+
+static int mlx4_en_dcbnl_setapp(struct net_device *netdev, u8 idtype,
+				u16 id, u8 up)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+	struct dcb_app app;
+
+	if (!(priv->cee_params.dcbx_cap & DCB_CAP_DCBX_VER_CEE))
+		return -EINVAL;
+
+	memset(&app, 0, sizeof(struct dcb_app));
+	app.selector = idtype;
+	app.protocol = id;
+	app.priority = up;
+
+	return dcb_setapp(netdev, &app);
+}
+
 static int mlx4_en_dcbnl_ieee_getets(struct net_device *dev,
 				   struct ieee_ets *ets)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct ieee_ets *my_ets = &priv->ets;
 
-	/* No IEEE PFC settings available */
 	if (!my_ets)
 		return -EINVAL;
 
@@ -237,18 +431,51 @@
 
 static u8 mlx4_en_dcbnl_getdcbx(struct net_device *dev)
 {
-	return DCB_CAP_DCBX_HOST | DCB_CAP_DCBX_VER_IEEE;
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+
+	return priv->cee_params.dcbx_cap;
 }
 
 static u8 mlx4_en_dcbnl_setdcbx(struct net_device *dev, u8 mode)
 {
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	struct ieee_ets ets = {0};
+	struct ieee_pfc pfc = {0};
+
+	if (mode == priv->cee_params.dcbx_cap)
+		return 0;
+
 	if ((mode & DCB_CAP_DCBX_LLD_MANAGED) ||
-	    (mode & DCB_CAP_DCBX_VER_CEE) ||
-	    !(mode & DCB_CAP_DCBX_VER_IEEE) ||
+	    ((mode & DCB_CAP_DCBX_VER_IEEE) &&
+	     (mode & DCB_CAP_DCBX_VER_CEE)) ||
 	    !(mode & DCB_CAP_DCBX_HOST))
-		return 1;
+		goto err;
+
+	priv->cee_params.dcbx_cap = mode;
+
+	ets.ets_cap = IEEE_8021QAZ_MAX_TCS;
+	pfc.pfc_cap = IEEE_8021QAZ_MAX_TCS;
+
+	if (mode & DCB_CAP_DCBX_VER_IEEE) {
+		if (mlx4_en_dcbnl_ieee_setets(dev, &ets))
+			goto err;
+		if (mlx4_en_dcbnl_ieee_setpfc(dev, &pfc))
+			goto err;
+	} else if (mode & DCB_CAP_DCBX_VER_CEE) {
+		if (mlx4_en_dcbnl_set_all(dev))
+			goto err;
+	} else {
+		if (mlx4_en_dcbnl_ieee_setets(dev, &ets))
+			goto err;
+		if (mlx4_en_dcbnl_ieee_setpfc(dev, &pfc))
+			goto err;
+		if (mlx4_en_setup_tc(dev, 0))
+			goto err;
+	}
 
 	return 0;
+err:
+	return 1;
 }
 
 #define MLX4_RATELIMIT_UNITS_IN_KB 100000 /* rate-limit HW unit in Kbps */
@@ -463,24 +690,46 @@
 }
 
 const struct dcbnl_rtnl_ops mlx4_en_dcbnl_ops = {
-	.ieee_getets	= mlx4_en_dcbnl_ieee_getets,
-	.ieee_setets	= mlx4_en_dcbnl_ieee_setets,
-	.ieee_getmaxrate = mlx4_en_dcbnl_ieee_getmaxrate,
-	.ieee_setmaxrate = mlx4_en_dcbnl_ieee_setmaxrate,
-	.ieee_getpfc	= mlx4_en_dcbnl_ieee_getpfc,
-	.ieee_setpfc	= mlx4_en_dcbnl_ieee_setpfc,
+	.ieee_getets		= mlx4_en_dcbnl_ieee_getets,
+	.ieee_setets		= mlx4_en_dcbnl_ieee_setets,
+	.ieee_getmaxrate	= mlx4_en_dcbnl_ieee_getmaxrate,
+	.ieee_setmaxrate	= mlx4_en_dcbnl_ieee_setmaxrate,
+	.ieee_getqcn		= mlx4_en_dcbnl_ieee_getqcn,
+	.ieee_setqcn		= mlx4_en_dcbnl_ieee_setqcn,
+	.ieee_getqcnstats	= mlx4_en_dcbnl_ieee_getqcnstats,
+	.ieee_getpfc		= mlx4_en_dcbnl_ieee_getpfc,
+	.ieee_setpfc		= mlx4_en_dcbnl_ieee_setpfc,
+
+	.getstate	= mlx4_en_dcbnl_get_state,
+	.setstate	= mlx4_en_dcbnl_set_state,
+	.getpfccfg	= mlx4_en_dcbnl_get_pfc_cfg,
+	.setpfccfg	= mlx4_en_dcbnl_set_pfc_cfg,
+	.setall		= mlx4_en_dcbnl_set_all,
+	.getcap		= mlx4_en_dcbnl_getcap,
+	.getnumtcs	= mlx4_en_dcbnl_getnumtcs,
+	.getpfcstate	= mlx4_en_dcbnl_getpfcstate,
+	.setpfcstate	= mlx4_en_dcbnl_setpfcstate,
+	.getapp		= mlx4_en_dcbnl_getapp,
+	.setapp		= mlx4_en_dcbnl_setapp,
 
 	.getdcbx	= mlx4_en_dcbnl_getdcbx,
 	.setdcbx	= mlx4_en_dcbnl_setdcbx,
-	.ieee_getqcn	= mlx4_en_dcbnl_ieee_getqcn,
-	.ieee_setqcn	= mlx4_en_dcbnl_ieee_setqcn,
-	.ieee_getqcnstats = mlx4_en_dcbnl_ieee_getqcnstats,
 };
 
 const struct dcbnl_rtnl_ops mlx4_en_dcbnl_pfc_ops = {
 	.ieee_getpfc	= mlx4_en_dcbnl_ieee_getpfc,
 	.ieee_setpfc	= mlx4_en_dcbnl_ieee_setpfc,
 
+	.setstate	= mlx4_en_dcbnl_set_state,
+	.getpfccfg	= mlx4_en_dcbnl_get_pfc_cfg,
+	.setpfccfg	= mlx4_en_dcbnl_set_pfc_cfg,
+	.setall		= mlx4_en_dcbnl_set_all,
+	.getnumtcs	= mlx4_en_dcbnl_getnumtcs,
+	.getpfcstate	= mlx4_en_dcbnl_getpfcstate,
+	.setpfcstate	= mlx4_en_dcbnl_setpfcstate,
+	.getapp		= mlx4_en_dcbnl_getapp,
+	.setapp		= mlx4_en_dcbnl_setapp,
+
 	.getdcbx	= mlx4_en_dcbnl_getdcbx,
 	.setdcbx	= mlx4_en_dcbnl_setdcbx,
 };
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index fc95aff..51a2e82 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1107,7 +1107,7 @@
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 
-	return priv->rx_ring_num;
+	return rounddown_pow_of_two(priv->rx_ring_num);
 }
 
 static u32 mlx4_en_get_rxfh_key_size(struct net_device *netdev)
@@ -1141,19 +1141,17 @@
 			    u8 *hfunc)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
-	struct mlx4_en_rss_map *rss_map = &priv->rss_map;
-	int rss_rings;
-	size_t n = priv->rx_ring_num;
+	u32 n = mlx4_en_get_rxfh_indir_size(dev);
+	u32 i, rss_rings;
 	int err = 0;
 
-	rss_rings = priv->prof->rss_rings ?: priv->rx_ring_num;
-	rss_rings = 1 << ilog2(rss_rings);
+	rss_rings = priv->prof->rss_rings ?: n;
+	rss_rings = rounddown_pow_of_two(rss_rings);
 
-	while (n--) {
+	for (i = 0; i < n; i++) {
 		if (!ring_index)
 			break;
-		ring_index[n] = rss_map->qps[n % rss_rings].qpn -
-			rss_map->base_qpn;
+		ring_index[i] = i % rss_rings;
 	}
 	if (key)
 		memcpy(key, priv->rss_key, MLX4_EN_RSS_KEY_SIZE);
@@ -1166,6 +1164,7 @@
 			    const u8 *key, const u8 hfunc)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
+	u32 n = mlx4_en_get_rxfh_indir_size(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
 	int port_up = 0;
 	int err = 0;
@@ -1175,18 +1174,18 @@
 	/* Calculate RSS table size and make sure flows are spread evenly
 	 * between rings
 	 */
-	for (i = 0; i < priv->rx_ring_num; i++) {
+	for (i = 0; i < n; i++) {
 		if (!ring_index)
-			continue;
+			break;
 		if (i > 0 && !ring_index[i] && !rss_rings)
 			rss_rings = i;
 
-		if (ring_index[i] != (i % (rss_rings ?: priv->rx_ring_num)))
+		if (ring_index[i] != (i % (rss_rings ?: n)))
 			return -EINVAL;
 	}
 
 	if (!rss_rings)
-		rss_rings = priv->rx_ring_num;
+		rss_rings = n;
 
 	/* RSS table size must be an order of 2 */
 	if (!is_power_of_2(rss_rings))
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 19ceced..d42083a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -67,6 +67,17 @@
 		offset += priv->num_tx_rings_p_up;
 	}
 
+#ifdef CONFIG_MLX4_EN_DCB
+	if (!mlx4_is_slave(priv->mdev->dev)) {
+		if (up) {
+			priv->flags |= MLX4_EN_FLAG_DCB_ENABLED;
+		} else {
+			priv->flags &= ~MLX4_EN_FLAG_DCB_ENABLED;
+			priv->cee_params.dcb_cfg.pfc_state = false;
+		}
+	}
+#endif /* CONFIG_MLX4_EN_DCB */
+
 	return 0;
 }
 
@@ -1197,8 +1208,8 @@
 	struct mlx4_en_cq *cq;
 	int i;
 
-	for (i = 0; i < priv->rx_ring_num; i++) {
-		cq = priv->rx_cq[i];
+	for (i = 0; i < priv->tx_ring_num; i++) {
+		cq = priv->tx_cq[i];
 		napi_schedule(&cq->napi);
 	}
 }
@@ -1692,10 +1703,9 @@
 	/* Schedule multicast task to populate multicast list */
 	queue_work(mdev->workqueue, &priv->rx_mode_task);
 
-#ifdef CONFIG_MLX4_EN_VXLAN
 	if (priv->mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)
-		vxlan_get_rx_port(dev);
-#endif
+		udp_tunnel_get_rx_info(dev);
+
 	priv->port_up = true;
 	netif_tx_start_all_queues(dev);
 	netif_device_attach(dev);
@@ -2342,7 +2352,6 @@
 	return 0;
 }
 
-#ifdef CONFIG_MLX4_EN_VXLAN
 static void mlx4_en_add_vxlan_offloads(struct work_struct *work)
 {
 	int ret;
@@ -2392,15 +2401,19 @@
 }
 
 static void mlx4_en_add_vxlan_port(struct  net_device *dev,
-				   sa_family_t sa_family, __be16 port)
+				   struct udp_tunnel_info *ti)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
+	__be16 port = ti->port;
 	__be16 current_port;
 
-	if (priv->mdev->dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
 		return;
 
-	if (sa_family == AF_INET6)
+	if (ti->sa_family != AF_INET)
+		return;
+
+	if (priv->mdev->dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)
 		return;
 
 	current_port = priv->vxlan_port;
@@ -2415,15 +2428,19 @@
 }
 
 static void mlx4_en_del_vxlan_port(struct  net_device *dev,
-				   sa_family_t sa_family, __be16 port)
+				   struct udp_tunnel_info *ti)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
+	__be16 port = ti->port;
 	__be16 current_port;
 
-	if (priv->mdev->dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
 		return;
 
-	if (sa_family == AF_INET6)
+	if (ti->sa_family != AF_INET)
+		return;
+
+	if (priv->mdev->dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)
 		return;
 
 	current_port = priv->vxlan_port;
@@ -2453,7 +2470,6 @@
 
 	return features;
 }
-#endif
 
 static int mlx4_en_set_tx_maxrate(struct net_device *dev, int queue_index, u32 maxrate)
 {
@@ -2506,11 +2522,9 @@
 	.ndo_rx_flow_steer	= mlx4_en_filter_rfs,
 #endif
 	.ndo_get_phys_port_id	= mlx4_en_get_phys_port_id,
-#ifdef CONFIG_MLX4_EN_VXLAN
-	.ndo_add_vxlan_port	= mlx4_en_add_vxlan_port,
-	.ndo_del_vxlan_port	= mlx4_en_del_vxlan_port,
+	.ndo_udp_tunnel_add	= mlx4_en_add_vxlan_port,
+	.ndo_udp_tunnel_del	= mlx4_en_del_vxlan_port,
 	.ndo_features_check	= mlx4_en_features_check,
-#endif
 	.ndo_set_tx_maxrate	= mlx4_en_set_tx_maxrate,
 };
 
@@ -2544,11 +2558,9 @@
 	.ndo_rx_flow_steer	= mlx4_en_filter_rfs,
 #endif
 	.ndo_get_phys_port_id	= mlx4_en_get_phys_port_id,
-#ifdef CONFIG_MLX4_EN_VXLAN
-	.ndo_add_vxlan_port	= mlx4_en_add_vxlan_port,
-	.ndo_del_vxlan_port	= mlx4_en_del_vxlan_port,
+	.ndo_udp_tunnel_add	= mlx4_en_add_vxlan_port,
+	.ndo_udp_tunnel_del	= mlx4_en_del_vxlan_port,
 	.ndo_features_check	= mlx4_en_features_check,
-#endif
 	.ndo_set_tx_maxrate	= mlx4_en_set_tx_maxrate,
 };
 
@@ -2814,6 +2826,9 @@
 	struct mlx4_en_priv *priv;
 	int i;
 	int err;
+#ifdef CONFIG_MLX4_EN_DCB
+	struct tc_configuration *tc;
+#endif
 
 	dev = alloc_etherdev_mqs(sizeof(struct mlx4_en_priv),
 				 MAX_TX_RINGS, MAX_RX_RINGS);
@@ -2839,10 +2854,8 @@
 	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);
-#ifdef CONFIG_MLX4_EN_VXLAN
 	INIT_WORK(&priv->vxlan_add_task, mlx4_en_add_vxlan_offloads);
 	INIT_WORK(&priv->vxlan_del_task, mlx4_en_del_vxlan_offloads);
-#endif
 #ifdef CONFIG_RFS_ACCEL
 	INIT_LIST_HEAD(&priv->filters);
 	spin_lock_init(&priv->filters_lock);
@@ -2882,6 +2895,17 @@
 	priv->msg_enable = MLX4_EN_MSG_LEVEL;
 #ifdef CONFIG_MLX4_EN_DCB
 	if (!mlx4_is_slave(priv->mdev->dev)) {
+		priv->cee_params.dcbx_cap = DCB_CAP_DCBX_VER_CEE |
+					    DCB_CAP_DCBX_HOST |
+					    DCB_CAP_DCBX_VER_IEEE;
+		priv->flags |= MLX4_EN_DCB_ENABLED;
+		priv->cee_params.dcb_cfg.pfc_state = false;
+
+		for (i = 0; i < MLX4_EN_NUM_UP; i++) {
+			tc = &priv->cee_params.dcb_cfg.tc_config[i];
+			tc->dcb_pfc = pfc_disabled;
+		}
+
 		if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_ETS_CFG) {
 			dev->dcbnl_ops = &mlx4_en_dcbnl_ops;
 		} else {
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index e970945..f4497cf 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -1128,6 +1128,7 @@
 		port_cap->max_pkeys	   = 1 << (field & 0xf);
 		MLX4_GET(field, outbox, QUERY_PORT_MAX_VL_OFFSET);
 		port_cap->max_vl	   = field & 0xf;
+		port_cap->max_tc_eth	   = field >> 4;
 		MLX4_GET(field, outbox, QUERY_PORT_MAX_MACVLAN_OFFSET);
 		port_cap->log_max_macs  = field & 0xf;
 		port_cap->log_max_vlans = field >> 4;
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h
index 7ea258a..cdbd76f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.h
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.h
@@ -53,6 +53,7 @@
 	int ib_mtu;
 	int max_port_width;
 	int max_vl;
+	int max_tc_eth;
 	int max_gids;
 	int max_pkeys;
 	u64 def_mac;
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 12c77a7..3564aad 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -292,6 +292,7 @@
 	dev->caps.pkey_table_len[port] = port_cap->max_pkeys;
 	dev->caps.port_width_cap[port] = port_cap->max_port_width;
 	dev->caps.eth_mtu_cap[port]    = port_cap->eth_mtu;
+	dev->caps.max_tc_eth	       = port_cap->max_tc_eth;
 	dev->caps.def_mac[port]        = port_cap->def_mac;
 	dev->caps.supported_type[port] = port_cap->supported_port_types;
 	dev->caps.suggested_type[port] = port_cap->suggested_type;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 467d47e..d39bf59 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -448,6 +448,27 @@
 
 #define MLX4_EN_TC_ETS 7
 
+enum dcb_pfc_type {
+	pfc_disabled = 0,
+	pfc_enabled_full,
+	pfc_enabled_tx,
+	pfc_enabled_rx
+};
+
+struct tc_configuration {
+	enum dcb_pfc_type  dcb_pfc;
+};
+
+struct mlx4_en_cee_config {
+	bool	pfc_state;
+	struct	tc_configuration tc_config[MLX4_EN_NUM_UP];
+};
+
+struct mlx4_en_cee_params {
+	u8 dcbx_cap;
+	struct mlx4_en_cee_config dcb_cfg;
+};
+
 #endif
 
 struct ethtool_flow_id {
@@ -467,6 +488,9 @@
 	MLX4_EN_FLAG_RX_FILTER_NEEDED	= (1 << 3),
 	MLX4_EN_FLAG_FORCE_PROMISC	= (1 << 4),
 	MLX4_EN_FLAG_RX_CSUM_NON_TCP_UDP	= (1 << 5),
+#ifdef CONFIG_MLX4_EN_DCB
+	MLX4_EN_FLAG_DCB_ENABLED        = (1 << 6),
+#endif
 };
 
 #define PORT_BEACON_MAX_LIMIT (65535)
@@ -545,10 +569,8 @@
 	struct work_struct linkstate_task;
 	struct delayed_work stats_task;
 	struct delayed_work service_task;
-#ifdef CONFIG_MLX4_EN_VXLAN
 	struct work_struct vxlan_add_task;
 	struct work_struct vxlan_del_task;
-#endif
 	struct mlx4_en_perf_stats pstats;
 	struct mlx4_en_pkt_stats pkstats;
 	struct mlx4_en_counter_stats pf_stats;
@@ -570,9 +592,11 @@
 	u32 counter_index;
 
 #ifdef CONFIG_MLX4_EN_DCB
+#define MLX4_EN_DCB_ENABLED	0x3
 	struct ieee_ets ets;
 	u16 maxrate[IEEE_8021QAZ_MAX_TCS];
 	enum dcbnl_cndd_states cndd_state[IEEE_8021QAZ_MAX_TCS];
+	struct mlx4_en_cee_params cee_params;
 #endif
 #ifdef CONFIG_RFS_ACCEL
 	spinlock_t filters_lock;
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index 087b23b..3d2095e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -52,6 +52,7 @@
 
 #define MLX4_FLAG_V_IGNORE_FCS_MASK		0x2
 #define MLX4_IGNORE_FCS_MASK			0x1
+#define MLNX4_TX_MAX_NUMBER			8
 
 void mlx4_init_mac_table(struct mlx4_dev *dev, struct mlx4_mac_table *table)
 {
@@ -2015,3 +2016,14 @@
 	return ret;
 }
 EXPORT_SYMBOL(mlx4_get_module_info);
+
+int mlx4_max_tc(struct mlx4_dev *dev)
+{
+	u8 num_tc = dev->caps.max_tc_eth;
+
+	if (!num_tc)
+		num_tc = MLNX4_TX_MAX_NUMBER;
+
+	return num_tc;
+}
+EXPORT_SYMBOL(mlx4_max_tc);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index fd43929..8b7c6f3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2520,25 +2520,31 @@
 }
 
 static void mlx5e_add_vxlan_port(struct net_device *netdev,
-				 sa_family_t sa_family, __be16 port)
+				 struct udp_tunnel_info *ti)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
+		return;
+
 	if (!mlx5e_vxlan_allowed(priv->mdev))
 		return;
 
-	mlx5e_vxlan_queue_work(priv, sa_family, be16_to_cpu(port), 1);
+	mlx5e_vxlan_queue_work(priv, ti->sa_family, be16_to_cpu(ti->port), 1);
 }
 
 static void mlx5e_del_vxlan_port(struct net_device *netdev,
-				 sa_family_t sa_family, __be16 port)
+				 struct udp_tunnel_info *ti)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
+		return;
+
 	if (!mlx5e_vxlan_allowed(priv->mdev))
 		return;
 
-	mlx5e_vxlan_queue_work(priv, sa_family, be16_to_cpu(port), 0);
+	mlx5e_vxlan_queue_work(priv, ti->sa_family, be16_to_cpu(ti->port), 0);
 }
 
 static netdev_features_t mlx5e_vxlan_features_check(struct mlx5e_priv *priv,
@@ -2624,8 +2630,8 @@
 	.ndo_set_features        = mlx5e_set_features,
 	.ndo_change_mtu          = mlx5e_change_mtu,
 	.ndo_do_ioctl            = mlx5e_ioctl,
-	.ndo_add_vxlan_port      = mlx5e_add_vxlan_port,
-	.ndo_del_vxlan_port      = mlx5e_del_vxlan_port,
+	.ndo_udp_tunnel_add	 = mlx5e_add_vxlan_port,
+	.ndo_udp_tunnel_del	 = mlx5e_del_vxlan_port,
 	.ndo_features_check      = mlx5e_features_check,
 #ifdef CONFIG_RFS_ACCEL
 	.ndo_rx_flow_steer	 = mlx5e_rx_flow_steer,
@@ -3128,7 +3134,7 @@
 
 	if (mlx5e_vxlan_allowed(mdev)) {
 		rtnl_lock();
-		vxlan_get_rx_port(netdev);
+		udp_tunnel_get_rx_info(netdev);
 		rtnl_unlock();
 	}
 
@@ -3192,10 +3198,7 @@
 	flush_workqueue(priv->wq);
 	if (test_bit(MLX5_INTERFACE_STATE_SHUTDOWN, &mdev->intf_state)) {
 		netif_device_detach(netdev);
-		mutex_lock(&priv->state_lock);
-		if (test_bit(MLX5E_STATE_OPENED, &priv->state))
-			mlx5e_close_locked(netdev);
-		mutex_unlock(&priv->state_lock);
+		mlx5e_close(netdev);
 	} else {
 		unregister_netdev(netdev);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 229ab16..b000ddc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -317,7 +317,8 @@
 	while ((sq->pc & wq->sz_m1) > sq->edge)
 		mlx5e_send_nop(sq, false);
 
-	sq->bf_budget = bf ? sq->bf_budget - 1 : 0;
+	if (bf)
+		sq->bf_budget--;
 
 	sq->stats.packets++;
 	sq->stats.bytes += num_bytes;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index b84a691..aebbd6c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -383,7 +383,7 @@
 				   match_v,
 				   MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
 				   0, &dest);
-	if (IS_ERR_OR_NULL(flow_rule)) {
+	if (IS_ERR(flow_rule)) {
 		pr_warn(
 			"FDB: Failed to add flow rule: dmac_v(%pM) dmac_c(%pM) -> vport(%d), err(%ld)\n",
 			 dmac_v, dmac_c, vport, PTR_ERR(flow_rule));
@@ -457,7 +457,7 @@
 
 	table_size = BIT(MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size));
 	fdb = mlx5_create_flow_table(root_ns, 0, table_size, 0);
-	if (IS_ERR_OR_NULL(fdb)) {
+	if (IS_ERR(fdb)) {
 		err = PTR_ERR(fdb);
 		esw_warn(dev, "Failed to create FDB Table err %d\n", err);
 		goto out;
@@ -474,7 +474,7 @@
 	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, table_size - 3);
 	eth_broadcast_addr(dmac);
 	g = mlx5_create_flow_group(fdb, flow_group_in);
-	if (IS_ERR_OR_NULL(g)) {
+	if (IS_ERR(g)) {
 		err = PTR_ERR(g);
 		esw_warn(dev, "Failed to create flow group err(%d)\n", err);
 		goto out;
@@ -489,7 +489,7 @@
 	eth_zero_addr(dmac);
 	dmac[0] = 0x01;
 	g = mlx5_create_flow_group(fdb, flow_group_in);
-	if (IS_ERR_OR_NULL(g)) {
+	if (IS_ERR(g)) {
 		err = PTR_ERR(g);
 		esw_warn(dev, "Failed to create allmulti flow group err(%d)\n", err);
 		goto out;
@@ -506,7 +506,7 @@
 	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, table_size - 1);
 	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, table_size - 1);
 	g = mlx5_create_flow_group(fdb, flow_group_in);
-	if (IS_ERR_OR_NULL(g)) {
+	if (IS_ERR(g)) {
 		err = PTR_ERR(g);
 		esw_warn(dev, "Failed to create promisc flow group err(%d)\n", err);
 		goto out;
@@ -529,7 +529,7 @@
 		}
 	}
 
-	kfree(flow_group_in);
+	kvfree(flow_group_in);
 	return err;
 }
 
@@ -651,6 +651,7 @@
 					esw_fdb_set_vport_rule(esw,
 							       mac,
 							       vport_idx);
+			iter_vaddr->mc_promisc = true;
 			break;
 		case MLX5_ACTION_DEL:
 			if (!iter_vaddr)
@@ -1060,7 +1061,7 @@
 		return;
 
 	acl = mlx5_create_vport_flow_table(root_ns, 0, table_size, 0, vport->vport);
-	if (IS_ERR_OR_NULL(acl)) {
+	if (IS_ERR(acl)) {
 		err = PTR_ERR(acl);
 		esw_warn(dev, "Failed to create E-Switch vport[%d] egress flow Table, err(%d)\n",
 			 vport->vport, err);
@@ -1075,7 +1076,7 @@
 	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 0);
 
 	vlan_grp = mlx5_create_flow_group(acl, flow_group_in);
-	if (IS_ERR_OR_NULL(vlan_grp)) {
+	if (IS_ERR(vlan_grp)) {
 		err = PTR_ERR(vlan_grp);
 		esw_warn(dev, "Failed to create E-Switch vport[%d] egress allowed vlans flow group, err(%d)\n",
 			 vport->vport, err);
@@ -1086,7 +1087,7 @@
 	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 1);
 	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 1);
 	drop_grp = mlx5_create_flow_group(acl, flow_group_in);
-	if (IS_ERR_OR_NULL(drop_grp)) {
+	if (IS_ERR(drop_grp)) {
 		err = PTR_ERR(drop_grp);
 		esw_warn(dev, "Failed to create E-Switch vport[%d] egress drop flow group, err(%d)\n",
 			 vport->vport, err);
@@ -1097,7 +1098,7 @@
 	vport->egress.drop_grp = drop_grp;
 	vport->egress.allowed_vlans_grp = vlan_grp;
 out:
-	kfree(flow_group_in);
+	kvfree(flow_group_in);
 	if (err && !IS_ERR_OR_NULL(vlan_grp))
 		mlx5_destroy_flow_group(vlan_grp);
 	if (err && !IS_ERR_OR_NULL(acl))
@@ -1174,7 +1175,7 @@
 		return;
 
 	acl = mlx5_create_vport_flow_table(root_ns, 0, table_size, 0, vport->vport);
-	if (IS_ERR_OR_NULL(acl)) {
+	if (IS_ERR(acl)) {
 		err = PTR_ERR(acl);
 		esw_warn(dev, "Failed to create E-Switch vport[%d] ingress flow Table, err(%d)\n",
 			 vport->vport, err);
@@ -1192,7 +1193,7 @@
 	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 0);
 
 	g = mlx5_create_flow_group(acl, flow_group_in);
-	if (IS_ERR_OR_NULL(g)) {
+	if (IS_ERR(g)) {
 		err = PTR_ERR(g);
 		esw_warn(dev, "Failed to create E-Switch vport[%d] ingress untagged spoofchk flow group, err(%d)\n",
 			 vport->vport, err);
@@ -1207,7 +1208,7 @@
 	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 1);
 
 	g = mlx5_create_flow_group(acl, flow_group_in);
-	if (IS_ERR_OR_NULL(g)) {
+	if (IS_ERR(g)) {
 		err = PTR_ERR(g);
 		esw_warn(dev, "Failed to create E-Switch vport[%d] ingress untagged flow group, err(%d)\n",
 			 vport->vport, err);
@@ -1223,7 +1224,7 @@
 	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 2);
 
 	g = mlx5_create_flow_group(acl, flow_group_in);
-	if (IS_ERR_OR_NULL(g)) {
+	if (IS_ERR(g)) {
 		err = PTR_ERR(g);
 		esw_warn(dev, "Failed to create E-Switch vport[%d] ingress spoofchk flow group, err(%d)\n",
 			 vport->vport, err);
@@ -1236,7 +1237,7 @@
 	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 3);
 
 	g = mlx5_create_flow_group(acl, flow_group_in);
-	if (IS_ERR_OR_NULL(g)) {
+	if (IS_ERR(g)) {
 		err = PTR_ERR(g);
 		esw_warn(dev, "Failed to create E-Switch vport[%d] ingress drop flow group, err(%d)\n",
 			 vport->vport, err);
@@ -1259,7 +1260,7 @@
 			mlx5_destroy_flow_table(vport->ingress.acl);
 	}
 
-	kfree(flow_group_in);
+	kvfree(flow_group_in);
 }
 
 static void esw_vport_cleanup_ingress_rules(struct mlx5_eswitch *esw,
@@ -1363,7 +1364,7 @@
 				   match_v,
 				   MLX5_FLOW_CONTEXT_ACTION_ALLOW,
 				   0, NULL);
-	if (IS_ERR_OR_NULL(vport->ingress.allow_rule)) {
+	if (IS_ERR(vport->ingress.allow_rule)) {
 		err = PTR_ERR(vport->ingress.allow_rule);
 		pr_warn("vport[%d] configure ingress allow rule, err(%d)\n",
 			vport->vport, err);
@@ -1380,7 +1381,7 @@
 				   match_v,
 				   MLX5_FLOW_CONTEXT_ACTION_DROP,
 				   0, NULL);
-	if (IS_ERR_OR_NULL(vport->ingress.drop_rule)) {
+	if (IS_ERR(vport->ingress.drop_rule)) {
 		err = PTR_ERR(vport->ingress.drop_rule);
 		pr_warn("vport[%d] configure ingress drop rule, err(%d)\n",
 			vport->vport, err);
@@ -1439,7 +1440,7 @@
 				   match_v,
 				   MLX5_FLOW_CONTEXT_ACTION_ALLOW,
 				   0, NULL);
-	if (IS_ERR_OR_NULL(vport->egress.allowed_vlan)) {
+	if (IS_ERR(vport->egress.allowed_vlan)) {
 		err = PTR_ERR(vport->egress.allowed_vlan);
 		pr_warn("vport[%d] configure egress allowed vlan rule failed, err(%d)\n",
 			vport->vport, err);
@@ -1457,7 +1458,7 @@
 				   match_v,
 				   MLX5_FLOW_CONTEXT_ACTION_DROP,
 				   0, NULL);
-	if (IS_ERR_OR_NULL(vport->egress.drop_rule)) {
+	if (IS_ERR(vport->egress.drop_rule)) {
 		err = PTR_ERR(vport->egress.drop_rule);
 		pr_warn("vport[%d] configure egress drop rule failed, err(%d)\n",
 			vport->vport, err);
@@ -1491,14 +1492,11 @@
 
 	/* Sync with current vport context */
 	vport->enabled_events = enable_events;
-	esw_vport_change_handle_locked(vport);
-
 	vport->enabled = true;
 
 	/* only PF is trusted by default */
 	vport->trusted = (vport_num) ? false : true;
-
-	arm_vport_context_events_cmd(esw->dev, vport_num, enable_events);
+	esw_vport_change_handle_locked(vport);
 
 	esw->enabled_vports++;
 	esw_debug(esw->dev, "Enabled VPORT(%d)\n", vport_num);
@@ -1728,11 +1726,24 @@
 	(esw && MLX5_CAP_GEN(esw->dev, vport_group_manager) && mlx5_core_is_pf(esw->dev))
 #define LEGAL_VPORT(esw, vport) (vport >= 0 && vport < esw->total_vports)
 
+static void node_guid_gen_from_mac(u64 *node_guid, u8 mac[ETH_ALEN])
+{
+	((u8 *)node_guid)[7] = mac[0];
+	((u8 *)node_guid)[6] = mac[1];
+	((u8 *)node_guid)[5] = mac[2];
+	((u8 *)node_guid)[4] = 0xff;
+	((u8 *)node_guid)[3] = 0xfe;
+	((u8 *)node_guid)[2] = mac[3];
+	((u8 *)node_guid)[1] = mac[4];
+	((u8 *)node_guid)[0] = mac[5];
+}
+
 int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
 			       int vport, u8 mac[ETH_ALEN])
 {
-	int err = 0;
 	struct mlx5_vport *evport;
+	u64 node_guid;
+	int err = 0;
 
 	if (!ESW_ALLOWED(esw))
 		return -EPERM;
@@ -1756,11 +1767,17 @@
 		return err;
 	}
 
+	node_guid_gen_from_mac(&node_guid, mac);
+	err = mlx5_modify_nic_vport_node_guid(esw->dev, vport, node_guid);
+	if (err)
+		mlx5_core_warn(esw->dev,
+			       "Failed to set vport %d node guid, err = %d. RDMA_CM will not function properly for this VF.\n",
+			       vport, err);
+
 	mutex_lock(&esw->state_lock);
 	if (evport->enabled)
 		err = esw_vport_ingress_config(esw, evport);
 	mutex_unlock(&esw->state_lock);
-
 	return err;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 8b5f0b2..e912a3d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -1292,8 +1292,8 @@
 				       ft->id);
 			return err;
 		}
-		root->root_ft = new_root_ft;
 	}
+	root->root_ft = new_root_ft;
 	return 0;
 }
 
@@ -1767,6 +1767,9 @@
 
 void mlx5_cleanup_fs(struct mlx5_core_dev *dev)
 {
+	if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH)
+		return;
+
 	cleanup_root_ns(dev);
 	cleanup_single_prio_root_ns(dev, dev->priv.fdb_root_ns);
 	cleanup_single_prio_root_ns(dev, dev->priv.esw_egress_root_ns);
@@ -1828,29 +1831,36 @@
 {
 	int err = 0;
 
+	if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH)
+		return 0;
+
 	err = mlx5_init_fc_stats(dev);
 	if (err)
 		return err;
 
-	if (MLX5_CAP_GEN(dev, nic_flow_table)) {
+	if (MLX5_CAP_GEN(dev, nic_flow_table) &&
+	    MLX5_CAP_FLOWTABLE_NIC_RX(dev, ft_support)) {
 		err = init_root_ns(dev);
 		if (err)
 			goto err;
 	}
+
 	if (MLX5_CAP_GEN(dev, eswitch_flow_table)) {
-		err = init_fdb_root_ns(dev);
-		if (err)
-			goto err;
-	}
-	if (MLX5_CAP_ESW_EGRESS_ACL(dev, ft_support)) {
-		err = init_egress_acl_root_ns(dev);
-		if (err)
-			goto err;
-	}
-	if (MLX5_CAP_ESW_INGRESS_ACL(dev, ft_support)) {
-		err = init_ingress_acl_root_ns(dev);
-		if (err)
-			goto err;
+		if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, ft_support)) {
+			err = init_fdb_root_ns(dev);
+			if (err)
+				goto err;
+		}
+		if (MLX5_CAP_ESW_EGRESS_ACL(dev, ft_support)) {
+			err = init_egress_acl_root_ns(dev);
+			if (err)
+				goto err;
+		}
+		if (MLX5_CAP_ESW_INGRESS_ACL(dev, ft_support)) {
+			err = init_ingress_acl_root_ns(dev);
+			if (err)
+				goto err;
+		}
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
index b720a27..b82d658 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
@@ -418,7 +418,7 @@
 	if (out.hdr.status)
 		err = mlx5_cmd_status_to_err(&out.hdr);
 	else
-		*xrcdn = be32_to_cpu(out.xrcdn);
+		*xrcdn = be32_to_cpu(out.xrcdn) & 0xffffff;
 
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index b69dadc..daf44cd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -508,6 +508,44 @@
 }
 EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_node_guid);
 
+int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev,
+				    u32 vport, u64 node_guid)
+{
+	int inlen = MLX5_ST_SZ_BYTES(modify_nic_vport_context_in);
+	void *nic_vport_context;
+	u8 *guid;
+	void *in;
+	int err;
+
+	if (!vport)
+		return -EINVAL;
+	if (!MLX5_CAP_GEN(mdev, vport_group_manager))
+		return -EACCES;
+	if (!MLX5_CAP_ESW(mdev, nic_vport_node_guid_modify))
+		return -ENOTSUPP;
+
+	in = mlx5_vzalloc(inlen);
+	if (!in)
+		return -ENOMEM;
+
+	MLX5_SET(modify_nic_vport_context_in, in,
+		 field_select.node_guid, 1);
+	MLX5_SET(modify_nic_vport_context_in, in, vport_number, vport);
+	MLX5_SET(modify_nic_vport_context_in, in, other_vport, !!vport);
+
+	nic_vport_context = MLX5_ADDR_OF(modify_nic_vport_context_in,
+					 in, nic_vport_context);
+	guid = MLX5_ADDR_OF(nic_vport_context, nic_vport_context,
+			    node_guid);
+	MLX5_SET64(nic_vport_context, nic_vport_context, node_guid, node_guid);
+
+	err = mlx5_modify_nic_vport_context(mdev, in, inlen);
+
+	kvfree(in);
+
+	return err;
+}
+
 int mlx5_query_nic_vport_qkey_viol_cntr(struct mlx5_core_dev *mdev,
 					u16 *qkey_viol_cntr)
 {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index b0a0b01..01ae548 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -1736,7 +1736,7 @@
 {
 	int err;
 
-	mlxsw_wq = create_workqueue(mlxsw_core_driver_name);
+	mlxsw_wq = alloc_workqueue(mlxsw_core_driver_name, WQ_MEM_RECLAIM, 0);
 	if (!mlxsw_wq)
 		return -ENOMEM;
 	mlxsw_core_dbg_root = debugfs_create_dir(mlxsw_core_driver_name, NULL);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 4a72737..d23948b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -49,6 +49,7 @@
 #include <linux/jiffies.h>
 #include <linux/bitops.h>
 #include <linux/list.h>
+#include <linux/notifier.h>
 #include <linux/dcbnl.h>
 #include <net/switchdev.h>
 #include <generated/utsrelease.h>
@@ -247,13 +248,21 @@
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pmtu), pmtu_pl);
 }
 
+static int __mlxsw_sp_port_swid_set(struct mlxsw_sp *mlxsw_sp, u8 local_port,
+				    u8 swid)
+{
+	char pspa_pl[MLXSW_REG_PSPA_LEN];
+
+	mlxsw_reg_pspa_pack(pspa_pl, swid, local_port);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pspa), pspa_pl);
+}
+
 static int mlxsw_sp_port_swid_set(struct mlxsw_sp_port *mlxsw_sp_port, u8 swid)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
-	char pspa_pl[MLXSW_REG_PSPA_LEN];
 
-	mlxsw_reg_pspa_pack(pspa_pl, swid, mlxsw_sp_port->local_port);
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pspa), pspa_pl);
+	return __mlxsw_sp_port_swid_set(mlxsw_sp, mlxsw_sp_port->local_port,
+					swid);
 }
 
 static int mlxsw_sp_port_vp_mode_set(struct mlxsw_sp_port *mlxsw_sp_port,
@@ -305,9 +314,9 @@
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sspr), sspr_pl);
 }
 
-static int __mlxsw_sp_port_module_info_get(struct mlxsw_sp *mlxsw_sp,
-					   u8 local_port, u8 *p_module,
-					   u8 *p_width, u8 *p_lane)
+static int mlxsw_sp_port_module_info_get(struct mlxsw_sp *mlxsw_sp,
+					 u8 local_port, u8 *p_module,
+					 u8 *p_width, u8 *p_lane)
 {
 	char pmlp_pl[MLXSW_REG_PMLP_LEN];
 	int err;
@@ -322,16 +331,6 @@
 	return 0;
 }
 
-static int mlxsw_sp_port_module_info_get(struct mlxsw_sp *mlxsw_sp,
-					 u8 local_port, u8 *p_module,
-					 u8 *p_width)
-{
-	u8 lane;
-
-	return __mlxsw_sp_port_module_info_get(mlxsw_sp, local_port, p_module,
-					       p_width, &lane);
-}
-
 static int mlxsw_sp_port_module_map(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 				    u8 module, u8 width, u8 lane)
 {
@@ -634,14 +633,14 @@
 	return 0;
 }
 
-static struct mlxsw_sp_vfid *
+static struct mlxsw_sp_fid *
 mlxsw_sp_vfid_find(const struct mlxsw_sp *mlxsw_sp, u16 vid)
 {
-	struct mlxsw_sp_vfid *vfid;
+	struct mlxsw_sp_fid *f;
 
-	list_for_each_entry(vfid, &mlxsw_sp->port_vfids.list, list) {
-		if (vfid->vid == vid)
-			return vfid;
+	list_for_each_entry(f, &mlxsw_sp->port_vfids.list, list) {
+		if (f->vid == vid)
+			return f;
 	}
 
 	return NULL;
@@ -653,75 +652,70 @@
 				   MLXSW_SP_VFID_PORT_MAX);
 }
 
-static int __mlxsw_sp_vfid_create(struct mlxsw_sp *mlxsw_sp, u16 vfid)
+static int mlxsw_sp_vfid_op(struct mlxsw_sp *mlxsw_sp, u16 fid, bool create)
 {
-	u16 fid = mlxsw_sp_vfid_to_fid(vfid);
 	char sfmr_pl[MLXSW_REG_SFMR_LEN];
 
-	mlxsw_reg_sfmr_pack(sfmr_pl, MLXSW_REG_SFMR_OP_CREATE_FID, fid, 0);
+	mlxsw_reg_sfmr_pack(sfmr_pl, !create, fid, 0);
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfmr), sfmr_pl);
 }
 
-static void __mlxsw_sp_vfid_destroy(struct mlxsw_sp *mlxsw_sp, u16 vfid)
-{
-	u16 fid = mlxsw_sp_vfid_to_fid(vfid);
-	char sfmr_pl[MLXSW_REG_SFMR_LEN];
+static void mlxsw_sp_vport_vfid_leave(struct mlxsw_sp_port *mlxsw_sp_vport);
 
-	mlxsw_reg_sfmr_pack(sfmr_pl, MLXSW_REG_SFMR_OP_DESTROY_FID, fid, 0);
-	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfmr), sfmr_pl);
-}
-
-static struct mlxsw_sp_vfid *mlxsw_sp_vfid_create(struct mlxsw_sp *mlxsw_sp,
-						  u16 vid)
+static struct mlxsw_sp_fid *mlxsw_sp_vfid_create(struct mlxsw_sp *mlxsw_sp,
+						 u16 vid)
 {
 	struct device *dev = mlxsw_sp->bus_info->dev;
-	struct mlxsw_sp_vfid *vfid;
-	u16 n_vfid;
+	struct mlxsw_sp_fid *f;
+	u16 vfid, fid;
 	int err;
 
-	n_vfid = mlxsw_sp_avail_vfid_get(mlxsw_sp);
-	if (n_vfid == MLXSW_SP_VFID_PORT_MAX) {
+	vfid = mlxsw_sp_avail_vfid_get(mlxsw_sp);
+	if (vfid == MLXSW_SP_VFID_PORT_MAX) {
 		dev_err(dev, "No available vFIDs\n");
 		return ERR_PTR(-ERANGE);
 	}
 
-	err = __mlxsw_sp_vfid_create(mlxsw_sp, n_vfid);
+	fid = mlxsw_sp_vfid_to_fid(vfid);
+	err = mlxsw_sp_vfid_op(mlxsw_sp, fid, true);
 	if (err) {
-		dev_err(dev, "Failed to create vFID=%d\n", n_vfid);
+		dev_err(dev, "Failed to create FID=%d\n", fid);
 		return ERR_PTR(err);
 	}
 
-	vfid = kzalloc(sizeof(*vfid), GFP_KERNEL);
-	if (!vfid)
+	f = kzalloc(sizeof(*f), GFP_KERNEL);
+	if (!f)
 		goto err_allocate_vfid;
 
-	vfid->vfid = n_vfid;
-	vfid->vid = vid;
+	f->leave = mlxsw_sp_vport_vfid_leave;
+	f->fid = fid;
+	f->vid = vid;
 
-	list_add(&vfid->list, &mlxsw_sp->port_vfids.list);
-	set_bit(n_vfid, mlxsw_sp->port_vfids.mapped);
+	list_add(&f->list, &mlxsw_sp->port_vfids.list);
+	set_bit(vfid, mlxsw_sp->port_vfids.mapped);
 
-	return vfid;
+	return f;
 
 err_allocate_vfid:
-	__mlxsw_sp_vfid_destroy(mlxsw_sp, n_vfid);
+	mlxsw_sp_vfid_op(mlxsw_sp, fid, false);
 	return ERR_PTR(-ENOMEM);
 }
 
 static void mlxsw_sp_vfid_destroy(struct mlxsw_sp *mlxsw_sp,
-				  struct mlxsw_sp_vfid *vfid)
+				  struct mlxsw_sp_fid *f)
 {
-	clear_bit(vfid->vfid, mlxsw_sp->port_vfids.mapped);
-	list_del(&vfid->list);
+	u16 vfid = mlxsw_sp_fid_to_vfid(f->fid);
 
-	__mlxsw_sp_vfid_destroy(mlxsw_sp, vfid->vfid);
+	clear_bit(vfid, mlxsw_sp->port_vfids.mapped);
+	list_del(&f->list);
 
-	kfree(vfid);
+	mlxsw_sp_vfid_op(mlxsw_sp, f->fid, false);
+
+	kfree(f);
 }
 
 static struct mlxsw_sp_port *
-mlxsw_sp_port_vport_create(struct mlxsw_sp_port *mlxsw_sp_port,
-			   struct mlxsw_sp_vfid *vfid)
+mlxsw_sp_port_vport_create(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid)
 {
 	struct mlxsw_sp_port *mlxsw_sp_vport;
 
@@ -739,8 +733,7 @@
 	mlxsw_sp_vport->stp_state = BR_STATE_FORWARDING;
 	mlxsw_sp_vport->lagged = mlxsw_sp_port->lagged;
 	mlxsw_sp_vport->lag_id = mlxsw_sp_port->lag_id;
-	mlxsw_sp_vport->vport.vfid = vfid;
-	mlxsw_sp_vport->vport.vid = vfid->vid;
+	mlxsw_sp_vport->vport.vid = vid;
 
 	list_add(&mlxsw_sp_vport->vport.list, &mlxsw_sp_port->vports_list);
 
@@ -753,13 +746,72 @@
 	kfree(mlxsw_sp_vport);
 }
 
+static int mlxsw_sp_vport_fid_map(struct mlxsw_sp_port *mlxsw_sp_vport, u16 fid,
+				  bool valid)
+{
+	enum mlxsw_reg_svfa_mt mt = MLXSW_REG_SVFA_MT_PORT_VID_TO_FID;
+	u16 vid = mlxsw_sp_vport_vid_get(mlxsw_sp_vport);
+
+	return mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport, mt, valid, fid,
+					    vid);
+}
+
+static int mlxsw_sp_vport_vfid_join(struct mlxsw_sp_port *mlxsw_sp_vport)
+{
+	u16 vid = mlxsw_sp_vport_vid_get(mlxsw_sp_vport);
+	struct mlxsw_sp_fid *f;
+	int err;
+
+	f = mlxsw_sp_vfid_find(mlxsw_sp_vport->mlxsw_sp, vid);
+	if (!f) {
+		f = mlxsw_sp_vfid_create(mlxsw_sp_vport->mlxsw_sp, vid);
+		if (IS_ERR(f))
+			return PTR_ERR(f);
+	}
+
+	if (!f->ref_count) {
+		err = mlxsw_sp_vport_flood_set(mlxsw_sp_vport, f->fid, true);
+		if (err)
+			goto err_vport_flood_set;
+	}
+
+	err = mlxsw_sp_vport_fid_map(mlxsw_sp_vport, f->fid, true);
+	if (err)
+		goto err_vport_fid_map;
+
+	mlxsw_sp_vport_fid_set(mlxsw_sp_vport, f);
+	f->ref_count++;
+
+	return 0;
+
+err_vport_fid_map:
+	if (!f->ref_count)
+		mlxsw_sp_vport_flood_set(mlxsw_sp_vport, f->fid, false);
+err_vport_flood_set:
+	if (!f->ref_count)
+		mlxsw_sp_vfid_destroy(mlxsw_sp_vport->mlxsw_sp, f);
+	return err;
+}
+
+static void mlxsw_sp_vport_vfid_leave(struct mlxsw_sp_port *mlxsw_sp_vport)
+{
+	struct mlxsw_sp_fid *f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport);
+
+	mlxsw_sp_vport_fid_set(mlxsw_sp_vport, NULL);
+
+	mlxsw_sp_vport_fid_map(mlxsw_sp_vport, f->fid, false);
+
+	if (--f->ref_count == 0) {
+		mlxsw_sp_vport_flood_set(mlxsw_sp_vport, f->fid, false);
+		mlxsw_sp_vfid_destroy(mlxsw_sp_vport->mlxsw_sp, f);
+	}
+}
+
 int mlxsw_sp_port_add_vid(struct net_device *dev, __be16 __always_unused proto,
 			  u16 vid)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	struct mlxsw_sp_port *mlxsw_sp_vport;
-	struct mlxsw_sp_vfid *vfid;
 	int err;
 
 	/* VLAN 0 is added to HW filter when device goes up, but it is
@@ -773,31 +825,10 @@
 		return 0;
 	}
 
-	vfid = mlxsw_sp_vfid_find(mlxsw_sp, vid);
-	if (!vfid) {
-		vfid = mlxsw_sp_vfid_create(mlxsw_sp, vid);
-		if (IS_ERR(vfid)) {
-			netdev_err(dev, "Failed to create vFID for VID=%d\n",
-				   vid);
-			return PTR_ERR(vfid);
-		}
-	}
-
-	mlxsw_sp_vport = mlxsw_sp_port_vport_create(mlxsw_sp_port, vfid);
+	mlxsw_sp_vport = mlxsw_sp_port_vport_create(mlxsw_sp_port, vid);
 	if (!mlxsw_sp_vport) {
 		netdev_err(dev, "Failed to create vPort for VID=%d\n", vid);
-		err = -ENOMEM;
-		goto err_port_vport_create;
-	}
-
-	if (!vfid->nr_vports) {
-		err = mlxsw_sp_vport_flood_set(mlxsw_sp_vport, vfid->vfid,
-					       true, false);
-		if (err) {
-			netdev_err(dev, "Failed to setup flooding for vFID=%d\n",
-				   vfid->vfid);
-			goto err_vport_flood_set;
-		}
+		return -ENOMEM;
 	}
 
 	/* When adding the first VLAN interface on a bridged port we need to
@@ -812,15 +843,10 @@
 		}
 	}
 
-	err = mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport,
-					   MLXSW_REG_SVFA_MT_PORT_VID_TO_FID,
-					   true,
-					   mlxsw_sp_vfid_to_fid(vfid->vfid),
-					   vid);
+	err = mlxsw_sp_vport_vfid_join(mlxsw_sp_vport);
 	if (err) {
-		netdev_err(dev, "Failed to map {Port, VID=%d} to vFID=%d\n",
-			   vid, vfid->vfid);
-		goto err_port_vid_to_fid_set;
+		netdev_err(dev, "Failed to join vFID\n");
+		goto err_vport_vfid_join;
 	}
 
 	err = mlxsw_sp_port_vid_learning_set(mlxsw_sp_vport, vid, false);
@@ -843,8 +869,6 @@
 		goto err_port_stp_state_set;
 	}
 
-	vfid->nr_vports++;
-
 	return 0;
 
 err_port_stp_state_set:
@@ -852,21 +876,12 @@
 err_port_add_vid:
 	mlxsw_sp_port_vid_learning_set(mlxsw_sp_vport, vid, true);
 err_port_vid_learning_set:
-	mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport,
-				     MLXSW_REG_SVFA_MT_PORT_VID_TO_FID, false,
-				     mlxsw_sp_vfid_to_fid(vfid->vfid), vid);
-err_port_vid_to_fid_set:
+	mlxsw_sp_vport_vfid_leave(mlxsw_sp_vport);
+err_vport_vfid_join:
 	if (list_is_singular(&mlxsw_sp_port->vports_list))
 		mlxsw_sp_port_vlan_mode_trans(mlxsw_sp_port);
 err_port_vp_mode_trans:
-	if (!vfid->nr_vports)
-		mlxsw_sp_vport_flood_set(mlxsw_sp_vport, vfid->vfid, false,
-					 false);
-err_vport_flood_set:
 	mlxsw_sp_port_vport_destroy(mlxsw_sp_vport);
-err_port_vport_create:
-	if (!vfid->nr_vports)
-		mlxsw_sp_vfid_destroy(mlxsw_sp, vfid);
 	return err;
 }
 
@@ -875,7 +890,7 @@
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
 	struct mlxsw_sp_port *mlxsw_sp_vport;
-	struct mlxsw_sp_vfid *vfid;
+	struct mlxsw_sp_fid *f;
 	int err;
 
 	/* VLAN 0 is removed from HW filter when device goes down, but
@@ -890,8 +905,6 @@
 		return 0;
 	}
 
-	vfid = mlxsw_sp_vport->vport.vfid;
-
 	err = mlxsw_sp_port_stp_state_set(mlxsw_sp_vport, vid,
 					  MLXSW_REG_SPMS_STATE_DISCARDING);
 	if (err) {
@@ -912,16 +925,12 @@
 		return err;
 	}
 
-	err = mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport,
-					   MLXSW_REG_SVFA_MT_PORT_VID_TO_FID,
-					   false,
-					   mlxsw_sp_vfid_to_fid(vfid->vfid),
-					   vid);
-	if (err) {
-		netdev_err(dev, "Failed to invalidate {Port, VID=%d} to vFID=%d mapping\n",
-			   vid, vfid->vfid);
-		return err;
-	}
+	/* Drop FID reference. If this was the last reference the
+	 * resources will be freed.
+	 */
+	f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport);
+	if (f && !WARN_ON(!f->leave))
+		f->leave(mlxsw_sp_vport);
 
 	/* When removing the last VLAN interface on a bridged port we need to
 	 * transition all active 802.1Q bridge VLANs to use VID to FID
@@ -935,13 +944,8 @@
 		}
 	}
 
-	vfid->nr_vports--;
 	mlxsw_sp_port_vport_destroy(mlxsw_sp_vport);
 
-	/* Destroy the vFID if no vPorts are assigned to it anymore. */
-	if (!vfid->nr_vports)
-		mlxsw_sp_vfid_destroy(mlxsw_sp_port->mlxsw_sp, vfid);
-
 	return 0;
 }
 
@@ -949,17 +953,11 @@
 					    size_t len)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
-	u8 module, width, lane;
+	u8 module = mlxsw_sp_port->mapping.module;
+	u8 width = mlxsw_sp_port->mapping.width;
+	u8 lane = mlxsw_sp_port->mapping.lane;
 	int err;
 
-	err = __mlxsw_sp_port_module_info_get(mlxsw_sp_port->mlxsw_sp,
-					      mlxsw_sp_port->local_port,
-					      &module, &width, &lane);
-	if (err) {
-		netdev_err(dev, "Failed to retrieve module information\n");
-		return err;
-	}
-
 	if (!mlxsw_sp_port->split)
 		err = snprintf(name, len, "p%d", module + 1);
 	else
@@ -1681,8 +1679,8 @@
 	return 0;
 }
 
-static int __mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
-				  bool split, u8 module, u8 width)
+static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
+				bool split, u8 module, u8 width, u8 lane)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port;
 	struct net_device *dev;
@@ -1697,6 +1695,9 @@
 	mlxsw_sp_port->mlxsw_sp = mlxsw_sp;
 	mlxsw_sp_port->local_port = local_port;
 	mlxsw_sp_port->split = split;
+	mlxsw_sp_port->mapping.module = module;
+	mlxsw_sp_port->mapping.width = width;
+	mlxsw_sp_port->mapping.lane = lane;
 	bytes = DIV_ROUND_UP(VLAN_N_VID, BITS_PER_BYTE);
 	mlxsw_sp_port->active_vlans = kzalloc(bytes, GFP_KERNEL);
 	if (!mlxsw_sp_port->active_vlans) {
@@ -1839,28 +1840,6 @@
 	return err;
 }
 
-static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
-				bool split, u8 module, u8 width, u8 lane)
-{
-	int err;
-
-	err = mlxsw_sp_port_module_map(mlxsw_sp, local_port, module, width,
-				       lane);
-	if (err)
-		return err;
-
-	err = __mlxsw_sp_port_create(mlxsw_sp, local_port, split, module,
-				     width);
-	if (err)
-		goto err_port_create;
-
-	return 0;
-
-err_port_create:
-	mlxsw_sp_port_module_unmap(mlxsw_sp, local_port);
-	return err;
-}
-
 static void mlxsw_sp_port_vports_fini(struct mlxsw_sp_port *mlxsw_sp_port)
 {
 	struct net_device *dev = mlxsw_sp_port->dev;
@@ -1909,8 +1888,8 @@
 
 static int mlxsw_sp_ports_create(struct mlxsw_sp *mlxsw_sp)
 {
+	u8 module, width, lane;
 	size_t alloc_size;
-	u8 module, width;
 	int i;
 	int err;
 
@@ -1921,13 +1900,14 @@
 
 	for (i = 1; i < MLXSW_PORT_MAX_PORTS; i++) {
 		err = mlxsw_sp_port_module_info_get(mlxsw_sp, i, &module,
-						    &width);
+						    &width, &lane);
 		if (err)
 			goto err_port_module_info_get;
 		if (!width)
 			continue;
 		mlxsw_sp->port_to_module[i] = module;
-		err = __mlxsw_sp_port_create(mlxsw_sp, i, false, module, width);
+		err = mlxsw_sp_port_create(mlxsw_sp, i, false, module, width,
+					   lane);
 		if (err)
 			goto err_port_create;
 	}
@@ -1948,12 +1928,85 @@
 	return local_port - offset;
 }
 
+static int mlxsw_sp_port_split_create(struct mlxsw_sp *mlxsw_sp, u8 base_port,
+				      u8 module, unsigned int count)
+{
+	u8 width = MLXSW_PORT_MODULE_MAX_WIDTH / count;
+	int err, i;
+
+	for (i = 0; i < count; i++) {
+		err = mlxsw_sp_port_module_map(mlxsw_sp, base_port + i, module,
+					       width, i * width);
+		if (err)
+			goto err_port_module_map;
+	}
+
+	for (i = 0; i < count; i++) {
+		err = __mlxsw_sp_port_swid_set(mlxsw_sp, base_port + i, 0);
+		if (err)
+			goto err_port_swid_set;
+	}
+
+	for (i = 0; i < count; i++) {
+		err = mlxsw_sp_port_create(mlxsw_sp, base_port + i, true,
+					   module, width, i * width);
+		if (err)
+			goto err_port_create;
+	}
+
+	return 0;
+
+err_port_create:
+	for (i--; i >= 0; i--)
+		mlxsw_sp_port_remove(mlxsw_sp, base_port + i);
+	i = count;
+err_port_swid_set:
+	for (i--; i >= 0; i--)
+		__mlxsw_sp_port_swid_set(mlxsw_sp, base_port + i,
+					 MLXSW_PORT_SWID_DISABLED_PORT);
+	i = count;
+err_port_module_map:
+	for (i--; i >= 0; i--)
+		mlxsw_sp_port_module_unmap(mlxsw_sp, base_port + i);
+	return err;
+}
+
+static void mlxsw_sp_port_unsplit_create(struct mlxsw_sp *mlxsw_sp,
+					 u8 base_port, unsigned int count)
+{
+	u8 local_port, module, width = MLXSW_PORT_MODULE_MAX_WIDTH;
+	int i;
+
+	/* Split by four means we need to re-create two ports, otherwise
+	 * only one.
+	 */
+	count = count / 2;
+
+	for (i = 0; i < count; i++) {
+		local_port = base_port + i * 2;
+		module = mlxsw_sp->port_to_module[local_port];
+
+		mlxsw_sp_port_module_map(mlxsw_sp, local_port, module, width,
+					 0);
+	}
+
+	for (i = 0; i < count; i++)
+		__mlxsw_sp_port_swid_set(mlxsw_sp, base_port + i * 2, 0);
+
+	for (i = 0; i < count; i++) {
+		local_port = base_port + i * 2;
+		module = mlxsw_sp->port_to_module[local_port];
+
+		mlxsw_sp_port_create(mlxsw_sp, local_port, false, module,
+				     width, 0);
+	}
+}
+
 static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port,
 			       unsigned int count)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
 	struct mlxsw_sp_port *mlxsw_sp_port;
-	u8 width = MLXSW_PORT_MODULE_MAX_WIDTH / count;
 	u8 module, cur_width, base_port;
 	int i;
 	int err;
@@ -1965,18 +2018,14 @@
 		return -EINVAL;
 	}
 
+	module = mlxsw_sp_port->mapping.module;
+	cur_width = mlxsw_sp_port->mapping.width;
+
 	if (count != 2 && count != 4) {
 		netdev_err(mlxsw_sp_port->dev, "Port can only be split into 2 or 4 ports\n");
 		return -EINVAL;
 	}
 
-	err = mlxsw_sp_port_module_info_get(mlxsw_sp, local_port, &module,
-					    &cur_width);
-	if (err) {
-		netdev_err(mlxsw_sp_port->dev, "Failed to get port's width\n");
-		return err;
-	}
-
 	if (cur_width != MLXSW_PORT_MODULE_MAX_WIDTH) {
 		netdev_err(mlxsw_sp_port->dev, "Port cannot be split further\n");
 		return -EINVAL;
@@ -2001,25 +2050,16 @@
 	for (i = 0; i < count; i++)
 		mlxsw_sp_port_remove(mlxsw_sp, base_port + i);
 
-	for (i = 0; i < count; i++) {
-		err = mlxsw_sp_port_create(mlxsw_sp, base_port + i, true,
-					   module, width, i * width);
-		if (err) {
-			dev_err(mlxsw_sp->bus_info->dev, "Failed to create split port\n");
-			goto err_port_create;
-		}
+	err = mlxsw_sp_port_split_create(mlxsw_sp, base_port, module, count);
+	if (err) {
+		dev_err(mlxsw_sp->bus_info->dev, "Failed to create split ports\n");
+		goto err_port_split_create;
 	}
 
 	return 0;
 
-err_port_create:
-	for (i--; i >= 0; i--)
-		mlxsw_sp_port_remove(mlxsw_sp, base_port + i);
-	for (i = 0; i < count / 2; i++) {
-		module = mlxsw_sp->port_to_module[base_port + i * 2];
-		mlxsw_sp_port_create(mlxsw_sp, base_port + i * 2, false,
-				     module, MLXSW_PORT_MODULE_MAX_WIDTH, 0);
-	}
+err_port_split_create:
+	mlxsw_sp_port_unsplit_create(mlxsw_sp, base_port, count);
 	return err;
 }
 
@@ -2027,10 +2067,9 @@
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
 	struct mlxsw_sp_port *mlxsw_sp_port;
-	u8 module, cur_width, base_port;
+	u8 cur_width, base_port;
 	unsigned int count;
 	int i;
-	int err;
 
 	mlxsw_sp_port = mlxsw_sp->ports[local_port];
 	if (!mlxsw_sp_port) {
@@ -2044,12 +2083,7 @@
 		return -EINVAL;
 	}
 
-	err = mlxsw_sp_port_module_info_get(mlxsw_sp, local_port, &module,
-					    &cur_width);
-	if (err) {
-		netdev_err(mlxsw_sp_port->dev, "Failed to get port's width\n");
-		return err;
-	}
+	cur_width = mlxsw_sp_port->mapping.width;
 	count = cur_width == 1 ? 4 : 2;
 
 	base_port = mlxsw_sp_cluster_base_port_get(local_port);
@@ -2061,14 +2095,7 @@
 	for (i = 0; i < count; i++)
 		mlxsw_sp_port_remove(mlxsw_sp, base_port + i);
 
-	for (i = 0; i < count / 2; i++) {
-		module = mlxsw_sp->port_to_module[base_port + i * 2];
-		err = mlxsw_sp_port_create(mlxsw_sp, base_port + i * 2, false,
-					   module, MLXSW_PORT_MODULE_MAX_WIDTH,
-					   0);
-		if (err)
-			dev_err(mlxsw_sp->bus_info->dev, "Failed to reinstantiate port\n");
-	}
+	mlxsw_sp_port_unsplit_create(mlxsw_sp, base_port, count);
 
 	return 0;
 }
@@ -2378,6 +2405,7 @@
 
 	mlxsw_sp->core = mlxsw_core;
 	mlxsw_sp->bus_info = mlxsw_bus_info;
+	INIT_LIST_HEAD(&mlxsw_sp->fids);
 	INIT_LIST_HEAD(&mlxsw_sp->port_vfids.list);
 	INIT_LIST_HEAD(&mlxsw_sp->br_vfids.list);
 	INIT_LIST_HEAD(&mlxsw_sp->br_mids.list);
@@ -2454,6 +2482,7 @@
 	mlxsw_sp_traps_fini(mlxsw_sp);
 	mlxsw_sp_event_unregister(mlxsw_sp, MLXSW_TRAP_ID_PUDE);
 	mlxsw_sp_ports_remove(mlxsw_sp);
+	WARN_ON(!list_empty(&mlxsw_sp->fids));
 }
 
 static struct mlxsw_config_profile mlxsw_sp_config_profile = {
@@ -2515,16 +2544,37 @@
 	.profile			= &mlxsw_sp_config_profile,
 };
 
-static int
-mlxsw_sp_port_fdb_flush_by_port(const struct mlxsw_sp_port *mlxsw_sp_port)
+static bool mlxsw_sp_lag_port_fid_member(struct mlxsw_sp_port *lag_port,
+					 u16 fid)
+{
+	if (mlxsw_sp_fid_is_vfid(fid))
+		return mlxsw_sp_port_vport_find_by_fid(lag_port, fid);
+	else
+		return test_bit(fid, lag_port->active_vlans);
+}
+
+static bool mlxsw_sp_port_fdb_should_flush(struct mlxsw_sp_port *mlxsw_sp_port,
+					   u16 fid)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
-	char sfdf_pl[MLXSW_REG_SFDF_LEN];
+	u8 local_port = mlxsw_sp_port->local_port;
+	u16 lag_id = mlxsw_sp_port->lag_id;
+	int i, count = 0;
 
-	mlxsw_reg_sfdf_pack(sfdf_pl, MLXSW_REG_SFDF_FLUSH_PER_PORT);
-	mlxsw_reg_sfdf_system_port_set(sfdf_pl, mlxsw_sp_port->local_port);
+	if (!mlxsw_sp_port->lagged)
+		return true;
 
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfdf), sfdf_pl);
+	for (i = 0; i < MLXSW_SP_PORT_PER_LAG_MAX; i++) {
+		struct mlxsw_sp_port *lag_port;
+
+		lag_port = mlxsw_sp_port_lagged_get(mlxsw_sp, lag_id, i);
+		if (!lag_port || lag_port->local_port == local_port)
+			continue;
+		if (mlxsw_sp_lag_port_fid_member(lag_port, fid))
+			count++;
+	}
+
+	return !count;
 }
 
 static int
@@ -2539,17 +2589,8 @@
 	mlxsw_reg_sfdf_port_fid_system_port_set(sfdf_pl,
 						mlxsw_sp_port->local_port);
 
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfdf), sfdf_pl);
-}
-
-static int
-mlxsw_sp_port_fdb_flush_by_lag_id(const struct mlxsw_sp_port *mlxsw_sp_port)
-{
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
-	char sfdf_pl[MLXSW_REG_SFDF_LEN];
-
-	mlxsw_reg_sfdf_pack(sfdf_pl, MLXSW_REG_SFDF_FLUSH_PER_LAG);
-	mlxsw_reg_sfdf_lag_id_set(sfdf_pl, mlxsw_sp_port->lag_id);
+	netdev_dbg(mlxsw_sp_port->dev, "FDB flushed using Port=%d, FID=%d\n",
+		   mlxsw_sp_port->local_port, fid);
 
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfdf), sfdf_pl);
 }
@@ -2565,63 +2606,22 @@
 	mlxsw_reg_sfdf_fid_set(sfdf_pl, fid);
 	mlxsw_reg_sfdf_lag_fid_lag_id_set(sfdf_pl, mlxsw_sp_port->lag_id);
 
+	netdev_dbg(mlxsw_sp_port->dev, "FDB flushed using LAG ID=%d, FID=%d\n",
+		   mlxsw_sp_port->lag_id, fid);
+
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfdf), sfdf_pl);
 }
 
-static int
-__mlxsw_sp_port_fdb_flush(const struct mlxsw_sp_port *mlxsw_sp_port)
+int mlxsw_sp_port_fdb_flush(struct mlxsw_sp_port *mlxsw_sp_port, u16 fid)
 {
-	int err, last_err = 0;
-	u16 vid;
+	if (!mlxsw_sp_port_fdb_should_flush(mlxsw_sp_port, fid))
+		return 0;
 
-	for (vid = 1; vid < VLAN_N_VID - 1; vid++) {
-		err = mlxsw_sp_port_fdb_flush_by_port_fid(mlxsw_sp_port, vid);
-		if (err)
-			last_err = err;
-	}
-
-	return last_err;
-}
-
-static int
-__mlxsw_sp_port_fdb_flush_lagged(const struct mlxsw_sp_port *mlxsw_sp_port)
-{
-	int err, last_err = 0;
-	u16 vid;
-
-	for (vid = 1; vid < VLAN_N_VID - 1; vid++) {
-		err = mlxsw_sp_port_fdb_flush_by_lag_id_fid(mlxsw_sp_port, vid);
-		if (err)
-			last_err = err;
-	}
-
-	return last_err;
-}
-
-static int mlxsw_sp_port_fdb_flush(struct mlxsw_sp_port *mlxsw_sp_port)
-{
-	if (!list_empty(&mlxsw_sp_port->vports_list))
-		if (mlxsw_sp_port->lagged)
-			return __mlxsw_sp_port_fdb_flush_lagged(mlxsw_sp_port);
-		else
-			return __mlxsw_sp_port_fdb_flush(mlxsw_sp_port);
-	else
-		if (mlxsw_sp_port->lagged)
-			return mlxsw_sp_port_fdb_flush_by_lag_id(mlxsw_sp_port);
-		else
-			return mlxsw_sp_port_fdb_flush_by_port(mlxsw_sp_port);
-}
-
-static int mlxsw_sp_vport_fdb_flush(struct mlxsw_sp_port *mlxsw_sp_vport)
-{
-	u16 vfid = mlxsw_sp_vport_vfid_get(mlxsw_sp_vport);
-	u16 fid = mlxsw_sp_vfid_to_fid(vfid);
-
-	if (mlxsw_sp_vport->lagged)
-		return mlxsw_sp_port_fdb_flush_by_lag_id_fid(mlxsw_sp_vport,
+	if (mlxsw_sp_port->lagged)
+		return mlxsw_sp_port_fdb_flush_by_lag_id_fid(mlxsw_sp_port,
 							     fid);
 	else
-		return mlxsw_sp_port_fdb_flush_by_port_fid(mlxsw_sp_vport, fid);
+		return mlxsw_sp_port_fdb_flush_by_port_fid(mlxsw_sp_port, fid);
 }
 
 static bool mlxsw_sp_port_dev_check(const struct net_device *dev)
@@ -2629,49 +2629,6 @@
 	return dev->netdev_ops == &mlxsw_sp_port_netdev_ops;
 }
 
-static int mlxsw_sp_port_bridge_join(struct mlxsw_sp_port *mlxsw_sp_port)
-{
-	struct net_device *dev = mlxsw_sp_port->dev;
-	int err;
-
-	/* When port is not bridged untagged packets are tagged with
-	 * PVID=VID=1, thereby creating an implicit VLAN interface in
-	 * the device. Remove it and let bridge code take care of its
-	 * own VLANs.
-	 */
-	err = mlxsw_sp_port_kill_vid(dev, 0, 1);
-	if (err)
-		return err;
-
-	mlxsw_sp_port->learning = 1;
-	mlxsw_sp_port->learning_sync = 1;
-	mlxsw_sp_port->uc_flood = 1;
-	mlxsw_sp_port->bridged = 1;
-
-	return 0;
-}
-
-static int mlxsw_sp_port_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_port,
-				      bool flush_fdb)
-{
-	struct net_device *dev = mlxsw_sp_port->dev;
-
-	if (flush_fdb && mlxsw_sp_port_fdb_flush(mlxsw_sp_port))
-		netdev_err(mlxsw_sp_port->dev, "Failed to flush FDB\n");
-
-	mlxsw_sp_port_pvid_set(mlxsw_sp_port, 1);
-
-	mlxsw_sp_port->learning = 0;
-	mlxsw_sp_port->learning_sync = 0;
-	mlxsw_sp_port->uc_flood = 0;
-	mlxsw_sp_port->bridged = 0;
-
-	/* Add implicit VLAN interface in the device, so that untagged
-	 * packets will be classified to the default vFID.
-	 */
-	return mlxsw_sp_port_add_vid(dev, 0, 1);
-}
-
 static bool mlxsw_sp_master_bridge_check(struct mlxsw_sp *mlxsw_sp,
 					 struct net_device *br_dev)
 {
@@ -2686,13 +2643,56 @@
 	mlxsw_sp->master_bridge.ref_count++;
 }
 
-static void mlxsw_sp_master_bridge_dec(struct mlxsw_sp *mlxsw_sp,
-				       struct net_device *br_dev)
+static void mlxsw_sp_master_bridge_dec(struct mlxsw_sp *mlxsw_sp)
 {
 	if (--mlxsw_sp->master_bridge.ref_count == 0)
 		mlxsw_sp->master_bridge.dev = NULL;
 }
 
+static int mlxsw_sp_port_bridge_join(struct mlxsw_sp_port *mlxsw_sp_port,
+				     struct net_device *br_dev)
+{
+	struct net_device *dev = mlxsw_sp_port->dev;
+	int err;
+
+	/* When port is not bridged untagged packets are tagged with
+	 * PVID=VID=1, thereby creating an implicit VLAN interface in
+	 * the device. Remove it and let bridge code take care of its
+	 * own VLANs.
+	 */
+	err = mlxsw_sp_port_kill_vid(dev, 0, 1);
+	if (err)
+		return err;
+
+	mlxsw_sp_master_bridge_inc(mlxsw_sp_port->mlxsw_sp, br_dev);
+
+	mlxsw_sp_port->learning = 1;
+	mlxsw_sp_port->learning_sync = 1;
+	mlxsw_sp_port->uc_flood = 1;
+	mlxsw_sp_port->bridged = 1;
+
+	return 0;
+}
+
+static void mlxsw_sp_port_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	struct net_device *dev = mlxsw_sp_port->dev;
+
+	mlxsw_sp_port_pvid_set(mlxsw_sp_port, 1);
+
+	mlxsw_sp_master_bridge_dec(mlxsw_sp_port->mlxsw_sp);
+
+	mlxsw_sp_port->learning = 0;
+	mlxsw_sp_port->learning_sync = 0;
+	mlxsw_sp_port->uc_flood = 0;
+	mlxsw_sp_port->bridged = 0;
+
+	/* Add implicit VLAN interface in the device, so that untagged
+	 * packets will be classified to the default vFID.
+	 */
+	mlxsw_sp_port_add_vid(dev, 0, 1);
+}
+
 static int mlxsw_sp_lag_create(struct mlxsw_sp *mlxsw_sp, u16 lag_id)
 {
 	char sldr_pl[MLXSW_REG_SLDR_LEN];
@@ -2851,65 +2851,33 @@
 	return err;
 }
 
-static int mlxsw_sp_vport_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_vport,
-				       struct net_device *br_dev,
-				       bool flush_fdb);
-
-static int mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port,
-				   struct net_device *lag_dev)
+static void mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port,
+				    struct net_device *lag_dev)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
-	struct mlxsw_sp_port *mlxsw_sp_vport;
-	struct mlxsw_sp_upper *lag;
 	u16 lag_id = mlxsw_sp_port->lag_id;
-	int err;
+	struct mlxsw_sp_upper *lag;
 
 	if (!mlxsw_sp_port->lagged)
-		return 0;
+		return;
 	lag = mlxsw_sp_lag_get(mlxsw_sp, lag_id);
 	WARN_ON(lag->ref_count == 0);
 
-	err = mlxsw_sp_lag_col_port_disable(mlxsw_sp_port, lag_id);
-	if (err)
-		return err;
-	err = mlxsw_sp_lag_col_port_remove(mlxsw_sp_port, lag_id);
-	if (err)
-		return err;
-
-	/* In case we leave a LAG device that has bridges built on top,
-	 * then their teardown sequence is never issued and we need to
-	 * invoke the necessary cleanup routines ourselves.
-	 */
-	list_for_each_entry(mlxsw_sp_vport, &mlxsw_sp_port->vports_list,
-			    vport.list) {
-		struct net_device *br_dev;
-
-		if (!mlxsw_sp_vport->bridged)
-			continue;
-
-		br_dev = mlxsw_sp_vport_br_get(mlxsw_sp_vport);
-		mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport, br_dev, false);
-	}
+	mlxsw_sp_lag_col_port_disable(mlxsw_sp_port, lag_id);
+	mlxsw_sp_lag_col_port_remove(mlxsw_sp_port, lag_id);
 
 	if (mlxsw_sp_port->bridged) {
 		mlxsw_sp_port_active_vlans_del(mlxsw_sp_port);
-		mlxsw_sp_port_bridge_leave(mlxsw_sp_port, false);
-		mlxsw_sp_master_bridge_dec(mlxsw_sp, NULL);
+		mlxsw_sp_port_bridge_leave(mlxsw_sp_port);
 	}
 
-	if (lag->ref_count == 1) {
-		if (mlxsw_sp_port_fdb_flush_by_lag_id(mlxsw_sp_port))
-			netdev_err(mlxsw_sp_port->dev, "Failed to flush FDB\n");
-		err = mlxsw_sp_lag_destroy(mlxsw_sp, lag_id);
-		if (err)
-			return err;
-	}
+	if (lag->ref_count == 1)
+		mlxsw_sp_lag_destroy(mlxsw_sp, lag_id);
 
 	mlxsw_core_lag_mapping_clear(mlxsw_sp->core, lag_id,
 				     mlxsw_sp_port->local_port);
 	mlxsw_sp_port->lagged = 0;
 	lag->ref_count--;
-	return 0;
 }
 
 static int mlxsw_sp_lag_dist_port_add(struct mlxsw_sp_port *mlxsw_sp_port,
@@ -2958,42 +2926,25 @@
 	u16 vid = vlan_dev_vlan_id(vlan_dev);
 
 	mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid);
-	if (!mlxsw_sp_vport) {
-		WARN_ON(!mlxsw_sp_vport);
+	if (WARN_ON(!mlxsw_sp_vport))
 		return -EINVAL;
-	}
 
 	mlxsw_sp_vport->dev = vlan_dev;
 
 	return 0;
 }
 
-static int mlxsw_sp_port_vlan_unlink(struct mlxsw_sp_port *mlxsw_sp_port,
-				     struct net_device *vlan_dev)
+static void mlxsw_sp_port_vlan_unlink(struct mlxsw_sp_port *mlxsw_sp_port,
+				      struct net_device *vlan_dev)
 {
 	struct mlxsw_sp_port *mlxsw_sp_vport;
 	u16 vid = vlan_dev_vlan_id(vlan_dev);
 
 	mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid);
-	if (!mlxsw_sp_vport) {
-		WARN_ON(!mlxsw_sp_vport);
-		return -EINVAL;
-	}
-
-	/* When removing a VLAN device while still bridged we should first
-	 * remove it from the bridge, as we receive the bridge's notification
-	 * when the vPort is already gone.
-	 */
-	if (mlxsw_sp_vport->bridged) {
-		struct net_device *br_dev;
-
-		br_dev = mlxsw_sp_vport_br_get(mlxsw_sp_vport);
-		mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport, br_dev, true);
-	}
+	if (WARN_ON(!mlxsw_sp_vport))
+		return;
 
 	mlxsw_sp_vport->dev = mlxsw_sp_port->dev;
-
-	return 0;
 }
 
 static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev,
@@ -3003,7 +2954,7 @@
 	struct mlxsw_sp_port *mlxsw_sp_port;
 	struct net_device *upper_dev;
 	struct mlxsw_sp *mlxsw_sp;
-	int err;
+	int err = 0;
 
 	mlxsw_sp_port = netdev_priv(dev);
 	mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
@@ -3012,73 +2963,56 @@
 	switch (event) {
 	case NETDEV_PRECHANGEUPPER:
 		upper_dev = info->upper_dev;
-		if (!info->master || !info->linking)
+		if (!is_vlan_dev(upper_dev) &&
+		    !netif_is_lag_master(upper_dev) &&
+		    !netif_is_bridge_master(upper_dev))
+			return -EINVAL;
+		if (!info->linking)
 			break;
 		/* HW limitation forbids to put ports to multiple bridges. */
 		if (netif_is_bridge_master(upper_dev) &&
 		    !mlxsw_sp_master_bridge_check(mlxsw_sp, upper_dev))
-			return NOTIFY_BAD;
+			return -EINVAL;
 		if (netif_is_lag_master(upper_dev) &&
 		    !mlxsw_sp_master_lag_check(mlxsw_sp, upper_dev,
 					       info->upper_info))
-			return NOTIFY_BAD;
+			return -EINVAL;
+		if (netif_is_lag_master(upper_dev) && vlan_uses_dev(dev))
+			return -EINVAL;
+		if (netif_is_lag_port(dev) && is_vlan_dev(upper_dev) &&
+		    !netif_is_lag_master(vlan_dev_real_dev(upper_dev)))
+			return -EINVAL;
 		break;
 	case NETDEV_CHANGEUPPER:
 		upper_dev = info->upper_dev;
 		if (is_vlan_dev(upper_dev)) {
-			if (info->linking) {
+			if (info->linking)
 				err = mlxsw_sp_port_vlan_link(mlxsw_sp_port,
 							      upper_dev);
-				if (err) {
-					netdev_err(dev, "Failed to link VLAN device\n");
-					return NOTIFY_BAD;
-				}
-			} else {
-				err = mlxsw_sp_port_vlan_unlink(mlxsw_sp_port,
-								upper_dev);
-				if (err) {
-					netdev_err(dev, "Failed to unlink VLAN device\n");
-					return NOTIFY_BAD;
-				}
-			}
+			else
+				 mlxsw_sp_port_vlan_unlink(mlxsw_sp_port,
+							   upper_dev);
 		} else if (netif_is_bridge_master(upper_dev)) {
-			if (info->linking) {
-				err = mlxsw_sp_port_bridge_join(mlxsw_sp_port);
-				if (err) {
-					netdev_err(dev, "Failed to join bridge\n");
-					return NOTIFY_BAD;
-				}
-				mlxsw_sp_master_bridge_inc(mlxsw_sp, upper_dev);
-			} else {
-				err = mlxsw_sp_port_bridge_leave(mlxsw_sp_port,
-								 true);
-				mlxsw_sp_master_bridge_dec(mlxsw_sp, upper_dev);
-				if (err) {
-					netdev_err(dev, "Failed to leave bridge\n");
-					return NOTIFY_BAD;
-				}
-			}
+			if (info->linking)
+				err = mlxsw_sp_port_bridge_join(mlxsw_sp_port,
+								upper_dev);
+			else
+				mlxsw_sp_port_bridge_leave(mlxsw_sp_port);
 		} else if (netif_is_lag_master(upper_dev)) {
-			if (info->linking) {
+			if (info->linking)
 				err = mlxsw_sp_port_lag_join(mlxsw_sp_port,
 							     upper_dev);
-				if (err) {
-					netdev_err(dev, "Failed to join link aggregation\n");
-					return NOTIFY_BAD;
-				}
-			} else {
-				err = mlxsw_sp_port_lag_leave(mlxsw_sp_port,
-							      upper_dev);
-				if (err) {
-					netdev_err(dev, "Failed to leave link aggregation\n");
-					return NOTIFY_BAD;
-				}
-			}
+			else
+				mlxsw_sp_port_lag_leave(mlxsw_sp_port,
+							upper_dev);
+		} else {
+			err = -EINVAL;
+			WARN_ON(1);
 		}
 		break;
 	}
 
-	return NOTIFY_DONE;
+	return err;
 }
 
 static int mlxsw_sp_netdevice_port_lower_event(struct net_device *dev,
@@ -3102,7 +3036,7 @@
 		break;
 	}
 
-	return NOTIFY_DONE;
+	return 0;
 }
 
 static int mlxsw_sp_netdevice_port_event(struct net_device *dev,
@@ -3116,7 +3050,7 @@
 		return mlxsw_sp_netdevice_port_lower_event(dev, event, ptr);
 	}
 
-	return NOTIFY_DONE;
+	return 0;
 }
 
 static int mlxsw_sp_netdevice_lag_event(struct net_device *lag_dev,
@@ -3129,23 +3063,23 @@
 	netdev_for_each_lower_dev(lag_dev, dev, iter) {
 		if (mlxsw_sp_port_dev_check(dev)) {
 			ret = mlxsw_sp_netdevice_port_event(dev, event, ptr);
-			if (ret == NOTIFY_BAD)
+			if (ret)
 				return ret;
 		}
 	}
 
-	return NOTIFY_DONE;
+	return 0;
 }
 
-static struct mlxsw_sp_vfid *
+static struct mlxsw_sp_fid *
 mlxsw_sp_br_vfid_find(const struct mlxsw_sp *mlxsw_sp,
 		      const struct net_device *br_dev)
 {
-	struct mlxsw_sp_vfid *vfid;
+	struct mlxsw_sp_fid *f;
 
-	list_for_each_entry(vfid, &mlxsw_sp->br_vfids.list, list) {
-		if (vfid->br_dev == br_dev)
-			return vfid;
+	list_for_each_entry(f, &mlxsw_sp->br_vfids.list, list) {
+		if (f->dev == br_dev)
+			return f;
 	}
 
 	return NULL;
@@ -3167,180 +3101,127 @@
 				   MLXSW_SP_VFID_BR_MAX);
 }
 
-static struct mlxsw_sp_vfid *mlxsw_sp_br_vfid_create(struct mlxsw_sp *mlxsw_sp,
-						     struct net_device *br_dev)
+static void mlxsw_sp_vport_br_vfid_leave(struct mlxsw_sp_port *mlxsw_sp_vport);
+
+static struct mlxsw_sp_fid *mlxsw_sp_br_vfid_create(struct mlxsw_sp *mlxsw_sp,
+						    struct net_device *br_dev)
 {
 	struct device *dev = mlxsw_sp->bus_info->dev;
-	struct mlxsw_sp_vfid *vfid;
-	u16 n_vfid;
+	struct mlxsw_sp_fid *f;
+	u16 vfid, fid;
 	int err;
 
-	n_vfid = mlxsw_sp_br_vfid_to_vfid(mlxsw_sp_avail_br_vfid_get(mlxsw_sp));
-	if (n_vfid == MLXSW_SP_VFID_MAX) {
+	vfid = mlxsw_sp_br_vfid_to_vfid(mlxsw_sp_avail_br_vfid_get(mlxsw_sp));
+	if (vfid == MLXSW_SP_VFID_MAX) {
 		dev_err(dev, "No available vFIDs\n");
 		return ERR_PTR(-ERANGE);
 	}
 
-	err = __mlxsw_sp_vfid_create(mlxsw_sp, n_vfid);
+	fid = mlxsw_sp_vfid_to_fid(vfid);
+	err = mlxsw_sp_vfid_op(mlxsw_sp, fid, true);
 	if (err) {
-		dev_err(dev, "Failed to create vFID=%d\n", n_vfid);
+		dev_err(dev, "Failed to create FID=%d\n", fid);
 		return ERR_PTR(err);
 	}
 
-	vfid = kzalloc(sizeof(*vfid), GFP_KERNEL);
-	if (!vfid)
+	f = kzalloc(sizeof(*f), GFP_KERNEL);
+	if (!f)
 		goto err_allocate_vfid;
 
-	vfid->vfid = n_vfid;
-	vfid->br_dev = br_dev;
+	f->leave = mlxsw_sp_vport_br_vfid_leave;
+	f->fid = fid;
+	f->dev = br_dev;
 
-	list_add(&vfid->list, &mlxsw_sp->br_vfids.list);
-	set_bit(mlxsw_sp_vfid_to_br_vfid(n_vfid), mlxsw_sp->br_vfids.mapped);
+	list_add(&f->list, &mlxsw_sp->br_vfids.list);
+	set_bit(mlxsw_sp_vfid_to_br_vfid(vfid), mlxsw_sp->br_vfids.mapped);
 
-	return vfid;
+	return f;
 
 err_allocate_vfid:
-	__mlxsw_sp_vfid_destroy(mlxsw_sp, n_vfid);
+	mlxsw_sp_vfid_op(mlxsw_sp, fid, false);
 	return ERR_PTR(-ENOMEM);
 }
 
 static void mlxsw_sp_br_vfid_destroy(struct mlxsw_sp *mlxsw_sp,
-				     struct mlxsw_sp_vfid *vfid)
+				     struct mlxsw_sp_fid *f)
 {
-	u16 br_vfid = mlxsw_sp_vfid_to_br_vfid(vfid->vfid);
+	u16 vfid = mlxsw_sp_fid_to_vfid(f->fid);
+	u16 br_vfid = mlxsw_sp_vfid_to_br_vfid(vfid);
 
 	clear_bit(br_vfid, mlxsw_sp->br_vfids.mapped);
-	list_del(&vfid->list);
+	list_del(&f->list);
 
-	__mlxsw_sp_vfid_destroy(mlxsw_sp, vfid->vfid);
+	mlxsw_sp_vfid_op(mlxsw_sp, f->fid, false);
 
-	kfree(vfid);
+	kfree(f);
 }
 
-static int mlxsw_sp_vport_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_vport,
-				       struct net_device *br_dev,
-				       bool flush_fdb)
+static int mlxsw_sp_vport_br_vfid_join(struct mlxsw_sp_port *mlxsw_sp_vport,
+				       struct net_device *br_dev)
 {
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp;
-	u16 vid = mlxsw_sp_vport_vid_get(mlxsw_sp_vport);
-	struct net_device *dev = mlxsw_sp_vport->dev;
-	struct mlxsw_sp_vfid *vfid, *new_vfid;
+	struct mlxsw_sp_fid *f;
 	int err;
 
-	vfid = mlxsw_sp_br_vfid_find(mlxsw_sp, br_dev);
-	if (!vfid) {
-		WARN_ON(!vfid);
-		return -EINVAL;
+	f = mlxsw_sp_br_vfid_find(mlxsw_sp_vport->mlxsw_sp, br_dev);
+	if (!f) {
+		f = mlxsw_sp_br_vfid_create(mlxsw_sp_vport->mlxsw_sp, br_dev);
+		if (IS_ERR(f))
+			return PTR_ERR(f);
 	}
 
-	/* We need a vFID to go back to after leaving the bridge's vFID. */
-	new_vfid = mlxsw_sp_vfid_find(mlxsw_sp, vid);
-	if (!new_vfid) {
-		new_vfid = mlxsw_sp_vfid_create(mlxsw_sp, vid);
-		if (IS_ERR(new_vfid)) {
-			netdev_err(dev, "Failed to create vFID for VID=%d\n",
-				   vid);
-			return PTR_ERR(new_vfid);
-		}
-	}
-
-	/* Invalidate existing {Port, VID} to vFID mapping and create a new
-	 * one for the new vFID.
-	 */
-	err = mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport,
-					   MLXSW_REG_SVFA_MT_PORT_VID_TO_FID,
-					   false,
-					   mlxsw_sp_vfid_to_fid(vfid->vfid),
-					   vid);
-	if (err) {
-		netdev_err(dev, "Failed to invalidate {Port, VID} to vFID=%d mapping\n",
-			   vfid->vfid);
-		goto err_port_vid_to_fid_invalidate;
-	}
-
-	err = mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport,
-					   MLXSW_REG_SVFA_MT_PORT_VID_TO_FID,
-					   true,
-					   mlxsw_sp_vfid_to_fid(new_vfid->vfid),
-					   vid);
-	if (err) {
-		netdev_err(dev, "Failed to map {Port, VID} to vFID=%d\n",
-			   new_vfid->vfid);
-		goto err_port_vid_to_fid_validate;
-	}
-
-	err = mlxsw_sp_port_vid_learning_set(mlxsw_sp_vport, vid, false);
-	if (err) {
-		netdev_err(dev, "Failed to disable learning\n");
-		goto err_port_vid_learning_set;
-	}
-
-	err = mlxsw_sp_vport_flood_set(mlxsw_sp_vport, vfid->vfid, false,
-				       false);
-	if (err) {
-		netdev_err(dev, "Failed clear to clear flooding\n");
+	err = mlxsw_sp_vport_flood_set(mlxsw_sp_vport, f->fid, true);
+	if (err)
 		goto err_vport_flood_set;
-	}
 
-	err = mlxsw_sp_port_stp_state_set(mlxsw_sp_vport, vid,
-					  MLXSW_REG_SPMS_STATE_FORWARDING);
-	if (err) {
-		netdev_err(dev, "Failed to set STP state\n");
-		goto err_port_stp_state_set;
-	}
+	err = mlxsw_sp_vport_fid_map(mlxsw_sp_vport, f->fid, true);
+	if (err)
+		goto err_vport_fid_map;
 
-	if (flush_fdb && mlxsw_sp_vport_fdb_flush(mlxsw_sp_vport))
-		netdev_err(dev, "Failed to flush FDB\n");
+	mlxsw_sp_vport_fid_set(mlxsw_sp_vport, f);
+	f->ref_count++;
 
-	/* Switch between the vFIDs and destroy the old one if needed. */
-	new_vfid->nr_vports++;
-	mlxsw_sp_vport->vport.vfid = new_vfid;
-	vfid->nr_vports--;
-	if (!vfid->nr_vports)
-		mlxsw_sp_br_vfid_destroy(mlxsw_sp, vfid);
-
-	mlxsw_sp_vport->learning = 0;
-	mlxsw_sp_vport->learning_sync = 0;
-	mlxsw_sp_vport->uc_flood = 0;
-	mlxsw_sp_vport->bridged = 0;
+	netdev_dbg(mlxsw_sp_vport->dev, "Joined FID=%d\n", f->fid);
 
 	return 0;
 
-err_port_stp_state_set:
+err_vport_fid_map:
+	mlxsw_sp_vport_flood_set(mlxsw_sp_vport, f->fid, false);
 err_vport_flood_set:
-err_port_vid_learning_set:
-err_port_vid_to_fid_validate:
-err_port_vid_to_fid_invalidate:
-	/* Rollback vFID only if new. */
-	if (!new_vfid->nr_vports)
-		mlxsw_sp_vfid_destroy(mlxsw_sp, new_vfid);
+	if (!f->ref_count)
+		mlxsw_sp_br_vfid_destroy(mlxsw_sp_vport->mlxsw_sp, f);
 	return err;
 }
 
+static void mlxsw_sp_vport_br_vfid_leave(struct mlxsw_sp_port *mlxsw_sp_vport)
+{
+	struct mlxsw_sp_fid *f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport);
+
+	netdev_dbg(mlxsw_sp_vport->dev, "Left FID=%d\n", f->fid);
+
+	mlxsw_sp_vport_fid_map(mlxsw_sp_vport, f->fid, false);
+
+	mlxsw_sp_vport_flood_set(mlxsw_sp_vport, f->fid, false);
+
+	mlxsw_sp_port_fdb_flush(mlxsw_sp_vport, f->fid);
+
+	mlxsw_sp_vport_fid_set(mlxsw_sp_vport, NULL);
+	if (--f->ref_count == 0)
+		mlxsw_sp_br_vfid_destroy(mlxsw_sp_vport->mlxsw_sp, f);
+}
+
 static int mlxsw_sp_vport_bridge_join(struct mlxsw_sp_port *mlxsw_sp_vport,
 				      struct net_device *br_dev)
 {
-	struct mlxsw_sp_vfid *old_vfid = mlxsw_sp_vport->vport.vfid;
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp;
 	u16 vid = mlxsw_sp_vport_vid_get(mlxsw_sp_vport);
 	struct net_device *dev = mlxsw_sp_vport->dev;
-	struct mlxsw_sp_vfid *vfid;
 	int err;
 
-	vfid = mlxsw_sp_br_vfid_find(mlxsw_sp, br_dev);
-	if (!vfid) {
-		vfid = mlxsw_sp_br_vfid_create(mlxsw_sp, br_dev);
-		if (IS_ERR(vfid)) {
-			netdev_err(dev, "Failed to create bridge vFID\n");
-			return PTR_ERR(vfid);
-		}
-	}
+	mlxsw_sp_vport_vfid_leave(mlxsw_sp_vport);
 
-	err = mlxsw_sp_vport_flood_set(mlxsw_sp_vport, vfid->vfid, true, false);
+	err = mlxsw_sp_vport_br_vfid_join(mlxsw_sp_vport, br_dev);
 	if (err) {
-		netdev_err(dev, "Failed to setup flooding for vFID=%d\n",
-			   vfid->vfid);
-		goto err_port_flood_set;
+		netdev_err(dev, "Failed to join vFID\n");
+		goto err_vport_br_vfid_join;
 	}
 
 	err = mlxsw_sp_port_vid_learning_set(mlxsw_sp_vport, vid, true);
@@ -3349,38 +3230,6 @@
 		goto err_port_vid_learning_set;
 	}
 
-	/* We need to invalidate existing {Port, VID} to vFID mapping and
-	 * create a new one for the bridge's vFID.
-	 */
-	err = mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport,
-					   MLXSW_REG_SVFA_MT_PORT_VID_TO_FID,
-					   false,
-					   mlxsw_sp_vfid_to_fid(old_vfid->vfid),
-					   vid);
-	if (err) {
-		netdev_err(dev, "Failed to invalidate {Port, VID} to vFID=%d mapping\n",
-			   old_vfid->vfid);
-		goto err_port_vid_to_fid_invalidate;
-	}
-
-	err = mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport,
-					   MLXSW_REG_SVFA_MT_PORT_VID_TO_FID,
-					   true,
-					   mlxsw_sp_vfid_to_fid(vfid->vfid),
-					   vid);
-	if (err) {
-		netdev_err(dev, "Failed to map {Port, VID} to vFID=%d\n",
-			   vfid->vfid);
-		goto err_port_vid_to_fid_validate;
-	}
-
-	/* Switch between the vFIDs and destroy the old one if needed. */
-	vfid->nr_vports++;
-	mlxsw_sp_vport->vport.vfid = vfid;
-	old_vfid->nr_vports--;
-	if (!old_vfid->nr_vports)
-		mlxsw_sp_vfid_destroy(mlxsw_sp, old_vfid);
-
 	mlxsw_sp_vport->learning = 1;
 	mlxsw_sp_vport->learning_sync = 1;
 	mlxsw_sp_vport->uc_flood = 1;
@@ -3388,20 +3237,32 @@
 
 	return 0;
 
-err_port_vid_to_fid_validate:
-	mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_vport,
-				     MLXSW_REG_SVFA_MT_PORT_VID_TO_FID, false,
-				     mlxsw_sp_vfid_to_fid(old_vfid->vfid), vid);
-err_port_vid_to_fid_invalidate:
-	mlxsw_sp_port_vid_learning_set(mlxsw_sp_vport, vid, false);
 err_port_vid_learning_set:
-	mlxsw_sp_vport_flood_set(mlxsw_sp_vport, vfid->vfid, false, false);
-err_port_flood_set:
-	if (!vfid->nr_vports)
-		mlxsw_sp_br_vfid_destroy(mlxsw_sp, vfid);
+	mlxsw_sp_vport_br_vfid_leave(mlxsw_sp_vport);
+err_vport_br_vfid_join:
+	mlxsw_sp_vport_vfid_join(mlxsw_sp_vport);
 	return err;
 }
 
+static void mlxsw_sp_vport_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_vport)
+{
+	u16 vid = mlxsw_sp_vport_vid_get(mlxsw_sp_vport);
+
+	mlxsw_sp_port_vid_learning_set(mlxsw_sp_vport, vid, false);
+
+	mlxsw_sp_vport_br_vfid_leave(mlxsw_sp_vport);
+
+	mlxsw_sp_vport_vfid_join(mlxsw_sp_vport);
+
+	mlxsw_sp_port_stp_state_set(mlxsw_sp_vport, vid,
+				    MLXSW_REG_SPMS_STATE_FORWARDING);
+
+	mlxsw_sp_vport->learning = 0;
+	mlxsw_sp_vport->learning_sync = 0;
+	mlxsw_sp_vport->uc_flood = 0;
+	mlxsw_sp_vport->bridged = 0;
+}
+
 static bool
 mlxsw_sp_port_master_bridge_check(const struct mlxsw_sp_port *mlxsw_sp_port,
 				  const struct net_device *br_dev)
@@ -3410,7 +3271,9 @@
 
 	list_for_each_entry(mlxsw_sp_vport, &mlxsw_sp_port->vports_list,
 			    vport.list) {
-		if (mlxsw_sp_vport_br_get(mlxsw_sp_vport) == br_dev)
+		struct net_device *dev = mlxsw_sp_vport_br_get(mlxsw_sp_vport);
+
+		if (dev && dev == br_dev)
 			return false;
 	}
 
@@ -3425,56 +3288,39 @@
 	struct netdev_notifier_changeupper_info *info = ptr;
 	struct mlxsw_sp_port *mlxsw_sp_vport;
 	struct net_device *upper_dev;
-	int err;
+	int err = 0;
 
 	mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid);
 
 	switch (event) {
 	case NETDEV_PRECHANGEUPPER:
 		upper_dev = info->upper_dev;
-		if (!info->master || !info->linking)
-			break;
 		if (!netif_is_bridge_master(upper_dev))
-			return NOTIFY_BAD;
+			return -EINVAL;
+		if (!info->linking)
+			break;
 		/* We can't have multiple VLAN interfaces configured on
 		 * the same port and being members in the same bridge.
 		 */
 		if (!mlxsw_sp_port_master_bridge_check(mlxsw_sp_port,
 						       upper_dev))
-			return NOTIFY_BAD;
+			return -EINVAL;
 		break;
 	case NETDEV_CHANGEUPPER:
 		upper_dev = info->upper_dev;
-		if (!info->master)
-			break;
 		if (info->linking) {
-			if (!mlxsw_sp_vport) {
-				WARN_ON(!mlxsw_sp_vport);
-				return NOTIFY_BAD;
-			}
+			if (WARN_ON(!mlxsw_sp_vport))
+				return -EINVAL;
 			err = mlxsw_sp_vport_bridge_join(mlxsw_sp_vport,
 							 upper_dev);
-			if (err) {
-				netdev_err(dev, "Failed to join bridge\n");
-				return NOTIFY_BAD;
-			}
 		} else {
-			/* We ignore bridge's unlinking notifications if vPort
-			 * is gone, since we already left the bridge when the
-			 * VLAN device was unlinked from the real device.
-			 */
 			if (!mlxsw_sp_vport)
-				return NOTIFY_DONE;
-			err = mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport,
-							  upper_dev, true);
-			if (err) {
-				netdev_err(dev, "Failed to leave bridge\n");
-				return NOTIFY_BAD;
-			}
+				return 0;
+			mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport);
 		}
 	}
 
-	return NOTIFY_DONE;
+	return err;
 }
 
 static int mlxsw_sp_netdevice_lag_vport_event(struct net_device *lag_dev,
@@ -3489,12 +3335,12 @@
 		if (mlxsw_sp_port_dev_check(dev)) {
 			ret = mlxsw_sp_netdevice_vport_event(dev, event, ptr,
 							     vid);
-			if (ret == NOTIFY_BAD)
+			if (ret)
 				return ret;
 		}
 	}
 
-	return NOTIFY_DONE;
+	return 0;
 }
 
 static int mlxsw_sp_netdevice_vlan_event(struct net_device *vlan_dev,
@@ -3510,24 +3356,23 @@
 		return mlxsw_sp_netdevice_lag_vport_event(real_dev, event, ptr,
 							  vid);
 
-	return NOTIFY_DONE;
+	return 0;
 }
 
 static int mlxsw_sp_netdevice_event(struct notifier_block *unused,
 				    unsigned long event, void *ptr)
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	int err = 0;
 
 	if (mlxsw_sp_port_dev_check(dev))
-		return mlxsw_sp_netdevice_port_event(dev, event, ptr);
+		err = mlxsw_sp_netdevice_port_event(dev, event, ptr);
+	else if (netif_is_lag_master(dev))
+		err = mlxsw_sp_netdevice_lag_event(dev, event, ptr);
+	else if (is_vlan_dev(dev))
+		err = mlxsw_sp_netdevice_vlan_event(dev, event, ptr);
 
-	if (netif_is_lag_master(dev))
-		return mlxsw_sp_netdevice_lag_event(dev, event, ptr);
-
-	if (is_vlan_dev(dev))
-		return mlxsw_sp_netdevice_vlan_event(dev, event, ptr);
-
-	return NOTIFY_DONE;
+	return notifier_from_errno(err);
 }
 
 static struct notifier_block mlxsw_sp_netdevice_nb __read_mostly = {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index e2c022d..36c9835 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -87,11 +87,12 @@
 	unsigned int ref_count;
 };
 
-struct mlxsw_sp_vfid {
+struct mlxsw_sp_fid {
+	void (*leave)(struct mlxsw_sp_port *mlxsw_sp_vport);
 	struct list_head list;
-	u16 nr_vports;
-	u16 vfid;	/* Starting at 0 */
-	struct net_device *br_dev;
+	unsigned int ref_count;
+	struct net_device *dev;
+	u16 fid;
 	u16 vid;
 };
 
@@ -155,17 +156,17 @@
 struct mlxsw_sp {
 	struct {
 		struct list_head list;
-		unsigned long mapped[BITS_TO_LONGS(MLXSW_SP_VFID_PORT_MAX)];
+		DECLARE_BITMAP(mapped, MLXSW_SP_VFID_PORT_MAX);
 	} port_vfids;
 	struct {
 		struct list_head list;
-		unsigned long mapped[BITS_TO_LONGS(MLXSW_SP_VFID_BR_MAX)];
+		DECLARE_BITMAP(mapped, MLXSW_SP_VFID_BR_MAX);
 	} br_vfids;
 	struct {
 		struct list_head list;
-		unsigned long mapped[BITS_TO_LONGS(MLXSW_SP_MID_MAX)];
+		DECLARE_BITMAP(mapped, MLXSW_SP_MID_MAX);
 	} br_mids;
-	unsigned long active_fids[BITS_TO_LONGS(VLAN_N_VID)];
+	struct list_head fids;	/* VLAN-aware bridge FIDs */
 	struct mlxsw_sp_port **ports;
 	struct mlxsw_core *core;
 	const struct mlxsw_bus_info *bus_info;
@@ -217,7 +218,7 @@
 	u16 lag_id;
 	struct {
 		struct list_head list;
-		struct mlxsw_sp_vfid *vfid;
+		struct mlxsw_sp_fid *f;
 		u16 vid;
 	} vport;
 	struct {
@@ -229,6 +230,11 @@
 		struct ieee_maxrate *maxrate;
 		struct ieee_pfc *pfc;
 	} dcb;
+	struct {
+		u8 module;
+		u8 width;
+		u8 lane;
+	} mapping;
 	/* 802.1Q bridge VLANs */
 	unsigned long *active_vlans;
 	unsigned long *untagged_vlans;
@@ -254,28 +260,38 @@
 	return mlxsw_sp_port && mlxsw_sp_port->lagged ? mlxsw_sp_port : NULL;
 }
 
-static inline bool
-mlxsw_sp_port_is_vport(const struct mlxsw_sp_port *mlxsw_sp_port)
-{
-	return mlxsw_sp_port->vport.vfid;
-}
-
-static inline struct net_device *
-mlxsw_sp_vport_br_get(const struct mlxsw_sp_port *mlxsw_sp_vport)
-{
-	return mlxsw_sp_vport->vport.vfid->br_dev;
-}
-
 static inline u16
 mlxsw_sp_vport_vid_get(const struct mlxsw_sp_port *mlxsw_sp_vport)
 {
 	return mlxsw_sp_vport->vport.vid;
 }
 
-static inline u16
-mlxsw_sp_vport_vfid_get(const struct mlxsw_sp_port *mlxsw_sp_vport)
+static inline bool
+mlxsw_sp_port_is_vport(const struct mlxsw_sp_port *mlxsw_sp_port)
 {
-	return mlxsw_sp_vport->vport.vfid->vfid;
+	u16 vid = mlxsw_sp_vport_vid_get(mlxsw_sp_port);
+
+	return vid != 0;
+}
+
+static inline void mlxsw_sp_vport_fid_set(struct mlxsw_sp_port *mlxsw_sp_vport,
+					  struct mlxsw_sp_fid *f)
+{
+	mlxsw_sp_vport->vport.f = f;
+}
+
+static inline struct mlxsw_sp_fid *
+mlxsw_sp_vport_fid_get(const struct mlxsw_sp_port *mlxsw_sp_vport)
+{
+	return mlxsw_sp_vport->vport.f;
+}
+
+static inline struct net_device *
+mlxsw_sp_vport_br_get(const struct mlxsw_sp_port *mlxsw_sp_vport)
+{
+	struct mlxsw_sp_fid *f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport);
+
+	return f ? f->dev : NULL;
 }
 
 static inline struct mlxsw_sp_port *
@@ -293,14 +309,16 @@
 }
 
 static inline struct mlxsw_sp_port *
-mlxsw_sp_port_vport_find_by_vfid(const struct mlxsw_sp_port *mlxsw_sp_port,
-				 u16 vfid)
+mlxsw_sp_port_vport_find_by_fid(const struct mlxsw_sp_port *mlxsw_sp_port,
+				u16 fid)
 {
 	struct mlxsw_sp_port *mlxsw_sp_vport;
 
 	list_for_each_entry(mlxsw_sp_vport, &mlxsw_sp_port->vports_list,
 			    vport.list) {
-		if (mlxsw_sp_vport_vfid_get(mlxsw_sp_vport) == vfid)
+		struct mlxsw_sp_fid *f = mlxsw_sp_vport_fid_get(mlxsw_sp_vport);
+
+		if (f && f->fid == fid)
 			return mlxsw_sp_vport;
 	}
 
@@ -361,10 +379,11 @@
 			  u16 vid);
 int mlxsw_sp_port_kill_vid(struct net_device *dev,
 			   __be16 __always_unused proto, u16 vid);
-int mlxsw_sp_vport_flood_set(struct mlxsw_sp_port *mlxsw_sp_vport, u16 vfid,
-			     bool set, bool only_uc);
+int mlxsw_sp_vport_flood_set(struct mlxsw_sp_port *mlxsw_sp_vport, u16 fid,
+			     bool set);
 void mlxsw_sp_port_active_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port);
 int mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid);
+int mlxsw_sp_port_fdb_flush(struct mlxsw_sp_port *mlxsw_sp_port, u16 fid);
 int mlxsw_sp_port_ets_set(struct mlxsw_sp_port *mlxsw_sp_port,
 			  enum mlxsw_reg_qeec_hr hr, u8 index, u8 next_index,
 			  bool dwrr, u8 dwrr_weight);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 3710f19..a0c7376 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -55,13 +55,10 @@
 static u16 mlxsw_sp_port_vid_to_fid_get(struct mlxsw_sp_port *mlxsw_sp_port,
 					u16 vid)
 {
+	struct mlxsw_sp_fid *f = mlxsw_sp_vport_fid_get(mlxsw_sp_port);
 	u16 fid = vid;
 
-	if (mlxsw_sp_port_is_vport(mlxsw_sp_port)) {
-		u16 vfid = mlxsw_sp_vport_vfid_get(mlxsw_sp_port);
-
-		fid = mlxsw_sp_vfid_to_fid(vfid);
-	}
+	fid = f ? f->fid : fid;
 
 	if (!fid)
 		fid = mlxsw_sp_port->pvid;
@@ -236,7 +233,8 @@
 	int err;
 
 	if (mlxsw_sp_port_is_vport(mlxsw_sp_port)) {
-		u16 vfid = mlxsw_sp_vport_vfid_get(mlxsw_sp_port);
+		u16 fid = mlxsw_sp_vport_fid_get(mlxsw_sp_port)->fid;
+		u16 vfid = mlxsw_sp_fid_to_vfid(fid);
 
 		return  __mlxsw_sp_port_flood_set(mlxsw_sp_port, vfid, vfid,
 						  set, true);
@@ -260,14 +258,17 @@
 	return err;
 }
 
-int mlxsw_sp_vport_flood_set(struct mlxsw_sp_port *mlxsw_sp_vport, u16 vfid,
-			     bool set, bool only_uc)
+int mlxsw_sp_vport_flood_set(struct mlxsw_sp_port *mlxsw_sp_vport, u16 fid,
+			     bool set)
 {
+	u16 vfid;
+
 	/* In case of vFIDs, index into the flooding table is relative to
 	 * the start of the vFIDs range.
 	 */
+	vfid = mlxsw_sp_fid_to_vfid(fid);
 	return __mlxsw_sp_port_flood_set(mlxsw_sp_vport, vfid, vfid, set,
-					 only_uc);
+					 false);
 }
 
 static int mlxsw_sp_port_attr_br_flags_set(struct mlxsw_sp_port *mlxsw_sp_port,
@@ -383,6 +384,198 @@
 	return err;
 }
 
+static struct mlxsw_sp_fid *mlxsw_sp_fid_find(struct mlxsw_sp *mlxsw_sp,
+					      u16 fid)
+{
+	struct mlxsw_sp_fid *f;
+
+	list_for_each_entry(f, &mlxsw_sp->fids, list)
+		if (f->fid == fid)
+			return f;
+
+	return NULL;
+}
+
+static int mlxsw_sp_fid_op(struct mlxsw_sp *mlxsw_sp, u16 fid, bool create)
+{
+	char sfmr_pl[MLXSW_REG_SFMR_LEN];
+
+	mlxsw_reg_sfmr_pack(sfmr_pl, !create, fid, fid);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfmr), sfmr_pl);
+}
+
+static int mlxsw_sp_fid_map(struct mlxsw_sp *mlxsw_sp, u16 fid, bool valid)
+{
+	enum mlxsw_reg_svfa_mt mt = MLXSW_REG_SVFA_MT_VID_TO_FID;
+	char svfa_pl[MLXSW_REG_SVFA_LEN];
+
+	mlxsw_reg_svfa_pack(svfa_pl, 0, mt, valid, fid, fid);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(svfa), svfa_pl);
+}
+
+static struct mlxsw_sp_fid *mlxsw_sp_fid_alloc(u16 fid)
+{
+	struct mlxsw_sp_fid *f;
+
+	f = kzalloc(sizeof(*f), GFP_KERNEL);
+	if (!f)
+		return NULL;
+
+	f->fid = fid;
+
+	return f;
+}
+
+static struct mlxsw_sp_fid *mlxsw_sp_fid_create(struct mlxsw_sp *mlxsw_sp,
+						u16 fid)
+{
+	struct mlxsw_sp_fid *f;
+	int err;
+
+	err = mlxsw_sp_fid_op(mlxsw_sp, fid, true);
+	if (err)
+		return ERR_PTR(err);
+
+	/* Although all the ports member in the FID might be using a
+	 * {Port, VID} to FID mapping, we create a global VID-to-FID
+	 * mapping. This allows a port to transition to VLAN mode,
+	 * knowing the global mapping exists.
+	 */
+	err = mlxsw_sp_fid_map(mlxsw_sp, fid, true);
+	if (err)
+		goto err_fid_map;
+
+	f = mlxsw_sp_fid_alloc(fid);
+	if (!f) {
+		err = -ENOMEM;
+		goto err_allocate_fid;
+	}
+
+	list_add(&f->list, &mlxsw_sp->fids);
+
+	return f;
+
+err_allocate_fid:
+	mlxsw_sp_fid_map(mlxsw_sp, fid, false);
+err_fid_map:
+	mlxsw_sp_fid_op(mlxsw_sp, fid, false);
+	return ERR_PTR(err);
+}
+
+static void mlxsw_sp_fid_destroy(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_fid *f)
+{
+	u16 fid = f->fid;
+
+	list_del(&f->list);
+
+	kfree(f);
+
+	mlxsw_sp_fid_op(mlxsw_sp, fid, false);
+}
+
+static int __mlxsw_sp_port_fid_join(struct mlxsw_sp_port *mlxsw_sp_port,
+				    u16 fid)
+{
+	struct mlxsw_sp_fid *f;
+
+	f = mlxsw_sp_fid_find(mlxsw_sp_port->mlxsw_sp, fid);
+	if (!f) {
+		f = mlxsw_sp_fid_create(mlxsw_sp_port->mlxsw_sp, fid);
+		if (IS_ERR(f))
+			return PTR_ERR(f);
+	}
+
+	f->ref_count++;
+
+	netdev_dbg(mlxsw_sp_port->dev, "Joined FID=%d\n", fid);
+
+	return 0;
+}
+
+static void __mlxsw_sp_port_fid_leave(struct mlxsw_sp_port *mlxsw_sp_port,
+				      u16 fid)
+{
+	struct mlxsw_sp_fid *f;
+
+	f = mlxsw_sp_fid_find(mlxsw_sp_port->mlxsw_sp, fid);
+	if (WARN_ON(!f))
+		return;
+
+	netdev_dbg(mlxsw_sp_port->dev, "Left FID=%d\n", fid);
+
+	mlxsw_sp_port_fdb_flush(mlxsw_sp_port, fid);
+
+	if (--f->ref_count == 0)
+		mlxsw_sp_fid_destroy(mlxsw_sp_port->mlxsw_sp, f);
+}
+
+static int mlxsw_sp_port_fid_map(struct mlxsw_sp_port *mlxsw_sp_port, u16 fid,
+				 bool valid)
+{
+	enum mlxsw_reg_svfa_mt mt = MLXSW_REG_SVFA_MT_PORT_VID_TO_FID;
+
+	/* If port doesn't have vPorts, then it can use the global
+	 * VID-to-FID mapping.
+	 */
+	if (list_empty(&mlxsw_sp_port->vports_list))
+		return 0;
+
+	return mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_port, mt, valid, fid, fid);
+}
+
+static int mlxsw_sp_port_fid_join(struct mlxsw_sp_port *mlxsw_sp_port,
+				  u16 fid_begin, u16 fid_end)
+{
+	int fid, err;
+
+	for (fid = fid_begin; fid <= fid_end; fid++) {
+		err = __mlxsw_sp_port_fid_join(mlxsw_sp_port, fid);
+		if (err)
+			goto err_port_fid_join;
+	}
+
+	err = __mlxsw_sp_port_flood_set(mlxsw_sp_port, fid_begin, fid_end,
+					true, false);
+	if (err)
+		goto err_port_flood_set;
+
+	for (fid = fid_begin; fid <= fid_end; fid++) {
+		err = mlxsw_sp_port_fid_map(mlxsw_sp_port, fid, true);
+		if (err)
+			goto err_port_fid_map;
+	}
+
+	return 0;
+
+err_port_fid_map:
+	for (fid--; fid >= fid_begin; fid--)
+		mlxsw_sp_port_fid_map(mlxsw_sp_port, fid, false);
+	__mlxsw_sp_port_flood_set(mlxsw_sp_port, fid_begin, fid_end, false,
+				  false);
+err_port_flood_set:
+	fid = fid_end;
+err_port_fid_join:
+	for (fid--; fid >= fid_begin; fid--)
+		__mlxsw_sp_port_fid_leave(mlxsw_sp_port, fid);
+	return err;
+}
+
+static void mlxsw_sp_port_fid_leave(struct mlxsw_sp_port *mlxsw_sp_port,
+				    u16 fid_begin, u16 fid_end)
+{
+	int fid;
+
+	for (fid = fid_begin; fid <= fid_end; fid++)
+		mlxsw_sp_port_fid_map(mlxsw_sp_port, fid, false);
+
+	__mlxsw_sp_port_flood_set(mlxsw_sp_port, fid_begin, fid_end, false,
+				  false);
+
+	for (fid = fid_begin; fid <= fid_end; fid++)
+		__mlxsw_sp_port_fid_leave(mlxsw_sp_port, fid);
+}
+
 static int __mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port,
 				    u16 vid)
 {
@@ -440,55 +633,6 @@
 	return err;
 }
 
-static int mlxsw_sp_fid_create(struct mlxsw_sp *mlxsw_sp, u16 fid)
-{
-	char sfmr_pl[MLXSW_REG_SFMR_LEN];
-	int err;
-
-	mlxsw_reg_sfmr_pack(sfmr_pl, MLXSW_REG_SFMR_OP_CREATE_FID, fid, fid);
-	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfmr), sfmr_pl);
-
-	if (err)
-		return err;
-
-	set_bit(fid, mlxsw_sp->active_fids);
-	return 0;
-}
-
-static void mlxsw_sp_fid_destroy(struct mlxsw_sp *mlxsw_sp, u16 fid)
-{
-	char sfmr_pl[MLXSW_REG_SFMR_LEN];
-
-	clear_bit(fid, mlxsw_sp->active_fids);
-
-	mlxsw_reg_sfmr_pack(sfmr_pl, MLXSW_REG_SFMR_OP_DESTROY_FID,
-			    fid, fid);
-	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfmr), sfmr_pl);
-}
-
-static int mlxsw_sp_port_fid_map(struct mlxsw_sp_port *mlxsw_sp_port, u16 fid)
-{
-	enum mlxsw_reg_svfa_mt mt;
-
-	if (!list_empty(&mlxsw_sp_port->vports_list))
-		mt = MLXSW_REG_SVFA_MT_PORT_VID_TO_FID;
-	else
-		mt = MLXSW_REG_SVFA_MT_VID_TO_FID;
-
-	return mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_port, mt, true, fid, fid);
-}
-
-static int mlxsw_sp_port_fid_unmap(struct mlxsw_sp_port *mlxsw_sp_port, u16 fid)
-{
-	enum mlxsw_reg_svfa_mt mt;
-
-	if (list_empty(&mlxsw_sp_port->vports_list))
-		return 0;
-
-	mt = MLXSW_REG_SVFA_MT_PORT_VID_TO_FID;
-	return mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_port, mt, false, fid, fid);
-}
-
 static int mlxsw_sp_port_add_vids(struct net_device *dev, u16 vid_begin,
 				  u16 vid_end)
 {
@@ -533,10 +677,8 @@
 				     u16 vid_begin, u16 vid_end,
 				     bool flag_untagged, bool flag_pvid)
 {
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	struct net_device *dev = mlxsw_sp_port->dev;
-	u16 vid, last_visited_vid, old_pvid;
-	enum mlxsw_reg_svfa_mt mt;
+	u16 vid, old_pvid;
 	int err;
 
 	/* In case this is invoked with BRIDGE_FLAGS_SELF and port is
@@ -546,44 +688,10 @@
 	if (!mlxsw_sp_port->bridged)
 		return mlxsw_sp_port_add_vids(dev, vid_begin, vid_end);
 
-	for (vid = vid_begin; vid <= vid_end; vid++) {
-		if (!test_bit(vid, mlxsw_sp->active_fids)) {
-			err = mlxsw_sp_fid_create(mlxsw_sp, vid);
-			if (err) {
-				netdev_err(dev, "Failed to create FID=%d\n",
-					   vid);
-				return err;
-			}
-
-			/* When creating a FID, we set a VID to FID mapping
-			 * regardless of the port's mode.
-			 */
-			mt = MLXSW_REG_SVFA_MT_VID_TO_FID;
-			err = mlxsw_sp_port_vid_to_fid_set(mlxsw_sp_port, mt,
-							   true, vid, vid);
-			if (err) {
-				netdev_err(dev, "Failed to create FID=VID=%d mapping\n",
-					   vid);
-				goto err_port_vid_to_fid_set;
-			}
-		}
-	}
-
-	/* Set FID mapping according to port's mode */
-	for (vid = vid_begin; vid <= vid_end; vid++) {
-		err = mlxsw_sp_port_fid_map(mlxsw_sp_port, vid);
-		if (err) {
-			netdev_err(dev, "Failed to map FID=%d", vid);
-			last_visited_vid = --vid;
-			goto err_port_fid_map;
-		}
-	}
-
-	err = __mlxsw_sp_port_flood_set(mlxsw_sp_port, vid_begin, vid_end,
-					true, false);
+	err = mlxsw_sp_port_fid_join(mlxsw_sp_port, vid_begin, vid_end);
 	if (err) {
-		netdev_err(dev, "Failed to configure flooding\n");
-		goto err_port_flood_set;
+		netdev_err(dev, "Failed to join FIDs\n");
+		return err;
 	}
 
 	err = __mlxsw_sp_port_vlans_set(mlxsw_sp_port, vid_begin, vid_end,
@@ -628,10 +736,6 @@
 
 	return 0;
 
-err_port_vid_to_fid_set:
-	mlxsw_sp_fid_destroy(mlxsw_sp, vid);
-	return err;
-
 err_port_stp_state_set:
 	for (vid = vid_begin; vid <= vid_end; vid++)
 		clear_bit(vid, mlxsw_sp_port->active_vlans);
@@ -641,13 +745,7 @@
 	__mlxsw_sp_port_vlans_set(mlxsw_sp_port, vid_begin, vid_end, false,
 				  false);
 err_port_vlans_set:
-	__mlxsw_sp_port_flood_set(mlxsw_sp_port, vid_begin, vid_end, false,
-				  false);
-err_port_flood_set:
-	last_visited_vid = vid_end;
-err_port_fid_map:
-	for (vid = last_visited_vid; vid >= vid_begin; vid--)
-		mlxsw_sp_port_fid_unmap(mlxsw_sp_port, vid);
+	mlxsw_sp_port_fid_leave(mlxsw_sp_port, vid_begin, vid_end);
 	return err;
 }
 
@@ -970,21 +1068,7 @@
 		}
 	}
 
-	err = __mlxsw_sp_port_flood_set(mlxsw_sp_port, vid_begin, vid_end,
-					false, false);
-	if (err) {
-		netdev_err(dev, "Failed to clear flooding\n");
-		return err;
-	}
-
-	for (vid = vid_begin; vid <= vid_end; vid++) {
-		/* Remove FID mapping in case of Virtual mode */
-		err = mlxsw_sp_port_fid_unmap(mlxsw_sp_port, vid);
-		if (err) {
-			netdev_err(dev, "Failed to unmap FID=%d", vid);
-			return err;
-		}
-	}
+	mlxsw_sp_port_fid_leave(mlxsw_sp_port, vid_begin, vid_end);
 
 out:
 	/* Changing activity bits only if HW operation succeded */
@@ -1118,7 +1202,8 @@
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	struct mlxsw_sp_port *tmp;
-	u16 vport_fid = 0;
+	struct mlxsw_sp_fid *f;
+	u16 vport_fid;
 	char *sfd_pl;
 	char mac[ETH_ALEN];
 	u16 fid;
@@ -1133,12 +1218,8 @@
 	if (!sfd_pl)
 		return -ENOMEM;
 
-	if (mlxsw_sp_port_is_vport(mlxsw_sp_port)) {
-		u16 tmp;
-
-		tmp = mlxsw_sp_vport_vfid_get(mlxsw_sp_port);
-		vport_fid = mlxsw_sp_vfid_to_fid(tmp);
-	}
+	f = mlxsw_sp_vport_fid_get(mlxsw_sp_port);
+	vport_fid = f ? f->fid : 0;
 
 	mlxsw_reg_sfd_pack(sfd_pl, MLXSW_REG_SFD_OP_QUERY_DUMP, 0);
 	do {
@@ -1310,11 +1391,10 @@
 	}
 
 	if (mlxsw_sp_fid_is_vfid(fid)) {
-		u16 vfid = mlxsw_sp_fid_to_vfid(fid);
 		struct mlxsw_sp_port *mlxsw_sp_vport;
 
-		mlxsw_sp_vport = mlxsw_sp_port_vport_find_by_vfid(mlxsw_sp_port,
-								  vfid);
+		mlxsw_sp_vport = mlxsw_sp_port_vport_find_by_fid(mlxsw_sp_port,
+								 fid);
 		if (!mlxsw_sp_vport) {
 			netdev_err(mlxsw_sp_port->dev, "Failed to find a matching vPort following FDB notification\n");
 			goto just_remove;
@@ -1370,11 +1450,10 @@
 	}
 
 	if (mlxsw_sp_fid_is_vfid(fid)) {
-		u16 vfid = mlxsw_sp_fid_to_vfid(fid);
 		struct mlxsw_sp_port *mlxsw_sp_vport;
 
-		mlxsw_sp_vport = mlxsw_sp_port_vport_find_by_vfid(mlxsw_sp_port,
-								  vfid);
+		mlxsw_sp_vport = mlxsw_sp_port_vport_find_by_fid(mlxsw_sp_port,
+								 fid);
 		if (!mlxsw_sp_vport) {
 			netdev_err(mlxsw_sp_port->dev, "Failed to find a matching vPort following FDB notification\n");
 			goto just_remove;
@@ -1495,14 +1574,6 @@
 	cancel_delayed_work_sync(&mlxsw_sp->fdb_notify.dw);
 }
 
-static void mlxsw_sp_fids_fini(struct mlxsw_sp *mlxsw_sp)
-{
-	u16 fid;
-
-	for_each_set_bit(fid, mlxsw_sp->active_fids, VLAN_N_VID)
-		mlxsw_sp_fid_destroy(mlxsw_sp, fid);
-}
-
 int mlxsw_sp_switchdev_init(struct mlxsw_sp *mlxsw_sp)
 {
 	return mlxsw_sp_fdb_init(mlxsw_sp);
@@ -1511,7 +1582,6 @@
 void mlxsw_sp_switchdev_fini(struct mlxsw_sp *mlxsw_sp)
 {
 	mlxsw_sp_fdb_fini(mlxsw_sp);
-	mlxsw_sp_fids_fini(mlxsw_sp);
 }
 
 int mlxsw_sp_port_vlan_init(struct mlxsw_sp_port *mlxsw_sp_port)
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index fa47c14..2195ed3 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -1979,7 +1979,7 @@
 	if (nn->ctrl & NFP_NET_CFG_CTRL_VXLAN) {
 		memset(&nn->vxlan_ports, 0, sizeof(nn->vxlan_ports));
 		memset(&nn->vxlan_usecnt, 0, sizeof(nn->vxlan_usecnt));
-		vxlan_get_rx_port(nn->netdev);
+		udp_tunnel_get_rx_info(nn->netdev);
 	}
 
 	return err;
@@ -2551,26 +2551,32 @@
 }
 
 static void nfp_net_add_vxlan_port(struct net_device *netdev,
-				   sa_family_t sa_family, __be16 port)
+				   struct udp_tunnel_info *ti)
 {
 	struct nfp_net *nn = netdev_priv(netdev);
 	int idx;
 
-	idx = nfp_net_find_vxlan_idx(nn, port);
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
+		return;
+
+	idx = nfp_net_find_vxlan_idx(nn, ti->port);
 	if (idx == -ENOSPC)
 		return;
 
 	if (!nn->vxlan_usecnt[idx]++)
-		nfp_net_set_vxlan_port(nn, idx, port);
+		nfp_net_set_vxlan_port(nn, idx, ti->port);
 }
 
 static void nfp_net_del_vxlan_port(struct net_device *netdev,
-				   sa_family_t sa_family, __be16 port)
+				   struct udp_tunnel_info *ti)
 {
 	struct nfp_net *nn = netdev_priv(netdev);
 	int idx;
 
-	idx = nfp_net_find_vxlan_idx(nn, port);
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
+		return;
+
+	idx = nfp_net_find_vxlan_idx(nn, ti->port);
 	if (!nn->vxlan_usecnt[idx] || idx == -ENOSPC)
 		return;
 
@@ -2589,8 +2595,8 @@
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_set_features	= nfp_net_set_features,
 	.ndo_features_check	= nfp_net_features_check,
-	.ndo_add_vxlan_port     = nfp_net_add_vxlan_port,
-	.ndo_del_vxlan_port     = nfp_net_del_vxlan_port,
+	.ndo_udp_tunnel_add	= nfp_net_add_vxlan_port,
+	.ndo_udp_tunnel_del	= nfp_net_del_vxlan_port,
 };
 
 /**
diff --git a/drivers/net/ethernet/qlogic/Kconfig b/drivers/net/ethernet/qlogic/Kconfig
index 680d8c7..6ba4840 100644
--- a/drivers/net/ethernet/qlogic/Kconfig
+++ b/drivers/net/ethernet/qlogic/Kconfig
@@ -54,16 +54,6 @@
 	  mode of DCB is supported. PG and PFC values are related only
 	  to Tx.
 
-config QLCNIC_VXLAN
-	bool "Virtual eXtensible Local Area Network (VXLAN) offload support"
-	default n
-	depends on QLCNIC && VXLAN && !(QLCNIC=y && VXLAN=m)
-	---help---
-	  This enables hardware offload support for VXLAN protocol over QLogic's
-	  84XX series adapters.
-	  Say Y here if you want to enable hardware offload support for
-	  Virtual eXtensible Local Area Network (VXLAN) in the driver.
-
 config QLCNIC_HWMON
 	bool "QLOGIC QLCNIC 82XX and 83XX family HWMON support"
 	depends on QLCNIC && HWMON && !(QLCNIC=y && HWMON=m)
@@ -114,24 +104,4 @@
 	---help---
 	  This enables the support for ...
 
-config QEDE_VXLAN
-	bool "Virtual eXtensible Local Area Network support"
-	default n
-	depends on QEDE && VXLAN && !(QEDE=y && VXLAN=m)
-	---help---
-	  This enables hardware offload support for VXLAN protocol over
-	  qede module. Say Y here if you want to enable hardware offload
-	  support for Virtual eXtensible Local Area Network (VXLAN)
-	  in the driver.
-
-config QEDE_GENEVE
-	bool "Generic Network Virtualization Encapsulation (GENEVE) support"
-	depends on QEDE && GENEVE && !(QEDE=y && GENEVE=m)
-	---help---
-	  This allows one to create GENEVE virtual interfaces that provide
-	  Layer 2 Networks over Layer 3 Networks. GENEVE is often used
-	  to tunnel virtual network infrastructure in virtualized environments.
-	  Say Y here if you want to enable hardware offload support for
-	  Generic Network Virtualization Encapsulation (GENEVE) in the driver.
-
 endif # NET_VENDOR_QLOGIC
diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
index d85b7ba..1c35f37 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
@@ -850,7 +850,7 @@
 			val = 0;
 		entries[j].next = cpu_to_be64(val);
 
-		conn_num -= ent_per_page;
+		conn_num -= ent_num;
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
index 21ec1c2..d0dc28f 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
@@ -9,6 +9,7 @@
 #include <linux/types.h>
 #include <asm/byteorder.h>
 #include <linux/bitops.h>
+#include <linux/dcbnl.h>
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
@@ -18,6 +19,9 @@
 #include "qed_dcbx.h"
 #include "qed_hsi.h"
 #include "qed_sp.h"
+#ifdef CONFIG_DCB
+#include <linux/qed/qed_eth_if.h>
+#endif
 
 #define QED_DCBX_MAX_MIB_READ_TRY       (100)
 #define QED_ETH_TYPE_DEFAULT            (0)
@@ -252,7 +256,7 @@
 		if (p_data->arr[type].update)
 			continue;
 
-		enable = (type == DCBX_PROTOCOL_ETH) ? false : dcbx_enabled;
+		enable = !(type == DCBX_PROTOCOL_ETH);
 		qed_dcbx_update_app_info(p_data, p_hwfn, enable, true,
 					 priority, tc, type);
 	}
@@ -351,6 +355,293 @@
 	return rc;
 }
 
+#ifdef CONFIG_DCB
+static void
+qed_dcbx_get_priority_info(struct qed_hwfn *p_hwfn,
+			   struct qed_dcbx_app_prio *p_prio,
+			   struct qed_dcbx_results *p_results)
+{
+	u8 val;
+
+	p_prio->roce = QED_DCBX_INVALID_PRIORITY;
+	p_prio->roce_v2 = QED_DCBX_INVALID_PRIORITY;
+	p_prio->iscsi = QED_DCBX_INVALID_PRIORITY;
+	p_prio->fcoe = QED_DCBX_INVALID_PRIORITY;
+
+	if (p_results->arr[DCBX_PROTOCOL_ROCE].update &&
+	    p_results->arr[DCBX_PROTOCOL_ROCE].enable)
+		p_prio->roce = p_results->arr[DCBX_PROTOCOL_ROCE].priority;
+
+	if (p_results->arr[DCBX_PROTOCOL_ROCE_V2].update &&
+	    p_results->arr[DCBX_PROTOCOL_ROCE_V2].enable) {
+		val = p_results->arr[DCBX_PROTOCOL_ROCE_V2].priority;
+		p_prio->roce_v2 = val;
+	}
+
+	if (p_results->arr[DCBX_PROTOCOL_ISCSI].update &&
+	    p_results->arr[DCBX_PROTOCOL_ISCSI].enable)
+		p_prio->iscsi = p_results->arr[DCBX_PROTOCOL_ISCSI].priority;
+
+	if (p_results->arr[DCBX_PROTOCOL_FCOE].update &&
+	    p_results->arr[DCBX_PROTOCOL_FCOE].enable)
+		p_prio->fcoe = p_results->arr[DCBX_PROTOCOL_FCOE].priority;
+
+	if (p_results->arr[DCBX_PROTOCOL_ETH].update &&
+	    p_results->arr[DCBX_PROTOCOL_ETH].enable)
+		p_prio->eth = p_results->arr[DCBX_PROTOCOL_ETH].priority;
+
+	DP_VERBOSE(p_hwfn, QED_MSG_DCB,
+		   "Priorities: iscsi %d, roce %d, roce v2 %d, fcoe %d, eth %d\n",
+		   p_prio->iscsi, p_prio->roce, p_prio->roce_v2, p_prio->fcoe,
+		   p_prio->eth);
+}
+
+static void
+qed_dcbx_get_app_data(struct qed_hwfn *p_hwfn,
+		      struct dcbx_app_priority_feature *p_app,
+		      struct dcbx_app_priority_entry *p_tbl,
+		      struct qed_dcbx_params *p_params)
+{
+	struct qed_app_entry *entry;
+	u8 pri_map;
+	int i;
+
+	p_params->app_willing = QED_MFW_GET_FIELD(p_app->flags,
+						  DCBX_APP_WILLING);
+	p_params->app_valid = QED_MFW_GET_FIELD(p_app->flags, DCBX_APP_ENABLED);
+	p_params->app_error = QED_MFW_GET_FIELD(p_app->flags, DCBX_APP_ERROR);
+	p_params->num_app_entries = QED_MFW_GET_FIELD(p_app->flags,
+						      DCBX_APP_NUM_ENTRIES);
+	for (i = 0; i < DCBX_MAX_APP_PROTOCOL; i++) {
+		entry = &p_params->app_entry[i];
+		entry->ethtype = !(QED_MFW_GET_FIELD(p_tbl[i].entry,
+						     DCBX_APP_SF));
+		pri_map = QED_MFW_GET_FIELD(p_tbl[i].entry, DCBX_APP_PRI_MAP);
+		entry->prio = ffs(pri_map) - 1;
+		entry->proto_id = QED_MFW_GET_FIELD(p_tbl[i].entry,
+						    DCBX_APP_PROTOCOL_ID);
+		qed_dcbx_get_app_protocol_type(p_hwfn, p_tbl[i].entry,
+					       entry->proto_id,
+					       &entry->proto_type);
+	}
+
+	DP_VERBOSE(p_hwfn, QED_MSG_DCB,
+		   "APP params: willing %d, valid %d error = %d\n",
+		   p_params->app_willing, p_params->app_valid,
+		   p_params->app_error);
+}
+
+static void
+qed_dcbx_get_pfc_data(struct qed_hwfn *p_hwfn,
+		      u32 pfc, struct qed_dcbx_params *p_params)
+{
+	u8 pfc_map;
+
+	p_params->pfc.willing = QED_MFW_GET_FIELD(pfc, DCBX_PFC_WILLING);
+	p_params->pfc.max_tc = QED_MFW_GET_FIELD(pfc, DCBX_PFC_CAPS);
+	p_params->pfc.enabled = QED_MFW_GET_FIELD(pfc, DCBX_PFC_ENABLED);
+	pfc_map = QED_MFW_GET_FIELD(pfc, DCBX_PFC_PRI_EN_BITMAP);
+	p_params->pfc.prio[0] = !!(pfc_map & DCBX_PFC_PRI_EN_BITMAP_PRI_0);
+	p_params->pfc.prio[1] = !!(pfc_map & DCBX_PFC_PRI_EN_BITMAP_PRI_1);
+	p_params->pfc.prio[2] = !!(pfc_map & DCBX_PFC_PRI_EN_BITMAP_PRI_2);
+	p_params->pfc.prio[3] = !!(pfc_map & DCBX_PFC_PRI_EN_BITMAP_PRI_3);
+	p_params->pfc.prio[4] = !!(pfc_map & DCBX_PFC_PRI_EN_BITMAP_PRI_4);
+	p_params->pfc.prio[5] = !!(pfc_map & DCBX_PFC_PRI_EN_BITMAP_PRI_5);
+	p_params->pfc.prio[6] = !!(pfc_map & DCBX_PFC_PRI_EN_BITMAP_PRI_6);
+	p_params->pfc.prio[7] = !!(pfc_map & DCBX_PFC_PRI_EN_BITMAP_PRI_7);
+
+	DP_VERBOSE(p_hwfn, QED_MSG_DCB,
+		   "PFC params: willing %d, pfc_bitmap %d\n",
+		   p_params->pfc.willing, pfc_map);
+}
+
+static void
+qed_dcbx_get_ets_data(struct qed_hwfn *p_hwfn,
+		      struct dcbx_ets_feature *p_ets,
+		      struct qed_dcbx_params *p_params)
+{
+	u32 bw_map[2], tsa_map[2], pri_map;
+	int i;
+
+	p_params->ets_willing = QED_MFW_GET_FIELD(p_ets->flags,
+						  DCBX_ETS_WILLING);
+	p_params->ets_enabled = QED_MFW_GET_FIELD(p_ets->flags,
+						  DCBX_ETS_ENABLED);
+	p_params->ets_cbs = QED_MFW_GET_FIELD(p_ets->flags, DCBX_ETS_CBS);
+	p_params->max_ets_tc = QED_MFW_GET_FIELD(p_ets->flags,
+						 DCBX_ETS_MAX_TCS);
+	DP_VERBOSE(p_hwfn, QED_MSG_DCB,
+		   "ETS params: willing %d, ets_cbs %d pri_tc_tbl_0 %x max_ets_tc %d\n",
+		   p_params->ets_willing,
+		   p_params->ets_cbs,
+		   p_ets->pri_tc_tbl[0], p_params->max_ets_tc);
+
+	/* 8 bit tsa and bw data corresponding to each of the 8 TC's are
+	 * encoded in a type u32 array of size 2.
+	 */
+	bw_map[0] = be32_to_cpu(p_ets->tc_bw_tbl[0]);
+	bw_map[1] = be32_to_cpu(p_ets->tc_bw_tbl[1]);
+	tsa_map[0] = be32_to_cpu(p_ets->tc_tsa_tbl[0]);
+	tsa_map[1] = be32_to_cpu(p_ets->tc_tsa_tbl[1]);
+	pri_map = be32_to_cpu(p_ets->pri_tc_tbl[0]);
+	for (i = 0; i < QED_MAX_PFC_PRIORITIES; i++) {
+		p_params->ets_tc_bw_tbl[i] = ((u8 *)bw_map)[i];
+		p_params->ets_tc_tsa_tbl[i] = ((u8 *)tsa_map)[i];
+		p_params->ets_pri_tc_tbl[i] = QED_DCBX_PRIO2TC(pri_map, i);
+		DP_VERBOSE(p_hwfn, QED_MSG_DCB,
+			   "elem %d  bw_tbl %x tsa_tbl %x\n",
+			   i, p_params->ets_tc_bw_tbl[i],
+			   p_params->ets_tc_tsa_tbl[i]);
+	}
+}
+
+static void
+qed_dcbx_get_common_params(struct qed_hwfn *p_hwfn,
+			   struct dcbx_app_priority_feature *p_app,
+			   struct dcbx_app_priority_entry *p_tbl,
+			   struct dcbx_ets_feature *p_ets,
+			   u32 pfc, struct qed_dcbx_params *p_params)
+{
+	qed_dcbx_get_app_data(p_hwfn, p_app, p_tbl, p_params);
+	qed_dcbx_get_ets_data(p_hwfn, p_ets, p_params);
+	qed_dcbx_get_pfc_data(p_hwfn, pfc, p_params);
+}
+
+static void
+qed_dcbx_get_local_params(struct qed_hwfn *p_hwfn,
+			  struct qed_ptt *p_ptt, struct qed_dcbx_get *params)
+{
+	struct dcbx_features *p_feat;
+
+	p_feat = &p_hwfn->p_dcbx_info->local_admin.features;
+	qed_dcbx_get_common_params(p_hwfn, &p_feat->app,
+				   p_feat->app.app_pri_tbl, &p_feat->ets,
+				   p_feat->pfc, &params->local.params);
+	params->local.valid = true;
+}
+
+static void
+qed_dcbx_get_remote_params(struct qed_hwfn *p_hwfn,
+			   struct qed_ptt *p_ptt, struct qed_dcbx_get *params)
+{
+	struct dcbx_features *p_feat;
+
+	p_feat = &p_hwfn->p_dcbx_info->remote.features;
+	qed_dcbx_get_common_params(p_hwfn, &p_feat->app,
+				   p_feat->app.app_pri_tbl, &p_feat->ets,
+				   p_feat->pfc, &params->remote.params);
+	params->remote.valid = true;
+}
+
+static void
+qed_dcbx_get_operational_params(struct qed_hwfn *p_hwfn,
+				struct qed_ptt *p_ptt,
+				struct qed_dcbx_get *params)
+{
+	struct qed_dcbx_operational_params *p_operational;
+	struct qed_dcbx_results *p_results;
+	struct dcbx_features *p_feat;
+	bool enabled, err;
+	u32 flags;
+	bool val;
+
+	flags = p_hwfn->p_dcbx_info->operational.flags;
+
+	/* If DCBx version is non zero, then negotiation
+	 * was successfuly performed
+	 */
+	p_operational = &params->operational;
+	enabled = !!(QED_MFW_GET_FIELD(flags, DCBX_CONFIG_VERSION) !=
+		     DCBX_CONFIG_VERSION_DISABLED);
+	if (!enabled) {
+		p_operational->enabled = enabled;
+		p_operational->valid = false;
+		return;
+	}
+
+	p_feat = &p_hwfn->p_dcbx_info->operational.features;
+	p_results = &p_hwfn->p_dcbx_info->results;
+
+	val = !!(QED_MFW_GET_FIELD(flags, DCBX_CONFIG_VERSION) ==
+		 DCBX_CONFIG_VERSION_IEEE);
+	p_operational->ieee = val;
+	val = !!(QED_MFW_GET_FIELD(flags, DCBX_CONFIG_VERSION) ==
+		 DCBX_CONFIG_VERSION_CEE);
+	p_operational->cee = val;
+
+	DP_VERBOSE(p_hwfn, QED_MSG_DCB, "Version support: ieee %d, cee %d\n",
+		   p_operational->ieee, p_operational->cee);
+
+	qed_dcbx_get_common_params(p_hwfn, &p_feat->app,
+				   p_feat->app.app_pri_tbl, &p_feat->ets,
+				   p_feat->pfc, &params->operational.params);
+	qed_dcbx_get_priority_info(p_hwfn, &p_operational->app_prio, p_results);
+	err = QED_MFW_GET_FIELD(p_feat->app.flags, DCBX_APP_ERROR);
+	p_operational->err = err;
+	p_operational->enabled = enabled;
+	p_operational->valid = true;
+}
+
+static void
+qed_dcbx_get_local_lldp_params(struct qed_hwfn *p_hwfn,
+			       struct qed_ptt *p_ptt,
+			       struct qed_dcbx_get *params)
+{
+	struct lldp_config_params_s *p_local;
+
+	p_local = &p_hwfn->p_dcbx_info->lldp_local[LLDP_NEAREST_BRIDGE];
+
+	memcpy(params->lldp_local.local_chassis_id, p_local->local_chassis_id,
+	       ARRAY_SIZE(p_local->local_chassis_id));
+	memcpy(params->lldp_local.local_port_id, p_local->local_port_id,
+	       ARRAY_SIZE(p_local->local_port_id));
+}
+
+static void
+qed_dcbx_get_remote_lldp_params(struct qed_hwfn *p_hwfn,
+				struct qed_ptt *p_ptt,
+				struct qed_dcbx_get *params)
+{
+	struct lldp_status_params_s *p_remote;
+
+	p_remote = &p_hwfn->p_dcbx_info->lldp_remote[LLDP_NEAREST_BRIDGE];
+
+	memcpy(params->lldp_remote.peer_chassis_id, p_remote->peer_chassis_id,
+	       ARRAY_SIZE(p_remote->peer_chassis_id));
+	memcpy(params->lldp_remote.peer_port_id, p_remote->peer_port_id,
+	       ARRAY_SIZE(p_remote->peer_port_id));
+}
+
+static int
+qed_dcbx_get_params(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
+		    struct qed_dcbx_get *p_params,
+		    enum qed_mib_read_type type)
+{
+	switch (type) {
+	case QED_DCBX_REMOTE_MIB:
+		qed_dcbx_get_remote_params(p_hwfn, p_ptt, p_params);
+		break;
+	case QED_DCBX_LOCAL_MIB:
+		qed_dcbx_get_local_params(p_hwfn, p_ptt, p_params);
+		break;
+	case QED_DCBX_OPERATIONAL_MIB:
+		qed_dcbx_get_operational_params(p_hwfn, p_ptt, p_params);
+		break;
+	case QED_DCBX_REMOTE_LLDP_MIB:
+		qed_dcbx_get_remote_lldp_params(p_hwfn, p_ptt, p_params);
+		break;
+	case QED_DCBX_LOCAL_LLDP_MIB:
+		qed_dcbx_get_local_lldp_params(p_hwfn, p_ptt, p_params);
+		break;
+	default:
+		DP_ERR(p_hwfn, "MIB read err, unknown mib type %d\n", type);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+#endif
+
 static int
 qed_dcbx_read_local_lldp_mib(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
@@ -561,3 +852,1333 @@
 	p_dcb_data = &p_dest->eth_dcb_data;
 	qed_dcbx_update_protocol_data(p_dcb_data, p_src, DCBX_PROTOCOL_ETH);
 }
+
+#ifdef CONFIG_DCB
+static int qed_dcbx_query_params(struct qed_hwfn *p_hwfn,
+				 struct qed_dcbx_get *p_get,
+				 enum qed_mib_read_type type)
+{
+	struct qed_ptt *p_ptt;
+	int rc;
+
+	p_ptt = qed_ptt_acquire(p_hwfn);
+	if (!p_ptt)
+		return -EBUSY;
+
+	rc = qed_dcbx_read_mib(p_hwfn, p_ptt, type);
+	if (rc)
+		goto out;
+
+	rc = qed_dcbx_get_params(p_hwfn, p_ptt, p_get, type);
+
+out:
+	qed_ptt_release(p_hwfn, p_ptt);
+	return rc;
+}
+
+static void
+qed_dcbx_set_pfc_data(struct qed_hwfn *p_hwfn,
+		      u32 *pfc, struct qed_dcbx_params *p_params)
+{
+	u8 pfc_map = 0;
+	int i;
+
+	if (p_params->pfc.willing)
+		*pfc |= DCBX_PFC_WILLING_MASK;
+	else
+		*pfc &= ~DCBX_PFC_WILLING_MASK;
+
+	if (p_params->pfc.enabled)
+		*pfc |= DCBX_PFC_ENABLED_MASK;
+	else
+		*pfc &= ~DCBX_PFC_ENABLED_MASK;
+
+	*pfc &= ~DCBX_PFC_CAPS_MASK;
+	*pfc |= (u32)p_params->pfc.max_tc << DCBX_PFC_CAPS_SHIFT;
+
+	for (i = 0; i < QED_MAX_PFC_PRIORITIES; i++)
+		if (p_params->pfc.prio[i])
+			pfc_map |= BIT(i);
+
+	*pfc |= (pfc_map << DCBX_PFC_PRI_EN_BITMAP_SHIFT);
+
+	DP_VERBOSE(p_hwfn, QED_MSG_DCB, "pfc = 0x%x\n", *pfc);
+}
+
+static void
+qed_dcbx_set_ets_data(struct qed_hwfn *p_hwfn,
+		      struct dcbx_ets_feature *p_ets,
+		      struct qed_dcbx_params *p_params)
+{
+	u8 *bw_map, *tsa_map;
+	u32 val;
+	int i;
+
+	if (p_params->ets_willing)
+		p_ets->flags |= DCBX_ETS_WILLING_MASK;
+	else
+		p_ets->flags &= ~DCBX_ETS_WILLING_MASK;
+
+	if (p_params->ets_cbs)
+		p_ets->flags |= DCBX_ETS_CBS_MASK;
+	else
+		p_ets->flags &= ~DCBX_ETS_CBS_MASK;
+
+	if (p_params->ets_enabled)
+		p_ets->flags |= DCBX_ETS_ENABLED_MASK;
+	else
+		p_ets->flags &= ~DCBX_ETS_ENABLED_MASK;
+
+	p_ets->flags &= ~DCBX_ETS_MAX_TCS_MASK;
+	p_ets->flags |= (u32)p_params->max_ets_tc << DCBX_ETS_MAX_TCS_SHIFT;
+
+	bw_map = (u8 *)&p_ets->tc_bw_tbl[0];
+	tsa_map = (u8 *)&p_ets->tc_tsa_tbl[0];
+	p_ets->pri_tc_tbl[0] = 0;
+	for (i = 0; i < QED_MAX_PFC_PRIORITIES; i++) {
+		bw_map[i] = p_params->ets_tc_bw_tbl[i];
+		tsa_map[i] = p_params->ets_tc_tsa_tbl[i];
+		/* Copy the priority value to the corresponding 4 bits in the
+		 * traffic class table.
+		 */
+		val = (((u32)p_params->ets_pri_tc_tbl[i]) << ((7 - i) * 4));
+		p_ets->pri_tc_tbl[0] |= val;
+	}
+	p_ets->pri_tc_tbl[0] = cpu_to_be32(p_ets->pri_tc_tbl[0]);
+	for (i = 0; i < 2; i++) {
+		p_ets->tc_bw_tbl[i] = cpu_to_be32(p_ets->tc_bw_tbl[i]);
+		p_ets->tc_tsa_tbl[i] = cpu_to_be32(p_ets->tc_tsa_tbl[i]);
+	}
+}
+
+static void
+qed_dcbx_set_app_data(struct qed_hwfn *p_hwfn,
+		      struct dcbx_app_priority_feature *p_app,
+		      struct qed_dcbx_params *p_params)
+{
+	u32 *entry;
+	int i;
+
+	if (p_params->app_willing)
+		p_app->flags |= DCBX_APP_WILLING_MASK;
+	else
+		p_app->flags &= ~DCBX_APP_WILLING_MASK;
+
+	if (p_params->app_valid)
+		p_app->flags |= DCBX_APP_ENABLED_MASK;
+	else
+		p_app->flags &= ~DCBX_APP_ENABLED_MASK;
+
+	p_app->flags &= ~DCBX_APP_NUM_ENTRIES_MASK;
+	p_app->flags |= (u32)p_params->num_app_entries <<
+	    DCBX_APP_NUM_ENTRIES_SHIFT;
+
+	for (i = 0; i < DCBX_MAX_APP_PROTOCOL; i++) {
+		entry = &p_app->app_pri_tbl[i].entry;
+		*entry &= ~DCBX_APP_SF_MASK;
+		if (p_params->app_entry[i].ethtype)
+			*entry |= ((u32)DCBX_APP_SF_ETHTYPE <<
+				   DCBX_APP_SF_SHIFT);
+		else
+			*entry |= ((u32)DCBX_APP_SF_PORT << DCBX_APP_SF_SHIFT);
+		*entry &= ~DCBX_APP_PROTOCOL_ID_MASK;
+		*entry |= ((u32)p_params->app_entry[i].proto_id <<
+			   DCBX_APP_PROTOCOL_ID_SHIFT);
+		*entry &= ~DCBX_APP_PRI_MAP_MASK;
+		*entry |= ((u32)(p_params->app_entry[i].prio) <<
+			   DCBX_APP_PRI_MAP_SHIFT);
+	}
+}
+
+static void
+qed_dcbx_set_local_params(struct qed_hwfn *p_hwfn,
+			  struct dcbx_local_params *local_admin,
+			  struct qed_dcbx_set *params)
+{
+	local_admin->flags = 0;
+	memcpy(&local_admin->features,
+	       &p_hwfn->p_dcbx_info->operational.features,
+	       sizeof(local_admin->features));
+
+	if (params->enabled)
+		local_admin->config = params->ver_num;
+	else
+		local_admin->config = DCBX_CONFIG_VERSION_DISABLED;
+
+	if (params->override_flags & QED_DCBX_OVERRIDE_PFC_CFG)
+		qed_dcbx_set_pfc_data(p_hwfn, &local_admin->features.pfc,
+				      &params->config.params);
+
+	if (params->override_flags & QED_DCBX_OVERRIDE_ETS_CFG)
+		qed_dcbx_set_ets_data(p_hwfn, &local_admin->features.ets,
+				      &params->config.params);
+
+	if (params->override_flags & QED_DCBX_OVERRIDE_APP_CFG)
+		qed_dcbx_set_app_data(p_hwfn, &local_admin->features.app,
+				      &params->config.params);
+}
+
+int qed_dcbx_config_params(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
+			   struct qed_dcbx_set *params, bool hw_commit)
+{
+	struct dcbx_local_params local_admin;
+	struct qed_dcbx_mib_meta_data data;
+	u32 resp = 0, param = 0;
+	int rc = 0;
+
+	if (!hw_commit) {
+		memcpy(&p_hwfn->p_dcbx_info->set, params,
+		       sizeof(struct qed_dcbx_set));
+		return 0;
+	}
+
+	/* clear set-parmas cache */
+	memset(&p_hwfn->p_dcbx_info->set, 0, sizeof(p_hwfn->p_dcbx_info->set));
+
+	memset(&local_admin, 0, sizeof(local_admin));
+	qed_dcbx_set_local_params(p_hwfn, &local_admin, params);
+
+	data.addr = p_hwfn->mcp_info->port_addr +
+	    offsetof(struct public_port, local_admin_dcbx_mib);
+	data.local_admin = &local_admin;
+	data.size = sizeof(struct dcbx_local_params);
+	qed_memcpy_to(p_hwfn, p_ptt, data.addr, data.local_admin, data.size);
+
+	rc = qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_SET_DCBX,
+			 1 << DRV_MB_PARAM_LLDP_SEND_SHIFT, &resp, &param);
+	if (rc)
+		DP_NOTICE(p_hwfn, "Failed to send DCBX update request\n");
+
+	return rc;
+}
+
+int qed_dcbx_get_config_params(struct qed_hwfn *p_hwfn,
+			       struct qed_dcbx_set *params)
+{
+	struct qed_dcbx_get *dcbx_info;
+	int rc;
+
+	if (p_hwfn->p_dcbx_info->set.config.valid) {
+		memcpy(params, &p_hwfn->p_dcbx_info->set,
+		       sizeof(struct qed_dcbx_set));
+		return 0;
+	}
+
+	dcbx_info = kmalloc(sizeof(*dcbx_info), GFP_KERNEL);
+	if (!dcbx_info) {
+		DP_ERR(p_hwfn, "Failed to allocate struct qed_dcbx_info\n");
+		return -ENOMEM;
+	}
+
+	rc = qed_dcbx_query_params(p_hwfn, dcbx_info, QED_DCBX_OPERATIONAL_MIB);
+	if (rc) {
+		kfree(dcbx_info);
+		return rc;
+	}
+
+	p_hwfn->p_dcbx_info->set.override_flags = 0;
+	p_hwfn->p_dcbx_info->set.ver_num = DCBX_CONFIG_VERSION_DISABLED;
+	if (dcbx_info->operational.cee)
+		p_hwfn->p_dcbx_info->set.ver_num |= DCBX_CONFIG_VERSION_CEE;
+	if (dcbx_info->operational.ieee)
+		p_hwfn->p_dcbx_info->set.ver_num |= DCBX_CONFIG_VERSION_IEEE;
+
+	p_hwfn->p_dcbx_info->set.enabled = dcbx_info->operational.enabled;
+	memcpy(&p_hwfn->p_dcbx_info->set.config.params,
+	       &dcbx_info->operational.params,
+	       sizeof(struct qed_dcbx_admin_params));
+	p_hwfn->p_dcbx_info->set.config.valid = true;
+
+	memcpy(params, &p_hwfn->p_dcbx_info->set, sizeof(struct qed_dcbx_set));
+
+	kfree(dcbx_info);
+
+	return 0;
+}
+
+static struct qed_dcbx_get *qed_dcbnl_get_dcbx(struct qed_hwfn *hwfn,
+					       enum qed_mib_read_type type)
+{
+	struct qed_dcbx_get *dcbx_info;
+
+	dcbx_info = kmalloc(sizeof(*dcbx_info), GFP_KERNEL);
+	if (!dcbx_info) {
+		DP_ERR(hwfn->cdev, "Failed to allocate memory for dcbx_info\n");
+		return NULL;
+	}
+
+	if (qed_dcbx_query_params(hwfn, dcbx_info, type)) {
+		kfree(dcbx_info);
+		return NULL;
+	}
+
+	if ((type == QED_DCBX_OPERATIONAL_MIB) &&
+	    !dcbx_info->operational.enabled) {
+		DP_INFO(hwfn, "DCBX is not enabled/operational\n");
+		kfree(dcbx_info);
+		return NULL;
+	}
+
+	return dcbx_info;
+}
+
+static u8 qed_dcbnl_getstate(struct qed_dev *cdev)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+	bool enabled;
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
+	if (!dcbx_info)
+		return 0;
+
+	enabled = dcbx_info->operational.enabled;
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "DCB state = %d\n", enabled);
+	kfree(dcbx_info);
+
+	return enabled;
+}
+
+static u8 qed_dcbnl_setstate(struct qed_dev *cdev, u8 state)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_set dcbx_set;
+	struct qed_ptt *ptt;
+	int rc;
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "DCB state = %d\n", state);
+
+	memset(&dcbx_set, 0, sizeof(dcbx_set));
+	rc = qed_dcbx_get_config_params(hwfn, &dcbx_set);
+	if (rc)
+		return 1;
+
+	dcbx_set.enabled = !!state;
+
+	ptt = qed_ptt_acquire(hwfn);
+	if (!ptt)
+		return 1;
+
+	rc = qed_dcbx_config_params(hwfn, ptt, &dcbx_set, 0);
+
+	qed_ptt_release(hwfn, ptt);
+
+	return rc ? 1 : 0;
+}
+
+static void qed_dcbnl_getpgtccfgtx(struct qed_dev *cdev, int tc, u8 *prio_type,
+				   u8 *pgid, u8 *bw_pct, u8 *up_map)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "tc = %d\n", tc);
+	*prio_type = *pgid = *bw_pct = *up_map = 0;
+	if (tc < 0 || tc >= QED_MAX_PFC_PRIORITIES) {
+		DP_INFO(hwfn, "Invalid tc %d\n", tc);
+		return;
+	}
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
+	if (!dcbx_info)
+		return;
+
+	*pgid = dcbx_info->operational.params.ets_pri_tc_tbl[tc];
+	kfree(dcbx_info);
+}
+
+static void qed_dcbnl_getpgbwgcfgtx(struct qed_dev *cdev, int pgid, u8 *bw_pct)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+
+	*bw_pct = 0;
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "pgid = %d\n", pgid);
+	if (pgid < 0 || pgid >= QED_MAX_PFC_PRIORITIES) {
+		DP_INFO(hwfn, "Invalid pgid %d\n", pgid);
+		return;
+	}
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
+	if (!dcbx_info)
+		return;
+
+	*bw_pct = dcbx_info->operational.params.ets_tc_bw_tbl[pgid];
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "bw_pct = %d\n", *bw_pct);
+	kfree(dcbx_info);
+}
+
+static void qed_dcbnl_getpgtccfgrx(struct qed_dev *cdev, int tc, u8 *prio,
+				   u8 *bwg_id, u8 *bw_pct, u8 *up_map)
+{
+	DP_INFO(QED_LEADING_HWFN(cdev), "Rx ETS is not supported\n");
+	*prio = *bwg_id = *bw_pct = *up_map = 0;
+}
+
+static void qed_dcbnl_getpgbwgcfgrx(struct qed_dev *cdev,
+				    int bwg_id, u8 *bw_pct)
+{
+	DP_INFO(QED_LEADING_HWFN(cdev), "Rx ETS is not supported\n");
+	*bw_pct = 0;
+}
+
+static void qed_dcbnl_getpfccfg(struct qed_dev *cdev,
+				int priority, u8 *setting)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "priority = %d\n", priority);
+	if (priority < 0 || priority >= QED_MAX_PFC_PRIORITIES) {
+		DP_INFO(hwfn, "Invalid priority %d\n", priority);
+		return;
+	}
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
+	if (!dcbx_info)
+		return;
+
+	*setting = dcbx_info->operational.params.pfc.prio[priority];
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "setting = %d\n", *setting);
+	kfree(dcbx_info);
+}
+
+static void qed_dcbnl_setpfccfg(struct qed_dev *cdev, int priority, u8 setting)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_set dcbx_set;
+	struct qed_ptt *ptt;
+	int rc;
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "priority = %d setting = %d\n",
+		   priority, setting);
+	if (priority < 0 || priority >= QED_MAX_PFC_PRIORITIES) {
+		DP_INFO(hwfn, "Invalid priority %d\n", priority);
+		return;
+	}
+
+	memset(&dcbx_set, 0, sizeof(dcbx_set));
+	rc = qed_dcbx_get_config_params(hwfn, &dcbx_set);
+	if (rc)
+		return;
+
+	dcbx_set.override_flags |= QED_DCBX_OVERRIDE_PFC_CFG;
+	dcbx_set.config.params.pfc.prio[priority] = !!setting;
+
+	ptt = qed_ptt_acquire(hwfn);
+	if (!ptt)
+		return;
+
+	rc = qed_dcbx_config_params(hwfn, ptt, &dcbx_set, 0);
+
+	qed_ptt_release(hwfn, ptt);
+}
+
+static u8 qed_dcbnl_getcap(struct qed_dev *cdev, int capid, u8 *cap)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+	int rc = 0;
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "capid = %d\n", capid);
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
+	if (!dcbx_info)
+		return 1;
+
+	switch (capid) {
+	case DCB_CAP_ATTR_PG:
+	case DCB_CAP_ATTR_PFC:
+	case DCB_CAP_ATTR_UP2TC:
+	case DCB_CAP_ATTR_GSP:
+		*cap = true;
+		break;
+	case DCB_CAP_ATTR_PG_TCS:
+	case DCB_CAP_ATTR_PFC_TCS:
+		*cap = 0x80;
+		break;
+	case DCB_CAP_ATTR_DCBX:
+		*cap = (DCB_CAP_DCBX_LLD_MANAGED | DCB_CAP_DCBX_VER_CEE |
+			DCB_CAP_DCBX_VER_IEEE);
+		break;
+	default:
+		*cap = false;
+		rc = 1;
+	}
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "id = %d caps = %d\n", capid, *cap);
+	kfree(dcbx_info);
+
+	return rc;
+}
+
+static int qed_dcbnl_getnumtcs(struct qed_dev *cdev, int tcid, u8 *num)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+	int rc = 0;
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "tcid = %d\n", tcid);
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
+	if (!dcbx_info)
+		return -EINVAL;
+
+	switch (tcid) {
+	case DCB_NUMTCS_ATTR_PG:
+		*num = dcbx_info->operational.params.max_ets_tc;
+		break;
+	case DCB_NUMTCS_ATTR_PFC:
+		*num = dcbx_info->operational.params.pfc.max_tc;
+		break;
+	default:
+		rc = -EINVAL;
+	}
+
+	kfree(dcbx_info);
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "numtcs = %d\n", *num);
+
+	return rc;
+}
+
+static u8 qed_dcbnl_getpfcstate(struct qed_dev *cdev)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+	bool enabled;
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
+	if (!dcbx_info)
+		return 0;
+
+	enabled = dcbx_info->operational.params.pfc.enabled;
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "pfc state = %d\n", enabled);
+	kfree(dcbx_info);
+
+	return enabled;
+}
+
+static u8 qed_dcbnl_getdcbx(struct qed_dev *cdev)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+	u8 mode = 0;
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
+	if (!dcbx_info)
+		return 0;
+
+	if (dcbx_info->operational.enabled)
+		mode |= DCB_CAP_DCBX_LLD_MANAGED;
+	if (dcbx_info->operational.ieee)
+		mode |= DCB_CAP_DCBX_VER_IEEE;
+	if (dcbx_info->operational.cee)
+		mode |= DCB_CAP_DCBX_VER_CEE;
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "dcb mode = %d\n", mode);
+	kfree(dcbx_info);
+
+	return mode;
+}
+
+static void qed_dcbnl_setpgtccfgtx(struct qed_dev *cdev,
+				   int tc,
+				   u8 pri_type, u8 pgid, u8 bw_pct, u8 up_map)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_set dcbx_set;
+	struct qed_ptt *ptt;
+	int rc;
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB,
+		   "tc = %d pri_type = %d pgid = %d bw_pct = %d up_map = %d\n",
+		   tc, pri_type, pgid, bw_pct, up_map);
+
+	if (tc < 0 || tc >= QED_MAX_PFC_PRIORITIES) {
+		DP_INFO(hwfn, "Invalid tc %d\n", tc);
+		return;
+	}
+
+	memset(&dcbx_set, 0, sizeof(dcbx_set));
+	rc = qed_dcbx_get_config_params(hwfn, &dcbx_set);
+	if (rc)
+		return;
+
+	dcbx_set.override_flags |= QED_DCBX_OVERRIDE_ETS_CFG;
+	dcbx_set.config.params.ets_pri_tc_tbl[tc] = pgid;
+
+	ptt = qed_ptt_acquire(hwfn);
+	if (!ptt)
+		return;
+
+	rc = qed_dcbx_config_params(hwfn, ptt, &dcbx_set, 0);
+
+	qed_ptt_release(hwfn, ptt);
+}
+
+static void qed_dcbnl_setpgtccfgrx(struct qed_dev *cdev, int prio,
+				   u8 pri_type, u8 pgid, u8 bw_pct, u8 up_map)
+{
+	DP_INFO(QED_LEADING_HWFN(cdev), "Rx ETS is not supported\n");
+}
+
+static void qed_dcbnl_setpgbwgcfgtx(struct qed_dev *cdev, int pgid, u8 bw_pct)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_set dcbx_set;
+	struct qed_ptt *ptt;
+	int rc;
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "pgid = %d bw_pct = %d\n", pgid, bw_pct);
+	if (pgid < 0 || pgid >= QED_MAX_PFC_PRIORITIES) {
+		DP_INFO(hwfn, "Invalid pgid %d\n", pgid);
+		return;
+	}
+
+	memset(&dcbx_set, 0, sizeof(dcbx_set));
+	rc = qed_dcbx_get_config_params(hwfn, &dcbx_set);
+	if (rc)
+		return;
+
+	dcbx_set.override_flags |= QED_DCBX_OVERRIDE_ETS_CFG;
+	dcbx_set.config.params.ets_tc_bw_tbl[pgid] = bw_pct;
+
+	ptt = qed_ptt_acquire(hwfn);
+	if (!ptt)
+		return;
+
+	rc = qed_dcbx_config_params(hwfn, ptt, &dcbx_set, 0);
+
+	qed_ptt_release(hwfn, ptt);
+}
+
+static void qed_dcbnl_setpgbwgcfgrx(struct qed_dev *cdev, int pgid, u8 bw_pct)
+{
+	DP_INFO(QED_LEADING_HWFN(cdev), "Rx ETS is not supported\n");
+}
+
+static u8 qed_dcbnl_setall(struct qed_dev *cdev)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_set dcbx_set;
+	struct qed_ptt *ptt;
+	int rc;
+
+	memset(&dcbx_set, 0, sizeof(dcbx_set));
+	rc = qed_dcbx_get_config_params(hwfn, &dcbx_set);
+	if (rc)
+		return 1;
+
+	ptt = qed_ptt_acquire(hwfn);
+	if (!ptt)
+		return 1;
+
+	rc = qed_dcbx_config_params(hwfn, ptt, &dcbx_set, 1);
+
+	qed_ptt_release(hwfn, ptt);
+
+	return rc;
+}
+
+static int qed_dcbnl_setnumtcs(struct qed_dev *cdev, int tcid, u8 num)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_set dcbx_set;
+	struct qed_ptt *ptt;
+	int rc;
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "tcid = %d num = %d\n", tcid, num);
+	memset(&dcbx_set, 0, sizeof(dcbx_set));
+	rc = qed_dcbx_get_config_params(hwfn, &dcbx_set);
+	if (rc)
+		return 1;
+
+	switch (tcid) {
+	case DCB_NUMTCS_ATTR_PG:
+		dcbx_set.override_flags |= QED_DCBX_OVERRIDE_ETS_CFG;
+		dcbx_set.config.params.max_ets_tc = num;
+		break;
+	case DCB_NUMTCS_ATTR_PFC:
+		dcbx_set.override_flags |= QED_DCBX_OVERRIDE_PFC_CFG;
+		dcbx_set.config.params.pfc.max_tc = num;
+		break;
+	default:
+		DP_INFO(hwfn, "Invalid tcid %d\n", tcid);
+		return -EINVAL;
+	}
+
+	ptt = qed_ptt_acquire(hwfn);
+	if (!ptt)
+		return -EINVAL;
+
+	rc = qed_dcbx_config_params(hwfn, ptt, &dcbx_set, 0);
+
+	qed_ptt_release(hwfn, ptt);
+
+	return 0;
+}
+
+static void qed_dcbnl_setpfcstate(struct qed_dev *cdev, u8 state)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_set dcbx_set;
+	struct qed_ptt *ptt;
+	int rc;
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "new state = %d\n", state);
+
+	memset(&dcbx_set, 0, sizeof(dcbx_set));
+	rc = qed_dcbx_get_config_params(hwfn, &dcbx_set);
+	if (rc)
+		return;
+
+	dcbx_set.override_flags |= QED_DCBX_OVERRIDE_PFC_CFG;
+	dcbx_set.config.params.pfc.enabled = !!state;
+
+	ptt = qed_ptt_acquire(hwfn);
+	if (!ptt)
+		return;
+
+	rc = qed_dcbx_config_params(hwfn, ptt, &dcbx_set, 0);
+
+	qed_ptt_release(hwfn, ptt);
+}
+
+static int qed_dcbnl_getapp(struct qed_dev *cdev, u8 idtype, u16 idval)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+	struct qed_app_entry *entry;
+	bool ethtype;
+	u8 prio = 0;
+	int i;
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
+	if (!dcbx_info)
+		return -EINVAL;
+
+	ethtype = !!(idtype == DCB_APP_IDTYPE_ETHTYPE);
+	for (i = 0; i < QED_DCBX_MAX_APP_PROTOCOL; i++) {
+		entry = &dcbx_info->operational.params.app_entry[i];
+		if ((entry->ethtype == ethtype) && (entry->proto_id == idval)) {
+			prio = entry->prio;
+			break;
+		}
+	}
+
+	if (i == QED_DCBX_MAX_APP_PROTOCOL) {
+		DP_ERR(cdev, "App entry (%d, %d) not found\n", idtype, idval);
+		kfree(dcbx_info);
+		return -EINVAL;
+	}
+
+	kfree(dcbx_info);
+
+	return prio;
+}
+
+static int qed_dcbnl_setapp(struct qed_dev *cdev,
+			    u8 idtype, u16 idval, u8 pri_map)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_set dcbx_set;
+	struct qed_app_entry *entry;
+	struct qed_ptt *ptt;
+	bool ethtype;
+	int rc, i;
+
+	memset(&dcbx_set, 0, sizeof(dcbx_set));
+	rc = qed_dcbx_get_config_params(hwfn, &dcbx_set);
+	if (rc)
+		return -EINVAL;
+
+	ethtype = !!(idtype == DCB_APP_IDTYPE_ETHTYPE);
+	for (i = 0; i < QED_DCBX_MAX_APP_PROTOCOL; i++) {
+		entry = &dcbx_set.config.params.app_entry[i];
+		if ((entry->ethtype == ethtype) && (entry->proto_id == idval))
+			break;
+		/* First empty slot */
+		if (!entry->proto_id)
+			break;
+	}
+
+	if (i == QED_DCBX_MAX_APP_PROTOCOL) {
+		DP_ERR(cdev, "App table is full\n");
+		return -EBUSY;
+	}
+
+	dcbx_set.override_flags |= QED_DCBX_OVERRIDE_APP_CFG;
+	dcbx_set.config.params.app_entry[i].ethtype = ethtype;
+	dcbx_set.config.params.app_entry[i].proto_id = idval;
+	dcbx_set.config.params.app_entry[i].prio = pri_map;
+
+	ptt = qed_ptt_acquire(hwfn);
+	if (!ptt)
+		return -EBUSY;
+
+	rc = qed_dcbx_config_params(hwfn, ptt, &dcbx_set, 0);
+
+	qed_ptt_release(hwfn, ptt);
+
+	return rc;
+}
+
+static u8 qed_dcbnl_setdcbx(struct qed_dev *cdev, u8 mode)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_set dcbx_set;
+	struct qed_ptt *ptt;
+	int rc;
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "new mode = %x\n", mode);
+
+	if (!(mode & DCB_CAP_DCBX_VER_IEEE) && !(mode & DCB_CAP_DCBX_VER_CEE)) {
+		DP_INFO(hwfn, "Allowed mode is cee, ieee or both\n");
+		return 1;
+	}
+
+	memset(&dcbx_set, 0, sizeof(dcbx_set));
+	rc = qed_dcbx_get_config_params(hwfn, &dcbx_set);
+	if (rc)
+		return 1;
+
+	dcbx_set.ver_num = 0;
+	if (mode & DCB_CAP_DCBX_VER_CEE) {
+		dcbx_set.ver_num |= DCBX_CONFIG_VERSION_CEE;
+		dcbx_set.enabled = true;
+	}
+
+	if (mode & DCB_CAP_DCBX_VER_IEEE) {
+		dcbx_set.ver_num |= DCBX_CONFIG_VERSION_IEEE;
+		dcbx_set.enabled = true;
+	}
+
+	ptt = qed_ptt_acquire(hwfn);
+	if (!ptt)
+		return 1;
+
+	rc = qed_dcbx_config_params(hwfn, ptt, &dcbx_set, 0);
+
+	qed_ptt_release(hwfn, ptt);
+
+	return 0;
+}
+
+static u8 qed_dcbnl_getfeatcfg(struct qed_dev *cdev, int featid, u8 *flags)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "Feature id  = %d\n", featid);
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
+	if (!dcbx_info)
+		return 1;
+
+	*flags = 0;
+	switch (featid) {
+	case DCB_FEATCFG_ATTR_PG:
+		if (dcbx_info->operational.params.ets_enabled)
+			*flags = DCB_FEATCFG_ENABLE;
+		else
+			*flags = DCB_FEATCFG_ERROR;
+		break;
+	case DCB_FEATCFG_ATTR_PFC:
+		if (dcbx_info->operational.params.pfc.enabled)
+			*flags = DCB_FEATCFG_ENABLE;
+		else
+			*flags = DCB_FEATCFG_ERROR;
+		break;
+	case DCB_FEATCFG_ATTR_APP:
+		if (dcbx_info->operational.params.app_valid)
+			*flags = DCB_FEATCFG_ENABLE;
+		else
+			*flags = DCB_FEATCFG_ERROR;
+		break;
+	default:
+		DP_INFO(hwfn, "Invalid feature-ID %d\n", featid);
+		kfree(dcbx_info);
+		return 1;
+	}
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "flags = %d\n", *flags);
+	kfree(dcbx_info);
+
+	return 0;
+}
+
+static u8 qed_dcbnl_setfeatcfg(struct qed_dev *cdev, int featid, u8 flags)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_set dcbx_set;
+	bool enabled, willing;
+	struct qed_ptt *ptt;
+	int rc;
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "featid = %d flags = %d\n",
+		   featid, flags);
+	memset(&dcbx_set, 0, sizeof(dcbx_set));
+	rc = qed_dcbx_get_config_params(hwfn, &dcbx_set);
+	if (rc)
+		return 1;
+
+	enabled = !!(flags & DCB_FEATCFG_ENABLE);
+	willing = !!(flags & DCB_FEATCFG_WILLING);
+	switch (featid) {
+	case DCB_FEATCFG_ATTR_PG:
+		dcbx_set.override_flags |= QED_DCBX_OVERRIDE_ETS_CFG;
+		dcbx_set.config.params.ets_enabled = enabled;
+		dcbx_set.config.params.ets_willing = willing;
+		break;
+	case DCB_FEATCFG_ATTR_PFC:
+		dcbx_set.override_flags |= QED_DCBX_OVERRIDE_PFC_CFG;
+		dcbx_set.config.params.pfc.enabled = enabled;
+		dcbx_set.config.params.pfc.willing = willing;
+		break;
+	case DCB_FEATCFG_ATTR_APP:
+		dcbx_set.override_flags |= QED_DCBX_OVERRIDE_APP_CFG;
+		dcbx_set.config.params.app_willing = willing;
+		break;
+	default:
+		DP_INFO(hwfn, "Invalid feature-ID %d\n", featid);
+		return 1;
+	}
+
+	ptt = qed_ptt_acquire(hwfn);
+	if (!ptt)
+		return 1;
+
+	rc = qed_dcbx_config_params(hwfn, ptt, &dcbx_set, 0);
+
+	qed_ptt_release(hwfn, ptt);
+
+	return 0;
+}
+
+static int qed_dcbnl_peer_getappinfo(struct qed_dev *cdev,
+				     struct dcb_peer_app_info *info,
+				     u16 *app_count)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_REMOTE_MIB);
+	if (!dcbx_info)
+		return -EINVAL;
+
+	info->willing = dcbx_info->remote.params.app_willing;
+	info->error = dcbx_info->remote.params.app_error;
+	*app_count = dcbx_info->remote.params.num_app_entries;
+	kfree(dcbx_info);
+
+	return 0;
+}
+
+static int qed_dcbnl_peer_getapptable(struct qed_dev *cdev,
+				      struct dcb_app *table)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+	int i;
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_REMOTE_MIB);
+	if (!dcbx_info)
+		return -EINVAL;
+
+	for (i = 0; i < dcbx_info->remote.params.num_app_entries; i++) {
+		if (dcbx_info->remote.params.app_entry[i].ethtype)
+			table[i].selector = DCB_APP_IDTYPE_ETHTYPE;
+		else
+			table[i].selector = DCB_APP_IDTYPE_PORTNUM;
+		table[i].priority = dcbx_info->remote.params.app_entry[i].prio;
+		table[i].protocol =
+		    dcbx_info->remote.params.app_entry[i].proto_id;
+	}
+
+	kfree(dcbx_info);
+
+	return 0;
+}
+
+static int qed_dcbnl_cee_peer_getpfc(struct qed_dev *cdev, struct cee_pfc *pfc)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+	int i;
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_REMOTE_MIB);
+	if (!dcbx_info)
+		return -EINVAL;
+
+	for (i = 0; i < QED_MAX_PFC_PRIORITIES; i++)
+		if (dcbx_info->remote.params.pfc.prio[i])
+			pfc->pfc_en |= BIT(i);
+
+	pfc->tcs_supported = dcbx_info->remote.params.pfc.max_tc;
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "pfc state = %d tcs_supported = %d\n",
+		   pfc->pfc_en, pfc->tcs_supported);
+	kfree(dcbx_info);
+
+	return 0;
+}
+
+static int qed_dcbnl_cee_peer_getpg(struct qed_dev *cdev, struct cee_pg *pg)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+	int i;
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_REMOTE_MIB);
+	if (!dcbx_info)
+		return -EINVAL;
+
+	pg->willing = dcbx_info->remote.params.ets_willing;
+	for (i = 0; i < QED_MAX_PFC_PRIORITIES; i++) {
+		pg->pg_bw[i] = dcbx_info->remote.params.ets_tc_bw_tbl[i];
+		pg->prio_pg[i] = dcbx_info->remote.params.ets_pri_tc_tbl[i];
+	}
+
+	DP_VERBOSE(hwfn, QED_MSG_DCB, "willing = %d", pg->willing);
+	kfree(dcbx_info);
+
+	return 0;
+}
+
+static int qed_dcbnl_get_ieee_pfc(struct qed_dev *cdev,
+				  struct ieee_pfc *pfc, bool remote)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_params *params;
+	struct qed_dcbx_get *dcbx_info;
+	int rc, i;
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
+	if (!dcbx_info)
+		return -EINVAL;
+
+	if (!dcbx_info->operational.ieee) {
+		DP_INFO(hwfn, "DCBX is not enabled/operational in IEEE mode\n");
+		return -EINVAL;
+	}
+
+	if (remote) {
+		memset(dcbx_info, 0, sizeof(*dcbx_info));
+		rc = qed_dcbx_query_params(hwfn, dcbx_info,
+					   QED_DCBX_REMOTE_MIB);
+		if (rc) {
+			kfree(dcbx_info);
+			return -EINVAL;
+		}
+
+		params = &dcbx_info->remote.params;
+	} else {
+		params = &dcbx_info->operational.params;
+	}
+
+	pfc->pfc_cap = params->pfc.max_tc;
+	pfc->pfc_en = 0;
+	for (i = 0; i < QED_MAX_PFC_PRIORITIES; i++)
+		if (params->pfc.prio[i])
+			pfc->pfc_en |= BIT(i);
+
+	kfree(dcbx_info);
+
+	return 0;
+}
+
+static int qed_dcbnl_ieee_getpfc(struct qed_dev *cdev, struct ieee_pfc *pfc)
+{
+	return qed_dcbnl_get_ieee_pfc(cdev, pfc, false);
+}
+
+static int qed_dcbnl_ieee_setpfc(struct qed_dev *cdev, struct ieee_pfc *pfc)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+	struct qed_dcbx_set dcbx_set;
+	struct qed_ptt *ptt;
+	int rc, i;
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
+	if (!dcbx_info)
+		return -EINVAL;
+
+	if (!dcbx_info->operational.ieee) {
+		DP_INFO(hwfn, "DCBX is not enabled/operational in IEEE mode\n");
+		kfree(dcbx_info);
+		return -EINVAL;
+	}
+
+	kfree(dcbx_info);
+
+	memset(&dcbx_set, 0, sizeof(dcbx_set));
+	rc = qed_dcbx_get_config_params(hwfn, &dcbx_set);
+	if (rc)
+		return -EINVAL;
+
+	dcbx_set.override_flags |= QED_DCBX_OVERRIDE_PFC_CFG;
+	for (i = 0; i < QED_MAX_PFC_PRIORITIES; i++)
+		dcbx_set.config.params.pfc.prio[i] = !!(pfc->pfc_en & BIT(i));
+
+	ptt = qed_ptt_acquire(hwfn);
+	if (!ptt)
+		return -EINVAL;
+
+	rc = qed_dcbx_config_params(hwfn, ptt, &dcbx_set, 0);
+
+	qed_ptt_release(hwfn, ptt);
+
+	return rc;
+}
+
+static int qed_dcbnl_get_ieee_ets(struct qed_dev *cdev,
+				  struct ieee_ets *ets, bool remote)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+	struct qed_dcbx_params *params;
+	int rc;
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
+	if (!dcbx_info)
+		return -EINVAL;
+
+	if (!dcbx_info->operational.ieee) {
+		DP_INFO(hwfn, "DCBX is not enabled/operational in IEEE mode\n");
+		kfree(dcbx_info);
+		return -EINVAL;
+	}
+
+	if (remote) {
+		memset(dcbx_info, 0, sizeof(*dcbx_info));
+		rc = qed_dcbx_query_params(hwfn, dcbx_info,
+					   QED_DCBX_REMOTE_MIB);
+		if (rc) {
+			kfree(dcbx_info);
+			return -EINVAL;
+		}
+
+		params = &dcbx_info->remote.params;
+	} else {
+		params = &dcbx_info->operational.params;
+	}
+
+	ets->ets_cap = params->max_ets_tc;
+	ets->willing = params->ets_willing;
+	ets->cbs = params->ets_cbs;
+	memcpy(ets->tc_tx_bw, params->ets_tc_bw_tbl, sizeof(ets->tc_tx_bw));
+	memcpy(ets->tc_tsa, params->ets_tc_tsa_tbl, sizeof(ets->tc_tsa));
+	memcpy(ets->prio_tc, params->ets_pri_tc_tbl, sizeof(ets->prio_tc));
+	kfree(dcbx_info);
+
+	return 0;
+}
+
+static int qed_dcbnl_ieee_getets(struct qed_dev *cdev, struct ieee_ets *ets)
+{
+	return qed_dcbnl_get_ieee_ets(cdev, ets, false);
+}
+
+static int qed_dcbnl_ieee_setets(struct qed_dev *cdev, struct ieee_ets *ets)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+	struct qed_dcbx_set dcbx_set;
+	struct qed_ptt *ptt;
+	int rc;
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
+	if (!dcbx_info)
+		return -EINVAL;
+
+	if (!dcbx_info->operational.ieee) {
+		DP_INFO(hwfn, "DCBX is not enabled/operational in IEEE mode\n");
+		kfree(dcbx_info);
+		return -EINVAL;
+	}
+
+	kfree(dcbx_info);
+
+	memset(&dcbx_set, 0, sizeof(dcbx_set));
+	rc = qed_dcbx_get_config_params(hwfn, &dcbx_set);
+	if (rc)
+		return -EINVAL;
+
+	dcbx_set.override_flags |= QED_DCBX_OVERRIDE_ETS_CFG;
+	dcbx_set.config.params.max_ets_tc = ets->ets_cap;
+	dcbx_set.config.params.ets_willing = ets->willing;
+	dcbx_set.config.params.ets_cbs = ets->cbs;
+	memcpy(dcbx_set.config.params.ets_tc_bw_tbl, ets->tc_tx_bw,
+	       sizeof(ets->tc_tx_bw));
+	memcpy(dcbx_set.config.params.ets_tc_tsa_tbl, ets->tc_tsa,
+	       sizeof(ets->tc_tsa));
+	memcpy(dcbx_set.config.params.ets_pri_tc_tbl, ets->prio_tc,
+	       sizeof(ets->prio_tc));
+
+	ptt = qed_ptt_acquire(hwfn);
+	if (!ptt)
+		return -EINVAL;
+
+	rc = qed_dcbx_config_params(hwfn, ptt, &dcbx_set, 0);
+
+	qed_ptt_release(hwfn, ptt);
+
+	return rc;
+}
+
+int qed_dcbnl_ieee_peer_getets(struct qed_dev *cdev, struct ieee_ets *ets)
+{
+	return qed_dcbnl_get_ieee_ets(cdev, ets, true);
+}
+
+int qed_dcbnl_ieee_peer_getpfc(struct qed_dev *cdev, struct ieee_pfc *pfc)
+{
+	return qed_dcbnl_get_ieee_pfc(cdev, pfc, true);
+}
+
+int qed_dcbnl_ieee_getapp(struct qed_dev *cdev, struct dcb_app *app)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+	struct qed_app_entry *entry;
+	bool ethtype;
+	u8 prio = 0;
+	int i;
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
+	if (!dcbx_info)
+		return -EINVAL;
+
+	if (!dcbx_info->operational.ieee) {
+		DP_INFO(hwfn, "DCBX is not enabled/operational in IEEE mode\n");
+		kfree(dcbx_info);
+		return -EINVAL;
+	}
+
+	/* ieee defines the selector field value for ethertype to be 1 */
+	ethtype = !!((app->selector - 1) == DCB_APP_IDTYPE_ETHTYPE);
+	for (i = 0; i < QED_DCBX_MAX_APP_PROTOCOL; i++) {
+		entry = &dcbx_info->operational.params.app_entry[i];
+		if ((entry->ethtype == ethtype) &&
+		    (entry->proto_id == app->protocol)) {
+			prio = entry->prio;
+			break;
+		}
+	}
+
+	if (i == QED_DCBX_MAX_APP_PROTOCOL) {
+		DP_ERR(cdev, "App entry (%d, %d) not found\n", app->selector,
+		       app->protocol);
+		kfree(dcbx_info);
+		return -EINVAL;
+	}
+
+	app->priority = ffs(prio) - 1;
+
+	kfree(dcbx_info);
+
+	return 0;
+}
+
+int qed_dcbnl_ieee_setapp(struct qed_dev *cdev, struct dcb_app *app)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_dcbx_get *dcbx_info;
+	struct qed_dcbx_set dcbx_set;
+	struct qed_app_entry *entry;
+	struct qed_ptt *ptt;
+	bool ethtype;
+	int rc, i;
+
+	if (app->priority < 0 || app->priority >= QED_MAX_PFC_PRIORITIES) {
+		DP_INFO(hwfn, "Invalid priority %d\n", app->priority);
+		return -EINVAL;
+	}
+
+	dcbx_info = qed_dcbnl_get_dcbx(hwfn, QED_DCBX_OPERATIONAL_MIB);
+	if (!dcbx_info)
+		return -EINVAL;
+
+	if (!dcbx_info->operational.ieee) {
+		DP_INFO(hwfn, "DCBX is not enabled/operational in IEEE mode\n");
+		kfree(dcbx_info);
+		return -EINVAL;
+	}
+
+	kfree(dcbx_info);
+
+	memset(&dcbx_set, 0, sizeof(dcbx_set));
+	rc = qed_dcbx_get_config_params(hwfn, &dcbx_set);
+	if (rc)
+		return -EINVAL;
+
+	/* ieee defines the selector field value for ethertype to be 1 */
+	ethtype = !!((app->selector - 1) == DCB_APP_IDTYPE_ETHTYPE);
+	for (i = 0; i < QED_DCBX_MAX_APP_PROTOCOL; i++) {
+		entry = &dcbx_set.config.params.app_entry[i];
+		if ((entry->ethtype == ethtype) &&
+		    (entry->proto_id == app->protocol))
+			break;
+		/* First empty slot */
+		if (!entry->proto_id)
+			break;
+	}
+
+	if (i == QED_DCBX_MAX_APP_PROTOCOL) {
+		DP_ERR(cdev, "App table is full\n");
+		return -EBUSY;
+	}
+
+	dcbx_set.override_flags |= QED_DCBX_OVERRIDE_APP_CFG;
+	dcbx_set.config.params.app_entry[i].ethtype = ethtype;
+	dcbx_set.config.params.app_entry[i].proto_id = app->protocol;
+	dcbx_set.config.params.app_entry[i].prio = BIT(app->priority);
+
+	ptt = qed_ptt_acquire(hwfn);
+	if (!ptt)
+		return -EBUSY;
+
+	rc = qed_dcbx_config_params(hwfn, ptt, &dcbx_set, 0);
+
+	qed_ptt_release(hwfn, ptt);
+
+	return rc;
+}
+
+const struct qed_eth_dcbnl_ops qed_dcbnl_ops_pass = {
+	.getstate = qed_dcbnl_getstate,
+	.setstate = qed_dcbnl_setstate,
+	.getpgtccfgtx = qed_dcbnl_getpgtccfgtx,
+	.getpgbwgcfgtx = qed_dcbnl_getpgbwgcfgtx,
+	.getpgtccfgrx = qed_dcbnl_getpgtccfgrx,
+	.getpgbwgcfgrx = qed_dcbnl_getpgbwgcfgrx,
+	.getpfccfg = qed_dcbnl_getpfccfg,
+	.setpfccfg = qed_dcbnl_setpfccfg,
+	.getcap = qed_dcbnl_getcap,
+	.getnumtcs = qed_dcbnl_getnumtcs,
+	.getpfcstate = qed_dcbnl_getpfcstate,
+	.getdcbx = qed_dcbnl_getdcbx,
+	.setpgtccfgtx = qed_dcbnl_setpgtccfgtx,
+	.setpgtccfgrx = qed_dcbnl_setpgtccfgrx,
+	.setpgbwgcfgtx = qed_dcbnl_setpgbwgcfgtx,
+	.setpgbwgcfgrx = qed_dcbnl_setpgbwgcfgrx,
+	.setall = qed_dcbnl_setall,
+	.setnumtcs = qed_dcbnl_setnumtcs,
+	.setpfcstate = qed_dcbnl_setpfcstate,
+	.setapp = qed_dcbnl_setapp,
+	.setdcbx = qed_dcbnl_setdcbx,
+	.setfeatcfg = qed_dcbnl_setfeatcfg,
+	.getfeatcfg = qed_dcbnl_getfeatcfg,
+	.getapp = qed_dcbnl_getapp,
+	.peer_getappinfo = qed_dcbnl_peer_getappinfo,
+	.peer_getapptable = qed_dcbnl_peer_getapptable,
+	.cee_peer_getpfc = qed_dcbnl_cee_peer_getpfc,
+	.cee_peer_getpg = qed_dcbnl_cee_peer_getpg,
+	.ieee_getpfc = qed_dcbnl_ieee_getpfc,
+	.ieee_setpfc = qed_dcbnl_ieee_setpfc,
+	.ieee_getets = qed_dcbnl_ieee_getets,
+	.ieee_setets = qed_dcbnl_ieee_setets,
+	.ieee_peer_getpfc = qed_dcbnl_ieee_peer_getpfc,
+	.ieee_peer_getets = qed_dcbnl_ieee_peer_getets,
+	.ieee_getapp = qed_dcbnl_ieee_getapp,
+	.ieee_setapp = qed_dcbnl_ieee_setapp,
+};
+
+#endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.h b/drivers/net/ethernet/qlogic/qed/qed_dcbx.h
index e7f834d..9ba6816 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.h
@@ -33,6 +33,24 @@
 	u8 tc;			/* Traffic Class */
 };
 
+#ifdef CONFIG_DCB
+#define QED_DCBX_VERSION_DISABLED       0
+#define QED_DCBX_VERSION_IEEE           1
+#define QED_DCBX_VERSION_CEE            2
+
+struct qed_dcbx_set {
+#define QED_DCBX_OVERRIDE_STATE	        BIT(0)
+#define QED_DCBX_OVERRIDE_PFC_CFG       BIT(1)
+#define QED_DCBX_OVERRIDE_ETS_CFG       BIT(2)
+#define QED_DCBX_OVERRIDE_APP_CFG       BIT(3)
+#define QED_DCBX_OVERRIDE_DSCP_CFG      BIT(4)
+	u32 override_flags;
+	bool enabled;
+	struct qed_dcbx_admin_params config;
+	u32 ver_num;
+};
+#endif
+
 struct qed_dcbx_results {
 	bool dcbx_enabled;
 	u8 pf_id;
@@ -55,6 +73,9 @@
 	struct qed_dcbx_results results;
 	struct dcbx_mib operational;
 	struct dcbx_mib remote;
+#ifdef CONFIG_DCB
+	struct qed_dcbx_set set;
+#endif
 	u8 dcbx_cap;
 };
 
@@ -67,6 +88,13 @@
 	u32 addr;
 };
 
+#ifdef CONFIG_DCB
+int qed_dcbx_get_config_params(struct qed_hwfn *, struct qed_dcbx_set *);
+
+int qed_dcbx_config_params(struct qed_hwfn *,
+			   struct qed_ptt *, struct qed_dcbx_set *, bool);
+#endif
+
 /* QED local interface routines */
 int
 qed_dcbx_mib_update_event(struct qed_hwfn *,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
index 72e0ad6..5927840 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
@@ -7244,6 +7244,9 @@
 #define DRV_MB_PARAM_CFG_VF_MSIX_VF_ID_MASK	0x000000FF
 #define DRV_MB_PARAM_CFG_VF_MSIX_SB_NUM_SHIFT	8
 #define DRV_MB_PARAM_CFG_VF_MSIX_SB_NUM_MASK	0x0000FF00
+#define DRV_MB_PARAM_LLDP_SEND_MASK		0x00000001
+#define DRV_MB_PARAM_LLDP_SEND_SHIFT		0
+
 
 #define DRV_MB_PARAM_SET_LED_MODE_OPER		0x0
 #define DRV_MB_PARAM_SET_LED_MODE_ON		0x1
diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c
index 2ee496e..d121a8b 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_l2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c
@@ -2166,11 +2166,18 @@
 extern const struct qed_iov_hv_ops qed_iov_ops_pass;
 #endif
 
+#ifdef CONFIG_DCB
+extern const struct qed_eth_dcbnl_ops qed_dcbnl_ops_pass;
+#endif
+
 static const struct qed_eth_ops qed_eth_ops_pass = {
 	.common = &qed_common_ops_pass,
 #ifdef CONFIG_QED_SRIOV
 	.iov = &qed_iov_ops_pass,
 #endif
+#ifdef CONFIG_DCB
+	.dcb = &qed_dcbnl_ops_pass,
+#endif
 	.fill_dev_info = &qed_fill_eth_dev_info,
 	.register_ops = &qed_register_eth_ops,
 	.check_mac = &qed_check_mac,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index f41f78d..6c4606b 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -1108,6 +1108,39 @@
 	return port_type;
 }
 
+static int qed_get_link_data(struct qed_hwfn *hwfn,
+			     struct qed_mcp_link_params *params,
+			     struct qed_mcp_link_state *link,
+			     struct qed_mcp_link_capabilities *link_caps)
+{
+	void *p;
+
+	if (!IS_PF(hwfn->cdev)) {
+		qed_vf_get_link_params(hwfn, params);
+		qed_vf_get_link_state(hwfn, link);
+		qed_vf_get_link_caps(hwfn, link_caps);
+
+		return 0;
+	}
+
+	p = qed_mcp_get_link_params(hwfn);
+	if (!p)
+		return -ENXIO;
+	memcpy(params, p, sizeof(*params));
+
+	p = qed_mcp_get_link_state(hwfn);
+	if (!p)
+		return -ENXIO;
+	memcpy(link, p, sizeof(*link));
+
+	p = qed_mcp_get_link_capabilities(hwfn);
+	if (!p)
+		return -ENXIO;
+	memcpy(link_caps, p, sizeof(*link_caps));
+
+	return 0;
+}
+
 static void qed_fill_link(struct qed_hwfn *hwfn,
 			  struct qed_link_output *if_link)
 {
@@ -1119,15 +1152,9 @@
 	memset(if_link, 0, sizeof(*if_link));
 
 	/* Prepare source inputs */
-	if (IS_PF(hwfn->cdev)) {
-		memcpy(&params, qed_mcp_get_link_params(hwfn), sizeof(params));
-		memcpy(&link, qed_mcp_get_link_state(hwfn), sizeof(link));
-		memcpy(&link_caps, qed_mcp_get_link_capabilities(hwfn),
-		       sizeof(link_caps));
-	} else {
-		qed_vf_get_link_params(hwfn, &params);
-		qed_vf_get_link_state(hwfn, &link);
-		qed_vf_get_link_caps(hwfn, &link_caps);
+	if (qed_get_link_data(hwfn, &params, &link, &link_caps)) {
+		dev_warn(&hwfn->cdev->pdev->dev, "no link data available\n");
+		return;
 	}
 
 	/* Set the link parameters to pass to protocol driver */
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
index eb75b82..4d161c75 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
@@ -21,18 +21,18 @@
 #include "qed_vf.h"
 
 /* IOV ramrods */
-static int qed_sp_vf_start(struct qed_hwfn *p_hwfn,
-			   u32 concrete_vfid, u16 opaque_vfid)
+static int qed_sp_vf_start(struct qed_hwfn *p_hwfn, struct qed_vf_info *p_vf)
 {
 	struct vf_start_ramrod_data *p_ramrod = NULL;
 	struct qed_spq_entry *p_ent = NULL;
 	struct qed_sp_init_data init_data;
 	int rc = -EINVAL;
+	u8 fp_minor;
 
 	/* Get SPQ entry */
 	memset(&init_data, 0, sizeof(init_data));
 	init_data.cid = qed_spq_get_cid(p_hwfn);
-	init_data.opaque_fid = opaque_vfid;
+	init_data.opaque_fid = p_vf->opaque_fid;
 	init_data.comp_mode = QED_SPQ_MODE_EBLOCK;
 
 	rc = qed_sp_init_request(p_hwfn, &p_ent,
@@ -43,12 +43,39 @@
 
 	p_ramrod = &p_ent->ramrod.vf_start;
 
-	p_ramrod->vf_id = GET_FIELD(concrete_vfid, PXP_CONCRETE_FID_VFID);
-	p_ramrod->opaque_fid = cpu_to_le16(opaque_vfid);
+	p_ramrod->vf_id = GET_FIELD(p_vf->concrete_fid, PXP_CONCRETE_FID_VFID);
+	p_ramrod->opaque_fid = cpu_to_le16(p_vf->opaque_fid);
 
-	p_ramrod->personality = PERSONALITY_ETH;
+	switch (p_hwfn->hw_info.personality) {
+	case QED_PCI_ETH:
+		p_ramrod->personality = PERSONALITY_ETH;
+		break;
+	case QED_PCI_ETH_ROCE:
+		p_ramrod->personality = PERSONALITY_RDMA_AND_ETH;
+		break;
+	default:
+		DP_NOTICE(p_hwfn, "Unknown VF personality %d\n",
+			  p_hwfn->hw_info.personality);
+		return -EINVAL;
+	}
+
+	fp_minor = p_vf->acquire.vfdev_info.eth_fp_hsi_minor;
+	if (fp_minor > ETH_HSI_VER_MINOR) {
+		DP_VERBOSE(p_hwfn,
+			   QED_MSG_IOV,
+			   "VF [%d] - Requested fp hsi %02x.%02x which is slightly newer than PF's %02x.%02x; Configuring PFs version\n",
+			   p_vf->abs_vf_id,
+			   ETH_HSI_VER_MAJOR,
+			   fp_minor, ETH_HSI_VER_MAJOR, ETH_HSI_VER_MINOR);
+		fp_minor = ETH_HSI_VER_MINOR;
+	}
+
 	p_ramrod->hsi_fp_ver.major_ver_arr[ETH_VER_KEY] = ETH_HSI_VER_MAJOR;
-	p_ramrod->hsi_fp_ver.minor_ver_arr[ETH_VER_KEY] = ETH_HSI_VER_MINOR;
+	p_ramrod->hsi_fp_ver.minor_ver_arr[ETH_VER_KEY] = fp_minor;
+
+	DP_VERBOSE(p_hwfn, QED_MSG_IOV,
+		   "VF[%d] - Starting using HSI %02x.%02x\n",
+		   p_vf->abs_vf_id, ETH_HSI_VER_MAJOR, fp_minor);
 
 	return qed_spq_post(p_hwfn, p_ent, NULL);
 }
@@ -119,6 +146,45 @@
 	return vf;
 }
 
+static bool qed_iov_validate_rxq(struct qed_hwfn *p_hwfn,
+				 struct qed_vf_info *p_vf, u16 rx_qid)
+{
+	if (rx_qid >= p_vf->num_rxqs)
+		DP_VERBOSE(p_hwfn,
+			   QED_MSG_IOV,
+			   "VF[0x%02x] - can't touch Rx queue[%04x]; Only 0x%04x are allocated\n",
+			   p_vf->abs_vf_id, rx_qid, p_vf->num_rxqs);
+	return rx_qid < p_vf->num_rxqs;
+}
+
+static bool qed_iov_validate_txq(struct qed_hwfn *p_hwfn,
+				 struct qed_vf_info *p_vf, u16 tx_qid)
+{
+	if (tx_qid >= p_vf->num_txqs)
+		DP_VERBOSE(p_hwfn,
+			   QED_MSG_IOV,
+			   "VF[0x%02x] - can't touch Tx queue[%04x]; Only 0x%04x are allocated\n",
+			   p_vf->abs_vf_id, tx_qid, p_vf->num_txqs);
+	return tx_qid < p_vf->num_txqs;
+}
+
+static bool qed_iov_validate_sb(struct qed_hwfn *p_hwfn,
+				struct qed_vf_info *p_vf, u16 sb_idx)
+{
+	int i;
+
+	for (i = 0; i < p_vf->num_sbs; i++)
+		if (p_vf->igu_sbs[i] == sb_idx)
+			return true;
+
+	DP_VERBOSE(p_hwfn,
+		   QED_MSG_IOV,
+		   "VF[0%02x] - tried using sb_idx %04x which doesn't exist as one of its 0x%02x SBs\n",
+		   p_vf->abs_vf_id, sb_idx, p_vf->num_sbs);
+
+	return false;
+}
+
 int qed_iov_post_vf_bulletin(struct qed_hwfn *p_hwfn,
 			     int vfid, struct qed_ptt *p_ptt)
 {
@@ -295,6 +361,9 @@
 		vf->opaque_fid = (p_hwfn->hw_info.opaque_fid & 0xff) |
 				 (vf->abs_vf_id << 8);
 		vf->vport_id = idx + 1;
+
+		vf->num_mac_filters = QED_ETH_VF_NUM_MAC_FILTERS;
+		vf->num_vlan_filters = QED_ETH_VF_NUM_VLAN_FILTERS;
 	}
 }
 
@@ -600,17 +669,6 @@
 	/* unpretend */
 	qed_fid_pretend(p_hwfn, p_ptt, (u16) p_hwfn->hw_info.concrete_fid);
 
-	if (vf->state != VF_STOPPED) {
-		DP_NOTICE(p_hwfn, "VF[%02x] is already started\n",
-			  vf->abs_vf_id);
-		return -EINVAL;
-	}
-
-	/* Start VF */
-	rc = qed_sp_vf_start(p_hwfn, vf->concrete_fid, vf->opaque_fid);
-	if (rc)
-		DP_NOTICE(p_hwfn, "Failed to start VF[%02x]\n", vf->abs_vf_id);
-
 	vf->state = VF_FREE;
 
 	return rc;
@@ -854,7 +912,6 @@
 	struct qed_mcp_link_params params;
 	struct qed_mcp_link_state link;
 	struct qed_vf_info *vf = NULL;
-	int rc = 0;
 
 	vf = qed_iov_get_vf_info(p_hwfn, rel_vf_id, true);
 	if (!vf) {
@@ -876,18 +933,8 @@
 	memcpy(&caps, qed_mcp_get_link_capabilities(p_hwfn), sizeof(caps));
 	qed_iov_set_link(p_hwfn, rel_vf_id, &params, &link, &caps);
 
-	if (vf->state != VF_STOPPED) {
-		/* Stopping the VF */
-		rc = qed_sp_vf_stop(p_hwfn, vf->concrete_fid, vf->opaque_fid);
-
-		if (rc != 0) {
-			DP_ERR(p_hwfn, "qed_sp_vf_stop returned error %d\n",
-			       rc);
-			return rc;
-		}
-
-		vf->state = VF_STOPPED;
-	}
+	/* Forget the VF's acquisition message */
+	memset(&vf->acquire, 0, sizeof(vf->acquire));
 
 	/* disablng interrupts and resetting permission table was done during
 	 * vf-close, however, we could get here without going through vf_close
@@ -1118,8 +1165,6 @@
 
 	p_vf->vf_bulletin = 0;
 	p_vf->vport_instance = 0;
-	p_vf->num_mac_filters = 0;
-	p_vf->num_vlan_filters = 0;
 	p_vf->configured_features = 0;
 
 	/* If VF previously requested less resources, go back to default */
@@ -1132,9 +1177,95 @@
 		p_vf->vf_queues[i].rxq_active = 0;
 
 	memset(&p_vf->shadow_config, 0, sizeof(p_vf->shadow_config));
+	memset(&p_vf->acquire, 0, sizeof(p_vf->acquire));
 	qed_iov_clean_vf(p_hwfn, p_vf->relative_vf_id);
 }
 
+static u8 qed_iov_vf_mbx_acquire_resc(struct qed_hwfn *p_hwfn,
+				      struct qed_ptt *p_ptt,
+				      struct qed_vf_info *p_vf,
+				      struct vf_pf_resc_request *p_req,
+				      struct pf_vf_resc *p_resp)
+{
+	int i;
+
+	/* Queue related information */
+	p_resp->num_rxqs = p_vf->num_rxqs;
+	p_resp->num_txqs = p_vf->num_txqs;
+	p_resp->num_sbs = p_vf->num_sbs;
+
+	for (i = 0; i < p_resp->num_sbs; i++) {
+		p_resp->hw_sbs[i].hw_sb_id = p_vf->igu_sbs[i];
+		p_resp->hw_sbs[i].sb_qid = 0;
+	}
+
+	/* These fields are filled for backward compatibility.
+	 * Unused by modern vfs.
+	 */
+	for (i = 0; i < p_resp->num_rxqs; i++) {
+		qed_fw_l2_queue(p_hwfn, p_vf->vf_queues[i].fw_rx_qid,
+				(u16 *)&p_resp->hw_qid[i]);
+		p_resp->cid[i] = p_vf->vf_queues[i].fw_cid;
+	}
+
+	/* Filter related information */
+	p_resp->num_mac_filters = min_t(u8, p_vf->num_mac_filters,
+					p_req->num_mac_filters);
+	p_resp->num_vlan_filters = min_t(u8, p_vf->num_vlan_filters,
+					 p_req->num_vlan_filters);
+
+	/* This isn't really needed/enforced, but some legacy VFs might depend
+	 * on the correct filling of this field.
+	 */
+	p_resp->num_mc_filters = QED_MAX_MC_ADDRS;
+
+	/* Validate sufficient resources for VF */
+	if (p_resp->num_rxqs < p_req->num_rxqs ||
+	    p_resp->num_txqs < p_req->num_txqs ||
+	    p_resp->num_sbs < p_req->num_sbs ||
+	    p_resp->num_mac_filters < p_req->num_mac_filters ||
+	    p_resp->num_vlan_filters < p_req->num_vlan_filters ||
+	    p_resp->num_mc_filters < p_req->num_mc_filters) {
+		DP_VERBOSE(p_hwfn,
+			   QED_MSG_IOV,
+			   "VF[%d] - Insufficient resources: rxq [%02x/%02x] txq [%02x/%02x] sbs [%02x/%02x] mac [%02x/%02x] vlan [%02x/%02x] mc [%02x/%02x]\n",
+			   p_vf->abs_vf_id,
+			   p_req->num_rxqs,
+			   p_resp->num_rxqs,
+			   p_req->num_rxqs,
+			   p_resp->num_txqs,
+			   p_req->num_sbs,
+			   p_resp->num_sbs,
+			   p_req->num_mac_filters,
+			   p_resp->num_mac_filters,
+			   p_req->num_vlan_filters,
+			   p_resp->num_vlan_filters,
+			   p_req->num_mc_filters, p_resp->num_mc_filters);
+		return PFVF_STATUS_NO_RESOURCE;
+	}
+
+	return PFVF_STATUS_SUCCESS;
+}
+
+static void qed_iov_vf_mbx_acquire_stats(struct qed_hwfn *p_hwfn,
+					 struct pfvf_stats_info *p_stats)
+{
+	p_stats->mstats.address = PXP_VF_BAR0_START_MSDM_ZONE_B +
+				  offsetof(struct mstorm_vf_zone,
+					   non_trigger.eth_queue_stat);
+	p_stats->mstats.len = sizeof(struct eth_mstorm_per_queue_stat);
+	p_stats->ustats.address = PXP_VF_BAR0_START_USDM_ZONE_B +
+				  offsetof(struct ustorm_vf_zone,
+					   non_trigger.eth_queue_stat);
+	p_stats->ustats.len = sizeof(struct eth_ustorm_per_queue_stat);
+	p_stats->pstats.address = PXP_VF_BAR0_START_PSDM_ZONE_B +
+				  offsetof(struct pstorm_vf_zone,
+					   non_trigger.eth_queue_stat);
+	p_stats->pstats.len = sizeof(struct eth_pstorm_per_queue_stat);
+	p_stats->tstats.address = 0;
+	p_stats->tstats.len = 0;
+}
+
 static void qed_iov_vf_mbx_acquire(struct qed_hwfn *p_hwfn,
 				   struct qed_ptt *p_ptt,
 				   struct qed_vf_info *vf)
@@ -1143,25 +1274,27 @@
 	struct pfvf_acquire_resp_tlv *resp = &mbx->reply_virt->acquire_resp;
 	struct pf_vf_pfdev_info *pfdev_info = &resp->pfdev_info;
 	struct vfpf_acquire_tlv *req = &mbx->req_virt->acquire;
-	u8 i, vfpf_status = PFVF_STATUS_SUCCESS;
+	u8 vfpf_status = PFVF_STATUS_NOT_SUPPORTED;
 	struct pf_vf_resc *resc = &resp->resc;
+	int rc;
+
+	memset(resp, 0, sizeof(*resp));
 
 	/* Validate FW compatibility */
-	if (req->vfdev_info.fw_major != FW_MAJOR_VERSION ||
-	    req->vfdev_info.fw_minor != FW_MINOR_VERSION ||
-	    req->vfdev_info.fw_revision != FW_REVISION_VERSION ||
-	    req->vfdev_info.fw_engineering != FW_ENGINEERING_VERSION) {
+	if (req->vfdev_info.eth_fp_hsi_major != ETH_HSI_VER_MAJOR) {
 		DP_INFO(p_hwfn,
-			"VF[%d] is running an incompatible driver [VF needs FW %02x:%02x:%02x:%02x but Hypervisor is using %02x:%02x:%02x:%02x]\n",
+			"VF[%d] needs fastpath HSI %02x.%02x, which is incompatible with loaded FW's faspath HSI %02x.%02x\n",
 			vf->abs_vf_id,
-			req->vfdev_info.fw_major,
-			req->vfdev_info.fw_minor,
-			req->vfdev_info.fw_revision,
-			req->vfdev_info.fw_engineering,
-			FW_MAJOR_VERSION,
-			FW_MINOR_VERSION,
-			FW_REVISION_VERSION, FW_ENGINEERING_VERSION);
-		vfpf_status = PFVF_STATUS_NOT_SUPPORTED;
+			req->vfdev_info.eth_fp_hsi_major,
+			req->vfdev_info.eth_fp_hsi_minor,
+			ETH_HSI_VER_MAJOR, ETH_HSI_VER_MINOR);
+
+		/* Write the PF version so that VF would know which version
+		 * is supported.
+		 */
+		pfdev_info->major_fp_hsi = ETH_HSI_VER_MAJOR;
+		pfdev_info->minor_fp_hsi = ETH_HSI_VER_MINOR;
+
 		goto out;
 	}
 
@@ -1171,16 +1304,13 @@
 		DP_INFO(p_hwfn,
 			"VF[%d] is running an old driver that doesn't support 100g\n",
 			vf->abs_vf_id);
-		vfpf_status = PFVF_STATUS_NOT_SUPPORTED;
 		goto out;
 	}
 
-	memset(resp, 0, sizeof(*resp));
+	/* Store the acquire message */
+	memcpy(&vf->acquire, req, sizeof(vf->acquire));
 
-	/* Fill in vf info stuff */
 	vf->opaque_fid = req->vfdev_info.opaque_fid;
-	vf->num_mac_filters = 1;
-	vf->num_vlan_filters = QED_ETH_VF_NUM_VLAN_FILTERS;
 
 	vf->vf_bulletin = req->bulletin_addr;
 	vf->bulletin.size = (vf->bulletin.size < req->bulletin_size) ?
@@ -1196,26 +1326,7 @@
 	if (p_hwfn->cdev->num_hwfns > 1)
 		pfdev_info->capabilities |= PFVF_ACQUIRE_CAP_100G;
 
-	pfdev_info->stats_info.mstats.address =
-	    PXP_VF_BAR0_START_MSDM_ZONE_B +
-	    offsetof(struct mstorm_vf_zone, non_trigger.eth_queue_stat);
-	pfdev_info->stats_info.mstats.len =
-	    sizeof(struct eth_mstorm_per_queue_stat);
-
-	pfdev_info->stats_info.ustats.address =
-	    PXP_VF_BAR0_START_USDM_ZONE_B +
-	    offsetof(struct ustorm_vf_zone, non_trigger.eth_queue_stat);
-	pfdev_info->stats_info.ustats.len =
-	    sizeof(struct eth_ustorm_per_queue_stat);
-
-	pfdev_info->stats_info.pstats.address =
-	    PXP_VF_BAR0_START_PSDM_ZONE_B +
-	    offsetof(struct pstorm_vf_zone, non_trigger.eth_queue_stat);
-	pfdev_info->stats_info.pstats.len =
-	    sizeof(struct eth_pstorm_per_queue_stat);
-
-	pfdev_info->stats_info.tstats.address = 0;
-	pfdev_info->stats_info.tstats.len = 0;
+	qed_iov_vf_mbx_acquire_stats(p_hwfn, &pfdev_info->stats_info);
 
 	memcpy(pfdev_info->port_mac, p_hwfn->hw_info.hw_mac_addr, ETH_ALEN);
 
@@ -1223,35 +1334,30 @@
 	pfdev_info->fw_minor = FW_MINOR_VERSION;
 	pfdev_info->fw_rev = FW_REVISION_VERSION;
 	pfdev_info->fw_eng = FW_ENGINEERING_VERSION;
+	pfdev_info->minor_fp_hsi = min_t(u8,
+					 ETH_HSI_VER_MINOR,
+					 req->vfdev_info.eth_fp_hsi_minor);
 	pfdev_info->os_type = VFPF_ACQUIRE_OS_LINUX;
 	qed_mcp_get_mfw_ver(p_hwfn, p_ptt, &pfdev_info->mfw_ver, NULL);
 
 	pfdev_info->dev_type = p_hwfn->cdev->type;
 	pfdev_info->chip_rev = p_hwfn->cdev->chip_rev;
 
-	resc->num_rxqs = vf->num_rxqs;
-	resc->num_txqs = vf->num_txqs;
-	resc->num_sbs = vf->num_sbs;
-	for (i = 0; i < resc->num_sbs; i++) {
-		resc->hw_sbs[i].hw_sb_id = vf->igu_sbs[i];
-		resc->hw_sbs[i].sb_qid = 0;
-	}
-
-	for (i = 0; i < resc->num_rxqs; i++) {
-		qed_fw_l2_queue(p_hwfn, vf->vf_queues[i].fw_rx_qid,
-				(u16 *)&resc->hw_qid[i]);
-		resc->cid[i] = vf->vf_queues[i].fw_cid;
-	}
-
-	resc->num_mac_filters = min_t(u8, vf->num_mac_filters,
-				      req->resc_request.num_mac_filters);
-	resc->num_vlan_filters = min_t(u8, vf->num_vlan_filters,
-				       req->resc_request.num_vlan_filters);
-
-	/* This isn't really required as VF isn't limited, but some VFs might
-	 * actually test this value, so need to provide it.
+	/* Fill resources available to VF; Make sure there are enough to
+	 * satisfy the VF's request.
 	 */
-	resc->num_mc_filters = req->resc_request.num_mc_filters;
+	vfpf_status = qed_iov_vf_mbx_acquire_resc(p_hwfn, p_ptt, vf,
+						  &req->resc_request, resc);
+	if (vfpf_status != PFVF_STATUS_SUCCESS)
+		goto out;
+
+	/* Start the VF in FW */
+	rc = qed_sp_vf_start(p_hwfn, vf);
+	if (rc) {
+		DP_NOTICE(p_hwfn, "Failed to start VF[%02x]\n", vf->abs_vf_id);
+		vfpf_status = PFVF_STATUS_FAILURE;
+		goto out;
+	}
 
 	/* Fill agreed size of bulletin board in response */
 	resp->bulletin_size = vf->bulletin.size;
@@ -1620,12 +1726,17 @@
 {
 	struct qed_queue_start_common_params params;
 	struct qed_iov_vf_mbx *mbx = &vf->vf_mbx;
-	u8 status = PFVF_STATUS_SUCCESS;
+	u8 status = PFVF_STATUS_NO_RESOURCE;
 	struct vfpf_start_rxq_tlv *req;
 	int rc;
 
 	memset(&params, 0, sizeof(params));
 	req = &mbx->req_virt->start_rxq;
+
+	if (!qed_iov_validate_rxq(p_hwfn, vf, req->rx_qid) ||
+	    !qed_iov_validate_sb(p_hwfn, vf, req->hw_sb))
+		goto out;
+
 	params.queue_id =  vf->vf_queues[req->rx_qid].fw_rx_qid;
 	params.vf_qid = req->rx_qid;
 	params.vport_id = vf->vport_id;
@@ -1643,22 +1754,48 @@
 	if (rc) {
 		status = PFVF_STATUS_FAILURE;
 	} else {
+		status = PFVF_STATUS_SUCCESS;
 		vf->vf_queues[req->rx_qid].rxq_active = true;
 		vf->num_active_rxqs++;
 	}
 
+out:
 	qed_iov_vf_mbx_start_rxq_resp(p_hwfn, p_ptt, vf, status);
 }
 
+static void qed_iov_vf_mbx_start_txq_resp(struct qed_hwfn *p_hwfn,
+					  struct qed_ptt *p_ptt,
+					  struct qed_vf_info *p_vf, u8 status)
+{
+	struct qed_iov_vf_mbx *mbx = &p_vf->vf_mbx;
+	struct pfvf_start_queue_resp_tlv *p_tlv;
+
+	mbx->offset = (u8 *)mbx->reply_virt;
+
+	p_tlv = qed_add_tlv(p_hwfn, &mbx->offset, CHANNEL_TLV_START_TXQ,
+			    sizeof(*p_tlv));
+	qed_add_tlv(p_hwfn, &mbx->offset, CHANNEL_TLV_LIST_END,
+		    sizeof(struct channel_list_end_tlv));
+
+	/* Update the TLV with the response */
+	if (status == PFVF_STATUS_SUCCESS) {
+		u16 qid = mbx->req_virt->start_txq.tx_qid;
+
+		p_tlv->offset = qed_db_addr(p_vf->vf_queues[qid].fw_cid,
+					    DQ_DEMS_LEGACY);
+	}
+
+	qed_iov_send_response(p_hwfn, p_ptt, p_vf, sizeof(*p_tlv), status);
+}
+
 static void qed_iov_vf_mbx_start_txq(struct qed_hwfn *p_hwfn,
 				     struct qed_ptt *p_ptt,
 				     struct qed_vf_info *vf)
 {
-	u16 length = sizeof(struct pfvf_def_resp_tlv);
 	struct qed_queue_start_common_params params;
 	struct qed_iov_vf_mbx *mbx = &vf->vf_mbx;
+	u8 status = PFVF_STATUS_NO_RESOURCE;
 	union qed_qm_pq_params pq_params;
-	u8 status = PFVF_STATUS_SUCCESS;
 	struct vfpf_start_txq_tlv *req;
 	int rc;
 
@@ -1669,6 +1806,11 @@
 
 	memset(&params, 0, sizeof(params));
 	req = &mbx->req_virt->start_txq;
+
+	if (!qed_iov_validate_txq(p_hwfn, vf, req->tx_qid) ||
+	    !qed_iov_validate_sb(p_hwfn, vf, req->hw_sb))
+		goto out;
+
 	params.queue_id =  vf->vf_queues[req->tx_qid].fw_tx_qid;
 	params.vport_id = vf->vport_id;
 	params.sb = req->hw_sb;
@@ -1682,13 +1824,15 @@
 					 req->pbl_addr,
 					 req->pbl_size, &pq_params);
 
-	if (rc)
+	if (rc) {
 		status = PFVF_STATUS_FAILURE;
-	else
+	} else {
+		status = PFVF_STATUS_SUCCESS;
 		vf->vf_queues[req->tx_qid].txq_active = true;
+	}
 
-	qed_iov_prepare_resp(p_hwfn, p_ptt, vf, CHANNEL_TLV_START_TXQ,
-			     length, status);
+out:
+	qed_iov_vf_mbx_start_txq_resp(p_hwfn, p_ptt, vf, status);
 }
 
 static int qed_iov_vf_stop_rxqs(struct qed_hwfn *p_hwfn,
@@ -2113,6 +2257,16 @@
 	u16 length;
 	int rc;
 
+	/* Valiate PF can send such a request */
+	if (!vf->vport_instance) {
+		DP_VERBOSE(p_hwfn,
+			   QED_MSG_IOV,
+			   "No VPORT instance available for VF[%d], failing vport update\n",
+			   vf->abs_vf_id);
+		status = PFVF_STATUS_FAILURE;
+		goto out;
+	}
+
 	memset(&params, 0, sizeof(params));
 	params.opaque_fid = vf->opaque_fid;
 	params.vport_id = vf->vport_id;
@@ -2155,15 +2309,12 @@
 	qed_iov_send_response(p_hwfn, p_ptt, vf, length, status);
 }
 
-static int qed_iov_vf_update_unicast_shadow(struct qed_hwfn *p_hwfn,
-					    struct qed_vf_info *p_vf,
-					    struct qed_filter_ucast *p_params)
+static int qed_iov_vf_update_vlan_shadow(struct qed_hwfn *p_hwfn,
+					 struct qed_vf_info *p_vf,
+					 struct qed_filter_ucast *p_params)
 {
 	int i;
 
-	if (p_params->type == QED_FILTER_MAC)
-		return 0;
-
 	/* First remove entries and then add new ones */
 	if (p_params->opcode == QED_FILTER_REMOVE) {
 		for (i = 0; i < QED_ETH_VF_NUM_VLAN_FILTERS + 1; i++)
@@ -2216,6 +2367,80 @@
 	return 0;
 }
 
+static int qed_iov_vf_update_mac_shadow(struct qed_hwfn *p_hwfn,
+					struct qed_vf_info *p_vf,
+					struct qed_filter_ucast *p_params)
+{
+	int i;
+
+	/* If we're in forced-mode, we don't allow any change */
+	if (p_vf->bulletin.p_virt->valid_bitmap & (1 << MAC_ADDR_FORCED))
+		return 0;
+
+	/* First remove entries and then add new ones */
+	if (p_params->opcode == QED_FILTER_REMOVE) {
+		for (i = 0; i < QED_ETH_VF_NUM_MAC_FILTERS; i++) {
+			if (ether_addr_equal(p_vf->shadow_config.macs[i],
+					     p_params->mac)) {
+				memset(p_vf->shadow_config.macs[i], 0,
+				       ETH_ALEN);
+				break;
+			}
+		}
+
+		if (i == QED_ETH_VF_NUM_MAC_FILTERS) {
+			DP_VERBOSE(p_hwfn, QED_MSG_IOV,
+				   "MAC isn't configured\n");
+			return -EINVAL;
+		}
+	} else if (p_params->opcode == QED_FILTER_REPLACE ||
+		   p_params->opcode == QED_FILTER_FLUSH) {
+		for (i = 0; i < QED_ETH_VF_NUM_MAC_FILTERS; i++)
+			memset(p_vf->shadow_config.macs[i], 0, ETH_ALEN);
+	}
+
+	/* List the new MAC address */
+	if (p_params->opcode != QED_FILTER_ADD &&
+	    p_params->opcode != QED_FILTER_REPLACE)
+		return 0;
+
+	for (i = 0; i < QED_ETH_VF_NUM_MAC_FILTERS; i++) {
+		if (is_zero_ether_addr(p_vf->shadow_config.macs[i])) {
+			ether_addr_copy(p_vf->shadow_config.macs[i],
+					p_params->mac);
+			DP_VERBOSE(p_hwfn, QED_MSG_IOV,
+				   "Added MAC at %d entry in shadow\n", i);
+			break;
+		}
+	}
+
+	if (i == QED_ETH_VF_NUM_MAC_FILTERS) {
+		DP_VERBOSE(p_hwfn, QED_MSG_IOV, "No available place for MAC\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int
+qed_iov_vf_update_unicast_shadow(struct qed_hwfn *p_hwfn,
+				 struct qed_vf_info *p_vf,
+				 struct qed_filter_ucast *p_params)
+{
+	int rc = 0;
+
+	if (p_params->type == QED_FILTER_MAC) {
+		rc = qed_iov_vf_update_mac_shadow(p_hwfn, p_vf, p_params);
+		if (rc)
+			return rc;
+	}
+
+	if (p_params->type == QED_FILTER_VLAN)
+		rc = qed_iov_vf_update_vlan_shadow(p_hwfn, p_vf, p_params);
+
+	return rc;
+}
+
 int qed_iov_chk_ucast(struct qed_hwfn *hwfn,
 		      int vfid, struct qed_filter_ucast *params)
 {
@@ -2360,11 +2585,27 @@
 				   struct qed_vf_info *p_vf)
 {
 	u16 length = sizeof(struct pfvf_def_resp_tlv);
+	u8 status = PFVF_STATUS_SUCCESS;
+	int rc = 0;
 
 	qed_iov_vf_cleanup(p_hwfn, p_vf);
 
+	if (p_vf->state != VF_STOPPED && p_vf->state != VF_FREE) {
+		/* Stopping the VF */
+		rc = qed_sp_vf_stop(p_hwfn, p_vf->concrete_fid,
+				    p_vf->opaque_fid);
+
+		if (rc) {
+			DP_ERR(p_hwfn, "qed_sp_vf_stop returned error %d\n",
+			       rc);
+			status = PFVF_STATUS_FAILURE;
+		}
+
+		p_vf->state = VF_STOPPED;
+	}
+
 	qed_iov_prepare_resp(p_hwfn, p_ptt, p_vf, CHANNEL_TLV_RELEASE,
-			     length, PFVF_STATUS_SUCCESS);
+			     length, status);
 }
 
 static int
@@ -2616,7 +2857,6 @@
 {
 	struct qed_iov_vf_mbx *mbx;
 	struct qed_vf_info *p_vf;
-	int i;
 
 	p_vf = qed_iov_get_vf_info(p_hwfn, (u16) vfid, true);
 	if (!p_vf)
@@ -2625,9 +2865,8 @@
 	mbx = &p_vf->vf_mbx;
 
 	/* qed_iov_process_mbx_request */
-	DP_VERBOSE(p_hwfn,
-		   QED_MSG_IOV,
-		   "qed_iov_process_mbx_req vfid %d\n", p_vf->abs_vf_id);
+	DP_VERBOSE(p_hwfn, QED_MSG_IOV,
+		   "VF[%02x]: Processing mailbox message\n", p_vf->abs_vf_id);
 
 	mbx->first_tlv = mbx->req_virt->first_tlv;
 
@@ -2681,15 +2920,28 @@
 		 * support them. Or this may be because someone wrote a crappy
 		 * VF driver and is sending garbage over the channel.
 		 */
-		DP_ERR(p_hwfn,
-		       "unknown TLV. type %d length %d. first 20 bytes of mailbox buffer:\n",
-		       mbx->first_tlv.tl.type, mbx->first_tlv.tl.length);
+		DP_NOTICE(p_hwfn,
+			  "VF[%02x]: unknown TLV. type %04x length %04x padding %08x reply address %llu\n",
+			  p_vf->abs_vf_id,
+			  mbx->first_tlv.tl.type,
+			  mbx->first_tlv.tl.length,
+			  mbx->first_tlv.padding, mbx->first_tlv.reply_address);
 
-		for (i = 0; i < 20; i++) {
+		/* Try replying in case reply address matches the acquisition's
+		 * posted address.
+		 */
+		if (p_vf->acquire.first_tlv.reply_address &&
+		    (mbx->first_tlv.reply_address ==
+		     p_vf->acquire.first_tlv.reply_address)) {
+			qed_iov_prepare_resp(p_hwfn, p_ptt, p_vf,
+					     mbx->first_tlv.tl.type,
+					     sizeof(struct pfvf_def_resp_tlv),
+					     PFVF_STATUS_NOT_SUPPORTED);
+		} else {
 			DP_VERBOSE(p_hwfn,
 				   QED_MSG_IOV,
-				   "%x ",
-				   mbx->req_virt->tlv_buf_size.tlv_buffer[i]);
+				   "VF[%02x]: Can't respond to TLV - no valid reply address\n",
+				   p_vf->abs_vf_id);
 		}
 	}
 }
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.h b/drivers/net/ethernet/qlogic/qed/qed_sriov.h
index c8667c6..0dd23e4 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.h
@@ -10,19 +10,23 @@
 #define _QED_SRIOV_H
 #include <linux/types.h>
 #include "qed_vf.h"
+
+#define QED_ETH_VF_NUM_MAC_FILTERS 1
+#define QED_ETH_VF_NUM_VLAN_FILTERS 2
 #define QED_VF_ARRAY_LENGTH (3)
 
+#ifdef CONFIG_QED_SRIOV
 #define IS_VF(cdev)             ((cdev)->b_is_vf)
 #define IS_PF(cdev)             (!((cdev)->b_is_vf))
-#ifdef CONFIG_QED_SRIOV
 #define IS_PF_SRIOV(p_hwfn)     (!!((p_hwfn)->cdev->p_iov_info))
 #else
+#define IS_VF(cdev)             (0)
+#define IS_PF(cdev)             (1)
 #define IS_PF_SRIOV(p_hwfn)     (0)
 #endif
 #define IS_PF_SRIOV_ALLOC(p_hwfn)       (!!((p_hwfn)->pf_iov_info))
 
 #define QED_MAX_VF_CHAINS_PER_PF 16
-#define QED_ETH_VF_NUM_VLAN_FILTERS 2
 
 #define QED_ETH_MAX_VF_NUM_VLAN_FILTERS	\
 	(MAX_NUM_VFS * QED_ETH_VF_NUM_VLAN_FILTERS)
@@ -118,6 +122,8 @@
 	/* Shadow copy of all guest vlans */
 	struct qed_vf_vlan_shadow vlans[QED_ETH_VF_NUM_VLAN_FILTERS + 1];
 
+	/* Shadow copy of all configured MACs; Empty if forcing MACs */
+	u8 macs[QED_ETH_VF_NUM_MAC_FILTERS][ETH_ALEN];
 	u8 inner_vlan_removal;
 };
 
@@ -131,6 +137,9 @@
 	struct qed_bulletin bulletin;
 	dma_addr_t vf_bulletin;
 
+	/* PF saves a copy of the last VF acquire message */
+	struct vfpf_acquire_tlv acquire;
+
 	u32 concrete_fid;
 	u16 opaque_fid;
 	u16 mtu;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c
index 72e69c0..9819230 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_vf.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c
@@ -117,36 +117,64 @@
 }
 
 #define VF_ACQUIRE_THRESH 3
-#define VF_ACQUIRE_MAC_FILTERS 1
+static void qed_vf_pf_acquire_reduce_resc(struct qed_hwfn *p_hwfn,
+					  struct vf_pf_resc_request *p_req,
+					  struct pf_vf_resc *p_resp)
+{
+	DP_VERBOSE(p_hwfn,
+		   QED_MSG_IOV,
+		   "PF unwilling to fullill resource request: rxq [%02x/%02x] txq [%02x/%02x] sbs [%02x/%02x] mac [%02x/%02x] vlan [%02x/%02x] mc [%02x/%02x]. Try PF recommended amount\n",
+		   p_req->num_rxqs,
+		   p_resp->num_rxqs,
+		   p_req->num_rxqs,
+		   p_resp->num_txqs,
+		   p_req->num_sbs,
+		   p_resp->num_sbs,
+		   p_req->num_mac_filters,
+		   p_resp->num_mac_filters,
+		   p_req->num_vlan_filters,
+		   p_resp->num_vlan_filters,
+		   p_req->num_mc_filters, p_resp->num_mc_filters);
+
+	/* humble our request */
+	p_req->num_txqs = p_resp->num_txqs;
+	p_req->num_rxqs = p_resp->num_rxqs;
+	p_req->num_sbs = p_resp->num_sbs;
+	p_req->num_mac_filters = p_resp->num_mac_filters;
+	p_req->num_vlan_filters = p_resp->num_vlan_filters;
+	p_req->num_mc_filters = p_resp->num_mc_filters;
+}
 
 static int qed_vf_pf_acquire(struct qed_hwfn *p_hwfn)
 {
 	struct qed_vf_iov *p_iov = p_hwfn->vf_iov_info;
 	struct pfvf_acquire_resp_tlv *resp = &p_iov->pf2vf_reply->acquire_resp;
 	struct pf_vf_pfdev_info *pfdev_info = &resp->pfdev_info;
-	u8 rx_count = 1, tx_count = 1, num_sbs = 1;
-	u8 num_mac = VF_ACQUIRE_MAC_FILTERS;
+	struct vf_pf_resc_request *p_resc;
 	bool resources_acquired = false;
 	struct vfpf_acquire_tlv *req;
 	int rc = 0, attempts = 0;
 
 	/* clear mailbox and prep first tlv */
 	req = qed_vf_pf_prep(p_hwfn, CHANNEL_TLV_ACQUIRE, sizeof(*req));
+	p_resc = &req->resc_request;
 
 	/* starting filling the request */
 	req->vfdev_info.opaque_fid = p_hwfn->hw_info.opaque_fid;
 
-	req->resc_request.num_rxqs = rx_count;
-	req->resc_request.num_txqs = tx_count;
-	req->resc_request.num_sbs = num_sbs;
-	req->resc_request.num_mac_filters = num_mac;
-	req->resc_request.num_vlan_filters = QED_ETH_VF_NUM_VLAN_FILTERS;
+	p_resc->num_rxqs = QED_MAX_VF_CHAINS_PER_PF;
+	p_resc->num_txqs = QED_MAX_VF_CHAINS_PER_PF;
+	p_resc->num_sbs = QED_MAX_VF_CHAINS_PER_PF;
+	p_resc->num_mac_filters = QED_ETH_VF_NUM_MAC_FILTERS;
+	p_resc->num_vlan_filters = QED_ETH_VF_NUM_VLAN_FILTERS;
 
 	req->vfdev_info.os_type = VFPF_ACQUIRE_OS_LINUX;
 	req->vfdev_info.fw_major = FW_MAJOR_VERSION;
 	req->vfdev_info.fw_minor = FW_MINOR_VERSION;
 	req->vfdev_info.fw_revision = FW_REVISION_VERSION;
 	req->vfdev_info.fw_engineering = FW_ENGINEERING_VERSION;
+	req->vfdev_info.eth_fp_hsi_major = ETH_HSI_VER_MAJOR;
+	req->vfdev_info.eth_fp_hsi_minor = ETH_HSI_VER_MINOR;
 
 	/* Fill capability field with any non-deprecated config we support */
 	req->vfdev_info.capabilities |= VFPF_ACQUIRE_CAP_100G;
@@ -185,21 +213,21 @@
 			resources_acquired = true;
 		} else if (resp->hdr.status == PFVF_STATUS_NO_RESOURCE &&
 			   attempts < VF_ACQUIRE_THRESH) {
-			DP_VERBOSE(p_hwfn,
-				   QED_MSG_IOV,
-				   "PF unwilling to fullfill resource request. Try PF recommended amount\n");
-
-			/* humble our request */
-			req->resc_request.num_txqs = resp->resc.num_txqs;
-			req->resc_request.num_rxqs = resp->resc.num_rxqs;
-			req->resc_request.num_sbs = resp->resc.num_sbs;
-			req->resc_request.num_mac_filters =
-			    resp->resc.num_mac_filters;
-			req->resc_request.num_vlan_filters =
-			    resp->resc.num_vlan_filters;
+			qed_vf_pf_acquire_reduce_resc(p_hwfn, p_resc,
+						      &resp->resc);
 
 			/* Clear response buffer */
 			memset(p_iov->pf2vf_reply, 0, sizeof(union pfvf_tlvs));
+		} else if ((resp->hdr.status == PFVF_STATUS_NOT_SUPPORTED) &&
+			   pfdev_info->major_fp_hsi &&
+			   (pfdev_info->major_fp_hsi != ETH_HSI_VER_MAJOR)) {
+			DP_NOTICE(p_hwfn,
+				  "PF uses an incompatible fastpath HSI %02x.%02x [VF requires %02x.%02x]. Please change to a VF driver using %02x.xx.\n",
+				  pfdev_info->major_fp_hsi,
+				  pfdev_info->minor_fp_hsi,
+				  ETH_HSI_VER_MAJOR,
+				  ETH_HSI_VER_MINOR, pfdev_info->major_fp_hsi);
+			return -EINVAL;
 		} else {
 			DP_ERR(p_hwfn,
 			       "PF returned error %d to VF acquisition request\n",
@@ -225,6 +253,13 @@
 		}
 	}
 
+	if (ETH_HSI_VER_MINOR &&
+	    (resp->pfdev_info.minor_fp_hsi < ETH_HSI_VER_MINOR)) {
+		DP_INFO(p_hwfn,
+			"PF is using older fastpath HSI; %02x.%02x is configured\n",
+			ETH_HSI_VER_MAJOR, resp->pfdev_info.minor_fp_hsi);
+	}
+
 	return 0;
 }
 
@@ -405,8 +440,8 @@
 			u16 pbl_size, void __iomem **pp_doorbell)
 {
 	struct qed_vf_iov *p_iov = p_hwfn->vf_iov_info;
+	struct pfvf_start_queue_resp_tlv *resp;
 	struct vfpf_start_txq_tlv *req;
-	struct pfvf_def_resp_tlv *resp;
 	int rc;
 
 	/* clear mailbox and prep first tlv */
@@ -424,20 +459,24 @@
 	qed_add_tlv(p_hwfn, &p_iov->offset,
 		    CHANNEL_TLV_LIST_END, sizeof(struct channel_list_end_tlv));
 
-	resp = &p_iov->pf2vf_reply->default_resp;
+	resp = &p_iov->pf2vf_reply->queue_start;
 	rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp));
 	if (rc)
-		return rc;
+		goto exit;
 
-	if (resp->hdr.status != PFVF_STATUS_SUCCESS)
-		return -EINVAL;
+	if (resp->hdr.status != PFVF_STATUS_SUCCESS) {
+		rc = -EINVAL;
+		goto exit;
+	}
 
 	if (pp_doorbell) {
-		u8 cid = p_iov->acquire_resp.resc.cid[tx_queue_id];
+		*pp_doorbell = (u8 __iomem *)p_hwfn->doorbells + resp->offset;
 
-		*pp_doorbell = (u8 __iomem *)p_hwfn->doorbells +
-					     qed_db_addr(cid, DQ_DEMS_LEGACY);
+		DP_VERBOSE(p_hwfn, QED_MSG_IOV,
+			   "Txq[0x%02x]: doorbell at %p [offset 0x%08x]\n",
+			   tx_queue_id, *pp_doorbell, resp->offset);
 	}
+exit:
 
 	return rc;
 }
diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.h b/drivers/net/ethernet/qlogic/qed/qed_vf.h
index b82fda9..b23ce58 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_vf.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_vf.h
@@ -96,7 +96,9 @@
 		u32 driver_version;
 		u16 opaque_fid;	/* ME register value */
 		u8 os_type;	/* VFPF_ACQUIRE_OS_* value */
-		u8 padding[5];
+		u8 eth_fp_hsi_major;
+		u8 eth_fp_hsi_minor;
+		u8 padding[3];
 	} vfdev_info;
 
 	struct vf_pf_resc_request resc_request;
@@ -171,7 +173,14 @@
 		struct pfvf_stats_info stats_info;
 
 		u8 port_mac[ETH_ALEN];
-		u8 padding2[2];
+
+		/* It's possible PF had to configure an older fastpath HSI
+		 * [in case VF is newer than PF]. This is communicated back
+		 * to the VF. It can also be used in case of error due to
+		 * non-matching versions to shed light in VF about failure.
+		 */
+		u8 major_fp_hsi;
+		u8 minor_fp_hsi;
 	} pfdev_info;
 
 	struct pf_vf_resc {
diff --git a/drivers/net/ethernet/qlogic/qede/Makefile b/drivers/net/ethernet/qlogic/qede/Makefile
index 06ff90d..74a4985 100644
--- a/drivers/net/ethernet/qlogic/qede/Makefile
+++ b/drivers/net/ethernet/qlogic/qede/Makefile
@@ -1,3 +1,4 @@
 obj-$(CONFIG_QEDE) := qede.o
 
 qede-y := qede_main.o qede_ethtool.o
+qede-$(CONFIG_DCB) += qede_dcbnl.o
diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index 47d6b22..1441c8f 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -304,6 +304,9 @@
 	u16 mtu;
 };
 
+#ifdef CONFIG_DCB
+void qede_set_dcbnl_ops(struct net_device *ndev);
+#endif
 void qede_config_debug(uint debug, u32 *p_dp_module, u8 *p_dp_level);
 void qede_set_ethtool_ops(struct net_device *netdev);
 void qede_reload(struct qede_dev *edev,
diff --git a/drivers/net/ethernet/qlogic/qede/qede_dcbnl.c b/drivers/net/ethernet/qlogic/qede/qede_dcbnl.c
new file mode 100644
index 0000000..03e8c02
--- /dev/null
+++ b/drivers/net/ethernet/qlogic/qede/qede_dcbnl.c
@@ -0,0 +1,348 @@
+/* QLogic qede NIC Driver
+* Copyright (c) 2015 QLogic Corporation
+*
+* This software is available under the terms of the GNU General Public License
+* (GPL) Version 2, available from the file COPYING in the main directory of
+* this source tree.
+*/
+
+#include <linux/types.h>
+#include <linux/netdevice.h>
+#include <linux/rtnetlink.h>
+#include <net/dcbnl.h>
+#include "qede.h"
+
+static u8 qede_dcbnl_getstate(struct net_device *netdev)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->getstate(edev->cdev);
+}
+
+static u8 qede_dcbnl_setstate(struct net_device *netdev, u8 state)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->setstate(edev->cdev, state);
+}
+
+static void qede_dcbnl_getpermhwaddr(struct net_device *netdev,
+				     u8 *perm_addr)
+{
+	memcpy(perm_addr, netdev->dev_addr, netdev->addr_len);
+}
+
+static void qede_dcbnl_getpgtccfgtx(struct net_device *netdev, int prio,
+				    u8 *prio_type, u8 *pgid, u8 *bw_pct,
+				    u8 *up_map)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	edev->ops->dcb->getpgtccfgtx(edev->cdev, prio, prio_type,
+				     pgid, bw_pct, up_map);
+}
+
+static void qede_dcbnl_getpgbwgcfgtx(struct net_device *netdev,
+				     int pgid, u8 *bw_pct)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	edev->ops->dcb->getpgbwgcfgtx(edev->cdev, pgid, bw_pct);
+}
+
+static void qede_dcbnl_getpgtccfgrx(struct net_device *netdev, int prio,
+				    u8 *prio_type, u8 *pgid, u8 *bw_pct,
+				    u8 *up_map)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	edev->ops->dcb->getpgtccfgrx(edev->cdev, prio, prio_type, pgid, bw_pct,
+				     up_map);
+}
+
+static void qede_dcbnl_getpgbwgcfgrx(struct net_device *netdev,
+				     int pgid, u8 *bw_pct)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	edev->ops->dcb->getpgbwgcfgrx(edev->cdev, pgid, bw_pct);
+}
+
+static void qede_dcbnl_getpfccfg(struct net_device *netdev, int prio,
+				 u8 *setting)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	edev->ops->dcb->getpfccfg(edev->cdev, prio, setting);
+}
+
+static void qede_dcbnl_setpfccfg(struct net_device *netdev, int prio,
+				 u8 setting)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	edev->ops->dcb->setpfccfg(edev->cdev, prio, setting);
+}
+
+static u8 qede_dcbnl_getcap(struct net_device *netdev, int capid, u8 *cap)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->getcap(edev->cdev, capid, cap);
+}
+
+static int qede_dcbnl_getnumtcs(struct net_device *netdev, int tcid, u8 *num)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->getnumtcs(edev->cdev, tcid, num);
+}
+
+static u8 qede_dcbnl_getpfcstate(struct net_device *netdev)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->getpfcstate(edev->cdev);
+}
+
+static int qede_dcbnl_getapp(struct net_device *netdev, u8 idtype, u16 id)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->getapp(edev->cdev, idtype, id);
+}
+
+static u8 qede_dcbnl_getdcbx(struct net_device *netdev)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->getdcbx(edev->cdev);
+}
+
+static void qede_dcbnl_setpgtccfgtx(struct net_device *netdev, int prio,
+				    u8 pri_type, u8 pgid, u8 bw_pct, u8 up_map)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->setpgtccfgtx(edev->cdev, prio, pri_type, pgid,
+					    bw_pct, up_map);
+}
+
+static void qede_dcbnl_setpgtccfgrx(struct net_device *netdev, int prio,
+				    u8 pri_type, u8 pgid, u8 bw_pct, u8 up_map)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->setpgtccfgrx(edev->cdev, prio, pri_type, pgid,
+					    bw_pct, up_map);
+}
+
+static void qede_dcbnl_setpgbwgcfgtx(struct net_device *netdev, int pgid,
+				     u8 bw_pct)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->setpgbwgcfgtx(edev->cdev, pgid, bw_pct);
+}
+
+static void qede_dcbnl_setpgbwgcfgrx(struct net_device *netdev, int pgid,
+				     u8 bw_pct)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->setpgbwgcfgrx(edev->cdev, pgid, bw_pct);
+}
+
+static u8 qede_dcbnl_setall(struct net_device *netdev)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->setall(edev->cdev);
+}
+
+static int qede_dcbnl_setnumtcs(struct net_device *netdev, int tcid, u8 num)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->setnumtcs(edev->cdev, tcid, num);
+}
+
+static void qede_dcbnl_setpfcstate(struct net_device *netdev, u8 state)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->setpfcstate(edev->cdev, state);
+}
+
+static int qede_dcbnl_setapp(struct net_device *netdev, u8 idtype, u16 idval,
+			     u8 up)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->setapp(edev->cdev, idtype, idval, up);
+}
+
+static u8 qede_dcbnl_setdcbx(struct net_device *netdev, u8 state)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->setdcbx(edev->cdev, state);
+}
+
+static u8 qede_dcbnl_getfeatcfg(struct net_device *netdev, int featid,
+				u8 *flags)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->getfeatcfg(edev->cdev, featid, flags);
+}
+
+static u8 qede_dcbnl_setfeatcfg(struct net_device *netdev, int featid, u8 flags)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->setfeatcfg(edev->cdev, featid, flags);
+}
+
+static int qede_dcbnl_peer_getappinfo(struct net_device *netdev,
+				      struct dcb_peer_app_info *info,
+				      u16 *count)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->peer_getappinfo(edev->cdev, info, count);
+}
+
+static int qede_dcbnl_peer_getapptable(struct net_device *netdev,
+				       struct dcb_app *app)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->peer_getapptable(edev->cdev, app);
+}
+
+static int qede_dcbnl_cee_peer_getpfc(struct net_device *netdev,
+				      struct cee_pfc *pfc)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->cee_peer_getpfc(edev->cdev, pfc);
+}
+
+static int qede_dcbnl_cee_peer_getpg(struct net_device *netdev,
+				     struct cee_pg *pg)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->cee_peer_getpg(edev->cdev, pg);
+}
+
+static int qede_dcbnl_ieee_getpfc(struct net_device *netdev,
+				  struct ieee_pfc *pfc)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->ieee_getpfc(edev->cdev, pfc);
+}
+
+static int qede_dcbnl_ieee_setpfc(struct net_device *netdev,
+				  struct ieee_pfc *pfc)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->ieee_setpfc(edev->cdev, pfc);
+}
+
+static int qede_dcbnl_ieee_getets(struct net_device *netdev,
+				  struct ieee_ets *ets)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->ieee_getets(edev->cdev, ets);
+}
+
+static int qede_dcbnl_ieee_setets(struct net_device *netdev,
+				  struct ieee_ets *ets)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->ieee_setets(edev->cdev, ets);
+}
+
+static int qede_dcbnl_ieee_getapp(struct net_device *netdev,
+				  struct dcb_app *app)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->ieee_getapp(edev->cdev, app);
+}
+
+static int qede_dcbnl_ieee_setapp(struct net_device *netdev,
+				  struct dcb_app *app)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->ieee_setapp(edev->cdev, app);
+}
+
+static int qede_dcbnl_ieee_peer_getpfc(struct net_device *netdev,
+				       struct ieee_pfc *pfc)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->ieee_peer_getpfc(edev->cdev, pfc);
+}
+
+static int qede_dcbnl_ieee_peer_getets(struct net_device *netdev,
+				       struct ieee_ets *ets)
+{
+	struct qede_dev *edev = netdev_priv(netdev);
+
+	return edev->ops->dcb->ieee_peer_getets(edev->cdev, ets);
+}
+
+static const struct dcbnl_rtnl_ops qede_dcbnl_ops = {
+	.ieee_getpfc = qede_dcbnl_ieee_getpfc,
+	.ieee_setpfc = qede_dcbnl_ieee_setpfc,
+	.ieee_getets = qede_dcbnl_ieee_getets,
+	.ieee_setets = qede_dcbnl_ieee_setets,
+	.ieee_getapp = qede_dcbnl_ieee_getapp,
+	.ieee_setapp = qede_dcbnl_ieee_setapp,
+	.getdcbx = qede_dcbnl_getdcbx,
+	.ieee_peer_getpfc = qede_dcbnl_ieee_peer_getpfc,
+	.ieee_peer_getets = qede_dcbnl_ieee_peer_getets,
+	.getstate = qede_dcbnl_getstate,
+	.setstate = qede_dcbnl_setstate,
+	.getpermhwaddr = qede_dcbnl_getpermhwaddr,
+	.getpgtccfgtx = qede_dcbnl_getpgtccfgtx,
+	.getpgbwgcfgtx = qede_dcbnl_getpgbwgcfgtx,
+	.getpgtccfgrx = qede_dcbnl_getpgtccfgrx,
+	.getpgbwgcfgrx = qede_dcbnl_getpgbwgcfgrx,
+	.getpfccfg = qede_dcbnl_getpfccfg,
+	.setpfccfg = qede_dcbnl_setpfccfg,
+	.getcap = qede_dcbnl_getcap,
+	.getnumtcs = qede_dcbnl_getnumtcs,
+	.getpfcstate = qede_dcbnl_getpfcstate,
+	.getapp = qede_dcbnl_getapp,
+	.getdcbx = qede_dcbnl_getdcbx,
+	.setpgtccfgtx = qede_dcbnl_setpgtccfgtx,
+	.setpgtccfgrx = qede_dcbnl_setpgtccfgrx,
+	.setpgbwgcfgtx = qede_dcbnl_setpgbwgcfgtx,
+	.setpgbwgcfgrx = qede_dcbnl_setpgbwgcfgrx,
+	.setall = qede_dcbnl_setall,
+	.setnumtcs = qede_dcbnl_setnumtcs,
+	.setpfcstate = qede_dcbnl_setpfcstate,
+	.setapp = qede_dcbnl_setapp,
+	.setdcbx = qede_dcbnl_setdcbx,
+	.setfeatcfg = qede_dcbnl_setfeatcfg,
+	.getfeatcfg = qede_dcbnl_getfeatcfg,
+	.peer_getappinfo = qede_dcbnl_peer_getappinfo,
+	.peer_getapptable = qede_dcbnl_peer_getapptable,
+	.cee_peer_getpfc = qede_dcbnl_cee_peer_getpfc,
+	.cee_peer_getpg = qede_dcbnl_cee_peer_getpg,
+};
+
+void qede_set_dcbnl_ops(struct net_device *dev)
+{
+	dev->dcbnl_ops = &qede_dcbnl_ops;
+}
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index edd2d90..2972742 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -24,12 +24,7 @@
 #include <linux/netdev_features.h>
 #include <linux/udp.h>
 #include <linux/tcp.h>
-#ifdef CONFIG_QEDE_VXLAN
-#include <net/vxlan.h>
-#endif
-#ifdef CONFIG_QEDE_GENEVE
-#include <net/geneve.h>
-#endif
+#include <net/udp_tunnel.h>
 #include <linux/ip.h>
 #include <net/ipv6.h>
 #include <net/tcp.h>
@@ -87,7 +82,9 @@
 	{PCI_VDEVICE(QLOGIC, PCI_DEVICE_ID_57980S_100), QEDE_PRIVATE_PF},
 	{PCI_VDEVICE(QLOGIC, PCI_DEVICE_ID_57980S_50), QEDE_PRIVATE_PF},
 	{PCI_VDEVICE(QLOGIC, PCI_DEVICE_ID_57980S_25), QEDE_PRIVATE_PF},
+#ifdef CONFIG_QED_SRIOV
 	{PCI_VDEVICE(QLOGIC, PCI_DEVICE_ID_57980S_IOV), QEDE_PRIVATE_VF},
+#endif
 	{ 0 }
 };
 
@@ -2110,75 +2107,75 @@
 	return 0;
 }
 
-#ifdef CONFIG_QEDE_VXLAN
-static void qede_add_vxlan_port(struct net_device *dev,
-				sa_family_t sa_family, __be16 port)
+static void qede_udp_tunnel_add(struct net_device *dev,
+				struct udp_tunnel_info *ti)
 {
 	struct qede_dev *edev = netdev_priv(dev);
-	u16 t_port = ntohs(port);
+	u16 t_port = ntohs(ti->port);
 
-	if (edev->vxlan_dst_port)
+	switch (ti->type) {
+	case UDP_TUNNEL_TYPE_VXLAN:
+		if (edev->vxlan_dst_port)
+			return;
+
+		edev->vxlan_dst_port = t_port;
+
+		DP_VERBOSE(edev, QED_MSG_DEBUG, "Added vxlan port=%d",
+			   t_port);
+
+		set_bit(QEDE_SP_VXLAN_PORT_CONFIG, &edev->sp_flags);
+		break;
+	case UDP_TUNNEL_TYPE_GENEVE:
+		if (edev->geneve_dst_port)
+			return;
+
+		edev->geneve_dst_port = t_port;
+
+		DP_VERBOSE(edev, QED_MSG_DEBUG, "Added geneve port=%d",
+			   t_port);
+		set_bit(QEDE_SP_GENEVE_PORT_CONFIG, &edev->sp_flags);
+		break;
+	default:
 		return;
+	}
 
-	edev->vxlan_dst_port = t_port;
-
-	DP_VERBOSE(edev, QED_MSG_DEBUG, "Added vxlan port=%d", t_port);
-
-	set_bit(QEDE_SP_VXLAN_PORT_CONFIG, &edev->sp_flags);
 	schedule_delayed_work(&edev->sp_task, 0);
 }
 
-static void qede_del_vxlan_port(struct net_device *dev,
-				sa_family_t sa_family, __be16 port)
+static void qede_udp_tunnel_del(struct net_device *dev,
+				struct udp_tunnel_info *ti)
 {
 	struct qede_dev *edev = netdev_priv(dev);
-	u16 t_port = ntohs(port);
+	u16 t_port = ntohs(ti->port);
 
-	if (t_port != edev->vxlan_dst_port)
+	switch (ti->type) {
+	case UDP_TUNNEL_TYPE_VXLAN:
+		if (t_port != edev->vxlan_dst_port)
+			return;
+
+		edev->vxlan_dst_port = 0;
+
+		DP_VERBOSE(edev, QED_MSG_DEBUG, "Deleted vxlan port=%d",
+			   t_port);
+
+		set_bit(QEDE_SP_VXLAN_PORT_CONFIG, &edev->sp_flags);
+		break;
+	case UDP_TUNNEL_TYPE_GENEVE:
+		if (t_port != edev->geneve_dst_port)
+			return;
+
+		edev->geneve_dst_port = 0;
+
+		DP_VERBOSE(edev, QED_MSG_DEBUG, "Deleted geneve port=%d",
+			   t_port);
+		set_bit(QEDE_SP_GENEVE_PORT_CONFIG, &edev->sp_flags);
+		break;
+	default:
 		return;
+	}
 
-	edev->vxlan_dst_port = 0;
-
-	DP_VERBOSE(edev, QED_MSG_DEBUG, "Deleted vxlan port=%d", t_port);
-
-	set_bit(QEDE_SP_VXLAN_PORT_CONFIG, &edev->sp_flags);
 	schedule_delayed_work(&edev->sp_task, 0);
 }
-#endif
-
-#ifdef CONFIG_QEDE_GENEVE
-static void qede_add_geneve_port(struct net_device *dev,
-				 sa_family_t sa_family, __be16 port)
-{
-	struct qede_dev *edev = netdev_priv(dev);
-	u16 t_port = ntohs(port);
-
-	if (edev->geneve_dst_port)
-		return;
-
-	edev->geneve_dst_port = t_port;
-
-	DP_VERBOSE(edev, QED_MSG_DEBUG, "Added geneve port=%d", t_port);
-	set_bit(QEDE_SP_GENEVE_PORT_CONFIG, &edev->sp_flags);
-	schedule_delayed_work(&edev->sp_task, 0);
-}
-
-static void qede_del_geneve_port(struct net_device *dev,
-				 sa_family_t sa_family, __be16 port)
-{
-	struct qede_dev *edev = netdev_priv(dev);
-	u16 t_port = ntohs(port);
-
-	if (t_port != edev->geneve_dst_port)
-		return;
-
-	edev->geneve_dst_port = 0;
-
-	DP_VERBOSE(edev, QED_MSG_DEBUG, "Deleted geneve port=%d", t_port);
-	set_bit(QEDE_SP_GENEVE_PORT_CONFIG, &edev->sp_flags);
-	schedule_delayed_work(&edev->sp_task, 0);
-}
-#endif
 
 static const struct net_device_ops qede_netdev_ops = {
 	.ndo_open = qede_open,
@@ -2202,14 +2199,8 @@
 	.ndo_get_vf_config = qede_get_vf_config,
 	.ndo_set_vf_rate = qede_set_vf_rate,
 #endif
-#ifdef CONFIG_QEDE_VXLAN
-	.ndo_add_vxlan_port = qede_add_vxlan_port,
-	.ndo_del_vxlan_port = qede_del_vxlan_port,
-#endif
-#ifdef CONFIG_QEDE_GENEVE
-	.ndo_add_geneve_port = qede_add_geneve_port,
-	.ndo_del_geneve_port = qede_del_geneve_port,
-#endif
+	.ndo_udp_tunnel_add = qede_udp_tunnel_add,
+	.ndo_udp_tunnel_del = qede_udp_tunnel_del,
 };
 
 /* -------------------------------------------------------------------------
@@ -2499,6 +2490,10 @@
 
 	edev->ops->register_ops(cdev, &qede_ll_ops, edev);
 
+#ifdef CONFIG_DCB
+	qede_set_dcbnl_ops(edev->ndev);
+#endif
+
 	INIT_DELAYED_WORK(&edev->sp_task, qede_sp_task);
 	mutex_init(&edev->qede_lock);
 
@@ -3573,12 +3568,8 @@
 	if (rc)
 		return rc;
 
-#ifdef CONFIG_QEDE_VXLAN
-	vxlan_get_rx_port(ndev);
-#endif
-#ifdef CONFIG_QEDE_GENEVE
-	geneve_get_rx_port(ndev);
-#endif
+	udp_tunnel_get_rx_info(ndev);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
index caf6ddb..fd973f4 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
@@ -1026,10 +1026,8 @@
 #define QLCNIC_HAS_PHYS_PORT_ID		0x40000
 #define QLCNIC_TSS_RSS			0x80000
 
-#ifdef CONFIG_QLCNIC_VXLAN
 #define QLCNIC_ADD_VXLAN_PORT		0x100000
 #define QLCNIC_DEL_VXLAN_PORT		0x200000
-#endif
 
 #define QLCNIC_VLAN_FILTERING		0x800000
 
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
index f9640d5ce..bdbcd2b 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
@@ -2159,7 +2159,6 @@
 	struct qlcnic_cmd_args cmd;
 	u32 mac_low, mac_high;
 
-	function = 0;
 	err = qlcnic_alloc_mbx_args(&cmd, adapter, QLCNIC_CMD_MAC_ADDRESS);
 	if (err)
 		return err;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
index bf89216..a496390 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
@@ -1020,7 +1020,6 @@
 	return 0;
 }
 
-#ifdef CONFIG_QLCNIC_VXLAN
 #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
@@ -1089,14 +1088,12 @@
 
 	return ret;
 }
-#endif
 
 static void qlcnic_83xx_periodic_tasks(struct qlcnic_adapter *adapter)
 {
 	if (adapter->fhash.fnum)
 		qlcnic_prune_lb_filters(adapter);
 
-#ifdef CONFIG_QLCNIC_VXLAN
 	if (adapter->flags & QLCNIC_ADD_VXLAN_PORT) {
 		if (qlcnic_set_vxlan_port(adapter))
 			return;
@@ -1112,7 +1109,6 @@
 		adapter->ahw->vxlan_port = 0;
 		adapter->flags &= ~QLCNIC_DEL_VXLAN_PORT;
 	}
-#endif
 }
 
 /**
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index 1c29105..3ebef27 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -16,9 +16,7 @@
 #include <linux/aer.h>
 #include <linux/log2.h>
 #include <linux/pci.h>
-#ifdef CONFIG_QLCNIC_VXLAN
 #include <net/vxlan.h>
-#endif
 
 #include "qlcnic.h"
 #include "qlcnic_sriov.h"
@@ -474,13 +472,15 @@
 	return 0;
 }
 
-#ifdef CONFIG_QLCNIC_VXLAN
 static void qlcnic_add_vxlan_port(struct net_device *netdev,
-				  sa_family_t sa_family, __be16 port)
+				  struct udp_tunnel_info *ti)
 {
 	struct qlcnic_adapter *adapter = netdev_priv(netdev);
 	struct qlcnic_hardware_context *ahw = adapter->ahw;
 
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
+		return;
+
 	/* Adapter supports only one VXLAN port. Use very first port
 	 * for enabling offload
 	 */
@@ -488,23 +488,26 @@
 		return;
 	if (!ahw->vxlan_port_count) {
 		ahw->vxlan_port_count = 1;
-		ahw->vxlan_port = ntohs(port);
+		ahw->vxlan_port = ntohs(ti->port);
 		adapter->flags |= QLCNIC_ADD_VXLAN_PORT;
 		return;
 	}
-	if (ahw->vxlan_port == ntohs(port))
+	if (ahw->vxlan_port == ntohs(ti->port))
 		ahw->vxlan_port_count++;
 
 }
 
 static void qlcnic_del_vxlan_port(struct net_device *netdev,
-				  sa_family_t sa_family, __be16 port)
+				  struct udp_tunnel_info *ti)
 {
 	struct qlcnic_adapter *adapter = netdev_priv(netdev);
 	struct qlcnic_hardware_context *ahw = adapter->ahw;
 
+	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
+		return;
+
 	if (!qlcnic_encap_rx_offload(adapter) || !ahw->vxlan_port_count ||
-	    (ahw->vxlan_port != ntohs(port)))
+	    (ahw->vxlan_port != ntohs(ti->port)))
 		return;
 
 	ahw->vxlan_port_count--;
@@ -519,7 +522,6 @@
 	features = vlan_features_check(skb, features);
 	return vxlan_features_check(skb, features);
 }
-#endif
 
 static const struct net_device_ops qlcnic_netdev_ops = {
 	.ndo_open	   = qlcnic_open,
@@ -539,11 +541,9 @@
 	.ndo_fdb_del		= qlcnic_fdb_del,
 	.ndo_fdb_dump		= qlcnic_fdb_dump,
 	.ndo_get_phys_port_id	= qlcnic_get_phys_port_id,
-#ifdef CONFIG_QLCNIC_VXLAN
-	.ndo_add_vxlan_port	= qlcnic_add_vxlan_port,
-	.ndo_del_vxlan_port	= qlcnic_del_vxlan_port,
+	.ndo_udp_tunnel_add	= qlcnic_add_vxlan_port,
+	.ndo_udp_tunnel_del	= qlcnic_del_vxlan_port,
 	.ndo_features_check	= qlcnic_features_check,
-#endif
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = qlcnic_poll_controller,
 #endif
@@ -2015,10 +2015,8 @@
 
 	qlcnic_create_sysfs_entries(adapter);
 
-#ifdef CONFIG_QLCNIC_VXLAN
 	if (qlcnic_encap_rx_offload(adapter))
-		vxlan_get_rx_port(netdev);
-#endif
+		udp_tunnel_get_rx_info(netdev);
 
 	adapter->is_up = QLCNIC_ADAPTER_UP_MAGIC;
 	return 0;
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 1f30912..f658fee 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -50,14 +50,34 @@
 #define HUNT_FILTER_TBL_ROWS 8192
 
 #define EFX_EF10_FILTER_ID_INVALID 0xffff
+
+#define EFX_EF10_FILTER_DEV_UC_MAX	32
+#define EFX_EF10_FILTER_DEV_MC_MAX	256
+
+/* VLAN list entry */
+struct efx_ef10_vlan {
+	struct list_head list;
+	u16 vid;
+};
+
+/* Per-VLAN filters information */
+struct efx_ef10_filter_vlan {
+	struct list_head list;
+	u16 vid;
+	u16 uc[EFX_EF10_FILTER_DEV_UC_MAX];
+	u16 mc[EFX_EF10_FILTER_DEV_MC_MAX];
+	u16 ucdef;
+	u16 bcast;
+	u16 mcdef;
+};
+
 struct efx_ef10_dev_addr {
 	u8 addr[ETH_ALEN];
-	u16 id;
 };
 
 struct efx_ef10_filter_table {
-/* The RX match field masks supported by this fw & hw, in order of priority */
-	enum efx_filter_match_flags rx_match_flags[
+/* The MCDI match masks supported by this fw & hw, in order of priority */
+	u32 rx_match_mcdi_flags[
 		MC_CMD_GET_PARSER_DISP_INFO_OUT_SUPPORTED_MATCHES_MAXNUM];
 	unsigned int rx_match_count;
 
@@ -73,16 +93,16 @@
 	} *entry;
 	wait_queue_head_t waitq;
 /* Shadow of net_device address lists, guarded by mac_lock */
-#define EFX_EF10_FILTER_DEV_UC_MAX	32
-#define EFX_EF10_FILTER_DEV_MC_MAX	256
 	struct efx_ef10_dev_addr dev_uc_list[EFX_EF10_FILTER_DEV_UC_MAX];
 	struct efx_ef10_dev_addr dev_mc_list[EFX_EF10_FILTER_DEV_MC_MAX];
 	int dev_uc_count;
 	int dev_mc_count;
-/* Indices (like efx_ef10_dev_addr.id) for promisc/allmulti filters */
-	u16 ucdef_id;
-	u16 bcast_id;
-	u16 mcdef_id;
+	bool uc_promisc;
+	bool mc_promisc;
+/* Whether in multicast promiscuous mode when last changed */
+	bool mc_promisc_last;
+	bool vlan_filter;
+	struct list_head vlan_list;
 };
 
 /* An arbitrary search limit for the software hash table */
@@ -90,6 +110,10 @@
 
 static void efx_ef10_rx_free_indir_table(struct efx_nic *efx);
 static void efx_ef10_filter_table_remove(struct efx_nic *efx);
+static int efx_ef10_filter_add_vlan(struct efx_nic *efx, u16 vid);
+static void efx_ef10_filter_del_vlan_internal(struct efx_nic *efx,
+					      struct efx_ef10_filter_vlan *vlan);
+static void efx_ef10_filter_del_vlan(struct efx_nic *efx, u16 vid);
 
 static int efx_ef10_get_warm_boot_count(struct efx_nic *efx)
 {
@@ -275,6 +299,131 @@
 		       ? 1 : 0);
 }
 
+static struct efx_ef10_vlan *efx_ef10_find_vlan(struct efx_nic *efx, u16 vid)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	struct efx_ef10_vlan *vlan;
+
+	WARN_ON(!mutex_is_locked(&nic_data->vlan_lock));
+
+	list_for_each_entry(vlan, &nic_data->vlan_list, list) {
+		if (vlan->vid == vid)
+			return vlan;
+	}
+
+	return NULL;
+}
+
+static int efx_ef10_add_vlan(struct efx_nic *efx, u16 vid)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	struct efx_ef10_vlan *vlan;
+	int rc;
+
+	mutex_lock(&nic_data->vlan_lock);
+
+	vlan = efx_ef10_find_vlan(efx, vid);
+	if (vlan) {
+		/* We add VID 0 on init. 8021q adds it on module init
+		 * for all interfaces with VLAN filtring feature.
+		 */
+		if (vid == 0)
+			goto done_unlock;
+		netif_warn(efx, drv, efx->net_dev,
+			   "VLAN %u already added\n", vid);
+		rc = -EALREADY;
+		goto fail_exist;
+	}
+
+	rc = -ENOMEM;
+	vlan = kzalloc(sizeof(*vlan), GFP_KERNEL);
+	if (!vlan)
+		goto fail_alloc;
+
+	vlan->vid = vid;
+
+	list_add_tail(&vlan->list, &nic_data->vlan_list);
+
+	if (efx->filter_state) {
+		mutex_lock(&efx->mac_lock);
+		down_write(&efx->filter_sem);
+		rc = efx_ef10_filter_add_vlan(efx, vlan->vid);
+		up_write(&efx->filter_sem);
+		mutex_unlock(&efx->mac_lock);
+		if (rc)
+			goto fail_filter_add_vlan;
+	}
+
+done_unlock:
+	mutex_unlock(&nic_data->vlan_lock);
+	return 0;
+
+fail_filter_add_vlan:
+	list_del(&vlan->list);
+	kfree(vlan);
+fail_alloc:
+fail_exist:
+	mutex_unlock(&nic_data->vlan_lock);
+	return rc;
+}
+
+static void efx_ef10_del_vlan_internal(struct efx_nic *efx,
+				       struct efx_ef10_vlan *vlan)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+
+	WARN_ON(!mutex_is_locked(&nic_data->vlan_lock));
+
+	if (efx->filter_state) {
+		down_write(&efx->filter_sem);
+		efx_ef10_filter_del_vlan(efx, vlan->vid);
+		up_write(&efx->filter_sem);
+	}
+
+	list_del(&vlan->list);
+	kfree(vlan);
+}
+
+static int efx_ef10_del_vlan(struct efx_nic *efx, u16 vid)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	struct efx_ef10_vlan *vlan;
+	int rc = 0;
+
+	/* 8021q removes VID 0 on module unload for all interfaces
+	 * with VLAN filtering feature. We need to keep it to receive
+	 * untagged traffic.
+	 */
+	if (vid == 0)
+		return 0;
+
+	mutex_lock(&nic_data->vlan_lock);
+
+	vlan = efx_ef10_find_vlan(efx, vid);
+	if (!vlan) {
+		netif_err(efx, drv, efx->net_dev,
+			  "VLAN %u to be deleted not found\n", vid);
+		rc = -ENOENT;
+	} else {
+		efx_ef10_del_vlan_internal(efx, vlan);
+	}
+
+	mutex_unlock(&nic_data->vlan_lock);
+
+	return rc;
+}
+
+static void efx_ef10_cleanup_vlans(struct efx_nic *efx)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	struct efx_ef10_vlan *vlan, *next_vlan;
+
+	mutex_lock(&nic_data->vlan_lock);
+	list_for_each_entry_safe(vlan, next_vlan, &nic_data->vlan_list, list)
+		efx_ef10_del_vlan_internal(efx, vlan);
+	mutex_unlock(&nic_data->vlan_lock);
+}
+
 static DEVICE_ATTR(link_control_flag, 0444, efx_ef10_show_link_control_flag,
 		   NULL);
 static DEVICE_ATTR(primary_flag, 0444, efx_ef10_show_primary_flag, NULL);
@@ -421,8 +570,30 @@
 #endif
 		ether_addr_copy(nic_data->port_id, efx->net_dev->perm_addr);
 
+	INIT_LIST_HEAD(&nic_data->vlan_list);
+	mutex_init(&nic_data->vlan_lock);
+
+	/* Add unspecified VID to support VLAN filtering being disabled */
+	rc = efx_ef10_add_vlan(efx, EFX_FILTER_VID_UNSPEC);
+	if (rc)
+		goto fail_add_vid_unspec;
+
+	/* If VLAN filtering is enabled, we need VID 0 to get untagged
+	 * traffic.  It is added automatically if 8021q module is loaded,
+	 * but we can't rely on it since module may be not loaded.
+	 */
+	rc = efx_ef10_add_vlan(efx, 0);
+	if (rc)
+		goto fail_add_vid_0;
+
 	return 0;
 
+fail_add_vid_0:
+	efx_ef10_cleanup_vlans(efx);
+fail_add_vid_unspec:
+	mutex_destroy(&nic_data->vlan_lock);
+	efx_ptp_remove(efx);
+	efx_mcdi_mon_remove(efx);
 fail5:
 	device_remove_file(&efx->pci_dev->dev, &dev_attr_primary_flag);
 fail4:
@@ -676,6 +847,9 @@
 	}
 #endif
 
+	efx_ef10_cleanup_vlans(efx);
+	mutex_destroy(&nic_data->vlan_lock);
+
 	efx_ptp_remove(efx);
 
 	efx_mcdi_mon_remove(efx);
@@ -704,6 +878,45 @@
 	return efx_ef10_probe(efx);
 }
 
+int efx_ef10_vadaptor_query(struct efx_nic *efx, unsigned int port_id,
+			    u32 *port_flags, u32 *vadaptor_flags,
+			    unsigned int *vlan_tags)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_VADAPTOR_QUERY_IN_LEN);
+	MCDI_DECLARE_BUF(outbuf, MC_CMD_VADAPTOR_QUERY_OUT_LEN);
+	size_t outlen;
+	int rc;
+
+	if (nic_data->datapath_caps &
+	    (1 << MC_CMD_GET_CAPABILITIES_OUT_VADAPTOR_QUERY_LBN)) {
+		MCDI_SET_DWORD(inbuf, VADAPTOR_QUERY_IN_UPSTREAM_PORT_ID,
+			       port_id);
+
+		rc = efx_mcdi_rpc(efx, MC_CMD_VADAPTOR_QUERY, inbuf, sizeof(inbuf),
+				  outbuf, sizeof(outbuf), &outlen);
+		if (rc)
+			return rc;
+
+		if (outlen < sizeof(outbuf)) {
+			rc = -EIO;
+			return rc;
+		}
+	}
+
+	if (port_flags)
+		*port_flags = MCDI_DWORD(outbuf, VADAPTOR_QUERY_OUT_PORT_FLAGS);
+	if (vadaptor_flags)
+		*vadaptor_flags =
+			MCDI_DWORD(outbuf, VADAPTOR_QUERY_OUT_VADAPTOR_FLAGS);
+	if (vlan_tags)
+		*vlan_tags =
+			MCDI_DWORD(outbuf,
+				   VADAPTOR_QUERY_OUT_NUM_AVAILABLE_VLAN_TAGS);
+
+	return 0;
+}
+
 int efx_ef10_vadaptor_alloc(struct efx_nic *efx, unsigned int port_id)
 {
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_VADAPTOR_ALLOC_IN_LEN);
@@ -3040,15 +3253,55 @@
 	return rc;
 }
 
-static int efx_ef10_filter_rx_match_pri(struct efx_ef10_filter_table *table,
-					enum efx_filter_match_flags match_flags)
+static u32 efx_ef10_filter_mcdi_flags_from_spec(const struct efx_filter_spec *spec)
 {
+	unsigned int match_flags = spec->match_flags;
+	u32 mcdi_flags = 0;
+
+	if (match_flags & EFX_FILTER_MATCH_LOC_MAC_IG) {
+		match_flags &= ~EFX_FILTER_MATCH_LOC_MAC_IG;
+		mcdi_flags |=
+			is_multicast_ether_addr(spec->loc_mac) ?
+			(1 << MC_CMD_FILTER_OP_IN_MATCH_UNKNOWN_MCAST_DST_LBN) :
+			(1 << MC_CMD_FILTER_OP_IN_MATCH_UNKNOWN_UCAST_DST_LBN);
+	}
+
+#define MAP_FILTER_TO_MCDI_FLAG(gen_flag, mcdi_field) {			\
+		unsigned int old_match_flags = match_flags;		\
+		match_flags &= ~EFX_FILTER_MATCH_ ## gen_flag;		\
+		if (match_flags != old_match_flags)			\
+			mcdi_flags |=					\
+				(1 << MC_CMD_FILTER_OP_IN_MATCH_ ##	\
+				 mcdi_field ## _LBN);			\
+	}
+	MAP_FILTER_TO_MCDI_FLAG(REM_HOST, SRC_IP);
+	MAP_FILTER_TO_MCDI_FLAG(LOC_HOST, DST_IP);
+	MAP_FILTER_TO_MCDI_FLAG(REM_MAC, SRC_MAC);
+	MAP_FILTER_TO_MCDI_FLAG(REM_PORT, SRC_PORT);
+	MAP_FILTER_TO_MCDI_FLAG(LOC_MAC, DST_MAC);
+	MAP_FILTER_TO_MCDI_FLAG(LOC_PORT, DST_PORT);
+	MAP_FILTER_TO_MCDI_FLAG(ETHER_TYPE, ETHER_TYPE);
+	MAP_FILTER_TO_MCDI_FLAG(INNER_VID, INNER_VLAN);
+	MAP_FILTER_TO_MCDI_FLAG(OUTER_VID, OUTER_VLAN);
+	MAP_FILTER_TO_MCDI_FLAG(IP_PROTO, IP_PROTO);
+#undef MAP_FILTER_TO_MCDI_FLAG
+
+	/* Did we map them all? */
+	WARN_ON_ONCE(match_flags);
+
+	return mcdi_flags;
+}
+
+static int efx_ef10_filter_pri(struct efx_ef10_filter_table *table,
+			       const struct efx_filter_spec *spec)
+{
+	u32 mcdi_flags = efx_ef10_filter_mcdi_flags_from_spec(spec);
 	unsigned int match_pri;
 
 	for (match_pri = 0;
 	     match_pri < table->rx_match_count;
 	     match_pri++)
-		if (table->rx_match_flags[match_pri] == match_flags)
+		if (table->rx_match_mcdi_flags[match_pri] == mcdi_flags)
 			return match_pri;
 
 	return -EPROTONOSUPPORT;
@@ -3074,7 +3327,7 @@
 	    EFX_FILTER_FLAG_RX)
 		return -EINVAL;
 
-	rc = efx_ef10_filter_rx_match_pri(table, spec->match_flags);
+	rc = efx_ef10_filter_pri(table, spec);
 	if (rc < 0)
 		return rc;
 	match_pri = rc;
@@ -3313,7 +3566,7 @@
 	spec = efx_ef10_filter_entry_spec(table, filter_idx);
 	if (!spec ||
 	    (!by_index &&
-	     efx_ef10_filter_rx_match_pri(table, spec->match_flags) !=
+	     efx_ef10_filter_pri(table, spec) !=
 	     filter_id / HUNT_FILTER_TBL_ROWS)) {
 		rc = -ENOENT;
 		goto out_unlock;
@@ -3394,12 +3647,13 @@
 	return filter_id % HUNT_FILTER_TBL_ROWS;
 }
 
-static int efx_ef10_filter_remove_unsafe(struct efx_nic *efx,
-					 enum efx_filter_priority priority,
-					 u32 filter_id)
+static void efx_ef10_filter_remove_unsafe(struct efx_nic *efx,
+					  enum efx_filter_priority priority,
+					  u32 filter_id)
 {
-	return efx_ef10_filter_remove_internal(efx, 1U << priority,
-					       filter_id, true);
+	if (filter_id == EFX_EF10_FILTER_ID_INVALID)
+		return;
+	efx_ef10_filter_remove_internal(efx, 1U << priority, filter_id, true);
 }
 
 static int efx_ef10_filter_get_safe(struct efx_nic *efx,
@@ -3414,7 +3668,7 @@
 	spin_lock_bh(&efx->filter_lock);
 	saved_spec = efx_ef10_filter_entry_spec(table, filter_idx);
 	if (saved_spec && saved_spec->priority == priority &&
-	    efx_ef10_filter_rx_match_pri(table, saved_spec->match_flags) ==
+	    efx_ef10_filter_pri(table, saved_spec) ==
 	    filter_id / HUNT_FILTER_TBL_ROWS) {
 		*spec = *saved_spec;
 		rc = 0;
@@ -3487,8 +3741,7 @@
 				count = -EMSGSIZE;
 				break;
 			}
-			buf[count++] = (efx_ef10_filter_rx_match_pri(
-						table, spec->match_flags) *
+			buf[count++] = (efx_ef10_filter_pri(table, spec) *
 					HUNT_FILTER_TBL_ROWS +
 					filter_idx);
 		}
@@ -3724,15 +3977,58 @@
 	return match_flags;
 }
 
+static void efx_ef10_filter_cleanup_vlans(struct efx_nic *efx)
+{
+	struct efx_ef10_filter_table *table = efx->filter_state;
+	struct efx_ef10_filter_vlan *vlan, *next_vlan;
+
+	/* See comment in efx_ef10_filter_table_remove() */
+	if (!efx_rwsem_assert_write_locked(&efx->filter_sem))
+		return;
+
+	if (!table)
+		return;
+
+	list_for_each_entry_safe(vlan, next_vlan, &table->vlan_list, list)
+		efx_ef10_filter_del_vlan_internal(efx, vlan);
+}
+
+static bool efx_ef10_filter_match_supported(struct efx_ef10_filter_table *table,
+					    enum efx_filter_match_flags match_flags)
+{
+	unsigned int match_pri;
+	int mf;
+
+	for (match_pri = 0;
+	     match_pri < table->rx_match_count;
+	     match_pri++) {
+		mf = efx_ef10_filter_match_flags_from_mcdi(
+				table->rx_match_mcdi_flags[match_pri]);
+		if (mf == match_flags)
+			return true;
+	}
+
+	return false;
+}
+
 static int efx_ef10_filter_table_probe(struct efx_nic *efx)
 {
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_GET_PARSER_DISP_INFO_IN_LEN);
 	MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_PARSER_DISP_INFO_OUT_LENMAX);
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	struct net_device *net_dev = efx->net_dev;
 	unsigned int pd_match_pri, pd_match_count;
 	struct efx_ef10_filter_table *table;
+	struct efx_ef10_vlan *vlan;
 	size_t outlen;
 	int rc;
 
+	if (!efx_rwsem_assert_write_locked(&efx->filter_sem))
+		return -EINVAL;
+
+	if (efx->filter_state) /* already probed */
+		return 0;
+
 	table = kzalloc(sizeof(*table), GFP_KERNEL);
 	if (!table)
 		return -ENOMEM;
@@ -3765,24 +4061,48 @@
 				  "%s: fw flags %#x pri %u supported as driver flags %#x pri %u\n",
 				  __func__, mcdi_flags, pd_match_pri,
 				  rc, table->rx_match_count);
-			table->rx_match_flags[table->rx_match_count++] = rc;
+			table->rx_match_mcdi_flags[table->rx_match_count] = mcdi_flags;
+			table->rx_match_count++;
 		}
 	}
 
+	if ((efx_supported_features(efx) & NETIF_F_HW_VLAN_CTAG_FILTER) &&
+	    !(efx_ef10_filter_match_supported(table,
+		(EFX_FILTER_MATCH_OUTER_VID | EFX_FILTER_MATCH_LOC_MAC)) &&
+	      efx_ef10_filter_match_supported(table,
+		(EFX_FILTER_MATCH_OUTER_VID | EFX_FILTER_MATCH_LOC_MAC_IG)))) {
+		netif_info(efx, probe, net_dev,
+			   "VLAN filters are not supported in this firmware variant\n");
+		net_dev->features &= ~NETIF_F_HW_VLAN_CTAG_FILTER;
+		efx->fixed_features &= ~NETIF_F_HW_VLAN_CTAG_FILTER;
+		net_dev->hw_features &= ~NETIF_F_HW_VLAN_CTAG_FILTER;
+	}
+
 	table->entry = vzalloc(HUNT_FILTER_TBL_ROWS * sizeof(*table->entry));
 	if (!table->entry) {
 		rc = -ENOMEM;
 		goto fail;
 	}
 
-	table->ucdef_id = EFX_EF10_FILTER_ID_INVALID;
-	table->bcast_id = EFX_EF10_FILTER_ID_INVALID;
-	table->mcdef_id = EFX_EF10_FILTER_ID_INVALID;
+	table->mc_promisc_last = false;
+	table->vlan_filter =
+		!!(efx->net_dev->features & NETIF_F_HW_VLAN_CTAG_FILTER);
+	INIT_LIST_HEAD(&table->vlan_list);
 
 	efx->filter_state = table;
 	init_waitqueue_head(&table->waitq);
+
+	list_for_each_entry(vlan, &nic_data->vlan_list, list) {
+		rc = efx_ef10_filter_add_vlan(efx, vlan->vid);
+		if (rc)
+			goto fail_add_vlan;
+	}
+
 	return 0;
 
+fail_add_vlan:
+	efx_ef10_filter_cleanup_vlans(efx);
+	efx->filter_state = NULL;
 fail:
 	kfree(table);
 	return rc;
@@ -3843,7 +4163,6 @@
 		nic_data->must_restore_filters = false;
 }
 
-/* Caller must hold efx->filter_sem for write */
 static void efx_ef10_filter_table_remove(struct efx_nic *efx)
 {
 	struct efx_ef10_filter_table *table = efx->filter_state;
@@ -3852,7 +4171,17 @@
 	unsigned int filter_idx;
 	int rc;
 
+	efx_ef10_filter_cleanup_vlans(efx);
 	efx->filter_state = NULL;
+	/* If we were called without locking, then it's not safe to free
+	 * the table as others might be using it.  So we just WARN, leak
+	 * the memory, and potentially get an inconsistent filter table
+	 * state.
+	 * This should never actually happen.
+	 */
+	if (!efx_rwsem_assert_write_locked(&efx->filter_sem))
+		return;
+
 	if (!table)
 		return;
 
@@ -3880,37 +4209,54 @@
 	kfree(table);
 }
 
-#define EFX_EF10_FILTER_DO_MARK_OLD(id) \
-	if (id != EFX_EF10_FILTER_ID_INVALID) { \
-		filter_idx = efx_ef10_filter_get_unsafe_id(efx, id); \
-		if (!table->entry[filter_idx].spec) \
-			netif_dbg(efx, drv, efx->net_dev, \
-				  "%s: marked null spec old %04x:%04x\n", \
-				  __func__, id, filter_idx); \
-		table->entry[filter_idx].spec |= EFX_EF10_FILTER_FLAG_AUTO_OLD;\
+static void efx_ef10_filter_mark_one_old(struct efx_nic *efx, uint16_t *id)
+{
+	struct efx_ef10_filter_table *table = efx->filter_state;
+	unsigned int filter_idx;
+
+	if (*id != EFX_EF10_FILTER_ID_INVALID) {
+		filter_idx = efx_ef10_filter_get_unsafe_id(efx, *id);
+		if (!table->entry[filter_idx].spec)
+			netif_dbg(efx, drv, efx->net_dev,
+				  "marked null spec old %04x:%04x\n", *id,
+				  filter_idx);
+		table->entry[filter_idx].spec |= EFX_EF10_FILTER_FLAG_AUTO_OLD;
+		*id = EFX_EF10_FILTER_ID_INVALID;
 	}
+}
+
+/* Mark old per-VLAN filters that may need to be removed */
+static void _efx_ef10_filter_vlan_mark_old(struct efx_nic *efx,
+					   struct efx_ef10_filter_vlan *vlan)
+{
+	struct efx_ef10_filter_table *table = efx->filter_state;
+	unsigned int i;
+
+	for (i = 0; i < table->dev_uc_count; i++)
+		efx_ef10_filter_mark_one_old(efx, &vlan->uc[i]);
+	for (i = 0; i < table->dev_mc_count; i++)
+		efx_ef10_filter_mark_one_old(efx, &vlan->mc[i]);
+	efx_ef10_filter_mark_one_old(efx, &vlan->ucdef);
+	efx_ef10_filter_mark_one_old(efx, &vlan->bcast);
+	efx_ef10_filter_mark_one_old(efx, &vlan->mcdef);
+}
+
+/* Mark old filters that may need to be removed.
+ * Caller must hold efx->filter_sem for read if race against
+ * efx_ef10_filter_table_remove() is possible
+ */
 static void efx_ef10_filter_mark_old(struct efx_nic *efx)
 {
 	struct efx_ef10_filter_table *table = efx->filter_state;
-	unsigned int filter_idx, i;
+	struct efx_ef10_filter_vlan *vlan;
 
-	if (!table)
-		return;
-
-	/* Mark old filters that may need to be removed */
 	spin_lock_bh(&efx->filter_lock);
-	for (i = 0; i < table->dev_uc_count; i++)
-		EFX_EF10_FILTER_DO_MARK_OLD(table->dev_uc_list[i].id);
-	for (i = 0; i < table->dev_mc_count; i++)
-		EFX_EF10_FILTER_DO_MARK_OLD(table->dev_mc_list[i].id);
-	EFX_EF10_FILTER_DO_MARK_OLD(table->ucdef_id);
-	EFX_EF10_FILTER_DO_MARK_OLD(table->bcast_id);
-	EFX_EF10_FILTER_DO_MARK_OLD(table->mcdef_id);
+	list_for_each_entry(vlan, &table->vlan_list, list)
+		_efx_ef10_filter_vlan_mark_old(efx, vlan);
 	spin_unlock_bh(&efx->filter_lock);
 }
-#undef EFX_EF10_FILTER_DO_MARK_OLD
 
-static void efx_ef10_filter_uc_addr_list(struct efx_nic *efx, bool *promisc)
+static void efx_ef10_filter_uc_addr_list(struct efx_nic *efx)
 {
 	struct efx_ef10_filter_table *table = efx->filter_state;
 	struct net_device *net_dev = efx->net_dev;
@@ -3918,45 +4264,38 @@
 	int addr_count;
 	unsigned int i;
 
-	table->ucdef_id = EFX_EF10_FILTER_ID_INVALID;
 	addr_count = netdev_uc_count(net_dev);
-	if (net_dev->flags & IFF_PROMISC)
-		*promisc = true;
+	table->uc_promisc = !!(net_dev->flags & IFF_PROMISC);
 	table->dev_uc_count = 1 + addr_count;
 	ether_addr_copy(table->dev_uc_list[0].addr, net_dev->dev_addr);
 	i = 1;
 	netdev_for_each_uc_addr(uc, net_dev) {
 		if (i >= EFX_EF10_FILTER_DEV_UC_MAX) {
-			*promisc = true;
+			table->uc_promisc = true;
 			break;
 		}
 		ether_addr_copy(table->dev_uc_list[i].addr, uc->addr);
-		table->dev_uc_list[i].id = EFX_EF10_FILTER_ID_INVALID;
 		i++;
 	}
 }
 
-static void efx_ef10_filter_mc_addr_list(struct efx_nic *efx, bool *promisc)
+static void efx_ef10_filter_mc_addr_list(struct efx_nic *efx)
 {
 	struct efx_ef10_filter_table *table = efx->filter_state;
 	struct net_device *net_dev = efx->net_dev;
 	struct netdev_hw_addr *mc;
 	unsigned int i, addr_count;
 
-	table->mcdef_id = EFX_EF10_FILTER_ID_INVALID;
-	table->bcast_id = EFX_EF10_FILTER_ID_INVALID;
-	if (net_dev->flags & (IFF_PROMISC | IFF_ALLMULTI))
-		*promisc = true;
+	table->mc_promisc = !!(net_dev->flags & (IFF_PROMISC | IFF_ALLMULTI));
 
 	addr_count = netdev_mc_count(net_dev);
 	i = 0;
 	netdev_for_each_mc_addr(mc, net_dev) {
 		if (i >= EFX_EF10_FILTER_DEV_MC_MAX) {
-			*promisc = true;
+			table->mc_promisc = true;
 			break;
 		}
 		ether_addr_copy(table->dev_mc_list[i].addr, mc->addr);
-		table->dev_mc_list[i].id = EFX_EF10_FILTER_ID_INVALID;
 		i++;
 	}
 
@@ -3964,7 +4303,8 @@
 }
 
 static int efx_ef10_filter_insert_addr_list(struct efx_nic *efx,
-					     bool multicast, bool rollback)
+					    struct efx_ef10_filter_vlan *vlan,
+					    bool multicast, bool rollback)
 {
 	struct efx_ef10_filter_table *table = efx->filter_state;
 	struct efx_ef10_dev_addr *addr_list;
@@ -3973,14 +4313,17 @@
 	u8 baddr[ETH_ALEN];
 	unsigned int i, j;
 	int addr_count;
+	u16 *ids;
 	int rc;
 
 	if (multicast) {
 		addr_list = table->dev_mc_list;
 		addr_count = table->dev_mc_count;
+		ids = vlan->mc;
 	} else {
 		addr_list = table->dev_uc_list;
 		addr_count = table->dev_uc_count;
+		ids = vlan->uc;
 	}
 
 	filter_flags = efx_rss_enabled(efx) ? EFX_FILTER_FLAG_RX_RSS : 0;
@@ -3988,8 +4331,7 @@
 	/* Insert/renew filters */
 	for (i = 0; i < addr_count; i++) {
 		efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, filter_flags, 0);
-		efx_filter_set_eth_local(&spec, EFX_FILTER_VID_UNSPEC,
-					 addr_list[i].addr);
+		efx_filter_set_eth_local(&spec, vlan->vid, addr_list[i].addr);
 		rc = efx_ef10_filter_insert(efx, &spec, true);
 		if (rc < 0) {
 			if (rollback) {
@@ -3998,12 +4340,10 @@
 					   rc);
 				/* Fall back to promiscuous */
 				for (j = 0; j < i; j++) {
-					if (addr_list[j].id == EFX_EF10_FILTER_ID_INVALID)
-						continue;
 					efx_ef10_filter_remove_unsafe(
 						efx, EFX_FILTER_PRI_AUTO,
-						addr_list[j].id);
-					addr_list[j].id = EFX_EF10_FILTER_ID_INVALID;
+						ids[j]);
+					ids[j] = EFX_EF10_FILTER_ID_INVALID;
 				}
 				return rc;
 			} else {
@@ -4011,40 +4351,40 @@
 				rc = EFX_EF10_FILTER_ID_INVALID;
 			}
 		}
-		addr_list[i].id = efx_ef10_filter_get_unsafe_id(efx, rc);
+		ids[i] = efx_ef10_filter_get_unsafe_id(efx, rc);
 	}
 
 	if (multicast && rollback) {
 		/* Also need an Ethernet broadcast filter */
 		efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, filter_flags, 0);
 		eth_broadcast_addr(baddr);
-		efx_filter_set_eth_local(&spec, EFX_FILTER_VID_UNSPEC, baddr);
+		efx_filter_set_eth_local(&spec, vlan->vid, baddr);
 		rc = efx_ef10_filter_insert(efx, &spec, true);
 		if (rc < 0) {
 			netif_warn(efx, drv, efx->net_dev,
 				   "Broadcast filter insert failed rc=%d\n", rc);
 			/* Fall back to promiscuous */
 			for (j = 0; j < i; j++) {
-				if (addr_list[j].id == EFX_EF10_FILTER_ID_INVALID)
-					continue;
 				efx_ef10_filter_remove_unsafe(
 					efx, EFX_FILTER_PRI_AUTO,
-					addr_list[j].id);
-				addr_list[j].id = EFX_EF10_FILTER_ID_INVALID;
+					ids[j]);
+				ids[j] = EFX_EF10_FILTER_ID_INVALID;
 			}
 			return rc;
 		} else {
-			table->bcast_id = efx_ef10_filter_get_unsafe_id(efx, rc);
+			EFX_WARN_ON_PARANOID(vlan->bcast !=
+					     EFX_EF10_FILTER_ID_INVALID);
+			vlan->bcast = efx_ef10_filter_get_unsafe_id(efx, rc);
 		}
 	}
 
 	return 0;
 }
 
-static int efx_ef10_filter_insert_def(struct efx_nic *efx, bool multicast,
-				      bool rollback)
+static int efx_ef10_filter_insert_def(struct efx_nic *efx,
+				      struct efx_ef10_filter_vlan *vlan,
+				      bool multicast, bool rollback)
 {
-	struct efx_ef10_filter_table *table = efx->filter_state;
 	struct efx_ef10_nic_data *nic_data = efx->nic_data;
 	enum efx_filter_flags filter_flags;
 	struct efx_filter_spec spec;
@@ -4060,6 +4400,9 @@
 	else
 		efx_filter_set_uc_def(&spec);
 
+	if (vlan->vid != EFX_FILTER_VID_UNSPEC)
+		efx_filter_set_eth_local(&spec, vlan->vid, NULL);
+
 	rc = efx_ef10_filter_insert(efx, &spec, true);
 	if (rc < 0) {
 		netif_printk(efx, drv, rc == -EPERM ? KERN_DEBUG : KERN_WARNING,
@@ -4067,14 +4410,14 @@
 			     "%scast mismatch filter insert failed rc=%d\n",
 			     multicast ? "Multi" : "Uni", rc);
 	} else if (multicast) {
-		table->mcdef_id = efx_ef10_filter_get_unsafe_id(efx, rc);
+		EFX_WARN_ON_PARANOID(vlan->mcdef != EFX_EF10_FILTER_ID_INVALID);
+		vlan->mcdef = efx_ef10_filter_get_unsafe_id(efx, rc);
 		if (!nic_data->workaround_26807) {
 			/* Also need an Ethernet broadcast filter */
 			efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO,
 					   filter_flags, 0);
 			eth_broadcast_addr(baddr);
-			efx_filter_set_eth_local(&spec, EFX_FILTER_VID_UNSPEC,
-						 baddr);
+			efx_filter_set_eth_local(&spec, vlan->vid, baddr);
 			rc = efx_ef10_filter_insert(efx, &spec, true);
 			if (rc < 0) {
 				netif_warn(efx, drv, efx->net_dev,
@@ -4084,17 +4427,20 @@
 					/* Roll back the mc_def filter */
 					efx_ef10_filter_remove_unsafe(
 							efx, EFX_FILTER_PRI_AUTO,
-							table->mcdef_id);
-					table->mcdef_id = EFX_EF10_FILTER_ID_INVALID;
+							vlan->mcdef);
+					vlan->mcdef = EFX_EF10_FILTER_ID_INVALID;
 					return rc;
 				}
 			} else {
-				table->bcast_id = efx_ef10_filter_get_unsafe_id(efx, rc);
+				EFX_WARN_ON_PARANOID(vlan->bcast !=
+						     EFX_EF10_FILTER_ID_INVALID);
+				vlan->bcast = efx_ef10_filter_get_unsafe_id(efx, rc);
 			}
 		}
 		rc = 0;
 	} else {
-		table->ucdef_id = rc;
+		EFX_WARN_ON_PARANOID(vlan->ucdef != EFX_EF10_FILTER_ID_INVALID);
+		vlan->ucdef = rc;
 		rc = 0;
 	}
 	return rc;
@@ -4203,12 +4549,82 @@
 /* Caller must hold efx->filter_sem for read if race against
  * efx_ef10_filter_table_remove() is possible
  */
-static void efx_ef10_filter_sync_rx_mode(struct efx_nic *efx)
+static void efx_ef10_filter_vlan_sync_rx_mode(struct efx_nic *efx,
+					      struct efx_ef10_filter_vlan *vlan)
 {
 	struct efx_ef10_filter_table *table = efx->filter_state;
 	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+
+	/* Do not install unspecified VID if VLAN filtering is enabled.
+	 * Do not install all specified VIDs if VLAN filtering is disabled.
+	 */
+	if ((vlan->vid == EFX_FILTER_VID_UNSPEC) == table->vlan_filter)
+		return;
+
+	/* Insert/renew unicast filters */
+	if (table->uc_promisc) {
+		efx_ef10_filter_insert_def(efx, vlan, false, false);
+		efx_ef10_filter_insert_addr_list(efx, vlan, false, false);
+	} else {
+		/* If any of the filters failed to insert, fall back to
+		 * promiscuous mode - add in the uc_def filter.  But keep
+		 * our individual unicast filters.
+		 */
+		if (efx_ef10_filter_insert_addr_list(efx, vlan, false, false))
+			efx_ef10_filter_insert_def(efx, vlan, false, false);
+	}
+
+	/* Insert/renew multicast filters */
+	/* If changing promiscuous state with cascaded multicast filters, remove
+	 * old filters first, so that packets are dropped rather than duplicated
+	 */
+	if (nic_data->workaround_26807 &&
+	    table->mc_promisc_last != table->mc_promisc)
+		efx_ef10_filter_remove_old(efx);
+	if (table->mc_promisc) {
+		if (nic_data->workaround_26807) {
+			/* If we failed to insert promiscuous filters, rollback
+			 * and fall back to individual multicast filters
+			 */
+			if (efx_ef10_filter_insert_def(efx, vlan, true, true)) {
+				/* Changing promisc state, so remove old filters */
+				efx_ef10_filter_remove_old(efx);
+				efx_ef10_filter_insert_addr_list(efx, vlan,
+								 true, false);
+			}
+		} else {
+			/* If we failed to insert promiscuous filters, don't
+			 * rollback.  Regardless, also insert the mc_list
+			 */
+			efx_ef10_filter_insert_def(efx, vlan, true, false);
+			efx_ef10_filter_insert_addr_list(efx, vlan, true, false);
+		}
+	} else {
+		/* If any filters failed to insert, rollback and fall back to
+		 * promiscuous mode - mc_def filter and maybe broadcast.  If
+		 * that fails, roll back again and insert as many of our
+		 * individual multicast filters as we can.
+		 */
+		if (efx_ef10_filter_insert_addr_list(efx, vlan, true, true)) {
+			/* Changing promisc state, so remove old filters */
+			if (nic_data->workaround_26807)
+				efx_ef10_filter_remove_old(efx);
+			if (efx_ef10_filter_insert_def(efx, vlan, true, true))
+				efx_ef10_filter_insert_addr_list(efx, vlan,
+								 true, false);
+		}
+	}
+}
+
+/* Caller must hold efx->filter_sem for read if race against
+ * efx_ef10_filter_table_remove() is possible
+ */
+static void efx_ef10_filter_sync_rx_mode(struct efx_nic *efx)
+{
+	struct efx_ef10_filter_table *table = efx->filter_state;
 	struct net_device *net_dev = efx->net_dev;
-	bool uc_promisc = false, mc_promisc = false;
+	struct efx_ef10_filter_vlan *vlan;
+	bool vlan_filter;
 
 	if (!efx_dev_registered(efx))
 		return;
@@ -4222,63 +4638,120 @@
 	 * address and broadcast address
 	 */
 	netif_addr_lock_bh(net_dev);
-	efx_ef10_filter_uc_addr_list(efx, &uc_promisc);
-	efx_ef10_filter_mc_addr_list(efx, &mc_promisc);
+	efx_ef10_filter_uc_addr_list(efx);
+	efx_ef10_filter_mc_addr_list(efx);
 	netif_addr_unlock_bh(net_dev);
 
-	/* Insert/renew unicast filters */
-	if (uc_promisc) {
-		efx_ef10_filter_insert_def(efx, false, false);
-		efx_ef10_filter_insert_addr_list(efx, false, false);
-	} else {
-		/* If any of the filters failed to insert, fall back to
-		 * promiscuous mode - add in the uc_def filter.  But keep
-		 * our individual unicast filters.
-		 */
-		if (efx_ef10_filter_insert_addr_list(efx, false, false))
-			efx_ef10_filter_insert_def(efx, false, false);
+	/* If VLAN filtering changes, all old filters are finally removed.
+	 * Do it in advance to avoid conflicts for unicast untagged and
+	 * VLAN 0 tagged filters.
+	 */
+	vlan_filter = !!(net_dev->features & NETIF_F_HW_VLAN_CTAG_FILTER);
+	if (table->vlan_filter != vlan_filter) {
+		table->vlan_filter = vlan_filter;
+		efx_ef10_filter_remove_old(efx);
 	}
 
-	/* Insert/renew multicast filters */
-	/* If changing promiscuous state with cascaded multicast filters, remove
-	 * old filters first, so that packets are dropped rather than duplicated
-	 */
-	if (nic_data->workaround_26807 && efx->mc_promisc != mc_promisc)
-		efx_ef10_filter_remove_old(efx);
-	if (mc_promisc) {
-		if (nic_data->workaround_26807) {
-			/* If we failed to insert promiscuous filters, rollback
-			 * and fall back to individual multicast filters
-			 */
-			if (efx_ef10_filter_insert_def(efx, true, true)) {
-				/* Changing promisc state, so remove old filters */
-				efx_ef10_filter_remove_old(efx);
-				efx_ef10_filter_insert_addr_list(efx, true, false);
-			}
-		} else {
-			/* If we failed to insert promiscuous filters, don't
-			 * rollback.  Regardless, also insert the mc_list
-			 */
-			efx_ef10_filter_insert_def(efx, true, false);
-			efx_ef10_filter_insert_addr_list(efx, true, false);
-		}
-	} else {
-		/* If any filters failed to insert, rollback and fall back to
-		 * promiscuous mode - mc_def filter and maybe broadcast.  If
-		 * that fails, roll back again and insert as many of our
-		 * individual multicast filters as we can.
-		 */
-		if (efx_ef10_filter_insert_addr_list(efx, true, true)) {
-			/* Changing promisc state, so remove old filters */
-			if (nic_data->workaround_26807)
-				efx_ef10_filter_remove_old(efx);
-			if (efx_ef10_filter_insert_def(efx, true, true))
-				efx_ef10_filter_insert_addr_list(efx, true, false);
-		}
-	}
+	list_for_each_entry(vlan, &table->vlan_list, list)
+		efx_ef10_filter_vlan_sync_rx_mode(efx, vlan);
 
 	efx_ef10_filter_remove_old(efx);
-	efx->mc_promisc = mc_promisc;
+	table->mc_promisc_last = table->mc_promisc;
+}
+
+static struct efx_ef10_filter_vlan *efx_ef10_filter_find_vlan(struct efx_nic *efx, u16 vid)
+{
+	struct efx_ef10_filter_table *table = efx->filter_state;
+	struct efx_ef10_filter_vlan *vlan;
+
+	WARN_ON(!rwsem_is_locked(&efx->filter_sem));
+
+	list_for_each_entry(vlan, &table->vlan_list, list) {
+		if (vlan->vid == vid)
+			return vlan;
+	}
+
+	return NULL;
+}
+
+static int efx_ef10_filter_add_vlan(struct efx_nic *efx, u16 vid)
+{
+	struct efx_ef10_filter_table *table = efx->filter_state;
+	struct efx_ef10_filter_vlan *vlan;
+	unsigned int i;
+
+	if (!efx_rwsem_assert_write_locked(&efx->filter_sem))
+		return -EINVAL;
+
+	vlan = efx_ef10_filter_find_vlan(efx, vid);
+	if (WARN_ON(vlan)) {
+		netif_err(efx, drv, efx->net_dev,
+			  "VLAN %u already added\n", vid);
+		return -EALREADY;
+	}
+
+	vlan = kzalloc(sizeof(*vlan), GFP_KERNEL);
+	if (!vlan)
+		return -ENOMEM;
+
+	vlan->vid = vid;
+
+	for (i = 0; i < ARRAY_SIZE(vlan->uc); i++)
+		vlan->uc[i] = EFX_EF10_FILTER_ID_INVALID;
+	for (i = 0; i < ARRAY_SIZE(vlan->mc); i++)
+		vlan->mc[i] = EFX_EF10_FILTER_ID_INVALID;
+	vlan->ucdef = EFX_EF10_FILTER_ID_INVALID;
+	vlan->bcast = EFX_EF10_FILTER_ID_INVALID;
+	vlan->mcdef = EFX_EF10_FILTER_ID_INVALID;
+
+	list_add_tail(&vlan->list, &table->vlan_list);
+
+	if (efx_dev_registered(efx))
+		efx_ef10_filter_vlan_sync_rx_mode(efx, vlan);
+
+	return 0;
+}
+
+static void efx_ef10_filter_del_vlan_internal(struct efx_nic *efx,
+					      struct efx_ef10_filter_vlan *vlan)
+{
+	unsigned int i;
+
+	/* See comment in efx_ef10_filter_table_remove() */
+	if (!efx_rwsem_assert_write_locked(&efx->filter_sem))
+		return;
+
+	list_del(&vlan->list);
+
+	for (i = 0; i < ARRAY_SIZE(vlan->uc); i++)
+		efx_ef10_filter_remove_unsafe(efx, EFX_FILTER_PRI_AUTO,
+					      vlan->uc[i]);
+	for (i = 0; i < ARRAY_SIZE(vlan->mc); i++)
+		efx_ef10_filter_remove_unsafe(efx, EFX_FILTER_PRI_AUTO,
+					      vlan->mc[i]);
+	efx_ef10_filter_remove_unsafe(efx, EFX_FILTER_PRI_AUTO, vlan->ucdef);
+	efx_ef10_filter_remove_unsafe(efx, EFX_FILTER_PRI_AUTO, vlan->bcast);
+	efx_ef10_filter_remove_unsafe(efx, EFX_FILTER_PRI_AUTO, vlan->mcdef);
+
+	kfree(vlan);
+}
+
+static void efx_ef10_filter_del_vlan(struct efx_nic *efx, u16 vid)
+{
+	struct efx_ef10_filter_vlan *vlan;
+
+	/* See comment in efx_ef10_filter_table_remove() */
+	if (!efx_rwsem_assert_write_locked(&efx->filter_sem))
+		return;
+
+	vlan = efx_ef10_filter_find_vlan(efx, vid);
+	if (!vlan) {
+		netif_err(efx, drv, efx->net_dev,
+			  "VLAN %u not found in filter state\n", vid);
+		return;
+	}
+
+	efx_ef10_filter_del_vlan_internal(efx, vlan);
 }
 
 static int efx_ef10_set_mac_address(struct efx_nic *efx)
@@ -4290,6 +4763,8 @@
 
 	efx_device_detach_sync(efx);
 	efx_net_stop(efx->net_dev);
+
+	mutex_lock(&efx->mac_lock);
 	down_write(&efx->filter_sem);
 	efx_ef10_filter_table_remove(efx);
 
@@ -4302,6 +4777,8 @@
 
 	efx_ef10_filter_table_probe(efx);
 	up_write(&efx->filter_sem);
+	mutex_unlock(&efx->mac_lock);
+
 	if (was_enabled)
 		efx_net_open(efx->net_dev);
 	netif_device_attach(efx->net_dev);
@@ -4703,6 +5180,29 @@
 	}
 }
 
+static int efx_ef10_vlan_rx_add_vid(struct efx_nic *efx, __be16 proto, u16 vid)
+{
+	if (proto != htons(ETH_P_8021Q))
+		return -EINVAL;
+
+	return efx_ef10_add_vlan(efx, vid);
+}
+
+static int efx_ef10_vlan_rx_kill_vid(struct efx_nic *efx, __be16 proto, u16 vid)
+{
+	if (proto != htons(ETH_P_8021Q))
+		return -EINVAL;
+
+	return efx_ef10_del_vlan(efx, vid);
+}
+
+#define EF10_OFFLOAD_FEATURES		\
+	(NETIF_F_IP_CSUM |		\
+	 NETIF_F_HW_VLAN_CTAG_FILTER |	\
+	 NETIF_F_IPV6_CSUM |		\
+	 NETIF_F_RXHASH |		\
+	 NETIF_F_NTUPLE)
+
 const struct efx_nic_type efx_hunt_a0_vf_nic_type = {
 	.is_vf = true,
 	.mem_bar = EFX_MEM_VF_BAR,
@@ -4780,6 +5280,8 @@
 #endif
 	.ptp_write_host_time = efx_ef10_ptp_write_host_time_vf,
 	.ptp_set_ts_config = efx_ef10_ptp_set_ts_config_vf,
+	.vlan_rx_add_vid = efx_ef10_vlan_rx_add_vid,
+	.vlan_rx_kill_vid = efx_ef10_vlan_rx_kill_vid,
 #ifdef CONFIG_SFC_SRIOV
 	.vswitching_probe = efx_ef10_vswitching_probe_vf,
 	.vswitching_restore = efx_ef10_vswitching_restore_vf,
@@ -4798,8 +5300,7 @@
 	.always_rx_scatter = true,
 	.max_interrupt_mode = EFX_INT_MODE_MSIX,
 	.timer_period_max = 1 << ERF_DD_EVQ_IND_TIMER_VAL_WIDTH,
-	.offload_features = (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
-			     NETIF_F_RXHASH | NETIF_F_NTUPLE),
+	.offload_features = EF10_OFFLOAD_FEATURES,
 	.mcdi_max_ver = 2,
 	.max_rx_ip_filters = HUNT_FILTER_TBL_ROWS,
 	.hwtstamp_filters = 1 << HWTSTAMP_FILTER_NONE |
@@ -4891,6 +5392,8 @@
 	.ptp_write_host_time = efx_ef10_ptp_write_host_time,
 	.ptp_set_ts_sync_events = efx_ef10_ptp_set_ts_sync_events,
 	.ptp_set_ts_config = efx_ef10_ptp_set_ts_config,
+	.vlan_rx_add_vid = efx_ef10_vlan_rx_add_vid,
+	.vlan_rx_kill_vid = efx_ef10_vlan_rx_kill_vid,
 #ifdef CONFIG_SFC_SRIOV
 	.sriov_configure = efx_ef10_sriov_configure,
 	.sriov_init = efx_ef10_sriov_init,
@@ -4919,8 +5422,7 @@
 	.always_rx_scatter = true,
 	.max_interrupt_mode = EFX_INT_MODE_MSIX,
 	.timer_period_max = 1 << ERF_DD_EVQ_IND_TIMER_VAL_WIDTH,
-	.offload_features = (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
-			     NETIF_F_RXHASH | NETIF_F_NTUPLE),
+	.offload_features = EF10_OFFLOAD_FEATURES,
 	.mcdi_max_ver = 2,
 	.max_rx_ip_filters = HUNT_FILTER_TBL_ROWS,
 	.hwtstamp_filters = 1 << HWTSTAMP_FILTER_NONE |
diff --git a/drivers/net/ethernet/sfc/ef10_sriov.c b/drivers/net/ethernet/sfc/ef10_sriov.c
index 3c17f27..a949b9d 100644
--- a/drivers/net/ethernet/sfc/ef10_sriov.c
+++ b/drivers/net/ethernet/sfc/ef10_sriov.c
@@ -232,6 +232,35 @@
 	return rc;
 }
 
+static int efx_ef10_vadaptor_alloc_set_features(struct efx_nic *efx)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	u32 port_flags;
+	int rc;
+
+	rc = efx_ef10_vadaptor_alloc(efx, nic_data->vport_id);
+	if (rc)
+		goto fail_vadaptor_alloc;
+
+	rc = efx_ef10_vadaptor_query(efx, nic_data->vport_id,
+				     &port_flags, NULL, NULL);
+	if (rc)
+		goto fail_vadaptor_query;
+
+	if (port_flags &
+	    (1 << MC_CMD_VPORT_ALLOC_IN_FLAG_VLAN_RESTRICT_LBN))
+		efx->fixed_features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+	else
+		efx->fixed_features &= ~NETIF_F_HW_VLAN_CTAG_FILTER;
+
+	return 0;
+
+fail_vadaptor_query:
+	efx_ef10_vadaptor_free(efx, EVB_PORT_ID_ASSIGNED);
+fail_vadaptor_alloc:
+	return rc;
+}
+
 /* On top of the default firmware vswitch setup, create a VEB vswitch and
  * expansion vport for use by this function.
  */
@@ -243,7 +272,7 @@
 
 	if (pci_sriov_get_totalvfs(efx->pci_dev) <= 0) {
 		/* vswitch not needed as we have no VFs */
-		efx_ef10_vadaptor_alloc(efx, nic_data->vport_id);
+		efx_ef10_vadaptor_alloc_set_features(efx);
 		return 0;
 	}
 
@@ -263,7 +292,7 @@
 		goto fail3;
 	ether_addr_copy(nic_data->vport_mac, net_dev->dev_addr);
 
-	rc = efx_ef10_vadaptor_alloc(efx, nic_data->vport_id);
+	rc = efx_ef10_vadaptor_alloc_set_features(efx);
 	if (rc)
 		goto fail4;
 
@@ -282,9 +311,7 @@
 
 int efx_ef10_vswitching_probe_vf(struct efx_nic *efx)
 {
-	struct efx_ef10_nic_data *nic_data = efx->nic_data;
-
-	return efx_ef10_vadaptor_alloc(efx, nic_data->vport_id);
+	return efx_ef10_vadaptor_alloc_set_features(efx);
 }
 
 int efx_ef10_vswitching_restore_pf(struct efx_nic *efx)
@@ -554,6 +581,7 @@
 		efx_device_detach_sync(vf->efx);
 		efx_net_stop(vf->efx->net_dev);
 
+		mutex_lock(&vf->efx->mac_lock);
 		down_write(&vf->efx->filter_sem);
 		vf->efx->type->filter_table_remove(vf->efx);
 
@@ -630,6 +658,7 @@
 			goto reset_nic_up_write;
 
 		up_write(&vf->efx->filter_sem);
+		mutex_unlock(&vf->efx->mac_lock);
 
 		up_write(&vf->efx->filter_sem);
 
@@ -642,9 +671,10 @@
 	return rc;
 
 reset_nic_up_write:
-	if (vf->efx)
+	if (vf->efx) {
 		up_write(&vf->efx->filter_sem);
-
+		mutex_unlock(&vf->efx->mac_lock);
+	}
 reset_nic:
 	if (vf->efx) {
 		netif_err(efx, drv, efx->net_dev,
diff --git a/drivers/net/ethernet/sfc/ef10_sriov.h b/drivers/net/ethernet/sfc/ef10_sriov.h
index 6d25b92..9ceb7ef 100644
--- a/drivers/net/ethernet/sfc/ef10_sriov.h
+++ b/drivers/net/ethernet/sfc/ef10_sriov.h
@@ -70,6 +70,9 @@
 int efx_ef10_vport_del_mac(struct efx_nic *efx,
 			   unsigned int port_id, u8 *mac);
 int efx_ef10_vadaptor_alloc(struct efx_nic *efx, unsigned int port_id);
+int efx_ef10_vadaptor_query(struct efx_nic *efx, unsigned int port_id,
+			    u32 *port_flags, u32 *vadaptor_flags,
+			    unsigned int *vlan_tags);
 int efx_ef10_vadaptor_free(struct efx_nic *efx, unsigned int port_id);
 
 #endif /* EF10_SRIOV_H */
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 097f363..14b821b 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -600,6 +600,7 @@
  */
 static void efx_start_datapath(struct efx_nic *efx)
 {
+	netdev_features_t old_features = efx->net_dev->features;
 	bool old_rx_scatter = efx->rx_scatter;
 	struct efx_tx_queue *tx_queue;
 	struct efx_rx_queue *rx_queue;
@@ -644,6 +645,15 @@
 			  efx->rx_dma_len, efx->rx_page_buf_step,
 			  efx->rx_bufs_per_page, efx->rx_pages_per_batch);
 
+	/* Restore previously fixed features in hw_features and remove
+	 * features which are fixed now
+	 */
+	efx->net_dev->hw_features |= efx->net_dev->features;
+	efx->net_dev->hw_features &= ~efx->fixed_features;
+	efx->net_dev->features |= efx->fixed_features;
+	if (efx->net_dev->features != old_features)
+		netdev_features_change(efx->net_dev);
+
 	/* RX filters may also have scatter-enabled flags */
 	if (efx->rx_scatter != old_rx_scatter)
 		efx->type->filter_update_rx_scatter(efx);
@@ -1719,6 +1729,7 @@
 
 	spin_lock_init(&efx->filter_lock);
 	init_rwsem(&efx->filter_sem);
+	mutex_lock(&efx->mac_lock);
 	down_write(&efx->filter_sem);
 	rc = efx->type->filter_table_probe(efx);
 	if (rc)
@@ -1757,6 +1768,7 @@
 #endif
 out_unlock:
 	up_write(&efx->filter_sem);
+	mutex_unlock(&efx->mac_lock);
 	return rc;
 }
 
@@ -2312,14 +2324,46 @@
 static int efx_set_features(struct net_device *net_dev, netdev_features_t data)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
+	int rc;
 
 	/* If disabling RX n-tuple filtering, clear existing filters */
-	if (net_dev->features & ~data & NETIF_F_NTUPLE)
-		return efx->type->filter_clear_rx(efx, EFX_FILTER_PRI_MANUAL);
+	if (net_dev->features & ~data & NETIF_F_NTUPLE) {
+		rc = efx->type->filter_clear_rx(efx, EFX_FILTER_PRI_MANUAL);
+		if (rc)
+			return rc;
+	}
+
+	/* If Rx VLAN filter is changed, update filters via mac_reconfigure */
+	if ((net_dev->features ^ data) & NETIF_F_HW_VLAN_CTAG_FILTER) {
+		/* efx_set_rx_mode() will schedule MAC work to update filters
+		 * when a new features are finally set in net_dev.
+		 */
+		efx_set_rx_mode(net_dev);
+	}
 
 	return 0;
 }
 
+static int efx_vlan_rx_add_vid(struct net_device *net_dev, __be16 proto, u16 vid)
+{
+	struct efx_nic *efx = netdev_priv(net_dev);
+
+	if (efx->type->vlan_rx_add_vid)
+		return efx->type->vlan_rx_add_vid(efx, proto, vid);
+	else
+		return -EOPNOTSUPP;
+}
+
+static int efx_vlan_rx_kill_vid(struct net_device *net_dev, __be16 proto, u16 vid)
+{
+	struct efx_nic *efx = netdev_priv(net_dev);
+
+	if (efx->type->vlan_rx_kill_vid)
+		return efx->type->vlan_rx_kill_vid(efx, proto, vid);
+	else
+		return -EOPNOTSUPP;
+}
+
 static const struct net_device_ops efx_netdev_ops = {
 	.ndo_open		= efx_net_open,
 	.ndo_stop		= efx_net_stop,
@@ -2332,6 +2376,8 @@
 	.ndo_set_mac_address	= efx_set_mac_address,
 	.ndo_set_rx_mode	= efx_set_rx_mode,
 	.ndo_set_features	= efx_set_features,
+	.ndo_vlan_rx_add_vid	= efx_vlan_rx_add_vid,
+	.ndo_vlan_rx_kill_vid	= efx_vlan_rx_kill_vid,
 #ifdef CONFIG_SFC_SRIOV
 	.ndo_set_vf_mac		= efx_sriov_set_vf_mac,
 	.ndo_set_vf_vlan	= efx_sriov_set_vf_vlan,
@@ -3147,17 +3193,25 @@
 		return -ENOMEM;
 	efx = netdev_priv(net_dev);
 	efx->type = (const struct efx_nic_type *) entry->driver_data;
+	efx->fixed_features |= NETIF_F_HIGHDMA;
 	net_dev->features |= (efx->type->offload_features | NETIF_F_SG |
-			      NETIF_F_HIGHDMA | NETIF_F_TSO |
-			      NETIF_F_RXCSUM);
+			      NETIF_F_TSO | NETIF_F_RXCSUM);
 	if (efx->type->offload_features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM))
 		net_dev->features |= NETIF_F_TSO6;
 	/* Mask for features that also apply to VLAN devices */
 	net_dev->vlan_features |= (NETIF_F_HW_CSUM | NETIF_F_SG |
 				   NETIF_F_HIGHDMA | NETIF_F_ALL_TSO |
 				   NETIF_F_RXCSUM);
-	/* All offloads can be toggled */
-	net_dev->hw_features = net_dev->features & ~NETIF_F_HIGHDMA;
+
+	net_dev->hw_features = net_dev->features & ~efx->fixed_features;
+
+	/* Disable VLAN filtering by default.  It may be enforced if
+	 * the feature is fixed (i.e. VLAN filters are required to
+	 * receive VLAN tagged packets due to vPort restrictions).
+	 */
+	net_dev->features &= ~NETIF_F_HW_VLAN_CTAG_FILTER;
+	net_dev->features |= efx->fixed_features;
+
 	pci_set_drvdata(pci_dev, efx);
 	SET_NETDEV_DEV(net_dev, &pci_dev->dev);
 	rc = efx_init_struct(efx, pci_dev, net_dev);
diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h
index 5e3f93f..c3ae739 100644
--- a/drivers/net/ethernet/sfc/efx.h
+++ b/drivers/net/ethernet/sfc/efx.h
@@ -274,4 +274,13 @@
 	netif_tx_unlock_bh(dev);
 }
 
+static inline bool efx_rwsem_assert_write_locked(struct rw_semaphore *sem)
+{
+	if (WARN_ON(down_read_trylock(sem))) {
+		up_read(sem);
+		return false;
+	}
+	return true;
+}
+
 #endif /* EFX_EFX_H */
diff --git a/drivers/net/ethernet/sfc/mcdi_pcol.h b/drivers/net/ethernet/sfc/mcdi_pcol.h
index 4cc7721..c9a5b00 100644
--- a/drivers/net/ethernet/sfc/mcdi_pcol.h
+++ b/drivers/net/ethernet/sfc/mcdi_pcol.h
@@ -273,6 +273,9 @@
  * have already installed filters. See the comment at
  * MC_CMD_WORKAROUND_BUG26807. */
 #define MC_CMD_ERR_FILTERS_PRESENT 0x1014
+/* The clock whose frequency you've attempted to set set
+ * doesn't exist on this NIC */
+#define MC_CMD_ERR_NO_CLOCK 0x1015
 
 #define MC_CMD_ERR_CODE_OFST 0
 
@@ -292,9 +295,11 @@
 /* Point to the copycode entry point. */
 #define SIENA_MC_BOOTROM_COPYCODE_VEC (0x800 - 3 * 0x4)
 #define HUNT_MC_BOOTROM_COPYCODE_VEC (0x8000 - 3 * 0x4)
+#define MEDFORD_MC_BOOTROM_COPYCODE_VEC (0x10000 - 3 * 0x4)
 /* Points to the recovery mode entry point. */
 #define SIENA_MC_BOOTROM_NOFLASH_VEC (0x800 - 2 * 0x4)
 #define HUNT_MC_BOOTROM_NOFLASH_VEC (0x8000 - 2 * 0x4)
+#define MEDFORD_MC_BOOTROM_NOFLASH_VEC (0x10000 - 2 * 0x4)
 
 /* The command set exported by the boot ROM (MCDI v0) */
 #define MC_CMD_GET_VERSION_V0_SUPPORTED_FUNCS {		\
@@ -686,6 +691,12 @@
 #define          FCDI_EVENT_CODE_PTP_STATUS 0x9
 /* enum: Port id config to map MC-FC port idx */
 #define          FCDI_EVENT_CODE_PORT_CONFIG 0xa
+/* enum: Boot result or error code */
+#define          FCDI_EVENT_CODE_BOOT_RESULT 0xb
+#define       FCDI_EVENT_REBOOT_SRC_LBN 36
+#define       FCDI_EVENT_REBOOT_SRC_WIDTH 8
+#define          FCDI_EVENT_REBOOT_FC_FW 0x0 /* enum */
+#define          FCDI_EVENT_REBOOT_FC_BOOTLOADER 0x1 /* enum */
 #define       FCDI_EVENT_ASSERT_INSTR_ADDRESS_OFST 0
 #define       FCDI_EVENT_ASSERT_INSTR_ADDRESS_LBN 0
 #define       FCDI_EVENT_ASSERT_INSTR_ADDRESS_WIDTH 32
@@ -717,6 +728,11 @@
 #define       FCDI_EVENT_PORT_CONFIG_DATA_OFST 0
 #define       FCDI_EVENT_PORT_CONFIG_DATA_LBN 0
 #define       FCDI_EVENT_PORT_CONFIG_DATA_WIDTH 32
+#define       FCDI_EVENT_BOOT_RESULT_OFST 0
+/*            Enum values, see field(s): */
+/*               MC_CMD_AOE/MC_CMD_AOE_OUT_INFO/FC_BOOT_RESULT */
+#define       FCDI_EVENT_BOOT_RESULT_LBN 0
+#define       FCDI_EVENT_BOOT_RESULT_WIDTH 32
 
 /* FCDI_EXTENDED_EVENT_PPS structuredef: Extended FCDI event to send PPS events
  * to the MC. Note that this structure | is overlayed over a normal FCDI event
@@ -1649,15 +1665,30 @@
 
 /* MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS msgresponse */
 #define    MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_LEN 16
-/* Uncorrected error on transmit timestamps in NIC clock format */
+/* Uncorrected error on PTP transmit timestamps in NIC clock format */
 #define       MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_TRANSMIT_OFST 0
-/* Uncorrected error on receive timestamps in NIC clock format */
+/* Uncorrected error on PTP receive timestamps in NIC clock format */
 #define       MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_RECEIVE_OFST 4
 /* Uncorrected error on PPS output in NIC clock format */
 #define       MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_PPS_OUT_OFST 8
 /* Uncorrected error on PPS input in NIC clock format */
 #define       MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_PPS_IN_OFST 12
 
+/* MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_V2 msgresponse */
+#define    MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_V2_LEN 24
+/* Uncorrected error on PTP transmit timestamps in NIC clock format */
+#define       MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_V2_PTP_TX_OFST 0
+/* Uncorrected error on PTP receive timestamps in NIC clock format */
+#define       MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_V2_PTP_RX_OFST 4
+/* Uncorrected error on PPS output in NIC clock format */
+#define       MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_V2_PPS_OUT_OFST 8
+/* Uncorrected error on PPS input in NIC clock format */
+#define       MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_V2_PPS_IN_OFST 12
+/* Uncorrected error on non-PTP transmit timestamps in NIC clock format */
+#define       MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_V2_GENERAL_TX_OFST 16
+/* Uncorrected error on non-PTP receive timestamps in NIC clock format */
+#define       MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_V2_GENERAL_RX_OFST 20
+
 /* MC_CMD_PTP_OUT_MANFTEST_PPS msgresponse */
 #define    MC_CMD_PTP_OUT_MANFTEST_PPS_LEN 4
 /* Results of testing */
@@ -2158,8 +2189,12 @@
 
 /* MC_CMD_DRV_ATTACH_IN msgrequest */
 #define    MC_CMD_DRV_ATTACH_IN_LEN 12
-/* new state (0=detached, 1=attached) to set if UPDATE=1 */
+/* new state to set if UPDATE=1 */
 #define       MC_CMD_DRV_ATTACH_IN_NEW_STATE_OFST 0
+#define        MC_CMD_DRV_ATTACH_LBN 0
+#define        MC_CMD_DRV_ATTACH_WIDTH 1
+#define        MC_CMD_DRV_PREBOOT_LBN 1
+#define        MC_CMD_DRV_PREBOOT_WIDTH 1
 /* 1 to set new state, or 0 to just report the existing state */
 #define       MC_CMD_DRV_ATTACH_IN_UPDATE_OFST 4
 /* preferred datapath firmware (for Huntington; ignored for Siena) */
@@ -2181,12 +2216,12 @@
 
 /* MC_CMD_DRV_ATTACH_OUT msgresponse */
 #define    MC_CMD_DRV_ATTACH_OUT_LEN 4
-/* previous or existing state (0=detached, 1=attached) */
+/* previous or existing state, see the bitmask at NEW_STATE */
 #define       MC_CMD_DRV_ATTACH_OUT_OLD_STATE_OFST 0
 
 /* MC_CMD_DRV_ATTACH_EXT_OUT msgresponse */
 #define    MC_CMD_DRV_ATTACH_EXT_OUT_LEN 8
-/* previous or existing state (0=detached, 1=attached) */
+/* previous or existing state, see the bitmask at NEW_STATE */
 #define       MC_CMD_DRV_ATTACH_EXT_OUT_OLD_STATE_OFST 0
 /* Flags associated with this function */
 #define       MC_CMD_DRV_ATTACH_EXT_OUT_FUNC_FLAGS_OFST 4
@@ -2198,6 +2233,10 @@
 #define          MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_LINKCTRL 0x1
 /* enum: The function can perform privileged operations */
 #define          MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_TRUSTED 0x2
+/* enum: The function does not have an active port associated with it. The port
+ * refers to the Sorrento external FPGA port.
+ */
+#define          MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_NO_ACTIVE_PORT 0x3
 
 
 /***********************************/
@@ -2892,7 +2931,7 @@
  */
 #define MC_CMD_SET_MAC 0x2c
 
-#define MC_CMD_0x2c_PRIVILEGE_CTG SRIOV_CTG_LINK
+#define MC_CMD_0x2c_PRIVILEGE_CTG SRIOV_CTG_GENERAL
 
 /* MC_CMD_SET_MAC_IN msgrequest */
 #define    MC_CMD_SET_MAC_IN_LEN 28
@@ -2927,9 +2966,66 @@
 #define        MC_CMD_SET_MAC_IN_FLAG_INCLUDE_FCS_LBN 0
 #define        MC_CMD_SET_MAC_IN_FLAG_INCLUDE_FCS_WIDTH 1
 
+/* MC_CMD_SET_MAC_EXT_IN msgrequest */
+#define    MC_CMD_SET_MAC_EXT_IN_LEN 32
+/* The MTU is the MTU programmed directly into the XMAC/GMAC (inclusive of
+ * EtherII, VLAN, bug16011 padding).
+ */
+#define       MC_CMD_SET_MAC_EXT_IN_MTU_OFST 0
+#define       MC_CMD_SET_MAC_EXT_IN_DRAIN_OFST 4
+#define       MC_CMD_SET_MAC_EXT_IN_ADDR_OFST 8
+#define       MC_CMD_SET_MAC_EXT_IN_ADDR_LEN 8
+#define       MC_CMD_SET_MAC_EXT_IN_ADDR_LO_OFST 8
+#define       MC_CMD_SET_MAC_EXT_IN_ADDR_HI_OFST 12
+#define       MC_CMD_SET_MAC_EXT_IN_REJECT_OFST 16
+#define        MC_CMD_SET_MAC_EXT_IN_REJECT_UNCST_LBN 0
+#define        MC_CMD_SET_MAC_EXT_IN_REJECT_UNCST_WIDTH 1
+#define        MC_CMD_SET_MAC_EXT_IN_REJECT_BRDCST_LBN 1
+#define        MC_CMD_SET_MAC_EXT_IN_REJECT_BRDCST_WIDTH 1
+#define       MC_CMD_SET_MAC_EXT_IN_FCNTL_OFST 20
+/* enum: Flow control is off. */
+/*               MC_CMD_FCNTL_OFF 0x0 */
+/* enum: Respond to flow control. */
+/*               MC_CMD_FCNTL_RESPOND 0x1 */
+/* enum: Respond to and Issue flow control. */
+/*               MC_CMD_FCNTL_BIDIR 0x2 */
+/* enum: Auto neg flow control. */
+/*               MC_CMD_FCNTL_AUTO 0x3 */
+/* enum: Priority flow control (eftest builds only). */
+/*               MC_CMD_FCNTL_QBB 0x4 */
+/* enum: Issue flow control. */
+/*               MC_CMD_FCNTL_GENERATE 0x5 */
+#define       MC_CMD_SET_MAC_EXT_IN_FLAGS_OFST 24
+#define        MC_CMD_SET_MAC_EXT_IN_FLAG_INCLUDE_FCS_LBN 0
+#define        MC_CMD_SET_MAC_EXT_IN_FLAG_INCLUDE_FCS_WIDTH 1
+/* Select which parameters to configure. A parameter will only be modified if
+ * the corresponding control flag is set. If SET_MAC_ENHANCED is not set in
+ * capabilities then this field is ignored (and all flags are assumed to be
+ * set).
+ */
+#define       MC_CMD_SET_MAC_EXT_IN_CONTROL_OFST 28
+#define        MC_CMD_SET_MAC_EXT_IN_CFG_MTU_LBN 0
+#define        MC_CMD_SET_MAC_EXT_IN_CFG_MTU_WIDTH 1
+#define        MC_CMD_SET_MAC_EXT_IN_CFG_DRAIN_LBN 1
+#define        MC_CMD_SET_MAC_EXT_IN_CFG_DRAIN_WIDTH 1
+#define        MC_CMD_SET_MAC_EXT_IN_CFG_REJECT_LBN 2
+#define        MC_CMD_SET_MAC_EXT_IN_CFG_REJECT_WIDTH 1
+#define        MC_CMD_SET_MAC_EXT_IN_CFG_FCNTL_LBN 3
+#define        MC_CMD_SET_MAC_EXT_IN_CFG_FCNTL_WIDTH 1
+#define        MC_CMD_SET_MAC_EXT_IN_CFG_FCS_LBN 4
+#define        MC_CMD_SET_MAC_EXT_IN_CFG_FCS_WIDTH 1
+
 /* MC_CMD_SET_MAC_OUT msgresponse */
 #define    MC_CMD_SET_MAC_OUT_LEN 0
 
+/* MC_CMD_SET_MAC_V2_OUT msgresponse */
+#define    MC_CMD_SET_MAC_V2_OUT_LEN 4
+/* MTU as configured after processing the request. See comment at
+ * MC_CMD_SET_MAC_IN/MTU. To query MTU without doing any changes, set CONTROL
+ * to 0.
+ */
+#define       MC_CMD_SET_MAC_V2_OUT_MTU_OFST 0
+
 
 /***********************************/
 /* MC_CMD_PHY_STATS
@@ -3521,6 +3617,26 @@
 #define       MC_CMD_NVRAM_INFO_OUT_PHYSDEV_OFST 16
 #define       MC_CMD_NVRAM_INFO_OUT_PHYSADDR_OFST 20
 
+/* MC_CMD_NVRAM_INFO_V2_OUT msgresponse */
+#define    MC_CMD_NVRAM_INFO_V2_OUT_LEN 28
+#define       MC_CMD_NVRAM_INFO_V2_OUT_TYPE_OFST 0
+/*            Enum values, see field(s): */
+/*               MC_CMD_NVRAM_TYPES/MC_CMD_NVRAM_TYPES_OUT/TYPES */
+#define       MC_CMD_NVRAM_INFO_V2_OUT_SIZE_OFST 4
+#define       MC_CMD_NVRAM_INFO_V2_OUT_ERASESIZE_OFST 8
+#define       MC_CMD_NVRAM_INFO_V2_OUT_FLAGS_OFST 12
+#define        MC_CMD_NVRAM_INFO_V2_OUT_PROTECTED_LBN 0
+#define        MC_CMD_NVRAM_INFO_V2_OUT_PROTECTED_WIDTH 1
+#define        MC_CMD_NVRAM_INFO_V2_OUT_TLV_LBN 1
+#define        MC_CMD_NVRAM_INFO_V2_OUT_TLV_WIDTH 1
+#define        MC_CMD_NVRAM_INFO_V2_OUT_A_B_LBN 7
+#define        MC_CMD_NVRAM_INFO_V2_OUT_A_B_WIDTH 1
+#define       MC_CMD_NVRAM_INFO_V2_OUT_PHYSDEV_OFST 16
+#define       MC_CMD_NVRAM_INFO_V2_OUT_PHYSADDR_OFST 20
+/* Writes must be multiples of this size. Added to support the MUM on Sorrento.
+ */
+#define       MC_CMD_NVRAM_INFO_V2_OUT_WRITESIZE_OFST 24
+
 
 /***********************************/
 /* MC_CMD_NVRAM_UPDATE_START
@@ -3561,6 +3677,37 @@
 /* amount to read in bytes */
 #define       MC_CMD_NVRAM_READ_IN_LENGTH_OFST 8
 
+/* MC_CMD_NVRAM_READ_IN_V2 msgrequest */
+#define    MC_CMD_NVRAM_READ_IN_V2_LEN 16
+#define       MC_CMD_NVRAM_READ_IN_V2_TYPE_OFST 0
+/*            Enum values, see field(s): */
+/*               MC_CMD_NVRAM_TYPES/MC_CMD_NVRAM_TYPES_OUT/TYPES */
+#define       MC_CMD_NVRAM_READ_IN_V2_OFFSET_OFST 4
+/* amount to read in bytes */
+#define       MC_CMD_NVRAM_READ_IN_V2_LENGTH_OFST 8
+/* Optional control info. If a partition is stored with an A/B versioning
+ * scheme (i.e. in more than one physical partition in NVRAM) the host can set
+ * this to control which underlying physical partition is used to read data
+ * from. This allows it to perform a read-modify-write-verify with the write
+ * lock continuously held by calling NVRAM_UPDATE_START, reading the old
+ * contents using MODE=TARGET_CURRENT, overwriting the old partition and then
+ * verifying by reading with MODE=TARGET_BACKUP.
+ */
+#define       MC_CMD_NVRAM_READ_IN_V2_MODE_OFST 12
+/* enum: Same as omitting MODE: caller sees data in current partition unless it
+ * holds the write lock in which case it sees data in the partition it is
+ * updating.
+ */
+#define          MC_CMD_NVRAM_READ_IN_V2_DEFAULT 0x0
+/* enum: Read from the current partition of an A/B pair, even if holding the
+ * write lock.
+ */
+#define          MC_CMD_NVRAM_READ_IN_V2_TARGET_CURRENT 0x1
+/* enum: Read from the non-current (i.e. to be updated) partition of an A/B
+ * pair
+ */
+#define          MC_CMD_NVRAM_READ_IN_V2_TARGET_BACKUP 0x2
+
 /* MC_CMD_NVRAM_READ_OUT msgresponse */
 #define    MC_CMD_NVRAM_READ_OUT_LENMIN 1
 #define    MC_CMD_NVRAM_READ_OUT_LENMAX 252
@@ -3895,6 +4042,8 @@
 #define          MC_CMD_SENSOR_CCOM_AVREG_1V8_SUPPLY  0x39
 /* enum: CCOM AVREG 1v8 supply (external ADC): mV */
 #define          MC_CMD_SENSOR_CCOM_AVREG_1V8_SUPPLY_EXTADC  0x3a
+/* enum: CCOM RTS temperature: degC */
+#define          MC_CMD_SENSOR_CONTROLLER_RTS  0x3b
 /* enum: Not a sensor: reserved for the next page flag */
 #define          MC_CMD_SENSOR_PAGE1_NEXT  0x3f
 /* enum: controller internal temperature sensor voltage on master core
@@ -3931,6 +4080,12 @@
 #define          MC_CMD_SENSOR_PHY0_VCC  0x4c
 /* enum: Voltage supplied to the QSFP #1 from their power supply: mV */
 #define          MC_CMD_SENSOR_PHY1_VCC  0x4d
+/* enum: Controller die temperature (TDIODE): degC */
+#define          MC_CMD_SENSOR_CONTROLLER_TDIODE_TEMP  0x4e
+/* enum: Board temperature (front): degC */
+#define          MC_CMD_SENSOR_BOARD_FRONT_TEMP  0x4f
+/* enum: Board temperature (back): degC */
+#define          MC_CMD_SENSOR_BOARD_BACK_TEMP  0x50
 /* MC_CMD_SENSOR_INFO_ENTRY_TYPEDEF */
 #define       MC_CMD_SENSOR_ENTRY_OFST 4
 #define       MC_CMD_SENSOR_ENTRY_LEN 8
@@ -4007,7 +4162,7 @@
 
 /* MC_CMD_READ_SENSORS_EXT_IN msgrequest */
 #define    MC_CMD_READ_SENSORS_EXT_IN_LEN 12
-/* DMA address of host buffer for sensor readings */
+/* DMA address of host buffer for sensor readings (must be 4Kbyte aligned). */
 #define       MC_CMD_READ_SENSORS_EXT_IN_DMA_ADDR_OFST 0
 #define       MC_CMD_READ_SENSORS_EXT_IN_DMA_ADDR_LEN 8
 #define       MC_CMD_READ_SENSORS_EXT_IN_DMA_ADDR_LO_OFST 0
@@ -4608,6 +4763,10 @@
  * operations
  */
 #define          MC_CMD_MUM_OP_QSFP 0xc
+/* enum: Request discrete and SODIMM DDR info (type, size, speed grade, voltage
+ * level) from MUM
+ */
+#define          MC_CMD_MUM_OP_READ_DDR_INFO 0xd
 
 /* MC_CMD_MUM_IN_NULL msgrequest */
 #define    MC_CMD_MUM_IN_NULL_LEN 4
@@ -4793,6 +4952,10 @@
 #define       MC_CMD_MUM_IN_PROGRAM_CLOCKS_FLAGS_OFST 8
 #define        MC_CMD_MUM_IN_PROGRAM_CLOCKS_OVERCLOCK_110_LBN 0
 #define        MC_CMD_MUM_IN_PROGRAM_CLOCKS_OVERCLOCK_110_WIDTH 1
+#define        MC_CMD_MUM_IN_PROGRAM_CLOCKS_CLOCK_NIC_FROM_FPGA_LBN 1
+#define        MC_CMD_MUM_IN_PROGRAM_CLOCKS_CLOCK_NIC_FROM_FPGA_WIDTH 1
+#define        MC_CMD_MUM_IN_PROGRAM_CLOCKS_CLOCK_REF_FROM_XO_LBN 2
+#define        MC_CMD_MUM_IN_PROGRAM_CLOCKS_CLOCK_REF_FROM_XO_WIDTH 1
 
 /* MC_CMD_MUM_IN_FPGA_LOAD msgrequest */
 #define    MC_CMD_MUM_IN_FPGA_LOAD_LEN 8
@@ -4862,6 +5025,11 @@
 #define       MC_CMD_MUM_IN_QSFP_POLL_BIST_HDR_OFST 4
 #define       MC_CMD_MUM_IN_QSFP_POLL_BIST_IDX_OFST 8
 
+/* MC_CMD_MUM_IN_READ_DDR_INFO msgrequest */
+#define    MC_CMD_MUM_IN_READ_DDR_INFO_LEN 4
+/* MUM cmd header */
+/*            MC_CMD_MUM_IN_CMD_OFST 0 */
+
 /* MC_CMD_MUM_OUT msgresponse */
 #define    MC_CMD_MUM_OUT_LEN 0
 
@@ -5004,6 +5172,69 @@
 #define    MC_CMD_MUM_OUT_QSFP_POLL_BIST_LEN 4
 #define       MC_CMD_MUM_OUT_QSFP_POLL_BIST_TEST_OFST 0
 
+/* MC_CMD_MUM_OUT_READ_DDR_INFO msgresponse */
+#define    MC_CMD_MUM_OUT_READ_DDR_INFO_LENMIN 24
+#define    MC_CMD_MUM_OUT_READ_DDR_INFO_LENMAX 248
+#define    MC_CMD_MUM_OUT_READ_DDR_INFO_LEN(num) (8+8*(num))
+/* Discrete (soldered) DDR resistor strap info */
+#define       MC_CMD_MUM_OUT_READ_DDR_INFO_DISCRETE_DDR_INFO_OFST 0
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_VRATIO_LBN 0
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_VRATIO_WIDTH 16
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_RESERVED1_LBN 16
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_RESERVED1_WIDTH 16
+/* Number of SODIMM info records */
+#define       MC_CMD_MUM_OUT_READ_DDR_INFO_NUM_RECORDS_OFST 4
+/* Array of SODIMM info records */
+#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_OFST 8
+#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_LEN 8
+#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_LO_OFST 8
+#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_HI_OFST 12
+#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_MINNUM 2
+#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_MAXNUM 30
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_BANK_ID_LBN 0
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_BANK_ID_WIDTH 8
+/* enum: SODIMM bank 1 (Top SODIMM for Sorrento) */
+#define          MC_CMD_MUM_OUT_READ_DDR_INFO_BANK1 0x0
+/* enum: SODIMM bank 2 (Bottom SODDIMM for Sorrento) */
+#define          MC_CMD_MUM_OUT_READ_DDR_INFO_BANK2 0x1
+/* enum: Total number of SODIMM banks */
+#define          MC_CMD_MUM_OUT_READ_DDR_INFO_NUM_BANKS 0x2
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_TYPE_LBN 8
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_TYPE_WIDTH 8
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_RANK_LBN 16
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_RANK_WIDTH 4
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_VOLTAGE_LBN 20
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_VOLTAGE_WIDTH 4
+#define          MC_CMD_MUM_OUT_READ_DDR_INFO_NOT_POWERED 0x0 /* enum */
+#define          MC_CMD_MUM_OUT_READ_DDR_INFO_1V25 0x1 /* enum */
+#define          MC_CMD_MUM_OUT_READ_DDR_INFO_1V35 0x2 /* enum */
+#define          MC_CMD_MUM_OUT_READ_DDR_INFO_1V5 0x3 /* enum */
+/* enum: Values 5-15 are reserved for future usage */
+#define          MC_CMD_MUM_OUT_READ_DDR_INFO_1V8 0x4
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_SIZE_LBN 24
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_SIZE_WIDTH 8
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_SPEED_LBN 32
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_SPEED_WIDTH 16
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_STATE_LBN 48
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_STATE_WIDTH 4
+/* enum: No module present */
+#define          MC_CMD_MUM_OUT_READ_DDR_INFO_ABSENT 0x0
+/* enum: Module present supported and powered on */
+#define          MC_CMD_MUM_OUT_READ_DDR_INFO_PRESENT_POWERED 0x1
+/* enum: Module present but bad type */
+#define          MC_CMD_MUM_OUT_READ_DDR_INFO_PRESENT_BAD_TYPE 0x2
+/* enum: Module present but incompatible voltage */
+#define          MC_CMD_MUM_OUT_READ_DDR_INFO_PRESENT_BAD_VOLTAGE 0x3
+/* enum: Module present but unknown SPD */
+#define          MC_CMD_MUM_OUT_READ_DDR_INFO_PRESENT_BAD_SPD 0x4
+/* enum: Module present but slot cannot support it */
+#define          MC_CMD_MUM_OUT_READ_DDR_INFO_PRESENT_BAD_SLOT 0x5
+/* enum: Modules may or may not be present, but cannot establish contact by I2C
+ */
+#define          MC_CMD_MUM_OUT_READ_DDR_INFO_NOT_REACHABLE 0x6
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_RESERVED2_LBN 52
+#define        MC_CMD_MUM_OUT_READ_DDR_INFO_RESERVED2_WIDTH 12
+
 /* MC_CMD_RESOURCE_SPECIFIER enum */
 /* enum: Any */
 #define          MC_CMD_RESOURCE_INSTANCE_ANY 0xffffffff
@@ -5076,6 +5307,8 @@
 #define          NVRAM_PARTITION_TYPE_DYNAMIC_CONFIG       0x500
 /* enum: Expansion ROM configuration data for port 0 */
 #define          NVRAM_PARTITION_TYPE_EXPROM_CONFIG_PORT0  0x600
+/* enum: Synonym for EXPROM_CONFIG_PORT0 as used in pmap files */
+#define          NVRAM_PARTITION_TYPE_EXPROM_CONFIG        0x600
 /* enum: Expansion ROM configuration data for port 1 */
 #define          NVRAM_PARTITION_TYPE_EXPROM_CONFIG_PORT1  0x601
 /* enum: Expansion ROM configuration data for port 2 */
@@ -5084,6 +5317,8 @@
 #define          NVRAM_PARTITION_TYPE_EXPROM_CONFIG_PORT3  0x603
 /* enum: Non-volatile log output partition */
 #define          NVRAM_PARTITION_TYPE_LOG                  0x700
+/* enum: Non-volatile log output of second core on dual-core device */
+#define          NVRAM_PARTITION_TYPE_LOG_SLAVE            0x701
 /* enum: Device state dump output partition */
 #define          NVRAM_PARTITION_TYPE_DUMP                 0x800
 /* enum: Application license key storage partition */
@@ -5116,6 +5351,20 @@
 #define          NVRAM_PARTITION_TYPE_MUM_USER_ROM         0xc05
 /* enum: MUM fuses and lockbits partition. */
 #define          NVRAM_PARTITION_TYPE_MUM_FUSELOCK         0xc06
+/* enum: UEFI expansion ROM if separate from PXE */
+#define          NVRAM_PARTITION_TYPE_EXPANSION_UEFI       0xd00
+/* enum: Spare partition 0 */
+#define          NVRAM_PARTITION_TYPE_SPARE_0              0x1000
+/* enum: Spare partition 1 */
+#define          NVRAM_PARTITION_TYPE_SPARE_1              0x1100
+/* enum: Spare partition 2 */
+#define          NVRAM_PARTITION_TYPE_SPARE_2              0x1200
+/* enum: Spare partition 3 */
+#define          NVRAM_PARTITION_TYPE_SPARE_3              0x1300
+/* enum: Spare partition 4 */
+#define          NVRAM_PARTITION_TYPE_SPARE_4              0x1400
+/* enum: Spare partition 5 */
+#define          NVRAM_PARTITION_TYPE_SPARE_5              0x1500
 /* enum: Start of reserved value range (firmware may use for any purpose) */
 #define          NVRAM_PARTITION_TYPE_RESERVED_VALUES_MIN  0xff00
 /* enum: End of reserved value range (firmware may use for any purpose) */
@@ -5149,6 +5398,90 @@
 #define       LICENSED_APP_ID_ID_LBN 0
 #define       LICENSED_APP_ID_ID_WIDTH 32
 
+/* LICENSED_FEATURES structuredef */
+#define    LICENSED_FEATURES_LEN 8
+/* Bitmask of licensed firmware features */
+#define       LICENSED_FEATURES_MASK_OFST 0
+#define       LICENSED_FEATURES_MASK_LEN 8
+#define       LICENSED_FEATURES_MASK_LO_OFST 0
+#define       LICENSED_FEATURES_MASK_HI_OFST 4
+#define        LICENSED_FEATURES_RX_CUT_THROUGH_LBN 0
+#define        LICENSED_FEATURES_RX_CUT_THROUGH_WIDTH 1
+#define        LICENSED_FEATURES_PIO_LBN 1
+#define        LICENSED_FEATURES_PIO_WIDTH 1
+#define        LICENSED_FEATURES_EVQ_TIMER_LBN 2
+#define        LICENSED_FEATURES_EVQ_TIMER_WIDTH 1
+#define        LICENSED_FEATURES_CLOCK_LBN 3
+#define        LICENSED_FEATURES_CLOCK_WIDTH 1
+#define        LICENSED_FEATURES_RX_TIMESTAMPS_LBN 4
+#define        LICENSED_FEATURES_RX_TIMESTAMPS_WIDTH 1
+#define        LICENSED_FEATURES_TX_TIMESTAMPS_LBN 5
+#define        LICENSED_FEATURES_TX_TIMESTAMPS_WIDTH 1
+#define        LICENSED_FEATURES_RX_SNIFF_LBN 6
+#define        LICENSED_FEATURES_RX_SNIFF_WIDTH 1
+#define        LICENSED_FEATURES_TX_SNIFF_LBN 7
+#define        LICENSED_FEATURES_TX_SNIFF_WIDTH 1
+#define        LICENSED_FEATURES_PROXY_FILTER_OPS_LBN 8
+#define        LICENSED_FEATURES_PROXY_FILTER_OPS_WIDTH 1
+#define        LICENSED_FEATURES_EVENT_CUT_THROUGH_LBN 9
+#define        LICENSED_FEATURES_EVENT_CUT_THROUGH_WIDTH 1
+#define       LICENSED_FEATURES_MASK_LBN 0
+#define       LICENSED_FEATURES_MASK_WIDTH 64
+
+/* LICENSED_V3_APPS structuredef */
+#define    LICENSED_V3_APPS_LEN 8
+/* Bitmask of licensed applications */
+#define       LICENSED_V3_APPS_MASK_OFST 0
+#define       LICENSED_V3_APPS_MASK_LEN 8
+#define       LICENSED_V3_APPS_MASK_LO_OFST 0
+#define       LICENSED_V3_APPS_MASK_HI_OFST 4
+#define        LICENSED_V3_APPS_ONLOAD_LBN 0
+#define        LICENSED_V3_APPS_ONLOAD_WIDTH 1
+#define        LICENSED_V3_APPS_PTP_LBN 1
+#define        LICENSED_V3_APPS_PTP_WIDTH 1
+#define        LICENSED_V3_APPS_SOLARCAPTURE_PRO_LBN 2
+#define        LICENSED_V3_APPS_SOLARCAPTURE_PRO_WIDTH 1
+#define        LICENSED_V3_APPS_SOLARSECURE_LBN 3
+#define        LICENSED_V3_APPS_SOLARSECURE_WIDTH 1
+#define        LICENSED_V3_APPS_PERF_MONITOR_LBN 4
+#define        LICENSED_V3_APPS_PERF_MONITOR_WIDTH 1
+#define        LICENSED_V3_APPS_SOLARCAPTURE_LIVE_LBN 5
+#define        LICENSED_V3_APPS_SOLARCAPTURE_LIVE_WIDTH 1
+#define        LICENSED_V3_APPS_CAPTURE_SOLARSYSTEM_LBN 6
+#define        LICENSED_V3_APPS_CAPTURE_SOLARSYSTEM_WIDTH 1
+#define        LICENSED_V3_APPS_NETWORK_ACCESS_CONTROL_LBN 7
+#define        LICENSED_V3_APPS_NETWORK_ACCESS_CONTROL_WIDTH 1
+#define       LICENSED_V3_APPS_MASK_LBN 0
+#define       LICENSED_V3_APPS_MASK_WIDTH 64
+
+/* LICENSED_V3_FEATURES structuredef */
+#define    LICENSED_V3_FEATURES_LEN 8
+/* Bitmask of licensed firmware features */
+#define       LICENSED_V3_FEATURES_MASK_OFST 0
+#define       LICENSED_V3_FEATURES_MASK_LEN 8
+#define       LICENSED_V3_FEATURES_MASK_LO_OFST 0
+#define       LICENSED_V3_FEATURES_MASK_HI_OFST 4
+#define        LICENSED_V3_FEATURES_RX_CUT_THROUGH_LBN 0
+#define        LICENSED_V3_FEATURES_RX_CUT_THROUGH_WIDTH 1
+#define        LICENSED_V3_FEATURES_PIO_LBN 1
+#define        LICENSED_V3_FEATURES_PIO_WIDTH 1
+#define        LICENSED_V3_FEATURES_EVQ_TIMER_LBN 2
+#define        LICENSED_V3_FEATURES_EVQ_TIMER_WIDTH 1
+#define        LICENSED_V3_FEATURES_CLOCK_LBN 3
+#define        LICENSED_V3_FEATURES_CLOCK_WIDTH 1
+#define        LICENSED_V3_FEATURES_RX_TIMESTAMPS_LBN 4
+#define        LICENSED_V3_FEATURES_RX_TIMESTAMPS_WIDTH 1
+#define        LICENSED_V3_FEATURES_TX_TIMESTAMPS_LBN 5
+#define        LICENSED_V3_FEATURES_TX_TIMESTAMPS_WIDTH 1
+#define        LICENSED_V3_FEATURES_RX_SNIFF_LBN 6
+#define        LICENSED_V3_FEATURES_RX_SNIFF_WIDTH 1
+#define        LICENSED_V3_FEATURES_TX_SNIFF_LBN 7
+#define        LICENSED_V3_FEATURES_TX_SNIFF_WIDTH 1
+#define        LICENSED_V3_FEATURES_PROXY_FILTER_OPS_LBN 8
+#define        LICENSED_V3_FEATURES_PROXY_FILTER_OPS_WIDTH 1
+#define       LICENSED_V3_FEATURES_MASK_LBN 0
+#define       LICENSED_V3_FEATURES_MASK_WIDTH 64
+
 /* TX_TIMESTAMP_EVENT structuredef */
 #define    TX_TIMESTAMP_EVENT_LEN 6
 /* lower 16 bits of timestamp data */
@@ -5258,6 +5591,8 @@
 #define        MC_CMD_INIT_EVQ_IN_FLAG_RX_MERGE_WIDTH 1
 #define        MC_CMD_INIT_EVQ_IN_FLAG_TX_MERGE_LBN 5
 #define        MC_CMD_INIT_EVQ_IN_FLAG_TX_MERGE_WIDTH 1
+#define        MC_CMD_INIT_EVQ_IN_FLAG_USE_TIMER_LBN 6
+#define        MC_CMD_INIT_EVQ_IN_FLAG_USE_TIMER_WIDTH 1
 #define       MC_CMD_INIT_EVQ_IN_TMR_MODE_OFST 20
 /* enum: Disabled */
 #define          MC_CMD_INIT_EVQ_IN_TMR_MODE_DIS 0x0
@@ -5362,6 +5697,8 @@
 #define        MC_CMD_INIT_RXQ_IN_FLAG_PREFIX_WIDTH 1
 #define        MC_CMD_INIT_RXQ_IN_FLAG_DISABLE_SCATTER_LBN 9
 #define        MC_CMD_INIT_RXQ_IN_FLAG_DISABLE_SCATTER_WIDTH 1
+#define        MC_CMD_INIT_RXQ_IN_FLAG_FORCE_EV_MERGING_LBN 10
+#define        MC_CMD_INIT_RXQ_IN_FLAG_FORCE_EV_MERGING_WIDTH 1
 /* Owner ID to use if in buffer mode (zero if physical) */
 #define       MC_CMD_INIT_RXQ_IN_OWNER_ID_OFST 20
 /* The port ID associated with the v-adaptor which should contain this DMAQ. */
@@ -5422,6 +5759,8 @@
 #define          MC_CMD_INIT_RXQ_EXT_IN_PS_BUFF_64K  0x4 /* enum */
 #define        MC_CMD_INIT_RXQ_EXT_IN_FLAG_WANT_OUTER_CLASSES_LBN 18
 #define        MC_CMD_INIT_RXQ_EXT_IN_FLAG_WANT_OUTER_CLASSES_WIDTH 1
+#define        MC_CMD_INIT_RXQ_EXT_IN_FLAG_FORCE_EV_MERGING_LBN 19
+#define        MC_CMD_INIT_RXQ_EXT_IN_FLAG_FORCE_EV_MERGING_WIDTH 1
 /* Owner ID to use if in buffer mode (zero if physical) */
 #define       MC_CMD_INIT_RXQ_EXT_IN_OWNER_ID_OFST 20
 /* The port ID associated with the v-adaptor which should contain this DMAQ. */
@@ -5535,6 +5874,8 @@
 #define        MC_CMD_INIT_TXQ_EXT_IN_FLAG_INNER_IP_CSUM_EN_WIDTH 1
 #define        MC_CMD_INIT_TXQ_EXT_IN_FLAG_INNER_TCP_CSUM_EN_LBN 11
 #define        MC_CMD_INIT_TXQ_EXT_IN_FLAG_INNER_TCP_CSUM_EN_WIDTH 1
+#define        MC_CMD_INIT_TXQ_EXT_IN_FLAG_TSOV2_EN_LBN 12
+#define        MC_CMD_INIT_TXQ_EXT_IN_FLAG_TSOV2_EN_WIDTH 1
 /* Owner ID to use if in buffer mode (zero if physical) */
 #define       MC_CMD_INIT_TXQ_EXT_IN_OWNER_ID_OFST 20
 /* The port ID associated with the v-adaptor which should contain this DMAQ. */
@@ -5747,6 +6088,46 @@
 #define       MC_CMD_PROXY_CONFIGURE_IN_ALLOWED_MCDI_MASK_OFST 44
 #define       MC_CMD_PROXY_CONFIGURE_IN_ALLOWED_MCDI_MASK_LEN 64
 
+/* MC_CMD_PROXY_CONFIGURE_EXT_IN msgrequest */
+#define    MC_CMD_PROXY_CONFIGURE_EXT_IN_LEN 112
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_FLAGS_OFST 0
+#define        MC_CMD_PROXY_CONFIGURE_EXT_IN_ENABLE_LBN 0
+#define        MC_CMD_PROXY_CONFIGURE_EXT_IN_ENABLE_WIDTH 1
+/* Host provides a contiguous memory buffer that contains at least NUM_BLOCKS
+ * of blocks, each of the size REQUEST_BLOCK_SIZE.
+ */
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BUFF_ADDR_OFST 4
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BUFF_ADDR_LEN 8
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BUFF_ADDR_LO_OFST 4
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BUFF_ADDR_HI_OFST 8
+/* Must be a power of 2 */
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BLOCK_SIZE_OFST 12
+/* Host provides a contiguous memory buffer that contains at least NUM_BLOCKS
+ * of blocks, each of the size REPLY_BLOCK_SIZE.
+ */
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BUFF_ADDR_OFST 16
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BUFF_ADDR_LEN 8
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BUFF_ADDR_LO_OFST 16
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BUFF_ADDR_HI_OFST 20
+/* Must be a power of 2 */
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BLOCK_SIZE_OFST 24
+/* Host provides a contiguous memory buffer that contains at least NUM_BLOCKS
+ * of blocks, each of the size STATUS_BLOCK_SIZE. This buffer is only needed if
+ * host intends to complete proxied operations by using MC_CMD_PROXY_CMD.
+ */
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BUFF_ADDR_OFST 28
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BUFF_ADDR_LEN 8
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BUFF_ADDR_LO_OFST 28
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BUFF_ADDR_HI_OFST 32
+/* Must be a power of 2, or zero if this buffer is not provided */
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BLOCK_SIZE_OFST 36
+/* Applies to all three buffers */
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_NUM_BLOCKS_OFST 40
+/* A bit mask defining which MCDI operations may be proxied */
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_ALLOWED_MCDI_MASK_OFST 44
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_ALLOWED_MCDI_MASK_LEN 64
+#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_RESERVED_OFST 108
+
 /* MC_CMD_PROXY_CONFIGURE_OUT msgresponse */
 #define    MC_CMD_PROXY_CONFIGURE_OUT_LEN 0
 
@@ -6323,6 +6704,15 @@
  * client
  */
 #define          MC_CMD_GET_PARSER_DISP_INFO_IN_OP_GET_RESTRICTIONS  0x2
+/* enum: read properties relating to security rules (Medford-only; for use by
+ * SolarSecure apps, not directly by drivers. See SF-114946-SW.)
+ */
+#define          MC_CMD_GET_PARSER_DISP_INFO_IN_OP_GET_SECURITY_RULE_INFO  0x3
+/* enum: read the list of supported RX filter matches for VXLAN/NVGRE
+ * encapsulated frames, which follow a different match sequence to normal
+ * frames (Medford only)
+ */
+#define          MC_CMD_GET_PARSER_DISP_INFO_IN_OP_GET_SUPPORTED_ENCAP_RX_MATCHES  0x4
 
 /* MC_CMD_GET_PARSER_DISP_INFO_OUT msgresponse */
 #define    MC_CMD_GET_PARSER_DISP_INFO_OUT_LENMIN 8
@@ -6356,7 +6746,10 @@
 
 /***********************************/
 /* MC_CMD_PARSER_DISP_RW
- * Direct read/write of parser-dispatcher state (DICPUs and LUE) for debugging
+ * Direct read/write of parser-dispatcher state (DICPUs and LUE) for debugging.
+ * Please note that this interface is only of use to debug tools which have
+ * knowledge of firmware and hardware data structures; nothing here is intended
+ * for use by normal driver code.
  */
 #define MC_CMD_PARSER_DISP_RW 0xe5
 
@@ -6374,6 +6767,12 @@
 #define          MC_CMD_PARSER_DISP_RW_IN_LUE  0x2
 /* enum: Lookup engine (with requested metadata format) */
 #define          MC_CMD_PARSER_DISP_RW_IN_LUE_VERSIONED_METADATA  0x3
+/* enum: RX0 dispatcher CPU (alias for RX_DICPU; Medford has 2 RX DICPUs) */
+#define          MC_CMD_PARSER_DISP_RW_IN_RX0_DICPU  0x0
+/* enum: RX1 dispatcher CPU (only valid for Medford) */
+#define          MC_CMD_PARSER_DISP_RW_IN_RX1_DICPU  0x4
+/* enum: Miscellaneous other state (only valid for Medford) */
+#define          MC_CMD_PARSER_DISP_RW_IN_MISC_STATE  0x5
 /* identifies the type of operation requested */
 #define       MC_CMD_PARSER_DISP_RW_IN_OP_OFST 4
 /* enum: read a word of DICPU DMEM or a LUE entry */
@@ -6382,8 +6781,12 @@
 #define          MC_CMD_PARSER_DISP_RW_IN_WRITE  0x1
 /* enum: read-modify-write a word of DICPU DMEM (not valid for LUE) */
 #define          MC_CMD_PARSER_DISP_RW_IN_RMW  0x2
-/* data memory address or LUE index */
+/* data memory address (DICPU targets) or LUE index (LUE targets) */
 #define       MC_CMD_PARSER_DISP_RW_IN_ADDRESS_OFST 8
+/* selector (for MISC_STATE target) */
+#define       MC_CMD_PARSER_DISP_RW_IN_SELECTOR_OFST 8
+/* enum: Port to datapath mapping */
+#define          MC_CMD_PARSER_DISP_RW_IN_PORT_DP_MAPPING  0x1
 /* value to write (for DMEM writes) */
 #define       MC_CMD_PARSER_DISP_RW_IN_DMEM_WRITE_VALUE_OFST 12
 /* XOR value (for DMEM read-modify-writes: new = (old & mask) ^ value) */
@@ -6408,6 +6811,12 @@
  */
 #define       MC_CMD_PARSER_DISP_RW_OUT_LUE_MGR_STATE_OFST 20
 #define       MC_CMD_PARSER_DISP_RW_OUT_LUE_MGR_STATE_LEN 32
+/* datapath(s) used for each port (for MISC_STATE PORT_DP_MAPPING selector) */
+#define       MC_CMD_PARSER_DISP_RW_OUT_PORT_DP_MAPPING_OFST 0
+#define       MC_CMD_PARSER_DISP_RW_OUT_PORT_DP_MAPPING_LEN 4
+#define       MC_CMD_PARSER_DISP_RW_OUT_PORT_DP_MAPPING_NUM 4
+#define          MC_CMD_PARSER_DISP_RW_OUT_DP0  0x1 /* enum */
+#define          MC_CMD_PARSER_DISP_RW_OUT_DP1  0x2 /* enum */
 
 
 /***********************************/
@@ -7071,6 +7480,24 @@
 #define    MC_CMD_GET_CAPABILITIES_OUT_LEN 20
 /* First word of flags. */
 #define       MC_CMD_GET_CAPABILITIES_OUT_FLAGS1_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_OUT_VPORT_RECONFIGURE_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_OUT_VPORT_RECONFIGURE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_OUT_TX_STRIPING_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_OUT_TX_STRIPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_OUT_VADAPTOR_QUERY_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_OUT_VADAPTOR_QUERY_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_OUT_EVB_PORT_VLAN_RESTRICT_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_OUT_EVB_PORT_VLAN_RESTRICT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_OUT_DRV_ATTACH_PREBOOT_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_OUT_DRV_ATTACH_PREBOOT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_OUT_RX_FORCE_EVENT_MERGING_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_OUT_RX_FORCE_EVENT_MERGING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_OUT_SET_MAC_ENHANCED_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_OUT_SET_MAC_ENHANCED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_WIDTH 1
 #define        MC_CMD_GET_CAPABILITIES_OUT_TX_MAC_SECURITY_FILTERING_LBN 12
 #define        MC_CMD_GET_CAPABILITIES_OUT_TX_MAC_SECURITY_FILTERING_WIDTH 1
 #define        MC_CMD_GET_CAPABILITIES_OUT_ADDITIONAL_RSS_MODES_LBN 13
@@ -7138,6 +7565,8 @@
 #define          MC_CMD_GET_CAPABILITIES_OUT_RXDP_TEST_FW_RX_HDR_SPLIT  0x107
 /* enum: RXDP Test firmware image 8 */
 #define          MC_CMD_GET_CAPABILITIES_OUT_RXDP_TEST_FW_DISABLE_DL  0x108
+/* enum: RXDP Test firmware image 9 */
+#define          MC_CMD_GET_CAPABILITIES_OUT_RXDP_TEST_FW_DOORBELL_DELAY  0x10b
 /* TxDPCPU firmware id. */
 #define       MC_CMD_GET_CAPABILITIES_OUT_TX_DPCPU_FW_ID_OFST 6
 #define       MC_CMD_GET_CAPABILITIES_OUT_TX_DPCPU_FW_ID_LEN 2
@@ -7153,6 +7582,8 @@
 #define          MC_CMD_GET_CAPABILITIES_OUT_TXDP_TEST_FW_TSO_EDIT  0x101
 /* enum: TXDP Test firmware image 2 */
 #define          MC_CMD_GET_CAPABILITIES_OUT_TXDP_TEST_FW_PACKET_EDITS  0x102
+/* enum: TXDP CSR bus test firmware */
+#define          MC_CMD_GET_CAPABILITIES_OUT_TXDP_TEST_FW_CSR  0x103
 #define       MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_VERSION_OFST 8
 #define       MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_VERSION_LEN 2
 #define        MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_VERSION_REV_LBN 0
@@ -7227,6 +7658,258 @@
 /* Licensed capabilities */
 #define       MC_CMD_GET_CAPABILITIES_OUT_LICENSE_CAPABILITIES_OFST 16
 
+/* MC_CMD_GET_CAPABILITIES_V2_IN msgrequest */
+#define    MC_CMD_GET_CAPABILITIES_V2_IN_LEN 0
+
+/* MC_CMD_GET_CAPABILITIES_V2_OUT msgresponse */
+#define    MC_CMD_GET_CAPABILITIES_V2_OUT_LEN 72
+/* First word of flags. */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_FLAGS1_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_VPORT_RECONFIGURE_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_VPORT_RECONFIGURE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_STRIPING_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_STRIPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_VADAPTOR_QUERY_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_VADAPTOR_QUERY_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EVB_PORT_VLAN_RESTRICT_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EVB_PORT_VLAN_RESTRICT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_DRV_ATTACH_PREBOOT_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_DRV_ATTACH_PREBOOT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_FORCE_EVENT_MERGING_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_FORCE_EVENT_MERGING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_SET_MAC_ENHANCED_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_SET_MAC_ENHANCED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_MAC_SECURITY_FILTERING_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_MAC_SECURITY_FILTERING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_ADDITIONAL_RSS_MODES_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_ADDITIONAL_RSS_MODES_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_QBB_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_QBB_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_PACKED_STREAM_VAR_BUFFERS_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_PACKED_STREAM_VAR_BUFFERS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_RSS_LIMITED_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_RSS_LIMITED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_PACKED_STREAM_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_PACKED_STREAM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_INCLUDE_FCS_LBN 18
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_INCLUDE_FCS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_VLAN_INSERTION_LBN 19
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_VLAN_INSERTION_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_VLAN_STRIPPING_LBN 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_VLAN_STRIPPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_PREFIX_LEN_0_LBN 22
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_PREFIX_LEN_0_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_PREFIX_LEN_14_LBN 23
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_PREFIX_LEN_14_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_TIMESTAMP_LBN 24
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_TIMESTAMP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_BATCHING_LBN 25
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_BATCHING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_MCAST_FILTER_CHAINING_LBN 26
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_MCAST_FILTER_CHAINING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_PM_AND_RXDP_COUNTERS_LBN 27
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_PM_AND_RXDP_COUNTERS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_DISABLE_SCATTER_LBN 28
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_DISABLE_SCATTER_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_MCAST_UDP_LOOPBACK_LBN 29
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_MCAST_UDP_LOOPBACK_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EVB_LBN 30
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EVB_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_VXLAN_NVGRE_LBN 31
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_VXLAN_NVGRE_WIDTH 1
+/* RxDPCPU firmware id. */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_RX_DPCPU_FW_ID_OFST 4
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_RX_DPCPU_FW_ID_LEN 2
+/* enum: Standard RXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP  0x0
+/* enum: Low latency RXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_LOW_LATENCY  0x1
+/* enum: Packed stream RXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_PACKED_STREAM  0x2
+/* enum: BIST RXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_BIST  0x10a
+/* enum: RXDP Test firmware image 1 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_FW_TO_MC_CUT_THROUGH  0x101
+/* enum: RXDP Test firmware image 2 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD  0x102
+/* enum: RXDP Test firmware image 3 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD_FIRST  0x103
+/* enum: RXDP Test firmware image 4 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_EVERY_EVENT_BATCHABLE  0x104
+/* enum: RXDP Test firmware image 5 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_BACKPRESSURE  0x105
+/* enum: RXDP Test firmware image 6 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_FW_PACKET_EDITS  0x106
+/* enum: RXDP Test firmware image 7 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_FW_RX_HDR_SPLIT  0x107
+/* enum: RXDP Test firmware image 8 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_FW_DISABLE_DL  0x108
+/* enum: RXDP Test firmware image 9 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_FW_DOORBELL_DELAY  0x10b
+/* TxDPCPU firmware id. */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_TX_DPCPU_FW_ID_OFST 6
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_TX_DPCPU_FW_ID_LEN 2
+/* enum: Standard TXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXDP  0x0
+/* enum: Low latency TXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXDP_LOW_LATENCY  0x1
+/* enum: High packet rate TXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXDP_HIGH_PACKET_RATE  0x3
+/* enum: BIST TXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXDP_BIST  0x12d
+/* enum: TXDP Test firmware image 1 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXDP_TEST_FW_TSO_EDIT  0x101
+/* enum: TXDP Test firmware image 2 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXDP_TEST_FW_PACKET_EDITS  0x102
+/* enum: TXDP CSR bus test firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXDP_TEST_FW_CSR  0x103
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_VERSION_OFST 8
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_VERSION_LEN 2
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_VERSION_REV_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_VERSION_REV_WIDTH 12
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_VERSION_TYPE_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_VERSION_TYPE_WIDTH 4
+/* enum: reserved value - do not use (may indicate alternative interpretation
+ * of REV field in future)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_RESERVED  0x0
+/* enum: Trivial RX PD firmware for early Huntington development (Huntington
+ * development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_FIRST_PKT  0x1
+/* enum: RX PD firmware with approximately Siena-compatible behaviour
+ * (Huntington development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_SIENA_COMPAT  0x2
+/* enum: Virtual switching (full feature) RX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_VSWITCH  0x3
+/* enum: siena_compat variant RX PD firmware using PM rather than MAC
+ * (Huntington development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_SIENA_COMPAT_PM  0x4
+/* enum: Low latency RX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_LOW_LATENCY  0x5
+/* enum: Packed stream RX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_PACKED_STREAM  0x6
+/* enum: RX PD firmware handling layer 2 only for high packet rate performance
+ * tests (Medford development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_LAYER2_PERF  0x7
+/* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE  0xe
+/* enum: RX PD firmware parsing but not filtering network overlay tunnel
+ * encapsulations (Medford development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_TESTFW_ENCAP_PARSING_ONLY  0xf
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_VERSION_OFST 10
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_VERSION_LEN 2
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_VERSION_REV_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_VERSION_REV_WIDTH 12
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_VERSION_TYPE_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_VERSION_TYPE_WIDTH 4
+/* enum: reserved value - do not use (may indicate alternative interpretation
+ * of REV field in future)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_RESERVED  0x0
+/* enum: Trivial TX PD firmware for early Huntington development (Huntington
+ * development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_FIRST_PKT  0x1
+/* enum: TX PD firmware with approximately Siena-compatible behaviour
+ * (Huntington development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_SIENA_COMPAT  0x2
+/* enum: Virtual switching (full feature) TX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_VSWITCH  0x3
+/* enum: siena_compat variant TX PD firmware using PM rather than MAC
+ * (Huntington development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_SIENA_COMPAT_PM  0x4
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_LOW_LATENCY  0x5 /* enum */
+/* enum: TX PD firmware handling layer 2 only for high packet rate performance
+ * tests (Medford development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_LAYER2_PERF  0x7
+/* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE  0xe
+/* Hardware capabilities of NIC */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_HW_CAPABILITIES_OFST 12
+/* Licensed capabilities */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_LICENSE_CAPABILITIES_OFST 16
+/* Second word of flags. Not present on older firmware (check the length). */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_FLAGS2_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_ENCAP_LBN 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_ENCAP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EVQ_TIMER_CTRL_LBN 2
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EVQ_TIMER_CTRL_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EVENT_CUT_THROUGH_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EVENT_CUT_THROUGH_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_CUT_THROUGH_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_CUT_THROUGH_WIDTH 1
+/* Number of FATSOv2 contexts per datapath supported by this NIC. Not present
+ * on older firmware (check the length).
+ */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_N_CONTEXTS_OFST 24
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_N_CONTEXTS_LEN 2
+/* One byte per PF containing the number of the external port assigned to this
+ * PF, indexed by PF number. Special values indicate that a PF is either not
+ * present or not assigned.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_PFS_TO_PORTS_ASSIGNMENT_OFST 26
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_PFS_TO_PORTS_ASSIGNMENT_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_PFS_TO_PORTS_ASSIGNMENT_NUM 16
+/* enum: The caller is not permitted to access information on this PF. */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_ACCESS_NOT_PERMITTED  0xff
+/* enum: PF does not exist. */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_PF_NOT_PRESENT  0xfe
+/* enum: PF does exist but is not assigned to any external port. */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_PF_NOT_ASSIGNED  0xfd
+/* enum: This value indicates that PF is assigned, but it cannot be expressed
+ * in this field. It is intended for a possible future situation where a more
+ * complex scheme of PFs to ports mapping is being used. The future driver
+ * should look for a new field supporting the new scheme. The current/old
+ * driver should treat this value as PF_NOT_ASSIGNED.
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_INCOMPATIBLE_ASSIGNMENT  0xfc
+/* One byte per PF containing the number of its VFs, indexed by PF number. A
+ * special value indicates that a PF is not present.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_VFS_PER_PF_OFST 42
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_VFS_PER_PF_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_VFS_PER_PF_NUM 16
+/* enum: The caller is not permitted to access information on this PF. */
+/*               MC_CMD_GET_CAPABILITIES_V2_OUT_ACCESS_NOT_PERMITTED  0xff */
+/* enum: PF does not exist. */
+/*               MC_CMD_GET_CAPABILITIES_V2_OUT_PF_NOT_PRESENT  0xfe */
+/* Number of VIs available for each external port */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_VIS_PER_PORT_OFST 58
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_VIS_PER_PORT_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_VIS_PER_PORT_NUM 4
+/* Size of RX descriptor cache expressed as binary logarithm The actual size
+ * equals (2 ^ RX_DESC_CACHE_SIZE)
+ */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_RX_DESC_CACHE_SIZE_OFST 66
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_RX_DESC_CACHE_SIZE_LEN 1
+/* Size of TX descriptor cache expressed as binary logarithm The actual size
+ * equals (2 ^ TX_DESC_CACHE_SIZE)
+ */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_TX_DESC_CACHE_SIZE_OFST 67
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_TX_DESC_CACHE_SIZE_LEN 1
+/* Total number of available PIO buffers */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_PIO_BUFFS_OFST 68
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_PIO_BUFFS_LEN 2
+/* Size of a single PIO buffer */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_SIZE_PIO_BUFF_OFST 70
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_SIZE_PIO_BUFF_LEN 2
+
 
 /***********************************/
 /* MC_CMD_V2_EXTN
@@ -7475,6 +8158,25 @@
 
 
 /***********************************/
+/* MC_CMD_VSWITCH_QUERY
+ * read some config of v-switch. For now this command is an empty placeholder.
+ * It may be used to check if a v-switch is connected to a given EVB port (if
+ * not, then the command returns ENOENT).
+ */
+#define MC_CMD_VSWITCH_QUERY 0x63
+
+#define MC_CMD_0x63_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_VSWITCH_QUERY_IN msgrequest */
+#define    MC_CMD_VSWITCH_QUERY_IN_LEN 4
+/* The port to which the v-switch is connected. */
+#define       MC_CMD_VSWITCH_QUERY_IN_UPSTREAM_PORT_ID_OFST 0
+
+/* MC_CMD_VSWITCH_QUERY_OUT msgresponse */
+#define    MC_CMD_VSWITCH_QUERY_OUT_LEN 0
+
+
+/***********************************/
 /* MC_CMD_VPORT_ALLOC
  * allocate a v-port.
  */
@@ -7510,6 +8212,8 @@
 #define       MC_CMD_VPORT_ALLOC_IN_FLAGS_OFST 8
 #define        MC_CMD_VPORT_ALLOC_IN_FLAG_AUTO_PORT_LBN 0
 #define        MC_CMD_VPORT_ALLOC_IN_FLAG_AUTO_PORT_WIDTH 1
+#define        MC_CMD_VPORT_ALLOC_IN_FLAG_VLAN_RESTRICT_LBN 1
+#define        MC_CMD_VPORT_ALLOC_IN_FLAG_VLAN_RESTRICT_WIDTH 1
 /* The number of VLAN tags to insert/remove. An error will be returned if
  * incompatible with the number of VLAN tags specified for the upstream
  * v-switch.
@@ -7561,6 +8265,8 @@
 #define       MC_CMD_VADAPTOR_ALLOC_IN_FLAGS_OFST 8
 #define        MC_CMD_VADAPTOR_ALLOC_IN_FLAG_AUTO_VADAPTOR_LBN 0
 #define        MC_CMD_VADAPTOR_ALLOC_IN_FLAG_AUTO_VADAPTOR_WIDTH 1
+#define        MC_CMD_VADAPTOR_ALLOC_IN_FLAG_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_LBN 1
+#define        MC_CMD_VADAPTOR_ALLOC_IN_FLAG_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_WIDTH 1
 /* The number of VLAN tags to strip on receive */
 #define       MC_CMD_VADAPTOR_ALLOC_IN_NUM_VLANS_OFST 12
 /* The number of VLAN tags to transparently insert/remove. */
@@ -7639,6 +8345,29 @@
 
 
 /***********************************/
+/* MC_CMD_VADAPTOR_QUERY
+ * read some config of v-adaptor.
+ */
+#define MC_CMD_VADAPTOR_QUERY 0x61
+
+#define MC_CMD_0x61_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_VADAPTOR_QUERY_IN msgrequest */
+#define    MC_CMD_VADAPTOR_QUERY_IN_LEN 4
+/* The port to which the v-adaptor is connected. */
+#define       MC_CMD_VADAPTOR_QUERY_IN_UPSTREAM_PORT_ID_OFST 0
+
+/* MC_CMD_VADAPTOR_QUERY_OUT msgresponse */
+#define    MC_CMD_VADAPTOR_QUERY_OUT_LEN 12
+/* The EVB port flags as defined at MC_CMD_VPORT_ALLOC. */
+#define       MC_CMD_VADAPTOR_QUERY_OUT_PORT_FLAGS_OFST 0
+/* The v-adaptor flags as defined at MC_CMD_VADAPTOR_ALLOC. */
+#define       MC_CMD_VADAPTOR_QUERY_OUT_VADAPTOR_FLAGS_OFST 4
+/* The number of VLAN tags that may still be added */
+#define       MC_CMD_VADAPTOR_QUERY_OUT_NUM_AVAILABLE_VLAN_TAGS_OFST 8
+
+
+/***********************************/
 /* MC_CMD_EVB_PORT_ASSIGN
  * assign a port to a PCI function.
  */
@@ -7875,10 +8604,17 @@
 #define    MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_LEN 8
 /* The handle of the RSS context */
 #define       MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_RSS_CONTEXT_ID_OFST 0
-/* Hash control flags. The _EN bits are always supported. The _MODE bits only
- * work when the firmware reports ADDITIONAL_RSS_MODES in
- * MC_CMD_GET_CAPABILITIES and override the _EN bits if any of them are not 0.
- * See the RSS_MODE structure for the meaning of the mode bits.
+/* Hash control flags. The _EN bits are always supported, but new modes are
+ * available when ADDITIONAL_RSS_MODES is reported by MC_CMD_GET_CAPABILITIES:
+ * in this case, the MODE fields may be set to non-zero values, and will take
+ * effect regardless of the settings of the _EN flags. See the RSS_MODE
+ * structure for the meaning of the mode bits. Drivers must check the
+ * capability before trying to set any _MODE fields, as older firmware will
+ * reject any attempt to set the FLAGS field to a value > 0xff with EINVAL. In
+ * the case where all the _MODE flags are zero, the _EN flags take effect,
+ * providing backward compatibility for existing drivers. (Setting all _MODE
+ * *and* all _EN flags to zero is valid, to disable RSS spreading for that
+ * particular packet type.)
  */
 #define       MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_FLAGS_OFST 4
 #define        MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_TOEPLITZ_IPV4_EN_LBN 0
@@ -7923,11 +8659,18 @@
 
 /* MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT msgresponse */
 #define    MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_LEN 8
-/* Hash control flags. If any _MODE bits are non-zero (which will only be true
- * when the firmware reports ADDITIONAL_RSS_MODES) then the _EN bits should be
- * disregarded (but are guaranteed to be consistent with the _MODE bits if
- * RSS_CONTEXT_SET_FLAGS has never been called for this context since it was
- * allocated).
+/* Hash control flags. If all _MODE bits are zero (which will always be true
+ * for older firmware which does not report the ADDITIONAL_RSS_MODES
+ * capability), the _EN bits report the state. If any _MODE bits are non-zero
+ * (which will only be true when the firmware reports ADDITIONAL_RSS_MODES)
+ * then the _EN bits should be disregarded, although the _MODE flags are
+ * guaranteed to be consistent with the _EN flags for a freshly-allocated RSS
+ * context and in the case where the _EN flags were used in the SET. This
+ * provides backward compatibility: old drivers will not be attempting to
+ * derive any meaning from the _MODE bits (and can never set them to any value
+ * not representable by the _EN bits); new drivers can always determine the
+ * mode by looking only at the _MODE bits; the value returned by a GET can
+ * always be used for a SET regardless of old/new driver vs. old/new firmware.
  */
 #define       MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_FLAGS_OFST 4
 #define        MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_TOEPLITZ_IPV4_EN_LBN 0
@@ -8155,6 +8898,74 @@
 
 
 /***********************************/
+/* MC_CMD_VPORT_RECONFIGURE
+ * Replace VLAN tags and/or MAC addresses of an existing v-port. If the v-port
+ * has already been passed to another function (v-port's user), then that
+ * function will be reset before applying the changes.
+ */
+#define MC_CMD_VPORT_RECONFIGURE 0xeb
+
+#define MC_CMD_0xeb_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_VPORT_RECONFIGURE_IN msgrequest */
+#define    MC_CMD_VPORT_RECONFIGURE_IN_LEN 44
+/* The handle of the v-port */
+#define       MC_CMD_VPORT_RECONFIGURE_IN_VPORT_ID_OFST 0
+/* Flags requesting what should be changed. */
+#define       MC_CMD_VPORT_RECONFIGURE_IN_FLAGS_OFST 4
+#define        MC_CMD_VPORT_RECONFIGURE_IN_REPLACE_VLAN_TAGS_LBN 0
+#define        MC_CMD_VPORT_RECONFIGURE_IN_REPLACE_VLAN_TAGS_WIDTH 1
+#define        MC_CMD_VPORT_RECONFIGURE_IN_REPLACE_MACADDRS_LBN 1
+#define        MC_CMD_VPORT_RECONFIGURE_IN_REPLACE_MACADDRS_WIDTH 1
+/* The number of VLAN tags to insert/remove. An error will be returned if
+ * incompatible with the number of VLAN tags specified for the upstream
+ * v-switch.
+ */
+#define       MC_CMD_VPORT_RECONFIGURE_IN_NUM_VLAN_TAGS_OFST 8
+/* The actual VLAN tags to insert/remove */
+#define       MC_CMD_VPORT_RECONFIGURE_IN_VLAN_TAGS_OFST 12
+#define        MC_CMD_VPORT_RECONFIGURE_IN_VLAN_TAG_0_LBN 0
+#define        MC_CMD_VPORT_RECONFIGURE_IN_VLAN_TAG_0_WIDTH 16
+#define        MC_CMD_VPORT_RECONFIGURE_IN_VLAN_TAG_1_LBN 16
+#define        MC_CMD_VPORT_RECONFIGURE_IN_VLAN_TAG_1_WIDTH 16
+/* The number of MAC addresses to add */
+#define       MC_CMD_VPORT_RECONFIGURE_IN_NUM_MACADDRS_OFST 16
+/* MAC addresses to add */
+#define       MC_CMD_VPORT_RECONFIGURE_IN_MACADDRS_OFST 20
+#define       MC_CMD_VPORT_RECONFIGURE_IN_MACADDRS_LEN 6
+#define       MC_CMD_VPORT_RECONFIGURE_IN_MACADDRS_NUM 4
+
+/* MC_CMD_VPORT_RECONFIGURE_OUT msgresponse */
+#define    MC_CMD_VPORT_RECONFIGURE_OUT_LEN 4
+#define       MC_CMD_VPORT_RECONFIGURE_OUT_FLAGS_OFST 0
+#define        MC_CMD_VPORT_RECONFIGURE_OUT_RESET_DONE_LBN 0
+#define        MC_CMD_VPORT_RECONFIGURE_OUT_RESET_DONE_WIDTH 1
+
+
+/***********************************/
+/* MC_CMD_EVB_PORT_QUERY
+ * read some config of v-port.
+ */
+#define MC_CMD_EVB_PORT_QUERY 0x62
+
+#define MC_CMD_0x62_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_EVB_PORT_QUERY_IN msgrequest */
+#define    MC_CMD_EVB_PORT_QUERY_IN_LEN 4
+/* The handle of the v-port */
+#define       MC_CMD_EVB_PORT_QUERY_IN_PORT_ID_OFST 0
+
+/* MC_CMD_EVB_PORT_QUERY_OUT msgresponse */
+#define    MC_CMD_EVB_PORT_QUERY_OUT_LEN 8
+/* The EVB port flags as defined at MC_CMD_VPORT_ALLOC. */
+#define       MC_CMD_EVB_PORT_QUERY_OUT_PORT_FLAGS_OFST 0
+/* The number of VLAN tags that may be used on a v-adaptor connected to this
+ * EVB port.
+ */
+#define       MC_CMD_EVB_PORT_QUERY_OUT_NUM_AVAILABLE_VLAN_TAGS_OFST 4
+
+
+/***********************************/
 /* MC_CMD_DUMP_BUFTBL_ENTRIES
  * Dump buffer table entries, mainly for command client debug use. Dumps
  * absolute entries, and does not use chunk handles. All entries must be in
@@ -8196,6 +9007,14 @@
 #define       MC_CMD_SET_RXDP_CONFIG_IN_DATA_OFST 0
 #define        MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_DMA_LBN 0
 #define        MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_DMA_WIDTH 1
+#define        MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_LEN_LBN 1
+#define        MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_LEN_WIDTH 2
+/* enum: pad to 64 bytes */
+#define          MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_64  0x0
+/* enum: pad to 128 bytes (Medford only) */
+#define          MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_128  0x1
+/* enum: pad to 256 bytes (Medford only) */
+#define          MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_256   0x2
 
 /* MC_CMD_SET_RXDP_CONFIG_OUT msgresponse */
 #define    MC_CMD_SET_RXDP_CONFIG_OUT_LEN 0
@@ -8217,6 +9036,10 @@
 #define       MC_CMD_GET_RXDP_CONFIG_OUT_DATA_OFST 0
 #define        MC_CMD_GET_RXDP_CONFIG_OUT_PAD_HOST_DMA_LBN 0
 #define        MC_CMD_GET_RXDP_CONFIG_OUT_PAD_HOST_DMA_WIDTH 1
+#define        MC_CMD_GET_RXDP_CONFIG_OUT_PAD_HOST_LEN_LBN 1
+#define        MC_CMD_GET_RXDP_CONFIG_OUT_PAD_HOST_LEN_WIDTH 2
+/*             Enum values, see field(s): */
+/*                MC_CMD_SET_RXDP_CONFIG/MC_CMD_SET_RXDP_CONFIG_IN/PAD_HOST_LEN */
 
 
 /***********************************/
@@ -8788,32 +9611,38 @@
 #define       MC_CMD_KR_TUNE_RXEQ_GET_OUT_PARAM_MAXNUM 63
 #define        MC_CMD_KR_TUNE_RXEQ_GET_OUT_PARAM_ID_LBN 0
 #define        MC_CMD_KR_TUNE_RXEQ_GET_OUT_PARAM_ID_WIDTH 8
-/* enum: Attenuation (0-15, TBD for Medford) */
+/* enum: Attenuation (0-15, Huntington) */
 #define          MC_CMD_KR_TUNE_RXEQ_GET_OUT_ATT  0x0
-/* enum: CTLE Boost (0-15, TBD for Medford) */
+/* enum: CTLE Boost (0-15, Huntington) */
 #define          MC_CMD_KR_TUNE_RXEQ_GET_OUT_BOOST  0x1
-/* enum: Edge DFE Tap1 (0 - max negative, 64 - zero, 127 - max positive, TBD
- * for Medford)
+/* enum: Edge DFE Tap1 (Huntington - 0 - max negative, 64 - zero, 127 - max
+ * positive, Medford - 0-31)
  */
 #define          MC_CMD_KR_TUNE_RXEQ_GET_OUT_EDFE_TAP1  0x2
-/* enum: Edge DFE Tap2 (0 - max negative, 32 - zero, 63 - max positive, TBD for
- * Medford)
+/* enum: Edge DFE Tap2 (Huntington - 0 - max negative, 32 - zero, 63 - max
+ * positive, Medford - 0-31)
  */
 #define          MC_CMD_KR_TUNE_RXEQ_GET_OUT_EDFE_TAP2  0x3
-/* enum: Edge DFE Tap3 (0 - max negative, 32 - zero, 63 - max positive, TBD for
- * Medford)
+/* enum: Edge DFE Tap3 (Huntington - 0 - max negative, 32 - zero, 63 - max
+ * positive, Medford - 0-16)
  */
 #define          MC_CMD_KR_TUNE_RXEQ_GET_OUT_EDFE_TAP3  0x4
-/* enum: Edge DFE Tap4 (0 - max negative, 32 - zero, 63 - max positive, TBD for
- * Medford)
+/* enum: Edge DFE Tap4 (Huntington - 0 - max negative, 32 - zero, 63 - max
+ * positive, Medford - 0-16)
  */
 #define          MC_CMD_KR_TUNE_RXEQ_GET_OUT_EDFE_TAP4  0x5
-/* enum: Edge DFE Tap5 (0 - max negative, 32 - zero, 63 - max positive, TBD for
- * Medford)
+/* enum: Edge DFE Tap5 (Huntington - 0 - max negative, 32 - zero, 63 - max
+ * positive, Medford - 0-16)
  */
 #define          MC_CMD_KR_TUNE_RXEQ_GET_OUT_EDFE_TAP5  0x6
-/* enum: Edge DFE DLEV (TBD for Medford) */
+/* enum: Edge DFE DLEV (0-128 for Medford) */
 #define          MC_CMD_KR_TUNE_RXEQ_GET_OUT_EDFE_DLEV  0x7
+/* enum: Variable Gain Amplifier (0-15, Medford) */
+#define          MC_CMD_KR_TUNE_RXEQ_GET_OUT_VGA  0x8
+/* enum: CTLE EQ Capacitor (0-15, Medford) */
+#define          MC_CMD_KR_TUNE_RXEQ_GET_OUT_CTLE_EQC  0x9
+/* enum: CTLE EQ Resistor (0-7, Medford) */
+#define          MC_CMD_KR_TUNE_RXEQ_GET_OUT_CTLE_EQRES  0xa
 #define        MC_CMD_KR_TUNE_RXEQ_GET_OUT_PARAM_LANE_LBN 8
 #define        MC_CMD_KR_TUNE_RXEQ_GET_OUT_PARAM_LANE_WIDTH 3
 #define          MC_CMD_KR_TUNE_RXEQ_GET_OUT_LANE_0  0x0 /* enum */
@@ -8885,26 +9714,32 @@
 #define       MC_CMD_KR_TUNE_TXEQ_GET_OUT_PARAM_MAXNUM 63
 #define        MC_CMD_KR_TUNE_TXEQ_GET_OUT_PARAM_ID_LBN 0
 #define        MC_CMD_KR_TUNE_TXEQ_GET_OUT_PARAM_ID_WIDTH 8
-/* enum: TX Amplitude */
+/* enum: TX Amplitude (Huntington, Medford) */
 #define          MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_LEV  0x0
-/* enum: De-Emphasis Tap1 Magnitude (0-7) */
+/* enum: De-Emphasis Tap1 Magnitude (0-7) (Huntington) */
 #define          MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_MODE  0x1
 /* enum: De-Emphasis Tap1 Fine */
 #define          MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_DTLEV  0x2
-/* enum: De-Emphasis Tap2 Magnitude (0-6) */
+/* enum: De-Emphasis Tap2 Magnitude (0-6) (Huntington) */
 #define          MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_D2  0x3
-/* enum: De-Emphasis Tap2 Fine */
+/* enum: De-Emphasis Tap2 Fine (Huntington) */
 #define          MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_D2TLEV  0x4
-/* enum: Pre-Emphasis Magnitude */
+/* enum: Pre-Emphasis Magnitude (Huntington) */
 #define          MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_E  0x5
-/* enum: Pre-Emphasis Fine */
+/* enum: Pre-Emphasis Fine (Huntington) */
 #define          MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_ETLEV  0x6
-/* enum: TX Slew Rate Coarse control */
+/* enum: TX Slew Rate Coarse control (Huntington) */
 #define          MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_PREDRV_DLY  0x7
-/* enum: TX Slew Rate Fine control */
+/* enum: TX Slew Rate Fine control (Huntington) */
 #define          MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_SR_SET  0x8
-/* enum: TX Termination Impedance control */
+/* enum: TX Termination Impedance control (Huntington) */
 #define          MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_RT_SET  0x9
+/* enum: TX Amplitude Fine control (Medford) */
+#define          MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_LEV_FINE  0xa
+/* enum: Pre-shoot Tap (Medford) */
+#define          MC_CMD_KR_TUNE_TXEQ_GET_OUT_TAP_ADV  0xb
+/* enum: De-emphasis Tap (Medford) */
+#define          MC_CMD_KR_TUNE_TXEQ_GET_OUT_TAP_DLY  0xc
 #define        MC_CMD_KR_TUNE_TXEQ_GET_OUT_PARAM_LANE_LBN 8
 #define        MC_CMD_KR_TUNE_TXEQ_GET_OUT_PARAM_LANE_WIDTH 3
 #define          MC_CMD_KR_TUNE_TXEQ_GET_OUT_LANE_0  0x0 /* enum */
@@ -9086,8 +9921,16 @@
 #define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_DFE_TAP4  0x5
 /* enum: DFE Tap5 (0 - max negative, 32 - zero, 63 - max positive) */
 #define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_DFE_TAP5  0x6
+/* enum: DFE DLev */
+#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_DFE_DLEV  0x7
+/* enum: Figure of Merit */
+#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_FOM  0x8
+/* enum: CTLE EQ Capacitor (HF Gain) */
+#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_CTLE_EQC  0x9
+/* enum: CTLE EQ Resistor (DC Gain) */
+#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_CTLE_EQRES  0xa
 #define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_LANE_LBN 8
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_LANE_WIDTH 4
+#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_LANE_WIDTH 5
 #define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_0  0x0 /* enum */
 #define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_1  0x1 /* enum */
 #define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_2  0x2 /* enum */
@@ -9096,12 +9939,57 @@
 #define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_5  0x5 /* enum */
 #define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_6  0x6 /* enum */
 #define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_7  0x7 /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_ALL  0x8 /* enum */
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_RESERVED_LBN 12
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_RESERVED_WIDTH 12
+#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_8  0x8 /* enum */
+#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_9  0x9 /* enum */
+#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_10  0xa /* enum */
+#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_11  0xb /* enum */
+#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_12  0xc /* enum */
+#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_13  0xd /* enum */
+#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_14  0xe /* enum */
+#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_15  0xf /* enum */
+#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_ALL  0x10 /* enum */
+#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_AUTOCAL_LBN 13
+#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_AUTOCAL_WIDTH 1
+#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_RESERVED_LBN 14
+#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_RESERVED_WIDTH 10
 #define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_CURRENT_LBN 24
 #define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_CURRENT_WIDTH 8
 
+/* MC_CMD_PCIE_TUNE_RXEQ_SET_IN msgrequest */
+#define    MC_CMD_PCIE_TUNE_RXEQ_SET_IN_LENMIN 8
+#define    MC_CMD_PCIE_TUNE_RXEQ_SET_IN_LENMAX 252
+#define    MC_CMD_PCIE_TUNE_RXEQ_SET_IN_LEN(num) (4+4*(num))
+/* Requested operation */
+#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PCIE_TUNE_OP_OFST 0
+#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PCIE_TUNE_OP_LEN 1
+/* Align the arguments to 32 bits */
+#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PCIE_TUNE_RSVD_OFST 1
+#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PCIE_TUNE_RSVD_LEN 3
+/* RXEQ Parameter */
+#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_OFST 4
+#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_LEN 4
+#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_MINNUM 1
+#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_MAXNUM 62
+#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_ID_LBN 0
+#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_ID_WIDTH 8
+/*             Enum values, see field(s): */
+/*                MC_CMD_PCIE_TUNE_RXEQ_GET_OUT/PARAM_ID */
+#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_LANE_LBN 8
+#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_LANE_WIDTH 5
+/*             Enum values, see field(s): */
+/*                MC_CMD_PCIE_TUNE_RXEQ_GET_OUT/PARAM_LANE */
+#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_AUTOCAL_LBN 13
+#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_AUTOCAL_WIDTH 1
+#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_RESERVED_LBN 14
+#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_RESERVED_WIDTH 2
+#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_INITIAL_LBN 16
+#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_INITIAL_WIDTH 8
+#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_RESERVED2_LBN 24
+#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_RESERVED2_WIDTH 8
+
+/* MC_CMD_PCIE_TUNE_RXEQ_SET_OUT msgresponse */
+#define    MC_CMD_PCIE_TUNE_RXEQ_SET_OUT_LEN 0
+
 /* MC_CMD_PCIE_TUNE_TXEQ_GET_IN msgrequest */
 #define    MC_CMD_PCIE_TUNE_TXEQ_GET_IN_LEN 4
 /* Requested operation */
@@ -9176,6 +10064,7 @@
 /***********************************/
 /* MC_CMD_LICENSING
  * Operations on the NVRAM_PARTITION_TYPE_LICENSE application license partition
+ * - not used for V3 licensing
  */
 #define MC_CMD_LICENSING 0xf3
 
@@ -9220,6 +10109,93 @@
 
 
 /***********************************/
+/* MC_CMD_LICENSING_V3
+ * Operations on the NVRAM_PARTITION_TYPE_LICENSE application license partition
+ * - V3 licensing (Medford)
+ */
+#define MC_CMD_LICENSING_V3 0xd0
+
+#define MC_CMD_0xd0_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_LICENSING_V3_IN msgrequest */
+#define    MC_CMD_LICENSING_V3_IN_LEN 4
+/* identifies the type of operation requested */
+#define       MC_CMD_LICENSING_V3_IN_OP_OFST 0
+/* enum: re-read and apply licenses after a license key partition update; note
+ * that this operation returns a zero-length response
+ */
+#define          MC_CMD_LICENSING_V3_IN_OP_UPDATE_LICENSE  0x0
+/* enum: report counts of installed licenses */
+#define          MC_CMD_LICENSING_V3_IN_OP_REPORT_LICENSE  0x1
+
+/* MC_CMD_LICENSING_V3_OUT msgresponse */
+#define    MC_CMD_LICENSING_V3_OUT_LEN 88
+/* count of keys which are valid */
+#define       MC_CMD_LICENSING_V3_OUT_VALID_KEYS_OFST 0
+/* sum of UNVERIFIABLE_KEYS + WRONG_NODE_KEYS (for compatibility with
+ * MC_CMD_FC_OP_LICENSE)
+ */
+#define       MC_CMD_LICENSING_V3_OUT_INVALID_KEYS_OFST 4
+/* count of keys which are invalid due to being unverifiable */
+#define       MC_CMD_LICENSING_V3_OUT_UNVERIFIABLE_KEYS_OFST 8
+/* count of keys which are invalid due to being for the wrong node */
+#define       MC_CMD_LICENSING_V3_OUT_WRONG_NODE_KEYS_OFST 12
+/* licensing state (for diagnostics; the exact meaning of the bits in this
+ * field are private to the firmware)
+ */
+#define       MC_CMD_LICENSING_V3_OUT_LICENSING_STATE_OFST 16
+/* licensing subsystem self-test report (for manftest) */
+#define       MC_CMD_LICENSING_V3_OUT_LICENSING_SELF_TEST_OFST 20
+/* enum: licensing subsystem self-test failed */
+#define          MC_CMD_LICENSING_V3_OUT_SELF_TEST_FAIL  0x0
+/* enum: licensing subsystem self-test passed */
+#define          MC_CMD_LICENSING_V3_OUT_SELF_TEST_PASS  0x1
+/* bitmask of licensed applications */
+#define       MC_CMD_LICENSING_V3_OUT_LICENSED_APPS_OFST 24
+#define       MC_CMD_LICENSING_V3_OUT_LICENSED_APPS_LEN 8
+#define       MC_CMD_LICENSING_V3_OUT_LICENSED_APPS_LO_OFST 24
+#define       MC_CMD_LICENSING_V3_OUT_LICENSED_APPS_HI_OFST 28
+/* reserved for future use */
+#define       MC_CMD_LICENSING_V3_OUT_RESERVED_0_OFST 32
+#define       MC_CMD_LICENSING_V3_OUT_RESERVED_0_LEN 24
+/* bitmask of licensed features */
+#define       MC_CMD_LICENSING_V3_OUT_LICENSED_FEATURES_OFST 56
+#define       MC_CMD_LICENSING_V3_OUT_LICENSED_FEATURES_LEN 8
+#define       MC_CMD_LICENSING_V3_OUT_LICENSED_FEATURES_LO_OFST 56
+#define       MC_CMD_LICENSING_V3_OUT_LICENSED_FEATURES_HI_OFST 60
+/* reserved for future use */
+#define       MC_CMD_LICENSING_V3_OUT_RESERVED_1_OFST 64
+#define       MC_CMD_LICENSING_V3_OUT_RESERVED_1_LEN 24
+
+
+/***********************************/
+/* MC_CMD_LICENSING_GET_ID_V3
+ * Get ID and type from the NVRAM_PARTITION_TYPE_LICENSE application license
+ * partition - V3 licensing (Medford)
+ */
+#define MC_CMD_LICENSING_GET_ID_V3 0xd1
+
+#define MC_CMD_0xd1_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_LICENSING_GET_ID_V3_IN msgrequest */
+#define    MC_CMD_LICENSING_GET_ID_V3_IN_LEN 0
+
+/* MC_CMD_LICENSING_GET_ID_V3_OUT msgresponse */
+#define    MC_CMD_LICENSING_GET_ID_V3_OUT_LENMIN 8
+#define    MC_CMD_LICENSING_GET_ID_V3_OUT_LENMAX 252
+#define    MC_CMD_LICENSING_GET_ID_V3_OUT_LEN(num) (8+1*(num))
+/* type of license (eg 3) */
+#define       MC_CMD_LICENSING_GET_ID_V3_OUT_LICENSE_TYPE_OFST 0
+/* length of the license ID (in bytes) */
+#define       MC_CMD_LICENSING_GET_ID_V3_OUT_LICENSE_ID_LENGTH_OFST 4
+/* the unique license ID of the adapter */
+#define       MC_CMD_LICENSING_GET_ID_V3_OUT_LICENSE_ID_OFST 8
+#define       MC_CMD_LICENSING_GET_ID_V3_OUT_LICENSE_ID_LEN 1
+#define       MC_CMD_LICENSING_GET_ID_V3_OUT_LICENSE_ID_MINNUM 0
+#define       MC_CMD_LICENSING_GET_ID_V3_OUT_LICENSE_ID_MAXNUM 244
+
+
+/***********************************/
 /* MC_CMD_MC2MC_PROXY
  * Execute an arbitrary MCDI command on the slave MC of a dual-core device.
  * This will fail on a single-core system.
@@ -9239,7 +10215,7 @@
 /* MC_CMD_GET_LICENSED_APP_STATE
  * Query the state of an individual licensed application. (Note that the actual
  * state may be invalidated by the MC_CMD_LICENSING OP_UPDATE_LICENSE operation
- * or a reboot of the MC.)
+ * or a reboot of the MC.) Not used for V3 licensing
  */
 #define MC_CMD_GET_LICENSED_APP_STATE 0xf5
 
@@ -9261,8 +10237,68 @@
 
 
 /***********************************/
+/* MC_CMD_GET_LICENSED_V3_APP_STATE
+ * Query the state of an individual licensed application. (Note that the actual
+ * state may be invalidated by the MC_CMD_LICENSING_V3 OP_UPDATE_LICENSE
+ * operation or a reboot of the MC.) Used for V3 licensing (Medford)
+ */
+#define MC_CMD_GET_LICENSED_V3_APP_STATE 0xd2
+
+#define MC_CMD_0xd2_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_GET_LICENSED_V3_APP_STATE_IN msgrequest */
+#define    MC_CMD_GET_LICENSED_V3_APP_STATE_IN_LEN 8
+/* application ID to query (LICENSED_V3_APPS_xxx) expressed as a single bit
+ * mask
+ */
+#define       MC_CMD_GET_LICENSED_V3_APP_STATE_IN_APP_ID_OFST 0
+#define       MC_CMD_GET_LICENSED_V3_APP_STATE_IN_APP_ID_LEN 8
+#define       MC_CMD_GET_LICENSED_V3_APP_STATE_IN_APP_ID_LO_OFST 0
+#define       MC_CMD_GET_LICENSED_V3_APP_STATE_IN_APP_ID_HI_OFST 4
+
+/* MC_CMD_GET_LICENSED_V3_APP_STATE_OUT msgresponse */
+#define    MC_CMD_GET_LICENSED_V3_APP_STATE_OUT_LEN 4
+/* state of this application */
+#define       MC_CMD_GET_LICENSED_V3_APP_STATE_OUT_STATE_OFST 0
+/* enum: no (or invalid) license is present for the application */
+#define          MC_CMD_GET_LICENSED_V3_APP_STATE_OUT_NOT_LICENSED  0x0
+/* enum: a valid license is present for the application */
+#define          MC_CMD_GET_LICENSED_V3_APP_STATE_OUT_LICENSED  0x1
+
+
+/***********************************/
+/* MC_CMD_GET_LICENSED_V3_FEATURE_STATES
+ * Query the state of an one or more licensed features. (Note that the actual
+ * state may be invalidated by the MC_CMD_LICENSING_V3 OP_UPDATE_LICENSE
+ * operation or a reboot of the MC.) Used for V3 licensing (Medford)
+ */
+#define MC_CMD_GET_LICENSED_V3_FEATURE_STATES 0xd3
+
+#define MC_CMD_0xd3_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN msgrequest */
+#define    MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN_LEN 8
+/* features to query (LICENSED_V3_FEATURES_xxx) expressed as a mask with one or
+ * more bits set
+ */
+#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN_FEATURES_OFST 0
+#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN_FEATURES_LEN 8
+#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN_FEATURES_LO_OFST 0
+#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN_FEATURES_HI_OFST 4
+
+/* MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT msgresponse */
+#define    MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT_LEN 8
+/* states of these features - bit set for licensed, clear for not licensed */
+#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT_STATES_OFST 0
+#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT_STATES_LEN 8
+#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT_STATES_LO_OFST 0
+#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT_STATES_HI_OFST 4
+
+
+/***********************************/
 /* MC_CMD_LICENSED_APP_OP
- * Perform an action for an individual licensed application.
+ * Perform an action for an individual licensed application - not used for V3
+ * licensing.
  */
 #define MC_CMD_LICENSED_APP_OP 0xf6
 
@@ -9328,6 +10364,67 @@
 
 
 /***********************************/
+/* MC_CMD_LICENSED_V3_VALIDATE_APP
+ * Perform validation for an individual licensed application - V3 licensing
+ * (Medford)
+ */
+#define MC_CMD_LICENSED_V3_VALIDATE_APP 0xd4
+
+#define MC_CMD_0xd4_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_LICENSED_V3_VALIDATE_APP_IN msgrequest */
+#define    MC_CMD_LICENSED_V3_VALIDATE_APP_IN_LEN 72
+/* application ID expressed as a single bit mask */
+#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_OFST 0
+#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_LEN 8
+#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_LO_OFST 0
+#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_HI_OFST 4
+/* challenge for validation */
+#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_CHALLENGE_OFST 8
+#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_CHALLENGE_LEN 64
+
+/* MC_CMD_LICENSED_V3_VALIDATE_APP_OUT msgresponse */
+#define    MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_LEN 72
+/* application expiry time */
+#define       MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_EXPIRY_TIME_OFST 0
+/* application expiry units */
+#define       MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_EXPIRY_UNITS_OFST 4
+/* enum: expiry units are accounting units */
+#define          MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_EXPIRY_UNIT_ACC  0x0
+/* enum: expiry units are calendar days */
+#define          MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_EXPIRY_UNIT_DAYS  0x1
+/* validation response to challenge */
+#define       MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_RESPONSE_OFST 8
+#define       MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_RESPONSE_LEN 64
+
+
+/***********************************/
+/* MC_CMD_LICENSED_V3_MASK_FEATURES
+ * Mask features - V3 licensing (Medford)
+ */
+#define MC_CMD_LICENSED_V3_MASK_FEATURES 0xd5
+
+#define MC_CMD_0xd5_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_LICENSED_V3_MASK_FEATURES_IN msgrequest */
+#define    MC_CMD_LICENSED_V3_MASK_FEATURES_IN_LEN 12
+/* mask to be applied to features to be changed */
+#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_MASK_OFST 0
+#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_MASK_LEN 8
+#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_MASK_LO_OFST 0
+#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_MASK_HI_OFST 4
+/* whether to turn on or turn off the masked features */
+#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_FLAG_OFST 8
+/* enum: turn the features off */
+#define          MC_CMD_LICENSED_V3_MASK_FEATURES_IN_OFF  0x0
+/* enum: turn the features back on */
+#define          MC_CMD_LICENSED_V3_MASK_FEATURES_IN_ON  0x1
+
+/* MC_CMD_LICENSED_V3_MASK_FEATURES_OUT msgresponse */
+#define    MC_CMD_LICENSED_V3_MASK_FEATURES_OUT_LEN 0
+
+
+/***********************************/
 /* MC_CMD_SET_PORT_SNIFF_CONFIG
  * Configure RX port sniffing for the physical port associated with the calling
  * function. Only a privileged function may change the port sniffing
@@ -9696,12 +10793,27 @@
 #define          MC_CMD_PRIVILEGE_MASK_IN_GRP_ONLOAD            0x4 /* enum */
 #define          MC_CMD_PRIVILEGE_MASK_IN_GRP_PTP               0x8 /* enum */
 #define          MC_CMD_PRIVILEGE_MASK_IN_GRP_INSECURE_FILTERS  0x10 /* enum */
-#define          MC_CMD_PRIVILEGE_MASK_IN_GRP_MAC_SPOOFING      0x20 /* enum */
+/* enum: Deprecated. Equivalent to MAC_SPOOFING_TX combined with CHANGE_MAC. */
+#define          MC_CMD_PRIVILEGE_MASK_IN_GRP_MAC_SPOOFING      0x20
 #define          MC_CMD_PRIVILEGE_MASK_IN_GRP_UNICAST           0x40 /* enum */
 #define          MC_CMD_PRIVILEGE_MASK_IN_GRP_MULTICAST         0x80 /* enum */
 #define          MC_CMD_PRIVILEGE_MASK_IN_GRP_BROADCAST         0x100 /* enum */
 #define          MC_CMD_PRIVILEGE_MASK_IN_GRP_ALL_MULTICAST     0x200 /* enum */
 #define          MC_CMD_PRIVILEGE_MASK_IN_GRP_PROMISCUOUS       0x400 /* enum */
+/* enum: Allows to set the TX packets' source MAC address to any arbitrary MAC
+ * adress.
+ */
+#define          MC_CMD_PRIVILEGE_MASK_IN_GRP_MAC_SPOOFING_TX   0x800
+/* enum: Privilege that allows a Function to change the MAC address configured
+ * in its associated vAdapter/vPort.
+ */
+#define          MC_CMD_PRIVILEGE_MASK_IN_GRP_CHANGE_MAC        0x1000
+/* enum: Privilege that allows a Function to install filters that specify VLANs
+ * that are not in the permit list for the associated vPort. This privilege is
+ * primarily to support ESX where vPorts are created that restrict traffic to
+ * only a set of permitted VLANs. See the vPort flag FLAG_VLAN_RESTRICT.
+ */
+#define          MC_CMD_PRIVILEGE_MASK_IN_GRP_UNRESTRICTED_VLAN  0x2000
 /* enum: Set this bit to indicate that a new privilege mask is to be set,
  * otherwise the command will only read the existing mask.
  */
@@ -9951,7 +11063,7 @@
 /* Sector type */
 #define       MC_CMD_XPM_WRITE_SECTOR_IN_TYPE_OFST 4
 /*            Enum values, see field(s): */
-/*               MC_CMD_XPM_READ_SECTOR_OUT/TYPE */
+/*               MC_CMD_XPM_READ_SECTOR/MC_CMD_XPM_READ_SECTOR_OUT/TYPE */
 /* Sector size */
 #define       MC_CMD_XPM_WRITE_SECTOR_IN_SIZE_OFST 8
 /* Sector data */
@@ -10067,4 +11179,123 @@
 #define    MC_CMD_XPM_WRITE_TEST_OUT_LEN 0
 
 
+/***********************************/
+/* MC_CMD_EXEC_SIGNED
+ * Check the CMAC of the contents of IMEM and DMEM against the value supplied
+ * and if correct begin execution from the start of IMEM. The caller supplies a
+ * key ID, the length of IMEM and DMEM to validate and the expected CMAC. CMAC
+ * computation runs from the start of IMEM, and from the start of DMEM + 16k,
+ * to match flash booting. The command will respond with EINVAL if the CMAC
+ * does match, otherwise it will respond with success before it jumps to IMEM.
+ */
+#define MC_CMD_EXEC_SIGNED 0x10c
+
+#define MC_CMD_0x10c_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
+/* MC_CMD_EXEC_SIGNED_IN msgrequest */
+#define    MC_CMD_EXEC_SIGNED_IN_LEN 28
+/* the length of code to include in the CMAC */
+#define       MC_CMD_EXEC_SIGNED_IN_CODELEN_OFST 0
+/* the length of date to include in the CMAC */
+#define       MC_CMD_EXEC_SIGNED_IN_DATALEN_OFST 4
+/* the XPM sector containing the key to use */
+#define       MC_CMD_EXEC_SIGNED_IN_KEYSECTOR_OFST 8
+/* the expected CMAC value */
+#define       MC_CMD_EXEC_SIGNED_IN_CMAC_OFST 12
+#define       MC_CMD_EXEC_SIGNED_IN_CMAC_LEN 16
+
+/* MC_CMD_EXEC_SIGNED_OUT msgresponse */
+#define    MC_CMD_EXEC_SIGNED_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_PREPARE_SIGNED
+ * Prepare to upload a signed image. This will scrub the specified length of
+ * the data region, which must be at least as large as the DATALEN supplied to
+ * MC_CMD_EXEC_SIGNED.
+ */
+#define MC_CMD_PREPARE_SIGNED 0x10d
+
+#define MC_CMD_0x10d_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
+/* MC_CMD_PREPARE_SIGNED_IN msgrequest */
+#define    MC_CMD_PREPARE_SIGNED_IN_LEN 4
+/* the length of data area to clear */
+#define       MC_CMD_PREPARE_SIGNED_IN_DATALEN_OFST 0
+
+/* MC_CMD_PREPARE_SIGNED_OUT msgresponse */
+#define    MC_CMD_PREPARE_SIGNED_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS
+ * Configure UDP ports for tunnel encapsulation hardware acceleration. The
+ * parser-dispatcher will attempt to parse traffic on these ports as tunnel
+ * encapsulation PDUs and filter them using the tunnel encapsulation filter
+ * chain rather than the standard filter chain. Note that this command can
+ * cause all functions to see a reset. (Available on Medford only.)
+ */
+#define MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS 0x117
+
+#define MC_CMD_0x117_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
+/* MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN msgrequest */
+#define    MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN_LENMIN 4
+#define    MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN_LENMAX 68
+#define    MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN_LEN(num) (4+4*(num))
+/* Flags */
+#define       MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN_FLAGS_OFST 0
+#define       MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN_FLAGS_LEN 2
+#define        MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN_UNLOADING_LBN 0
+#define        MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN_UNLOADING_WIDTH 1
+/* The number of entries in the ENTRIES array */
+#define       MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN_NUM_ENTRIES_OFST 2
+#define       MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN_NUM_ENTRIES_LEN 2
+/* Entries defining the UDP port to protocol mapping, each laid out as a
+ * TUNNEL_ENCAP_UDP_PORT_ENTRY
+ */
+#define       MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN_ENTRIES_OFST 4
+#define       MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN_ENTRIES_LEN 4
+#define       MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN_ENTRIES_MINNUM 0
+#define       MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_IN_ENTRIES_MAXNUM 16
+
+/* MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_OUT msgresponse */
+#define    MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_OUT_LEN 2
+/* Flags */
+#define       MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_OUT_FLAGS_OFST 0
+#define       MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_OUT_FLAGS_LEN 2
+#define        MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_OUT_RESETTING_LBN 0
+#define        MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_OUT_RESETTING_WIDTH 1
+
+
+/***********************************/
+/* MC_CMD_RX_BALANCING
+ * Configure a port upconverter to distribute the packets on both RX engines.
+ * Packets are distributed based on a table with the destination vFIFO. The
+ * index of the table is a hash of source and destination of IPV4 and VLAN
+ * priority.
+ */
+#define MC_CMD_RX_BALANCING 0x118
+
+#define MC_CMD_0x118_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
+/* MC_CMD_RX_BALANCING_IN msgrequest */
+#define    MC_CMD_RX_BALANCING_IN_LEN 4
+/* The RX port whose upconverter table will be modified */
+#define       MC_CMD_RX_BALANCING_IN_PORT_OFST 0
+#define       MC_CMD_RX_BALANCING_IN_PORT_LEN 1
+/* The VLAN priority associated to the table index and vFIFO */
+#define       MC_CMD_RX_BALANCING_IN_PRIORITY_OFST 1
+#define       MC_CMD_RX_BALANCING_IN_PRIORITY_LEN 1
+/* The resulting bit of SRC^DST for indexing the table */
+#define       MC_CMD_RX_BALANCING_IN_SRC_DST_OFST 2
+#define       MC_CMD_RX_BALANCING_IN_SRC_DST_LEN 1
+/* The RX engine to which the vFIFO in the table entry will point to */
+#define       MC_CMD_RX_BALANCING_IN_ENG_OFST 3
+#define       MC_CMD_RX_BALANCING_IN_ENG_LEN 1
+
+/* MC_CMD_RX_BALANCING_OUT msgresponse */
+#define    MC_CMD_RX_BALANCING_OUT_LEN 0
+
+
 #endif /* MCDI_PCOL_H */
diff --git a/drivers/net/ethernet/sfc/mcdi_port.c b/drivers/net/ethernet/sfc/mcdi_port.c
index 7f295c4..2a9228a 100644
--- a/drivers/net/ethernet/sfc/mcdi_port.c
+++ b/drivers/net/ethernet/sfc/mcdi_port.c
@@ -189,11 +189,12 @@
 
 	case MC_CMD_MEDIA_XFP:
 	case MC_CMD_MEDIA_SFP_PLUS:
-		result |= SUPPORTED_FIBRE;
-		break;
-
 	case MC_CMD_MEDIA_QSFP_PLUS:
 		result |= SUPPORTED_FIBRE;
+		if (cap & (1 << MC_CMD_PHY_CAP_1000FDX_LBN))
+			result |= SUPPORTED_1000baseT_Full;
+		if (cap & (1 << MC_CMD_PHY_CAP_10000FDX_LBN))
+			result |= SUPPORTED_10000baseT_Full;
 		if (cap & (1 << MC_CMD_PHY_CAP_40000FDX_LBN))
 			result |= SUPPORTED_40000baseCR4_Full;
 		break;
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index d13ddf9..9ff062a 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -868,6 +868,7 @@
  *	be held to modify it.
  * @port_initialized: Port initialized?
  * @net_dev: Operating system network device. Consider holding the rtnl lock
+ * @fixed_features: Features which cannot be turned off
  * @stats_buffer: DMA buffer for statistics
  * @phy_type: PHY type
  * @phy_op: PHY interface
@@ -916,7 +917,6 @@
  * @stats_lock: Statistics update lock. Must be held when calling
  *	efx_nic_type::{update,start,stop}_stats.
  * @n_rx_noskb_drops: Count of RX packets dropped due to failure to allocate an skb
- * @mc_promisc: Whether in multicast promiscuous mode when last changed
  *
  * This is stored in the private area of the &struct net_device.
  */
@@ -1008,6 +1008,8 @@
 	bool port_initialized;
 	struct net_device *net_dev;
 
+	netdev_features_t fixed_features;
+
 	struct efx_buffer stats_buffer;
 	u64 rx_nodesc_drops_total;
 	u64 rx_nodesc_drops_while_down;
@@ -1065,7 +1067,6 @@
 	int last_irq_cpu;
 	spinlock_t stats_lock;
 	atomic_t n_rx_noskb_drops;
-	bool mc_promisc;
 };
 
 static inline int efx_dev_registered(struct efx_nic *efx)
@@ -1333,6 +1334,8 @@
 	int (*ptp_set_ts_config)(struct efx_nic *efx,
 				 struct hwtstamp_config *init);
 	int (*sriov_configure)(struct efx_nic *efx, int num_vfs);
+	int (*vlan_rx_add_vid)(struct efx_nic *efx, __be16 proto, u16 vid);
+	int (*vlan_rx_kill_vid)(struct efx_nic *efx, __be16 proto, u16 vid);
 	int (*sriov_init)(struct efx_nic *efx);
 	void (*sriov_fini)(struct efx_nic *efx);
 	bool (*sriov_wanted)(struct efx_nic *efx);
@@ -1521,4 +1524,16 @@
 	skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 }
 
+/* Get all supported features.
+ * If a feature is not fixed, it is present in hw_features.
+ * If a feature is fixed, it does not present in hw_features, but
+ * always in features.
+ */
+static inline netdev_features_t efx_supported_features(const struct efx_nic *efx)
+{
+	const struct net_device *net_dev = efx->net_dev;
+
+	return net_dev->features | net_dev->hw_features;
+}
+
 #endif /* EFX_NET_DRIVER_H */
diff --git a/drivers/net/ethernet/sfc/nic.h b/drivers/net/ethernet/sfc/nic.h
index 0b536e2..96944c3 100644
--- a/drivers/net/ethernet/sfc/nic.h
+++ b/drivers/net/ethernet/sfc/nic.h
@@ -519,6 +519,9 @@
 #ifdef CONFIG_SFC_SRIOV
  * @vf: Pointer to VF data structure
 #endif
+ * @vport_mac: The MAC address on the vport, only for PFs; VFs will be zero
+ * @vlan_list: List of VLANs added over the interface. Serialised by vlan_lock.
+ * @vlan_lock: Lock to serialize access to vlan_list.
  */
 struct efx_ef10_nic_data {
 	struct efx_buffer mcdi_buf;
@@ -550,6 +553,8 @@
 	struct ef10_vf *vf;
 #endif
 	u8 vport_mac[ETH_ALEN];
+	struct list_head vlan_list;
+	struct mutex vlan_lock;
 };
 
 int efx_init_sriov(void);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index 0cd3ecf..63c2e4f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -46,6 +46,7 @@
 	struct platform_device *pdev;
 	int phy_iface;
 	struct regulator *regulator;
+	bool suspended;
 	const struct rk_gmac_ops *ops;
 
 	bool clk_enabled;
@@ -529,9 +530,8 @@
 	return bsp_priv;
 }
 
-static int rk_gmac_init(struct platform_device *pdev, void *priv)
+static int rk_gmac_powerup(struct rk_priv_data *bsp_priv)
 {
-	struct rk_priv_data *bsp_priv = priv;
 	int ret;
 
 	ret = phy_power_on(bsp_priv, true);
@@ -545,14 +545,50 @@
 	return 0;
 }
 
-static void rk_gmac_exit(struct platform_device *pdev, void *priv)
+static void rk_gmac_powerdown(struct rk_priv_data *gmac)
 {
-	struct rk_priv_data *gmac = priv;
-
 	phy_power_on(gmac, false);
 	gmac_clk_enable(gmac, false);
 }
 
+static int rk_gmac_init(struct platform_device *pdev, void *priv)
+{
+	struct rk_priv_data *bsp_priv = priv;
+
+	return rk_gmac_powerup(bsp_priv);
+}
+
+static void rk_gmac_exit(struct platform_device *pdev, void *priv)
+{
+	struct rk_priv_data *bsp_priv = priv;
+
+	rk_gmac_powerdown(bsp_priv);
+}
+
+static void rk_gmac_suspend(struct platform_device *pdev, void *priv)
+{
+	struct rk_priv_data *bsp_priv = priv;
+
+	/* Keep the PHY up if we use Wake-on-Lan. */
+	if (device_may_wakeup(&pdev->dev))
+		return;
+
+	rk_gmac_powerdown(bsp_priv);
+	bsp_priv->suspended = true;
+}
+
+static void rk_gmac_resume(struct platform_device *pdev, void *priv)
+{
+	struct rk_priv_data *bsp_priv = priv;
+
+	/* The PHY was up for Wake-on-Lan. */
+	if (!bsp_priv->suspended)
+		return;
+
+	rk_gmac_powerup(bsp_priv);
+	bsp_priv->suspended = false;
+}
+
 static void rk_fix_speed(void *priv, unsigned int speed)
 {
 	struct rk_priv_data *bsp_priv = priv;
@@ -591,6 +627,8 @@
 	plat_dat->init = rk_gmac_init;
 	plat_dat->exit = rk_gmac_exit;
 	plat_dat->fix_mac_speed = rk_fix_speed;
+	plat_dat->suspend = rk_gmac_suspend;
+	plat_dat->resume = rk_gmac_resume;
 
 	plat_dat->bsp_priv = rk_gmac_setup(pdev, data);
 	if (IS_ERR(plat_dat->bsp_priv))
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index 4f7283d..44da877 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -156,7 +156,7 @@
 		struct netdev_hw_addr *ha;
 
 		netdev_for_each_uc_addr(ha, dev) {
-			dwmac4_set_umac_addr(ioaddr, ha->addr, reg);
+			dwmac4_set_umac_addr(hw, ha->addr, reg);
 			reg++;
 		}
 	}
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index eac45d0..a473c18 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3450,8 +3450,6 @@
 	if (!netif_running(ndev))
 		return 0;
 
-	spin_lock_irqsave(&priv->lock, flags);
-
 	/* Power Down bit, into the PM register, is cleared
 	 * automatically as soon as a magic packet or a Wake-up frame
 	 * is received. Anyway, it's better to manually clear
@@ -3459,7 +3457,9 @@
 	 * from another devices (e.g. serial console).
 	 */
 	if (device_may_wakeup(priv->device)) {
+		spin_lock_irqsave(&priv->lock, flags);
 		priv->hw->mac->pmt(priv->hw, 0);
+		spin_unlock_irqrestore(&priv->lock, flags);
 		priv->irq_wake = 0;
 	} else {
 		pinctrl_pm_select_default_state(priv->device);
@@ -3473,6 +3473,8 @@
 
 	netif_device_attach(ndev);
 
+	spin_lock_irqsave(&priv->lock, flags);
+
 	priv->cur_rx = 0;
 	priv->dirty_rx = 0;
 	priv->dirty_tx = 0;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 409db91..a96714d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -411,7 +411,9 @@
 	struct platform_device *pdev = to_platform_device(dev);
 
 	ret = stmmac_suspend(dev);
-	if (priv->plat->exit)
+	if (priv->plat->suspend)
+		priv->plat->suspend(pdev, priv->plat->bsp_priv);
+	else if (priv->plat->exit)
 		priv->plat->exit(pdev, priv->plat->bsp_priv);
 
 	return ret;
@@ -430,7 +432,9 @@
 	struct stmmac_priv *priv = netdev_priv(ndev);
 	struct platform_device *pdev = to_platform_device(dev);
 
-	if (priv->plat->init)
+	if (priv->plat->resume)
+		priv->plat->resume(pdev, priv->plat->bsp_priv);
+	else if (priv->plat->init)
 		priv->plat->init(pdev, priv->plat->bsp_priv);
 
 	return stmmac_resume(dev);
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 635979b..9c924f1 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -1277,6 +1277,7 @@
 
 	if (!cpsw_common_res_usage_state(priv)) {
 		struct cpsw_priv *priv_sl0 = cpsw_get_slave_priv(priv, 0);
+		int buf_num;
 
 		/* setup tx dma to fixed prio and zero offset */
 		cpdma_control_set(priv->dma, CPDMA_TX_PRIO_FIXED, 1);
@@ -1304,10 +1305,8 @@
 			enable_irq(priv->irqs_table[0]);
 		}
 
-		if (WARN_ON(!priv->data.rx_descs))
-			priv->data.rx_descs = 128;
-
-		for (i = 0; i < priv->data.rx_descs; i++) {
+		buf_num = cpdma_chan_get_rx_buf_num(priv->dma);
+		for (i = 0; i < buf_num; i++) {
 			struct sk_buff *skb;
 
 			ret = -ENOMEM;
@@ -1338,7 +1337,7 @@
 	if (priv->coal_intvl != 0) {
 		struct ethtool_coalesce coal;
 
-		coal.rx_coalesce_usecs = (priv->coal_intvl << 4);
+		coal.rx_coalesce_usecs = priv->coal_intvl;
 		cpsw_set_coalesce(ndev, &coal);
 	}
 
@@ -1998,12 +1997,6 @@
 	}
 	data->bd_ram_size = prop;
 
-	if (of_property_read_u32(node, "rx_descs", &prop)) {
-		dev_err(&pdev->dev, "Missing rx_descs property in the DT.\n");
-		return -EINVAL;
-	}
-	data->rx_descs = prop;
-
 	if (of_property_read_u32(node, "mac_control", &prop)) {
 		dev_err(&pdev->dev, "Missing mac_control property in the DT.\n");
 		return -EINVAL;
@@ -2021,7 +2014,7 @@
 	if (ret)
 		dev_warn(&pdev->dev, "Doesn't have any child node\n");
 
-	for_each_child_of_node(node, slave_node) {
+	for_each_available_child_of_node(node, slave_node) {
 		struct cpsw_slave_data *slave_data = data->slave_data + i;
 		const void *mac_addr = NULL;
 		int lenp;
diff --git a/drivers/net/ethernet/ti/cpsw.h b/drivers/net/ethernet/ti/cpsw.h
index e50afd1..16b54c6 100644
--- a/drivers/net/ethernet/ti/cpsw.h
+++ b/drivers/net/ethernet/ti/cpsw.h
@@ -35,7 +35,6 @@
 	u32	cpts_clock_shift; /* convert input clock ticks to nanoseconds */
 	u32	ale_entries;	/* ale table size */
 	u32	bd_ram_size;  /*buffer descriptor ram size */
-	u32	rx_descs;	/* Number of Rx Descriptios */
 	u32	mac_control;	/* Mac control register */
 	u16	default_vlan;	/* Def VLAN for ALE lookup in VLAN aware mode*/
 	bool	dual_emac;	/* Enable Dual EMAC mode */
diff --git a/drivers/net/ethernet/ti/davinci_cpdma.c b/drivers/net/ethernet/ti/davinci_cpdma.c
index 18bf3a8..bcd9e45 100644
--- a/drivers/net/ethernet/ti/davinci_cpdma.c
+++ b/drivers/net/ethernet/ti/davinci_cpdma.c
@@ -543,6 +543,12 @@
 }
 EXPORT_SYMBOL_GPL(cpdma_chan_create);
 
+int cpdma_chan_get_rx_buf_num(struct cpdma_ctlr *ctlr)
+{
+	return ctlr->pool->num_desc / 2;
+}
+EXPORT_SYMBOL_GPL(cpdma_chan_get_rx_buf_num);
+
 int cpdma_chan_destroy(struct cpdma_chan *chan)
 {
 	struct cpdma_ctlr *ctlr;
diff --git a/drivers/net/ethernet/ti/davinci_cpdma.h b/drivers/net/ethernet/ti/davinci_cpdma.h
index 86dee48..80c015c 100644
--- a/drivers/net/ethernet/ti/davinci_cpdma.h
+++ b/drivers/net/ethernet/ti/davinci_cpdma.h
@@ -81,6 +81,7 @@
 
 struct cpdma_chan *cpdma_chan_create(struct cpdma_ctlr *ctlr, int chan_num,
 				     cpdma_handler_fn handler);
+int cpdma_chan_get_rx_buf_num(struct cpdma_ctlr *ctlr);
 int cpdma_chan_destroy(struct cpdma_chan *chan);
 int cpdma_chan_start(struct cpdma_chan *chan);
 int cpdma_chan_stop(struct cpdma_chan *chan);
diff --git a/drivers/net/ethernet/ti/tlan.c b/drivers/net/ethernet/ti/tlan.c
index 5617033..ece0ea0 100644
--- a/drivers/net/ethernet/ti/tlan.c
+++ b/drivers/net/ethernet/ti/tlan.c
@@ -1651,7 +1651,6 @@
 	dma_addr_t		head_list_phys;
 	u32			ack = 1;
 
-	host_int = 0;
 	if (priv->tlan_rev < 0x30) {
 		TLAN_DBG(TLAN_DEBUG_TX,
 			 "TRANSMIT:  handling TX EOC (Head=%d Tail=%d) -- IRQ\n",
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index cadefe4..aa61708 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -12,7 +12,6 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/hash.h>
 #include <net/dst_metadata.h>
@@ -397,23 +396,6 @@
 	return sock;
 }
 
-static void geneve_notify_add_rx_port(struct geneve_sock *gs)
-{
-	struct net_device *dev;
-	struct sock *sk = gs->sock->sk;
-	struct net *net = sock_net(sk);
-	sa_family_t sa_family = geneve_get_sk_family(gs);
-	__be16 port = inet_sk(sk)->inet_sport;
-
-	rcu_read_lock();
-	for_each_netdev_rcu(net, dev) {
-		if (dev->netdev_ops->ndo_add_geneve_port)
-			dev->netdev_ops->ndo_add_geneve_port(dev, sa_family,
-							     port);
-	}
-	rcu_read_unlock();
-}
-
 static int geneve_hlen(struct genevehdr *gh)
 {
 	return sizeof(*gh) + gh->opt_len * 4;
@@ -533,7 +515,7 @@
 		INIT_HLIST_HEAD(&gs->vni_list[h]);
 
 	/* Initialize the geneve udp offloads structure */
-	geneve_notify_add_rx_port(gs);
+	udp_tunnel_notify_add_rx_port(gs->sock, UDP_TUNNEL_TYPE_GENEVE);
 
 	/* Mark socket as an encapsulation socket */
 	memset(&tunnel_cfg, 0, sizeof(tunnel_cfg));
@@ -548,31 +530,13 @@
 	return gs;
 }
 
-static void geneve_notify_del_rx_port(struct geneve_sock *gs)
-{
-	struct net_device *dev;
-	struct sock *sk = gs->sock->sk;
-	struct net *net = sock_net(sk);
-	sa_family_t sa_family = geneve_get_sk_family(gs);
-	__be16 port = inet_sk(sk)->inet_sport;
-
-	rcu_read_lock();
-	for_each_netdev_rcu(net, dev) {
-		if (dev->netdev_ops->ndo_del_geneve_port)
-			dev->netdev_ops->ndo_del_geneve_port(dev, sa_family,
-							     port);
-	}
-
-	rcu_read_unlock();
-}
-
 static void __geneve_sock_release(struct geneve_sock *gs)
 {
 	if (!gs || --gs->refcnt)
 		return;
 
 	list_del(&gs->list);
-	geneve_notify_del_rx_port(gs);
+	udp_tunnel_notify_del_rx_port(gs->sock, UDP_TUNNEL_TYPE_GENEVE);
 	udp_tunnel_sock_release(gs->sock);
 	kfree_rcu(gs, rcu);
 }
@@ -1165,29 +1129,20 @@
 	.name = "geneve",
 };
 
-/* Calls the ndo_add_geneve_port of the caller in order to
+/* Calls the ndo_add_udp_enc_port of the caller in order to
  * supply the listening GENEVE udp ports. Callers are expected
- * to implement the ndo_add_geneve_port.
+ * to implement the ndo_add_udp_enc_port.
  */
 static void geneve_push_rx_ports(struct net_device *dev)
 {
 	struct net *net = dev_net(dev);
 	struct geneve_net *gn = net_generic(net, geneve_net_id);
 	struct geneve_sock *gs;
-	sa_family_t sa_family;
-	struct sock *sk;
-	__be16 port;
-
-	if (!dev->netdev_ops->ndo_add_geneve_port)
-		return;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(gs, &gn->sock_list, list) {
-		sk = gs->sock->sk;
-		sa_family = sk->sk_family;
-		port = inet_sk(sk)->inet_sport;
-		dev->netdev_ops->ndo_add_geneve_port(dev, sa_family, port);
-	}
+	list_for_each_entry_rcu(gs, &gn->sock_list, list)
+		udp_tunnel_push_rx_port(dev, gs->sock,
+					UDP_TUNNEL_TYPE_GENEVE);
 	rcu_read_unlock();
 }
 
@@ -1542,7 +1497,7 @@
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 
-	if (event == NETDEV_OFFLOAD_PUSH_GENEVE)
+	if (event == NETDEV_UDP_TUNNEL_PUSH_INFO)
 		geneve_push_rx_ports(dev);
 
 	return NOTIFY_DONE;
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 4e976a0..97e0cbc 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -16,7 +16,6 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/module.h>
-#include <linux/version.h>
 #include <linux/skbuff.h>
 #include <linux/udp.h>
 #include <linux/rculist.h>
diff --git a/drivers/net/hamradio/baycom_par.c b/drivers/net/hamradio/baycom_par.c
index acb6369..072cddc 100644
--- a/drivers/net/hamradio/baycom_par.c
+++ b/drivers/net/hamradio/baycom_par.c
@@ -156,7 +156,7 @@
 
 /* --------------------------------------------------------------------- */
 
-static void __inline__ baycom_int_freq(struct baycom_state *bc)
+static inline void baycom_int_freq(struct baycom_state *bc)
 {
 #ifdef BAYCOM_DEBUG
 	unsigned long cur_jiffies = jiffies;
@@ -192,7 +192,7 @@
 
 /* --------------------------------------------------------------------- */
 
-static __inline__ void par96_tx(struct net_device *dev, struct baycom_state *bc)
+static inline void par96_tx(struct net_device *dev, struct baycom_state *bc)
 {
 	int i;
 	unsigned int data = hdlcdrv_getbits(&bc->hdrv);
@@ -216,7 +216,7 @@
 
 /* --------------------------------------------------------------------- */
 
-static __inline__ void par96_rx(struct net_device *dev, struct baycom_state *bc)
+static inline void par96_rx(struct net_device *dev, struct baycom_state *bc)
 {
 	int i;
 	unsigned int data, mask, mask2, descx;
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index c270c5a..467fb8b 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -173,6 +173,7 @@
 
 /* Interface */
 struct rndis_message;
+struct netvsc_device;
 int netvsc_device_add(struct hv_device *device, void *additional_info);
 int netvsc_device_remove(struct hv_device *device);
 int netvsc_send(struct hv_device *device,
@@ -189,8 +190,8 @@
 			struct vmbus_channel *channel,
 			u16 vlan_tci);
 void netvsc_channel_cb(void *context);
-int rndis_filter_open(struct hv_device *dev);
-int rndis_filter_close(struct hv_device *dev);
+int rndis_filter_open(struct netvsc_device *nvdev);
+int rndis_filter_close(struct netvsc_device *nvdev);
 int rndis_filter_device_add(struct hv_device *dev,
 			void *additional_info);
 void rndis_filter_device_remove(struct hv_device *dev);
@@ -200,7 +201,7 @@
 			struct vmbus_channel *channel);
 
 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);
+int rndis_filter_set_device_mac(struct net_device *ndev, char *mac);
 
 void netvsc_switch_datapath(struct net_device *nv_dev, bool vf);
 
@@ -743,6 +744,18 @@
 	atomic_t vf_use_cnt;
 };
 
+static inline struct netvsc_device *
+net_device_to_netvsc_device(struct net_device *ndev)
+{
+	return ((struct net_device_context *)netdev_priv(ndev))->nvdev;
+}
+
+static inline struct netvsc_device *
+hv_device_to_netvsc_device(struct hv_device *device)
+{
+	return net_device_to_netvsc_device(hv_get_drvdata(device));
+}
+
 /* NdisInitialize message */
 struct rndis_initialize_request {
 	u32 req_id;
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 719cb35..6909c32 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -95,9 +95,7 @@
 
 static struct netvsc_device *get_outbound_net_device(struct hv_device *device)
 {
-	struct net_device *ndev = hv_get_drvdata(device);
-	struct net_device_context *net_device_ctx = netdev_priv(ndev);
-	struct netvsc_device *net_device = net_device_ctx->nvdev;
+	struct netvsc_device *net_device = hv_device_to_netvsc_device(device);
 
 	if (net_device && net_device->destroy)
 		net_device = NULL;
@@ -107,9 +105,7 @@
 
 static struct netvsc_device *get_inbound_net_device(struct hv_device *device)
 {
-	struct net_device *ndev = hv_get_drvdata(device);
-	struct net_device_context *net_device_ctx = netdev_priv(ndev);
-	struct netvsc_device *net_device = net_device_ctx->nvdev;
+	struct netvsc_device *net_device = hv_device_to_netvsc_device(device);
 
 	if (!net_device)
 		goto get_in_err;
@@ -128,8 +124,7 @@
 	struct nvsp_message *revoke_packet;
 	int ret = 0;
 	struct net_device *ndev = hv_get_drvdata(device);
-	struct net_device_context *net_device_ctx = netdev_priv(ndev);
-	struct netvsc_device *net_device = net_device_ctx->nvdev;
+	struct netvsc_device *net_device = net_device_to_netvsc_device(ndev);
 
 	/*
 	 * If we got a section count, it means we received a
@@ -249,7 +244,6 @@
 static int netvsc_init_buf(struct hv_device *device)
 {
 	int ret = 0;
-	unsigned long t;
 	struct netvsc_device *net_device;
 	struct nvsp_message *init_packet;
 	struct net_device *ndev;
@@ -310,9 +304,7 @@
 		goto cleanup;
 	}
 
-	t = wait_for_completion_timeout(&net_device->channel_init_wait, 5*HZ);
-	BUG_ON(t == 0);
-
+	wait_for_completion(&net_device->channel_init_wait);
 
 	/* Check the response */
 	if (init_packet->msg.v1_msg.
@@ -395,8 +387,7 @@
 		goto cleanup;
 	}
 
-	t = wait_for_completion_timeout(&net_device->channel_init_wait, 5*HZ);
-	BUG_ON(t == 0);
+	wait_for_completion(&net_device->channel_init_wait);
 
 	/* Check the response */
 	if (init_packet->msg.v1_msg.
@@ -450,7 +441,6 @@
 {
 	struct net_device *ndev = hv_get_drvdata(device);
 	int ret;
-	unsigned long t;
 
 	memset(init_packet, 0, sizeof(struct nvsp_message));
 	init_packet->hdr.msg_type = NVSP_MSG_TYPE_INIT;
@@ -467,10 +457,7 @@
 	if (ret != 0)
 		return ret;
 
-	t = wait_for_completion_timeout(&net_device->channel_init_wait, 5*HZ);
-
-	if (t == 0)
-		return -ETIMEDOUT;
+	wait_for_completion(&net_device->channel_init_wait);
 
 	if (init_packet->msg.init_msg.init_complete.status !=
 	    NVSP_STAT_SUCCESS)
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 5ac1267..787a202 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -98,16 +98,14 @@
 
 static int netvsc_open(struct net_device *net)
 {
-	struct net_device_context *net_device_ctx = netdev_priv(net);
-	struct hv_device *device_obj = net_device_ctx->device_ctx;
-	struct netvsc_device *nvdev = net_device_ctx->nvdev;
+	struct netvsc_device *nvdev = net_device_to_netvsc_device(net);
 	struct rndis_device *rdev;
 	int ret = 0;
 
 	netif_carrier_off(net);
 
 	/* Open up the device */
-	ret = rndis_filter_open(device_obj);
+	ret = rndis_filter_open(nvdev);
 	if (ret != 0) {
 		netdev_err(net, "unable to open device (ret %d).\n", ret);
 		return ret;
@@ -125,7 +123,6 @@
 static int netvsc_close(struct net_device *net)
 {
 	struct net_device_context *net_device_ctx = netdev_priv(net);
-	struct hv_device *device_obj = net_device_ctx->device_ctx;
 	struct netvsc_device *nvdev = net_device_ctx->nvdev;
 	int ret;
 	u32 aread, awrite, i, msec = 10, retry = 0, retry_max = 20;
@@ -135,7 +132,7 @@
 
 	/* Make sure netvsc_set_multicast_list doesn't re-enable filter! */
 	cancel_work_sync(&net_device_ctx->work);
-	ret = rndis_filter_close(device_obj);
+	ret = rndis_filter_close(nvdev);
 	if (ret != 0) {
 		netdev_err(net, "unable to close device (ret %d).\n", ret);
 		return ret;
@@ -701,7 +698,6 @@
 	}
 
 vf_injection_done:
-	net_device_ctx = netdev_priv(net);
 	rx_stats = this_cpu_ptr(net_device_ctx->rx_stats);
 
 	/* Allocate a skb - TODO direct I/O to pages? */
@@ -986,8 +982,6 @@
 
 static int netvsc_set_mac_addr(struct net_device *ndev, void *p)
 {
-	struct net_device_context *ndevctx = netdev_priv(ndev);
-	struct hv_device *hdev =  ndevctx->device_ctx;
 	struct sockaddr *addr = p;
 	char save_adr[ETH_ALEN];
 	unsigned char save_aatype;
@@ -1000,7 +994,7 @@
 	if (err != 0)
 		return err;
 
-	err = rndis_filter_set_device_mac(hdev, addr->sa_data);
+	err = rndis_filter_set_device_mac(ndev, addr->sa_data);
 	if (err != 0) {
 		/* roll back to saved MAC */
 		memcpy(ndev->dev_addr, save_adr, ETH_ALEN);
@@ -1248,7 +1242,7 @@
 	/*
 	 * Open the device before switching data path.
 	 */
-	rndis_filter_open(net_device_ctx->device_ctx);
+	rndis_filter_open(netvsc_dev);
 
 	/*
 	 * notify the host to switch the data path.
@@ -1303,7 +1297,7 @@
 		udelay(50);
 	netvsc_switch_datapath(ndev, false);
 	netdev_info(ndev, "Data path switched from VF: %s\n", vf_netdev->name);
-	rndis_filter_close(net_device_ctx->device_ctx);
+	rndis_filter_close(netvsc_dev);
 	netif_carrier_on(ndev);
 	/*
 	 * Notify peers.
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 97c292b..8e830f7 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -466,7 +466,6 @@
 	struct rndis_query_request *query;
 	struct rndis_query_complete *query_complete;
 	int ret = 0;
-	unsigned long t;
 
 	if (!result)
 		return -EINVAL;
@@ -503,11 +502,7 @@
 	if (ret != 0)
 		goto cleanup;
 
-	t = wait_for_completion_timeout(&request->wait_event, 5*HZ);
-	if (t == 0) {
-		ret = -ETIMEDOUT;
-		goto cleanup;
-	}
+	wait_for_completion(&request->wait_event);
 
 	/* Copy the response back */
 	query_complete = &request->response_msg.msg.query_complete;
@@ -543,11 +538,9 @@
 #define NWADR_STR "NetworkAddress"
 #define NWADR_STRLEN 14
 
-int rndis_filter_set_device_mac(struct hv_device *hdev, char *mac)
+int rndis_filter_set_device_mac(struct net_device *ndev, char *mac)
 {
-	struct net_device *ndev = hv_get_drvdata(hdev);
-	struct net_device_context *net_device_ctx = netdev_priv(ndev);
-	struct netvsc_device *nvdev = net_device_ctx->nvdev;
+	struct netvsc_device *nvdev = net_device_to_netvsc_device(ndev);
 	struct rndis_device *rdev = nvdev->extension;
 	struct rndis_request *request;
 	struct rndis_set_request *set;
@@ -558,7 +551,6 @@
 	u32 extlen = sizeof(struct rndis_config_parameter_info) +
 		2*NWADR_STRLEN + 4*ETH_ALEN;
 	int ret;
-	unsigned long t;
 
 	request = get_rndis_request(rdev, RNDIS_MSG_SET,
 		RNDIS_MESSAGE_SIZE(struct rndis_set_request) + extlen);
@@ -599,21 +591,13 @@
 	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 a 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;
-		}
+	wait_for_completion(&request->wait_event);
+
+	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:
@@ -622,12 +606,10 @@
 }
 
 static int
-rndis_filter_set_offload_params(struct hv_device *hdev,
+rndis_filter_set_offload_params(struct net_device *ndev,
 				struct ndis_offload_params *req_offloads)
 {
-	struct net_device *ndev = hv_get_drvdata(hdev);
-	struct net_device_context *net_device_ctx = netdev_priv(ndev);
-	struct netvsc_device *nvdev = net_device_ctx->nvdev;
+	struct netvsc_device *nvdev = net_device_to_netvsc_device(ndev);
 	struct rndis_device *rdev = nvdev->extension;
 	struct rndis_request *request;
 	struct rndis_set_request *set;
@@ -635,7 +617,6 @@
 	struct rndis_set_complete *set_complete;
 	u32 extlen = sizeof(struct ndis_offload_params);
 	int ret;
-	unsigned long t;
 	u32 vsp_version = nvdev->nvsp_version;
 
 	if (vsp_version <= NVSP_PROTOCOL_VERSION_4) {
@@ -669,20 +650,12 @@
 	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 offload on host side:0x%x\n",
-				   set_complete->status);
-			ret = -EINVAL;
-		}
+	wait_for_completion(&request->wait_event);
+	set_complete = &request->response_msg.msg.set_complete;
+	if (set_complete->status != RNDIS_STATUS_SUCCESS) {
+		netdev_err(ndev, "Fail to set offload on host side:0x%x\n",
+			   set_complete->status);
+		ret = -EINVAL;
 	}
 
 cleanup:
@@ -710,7 +683,6 @@
 	u32 *itab;
 	u8 *keyp;
 	int i, ret;
-	unsigned long t;
 
 	request = get_rndis_request(
 			rdev, RNDIS_MSG_SET,
@@ -753,20 +725,12 @@
 	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 a set response...\n");
-		/* can't put_rndis_request, since we may still receive a
-		 * send-completion.
-		 */
-		return -ETIMEDOUT;
-	} else {
-		set_complete = &request->response_msg.msg.set_complete;
-		if (set_complete->status != RNDIS_STATUS_SUCCESS) {
-			netdev_err(ndev, "Fail to set RSS parameters:0x%x\n",
-				   set_complete->status);
-			ret = -EINVAL;
-		}
+	wait_for_completion(&request->wait_event);
+	set_complete = &request->response_msg.msg.set_complete;
+	if (set_complete->status != RNDIS_STATUS_SUCCESS) {
+		netdev_err(ndev, "Fail to set RSS parameters:0x%x\n",
+			   set_complete->status);
+		ret = -EINVAL;
 	}
 
 cleanup:
@@ -795,8 +759,6 @@
 	struct rndis_set_complete *set_complete;
 	u32 status;
 	int ret;
-	unsigned long t;
-	struct net_device *ndev = dev->ndev;
 
 	request = get_rndis_request(dev, RNDIS_MSG_SET,
 			RNDIS_MESSAGE_SIZE(struct rndis_set_request) +
@@ -819,26 +781,14 @@
 	if (ret != 0)
 		goto cleanup;
 
-	t = wait_for_completion_timeout(&request->wait_event, 5*HZ);
+	wait_for_completion(&request->wait_event);
 
-	if (t == 0) {
-		netdev_err(ndev,
-			"timeout before we got a set response...\n");
-		ret = -ETIMEDOUT;
-		/*
-		 * We can't deallocate the request since we may still receive a
-		 * send completion for it.
-		 */
-		goto exit;
-	} else {
-		set_complete = &request->response_msg.msg.set_complete;
-		status = set_complete->status;
-	}
+	set_complete = &request->response_msg.msg.set_complete;
+	status = set_complete->status;
 
 cleanup:
 	if (request)
 		put_rndis_request(dev, request);
-exit:
 	return ret;
 }
 
@@ -850,9 +800,7 @@
 	struct rndis_initialize_complete *init_complete;
 	u32 status;
 	int ret;
-	unsigned long t;
-	struct net_device_context *net_device_ctx = netdev_priv(dev->ndev);
-	struct netvsc_device *nvdev = net_device_ctx->nvdev;
+	struct netvsc_device *nvdev = net_device_to_netvsc_device(dev->ndev);
 
 	request = get_rndis_request(dev, RNDIS_MSG_INIT,
 			RNDIS_MESSAGE_SIZE(struct rndis_initialize_request));
@@ -875,12 +823,7 @@
 		goto cleanup;
 	}
 
-	t = wait_for_completion_timeout(&request->wait_event, 5*HZ);
-
-	if (t == 0) {
-		ret = -ETIMEDOUT;
-		goto cleanup;
-	}
+	wait_for_completion(&request->wait_event);
 
 	init_complete = &request->response_msg.msg.init_complete;
 	status = init_complete->status;
@@ -977,8 +920,7 @@
 {
 	struct net_device *ndev =
 		hv_get_drvdata(new_sc->primary_channel->device_obj);
-	struct net_device_context *net_device_ctx = netdev_priv(ndev);
-	struct netvsc_device *nvscdev = net_device_ctx->nvdev;
+	struct netvsc_device *nvscdev = net_device_to_netvsc_device(ndev);
 	u16 chn_index = new_sc->offermsg.offer.sub_channel_index;
 	int ret;
 	unsigned long flags;
@@ -1014,7 +956,6 @@
 	struct netvsc_device_info *device_info = additional_info;
 	struct ndis_offload_params offloads;
 	struct nvsp_message *init_packet;
-	unsigned long t;
 	struct ndis_recv_scale_cap rsscap;
 	u32 rsscap_size = sizeof(struct ndis_recv_scale_cap);
 	u32 mtu, size;
@@ -1088,7 +1029,7 @@
 	offloads.lso_v2_ipv4 = NDIS_OFFLOAD_PARAMETERS_LSOV2_ENABLED;
 
 
-	ret = rndis_filter_set_offload_params(dev, &offloads);
+	ret = rndis_filter_set_offload_params(net, &offloads);
 	if (ret)
 		goto err_dev_remv;
 
@@ -1157,11 +1098,8 @@
 			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
 	if (ret)
 		goto out;
-	t = wait_for_completion_timeout(&net_device->channel_init_wait, 5*HZ);
-	if (t == 0) {
-		ret = -ETIMEDOUT;
-		goto out;
-	}
+	wait_for_completion(&net_device->channel_init_wait);
+
 	if (init_packet->msg.v5_msg.subchn_comp.status !=
 	    NVSP_STAT_SUCCESS) {
 		ret = -ENODEV;
@@ -1196,21 +1134,14 @@
 
 void rndis_filter_device_remove(struct hv_device *dev)
 {
-	struct net_device *ndev = hv_get_drvdata(dev);
-	struct net_device_context *net_device_ctx = netdev_priv(ndev);
-	struct netvsc_device *net_dev = net_device_ctx->nvdev;
+	struct netvsc_device *net_dev = hv_device_to_netvsc_device(dev);
 	struct rndis_device *rndis_dev = net_dev->extension;
-	unsigned long t;
 
 	/* If not all subchannel offers are complete, wait for them until
 	 * completion to avoid race.
 	 */
-	while (net_dev->num_sc_offered > 0) {
-		t = wait_for_completion_timeout(&net_dev->channel_init_wait,
-						10 * HZ);
-		if (t == 0)
-			WARN(1, "Netvsc: Waiting for sub-channel processing");
-	}
+	if (net_dev->num_sc_offered > 0)
+		wait_for_completion(&net_dev->channel_init_wait);
 
 	/* Halt and release the rndis device */
 	rndis_filter_halt_device(rndis_dev);
@@ -1222,27 +1153,19 @@
 }
 
 
-int rndis_filter_open(struct hv_device *dev)
+int rndis_filter_open(struct netvsc_device *nvdev)
 {
-	struct net_device *ndev = hv_get_drvdata(dev);
-	struct net_device_context *net_device_ctx = netdev_priv(ndev);
-	struct netvsc_device *net_device = net_device_ctx->nvdev;
-
-	if (!net_device)
+	if (!nvdev)
 		return -EINVAL;
 
-	if (atomic_inc_return(&net_device->open_cnt) != 1)
+	if (atomic_inc_return(&nvdev->open_cnt) != 1)
 		return 0;
 
-	return rndis_filter_open_device(net_device->extension);
+	return rndis_filter_open_device(nvdev->extension);
 }
 
-int rndis_filter_close(struct hv_device *dev)
+int rndis_filter_close(struct netvsc_device *nvdev)
 {
-	struct net_device *ndev = hv_get_drvdata(dev);
-	struct net_device_context *net_device_ctx = netdev_priv(ndev);
-	struct netvsc_device *nvdev = net_device_ctx->nvdev;
-
 	if (!nvdev)
 		return -EINVAL;
 
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 1c4d395..18b4e8c 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -80,13 +80,6 @@
 	kfree_rcu(port, rcu);
 }
 
-/* ipvlan network devices have devices nesting below it and are a special
- * "super class" of normal network devices; split their locks off into a
- * separate class since they always nest.
- */
-static struct lock_class_key ipvlan_netdev_xmit_lock_key;
-static struct lock_class_key ipvlan_netdev_addr_lock_key;
-
 #define IPVLAN_FEATURES \
 	(NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \
 	 NETIF_F_GSO | NETIF_F_TSO | NETIF_F_UFO | NETIF_F_GSO_ROBUST | \
@@ -96,19 +89,6 @@
 #define IPVLAN_STATE_MASK \
 	((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT))
 
-static void ipvlan_set_lockdep_class_one(struct net_device *dev,
-					 struct netdev_queue *txq,
-					 void *_unused)
-{
-	lockdep_set_class(&txq->_xmit_lock, &ipvlan_netdev_xmit_lock_key);
-}
-
-static void ipvlan_set_lockdep_class(struct net_device *dev)
-{
-	lockdep_set_class(&dev->addr_list_lock, &ipvlan_netdev_addr_lock_key);
-	netdev_for_each_tx_queue(dev, ipvlan_set_lockdep_class_one, NULL);
-}
-
 static int ipvlan_init(struct net_device *dev)
 {
 	struct ipvl_dev *ipvlan = netdev_priv(dev);
@@ -123,7 +103,7 @@
 	dev->gso_max_segs = phy_dev->gso_max_segs;
 	dev->hard_header_len = phy_dev->hard_header_len;
 
-	ipvlan_set_lockdep_class(dev);
+	netdev_lockdep_set_classes(dev);
 
 	ipvlan->pcpu_stats = alloc_percpu(struct ipvl_pcpu_stats);
 	if (!ipvlan->pcpu_stats)
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 0c65bd9..cd9b538 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -788,7 +788,6 @@
  * "super class" of normal network devices; split their locks off into a
  * separate class since they always nest.
  */
-static struct lock_class_key macvlan_netdev_xmit_lock_key;
 static struct lock_class_key macvlan_netdev_addr_lock_key;
 
 #define ALWAYS_ON_FEATURES \
@@ -809,20 +808,12 @@
 	return ((struct macvlan_dev *)netdev_priv(dev))->nest_level;
 }
 
-static void macvlan_set_lockdep_class_one(struct net_device *dev,
-					  struct netdev_queue *txq,
-					  void *_unused)
-{
-	lockdep_set_class(&txq->_xmit_lock,
-			  &macvlan_netdev_xmit_lock_key);
-}
-
 static void macvlan_set_lockdep_class(struct net_device *dev)
 {
+	netdev_lockdep_set_classes(dev);
 	lockdep_set_class_and_subclass(&dev->addr_list_lock,
 				       &macvlan_netdev_addr_lock_key,
 				       macvlan_get_nest_level(dev));
-	netdev_for_each_tx_queue(dev, macvlan_set_lockdep_class_one, NULL);
 }
 
 static int macvlan_init(struct net_device *dev)
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index bd67209..95a1332 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -627,93 +627,6 @@
 	return skb;
 }
 
-/*
- * macvtap_skb_from_vnet_hdr and macvtap_skb_to_vnet_hdr should
- * be shared with the tun/tap driver.
- */
-static int macvtap_skb_from_vnet_hdr(struct macvtap_queue *q,
-				     struct sk_buff *skb,
-				     struct virtio_net_hdr *vnet_hdr)
-{
-	unsigned short gso_type = 0;
-	if (vnet_hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
-		switch (vnet_hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
-		case VIRTIO_NET_HDR_GSO_TCPV4:
-			gso_type = SKB_GSO_TCPV4;
-			break;
-		case VIRTIO_NET_HDR_GSO_TCPV6:
-			gso_type = SKB_GSO_TCPV6;
-			break;
-		case VIRTIO_NET_HDR_GSO_UDP:
-			gso_type = SKB_GSO_UDP;
-			break;
-		default:
-			return -EINVAL;
-		}
-
-		if (vnet_hdr->gso_type & VIRTIO_NET_HDR_GSO_ECN)
-			gso_type |= SKB_GSO_TCP_ECN;
-
-		if (vnet_hdr->gso_size == 0)
-			return -EINVAL;
-	}
-
-	if (vnet_hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
-		if (!skb_partial_csum_set(skb, macvtap16_to_cpu(q, vnet_hdr->csum_start),
-					  macvtap16_to_cpu(q, vnet_hdr->csum_offset)))
-			return -EINVAL;
-	}
-
-	if (vnet_hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
-		skb_shinfo(skb)->gso_size = macvtap16_to_cpu(q, vnet_hdr->gso_size);
-		skb_shinfo(skb)->gso_type = gso_type;
-
-		/* Header must be checked, and gso_segs computed. */
-		skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
-		skb_shinfo(skb)->gso_segs = 0;
-	}
-	return 0;
-}
-
-static void macvtap_skb_to_vnet_hdr(struct macvtap_queue *q,
-				    const struct sk_buff *skb,
-				    struct virtio_net_hdr *vnet_hdr)
-{
-	memset(vnet_hdr, 0, sizeof(*vnet_hdr));
-
-	if (skb_is_gso(skb)) {
-		struct skb_shared_info *sinfo = skb_shinfo(skb);
-
-		/* This is a hint as to how much should be linear. */
-		vnet_hdr->hdr_len = cpu_to_macvtap16(q, skb_headlen(skb));
-		vnet_hdr->gso_size = cpu_to_macvtap16(q, sinfo->gso_size);
-		if (sinfo->gso_type & SKB_GSO_TCPV4)
-			vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
-		else if (sinfo->gso_type & SKB_GSO_TCPV6)
-			vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
-		else if (sinfo->gso_type & SKB_GSO_UDP)
-			vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP;
-		else
-			BUG();
-		if (sinfo->gso_type & SKB_GSO_TCP_ECN)
-			vnet_hdr->gso_type |= VIRTIO_NET_HDR_GSO_ECN;
-	} else
-		vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_NONE;
-
-	if (skb->ip_summed == CHECKSUM_PARTIAL) {
-		vnet_hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
-		if (skb_vlan_tag_present(skb))
-			vnet_hdr->csum_start = cpu_to_macvtap16(q,
-				skb_checksum_start_offset(skb) + VLAN_HLEN);
-		else
-			vnet_hdr->csum_start = cpu_to_macvtap16(q,
-				skb_checksum_start_offset(skb));
-		vnet_hdr->csum_offset = cpu_to_macvtap16(q, skb->csum_offset);
-	} else if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
-		vnet_hdr->flags = VIRTIO_NET_HDR_F_DATA_VALID;
-	} /* else everything is zero */
-}
-
 /* Neighbour code has some assumptions on HH_DATA_MOD alignment */
 #define MACVTAP_RESERVE HH_DATA_OFF(ETH_HLEN)
 
@@ -812,7 +725,8 @@
 	skb->protocol = eth_hdr(skb)->h_proto;
 
 	if (vnet_hdr_len) {
-		err = macvtap_skb_from_vnet_hdr(q, skb, &vnet_hdr);
+		err = virtio_net_hdr_to_skb(skb, &vnet_hdr,
+					    macvtap_is_little_endian(q));
 		if (err)
 			goto err_kfree;
 	}
@@ -880,7 +794,10 @@
 		if (iov_iter_count(iter) < vnet_hdr_len)
 			return -EINVAL;
 
-		macvtap_skb_to_vnet_hdr(q, skb, &vnet_hdr);
+		ret = virtio_net_hdr_from_skb(skb, &vnet_hdr,
+					      macvtap_is_little_endian(q));
+		if (ret)
+			BUG();
 
 		if (copy_to_iter(&vnet_hdr, sizeof(vnet_hdr), iter) !=
 		    sizeof(vnet_hdr))
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 6dad9a9..8dac88a 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -254,6 +254,17 @@
 
 	  Currently, only 8-bit registers are supported.
 
+config MDIO_BUS_MUX_BCM_IPROC
+	tristate "Support for iProc based MDIO bus multiplexers"
+	depends on OF && OF_MDIO && (ARCH_BCM_IPROC || COMPILE_TEST)
+	select MDIO_BUS_MUX
+	default ARCH_BCM_IPROC
+	help
+	  This module provides a driver for MDIO bus multiplexers found in
+	  iProc based Broadcom SoCs. This multiplexer connects one of several
+	  child MDIO bus to a parent bus. Buses could be internal as well as
+	  external and selection logic lies inside the same multiplexer.
+
 config MDIO_BCM_UNIMAC
 	tristate "Broadcom UniMAC MDIO bus controller"
 	depends on HAS_IOMEM
@@ -271,6 +282,14 @@
 	  This module provides a driver for the MDIO busses found in the
 	  Broadcom iProc SoC's.
 
+config INTEL_XWAY_PHY
+	tristate "Driver for Intel XWAY PHYs"
+	---help---
+	  Supports the Intel XWAY (former Lantiq) 11G and 22E PHYs.
+	  These PHYs are marked as standalone chips under the names
+	  PEF 7061, PEF 7071 and PEF 7072 or integrated into the Intel
+	  SoCs xRX200, xRX300, xRX330, xRX350 and xRX550.
+
 endif # PHYLIB
 
 config MICREL_KS8995MA
diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
index fcdbb92..4170642 100644
--- a/drivers/net/phy/Makefile
+++ b/drivers/net/phy/Makefile
@@ -39,8 +39,10 @@
 obj-$(CONFIG_MDIO_BUS_MUX)	+= mdio-mux.o
 obj-$(CONFIG_MDIO_BUS_MUX_GPIO)	+= mdio-mux-gpio.o
 obj-$(CONFIG_MDIO_BUS_MUX_MMIOREG) += mdio-mux-mmioreg.o
+obj-$(CONFIG_MDIO_BUS_MUX_BCM_IPROC)	+= mdio-mux-bcm-iproc.o
 obj-$(CONFIG_MDIO_SUN4I)	+= mdio-sun4i.o
 obj-$(CONFIG_MDIO_MOXART)	+= mdio-moxart.o
 obj-$(CONFIG_MDIO_BCM_UNIMAC)	+= mdio-bcm-unimac.o
 obj-$(CONFIG_MICROCHIP_PHY)	+= microchip.o
 obj-$(CONFIG_MDIO_BCM_IPROC)	+= mdio-bcm-iproc.o
+obj-$(CONFIG_INTEL_XWAY_PHY)	+= intel-xway.o
diff --git a/drivers/net/phy/intel-xway.c b/drivers/net/phy/intel-xway.c
new file mode 100644
index 0000000..c300ab5
--- /dev/null
+++ b/drivers/net/phy/intel-xway.c
@@ -0,0 +1,376 @@
+/*
+ * Copyright (C) 2012 Daniel Schwierzeck <daniel.schwierzeck@googlemail.com>
+ * Copyright (C) 2016 Hauke Mehrtens <hauke@hauke-m.de>
+ *
+ * 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.
+ */
+
+#include <linux/mdio.h>
+#include <linux/module.h>
+#include <linux/phy.h>
+#include <linux/of.h>
+
+#define XWAY_MDIO_IMASK			0x19	/* interrupt mask */
+#define XWAY_MDIO_ISTAT			0x1A	/* interrupt status */
+
+#define XWAY_MDIO_INIT_WOL		BIT(15)	/* Wake-On-LAN */
+#define XWAY_MDIO_INIT_MSRE		BIT(14)
+#define XWAY_MDIO_INIT_NPRX		BIT(13)
+#define XWAY_MDIO_INIT_NPTX		BIT(12)
+#define XWAY_MDIO_INIT_ANE		BIT(11)	/* Auto-Neg error */
+#define XWAY_MDIO_INIT_ANC		BIT(10)	/* Auto-Neg complete */
+#define XWAY_MDIO_INIT_ADSC		BIT(5)	/* Link auto-downspeed detect */
+#define XWAY_MDIO_INIT_MPIPC		BIT(4)
+#define XWAY_MDIO_INIT_MDIXC		BIT(3)
+#define XWAY_MDIO_INIT_DXMC		BIT(2)	/* Duplex mode change */
+#define XWAY_MDIO_INIT_LSPC		BIT(1)	/* Link speed change */
+#define XWAY_MDIO_INIT_LSTC		BIT(0)	/* Link state change */
+#define XWAY_MDIO_INIT_MASK		(XWAY_MDIO_INIT_LSTC | \
+					 XWAY_MDIO_INIT_ADSC)
+
+#define ADVERTISED_MPD			BIT(10)	/* Multi-port device */
+
+/* LED Configuration */
+#define XWAY_MMD_LEDCH			0x01E0
+/* Inverse of SCAN Function */
+#define  XWAY_MMD_LEDCH_NACS_NONE	0x0000
+#define  XWAY_MMD_LEDCH_NACS_LINK	0x0001
+#define  XWAY_MMD_LEDCH_NACS_PDOWN	0x0002
+#define  XWAY_MMD_LEDCH_NACS_EEE	0x0003
+#define  XWAY_MMD_LEDCH_NACS_ANEG	0x0004
+#define  XWAY_MMD_LEDCH_NACS_ABIST	0x0005
+#define  XWAY_MMD_LEDCH_NACS_CDIAG	0x0006
+#define  XWAY_MMD_LEDCH_NACS_TEST	0x0007
+/* Slow Blink Frequency */
+#define  XWAY_MMD_LEDCH_SBF_F02HZ	0x0000
+#define  XWAY_MMD_LEDCH_SBF_F04HZ	0x0010
+#define  XWAY_MMD_LEDCH_SBF_F08HZ	0x0020
+#define  XWAY_MMD_LEDCH_SBF_F16HZ	0x0030
+/* Fast Blink Frequency */
+#define  XWAY_MMD_LEDCH_FBF_F02HZ	0x0000
+#define  XWAY_MMD_LEDCH_FBF_F04HZ	0x0040
+#define  XWAY_MMD_LEDCH_FBF_F08HZ	0x0080
+#define  XWAY_MMD_LEDCH_FBF_F16HZ	0x00C0
+/* LED Configuration */
+#define XWAY_MMD_LEDCL			0x01E1
+/* Complex Blinking Configuration */
+#define  XWAY_MMD_LEDCH_CBLINK_NONE	0x0000
+#define  XWAY_MMD_LEDCH_CBLINK_LINK	0x0001
+#define  XWAY_MMD_LEDCH_CBLINK_PDOWN	0x0002
+#define  XWAY_MMD_LEDCH_CBLINK_EEE	0x0003
+#define  XWAY_MMD_LEDCH_CBLINK_ANEG	0x0004
+#define  XWAY_MMD_LEDCH_CBLINK_ABIST	0x0005
+#define  XWAY_MMD_LEDCH_CBLINK_CDIAG	0x0006
+#define  XWAY_MMD_LEDCH_CBLINK_TEST	0x0007
+/* Complex SCAN Configuration */
+#define  XWAY_MMD_LEDCH_SCAN_NONE	0x0000
+#define  XWAY_MMD_LEDCH_SCAN_LINK	0x0010
+#define  XWAY_MMD_LEDCH_SCAN_PDOWN	0x0020
+#define  XWAY_MMD_LEDCH_SCAN_EEE	0x0030
+#define  XWAY_MMD_LEDCH_SCAN_ANEG	0x0040
+#define  XWAY_MMD_LEDCH_SCAN_ABIST	0x0050
+#define  XWAY_MMD_LEDCH_SCAN_CDIAG	0x0060
+#define  XWAY_MMD_LEDCH_SCAN_TEST	0x0070
+/* Configuration for LED Pin x */
+#define XWAY_MMD_LED0H			0x01E2
+/* Fast Blinking Configuration */
+#define  XWAY_MMD_LEDxH_BLINKF_MASK	0x000F
+#define  XWAY_MMD_LEDxH_BLINKF_NONE	0x0000
+#define  XWAY_MMD_LEDxH_BLINKF_LINK10	0x0001
+#define  XWAY_MMD_LEDxH_BLINKF_LINK100	0x0002
+#define  XWAY_MMD_LEDxH_BLINKF_LINK10X	0x0003
+#define  XWAY_MMD_LEDxH_BLINKF_LINK1000	0x0004
+#define  XWAY_MMD_LEDxH_BLINKF_LINK10_0	0x0005
+#define  XWAY_MMD_LEDxH_BLINKF_LINK100X	0x0006
+#define  XWAY_MMD_LEDxH_BLINKF_LINK10XX	0x0007
+#define  XWAY_MMD_LEDxH_BLINKF_PDOWN	0x0008
+#define  XWAY_MMD_LEDxH_BLINKF_EEE	0x0009
+#define  XWAY_MMD_LEDxH_BLINKF_ANEG	0x000A
+#define  XWAY_MMD_LEDxH_BLINKF_ABIST	0x000B
+#define  XWAY_MMD_LEDxH_BLINKF_CDIAG	0x000C
+/* Constant On Configuration */
+#define  XWAY_MMD_LEDxH_CON_MASK	0x00F0
+#define  XWAY_MMD_LEDxH_CON_NONE	0x0000
+#define  XWAY_MMD_LEDxH_CON_LINK10	0x0010
+#define  XWAY_MMD_LEDxH_CON_LINK100	0x0020
+#define  XWAY_MMD_LEDxH_CON_LINK10X	0x0030
+#define  XWAY_MMD_LEDxH_CON_LINK1000	0x0040
+#define  XWAY_MMD_LEDxH_CON_LINK10_0	0x0050
+#define  XWAY_MMD_LEDxH_CON_LINK100X	0x0060
+#define  XWAY_MMD_LEDxH_CON_LINK10XX	0x0070
+#define  XWAY_MMD_LEDxH_CON_PDOWN	0x0080
+#define  XWAY_MMD_LEDxH_CON_EEE		0x0090
+#define  XWAY_MMD_LEDxH_CON_ANEG	0x00A0
+#define  XWAY_MMD_LEDxH_CON_ABIST	0x00B0
+#define  XWAY_MMD_LEDxH_CON_CDIAG	0x00C0
+#define  XWAY_MMD_LEDxH_CON_COPPER	0x00D0
+#define  XWAY_MMD_LEDxH_CON_FIBER	0x00E0
+/* Configuration for LED Pin x */
+#define XWAY_MMD_LED0L			0x01E3
+/* Pulsing Configuration */
+#define  XWAY_MMD_LEDxL_PULSE_MASK	0x000F
+#define  XWAY_MMD_LEDxL_PULSE_NONE	0x0000
+#define  XWAY_MMD_LEDxL_PULSE_TXACT	0x0001
+#define  XWAY_MMD_LEDxL_PULSE_RXACT	0x0002
+#define  XWAY_MMD_LEDxL_PULSE_COL	0x0004
+/* Slow Blinking Configuration */
+#define  XWAY_MMD_LEDxL_BLINKS_MASK	0x00F0
+#define  XWAY_MMD_LEDxL_BLINKS_NONE	0x0000
+#define  XWAY_MMD_LEDxL_BLINKS_LINK10	0x0010
+#define  XWAY_MMD_LEDxL_BLINKS_LINK100	0x0020
+#define  XWAY_MMD_LEDxL_BLINKS_LINK10X	0x0030
+#define  XWAY_MMD_LEDxL_BLINKS_LINK1000	0x0040
+#define  XWAY_MMD_LEDxL_BLINKS_LINK10_0	0x0050
+#define  XWAY_MMD_LEDxL_BLINKS_LINK100X	0x0060
+#define  XWAY_MMD_LEDxL_BLINKS_LINK10XX	0x0070
+#define  XWAY_MMD_LEDxL_BLINKS_PDOWN	0x0080
+#define  XWAY_MMD_LEDxL_BLINKS_EEE	0x0090
+#define  XWAY_MMD_LEDxL_BLINKS_ANEG	0x00A0
+#define  XWAY_MMD_LEDxL_BLINKS_ABIST	0x00B0
+#define  XWAY_MMD_LEDxL_BLINKS_CDIAG	0x00C0
+#define XWAY_MMD_LED1H			0x01E4
+#define XWAY_MMD_LED1L			0x01E5
+#define XWAY_MMD_LED2H			0x01E6
+#define XWAY_MMD_LED2L			0x01E7
+#define XWAY_MMD_LED3H			0x01E8
+#define XWAY_MMD_LED3L			0x01E9
+
+#define PHY_ID_PHY11G_1_3		0x030260D1
+#define PHY_ID_PHY22F_1_3		0x030260E1
+#define PHY_ID_PHY11G_1_4		0xD565A400
+#define PHY_ID_PHY22F_1_4		0xD565A410
+#define PHY_ID_PHY11G_1_5		0xD565A401
+#define PHY_ID_PHY22F_1_5		0xD565A411
+#define PHY_ID_PHY11G_VR9		0xD565A409
+#define PHY_ID_PHY22F_VR9		0xD565A419
+
+static int xway_gphy_config_init(struct phy_device *phydev)
+{
+	int err;
+	u32 ledxh;
+	u32 ledxl;
+
+	/* Mask all interrupts */
+	err = phy_write(phydev, XWAY_MDIO_IMASK, 0);
+	if (err)
+		return err;
+
+	/* Clear all pending interrupts */
+	phy_read(phydev, XWAY_MDIO_ISTAT);
+
+	phy_write_mmd_indirect(phydev, XWAY_MMD_LEDCH, MDIO_MMD_VEND2,
+			       XWAY_MMD_LEDCH_NACS_NONE |
+			       XWAY_MMD_LEDCH_SBF_F02HZ |
+			       XWAY_MMD_LEDCH_FBF_F16HZ);
+	phy_write_mmd_indirect(phydev, XWAY_MMD_LEDCL, MDIO_MMD_VEND2,
+			       XWAY_MMD_LEDCH_CBLINK_NONE |
+			       XWAY_MMD_LEDCH_SCAN_NONE);
+
+	/**
+	 * In most cases only one LED is connected to this phy, so
+	 * configure them all to constant on and pulse mode. LED3 is
+	 * only available in some packages, leave it in its reset
+	 * configuration.
+	 */
+	ledxh = XWAY_MMD_LEDxH_BLINKF_NONE | XWAY_MMD_LEDxH_CON_LINK10XX;
+	ledxl = XWAY_MMD_LEDxL_PULSE_TXACT | XWAY_MMD_LEDxL_PULSE_RXACT |
+		XWAY_MMD_LEDxL_BLINKS_NONE;
+	phy_write_mmd_indirect(phydev, XWAY_MMD_LED0H, MDIO_MMD_VEND2, ledxh);
+	phy_write_mmd_indirect(phydev, XWAY_MMD_LED0L, MDIO_MMD_VEND2, ledxl);
+	phy_write_mmd_indirect(phydev, XWAY_MMD_LED1H, MDIO_MMD_VEND2, ledxh);
+	phy_write_mmd_indirect(phydev, XWAY_MMD_LED1L, MDIO_MMD_VEND2, ledxl);
+	phy_write_mmd_indirect(phydev, XWAY_MMD_LED2H, MDIO_MMD_VEND2, ledxh);
+	phy_write_mmd_indirect(phydev, XWAY_MMD_LED2L, MDIO_MMD_VEND2, ledxl);
+
+	return 0;
+}
+
+static int xway_gphy14_config_aneg(struct phy_device *phydev)
+{
+	int reg, err;
+
+	/* Advertise as multi-port device, see IEEE802.3-2002 40.5.1.1 */
+	/* This is a workaround for an errata in rev < 1.5 devices */
+	reg = phy_read(phydev, MII_CTRL1000);
+	reg |= ADVERTISED_MPD;
+	err = phy_write(phydev, MII_CTRL1000, reg);
+	if (err)
+		return err;
+
+	return genphy_config_aneg(phydev);
+}
+
+static int xway_gphy_ack_interrupt(struct phy_device *phydev)
+{
+	int reg;
+
+	reg = phy_read(phydev, XWAY_MDIO_ISTAT);
+	return (reg < 0) ? reg : 0;
+}
+
+static int xway_gphy_did_interrupt(struct phy_device *phydev)
+{
+	int reg;
+
+	reg = phy_read(phydev, XWAY_MDIO_ISTAT);
+	return reg & XWAY_MDIO_INIT_MASK;
+}
+
+static int xway_gphy_config_intr(struct phy_device *phydev)
+{
+	u16 mask = 0;
+
+	if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
+		mask = XWAY_MDIO_INIT_MASK;
+
+	return phy_write(phydev, XWAY_MDIO_IMASK, mask);
+}
+
+static struct phy_driver xway_gphy[] = {
+	{
+		.phy_id		= PHY_ID_PHY11G_1_3,
+		.phy_id_mask	= 0xffffffff,
+		.name		= "Intel XWAY PHY11G (PEF 7071/PEF 7072) v1.3",
+		.features	= (PHY_GBIT_FEATURES | SUPPORTED_Pause |
+				   SUPPORTED_Asym_Pause),
+		.flags		= PHY_HAS_INTERRUPT,
+		.config_init	= xway_gphy_config_init,
+		.config_aneg	= xway_gphy14_config_aneg,
+		.read_status	= genphy_read_status,
+		.ack_interrupt	= xway_gphy_ack_interrupt,
+		.did_interrupt	= xway_gphy_did_interrupt,
+		.config_intr	= xway_gphy_config_intr,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+	}, {
+		.phy_id		= PHY_ID_PHY22F_1_3,
+		.phy_id_mask	= 0xffffffff,
+		.name		= "Intel XWAY PHY22F (PEF 7061) v1.3",
+		.features	= (PHY_BASIC_FEATURES | SUPPORTED_Pause |
+				   SUPPORTED_Asym_Pause),
+		.flags		= PHY_HAS_INTERRUPT,
+		.config_init	= xway_gphy_config_init,
+		.config_aneg	= xway_gphy14_config_aneg,
+		.read_status	= genphy_read_status,
+		.ack_interrupt	= xway_gphy_ack_interrupt,
+		.did_interrupt	= xway_gphy_did_interrupt,
+		.config_intr	= xway_gphy_config_intr,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+	}, {
+		.phy_id		= PHY_ID_PHY11G_1_4,
+		.phy_id_mask	= 0xffffffff,
+		.name		= "Intel XWAY PHY11G (PEF 7071/PEF 7072) v1.4",
+		.features	= (PHY_GBIT_FEATURES | SUPPORTED_Pause |
+				   SUPPORTED_Asym_Pause),
+		.flags		= PHY_HAS_INTERRUPT,
+		.config_init	= xway_gphy_config_init,
+		.config_aneg	= xway_gphy14_config_aneg,
+		.read_status	= genphy_read_status,
+		.ack_interrupt	= xway_gphy_ack_interrupt,
+		.did_interrupt	= xway_gphy_did_interrupt,
+		.config_intr	= xway_gphy_config_intr,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+	}, {
+		.phy_id		= PHY_ID_PHY22F_1_4,
+		.phy_id_mask	= 0xffffffff,
+		.name		= "Intel XWAY PHY22F (PEF 7061) v1.4",
+		.features	= (PHY_BASIC_FEATURES | SUPPORTED_Pause |
+				   SUPPORTED_Asym_Pause),
+		.flags		= PHY_HAS_INTERRUPT,
+		.config_init	= xway_gphy_config_init,
+		.config_aneg	= xway_gphy14_config_aneg,
+		.read_status	= genphy_read_status,
+		.ack_interrupt	= xway_gphy_ack_interrupt,
+		.did_interrupt	= xway_gphy_did_interrupt,
+		.config_intr	= xway_gphy_config_intr,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+	}, {
+		.phy_id		= PHY_ID_PHY11G_1_5,
+		.phy_id_mask	= 0xffffffff,
+		.name		= "Intel XWAY PHY11G (PEF 7071/PEF 7072) v1.5 / v1.6",
+		.features	= (PHY_GBIT_FEATURES | SUPPORTED_Pause |
+				   SUPPORTED_Asym_Pause),
+		.flags		= PHY_HAS_INTERRUPT,
+		.config_init	= xway_gphy_config_init,
+		.config_aneg	= genphy_config_aneg,
+		.read_status	= genphy_read_status,
+		.ack_interrupt	= xway_gphy_ack_interrupt,
+		.did_interrupt	= xway_gphy_did_interrupt,
+		.config_intr	= xway_gphy_config_intr,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+	}, {
+		.phy_id		= PHY_ID_PHY22F_1_5,
+		.phy_id_mask	= 0xffffffff,
+		.name		= "Intel XWAY PHY22F (PEF 7061) v1.5 / v1.6",
+		.features	= (PHY_BASIC_FEATURES | SUPPORTED_Pause |
+				   SUPPORTED_Asym_Pause),
+		.flags		= PHY_HAS_INTERRUPT,
+		.config_init	= xway_gphy_config_init,
+		.config_aneg	= genphy_config_aneg,
+		.read_status	= genphy_read_status,
+		.ack_interrupt	= xway_gphy_ack_interrupt,
+		.did_interrupt	= xway_gphy_did_interrupt,
+		.config_intr	= xway_gphy_config_intr,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+	}, {
+		.phy_id		= PHY_ID_PHY11G_VR9,
+		.phy_id_mask	= 0xffffffff,
+		.name		= "Intel XWAY PHY11G (xRX integrated)",
+		.features	= (PHY_GBIT_FEATURES | SUPPORTED_Pause |
+				   SUPPORTED_Asym_Pause),
+		.flags		= PHY_HAS_INTERRUPT,
+		.config_init	= xway_gphy_config_init,
+		.config_aneg	= genphy_config_aneg,
+		.read_status	= genphy_read_status,
+		.ack_interrupt	= xway_gphy_ack_interrupt,
+		.did_interrupt	= xway_gphy_did_interrupt,
+		.config_intr	= xway_gphy_config_intr,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+	}, {
+		.phy_id		= PHY_ID_PHY22F_VR9,
+		.phy_id_mask	= 0xffffffff,
+		.name		= "Intel XWAY PHY22F (xRX integrated)",
+		.features	= (PHY_BASIC_FEATURES | SUPPORTED_Pause |
+				   SUPPORTED_Asym_Pause),
+		.flags		= PHY_HAS_INTERRUPT,
+		.config_init	= xway_gphy_config_init,
+		.config_aneg	= genphy_config_aneg,
+		.read_status	= genphy_read_status,
+		.ack_interrupt	= xway_gphy_ack_interrupt,
+		.did_interrupt	= xway_gphy_did_interrupt,
+		.config_intr	= xway_gphy_config_intr,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+	},
+};
+module_phy_driver(xway_gphy);
+
+static struct mdio_device_id __maybe_unused xway_gphy_tbl[] = {
+	{ PHY_ID_PHY11G_1_3, 0xffffffff },
+	{ PHY_ID_PHY22F_1_3, 0xffffffff },
+	{ PHY_ID_PHY11G_1_4, 0xffffffff },
+	{ PHY_ID_PHY22F_1_4, 0xffffffff },
+	{ PHY_ID_PHY11G_1_5, 0xffffffff },
+	{ PHY_ID_PHY22F_1_5, 0xffffffff },
+	{ PHY_ID_PHY11G_VR9, 0xffffffff },
+	{ PHY_ID_PHY22F_VR9, 0xffffffff },
+	{ }
+};
+MODULE_DEVICE_TABLE(mdio, xway_gphy_tbl);
+
+MODULE_DESCRIPTION("Intel XWAY PHY driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/phy/mdio-mux-bcm-iproc.c b/drivers/net/phy/mdio-mux-bcm-iproc.c
new file mode 100644
index 0000000..0a04125
--- /dev/null
+++ b/drivers/net/phy/mdio-mux-bcm-iproc.c
@@ -0,0 +1,248 @@
+/*
+ * Copyright 2016 Broadcom
+ *
+ * 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 (the "GPL").
+ *
+ * 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 version 2 (GPLv2) for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * version 2 (GPLv2) along with this source code.
+ */
+
+#include <linux/platform_device.h>
+#include <linux/device.h>
+#include <linux/of_mdio.h>
+#include <linux/module.h>
+#include <linux/phy.h>
+#include <linux/mdio-mux.h>
+#include <linux/delay.h>
+
+#define MDIO_PARAM_OFFSET		0x00
+#define MDIO_PARAM_MIIM_CYCLE		29
+#define MDIO_PARAM_INTERNAL_SEL		25
+#define MDIO_PARAM_BUS_ID		22
+#define MDIO_PARAM_C45_SEL		21
+#define MDIO_PARAM_PHY_ID		16
+#define MDIO_PARAM_PHY_DATA		0
+
+#define MDIO_READ_OFFSET		0x04
+#define MDIO_READ_DATA_MASK		0xffff
+#define MDIO_ADDR_OFFSET		0x08
+
+#define MDIO_CTRL_OFFSET		0x0C
+#define MDIO_CTRL_WRITE_OP		0x1
+#define MDIO_CTRL_READ_OP		0x2
+
+#define MDIO_STAT_OFFSET		0x10
+#define MDIO_STAT_DONE			1
+
+#define BUS_MAX_ADDR			32
+#define EXT_BUS_START_ADDR		16
+
+struct iproc_mdiomux_desc {
+	void *mux_handle;
+	void __iomem *base;
+	struct device *dev;
+	struct mii_bus *mii_bus;
+};
+
+static int iproc_mdio_wait_for_idle(void __iomem *base, bool result)
+{
+	unsigned int timeout = 1000; /* loop for 1s */
+	u32 val;
+
+	do {
+		val = readl(base + MDIO_STAT_OFFSET);
+		if ((val & MDIO_STAT_DONE) == result)
+			return 0;
+
+		usleep_range(1000, 2000);
+	} while (timeout--);
+
+	return -ETIMEDOUT;
+}
+
+/* start_miim_ops- Program and start MDIO transaction over mdio bus.
+ * @base: Base address
+ * @phyid: phyid of the selected bus.
+ * @reg: register offset to be read/written.
+ * @val :0 if read op else value to be written in @reg;
+ * @op: Operation that need to be carried out.
+ *      MDIO_CTRL_READ_OP: Read transaction.
+ *      MDIO_CTRL_WRITE_OP: Write transaction.
+ *
+ * Return value: Successful Read operation returns read reg values and write
+ *      operation returns 0. Failure operation returns negative error code.
+ */
+static int start_miim_ops(void __iomem *base,
+			  u16 phyid, u32 reg, u16 val, u32 op)
+{
+	u32 param;
+	int ret;
+
+	writel(0, base + MDIO_CTRL_OFFSET);
+	ret = iproc_mdio_wait_for_idle(base, 0);
+	if (ret)
+		goto err;
+
+	param = readl(base + MDIO_PARAM_OFFSET);
+	param |= phyid << MDIO_PARAM_PHY_ID;
+	param |= val << MDIO_PARAM_PHY_DATA;
+	if (reg & MII_ADDR_C45)
+		param |= BIT(MDIO_PARAM_C45_SEL);
+
+	writel(param, base + MDIO_PARAM_OFFSET);
+
+	writel(reg, base + MDIO_ADDR_OFFSET);
+
+	writel(op, base + MDIO_CTRL_OFFSET);
+
+	ret = iproc_mdio_wait_for_idle(base, 1);
+	if (ret)
+		goto err;
+
+	if (op == MDIO_CTRL_READ_OP)
+		ret = readl(base + MDIO_READ_OFFSET) & MDIO_READ_DATA_MASK;
+err:
+	return ret;
+}
+
+static int iproc_mdiomux_read(struct mii_bus *bus, int phyid, int reg)
+{
+	struct iproc_mdiomux_desc *md = bus->priv;
+	int ret;
+
+	ret = start_miim_ops(md->base, phyid, reg, 0, MDIO_CTRL_READ_OP);
+	if (ret < 0)
+		dev_err(&bus->dev, "mdiomux read operation failed!!!");
+
+	return ret;
+}
+
+static int iproc_mdiomux_write(struct mii_bus *bus,
+			       int phyid, int reg, u16 val)
+{
+	struct iproc_mdiomux_desc *md = bus->priv;
+	int ret;
+
+	/* Write val at reg offset */
+	ret = start_miim_ops(md->base, phyid, reg, val, MDIO_CTRL_WRITE_OP);
+	if (ret < 0)
+		dev_err(&bus->dev, "mdiomux write operation failed!!!");
+
+	return ret;
+}
+
+static int mdio_mux_iproc_switch_fn(int current_child, int desired_child,
+				    void *data)
+{
+	struct iproc_mdiomux_desc *md = data;
+	u32 param, bus_id;
+	bool bus_dir;
+
+	/* select bus and its properties */
+	bus_dir = (desired_child < EXT_BUS_START_ADDR);
+	bus_id = bus_dir ? desired_child : (desired_child - EXT_BUS_START_ADDR);
+
+	param = (bus_dir ? 1 : 0) << MDIO_PARAM_INTERNAL_SEL;
+	param |= (bus_id << MDIO_PARAM_BUS_ID);
+
+	writel(param, md->base + MDIO_PARAM_OFFSET);
+	return 0;
+}
+
+static int mdio_mux_iproc_probe(struct platform_device *pdev)
+{
+	struct iproc_mdiomux_desc *md;
+	struct mii_bus *bus;
+	struct resource *res;
+	int rc;
+
+	md = devm_kzalloc(&pdev->dev, sizeof(*md), GFP_KERNEL);
+	if (!md)
+		return -ENOMEM;
+	md->dev = &pdev->dev;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	md->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(md->base)) {
+		dev_err(&pdev->dev, "failed to ioremap register\n");
+		return PTR_ERR(md->base);
+	}
+
+	md->mii_bus = mdiobus_alloc();
+	if (!md->mii_bus) {
+		dev_err(&pdev->dev, "mdiomux bus alloc failed\n");
+		return -ENOMEM;
+	}
+
+	bus = md->mii_bus;
+	bus->priv = md;
+	bus->name = "iProc MDIO mux bus";
+	snprintf(bus->id, MII_BUS_ID_SIZE, "%s-%d", pdev->name, pdev->id);
+	bus->parent = &pdev->dev;
+	bus->read = iproc_mdiomux_read;
+	bus->write = iproc_mdiomux_write;
+
+	bus->phy_mask = ~0;
+	bus->dev.of_node = pdev->dev.of_node;
+	rc = mdiobus_register(bus);
+	if (rc) {
+		dev_err(&pdev->dev, "mdiomux registration failed\n");
+		goto out;
+	}
+
+	platform_set_drvdata(pdev, md);
+
+	rc = mdio_mux_init(md->dev, mdio_mux_iproc_switch_fn,
+			   &md->mux_handle, md, md->mii_bus);
+	if (rc) {
+		dev_info(md->dev, "mdiomux initialization failed\n");
+		goto out;
+	}
+
+	dev_info(md->dev, "iProc mdiomux registered\n");
+	return 0;
+out:
+	mdiobus_free(bus);
+	return rc;
+}
+
+static int mdio_mux_iproc_remove(struct platform_device *pdev)
+{
+	struct iproc_mdiomux_desc *md = dev_get_platdata(&pdev->dev);
+
+	mdio_mux_uninit(md->mux_handle);
+	mdiobus_unregister(md->mii_bus);
+	mdiobus_free(md->mii_bus);
+
+	return 0;
+}
+
+static const struct of_device_id mdio_mux_iproc_match[] = {
+	{
+		.compatible = "brcm,mdio-mux-iproc",
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(of, mdio_mux_iproc_match);
+
+static struct platform_driver mdiomux_iproc_driver = {
+	.driver = {
+		.name		= "mdio-mux-iproc",
+		.of_match_table = mdio_mux_iproc_match,
+	},
+	.probe		= mdio_mux_iproc_probe,
+	.remove		= mdio_mux_iproc_remove,
+};
+
+module_platform_driver(mdiomux_iproc_driver);
+
+MODULE_DESCRIPTION("iProc MDIO Mux Bus Driver");
+MODULE_AUTHOR("Pramod Kumar <pramod.kumar@broadcom.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/phy/mdio-mux-gpio.c b/drivers/net/phy/mdio-mux-gpio.c
index 7ddb1ab..9199499 100644
--- a/drivers/net/phy/mdio-mux-gpio.c
+++ b/drivers/net/phy/mdio-mux-gpio.c
@@ -55,7 +55,7 @@
 		return PTR_ERR(s->gpios);
 
 	r = mdio_mux_init(&pdev->dev,
-			  mdio_mux_gpio_switch_fn, &s->mux_handle, s);
+			  mdio_mux_gpio_switch_fn, &s->mux_handle, s, NULL);
 
 	if (r != 0) {
 		gpiod_put_array(s->gpios);
diff --git a/drivers/net/phy/mdio-mux-mmioreg.c b/drivers/net/phy/mdio-mux-mmioreg.c
index 7fde454..d0bed52 100644
--- a/drivers/net/phy/mdio-mux-mmioreg.c
+++ b/drivers/net/phy/mdio-mux-mmioreg.c
@@ -126,7 +126,7 @@
 	}
 
 	ret = mdio_mux_init(&pdev->dev, mdio_mux_mmioreg_switch_fn,
-			    &s->mux_handle, s);
+			    &s->mux_handle, s, NULL);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to register mdio-mux bus %s\n",
 			np->full_name);
diff --git a/drivers/net/phy/mdio-mux.c b/drivers/net/phy/mdio-mux.c
index 5c81d6f..963838d 100644
--- a/drivers/net/phy/mdio-mux.c
+++ b/drivers/net/phy/mdio-mux.c
@@ -89,7 +89,8 @@
 int mdio_mux_init(struct device *dev,
 		  int (*switch_fn)(int cur, int desired, void *data),
 		  void **mux_handle,
-		  void *data)
+		  void *data,
+		  struct mii_bus *mux_bus)
 {
 	struct device_node *parent_bus_node;
 	struct device_node *child_bus_node;
@@ -101,10 +102,22 @@
 	if (!dev->of_node)
 		return -ENODEV;
 
-	parent_bus_node = of_parse_phandle(dev->of_node, "mdio-parent-bus", 0);
+	if (!mux_bus) {
+		parent_bus_node = of_parse_phandle(dev->of_node,
+						   "mdio-parent-bus", 0);
 
-	if (!parent_bus_node)
-		return -ENODEV;
+		if (!parent_bus_node)
+			return -ENODEV;
+
+		parent_bus = of_mdio_find_bus(parent_bus_node);
+		if (!parent_bus) {
+			ret_val = -EPROBE_DEFER;
+			goto err_parent_bus;
+		}
+	} else {
+		parent_bus_node = NULL;
+		parent_bus = mux_bus;
+	}
 
 	pb = devm_kzalloc(dev, sizeof(*pb), GFP_KERNEL);
 	if (pb == NULL) {
@@ -112,11 +125,6 @@
 		goto err_parent_bus;
 	}
 
-	parent_bus = of_mdio_find_bus(parent_bus_node);
-	if (parent_bus == NULL) {
-		ret_val = -EPROBE_DEFER;
-		goto err_parent_bus;
-	}
 
 	pb->switch_data = data;
 	pb->switch_fn = switch_fn;
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 8dedafa..17953ab 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -1312,10 +1312,9 @@
 	return stats64;
 }
 
-static struct lock_class_key ppp_tx_busylock;
 static int ppp_dev_init(struct net_device *dev)
 {
-	dev->qdisc_tx_busylock = &ppp_tx_busylock;
+	netdev_lockdep_set_classes(dev);
 	return 0;
 }
 
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 2ace126..0a1bb83 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1574,23 +1574,6 @@
 	},
 };
 
-static struct lock_class_key team_netdev_xmit_lock_key;
-static struct lock_class_key team_netdev_addr_lock_key;
-static struct lock_class_key team_tx_busylock_key;
-
-static void team_set_lockdep_class_one(struct net_device *dev,
-				       struct netdev_queue *txq,
-				       void *unused)
-{
-	lockdep_set_class(&txq->_xmit_lock, &team_netdev_xmit_lock_key);
-}
-
-static void team_set_lockdep_class(struct net_device *dev)
-{
-	lockdep_set_class(&dev->addr_list_lock, &team_netdev_addr_lock_key);
-	netdev_for_each_tx_queue(dev, team_set_lockdep_class_one, NULL);
-	dev->qdisc_tx_busylock = &team_tx_busylock_key;
-}
 
 static int team_init(struct net_device *dev)
 {
@@ -1626,7 +1609,7 @@
 		goto err_options_register;
 	netif_carrier_off(dev);
 
-	team_set_lockdep_class(dev);
+	netdev_lockdep_set_classes(dev);
 
 	return 0;
 
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index e16487c..4884802 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1254,13 +1254,11 @@
 		return -EFAULT;
 	}
 
-	if (gso.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
-		if (!skb_partial_csum_set(skb, tun16_to_cpu(tun, gso.csum_start),
-					  tun16_to_cpu(tun, gso.csum_offset))) {
-			this_cpu_inc(tun->pcpu_stats->rx_frame_errors);
-			kfree_skb(skb);
-			return -EINVAL;
-		}
+	err = virtio_net_hdr_to_skb(skb, &gso, tun_is_little_endian(tun));
+	if (err) {
+		this_cpu_inc(tun->pcpu_stats->rx_frame_errors);
+		kfree_skb(skb);
+		return -EINVAL;
 	}
 
 	switch (tun->flags & TUN_TYPE_MASK) {
@@ -1289,39 +1287,6 @@
 		break;
 	}
 
-	if (gso.gso_type != VIRTIO_NET_HDR_GSO_NONE) {
-		pr_debug("GSO!\n");
-		switch (gso.gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
-		case VIRTIO_NET_HDR_GSO_TCPV4:
-			skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
-			break;
-		case VIRTIO_NET_HDR_GSO_TCPV6:
-			skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
-			break;
-		case VIRTIO_NET_HDR_GSO_UDP:
-			skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
-			break;
-		default:
-			this_cpu_inc(tun->pcpu_stats->rx_frame_errors);
-			kfree_skb(skb);
-			return -EINVAL;
-		}
-
-		if (gso.gso_type & VIRTIO_NET_HDR_GSO_ECN)
-			skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;
-
-		skb_shinfo(skb)->gso_size = tun16_to_cpu(tun, gso.gso_size);
-		if (skb_shinfo(skb)->gso_size == 0) {
-			this_cpu_inc(tun->pcpu_stats->rx_frame_errors);
-			kfree_skb(skb);
-			return -EINVAL;
-		}
-
-		/* Header must be checked, and gso_segs computed. */
-		skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
-		skb_shinfo(skb)->gso_segs = 0;
-	}
-
 	/* copy skb_ubuf_info for callback when skb has no error */
 	if (zerocopy) {
 		skb_shinfo(skb)->destructor_arg = msg_control;
@@ -1399,46 +1364,26 @@
 
 	if (vnet_hdr_sz) {
 		struct virtio_net_hdr gso = { 0 }; /* no info leak */
+		int ret;
+
 		if (iov_iter_count(iter) < vnet_hdr_sz)
 			return -EINVAL;
 
-		if (skb_is_gso(skb)) {
+		ret = virtio_net_hdr_from_skb(skb, &gso,
+					      tun_is_little_endian(tun));
+		if (ret) {
 			struct skb_shared_info *sinfo = skb_shinfo(skb);
-
-			/* This is a hint as to how much should be linear. */
-			gso.hdr_len = cpu_to_tun16(tun, skb_headlen(skb));
-			gso.gso_size = cpu_to_tun16(tun, sinfo->gso_size);
-			if (sinfo->gso_type & SKB_GSO_TCPV4)
-				gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
-			else if (sinfo->gso_type & SKB_GSO_TCPV6)
-				gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
-			else if (sinfo->gso_type & SKB_GSO_UDP)
-				gso.gso_type = VIRTIO_NET_HDR_GSO_UDP;
-			else {
-				pr_err("unexpected GSO type: "
-				       "0x%x, gso_size %d, hdr_len %d\n",
-				       sinfo->gso_type, tun16_to_cpu(tun, gso.gso_size),
-				       tun16_to_cpu(tun, gso.hdr_len));
-				print_hex_dump(KERN_ERR, "tun: ",
-					       DUMP_PREFIX_NONE,
-					       16, 1, skb->head,
-					       min((int)tun16_to_cpu(tun, gso.hdr_len), 64), true);
-				WARN_ON_ONCE(1);
-				return -EINVAL;
-			}
-			if (sinfo->gso_type & SKB_GSO_TCP_ECN)
-				gso.gso_type |= VIRTIO_NET_HDR_GSO_ECN;
-		} else
-			gso.gso_type = VIRTIO_NET_HDR_GSO_NONE;
-
-		if (skb->ip_summed == CHECKSUM_PARTIAL) {
-			gso.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
-			gso.csum_start = cpu_to_tun16(tun, skb_checksum_start_offset(skb) +
-						      vlan_hlen);
-			gso.csum_offset = cpu_to_tun16(tun, skb->csum_offset);
-		} else if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
-			gso.flags = VIRTIO_NET_HDR_F_DATA_VALID;
-		} /* else everything is zero */
+			pr_err("unexpected GSO type: "
+			       "0x%x, gso_size %d, hdr_len %d\n",
+			       sinfo->gso_type, tun16_to_cpu(tun, gso.gso_size),
+			       tun16_to_cpu(tun, gso.hdr_len));
+			print_hex_dump(KERN_ERR, "tun: ",
+				       DUMP_PREFIX_NONE,
+				       16, 1, skb->head,
+				       min((int)tun16_to_cpu(tun, gso.hdr_len), 64), true);
+			WARN_ON_ONCE(1);
+			return -EINVAL;
+		}
 
 		if (copy_to_iter(&gso, sizeof(gso), iter) != sizeof(gso))
 			return -EFAULT;
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 3f9f6ed..11178f9 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -602,7 +602,7 @@
 	struct list_head rx_done, tx_free;
 	struct sk_buff_head tx_queue, rx_queue;
 	spinlock_t rx_lock, tx_lock;
-	struct delayed_work schedule;
+	struct delayed_work schedule, hw_phy_work;
 	struct mii_if_info mii;
 	struct mutex control;	/* use for hw setting */
 #ifdef CONFIG_PM_SLEEP
@@ -619,6 +619,7 @@
 		int (*eee_get)(struct r8152 *, struct ethtool_eee *);
 		int (*eee_set)(struct r8152 *, struct ethtool_eee *);
 		bool (*in_nway)(struct r8152 *);
+		void (*hw_phy_cfg)(struct r8152 *);
 	} rtl_ops;
 
 	int intr_interval;
@@ -627,8 +628,11 @@
 	u32 tx_qlen;
 	u32 coalesce;
 	u16 ocp_base;
+	u16 speed;
 	u8 *intr_buff;
 	u8 version;
+	u8 duplex;
+	u8 autoneg;
 };
 
 enum rtl_version {
@@ -1742,7 +1746,7 @@
 			pkt_len -= CRC_SIZE;
 			rx_data += sizeof(struct rx_desc);
 
-			skb = netdev_alloc_skb_ip_align(netdev, pkt_len);
+			skb = napi_alloc_skb(&tp->napi, pkt_len);
 			if (!skb) {
 				stats->rx_dropped++;
 				goto find_next_rx;
@@ -2499,8 +2503,6 @@
 
 	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);
 
@@ -2678,8 +2680,6 @@
 	ocp_data &= ~RCR_ACPT_ALL;
 	ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RCR, ocp_data);
 
-	r8153_hw_phy_cfg(tp);
-
 	rtl8152_nic_reset(tp);
 
 	ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL);
@@ -2872,7 +2872,7 @@
 		bmcr = BMCR_ANENABLE | BMCR_ANRESTART;
 	}
 
-	if (test_bit(PHY_RESET, &tp->flags))
+	if (test_and_clear_bit(PHY_RESET, &tp->flags))
 		bmcr |= BMCR_RESET;
 
 	if (tp->mii.supports_gmii)
@@ -2881,7 +2881,7 @@
 	r8152_mdio_write(tp, MII_ADVERTISE, anar);
 	r8152_mdio_write(tp, MII_BMCR, bmcr);
 
-	if (test_and_clear_bit(PHY_RESET, &tp->flags)) {
+	if (bmcr & BMCR_RESET) {
 		int i;
 
 		for (i = 0; i < 50; i++) {
@@ -3040,6 +3040,27 @@
 	usb_autopm_put_interface(tp->intf);
 }
 
+static void rtl_hw_phy_work_func_t(struct work_struct *work)
+{
+	struct r8152 *tp = container_of(work, struct r8152, hw_phy_work.work);
+
+	if (test_bit(RTL8152_UNPLUG, &tp->flags))
+		return;
+
+	if (usb_autopm_get_interface(tp->intf) < 0)
+		return;
+
+	mutex_lock(&tp->control);
+
+	tp->rtl_ops.hw_phy_cfg(tp);
+
+	rtl8152_set_speed(tp, tp->autoneg, tp->speed, tp->duplex);
+
+	mutex_unlock(&tp->control);
+
+	usb_autopm_put_interface(tp->intf);
+}
+
 #ifdef CONFIG_PM_SLEEP
 static int rtl_notifier(struct notifier_block *nb, unsigned long action,
 			void *data)
@@ -3088,9 +3109,6 @@
 
 	tp->rtl_ops.up(tp);
 
-	rtl8152_set_speed(tp, AUTONEG_ENABLE,
-			  tp->mii.supports_gmii ? SPEED_1000 : SPEED_100,
-			  DUPLEX_FULL);
 	netif_carrier_off(netdev);
 	netif_start_queue(netdev);
 	set_bit(WORK_ENABLE, &tp->flags);
@@ -3518,6 +3536,7 @@
 
 	if (!test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
 		tp->rtl_ops.init(tp);
+		queue_delayed_work(system_long_wq, &tp->hw_phy_work, 0);
 		netif_device_attach(tp->netdev);
 	}
 
@@ -3532,10 +3551,6 @@
 			napi_enable(&tp->napi);
 		} else {
 			tp->rtl_ops.up(tp);
-			rtl8152_set_speed(tp, AUTONEG_ENABLE,
-					  tp->mii.supports_gmii ?
-					  SPEED_1000 : SPEED_100,
-					  DUPLEX_FULL);
 			netif_carrier_off(tp->netdev);
 			set_bit(WORK_ENABLE, &tp->flags);
 		}
@@ -3665,6 +3680,11 @@
 	mutex_lock(&tp->control);
 
 	ret = rtl8152_set_speed(tp, cmd->autoneg, cmd->speed, cmd->duplex);
+	if (!ret) {
+		tp->autoneg = cmd->autoneg;
+		tp->speed = cmd->speed;
+		tp->duplex = cmd->duplex;
+	}
 
 	mutex_unlock(&tp->control);
 
@@ -4122,6 +4142,7 @@
 		ops->eee_get		= r8152_get_eee;
 		ops->eee_set		= r8152_set_eee;
 		ops->in_nway		= rtl8152_in_nway;
+		ops->hw_phy_cfg		= r8152b_hw_phy_cfg;
 		break;
 
 	case RTL_VER_03:
@@ -4137,6 +4158,7 @@
 		ops->eee_get		= r8153_get_eee;
 		ops->eee_set		= r8153_set_eee;
 		ops->in_nway		= rtl8153_in_nway;
+		ops->hw_phy_cfg		= r8153_hw_phy_cfg;
 		break;
 
 	default:
@@ -4183,6 +4205,7 @@
 
 	mutex_init(&tp->control);
 	INIT_DELAYED_WORK(&tp->schedule, rtl_work_func_t);
+	INIT_DELAYED_WORK(&tp->hw_phy_work, rtl_hw_phy_work_func_t);
 
 	netdev->netdev_ops = &rtl8152_netdev_ops;
 	netdev->watchdog_timeo = RTL8152_TX_TIMEOUT;
@@ -4222,9 +4245,14 @@
 		break;
 	}
 
+	tp->autoneg = AUTONEG_ENABLE;
+	tp->speed = tp->mii.supports_gmii ? SPEED_1000 : SPEED_100;
+	tp->duplex = DUPLEX_FULL;
+
 	intf->needs_remote_wakeup = 1;
 
 	tp->rtl_ops.init(tp);
+	queue_delayed_work(system_long_wq, &tp->hw_phy_work, 0);
 	set_ethernet_addr(tp);
 
 	usb_set_intfdata(intf, tp);
@@ -4270,6 +4298,7 @@
 
 		netif_napi_del(&tp->napi);
 		unregister_netdev(tp->netdev);
+		cancel_delayed_work_sync(&tp->hw_phy_work);
 		tp->rtl_ops.unload(tp);
 		free_netdev(tp->netdev);
 	}
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index e0638e5..1dd08d4 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -479,53 +479,21 @@
 	stats->rx_packets++;
 	u64_stats_update_end(&stats->rx_syncp);
 
-	if (hdr->hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
-		pr_debug("Needs csum!\n");
-		if (!skb_partial_csum_set(skb,
-			  virtio16_to_cpu(vi->vdev, hdr->hdr.csum_start),
-			  virtio16_to_cpu(vi->vdev, hdr->hdr.csum_offset)))
-			goto frame_err;
-	} else if (hdr->hdr.flags & VIRTIO_NET_HDR_F_DATA_VALID) {
+	if (hdr->hdr.flags & VIRTIO_NET_HDR_F_DATA_VALID)
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+	if (virtio_net_hdr_to_skb(skb, &hdr->hdr,
+				  virtio_is_little_endian(vi->vdev))) {
+		net_warn_ratelimited("%s: bad gso: type: %u, size: %u\n",
+				     dev->name, hdr->hdr.gso_type,
+				     hdr->hdr.gso_size);
+		goto frame_err;
 	}
 
 	skb->protocol = eth_type_trans(skb, dev);
 	pr_debug("Receiving skb proto 0x%04x len %i type %i\n",
 		 ntohs(skb->protocol), skb->len, skb->pkt_type);
 
-	if (hdr->hdr.gso_type != VIRTIO_NET_HDR_GSO_NONE) {
-		pr_debug("GSO!\n");
-		switch (hdr->hdr.gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
-		case VIRTIO_NET_HDR_GSO_TCPV4:
-			skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
-			break;
-		case VIRTIO_NET_HDR_GSO_UDP:
-			skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
-			break;
-		case VIRTIO_NET_HDR_GSO_TCPV6:
-			skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
-			break;
-		default:
-			net_warn_ratelimited("%s: bad gso type %u.\n",
-					     dev->name, hdr->hdr.gso_type);
-			goto frame_err;
-		}
-
-		if (hdr->hdr.gso_type & VIRTIO_NET_HDR_GSO_ECN)
-			skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;
-
-		skb_shinfo(skb)->gso_size = virtio16_to_cpu(vi->vdev,
-							    hdr->hdr.gso_size);
-		if (skb_shinfo(skb)->gso_size == 0) {
-			net_warn_ratelimited("%s: zero gso size.\n", dev->name);
-			goto frame_err;
-		}
-
-		/* Header must be checked, and gso_segs computed. */
-		skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
-		skb_shinfo(skb)->gso_segs = 0;
-	}
-
 	napi_gro_receive(&rq->napi, skb);
 	return;
 
@@ -868,35 +836,9 @@
 	else
 		hdr = skb_vnet_hdr(skb);
 
-	if (skb->ip_summed == CHECKSUM_PARTIAL) {
-		hdr->hdr.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
-		hdr->hdr.csum_start = cpu_to_virtio16(vi->vdev,
-						skb_checksum_start_offset(skb));
-		hdr->hdr.csum_offset = cpu_to_virtio16(vi->vdev,
-							 skb->csum_offset);
-	} else {
-		hdr->hdr.flags = 0;
-		hdr->hdr.csum_offset = hdr->hdr.csum_start = 0;
-	}
-
-	if (skb_is_gso(skb)) {
-		hdr->hdr.hdr_len = cpu_to_virtio16(vi->vdev, skb_headlen(skb));
-		hdr->hdr.gso_size = cpu_to_virtio16(vi->vdev,
-						    skb_shinfo(skb)->gso_size);
-		if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
-			hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
-		else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
-			hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
-		else if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
-			hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_UDP;
-		else
-			BUG();
-		if (skb_shinfo(skb)->gso_type & SKB_GSO_TCP_ECN)
-			hdr->hdr.gso_type |= VIRTIO_NET_HDR_GSO_ECN;
-	} else {
-		hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_NONE;
-		hdr->hdr.gso_size = hdr->hdr.hdr_len = 0;
-	}
+	if (virtio_net_hdr_from_skb(skb, &hdr->hdr,
+				    virtio_is_little_endian(vi->vdev)))
+		BUG();
 
 	if (vi->mergeable_rx_bufs)
 		hdr->num_buffers = 0;
@@ -1780,6 +1722,7 @@
 	struct net_device *dev;
 	struct virtnet_info *vi;
 	u16 max_queue_pairs;
+	int mtu;
 
 	if (!vdev->config->get) {
 		dev_err(&vdev->dev, "%s failure: config access disabled\n",
@@ -1896,6 +1839,14 @@
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ))
 		vi->has_cvq = true;
 
+	if (virtio_has_feature(vdev, VIRTIO_NET_F_MTU)) {
+		mtu = virtio_cread16(vdev,
+				     offsetof(struct virtio_net_config,
+					      mtu));
+		if (virtnet_change_mtu(dev, mtu))
+			__virtio_clear_bit(vdev, VIRTIO_NET_F_MTU);
+	}
+
 	if (vi->any_header_sg)
 		dev->needed_headroom = vi->hdr_len;
 
@@ -2067,6 +2018,7 @@
 	VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ,
 	VIRTIO_NET_F_CTRL_MAC_ADDR,
 	VIRTIO_F_ANY_LAYOUT,
+	VIRTIO_NET_F_MTU,
 };
 
 static struct virtio_driver virtio_net_driver = {
diff --git a/drivers/net/vmxnet3/Makefile b/drivers/net/vmxnet3/Makefile
index 880f509..8cdbb63 100644
--- a/drivers/net/vmxnet3/Makefile
+++ b/drivers/net/vmxnet3/Makefile
@@ -2,7 +2,7 @@
 #
 # Linux driver for VMware's vmxnet3 ethernet NIC.
 #
-# Copyright (C) 2007-2009, VMware, Inc. All Rights Reserved.
+# Copyright (C) 2007-2016, VMware, Inc. 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 as published by the
@@ -21,7 +21,7 @@
 # The full GNU General Public License is included in this distribution in
 # the file called "COPYING".
 #
-# Maintained by: Shreyas Bhatewara <pv-drivers@vmware.com>
+# Maintained by: pv-drivers@vmware.com
 #
 #
 ################################################################################
diff --git a/drivers/net/vmxnet3/upt1_defs.h b/drivers/net/vmxnet3/upt1_defs.h
index 969c751..db9f1fd 100644
--- a/drivers/net/vmxnet3/upt1_defs.h
+++ b/drivers/net/vmxnet3/upt1_defs.h
@@ -1,7 +1,7 @@
 /*
  * Linux driver for VMware's vmxnet3 ethernet NIC.
  *
- * Copyright (C) 2008-2009, VMware, Inc. All Rights Reserved.
+ * Copyright (C) 2008-2016, VMware, Inc. 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 as published by the
@@ -20,7 +20,7 @@
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
- * Maintained by: Shreyas Bhatewara <pv-drivers@vmware.com>
+ * Maintained by: pv-drivers@vmware.com
  *
  */
 
diff --git a/drivers/net/vmxnet3/vmxnet3_defs.h b/drivers/net/vmxnet3/vmxnet3_defs.h
index 72ba8ae..c3a3164 100644
--- a/drivers/net/vmxnet3/vmxnet3_defs.h
+++ b/drivers/net/vmxnet3/vmxnet3_defs.h
@@ -1,7 +1,7 @@
 /*
  * Linux driver for VMware's vmxnet3 ethernet NIC.
  *
- * Copyright (C) 2008-2015, VMware, Inc. All Rights Reserved.
+ * Copyright (C) 2008-2016, VMware, Inc. 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 as published by the
@@ -20,7 +20,7 @@
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
- * Maintained by: Shreyas Bhatewara <pv-drivers@vmware.com>
+ * Maintained by: pv-drivers@vmware.com
  *
  */
 
@@ -76,7 +76,12 @@
 	VMXNET3_CMD_UPDATE_IML,
 	VMXNET3_CMD_UPDATE_PMCFG,
 	VMXNET3_CMD_UPDATE_FEATURE,
+	VMXNET3_CMD_RESERVED1,
 	VMXNET3_CMD_LOAD_PLUGIN,
+	VMXNET3_CMD_RESERVED2,
+	VMXNET3_CMD_RESERVED3,
+	VMXNET3_CMD_SET_COALESCE,
+	VMXNET3_CMD_REGISTER_MEMREGS,
 
 	VMXNET3_CMD_FIRST_GET = 0xF00D0000,
 	VMXNET3_CMD_GET_QUEUE_STATUS = VMXNET3_CMD_FIRST_GET,
@@ -87,7 +92,10 @@
 	VMXNET3_CMD_GET_DID_LO,
 	VMXNET3_CMD_GET_DID_HI,
 	VMXNET3_CMD_GET_DEV_EXTRA_INFO,
-	VMXNET3_CMD_GET_CONF_INTR
+	VMXNET3_CMD_GET_CONF_INTR,
+	VMXNET3_CMD_GET_RESERVED1,
+	VMXNET3_CMD_GET_TXDATA_DESC_SIZE,
+	VMXNET3_CMD_GET_COALESCE,
 };
 
 /*
@@ -169,6 +177,8 @@
 	u8		data[VMXNET3_HDR_COPY_SIZE];
 };
 
+typedef u8 Vmxnet3_RxDataDesc;
+
 #define VMXNET3_TCD_GEN_SHIFT	31
 #define VMXNET3_TCD_GEN_SIZE	1
 #define VMXNET3_TCD_TXIDX_SHIFT	0
@@ -373,6 +383,14 @@
 #define VMXNET3_RING_SIZE_ALIGN 32
 #define VMXNET3_RING_SIZE_MASK  (VMXNET3_RING_SIZE_ALIGN - 1)
 
+/* Tx Data Ring buffer size must be a multiple of 64 */
+#define VMXNET3_TXDATA_DESC_SIZE_ALIGN 64
+#define VMXNET3_TXDATA_DESC_SIZE_MASK  (VMXNET3_TXDATA_DESC_SIZE_ALIGN - 1)
+
+/* Rx Data Ring buffer size must be a multiple of 64 */
+#define VMXNET3_RXDATA_DESC_SIZE_ALIGN 64
+#define VMXNET3_RXDATA_DESC_SIZE_MASK  (VMXNET3_RXDATA_DESC_SIZE_ALIGN - 1)
+
 /* Max ring size */
 #define VMXNET3_TX_RING_MAX_SIZE   4096
 #define VMXNET3_TC_RING_MAX_SIZE   4096
@@ -380,6 +398,11 @@
 #define VMXNET3_RX_RING2_MAX_SIZE  4096
 #define VMXNET3_RC_RING_MAX_SIZE   8192
 
+#define VMXNET3_TXDATA_DESC_MIN_SIZE 128
+#define VMXNET3_TXDATA_DESC_MAX_SIZE 2048
+
+#define VMXNET3_RXDATA_DESC_MAX_SIZE 2048
+
 /* a list of reasons for queue stop */
 
 enum {
@@ -466,7 +489,9 @@
 	__le32		compRingSize; /* # of comp desc */
 	__le32		ddLen;        /* size of driver data */
 	u8		intrIdx;
-	u8		_pad[7];
+	u8		_pad1[1];
+	__le16		txDataRingDescSize;
+	u8		_pad2[4];
 };
 
 
@@ -474,12 +499,14 @@
 	__le64		rxRingBasePA[2];
 	__le64		compRingBasePA;
 	__le64		ddPA;            /* driver data */
-	__le64		reserved;
+	__le64		rxDataRingBasePA;
 	__le32		rxRingSize[2];   /* # of rx desc */
 	__le32		compRingSize;    /* # of rx comp desc */
 	__le32		ddLen;           /* size of driver data */
 	u8		intrIdx;
-	u8		_pad[7];
+	u8		_pad1[1];
+	__le16		rxDataRingDescSize;  /* size of rx data ring buffer */
+	u8		_pad2[4];
 };
 
 
@@ -609,6 +636,63 @@
 	u8				      __pad[88]; /* 128 aligned */
 };
 
+struct Vmxnet3_SetPolling {
+	u8					enablePolling;
+};
+
+#define VMXNET3_COAL_STATIC_MAX_DEPTH		128
+#define VMXNET3_COAL_RBC_MIN_RATE		100
+#define VMXNET3_COAL_RBC_MAX_RATE		100000
+
+enum Vmxnet3_CoalesceMode {
+	VMXNET3_COALESCE_DISABLED   = 0,
+	VMXNET3_COALESCE_ADAPT      = 1,
+	VMXNET3_COALESCE_STATIC     = 2,
+	VMXNET3_COALESCE_RBC        = 3
+};
+
+struct Vmxnet3_CoalesceRbc {
+	u32					rbc_rate;
+};
+
+struct Vmxnet3_CoalesceStatic {
+	u32					tx_depth;
+	u32					tx_comp_depth;
+	u32					rx_depth;
+};
+
+struct Vmxnet3_CoalesceScheme {
+	enum Vmxnet3_CoalesceMode		coalMode;
+	union {
+		struct Vmxnet3_CoalesceRbc	coalRbc;
+		struct Vmxnet3_CoalesceStatic	coalStatic;
+	} coalPara;
+};
+
+struct Vmxnet3_MemoryRegion {
+	__le64					startPA;
+	__le32					length;
+	__le16					txQueueBits;
+	__le16					rxQueueBits;
+};
+
+#define MAX_MEMORY_REGION_PER_QUEUE 16
+#define MAX_MEMORY_REGION_PER_DEVICE 256
+
+struct Vmxnet3_MemRegs {
+	__le16					numRegs;
+	__le16					pad[3];
+	struct Vmxnet3_MemoryRegion		memRegs[1];
+};
+
+/* If the command data <= 16 bytes, use the shared memory directly.
+ * otherwise, use variable length configuration descriptor.
+ */
+union Vmxnet3_CmdInfo {
+	struct Vmxnet3_VariableLenConfDesc	varConf;
+	struct Vmxnet3_SetPolling		setPolling;
+	__le64					data[2];
+};
 
 struct Vmxnet3_DSDevRead {
 	/* read-only region for device, read by dev in response to a SET cmd */
@@ -627,7 +711,14 @@
 	__le32				pad;
 	struct Vmxnet3_DSDevRead	devRead;
 	__le32				ecr;
-	__le32				reserved[5];
+	__le32				reserved;
+	union {
+		__le32			reserved1[4];
+		union Vmxnet3_CmdInfo	cmdInfo; /* only valid in the context of
+						  * executing the relevant
+						  * command
+						  */
+	} cu;
 };
 
 
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index db8022a..c68fe49 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -1,7 +1,7 @@
 /*
  * Linux driver for VMware's vmxnet3 ethernet NIC.
  *
- * Copyright (C) 2008-2009, VMware, Inc. All Rights Reserved.
+ * Copyright (C) 2008-2016, VMware, Inc. 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 as published by the
@@ -20,7 +20,7 @@
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
- * Maintained by: Shreyas Bhatewara <pv-drivers@vmware.com>
+ * Maintained by: pv-drivers@vmware.com
  *
  */
 
@@ -435,8 +435,8 @@
 		tq->tx_ring.base = NULL;
 	}
 	if (tq->data_ring.base) {
-		dma_free_coherent(&adapter->pdev->dev, tq->data_ring.size *
-				  sizeof(struct Vmxnet3_TxDataDesc),
+		dma_free_coherent(&adapter->pdev->dev,
+				  tq->data_ring.size * tq->txdata_desc_size,
 				  tq->data_ring.base, tq->data_ring.basePA);
 		tq->data_ring.base = NULL;
 	}
@@ -478,8 +478,8 @@
 	tq->tx_ring.next2fill = tq->tx_ring.next2comp = 0;
 	tq->tx_ring.gen = VMXNET3_INIT_GEN;
 
-	memset(tq->data_ring.base, 0, tq->data_ring.size *
-	       sizeof(struct Vmxnet3_TxDataDesc));
+	memset(tq->data_ring.base, 0,
+	       tq->data_ring.size * tq->txdata_desc_size);
 
 	/* reset the tx comp ring contents to 0 and reset comp ring states */
 	memset(tq->comp_ring.base, 0, tq->comp_ring.size *
@@ -514,10 +514,10 @@
 	}
 
 	tq->data_ring.base = dma_alloc_coherent(&adapter->pdev->dev,
-			tq->data_ring.size * sizeof(struct Vmxnet3_TxDataDesc),
+			tq->data_ring.size * tq->txdata_desc_size,
 			&tq->data_ring.basePA, GFP_KERNEL);
 	if (!tq->data_ring.base) {
-		netdev_err(adapter->netdev, "failed to allocate data ring\n");
+		netdev_err(adapter->netdev, "failed to allocate tx data ring\n");
 		goto err;
 	}
 
@@ -689,7 +689,7 @@
 	if (ctx->copy_size) {
 		ctx->sop_txd->txd.addr = cpu_to_le64(tq->data_ring.basePA +
 					tq->tx_ring.next2fill *
-					sizeof(struct Vmxnet3_TxDataDesc));
+					tq->txdata_desc_size);
 		ctx->sop_txd->dword[2] = cpu_to_le32(dw2 | ctx->copy_size);
 		ctx->sop_txd->dword[3] = 0;
 
@@ -873,8 +873,9 @@
 			ctx->eth_ip_hdr_size = 0;
 			ctx->l4_hdr_size = 0;
 			/* copy as much as allowed */
-			ctx->copy_size = min((unsigned int)VMXNET3_HDR_COPY_SIZE
-					     , skb_headlen(skb));
+			ctx->copy_size = min_t(unsigned int,
+					       tq->txdata_desc_size,
+					       skb_headlen(skb));
 		}
 
 		if (skb->len <= VMXNET3_HDR_COPY_SIZE)
@@ -885,7 +886,7 @@
 			goto err;
 	}
 
-	if (unlikely(ctx->copy_size > VMXNET3_HDR_COPY_SIZE)) {
+	if (unlikely(ctx->copy_size > tq->txdata_desc_size)) {
 		tq->stats.oversized_hdr++;
 		ctx->copy_size = 0;
 		return 0;
@@ -1283,9 +1284,10 @@
 			 */
 			break;
 		}
-		BUG_ON(rcd->rqID != rq->qid && rcd->rqID != rq->qid2);
+		BUG_ON(rcd->rqID != rq->qid && rcd->rqID != rq->qid2 &&
+		       rcd->rqID != rq->dataRingQid);
 		idx = rcd->rxdIdx;
-		ring_idx = rcd->rqID < adapter->num_rx_queues ? 0 : 1;
+		ring_idx = VMXNET3_GET_RING_IDX(adapter, rcd->rqID);
 		ring = rq->rx_ring + ring_idx;
 		vmxnet3_getRxDesc(rxd, &rq->rx_ring[ring_idx].base[idx].rxd,
 				  &rxCmdDesc);
@@ -1300,8 +1302,12 @@
 		}
 
 		if (rcd->sop) { /* first buf of the pkt */
+			bool rxDataRingUsed;
+			u16 len;
+
 			BUG_ON(rxd->btype != VMXNET3_RXD_BTYPE_HEAD ||
-			       rcd->rqID != rq->qid);
+			       (rcd->rqID != rq->qid &&
+				rcd->rqID != rq->dataRingQid));
 
 			BUG_ON(rbi->buf_type != VMXNET3_RX_BUF_SKB);
 			BUG_ON(ctx->skb != NULL || rbi->skb == NULL);
@@ -1317,8 +1323,12 @@
 
 			skip_page_frags = false;
 			ctx->skb = rbi->skb;
+
+			rxDataRingUsed =
+				VMXNET3_RX_DATA_RING(adapter, rcd->rqID);
+			len = rxDataRingUsed ? rcd->len : rbi->len;
 			new_skb = netdev_alloc_skb_ip_align(adapter->netdev,
-							    rbi->len);
+							    len);
 			if (new_skb == NULL) {
 				/* Skb allocation failed, do not handover this
 				 * skb to stack. Reuse it. Drop the existing pkt
@@ -1329,25 +1339,48 @@
 				skip_page_frags = true;
 				goto rcd_done;
 			}
-			new_dma_addr = dma_map_single(&adapter->pdev->dev,
-						      new_skb->data, rbi->len,
-						      PCI_DMA_FROMDEVICE);
-			if (dma_mapping_error(&adapter->pdev->dev,
-					      new_dma_addr)) {
-				dev_kfree_skb(new_skb);
-				/* Skb allocation failed, do not handover this
-				 * skb to stack. Reuse it. Drop the existing pkt
-				 */
-				rq->stats.rx_buf_alloc_failure++;
-				ctx->skb = NULL;
-				rq->stats.drop_total++;
-				skip_page_frags = true;
-				goto rcd_done;
-			}
 
-			dma_unmap_single(&adapter->pdev->dev, rbi->dma_addr,
-					 rbi->len,
-					 PCI_DMA_FROMDEVICE);
+			if (rxDataRingUsed) {
+				size_t sz;
+
+				BUG_ON(rcd->len > rq->data_ring.desc_size);
+
+				ctx->skb = new_skb;
+				sz = rcd->rxdIdx * rq->data_ring.desc_size;
+				memcpy(new_skb->data,
+				       &rq->data_ring.base[sz], rcd->len);
+			} else {
+				ctx->skb = rbi->skb;
+
+				new_dma_addr =
+					dma_map_single(&adapter->pdev->dev,
+						       new_skb->data, rbi->len,
+						       PCI_DMA_FROMDEVICE);
+				if (dma_mapping_error(&adapter->pdev->dev,
+						      new_dma_addr)) {
+					dev_kfree_skb(new_skb);
+					/* Skb allocation failed, do not
+					 * handover this skb to stack. Reuse
+					 * it. Drop the existing pkt.
+					 */
+					rq->stats.rx_buf_alloc_failure++;
+					ctx->skb = NULL;
+					rq->stats.drop_total++;
+					skip_page_frags = true;
+					goto rcd_done;
+				}
+
+				dma_unmap_single(&adapter->pdev->dev,
+						 rbi->dma_addr,
+						 rbi->len,
+						 PCI_DMA_FROMDEVICE);
+
+				/* Immediate refill */
+				rbi->skb = new_skb;
+				rbi->dma_addr = new_dma_addr;
+				rxd->addr = cpu_to_le64(rbi->dma_addr);
+				rxd->len = rbi->len;
+			}
 
 #ifdef VMXNET3_RSS
 			if (rcd->rssType != VMXNET3_RCD_RSS_TYPE_NONE &&
@@ -1358,18 +1391,13 @@
 #endif
 			skb_put(ctx->skb, rcd->len);
 
-			/* Immediate refill */
-			rbi->skb = new_skb;
-			rbi->dma_addr = new_dma_addr;
-			rxd->addr = cpu_to_le64(rbi->dma_addr);
-			rxd->len = rbi->len;
-			if (adapter->version == 2 &&
+			if (VMXNET3_VERSION_GE_2(adapter) &&
 			    rcd->type == VMXNET3_CDTYPE_RXCOMP_LRO) {
 				struct Vmxnet3_RxCompDescExt *rcdlro;
 				rcdlro = (struct Vmxnet3_RxCompDescExt *)rcd;
 
 				segCnt = rcdlro->segCnt;
-				BUG_ON(segCnt <= 1);
+				WARN_ON_ONCE(segCnt == 0);
 				mss = rcdlro->mss;
 				if (unlikely(segCnt <= 1))
 					segCnt = 0;
@@ -1589,6 +1617,13 @@
 		rq->buf_info[i] = NULL;
 	}
 
+	if (rq->data_ring.base) {
+		dma_free_coherent(&adapter->pdev->dev,
+				  rq->rx_ring[0].size * rq->data_ring.desc_size,
+				  rq->data_ring.base, rq->data_ring.basePA);
+		rq->data_ring.base = NULL;
+	}
+
 	if (rq->comp_ring.base) {
 		dma_free_coherent(&adapter->pdev->dev, rq->comp_ring.size
 				  * sizeof(struct Vmxnet3_RxCompDesc),
@@ -1604,6 +1639,25 @@
 	}
 }
 
+void
+vmxnet3_rq_destroy_all_rxdataring(struct vmxnet3_adapter *adapter)
+{
+	int i;
+
+	for (i = 0; i < adapter->num_rx_queues; i++) {
+		struct vmxnet3_rx_queue *rq = &adapter->rx_queue[i];
+
+		if (rq->data_ring.base) {
+			dma_free_coherent(&adapter->pdev->dev,
+					  (rq->rx_ring[0].size *
+					  rq->data_ring.desc_size),
+					  rq->data_ring.base,
+					  rq->data_ring.basePA);
+			rq->data_ring.base = NULL;
+			rq->data_ring.desc_size = 0;
+		}
+	}
+}
 
 static int
 vmxnet3_rq_init(struct vmxnet3_rx_queue *rq,
@@ -1697,6 +1751,22 @@
 		}
 	}
 
+	if ((adapter->rxdataring_enabled) && (rq->data_ring.desc_size != 0)) {
+		sz = rq->rx_ring[0].size * rq->data_ring.desc_size;
+		rq->data_ring.base =
+			dma_alloc_coherent(&adapter->pdev->dev, sz,
+					   &rq->data_ring.basePA,
+					   GFP_KERNEL);
+		if (!rq->data_ring.base) {
+			netdev_err(adapter->netdev,
+				   "rx data ring will be disabled\n");
+			adapter->rxdataring_enabled = false;
+		}
+	} else {
+		rq->data_ring.base = NULL;
+		rq->data_ring.desc_size = 0;
+	}
+
 	sz = rq->comp_ring.size * sizeof(struct Vmxnet3_RxCompDesc);
 	rq->comp_ring.base = dma_alloc_coherent(&adapter->pdev->dev, sz,
 						&rq->comp_ring.basePA,
@@ -1729,6 +1799,8 @@
 {
 	int i, err = 0;
 
+	adapter->rxdataring_enabled = VMXNET3_VERSION_GE_3(adapter);
+
 	for (i = 0; i < adapter->num_rx_queues; i++) {
 		err = vmxnet3_rq_create(&adapter->rx_queue[i], adapter);
 		if (unlikely(err)) {
@@ -1738,6 +1810,10 @@
 			goto err_out;
 		}
 	}
+
+	if (!adapter->rxdataring_enabled)
+		vmxnet3_rq_destroy_all_rxdataring(adapter);
+
 	return err;
 err_out:
 	vmxnet3_rq_destroy_all(adapter);
@@ -2045,10 +2121,9 @@
 			struct vmxnet3_rx_queue *rq = &adapter->rx_queue[i];
 			rq->qid = i;
 			rq->qid2 = i + adapter->num_rx_queues;
+			rq->dataRingQid = i + 2 * adapter->num_rx_queues;
 		}
 
-
-
 		/* init our intr settings */
 		for (i = 0; i < intr->num_intrs; i++)
 			intr->mod_levels[i] = UPT1_IML_ADAPTIVE;
@@ -2336,6 +2411,7 @@
 		tqc->ddPA           = cpu_to_le64(tq->buf_info_pa);
 		tqc->txRingSize     = cpu_to_le32(tq->tx_ring.size);
 		tqc->dataRingSize   = cpu_to_le32(tq->data_ring.size);
+		tqc->txDataRingDescSize = cpu_to_le32(tq->txdata_desc_size);
 		tqc->compRingSize   = cpu_to_le32(tq->comp_ring.size);
 		tqc->ddLen          = cpu_to_le32(
 					sizeof(struct vmxnet3_tx_buf_info) *
@@ -2360,6 +2436,12 @@
 					(rqc->rxRingSize[0] +
 					 rqc->rxRingSize[1]));
 		rqc->intrIdx         = rq->comp_ring.intr_idx;
+		if (VMXNET3_VERSION_GE_3(adapter)) {
+			rqc->rxDataRingBasePA =
+				cpu_to_le64(rq->data_ring.basePA);
+			rqc->rxDataRingDescSize =
+				cpu_to_le16(rq->data_ring.desc_size);
+		}
 	}
 
 #ifdef VMXNET3_RSS
@@ -2409,6 +2491,32 @@
 	/* the rest are already zeroed */
 }
 
+static void
+vmxnet3_init_coalesce(struct vmxnet3_adapter *adapter)
+{
+	struct Vmxnet3_DriverShared *shared = adapter->shared;
+	union Vmxnet3_CmdInfo *cmdInfo = &shared->cu.cmdInfo;
+	unsigned long flags;
+
+	if (!VMXNET3_VERSION_GE_3(adapter))
+		return;
+
+	spin_lock_irqsave(&adapter->cmd_lock, flags);
+	cmdInfo->varConf.confVer = 1;
+	cmdInfo->varConf.confLen =
+		cpu_to_le32(sizeof(*adapter->coal_conf));
+	cmdInfo->varConf.confPA  = cpu_to_le64(adapter->coal_conf_pa);
+
+	if (adapter->default_coal_mode) {
+		VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
+				       VMXNET3_CMD_GET_COALESCE);
+	} else {
+		VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
+				       VMXNET3_CMD_SET_COALESCE);
+	}
+
+	spin_unlock_irqrestore(&adapter->cmd_lock, flags);
+}
 
 int
 vmxnet3_activate_dev(struct vmxnet3_adapter *adapter)
@@ -2458,6 +2566,8 @@
 		goto activate_err;
 	}
 
+	vmxnet3_init_coalesce(adapter);
+
 	for (i = 0; i < adapter->num_rx_queues; i++) {
 		VMXNET3_WRITE_BAR0_REG(adapter,
 				VMXNET3_REG_RXPROD + i * VMXNET3_REG_ALIGN,
@@ -2689,7 +2799,8 @@
 
 int
 vmxnet3_create_queues(struct vmxnet3_adapter *adapter, u32 tx_ring_size,
-		      u32 rx_ring_size, u32 rx_ring2_size)
+		      u32 rx_ring_size, u32 rx_ring2_size,
+		      u16 txdata_desc_size, u16 rxdata_desc_size)
 {
 	int err = 0, i;
 
@@ -2698,6 +2809,7 @@
 		tq->tx_ring.size   = tx_ring_size;
 		tq->data_ring.size = tx_ring_size;
 		tq->comp_ring.size = tx_ring_size;
+		tq->txdata_desc_size = txdata_desc_size;
 		tq->shared = &adapter->tqd_start[i].ctrl;
 		tq->stopped = true;
 		tq->adapter = adapter;
@@ -2714,12 +2826,15 @@
 	adapter->rx_queue[0].rx_ring[0].size = rx_ring_size;
 	adapter->rx_queue[0].rx_ring[1].size = rx_ring2_size;
 	vmxnet3_adjust_rx_ring_size(adapter);
+
+	adapter->rxdataring_enabled = VMXNET3_VERSION_GE_3(adapter);
 	for (i = 0; i < adapter->num_rx_queues; i++) {
 		struct vmxnet3_rx_queue *rq = &adapter->rx_queue[i];
 		/* qid and qid2 for rx queues will be assigned later when num
 		 * of rx queues is finalized after allocating intrs */
 		rq->shared = &adapter->rqd_start[i].ctrl;
 		rq->adapter = adapter;
+		rq->data_ring.desc_size = rxdata_desc_size;
 		err = vmxnet3_rq_create(rq, adapter);
 		if (err) {
 			if (i == 0) {
@@ -2737,6 +2852,10 @@
 			}
 		}
 	}
+
+	if (!adapter->rxdataring_enabled)
+		vmxnet3_rq_destroy_all_rxdataring(adapter);
+
 	return err;
 queue_err:
 	vmxnet3_tq_destroy_all(adapter);
@@ -2754,9 +2873,35 @@
 	for (i = 0; i < adapter->num_tx_queues; i++)
 		spin_lock_init(&adapter->tx_queue[i].tx_lock);
 
-	err = vmxnet3_create_queues(adapter, adapter->tx_ring_size,
+	if (VMXNET3_VERSION_GE_3(adapter)) {
+		unsigned long flags;
+		u16 txdata_desc_size;
+
+		spin_lock_irqsave(&adapter->cmd_lock, flags);
+		VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
+				       VMXNET3_CMD_GET_TXDATA_DESC_SIZE);
+		txdata_desc_size = VMXNET3_READ_BAR1_REG(adapter,
+							 VMXNET3_REG_CMD);
+		spin_unlock_irqrestore(&adapter->cmd_lock, flags);
+
+		if ((txdata_desc_size < VMXNET3_TXDATA_DESC_MIN_SIZE) ||
+		    (txdata_desc_size > VMXNET3_TXDATA_DESC_MAX_SIZE) ||
+		    (txdata_desc_size & VMXNET3_TXDATA_DESC_SIZE_MASK)) {
+			adapter->txdata_desc_size =
+				sizeof(struct Vmxnet3_TxDataDesc);
+		} else {
+			adapter->txdata_desc_size = txdata_desc_size;
+		}
+	} else {
+		adapter->txdata_desc_size = sizeof(struct Vmxnet3_TxDataDesc);
+	}
+
+	err = vmxnet3_create_queues(adapter,
+				    adapter->tx_ring_size,
 				    adapter->rx_ring_size,
-				    adapter->rx_ring2_size);
+				    adapter->rx_ring2_size,
+				    adapter->txdata_desc_size,
+				    adapter->rxdata_desc_size);
 	if (err)
 		goto queue_err;
 
@@ -3200,12 +3345,21 @@
 		goto err_alloc_pci;
 
 	ver = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_VRRS);
-	if (ver & 2) {
-		VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_VRRS, 2);
-		adapter->version = 2;
-	} else if (ver & 1) {
-		VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_VRRS, 1);
-		adapter->version = 1;
+	if (ver & (1 << VMXNET3_REV_3)) {
+		VMXNET3_WRITE_BAR1_REG(adapter,
+				       VMXNET3_REG_VRRS,
+				       1 << VMXNET3_REV_3);
+		adapter->version = VMXNET3_REV_3 + 1;
+	} else if (ver & (1 << VMXNET3_REV_2)) {
+		VMXNET3_WRITE_BAR1_REG(adapter,
+				       VMXNET3_REG_VRRS,
+				       1 << VMXNET3_REV_2);
+		adapter->version = VMXNET3_REV_2 + 1;
+	} else if (ver & (1 << VMXNET3_REV_1)) {
+		VMXNET3_WRITE_BAR1_REG(adapter,
+				       VMXNET3_REG_VRRS,
+				       1 << VMXNET3_REV_1);
+		adapter->version = VMXNET3_REV_1 + 1;
 	} else {
 		dev_err(&pdev->dev,
 			"Incompatible h/w version (0x%x) for adapter\n", ver);
@@ -3224,9 +3378,28 @@
 		goto err_ver;
 	}
 
+	if (VMXNET3_VERSION_GE_3(adapter)) {
+		adapter->coal_conf =
+			dma_alloc_coherent(&adapter->pdev->dev,
+					   sizeof(struct Vmxnet3_CoalesceScheme)
+					   ,
+					   &adapter->coal_conf_pa,
+					   GFP_KERNEL);
+		if (!adapter->coal_conf) {
+			err = -ENOMEM;
+			goto err_ver;
+		}
+		memset(adapter->coal_conf, 0, sizeof(*adapter->coal_conf));
+		adapter->coal_conf->coalMode = VMXNET3_COALESCE_DISABLED;
+		adapter->default_coal_mode = true;
+	}
+
 	SET_NETDEV_DEV(netdev, &pdev->dev);
 	vmxnet3_declare_features(adapter, dma64);
 
+	adapter->rxdata_desc_size = VMXNET3_VERSION_GE_3(adapter) ?
+		VMXNET3_DEF_RXDATA_DESC_SIZE : 0;
+
 	if (adapter->num_tx_queues == adapter->num_rx_queues)
 		adapter->share_intr = VMXNET3_INTR_BUDDYSHARE;
 	else
@@ -3283,6 +3456,11 @@
 	return 0;
 
 err_register:
+	if (VMXNET3_VERSION_GE_3(adapter)) {
+		dma_free_coherent(&adapter->pdev->dev,
+				  sizeof(struct Vmxnet3_CoalesceScheme),
+				  adapter->coal_conf, adapter->coal_conf_pa);
+	}
 	vmxnet3_free_intr_resources(adapter);
 err_ver:
 	vmxnet3_free_pci_resources(adapter);
@@ -3333,6 +3511,11 @@
 
 	vmxnet3_free_intr_resources(adapter);
 	vmxnet3_free_pci_resources(adapter);
+	if (VMXNET3_VERSION_GE_3(adapter)) {
+		dma_free_coherent(&adapter->pdev->dev,
+				  sizeof(struct Vmxnet3_CoalesceScheme),
+				  adapter->coal_conf, adapter->coal_conf_pa);
+	}
 #ifdef VMXNET3_RSS
 	dma_free_coherent(&adapter->pdev->dev, sizeof(struct UPT1_RSSConf),
 			  adapter->rss_conf, adapter->rss_conf_pa);
diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c
index 9ba11d7..aabc6ef 100644
--- a/drivers/net/vmxnet3/vmxnet3_ethtool.c
+++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c
@@ -1,7 +1,7 @@
 /*
  * Linux driver for VMware's vmxnet3 ethernet NIC.
  *
- * Copyright (C) 2008-2009, VMware, Inc. All Rights Reserved.
+ * Copyright (C) 2008-2016, VMware, Inc. 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 as published by the
@@ -20,7 +20,7 @@
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
- * Maintained by: Shreyas Bhatewara <pv-drivers@vmware.com>
+ * Maintained by: pv-drivers@vmware.com
  *
  */
 
@@ -396,8 +396,7 @@
 		buf[j++] = VMXNET3_GET_ADDR_LO(tq->data_ring.basePA);
 		buf[j++] = VMXNET3_GET_ADDR_HI(tq->data_ring.basePA);
 		buf[j++] = tq->data_ring.size;
-		/* transmit data ring buffer size */
-		buf[j++] = VMXNET3_HDR_COPY_SIZE;
+		buf[j++] = tq->txdata_desc_size;
 
 		buf[j++] = VMXNET3_GET_ADDR_LO(tq->comp_ring.basePA);
 		buf[j++] = VMXNET3_GET_ADDR_HI(tq->comp_ring.basePA);
@@ -431,11 +430,10 @@
 		buf[j++] = rq->rx_ring[1].next2comp;
 		buf[j++] = rq->rx_ring[1].gen;
 
-		/* receive data ring */
-		buf[j++] = 0;
-		buf[j++] = 0;
-		buf[j++] = 0;
-		buf[j++] = 0;
+		buf[j++] = VMXNET3_GET_ADDR_LO(rq->data_ring.basePA);
+		buf[j++] = VMXNET3_GET_ADDR_HI(rq->data_ring.basePA);
+		buf[j++] = rq->rx_ring[0].size;
+		buf[j++] = rq->data_ring.desc_size;
 
 		buf[j++] = VMXNET3_GET_ADDR_LO(rq->comp_ring.basePA);
 		buf[j++] = VMXNET3_GET_ADDR_HI(rq->comp_ring.basePA);
@@ -504,12 +502,14 @@
 
 	param->rx_max_pending = VMXNET3_RX_RING_MAX_SIZE;
 	param->tx_max_pending = VMXNET3_TX_RING_MAX_SIZE;
-	param->rx_mini_max_pending = 0;
+	param->rx_mini_max_pending = VMXNET3_VERSION_GE_3(adapter) ?
+		VMXNET3_RXDATA_DESC_MAX_SIZE : 0;
 	param->rx_jumbo_max_pending = VMXNET3_RX_RING2_MAX_SIZE;
 
 	param->rx_pending = adapter->rx_ring_size;
 	param->tx_pending = adapter->tx_ring_size;
-	param->rx_mini_pending = 0;
+	param->rx_mini_pending = VMXNET3_VERSION_GE_3(adapter) ?
+		adapter->rxdata_desc_size : 0;
 	param->rx_jumbo_pending = adapter->rx_ring2_size;
 }
 
@@ -520,6 +520,7 @@
 {
 	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
 	u32 new_tx_ring_size, new_rx_ring_size, new_rx_ring2_size;
+	u16 new_rxdata_desc_size;
 	u32 sz;
 	int err = 0;
 
@@ -542,6 +543,15 @@
 		return -EOPNOTSUPP;
 	}
 
+	if (VMXNET3_VERSION_GE_3(adapter)) {
+		if (param->rx_mini_pending < 0 ||
+		    param->rx_mini_pending > VMXNET3_RXDATA_DESC_MAX_SIZE) {
+			return -EINVAL;
+		}
+	} else if (param->rx_mini_pending != 0) {
+		return -EINVAL;
+	}
+
 	/* round it up to a multiple of VMXNET3_RING_SIZE_ALIGN */
 	new_tx_ring_size = (param->tx_pending + VMXNET3_RING_SIZE_MASK) &
 							~VMXNET3_RING_SIZE_MASK;
@@ -568,9 +578,19 @@
 	new_rx_ring2_size = min_t(u32, new_rx_ring2_size,
 				  VMXNET3_RX_RING2_MAX_SIZE);
 
+	/* rx data ring buffer size has to be a multiple of
+	 * VMXNET3_RXDATA_DESC_SIZE_ALIGN
+	 */
+	new_rxdata_desc_size =
+		(param->rx_mini_pending + VMXNET3_RXDATA_DESC_SIZE_MASK) &
+		~VMXNET3_RXDATA_DESC_SIZE_MASK;
+	new_rxdata_desc_size = min_t(u16, new_rxdata_desc_size,
+				     VMXNET3_RXDATA_DESC_MAX_SIZE);
+
 	if (new_tx_ring_size == adapter->tx_ring_size &&
 	    new_rx_ring_size == adapter->rx_ring_size &&
-	    new_rx_ring2_size == adapter->rx_ring2_size) {
+	    new_rx_ring2_size == adapter->rx_ring2_size &&
+	    new_rxdata_desc_size == adapter->rxdata_desc_size) {
 		return 0;
 	}
 
@@ -591,8 +611,9 @@
 		vmxnet3_rq_destroy_all(adapter);
 
 		err = vmxnet3_create_queues(adapter, new_tx_ring_size,
-			new_rx_ring_size, new_rx_ring2_size);
-
+					    new_rx_ring_size, new_rx_ring2_size,
+					    adapter->txdata_desc_size,
+					    new_rxdata_desc_size);
 		if (err) {
 			/* failed, most likely because of OOM, try default
 			 * size */
@@ -601,10 +622,15 @@
 			new_rx_ring_size = VMXNET3_DEF_RX_RING_SIZE;
 			new_rx_ring2_size = VMXNET3_DEF_RX_RING2_SIZE;
 			new_tx_ring_size = VMXNET3_DEF_TX_RING_SIZE;
+			new_rxdata_desc_size = VMXNET3_VERSION_GE_3(adapter) ?
+				VMXNET3_DEF_RXDATA_DESC_SIZE : 0;
+
 			err = vmxnet3_create_queues(adapter,
 						    new_tx_ring_size,
 						    new_rx_ring_size,
-						    new_rx_ring2_size);
+						    new_rx_ring2_size,
+						    adapter->txdata_desc_size,
+						    new_rxdata_desc_size);
 			if (err) {
 				netdev_err(netdev, "failed to create queues "
 					   "with default sizes. Closing it\n");
@@ -620,6 +646,7 @@
 	adapter->tx_ring_size = new_tx_ring_size;
 	adapter->rx_ring_size = new_rx_ring_size;
 	adapter->rx_ring2_size = new_rx_ring2_size;
+	adapter->rxdata_desc_size = new_rxdata_desc_size;
 
 out:
 	clear_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state);
@@ -698,6 +725,162 @@
 }
 #endif
 
+static int
+vmxnet3_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec)
+{
+	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
+
+	if (!VMXNET3_VERSION_GE_3(adapter))
+		return -EOPNOTSUPP;
+
+	switch (adapter->coal_conf->coalMode) {
+	case VMXNET3_COALESCE_DISABLED:
+		/* struct ethtool_coalesce is already initialized to 0 */
+		break;
+	case VMXNET3_COALESCE_ADAPT:
+		ec->use_adaptive_rx_coalesce = true;
+		break;
+	case VMXNET3_COALESCE_STATIC:
+		ec->tx_max_coalesced_frames =
+			adapter->coal_conf->coalPara.coalStatic.tx_comp_depth;
+		ec->rx_max_coalesced_frames =
+			adapter->coal_conf->coalPara.coalStatic.rx_depth;
+		break;
+	case VMXNET3_COALESCE_RBC: {
+		u32 rbc_rate;
+
+		rbc_rate = adapter->coal_conf->coalPara.coalRbc.rbc_rate;
+		ec->rx_coalesce_usecs = VMXNET3_COAL_RBC_USECS(rbc_rate);
+	}
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int
+vmxnet3_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec)
+{
+	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
+	struct Vmxnet3_DriverShared *shared = adapter->shared;
+	union Vmxnet3_CmdInfo *cmdInfo = &shared->cu.cmdInfo;
+	unsigned long flags;
+
+	if (!VMXNET3_VERSION_GE_3(adapter))
+		return -EOPNOTSUPP;
+
+	if (ec->rx_coalesce_usecs_irq ||
+	    ec->rx_max_coalesced_frames_irq ||
+	    ec->tx_coalesce_usecs ||
+	    ec->tx_coalesce_usecs_irq ||
+	    ec->tx_max_coalesced_frames_irq ||
+	    ec->stats_block_coalesce_usecs ||
+	    ec->use_adaptive_tx_coalesce ||
+	    ec->pkt_rate_low ||
+	    ec->rx_coalesce_usecs_low ||
+	    ec->rx_max_coalesced_frames_low ||
+	    ec->tx_coalesce_usecs_low ||
+	    ec->tx_max_coalesced_frames_low ||
+	    ec->pkt_rate_high ||
+	    ec->rx_coalesce_usecs_high ||
+	    ec->rx_max_coalesced_frames_high ||
+	    ec->tx_coalesce_usecs_high ||
+	    ec->tx_max_coalesced_frames_high ||
+	    ec->rate_sample_interval) {
+		return -EINVAL;
+	}
+
+	if ((ec->rx_coalesce_usecs == 0) &&
+	    (ec->use_adaptive_rx_coalesce == 0) &&
+	    (ec->tx_max_coalesced_frames == 0) &&
+	    (ec->rx_max_coalesced_frames == 0)) {
+		memset(adapter->coal_conf, 0, sizeof(*adapter->coal_conf));
+		adapter->coal_conf->coalMode = VMXNET3_COALESCE_DISABLED;
+		goto done;
+	}
+
+	if (ec->rx_coalesce_usecs != 0) {
+		u32 rbc_rate;
+
+		if ((ec->use_adaptive_rx_coalesce != 0) ||
+		    (ec->tx_max_coalesced_frames != 0) ||
+		    (ec->rx_max_coalesced_frames != 0)) {
+			return -EINVAL;
+		}
+
+		rbc_rate = VMXNET3_COAL_RBC_RATE(ec->rx_coalesce_usecs);
+		if (rbc_rate < VMXNET3_COAL_RBC_MIN_RATE ||
+		    rbc_rate > VMXNET3_COAL_RBC_MAX_RATE) {
+			return -EINVAL;
+		}
+
+		memset(adapter->coal_conf, 0, sizeof(*adapter->coal_conf));
+		adapter->coal_conf->coalMode = VMXNET3_COALESCE_RBC;
+		adapter->coal_conf->coalPara.coalRbc.rbc_rate = rbc_rate;
+		goto done;
+	}
+
+	if (ec->use_adaptive_rx_coalesce != 0) {
+		if ((ec->rx_coalesce_usecs != 0) ||
+		    (ec->tx_max_coalesced_frames != 0) ||
+		    (ec->rx_max_coalesced_frames != 0)) {
+			return -EINVAL;
+		}
+		memset(adapter->coal_conf, 0, sizeof(*adapter->coal_conf));
+		adapter->coal_conf->coalMode = VMXNET3_COALESCE_ADAPT;
+		goto done;
+	}
+
+	if ((ec->tx_max_coalesced_frames != 0) ||
+	    (ec->rx_max_coalesced_frames != 0)) {
+		if ((ec->rx_coalesce_usecs != 0) ||
+		    (ec->use_adaptive_rx_coalesce != 0)) {
+			return -EINVAL;
+		}
+
+		if ((ec->tx_max_coalesced_frames >
+		    VMXNET3_COAL_STATIC_MAX_DEPTH) ||
+		    (ec->rx_max_coalesced_frames >
+		     VMXNET3_COAL_STATIC_MAX_DEPTH)) {
+			return -EINVAL;
+		}
+
+		memset(adapter->coal_conf, 0, sizeof(*adapter->coal_conf));
+		adapter->coal_conf->coalMode = VMXNET3_COALESCE_STATIC;
+
+		adapter->coal_conf->coalPara.coalStatic.tx_comp_depth =
+			(ec->tx_max_coalesced_frames ?
+			 ec->tx_max_coalesced_frames :
+			 VMXNET3_COAL_STATIC_DEFAULT_DEPTH);
+
+		adapter->coal_conf->coalPara.coalStatic.rx_depth =
+			(ec->rx_max_coalesced_frames ?
+			 ec->rx_max_coalesced_frames :
+			 VMXNET3_COAL_STATIC_DEFAULT_DEPTH);
+
+		adapter->coal_conf->coalPara.coalStatic.tx_depth =
+			 VMXNET3_COAL_STATIC_DEFAULT_DEPTH;
+		goto done;
+	}
+
+done:
+	adapter->default_coal_mode = false;
+	if (netif_running(netdev)) {
+		spin_lock_irqsave(&adapter->cmd_lock, flags);
+		cmdInfo->varConf.confVer = 1;
+		cmdInfo->varConf.confLen =
+			cpu_to_le32(sizeof(*adapter->coal_conf));
+		cmdInfo->varConf.confPA  = cpu_to_le64(adapter->coal_conf_pa);
+		VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
+				       VMXNET3_CMD_SET_COALESCE);
+		spin_unlock_irqrestore(&adapter->cmd_lock, flags);
+	}
+
+	return 0;
+}
+
 static const struct ethtool_ops vmxnet3_ethtool_ops = {
 	.get_settings      = vmxnet3_get_settings,
 	.get_drvinfo       = vmxnet3_get_drvinfo,
@@ -706,6 +889,8 @@
 	.get_wol           = vmxnet3_get_wol,
 	.set_wol           = vmxnet3_set_wol,
 	.get_link          = ethtool_op_get_link,
+	.get_coalesce      = vmxnet3_get_coalesce,
+	.set_coalesce      = vmxnet3_set_coalesce,
 	.get_strings       = vmxnet3_get_strings,
 	.get_sset_count	   = vmxnet3_get_sset_count,
 	.get_ethtool_stats = vmxnet3_get_ethtool_stats,
diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h
index c482539..74fc030 100644
--- a/drivers/net/vmxnet3/vmxnet3_int.h
+++ b/drivers/net/vmxnet3/vmxnet3_int.h
@@ -1,7 +1,7 @@
 /*
  * Linux driver for VMware's vmxnet3 ethernet NIC.
  *
- * Copyright (C) 2008-2009, VMware, Inc. All Rights Reserved.
+ * Copyright (C) 2008-2016, VMware, Inc. 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 as published by the
@@ -20,7 +20,7 @@
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
- * Maintained by: Shreyas Bhatewara <pv-drivers@vmware.com>
+ * Maintained by: pv-drivers@vmware.com
  *
  */
 
@@ -69,16 +69,20 @@
 /*
  * Version numbers
  */
-#define VMXNET3_DRIVER_VERSION_STRING   "1.4.7.0-k"
+#define VMXNET3_DRIVER_VERSION_STRING   "1.4.9.0-k"
 
 /* a 32-bit int, each byte encode a verion number in VMXNET3_DRIVER_VERSION */
-#define VMXNET3_DRIVER_VERSION_NUM      0x01040700
+#define VMXNET3_DRIVER_VERSION_NUM      0x01040900
 
 #if defined(CONFIG_PCI_MSI)
 	/* RSS only makes sense if MSI-X is supported. */
 	#define VMXNET3_RSS
 #endif
 
+#define VMXNET3_REV_3		2	/* Vmxnet3 Rev. 3 */
+#define VMXNET3_REV_2		1	/* Vmxnet3 Rev. 2 */
+#define VMXNET3_REV_1		0	/* Vmxnet3 Rev. 1 */
+
 /*
  * Capabilities
  */
@@ -237,6 +241,7 @@
 	int                             num_stop;  /* # of times the queue is
 						    * stopped */
 	int				qid;
+	u16				txdata_desc_size;
 } __attribute__((__aligned__(SMP_CACHE_BYTES)));
 
 enum vmxnet3_rx_buf_type {
@@ -267,15 +272,23 @@
 	u64 rx_buf_alloc_failure;
 };
 
+struct vmxnet3_rx_data_ring {
+	Vmxnet3_RxDataDesc *base;
+	dma_addr_t basePA;
+	u16 desc_size;
+};
+
 struct vmxnet3_rx_queue {
 	char			name[IFNAMSIZ + 8]; /* To identify interrupt */
 	struct vmxnet3_adapter	  *adapter;
 	struct napi_struct        napi;
 	struct vmxnet3_cmd_ring   rx_ring[2];
+	struct vmxnet3_rx_data_ring data_ring;
 	struct vmxnet3_comp_ring  comp_ring;
 	struct vmxnet3_rx_ctx     rx_ctx;
 	u32 qid;            /* rqID in RCD for buffer from 1st ring */
 	u32 qid2;           /* rqID in RCD for buffer from 2nd ring */
+	u32 dataRingQid;    /* rqID in RCD for buffer from data ring */
 	struct vmxnet3_rx_buf_info     *buf_info[2];
 	dma_addr_t                      buf_info_pa;
 	struct Vmxnet3_RxQueueCtrl            *shared;
@@ -345,6 +358,7 @@
 	int		rx_buf_per_pkt;  /* only apply to the 1st ring */
 	dma_addr_t			shared_pa;
 	dma_addr_t queue_desc_pa;
+	dma_addr_t coal_conf_pa;
 
 	/* Wake-on-LAN */
 	u32     wol;
@@ -359,12 +373,21 @@
 	u32 rx_ring_size;
 	u32 rx_ring2_size;
 
+	/* Size of buffer in the data ring */
+	u16 txdata_desc_size;
+	u16 rxdata_desc_size;
+
+	bool rxdataring_enabled;
+
 	struct work_struct work;
 
 	unsigned long  state;    /* VMXNET3_STATE_BIT_xxx */
 
 	int share_intr;
 
+	struct Vmxnet3_CoalesceScheme *coal_conf;
+	bool   default_coal_mode;
+
 	dma_addr_t adapter_pa;
 	dma_addr_t pm_conf_pa;
 	dma_addr_t rss_conf_pa;
@@ -387,14 +410,34 @@
 #define VMXNET3_GET_ADDR_LO(dma)   ((u32)(dma))
 #define VMXNET3_GET_ADDR_HI(dma)   ((u32)(((u64)(dma)) >> 32))
 
+#define VMXNET3_VERSION_GE_2(adapter) \
+	(adapter->version >= VMXNET3_REV_2 + 1)
+#define VMXNET3_VERSION_GE_3(adapter) \
+	(adapter->version >= VMXNET3_REV_3 + 1)
+
 /* must be a multiple of VMXNET3_RING_SIZE_ALIGN */
 #define VMXNET3_DEF_TX_RING_SIZE    512
 #define VMXNET3_DEF_RX_RING_SIZE    256
 #define VMXNET3_DEF_RX_RING2_SIZE   128
 
+#define VMXNET3_DEF_RXDATA_DESC_SIZE 128
+
 #define VMXNET3_MAX_ETH_HDR_SIZE    22
 #define VMXNET3_MAX_SKB_BUF_SIZE    (3*1024)
 
+#define VMXNET3_GET_RING_IDX(adapter, rqID)		\
+	((rqID >= adapter->num_rx_queues &&		\
+	 rqID < 2 * adapter->num_rx_queues) ? 1 : 0)	\
+
+#define VMXNET3_RX_DATA_RING(adapter, rqID)		\
+	(rqID >= 2 * adapter->num_rx_queues &&		\
+	rqID < 3 * adapter->num_rx_queues)		\
+
+#define VMXNET3_COAL_STATIC_DEFAULT_DEPTH	64
+
+#define VMXNET3_COAL_RBC_RATE(usecs) (1000000 / usecs)
+#define VMXNET3_COAL_RBC_USECS(rbc_rate) (1000000 / rbc_rate)
+
 int
 vmxnet3_quiesce_dev(struct vmxnet3_adapter *adapter);
 
@@ -418,7 +461,8 @@
 
 int
 vmxnet3_create_queues(struct vmxnet3_adapter *adapter,
-		      u32 tx_ring_size, u32 rx_ring_size, u32 rx_ring2_size);
+		      u32 tx_ring_size, u32 rx_ring_size, u32 rx_ring2_size,
+		      u16 txdata_desc_size, u16 rxdata_desc_size);
 
 void vmxnet3_set_ethtool_ops(struct net_device *netdev);
 
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index d356f5d..b376282 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -35,6 +35,7 @@
 #include <net/route.h>
 #include <net/addrconf.h>
 #include <net/l3mdev.h>
+#include <net/fib_rules.h>
 
 #define RT_FL_TOS(oldflp4) \
 	((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK))
@@ -42,9 +43,14 @@
 #define DRV_NAME	"vrf"
 #define DRV_VERSION	"1.0"
 
+#define FIB_RULE_PREF  1000       /* default preference for FIB rules */
+static bool add_fib_rules = true;
+
 struct net_vrf {
 	struct rtable __rcu	*rth;
+	struct rtable __rcu	*rth_local;
 	struct rt6_info	__rcu	*rt6;
+	struct rt6_info	__rcu	*rt6_local;
 	u32                     tb_id;
 };
 
@@ -54,9 +60,20 @@
 	u64			tx_drps;
 	u64			rx_pkts;
 	u64			rx_bytes;
+	u64			rx_drps;
 	struct u64_stats_sync	syncp;
 };
 
+static void vrf_rx_stats(struct net_device *dev, int len)
+{
+	struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats);
+
+	u64_stats_update_begin(&dstats->syncp);
+	dstats->rx_pkts++;
+	dstats->rx_bytes += len;
+	u64_stats_update_end(&dstats->syncp);
+}
+
 static void vrf_tx_error(struct net_device *vrf_dev, struct sk_buff *skb)
 {
 	vrf_dev->stats.tx_errors++;
@@ -91,6 +108,34 @@
 	return stats;
 }
 
+/* Local traffic destined to local address. Reinsert the packet to rx
+ * path, similar to loopback handling.
+ */
+static int vrf_local_xmit(struct sk_buff *skb, struct net_device *dev,
+			  struct dst_entry *dst)
+{
+	int len = skb->len;
+
+	skb_orphan(skb);
+
+	skb_dst_set(skb, dst);
+	skb_dst_force(skb);
+
+	/* set pkt_type to avoid skb hitting packet taps twice -
+	 * once on Tx and again in Rx processing
+	 */
+	skb->pkt_type = PACKET_LOOPBACK;
+
+	skb->protocol = eth_type_trans(skb, dev);
+
+	if (likely(netif_rx(skb) == NET_RX_SUCCESS))
+		vrf_rx_stats(dev, len);
+	else
+		this_cpu_inc(dev->dstats->rx_drps);
+
+	return NETDEV_TX_OK;
+}
+
 #if IS_ENABLED(CONFIG_IPV6)
 static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
 					   struct net_device *dev)
@@ -117,8 +162,51 @@
 		goto err;
 
 	skb_dst_drop(skb);
+
+	/* if dst.dev is loopback or the VRF device again this is locally
+	 * originated traffic destined to a local address. Short circuit
+	 * to Rx path using our local dst
+	 */
+	if (dst->dev == net->loopback_dev || dst->dev == dev) {
+		struct net_vrf *vrf = netdev_priv(dev);
+		struct rt6_info *rt6_local;
+
+		/* release looked up dst and use cached local dst */
+		dst_release(dst);
+
+		rcu_read_lock();
+
+		rt6_local = rcu_dereference(vrf->rt6_local);
+		if (unlikely(!rt6_local)) {
+			rcu_read_unlock();
+			goto err;
+		}
+
+		/* Ordering issue: cached local dst is created on newlink
+		 * before the IPv6 initialization. Using the local dst
+		 * requires rt6i_idev to be set so make sure it is.
+		 */
+		if (unlikely(!rt6_local->rt6i_idev)) {
+			rt6_local->rt6i_idev = in6_dev_get(dev);
+			if (!rt6_local->rt6i_idev) {
+				rcu_read_unlock();
+				goto err;
+			}
+		}
+
+		dst = &rt6_local->dst;
+		dst_hold(dst);
+
+		rcu_read_unlock();
+
+		return vrf_local_xmit(skb, dev, &rt6_local->dst);
+	}
+
 	skb_dst_set(skb, dst);
 
+	/* strip the ethernet header added for pass through VRF device */
+	__skb_pull(skb, skb_network_offset(skb));
+
 	ret = ip6_local_out(net, skb->sk, skb);
 	if (unlikely(net_xmit_eval(ret)))
 		dev->stats.tx_errors++;
@@ -139,29 +227,6 @@
 }
 #endif
 
-static int vrf_send_v4_prep(struct sk_buff *skb, struct flowi4 *fl4,
-			    struct net_device *vrf_dev)
-{
-	struct rtable *rt;
-	int err = 1;
-
-	rt = ip_route_output_flow(dev_net(vrf_dev), fl4, NULL);
-	if (IS_ERR(rt))
-		goto out;
-
-	/* TO-DO: what about broadcast ? */
-	if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) {
-		ip_rt_put(rt);
-		goto out;
-	}
-
-	skb_dst_drop(skb);
-	skb_dst_set(skb, &rt->dst);
-	err = 0;
-out:
-	return err;
-}
-
 static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb,
 					   struct net_device *vrf_dev)
 {
@@ -176,10 +241,52 @@
 				FLOWI_FLAG_SKIP_NH_OIF,
 		.daddr = ip4h->daddr,
 	};
+	struct net *net = dev_net(vrf_dev);
+	struct rtable *rt;
 
-	if (vrf_send_v4_prep(skb, &fl4, vrf_dev))
+	rt = ip_route_output_flow(net, &fl4, NULL);
+	if (IS_ERR(rt))
 		goto err;
 
+	if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) {
+		ip_rt_put(rt);
+		goto err;
+	}
+
+	skb_dst_drop(skb);
+
+	/* if dst.dev is loopback or the VRF device again this is locally
+	 * originated traffic destined to a local address. Short circuit
+	 * to Rx path using our local dst
+	 */
+	if (rt->dst.dev == net->loopback_dev || rt->dst.dev == vrf_dev) {
+		struct net_vrf *vrf = netdev_priv(vrf_dev);
+		struct rtable *rth_local;
+		struct dst_entry *dst = NULL;
+
+		ip_rt_put(rt);
+
+		rcu_read_lock();
+
+		rth_local = rcu_dereference(vrf->rth_local);
+		if (likely(rth_local)) {
+			dst = &rth_local->dst;
+			dst_hold(dst);
+		}
+
+		rcu_read_unlock();
+
+		if (unlikely(!dst))
+			goto err;
+
+		return vrf_local_xmit(skb, vrf_dev, dst);
+	}
+
+	skb_dst_set(skb, &rt->dst);
+
+	/* strip the ethernet header added for pass through VRF device */
+	__skb_pull(skb, skb_network_offset(skb));
+
 	if (!ip4h->saddr) {
 		ip4h->saddr = inet_select_addr(skb_dst(skb)->dev, 0,
 					       RT_SCOPE_LINK);
@@ -200,9 +307,6 @@
 
 static netdev_tx_t is_ip_tx_frame(struct sk_buff *skb, struct net_device *dev)
 {
-	/* strip the ethernet header added for pass through VRF device */
-	__skb_pull(skb, skb_network_offset(skb));
-
 	switch (skb->protocol) {
 	case htons(ETH_P_IP):
 		return vrf_process_v4_outbound(skb, dev);
@@ -274,30 +378,59 @@
 }
 
 /* holding rtnl */
-static void vrf_rt6_release(struct net_vrf *vrf)
+static void vrf_rt6_release(struct net_device *dev, struct net_vrf *vrf)
 {
 	struct rt6_info *rt6 = rtnl_dereference(vrf->rt6);
+	struct rt6_info *rt6_local = rtnl_dereference(vrf->rt6_local);
+	struct net *net = dev_net(dev);
+	struct dst_entry *dst;
 
-	rcu_assign_pointer(vrf->rt6, NULL);
+	RCU_INIT_POINTER(vrf->rt6, NULL);
+	RCU_INIT_POINTER(vrf->rt6_local, NULL);
+	synchronize_rcu();
 
-	if (rt6)
-		dst_release(&rt6->dst);
+	/* move dev in dst's to loopback so this VRF device can be deleted
+	 * - based on dst_ifdown
+	 */
+	if (rt6) {
+		dst = &rt6->dst;
+		dev_put(dst->dev);
+		dst->dev = net->loopback_dev;
+		dev_hold(dst->dev);
+		dst_release(dst);
+	}
+
+	if (rt6_local) {
+		if (rt6_local->rt6i_idev)
+			in6_dev_put(rt6_local->rt6i_idev);
+
+		dst = &rt6_local->dst;
+		dev_put(dst->dev);
+		dst->dev = net->loopback_dev;
+		dev_hold(dst->dev);
+		dst_release(dst);
+	}
 }
 
 static int vrf_rt6_create(struct net_device *dev)
 {
+	int flags = DST_HOST | DST_NOPOLICY | DST_NOXFRM | DST_NOCACHE;
 	struct net_vrf *vrf = netdev_priv(dev);
 	struct net *net = dev_net(dev);
 	struct fib6_table *rt6i_table;
-	struct rt6_info *rt6;
+	struct rt6_info *rt6, *rt6_local;
 	int rc = -ENOMEM;
 
+	/* IPv6 can be CONFIG enabled and then disabled runtime */
+	if (!ipv6_mod_enabled())
+		return 0;
+
 	rt6i_table = fib6_new_table(net, vrf->tb_id);
 	if (!rt6i_table)
 		goto out;
 
-	rt6 = ip6_dst_alloc(net, dev,
-			    DST_HOST | DST_NOPOLICY | DST_NOXFRM | DST_NOCACHE);
+	/* create a dst for routing packets out a VRF device */
+	rt6 = ip6_dst_alloc(net, dev, flags);
 	if (!rt6)
 		goto out;
 
@@ -305,14 +438,32 @@
 
 	rt6->rt6i_table = rt6i_table;
 	rt6->dst.output	= vrf_output6;
+
+	/* create a dst for local routing - packets sent locally
+	 * to local address via the VRF device as a loopback
+	 */
+	rt6_local = ip6_dst_alloc(net, dev, flags);
+	if (!rt6_local) {
+		dst_release(&rt6->dst);
+		goto out;
+	}
+
+	dst_hold(&rt6_local->dst);
+
+	rt6_local->rt6i_idev  = in6_dev_get(dev);
+	rt6_local->rt6i_flags = RTF_UP | RTF_NONEXTHOP | RTF_LOCAL;
+	rt6_local->rt6i_table = rt6i_table;
+	rt6_local->dst.input  = ip6_input;
+
 	rcu_assign_pointer(vrf->rt6, rt6);
+	rcu_assign_pointer(vrf->rt6_local, rt6_local);
 
 	rc = 0;
 out:
 	return rc;
 }
 #else
-static void vrf_rt6_release(struct net_vrf *vrf)
+static void vrf_rt6_release(struct net_device *dev, struct net_vrf *vrf)
 {
 }
 
@@ -381,32 +532,66 @@
 }
 
 /* holding rtnl */
-static void vrf_rtable_release(struct net_vrf *vrf)
+static void vrf_rtable_release(struct net_device *dev, struct net_vrf *vrf)
 {
 	struct rtable *rth = rtnl_dereference(vrf->rth);
+	struct rtable *rth_local = rtnl_dereference(vrf->rth_local);
+	struct net *net = dev_net(dev);
+	struct dst_entry *dst;
 
-	rcu_assign_pointer(vrf->rth, NULL);
+	RCU_INIT_POINTER(vrf->rth, NULL);
+	RCU_INIT_POINTER(vrf->rth_local, NULL);
+	synchronize_rcu();
 
-	if (rth)
-		dst_release(&rth->dst);
+	/* move dev in dst's to loopback so this VRF device can be deleted
+	 * - based on dst_ifdown
+	 */
+	if (rth) {
+		dst = &rth->dst;
+		dev_put(dst->dev);
+		dst->dev = net->loopback_dev;
+		dev_hold(dst->dev);
+		dst_release(dst);
+	}
+
+	if (rth_local) {
+		dst = &rth_local->dst;
+		dev_put(dst->dev);
+		dst->dev = net->loopback_dev;
+		dev_hold(dst->dev);
+		dst_release(dst);
+	}
 }
 
 static int vrf_rtable_create(struct net_device *dev)
 {
 	struct net_vrf *vrf = netdev_priv(dev);
-	struct rtable *rth;
+	struct rtable *rth, *rth_local;
 
 	if (!fib_new_table(dev_net(dev), vrf->tb_id))
 		return -ENOMEM;
 
+	/* create a dst for routing packets out through a VRF device */
 	rth = rt_dst_alloc(dev, 0, RTN_UNICAST, 1, 1, 0);
 	if (!rth)
 		return -ENOMEM;
 
+	/* create a dst for local ingress routing - packets sent locally
+	 * to local address via the VRF device as a loopback
+	 */
+	rth_local = rt_dst_alloc(dev, RTCF_LOCAL, RTN_LOCAL, 1, 1, 0);
+	if (!rth_local) {
+		dst_release(&rth->dst);
+		return -ENOMEM;
+	}
+
 	rth->dst.output	= vrf_output;
 	rth->rt_table_id = vrf->tb_id;
 
+	rth_local->rt_table_id = vrf->tb_id;
+
 	rcu_assign_pointer(vrf->rth, rth);
+	rcu_assign_pointer(vrf->rth_local, rth_local);
 
 	return 0;
 }
@@ -477,8 +662,8 @@
 	struct net_device *port_dev;
 	struct list_head *iter;
 
-	vrf_rtable_release(vrf);
-	vrf_rt6_release(vrf);
+	vrf_rtable_release(dev, vrf);
+	vrf_rt6_release(dev, vrf);
 
 	netdev_for_each_lower_dev(dev, port_dev, iter)
 		vrf_del_slave(dev, port_dev);
@@ -509,11 +694,11 @@
 
 	/* similarly, oper state is irrelevant; set to up to avoid confusion */
 	dev->operstate = IF_OPER_UP;
-
+	netdev_lockdep_set_classes(dev);
 	return 0;
 
 out_rth:
-	vrf_rtable_release(vrf);
+	vrf_rtable_release(dev, vrf);
 out_stats:
 	free_percpu(dev->dstats);
 	dev->dstats = NULL;
@@ -629,11 +814,78 @@
 	return rc;
 }
 
+static struct rt6_info *vrf_ip6_route_lookup(struct net *net,
+					     const struct net_device *dev,
+					     struct flowi6 *fl6,
+					     int ifindex,
+					     int flags)
+{
+	struct net_vrf *vrf = netdev_priv(dev);
+	struct fib6_table *table = NULL;
+	struct rt6_info *rt6;
+
+	rcu_read_lock();
+
+	/* fib6_table does not have a refcnt and can not be freed */
+	rt6 = rcu_dereference(vrf->rt6);
+	if (likely(rt6))
+		table = rt6->rt6i_table;
+
+	rcu_read_unlock();
+
+	if (!table)
+		return NULL;
+
+	return ip6_pol_route(net, table, ifindex, fl6, flags);
+}
+
+static void vrf_ip6_input_dst(struct sk_buff *skb, struct net_device *vrf_dev,
+			      int ifindex)
+{
+	const struct ipv6hdr *iph = ipv6_hdr(skb);
+	struct flowi6 fl6 = {
+		.daddr          = iph->daddr,
+		.saddr          = iph->saddr,
+		.flowlabel      = ip6_flowinfo(iph),
+		.flowi6_mark    = skb->mark,
+		.flowi6_proto   = iph->nexthdr,
+		.flowi6_iif     = ifindex,
+	};
+	struct net *net = dev_net(vrf_dev);
+	struct rt6_info *rt6;
+
+	rt6 = vrf_ip6_route_lookup(net, vrf_dev, &fl6, ifindex,
+				   RT6_LOOKUP_F_HAS_SADDR | RT6_LOOKUP_F_IFACE);
+	if (unlikely(!rt6))
+		return;
+
+	if (unlikely(&rt6->dst == &net->ipv6.ip6_null_entry->dst))
+		return;
+
+	skb_dst_set(skb, &rt6->dst);
+}
+
 static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev,
 				   struct sk_buff *skb)
 {
-	/* if packet is NDISC keep the ingress interface */
-	if (!ipv6_ndisc_frame(skb)) {
+	int orig_iif = skb->skb_iif;
+	bool need_strict;
+
+	/* loopback traffic; do not push through packet taps again.
+	 * Reset pkt_type for upper layers to process skb
+	 */
+	if (skb->pkt_type == PACKET_LOOPBACK) {
+		skb->dev = vrf_dev;
+		skb->skb_iif = vrf_dev->ifindex;
+		skb->pkt_type = PACKET_HOST;
+		goto out;
+	}
+
+	/* if packet is NDISC or addressed to multicast or link-local
+	 * then keep the ingress interface
+	 */
+	need_strict = rt6_need_strict(&ipv6_hdr(skb)->daddr);
+	if (!ipv6_ndisc_frame(skb) && !need_strict) {
 		skb->dev = vrf_dev;
 		skb->skb_iif = vrf_dev->ifindex;
 
@@ -644,6 +896,10 @@
 		IP6CB(skb)->flags |= IP6SKB_L3SLAVE;
 	}
 
+	if (need_strict)
+		vrf_ip6_input_dst(skb, vrf_dev, orig_iif);
+
+out:
 	return skb;
 }
 
@@ -661,10 +917,19 @@
 	skb->dev = vrf_dev;
 	skb->skb_iif = vrf_dev->ifindex;
 
+	/* loopback traffic; do not push through packet taps again.
+	 * Reset pkt_type for upper layers to process skb
+	 */
+	if (skb->pkt_type == PACKET_LOOPBACK) {
+		skb->pkt_type = PACKET_HOST;
+		goto out;
+	}
+
 	skb_push(skb, skb->mac_len);
 	dev_queue_xmit_nit(skb, vrf_dev);
 	skb_pull(skb, skb->mac_len);
 
+out:
 	return skb;
 }
 
@@ -685,13 +950,37 @@
 
 #if IS_ENABLED(CONFIG_IPV6)
 static struct dst_entry *vrf_get_rt6_dst(const struct net_device *dev,
-					 const struct flowi6 *fl6)
+					 struct flowi6 *fl6)
 {
+	bool need_strict = rt6_need_strict(&fl6->daddr);
+	struct net_vrf *vrf = netdev_priv(dev);
+	struct net *net = dev_net(dev);
 	struct dst_entry *dst = NULL;
+	struct rt6_info *rt;
 
-	if (!(fl6->flowi6_flags & FLOWI_FLAG_L3MDEV_SRC)) {
-		struct net_vrf *vrf = netdev_priv(dev);
-		struct rt6_info *rt;
+	/* send to link-local or multicast address */
+	if (need_strict) {
+		int flags = RT6_LOOKUP_F_IFACE;
+
+		/* VRF device does not have a link-local address and
+		 * sending packets to link-local or mcast addresses over
+		 * a VRF device does not make sense
+		 */
+		if (fl6->flowi6_oif == dev->ifindex) {
+			struct dst_entry *dst = &net->ipv6.ip6_null_entry->dst;
+
+			dst_hold(dst);
+			return dst;
+		}
+
+		if (!ipv6_addr_any(&fl6->saddr))
+			flags |= RT6_LOOKUP_F_HAS_SADDR;
+
+		rt = vrf_ip6_route_lookup(net, dev, fl6, fl6->flowi6_oif, flags);
+		if (rt)
+			dst = &rt->dst;
+
+	} else if (!(fl6->flowi6_flags & FLOWI_FLAG_L3MDEV_SRC)) {
 
 		rcu_read_lock();
 
@@ -704,8 +993,52 @@
 		rcu_read_unlock();
 	}
 
+	/* make sure oif is set to VRF device for lookup */
+	if (!need_strict)
+		fl6->flowi6_oif = dev->ifindex;
+
 	return dst;
 }
+
+/* called under rcu_read_lock */
+static int vrf_get_saddr6(struct net_device *dev, const struct sock *sk,
+			  struct flowi6 *fl6)
+{
+	struct net *net = dev_net(dev);
+	struct dst_entry *dst;
+	struct rt6_info *rt;
+	int err;
+
+	if (rt6_need_strict(&fl6->daddr)) {
+		rt = vrf_ip6_route_lookup(net, dev, fl6, fl6->flowi6_oif,
+					  RT6_LOOKUP_F_IFACE);
+		if (unlikely(!rt))
+			return 0;
+
+		dst = &rt->dst;
+	} else {
+		__u8 flags = fl6->flowi6_flags;
+
+		fl6->flowi6_flags |= FLOWI_FLAG_L3MDEV_SRC;
+		fl6->flowi6_flags |= FLOWI_FLAG_SKIP_NH_OIF;
+
+		dst = ip6_route_output(net, sk, fl6);
+		rt = (struct rt6_info *)dst;
+
+		fl6->flowi6_flags = flags;
+	}
+
+	err = dst->error;
+	if (!err) {
+		err = ip6_route_get_saddr(net, rt, &fl6->daddr,
+					  sk ? inet6_sk(sk)->srcprefs : 0,
+					  &fl6->saddr);
+	}
+
+	dst_release(dst);
+
+	return err;
+}
 #endif
 
 static const struct l3mdev_ops vrf_l3mdev_ops = {
@@ -715,6 +1048,7 @@
 	.l3mdev_l3_rcv		= vrf_l3_rcv,
 #if IS_ENABLED(CONFIG_IPV6)
 	.l3mdev_get_rt6_dst	= vrf_get_rt6_dst,
+	.l3mdev_get_saddr6	= vrf_get_saddr6,
 #endif
 };
 
@@ -729,6 +1063,94 @@
 	.get_drvinfo	= vrf_get_drvinfo,
 };
 
+static inline size_t vrf_fib_rule_nl_size(void)
+{
+	size_t sz;
+
+	sz  = NLMSG_ALIGN(sizeof(struct fib_rule_hdr));
+	sz += nla_total_size(sizeof(u8));	/* FRA_L3MDEV */
+	sz += nla_total_size(sizeof(u32));	/* FRA_PRIORITY */
+
+	return sz;
+}
+
+static int vrf_fib_rule(const struct net_device *dev, __u8 family, bool add_it)
+{
+	struct fib_rule_hdr *frh;
+	struct nlmsghdr *nlh;
+	struct sk_buff *skb;
+	int err;
+
+	if (family == AF_INET6 && !ipv6_mod_enabled())
+		return 0;
+
+	skb = nlmsg_new(vrf_fib_rule_nl_size(), GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	nlh = nlmsg_put(skb, 0, 0, 0, sizeof(*frh), 0);
+	if (!nlh)
+		goto nla_put_failure;
+
+	/* rule only needs to appear once */
+	nlh->nlmsg_flags &= NLM_F_EXCL;
+
+	frh = nlmsg_data(nlh);
+	memset(frh, 0, sizeof(*frh));
+	frh->family = family;
+	frh->action = FR_ACT_TO_TBL;
+
+	if (nla_put_u32(skb, FRA_L3MDEV, 1))
+		goto nla_put_failure;
+
+	if (nla_put_u32(skb, FRA_PRIORITY, FIB_RULE_PREF))
+		goto nla_put_failure;
+
+	nlmsg_end(skb, nlh);
+
+	/* fib_nl_{new,del}rule handling looks for net from skb->sk */
+	skb->sk = dev_net(dev)->rtnl;
+	if (add_it) {
+		err = fib_nl_newrule(skb, nlh);
+		if (err == -EEXIST)
+			err = 0;
+	} else {
+		err = fib_nl_delrule(skb, nlh);
+		if (err == -ENOENT)
+			err = 0;
+	}
+	nlmsg_free(skb);
+
+	return err;
+
+nla_put_failure:
+	nlmsg_free(skb);
+
+	return -EMSGSIZE;
+}
+
+static int vrf_add_fib_rules(const struct net_device *dev)
+{
+	int err;
+
+	err = vrf_fib_rule(dev, AF_INET,  true);
+	if (err < 0)
+		goto out_err;
+
+	err = vrf_fib_rule(dev, AF_INET6, true);
+	if (err < 0)
+		goto ipv6_err;
+
+	return 0;
+
+ipv6_err:
+	vrf_fib_rule(dev, AF_INET,  false);
+
+out_err:
+	netdev_err(dev, "Failed to add FIB rules.\n");
+	return err;
+}
+
 static void vrf_setup(struct net_device *dev)
 {
 	ether_setup(dev);
@@ -747,6 +1169,20 @@
 
 	/* don't allow vrf devices to change network namespaces. */
 	dev->features |= NETIF_F_NETNS_LOCAL;
+
+	/* does not make sense for a VLAN to be added to a vrf device */
+	dev->features   |= NETIF_F_VLAN_CHALLENGED;
+
+	/* enable offload features */
+	dev->features   |= NETIF_F_GSO_SOFTWARE;
+	dev->features   |= NETIF_F_RXCSUM | NETIF_F_HW_CSUM;
+	dev->features   |= NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA;
+
+	dev->hw_features = dev->features;
+	dev->hw_enc_features = dev->features;
+
+	/* default to no qdisc; user can add if desired */
+	dev->priv_flags |= IFF_NO_QUEUE;
 }
 
 static int vrf_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -769,6 +1205,7 @@
 		       struct nlattr *tb[], struct nlattr *data[])
 {
 	struct net_vrf *vrf = netdev_priv(dev);
+	int err;
 
 	if (!data || !data[IFLA_VRF_TABLE])
 		return -EINVAL;
@@ -777,7 +1214,21 @@
 
 	dev->priv_flags |= IFF_L3MDEV_MASTER;
 
-	return register_netdevice(dev);
+	err = register_netdevice(dev);
+	if (err)
+		goto out;
+
+	if (add_fib_rules) {
+		err = vrf_add_fib_rules(dev);
+		if (err) {
+			unregister_netdevice(dev);
+			goto out;
+		}
+		add_fib_rules = false;
+	}
+
+out:
+	return err;
 }
 
 static size_t vrf_nl_getsize(const struct net_device *dev)
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index f999db2..abb9cd2 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -11,32 +11,18 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/kernel.h>
-#include <linux/types.h>
 #include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
-#include <linux/skbuff.h>
-#include <linux/rculist.h>
-#include <linux/netdevice.h>
-#include <linux/in.h>
-#include <linux/ip.h>
 #include <linux/udp.h>
 #include <linux/igmp.h>
-#include <linux/etherdevice.h>
 #include <linux/if_ether.h>
-#include <linux/if_vlan.h>
-#include <linux/hash.h>
 #include <linux/ethtool.h>
 #include <net/arp.h>
 #include <net/ndisc.h>
 #include <net/ip.h>
-#include <net/ip_tunnels.h>
 #include <net/icmp.h>
-#include <net/udp.h>
-#include <net/udp_tunnel.h>
 #include <net/rtnetlink.h>
-#include <net/route.h>
-#include <net/dsfield.h>
 #include <net/inet_ecn.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
@@ -44,12 +30,9 @@
 #include <net/protocol.h>
 
 #if IS_ENABLED(CONFIG_IPV6)
-#include <net/ipv6.h>
-#include <net/addrconf.h>
 #include <net/ip6_tunnel.h>
 #include <net/ip6_checksum.h>
 #endif
-#include <net/dst_metadata.h>
 
 #define VXLAN_VERSION	"0.1"
 
@@ -619,42 +602,6 @@
 	return eth_gro_complete(skb, nhoff + sizeof(struct vxlanhdr));
 }
 
-/* Notify netdevs that UDP port started listening */
-static void vxlan_notify_add_rx_port(struct vxlan_sock *vs)
-{
-	struct net_device *dev;
-	struct sock *sk = vs->sock->sk;
-	struct net *net = sock_net(sk);
-	sa_family_t sa_family = vxlan_get_sk_family(vs);
-	__be16 port = inet_sk(sk)->inet_sport;
-
-	rcu_read_lock();
-	for_each_netdev_rcu(net, dev) {
-		if (dev->netdev_ops->ndo_add_vxlan_port)
-			dev->netdev_ops->ndo_add_vxlan_port(dev, sa_family,
-							    port);
-	}
-	rcu_read_unlock();
-}
-
-/* Notify netdevs that UDP port is no more listening */
-static void vxlan_notify_del_rx_port(struct vxlan_sock *vs)
-{
-	struct net_device *dev;
-	struct sock *sk = vs->sock->sk;
-	struct net *net = sock_net(sk);
-	sa_family_t sa_family = vxlan_get_sk_family(vs);
-	__be16 port = inet_sk(sk)->inet_sport;
-
-	rcu_read_lock();
-	for_each_netdev_rcu(net, dev) {
-		if (dev->netdev_ops->ndo_del_vxlan_port)
-			dev->netdev_ops->ndo_del_vxlan_port(dev, sa_family,
-							    port);
-	}
-	rcu_read_unlock();
-}
-
 /* Add new entry to forwarding table -- assumes lock held */
 static int vxlan_fdb_create(struct vxlan_dev *vxlan,
 			    const u8 *mac, union vxlan_addr *ip,
@@ -1050,7 +997,10 @@
 	vn = net_generic(sock_net(vs->sock->sk), vxlan_net_id);
 	spin_lock(&vn->sock_lock);
 	hlist_del_rcu(&vs->hlist);
-	vxlan_notify_del_rx_port(vs);
+	udp_tunnel_notify_del_rx_port(vs->sock,
+				      (vs->flags & VXLAN_F_GPE) ?
+				      UDP_TUNNEL_TYPE_VXLAN_GPE :
+				      UDP_TUNNEL_TYPE_VXLAN);
 	spin_unlock(&vn->sock_lock);
 
 	return true;
@@ -2525,30 +2475,24 @@
 	.name = "vxlan",
 };
 
-/* Calls the ndo_add_vxlan_port of the caller in order to
+/* Calls the ndo_add_udp_enc_port of the caller in order to
  * supply the listening VXLAN udp ports. Callers are expected
- * to implement the ndo_add_vxlan_port.
+ * to implement the ndo_add_udp_enc_port.
  */
 static void vxlan_push_rx_ports(struct net_device *dev)
 {
 	struct vxlan_sock *vs;
 	struct net *net = dev_net(dev);
 	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
-	sa_family_t sa_family;
-	__be16 port;
 	unsigned int i;
 
-	if (!dev->netdev_ops->ndo_add_vxlan_port)
-		return;
-
 	spin_lock(&vn->sock_lock);
 	for (i = 0; i < PORT_HASH_SIZE; ++i) {
-		hlist_for_each_entry_rcu(vs, &vn->sock_list[i], hlist) {
-			port = inet_sk(vs->sock->sk)->inet_sport;
-			sa_family = vxlan_get_sk_family(vs);
-			dev->netdev_ops->ndo_add_vxlan_port(dev, sa_family,
-							    port);
-		}
+		hlist_for_each_entry_rcu(vs, &vn->sock_list[i], hlist)
+			udp_tunnel_push_rx_port(dev, vs->sock,
+						(vs->flags & VXLAN_F_GPE) ?
+						UDP_TUNNEL_TYPE_VXLAN_GPE :
+						UDP_TUNNEL_TYPE_VXLAN);
 	}
 	spin_unlock(&vn->sock_lock);
 }
@@ -2750,7 +2694,10 @@
 
 	spin_lock(&vn->sock_lock);
 	hlist_add_head_rcu(&vs->hlist, vs_head(net, port));
-	vxlan_notify_add_rx_port(vs);
+	udp_tunnel_notify_add_rx_port(sock,
+				      (vs->flags & VXLAN_F_GPE) ?
+				      UDP_TUNNEL_TYPE_VXLAN_GPE :
+				      UDP_TUNNEL_TYPE_VXLAN);
 	spin_unlock(&vn->sock_lock);
 
 	/* Mark socket as an encapsulation socket. */
@@ -3298,7 +3245,7 @@
 
 	if (event == NETDEV_UNREGISTER)
 		vxlan_handle_lowerdev_unregister(vn, dev);
-	else if (event == NETDEV_OFFLOAD_PUSH_VXLAN)
+	else if (event == NETDEV_UDP_TUNNEL_PUSH_INFO)
 		vxlan_push_rx_ports(dev);
 
 	return NOTIFY_DONE;
diff --git a/drivers/net/wan/Kconfig b/drivers/net/wan/Kconfig
index a2fdd15..9e314b7 100644
--- a/drivers/net/wan/Kconfig
+++ b/drivers/net/wan/Kconfig
@@ -280,6 +280,17 @@
 	  To compile this driver as a module, choose M here: the
 	  module will be called dscc4.
 
+config FSL_UCC_HDLC
+	tristate "Freescale QUICC Engine HDLC support"
+	depends on HDLC
+	depends on QUICC_ENGINE
+	help
+	  Driver for Freescale QUICC Engine HDLC controller. The driver
+	  supports HDLC in NMSI and TDM mode.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called fsl_ucc_hdlc.
+
 config DSCC4_PCISYNC
 	bool "Etinc PCISYNC features"
 	depends on DSCC4
diff --git a/drivers/net/wan/Makefile b/drivers/net/wan/Makefile
index c135ef4..25fec40 100644
--- a/drivers/net/wan/Makefile
+++ b/drivers/net/wan/Makefile
@@ -32,6 +32,7 @@
 obj-$(CONFIG_PCI200SYN)		+= pci200syn.o
 obj-$(CONFIG_PC300TOO)		+= pc300too.o
 obj-$(CONFIG_IXP4XX_HSS)	+= ixp4xx_hss.o
+obj-$(CONFIG_FSL_UCC_HDLC)	+= fsl_ucc_hdlc.o
 
 clean-files := wanxlfw.inc
 $(obj)/wanxl.o:	$(obj)/wanxlfw.inc
diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c
new file mode 100644
index 0000000..19174ac
--- /dev/null
+++ b/drivers/net/wan/fsl_ucc_hdlc.c
@@ -0,0 +1,1192 @@
+/* Freescale QUICC Engine HDLC Device Driver
+ *
+ * Copyright 2016 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.
+ */
+
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/hdlc.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/sched.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/stddef.h>
+#include <soc/fsl/qe/qe_tdm.h>
+#include <uapi/linux/if_arp.h>
+
+#include "fsl_ucc_hdlc.h"
+
+#define DRV_DESC "Freescale QE UCC HDLC Driver"
+#define DRV_NAME "ucc_hdlc"
+
+#define TDM_PPPOHT_SLIC_MAXIN
+#define BROKEN_FRAME_INFO
+
+static struct ucc_tdm_info utdm_primary_info = {
+	.uf_info = {
+		.tsa = 0,
+		.cdp = 0,
+		.cds = 1,
+		.ctsp = 1,
+		.ctss = 1,
+		.revd = 0,
+		.urfs = 256,
+		.utfs = 256,
+		.urfet = 128,
+		.urfset = 192,
+		.utfet = 128,
+		.utftt = 0x40,
+		.ufpt = 256,
+		.mode = UCC_FAST_PROTOCOL_MODE_HDLC,
+		.ttx_trx = UCC_FAST_GUMR_TRANSPARENT_TTX_TRX_NORMAL,
+		.tenc = UCC_FAST_TX_ENCODING_NRZ,
+		.renc = UCC_FAST_RX_ENCODING_NRZ,
+		.tcrc = UCC_FAST_16_BIT_CRC,
+		.synl = UCC_FAST_SYNC_LEN_NOT_USED,
+	},
+
+	.si_info = {
+#ifdef TDM_PPPOHT_SLIC_MAXIN
+		.simr_rfsd = 1,
+		.simr_tfsd = 2,
+#else
+		.simr_rfsd = 0,
+		.simr_tfsd = 0,
+#endif
+		.simr_crt = 0,
+		.simr_sl = 0,
+		.simr_ce = 1,
+		.simr_fe = 1,
+		.simr_gm = 0,
+	},
+};
+
+static struct ucc_tdm_info utdm_info[MAX_HDLC_NUM];
+
+static int uhdlc_init(struct ucc_hdlc_private *priv)
+{
+	struct ucc_tdm_info *ut_info;
+	struct ucc_fast_info *uf_info;
+	u32 cecr_subblock;
+	u16 bd_status;
+	int ret, i;
+	void *bd_buffer;
+	dma_addr_t bd_dma_addr;
+	u32 riptr;
+	u32 tiptr;
+	u32 gumr;
+
+	ut_info = priv->ut_info;
+	uf_info = &ut_info->uf_info;
+
+	if (priv->tsa) {
+		uf_info->tsa = 1;
+		uf_info->ctsp = 1;
+	}
+	uf_info->uccm_mask = ((UCC_HDLC_UCCE_RXB | UCC_HDLC_UCCE_RXF |
+				UCC_HDLC_UCCE_TXB) << 16);
+
+	ret = ucc_fast_init(uf_info, &priv->uccf);
+	if (ret) {
+		dev_err(priv->dev, "Failed to init uccf.");
+		return ret;
+	}
+
+	priv->uf_regs = priv->uccf->uf_regs;
+	ucc_fast_disable(priv->uccf, COMM_DIR_RX | COMM_DIR_TX);
+
+	/* Loopback mode */
+	if (priv->loopback) {
+		dev_info(priv->dev, "Loopback Mode\n");
+		gumr = ioread32be(&priv->uf_regs->gumr);
+		gumr |= (UCC_FAST_GUMR_LOOPBACK | UCC_FAST_GUMR_CDS |
+			 UCC_FAST_GUMR_TCI);
+		gumr &= ~(UCC_FAST_GUMR_CTSP | UCC_FAST_GUMR_RSYN);
+		iowrite32be(gumr, &priv->uf_regs->gumr);
+	}
+
+	/* Initialize SI */
+	if (priv->tsa)
+		ucc_tdm_init(priv->utdm, priv->ut_info);
+
+	/* Write to QE CECR, UCCx channel to Stop Transmission */
+	cecr_subblock = ucc_fast_get_qe_cr_subblock(uf_info->ucc_num);
+	ret = qe_issue_cmd(QE_STOP_TX, cecr_subblock,
+			   QE_CR_PROTOCOL_UNSPECIFIED, 0);
+
+	/* Set UPSMR normal mode (need fixed)*/
+	iowrite32be(0, &priv->uf_regs->upsmr);
+
+	priv->rx_ring_size = RX_BD_RING_LEN;
+	priv->tx_ring_size = TX_BD_RING_LEN;
+	/* Alloc Rx BD */
+	priv->rx_bd_base = dma_alloc_coherent(priv->dev,
+			RX_BD_RING_LEN * sizeof(struct qe_bd *),
+			&priv->dma_rx_bd, GFP_KERNEL);
+
+	if (!priv->rx_bd_base) {
+		dev_err(priv->dev, "Cannot allocate MURAM memory for RxBDs\n");
+		ret = -ENOMEM;
+		goto rxbd_alloc_error;
+	}
+
+	/* Alloc Tx BD */
+	priv->tx_bd_base = dma_alloc_coherent(priv->dev,
+			TX_BD_RING_LEN * sizeof(struct qe_bd *),
+			&priv->dma_tx_bd, GFP_KERNEL);
+
+	if (!priv->tx_bd_base) {
+		dev_err(priv->dev, "Cannot allocate MURAM memory for TxBDs\n");
+		ret = -ENOMEM;
+		goto txbd_alloc_error;
+	}
+
+	/* Alloc parameter ram for ucc hdlc */
+	priv->ucc_pram_offset = qe_muram_alloc(sizeof(priv->ucc_pram),
+				ALIGNMENT_OF_UCC_HDLC_PRAM);
+
+	if (priv->ucc_pram_offset < 0) {
+		dev_err(priv->dev, "Can not allocate MURAM for hdlc prameter.\n");
+		ret = -ENOMEM;
+		goto pram_alloc_error;
+	}
+
+	priv->rx_skbuff = kzalloc(priv->rx_ring_size * sizeof(*priv->rx_skbuff),
+				  GFP_KERNEL);
+	if (!priv->rx_skbuff)
+		goto rx_skb_alloc_error;
+
+	priv->tx_skbuff = kzalloc(priv->tx_ring_size * sizeof(*priv->tx_skbuff),
+				  GFP_KERNEL);
+	if (!priv->tx_skbuff)
+		goto tx_skb_alloc_error;
+
+	priv->skb_curtx = 0;
+	priv->skb_dirtytx = 0;
+	priv->curtx_bd = priv->tx_bd_base;
+	priv->dirty_tx = priv->tx_bd_base;
+	priv->currx_bd = priv->rx_bd_base;
+	priv->currx_bdnum = 0;
+
+	/* init parameter base */
+	cecr_subblock = ucc_fast_get_qe_cr_subblock(uf_info->ucc_num);
+	ret = qe_issue_cmd(QE_ASSIGN_PAGE_TO_DEVICE, cecr_subblock,
+			   QE_CR_PROTOCOL_UNSPECIFIED, priv->ucc_pram_offset);
+
+	priv->ucc_pram = (struct ucc_hdlc_param __iomem *)
+					qe_muram_addr(priv->ucc_pram_offset);
+
+	/* Zero out parameter ram */
+	memset_io(priv->ucc_pram, 0, sizeof(struct ucc_hdlc_param));
+
+	/* Alloc riptr, tiptr */
+	riptr = qe_muram_alloc(32, 32);
+	if (riptr < 0) {
+		dev_err(priv->dev, "Cannot allocate MURAM mem for Receive internal temp data pointer\n");
+		ret = -ENOMEM;
+		goto riptr_alloc_error;
+	}
+
+	tiptr = qe_muram_alloc(32, 32);
+	if (tiptr < 0) {
+		dev_err(priv->dev, "Cannot allocate MURAM mem for Transmit internal temp data pointer\n");
+		ret = -ENOMEM;
+		goto tiptr_alloc_error;
+	}
+
+	/* Set RIPTR, TIPTR */
+	iowrite16be(riptr, &priv->ucc_pram->riptr);
+	iowrite16be(tiptr, &priv->ucc_pram->tiptr);
+
+	/* Set MRBLR */
+	iowrite16be(MAX_RX_BUF_LENGTH, &priv->ucc_pram->mrblr);
+
+	/* Set RBASE, TBASE */
+	iowrite32be(priv->dma_rx_bd, &priv->ucc_pram->rbase);
+	iowrite32be(priv->dma_tx_bd, &priv->ucc_pram->tbase);
+
+	/* Set RSTATE, TSTATE */
+	iowrite32be(BMR_GBL | BMR_BIG_ENDIAN, &priv->ucc_pram->rstate);
+	iowrite32be(BMR_GBL | BMR_BIG_ENDIAN, &priv->ucc_pram->tstate);
+
+	/* Set C_MASK, C_PRES for 16bit CRC */
+	iowrite32be(CRC_16BIT_MASK, &priv->ucc_pram->c_mask);
+	iowrite32be(CRC_16BIT_PRES, &priv->ucc_pram->c_pres);
+
+	iowrite16be(MAX_FRAME_LENGTH, &priv->ucc_pram->mflr);
+	iowrite16be(DEFAULT_RFTHR, &priv->ucc_pram->rfthr);
+	iowrite16be(DEFAULT_RFTHR, &priv->ucc_pram->rfcnt);
+	iowrite16be(DEFAULT_ADDR_MASK, &priv->ucc_pram->hmask);
+	iowrite16be(DEFAULT_HDLC_ADDR, &priv->ucc_pram->haddr1);
+	iowrite16be(DEFAULT_HDLC_ADDR, &priv->ucc_pram->haddr2);
+	iowrite16be(DEFAULT_HDLC_ADDR, &priv->ucc_pram->haddr3);
+	iowrite16be(DEFAULT_HDLC_ADDR, &priv->ucc_pram->haddr4);
+
+	/* Get BD buffer */
+	bd_buffer = dma_alloc_coherent(priv->dev,
+				       (RX_BD_RING_LEN + TX_BD_RING_LEN) *
+				       MAX_RX_BUF_LENGTH,
+				       &bd_dma_addr, GFP_KERNEL);
+
+	if (!bd_buffer) {
+		dev_err(priv->dev, "Could not allocate buffer descriptors\n");
+		ret = -ENOMEM;
+		goto bd_alloc_error;
+	}
+
+	memset(bd_buffer, 0, (RX_BD_RING_LEN + TX_BD_RING_LEN)
+			* MAX_RX_BUF_LENGTH);
+
+	priv->rx_buffer = bd_buffer;
+	priv->tx_buffer = bd_buffer + RX_BD_RING_LEN * MAX_RX_BUF_LENGTH;
+
+	priv->dma_rx_addr = bd_dma_addr;
+	priv->dma_tx_addr = bd_dma_addr + RX_BD_RING_LEN * MAX_RX_BUF_LENGTH;
+
+	for (i = 0; i < RX_BD_RING_LEN; i++) {
+		if (i < (RX_BD_RING_LEN - 1))
+			bd_status = R_E_S | R_I_S;
+		else
+			bd_status = R_E_S | R_I_S | R_W_S;
+
+		iowrite16be(bd_status, &priv->rx_bd_base[i].status);
+		iowrite32be(priv->dma_rx_addr + i * MAX_RX_BUF_LENGTH,
+			    &priv->rx_bd_base[i].buf);
+	}
+
+	for (i = 0; i < TX_BD_RING_LEN; i++) {
+		if (i < (TX_BD_RING_LEN - 1))
+			bd_status =  T_I_S | T_TC_S;
+		else
+			bd_status =  T_I_S | T_TC_S | T_W_S;
+
+		iowrite16be(bd_status, &priv->tx_bd_base[i].status);
+		iowrite32be(priv->dma_tx_addr + i * MAX_RX_BUF_LENGTH,
+			    &priv->tx_bd_base[i].buf);
+	}
+
+	return 0;
+
+bd_alloc_error:
+	qe_muram_free(tiptr);
+tiptr_alloc_error:
+	qe_muram_free(riptr);
+riptr_alloc_error:
+	kfree(priv->tx_skbuff);
+tx_skb_alloc_error:
+	kfree(priv->rx_skbuff);
+rx_skb_alloc_error:
+	qe_muram_free(priv->ucc_pram_offset);
+pram_alloc_error:
+	dma_free_coherent(priv->dev,
+			  TX_BD_RING_LEN * sizeof(struct qe_bd),
+			  priv->tx_bd_base, priv->dma_tx_bd);
+txbd_alloc_error:
+	dma_free_coherent(priv->dev,
+			  RX_BD_RING_LEN * sizeof(struct qe_bd),
+			  priv->rx_bd_base, priv->dma_rx_bd);
+rxbd_alloc_error:
+	ucc_fast_free(priv->uccf);
+
+	return ret;
+}
+
+static netdev_tx_t ucc_hdlc_tx(struct sk_buff *skb, struct net_device *dev)
+{
+	hdlc_device *hdlc = dev_to_hdlc(dev);
+	struct ucc_hdlc_private *priv = (struct ucc_hdlc_private *)hdlc->priv;
+	struct qe_bd __iomem *bd;
+	u16 bd_status;
+	unsigned long flags;
+	u8 *send_buf;
+	int i;
+	u16 *proto_head;
+
+	switch (dev->type) {
+	case ARPHRD_RAWHDLC:
+		if (skb_headroom(skb) < HDLC_HEAD_LEN) {
+			dev->stats.tx_dropped++;
+			dev_kfree_skb(skb);
+			netdev_err(dev, "No enough space for hdlc head\n");
+			return -ENOMEM;
+		}
+
+		skb_push(skb, HDLC_HEAD_LEN);
+
+		proto_head = (u16 *)skb->data;
+		*proto_head = htons(DEFAULT_HDLC_HEAD);
+
+		dev->stats.tx_bytes += skb->len;
+		break;
+
+	case ARPHRD_PPP:
+		proto_head = (u16 *)skb->data;
+		if (*proto_head != htons(DEFAULT_PPP_HEAD)) {
+			dev->stats.tx_dropped++;
+			dev_kfree_skb(skb);
+			netdev_err(dev, "Wrong ppp header\n");
+			return -ENOMEM;
+		}
+
+		dev->stats.tx_bytes += skb->len;
+		break;
+
+	default:
+		dev->stats.tx_dropped++;
+		dev_kfree_skb(skb);
+		return -ENOMEM;
+	}
+
+	pr_info("Tx data skb->len:%d ", skb->len);
+	send_buf = (u8 *)skb->data;
+	pr_info("\nTransmitted data:\n");
+	for (i = 0; i < 16; i++) {
+		if (i == skb->len)
+			pr_info("++++");
+		else
+		pr_info("%02x\n", send_buf[i]);
+	}
+	spin_lock_irqsave(&priv->lock, flags);
+
+	/* Start from the next BD that should be filled */
+	bd = priv->curtx_bd;
+	bd_status = ioread16be(&bd->status);
+	/* Save the skb pointer so we can free it later */
+	priv->tx_skbuff[priv->skb_curtx] = skb;
+
+	/* Update the current skb pointer (wrapping if this was the last) */
+	priv->skb_curtx =
+	    (priv->skb_curtx + 1) & TX_RING_MOD_MASK(TX_BD_RING_LEN);
+
+	/* copy skb data to tx buffer for sdma processing */
+	memcpy(priv->tx_buffer + (be32_to_cpu(bd->buf) - priv->dma_tx_addr),
+	       skb->data, skb->len);
+
+	/* set bd status and length */
+	bd_status = (bd_status & T_W_S) | T_R_S | T_I_S | T_L_S | T_TC_S;
+
+	iowrite16be(bd_status, &bd->status);
+	iowrite16be(skb->len, &bd->length);
+
+	/* Move to next BD in the ring */
+	if (!(bd_status & T_W_S))
+		bd += 1;
+	else
+		bd = priv->tx_bd_base;
+
+	if (bd == priv->dirty_tx) {
+		if (!netif_queue_stopped(dev))
+			netif_stop_queue(dev);
+	}
+
+	priv->curtx_bd = bd;
+
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	return NETDEV_TX_OK;
+}
+
+static int hdlc_tx_done(struct ucc_hdlc_private *priv)
+{
+	/* Start from the next BD that should be filled */
+	struct net_device *dev = priv->ndev;
+	struct qe_bd *bd;		/* BD pointer */
+	u16 bd_status;
+
+	bd = priv->dirty_tx;
+	bd_status = ioread16be(&bd->status);
+
+	/* Normal processing. */
+	while ((bd_status & T_R_S) == 0) {
+		struct sk_buff *skb;
+
+		/* BD contains already transmitted buffer.   */
+		/* Handle the transmitted buffer and release */
+		/* the BD to be used with the current frame  */
+
+		skb = priv->tx_skbuff[priv->skb_dirtytx];
+		if (!skb)
+			break;
+		pr_info("TxBD: %x\n", bd_status);
+		dev->stats.tx_packets++;
+		memset(priv->tx_buffer +
+		       (be32_to_cpu(bd->buf) - priv->dma_tx_addr),
+		       0, skb->len);
+		dev_kfree_skb_irq(skb);
+
+		priv->tx_skbuff[priv->skb_dirtytx] = NULL;
+		priv->skb_dirtytx =
+		    (priv->skb_dirtytx +
+		     1) & TX_RING_MOD_MASK(TX_BD_RING_LEN);
+
+		/* We freed a buffer, so now we can restart transmission */
+		if (netif_queue_stopped(dev))
+			netif_wake_queue(dev);
+
+		/* Advance the confirmation BD pointer */
+		if (!(bd_status & T_W_S))
+			bd += 1;
+		else
+			bd = priv->tx_bd_base;
+		bd_status = ioread16be(&bd->status);
+	}
+	priv->dirty_tx = bd;
+
+	return 0;
+}
+
+static int hdlc_rx_done(struct ucc_hdlc_private *priv, int rx_work_limit)
+{
+	struct net_device *dev = priv->ndev;
+	struct sk_buff *skb;
+	hdlc_device *hdlc = dev_to_hdlc(dev);
+	struct qe_bd *bd;
+	u32 bd_status;
+	u16 length, howmany = 0;
+	u8 *bdbuffer;
+	int i;
+	static int entry;
+
+	bd = priv->currx_bd;
+	bd_status = ioread16be(&bd->status);
+
+	/* while there are received buffers and BD is full (~R_E) */
+	while (!((bd_status & (R_E_S)) || (--rx_work_limit < 0))) {
+		if (bd_status & R_OV_S)
+			dev->stats.rx_over_errors++;
+		if (bd_status & R_CR_S) {
+#ifdef BROKEN_FRAME_INFO
+			pr_info("Broken Frame with RxBD: %x\n", bd_status);
+#endif
+			dev->stats.rx_crc_errors++;
+			dev->stats.rx_dropped++;
+			goto recycle;
+		}
+		bdbuffer = priv->rx_buffer +
+			(priv->currx_bdnum * MAX_RX_BUF_LENGTH);
+		length = ioread16be(&bd->length);
+
+		pr_info("Received data length:%d", length);
+		pr_info("while entry times:%d", entry++);
+
+		pr_info("\nReceived data:\n");
+		for (i = 0; (i < 16); i++) {
+			if (i == length)
+				pr_info("++++");
+			else
+			pr_info("%02x\n", bdbuffer[i]);
+		}
+
+		switch (dev->type) {
+		case ARPHRD_RAWHDLC:
+			bdbuffer += HDLC_HEAD_LEN;
+			length -= (HDLC_HEAD_LEN + HDLC_CRC_SIZE);
+
+			skb = dev_alloc_skb(length);
+			if (!skb) {
+				dev->stats.rx_dropped++;
+				return -ENOMEM;
+			}
+
+			skb_put(skb, length);
+			skb->len = length;
+			skb->dev = dev;
+			memcpy(skb->data, bdbuffer, length);
+			break;
+
+		case ARPHRD_PPP:
+			length -= HDLC_CRC_SIZE;
+
+			skb = dev_alloc_skb(length);
+			if (!skb) {
+				dev->stats.rx_dropped++;
+				return -ENOMEM;
+			}
+
+			skb_put(skb, length);
+			skb->len = length;
+			skb->dev = dev;
+			memcpy(skb->data, bdbuffer, length);
+			break;
+		}
+
+		dev->stats.rx_packets++;
+		dev->stats.rx_bytes += skb->len;
+		howmany++;
+		if (hdlc->proto)
+			skb->protocol = hdlc_type_trans(skb, dev);
+		pr_info("skb->protocol:%x\n", skb->protocol);
+		netif_receive_skb(skb);
+
+recycle:
+		iowrite16be(bd_status | R_E_S | R_I_S, &bd->status);
+
+		/* update to point at the next bd */
+		if (bd_status & R_W_S) {
+			priv->currx_bdnum = 0;
+			bd = priv->rx_bd_base;
+		} else {
+			if (priv->currx_bdnum < (RX_BD_RING_LEN - 1))
+				priv->currx_bdnum += 1;
+			else
+				priv->currx_bdnum = RX_BD_RING_LEN - 1;
+
+			bd += 1;
+		}
+
+		bd_status = ioread16be(&bd->status);
+	}
+
+	priv->currx_bd = bd;
+	return howmany;
+}
+
+static int ucc_hdlc_poll(struct napi_struct *napi, int budget)
+{
+	struct ucc_hdlc_private *priv = container_of(napi,
+						     struct ucc_hdlc_private,
+						     napi);
+	int howmany;
+
+	/* Tx event processing */
+	spin_lock(&priv->lock);
+		hdlc_tx_done(priv);
+	spin_unlock(&priv->lock);
+
+	howmany = 0;
+	howmany += hdlc_rx_done(priv, budget - howmany);
+
+	if (howmany < budget) {
+		napi_complete(napi);
+		qe_setbits32(priv->uccf->p_uccm,
+			     (UCCE_HDLC_RX_EVENTS | UCCE_HDLC_TX_EVENTS) << 16);
+	}
+
+	return howmany;
+}
+
+static irqreturn_t ucc_hdlc_irq_handler(int irq, void *dev_id)
+{
+	struct ucc_hdlc_private *priv = (struct ucc_hdlc_private *)dev_id;
+	struct net_device *dev = priv->ndev;
+	struct ucc_fast_private *uccf;
+	struct ucc_tdm_info *ut_info;
+	u32 ucce;
+	u32 uccm;
+
+	ut_info = priv->ut_info;
+	uccf = priv->uccf;
+
+	ucce = ioread32be(uccf->p_ucce);
+	uccm = ioread32be(uccf->p_uccm);
+	ucce &= uccm;
+	iowrite32be(ucce, uccf->p_ucce);
+	pr_info("irq ucce:%x\n", ucce);
+	if (!ucce)
+		return IRQ_NONE;
+
+	if ((ucce >> 16) & (UCCE_HDLC_RX_EVENTS | UCCE_HDLC_TX_EVENTS)) {
+		if (napi_schedule_prep(&priv->napi)) {
+			uccm &= ~((UCCE_HDLC_RX_EVENTS | UCCE_HDLC_TX_EVENTS)
+				  << 16);
+			iowrite32be(uccm, uccf->p_uccm);
+			__napi_schedule(&priv->napi);
+		}
+	}
+
+	/* Errors and other events */
+	if (ucce >> 16 & UCC_HDLC_UCCE_BSY)
+		dev->stats.rx_errors++;
+	if (ucce >> 16 & UCC_HDLC_UCCE_TXE)
+		dev->stats.tx_errors++;
+
+	return IRQ_HANDLED;
+}
+
+static int uhdlc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+{
+	const size_t size = sizeof(te1_settings);
+	te1_settings line;
+	struct ucc_hdlc_private *priv = netdev_priv(dev);
+
+	if (cmd != SIOCWANDEV)
+		return hdlc_ioctl(dev, ifr, cmd);
+
+	switch (ifr->ifr_settings.type) {
+	case IF_GET_IFACE:
+		ifr->ifr_settings.type = IF_IFACE_E1;
+		if (ifr->ifr_settings.size < size) {
+			ifr->ifr_settings.size = size; /* data size wanted */
+			return -ENOBUFS;
+		}
+		line.clock_type = priv->clocking;
+		line.clock_rate = 0;
+		line.loopback = 0;
+
+		if (copy_to_user(ifr->ifr_settings.ifs_ifsu.sync, &line, size))
+			return -EFAULT;
+		return 0;
+
+	default:
+		return hdlc_ioctl(dev, ifr, cmd);
+	}
+}
+
+static int uhdlc_open(struct net_device *dev)
+{
+	u32 cecr_subblock;
+	hdlc_device *hdlc = dev_to_hdlc(dev);
+	struct ucc_hdlc_private *priv = hdlc->priv;
+	struct ucc_tdm *utdm = priv->utdm;
+
+	if (priv->hdlc_busy != 1) {
+		if (request_irq(priv->ut_info->uf_info.irq,
+				ucc_hdlc_irq_handler, 0, "hdlc", priv))
+			return -ENODEV;
+
+		cecr_subblock = ucc_fast_get_qe_cr_subblock(
+					priv->ut_info->uf_info.ucc_num);
+
+		qe_issue_cmd(QE_INIT_TX_RX, cecr_subblock,
+			     QE_CR_PROTOCOL_UNSPECIFIED, 0);
+
+		ucc_fast_enable(priv->uccf, COMM_DIR_RX | COMM_DIR_TX);
+
+		/* Enable the TDM port */
+		if (priv->tsa)
+			utdm->si_regs->siglmr1_h |= (0x1 << utdm->tdm_port);
+
+		priv->hdlc_busy = 1;
+		netif_device_attach(priv->ndev);
+		napi_enable(&priv->napi);
+		netif_start_queue(dev);
+		hdlc_open(dev);
+	}
+
+	return 0;
+}
+
+static void uhdlc_memclean(struct ucc_hdlc_private *priv)
+{
+	qe_muram_free(priv->ucc_pram->riptr);
+	qe_muram_free(priv->ucc_pram->tiptr);
+
+	if (priv->rx_bd_base) {
+		dma_free_coherent(priv->dev,
+				  RX_BD_RING_LEN * sizeof(struct qe_bd),
+				  priv->rx_bd_base, priv->dma_rx_bd);
+
+		priv->rx_bd_base = NULL;
+		priv->dma_rx_bd = 0;
+	}
+
+	if (priv->tx_bd_base) {
+		dma_free_coherent(priv->dev,
+				  TX_BD_RING_LEN * sizeof(struct qe_bd),
+				  priv->tx_bd_base, priv->dma_tx_bd);
+
+		priv->tx_bd_base = NULL;
+		priv->dma_tx_bd = 0;
+	}
+
+	if (priv->ucc_pram) {
+		qe_muram_free(priv->ucc_pram_offset);
+		priv->ucc_pram = NULL;
+		priv->ucc_pram_offset = 0;
+	 }
+
+	kfree(priv->rx_skbuff);
+	priv->rx_skbuff = NULL;
+
+	kfree(priv->tx_skbuff);
+	priv->tx_skbuff = NULL;
+
+	if (priv->uf_regs) {
+		iounmap(priv->uf_regs);
+		priv->uf_regs = NULL;
+	}
+
+	if (priv->uccf) {
+		ucc_fast_free(priv->uccf);
+		priv->uccf = NULL;
+	}
+
+	if (priv->rx_buffer) {
+		dma_free_coherent(priv->dev,
+				  RX_BD_RING_LEN * MAX_RX_BUF_LENGTH,
+				  priv->rx_buffer, priv->dma_rx_addr);
+		priv->rx_buffer = NULL;
+		priv->dma_rx_addr = 0;
+	}
+
+	if (priv->tx_buffer) {
+		dma_free_coherent(priv->dev,
+				  TX_BD_RING_LEN * MAX_RX_BUF_LENGTH,
+				  priv->tx_buffer, priv->dma_tx_addr);
+		priv->tx_buffer = NULL;
+		priv->dma_tx_addr = 0;
+	}
+}
+
+static int uhdlc_close(struct net_device *dev)
+{
+	struct ucc_hdlc_private *priv = dev_to_hdlc(dev)->priv;
+	struct ucc_tdm *utdm = priv->utdm;
+	u32 cecr_subblock;
+
+	napi_disable(&priv->napi);
+	cecr_subblock = ucc_fast_get_qe_cr_subblock(
+				priv->ut_info->uf_info.ucc_num);
+
+	qe_issue_cmd(QE_GRACEFUL_STOP_TX, cecr_subblock,
+		     (u8)QE_CR_PROTOCOL_UNSPECIFIED, 0);
+	qe_issue_cmd(QE_CLOSE_RX_BD, cecr_subblock,
+		     (u8)QE_CR_PROTOCOL_UNSPECIFIED, 0);
+
+	if (priv->tsa)
+		utdm->si_regs->siglmr1_h &= ~(0x1 << utdm->tdm_port);
+
+	ucc_fast_disable(priv->uccf, COMM_DIR_RX | COMM_DIR_TX);
+
+	free_irq(priv->ut_info->uf_info.irq, priv);
+	netif_stop_queue(dev);
+	priv->hdlc_busy = 0;
+
+	return 0;
+}
+
+static int ucc_hdlc_attach(struct net_device *dev, unsigned short encoding,
+			   unsigned short parity)
+{
+	struct ucc_hdlc_private *priv = dev_to_hdlc(dev)->priv;
+
+	if (encoding != ENCODING_NRZ &&
+	    encoding != ENCODING_NRZI)
+		return -EINVAL;
+
+	if (parity != PARITY_NONE &&
+	    parity != PARITY_CRC32_PR1_CCITT &&
+	    parity != PARITY_CRC16_PR1_CCITT)
+		return -EINVAL;
+
+	priv->encoding = encoding;
+	priv->parity = parity;
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static void store_clk_config(struct ucc_hdlc_private *priv)
+{
+	struct qe_mux *qe_mux_reg = &qe_immr->qmx;
+
+	/* store si clk */
+	priv->cmxsi1cr_h = ioread32be(&qe_mux_reg->cmxsi1cr_h);
+	priv->cmxsi1cr_l = ioread32be(&qe_mux_reg->cmxsi1cr_l);
+
+	/* store si sync */
+	priv->cmxsi1syr = ioread32be(&qe_mux_reg->cmxsi1syr);
+
+	/* store ucc clk */
+	memcpy_fromio(priv->cmxucr, qe_mux_reg->cmxucr, 4 * sizeof(u32));
+}
+
+static void resume_clk_config(struct ucc_hdlc_private *priv)
+{
+	struct qe_mux *qe_mux_reg = &qe_immr->qmx;
+
+	memcpy_toio(qe_mux_reg->cmxucr, priv->cmxucr, 4 * sizeof(u32));
+
+	iowrite32be(priv->cmxsi1cr_h, &qe_mux_reg->cmxsi1cr_h);
+	iowrite32be(priv->cmxsi1cr_l, &qe_mux_reg->cmxsi1cr_l);
+
+	iowrite32be(priv->cmxsi1syr, &qe_mux_reg->cmxsi1syr);
+}
+
+static int uhdlc_suspend(struct device *dev)
+{
+	struct ucc_hdlc_private *priv = dev_get_drvdata(dev);
+	struct ucc_tdm_info *ut_info;
+	struct ucc_fast __iomem *uf_regs;
+
+	if (!priv)
+		return -EINVAL;
+
+	if (!netif_running(priv->ndev))
+		return 0;
+
+	netif_device_detach(priv->ndev);
+	napi_disable(&priv->napi);
+
+	ut_info = priv->ut_info;
+	uf_regs = priv->uf_regs;
+
+	/* backup gumr guemr*/
+	priv->gumr = ioread32be(&uf_regs->gumr);
+	priv->guemr = ioread8(&uf_regs->guemr);
+
+	priv->ucc_pram_bak = kmalloc(sizeof(*priv->ucc_pram_bak),
+					GFP_KERNEL);
+	if (!priv->ucc_pram_bak)
+		return -ENOMEM;
+
+	/* backup HDLC parameter */
+	memcpy_fromio(priv->ucc_pram_bak, priv->ucc_pram,
+		      sizeof(struct ucc_hdlc_param));
+
+	/* store the clk configuration */
+	store_clk_config(priv);
+
+	/* save power */
+	ucc_fast_disable(priv->uccf, COMM_DIR_RX | COMM_DIR_TX);
+
+	dev_dbg(dev, "ucc hdlc suspend\n");
+	return 0;
+}
+
+static int uhdlc_resume(struct device *dev)
+{
+	struct ucc_hdlc_private *priv = dev_get_drvdata(dev);
+	struct ucc_tdm *utdm = priv->utdm;
+	struct ucc_tdm_info *ut_info;
+	struct ucc_fast __iomem *uf_regs;
+	struct ucc_fast_private *uccf;
+	struct ucc_fast_info *uf_info;
+	int ret, i;
+	u32 cecr_subblock;
+	u16 bd_status;
+
+	if (!priv)
+		return -EINVAL;
+
+	if (!netif_running(priv->ndev))
+		return 0;
+
+	ut_info = priv->ut_info;
+	uf_info = &ut_info->uf_info;
+	uf_regs = priv->uf_regs;
+	uccf = priv->uccf;
+
+	/* restore gumr guemr */
+	iowrite8(priv->guemr, &uf_regs->guemr);
+	iowrite32be(priv->gumr, &uf_regs->gumr);
+
+	/* Set Virtual Fifo registers */
+	iowrite16be(uf_info->urfs, &uf_regs->urfs);
+	iowrite16be(uf_info->urfet, &uf_regs->urfet);
+	iowrite16be(uf_info->urfset, &uf_regs->urfset);
+	iowrite16be(uf_info->utfs, &uf_regs->utfs);
+	iowrite16be(uf_info->utfet, &uf_regs->utfet);
+	iowrite16be(uf_info->utftt, &uf_regs->utftt);
+	/* utfb, urfb are offsets from MURAM base */
+	iowrite32be(uccf->ucc_fast_tx_virtual_fifo_base_offset, &uf_regs->utfb);
+	iowrite32be(uccf->ucc_fast_rx_virtual_fifo_base_offset, &uf_regs->urfb);
+
+	/* Rx Tx and sync clock routing */
+	resume_clk_config(priv);
+
+	iowrite32be(uf_info->uccm_mask, &uf_regs->uccm);
+	iowrite32be(0xffffffff, &uf_regs->ucce);
+
+	ucc_fast_disable(priv->uccf, COMM_DIR_RX | COMM_DIR_TX);
+
+	/* rebuild SIRAM */
+	if (priv->tsa)
+		ucc_tdm_init(priv->utdm, priv->ut_info);
+
+	/* Write to QE CECR, UCCx channel to Stop Transmission */
+	cecr_subblock = ucc_fast_get_qe_cr_subblock(uf_info->ucc_num);
+	ret = qe_issue_cmd(QE_STOP_TX, cecr_subblock,
+			   (u8)QE_CR_PROTOCOL_UNSPECIFIED, 0);
+
+	/* Set UPSMR normal mode */
+	iowrite32be(0, &uf_regs->upsmr);
+
+	/* init parameter base */
+	cecr_subblock = ucc_fast_get_qe_cr_subblock(uf_info->ucc_num);
+	ret = qe_issue_cmd(QE_ASSIGN_PAGE_TO_DEVICE, cecr_subblock,
+			   QE_CR_PROTOCOL_UNSPECIFIED, priv->ucc_pram_offset);
+
+	priv->ucc_pram = (struct ucc_hdlc_param __iomem *)
+				qe_muram_addr(priv->ucc_pram_offset);
+
+	/* restore ucc parameter */
+	memcpy_toio(priv->ucc_pram, priv->ucc_pram_bak,
+		    sizeof(struct ucc_hdlc_param));
+	kfree(priv->ucc_pram_bak);
+
+	/* rebuild BD entry */
+	for (i = 0; i < RX_BD_RING_LEN; i++) {
+		if (i < (RX_BD_RING_LEN - 1))
+			bd_status = R_E_S | R_I_S;
+		else
+			bd_status = R_E_S | R_I_S | R_W_S;
+
+		iowrite16be(bd_status, &priv->rx_bd_base[i].status);
+		iowrite32be(priv->dma_rx_addr + i * MAX_RX_BUF_LENGTH,
+			    &priv->rx_bd_base[i].buf);
+	}
+
+	for (i = 0; i < TX_BD_RING_LEN; i++) {
+		if (i < (TX_BD_RING_LEN - 1))
+			bd_status =  T_I_S | T_TC_S;
+		else
+			bd_status =  T_I_S | T_TC_S | T_W_S;
+
+		iowrite16be(bd_status, &priv->tx_bd_base[i].status);
+		iowrite32be(priv->dma_tx_addr + i * MAX_RX_BUF_LENGTH,
+			    &priv->tx_bd_base[i].buf);
+	}
+
+	/* if hdlc is busy enable TX and RX */
+	if (priv->hdlc_busy == 1) {
+		cecr_subblock = ucc_fast_get_qe_cr_subblock(
+					priv->ut_info->uf_info.ucc_num);
+
+		qe_issue_cmd(QE_INIT_TX_RX, cecr_subblock,
+			     (u8)QE_CR_PROTOCOL_UNSPECIFIED, 0);
+
+		ucc_fast_enable(priv->uccf, COMM_DIR_RX | COMM_DIR_TX);
+
+		/* Enable the TDM port */
+		if (priv->tsa)
+			utdm->si_regs->siglmr1_h |= (0x1 << utdm->tdm_port);
+	}
+
+	napi_enable(&priv->napi);
+	netif_device_attach(priv->ndev);
+
+	return 0;
+}
+
+static const struct dev_pm_ops uhdlc_pm_ops = {
+	.suspend = uhdlc_suspend,
+	.resume = uhdlc_resume,
+	.freeze = uhdlc_suspend,
+	.thaw = uhdlc_resume,
+};
+
+#define HDLC_PM_OPS (&uhdlc_pm_ops)
+
+#else
+
+#define HDLC_PM_OPS NULL
+
+#endif
+static const struct net_device_ops uhdlc_ops = {
+	.ndo_open       = uhdlc_open,
+	.ndo_stop       = uhdlc_close,
+	.ndo_change_mtu = hdlc_change_mtu,
+	.ndo_start_xmit = hdlc_start_xmit,
+	.ndo_do_ioctl   = uhdlc_ioctl,
+};
+
+static int ucc_hdlc_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct ucc_hdlc_private *uhdlc_priv = NULL;
+	struct ucc_tdm_info *ut_info;
+	struct ucc_tdm *utdm;
+	struct resource res;
+	struct net_device *dev;
+	hdlc_device *hdlc;
+	int ucc_num;
+	const char *sprop;
+	int ret;
+	u32 val;
+
+	ret = of_property_read_u32_index(np, "cell-index", 0, &val);
+	if (ret) {
+		dev_err(&pdev->dev, "Invalid ucc property\n");
+		return -ENODEV;
+	}
+
+	ucc_num = val - 1;
+	if ((ucc_num > 3) || (ucc_num < 0)) {
+		dev_err(&pdev->dev, ": Invalid UCC num\n");
+		return -EINVAL;
+	}
+
+	memcpy(&utdm_info[ucc_num], &utdm_primary_info,
+	       sizeof(utdm_primary_info));
+
+	ut_info = &utdm_info[ucc_num];
+	ut_info->uf_info.ucc_num = ucc_num;
+
+	sprop = of_get_property(np, "rx-clock-name", NULL);
+	if (sprop) {
+		ut_info->uf_info.rx_clock = qe_clock_source(sprop);
+		if ((ut_info->uf_info.rx_clock < QE_CLK_NONE) ||
+		    (ut_info->uf_info.rx_clock > QE_CLK24)) {
+			dev_err(&pdev->dev, "Invalid rx-clock-name property\n");
+			return -EINVAL;
+		}
+	} else {
+		dev_err(&pdev->dev, "Invalid rx-clock-name property\n");
+		return -EINVAL;
+	}
+
+	sprop = of_get_property(np, "tx-clock-name", NULL);
+	if (sprop) {
+		ut_info->uf_info.tx_clock = qe_clock_source(sprop);
+		if ((ut_info->uf_info.tx_clock < QE_CLK_NONE) ||
+		    (ut_info->uf_info.tx_clock > QE_CLK24)) {
+			dev_err(&pdev->dev, "Invalid tx-clock-name property\n");
+			return -EINVAL;
+		}
+	} else {
+		dev_err(&pdev->dev, "Invalid tx-clock-name property\n");
+		return -EINVAL;
+	}
+
+	/* use the same clock when work in loopback */
+	if (ut_info->uf_info.rx_clock == ut_info->uf_info.tx_clock)
+		qe_setbrg(ut_info->uf_info.rx_clock, 20000000, 1);
+
+	ret = of_address_to_resource(np, 0, &res);
+	if (ret)
+		return -EINVAL;
+
+	ut_info->uf_info.regs = res.start;
+	ut_info->uf_info.irq = irq_of_parse_and_map(np, 0);
+
+	uhdlc_priv = kzalloc(sizeof(*uhdlc_priv), GFP_KERNEL);
+	if (!uhdlc_priv) {
+		ret = -ENOMEM;
+		dev_err(&pdev->dev, "No mem to alloc hdlc private data\n");
+		goto err_alloc_priv;
+	}
+
+	dev_set_drvdata(&pdev->dev, uhdlc_priv);
+	uhdlc_priv->dev = &pdev->dev;
+	uhdlc_priv->ut_info = ut_info;
+
+	if (of_get_property(np, "fsl,tdm-interface", NULL))
+		uhdlc_priv->tsa = 1;
+
+	if (of_get_property(np, "fsl,ucc-internal-loopback", NULL))
+		uhdlc_priv->loopback = 1;
+
+	if (uhdlc_priv->tsa == 1) {
+		utdm = kzalloc(sizeof(*utdm), GFP_KERNEL);
+		if (!utdm) {
+			ret = -ENOMEM;
+			dev_err(&pdev->dev, "No mem to alloc ucc tdm data\n");
+			goto err_alloc_utdm;
+		}
+		uhdlc_priv->utdm = utdm;
+		ret = ucc_of_parse_tdm(np, utdm, ut_info);
+		if (ret)
+			goto err_miss_tsa_property;
+	}
+
+	ret = uhdlc_init(uhdlc_priv);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to init uhdlc\n");
+		goto err_hdlc_init;
+	}
+
+	dev = alloc_hdlcdev(uhdlc_priv);
+	if (!dev) {
+		ret = -ENOMEM;
+		pr_err("ucc_hdlc: unable to allocate memory\n");
+		goto err_hdlc_init;
+	}
+
+	uhdlc_priv->ndev = dev;
+	hdlc = dev_to_hdlc(dev);
+	dev->tx_queue_len = 16;
+	dev->netdev_ops = &uhdlc_ops;
+	hdlc->attach = ucc_hdlc_attach;
+	hdlc->xmit = ucc_hdlc_tx;
+	netif_napi_add(dev, &uhdlc_priv->napi, ucc_hdlc_poll, 32);
+	if (register_hdlc_device(dev)) {
+		ret = -ENOBUFS;
+		pr_err("ucc_hdlc: unable to register hdlc device\n");
+		free_netdev(dev);
+		goto err_hdlc_init;
+	}
+
+	return 0;
+
+err_hdlc_init:
+err_miss_tsa_property:
+	kfree(uhdlc_priv);
+	if (uhdlc_priv->tsa)
+		kfree(utdm);
+err_alloc_utdm:
+	kfree(uhdlc_priv);
+err_alloc_priv:
+	return ret;
+}
+
+static int ucc_hdlc_remove(struct platform_device *pdev)
+{
+	struct ucc_hdlc_private *priv = dev_get_drvdata(&pdev->dev);
+
+	uhdlc_memclean(priv);
+
+	if (priv->utdm->si_regs) {
+		iounmap(priv->utdm->si_regs);
+		priv->utdm->si_regs = NULL;
+	}
+
+	if (priv->utdm->siram) {
+		iounmap(priv->utdm->siram);
+		priv->utdm->siram = NULL;
+	}
+	kfree(priv);
+
+	dev_info(&pdev->dev, "UCC based hdlc module removed\n");
+
+	return 0;
+}
+
+static const struct of_device_id fsl_ucc_hdlc_of_match[] = {
+	{
+	.compatible = "fsl,ucc-hdlc",
+	},
+	{},
+};
+
+MODULE_DEVICE_TABLE(of, fsl_ucc_hdlc_of_match);
+
+static struct platform_driver ucc_hdlc_driver = {
+	.probe	= ucc_hdlc_probe,
+	.remove	= ucc_hdlc_remove,
+	.driver	= {
+		.owner		= THIS_MODULE,
+		.name		= DRV_NAME,
+		.pm		= HDLC_PM_OPS,
+		.of_match_table	= fsl_ucc_hdlc_of_match,
+	},
+};
+
+static int __init ucc_hdlc_init(void)
+{
+	return platform_driver_register(&ucc_hdlc_driver);
+}
+
+static void __exit ucc_hdlc_exit(void)
+{
+	platform_driver_unregister(&ucc_hdlc_driver);
+}
+
+module_init(ucc_hdlc_init);
+module_exit(ucc_hdlc_exit);
diff --git a/drivers/net/wan/fsl_ucc_hdlc.h b/drivers/net/wan/fsl_ucc_hdlc.h
new file mode 100644
index 0000000..881ecde
--- /dev/null
+++ b/drivers/net/wan/fsl_ucc_hdlc.h
@@ -0,0 +1,147 @@
+/* Freescale QUICC Engine HDLC Device Driver
+ *
+ * Copyright 2014 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.
+ */
+
+#ifndef _UCC_HDLC_H_
+#define _UCC_HDLC_H_
+
+#include <linux/kernel.h>
+#include <linux/list.h>
+
+#include <soc/fsl/qe/immap_qe.h>
+#include <soc/fsl/qe/qe.h>
+
+#include <soc/fsl/qe/ucc.h>
+#include <soc/fsl/qe/ucc_fast.h>
+
+/* UCC HDLC event register */
+#define UCCE_HDLC_RX_EVENTS	\
+(UCC_HDLC_UCCE_RXF | UCC_HDLC_UCCE_RXB | UCC_HDLC_UCCE_BSY)
+#define UCCE_HDLC_TX_EVENTS	(UCC_HDLC_UCCE_TXB | UCC_HDLC_UCCE_TXE)
+
+struct ucc_hdlc_param {
+	__be16 riptr;
+	__be16 tiptr;
+	__be16 res0;
+	__be16 mrblr;
+	__be32 rstate;
+	__be32 rbase;
+	__be16 rbdstat;
+	__be16 rbdlen;
+	__be32 rdptr;
+	__be32 tstate;
+	__be32 tbase;
+	__be16 tbdstat;
+	__be16 tbdlen;
+	__be32 tdptr;
+	__be32 rbptr;
+	__be32 tbptr;
+	__be32 rcrc;
+	__be32 res1;
+	__be32 tcrc;
+	__be32 res2;
+	__be32 res3;
+	__be32 c_mask;
+	__be32 c_pres;
+	__be16 disfc;
+	__be16 crcec;
+	__be16 abtsc;
+	__be16 nmarc;
+	__be32 max_cnt;
+	__be16 mflr;
+	__be16 rfthr;
+	__be16 rfcnt;
+	__be16 hmask;
+	__be16 haddr1;
+	__be16 haddr2;
+	__be16 haddr3;
+	__be16 haddr4;
+	__be16 ts_tmp;
+	__be16 tmp_mb;
+};
+
+struct ucc_hdlc_private {
+	struct ucc_tdm	*utdm;
+	struct ucc_tdm_info *ut_info;
+	struct ucc_fast_private *uccf;
+	struct device *dev;
+	struct net_device *ndev;
+	struct napi_struct napi;
+	struct ucc_fast __iomem *uf_regs;	/* UCC Fast registers */
+	struct ucc_hdlc_param __iomem *ucc_pram;
+	u16 tsa;
+	bool hdlc_busy;
+	bool loopback;
+
+	u8 *tx_buffer;
+	u8 *rx_buffer;
+	dma_addr_t dma_tx_addr;
+	dma_addr_t dma_rx_addr;
+
+	struct qe_bd *tx_bd_base;
+	struct qe_bd *rx_bd_base;
+	dma_addr_t dma_tx_bd;
+	dma_addr_t dma_rx_bd;
+	struct qe_bd *curtx_bd;
+	struct qe_bd *currx_bd;
+	struct qe_bd *dirty_tx;
+	u16 currx_bdnum;
+
+	struct sk_buff **tx_skbuff;
+	struct sk_buff **rx_skbuff;
+	u16 skb_curtx;
+	u16 skb_currx;
+	unsigned short skb_dirtytx;
+
+	unsigned short tx_ring_size;
+	unsigned short rx_ring_size;
+	u32 ucc_pram_offset;
+
+	unsigned short encoding;
+	unsigned short parity;
+	u32 clocking;
+	spinlock_t lock;	/* lock for Tx BD and Tx buffer */
+#ifdef CONFIG_PM
+	struct ucc_hdlc_param *ucc_pram_bak;
+	u32 gumr;
+	u8 guemr;
+	u32 cmxsi1cr_l, cmxsi1cr_h;
+	u32 cmxsi1syr;
+	u32 cmxucr[4];
+#endif
+};
+
+#define TX_BD_RING_LEN	0x10
+#define RX_BD_RING_LEN	0x20
+#define RX_CLEAN_MAX	0x10
+#define NUM_OF_BUF	4
+#define MAX_RX_BUF_LENGTH	(48 * 0x20)
+#define MAX_FRAME_LENGTH	(MAX_RX_BUF_LENGTH + 8)
+#define ALIGNMENT_OF_UCC_HDLC_PRAM	64
+#define SI_BANK_SIZE	128
+#define MAX_HDLC_NUM	4
+#define HDLC_HEAD_LEN	2
+#define HDLC_CRC_SIZE	2
+#define TX_RING_MOD_MASK(size) (size - 1)
+#define RX_RING_MOD_MASK(size) (size - 1)
+
+#define HDLC_HEAD_MASK		0x0000
+#define DEFAULT_HDLC_HEAD	0xff44
+#define DEFAULT_ADDR_MASK	0x00ff
+#define DEFAULT_HDLC_ADDR	0x00ff
+
+#define BMR_GBL			0x20000000
+#define BMR_BIG_ENDIAN		0x10000000
+#define CRC_16BIT_MASK		0x0000F0B8
+#define CRC_16BIT_PRES		0x0000FFFF
+#define DEFAULT_RFTHR		1
+
+#define DEFAULT_PPP_HEAD    0xff03
+
+#endif
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index 502b0a0..264bd63 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -2559,12 +2559,14 @@
 			   const u8 *mac, struct station_info *sinfo)
 {
 	struct brcmf_if *ifp = netdev_priv(ndev);
+	struct brcmf_scb_val_le scb_val;
 	s32 err = 0;
 	struct brcmf_sta_info_le sta_info_le;
 	u32 sta_flags;
 	u32 is_tdls_peer;
 	s32 total_rssi;
 	s32 count_rssi;
+	int rssi;
 	u32 i;
 
 	brcmf_dbg(TRACE, "Enter, MAC %pM\n", mac);
@@ -2648,6 +2650,20 @@
 			sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
 			total_rssi /= count_rssi;
 			sinfo->signal = total_rssi;
+		} else if (test_bit(BRCMF_VIF_STATUS_CONNECTED,
+			&ifp->vif->sme_state)) {
+			memset(&scb_val, 0, sizeof(scb_val));
+			err = brcmf_fil_cmd_data_get(ifp, BRCMF_C_GET_RSSI,
+						     &scb_val, sizeof(scb_val));
+			if (err) {
+				brcmf_err("Could not get rssi (%d)\n", err);
+				goto done;
+			} else {
+				rssi = le32_to_cpu(scb_val.val);
+				sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
+				sinfo->signal = rssi;
+				brcmf_dbg(CONN, "RSSI %d dBm\n", rssi);
+			}
 		}
 	}
 done:
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c
index 68f1ce0..2b9a2bc 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c
@@ -1157,6 +1157,8 @@
 		brcmu_pkt_buf_free_skb(skb);
 		return;
 	}
+
+	skb->protocol = eth_type_trans(skb, ifp->ndev);
 	brcmf_netif_rx(ifp, skb);
 }
 
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 9ed0ed1..a1e28a4 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -30,6 +30,8 @@
 #include <linux/module.h>
 #include <linux/ktime.h>
 #include <net/genetlink.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
 #include "mac80211_hwsim.h"
 
 #define WARN_QUEUE 100
@@ -250,6 +252,28 @@
 	cp->magic = 0;
 }
 
+static unsigned int hwsim_net_id;
+
+static int hwsim_netgroup;
+
+struct hwsim_net {
+	int netgroup;
+};
+
+static inline int hwsim_net_get_netgroup(struct net *net)
+{
+	struct hwsim_net *hwsim_net = net_generic(net, hwsim_net_id);
+
+	return hwsim_net->netgroup;
+}
+
+static inline void hwsim_net_set_netgroup(struct net *net)
+{
+	struct hwsim_net *hwsim_net = net_generic(net, hwsim_net_id);
+
+	hwsim_net->netgroup = hwsim_netgroup++;
+}
+
 static struct class *hwsim_class;
 
 static struct net_device *hwsim_mon; /* global monitor netdev */
@@ -526,6 +550,9 @@
 	 */
 	u64 group;
 
+	/* group shared by radios created in the same netns */
+	int netgroup;
+
 	int power_level;
 
 	/* difference between this hw's clock and the real clock, in usecs */
@@ -568,6 +595,7 @@
 	.name = "MAC80211_HWSIM",
 	.version = 1,
 	.maxattr = HWSIM_ATTR_MAX,
+	.netnsok = true,
 };
 
 enum hwsim_multicast_groups {
@@ -1202,6 +1230,9 @@
 		if (!(data->group & data2->group))
 			continue;
 
+		if (data->netgroup != data2->netgroup)
+			continue;
+
 		if (!hwsim_chans_compat(chan, data2->tmp_chan) &&
 		    !hwsim_chans_compat(chan, data2->channel)) {
 			ieee80211_iterate_active_interfaces_atomic(
@@ -2349,6 +2380,7 @@
 	struct ieee80211_hw *hw;
 	enum nl80211_band band;
 	const struct ieee80211_ops *ops = &mac80211_hwsim_ops;
+	struct net *net;
 	int idx;
 
 	if (WARN_ON(param->channels > 1 && !param->use_chanctx))
@@ -2366,6 +2398,13 @@
 		err = -ENOMEM;
 		goto failed;
 	}
+
+	if (info)
+		net = genl_info_net(info);
+	else
+		net = &init_net;
+	wiphy_net_set(hw->wiphy, net);
+
 	data = hw->priv;
 	data->hw = hw;
 
@@ -2541,6 +2580,8 @@
 	data->group = 1;
 	mutex_init(&data->mutex);
 
+	data->netgroup = hwsim_net_get_netgroup(net);
+
 	/* Enable frame retransmissions for lossy channels */
 	hw->max_rates = 4;
 	hw->max_rate_tries = 11;
@@ -2776,6 +2817,7 @@
 	if (!info->attrs[HWSIM_ATTR_ADDR_TRANSMITTER] ||
 	    !info->attrs[HWSIM_ATTR_FLAGS] ||
 	    !info->attrs[HWSIM_ATTR_COOKIE] ||
+	    !info->attrs[HWSIM_ATTR_SIGNAL] ||
 	    !info->attrs[HWSIM_ATTR_TX_INFO])
 		goto out;
 
@@ -3013,6 +3055,9 @@
 				continue;
 		}
 
+		if (!net_eq(wiphy_net(data->hw->wiphy), genl_info_net(info)))
+			continue;
+
 		list_del(&data->list);
 		spin_unlock_bh(&hwsim_radio_lock);
 		mac80211_hwsim_del_radio(data, wiphy_name(data->hw->wiphy),
@@ -3039,6 +3084,9 @@
 		if (data->idx != idx)
 			continue;
 
+		if (!net_eq(wiphy_net(data->hw->wiphy), genl_info_net(info)))
+			continue;
+
 		skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 		if (!skb) {
 			res = -ENOMEM;
@@ -3078,6 +3126,9 @@
 		if (data->idx < idx)
 			continue;
 
+		if (!net_eq(wiphy_net(data->hw->wiphy), sock_net(skb->sk)))
+			continue;
+
 		res = mac80211_hwsim_get_radio(skb, data,
 					       NETLINK_CB(cb->skb).portid,
 					       cb->nlh->nlmsg_seq, cb,
@@ -3117,13 +3168,13 @@
 		.cmd = HWSIM_CMD_NEW_RADIO,
 		.policy = hwsim_genl_policy,
 		.doit = hwsim_new_radio_nl,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = HWSIM_CMD_DEL_RADIO,
 		.policy = hwsim_genl_policy,
 		.doit = hwsim_del_radio_nl,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = HWSIM_CMD_GET_RADIO,
@@ -3205,6 +3256,40 @@
 	return -EINVAL;
 }
 
+static __net_init int hwsim_init_net(struct net *net)
+{
+	hwsim_net_set_netgroup(net);
+
+	return 0;
+}
+
+static void __net_exit hwsim_exit_net(struct net *net)
+{
+	struct mac80211_hwsim_data *data, *tmp;
+
+	spin_lock_bh(&hwsim_radio_lock);
+	list_for_each_entry_safe(data, tmp, &hwsim_radios, list) {
+		if (!net_eq(wiphy_net(data->hw->wiphy), net))
+			continue;
+
+		/* Radios created in init_net are returned to init_net. */
+		if (data->netgroup == hwsim_net_get_netgroup(&init_net))
+			continue;
+
+		list_del(&data->list);
+		INIT_WORK(&data->destroy_work, destroy_radio);
+		schedule_work(&data->destroy_work);
+	}
+	spin_unlock_bh(&hwsim_radio_lock);
+}
+
+static struct pernet_operations hwsim_net_ops = {
+	.init = hwsim_init_net,
+	.exit = hwsim_exit_net,
+	.id   = &hwsim_net_id,
+	.size = sizeof(struct hwsim_net),
+};
+
 static void hwsim_exit_netlink(void)
 {
 	/* unregister the notifier */
@@ -3241,10 +3326,14 @@
 	spin_lock_init(&hwsim_radio_lock);
 	INIT_LIST_HEAD(&hwsim_radios);
 
-	err = platform_driver_register(&mac80211_hwsim_driver);
+	err = register_pernet_device(&hwsim_net_ops);
 	if (err)
 		return err;
 
+	err = platform_driver_register(&mac80211_hwsim_driver);
+	if (err)
+		goto out_unregister_pernet;
+
 	hwsim_class = class_create(THIS_MODULE, "mac80211_hwsim");
 	if (IS_ERR(hwsim_class)) {
 		err = PTR_ERR(hwsim_class);
@@ -3362,6 +3451,8 @@
 	mac80211_hwsim_free();
 out_unregister_driver:
 	platform_driver_unregister(&mac80211_hwsim_driver);
+out_unregister_pernet:
+	unregister_pernet_device(&hwsim_net_ops);
 	return err;
 }
 module_init(init_mac80211_hwsim);
@@ -3375,5 +3466,6 @@
 	mac80211_hwsim_free();
 	unregister_netdev(hwsim_mon);
 	platform_driver_unregister(&mac80211_hwsim_driver);
+	unregister_pernet_device(&hwsim_net_ops);
 }
 module_exit(exit_mac80211_hwsim);
diff --git a/drivers/net/wireless/realtek/rtlwifi/core.c b/drivers/net/wireless/realtek/rtlwifi/core.c
index 0f48048..3a0faa8 100644
--- a/drivers/net/wireless/realtek/rtlwifi/core.c
+++ b/drivers/net/wireless/realtek/rtlwifi/core.c
@@ -54,7 +54,7 @@
 void rtl_addr_delay(u32 addr)
 {
 	if (addr == 0xfe)
-		msleep(50);
+		mdelay(50);
 	else if (addr == 0xfd)
 		msleep(5);
 	else if (addr == 0xfc)
@@ -75,7 +75,7 @@
 		rtl_addr_delay(addr);
 	} else {
 		rtl_set_rfreg(hw, rfpath, addr, mask, data);
-		usleep_range(1, 2);
+		udelay(1);
 	}
 }
 EXPORT_SYMBOL(rtl_rfreg_delay);
@@ -86,7 +86,7 @@
 		rtl_addr_delay(addr);
 	} else {
 		rtl_set_bbreg(hw, addr, MASKDWORD, data);
-		usleep_range(1, 2);
+		udelay(1);
 	}
 }
 EXPORT_SYMBOL(rtl_bb_delay);
diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c
index e051e1b..de68707 100644
--- a/drivers/of/of_mdio.c
+++ b/drivers/of/of_mdio.c
@@ -361,7 +361,7 @@
 }
 EXPORT_SYMBOL(of_phy_attach);
 
-#if defined(CONFIG_FIXED_PHY)
+#if IS_ENABLED(CONFIG_FIXED_PHY)
 /*
  * of_phy_is_fixed_link() and of_phy_register_fixed_link() must
  * support two DT bindings:
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index f2d01d4..1b8304e 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -950,17 +950,14 @@
 
 		/* For SPIs, we need to track the affinity per IRQ */
 		if (using_spi) {
-			if (i >= pdev->num_resources) {
-				of_node_put(dn);
+			if (i >= pdev->num_resources)
 				break;
-			}
 
 			irqs[i] = cpu;
 		}
 
 		/* Keep track of the CPUs containing this PMU type */
 		cpumask_set_cpu(cpu, &pmu->supported_cpus);
-		of_node_put(dn);
 		i++;
 	} while (1);
 
@@ -995,9 +992,6 @@
 
 	armpmu_init(pmu);
 
-	if (!__oprofile_cpu_pmu)
-		__oprofile_cpu_pmu = pmu;
-
 	pmu->plat_device = pdev;
 
 	if (node && (of_id = of_match_node(of_table, pdev->dev.of_node))) {
@@ -1033,6 +1027,9 @@
 	if (ret)
 		goto out_destroy;
 
+	if (!__oprofile_cpu_pmu)
+		__oprofile_cpu_pmu = pmu;
+
 	pr_info("enabled with %s PMU driver, %d counters available\n",
 			pmu->name, pmu->num_events);
 
@@ -1043,6 +1040,7 @@
 out_free:
 	pr_info("%s: failed to register PMU devices!\n",
 		of_node_full_name(node));
+	kfree(pmu->irq_affinity);
 	kfree(pmu);
 	return ret;
 }
diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig
index b869b98..01fb93b 100644
--- a/drivers/phy/Kconfig
+++ b/drivers/phy/Kconfig
@@ -434,4 +434,12 @@
 
 source "drivers/phy/tegra/Kconfig"
 
+config PHY_NS2_PCIE
+	tristate "Broadcom Northstar2 PCIe PHY driver"
+	depends on OF && MDIO_BUS_MUX_BCM_IPROC
+	select GENERIC_PHY
+	default ARCH_BCM_IPROC
+	help
+	  Enable this to support the Broadcom Northstar2 PCIe PHY.
+	  If unsure, say N.
 endmenu
diff --git a/drivers/phy/Makefile b/drivers/phy/Makefile
index 9c3e73c..7aea094 100644
--- a/drivers/phy/Makefile
+++ b/drivers/phy/Makefile
@@ -53,5 +53,5 @@
 obj-$(CONFIG_PHY_BRCM_SATA)		+= phy-brcm-sata.o
 obj-$(CONFIG_PHY_PISTACHIO_USB)		+= phy-pistachio-usb.o
 obj-$(CONFIG_PHY_CYGNUS_PCIE)		+= phy-bcm-cygnus-pcie.o
-
 obj-$(CONFIG_ARCH_TEGRA) += tegra/
+obj-$(CONFIG_PHY_NS2_PCIE)		+= phy-bcm-ns2-pcie.o
diff --git a/drivers/phy/phy-bcm-ns2-pcie.c b/drivers/phy/phy-bcm-ns2-pcie.c
new file mode 100644
index 0000000..9513f7a
--- /dev/null
+++ b/drivers/phy/phy-bcm-ns2-pcie.c
@@ -0,0 +1,115 @@
+/*
+ * Copyright (C) 2016 Broadcom
+ *
+ * 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 version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/of_mdio.h>
+#include <linux/mdio.h>
+#include <linux/phy.h>
+#include <linux/phy/phy.h>
+
+struct ns2_pci_phy {
+	struct mdio_device *mdiodev;
+	struct phy *phy;
+};
+
+#define BLK_ADDR_REG_OFFSET	0x1f
+#define PLL_AFE1_100MHZ_BLK	0x2100
+#define PLL_CLK_AMP_OFFSET	0x03
+#define PLL_CLK_AMP_2P05V	0x2b18
+
+static int ns2_pci_phy_init(struct phy *p)
+{
+	struct ns2_pci_phy *phy = phy_get_drvdata(p);
+	int rc;
+
+	/* select the AFE 100MHz block page */
+	rc = mdiobus_write(phy->mdiodev->bus, phy->mdiodev->addr,
+			   BLK_ADDR_REG_OFFSET, PLL_AFE1_100MHZ_BLK);
+	if (rc)
+		goto err;
+
+	/* set the 100 MHz reference clock amplitude to 2.05 v */
+	rc = mdiobus_write(phy->mdiodev->bus, phy->mdiodev->addr,
+			   PLL_CLK_AMP_OFFSET, PLL_CLK_AMP_2P05V);
+	if (rc)
+		goto err;
+
+	return 0;
+
+err:
+	dev_err(&phy->mdiodev->dev, "Error %d writing to phy\n", rc);
+	return rc;
+}
+
+static struct phy_ops ns2_pci_phy_ops = {
+	.init = ns2_pci_phy_init,
+};
+
+static int ns2_pci_phy_probe(struct mdio_device *mdiodev)
+{
+	struct device *dev = &mdiodev->dev;
+	struct phy_provider *provider;
+	struct ns2_pci_phy *p;
+	struct phy *phy;
+
+	phy = devm_phy_create(dev, dev->of_node, &ns2_pci_phy_ops);
+	if (IS_ERR(phy)) {
+		dev_err(dev, "failed to create Phy\n");
+		return PTR_ERR(phy);
+	}
+
+	p = devm_kmalloc(dev, sizeof(struct ns2_pci_phy),
+			 GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	p->mdiodev = mdiodev;
+	dev_set_drvdata(dev, p);
+
+	p->phy = phy;
+	phy_set_drvdata(phy, p);
+
+	provider = devm_of_phy_provider_register(&phy->dev,
+						 of_phy_simple_xlate);
+	if (IS_ERR(provider)) {
+		dev_err(dev, "failed to register Phy provider\n");
+		return PTR_ERR(provider);
+	}
+
+	dev_info(dev, "%s PHY registered\n", dev_name(dev));
+
+	return 0;
+}
+
+static const struct of_device_id ns2_pci_phy_of_match[] = {
+	{ .compatible = "brcm,ns2-pcie-phy", },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, ns2_pci_phy_of_match);
+
+static struct mdio_driver ns2_pci_phy_driver = {
+	.mdiodrv = {
+		.driver = {
+			.name = "phy-bcm-ns2-pci",
+			.of_match_table = ns2_pci_phy_of_match,
+		},
+	},
+	.probe = ns2_pci_phy_probe,
+};
+mdio_module_driver(ns2_pci_phy_driver);
+
+MODULE_AUTHOR("Broadcom");
+MODULE_DESCRIPTION("Broadcom Northstar2 PCI Phy driver");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:phy-bcm-ns2-pci");
diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
index 207b13b..a607655 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
@@ -1256,9 +1256,10 @@
 	const struct mtk_desc_pin *pin;
 
 	chained_irq_enter(chip, desc);
-	for (eint_num = 0; eint_num < pctl->devdata->ap_num; eint_num += 32) {
+	for (eint_num = 0;
+	     eint_num < pctl->devdata->ap_num;
+	     eint_num += 32, reg += 4) {
 		status = readl(reg);
-		reg += 4;
 		while (status) {
 			offset = __ffs(status);
 			index = eint_num + offset;
diff --git a/drivers/pinctrl/nomadik/pinctrl-nomadik.c b/drivers/pinctrl/nomadik/pinctrl-nomadik.c
index ccbfc32..38facef 100644
--- a/drivers/pinctrl/nomadik/pinctrl-nomadik.c
+++ b/drivers/pinctrl/nomadik/pinctrl-nomadik.c
@@ -854,7 +854,7 @@
 
 	clk_enable(nmk_chip->clk);
 
-	dir = !!(readl(nmk_chip->addr + NMK_GPIO_DIR) & BIT(offset));
+	dir = !(readl(nmk_chip->addr + NMK_GPIO_DIR) & BIT(offset));
 
 	clk_disable(nmk_chip->clk);
 
diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index ec2e014..bf40063 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -19,6 +19,7 @@
 #include <linux/seq_file.h>
 #include <linux/ethtool.h>
 #include <linux/hashtable.h>
+#include <linux/ip.h>
 
 #include <net/ipv6.h>
 #include <net/if_inet6.h>
@@ -144,6 +145,7 @@
 	unsigned int sg_alloc_page_rx;
 	unsigned int tx_csum;
 	unsigned int tx_lin;
+	unsigned int tx_linfail;
 };
 
 /* Routing stuff */
@@ -559,7 +561,6 @@
 	QETH_IP_TYPE_NORMAL,
 	QETH_IP_TYPE_VIPA,
 	QETH_IP_TYPE_RXIP,
-	QETH_IP_TYPE_DEL_ALL_MC,
 };
 
 enum qeth_cmd_buffer_state {
@@ -740,17 +741,10 @@
 	unsigned short vid;
 };
 
-enum qeth_mac_disposition {
-	QETH_DISP_MAC_DELETE = 0,
-	QETH_DISP_MAC_DO_NOTHING = 1,
-	QETH_DISP_MAC_ADD = 2,
-};
-
-struct qeth_mac {
-	u8 mac_addr[OSA_ADDR_LEN];
-	u8 is_uc:1;
-	u8 disp_flag:2;
-	struct hlist_node hnode;
+enum qeth_addr_disposition {
+	QETH_DISP_ADDR_DELETE = 0,
+	QETH_DISP_ADDR_DO_NOTHING = 1,
+	QETH_DISP_ADDR_ADD = 2,
 };
 
 struct qeth_rx {
@@ -798,6 +792,8 @@
 	unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
 	struct list_head vid_list;
 	DECLARE_HASHTABLE(mac_htable, 4);
+	DECLARE_HASHTABLE(ip_htable, 4);
+	DECLARE_HASHTABLE(ip_mc_htable, 4);
 	struct work_struct kernel_thread_starter;
 	spinlock_t thread_mask_lock;
 	unsigned long thread_start_mask;
@@ -805,8 +801,6 @@
 	unsigned long thread_running_mask;
 	struct task_struct *recovery_task;
 	spinlock_t ip_lock;
-	struct list_head ip_list;
-	struct list_head *ip_tbd_list;
 	struct qeth_ipato ipato;
 	struct list_head cmd_waiter_list;
 	/* QDIO buffer handling */
@@ -844,6 +838,19 @@
 /*some helper functions*/
 #define QETH_CARD_IFNAME(card) (((card)->dev)? (card)->dev->name : "")
 
+/**
+ * qeth_get_elements_for_range() -	find number of SBALEs to cover range.
+ * @start:				Start of the address range.
+ * @end:				Address after the end of the range.
+ *
+ * Returns the number of pages, and thus QDIO buffer elements, needed to cover
+ * the specified address range.
+ */
+static inline int qeth_get_elements_for_range(addr_t start, addr_t end)
+{
+	return PFN_UP(end - 1) - PFN_DOWN(start);
+}
+
 static inline int qeth_get_micros(void)
 {
 	return (int) (get_tod_clock() >> 12);
@@ -865,6 +872,11 @@
 	}
 }
 
+static inline int qeth_get_ip_protocol(struct sk_buff *skb)
+{
+	return ip_hdr(skb)->protocol;
+}
+
 static inline void qeth_put_buffer_pool_entry(struct qeth_card *card,
 		struct qeth_buffer_pool_entry *entry)
 {
@@ -981,12 +993,13 @@
 			  int (*reply_cb)(struct qeth_card *,
 					  struct qeth_reply *, unsigned long),
 			  void *);
+int qeth_setassparms_cb(struct qeth_card *, struct qeth_reply *, unsigned long);
 struct qeth_cmd_buffer *qeth_get_setassparms_cmd(struct qeth_card *,
 						 enum qeth_ipa_funcs,
 						 __u16, __u16,
 						 enum qeth_prot_versions);
-int qeth_start_ipa_tx_checksum(struct qeth_card *);
-int qeth_set_rx_csum(struct qeth_card *, int);
+int qeth_set_features(struct net_device *, netdev_features_t);
+netdev_features_t qeth_fix_features(struct net_device *, netdev_features_t);
 
 /* exports for OSN */
 int qeth_osn_assist(struct net_device *, void *, int);
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index b7b7477..7dba6c8 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -1464,8 +1464,6 @@
 	card->thread_allowed_mask = 0;
 	card->thread_running_mask = 0;
 	INIT_WORK(&card->kernel_thread_starter, qeth_start_kernel_thread);
-	INIT_LIST_HEAD(&card->ip_list);
-	INIT_LIST_HEAD(card->ip_tbd_list);
 	INIT_LIST_HEAD(&card->cmd_waiter_list);
 	init_waitqueue_head(&card->wait_q);
 	/* initial options */
@@ -1500,11 +1498,6 @@
 	if (!card)
 		goto out;
 	QETH_DBF_HEX(SETUP, 2, &card, sizeof(void *));
-	card->ip_tbd_list = kzalloc(sizeof(struct list_head), GFP_KERNEL);
-	if (!card->ip_tbd_list) {
-		QETH_DBF_TEXT(SETUP, 0, "iptbdnom");
-		goto out_card;
-	}
 	if (qeth_setup_channel(&card->read))
 		goto out_ip;
 	if (qeth_setup_channel(&card->write))
@@ -1517,8 +1510,6 @@
 out_channel:
 	qeth_clean_channel(&card->read);
 out_ip:
-	kfree(card->ip_tbd_list);
-out_card:
 	kfree(card);
 out:
 	return NULL;
@@ -3757,6 +3748,14 @@
 }
 EXPORT_SYMBOL_GPL(qeth_qdio_output_handler);
 
+/* We cannot use outbound queue 3 for unicast packets on HiperSockets */
+static inline int qeth_cut_iqd_prio(struct qeth_card *card, int queue_num)
+{
+	if ((card->info.type == QETH_CARD_TYPE_IQD) && (queue_num == 3))
+		return 2;
+	return queue_num;
+}
+
 /**
  * Note: Function assumes that we have 4 outbound queues.
  */
@@ -3784,9 +3783,9 @@
 			return card->qdio.default_out_queue;
 		}
 		if (card->qdio.do_prio_queueing == QETH_PRIO_Q_ING_PREC)
-			return ~tos >> 6 & 3;
+			return qeth_cut_iqd_prio(card, ~tos >> 6 & 3);
 		if (tos & IPTOS_MINCOST)
-			return 3;
+			return qeth_cut_iqd_prio(card, 3);
 		if (tos & IPTOS_RELIABILITY)
 			return 2;
 		if (tos & IPTOS_THROUGHPUT)
@@ -3797,11 +3796,12 @@
 	case QETH_PRIO_Q_ING_SKB:
 		if (skb->priority > 5)
 			return 0;
-		return ~skb->priority >> 1 & 3;
+		return qeth_cut_iqd_prio(card, ~skb->priority >> 1 & 3);
 	case QETH_PRIO_Q_ING_VLAN:
 		tci = &((struct ethhdr *)skb->data)->h_proto;
 		if (*tci == ETH_P_8021Q)
-			return ~*(tci + 1) >> (VLAN_PRIO_SHIFT + 1) & 3;
+			return qeth_cut_iqd_prio(card, ~*(tci + 1) >>
+			(VLAN_PRIO_SHIFT + 1) & 3);
 		break;
 	default:
 		break;
@@ -3810,41 +3810,54 @@
 }
 EXPORT_SYMBOL_GPL(qeth_get_priority_queue);
 
+/**
+ * qeth_get_elements_for_frags() -	find number of SBALEs for skb frags.
+ * @skb:				SKB address
+ *
+ * Returns the number of pages, and thus QDIO buffer elements, needed to cover
+ * fragmented part of the SKB. Returns zero for linear SKB.
+ */
 int qeth_get_elements_for_frags(struct sk_buff *skb)
 {
-	int cnt, length, e, elements = 0;
-	struct skb_frag_struct *frag;
-	char *data;
+	int cnt, elements = 0;
 
 	for (cnt = 0; cnt < skb_shinfo(skb)->nr_frags; cnt++) {
-		frag = &skb_shinfo(skb)->frags[cnt];
-		data = (char *)page_to_phys(skb_frag_page(frag)) +
-			frag->page_offset;
-		length = frag->size;
-		e = PFN_UP((unsigned long)data + length - 1) -
-			PFN_DOWN((unsigned long)data);
-		elements += e;
+		struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[cnt];
+
+		elements += qeth_get_elements_for_range(
+			(addr_t)skb_frag_address(frag),
+			(addr_t)skb_frag_address(frag) + skb_frag_size(frag));
 	}
 	return elements;
 }
 EXPORT_SYMBOL_GPL(qeth_get_elements_for_frags);
 
+/**
+ * qeth_get_elements_no() -	find number of SBALEs for skb data, inc. frags.
+ * @card:			qeth card structure, to check max. elems.
+ * @skb:			SKB address
+ * @extra_elems:		extra elems needed, to check against max.
+ *
+ * Returns the number of pages, and thus QDIO buffer elements, needed to cover
+ * skb data, including linear part and fragments. Checks if the result plus
+ * extra_elems fits under the limit for the card. Returns 0 if it does not.
+ * Note: extra_elems is not included in the returned result.
+ */
 int qeth_get_elements_no(struct qeth_card *card,
-		     struct sk_buff *skb, int elems)
+		     struct sk_buff *skb, int extra_elems)
 {
-	int dlen = skb->len - skb->data_len;
-	int elements_needed = PFN_UP((unsigned long)skb->data + dlen - 1) -
-		PFN_DOWN((unsigned long)skb->data);
+	int elements = qeth_get_elements_for_range(
+				(addr_t)skb->data,
+				(addr_t)skb->data + skb_headlen(skb)) +
+			qeth_get_elements_for_frags(skb);
 
-	elements_needed += qeth_get_elements_for_frags(skb);
-
-	if ((elements_needed + elems) > QETH_MAX_BUFFER_ELEMENTS(card)) {
+	if ((elements + extra_elems) > QETH_MAX_BUFFER_ELEMENTS(card)) {
 		QETH_DBF_MESSAGE(2, "Invalid size of IP packet "
 			"(Number=%d / Length=%d). Discarded.\n",
-			(elements_needed+elems), skb->len);
+			elements + extra_elems, skb->len);
 		return 0;
 	}
-	return elements_needed;
+	return elements;
 }
 EXPORT_SYMBOL_GPL(qeth_get_elements_no);
 
@@ -3859,7 +3872,7 @@
 		rest = len - inpage;
 		if (rest > hroom)
 			return 1;
-		memmove(skb->data - rest, skb->data, skb->len - skb->data_len);
+		memmove(skb->data - rest, skb->data, skb_headlen(skb));
 		skb->data -= rest;
 		skb->tail -= rest;
 		*hdr = (struct qeth_hdr *)skb->data;
@@ -3873,7 +3886,7 @@
 	struct qdio_buffer *buffer, int is_tso, int *next_element_to_fill,
 	int offset)
 {
-	int length = skb->len - skb->data_len;
+	int length = skb_headlen(skb);
 	int length_here;
 	int element;
 	char *data;
@@ -4967,7 +4980,6 @@
 	qeth_clean_channel(&card->write);
 	if (card->dev)
 		free_netdev(card->dev);
-	kfree(card->ip_tbd_list);
 	qeth_free_qdio_buffers(card);
 	unregister_service_level(&card->qeth_service_level);
 	kfree(card);
@@ -5265,8 +5277,8 @@
 }
 EXPORT_SYMBOL_GPL(qeth_core_get_next_skb);
 
-static int qeth_setassparms_cb(struct qeth_card *card,
-			       struct qeth_reply *reply, unsigned long data)
+int qeth_setassparms_cb(struct qeth_card *card,
+			struct qeth_reply *reply, unsigned long data)
 {
 	struct qeth_ipa_cmd *cmd;
 
@@ -5294,6 +5306,7 @@
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(qeth_setassparms_cb);
 
 struct qeth_cmd_buffer *qeth_get_setassparms_cmd(struct qeth_card *card,
 						 enum qeth_ipa_funcs ipa_func,
@@ -5788,6 +5801,7 @@
 	{"tx do_QDIO count"},
 	{"tx csum"},
 	{"tx lin"},
+	{"tx linfail"},
 	{"cq handler count"},
 	{"cq handler time"}
 };
@@ -5848,8 +5862,9 @@
 	data[32] = card->perf_stats.outbound_do_qdio_cnt;
 	data[33] = card->perf_stats.tx_csum;
 	data[34] = card->perf_stats.tx_lin;
-	data[35] = card->perf_stats.cq_cnt;
-	data[36] = card->perf_stats.cq_time;
+	data[35] = card->perf_stats.tx_linfail;
+	data[36] = card->perf_stats.cq_cnt;
+	data[37] = card->perf_stats.cq_time;
 }
 EXPORT_SYMBOL_GPL(qeth_core_get_ethtool_stats);
 
@@ -6048,74 +6063,136 @@
 }
 EXPORT_SYMBOL_GPL(qeth_core_ethtool_get_settings);
 
-static int qeth_send_checksum_command(struct qeth_card *card)
+static int qeth_send_checksum_on(struct qeth_card *card, int cstype)
 {
+	long rxtx_arg;
 	int rc;
 
-	rc = qeth_send_simple_setassparms(card, IPA_INBOUND_CHECKSUM,
-					  IPA_CMD_ASS_START, 0);
+	rc = qeth_send_simple_setassparms(card, cstype, IPA_CMD_ASS_START, 0);
 	if (rc) {
-		dev_warn(&card->gdev->dev, "Starting HW checksumming for %s "
-			"failed, using SW checksumming\n",
-			QETH_CARD_IFNAME(card));
+		dev_warn(&card->gdev->dev,
+			 "Starting HW checksumming for %s failed, using SW checksumming\n",
+			 QETH_CARD_IFNAME(card));
 		return rc;
 	}
-	rc = qeth_send_simple_setassparms(card, IPA_INBOUND_CHECKSUM,
-					  IPA_CMD_ASS_ENABLE,
-					  card->info.csum_mask);
+	rxtx_arg = (cstype == IPA_OUTBOUND_CHECKSUM) ? card->info.tx_csum_mask
+						     : card->info.csum_mask;
+	rc = qeth_send_simple_setassparms(card, cstype, IPA_CMD_ASS_ENABLE,
+					  rxtx_arg);
 	if (rc) {
-		dev_warn(&card->gdev->dev, "Enabling HW checksumming for %s "
-			"failed, using SW checksumming\n",
-			QETH_CARD_IFNAME(card));
+		dev_warn(&card->gdev->dev,
+			 "Enabling HW checksumming for %s failed, using SW checksumming\n",
+			 QETH_CARD_IFNAME(card));
 		return rc;
 	}
+
+	dev_info(&card->gdev->dev, "HW Checksumming (%sbound) enabled\n",
+		 cstype == IPA_INBOUND_CHECKSUM ? "in" : "out");
 	return 0;
 }
 
-int qeth_set_rx_csum(struct qeth_card *card, int on)
+static int qeth_set_ipa_csum(struct qeth_card *card, int on, int cstype)
 {
 	int rc;
 
 	if (on) {
-		rc = qeth_send_checksum_command(card);
+		rc = qeth_send_checksum_on(card, cstype);
 		if (rc)
 			return -EIO;
-		dev_info(&card->gdev->dev,
-			"HW Checksumming (inbound) enabled\n");
 	} else {
-		rc = qeth_send_simple_setassparms(card,
-			IPA_INBOUND_CHECKSUM, IPA_CMD_ASS_STOP, 0);
+		rc = qeth_send_simple_setassparms(card, cstype,
+						  IPA_CMD_ASS_STOP, 0);
 		if (rc)
 			return -EIO;
 	}
 	return 0;
 }
-EXPORT_SYMBOL_GPL(qeth_set_rx_csum);
 
-int qeth_start_ipa_tx_checksum(struct qeth_card *card)
+static int qeth_set_ipa_tso(struct qeth_card *card, int on)
 {
-	int rc = 0;
+	int rc;
 
-	if (!qeth_is_supported(card, IPA_OUTBOUND_CHECKSUM))
-		return rc;
-	rc = qeth_send_simple_setassparms(card, IPA_OUTBOUND_CHECKSUM,
-					  IPA_CMD_ASS_START, 0);
-	if (rc)
-		goto err_out;
-	rc = qeth_send_simple_setassparms(card, IPA_OUTBOUND_CHECKSUM,
-					  IPA_CMD_ASS_ENABLE,
-					  card->info.tx_csum_mask);
-	if (rc)
-		goto err_out;
+	QETH_CARD_TEXT(card, 3, "sttso");
 
-	dev_info(&card->gdev->dev, "HW TX Checksumming enabled\n");
-	return rc;
-err_out:
-	dev_warn(&card->gdev->dev, "Enabling HW TX checksumming for %s "
-		"failed, using SW TX checksumming\n", QETH_CARD_IFNAME(card));
+	if (on) {
+		rc = qeth_send_simple_setassparms(card, IPA_OUTBOUND_TSO,
+						  IPA_CMD_ASS_START, 0);
+		if (rc) {
+			dev_warn(&card->gdev->dev,
+				 "Starting outbound TCP segmentation offload for %s failed\n",
+				 QETH_CARD_IFNAME(card));
+			return -EIO;
+		}
+		dev_info(&card->gdev->dev, "Outbound TSO enabled\n");
+	} else {
+		rc = qeth_send_simple_setassparms(card, IPA_OUTBOUND_TSO,
+						  IPA_CMD_ASS_STOP, 0);
+	}
 	return rc;
 }
-EXPORT_SYMBOL_GPL(qeth_start_ipa_tx_checksum);
+
+int qeth_set_features(struct net_device *dev, netdev_features_t features)
+{
+	struct qeth_card *card = dev->ml_priv;
+	netdev_features_t changed = dev->features ^ features;
+	int rc = 0;
+
+	QETH_DBF_TEXT(SETUP, 2, "setfeat");
+	QETH_DBF_HEX(SETUP, 2, &features, sizeof(features));
+
+	if ((changed & NETIF_F_IP_CSUM)) {
+		rc = qeth_set_ipa_csum(card,
+				       features & NETIF_F_IP_CSUM ? 1 : 0,
+				       IPA_OUTBOUND_CHECKSUM);
+		if (rc)
+			changed ^= NETIF_F_IP_CSUM;
+	}
+	if ((changed & NETIF_F_RXCSUM)) {
+		rc = qeth_set_ipa_csum(card,
+					features & NETIF_F_RXCSUM ? 1 : 0,
+					IPA_INBOUND_CHECKSUM);
+		if (rc)
+			changed ^= NETIF_F_RXCSUM;
+	}
+	if ((changed & NETIF_F_TSO)) {
+		rc = qeth_set_ipa_tso(card, features & NETIF_F_TSO ? 1 : 0);
+		if (rc)
+			changed ^= NETIF_F_TSO;
+	}
+
+	/* everything changed successfully? */
+	if ((dev->features ^ features) == changed)
+		return 0;
+	/* something went wrong. save changed features and return error */
+	dev->features ^= changed;
+	return -EIO;
+}
+EXPORT_SYMBOL_GPL(qeth_set_features);
+
+netdev_features_t qeth_fix_features(struct net_device *dev,
+				    netdev_features_t features)
+{
+	struct qeth_card *card = dev->ml_priv;
+
+	QETH_DBF_TEXT(SETUP, 2, "fixfeat");
+	if (!qeth_is_supported(card, IPA_OUTBOUND_CHECKSUM))
+		features &= ~NETIF_F_IP_CSUM;
+	if (!qeth_is_supported(card, IPA_INBOUND_CHECKSUM))
+		features &= ~NETIF_F_RXCSUM;
+	if (!qeth_is_supported(card, IPA_OUTBOUND_TSO)) {
+		features &= ~NETIF_F_TSO;
+		dev_info(&card->gdev->dev, "Outbound TSO not supported on %s\n",
+			 QETH_CARD_IFNAME(card));
+	}
+	/* if the card isn't up, remove features that require hw changes */
+	if (card->state == CARD_STATE_DOWN ||
+	    card->state == CARD_STATE_RECOVER)
+		features = features & ~(NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
+					NETIF_F_TSO);
+	QETH_DBF_HEX(SETUP, 2, &features, sizeof(features));
+	return features;
+}
+EXPORT_SYMBOL_GPL(qeth_fix_features);
 
 static int __init qeth_core_init(void)
 {
diff --git a/drivers/s390/net/qeth_core_sys.c b/drivers/s390/net/qeth_core_sys.c
index e6e5b96..75b29fd2 100644
--- a/drivers/s390/net/qeth_core_sys.c
+++ b/drivers/s390/net/qeth_core_sys.c
@@ -243,6 +243,10 @@
 		card->qdio.do_prio_queueing = QETH_NO_PRIO_QUEUEING;
 		card->qdio.default_out_queue = 2;
 	} else if (sysfs_streq(buf, "no_prio_queueing:3")) {
+		if (card->info.type == QETH_CARD_TYPE_IQD) {
+			rc = -EPERM;
+			goto out;
+		}
 		card->qdio.do_prio_queueing = QETH_NO_PRIO_QUEUEING;
 		card->qdio.default_out_queue = 3;
 	} else if (sysfs_streq(buf, "no_prio_queueing")) {
diff --git a/drivers/s390/net/qeth_l2.h b/drivers/s390/net/qeth_l2.h
index 0767556..29d9fb3 100644
--- a/drivers/s390/net/qeth_l2.h
+++ b/drivers/s390/net/qeth_l2.h
@@ -12,4 +12,11 @@
 void qeth_l2_remove_device_attributes(struct device *);
 void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card);
 
+struct qeth_mac {
+	u8 mac_addr[OSA_ADDR_LEN];
+	u8 is_uc:1;
+	u8 disp_flag:2;
+	struct hlist_node hnode;
+};
+
 #endif /* __QETH_L2_H__ */
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 80b1979..9fd48de 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -404,38 +404,6 @@
 	return rc;
 }
 
-static netdev_features_t qeth_l2_fix_features(struct net_device *dev,
-					      netdev_features_t features)
-{
-	struct qeth_card *card = dev->ml_priv;
-
-	QETH_DBF_TEXT(SETUP, 2, "fixfeat");
-	if (!qeth_is_supported(card, IPA_OUTBOUND_CHECKSUM))
-		features &= ~NETIF_F_IP_CSUM;
-	if (!qeth_is_supported(card, IPA_INBOUND_CHECKSUM))
-		features &= ~NETIF_F_RXCSUM;
-	QETH_DBF_HEX(SETUP, 2, &features, sizeof(features));
-	return features;
-}
-
-static int qeth_l2_set_features(struct net_device *dev,
-				netdev_features_t features)
-{
-	struct qeth_card *card = dev->ml_priv;
-	netdev_features_t changed = dev->features ^ features;
-
-	QETH_DBF_TEXT(SETUP, 2, "setfeat");
-	QETH_DBF_HEX(SETUP, 2, &features, sizeof(features));
-
-	if (card->state == CARD_STATE_DOWN ||
-	    card->state == CARD_STATE_RECOVER)
-		return 0;
-
-	if (!(changed & NETIF_F_RXCSUM))
-		return 0;
-	return qeth_set_rx_csum(card, features & NETIF_F_RXCSUM ? 1 : 0);
-}
-
 static void qeth_l2_stop_card(struct qeth_card *card, int recovery_mode)
 {
 	QETH_DBF_TEXT(SETUP , 2, "stopcard");
@@ -780,7 +748,7 @@
 			qeth_l2_mac_hash(ha->addr)) {
 		if (is_uc == mac->is_uc &&
 		    !memcmp(ha->addr, mac->mac_addr, OSA_ADDR_LEN)) {
-			mac->disp_flag = QETH_DISP_MAC_DO_NOTHING;
+			mac->disp_flag = QETH_DISP_ADDR_DO_NOTHING;
 			return;
 		}
 	}
@@ -792,7 +760,7 @@
 
 	memcpy(mac->mac_addr, ha->addr, OSA_ADDR_LEN);
 	mac->is_uc = is_uc;
-	mac->disp_flag = QETH_DISP_MAC_ADD;
+	mac->disp_flag = QETH_DISP_ADDR_ADD;
 
 	hash_add(card->mac_htable, &mac->hnode,
 			qeth_l2_mac_hash(mac->mac_addr));
@@ -825,7 +793,7 @@
 		qeth_l2_add_mac(card, ha, 1);
 
 	hash_for_each_safe(card->mac_htable, i, tmp, mac, hnode) {
-		if (mac->disp_flag == QETH_DISP_MAC_DELETE) {
+		if (mac->disp_flag == QETH_DISP_ADDR_DELETE) {
 			if (!mac->is_uc)
 				rc = qeth_l2_send_delgroupmac(card,
 						mac->mac_addr);
@@ -837,15 +805,15 @@
 			hash_del(&mac->hnode);
 			kfree(mac);
 
-		} else if (mac->disp_flag == QETH_DISP_MAC_ADD) {
+		} else if (mac->disp_flag == QETH_DISP_ADDR_ADD) {
 			rc = qeth_l2_write_mac(card, mac);
 			if (rc) {
 				hash_del(&mac->hnode);
 				kfree(mac);
 			} else
-				mac->disp_flag = QETH_DISP_MAC_DELETE;
+				mac->disp_flag = QETH_DISP_ADDR_DELETE;
 		} else
-			mac->disp_flag = QETH_DISP_MAC_DELETE;
+			mac->disp_flag = QETH_DISP_ADDR_DELETE;
 	}
 
 	spin_unlock_bh(&card->mclock);
@@ -869,6 +837,7 @@
 	int data_offset = -1;
 	int elements_needed = 0;
 	int hd_len = 0;
+	int nr_frags;
 
 	if (card->qdio.do_prio_queueing || (cast_type &&
 					card->info.is_multicast_different))
@@ -892,6 +861,23 @@
 	}
 	netif_stop_queue(dev);
 
+	/* fix hardware limitation: as long as we do not have sbal
+	 * chaining we can not send long frag lists
+	 */
+	if ((card->info.type != QETH_CARD_TYPE_IQD) &&
+	    !qeth_get_elements_no(card, new_skb, 0)) {
+		int lin_rc = skb_linearize(new_skb);
+
+		if (card->options.performance_stats) {
+			if (lin_rc)
+				card->perf_stats.tx_linfail++;
+			else
+				card->perf_stats.tx_lin++;
+		}
+		if (lin_rc)
+			goto tx_drop;
+	}
+
 	if (card->info.type == QETH_CARD_TYPE_OSN)
 		hdr = (struct qeth_hdr *)skb->data;
 	else {
@@ -943,6 +929,14 @@
 	if (!rc) {
 		card->stats.tx_packets++;
 		card->stats.tx_bytes += tx_bytes;
+		if (card->options.performance_stats) {
+			nr_frags = skb_shinfo(new_skb)->nr_frags;
+			if (nr_frags) {
+				card->perf_stats.sg_skbs_sent++;
+				/* nr_frags + skb->data */
+				card->perf_stats.sg_frags_sent += nr_frags + 1;
+			}
+		}
 		if (new_skb != skb)
 			dev_kfree_skb_any(skb);
 		rc = NETDEV_TX_OK;
@@ -1086,8 +1080,8 @@
 	.ndo_vlan_rx_add_vid	= qeth_l2_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid   = qeth_l2_vlan_rx_kill_vid,
 	.ndo_tx_timeout	   	= qeth_tx_timeout,
-	.ndo_fix_features	= qeth_l2_fix_features,
-	.ndo_set_features	= qeth_l2_set_features
+	.ndo_fix_features	= qeth_fix_features,
+	.ndo_set_features	= qeth_set_features
 };
 
 static int qeth_l2_setup_netdev(struct qeth_card *card)
@@ -1118,12 +1112,25 @@
 		&qeth_l2_ethtool_ops : &qeth_l2_osn_ops;
 	card->dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
 	if (card->info.type == QETH_CARD_TYPE_OSD && !card->info.guestlan) {
-		card->dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_RXCSUM;
-		/* Turn on RX offloading per default */
-		card->dev->features |= NETIF_F_RXCSUM;
+		card->dev->hw_features = NETIF_F_SG;
+		card->dev->vlan_features = NETIF_F_SG;
+		/* OSA 3S and earlier has no RX/TX support */
+		if (qeth_is_supported(card, IPA_OUTBOUND_CHECKSUM)) {
+			card->dev->hw_features |= NETIF_F_IP_CSUM;
+			card->dev->vlan_features |= NETIF_F_IP_CSUM;
+		}
+		if (qeth_is_supported(card, IPA_INBOUND_CHECKSUM)) {
+			card->dev->hw_features |= NETIF_F_RXCSUM;
+			card->dev->vlan_features |= NETIF_F_RXCSUM;
+		}
+		/* Turn on SG per default */
+		card->dev->features |= NETIF_F_SG;
 	}
 	card->info.broadcast_capable = 1;
 	qeth_l2_request_initial_mac(card);
+	card->dev->gso_max_size = (QETH_MAX_BUFFER_ELEMENTS(card) - 1) *
+				  PAGE_SIZE;
+	card->dev->gso_max_segs = (QETH_MAX_BUFFER_ELEMENTS(card) - 1);
 	SET_NETDEV_DEV(card->dev, &card->gdev->dev);
 	netif_napi_add(card->dev, &card->napi, qeth_l2_poll, QETH_NAPI_WEIGHT);
 	netif_carrier_off(card->dev);
@@ -1135,9 +1142,6 @@
 	/* configure isolation level */
 	if (qeth_set_access_ctrl_online(card, 0))
 		return -ENODEV;
-	if (qeth_is_supported(card, IPA_INBOUND_CHECKSUM))
-		qeth_set_rx_csum(card, 1);
-	qeth_start_ipa_tx_checksum(card);
 	return 0;
 }
 
@@ -1206,7 +1210,8 @@
 contin:
 	if ((card->info.type == QETH_CARD_TYPE_OSD) ||
 	    (card->info.type == QETH_CARD_TYPE_OSX)) {
-		if (qeth_l2_start_ipassists(card))
+		rc = qeth_l2_start_ipassists(card);
+		if (rc)
 			goto out_remove;
 	}
 
@@ -1800,6 +1805,12 @@
 			dev_err(&card->gdev->dev,
 	"The device is not configured as a Bridge Port\n");
 			break;
+		case 0x2B10:
+		case 0x0010: /* OS mismatch */
+			rc = -EPERM;
+			dev_err(&card->gdev->dev,
+	"A Bridge Port is already configured by a different operating system\n");
+			break;
 		case 0x2B14:
 		case 0x0014: /* Another device is Primary */
 			switch (setcmd) {
diff --git a/drivers/s390/net/qeth_l3.h b/drivers/s390/net/qeth_l3.h
index 551a4b4..26f7953 100644
--- a/drivers/s390/net/qeth_l3.h
+++ b/drivers/s390/net/qeth_l3.h
@@ -10,16 +10,23 @@
 #define __QETH_L3_H__
 
 #include "qeth_core.h"
+#include <linux/hashtable.h>
 
 #define QETH_SNIFF_AVAIL	0x0008
 
 struct qeth_ipaddr {
-	struct list_head entry;
+	struct hlist_node hnode;
 	enum qeth_ip_types type;
 	enum qeth_ipa_setdelip_flags set_flags;
 	enum qeth_ipa_setdelip_flags del_flags;
-	int is_multicast;
-	int users;
+	u8 is_multicast:1;
+	u8 in_progress:1;
+	u8 disp_flag:2;
+
+	/* is changed only for normal ip addresses
+	 * for non-normal addresses it always is  1
+	 */
+	int  ref_counter;
 	enum qeth_prot_versions proto;
 	unsigned char mac[OSA_ADDR_LEN];
 	union {
@@ -32,7 +39,24 @@
 			unsigned int pfxlen;
 		} a6;
 	} u;
+
 };
+static inline  u64 qeth_l3_ipaddr_hash(struct qeth_ipaddr *addr)
+{
+	u64  ret = 0;
+	u8 *point;
+
+	if (addr->proto == QETH_PROT_IPV6) {
+		point = (u8 *) &addr->u.a6.addr;
+		ret = get_unaligned((u64 *)point) ^
+			get_unaligned((u64 *) (point + 8));
+	}
+	if (addr->proto == QETH_PROT_IPV4) {
+		point = (u8 *) &addr->u.a4.addr;
+		ret = get_unaligned((u32 *) point);
+	}
+	return ret;
+}
 
 struct qeth_ipato_entry {
 	struct list_head entry;
@@ -60,6 +84,5 @@
 struct qeth_ipaddr *qeth_l3_get_addr_buffer(enum qeth_prot_versions);
 int qeth_l3_add_ip(struct qeth_card *, struct qeth_ipaddr *);
 int qeth_l3_delete_ip(struct qeth_card *, struct qeth_ipaddr *);
-void qeth_l3_set_ip_addr_list(struct qeth_card *);
 
 #endif /* __QETH_L3_H__ */
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index ac54433..bcd324e 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -30,6 +30,7 @@
 #include <net/ip6_fib.h>
 #include <net/ip6_checksum.h>
 #include <net/iucv/af_iucv.h>
+#include <linux/hashtable.h>
 
 #include "qeth_l3.h"
 
@@ -57,7 +58,7 @@
 
 static void qeth_l3_ipaddr4_to_string(const __u8 *addr, char *buf)
 {
-	sprintf(buf, "%i.%i.%i.%i", addr[0], addr[1], addr[2], addr[3]);
+	sprintf(buf, "%pI4", addr);
 }
 
 static int qeth_l3_string_to_ipaddr4(const char *buf, __u8 *addr)
@@ -204,104 +205,129 @@
 	return rc;
 }
 
-/*
- * Add IP to be added to todo list. If there is already an "add todo"
- * in this list we just incremenent the reference count.
- * Returns 0 if we  just incremented reference count.
- */
-static int __qeth_l3_insert_ip_todo(struct qeth_card *card,
-					struct qeth_ipaddr *addr, int add)
+inline int
+qeth_l3_ipaddrs_is_equal(struct qeth_ipaddr *addr1, struct qeth_ipaddr *addr2)
 {
-	struct qeth_ipaddr *tmp, *t;
-	int found = 0;
-
-	if (card->options.sniffer)
-		return 0;
-	list_for_each_entry_safe(tmp, t, card->ip_tbd_list, entry) {
-		if ((addr->type == QETH_IP_TYPE_DEL_ALL_MC) &&
-		    (tmp->type == QETH_IP_TYPE_DEL_ALL_MC))
-			return 0;
-		if ((tmp->proto        == QETH_PROT_IPV4)     &&
-		    (addr->proto       == QETH_PROT_IPV4)     &&
-		    (tmp->type         == addr->type)         &&
-		    (tmp->is_multicast == addr->is_multicast) &&
-		    (tmp->u.a4.addr    == addr->u.a4.addr)    &&
-		    (tmp->u.a4.mask    == addr->u.a4.mask)) {
-			found = 1;
-			break;
-		}
-		if ((tmp->proto        == QETH_PROT_IPV6)      &&
-		    (addr->proto       == QETH_PROT_IPV6)      &&
-		    (tmp->type         == addr->type)          &&
-		    (tmp->is_multicast == addr->is_multicast)  &&
-		    (tmp->u.a6.pfxlen  == addr->u.a6.pfxlen)   &&
-		    (memcmp(&tmp->u.a6.addr, &addr->u.a6.addr,
-			    sizeof(struct in6_addr)) == 0)) {
-			found = 1;
-			break;
-		}
-	}
-	if (found) {
-		if (addr->users != 0)
-			tmp->users += addr->users;
-		else
-			tmp->users += add ? 1 : -1;
-		if (tmp->users == 0) {
-			list_del(&tmp->entry);
-			kfree(tmp);
-		}
-		return 0;
-	} else {
-		if (addr->type == QETH_IP_TYPE_DEL_ALL_MC)
-			list_add(&addr->entry, card->ip_tbd_list);
-		else {
-			if (addr->users == 0)
-				addr->users += add ? 1 : -1;
-			if (add && (addr->type == QETH_IP_TYPE_NORMAL) &&
-			    qeth_l3_is_addr_covered_by_ipato(card, addr)) {
-				QETH_CARD_TEXT(card, 2, "tkovaddr");
-				addr->set_flags |= QETH_IPA_SETIP_TAKEOVER_FLAG;
-			}
-			list_add_tail(&addr->entry, card->ip_tbd_list);
-		}
-		return 1;
-	}
+	return addr1->proto == addr2->proto &&
+		!memcmp(&addr1->u, &addr2->u, sizeof(addr1->u))  &&
+		!memcmp(&addr1->mac, &addr2->mac, sizeof(addr1->mac));
 }
 
-int qeth_l3_delete_ip(struct qeth_card *card, struct qeth_ipaddr *addr)
+static struct qeth_ipaddr *
+qeth_l3_ip_from_hash(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
 {
-	unsigned long flags;
+	struct qeth_ipaddr *addr;
+
+	if (tmp_addr->is_multicast) {
+		hash_for_each_possible(card->ip_mc_htable,  addr,
+				hnode, qeth_l3_ipaddr_hash(tmp_addr))
+			if (qeth_l3_ipaddrs_is_equal(tmp_addr, addr))
+				return addr;
+	} else {
+		hash_for_each_possible(card->ip_htable,  addr,
+				hnode, qeth_l3_ipaddr_hash(tmp_addr))
+			if (qeth_l3_ipaddrs_is_equal(tmp_addr, addr))
+				return addr;
+	}
+
+	return NULL;
+}
+
+int qeth_l3_delete_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
+{
 	int rc = 0;
+	struct qeth_ipaddr *addr;
 
 	QETH_CARD_TEXT(card, 4, "delip");
 
-	if (addr->proto == QETH_PROT_IPV4)
-		QETH_CARD_HEX(card, 4, &addr->u.a4.addr, 4);
+	if (tmp_addr->proto == QETH_PROT_IPV4)
+		QETH_CARD_HEX(card, 4, &tmp_addr->u.a4.addr, 4);
 	else {
-		QETH_CARD_HEX(card, 4, &addr->u.a6.addr, 8);
-		QETH_CARD_HEX(card, 4, ((char *)&addr->u.a6.addr) + 8, 8);
+		QETH_CARD_HEX(card, 4, &tmp_addr->u.a6.addr, 8);
+		QETH_CARD_HEX(card, 4, ((char *)&tmp_addr->u.a6.addr) + 8, 8);
 	}
-	spin_lock_irqsave(&card->ip_lock, flags);
-	rc = __qeth_l3_insert_ip_todo(card, addr, 0);
-	spin_unlock_irqrestore(&card->ip_lock, flags);
+
+	addr = qeth_l3_ip_from_hash(card, tmp_addr);
+	if (!addr)
+		return -ENOENT;
+
+	addr->ref_counter--;
+	if (addr->type == QETH_IP_TYPE_NORMAL && addr->ref_counter > 0)
+		return rc;
+	if (addr->in_progress)
+		return -EINPROGRESS;
+
+	rc = qeth_l3_deregister_addr_entry(card, addr);
+
+	hash_del(&addr->hnode);
+	kfree(addr);
+
 	return rc;
 }
 
-int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *addr)
+int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
 {
-	unsigned long flags;
 	int rc = 0;
+	struct qeth_ipaddr *addr;
 
 	QETH_CARD_TEXT(card, 4, "addip");
-	if (addr->proto == QETH_PROT_IPV4)
-		QETH_CARD_HEX(card, 4, &addr->u.a4.addr, 4);
+
+	if (tmp_addr->proto == QETH_PROT_IPV4)
+		QETH_CARD_HEX(card, 4, &tmp_addr->u.a4.addr, 4);
 	else {
-		QETH_CARD_HEX(card, 4, &addr->u.a6.addr, 8);
-		QETH_CARD_HEX(card, 4, ((char *)&addr->u.a6.addr) + 8, 8);
+		QETH_CARD_HEX(card, 4, &tmp_addr->u.a6.addr, 8);
+		QETH_CARD_HEX(card, 4, ((char *)&tmp_addr->u.a6.addr) + 8, 8);
 	}
-	spin_lock_irqsave(&card->ip_lock, flags);
-	rc = __qeth_l3_insert_ip_todo(card, addr, 1);
-	spin_unlock_irqrestore(&card->ip_lock, flags);
+
+	addr = qeth_l3_ip_from_hash(card, tmp_addr);
+	if (!addr) {
+		addr = qeth_l3_get_addr_buffer(tmp_addr->proto);
+		if (!addr)
+			return -ENOMEM;
+
+		memcpy(addr, tmp_addr, sizeof(struct qeth_ipaddr));
+		addr->ref_counter = 1;
+
+		if (addr->type == QETH_IP_TYPE_NORMAL  &&
+				qeth_l3_is_addr_covered_by_ipato(card, addr)) {
+			QETH_CARD_TEXT(card, 2, "tkovaddr");
+			addr->set_flags |= QETH_IPA_SETIP_TAKEOVER_FLAG;
+		}
+		hash_add(card->ip_htable, &addr->hnode,
+				qeth_l3_ipaddr_hash(addr));
+
+		/* qeth_l3_register_addr_entry can go to sleep
+		 * if we add a IPV4 addr. It is caused by the reason
+		 * that SETIP ipa cmd starts ARP staff for IPV4 addr.
+		 * Thus we should unlock spinlock, and make a protection
+		 * using in_progress variable to indicate that there is
+		 * an hardware operation with this IPV4 address
+		 */
+		if (addr->proto == QETH_PROT_IPV4) {
+			addr->in_progress = 1;
+			spin_unlock_bh(&card->ip_lock);
+			rc = qeth_l3_register_addr_entry(card, addr);
+			spin_lock_bh(&card->ip_lock);
+			addr->in_progress = 0;
+		} else
+			rc = qeth_l3_register_addr_entry(card, addr);
+
+		if (!rc || (rc == IPA_RC_DUPLICATE_IP_ADDRESS) ||
+				(rc == IPA_RC_LAN_OFFLINE)) {
+			addr->disp_flag = QETH_DISP_ADDR_DO_NOTHING;
+			if (addr->ref_counter < 1) {
+				qeth_l3_delete_ip(card, addr);
+				kfree(addr);
+			}
+		} else {
+			hash_del(&addr->hnode);
+			kfree(addr);
+		}
+	} else {
+			if (addr->type == QETH_IP_TYPE_NORMAL)
+				addr->ref_counter++;
+	}
+
 	return rc;
 }
 
@@ -312,229 +338,88 @@
 	struct qeth_ipaddr *addr;
 
 	addr = kzalloc(sizeof(struct qeth_ipaddr), GFP_ATOMIC);
-	if (addr == NULL) {
+	if (!addr)
 		return NULL;
-	}
+
 	addr->type = QETH_IP_TYPE_NORMAL;
+	addr->disp_flag = QETH_DISP_ADDR_DO_NOTHING;
 	addr->proto = prot;
+
 	return addr;
 }
 
-static void qeth_l3_delete_mc_addresses(struct qeth_card *card)
-{
-	struct qeth_ipaddr *iptodo;
-	unsigned long flags;
-
-	QETH_CARD_TEXT(card, 4, "delmc");
-	iptodo = qeth_l3_get_addr_buffer(QETH_PROT_IPV4);
-	if (!iptodo) {
-		QETH_CARD_TEXT(card, 2, "dmcnomem");
-		return;
-	}
-	iptodo->type = QETH_IP_TYPE_DEL_ALL_MC;
-	spin_lock_irqsave(&card->ip_lock, flags);
-	if (!__qeth_l3_insert_ip_todo(card, iptodo, 0))
-		kfree(iptodo);
-	spin_unlock_irqrestore(&card->ip_lock, flags);
-}
-
-/*
- * Add/remove address to/from card's ip list, i.e. try to add or remove
- * reference to/from an IP address that is already registered on the card.
- * Returns:
- *	0  address was on card and its reference count has been adjusted,
- *	   but is still > 0, so nothing has to be done
- *	   also returns 0 if card was not on card and the todo was to delete
- *	   the address -> there is also nothing to be done
- *	1  address was not on card and the todo is to add it to the card's ip
- *	   list
- *	-1 address was on card and its reference count has been decremented
- *	   to <= 0 by the todo -> address must be removed from card
- */
-static int __qeth_l3_ref_ip_on_card(struct qeth_card *card,
-		struct qeth_ipaddr *todo, struct qeth_ipaddr **__addr)
+static void qeth_l3_clear_ip_htable(struct qeth_card *card, int recover)
 {
 	struct qeth_ipaddr *addr;
-	int found = 0;
-
-	list_for_each_entry(addr, &card->ip_list, entry) {
-		if ((addr->proto == QETH_PROT_IPV4) &&
-		    (todo->proto == QETH_PROT_IPV4) &&
-		    (addr->type == todo->type) &&
-		    (addr->u.a4.addr == todo->u.a4.addr) &&
-		    (addr->u.a4.mask == todo->u.a4.mask)) {
-			found = 1;
-			break;
-		}
-		if ((addr->proto == QETH_PROT_IPV6) &&
-		    (todo->proto == QETH_PROT_IPV6) &&
-		    (addr->type == todo->type) &&
-		    (addr->u.a6.pfxlen == todo->u.a6.pfxlen) &&
-		    (memcmp(&addr->u.a6.addr, &todo->u.a6.addr,
-			    sizeof(struct in6_addr)) == 0)) {
-			found = 1;
-			break;
-		}
-	}
-	if (found) {
-		addr->users += todo->users;
-		if (addr->users <= 0) {
-			*__addr = addr;
-			return -1;
-		} else {
-			/* for VIPA and RXIP limit refcount to 1 */
-			if (addr->type != QETH_IP_TYPE_NORMAL)
-				addr->users = 1;
-			return 0;
-		}
-	}
-	if (todo->users > 0) {
-		/* for VIPA and RXIP limit refcount to 1 */
-		if (todo->type != QETH_IP_TYPE_NORMAL)
-			todo->users = 1;
-		return 1;
-	} else
-		return 0;
-}
-
-static void __qeth_l3_delete_all_mc(struct qeth_card *card,
-					unsigned long *flags)
-{
-	struct list_head fail_list;
-	struct qeth_ipaddr *addr, *tmp;
-	int rc;
-
-	INIT_LIST_HEAD(&fail_list);
-again:
-	list_for_each_entry_safe(addr, tmp, &card->ip_list, entry) {
-		if (addr->is_multicast) {
-			list_del(&addr->entry);
-			spin_unlock_irqrestore(&card->ip_lock, *flags);
-			rc = qeth_l3_deregister_addr_entry(card, addr);
-			spin_lock_irqsave(&card->ip_lock, *flags);
-			if (!rc || (rc == IPA_RC_MC_ADDR_NOT_FOUND))
-				kfree(addr);
-			else
-				list_add_tail(&addr->entry, &fail_list);
-			goto again;
-		}
-	}
-	list_splice(&fail_list, &card->ip_list);
-}
-
-void qeth_l3_set_ip_addr_list(struct qeth_card *card)
-{
-	struct list_head *tbd_list;
-	struct qeth_ipaddr *todo, *addr;
-	unsigned long flags;
-	int rc;
-
-	QETH_CARD_TEXT(card, 2, "sdiplist");
-	QETH_CARD_HEX(card, 2, &card, sizeof(void *));
-
-	if (!qeth_card_hw_is_reachable(card) || card->options.sniffer)
-		return;
-
-	spin_lock_irqsave(&card->ip_lock, flags);
-	tbd_list = card->ip_tbd_list;
-	card->ip_tbd_list = kzalloc(sizeof(struct list_head), GFP_ATOMIC);
-	if (!card->ip_tbd_list) {
-		QETH_CARD_TEXT(card, 0, "silnomem");
-		card->ip_tbd_list = tbd_list;
-		spin_unlock_irqrestore(&card->ip_lock, flags);
-		return;
-	} else
-		INIT_LIST_HEAD(card->ip_tbd_list);
-
-	while (!list_empty(tbd_list)) {
-		todo = list_entry(tbd_list->next, struct qeth_ipaddr, entry);
-		list_del(&todo->entry);
-		if (todo->type == QETH_IP_TYPE_DEL_ALL_MC) {
-			__qeth_l3_delete_all_mc(card, &flags);
-			kfree(todo);
-			continue;
-		}
-		rc = __qeth_l3_ref_ip_on_card(card, todo, &addr);
-		if (rc == 0) {
-			/* nothing to be done; only adjusted refcount */
-			kfree(todo);
-		} else if (rc == 1) {
-			/* new entry to be added to on-card list */
-			spin_unlock_irqrestore(&card->ip_lock, flags);
-			rc = qeth_l3_register_addr_entry(card, todo);
-			spin_lock_irqsave(&card->ip_lock, flags);
-			if (!rc || (rc == IPA_RC_LAN_OFFLINE))
-				list_add_tail(&todo->entry, &card->ip_list);
-			else
-				kfree(todo);
-		} else if (rc == -1) {
-			/* on-card entry to be removed */
-			list_del_init(&addr->entry);
-			spin_unlock_irqrestore(&card->ip_lock, flags);
-			rc = qeth_l3_deregister_addr_entry(card, addr);
-			spin_lock_irqsave(&card->ip_lock, flags);
-			if (!rc || (rc == IPA_RC_IP_ADDRESS_NOT_DEFINED))
-				kfree(addr);
-			else
-				list_add_tail(&addr->entry, &card->ip_list);
-			kfree(todo);
-		}
-	}
-	spin_unlock_irqrestore(&card->ip_lock, flags);
-	kfree(tbd_list);
-}
-
-static void qeth_l3_clear_ip_list(struct qeth_card *card, int recover)
-{
-	struct qeth_ipaddr *addr, *tmp;
-	unsigned long flags;
+	struct hlist_node *tmp;
+	int i;
 
 	QETH_CARD_TEXT(card, 4, "clearip");
+
 	if (recover && card->options.sniffer)
 		return;
-	spin_lock_irqsave(&card->ip_lock, flags);
-	/* clear todo list */
-	list_for_each_entry_safe(addr, tmp, card->ip_tbd_list, entry) {
-		list_del(&addr->entry);
-		kfree(addr);
-	}
 
-	while (!list_empty(&card->ip_list)) {
-		addr = list_entry(card->ip_list.next,
-				  struct qeth_ipaddr, entry);
-		list_del_init(&addr->entry);
-		if (!recover || addr->is_multicast) {
+	spin_lock_bh(&card->ip_lock);
+
+	hash_for_each_safe(card->ip_htable, i, tmp, addr, hnode) {
+		if (!recover) {
+			hash_del(&addr->hnode);
 			kfree(addr);
 			continue;
 		}
-		list_add_tail(&addr->entry, card->ip_tbd_list);
+		addr->disp_flag = QETH_DISP_ADDR_ADD;
 	}
-	spin_unlock_irqrestore(&card->ip_lock, flags);
+
+	spin_unlock_bh(&card->ip_lock);
+
+	spin_lock_bh(&card->mclock);
+
+	hash_for_each_safe(card->ip_mc_htable, i, tmp, addr, hnode) {
+		hash_del(&addr->hnode);
+		kfree(addr);
+	}
+
+	spin_unlock_bh(&card->mclock);
+
+
 }
-
-static int qeth_l3_address_exists_in_list(struct list_head *list,
-		struct qeth_ipaddr *addr, int same_type)
+static void qeth_l3_recover_ip(struct qeth_card *card)
 {
-	struct qeth_ipaddr *tmp;
+	struct qeth_ipaddr *addr;
+	struct hlist_node *tmp;
+	int i;
+	int rc;
 
-	list_for_each_entry(tmp, list, entry) {
-		if ((tmp->proto == QETH_PROT_IPV4) &&
-		    (addr->proto == QETH_PROT_IPV4) &&
-		    ((same_type && (tmp->type == addr->type)) ||
-		    (!same_type && (tmp->type != addr->type))) &&
-		    (tmp->u.a4.addr == addr->u.a4.addr))
-			return 1;
+	QETH_CARD_TEXT(card, 4, "recoverip");
 
-		if ((tmp->proto == QETH_PROT_IPV6) &&
-		    (addr->proto == QETH_PROT_IPV6) &&
-		    ((same_type && (tmp->type == addr->type)) ||
-		    (!same_type && (tmp->type != addr->type))) &&
-		    (memcmp(&tmp->u.a6.addr, &addr->u.a6.addr,
-			    sizeof(struct in6_addr)) == 0))
-			return 1;
+	spin_lock_bh(&card->ip_lock);
 
+	hash_for_each_safe(card->ip_htable, i, tmp, addr, hnode) {
+		if (addr->disp_flag == QETH_DISP_ADDR_ADD) {
+			if (addr->proto == QETH_PROT_IPV4) {
+				addr->in_progress = 1;
+				spin_unlock_bh(&card->ip_lock);
+				rc = qeth_l3_register_addr_entry(card, addr);
+				spin_lock_bh(&card->ip_lock);
+				addr->in_progress = 0;
+			} else
+				rc = qeth_l3_register_addr_entry(card, addr);
+
+			if (!rc) {
+				addr->disp_flag = QETH_DISP_ADDR_DO_NOTHING;
+				if (addr->ref_counter < 1) {
+					qeth_l3_delete_ip(card, addr);
+					kfree(addr);
+				}
+			} else {
+				hash_del(&addr->hnode);
+				kfree(addr);
+			}
+		}
 	}
-	return 0;
+
+	spin_unlock_bh(&card->ip_lock);
+
 }
 
 static int qeth_l3_send_setdelmc(struct qeth_card *card,
@@ -712,27 +597,28 @@
  */
 static void qeth_l3_clear_ipato_list(struct qeth_card *card)
 {
-
 	struct qeth_ipato_entry *ipatoe, *tmp;
-	unsigned long flags;
 
-	spin_lock_irqsave(&card->ip_lock, flags);
+	spin_lock_bh(&card->ip_lock);
+
 	list_for_each_entry_safe(ipatoe, tmp, &card->ipato.entries, entry) {
 		list_del(&ipatoe->entry);
 		kfree(ipatoe);
 	}
-	spin_unlock_irqrestore(&card->ip_lock, flags);
+
+	spin_unlock_bh(&card->ip_lock);
 }
 
 int qeth_l3_add_ipato_entry(struct qeth_card *card,
 				struct qeth_ipato_entry *new)
 {
 	struct qeth_ipato_entry *ipatoe;
-	unsigned long flags;
 	int rc = 0;
 
 	QETH_CARD_TEXT(card, 2, "addipato");
-	spin_lock_irqsave(&card->ip_lock, flags);
+
+	spin_lock_bh(&card->ip_lock);
+
 	list_for_each_entry(ipatoe, &card->ipato.entries, entry) {
 		if (ipatoe->proto != new->proto)
 			continue;
@@ -743,10 +629,12 @@
 			break;
 		}
 	}
+
 	if (!rc)
 		list_add_tail(&new->entry, &card->ipato.entries);
 
-	spin_unlock_irqrestore(&card->ip_lock, flags);
+	spin_unlock_bh(&card->ip_lock);
+
 	return rc;
 }
 
@@ -754,10 +642,11 @@
 		enum qeth_prot_versions proto, u8 *addr, int mask_bits)
 {
 	struct qeth_ipato_entry *ipatoe, *tmp;
-	unsigned long flags;
 
 	QETH_CARD_TEXT(card, 2, "delipato");
-	spin_lock_irqsave(&card->ip_lock, flags);
+
+	spin_lock_bh(&card->ip_lock);
+
 	list_for_each_entry_safe(ipatoe, tmp, &card->ipato.entries, entry) {
 		if (ipatoe->proto != proto)
 			continue;
@@ -768,7 +657,8 @@
 			kfree(ipatoe);
 		}
 	}
-	spin_unlock_irqrestore(&card->ip_lock, flags);
+
+	spin_unlock_bh(&card->ip_lock);
 }
 
 /*
@@ -778,7 +668,6 @@
 	      const u8 *addr)
 {
 	struct qeth_ipaddr *ipaddr;
-	unsigned long flags;
 	int rc = 0;
 
 	ipaddr = qeth_l3_get_addr_buffer(proto);
@@ -797,18 +686,18 @@
 		ipaddr->del_flags = QETH_IPA_DELIP_VIPA_FLAG;
 	} else
 		return -ENOMEM;
-	spin_lock_irqsave(&card->ip_lock, flags);
-	if (qeth_l3_address_exists_in_list(&card->ip_list, ipaddr, 0) ||
-	    qeth_l3_address_exists_in_list(card->ip_tbd_list, ipaddr, 0))
+
+	spin_lock_bh(&card->ip_lock);
+
+	if (!qeth_l3_ip_from_hash(card, ipaddr))
 		rc = -EEXIST;
-	spin_unlock_irqrestore(&card->ip_lock, flags);
-	if (rc) {
-		kfree(ipaddr);
-		return rc;
-	}
-	if (!qeth_l3_add_ip(card, ipaddr))
-		kfree(ipaddr);
-	qeth_l3_set_ip_addr_list(card);
+	else
+		qeth_l3_add_ip(card, ipaddr);
+
+	spin_unlock_bh(&card->ip_lock);
+
+	kfree(ipaddr);
+
 	return rc;
 }
 
@@ -831,9 +720,12 @@
 		ipaddr->type = QETH_IP_TYPE_VIPA;
 	} else
 		return;
-	if (!qeth_l3_delete_ip(card, ipaddr))
-		kfree(ipaddr);
-	qeth_l3_set_ip_addr_list(card);
+
+	spin_lock_bh(&card->ip_lock);
+	qeth_l3_delete_ip(card, ipaddr);
+	spin_unlock_bh(&card->ip_lock);
+
+	kfree(ipaddr);
 }
 
 /*
@@ -843,7 +735,6 @@
 	      const u8 *addr)
 {
 	struct qeth_ipaddr *ipaddr;
-	unsigned long flags;
 	int rc = 0;
 
 	ipaddr = qeth_l3_get_addr_buffer(proto);
@@ -857,24 +748,25 @@
 			memcpy(&ipaddr->u.a6.addr, addr, 16);
 			ipaddr->u.a6.pfxlen = 0;
 		}
+
 		ipaddr->type = QETH_IP_TYPE_RXIP;
 		ipaddr->set_flags = QETH_IPA_SETIP_TAKEOVER_FLAG;
 		ipaddr->del_flags = 0;
 	} else
 		return -ENOMEM;
-	spin_lock_irqsave(&card->ip_lock, flags);
-	if (qeth_l3_address_exists_in_list(&card->ip_list, ipaddr, 0) ||
-	    qeth_l3_address_exists_in_list(card->ip_tbd_list, ipaddr, 0))
+
+	spin_lock_bh(&card->ip_lock);
+
+	if (!qeth_l3_ip_from_hash(card, ipaddr))
 		rc = -EEXIST;
-	spin_unlock_irqrestore(&card->ip_lock, flags);
-	if (rc) {
-		kfree(ipaddr);
-		return rc;
-	}
-	if (!qeth_l3_add_ip(card, ipaddr))
-		kfree(ipaddr);
-	qeth_l3_set_ip_addr_list(card);
-	return 0;
+	else
+		qeth_l3_add_ip(card, ipaddr);
+
+	spin_unlock_bh(&card->ip_lock);
+
+	kfree(ipaddr);
+
+	return rc;
 }
 
 void qeth_l3_del_rxip(struct qeth_card *card, enum qeth_prot_versions proto,
@@ -896,9 +788,12 @@
 		ipaddr->type = QETH_IP_TYPE_RXIP;
 	} else
 		return;
-	if (!qeth_l3_delete_ip(card, ipaddr))
-		kfree(ipaddr);
-	qeth_l3_set_ip_addr_list(card);
+
+	spin_lock_bh(&card->ip_lock);
+	qeth_l3_delete_ip(card, ipaddr);
+	spin_unlock_bh(&card->ip_lock);
+
+	kfree(ipaddr);
 }
 
 static int qeth_l3_register_addr_entry(struct qeth_card *card,
@@ -908,6 +803,7 @@
 	int rc = 0;
 	int cnt = 3;
 
+
 	if (addr->proto == QETH_PROT_IPV4) {
 		QETH_CARD_TEXT(card, 2, "setaddr4");
 		QETH_CARD_HEX(card, 3, &addr->u.a4.addr, sizeof(int));
@@ -1013,36 +909,6 @@
 	return rc;
 }
 
-static int qeth_l3_default_setassparms_cb(struct qeth_card *card,
-			struct qeth_reply *reply, unsigned long data)
-{
-	struct qeth_ipa_cmd *cmd;
-
-	QETH_CARD_TEXT(card, 4, "defadpcb");
-
-	cmd = (struct qeth_ipa_cmd *) data;
-	if (cmd->hdr.return_code == 0) {
-		cmd->hdr.return_code = cmd->data.setassparms.hdr.return_code;
-		if (cmd->hdr.prot_version == QETH_PROT_IPV4)
-			card->options.ipa4.enabled_funcs = cmd->hdr.ipa_enabled;
-		if (cmd->hdr.prot_version == QETH_PROT_IPV6)
-			card->options.ipa6.enabled_funcs = cmd->hdr.ipa_enabled;
-	}
-	if (cmd->data.setassparms.hdr.assist_no == IPA_INBOUND_CHECKSUM &&
-	    cmd->data.setassparms.hdr.command_code == IPA_CMD_ASS_START) {
-		card->info.csum_mask = cmd->data.setassparms.data.flags_32bit;
-		QETH_CARD_TEXT_(card, 3, "csum:%d", card->info.csum_mask);
-	}
-	if (cmd->data.setassparms.hdr.assist_no == IPA_OUTBOUND_CHECKSUM &&
-	    cmd->data.setassparms.hdr.command_code == IPA_CMD_ASS_START) {
-		card->info.tx_csum_mask =
-			cmd->data.setassparms.data.flags_32bit;
-		QETH_CARD_TEXT_(card, 3, "tcsu:%d", card->info.tx_csum_mask);
-	}
-
-	return 0;
-}
-
 #ifdef CONFIG_QETH_IPV6
 static int qeth_l3_send_simple_setassparms_ipv6(struct qeth_card *card,
 		enum qeth_ipa_funcs ipa_func, __u16 cmd_code)
@@ -1056,7 +922,7 @@
 	if (!iob)
 		return -ENOMEM;
 	rc = qeth_send_setassparms(card, iob, 0, 0,
-				   qeth_l3_default_setassparms_cb, NULL);
+				   qeth_setassparms_cb, NULL);
 	return rc;
 }
 #endif
@@ -1291,47 +1157,6 @@
 	return rc;
 }
 
-static void qeth_l3_start_ipa_checksum(struct qeth_card *card)
-{
-	QETH_CARD_TEXT(card, 3, "strtcsum");
-	if (qeth_is_supported(card, IPA_INBOUND_CHECKSUM)
-	    && (card->dev->features & NETIF_F_RXCSUM))
-		qeth_set_rx_csum(card, 1);
-}
-
-static void qeth_l3_start_ipa_tx_checksum(struct qeth_card *card)
-{
-	QETH_CARD_TEXT(card, 3, "strttxcs");
-	qeth_start_ipa_tx_checksum(card);
-}
-
-static int qeth_l3_start_ipa_tso(struct qeth_card *card)
-{
-	int rc;
-
-	QETH_CARD_TEXT(card, 3, "sttso");
-
-	if (!qeth_is_supported(card, IPA_OUTBOUND_TSO)) {
-		dev_info(&card->gdev->dev,
-			"Outbound TSO not supported on %s\n",
-			QETH_CARD_IFNAME(card));
-		rc = -EOPNOTSUPP;
-	} else {
-		rc = qeth_send_simple_setassparms(card, IPA_OUTBOUND_TSO,
-						  IPA_CMD_ASS_START, 0);
-		if (rc)
-			dev_warn(&card->gdev->dev, "Starting outbound TCP "
-				"segmentation offload for %s failed\n",
-				QETH_CARD_IFNAME(card));
-		else
-			dev_info(&card->gdev->dev,
-				"Outbound TSO enabled\n");
-	}
-	if (rc)
-		card->dev->features &= ~NETIF_F_TSO;
-	return rc;
-}
-
 static int qeth_l3_start_ipassists(struct qeth_card *card)
 {
 	QETH_CARD_TEXT(card, 3, "strtipas");
@@ -1345,9 +1170,6 @@
 	qeth_l3_start_ipa_multicast(card);		/* go on*/
 	qeth_l3_start_ipa_ipv6(card);		/* go on*/
 	qeth_l3_start_ipa_broadcast(card);		/* go on*/
-	qeth_l3_start_ipa_checksum(card);		/* go on*/
-	qeth_l3_start_ipa_tx_checksum(card);
-	qeth_l3_start_ipa_tso(card);		/* go on*/
 	return 0;
 }
 
@@ -1507,31 +1329,99 @@
 	return qeth_send_ipa_cmd(card, iob, qeth_diags_trace_cb, NULL);
 }
 
-static void qeth_l3_get_mac_for_ipm(__u32 ipm, char *mac,
-				struct net_device *dev)
+static void qeth_l3_get_mac_for_ipm(__u32 ipm, char *mac)
 {
 	ip_eth_mc_map(ipm, mac);
 }
 
-static void qeth_l3_add_mc(struct qeth_card *card, struct in_device *in4_dev)
+static void qeth_l3_mark_all_mc_to_be_deleted(struct qeth_card *card)
 {
-	struct qeth_ipaddr *ipm;
+	struct qeth_ipaddr *addr;
+	int i;
+
+	hash_for_each(card->ip_mc_htable, i, addr, hnode)
+		addr->disp_flag = QETH_DISP_ADDR_DELETE;
+
+}
+
+static void qeth_l3_add_all_new_mc(struct qeth_card *card)
+{
+	struct qeth_ipaddr *addr;
+	struct hlist_node *tmp;
+	int i;
+	int rc;
+
+	hash_for_each_safe(card->ip_mc_htable, i, tmp, addr, hnode) {
+		if (addr->disp_flag == QETH_DISP_ADDR_ADD) {
+			rc = qeth_l3_register_addr_entry(card, addr);
+			if (!rc || (rc == IPA_RC_LAN_OFFLINE))
+				addr->ref_counter = 1;
+			else {
+				hash_del(&addr->hnode);
+				kfree(addr);
+			}
+		}
+	}
+
+}
+
+static void qeth_l3_delete_nonused_mc(struct qeth_card *card)
+{
+	struct qeth_ipaddr *addr;
+	struct hlist_node *tmp;
+	int i;
+	int rc;
+
+	hash_for_each_safe(card->ip_mc_htable, i, tmp, addr, hnode) {
+		if (addr->disp_flag == QETH_DISP_ADDR_DELETE) {
+			rc = qeth_l3_deregister_addr_entry(card, addr);
+			if (!rc || (rc == IPA_RC_MC_ADDR_NOT_FOUND)) {
+				hash_del(&addr->hnode);
+				kfree(addr);
+			}
+		}
+	}
+
+}
+
+
+static void
+qeth_l3_add_mc_to_hash(struct qeth_card *card, struct in_device *in4_dev)
+{
 	struct ip_mc_list *im4;
+	struct qeth_ipaddr *tmp, *ipm;
 	char buf[MAX_ADDR_LEN];
 
 	QETH_CARD_TEXT(card, 4, "addmc");
+
+	tmp = qeth_l3_get_addr_buffer(QETH_PROT_IPV4);
+		if (!tmp)
+			return;
+
 	for (im4 = rcu_dereference(in4_dev->mc_list); im4 != NULL;
 	     im4 = rcu_dereference(im4->next_rcu)) {
-		qeth_l3_get_mac_for_ipm(im4->multiaddr, buf, in4_dev->dev);
-		ipm = qeth_l3_get_addr_buffer(QETH_PROT_IPV4);
-		if (!ipm)
-			continue;
-		ipm->u.a4.addr = im4->multiaddr;
-		memcpy(ipm->mac, buf, OSA_ADDR_LEN);
-		ipm->is_multicast = 1;
-		if (!qeth_l3_add_ip(card, ipm))
-			kfree(ipm);
+		qeth_l3_get_mac_for_ipm(im4->multiaddr, buf);
+
+		tmp->u.a4.addr = im4->multiaddr;
+		memcpy(tmp->mac, buf, sizeof(tmp->mac));
+
+		ipm = qeth_l3_ip_from_hash(card, tmp);
+		if (ipm) {
+			ipm->disp_flag = QETH_DISP_ADDR_DO_NOTHING;
+		} else {
+			ipm = qeth_l3_get_addr_buffer(QETH_PROT_IPV4);
+			if (!ipm)
+				continue;
+			memcpy(ipm->mac, buf, sizeof(tmp->mac));
+			ipm->u.a4.addr = im4->multiaddr;
+			ipm->is_multicast = 1;
+			ipm->disp_flag = QETH_DISP_ADDR_ADD;
+			hash_add(card->ip_mc_htable,
+					&ipm->hnode, qeth_l3_ipaddr_hash(ipm));
+		}
 	}
+
+	kfree(tmp);
 }
 
 /* called with rcu_read_lock */
@@ -1541,6 +1431,7 @@
 	u16 vid;
 
 	QETH_CARD_TEXT(card, 4, "addmcvl");
+
 	if (!qeth_is_supported(card, IPA_FULL_VLAN))
 		return;
 
@@ -1555,7 +1446,7 @@
 		in_dev = __in_dev_get_rcu(netdev);
 		if (!in_dev)
 			continue;
-		qeth_l3_add_mc(card, in_dev);
+		qeth_l3_add_mc_to_hash(card, in_dev);
 	}
 }
 
@@ -1564,36 +1455,60 @@
 	struct in_device *in4_dev;
 
 	QETH_CARD_TEXT(card, 4, "chkmcv4");
+
 	rcu_read_lock();
 	in4_dev = __in_dev_get_rcu(card->dev);
 	if (in4_dev == NULL)
 		goto unlock;
-	qeth_l3_add_mc(card, in4_dev);
+	qeth_l3_add_mc_to_hash(card, in4_dev);
 	qeth_l3_add_vlan_mc(card);
 unlock:
 	rcu_read_unlock();
 }
 
 #ifdef CONFIG_QETH_IPV6
-static void qeth_l3_add_mc6(struct qeth_card *card, struct inet6_dev *in6_dev)
+static void
+qeth_l3_add_mc6_to_hash(struct qeth_card *card, struct inet6_dev *in6_dev)
 {
 	struct qeth_ipaddr *ipm;
 	struct ifmcaddr6 *im6;
+	struct qeth_ipaddr *tmp;
 	char buf[MAX_ADDR_LEN];
 
 	QETH_CARD_TEXT(card, 4, "addmc6");
+
+	tmp = qeth_l3_get_addr_buffer(QETH_PROT_IPV6);
+		if (!tmp)
+			return;
+
 	for (im6 = in6_dev->mc_list; im6 != NULL; im6 = im6->next) {
 		ndisc_mc_map(&im6->mca_addr, buf, in6_dev->dev, 0);
+
+		memcpy(tmp->mac, buf, sizeof(tmp->mac));
+		memcpy(&tmp->u.a6.addr, &im6->mca_addr.s6_addr,
+		       sizeof(struct in6_addr));
+		tmp->is_multicast = 1;
+
+		ipm = qeth_l3_ip_from_hash(card, tmp);
+		if (ipm) {
+			ipm->disp_flag = QETH_DISP_ADDR_DO_NOTHING;
+			continue;
+		}
+
 		ipm = qeth_l3_get_addr_buffer(QETH_PROT_IPV6);
 		if (!ipm)
 			continue;
-		ipm->is_multicast = 1;
+
 		memcpy(ipm->mac, buf, OSA_ADDR_LEN);
 		memcpy(&ipm->u.a6.addr, &im6->mca_addr.s6_addr,
 		       sizeof(struct in6_addr));
-		if (!qeth_l3_add_ip(card, ipm))
-			kfree(ipm);
+		ipm->is_multicast = 1;
+		ipm->disp_flag = QETH_DISP_ADDR_ADD;
+		hash_add(card->ip_mc_htable,
+				&ipm->hnode, qeth_l3_ipaddr_hash(ipm));
+
 	}
+	kfree(tmp);
 }
 
 /* called with rcu_read_lock */
@@ -1603,6 +1518,7 @@
 	u16 vid;
 
 	QETH_CARD_TEXT(card, 4, "admc6vl");
+
 	if (!qeth_is_supported(card, IPA_FULL_VLAN))
 		return;
 
@@ -1618,7 +1534,7 @@
 		if (!in_dev)
 			continue;
 		read_lock_bh(&in_dev->lock);
-		qeth_l3_add_mc6(card, in_dev);
+		qeth_l3_add_mc6_to_hash(card, in_dev);
 		read_unlock_bh(&in_dev->lock);
 		in6_dev_put(in_dev);
 	}
@@ -1629,14 +1545,16 @@
 	struct inet6_dev *in6_dev;
 
 	QETH_CARD_TEXT(card, 4, "chkmcv6");
+
 	if (!qeth_is_supported(card, IPA_IPV6))
 		return ;
 	in6_dev = in6_dev_get(card->dev);
-	if (in6_dev == NULL)
+	if (!in6_dev)
 		return;
+
 	rcu_read_lock();
 	read_lock_bh(&in6_dev->lock);
-	qeth_l3_add_mc6(card, in6_dev);
+	qeth_l3_add_mc6_to_hash(card, in6_dev);
 	qeth_l3_add_vlan_mc6(card);
 	read_unlock_bh(&in6_dev->lock);
 	rcu_read_unlock();
@@ -1660,16 +1578,23 @@
 	in_dev = in_dev_get(netdev);
 	if (!in_dev)
 		return;
+
+	addr = qeth_l3_get_addr_buffer(QETH_PROT_IPV4);
+	if (!addr)
+		return;
+
+	spin_lock_bh(&card->ip_lock);
+
 	for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) {
-		addr = qeth_l3_get_addr_buffer(QETH_PROT_IPV4);
-		if (addr) {
-			addr->u.a4.addr = ifa->ifa_address;
-			addr->u.a4.mask = ifa->ifa_mask;
-			addr->type = QETH_IP_TYPE_NORMAL;
-			if (!qeth_l3_delete_ip(card, addr))
-				kfree(addr);
-		}
+		addr->u.a4.addr = ifa->ifa_address;
+		addr->u.a4.mask = ifa->ifa_mask;
+		addr->type = QETH_IP_TYPE_NORMAL;
+		qeth_l3_delete_ip(card, addr);
 	}
+
+	spin_unlock_bh(&card->ip_lock);
+
+	kfree(addr);
 	in_dev_put(in_dev);
 }
 
@@ -1687,20 +1612,28 @@
 	netdev = __vlan_find_dev_deep_rcu(card->dev, htons(ETH_P_8021Q), vid);
 	if (!netdev)
 		return;
+
 	in6_dev = in6_dev_get(netdev);
 	if (!in6_dev)
 		return;
+
+	addr = qeth_l3_get_addr_buffer(QETH_PROT_IPV6);
+	if (!addr)
+		return;
+
+	spin_lock_bh(&card->ip_lock);
+
 	list_for_each_entry(ifa, &in6_dev->addr_list, if_list) {
-		addr = qeth_l3_get_addr_buffer(QETH_PROT_IPV6);
-		if (addr) {
-			memcpy(&addr->u.a6.addr, &ifa->addr,
-			       sizeof(struct in6_addr));
-			addr->u.a6.pfxlen = ifa->prefix_len;
-			addr->type = QETH_IP_TYPE_NORMAL;
-			if (!qeth_l3_delete_ip(card, addr))
-				kfree(addr);
-		}
+		memcpy(&addr->u.a6.addr, &ifa->addr,
+		       sizeof(struct in6_addr));
+		addr->u.a6.pfxlen = ifa->prefix_len;
+		addr->type = QETH_IP_TYPE_NORMAL;
+		qeth_l3_delete_ip(card, addr);
 	}
+
+	spin_unlock_bh(&card->ip_lock);
+
+	kfree(addr);
 	in6_dev_put(in6_dev);
 #endif /* CONFIG_QETH_IPV6 */
 }
@@ -1727,18 +1660,16 @@
 				    __be16 proto, u16 vid)
 {
 	struct qeth_card *card = dev->ml_priv;
-	unsigned long flags;
 
 	QETH_CARD_TEXT_(card, 4, "kid:%d", vid);
+
 	if (qeth_wait_for_threads(card, QETH_RECOVER_THREAD)) {
 		QETH_CARD_TEXT(card, 3, "kidREC");
 		return 0;
 	}
-	spin_lock_irqsave(&card->vlanlock, flags);
 	/* unregister IP addresses of vlan device */
 	qeth_l3_free_vlan_addresses(card, vid);
 	clear_bit(vid, card->active_vlans);
-	spin_unlock_irqrestore(&card->vlanlock, flags);
 	qeth_l3_set_multicast_list(card->dev);
 	return 0;
 }
@@ -1994,8 +1925,8 @@
 static int qeth_l3_verify_dev(struct net_device *dev)
 {
 	struct qeth_card *card;
-	unsigned long flags;
 	int rc = 0;
+	unsigned long flags;
 
 	read_lock_irqsave(&qeth_core_card_list.rwlock, flags);
 	list_for_each_entry(card, &qeth_core_card_list.list, list) {
@@ -2051,7 +1982,7 @@
 		card->state = CARD_STATE_SOFTSETUP;
 	}
 	if (card->state == CARD_STATE_SOFTSETUP) {
-		qeth_l3_clear_ip_list(card, 1);
+		qeth_l3_clear_ip_htable(card, 1);
 		qeth_clear_ipacmd_list(card);
 		card->state = CARD_STATE_HARDSETUP;
 	}
@@ -2106,12 +2037,20 @@
 	    (card->state != CARD_STATE_UP))
 		return;
 	if (!card->options.sniffer) {
-		qeth_l3_delete_mc_addresses(card);
+
+		spin_lock_bh(&card->mclock);
+
+		qeth_l3_mark_all_mc_to_be_deleted(card);
+
 		qeth_l3_add_multicast_ipv4(card);
 #ifdef CONFIG_QETH_IPV6
 		qeth_l3_add_multicast_ipv6(card);
 #endif
-		qeth_l3_set_ip_addr_list(card);
+		qeth_l3_delete_nonused_mc(card);
+		qeth_l3_add_all_new_mc(card);
+
+		spin_unlock_bh(&card->mclock);
+
 		if (!qeth_adp_supported(card, IPA_SETADP_SET_PROMISC_MODE))
 			return;
 	}
@@ -2375,22 +2314,21 @@
 	if (rc) {
 		if (copy_to_user(udata, qinfo.udata, 4))
 			rc = -EFAULT;
-			goto free_and_out;
-	} else {
-#ifdef CONFIG_QETH_IPV6
-		if (qinfo.mask_bits & QETH_QARP_WITH_IPV6) {
-			/* fails in case of GuestLAN QDIO mode */
-			qeth_l3_query_arp_cache_info(card, QETH_PROT_IPV6,
-				&qinfo);
-		}
-#endif
-		if (copy_to_user(udata, qinfo.udata, qinfo.udata_len)) {
-			QETH_CARD_TEXT(card, 4, "qactf");
-			rc = -EFAULT;
-			goto free_and_out;
-		}
-		QETH_CARD_TEXT(card, 4, "qacts");
+		goto free_and_out;
 	}
+#ifdef CONFIG_QETH_IPV6
+	if (qinfo.mask_bits & QETH_QARP_WITH_IPV6) {
+		/* fails in case of GuestLAN QDIO mode */
+		qeth_l3_query_arp_cache_info(card, QETH_PROT_IPV6, &qinfo);
+	}
+#endif
+	if (copy_to_user(udata, qinfo.udata, qinfo.udata_len)) {
+		QETH_CARD_TEXT(card, 4, "qactf");
+		rc = -EFAULT;
+		goto free_and_out;
+	}
+	QETH_CARD_TEXT(card, 4, "qacts");
+
 free_and_out:
 	kfree(qinfo.udata);
 out:
@@ -2427,7 +2365,7 @@
 	rc = qeth_send_setassparms(card, iob,
 				   sizeof(struct qeth_arp_cache_entry),
 				   (unsigned long) entry,
-				   qeth_l3_default_setassparms_cb, NULL);
+				   qeth_setassparms_cb, NULL);
 	if (rc) {
 		tmp = rc;
 		qeth_l3_ipaddr4_to_string((u8 *)entry->ipaddr, buf);
@@ -2467,7 +2405,7 @@
 		return -ENOMEM;
 	rc = qeth_send_setassparms(card, iob,
 				   12, (unsigned long)buf,
-				   qeth_l3_default_setassparms_cb, NULL);
+				   qeth_setassparms_cb, NULL);
 	if (rc) {
 		tmp = rc;
 		memset(buf, 0, 16);
@@ -2793,15 +2731,34 @@
 	}
 }
 
-static inline int qeth_l3_tso_elements(struct sk_buff *skb)
+/**
+ * qeth_l3_get_elements_no_tso() - find number of SBALEs for skb data for tso
+ * @card:			   qeth card structure, to check max. elems.
+ * @skb:			   SKB address
+ * @extra_elems:		   extra elems needed, to check against max.
+ *
+ * Returns the number of pages, and thus QDIO buffer elements, needed to cover
+ * skb data, including linear part and fragments, but excluding TCP header.
+ * (Exclusion of TCP header distinguishes it from qeth_get_elements_no().)
+ * Checks if the result plus extra_elems fits under the limit for the card.
+ * Returns 0 if it does not.
+ * Note: extra_elems is not included in the returned result.
+ */
+static int qeth_l3_get_elements_no_tso(struct qeth_card *card,
+			struct sk_buff *skb, int extra_elems)
 {
-	unsigned long tcpd = (unsigned long)tcp_hdr(skb) +
-		tcp_hdr(skb)->doff * 4;
-	int tcpd_len = skb_headlen(skb) - (tcpd - (unsigned long)skb->data);
-	int elements = PFN_UP(tcpd + tcpd_len - 1) - PFN_DOWN(tcpd);
+	addr_t tcpdptr = (addr_t)tcp_hdr(skb) + tcp_hdrlen(skb);
+	int elements = qeth_get_elements_for_range(
+				tcpdptr,
+				(addr_t)skb->data + skb_headlen(skb)) +
+				qeth_get_elements_for_frags(skb);
 
-	elements += qeth_get_elements_for_frags(skb);
-
+	if ((elements + extra_elems) > QETH_MAX_BUFFER_ELEMENTS(card)) {
+		QETH_DBF_MESSAGE(2,
+	"Invalid size of TSO IP packet (Number=%d / Length=%d). Discarded.\n",
+				elements + extra_elems, skb->len);
+		return 0;
+	}
 	return elements;
 }
 
@@ -2810,8 +2767,8 @@
 	int rc;
 	u16 *tag;
 	struct qeth_hdr *hdr = NULL;
-	int elements_needed = 0;
-	int elems;
+	int hdr_elements = 0;
+	int elements;
 	struct qeth_card *card = dev->ml_priv;
 	struct sk_buff *new_skb = NULL;
 	int ipv = qeth_get_ip_version(skb);
@@ -2822,7 +2779,7 @@
 			qeth_get_priority_queue(card, skb, ipv, cast_type) :
 			card->qdio.default_out_queue];
 	int tx_bytes = skb->len;
-	bool large_send;
+	bool use_tso;
 	int data_offset = -1;
 	int nr_frags;
 
@@ -2847,10 +2804,12 @@
 		card->perf_stats.outbound_start_time = qeth_get_micros();
 	}
 
-	large_send = skb_is_gso(skb);
+	/* Ignore segment size from skb_is_gso(), 1 page is always used. */
+	use_tso = skb_is_gso(skb) &&
+		  (qeth_get_ip_protocol(skb) == IPPROTO_TCP) && (ipv == 4);
 
-	if ((card->info.type == QETH_CARD_TYPE_IQD) && (!large_send) &&
-	    (skb_shinfo(skb)->nr_frags == 0)) {
+	if ((card->info.type == QETH_CARD_TYPE_IQD) &&
+	    !skb_is_nonlinear(skb)) {
 		new_skb = skb;
 		if (new_skb->protocol == ETH_P_AF_IUCV)
 			data_offset = 0;
@@ -2859,7 +2818,7 @@
 		hdr = kmem_cache_alloc(qeth_core_header_cache, GFP_ATOMIC);
 		if (!hdr)
 			goto tx_drop;
-		elements_needed++;
+		hdr_elements++;
 	} else {
 		/* create a clone with writeable headroom */
 		new_skb = skb_realloc_headroom(skb, sizeof(struct qeth_hdr_tso)
@@ -2894,22 +2853,28 @@
 	/* fix hardware limitation: as long as we do not have sbal
 	 * chaining we can not send long frag lists
 	 */
-	if (large_send) {
-		if (qeth_l3_tso_elements(new_skb) + 1 > 16) {
-			if (skb_linearize(new_skb))
-				goto tx_drop;
-			if (card->options.performance_stats)
+	if ((card->info.type != QETH_CARD_TYPE_IQD) &&
+	    ((use_tso && !qeth_l3_get_elements_no_tso(card, new_skb, 1)) ||
+	     (!use_tso && !qeth_get_elements_no(card, new_skb, 0)))) {
+		int lin_rc = skb_linearize(new_skb);
+
+		if (card->options.performance_stats) {
+			if (lin_rc)
+				card->perf_stats.tx_linfail++;
+			else
 				card->perf_stats.tx_lin++;
 		}
+		if (lin_rc)
+			goto tx_drop;
 	}
 
-	if (large_send && (cast_type == RTN_UNSPEC)) {
+	if (use_tso) {
 		hdr = (struct qeth_hdr *)skb_push(new_skb,
 						sizeof(struct qeth_hdr_tso));
 		memset(hdr, 0, sizeof(struct qeth_hdr_tso));
 		qeth_l3_fill_header(card, hdr, new_skb, ipv, cast_type);
 		qeth_tso_fill_header(card, hdr, new_skb);
-		elements_needed++;
+		hdr_elements++;
 	} else {
 		if (data_offset < 0) {
 			hdr = (struct qeth_hdr *)skb_push(new_skb,
@@ -2930,31 +2895,31 @@
 			qeth_l3_hdr_csum(card, hdr, new_skb);
 	}
 
-	elems = qeth_get_elements_no(card, new_skb, elements_needed);
-	if (!elems) {
+	elements = use_tso ?
+		   qeth_l3_get_elements_no_tso(card, new_skb, hdr_elements) :
+		   qeth_get_elements_no(card, new_skb, hdr_elements);
+	if (!elements) {
 		if (data_offset >= 0)
 			kmem_cache_free(qeth_core_header_cache, hdr);
 		goto tx_drop;
 	}
-	elements_needed += elems;
-	nr_frags = skb_shinfo(new_skb)->nr_frags;
+	elements += hdr_elements;
 
 	if (card->info.type != QETH_CARD_TYPE_IQD) {
 		int len;
-		if (large_send)
+		if (use_tso)
 			len = ((unsigned long)tcp_hdr(new_skb) +
-				tcp_hdr(new_skb)->doff * 4) -
+				tcp_hdrlen(new_skb)) -
 				(unsigned long)new_skb->data;
 		else
 			len = sizeof(struct qeth_hdr_layer3);
 
 		if (qeth_hdr_chk_and_bounce(new_skb, &hdr, len))
 			goto tx_drop;
-		rc = qeth_do_send_packet(card, queue, new_skb, hdr,
-					 elements_needed);
+		rc = qeth_do_send_packet(card, queue, new_skb, hdr, elements);
 	} else
 		rc = qeth_do_send_packet_fast(card, queue, new_skb, hdr,
-					elements_needed, data_offset, 0);
+					elements, data_offset, 0);
 
 	if (!rc) {
 		card->stats.tx_packets++;
@@ -2962,7 +2927,8 @@
 		if (new_skb != skb)
 			dev_kfree_skb_any(skb);
 		if (card->options.performance_stats) {
-			if (large_send) {
+			nr_frags = skb_shinfo(new_skb)->nr_frags;
+			if (use_tso) {
 				card->perf_stats.large_send_bytes += tx_bytes;
 				card->perf_stats.large_send_cnt++;
 			}
@@ -3048,36 +3014,6 @@
 	return 0;
 }
 
-static netdev_features_t qeth_l3_fix_features(struct net_device *dev,
-	netdev_features_t features)
-{
-	struct qeth_card *card = dev->ml_priv;
-
-	if (!qeth_is_supported(card, IPA_OUTBOUND_CHECKSUM))
-		features &= ~NETIF_F_IP_CSUM;
-	if (!qeth_is_supported(card, IPA_OUTBOUND_TSO))
-		features &= ~NETIF_F_TSO;
-	if (!qeth_is_supported(card, IPA_INBOUND_CHECKSUM))
-		features &= ~NETIF_F_RXCSUM;
-	return features;
-}
-
-static int qeth_l3_set_features(struct net_device *dev,
-	netdev_features_t features)
-{
-	struct qeth_card *card = dev->ml_priv;
-	netdev_features_t changed = dev->features ^ features;
-
-	if (!(changed & NETIF_F_RXCSUM))
-		return 0;
-
-	if (card->state == CARD_STATE_DOWN ||
-	    card->state == CARD_STATE_RECOVER)
-		return 0;
-
-	return qeth_set_rx_csum(card, features & NETIF_F_RXCSUM ? 1 : 0);
-}
-
 static const struct ethtool_ops qeth_l3_ethtool_ops = {
 	.get_link = ethtool_op_get_link,
 	.get_strings = qeth_core_get_strings,
@@ -3120,8 +3056,8 @@
 	.ndo_set_rx_mode	= qeth_l3_set_multicast_list,
 	.ndo_do_ioctl		= qeth_l3_do_ioctl,
 	.ndo_change_mtu		= qeth_change_mtu,
-	.ndo_fix_features	= qeth_l3_fix_features,
-	.ndo_set_features	= qeth_l3_set_features,
+	.ndo_fix_features	= qeth_fix_features,
+	.ndo_set_features	= qeth_set_features,
 	.ndo_vlan_rx_add_vid	= qeth_l3_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid   = qeth_l3_vlan_rx_kill_vid,
 	.ndo_tx_timeout		= qeth_tx_timeout,
@@ -3136,8 +3072,8 @@
 	.ndo_set_rx_mode	= qeth_l3_set_multicast_list,
 	.ndo_do_ioctl		= qeth_l3_do_ioctl,
 	.ndo_change_mtu		= qeth_change_mtu,
-	.ndo_fix_features	= qeth_l3_fix_features,
-	.ndo_set_features	= qeth_l3_set_features,
+	.ndo_fix_features	= qeth_fix_features,
+	.ndo_set_features	= qeth_set_features,
 	.ndo_vlan_rx_add_vid	= qeth_l3_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid   = qeth_l3_vlan_rx_kill_vid,
 	.ndo_tx_timeout		= qeth_tx_timeout,
@@ -3169,7 +3105,10 @@
 				card->dev->hw_features = NETIF_F_SG |
 					NETIF_F_RXCSUM | NETIF_F_IP_CSUM |
 					NETIF_F_TSO;
-				card->dev->features = NETIF_F_RXCSUM;
+				card->dev->vlan_features = NETIF_F_SG |
+					NETIF_F_RXCSUM | NETIF_F_IP_CSUM |
+					NETIF_F_TSO;
+				card->dev->features = NETIF_F_SG;
 			}
 		}
 	} else if (card->info.type == QETH_CARD_TYPE_IQD) {
@@ -3195,7 +3134,9 @@
 				NETIF_F_HW_VLAN_CTAG_RX |
 				NETIF_F_HW_VLAN_CTAG_FILTER;
 	netif_keep_dst(card->dev);
-	card->dev->gso_max_size = 15 * PAGE_SIZE;
+	card->dev->gso_max_size = (QETH_MAX_BUFFER_ELEMENTS(card) - 1) *
+				  PAGE_SIZE;
+	card->dev->gso_max_segs = (QETH_MAX_BUFFER_ELEMENTS(card) - 1);
 
 	SET_NETDEV_DEV(card->dev, &card->gdev->dev);
 	netif_napi_add(card->dev, &card->napi, qeth_l3_poll, QETH_NAPI_WEIGHT);
@@ -3230,7 +3171,7 @@
 		card->dev = NULL;
 	}
 
-	qeth_l3_clear_ip_list(card, 0);
+	qeth_l3_clear_ip_htable(card, 0);
 	qeth_l3_clear_ipato_list(card);
 	return;
 }
@@ -3315,7 +3256,7 @@
 	card->state = CARD_STATE_SOFTSETUP;
 
 	qeth_set_allowed_threads(card, 0xffffffff, 0);
-	qeth_l3_set_ip_addr_list(card);
+	qeth_l3_recover_ip(card);
 	if (card->lan_online)
 		netif_carrier_on(card->dev);
 	else
@@ -3516,6 +3457,7 @@
 static int qeth_l3_ip_event(struct notifier_block *this,
 			    unsigned long event, void *ptr)
 {
+
 	struct in_ifaddr *ifa = (struct in_ifaddr *)ptr;
 	struct net_device *dev = (struct net_device *)ifa->ifa_dev->dev;
 	struct qeth_ipaddr *addr;
@@ -3530,27 +3472,27 @@
 	QETH_CARD_TEXT(card, 3, "ipevent");
 
 	addr = qeth_l3_get_addr_buffer(QETH_PROT_IPV4);
-	if (addr != NULL) {
+	if (addr) {
 		addr->u.a4.addr = ifa->ifa_address;
 		addr->u.a4.mask = ifa->ifa_mask;
 		addr->type = QETH_IP_TYPE_NORMAL;
 	} else
-		goto out;
+		return NOTIFY_DONE;
 
 	switch (event) {
 	case NETDEV_UP:
-		if (!qeth_l3_add_ip(card, addr))
-			kfree(addr);
+		spin_lock_bh(&card->ip_lock);
+		qeth_l3_add_ip(card, addr);
+		spin_unlock_bh(&card->ip_lock);
 		break;
 	case NETDEV_DOWN:
-		if (!qeth_l3_delete_ip(card, addr))
-			kfree(addr);
-		break;
-	default:
+		spin_lock_bh(&card->ip_lock);
+		qeth_l3_delete_ip(card, addr);
+		spin_unlock_bh(&card->ip_lock);
 		break;
 	}
-	qeth_l3_set_ip_addr_list(card);
-out:
+
+	kfree(addr);
 	return NOTIFY_DONE;
 }
 
@@ -3579,27 +3521,27 @@
 		return NOTIFY_DONE;
 
 	addr = qeth_l3_get_addr_buffer(QETH_PROT_IPV6);
-	if (addr != NULL) {
+	if (addr) {
 		memcpy(&addr->u.a6.addr, &ifa->addr, sizeof(struct in6_addr));
 		addr->u.a6.pfxlen = ifa->prefix_len;
 		addr->type = QETH_IP_TYPE_NORMAL;
 	} else
-		goto out;
+		return NOTIFY_DONE;
 
 	switch (event) {
 	case NETDEV_UP:
-		if (!qeth_l3_add_ip(card, addr))
-			kfree(addr);
+		spin_lock_bh(&card->ip_lock);
+		qeth_l3_add_ip(card, addr);
+		spin_unlock_bh(&card->ip_lock);
 		break;
 	case NETDEV_DOWN:
-		if (!qeth_l3_delete_ip(card, addr))
-			kfree(addr);
-		break;
-	default:
+		spin_lock_bh(&card->ip_lock);
+		qeth_l3_delete_ip(card, addr);
+		spin_unlock_bh(&card->ip_lock);
 		break;
 	}
-	qeth_l3_set_ip_addr_list(card);
-out:
+
+	kfree(addr);
 	return NOTIFY_DONE;
 }
 
diff --git a/drivers/s390/net/qeth_l3_sys.c b/drivers/s390/net/qeth_l3_sys.c
index 386eb7b..65645b1 100644
--- a/drivers/s390/net/qeth_l3_sys.c
+++ b/drivers/s390/net/qeth_l3_sys.c
@@ -8,6 +8,7 @@
 
 #include <linux/slab.h>
 #include <asm/ebcdic.h>
+#include <linux/hashtable.h>
 #include "qeth_l3.h"
 
 #define QETH_DEVICE_ATTR(_id, _name, _mode, _show, _store) \
@@ -285,19 +286,19 @@
 	if (card->options.hsuid[0]) {
 		/* delete old ip address */
 		addr = qeth_l3_get_addr_buffer(QETH_PROT_IPV6);
-		if (addr != NULL) {
-			addr->u.a6.addr.s6_addr32[0] = 0xfe800000;
-			addr->u.a6.addr.s6_addr32[1] = 0x00000000;
-			for (i = 8; i < 16; i++)
-				addr->u.a6.addr.s6_addr[i] =
-					card->options.hsuid[i - 8];
-			addr->u.a6.pfxlen = 0;
-			addr->type = QETH_IP_TYPE_NORMAL;
-		} else
+		if (!addr)
 			return -ENOMEM;
-		if (!qeth_l3_delete_ip(card, addr))
-			kfree(addr);
-		qeth_l3_set_ip_addr_list(card);
+
+		addr->u.a6.addr.s6_addr32[0] = 0xfe800000;
+		addr->u.a6.addr.s6_addr32[1] = 0x00000000;
+		for (i = 8; i < 16; i++)
+			addr->u.a6.addr.s6_addr[i] =
+				card->options.hsuid[i - 8];
+		addr->u.a6.pfxlen = 0;
+		addr->type = QETH_IP_TYPE_NORMAL;
+
+		qeth_l3_delete_ip(card, addr);
+		kfree(addr);
 	}
 
 	if (strlen(tmp) == 0) {
@@ -328,9 +329,8 @@
 		addr->type = QETH_IP_TYPE_NORMAL;
 	} else
 		return -ENOMEM;
-	if (!qeth_l3_add_ip(card, addr))
-		kfree(addr);
-	qeth_l3_set_ip_addr_list(card);
+	qeth_l3_add_ip(card, addr);
+	kfree(addr);
 
 	return count;
 }
@@ -367,8 +367,8 @@
 		struct device_attribute *attr, const char *buf, size_t count)
 {
 	struct qeth_card *card = dev_get_drvdata(dev);
-	struct qeth_ipaddr *tmpipa, *t;
-	int rc = 0;
+	struct qeth_ipaddr *addr;
+	int i, rc = 0;
 
 	if (!card)
 		return -EINVAL;
@@ -384,21 +384,20 @@
 		card->ipato.enabled = (card->ipato.enabled)? 0 : 1;
 	} else if (sysfs_streq(buf, "1")) {
 		card->ipato.enabled = 1;
-		list_for_each_entry_safe(tmpipa, t, card->ip_tbd_list, entry) {
-			if ((tmpipa->type == QETH_IP_TYPE_NORMAL) &&
-				qeth_l3_is_addr_covered_by_ipato(card, tmpipa))
-				tmpipa->set_flags |=
+		hash_for_each(card->ip_htable, i, addr, hnode) {
+				if ((addr->type == QETH_IP_TYPE_NORMAL) &&
+				qeth_l3_is_addr_covered_by_ipato(card, addr))
+					addr->set_flags |=
 					QETH_IPA_SETIP_TAKEOVER_FLAG;
-		}
-
+			}
 	} else if (sysfs_streq(buf, "0")) {
 		card->ipato.enabled = 0;
-		list_for_each_entry_safe(tmpipa, t, card->ip_tbd_list, entry) {
-			if (tmpipa->set_flags &
-				QETH_IPA_SETIP_TAKEOVER_FLAG)
-				tmpipa->set_flags &=
-					~QETH_IPA_SETIP_TAKEOVER_FLAG;
-		}
+		hash_for_each(card->ip_htable, i, addr, hnode) {
+			if (addr->set_flags &
+			QETH_IPA_SETIP_TAKEOVER_FLAG)
+				addr->set_flags &=
+				~QETH_IPA_SETIP_TAKEOVER_FLAG;
+			}
 	} else
 		rc = -EINVAL;
 out:
@@ -452,7 +451,6 @@
 			enum qeth_prot_versions proto)
 {
 	struct qeth_ipato_entry *ipatoe;
-	unsigned long flags;
 	char addr_str[40];
 	int entry_len; /* length of 1 entry string, differs between v4 and v6 */
 	int i = 0;
@@ -460,7 +458,7 @@
 	entry_len = (proto == QETH_PROT_IPV4)? 12 : 40;
 	/* add strlen for "/<mask>\n" */
 	entry_len += (proto == QETH_PROT_IPV4)? 5 : 6;
-	spin_lock_irqsave(&card->ip_lock, flags);
+	spin_lock_bh(&card->ip_lock);
 	list_for_each_entry(ipatoe, &card->ipato.entries, entry) {
 		if (ipatoe->proto != proto)
 			continue;
@@ -473,7 +471,7 @@
 		i += snprintf(buf + i, PAGE_SIZE - i,
 			      "%s/%i\n", addr_str, ipatoe->mask_bits);
 	}
-	spin_unlock_irqrestore(&card->ip_lock, flags);
+	spin_unlock_bh(&card->ip_lock);
 	i += snprintf(buf + i, PAGE_SIZE - i, "\n");
 
 	return i;
@@ -689,15 +687,15 @@
 			enum qeth_prot_versions proto)
 {
 	struct qeth_ipaddr *ipaddr;
+	struct hlist_node  *tmp;
 	char addr_str[40];
 	int entry_len; /* length of 1 entry string, differs between v4 and v6 */
-	unsigned long flags;
 	int i = 0;
 
 	entry_len = (proto == QETH_PROT_IPV4)? 12 : 40;
 	entry_len += 2; /* \n + terminator */
-	spin_lock_irqsave(&card->ip_lock, flags);
-	list_for_each_entry(ipaddr, &card->ip_list, entry) {
+	spin_lock_bh(&card->ip_lock);
+	hash_for_each_safe(card->ip_htable, i, tmp, ipaddr, hnode) {
 		if (ipaddr->proto != proto)
 			continue;
 		if (ipaddr->type != QETH_IP_TYPE_VIPA)
@@ -711,7 +709,7 @@
 			addr_str);
 		i += snprintf(buf + i, PAGE_SIZE - i, "%s\n", addr_str);
 	}
-	spin_unlock_irqrestore(&card->ip_lock, flags);
+	spin_unlock_bh(&card->ip_lock);
 	i += snprintf(buf + i, PAGE_SIZE - i, "\n");
 
 	return i;
@@ -851,15 +849,15 @@
 		       enum qeth_prot_versions proto)
 {
 	struct qeth_ipaddr *ipaddr;
+	struct hlist_node *tmp;
 	char addr_str[40];
 	int entry_len; /* length of 1 entry string, differs between v4 and v6 */
-	unsigned long flags;
 	int i = 0;
 
 	entry_len = (proto == QETH_PROT_IPV4)? 12 : 40;
 	entry_len += 2; /* \n + terminator */
-	spin_lock_irqsave(&card->ip_lock, flags);
-	list_for_each_entry(ipaddr, &card->ip_list, entry) {
+	spin_lock_bh(&card->ip_lock);
+	hash_for_each_safe(card->ip_htable, i, tmp, ipaddr, hnode) {
 		if (ipaddr->proto != proto)
 			continue;
 		if (ipaddr->type != QETH_IP_TYPE_RXIP)
@@ -873,7 +871,7 @@
 			addr_str);
 		i += snprintf(buf + i, PAGE_SIZE - i, "%s\n", addr_str);
 	}
-	spin_unlock_irqrestore(&card->ip_lock, flags);
+	spin_unlock_bh(&card->ip_lock);
 	i += snprintf(buf + i, PAGE_SIZE - i, "\n");
 
 	return i;
diff --git a/drivers/soc/fsl/qe/Kconfig b/drivers/soc/fsl/qe/Kconfig
index 20978f2..73a2e08 100644
--- a/drivers/soc/fsl/qe/Kconfig
+++ b/drivers/soc/fsl/qe/Kconfig
@@ -22,7 +22,7 @@
 
 config UCC_FAST
 	bool
-	default y if UCC_GETH
+	default y if UCC_GETH || QE_TDM
 	help
 	  This option provides qe_lib support to UCC fast
 	  protocols: HDLC, Ethernet, ATM, transparent
@@ -31,6 +31,10 @@
 	bool
 	default y if UCC_FAST || UCC_SLOW
 
+config QE_TDM
+	bool
+	default y if FSL_UCC_HDLC
+
 config QE_USB
 	bool
 	default y if USB_FSL_QE
diff --git a/drivers/soc/fsl/qe/Makefile b/drivers/soc/fsl/qe/Makefile
index ffac541..2031d38 100644
--- a/drivers/soc/fsl/qe/Makefile
+++ b/drivers/soc/fsl/qe/Makefile
@@ -6,5 +6,6 @@
 obj-$(CONFIG_UCC)	+= ucc.o
 obj-$(CONFIG_UCC_SLOW)	+= ucc_slow.o
 obj-$(CONFIG_UCC_FAST)	+= ucc_fast.o
+obj-$(CONFIG_QE_TDM)	+= qe_tdm.o
 obj-$(CONFIG_QE_USB)	+= usb.o
 obj-$(CONFIG_QE_GPIO)	+= gpio.o
diff --git a/drivers/soc/fsl/qe/qe.c b/drivers/soc/fsl/qe/qe.c
index 709fc63..7026507 100644
--- a/drivers/soc/fsl/qe/qe.c
+++ b/drivers/soc/fsl/qe/qe.c
@@ -239,6 +239,12 @@
 	if (strcasecmp(source, "none") == 0)
 		return QE_CLK_NONE;
 
+	if (strcmp(source, "tsync_pin") == 0)
+		return QE_TSYNC_PIN;
+
+	if (strcmp(source, "rsync_pin") == 0)
+		return QE_RSYNC_PIN;
+
 	if (strncasecmp(source, "brg", 3) == 0) {
 		i = simple_strtoul(source + 3, NULL, 10);
 		if ((i >= 1) && (i <= 16))
diff --git a/drivers/soc/fsl/qe/qe_tdm.c b/drivers/soc/fsl/qe/qe_tdm.c
new file mode 100644
index 0000000..5e48b14
--- /dev/null
+++ b/drivers/soc/fsl/qe/qe_tdm.c
@@ -0,0 +1,276 @@
+/*
+ * Copyright (C) 2015 Freescale Semiconductor, Inc. All rights reserved.
+ *
+ * Authors:	Zhao Qiang <qiang.zhao@nxp.com>
+ *
+ * Description:
+ * QE TDM API Set - TDM specific routines implementations.
+ *
+ * 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/io.h>
+#include <linux/kernel.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
+#include <soc/fsl/qe/qe_tdm.h>
+
+static int set_tdm_framer(const char *tdm_framer_type)
+{
+	if (strcmp(tdm_framer_type, "e1") == 0)
+		return TDM_FRAMER_E1;
+	else if (strcmp(tdm_framer_type, "t1") == 0)
+		return TDM_FRAMER_T1;
+	else
+		return -EINVAL;
+}
+
+static void set_si_param(struct ucc_tdm *utdm, struct ucc_tdm_info *ut_info)
+{
+	struct si_mode_info *si_info = &ut_info->si_info;
+
+	if (utdm->tdm_mode == TDM_INTERNAL_LOOPBACK) {
+		si_info->simr_crt = 1;
+		si_info->simr_rfsd = 0;
+	}
+}
+
+int ucc_of_parse_tdm(struct device_node *np, struct ucc_tdm *utdm,
+		     struct ucc_tdm_info *ut_info)
+{
+	const char *sprop;
+	int ret = 0;
+	u32 val;
+	struct resource *res;
+	struct device_node *np2;
+	static int siram_init_flag;
+	struct platform_device *pdev;
+
+	sprop = of_get_property(np, "fsl,rx-sync-clock", NULL);
+	if (sprop) {
+		ut_info->uf_info.rx_sync = qe_clock_source(sprop);
+		if ((ut_info->uf_info.rx_sync < QE_CLK_NONE) ||
+		    (ut_info->uf_info.rx_sync > QE_RSYNC_PIN)) {
+			pr_err("QE-TDM: Invalid rx-sync-clock property\n");
+			return -EINVAL;
+		}
+	} else {
+		pr_err("QE-TDM: Invalid rx-sync-clock property\n");
+		return -EINVAL;
+	}
+
+	sprop = of_get_property(np, "fsl,tx-sync-clock", NULL);
+	if (sprop) {
+		ut_info->uf_info.tx_sync = qe_clock_source(sprop);
+		if ((ut_info->uf_info.tx_sync < QE_CLK_NONE) ||
+		    (ut_info->uf_info.tx_sync > QE_TSYNC_PIN)) {
+			pr_err("QE-TDM: Invalid tx-sync-clock property\n");
+		return -EINVAL;
+		}
+	} else {
+		pr_err("QE-TDM: Invalid tx-sync-clock property\n");
+		return -EINVAL;
+	}
+
+	ret = of_property_read_u32_index(np, "fsl,tx-timeslot-mask", 0, &val);
+	if (ret) {
+		pr_err("QE-TDM: Invalid tx-timeslot-mask property\n");
+		return -EINVAL;
+	}
+	utdm->tx_ts_mask = val;
+
+	ret = of_property_read_u32_index(np, "fsl,rx-timeslot-mask", 0, &val);
+	if (ret) {
+		ret = -EINVAL;
+		pr_err("QE-TDM: Invalid rx-timeslot-mask property\n");
+		return ret;
+	}
+	utdm->rx_ts_mask = val;
+
+	ret = of_property_read_u32_index(np, "fsl,tdm-id", 0, &val);
+	if (ret) {
+		ret = -EINVAL;
+		pr_err("QE-TDM: No fsl,tdm-id property for this UCC\n");
+		return ret;
+	}
+	utdm->tdm_port = val;
+	ut_info->uf_info.tdm_num = utdm->tdm_port;
+
+	if (of_get_property(np, "fsl,tdm-internal-loopback", NULL))
+		utdm->tdm_mode = TDM_INTERNAL_LOOPBACK;
+	else
+		utdm->tdm_mode = TDM_NORMAL;
+
+	sprop = of_get_property(np, "fsl,tdm-framer-type", NULL);
+	if (!sprop) {
+		ret = -EINVAL;
+		pr_err("QE-TDM: No tdm-framer-type property for UCC\n");
+		return ret;
+	}
+	ret = set_tdm_framer(sprop);
+	if (ret < 0)
+		return -EINVAL;
+	utdm->tdm_framer_type = ret;
+
+	ret = of_property_read_u32_index(np, "fsl,siram-entry-id", 0, &val);
+	if (ret) {
+		ret = -EINVAL;
+		pr_err("QE-TDM: No siram entry id for UCC\n");
+		return ret;
+	}
+	utdm->siram_entry_id = val;
+
+	set_si_param(utdm, ut_info);
+
+	np2 = of_find_compatible_node(NULL, NULL, "fsl,t1040-qe-si");
+	if (!np2)
+		return -EINVAL;
+
+	pdev = of_find_device_by_node(np2);
+	if (!pdev) {
+		pr_err("%s: failed to lookup pdev\n", np2->name);
+		of_node_put(np2);
+		return -EINVAL;
+	}
+
+	of_node_put(np2);
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	utdm->si_regs = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(utdm->si_regs)) {
+		ret = PTR_ERR(utdm->si_regs);
+		goto err_miss_siram_property;
+	}
+
+	np2 = of_find_compatible_node(NULL, NULL, "fsl,t1040-qe-siram");
+	if (!np2) {
+		ret = -EINVAL;
+		goto err_miss_siram_property;
+	}
+
+	pdev = of_find_device_by_node(np2);
+	if (!pdev) {
+		ret = -EINVAL;
+		pr_err("%s: failed to lookup pdev\n", np2->name);
+		of_node_put(np2);
+		goto err_miss_siram_property;
+	}
+
+	of_node_put(np2);
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	utdm->siram = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(utdm->siram)) {
+		ret = PTR_ERR(utdm->siram);
+		goto err_miss_siram_property;
+	}
+
+	if (siram_init_flag == 0) {
+		memset_io(utdm->siram, 0,  res->end - res->start + 1);
+		siram_init_flag = 1;
+	}
+
+	return ret;
+
+err_miss_siram_property:
+	devm_iounmap(&pdev->dev, utdm->si_regs);
+	return ret;
+}
+
+void ucc_tdm_init(struct ucc_tdm *utdm, struct ucc_tdm_info *ut_info)
+{
+	struct si1 __iomem *si_regs;
+	u16 __iomem *siram;
+	u16 siram_entry_valid;
+	u16 siram_entry_closed;
+	u16 ucc_num;
+	u8 csel;
+	u16 sixmr;
+	u16 tdm_port;
+	u32 siram_entry_id;
+	u32 mask;
+	int i;
+
+	si_regs = utdm->si_regs;
+	siram = utdm->siram;
+	ucc_num = ut_info->uf_info.ucc_num;
+	tdm_port = utdm->tdm_port;
+	siram_entry_id = utdm->siram_entry_id;
+
+	if (utdm->tdm_framer_type == TDM_FRAMER_T1)
+		utdm->num_of_ts = 24;
+	if (utdm->tdm_framer_type == TDM_FRAMER_E1)
+		utdm->num_of_ts = 32;
+
+	/* set siram table */
+	csel = (ucc_num < 4) ? ucc_num + 9 : ucc_num - 3;
+
+	siram_entry_valid = SIR_CSEL(csel) | SIR_BYTE | SIR_CNT(0);
+	siram_entry_closed = SIR_IDLE | SIR_BYTE | SIR_CNT(0);
+
+	for (i = 0; i < utdm->num_of_ts; i++) {
+		mask = 0x01 << i;
+
+		if (utdm->tx_ts_mask & mask)
+			iowrite16be(siram_entry_valid,
+				    &siram[siram_entry_id * 32 + i]);
+		else
+			iowrite16be(siram_entry_closed,
+				    &siram[siram_entry_id * 32 + i]);
+
+		if (utdm->rx_ts_mask & mask)
+			iowrite16be(siram_entry_valid,
+				    &siram[siram_entry_id * 32 + 0x200 +  i]);
+		else
+			iowrite16be(siram_entry_closed,
+				    &siram[siram_entry_id * 32 + 0x200 +  i]);
+	}
+
+	setbits16(&siram[(siram_entry_id * 32) + (utdm->num_of_ts - 1)],
+		  SIR_LAST);
+	setbits16(&siram[(siram_entry_id * 32) + 0x200 + (utdm->num_of_ts - 1)],
+		  SIR_LAST);
+
+	/* Set SIxMR register */
+	sixmr = SIMR_SAD(siram_entry_id);
+
+	sixmr &= ~SIMR_SDM_MASK;
+
+	if (utdm->tdm_mode == TDM_INTERNAL_LOOPBACK)
+		sixmr |= SIMR_SDM_INTERNAL_LOOPBACK;
+	else
+		sixmr |= SIMR_SDM_NORMAL;
+
+	sixmr |= SIMR_RFSD(ut_info->si_info.simr_rfsd) |
+			SIMR_TFSD(ut_info->si_info.simr_tfsd);
+
+	if (ut_info->si_info.simr_crt)
+		sixmr |= SIMR_CRT;
+	if (ut_info->si_info.simr_sl)
+		sixmr |= SIMR_SL;
+	if (ut_info->si_info.simr_ce)
+		sixmr |= SIMR_CE;
+	if (ut_info->si_info.simr_fe)
+		sixmr |= SIMR_FE;
+	if (ut_info->si_info.simr_gm)
+		sixmr |= SIMR_GM;
+
+	switch (tdm_port) {
+	case 0:
+		iowrite16be(sixmr, &si_regs->sixmr1[0]);
+		break;
+	case 1:
+		iowrite16be(sixmr, &si_regs->sixmr1[1]);
+		break;
+	case 2:
+		iowrite16be(sixmr, &si_regs->sixmr1[2]);
+		break;
+	case 3:
+		iowrite16be(sixmr, &si_regs->sixmr1[3]);
+		break;
+	default:
+		pr_err("QE-TDM: can not find tdm sixmr reg\n");
+		break;
+	}
+}
diff --git a/drivers/soc/fsl/qe/ucc.c b/drivers/soc/fsl/qe/ucc.c
index b59d335..c646d87 100644
--- a/drivers/soc/fsl/qe/ucc.c
+++ b/drivers/soc/fsl/qe/ucc.c
@@ -25,6 +25,12 @@
 #include <soc/fsl/qe/qe.h>
 #include <soc/fsl/qe/ucc.h>
 
+#define UCC_TDM_NUM 8
+#define RX_SYNC_SHIFT_BASE 30
+#define TX_SYNC_SHIFT_BASE 14
+#define RX_CLK_SHIFT_BASE 28
+#define TX_CLK_SHIFT_BASE 12
+
 int ucc_set_qe_mux_mii_mng(unsigned int ucc_num)
 {
 	unsigned long flags;
@@ -210,3 +216,447 @@
 
 	return 0;
 }
+
+static int ucc_get_tdm_common_clk(u32 tdm_num, enum qe_clock clock)
+{
+	int clock_bits = -EINVAL;
+
+	/*
+	 * for TDM[0, 1, 2, 3], TX and RX use  common
+	 * clock source BRG3,4 and CLK1,2
+	 * for TDM[4, 5, 6, 7], TX and RX use  common
+	 * clock source BRG12,13 and CLK23,24
+	 */
+	switch (tdm_num) {
+	case 0:
+	case 1:
+	case 2:
+	case 3:
+		switch (clock) {
+		case QE_BRG3:
+			clock_bits = 1;
+			break;
+		case QE_BRG4:
+			clock_bits = 2;
+			break;
+		case QE_CLK1:
+			clock_bits = 4;
+			break;
+		case QE_CLK2:
+			clock_bits = 5;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 4:
+	case 5:
+	case 6:
+	case 7:
+		switch (clock) {
+		case QE_BRG12:
+			clock_bits = 1;
+			break;
+		case QE_BRG13:
+			clock_bits = 2;
+			break;
+		case QE_CLK23:
+			clock_bits = 4;
+			break;
+		case QE_CLK24:
+			clock_bits = 5;
+			break;
+		default:
+			break;
+		}
+		break;
+	default:
+		break;
+	}
+
+	return clock_bits;
+}
+
+static int ucc_get_tdm_rx_clk(u32 tdm_num, enum qe_clock clock)
+{
+	int clock_bits = -EINVAL;
+
+	switch (tdm_num) {
+	case 0:
+		switch (clock) {
+		case QE_CLK3:
+			clock_bits = 6;
+			break;
+		case QE_CLK8:
+			clock_bits = 7;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 1:
+		switch (clock) {
+		case QE_CLK5:
+			clock_bits = 6;
+			break;
+		case QE_CLK10:
+			clock_bits = 7;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 2:
+		switch (clock) {
+		case QE_CLK7:
+			clock_bits = 6;
+			break;
+		case QE_CLK12:
+			clock_bits = 7;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 3:
+		switch (clock) {
+		case QE_CLK9:
+			clock_bits = 6;
+			break;
+		case QE_CLK14:
+			clock_bits = 7;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 4:
+		switch (clock) {
+		case QE_CLK11:
+			clock_bits = 6;
+			break;
+		case QE_CLK16:
+			clock_bits = 7;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 5:
+		switch (clock) {
+		case QE_CLK13:
+			clock_bits = 6;
+			break;
+		case QE_CLK18:
+			clock_bits = 7;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 6:
+		switch (clock) {
+		case QE_CLK15:
+			clock_bits = 6;
+			break;
+		case QE_CLK20:
+			clock_bits = 7;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 7:
+		switch (clock) {
+		case QE_CLK17:
+			clock_bits = 6;
+			break;
+		case QE_CLK22:
+			clock_bits = 7;
+			break;
+		default:
+			break;
+		}
+		break;
+	}
+
+	return clock_bits;
+}
+
+static int ucc_get_tdm_tx_clk(u32 tdm_num, enum qe_clock clock)
+{
+	int clock_bits = -EINVAL;
+
+	switch (tdm_num) {
+	case 0:
+		switch (clock) {
+		case QE_CLK4:
+			clock_bits = 6;
+			break;
+		case QE_CLK9:
+			clock_bits = 7;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 1:
+		switch (clock) {
+		case QE_CLK6:
+			clock_bits = 6;
+			break;
+		case QE_CLK11:
+			clock_bits = 7;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 2:
+		switch (clock) {
+		case QE_CLK8:
+			clock_bits = 6;
+			break;
+		case QE_CLK13:
+			clock_bits = 7;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 3:
+		switch (clock) {
+		case QE_CLK10:
+			clock_bits = 6;
+			break;
+		case QE_CLK15:
+			clock_bits = 7;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 4:
+		switch (clock) {
+		case QE_CLK12:
+			clock_bits = 6;
+			break;
+		case QE_CLK17:
+			clock_bits = 7;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 5:
+		switch (clock) {
+		case QE_CLK14:
+			clock_bits = 6;
+			break;
+		case QE_CLK19:
+			clock_bits = 7;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 6:
+		switch (clock) {
+		case QE_CLK16:
+			clock_bits = 6;
+			break;
+		case QE_CLK21:
+			clock_bits = 7;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 7:
+		switch (clock) {
+		case QE_CLK18:
+			clock_bits = 6;
+			break;
+		case QE_CLK3:
+			clock_bits = 7;
+			break;
+		default:
+			break;
+		}
+		break;
+	}
+
+	return clock_bits;
+}
+
+/* tdm_num: TDM A-H port num is 0-7 */
+static int ucc_get_tdm_rxtx_clk(enum comm_dir mode, u32 tdm_num,
+				enum qe_clock clock)
+{
+	int clock_bits;
+
+	clock_bits = ucc_get_tdm_common_clk(tdm_num, clock);
+	if (clock_bits > 0)
+		return clock_bits;
+	if (mode == COMM_DIR_RX)
+		clock_bits = ucc_get_tdm_rx_clk(tdm_num, clock);
+	if (mode == COMM_DIR_TX)
+		clock_bits = ucc_get_tdm_tx_clk(tdm_num, clock);
+	return clock_bits;
+}
+
+static u32 ucc_get_tdm_clk_shift(enum comm_dir mode, u32 tdm_num)
+{
+	u32 shift;
+
+	shift = (mode == COMM_DIR_RX) ? RX_CLK_SHIFT_BASE : TX_CLK_SHIFT_BASE;
+	if (tdm_num < 4)
+		shift -= tdm_num * 4;
+	else
+		shift -= (tdm_num - 4) * 4;
+
+	return shift;
+}
+
+int ucc_set_tdm_rxtx_clk(u32 tdm_num, enum qe_clock clock,
+			 enum comm_dir mode)
+{
+	int clock_bits;
+	u32 shift;
+	struct qe_mux __iomem *qe_mux_reg;
+	 __be32 __iomem *cmxs1cr;
+
+	qe_mux_reg = &qe_immr->qmx;
+
+	if (tdm_num > 7 || tdm_num < 0)
+		return -EINVAL;
+
+	/* The communications direction must be RX or TX */
+	if (mode != COMM_DIR_RX && mode != COMM_DIR_TX)
+		return -EINVAL;
+
+	clock_bits = ucc_get_tdm_rxtx_clk(mode, tdm_num, clock);
+	if (clock_bits < 0)
+		return -EINVAL;
+
+	shift = ucc_get_tdm_clk_shift(mode, tdm_num);
+
+	cmxs1cr = (tdm_num < 4) ? &qe_mux_reg->cmxsi1cr_l :
+				  &qe_mux_reg->cmxsi1cr_h;
+
+	qe_clrsetbits32(cmxs1cr, QE_CMXUCR_TX_CLK_SRC_MASK << shift,
+			clock_bits << shift);
+
+	return 0;
+}
+
+static int ucc_get_tdm_sync_source(u32 tdm_num, enum qe_clock clock,
+				   enum comm_dir mode)
+{
+	int source = -EINVAL;
+
+	if (mode == COMM_DIR_RX && clock == QE_RSYNC_PIN) {
+		source = 0;
+		return source;
+	}
+	if (mode == COMM_DIR_TX && clock == QE_TSYNC_PIN) {
+		source = 0;
+		return source;
+	}
+
+	switch (tdm_num) {
+	case 0:
+	case 1:
+		switch (clock) {
+		case QE_BRG9:
+			source = 1;
+			break;
+		case QE_BRG10:
+			source = 2;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 2:
+	case 3:
+		switch (clock) {
+		case QE_BRG9:
+			source = 1;
+			break;
+		case QE_BRG11:
+			source = 2;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 4:
+	case 5:
+		switch (clock) {
+		case QE_BRG13:
+			source = 1;
+			break;
+		case QE_BRG14:
+			source = 2;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 6:
+	case 7:
+		switch (clock) {
+		case QE_BRG13:
+			source = 1;
+			break;
+		case QE_BRG15:
+			source = 2;
+			break;
+		default:
+			break;
+		}
+		break;
+	}
+
+	return source;
+}
+
+static u32 ucc_get_tdm_sync_shift(enum comm_dir mode, u32 tdm_num)
+{
+	u32 shift;
+
+	shift = (mode == COMM_DIR_RX) ? RX_SYNC_SHIFT_BASE : RX_SYNC_SHIFT_BASE;
+	shift -= tdm_num * 2;
+
+	return shift;
+}
+
+int ucc_set_tdm_rxtx_sync(u32 tdm_num, enum qe_clock clock,
+			  enum comm_dir mode)
+{
+	int source;
+	u32 shift;
+	struct qe_mux *qe_mux_reg;
+
+	qe_mux_reg = &qe_immr->qmx;
+
+	if (tdm_num >= UCC_TDM_NUM)
+		return -EINVAL;
+
+	/* The communications direction must be RX or TX */
+	if (mode != COMM_DIR_RX && mode != COMM_DIR_TX)
+		return -EINVAL;
+
+	source = ucc_get_tdm_sync_source(tdm_num, clock, mode);
+	if (source < 0)
+		return -EINVAL;
+
+	shift = ucc_get_tdm_sync_shift(mode, tdm_num);
+
+	qe_clrsetbits32(&qe_mux_reg->cmxsi1syr,
+			QE_CMXUCR_TX_CLK_SRC_MASK << shift,
+			source << shift);
+
+	return 0;
+}
diff --git a/drivers/soc/fsl/qe/ucc_fast.c b/drivers/soc/fsl/qe/ucc_fast.c
index a768931..83d8d16 100644
--- a/drivers/soc/fsl/qe/ucc_fast.c
+++ b/drivers/soc/fsl/qe/ucc_fast.c
@@ -327,6 +327,42 @@
 			ucc_fast_free(uccf);
 			return -EINVAL;
 		}
+	} else {
+		/* tdm Rx clock routing */
+		if ((uf_info->rx_clock != QE_CLK_NONE) &&
+		    ucc_set_tdm_rxtx_clk(uf_info->tdm_num, uf_info->rx_clock,
+					 COMM_DIR_RX)) {
+			pr_err("%s: illegal value for RX clock", __func__);
+			ucc_fast_free(uccf);
+			return -EINVAL;
+		}
+
+		/* tdm Tx clock routing */
+		if ((uf_info->tx_clock != QE_CLK_NONE) &&
+		    ucc_set_tdm_rxtx_clk(uf_info->tdm_num, uf_info->tx_clock,
+					 COMM_DIR_TX)) {
+			pr_err("%s: illegal value for TX clock", __func__);
+			ucc_fast_free(uccf);
+			return -EINVAL;
+		}
+
+		/* tdm Rx sync clock routing */
+		if ((uf_info->rx_sync != QE_CLK_NONE) &&
+		    ucc_set_tdm_rxtx_sync(uf_info->tdm_num, uf_info->rx_sync,
+					  COMM_DIR_RX)) {
+			pr_err("%s: illegal value for RX clock", __func__);
+			ucc_fast_free(uccf);
+			return -EINVAL;
+		}
+
+		/* tdm Tx sync clock routing */
+		if ((uf_info->tx_sync != QE_CLK_NONE) &&
+		    ucc_set_tdm_rxtx_sync(uf_info->tdm_num, uf_info->tx_sync,
+					  COMM_DIR_TX)) {
+			pr_err("%s: illegal value for TX clock", __func__);
+			ucc_fast_free(uccf);
+			return -EINVAL;
+		}
 	}
 
 	/* Set interrupt mask register at UCC level. */
diff --git a/drivers/thermal/int340x_thermal/int3406_thermal.c b/drivers/thermal/int340x_thermal/int3406_thermal.c
index 13d431c..a578cd2 100644
--- a/drivers/thermal/int340x_thermal/int3406_thermal.c
+++ b/drivers/thermal/int340x_thermal/int3406_thermal.c
@@ -177,7 +177,7 @@
 		return -ENODEV;
 	d->raw_bd = bd;
 
-	ret = acpi_video_get_levels(ACPI_COMPANION(&pdev->dev), &d->br);
+	ret = acpi_video_get_levels(ACPI_COMPANION(&pdev->dev), &d->br, NULL);
 	if (ret)
 		return ret;
 
diff --git a/drivers/tty/Kconfig b/drivers/tty/Kconfig
index 82c4d2e..9510305 100644
--- a/drivers/tty/Kconfig
+++ b/drivers/tty/Kconfig
@@ -120,17 +120,6 @@
 	  All modern Linux systems use the Unix98 ptys.  Say Y unless
 	  you're on an embedded system and want to conserve memory.
 
-config DEVPTS_MULTIPLE_INSTANCES
-	bool "Support multiple instances of devpts"
-	depends on UNIX98_PTYS
-	default n
-	---help---
-	  Enable support for multiple instances of devpts filesystem.
-	  If you want to have isolated PTY namespaces (eg: in containers),
-	  say Y here.  Otherwise, say N. If enabled, each mount of devpts
-	  filesystem with the '-o newinstance' option will create an
-	  independent PTY namespace.
-
 config LEGACY_PTYS
 	bool "Legacy (BSD) PTY support"
 	default y
diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c
index dd4b841..f856c45 100644
--- a/drivers/tty/pty.c
+++ b/drivers/tty/pty.c
@@ -668,7 +668,7 @@
 	else
 		fsi = tty->link->driver_data;
 	devpts_kill_index(fsi, tty->index);
-	devpts_put_ref(fsi);
+	devpts_release(fsi);
 }
 
 static const struct tty_operations ptm_unix98_ops = {
@@ -733,10 +733,11 @@
 	if (retval)
 		return retval;
 
-	fsi = devpts_get_ref(inode, filp);
-	retval = -ENODEV;
-	if (!fsi)
+	fsi = devpts_acquire(filp);
+	if (IS_ERR(fsi)) {
+		retval = PTR_ERR(fsi);
 		goto out_free_file;
+	}
 
 	/* find a device that is not in use. */
 	mutex_lock(&devpts_mutex);
@@ -745,7 +746,7 @@
 
 	retval = index;
 	if (index < 0)
-		goto out_put_ref;
+		goto out_put_fsi;
 
 
 	mutex_lock(&tty_mutex);
@@ -789,8 +790,8 @@
 	return retval;
 out:
 	devpts_kill_index(fsi, index);
-out_put_ref:
-	devpts_put_ref(fsi);
+out_put_fsi:
+	devpts_release(fsi);
 out_free_file:
 	tty_free_file(filp);
 	return retval;
diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c
index 9360140..688691d 100644
--- a/drivers/vfio/pci/vfio_pci_config.c
+++ b/drivers/vfio/pci/vfio_pci_config.c
@@ -749,7 +749,8 @@
 		if (pci_write_vpd(pdev, addr & ~PCI_VPD_ADDR_F, 4, &data) != 4)
 			return count;
 	} else {
-		if (pci_read_vpd(pdev, addr, 4, &data) != 4)
+		data = 0;
+		if (pci_read_vpd(pdev, addr, 4, &data) < 0)
 			return count;
 		*pdata = cpu_to_le32(data);
 	}
diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
index e9ea3fe..15ecfc9 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -228,9 +228,9 @@
 
 static void vfio_intx_disable(struct vfio_pci_device *vdev)
 {
-	vfio_intx_set_signal(vdev, -1);
 	vfio_virqfd_disable(&vdev->ctx[0].unmask);
 	vfio_virqfd_disable(&vdev->ctx[0].mask);
+	vfio_intx_set_signal(vdev, -1);
 	vdev->irq_type = VFIO_PCI_NUM_IRQS;
 	vdev->num_ctx = 0;
 	kfree(vdev->ctx);
@@ -401,13 +401,13 @@
 	struct pci_dev *pdev = vdev->pdev;
 	int i;
 
-	vfio_msi_set_block(vdev, 0, vdev->num_ctx, NULL, msix);
-
 	for (i = 0; i < vdev->num_ctx; i++) {
 		vfio_virqfd_disable(&vdev->ctx[i].unmask);
 		vfio_virqfd_disable(&vdev->ctx[i].mask);
 	}
 
+	vfio_msi_set_block(vdev, 0, vdev->num_ctx, NULL, msix);
+
 	if (msix) {
 		pci_disable_msix(vdev->pdev);
 		kfree(vdev->msix);
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 15a6582..2ba1942 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -515,7 +515,7 @@
 			  unsigned long pfn, long npage, int prot)
 {
 	long i;
-	int ret;
+	int ret = 0;
 
 	for (i = 0; i < npage; i++, pfn++, iova += PAGE_SIZE) {
 		ret = iommu_map(domain->domain, iova,
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index f744eeb..1d3e45f 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -301,6 +301,32 @@
 	       !vhost_has_work(dev);
 }
 
+static void vhost_net_disable_vq(struct vhost_net *n,
+				 struct vhost_virtqueue *vq)
+{
+	struct vhost_net_virtqueue *nvq =
+		container_of(vq, struct vhost_net_virtqueue, vq);
+	struct vhost_poll *poll = n->poll + (nvq - n->vqs);
+	if (!vq->private_data)
+		return;
+	vhost_poll_stop(poll);
+}
+
+static int vhost_net_enable_vq(struct vhost_net *n,
+				struct vhost_virtqueue *vq)
+{
+	struct vhost_net_virtqueue *nvq =
+		container_of(vq, struct vhost_net_virtqueue, vq);
+	struct vhost_poll *poll = n->poll + (nvq - n->vqs);
+	struct socket *sock;
+
+	sock = vq->private_data;
+	if (!sock)
+		return 0;
+
+	return vhost_poll_start(poll, sock->file);
+}
+
 static int vhost_net_tx_get_vq_desc(struct vhost_net *net,
 				    struct vhost_virtqueue *vq,
 				    struct iovec iov[], unsigned int iov_size,
@@ -613,6 +639,7 @@
 	if (!sock)
 		goto out;
 	vhost_disable_notify(&net->dev, vq);
+	vhost_net_disable_vq(net, vq);
 
 	vhost_hlen = nvq->vhost_hlen;
 	sock_hlen = nvq->sock_hlen;
@@ -629,7 +656,7 @@
 					likely(mergeable) ? UIO_MAXIOV : 1);
 		/* On error, stop handling until the next kick. */
 		if (unlikely(headcount < 0))
-			break;
+			goto out;
 		/* On overrun, truncate and discard */
 		if (unlikely(headcount > UIO_MAXIOV)) {
 			iov_iter_init(&msg.msg_iter, READ, vq->iov, 1, 1);
@@ -648,7 +675,7 @@
 			}
 			/* Nothing new?  Wait for eventfd to tell us
 			 * they refilled. */
-			break;
+			goto out;
 		}
 		/* We don't need to be notified again. */
 		iov_iter_init(&msg.msg_iter, READ, vq->iov, in, vhost_len);
@@ -676,7 +703,7 @@
 					 &fixup) != sizeof(hdr)) {
 				vq_err(vq, "Unable to write vnet_hdr "
 				       "at addr %p\n", vq->iov->iov_base);
-				break;
+				goto out;
 			}
 		} else {
 			/* Header came from socket; we'll need to patch
@@ -692,7 +719,7 @@
 				 &fixup) != sizeof num_buffers) {
 			vq_err(vq, "Failed num_buffers write");
 			vhost_discard_vq_desc(vq, headcount);
-			break;
+			goto out;
 		}
 		vhost_add_used_and_signal_n(&net->dev, vq, vq->heads,
 					    headcount);
@@ -701,9 +728,10 @@
 		total_len += vhost_len;
 		if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
 			vhost_poll_queue(&vq->poll);
-			break;
+			goto out;
 		}
 	}
+	vhost_net_enable_vq(net, vq);
 out:
 	mutex_unlock(&vq->mutex);
 }
@@ -782,32 +810,6 @@
 	return 0;
 }
 
-static void vhost_net_disable_vq(struct vhost_net *n,
-				 struct vhost_virtqueue *vq)
-{
-	struct vhost_net_virtqueue *nvq =
-		container_of(vq, struct vhost_net_virtqueue, vq);
-	struct vhost_poll *poll = n->poll + (nvq - n->vqs);
-	if (!vq->private_data)
-		return;
-	vhost_poll_stop(poll);
-}
-
-static int vhost_net_enable_vq(struct vhost_net *n,
-				struct vhost_virtqueue *vq)
-{
-	struct vhost_net_virtqueue *nvq =
-		container_of(vq, struct vhost_net_virtqueue, vq);
-	struct vhost_poll *poll = n->poll + (nvq - n->vqs);
-	struct socket *sock;
-
-	sock = vq->private_data;
-	if (!sock)
-		return 0;
-
-	return vhost_poll_start(poll, sock->file);
-}
-
 static struct socket *vhost_net_stop_vq(struct vhost_net *n,
 					struct vhost_virtqueue *vq)
 {
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/hdmi5_core.c b/drivers/video/fbdev/omap2/omapfb/dss/hdmi5_core.c
index 8ea531d..bbfe7e2 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/hdmi5_core.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/hdmi5_core.c
@@ -51,8 +51,8 @@
 {
 	void __iomem *base = core->base;
 	const unsigned long long iclk = 266000000;	/* DSS L3 ICLK */
-	const unsigned ss_scl_high = 4000;		/* ns */
-	const unsigned ss_scl_low = 4700;		/* ns */
+	const unsigned ss_scl_high = 4600;		/* ns */
+	const unsigned ss_scl_low = 5400;		/* ns */
 	const unsigned fs_scl_high = 600;		/* ns */
 	const unsigned fs_scl_low = 1300;		/* ns */
 	const unsigned sda_hold = 1000;			/* ns */
@@ -442,7 +442,7 @@
 
 	c = (ptr[1] >> 6) & 0x3;
 	m = (ptr[1] >> 4) & 0x3;
-	r = (ptr[1] >> 0) & 0x3;
+	r = (ptr[1] >> 0) & 0xf;
 
 	itc = (ptr[2] >> 7) & 0x1;
 	ec = (ptr[2] >> 4) & 0x7;
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 63cd9f9..4832de84 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -85,18 +85,14 @@
 
 	skb_queue_head_init(&afs_incoming_calls);
 
+	ret = -ENOMEM;
 	afs_async_calls = create_singlethread_workqueue("kafsd");
-	if (!afs_async_calls) {
-		_leave(" = -ENOMEM [wq]");
-		return -ENOMEM;
-	}
+	if (!afs_async_calls)
+		goto error_0;
 
 	ret = sock_create_kern(&init_net, AF_RXRPC, SOCK_DGRAM, PF_INET, &socket);
-	if (ret < 0) {
-		destroy_workqueue(afs_async_calls);
-		_leave(" = %d [socket]", ret);
-		return ret;
-	}
+	if (ret < 0)
+		goto error_1;
 
 	socket->sk->sk_allocation = GFP_NOFS;
 
@@ -111,18 +107,26 @@
 	       sizeof(srx.transport.sin.sin_addr));
 
 	ret = kernel_bind(socket, (struct sockaddr *) &srx, sizeof(srx));
-	if (ret < 0) {
-		sock_release(socket);
-		destroy_workqueue(afs_async_calls);
-		_leave(" = %d [bind]", ret);
-		return ret;
-	}
+	if (ret < 0)
+		goto error_2;
+
+	ret = kernel_listen(socket, INT_MAX);
+	if (ret < 0)
+		goto error_2;
 
 	rxrpc_kernel_intercept_rx_messages(socket, afs_rx_interceptor);
 
 	afs_socket = socket;
 	_leave(" = 0");
 	return 0;
+
+error_2:
+	sock_release(socket);
+error_1:
+	destroy_workqueue(afs_async_calls);
+error_0:
+	_leave(" = %d", ret);
+	return ret;
 }
 
 /*
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index e158b22..a7a28110 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -2275,7 +2275,7 @@
 		goto end_coredump;
 
 	/* Align to page */
-	if (!dump_skip(cprm, dataoff - cprm->file->f_pos))
+	if (!dump_skip(cprm, dataoff - cprm->pos))
 		goto end_coredump;
 
 	for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 71ade0e..2035893 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -1787,7 +1787,7 @@
 				goto end_coredump;
 	}
 
-	if (!dump_skip(cprm, dataoff - cprm->file->f_pos))
+	if (!dump_skip(cprm, dataoff - cprm->pos))
 		goto end_coredump;
 
 	if (!elf_fdpic_dump_segments(cprm))
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index a400951..689d25a 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2042,6 +2042,11 @@
 	struct btrfs_bio *bbio = NULL;
 
 
+	/*
+	 * Avoid races with device replace and make sure our bbio has devices
+	 * associated to its stripes that don't go away while we are discarding.
+	 */
+	btrfs_bio_counter_inc_blocked(root->fs_info);
 	/* Tell the block device(s) that the sectors can be discarded */
 	ret = btrfs_map_block(root->fs_info, REQ_DISCARD,
 			      bytenr, &num_bytes, &bbio, 0);
@@ -2074,6 +2079,7 @@
 		}
 		btrfs_put_bbio(bbio);
 	}
+	btrfs_bio_counter_dec(root->fs_info);
 
 	if (actual_bytes)
 		*actual_bytes = discarded_bytes;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 3cd5782..6e953de 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2025,9 +2025,16 @@
 	bio->bi_iter.bi_size = 0;
 	map_length = length;
 
+	/*
+	 * Avoid races with device replace and make sure our bbio has devices
+	 * associated to its stripes that don't go away while we are doing the
+	 * read repair operation.
+	 */
+	btrfs_bio_counter_inc_blocked(fs_info);
 	ret = btrfs_map_block(fs_info, WRITE, logical,
 			      &map_length, &bbio, mirror_num);
 	if (ret) {
+		btrfs_bio_counter_dec(fs_info);
 		bio_put(bio);
 		return -EIO;
 	}
@@ -2037,6 +2044,7 @@
 	dev = bbio->stripes[mirror_num-1].dev;
 	btrfs_put_bbio(bbio);
 	if (!dev || !dev->bdev || !dev->writeable) {
+		btrfs_bio_counter_dec(fs_info);
 		bio_put(bio);
 		return -EIO;
 	}
@@ -2045,6 +2053,7 @@
 
 	if (btrfsic_submit_bio_wait(WRITE_SYNC, bio)) {
 		/* try to remap that extent elsewhere? */
+		btrfs_bio_counter_dec(fs_info);
 		bio_put(bio);
 		btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS);
 		return -EIO;
@@ -2054,6 +2063,7 @@
 		"read error corrected: ino %llu off %llu (dev %s sector %llu)",
 				  btrfs_ino(inode), start,
 				  rcu_str_deref(dev->name), sector);
+	btrfs_bio_counter_dec(fs_info);
 	bio_put(bio);
 	return 0;
 }
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 2704995..8b1212e 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6979,7 +6979,18 @@
 		 * existing will always be non-NULL, since there must be
 		 * extent causing the -EEXIST.
 		 */
-		if (start >= extent_map_end(existing) ||
+		if (existing->start == em->start &&
+		    extent_map_end(existing) == extent_map_end(em) &&
+		    em->block_start == existing->block_start) {
+			/*
+			 * these two extents are the same, it happens
+			 * with inlines especially
+			 */
+			free_extent_map(em);
+			em = existing;
+			err = 0;
+
+		} else if (start >= extent_map_end(existing) ||
 		    start <= existing->start) {
 			/*
 			 * The existing extent map is the one nearest to
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 5591704..e96634a 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -718,12 +718,13 @@
 	return count;
 }
 
-void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr,
+int btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr,
 			      const u64 range_start, const u64 range_len)
 {
 	struct btrfs_root *root;
 	struct list_head splice;
 	int done;
+	int total_done = 0;
 
 	INIT_LIST_HEAD(&splice);
 
@@ -742,6 +743,7 @@
 		done = btrfs_wait_ordered_extents(root, nr,
 						  range_start, range_len);
 		btrfs_put_fs_root(root);
+		total_done += done;
 
 		spin_lock(&fs_info->ordered_root_lock);
 		if (nr != -1) {
@@ -752,6 +754,8 @@
 	list_splice_tail(&splice, &fs_info->ordered_roots);
 	spin_unlock(&fs_info->ordered_root_lock);
 	mutex_unlock(&fs_info->ordered_operations_mutex);
+
+	return total_done;
 }
 
 /*
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index 2049c9b..4515077 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -199,7 +199,7 @@
 			   u32 *sum, int len);
 int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr,
 			       const u64 range_start, const u64 range_len);
-void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr,
+int btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr,
 			      const u64 range_start, const u64 range_len);
 void btrfs_get_logged_extents(struct inode *inode,
 			      struct list_head *logged_list,
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index 298631ea..8428db7 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -761,12 +761,14 @@
 
 	do {
 		enqueued = 0;
+		mutex_lock(&fs_devices->device_list_mutex);
 		list_for_each_entry(device, &fs_devices->devices, dev_list) {
 			if (atomic_read(&device->reada_in_flight) <
 			    MAX_IN_FLIGHT)
 				enqueued += reada_start_machine_dev(fs_info,
 								    device);
 		}
+		mutex_unlock(&fs_devices->device_list_mutex);
 		total += enqueued;
 	} while (enqueued && total < 10000);
 
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 46d847f..70427ef 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -3582,6 +3582,46 @@
 		 */
 		scrub_pause_on(fs_info);
 		ret = btrfs_inc_block_group_ro(root, cache);
+		if (!ret && is_dev_replace) {
+			/*
+			 * If we are doing a device replace wait for any tasks
+			 * that started dellaloc right before we set the block
+			 * group to RO mode, as they might have just allocated
+			 * an extent from it or decided they could do a nocow
+			 * write. And if any such tasks did that, wait for their
+			 * ordered extents to complete and then commit the
+			 * current transaction, so that we can later see the new
+			 * extent items in the extent tree - the ordered extents
+			 * create delayed data references (for cow writes) when
+			 * they complete, which will be run and insert the
+			 * corresponding extent items into the extent tree when
+			 * we commit the transaction they used when running
+			 * inode.c:btrfs_finish_ordered_io(). We later use
+			 * the commit root of the extent tree to find extents
+			 * to copy from the srcdev into the tgtdev, and we don't
+			 * want to miss any new extents.
+			 */
+			btrfs_wait_block_group_reservations(cache);
+			btrfs_wait_nocow_writers(cache);
+			ret = btrfs_wait_ordered_roots(fs_info, -1,
+						       cache->key.objectid,
+						       cache->key.offset);
+			if (ret > 0) {
+				struct btrfs_trans_handle *trans;
+
+				trans = btrfs_join_transaction(root);
+				if (IS_ERR(trans))
+					ret = PTR_ERR(trans);
+				else
+					ret = btrfs_commit_transaction(trans,
+								       root);
+				if (ret) {
+					scrub_pause_off(fs_info);
+					btrfs_put_block_group(cache);
+					break;
+				}
+			}
+		}
 		scrub_pause_off(fs_info);
 
 		if (ret == 0) {
@@ -3602,9 +3642,11 @@
 			break;
 		}
 
+		btrfs_dev_replace_lock(&fs_info->dev_replace, 1);
 		dev_replace->cursor_right = found_key.offset + length;
 		dev_replace->cursor_left = found_key.offset;
 		dev_replace->item_needs_writeback = 1;
+		btrfs_dev_replace_unlock(&fs_info->dev_replace, 1);
 		ret = scrub_chunk(sctx, scrub_dev, chunk_offset, length,
 				  found_key.offset, cache, is_dev_replace);
 
@@ -3640,6 +3682,11 @@
 
 		scrub_pause_off(fs_info);
 
+		btrfs_dev_replace_lock(&fs_info->dev_replace, 1);
+		dev_replace->cursor_left = dev_replace->cursor_right;
+		dev_replace->item_needs_writeback = 1;
+		btrfs_dev_replace_unlock(&fs_info->dev_replace, 1);
+
 		if (ro_set)
 			btrfs_dec_block_group_ro(root, cache);
 
@@ -3677,9 +3724,6 @@
 			ret = -ENOMEM;
 			break;
 		}
-
-		dev_replace->cursor_left = dev_replace->cursor_right;
-		dev_replace->item_needs_writeback = 1;
 skip:
 		key.offset = found_key.offset + length;
 		btrfs_release_path(path);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index bdc6256..da9e003 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2761,6 +2761,7 @@
 	u64 dev_extent_len = 0;
 	u64 chunk_objectid = BTRFS_FIRST_CHUNK_TREE_OBJECTID;
 	int i, ret = 0;
+	struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices;
 
 	/* Just in case */
 	root = root->fs_info->chunk_root;
@@ -2787,12 +2788,19 @@
 	check_system_chunk(trans, extent_root, map->type);
 	unlock_chunks(root->fs_info->chunk_root);
 
+	/*
+	 * Take the device list mutex to prevent races with the final phase of
+	 * a device replace operation that replaces the device object associated
+	 * with map stripes (dev-replace.c:btrfs_dev_replace_finishing()).
+	 */
+	mutex_lock(&fs_devices->device_list_mutex);
 	for (i = 0; i < map->num_stripes; i++) {
 		struct btrfs_device *device = map->stripes[i].dev;
 		ret = btrfs_free_dev_extent(trans, device,
 					    map->stripes[i].physical,
 					    &dev_extent_len);
 		if (ret) {
+			mutex_unlock(&fs_devices->device_list_mutex);
 			btrfs_abort_transaction(trans, root, ret);
 			goto out;
 		}
@@ -2811,11 +2819,14 @@
 		if (map->stripes[i].dev) {
 			ret = btrfs_update_device(trans, map->stripes[i].dev);
 			if (ret) {
+				mutex_unlock(&fs_devices->device_list_mutex);
 				btrfs_abort_transaction(trans, root, ret);
 				goto out;
 			}
 		}
 	}
+	mutex_unlock(&fs_devices->device_list_mutex);
+
 	ret = btrfs_free_chunk(trans, root, chunk_objectid, chunk_offset);
 	if (ret) {
 		btrfs_abort_transaction(trans, root, ret);
@@ -5762,20 +5773,17 @@
 			}
 		}
 		if (found) {
-			if (physical_of_found + map->stripe_len <=
-			    dev_replace->cursor_left) {
-				struct btrfs_bio_stripe *tgtdev_stripe =
-					bbio->stripes + num_stripes;
+			struct btrfs_bio_stripe *tgtdev_stripe =
+				bbio->stripes + num_stripes;
 
-				tgtdev_stripe->physical = physical_of_found;
-				tgtdev_stripe->length =
-					bbio->stripes[index_srcdev].length;
-				tgtdev_stripe->dev = dev_replace->tgtdev;
-				bbio->tgtdev_map[index_srcdev] = num_stripes;
+			tgtdev_stripe->physical = physical_of_found;
+			tgtdev_stripe->length =
+				bbio->stripes[index_srcdev].length;
+			tgtdev_stripe->dev = dev_replace->tgtdev;
+			bbio->tgtdev_map[index_srcdev] = num_stripes;
 
-				tgtdev_indexes++;
-				num_stripes++;
-			}
+			tgtdev_indexes++;
+			num_stripes++;
 		}
 	}
 
diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c
index 861d611..ce5f345 100644
--- a/fs/cachefiles/interface.c
+++ b/fs/cachefiles/interface.c
@@ -380,7 +380,7 @@
  * check if the backing cache is updated to FS-Cache
  * - called by FS-Cache when evaluates if need to invalidate the cache
  */
-static bool cachefiles_check_consistency(struct fscache_operation *op)
+static int cachefiles_check_consistency(struct fscache_operation *op)
 {
 	struct cachefiles_object *object;
 	struct cachefiles_cache *cache;
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index eeb71e5..26a9d10 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -276,8 +276,10 @@
 	for (i = 0; i < num_pages; i++) {
 		struct page *page = osd_data->pages[i];
 
-		if (rc < 0 && rc != -ENOENT)
+		if (rc < 0 && rc != -ENOENT) {
+			ceph_fscache_readpage_cancel(inode, page);
 			goto unlock;
+		}
 		if (bytes < (int)PAGE_SIZE) {
 			/* zero (remainder of) page */
 			int s = bytes < 0 ? 0 : bytes;
@@ -535,8 +537,6 @@
 	    CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb))
 		set_bdi_congested(&fsc->backing_dev_info, BLK_RW_ASYNC);
 
-	ceph_readpage_to_fscache(inode, page);
-
 	set_page_writeback(page);
 	err = ceph_osdc_writepages(osdc, ceph_vino(inode),
 				   &ci->i_layout, snapc,
diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c
index c052b5b..238c55b 100644
--- a/fs/ceph/cache.c
+++ b/fs/ceph/cache.c
@@ -25,6 +25,7 @@
 #include "cache.h"
 
 struct ceph_aux_inode {
+	u64 		version;
 	struct timespec	mtime;
 	loff_t          size;
 };
@@ -69,15 +70,8 @@
 	fsc->fscache = fscache_acquire_cookie(ceph_cache_netfs.primary_index,
 					      &ceph_fscache_fsid_object_def,
 					      fsc, true);
-
-	if (fsc->fscache == NULL) {
+	if (!fsc->fscache)
 		pr_err("Unable to resgister fsid: %p fscache cookie", fsc);
-		return 0;
-	}
-
-	fsc->revalidate_wq = alloc_workqueue("ceph-revalidate", 0, 1);
-	if (fsc->revalidate_wq == NULL)
-		return -ENOMEM;
 
 	return 0;
 }
@@ -105,6 +99,7 @@
 	const struct inode* inode = &ci->vfs_inode;
 
 	memset(&aux, 0, sizeof(aux));
+	aux.version = ci->i_version;
 	aux.mtime = inode->i_mtime;
 	aux.size = i_size_read(inode);
 
@@ -131,6 +126,7 @@
 		return FSCACHE_CHECKAUX_OBSOLETE;
 
 	memset(&aux, 0, sizeof(aux));
+	aux.version = ci->i_version;
 	aux.mtime = inode->i_mtime;
 	aux.size = i_size_read(inode);
 
@@ -181,32 +177,26 @@
 	.now_uncached	= ceph_fscache_inode_now_uncached,
 };
 
-void ceph_fscache_register_inode_cookie(struct ceph_fs_client* fsc,
-					struct ceph_inode_info* ci)
+void ceph_fscache_register_inode_cookie(struct inode *inode)
 {
-	struct inode* inode = &ci->vfs_inode;
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
 
 	/* No caching for filesystem */
 	if (fsc->fscache == NULL)
 		return;
 
 	/* Only cache for regular files that are read only */
-	if ((ci->vfs_inode.i_mode & S_IFREG) == 0)
+	if (!S_ISREG(inode->i_mode))
 		return;
 
-	/* Avoid multiple racing open requests */
-	inode_lock(inode);
-
-	if (ci->fscache)
-		goto done;
-
-	ci->fscache = fscache_acquire_cookie(fsc->fscache,
-					     &ceph_fscache_inode_object_def,
-					     ci, true);
-	fscache_check_consistency(ci->fscache);
-done:
+	inode_lock_nested(inode, I_MUTEX_CHILD);
+	if (!ci->fscache) {
+		ci->fscache = fscache_acquire_cookie(fsc->fscache,
+					&ceph_fscache_inode_object_def,
+					ci, false);
+	}
 	inode_unlock(inode);
-
 }
 
 void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci)
@@ -222,6 +212,34 @@
 	fscache_relinquish_cookie(cookie, 0);
 }
 
+static bool ceph_fscache_can_enable(void *data)
+{
+	struct inode *inode = data;
+	return !inode_is_open_for_write(inode);
+}
+
+void ceph_fscache_file_set_cookie(struct inode *inode, struct file *filp)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+
+	if (!fscache_cookie_valid(ci->fscache))
+		return;
+
+	if (inode_is_open_for_write(inode)) {
+		dout("fscache_file_set_cookie %p %p disabling cache\n",
+		     inode, filp);
+		fscache_disable_cookie(ci->fscache, false);
+		fscache_uncache_all_inode_pages(ci->fscache, inode);
+	} else {
+		fscache_enable_cookie(ci->fscache, ceph_fscache_can_enable,
+				inode);
+		if (fscache_cookie_enabled(ci->fscache)) {
+			dout("fscache_file_set_cookie %p %p enabing cache\n",
+			     inode, filp);
+		}
+	}
+}
+
 static void ceph_vfs_readpage_complete(struct page *page, void *data, int error)
 {
 	if (!error)
@@ -238,8 +256,7 @@
 
 static inline bool cache_valid(struct ceph_inode_info *ci)
 {
-	return ((ceph_caps_issued(ci) & CEPH_CAP_FILE_CACHE) &&
-		(ci->i_fscache_gen == ci->i_rdcache_gen));
+	return ci->i_fscache_gen == ci->i_rdcache_gen;
 }
 
 
@@ -332,69 +349,27 @@
 
 void ceph_fscache_unregister_fs(struct ceph_fs_client* fsc)
 {
-	if (fsc->revalidate_wq)
-		destroy_workqueue(fsc->revalidate_wq);
-
 	fscache_relinquish_cookie(fsc->fscache, 0);
 	fsc->fscache = NULL;
 }
 
-static void ceph_revalidate_work(struct work_struct *work)
+/*
+ * caller should hold CEPH_CAP_FILE_{RD,CACHE}
+ */
+void ceph_fscache_revalidate_cookie(struct ceph_inode_info *ci)
 {
-	int issued;
-	u32 orig_gen;
-	struct ceph_inode_info *ci = container_of(work, struct ceph_inode_info,
-						  i_revalidate_work);
-	struct inode *inode = &ci->vfs_inode;
-
-	spin_lock(&ci->i_ceph_lock);
-	issued = __ceph_caps_issued(ci, NULL);
-	orig_gen = ci->i_rdcache_gen;
-	spin_unlock(&ci->i_ceph_lock);
-
-	if (!(issued & CEPH_CAP_FILE_CACHE)) {
-		dout("revalidate_work lost cache before validation %p\n",
-		     inode);
-		goto out;
-	}
-
-	if (!fscache_check_consistency(ci->fscache))
-		fscache_invalidate(ci->fscache);
-
-	spin_lock(&ci->i_ceph_lock);
-	/* Update the new valid generation (backwards sanity check too) */
-	if (orig_gen > ci->i_fscache_gen) {
-		ci->i_fscache_gen = orig_gen;
-	}
-	spin_unlock(&ci->i_ceph_lock);
-
-out:
-	iput(&ci->vfs_inode);
-}
-
-void ceph_queue_revalidate(struct inode *inode)
-{
-	struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
-	struct ceph_inode_info *ci = ceph_inode(inode);
-
-	if (fsc->revalidate_wq == NULL || ci->fscache == NULL)
+	if (cache_valid(ci))
 		return;
 
-	ihold(inode);
-
-	if (queue_work(ceph_sb_to_client(inode->i_sb)->revalidate_wq,
-		       &ci->i_revalidate_work)) {
-		dout("ceph_queue_revalidate %p\n", inode);
-	} else {
-		dout("ceph_queue_revalidate %p failed\n)", inode);
-		iput(inode);
+	/* resue i_truncate_mutex. There should be no pending
+	 * truncate while the caller holds CEPH_CAP_FILE_RD */
+	mutex_lock(&ci->i_truncate_mutex);
+	if (!cache_valid(ci)) {
+		if (fscache_check_consistency(ci->fscache))
+			fscache_invalidate(ci->fscache);
+		spin_lock(&ci->i_ceph_lock);
+		ci->i_fscache_gen = ci->i_rdcache_gen;
+		spin_unlock(&ci->i_ceph_lock);
 	}
-}
-
-void ceph_fscache_inode_init(struct ceph_inode_info *ci)
-{
-	ci->fscache = NULL;
-	/* The first load is verifed cookie open time */
-	ci->i_fscache_gen = 1;
-	INIT_WORK(&ci->i_revalidate_work, ceph_revalidate_work);
+	mutex_unlock(&ci->i_truncate_mutex);
 }
diff --git a/fs/ceph/cache.h b/fs/ceph/cache.h
index 5ac591b..7e72c75 100644
--- a/fs/ceph/cache.h
+++ b/fs/ceph/cache.h
@@ -34,10 +34,10 @@
 int ceph_fscache_register_fs(struct ceph_fs_client* fsc);
 void ceph_fscache_unregister_fs(struct ceph_fs_client* fsc);
 
-void ceph_fscache_inode_init(struct ceph_inode_info *ci);
-void ceph_fscache_register_inode_cookie(struct ceph_fs_client* fsc,
-					struct ceph_inode_info* ci);
+void ceph_fscache_register_inode_cookie(struct inode *inode);
 void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci);
+void ceph_fscache_file_set_cookie(struct inode *inode, struct file *filp);
+void ceph_fscache_revalidate_cookie(struct ceph_inode_info *ci);
 
 int ceph_readpage_from_fscache(struct inode *inode, struct page *page);
 int ceph_readpages_from_fscache(struct inode *inode,
@@ -46,12 +46,11 @@
 				unsigned *nr_pages);
 void ceph_readpage_to_fscache(struct inode *inode, struct page *page);
 void ceph_invalidate_fscache_page(struct inode* inode, struct page *page);
-void ceph_queue_revalidate(struct inode *inode);
 
-static inline void ceph_fscache_update_objectsize(struct inode *inode)
+static inline void ceph_fscache_inode_init(struct ceph_inode_info *ci)
 {
-	struct ceph_inode_info *ci = ceph_inode(inode);
-	fscache_attr_changed(ci->fscache);
+	ci->fscache = NULL;
+	ci->i_fscache_gen = 0;
 }
 
 static inline void ceph_fscache_invalidate(struct inode *inode)
@@ -88,6 +87,11 @@
 	return fscache_readpages_cancel(ci->fscache, pages);
 }
 
+static inline void ceph_disable_fscache_readpage(struct ceph_inode_info *ci)
+{
+	ci->i_fscache_gen = ci->i_rdcache_gen - 1;
+}
+
 #else
 
 static inline int ceph_fscache_register(void)
@@ -112,8 +116,20 @@
 {
 }
 
-static inline void ceph_fscache_register_inode_cookie(struct ceph_fs_client* parent_fsc,
-						      struct ceph_inode_info* ci)
+static inline void ceph_fscache_register_inode_cookie(struct inode *inode)
+{
+}
+
+static inline void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci)
+{
+}
+
+static inline void ceph_fscache_file_set_cookie(struct inode *inode,
+						struct file *filp)
+{
+}
+
+static inline void ceph_fscache_revalidate_cookie(struct ceph_inode_info *ci)
 {
 }
 
@@ -141,10 +157,6 @@
 {
 }
 
-static inline void ceph_fscache_update_objectsize(struct inode *inode)
-{
-}
-
 static inline void ceph_fscache_invalidate(struct inode *inode)
 {
 }
@@ -154,10 +166,6 @@
 {
 }
 
-static inline void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci)
-{
-}
-
 static inline int ceph_release_fscache_page(struct page *page, gfp_t gfp)
 {
 	return 1;
@@ -173,7 +181,7 @@
 {
 }
 
-static inline void ceph_queue_revalidate(struct inode *inode)
+static inline void ceph_disable_fscache_readpage(struct ceph_inode_info *ci)
 {
 }
 
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index c17b5d7..6f60d0a 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -2393,6 +2393,9 @@
 				snap_rwsem_locked = true;
 			}
 			*got = need | (have & want);
+			if ((need & CEPH_CAP_FILE_RD) &&
+			    !(*got & CEPH_CAP_FILE_CACHE))
+				ceph_disable_fscache_readpage(ci);
 			__take_cap_refs(ci, *got, true);
 			ret = 1;
 		}
@@ -2554,6 +2557,9 @@
 		break;
 	}
 
+	if ((_got & CEPH_CAP_FILE_RD) && (_got & CEPH_CAP_FILE_CACHE))
+		ceph_fscache_revalidate_cookie(ci);
+
 	*got = _got;
 	return 0;
 }
@@ -2795,7 +2801,6 @@
 	bool writeback = false;
 	bool queue_trunc = false;
 	bool queue_invalidate = false;
-	bool queue_revalidate = false;
 	bool deleted_inode = false;
 	bool fill_inline = false;
 
@@ -2837,8 +2842,6 @@
 				ci->i_rdcache_revoking = ci->i_rdcache_gen;
 			}
 		}
-
-		ceph_fscache_invalidate(inode);
 	}
 
 	/* side effects now are allowed */
@@ -2880,11 +2883,6 @@
 		}
 	}
 
-	/* Do we need to revalidate our fscache cookie. Don't bother on the
-	 * first cache cap as we already validate at cookie creation time. */
-	if ((issued & CEPH_CAP_FILE_CACHE) && ci->i_rdcache_gen > 1)
-		queue_revalidate = true;
-
 	if (newcaps & CEPH_CAP_ANY_RD) {
 		/* ctime/mtime/atime? */
 		ceph_decode_timespec(&mtime, &grant->mtime);
@@ -2993,11 +2991,8 @@
 	if (fill_inline)
 		ceph_fill_inline_data(inode, NULL, inline_data, inline_len);
 
-	if (queue_trunc) {
+	if (queue_trunc)
 		ceph_queue_vmtruncate(inode);
-		ceph_queue_revalidate(inode);
-	} else if (queue_revalidate)
-		ceph_queue_revalidate(inode);
 
 	if (writeback)
 		/*
@@ -3199,10 +3194,8 @@
 					  truncate_seq, truncate_size, size);
 	spin_unlock(&ci->i_ceph_lock);
 
-	if (queue_trunc) {
+	if (queue_trunc)
 		ceph_queue_vmtruncate(inode);
-		ceph_fscache_invalidate(inode);
-	}
 }
 
 /*
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index a888df6..ce2f579 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -137,23 +137,11 @@
 {
 	struct ceph_file_info *cf;
 	int ret = 0;
-	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
-	struct ceph_mds_client *mdsc = fsc->mdsc;
 
 	switch (inode->i_mode & S_IFMT) {
 	case S_IFREG:
-		/* First file open request creates the cookie, we want to keep
-		 * this cookie around for the filetime of the inode as not to
-		 * have to worry about fscache register / revoke / operation
-		 * races.
-		 *
-		 * Also, if we know the operation is going to invalidate data
-		 * (non readonly) just nuke the cache right away.
-		 */
-		ceph_fscache_register_inode_cookie(mdsc->fsc, ci);
-		if ((fmode & CEPH_FILE_MODE_WR))
-			ceph_fscache_invalidate(inode);
+		ceph_fscache_register_inode_cookie(inode);
+		ceph_fscache_file_set_cookie(inode, file);
 	case S_IFDIR:
 		dout("init_file %p %p 0%o (regular)\n", inode, file,
 		     inode->i_mode);
@@ -1349,7 +1337,7 @@
 	}
 
 retry_snap:
-	if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL)) {
+	if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL)) {
 		err = -ENOSPC;
 		goto out;
 	}
@@ -1407,7 +1395,6 @@
 			iov_iter_advance(from, written);
 		ceph_put_snap_context(snapc);
 	} else {
-		loff_t old_size = i_size_read(inode);
 		/*
 		 * No need to acquire the i_truncate_mutex. Because
 		 * the MDS revokes Fwb caps before sending truncate
@@ -1418,8 +1405,6 @@
 		written = generic_perform_write(file, from, pos);
 		if (likely(written >= 0))
 			iocb->ki_pos = pos + written;
-		if (i_size_read(inode) > old_size)
-			ceph_fscache_update_objectsize(inode);
 		inode_unlock(inode);
 	}
 
@@ -1440,7 +1425,7 @@
 	ceph_put_cap_refs(ci, got);
 
 	if (written >= 0) {
-		if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_NEARFULL))
+		if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_NEARFULL))
 			iocb->ki_flags |= IOCB_DSYNC;
 
 		written = generic_write_sync(iocb, written);
@@ -1672,8 +1657,8 @@
 		goto unlock;
 	}
 
-	if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL) &&
-		!(mode & FALLOC_FL_PUNCH_HOLE)) {
+	if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) &&
+	    !(mode & FALLOC_FL_PUNCH_HOLE)) {
 		ret = -ENOSPC;
 		goto unlock;
 	}
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 0130a85..0168b49 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -103,7 +103,6 @@
 
 #ifdef CONFIG_CEPH_FSCACHE
 	struct fscache_cookie *fscache;
-	struct workqueue_struct *revalidate_wq;
 #endif
 };
 
@@ -360,8 +359,7 @@
 
 #ifdef CONFIG_CEPH_FSCACHE
 	struct fscache_cookie *fscache;
-	u32 i_fscache_gen; /* sequence, for delayed fscache validate */
-	struct work_struct i_revalidate_work;
+	u32 i_fscache_gen;
 #endif
 	struct inode vfs_inode; /* at end */
 };
diff --git a/fs/coredump.c b/fs/coredump.c
index 38a7ab8..281b768 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -794,6 +794,7 @@
 			return 0;
 		file->f_pos = pos;
 		cprm->written += n;
+		cprm->pos += n;
 		nr -= n;
 	}
 	return 1;
@@ -808,6 +809,7 @@
 		if (dump_interrupted() ||
 		    file->f_op->llseek(file, nr, SEEK_CUR) < 0)
 			return 0;
+		cprm->pos += nr;
 		return 1;
 	} else {
 		while (nr > PAGE_SIZE) {
@@ -822,7 +824,7 @@
 
 int dump_align(struct coredump_params *cprm, int align)
 {
-	unsigned mod = cprm->file->f_pos & (align - 1);
+	unsigned mod = cprm->pos & (align - 1);
 	if (align & (align - 1))
 		return 0;
 	return mod ? dump_skip(cprm, align - mod) : 1;
diff --git a/fs/dcache.c b/fs/dcache.c
index ad4a542..817c243 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1636,7 +1636,7 @@
 	struct dentry *dentry = __d_alloc(parent->d_sb, name);
 	if (!dentry)
 		return NULL;
-
+	dentry->d_flags |= DCACHE_RCUACCESS;
 	spin_lock(&parent->d_lock);
 	/*
 	 * don't need child lock because it is not subject
@@ -2358,7 +2358,6 @@
 {
 	BUG_ON(!d_unhashed(entry));
 	hlist_bl_lock(b);
-	entry->d_flags |= DCACHE_RCUACCESS;
 	hlist_bl_add_head_rcu(&entry->d_hash, b);
 	hlist_bl_unlock(b);
 }
@@ -2843,6 +2842,7 @@
 	/* ... and switch them in the tree */
 	if (IS_ROOT(dentry)) {
 		/* splicing a tree */
+		dentry->d_flags |= DCACHE_RCUACCESS;
 		dentry->d_parent = target->d_parent;
 		target->d_parent = target;
 		list_del_init(&target->d_child);
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 0b2954d..37c134a 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -95,8 +95,6 @@
 
 static DEFINE_MUTEX(allocated_ptys_lock);
 
-static struct vfsmount *devpts_mnt;
-
 struct pts_mount_opts {
 	int setuid;
 	int setgid;
@@ -104,7 +102,7 @@
 	kgid_t   gid;
 	umode_t mode;
 	umode_t ptmxmode;
-	int newinstance;
+	int reserve;
 	int max;
 };
 
@@ -117,11 +115,9 @@
 	{Opt_uid, "uid=%u"},
 	{Opt_gid, "gid=%u"},
 	{Opt_mode, "mode=%o"},
-#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
 	{Opt_ptmxmode, "ptmxmode=%o"},
 	{Opt_newinstance, "newinstance"},
 	{Opt_max, "max=%d"},
-#endif
 	{Opt_err, NULL}
 };
 
@@ -137,15 +133,48 @@
 	return sb->s_fs_info;
 }
 
-static inline struct super_block *pts_sb_from_inode(struct inode *inode)
+struct pts_fs_info *devpts_acquire(struct file *filp)
 {
-#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
-	if (inode->i_sb->s_magic == DEVPTS_SUPER_MAGIC)
-		return inode->i_sb;
-#endif
-	if (!devpts_mnt)
-		return NULL;
-	return devpts_mnt->mnt_sb;
+	struct pts_fs_info *result;
+	struct path path;
+	struct super_block *sb;
+	int err;
+
+	path = filp->f_path;
+	path_get(&path);
+
+	/* Has the devpts filesystem already been found? */
+	sb = path.mnt->mnt_sb;
+	if (sb->s_magic != DEVPTS_SUPER_MAGIC) {
+		/* Is a devpts filesystem at "pts" in the same directory? */
+		err = path_pts(&path);
+		if (err) {
+			result = ERR_PTR(err);
+			goto out;
+		}
+
+		/* Is the path the root of a devpts filesystem? */
+		result = ERR_PTR(-ENODEV);
+		sb = path.mnt->mnt_sb;
+		if ((sb->s_magic != DEVPTS_SUPER_MAGIC) ||
+		    (path.mnt->mnt_root != sb->s_root))
+			goto out;
+	}
+
+	/*
+	 * pty code needs to hold extra references in case of last /dev/tty close
+	 */
+	atomic_inc(&sb->s_active);
+	result = DEVPTS_SB(sb);
+
+out:
+	path_put(&path);
+	return result;
+}
+
+void devpts_release(struct pts_fs_info *fsi)
+{
+	deactivate_super(fsi->sb);
 }
 
 #define PARSE_MOUNT	0
@@ -154,9 +183,7 @@
 /*
  * parse_mount_options():
  *	Set @opts to mount options specified in @data. If an option is not
- *	specified in @data, set it to its default value. The exception is
- *	'newinstance' option which can only be set/cleared on a mount (i.e.
- *	cannot be changed during remount).
+ *	specified in @data, set it to its default value.
  *
  * Note: @data may be NULL (in which case all options are set to default).
  */
@@ -174,9 +201,12 @@
 	opts->ptmxmode = DEVPTS_DEFAULT_PTMX_MODE;
 	opts->max     = NR_UNIX98_PTY_MAX;
 
-	/* newinstance makes sense only on initial mount */
+	/* Only allow instances mounted from the initial mount
+	 * namespace to tap the reserve pool of ptys.
+	 */
 	if (op == PARSE_MOUNT)
-		opts->newinstance = 0;
+		opts->reserve =
+			(current->nsproxy->mnt_ns == init_task.nsproxy->mnt_ns);
 
 	while ((p = strsep(&data, ",")) != NULL) {
 		substring_t args[MAX_OPT_ARGS];
@@ -211,16 +241,12 @@
 				return -EINVAL;
 			opts->mode = option & S_IALLUGO;
 			break;
-#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
 		case Opt_ptmxmode:
 			if (match_octal(&args[0], &option))
 				return -EINVAL;
 			opts->ptmxmode = option & S_IALLUGO;
 			break;
 		case Opt_newinstance:
-			/* newinstance makes sense only on initial mount */
-			if (op == PARSE_MOUNT)
-				opts->newinstance = 1;
 			break;
 		case Opt_max:
 			if (match_int(&args[0], &option) ||
@@ -228,7 +254,6 @@
 				return -EINVAL;
 			opts->max = option;
 			break;
-#endif
 		default:
 			pr_err("called with bogus options\n");
 			return -EINVAL;
@@ -238,7 +263,6 @@
 	return 0;
 }
 
-#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
 static int mknod_ptmx(struct super_block *sb)
 {
 	int mode;
@@ -305,12 +329,6 @@
 		inode->i_mode = S_IFCHR|fsi->mount_opts.ptmxmode;
 	}
 }
-#else
-static inline void update_ptmx_mode(struct pts_fs_info *fsi)
-{
-	return;
-}
-#endif
 
 static int devpts_remount(struct super_block *sb, int *flags, char *data)
 {
@@ -344,11 +362,9 @@
 		seq_printf(seq, ",gid=%u",
 			   from_kgid_munged(&init_user_ns, opts->gid));
 	seq_printf(seq, ",mode=%03o", opts->mode);
-#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
 	seq_printf(seq, ",ptmxmode=%03o", opts->ptmxmode);
 	if (opts->max < NR_UNIX98_PTY_MAX)
 		seq_printf(seq, ",max=%d", opts->max);
-#endif
 
 	return 0;
 }
@@ -410,40 +426,11 @@
 	return -ENOMEM;
 }
 
-#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
-static int compare_init_pts_sb(struct super_block *s, void *p)
-{
-	if (devpts_mnt)
-		return devpts_mnt->mnt_sb == s;
-	return 0;
-}
-
 /*
  * devpts_mount()
  *
- *     If the '-o newinstance' mount option was specified, mount a new
- *     (private) instance of devpts.  PTYs created in this instance are
- *     independent of the PTYs in other devpts instances.
- *
- *     If the '-o newinstance' option was not specified, mount/remount the
- *     initial kernel mount of devpts.  This type of mount gives the
- *     legacy, single-instance semantics.
- *
- *     The 'newinstance' option is needed to support multiple namespace
- *     semantics in devpts while preserving backward compatibility of the
- *     current 'single-namespace' semantics. i.e all mounts of devpts
- *     without the 'newinstance' mount option should bind to the initial
- *     kernel mount, like mount_single().
- *
- *     Mounts with 'newinstance' option create a new, private namespace.
- *
- *     NOTE:
- *
- *     For single-mount semantics, devpts cannot use mount_single(),
- *     because mount_single()/sget() find and use the super-block from
- *     the most recent mount of devpts. But that recent mount may be a
- *     'newinstance' mount and mount_single() would pick the newinstance
- *     super-block instead of the initial super-block.
+ *     Mount a new (private) instance of devpts.  PTYs created in this
+ *     instance are independent of the PTYs in other devpts instances.
  */
 static struct dentry *devpts_mount(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *data)
@@ -456,18 +443,7 @@
 	if (error)
 		return ERR_PTR(error);
 
-	/* Require newinstance for all user namespace mounts to ensure
-	 * the mount options are not changed.
-	 */
-	if ((current_user_ns() != &init_user_ns) && !opts.newinstance)
-		return ERR_PTR(-EINVAL);
-
-	if (opts.newinstance)
-		s = sget(fs_type, NULL, set_anon_super, flags, NULL);
-	else
-		s = sget(fs_type, compare_init_pts_sb, set_anon_super, flags,
-			 NULL);
-
+	s = sget(fs_type, NULL, set_anon_super, flags, NULL);
 	if (IS_ERR(s))
 		return ERR_CAST(s);
 
@@ -491,18 +467,6 @@
 	return ERR_PTR(error);
 }
 
-#else
-/*
- * This supports only the legacy single-instance semantics (no
- * multiple-instance semantics)
- */
-static struct dentry *devpts_mount(struct file_system_type *fs_type, int flags,
-		const char *dev_name, void *data)
-{
-	return mount_single(fs_type, flags, data, devpts_fill_super);
-}
-#endif
-
 static void devpts_kill_sb(struct super_block *sb)
 {
 	struct pts_fs_info *fsi = DEVPTS_SB(sb);
@@ -516,9 +480,7 @@
 	.name		= "devpts",
 	.mount		= devpts_mount,
 	.kill_sb	= devpts_kill_sb,
-#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
 	.fs_flags	= FS_USERNS_MOUNT | FS_USERNS_DEV_MOUNT,
-#endif
 };
 
 /*
@@ -531,16 +493,13 @@
 	int index;
 	int ida_ret;
 
-	if (!fsi)
-		return -ENODEV;
-
 retry:
 	if (!ida_pre_get(&fsi->allocated_ptys, GFP_KERNEL))
 		return -ENOMEM;
 
 	mutex_lock(&allocated_ptys_lock);
-	if (pty_count >= pty_limit -
-			(fsi->mount_opts.newinstance ? pty_reserve : 0)) {
+	if (pty_count >= (pty_limit -
+			  (fsi->mount_opts.reserve ? 0 : pty_reserve))) {
 		mutex_unlock(&allocated_ptys_lock);
 		return -ENOSPC;
 	}
@@ -571,30 +530,6 @@
 	mutex_unlock(&allocated_ptys_lock);
 }
 
-/*
- * pty code needs to hold extra references in case of last /dev/tty close
- */
-struct pts_fs_info *devpts_get_ref(struct inode *ptmx_inode, struct file *file)
-{
-	struct super_block *sb;
-	struct pts_fs_info *fsi;
-
-	sb = pts_sb_from_inode(ptmx_inode);
-	if (!sb)
-		return NULL;
-	fsi = DEVPTS_SB(sb);
-	if (!fsi)
-		return NULL;
-
-	atomic_inc(&sb->s_active);
-	return fsi;
-}
-
-void devpts_put_ref(struct pts_fs_info *fsi)
-{
-	deactivate_super(fsi->sb);
-}
-
 /**
  * devpts_pty_new -- create a new inode in /dev/pts/
  * @ptmx_inode: inode of the master
@@ -607,16 +542,12 @@
 struct dentry *devpts_pty_new(struct pts_fs_info *fsi, int index, void *priv)
 {
 	struct dentry *dentry;
-	struct super_block *sb;
+	struct super_block *sb = fsi->sb;
 	struct inode *inode;
 	struct dentry *root;
 	struct pts_mount_opts *opts;
 	char s[12];
 
-	if (!fsi)
-		return ERR_PTR(-ENODEV);
-
-	sb = fsi->sb;
 	root = sb->s_root;
 	opts = &fsi->mount_opts;
 
@@ -676,20 +607,8 @@
 static int __init init_devpts_fs(void)
 {
 	int err = register_filesystem(&devpts_fs_type);
-	struct ctl_table_header *table;
-
 	if (!err) {
-		struct vfsmount *mnt;
-
-		table = register_sysctl_table(pty_root_table);
-		mnt = kern_mount(&devpts_fs_type);
-		if (IS_ERR(mnt)) {
-			err = PTR_ERR(mnt);
-			unregister_filesystem(&devpts_fs_type);
-			unregister_sysctl_table(table);
-		} else {
-			devpts_mnt = mnt;
-		}
+		register_sysctl_table(pty_root_table);
 	}
 	return err;
 }
diff --git a/fs/fscache/page.c b/fs/fscache/page.c
index 3078b67..c8c4f79 100644
--- a/fs/fscache/page.c
+++ b/fs/fscache/page.c
@@ -887,6 +887,8 @@
 			put_page(results[i]);
 	}
 
+	wake_up_bit(&cookie->flags, 0);
+
 	_leave("");
 }
 
diff --git a/fs/namei.c b/fs/namei.c
index 4c4f95a..70580ab 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1416,21 +1416,28 @@
 	}
 }
 
+static int path_parent_directory(struct path *path)
+{
+	struct dentry *old = path->dentry;
+	/* rare case of legitimate dget_parent()... */
+	path->dentry = dget_parent(path->dentry);
+	dput(old);
+	if (unlikely(!path_connected(path)))
+		return -ENOENT;
+	return 0;
+}
+
 static int follow_dotdot(struct nameidata *nd)
 {
 	while(1) {
-		struct dentry *old = nd->path.dentry;
-
 		if (nd->path.dentry == nd->root.dentry &&
 		    nd->path.mnt == nd->root.mnt) {
 			break;
 		}
 		if (nd->path.dentry != nd->path.mnt->mnt_root) {
-			/* rare case of legitimate dget_parent()... */
-			nd->path.dentry = dget_parent(nd->path.dentry);
-			dput(old);
-			if (unlikely(!path_connected(&nd->path)))
-				return -ENOENT;
+			int ret = path_parent_directory(&nd->path);
+			if (ret)
+				return ret;
 			break;
 		}
 		if (!follow_up(&nd->path))
@@ -2514,6 +2521,34 @@
 }
 EXPORT_SYMBOL(lookup_one_len_unlocked);
 
+#ifdef CONFIG_UNIX98_PTYS
+int path_pts(struct path *path)
+{
+	/* Find something mounted on "pts" in the same directory as
+	 * the input path.
+	 */
+	struct dentry *child, *parent;
+	struct qstr this;
+	int ret;
+
+	ret = path_parent_directory(path);
+	if (ret)
+		return ret;
+
+	parent = path->dentry;
+	this.name = "pts";
+	this.len = 3;
+	child = d_hash_and_lookup(parent, &this);
+	if (!child)
+		return -ENOENT;
+
+	path->dentry = child;
+	dput(parent);
+	follow_mount(path);
+	return 0;
+}
+#endif
+
 int user_path_at_empty(int dfd, const char __user *name, unsigned flags,
 		 struct path *path, int *empty)
 {
@@ -2995,9 +3030,13 @@
 			}
 			if (*opened & FILE_CREATED)
 				fsnotify_create(dir, dentry);
-			path->dentry = dentry;
-			path->mnt = nd->path.mnt;
-			return 1;
+			if (unlikely(d_is_negative(dentry))) {
+				error = -ENOENT;
+			} else {
+				path->dentry = dentry;
+				path->mnt = nd->path.mnt;
+				return 1;
+			}
 		}
 	}
 	dput(dentry);
@@ -3166,9 +3205,7 @@
 	int acc_mode = op->acc_mode;
 	unsigned seq;
 	struct inode *inode;
-	struct path save_parent = { .dentry = NULL, .mnt = NULL };
 	struct path path;
-	bool retried = false;
 	int error;
 
 	nd->flags &= ~LOOKUP_PARENT;
@@ -3211,7 +3248,6 @@
 			return -EISDIR;
 	}
 
-retry_lookup:
 	if (open_flag & (O_CREAT | O_TRUNC | O_WRONLY | O_RDWR)) {
 		error = mnt_want_write(nd->path.mnt);
 		if (!error)
@@ -3263,6 +3299,10 @@
 		got_write = false;
 	}
 
+	error = follow_managed(&path, nd);
+	if (unlikely(error < 0))
+		return error;
+
 	if (unlikely(d_is_negative(path.dentry))) {
 		path_to_nameidata(&path, nd);
 		return -ENOENT;
@@ -3278,10 +3318,6 @@
 		return -EEXIST;
 	}
 
-	error = follow_managed(&path, nd);
-	if (unlikely(error < 0))
-		return error;
-
 	seq = 0;	/* out of RCU mode, so the value doesn't matter */
 	inode = d_backing_inode(path.dentry);
 finish_lookup:
@@ -3292,23 +3328,14 @@
 	if (unlikely(error))
 		return error;
 
-	if ((nd->flags & LOOKUP_RCU) || nd->path.mnt != path.mnt) {
-		path_to_nameidata(&path, nd);
-	} else {
-		save_parent.dentry = nd->path.dentry;
-		save_parent.mnt = mntget(path.mnt);
-		nd->path.dentry = path.dentry;
-
-	}
+	path_to_nameidata(&path, nd);
 	nd->inode = inode;
 	nd->seq = seq;
 	/* Why this, you ask?  _Now_ we might have grown LOOKUP_JUMPED... */
 finish_open:
 	error = complete_walk(nd);
-	if (error) {
-		path_put(&save_parent);
+	if (error)
 		return error;
-	}
 	audit_inode(nd->name, nd->path.dentry, 0);
 	error = -EISDIR;
 	if ((open_flag & O_CREAT) && d_is_dir(nd->path.dentry))
@@ -3331,13 +3358,9 @@
 		goto out;
 	BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */
 	error = vfs_open(&nd->path, file, current_cred());
-	if (!error) {
-		*opened |= FILE_OPENED;
-	} else {
-		if (error == -EOPENSTALE)
-			goto stale_open;
+	if (error)
 		goto out;
-	}
+	*opened |= FILE_OPENED;
 opened:
 	error = open_check_o_direct(file);
 	if (!error)
@@ -3353,26 +3376,7 @@
 	}
 	if (got_write)
 		mnt_drop_write(nd->path.mnt);
-	path_put(&save_parent);
 	return error;
-
-stale_open:
-	/* If no saved parent or already retried then can't retry */
-	if (!save_parent.dentry || retried)
-		goto out;
-
-	BUG_ON(save_parent.dentry != dir);
-	path_put(&nd->path);
-	nd->path = save_parent;
-	nd->inode = dir->d_inode;
-	save_parent.mnt = NULL;
-	save_parent.dentry = NULL;
-	if (got_write) {
-		mnt_drop_write(nd->path.mnt);
-		got_write = false;
-	}
-	retried = true;
-	goto retry_lookup;
 }
 
 static int do_tmpfile(struct nameidata *nd, unsigned flags,
diff --git a/fs/namespace.c b/fs/namespace.c
index 4fb1691..a7ec92c 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2409,8 +2409,10 @@
 			mnt_flags |= MNT_NODEV | MNT_LOCK_NODEV;
 		}
 		if (type->fs_flags & FS_USERNS_VISIBLE) {
-			if (!fs_fully_visible(type, &mnt_flags))
+			if (!fs_fully_visible(type, &mnt_flags)) {
+				put_filesystem(type);
 				return -EPERM;
+			}
 		}
 	}
 
@@ -3271,7 +3273,7 @@
 		list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {
 			struct inode *inode = child->mnt_mountpoint->d_inode;
 			/* Only worry about locked mounts */
-			if (!(mnt_flags & MNT_LOCKED))
+			if (!(child->mnt.mnt_flags & MNT_LOCKED))
 				continue;
 			/* Is the directory permanetly empty? */
 			if (!is_empty_dir_inode(inode))
diff --git a/include/acpi/video.h b/include/acpi/video.h
index 70a41f7..5731ccb 100644
--- a/include/acpi/video.h
+++ b/include/acpi/video.h
@@ -51,7 +51,8 @@
  */
 extern bool acpi_video_handles_brightness_key_presses(void);
 extern int acpi_video_get_levels(struct acpi_device *device,
-				 struct acpi_video_device_brightness **dev_br);
+				 struct acpi_video_device_brightness **dev_br,
+				 int *pmax_level);
 #else
 static inline int acpi_video_register(void) { return 0; }
 static inline void acpi_video_unregister(void) { return; }
@@ -72,7 +73,8 @@
 	return false;
 }
 static inline int acpi_video_get_levels(struct acpi_device *device,
-			struct acpi_video_device_brightness **dev_br)
+			struct acpi_video_device_brightness **dev_br,
+			int *pmax_level)
 {
 	return -ENODEV;
 }
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 288fac5..4d4bb49 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -543,6 +543,11 @@
 
 struct fwnode_handle;
 
+static inline bool acpi_dev_found(const char *hid)
+{
+	return false;
+}
+
 static inline bool is_acpi_node(struct fwnode_handle *fwnode)
 {
 	return false;
@@ -654,6 +659,14 @@
 	return false;
 }
 
+static inline union acpi_object *acpi_evaluate_dsm(acpi_handle handle,
+						   const u8 *uuid,
+						   int rev, int func,
+						   union acpi_object *argv4)
+{
+	return NULL;
+}
+
 static inline int acpi_device_uevent_modalias(struct device *dev,
 				struct kobj_uevent_env *env)
 {
diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index 576e463..314b3ca 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -65,6 +65,7 @@
 	unsigned long limit;
 	unsigned long mm_flags;
 	loff_t written;
+	loff_t pos;
 };
 
 /*
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 8ee27b8..9adfef6 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -11,14 +11,17 @@
 #include <linux/workqueue.h>
 #include <linux/file.h>
 #include <linux/percpu.h>
+#include <linux/err.h>
 
+struct perf_event;
 struct bpf_map;
 
 /* map is generic key/value storage optionally accesible by eBPF programs */
 struct bpf_map_ops {
 	/* funcs callable from userspace (via syscall) */
 	struct bpf_map *(*map_alloc)(union bpf_attr *attr);
-	void (*map_free)(struct bpf_map *);
+	void (*map_release)(struct bpf_map *map, struct file *map_file);
+	void (*map_free)(struct bpf_map *map);
 	int (*map_get_next_key)(struct bpf_map *map, void *key, void *next_key);
 
 	/* funcs callable from userspace and from eBPF programs */
@@ -27,8 +30,9 @@
 	int (*map_delete_elem)(struct bpf_map *map, void *key);
 
 	/* funcs called by prog_array and perf_event_array map */
-	void *(*map_fd_get_ptr) (struct bpf_map *map, int fd);
-	void (*map_fd_put_ptr) (void *ptr);
+	void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file,
+				int fd);
+	void (*map_fd_put_ptr)(void *ptr);
 };
 
 struct bpf_map {
@@ -163,11 +167,19 @@
 		void __percpu *pptrs[0] __aligned(8);
 	};
 };
+
 #define MAX_TAIL_CALL_CNT 32
 
+struct bpf_event_entry {
+	struct perf_event *event;
+	struct file *perf_file;
+	struct file *map_file;
+	struct rcu_head rcu;
+};
+
 u64 bpf_tail_call(u64 ctx, u64 r2, u64 index, u64 r4, u64 r5);
 u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
-void bpf_fd_array_map_clear(struct bpf_map *map);
+
 bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp);
 
 const struct bpf_func_proto *bpf_get_trace_printk_proto(void);
@@ -205,8 +217,13 @@
 			   u64 flags);
 int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value,
 			    u64 flags);
+
 int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value);
 
+int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file,
+				 void *key, void *value, u64 map_flags);
+void bpf_fd_array_map_clear(struct bpf_map *map);
+
 /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and
  * forced to use 'long' read/writes to try to atomically copy long counters.
  * Best-effort only.  No barriers here, since it _will_ race with concurrent
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index 19b1486..1b3b6e1 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -279,6 +279,11 @@
 	struct workqueue_struct	*notify_wq;
 };
 
+static inline bool ceph_osdmap_flag(struct ceph_osd_client *osdc, int flag)
+{
+	return osdc->osdmap->flags & flag;
+}
+
 extern int ceph_osdc_setup(void);
 extern void ceph_osdc_cleanup(void);
 
diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index ddc426b2..9ccf4db 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -189,11 +189,6 @@
 	return !ceph_osd_is_up(map, osd);
 }
 
-static inline bool ceph_osdmap_flag(struct ceph_osdmap *map, int flag)
-{
-	return map && (map->flags & flag);
-}
-
 extern char *ceph_osdmap_state_str(char *str, int len, int state);
 extern u32 ceph_get_primary_affinity(struct ceph_osdmap *map, int osd);
 
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index 0c72204..fb39d5a 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -25,7 +25,7 @@
 #define CLK_SET_PARENT_GATE	BIT(1) /* must be gated across re-parent */
 #define CLK_SET_RATE_PARENT	BIT(2) /* propagate rate change up one level */
 #define CLK_IGNORE_UNUSED	BIT(3) /* do not gate even if unused */
-#define CLK_IS_ROOT		BIT(4) /* Deprecated: Don't use */
+				/* unused */
 #define CLK_IS_BASIC		BIT(5) /* Basic clk, can't do a to_clk_foo() */
 #define CLK_GET_RATE_NOCACHE	BIT(6) /* do not use the cached clk rate */
 #define CLK_SET_RATE_NO_REPARENT BIT(7) /* don't re-parent on rate change */
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 786ad32..07b83d3 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -152,6 +152,8 @@
 extern int cpuidle_play_dead(void);
 
 extern struct cpuidle_driver *cpuidle_get_cpu_driver(struct cpuidle_device *dev);
+static inline struct cpuidle_device *cpuidle_get_device(void)
+{return __this_cpu_read(cpuidle_devices); }
 #else
 static inline void disable_cpuidle(void) { }
 static inline bool cpuidle_not_available(struct cpuidle_driver *drv,
@@ -187,6 +189,7 @@
 static inline int cpuidle_play_dead(void) {return -ENODEV; }
 static inline struct cpuidle_driver *cpuidle_get_cpu_driver(
 	struct cpuidle_device *dev) {return NULL; }
+static inline struct cpuidle_device *cpuidle_get_device(void) {return NULL; }
 #endif
 
 #if defined(CONFIG_CPU_IDLE) && defined(CONFIG_SUSPEND)
diff --git a/include/linux/devpts_fs.h b/include/linux/devpts_fs.h
index 5871f29..277ab9a 100644
--- a/include/linux/devpts_fs.h
+++ b/include/linux/devpts_fs.h
@@ -15,13 +15,12 @@
 
 #include <linux/errno.h>
 
-struct pts_fs_info;
-
 #ifdef CONFIG_UNIX98_PTYS
 
-/* Look up a pts fs info and get a ref to it */
-struct pts_fs_info *devpts_get_ref(struct inode *, struct file *);
-void devpts_put_ref(struct pts_fs_info *);
+struct pts_fs_info;
+
+struct pts_fs_info *devpts_acquire(struct file *);
+void devpts_release(struct pts_fs_info *);
 
 int devpts_new_index(struct pts_fs_info *);
 void devpts_kill_index(struct pts_fs_info *, int);
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index 3fe90d4..4551c6f 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -112,19 +112,24 @@
  * @file: file pointer used for sharing buffers across, and for refcounting.
  * @attachments: list of dma_buf_attachment that denotes all devices attached.
  * @ops: dma_buf_ops associated with this buffer object.
+ * @lock: used internally to serialize list manipulation, attach/detach and vmap/unmap
+ * @vmapping_counter: used internally to refcnt the vmaps
+ * @vmap_ptr: the current vmap ptr if vmapping_counter > 0
  * @exp_name: name of the exporter; useful for debugging.
  * @owner: pointer to exporter module; used for refcounting when exporter is a
  *         kernel module.
  * @list_node: node for dma_buf accounting and debugging.
  * @priv: exporter specific private data for this buffer object.
  * @resv: reservation object linked to this dma-buf
+ * @poll: for userspace poll support
+ * @cb_excl: for userspace poll support
+ * @cb_shared: for userspace poll support
  */
 struct dma_buf {
 	size_t size;
 	struct file *file;
 	struct list_head attachments;
 	const struct dma_buf_ops *ops;
-	/* mutex to serialize list manipulation, attach/detach and vmap/unmap */
 	struct mutex lock;
 	unsigned vmapping_counter;
 	void *vmap_ptr;
@@ -188,9 +193,11 @@
 
 /**
  * helper macro for exporters; zeros and fills in most common values
+ *
+ * @name: export-info name
  */
-#define DEFINE_DMA_BUF_EXPORT_INFO(a)	\
-	struct dma_buf_export_info a = { .exp_name = KBUILD_MODNAME, \
+#define DEFINE_DMA_BUF_EXPORT_INFO(name)	\
+	struct dma_buf_export_info name = { .exp_name = KBUILD_MODNAME, \
 					 .owner = THIS_MODULE }
 
 /**
diff --git a/include/linux/fence.h b/include/linux/fence.h
index 2b17698..2056e9f 100644
--- a/include/linux/fence.h
+++ b/include/linux/fence.h
@@ -49,6 +49,8 @@
  * @timestamp: Timestamp when the fence was signaled.
  * @status: Optional, only valid if < 0, must be set before calling
  * fence_signal, indicates that the fence has completed with an error.
+ * @child_list: list of children fences
+ * @active_list: list of active fences
  *
  * the flags member must be manipulated and read using the appropriate
  * atomic ops (bit_*), so taking the spinlock will not be needed most
diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h
index 604e152..13ba552 100644
--- a/include/linux/fscache-cache.h
+++ b/include/linux/fscache-cache.h
@@ -241,7 +241,7 @@
 
 	/* check the consistency between the backing cache and the FS-Cache
 	 * cookie */
-	bool (*check_consistency)(struct fscache_operation *op);
+	int (*check_consistency)(struct fscache_operation *op);
 
 	/* store the updated auxiliary data on an object */
 	void (*update_object)(struct fscache_object *object);
diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h
index 630f453..57086e9 100644
--- a/include/linux/icmpv6.h
+++ b/include/linux/icmpv6.h
@@ -14,9 +14,12 @@
 #if IS_ENABLED(CONFIG_IPV6)
 extern void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info);
 
-typedef void ip6_icmp_send_t(struct sk_buff *skb, u8 type, u8 code, __u32 info);
+typedef void ip6_icmp_send_t(struct sk_buff *skb, u8 type, u8 code, __u32 info,
+			     const struct in6_addr *force_saddr);
 extern int inet6_register_icmp_sender(ip6_icmp_send_t *fn);
 extern int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn);
+int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type,
+			       unsigned int data_len);
 
 #else
 
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 5c91b0b..c6dbcd8 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -283,6 +283,8 @@
 };
 
 #if IS_ENABLED(CONFIG_IPV6)
+bool ipv6_mod_enabled(void);
+
 static inline struct ipv6_pinfo *inet6_sk(const struct sock *__sk)
 {
 	return sk_fullsock(__sk) ? inet_sk(__sk)->pinet6 : NULL;
@@ -326,6 +328,11 @@
 #define ipv6_only_sock(sk)	0
 #define ipv6_sk_rxinfo(sk)	0
 
+static inline bool ipv6_mod_enabled(void)
+{
+	return false;
+}
+
 static inline struct ipv6_pinfo * inet6_sk(const struct sock *__sk)
 {
 	return NULL;
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index bfbd707..dc493e0 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -305,12 +305,12 @@
 #define ICC_SGI1R_AFFINITY_1_SHIFT	16
 #define ICC_SGI1R_AFFINITY_1_MASK	(0xff << ICC_SGI1R_AFFINITY_1_SHIFT)
 #define ICC_SGI1R_SGI_ID_SHIFT		24
-#define ICC_SGI1R_SGI_ID_MASK		(0xff << ICC_SGI1R_SGI_ID_SHIFT)
+#define ICC_SGI1R_SGI_ID_MASK		(0xfULL << ICC_SGI1R_SGI_ID_SHIFT)
 #define ICC_SGI1R_AFFINITY_2_SHIFT	32
-#define ICC_SGI1R_AFFINITY_2_MASK	(0xffULL << ICC_SGI1R_AFFINITY_1_SHIFT)
+#define ICC_SGI1R_AFFINITY_2_MASK	(0xffULL << ICC_SGI1R_AFFINITY_2_SHIFT)
 #define ICC_SGI1R_IRQ_ROUTING_MODE_BIT	40
 #define ICC_SGI1R_AFFINITY_3_SHIFT	48
-#define ICC_SGI1R_AFFINITY_3_MASK	(0xffULL << ICC_SGI1R_AFFINITY_1_SHIFT)
+#define ICC_SGI1R_AFFINITY_3_MASK	(0xffULL << ICC_SGI1R_AFFINITY_3_SHIFT)
 
 #include <asm/arch_gicv3.h>
 
diff --git a/include/linux/mdio-mux.h b/include/linux/mdio-mux.h
index a243dbb..61f5b21 100644
--- a/include/linux/mdio-mux.h
+++ b/include/linux/mdio-mux.h
@@ -10,11 +10,13 @@
 #ifndef __LINUX_MDIO_MUX_H
 #define __LINUX_MDIO_MUX_H
 #include <linux/device.h>
+#include <linux/phy.h>
 
 int mdio_mux_init(struct device *dev,
 		  int (*switch_fn) (int cur, int desired, void *data),
 		  void **mux_handle,
-		  void *data);
+		  void *data,
+		  struct mii_bus *mux_bus);
 
 void mdio_mux_uninit(void *mux_handle);
 
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 80dec87..4dbc145 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -535,6 +535,7 @@
 	int			max_rq_desc_sz;
 	int			max_qp_init_rdma;
 	int			max_qp_dest_rdma;
+	int			max_tc_eth;
 	u32			*qp0_qkey;
 	u32			*qp0_proxy;
 	u32			*qp1_proxy;
@@ -1494,6 +1495,7 @@
 
 int mlx4_get_module_info(struct mlx4_dev *dev, u8 port,
 			 u16 offset, u16 size, u8 *data);
+int mlx4_max_tc(struct mlx4_dev *dev);
 
 /* Returns true if running in low memory profile (kdump kernel) */
 static inline bool mlx4_low_memory_profile(void)
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 035abdf..73a4847 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -1240,8 +1240,6 @@
 	u8                      rsvd[8];
 };
 
-#define MLX5_CMD_OP_MAX 0x920
-
 enum {
 	VPORT_STATE_DOWN		= 0x0,
 	VPORT_STATE_UP			= 0x1,
@@ -1369,6 +1367,12 @@
 #define MLX5_CAP_FLOWTABLE_MAX(mdev, cap) \
 	MLX5_GET(flow_table_nic_cap, mdev->hca_caps_max[MLX5_CAP_FLOW_TABLE], cap)
 
+#define MLX5_CAP_FLOWTABLE_NIC_RX(mdev, cap) \
+	MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive.cap)
+
+#define MLX5_CAP_FLOWTABLE_NIC_RX_MAX(mdev, cap) \
+	MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_receive.cap)
+
 #define MLX5_CAP_ESW_FLOWTABLE(mdev, cap) \
 	MLX5_GET(flow_table_eswitch_cap, \
 		 mdev->hca_caps_cur[MLX5_CAP_ESWITCH_FLOW_TABLE], cap)
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 9a05cd7..152421c 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -123,6 +123,10 @@
 	MLX5_CMD_OP_DRAIN_DCT                     = 0x712,
 	MLX5_CMD_OP_QUERY_DCT                     = 0x713,
 	MLX5_CMD_OP_ARM_DCT_FOR_KEY_VIOLATION     = 0x714,
+	MLX5_CMD_OP_CREATE_XRQ                    = 0x717,
+	MLX5_CMD_OP_DESTROY_XRQ                   = 0x718,
+	MLX5_CMD_OP_QUERY_XRQ                     = 0x719,
+	MLX5_CMD_OP_ARM_XRQ                       = 0x71a,
 	MLX5_CMD_OP_QUERY_VPORT_STATE             = 0x750,
 	MLX5_CMD_OP_MODIFY_VPORT_STATE            = 0x751,
 	MLX5_CMD_OP_QUERY_ESW_VPORT_CONTEXT       = 0x752,
@@ -139,6 +143,8 @@
 	MLX5_CMD_OP_ALLOC_Q_COUNTER               = 0x771,
 	MLX5_CMD_OP_DEALLOC_Q_COUNTER             = 0x772,
 	MLX5_CMD_OP_QUERY_Q_COUNTER               = 0x773,
+	MLX5_CMD_OP_SET_RATE_LIMIT                = 0x780,
+	MLX5_CMD_OP_QUERY_RATE_LIMIT              = 0x781,
 	MLX5_CMD_OP_ALLOC_PD                      = 0x800,
 	MLX5_CMD_OP_DEALLOC_PD                    = 0x801,
 	MLX5_CMD_OP_ALLOC_UAR                     = 0x802,
@@ -205,7 +211,8 @@
 	MLX5_CMD_OP_ALLOC_FLOW_COUNTER            = 0x939,
 	MLX5_CMD_OP_DEALLOC_FLOW_COUNTER          = 0x93a,
 	MLX5_CMD_OP_QUERY_FLOW_COUNTER            = 0x93b,
-	MLX5_CMD_OP_MODIFY_FLOW_TABLE             = 0x93c
+	MLX5_CMD_OP_MODIFY_FLOW_TABLE             = 0x93c,
+	MLX5_CMD_OP_MAX
 };
 
 struct mlx5_ifc_flow_table_fields_supported_bits {
@@ -361,7 +368,8 @@
 };
 
 struct mlx5_ifc_fte_match_set_misc_bits {
-	u8         reserved_at_0[0x20];
+	u8         reserved_at_0[0x8];
+	u8         source_sqn[0x18];
 
 	u8         reserved_at_20[0x10];
 	u8         source_port[0x10];
@@ -500,11 +508,24 @@
 	u8         vport_svlan_insert[0x1];
 	u8         vport_cvlan_insert_if_not_exist[0x1];
 	u8         vport_cvlan_insert_overwrite[0x1];
-	u8         reserved_at_5[0x1b];
+	u8         reserved_at_5[0x19];
+	u8         nic_vport_node_guid_modify[0x1];
+	u8         nic_vport_port_guid_modify[0x1];
 
 	u8         reserved_at_20[0x7e0];
 };
 
+struct mlx5_ifc_qos_cap_bits {
+	u8         packet_pacing[0x1];
+	u8         reserved_0[0x1f];
+	u8         reserved_1[0x20];
+	u8         packet_pacing_max_rate[0x20];
+	u8         packet_pacing_min_rate[0x20];
+	u8         reserved_2[0x10];
+	u8         packet_pacing_rate_table_size[0x10];
+	u8         reserved_3[0x760];
+};
+
 struct mlx5_ifc_per_protocol_networking_offload_caps_bits {
 	u8         csum_cap[0x1];
 	u8         vlan_cap[0x1];
@@ -744,7 +765,8 @@
 
 	u8         out_of_seq_cnt[0x1];
 	u8         vport_counters[0x1];
-	u8         reserved_at_182[0x4];
+	u8         retransmission_q_counters[0x1];
+	u8         reserved_at_183[0x3];
 	u8         max_qp_cnt[0xa];
 	u8         pkey_table_size[0x10];
 
@@ -771,7 +793,9 @@
 	u8         log_max_msg[0x5];
 	u8         reserved_at_1c8[0x4];
 	u8         max_tc[0x4];
-	u8         reserved_at_1d0[0x6];
+	u8         reserved_at_1d0[0x1];
+	u8         dcbx[0x1];
+	u8         reserved_at_1d2[0x4];
 	u8         rol_s[0x1];
 	u8         rol_g[0x1];
 	u8         reserved_at_1d8[0x1];
@@ -803,7 +827,7 @@
 	u8         tph[0x1];
 	u8         rf[0x1];
 	u8         dct[0x1];
-	u8         reserved_at_21b[0x1];
+	u8         qos[0x1];
 	u8         eth_net_offloads[0x1];
 	u8         roce[0x1];
 	u8         atomic[0x1];
@@ -929,7 +953,15 @@
 	u8         cqe_compression_timeout[0x10];
 	u8         cqe_compression_max_num[0x10];
 
-	u8         reserved_at_5e0[0x220];
+	u8         reserved_at_5e0[0x10];
+	u8         tag_matching[0x1];
+	u8         rndv_offload_rc[0x1];
+	u8         rndv_offload_dc[0x1];
+	u8         log_tag_matching_list_sz[0x5];
+	u8         reserved_at_5e8[0x3];
+	u8         log_max_xrq[0x5];
+
+	u8         reserved_at_5f0[0x200];
 };
 
 enum mlx5_flow_destination_type {
@@ -1967,7 +1999,7 @@
 
 	u8         reserved_at_560[0x5];
 	u8         rq_type[0x3];
-	u8         srqn_rmpn[0x18];
+	u8         srqn_rmpn_xrqn[0x18];
 
 	u8         reserved_at_580[0x8];
 	u8         rmsn[0x18];
@@ -2018,6 +2050,7 @@
 	struct mlx5_ifc_flow_table_eswitch_cap_bits flow_table_eswitch_cap;
 	struct mlx5_ifc_e_switch_cap_bits e_switch_cap;
 	struct mlx5_ifc_vector_calc_cap_bits vector_calc_cap;
+	struct mlx5_ifc_qos_cap_bits qos_cap;
 	u8         reserved_at_0[0x8000];
 };
 
@@ -2244,8 +2277,9 @@
 	u8         reserved_at_40[0x8];
 	u8         cqn[0x18];
 
-	u8         reserved_at_60[0xa0];
+	u8         reserved_at_60[0x90];
 
+	u8         packet_pacing_rate_limit_index[0x10];
 	u8         tis_lst_sz[0x10];
 	u8         reserved_at_110[0x10];
 
@@ -2593,7 +2627,7 @@
 	u8         reserved_at_98[0x8];
 
 	u8         reserved_at_a0[0x8];
-	u8         srqn[0x18];
+	u8         srqn_xrqn[0x18];
 
 	u8         reserved_at_c0[0x8];
 	u8         pd[0x18];
@@ -2645,6 +2679,7 @@
 enum {
 	MLX5_CQ_PERIOD_MODE_START_FROM_EQE = 0x0,
 	MLX5_CQ_PERIOD_MODE_START_FROM_CQE = 0x1,
+	MLX5_CQ_PERIOD_NUM_MODES
 };
 
 struct mlx5_ifc_cqc_bits {
@@ -2722,6 +2757,54 @@
 	u8         vsd_contd_psid[16][0x8];
 };
 
+enum {
+	MLX5_XRQC_STATE_GOOD   = 0x0,
+	MLX5_XRQC_STATE_ERROR  = 0x1,
+};
+
+enum {
+	MLX5_XRQC_TOPOLOGY_NO_SPECIAL_TOPOLOGY = 0x0,
+	MLX5_XRQC_TOPOLOGY_TAG_MATCHING        = 0x1,
+};
+
+enum {
+	MLX5_XRQC_OFFLOAD_RNDV = 0x1,
+};
+
+struct mlx5_ifc_tag_matching_topology_context_bits {
+	u8         log_matching_list_sz[0x4];
+	u8         reserved_at_4[0xc];
+	u8         append_next_index[0x10];
+
+	u8         sw_phase_cnt[0x10];
+	u8         hw_phase_cnt[0x10];
+
+	u8         reserved_at_40[0x40];
+};
+
+struct mlx5_ifc_xrqc_bits {
+	u8         state[0x4];
+	u8         rlkey[0x1];
+	u8         reserved_at_5[0xf];
+	u8         topology[0x4];
+	u8         reserved_at_18[0x4];
+	u8         offload[0x4];
+
+	u8         reserved_at_20[0x8];
+	u8         user_index[0x18];
+
+	u8         reserved_at_40[0x8];
+	u8         cqn[0x18];
+
+	u8         reserved_at_60[0xa0];
+
+	struct mlx5_ifc_tag_matching_topology_context_bits tag_matching_topology_context;
+
+	u8         reserved_at_180[0x180];
+
+	struct mlx5_ifc_wq_bits wq;
+};
+
 union mlx5_ifc_modify_field_select_resize_field_select_auto_bits {
 	struct mlx5_ifc_modify_field_select_bits modify_field_select;
 	struct mlx5_ifc_resize_field_select_bits resize_field_select;
@@ -3144,6 +3227,30 @@
 	u8         reserved_at_800[0x80];
 };
 
+struct mlx5_ifc_query_xrq_out_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_at_40[0x40];
+
+	struct mlx5_ifc_xrqc_bits xrq_context;
+};
+
+struct mlx5_ifc_query_xrq_in_bits {
+	u8         opcode[0x10];
+	u8         reserved_at_10[0x10];
+
+	u8         reserved_at_20[0x10];
+	u8         op_mod[0x10];
+
+	u8         reserved_at_40[0x8];
+	u8         xrqn[0x18];
+
+	u8         reserved_at_60[0x20];
+};
+
 struct mlx5_ifc_query_xrc_srq_out_bits {
 	u8         status[0x8];
 	u8         reserved_at_8[0x18];
@@ -3547,7 +3654,27 @@
 
 	u8         out_of_sequence[0x20];
 
-	u8         reserved_at_1e0[0x620];
+	u8         reserved_at_1e0[0x20];
+
+	u8         duplicate_request[0x20];
+
+	u8         reserved_at_220[0x20];
+
+	u8         rnr_nak_retry_err[0x20];
+
+	u8         reserved_at_260[0x20];
+
+	u8         packet_seq_err[0x20];
+
+	u8         reserved_at_2a0[0x20];
+
+	u8         implied_nak_seq_err[0x20];
+
+	u8         reserved_at_2e0[0x20];
+
+	u8         local_ack_timeout_err[0x20];
+
+	u8         reserved_at_320[0x4e0];
 };
 
 struct mlx5_ifc_query_q_counter_in_bits {
@@ -4583,7 +4710,10 @@
 };
 
 struct mlx5_ifc_modify_nic_vport_field_select_bits {
-	u8         reserved_at_0[0x19];
+	u8         reserved_at_0[0x16];
+	u8         node_guid[0x1];
+	u8         port_guid[0x1];
+	u8         reserved_at_18[0x1];
 	u8         mtu[0x1];
 	u8         change_event[0x1];
 	u8         promisc[0x1];
@@ -4998,6 +5128,28 @@
 	u8         multicast_gid[16][0x8];
 };
 
+struct mlx5_ifc_destroy_xrq_out_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_at_40[0x40];
+};
+
+struct mlx5_ifc_destroy_xrq_in_bits {
+	u8         opcode[0x10];
+	u8         reserved_at_10[0x10];
+
+	u8         reserved_at_20[0x10];
+	u8         op_mod[0x10];
+
+	u8         reserved_at_40[0x8];
+	u8         xrqn[0x18];
+
+	u8         reserved_at_60[0x20];
+};
+
 struct mlx5_ifc_destroy_xrc_srq_out_bits {
 	u8         status[0x8];
 	u8         reserved_at_8[0x18];
@@ -5583,6 +5735,30 @@
 	u8         reserved_at_60[0x20];
 };
 
+struct mlx5_ifc_create_xrq_out_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_at_40[0x8];
+	u8         xrqn[0x18];
+
+	u8         reserved_at_60[0x20];
+};
+
+struct mlx5_ifc_create_xrq_in_bits {
+	u8         opcode[0x10];
+	u8         reserved_at_10[0x10];
+
+	u8         reserved_at_20[0x10];
+	u8         op_mod[0x10];
+
+	u8         reserved_at_40[0x40];
+
+	struct mlx5_ifc_xrqc_bits xrq_context;
+};
+
 struct mlx5_ifc_create_xrc_srq_out_bits {
 	u8         status[0x8];
 	u8         reserved_at_8[0x18];
@@ -6124,6 +6300,29 @@
 	u8         multicast_gid[16][0x8];
 };
 
+struct mlx5_ifc_arm_xrq_out_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_at_40[0x40];
+};
+
+struct mlx5_ifc_arm_xrq_in_bits {
+	u8         opcode[0x10];
+	u8         reserved_at_10[0x10];
+
+	u8         reserved_at_20[0x10];
+	u8         op_mod[0x10];
+
+	u8         reserved_at_40[0x8];
+	u8         xrqn[0x18];
+
+	u8         reserved_at_60[0x10];
+	u8         lwm[0x10];
+};
+
 struct mlx5_ifc_arm_xrc_srq_out_bits {
 	u8         status[0x8];
 	u8         reserved_at_8[0x18];
@@ -6161,7 +6360,8 @@
 };
 
 enum {
-	MLX5_ARM_RQ_IN_OP_MOD_SRQ_  = 0x1,
+	MLX5_ARM_RQ_IN_OP_MOD_SRQ = 0x1,
+	MLX5_ARM_RQ_IN_OP_MOD_XRQ = 0x2,
 };
 
 struct mlx5_ifc_arm_rq_in_bits {
@@ -6354,6 +6554,30 @@
 	u8         vxlan_udp_port[0x10];
 };
 
+struct mlx5_ifc_set_rate_limit_out_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_at_40[0x40];
+};
+
+struct mlx5_ifc_set_rate_limit_in_bits {
+	u8         opcode[0x10];
+	u8         reserved_at_10[0x10];
+
+	u8         reserved_at_20[0x10];
+	u8         op_mod[0x10];
+
+	u8         reserved_at_40[0x10];
+	u8         rate_limit_index[0x10];
+
+	u8         reserved_at_60[0x20];
+
+	u8         rate_limit[0x20];
+};
+
 struct mlx5_ifc_access_register_out_bits {
 	u8         status[0x8];
 	u8         reserved_at_8[0x18];
@@ -6478,12 +6702,15 @@
 };
 
 struct mlx5_ifc_ptys_reg_bits {
-	u8         reserved_at_0[0x8];
+	u8         an_disable_cap[0x1];
+	u8         an_disable_admin[0x1];
+	u8         reserved_at_2[0x6];
 	u8         local_port[0x8];
 	u8         reserved_at_10[0xd];
 	u8         proto_mask[0x3];
 
-	u8         reserved_at_20[0x40];
+	u8         an_status[0x4];
+	u8         reserved_at_24[0x3c];
 
 	u8         eth_proto_capability[0x20];
 
@@ -7444,4 +7671,34 @@
 	u8         dword_11[0x20];
 };
 
+struct mlx5_ifc_dcbx_param_bits {
+	u8         dcbx_cee_cap[0x1];
+	u8         dcbx_ieee_cap[0x1];
+	u8         dcbx_standby_cap[0x1];
+	u8         reserved_at_0[0x5];
+	u8         port_number[0x8];
+	u8         reserved_at_10[0xa];
+	u8         max_application_table_size[6];
+	u8         reserved_at_20[0x15];
+	u8         version_oper[0x3];
+	u8         reserved_at_38[5];
+	u8         version_admin[0x3];
+	u8         willing_admin[0x1];
+	u8         reserved_at_41[0x3];
+	u8         pfc_cap_oper[0x4];
+	u8         reserved_at_48[0x4];
+	u8         pfc_cap_admin[0x4];
+	u8         reserved_at_50[0x4];
+	u8         num_of_tc_oper[0x4];
+	u8         reserved_at_58[0x4];
+	u8         num_of_tc_admin[0x4];
+	u8         remote_willing[0x1];
+	u8         reserved_at_61[3];
+	u8         remote_pfc_cap[4];
+	u8         reserved_at_68[0x14];
+	u8         remote_num_of_tc[0x4];
+	u8         reserved_at_80[0x18];
+	u8         error[0x8];
+	u8         reserved_at_a0[0x160];
+};
 #endif /* MLX5_IFC_H */
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index 6422102..266320f 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -460,10 +460,9 @@
 };
 
 struct mlx5_qp_path {
-	u8			fl;
+	u8			fl_free_ar;
 	u8			rsvd3;
-	u8			free_ar;
-	u8			pkey_index;
+	__be16			pkey_index;
 	u8			rsvd0;
 	u8			grh_mlid;
 	__be16			rlid;
@@ -560,6 +559,7 @@
 	__be32			optparam;
 	u8			rsvd0[4];
 	struct mlx5_qp_context	ctx;
+	u8			rsvd2[16];
 };
 
 struct mlx5_modify_qp_mbox_out {
diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h
index 301da4a..6c16c19 100644
--- a/include/linux/mlx5/vport.h
+++ b/include/linux/mlx5/vport.h
@@ -50,6 +50,8 @@
 int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev,
 					   u64 *system_image_guid);
 int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid);
+int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev,
+				    u32 vport, u64 node_guid);
 int mlx5_query_nic_vport_qkey_viol_cntr(struct mlx5_core_dev *mdev,
 					u16 *qkey_viol_cntr);
 int mlx5_query_hca_vport_gid(struct mlx5_core_dev *dev, u8 other_vport,
diff --git a/include/linux/namei.h b/include/linux/namei.h
index ec5ec28..d3d0398 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -45,6 +45,8 @@
 #define LOOKUP_ROOT		0x2000
 #define LOOKUP_EMPTY		0x4000
 
+extern int path_pts(struct path *path);
+
 extern int user_path_at_empty(int, const char __user *, unsigned, struct path *, int *empty);
 
 static inline int user_path_at(int dfd, const char __user *name, unsigned flags,
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index fa6df26..e84d9d2 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -61,6 +61,8 @@
 /* 802.15.4 specific */
 struct wpan_dev;
 struct mpls_dev;
+/* UDP Tunnel offloads */
+struct udp_tunnel_info;
 
 void netdev_set_default_ethtool_ops(struct net_device *dev,
 				    const struct ethtool_ops *ops);
@@ -90,7 +92,6 @@
 #define NET_XMIT_SUCCESS	0x00
 #define NET_XMIT_DROP		0x01	/* skb dropped			*/
 #define NET_XMIT_CN		0x02	/* congestion notification	*/
-#define NET_XMIT_POLICED	0x03	/* skb is shot by police	*/
 #define NET_XMIT_MASK		0x0f	/* qdisc flags in net/sch_generic.h */
 
 /* NET_XMIT_CN is special. It does not guarantee that this packet is lost. It
@@ -1025,31 +1026,18 @@
  *	not implement this, it is assumed that the hw is not able to have
  *	multiple net devices on single physical port.
  *
- * void (*ndo_add_vxlan_port)(struct  net_device *dev,
- *			      sa_family_t sa_family, __be16 port);
- *	Called by vxlan to notify a driver about the UDP port and socket
- *	address family that vxlan is listening to. It is called only when
- *	a new port starts listening. The operation is protected by the
- *	vxlan_net->sock_lock.
+ * void (*ndo_udp_tunnel_add)(struct net_device *dev,
+ *			      struct udp_tunnel_info *ti);
+ *	Called by UDP tunnel to notify a driver about the UDP port and socket
+ *	address family that a UDP tunnel is listnening to. It is called only
+ *	when a new port starts listening. The operation is protected by the
+ *	RTNL.
  *
- * void (*ndo_add_geneve_port)(struct net_device *dev,
- *			       sa_family_t sa_family, __be16 port);
- *	Called by geneve to notify a driver about the UDP port and socket
- *	address family that geneve is listnening to. It is called only when
- *	a new port starts listening. The operation is protected by the
- *	geneve_net->sock_lock.
- *
- * void (*ndo_del_geneve_port)(struct net_device *dev,
- *			       sa_family_t sa_family, __be16 port);
- *	Called by geneve to notify the driver about a UDP port and socket
- *	address family that geneve is not listening to anymore. The operation
- *	is protected by the geneve_net->sock_lock.
- *
- * void (*ndo_del_vxlan_port)(struct  net_device *dev,
- *			      sa_family_t sa_family, __be16 port);
- *	Called by vxlan to notify the driver about a UDP port and socket
- *	address family that vxlan is not listening to anymore. The operation
- *	is protected by the vxlan_net->sock_lock.
+ * void (*ndo_udp_tunnel_del)(struct net_device *dev,
+ *			      struct udp_tunnel_info *ti);
+ *	Called by UDP tunnel to notify the driver about a UDP port and socket
+ *	address family that the UDP tunnel is not listening to anymore. The
+ *	operation is protected by the RTNL.
  *
  * void* (*ndo_dfwd_add_station)(struct net_device *pdev,
  *				 struct net_device *dev)
@@ -1258,18 +1246,10 @@
 							struct netdev_phys_item_id *ppid);
 	int			(*ndo_get_phys_port_name)(struct net_device *dev,
 							  char *name, size_t len);
-	void			(*ndo_add_vxlan_port)(struct  net_device *dev,
-						      sa_family_t sa_family,
-						      __be16 port);
-	void			(*ndo_del_vxlan_port)(struct  net_device *dev,
-						      sa_family_t sa_family,
-						      __be16 port);
-	void			(*ndo_add_geneve_port)(struct  net_device *dev,
-						       sa_family_t sa_family,
-						       __be16 port);
-	void			(*ndo_del_geneve_port)(struct  net_device *dev,
-						       sa_family_t sa_family,
-						       __be16 port);
+	void			(*ndo_udp_tunnel_add)(struct net_device *dev,
+						      struct udp_tunnel_info *ti);
+	void			(*ndo_udp_tunnel_del)(struct net_device *dev,
+						      struct udp_tunnel_info *ti);
 	void*			(*ndo_dfwd_add_station)(struct net_device *pdev,
 							struct net_device *dev);
 	void			(*ndo_dfwd_del_station)(struct net_device *pdev,
@@ -1457,6 +1437,8 @@
  *	@netdev_ops:	Includes several pointers to callbacks,
  *			if one wants to override the ndo_*() functions
  *	@ethtool_ops:	Management operations
+ *	@ndisc_ops:	Includes callbacks for different IPv6 neighbour
+ *			discovery handling. Necessary for e.g. 6LoWPAN.
  *	@header_ops:	Includes callbacks for creating,parsing,caching,etc
  *			of Layer 2 headers.
  *
@@ -1484,8 +1466,7 @@
  * 	@perm_addr:		Permanent hw address
  * 	@addr_assign_type:	Hw address assignment type
  * 	@addr_len:		Hardware address length
- * 	@neigh_priv_len;	Used in neigh_alloc(),
- * 				initialized only in atm/clip.c
+ *	@neigh_priv_len:	Used in neigh_alloc()
  * 	@dev_id:		Used to differentiate devices that share
  * 				the same link layer address
  * 	@dev_port:		Used to differentiate devices that share
@@ -1594,7 +1575,8 @@
  *	@phydev:	Physical device may attach itself
  *			for hardware timestamping
  *
- *	@qdisc_tx_busylock:	XXX: need comments on this one
+ *	@qdisc_tx_busylock: lockdep class annotating Qdisc->busylock spinlock
+ *	@qdisc_running_key: lockdep class annotating Qdisc->running seqcount
  *
  *	@proto_down:	protocol port state information can be sent to the
  *			switch driver and used to set the phys state of the
@@ -1673,6 +1655,9 @@
 #ifdef CONFIG_NET_L3_MASTER_DEV
 	const struct l3mdev_ops	*l3mdev_ops;
 #endif
+#if IS_ENABLED(CONFIG_IPV6)
+	const struct ndisc_ops *ndisc_ops;
+#endif
 
 	const struct header_ops *header_ops;
 
@@ -1862,6 +1847,7 @@
 #endif
 	struct phy_device	*phydev;
 	struct lock_class_key	*qdisc_tx_busylock;
+	struct lock_class_key	*qdisc_running_key;
 	bool			proto_down;
 };
 #define to_net_dev(d) container_of(d, struct net_device, dev)
@@ -1944,6 +1930,23 @@
 		f(dev, &dev->_tx[i], arg);
 }
 
+#define netdev_lockdep_set_classes(dev)				\
+{								\
+	static struct lock_class_key qdisc_tx_busylock_key;	\
+	static struct lock_class_key qdisc_running_key;		\
+	static struct lock_class_key qdisc_xmit_lock_key;	\
+	static struct lock_class_key dev_addr_list_lock_key;	\
+	unsigned int i;						\
+								\
+	(dev)->qdisc_tx_busylock = &qdisc_tx_busylock_key;	\
+	(dev)->qdisc_running_key = &qdisc_running_key;		\
+	lockdep_set_class(&(dev)->addr_list_lock,		\
+			  &dev_addr_list_lock_key); 		\
+	for (i = 0; i < (dev)->num_tx_queues; i++)		\
+		lockdep_set_class(&(dev)->_tx[i]._xmit_lock,	\
+				  &qdisc_xmit_lock_key);	\
+}
+
 struct netdev_queue *netdev_pick_tx(struct net_device *dev,
 				    struct sk_buff *skb,
 				    void *accel_priv);
@@ -2233,8 +2236,7 @@
 #define NETDEV_BONDING_INFO	0x0019
 #define NETDEV_PRECHANGEUPPER	0x001A
 #define NETDEV_CHANGELOWERSTATE	0x001B
-#define NETDEV_OFFLOAD_PUSH_VXLAN	0x001C
-#define NETDEV_OFFLOAD_PUSH_GENEVE	0x001D
+#define NETDEV_UDP_TUNNEL_PUSH_INFO	0x001C
 
 int register_netdevice_notifier(struct notifier_block *nb);
 int unregister_netdevice_notifier(struct notifier_block *nb);
@@ -2370,6 +2372,8 @@
 int init_dummy_netdev(struct net_device *dev);
 
 DECLARE_PER_CPU(int, xmit_recursion);
+#define XMIT_RECURSION_LIMIT	10
+
 static inline int dev_recursion_level(void)
 {
 	return this_cpu_read(xmit_recursion);
diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h
index 8f2237e..6c8cb9a 100644
--- a/include/linux/of_mdio.h
+++ b/include/linux/of_mdio.h
@@ -69,7 +69,7 @@
 }
 #endif /* CONFIG_OF */
 
-#if defined(CONFIG_OF) && defined(CONFIG_FIXED_PHY)
+#if defined(CONFIG_OF) && IS_ENABLED(CONFIG_FIXED_PHY)
 extern int of_phy_register_fixed_link(struct device_node *np);
 extern bool of_phy_is_fixed_link(struct device_node *np);
 #else
diff --git a/include/linux/page_idle.h b/include/linux/page_idle.h
index bf268fa..fec4027 100644
--- a/include/linux/page_idle.h
+++ b/include/linux/page_idle.h
@@ -46,33 +46,62 @@
 
 static inline bool page_is_young(struct page *page)
 {
-	return test_bit(PAGE_EXT_YOUNG, &lookup_page_ext(page)->flags);
+	struct page_ext *page_ext = lookup_page_ext(page);
+
+	if (unlikely(!page_ext))
+		return false;
+
+	return test_bit(PAGE_EXT_YOUNG, &page_ext->flags);
 }
 
 static inline void set_page_young(struct page *page)
 {
-	set_bit(PAGE_EXT_YOUNG, &lookup_page_ext(page)->flags);
+	struct page_ext *page_ext = lookup_page_ext(page);
+
+	if (unlikely(!page_ext))
+		return;
+
+	set_bit(PAGE_EXT_YOUNG, &page_ext->flags);
 }
 
 static inline bool test_and_clear_page_young(struct page *page)
 {
-	return test_and_clear_bit(PAGE_EXT_YOUNG,
-				  &lookup_page_ext(page)->flags);
+	struct page_ext *page_ext = lookup_page_ext(page);
+
+	if (unlikely(!page_ext))
+		return false;
+
+	return test_and_clear_bit(PAGE_EXT_YOUNG, &page_ext->flags);
 }
 
 static inline bool page_is_idle(struct page *page)
 {
-	return test_bit(PAGE_EXT_IDLE, &lookup_page_ext(page)->flags);
+	struct page_ext *page_ext = lookup_page_ext(page);
+
+	if (unlikely(!page_ext))
+		return false;
+
+	return test_bit(PAGE_EXT_IDLE, &page_ext->flags);
 }
 
 static inline void set_page_idle(struct page *page)
 {
-	set_bit(PAGE_EXT_IDLE, &lookup_page_ext(page)->flags);
+	struct page_ext *page_ext = lookup_page_ext(page);
+
+	if (unlikely(!page_ext))
+		return;
+
+	set_bit(PAGE_EXT_IDLE, &page_ext->flags);
 }
 
 static inline void clear_page_idle(struct page *page)
 {
-	clear_bit(PAGE_EXT_IDLE, &lookup_page_ext(page)->flags);
+	struct page_ext *page_ext = lookup_page_ext(page);
+
+	if (unlikely(!page_ext))
+		return;
+
+	clear_bit(PAGE_EXT_IDLE, &page_ext->flags);
 }
 #endif /* CONFIG_64BIT */
 
diff --git a/include/linux/platform_data/b53.h b/include/linux/platform_data/b53.h
new file mode 100644
index 0000000..69d279c
--- /dev/null
+++ b/include/linux/platform_data/b53.h
@@ -0,0 +1,33 @@
+/*
+ * B53 platform data
+ *
+ * Copyright (C) 2013 Jonas Gorski <jogo@openwrt.org>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#ifndef __B53_H
+#define __B53_H
+
+#include <linux/kernel.h>
+
+struct b53_platform_data {
+	u32 chip_id;
+	u16 enabled_ports;
+
+	/* only used by MMAP'd driver */
+	unsigned big_endian:1;
+	void __iomem *regs;
+};
+
+#endif
diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h
new file mode 100644
index 0000000..562a65e
--- /dev/null
+++ b/include/linux/ptr_ring.h
@@ -0,0 +1,393 @@
+/*
+ *	Definitions for the 'struct ptr_ring' datastructure.
+ *
+ *	Author:
+ *		Michael S. Tsirkin <mst@redhat.com>
+ *
+ *	Copyright (C) 2016 Red Hat, 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.
+ *
+ *	This is a limited-size FIFO maintaining pointers in FIFO order, with
+ *	one CPU producing entries and another consuming entries from a FIFO.
+ *
+ *	This implementation tries to minimize cache-contention when there is a
+ *	single producer and a single consumer CPU.
+ */
+
+#ifndef _LINUX_PTR_RING_H
+#define _LINUX_PTR_RING_H 1
+
+#ifdef __KERNEL__
+#include <linux/spinlock.h>
+#include <linux/cache.h>
+#include <linux/types.h>
+#include <linux/compiler.h>
+#include <linux/cache.h>
+#include <linux/slab.h>
+#include <asm/errno.h>
+#endif
+
+struct ptr_ring {
+	int producer ____cacheline_aligned_in_smp;
+	spinlock_t producer_lock;
+	int consumer ____cacheline_aligned_in_smp;
+	spinlock_t consumer_lock;
+	/* Shared consumer/producer data */
+	/* Read-only by both the producer and the consumer */
+	int size ____cacheline_aligned_in_smp; /* max entries in queue */
+	void **queue;
+};
+
+/* Note: callers invoking this in a loop must use a compiler barrier,
+ * for example cpu_relax().  If ring is ever resized, callers must hold
+ * producer_lock - see e.g. ptr_ring_full.  Otherwise, if callers don't hold
+ * producer_lock, the next call to __ptr_ring_produce may fail.
+ */
+static inline bool __ptr_ring_full(struct ptr_ring *r)
+{
+	return r->queue[r->producer];
+}
+
+static inline bool ptr_ring_full(struct ptr_ring *r)
+{
+	bool ret;
+
+	spin_lock(&r->producer_lock);
+	ret = __ptr_ring_full(r);
+	spin_unlock(&r->producer_lock);
+
+	return ret;
+}
+
+static inline bool ptr_ring_full_irq(struct ptr_ring *r)
+{
+	bool ret;
+
+	spin_lock_irq(&r->producer_lock);
+	ret = __ptr_ring_full(r);
+	spin_unlock_irq(&r->producer_lock);
+
+	return ret;
+}
+
+static inline bool ptr_ring_full_any(struct ptr_ring *r)
+{
+	unsigned long flags;
+	bool ret;
+
+	spin_lock_irqsave(&r->producer_lock, flags);
+	ret = __ptr_ring_full(r);
+	spin_unlock_irqrestore(&r->producer_lock, flags);
+
+	return ret;
+}
+
+static inline bool ptr_ring_full_bh(struct ptr_ring *r)
+{
+	bool ret;
+
+	spin_lock_bh(&r->producer_lock);
+	ret = __ptr_ring_full(r);
+	spin_unlock_bh(&r->producer_lock);
+
+	return ret;
+}
+
+/* Note: callers invoking this in a loop must use a compiler barrier,
+ * for example cpu_relax(). Callers must hold producer_lock.
+ */
+static inline int __ptr_ring_produce(struct ptr_ring *r, void *ptr)
+{
+	if (r->queue[r->producer])
+		return -ENOSPC;
+
+	r->queue[r->producer++] = ptr;
+	if (unlikely(r->producer >= r->size))
+		r->producer = 0;
+	return 0;
+}
+
+static inline int ptr_ring_produce(struct ptr_ring *r, void *ptr)
+{
+	int ret;
+
+	spin_lock(&r->producer_lock);
+	ret = __ptr_ring_produce(r, ptr);
+	spin_unlock(&r->producer_lock);
+
+	return ret;
+}
+
+static inline int ptr_ring_produce_irq(struct ptr_ring *r, void *ptr)
+{
+	int ret;
+
+	spin_lock_irq(&r->producer_lock);
+	ret = __ptr_ring_produce(r, ptr);
+	spin_unlock_irq(&r->producer_lock);
+
+	return ret;
+}
+
+static inline int ptr_ring_produce_any(struct ptr_ring *r, void *ptr)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&r->producer_lock, flags);
+	ret = __ptr_ring_produce(r, ptr);
+	spin_unlock_irqrestore(&r->producer_lock, flags);
+
+	return ret;
+}
+
+static inline int ptr_ring_produce_bh(struct ptr_ring *r, void *ptr)
+{
+	int ret;
+
+	spin_lock_bh(&r->producer_lock);
+	ret = __ptr_ring_produce(r, ptr);
+	spin_unlock_bh(&r->producer_lock);
+
+	return ret;
+}
+
+/* Note: callers invoking this in a loop must use a compiler barrier,
+ * for example cpu_relax(). Callers must take consumer_lock
+ * if they dereference the pointer - see e.g. PTR_RING_PEEK_CALL.
+ * If ring is never resized, and if the pointer is merely
+ * tested, there's no need to take the lock - see e.g.  __ptr_ring_empty.
+ */
+static inline void *__ptr_ring_peek(struct ptr_ring *r)
+{
+	return r->queue[r->consumer];
+}
+
+/* Note: callers invoking this in a loop must use a compiler barrier,
+ * for example cpu_relax(). Callers must take consumer_lock
+ * if the ring is ever resized - see e.g. ptr_ring_empty.
+ */
+static inline bool __ptr_ring_empty(struct ptr_ring *r)
+{
+	return !__ptr_ring_peek(r);
+}
+
+static inline bool ptr_ring_empty(struct ptr_ring *r)
+{
+	bool ret;
+
+	spin_lock(&r->consumer_lock);
+	ret = __ptr_ring_empty(r);
+	spin_unlock(&r->consumer_lock);
+
+	return ret;
+}
+
+static inline bool ptr_ring_empty_irq(struct ptr_ring *r)
+{
+	bool ret;
+
+	spin_lock_irq(&r->consumer_lock);
+	ret = __ptr_ring_empty(r);
+	spin_unlock_irq(&r->consumer_lock);
+
+	return ret;
+}
+
+static inline bool ptr_ring_empty_any(struct ptr_ring *r)
+{
+	unsigned long flags;
+	bool ret;
+
+	spin_lock_irqsave(&r->consumer_lock, flags);
+	ret = __ptr_ring_empty(r);
+	spin_unlock_irqrestore(&r->consumer_lock, flags);
+
+	return ret;
+}
+
+static inline bool ptr_ring_empty_bh(struct ptr_ring *r)
+{
+	bool ret;
+
+	spin_lock_bh(&r->consumer_lock);
+	ret = __ptr_ring_empty(r);
+	spin_unlock_bh(&r->consumer_lock);
+
+	return ret;
+}
+
+/* Must only be called after __ptr_ring_peek returned !NULL */
+static inline void __ptr_ring_discard_one(struct ptr_ring *r)
+{
+	r->queue[r->consumer++] = NULL;
+	if (unlikely(r->consumer >= r->size))
+		r->consumer = 0;
+}
+
+static inline void *__ptr_ring_consume(struct ptr_ring *r)
+{
+	void *ptr;
+
+	ptr = __ptr_ring_peek(r);
+	if (ptr)
+		__ptr_ring_discard_one(r);
+
+	return ptr;
+}
+
+static inline void *ptr_ring_consume(struct ptr_ring *r)
+{
+	void *ptr;
+
+	spin_lock(&r->consumer_lock);
+	ptr = __ptr_ring_consume(r);
+	spin_unlock(&r->consumer_lock);
+
+	return ptr;
+}
+
+static inline void *ptr_ring_consume_irq(struct ptr_ring *r)
+{
+	void *ptr;
+
+	spin_lock_irq(&r->consumer_lock);
+	ptr = __ptr_ring_consume(r);
+	spin_unlock_irq(&r->consumer_lock);
+
+	return ptr;
+}
+
+static inline void *ptr_ring_consume_any(struct ptr_ring *r)
+{
+	unsigned long flags;
+	void *ptr;
+
+	spin_lock_irqsave(&r->consumer_lock, flags);
+	ptr = __ptr_ring_consume(r);
+	spin_unlock_irqrestore(&r->consumer_lock, flags);
+
+	return ptr;
+}
+
+static inline void *ptr_ring_consume_bh(struct ptr_ring *r)
+{
+	void *ptr;
+
+	spin_lock_bh(&r->consumer_lock);
+	ptr = __ptr_ring_consume(r);
+	spin_unlock_bh(&r->consumer_lock);
+
+	return ptr;
+}
+
+/* Cast to structure type and call a function without discarding from FIFO.
+ * Function must return a value.
+ * Callers must take consumer_lock.
+ */
+#define __PTR_RING_PEEK_CALL(r, f) ((f)(__ptr_ring_peek(r)))
+
+#define PTR_RING_PEEK_CALL(r, f) ({ \
+	typeof((f)(NULL)) __PTR_RING_PEEK_CALL_v; \
+	\
+	spin_lock(&(r)->consumer_lock); \
+	__PTR_RING_PEEK_CALL_v = __PTR_RING_PEEK_CALL(r, f); \
+	spin_unlock(&(r)->consumer_lock); \
+	__PTR_RING_PEEK_CALL_v; \
+})
+
+#define PTR_RING_PEEK_CALL_IRQ(r, f) ({ \
+	typeof((f)(NULL)) __PTR_RING_PEEK_CALL_v; \
+	\
+	spin_lock_irq(&(r)->consumer_lock); \
+	__PTR_RING_PEEK_CALL_v = __PTR_RING_PEEK_CALL(r, f); \
+	spin_unlock_irq(&(r)->consumer_lock); \
+	__PTR_RING_PEEK_CALL_v; \
+})
+
+#define PTR_RING_PEEK_CALL_BH(r, f) ({ \
+	typeof((f)(NULL)) __PTR_RING_PEEK_CALL_v; \
+	\
+	spin_lock_bh(&(r)->consumer_lock); \
+	__PTR_RING_PEEK_CALL_v = __PTR_RING_PEEK_CALL(r, f); \
+	spin_unlock_bh(&(r)->consumer_lock); \
+	__PTR_RING_PEEK_CALL_v; \
+})
+
+#define PTR_RING_PEEK_CALL_ANY(r, f) ({ \
+	typeof((f)(NULL)) __PTR_RING_PEEK_CALL_v; \
+	unsigned long __PTR_RING_PEEK_CALL_f;\
+	\
+	spin_lock_irqsave(&(r)->consumer_lock, __PTR_RING_PEEK_CALL_f); \
+	__PTR_RING_PEEK_CALL_v = __PTR_RING_PEEK_CALL(r, f); \
+	spin_unlock_irqrestore(&(r)->consumer_lock, __PTR_RING_PEEK_CALL_f); \
+	__PTR_RING_PEEK_CALL_v; \
+})
+
+static inline void **__ptr_ring_init_queue_alloc(int size, gfp_t gfp)
+{
+	return kzalloc(ALIGN(size * sizeof(void *), SMP_CACHE_BYTES), gfp);
+}
+
+static inline int ptr_ring_init(struct ptr_ring *r, int size, gfp_t gfp)
+{
+	r->queue = __ptr_ring_init_queue_alloc(size, gfp);
+	if (!r->queue)
+		return -ENOMEM;
+
+	r->size = size;
+	r->producer = r->consumer = 0;
+	spin_lock_init(&r->producer_lock);
+	spin_lock_init(&r->consumer_lock);
+
+	return 0;
+}
+
+static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp,
+				  void (*destroy)(void *))
+{
+	unsigned long flags;
+	int producer = 0;
+	void **queue = __ptr_ring_init_queue_alloc(size, gfp);
+	void **old;
+	void *ptr;
+
+	if (!queue)
+		return -ENOMEM;
+
+	spin_lock_irqsave(&(r)->producer_lock, flags);
+
+	while ((ptr = ptr_ring_consume(r)))
+		if (producer < size)
+			queue[producer++] = ptr;
+		else if (destroy)
+			destroy(ptr);
+
+	r->size = size;
+	r->producer = producer;
+	r->consumer = 0;
+	old = r->queue;
+	r->queue = queue;
+
+	spin_unlock_irqrestore(&(r)->producer_lock, flags);
+
+	kfree(old);
+
+	return 0;
+}
+
+static inline void ptr_ring_cleanup(struct ptr_ring *r, void (*destroy)(void *))
+{
+	void *ptr;
+
+	if (destroy)
+		while ((ptr = ptr_ring_consume(r)))
+			destroy(ptr);
+	kfree(r->queue);
+}
+
+#endif /* _LINUX_PTR_RING_H  */
diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h
index f8ff711..71d523b 100644
--- a/include/linux/qed/qed_eth_if.h
+++ b/include/linux/qed/qed_eth_if.h
@@ -128,11 +128,73 @@
 	void (*force_mac) (void *dev, u8 *mac);
 };
 
+#ifdef CONFIG_DCB
+/* Prototype declaration of qed_eth_dcbnl_ops should match with the declaration
+ * of dcbnl_rtnl_ops structure.
+ */
+struct qed_eth_dcbnl_ops {
+	/* IEEE 802.1Qaz std */
+	int (*ieee_getpfc)(struct qed_dev *cdev, struct ieee_pfc *pfc);
+	int (*ieee_setpfc)(struct qed_dev *cdev, struct ieee_pfc *pfc);
+	int (*ieee_getets)(struct qed_dev *cdev, struct ieee_ets *ets);
+	int (*ieee_setets)(struct qed_dev *cdev, struct ieee_ets *ets);
+	int (*ieee_peer_getets)(struct qed_dev *cdev, struct ieee_ets *ets);
+	int (*ieee_peer_getpfc)(struct qed_dev *cdev, struct ieee_pfc *pfc);
+	int (*ieee_getapp)(struct qed_dev *cdev, struct dcb_app *app);
+	int (*ieee_setapp)(struct qed_dev *cdev, struct dcb_app *app);
+
+	/* CEE std */
+	u8 (*getstate)(struct qed_dev *cdev);
+	u8 (*setstate)(struct qed_dev *cdev, u8 state);
+	void (*getpgtccfgtx)(struct qed_dev *cdev, int prio, u8 *prio_type,
+			     u8 *pgid, u8 *bw_pct, u8 *up_map);
+	void (*getpgbwgcfgtx)(struct qed_dev *cdev, int pgid, u8 *bw_pct);
+	void (*getpgtccfgrx)(struct qed_dev *cdev, int prio, u8 *prio_type,
+			     u8 *pgid, u8 *bw_pct, u8 *up_map);
+	void (*getpgbwgcfgrx)(struct qed_dev *cdev, int pgid, u8 *bw_pct);
+	void (*getpfccfg)(struct qed_dev *cdev, int prio, u8 *setting);
+	void (*setpfccfg)(struct qed_dev *cdev, int prio, u8 setting);
+	u8 (*getcap)(struct qed_dev *cdev, int capid, u8 *cap);
+	int (*getnumtcs)(struct qed_dev *cdev, int tcid, u8 *num);
+	u8 (*getpfcstate)(struct qed_dev *cdev);
+	int (*getapp)(struct qed_dev *cdev, u8 idtype, u16 id);
+	u8 (*getfeatcfg)(struct qed_dev *cdev, int featid, u8 *flags);
+
+	/* DCBX configuration */
+	u8 (*getdcbx)(struct qed_dev *cdev);
+	void (*setpgtccfgtx)(struct qed_dev *cdev, int prio,
+			     u8 pri_type, u8 pgid, u8 bw_pct, u8 up_map);
+	void (*setpgtccfgrx)(struct qed_dev *cdev, int prio,
+			     u8 pri_type, u8 pgid, u8 bw_pct, u8 up_map);
+	void (*setpgbwgcfgtx)(struct qed_dev *cdev, int pgid, u8 bw_pct);
+	void (*setpgbwgcfgrx)(struct qed_dev *cdev, int pgid, u8 bw_pct);
+	u8 (*setall)(struct qed_dev *cdev);
+	int (*setnumtcs)(struct qed_dev *cdev, int tcid, u8 num);
+	void (*setpfcstate)(struct qed_dev *cdev, u8 state);
+	int (*setapp)(struct qed_dev *cdev, u8 idtype, u16 idval, u8 up);
+	u8 (*setdcbx)(struct qed_dev *cdev, u8 state);
+	u8 (*setfeatcfg)(struct qed_dev *cdev, int featid, u8 flags);
+
+	/* Peer apps */
+	int (*peer_getappinfo)(struct qed_dev *cdev,
+			       struct dcb_peer_app_info *info,
+			       u16 *app_count);
+	int (*peer_getapptable)(struct qed_dev *cdev, struct dcb_app *table);
+
+	/* CEE peer */
+	int (*cee_peer_getpfc)(struct qed_dev *cdev, struct cee_pfc *pfc);
+	int (*cee_peer_getpg)(struct qed_dev *cdev, struct cee_pg *pg);
+};
+#endif
+
 struct qed_eth_ops {
 	const struct qed_common_ops *common;
 #ifdef CONFIG_QED_SRIOV
 	const struct qed_iov_hv_ops *iov;
 #endif
+#ifdef CONFIG_DCB
+	const struct qed_eth_dcbnl_ops *dcb;
+#endif
 
 	int (*fill_dev_info)(struct qed_dev *cdev,
 			     struct qed_dev_eth_info *info);
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index e8cc49f..e1d5122 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -34,6 +34,96 @@
 	DCBX_MAX_PROTOCOL_TYPE
 };
 
+#ifdef CONFIG_DCB
+#define QED_LLDP_CHASSIS_ID_STAT_LEN 4
+#define QED_LLDP_PORT_ID_STAT_LEN 4
+#define QED_DCBX_MAX_APP_PROTOCOL 32
+#define QED_MAX_PFC_PRIORITIES 8
+#define QED_DCBX_DSCP_SIZE 64
+
+struct qed_dcbx_lldp_remote {
+	u32 peer_chassis_id[QED_LLDP_CHASSIS_ID_STAT_LEN];
+	u32 peer_port_id[QED_LLDP_PORT_ID_STAT_LEN];
+	bool enable_rx;
+	bool enable_tx;
+	u32 tx_interval;
+	u32 max_credit;
+};
+
+struct qed_dcbx_lldp_local {
+	u32 local_chassis_id[QED_LLDP_CHASSIS_ID_STAT_LEN];
+	u32 local_port_id[QED_LLDP_PORT_ID_STAT_LEN];
+};
+
+struct qed_dcbx_app_prio {
+	u8 roce;
+	u8 roce_v2;
+	u8 fcoe;
+	u8 iscsi;
+	u8 eth;
+};
+
+struct qed_dbcx_pfc_params {
+	bool willing;
+	bool enabled;
+	u8 prio[QED_MAX_PFC_PRIORITIES];
+	u8 max_tc;
+};
+
+struct qed_app_entry {
+	bool ethtype;
+	bool enabled;
+	u8 prio;
+	u16 proto_id;
+	enum dcbx_protocol_type proto_type;
+};
+
+struct qed_dcbx_params {
+	struct qed_app_entry app_entry[QED_DCBX_MAX_APP_PROTOCOL];
+	u16 num_app_entries;
+	bool app_willing;
+	bool app_valid;
+	bool app_error;
+	bool ets_willing;
+	bool ets_enabled;
+	bool ets_cbs;
+	bool valid;
+	u8 ets_pri_tc_tbl[QED_MAX_PFC_PRIORITIES];
+	u8 ets_tc_bw_tbl[QED_MAX_PFC_PRIORITIES];
+	u8 ets_tc_tsa_tbl[QED_MAX_PFC_PRIORITIES];
+	struct qed_dbcx_pfc_params pfc;
+	u8 max_ets_tc;
+};
+
+struct qed_dcbx_admin_params {
+	struct qed_dcbx_params params;
+	bool valid;
+};
+
+struct qed_dcbx_remote_params {
+	struct qed_dcbx_params params;
+	bool valid;
+};
+
+struct qed_dcbx_operational_params {
+	struct qed_dcbx_app_prio app_prio;
+	struct qed_dcbx_params params;
+	bool valid;
+	bool enabled;
+	bool ieee;
+	bool cee;
+	u32 err;
+};
+
+struct qed_dcbx_get {
+	struct qed_dcbx_operational_params operational;
+	struct qed_dcbx_lldp_remote lldp_remote;
+	struct qed_dcbx_lldp_local lldp_local;
+	struct qed_dcbx_remote_params remote;
+	struct qed_dcbx_admin_params local;
+};
+#endif
+
 enum qed_led_mode {
 	QED_LED_MODE_OFF,
 	QED_LED_MODE_ON,
diff --git a/include/linux/reservation.h b/include/linux/reservation.h
index 49d0576..b0f305e 100644
--- a/include/linux/reservation.h
+++ b/include/linux/reservation.h
@@ -49,12 +49,27 @@
 extern struct lock_class_key reservation_seqcount_class;
 extern const char reservation_seqcount_string[];
 
+/**
+ * struct reservation_object_list - a list of shared fences
+ * @rcu: for internal use
+ * @shared_count: table of shared fences
+ * @shared_max: for growing shared fence table
+ * @shared: shared fence table
+ */
 struct reservation_object_list {
 	struct rcu_head rcu;
 	u32 shared_count, shared_max;
 	struct fence __rcu *shared[];
 };
 
+/**
+ * struct reservation_object - a reservation object manages fences for a buffer
+ * @lock: update side lock
+ * @seq: sequence count for managing RCU read-side synchronization
+ * @fence_excl: the exclusive fence, if there is one currently
+ * @fence: list of current shared fences
+ * @staged: staged copy of shared fences for RCU updates
+ */
 struct reservation_object {
 	struct ww_mutex lock;
 	seqcount_t seq;
@@ -68,6 +83,10 @@
 #define reservation_object_assert_held(obj) \
 	lockdep_assert_held(&(obj)->lock.base)
 
+/**
+ * reservation_object_init - initialize a reservation object
+ * @obj: the reservation object
+ */
 static inline void
 reservation_object_init(struct reservation_object *obj)
 {
@@ -79,6 +98,10 @@
 	obj->staged = NULL;
 }
 
+/**
+ * reservation_object_fini - destroys a reservation object
+ * @obj: the reservation object
+ */
 static inline void
 reservation_object_fini(struct reservation_object *obj)
 {
@@ -106,6 +129,14 @@
 	ww_mutex_destroy(&obj->lock);
 }
 
+/**
+ * reservation_object_get_list - get the reservation object's
+ * shared fence list, with update-side lock held
+ * @obj: the reservation object
+ *
+ * Returns the shared fence list.  Does NOT take references to
+ * the fence.  The obj->lock must be held.
+ */
 static inline struct reservation_object_list *
 reservation_object_get_list(struct reservation_object *obj)
 {
@@ -113,6 +144,17 @@
 					 reservation_object_held(obj));
 }
 
+/**
+ * reservation_object_get_excl - get the reservation object's
+ * exclusive fence, with update-side lock held
+ * @obj: the reservation object
+ *
+ * Returns the exclusive fence (if any).  Does NOT take a
+ * reference.  The obj->lock must be held.
+ *
+ * RETURNS
+ * The exclusive fence or NULL
+ */
 static inline struct fence *
 reservation_object_get_excl(struct reservation_object *obj)
 {
@@ -120,6 +162,17 @@
 					 reservation_object_held(obj));
 }
 
+/**
+ * reservation_object_get_excl_rcu - get the reservation object's
+ * exclusive fence, without lock held.
+ * @obj: the reservation object
+ *
+ * If there is an exclusive fence, this atomically increments it's
+ * reference count and returns it.
+ *
+ * RETURNS
+ * The exclusive fence or NULL if none
+ */
 static inline struct fence *
 reservation_object_get_excl_rcu(struct reservation_object *obj)
 {
diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index c006cc9..2daece8 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -89,8 +89,9 @@
 void net_dec_egress_queue(void);
 #endif
 
-extern void rtnetlink_init(void);
-extern void __rtnl_unlock(void);
+void rtnetlink_init(void);
+void __rtnl_unlock(void);
+void rtnl_kfree_skbs(struct sk_buff *head, struct sk_buff *tail);
 
 #define ASSERT_RTNL() do { \
 	if (unlikely(!rtnl_is_locked())) { \
diff --git a/include/linux/rxrpc.h b/include/linux/rxrpc.h
index a53915c..1e8f216 100644
--- a/include/linux/rxrpc.h
+++ b/include/linux/rxrpc.h
@@ -40,16 +40,18 @@
 
 /*
  * RxRPC control messages
+ * - If neither abort or accept are specified, the message is a data message.
  * - terminal messages mean that a user call ID tag can be recycled
+ * - s/r/- indicate whether these are applicable to sendmsg() and/or recvmsg()
  */
-#define RXRPC_USER_CALL_ID	1	/* user call ID specifier */
-#define RXRPC_ABORT		2	/* abort request / notification [terminal] */
-#define RXRPC_ACK		3	/* [Server] RPC op final ACK received [terminal] */
-#define RXRPC_NET_ERROR		5	/* network error received [terminal] */
-#define RXRPC_BUSY		6	/* server busy received [terminal] */
-#define RXRPC_LOCAL_ERROR	7	/* local error generated [terminal] */
-#define RXRPC_NEW_CALL		8	/* [Server] new incoming call notification */
-#define RXRPC_ACCEPT		9	/* [Server] accept request */
+#define RXRPC_USER_CALL_ID	1	/* sr: user call ID specifier */
+#define RXRPC_ABORT		2	/* sr: abort request / notification [terminal] */
+#define RXRPC_ACK		3	/* -r: [Service] RPC op final ACK received [terminal] */
+#define RXRPC_NET_ERROR		5	/* -r: network error received [terminal] */
+#define RXRPC_BUSY		6	/* -r: server busy received [terminal] */
+#define RXRPC_LOCAL_ERROR	7	/* -r: local error generated [terminal] */
+#define RXRPC_NEW_CALL		8	/* -r: [Service] new incoming call notification */
+#define RXRPC_ACCEPT		9	/* s-: [Service] accept request */
 
 /*
  * RxRPC security levels
diff --git a/include/linux/skb_array.h b/include/linux/skb_array.h
new file mode 100644
index 0000000..678bfbf
--- /dev/null
+++ b/include/linux/skb_array.h
@@ -0,0 +1,169 @@
+/*
+ *	Definitions for the 'struct skb_array' datastructure.
+ *
+ *	Author:
+ *		Michael S. Tsirkin <mst@redhat.com>
+ *
+ *	Copyright (C) 2016 Red Hat, 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.
+ *
+ *	Limited-size FIFO of skbs. Can be used more or less whenever
+ *	sk_buff_head can be used, except you need to know the queue size in
+ *	advance.
+ *	Implemented as a type-safe wrapper around ptr_ring.
+ */
+
+#ifndef _LINUX_SKB_ARRAY_H
+#define _LINUX_SKB_ARRAY_H 1
+
+#ifdef __KERNEL__
+#include <linux/ptr_ring.h>
+#include <linux/skbuff.h>
+#include <linux/if_vlan.h>
+#endif
+
+struct skb_array {
+	struct ptr_ring ring;
+};
+
+/* Might be slightly faster than skb_array_full below, but callers invoking
+ * this in a loop must use a compiler barrier, for example cpu_relax().
+ */
+static inline bool __skb_array_full(struct skb_array *a)
+{
+	return __ptr_ring_full(&a->ring);
+}
+
+static inline bool skb_array_full(struct skb_array *a)
+{
+	return ptr_ring_full(&a->ring);
+}
+
+static inline int skb_array_produce(struct skb_array *a, struct sk_buff *skb)
+{
+	return ptr_ring_produce(&a->ring, skb);
+}
+
+static inline int skb_array_produce_irq(struct skb_array *a, struct sk_buff *skb)
+{
+	return ptr_ring_produce_irq(&a->ring, skb);
+}
+
+static inline int skb_array_produce_bh(struct skb_array *a, struct sk_buff *skb)
+{
+	return ptr_ring_produce_bh(&a->ring, skb);
+}
+
+static inline int skb_array_produce_any(struct skb_array *a, struct sk_buff *skb)
+{
+	return ptr_ring_produce_any(&a->ring, skb);
+}
+
+/* Might be slightly faster than skb_array_empty below, but only safe if the
+ * array is never resized. Also, callers invoking this in a loop must take care
+ * to use a compiler barrier, for example cpu_relax().
+ */
+static inline bool __skb_array_empty(struct skb_array *a)
+{
+	return !__ptr_ring_peek(&a->ring);
+}
+
+static inline bool skb_array_empty(struct skb_array *a)
+{
+	return ptr_ring_empty(&a->ring);
+}
+
+static inline bool skb_array_empty_bh(struct skb_array *a)
+{
+	return ptr_ring_empty_bh(&a->ring);
+}
+
+static inline bool skb_array_empty_irq(struct skb_array *a)
+{
+	return ptr_ring_empty_irq(&a->ring);
+}
+
+static inline bool skb_array_empty_any(struct skb_array *a)
+{
+	return ptr_ring_empty_any(&a->ring);
+}
+
+static inline struct sk_buff *skb_array_consume(struct skb_array *a)
+{
+	return ptr_ring_consume(&a->ring);
+}
+
+static inline struct sk_buff *skb_array_consume_irq(struct skb_array *a)
+{
+	return ptr_ring_consume_irq(&a->ring);
+}
+
+static inline struct sk_buff *skb_array_consume_any(struct skb_array *a)
+{
+	return ptr_ring_consume_any(&a->ring);
+}
+
+static inline struct sk_buff *skb_array_consume_bh(struct skb_array *a)
+{
+	return ptr_ring_consume_bh(&a->ring);
+}
+
+static inline int __skb_array_len_with_tag(struct sk_buff *skb)
+{
+	if (likely(skb)) {
+		int len = skb->len;
+
+		if (skb_vlan_tag_present(skb))
+			len += VLAN_HLEN;
+
+		return len;
+	} else {
+		return 0;
+	}
+}
+
+static inline int skb_array_peek_len(struct skb_array *a)
+{
+	return PTR_RING_PEEK_CALL(&a->ring, __skb_array_len_with_tag);
+}
+
+static inline int skb_array_peek_len_irq(struct skb_array *a)
+{
+	return PTR_RING_PEEK_CALL_IRQ(&a->ring, __skb_array_len_with_tag);
+}
+
+static inline int skb_array_peek_len_bh(struct skb_array *a)
+{
+	return PTR_RING_PEEK_CALL_BH(&a->ring, __skb_array_len_with_tag);
+}
+
+static inline int skb_array_peek_len_any(struct skb_array *a)
+{
+	return PTR_RING_PEEK_CALL_ANY(&a->ring, __skb_array_len_with_tag);
+}
+
+static inline int skb_array_init(struct skb_array *a, int size, gfp_t gfp)
+{
+	return ptr_ring_init(&a->ring, size, gfp);
+}
+
+void __skb_array_destroy_skb(void *ptr)
+{
+	kfree_skb(ptr);
+}
+
+int skb_array_resize(struct skb_array *a, int size, gfp_t gfp)
+{
+	return ptr_ring_resize(&a->ring, size, gfp, __skb_array_destroy_skb);
+}
+
+static inline void skb_array_cleanup(struct skb_array *a)
+{
+	ptr_ring_cleanup(&a->ring, __skb_array_destroy_skb);
+}
+
+#endif /* _LINUX_SKB_ARRAY_H  */
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index ffdaca9..0507dbf 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -135,6 +135,8 @@
 	void (*bus_setup)(void __iomem *ioaddr);
 	int (*init)(struct platform_device *pdev, void *priv);
 	void (*exit)(struct platform_device *pdev, void *priv);
+	void (*suspend)(struct platform_device *pdev, void *priv);
+	void (*resume)(struct platform_device *pdev, void *priv);
 	void *bsp_priv;
 	struct stmmac_axi *axi;
 	int has_gmac4;
diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 37dbacf..816b754 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -21,6 +21,9 @@
 	struct timespec64 ts64;
 
 	if (!tv)
+		return do_sys_settimeofday64(NULL, tz);
+
+	if (!timespec_valid(tv))
 		return -EINVAL;
 
 	ts64 = timespec_to_timespec64(*tv);
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
new file mode 100644
index 0000000..1c912f8
--- /dev/null
+++ b/include/linux/virtio_net.h
@@ -0,0 +1,101 @@
+#ifndef _LINUX_VIRTIO_NET_H
+#define _LINUX_VIRTIO_NET_H
+
+#include <linux/if_vlan.h>
+#include <uapi/linux/virtio_net.h>
+
+static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
+					const struct virtio_net_hdr *hdr,
+					bool little_endian)
+{
+	unsigned short gso_type = 0;
+
+	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
+		switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
+		case VIRTIO_NET_HDR_GSO_TCPV4:
+			gso_type = SKB_GSO_TCPV4;
+			break;
+		case VIRTIO_NET_HDR_GSO_TCPV6:
+			gso_type = SKB_GSO_TCPV6;
+			break;
+		case VIRTIO_NET_HDR_GSO_UDP:
+			gso_type = SKB_GSO_UDP;
+			break;
+		default:
+			return -EINVAL;
+		}
+
+		if (hdr->gso_type & VIRTIO_NET_HDR_GSO_ECN)
+			gso_type |= SKB_GSO_TCP_ECN;
+
+		if (hdr->gso_size == 0)
+			return -EINVAL;
+	}
+
+	if (hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
+		u16 start = __virtio16_to_cpu(little_endian, hdr->csum_start);
+		u16 off = __virtio16_to_cpu(little_endian, hdr->csum_offset);
+
+		if (!skb_partial_csum_set(skb, start, off))
+			return -EINVAL;
+	}
+
+	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
+		u16 gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size);
+
+		skb_shinfo(skb)->gso_size = gso_size;
+		skb_shinfo(skb)->gso_type = gso_type;
+
+		/* Header must be checked, and gso_segs computed. */
+		skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
+		skb_shinfo(skb)->gso_segs = 0;
+	}
+
+	return 0;
+}
+
+static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb,
+					  struct virtio_net_hdr *hdr,
+					  bool little_endian)
+{
+	memset(hdr, 0, sizeof(*hdr));
+
+	if (skb_is_gso(skb)) {
+		struct skb_shared_info *sinfo = skb_shinfo(skb);
+
+		/* This is a hint as to how much should be linear. */
+		hdr->hdr_len = __cpu_to_virtio16(little_endian,
+						 skb_headlen(skb));
+		hdr->gso_size = __cpu_to_virtio16(little_endian,
+						  sinfo->gso_size);
+		if (sinfo->gso_type & SKB_GSO_TCPV4)
+			hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
+		else if (sinfo->gso_type & SKB_GSO_TCPV6)
+			hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
+		else if (sinfo->gso_type & SKB_GSO_UDP)
+			hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP;
+		else
+			return -EINVAL;
+		if (sinfo->gso_type & SKB_GSO_TCP_ECN)
+			hdr->gso_type |= VIRTIO_NET_HDR_GSO_ECN;
+	} else
+		hdr->gso_type = VIRTIO_NET_HDR_GSO_NONE;
+
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
+		hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
+		if (skb_vlan_tag_present(skb))
+			hdr->csum_start = __cpu_to_virtio16(little_endian,
+				skb_checksum_start_offset(skb) + VLAN_HLEN);
+		else
+			hdr->csum_start = __cpu_to_virtio16(little_endian,
+				skb_checksum_start_offset(skb));
+		hdr->csum_offset = __cpu_to_virtio16(little_endian,
+				skb->csum_offset);
+	} else if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
+		hdr->flags = VIRTIO_NET_HDR_F_DATA_VALID;
+	} /* else everything is zero */
+
+	return 0;
+}
+
+#endif /* _LINUX_VIRTIO_BYTEORDER */
diff --git a/include/net/6lowpan.h b/include/net/6lowpan.h
index da84cf9..5ab4c99 100644
--- a/include/net/6lowpan.h
+++ b/include/net/6lowpan.h
@@ -141,6 +141,16 @@
 	u8 priv[0] __aligned(sizeof(void *));
 };
 
+struct lowpan_802154_neigh {
+	__le16 short_addr;
+};
+
+static inline
+struct lowpan_802154_neigh *lowpan_802154_neigh(void *neigh_priv)
+{
+	return neigh_priv;
+}
+
 static inline
 struct lowpan_dev *lowpan_dev(const struct net_device *dev)
 {
@@ -244,6 +254,12 @@
 	return false;
 }
 
+static inline bool lowpan_802154_is_valid_src_short_addr(__le16 addr)
+{
+	/* First bit of addr is multicast, reserved or 802.15.4 specific */
+	return !(addr & cpu_to_le16(0x8000));
+}
+
 static inline void lowpan_push_hc_data(u8 **hc_ptr, const void *data,
 				       const size_t len)
 {
diff --git a/include/net/act_api.h b/include/net/act_api.h
index 9a9a8ed..fb82b5b 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -2,8 +2,8 @@
 #define __NET_ACT_API_H
 
 /*
- * Public police action API for classifiers/qdiscs
- */
+ * Public action API for classifiers/qdiscs
+*/
 
 #include <net/sch_generic.h>
 #include <net/pkt_sched.h>
@@ -76,6 +76,16 @@
 
 	if (tm->lastuse != now)
 		tm->lastuse = now;
+	if (unlikely(!tm->firstuse))
+		tm->firstuse = now;
+}
+
+static inline void tcf_tm_dump(struct tcf_t *dtm, const struct tcf_t *stm)
+{
+	dtm->install = jiffies_to_clock_t(jiffies - stm->install);
+	dtm->lastuse = jiffies_to_clock_t(jiffies - stm->lastuse);
+	dtm->firstuse = jiffies_to_clock_t(jiffies - stm->firstuse);
+	dtm->expires = jiffies_to_clock_t(stm->expires);
 }
 
 struct tc_action {
@@ -97,7 +107,8 @@
 	char    kind[IFNAMSIZ];
 	__u32   type; /* TBD to match kind */
 	struct module		*owner;
-	int     (*act)(struct sk_buff *, const struct tc_action *, struct tcf_result *);
+	int     (*act)(struct sk_buff *, const struct tc_action *,
+		       struct tcf_result *);
 	int     (*dump)(struct sk_buff *, struct tc_action *, int, int);
 	void	(*cleanup)(struct tc_action *, int bind);
 	int     (*lookup)(struct net *, struct tc_action *, u32);
@@ -115,8 +126,8 @@
 };
 
 static inline
-int tc_action_net_init(struct tc_action_net *tn, const struct tc_action_ops *ops,
-		       unsigned int mask)
+int tc_action_net_init(struct tc_action_net *tn,
+		       const struct tc_action_ops *ops, unsigned int mask)
 {
 	int err = 0;
 
@@ -144,8 +155,8 @@
 		       struct tc_action *a);
 int tcf_hash_search(struct tc_action_net *tn, struct tc_action *a, u32 index);
 u32 tcf_hash_new_index(struct tc_action_net *tn);
-int tcf_hash_check(struct tc_action_net *tn, u32 index, struct tc_action *a,
-		   int bind);
+bool tcf_hash_check(struct tc_action_net *tn, u32 index, struct tc_action *a,
+		    int bind);
 int tcf_hash_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
 		    struct tc_action *a, int size, int bind, bool cpustats);
 void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est);
@@ -159,7 +170,8 @@
 }
 
 int tcf_register_action(struct tc_action_ops *a, struct pernet_operations *ops);
-int tcf_unregister_action(struct tc_action_ops *a, struct pernet_operations *ops);
+int tcf_unregister_action(struct tc_action_ops *a,
+			  struct pernet_operations *ops);
 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);
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 730d856..9826d3a 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -94,6 +94,16 @@
 void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr);
 void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr);
 
+void addrconf_add_linklocal(struct inet6_dev *idev,
+			    const struct in6_addr *addr, u32 flags);
+
+int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev,
+				 const struct prefix_info *pinfo,
+				 struct inet6_dev *in6_dev,
+				 const struct in6_addr *addr, int addr_type,
+				 u32 addr_flags, bool sllao, bool tokenized,
+				 __u32 valid_lft, u32 prefered_lft);
+
 static inline int addrconf_ifid_eui48(u8 *eui, struct net_device *dev)
 {
 	if (dev->addr_len != ETH_ALEN)
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 6392167..7bbb00d 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -2367,19 +2367,23 @@
  *	(invoked with the wireless_dev mutex held)
  *
  * @connect: Connect to the ESS with the specified parameters. When connected,
- *	call cfg80211_connect_result() with status code %WLAN_STATUS_SUCCESS.
- *	If the connection fails for some reason, call cfg80211_connect_result()
- *	with the status from the AP. The driver is allowed to roam to other
- *	BSSes within the ESS when the other BSS matches the connect parameters.
- *	When such roaming is initiated by the driver, the driver is expected to
- *	verify that the target matches the configured security parameters and
- *	to use Reassociation Request frame instead of Association Request frame.
- *	The connect function can also be used to request the driver to perform
- *	a specific roam when connected to an ESS. In that case, the prev_bssid
+ *	call cfg80211_connect_result()/cfg80211_connect_bss() with status code
+ *	%WLAN_STATUS_SUCCESS. If the connection fails for some reason, call
+ *	cfg80211_connect_result()/cfg80211_connect_bss() with the status code
+ *	from the AP or cfg80211_connect_timeout() if no frame with status code
+ *	was received.
+ *	The driver is allowed to roam to other BSSes within the ESS when the
+ *	other BSS matches the connect parameters. When such roaming is initiated
+ *	by the driver, the driver is expected to verify that the target matches
+ *	the configured security parameters and to use Reassociation Request
+ *	frame instead of Association Request frame.
+ *	The connect function can also be used to request the driver to perform a
+ *	specific roam when connected to an ESS. In that case, the prev_bssid
  *	parameter is set to the BSSID of the currently associated BSS as an
- *	indication of requesting reassociation. In both the driver-initiated and
- *	new connect() call initiated roaming cases, the result of roaming is
- *	indicated with a call to cfg80211_roamed() or cfg80211_roamed_bss().
+ *	indication of requesting reassociation.
+ *	In both the driver-initiated and new connect() call initiated roaming
+ *	cases, the result of roaming is indicated with a call to
+ *	cfg80211_roamed() or cfg80211_roamed_bss().
  *	(invoked with the wireless_dev mutex held)
  * @disconnect: Disconnect from the BSS/ESS.
  *	(invoked with the wireless_dev mutex held)
@@ -3080,6 +3084,24 @@
 };
 
 /**
+ * struct wiphy_iftype_ext_capab - extended capabilities per interface type
+ * @iftype: interface type
+ * @extended_capabilities: extended capabilities supported by the driver,
+ *	additional capabilities might be supported by userspace; these are the
+ *	802.11 extended capabilities ("Extended Capabilities element") and are
+ *	in the same format as in the information element. See IEEE Std
+ *	802.11-2012 8.4.2.29 for the defined fields.
+ * @extended_capabilities_mask: mask of the valid values
+ * @extended_capabilities_len: length of the extended capabilities
+ */
+struct wiphy_iftype_ext_capab {
+	enum nl80211_iftype iftype;
+	const u8 *extended_capabilities;
+	const u8 *extended_capabilities_mask;
+	u8 extended_capabilities_len;
+};
+
+/**
  * struct wiphy - wireless hardware description
  * @reg_notifier: the driver's regulatory notification callback,
  *	note that if your driver uses wiphy_apply_custom_regulatory()
@@ -3199,9 +3221,14 @@
  *	additional capabilities might be supported by userspace; these are
  *	the 802.11 extended capabilities ("Extended Capabilities element")
  *	and are in the same format as in the information element. See
- *	802.11-2012 8.4.2.29 for the defined fields.
+ *	802.11-2012 8.4.2.29 for the defined fields. These are the default
+ *	extended capabilities to be used if the capabilities are not specified
+ *	for a specific interface type in iftype_ext_capab.
  * @extended_capabilities_mask: mask of the valid values
  * @extended_capabilities_len: length of the extended capabilities
+ * @iftype_ext_capab: array of extended capabilities per interface type
+ * @num_iftype_ext_capab: number of interface types for which extended
+ *	capabilities are specified separately.
  * @coalesce: packet coalescing support information
  *
  * @vendor_commands: array of vendor commands supported by the hardware
@@ -3301,6 +3328,9 @@
 	const u8 *extended_capabilities, *extended_capabilities_mask;
 	u8 extended_capabilities_len;
 
+	const struct wiphy_iftype_ext_capab *iftype_ext_capab;
+	unsigned int num_iftype_ext_capab;
+
 	/* If multiple wiphys are registered and you're handed e.g.
 	 * a regular netdev with assigned ieee80211_ptr, you won't
 	 * know whether it points to a wiphy your driver has registered
@@ -4680,7 +4710,7 @@
 void cfg80211_connect_bss(struct net_device *dev, const u8 *bssid,
 			  struct cfg80211_bss *bss, const u8 *req_ie,
 			  size_t req_ie_len, const u8 *resp_ie,
-			  size_t resp_ie_len, u16 status, gfp_t gfp);
+			  size_t resp_ie_len, int status, gfp_t gfp);
 
 /**
  * cfg80211_connect_result - notify cfg80211 of connection result
@@ -4710,6 +4740,29 @@
 }
 
 /**
+ * cfg80211_connect_timeout - notify cfg80211 of connection timeout
+ *
+ * @dev: network device
+ * @bssid: the BSSID of the AP
+ * @req_ie: association request IEs (maybe be %NULL)
+ * @req_ie_len: association request IEs length
+ * @gfp: allocation flags
+ *
+ * It should be called by the underlying driver whenever connect() has failed
+ * in a sequence where no explicit authentication/association rejection was
+ * received from the AP. This could happen, e.g., due to not being able to send
+ * out the Authentication or Association Request frame or timing out while
+ * waiting for the response.
+ */
+static inline void
+cfg80211_connect_timeout(struct net_device *dev, const u8 *bssid,
+			 const u8 *req_ie, size_t req_ie_len, gfp_t gfp)
+{
+	cfg80211_connect_bss(dev, bssid, NULL, req_ie, req_ie_len, NULL, 0, -1,
+			     gfp);
+}
+
+/**
  * cfg80211_roamed - notify cfg80211 of roaming
  *
  * @dev: network device
diff --git a/include/net/compat.h b/include/net/compat.h
index 48103cf..13de0cc 100644
--- a/include/net/compat.h
+++ b/include/net/compat.h
@@ -42,6 +42,7 @@
 
 int get_compat_msghdr(struct msghdr *, struct compat_msghdr __user *,
 		      struct sockaddr __user **, struct iovec **);
+struct sock_fprog __user *get_compat_bpf_fprog(char __user *optval);
 asmlinkage long compat_sys_sendmsg(int, struct compat_msghdr __user *,
 				   unsigned int);
 asmlinkage long compat_sys_sendmmsg(int, struct compat_mmsghdr __user *,
diff --git a/include/net/dsa.h b/include/net/dsa.h
index 17c3d37..20b3087 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -26,6 +26,7 @@
 	DSA_TAG_PROTO_TRAILER,
 	DSA_TAG_PROTO_EDSA,
 	DSA_TAG_PROTO_BRCM,
+	DSA_TAG_LAST,		/* MUST BE LAST */
 };
 
 #define DSA_MAX_SWITCHES	4
@@ -58,12 +59,11 @@
 	struct device_node *port_dn[DSA_MAX_PORTS];
 
 	/*
-	 * An array (with nr_chips elements) of which element [a]
-	 * indicates which port on this switch should be used to
-	 * send packets to that are destined for switch a.  Can be
-	 * NULL if there is only one switch chip.
+	 * An array of which element [a] indicates which port on this
+	 * switch should be used to send packets to that are destined
+	 * for switch a. Can be NULL if there is only one switch chip.
 	 */
-	s8		*rtable;
+	s8		rtable[DSA_MAX_SWITCHES];
 };
 
 struct dsa_platform_data {
@@ -85,6 +85,17 @@
 struct packet_type;
 
 struct dsa_switch_tree {
+	struct list_head	list;
+
+	/* Tree identifier */
+	u32 tree;
+
+	/* Number of switches attached to this tree */
+	struct kref refcount;
+
+	/* Has this tree been applied to the hardware? */
+	bool applied;
+
 	/*
 	 * Configuration data for the platform device that owns
 	 * this dsa switch tree instance.
@@ -100,12 +111,12 @@
 				       struct net_device *dev,
 				       struct packet_type *pt,
 				       struct net_device *orig_dev);
-	enum dsa_tag_protocol	tag_protocol;
 
 	/*
 	 * Original copy of the master netdev ethtool_ops
 	 */
 	struct ethtool_ops	master_ethtool_ops;
+	const struct ethtool_ops *master_orig_ethtool_ops;
 
 	/*
 	 * The switch and port to which the CPU is attached.
@@ -117,6 +128,17 @@
 	 * Data for the individual switch chips.
 	 */
 	struct dsa_switch	*ds[DSA_MAX_SWITCHES];
+
+	/*
+	 * Tagging protocol operations for adding and removing an
+	 * encapsulation tag.
+	 */
+	const struct dsa_device_ops *tag_ops;
+};
+
+struct dsa_port {
+	struct net_device	*netdev;
+	struct device_node	*dn;
 };
 
 struct dsa_switch {
@@ -144,6 +166,13 @@
 	 */
 	struct dsa_switch_driver	*drv;
 
+	/*
+	 * An array of which element [a] indicates which port on this
+	 * switch should be used to send packets to that are destined
+	 * for switch a. Can be NULL if there is only one switch chip.
+	 */
+	s8		rtable[DSA_MAX_SWITCHES];
+
 #ifdef CONFIG_NET_DSA_HWMON
 	/*
 	 * Hardware monitoring information
@@ -153,13 +182,19 @@
 #endif
 
 	/*
+	 * The lower device this switch uses to talk to the host
+	 */
+	struct net_device *master_netdev;
+
+	/*
 	 * Slave mii_bus and devices for the individual ports.
 	 */
 	u32			dsa_port_mask;
+	u32			cpu_port_mask;
 	u32			enabled_port_mask;
 	u32			phys_mii_mask;
+	struct dsa_port		ports[DSA_MAX_PORTS];
 	struct mii_bus		*slave_mii_bus;
-	struct net_device	*ports[DSA_MAX_PORTS];
 };
 
 static inline bool dsa_is_cpu_port(struct dsa_switch *ds, int p)
@@ -174,7 +209,7 @@
 
 static inline bool dsa_is_port_initialized(struct dsa_switch *ds, int p)
 {
-	return ds->enabled_port_mask & (1 << p) && ds->ports[p];
+	return ds->enabled_port_mask & (1 << p) && ds->ports[p].netdev;
 }
 
 static inline u8 dsa_upstream_port(struct dsa_switch *ds)
@@ -190,7 +225,7 @@
 	if (dst->cpu_switch == ds->index)
 		return dst->cpu_port;
 	else
-		return ds->cd->rtable[dst->cpu_switch];
+		return ds->rtable[dst->cpu_switch];
 }
 
 struct switchdev_trans;
@@ -344,4 +379,7 @@
 {
 	return dst->rcv != NULL;
 }
+
+void dsa_unregister_switch(struct dsa_switch *ds);
+int dsa_register_switch(struct dsa_switch *ds, struct device_node *np);
 #endif
diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index 59160de..456e4a6 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -17,7 +17,8 @@
 	u32			flags;
 	u32			table;
 	u8			action;
-	/* 3 bytes hole, try to use */
+	u8			l3mdev;
+	/* 2 bytes hole, try to use */
 	u32			target;
 	__be64			tun_id;
 	struct fib_rule __rcu	*ctarget;
@@ -36,6 +37,7 @@
 	void			*lookup_ptr;
 	void			*result;
 	struct fib_rule		*rule;
+	u32			table;
 	int			flags;
 #define FIB_LOOKUP_NOREF		1
 #define FIB_LOOKUP_IGNORE_LINKSTATE	2
@@ -89,7 +91,8 @@
 	[FRA_TABLE]     = { .type = NLA_U32 }, \
 	[FRA_SUPPRESS_PREFIXLEN] = { .type = NLA_U32 }, \
 	[FRA_SUPPRESS_IFGROUP] = { .type = NLA_U32 }, \
-	[FRA_GOTO]	= { .type = NLA_U32 }
+	[FRA_GOTO]	= { .type = NLA_U32 }, \
+	[FRA_L3MDEV]	= { .type = NLA_U8 }
 
 static inline void fib_rule_get(struct fib_rule *rule)
 {
@@ -102,6 +105,20 @@
 		kfree_rcu(rule, rcu);
 }
 
+#ifdef CONFIG_NET_L3_MASTER_DEV
+static inline u32 fib_rule_get_table(struct fib_rule *rule,
+				     struct fib_lookup_arg *arg)
+{
+	return rule->l3mdev ? arg->table : rule->table;
+}
+#else
+static inline u32 fib_rule_get_table(struct fib_rule *rule,
+				     struct fib_lookup_arg *arg)
+{
+	return rule->table;
+}
+#endif
+
 static inline u32 frh_get_table(struct fib_rule_hdr *frh, struct nlattr **nla)
 {
 	if (nla[FRA_TABLE])
@@ -117,4 +134,7 @@
 		     struct fib_lookup_arg *);
 int fib_default_rule_add(struct fib_rules_ops *, u32 pref, u32 table,
 			 u32 flags);
+
+int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh);
+int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh);
 #endif
diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h
index 610cd39..231e121 100644
--- a/include/net/gen_stats.h
+++ b/include/net/gen_stats.h
@@ -33,10 +33,12 @@
 				 spinlock_t *lock, struct gnet_dump *d,
 				 int padattr);
 
-int gnet_stats_copy_basic(struct gnet_dump *d,
+int gnet_stats_copy_basic(const seqcount_t *running,
+			  struct gnet_dump *d,
 			  struct gnet_stats_basic_cpu __percpu *cpu,
 			  struct gnet_stats_basic_packed *b);
-void __gnet_stats_copy_basic(struct gnet_stats_basic_packed *bstats,
+void __gnet_stats_copy_basic(const seqcount_t *running,
+			     struct gnet_stats_basic_packed *bstats,
 			     struct gnet_stats_basic_cpu __percpu *cpu,
 			     struct gnet_stats_basic_packed *b);
 int gnet_stats_copy_rate_est(struct gnet_dump *d,
@@ -52,13 +54,15 @@
 int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
 		      struct gnet_stats_basic_cpu __percpu *cpu_bstats,
 		      struct gnet_stats_rate_est64 *rate_est,
-		      spinlock_t *stats_lock, struct nlattr *opt);
+		      spinlock_t *stats_lock,
+		      seqcount_t *running, struct nlattr *opt);
 void gen_kill_estimator(struct gnet_stats_basic_packed *bstats,
 			struct gnet_stats_rate_est64 *rate_est);
 int gen_replace_estimator(struct gnet_stats_basic_packed *bstats,
 			  struct gnet_stats_basic_cpu __percpu *cpu_bstats,
 			  struct gnet_stats_rate_est64 *rate_est,
-			  spinlock_t *stats_lock, struct nlattr *opt);
+			  spinlock_t *stats_lock,
+			  seqcount_t *running, struct nlattr *opt);
 bool gen_estimator_active(const struct gnet_stats_basic_packed *bstats,
 			  const struct gnet_stats_rate_est64 *rate_est);
 #endif
diff --git a/include/net/geneve.h b/include/net/geneve.h
index cb544a5..ec0327d 100644
--- a/include/net/geneve.h
+++ b/include/net/geneve.h
@@ -1,10 +1,7 @@
 #ifndef __NET_GENEVE_H
 #define __NET_GENEVE_H  1
 
-#ifdef CONFIG_INET
 #include <net/udp_tunnel.h>
-#endif
-
 
 /* Geneve Header:
  *  +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
@@ -62,12 +59,6 @@
 	struct geneve_opt options[];
 };
 
-static inline void geneve_get_rx_port(struct net_device *netdev)
-{
-	ASSERT_RTNL();
-	call_netdevice_notifiers(NETDEV_OFFLOAD_PUSH_GENEVE, netdev);
-}
-
 #ifdef CONFIG_INET
 struct net_device *geneve_dev_create_fb(struct net *net, const char *name,
 					u8 name_assign_type, u16 dst_port);
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 54c7794..d97305d 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -18,6 +18,7 @@
 	__u8			prefix[0];	/* 0,8 or 16 */
 };
 
+#include <net/addrconf.h>
 #include <net/flow.h>
 #include <net/ip6_fib.h>
 #include <net/sock.h>
@@ -76,6 +77,8 @@
 
 struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6,
 				   int flags);
+struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
+			       int ifindex, struct flowi6 *fl6, int flags);
 
 int ip6_route_init(void);
 void ip6_route_cleanup(void);
@@ -86,9 +89,23 @@
 int ip6_ins_rt(struct rt6_info *);
 int ip6_del_rt(struct rt6_info *);
 
-int ip6_route_get_saddr(struct net *net, struct rt6_info *rt,
-			const struct in6_addr *daddr, unsigned int prefs,
-			struct in6_addr *saddr);
+static inline int ip6_route_get_saddr(struct net *net, struct rt6_info *rt,
+				      const struct in6_addr *daddr,
+				      unsigned int prefs,
+				      struct in6_addr *saddr)
+{
+	struct inet6_dev *idev =
+			rt ? ip6_dst_idev((struct dst_entry *)rt) : NULL;
+	int err = 0;
+
+	if (rt && rt->rt6i_prefsrc.plen)
+		*saddr = rt->rt6i_prefsrc.addr;
+	else
+		err = ipv6_dev_get_saddr(net, idev ? idev->dev : NULL,
+					 daddr, prefs, saddr);
+
+	return err;
+}
 
 struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr,
 			    const struct in6_addr *saddr, int oif, int flags);
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index dbf4444..a5e7035 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -132,6 +132,7 @@
 	int			ip_tnl_net_id;
 	struct gro_cells	gro_cells;
 	bool			collect_md;
+	bool			ignore_df;
 };
 
 #define TUNNEL_CSUM		__cpu_to_be16(0x01)
@@ -156,6 +157,7 @@
 	__be16 proto;
 	__be32 key;
 	__be32 seq;
+	int hdr_len;
 };
 
 #define PACKET_RCVD	0
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index af4c10e..cd6018a 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1232,7 +1232,7 @@
 const char *ip_vs_state_name(__u16 proto, int state);
 
 void ip_vs_tcp_conn_listen(struct ip_vs_conn *cp);
-int ip_vs_check_template(struct ip_vs_conn *ct);
+int ip_vs_check_template(struct ip_vs_conn *ct, struct ip_vs_dest *cdest);
 void ip_vs_random_dropentry(struct netns_ipvs *ipvs);
 int ip_vs_conn_init(void);
 void ip_vs_conn_cleanup(void);
diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h
index 374388d..e900950 100644
--- a/include/net/l3mdev.h
+++ b/include/net/l3mdev.h
@@ -11,6 +11,8 @@
 #ifndef _NET_L3MDEV_H_
 #define _NET_L3MDEV_H_
 
+#include <net/fib_rules.h>
+
 /**
  * struct l3mdev_ops - l3mdev operations
  *
@@ -36,11 +38,17 @@
 
 	/* IPv6 ops */
 	struct dst_entry * (*l3mdev_get_rt6_dst)(const struct net_device *dev,
-						 const struct flowi6 *fl6);
+						 struct flowi6 *fl6);
+	int		   (*l3mdev_get_saddr6)(struct net_device *dev,
+						const struct sock *sk,
+						struct flowi6 *fl6);
 };
 
 #ifdef CONFIG_NET_L3_MASTER_DEV
 
+int l3mdev_fib_rule_match(struct net *net, struct flowi *fl,
+			  struct fib_lookup_arg *arg);
+
 int l3mdev_master_ifindex_rcu(const struct net_device *dev);
 static inline int l3mdev_master_ifindex(struct net_device *dev)
 {
@@ -71,6 +79,31 @@
 	return rc;
 }
 
+static inline
+const struct net_device *l3mdev_master_dev_rcu(const struct net_device *_dev)
+{
+	/* netdev_master_upper_dev_get_rcu calls
+	 * list_first_or_null_rcu to walk the upper dev list.
+	 * list_first_or_null_rcu does not handle a const arg. We aren't
+	 * making changes, just want the master device from that list so
+	 * typecast to remove the const
+	 */
+	struct net_device *dev = (struct net_device *)_dev;
+	const struct net_device *master;
+
+	if (!dev)
+		return NULL;
+
+	if (netif_is_l3_master(dev))
+		master = dev;
+	else if (netif_is_l3_slave(dev))
+		master = netdev_master_upper_dev_get_rcu(dev);
+	else
+		master = NULL;
+
+	return master;
+}
+
 /* get index of an interface to use for FIB lookups. For devices
  * enslaved to an L3 master device FIB lookups are based on the
  * master index
@@ -134,7 +167,9 @@
 
 int l3mdev_get_saddr(struct net *net, int ifindex, struct flowi4 *fl4);
 
-struct dst_entry *l3mdev_get_rt6_dst(struct net *net, const struct flowi6 *fl6);
+struct dst_entry *l3mdev_get_rt6_dst(struct net *net, struct flowi6 *fl6);
+int l3mdev_get_saddr6(struct net *net, const struct sock *sk,
+		      struct flowi6 *fl6);
 
 static inline
 struct sk_buff *l3mdev_l3_rcv(struct sk_buff *skb, u16 proto)
@@ -180,6 +215,12 @@
 	return 0;
 }
 
+static inline
+const struct net_device *l3mdev_master_dev_rcu(const struct net_device *dev)
+{
+	return NULL;
+}
+
 static inline int l3mdev_fib_oif_rcu(struct net_device *dev)
 {
 	return dev ? dev->ifindex : 0;
@@ -220,11 +261,17 @@
 }
 
 static inline
-struct dst_entry *l3mdev_get_rt6_dst(struct net *net, const struct flowi6 *fl6)
+struct dst_entry *l3mdev_get_rt6_dst(struct net *net, struct flowi6 *fl6)
 {
 	return NULL;
 }
 
+static inline int l3mdev_get_saddr6(struct net *net, const struct sock *sk,
+				    struct flowi6 *fl6)
+{
+	return 0;
+}
+
 static inline
 struct sk_buff *l3mdev_ip_rcv(struct sk_buff *skb)
 {
@@ -236,6 +283,13 @@
 {
 	return skb;
 }
+
+static inline
+int l3mdev_fib_rule_match(struct net *net, struct flowi *fl,
+			  struct fib_lookup_arg *arg)
+{
+	return 1;
+}
 #endif
 
 #endif /* _NET_L3MDEV_H_ */
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index be30b05..a52009f 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -21,6 +21,7 @@
 #include <linux/skbuff.h>
 #include <linux/ieee80211.h>
 #include <net/cfg80211.h>
+#include <net/codel.h>
 #include <asm/unaligned.h>
 
 /**
@@ -895,7 +896,18 @@
 				unsigned long jiffies;
 			};
 			/* NB: vif can be NULL for injected frames */
-			struct ieee80211_vif *vif;
+			union {
+				/* NB: vif can be NULL for injected frames */
+				struct ieee80211_vif *vif;
+
+				/* When packets are enqueued on txq it's easy
+				 * to re-construct the vif pointer. There's no
+				 * more space in tx_info so it can be used to
+				 * store the necessary enqueue time for packet
+				 * sojourn time computation.
+				 */
+				codel_time_t enqueue_time;
+			};
 			struct ieee80211_key_conf *hw_key;
 			u32 flags;
 			/* 4 bytes free */
@@ -2147,9 +2159,6 @@
  * @n_cipher_schemes: a size of an array of cipher schemes definitions.
  * @cipher_schemes: a pointer to an array of cipher scheme definitions
  *	supported by HW.
- *
- * @txq_ac_max_pending: maximum number of frames per AC pending in all txq
- *	entries for a vif.
  */
 struct ieee80211_hw {
 	struct ieee80211_conf conf;
@@ -2180,7 +2189,6 @@
 	u8 uapsd_max_sp_len;
 	u8 n_cipher_schemes;
 	const struct ieee80211_cipher_scheme *cipher_schemes;
-	int txq_ac_max_pending;
 };
 
 static inline bool _ieee80211_hw_check(struct ieee80211_hw *hw,
diff --git a/include/net/ndisc.h b/include/net/ndisc.h
index 2d8edaa..be1fe228 100644
--- a/include/net/ndisc.h
+++ b/include/net/ndisc.h
@@ -35,6 +35,7 @@
 	ND_OPT_ROUTE_INFO = 24,		/* RFC4191 */
 	ND_OPT_RDNSS = 25,		/* RFC5006 */
 	ND_OPT_DNSSL = 31,		/* RFC6106 */
+	ND_OPT_6CO = 34,		/* RFC6775 */
 	__ND_OPT_MAX
 };
 
@@ -53,11 +54,21 @@
 
 #include <net/neighbour.h>
 
+/* Set to 3 to get tracing... */
+#define ND_DEBUG 1
+
+#define ND_PRINTK(val, level, fmt, ...)				\
+do {								\
+	if (val <= ND_DEBUG)					\
+		net_##level##_ratelimited(fmt, ##__VA_ARGS__);	\
+} while (0)
+
 struct ctl_table;
 struct inet6_dev;
 struct net_device;
 struct net_proto_family;
 struct sk_buff;
+struct prefix_info;
 
 extern struct neigh_table nd_tbl;
 
@@ -99,20 +110,201 @@
 #endif
 	struct nd_opt_hdr *nd_useropts;
 	struct nd_opt_hdr *nd_useropts_end;
+#if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN)
+	struct nd_opt_hdr *nd_802154_opt_array[ND_OPT_TARGET_LL_ADDR + 1];
+#endif
 };
 
-#define nd_opts_src_lladdr	nd_opt_array[ND_OPT_SOURCE_LL_ADDR]
-#define nd_opts_tgt_lladdr	nd_opt_array[ND_OPT_TARGET_LL_ADDR]
-#define nd_opts_pi		nd_opt_array[ND_OPT_PREFIX_INFO]
-#define nd_opts_pi_end		nd_opt_array[__ND_OPT_PREFIX_INFO_END]
-#define nd_opts_rh		nd_opt_array[ND_OPT_REDIRECT_HDR]
-#define nd_opts_mtu		nd_opt_array[ND_OPT_MTU]
+#define nd_opts_src_lladdr		nd_opt_array[ND_OPT_SOURCE_LL_ADDR]
+#define nd_opts_tgt_lladdr		nd_opt_array[ND_OPT_TARGET_LL_ADDR]
+#define nd_opts_pi			nd_opt_array[ND_OPT_PREFIX_INFO]
+#define nd_opts_pi_end			nd_opt_array[__ND_OPT_PREFIX_INFO_END]
+#define nd_opts_rh			nd_opt_array[ND_OPT_REDIRECT_HDR]
+#define nd_opts_mtu			nd_opt_array[ND_OPT_MTU]
+#define nd_802154_opts_src_lladdr	nd_802154_opt_array[ND_OPT_SOURCE_LL_ADDR]
+#define nd_802154_opts_tgt_lladdr	nd_802154_opt_array[ND_OPT_TARGET_LL_ADDR]
 
 #define NDISC_OPT_SPACE(len) (((len)+2+7)&~7)
 
-struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len,
+struct ndisc_options *ndisc_parse_options(const struct net_device *dev,
+					  u8 *opt, int opt_len,
 					  struct ndisc_options *ndopts);
 
+void __ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data,
+			      int data_len, int pad);
+
+#define NDISC_OPS_REDIRECT_DATA_SPACE	2
+
+/*
+ * This structure defines the hooks for IPv6 neighbour discovery.
+ * The following hooks can be defined; unless noted otherwise, they are
+ * optional and can be filled with a null pointer.
+ *
+ * int (*is_useropt)(u8 nd_opt_type):
+ *     This function is called when IPv6 decide RA userspace options. if
+ *     this function returns 1 then the option given by nd_opt_type will
+ *     be handled as userspace option additional to the IPv6 options.
+ *
+ * int (*parse_options)(const struct net_device *dev,
+ *			struct nd_opt_hdr *nd_opt,
+ *			struct ndisc_options *ndopts):
+ *     This function is called while parsing ndisc ops and put each position
+ *     as pointer into ndopts. If this function return unequal 0, then this
+ *     function took care about the ndisc option, if 0 then the IPv6 ndisc
+ *     option parser will take care about that option.
+ *
+ * void (*update)(const struct net_device *dev, struct neighbour *n,
+ *		  u32 flags, u8 icmp6_type,
+ *		  const struct ndisc_options *ndopts):
+ *     This function is called when IPv6 ndisc updates the neighbour cache
+ *     entry. Additional options which can be updated may be previously
+ *     parsed by parse_opts callback and accessible over ndopts parameter.
+ *
+ * int (*opt_addr_space)(const struct net_device *dev, u8 icmp6_type,
+ *			 struct neighbour *neigh, u8 *ha_buf,
+ *			 u8 **ha):
+ *     This function is called when the necessary option space will be
+ *     calculated before allocating a skb. The parameters neigh, ha_buf
+ *     abd ha are available on NDISC_REDIRECT messages only.
+ *
+ * void (*fill_addr_option)(const struct net_device *dev,
+ *			    struct sk_buff *skb, u8 icmp6_type,
+ *			    const u8 *ha):
+ *     This function is called when the skb will finally fill the option
+ *     fields inside skb. NOTE: this callback should fill the option
+ *     fields to the skb which are previously indicated by opt_space
+ *     parameter. That means the decision to add such option should
+ *     not lost between these two callbacks, e.g. protected by interface
+ *     up state.
+ *
+ * void (*prefix_rcv_add_addr)(struct net *net, struct net_device *dev,
+ *			       const struct prefix_info *pinfo,
+ *			       struct inet6_dev *in6_dev,
+ *			       struct in6_addr *addr,
+ *			       int addr_type, u32 addr_flags,
+ *			       bool sllao, bool tokenized,
+ *			       __u32 valid_lft, u32 prefered_lft,
+ *			       bool dev_addr_generated):
+ *     This function is called when a RA messages is received with valid
+ *     PIO option fields and an IPv6 address will be added to the interface
+ *     for autoconfiguration. The parameter dev_addr_generated reports about
+ *     if the address was based on dev->dev_addr or not. This can be used
+ *     to add a second address if link-layer operates with two link layer
+ *     addresses. E.g. 802.15.4 6LoWPAN.
+ */
+struct ndisc_ops {
+	int	(*is_useropt)(u8 nd_opt_type);
+	int	(*parse_options)(const struct net_device *dev,
+				 struct nd_opt_hdr *nd_opt,
+				 struct ndisc_options *ndopts);
+	void	(*update)(const struct net_device *dev, struct neighbour *n,
+			  u32 flags, u8 icmp6_type,
+			  const struct ndisc_options *ndopts);
+	int	(*opt_addr_space)(const struct net_device *dev, u8 icmp6_type,
+				  struct neighbour *neigh, u8 *ha_buf,
+				  u8 **ha);
+	void	(*fill_addr_option)(const struct net_device *dev,
+				    struct sk_buff *skb, u8 icmp6_type,
+				    const u8 *ha);
+	void	(*prefix_rcv_add_addr)(struct net *net, struct net_device *dev,
+				       const struct prefix_info *pinfo,
+				       struct inet6_dev *in6_dev,
+				       struct in6_addr *addr,
+				       int addr_type, u32 addr_flags,
+				       bool sllao, bool tokenized,
+				       __u32 valid_lft, u32 prefered_lft,
+				       bool dev_addr_generated);
+};
+
+#if IS_ENABLED(CONFIG_IPV6)
+static inline int ndisc_ops_is_useropt(const struct net_device *dev,
+				       u8 nd_opt_type)
+{
+	if (dev->ndisc_ops && dev->ndisc_ops->is_useropt)
+		return dev->ndisc_ops->is_useropt(nd_opt_type);
+	else
+		return 0;
+}
+
+static inline int ndisc_ops_parse_options(const struct net_device *dev,
+					  struct nd_opt_hdr *nd_opt,
+					  struct ndisc_options *ndopts)
+{
+	if (dev->ndisc_ops && dev->ndisc_ops->parse_options)
+		return dev->ndisc_ops->parse_options(dev, nd_opt, ndopts);
+	else
+		return 0;
+}
+
+static inline void ndisc_ops_update(const struct net_device *dev,
+					  struct neighbour *n, u32 flags,
+					  u8 icmp6_type,
+					  const struct ndisc_options *ndopts)
+{
+	if (dev->ndisc_ops && dev->ndisc_ops->update)
+		dev->ndisc_ops->update(dev, n, flags, icmp6_type, ndopts);
+}
+
+static inline int ndisc_ops_opt_addr_space(const struct net_device *dev,
+					   u8 icmp6_type)
+{
+	if (dev->ndisc_ops && dev->ndisc_ops->opt_addr_space &&
+	    icmp6_type != NDISC_REDIRECT)
+		return dev->ndisc_ops->opt_addr_space(dev, icmp6_type, NULL,
+						      NULL, NULL);
+	else
+		return 0;
+}
+
+static inline int ndisc_ops_redirect_opt_addr_space(const struct net_device *dev,
+						    struct neighbour *neigh,
+						    u8 *ha_buf, u8 **ha)
+{
+	if (dev->ndisc_ops && dev->ndisc_ops->opt_addr_space)
+		return dev->ndisc_ops->opt_addr_space(dev, NDISC_REDIRECT,
+						      neigh, ha_buf, ha);
+	else
+		return 0;
+}
+
+static inline void ndisc_ops_fill_addr_option(const struct net_device *dev,
+					      struct sk_buff *skb,
+					      u8 icmp6_type)
+{
+	if (dev->ndisc_ops && dev->ndisc_ops->fill_addr_option &&
+	    icmp6_type != NDISC_REDIRECT)
+		dev->ndisc_ops->fill_addr_option(dev, skb, icmp6_type, NULL);
+}
+
+static inline void ndisc_ops_fill_redirect_addr_option(const struct net_device *dev,
+						       struct sk_buff *skb,
+						       const u8 *ha)
+{
+	if (dev->ndisc_ops && dev->ndisc_ops->fill_addr_option)
+		dev->ndisc_ops->fill_addr_option(dev, skb, NDISC_REDIRECT, ha);
+}
+
+static inline void ndisc_ops_prefix_rcv_add_addr(struct net *net,
+						 struct net_device *dev,
+						 const struct prefix_info *pinfo,
+						 struct inet6_dev *in6_dev,
+						 struct in6_addr *addr,
+						 int addr_type, u32 addr_flags,
+						 bool sllao, bool tokenized,
+						 __u32 valid_lft,
+						 u32 prefered_lft,
+						 bool dev_addr_generated)
+{
+	if (dev->ndisc_ops && dev->ndisc_ops->prefix_rcv_add_addr)
+		dev->ndisc_ops->prefix_rcv_add_addr(net, dev, pinfo, in6_dev,
+						    addr, addr_type,
+						    addr_flags, sllao,
+						    tokenized, valid_lft,
+						    prefered_lft,
+						    dev_addr_generated);
+}
+#endif
+
 /*
  * Return the padding between the option length and the start of the
  * link addr.  Currently only IP-over-InfiniBand needs this, although
@@ -127,21 +319,46 @@
 	}
 }
 
-static inline int ndisc_opt_addr_space(struct net_device *dev)
+static inline int __ndisc_opt_addr_space(unsigned char addr_len, int pad)
 {
-	return NDISC_OPT_SPACE(dev->addr_len +
-			       ndisc_addr_option_pad(dev->type));
+	return NDISC_OPT_SPACE(addr_len + pad);
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+static inline int ndisc_opt_addr_space(struct net_device *dev, u8 icmp6_type)
+{
+	return __ndisc_opt_addr_space(dev->addr_len,
+				      ndisc_addr_option_pad(dev->type)) +
+		ndisc_ops_opt_addr_space(dev, icmp6_type);
+}
+
+static inline int ndisc_redirect_opt_addr_space(struct net_device *dev,
+						struct neighbour *neigh,
+						u8 *ops_data_buf,
+						u8 **ops_data)
+{
+	return __ndisc_opt_addr_space(dev->addr_len,
+				      ndisc_addr_option_pad(dev->type)) +
+		ndisc_ops_redirect_opt_addr_space(dev, neigh, ops_data_buf,
+						  ops_data);
+}
+#endif
+
+static inline u8 *__ndisc_opt_addr_data(struct nd_opt_hdr *p,
+					unsigned char addr_len, int prepad)
+{
+	u8 *lladdr = (u8 *)(p + 1);
+	int lladdrlen = p->nd_opt_len << 3;
+	if (lladdrlen != __ndisc_opt_addr_space(addr_len, prepad))
+		return NULL;
+	return lladdr + prepad;
 }
 
 static inline u8 *ndisc_opt_addr_data(struct nd_opt_hdr *p,
 				      struct net_device *dev)
 {
-	u8 *lladdr = (u8 *)(p + 1);
-	int lladdrlen = p->nd_opt_len << 3;
-	int prepad = ndisc_addr_option_pad(dev->type);
-	if (lladdrlen != ndisc_opt_addr_space(dev))
-		return NULL;
-	return lladdr + prepad;
+	return __ndisc_opt_addr_data(p, dev->addr_len,
+				     ndisc_addr_option_pad(dev->type));
 }
 
 static inline u32 ndisc_hashfn(const void *pkey, const struct net_device *dev, __u32 *hash_rnd)
@@ -194,6 +411,9 @@
 int ndisc_mc_map(const struct in6_addr *addr, char *buf, struct net_device *dev,
 		 int dir);
 
+void ndisc_update(const struct net_device *dev, struct neighbour *neigh,
+		  const u8 *lladdr, u8 new, u32 flags, u8 icmp6_type,
+		  struct ndisc_options *ndopts);
 
 /*
  *	IGMP
diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h
index 9c5638a..0dbce55 100644
--- a/include/net/netfilter/nf_queue.h
+++ b/include/net/netfilter/nf_queue.h
@@ -28,8 +28,8 @@
 						struct nf_hook_ops *ops);
 };
 
-void nf_register_queue_handler(const struct nf_queue_handler *qh);
-void nf_unregister_queue_handler(void);
+void nf_register_queue_handler(struct net *net, const struct nf_queue_handler *qh);
+void nf_unregister_queue_handler(struct net *net);
 void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict);
 
 void nf_queue_entry_get_refs(struct nf_queue_entry *entry);
diff --git a/include/net/netns/netfilter.h b/include/net/netns/netfilter.h
index 38aa498..36d7235 100644
--- a/include/net/netns/netfilter.h
+++ b/include/net/netns/netfilter.h
@@ -5,11 +5,13 @@
 
 struct proc_dir_entry;
 struct nf_logger;
+struct nf_queue_handler;
 
 struct netns_nf {
 #if defined CONFIG_PROC_FS
 	struct proc_dir_entry *proc_netfilter;
 #endif
+	const struct nf_queue_handler __rcu *queue_handler;
 	const struct nf_logger __rcu *nf_loggers[NFPROTO_NUMPROTO];
 #ifdef CONFIG_SYSCTL
 	struct ctl_table_header *nf_log_dir_header;
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 0f7efa8..3722dda 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -392,16 +392,20 @@
 	};
 };
 
-static inline bool tc_should_offload(struct net_device *dev, u32 flags)
+static inline bool tc_should_offload(const struct net_device *dev,
+				     const struct tcf_proto *tp, u32 flags)
 {
+	const struct Qdisc *sch = tp->q;
+	const struct Qdisc_class_ops *cops = sch->ops->cl_ops;
+
 	if (!(dev->features & NETIF_F_HW_TC))
 		return false;
-
 	if (flags & TCA_CLS_FLAGS_SKIP_HW)
 		return false;
-
 	if (!dev->netdev_ops->ndo_setup_tc)
 		return false;
+	if (cops && cops->tcf_cl_offload)
+		return cops->tcf_cl_offload(tp->classid);
 
 	return true;
 }
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index fea53f4..7caa99b 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -67,12 +67,12 @@
 };
 
 void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc);
-void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires, bool throttle);
+void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires);
 
 static inline void qdisc_watchdog_schedule(struct qdisc_watchdog *wd,
 					   psched_time_t expires)
 {
-	qdisc_watchdog_schedule_ns(wd, PSCHED_TICKS2NS(expires), true);
+	qdisc_watchdog_schedule_ns(wd, PSCHED_TICKS2NS(expires));
 }
 
 void qdisc_watchdog_cancel(struct qdisc_watchdog *wd);
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index a1fd76c..4f7cee8 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -26,14 +26,6 @@
 enum qdisc_state_t {
 	__QDISC_STATE_SCHED,
 	__QDISC_STATE_DEACTIVATED,
-	__QDISC_STATE_THROTTLED,
-};
-
-/*
- * following bits are only changed while qdisc lock is held
- */
-enum qdisc___state_t {
-	__QDISC___STATE_RUNNING = 1,
 };
 
 struct qdisc_size_table {
@@ -70,30 +62,23 @@
 	struct list_head	list;
 	u32			handle;
 	u32			parent;
-	int			(*reshape_fail)(struct sk_buff *skb,
-					struct Qdisc *q);
-
 	void			*u32_node;
 
-	/* This field is deprecated, but it is still used by CBQ
-	 * and it will live until better solution will be invented.
-	 */
-	struct Qdisc		*__parent;
 	struct netdev_queue	*dev_queue;
 
 	struct gnet_stats_rate_est64	rate_est;
 	struct gnet_stats_basic_cpu __percpu *cpu_bstats;
 	struct gnet_stats_queue	__percpu *cpu_qstats;
 
-	struct Qdisc		*next_sched;
-	struct sk_buff		*gso_skb;
 	/*
 	 * For performance sake on SMP, we put highly modified fields at the end
 	 */
+	struct Qdisc		*next_sched ____cacheline_aligned_in_smp;
+	struct sk_buff		*gso_skb;
 	unsigned long		state;
 	struct sk_buff_head	q;
 	struct gnet_stats_basic_packed bstats;
-	unsigned int		__state;
+	seqcount_t		running;
 	struct gnet_stats_queue	qstats;
 	struct rcu_head		rcu_head;
 	int			padded;
@@ -104,20 +89,24 @@
 
 static inline bool qdisc_is_running(const struct Qdisc *qdisc)
 {
-	return (qdisc->__state & __QDISC___STATE_RUNNING) ? true : false;
+	return (raw_read_seqcount(&qdisc->running) & 1) ? true : false;
 }
 
 static inline bool qdisc_run_begin(struct Qdisc *qdisc)
 {
 	if (qdisc_is_running(qdisc))
 		return false;
-	qdisc->__state |= __QDISC___STATE_RUNNING;
+	/* Variant of write_seqcount_begin() telling lockdep a trylock
+	 * was attempted.
+	 */
+	raw_write_seqcount_begin(&qdisc->running);
+	seqcount_acquire(&qdisc->running.dep_map, 0, 1, _RET_IP_);
 	return true;
 }
 
 static inline void qdisc_run_end(struct Qdisc *qdisc)
 {
-	qdisc->__state &= ~__QDISC___STATE_RUNNING;
+	write_seqcount_end(&qdisc->running);
 }
 
 static inline bool qdisc_may_bulk(const struct Qdisc *qdisc)
@@ -135,21 +124,6 @@
 #endif
 }
 
-static inline bool qdisc_is_throttled(const struct Qdisc *qdisc)
-{
-	return test_bit(__QDISC_STATE_THROTTLED, &qdisc->state) ? true : false;
-}
-
-static inline void qdisc_throttled(struct Qdisc *qdisc)
-{
-	set_bit(__QDISC_STATE_THROTTLED, &qdisc->state);
-}
-
-static inline void qdisc_unthrottled(struct Qdisc *qdisc)
-{
-	clear_bit(__QDISC_STATE_THROTTLED, &qdisc->state);
-}
-
 struct Qdisc_class_ops {
 	/* Child qdisc manipulation */
 	struct netdev_queue *	(*select_queue)(struct Qdisc *, struct tcmsg *);
@@ -168,6 +142,7 @@
 
 	/* Filter manipulation */
 	struct tcf_proto __rcu ** (*tcf_chain)(struct Qdisc *, unsigned long);
+	bool			(*tcf_cl_offload)(u32 classid);
 	unsigned long		(*bind_tcf)(struct Qdisc *, unsigned long,
 					u32 classid);
 	void			(*unbind_tcf)(struct Qdisc *, unsigned long);
@@ -188,7 +163,6 @@
 	int 			(*enqueue)(struct sk_buff *, struct Qdisc *);
 	struct sk_buff *	(*dequeue)(struct Qdisc *);
 	struct sk_buff *	(*peek)(struct Qdisc *);
-	unsigned int		(*drop)(struct Qdisc *);
 
 	int			(*init)(struct Qdisc *, struct nlattr *arg);
 	void			(*reset)(struct Qdisc *);
@@ -321,6 +295,14 @@
 	return qdisc_lock(root);
 }
 
+static inline seqcount_t *qdisc_root_sleeping_running(const struct Qdisc *qdisc)
+{
+	struct Qdisc *root = qdisc_root_sleeping(qdisc);
+
+	ASSERT_RTNL();
+	return &root->running;
+}
+
 static inline struct net_device *qdisc_dev(const struct Qdisc *qdisc)
 {
 	return qdisc->dev_queue->dev;
@@ -664,22 +646,6 @@
 	return __qdisc_queue_drop_head(sch, &sch->q);
 }
 
-static inline struct sk_buff *__qdisc_dequeue_tail(struct Qdisc *sch,
-						   struct sk_buff_head *list)
-{
-	struct sk_buff *skb = __skb_dequeue_tail(list);
-
-	if (likely(skb != NULL))
-		qdisc_qstats_backlog_dec(sch, skb);
-
-	return skb;
-}
-
-static inline struct sk_buff *qdisc_dequeue_tail(struct Qdisc *sch)
-{
-	return __qdisc_dequeue_tail(sch, &sch->q);
-}
-
 static inline struct sk_buff *qdisc_peek_head(struct Qdisc *sch)
 {
 	return skb_peek(&sch->q);
@@ -691,9 +657,11 @@
 	/* we can reuse ->gso_skb because peek isn't called for root qdiscs */
 	if (!sch->gso_skb) {
 		sch->gso_skb = sch->dequeue(sch);
-		if (sch->gso_skb)
+		if (sch->gso_skb) {
 			/* it's still part of the queue */
+			qdisc_qstats_backlog_inc(sch, sch->gso_skb);
 			sch->q.qlen++;
+		}
 	}
 
 	return sch->gso_skb;
@@ -706,6 +674,7 @@
 
 	if (skb) {
 		sch->gso_skb = NULL;
+		qdisc_qstats_backlog_dec(sch, skb);
 		sch->q.qlen--;
 	} else {
 		skb = sch->dequeue(sch);
@@ -714,19 +683,21 @@
 	return skb;
 }
 
-static inline void __qdisc_reset_queue(struct Qdisc *sch,
-				       struct sk_buff_head *list)
+static inline void __qdisc_reset_queue(struct sk_buff_head *list)
 {
 	/*
 	 * We do not know the backlog in bytes of this list, it
 	 * is up to the caller to correct it
 	 */
-	__skb_queue_purge(list);
+	if (!skb_queue_empty(list)) {
+		rtnl_kfree_skbs(list->next, list->prev);
+		__skb_queue_head_init(list);
+	}
 }
 
 static inline void qdisc_reset_queue(struct Qdisc *sch)
 {
-	__qdisc_reset_queue(sch, &sch->q);
+	__qdisc_reset_queue(&sch->q);
 	sch->qstats.backlog = 0;
 }
 
@@ -747,23 +718,10 @@
 	return old;
 }
 
-static inline unsigned int __qdisc_queue_drop(struct Qdisc *sch,
-					      struct sk_buff_head *list)
+static inline void rtnl_qdisc_drop(struct sk_buff *skb, struct Qdisc *sch)
 {
-	struct sk_buff *skb = __qdisc_dequeue_tail(sch, list);
-
-	if (likely(skb != NULL)) {
-		unsigned int len = qdisc_pkt_len(skb);
-		kfree_skb(skb);
-		return len;
-	}
-
-	return 0;
-}
-
-static inline unsigned int qdisc_queue_drop(struct Qdisc *sch)
-{
-	return __qdisc_queue_drop(sch, &sch->q);
+	rtnl_kfree_skbs(skb, skb);
+	qdisc_qstats_drop(sch);
 }
 
 static inline int qdisc_drop(struct sk_buff *skb, struct Qdisc *sch)
@@ -774,22 +732,6 @@
 	return NET_XMIT_DROP;
 }
 
-static inline int qdisc_reshape_fail(struct sk_buff *skb, struct Qdisc *sch)
-{
-	qdisc_qstats_drop(sch);
-
-#ifdef CONFIG_NET_CLS_ACT
-	if (sch->reshape_fail == NULL || sch->reshape_fail(skb, sch))
-		goto drop;
-
-	return NET_XMIT_SUCCESS;
-
-drop:
-#endif
-	kfree_skb(skb);
-	return NET_XMIT_DROP;
-}
-
 /* Length to Time (L2T) lookup in a qdisc_rate_table, to determine how
    long it will take to send a packet given its size.
  */
diff --git a/include/net/tc_act/tc_defact.h b/include/net/tc_act/tc_defact.h
index 9763dcb..ab9b5d6 100644
--- a/include/net/tc_act/tc_defact.h
+++ b/include/net/tc_act/tc_defact.h
@@ -5,8 +5,8 @@
 
 struct tcf_defact {
 	struct tcf_common	common;
-	u32     		tcfd_datalen;
-	void    		*tcfd_defdata;
+	u32		tcfd_datalen;
+	void		*tcfd_defdata;
 };
 #define to_defact(a) \
 	container_of(a->priv, struct tcf_defact, common)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 0bcc70f..a79894b 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -767,6 +767,7 @@
 	union {
 		struct {
 			/* There is space for up to 20 bytes */
+			__u32 in_flight;/* Bytes in flight when packet sent */
 		} tx;   /* only used for outgoing skbs */
 		union {
 			struct inet_skb_parm	h4;
@@ -859,6 +860,7 @@
 struct ack_sample {
 	u32 pkts_acked;
 	s32 rtt_us;
+	u32 in_flight;
 };
 
 struct tcp_congestion_ops {
diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index 9d14f70..02c5be0 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -84,6 +84,46 @@
 void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
 			   struct udp_tunnel_sock_cfg *sock_cfg);
 
+/* -- List of parsable UDP tunnel types --
+ *
+ * Adding to this list will result in serious debate.  The main issue is
+ * that this list is essentially a list of workarounds for either poorly
+ * designed tunnels, or poorly designed device offloads.
+ *
+ * The parsing supported via these types should really be used for Rx
+ * traffic only as the network stack will have already inserted offsets for
+ * the location of the headers in the skb.  In addition any ports that are
+ * pushed should be kept within the namespace without leaking to other
+ * devices such as VFs or other ports on the same device.
+ *
+ * It is strongly encouraged to use CHECKSUM_COMPLETE for Rx to avoid the
+ * need to use this for Rx checksum offload.  It should not be necessary to
+ * call this function to perform Tx offloads on outgoing traffic.
+ */
+enum udp_parsable_tunnel_type {
+	UDP_TUNNEL_TYPE_VXLAN,		/* RFC 7348 */
+	UDP_TUNNEL_TYPE_GENEVE,		/* draft-ietf-nvo3-geneve */
+	UDP_TUNNEL_TYPE_VXLAN_GPE,	/* draft-ietf-nvo3-vxlan-gpe */
+};
+
+struct udp_tunnel_info {
+	unsigned short type;
+	sa_family_t sa_family;
+	__be16 port;
+};
+
+/* Notify network devices of offloadable types */
+void udp_tunnel_push_rx_port(struct net_device *dev, struct socket *sock,
+			     unsigned short type);
+void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type);
+void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type);
+
+static inline void udp_tunnel_get_rx_info(struct net_device *dev)
+{
+	ASSERT_RTNL();
+	call_netdevice_notifiers(NETDEV_UDP_TUNNEL_PUSH_INFO, dev);
+}
+
 /* Transmit the skb using UDP encapsulation. */
 void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb,
 			 __be32 src, __be32 dst, __u8 tos, __u8 ttl,
@@ -105,12 +145,14 @@
 				    __be16 flags, __be64 tunnel_id,
 				    int md_size);
 
+#ifdef CONFIG_INET
 static inline int udp_tunnel_handle_offloads(struct sk_buff *skb, bool udp_csum)
 {
 	int type = udp_csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
 
 	return iptunnel_handle_offloads(skb, type);
 }
+#endif
 
 static inline void udp_tunnel_encap_enable(struct socket *sock)
 {
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index b880316..b96d036 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -1,13 +1,10 @@
 #ifndef __NET_VXLAN_H
 #define __NET_VXLAN_H 1
 
-#include <linux/ip.h>
-#include <linux/ipv6.h>
 #include <linux/if_vlan.h>
-#include <linux/skbuff.h>
-#include <linux/netdevice.h>
-#include <linux/udp.h>
+#include <net/udp_tunnel.h>
 #include <net/dst_metadata.h>
+#include <net/udp_tunnel.h>
 
 /* VXLAN protocol (RFC 7348) header:
  * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
@@ -392,12 +389,6 @@
 	return vni_field;
 }
 
-static inline void vxlan_get_rx_port(struct net_device *netdev)
-{
-	ASSERT_RTNL();
-	call_netdevice_notifiers(NETDEV_OFFLOAD_PUSH_VXLAN, netdev);
-}
-
 static inline unsigned short vxlan_get_sk_family(struct vxlan_sock *vs)
 {
 	return vs->sock->sk->sk_family;
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 432bed5..7e440d4 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -217,10 +217,10 @@
 	IB_DEVICE_CROSS_CHANNEL		= (1 << 27),
 	IB_DEVICE_MANAGED_FLOW_STEERING		= (1 << 29),
 	IB_DEVICE_SIGNATURE_HANDOVER		= (1 << 30),
-	IB_DEVICE_ON_DEMAND_PAGING		= (1 << 31),
+	IB_DEVICE_ON_DEMAND_PAGING		= (1ULL << 31),
 	IB_DEVICE_SG_GAPS_REG			= (1ULL << 32),
-	IB_DEVICE_VIRTUAL_FUNCTION		= ((u64)1 << 33),
-	IB_DEVICE_RAW_SCATTER_FCS		= ((u64)1 << 34),
+	IB_DEVICE_VIRTUAL_FUNCTION		= (1ULL << 33),
+	IB_DEVICE_RAW_SCATTER_FCS		= (1ULL << 34),
 };
 
 enum ib_signature_prot_cap {
diff --git a/include/soc/fsl/qe/immap_qe.h b/include/soc/fsl/qe/immap_qe.h
index bedbff8..c76ef30 100644
--- a/include/soc/fsl/qe/immap_qe.h
+++ b/include/soc/fsl/qe/immap_qe.h
@@ -159,10 +159,7 @@
 
 /* SI */
 struct si1 {
-	__be16	siamr1;		/* SI1 TDMA mode register */
-	__be16	sibmr1;		/* SI1 TDMB mode register */
-	__be16	sicmr1;		/* SI1 TDMC mode register */
-	__be16	sidmr1;		/* SI1 TDMD mode register */
+	__be16	sixmr1[4];	/* SI1 TDMx (x = A B C D) mode register */
 	u8	siglmr1_h;	/* SI1 global mode register high */
 	u8	res0[0x1];
 	u8	sicmdr1_h;	/* SI1 command register high */
diff --git a/include/soc/fsl/qe/qe.h b/include/soc/fsl/qe/qe.h
index 33b29ea..70339d7 100644
--- a/include/soc/fsl/qe/qe.h
+++ b/include/soc/fsl/qe/qe.h
@@ -80,6 +80,8 @@
 	QE_CLK22,		/* Clock 22 */
 	QE_CLK23,		/* Clock 23 */
 	QE_CLK24,		/* Clock 24 */
+	QE_RSYNC_PIN,		/* RSYNC from pin */
+	QE_TSYNC_PIN,		/* TSYNC from pin */
 	QE_CLK_DUMMY
 };
 
@@ -242,6 +244,22 @@
 #define qe_muram_addr cpm_muram_addr
 #define qe_muram_offset cpm_muram_offset
 
+#define qe_setbits32(_addr, _v) iowrite32be(ioread32be(_addr) |  (_v), (_addr))
+#define qe_clrbits32(_addr, _v) iowrite32be(ioread32be(_addr) & ~(_v), (_addr))
+
+#define qe_setbits16(_addr, _v) iowrite16be(ioread16be(_addr) |  (_v), (_addr))
+#define qe_clrbits16(_addr, _v) iowrite16be(ioread16be(_addr) & ~(_v), (_addr))
+
+#define qe_setbits8(_addr, _v) iowrite8(ioread8(_addr) |  (_v), (_addr))
+#define qe_clrbits8(_addr, _v) iowrite8(ioread8(_addr) & ~(_v), (_addr))
+
+#define qe_clrsetbits32(addr, clear, set) \
+	iowrite32be((ioread32be(addr) & ~(clear)) | (set), (addr))
+#define qe_clrsetbits16(addr, clear, set) \
+	iowrite16be((ioread16be(addr) & ~(clear)) | (set), (addr))
+#define qe_clrsetbits8(addr, clear, set) \
+	iowrite8((ioread8(addr) & ~(clear)) | (set), (addr))
+
 /* Structure that defines QE firmware binary files.
  *
  * See Documentation/powerpc/qe_firmware.txt for a description of these
@@ -639,6 +657,7 @@
 #define UCC_SLOW_GUMR_L_MODE_QMC	0x00000002
 
 /* General UCC FAST Mode Register */
+#define UCC_FAST_GUMR_LOOPBACK	0x40000000
 #define UCC_FAST_GUMR_TCI	0x20000000
 #define UCC_FAST_GUMR_TRX	0x10000000
 #define UCC_FAST_GUMR_TTX	0x08000000
diff --git a/include/soc/fsl/qe/qe_tdm.h b/include/soc/fsl/qe/qe_tdm.h
new file mode 100644
index 0000000..a1664b6
--- /dev/null
+++ b/include/soc/fsl/qe/qe_tdm.h
@@ -0,0 +1,94 @@
+/*
+ * Internal header file for QE TDM mode routines.
+ *
+ * Copyright (C) 2016 Freescale Semiconductor, Inc. All rights reserved.
+ *
+ * Authors:	Zhao Qiang <qiang.zhao@nxp.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
+ */
+
+#ifndef _QE_TDM_H_
+#define _QE_TDM_H_
+
+#include <linux/kernel.h>
+#include <linux/list.h>
+
+#include <soc/fsl/qe/immap_qe.h>
+#include <soc/fsl/qe/qe.h>
+
+#include <soc/fsl/qe/ucc.h>
+#include <soc/fsl/qe/ucc_fast.h>
+
+/* SI RAM entries */
+#define SIR_LAST	0x0001
+#define SIR_BYTE	0x0002
+#define SIR_CNT(x)	((x) << 2)
+#define SIR_CSEL(x)	((x) << 5)
+#define SIR_SGS		0x0200
+#define SIR_SWTR	0x4000
+#define SIR_MCC		0x8000
+#define SIR_IDLE	0
+
+/* SIxMR fields */
+#define SIMR_SAD(x) ((x) << 12)
+#define SIMR_SDM_NORMAL	0x0000
+#define SIMR_SDM_INTERNAL_LOOPBACK	0x0800
+#define SIMR_SDM_MASK	0x0c00
+#define SIMR_CRT	0x0040
+#define SIMR_SL		0x0020
+#define SIMR_CE		0x0010
+#define SIMR_FE		0x0008
+#define SIMR_GM		0x0004
+#define SIMR_TFSD(n)	(n)
+#define SIMR_RFSD(n)	((n) << 8)
+
+enum tdm_ts_t {
+	TDM_TX_TS,
+	TDM_RX_TS
+};
+
+enum tdm_framer_t {
+	TDM_FRAMER_T1,
+	TDM_FRAMER_E1
+};
+
+enum tdm_mode_t {
+	TDM_INTERNAL_LOOPBACK,
+	TDM_NORMAL
+};
+
+struct si_mode_info {
+	u8 simr_rfsd;
+	u8 simr_tfsd;
+	u8 simr_crt;
+	u8 simr_sl;
+	u8 simr_ce;
+	u8 simr_fe;
+	u8 simr_gm;
+};
+
+struct ucc_tdm_info {
+	struct ucc_fast_info uf_info;
+	struct si_mode_info si_info;
+};
+
+struct ucc_tdm {
+	u16 tdm_port;		/* port for this tdm:TDMA,TDMB */
+	u32 siram_entry_id;
+	u16 __iomem *siram;
+	struct si1 __iomem *si_regs;
+	enum tdm_framer_t tdm_framer_type;
+	enum tdm_mode_t tdm_mode;
+	u8 num_of_ts;		/* the number of timeslots in this tdm frame */
+	u32 tx_ts_mask;		/* tx time slot mask */
+	u32 rx_ts_mask;		/* rx time slot mask */
+};
+
+int ucc_of_parse_tdm(struct device_node *np, struct ucc_tdm *utdm,
+		     struct ucc_tdm_info *ut_info);
+void ucc_tdm_init(struct ucc_tdm *utdm, struct ucc_tdm_info *ut_info);
+#endif
diff --git a/include/soc/fsl/qe/ucc.h b/include/soc/fsl/qe/ucc.h
index 894f14c..6bbbb59 100644
--- a/include/soc/fsl/qe/ucc.h
+++ b/include/soc/fsl/qe/ucc.h
@@ -41,6 +41,10 @@
 
 int ucc_set_qe_mux_rxtx(unsigned int ucc_num, enum qe_clock clock,
 	enum comm_dir mode);
+int ucc_set_tdm_rxtx_clk(unsigned int tdm_num, enum qe_clock clock,
+			 enum comm_dir mode);
+int ucc_set_tdm_rxtx_sync(unsigned int tdm_num, enum qe_clock clock,
+			  enum comm_dir mode);
 
 int ucc_mux_set_grant_tsa_bkpt(unsigned int ucc_num, int set, u32 mask);
 
diff --git a/include/soc/fsl/qe/ucc_fast.h b/include/soc/fsl/qe/ucc_fast.h
index df8ea79..3ee9e7c 100644
--- a/include/soc/fsl/qe/ucc_fast.h
+++ b/include/soc/fsl/qe/ucc_fast.h
@@ -21,19 +21,37 @@
 
 #include <soc/fsl/qe/ucc.h>
 
-/* Receive BD's status */
+/* Receive BD's status and length*/
 #define R_E	0x80000000	/* buffer empty */
 #define R_W	0x20000000	/* wrap bit */
 #define R_I	0x10000000	/* interrupt on reception */
 #define R_L	0x08000000	/* last */
 #define R_F	0x04000000	/* first */
 
-/* transmit BD's status */
+/* transmit BD's status and length*/
 #define T_R	0x80000000	/* ready bit */
 #define T_W	0x20000000	/* wrap bit */
 #define T_I	0x10000000	/* interrupt on completion */
 #define T_L	0x08000000	/* last */
 
+/* Receive BD's status */
+#define R_E_S	0x8000	/* buffer empty */
+#define R_W_S	0x2000	/* wrap bit */
+#define R_I_S	0x1000	/* interrupt on reception */
+#define R_L_S	0x0800	/* last */
+#define R_F_S	0x0400	/* first */
+#define R_CM_S	0x0200	/* continuous mode */
+#define R_CR_S	0x0004	/* crc */
+#define R_OV_S	0x0002	/* crc */
+
+/* transmit BD's status */
+#define T_R_S	0x8000	/* ready bit */
+#define T_W_S	0x2000	/* wrap bit */
+#define T_I_S	0x1000	/* interrupt on completion */
+#define T_L_S	0x0800	/* last */
+#define T_TC_S	0x0400	/* crc */
+#define T_TM_S	0x0200	/* continuous mode */
+
 /* Rx Data buffer must be 4 bytes aligned in most cases */
 #define UCC_FAST_RX_ALIGN			4
 #define UCC_FAST_MRBLR_ALIGNMENT		4
@@ -118,9 +136,12 @@
 /* Fast UCC initialization structure */
 struct ucc_fast_info {
 	int ucc_num;
+	int tdm_num;
 	enum qe_clock rx_clock;
 	enum qe_clock tx_clock;
-	u32 regs;
+	enum qe_clock rx_sync;
+	enum qe_clock tx_sync;
+	resource_size_t regs;
 	int irq;
 	u32 uccm_mask;
 	int bd_mem_part;
diff --git a/include/uapi/linux/can/bcm.h b/include/uapi/linux/can/bcm.h
index 7a291dc..cefb304 100644
--- a/include/uapi/linux/can/bcm.h
+++ b/include/uapi/linux/can/bcm.h
@@ -99,5 +99,6 @@
 #define RX_ANNOUNCE_RESUME  0x0100
 #define TX_RESET_MULTI_IDX  0x0200
 #define RX_RTR_FRAME        0x0400
+#define CAN_FD_FRAME        0x0800
 
 #endif /* !_UAPI_CAN_BCM_H */
diff --git a/include/uapi/linux/fib_rules.h b/include/uapi/linux/fib_rules.h
index 620c8a5..14404b3 100644
--- a/include/uapi/linux/fib_rules.h
+++ b/include/uapi/linux/fib_rules.h
@@ -50,6 +50,7 @@
 	FRA_FWMASK,	/* mask for netfilter mark */
 	FRA_OIFNAME,
 	FRA_PAD,
+	FRA_L3MDEV,	/* iif or oif is l3mdev goto its table */
 	__FRA_MAX
 };
 
diff --git a/include/uapi/linux/gtp.h b/include/uapi/linux/gtp.h
index ca1054d..72a04a0 100644
--- a/include/uapi/linux/gtp.h
+++ b/include/uapi/linux/gtp.h
@@ -1,5 +1,5 @@
 #ifndef _UAPI_LINUX_GTP_H_
-#define _UAPI_LINUX_GTP_H__
+#define _UAPI_LINUX_GTP_H_
 
 enum gtp_genl_cmds {
 	GTP_CMD_NEWPDP,
diff --git a/include/uapi/linux/icmp.h b/include/uapi/linux/icmp.h
index 16fff05..fddd9d7 100644
--- a/include/uapi/linux/icmp.h
+++ b/include/uapi/linux/icmp.h
@@ -79,6 +79,7 @@
 		__be16	__unused;
 		__be16	mtu;
 	} frag;
+	__u8	reserved[4];
   } un;
 };
 
diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h
index af4de90..1046f55 100644
--- a/include/uapi/linux/if_tunnel.h
+++ b/include/uapi/linux/if_tunnel.h
@@ -113,6 +113,7 @@
 	IFLA_GRE_ENCAP_SPORT,
 	IFLA_GRE_ENCAP_DPORT,
 	IFLA_GRE_COLLECT_METADATA,
+	IFLA_GRE_IGNORE_DF,
 	__IFLA_GRE_MAX,
 };
 
diff --git a/include/uapi/linux/netlink_diag.h b/include/uapi/linux/netlink_diag.h
index d793993..76b4d87 100644
--- a/include/uapi/linux/netlink_diag.h
+++ b/include/uapi/linux/netlink_diag.h
@@ -49,6 +49,7 @@
 #define NDIAG_SHOW_MEMINFO	0x00000001 /* show memory info of a socket */
 #define NDIAG_SHOW_GROUPS	0x00000002 /* show groups of a netlink socket */
 #ifndef __KERNEL__
+/* deprecated since 4.6 */
 #define NDIAG_SHOW_RING_CFG	0x00000004 /* show ring configuration */
 #endif
 
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index e23d786..53c8278 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -493,7 +493,12 @@
  *	This attribute is ignored if driver does not support roam scan.
  *	It is also sent as an event, with the BSSID and response IEs when the
  *	connection is established or failed to be established. This can be
- *	determined by the STATUS_CODE attribute.
+ *	determined by the %NL80211_ATTR_STATUS_CODE attribute (0 = success,
+ *	non-zero = failure). If %NL80211_ATTR_TIMED_OUT is included in the
+ *	event, the connection attempt failed due to not being able to initiate
+ *	authentication/association or not receiving a response from the AP.
+ *	Non-zero %NL80211_ATTR_STATUS_CODE value is indicated in that case as
+ *	well to remain backwards compatible.
  * @NL80211_CMD_ROAM: request that the card roam (currently not implemented),
  *	sent as an event when the card/driver roamed by itself.
  * @NL80211_CMD_DISCONNECT: drop a given connection; also used to notify
@@ -1819,6 +1824,11 @@
  *
  * @NL80211_ATTR_PAD: attribute used for padding for 64-bit alignment
  *
+ * @NL80211_ATTR_IFTYPE_EXT_CAPA: Nested attribute of the following attributes:
+ *	%NL80211_ATTR_IFTYPE, %NL80211_ATTR_EXT_CAPA,
+ *	%NL80211_ATTR_EXT_CAPA_MASK, to specify the extended capabilities per
+ *	interface type.
+ *
  * @NUM_NL80211_ATTR: total number of nl80211_attrs available
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
@@ -2201,6 +2211,8 @@
 
 	NL80211_ATTR_PAD,
 
+	NL80211_ATTR_IFTYPE_EXT_CAPA,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index bb0d515..d95a301 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -166,6 +166,7 @@
  * output port is actually a tunnel port. Contains the output tunnel key
  * extracted from the packet as nested %OVS_TUNNEL_KEY_ATTR_* attributes.
  * @OVS_PACKET_ATTR_MRU: Present for an %OVS_PACKET_CMD_ACTION and
+ * @OVS_PACKET_ATTR_LEN: Packet size before truncation.
  * %OVS_PACKET_ATTR_USERSPACE action specify the Maximum received fragment
  * size.
  *
@@ -185,6 +186,7 @@
 	OVS_PACKET_ATTR_PROBE,      /* Packet operation is a feature probe,
 				       error logging should be suppressed. */
 	OVS_PACKET_ATTR_MRU,	    /* Maximum received IP fragment size. */
+	OVS_PACKET_ATTR_LEN,		/* Packet size before truncation. */
 	__OVS_PACKET_ATTR_MAX
 };
 
@@ -580,6 +582,10 @@
 
 #define OVS_USERSPACE_ATTR_MAX (__OVS_USERSPACE_ATTR_MAX - 1)
 
+struct ovs_action_trunc {
+	uint32_t max_len; /* Max packet size in bytes. */
+};
+
 /**
  * struct ovs_action_push_mpls - %OVS_ACTION_ATTR_PUSH_MPLS action argument.
  * @mpls_lse: MPLS label stack entry to push.
@@ -703,6 +709,7 @@
  * enum ovs_action_attr - Action types.
  *
  * @OVS_ACTION_ATTR_OUTPUT: Output packet to port.
+ * @OVS_ACTION_ATTR_TRUNC: Output packet to port with truncated packet size.
  * @OVS_ACTION_ATTR_USERSPACE: Send packet to userspace according to nested
  * %OVS_USERSPACE_ATTR_* attributes.
  * @OVS_ACTION_ATTR_SET: Replaces the contents of an existing header.  The
@@ -756,6 +763,7 @@
 				       * The data must be zero for the unmasked
 				       * bits. */
 	OVS_ACTION_ATTR_CT,           /* Nested OVS_CT_ATTR_* . */
+	OVS_ACTION_ATTR_TRUNC,        /* u32 struct ovs_action_trunc. */
 
 	__OVS_ACTION_ATTR_MAX,	      /* Nothing past this will be accepted
 				       * from userspace. */
diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index f4297c8..5702e93 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -115,8 +115,8 @@
 	__u32			mtu;
 	struct tc_ratespec	rate;
 	struct tc_ratespec	peakrate;
-	int 			refcnt;
-	int 			bindcnt;
+	int			refcnt;
+	int			bindcnt;
 	__u32			capab;
 };
 
@@ -124,10 +124,11 @@
 	__u64   install;
 	__u64   lastuse;
 	__u64   expires;
+	__u64   firstuse;
 };
 
 struct tc_cnt {
-	int                   refcnt; 
+	int                   refcnt;
 	int                   bindcnt;
 };
 
diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h
index ec32293..fc353b5 100644
--- a/include/uapi/linux/virtio_net.h
+++ b/include/uapi/linux/virtio_net.h
@@ -1,5 +1,5 @@
-#ifndef _LINUX_VIRTIO_NET_H
-#define _LINUX_VIRTIO_NET_H
+#ifndef _UAPI_LINUX_VIRTIO_NET_H
+#define _UAPI_LINUX_VIRTIO_NET_H
 /* This header is BSD licensed so anyone can use the definitions to implement
  * compatible drivers/servers.
  *
@@ -35,6 +35,7 @@
 #define VIRTIO_NET_F_CSUM	0	/* Host handles pkts w/ partial csum */
 #define VIRTIO_NET_F_GUEST_CSUM	1	/* Guest handles pkts w/ partial csum */
 #define VIRTIO_NET_F_CTRL_GUEST_OFFLOADS 2 /* Dynamic offload configuration. */
+#define VIRTIO_NET_F_MTU	3	/* Initial MTU advice */
 #define VIRTIO_NET_F_MAC	5	/* Host has given MAC address. */
 #define VIRTIO_NET_F_GUEST_TSO4	7	/* Guest can handle TSOv4 in. */
 #define VIRTIO_NET_F_GUEST_TSO6	8	/* Guest can handle TSOv6 in. */
@@ -73,6 +74,8 @@
 	 * Legal values are between 1 and 0x8000
 	 */
 	__u16 max_virtqueue_pairs;
+	/* Default maximum transmit unit advice */
+	__u16 mtu;
 } __attribute__((packed));
 
 /*
@@ -242,4 +245,4 @@
 #define VIRTIO_NET_CTRL_GUEST_OFFLOADS   5
 #define VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET        0
 
-#endif /* _LINUX_VIRTIO_NET_H */
+#endif /* _UAPI_LINUX_VIRTIO_NET_H */
diff --git a/include/uapi/linux/wireless.h b/include/uapi/linux/wireless.h
index c1592e3..d9ecd7c 100644
--- a/include/uapi/linux/wireless.h
+++ b/include/uapi/linux/wireless.h
@@ -670,8 +670,7 @@
 /*
  *	Generic format for most parameters that fit in an int
  */
-struct	iw_param
-{
+struct iw_param {
   __s32		value;		/* The value of the parameter itself */
   __u8		fixed;		/* Hardware should not use auto select */
   __u8		disabled;	/* Disable the feature */
@@ -682,8 +681,7 @@
  *	For all data larger than 16 octets, we need to use a
  *	pointer to memory allocated in user space.
  */
-struct	iw_point
-{
+struct iw_point {
   void __user	*pointer;	/* Pointer to the data  (in user space) */
   __u16		length;		/* number of fields or size in bytes */
   __u16		flags;		/* Optional params */
@@ -698,8 +696,7 @@
  *	of 10 to get 'm' lower than 10^9, with 'm'= f / (10^'e')...
  *	The power of 10 is in 'e', the result of the division is in 'm'.
  */
-struct	iw_freq
-{
+struct iw_freq {
 	__s32		m;		/* Mantissa */
 	__s16		e;		/* Exponent */
 	__u8		i;		/* List index (when in range struct) */
@@ -709,8 +706,7 @@
 /*
  *	Quality of the link
  */
-struct	iw_quality
-{
+struct iw_quality {
 	__u8		qual;		/* link quality (%retries, SNR,
 					   %missed beacons or better...) */
 	__u8		level;		/* signal level (dBm) */
@@ -725,8 +721,7 @@
  *	is already pretty exhaustive, and you should use that first.
  *	This is only additional stats...
  */
-struct	iw_discarded
-{
+struct iw_discarded {
 	__u32		nwid;		/* Rx : Wrong nwid/essid */
 	__u32		code;		/* Rx : Unable to code/decode (WEP) */
 	__u32		fragment;	/* Rx : Can't perform MAC reassembly */
@@ -738,16 +733,14 @@
  *	Packet/Time period missed in the wireless adapter due to
  *	"wireless" specific problems...
  */
-struct	iw_missed
-{
+struct iw_missed {
 	__u32		beacon;		/* Missed beacons/superframe */
 };
 
 /*
  *	Quality range (for spy threshold)
  */
-struct	iw_thrspy
-{
+struct iw_thrspy {
 	struct sockaddr		addr;		/* Source address (hw/mac) */
 	struct iw_quality	qual;		/* Quality of the link */
 	struct iw_quality	low;		/* Low threshold */
@@ -765,8 +758,7 @@
  *	Especially, scan results are required to include an entry for the
  *	current BSS if the driver is in Managed mode and associated with an AP.
  */
-struct	iw_scan_req
-{
+struct iw_scan_req {
 	__u8		scan_type; /* IW_SCAN_TYPE_{ACTIVE,PASSIVE} */
 	__u8		essid_len;
 	__u8		num_channels; /* num entries in channel_list;
@@ -827,8 +819,7 @@
  *	RX_SEQ_VALID for SIOCGIWENCODEEXT are optional, but can be useful for
  *	debugging/testing.
  */
-struct	iw_encode_ext
-{
+struct iw_encode_ext {
 	__u32		ext_flags; /* IW_ENCODE_EXT_* */
 	__u8		tx_seq[IW_ENCODE_SEQ_MAX_SIZE]; /* LSB first */
 	__u8		rx_seq[IW_ENCODE_SEQ_MAX_SIZE]; /* LSB first */
@@ -841,8 +832,7 @@
 };
 
 /* SIOCSIWMLME data */
-struct	iw_mlme
-{
+struct iw_mlme {
 	__u16		cmd; /* IW_MLME_* */
 	__u16		reason_code;
 	struct sockaddr	addr;
@@ -855,16 +845,14 @@
 
 #define IW_PMKID_LEN	16
 
-struct	iw_pmksa
-{
+struct iw_pmksa {
 	__u32		cmd; /* IW_PMKSA_* */
 	struct sockaddr	bssid;
 	__u8		pmkid[IW_PMKID_LEN];
 };
 
 /* IWEVMICHAELMICFAILURE data */
-struct	iw_michaelmicfailure
-{
+struct iw_michaelmicfailure {
 	__u32		flags;
 	struct sockaddr	src_addr;
 	__u8		tsc[IW_ENCODE_SEQ_MAX_SIZE]; /* LSB first */
@@ -872,8 +860,7 @@
 
 /* IWEVPMKIDCAND data */
 #define IW_PMKID_CAND_PREAUTH	0x00000001 /* RNS pre-authentication enabled */
-struct	iw_pmkid_cand
-{
+struct iw_pmkid_cand {
 	__u32		flags; /* IW_PMKID_CAND_* */
 	__u32		index; /* the smaller the index, the higher the
 				* priority */
@@ -884,8 +871,7 @@
 /*
  * Wireless statistics (used for /proc/net/wireless)
  */
-struct	iw_statistics
-{
+struct iw_statistics {
 	__u16		status;		/* Status
 					 * - device dependent for now */
 
@@ -897,7 +883,7 @@
 
 /* ------------------------ IOCTL REQUEST ------------------------ */
 /*
- * This structure defines the payload of an ioctl, and is used 
+ * This structure defines the payload of an ioctl, and is used
  * below.
  *
  * Note that this structure should fit on the memory footprint
@@ -906,8 +892,7 @@
  * You should check this when increasing the structures defined
  * above in this file...
  */
-union	iwreq_data
-{
+union iwreq_data {
 	/* Config - generic */
 	char		name[IFNAMSIZ];
 	/* Name : used to verify the presence of  wireless extensions.
@@ -944,15 +929,14 @@
  * convenience...
  * Do I need to remind you about structure size (32 octets) ?
  */
-struct	iwreq 
-{
+struct iwreq {
 	union
 	{
 		char	ifrn_name[IFNAMSIZ];	/* if name, e.g. "eth0" */
 	} ifr_ifrn;
 
 	/* Data part (defined just above) */
-	union	iwreq_data	u;
+	union iwreq_data	u;
 };
 
 /* -------------------------- IOCTL DATA -------------------------- */
@@ -965,8 +949,7 @@
  *	Range of parameters
  */
 
-struct	iw_range
-{
+struct iw_range {
 	/* Informative stuff (to choose between different interface) */
 	__u32		throughput;	/* To give an idea... */
 	/* In theory this value should be the maximum benchmarked
@@ -1069,9 +1052,8 @@
 /*
  * Private ioctl interface information
  */
- 
-struct	iw_priv_args
-{
+
+struct iw_priv_args {
 	__u32		cmd;		/* Number of the ioctl to issue */
 	__u16		set_args;	/* Type and number of args */
 	__u16		get_args;	/* Type and number of args */
@@ -1088,8 +1070,7 @@
 /*
  * A Wireless Event. Contains basically the same data as the ioctl...
  */
-struct iw_event
-{
+struct iw_event {
 	__u16		len;			/* Real length of this stuff */
 	__u16		cmd;			/* Wireless IOCTL */
 	union iwreq_data	u;		/* IOCTL fixed payload */
diff --git a/include/uapi/sound/Kbuild b/include/uapi/sound/Kbuild
index a7f2770..691984c 100644
--- a/include/uapi/sound/Kbuild
+++ b/include/uapi/sound/Kbuild
@@ -1,5 +1,6 @@
 # UAPI Header export list
 header-y += asequencer.h
+header-y += asoc.h
 header-y += asound.h
 header-y += asound_fm.h
 header-y += compress_offload.h
@@ -10,3 +11,5 @@
 header-y += hdspm.h
 header-y += sb16_csp.h
 header-y += sfnt_info.h
+header-y += tlv.h
+header-y += usb_stream.h
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 76d5a79..5af3073 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -328,8 +328,8 @@
 }
 
 /* only called from syscall */
-static int fd_array_map_update_elem(struct bpf_map *map, void *key,
-				    void *value, u64 map_flags)
+int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file,
+				 void *key, void *value, u64 map_flags)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	void *new_ptr, *old_ptr;
@@ -342,7 +342,7 @@
 		return -E2BIG;
 
 	ufd = *(u32 *)value;
-	new_ptr = map->ops->map_fd_get_ptr(map, ufd);
+	new_ptr = map->ops->map_fd_get_ptr(map, map_file, ufd);
 	if (IS_ERR(new_ptr))
 		return PTR_ERR(new_ptr);
 
@@ -371,10 +371,12 @@
 	}
 }
 
-static void *prog_fd_array_get_ptr(struct bpf_map *map, int fd)
+static void *prog_fd_array_get_ptr(struct bpf_map *map,
+				   struct file *map_file, int fd)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	struct bpf_prog *prog = bpf_prog_get(fd);
+
 	if (IS_ERR(prog))
 		return prog;
 
@@ -382,6 +384,7 @@
 		bpf_prog_put(prog);
 		return ERR_PTR(-EINVAL);
 	}
+
 	return prog;
 }
 
@@ -407,7 +410,6 @@
 	.map_free = fd_array_map_free,
 	.map_get_next_key = array_map_get_next_key,
 	.map_lookup_elem = fd_array_map_lookup_elem,
-	.map_update_elem = fd_array_map_update_elem,
 	.map_delete_elem = fd_array_map_delete_elem,
 	.map_fd_get_ptr = prog_fd_array_get_ptr,
 	.map_fd_put_ptr = prog_fd_array_put_ptr,
@@ -425,59 +427,105 @@
 }
 late_initcall(register_prog_array_map);
 
-static void perf_event_array_map_free(struct bpf_map *map)
+static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file,
+						   struct file *map_file)
 {
-	bpf_fd_array_map_clear(map);
-	fd_array_map_free(map);
+	struct bpf_event_entry *ee;
+
+	ee = kzalloc(sizeof(*ee), GFP_KERNEL);
+	if (ee) {
+		ee->event = perf_file->private_data;
+		ee->perf_file = perf_file;
+		ee->map_file = map_file;
+	}
+
+	return ee;
 }
 
-static void *perf_event_fd_array_get_ptr(struct bpf_map *map, int fd)
+static void __bpf_event_entry_free(struct rcu_head *rcu)
 {
-	struct perf_event *event;
+	struct bpf_event_entry *ee;
+
+	ee = container_of(rcu, struct bpf_event_entry, rcu);
+	fput(ee->perf_file);
+	kfree(ee);
+}
+
+static void bpf_event_entry_free_rcu(struct bpf_event_entry *ee)
+{
+	call_rcu(&ee->rcu, __bpf_event_entry_free);
+}
+
+static void *perf_event_fd_array_get_ptr(struct bpf_map *map,
+					 struct file *map_file, int fd)
+{
 	const struct perf_event_attr *attr;
-	struct file *file;
+	struct bpf_event_entry *ee;
+	struct perf_event *event;
+	struct file *perf_file;
 
-	file = perf_event_get(fd);
-	if (IS_ERR(file))
-		return file;
+	perf_file = perf_event_get(fd);
+	if (IS_ERR(perf_file))
+		return perf_file;
 
-	event = file->private_data;
+	event = perf_file->private_data;
+	ee = ERR_PTR(-EINVAL);
 
 	attr = perf_event_attrs(event);
-	if (IS_ERR(attr))
-		goto err;
+	if (IS_ERR(attr) || attr->inherit)
+		goto err_out;
 
-	if (attr->inherit)
-		goto err;
+	switch (attr->type) {
+	case PERF_TYPE_SOFTWARE:
+		if (attr->config != PERF_COUNT_SW_BPF_OUTPUT)
+			goto err_out;
+		/* fall-through */
+	case PERF_TYPE_RAW:
+	case PERF_TYPE_HARDWARE:
+		ee = bpf_event_entry_gen(perf_file, map_file);
+		if (ee)
+			return ee;
+		ee = ERR_PTR(-ENOMEM);
+		/* fall-through */
+	default:
+		break;
+	}
 
-	if (attr->type == PERF_TYPE_RAW)
-		return file;
-
-	if (attr->type == PERF_TYPE_HARDWARE)
-		return file;
-
-	if (attr->type == PERF_TYPE_SOFTWARE &&
-	    attr->config == PERF_COUNT_SW_BPF_OUTPUT)
-		return file;
-err:
-	fput(file);
-	return ERR_PTR(-EINVAL);
+err_out:
+	fput(perf_file);
+	return ee;
 }
 
 static void perf_event_fd_array_put_ptr(void *ptr)
 {
-	fput((struct file *)ptr);
+	bpf_event_entry_free_rcu(ptr);
+}
+
+static void perf_event_fd_array_release(struct bpf_map *map,
+					struct file *map_file)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	struct bpf_event_entry *ee;
+	int i;
+
+	rcu_read_lock();
+	for (i = 0; i < array->map.max_entries; i++) {
+		ee = READ_ONCE(array->ptrs[i]);
+		if (ee && ee->map_file == map_file)
+			fd_array_map_delete_elem(map, &i);
+	}
+	rcu_read_unlock();
 }
 
 static const struct bpf_map_ops perf_event_array_ops = {
 	.map_alloc = fd_array_map_alloc,
-	.map_free = perf_event_array_map_free,
+	.map_free = fd_array_map_free,
 	.map_get_next_key = array_map_get_next_key,
 	.map_lookup_elem = fd_array_map_lookup_elem,
-	.map_update_elem = fd_array_map_update_elem,
 	.map_delete_elem = fd_array_map_delete_elem,
 	.map_fd_get_ptr = perf_event_fd_array_get_ptr,
 	.map_fd_put_ptr = perf_event_fd_array_put_ptr,
+	.map_release = perf_event_fd_array_release,
 };
 
 static struct bpf_map_type_list perf_event_array_type __read_mostly = {
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 46ecce4..c23a4e93 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -124,7 +124,12 @@
 
 static int bpf_map_release(struct inode *inode, struct file *filp)
 {
-	bpf_map_put_with_uref(filp->private_data);
+	struct bpf_map *map = filp->private_data;
+
+	if (map->ops->map_release)
+		map->ops->map_release(map, filp);
+
+	bpf_map_put_with_uref(map);
 	return 0;
 }
 
@@ -387,6 +392,12 @@
 		err = bpf_percpu_hash_update(map, key, value, attr->flags);
 	} else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
 		err = bpf_percpu_array_update(map, key, value, attr->flags);
+	} else if (map->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY ||
+		   map->map_type == BPF_MAP_TYPE_PROG_ARRAY) {
+		rcu_read_lock();
+		err = bpf_fd_array_map_update_elem(map, f.file, key, value,
+						   attr->flags);
+		rcu_read_unlock();
 	} else {
 		rcu_read_lock();
 		err = map->ops->map_update_elem(map, key, value, attr->flags);
diff --git a/kernel/irq/ipi.c b/kernel/irq/ipi.c
index c427422..89b49f6 100644
--- a/kernel/irq/ipi.c
+++ b/kernel/irq/ipi.c
@@ -125,7 +125,7 @@
 
 	domain = data->domain;
 	if (WARN_ON(domain == NULL))
-		return;
+		return -EINVAL;
 
 	if (!irq_domain_is_ipi(domain)) {
 		pr_warn("Trying to destroy a non IPI domain!\n");
diff --git a/kernel/relay.c b/kernel/relay.c
index 074994b..04d7cf3 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -614,6 +614,7 @@
 
 	kref_put(&chan->kref, relay_destroy_channel);
 	mutex_unlock(&relay_channels_mutex);
+	kfree(chan);
 	return NULL;
 }
 EXPORT_SYMBOL_GPL(relay_open);
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index bd12c6c..c5aeedf 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -127,7 +127,7 @@
  */
 static void cpuidle_idle_call(void)
 {
-	struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
+	struct cpuidle_device *dev = cpuidle_get_device();
 	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
 	int next_state, entered_state;
 
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 780bcbe..037ea6e 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -192,18 +192,17 @@
 {
 	struct bpf_map *map = (struct bpf_map *) (unsigned long) r1;
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	struct bpf_event_entry *ee;
 	struct perf_event *event;
-	struct file *file;
 
 	if (unlikely(index >= array->map.max_entries))
 		return -E2BIG;
 
-	file = (struct file *)array->ptrs[index];
-	if (unlikely(!file))
+	ee = READ_ONCE(array->ptrs[index]);
+	if (unlikely(!ee))
 		return -ENOENT;
 
-	event = file->private_data;
-
+	event = ee->event;
 	/* make sure event is local and doesn't have pmu::count */
 	if (event->oncpu != smp_processor_id() ||
 	    event->pmu->count)
@@ -233,8 +232,8 @@
 	u64 index = flags & BPF_F_INDEX_MASK;
 	void *data = (void *) (long) r4;
 	struct perf_sample_data sample_data;
+	struct bpf_event_entry *ee;
 	struct perf_event *event;
-	struct file *file;
 	struct perf_raw_record raw = {
 		.size = size,
 		.data = data,
@@ -247,12 +246,11 @@
 	if (unlikely(index >= array->map.max_entries))
 		return -E2BIG;
 
-	file = (struct file *)array->ptrs[index];
-	if (unlikely(!file))
+	ee = READ_ONCE(array->ptrs[index]);
+	if (unlikely(!ee))
 		return -ENOENT;
 
-	event = file->private_data;
-
+	event = ee->event;
 	if (unlikely(event->attr.type != PERF_TYPE_SOFTWARE ||
 		     event->attr.config != PERF_COUNT_SW_BPF_OUTPUT))
 		return -EINVAL;
diff --git a/mm/fadvise.c b/mm/fadvise.c
index b8024fa..6c707bf 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -126,6 +126,17 @@
 		 */
 		start_index = (offset+(PAGE_SIZE-1)) >> PAGE_SHIFT;
 		end_index = (endbyte >> PAGE_SHIFT);
+		if ((endbyte & ~PAGE_MASK) != ~PAGE_MASK) {
+			/* First page is tricky as 0 - 1 = -1, but pgoff_t
+			 * is unsigned, so the end_index >= start_index
+			 * check below would be true and we'll discard the whole
+			 * file cache which is not what was asked.
+			 */
+			if (end_index == 0)
+				break;
+
+			end_index--;
+		}
 
 		if (end_index >= start_index) {
 			unsigned long count = invalidate_mapping_pages(mapping,
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index d26162e..388c2bb 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -832,8 +832,27 @@
 	 * Only the process that called mmap() has reserves for
 	 * private mappings.
 	 */
-	if (is_vma_resv_set(vma, HPAGE_RESV_OWNER))
-		return true;
+	if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
+		/*
+		 * Like the shared case above, a hole punch or truncate
+		 * could have been performed on the private mapping.
+		 * Examine the value of chg to determine if reserves
+		 * actually exist or were previously consumed.
+		 * Very Subtle - The value of chg comes from a previous
+		 * call to vma_needs_reserves().  The reserve map for
+		 * private mappings has different (opposite) semantics
+		 * than that of shared mappings.  vma_needs_reserves()
+		 * has already taken this difference in semantics into
+		 * account.  Therefore, the meaning of chg is the same
+		 * as in the shared case above.  Code could easily be
+		 * combined, but keeping it separate draws attention to
+		 * subtle differences.
+		 */
+		if (chg)
+			return false;
+		else
+			return true;
+	}
 
 	return false;
 }
@@ -1816,6 +1835,25 @@
 
 	if (vma->vm_flags & VM_MAYSHARE)
 		return ret;
+	else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER) && ret >= 0) {
+		/*
+		 * In most cases, reserves always exist for private mappings.
+		 * However, a file associated with mapping could have been
+		 * hole punched or truncated after reserves were consumed.
+		 * As subsequent fault on such a range will not use reserves.
+		 * Subtle - The reserve map for private mappings has the
+		 * opposite meaning than that of shared mappings.  If NO
+		 * entry is in the reserve map, it means a reservation exists.
+		 * If an entry exists in the reserve map, it means the
+		 * reservation has already been consumed.  As a result, the
+		 * return value of this routine is the opposite of the
+		 * value returned from reserve map manipulation routines above.
+		 */
+		if (ret)
+			return 0;
+		else
+			return 1;
+	}
 	else
 		return ret < 0 ? ret : 0;
 }
diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c
index 18b6a2b..28439ac 100644
--- a/mm/kasan/kasan.c
+++ b/mm/kasan/kasan.c
@@ -763,8 +763,8 @@
 
 static int __init kasan_memhotplug_init(void)
 {
-	pr_err("WARNING: KASAN doesn't support memory hot-add\n");
-	pr_err("Memory hot-add will be disabled\n");
+	pr_info("WARNING: KASAN doesn't support memory hot-add\n");
+	pr_info("Memory hot-add will be disabled\n");
 
 	hotplug_memory_notifier(kasan_mem_notifier, 0);
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 925b431..75e7440 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1608,7 +1608,7 @@
 
 static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
 {
-	if (!current->memcg_may_oom || current->memcg_in_oom)
+	if (!current->memcg_may_oom)
 		return;
 	/*
 	 * We are in the middle of the charge context here, so we
@@ -2896,6 +2896,7 @@
 	 * ordering is imposed by list_lru_node->lock taken by
 	 * memcg_drain_all_list_lrus().
 	 */
+	rcu_read_lock(); /* can be called from css_free w/o cgroup_mutex */
 	css_for_each_descendant_pre(css, &memcg->css) {
 		child = mem_cgroup_from_css(css);
 		BUG_ON(child->kmemcg_id != kmemcg_id);
@@ -2903,6 +2904,8 @@
 		if (!memcg->use_hierarchy)
 			break;
 	}
+	rcu_read_unlock();
+
 	memcg_drain_all_list_lrus(kmemcg_id, parent->kmemcg_id);
 
 	memcg_free_cache_id(kmemcg_id);
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index dfb1ab6..acbc432 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -625,8 +625,6 @@
 	if (atomic_read(&mm->mm_users) > 1) {
 		rcu_read_lock();
 		for_each_process(p) {
-			bool exiting;
-
 			if (!process_shares_mm(p, mm))
 				continue;
 			if (fatal_signal_pending(p))
@@ -636,10 +634,7 @@
 			 * If the task is exiting make sure the whole thread group
 			 * is exiting and cannot acces mm anymore.
 			 */
-			spin_lock_irq(&p->sighand->siglock);
-			exiting = signal_group_exit(p->signal);
-			spin_unlock_irq(&p->sighand->siglock);
-			if (exiting)
+			if (signal_group_exit(p->signal))
 				continue;
 
 			/* Give up */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index f8f3bfc..6903b69 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -656,6 +656,9 @@
 		return;
 
 	page_ext = lookup_page_ext(page);
+	if (unlikely(!page_ext))
+		return;
+
 	__set_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags);
 
 	INIT_LIST_HEAD(&page->lru);
@@ -673,6 +676,9 @@
 		return;
 
 	page_ext = lookup_page_ext(page);
+	if (unlikely(!page_ext))
+		return;
+
 	__clear_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags);
 
 	set_page_private(page, 0);
@@ -2609,11 +2615,12 @@
 				page = list_last_entry(list, struct page, lru);
 			else
 				page = list_first_entry(list, struct page, lru);
-		} while (page && check_new_pcp(page));
 
-		__dec_zone_state(zone, NR_ALLOC_BATCH);
-		list_del(&page->lru);
-		pcp->count--;
+			__dec_zone_state(zone, NR_ALLOC_BATCH);
+			list_del(&page->lru);
+			pcp->count--;
+
+		} while (check_new_pcp(page));
 	} else {
 		/*
 		 * We most definitely don't want callers attempting to
@@ -3023,6 +3030,7 @@
 		apply_fair = false;
 		fair_skipped = false;
 		reset_alloc_batches(ac->preferred_zoneref->zone);
+		z = ac->preferred_zoneref;
 		goto zonelist_scan;
 	}
 
@@ -3596,6 +3604,17 @@
 	 */
 	alloc_flags = gfp_to_alloc_flags(gfp_mask);
 
+	/*
+	 * Reset the zonelist iterators if memory policies can be ignored.
+	 * These allocations are high priority and system rather than user
+	 * orientated.
+	 */
+	if ((alloc_flags & ALLOC_NO_WATERMARKS) || !(alloc_flags & ALLOC_CPUSET)) {
+		ac->zonelist = node_zonelist(numa_node_id(), gfp_mask);
+		ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
+					ac->high_zoneidx, ac->nodemask);
+	}
+
 	/* This is the last chance, in general, before the goto nopage. */
 	page = get_page_from_freelist(gfp_mask, order,
 				alloc_flags & ~ALLOC_NO_WATERMARKS, ac);
@@ -3604,12 +3623,6 @@
 
 	/* Allocate without watermarks if the context allows */
 	if (alloc_flags & ALLOC_NO_WATERMARKS) {
-		/*
-		 * Ignore mempolicies if ALLOC_NO_WATERMARKS on the grounds
-		 * the allocation is high priority and these type of
-		 * allocations are system rather than user orientated
-		 */
-		ac->zonelist = node_zonelist(numa_node_id(), gfp_mask);
 		page = get_page_from_freelist(gfp_mask, order,
 						ALLOC_NO_WATERMARKS, ac);
 		if (page)
@@ -3808,7 +3821,11 @@
 	/* Dirty zone balancing only done in the fast path */
 	ac.spread_dirty_pages = (gfp_mask & __GFP_WRITE);
 
-	/* The preferred zone is used for statistics later */
+	/*
+	 * The preferred zone is used for statistics but crucially it is
+	 * also used as the starting point for the zonelist iterator. It
+	 * may get reset for allocations that ignore memory policies.
+	 */
 	ac.preferred_zoneref = first_zones_zonelist(ac.zonelist,
 					ac.high_zoneidx, ac.nodemask);
 	if (!ac.preferred_zoneref) {
diff --git a/mm/page_owner.c b/mm/page_owner.c
index 792b56d..c6cda3e 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -55,6 +55,8 @@
 
 	for (i = 0; i < (1 << order); i++) {
 		page_ext = lookup_page_ext(page + i);
+		if (unlikely(!page_ext))
+			continue;
 		__clear_bit(PAGE_EXT_OWNER, &page_ext->flags);
 	}
 }
@@ -62,6 +64,7 @@
 void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask)
 {
 	struct page_ext *page_ext = lookup_page_ext(page);
+
 	struct stack_trace trace = {
 		.nr_entries = 0,
 		.max_entries = ARRAY_SIZE(page_ext->trace_entries),
@@ -69,6 +72,9 @@
 		.skip = 3,
 	};
 
+	if (unlikely(!page_ext))
+		return;
+
 	save_stack_trace(&trace);
 
 	page_ext->order = order;
@@ -82,6 +88,8 @@
 void __set_page_owner_migrate_reason(struct page *page, int reason)
 {
 	struct page_ext *page_ext = lookup_page_ext(page);
+	if (unlikely(!page_ext))
+		return;
 
 	page_ext->last_migrate_reason = reason;
 }
@@ -89,6 +97,12 @@
 gfp_t __get_page_owner_gfp(struct page *page)
 {
 	struct page_ext *page_ext = lookup_page_ext(page);
+	if (unlikely(!page_ext))
+		/*
+		 * The caller just returns 0 if no valid gfp
+		 * So return 0 here too.
+		 */
+		return 0;
 
 	return page_ext->gfp_mask;
 }
@@ -99,6 +113,9 @@
 	struct page_ext *new_ext = lookup_page_ext(newpage);
 	int i;
 
+	if (unlikely(!old_ext || !new_ext))
+		return;
+
 	new_ext->order = old_ext->order;
 	new_ext->gfp_mask = old_ext->gfp_mask;
 	new_ext->nr_entries = old_ext->nr_entries;
@@ -193,6 +210,11 @@
 	gfp_t gfp_mask = page_ext->gfp_mask;
 	int mt = gfpflags_to_migratetype(gfp_mask);
 
+	if (unlikely(!page_ext)) {
+		pr_alert("There is not page extension available.\n");
+		return;
+	}
+
 	if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) {
 		pr_alert("page_owner info is not active (free page?)\n");
 		return;
@@ -251,6 +273,8 @@
 		}
 
 		page_ext = lookup_page_ext(page);
+		if (unlikely(!page_ext))
+			continue;
 
 		/*
 		 * Some pages could be missed by concurrent allocation or free,
@@ -317,6 +341,8 @@
 				continue;
 
 			page_ext = lookup_page_ext(page);
+			if (unlikely(!page_ext))
+				continue;
 
 			/* Maybe overraping zone */
 			if (test_bit(PAGE_EXT_OWNER, &page_ext->flags))
diff --git a/mm/page_poison.c b/mm/page_poison.c
index 1eae5fa..2e647c6 100644
--- a/mm/page_poison.c
+++ b/mm/page_poison.c
@@ -54,6 +54,9 @@
 	struct page_ext *page_ext;
 
 	page_ext = lookup_page_ext(page);
+	if (unlikely(!page_ext))
+		return;
+
 	__set_bit(PAGE_EXT_DEBUG_POISON, &page_ext->flags);
 }
 
@@ -62,6 +65,9 @@
 	struct page_ext *page_ext;
 
 	page_ext = lookup_page_ext(page);
+	if (unlikely(!page_ext))
+		return;
+
 	__clear_bit(PAGE_EXT_DEBUG_POISON, &page_ext->flags);
 }
 
@@ -70,7 +76,7 @@
 	struct page_ext *page_ext;
 
 	page_ext = lookup_page_ext(page);
-	if (!page_ext)
+	if (unlikely(!page_ext))
 		return false;
 
 	return test_bit(PAGE_EXT_DEBUG_POISON, &page_ext->flags);
diff --git a/mm/swap.c b/mm/swap.c
index 9591614..59f5faf 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -667,6 +667,24 @@
 
 static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work);
 
+/*
+ * lru_add_drain_wq is used to do lru_add_drain_all() from a WQ_MEM_RECLAIM
+ * workqueue, aiding in getting memory freed.
+ */
+static struct workqueue_struct *lru_add_drain_wq;
+
+static int __init lru_init(void)
+{
+	lru_add_drain_wq = alloc_workqueue("lru-add-drain", WQ_MEM_RECLAIM, 0);
+
+	if (WARN(!lru_add_drain_wq,
+		"Failed to create workqueue lru_add_drain_wq"))
+		return -ENOMEM;
+
+	return 0;
+}
+early_initcall(lru_init);
+
 void lru_add_drain_all(void)
 {
 	static DEFINE_MUTEX(lock);
@@ -686,7 +704,7 @@
 		    pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) ||
 		    need_activate_page_drain(cpu)) {
 			INIT_WORK(work, lru_add_drain_per_cpu);
-			schedule_work_on(cpu, work);
+			queue_work_on(cpu, lru_add_drain_wq, work);
 			cpumask_set_cpu(cpu, &has_work);
 		}
 	}
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 0d457e7..c99463a 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -252,7 +252,10 @@
 void free_page_and_swap_cache(struct page *page)
 {
 	free_swap_cache(page);
-	put_page(page);
+	if (is_huge_zero_page(page))
+		put_huge_zero_page();
+	else
+		put_page(page);
 }
 
 /*
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index cf7ad1a..e11475c 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1105,7 +1105,7 @@
  */
 void vm_unmap_ram(const void *mem, unsigned int count)
 {
-	unsigned long size = count << PAGE_SHIFT;
+	unsigned long size = (unsigned long)count << PAGE_SHIFT;
 	unsigned long addr = (unsigned long)mem;
 
 	BUG_ON(!addr);
@@ -1140,7 +1140,7 @@
  */
 void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t prot)
 {
-	unsigned long size = count << PAGE_SHIFT;
+	unsigned long size = (unsigned long)count << PAGE_SHIFT;
 	unsigned long addr;
 	void *mem;
 
@@ -1574,14 +1574,15 @@
 		unsigned long flags, pgprot_t prot)
 {
 	struct vm_struct *area;
+	unsigned long size;		/* In bytes */
 
 	might_sleep();
 
 	if (count > totalram_pages)
 		return NULL;
 
-	area = get_vm_area_caller((count << PAGE_SHIFT), flags,
-					__builtin_return_address(0));
+	size = (unsigned long)count << PAGE_SHIFT;
+	area = get_vm_area_caller(size, flags, __builtin_return_address(0));
 	if (!area)
 		return NULL;
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 77e42ef..cb2a67b 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1061,6 +1061,8 @@
 				continue;
 
 			page_ext = lookup_page_ext(page);
+			if (unlikely(!page_ext))
+				continue;
 
 			if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags))
 				continue;
diff --git a/mm/z3fold.c b/mm/z3fold.c
index 34917d5..8f9e89c 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -412,7 +412,7 @@
 		/* HEADLESS page stored */
 		bud = HEADLESS;
 	} else {
-		bud = (handle - zhdr->first_num) & BUDDY_MASK;
+		bud = handle_to_buddy(handle);
 
 		switch (bud) {
 		case FIRST:
@@ -572,15 +572,19 @@
 			pool->pages_nr--;
 			spin_unlock(&pool->lock);
 			return 0;
-		} else if (zhdr->first_chunks != 0 &&
-			   zhdr->last_chunks != 0 && zhdr->middle_chunks != 0) {
-			/* Full, add to buddied list */
-			list_add(&zhdr->buddy, &pool->buddied);
-		} else if (!test_bit(PAGE_HEADLESS, &page->private)) {
-			z3fold_compact_page(zhdr);
-			/* add to unbuddied list */
-			freechunks = num_free_chunks(zhdr);
-			list_add(&zhdr->buddy, &pool->unbuddied[freechunks]);
+		}  else if (!test_bit(PAGE_HEADLESS, &page->private)) {
+			if (zhdr->first_chunks != 0 &&
+			    zhdr->last_chunks != 0 &&
+			    zhdr->middle_chunks != 0) {
+				/* Full, add to buddied list */
+				list_add(&zhdr->buddy, &pool->buddied);
+			} else {
+				z3fold_compact_page(zhdr);
+				/* add to unbuddied list */
+				freechunks = num_free_chunks(zhdr);
+				list_add(&zhdr->buddy,
+					 &pool->unbuddied[freechunks]);
+			}
 		}
 
 		/* add to beginning of LRU */
diff --git a/net/6lowpan/6lowpan_i.h b/net/6lowpan/6lowpan_i.h
index 97ecc27..a67caee 100644
--- a/net/6lowpan/6lowpan_i.h
+++ b/net/6lowpan/6lowpan_i.h
@@ -12,6 +12,10 @@
 	return lowpan_dev(dev)->lltype == lltype;
 }
 
+extern const struct ndisc_ops lowpan_ndisc_ops;
+
+int addrconf_ifid_802154_6lowpan(u8 *eui, struct net_device *dev);
+
 #ifdef CONFIG_6LOWPAN_DEBUGFS
 int lowpan_dev_debugfs_init(struct net_device *dev);
 void lowpan_dev_debugfs_exit(struct net_device *dev);
diff --git a/net/6lowpan/Makefile b/net/6lowpan/Makefile
index e44f3bf..12d131a 100644
--- a/net/6lowpan/Makefile
+++ b/net/6lowpan/Makefile
@@ -1,6 +1,6 @@
 obj-$(CONFIG_6LOWPAN) += 6lowpan.o
 
-6lowpan-y := core.o iphc.o nhc.o
+6lowpan-y := core.o iphc.o nhc.o ndisc.o
 6lowpan-$(CONFIG_6LOWPAN_DEBUGFS) += debugfs.o
 
 #rfc6282 nhcs
diff --git a/net/6lowpan/core.c b/net/6lowpan/core.c
index 7a240b3..5945f7e 100644
--- a/net/6lowpan/core.c
+++ b/net/6lowpan/core.c
@@ -14,6 +14,7 @@
 #include <linux/module.h>
 
 #include <net/6lowpan.h>
+#include <net/addrconf.h>
 
 #include "6lowpan_i.h"
 
@@ -33,6 +34,8 @@
 	for (i = 0; i < LOWPAN_IPHC_CTX_TABLE_SIZE; i++)
 		lowpan_dev(dev)->ctx.table[i].id = i;
 
+	dev->ndisc_ops = &lowpan_ndisc_ops;
+
 	ret = register_netdevice(dev);
 	if (ret < 0)
 		return ret;
@@ -72,16 +75,61 @@
 }
 EXPORT_SYMBOL(lowpan_unregister_netdev);
 
+int addrconf_ifid_802154_6lowpan(u8 *eui, struct net_device *dev)
+{
+	struct wpan_dev *wpan_dev = lowpan_802154_dev(dev)->wdev->ieee802154_ptr;
+
+	/* Set short_addr autoconfiguration if short_addr is present only */
+	if (!lowpan_802154_is_valid_src_short_addr(wpan_dev->short_addr))
+		return -1;
+
+	/* For either address format, all zero addresses MUST NOT be used */
+	if (wpan_dev->pan_id == cpu_to_le16(0x0000) &&
+	    wpan_dev->short_addr == cpu_to_le16(0x0000))
+		return -1;
+
+	/* Alternatively, if no PAN ID is known, 16 zero bits may be used */
+	if (wpan_dev->pan_id == cpu_to_le16(IEEE802154_PAN_ID_BROADCAST))
+		memset(eui, 0, 2);
+	else
+		ieee802154_le16_to_be16(eui, &wpan_dev->pan_id);
+
+	/* The "Universal/Local" (U/L) bit shall be set to zero */
+	eui[0] &= ~2;
+	eui[2] = 0;
+	eui[3] = 0xFF;
+	eui[4] = 0xFE;
+	eui[5] = 0;
+	ieee802154_le16_to_be16(&eui[6], &wpan_dev->short_addr);
+	return 0;
+}
+
 static int lowpan_event(struct notifier_block *unused,
 			unsigned long event, void *ptr)
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct inet6_dev *idev;
+	struct in6_addr addr;
 	int i;
 
 	if (dev->type != ARPHRD_6LOWPAN)
 		return NOTIFY_DONE;
 
+	idev = __in6_dev_get(dev);
+	if (!idev)
+		return NOTIFY_DONE;
+
 	switch (event) {
+	case NETDEV_UP:
+	case NETDEV_CHANGE:
+		/* (802.15.4 6LoWPAN short address slaac handling */
+		if (lowpan_is_ll(dev, LOWPAN_LLTYPE_IEEE802154) &&
+		    addrconf_ifid_802154_6lowpan(addr.s6_addr + 8, dev) == 0) {
+			__ipv6_addr_set_half(&addr.s6_addr32[0],
+					     htonl(0xFE800000), 0);
+			addrconf_add_linklocal(idev, &addr, 0);
+		}
+		break;
 	case NETDEV_DOWN:
 		for (i = 0; i < LOWPAN_IPHC_CTX_TABLE_SIZE; i++)
 			clear_bit(LOWPAN_IPHC_CTX_FLAG_ACTIVE,
@@ -112,8 +160,6 @@
 		return ret;
 	}
 
-	request_module_nowait("ipv6");
-
 	request_module_nowait("nhc_dest");
 	request_module_nowait("nhc_fragment");
 	request_module_nowait("nhc_hop");
diff --git a/net/6lowpan/debugfs.c b/net/6lowpan/debugfs.c
index acbaa3d..24915e0 100644
--- a/net/6lowpan/debugfs.c
+++ b/net/6lowpan/debugfs.c
@@ -245,6 +245,41 @@
 	.release	= single_release,
 };
 
+static int lowpan_short_addr_get(void *data, u64 *val)
+{
+	struct wpan_dev *wdev = data;
+
+	rtnl_lock();
+	*val = le16_to_cpu(wdev->short_addr);
+	rtnl_unlock();
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(lowpan_short_addr_fops, lowpan_short_addr_get,
+			NULL, "0x%04llx\n");
+
+static int lowpan_dev_debugfs_802154_init(const struct net_device *dev,
+					  struct lowpan_dev *ldev)
+{
+	struct dentry *dentry, *root;
+
+	if (!lowpan_is_ll(dev, LOWPAN_LLTYPE_IEEE802154))
+		return 0;
+
+	root = debugfs_create_dir("ieee802154", ldev->iface_debugfs);
+	if (!root)
+		return -EINVAL;
+
+	dentry = debugfs_create_file("short_addr", 0444, root,
+				     lowpan_802154_dev(dev)->wdev->ieee802154_ptr,
+				     &lowpan_short_addr_fops);
+	if (!dentry)
+		return -EINVAL;
+
+	return 0;
+}
+
 int lowpan_dev_debugfs_init(struct net_device *dev)
 {
 	struct lowpan_dev *ldev = lowpan_dev(dev);
@@ -272,6 +307,10 @@
 			goto remove_root;
 	}
 
+	ret = lowpan_dev_debugfs_802154_init(dev, ldev);
+	if (ret < 0)
+		goto remove_root;
+
 	return 0;
 
 remove_root:
diff --git a/net/6lowpan/iphc.c b/net/6lowpan/iphc.c
index 8501dd5..79f1fa2 100644
--- a/net/6lowpan/iphc.c
+++ b/net/6lowpan/iphc.c
@@ -761,22 +761,75 @@
 	[LOWPAN_IPHC_DAM_11] = LOWPAN_IPHC_SAM_11,
 };
 
-static u8 lowpan_compress_ctx_addr(u8 **hc_ptr, const struct in6_addr *ipaddr,
+static inline bool
+lowpan_iphc_compress_ctx_802154_lladdr(const struct in6_addr *ipaddr,
+				       const struct lowpan_iphc_ctx *ctx,
+				       const void *lladdr)
+{
+	const struct ieee802154_addr *addr = lladdr;
+	unsigned char extended_addr[EUI64_ADDR_LEN];
+	bool lladdr_compress = false;
+	struct in6_addr tmp = {};
+
+	switch (addr->mode) {
+	case IEEE802154_ADDR_LONG:
+		ieee802154_le64_to_be64(&extended_addr, &addr->extended_addr);
+		/* check for SAM/DAM = 11 */
+		memcpy(&tmp.s6_addr[8], &extended_addr, EUI64_ADDR_LEN);
+		/* second bit-flip (Universe/Local) is done according RFC2464 */
+		tmp.s6_addr[8] ^= 0x02;
+		/* context information are always used */
+		ipv6_addr_prefix_copy(&tmp, &ctx->pfx, ctx->plen);
+		if (ipv6_addr_equal(&tmp, ipaddr))
+			lladdr_compress = true;
+		break;
+	case IEEE802154_ADDR_SHORT:
+		tmp.s6_addr[11] = 0xFF;
+		tmp.s6_addr[12] = 0xFE;
+		ieee802154_le16_to_be16(&tmp.s6_addr16[7],
+					&addr->short_addr);
+		/* context information are always used */
+		ipv6_addr_prefix_copy(&tmp, &ctx->pfx, ctx->plen);
+		if (ipv6_addr_equal(&tmp, ipaddr))
+			lladdr_compress = true;
+		break;
+	default:
+		/* should never handled and filtered by 802154 6lowpan */
+		WARN_ON_ONCE(1);
+		break;
+	}
+
+	return lladdr_compress;
+}
+
+static u8 lowpan_compress_ctx_addr(u8 **hc_ptr, const struct net_device *dev,
+				   const struct in6_addr *ipaddr,
 				   const struct lowpan_iphc_ctx *ctx,
 				   const unsigned char *lladdr, bool sam)
 {
 	struct in6_addr tmp = {};
 	u8 dam;
 
-	/* check for SAM/DAM = 11 */
-	memcpy(&tmp.s6_addr[8], lladdr, 8);
-	/* second bit-flip (Universe/Local) is done according RFC2464 */
-	tmp.s6_addr[8] ^= 0x02;
-	/* context information are always used */
-	ipv6_addr_prefix_copy(&tmp, &ctx->pfx, ctx->plen);
-	if (ipv6_addr_equal(&tmp, ipaddr)) {
-		dam = LOWPAN_IPHC_DAM_11;
-		goto out;
+	switch (lowpan_dev(dev)->lltype) {
+	case LOWPAN_LLTYPE_IEEE802154:
+		if (lowpan_iphc_compress_ctx_802154_lladdr(ipaddr, ctx,
+							   lladdr)) {
+			dam = LOWPAN_IPHC_DAM_11;
+			goto out;
+		}
+		break;
+	default:
+		/* check for SAM/DAM = 11 */
+		memcpy(&tmp.s6_addr[8], lladdr, EUI64_ADDR_LEN);
+		/* second bit-flip (Universe/Local) is done according RFC2464 */
+		tmp.s6_addr[8] ^= 0x02;
+		/* context information are always used */
+		ipv6_addr_prefix_copy(&tmp, &ctx->pfx, ctx->plen);
+		if (ipv6_addr_equal(&tmp, ipaddr)) {
+			dam = LOWPAN_IPHC_DAM_11;
+			goto out;
+		}
+		break;
 	}
 
 	memset(&tmp, 0, sizeof(tmp));
@@ -813,28 +866,85 @@
 		return dam;
 }
 
-static u8 lowpan_compress_addr_64(u8 **hc_ptr, const struct in6_addr *ipaddr,
+static inline bool
+lowpan_iphc_compress_802154_lladdr(const struct in6_addr *ipaddr,
+				   const void *lladdr)
+{
+	const struct ieee802154_addr *addr = lladdr;
+	unsigned char extended_addr[EUI64_ADDR_LEN];
+	bool lladdr_compress = false;
+	struct in6_addr tmp = {};
+
+	switch (addr->mode) {
+	case IEEE802154_ADDR_LONG:
+		ieee802154_le64_to_be64(&extended_addr, &addr->extended_addr);
+		if (is_addr_mac_addr_based(ipaddr, extended_addr))
+			lladdr_compress = true;
+		break;
+	case IEEE802154_ADDR_SHORT:
+		/* fe:80::ff:fe00:XXXX
+		 *                \__/
+		 *             short_addr
+		 *
+		 * Universe/Local bit is zero.
+		 */
+		tmp.s6_addr[0] = 0xFE;
+		tmp.s6_addr[1] = 0x80;
+		tmp.s6_addr[11] = 0xFF;
+		tmp.s6_addr[12] = 0xFE;
+		ieee802154_le16_to_be16(&tmp.s6_addr16[7],
+					&addr->short_addr);
+		if (ipv6_addr_equal(&tmp, ipaddr))
+			lladdr_compress = true;
+		break;
+	default:
+		/* should never handled and filtered by 802154 6lowpan */
+		WARN_ON_ONCE(1);
+		break;
+	}
+
+	return lladdr_compress;
+}
+
+static u8 lowpan_compress_addr_64(u8 **hc_ptr, const struct net_device *dev,
+				  const struct in6_addr *ipaddr,
 				  const unsigned char *lladdr, bool sam)
 {
-	u8 dam = LOWPAN_IPHC_DAM_00;
+	u8 dam = LOWPAN_IPHC_DAM_01;
 
-	if (is_addr_mac_addr_based(ipaddr, lladdr)) {
-		dam = LOWPAN_IPHC_DAM_11; /* 0-bits */
-		pr_debug("address compression 0 bits\n");
-	} else if (lowpan_is_iid_16_bit_compressable(ipaddr)) {
+	switch (lowpan_dev(dev)->lltype) {
+	case LOWPAN_LLTYPE_IEEE802154:
+		if (lowpan_iphc_compress_802154_lladdr(ipaddr, lladdr)) {
+			dam = LOWPAN_IPHC_DAM_11; /* 0-bits */
+			pr_debug("address compression 0 bits\n");
+			goto out;
+		}
+		break;
+	default:
+		if (is_addr_mac_addr_based(ipaddr, lladdr)) {
+			dam = LOWPAN_IPHC_DAM_11; /* 0-bits */
+			pr_debug("address compression 0 bits\n");
+			goto out;
+		}
+		break;
+	}
+
+	if (lowpan_is_iid_16_bit_compressable(ipaddr)) {
 		/* compress IID to 16 bits xxxx::XXXX */
 		lowpan_push_hc_data(hc_ptr, &ipaddr->s6_addr16[7], 2);
 		dam = LOWPAN_IPHC_DAM_10; /* 16-bits */
 		raw_dump_inline(NULL, "Compressed ipv6 addr is (16 bits)",
 				*hc_ptr - 2, 2);
-	} else {
-		/* do not compress IID => xxxx::IID */
-		lowpan_push_hc_data(hc_ptr, &ipaddr->s6_addr16[4], 8);
-		dam = LOWPAN_IPHC_DAM_01; /* 64-bits */
-		raw_dump_inline(NULL, "Compressed ipv6 addr is (64 bits)",
-				*hc_ptr - 8, 8);
+		goto out;
 	}
 
+	/* do not compress IID => xxxx::IID */
+	lowpan_push_hc_data(hc_ptr, &ipaddr->s6_addr16[4], 8);
+	raw_dump_inline(NULL, "Compressed ipv6 addr is (64 bits)",
+			*hc_ptr - 8, 8);
+
+out:
+
 	if (sam)
 		return lowpan_iphc_dam_to_sam_value[dam];
 	else
@@ -1013,9 +1123,6 @@
 	iphc0 = LOWPAN_DISPATCH_IPHC;
 	iphc1 = 0;
 
-	raw_dump_inline(__func__, "saddr", saddr, EUI64_ADDR_LEN);
-	raw_dump_inline(__func__, "daddr", daddr, EUI64_ADDR_LEN);
-
 	raw_dump_table(__func__, "sending raw skb network uncompressed packet",
 		       skb->data, skb->len);
 
@@ -1088,14 +1195,15 @@
 		iphc1 |= LOWPAN_IPHC_SAC;
 	} else {
 		if (sci) {
-			iphc1 |= lowpan_compress_ctx_addr(&hc_ptr, &hdr->saddr,
+			iphc1 |= lowpan_compress_ctx_addr(&hc_ptr, dev,
+							  &hdr->saddr,
 							  &sci_entry, saddr,
 							  true);
 			iphc1 |= LOWPAN_IPHC_SAC;
 		} else {
 			if (ipv6_saddr_type & IPV6_ADDR_LINKLOCAL &&
 			    lowpan_is_linklocal_zero_padded(hdr->saddr)) {
-				iphc1 |= lowpan_compress_addr_64(&hc_ptr,
+				iphc1 |= lowpan_compress_addr_64(&hc_ptr, dev,
 								 &hdr->saddr,
 								 saddr, true);
 				pr_debug("source address unicast link-local %pI6c iphc1 0x%02x\n",
@@ -1123,14 +1231,15 @@
 		}
 	} else {
 		if (dci) {
-			iphc1 |= lowpan_compress_ctx_addr(&hc_ptr, &hdr->daddr,
+			iphc1 |= lowpan_compress_ctx_addr(&hc_ptr, dev,
+							  &hdr->daddr,
 							  &dci_entry, daddr,
 							  false);
 			iphc1 |= LOWPAN_IPHC_DAC;
 		} else {
 			if (ipv6_daddr_type & IPV6_ADDR_LINKLOCAL &&
 			    lowpan_is_linklocal_zero_padded(hdr->daddr)) {
-				iphc1 |= lowpan_compress_addr_64(&hc_ptr,
+				iphc1 |= lowpan_compress_addr_64(&hc_ptr, dev,
 								 &hdr->daddr,
 								 daddr, false);
 				pr_debug("dest address unicast link-local %pI6c iphc1 0x%02x\n",
diff --git a/net/6lowpan/ndisc.c b/net/6lowpan/ndisc.c
new file mode 100644
index 0000000..ae1d419
--- /dev/null
+++ b/net/6lowpan/ndisc.c
@@ -0,0 +1,234 @@
+/* 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.
+ *
+ * Authors:
+ * (C) 2016 Pengutronix, Alexander Aring <aar@pengutronix.de>
+ */
+
+#include <net/6lowpan.h>
+#include <net/addrconf.h>
+#include <net/ndisc.h>
+
+#include "6lowpan_i.h"
+
+static int lowpan_ndisc_is_useropt(u8 nd_opt_type)
+{
+	return nd_opt_type == ND_OPT_6CO;
+}
+
+#if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN)
+#define NDISC_802154_SHORT_ADDR_LENGTH	1
+static int lowpan_ndisc_parse_802154_options(const struct net_device *dev,
+					     struct nd_opt_hdr *nd_opt,
+					     struct ndisc_options *ndopts)
+{
+	switch (nd_opt->nd_opt_len) {
+	case NDISC_802154_SHORT_ADDR_LENGTH:
+		if (ndopts->nd_802154_opt_array[nd_opt->nd_opt_type])
+			ND_PRINTK(2, warn,
+				  "%s: duplicated short addr ND6 option found: type=%d\n",
+				  __func__, nd_opt->nd_opt_type);
+		else
+			ndopts->nd_802154_opt_array[nd_opt->nd_opt_type] = nd_opt;
+		return 1;
+	default:
+		/* all others will be handled by ndisc IPv6 option parsing */
+		return 0;
+	}
+}
+
+static int lowpan_ndisc_parse_options(const struct net_device *dev,
+				      struct nd_opt_hdr *nd_opt,
+				      struct ndisc_options *ndopts)
+{
+	switch (nd_opt->nd_opt_type) {
+	case ND_OPT_SOURCE_LL_ADDR:
+	case ND_OPT_TARGET_LL_ADDR:
+		return lowpan_ndisc_parse_802154_options(dev, nd_opt, ndopts);
+	default:
+		return 0;
+	}
+}
+
+static void lowpan_ndisc_802154_update(struct neighbour *n, u32 flags,
+				       u8 icmp6_type,
+				       const struct ndisc_options *ndopts)
+{
+	struct lowpan_802154_neigh *neigh = lowpan_802154_neigh(neighbour_priv(n));
+	u8 *lladdr_short = NULL;
+
+	switch (icmp6_type) {
+	case NDISC_ROUTER_SOLICITATION:
+	case NDISC_ROUTER_ADVERTISEMENT:
+	case NDISC_NEIGHBOUR_SOLICITATION:
+		if (ndopts->nd_802154_opts_src_lladdr) {
+			lladdr_short = __ndisc_opt_addr_data(ndopts->nd_802154_opts_src_lladdr,
+							     IEEE802154_SHORT_ADDR_LEN, 0);
+			if (!lladdr_short) {
+				ND_PRINTK(2, warn,
+					  "NA: invalid short link-layer address length\n");
+				return;
+			}
+		}
+		break;
+	case NDISC_REDIRECT:
+	case NDISC_NEIGHBOUR_ADVERTISEMENT:
+		if (ndopts->nd_802154_opts_tgt_lladdr) {
+			lladdr_short = __ndisc_opt_addr_data(ndopts->nd_802154_opts_tgt_lladdr,
+							     IEEE802154_SHORT_ADDR_LEN, 0);
+			if (!lladdr_short) {
+				ND_PRINTK(2, warn,
+					  "NA: invalid short link-layer address length\n");
+				return;
+			}
+		}
+		break;
+	default:
+		break;
+	}
+
+	write_lock_bh(&n->lock);
+	if (lladdr_short)
+		ieee802154_be16_to_le16(&neigh->short_addr, lladdr_short);
+	else
+		neigh->short_addr = cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC);
+	write_unlock_bh(&n->lock);
+}
+
+static void lowpan_ndisc_update(const struct net_device *dev,
+				struct neighbour *n, u32 flags, u8 icmp6_type,
+				const struct ndisc_options *ndopts)
+{
+	if (!lowpan_is_ll(dev, LOWPAN_LLTYPE_IEEE802154))
+		return;
+
+	/* react on overrides only. TODO check if this is really right. */
+	if (flags & NEIGH_UPDATE_F_OVERRIDE)
+		lowpan_ndisc_802154_update(n, flags, icmp6_type, ndopts);
+}
+
+static int lowpan_ndisc_opt_addr_space(const struct net_device *dev,
+				       u8 icmp6_type, struct neighbour *neigh,
+				       u8 *ha_buf, u8 **ha)
+{
+	struct lowpan_802154_neigh *n;
+	struct wpan_dev *wpan_dev;
+	int addr_space = 0;
+
+	if (!lowpan_is_ll(dev, LOWPAN_LLTYPE_IEEE802154))
+		return 0;
+
+	switch (icmp6_type) {
+	case NDISC_REDIRECT:
+		n = lowpan_802154_neigh(neighbour_priv(neigh));
+
+		read_lock_bh(&neigh->lock);
+		if (lowpan_802154_is_valid_src_short_addr(n->short_addr)) {
+			memcpy(ha_buf, &n->short_addr,
+			       IEEE802154_SHORT_ADDR_LEN);
+			read_unlock_bh(&neigh->lock);
+			addr_space += __ndisc_opt_addr_space(IEEE802154_SHORT_ADDR_LEN, 0);
+			*ha = ha_buf;
+		}
+		read_unlock_bh(&neigh->lock);
+		break;
+	case NDISC_NEIGHBOUR_ADVERTISEMENT:
+	case NDISC_NEIGHBOUR_SOLICITATION:
+	case NDISC_ROUTER_SOLICITATION:
+		wpan_dev = lowpan_802154_dev(dev)->wdev->ieee802154_ptr;
+
+		if (lowpan_802154_is_valid_src_short_addr(wpan_dev->short_addr))
+			addr_space = __ndisc_opt_addr_space(IEEE802154_SHORT_ADDR_LEN, 0);
+		break;
+	default:
+		break;
+	}
+
+	return addr_space;
+}
+
+static void lowpan_ndisc_fill_addr_option(const struct net_device *dev,
+					  struct sk_buff *skb, u8 icmp6_type,
+					  const u8 *ha)
+{
+	struct wpan_dev *wpan_dev;
+	__be16 short_addr;
+	u8 opt_type;
+
+	if (!lowpan_is_ll(dev, LOWPAN_LLTYPE_IEEE802154))
+		return;
+
+	switch (icmp6_type) {
+	case NDISC_REDIRECT:
+		if (ha) {
+			ieee802154_le16_to_be16(&short_addr, ha);
+			__ndisc_fill_addr_option(skb, ND_OPT_TARGET_LL_ADDR,
+						 &short_addr,
+						 IEEE802154_SHORT_ADDR_LEN, 0);
+		}
+		return;
+	case NDISC_NEIGHBOUR_ADVERTISEMENT:
+		opt_type = ND_OPT_TARGET_LL_ADDR;
+		break;
+	case NDISC_ROUTER_SOLICITATION:
+	case NDISC_NEIGHBOUR_SOLICITATION:
+		opt_type = ND_OPT_SOURCE_LL_ADDR;
+		break;
+	default:
+		return;
+	}
+
+	wpan_dev = lowpan_802154_dev(dev)->wdev->ieee802154_ptr;
+
+	if (lowpan_802154_is_valid_src_short_addr(wpan_dev->short_addr)) {
+		ieee802154_le16_to_be16(&short_addr,
+					&wpan_dev->short_addr);
+		__ndisc_fill_addr_option(skb, opt_type, &short_addr,
+					 IEEE802154_SHORT_ADDR_LEN, 0);
+	}
+}
+
+static void lowpan_ndisc_prefix_rcv_add_addr(struct net *net,
+					     struct net_device *dev,
+					     const struct prefix_info *pinfo,
+					     struct inet6_dev *in6_dev,
+					     struct in6_addr *addr,
+					     int addr_type, u32 addr_flags,
+					     bool sllao, bool tokenized,
+					     __u32 valid_lft,
+					     u32 prefered_lft,
+					     bool dev_addr_generated)
+{
+	int err;
+
+	/* generates short based address for RA PIO's */
+	if (lowpan_is_ll(dev, LOWPAN_LLTYPE_IEEE802154) && dev_addr_generated &&
+	    !addrconf_ifid_802154_6lowpan(addr->s6_addr + 8, dev)) {
+		err = addrconf_prefix_rcv_add_addr(net, dev, pinfo, in6_dev,
+						   addr, addr_type, addr_flags,
+						   sllao, tokenized, valid_lft,
+						   prefered_lft);
+		if (err)
+			ND_PRINTK(2, warn,
+				  "RA: could not add a short address based address for prefix: %pI6c\n",
+				  &pinfo->prefix);
+	}
+}
+#endif
+
+const struct ndisc_ops lowpan_ndisc_ops = {
+	.is_useropt		= lowpan_ndisc_is_useropt,
+#if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN)
+	.parse_options		= lowpan_ndisc_parse_options,
+	.update			= lowpan_ndisc_update,
+	.opt_addr_space		= lowpan_ndisc_opt_addr_space,
+	.fill_addr_option	= lowpan_ndisc_fill_addr_option,
+	.prefix_rcv_add_addr	= lowpan_ndisc_prefix_rcv_add_addr,
+#endif
+};
diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index e3857ed..f75091c 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -653,7 +653,7 @@
 				   len + ETH_HLEN);
 
 		ret = NET_RX_SUCCESS;
-	} else if (res == NET_XMIT_POLICED) {
+	} else if (res == -EINPROGRESS) {
 		/* skb was buffered and consumed */
 		ret = NET_RX_SUCCESS;
 	}
diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c
index f2f1256..b1a4e8a 100644
--- a/net/batman-adv/send.c
+++ b/net/batman-adv/send.c
@@ -156,7 +156,7 @@
  * attempted.
  *
  * Return: NET_XMIT_SUCCESS on success, NET_XMIT_DROP on failure, or
- * NET_XMIT_POLICED if the skb is buffered for later transmit.
+ * -EINPROGRESS if the skb is buffered for later transmit.
  */
 int batadv_send_skb_to_orig(struct sk_buff *skb,
 			    struct batadv_orig_node *orig_node,
@@ -188,7 +188,7 @@
 	 * network coding fails, then send the packet as usual.
 	 */
 	if (recv_if && batadv_nc_skb_forward(skb, neigh_node)) {
-		ret = NET_XMIT_POLICED;
+		ret = -EINPROGRESS;
 	} else {
 		batadv_send_unicast_skb(skb, neigh_node);
 		ret = NET_XMIT_SUCCESS;
diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index 780089d..d020299 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -627,20 +627,9 @@
 	return err < 0 ? NET_XMIT_DROP : err;
 }
 
-static struct lock_class_key bt_tx_busylock;
-static struct lock_class_key bt_netdev_xmit_lock_key;
-
-static void bt_set_lockdep_class_one(struct net_device *dev,
-				     struct netdev_queue *txq,
-				     void *_unused)
-{
-	lockdep_set_class(&txq->_xmit_lock, &bt_netdev_xmit_lock_key);
-}
-
 static int bt_dev_init(struct net_device *dev)
 {
-	netdev_for_each_tx_queue(dev, bt_set_lockdep_class_one, NULL);
-	dev->qdisc_tx_busylock = &bt_tx_busylock;
+	netdev_lockdep_set_classes(dev);
 
 	return 0;
 }
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index dcea4f4..c18080a 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -279,6 +279,8 @@
 	 * change from under us.
 	 */
 	list_for_each_entry(v, &vg->vlan_list, vlist) {
+		if (!br_vlan_should_use(v))
+			continue;
 		f = __br_fdb_get(br, br->dev->dev_addr, v->vid);
 		if (f && f->is_local && !f->dst)
 			fdb_delete_local(br, NULL, f);
diff --git a/net/can/Makefile b/net/can/Makefile
index cef49eb..1093675 100644
--- a/net/can/Makefile
+++ b/net/can/Makefile
@@ -3,7 +3,8 @@
 #
 
 obj-$(CONFIG_CAN)	+= can.o
-can-y			:= af_can.o proc.o
+can-y			:= af_can.o
+can-$(CONFIG_PROC_FS)	+= proc.o
 
 obj-$(CONFIG_CAN_RAW)	+= can-raw.o
 can-raw-y		:= raw.o
diff --git a/net/can/af_can.h b/net/can/af_can.h
index fca0fe9..38a79ff 100644
--- a/net/can/af_can.h
+++ b/net/can/af_can.h
@@ -113,8 +113,19 @@
 extern struct dev_rcv_lists can_rx_alldev_list;
 
 /* function prototypes for the CAN networklayer procfs (proc.c) */
+#ifdef CONFIG_PROC_FS
 void can_init_proc(void);
 void can_remove_proc(void);
+#else
+static inline void can_init_proc(void)
+{
+	pr_info("can: Can't create /proc/net/can. CONFIG_PROC_FS missing!\n");
+}
+
+static inline void can_remove_proc(void)
+{
+}
+#endif
 void can_stat_update(unsigned long data);
 
 /* structures and variables from af_can.c needed in proc.c for reading */
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 6863310..8e999ff 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -1,7 +1,7 @@
 /*
  * bcm.c - Broadcast Manager to filter/send (cyclic) CAN content
  *
- * Copyright (c) 2002-2007 Volkswagen Group Electronic Research
+ * Copyright (c) 2002-2016 Volkswagen Group Electronic Research
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -67,27 +67,31 @@
  */
 #define MAX_NFRAMES 256
 
-/* use of last_frames[index].can_dlc */
+/* use of last_frames[index].flags */
 #define RX_RECV    0x40 /* received data for this element */
 #define RX_THR     0x80 /* element not been sent due to throttle feature */
-#define BCM_CAN_DLC_MASK 0x0F /* clean private flags in can_dlc by masking */
+#define BCM_CAN_FLAGS_MASK 0x3F /* to clean private flags after usage */
 
 /* get best masking value for can_rx_register() for a given single can_id */
 #define REGMASK(id) ((id & CAN_EFF_FLAG) ? \
 		     (CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG) : \
 		     (CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG))
 
-#define CAN_BCM_VERSION CAN_VERSION
+#define CAN_BCM_VERSION "20160617"
 
 MODULE_DESCRIPTION("PF_CAN broadcast manager protocol");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Oliver Hartkopp <oliver.hartkopp@volkswagen.de>");
 MODULE_ALIAS("can-proto-2");
 
-/* easy access to can_frame payload */
-static inline u64 GET_U64(const struct can_frame *cp)
+/*
+ * easy access to the first 64 bit of can(fd)_frame payload. cp->data is
+ * 64 bit aligned so the offset has to be multiples of 8 which is ensured
+ * by the only callers in bcm_rx_cmp_to_index() bcm_rx_handler().
+ */
+static inline u64 get_u64(const struct canfd_frame *cp, int offset)
 {
-	return *(u64 *)cp->data;
+	return *(u64 *)(cp->data + offset);
 }
 
 struct bcm_op {
@@ -101,13 +105,14 @@
 	struct tasklet_struct tsklet, thrtsklet;
 	ktime_t rx_stamp, kt_ival1, kt_ival2, kt_lastmsg;
 	int rx_ifindex;
+	int cfsiz;
 	u32 count;
 	u32 nframes;
 	u32 currframe;
-	struct can_frame *frames;
-	struct can_frame *last_frames;
-	struct can_frame sframe;
-	struct can_frame last_sframe;
+	struct canfd_frame *frames;
+	struct canfd_frame *last_frames;
+	struct canfd_frame sframe;
+	struct canfd_frame last_sframe;
 	struct sock *sk;
 	struct net_device *rx_reg_dev;
 };
@@ -136,7 +141,7 @@
 	return ktime_set(tv.tv_sec, tv.tv_usec * NSEC_PER_USEC);
 }
 
-#define CFSIZ sizeof(struct can_frame)
+#define CFSIZ(flags) ((flags & CAN_FD_FRAME) ? CANFD_MTU : CAN_MTU)
 #define OPSIZ sizeof(struct bcm_op)
 #define MHSIZ sizeof(struct bcm_msg_head)
 
@@ -183,43 +188,50 @@
 		if (!op->frames_abs)
 			continue;
 
-		seq_printf(m, "rx_op: %03X %-5s ",
-				op->can_id, bcm_proc_getifname(ifname, op->ifindex));
-		seq_printf(m, "[%u]%c ", op->nframes,
-				(op->flags & RX_CHECK_DLC)?'d':' ');
+		seq_printf(m, "rx_op: %03X %-5s ", op->can_id,
+			   bcm_proc_getifname(ifname, op->ifindex));
+
+		if (op->flags & CAN_FD_FRAME)
+			seq_printf(m, "(%u)", op->nframes);
+		else
+			seq_printf(m, "[%u]", op->nframes);
+
+		seq_printf(m, "%c ", (op->flags & RX_CHECK_DLC) ? 'd' : ' ');
+
 		if (op->kt_ival1.tv64)
 			seq_printf(m, "timeo=%lld ",
-					(long long)
-					ktime_to_us(op->kt_ival1));
+				   (long long)ktime_to_us(op->kt_ival1));
 
 		if (op->kt_ival2.tv64)
 			seq_printf(m, "thr=%lld ",
-					(long long)
-					ktime_to_us(op->kt_ival2));
+				   (long long)ktime_to_us(op->kt_ival2));
 
 		seq_printf(m, "# recv %ld (%ld) => reduction: ",
-				op->frames_filtered, op->frames_abs);
+			   op->frames_filtered, op->frames_abs);
 
 		reduction = 100 - (op->frames_filtered * 100) / op->frames_abs;
 
 		seq_printf(m, "%s%ld%%\n",
-				(reduction == 100)?"near ":"", reduction);
+			   (reduction == 100) ? "near " : "", reduction);
 	}
 
 	list_for_each_entry(op, &bo->tx_ops, list) {
 
-		seq_printf(m, "tx_op: %03X %s [%u] ",
-				op->can_id,
-				bcm_proc_getifname(ifname, op->ifindex),
-				op->nframes);
+		seq_printf(m, "tx_op: %03X %s ", op->can_id,
+			   bcm_proc_getifname(ifname, op->ifindex));
+
+		if (op->flags & CAN_FD_FRAME)
+			seq_printf(m, "(%u) ", op->nframes);
+		else
+			seq_printf(m, "[%u] ", op->nframes);
 
 		if (op->kt_ival1.tv64)
 			seq_printf(m, "t1=%lld ",
-					(long long) ktime_to_us(op->kt_ival1));
+				   (long long)ktime_to_us(op->kt_ival1));
 
 		if (op->kt_ival2.tv64)
 			seq_printf(m, "t2=%lld ",
-					(long long) ktime_to_us(op->kt_ival2));
+				   (long long)ktime_to_us(op->kt_ival2));
 
 		seq_printf(m, "# sent %ld\n", op->frames_abs);
 	}
@@ -248,7 +260,7 @@
 {
 	struct sk_buff *skb;
 	struct net_device *dev;
-	struct can_frame *cf = &op->frames[op->currframe];
+	struct canfd_frame *cf = op->frames + op->cfsiz * op->currframe;
 
 	/* no target device? => exit */
 	if (!op->ifindex)
@@ -260,7 +272,7 @@
 		return;
 	}
 
-	skb = alloc_skb(CFSIZ + sizeof(struct can_skb_priv), gfp_any());
+	skb = alloc_skb(op->cfsiz + sizeof(struct can_skb_priv), gfp_any());
 	if (!skb)
 		goto out;
 
@@ -268,7 +280,7 @@
 	can_skb_prv(skb)->ifindex = dev->ifindex;
 	can_skb_prv(skb)->skbcnt = 0;
 
-	memcpy(skb_put(skb, CFSIZ), cf, CFSIZ);
+	memcpy(skb_put(skb, op->cfsiz), cf, op->cfsiz);
 
 	/* send with loopback */
 	skb->dev = dev;
@@ -282,7 +294,7 @@
 	/* reached last frame? */
 	if (op->currframe >= op->nframes)
 		op->currframe = 0;
- out:
+out:
 	dev_put(dev);
 }
 
@@ -291,13 +303,13 @@
  *                    (consisting of bcm_msg_head + x CAN frames)
  */
 static void bcm_send_to_user(struct bcm_op *op, struct bcm_msg_head *head,
-			     struct can_frame *frames, int has_timestamp)
+			     struct canfd_frame *frames, int has_timestamp)
 {
 	struct sk_buff *skb;
-	struct can_frame *firstframe;
+	struct canfd_frame *firstframe;
 	struct sockaddr_can *addr;
 	struct sock *sk = op->sk;
-	unsigned int datalen = head->nframes * CFSIZ;
+	unsigned int datalen = head->nframes * op->cfsiz;
 	int err;
 
 	skb = alloc_skb(sizeof(*head) + datalen, gfp_any());
@@ -307,19 +319,19 @@
 	memcpy(skb_put(skb, sizeof(*head)), head, sizeof(*head));
 
 	if (head->nframes) {
-		/* can_frames starting here */
-		firstframe = (struct can_frame *)skb_tail_pointer(skb);
+		/* CAN frames starting here */
+		firstframe = (struct canfd_frame *)skb_tail_pointer(skb);
 
 		memcpy(skb_put(skb, datalen), frames, datalen);
 
 		/*
-		 * the BCM uses the can_dlc-element of the can_frame
+		 * the BCM uses the flags-element of the canfd_frame
 		 * structure for internal purposes. This is only
 		 * relevant for updates that are generated by the
 		 * BCM, where nframes is 1
 		 */
 		if (head->nframes == 1)
-			firstframe->can_dlc &= BCM_CAN_DLC_MASK;
+			firstframe->flags &= BCM_CAN_FLAGS_MASK;
 	}
 
 	if (has_timestamp) {
@@ -406,7 +418,7 @@
 /*
  * bcm_rx_changed - create a RX_CHANGED notification due to changed content
  */
-static void bcm_rx_changed(struct bcm_op *op, struct can_frame *data)
+static void bcm_rx_changed(struct bcm_op *op, struct canfd_frame *data)
 {
 	struct bcm_msg_head head;
 
@@ -418,7 +430,7 @@
 		op->frames_filtered = op->frames_abs = 0;
 
 	/* this element is not throttled anymore */
-	data->can_dlc &= (BCM_CAN_DLC_MASK|RX_RECV);
+	data->flags &= (BCM_CAN_FLAGS_MASK|RX_RECV);
 
 	head.opcode  = RX_CHANGED;
 	head.flags   = op->flags;
@@ -437,13 +449,13 @@
  *                          2. send a notification to the user (if possible)
  */
 static void bcm_rx_update_and_send(struct bcm_op *op,
-				   struct can_frame *lastdata,
-				   const struct can_frame *rxdata)
+				   struct canfd_frame *lastdata,
+				   const struct canfd_frame *rxdata)
 {
-	memcpy(lastdata, rxdata, CFSIZ);
+	memcpy(lastdata, rxdata, op->cfsiz);
 
 	/* mark as used and throttled by default */
-	lastdata->can_dlc |= (RX_RECV|RX_THR);
+	lastdata->flags |= (RX_RECV|RX_THR);
 
 	/* throttling mode inactive ? */
 	if (!op->kt_ival2.tv64) {
@@ -481,33 +493,36 @@
  *                       received data stored in op->last_frames[]
  */
 static void bcm_rx_cmp_to_index(struct bcm_op *op, unsigned int index,
-				const struct can_frame *rxdata)
+				const struct canfd_frame *rxdata)
 {
+	struct canfd_frame *cf = op->frames + op->cfsiz * index;
+	struct canfd_frame *lcf = op->last_frames + op->cfsiz * index;
+	int i;
+
 	/*
-	 * no one uses the MSBs of can_dlc for comparison,
+	 * no one uses the MSBs of flags for comparison,
 	 * so we use it here to detect the first time of reception
 	 */
 
-	if (!(op->last_frames[index].can_dlc & RX_RECV)) {
+	if (!(lcf->flags & RX_RECV)) {
 		/* received data for the first time => send update to user */
-		bcm_rx_update_and_send(op, &op->last_frames[index], rxdata);
+		bcm_rx_update_and_send(op, lcf, rxdata);
 		return;
 	}
 
-	/* do a real check in can_frame data section */
-
-	if ((GET_U64(&op->frames[index]) & GET_U64(rxdata)) !=
-	    (GET_U64(&op->frames[index]) & GET_U64(&op->last_frames[index]))) {
-		bcm_rx_update_and_send(op, &op->last_frames[index], rxdata);
-		return;
+	/* do a real check in CAN frame data section */
+	for (i = 0; i < rxdata->len; i += 8) {
+		if ((get_u64(cf, i) & get_u64(rxdata, i)) !=
+		    (get_u64(cf, i) & get_u64(lcf, i))) {
+			bcm_rx_update_and_send(op, lcf, rxdata);
+			return;
+		}
 	}
 
 	if (op->flags & RX_CHECK_DLC) {
-		/* do a real check in can_frame dlc */
-		if (rxdata->can_dlc != (op->last_frames[index].can_dlc &
-					BCM_CAN_DLC_MASK)) {
-			bcm_rx_update_and_send(op, &op->last_frames[index],
-					       rxdata);
+		/* do a real check in CAN frame length */
+		if (rxdata->len != lcf->len) {
+			bcm_rx_update_and_send(op, lcf, rxdata);
 			return;
 		}
 	}
@@ -556,8 +571,8 @@
 
 	/* if user wants to be informed, when cyclic CAN-Messages come back */
 	if ((op->flags & RX_ANNOUNCE_RESUME) && op->last_frames) {
-		/* clear received can_frames to indicate 'nothing received' */
-		memset(op->last_frames, 0, op->nframes * CFSIZ);
+		/* clear received CAN frames to indicate 'nothing received' */
+		memset(op->last_frames, 0, op->nframes * op->cfsiz);
 	}
 
 	return HRTIMER_NORESTART;
@@ -569,9 +584,11 @@
 static inline int bcm_rx_do_flush(struct bcm_op *op, int update,
 				  unsigned int index)
 {
-	if ((op->last_frames) && (op->last_frames[index].can_dlc & RX_THR)) {
+	struct canfd_frame *lcf = op->last_frames + op->cfsiz * index;
+
+	if ((op->last_frames) && (lcf->flags & RX_THR)) {
 		if (update)
-			bcm_rx_changed(op, &op->last_frames[index]);
+			bcm_rx_changed(op, lcf);
 		return 1;
 	}
 	return 0;
@@ -636,15 +653,19 @@
 static void bcm_rx_handler(struct sk_buff *skb, void *data)
 {
 	struct bcm_op *op = (struct bcm_op *)data;
-	const struct can_frame *rxframe = (struct can_frame *)skb->data;
+	const struct canfd_frame *rxframe = (struct canfd_frame *)skb->data;
 	unsigned int i;
 
-	/* disable timeout */
-	hrtimer_cancel(&op->timer);
-
 	if (op->can_id != rxframe->can_id)
 		return;
 
+	/* make sure to handle the correct frame type (CAN / CAN FD) */
+	if (skb->len != op->cfsiz)
+		return;
+
+	/* disable timeout */
+	hrtimer_cancel(&op->timer);
+
 	/* save rx timestamp */
 	op->rx_stamp = skb->tstamp;
 	/* save originator for recvfrom() */
@@ -675,13 +696,14 @@
 		 * multiplex compare
 		 *
 		 * find the first multiplex mask that fits.
-		 * Remark: The MUX-mask is stored in index 0
+		 * Remark: The MUX-mask is stored in index 0 - but only the
+		 * first 64 bits of the frame data[] are relevant (CAN FD)
 		 */
 
 		for (i = 1; i < op->nframes; i++) {
-			if ((GET_U64(&op->frames[0]) & GET_U64(rxframe)) ==
-			    (GET_U64(&op->frames[0]) &
-			     GET_U64(&op->frames[i]))) {
+			if ((get_u64(op->frames, 0) & get_u64(rxframe, 0)) ==
+			    (get_u64(op->frames, 0) &
+			     get_u64(op->frames + op->cfsiz * i, 0))) {
 				bcm_rx_cmp_to_index(op, i, rxframe);
 				break;
 			}
@@ -695,13 +717,14 @@
 /*
  * helpers for bcm_op handling: find & delete bcm [rx|tx] op elements
  */
-static struct bcm_op *bcm_find_op(struct list_head *ops, canid_t can_id,
-				  int ifindex)
+static struct bcm_op *bcm_find_op(struct list_head *ops,
+				  struct bcm_msg_head *mh, int ifindex)
 {
 	struct bcm_op *op;
 
 	list_for_each_entry(op, ops, list) {
-		if ((op->can_id == can_id) && (op->ifindex == ifindex))
+		if ((op->can_id == mh->can_id) && (op->ifindex == ifindex) &&
+		    (op->flags & CAN_FD_FRAME) == (mh->flags & CAN_FD_FRAME))
 			return op;
 	}
 
@@ -744,12 +767,14 @@
 /*
  * bcm_delete_rx_op - find and remove a rx op (returns number of removed ops)
  */
-static int bcm_delete_rx_op(struct list_head *ops, canid_t can_id, int ifindex)
+static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh,
+			    int ifindex)
 {
 	struct bcm_op *op, *n;
 
 	list_for_each_entry_safe(op, n, ops, list) {
-		if ((op->can_id == can_id) && (op->ifindex == ifindex)) {
+		if ((op->can_id == mh->can_id) && (op->ifindex == ifindex) &&
+		    (op->flags & CAN_FD_FRAME) == (mh->flags & CAN_FD_FRAME)) {
 
 			/*
 			 * Don't care if we're bound or not (due to netdev
@@ -789,12 +814,14 @@
 /*
  * bcm_delete_tx_op - find and remove a tx op (returns number of removed ops)
  */
-static int bcm_delete_tx_op(struct list_head *ops, canid_t can_id, int ifindex)
+static int bcm_delete_tx_op(struct list_head *ops, struct bcm_msg_head *mh,
+			    int ifindex)
 {
 	struct bcm_op *op, *n;
 
 	list_for_each_entry_safe(op, n, ops, list) {
-		if ((op->can_id == can_id) && (op->ifindex == ifindex)) {
+		if ((op->can_id == mh->can_id) && (op->ifindex == ifindex) &&
+		    (op->flags & CAN_FD_FRAME) == (mh->flags & CAN_FD_FRAME)) {
 			list_del(&op->list);
 			bcm_remove_op(op);
 			return 1; /* done */
@@ -810,7 +837,7 @@
 static int bcm_read_op(struct list_head *ops, struct bcm_msg_head *msg_head,
 		       int ifindex)
 {
-	struct bcm_op *op = bcm_find_op(ops, msg_head->can_id, ifindex);
+	struct bcm_op *op = bcm_find_op(ops, msg_head, ifindex);
 
 	if (!op)
 		return -EINVAL;
@@ -835,6 +862,7 @@
 {
 	struct bcm_sock *bo = bcm_sk(sk);
 	struct bcm_op *op;
+	struct canfd_frame *cf;
 	unsigned int i;
 	int err;
 
@@ -842,39 +870,46 @@
 	if (!ifindex)
 		return -ENODEV;
 
-	/* check nframes boundaries - we need at least one can_frame */
+	/* check nframes boundaries - we need at least one CAN frame */
 	if (msg_head->nframes < 1 || msg_head->nframes > MAX_NFRAMES)
 		return -EINVAL;
 
 	/* check the given can_id */
-	op = bcm_find_op(&bo->tx_ops, msg_head->can_id, ifindex);
-
+	op = bcm_find_op(&bo->tx_ops, msg_head, ifindex);
 	if (op) {
 		/* update existing BCM operation */
 
 		/*
-		 * Do we need more space for the can_frames than currently
+		 * Do we need more space for the CAN frames than currently
 		 * allocated? -> This is a _really_ unusual use-case and
 		 * therefore (complexity / locking) it is not supported.
 		 */
 		if (msg_head->nframes > op->nframes)
 			return -E2BIG;
 
-		/* update can_frames content */
+		/* update CAN frames content */
 		for (i = 0; i < msg_head->nframes; i++) {
-			err = memcpy_from_msg((u8 *)&op->frames[i], msg, CFSIZ);
 
-			if (op->frames[i].can_dlc > 8)
-				err = -EINVAL;
+			cf = op->frames + op->cfsiz * i;
+			err = memcpy_from_msg((u8 *)cf, msg, op->cfsiz);
+
+			if (op->flags & CAN_FD_FRAME) {
+				if (cf->len > 64)
+					err = -EINVAL;
+			} else {
+				if (cf->len > 8)
+					err = -EINVAL;
+			}
 
 			if (err < 0)
 				return err;
 
 			if (msg_head->flags & TX_CP_CAN_ID) {
 				/* copy can_id into frame */
-				op->frames[i].can_id = msg_head->can_id;
+				cf->can_id = msg_head->can_id;
 			}
 		}
+		op->flags = msg_head->flags;
 
 	} else {
 		/* insert new BCM operation for the given can_id */
@@ -883,11 +918,13 @@
 		if (!op)
 			return -ENOMEM;
 
-		op->can_id    = msg_head->can_id;
+		op->can_id = msg_head->can_id;
+		op->cfsiz = CFSIZ(msg_head->flags);
+		op->flags = msg_head->flags;
 
-		/* create array for can_frames and copy the data */
+		/* create array for CAN frames and copy the data */
 		if (msg_head->nframes > 1) {
-			op->frames = kmalloc(msg_head->nframes * CFSIZ,
+			op->frames = kmalloc(msg_head->nframes * op->cfsiz,
 					     GFP_KERNEL);
 			if (!op->frames) {
 				kfree(op);
@@ -897,10 +934,17 @@
 			op->frames = &op->sframe;
 
 		for (i = 0; i < msg_head->nframes; i++) {
-			err = memcpy_from_msg((u8 *)&op->frames[i], msg, CFSIZ);
 
-			if (op->frames[i].can_dlc > 8)
-				err = -EINVAL;
+			cf = op->frames + op->cfsiz * i;
+			err = memcpy_from_msg((u8 *)cf, msg, op->cfsiz);
+
+			if (op->flags & CAN_FD_FRAME) {
+				if (cf->len > 64)
+					err = -EINVAL;
+			} else {
+				if (cf->len > 8)
+					err = -EINVAL;
+			}
 
 			if (err < 0) {
 				if (op->frames != &op->sframe)
@@ -911,7 +955,7 @@
 
 			if (msg_head->flags & TX_CP_CAN_ID) {
 				/* copy can_id into frame */
-				op->frames[i].can_id = msg_head->can_id;
+				cf->can_id = msg_head->can_id;
 			}
 		}
 
@@ -946,8 +990,6 @@
 
 	/* check flags */
 
-	op->flags = msg_head->flags;
-
 	if (op->flags & TX_RESET_MULTI_IDX) {
 		/* start multiple frame transmission with index 0 */
 		op->currframe = 0;
@@ -968,7 +1010,7 @@
 
 	if (op->flags & STARTTIMER) {
 		hrtimer_cancel(&op->timer);
-		/* spec: send can_frame when starting timer */
+		/* spec: send CAN frame when starting timer */
 		op->flags |= TX_ANNOUNCE;
 	}
 
@@ -981,7 +1023,7 @@
 	if (op->flags & STARTTIMER)
 		bcm_tx_start_timer(op);
 
-	return msg_head->nframes * CFSIZ + MHSIZ;
+	return msg_head->nframes * op->cfsiz + MHSIZ;
 }
 
 /*
@@ -1012,12 +1054,12 @@
 		return -EINVAL;
 
 	/* check the given can_id */
-	op = bcm_find_op(&bo->rx_ops, msg_head->can_id, ifindex);
+	op = bcm_find_op(&bo->rx_ops, msg_head, ifindex);
 	if (op) {
 		/* update existing BCM operation */
 
 		/*
-		 * Do we need more space for the can_frames than currently
+		 * Do we need more space for the CAN frames than currently
 		 * allocated? -> This is a _really_ unusual use-case and
 		 * therefore (complexity / locking) it is not supported.
 		 */
@@ -1025,17 +1067,18 @@
 			return -E2BIG;
 
 		if (msg_head->nframes) {
-			/* update can_frames content */
+			/* update CAN frames content */
 			err = memcpy_from_msg((u8 *)op->frames, msg,
-					      msg_head->nframes * CFSIZ);
+					      msg_head->nframes * op->cfsiz);
 			if (err < 0)
 				return err;
 
 			/* clear last_frames to indicate 'nothing received' */
-			memset(op->last_frames, 0, msg_head->nframes * CFSIZ);
+			memset(op->last_frames, 0, msg_head->nframes * op->cfsiz);
 		}
 
 		op->nframes = msg_head->nframes;
+		op->flags = msg_head->flags;
 
 		/* Only an update -> do not call can_rx_register() */
 		do_rx_register = 0;
@@ -1046,20 +1089,22 @@
 		if (!op)
 			return -ENOMEM;
 
-		op->can_id    = msg_head->can_id;
-		op->nframes   = msg_head->nframes;
+		op->can_id = msg_head->can_id;
+		op->nframes = msg_head->nframes;
+		op->cfsiz = CFSIZ(msg_head->flags);
+		op->flags = msg_head->flags;
 
 		if (msg_head->nframes > 1) {
-			/* create array for can_frames and copy the data */
-			op->frames = kmalloc(msg_head->nframes * CFSIZ,
+			/* create array for CAN frames and copy the data */
+			op->frames = kmalloc(msg_head->nframes * op->cfsiz,
 					     GFP_KERNEL);
 			if (!op->frames) {
 				kfree(op);
 				return -ENOMEM;
 			}
 
-			/* create and init array for received can_frames */
-			op->last_frames = kzalloc(msg_head->nframes * CFSIZ,
+			/* create and init array for received CAN frames */
+			op->last_frames = kzalloc(msg_head->nframes * op->cfsiz,
 						  GFP_KERNEL);
 			if (!op->last_frames) {
 				kfree(op->frames);
@@ -1074,7 +1119,7 @@
 
 		if (msg_head->nframes) {
 			err = memcpy_from_msg((u8 *)op->frames, msg,
-					      msg_head->nframes * CFSIZ);
+					      msg_head->nframes * op->cfsiz);
 			if (err < 0) {
 				if (op->frames != &op->sframe)
 					kfree(op->frames);
@@ -1116,7 +1161,6 @@
 	} /* if ((op = bcm_find_op(&bo->rx_ops, msg_head->can_id, ifindex))) */
 
 	/* check flags */
-	op->flags = msg_head->flags;
 
 	if (op->flags & RX_RTR_FRAME) {
 
@@ -1188,13 +1232,14 @@
 		}
 	}
 
-	return msg_head->nframes * CFSIZ + MHSIZ;
+	return msg_head->nframes * op->cfsiz + MHSIZ;
 }
 
 /*
  * bcm_tx_send - send a single CAN frame to the CAN interface (for bcm_sendmsg)
  */
-static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk)
+static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk,
+		       int cfsiz)
 {
 	struct sk_buff *skb;
 	struct net_device *dev;
@@ -1204,13 +1249,13 @@
 	if (!ifindex)
 		return -ENODEV;
 
-	skb = alloc_skb(CFSIZ + sizeof(struct can_skb_priv), GFP_KERNEL);
+	skb = alloc_skb(cfsiz + sizeof(struct can_skb_priv), GFP_KERNEL);
 	if (!skb)
 		return -ENOMEM;
 
 	can_skb_reserve(skb);
 
-	err = memcpy_from_msg(skb_put(skb, CFSIZ), msg, CFSIZ);
+	err = memcpy_from_msg(skb_put(skb, cfsiz), msg, cfsiz);
 	if (err < 0) {
 		kfree_skb(skb);
 		return err;
@@ -1232,7 +1277,7 @@
 	if (err)
 		return err;
 
-	return CFSIZ + MHSIZ;
+	return cfsiz + MHSIZ;
 }
 
 /*
@@ -1244,13 +1289,23 @@
 	struct bcm_sock *bo = bcm_sk(sk);
 	int ifindex = bo->ifindex; /* default ifindex for this bcm_op */
 	struct bcm_msg_head msg_head;
+	int cfsiz;
 	int ret; /* read bytes or error codes as return value */
 
 	if (!bo->bound)
 		return -ENOTCONN;
 
 	/* check for valid message length from userspace */
-	if (size < MHSIZ || (size - MHSIZ) % CFSIZ)
+	if (size < MHSIZ)
+		return -EINVAL;
+
+	/* read message head information */
+	ret = memcpy_from_msg((u8 *)&msg_head, msg, MHSIZ);
+	if (ret < 0)
+		return ret;
+
+	cfsiz = CFSIZ(msg_head.flags);
+	if ((size - MHSIZ) % cfsiz)
 		return -EINVAL;
 
 	/* check for alternative ifindex for this bcm_op */
@@ -1284,12 +1339,6 @@
 		}
 	}
 
-	/* read message head information */
-
-	ret = memcpy_from_msg((u8 *)&msg_head, msg, MHSIZ);
-	if (ret < 0)
-		return ret;
-
 	lock_sock(sk);
 
 	switch (msg_head.opcode) {
@@ -1303,14 +1352,14 @@
 		break;
 
 	case TX_DELETE:
-		if (bcm_delete_tx_op(&bo->tx_ops, msg_head.can_id, ifindex))
+		if (bcm_delete_tx_op(&bo->tx_ops, &msg_head, ifindex))
 			ret = MHSIZ;
 		else
 			ret = -EINVAL;
 		break;
 
 	case RX_DELETE:
-		if (bcm_delete_rx_op(&bo->rx_ops, msg_head.can_id, ifindex))
+		if (bcm_delete_rx_op(&bo->rx_ops, &msg_head, ifindex))
 			ret = MHSIZ;
 		else
 			ret = -EINVAL;
@@ -1329,11 +1378,11 @@
 		break;
 
 	case TX_SEND:
-		/* we need exactly one can_frame behind the msg head */
-		if ((msg_head.nframes != 1) || (size != CFSIZ + MHSIZ))
+		/* we need exactly one CAN frame behind the msg head */
+		if ((msg_head.nframes != 1) || (size != cfsiz + MHSIZ))
 			ret = -EINVAL;
 		else
-			ret = bcm_tx_send(msg, ifindex, sk);
+			ret = bcm_tx_send(msg, ifindex, sk, cfsiz);
 		break;
 
 	default:
diff --git a/net/can/proc.c b/net/can/proc.c
index 1a19b98..85ef7bb 100644
--- a/net/can/proc.c
+++ b/net/can/proc.c
@@ -517,8 +517,7 @@
 	can_dir = proc_mkdir("can", init_net.proc_net);
 
 	if (!can_dir) {
-		printk(KERN_INFO "can: failed to create /proc/net/can . "
-		       "CONFIG_PROC_FS missing?\n");
+		pr_info("can: failed to create /proc/net/can.\n");
 		return;
 	}
 
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 0160d7d..8946959 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -1276,9 +1276,9 @@
 				    const struct ceph_osd_request_target *t,
 				    struct ceph_pg_pool_info *pi)
 {
-	bool pauserd = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSERD);
-	bool pausewr = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSEWR) ||
-		       ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL) ||
+	bool pauserd = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD);
+	bool pausewr = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR) ||
+		       ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) ||
 		       __pool_full(pi);
 
 	WARN_ON(pi->id != t->base_oloc.pool);
@@ -1303,8 +1303,7 @@
 	bool force_resend = false;
 	bool need_check_tiering = false;
 	bool need_resend = false;
-	bool sort_bitwise = ceph_osdmap_flag(osdc->osdmap,
-					     CEPH_OSDMAP_SORTBITWISE);
+	bool sort_bitwise = ceph_osdmap_flag(osdc, CEPH_OSDMAP_SORTBITWISE);
 	enum calc_target_result ct_res;
 	int ret;
 
@@ -1540,9 +1539,9 @@
 	 */
 	msg->hdr.data_off = cpu_to_le16(req->r_data_offset);
 
-	dout("%s req %p oid %*pE oid_len %d front %zu data %u\n", __func__,
-	     req, req->r_t.target_oid.name_len, req->r_t.target_oid.name,
-	     req->r_t.target_oid.name_len, msg->front.iov_len, data_len);
+	dout("%s req %p oid %s oid_len %d front %zu data %u\n", __func__,
+	     req, req->r_t.target_oid.name, req->r_t.target_oid.name_len,
+	     msg->front.iov_len, data_len);
 }
 
 /*
@@ -1590,9 +1589,9 @@
 	verify_osdc_locked(osdc);
 	WARN_ON(!osdc->osdmap->epoch);
 
-	if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL) ||
-	    ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSERD) ||
-	    ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSEWR)) {
+	if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) ||
+	    ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD) ||
+	    ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR)) {
 		dout("%s osdc %p continuous\n", __func__, osdc);
 		continuous = true;
 	} else {
@@ -1629,19 +1628,19 @@
 	}
 
 	if ((req->r_flags & CEPH_OSD_FLAG_WRITE) &&
-	    ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSEWR)) {
+	    ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR)) {
 		dout("req %p pausewr\n", req);
 		req->r_t.paused = true;
 		maybe_request_map(osdc);
 	} else if ((req->r_flags & CEPH_OSD_FLAG_READ) &&
-		   ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSERD)) {
+		   ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD)) {
 		dout("req %p pauserd\n", req);
 		req->r_t.paused = true;
 		maybe_request_map(osdc);
 	} else if ((req->r_flags & CEPH_OSD_FLAG_WRITE) &&
 		   !(req->r_flags & (CEPH_OSD_FLAG_FULL_TRY |
 				     CEPH_OSD_FLAG_FULL_FORCE)) &&
-		   (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL) ||
+		   (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) ||
 		    pool_full(osdc, req->r_t.base_oloc.pool))) {
 		dout("req %p full/pool_full\n", req);
 		pr_warn_ratelimited("FULL or reached pool quota\n");
@@ -2280,7 +2279,7 @@
 	struct ceph_osd_request *req = lreq->ping_req;
 	struct ceph_osd_req_op *op = &req->r_ops[0];
 
-	if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSERD)) {
+	if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD)) {
 		dout("%s PAUSERD\n", __func__);
 		return;
 	}
@@ -2893,6 +2892,9 @@
 			dout("req %p tid %llu cb\n", req, req->r_tid);
 			__complete_request(req);
 		}
+		if (m.flags & CEPH_OSD_FLAG_ONDISK)
+			complete_all(&req->r_safe_completion);
+		ceph_osdc_put_request(req);
 	} else {
 		if (req->r_unsafe_callback) {
 			dout("req %p tid %llu unsafe-cb\n", req, req->r_tid);
@@ -2901,10 +2903,7 @@
 			WARN_ON(1);
 		}
 	}
-	if (m.flags & CEPH_OSD_FLAG_ONDISK)
-		complete_all(&req->r_safe_completion);
 
-	ceph_osdc_put_request(req);
 	return;
 
 fail_request:
@@ -3050,7 +3049,7 @@
 	bool skipped_map = false;
 	bool was_full;
 
-	was_full = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL);
+	was_full = ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL);
 	set_pool_was_full(osdc);
 
 	if (incremental)
@@ -3088,7 +3087,7 @@
 		osdc->osdmap = newmap;
 	}
 
-	was_full &= !ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL);
+	was_full &= !ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL);
 	scan_requests(&osdc->homeless_osd, skipped_map, was_full, true,
 		      need_resend, need_resend_linger);
 
@@ -3174,9 +3173,9 @@
 	if (ceph_check_fsid(osdc->client, &fsid) < 0)
 		goto bad;
 
-	was_pauserd = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSERD);
-	was_pausewr = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSEWR) ||
-		      ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL) ||
+	was_pauserd = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD);
+	was_pausewr = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR) ||
+		      ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) ||
 		      have_pool_full(osdc);
 
 	/* incremental maps */
@@ -3238,9 +3237,9 @@
 	 * we find out when we are no longer full and stop returning
 	 * ENOSPC.
 	 */
-	pauserd = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSERD);
-	pausewr = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSEWR) ||
-		  ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL) ||
+	pauserd = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD);
+	pausewr = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR) ||
+		  ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) ||
 		  have_pool_full(osdc);
 	if (was_pauserd || was_pausewr || pauserd || pausewr)
 		maybe_request_map(osdc);
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index cde52e9..03062bb 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -1778,8 +1778,8 @@
 	raw_pgid->seed = ceph_str_hash(pi->object_hash, oid->name,
 				       oid->name_len);
 
-	dout("%s %*pE -> raw_pgid %llu.%x\n", __func__, oid->name_len,
-	     oid->name, raw_pgid->pool, raw_pgid->seed);
+	dout("%s %s -> raw_pgid %llu.%x\n", __func__, oid->name,
+	     raw_pgid->pool, raw_pgid->seed);
 	return 0;
 }
 EXPORT_SYMBOL(ceph_object_locator_to_pg);
diff --git a/net/compat.c b/net/compat.c
index 5cfd26a..1cd2ec0 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -309,8 +309,8 @@
 	__scm_destroy(scm);
 }
 
-static int do_set_attach_filter(struct socket *sock, int level, int optname,
-				char __user *optval, unsigned int optlen)
+/* allocate a 64-bit sock_fprog on the user stack for duration of syscall. */
+struct sock_fprog __user *get_compat_bpf_fprog(char __user *optval)
 {
 	struct compat_sock_fprog __user *fprog32 = (struct compat_sock_fprog __user *)optval;
 	struct sock_fprog __user *kfprog = compat_alloc_user_space(sizeof(struct sock_fprog));
@@ -323,6 +323,19 @@
 	    __get_user(ptr, &fprog32->filter) ||
 	    __put_user(len, &kfprog->len) ||
 	    __put_user(compat_ptr(ptr), &kfprog->filter))
+		return NULL;
+
+	return kfprog;
+}
+EXPORT_SYMBOL_GPL(get_compat_bpf_fprog);
+
+static int do_set_attach_filter(struct socket *sock, int level, int optname,
+				char __user *optval, unsigned int optlen)
+{
+	struct sock_fprog __user *kfprog;
+
+	kfprog = get_compat_bpf_fprog(optval);
+	if (!kfprog)
 		return -EFAULT;
 
 	return sock_setsockopt(sock, level, optname, (char __user *)kfprog,
@@ -354,7 +367,8 @@
 static int compat_sock_setsockopt(struct socket *sock, int level, int optname,
 				char __user *optval, unsigned int optlen)
 {
-	if (optname == SO_ATTACH_FILTER)
+	if (optname == SO_ATTACH_FILTER ||
+	    optname == SO_ATTACH_REUSEPORT_CBPF)
 		return do_set_attach_filter(sock, level, optname,
 					    optval, optlen);
 	if (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO)
diff --git a/net/core/dev.c b/net/core/dev.c
index 904ff43..d40593b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -139,6 +139,7 @@
 #include <linux/hrtimer.h>
 #include <linux/netfilter_ingress.h>
 #include <linux/sctp.h>
+#include <linux/crash_dump.h>
 
 #include "net-sysfs.h"
 
@@ -2249,11 +2250,12 @@
  */
 int netif_get_num_default_rss_queues(void)
 {
-	return min_t(int, DEFAULT_MAX_NUM_RSS_QUEUES, num_online_cpus());
+	return is_kdump_kernel() ?
+		1 : min_t(int, DEFAULT_MAX_NUM_RSS_QUEUES, num_online_cpus());
 }
 EXPORT_SYMBOL(netif_get_num_default_rss_queues);
 
-static inline void __netif_reschedule(struct Qdisc *q)
+static void __netif_reschedule(struct Qdisc *q)
 {
 	struct softnet_data *sd;
 	unsigned long flags;
@@ -2420,7 +2422,7 @@
 
 static void skb_warn_bad_offload(const struct sk_buff *skb)
 {
-	static const netdev_features_t null_features = 0;
+	static const netdev_features_t null_features;
 	struct net_device *dev = skb->dev;
 	const char *name = "";
 
@@ -3075,7 +3077,7 @@
 	/*
 	 * Heuristic to force contended enqueues to serialize on a
 	 * separate lock before trying to get qdisc main lock.
-	 * This permits __QDISC___STATE_RUNNING owner to get the lock more
+	 * This permits qdisc->running owner to get the lock more
 	 * often and dequeue packets faster.
 	 */
 	contended = qdisc_is_running(q);
@@ -3142,8 +3144,6 @@
 DEFINE_PER_CPU(int, xmit_recursion);
 EXPORT_SYMBOL(xmit_recursion);
 
-#define RECURSION_LIMIT 10
-
 /**
  *	dev_loopback_xmit - loop back @skb
  *	@net: network namespace this loopback is happening in
@@ -3386,8 +3386,8 @@
 		int cpu = smp_processor_id(); /* ok because BHs are off */
 
 		if (txq->xmit_lock_owner != cpu) {
-
-			if (__this_cpu_read(xmit_recursion) > RECURSION_LIMIT)
+			if (unlikely(__this_cpu_read(xmit_recursion) >
+				     XMIT_RECURSION_LIMIT))
 				goto recursion_alert;
 
 			skb = validate_xmit_skb(skb, dev);
@@ -3898,22 +3898,14 @@
 			head = head->next_sched;
 
 			root_lock = qdisc_lock(q);
-			if (spin_trylock(root_lock)) {
-				smp_mb__before_atomic();
-				clear_bit(__QDISC_STATE_SCHED,
-					  &q->state);
-				qdisc_run(q);
-				spin_unlock(root_lock);
-			} else {
-				if (!test_bit(__QDISC_STATE_DEACTIVATED,
-					      &q->state)) {
-					__netif_reschedule(q);
-				} else {
-					smp_mb__before_atomic();
-					clear_bit(__QDISC_STATE_SCHED,
-						  &q->state);
-				}
-			}
+			spin_lock(root_lock);
+			/* We need to make sure head->next_sched is read
+			 * before clearing __QDISC_STATE_SCHED
+			 */
+			smp_mb__before_atomic();
+			clear_bit(__QDISC_STATE_SCHED, &q->state);
+			qdisc_run(q);
+			spin_unlock(root_lock);
 		}
 	}
 }
@@ -5919,7 +5911,7 @@
 	struct net *net = dev_net(dev);
 
 	list_for_each_entry(iter, &dev->adj_list.upper, list) {
-		if (!net_eq(net,dev_net(iter->dev)))
+		if (!net_eq(net, dev_net(iter->dev)))
 			continue;
 		netdev_adjacent_sysfs_add(iter->dev, dev,
 					  &iter->dev->adj_list.lower);
@@ -5928,7 +5920,7 @@
 	}
 
 	list_for_each_entry(iter, &dev->adj_list.lower, list) {
-		if (!net_eq(net,dev_net(iter->dev)))
+		if (!net_eq(net, dev_net(iter->dev)))
 			continue;
 		netdev_adjacent_sysfs_add(iter->dev, dev,
 					  &iter->dev->adj_list.upper);
@@ -5944,7 +5936,7 @@
 	struct net *net = dev_net(dev);
 
 	list_for_each_entry(iter, &dev->adj_list.upper, list) {
-		if (!net_eq(net,dev_net(iter->dev)))
+		if (!net_eq(net, dev_net(iter->dev)))
 			continue;
 		netdev_adjacent_sysfs_del(iter->dev, dev->name,
 					  &iter->dev->adj_list.lower);
@@ -5953,7 +5945,7 @@
 	}
 
 	list_for_each_entry(iter, &dev->adj_list.lower, list) {
-		if (!net_eq(net,dev_net(iter->dev)))
+		if (!net_eq(net, dev_net(iter->dev)))
 			continue;
 		netdev_adjacent_sysfs_del(iter->dev, dev->name,
 					  &iter->dev->adj_list.upper);
@@ -5969,7 +5961,7 @@
 	struct net *net = dev_net(dev);
 
 	list_for_each_entry(iter, &dev->adj_list.upper, list) {
-		if (!net_eq(net,dev_net(iter->dev)))
+		if (!net_eq(net, dev_net(iter->dev)))
 			continue;
 		netdev_adjacent_sysfs_del(iter->dev, oldname,
 					  &iter->dev->adj_list.lower);
@@ -5978,7 +5970,7 @@
 	}
 
 	list_for_each_entry(iter, &dev->adj_list.lower, list) {
-		if (!net_eq(net,dev_net(iter->dev)))
+		if (!net_eq(net, dev_net(iter->dev)))
 			continue;
 		netdev_adjacent_sysfs_del(iter->dev, oldname,
 					  &iter->dev->adj_list.upper);
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 840aceb..98298b1 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -173,7 +173,8 @@
 EXPORT_SYMBOL_GPL(fib_rules_unregister);
 
 static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
-			  struct flowi *fl, int flags)
+			  struct flowi *fl, int flags,
+			  struct fib_lookup_arg *arg)
 {
 	int ret = 0;
 
@@ -189,6 +190,9 @@
 	if (rule->tun_id && (rule->tun_id != fl->flowi_tun_key.tun_id))
 		goto out;
 
+	if (rule->l3mdev && !l3mdev_fib_rule_match(rule->fr_net, fl, arg))
+		goto out;
+
 	ret = ops->match(rule, fl, flags);
 out:
 	return (rule->flags & FIB_RULE_INVERT) ? !ret : ret;
@@ -204,7 +208,7 @@
 
 	list_for_each_entry_rcu(rule, &ops->rules_list, list) {
 jumped:
-		if (!fib_rule_match(rule, ops, fl, flags))
+		if (!fib_rule_match(rule, ops, fl, flags, arg))
 			continue;
 
 		if (rule->action == FR_ACT_GOTO) {
@@ -265,7 +269,7 @@
 	return err;
 }
 
-static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh)
+int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct fib_rule_hdr *frh = nlmsg_data(nlh);
@@ -336,6 +340,14 @@
 	if (tb[FRA_TUN_ID])
 		rule->tun_id = nla_get_be64(tb[FRA_TUN_ID]);
 
+	if (tb[FRA_L3MDEV]) {
+#ifdef CONFIG_NET_L3_MASTER_DEV
+		rule->l3mdev = nla_get_u8(tb[FRA_L3MDEV]);
+		if (rule->l3mdev != 1)
+#endif
+			goto errout_free;
+	}
+
 	rule->action = frh->action;
 	rule->flags = frh->flags;
 	rule->table = frh_get_table(frh, tb);
@@ -371,6 +383,9 @@
 	} else if (rule->action == FR_ACT_GOTO)
 		goto errout_free;
 
+	if (rule->l3mdev && rule->table)
+		goto errout_free;
+
 	err = ops->configure(rule, skb, frh, tb);
 	if (err < 0)
 		goto errout_free;
@@ -424,8 +439,9 @@
 	rules_ops_put(ops);
 	return err;
 }
+EXPORT_SYMBOL_GPL(fib_nl_newrule);
 
-static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh)
+int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct fib_rule_hdr *frh = nlmsg_data(nlh);
@@ -483,6 +499,10 @@
 		    (rule->tun_id != nla_get_be64(tb[FRA_TUN_ID])))
 			continue;
 
+		if (tb[FRA_L3MDEV] &&
+		    (rule->l3mdev != nla_get_u8(tb[FRA_L3MDEV])))
+			continue;
+
 		if (!ops->compare(rule, frh, tb))
 			continue;
 
@@ -536,6 +556,7 @@
 	rules_ops_put(ops);
 	return err;
 }
+EXPORT_SYMBOL_GPL(fib_nl_delrule);
 
 static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops,
 					 struct fib_rule *rule)
@@ -607,7 +628,9 @@
 	    (rule->target &&
 	     nla_put_u32(skb, FRA_GOTO, rule->target)) ||
 	    (rule->tun_id &&
-	     nla_put_be64(skb, FRA_TUN_ID, rule->tun_id, FRA_PAD)))
+	     nla_put_be64(skb, FRA_TUN_ID, rule->tun_id, FRA_PAD)) ||
+	    (rule->l3mdev &&
+	     nla_put_u8(skb, FRA_L3MDEV, rule->l3mdev)))
 		goto nla_put_failure;
 
 	if (rule->suppress_ifgroup != -1) {
diff --git a/net/core/filter.c b/net/core/filter.c
index 68adb5f..df6860c 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -748,6 +748,17 @@
 	return codes[code_to_probe];
 }
 
+static bool bpf_check_basics_ok(const struct sock_filter *filter,
+				unsigned int flen)
+{
+	if (filter == NULL)
+		return false;
+	if (flen == 0 || flen > BPF_MAXINSNS)
+		return false;
+
+	return true;
+}
+
 /**
  *	bpf_check_classic - verify socket filter code
  *	@filter: filter to verify
@@ -768,9 +779,6 @@
 	bool anc_found;
 	int pc;
 
-	if (flen == 0 || flen > BPF_MAXINSNS)
-		return -EINVAL;
-
 	/* Check the filter code now */
 	for (pc = 0; pc < flen; pc++) {
 		const struct sock_filter *ftest = &filter[pc];
@@ -1065,7 +1073,7 @@
 	struct bpf_prog *fp;
 
 	/* Make sure new filter is there and in the right amounts. */
-	if (fprog->filter == NULL)
+	if (!bpf_check_basics_ok(fprog->filter, fprog->len))
 		return -EINVAL;
 
 	fp = bpf_prog_alloc(bpf_prog_size(fprog->len), 0);
@@ -1112,7 +1120,7 @@
 	int err;
 
 	/* Make sure new filter is there and in the right amounts. */
-	if (fprog->filter == NULL)
+	if (!bpf_check_basics_ok(fprog->filter, fprog->len))
 		return -EINVAL;
 
 	fp = bpf_prog_alloc(bpf_prog_size(fprog->len), 0);
@@ -1207,7 +1215,6 @@
 struct bpf_prog *__get_filter(struct sock_fprog *fprog, struct sock *sk)
 {
 	unsigned int fsize = bpf_classic_proglen(fprog);
-	unsigned int bpf_fsize = bpf_prog_size(fprog->len);
 	struct bpf_prog *prog;
 	int err;
 
@@ -1215,10 +1222,10 @@
 		return ERR_PTR(-EPERM);
 
 	/* Make sure new filter is there and in the right amounts. */
-	if (fprog->filter == NULL)
+	if (!bpf_check_basics_ok(fprog->filter, fprog->len))
 		return ERR_PTR(-EINVAL);
 
-	prog = bpf_prog_alloc(bpf_fsize, 0);
+	prog = bpf_prog_alloc(bpf_prog_size(fprog->len), 0);
 	if (!prog)
 		return ERR_PTR(-ENOMEM);
 
@@ -1603,9 +1610,36 @@
 	.arg5_type	= ARG_ANYTHING,
 };
 
+static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb)
+{
+	if (skb_at_tc_ingress(skb))
+		skb_postpush_rcsum(skb, skb_mac_header(skb), skb->mac_len);
+
+	return dev_forward_skb(dev, skb);
+}
+
+static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb)
+{
+	int ret;
+
+	if (unlikely(__this_cpu_read(xmit_recursion) > XMIT_RECURSION_LIMIT)) {
+		net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n");
+		kfree_skb(skb);
+		return -ENETDOWN;
+	}
+
+	skb->dev = dev;
+
+	__this_cpu_inc(xmit_recursion);
+	ret = dev_queue_xmit(skb);
+	__this_cpu_dec(xmit_recursion);
+
+	return ret;
+}
+
 static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5)
 {
-	struct sk_buff *skb = (struct sk_buff *) (long) r1, *skb2;
+	struct sk_buff *skb = (struct sk_buff *) (long) r1;
 	struct net_device *dev;
 
 	if (unlikely(flags & ~(BPF_F_INGRESS)))
@@ -1615,19 +1649,12 @@
 	if (unlikely(!dev))
 		return -EINVAL;
 
-	skb2 = skb_clone(skb, GFP_ATOMIC);
-	if (unlikely(!skb2))
+	skb = skb_clone(skb, GFP_ATOMIC);
+	if (unlikely(!skb))
 		return -ENOMEM;
 
-	if (flags & BPF_F_INGRESS) {
-		if (skb_at_tc_ingress(skb2))
-			skb_postpush_rcsum(skb2, skb_mac_header(skb2),
-					   skb2->mac_len);
-		return dev_forward_skb(dev, skb2);
-	}
-
-	skb2->dev = dev;
-	return dev_queue_xmit(skb2);
+	return flags & BPF_F_INGRESS ?
+	       __bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb);
 }
 
 static const struct bpf_func_proto bpf_clone_redirect_proto = {
@@ -1671,15 +1698,8 @@
 		return -EINVAL;
 	}
 
-	if (ri->flags & BPF_F_INGRESS) {
-		if (skb_at_tc_ingress(skb))
-			skb_postpush_rcsum(skb, skb_mac_header(skb),
-					   skb->mac_len);
-		return dev_forward_skb(dev, skb);
-	}
-
-	skb->dev = dev;
-	return dev_queue_xmit(skb);
+	return ri->flags & BPF_F_INGRESS ?
+	       __bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb);
 }
 
 static const struct bpf_func_proto bpf_redirect_proto = {
diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c
index 4573d81..cad8e79 100644
--- a/net/core/gen_estimator.c
+++ b/net/core/gen_estimator.c
@@ -84,6 +84,7 @@
 	struct gnet_stats_basic_packed	*bstats;
 	struct gnet_stats_rate_est64	*rate_est;
 	spinlock_t		*stats_lock;
+	seqcount_t		*running;
 	int			ewma_log;
 	u32			last_packets;
 	unsigned long		avpps;
@@ -121,26 +122,28 @@
 		unsigned long rate;
 		u64 brate;
 
-		spin_lock(e->stats_lock);
+		if (e->stats_lock)
+			spin_lock(e->stats_lock);
 		read_lock(&est_lock);
 		if (e->bstats == NULL)
 			goto skip;
 
-		__gnet_stats_copy_basic(&b, e->cpu_bstats, e->bstats);
+		__gnet_stats_copy_basic(e->running, &b, e->cpu_bstats, e->bstats);
 
 		brate = (b.bytes - e->last_bytes)<<(7 - idx);
 		e->last_bytes = b.bytes;
 		e->avbps += (brate >> e->ewma_log) - (e->avbps >> e->ewma_log);
-		e->rate_est->bps = (e->avbps+0xF)>>5;
+		WRITE_ONCE(e->rate_est->bps, (e->avbps + 0xF) >> 5);
 
 		rate = b.packets - e->last_packets;
 		rate <<= (7 - idx);
 		e->last_packets = b.packets;
 		e->avpps += (rate >> e->ewma_log) - (e->avpps >> e->ewma_log);
-		e->rate_est->pps = (e->avpps + 0xF) >> 5;
+		WRITE_ONCE(e->rate_est->pps, (e->avpps + 0xF) >> 5);
 skip:
 		read_unlock(&est_lock);
-		spin_unlock(e->stats_lock);
+		if (e->stats_lock)
+			spin_unlock(e->stats_lock);
 	}
 
 	if (!list_empty(&elist[idx].list))
@@ -194,6 +197,7 @@
  * @cpu_bstats: bstats per cpu
  * @rate_est: rate estimator statistics
  * @stats_lock: statistics lock
+ * @running: qdisc running seqcount
  * @opt: rate estimator configuration TLV
  *
  * Creates a new rate estimator with &bstats as source and &rate_est
@@ -209,6 +213,7 @@
 		      struct gnet_stats_basic_cpu __percpu *cpu_bstats,
 		      struct gnet_stats_rate_est64 *rate_est,
 		      spinlock_t *stats_lock,
+		      seqcount_t *running,
 		      struct nlattr *opt)
 {
 	struct gen_estimator *est;
@@ -226,12 +231,13 @@
 	if (est == NULL)
 		return -ENOBUFS;
 
-	__gnet_stats_copy_basic(&b, cpu_bstats, bstats);
+	__gnet_stats_copy_basic(running, &b, cpu_bstats, bstats);
 
 	idx = parm->interval + 2;
 	est->bstats = bstats;
 	est->rate_est = rate_est;
 	est->stats_lock = stats_lock;
+	est->running  = running;
 	est->ewma_log = parm->ewma_log;
 	est->last_bytes = b.bytes;
 	est->avbps = rate_est->bps<<5;
@@ -291,6 +297,7 @@
  * @cpu_bstats: bstats per cpu
  * @rate_est: rate estimator statistics
  * @stats_lock: statistics lock
+ * @running: qdisc running seqcount (might be NULL)
  * @opt: rate estimator configuration TLV
  *
  * Replaces the configuration of a rate estimator by calling
@@ -301,10 +308,11 @@
 int gen_replace_estimator(struct gnet_stats_basic_packed *bstats,
 			  struct gnet_stats_basic_cpu __percpu *cpu_bstats,
 			  struct gnet_stats_rate_est64 *rate_est,
-			  spinlock_t *stats_lock, struct nlattr *opt)
+			  spinlock_t *stats_lock,
+			  seqcount_t *running, struct nlattr *opt)
 {
 	gen_kill_estimator(bstats, rate_est);
-	return gen_new_estimator(bstats, cpu_bstats, rate_est, stats_lock, opt);
+	return gen_new_estimator(bstats, cpu_bstats, rate_est, stats_lock, running, opt);
 }
 EXPORT_SYMBOL(gen_replace_estimator);
 
diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c
index f96ee8b..508e051 100644
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -32,10 +32,11 @@
 	return 0;
 
 nla_put_failure:
+	if (d->lock)
+		spin_unlock_bh(d->lock);
 	kfree(d->xstats);
 	d->xstats = NULL;
 	d->xstats_len = 0;
-	spin_unlock_bh(d->lock);
 	return -1;
 }
 
@@ -47,6 +48,7 @@
  * @xstats_type: TLV type for backward compatibility xstats TLV
  * @lock: statistics lock
  * @d: dumping handle
+ * @padattr: padding attribute
  *
  * Initializes the dumping handle, grabs the statistic lock and appends
  * an empty TLV header to the socket buffer for use a container for all
@@ -65,15 +67,16 @@
 {
 	memset(d, 0, sizeof(*d));
 
-	spin_lock_bh(lock);
-	d->lock = lock;
 	if (type)
 		d->tail = (struct nlattr *)skb_tail_pointer(skb);
 	d->skb = skb;
 	d->compat_tc_stats = tc_stats_type;
 	d->compat_xstats = xstats_type;
 	d->padattr = padattr;
-
+	if (lock) {
+		d->lock = lock;
+		spin_lock_bh(lock);
+	}
 	if (d->tail)
 		return gnet_stats_copy(d, type, NULL, 0, padattr);
 
@@ -87,6 +90,7 @@
  * @type: TLV type for top level statistic TLV
  * @lock: statistics lock
  * @d: dumping handle
+ * @padattr: padding attribute
  *
  * Initializes the dumping handle, grabs the statistic lock and appends
  * an empty TLV header to the socket buffer for use a container for all
@@ -126,21 +130,29 @@
 }
 
 void
-__gnet_stats_copy_basic(struct gnet_stats_basic_packed *bstats,
+__gnet_stats_copy_basic(const seqcount_t *running,
+			struct gnet_stats_basic_packed *bstats,
 			struct gnet_stats_basic_cpu __percpu *cpu,
 			struct gnet_stats_basic_packed *b)
 {
+	unsigned int seq;
+
 	if (cpu) {
 		__gnet_stats_copy_basic_cpu(bstats, cpu);
-	} else {
+		return;
+	}
+	do {
+		if (running)
+			seq = read_seqcount_begin(running);
 		bstats->bytes = b->bytes;
 		bstats->packets = b->packets;
-	}
+	} while (running && read_seqcount_retry(running, seq));
 }
 EXPORT_SYMBOL(__gnet_stats_copy_basic);
 
 /**
  * gnet_stats_copy_basic - copy basic statistics into statistic TLV
+ * @running: seqcount_t pointer
  * @d: dumping handle
  * @cpu: copy statistic per cpu
  * @b: basic statistics
@@ -152,13 +164,14 @@
  * if the room in the socket buffer was not sufficient.
  */
 int
-gnet_stats_copy_basic(struct gnet_dump *d,
+gnet_stats_copy_basic(const seqcount_t *running,
+		      struct gnet_dump *d,
 		      struct gnet_stats_basic_cpu __percpu *cpu,
 		      struct gnet_stats_basic_packed *b)
 {
 	struct gnet_stats_basic_packed bstats = {0};
 
-	__gnet_stats_copy_basic(&bstats, cpu, b);
+	__gnet_stats_copy_basic(running, &bstats, cpu, b);
 
 	if (d->compat_tc_stats) {
 		d->tc_stats.bytes = bstats.bytes;
@@ -328,8 +341,9 @@
 	return 0;
 
 err_out:
+	if (d->lock)
+		spin_unlock_bh(d->lock);
 	d->xstats_len = 0;
-	spin_unlock_bh(d->lock);
 	return -1;
 }
 EXPORT_SYMBOL(gnet_stats_copy_app);
@@ -363,10 +377,11 @@
 			return -1;
 	}
 
+	if (d->lock)
+		spin_unlock_bh(d->lock);
 	kfree(d->xstats);
 	d->xstats = NULL;
 	d->xstats_len = 0;
-	spin_unlock_bh(d->lock);
 	return 0;
 }
 EXPORT_SYMBOL(gnet_stats_finish_copy);
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 2b3f76f..7a0b616 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -24,6 +24,7 @@
 #include <linux/jiffies.h>
 #include <linux/pm_runtime.h>
 #include <linux/of.h>
+#include <linux/of_net.h>
 
 #include "net-sysfs.h"
 
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 8b02df0..f74ab9c 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -3463,7 +3463,6 @@
 		break;
 	case NET_XMIT_DROP:
 	case NET_XMIT_CN:
-	case NET_XMIT_POLICED:
 		/* skb has been consumed */
 		pkt_dev->errors++;
 		break;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index d69c464..eb49ca2 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -71,9 +71,31 @@
 }
 EXPORT_SYMBOL(rtnl_lock);
 
+static struct sk_buff *defer_kfree_skb_list;
+void rtnl_kfree_skbs(struct sk_buff *head, struct sk_buff *tail)
+{
+	if (head && tail) {
+		tail->next = defer_kfree_skb_list;
+		defer_kfree_skb_list = head;
+	}
+}
+EXPORT_SYMBOL(rtnl_kfree_skbs);
+
 void __rtnl_unlock(void)
 {
+	struct sk_buff *head = defer_kfree_skb_list;
+
+	defer_kfree_skb_list = NULL;
+
 	mutex_unlock(&rtnl_mutex);
+
+	while (head) {
+		struct sk_buff *next = head->next;
+
+		kfree_skb(head);
+		cond_resched();
+		head = next;
+	}
 }
 
 void rtnl_unlock(void)
diff --git a/net/dsa/Makefile b/net/dsa/Makefile
index da06ed1..8af4ded 100644
--- a/net/dsa/Makefile
+++ b/net/dsa/Makefile
@@ -1,6 +1,6 @@
 # the core
 obj-$(CONFIG_NET_DSA) += dsa_core.o
-dsa_core-y += dsa.o slave.o
+dsa_core-y += dsa.o slave.o dsa2.o
 
 # tagging formats
 dsa_core-$(CONFIG_NET_DSA_TAG_BRCM) += tag_brcm.o
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index eff5dfc..766d2a5 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -29,6 +29,33 @@
 
 char dsa_driver_version[] = "0.1";
 
+static struct sk_buff *dsa_slave_notag_xmit(struct sk_buff *skb,
+					    struct net_device *dev)
+{
+	/* Just return the original SKB */
+	return skb;
+}
+
+static const struct dsa_device_ops none_ops = {
+	.xmit	= dsa_slave_notag_xmit,
+	.rcv	= NULL,
+};
+
+const struct dsa_device_ops *dsa_device_ops[DSA_TAG_LAST] = {
+#ifdef CONFIG_NET_DSA_TAG_DSA
+	[DSA_TAG_PROTO_DSA] = &dsa_netdev_ops,
+#endif
+#ifdef CONFIG_NET_DSA_TAG_EDSA
+	[DSA_TAG_PROTO_EDSA] = &edsa_netdev_ops,
+#endif
+#ifdef CONFIG_NET_DSA_TAG_TRAILER
+	[DSA_TAG_PROTO_TRAILER] = &trailer_netdev_ops,
+#endif
+#ifdef CONFIG_NET_DSA_TAG_BRCM
+	[DSA_TAG_PROTO_BRCM] = &brcm_netdev_ops,
+#endif
+	[DSA_TAG_PROTO_NONE] = &none_ops,
+};
 
 /* switch driver registration ***********************************************/
 static DEFINE_MUTEX(dsa_switch_drivers_mutex);
@@ -180,41 +207,100 @@
 #endif /* CONFIG_NET_DSA_HWMON */
 
 /* basic switch operations **************************************************/
-static int dsa_cpu_dsa_setup(struct dsa_switch *ds, struct net_device *master)
+int dsa_cpu_dsa_setup(struct dsa_switch *ds, struct device *dev,
+		      struct device_node *port_dn, int port)
 {
-	struct dsa_chip_data *cd = ds->cd;
-	struct device_node *port_dn;
 	struct phy_device *phydev;
-	int ret, port, mode;
+	int ret, mode;
+
+	if (of_phy_is_fixed_link(port_dn)) {
+		ret = of_phy_register_fixed_link(port_dn);
+		if (ret) {
+			dev_err(dev, "failed to register fixed PHY\n");
+			return ret;
+		}
+		phydev = of_phy_find_device(port_dn);
+
+		mode = of_get_phy_mode(port_dn);
+		if (mode < 0)
+			mode = PHY_INTERFACE_MODE_NA;
+		phydev->interface = mode;
+
+		genphy_config_init(phydev);
+		genphy_read_status(phydev);
+		if (ds->drv->adjust_link)
+			ds->drv->adjust_link(ds, port, phydev);
+	}
+
+	return 0;
+}
+
+static int dsa_cpu_dsa_setups(struct dsa_switch *ds, struct device *dev)
+{
+	struct device_node *port_dn;
+	int ret, port;
 
 	for (port = 0; port < DSA_MAX_PORTS; port++) {
 		if (!(dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)))
 			continue;
 
-		port_dn = cd->port_dn[port];
-		if (of_phy_is_fixed_link(port_dn)) {
-			ret = of_phy_register_fixed_link(port_dn);
-			if (ret) {
-				netdev_err(master,
-					   "failed to register fixed PHY\n");
-				return ret;
-			}
-			phydev = of_phy_find_device(port_dn);
-
-			mode = of_get_phy_mode(port_dn);
-			if (mode < 0)
-				mode = PHY_INTERFACE_MODE_NA;
-			phydev->interface = mode;
-
-			genphy_config_init(phydev);
-			genphy_read_status(phydev);
-			if (ds->drv->adjust_link)
-				ds->drv->adjust_link(ds, port, phydev);
-		}
+		port_dn = ds->ports[port].dn;
+		ret = dsa_cpu_dsa_setup(ds, dev, port_dn, port);
+		if (ret)
+			return ret;
 	}
 	return 0;
 }
 
+const struct dsa_device_ops *dsa_resolve_tag_protocol(int tag_protocol)
+{
+	const struct dsa_device_ops *ops;
+
+	if (tag_protocol >= DSA_TAG_LAST)
+		return ERR_PTR(-EINVAL);
+	ops = dsa_device_ops[tag_protocol];
+
+	if (!ops)
+		return ERR_PTR(-ENOPROTOOPT);
+
+	return ops;
+}
+
+int dsa_cpu_port_ethtool_setup(struct dsa_switch *ds)
+{
+	struct net_device *master;
+	struct ethtool_ops *cpu_ops;
+
+	master = ds->dst->master_netdev;
+	if (ds->master_netdev)
+		master = ds->master_netdev;
+
+	cpu_ops = devm_kzalloc(ds->dev, sizeof(*cpu_ops), GFP_KERNEL);
+	if (!cpu_ops)
+		return -ENOMEM;
+
+	memcpy(&ds->dst->master_ethtool_ops, master->ethtool_ops,
+	       sizeof(struct ethtool_ops));
+	ds->dst->master_orig_ethtool_ops = master->ethtool_ops;
+	memcpy(cpu_ops, &ds->dst->master_ethtool_ops,
+	       sizeof(struct ethtool_ops));
+	dsa_cpu_port_ethtool_init(cpu_ops);
+	master->ethtool_ops = cpu_ops;
+
+	return 0;
+}
+
+void dsa_cpu_port_ethtool_restore(struct dsa_switch *ds)
+{
+	struct net_device *master;
+
+	master = ds->dst->master_netdev;
+	if (ds->master_netdev)
+		master = ds->master_netdev;
+
+	master->ethtool_ops = ds->dst->master_orig_ethtool_ops;
+}
+
 static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent)
 {
 	struct dsa_switch_driver *drv = ds->drv;
@@ -243,6 +329,7 @@
 			}
 			dst->cpu_switch = index;
 			dst->cpu_port = i;
+			ds->cpu_port_mask |= 1 << i;
 		} else if (!strcmp(name, "dsa")) {
 			ds->dsa_port_mask |= 1 << i;
 		} else {
@@ -267,37 +354,17 @@
 	 * switch.
 	 */
 	if (dst->cpu_switch == index) {
-		switch (drv->tag_protocol) {
-#ifdef CONFIG_NET_DSA_TAG_DSA
-		case DSA_TAG_PROTO_DSA:
-			dst->rcv = dsa_netdev_ops.rcv;
-			break;
-#endif
-#ifdef CONFIG_NET_DSA_TAG_EDSA
-		case DSA_TAG_PROTO_EDSA:
-			dst->rcv = edsa_netdev_ops.rcv;
-			break;
-#endif
-#ifdef CONFIG_NET_DSA_TAG_TRAILER
-		case DSA_TAG_PROTO_TRAILER:
-			dst->rcv = trailer_netdev_ops.rcv;
-			break;
-#endif
-#ifdef CONFIG_NET_DSA_TAG_BRCM
-		case DSA_TAG_PROTO_BRCM:
-			dst->rcv = brcm_netdev_ops.rcv;
-			break;
-#endif
-		case DSA_TAG_PROTO_NONE:
-			break;
-		default:
-			ret = -ENOPROTOOPT;
+		dst->tag_ops = dsa_resolve_tag_protocol(drv->tag_protocol);
+		if (IS_ERR(dst->tag_ops)) {
+			ret = PTR_ERR(dst->tag_ops);
 			goto out;
 		}
 
-		dst->tag_protocol = drv->tag_protocol;
+		dst->rcv = dst->tag_ops->rcv;
 	}
 
+	memcpy(ds->rtable, cd->rtable, sizeof(ds->rtable));
+
 	/*
 	 * Do basic register setup.
 	 */
@@ -309,22 +376,25 @@
 	if (ret < 0)
 		goto out;
 
-	ds->slave_mii_bus = devm_mdiobus_alloc(parent);
-	if (ds->slave_mii_bus == NULL) {
-		ret = -ENOMEM;
-		goto out;
+	if (!ds->slave_mii_bus && drv->phy_read) {
+		ds->slave_mii_bus = devm_mdiobus_alloc(parent);
+		if (!ds->slave_mii_bus) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		dsa_slave_mii_bus_init(ds);
+
+		ret = mdiobus_register(ds->slave_mii_bus);
+		if (ret < 0)
+			goto out;
 	}
-	dsa_slave_mii_bus_init(ds);
-
-	ret = mdiobus_register(ds->slave_mii_bus);
-	if (ret < 0)
-		goto out;
-
 
 	/*
 	 * Create network devices for physical switch ports.
 	 */
 	for (i = 0; i < DSA_MAX_PORTS; i++) {
+		ds->ports[i].dn = cd->port_dn[i];
+
 		if (!(ds->enabled_port_mask & (1 << i)))
 			continue;
 
@@ -337,13 +407,17 @@
 	}
 
 	/* Perform configuration of the CPU and DSA ports */
-	ret = dsa_cpu_dsa_setup(ds, dst->master_netdev);
+	ret = dsa_cpu_dsa_setups(ds, parent);
 	if (ret < 0) {
 		netdev_err(dst->master_netdev, "[%d] : can't configure CPU and DSA ports\n",
 			   index);
 		ret = 0;
 	}
 
+	ret = dsa_cpu_port_ethtool_setup(ds);
+	if (ret)
+		return ret;
+
 #ifdef CONFIG_NET_DSA_HWMON
 	/* If the switch provides a temperature sensor,
 	 * register with hardware monitoring subsystem.
@@ -420,11 +494,21 @@
 	return ds;
 }
 
+void dsa_cpu_dsa_destroy(struct device_node *port_dn)
+{
+	struct phy_device *phydev;
+
+	if (of_phy_is_fixed_link(port_dn)) {
+		phydev = of_phy_find_device(port_dn);
+		if (phydev) {
+			phy_device_free(phydev);
+			fixed_phy_unregister(phydev);
+		}
+	}
+}
+
 static void dsa_switch_destroy(struct dsa_switch *ds)
 {
-	struct device_node *port_dn;
-	struct phy_device *phydev;
-	struct dsa_chip_data *cd = ds->cd;
 	int port;
 
 #ifdef CONFIG_NET_DSA_HWMON
@@ -437,26 +521,25 @@
 		if (!(ds->enabled_port_mask & (1 << port)))
 			continue;
 
-		if (!ds->ports[port])
+		if (!ds->ports[port].netdev)
 			continue;
 
-		dsa_slave_destroy(ds->ports[port]);
+		dsa_slave_destroy(ds->ports[port].netdev);
 	}
 
-	/* Remove any fixed link PHYs */
+	/* Disable configuration of the CPU and DSA ports */
 	for (port = 0; port < DSA_MAX_PORTS; port++) {
-		port_dn = cd->port_dn[port];
-		if (of_phy_is_fixed_link(port_dn)) {
-			phydev = of_phy_find_device(port_dn);
-			if (phydev) {
-				phy_device_free(phydev);
-				of_node_put(port_dn);
-				fixed_phy_unregister(phydev);
-			}
-		}
+		if (!(dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)))
+			continue;
+		dsa_cpu_dsa_destroy(ds->ports[port].dn);
+
+		/* Clearing a bit which is not set does no harm */
+		ds->cpu_port_mask |= ~(1 << port);
+		ds->dsa_port_mask |= ~(1 << port);
 	}
 
-	mdiobus_unregister(ds->slave_mii_bus);
+	if (ds->slave_mii_bus && ds->drv->phy_read)
+		mdiobus_unregister(ds->slave_mii_bus);
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -469,7 +552,7 @@
 		if (!dsa_is_port_initialized(ds, i))
 			continue;
 
-		ret = dsa_slave_suspend(ds->ports[i]);
+		ret = dsa_slave_suspend(ds->ports[i].netdev);
 		if (ret)
 			return ret;
 	}
@@ -495,7 +578,7 @@
 		if (!dsa_is_port_initialized(ds, i))
 			continue;
 
-		ret = dsa_slave_resume(ds->ports[i]);
+		ret = dsa_slave_resume(ds->ports[i].netdev);
 		if (ret)
 			return ret;
 	}
@@ -587,17 +670,6 @@
 	if (link_sw_addr >= pd->nr_chips)
 		return -EINVAL;
 
-	/* First time routing table allocation */
-	if (!cd->rtable) {
-		cd->rtable = kmalloc_array(pd->nr_chips, sizeof(s8),
-					   GFP_KERNEL);
-		if (!cd->rtable)
-			return -ENOMEM;
-
-		/* default to no valid uplink/downlink */
-		memset(cd->rtable, -1, pd->nr_chips * sizeof(s8));
-	}
-
 	cd->rtable[link_sw_addr] = port_index;
 
 	return 0;
@@ -639,7 +711,6 @@
 			kfree(pd->chip[i].port_names[port_index]);
 			port_index++;
 		}
-		kfree(pd->chip[i].rtable);
 
 		/* Drop our reference to the MDIO bus device */
 		if (pd->chip[i].host_dev)
@@ -931,6 +1002,8 @@
 			dsa_switch_destroy(ds);
 	}
 
+	dsa_cpu_port_ethtool_restore(dst->ds[0]);
+
 	dev_put(dst->master_netdev);
 }
 
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
new file mode 100644
index 0000000..83b95fc
--- /dev/null
+++ b/net/dsa/dsa2.c
@@ -0,0 +1,690 @@
+/*
+ * net/dsa/dsa2.c - Hardware switch handling, binding version 2
+ * Copyright (c) 2008-2009 Marvell Semiconductor
+ * Copyright (c) 2013 Florian Fainelli <florian@openwrt.org>
+ * Copyright (c) 2016 Andrew Lunn <andrew@lunn.ch>
+ *
+ * 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/device.h>
+#include <linux/err.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <linux/rtnetlink.h>
+#include <net/dsa.h>
+#include <linux/of.h>
+#include <linux/of_net.h>
+#include "dsa_priv.h"
+
+static LIST_HEAD(dsa_switch_trees);
+static DEFINE_MUTEX(dsa2_mutex);
+
+static struct dsa_switch_tree *dsa_get_dst(u32 tree)
+{
+	struct dsa_switch_tree *dst;
+
+	list_for_each_entry(dst, &dsa_switch_trees, list)
+		if (dst->tree == tree)
+			return dst;
+	return NULL;
+}
+
+static void dsa_free_dst(struct kref *ref)
+{
+	struct dsa_switch_tree *dst = container_of(ref, struct dsa_switch_tree,
+						   refcount);
+
+	list_del(&dst->list);
+	kfree(dst);
+}
+
+static void dsa_put_dst(struct dsa_switch_tree *dst)
+{
+	kref_put(&dst->refcount, dsa_free_dst);
+}
+
+static struct dsa_switch_tree *dsa_add_dst(u32 tree)
+{
+	struct dsa_switch_tree *dst;
+
+	dst = kzalloc(sizeof(*dst), GFP_KERNEL);
+	if (!dst)
+		return NULL;
+	dst->tree = tree;
+	dst->cpu_switch = -1;
+	INIT_LIST_HEAD(&dst->list);
+	list_add_tail(&dsa_switch_trees, &dst->list);
+	kref_init(&dst->refcount);
+
+	return dst;
+}
+
+static void dsa_dst_add_ds(struct dsa_switch_tree *dst,
+			   struct dsa_switch *ds, u32 index)
+{
+	kref_get(&dst->refcount);
+	dst->ds[index] = ds;
+}
+
+static void dsa_dst_del_ds(struct dsa_switch_tree *dst,
+			   struct dsa_switch *ds, u32 index)
+{
+	dst->ds[index] = NULL;
+	kref_put(&dst->refcount, dsa_free_dst);
+}
+
+static bool dsa_port_is_dsa(struct device_node *port)
+{
+	const char *name;
+
+	name = of_get_property(port, "label", NULL);
+	if (!name)
+		return false;
+
+	if (!strcmp(name, "dsa"))
+		return true;
+
+	return false;
+}
+
+static bool dsa_port_is_cpu(struct device_node *port)
+{
+	const char *name;
+
+	name = of_get_property(port, "label", NULL);
+	if (!name)
+		return false;
+
+	if (!strcmp(name, "cpu"))
+		return true;
+
+	return false;
+}
+
+static bool dsa_ds_find_port(struct dsa_switch *ds,
+			     struct device_node *port)
+{
+	u32 index;
+
+	for (index = 0; index < DSA_MAX_PORTS; index++)
+		if (ds->ports[index].dn == port)
+			return true;
+	return false;
+}
+
+static struct dsa_switch *dsa_dst_find_port(struct dsa_switch_tree *dst,
+					    struct device_node *port)
+{
+	struct dsa_switch *ds;
+	u32 index;
+
+	for (index = 0; index < DSA_MAX_SWITCHES; index++) {
+		ds = dst->ds[index];
+		if (!ds)
+			continue;
+
+		if (dsa_ds_find_port(ds, port))
+			return ds;
+	}
+
+	return NULL;
+}
+
+static int dsa_port_complete(struct dsa_switch_tree *dst,
+			     struct dsa_switch *src_ds,
+			     struct device_node *port,
+			     u32 src_port)
+{
+	struct device_node *link;
+	int index;
+	struct dsa_switch *dst_ds;
+
+	for (index = 0;; index++) {
+		link = of_parse_phandle(port, "link", index);
+		if (!link)
+			break;
+
+		dst_ds = dsa_dst_find_port(dst, link);
+		of_node_put(link);
+
+		if (!dst_ds)
+			return 1;
+
+		src_ds->rtable[dst_ds->index] = src_port;
+	}
+
+	return 0;
+}
+
+/* A switch is complete if all the DSA ports phandles point to ports
+ * known in the tree. A return value of 1 means the tree is not
+ * complete. This is not an error condition. A value of 0 is
+ * success.
+ */
+static int dsa_ds_complete(struct dsa_switch_tree *dst, struct dsa_switch *ds)
+{
+	struct device_node *port;
+	u32 index;
+	int err;
+
+	for (index = 0; index < DSA_MAX_PORTS; index++) {
+		port = ds->ports[index].dn;
+		if (!port)
+			continue;
+
+		if (!dsa_port_is_dsa(port))
+			continue;
+
+		err = dsa_port_complete(dst, ds, port, index);
+		if (err != 0)
+			return err;
+
+		ds->dsa_port_mask |= BIT(index);
+	}
+
+	return 0;
+}
+
+/* A tree is complete if all the DSA ports phandles point to ports
+ * known in the tree. A return value of 1 means the tree is not
+ * complete. This is not an error condition. A value of 0 is
+ * success.
+ */
+static int dsa_dst_complete(struct dsa_switch_tree *dst)
+{
+	struct dsa_switch *ds;
+	u32 index;
+	int err;
+
+	for (index = 0; index < DSA_MAX_SWITCHES; index++) {
+		ds = dst->ds[index];
+		if (!ds)
+			continue;
+
+		err = dsa_ds_complete(dst, ds);
+		if (err != 0)
+			return err;
+	}
+
+	return 0;
+}
+
+static int dsa_dsa_port_apply(struct device_node *port, u32 index,
+			      struct dsa_switch *ds)
+{
+	int err;
+
+	err = dsa_cpu_dsa_setup(ds, ds->dev, port, index);
+	if (err) {
+		dev_warn(ds->dev, "Failed to setup dsa port %d: %d\n",
+			 index, err);
+		return err;
+	}
+
+	return 0;
+}
+
+static void dsa_dsa_port_unapply(struct device_node *port, u32 index,
+				 struct dsa_switch *ds)
+{
+	dsa_cpu_dsa_destroy(port);
+}
+
+static int dsa_cpu_port_apply(struct device_node *port, u32 index,
+			      struct dsa_switch *ds)
+{
+	int err;
+
+	err = dsa_cpu_dsa_setup(ds, ds->dev, port, index);
+	if (err) {
+		dev_warn(ds->dev, "Failed to setup cpu port %d: %d\n",
+			 index, err);
+		return err;
+	}
+
+	ds->cpu_port_mask |= BIT(index);
+
+	return 0;
+}
+
+static void dsa_cpu_port_unapply(struct device_node *port, u32 index,
+				 struct dsa_switch *ds)
+{
+	dsa_cpu_dsa_destroy(port);
+	ds->cpu_port_mask &= ~BIT(index);
+
+}
+
+static int dsa_user_port_apply(struct device_node *port, u32 index,
+			       struct dsa_switch *ds)
+{
+	const char *name;
+	int err;
+
+	name = of_get_property(port, "label", NULL);
+
+	err = dsa_slave_create(ds, ds->dev, index, name);
+	if (err) {
+		dev_warn(ds->dev, "Failed to create slave %d: %d\n",
+			 index, err);
+		return err;
+	}
+
+	return 0;
+}
+
+static void dsa_user_port_unapply(struct device_node *port, u32 index,
+				  struct dsa_switch *ds)
+{
+	if (ds->ports[index].netdev) {
+		dsa_slave_destroy(ds->ports[index].netdev);
+		ds->ports[index].netdev = NULL;
+		ds->enabled_port_mask &= ~(1 << index);
+	}
+}
+
+static int dsa_ds_apply(struct dsa_switch_tree *dst, struct dsa_switch *ds)
+{
+	struct device_node *port;
+	u32 index;
+	int err;
+
+	/* Initialize ds->phys_mii_mask before registering the slave MDIO bus
+	 * driver and before drv->setup() has run, since the switch drivers and
+	 * the slave MDIO bus driver rely on these values for probing PHY
+	 * devices or not
+	 */
+	ds->phys_mii_mask = ds->enabled_port_mask;
+
+	err = ds->drv->setup(ds);
+	if (err < 0)
+		return err;
+
+	err = ds->drv->set_addr(ds, dst->master_netdev->dev_addr);
+	if (err < 0)
+		return err;
+
+	err = ds->drv->set_addr(ds, dst->master_netdev->dev_addr);
+	if (err < 0)
+		return err;
+
+	if (!ds->slave_mii_bus && ds->drv->phy_read) {
+		ds->slave_mii_bus = devm_mdiobus_alloc(ds->dev);
+		if (!ds->slave_mii_bus)
+			return -ENOMEM;
+
+		dsa_slave_mii_bus_init(ds);
+
+		err = mdiobus_register(ds->slave_mii_bus);
+		if (err < 0)
+			return err;
+	}
+
+	for (index = 0; index < DSA_MAX_PORTS; index++) {
+		port = ds->ports[index].dn;
+		if (!port)
+			continue;
+
+		if (dsa_port_is_dsa(port)) {
+			err = dsa_dsa_port_apply(port, index, ds);
+			if (err)
+				return err;
+			continue;
+		}
+
+		if (dsa_port_is_cpu(port)) {
+			err = dsa_cpu_port_apply(port, index, ds);
+			if (err)
+				return err;
+			continue;
+		}
+
+		err = dsa_user_port_apply(port, index, ds);
+		if (err)
+			continue;
+	}
+
+	return 0;
+}
+
+static void dsa_ds_unapply(struct dsa_switch_tree *dst, struct dsa_switch *ds)
+{
+	struct device_node *port;
+	u32 index;
+
+	for (index = 0; index < DSA_MAX_PORTS; index++) {
+		port = ds->ports[index].dn;
+		if (!port)
+			continue;
+
+		if (dsa_port_is_dsa(port)) {
+			dsa_dsa_port_unapply(port, index, ds);
+			continue;
+		}
+
+		if (dsa_port_is_cpu(port)) {
+			dsa_cpu_port_unapply(port, index, ds);
+			continue;
+		}
+
+		dsa_user_port_unapply(port, index, ds);
+	}
+
+	if (ds->slave_mii_bus && ds->drv->phy_read)
+		mdiobus_unregister(ds->slave_mii_bus);
+}
+
+static int dsa_dst_apply(struct dsa_switch_tree *dst)
+{
+	struct dsa_switch *ds;
+	u32 index;
+	int err;
+
+	for (index = 0; index < DSA_MAX_SWITCHES; index++) {
+		ds = dst->ds[index];
+		if (!ds)
+			continue;
+
+		err = dsa_ds_apply(dst, ds);
+		if (err)
+			return err;
+	}
+
+	err = dsa_cpu_port_ethtool_setup(dst->ds[0]);
+	if (err)
+		return err;
+
+	/* If we use a tagging format that doesn't have an ethertype
+	 * field, make sure that all packets from this point on get
+	 * sent to the tag format's receive function.
+	 */
+	wmb();
+	dst->master_netdev->dsa_ptr = (void *)dst;
+	dst->applied = true;
+
+	return 0;
+}
+
+static void dsa_dst_unapply(struct dsa_switch_tree *dst)
+{
+	struct dsa_switch *ds;
+	u32 index;
+
+	if (!dst->applied)
+		return;
+
+	dst->master_netdev->dsa_ptr = NULL;
+
+	/* If we used a tagging format that doesn't have an ethertype
+	 * field, make sure that all packets from this point get sent
+	 * without the tag and go through the regular receive path.
+	 */
+	wmb();
+
+	for (index = 0; index < DSA_MAX_SWITCHES; index++) {
+		ds = dst->ds[index];
+		if (!ds)
+			continue;
+
+		dsa_ds_unapply(dst, ds);
+	}
+
+	dsa_cpu_port_ethtool_restore(dst->ds[0]);
+
+	pr_info("DSA: tree %d unapplied\n", dst->tree);
+	dst->applied = false;
+}
+
+static int dsa_cpu_parse(struct device_node *port, u32 index,
+			 struct dsa_switch_tree *dst,
+			 struct dsa_switch *ds)
+{
+	struct net_device *ethernet_dev;
+	struct device_node *ethernet;
+
+	ethernet = of_parse_phandle(port, "ethernet", 0);
+	if (!ethernet)
+		return -EINVAL;
+
+	ethernet_dev = of_find_net_device_by_node(ethernet);
+	if (!ethernet_dev)
+		return -EPROBE_DEFER;
+
+	if (!ds->master_netdev)
+		ds->master_netdev = ethernet_dev;
+
+	if (!dst->master_netdev)
+		dst->master_netdev = ethernet_dev;
+
+	if (dst->cpu_switch == -1) {
+		dst->cpu_switch = ds->index;
+		dst->cpu_port = index;
+	}
+
+	dst->tag_ops = dsa_resolve_tag_protocol(ds->drv->tag_protocol);
+	if (IS_ERR(dst->tag_ops)) {
+		dev_warn(ds->dev, "No tagger for this switch\n");
+		return PTR_ERR(dst->tag_ops);
+	}
+
+	dst->rcv = dst->tag_ops->rcv;
+
+	return 0;
+}
+
+static int dsa_ds_parse(struct dsa_switch_tree *dst, struct dsa_switch *ds)
+{
+	struct device_node *port;
+	u32 index;
+	int err;
+
+	for (index = 0; index < DSA_MAX_PORTS; index++) {
+		port = ds->ports[index].dn;
+		if (!port)
+			continue;
+
+		if (dsa_port_is_cpu(port)) {
+			err = dsa_cpu_parse(port, index, dst, ds);
+			if (err)
+				return err;
+		}
+	}
+
+	pr_info("DSA: switch %d %d parsed\n", dst->tree, ds->index);
+
+	return 0;
+}
+
+static int dsa_dst_parse(struct dsa_switch_tree *dst)
+{
+	struct dsa_switch *ds;
+	u32 index;
+	int err;
+
+	for (index = 0; index < DSA_MAX_SWITCHES; index++) {
+		ds = dst->ds[index];
+		if (!ds)
+			continue;
+
+		err = dsa_ds_parse(dst, ds);
+		if (err)
+			return err;
+	}
+
+	if (!dst->master_netdev) {
+		pr_warn("Tree has no master device\n");
+		return -EINVAL;
+	}
+
+	pr_info("DSA: tree %d parsed\n", dst->tree);
+
+	return 0;
+}
+
+static int dsa_parse_ports_dn(struct device_node *ports, struct dsa_switch *ds)
+{
+	struct device_node *port;
+	int err;
+	u32 reg;
+
+	for_each_available_child_of_node(ports, port) {
+		err = of_property_read_u32(port, "reg", &reg);
+		if (err)
+			return err;
+
+		if (reg >= DSA_MAX_PORTS)
+			return -EINVAL;
+
+		ds->ports[reg].dn = port;
+
+		/* Initialize enabled_port_mask now for drv->setup()
+		 * to have access to a correct value, just like what
+		 * net/dsa/dsa.c::dsa_switch_setup_one does.
+		 */
+		if (!dsa_port_is_cpu(port))
+			ds->enabled_port_mask |= 1 << reg;
+	}
+
+	return 0;
+}
+
+static int dsa_parse_member(struct device_node *np, u32 *tree, u32 *index)
+{
+	int err;
+
+	*tree = *index = 0;
+
+	err = of_property_read_u32_index(np, "dsa,member", 0, tree);
+	if (err) {
+		/* Does not exist, but it is optional */
+		if (err == -EINVAL)
+			return 0;
+		return err;
+	}
+
+	err = of_property_read_u32_index(np, "dsa,member", 1, index);
+	if (err)
+		return err;
+
+	if (*index >= DSA_MAX_SWITCHES)
+		return -EINVAL;
+
+	return 0;
+}
+
+static struct device_node *dsa_get_ports(struct dsa_switch *ds,
+					 struct device_node *np)
+{
+	struct device_node *ports;
+
+	ports = of_get_child_by_name(np, "ports");
+	if (!ports) {
+		dev_err(ds->dev, "no ports child node found\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	return ports;
+}
+
+static int _dsa_register_switch(struct dsa_switch *ds, struct device_node *np)
+{
+	struct device_node *ports = dsa_get_ports(ds, np);
+	struct dsa_switch_tree *dst;
+	u32 tree, index;
+	int err;
+
+	err = dsa_parse_member(np, &tree, &index);
+	if (err)
+		return err;
+
+	if (IS_ERR(ports))
+		return PTR_ERR(ports);
+
+	err = dsa_parse_ports_dn(ports, ds);
+	if (err)
+		return err;
+
+	dst = dsa_get_dst(tree);
+	if (!dst) {
+		dst = dsa_add_dst(tree);
+		if (!dst)
+			return -ENOMEM;
+	}
+
+	if (dst->ds[index]) {
+		err = -EBUSY;
+		goto out;
+	}
+
+	ds->dst = dst;
+	ds->index = index;
+	dsa_dst_add_ds(dst, ds, index);
+
+	err = dsa_dst_complete(dst);
+	if (err < 0)
+		goto out_del_dst;
+
+	if (err == 1) {
+		/* Not all switches registered yet */
+		err = 0;
+		goto out;
+	}
+
+	if (dst->applied) {
+		pr_info("DSA: Disjoint trees?\n");
+		return -EINVAL;
+	}
+
+	err = dsa_dst_parse(dst);
+	if (err)
+		goto out_del_dst;
+
+	err = dsa_dst_apply(dst);
+	if (err) {
+		dsa_dst_unapply(dst);
+		goto out_del_dst;
+	}
+
+	dsa_put_dst(dst);
+	return 0;
+
+out_del_dst:
+	dsa_dst_del_ds(dst, ds, ds->index);
+out:
+	dsa_put_dst(dst);
+
+	return err;
+}
+
+int dsa_register_switch(struct dsa_switch *ds, struct device_node *np)
+{
+	int err;
+
+	mutex_lock(&dsa2_mutex);
+	err = _dsa_register_switch(ds, np);
+	mutex_unlock(&dsa2_mutex);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(dsa_register_switch);
+
+void _dsa_unregister_switch(struct dsa_switch *ds)
+{
+	struct dsa_switch_tree *dst = ds->dst;
+
+	dsa_dst_unapply(dst);
+
+	dsa_dst_del_ds(dst, ds, ds->index);
+}
+
+void dsa_unregister_switch(struct dsa_switch *ds)
+{
+	mutex_lock(&dsa2_mutex);
+	_dsa_unregister_switch(ds);
+	mutex_unlock(&dsa2_mutex);
+}
+EXPORT_SYMBOL_GPL(dsa_unregister_switch);
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index dfa3377..00077a9 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -50,12 +50,19 @@
 
 /* dsa.c */
 extern char dsa_driver_version[];
+int dsa_cpu_dsa_setup(struct dsa_switch *ds, struct device *dev,
+		      struct device_node *port_dn, int port);
+void dsa_cpu_dsa_destroy(struct device_node *port_dn);
+const struct dsa_device_ops *dsa_resolve_tag_protocol(int tag_protocol);
+int dsa_cpu_port_ethtool_setup(struct dsa_switch *ds);
+void dsa_cpu_port_ethtool_restore(struct dsa_switch *ds);
 
 /* slave.c */
 extern const struct dsa_device_ops notag_netdev_ops;
 void dsa_slave_mii_bus_init(struct dsa_switch *ds);
+void dsa_cpu_port_ethtool_init(struct ethtool_ops *ops);
 int dsa_slave_create(struct dsa_switch *ds, struct device *parent,
-		     int port, char *name);
+		     int port, const char *name);
 void dsa_slave_destroy(struct net_device *slave_dev);
 int dsa_slave_suspend(struct net_device *slave_dev);
 int dsa_slave_resume(struct net_device *slave_dev);
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 152436c..7236eb2 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -49,8 +49,8 @@
 	ds->slave_mii_bus->name = "dsa slave smi";
 	ds->slave_mii_bus->read = dsa_slave_phy_read;
 	ds->slave_mii_bus->write = dsa_slave_phy_write;
-	snprintf(ds->slave_mii_bus->id, MII_BUS_ID_SIZE, "dsa-%d:%.2x",
-			ds->index, ds->cd->sw_addr);
+	snprintf(ds->slave_mii_bus->id, MII_BUS_ID_SIZE, "dsa-%d.%d",
+		 ds->dst->tree, ds->index);
 	ds->slave_mii_bus->parent = ds->dev;
 	ds->slave_mii_bus->phy_mask = ~ds->phys_mii_mask;
 }
@@ -522,14 +522,6 @@
 	return NETDEV_TX_OK;
 }
 
-static struct sk_buff *dsa_slave_notag_xmit(struct sk_buff *skb,
-					    struct net_device *dev)
-{
-	/* Just return the original SKB */
-	return skb;
-}
-
-
 /* ethtool operations *******************************************************/
 static int
 dsa_slave_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
@@ -615,7 +607,7 @@
 	struct dsa_slave_priv *p = netdev_priv(dev);
 	struct dsa_switch *ds = p->parent;
 
-	if (ds->cd->eeprom_len)
+	if (ds->cd && ds->cd->eeprom_len)
 		return ds->cd->eeprom_len;
 
 	if (ds->drv->get_eeprom_len)
@@ -873,6 +865,13 @@
 }
 #endif
 
+void dsa_cpu_port_ethtool_init(struct ethtool_ops *ops)
+{
+	ops->get_sset_count = dsa_cpu_port_get_sset_count;
+	ops->get_ethtool_stats = dsa_cpu_port_get_ethtool_stats;
+	ops->get_strings = dsa_cpu_port_get_strings;
+}
+
 static const struct ethtool_ops dsa_slave_ethtool_ops = {
 	.get_settings		= dsa_slave_get_settings,
 	.set_settings		= dsa_slave_set_settings,
@@ -893,8 +892,6 @@
 	.get_eee		= dsa_slave_get_eee,
 };
 
-static struct ethtool_ops dsa_cpu_port_ethtool_ops;
-
 static const struct net_device_ops dsa_slave_netdev_ops = {
 	.ndo_open	 	= dsa_slave_open,
 	.ndo_stop		= dsa_slave_close,
@@ -999,13 +996,12 @@
 				struct net_device *slave_dev)
 {
 	struct dsa_switch *ds = p->parent;
-	struct dsa_chip_data *cd = ds->cd;
 	struct device_node *phy_dn, *port_dn;
 	bool phy_is_fixed = false;
 	u32 phy_flags = 0;
 	int mode, ret;
 
-	port_dn = cd->port_dn[p->port];
+	port_dn = ds->ports[p->port].dn;
 	mode = of_get_phy_mode(port_dn);
 	if (mode < 0)
 		mode = PHY_INTERFACE_MODE_NA;
@@ -1109,14 +1105,18 @@
 }
 
 int dsa_slave_create(struct dsa_switch *ds, struct device *parent,
-		     int port, char *name)
+		     int port, const char *name)
 {
-	struct net_device *master = ds->dst->master_netdev;
 	struct dsa_switch_tree *dst = ds->dst;
+	struct net_device *master;
 	struct net_device *slave_dev;
 	struct dsa_slave_priv *p;
 	int ret;
 
+	master = ds->dst->master_netdev;
+	if (ds->master_netdev)
+		master = ds->master_netdev;
+
 	slave_dev = alloc_netdev(sizeof(struct dsa_slave_priv), name,
 				 NET_NAME_UNKNOWN, ether_setup);
 	if (slave_dev == NULL)
@@ -1124,19 +1124,6 @@
 
 	slave_dev->features = master->vlan_features;
 	slave_dev->ethtool_ops = &dsa_slave_ethtool_ops;
-	if (master->ethtool_ops != &dsa_cpu_port_ethtool_ops) {
-		memcpy(&dst->master_ethtool_ops, master->ethtool_ops,
-		       sizeof(struct ethtool_ops));
-		memcpy(&dsa_cpu_port_ethtool_ops, &dst->master_ethtool_ops,
-		       sizeof(struct ethtool_ops));
-		dsa_cpu_port_ethtool_ops.get_sset_count =
-					dsa_cpu_port_get_sset_count;
-		dsa_cpu_port_ethtool_ops.get_ethtool_stats =
-					dsa_cpu_port_get_ethtool_stats;
-		dsa_cpu_port_ethtool_ops.get_strings =
-					dsa_cpu_port_get_strings;
-		master->ethtool_ops = &dsa_cpu_port_ethtool_ops;
-	}
 	eth_hw_addr_inherit(slave_dev, master);
 	slave_dev->priv_flags |= IFF_NO_QUEUE;
 	slave_dev->netdev_ops = &dsa_slave_netdev_ops;
@@ -1147,49 +1134,24 @@
 				 NULL);
 
 	SET_NETDEV_DEV(slave_dev, parent);
-	slave_dev->dev.of_node = ds->cd->port_dn[port];
+	slave_dev->dev.of_node = ds->ports[port].dn;
 	slave_dev->vlan_features = master->vlan_features;
 
 	p = netdev_priv(slave_dev);
 	p->parent = ds;
 	p->port = port;
-
-	switch (ds->dst->tag_protocol) {
-#ifdef CONFIG_NET_DSA_TAG_DSA
-	case DSA_TAG_PROTO_DSA:
-		p->xmit = dsa_netdev_ops.xmit;
-		break;
-#endif
-#ifdef CONFIG_NET_DSA_TAG_EDSA
-	case DSA_TAG_PROTO_EDSA:
-		p->xmit = edsa_netdev_ops.xmit;
-		break;
-#endif
-#ifdef CONFIG_NET_DSA_TAG_TRAILER
-	case DSA_TAG_PROTO_TRAILER:
-		p->xmit = trailer_netdev_ops.xmit;
-		break;
-#endif
-#ifdef CONFIG_NET_DSA_TAG_BRCM
-	case DSA_TAG_PROTO_BRCM:
-		p->xmit = brcm_netdev_ops.xmit;
-		break;
-#endif
-	default:
-		p->xmit	= dsa_slave_notag_xmit;
-		break;
-	}
+	p->xmit = dst->tag_ops->xmit;
 
 	p->old_pause = -1;
 	p->old_link = -1;
 	p->old_duplex = -1;
 
-	ds->ports[port] = slave_dev;
+	ds->ports[port].netdev = slave_dev;
 	ret = register_netdev(slave_dev);
 	if (ret) {
 		netdev_err(master, "error %d registering interface %s\n",
 			   ret, slave_dev->name);
-		ds->ports[port] = NULL;
+		ds->ports[port].netdev = NULL;
 		free_netdev(slave_dev);
 		return ret;
 	}
diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c
index e2aadb7..21bffde 100644
--- a/net/dsa/tag_brcm.c
+++ b/net/dsa/tag_brcm.c
@@ -127,7 +127,7 @@
 	source_port = brcm_tag[3] & BRCM_EG_PID_MASK;
 
 	/* Validate port against switch setup, either the port is totally */
-	if (source_port >= DSA_MAX_PORTS || ds->ports[source_port] == NULL)
+	if (source_port >= DSA_MAX_PORTS || !ds->ports[source_port].netdev)
 		goto out_drop;
 
 	/* Remove Broadcom tag and update checksum */
@@ -140,7 +140,7 @@
 
 	skb_push(skb, ETH_HLEN);
 	skb->pkt_type = PACKET_HOST;
-	skb->dev = ds->ports[source_port];
+	skb->dev = ds->ports[source_port].netdev;
 	skb->protocol = eth_type_trans(skb, skb->dev);
 
 	skb->dev->stats.rx_packets++;
diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c
index aa780e4..bce79ff 100644
--- a/net/dsa/tag_dsa.c
+++ b/net/dsa/tag_dsa.c
@@ -107,10 +107,14 @@
 	 * Check that the source device exists and that the source
 	 * port is a registered DSA port.
 	 */
-	if (source_device >= dst->pd->nr_chips)
+	if (source_device >= DSA_MAX_SWITCHES)
 		goto out_drop;
+
 	ds = dst->ds[source_device];
-	if (source_port >= DSA_MAX_PORTS || ds->ports[source_port] == NULL)
+	if (!ds)
+		goto out_drop;
+
+	if (source_port >= DSA_MAX_PORTS || !ds->ports[source_port].netdev)
 		goto out_drop;
 
 	/*
@@ -159,7 +163,7 @@
 			2 * ETH_ALEN);
 	}
 
-	skb->dev = ds->ports[source_port];
+	skb->dev = ds->ports[source_port].netdev;
 	skb_push(skb, ETH_HLEN);
 	skb->pkt_type = PACKET_HOST;
 	skb->protocol = eth_type_trans(skb, skb->dev);
diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c
index 2288c80..6c1720e 100644
--- a/net/dsa/tag_edsa.c
+++ b/net/dsa/tag_edsa.c
@@ -120,10 +120,14 @@
 	 * Check that the source device exists and that the source
 	 * port is a registered DSA port.
 	 */
-	if (source_device >= dst->pd->nr_chips)
+	if (source_device >= DSA_MAX_SWITCHES)
 		goto out_drop;
+
 	ds = dst->ds[source_device];
-	if (source_port >= DSA_MAX_PORTS || ds->ports[source_port] == NULL)
+	if (!ds)
+		goto out_drop;
+
+	if (source_port >= DSA_MAX_PORTS || !ds->ports[source_port].netdev)
 		goto out_drop;
 
 	/*
@@ -178,7 +182,7 @@
 			2 * ETH_ALEN);
 	}
 
-	skb->dev = ds->ports[source_port];
+	skb->dev = ds->ports[source_port].netdev;
 	skb_push(skb, ETH_HLEN);
 	skb->pkt_type = PACKET_HOST;
 	skb->protocol = eth_type_trans(skb, skb->dev);
diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c
index b6ca089..5e3903e 100644
--- a/net/dsa/tag_trailer.c
+++ b/net/dsa/tag_trailer.c
@@ -82,12 +82,12 @@
 		goto out_drop;
 
 	source_port = trailer[1] & 7;
-	if (source_port >= DSA_MAX_PORTS || ds->ports[source_port] == NULL)
+	if (source_port >= DSA_MAX_PORTS || !ds->ports[source_port].netdev)
 		goto out_drop;
 
 	pskb_trim_rcsum(skb, skb->len - 4);
 
-	skb->dev = ds->ports[source_port];
+	skb->dev = ds->ports[source_port].netdev;
 	skb_push(skb, ETH_HLEN);
 	skb->pkt_type = PACKET_HOST;
 	skb->protocol = eth_type_trans(skb, skb->dev);
diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c
index dd085db..8c004a0 100644
--- a/net/ieee802154/6lowpan/core.c
+++ b/net/ieee802154/6lowpan/core.c
@@ -58,21 +58,10 @@
 	.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 *ldev,
-					 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 *ldev)
 {
-	netdev_for_each_tx_queue(ldev, lowpan_set_lockdep_class_one, NULL);
-	ldev->qdisc_tx_busylock = &lowpan_tx_busylock;
+	netdev_lockdep_set_classes(ldev);
+
 	return 0;
 }
 
@@ -92,11 +81,21 @@
 	return 0;
 }
 
+static int lowpan_neigh_construct(struct neighbour *n)
+{
+	struct lowpan_802154_neigh *neigh = lowpan_802154_neigh(neighbour_priv(n));
+
+	/* default no short_addr is available for a neighbour */
+	neigh->short_addr = cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC);
+	return 0;
+}
+
 static const struct net_device_ops lowpan_netdev_ops = {
 	.ndo_init		= lowpan_dev_init,
 	.ndo_start_xmit		= lowpan_xmit,
 	.ndo_open		= lowpan_open,
 	.ndo_stop		= lowpan_stop,
+	.ndo_neigh_construct    = lowpan_neigh_construct,
 };
 
 static void lowpan_setup(struct net_device *ldev)
@@ -161,6 +160,8 @@
 				wdev->needed_headroom;
 	ldev->needed_tailroom = wdev->needed_tailroom;
 
+	ldev->neigh_priv_len = sizeof(struct lowpan_802154_neigh);
+
 	ret = lowpan_register_netdevice(ldev, LOWPAN_LLTYPE_IEEE802154);
 	if (ret < 0) {
 		dev_put(wdev);
diff --git a/net/ieee802154/6lowpan/tx.c b/net/ieee802154/6lowpan/tx.c
index e459afd..dbb476d 100644
--- a/net/ieee802154/6lowpan/tx.c
+++ b/net/ieee802154/6lowpan/tx.c
@@ -9,6 +9,7 @@
  */
 
 #include <net/6lowpan.h>
+#include <net/ndisc.h>
 #include <net/ieee802154_netdev.h>
 #include <net/mac802154.h>
 
@@ -17,19 +18,9 @@
 #define LOWPAN_FRAG1_HEAD_SIZE	0x4
 #define LOWPAN_FRAGN_HEAD_SIZE	0x5
 
-/* don't save pan id, it's intra pan */
-struct lowpan_addr {
-	u8 mode;
-	union {
-		/* IPv6 needs big endian here */
-		__be64 extended_addr;
-		__be16 short_addr;
-	} u;
-};
-
 struct lowpan_addr_info {
-	struct lowpan_addr daddr;
-	struct lowpan_addr saddr;
+	struct ieee802154_addr daddr;
+	struct ieee802154_addr saddr;
 };
 
 static inline struct
@@ -48,12 +39,14 @@
  * RAW/DGRAM sockets.
  */
 int lowpan_header_create(struct sk_buff *skb, struct net_device *ldev,
-			 unsigned short type, const void *_daddr,
-			 const void *_saddr, unsigned int len)
+			 unsigned short type, const void *daddr,
+			 const void *saddr, unsigned int len)
 {
-	const u8 *saddr = _saddr;
-	const u8 *daddr = _daddr;
-	struct lowpan_addr_info *info;
+	struct wpan_dev *wpan_dev = lowpan_802154_dev(ldev)->wdev->ieee802154_ptr;
+	struct lowpan_addr_info *info = lowpan_skb_priv(skb);
+	struct lowpan_802154_neigh *llneigh = NULL;
+	const struct ipv6hdr *hdr = ipv6_hdr(skb);
+	struct neighbour *n;
 
 	/* TODO:
 	 * if this package isn't ipv6 one, where should it be routed?
@@ -61,21 +54,50 @@
 	if (type != ETH_P_IPV6)
 		return 0;
 
-	if (!saddr)
-		saddr = ldev->dev_addr;
+	/* intra-pan communication */
+	info->saddr.pan_id = wpan_dev->pan_id;
+	info->daddr.pan_id = info->saddr.pan_id;
 
-	raw_dump_inline(__func__, "saddr", (unsigned char *)saddr, 8);
-	raw_dump_inline(__func__, "daddr", (unsigned char *)daddr, 8);
+	if (!memcmp(daddr, ldev->broadcast, EUI64_ADDR_LEN)) {
+		info->daddr.short_addr = cpu_to_le16(IEEE802154_ADDR_BROADCAST);
+		info->daddr.mode = IEEE802154_ADDR_SHORT;
+	} else {
+		__le16 short_addr = cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC);
 
-	info = lowpan_skb_priv(skb);
+		n = neigh_lookup(&nd_tbl, &hdr->daddr, ldev);
+		if (n) {
+			llneigh = lowpan_802154_neigh(neighbour_priv(n));
+			read_lock_bh(&n->lock);
+			short_addr = llneigh->short_addr;
+			read_unlock_bh(&n->lock);
+		}
 
-	/* TODO: Currently we only support extended_addr */
-	info->daddr.mode = IEEE802154_ADDR_LONG;
-	memcpy(&info->daddr.u.extended_addr, daddr,
-	       sizeof(info->daddr.u.extended_addr));
-	info->saddr.mode = IEEE802154_ADDR_LONG;
-	memcpy(&info->saddr.u.extended_addr, saddr,
-	       sizeof(info->daddr.u.extended_addr));
+		if (llneigh &&
+		    lowpan_802154_is_valid_src_short_addr(short_addr)) {
+			info->daddr.short_addr = short_addr;
+			info->daddr.mode = IEEE802154_ADDR_SHORT;
+		} else {
+			info->daddr.mode = IEEE802154_ADDR_LONG;
+			ieee802154_be64_to_le64(&info->daddr.extended_addr,
+						daddr);
+		}
+
+		if (n)
+			neigh_release(n);
+	}
+
+	if (!saddr) {
+		if (lowpan_802154_is_valid_src_short_addr(wpan_dev->short_addr)) {
+			info->saddr.mode = IEEE802154_ADDR_SHORT;
+			info->saddr.short_addr = wpan_dev->short_addr;
+		} else {
+			info->saddr.mode = IEEE802154_ADDR_LONG;
+			info->saddr.extended_addr = wpan_dev->extended_addr;
+		}
+	} else {
+		info->saddr.mode = IEEE802154_ADDR_LONG;
+		ieee802154_be64_to_le64(&info->saddr.extended_addr, saddr);
+	}
 
 	return 0;
 }
@@ -209,47 +231,26 @@
 			 u16 *dgram_size, u16 *dgram_offset)
 {
 	struct wpan_dev *wpan_dev = lowpan_802154_dev(ldev)->wdev->ieee802154_ptr;
-	struct ieee802154_addr sa, da;
 	struct ieee802154_mac_cb *cb = mac_cb_init(skb);
 	struct lowpan_addr_info info;
-	void *daddr, *saddr;
 
 	memcpy(&info, lowpan_skb_priv(skb), sizeof(info));
 
-	/* TODO: Currently we only support extended_addr */
-	daddr = &info.daddr.u.extended_addr;
-	saddr = &info.saddr.u.extended_addr;
-
 	*dgram_size = skb->len;
-	lowpan_header_compress(skb, ldev, daddr, saddr);
+	lowpan_header_compress(skb, ldev, &info.daddr, &info.saddr);
 	/* dgram_offset = (saved bytes after compression) + lowpan header len */
 	*dgram_offset = (*dgram_size - skb->len) + skb_network_header_len(skb);
 
 	cb->type = IEEE802154_FC_TYPE_DATA;
 
-	/* prepare wpan address data */
-	sa.mode = IEEE802154_ADDR_LONG;
-	sa.pan_id = wpan_dev->pan_id;
-	sa.extended_addr = ieee802154_devaddr_from_raw(saddr);
-
-	/* intra-PAN communications */
-	da.pan_id = sa.pan_id;
-
-	/* if the destination address is the broadcast address, use the
-	 * corresponding short address
-	 */
-	if (!memcmp(daddr, ldev->broadcast, EUI64_ADDR_LEN)) {
-		da.mode = IEEE802154_ADDR_SHORT;
-		da.short_addr = cpu_to_le16(IEEE802154_ADDR_BROADCAST);
+	if (info.daddr.mode == IEEE802154_ADDR_SHORT &&
+	    ieee802154_is_broadcast_short_addr(info.daddr.short_addr))
 		cb->ackreq = false;
-	} else {
-		da.mode = IEEE802154_ADDR_LONG;
-		da.extended_addr = ieee802154_devaddr_from_raw(daddr);
+	else
 		cb->ackreq = wpan_dev->ackreq;
-	}
 
-	return wpan_dev_hard_header(skb, lowpan_802154_dev(ldev)->wdev, &da,
-				    &sa, 0);
+	return wpan_dev_hard_header(skb, lowpan_802154_dev(ldev)->wdev,
+				    &info.daddr, &info.saddr, 0);
 }
 
 netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *ldev)
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 238225b..50d6a9b 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -532,6 +532,22 @@
 	window. TCP Vegas should provide less packet loss, but it is
 	not as aggressive as TCP Reno.
 
+config TCP_CONG_NV
+       tristate "TCP NV"
+       default n
+       ---help---
+       TCP NV is a follow up to TCP Vegas. It has been modified to deal with
+       10G networks, measurement noise introduced by LRO, GRO and interrupt
+       coalescence. In addition, it will decrease its cwnd multiplicatively
+       instead of linearly.
+
+       Note that in general congestion avoidance (cwnd decreased when # packets
+       queued grows) cannot coexist with congestion control (cwnd decreased only
+       when there is packet loss) due to fairness issues. One scenario when they
+       can coexist safely is when the CA flows have RTTs << CC flows RTTs.
+
+       For further details see http://www.brakmo.org/networking/tcp-nv/
+
 config TCP_CONG_SCALABLE
 	tristate "Scalable TCP"
 	default n
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index bfa1336..24629b6 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -50,6 +50,7 @@
 obj-$(CONFIG_TCP_CONG_HYBLA) += tcp_hybla.o
 obj-$(CONFIG_TCP_CONG_HTCP) += tcp_htcp.o
 obj-$(CONFIG_TCP_CONG_VEGAS) += tcp_vegas.o
+obj-$(CONFIG_TCP_CONG_NV) += tcp_nv.o
 obj-$(CONFIG_TCP_CONG_VENO) += tcp_veno.o
 obj-$(CONFIG_TCP_CONG_SCALABLE) += tcp_scalable.o
 obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index f2bda9e..6e9ea69 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -76,6 +76,7 @@
 {
 	int err = -EAGAIN;
 	struct fib_table *tbl;
+	u32 tb_id;
 
 	switch (rule->action) {
 	case FR_ACT_TO_TBL:
@@ -94,7 +95,8 @@
 
 	rcu_read_lock();
 
-	tbl = fib_get_table(rule->fr_net, rule->table);
+	tb_id = fib_rule_get_table(rule, arg);
+	tbl = fib_get_table(rule->fr_net, tb_id);
 	if (tbl)
 		err = fib_table_lookup(tbl, &flp->u.ip4,
 				       (struct fib_result *)arg->result,
@@ -180,7 +182,7 @@
 	if (err)
 		goto errout;
 
-	if (rule->table == RT_TABLE_UNSPEC) {
+	if (rule->table == RT_TABLE_UNSPEC && !rule->l3mdev) {
 		if (rule->action == FR_ACT_TO_TBL) {
 			struct fib_table *table;
 
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 5f9207c..321d57f 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -129,6 +129,36 @@
 
 	guehdr = (struct guehdr *)&udp_hdr(skb)[1];
 
+	switch (guehdr->version) {
+	case 0: /* Full GUE header present */
+		break;
+
+	case 1: {
+		/* Direct encasulation of IPv4 or IPv6 */
+
+		int prot;
+
+		switch (((struct iphdr *)guehdr)->version) {
+		case 4:
+			prot = IPPROTO_IPIP;
+			break;
+		case 6:
+			prot = IPPROTO_IPV6;
+			break;
+		default:
+			goto drop;
+		}
+
+		if (fou_recv_pull(skb, fou, sizeof(struct udphdr)))
+			goto drop;
+
+		return -prot;
+	}
+
+	default: /* Undefined version */
+		goto drop;
+	}
+
 	optlen = guehdr->hlen << 2;
 	len += optlen;
 
@@ -289,6 +319,7 @@
 	int flush = 1;
 	struct fou *fou = fou_from_sock(sk);
 	struct gro_remcsum grc;
+	u8 proto;
 
 	skb_gro_remcsum_init(&grc);
 
@@ -302,6 +333,25 @@
 			goto out;
 	}
 
+	switch (guehdr->version) {
+	case 0:
+		break;
+	case 1:
+		switch (((struct iphdr *)guehdr)->version) {
+		case 4:
+			proto = IPPROTO_IPIP;
+			break;
+		case 6:
+			proto = IPPROTO_IPV6;
+			break;
+		default:
+			goto out;
+		}
+		goto next_proto;
+	default:
+		goto out;
+	}
+
 	optlen = guehdr->hlen << 2;
 	len += optlen;
 
@@ -370,6 +420,10 @@
 		}
 	}
 
+	proto = guehdr->proto_ctype;
+
+next_proto:
+
 	/* We can clear the encap_mark for GUE as we are essentially doing
 	 * one of two possible things.  We are either adding an L4 tunnel
 	 * header to the outer L3 tunnel header, or we are are simply
@@ -383,7 +437,7 @@
 
 	rcu_read_lock();
 	offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
-	ops = rcu_dereference(offloads[guehdr->proto_ctype]);
+	ops = rcu_dereference(offloads[proto]);
 	if (WARN_ON_ONCE(!ops || !ops->callbacks.gro_receive))
 		goto out_unlock;
 
@@ -404,13 +458,30 @@
 	const struct net_offload **offloads;
 	struct guehdr *guehdr = (struct guehdr *)(skb->data + nhoff);
 	const struct net_offload *ops;
-	unsigned int guehlen;
+	unsigned int guehlen = 0;
 	u8 proto;
 	int err = -ENOENT;
 
-	proto = guehdr->proto_ctype;
-
-	guehlen = sizeof(*guehdr) + (guehdr->hlen << 2);
+	switch (guehdr->version) {
+	case 0:
+		proto = guehdr->proto_ctype;
+		guehlen = sizeof(*guehdr) + (guehdr->hlen << 2);
+		break;
+	case 1:
+		switch (((struct iphdr *)guehdr)->version) {
+		case 4:
+			proto = IPPROTO_IPIP;
+			break;
+		case 6:
+			proto = IPPROTO_IPV6;
+			break;
+		default:
+			return err;
+		}
+		break;
+	default:
+		return err;
+	}
 
 	rcu_read_lock();
 	offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c
index 4c39f4f..c4c3e43 100644
--- a/net/ipv4/gre_demux.c
+++ b/net/ipv4/gre_demux.c
@@ -117,6 +117,7 @@
 		if ((*(u8 *)options & 0xF0) != 0x40)
 			hdr_len += 4;
 	}
+	tpi->hdr_len = hdr_len;
 	return hdr_len;
 }
 EXPORT_SYMBOL(gre_parse_header);
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 3a88b0c..b5e9317 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -355,7 +355,7 @@
 {
 	struct inet_frag_queue *q;
 
-	if (frag_mem_limit(nf) > nf->high_thresh) {
+	if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh) {
 		inet_frag_schedule_worker(f);
 		return NULL;
 	}
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 4d2025f..8eec78f 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -144,6 +144,7 @@
 	const struct iphdr *iph;
 	const int type = icmp_hdr(skb)->type;
 	const int code = icmp_hdr(skb)->code;
+	unsigned int data_len = 0;
 	struct ip_tunnel *t;
 
 	switch (type) {
@@ -169,6 +170,7 @@
 	case ICMP_TIME_EXCEEDED:
 		if (code != ICMP_EXC_TTL)
 			return;
+		data_len = icmp_hdr(skb)->un.reserved[1] * 4; /* RFC 4884 4.1 */
 		break;
 
 	case ICMP_REDIRECT:
@@ -187,6 +189,13 @@
 	if (!t)
 		return;
 
+#if IS_ENABLED(CONFIG_IPV6)
+       if (tpi->proto == htons(ETH_P_IPV6) &&
+           !ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4 + tpi->hdr_len,
+				       type, data_len))
+               return;
+#endif
+
 	if (t->parms.iph.daddr == 0 ||
 	    ipv4_is_multicast(t->parms.iph.daddr))
 		return;
@@ -841,17 +850,19 @@
 	return ipgre_tunnel_validate(tb, data);
 }
 
-static void ipgre_netlink_parms(struct net_device *dev,
+static int ipgre_netlink_parms(struct net_device *dev,
 				struct nlattr *data[],
 				struct nlattr *tb[],
 				struct ip_tunnel_parm *parms)
 {
+	struct ip_tunnel *t = netdev_priv(dev);
+
 	memset(parms, 0, sizeof(*parms));
 
 	parms->iph.protocol = IPPROTO_GRE;
 
 	if (!data)
-		return;
+		return 0;
 
 	if (data[IFLA_GRE_LINK])
 		parms->link = nla_get_u32(data[IFLA_GRE_LINK]);
@@ -880,16 +891,26 @@
 	if (data[IFLA_GRE_TOS])
 		parms->iph.tos = nla_get_u8(data[IFLA_GRE_TOS]);
 
-	if (!data[IFLA_GRE_PMTUDISC] || nla_get_u8(data[IFLA_GRE_PMTUDISC]))
+	if (!data[IFLA_GRE_PMTUDISC] || nla_get_u8(data[IFLA_GRE_PMTUDISC])) {
+		if (t->ignore_df)
+			return -EINVAL;
 		parms->iph.frag_off = htons(IP_DF);
+	}
 
 	if (data[IFLA_GRE_COLLECT_METADATA]) {
-		struct ip_tunnel *t = netdev_priv(dev);
-
 		t->collect_md = true;
 		if (dev->type == ARPHRD_IPGRE)
 			dev->type = ARPHRD_NONE;
 	}
+
+	if (data[IFLA_GRE_IGNORE_DF]) {
+		if (nla_get_u8(data[IFLA_GRE_IGNORE_DF])
+		  && (parms->iph.frag_off & htons(IP_DF)))
+			return -EINVAL;
+		t->ignore_df = !!nla_get_u8(data[IFLA_GRE_IGNORE_DF]);
+	}
+
+	return 0;
 }
 
 /* This function returns true when ENCAP attributes are present in the nl msg */
@@ -960,16 +981,19 @@
 {
 	struct ip_tunnel_parm p;
 	struct ip_tunnel_encap ipencap;
+	int err;
 
 	if (ipgre_netlink_encap_parms(data, &ipencap)) {
 		struct ip_tunnel *t = netdev_priv(dev);
-		int err = ip_tunnel_encap_setup(t, &ipencap);
+		err = ip_tunnel_encap_setup(t, &ipencap);
 
 		if (err < 0)
 			return err;
 	}
 
-	ipgre_netlink_parms(dev, data, tb, &p);
+	err = ipgre_netlink_parms(dev, data, tb, &p);
+	if (err < 0)
+		return err;
 	return ip_tunnel_newlink(dev, tb, &p);
 }
 
@@ -978,16 +1002,19 @@
 {
 	struct ip_tunnel_parm p;
 	struct ip_tunnel_encap ipencap;
+	int err;
 
 	if (ipgre_netlink_encap_parms(data, &ipencap)) {
 		struct ip_tunnel *t = netdev_priv(dev);
-		int err = ip_tunnel_encap_setup(t, &ipencap);
+		err = ip_tunnel_encap_setup(t, &ipencap);
 
 		if (err < 0)
 			return err;
 	}
 
-	ipgre_netlink_parms(dev, data, tb, &p);
+	err = ipgre_netlink_parms(dev, data, tb, &p);
+	if (err < 0)
+		return err;
 	return ip_tunnel_changelink(dev, tb, &p);
 }
 
@@ -1024,6 +1051,8 @@
 		nla_total_size(2) +
 		/* IFLA_GRE_COLLECT_METADATA */
 		nla_total_size(0) +
+		/* IFLA_GRE_IGNORE_DF */
+		nla_total_size(1) +
 		0;
 }
 
@@ -1057,6 +1086,9 @@
 			t->encap.flags))
 		goto nla_put_failure;
 
+	if (nla_put_u8(skb, IFLA_GRE_IGNORE_DF, t->ignore_df))
+		goto nla_put_failure;
+
 	if (t->collect_md) {
 		if (nla_put_flag(skb, IFLA_GRE_COLLECT_METADATA))
 			goto nla_put_failure;
@@ -1084,6 +1116,7 @@
 	[IFLA_GRE_ENCAP_SPORT]	= { .type = NLA_U16 },
 	[IFLA_GRE_ENCAP_DPORT]	= { .type = NLA_U16 },
 	[IFLA_GRE_COLLECT_METADATA]	= { .type = NLA_FLAG },
+	[IFLA_GRE_IGNORE_DF]	= { .type = NLA_U8 },
 };
 
 static struct rtnl_link_ops ipgre_link_ops __read_mostly = {
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index d8f5e0a..95649eb 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -682,7 +682,7 @@
 	}
 
 	df = tnl_params->frag_off;
-	if (skb->protocol == htons(ETH_P_IP))
+	if (skb->protocol == htons(ETH_P_IP) && !tunnel->ignore_df)
 		df |= (inner_iph->frag_off&htons(IP_DF));
 
 	max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr)
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 7e538f7..10d728b 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -293,7 +293,7 @@
 	 */
 	if (ext & (1 << (INET_DIAG_DCTCPINFO - 1)) ||
 	    ext & (1 << (INET_DIAG_VEGASINFO - 1))) {
-		memset(info, 0, sizeof(struct tcp_dctcp_info));
+		memset(&info->dctcp, 0, sizeof(info->dctcp));
 		if (inet_csk(sk)->icsk_ca_ops != &dctcp_reno) {
 			info->dctcp.dctcp_enabled = 1;
 			info->dctcp.dctcp_ce_state = (u16) ca->ce_state;
@@ -303,7 +303,7 @@
 		}
 
 		*attr = INET_DIAG_DCTCPINFO;
-		return sizeof(*info);
+		return sizeof(info->dctcp);
 	}
 	return 0;
 }
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index d6c8f4cd0..94d4aff 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3115,6 +3115,7 @@
 	long ca_rtt_us = -1L;
 	struct sk_buff *skb;
 	u32 pkts_acked = 0;
+	u32 last_in_flight = 0;
 	bool rtt_update;
 	int flag = 0;
 
@@ -3154,6 +3155,7 @@
 			if (!first_ackt.v64)
 				first_ackt = last_ackt;
 
+			last_in_flight = TCP_SKB_CB(skb)->tx.in_flight;
 			reord = min(pkts_acked, reord);
 			if (!after(scb->end_seq, tp->high_seq))
 				flag |= FLAG_ORIG_SACK_ACKED;
@@ -3250,7 +3252,8 @@
 
 	if (icsk->icsk_ca_ops->pkts_acked) {
 		struct ack_sample sample = { .pkts_acked = pkts_acked,
-					     .rtt_us = ca_rtt_us };
+					     .rtt_us = ca_rtt_us,
+					     .in_flight = last_in_flight };
 
 		icsk->icsk_ca_ops->pkts_acked(sk, &sample);
 	}
@@ -5159,6 +5162,7 @@
 				  const struct tcphdr *th, int syn_inerr)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	bool rst_seq_match = false;
 
 	/* RFC1323: H1. Apply PAWS check first. */
 	if (tcp_fast_parse_options(skb, th, tp) && tp->rx_opt.saw_tstamp &&
@@ -5195,13 +5199,32 @@
 
 	/* Step 2: check RST bit */
 	if (th->rst) {
-		/* RFC 5961 3.2 :
-		 * If sequence number exactly matches RCV.NXT, then
+		/* RFC 5961 3.2 (extend to match against SACK too if available):
+		 * If seq num matches RCV.NXT or the right-most SACK block,
+		 * then
 		 *     RESET the connection
 		 * else
 		 *     Send a challenge ACK
 		 */
-		if (TCP_SKB_CB(skb)->seq == tp->rcv_nxt)
+		if (TCP_SKB_CB(skb)->seq == tp->rcv_nxt) {
+			rst_seq_match = true;
+		} else if (tcp_is_sack(tp) && tp->rx_opt.num_sacks > 0) {
+			struct tcp_sack_block *sp = &tp->selective_acks[0];
+			int max_sack = sp[0].end_seq;
+			int this_sack;
+
+			for (this_sack = 1; this_sack < tp->rx_opt.num_sacks;
+			     ++this_sack) {
+				max_sack = after(sp[this_sack].end_seq,
+						 max_sack) ?
+					sp[this_sack].end_seq : max_sack;
+			}
+
+			if (TCP_SKB_CB(skb)->seq == max_sack)
+				rst_seq_match = true;
+		}
+
+		if (rst_seq_match)
 			tcp_reset(sk);
 		else
 			tcp_send_challenge_ack(sk, skb);
diff --git a/net/ipv4/tcp_nv.c b/net/ipv4/tcp_nv.c
new file mode 100644
index 0000000..5de82a8
--- /dev/null
+++ b/net/ipv4/tcp_nv.c
@@ -0,0 +1,476 @@
+/*
+ * TCP NV: TCP with Congestion Avoidance
+ *
+ * TCP-NV is a successor of TCP-Vegas that has been developed to
+ * deal with the issues that occur in modern networks.
+ * Like TCP-Vegas, TCP-NV supports true congestion avoidance,
+ * the ability to detect congestion before packet losses occur.
+ * When congestion (queue buildup) starts to occur, TCP-NV
+ * predicts what the cwnd size should be for the current
+ * throughput and it reduces the cwnd proportionally to
+ * the difference between the current cwnd and the predicted cwnd.
+ *
+ * NV is only recommeneded for traffic within a data center, and when
+ * all the flows are NV (at least those within the data center). This
+ * is due to the inherent unfairness between flows using losses to
+ * detect congestion (congestion control) and those that use queue
+ * buildup to detect congestion (congestion avoidance).
+ *
+ * Note: High NIC coalescence values may lower the performance of NV
+ * due to the increased noise in RTT values. In particular, we have
+ * seen issues with rx-frames values greater than 8.
+ *
+ * TODO:
+ * 1) Add mechanism to deal with reverse congestion.
+ */
+
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/math64.h>
+#include <net/tcp.h>
+#include <linux/inet_diag.h>
+
+/* TCP NV parameters
+ *
+ * nv_pad		Max number of queued packets allowed in network
+ * nv_pad_buffer	Do not grow cwnd if this closed to nv_pad
+ * nv_reset_period	How often (in) seconds)to reset min_rtt
+ * nv_min_cwnd		Don't decrease cwnd below this if there are no losses
+ * nv_cong_dec_mult	Decrease cwnd by X% (30%) of congestion when detected
+ * nv_ssthresh_factor	On congestion set ssthresh to this * <desired cwnd> / 8
+ * nv_rtt_factor	RTT averaging factor
+ * nv_loss_dec_factor	Decrease cwnd by this (50%) when losses occur
+ * nv_dec_eval_min_calls	Wait this many RTT measurements before dec cwnd
+ * nv_inc_eval_min_calls	Wait this many RTT measurements before inc cwnd
+ * nv_ssthresh_eval_min_calls	Wait this many RTT measurements before stopping
+ *				slow-start due to congestion
+ * nv_stop_rtt_cnt	Only grow cwnd for this many RTTs after non-congestion
+ * nv_rtt_min_cnt	Wait these many RTTs before making congesion decision
+ * nv_cwnd_growth_rate_neg
+ * nv_cwnd_growth_rate_pos
+ *	How quickly to double growth rate (not rate) of cwnd when not
+ *	congested. One value (nv_cwnd_growth_rate_neg) for when
+ *	rate < 1 pkt/RTT (after losses). The other (nv_cwnd_growth_rate_pos)
+ *	otherwise.
+ */
+
+static int nv_pad __read_mostly = 10;
+static int nv_pad_buffer __read_mostly = 2;
+static int nv_reset_period __read_mostly = 5; /* in seconds */
+static int nv_min_cwnd __read_mostly = 2;
+static int nv_cong_dec_mult __read_mostly = 30 * 128 / 100; /* = 30% */
+static int nv_ssthresh_factor __read_mostly = 8; /* = 1 */
+static int nv_rtt_factor __read_mostly = 128; /* = 1/2*old + 1/2*new */
+static int nv_loss_dec_factor __read_mostly = 512; /* => 50% */
+static int nv_cwnd_growth_rate_neg __read_mostly = 8;
+static int nv_cwnd_growth_rate_pos __read_mostly; /* 0 => fixed like Reno */
+static int nv_dec_eval_min_calls __read_mostly = 60;
+static int nv_inc_eval_min_calls __read_mostly = 20;
+static int nv_ssthresh_eval_min_calls __read_mostly = 30;
+static int nv_stop_rtt_cnt __read_mostly = 10;
+static int nv_rtt_min_cnt __read_mostly = 2;
+
+module_param(nv_pad, int, 0644);
+MODULE_PARM_DESC(nv_pad, "max queued packets allowed in network");
+module_param(nv_reset_period, int, 0644);
+MODULE_PARM_DESC(nv_reset_period, "nv_min_rtt reset period (secs)");
+module_param(nv_min_cwnd, int, 0644);
+MODULE_PARM_DESC(nv_min_cwnd, "NV will not decrease cwnd below this value"
+		 " without losses");
+
+/* TCP NV Parameters */
+struct tcpnv {
+	unsigned long nv_min_rtt_reset_jiffies;  /* when to switch to
+						  * nv_min_rtt_new */
+	s8  cwnd_growth_factor;	/* Current cwnd growth factor,
+				 * < 0 => less than 1 packet/RTT */
+	u8  available8;
+	u16 available16;
+	u32 loss_cwnd;	/* cwnd at last loss */
+	u8  nv_allow_cwnd_growth:1, /* whether cwnd can grow */
+		nv_reset:1,	    /* whether to reset values */
+		nv_catchup:1;	    /* whether we are growing because
+				     * of temporary cwnd decrease */
+	u8  nv_eval_call_cnt;	/* call count since last eval */
+	u8  nv_min_cwnd;	/* nv won't make a ca decision if cwnd is
+				 * smaller than this. It may grow to handle
+				 * TSO, LRO and interrupt coalescence because
+				 * with these a small cwnd cannot saturate
+				 * the link. Note that this is different from
+				 * the file local nv_min_cwnd */
+	u8  nv_rtt_cnt;		/* RTTs without making ca decision */;
+	u32 nv_last_rtt;	/* last rtt */
+	u32 nv_min_rtt;		/* active min rtt. Used to determine slope */
+	u32 nv_min_rtt_new;	/* min rtt for future use */
+	u32 nv_rtt_max_rate;	/* max rate seen during current RTT */
+	u32 nv_rtt_start_seq;	/* current RTT ends when packet arrives
+				 * acking beyond nv_rtt_start_seq */
+	u32 nv_last_snd_una;	/* Previous value of tp->snd_una. It is
+				 * used to determine bytes acked since last
+				 * call to bictcp_acked */
+	u32 nv_no_cong_cnt;	/* Consecutive no congestion decisions */
+};
+
+#define NV_INIT_RTT	  U32_MAX
+#define NV_MIN_CWND	  4
+#define NV_MIN_CWND_GROW  2
+#define NV_TSO_CWND_BOUND 80
+
+static inline void tcpnv_reset(struct tcpnv *ca, struct sock *sk)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	ca->nv_reset = 0;
+	ca->loss_cwnd = 0;
+	ca->nv_no_cong_cnt = 0;
+	ca->nv_rtt_cnt = 0;
+	ca->nv_last_rtt = 0;
+	ca->nv_rtt_max_rate = 0;
+	ca->nv_rtt_start_seq = tp->snd_una;
+	ca->nv_eval_call_cnt = 0;
+	ca->nv_last_snd_una = tp->snd_una;
+}
+
+static void tcpnv_init(struct sock *sk)
+{
+	struct tcpnv *ca = inet_csk_ca(sk);
+
+	tcpnv_reset(ca, sk);
+
+	ca->nv_allow_cwnd_growth = 1;
+	ca->nv_min_rtt_reset_jiffies = jiffies + 2 * HZ;
+	ca->nv_min_rtt = NV_INIT_RTT;
+	ca->nv_min_rtt_new = NV_INIT_RTT;
+	ca->nv_min_cwnd = NV_MIN_CWND;
+	ca->nv_catchup = 0;
+	ca->cwnd_growth_factor = 0;
+}
+
+static void tcpnv_cong_avoid(struct sock *sk, u32 ack, u32 acked)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct tcpnv *ca = inet_csk_ca(sk);
+	u32 cnt;
+
+	if (!tcp_is_cwnd_limited(sk))
+		return;
+
+	/* Only grow cwnd if NV has not detected congestion */
+	if (!ca->nv_allow_cwnd_growth)
+		return;
+
+	if (tcp_in_slow_start(tp)) {
+		acked = tcp_slow_start(tp, acked);
+		if (!acked)
+			return;
+	}
+
+	if (ca->cwnd_growth_factor < 0) {
+		cnt = tp->snd_cwnd << -ca->cwnd_growth_factor;
+		tcp_cong_avoid_ai(tp, cnt, acked);
+	} else {
+		cnt = max(4U, tp->snd_cwnd >> ca->cwnd_growth_factor);
+		tcp_cong_avoid_ai(tp, cnt, acked);
+	}
+}
+
+static u32 tcpnv_recalc_ssthresh(struct sock *sk)
+{
+	const struct tcp_sock *tp = tcp_sk(sk);
+	struct tcpnv *ca = inet_csk_ca(sk);
+
+	ca->loss_cwnd = tp->snd_cwnd;
+	return max((tp->snd_cwnd * nv_loss_dec_factor) >> 10, 2U);
+}
+
+static u32 tcpnv_undo_cwnd(struct sock *sk)
+{
+	struct tcpnv *ca = inet_csk_ca(sk);
+
+	return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd);
+}
+
+static void tcpnv_state(struct sock *sk, u8 new_state)
+{
+	struct tcpnv *ca = inet_csk_ca(sk);
+
+	if (new_state == TCP_CA_Open && ca->nv_reset) {
+		tcpnv_reset(ca, sk);
+	} else if (new_state == TCP_CA_Loss || new_state == TCP_CA_CWR ||
+		new_state == TCP_CA_Recovery) {
+		ca->nv_reset = 1;
+		ca->nv_allow_cwnd_growth = 0;
+		if (new_state == TCP_CA_Loss) {
+			/* Reset cwnd growth factor to Reno value */
+			if (ca->cwnd_growth_factor > 0)
+				ca->cwnd_growth_factor = 0;
+			/* Decrease growth rate if allowed */
+			if (nv_cwnd_growth_rate_neg > 0 &&
+			    ca->cwnd_growth_factor > -8)
+				ca->cwnd_growth_factor--;
+		}
+	}
+}
+
+/* Do congestion avoidance calculations for TCP-NV
+ */
+static void tcpnv_acked(struct sock *sk, const struct ack_sample *sample)
+{
+	const struct inet_connection_sock *icsk = inet_csk(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct tcpnv *ca = inet_csk_ca(sk);
+	unsigned long now = jiffies;
+	s64 rate64 = 0;
+	u32 rate, max_win, cwnd_by_slope;
+	u32 avg_rtt;
+	u32 bytes_acked = 0;
+
+	/* Some calls are for duplicates without timetamps */
+	if (sample->rtt_us < 0)
+		return;
+
+	/* If not in TCP_CA_Open or TCP_CA_Disorder states, skip. */
+	if (icsk->icsk_ca_state != TCP_CA_Open &&
+	    icsk->icsk_ca_state != TCP_CA_Disorder)
+		return;
+
+	/* Stop cwnd growth if we were in catch up mode */
+	if (ca->nv_catchup && tp->snd_cwnd >= nv_min_cwnd) {
+		ca->nv_catchup = 0;
+		ca->nv_allow_cwnd_growth = 0;
+	}
+
+	bytes_acked = tp->snd_una - ca->nv_last_snd_una;
+	ca->nv_last_snd_una = tp->snd_una;
+
+	if (sample->in_flight == 0)
+		return;
+
+	/* Calculate moving average of RTT */
+	if (nv_rtt_factor > 0) {
+		if (ca->nv_last_rtt > 0) {
+			avg_rtt = (((u64)sample->rtt_us) * nv_rtt_factor +
+				   ((u64)ca->nv_last_rtt)
+				   * (256 - nv_rtt_factor)) >> 8;
+		} else {
+			avg_rtt = sample->rtt_us;
+			ca->nv_min_rtt = avg_rtt << 1;
+		}
+		ca->nv_last_rtt = avg_rtt;
+	} else {
+		avg_rtt = sample->rtt_us;
+	}
+
+	/* rate in 100's bits per second */
+	rate64 = ((u64)sample->in_flight) * 8000000;
+	rate = (u32)div64_u64(rate64, (u64)(avg_rtt * 100));
+
+	/* Remember the maximum rate seen during this RTT
+	 * Note: It may be more than one RTT. This function should be
+	 *       called at least nv_dec_eval_min_calls times.
+	 */
+	if (ca->nv_rtt_max_rate < rate)
+		ca->nv_rtt_max_rate = rate;
+
+	/* We have valid information, increment counter */
+	if (ca->nv_eval_call_cnt < 255)
+		ca->nv_eval_call_cnt++;
+
+	/* update min rtt if necessary */
+	if (avg_rtt < ca->nv_min_rtt)
+		ca->nv_min_rtt = avg_rtt;
+
+	/* update future min_rtt if necessary */
+	if (avg_rtt < ca->nv_min_rtt_new)
+		ca->nv_min_rtt_new = avg_rtt;
+
+	/* nv_min_rtt is updated with the minimum (possibley averaged) rtt
+	 * seen in the last sysctl_tcp_nv_reset_period seconds (i.e. a
+	 * warm reset). This new nv_min_rtt will be continued to be updated
+	 * and be used for another sysctl_tcp_nv_reset_period seconds,
+	 * when it will be updated again.
+	 * In practice we introduce some randomness, so the actual period used
+	 * is chosen randomly from the range:
+	 *   [sysctl_tcp_nv_reset_period*3/4, sysctl_tcp_nv_reset_period*5/4)
+	 */
+	if (time_after_eq(now, ca->nv_min_rtt_reset_jiffies)) {
+		unsigned char rand;
+
+		ca->nv_min_rtt = ca->nv_min_rtt_new;
+		ca->nv_min_rtt_new = NV_INIT_RTT;
+		get_random_bytes(&rand, 1);
+		ca->nv_min_rtt_reset_jiffies =
+			now + ((nv_reset_period * (384 + rand) * HZ) >> 9);
+		/* Every so often we decrease ca->nv_min_cwnd in case previous
+		 *  value is no longer accurate.
+		 */
+		ca->nv_min_cwnd = max(ca->nv_min_cwnd / 2, NV_MIN_CWND);
+	}
+
+	/* Once per RTT check if we need to do congestion avoidance */
+	if (before(ca->nv_rtt_start_seq, tp->snd_una)) {
+		ca->nv_rtt_start_seq = tp->snd_nxt;
+		if (ca->nv_rtt_cnt < 0xff)
+			/* Increase counter for RTTs without CA decision */
+			ca->nv_rtt_cnt++;
+
+		/* If this function is only called once within an RTT
+		 * the cwnd is probably too small (in some cases due to
+		 * tso, lro or interrupt coalescence), so we increase
+		 * ca->nv_min_cwnd.
+		 */
+		if (ca->nv_eval_call_cnt == 1 &&
+		    bytes_acked >= (ca->nv_min_cwnd - 1) * tp->mss_cache &&
+		    ca->nv_min_cwnd < (NV_TSO_CWND_BOUND + 1)) {
+			ca->nv_min_cwnd = min(ca->nv_min_cwnd
+					      + NV_MIN_CWND_GROW,
+					      NV_TSO_CWND_BOUND + 1);
+			ca->nv_rtt_start_seq = tp->snd_nxt +
+				ca->nv_min_cwnd * tp->mss_cache;
+			ca->nv_eval_call_cnt = 0;
+			ca->nv_allow_cwnd_growth = 1;
+			return;
+		}
+
+		/* Find the ideal cwnd for current rate from slope
+		 * slope = 80000.0 * mss / nv_min_rtt
+		 * cwnd_by_slope = nv_rtt_max_rate / slope
+		 */
+		cwnd_by_slope = (u32)
+			div64_u64(((u64)ca->nv_rtt_max_rate) * ca->nv_min_rtt,
+				  (u64)(80000 * tp->mss_cache));
+		max_win = cwnd_by_slope + nv_pad;
+
+		/* If cwnd > max_win, decrease cwnd
+		 * if cwnd < max_win, grow cwnd
+		 * else leave the same
+		 */
+		if (tp->snd_cwnd > max_win) {
+			/* there is congestion, check that it is ok
+			 * to make a CA decision
+			 * 1. We should have at least nv_dec_eval_min_calls
+			 *    data points before making a CA  decision
+			 * 2. We only make a congesion decision after
+			 *    nv_rtt_min_cnt RTTs
+			 */
+			if (ca->nv_rtt_cnt < nv_rtt_min_cnt) {
+				return;
+			} else if (tp->snd_ssthresh == TCP_INFINITE_SSTHRESH) {
+				if (ca->nv_eval_call_cnt <
+				    nv_ssthresh_eval_min_calls)
+					return;
+				/* otherwise we will decrease cwnd */
+			} else if (ca->nv_eval_call_cnt <
+				   nv_dec_eval_min_calls) {
+				if (ca->nv_allow_cwnd_growth &&
+				    ca->nv_rtt_cnt > nv_stop_rtt_cnt)
+					ca->nv_allow_cwnd_growth = 0;
+				return;
+			}
+
+			/* We have enough data to determine we are congested */
+			ca->nv_allow_cwnd_growth = 0;
+			tp->snd_ssthresh =
+				(nv_ssthresh_factor * max_win) >> 3;
+			if (tp->snd_cwnd - max_win > 2) {
+				/* gap > 2, we do exponential cwnd decrease */
+				int dec;
+
+				dec = max(2U, ((tp->snd_cwnd - max_win) *
+					       nv_cong_dec_mult) >> 7);
+				tp->snd_cwnd -= dec;
+			} else if (nv_cong_dec_mult > 0) {
+				tp->snd_cwnd = max_win;
+			}
+			if (ca->cwnd_growth_factor > 0)
+				ca->cwnd_growth_factor = 0;
+			ca->nv_no_cong_cnt = 0;
+		} else if (tp->snd_cwnd <= max_win - nv_pad_buffer) {
+			/* There is no congestion, grow cwnd if allowed*/
+			if (ca->nv_eval_call_cnt < nv_inc_eval_min_calls)
+				return;
+
+			ca->nv_allow_cwnd_growth = 1;
+			ca->nv_no_cong_cnt++;
+			if (ca->cwnd_growth_factor < 0 &&
+			    nv_cwnd_growth_rate_neg > 0 &&
+			    ca->nv_no_cong_cnt > nv_cwnd_growth_rate_neg) {
+				ca->cwnd_growth_factor++;
+				ca->nv_no_cong_cnt = 0;
+			} else if (ca->cwnd_growth_factor >= 0 &&
+				   nv_cwnd_growth_rate_pos > 0 &&
+				   ca->nv_no_cong_cnt >
+				   nv_cwnd_growth_rate_pos) {
+				ca->cwnd_growth_factor++;
+				ca->nv_no_cong_cnt = 0;
+			}
+		} else {
+			/* cwnd is in-between, so do nothing */
+			return;
+		}
+
+		/* update state */
+		ca->nv_eval_call_cnt = 0;
+		ca->nv_rtt_cnt = 0;
+		ca->nv_rtt_max_rate = 0;
+
+		/* Don't want to make cwnd < nv_min_cwnd
+		 * (it wasn't before, if it is now is because nv
+		 *  decreased it).
+		 */
+		if (tp->snd_cwnd < nv_min_cwnd)
+			tp->snd_cwnd = nv_min_cwnd;
+	}
+}
+
+/* Extract info for Tcp socket info provided via netlink */
+size_t tcpnv_get_info(struct sock *sk, u32 ext, int *attr,
+		      union tcp_cc_info *info)
+{
+	const struct tcpnv *ca = inet_csk_ca(sk);
+
+	if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) {
+		info->vegas.tcpv_enabled = 1;
+		info->vegas.tcpv_rttcnt = ca->nv_rtt_cnt;
+		info->vegas.tcpv_rtt = ca->nv_last_rtt;
+		info->vegas.tcpv_minrtt = ca->nv_min_rtt;
+
+		*attr = INET_DIAG_VEGASINFO;
+		return sizeof(struct tcpvegas_info);
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(tcpnv_get_info);
+
+static struct tcp_congestion_ops tcpnv __read_mostly = {
+	.init		= tcpnv_init,
+	.ssthresh	= tcpnv_recalc_ssthresh,
+	.cong_avoid	= tcpnv_cong_avoid,
+	.set_state	= tcpnv_state,
+	.undo_cwnd	= tcpnv_undo_cwnd,
+	.pkts_acked     = tcpnv_acked,
+	.get_info	= tcpnv_get_info,
+
+	.owner		= THIS_MODULE,
+	.name		= "nv",
+};
+
+static int __init tcpnv_register(void)
+{
+	BUILD_BUG_ON(sizeof(struct tcpnv) > ICSK_CA_PRIV_SIZE);
+
+	return tcp_register_congestion_control(&tcpnv);
+}
+
+static void __exit tcpnv_unregister(void)
+{
+	tcp_unregister_congestion_control(&tcpnv);
+}
+
+module_init(tcpnv_register);
+module_exit(tcpnv_unregister);
+
+MODULE_AUTHOR("Lawrence Brakmo");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("TCP NV");
+MODULE_VERSION("1.0");
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 8bd9911..b1bcba0 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -911,9 +911,12 @@
 	int err;
 
 	BUG_ON(!skb || !tcp_skb_pcount(skb));
+	tp = tcp_sk(sk);
 
 	if (clone_it) {
 		skb_mstamp_get(&skb->skb_mstamp);
+		TCP_SKB_CB(skb)->tx.in_flight = TCP_SKB_CB(skb)->end_seq
+			- tp->snd_una;
 
 		if (unlikely(skb_cloned(skb)))
 			skb = pskb_copy(skb, gfp_mask);
@@ -924,7 +927,6 @@
 	}
 
 	inet = inet_sk(sk);
-	tp = tcp_sk(sk);
 	tcb = TCP_SKB_CB(skb);
 	memset(&opts, 0, sizeof(opts));
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index d56c055..0ff31d9 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1618,12 +1618,12 @@
 		}
 	}
 
-	if (rcu_access_pointer(sk->sk_filter)) {
-		if (udp_lib_checksum_complete(skb))
+	if (rcu_access_pointer(sk->sk_filter) &&
+	    udp_lib_checksum_complete(skb))
 			goto csum_error;
-		if (sk_filter(sk, skb))
-			goto drop;
-	}
+
+	if (sk_filter(sk, skb))
+		goto drop;
 
 	udp_csum_pull_header(skb);
 	if (sk_rcvqueues_full(sk, sk->sk_rcvbuf)) {
diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c
index 47f12c7..58bd39f 100644
--- a/net/ipv4/udp_tunnel.c
+++ b/net/ipv4/udp_tunnel.c
@@ -76,6 +76,67 @@
 }
 EXPORT_SYMBOL_GPL(setup_udp_tunnel_sock);
 
+void udp_tunnel_push_rx_port(struct net_device *dev, struct socket *sock,
+			     unsigned short type)
+{
+	struct sock *sk = sock->sk;
+	struct udp_tunnel_info ti;
+
+	if (!dev->netdev_ops->ndo_udp_tunnel_add)
+		return;
+
+	ti.type = type;
+	ti.sa_family = sk->sk_family;
+	ti.port = inet_sk(sk)->inet_sport;
+
+	dev->netdev_ops->ndo_udp_tunnel_add(dev, &ti);
+}
+EXPORT_SYMBOL_GPL(udp_tunnel_push_rx_port);
+
+/* Notify netdevs that UDP port started listening */
+void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type)
+{
+	struct sock *sk = sock->sk;
+	struct net *net = sock_net(sk);
+	struct udp_tunnel_info ti;
+	struct net_device *dev;
+
+	ti.type = type;
+	ti.sa_family = sk->sk_family;
+	ti.port = inet_sk(sk)->inet_sport;
+
+	rcu_read_lock();
+	for_each_netdev_rcu(net, dev) {
+		if (!dev->netdev_ops->ndo_udp_tunnel_add)
+			continue;
+		dev->netdev_ops->ndo_udp_tunnel_add(dev, &ti);
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(udp_tunnel_notify_add_rx_port);
+
+/* Notify netdevs that UDP port is no more listening */
+void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type)
+{
+	struct sock *sk = sock->sk;
+	struct net *net = sock_net(sk);
+	struct udp_tunnel_info ti;
+	struct net_device *dev;
+
+	ti.type = type;
+	ti.sa_family = sk->sk_family;
+	ti.port = inet_sk(sk)->inet_sport;
+
+	rcu_read_lock();
+	for_each_netdev_rcu(net, dev) {
+		if (!dev->netdev_ops->ndo_udp_tunnel_del)
+			continue;
+		dev->netdev_ops->ndo_udp_tunnel_del(dev, &ti);
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(udp_tunnel_notify_del_rx_port);
+
 void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb,
 			 __be32 src, __be32 dst, __u8 tos, __u8 ttl,
 			 __be16 df, __be16 src_port, __be16 dst_port,
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 7b0edb3..b644a23 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -295,7 +295,7 @@
 	{ }
 };
 
-static int __net_init xfrm4_net_sysctl_init(struct net *net)
+static __net_init int xfrm4_net_sysctl_init(struct net *net)
 {
 	struct ctl_table *table;
 	struct ctl_table_header *hdr;
@@ -323,7 +323,7 @@
 	return -ENOMEM;
 }
 
-static void __net_exit xfrm4_net_sysctl_exit(struct net *net)
+static __net_exit void xfrm4_net_sysctl_exit(struct net *net)
 {
 	struct ctl_table *table;
 
@@ -336,12 +336,12 @@
 		kfree(table);
 }
 #else /* CONFIG_SYSCTL */
-static int inline xfrm4_net_sysctl_init(struct net *net)
+static inline int xfrm4_net_sysctl_init(struct net *net)
 {
 	return 0;
 }
 
-static void inline xfrm4_net_sysctl_exit(struct net *net)
+static inline void xfrm4_net_sysctl_exit(struct net *net)
 {
 }
 #endif
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 47f837a..a1f6b7b 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1524,6 +1524,28 @@
 	return hiscore_idx;
 }
 
+static int ipv6_get_saddr_master(struct net *net,
+				 const struct net_device *dst_dev,
+				 const struct net_device *master,
+				 struct ipv6_saddr_dst *dst,
+				 struct ipv6_saddr_score *scores,
+				 int hiscore_idx)
+{
+	struct inet6_dev *idev;
+
+	idev = __in6_dev_get(dst_dev);
+	if (idev)
+		hiscore_idx = __ipv6_dev_get_saddr(net, dst, idev,
+						   scores, hiscore_idx);
+
+	idev = __in6_dev_get(master);
+	if (idev)
+		hiscore_idx = __ipv6_dev_get_saddr(net, dst, idev,
+						   scores, hiscore_idx);
+
+	return hiscore_idx;
+}
+
 int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev,
 		       const struct in6_addr *daddr, unsigned int prefs,
 		       struct in6_addr *saddr)
@@ -1577,13 +1599,39 @@
 		if (idev)
 			hiscore_idx = __ipv6_dev_get_saddr(net, &dst, idev, scores, hiscore_idx);
 	} else {
+		const struct net_device *master;
+		int master_idx = 0;
+
+		/* if dst_dev exists and is enslaved to an L3 device, then
+		 * prefer addresses from dst_dev and then the master over
+		 * any other enslaved devices in the L3 domain.
+		 */
+		master = l3mdev_master_dev_rcu(dst_dev);
+		if (master) {
+			master_idx = master->ifindex;
+
+			hiscore_idx = ipv6_get_saddr_master(net, dst_dev,
+							    master, &dst,
+							    scores, hiscore_idx);
+
+			if (scores[hiscore_idx].ifa)
+				goto out;
+		}
+
 		for_each_netdev_rcu(net, dev) {
+			/* only consider addresses on devices in the
+			 * same L3 domain
+			 */
+			if (l3mdev_master_ifindex_rcu(dev) != master_idx)
+				continue;
 			idev = __in6_dev_get(dev);
 			if (!idev)
 				continue;
 			hiscore_idx = __ipv6_dev_get_saddr(net, &dst, idev, scores, hiscore_idx);
 		}
 	}
+
+out:
 	rcu_read_unlock();
 
 	hiscore = &scores[hiscore_idx];
@@ -2254,7 +2302,7 @@
 		return ERR_PTR(-EACCES);
 
 	/* Add default multicast route */
-	if (!(dev->flags & IFF_LOOPBACK))
+	if (!(dev->flags & IFF_LOOPBACK) && !netif_is_l3_master(dev))
 		addrconf_add_mroute(dev);
 
 	return idev;
@@ -2333,12 +2381,109 @@
 	       idev->addr_gen_mode == IN6_ADDR_GEN_MODE_RANDOM;
 }
 
+int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev,
+				 const struct prefix_info *pinfo,
+				 struct inet6_dev *in6_dev,
+				 const struct in6_addr *addr, int addr_type,
+				 u32 addr_flags, bool sllao, bool tokenized,
+				 __u32 valid_lft, u32 prefered_lft)
+{
+	struct inet6_ifaddr *ifp = ipv6_get_ifaddr(net, addr, dev, 1);
+	int create = 0, update_lft = 0;
+
+	if (!ifp && valid_lft) {
+		int max_addresses = in6_dev->cnf.max_addresses;
+
+#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
+		if (in6_dev->cnf.optimistic_dad &&
+		    !net->ipv6.devconf_all->forwarding && sllao)
+			addr_flags |= IFA_F_OPTIMISTIC;
+#endif
+
+		/* Do not allow to create too much of autoconfigured
+		 * addresses; this would be too easy way to crash kernel.
+		 */
+		if (!max_addresses ||
+		    ipv6_count_addresses(in6_dev) < max_addresses)
+			ifp = ipv6_add_addr(in6_dev, addr, NULL,
+					    pinfo->prefix_len,
+					    addr_type&IPV6_ADDR_SCOPE_MASK,
+					    addr_flags, valid_lft,
+					    prefered_lft);
+
+		if (IS_ERR_OR_NULL(ifp))
+			return -1;
+
+		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);
+	}
+
+	if (ifp) {
+		u32 flags;
+		unsigned long now;
+		u32 stored_lft;
+
+		/* update lifetime (RFC2462 5.5.3 e) */
+		spin_lock_bh(&ifp->lock);
+		now = jiffies;
+		if (ifp->valid_lft > (now - ifp->tstamp) / HZ)
+			stored_lft = ifp->valid_lft - (now - ifp->tstamp) / HZ;
+		else
+			stored_lft = 0;
+		if (!update_lft && !create && stored_lft) {
+			const u32 minimum_lft = min_t(u32,
+				stored_lft, MIN_VALID_LIFETIME);
+			valid_lft = max(valid_lft, minimum_lft);
+
+			/* RFC4862 Section 5.5.3e:
+			 * "Note that the preferred lifetime of the
+			 *  corresponding address is always reset to
+			 *  the Preferred Lifetime in the received
+			 *  Prefix Information option, regardless of
+			 *  whether the valid lifetime is also reset or
+			 *  ignored."
+			 *
+			 * So we should always update prefered_lft here.
+			 */
+			update_lft = 1;
+		}
+
+		if (update_lft) {
+			ifp->valid_lft = valid_lft;
+			ifp->prefered_lft = prefered_lft;
+			ifp->tstamp = now;
+			flags = ifp->flags;
+			ifp->flags &= ~IFA_F_DEPRECATED;
+			spin_unlock_bh(&ifp->lock);
+
+			if (!(flags&IFA_F_TENTATIVE))
+				ipv6_ifa_notify(0, ifp);
+		} else
+			spin_unlock_bh(&ifp->lock);
+
+		manage_tempaddrs(in6_dev, ifp, valid_lft, prefered_lft,
+				 create, now);
+
+		in6_ifa_put(ifp);
+		addrconf_verify();
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(addrconf_prefix_rcv_add_addr);
+
 void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
 {
 	struct prefix_info *pinfo;
 	__u32 valid_lft;
 	__u32 prefered_lft;
-	int addr_type;
+	int addr_type, err;
 	u32 addr_flags = 0;
 	struct inet6_dev *in6_dev;
 	struct net *net = dev_net(dev);
@@ -2432,10 +2577,8 @@
 	/* Try to figure out our local address for this prefix */
 
 	if (pinfo->autoconf && in6_dev->cnf.autoconf) {
-		struct inet6_ifaddr *ifp;
 		struct in6_addr addr;
-		int create = 0, update_lft = 0;
-		bool tokenized = false;
+		bool tokenized = false, dev_addr_generated = false;
 
 		if (pinfo->prefix_len == 64) {
 			memcpy(&addr, &pinfo->prefix, 8);
@@ -2453,106 +2596,36 @@
 				goto ok;
 			} else if (ipv6_generate_eui64(addr.s6_addr + 8, dev) &&
 				   ipv6_inherit_eui64(addr.s6_addr + 8, in6_dev)) {
-				in6_dev_put(in6_dev);
-				return;
+				goto put;
+			} else {
+				dev_addr_generated = true;
 			}
 			goto ok;
 		}
 		net_dbg_ratelimited("IPv6 addrconf: prefix with wrong length %d\n",
 				    pinfo->prefix_len);
-		in6_dev_put(in6_dev);
-		return;
+		goto put;
 
 ok:
+		err = addrconf_prefix_rcv_add_addr(net, dev, pinfo, in6_dev,
+						   &addr, addr_type,
+						   addr_flags, sllao,
+						   tokenized, valid_lft,
+						   prefered_lft);
+		if (err)
+			goto put;
 
-		ifp = ipv6_get_ifaddr(net, &addr, dev, 1);
-
-		if (!ifp && valid_lft) {
-			int max_addresses = in6_dev->cnf.max_addresses;
-
-#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
-			if (in6_dev->cnf.optimistic_dad &&
-			    !net->ipv6.devconf_all->forwarding && sllao)
-				addr_flags |= IFA_F_OPTIMISTIC;
-#endif
-
-			/* Do not allow to create too much of autoconfigured
-			 * addresses; this would be too easy way to crash kernel.
-			 */
-			if (!max_addresses ||
-			    ipv6_count_addresses(in6_dev) < max_addresses)
-				ifp = ipv6_add_addr(in6_dev, &addr, NULL,
-						    pinfo->prefix_len,
-						    addr_type&IPV6_ADDR_SCOPE_MASK,
-						    addr_flags, valid_lft,
-						    prefered_lft);
-
-			if (IS_ERR_OR_NULL(ifp)) {
-				in6_dev_put(in6_dev);
-				return;
-			}
-
-			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);
-		}
-
-		if (ifp) {
-			u32 flags;
-			unsigned long now;
-			u32 stored_lft;
-
-			/* update lifetime (RFC2462 5.5.3 e) */
-			spin_lock_bh(&ifp->lock);
-			now = jiffies;
-			if (ifp->valid_lft > (now - ifp->tstamp) / HZ)
-				stored_lft = ifp->valid_lft - (now - ifp->tstamp) / HZ;
-			else
-				stored_lft = 0;
-			if (!update_lft && !create && stored_lft) {
-				const u32 minimum_lft = min_t(u32,
-					stored_lft, MIN_VALID_LIFETIME);
-				valid_lft = max(valid_lft, minimum_lft);
-
-				/* RFC4862 Section 5.5.3e:
-				 * "Note that the preferred lifetime of the
-				 *  corresponding address is always reset to
-				 *  the Preferred Lifetime in the received
-				 *  Prefix Information option, regardless of
-				 *  whether the valid lifetime is also reset or
-				 *  ignored."
-				 *
-				 * So we should always update prefered_lft here.
-				 */
-				update_lft = 1;
-			}
-
-			if (update_lft) {
-				ifp->valid_lft = valid_lft;
-				ifp->prefered_lft = prefered_lft;
-				ifp->tstamp = now;
-				flags = ifp->flags;
-				ifp->flags &= ~IFA_F_DEPRECATED;
-				spin_unlock_bh(&ifp->lock);
-
-				if (!(flags&IFA_F_TENTATIVE))
-					ipv6_ifa_notify(0, ifp);
-			} else
-				spin_unlock_bh(&ifp->lock);
-
-			manage_tempaddrs(in6_dev, ifp, valid_lft, prefered_lft,
-					 create, now);
-
-			in6_ifa_put(ifp);
-			addrconf_verify();
-		}
+		/* Ignore error case here because previous prefix add addr was
+		 * successful which will be notified.
+		 */
+		ndisc_ops_prefix_rcv_add_addr(net, dev, pinfo, in6_dev, &addr,
+					      addr_type, addr_flags, sllao,
+					      tokenized, valid_lft,
+					      prefered_lft,
+					      dev_addr_generated);
 	}
 	inet6_prefix_notify(RTM_NEWPREFIX, in6_dev, pinfo);
+put:
 	in6_dev_put(in6_dev);
 }
 
@@ -2947,8 +3020,8 @@
 	}
 }
 
-static void addrconf_add_linklocal(struct inet6_dev *idev,
-				   const struct in6_addr *addr, u32 flags)
+void addrconf_add_linklocal(struct inet6_dev *idev,
+			    const struct in6_addr *addr, u32 flags)
 {
 	struct inet6_ifaddr *ifp;
 	u32 addr_flags = flags | IFA_F_PERMANENT;
@@ -2967,6 +3040,7 @@
 		in6_ifa_put(ifp);
 	}
 }
+EXPORT_SYMBOL_GPL(addrconf_add_linklocal);
 
 static bool ipv6_reserved_interfaceid(struct in6_addr address)
 {
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index bfa86f0..2076c21 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -92,6 +92,12 @@
 module_param_named(autoconf, ipv6_defaults.autoconf, int, 0444);
 MODULE_PARM_DESC(autoconf, "Enable IPv6 address autoconfiguration on all interfaces");
 
+bool ipv6_mod_enabled(void)
+{
+	return disable_ipv6_mod == 0;
+}
+EXPORT_SYMBOL_GPL(ipv6_mod_enabled);
+
 static __inline__ struct ipv6_pinfo *inet6_sk_generic(struct sock *sk)
 {
 	const int offset = sk->sk_prot->obj_size - sizeof(struct ipv6_pinfo);
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index ed33abf..5857c1f 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -67,6 +67,7 @@
 	struct net *net = rule->fr_net;
 	pol_lookup_t lookup = arg->lookup_ptr;
 	int err = 0;
+	u32 tb_id;
 
 	switch (rule->action) {
 	case FR_ACT_TO_TBL:
@@ -86,7 +87,8 @@
 		goto discard_pkt;
 	}
 
-	table = fib6_get_table(net, rule->table);
+	tb_id = fib_rule_get_table(rule, arg);
+	table = fib6_get_table(net, tb_id);
 	if (!table) {
 		err = -EAGAIN;
 		goto out;
@@ -199,7 +201,7 @@
 	struct net *net = sock_net(skb->sk);
 	struct fib6_rule *rule6 = (struct fib6_rule *) rule;
 
-	if (rule->action == FR_ACT_TO_TBL) {
+	if (rule->action == FR_ACT_TO_TBL && !rule->l3mdev) {
 		if (rule->table == RT6_TABLE_UNSPEC)
 			goto errout;
 
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 4527285..fd11f58 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -388,7 +388,8 @@
 /*
  *	Send an ICMP message in response to a packet in error
  */
-static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
+static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
+		       const struct in6_addr *force_saddr)
 {
 	struct net *net = dev_net(skb->dev);
 	struct inet6_dev *idev = NULL;
@@ -475,6 +476,8 @@
 	memset(&fl6, 0, sizeof(fl6));
 	fl6.flowi6_proto = IPPROTO_ICMPV6;
 	fl6.daddr = hdr->saddr;
+	if (force_saddr)
+		saddr = force_saddr;
 	if (saddr)
 		fl6.saddr = *saddr;
 	fl6.flowi6_mark = mark;
@@ -502,12 +505,14 @@
 	else if (!fl6.flowi6_oif)
 		fl6.flowi6_oif = np->ucast_oif;
 
+	ipc6.tclass = np->tclass;
+	fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
+
 	dst = icmpv6_route_lookup(net, skb, sk, &fl6);
 	if (IS_ERR(dst))
 		goto out;
 
 	ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
-	ipc6.tclass = np->tclass;
 	ipc6.dontfrag = np->dontfrag;
 	ipc6.opt = NULL;
 
@@ -549,10 +554,75 @@
  */
 void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos)
 {
-	icmp6_send(skb, ICMPV6_PARAMPROB, code, pos);
+	icmp6_send(skb, ICMPV6_PARAMPROB, code, pos, NULL);
 	kfree_skb(skb);
 }
 
+/* Generate icmpv6 with type/code ICMPV6_DEST_UNREACH/ICMPV6_ADDR_UNREACH
+ * if sufficient data bytes are available
+ * @nhs is the size of the tunnel header(s) :
+ *  Either an IPv4 header for SIT encap
+ *         an IPv4 header + GRE header for GRE encap
+ */
+int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type,
+			       unsigned int data_len)
+{
+	struct in6_addr temp_saddr;
+	struct rt6_info *rt;
+	struct sk_buff *skb2;
+	u32 info = 0;
+
+	if (!pskb_may_pull(skb, nhs + sizeof(struct ipv6hdr) + 8))
+		return 1;
+
+	/* RFC 4884 (partial) support for ICMP extensions */
+	if (data_len < 128 || (data_len & 7) || skb->len < data_len)
+		data_len = 0;
+
+	skb2 = data_len ? skb_copy(skb, GFP_ATOMIC) : skb_clone(skb, GFP_ATOMIC);
+
+	if (!skb2)
+		return 1;
+
+	skb_dst_drop(skb2);
+	skb_pull(skb2, nhs);
+	skb_reset_network_header(skb2);
+
+	rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0, 0);
+
+	if (rt && rt->dst.dev)
+		skb2->dev = rt->dst.dev;
+
+	ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr, &temp_saddr);
+
+	if (data_len) {
+		/* RFC 4884 (partial) support :
+		 * insert 0 padding at the end, before the extensions
+		 */
+		__skb_push(skb2, nhs);
+		skb_reset_network_header(skb2);
+		memmove(skb2->data, skb2->data + nhs, data_len - nhs);
+		memset(skb2->data + data_len - nhs, 0, nhs);
+		/* RFC 4884 4.5 : Length is measured in 64-bit words,
+		 * and stored in reserved[0]
+		 */
+		info = (data_len/8) << 24;
+	}
+	if (type == ICMP_TIME_EXCEEDED)
+		icmp6_send(skb2, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT,
+			   info, &temp_saddr);
+	else
+		icmp6_send(skb2, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH,
+			   info, &temp_saddr);
+	if (rt)
+		ip6_rt_put(rt);
+
+	kfree_skb(skb2);
+
+	return 0;
+}
+EXPORT_SYMBOL(ip6_err_gen_icmpv6_unreach);
+
 static void icmpv6_echo_reply(struct sk_buff *skb)
 {
 	struct net *net = dev_net(skb->dev);
@@ -585,7 +655,7 @@
 	fl6.daddr = ipv6_hdr(skb)->saddr;
 	if (saddr)
 		fl6.saddr = *saddr;
-	fl6.flowi6_oif = l3mdev_fib_oif(skb->dev);
+	fl6.flowi6_oif = skb->dev->ifindex;
 	fl6.fl6_icmp_type = ICMPV6_ECHO_REPLY;
 	fl6.flowi6_mark = mark;
 	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
diff --git a/net/ipv6/ila/ila.h b/net/ipv6/ila/ila.h
index d08fd2d..e0170f6 100644
--- a/net/ipv6/ila/ila.h
+++ b/net/ipv6/ila/ila.h
@@ -109,7 +109,8 @@
 	return !!(ident.csum_neutral);
 }
 
-void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p);
+void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p,
+			     bool set_csum_neutral);
 
 void ila_init_saved_csum(struct ila_params *p);
 
diff --git a/net/ipv6/ila/ila_common.c b/net/ipv6/ila/ila_common.c
index 0e94042..ec9efbc 100644
--- a/net/ipv6/ila/ila_common.c
+++ b/net/ipv6/ila/ila_common.c
@@ -34,12 +34,12 @@
 	if (p->locator_match.v64) {
 		diff = p->csum_diff;
 	} else {
-		diff = compute_csum_diff8((__be32 *)iaddr,
-					  (__be32 *)&p->locator);
+		diff = compute_csum_diff8((__be32 *)&p->locator,
+					  (__be32 *)iaddr);
 	}
 
 	fval = (__force __wsum)(ila_csum_neutral_set(iaddr->ident) ?
-			~CSUM_NEUTRAL_FLAG : CSUM_NEUTRAL_FLAG);
+			CSUM_NEUTRAL_FLAG : ~CSUM_NEUTRAL_FLAG);
 
 	diff = csum_add(diff, fval);
 
@@ -103,7 +103,8 @@
 	iaddr->loc = p->locator;
 }
 
-void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p)
+void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p,
+			     bool set_csum_neutral)
 {
 	struct ipv6hdr *ip6h = ipv6_hdr(skb);
 	struct ila_addr *iaddr = ila_a2i(&ip6h->daddr);
@@ -114,7 +115,8 @@
 		 * is a locator being translated to a SIR address.
 		 * Perform (receiver) checksum-neutral translation.
 		 */
-		ila_csum_do_neutral(iaddr, p);
+		if (!set_csum_neutral)
+			ila_csum_do_neutral(iaddr, p);
 	} else {
 		switch (p->csum_mode) {
 		case ILA_CSUM_ADJUST_TRANSPORT:
@@ -138,8 +140,8 @@
 		return;
 
 	p->csum_diff = compute_csum_diff8(
-				(__be32 *)&p->locator_match,
-				(__be32 *)&p->locator);
+				(__be32 *)&p->locator,
+				(__be32 *)&p->locator_match);
 }
 
 static int __init ila_init(void)
diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c
index 1dfb641..c8314c6 100644
--- a/net/ipv6/ila/ila_lwt.c
+++ b/net/ipv6/ila/ila_lwt.c
@@ -26,7 +26,7 @@
 	if (skb->protocol != htons(ETH_P_IPV6))
 		goto drop;
 
-	ila_update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate));
+	ila_update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate), true);
 
 	return dst->lwtstate->orig_output(net, sk, skb);
 
@@ -42,7 +42,7 @@
 	if (skb->protocol != htons(ETH_P_IPV6))
 		goto drop;
 
-	ila_update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate));
+	ila_update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate), false);
 
 	return dst->lwtstate->orig_input(skb);
 
diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c
index a90e572..e6eca5f 100644
--- a/net/ipv6/ila/ila_xlat.c
+++ b/net/ipv6/ila/ila_xlat.c
@@ -210,14 +210,14 @@
 	}
 }
 
-static int ila_xlat_addr(struct sk_buff *skb);
+static int ila_xlat_addr(struct sk_buff *skb, bool set_csum_neutral);
 
 static unsigned int
 ila_nf_input(void *priv,
 	     struct sk_buff *skb,
 	     const struct nf_hook_state *state)
 {
-	ila_xlat_addr(skb);
+	ila_xlat_addr(skb, false);
 	return NF_ACCEPT;
 }
 
@@ -597,7 +597,7 @@
 	.size = sizeof(struct ila_net),
 };
 
-static int ila_xlat_addr(struct sk_buff *skb)
+static int ila_xlat_addr(struct sk_buff *skb, bool set_csum_neutral)
 {
 	struct ila_map *ila;
 	struct ipv6hdr *ip6h = ipv6_hdr(skb);
@@ -616,7 +616,7 @@
 
 	ila = ila_lookup_wildcards(iaddr, skb->dev->ifindex, ilan);
 	if (ila)
-		ila_update_ipv6_locator(skb, &ila->xp.ip);
+		ila_update_ipv6_locator(skb, &ila->xp.ip, set_csum_neutral);
 
 	rcu_read_unlock();
 
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index f4ac284..fdc9de2 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1256,6 +1256,8 @@
 	if (ret)
 		return ret;
 
+	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
+
 	tunnel = netdev_priv(dev);
 
 	ip6gre_tnl_link_config(tunnel, 1);
@@ -1289,6 +1291,7 @@
 
 	dev->features |= NETIF_F_NETNS_LOCAL;
 	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
+	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 }
 
 static bool ip6gre_netlink_encap_parms(struct nlattr *data[],
diff --git a/net/ipv6/ip6_icmp.c b/net/ipv6/ip6_icmp.c
index 14dacc5..713676f 100644
--- a/net/ipv6/ip6_icmp.c
+++ b/net/ipv6/ip6_icmp.c
@@ -39,7 +39,7 @@
 
 	if (!send)
 		goto out;
-	send(skb, type, code, info);
+	send(skb, type, code, info, NULL);
 out:
 	rcu_read_unlock();
 }
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 94611e4..aacfb4b 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -323,6 +323,7 @@
 		       dev_net(skb->dev), NULL, skb, skb->dev, NULL,
 		       ip6_input_finish);
 }
+EXPORT_SYMBOL_GPL(ip6_input);
 
 int ip6_mc_input(struct sk_buff *skb)
 {
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 6b2f60a..1dfc402 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -910,6 +910,13 @@
 	int err;
 	int flags = 0;
 
+	if (ipv6_addr_any(&fl6->saddr) && fl6->flowi6_oif &&
+	    (!*dst || !(*dst)->error)) {
+		err = l3mdev_get_saddr6(net, sk, fl6);
+		if (err)
+			goto out_err;
+	}
+
 	/* The correct way to handle this would be to do
 	 * ip6_route_get_saddr, and then ip6_route_output; however,
 	 * the route-specific preferred source forces the
@@ -999,10 +1006,11 @@
 	return 0;
 
 out_err_release:
-	if (err == -ENETUNREACH)
-		IP6_INC_STATS(net, NULL, IPSTATS_MIB_OUTNOROUTES);
 	dst_release(*dst);
 	*dst = NULL;
+out_err:
+	if (err == -ENETUNREACH)
+		IP6_INC_STATS(net, NULL, IPSTATS_MIB_OUTNOROUTES);
 	return err;
 }
 
@@ -1071,17 +1079,12 @@
 					 const struct in6_addr *final_dst)
 {
 	struct dst_entry *dst = sk_dst_check(sk, inet6_sk(sk)->dst_cookie);
-	int err;
 
 	dst = ip6_sk_dst_check(sk, dst, fl6);
+	if (!dst)
+		dst = ip6_dst_lookup_flow(sk, fl6, final_dst);
 
-	err = ip6_dst_lookup_tail(sock_net(sk), sk, &dst, fl6);
-	if (err)
-		return ERR_PTR(err);
-	if (final_dst)
-		fl6->daddr = *final_dst;
-
-	return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
+	return dst;
 }
 EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow);
 
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index c245895..fe65cdc 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -73,15 +73,6 @@
 #include <linux/netfilter.h>
 #include <linux/netfilter_ipv6.h>
 
-/* Set to 3 to get tracing... */
-#define ND_DEBUG 1
-
-#define ND_PRINTK(val, level, fmt, ...)				\
-do {								\
-	if (val <= ND_DEBUG)					\
-		net_##level##_ratelimited(fmt, ##__VA_ARGS__);	\
-} while (0)
-
 static u32 ndisc_hash(const void *pkey,
 		      const struct net_device *dev,
 		      __u32 *hash_rnd);
@@ -150,11 +141,10 @@
 };
 EXPORT_SYMBOL_GPL(nd_tbl);
 
-static void ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data)
+void __ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data,
+			      int data_len, int pad)
 {
-	int pad   = ndisc_addr_option_pad(skb->dev->type);
-	int data_len = skb->dev->addr_len;
-	int space = ndisc_opt_addr_space(skb->dev);
+	int space = __ndisc_opt_addr_space(data_len, pad);
 	u8 *opt = skb_put(skb, space);
 
 	opt[0] = type;
@@ -171,6 +161,23 @@
 	if (space > 0)
 		memset(opt, 0, space);
 }
+EXPORT_SYMBOL_GPL(__ndisc_fill_addr_option);
+
+static inline void ndisc_fill_addr_option(struct sk_buff *skb, int type,
+					  void *data, u8 icmp6_type)
+{
+	__ndisc_fill_addr_option(skb, type, data, skb->dev->addr_len,
+				 ndisc_addr_option_pad(skb->dev->type));
+	ndisc_ops_fill_addr_option(skb->dev, skb, icmp6_type);
+}
+
+static inline void ndisc_fill_redirect_addr_option(struct sk_buff *skb,
+						   void *ha,
+						   const u8 *ops_data)
+{
+	ndisc_fill_addr_option(skb, ND_OPT_TARGET_LL_ADDR, ha, NDISC_REDIRECT);
+	ndisc_ops_fill_redirect_addr_option(skb->dev, skb, ops_data);
+}
 
 static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur,
 					    struct nd_opt_hdr *end)
@@ -185,24 +192,28 @@
 	return cur <= end && cur->nd_opt_type == type ? cur : NULL;
 }
 
-static inline int ndisc_is_useropt(struct nd_opt_hdr *opt)
+static inline int ndisc_is_useropt(const struct net_device *dev,
+				   struct nd_opt_hdr *opt)
 {
 	return opt->nd_opt_type == ND_OPT_RDNSS ||
-		opt->nd_opt_type == ND_OPT_DNSSL;
+		opt->nd_opt_type == ND_OPT_DNSSL ||
+		ndisc_ops_is_useropt(dev, opt->nd_opt_type);
 }
 
-static struct nd_opt_hdr *ndisc_next_useropt(struct nd_opt_hdr *cur,
+static struct nd_opt_hdr *ndisc_next_useropt(const struct net_device *dev,
+					     struct nd_opt_hdr *cur,
 					     struct nd_opt_hdr *end)
 {
 	if (!cur || !end || cur >= end)
 		return NULL;
 	do {
 		cur = ((void *)cur) + (cur->nd_opt_len << 3);
-	} while (cur < end && !ndisc_is_useropt(cur));
-	return cur <= end && ndisc_is_useropt(cur) ? cur : NULL;
+	} while (cur < end && !ndisc_is_useropt(dev, cur));
+	return cur <= end && ndisc_is_useropt(dev, cur) ? cur : NULL;
 }
 
-struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len,
+struct ndisc_options *ndisc_parse_options(const struct net_device *dev,
+					  u8 *opt, int opt_len,
 					  struct ndisc_options *ndopts)
 {
 	struct nd_opt_hdr *nd_opt = (struct nd_opt_hdr *)opt;
@@ -217,6 +228,8 @@
 		l = nd_opt->nd_opt_len << 3;
 		if (opt_len < l || l == 0)
 			return NULL;
+		if (ndisc_ops_parse_options(dev, nd_opt, ndopts))
+			goto next_opt;
 		switch (nd_opt->nd_opt_type) {
 		case ND_OPT_SOURCE_LL_ADDR:
 		case ND_OPT_TARGET_LL_ADDR:
@@ -243,7 +256,7 @@
 			break;
 #endif
 		default:
-			if (ndisc_is_useropt(nd_opt)) {
+			if (ndisc_is_useropt(dev, nd_opt)) {
 				ndopts->nd_useropts_end = nd_opt;
 				if (!ndopts->nd_useropts)
 					ndopts->nd_useropts = nd_opt;
@@ -260,6 +273,7 @@
 					  nd_opt->nd_opt_len);
 			}
 		}
+next_opt:
 		opt_len -= l;
 		nd_opt = ((void *)nd_opt) + l;
 	}
@@ -509,7 +523,8 @@
 	if (!dev->addr_len)
 		inc_opt = 0;
 	if (inc_opt)
-		optlen += ndisc_opt_addr_space(dev);
+		optlen += ndisc_opt_addr_space(dev,
+					       NDISC_NEIGHBOUR_ADVERTISEMENT);
 
 	skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen);
 	if (!skb)
@@ -528,8 +543,8 @@
 
 	if (inc_opt)
 		ndisc_fill_addr_option(skb, ND_OPT_TARGET_LL_ADDR,
-				       dev->dev_addr);
-
+				       dev->dev_addr,
+				       NDISC_NEIGHBOUR_ADVERTISEMENT);
 
 	ndisc_send_skb(skb, daddr, src_addr);
 }
@@ -574,7 +589,8 @@
 	if (ipv6_addr_any(saddr))
 		inc_opt = false;
 	if (inc_opt)
-		optlen += ndisc_opt_addr_space(dev);
+		optlen += ndisc_opt_addr_space(dev,
+					       NDISC_NEIGHBOUR_SOLICITATION);
 
 	skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen);
 	if (!skb)
@@ -590,7 +606,8 @@
 
 	if (inc_opt)
 		ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR,
-				       dev->dev_addr);
+				       dev->dev_addr,
+				       NDISC_NEIGHBOUR_SOLICITATION);
 
 	ndisc_send_skb(skb, daddr, saddr);
 }
@@ -626,7 +643,7 @@
 	}
 #endif
 	if (send_sllao)
-		optlen += ndisc_opt_addr_space(dev);
+		optlen += ndisc_opt_addr_space(dev, NDISC_ROUTER_SOLICITATION);
 
 	skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen);
 	if (!skb)
@@ -641,7 +658,8 @@
 
 	if (send_sllao)
 		ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR,
-				       dev->dev_addr);
+				       dev->dev_addr,
+				       NDISC_ROUTER_SOLICITATION);
 
 	ndisc_send_skb(skb, daddr, saddr);
 }
@@ -702,6 +720,15 @@
 	return ret;
 }
 
+void ndisc_update(const struct net_device *dev, struct neighbour *neigh,
+		  const u8 *lladdr, u8 new, u32 flags, u8 icmp6_type,
+		  struct ndisc_options *ndopts)
+{
+	neigh_update(neigh, lladdr, new, flags);
+	/* report ndisc ops about neighbour update */
+	ndisc_ops_update(dev, neigh, flags, icmp6_type, ndopts);
+}
+
 static void ndisc_recv_ns(struct sk_buff *skb)
 {
 	struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb);
@@ -738,7 +765,7 @@
 		return;
 	}
 
-	if (!ndisc_parse_options(msg->opt, ndoptlen, &ndopts)) {
+	if (!ndisc_parse_options(dev, msg->opt, ndoptlen, &ndopts)) {
 		ND_PRINTK(2, warn, "NS: invalid ND options\n");
 		return;
 	}
@@ -856,9 +883,10 @@
 	neigh = __neigh_lookup(&nd_tbl, saddr, dev,
 			       !inc || lladdr || !dev->addr_len);
 	if (neigh)
-		neigh_update(neigh, lladdr, NUD_STALE,
+		ndisc_update(dev, neigh, lladdr, NUD_STALE,
 			     NEIGH_UPDATE_F_WEAK_OVERRIDE|
-			     NEIGH_UPDATE_F_OVERRIDE);
+			     NEIGH_UPDATE_F_OVERRIDE,
+			     NDISC_NEIGHBOUR_SOLICITATION, &ndopts);
 	if (neigh || !dev->header_ops) {
 		ndisc_send_na(dev, saddr, &msg->target, !!is_router,
 			      true, (ifp != NULL && inc), inc);
@@ -911,7 +939,7 @@
 	    idev->cnf.drop_unsolicited_na)
 		return;
 
-	if (!ndisc_parse_options(msg->opt, ndoptlen, &ndopts)) {
+	if (!ndisc_parse_options(dev, msg->opt, ndoptlen, &ndopts)) {
 		ND_PRINTK(2, warn, "NS: invalid ND option\n");
 		return;
 	}
@@ -967,12 +995,13 @@
 			goto out;
 		}
 
-		neigh_update(neigh, lladdr,
+		ndisc_update(dev, neigh, lladdr,
 			     msg->icmph.icmp6_solicited ? NUD_REACHABLE : NUD_STALE,
 			     NEIGH_UPDATE_F_WEAK_OVERRIDE|
 			     (msg->icmph.icmp6_override ? NEIGH_UPDATE_F_OVERRIDE : 0)|
 			     NEIGH_UPDATE_F_OVERRIDE_ISROUTER|
-			     (msg->icmph.icmp6_router ? NEIGH_UPDATE_F_ISROUTER : 0));
+			     (msg->icmph.icmp6_router ? NEIGH_UPDATE_F_ISROUTER : 0),
+			     NDISC_NEIGHBOUR_ADVERTISEMENT, &ndopts);
 
 		if ((old_flags & ~neigh->flags) & NTF_ROUTER) {
 			/*
@@ -1017,7 +1046,7 @@
 		goto out;
 
 	/* Parse ND options */
-	if (!ndisc_parse_options(rs_msg->opt, ndoptlen, &ndopts)) {
+	if (!ndisc_parse_options(skb->dev, rs_msg->opt, ndoptlen, &ndopts)) {
 		ND_PRINTK(2, notice, "NS: invalid ND option, ignored\n");
 		goto out;
 	}
@@ -1031,10 +1060,11 @@
 
 	neigh = __neigh_lookup(&nd_tbl, saddr, skb->dev, 1);
 	if (neigh) {
-		neigh_update(neigh, lladdr, NUD_STALE,
+		ndisc_update(skb->dev, neigh, lladdr, NUD_STALE,
 			     NEIGH_UPDATE_F_WEAK_OVERRIDE|
 			     NEIGH_UPDATE_F_OVERRIDE|
-			     NEIGH_UPDATE_F_OVERRIDE_ISROUTER);
+			     NEIGH_UPDATE_F_OVERRIDE_ISROUTER,
+			     NDISC_ROUTER_SOLICITATION, &ndopts);
 		neigh_release(neigh);
 	}
 out:
@@ -1135,7 +1165,7 @@
 		return;
 	}
 
-	if (!ndisc_parse_options(opt, optlen, &ndopts)) {
+	if (!ndisc_parse_options(skb->dev, opt, optlen, &ndopts)) {
 		ND_PRINTK(2, warn, "RA: invalid ND options\n");
 		return;
 	}
@@ -1329,11 +1359,12 @@
 				goto out;
 			}
 		}
-		neigh_update(neigh, lladdr, NUD_STALE,
+		ndisc_update(skb->dev, neigh, lladdr, NUD_STALE,
 			     NEIGH_UPDATE_F_WEAK_OVERRIDE|
 			     NEIGH_UPDATE_F_OVERRIDE|
 			     NEIGH_UPDATE_F_OVERRIDE_ISROUTER|
-			     NEIGH_UPDATE_F_ISROUTER);
+			     NEIGH_UPDATE_F_ISROUTER,
+			     NDISC_ROUTER_ADVERTISEMENT, &ndopts);
 	}
 
 	if (!ipv6_accept_ra(in6_dev)) {
@@ -1421,7 +1452,8 @@
 		struct nd_opt_hdr *p;
 		for (p = ndopts.nd_useropts;
 		     p;
-		     p = ndisc_next_useropt(p, ndopts.nd_useropts_end)) {
+		     p = ndisc_next_useropt(skb->dev, p,
+					    ndopts.nd_useropts_end)) {
 			ndisc_ra_useropt(skb, p);
 		}
 	}
@@ -1459,7 +1491,7 @@
 		return;
 	}
 
-	if (!ndisc_parse_options(msg->opt, ndoptlen, &ndopts))
+	if (!ndisc_parse_options(skb->dev, msg->opt, ndoptlen, &ndopts))
 		return;
 
 	if (!ndopts.nd_opts_rh) {
@@ -1504,7 +1536,8 @@
 	struct dst_entry *dst;
 	struct flowi6 fl6;
 	int rd_len;
-	u8 ha_buf[MAX_ADDR_LEN], *ha = NULL;
+	u8 ha_buf[MAX_ADDR_LEN], *ha = NULL,
+	   ops_data_buf[NDISC_OPS_REDIRECT_DATA_SPACE], *ops_data = NULL;
 	int oif = l3mdev_fib_oif(dev);
 	bool ret;
 
@@ -1563,7 +1596,9 @@
 			memcpy(ha_buf, neigh->ha, dev->addr_len);
 			read_unlock_bh(&neigh->lock);
 			ha = ha_buf;
-			optlen += ndisc_opt_addr_space(dev);
+			optlen += ndisc_redirect_opt_addr_space(dev, neigh,
+								ops_data_buf,
+								&ops_data);
 		} else
 			read_unlock_bh(&neigh->lock);
 
@@ -1594,7 +1629,7 @@
 	 */
 
 	if (ha)
-		ndisc_fill_addr_option(buff, ND_OPT_TARGET_LL_ADDR, ha);
+		ndisc_fill_redirect_addr_option(buff, ha, ops_data);
 
 	/*
 	 *	build redirect option and copy skb over to the new packet.
diff --git a/net/ipv6/netfilter/nf_dup_ipv6.c b/net/ipv6/netfilter/nf_dup_ipv6.c
index 6989c70..4a84b5a 100644
--- a/net/ipv6/netfilter/nf_dup_ipv6.c
+++ b/net/ipv6/netfilter/nf_dup_ipv6.c
@@ -33,6 +33,7 @@
 	fl6.daddr = *gw;
 	fl6.flowlabel = (__force __be32)(((iph->flow_lbl[0] & 0xF) << 16) |
 			(iph->flow_lbl[1] << 8) | iph->flow_lbl[2]);
+	fl6.flowi6_flags = FLOWI_FLAG_KNOWN_NH;
 	dst = ip6_route_output(net, NULL, &fl6);
 	if (dst->error) {
 		dst_release(dst);
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 3ee3e44..fed40d1 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -116,6 +116,9 @@
 	else if (!fl6.flowi6_oif)
 		fl6.flowi6_oif = np->ucast_oif;
 
+	ipc6.tclass = np->tclass;
+	fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
+
 	dst = ip6_sk_dst_lookup_flow(sk, &fl6,  daddr);
 	if (IS_ERR(dst))
 		return PTR_ERR(dst);
@@ -140,7 +143,6 @@
 	pfh.family = AF_INET6;
 
 	ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
-	ipc6.tclass = np->tclass;
 	ipc6.dontfrag = np->dontfrag;
 	ipc6.opt = NULL;
 
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 896350d..590dd1f 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -878,6 +878,11 @@
 	if (inet->hdrincl)
 		fl6.flowi6_flags |= FLOWI_FLAG_KNOWN_NH;
 
+	if (ipc6.tclass < 0)
+		ipc6.tclass = np->tclass;
+
+	fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
+
 	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
@@ -886,9 +891,6 @@
 	if (ipc6.hlimit < 0)
 		ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
 
-	if (ipc6.tclass < 0)
-		ipc6.tclass = np->tclass;
-
 	if (ipc6.dontfrag < 0)
 		ipc6.dontfrag = np->dontfrag;
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 969913d..08b77f4 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1042,8 +1042,8 @@
 	return pcpu_rt;
 }
 
-static struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif,
-				      struct flowi6 *fl6, int flags)
+struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
+			       int oif, struct flowi6 *fl6, int flags)
 {
 	struct fib6_node *fn, *saved_fn;
 	struct rt6_info *rt;
@@ -1139,6 +1139,7 @@
 
 	}
 }
+EXPORT_SYMBOL_GPL(ip6_pol_route);
 
 static struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table,
 					    struct flowi6 *fl6, int flags)
@@ -2200,7 +2201,7 @@
 	 *	first-hop router for the specified ICMP Destination Address.
 	 */
 
-	if (!ndisc_parse_options(msg->opt, optlen, &ndopts)) {
+	if (!ndisc_parse_options(skb->dev, msg->opt, optlen, &ndopts)) {
 		net_dbg_ratelimited("rt6_redirect: invalid ND options\n");
 		return;
 	}
@@ -2235,12 +2236,12 @@
 	 *	We have finally decided to accept it.
 	 */
 
-	neigh_update(neigh, lladdr, NUD_STALE,
+	ndisc_update(skb->dev, neigh, lladdr, NUD_STALE,
 		     NEIGH_UPDATE_F_WEAK_OVERRIDE|
 		     NEIGH_UPDATE_F_OVERRIDE|
 		     (on_link ? 0 : (NEIGH_UPDATE_F_OVERRIDE_ISROUTER|
-				     NEIGH_UPDATE_F_ISROUTER))
-		     );
+				     NEIGH_UPDATE_F_ISROUTER)),
+		     NDISC_REDIRECT, &ndopts);
 
 	nrt = ip6_rt_cache_alloc(rt, &msg->dest, NULL);
 	if (!nrt)
@@ -2585,23 +2586,6 @@
 	return rt;
 }
 
-int ip6_route_get_saddr(struct net *net,
-			struct rt6_info *rt,
-			const struct in6_addr *daddr,
-			unsigned int prefs,
-			struct in6_addr *saddr)
-{
-	struct inet6_dev *idev =
-		rt ? ip6_dst_idev((struct dst_entry *)rt) : NULL;
-	int err = 0;
-	if (rt && rt->rt6i_prefsrc.plen)
-		*saddr = rt->rt6i_prefsrc.addr;
-	else
-		err = ipv6_dev_get_saddr(net, idev ? idev->dev : NULL,
-					 daddr, prefs, saddr);
-	return err;
-}
-
 /* remove deleted ip from prefsrc entries */
 struct arg_dev_net_ip {
 	struct net_device *dev;
@@ -3306,6 +3290,8 @@
 
 	err = -EINVAL;
 	memset(&fl6, 0, sizeof(fl6));
+	rtm = nlmsg_data(nlh);
+	fl6.flowlabel = ip6_make_flowinfo(rtm->rtm_tos, 0);
 
 	if (tb[RTA_SRC]) {
 		if (nla_len(tb[RTA_SRC]) < sizeof(struct in6_addr))
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 0a5a255..cdd7146 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -479,47 +479,12 @@
 	dev_put(dev);
 }
 
-/* Generate icmpv6 with type/code ICMPV6_DEST_UNREACH/ICMPV6_ADDR_UNREACH
- * if sufficient data bytes are available
- */
-static int ipip6_err_gen_icmpv6_unreach(struct sk_buff *skb)
-{
-	int ihl = ((const struct iphdr *)skb->data)->ihl*4;
-	struct rt6_info *rt;
-	struct sk_buff *skb2;
-
-	if (!pskb_may_pull(skb, ihl + sizeof(struct ipv6hdr) + 8))
-		return 1;
-
-	skb2 = skb_clone(skb, GFP_ATOMIC);
-
-	if (!skb2)
-		return 1;
-
-	skb_dst_drop(skb2);
-	skb_pull(skb2, ihl);
-	skb_reset_network_header(skb2);
-
-	rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0, 0);
-
-	if (rt && rt->dst.dev)
-		skb2->dev = rt->dst.dev;
-
-	icmpv6_send(skb2, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0);
-
-	if (rt)
-		ip6_rt_put(rt);
-
-	kfree_skb(skb2);
-
-	return 0;
-}
-
 static int ipip6_err(struct sk_buff *skb, u32 info)
 {
 	const struct iphdr *iph = (const struct iphdr *)skb->data;
 	const int type = icmp_hdr(skb)->type;
 	const int code = icmp_hdr(skb)->code;
+	unsigned int data_len = 0;
 	struct ip_tunnel *t;
 	int err;
 
@@ -544,6 +509,7 @@
 	case ICMP_TIME_EXCEEDED:
 		if (code != ICMP_EXC_TTL)
 			return 0;
+		data_len = icmp_hdr(skb)->un.reserved[1] * 4; /* RFC 4884 4.1 */
 		break;
 	case ICMP_REDIRECT:
 		break;
@@ -571,11 +537,11 @@
 		goto out;
 	}
 
-	if (t->parms.iph.daddr == 0)
+	err = 0;
+	if (!ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4, type, data_len))
 		goto out;
 
-	err = 0;
-	if (!ipip6_err_gen_icmpv6_unreach(skb))
+	if (t->parms.iph.daddr == 0)
 		goto out;
 
 	if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
@@ -825,9 +791,6 @@
 	u8 protocol = IPPROTO_IPV6;
 	int t_hlen = tunnel->hlen + sizeof(struct iphdr);
 
-	if (skb->protocol != htons(ETH_P_IPV6))
-		goto tx_error;
-
 	if (tos == 1)
 		tos = ipv6_get_dsfield(iph6);
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 79e33e0..f36c2d0 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1721,7 +1721,9 @@
 	destp = ntohs(inet->inet_dport);
 	srcp  = ntohs(inet->inet_sport);
 
-	if (icsk->icsk_pending == ICSK_TIME_RETRANS) {
+	if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
+	    icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
+	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
 		timer_active	= 1;
 		timer_expires	= icsk->icsk_timeout;
 	} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 2da1896..4bb5c13 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -653,12 +653,12 @@
 		}
 	}
 
-	if (rcu_access_pointer(sk->sk_filter)) {
-		if (udp_lib_checksum_complete(skb))
-			goto csum_error;
-		if (sk_filter(sk, skb))
-			goto drop;
-	}
+	if (rcu_access_pointer(sk->sk_filter) &&
+	    udp_lib_checksum_complete(skb))
+		goto csum_error;
+
+	if (sk_filter(sk, skb))
+		goto drop;
 
 	udp_csum_pull_header(skb);
 	if (sk_rcvqueues_full(sk, sk->sk_rcvbuf)) {
@@ -1246,6 +1246,11 @@
 
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
+	if (ipc6.tclass < 0)
+		ipc6.tclass = np->tclass;
+
+	fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
+
 	dst = ip6_sk_dst_lookup_flow(sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
@@ -1256,9 +1261,6 @@
 	if (ipc6.hlimit < 0)
 		ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
 
-	if (ipc6.tclass < 0)
-		ipc6.tclass = np->tclass;
-
 	if (msg->msg_flags&MSG_CONFIRM)
 		goto do_confirm;
 back_from_confirm:
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index c074771..6cc9700 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -366,12 +366,12 @@
 		kfree(table);
 }
 #else /* CONFIG_SYSCTL */
-static int inline xfrm6_net_sysctl_init(struct net *net)
+static inline int xfrm6_net_sysctl_init(struct net *net)
 {
 	return 0;
 }
 
-static void inline xfrm6_net_sysctl_exit(struct net *net)
+static inline void xfrm6_net_sysctl_exit(struct net *net)
 {
 }
 #endif
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index fc3598a..37d674e 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1033,6 +1033,7 @@
 {
 	struct sock *sk = sock->sk;
 	struct iucv_sock *iucv = iucv_sk(sk);
+	size_t headroom, linear;
 	struct sk_buff *skb;
 	struct iucv_message txmsg = {0};
 	struct cmsghdr *cmsg;
@@ -1110,20 +1111,31 @@
 	 * this is fine for SOCK_SEQPACKET (unless we want to support
 	 * segmented records using the MSG_EOR flag), but
 	 * for SOCK_STREAM we might want to improve it in future */
-	if (iucv->transport == AF_IUCV_TRANS_HIPER)
-		skb = sock_alloc_send_skb(sk,
-			len + sizeof(struct af_iucv_trans_hdr) + ETH_HLEN,
-			noblock, &err);
-	else
-		skb = sock_alloc_send_skb(sk, len, noblock, &err);
+	headroom = (iucv->transport == AF_IUCV_TRANS_HIPER)
+		   ? sizeof(struct af_iucv_trans_hdr) + ETH_HLEN : 0;
+	if (headroom + len < PAGE_SIZE) {
+		linear = len;
+	} else {
+		/* In nonlinear "classic" iucv skb,
+		 * reserve space for iucv_array
+		 */
+		if (iucv->transport != AF_IUCV_TRANS_HIPER)
+			headroom += sizeof(struct iucv_array) *
+				    (MAX_SKB_FRAGS + 1);
+		linear = PAGE_SIZE - headroom;
+	}
+	skb = sock_alloc_send_pskb(sk, headroom + linear, len - linear,
+				   noblock, &err, 0);
 	if (!skb)
 		goto out;
-	if (iucv->transport == AF_IUCV_TRANS_HIPER)
-		skb_reserve(skb, sizeof(struct af_iucv_trans_hdr) + ETH_HLEN);
-	if (memcpy_from_msg(skb_put(skb, len), msg, len)) {
-		err = -EFAULT;
+	if (headroom)
+		skb_reserve(skb, headroom);
+	skb_put(skb, linear);
+	skb->len = len;
+	skb->data_len = len - linear;
+	err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, len);
+	if (err)
 		goto fail;
-	}
 
 	/* wait if outstanding messages for iucv path has reached */
 	timeo = sock_sndtimeo(sk, noblock);
@@ -1148,49 +1160,67 @@
 			atomic_dec(&iucv->msg_sent);
 			goto fail;
 		}
-		goto release;
-	}
-	skb_queue_tail(&iucv->send_skb_q, skb);
+	} else { /* Classic VM IUCV transport */
+		skb_queue_tail(&iucv->send_skb_q, skb);
 
-	if (((iucv->path->flags & IUCV_IPRMDATA) & iucv->flags)
-	      && skb->len <= 7) {
-		err = iucv_send_iprm(iucv->path, &txmsg, skb);
+		if (((iucv->path->flags & IUCV_IPRMDATA) & iucv->flags) &&
+		    skb->len <= 7) {
+			err = iucv_send_iprm(iucv->path, &txmsg, skb);
 
-		/* on success: there is no message_complete callback
-		 * for an IPRMDATA msg; remove skb from send queue */
-		if (err == 0) {
-			skb_unlink(skb, &iucv->send_skb_q);
-			kfree_skb(skb);
+			/* on success: there is no message_complete callback */
+			/* for an IPRMDATA msg; remove skb from send queue   */
+			if (err == 0) {
+				skb_unlink(skb, &iucv->send_skb_q);
+				kfree_skb(skb);
+			}
+
+			/* this error should never happen since the	*/
+			/* IUCV_IPRMDATA path flag is set... sever path */
+			if (err == 0x15) {
+				pr_iucv->path_sever(iucv->path, NULL);
+				skb_unlink(skb, &iucv->send_skb_q);
+				err = -EPIPE;
+				goto fail;
+			}
+		} else if (skb_is_nonlinear(skb)) {
+			struct iucv_array *iba = (struct iucv_array *)skb->head;
+			int i;
+
+			/* skip iucv_array lying in the headroom */
+			iba[0].address = (u32)(addr_t)skb->data;
+			iba[0].length = (u32)skb_headlen(skb);
+			for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+				skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+				iba[i + 1].address =
+					(u32)(addr_t)skb_frag_address(frag);
+				iba[i + 1].length = (u32)skb_frag_size(frag);
+			}
+			err = pr_iucv->message_send(iucv->path, &txmsg,
+						    IUCV_IPBUFLST, 0,
+						    (void *)iba, skb->len);
+		} else { /* non-IPRM Linear skb */
+			err = pr_iucv->message_send(iucv->path, &txmsg,
+					0, 0, (void *)skb->data, skb->len);
 		}
-
-		/* this error should never happen since the
-		 * IUCV_IPRMDATA path flag is set... sever path */
-		if (err == 0x15) {
-			pr_iucv->path_sever(iucv->path, NULL);
+		if (err) {
+			if (err == 3) {
+				user_id[8] = 0;
+				memcpy(user_id, iucv->dst_user_id, 8);
+				appl_id[8] = 0;
+				memcpy(appl_id, iucv->dst_name, 8);
+				pr_err(
+		"Application %s on z/VM guest %s exceeds message limit\n",
+					appl_id, user_id);
+				err = -EAGAIN;
+			} else {
+				err = -EPIPE;
+			}
 			skb_unlink(skb, &iucv->send_skb_q);
-			err = -EPIPE;
 			goto fail;
 		}
-	} else
-		err = pr_iucv->message_send(iucv->path, &txmsg, 0, 0,
-					(void *) skb->data, skb->len);
-	if (err) {
-		if (err == 3) {
-			user_id[8] = 0;
-			memcpy(user_id, iucv->dst_user_id, 8);
-			appl_id[8] = 0;
-			memcpy(appl_id, iucv->dst_name, 8);
-			pr_err("Application %s on z/VM guest %s"
-				" exceeds message limit\n",
-				appl_id, user_id);
-			err = -EAGAIN;
-		} else
-			err = -EPIPE;
-		skb_unlink(skb, &iucv->send_skb_q);
-		goto fail;
 	}
 
-release:
 	release_sock(sk);
 	return len;
 
@@ -1201,42 +1231,32 @@
 	return err;
 }
 
-/* iucv_fragment_skb() - Fragment a single IUCV message into multiple skb's
- *
- * Locking: must be called with message_q.lock held
- */
-static int iucv_fragment_skb(struct sock *sk, struct sk_buff *skb, int len)
+static struct sk_buff *alloc_iucv_recv_skb(unsigned long len)
 {
-	int dataleft, size, copied = 0;
-	struct sk_buff *nskb;
+	size_t headroom, linear;
+	struct sk_buff *skb;
+	int err;
 
-	dataleft = len;
-	while (dataleft) {
-		if (dataleft >= sk->sk_rcvbuf / 4)
-			size = sk->sk_rcvbuf / 4;
-		else
-			size = dataleft;
-
-		nskb = alloc_skb(size, GFP_ATOMIC | GFP_DMA);
-		if (!nskb)
-			return -ENOMEM;
-
-		/* copy target class to control buffer of new skb */
-		IUCV_SKB_CB(nskb)->class = IUCV_SKB_CB(skb)->class;
-
-		/* copy data fragment */
-		memcpy(nskb->data, skb->data + copied, size);
-		copied += size;
-		dataleft -= size;
-
-		skb_reset_transport_header(nskb);
-		skb_reset_network_header(nskb);
-		nskb->len = size;
-
-		skb_queue_tail(&iucv_sk(sk)->backlog_skb_q, nskb);
+	if (len < PAGE_SIZE) {
+		headroom = 0;
+		linear = len;
+	} else {
+		headroom = sizeof(struct iucv_array) * (MAX_SKB_FRAGS + 1);
+		linear = PAGE_SIZE - headroom;
 	}
-
-	return 0;
+	skb = alloc_skb_with_frags(headroom + linear, len - linear,
+				   0, &err, GFP_ATOMIC | GFP_DMA);
+	WARN_ONCE(!skb,
+		  "alloc of recv iucv skb len=%lu failed with errcode=%d\n",
+		  len, err);
+	if (skb) {
+		if (headroom)
+			skb_reserve(skb, headroom);
+		skb_put(skb, linear);
+		skb->len = len;
+		skb->data_len = len - linear;
+	}
+	return skb;
 }
 
 /* iucv_process_message() - Receive a single outstanding IUCV message
@@ -1263,31 +1283,32 @@
 			skb->len = 0;
 		}
 	} else {
-		rc = pr_iucv->message_receive(path, msg,
+		if (skb_is_nonlinear(skb)) {
+			struct iucv_array *iba = (struct iucv_array *)skb->head;
+			int i;
+
+			iba[0].address = (u32)(addr_t)skb->data;
+			iba[0].length = (u32)skb_headlen(skb);
+			for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+				skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+				iba[i + 1].address =
+					(u32)(addr_t)skb_frag_address(frag);
+				iba[i + 1].length = (u32)skb_frag_size(frag);
+			}
+			rc = pr_iucv->message_receive(path, msg,
+					      IUCV_IPBUFLST,
+					      (void *)iba, len, NULL);
+		} else {
+			rc = pr_iucv->message_receive(path, msg,
 					      msg->flags & IUCV_IPRMDATA,
 					      skb->data, len, NULL);
+		}
 		if (rc) {
 			kfree_skb(skb);
 			return;
 		}
-		/* we need to fragment iucv messages for SOCK_STREAM only;
-		 * for SOCK_SEQPACKET, it is only relevant if we support
-		 * record segmentation using MSG_EOR (see also recvmsg()) */
-		if (sk->sk_type == SOCK_STREAM &&
-		    skb->truesize >= sk->sk_rcvbuf / 4) {
-			rc = iucv_fragment_skb(sk, skb, len);
-			kfree_skb(skb);
-			skb = NULL;
-			if (rc) {
-				pr_iucv->path_sever(path, NULL);
-				return;
-			}
-			skb = skb_dequeue(&iucv_sk(sk)->backlog_skb_q);
-		} else {
-			skb_reset_transport_header(skb);
-			skb_reset_network_header(skb);
-			skb->len = len;
-		}
+		WARN_ON_ONCE(skb->len != len);
 	}
 
 	IUCV_SKB_CB(skb)->offset = 0;
@@ -1306,7 +1327,7 @@
 	struct sock_msg_q *p, *n;
 
 	list_for_each_entry_safe(p, n, &iucv->message_q.list, list) {
-		skb = alloc_skb(iucv_msg_length(&p->msg), GFP_ATOMIC | GFP_DMA);
+		skb = alloc_iucv_recv_skb(iucv_msg_length(&p->msg));
 		if (!skb)
 			break;
 		iucv_process_message(sk, skb, p->path, &p->msg);
@@ -1801,7 +1822,7 @@
 	if (len > sk->sk_rcvbuf)
 		goto save_message;
 
-	skb = alloc_skb(iucv_msg_length(msg), GFP_ATOMIC | GFP_DMA);
+	skb = alloc_iucv_recv_skb(iucv_msg_length(msg));
 	if (!skb)
 		goto save_message;
 
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 6edfa99..1e40dac 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1581,7 +1581,7 @@
 	/* Mark socket as an encapsulation socket. See net/ipv4/udp.c */
 	tunnel->encap = encap;
 	if (encap == L2TP_ENCAPTYPE_UDP) {
-		struct udp_tunnel_sock_cfg udp_cfg;
+		struct udp_tunnel_sock_cfg udp_cfg = { };
 
 		udp_cfg.sk_user_data = tunnel;
 		udp_cfg.encap_type = UDP_ENCAP_L2TPINUDP;
diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index e253c26..57fc5a4 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -67,7 +67,6 @@
 	return net_generic(net, l2tp_eth_net_id);
 }
 
-static struct lock_class_key l2tp_eth_tx_busylock;
 static int l2tp_eth_dev_init(struct net_device *dev)
 {
 	struct l2tp_eth *priv = netdev_priv(dev);
@@ -75,7 +74,8 @@
 	priv->dev = dev;
 	eth_hw_addr_random(dev);
 	eth_broadcast_addr(dev->broadcast);
-	dev->qdisc_tx_busylock = &l2tp_eth_tx_busylock;
+	netdev_lockdep_set_classes(dev);
+
 	return 0;
 }
 
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 6c54e03..ea2ae66 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -611,6 +611,11 @@
 
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
+	if (ipc6.tclass < 0)
+		ipc6.tclass = np->tclass;
+
+	fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
+
 	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
@@ -620,9 +625,6 @@
 	if (ipc6.hlimit < 0)
 		ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
 
-	if (ipc6.tclass < 0)
-		ipc6.tclass = np->tclass;
-
 	if (ipc6.dontfrag < 0)
 		ipc6.dontfrag = np->dontfrag;
 
diff --git a/net/l3mdev/l3mdev.c b/net/l3mdev/l3mdev.c
index 6651a78..c4a1c3e 100644
--- a/net/l3mdev/l3mdev.c
+++ b/net/l3mdev/l3mdev.c
@@ -10,6 +10,7 @@
  */
 
 #include <linux/netdevice.h>
+#include <net/fib_rules.h>
 #include <net/l3mdev.h>
 
 /**
@@ -107,7 +108,7 @@
  */
 
 struct dst_entry *l3mdev_get_rt6_dst(struct net *net,
-				     const struct flowi6 *fl6)
+				     struct flowi6 *fl6)
 {
 	struct dst_entry *dst = NULL;
 	struct net_device *dev;
@@ -160,3 +161,64 @@
 	return rc;
 }
 EXPORT_SYMBOL_GPL(l3mdev_get_saddr);
+
+int l3mdev_get_saddr6(struct net *net, const struct sock *sk,
+		      struct flowi6 *fl6)
+{
+	struct net_device *dev;
+	int rc = 0;
+
+	if (fl6->flowi6_oif) {
+		rcu_read_lock();
+
+		dev = dev_get_by_index_rcu(net, fl6->flowi6_oif);
+		if (dev && netif_is_l3_slave(dev))
+			dev = netdev_master_upper_dev_get_rcu(dev);
+
+		if (dev && netif_is_l3_master(dev) &&
+		    dev->l3mdev_ops->l3mdev_get_saddr6)
+			rc = dev->l3mdev_ops->l3mdev_get_saddr6(dev, sk, fl6);
+
+		rcu_read_unlock();
+	}
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(l3mdev_get_saddr6);
+
+/**
+ *	l3mdev_fib_rule_match - Determine if flowi references an
+ *				L3 master device
+ *	@net: network namespace for device index lookup
+ *	@fl:  flow struct
+ */
+
+int l3mdev_fib_rule_match(struct net *net, struct flowi *fl,
+			  struct fib_lookup_arg *arg)
+{
+	struct net_device *dev;
+	int rc = 0;
+
+	rcu_read_lock();
+
+	dev = dev_get_by_index_rcu(net, fl->flowi_oif);
+	if (dev && netif_is_l3_master(dev) &&
+	    dev->l3mdev_ops->l3mdev_fib_table) {
+		arg->table = dev->l3mdev_ops->l3mdev_fib_table(dev);
+		rc = 1;
+		goto out;
+	}
+
+	dev = dev_get_by_index_rcu(net, fl->flowi_iif);
+	if (dev && netif_is_l3_master(dev) &&
+	    dev->l3mdev_ops->l3mdev_fib_table) {
+		arg->table = dev->l3mdev_ops->l3mdev_fib_table(dev);
+		rc = 1;
+		goto out;
+	}
+
+out:
+	rcu_read_unlock();
+
+	return rc;
+}
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index 42fa810..5650c46 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -194,17 +194,21 @@
 ieee80211_agg_stop_txq(struct sta_info *sta, int tid)
 {
 	struct ieee80211_txq *txq = sta->sta.txq[tid];
+	struct ieee80211_sub_if_data *sdata;
+	struct fq *fq;
 	struct txq_info *txqi;
 
 	if (!txq)
 		return;
 
 	txqi = to_txq_info(txq);
+	sdata = vif_to_sdata(txq->vif);
+	fq = &sdata->local->fq;
 
 	/* Lock here to protect against further seqno updates on dequeue */
-	spin_lock_bh(&txqi->queue.lock);
+	spin_lock_bh(&fq->lock);
 	set_bit(IEEE80211_TXQ_STOP, &txqi->flags);
-	spin_unlock_bh(&txqi->queue.lock);
+	spin_unlock_bh(&fq->lock);
 }
 
 static void
diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c
index b251b2f..2906c10 100644
--- a/net/mac80211/debugfs.c
+++ b/net/mac80211/debugfs.c
@@ -10,6 +10,7 @@
 
 #include <linux/debugfs.h>
 #include <linux/rtnetlink.h>
+#include <linux/vmalloc.h>
 #include "ieee80211_i.h"
 #include "driver-ops.h"
 #include "rate.h"
@@ -70,6 +71,177 @@
 DEBUGFS_READONLY_FILE(rate_ctrl_alg, "%s",
 	local->rate_ctrl ? local->rate_ctrl->ops->name : "hw/driver");
 
+struct aqm_info {
+	struct ieee80211_local *local;
+	size_t size;
+	size_t len;
+	unsigned char buf[0];
+};
+
+#define AQM_HDR_LEN 200
+#define AQM_HW_ENTRY_LEN 40
+#define AQM_TXQ_ENTRY_LEN 110
+
+static int aqm_open(struct inode *inode, struct file *file)
+{
+	struct ieee80211_local *local = inode->i_private;
+	struct ieee80211_sub_if_data *sdata;
+	struct sta_info *sta;
+	struct txq_info *txqi;
+	struct fq *fq = &local->fq;
+	struct aqm_info *info = NULL;
+	int len = 0;
+	int i;
+
+	if (!local->ops->wake_tx_queue)
+		return -EOPNOTSUPP;
+
+	len += AQM_HDR_LEN;
+	len += 6 * AQM_HW_ENTRY_LEN;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(sdata, &local->interfaces, list)
+		len += AQM_TXQ_ENTRY_LEN;
+	list_for_each_entry_rcu(sta, &local->sta_list, list)
+		len += AQM_TXQ_ENTRY_LEN * ARRAY_SIZE(sta->sta.txq);
+	rcu_read_unlock();
+
+	info = vmalloc(len);
+	if (!info)
+		return -ENOMEM;
+
+	spin_lock_bh(&local->fq.lock);
+	rcu_read_lock();
+
+	file->private_data = info;
+	info->local = local;
+	info->size = len;
+	len = 0;
+
+	len += scnprintf(info->buf + len, info->size - len,
+			 "* hw\n"
+			 "access name value\n"
+			 "R fq_flows_cnt %u\n"
+			 "R fq_backlog %u\n"
+			 "R fq_overlimit %u\n"
+			 "R fq_collisions %u\n"
+			 "RW fq_limit %u\n"
+			 "RW fq_quantum %u\n",
+			 fq->flows_cnt,
+			 fq->backlog,
+			 fq->overlimit,
+			 fq->collisions,
+			 fq->limit,
+			 fq->quantum);
+
+	len += scnprintf(info->buf + len,
+			 info->size - len,
+			 "* vif\n"
+			 "ifname addr ac backlog-bytes backlog-packets flows overlimit collisions tx-bytes tx-packets\n");
+
+	list_for_each_entry_rcu(sdata, &local->interfaces, list) {
+		txqi = to_txq_info(sdata->vif.txq);
+		len += scnprintf(info->buf + len, info->size - len,
+				 "%s %pM %u %u %u %u %u %u %u %u\n",
+				 sdata->name,
+				 sdata->vif.addr,
+				 txqi->txq.ac,
+				 txqi->tin.backlog_bytes,
+				 txqi->tin.backlog_packets,
+				 txqi->tin.flows,
+				 txqi->tin.overlimit,
+				 txqi->tin.collisions,
+				 txqi->tin.tx_bytes,
+				 txqi->tin.tx_packets);
+	}
+
+	len += scnprintf(info->buf + len,
+			 info->size - len,
+			 "* sta\n"
+			 "ifname addr tid ac backlog-bytes backlog-packets flows overlimit collisions tx-bytes tx-packets\n");
+
+	list_for_each_entry_rcu(sta, &local->sta_list, list) {
+		sdata = sta->sdata;
+		for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) {
+			txqi = to_txq_info(sta->sta.txq[i]);
+			len += scnprintf(info->buf + len, info->size - len,
+					 "%s %pM %d %d %u %u %u %u %u %u %u\n",
+					 sdata->name,
+					 sta->sta.addr,
+					 txqi->txq.tid,
+					 txqi->txq.ac,
+					 txqi->tin.backlog_bytes,
+					 txqi->tin.backlog_packets,
+					 txqi->tin.flows,
+					 txqi->tin.overlimit,
+					 txqi->tin.collisions,
+					 txqi->tin.tx_bytes,
+					 txqi->tin.tx_packets);
+		}
+	}
+
+	info->len = len;
+
+	rcu_read_unlock();
+	spin_unlock_bh(&local->fq.lock);
+
+	return 0;
+}
+
+static int aqm_release(struct inode *inode, struct file *file)
+{
+	vfree(file->private_data);
+	return 0;
+}
+
+static ssize_t aqm_read(struct file *file,
+			char __user *user_buf,
+			size_t count,
+			loff_t *ppos)
+{
+	struct aqm_info *info = file->private_data;
+
+	return simple_read_from_buffer(user_buf, count, ppos,
+				       info->buf, info->len);
+}
+
+static ssize_t aqm_write(struct file *file,
+			 const char __user *user_buf,
+			 size_t count,
+			 loff_t *ppos)
+{
+	struct aqm_info *info = file->private_data;
+	struct ieee80211_local *local = info->local;
+	char buf[100];
+	size_t len;
+
+	if (count > sizeof(buf))
+		return -EINVAL;
+
+	if (copy_from_user(buf, user_buf, count))
+		return -EFAULT;
+
+	buf[sizeof(buf) - 1] = '\0';
+	len = strlen(buf);
+	if (len > 0 && buf[len-1] == '\n')
+		buf[len-1] = 0;
+
+	if (sscanf(buf, "fq_limit %u", &local->fq.limit) == 1)
+		return count;
+	else if (sscanf(buf, "fq_quantum %u", &local->fq.quantum) == 1)
+		return count;
+
+	return -EINVAL;
+}
+
+static const struct file_operations aqm_ops = {
+	.write = aqm_write,
+	.read = aqm_read,
+	.open = aqm_open,
+	.release = aqm_release,
+	.llseek = default_llseek,
+};
+
 #ifdef CONFIG_PM
 static ssize_t reset_write(struct file *file, const char __user *user_buf,
 			   size_t count, loff_t *ppos)
@@ -256,6 +428,7 @@
 	DEBUGFS_ADD(hwflags);
 	DEBUGFS_ADD(user_power);
 	DEBUGFS_ADD(power);
+	DEBUGFS_ADD_MODE(aqm, 0600);
 
 	statsd = debugfs_create_dir("statistics", phyd);
 
diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c
index 33dfcbc..fd33413 100644
--- a/net/mac80211/debugfs_sta.c
+++ b/net/mac80211/debugfs_sta.c
@@ -328,14 +328,88 @@
 static ssize_t sta_vht_capa_read(struct file *file, char __user *userbuf,
 				 size_t count, loff_t *ppos)
 {
-	char buf[128], *p = buf;
+	char buf[512], *p = buf;
 	struct sta_info *sta = file->private_data;
 	struct ieee80211_sta_vht_cap *vhtc = &sta->sta.vht_cap;
 
 	p += scnprintf(p, sizeof(buf) + buf - p, "VHT %ssupported\n",
 			vhtc->vht_supported ? "" : "not ");
 	if (vhtc->vht_supported) {
-		p += scnprintf(p, sizeof(buf)+buf-p, "cap: %#.8x\n", vhtc->cap);
+		p += scnprintf(p, sizeof(buf) + buf - p, "cap: %#.8x\n",
+			       vhtc->cap);
+#define PFLAG(a, b)							\
+		do {							\
+			if (vhtc->cap & IEEE80211_VHT_CAP_ ## a)	\
+				p += scnprintf(p, sizeof(buf) + buf - p, \
+					       "\t\t%s\n", b);		\
+		} while (0)
+
+		switch (vhtc->cap & 0x3) {
+		case IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895:
+			p += scnprintf(p, sizeof(buf) + buf - p,
+				       "\t\tMAX-MPDU-3895\n");
+			break;
+		case IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991:
+			p += scnprintf(p, sizeof(buf) + buf - p,
+				       "\t\tMAX-MPDU-7991\n");
+			break;
+		case IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454:
+			p += scnprintf(p, sizeof(buf) + buf - p,
+				       "\t\tMAX-MPDU-11454\n");
+			break;
+		default:
+			p += scnprintf(p, sizeof(buf) + buf - p,
+				       "\t\tMAX-MPDU-UNKNOWN\n");
+		};
+		switch (vhtc->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK) {
+		case 0:
+			p += scnprintf(p, sizeof(buf) + buf - p,
+				       "\t\t80Mhz\n");
+			break;
+		case IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ:
+			p += scnprintf(p, sizeof(buf) + buf - p,
+				       "\t\t160Mhz\n");
+			break;
+		case IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ:
+			p += scnprintf(p, sizeof(buf) + buf - p,
+				       "\t\t80+80Mhz\n");
+			break;
+		default:
+			p += scnprintf(p, sizeof(buf) + buf - p,
+				       "\t\tUNKNOWN-MHZ: 0x%x\n",
+				       (vhtc->cap >> 2) & 0x3);
+		};
+		PFLAG(RXLDPC, "RXLDPC");
+		PFLAG(SHORT_GI_80, "SHORT-GI-80");
+		PFLAG(SHORT_GI_160, "SHORT-GI-160");
+		PFLAG(TXSTBC, "TXSTBC");
+		p += scnprintf(p, sizeof(buf) + buf - p,
+			       "\t\tRXSTBC_%d\n", (vhtc->cap >> 8) & 0x7);
+		PFLAG(SU_BEAMFORMER_CAPABLE, "SU-BEAMFORMER-CAPABLE");
+		PFLAG(SU_BEAMFORMEE_CAPABLE, "SU-BEAMFORMEE-CAPABLE");
+		p += scnprintf(p, sizeof(buf) + buf - p,
+			"\t\tBEAMFORMEE-STS: 0x%x\n",
+			(vhtc->cap & IEEE80211_VHT_CAP_BEAMFORMEE_STS_MASK) >>
+			IEEE80211_VHT_CAP_BEAMFORMEE_STS_SHIFT);
+		p += scnprintf(p, sizeof(buf) + buf - p,
+			"\t\tSOUNDING-DIMENSIONS: 0x%x\n",
+			(vhtc->cap & IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_MASK)
+			>> IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_SHIFT);
+		PFLAG(MU_BEAMFORMER_CAPABLE, "MU-BEAMFORMER-CAPABLE");
+		PFLAG(MU_BEAMFORMEE_CAPABLE, "MU-BEAMFORMEE-CAPABLE");
+		PFLAG(VHT_TXOP_PS, "TXOP-PS");
+		PFLAG(HTC_VHT, "HTC-VHT");
+		p += scnprintf(p, sizeof(buf) + buf - p,
+			"\t\tMPDU-LENGTH-EXPONENT: 0x%x\n",
+			(vhtc->cap & IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK) >>
+			IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_SHIFT);
+		PFLAG(VHT_LINK_ADAPTATION_VHT_UNSOL_MFB,
+		      "LINK-ADAPTATION-VHT-UNSOL-MFB");
+		p += scnprintf(p, sizeof(buf) + buf - p,
+			"\t\tLINK-ADAPTATION-VHT-MRQ-MFB: 0x%x\n",
+			(vhtc->cap & IEEE80211_VHT_CAP_VHT_LINK_ADAPTATION_VHT_MRQ_MFB) >> 26);
+		PFLAG(RX_ANTENNA_PATTERN, "RX-ANTENNA-PATTERN");
+		PFLAG(TX_ANTENNA_PATTERN, "TX-ANTENNA-PATTERN");
 
 		p += scnprintf(p, sizeof(buf)+buf-p, "RX MCS: %.4x\n",
 			       le16_to_cpu(vhtc->vht_mcs.rx_mcs_map));
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 9438c94..54edfb6 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -30,6 +30,7 @@
 #include <net/ieee80211_radiotap.h>
 #include <net/cfg80211.h>
 #include <net/mac80211.h>
+#include <net/fq.h>
 #include "key.h"
 #include "sta_info.h"
 #include "debug.h"
@@ -805,10 +806,19 @@
 	IEEE80211_TXQ_NO_AMSDU,
 };
 
+/**
+ * struct txq_info - per tid queue
+ *
+ * @tin: contains packets split into multiple flows
+ * @def_flow: used as a fallback flow when a packet destined to @tin hashes to
+ *	a fq_flow which is already owned by a different tin
+ * @def_cvars: codel vars for @def_flow
+ */
 struct txq_info {
-	struct sk_buff_head queue;
+	struct fq_tin tin;
+	struct fq_flow def_flow;
+	struct codel_vars def_cvars;
 	unsigned long flags;
-	unsigned long byte_cnt;
 
 	/* keep last! */
 	struct ieee80211_txq txq;
@@ -856,7 +866,7 @@
 	bool control_port_no_encrypt;
 	int encrypt_headroom;
 
-	atomic_t txqs_len[IEEE80211_NUM_ACS];
+	atomic_t num_tx_queued;
 	struct ieee80211_tx_queue_params tx_conf[IEEE80211_NUM_ACS];
 	struct mac80211_qos_map __rcu *qos_map;
 
@@ -1099,6 +1109,11 @@
 	 * it first anyway so they become a no-op */
 	struct ieee80211_hw hw;
 
+	struct fq fq;
+	struct codel_vars *cvars;
+	struct codel_params cparams;
+	struct codel_stats cstats;
+
 	const struct ieee80211_ops *ops;
 
 	/*
@@ -1931,9 +1946,13 @@
 	return true;
 }
 
-void ieee80211_init_tx_queue(struct ieee80211_sub_if_data *sdata,
-			     struct sta_info *sta,
-			     struct txq_info *txq, int tid);
+int ieee80211_txq_setup_flows(struct ieee80211_local *local);
+void ieee80211_txq_teardown_flows(struct ieee80211_local *local);
+void ieee80211_txq_init(struct ieee80211_sub_if_data *sdata,
+			struct sta_info *sta,
+			struct txq_info *txq, int tid);
+void ieee80211_txq_purge(struct ieee80211_local *local,
+			 struct txq_info *txqi);
 void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata,
 			 u16 transaction, u16 auth_alg, u16 status,
 			 const u8 *extra, size_t extra_len, const u8 *bssid,
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index c59af3e..b123a9e 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -779,6 +779,7 @@
 			      bool going_down)
 {
 	struct ieee80211_local *local = sdata->local;
+	struct fq *fq = &local->fq;
 	unsigned long flags;
 	struct sk_buff *skb, *tmp;
 	u32 hw_reconf_flags = 0;
@@ -977,12 +978,9 @@
 	if (sdata->vif.txq) {
 		struct txq_info *txqi = to_txq_info(sdata->vif.txq);
 
-		spin_lock_bh(&txqi->queue.lock);
-		ieee80211_purge_tx_queue(&local->hw, &txqi->queue);
-		txqi->byte_cnt = 0;
-		spin_unlock_bh(&txqi->queue.lock);
-
-		atomic_set(&sdata->txqs_len[txqi->txq.ac], 0);
+		spin_lock_bh(&fq->lock);
+		ieee80211_txq_purge(local, txqi);
+		spin_unlock_bh(&fq->lock);
 	}
 
 	if (local->open_count == 0)
@@ -1198,6 +1196,12 @@
 	dev->destructor = ieee80211_if_free;
 }
 
+static void ieee80211_if_setup_no_queue(struct net_device *dev)
+{
+	ieee80211_if_setup(dev);
+	dev->priv_flags |= IFF_NO_QUEUE;
+}
+
 static void ieee80211_iface_work(struct work_struct *work)
 {
 	struct ieee80211_sub_if_data *sdata =
@@ -1707,6 +1711,7 @@
 	struct net_device *ndev = NULL;
 	struct ieee80211_sub_if_data *sdata = NULL;
 	struct txq_info *txqi;
+	void (*if_setup)(struct net_device *dev);
 	int ret, i;
 	int txqs = 1;
 
@@ -1734,12 +1739,17 @@
 			txq_size += sizeof(struct txq_info) +
 				    local->hw.txq_data_size;
 
+		if (local->ops->wake_tx_queue)
+			if_setup = ieee80211_if_setup_no_queue;
+		else
+			if_setup = ieee80211_if_setup;
+
 		if (local->hw.queues >= IEEE80211_NUM_ACS)
 			txqs = IEEE80211_NUM_ACS;
 
 		ndev = alloc_netdev_mqs(size + txq_size,
 					name, name_assign_type,
-					ieee80211_if_setup, txqs, 1);
+					if_setup, txqs, 1);
 		if (!ndev)
 			return -ENOMEM;
 		dev_net_set(ndev, wiphy_net(local->hw.wiphy));
@@ -1780,7 +1790,7 @@
 
 		if (txq_size) {
 			txqi = netdev_priv(ndev) + size;
-			ieee80211_init_tx_queue(sdata, NULL, txqi, 0);
+			ieee80211_txq_init(sdata, NULL, txqi, 0);
 		}
 
 		sdata->dev = ndev;
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 7ee91d6..d00ea9b 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -1055,9 +1055,6 @@
 
 	local->dynamic_ps_forced_timeout = -1;
 
-	if (!local->hw.txq_ac_max_pending)
-		local->hw.txq_ac_max_pending = 64;
-
 	result = ieee80211_wep_init(local);
 	if (result < 0)
 		wiphy_debug(local->hw.wiphy, "Failed to initialize wep: %d\n",
@@ -1089,6 +1086,10 @@
 
 	rtnl_unlock();
 
+	result = ieee80211_txq_setup_flows(local);
+	if (result)
+		goto fail_flows;
+
 #ifdef CONFIG_INET
 	local->ifa_notifier.notifier_call = ieee80211_ifa_changed;
 	result = register_inetaddr_notifier(&local->ifa_notifier);
@@ -1114,6 +1115,8 @@
 #if defined(CONFIG_INET) || defined(CONFIG_IPV6)
  fail_ifa:
 #endif
+	ieee80211_txq_teardown_flows(local);
+ fail_flows:
 	rtnl_lock();
 	rate_control_deinitialize(local);
 	ieee80211_remove_interfaces(local);
@@ -1172,6 +1175,7 @@
 	skb_queue_purge(&local->skb_queue);
 	skb_queue_purge(&local->skb_queue_unreliable);
 	skb_queue_purge(&local->skb_queue_tdls_chsw);
+	ieee80211_txq_teardown_flows(local);
 
 	destroy_workqueue(local->workqueue);
 	wiphy_unregister(local->hw.wiphy);
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index 4c6404e..21b1fdf 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -161,6 +161,10 @@
 		del_timer_sync(&sta->mesh->plink_timer);
 	}
 
+	/* make sure no readers can access nexthop sta from here on */
+	mesh_path_flush_by_nexthop(sta);
+	synchronize_net();
+
 	if (changed)
 		ieee80211_mbss_info_change_notify(sdata, changed);
 }
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 5e65e83..9a1eb70 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -1268,7 +1268,7 @@
 	for (tid = 0; tid < ARRAY_SIZE(sta->sta.txq); tid++) {
 		struct txq_info *txqi = to_txq_info(sta->sta.txq[tid]);
 
-		if (!skb_queue_len(&txqi->queue))
+		if (!txqi->tin.backlog_packets)
 			set_bit(tid, &sta->txq_buffered_tids);
 		else
 			clear_bit(tid, &sta->txq_buffered_tids);
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 5ccfdbd..76b737d 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -90,6 +90,7 @@
 	struct tid_ampdu_tx *tid_tx;
 	struct ieee80211_sub_if_data *sdata = sta->sdata;
 	struct ieee80211_local *local = sdata->local;
+	struct fq *fq = &local->fq;
 	struct ps_data *ps;
 
 	if (test_sta_flag(sta, WLAN_STA_PS_STA) ||
@@ -113,11 +114,10 @@
 	if (sta->sta.txq[0]) {
 		for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) {
 			struct txq_info *txqi = to_txq_info(sta->sta.txq[i]);
-			int n = skb_queue_len(&txqi->queue);
 
-			ieee80211_purge_tx_queue(&local->hw, &txqi->queue);
-			atomic_sub(n, &sdata->txqs_len[txqi->txq.ac]);
-			txqi->byte_cnt = 0;
+			spin_lock_bh(&fq->lock);
+			ieee80211_txq_purge(local, txqi);
+			spin_unlock_bh(&fq->lock);
 		}
 	}
 
@@ -368,7 +368,7 @@
 		for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) {
 			struct txq_info *txq = txq_data + i * size;
 
-			ieee80211_init_tx_queue(sdata, sta, txq, i);
+			ieee80211_txq_init(sdata, sta, txq, i);
 		}
 	}
 
@@ -1211,7 +1211,7 @@
 		for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) {
 			struct txq_info *txqi = to_txq_info(sta->sta.txq[i]);
 
-			if (!skb_queue_len(&txqi->queue))
+			if (!txqi->tin.backlog_packets)
 				continue;
 
 			drv_wake_tx_queue(local, txqi);
@@ -1648,7 +1648,7 @@
 		for (tid = 0; tid < ARRAY_SIZE(sta->sta.txq); tid++) {
 			struct txq_info *txqi = to_txq_info(sta->sta.txq[tid]);
 
-			if (!(tids & BIT(tid)) || skb_queue_len(&txqi->queue))
+			if (!(tids & BIT(tid)) || txqi->tin.backlog_packets)
 				continue;
 
 			sta_info_recalc_tim(sta);
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index c8b8ccc..78b0ef3 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -280,7 +280,7 @@
 	u8 sa_offs, da_offs, pn_offs;
 	u8 band;
 	u8 hdr[30 + 2 + IEEE80211_FAST_XMIT_MAX_IV +
-	       sizeof(rfc1042_header)];
+	       sizeof(rfc1042_header)] __aligned(2);
 
 	struct rcu_head rcu_head;
 };
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 2030443..44ec605 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -24,7 +24,10 @@
 #include <net/ieee80211_radiotap.h>
 #include <net/cfg80211.h>
 #include <net/mac80211.h>
+#include <net/codel.h>
+#include <net/codel_impl.h>
 #include <asm/unaligned.h>
+#include <net/fq_impl.h>
 
 #include "ieee80211_i.h"
 #include "driver-ops.h"
@@ -1236,27 +1239,21 @@
 	return TX_CONTINUE;
 }
 
-static void ieee80211_drv_tx(struct ieee80211_local *local,
-			     struct ieee80211_vif *vif,
-			     struct ieee80211_sta *pubsta,
-			     struct sk_buff *skb)
+static struct txq_info *ieee80211_get_txq(struct ieee80211_local *local,
+					  struct ieee80211_vif *vif,
+					  struct ieee80211_sta *pubsta,
+					  struct sk_buff *skb)
 {
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
-	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
-	struct ieee80211_tx_control control = {
-		.sta = pubsta,
-	};
 	struct ieee80211_txq *txq = NULL;
-	struct txq_info *txqi;
-	u8 ac;
 
 	if ((info->flags & IEEE80211_TX_CTL_SEND_AFTER_DTIM) ||
 	    (info->control.flags & IEEE80211_TX_CTRL_PS_RESPONSE))
-		goto tx_normal;
+		return NULL;
 
 	if (!ieee80211_is_data(hdr->frame_control))
-		goto tx_normal;
+		return NULL;
 
 	if (pubsta) {
 		u8 tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK;
@@ -1267,51 +1264,230 @@
 	}
 
 	if (!txq)
-		goto tx_normal;
+		return NULL;
 
-	ac = txq->ac;
-	txqi = to_txq_info(txq);
-	atomic_inc(&sdata->txqs_len[ac]);
-	if (atomic_read(&sdata->txqs_len[ac]) >= local->hw.txq_ac_max_pending)
-		netif_stop_subqueue(sdata->dev, ac);
+	return to_txq_info(txq);
+}
 
-	spin_lock_bh(&txqi->queue.lock);
-	txqi->byte_cnt += skb->len;
-	__skb_queue_tail(&txqi->queue, skb);
-	spin_unlock_bh(&txqi->queue.lock);
+static void ieee80211_set_skb_enqueue_time(struct sk_buff *skb)
+{
+	IEEE80211_SKB_CB(skb)->control.enqueue_time = codel_get_time();
+}
 
-	drv_wake_tx_queue(local, txqi);
+static void ieee80211_set_skb_vif(struct sk_buff *skb, struct txq_info *txqi)
+{
+	IEEE80211_SKB_CB(skb)->control.vif = txqi->txq.vif;
+}
 
-	return;
+static u32 codel_skb_len_func(const struct sk_buff *skb)
+{
+	return skb->len;
+}
 
-tx_normal:
-	drv_tx(local, &control, skb);
+static codel_time_t codel_skb_time_func(const struct sk_buff *skb)
+{
+	const struct ieee80211_tx_info *info;
+
+	info = (const struct ieee80211_tx_info *)skb->cb;
+	return info->control.enqueue_time;
+}
+
+static struct sk_buff *codel_dequeue_func(struct codel_vars *cvars,
+					  void *ctx)
+{
+	struct ieee80211_local *local;
+	struct txq_info *txqi;
+	struct fq *fq;
+	struct fq_flow *flow;
+
+	txqi = ctx;
+	local = vif_to_sdata(txqi->txq.vif)->local;
+	fq = &local->fq;
+
+	if (cvars == &txqi->def_cvars)
+		flow = &txqi->def_flow;
+	else
+		flow = &fq->flows[cvars - local->cvars];
+
+	return fq_flow_dequeue(fq, flow);
+}
+
+static void codel_drop_func(struct sk_buff *skb,
+			    void *ctx)
+{
+	struct ieee80211_local *local;
+	struct ieee80211_hw *hw;
+	struct txq_info *txqi;
+
+	txqi = ctx;
+	local = vif_to_sdata(txqi->txq.vif)->local;
+	hw = &local->hw;
+
+	ieee80211_free_txskb(hw, skb);
+}
+
+static struct sk_buff *fq_tin_dequeue_func(struct fq *fq,
+					   struct fq_tin *tin,
+					   struct fq_flow *flow)
+{
+	struct ieee80211_local *local;
+	struct txq_info *txqi;
+	struct codel_vars *cvars;
+	struct codel_params *cparams;
+	struct codel_stats *cstats;
+
+	local = container_of(fq, struct ieee80211_local, fq);
+	txqi = container_of(tin, struct txq_info, tin);
+	cparams = &local->cparams;
+	cstats = &local->cstats;
+
+	if (flow == &txqi->def_flow)
+		cvars = &txqi->def_cvars;
+	else
+		cvars = &local->cvars[flow - fq->flows];
+
+	return codel_dequeue(txqi,
+			     &flow->backlog,
+			     cparams,
+			     cvars,
+			     cstats,
+			     codel_skb_len_func,
+			     codel_skb_time_func,
+			     codel_drop_func,
+			     codel_dequeue_func);
+}
+
+static void fq_skb_free_func(struct fq *fq,
+			     struct fq_tin *tin,
+			     struct fq_flow *flow,
+			     struct sk_buff *skb)
+{
+	struct ieee80211_local *local;
+
+	local = container_of(fq, struct ieee80211_local, fq);
+	ieee80211_free_txskb(&local->hw, skb);
+}
+
+static struct fq_flow *fq_flow_get_default_func(struct fq *fq,
+						struct fq_tin *tin,
+						int idx,
+						struct sk_buff *skb)
+{
+	struct txq_info *txqi;
+
+	txqi = container_of(tin, struct txq_info, tin);
+	return &txqi->def_flow;
+}
+
+static void ieee80211_txq_enqueue(struct ieee80211_local *local,
+				  struct txq_info *txqi,
+				  struct sk_buff *skb)
+{
+	struct fq *fq = &local->fq;
+	struct fq_tin *tin = &txqi->tin;
+
+	ieee80211_set_skb_enqueue_time(skb);
+	fq_tin_enqueue(fq, tin, skb,
+		       fq_skb_free_func,
+		       fq_flow_get_default_func);
+}
+
+void ieee80211_txq_init(struct ieee80211_sub_if_data *sdata,
+			struct sta_info *sta,
+			struct txq_info *txqi, int tid)
+{
+	fq_tin_init(&txqi->tin);
+	fq_flow_init(&txqi->def_flow);
+	codel_vars_init(&txqi->def_cvars);
+
+	txqi->txq.vif = &sdata->vif;
+
+	if (sta) {
+		txqi->txq.sta = &sta->sta;
+		sta->sta.txq[tid] = &txqi->txq;
+		txqi->txq.tid = tid;
+		txqi->txq.ac = ieee802_1d_to_ac[tid & 7];
+	} else {
+		sdata->vif.txq = &txqi->txq;
+		txqi->txq.tid = 0;
+		txqi->txq.ac = IEEE80211_AC_BE;
+	}
+}
+
+void ieee80211_txq_purge(struct ieee80211_local *local,
+			 struct txq_info *txqi)
+{
+	struct fq *fq = &local->fq;
+	struct fq_tin *tin = &txqi->tin;
+
+	fq_tin_reset(fq, tin, fq_skb_free_func);
+}
+
+int ieee80211_txq_setup_flows(struct ieee80211_local *local)
+{
+	struct fq *fq = &local->fq;
+	int ret;
+	int i;
+
+	if (!local->ops->wake_tx_queue)
+		return 0;
+
+	ret = fq_init(fq, 4096);
+	if (ret)
+		return ret;
+
+	codel_params_init(&local->cparams);
+	codel_stats_init(&local->cstats);
+	local->cparams.interval = MS2TIME(100);
+	local->cparams.target = MS2TIME(20);
+	local->cparams.ecn = true;
+
+	local->cvars = kcalloc(fq->flows_cnt, sizeof(local->cvars[0]),
+			       GFP_KERNEL);
+	if (!local->cvars) {
+		fq_reset(fq, fq_skb_free_func);
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < fq->flows_cnt; i++)
+		codel_vars_init(&local->cvars[i]);
+
+	return 0;
+}
+
+void ieee80211_txq_teardown_flows(struct ieee80211_local *local)
+{
+	struct fq *fq = &local->fq;
+
+	if (!local->ops->wake_tx_queue)
+		return;
+
+	kfree(local->cvars);
+	local->cvars = NULL;
+
+	fq_reset(fq, fq_skb_free_func);
 }
 
 struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw,
 				     struct ieee80211_txq *txq)
 {
 	struct ieee80211_local *local = hw_to_local(hw);
-	struct ieee80211_sub_if_data *sdata = vif_to_sdata(txq->vif);
 	struct txq_info *txqi = container_of(txq, struct txq_info, txq);
 	struct ieee80211_hdr *hdr;
 	struct sk_buff *skb = NULL;
-	u8 ac = txq->ac;
+	struct fq *fq = &local->fq;
+	struct fq_tin *tin = &txqi->tin;
 
-	spin_lock_bh(&txqi->queue.lock);
+	spin_lock_bh(&fq->lock);
 
 	if (test_bit(IEEE80211_TXQ_STOP, &txqi->flags))
 		goto out;
 
-	skb = __skb_dequeue(&txqi->queue);
+	skb = fq_tin_dequeue(fq, tin, fq_tin_dequeue_func);
 	if (!skb)
 		goto out;
 
-	txqi->byte_cnt -= skb->len;
-
-	atomic_dec(&sdata->txqs_len[ac]);
-	if (__netif_subqueue_stopped(sdata->dev, ac))
-		ieee80211_propagate_queue_wake(local, sdata->vif.hw_queue[ac]);
+	ieee80211_set_skb_vif(skb, txqi);
 
 	hdr = (struct ieee80211_hdr *)skb->data;
 	if (txq->sta && ieee80211_is_data_qos(hdr->frame_control)) {
@@ -1327,7 +1503,7 @@
 	}
 
 out:
-	spin_unlock_bh(&txqi->queue.lock);
+	spin_unlock_bh(&fq->lock);
 
 	if (skb && skb_has_frag_list(skb) &&
 	    !ieee80211_hw_check(&local->hw, TX_FRAG_LIST))
@@ -1343,7 +1519,10 @@
 			       struct sk_buff_head *skbs,
 			       bool txpending)
 {
+	struct ieee80211_tx_control control = {};
+	struct fq *fq = &local->fq;
 	struct sk_buff *skb, *tmp;
+	struct txq_info *txqi;
 	unsigned long flags;
 
 	skb_queue_walk_safe(skbs, skb, tmp) {
@@ -1358,6 +1537,21 @@
 		}
 #endif
 
+		txqi = ieee80211_get_txq(local, vif, sta, skb);
+		if (txqi) {
+			info->control.vif = vif;
+
+			__skb_unlink(skb, skbs);
+
+			spin_lock_bh(&fq->lock);
+			ieee80211_txq_enqueue(local, txqi, skb);
+			spin_unlock_bh(&fq->lock);
+
+			drv_wake_tx_queue(local, txqi);
+
+			continue;
+		}
+
 		spin_lock_irqsave(&local->queue_stop_reason_lock, flags);
 		if (local->queue_stop_reasons[q] ||
 		    (!txpending && !skb_queue_empty(&local->pending[q]))) {
@@ -1400,9 +1594,10 @@
 		spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);
 
 		info->control.vif = vif;
+		control.sta = sta;
 
 		__skb_unlink(skb, skbs);
-		ieee80211_drv_tx(local, vif, sta, skb);
+		drv_tx(local, &control, skb);
 	}
 
 	return true;
@@ -2882,6 +3077,9 @@
 				      struct sk_buff *skb)
 {
 	struct ieee80211_local *local = sdata->local;
+	struct fq *fq = &local->fq;
+	struct fq_tin *tin;
+	struct fq_flow *flow;
 	u8 tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK;
 	struct ieee80211_txq *txq = sta->sta.txq[tid];
 	struct txq_info *txqi;
@@ -2893,6 +3091,7 @@
 	__be16 len;
 	void *data;
 	bool ret = false;
+	unsigned int orig_len;
 	int n = 1, nfrags;
 
 	if (!ieee80211_hw_check(&local->hw, TX_AMSDU))
@@ -2909,12 +3108,20 @@
 		max_amsdu_len = min_t(int, max_amsdu_len,
 				      sta->sta.max_rc_amsdu_len);
 
-	spin_lock_bh(&txqi->queue.lock);
+	spin_lock_bh(&fq->lock);
 
-	head = skb_peek_tail(&txqi->queue);
+	/* TODO: Ideally aggregation should be done on dequeue to remain
+	 * responsive to environment changes.
+	 */
+
+	tin = &txqi->tin;
+	flow = fq_flow_classify(fq, tin, skb, fq_flow_get_default_func);
+	head = skb_peek_tail(&flow->queue);
 	if (!head)
 		goto out;
 
+	orig_len = head->len;
+
 	if (skb->len + head->len > max_amsdu_len)
 		goto out;
 
@@ -2953,8 +3160,13 @@
 	head->data_len += skb->len;
 	*frag_tail = skb;
 
+	flow->backlog += head->len - orig_len;
+	tin->backlog_bytes += head->len - orig_len;
+
+	fq_recalc_backlog(fq, tin, flow);
+
 out:
-	spin_unlock_bh(&txqi->queue.lock);
+	spin_unlock_bh(&fq->lock);
 
 	return ret;
 }
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 905003f..42bf0b6 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -244,6 +244,9 @@
 	struct ieee80211_sub_if_data *sdata;
 	int n_acs = IEEE80211_NUM_ACS;
 
+	if (local->ops->wake_tx_queue)
+		return;
+
 	if (local->hw.queues < IEEE80211_NUM_ACS)
 		n_acs = 1;
 
@@ -260,11 +263,6 @@
 		for (ac = 0; ac < n_acs; ac++) {
 			int ac_queue = sdata->vif.hw_queue[ac];
 
-			if (local->ops->wake_tx_queue &&
-			    (atomic_read(&sdata->txqs_len[ac]) >
-			     local->hw.txq_ac_max_pending))
-				continue;
-
 			if (ac_queue == queue ||
 			    (sdata->vif.cab_queue == queue &&
 			     local->queue_stop_reasons[ac_queue] == 0 &&
@@ -352,6 +350,9 @@
 	if (__test_and_set_bit(reason, &local->queue_stop_reasons[queue]))
 		return;
 
+	if (local->ops->wake_tx_queue)
+		return;
+
 	if (local->hw.queues < IEEE80211_NUM_ACS)
 		n_acs = 1;
 
@@ -3388,25 +3389,6 @@
 	return buf;
 }
 
-void ieee80211_init_tx_queue(struct ieee80211_sub_if_data *sdata,
-			     struct sta_info *sta,
-			     struct txq_info *txqi, int tid)
-{
-	skb_queue_head_init(&txqi->queue);
-	txqi->txq.vif = &sdata->vif;
-
-	if (sta) {
-		txqi->txq.sta = &sta->sta;
-		sta->sta.txq[tid] = &txqi->txq;
-		txqi->txq.tid = tid;
-		txqi->txq.ac = ieee802_1d_to_ac[tid & 7];
-	} else {
-		sdata->vif.txq = &txqi->txq;
-		txqi->txq.tid = 0;
-		txqi->txq.ac = IEEE80211_AC_BE;
-	}
-}
-
 void ieee80211_txq_get_depth(struct ieee80211_txq *txq,
 			     unsigned long *frame_cnt,
 			     unsigned long *byte_cnt)
@@ -3414,9 +3396,9 @@
 	struct txq_info *txqi = to_txq_info(txq);
 
 	if (frame_cnt)
-		*frame_cnt = txqi->queue.qlen;
+		*frame_cnt = txqi->tin.backlog_packets;
 
 	if (byte_cnt)
-		*byte_cnt = txqi->byte_cnt;
+		*byte_cnt = txqi->tin.backlog_bytes;
 }
 EXPORT_SYMBOL(ieee80211_txq_get_depth);
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 7a4aa34..e9beaa5 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -1009,9 +1009,10 @@
 	unsigned int flags;
 
 	if (event == NETDEV_REGISTER) {
-		/* For now just support ethernet devices */
-		if ((dev->type == ARPHRD_ETHER) ||
-		    (dev->type == ARPHRD_LOOPBACK)) {
+		/* For now just support Ethernet and IPGRE devices */
+		if (dev->type == ARPHRD_ETHER ||
+		    dev->type == ARPHRD_LOOPBACK ||
+		    dev->type == ARPHRD_IPGRE) {
 			mdev = mpls_add_dev(dev);
 			if (IS_ERR(mdev))
 				return notifier_from_errno(PTR_ERR(mdev));
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 2cb3c62..096a451 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -762,7 +762,7 @@
  *	If available, return 1, otherwise invalidate this connection
  *	template and return 0.
  */
-int ip_vs_check_template(struct ip_vs_conn *ct)
+int ip_vs_check_template(struct ip_vs_conn *ct, struct ip_vs_dest *cdest)
 {
 	struct ip_vs_dest *dest = ct->dest;
 	struct netns_ipvs *ipvs = ct->ipvs;
@@ -772,7 +772,8 @@
 	 */
 	if ((dest == NULL) ||
 	    !(dest->flags & IP_VS_DEST_F_AVAILABLE) ||
-	    expire_quiescent_template(ipvs, dest)) {
+	    expire_quiescent_template(ipvs, dest) ||
+	    (cdest && (dest != cdest))) {
 		IP_VS_DBG_BUF(9, "check_template: dest not available for "
 			      "protocol %s s:%s:%d v:%s:%d "
 			      "-> d:%s:%d\n",
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 1207f20..2c1b498 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -321,7 +321,7 @@
 
 	/* Check if a template already exists */
 	ct = ip_vs_ct_in_get(&param);
-	if (!ct || !ip_vs_check_template(ct)) {
+	if (!ct || !ip_vs_check_template(ct, NULL)) {
 		struct ip_vs_scheduler *sched;
 
 		/*
@@ -1154,7 +1154,8 @@
 						  vport, &param) < 0)
 			return NULL;
 		ct = ip_vs_ct_in_get(&param);
-		if (!ct) {
+		/* check if template exists and points to the same dest */
+		if (!ct || !ip_vs_check_template(ct, dest)) {
 			ct = ip_vs_conn_new(&param, dest->af, daddr, dport,
 					    IP_VS_CONN_F_TEMPLATE, dest, 0);
 			if (!ct) {
diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c
index 883c691..19efeba 100644
--- a/net/netfilter/nf_conntrack_ftp.c
+++ b/net/netfilter/nf_conntrack_ftp.c
@@ -632,6 +632,7 @@
 			if (ret) {
 				pr_err("failed to register helper for pf: %d port: %d\n",
 				       ftp[i][j].tuple.src.l3num, ports[i]);
+				ports_c = i;
 				nf_conntrack_ftp_fini();
 				return ret;
 			}
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index f703adb..196cb39 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -361,9 +361,10 @@
 
 int nf_conntrack_helper_register(struct nf_conntrack_helper *me)
 {
-	int ret = 0;
-	struct nf_conntrack_helper *cur;
+	struct nf_conntrack_tuple_mask mask = { .src.u.all = htons(0xFFFF) };
 	unsigned int h = helper_hash(&me->tuple);
+	struct nf_conntrack_helper *cur;
+	int ret = 0;
 
 	BUG_ON(me->expect_policy == NULL);
 	BUG_ON(me->expect_class_max >= NF_CT_MAX_EXPECT_CLASSES);
@@ -371,9 +372,7 @@
 
 	mutex_lock(&nf_ct_helper_mutex);
 	hlist_for_each_entry(cur, &nf_ct_helper_hash[h], hnode) {
-		if (strncmp(cur->name, me->name, NF_CT_HELPER_NAME_LEN) == 0 &&
-		    cur->tuple.src.l3num == me->tuple.src.l3num &&
-		    cur->tuple.dst.protonum == me->tuple.dst.protonum) {
+		if (nf_ct_tuple_src_mask_cmp(&cur->tuple, &me->tuple, &mask)) {
 			ret = -EEXIST;
 			goto out;
 		}
diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c
index 8b6da27..f97ac61 100644
--- a/net/netfilter/nf_conntrack_irc.c
+++ b/net/netfilter/nf_conntrack_irc.c
@@ -271,6 +271,7 @@
 		if (ret) {
 			pr_err("failed to register helper for pf: %u port: %u\n",
 			       irc[i].tuple.src.l3num, ports[i]);
+			ports_c = i;
 			nf_conntrack_irc_fini();
 			return ret;
 		}
diff --git a/net/netfilter/nf_conntrack_sane.c b/net/netfilter/nf_conntrack_sane.c
index 7523a57..3fcbaab 100644
--- a/net/netfilter/nf_conntrack_sane.c
+++ b/net/netfilter/nf_conntrack_sane.c
@@ -223,6 +223,7 @@
 			if (ret) {
 				pr_err("failed to register helper for pf: %d port: %d\n",
 				       sane[i][j].tuple.src.l3num, ports[i]);
+				ports_c = i;
 				nf_conntrack_sane_fini();
 				return ret;
 			}
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index 3e06402..f72ba55 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -1669,6 +1669,7 @@
 			if (ret) {
 				pr_err("failed to register helper for pf: %u port: %u\n",
 				       sip[i][j].tuple.src.l3num, ports[i]);
+				ports_c = i;
 				nf_conntrack_sip_fini();
 				return ret;
 			}
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index f87e84e..c026c47 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -487,8 +487,6 @@
 	{ }
 };
 
-#define NET_NF_CONNTRACK_MAX 2089
-
 static struct ctl_table nf_ct_netfilter_table[] = {
 	{
 		.procname	= "nf_conntrack_max",
diff --git a/net/netfilter/nf_conntrack_tftp.c b/net/netfilter/nf_conntrack_tftp.c
index 36f9640..2e65b543 100644
--- a/net/netfilter/nf_conntrack_tftp.c
+++ b/net/netfilter/nf_conntrack_tftp.c
@@ -142,6 +142,7 @@
 			if (ret) {
 				pr_err("failed to register helper for pf: %u port: %u\n",
 				       tftp[i][j].tuple.src.l3num, ports[i]);
+				ports_c = i;
 				nf_conntrack_tftp_fini();
 				return ret;
 			}
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index 5baa8e2..b19ad20 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -26,23 +26,21 @@
  * Once the queue is registered it must reinject all packets it
  * receives, no matter what.
  */
-static const struct nf_queue_handler __rcu *queue_handler __read_mostly;
 
 /* return EBUSY when somebody else is registered, return EEXIST if the
  * same handler is registered, return 0 in case of success. */
-void nf_register_queue_handler(const struct nf_queue_handler *qh)
+void nf_register_queue_handler(struct net *net, const struct nf_queue_handler *qh)
 {
 	/* should never happen, we only have one queueing backend in kernel */
-	WARN_ON(rcu_access_pointer(queue_handler));
-	rcu_assign_pointer(queue_handler, qh);
+	WARN_ON(rcu_access_pointer(net->nf.queue_handler));
+	rcu_assign_pointer(net->nf.queue_handler, qh);
 }
 EXPORT_SYMBOL(nf_register_queue_handler);
 
 /* The caller must flush their queue before this */
-void nf_unregister_queue_handler(void)
+void nf_unregister_queue_handler(struct net *net)
 {
-	RCU_INIT_POINTER(queue_handler, NULL);
-	synchronize_rcu();
+	RCU_INIT_POINTER(net->nf.queue_handler, NULL);
 }
 EXPORT_SYMBOL(nf_unregister_queue_handler);
 
@@ -103,7 +101,7 @@
 	const struct nf_queue_handler *qh;
 
 	rcu_read_lock();
-	qh = rcu_dereference(queue_handler);
+	qh = rcu_dereference(net->nf.queue_handler);
 	if (qh)
 		qh->nf_hook_drop(net, ops);
 	rcu_read_unlock();
@@ -122,9 +120,10 @@
 	struct nf_queue_entry *entry = NULL;
 	const struct nf_afinfo *afinfo;
 	const struct nf_queue_handler *qh;
+	struct net *net = state->net;
 
 	/* QUEUE == DROP if no one is waiting, to be safe. */
-	qh = rcu_dereference(queue_handler);
+	qh = rcu_dereference(net->nf.queue_handler);
 	if (!qh) {
 		status = -ESRCH;
 		goto err;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 4d292b9..7b7aa87 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2647,6 +2647,8 @@
 	/* Only accept unspec with dump */
 	if (nfmsg->nfgen_family == NFPROTO_UNSPEC)
 		return -EAFNOSUPPORT;
+	if (!nla[NFTA_SET_TABLE])
+		return -EINVAL;
 
 	set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_NAME]);
 	if (IS_ERR(set))
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index aa93877..5d36a09 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -557,7 +557,7 @@
 
 	if (entskb->tstamp.tv64) {
 		struct nfqnl_msg_packet_timestamp ts;
-		struct timespec64 kts = ktime_to_timespec64(skb->tstamp);
+		struct timespec64 kts = ktime_to_timespec64(entskb->tstamp);
 
 		ts.sec = cpu_to_be64(kts.tv_sec);
 		ts.usec = cpu_to_be64(kts.tv_nsec / NSEC_PER_USEC);
@@ -1482,21 +1482,29 @@
 			 net->nf.proc_netfilter, &nfqnl_file_ops))
 		return -ENOMEM;
 #endif
+	nf_register_queue_handler(net, &nfqh);
 	return 0;
 }
 
 static void __net_exit nfnl_queue_net_exit(struct net *net)
 {
+	nf_unregister_queue_handler(net);
 #ifdef CONFIG_PROC_FS
 	remove_proc_entry("nfnetlink_queue", net->nf.proc_netfilter);
 #endif
 }
 
+static void nfnl_queue_net_exit_batch(struct list_head *net_exit_list)
+{
+	synchronize_rcu();
+}
+
 static struct pernet_operations nfnl_queue_net_ops = {
-	.init	= nfnl_queue_net_init,
-	.exit	= nfnl_queue_net_exit,
-	.id	= &nfnl_queue_net_id,
-	.size	= sizeof(struct nfnl_queue_net),
+	.init		= nfnl_queue_net_init,
+	.exit		= nfnl_queue_net_exit,
+	.exit_batch	= nfnl_queue_net_exit_batch,
+	.id		= &nfnl_queue_net_id,
+	.size		= sizeof(struct nfnl_queue_net),
 };
 
 static int __init nfnetlink_queue_init(void)
@@ -1517,7 +1525,6 @@
 	}
 
 	register_netdevice_notifier(&nfqnl_dev_notifier);
-	nf_register_queue_handler(&nfqh);
 	return status;
 
 cleanup_netlink_notifier:
@@ -1529,7 +1536,6 @@
 
 static void __exit nfnetlink_queue_fini(void)
 {
-	nf_unregister_queue_handler();
 	unregister_netdevice_notifier(&nfqnl_dev_notifier);
 	nfnetlink_subsys_unregister(&nfqnl_subsys);
 	netlink_unregister_notifier(&nfqnl_rtnl_notifier);
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index c69c892..2675d58 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -612,7 +612,7 @@
 		return -EINVAL;
 
 	if (strcmp(t->u.user.name, XT_STANDARD_TARGET) == 0 &&
-	    target_offset + sizeof(struct compat_xt_standard_target) != next_offset)
+	    COMPAT_XT_ALIGN(target_offset + sizeof(struct compat_xt_standard_target)) != next_offset)
 		return -EINVAL;
 
 	/* compat_xt_entry match has less strict aligment requirements,
@@ -694,7 +694,7 @@
 		return -EINVAL;
 
 	if (strcmp(t->u.user.name, XT_STANDARD_TARGET) == 0 &&
-	    target_offset + sizeof(struct xt_standard_target) != next_offset)
+	    XT_ALIGN(target_offset + sizeof(struct xt_standard_target)) != next_offset)
 		return -EINVAL;
 
 	return xt_check_entry_match(elems, base + target_offset,
diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c
index 604df6f..515131f 100644
--- a/net/netfilter/xt_RATEEST.c
+++ b/net/netfilter/xt_RATEEST.c
@@ -137,7 +137,7 @@
 	cfg.est.ewma_log	= info->ewma_log;
 
 	ret = gen_new_estimator(&est->bstats, NULL, &est->rstats,
-				&est->lock, &cfg.opt);
+				&est->lock, NULL, &cfg.opt);
 	if (ret < 0)
 		goto err2;
 
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index e68ef9c..3cfd6cc 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -8,20 +8,6 @@
 #define NLGRPSZ(x)	(ALIGN(x, sizeof(unsigned long) * 8) / 8)
 #define NLGRPLONGS(x)	(NLGRPSZ(x)/sizeof(unsigned long))
 
-struct netlink_ring {
-	void			**pg_vec;
-	unsigned int		head;
-	unsigned int		frames_per_block;
-	unsigned int		frame_size;
-	unsigned int		frame_max;
-
-	unsigned int		pg_vec_order;
-	unsigned int		pg_vec_pages;
-	unsigned int		pg_vec_len;
-
-	atomic_t		pending;
-};
-
 struct netlink_sock {
 	/* struct sock has to be the first member of netlink_sock */
 	struct sock		sk;
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 9a3eb7a..1ecbd77 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -750,6 +750,14 @@
 
 	if (likely(vport)) {
 		u16 mru = OVS_CB(skb)->mru;
+		u32 cutlen = OVS_CB(skb)->cutlen;
+
+		if (unlikely(cutlen > 0)) {
+			if (skb->len - cutlen > ETH_HLEN)
+				pskb_trim(skb, skb->len - cutlen);
+			else
+				pskb_trim(skb, ETH_HLEN);
+		}
 
 		if (likely(!mru || (skb->len <= mru + ETH_HLEN))) {
 			ovs_vport_send(vport, skb);
@@ -775,7 +783,8 @@
 
 static int output_userspace(struct datapath *dp, struct sk_buff *skb,
 			    struct sw_flow_key *key, const struct nlattr *attr,
-			    const struct nlattr *actions, int actions_len)
+			    const struct nlattr *actions, int actions_len,
+			    uint32_t cutlen)
 {
 	struct dp_upcall_info upcall;
 	const struct nlattr *a;
@@ -822,7 +831,7 @@
 		} /* End of switch. */
 	}
 
-	return ovs_dp_upcall(dp, skb, key, &upcall);
+	return ovs_dp_upcall(dp, skb, key, &upcall, cutlen);
 }
 
 static int sample(struct datapath *dp, struct sk_buff *skb,
@@ -832,6 +841,7 @@
 	const struct nlattr *acts_list = NULL;
 	const struct nlattr *a;
 	int rem;
+	u32 cutlen = 0;
 
 	for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
 		 a = nla_next(a, &rem)) {
@@ -858,13 +868,24 @@
 		return 0;
 
 	/* The only known usage of sample action is having a single user-space
+	 * action, or having a truncate action followed by a single user-space
 	 * action. Treat this usage as a special case.
 	 * The output_userspace() should clone the skb to be sent to the
 	 * user space. This skb will be consumed by its caller.
 	 */
+	if (unlikely(nla_type(a) == OVS_ACTION_ATTR_TRUNC)) {
+		struct ovs_action_trunc *trunc = nla_data(a);
+
+		if (skb->len > trunc->max_len)
+			cutlen = skb->len - trunc->max_len;
+
+		a = nla_next(a, &rem);
+	}
+
 	if (likely(nla_type(a) == OVS_ACTION_ATTR_USERSPACE &&
 		   nla_is_last(a, rem)))
-		return output_userspace(dp, skb, key, a, actions, actions_len);
+		return output_userspace(dp, skb, key, a, actions,
+					actions_len, cutlen);
 
 	skb = skb_clone(skb, GFP_ATOMIC);
 	if (!skb)
@@ -1051,6 +1072,7 @@
 			if (out_skb)
 				do_output(dp, out_skb, prev_port, key);
 
+			OVS_CB(skb)->cutlen = 0;
 			prev_port = -1;
 		}
 
@@ -1059,8 +1081,18 @@
 			prev_port = nla_get_u32(a);
 			break;
 
+		case OVS_ACTION_ATTR_TRUNC: {
+			struct ovs_action_trunc *trunc = nla_data(a);
+
+			if (skb->len > trunc->max_len)
+				OVS_CB(skb)->cutlen = skb->len - trunc->max_len;
+			break;
+		}
+
 		case OVS_ACTION_ATTR_USERSPACE:
-			output_userspace(dp, skb, key, a, attr, len);
+			output_userspace(dp, skb, key, a, attr,
+						     len, OVS_CB(skb)->cutlen);
+			OVS_CB(skb)->cutlen = 0;
 			break;
 
 		case OVS_ACTION_ATTR_HASH:
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 856bd8d..524c0fd 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -137,10 +137,12 @@
 static struct vport *new_vport(const struct vport_parms *);
 static int queue_gso_packets(struct datapath *dp, struct sk_buff *,
 			     const struct sw_flow_key *,
-			     const struct dp_upcall_info *);
+			     const struct dp_upcall_info *,
+			     uint32_t cutlen);
 static int queue_userspace_packet(struct datapath *dp, struct sk_buff *,
 				  const struct sw_flow_key *,
-				  const struct dp_upcall_info *);
+				  const struct dp_upcall_info *,
+				  uint32_t cutlen);
 
 /* Must be called with rcu_read_lock. */
 static struct datapath *get_dp_rcu(struct net *net, int dp_ifindex)
@@ -275,7 +277,7 @@
 		upcall.cmd = OVS_PACKET_CMD_MISS;
 		upcall.portid = ovs_vport_find_upcall_portid(p, skb);
 		upcall.mru = OVS_CB(skb)->mru;
-		error = ovs_dp_upcall(dp, skb, key, &upcall);
+		error = ovs_dp_upcall(dp, skb, key, &upcall, 0);
 		if (unlikely(error))
 			kfree_skb(skb);
 		else
@@ -300,7 +302,8 @@
 
 int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb,
 		  const struct sw_flow_key *key,
-		  const struct dp_upcall_info *upcall_info)
+		  const struct dp_upcall_info *upcall_info,
+		  uint32_t cutlen)
 {
 	struct dp_stats_percpu *stats;
 	int err;
@@ -311,9 +314,9 @@
 	}
 
 	if (!skb_is_gso(skb))
-		err = queue_userspace_packet(dp, skb, key, upcall_info);
+		err = queue_userspace_packet(dp, skb, key, upcall_info, cutlen);
 	else
-		err = queue_gso_packets(dp, skb, key, upcall_info);
+		err = queue_gso_packets(dp, skb, key, upcall_info, cutlen);
 	if (err)
 		goto err;
 
@@ -331,7 +334,8 @@
 
 static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
 			     const struct sw_flow_key *key,
-			     const struct dp_upcall_info *upcall_info)
+			     const struct dp_upcall_info *upcall_info,
+				 uint32_t cutlen)
 {
 	unsigned short gso_type = skb_shinfo(skb)->gso_type;
 	struct sw_flow_key later_key;
@@ -360,7 +364,7 @@
 		if (gso_type & SKB_GSO_UDP && skb != segs)
 			key = &later_key;
 
-		err = queue_userspace_packet(dp, skb, key, upcall_info);
+		err = queue_userspace_packet(dp, skb, key, upcall_info, cutlen);
 		if (err)
 			break;
 
@@ -383,7 +387,8 @@
 {
 	size_t size = NLMSG_ALIGN(sizeof(struct ovs_header))
 		+ nla_total_size(hdrlen) /* OVS_PACKET_ATTR_PACKET */
-		+ nla_total_size(ovs_key_attr_size()); /* OVS_PACKET_ATTR_KEY */
+		+ nla_total_size(ovs_key_attr_size()) /* OVS_PACKET_ATTR_KEY */
+		+ nla_total_size(sizeof(unsigned int)); /* OVS_PACKET_ATTR_LEN */
 
 	/* OVS_PACKET_ATTR_USERDATA */
 	if (upcall_info->userdata)
@@ -416,7 +421,8 @@
 
 static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 				  const struct sw_flow_key *key,
-				  const struct dp_upcall_info *upcall_info)
+				  const struct dp_upcall_info *upcall_info,
+				  uint32_t cutlen)
 {
 	struct ovs_header *upcall;
 	struct sk_buff *nskb = NULL;
@@ -461,7 +467,7 @@
 	else
 		hlen = skb->len;
 
-	len = upcall_msg_size(upcall_info, hlen);
+	len = upcall_msg_size(upcall_info, hlen - cutlen);
 	user_skb = genlmsg_new(len, GFP_ATOMIC);
 	if (!user_skb) {
 		err = -ENOMEM;
@@ -509,15 +515,25 @@
 		pad_packet(dp, user_skb);
 	}
 
+	/* Add OVS_PACKET_ATTR_LEN when packet is truncated */
+	if (cutlen > 0) {
+		if (nla_put_u32(user_skb, OVS_PACKET_ATTR_LEN,
+				skb->len)) {
+			err = -ENOBUFS;
+			goto out;
+		}
+		pad_packet(dp, user_skb);
+	}
+
 	/* Only reserve room for attribute header, packet data is added
 	 * in skb_zerocopy() */
 	if (!(nla = nla_reserve(user_skb, OVS_PACKET_ATTR_PACKET, 0))) {
 		err = -ENOBUFS;
 		goto out;
 	}
-	nla->nla_len = nla_attr_size(skb->len);
+	nla->nla_len = nla_attr_size(skb->len - cutlen);
 
-	err = skb_zerocopy(user_skb, skb, skb->len, hlen);
+	err = skb_zerocopy(user_skb, skb, skb->len - cutlen, hlen);
 	if (err)
 		goto out;
 
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index 427e39a..ab85c1c 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -100,11 +100,13 @@
  * @input_vport: The original vport packet came in on. This value is cached
  * when a packet is received by OVS.
  * @mru: The maximum received fragement size; 0 if the packet is not
+ * @cutlen: The number of bytes from the packet end to be removed.
  * fragmented.
  */
 struct ovs_skb_cb {
 	struct vport		*input_vport;
 	u16			mru;
+	u32			cutlen;
 };
 #define OVS_CB(skb) ((struct ovs_skb_cb *)(skb)->cb)
 
@@ -194,7 +196,8 @@
 void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key);
 void ovs_dp_detach_port(struct vport *);
 int ovs_dp_upcall(struct datapath *, struct sk_buff *,
-		  const struct sw_flow_key *, const struct dp_upcall_info *);
+		  const struct sw_flow_key *, const struct dp_upcall_info *,
+		  uint32_t cutlen);
 
 const char *ovs_dp_name(const struct datapath *dp);
 struct sk_buff *ovs_vport_cmd_build_info(struct vport *, u32 pid, u32 seq,
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 0bb650f..c78a6a1 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -2229,6 +2229,7 @@
 			[OVS_ACTION_ATTR_SAMPLE] = (u32)-1,
 			[OVS_ACTION_ATTR_HASH] = sizeof(struct ovs_action_hash),
 			[OVS_ACTION_ATTR_CT] = (u32)-1,
+			[OVS_ACTION_ATTR_TRUNC] = sizeof(struct ovs_action_trunc),
 		};
 		const struct ovs_action_push_vlan *vlan;
 		int type = nla_type(a);
@@ -2255,6 +2256,14 @@
 				return -EINVAL;
 			break;
 
+		case OVS_ACTION_ATTR_TRUNC: {
+			const struct ovs_action_trunc *trunc = nla_data(a);
+
+			if (trunc->max_len < ETH_HLEN)
+				return -EINVAL;
+			break;
+		}
+
 		case OVS_ACTION_ATTR_HASH: {
 			const struct ovs_action_hash *act_hash = nla_data(a);
 
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index 31cbc8c..6b21fd0 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -444,6 +444,7 @@
 
 	OVS_CB(skb)->input_vport = vport;
 	OVS_CB(skb)->mru = 0;
+	OVS_CB(skb)->cutlen = 0;
 	if (unlikely(dev_net(skb->dev) != ovs_dp_get_net(vport->dp))) {
 		u32 mark;
 
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 4040eb9..d1f3b9e 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -93,6 +93,7 @@
 #include <net/inet_common.h>
 #endif
 #include <linux/bpf.h>
+#include <net/compat.h>
 
 #include "internal.h"
 
@@ -1978,40 +1979,8 @@
 {
 	*vnet_hdr = (const struct virtio_net_hdr) { 0 };
 
-	if (skb_is_gso(skb)) {
-		struct skb_shared_info *sinfo = skb_shinfo(skb);
-
-		/* This is a hint as to how much should be linear. */
-		vnet_hdr->hdr_len =
-			__cpu_to_virtio16(vio_le(), skb_headlen(skb));
-		vnet_hdr->gso_size =
-			__cpu_to_virtio16(vio_le(), sinfo->gso_size);
-
-		if (sinfo->gso_type & SKB_GSO_TCPV4)
-			vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
-		else if (sinfo->gso_type & SKB_GSO_TCPV6)
-			vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
-		else if (sinfo->gso_type & SKB_GSO_UDP)
-			vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP;
-		else if (sinfo->gso_type & SKB_GSO_FCOE)
-			return -EINVAL;
-		else
-			BUG();
-
-		if (sinfo->gso_type & SKB_GSO_TCP_ECN)
-			vnet_hdr->gso_type |= VIRTIO_NET_HDR_GSO_ECN;
-	} else
-		vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_NONE;
-
-	if (skb->ip_summed == CHECKSUM_PARTIAL) {
-		vnet_hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
-		vnet_hdr->csum_start = __cpu_to_virtio16(vio_le(),
-				  skb_checksum_start_offset(skb));
-		vnet_hdr->csum_offset = __cpu_to_virtio16(vio_le(),
-						 skb->csum_offset);
-	} else if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
-		vnet_hdr->flags = VIRTIO_NET_HDR_F_DATA_VALID;
-	} /* else everything is zero */
+	if (virtio_net_hdr_from_skb(skb, vnet_hdr, vio_le()))
+		BUG();
 
 	return 0;
 }
@@ -3940,6 +3909,27 @@
 }
 
 
+#ifdef CONFIG_COMPAT
+static int compat_packet_setsockopt(struct socket *sock, int level, int optname,
+				    char __user *optval, unsigned int optlen)
+{
+	struct packet_sock *po = pkt_sk(sock->sk);
+
+	if (level != SOL_PACKET)
+		return -ENOPROTOOPT;
+
+	if (optname == PACKET_FANOUT_DATA &&
+	    po->fanout && po->fanout->type == PACKET_FANOUT_CBPF) {
+		optval = (char __user *)get_compat_bpf_fprog(optval);
+		if (!optval)
+			return -EFAULT;
+		optlen = sizeof(struct sock_fprog);
+	}
+
+	return packet_setsockopt(sock, level, optname, optval, optlen);
+}
+#endif
+
 static int packet_notifier(struct notifier_block *this,
 			   unsigned long msg, void *ptr)
 {
@@ -4416,6 +4406,9 @@
 	.shutdown =	sock_no_shutdown,
 	.setsockopt =	packet_setsockopt,
 	.getsockopt =	packet_getsockopt,
+#ifdef CONFIG_COMPAT
+	.compat_setsockopt = compat_packet_setsockopt,
+#endif
 	.sendmsg =	packet_sendmsg,
 	.recvmsg =	packet_recvmsg,
 	.mmap =		packet_mmap,
diff --git a/net/rds/cong.c b/net/rds/cong.c
index 6641bcf..8398fee 100644
--- a/net/rds/cong.c
+++ b/net/rds/cong.c
@@ -235,7 +235,8 @@
 			 *    therefore trigger warnings.
 			 * Defer the xmit to rds_send_worker() instead.
 			 */
-			queue_delayed_work(rds_wq, &conn->c_send_w, 0);
+			queue_delayed_work(rds_wq,
+					   &conn->c_path[0].cp_send_w, 0);
 		}
 	}
 
diff --git a/net/rds/connection.c b/net/rds/connection.c
index e3b118c..a4b07c8 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -95,14 +95,16 @@
  * and receiving over this connection again in the future.  It is up to
  * the transport to have serialized this call with its send and recv.
  */
-static void rds_conn_reset(struct rds_connection *conn)
+static void rds_conn_path_reset(struct rds_conn_path *cp)
 {
+	struct rds_connection *conn = cp->cp_conn;
+
 	rdsdebug("connection %pI4 to %pI4 reset\n",
 	  &conn->c_laddr, &conn->c_faddr);
 
 	rds_stats_inc(s_conn_reset);
-	rds_send_reset(conn);
-	conn->c_flags = 0;
+	rds_send_path_reset(cp);
+	cp->cp_flags = 0;
 
 	/* Do not clear next_rx_seq here, else we cannot distinguish
 	 * retransmitted packets from new packets, and will hand all
@@ -110,6 +112,32 @@
 	 * reliability guarantees of RDS. */
 }
 
+static void __rds_conn_path_init(struct rds_connection *conn,
+				 struct rds_conn_path *cp, bool is_outgoing)
+{
+	spin_lock_init(&cp->cp_lock);
+	cp->cp_next_tx_seq = 1;
+	init_waitqueue_head(&cp->cp_waitq);
+	INIT_LIST_HEAD(&cp->cp_send_queue);
+	INIT_LIST_HEAD(&cp->cp_retrans);
+
+	cp->cp_conn = conn;
+	atomic_set(&cp->cp_state, RDS_CONN_DOWN);
+	cp->cp_send_gen = 0;
+	/* cp_outgoing is per-path. So we can only set it here
+	 * for the single-path transports.
+	 */
+	if (!conn->c_trans->t_mp_capable)
+		cp->cp_outgoing = (is_outgoing ? 1 : 0);
+	cp->cp_reconnect_jiffies = 0;
+	INIT_DELAYED_WORK(&cp->cp_send_w, rds_send_worker);
+	INIT_DELAYED_WORK(&cp->cp_recv_w, rds_recv_worker);
+	INIT_DELAYED_WORK(&cp->cp_conn_w, rds_connect_worker);
+	INIT_WORK(&cp->cp_down_w, rds_shutdown_worker);
+	mutex_init(&cp->cp_cm_lock);
+	cp->cp_flags = 0;
+}
+
 /*
  * There is only every one 'conn' for a given pair of addresses in the
  * system at a time.  They contain messages to be retransmitted and so
@@ -153,13 +181,8 @@
 	INIT_HLIST_NODE(&conn->c_hash_node);
 	conn->c_laddr = laddr;
 	conn->c_faddr = faddr;
-	spin_lock_init(&conn->c_lock);
-	conn->c_next_tx_seq = 1;
-	rds_conn_net_set(conn, net);
 
-	init_waitqueue_head(&conn->c_waitq);
-	INIT_LIST_HEAD(&conn->c_send_queue);
-	INIT_LIST_HEAD(&conn->c_retrans);
+	rds_conn_net_set(conn, net);
 
 	ret = rds_cong_get_maps(conn);
 	if (ret) {
@@ -195,17 +218,6 @@
 		goto out;
 	}
 
-	atomic_set(&conn->c_state, RDS_CONN_DOWN);
-	conn->c_send_gen = 0;
-	conn->c_outgoing = (is_outgoing ? 1 : 0);
-	conn->c_reconnect_jiffies = 0;
-	INIT_DELAYED_WORK(&conn->c_send_w, rds_send_worker);
-	INIT_DELAYED_WORK(&conn->c_recv_w, rds_recv_worker);
-	INIT_DELAYED_WORK(&conn->c_conn_w, rds_connect_worker);
-	INIT_WORK(&conn->c_down_w, rds_shutdown_worker);
-	mutex_init(&conn->c_cm_lock);
-	conn->c_flags = 0;
-
 	rdsdebug("allocated conn %p for %pI4 -> %pI4 over %s %s\n",
 	  conn, &laddr, &faddr,
 	  trans->t_name ? trans->t_name : "[unknown]",
@@ -222,7 +234,7 @@
 	if (parent) {
 		/* Creating passive conn */
 		if (parent->c_passive) {
-			trans->conn_free(conn->c_transport_data);
+			trans->conn_free(conn->c_path[0].cp_transport_data);
 			kmem_cache_free(rds_conn_slab, conn);
 			conn = parent->c_passive;
 		} else {
@@ -236,10 +248,26 @@
 
 		found = rds_conn_lookup(net, head, laddr, faddr, trans);
 		if (found) {
-			trans->conn_free(conn->c_transport_data);
+			struct rds_conn_path *cp;
+			int i;
+
+			for (i = 0; i < RDS_MPATH_WORKERS; i++) {
+				cp = &conn->c_path[i];
+				trans->conn_free(cp->cp_transport_data);
+				if (!trans->t_mp_capable)
+					break;
+			}
 			kmem_cache_free(rds_conn_slab, conn);
 			conn = found;
 		} else {
+			int i;
+
+			for (i = 0; i < RDS_MPATH_WORKERS; i++) {
+				__rds_conn_path_init(conn, &conn->c_path[i],
+						     is_outgoing);
+				conn->c_path[i].cp_index = i;
+			}
+
 			hlist_add_head_rcu(&conn->c_hash_node, head);
 			rds_cong_add_conn(conn);
 			rds_conn_count++;
@@ -267,10 +295,12 @@
 }
 EXPORT_SYMBOL_GPL(rds_conn_create_outgoing);
 
-void rds_conn_shutdown(struct rds_connection *conn)
+void rds_conn_shutdown(struct rds_conn_path *cp)
 {
+	struct rds_connection *conn = cp->cp_conn;
+
 	/* shut it down unless it's down already */
-	if (!rds_conn_transition(conn, RDS_CONN_DOWN, RDS_CONN_DOWN)) {
+	if (!rds_conn_path_transition(cp, RDS_CONN_DOWN, RDS_CONN_DOWN)) {
 		/*
 		 * Quiesce the connection mgmt handlers before we start tearing
 		 * things down. We don't hold the mutex for the entire
@@ -278,35 +308,41 @@
 		 * deadlocking with the CM handler. Instead, the CM event
 		 * handler is supposed to check for state DISCONNECTING
 		 */
-		mutex_lock(&conn->c_cm_lock);
-		if (!rds_conn_transition(conn, RDS_CONN_UP, RDS_CONN_DISCONNECTING)
-		 && !rds_conn_transition(conn, RDS_CONN_ERROR, RDS_CONN_DISCONNECTING)) {
-			rds_conn_error(conn, "shutdown called in state %d\n",
-					atomic_read(&conn->c_state));
-			mutex_unlock(&conn->c_cm_lock);
+		mutex_lock(&cp->cp_cm_lock);
+		if (!rds_conn_path_transition(cp, RDS_CONN_UP,
+					      RDS_CONN_DISCONNECTING) &&
+		    !rds_conn_path_transition(cp, RDS_CONN_ERROR,
+					      RDS_CONN_DISCONNECTING)) {
+			rds_conn_path_error(cp,
+					    "shutdown called in state %d\n",
+					    atomic_read(&cp->cp_state));
+			mutex_unlock(&cp->cp_cm_lock);
 			return;
 		}
-		mutex_unlock(&conn->c_cm_lock);
+		mutex_unlock(&cp->cp_cm_lock);
 
-		wait_event(conn->c_waitq,
-			   !test_bit(RDS_IN_XMIT, &conn->c_flags));
-		wait_event(conn->c_waitq,
-			   !test_bit(RDS_RECV_REFILL, &conn->c_flags));
+		wait_event(cp->cp_waitq,
+			   !test_bit(RDS_IN_XMIT, &cp->cp_flags));
+		wait_event(cp->cp_waitq,
+			   !test_bit(RDS_RECV_REFILL, &cp->cp_flags));
 
-		conn->c_trans->conn_shutdown(conn);
-		rds_conn_reset(conn);
+		if (!conn->c_trans->t_mp_capable)
+			conn->c_trans->conn_shutdown(conn);
+		else
+			conn->c_trans->conn_path_shutdown(cp);
+		rds_conn_path_reset(cp);
 
-		if (!rds_conn_transition(conn, RDS_CONN_DISCONNECTING, RDS_CONN_DOWN)) {
+		if (!rds_conn_path_transition(cp, RDS_CONN_DISCONNECTING,
+					      RDS_CONN_DOWN)) {
 			/* This can happen - eg when we're in the middle of tearing
 			 * down the connection, and someone unloads the rds module.
 			 * Quite reproduceable with loopback connections.
 			 * Mostly harmless.
 			 */
-			rds_conn_error(conn,
-				"%s: failed to transition to state DOWN, "
-				"current state is %d\n",
-				__func__,
-				atomic_read(&conn->c_state));
+			rds_conn_path_error(cp, "%s: failed to transition "
+					    "to state DOWN, current state "
+					    "is %d\n", __func__,
+					    atomic_read(&cp->cp_state));
 			return;
 		}
 	}
@@ -315,18 +351,46 @@
 	 * The passive side of an IB loopback connection is never added
 	 * to the conn hash, so we never trigger a reconnect on this
 	 * conn - the reconnect is always triggered by the active peer. */
-	cancel_delayed_work_sync(&conn->c_conn_w);
+	cancel_delayed_work_sync(&cp->cp_conn_w);
 	rcu_read_lock();
 	if (!hlist_unhashed(&conn->c_hash_node)) {
 		rcu_read_unlock();
 		if (conn->c_trans->t_type != RDS_TRANS_TCP ||
-		    conn->c_outgoing == 1)
-			rds_queue_reconnect(conn);
+		    cp->cp_outgoing == 1)
+			rds_queue_reconnect(cp);
 	} else {
 		rcu_read_unlock();
 	}
 }
 
+/* destroy a single rds_conn_path. rds_conn_destroy() iterates over
+ * all paths using rds_conn_path_destroy()
+ */
+static void rds_conn_path_destroy(struct rds_conn_path *cp)
+{
+	struct rds_message *rm, *rtmp;
+
+	rds_conn_path_drop(cp);
+	flush_work(&cp->cp_down_w);
+
+	/* make sure lingering queued work won't try to ref the conn */
+	cancel_delayed_work_sync(&cp->cp_send_w);
+	cancel_delayed_work_sync(&cp->cp_recv_w);
+
+	/* tear down queued messages */
+	list_for_each_entry_safe(rm, rtmp,
+				 &cp->cp_send_queue,
+				 m_conn_item) {
+		list_del_init(&rm->m_conn_item);
+		BUG_ON(!list_empty(&rm->m_sock_item));
+		rds_message_put(rm);
+	}
+	if (cp->cp_xmit_rm)
+		rds_message_put(cp->cp_xmit_rm);
+
+	cp->cp_conn->c_trans->conn_free(cp->cp_transport_data);
+}
+
 /*
  * Stop and free a connection.
  *
@@ -336,7 +400,6 @@
  */
 void rds_conn_destroy(struct rds_connection *conn)
 {
-	struct rds_message *rm, *rtmp;
 	unsigned long flags;
 
 	rdsdebug("freeing conn %p for %pI4 -> "
@@ -350,25 +413,19 @@
 	synchronize_rcu();
 
 	/* shut the connection down */
-	rds_conn_drop(conn);
-	flush_work(&conn->c_down_w);
+	if (!conn->c_trans->t_mp_capable) {
+		rds_conn_path_destroy(&conn->c_path[0]);
+		BUG_ON(!list_empty(&conn->c_path[0].cp_retrans));
+	} else {
+		int i;
+		struct rds_conn_path *cp;
 
-	/* make sure lingering queued work won't try to ref the conn */
-	cancel_delayed_work_sync(&conn->c_send_w);
-	cancel_delayed_work_sync(&conn->c_recv_w);
-
-	/* tear down queued messages */
-	list_for_each_entry_safe(rm, rtmp,
-				 &conn->c_send_queue,
-				 m_conn_item) {
-		list_del_init(&rm->m_conn_item);
-		BUG_ON(!list_empty(&rm->m_sock_item));
-		rds_message_put(rm);
+		for (i = 0; i < RDS_MPATH_WORKERS; i++) {
+			cp = &conn->c_path[i];
+			rds_conn_path_destroy(cp);
+			BUG_ON(!list_empty(&cp->cp_retrans));
+		}
 	}
-	if (conn->c_xmit_rm)
-		rds_message_put(conn->c_xmit_rm);
-
-	conn->c_trans->conn_free(conn->c_transport_data);
 
 	/*
 	 * The congestion maps aren't freed up here.  They're
@@ -377,7 +434,6 @@
 	 */
 	rds_cong_remove_conn(conn);
 
-	BUG_ON(!list_empty(&conn->c_retrans));
 	kmem_cache_free(rds_conn_slab, conn);
 
 	spin_lock_irqsave(&rds_conn_lock, flags);
@@ -398,6 +454,7 @@
 	unsigned int total = 0;
 	unsigned long flags;
 	size_t i;
+	int j;
 
 	len /= sizeof(struct rds_info_message);
 
@@ -406,23 +463,32 @@
 	for (i = 0, head = rds_conn_hash; i < ARRAY_SIZE(rds_conn_hash);
 	     i++, head++) {
 		hlist_for_each_entry_rcu(conn, head, c_hash_node) {
-			if (want_send)
-				list = &conn->c_send_queue;
-			else
-				list = &conn->c_retrans;
+			struct rds_conn_path *cp;
 
-			spin_lock_irqsave(&conn->c_lock, flags);
+			for (j = 0; j < RDS_MPATH_WORKERS; j++) {
+				cp = &conn->c_path[j];
+				if (want_send)
+					list = &cp->cp_send_queue;
+				else
+					list = &cp->cp_retrans;
 
-			/* XXX too lazy to maintain counts.. */
-			list_for_each_entry(rm, list, m_conn_item) {
-				total++;
-				if (total <= len)
-					rds_inc_info_copy(&rm->m_inc, iter,
-							  conn->c_laddr,
-							  conn->c_faddr, 0);
+				spin_lock_irqsave(&cp->cp_lock, flags);
+
+				/* XXX too lazy to maintain counts.. */
+				list_for_each_entry(rm, list, m_conn_item) {
+					total++;
+					if (total <= len)
+						rds_inc_info_copy(&rm->m_inc,
+								  iter,
+								  conn->c_laddr,
+								  conn->c_faddr,
+								  0);
+				}
+
+				spin_unlock_irqrestore(&cp->cp_lock, flags);
+				if (!conn->c_trans->t_mp_capable)
+					break;
 			}
-
-			spin_unlock_irqrestore(&conn->c_lock, flags);
 		}
 	}
 	rcu_read_unlock();
@@ -484,27 +550,72 @@
 }
 EXPORT_SYMBOL_GPL(rds_for_each_conn_info);
 
-static int rds_conn_info_visitor(struct rds_connection *conn,
-				  void *buffer)
+void rds_walk_conn_path_info(struct socket *sock, unsigned int len,
+			     struct rds_info_iterator *iter,
+			     struct rds_info_lengths *lens,
+			     int (*visitor)(struct rds_conn_path *, void *),
+			     size_t item_len)
+{
+	u64  buffer[(item_len + 7) / 8];
+	struct hlist_head *head;
+	struct rds_connection *conn;
+	size_t i;
+	int j;
+
+	rcu_read_lock();
+
+	lens->nr = 0;
+	lens->each = item_len;
+
+	for (i = 0, head = rds_conn_hash; i < ARRAY_SIZE(rds_conn_hash);
+	     i++, head++) {
+		hlist_for_each_entry_rcu(conn, head, c_hash_node) {
+			struct rds_conn_path *cp;
+
+			for (j = 0; j < RDS_MPATH_WORKERS; j++) {
+				cp = &conn->c_path[j];
+
+				/* XXX no cp_lock usage.. */
+				if (!visitor(cp, buffer))
+					continue;
+				if (!conn->c_trans->t_mp_capable)
+					break;
+			}
+
+			/* We copy as much as we can fit in the buffer,
+			 * but we count all items so that the caller
+			 * can resize the buffer.
+			 */
+			if (len >= item_len) {
+				rds_info_copy(iter, buffer, item_len);
+				len -= item_len;
+			}
+			lens->nr++;
+		}
+	}
+	rcu_read_unlock();
+}
+
+static int rds_conn_info_visitor(struct rds_conn_path *cp, void *buffer)
 {
 	struct rds_info_connection *cinfo = buffer;
 
-	cinfo->next_tx_seq = conn->c_next_tx_seq;
-	cinfo->next_rx_seq = conn->c_next_rx_seq;
-	cinfo->laddr = conn->c_laddr;
-	cinfo->faddr = conn->c_faddr;
-	strncpy(cinfo->transport, conn->c_trans->t_name,
+	cinfo->next_tx_seq = cp->cp_next_tx_seq;
+	cinfo->next_rx_seq = cp->cp_next_rx_seq;
+	cinfo->laddr = cp->cp_conn->c_laddr;
+	cinfo->faddr = cp->cp_conn->c_faddr;
+	strncpy(cinfo->transport, cp->cp_conn->c_trans->t_name,
 		sizeof(cinfo->transport));
 	cinfo->flags = 0;
 
-	rds_conn_info_set(cinfo->flags, test_bit(RDS_IN_XMIT, &conn->c_flags),
+	rds_conn_info_set(cinfo->flags, test_bit(RDS_IN_XMIT, &cp->cp_flags),
 			  SENDING);
 	/* XXX Future: return the state rather than these funky bits */
 	rds_conn_info_set(cinfo->flags,
-			  atomic_read(&conn->c_state) == RDS_CONN_CONNECTING,
+			  atomic_read(&cp->cp_state) == RDS_CONN_CONNECTING,
 			  CONNECTING);
 	rds_conn_info_set(cinfo->flags,
-			  atomic_read(&conn->c_state) == RDS_CONN_UP,
+			  atomic_read(&cp->cp_state) == RDS_CONN_UP,
 			  CONNECTED);
 	return 1;
 }
@@ -513,7 +624,7 @@
 			  struct rds_info_iterator *iter,
 			  struct rds_info_lengths *lens)
 {
-	rds_for_each_conn_info(sock, len, iter, lens,
+	rds_walk_conn_path_info(sock, len, iter, lens,
 				rds_conn_info_visitor,
 				sizeof(struct rds_info_connection));
 }
@@ -553,10 +664,16 @@
 /*
  * Force a disconnect
  */
+void rds_conn_path_drop(struct rds_conn_path *cp)
+{
+	atomic_set(&cp->cp_state, RDS_CONN_ERROR);
+	queue_work(rds_wq, &cp->cp_down_w);
+}
+EXPORT_SYMBOL_GPL(rds_conn_path_drop);
+
 void rds_conn_drop(struct rds_connection *conn)
 {
-	atomic_set(&conn->c_state, RDS_CONN_ERROR);
-	queue_work(rds_wq, &conn->c_down_w);
+	rds_conn_path_drop(&conn->c_path[0]);
 }
 EXPORT_SYMBOL_GPL(rds_conn_drop);
 
@@ -564,11 +681,17 @@
  * If the connection is down, trigger a connect. We may have scheduled a
  * delayed reconnect however - in this case we should not interfere.
  */
+void rds_conn_path_connect_if_down(struct rds_conn_path *cp)
+{
+	if (rds_conn_path_state(cp) == RDS_CONN_DOWN &&
+	    !test_and_set_bit(RDS_RECONNECT_PENDING, &cp->cp_flags))
+		queue_delayed_work(rds_wq, &cp->cp_conn_w, 0);
+}
+
 void rds_conn_connect_if_down(struct rds_connection *conn)
 {
-	if (rds_conn_state(conn) == RDS_CONN_DOWN &&
-	    !test_and_set_bit(RDS_RECONNECT_PENDING, &conn->c_flags))
-		queue_delayed_work(rds_wq, &conn->c_conn_w, 0);
+	WARN_ON(conn->c_trans->t_mp_capable);
+	rds_conn_path_connect_if_down(&conn->c_path[0]);
 }
 EXPORT_SYMBOL_GPL(rds_conn_connect_if_down);
 
@@ -586,3 +709,15 @@
 
 	rds_conn_drop(conn);
 }
+
+void
+__rds_conn_path_error(struct rds_conn_path *cp, const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	vprintk(fmt, ap);
+	va_end(ap);
+
+	rds_conn_path_drop(cp);
+}
diff --git a/net/rds/ib.c b/net/rds/ib.c
index b5342fd..44946a6 100644
--- a/net/rds/ib.c
+++ b/net/rds/ib.c
@@ -40,6 +40,7 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 
+#include "rds_single_path.h"
 #include "rds.h"
 #include "ib.h"
 #include "ib_mr.h"
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index 310cabc..3342876 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -36,6 +36,7 @@
 #include <linux/vmalloc.h>
 #include <linux/ratelimit.h>
 
+#include "rds_single_path.h"
 #include "rds.h"
 #include "ib.h"
 
@@ -273,7 +274,7 @@
 	if (rds_conn_up(conn) &&
 	    (!test_bit(RDS_LL_SEND_FULL, &conn->c_flags) ||
 	    test_bit(0, &conn->c_map_queued)))
-		rds_send_xmit(ic->conn);
+		rds_send_xmit(&ic->conn->c_path[0]);
 }
 
 static void poll_rcq(struct rds_ib_connection *ic, struct ib_cq *cq,
diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
index f7164ac..977f698 100644
--- a/net/rds/ib_rdma.c
+++ b/net/rds/ib_rdma.c
@@ -35,6 +35,7 @@
 #include <linux/rculist.h>
 #include <linux/llist.h>
 
+#include "rds_single_path.h"
 #include "ib_mr.h"
 
 struct workqueue_struct *rds_ib_mr_wq;
@@ -618,7 +619,7 @@
 
 int rds_ib_mr_init(void)
 {
-	rds_ib_mr_wq = create_workqueue("rds_mr_flushd");
+	rds_ib_mr_wq = alloc_workqueue("rds_mr_flushd", WQ_MEM_RECLAIM, 0);
 	if (!rds_ib_mr_wq)
 		return -ENOMEM;
 	return 0;
diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c
index abc8cc8..4ea8cb1 100644
--- a/net/rds/ib_recv.c
+++ b/net/rds/ib_recv.c
@@ -36,6 +36,7 @@
 #include <linux/dma-mapping.h>
 #include <rdma/rdma_cm.h>
 
+#include "rds_single_path.h"
 #include "rds.h"
 #include "ib.h"
 
diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c
index f27d2c8..6e4110a 100644
--- a/net/rds/ib_send.c
+++ b/net/rds/ib_send.c
@@ -36,6 +36,7 @@
 #include <linux/dmapool.h>
 #include <linux/ratelimit.h>
 
+#include "rds_single_path.h"
 #include "rds.h"
 #include "ib.h"
 
diff --git a/net/rds/loop.c b/net/rds/loop.c
index 6b12b68..268f07f 100644
--- a/net/rds/loop.c
+++ b/net/rds/loop.c
@@ -34,6 +34,7 @@
 #include <linux/slab.h>
 #include <linux/in.h>
 
+#include "rds_single_path.h"
 #include "rds.h"
 #include "loop.h"
 
diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c
index 7220beb..345f090 100644
--- a/net/rds/rdma_transport.c
+++ b/net/rds/rdma_transport.c
@@ -33,6 +33,7 @@
 #include <linux/module.h>
 #include <rdma/rdma_cm.h>
 
+#include "rds_single_path.h"
 #include "rdma_transport.h"
 #include "ib.h"
 
diff --git a/net/rds/rds.h b/net/rds/rds.h
index 80256b0..2e35b73 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -74,6 +74,7 @@
 	RDS_CONN_CONNECTING,
 	RDS_CONN_DISCONNECTING,
 	RDS_CONN_UP,
+	RDS_CONN_RESETTING,
 	RDS_CONN_ERROR,
 };
 
@@ -83,56 +84,69 @@
 #define RDS_IN_XMIT		2
 #define RDS_RECV_REFILL		3
 
+/* Max number of multipaths per RDS connection. Must be a power of 2 */
+#define	RDS_MPATH_WORKERS	1
+
+/* Per mpath connection state */
+struct rds_conn_path {
+	struct rds_connection	*cp_conn;
+	struct rds_message	*cp_xmit_rm;
+	unsigned long		cp_xmit_sg;
+	unsigned int		cp_xmit_hdr_off;
+	unsigned int		cp_xmit_data_off;
+	unsigned int		cp_xmit_atomic_sent;
+	unsigned int		cp_xmit_rdma_sent;
+	unsigned int		cp_xmit_data_sent;
+
+	spinlock_t		cp_lock;		/* protect msg queues */
+	u64			cp_next_tx_seq;
+	struct list_head	cp_send_queue;
+	struct list_head	cp_retrans;
+
+	u64			cp_next_rx_seq;
+
+	void			*cp_transport_data;
+
+	atomic_t		cp_state;
+	unsigned long		cp_send_gen;
+	unsigned long		cp_flags;
+	unsigned long		cp_reconnect_jiffies;
+	struct delayed_work	cp_send_w;
+	struct delayed_work	cp_recv_w;
+	struct delayed_work	cp_conn_w;
+	struct work_struct	cp_down_w;
+	struct mutex		cp_cm_lock;	/* protect cp_state & cm */
+	wait_queue_head_t	cp_waitq;
+
+	unsigned int		cp_unacked_packets;
+	unsigned int		cp_unacked_bytes;
+	unsigned int		cp_outgoing:1,
+				cp_pad_to_32:31;
+	unsigned int		cp_index;
+};
+
+/* One rds_connection per RDS address pair */
 struct rds_connection {
 	struct hlist_node	c_hash_node;
 	__be32			c_laddr;
 	__be32			c_faddr;
 	unsigned int		c_loopback:1,
-				c_outgoing:1,
-				c_pad_to_32:30;
+				c_pad_to_32:31;
+	int			c_npaths;
 	struct rds_connection	*c_passive;
+	struct rds_transport	*c_trans;
 
 	struct rds_cong_map	*c_lcong;
 	struct rds_cong_map	*c_fcong;
 
-	struct rds_message	*c_xmit_rm;
-	unsigned long		c_xmit_sg;
-	unsigned int		c_xmit_hdr_off;
-	unsigned int		c_xmit_data_off;
-	unsigned int		c_xmit_atomic_sent;
-	unsigned int		c_xmit_rdma_sent;
-	unsigned int		c_xmit_data_sent;
-
-	spinlock_t		c_lock;		/* protect msg queues */
-	u64			c_next_tx_seq;
-	struct list_head	c_send_queue;
-	struct list_head	c_retrans;
-
-	u64			c_next_rx_seq;
-
-	struct rds_transport	*c_trans;
-	void			*c_transport_data;
-
-	atomic_t		c_state;
-	unsigned long		c_send_gen;
-	unsigned long		c_flags;
-	unsigned long		c_reconnect_jiffies;
-	struct delayed_work	c_send_w;
-	struct delayed_work	c_recv_w;
-	struct delayed_work	c_conn_w;
-	struct work_struct	c_down_w;
-	struct mutex		c_cm_lock;	/* protect conn state & cm */
-	wait_queue_head_t	c_waitq;
+	/* Protocol version */
+	unsigned int		c_version;
+	possible_net_t		c_net;
 
 	struct list_head	c_map_item;
 	unsigned long		c_map_queued;
 
-	unsigned int		c_unacked_packets;
-	unsigned int		c_unacked_bytes;
-
-	/* Protocol version */
-	unsigned int		c_version;
-	possible_net_t		c_net;
+	struct rds_conn_path	c_path[RDS_MPATH_WORKERS];
 };
 
 static inline
@@ -217,6 +231,7 @@
 	atomic_t		i_refcount;
 	struct list_head	i_item;
 	struct rds_connection	*i_conn;
+	struct rds_conn_path	*i_conn_path;
 	struct rds_header	i_hdr;
 	unsigned long		i_rx_jiffies;
 	__be32			i_saddr;
@@ -432,7 +447,8 @@
 	char			t_name[TRANSNAMSIZ];
 	struct list_head	t_item;
 	struct module		*t_owner;
-	unsigned int		t_prefer_loopback:1;
+	unsigned int		t_prefer_loopback:1,
+				t_mp_capable:1;
 	unsigned int		t_type;
 
 	int (*laddr_check)(struct net *net, __be32 addr);
@@ -440,8 +456,11 @@
 	void (*conn_free)(void *data);
 	int (*conn_connect)(struct rds_connection *conn);
 	void (*conn_shutdown)(struct rds_connection *conn);
+	void (*conn_path_shutdown)(struct rds_conn_path *conn);
 	void (*xmit_prepare)(struct rds_connection *conn);
+	void (*xmit_path_prepare)(struct rds_conn_path *cp);
 	void (*xmit_complete)(struct rds_connection *conn);
+	void (*xmit_path_complete)(struct rds_conn_path *cp);
 	int (*xmit)(struct rds_connection *conn, struct rds_message *rm,
 		    unsigned int hdr_off, unsigned int sg, unsigned int off);
 	int (*xmit_rdma)(struct rds_connection *conn, struct rm_rdma_op *op);
@@ -635,10 +654,12 @@
 struct rds_connection *rds_conn_create_outgoing(struct net *net,
 						__be32 laddr, __be32 faddr,
 			       struct rds_transport *trans, gfp_t gfp);
-void rds_conn_shutdown(struct rds_connection *conn);
+void rds_conn_shutdown(struct rds_conn_path *cpath);
 void rds_conn_destroy(struct rds_connection *conn);
 void rds_conn_drop(struct rds_connection *conn);
+void rds_conn_path_drop(struct rds_conn_path *cpath);
 void rds_conn_connect_if_down(struct rds_connection *conn);
+void rds_conn_path_connect_if_down(struct rds_conn_path *cp);
 void rds_for_each_conn_info(struct socket *sock, unsigned int len,
 			  struct rds_info_iterator *iter,
 			  struct rds_info_lengths *lens,
@@ -649,28 +670,60 @@
 #define rds_conn_error(conn, fmt...) \
 	__rds_conn_error(conn, KERN_WARNING "RDS: " fmt)
 
+void __rds_conn_path_error(struct rds_conn_path *cp, const char *, ...);
+#define rds_conn_path_error(cp, fmt...) \
+	__rds_conn_path_error(cp, KERN_WARNING "RDS: " fmt)
+
+static inline int
+rds_conn_path_transition(struct rds_conn_path *cp, int old, int new)
+{
+	return atomic_cmpxchg(&cp->cp_state, old, new) == old;
+}
+
 static inline int
 rds_conn_transition(struct rds_connection *conn, int old, int new)
 {
-	return atomic_cmpxchg(&conn->c_state, old, new) == old;
+	WARN_ON(conn->c_trans->t_mp_capable);
+	return rds_conn_path_transition(&conn->c_path[0], old, new);
+}
+
+static inline int
+rds_conn_path_state(struct rds_conn_path *cp)
+{
+	return atomic_read(&cp->cp_state);
 }
 
 static inline int
 rds_conn_state(struct rds_connection *conn)
 {
-	return atomic_read(&conn->c_state);
+	WARN_ON(conn->c_trans->t_mp_capable);
+	return rds_conn_path_state(&conn->c_path[0]);
+}
+
+static inline int
+rds_conn_path_up(struct rds_conn_path *cp)
+{
+	return atomic_read(&cp->cp_state) == RDS_CONN_UP;
 }
 
 static inline int
 rds_conn_up(struct rds_connection *conn)
 {
-	return atomic_read(&conn->c_state) == RDS_CONN_UP;
+	WARN_ON(conn->c_trans->t_mp_capable);
+	return rds_conn_path_up(&conn->c_path[0]);
+}
+
+static inline int
+rds_conn_path_connecting(struct rds_conn_path *cp)
+{
+	return atomic_read(&cp->cp_state) == RDS_CONN_CONNECTING;
 }
 
 static inline int
 rds_conn_connecting(struct rds_connection *conn)
 {
-	return atomic_read(&conn->c_state) == RDS_CONN_CONNECTING;
+	WARN_ON(conn->c_trans->t_mp_capable);
+	return rds_conn_path_connecting(&conn->c_path[0]);
 }
 
 /* message.c */
@@ -719,6 +772,8 @@
 /* recv.c */
 void rds_inc_init(struct rds_incoming *inc, struct rds_connection *conn,
 		  __be32 saddr);
+void rds_inc_path_init(struct rds_incoming *inc, struct rds_conn_path *conn,
+		       __be32 saddr);
 void rds_inc_put(struct rds_incoming *inc);
 void rds_recv_incoming(struct rds_connection *conn, __be32 saddr, __be32 daddr,
 		       struct rds_incoming *inc, gfp_t gfp);
@@ -732,16 +787,16 @@
 
 /* send.c */
 int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len);
-void rds_send_reset(struct rds_connection *conn);
-int rds_send_xmit(struct rds_connection *conn);
+void rds_send_path_reset(struct rds_conn_path *conn);
+int rds_send_xmit(struct rds_conn_path *cp);
 struct sockaddr_in;
 void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest);
 typedef int (*is_acked_func)(struct rds_message *rm, uint64_t ack);
 void rds_send_drop_acked(struct rds_connection *conn, u64 ack,
 			 is_acked_func is_acked);
-int rds_send_pong(struct rds_connection *conn, __be16 dport);
-struct rds_message *rds_send_get_message(struct rds_connection *,
-					 struct rm_rdma_op *);
+void rds_send_path_drop_acked(struct rds_conn_path *cp, u64 ack,
+			      is_acked_func is_acked);
+int rds_send_pong(struct rds_conn_path *cp, __be16 dport);
 
 /* rdma.c */
 void rds_rdma_unuse(struct rds_sock *rs, u32 r_key, int force);
@@ -808,11 +863,12 @@
 int rds_threads_init(void);
 void rds_threads_exit(void);
 extern struct workqueue_struct *rds_wq;
-void rds_queue_reconnect(struct rds_connection *conn);
+void rds_queue_reconnect(struct rds_conn_path *cp);
 void rds_connect_worker(struct work_struct *);
 void rds_shutdown_worker(struct work_struct *);
 void rds_send_worker(struct work_struct *);
 void rds_recv_worker(struct work_struct *);
+void rds_connect_path_complete(struct rds_conn_path *conn, int curr);
 void rds_connect_complete(struct rds_connection *conn);
 
 /* transport.c */
diff --git a/net/rds/rds_single_path.h b/net/rds/rds_single_path.h
new file mode 100644
index 0000000..e1241af
--- /dev/null
+++ b/net/rds/rds_single_path.h
@@ -0,0 +1,30 @@
+#ifndef _RDS_RDS_SINGLE_H
+#define _RDS_RDS_SINGLE_H
+
+#define	c_xmit_rm		c_path[0].cp_xmit_rm
+#define	c_xmit_sg		c_path[0].cp_xmit_sg
+#define	c_xmit_hdr_off		c_path[0].cp_xmit_hdr_off
+#define	c_xmit_data_off		c_path[0].cp_xmit_data_off
+#define	c_xmit_atomic_sent	c_path[0].cp_xmit_atomic_sent
+#define	c_xmit_rdma_sent	c_path[0].cp_xmit_rdma_sent
+#define	c_xmit_data_sent	c_path[0].cp_xmit_data_sent
+#define	c_lock			c_path[0].cp_lock
+#define c_next_tx_seq		c_path[0].cp_next_tx_seq
+#define c_send_queue		c_path[0].cp_send_queue
+#define c_retrans		c_path[0].cp_retrans
+#define c_next_rx_seq		c_path[0].cp_next_rx_seq
+#define c_transport_data	c_path[0].cp_transport_data
+#define c_state			c_path[0].cp_state
+#define c_send_gen		c_path[0].cp_send_gen
+#define c_flags			c_path[0].cp_flags
+#define c_reconnect_jiffies	c_path[0].cp_reconnect_jiffies
+#define c_send_w		c_path[0].cp_send_w
+#define c_recv_w		c_path[0].cp_recv_w
+#define c_conn_w		c_path[0].cp_conn_w
+#define c_down_w		c_path[0].cp_down_w
+#define c_cm_lock		c_path[0].cp_cm_lock
+#define c_waitq			c_path[0].cp_waitq
+#define c_unacked_packets	c_path[0].cp_unacked_packets
+#define c_unacked_bytes		c_path[0].cp_unacked_bytes
+
+#endif /* _RDS_RDS_SINGLE_H */
diff --git a/net/rds/recv.c b/net/rds/recv.c
index c0be1ec..b58f505 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -53,6 +53,20 @@
 }
 EXPORT_SYMBOL_GPL(rds_inc_init);
 
+void rds_inc_path_init(struct rds_incoming *inc, struct rds_conn_path *cp,
+		       __be32 saddr)
+{
+	atomic_set(&inc->i_refcount, 1);
+	INIT_LIST_HEAD(&inc->i_item);
+	inc->i_conn = cp->cp_conn;
+	inc->i_conn_path = cp;
+	inc->i_saddr = saddr;
+	inc->i_rdma_cookie = 0;
+	inc->i_rx_tstamp.tv_sec = 0;
+	inc->i_rx_tstamp.tv_usec = 0;
+}
+EXPORT_SYMBOL_GPL(rds_inc_path_init);
+
 static void rds_inc_addref(struct rds_incoming *inc)
 {
 	rdsdebug("addref inc %p ref %d\n", inc, atomic_read(&inc->i_refcount));
@@ -164,13 +178,18 @@
 	struct rds_sock *rs = NULL;
 	struct sock *sk;
 	unsigned long flags;
+	struct rds_conn_path *cp;
 
 	inc->i_conn = conn;
 	inc->i_rx_jiffies = jiffies;
+	if (conn->c_trans->t_mp_capable)
+		cp = inc->i_conn_path;
+	else
+		cp = &conn->c_path[0];
 
 	rdsdebug("conn %p next %llu inc %p seq %llu len %u sport %u dport %u "
 		 "flags 0x%x rx_jiffies %lu\n", conn,
-		 (unsigned long long)conn->c_next_rx_seq,
+		 (unsigned long long)cp->cp_next_rx_seq,
 		 inc,
 		 (unsigned long long)be64_to_cpu(inc->i_hdr.h_sequence),
 		 be32_to_cpu(inc->i_hdr.h_len),
@@ -199,16 +218,16 @@
 	 * XXX we could spend more on the wire to get more robust failure
 	 * detection, arguably worth it to avoid data corruption.
 	 */
-	if (be64_to_cpu(inc->i_hdr.h_sequence) < conn->c_next_rx_seq &&
+	if (be64_to_cpu(inc->i_hdr.h_sequence) < cp->cp_next_rx_seq &&
 	    (inc->i_hdr.h_flags & RDS_FLAG_RETRANSMITTED)) {
 		rds_stats_inc(s_recv_drop_old_seq);
 		goto out;
 	}
-	conn->c_next_rx_seq = be64_to_cpu(inc->i_hdr.h_sequence) + 1;
+	cp->cp_next_rx_seq = be64_to_cpu(inc->i_hdr.h_sequence) + 1;
 
 	if (rds_sysctl_ping_enable && inc->i_hdr.h_dport == 0) {
 		rds_stats_inc(s_recv_ping);
-		rds_send_pong(conn, inc->i_hdr.h_sport);
+		rds_send_pong(cp, inc->i_hdr.h_sport);
 		goto out;
 	}
 
@@ -561,5 +580,7 @@
 		minfo.fport = inc->i_hdr.h_dport;
 	}
 
+	minfo.flags = 0;
+
 	rds_info_copy(iter, &minfo, sizeof(minfo));
 }
diff --git a/net/rds/send.c b/net/rds/send.c
index c9cdb35..ee43d6b 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -62,14 +62,14 @@
  * Reset the send state.  Callers must ensure that this doesn't race with
  * rds_send_xmit().
  */
-void rds_send_reset(struct rds_connection *conn)
+void rds_send_path_reset(struct rds_conn_path *cp)
 {
 	struct rds_message *rm, *tmp;
 	unsigned long flags;
 
-	if (conn->c_xmit_rm) {
-		rm = conn->c_xmit_rm;
-		conn->c_xmit_rm = NULL;
+	if (cp->cp_xmit_rm) {
+		rm = cp->cp_xmit_rm;
+		cp->cp_xmit_rm = NULL;
 		/* Tell the user the RDMA op is no longer mapped by the
 		 * transport. This isn't entirely true (it's flushed out
 		 * independently) but as the connection is down, there's
@@ -78,36 +78,37 @@
 		rds_message_put(rm);
 	}
 
-	conn->c_xmit_sg = 0;
-	conn->c_xmit_hdr_off = 0;
-	conn->c_xmit_data_off = 0;
-	conn->c_xmit_atomic_sent = 0;
-	conn->c_xmit_rdma_sent = 0;
-	conn->c_xmit_data_sent = 0;
+	cp->cp_xmit_sg = 0;
+	cp->cp_xmit_hdr_off = 0;
+	cp->cp_xmit_data_off = 0;
+	cp->cp_xmit_atomic_sent = 0;
+	cp->cp_xmit_rdma_sent = 0;
+	cp->cp_xmit_data_sent = 0;
 
-	conn->c_map_queued = 0;
+	cp->cp_conn->c_map_queued = 0;
 
-	conn->c_unacked_packets = rds_sysctl_max_unacked_packets;
-	conn->c_unacked_bytes = rds_sysctl_max_unacked_bytes;
+	cp->cp_unacked_packets = rds_sysctl_max_unacked_packets;
+	cp->cp_unacked_bytes = rds_sysctl_max_unacked_bytes;
 
 	/* Mark messages as retransmissions, and move them to the send q */
-	spin_lock_irqsave(&conn->c_lock, flags);
-	list_for_each_entry_safe(rm, tmp, &conn->c_retrans, m_conn_item) {
+	spin_lock_irqsave(&cp->cp_lock, flags);
+	list_for_each_entry_safe(rm, tmp, &cp->cp_retrans, m_conn_item) {
 		set_bit(RDS_MSG_ACK_REQUIRED, &rm->m_flags);
 		set_bit(RDS_MSG_RETRANSMITTED, &rm->m_flags);
 	}
-	list_splice_init(&conn->c_retrans, &conn->c_send_queue);
-	spin_unlock_irqrestore(&conn->c_lock, flags);
+	list_splice_init(&cp->cp_retrans, &cp->cp_send_queue);
+	spin_unlock_irqrestore(&cp->cp_lock, flags);
+}
+EXPORT_SYMBOL_GPL(rds_send_path_reset);
+
+static int acquire_in_xmit(struct rds_conn_path *cp)
+{
+	return test_and_set_bit(RDS_IN_XMIT, &cp->cp_flags) == 0;
 }
 
-static int acquire_in_xmit(struct rds_connection *conn)
+static void release_in_xmit(struct rds_conn_path *cp)
 {
-	return test_and_set_bit(RDS_IN_XMIT, &conn->c_flags) == 0;
-}
-
-static void release_in_xmit(struct rds_connection *conn)
-{
-	clear_bit(RDS_IN_XMIT, &conn->c_flags);
+	clear_bit(RDS_IN_XMIT, &cp->cp_flags);
 	smp_mb__after_atomic();
 	/*
 	 * We don't use wait_on_bit()/wake_up_bit() because our waking is in a
@@ -115,8 +116,8 @@
 	 * the system-wide hashed waitqueue buckets in the fast path only to
 	 * almost never find waiters.
 	 */
-	if (waitqueue_active(&conn->c_waitq))
-		wake_up_all(&conn->c_waitq);
+	if (waitqueue_active(&cp->cp_waitq))
+		wake_up_all(&cp->cp_waitq);
 }
 
 /*
@@ -133,8 +134,9 @@
  *      - small message latency is higher behind queued large messages
  *      - large message latency isn't starved by intervening small sends
  */
-int rds_send_xmit(struct rds_connection *conn)
+int rds_send_xmit(struct rds_conn_path *cp)
 {
+	struct rds_connection *conn = cp->cp_conn;
 	struct rds_message *rm;
 	unsigned long flags;
 	unsigned int tmp;
@@ -154,7 +156,7 @@
 	 * avoids blocking the caller and trading per-connection data between
 	 * caches per message.
 	 */
-	if (!acquire_in_xmit(conn)) {
+	if (!acquire_in_xmit(cp)) {
 		rds_stats_inc(s_send_lock_contention);
 		ret = -ENOMEM;
 		goto out;
@@ -168,21 +170,25 @@
 	 * The acquire_in_xmit() check above ensures that only one
 	 * caller can increment c_send_gen at any time.
 	 */
-	conn->c_send_gen++;
-	send_gen = conn->c_send_gen;
+	cp->cp_send_gen++;
+	send_gen = cp->cp_send_gen;
 
 	/*
 	 * rds_conn_shutdown() sets the conn state and then tests RDS_IN_XMIT,
 	 * we do the opposite to avoid races.
 	 */
-	if (!rds_conn_up(conn)) {
-		release_in_xmit(conn);
+	if (!rds_conn_path_up(cp)) {
+		release_in_xmit(cp);
 		ret = 0;
 		goto out;
 	}
 
-	if (conn->c_trans->xmit_prepare)
+	if (conn->c_trans->t_mp_capable) {
+		if (conn->c_trans->xmit_path_prepare)
+			conn->c_trans->xmit_path_prepare(cp);
+	} else if (conn->c_trans->xmit_prepare) {
 		conn->c_trans->xmit_prepare(conn);
+	}
 
 	/*
 	 * spin trying to push headers and data down the connection until
@@ -190,7 +196,7 @@
 	 */
 	while (1) {
 
-		rm = conn->c_xmit_rm;
+		rm = cp->cp_xmit_rm;
 
 		/*
 		 * If between sending messages, we can send a pending congestion
@@ -203,14 +209,16 @@
 				break;
 			}
 			rm->data.op_active = 1;
+			rm->m_inc.i_conn_path = cp;
+			rm->m_inc.i_conn = cp->cp_conn;
 
-			conn->c_xmit_rm = rm;
+			cp->cp_xmit_rm = rm;
 		}
 
 		/*
 		 * If not already working on one, grab the next message.
 		 *
-		 * c_xmit_rm holds a ref while we're sending this message down
+		 * cp_xmit_rm holds a ref while we're sending this message down
 		 * the connction.  We can use this ref while holding the
 		 * send_sem.. rds_send_reset() is serialized with it.
 		 */
@@ -227,10 +235,10 @@
 			if (batch_count >= send_batch_count)
 				goto over_batch;
 
-			spin_lock_irqsave(&conn->c_lock, flags);
+			spin_lock_irqsave(&cp->cp_lock, flags);
 
-			if (!list_empty(&conn->c_send_queue)) {
-				rm = list_entry(conn->c_send_queue.next,
+			if (!list_empty(&cp->cp_send_queue)) {
+				rm = list_entry(cp->cp_send_queue.next,
 						struct rds_message,
 						m_conn_item);
 				rds_message_addref(rm);
@@ -239,10 +247,11 @@
 				 * Move the message from the send queue to the retransmit
 				 * list right away.
 				 */
-				list_move_tail(&rm->m_conn_item, &conn->c_retrans);
+				list_move_tail(&rm->m_conn_item,
+					       &cp->cp_retrans);
 			}
 
-			spin_unlock_irqrestore(&conn->c_lock, flags);
+			spin_unlock_irqrestore(&cp->cp_lock, flags);
 
 			if (!rm)
 				break;
@@ -256,32 +265,34 @@
 			 */
 			if (rm->rdma.op_active &&
 			    test_bit(RDS_MSG_RETRANSMITTED, &rm->m_flags)) {
-				spin_lock_irqsave(&conn->c_lock, flags);
+				spin_lock_irqsave(&cp->cp_lock, flags);
 				if (test_and_clear_bit(RDS_MSG_ON_CONN, &rm->m_flags))
 					list_move(&rm->m_conn_item, &to_be_dropped);
-				spin_unlock_irqrestore(&conn->c_lock, flags);
+				spin_unlock_irqrestore(&cp->cp_lock, flags);
 				continue;
 			}
 
 			/* Require an ACK every once in a while */
 			len = ntohl(rm->m_inc.i_hdr.h_len);
-			if (conn->c_unacked_packets == 0 ||
-			    conn->c_unacked_bytes < len) {
+			if (cp->cp_unacked_packets == 0 ||
+			    cp->cp_unacked_bytes < len) {
 				__set_bit(RDS_MSG_ACK_REQUIRED, &rm->m_flags);
 
-				conn->c_unacked_packets = rds_sysctl_max_unacked_packets;
-				conn->c_unacked_bytes = rds_sysctl_max_unacked_bytes;
+				cp->cp_unacked_packets =
+					rds_sysctl_max_unacked_packets;
+				cp->cp_unacked_bytes =
+					rds_sysctl_max_unacked_bytes;
 				rds_stats_inc(s_send_ack_required);
 			} else {
-				conn->c_unacked_bytes -= len;
-				conn->c_unacked_packets--;
+				cp->cp_unacked_bytes -= len;
+				cp->cp_unacked_packets--;
 			}
 
-			conn->c_xmit_rm = rm;
+			cp->cp_xmit_rm = rm;
 		}
 
 		/* The transport either sends the whole rdma or none of it */
-		if (rm->rdma.op_active && !conn->c_xmit_rdma_sent) {
+		if (rm->rdma.op_active && !cp->cp_xmit_rdma_sent) {
 			rm->m_final_op = &rm->rdma;
 			/* The transport owns the mapped memory for now.
 			 * You can't unmap it while it's on the send queue
@@ -293,11 +304,11 @@
 				wake_up_interruptible(&rm->m_flush_wait);
 				break;
 			}
-			conn->c_xmit_rdma_sent = 1;
+			cp->cp_xmit_rdma_sent = 1;
 
 		}
 
-		if (rm->atomic.op_active && !conn->c_xmit_atomic_sent) {
+		if (rm->atomic.op_active && !cp->cp_xmit_atomic_sent) {
 			rm->m_final_op = &rm->atomic;
 			/* The transport owns the mapped memory for now.
 			 * You can't unmap it while it's on the send queue
@@ -309,7 +320,7 @@
 				wake_up_interruptible(&rm->m_flush_wait);
 				break;
 			}
-			conn->c_xmit_atomic_sent = 1;
+			cp->cp_xmit_atomic_sent = 1;
 
 		}
 
@@ -335,41 +346,42 @@
 				rm->data.op_active = 0;
 		}
 
-		if (rm->data.op_active && !conn->c_xmit_data_sent) {
+		if (rm->data.op_active && !cp->cp_xmit_data_sent) {
 			rm->m_final_op = &rm->data;
+
 			ret = conn->c_trans->xmit(conn, rm,
-						  conn->c_xmit_hdr_off,
-						  conn->c_xmit_sg,
-						  conn->c_xmit_data_off);
+						  cp->cp_xmit_hdr_off,
+						  cp->cp_xmit_sg,
+						  cp->cp_xmit_data_off);
 			if (ret <= 0)
 				break;
 
-			if (conn->c_xmit_hdr_off < sizeof(struct rds_header)) {
+			if (cp->cp_xmit_hdr_off < sizeof(struct rds_header)) {
 				tmp = min_t(int, ret,
 					    sizeof(struct rds_header) -
-					    conn->c_xmit_hdr_off);
-				conn->c_xmit_hdr_off += tmp;
+					    cp->cp_xmit_hdr_off);
+				cp->cp_xmit_hdr_off += tmp;
 				ret -= tmp;
 			}
 
-			sg = &rm->data.op_sg[conn->c_xmit_sg];
+			sg = &rm->data.op_sg[cp->cp_xmit_sg];
 			while (ret) {
 				tmp = min_t(int, ret, sg->length -
-						      conn->c_xmit_data_off);
-				conn->c_xmit_data_off += tmp;
+						      cp->cp_xmit_data_off);
+				cp->cp_xmit_data_off += tmp;
 				ret -= tmp;
-				if (conn->c_xmit_data_off == sg->length) {
-					conn->c_xmit_data_off = 0;
+				if (cp->cp_xmit_data_off == sg->length) {
+					cp->cp_xmit_data_off = 0;
 					sg++;
-					conn->c_xmit_sg++;
-					BUG_ON(ret != 0 &&
-					       conn->c_xmit_sg == rm->data.op_nents);
+					cp->cp_xmit_sg++;
+					BUG_ON(ret != 0 && cp->cp_xmit_sg ==
+					       rm->data.op_nents);
 				}
 			}
 
-			if (conn->c_xmit_hdr_off == sizeof(struct rds_header) &&
-			    (conn->c_xmit_sg == rm->data.op_nents))
-				conn->c_xmit_data_sent = 1;
+			if (cp->cp_xmit_hdr_off == sizeof(struct rds_header) &&
+			    (cp->cp_xmit_sg == rm->data.op_nents))
+				cp->cp_xmit_data_sent = 1;
 		}
 
 		/*
@@ -377,23 +389,27 @@
 		 * if there is a data op. Thus, if the data is sent (or there was
 		 * none), then we're done with the rm.
 		 */
-		if (!rm->data.op_active || conn->c_xmit_data_sent) {
-			conn->c_xmit_rm = NULL;
-			conn->c_xmit_sg = 0;
-			conn->c_xmit_hdr_off = 0;
-			conn->c_xmit_data_off = 0;
-			conn->c_xmit_rdma_sent = 0;
-			conn->c_xmit_atomic_sent = 0;
-			conn->c_xmit_data_sent = 0;
+		if (!rm->data.op_active || cp->cp_xmit_data_sent) {
+			cp->cp_xmit_rm = NULL;
+			cp->cp_xmit_sg = 0;
+			cp->cp_xmit_hdr_off = 0;
+			cp->cp_xmit_data_off = 0;
+			cp->cp_xmit_rdma_sent = 0;
+			cp->cp_xmit_atomic_sent = 0;
+			cp->cp_xmit_data_sent = 0;
 
 			rds_message_put(rm);
 		}
 	}
 
 over_batch:
-	if (conn->c_trans->xmit_complete)
+	if (conn->c_trans->t_mp_capable) {
+		if (conn->c_trans->xmit_path_complete)
+			conn->c_trans->xmit_path_complete(cp);
+	} else if (conn->c_trans->xmit_complete) {
 		conn->c_trans->xmit_complete(conn);
-	release_in_xmit(conn);
+	}
+	release_in_xmit(cp);
 
 	/* Nuke any messages we decided not to retransmit. */
 	if (!list_empty(&to_be_dropped)) {
@@ -421,12 +437,12 @@
 	if (ret == 0) {
 		smp_mb();
 		if ((test_bit(0, &conn->c_map_queued) ||
-		     !list_empty(&conn->c_send_queue)) &&
-		    send_gen == conn->c_send_gen) {
+		     !list_empty(&cp->cp_send_queue)) &&
+		    send_gen == cp->cp_send_gen) {
 			rds_stats_inc(s_send_lock_queue_raced);
 			if (batch_count < send_batch_count)
 				goto restart;
-			queue_delayed_work(rds_wq, &conn->c_send_w, 1);
+			queue_delayed_work(rds_wq, &cp->cp_send_w, 1);
 		}
 	}
 out:
@@ -559,42 +575,6 @@
 }
 
 /*
- * This is called from the IB send completion when we detect
- * a RDMA operation that failed with remote access error.
- * So speed is not an issue here.
- */
-struct rds_message *rds_send_get_message(struct rds_connection *conn,
-					 struct rm_rdma_op *op)
-{
-	struct rds_message *rm, *tmp, *found = NULL;
-	unsigned long flags;
-
-	spin_lock_irqsave(&conn->c_lock, flags);
-
-	list_for_each_entry_safe(rm, tmp, &conn->c_retrans, m_conn_item) {
-		if (&rm->rdma == op) {
-			atomic_inc(&rm->m_refcount);
-			found = rm;
-			goto out;
-		}
-	}
-
-	list_for_each_entry_safe(rm, tmp, &conn->c_send_queue, m_conn_item) {
-		if (&rm->rdma == op) {
-			atomic_inc(&rm->m_refcount);
-			found = rm;
-			break;
-		}
-	}
-
-out:
-	spin_unlock_irqrestore(&conn->c_lock, flags);
-
-	return found;
-}
-EXPORT_SYMBOL_GPL(rds_send_get_message);
-
-/*
  * This removes messages from the socket's list if they're on it.  The list
  * argument must be private to the caller, we must be able to modify it
  * without locks.  The messages must have a reference held for their
@@ -684,16 +664,16 @@
  * assigned the m_ack_seq yet - but that's fine as long as tcp_is_acked
  * checks the RDS_MSG_HAS_ACK_SEQ bit.
  */
-void rds_send_drop_acked(struct rds_connection *conn, u64 ack,
-			 is_acked_func is_acked)
+void rds_send_path_drop_acked(struct rds_conn_path *cp, u64 ack,
+			      is_acked_func is_acked)
 {
 	struct rds_message *rm, *tmp;
 	unsigned long flags;
 	LIST_HEAD(list);
 
-	spin_lock_irqsave(&conn->c_lock, flags);
+	spin_lock_irqsave(&cp->cp_lock, flags);
 
-	list_for_each_entry_safe(rm, tmp, &conn->c_retrans, m_conn_item) {
+	list_for_each_entry_safe(rm, tmp, &cp->cp_retrans, m_conn_item) {
 		if (!rds_send_is_acked(rm, ack, is_acked))
 			break;
 
@@ -705,17 +685,26 @@
 	if (!list_empty(&list))
 		smp_mb__after_atomic();
 
-	spin_unlock_irqrestore(&conn->c_lock, flags);
+	spin_unlock_irqrestore(&cp->cp_lock, flags);
 
 	/* now remove the messages from the sock list as needed */
 	rds_send_remove_from_sock(&list, RDS_RDMA_SUCCESS);
 }
+EXPORT_SYMBOL_GPL(rds_send_path_drop_acked);
+
+void rds_send_drop_acked(struct rds_connection *conn, u64 ack,
+			 is_acked_func is_acked)
+{
+	WARN_ON(conn->c_trans->t_mp_capable);
+	rds_send_path_drop_acked(&conn->c_path[0], ack, is_acked);
+}
 EXPORT_SYMBOL_GPL(rds_send_drop_acked);
 
 void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest)
 {
 	struct rds_message *rm, *tmp;
 	struct rds_connection *conn;
+	struct rds_conn_path *cp;
 	unsigned long flags;
 	LIST_HEAD(list);
 
@@ -744,22 +733,26 @@
 	list_for_each_entry(rm, &list, m_sock_item) {
 
 		conn = rm->m_inc.i_conn;
+		if (conn->c_trans->t_mp_capable)
+			cp = rm->m_inc.i_conn_path;
+		else
+			cp = &conn->c_path[0];
 
-		spin_lock_irqsave(&conn->c_lock, flags);
+		spin_lock_irqsave(&cp->cp_lock, flags);
 		/*
 		 * Maybe someone else beat us to removing rm from the conn.
 		 * If we race with their flag update we'll get the lock and
 		 * then really see that the flag has been cleared.
 		 */
 		if (!test_and_clear_bit(RDS_MSG_ON_CONN, &rm->m_flags)) {
-			spin_unlock_irqrestore(&conn->c_lock, flags);
+			spin_unlock_irqrestore(&cp->cp_lock, flags);
 			spin_lock_irqsave(&rm->m_rs_lock, flags);
 			rm->m_rs = NULL;
 			spin_unlock_irqrestore(&rm->m_rs_lock, flags);
 			continue;
 		}
 		list_del_init(&rm->m_conn_item);
-		spin_unlock_irqrestore(&conn->c_lock, flags);
+		spin_unlock_irqrestore(&cp->cp_lock, flags);
 
 		/*
 		 * Couldn't grab m_rs_lock in top loop (lock ordering),
@@ -808,6 +801,7 @@
  * message from the flow with RDS_CANCEL_SENT_TO.
  */
 static int rds_send_queue_rm(struct rds_sock *rs, struct rds_connection *conn,
+			     struct rds_conn_path *cp,
 			     struct rds_message *rm, __be16 sport,
 			     __be16 dport, int *queued)
 {
@@ -851,13 +845,14 @@
 		   trying to minimize the time we hold c_lock */
 		rds_message_populate_header(&rm->m_inc.i_hdr, sport, dport, 0);
 		rm->m_inc.i_conn = conn;
+		rm->m_inc.i_conn_path = cp;
 		rds_message_addref(rm);
 
-		spin_lock(&conn->c_lock);
-		rm->m_inc.i_hdr.h_sequence = cpu_to_be64(conn->c_next_tx_seq++);
-		list_add_tail(&rm->m_conn_item, &conn->c_send_queue);
+		spin_lock(&cp->cp_lock);
+		rm->m_inc.i_hdr.h_sequence = cpu_to_be64(cp->cp_next_tx_seq++);
+		list_add_tail(&rm->m_conn_item, &cp->cp_send_queue);
 		set_bit(RDS_MSG_ON_CONN, &rm->m_flags);
-		spin_unlock(&conn->c_lock);
+		spin_unlock(&cp->cp_lock);
 
 		rdsdebug("queued msg %p len %d, rs %p bytes %d seq %llu\n",
 			 rm, len, rs, rs->rs_snd_bytes,
@@ -989,6 +984,7 @@
 	int queued = 0, allocated_mr = 0;
 	int nonblock = msg->msg_flags & MSG_DONTWAIT;
 	long timeo = sock_sndtimeo(sk, nonblock);
+	struct rds_conn_path *cpath;
 
 	/* Mirror Linux UDP mirror of BSD error message compatibility */
 	/* XXX: Perhaps MSG_MORE someday */
@@ -1087,15 +1083,16 @@
 		goto out;
 	}
 
-	rds_conn_connect_if_down(conn);
+	cpath = &conn->c_path[0];
+
+	rds_conn_path_connect_if_down(cpath);
 
 	ret = rds_cong_wait(conn->c_fcong, dport, nonblock, rs);
 	if (ret) {
 		rs->rs_seen_congestion = 1;
 		goto out;
 	}
-
-	while (!rds_send_queue_rm(rs, conn, rm, rs->rs_bound_port,
+	while (!rds_send_queue_rm(rs, conn, cpath, rm, rs->rs_bound_port,
 				  dport, &queued)) {
 		rds_stats_inc(s_send_queue_full);
 
@@ -1105,7 +1102,7 @@
 		}
 
 		timeo = wait_event_interruptible_timeout(*sk_sleep(sk),
-					rds_send_queue_rm(rs, conn, rm,
+					rds_send_queue_rm(rs, conn, cpath, rm,
 							  rs->rs_bound_port,
 							  dport,
 							  &queued),
@@ -1126,9 +1123,9 @@
 	 */
 	rds_stats_inc(s_send_queued);
 
-	ret = rds_send_xmit(conn);
+	ret = rds_send_xmit(cpath);
 	if (ret == -ENOMEM || ret == -EAGAIN)
-		queue_delayed_work(rds_wq, &conn->c_send_w, 1);
+		queue_delayed_work(rds_wq, &cpath->cp_send_w, 1);
 
 	rds_message_put(rm);
 	return payload_len;
@@ -1149,7 +1146,7 @@
  * Reply to a ping packet.
  */
 int
-rds_send_pong(struct rds_connection *conn, __be16 dport)
+rds_send_pong(struct rds_conn_path *cp, __be16 dport)
 {
 	struct rds_message *rm;
 	unsigned long flags;
@@ -1161,31 +1158,32 @@
 		goto out;
 	}
 
-	rm->m_daddr = conn->c_faddr;
+	rm->m_daddr = cp->cp_conn->c_faddr;
 	rm->data.op_active = 1;
 
-	rds_conn_connect_if_down(conn);
+	rds_conn_path_connect_if_down(cp);
 
-	ret = rds_cong_wait(conn->c_fcong, dport, 1, NULL);
+	ret = rds_cong_wait(cp->cp_conn->c_fcong, dport, 1, NULL);
 	if (ret)
 		goto out;
 
-	spin_lock_irqsave(&conn->c_lock, flags);
-	list_add_tail(&rm->m_conn_item, &conn->c_send_queue);
+	spin_lock_irqsave(&cp->cp_lock, flags);
+	list_add_tail(&rm->m_conn_item, &cp->cp_send_queue);
 	set_bit(RDS_MSG_ON_CONN, &rm->m_flags);
 	rds_message_addref(rm);
-	rm->m_inc.i_conn = conn;
+	rm->m_inc.i_conn = cp->cp_conn;
+	rm->m_inc.i_conn_path = cp;
 
 	rds_message_populate_header(&rm->m_inc.i_hdr, 0, dport,
-				    conn->c_next_tx_seq);
-	conn->c_next_tx_seq++;
-	spin_unlock_irqrestore(&conn->c_lock, flags);
+				    cp->cp_next_tx_seq);
+	cp->cp_next_tx_seq++;
+	spin_unlock_irqrestore(&cp->cp_lock, flags);
 
 	rds_stats_inc(s_send_queued);
 	rds_stats_inc(s_send_pong);
 
 	/* schedule the send work on rds_wq */
-	queue_delayed_work(rds_wq, &conn->c_send_w, 1);
+	queue_delayed_work(rds_wq, &cp->cp_send_w, 1);
 
 	rds_message_put(rm);
 	return 0;
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index 86187da..5217d49 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -38,6 +38,7 @@
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 
+#include "rds_single_path.h"
 #include "rds.h"
 #include "tcp.h"
 
@@ -56,8 +57,8 @@
 				 void __user *buffer, size_t *lenp,
 				 loff_t *fpos);
 
-int rds_tcp_min_sndbuf = SOCK_MIN_SNDBUF;
-int rds_tcp_min_rcvbuf = SOCK_MIN_RCVBUF;
+static int rds_tcp_min_sndbuf = SOCK_MIN_SNDBUF;
+static int rds_tcp_min_rcvbuf = SOCK_MIN_RCVBUF;
 
 static struct ctl_table rds_tcp_sysctl_table[] = {
 #define	RDS_TCP_SNDBUF	0
@@ -126,9 +127,81 @@
 }
 
 /*
- * This is the only path that sets tc->t_sock.  Send and receive trust that
- * it is set.  The RDS_CONN_UP bit protects those paths from being
- * called while it isn't set.
+ * rds_tcp_reset_callbacks() switches the to the new sock and
+ * returns the existing tc->t_sock.
+ *
+ * The only functions that set tc->t_sock are rds_tcp_set_callbacks
+ * and rds_tcp_reset_callbacks.  Send and receive trust that
+ * it is set.  The absence of RDS_CONN_UP bit protects those paths
+ * from being called while it isn't set.
+ */
+void rds_tcp_reset_callbacks(struct socket *sock,
+			     struct rds_connection *conn)
+{
+	struct rds_tcp_connection *tc = conn->c_transport_data;
+	struct socket *osock = tc->t_sock;
+
+	if (!osock)
+		goto newsock;
+
+	/* Need to resolve a duelling SYN between peers.
+	 * We have an outstanding SYN to this peer, which may
+	 * potentially have transitioned to the RDS_CONN_UP state,
+	 * so we must quiesce any send threads before resetting
+	 * c_transport_data. We quiesce these threads by setting
+	 * c_state to something other than RDS_CONN_UP, and then
+	 * waiting for any existing threads in rds_send_xmit to
+	 * complete release_in_xmit(). (Subsequent threads entering
+	 * rds_send_xmit() will bail on !rds_conn_up().
+	 *
+	 * However an incoming syn-ack at this point would end up
+	 * marking the conn as RDS_CONN_UP, and would again permit
+	 * rds_send_xmi() threads through, so ideally we would
+	 * synchronize on RDS_CONN_UP after lock_sock(), but cannot
+	 * do that: waiting on !RDS_IN_XMIT after lock_sock() may
+	 * end up deadlocking with tcp_sendmsg(), and the RDS_IN_XMIT
+	 * would not get set. As a result, we set c_state to
+	 * RDS_CONN_RESETTTING, to ensure that rds_tcp_state_change
+	 * cannot mark rds_conn_path_up() in the window before lock_sock()
+	 */
+	atomic_set(&conn->c_state, RDS_CONN_RESETTING);
+	wait_event(conn->c_waitq, !test_bit(RDS_IN_XMIT, &conn->c_flags));
+	lock_sock(osock->sk);
+	/* reset receive side state for rds_tcp_data_recv() for osock  */
+	if (tc->t_tinc) {
+		rds_inc_put(&tc->t_tinc->ti_inc);
+		tc->t_tinc = NULL;
+	}
+	tc->t_tinc_hdr_rem = sizeof(struct rds_header);
+	tc->t_tinc_data_rem = 0;
+	tc->t_sock = NULL;
+
+	write_lock_bh(&osock->sk->sk_callback_lock);
+
+	osock->sk->sk_user_data = NULL;
+	osock->sk->sk_data_ready = tc->t_orig_data_ready;
+	osock->sk->sk_write_space = tc->t_orig_write_space;
+	osock->sk->sk_state_change = tc->t_orig_state_change;
+	write_unlock_bh(&osock->sk->sk_callback_lock);
+	release_sock(osock->sk);
+	sock_release(osock);
+newsock:
+	rds_send_path_reset(&conn->c_path[0]);
+	lock_sock(sock->sk);
+	write_lock_bh(&sock->sk->sk_callback_lock);
+	tc->t_sock = sock;
+	sock->sk->sk_user_data = conn;
+	sock->sk->sk_data_ready = rds_tcp_data_ready;
+	sock->sk->sk_write_space = rds_tcp_write_space;
+	sock->sk->sk_state_change = rds_tcp_state_change;
+
+	write_unlock_bh(&sock->sk->sk_callback_lock);
+	release_sock(sock->sk);
+}
+
+/* Add tc to rds_tcp_tc_list and set tc->t_sock. See comments
+ * above rds_tcp_reset_callbacks for notes about synchronization
+ * with data path
  */
 void rds_tcp_set_callbacks(struct socket *sock, struct rds_connection *conn)
 {
diff --git a/net/rds/tcp.h b/net/rds/tcp.h
index 41c2283..ec0602b 100644
--- a/net/rds/tcp.h
+++ b/net/rds/tcp.h
@@ -50,6 +50,7 @@
 void rds_tcp_tune(struct socket *sock);
 void rds_tcp_nonagle(struct socket *sock);
 void rds_tcp_set_callbacks(struct socket *sock, struct rds_connection *conn);
+void rds_tcp_reset_callbacks(struct socket *sock, struct rds_connection *conn);
 void rds_tcp_restore_callbacks(struct socket *sock,
 			       struct rds_tcp_connection *tc);
 u32 rds_tcp_snd_nxt(struct rds_tcp_connection *tc);
diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c
index fb82e0a..ba9ec67 100644
--- a/net/rds/tcp_connect.c
+++ b/net/rds/tcp_connect.c
@@ -34,6 +34,7 @@
 #include <linux/in.h>
 #include <net/tcp.h>
 
+#include "rds_single_path.h"
 #include "rds.h"
 #include "tcp.h"
 
@@ -60,7 +61,8 @@
 		case TCP_SYN_RECV:
 			break;
 		case TCP_ESTABLISHED:
-			rds_connect_complete(conn);
+			rds_connect_path_complete(&conn->c_path[0],
+						  RDS_CONN_CONNECTING);
 			break;
 		case TCP_CLOSE_WAIT:
 		case TCP_CLOSE:
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index 4bf4bef..22d9bb1 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -35,6 +35,7 @@
 #include <linux/in.h>
 #include <net/tcp.h>
 
+#include "rds_single_path.h"
 #include "rds.h"
 #include "tcp.h"
 
@@ -78,7 +79,6 @@
 	struct inet_sock *inet;
 	struct rds_tcp_connection *rs_tcp = NULL;
 	int conn_state;
-	struct sock *nsk;
 
 	if (!sock) /* module unload or netns delete in progress */
 		return -ENETUNREACH;
@@ -133,29 +133,26 @@
 		 * c_transport_data.
 		 */
 		if (ntohl(inet->inet_saddr) < ntohl(inet->inet_daddr) ||
-		    !conn->c_outgoing) {
+		    !conn->c_path[0].cp_outgoing) {
 			goto rst_nsk;
 		} else {
-			atomic_set(&conn->c_state, RDS_CONN_CONNECTING);
-			wait_event(conn->c_waitq,
-				   !test_bit(RDS_IN_XMIT, &conn->c_flags));
-			rds_tcp_restore_callbacks(rs_tcp->t_sock, rs_tcp);
-			conn->c_outgoing = 0;
+			rds_tcp_reset_callbacks(new_sock, conn);
+			conn->c_path[0].cp_outgoing = 0;
+			/* rds_connect_path_complete() marks RDS_CONN_UP */
+			rds_connect_path_complete(&conn->c_path[0],
+						  RDS_CONN_DISCONNECTING);
 		}
+	} else {
+		rds_tcp_set_callbacks(new_sock, conn);
+		rds_connect_path_complete(&conn->c_path[0],
+					  RDS_CONN_CONNECTING);
 	}
-	rds_tcp_set_callbacks(new_sock, conn);
-	rds_connect_complete(conn); /* marks RDS_CONN_UP */
 	new_sock = NULL;
 	ret = 0;
 	goto out;
 rst_nsk:
 	/* reset the newly returned accept sock and bail */
-	nsk = new_sock->sk;
-	rds_tcp_stats_inc(s_tcp_listen_closed_stale);
-	nsk->sk_user_data = NULL;
-	nsk->sk_prot->disconnect(nsk, 0);
-	tcp_done(nsk);
-	new_sock = NULL;
+	kernel_sock_shutdown(new_sock, SHUT_RDWR);
 	ret = 0;
 out:
 	if (rs_tcp)
diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c
index c3196f9..3f8fb38 100644
--- a/net/rds/tcp_recv.c
+++ b/net/rds/tcp_recv.c
@@ -34,6 +34,7 @@
 #include <linux/slab.h>
 #include <net/tcp.h>
 
+#include "rds_single_path.h"
 #include "rds.h"
 #include "tcp.h"
 
diff --git a/net/rds/tcp_send.c b/net/rds/tcp_send.c
index 22d0f20..2b3414f 100644
--- a/net/rds/tcp_send.c
+++ b/net/rds/tcp_send.c
@@ -34,6 +34,7 @@
 #include <linux/in.h>
 #include <net/tcp.h>
 
+#include "rds_single_path.h"
 #include "rds.h"
 #include "tcp.h"
 
diff --git a/net/rds/threads.c b/net/rds/threads.c
index 454aa6d..9fbe95b 100644
--- a/net/rds/threads.c
+++ b/net/rds/threads.c
@@ -71,24 +71,30 @@
 struct workqueue_struct *rds_wq;
 EXPORT_SYMBOL_GPL(rds_wq);
 
-void rds_connect_complete(struct rds_connection *conn)
+void rds_connect_path_complete(struct rds_conn_path *cp, int curr)
 {
-	if (!rds_conn_transition(conn, RDS_CONN_CONNECTING, RDS_CONN_UP)) {
+	if (!rds_conn_path_transition(cp, curr, RDS_CONN_UP)) {
 		printk(KERN_WARNING "%s: Cannot transition to state UP, "
 				"current state is %d\n",
 				__func__,
-				atomic_read(&conn->c_state));
-		rds_conn_drop(conn);
+				atomic_read(&cp->cp_state));
+		rds_conn_path_drop(cp);
 		return;
 	}
 
 	rdsdebug("conn %p for %pI4 to %pI4 complete\n",
-	  conn, &conn->c_laddr, &conn->c_faddr);
+	  cp->cp_conn, &cp->cp_conn->c_laddr, &cp->cp_conn->c_faddr);
 
-	conn->c_reconnect_jiffies = 0;
-	set_bit(0, &conn->c_map_queued);
-	queue_delayed_work(rds_wq, &conn->c_send_w, 0);
-	queue_delayed_work(rds_wq, &conn->c_recv_w, 0);
+	cp->cp_reconnect_jiffies = 0;
+	set_bit(0, &cp->cp_conn->c_map_queued);
+	queue_delayed_work(rds_wq, &cp->cp_send_w, 0);
+	queue_delayed_work(rds_wq, &cp->cp_recv_w, 0);
+}
+EXPORT_SYMBOL_GPL(rds_connect_path_complete);
+
+void rds_connect_complete(struct rds_connection *conn)
+{
+	rds_connect_path_complete(&conn->c_path[0], RDS_CONN_CONNECTING);
 }
 EXPORT_SYMBOL_GPL(rds_connect_complete);
 
@@ -110,70 +116,79 @@
  * We should *always* start with a random backoff; otherwise a broken connection
  * will always take several iterations to be re-established.
  */
-void rds_queue_reconnect(struct rds_connection *conn)
+void rds_queue_reconnect(struct rds_conn_path *cp)
 {
 	unsigned long rand;
+	struct rds_connection *conn = cp->cp_conn;
 
 	rdsdebug("conn %p for %pI4 to %pI4 reconnect jiffies %lu\n",
 	  conn, &conn->c_laddr, &conn->c_faddr,
-	  conn->c_reconnect_jiffies);
+	  cp->cp_reconnect_jiffies);
 
-	set_bit(RDS_RECONNECT_PENDING, &conn->c_flags);
-	if (conn->c_reconnect_jiffies == 0) {
-		conn->c_reconnect_jiffies = rds_sysctl_reconnect_min_jiffies;
-		queue_delayed_work(rds_wq, &conn->c_conn_w, 0);
+	set_bit(RDS_RECONNECT_PENDING, &cp->cp_flags);
+	if (cp->cp_reconnect_jiffies == 0) {
+		cp->cp_reconnect_jiffies = rds_sysctl_reconnect_min_jiffies;
+		queue_delayed_work(rds_wq, &cp->cp_conn_w, 0);
 		return;
 	}
 
 	get_random_bytes(&rand, sizeof(rand));
 	rdsdebug("%lu delay %lu ceil conn %p for %pI4 -> %pI4\n",
-		 rand % conn->c_reconnect_jiffies, conn->c_reconnect_jiffies,
+		 rand % cp->cp_reconnect_jiffies, cp->cp_reconnect_jiffies,
 		 conn, &conn->c_laddr, &conn->c_faddr);
-	queue_delayed_work(rds_wq, &conn->c_conn_w,
-			   rand % conn->c_reconnect_jiffies);
+	queue_delayed_work(rds_wq, &cp->cp_conn_w,
+			   rand % cp->cp_reconnect_jiffies);
 
-	conn->c_reconnect_jiffies = min(conn->c_reconnect_jiffies * 2,
+	cp->cp_reconnect_jiffies = min(cp->cp_reconnect_jiffies * 2,
 					rds_sysctl_reconnect_max_jiffies);
 }
 
 void rds_connect_worker(struct work_struct *work)
 {
-	struct rds_connection *conn = container_of(work, struct rds_connection, c_conn_w.work);
+	struct rds_conn_path *cp = container_of(work,
+						struct rds_conn_path,
+						cp_conn_w.work);
+	struct rds_connection *conn = cp->cp_conn;
 	int ret;
 
-	clear_bit(RDS_RECONNECT_PENDING, &conn->c_flags);
-	if (rds_conn_transition(conn, RDS_CONN_DOWN, RDS_CONN_CONNECTING)) {
+	clear_bit(RDS_RECONNECT_PENDING, &cp->cp_flags);
+	if (rds_conn_path_transition(cp, RDS_CONN_DOWN, RDS_CONN_CONNECTING)) {
 		ret = conn->c_trans->conn_connect(conn);
 		rdsdebug("conn %p for %pI4 to %pI4 dispatched, ret %d\n",
 			conn, &conn->c_laddr, &conn->c_faddr, ret);
 
 		if (ret) {
-			if (rds_conn_transition(conn, RDS_CONN_CONNECTING, RDS_CONN_DOWN))
-				rds_queue_reconnect(conn);
+			if (rds_conn_path_transition(cp,
+						     RDS_CONN_CONNECTING,
+						     RDS_CONN_DOWN))
+				rds_queue_reconnect(cp);
 			else
-				rds_conn_error(conn, "RDS: connect failed\n");
+				rds_conn_path_error(cp,
+						    "RDS: connect failed\n");
 		}
 	}
 }
 
 void rds_send_worker(struct work_struct *work)
 {
-	struct rds_connection *conn = container_of(work, struct rds_connection, c_send_w.work);
+	struct rds_conn_path *cp = container_of(work,
+						struct rds_conn_path,
+						cp_send_w.work);
 	int ret;
 
-	if (rds_conn_state(conn) == RDS_CONN_UP) {
-		clear_bit(RDS_LL_SEND_FULL, &conn->c_flags);
-		ret = rds_send_xmit(conn);
+	if (rds_conn_path_state(cp) == RDS_CONN_UP) {
+		clear_bit(RDS_LL_SEND_FULL, &cp->cp_flags);
+		ret = rds_send_xmit(cp);
 		cond_resched();
-		rdsdebug("conn %p ret %d\n", conn, ret);
+		rdsdebug("conn %p ret %d\n", cp->cp_conn, ret);
 		switch (ret) {
 		case -EAGAIN:
 			rds_stats_inc(s_send_immediate_retry);
-			queue_delayed_work(rds_wq, &conn->c_send_w, 0);
+			queue_delayed_work(rds_wq, &cp->cp_send_w, 0);
 			break;
 		case -ENOMEM:
 			rds_stats_inc(s_send_delayed_retry);
-			queue_delayed_work(rds_wq, &conn->c_send_w, 2);
+			queue_delayed_work(rds_wq, &cp->cp_send_w, 2);
 		default:
 			break;
 		}
@@ -182,20 +197,22 @@
 
 void rds_recv_worker(struct work_struct *work)
 {
-	struct rds_connection *conn = container_of(work, struct rds_connection, c_recv_w.work);
+	struct rds_conn_path *cp = container_of(work,
+						struct rds_conn_path,
+						cp_recv_w.work);
 	int ret;
 
-	if (rds_conn_state(conn) == RDS_CONN_UP) {
-		ret = conn->c_trans->recv(conn);
-		rdsdebug("conn %p ret %d\n", conn, ret);
+	if (rds_conn_path_state(cp) == RDS_CONN_UP) {
+		ret = cp->cp_conn->c_trans->recv(cp->cp_conn);
+		rdsdebug("conn %p ret %d\n", cp->cp_conn, ret);
 		switch (ret) {
 		case -EAGAIN:
 			rds_stats_inc(s_recv_immediate_retry);
-			queue_delayed_work(rds_wq, &conn->c_recv_w, 0);
+			queue_delayed_work(rds_wq, &cp->cp_recv_w, 0);
 			break;
 		case -ENOMEM:
 			rds_stats_inc(s_recv_delayed_retry);
-			queue_delayed_work(rds_wq, &conn->c_recv_w, 2);
+			queue_delayed_work(rds_wq, &cp->cp_recv_w, 2);
 		default:
 			break;
 		}
@@ -204,9 +221,11 @@
 
 void rds_shutdown_worker(struct work_struct *work)
 {
-	struct rds_connection *conn = container_of(work, struct rds_connection, c_down_w);
+	struct rds_conn_path *cp = container_of(work,
+						struct rds_conn_path,
+						cp_down_w);
 
-	rds_conn_shutdown(conn);
+	rds_conn_shutdown(cp);
 }
 
 void rds_threads_exit(void)
diff --git a/net/rxrpc/Makefile b/net/rxrpc/Makefile
index e05a06e..b005027 100644
--- a/net/rxrpc/Makefile
+++ b/net/rxrpc/Makefile
@@ -4,25 +4,27 @@
 
 af-rxrpc-y := \
 	af_rxrpc.o \
-	ar-accept.o \
-	ar-ack.o \
-	ar-call.o \
-	ar-connection.o \
-	ar-connevent.o \
-	ar-error.o \
-	ar-input.o \
-	ar-key.o \
-	ar-local.o \
-	ar-output.o \
-	ar-peer.o \
-	ar-recvmsg.o \
-	ar-security.o \
-	ar-skbuff.o \
-	ar-transport.o \
+	call_accept.o \
+	call_event.o \
+	call_object.o \
+	conn_event.o \
+	conn_object.o \
+	input.o \
 	insecure.o \
-	misc.o
+	key.o \
+	local_event.o \
+	local_object.o \
+	misc.o \
+	output.o \
+	peer_event.o \
+	peer_object.o \
+	recvmsg.o \
+	security.o \
+	skbuff.o \
+	transport.o \
+	utils.o
 
-af-rxrpc-$(CONFIG_PROC_FS) += ar-proc.o
+af-rxrpc-$(CONFIG_PROC_FS) += proc.o
 af-rxrpc-$(CONFIG_RXKAD) += rxkad.o
 af-rxrpc-$(CONFIG_SYSCTL) += sysctl.o
 
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 7840b8e..c83c3c7 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -33,8 +33,6 @@
 module_param_named(debug, rxrpc_debug, uint, S_IWUSR | S_IRUGO);
 MODULE_PARM_DESC(debug, "RxRPC debugging mask");
 
-static int sysctl_rxrpc_max_qlen __read_mostly = 10;
-
 static struct proto rxrpc_proto;
 static const struct proto_ops rxrpc_rpc_ops;
 
@@ -104,6 +102,8 @@
 
 	switch (srx->transport.family) {
 	case AF_INET:
+		if (srx->transport_len < sizeof(struct sockaddr_in))
+			return -EINVAL;
 		_debug("INET: %x @ %pI4",
 		       ntohs(srx->transport.sin.sin_port),
 		       &srx->transport.sin.sin_addr);
@@ -139,33 +139,33 @@
 
 	lock_sock(&rx->sk);
 
-	if (rx->sk.sk_state != RXRPC_UNCONNECTED) {
+	if (rx->sk.sk_state != RXRPC_UNBOUND) {
 		ret = -EINVAL;
 		goto error_unlock;
 	}
 
 	memcpy(&rx->srx, srx, sizeof(rx->srx));
 
-	/* Find or create a local transport endpoint to use */
 	local = rxrpc_lookup_local(&rx->srx);
 	if (IS_ERR(local)) {
 		ret = PTR_ERR(local);
 		goto error_unlock;
 	}
 
-	rx->local = local;
-	if (srx->srx_service) {
+	if (rx->srx.srx_service) {
 		write_lock_bh(&local->services_lock);
 		list_for_each_entry(prx, &local->services, listen_link) {
-			if (prx->srx.srx_service == srx->srx_service)
+			if (prx->srx.srx_service == rx->srx.srx_service)
 				goto service_in_use;
 		}
 
+		rx->local = local;
 		list_add_tail(&rx->listen_link, &local->services);
 		write_unlock_bh(&local->services_lock);
 
 		rx->sk.sk_state = RXRPC_SERVER_BOUND;
 	} else {
+		rx->local = local;
 		rx->sk.sk_state = RXRPC_CLIENT_BOUND;
 	}
 
@@ -174,8 +174,9 @@
 	return 0;
 
 service_in_use:
-	ret = -EADDRINUSE;
 	write_unlock_bh(&local->services_lock);
+	rxrpc_put_local(local);
+	ret = -EADDRINUSE;
 error_unlock:
 	release_sock(&rx->sk);
 error:
@@ -190,6 +191,7 @@
 {
 	struct sock *sk = sock->sk;
 	struct rxrpc_sock *rx = rxrpc_sk(sk);
+	unsigned int max;
 	int ret;
 
 	_enter("%p,%d", rx, backlog);
@@ -197,20 +199,24 @@
 	lock_sock(&rx->sk);
 
 	switch (rx->sk.sk_state) {
-	case RXRPC_UNCONNECTED:
+	case RXRPC_UNBOUND:
 		ret = -EADDRNOTAVAIL;
 		break;
-	case RXRPC_CLIENT_BOUND:
-	case RXRPC_CLIENT_CONNECTED:
-	default:
-		ret = -EBUSY;
-		break;
 	case RXRPC_SERVER_BOUND:
 		ASSERT(rx->local != NULL);
+		max = READ_ONCE(rxrpc_max_backlog);
+		ret = -EINVAL;
+		if (backlog == INT_MAX)
+			backlog = max;
+		else if (backlog < 0 || backlog > max)
+			break;
 		sk->sk_max_ack_backlog = backlog;
 		rx->sk.sk_state = RXRPC_SERVER_LISTENING;
 		ret = 0;
 		break;
+	default:
+		ret = -EBUSY;
+		break;
 	}
 
 	release_sock(&rx->sk);
@@ -221,20 +227,18 @@
 /*
  * find a transport by address
  */
-static struct rxrpc_transport *rxrpc_name_to_transport(struct socket *sock,
-						       struct sockaddr *addr,
-						       int addr_len, int flags,
-						       gfp_t gfp)
+struct rxrpc_transport *rxrpc_name_to_transport(struct rxrpc_sock *rx,
+						struct sockaddr *addr,
+						int addr_len, int flags,
+						gfp_t gfp)
 {
 	struct sockaddr_rxrpc *srx = (struct sockaddr_rxrpc *) addr;
 	struct rxrpc_transport *trans;
-	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
 	struct rxrpc_peer *peer;
 
 	_enter("%p,%p,%d,%d", rx, addr, addr_len, flags);
 
 	ASSERT(rx->local != NULL);
-	ASSERT(rx->sk.sk_state > RXRPC_UNCONNECTED);
 
 	if (rx->srx.transport_type != srx->transport_type)
 		return ERR_PTR(-ESOCKTNOSUPPORT);
@@ -242,7 +246,7 @@
 		return ERR_PTR(-EAFNOSUPPORT);
 
 	/* find a remote transport endpoint from the local one */
-	peer = rxrpc_get_peer(srx, gfp);
+	peer = rxrpc_lookup_peer(rx->local, srx, gfp);
 	if (IS_ERR(peer))
 		return ERR_CAST(peer);
 
@@ -256,7 +260,7 @@
 /**
  * rxrpc_kernel_begin_call - Allow a kernel service to begin a call
  * @sock: The socket on which to make the call
- * @srx: The address of the peer to contact (defaults to socket setting)
+ * @srx: The address of the peer to contact
  * @key: The security context to use (defaults to socket setting)
  * @user_call_ID: The ID to use
  *
@@ -282,25 +286,14 @@
 
 	lock_sock(&rx->sk);
 
-	if (srx) {
-		trans = rxrpc_name_to_transport(sock, (struct sockaddr *) srx,
-						sizeof(*srx), 0, gfp);
-		if (IS_ERR(trans)) {
-			call = ERR_CAST(trans);
-			trans = NULL;
-			goto out_notrans;
-		}
-	} else {
-		trans = rx->trans;
-		if (!trans) {
-			call = ERR_PTR(-ENOTCONN);
-			goto out_notrans;
-		}
-		atomic_inc(&trans->usage);
+	trans = rxrpc_name_to_transport(rx, (struct sockaddr *)srx,
+					sizeof(*srx), 0, gfp);
+	if (IS_ERR(trans)) {
+		call = ERR_CAST(trans);
+		trans = NULL;
+		goto out_notrans;
 	}
 
-	if (!srx)
-		srx = &rx->srx;
 	if (!key)
 		key = rx->key;
 	if (key && !key->payload.data[0])
@@ -312,8 +305,7 @@
 		goto out;
 	}
 
-	call = rxrpc_get_client_call(rx, trans, bundle, user_call_ID, true,
-				     gfp);
+	call = rxrpc_new_client_call(rx, trans, bundle, user_call_ID, gfp);
 	rxrpc_put_bundle(trans, bundle);
 out:
 	rxrpc_put_transport(trans);
@@ -369,11 +361,8 @@
 static int rxrpc_connect(struct socket *sock, struct sockaddr *addr,
 			 int addr_len, int flags)
 {
-	struct sockaddr_rxrpc *srx = (struct sockaddr_rxrpc *) addr;
-	struct sock *sk = sock->sk;
-	struct rxrpc_transport *trans;
-	struct rxrpc_local *local;
-	struct rxrpc_sock *rx = rxrpc_sk(sk);
+	struct sockaddr_rxrpc *srx = (struct sockaddr_rxrpc *)addr;
+	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
 	int ret;
 
 	_enter("%p,%p,%d,%d", rx, addr, addr_len, flags);
@@ -386,45 +375,28 @@
 
 	lock_sock(&rx->sk);
 
+	ret = -EISCONN;
+	if (test_bit(RXRPC_SOCK_CONNECTED, &rx->flags))
+		goto error;
+
 	switch (rx->sk.sk_state) {
-	case RXRPC_UNCONNECTED:
-		/* find a local transport endpoint if we don't have one already */
-		ASSERTCMP(rx->local, ==, NULL);
-		rx->srx.srx_family = AF_RXRPC;
-		rx->srx.srx_service = 0;
-		rx->srx.transport_type = srx->transport_type;
-		rx->srx.transport_len = sizeof(sa_family_t);
-		rx->srx.transport.family = srx->transport.family;
-		local = rxrpc_lookup_local(&rx->srx);
-		if (IS_ERR(local)) {
-			release_sock(&rx->sk);
-			return PTR_ERR(local);
-		}
-		rx->local = local;
-		rx->sk.sk_state = RXRPC_CLIENT_BOUND;
+	case RXRPC_UNBOUND:
+		rx->sk.sk_state = RXRPC_CLIENT_UNBOUND;
+	case RXRPC_CLIENT_UNBOUND:
 	case RXRPC_CLIENT_BOUND:
 		break;
-	case RXRPC_CLIENT_CONNECTED:
-		release_sock(&rx->sk);
-		return -EISCONN;
 	default:
-		release_sock(&rx->sk);
-		return -EBUSY; /* server sockets can't connect as well */
+		ret = -EBUSY;
+		goto error;
 	}
 
-	trans = rxrpc_name_to_transport(sock, addr, addr_len, flags,
-					GFP_KERNEL);
-	if (IS_ERR(trans)) {
-		release_sock(&rx->sk);
-		_leave(" = %ld", PTR_ERR(trans));
-		return PTR_ERR(trans);
-	}
+	rx->connect_srx = *srx;
+	set_bit(RXRPC_SOCK_CONNECTED, &rx->flags);
+	ret = 0;
 
-	rx->trans = trans;
-	rx->sk.sk_state = RXRPC_CLIENT_CONNECTED;
-
+error:
 	release_sock(&rx->sk);
-	return 0;
+	return ret;
 }
 
 /*
@@ -438,7 +410,7 @@
  */
 static int rxrpc_sendmsg(struct socket *sock, struct msghdr *m, size_t len)
 {
-	struct rxrpc_transport *trans;
+	struct rxrpc_local *local;
 	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
 	int ret;
 
@@ -455,48 +427,38 @@
 		}
 	}
 
-	trans = NULL;
 	lock_sock(&rx->sk);
 
-	if (m->msg_name) {
-		ret = -EISCONN;
-		trans = rxrpc_name_to_transport(sock, m->msg_name,
-						m->msg_namelen, 0, GFP_KERNEL);
-		if (IS_ERR(trans)) {
-			ret = PTR_ERR(trans);
-			trans = NULL;
-			goto out;
-		}
-	} else {
-		trans = rx->trans;
-		if (trans)
-			atomic_inc(&trans->usage);
-	}
-
 	switch (rx->sk.sk_state) {
-	case RXRPC_SERVER_LISTENING:
-		if (!m->msg_name) {
-			ret = rxrpc_server_sendmsg(rx, m, len);
-			break;
+	case RXRPC_UNBOUND:
+		local = rxrpc_lookup_local(&rx->srx);
+		if (IS_ERR(local)) {
+			ret = PTR_ERR(local);
+			goto error_unlock;
+		}
+
+		rx->local = local;
+		rx->sk.sk_state = RXRPC_CLIENT_UNBOUND;
+		/* Fall through */
+
+	case RXRPC_CLIENT_UNBOUND:
+	case RXRPC_CLIENT_BOUND:
+		if (!m->msg_name &&
+		    test_bit(RXRPC_SOCK_CONNECTED, &rx->flags)) {
+			m->msg_name = &rx->connect_srx;
+			m->msg_namelen = sizeof(rx->connect_srx);
 		}
 	case RXRPC_SERVER_BOUND:
-	case RXRPC_CLIENT_BOUND:
-		if (!m->msg_name) {
-			ret = -ENOTCONN;
-			break;
-		}
-	case RXRPC_CLIENT_CONNECTED:
-		ret = rxrpc_client_sendmsg(rx, trans, m, len);
+	case RXRPC_SERVER_LISTENING:
+		ret = rxrpc_do_sendmsg(rx, m, len);
 		break;
 	default:
-		ret = -ENOTCONN;
+		ret = -EINVAL;
 		break;
 	}
 
-out:
+error_unlock:
 	release_sock(&rx->sk);
-	if (trans)
-		rxrpc_put_transport(trans);
 	_leave(" = %d", ret);
 	return ret;
 }
@@ -523,7 +485,7 @@
 			if (optlen != 0)
 				goto error;
 			ret = -EISCONN;
-			if (rx->sk.sk_state != RXRPC_UNCONNECTED)
+			if (rx->sk.sk_state != RXRPC_UNBOUND)
 				goto error;
 			set_bit(RXRPC_SOCK_EXCLUSIVE_CONN, &rx->flags);
 			goto success;
@@ -533,7 +495,7 @@
 			if (rx->key)
 				goto error;
 			ret = -EISCONN;
-			if (rx->sk.sk_state != RXRPC_UNCONNECTED)
+			if (rx->sk.sk_state != RXRPC_UNBOUND)
 				goto error;
 			ret = rxrpc_request_key(rx, optval, optlen);
 			goto error;
@@ -543,7 +505,7 @@
 			if (rx->key)
 				goto error;
 			ret = -EISCONN;
-			if (rx->sk.sk_state != RXRPC_UNCONNECTED)
+			if (rx->sk.sk_state != RXRPC_UNBOUND)
 				goto error;
 			ret = rxrpc_server_keyring(rx, optval, optlen);
 			goto error;
@@ -553,7 +515,7 @@
 			if (optlen != sizeof(unsigned int))
 				goto error;
 			ret = -EISCONN;
-			if (rx->sk.sk_state != RXRPC_UNCONNECTED)
+			if (rx->sk.sk_state != RXRPC_UNBOUND)
 				goto error;
 			ret = get_user(min_sec_level,
 				       (unsigned int __user *) optval);
@@ -632,9 +594,9 @@
 		return -ENOMEM;
 
 	sock_init_data(sock, sk);
-	sk->sk_state		= RXRPC_UNCONNECTED;
+	sk->sk_state		= RXRPC_UNBOUND;
 	sk->sk_write_space	= rxrpc_write_space;
-	sk->sk_max_ack_backlog	= sysctl_rxrpc_max_qlen;
+	sk->sk_max_ack_backlog	= 0;
 	sk->sk_destruct		= rxrpc_sock_destructor;
 
 	rx = rxrpc_sk(sk);
@@ -705,14 +667,6 @@
 		rx->conn = NULL;
 	}
 
-	if (rx->bundle) {
-		rxrpc_put_bundle(rx->trans, rx->bundle);
-		rx->bundle = NULL;
-	}
-	if (rx->trans) {
-		rxrpc_put_transport(rx->trans);
-		rx->trans = NULL;
-	}
 	if (rx->local) {
 		rxrpc_put_local(rx->local);
 		rx->local = NULL;
@@ -883,13 +837,27 @@
 	rxrpc_destroy_all_calls();
 	rxrpc_destroy_all_connections();
 	rxrpc_destroy_all_transports();
-	rxrpc_destroy_all_peers();
-	rxrpc_destroy_all_locals();
 
 	ASSERTCMP(atomic_read(&rxrpc_n_skbs), ==, 0);
 
+	/* We need to flush the scheduled work twice because the local endpoint
+	 * records involve a work item in their destruction as they can only be
+	 * destroyed from process context.  However, a connection may have a
+	 * work item outstanding - and this will pin the local endpoint record
+	 * until the connection goes away.
+	 *
+	 * Peers don't pin locals and calls pin sockets - which prevents the
+	 * module from being unloaded - so we should only need two flushes.
+	 */
 	_debug("flush scheduled work");
 	flush_workqueue(rxrpc_workqueue);
+	_debug("flush scheduled work 2");
+	flush_workqueue(rxrpc_workqueue);
+	_debug("synchronise RCU");
+	rcu_barrier();
+	_debug("destroy locals");
+	rxrpc_destroy_all_locals();
+
 	remove_proc_entry("rxrpc_conns", init_net.proc_net);
 	remove_proc_entry("rxrpc_calls", init_net.proc_net);
 	destroy_workqueue(rxrpc_workqueue);
diff --git a/net/rxrpc/ar-error.c b/net/rxrpc/ar-error.c
deleted file mode 100644
index 3e82d6f..0000000
--- a/net/rxrpc/ar-error.c
+++ /dev/null
@@ -1,230 +0,0 @@
-/* Error message handling (ICMP)
- *
- * Copyright (C) 2007 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 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/net.h>
-#include <linux/skbuff.h>
-#include <linux/errqueue.h>
-#include <linux/udp.h>
-#include <linux/in.h>
-#include <linux/in6.h>
-#include <linux/icmp.h>
-#include <net/sock.h>
-#include <net/af_rxrpc.h>
-#include <net/ip.h>
-#include "ar-internal.h"
-
-/*
- * handle an error received on the local endpoint
- */
-void rxrpc_UDP_error_report(struct sock *sk)
-{
-	struct sock_exterr_skb *serr;
-	struct rxrpc_transport *trans;
-	struct rxrpc_local *local = sk->sk_user_data;
-	struct rxrpc_peer *peer;
-	struct sk_buff *skb;
-	__be32 addr;
-	__be16 port;
-
-	_enter("%p{%d}", sk, local->debug_id);
-
-	skb = sock_dequeue_err_skb(sk);
-	if (!skb) {
-		_leave("UDP socket errqueue empty");
-		return;
-	}
-	serr = SKB_EXT_ERR(skb);
-	if (!skb->len && serr->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) {
-		_leave("UDP empty message");
-		kfree_skb(skb);
-		return;
-	}
-
-	rxrpc_new_skb(skb);
-
-	addr = *(__be32 *)(skb_network_header(skb) + serr->addr_offset);
-	port = serr->port;
-
-	_net("Rx UDP Error from %pI4:%hu", &addr, ntohs(port));
-	_debug("Msg l:%d d:%d", skb->len, skb->data_len);
-
-	peer = rxrpc_find_peer(local, addr, port);
-	if (IS_ERR(peer)) {
-		rxrpc_free_skb(skb);
-		_leave(" [no peer]");
-		return;
-	}
-
-	trans = rxrpc_find_transport(local, peer);
-	if (!trans) {
-		rxrpc_put_peer(peer);
-		rxrpc_free_skb(skb);
-		_leave(" [no trans]");
-		return;
-	}
-
-	if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP &&
-	    serr->ee.ee_type == ICMP_DEST_UNREACH &&
-	    serr->ee.ee_code == ICMP_FRAG_NEEDED
-	    ) {
-		u32 mtu = serr->ee.ee_info;
-
-		_net("Rx Received ICMP Fragmentation Needed (%d)", mtu);
-
-		/* wind down the local interface MTU */
-		if (mtu > 0 && peer->if_mtu == 65535 && mtu < peer->if_mtu) {
-			peer->if_mtu = mtu;
-			_net("I/F MTU %u", mtu);
-		}
-
-		if (mtu == 0) {
-			/* they didn't give us a size, estimate one */
-			mtu = peer->if_mtu;
-			if (mtu > 1500) {
-				mtu >>= 1;
-				if (mtu < 1500)
-					mtu = 1500;
-			} else {
-				mtu -= 100;
-				if (mtu < peer->hdrsize)
-					mtu = peer->hdrsize + 4;
-			}
-		}
-
-		if (mtu < peer->mtu) {
-			spin_lock_bh(&peer->lock);
-			peer->mtu = mtu;
-			peer->maxdata = peer->mtu - peer->hdrsize;
-			spin_unlock_bh(&peer->lock);
-			_net("Net MTU %u (maxdata %u)",
-			     peer->mtu, peer->maxdata);
-		}
-	}
-
-	rxrpc_put_peer(peer);
-
-	/* pass the transport ref to error_handler to release */
-	skb_queue_tail(&trans->error_queue, skb);
-	rxrpc_queue_work(&trans->error_handler);
-	_leave("");
-}
-
-/*
- * deal with UDP error messages
- */
-void rxrpc_UDP_error_handler(struct work_struct *work)
-{
-	struct sock_extended_err *ee;
-	struct sock_exterr_skb *serr;
-	struct rxrpc_transport *trans =
-		container_of(work, struct rxrpc_transport, error_handler);
-	struct sk_buff *skb;
-	int err;
-
-	_enter("");
-
-	skb = skb_dequeue(&trans->error_queue);
-	if (!skb)
-		return;
-
-	serr = SKB_EXT_ERR(skb);
-	ee = &serr->ee;
-
-	_net("Rx Error o=%d t=%d c=%d e=%d",
-	     ee->ee_origin, ee->ee_type, ee->ee_code, ee->ee_errno);
-
-	err = ee->ee_errno;
-
-	switch (ee->ee_origin) {
-	case SO_EE_ORIGIN_ICMP:
-		switch (ee->ee_type) {
-		case ICMP_DEST_UNREACH:
-			switch (ee->ee_code) {
-			case ICMP_NET_UNREACH:
-				_net("Rx Received ICMP Network Unreachable");
-				break;
-			case ICMP_HOST_UNREACH:
-				_net("Rx Received ICMP Host Unreachable");
-				break;
-			case ICMP_PORT_UNREACH:
-				_net("Rx Received ICMP Port Unreachable");
-				break;
-			case ICMP_NET_UNKNOWN:
-				_net("Rx Received ICMP Unknown Network");
-				break;
-			case ICMP_HOST_UNKNOWN:
-				_net("Rx Received ICMP Unknown Host");
-				break;
-			default:
-				_net("Rx Received ICMP DestUnreach code=%u",
-				     ee->ee_code);
-				break;
-			}
-			break;
-
-		case ICMP_TIME_EXCEEDED:
-			_net("Rx Received ICMP TTL Exceeded");
-			break;
-
-		default:
-			_proto("Rx Received ICMP error { type=%u code=%u }",
-			       ee->ee_type, ee->ee_code);
-			break;
-		}
-		break;
-
-	case SO_EE_ORIGIN_LOCAL:
-		_proto("Rx Received local error { error=%d }",
-		       ee->ee_errno);
-		break;
-
-	case SO_EE_ORIGIN_NONE:
-	case SO_EE_ORIGIN_ICMP6:
-	default:
-		_proto("Rx Received error report { orig=%u }",
-		       ee->ee_origin);
-		break;
-	}
-
-	/* terminate all the affected calls if there's an unrecoverable
-	 * error */
-	if (err) {
-		struct rxrpc_call *call, *_n;
-
-		_debug("ISSUE ERROR %d", err);
-
-		spin_lock_bh(&trans->peer->lock);
-		trans->peer->net_error = err;
-
-		list_for_each_entry_safe(call, _n, &trans->peer->error_targets,
-					 error_link) {
-			write_lock(&call->state_lock);
-			if (call->state != RXRPC_CALL_COMPLETE &&
-			    call->state < RXRPC_CALL_NETWORK_ERROR) {
-				call->state = RXRPC_CALL_NETWORK_ERROR;
-				set_bit(RXRPC_CALL_EV_RCVD_ERROR, &call->events);
-				rxrpc_queue_call(call);
-			}
-			write_unlock(&call->state_lock);
-			list_del_init(&call->error_link);
-		}
-
-		spin_unlock_bh(&trans->peer->lock);
-	}
-
-	if (!skb_queue_empty(&trans->error_queue))
-		rxrpc_queue_work(&trans->error_handler);
-
-	rxrpc_free_skb(skb);
-	rxrpc_put_transport(trans);
-	_leave("");
-}
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 18ab5c5..c168268 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -9,7 +9,9 @@
  * 2 of the License, or (at your option) any later version.
  */
 
+#include <linux/atomic.h>
 #include <net/sock.h>
+#include <net/af_rxrpc.h>
 #include <rxrpc/packet.h>
 
 #if 0
@@ -39,9 +41,9 @@
  * sk_state for RxRPC sockets
  */
 enum {
-	RXRPC_UNCONNECTED = 0,
+	RXRPC_UNBOUND = 0,
+	RXRPC_CLIENT_UNBOUND,		/* Unbound socket used as client */
 	RXRPC_CLIENT_BOUND,		/* client local address bound */
-	RXRPC_CLIENT_CONNECTED,		/* client is connected */
 	RXRPC_SERVER_BOUND,		/* server local address bound */
 	RXRPC_SERVER_LISTENING,		/* server listening for connections */
 	RXRPC_CLOSE,			/* socket is being closed */
@@ -55,8 +57,6 @@
 	struct sock		sk;
 	rxrpc_interceptor_t	interceptor;	/* kernel service Rx interceptor function */
 	struct rxrpc_local	*local;		/* local endpoint */
-	struct rxrpc_transport	*trans;		/* transport handler */
-	struct rxrpc_conn_bundle *bundle;	/* virtual connection bundle */
 	struct rxrpc_connection	*conn;		/* exclusive virtual connection */
 	struct list_head	listen_link;	/* link in the local endpoint's listen list */
 	struct list_head	secureq;	/* calls awaiting connection security clearance */
@@ -65,11 +65,13 @@
 	struct key		*securities;	/* list of server security descriptors */
 	struct rb_root		calls;		/* outstanding calls on this socket */
 	unsigned long		flags;
+#define RXRPC_SOCK_CONNECTED		0	/* connect_srx is set */
 #define RXRPC_SOCK_EXCLUSIVE_CONN	1	/* exclusive connection for a client socket */
 	rwlock_t		call_lock;	/* lock for calls */
 	u32			min_sec_level;	/* minimum security level */
 #define RXRPC_SECURITY_MAX	RXRPC_SECURITY_ENCRYPT
 	struct sockaddr_rxrpc	srx;		/* local address */
+	struct sockaddr_rxrpc	connect_srx;	/* Default client address from connect() */
 	sa_family_t		proto;		/* protocol created with */
 };
 
@@ -168,46 +170,49 @@
 };
 
 /*
- * RxRPC local transport endpoint definition
- * - matched by local port, address and protocol type
+ * RxRPC local transport endpoint description
+ * - owned by a single AF_RXRPC socket
+ * - pointed to by transport socket struct sk_user_data
  */
 struct rxrpc_local {
+	struct rcu_head		rcu;
+	atomic_t		usage;
+	struct list_head	link;
 	struct socket		*socket;	/* my UDP socket */
-	struct work_struct	destroyer;	/* endpoint destroyer */
-	struct work_struct	acceptor;	/* incoming call processor */
-	struct work_struct	rejecter;	/* packet reject writer */
-	struct work_struct	event_processor; /* endpoint event processor */
+	struct work_struct	processor;
 	struct list_head	services;	/* services listening on this endpoint */
-	struct list_head	link;		/* link in endpoint list */
 	struct rw_semaphore	defrag_sem;	/* control re-enablement of IP DF bit */
 	struct sk_buff_head	accept_queue;	/* incoming calls awaiting acceptance */
 	struct sk_buff_head	reject_queue;	/* packets awaiting rejection */
 	struct sk_buff_head	event_queue;	/* endpoint event packets awaiting processing */
+	struct mutex		conn_lock;	/* Client connection creation lock */
 	spinlock_t		lock;		/* access lock */
 	rwlock_t		services_lock;	/* lock for services list */
-	atomic_t		usage;
 	int			debug_id;	/* debug ID for printks */
-	volatile char		error_rcvd;	/* T if received ICMP error outstanding */
+	bool			dead;
 	struct sockaddr_rxrpc	srx;		/* local address */
 };
 
 /*
  * RxRPC remote transport endpoint definition
- * - matched by remote port, address and protocol type
- * - holds the connection ID counter for connections between the two endpoints
+ * - matched by local endpoint, remote port, address and protocol type
  */
 struct rxrpc_peer {
-	struct work_struct	destroyer;	/* peer destroyer */
-	struct list_head	link;		/* link in master peer list */
-	struct list_head	error_targets;	/* targets for net error distribution */
-	spinlock_t		lock;		/* access lock */
+	struct rcu_head		rcu;		/* This must be first */
 	atomic_t		usage;
+	unsigned long		hash_key;
+	struct hlist_node	hash_link;
+	struct rxrpc_local	*local;
+	struct hlist_head	error_targets;	/* targets for net error distribution */
+	struct work_struct	error_distributor;
+	spinlock_t		lock;		/* access lock */
 	unsigned int		if_mtu;		/* interface MTU for this peer */
 	unsigned int		mtu;		/* network MTU for this peer */
 	unsigned int		maxdata;	/* data size (MTU - hdrsize) */
 	unsigned short		hdrsize;	/* header size (IP + UDP + RxRPC) */
 	int			debug_id;	/* debug ID for printks */
-	int			net_error;	/* network error distributed */
+	int			error_report;	/* Net (+0) or local (+1000000) to distribute */
+#define RXRPC_LOCAL_ERROR_OFFSET 1000000
 	struct sockaddr_rxrpc	srx;		/* remote address */
 
 	/* calculated RTT cache */
@@ -226,12 +231,10 @@
 struct rxrpc_transport {
 	struct rxrpc_local	*local;		/* local transport endpoint */
 	struct rxrpc_peer	*peer;		/* remote transport endpoint */
-	struct work_struct	error_handler;	/* network error distributor */
 	struct rb_root		bundles;	/* client connection bundles on this transport */
 	struct rb_root		client_conns;	/* client connections on this transport */
 	struct rb_root		server_conns;	/* server connections on this transport */
 	struct list_head	link;		/* link in master session list */
-	struct sk_buff_head	error_queue;	/* error packets awaiting processing */
 	unsigned long		put_time;	/* time at which to reap */
 	spinlock_t		client_lock;	/* client connection allocation lock */
 	rwlock_t		conn_lock;	/* lock for active/dead connections */
@@ -390,7 +393,7 @@
 	struct work_struct	destroyer;	/* call destroyer */
 	struct work_struct	processor;	/* packet processor and ACK generator */
 	struct list_head	link;		/* link in master call list */
-	struct list_head	error_link;	/* link in error distribution list */
+	struct hlist_node	error_link;	/* link in error distribution list */
 	struct list_head	accept_link;	/* calls awaiting acceptance */
 	struct rb_node		sock_node;	/* node in socket call tree */
 	struct rb_node		conn_node;	/* node in connection call tree */
@@ -408,7 +411,8 @@
 	atomic_t		sequence;	/* Tx data packet sequence counter */
 	u32			local_abort;	/* local abort code */
 	u32			remote_abort;	/* remote abort code */
-	int			error;		/* local error incurred */
+	int			error_report;	/* Network error (ICMP/local transport) */
+	int			error;		/* Local error incurred */
 	enum rxrpc_call_state	state : 8;	/* current state of call */
 	int			debug_id;	/* debug ID for printks */
 	u8			channel;	/* connection channel occupied by this call */
@@ -477,22 +481,26 @@
 extern atomic_t rxrpc_debug_id;
 extern struct workqueue_struct *rxrpc_workqueue;
 
+extern struct rxrpc_transport *rxrpc_name_to_transport(struct rxrpc_sock *,
+						       struct sockaddr *,
+						       int, int, gfp_t);
+
 /*
- * ar-accept.c
+ * call_accept.c
  */
-void rxrpc_accept_incoming_calls(struct work_struct *);
+void rxrpc_accept_incoming_calls(struct rxrpc_local *);
 struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *, unsigned long);
 int rxrpc_reject_call(struct rxrpc_sock *);
 
 /*
- * ar-ack.c
+ * call_event.c
  */
 void __rxrpc_propose_ACK(struct rxrpc_call *, u8, u32, bool);
 void rxrpc_propose_ACK(struct rxrpc_call *, u8, u32, bool);
 void rxrpc_process_call(struct work_struct *);
 
 /*
- * ar-call.c
+ * call_object.c
  */
 extern unsigned int rxrpc_max_call_lifetime;
 extern unsigned int rxrpc_dead_call_expiry;
@@ -502,21 +510,28 @@
 
 struct rxrpc_call *rxrpc_find_call_hash(struct rxrpc_host_header *,
 					void *, sa_family_t, const void *);
-struct rxrpc_call *rxrpc_get_client_call(struct rxrpc_sock *,
+struct rxrpc_call *rxrpc_find_call_by_user_ID(struct rxrpc_sock *, unsigned long);
+struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *,
 					 struct rxrpc_transport *,
 					 struct rxrpc_conn_bundle *,
-					 unsigned long, int, gfp_t);
+					 unsigned long, gfp_t);
 struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *,
 				       struct rxrpc_connection *,
 				       struct rxrpc_host_header *);
-struct rxrpc_call *rxrpc_find_server_call(struct rxrpc_sock *, unsigned long);
 void rxrpc_release_call(struct rxrpc_call *);
 void rxrpc_release_calls_on_socket(struct rxrpc_sock *);
 void __rxrpc_put_call(struct rxrpc_call *);
 void __exit rxrpc_destroy_all_calls(void);
 
 /*
- * ar-connection.c
+ * conn_event.c
+ */
+void rxrpc_process_connection(struct work_struct *);
+void rxrpc_reject_packet(struct rxrpc_local *, struct sk_buff *);
+void rxrpc_reject_packets(struct rxrpc_local *);
+
+/*
+ * conn_object.c
  */
 extern unsigned int rxrpc_connection_expiry;
 extern struct list_head rxrpc_connections;
@@ -536,36 +551,19 @@
 rxrpc_incoming_connection(struct rxrpc_transport *, struct rxrpc_host_header *);
 
 /*
- * ar-connevent.c
- */
-void rxrpc_process_connection(struct work_struct *);
-void rxrpc_reject_packet(struct rxrpc_local *, struct sk_buff *);
-void rxrpc_reject_packets(struct work_struct *);
-
-/*
- * ar-error.c
- */
-void rxrpc_UDP_error_report(struct sock *);
-void rxrpc_UDP_error_handler(struct work_struct *);
-
-/*
- * ar-input.c
+ * input.c
  */
 void rxrpc_data_ready(struct sock *);
 int rxrpc_queue_rcv_skb(struct rxrpc_call *, struct sk_buff *, bool, bool);
 void rxrpc_fast_process_packet(struct rxrpc_call *, struct sk_buff *);
 
 /*
- * ar-local.c
+ * insecure.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);
+extern const struct rxrpc_security rxrpc_no_security;
 
 /*
- * ar-key.c
+ * key.c
  */
 extern struct key_type key_type_rxrpc;
 extern struct key_type key_type_rxrpc_s;
@@ -576,69 +574,38 @@
 			      u32);
 
 /*
- * ar-output.c
+ * local_event.c
  */
-extern unsigned int rxrpc_resend_timeout;
-
-int rxrpc_send_packet(struct rxrpc_transport *, struct sk_buff *);
-int rxrpc_client_sendmsg(struct rxrpc_sock *, struct rxrpc_transport *,
-			 struct msghdr *, size_t);
-int rxrpc_server_sendmsg(struct rxrpc_sock *, struct msghdr *, size_t);
+extern void rxrpc_process_local_events(struct rxrpc_local *);
 
 /*
- * ar-peer.c
+ * local_object.c
  */
-struct rxrpc_peer *rxrpc_get_peer(struct sockaddr_rxrpc *, gfp_t);
-void rxrpc_put_peer(struct rxrpc_peer *);
-struct rxrpc_peer *rxrpc_find_peer(struct rxrpc_local *, __be32, __be16);
-void __exit rxrpc_destroy_all_peers(void);
+struct rxrpc_local *rxrpc_lookup_local(const struct sockaddr_rxrpc *);
+void __rxrpc_put_local(struct rxrpc_local *);
+void __exit rxrpc_destroy_all_locals(void);
 
-/*
- * ar-proc.c
- */
-extern const char *const rxrpc_call_states[];
-extern const struct file_operations rxrpc_call_seq_fops;
-extern const struct file_operations rxrpc_connection_seq_fops;
+static inline void rxrpc_get_local(struct rxrpc_local *local)
+{
+	atomic_inc(&local->usage);
+}
 
-/*
- * ar-recvmsg.c
- */
-void rxrpc_remove_user_ID(struct rxrpc_sock *, struct rxrpc_call *);
-int rxrpc_recvmsg(struct socket *, struct msghdr *, size_t, int);
+static inline
+struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local)
+{
+	return atomic_inc_not_zero(&local->usage) ? local : NULL;
+}
 
-/*
- * ar-security.c
- */
-int __init rxrpc_init_security(void);
-void rxrpc_exit_security(void);
-int rxrpc_init_client_conn_security(struct rxrpc_connection *);
-int rxrpc_init_server_conn_security(struct rxrpc_connection *);
-
-/*
- * ar-skbuff.c
- */
-void rxrpc_packet_destructor(struct sk_buff *);
-
-/*
- * ar-transport.c
- */
-extern unsigned int rxrpc_transport_expiry;
-
-struct rxrpc_transport *rxrpc_get_transport(struct rxrpc_local *,
-					    struct rxrpc_peer *, gfp_t);
-void rxrpc_put_transport(struct rxrpc_transport *);
-void __exit rxrpc_destroy_all_transports(void);
-struct rxrpc_transport *rxrpc_find_transport(struct rxrpc_local *,
-					     struct rxrpc_peer *);
-
-/*
- * insecure.c
- */
-extern const struct rxrpc_security rxrpc_no_security;
+static inline void rxrpc_put_local(struct rxrpc_local *local)
+{
+	if (atomic_dec_and_test(&local->usage))
+		__rxrpc_put_local(local);
+}
 
 /*
  * misc.c
  */
+extern unsigned int rxrpc_max_backlog __read_mostly;
 extern unsigned int rxrpc_requested_ack_delay;
 extern unsigned int rxrpc_soft_ack_delay;
 extern unsigned int rxrpc_idle_ack_delay;
@@ -652,6 +619,60 @@
 extern const char *rxrpc_acks(u8 reason);
 
 /*
+ * output.c
+ */
+extern unsigned int rxrpc_resend_timeout;
+
+int rxrpc_send_packet(struct rxrpc_transport *, struct sk_buff *);
+int rxrpc_do_sendmsg(struct rxrpc_sock *, struct msghdr *, size_t);
+
+/*
+ * peer_event.c
+ */
+void rxrpc_error_report(struct sock *);
+void rxrpc_peer_error_distributor(struct work_struct *);
+
+/*
+ * peer_object.c
+ */
+struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *,
+					 const struct sockaddr_rxrpc *);
+struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *,
+				     struct sockaddr_rxrpc *, gfp_t);
+struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *, gfp_t);
+
+static inline void rxrpc_get_peer(struct rxrpc_peer *peer)
+{
+	atomic_inc(&peer->usage);
+}
+
+static inline
+struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer)
+{
+	return atomic_inc_not_zero(&peer->usage) ? peer : NULL;
+}
+
+extern void __rxrpc_put_peer(struct rxrpc_peer *peer);
+static inline void rxrpc_put_peer(struct rxrpc_peer *peer)
+{
+	if (atomic_dec_and_test(&peer->usage))
+		__rxrpc_put_peer(peer);
+}
+
+/*
+ * proc.c
+ */
+extern const char *const rxrpc_call_states[];
+extern const struct file_operations rxrpc_call_seq_fops;
+extern const struct file_operations rxrpc_connection_seq_fops;
+
+/*
+ * recvmsg.c
+ */
+void rxrpc_remove_user_ID(struct rxrpc_sock *, struct rxrpc_call *);
+int rxrpc_recvmsg(struct socket *, struct msghdr *, size_t, int);
+
+/*
  * rxkad.c
  */
 #ifdef CONFIG_RXKAD
@@ -659,6 +680,19 @@
 #endif
 
 /*
+ * security.c
+ */
+int __init rxrpc_init_security(void);
+void rxrpc_exit_security(void);
+int rxrpc_init_client_conn_security(struct rxrpc_connection *);
+int rxrpc_init_server_conn_security(struct rxrpc_connection *);
+
+/*
+ * skbuff.c
+ */
+void rxrpc_packet_destructor(struct sk_buff *);
+
+/*
  * sysctl.c
  */
 #ifdef CONFIG_SYSCTL
@@ -670,6 +704,24 @@
 #endif
 
 /*
+ * transport.c
+ */
+extern unsigned int rxrpc_transport_expiry;
+
+struct rxrpc_transport *rxrpc_get_transport(struct rxrpc_local *,
+					    struct rxrpc_peer *, gfp_t);
+void rxrpc_put_transport(struct rxrpc_transport *);
+void __exit rxrpc_destroy_all_transports(void);
+struct rxrpc_transport *rxrpc_find_transport(struct rxrpc_local *,
+					     struct rxrpc_peer *);
+
+/*
+ * utils.c
+ */
+void rxrpc_get_addr_from_skb(struct rxrpc_local *, const struct sk_buff *,
+			     struct sockaddr_rxrpc *);
+
+/*
  * debug tracing
  */
 extern unsigned int rxrpc_debug;
@@ -838,15 +890,6 @@
 		rxrpc_free_skb(skb);
 }
 
-static inline void __rxrpc_get_local(struct rxrpc_local *local, const char *f)
-{
-	CHECK_SLAB_OKAY(&local->usage);
-	if (atomic_inc_return(&local->usage) == 1)
-		printk("resurrected (%s)\n", f);
-}
-
-#define rxrpc_get_local(LOCAL) __rxrpc_get_local((LOCAL), __func__)
-
 #define rxrpc_get_call(CALL)				\
 do {							\
 	CHECK_SLAB_OKAY(&(CALL)->usage);		\
diff --git a/net/rxrpc/ar-local.c b/net/rxrpc/ar-local.c
deleted file mode 100644
index 701c42b..0000000
--- a/net/rxrpc/ar-local.c
+++ /dev/null
@@ -1,417 +0,0 @@
-/* AF_RXRPC local endpoint management
- *
- * Copyright (C) 2007 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 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) KBUILD_MODNAME ": " fmt
-
-#include <linux/module.h>
-#include <linux/net.h>
-#include <linux/skbuff.h>
-#include <linux/slab.h>
-#include <linux/udp.h>
-#include <linux/ip.h>
-#include <net/sock.h>
-#include <net/af_rxrpc.h>
-#include <generated/utsrelease.h>
-#include "ar-internal.h"
-
-static const char rxrpc_version_string[65] = "linux-" UTS_RELEASE " AF_RXRPC";
-
-static LIST_HEAD(rxrpc_locals);
-DEFINE_RWLOCK(rxrpc_local_lock);
-static DECLARE_RWSEM(rxrpc_local_sem);
-static DECLARE_WAIT_QUEUE_HEAD(rxrpc_local_wq);
-
-static void rxrpc_destroy_local(struct work_struct *work);
-static void rxrpc_process_local_events(struct work_struct *work);
-
-/*
- * allocate a new local
- */
-static
-struct rxrpc_local *rxrpc_alloc_local(struct sockaddr_rxrpc *srx)
-{
-	struct rxrpc_local *local;
-
-	local = kzalloc(sizeof(struct rxrpc_local), GFP_KERNEL);
-	if (local) {
-		INIT_WORK(&local->destroyer, &rxrpc_destroy_local);
-		INIT_WORK(&local->acceptor, &rxrpc_accept_incoming_calls);
-		INIT_WORK(&local->rejecter, &rxrpc_reject_packets);
-		INIT_WORK(&local->event_processor, &rxrpc_process_local_events);
-		INIT_LIST_HEAD(&local->services);
-		INIT_LIST_HEAD(&local->link);
-		init_rwsem(&local->defrag_sem);
-		skb_queue_head_init(&local->accept_queue);
-		skb_queue_head_init(&local->reject_queue);
-		skb_queue_head_init(&local->event_queue);
-		spin_lock_init(&local->lock);
-		rwlock_init(&local->services_lock);
-		atomic_set(&local->usage, 1);
-		local->debug_id = atomic_inc_return(&rxrpc_debug_id);
-		memcpy(&local->srx, srx, sizeof(*srx));
-	}
-
-	_leave(" = %p", local);
-	return local;
-}
-
-/*
- * create the local socket
- * - must be called with rxrpc_local_sem writelocked
- */
-static int rxrpc_create_local(struct rxrpc_local *local)
-{
-	struct sock *sock;
-	int ret, opt;
-
-	_enter("%p{%d}", local, local->srx.transport_type);
-
-	/* create a socket to represent the local endpoint */
-	ret = sock_create_kern(&init_net, PF_INET, local->srx.transport_type,
-			       IPPROTO_UDP, &local->socket);
-	if (ret < 0) {
-		_leave(" = %d [socket]", ret);
-		return ret;
-	}
-
-	/* if a local address was supplied then bind it */
-	if (local->srx.transport_len > sizeof(sa_family_t)) {
-		_debug("bind");
-		ret = kernel_bind(local->socket,
-				  (struct sockaddr *) &local->srx.transport,
-				  local->srx.transport_len);
-		if (ret < 0) {
-			_debug("bind failed");
-			goto error;
-		}
-	}
-
-	/* we want to receive ICMP errors */
-	opt = 1;
-	ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR,
-				(char *) &opt, sizeof(opt));
-	if (ret < 0) {
-		_debug("setsockopt failed");
-		goto error;
-	}
-
-	/* we want to set the don't fragment bit */
-	opt = IP_PMTUDISC_DO;
-	ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER,
-				(char *) &opt, sizeof(opt));
-	if (ret < 0) {
-		_debug("setsockopt failed");
-		goto error;
-	}
-
-	write_lock_bh(&rxrpc_local_lock);
-	list_add(&local->link, &rxrpc_locals);
-	write_unlock_bh(&rxrpc_local_lock);
-
-	/* set the socket up */
-	sock = local->socket->sk;
-	sock->sk_user_data	= local;
-	sock->sk_data_ready	= rxrpc_data_ready;
-	sock->sk_error_report	= rxrpc_UDP_error_report;
-	_leave(" = 0");
-	return 0;
-
-error:
-	kernel_sock_shutdown(local->socket, SHUT_RDWR);
-	local->socket->sk->sk_user_data = NULL;
-	sock_release(local->socket);
-	local->socket = NULL;
-
-	_leave(" = %d", ret);
-	return ret;
-}
-
-/*
- * create a new local endpoint using the specified UDP address
- */
-struct rxrpc_local *rxrpc_lookup_local(struct sockaddr_rxrpc *srx)
-{
-	struct rxrpc_local *local;
-	int ret;
-
-	_enter("{%d,%u,%pI4+%hu}",
-	       srx->transport_type,
-	       srx->transport.family,
-	       &srx->transport.sin.sin_addr,
-	       ntohs(srx->transport.sin.sin_port));
-
-	down_write(&rxrpc_local_sem);
-
-	/* see if we have a suitable local local endpoint already */
-	read_lock_bh(&rxrpc_local_lock);
-
-	list_for_each_entry(local, &rxrpc_locals, link) {
-		_debug("CMP {%d,%u,%pI4+%hu}",
-		       local->srx.transport_type,
-		       local->srx.transport.family,
-		       &local->srx.transport.sin.sin_addr,
-		       ntohs(local->srx.transport.sin.sin_port));
-
-		if (local->srx.transport_type != srx->transport_type ||
-		    local->srx.transport.family != srx->transport.family)
-			continue;
-
-		switch (srx->transport.family) {
-		case AF_INET:
-			if (local->srx.transport.sin.sin_port !=
-			    srx->transport.sin.sin_port)
-				continue;
-			if (memcmp(&local->srx.transport.sin.sin_addr,
-				   &srx->transport.sin.sin_addr,
-				   sizeof(struct in_addr)) != 0)
-				continue;
-			goto found_local;
-
-		default:
-			BUG();
-		}
-	}
-
-	read_unlock_bh(&rxrpc_local_lock);
-
-	/* we didn't find one, so we need to create one */
-	local = rxrpc_alloc_local(srx);
-	if (!local) {
-		up_write(&rxrpc_local_sem);
-		return ERR_PTR(-ENOMEM);
-	}
-
-	ret = rxrpc_create_local(local);
-	if (ret < 0) {
-		up_write(&rxrpc_local_sem);
-		kfree(local);
-		_leave(" = %d", ret);
-		return ERR_PTR(ret);
-	}
-
-	up_write(&rxrpc_local_sem);
-
-	_net("LOCAL new %d {%d,%u,%pI4+%hu}",
-	     local->debug_id,
-	     local->srx.transport_type,
-	     local->srx.transport.family,
-	     &local->srx.transport.sin.sin_addr,
-	     ntohs(local->srx.transport.sin.sin_port));
-
-	_leave(" = %p [new]", local);
-	return local;
-
-found_local:
-	rxrpc_get_local(local);
-	read_unlock_bh(&rxrpc_local_lock);
-	up_write(&rxrpc_local_sem);
-
-	_net("LOCAL old %d {%d,%u,%pI4+%hu}",
-	     local->debug_id,
-	     local->srx.transport_type,
-	     local->srx.transport.family,
-	     &local->srx.transport.sin.sin_addr,
-	     ntohs(local->srx.transport.sin.sin_port));
-
-	_leave(" = %p [reuse]", local);
-	return local;
-}
-
-/*
- * release a local endpoint
- */
-void rxrpc_put_local(struct rxrpc_local *local)
-{
-	_enter("%p{u=%d}", local, atomic_read(&local->usage));
-
-	ASSERTCMP(atomic_read(&local->usage), >, 0);
-
-	/* to prevent a race, the decrement and the dequeue must be effectively
-	 * atomic */
-	write_lock_bh(&rxrpc_local_lock);
-	if (unlikely(atomic_dec_and_test(&local->usage))) {
-		_debug("destroy local");
-		rxrpc_queue_work(&local->destroyer);
-	}
-	write_unlock_bh(&rxrpc_local_lock);
-	_leave("");
-}
-
-/*
- * destroy a local endpoint
- */
-static void rxrpc_destroy_local(struct work_struct *work)
-{
-	struct rxrpc_local *local =
-		container_of(work, struct rxrpc_local, destroyer);
-
-	_enter("%p{%d}", local, atomic_read(&local->usage));
-
-	down_write(&rxrpc_local_sem);
-
-	write_lock_bh(&rxrpc_local_lock);
-	if (atomic_read(&local->usage) > 0) {
-		write_unlock_bh(&rxrpc_local_lock);
-		up_read(&rxrpc_local_sem);
-		_leave(" [resurrected]");
-		return;
-	}
-
-	list_del(&local->link);
-	local->socket->sk->sk_user_data = NULL;
-	write_unlock_bh(&rxrpc_local_lock);
-
-	downgrade_write(&rxrpc_local_sem);
-
-	ASSERT(list_empty(&local->services));
-	ASSERT(!work_pending(&local->acceptor));
-	ASSERT(!work_pending(&local->rejecter));
-	ASSERT(!work_pending(&local->event_processor));
-
-	/* finish cleaning up the local descriptor */
-	rxrpc_purge_queue(&local->accept_queue);
-	rxrpc_purge_queue(&local->reject_queue);
-	rxrpc_purge_queue(&local->event_queue);
-	kernel_sock_shutdown(local->socket, SHUT_RDWR);
-	sock_release(local->socket);
-
-	up_read(&rxrpc_local_sem);
-
-	_net("DESTROY LOCAL %d", local->debug_id);
-	kfree(local);
-
-	if (list_empty(&rxrpc_locals))
-		wake_up_all(&rxrpc_local_wq);
-
-	_leave("");
-}
-
-/*
- * preemptively destroy all local local endpoint rather than waiting for
- * them to be destroyed
- */
-void __exit rxrpc_destroy_all_locals(void)
-{
-	DECLARE_WAITQUEUE(myself,current);
-
-	_enter("");
-
-	/* we simply have to wait for them to go away */
-	if (!list_empty(&rxrpc_locals)) {
-		set_current_state(TASK_UNINTERRUPTIBLE);
-		add_wait_queue(&rxrpc_local_wq, &myself);
-
-		while (!list_empty(&rxrpc_locals)) {
-			schedule();
-			set_current_state(TASK_UNINTERRUPTIBLE);
-		}
-
-		remove_wait_queue(&rxrpc_local_wq, &myself);
-		set_current_state(TASK_RUNNING);
-	}
-
-	_leave("");
-}
-
-/*
- * Reply to a version request
- */
-static void rxrpc_send_version_request(struct rxrpc_local *local,
-				       struct rxrpc_host_header *hdr,
-				       struct sk_buff *skb)
-{
-	struct rxrpc_wire_header whdr;
-	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
-	struct sockaddr_in sin;
-	struct msghdr msg;
-	struct kvec iov[2];
-	size_t len;
-	int ret;
-
-	_enter("");
-
-	sin.sin_family = AF_INET;
-	sin.sin_port = udp_hdr(skb)->source;
-	sin.sin_addr.s_addr = ip_hdr(skb)->saddr;
-
-	msg.msg_name	= &sin;
-	msg.msg_namelen	= sizeof(sin);
-	msg.msg_control	= NULL;
-	msg.msg_controllen = 0;
-	msg.msg_flags	= 0;
-
-	whdr.epoch	= htonl(sp->hdr.epoch);
-	whdr.cid	= htonl(sp->hdr.cid);
-	whdr.callNumber	= htonl(sp->hdr.callNumber);
-	whdr.seq	= 0;
-	whdr.serial	= 0;
-	whdr.type	= RXRPC_PACKET_TYPE_VERSION;
-	whdr.flags	= RXRPC_LAST_PACKET | (~hdr->flags & RXRPC_CLIENT_INITIATED);
-	whdr.userStatus	= 0;
-	whdr.securityIndex = 0;
-	whdr._rsvd	= 0;
-	whdr.serviceId	= htons(sp->hdr.serviceId);
-
-	iov[0].iov_base	= &whdr;
-	iov[0].iov_len	= sizeof(whdr);
-	iov[1].iov_base	= (char *)rxrpc_version_string;
-	iov[1].iov_len	= sizeof(rxrpc_version_string);
-
-	len = iov[0].iov_len + iov[1].iov_len;
-
-	_proto("Tx VERSION (reply)");
-
-	ret = kernel_sendmsg(local->socket, &msg, iov, 2, len);
-	if (ret < 0)
-		_debug("sendmsg failed: %d", ret);
-
-	_leave("");
-}
-
-/*
- * Process event packets targetted at a local endpoint.
- */
-static void rxrpc_process_local_events(struct work_struct *work)
-{
-	struct rxrpc_local *local = container_of(work, struct rxrpc_local, event_processor);
-	struct sk_buff *skb;
-	char v;
-
-	_enter("");
-
-	atomic_inc(&local->usage);
-	
-	while ((skb = skb_dequeue(&local->event_queue))) {
-		struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
-
-		_debug("{%d},{%u}", local->debug_id, sp->hdr.type);
-
-		switch (sp->hdr.type) {
-		case RXRPC_PACKET_TYPE_VERSION:
-			if (skb_copy_bits(skb, 0, &v, 1) < 0)
-				return;
-			_proto("Rx VERSION { %02x }", v);
-			if (v == 0)
-				rxrpc_send_version_request(local, &sp->hdr, skb);
-			break;
-
-		default:
-			/* Just ignore anything we don't understand */
-			break;
-		}
-
-		rxrpc_put_local(local);
-		rxrpc_free_skb(skb);
-	}
-
-	rxrpc_put_local(local);
-	_leave("");
-}
diff --git a/net/rxrpc/ar-peer.c b/net/rxrpc/ar-peer.c
deleted file mode 100644
index 0b54cda..0000000
--- a/net/rxrpc/ar-peer.c
+++ /dev/null
@@ -1,305 +0,0 @@
-/* RxRPC remote transport endpoint management
- *
- * Copyright (C) 2007 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 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) KBUILD_MODNAME ": " fmt
-
-#include <linux/module.h>
-#include <linux/net.h>
-#include <linux/skbuff.h>
-#include <linux/udp.h>
-#include <linux/in.h>
-#include <linux/in6.h>
-#include <linux/icmp.h>
-#include <linux/slab.h>
-#include <net/sock.h>
-#include <net/af_rxrpc.h>
-#include <net/ip.h>
-#include <net/route.h>
-#include "ar-internal.h"
-
-static LIST_HEAD(rxrpc_peers);
-static DEFINE_RWLOCK(rxrpc_peer_lock);
-static DECLARE_WAIT_QUEUE_HEAD(rxrpc_peer_wq);
-
-static void rxrpc_destroy_peer(struct work_struct *work);
-
-/*
- * assess the MTU size for the network interface through which this peer is
- * reached
- */
-static void rxrpc_assess_MTU_size(struct rxrpc_peer *peer)
-{
-	struct rtable *rt;
-	struct flowi4 fl4;
-
-	peer->if_mtu = 1500;
-
-	rt = ip_route_output_ports(&init_net, &fl4, NULL,
-				   peer->srx.transport.sin.sin_addr.s_addr, 0,
-				   htons(7000), htons(7001),
-				   IPPROTO_UDP, 0, 0);
-	if (IS_ERR(rt)) {
-		_leave(" [route err %ld]", PTR_ERR(rt));
-		return;
-	}
-
-	peer->if_mtu = dst_mtu(&rt->dst);
-	dst_release(&rt->dst);
-
-	_leave(" [if_mtu %u]", peer->if_mtu);
-}
-
-/*
- * allocate a new peer
- */
-static struct rxrpc_peer *rxrpc_alloc_peer(struct sockaddr_rxrpc *srx,
-					   gfp_t gfp)
-{
-	struct rxrpc_peer *peer;
-
-	_enter("");
-
-	peer = kzalloc(sizeof(struct rxrpc_peer), gfp);
-	if (peer) {
-		INIT_WORK(&peer->destroyer, &rxrpc_destroy_peer);
-		INIT_LIST_HEAD(&peer->link);
-		INIT_LIST_HEAD(&peer->error_targets);
-		spin_lock_init(&peer->lock);
-		atomic_set(&peer->usage, 1);
-		peer->debug_id = atomic_inc_return(&rxrpc_debug_id);
-		memcpy(&peer->srx, srx, sizeof(*srx));
-
-		rxrpc_assess_MTU_size(peer);
-		peer->mtu = peer->if_mtu;
-
-		if (srx->transport.family == AF_INET) {
-			peer->hdrsize = sizeof(struct iphdr);
-			switch (srx->transport_type) {
-			case SOCK_DGRAM:
-				peer->hdrsize += sizeof(struct udphdr);
-				break;
-			default:
-				BUG();
-				break;
-			}
-		} else {
-			BUG();
-		}
-
-		peer->hdrsize += sizeof(struct rxrpc_wire_header);
-		peer->maxdata = peer->mtu - peer->hdrsize;
-	}
-
-	_leave(" = %p", peer);
-	return peer;
-}
-
-/*
- * obtain a remote transport endpoint for the specified address
- */
-struct rxrpc_peer *rxrpc_get_peer(struct sockaddr_rxrpc *srx, gfp_t gfp)
-{
-	struct rxrpc_peer *peer, *candidate;
-	const char *new = "old";
-	int usage;
-
-	_enter("{%d,%d,%pI4+%hu}",
-	       srx->transport_type,
-	       srx->transport_len,
-	       &srx->transport.sin.sin_addr,
-	       ntohs(srx->transport.sin.sin_port));
-
-	/* search the peer list first */
-	read_lock_bh(&rxrpc_peer_lock);
-	list_for_each_entry(peer, &rxrpc_peers, link) {
-		_debug("check PEER %d { u=%d t=%d l=%d }",
-		       peer->debug_id,
-		       atomic_read(&peer->usage),
-		       peer->srx.transport_type,
-		       peer->srx.transport_len);
-
-		if (atomic_read(&peer->usage) > 0 &&
-		    peer->srx.transport_type == srx->transport_type &&
-		    peer->srx.transport_len == srx->transport_len &&
-		    memcmp(&peer->srx.transport,
-			   &srx->transport,
-			   srx->transport_len) == 0)
-			goto found_extant_peer;
-	}
-	read_unlock_bh(&rxrpc_peer_lock);
-
-	/* not yet present - create a candidate for a new record and then
-	 * redo the search */
-	candidate = rxrpc_alloc_peer(srx, gfp);
-	if (!candidate) {
-		_leave(" = -ENOMEM");
-		return ERR_PTR(-ENOMEM);
-	}
-
-	write_lock_bh(&rxrpc_peer_lock);
-
-	list_for_each_entry(peer, &rxrpc_peers, link) {
-		if (atomic_read(&peer->usage) > 0 &&
-		    peer->srx.transport_type == srx->transport_type &&
-		    peer->srx.transport_len == srx->transport_len &&
-		    memcmp(&peer->srx.transport,
-			   &srx->transport,
-			   srx->transport_len) == 0)
-			goto found_extant_second;
-	}
-
-	/* we can now add the new candidate to the list */
-	peer = candidate;
-	candidate = NULL;
-	usage = atomic_read(&peer->usage);
-
-	list_add_tail(&peer->link, &rxrpc_peers);
-	write_unlock_bh(&rxrpc_peer_lock);
-	new = "new";
-
-success:
-	_net("PEER %s %d {%d,%u,%pI4+%hu}",
-	     new,
-	     peer->debug_id,
-	     peer->srx.transport_type,
-	     peer->srx.transport.family,
-	     &peer->srx.transport.sin.sin_addr,
-	     ntohs(peer->srx.transport.sin.sin_port));
-
-	_leave(" = %p {u=%d}", peer, usage);
-	return peer;
-
-	/* we found the peer in the list immediately */
-found_extant_peer:
-	usage = atomic_inc_return(&peer->usage);
-	read_unlock_bh(&rxrpc_peer_lock);
-	goto success;
-
-	/* we found the peer on the second time through the list */
-found_extant_second:
-	usage = atomic_inc_return(&peer->usage);
-	write_unlock_bh(&rxrpc_peer_lock);
-	kfree(candidate);
-	goto success;
-}
-
-/*
- * find the peer associated with a packet
- */
-struct rxrpc_peer *rxrpc_find_peer(struct rxrpc_local *local,
-				   __be32 addr, __be16 port)
-{
-	struct rxrpc_peer *peer;
-
-	_enter("");
-
-	/* search the peer list */
-	read_lock_bh(&rxrpc_peer_lock);
-
-	if (local->srx.transport.family == AF_INET &&
-	    local->srx.transport_type == SOCK_DGRAM
-	    ) {
-		list_for_each_entry(peer, &rxrpc_peers, link) {
-			if (atomic_read(&peer->usage) > 0 &&
-			    peer->srx.transport_type == SOCK_DGRAM &&
-			    peer->srx.transport.family == AF_INET &&
-			    peer->srx.transport.sin.sin_port == port &&
-			    peer->srx.transport.sin.sin_addr.s_addr == addr)
-				goto found_UDP_peer;
-		}
-
-		goto new_UDP_peer;
-	}
-
-	read_unlock_bh(&rxrpc_peer_lock);
-	_leave(" = -EAFNOSUPPORT");
-	return ERR_PTR(-EAFNOSUPPORT);
-
-found_UDP_peer:
-	_net("Rx UDP DGRAM from peer %d", peer->debug_id);
-	atomic_inc(&peer->usage);
-	read_unlock_bh(&rxrpc_peer_lock);
-	_leave(" = %p", peer);
-	return peer;
-
-new_UDP_peer:
-	_net("Rx UDP DGRAM from NEW peer");
-	read_unlock_bh(&rxrpc_peer_lock);
-	_leave(" = -EBUSY [new]");
-	return ERR_PTR(-EBUSY);
-}
-
-/*
- * release a remote transport endpoint
- */
-void rxrpc_put_peer(struct rxrpc_peer *peer)
-{
-	_enter("%p{u=%d}", peer, atomic_read(&peer->usage));
-
-	ASSERTCMP(atomic_read(&peer->usage), >, 0);
-
-	if (likely(!atomic_dec_and_test(&peer->usage))) {
-		_leave(" [in use]");
-		return;
-	}
-
-	rxrpc_queue_work(&peer->destroyer);
-	_leave("");
-}
-
-/*
- * destroy a remote transport endpoint
- */
-static void rxrpc_destroy_peer(struct work_struct *work)
-{
-	struct rxrpc_peer *peer =
-		container_of(work, struct rxrpc_peer, destroyer);
-
-	_enter("%p{%d}", peer, atomic_read(&peer->usage));
-
-	write_lock_bh(&rxrpc_peer_lock);
-	list_del(&peer->link);
-	write_unlock_bh(&rxrpc_peer_lock);
-
-	_net("DESTROY PEER %d", peer->debug_id);
-	kfree(peer);
-
-	if (list_empty(&rxrpc_peers))
-		wake_up_all(&rxrpc_peer_wq);
-	_leave("");
-}
-
-/*
- * preemptively destroy all the peer records from a transport endpoint rather
- * than waiting for them to time out
- */
-void __exit rxrpc_destroy_all_peers(void)
-{
-	DECLARE_WAITQUEUE(myself,current);
-
-	_enter("");
-
-	/* we simply have to wait for them to go away */
-	if (!list_empty(&rxrpc_peers)) {
-		set_current_state(TASK_UNINTERRUPTIBLE);
-		add_wait_queue(&rxrpc_peer_wq, &myself);
-
-		while (!list_empty(&rxrpc_peers)) {
-			schedule();
-			set_current_state(TASK_UNINTERRUPTIBLE);
-		}
-
-		remove_wait_queue(&rxrpc_peer_wq, &myself);
-		set_current_state(TASK_RUNNING);
-	}
-
-	_leave("");
-}
diff --git a/net/rxrpc/ar-accept.c b/net/rxrpc/call_accept.c
similarity index 95%
rename from net/rxrpc/ar-accept.c
rename to net/rxrpc/call_accept.c
index eea5f4a..50136c7 100644
--- a/net/rxrpc/ar-accept.c
+++ b/net/rxrpc/call_accept.c
@@ -95,7 +95,7 @@
 	rxrpc_new_skb(notification);
 	notification->mark = RXRPC_SKB_MARK_NEW_CALL;
 
-	peer = rxrpc_get_peer(srx, GFP_NOIO);
+	peer = rxrpc_lookup_peer(local, srx, GFP_NOIO);
 	if (IS_ERR(peer)) {
 		_debug("no peer");
 		ret = -EBUSY;
@@ -202,10 +202,8 @@
  * accept incoming calls that need peer, transport and/or connection setting up
  * - the packets we get are all incoming client DATA packets that have seq == 1
  */
-void rxrpc_accept_incoming_calls(struct work_struct *work)
+void rxrpc_accept_incoming_calls(struct rxrpc_local *local)
 {
-	struct rxrpc_local *local =
-		container_of(work, struct rxrpc_local, acceptor);
 	struct rxrpc_skb_priv *sp;
 	struct sockaddr_rxrpc srx;
 	struct rxrpc_sock *rx;
@@ -215,21 +213,8 @@
 
 	_enter("%d", local->debug_id);
 
-	read_lock_bh(&rxrpc_local_lock);
-	if (atomic_read(&local->usage) > 0)
-		rxrpc_get_local(local);
-	else
-		local = NULL;
-	read_unlock_bh(&rxrpc_local_lock);
-	if (!local) {
-		_leave(" [local dead]");
-		return;
-	}
-
-process_next_packet:
 	skb = skb_dequeue(&local->accept_queue);
 	if (!skb) {
-		rxrpc_put_local(local);
 		_leave("\n");
 		return;
 	}
@@ -292,7 +277,7 @@
 	case -ECONNRESET: /* old calls are ignored */
 	case -ECONNABORTED: /* aborted calls are reaborted or ignored */
 	case 0:
-		goto process_next_packet;
+		return;
 	case -ECONNREFUSED:
 		goto invalid_service;
 	case -EBUSY:
@@ -308,18 +293,18 @@
 busy:
 	rxrpc_busy(local, &srx, &whdr);
 	rxrpc_free_skb(skb);
-	goto process_next_packet;
+	return;
 
 invalid_service:
 	skb->priority = RX_INVALID_OPERATION;
 	rxrpc_reject_packet(local, skb);
-	goto process_next_packet;
+	return;
 
 	/* can't change connection security type mid-flow */
 security_mismatch:
 	skb->priority = RX_PROTOCOL_ERROR;
 	rxrpc_reject_packet(local, skb);
-	goto process_next_packet;
+	return;
 }
 
 /*
diff --git a/net/rxrpc/ar-ack.c b/net/rxrpc/call_event.c
similarity index 98%
rename from net/rxrpc/ar-ack.c
rename to net/rxrpc/call_event.c
index 1838178..e610b10 100644
--- a/net/rxrpc/ar-ack.c
+++ b/net/rxrpc/call_event.c
@@ -864,17 +864,24 @@
 	}
 
 	if (test_bit(RXRPC_CALL_EV_RCVD_ERROR, &call->events)) {
+		enum rxrpc_skb_mark mark;
 		int error;
 
 		clear_bit(RXRPC_CALL_EV_CONN_ABORT, &call->events);
 		clear_bit(RXRPC_CALL_EV_REJECT_BUSY, &call->events);
 		clear_bit(RXRPC_CALL_EV_ABORT, &call->events);
 
-		error = call->conn->trans->peer->net_error;
-		_debug("post net error %d", error);
+		error = call->error_report;
+		if (error < RXRPC_LOCAL_ERROR_OFFSET) {
+			mark = RXRPC_SKB_MARK_NET_ERROR;
+			_debug("post net error %d", error);
+		} else {
+			mark = RXRPC_SKB_MARK_LOCAL_ERROR;
+			error -= RXRPC_LOCAL_ERROR_OFFSET;
+			_debug("post net local error %d", error);
+		}
 
-		if (rxrpc_post_message(call, RXRPC_SKB_MARK_NET_ERROR,
-				       error, true) < 0)
+		if (rxrpc_post_message(call, mark, error, true) < 0)
 			goto no_mem;
 		clear_bit(RXRPC_CALL_EV_RCVD_ERROR, &call->events);
 		goto kill_ACKs;
diff --git a/net/rxrpc/ar-call.c b/net/rxrpc/call_object.c
similarity index 91%
rename from net/rxrpc/ar-call.c
rename to net/rxrpc/call_object.c
index 1fbaae1..8b4d47b 100644
--- a/net/rxrpc/ar-call.c
+++ b/net/rxrpc/call_object.c
@@ -196,6 +196,43 @@
 }
 
 /*
+ * find an extant server call
+ * - called in process context with IRQs enabled
+ */
+struct rxrpc_call *rxrpc_find_call_by_user_ID(struct rxrpc_sock *rx,
+					      unsigned long user_call_ID)
+{
+	struct rxrpc_call *call;
+	struct rb_node *p;
+
+	_enter("%p,%lx", rx, user_call_ID);
+
+	read_lock(&rx->call_lock);
+
+	p = rx->calls.rb_node;
+	while (p) {
+		call = rb_entry(p, struct rxrpc_call, sock_node);
+
+		if (user_call_ID < call->user_call_ID)
+			p = p->rb_left;
+		else if (user_call_ID > call->user_call_ID)
+			p = p->rb_right;
+		else
+			goto found_extant_call;
+	}
+
+	read_unlock(&rx->call_lock);
+	_leave(" = NULL");
+	return NULL;
+
+found_extant_call:
+	rxrpc_get_call(call);
+	read_unlock(&rx->call_lock);
+	_leave(" = %p [%d]", call, atomic_read(&call->usage));
+	return call;
+}
+
+/*
  * allocate a new call
  */
 static struct rxrpc_call *rxrpc_alloc_call(gfp_t gfp)
@@ -297,7 +334,7 @@
 	rxrpc_call_hash_add(call);
 
 	spin_lock(&call->conn->trans->peer->lock);
-	list_add(&call->error_link, &call->conn->trans->peer->error_targets);
+	hlist_add_head(&call->error_link, &call->conn->trans->peer->error_targets);
 	spin_unlock(&call->conn->trans->peer->lock);
 
 	call->lifetimer.expires = jiffies + rxrpc_max_call_lifetime;
@@ -311,51 +348,27 @@
  * set up a call for the given data
  * - called in process context with IRQs enabled
  */
-struct rxrpc_call *rxrpc_get_client_call(struct rxrpc_sock *rx,
+struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
 					 struct rxrpc_transport *trans,
 					 struct rxrpc_conn_bundle *bundle,
 					 unsigned long user_call_ID,
-					 int create,
 					 gfp_t gfp)
 {
-	struct rxrpc_call *call, *candidate;
-	struct rb_node *p, *parent, **pp;
+	struct rxrpc_call *call, *xcall;
+	struct rb_node *parent, **pp;
 
-	_enter("%p,%d,%d,%lx,%d",
-	       rx, trans ? trans->debug_id : -1, bundle ? bundle->debug_id : -1,
-	       user_call_ID, create);
+	_enter("%p,%d,%d,%lx",
+	       rx, trans->debug_id, bundle ? bundle->debug_id : -1,
+	       user_call_ID);
 
-	/* search the extant calls first for one that matches the specified
-	 * user ID */
-	read_lock(&rx->call_lock);
-
-	p = rx->calls.rb_node;
-	while (p) {
-		call = rb_entry(p, struct rxrpc_call, sock_node);
-
-		if (user_call_ID < call->user_call_ID)
-			p = p->rb_left;
-		else if (user_call_ID > call->user_call_ID)
-			p = p->rb_right;
-		else
-			goto found_extant_call;
+	call = rxrpc_alloc_client_call(rx, trans, bundle, gfp);
+	if (IS_ERR(call)) {
+		_leave(" = %ld", PTR_ERR(call));
+		return call;
 	}
 
-	read_unlock(&rx->call_lock);
-
-	if (!create || !trans)
-		return ERR_PTR(-EBADSLT);
-
-	/* not yet present - create a candidate for a new record and then
-	 * redo the search */
-	candidate = rxrpc_alloc_client_call(rx, trans, bundle, gfp);
-	if (IS_ERR(candidate)) {
-		_leave(" = %ld", PTR_ERR(candidate));
-		return candidate;
-	}
-
-	candidate->user_call_ID = user_call_ID;
-	__set_bit(RXRPC_CALL_HAS_USERID, &candidate->flags);
+	call->user_call_ID = user_call_ID;
+	__set_bit(RXRPC_CALL_HAS_USERID, &call->flags);
 
 	write_lock(&rx->call_lock);
 
@@ -363,19 +376,16 @@
 	parent = NULL;
 	while (*pp) {
 		parent = *pp;
-		call = rb_entry(parent, struct rxrpc_call, sock_node);
+		xcall = rb_entry(parent, struct rxrpc_call, sock_node);
 
-		if (user_call_ID < call->user_call_ID)
+		if (user_call_ID < xcall->user_call_ID)
 			pp = &(*pp)->rb_left;
-		else if (user_call_ID > call->user_call_ID)
+		else if (user_call_ID > xcall->user_call_ID)
 			pp = &(*pp)->rb_right;
 		else
-			goto found_extant_second;
+			goto found_user_ID_now_present;
 	}
 
-	/* second search also failed; add the new call */
-	call = candidate;
-	candidate = NULL;
 	rxrpc_get_call(call);
 
 	rb_link_node(&call->sock_node, parent, pp);
@@ -391,20 +401,16 @@
 	_leave(" = %p [new]", call);
 	return call;
 
-	/* we found the call in the list immediately */
-found_extant_call:
-	rxrpc_get_call(call);
-	read_unlock(&rx->call_lock);
-	_leave(" = %p [extant %d]", call, atomic_read(&call->usage));
-	return call;
-
-	/* we found the call on the second time through the list */
-found_extant_second:
-	rxrpc_get_call(call);
+	/* We unexpectedly found the user ID in the list after taking
+	 * the call_lock.  This shouldn't happen unless the user races
+	 * with itself and tries to add the same user ID twice at the
+	 * same time in different threads.
+	 */
+found_user_ID_now_present:
 	write_unlock(&rx->call_lock);
-	rxrpc_put_call(candidate);
-	_leave(" = %p [second %d]", call, atomic_read(&call->usage));
-	return call;
+	rxrpc_put_call(call);
+	_leave(" = -EEXIST [%p]", call);
+	return ERR_PTR(-EEXIST);
 }
 
 /*
@@ -510,7 +516,7 @@
 	write_unlock_bh(&conn->lock);
 
 	spin_lock(&conn->trans->peer->lock);
-	list_add(&call->error_link, &conn->trans->peer->error_targets);
+	hlist_add_head(&call->error_link, &conn->trans->peer->error_targets);
 	spin_unlock(&conn->trans->peer->lock);
 
 	write_lock_bh(&rxrpc_call_lock);
@@ -566,46 +572,6 @@
 }
 
 /*
- * find an extant server call
- * - called in process context with IRQs enabled
- */
-struct rxrpc_call *rxrpc_find_server_call(struct rxrpc_sock *rx,
-					  unsigned long user_call_ID)
-{
-	struct rxrpc_call *call;
-	struct rb_node *p;
-
-	_enter("%p,%lx", rx, user_call_ID);
-
-	/* search the extant calls for one that matches the specified user
-	 * ID */
-	read_lock(&rx->call_lock);
-
-	p = rx->calls.rb_node;
-	while (p) {
-		call = rb_entry(p, struct rxrpc_call, sock_node);
-
-		if (user_call_ID < call->user_call_ID)
-			p = p->rb_left;
-		else if (user_call_ID > call->user_call_ID)
-			p = p->rb_right;
-		else
-			goto found_extant_call;
-	}
-
-	read_unlock(&rx->call_lock);
-	_leave(" = NULL");
-	return NULL;
-
-	/* we found the call in the list immediately */
-found_extant_call:
-	rxrpc_get_call(call);
-	read_unlock(&rx->call_lock);
-	_leave(" = %p [%d]", call, atomic_read(&call->usage));
-	return call;
-}
-
-/*
  * detach a call from a socket and set up for release
  */
 void rxrpc_release_call(struct rxrpc_call *call)
@@ -846,7 +812,7 @@
 
 	if (call->conn) {
 		spin_lock(&call->conn->trans->peer->lock);
-		list_del(&call->error_link);
+		hlist_del_init(&call->error_link);
 		spin_unlock(&call->conn->trans->peer->lock);
 
 		write_lock_bh(&call->conn->lock);
diff --git a/net/rxrpc/ar-connevent.c b/net/rxrpc/conn_event.c
similarity index 96%
rename from net/rxrpc/ar-connevent.c
rename to net/rxrpc/conn_event.c
index 8bdd692..00c92b6 100644
--- a/net/rxrpc/ar-connevent.c
+++ b/net/rxrpc/conn_event.c
@@ -314,19 +314,14 @@
 {
 	CHECK_SLAB_OKAY(&local->usage);
 
-	if (!atomic_inc_not_zero(&local->usage)) {
-		printk("resurrected on reject\n");
-		BUG();
-	}
-
 	skb_queue_tail(&local->reject_queue, skb);
-	rxrpc_queue_work(&local->rejecter);
+	rxrpc_queue_work(&local->processor);
 }
 
 /*
  * reject packets through the local endpoint
  */
-void rxrpc_reject_packets(struct work_struct *work)
+void rxrpc_reject_packets(struct rxrpc_local *local)
 {
 	union {
 		struct sockaddr sa;
@@ -334,16 +329,12 @@
 	} sa;
 	struct rxrpc_skb_priv *sp;
 	struct rxrpc_wire_header whdr;
-	struct rxrpc_local *local;
 	struct sk_buff *skb;
 	struct msghdr msg;
 	struct kvec iov[2];
 	size_t size;
 	__be32 code;
 
-	local = container_of(work, struct rxrpc_local, rejecter);
-	rxrpc_get_local(local);
-
 	_enter("%d", local->debug_id);
 
 	iov[0].iov_base = &whdr;
@@ -395,9 +386,7 @@
 		}
 
 		rxrpc_free_skb(skb);
-		rxrpc_put_local(local);
 	}
 
-	rxrpc_put_local(local);
 	_leave("");
 }
diff --git a/net/rxrpc/ar-connection.c b/net/rxrpc/conn_object.c
similarity index 97%
rename from net/rxrpc/ar-connection.c
rename to net/rxrpc/conn_object.c
index d67b1f1..8ecde4b 100644
--- a/net/rxrpc/ar-connection.c
+++ b/net/rxrpc/conn_object.c
@@ -80,11 +80,6 @@
 	_enter("%p{%x},%x,%hx,",
 	       rx, key_serial(key), trans->debug_id, service_id);
 
-	if (rx->trans == trans && rx->bundle) {
-		atomic_inc(&rx->bundle->usage);
-		return rx->bundle;
-	}
-
 	/* search the extant bundles first for one that matches the specified
 	 * user ID */
 	spin_lock(&trans->client_lock);
@@ -138,10 +133,6 @@
 	rb_insert_color(&bundle->node, &trans->bundles);
 	spin_unlock(&trans->client_lock);
 	_net("BUNDLE new on trans %d", trans->debug_id);
-	if (!rx->bundle && rx->sk.sk_state == RXRPC_CLIENT_CONNECTED) {
-		atomic_inc(&bundle->usage);
-		rx->bundle = bundle;
-	}
 	_leave(" = %p [new]", bundle);
 	return bundle;
 
@@ -150,10 +141,6 @@
 	atomic_inc(&bundle->usage);
 	spin_unlock(&trans->client_lock);
 	_net("BUNDLE old on trans %d", trans->debug_id);
-	if (!rx->bundle && rx->sk.sk_state == RXRPC_CLIENT_CONNECTED) {
-		atomic_inc(&bundle->usage);
-		rx->bundle = bundle;
-	}
 	_leave(" = %p [extant %d]", bundle, atomic_read(&bundle->usage));
 	return bundle;
 
@@ -163,10 +150,6 @@
 	spin_unlock(&trans->client_lock);
 	kfree(candidate);
 	_net("BUNDLE old2 on trans %d", trans->debug_id);
-	if (!rx->bundle && rx->sk.sk_state == RXRPC_CLIENT_CONNECTED) {
-		atomic_inc(&bundle->usage);
-		rx->bundle = bundle;
-	}
 	_leave(" = %p [second %d]", bundle, atomic_read(&bundle->usage));
 	return bundle;
 }
diff --git a/net/rxrpc/ar-input.c b/net/rxrpc/input.c
similarity index 96%
rename from net/rxrpc/ar-input.c
rename to net/rxrpc/input.c
index d7c2a0b..47fb167 100644
--- a/net/rxrpc/ar-input.c
+++ b/net/rxrpc/input.c
@@ -594,9 +594,8 @@
 {
 	_enter("%p,%p", local, skb);
 
-	atomic_inc(&local->usage);
 	skb_queue_tail(&local->event_queue, skb);
-	rxrpc_queue_work(&local->event_processor);
+	rxrpc_queue_work(&local->processor);
 }
 
 /*
@@ -635,14 +634,16 @@
 	struct rxrpc_peer *peer;
 	struct rxrpc_transport *trans;
 	struct rxrpc_connection *conn;
+	struct sockaddr_rxrpc srx;
 
-	peer = rxrpc_find_peer(local, ip_hdr(skb)->saddr,
-				udp_hdr(skb)->source);
+	rxrpc_get_addr_from_skb(local, skb, &srx);
+	rcu_read_lock();
+	peer = rxrpc_lookup_peer_rcu(local, &srx);
 	if (IS_ERR(peer))
-		goto cant_find_conn;
+		goto cant_find_peer;
 
 	trans = rxrpc_find_transport(local, peer);
-	rxrpc_put_peer(peer);
+	rcu_read_unlock();
 	if (!trans)
 		goto cant_find_conn;
 
@@ -652,6 +653,9 @@
 		goto cant_find_conn;
 
 	return conn;
+
+cant_find_peer:
+	rcu_read_unlock();
 cant_find_conn:
 	return NULL;
 }
@@ -659,11 +663,15 @@
 /*
  * handle data received on the local endpoint
  * - may be called in interrupt context
+ *
+ * The socket is locked by the caller and this prevents the socket from being
+ * shut down and the local endpoint from going away, thus sk_user_data will not
+ * be cleared until this function returns.
  */
 void rxrpc_data_ready(struct sock *sk)
 {
 	struct rxrpc_skb_priv *sp;
-	struct rxrpc_local *local;
+	struct rxrpc_local *local = sk->sk_user_data;
 	struct sk_buff *skb;
 	int ret;
 
@@ -671,21 +679,8 @@
 
 	ASSERT(!irqs_disabled());
 
-	read_lock_bh(&rxrpc_local_lock);
-	local = sk->sk_user_data;
-	if (local && atomic_read(&local->usage) > 0)
-		rxrpc_get_local(local);
-	else
-		local = NULL;
-	read_unlock_bh(&rxrpc_local_lock);
-	if (!local) {
-		_leave(" [local dead]");
-		return;
-	}
-
 	skb = skb_recv_datagram(sk, 0, 1, &ret);
 	if (!skb) {
-		rxrpc_put_local(local);
 		if (ret == -EAGAIN)
 			return;
 		_debug("UDP socket error %d", ret);
@@ -699,7 +694,6 @@
 	/* we'll probably need to checksum it (didn't call sock_recvmsg) */
 	if (skb_checksum_complete(skb)) {
 		rxrpc_free_skb(skb);
-		rxrpc_put_local(local);
 		__UDP_INC_STATS(&init_net, UDP_MIB_INERRORS, 0);
 		_leave(" [CSUM failed]");
 		return;
@@ -734,7 +728,7 @@
 		rxrpc_post_packet_to_local(local, skb);
 		goto out;
 	}
-	
+
 	if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA &&
 	    (sp->hdr.callNumber == 0 || sp->hdr.seq == 0))
 		goto bad_message;
@@ -764,7 +758,6 @@
 	}
 
 out:
-	rxrpc_put_local(local);
 	return;
 
 cant_route_call:
@@ -774,8 +767,7 @@
 		if (sp->hdr.seq == 1) {
 			_debug("first packet");
 			skb_queue_tail(&local->accept_queue, skb);
-			rxrpc_queue_work(&local->acceptor);
-			rxrpc_put_local(local);
+			rxrpc_queue_work(&local->processor);
 			_leave(" [incoming]");
 			return;
 		}
@@ -788,13 +780,11 @@
 		_debug("reject type %d",sp->hdr.type);
 		rxrpc_reject_packet(local, skb);
 	}
-	rxrpc_put_local(local);
 	_leave(" [no call]");
 	return;
 
 bad_message:
 	skb->priority = RX_PROTOCOL_ERROR;
 	rxrpc_reject_packet(local, skb);
-	rxrpc_put_local(local);
 	_leave(" [badmsg]");
 }
diff --git a/net/rxrpc/ar-key.c b/net/rxrpc/key.c
similarity index 100%
rename from net/rxrpc/ar-key.c
rename to net/rxrpc/key.c
diff --git a/net/rxrpc/local_event.c b/net/rxrpc/local_event.c
new file mode 100644
index 0000000..31a3f86
--- /dev/null
+++ b/net/rxrpc/local_event.c
@@ -0,0 +1,116 @@
+/* AF_RXRPC local endpoint management
+ *
+ * Copyright (C) 2007 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 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) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/udp.h>
+#include <linux/ip.h>
+#include <net/sock.h>
+#include <net/af_rxrpc.h>
+#include <generated/utsrelease.h>
+#include "ar-internal.h"
+
+static const char rxrpc_version_string[65] = "linux-" UTS_RELEASE " AF_RXRPC";
+
+/*
+ * Reply to a version request
+ */
+static void rxrpc_send_version_request(struct rxrpc_local *local,
+				       struct rxrpc_host_header *hdr,
+				       struct sk_buff *skb)
+{
+	struct rxrpc_wire_header whdr;
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	struct sockaddr_in sin;
+	struct msghdr msg;
+	struct kvec iov[2];
+	size_t len;
+	int ret;
+
+	_enter("");
+
+	sin.sin_family = AF_INET;
+	sin.sin_port = udp_hdr(skb)->source;
+	sin.sin_addr.s_addr = ip_hdr(skb)->saddr;
+
+	msg.msg_name	= &sin;
+	msg.msg_namelen	= sizeof(sin);
+	msg.msg_control	= NULL;
+	msg.msg_controllen = 0;
+	msg.msg_flags	= 0;
+
+	whdr.epoch	= htonl(sp->hdr.epoch);
+	whdr.cid	= htonl(sp->hdr.cid);
+	whdr.callNumber	= htonl(sp->hdr.callNumber);
+	whdr.seq	= 0;
+	whdr.serial	= 0;
+	whdr.type	= RXRPC_PACKET_TYPE_VERSION;
+	whdr.flags	= RXRPC_LAST_PACKET | (~hdr->flags & RXRPC_CLIENT_INITIATED);
+	whdr.userStatus	= 0;
+	whdr.securityIndex = 0;
+	whdr._rsvd	= 0;
+	whdr.serviceId	= htons(sp->hdr.serviceId);
+
+	iov[0].iov_base	= &whdr;
+	iov[0].iov_len	= sizeof(whdr);
+	iov[1].iov_base	= (char *)rxrpc_version_string;
+	iov[1].iov_len	= sizeof(rxrpc_version_string);
+
+	len = iov[0].iov_len + iov[1].iov_len;
+
+	_proto("Tx VERSION (reply)");
+
+	ret = kernel_sendmsg(local->socket, &msg, iov, 2, len);
+	if (ret < 0)
+		_debug("sendmsg failed: %d", ret);
+
+	_leave("");
+}
+
+/*
+ * Process event packets targetted at a local endpoint.
+ */
+void rxrpc_process_local_events(struct rxrpc_local *local)
+{
+	struct sk_buff *skb;
+	char v;
+
+	_enter("");
+
+	skb = skb_dequeue(&local->event_queue);
+	if (skb) {
+		struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+
+		_debug("{%d},{%u}", local->debug_id, sp->hdr.type);
+
+		switch (sp->hdr.type) {
+		case RXRPC_PACKET_TYPE_VERSION:
+			if (skb_copy_bits(skb, 0, &v, 1) < 0)
+				return;
+			_proto("Rx VERSION { %02x }", v);
+			if (v == 0)
+				rxrpc_send_version_request(local, &sp->hdr, skb);
+			break;
+
+		default:
+			/* Just ignore anything we don't understand */
+			break;
+		}
+
+		rxrpc_free_skb(skb);
+	}
+
+	_leave("");
+}
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
new file mode 100644
index 0000000..009b321
--- /dev/null
+++ b/net/rxrpc/local_object.c
@@ -0,0 +1,385 @@
+/* Local endpoint object management
+ *
+ * Copyright (C) 2016 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.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/udp.h>
+#include <linux/ip.h>
+#include <linux/hashtable.h>
+#include <net/sock.h>
+#include <net/af_rxrpc.h>
+#include "ar-internal.h"
+
+static void rxrpc_local_processor(struct work_struct *);
+static void rxrpc_local_rcu(struct rcu_head *);
+
+static DEFINE_MUTEX(rxrpc_local_mutex);
+static LIST_HEAD(rxrpc_local_endpoints);
+
+/*
+ * Compare a local to an address.  Return -ve, 0 or +ve to indicate less than,
+ * same or greater than.
+ *
+ * We explicitly don't compare the RxRPC service ID as we want to reject
+ * conflicting uses by differing services.  Further, we don't want to share
+ * addresses with different options (IPv6), so we don't compare those bits
+ * either.
+ */
+static long rxrpc_local_cmp_key(const struct rxrpc_local *local,
+				const struct sockaddr_rxrpc *srx)
+{
+	long diff;
+
+	diff = ((local->srx.transport_type - srx->transport_type) ?:
+		(local->srx.transport_len - srx->transport_len) ?:
+		(local->srx.transport.family - srx->transport.family));
+	if (diff != 0)
+		return diff;
+
+	switch (srx->transport.family) {
+	case AF_INET:
+		/* If the choice of UDP port is left up to the transport, then
+		 * the endpoint record doesn't match.
+		 */
+		return ((u16 __force)local->srx.transport.sin.sin_port -
+			(u16 __force)srx->transport.sin.sin_port) ?:
+			memcmp(&local->srx.transport.sin.sin_addr,
+			       &srx->transport.sin.sin_addr,
+			       sizeof(struct in_addr));
+	default:
+		BUG();
+	}
+}
+
+/*
+ * Allocate a new local endpoint.
+ */
+static struct rxrpc_local *rxrpc_alloc_local(const struct sockaddr_rxrpc *srx)
+{
+	struct rxrpc_local *local;
+
+	local = kzalloc(sizeof(struct rxrpc_local), GFP_KERNEL);
+	if (local) {
+		atomic_set(&local->usage, 1);
+		INIT_LIST_HEAD(&local->link);
+		INIT_WORK(&local->processor, rxrpc_local_processor);
+		INIT_LIST_HEAD(&local->services);
+		init_rwsem(&local->defrag_sem);
+		skb_queue_head_init(&local->accept_queue);
+		skb_queue_head_init(&local->reject_queue);
+		skb_queue_head_init(&local->event_queue);
+		mutex_init(&local->conn_lock);
+		spin_lock_init(&local->lock);
+		rwlock_init(&local->services_lock);
+		local->debug_id = atomic_inc_return(&rxrpc_debug_id);
+		memcpy(&local->srx, srx, sizeof(*srx));
+	}
+
+	_leave(" = %p", local);
+	return local;
+}
+
+/*
+ * create the local socket
+ * - must be called with rxrpc_local_mutex locked
+ */
+static int rxrpc_open_socket(struct rxrpc_local *local)
+{
+	struct sock *sock;
+	int ret, opt;
+
+	_enter("%p{%d}", local, local->srx.transport_type);
+
+	/* create a socket to represent the local endpoint */
+	ret = sock_create_kern(&init_net, PF_INET, local->srx.transport_type,
+			       IPPROTO_UDP, &local->socket);
+	if (ret < 0) {
+		_leave(" = %d [socket]", ret);
+		return ret;
+	}
+
+	/* if a local address was supplied then bind it */
+	if (local->srx.transport_len > sizeof(sa_family_t)) {
+		_debug("bind");
+		ret = kernel_bind(local->socket,
+				  (struct sockaddr *)&local->srx.transport,
+				  local->srx.transport_len);
+		if (ret < 0) {
+			_debug("bind failed %d", ret);
+			goto error;
+		}
+	}
+
+	/* we want to receive ICMP errors */
+	opt = 1;
+	ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR,
+				(char *) &opt, sizeof(opt));
+	if (ret < 0) {
+		_debug("setsockopt failed");
+		goto error;
+	}
+
+	/* we want to set the don't fragment bit */
+	opt = IP_PMTUDISC_DO;
+	ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER,
+				(char *) &opt, sizeof(opt));
+	if (ret < 0) {
+		_debug("setsockopt failed");
+		goto error;
+	}
+
+	/* set the socket up */
+	sock = local->socket->sk;
+	sock->sk_user_data	= local;
+	sock->sk_data_ready	= rxrpc_data_ready;
+	sock->sk_error_report	= rxrpc_error_report;
+	_leave(" = 0");
+	return 0;
+
+error:
+	kernel_sock_shutdown(local->socket, SHUT_RDWR);
+	local->socket->sk->sk_user_data = NULL;
+	sock_release(local->socket);
+	local->socket = NULL;
+
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * Look up or create a new local endpoint using the specified local address.
+ */
+struct rxrpc_local *rxrpc_lookup_local(const struct sockaddr_rxrpc *srx)
+{
+	struct rxrpc_local *local;
+	struct list_head *cursor;
+	const char *age;
+	long diff;
+	int ret;
+
+	if (srx->transport.family == AF_INET) {
+		_enter("{%d,%u,%pI4+%hu}",
+		       srx->transport_type,
+		       srx->transport.family,
+		       &srx->transport.sin.sin_addr,
+		       ntohs(srx->transport.sin.sin_port));
+	} else {
+		_enter("{%d,%u}",
+		       srx->transport_type,
+		       srx->transport.family);
+		return ERR_PTR(-EAFNOSUPPORT);
+	}
+
+	mutex_lock(&rxrpc_local_mutex);
+
+	for (cursor = rxrpc_local_endpoints.next;
+	     cursor != &rxrpc_local_endpoints;
+	     cursor = cursor->next) {
+		local = list_entry(cursor, struct rxrpc_local, link);
+
+		diff = rxrpc_local_cmp_key(local, srx);
+		if (diff < 0)
+			continue;
+		if (diff > 0)
+			break;
+
+		/* Services aren't allowed to share transport sockets, so
+		 * reject that here.  It is possible that the object is dying -
+		 * but it may also still have the local transport address that
+		 * we want bound.
+		 */
+		if (srx->srx_service) {
+			local = NULL;
+			goto addr_in_use;
+		}
+
+		/* Found a match.  We replace a dying object.  Attempting to
+		 * bind the transport socket may still fail if we're attempting
+		 * to use a local address that the dying object is still using.
+		 */
+		if (!atomic_inc_not_zero(&local->usage)) {
+			cursor = cursor->next;
+			list_del_init(&local->link);
+			break;
+		}
+
+		age = "old";
+		goto found;
+	}
+
+	local = rxrpc_alloc_local(srx);
+	if (!local)
+		goto nomem;
+
+	ret = rxrpc_open_socket(local);
+	if (ret < 0)
+		goto sock_error;
+
+	list_add_tail(&local->link, cursor);
+	age = "new";
+
+found:
+	mutex_unlock(&rxrpc_local_mutex);
+
+	_net("LOCAL %s %d {%d,%u,%pI4+%hu}",
+	     age,
+	     local->debug_id,
+	     local->srx.transport_type,
+	     local->srx.transport.family,
+	     &local->srx.transport.sin.sin_addr,
+	     ntohs(local->srx.transport.sin.sin_port));
+
+	_leave(" = %p", local);
+	return local;
+
+nomem:
+	ret = -ENOMEM;
+sock_error:
+	mutex_unlock(&rxrpc_local_mutex);
+	kfree(local);
+	_leave(" = %d", ret);
+	return ERR_PTR(ret);
+
+addr_in_use:
+	mutex_unlock(&rxrpc_local_mutex);
+	_leave(" = -EADDRINUSE");
+	return ERR_PTR(-EADDRINUSE);
+}
+
+/*
+ * A local endpoint reached its end of life.
+ */
+void __rxrpc_put_local(struct rxrpc_local *local)
+{
+	_enter("%d", local->debug_id);
+	rxrpc_queue_work(&local->processor);
+}
+
+/*
+ * Destroy a local endpoint's socket and then hand the record to RCU to dispose
+ * of.
+ *
+ * Closing the socket cannot be done from bottom half context or RCU callback
+ * context because it might sleep.
+ */
+static void rxrpc_local_destroyer(struct rxrpc_local *local)
+{
+	struct socket *socket = local->socket;
+
+	_enter("%d", local->debug_id);
+
+	/* We can get a race between an incoming call packet queueing the
+	 * processor again and the work processor starting the destruction
+	 * process which will shut down the UDP socket.
+	 */
+	if (local->dead) {
+		_leave(" [already dead]");
+		return;
+	}
+	local->dead = true;
+
+	mutex_lock(&rxrpc_local_mutex);
+	list_del_init(&local->link);
+	mutex_unlock(&rxrpc_local_mutex);
+
+	ASSERT(list_empty(&local->services));
+
+	if (socket) {
+		local->socket = NULL;
+		kernel_sock_shutdown(socket, SHUT_RDWR);
+		socket->sk->sk_user_data = NULL;
+		sock_release(socket);
+	}
+
+	/* At this point, there should be no more packets coming in to the
+	 * local endpoint.
+	 */
+	rxrpc_purge_queue(&local->accept_queue);
+	rxrpc_purge_queue(&local->reject_queue);
+	rxrpc_purge_queue(&local->event_queue);
+
+	_debug("rcu local %d", local->debug_id);
+	call_rcu(&local->rcu, rxrpc_local_rcu);
+}
+
+/*
+ * Process events on an endpoint
+ */
+static void rxrpc_local_processor(struct work_struct *work)
+{
+	struct rxrpc_local *local =
+		container_of(work, struct rxrpc_local, processor);
+	bool again;
+
+	_enter("%d", local->debug_id);
+
+	do {
+		again = false;
+		if (atomic_read(&local->usage) == 0)
+			return rxrpc_local_destroyer(local);
+
+		if (!skb_queue_empty(&local->accept_queue)) {
+			rxrpc_accept_incoming_calls(local);
+			again = true;
+		}
+
+		if (!skb_queue_empty(&local->reject_queue)) {
+			rxrpc_reject_packets(local);
+			again = true;
+		}
+
+		if (!skb_queue_empty(&local->event_queue)) {
+			rxrpc_process_local_events(local);
+			again = true;
+		}
+	} while (again);
+}
+
+/*
+ * Destroy a local endpoint after the RCU grace period expires.
+ */
+static void rxrpc_local_rcu(struct rcu_head *rcu)
+{
+	struct rxrpc_local *local = container_of(rcu, struct rxrpc_local, rcu);
+
+	_enter("%d", local->debug_id);
+
+	ASSERT(!work_pending(&local->processor));
+
+	_net("DESTROY LOCAL %d", local->debug_id);
+	kfree(local);
+	_leave("");
+}
+
+/*
+ * Verify the local endpoint list is empty by this point.
+ */
+void __exit rxrpc_destroy_all_locals(void)
+{
+	struct rxrpc_local *local;
+
+	_enter("");
+
+	if (list_empty(&rxrpc_local_endpoints))
+		return;
+
+	mutex_lock(&rxrpc_local_mutex);
+	list_for_each_entry(local, &rxrpc_local_endpoints, link) {
+		pr_err("AF_RXRPC: Leaked local %p {%d}\n",
+		       local, atomic_read(&local->usage));
+	}
+	mutex_unlock(&rxrpc_local_mutex);
+	BUG();
+}
diff --git a/net/rxrpc/misc.c b/net/rxrpc/misc.c
index 1afe987..bdc5e42 100644
--- a/net/rxrpc/misc.c
+++ b/net/rxrpc/misc.c
@@ -15,6 +15,12 @@
 #include "ar-internal.h"
 
 /*
+ * The maximum listening backlog queue size that may be set on a socket by
+ * listen().
+ */
+unsigned int rxrpc_max_backlog __read_mostly = 10;
+
+/*
  * How long to wait before scheduling ACK generation after seeing a
  * packet with RXRPC_REQUEST_ACK set (in jiffies).
  */
diff --git a/net/rxrpc/ar-output.c b/net/rxrpc/output.c
similarity index 88%
rename from net/rxrpc/ar-output.c
rename to net/rxrpc/output.c
index ea61953..e6fb386 100644
--- a/net/rxrpc/ar-output.c
+++ b/net/rxrpc/output.c
@@ -32,13 +32,13 @@
 /*
  * extract control messages from the sendmsg() control buffer
  */
-static int rxrpc_sendmsg_cmsg(struct rxrpc_sock *rx, struct msghdr *msg,
+static int rxrpc_sendmsg_cmsg(struct msghdr *msg,
 			      unsigned long *user_call_ID,
 			      enum rxrpc_command *command,
-			      u32 *abort_code,
-			      bool server)
+			      u32 *abort_code)
 {
 	struct cmsghdr *cmsg;
+	bool got_user_ID = false;
 	int len;
 
 	*command = RXRPC_CMD_SEND_DATA;
@@ -70,6 +70,7 @@
 					CMSG_DATA(cmsg);
 			}
 			_debug("User Call ID %lx", *user_call_ID);
+			got_user_ID = true;
 			break;
 
 		case RXRPC_ABORT:
@@ -90,8 +91,6 @@
 			*command = RXRPC_CMD_ACCEPT;
 			if (len != 0)
 				return -EINVAL;
-			if (!server)
-				return -EISCONN;
 			break;
 
 		default:
@@ -99,6 +98,8 @@
 		}
 	}
 
+	if (!got_user_ID)
+		return -EINVAL;
 	_leave(" = 0");
 	return 0;
 }
@@ -126,55 +127,96 @@
 }
 
 /*
+ * Create a new client call for sendmsg().
+ */
+static struct rxrpc_call *
+rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg,
+				  unsigned long user_call_ID)
+{
+	struct rxrpc_conn_bundle *bundle;
+	struct rxrpc_transport *trans;
+	struct rxrpc_call *call;
+	struct key *key;
+	long ret;
+
+	DECLARE_SOCKADDR(struct sockaddr_rxrpc *, srx, msg->msg_name);
+
+	_enter("");
+
+	if (!msg->msg_name)
+		return ERR_PTR(-EDESTADDRREQ);
+
+	trans = rxrpc_name_to_transport(rx, msg->msg_name, msg->msg_namelen, 0,
+					GFP_KERNEL);
+	if (IS_ERR(trans)) {
+		ret = PTR_ERR(trans);
+		goto out;
+	}
+
+	key = rx->key;
+	if (key && !rx->key->payload.data[0])
+		key = NULL;
+	bundle = rxrpc_get_bundle(rx, trans, key, srx->srx_service, GFP_KERNEL);
+	if (IS_ERR(bundle)) {
+		ret = PTR_ERR(bundle);
+		goto out_trans;
+	}
+
+	call = rxrpc_new_client_call(rx, trans, bundle, user_call_ID,
+				     GFP_KERNEL);
+	rxrpc_put_bundle(trans, bundle);
+	rxrpc_put_transport(trans);
+	if (IS_ERR(call)) {
+		ret = PTR_ERR(call);
+		goto out_trans;
+	}
+
+	_leave(" = %p\n", call);
+	return call;
+
+out_trans:
+	rxrpc_put_transport(trans);
+out:
+	_leave(" = %ld", ret);
+	return ERR_PTR(ret);
+}
+
+/*
  * send a message forming part of a client call through an RxRPC socket
  * - caller holds the socket locked
  * - the socket may be either a client socket or a server socket
  */
-int rxrpc_client_sendmsg(struct rxrpc_sock *rx, struct rxrpc_transport *trans,
-			 struct msghdr *msg, size_t len)
+int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
 {
-	struct rxrpc_conn_bundle *bundle;
 	enum rxrpc_command cmd;
 	struct rxrpc_call *call;
 	unsigned long user_call_ID = 0;
-	struct key *key;
-	u16 service_id;
 	u32 abort_code = 0;
 	int ret;
 
 	_enter("");
 
-	ASSERT(trans != NULL);
-
-	ret = rxrpc_sendmsg_cmsg(rx, msg, &user_call_ID, &cmd, &abort_code,
-				 false);
+	ret = rxrpc_sendmsg_cmsg(msg, &user_call_ID, &cmd, &abort_code);
 	if (ret < 0)
 		return ret;
 
-	bundle = NULL;
-	if (trans) {
-		service_id = rx->srx.srx_service;
-		if (msg->msg_name) {
-			DECLARE_SOCKADDR(struct sockaddr_rxrpc *, srx,
-					 msg->msg_name);
-			service_id = srx->srx_service;
-		}
-		key = rx->key;
-		if (key && !rx->key->payload.data[0])
-			key = NULL;
-		bundle = rxrpc_get_bundle(rx, trans, key, service_id,
-					  GFP_KERNEL);
-		if (IS_ERR(bundle))
-			return PTR_ERR(bundle);
+	if (cmd == RXRPC_CMD_ACCEPT) {
+		if (rx->sk.sk_state != RXRPC_SERVER_LISTENING)
+			return -EINVAL;
+		call = rxrpc_accept_call(rx, user_call_ID);
+		if (IS_ERR(call))
+			return PTR_ERR(call);
+		rxrpc_put_call(call);
+		return 0;
 	}
 
-	call = rxrpc_get_client_call(rx, trans, bundle, user_call_ID,
-				     abort_code == 0, GFP_KERNEL);
-	if (trans)
-		rxrpc_put_bundle(trans, bundle);
-	if (IS_ERR(call)) {
-		_leave(" = %ld", PTR_ERR(call));
-		return PTR_ERR(call);
+	call = rxrpc_find_call_by_user_ID(rx, user_call_ID);
+	if (!call) {
+		if (cmd != RXRPC_CMD_SEND_DATA)
+			return -EBADSLT;
+		call = rxrpc_new_client_call_for_sendmsg(rx, msg, user_call_ID);
+		if (IS_ERR(call))
+			return PTR_ERR(call);
 	}
 
 	_debug("CALL %d USR %lx ST %d on CONN %p",
@@ -182,14 +224,21 @@
 
 	if (call->state >= RXRPC_CALL_COMPLETE) {
 		/* it's too late for this call */
-		ret = -ESHUTDOWN;
+		ret = -ECONNRESET;
 	} else if (cmd == RXRPC_CMD_SEND_ABORT) {
 		rxrpc_send_abort(call, abort_code);
+		ret = 0;
 	} else if (cmd != RXRPC_CMD_SEND_DATA) {
 		ret = -EINVAL;
-	} else if (call->state != RXRPC_CALL_CLIENT_SEND_REQUEST) {
+	} else if (!call->in_clientflag &&
+		   call->state != RXRPC_CALL_CLIENT_SEND_REQUEST) {
 		/* request phase complete for this client call */
 		ret = -EPROTO;
+	} else if (call->in_clientflag &&
+		   call->state != RXRPC_CALL_SERVER_ACK_REQUEST &&
+		   call->state != RXRPC_CALL_SERVER_SEND_REPLY) {
+		/* Reply phase not begun or not complete for service call. */
+		ret = -EPROTO;
 	} else {
 		ret = rxrpc_send_data(rx, call, msg, len);
 	}
@@ -268,67 +317,6 @@
 EXPORT_SYMBOL(rxrpc_kernel_abort_call);
 
 /*
- * send a message through a server socket
- * - caller holds the socket locked
- */
-int rxrpc_server_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
-{
-	enum rxrpc_command cmd;
-	struct rxrpc_call *call;
-	unsigned long user_call_ID = 0;
-	u32 abort_code = 0;
-	int ret;
-
-	_enter("");
-
-	ret = rxrpc_sendmsg_cmsg(rx, msg, &user_call_ID, &cmd, &abort_code,
-				 true);
-	if (ret < 0)
-		return ret;
-
-	if (cmd == RXRPC_CMD_ACCEPT) {
-		call = rxrpc_accept_call(rx, user_call_ID);
-		if (IS_ERR(call))
-			return PTR_ERR(call);
-		rxrpc_put_call(call);
-		return 0;
-	}
-
-	call = rxrpc_find_server_call(rx, user_call_ID);
-	if (!call)
-		return -EBADSLT;
-	if (call->state >= RXRPC_CALL_COMPLETE) {
-		ret = -ESHUTDOWN;
-		goto out;
-	}
-
-	switch (cmd) {
-	case RXRPC_CMD_SEND_DATA:
-		if (call->state != RXRPC_CALL_CLIENT_SEND_REQUEST &&
-		    call->state != RXRPC_CALL_SERVER_ACK_REQUEST &&
-		    call->state != RXRPC_CALL_SERVER_SEND_REPLY) {
-			/* Tx phase not yet begun for this call */
-			ret = -EPROTO;
-			break;
-		}
-
-		ret = rxrpc_send_data(rx, call, msg, len);
-		break;
-
-	case RXRPC_CMD_SEND_ABORT:
-		rxrpc_send_abort(call, abort_code);
-		break;
-	default:
-		BUG();
-	}
-
-	out:
-	rxrpc_put_call(call);
-	_leave(" = %d", ret);
-	return ret;
-}
-
-/*
  * send a packet through the transport endpoint
  */
 int rxrpc_send_packet(struct rxrpc_transport *trans, struct sk_buff *skb)
@@ -719,7 +707,9 @@
 call_aborted:
 	rxrpc_free_skb(skb);
 	if (call->state == RXRPC_CALL_NETWORK_ERROR)
-		ret = call->conn->trans->peer->net_error;
+		ret = call->error_report < RXRPC_LOCAL_ERROR_OFFSET ?
+			call->error_report :
+			call->error_report - RXRPC_LOCAL_ERROR_OFFSET;
 	else
 		ret = -ECONNABORTED;
 	_leave(" = %d", ret);
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
new file mode 100644
index 0000000..8940674
--- /dev/null
+++ b/net/rxrpc/peer_event.c
@@ -0,0 +1,281 @@
+/* Peer event handling, typically ICMP messages.
+ *
+ * Copyright (C) 2007 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 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/net.h>
+#include <linux/skbuff.h>
+#include <linux/errqueue.h>
+#include <linux/udp.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <linux/icmp.h>
+#include <net/sock.h>
+#include <net/af_rxrpc.h>
+#include <net/ip.h>
+#include "ar-internal.h"
+
+static void rxrpc_store_error(struct rxrpc_peer *, struct sock_exterr_skb *);
+
+/*
+ * Find the peer associated with an ICMP packet.
+ */
+static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local,
+						     const struct sk_buff *skb)
+{
+	struct sock_exterr_skb *serr = SKB_EXT_ERR(skb);
+	struct sockaddr_rxrpc srx;
+
+	_enter("");
+
+	memset(&srx, 0, sizeof(srx));
+	srx.transport_type = local->srx.transport_type;
+	srx.transport.family = local->srx.transport.family;
+
+	/* Can we see an ICMP4 packet on an ICMP6 listening socket?  and vice
+	 * versa?
+	 */
+	switch (srx.transport.family) {
+	case AF_INET:
+		srx.transport.sin.sin_port = serr->port;
+		srx.transport_len = sizeof(struct sockaddr_in);
+		switch (serr->ee.ee_origin) {
+		case SO_EE_ORIGIN_ICMP:
+			_net("Rx ICMP");
+			memcpy(&srx.transport.sin.sin_addr,
+			       skb_network_header(skb) + serr->addr_offset,
+			       sizeof(struct in_addr));
+			break;
+		case SO_EE_ORIGIN_ICMP6:
+			_net("Rx ICMP6 on v4 sock");
+			memcpy(&srx.transport.sin.sin_addr,
+			       skb_network_header(skb) + serr->addr_offset + 12,
+			       sizeof(struct in_addr));
+			break;
+		default:
+			memcpy(&srx.transport.sin.sin_addr, &ip_hdr(skb)->saddr,
+			       sizeof(struct in_addr));
+			break;
+		}
+		break;
+
+	default:
+		BUG();
+	}
+
+	return rxrpc_lookup_peer_rcu(local, &srx);
+}
+
+/*
+ * Handle an MTU/fragmentation problem.
+ */
+static void rxrpc_adjust_mtu(struct rxrpc_peer *peer, struct sock_exterr_skb *serr)
+{
+	u32 mtu = serr->ee.ee_info;
+
+	_net("Rx ICMP Fragmentation Needed (%d)", mtu);
+
+	/* wind down the local interface MTU */
+	if (mtu > 0 && peer->if_mtu == 65535 && mtu < peer->if_mtu) {
+		peer->if_mtu = mtu;
+		_net("I/F MTU %u", mtu);
+	}
+
+	if (mtu == 0) {
+		/* they didn't give us a size, estimate one */
+		mtu = peer->if_mtu;
+		if (mtu > 1500) {
+			mtu >>= 1;
+			if (mtu < 1500)
+				mtu = 1500;
+		} else {
+			mtu -= 100;
+			if (mtu < peer->hdrsize)
+				mtu = peer->hdrsize + 4;
+		}
+	}
+
+	if (mtu < peer->mtu) {
+		spin_lock_bh(&peer->lock);
+		peer->mtu = mtu;
+		peer->maxdata = peer->mtu - peer->hdrsize;
+		spin_unlock_bh(&peer->lock);
+		_net("Net MTU %u (maxdata %u)",
+		     peer->mtu, peer->maxdata);
+	}
+}
+
+/*
+ * Handle an error received on the local endpoint.
+ */
+void rxrpc_error_report(struct sock *sk)
+{
+	struct sock_exterr_skb *serr;
+	struct rxrpc_local *local = sk->sk_user_data;
+	struct rxrpc_peer *peer;
+	struct sk_buff *skb;
+
+	_enter("%p{%d}", sk, local->debug_id);
+
+	skb = sock_dequeue_err_skb(sk);
+	if (!skb) {
+		_leave("UDP socket errqueue empty");
+		return;
+	}
+	serr = SKB_EXT_ERR(skb);
+	if (!skb->len && serr->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) {
+		_leave("UDP empty message");
+		kfree_skb(skb);
+		return;
+	}
+
+	rxrpc_new_skb(skb);
+
+	rcu_read_lock();
+	peer = rxrpc_lookup_peer_icmp_rcu(local, skb);
+	if (peer && !rxrpc_get_peer_maybe(peer))
+		peer = NULL;
+	if (!peer) {
+		rcu_read_unlock();
+		rxrpc_free_skb(skb);
+		_leave(" [no peer]");
+		return;
+	}
+
+	if ((serr->ee.ee_origin == SO_EE_ORIGIN_ICMP &&
+	     serr->ee.ee_type == ICMP_DEST_UNREACH &&
+	     serr->ee.ee_code == ICMP_FRAG_NEEDED)) {
+		rxrpc_adjust_mtu(peer, serr);
+		rcu_read_unlock();
+		rxrpc_free_skb(skb);
+		rxrpc_put_peer(peer);
+		_leave(" [MTU update]");
+		return;
+	}
+
+	rxrpc_store_error(peer, serr);
+	rcu_read_unlock();
+	rxrpc_free_skb(skb);
+
+	/* The ref we obtained is passed off to the work item */
+	rxrpc_queue_work(&peer->error_distributor);
+	_leave("");
+}
+
+/*
+ * Map an error report to error codes on the peer record.
+ */
+static void rxrpc_store_error(struct rxrpc_peer *peer,
+			      struct sock_exterr_skb *serr)
+{
+	struct sock_extended_err *ee;
+	int err;
+
+	_enter("");
+
+	ee = &serr->ee;
+
+	_net("Rx Error o=%d t=%d c=%d e=%d",
+	     ee->ee_origin, ee->ee_type, ee->ee_code, ee->ee_errno);
+
+	err = ee->ee_errno;
+
+	switch (ee->ee_origin) {
+	case SO_EE_ORIGIN_ICMP:
+		switch (ee->ee_type) {
+		case ICMP_DEST_UNREACH:
+			switch (ee->ee_code) {
+			case ICMP_NET_UNREACH:
+				_net("Rx Received ICMP Network Unreachable");
+				break;
+			case ICMP_HOST_UNREACH:
+				_net("Rx Received ICMP Host Unreachable");
+				break;
+			case ICMP_PORT_UNREACH:
+				_net("Rx Received ICMP Port Unreachable");
+				break;
+			case ICMP_NET_UNKNOWN:
+				_net("Rx Received ICMP Unknown Network");
+				break;
+			case ICMP_HOST_UNKNOWN:
+				_net("Rx Received ICMP Unknown Host");
+				break;
+			default:
+				_net("Rx Received ICMP DestUnreach code=%u",
+				     ee->ee_code);
+				break;
+			}
+			break;
+
+		case ICMP_TIME_EXCEEDED:
+			_net("Rx Received ICMP TTL Exceeded");
+			break;
+
+		default:
+			_proto("Rx Received ICMP error { type=%u code=%u }",
+			       ee->ee_type, ee->ee_code);
+			break;
+		}
+		break;
+
+	case SO_EE_ORIGIN_NONE:
+	case SO_EE_ORIGIN_LOCAL:
+		_proto("Rx Received local error { error=%d }", err);
+		err += RXRPC_LOCAL_ERROR_OFFSET;
+		break;
+
+	case SO_EE_ORIGIN_ICMP6:
+	default:
+		_proto("Rx Received error report { orig=%u }", ee->ee_origin);
+		break;
+	}
+
+	peer->error_report = err;
+}
+
+/*
+ * Distribute an error that occurred on a peer
+ */
+void rxrpc_peer_error_distributor(struct work_struct *work)
+{
+	struct rxrpc_peer *peer =
+		container_of(work, struct rxrpc_peer, error_distributor);
+	struct rxrpc_call *call;
+	int error_report;
+
+	_enter("");
+
+	error_report = READ_ONCE(peer->error_report);
+
+	_debug("ISSUE ERROR %d", error_report);
+
+	spin_lock_bh(&peer->lock);
+
+	while (!hlist_empty(&peer->error_targets)) {
+		call = hlist_entry(peer->error_targets.first,
+				   struct rxrpc_call, error_link);
+		hlist_del_init(&call->error_link);
+
+		write_lock(&call->state_lock);
+		if (call->state != RXRPC_CALL_COMPLETE &&
+		    call->state < RXRPC_CALL_NETWORK_ERROR) {
+			call->error_report = error_report;
+			call->state = RXRPC_CALL_NETWORK_ERROR;
+			set_bit(RXRPC_CALL_EV_RCVD_ERROR, &call->events);
+			rxrpc_queue_call(call);
+		}
+		write_unlock(&call->state_lock);
+	}
+
+	spin_unlock_bh(&peer->lock);
+
+	rxrpc_put_peer(peer);
+	_leave("");
+}
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
new file mode 100644
index 0000000..faf222c
--- /dev/null
+++ b/net/rxrpc/peer_object.c
@@ -0,0 +1,310 @@
+/* RxRPC remote transport endpoint record management
+ *
+ * Copyright (C) 2007, 2016 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 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) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <linux/udp.h>
+#include <linux/in.h>
+#include <linux/slab.h>
+#include <linux/hashtable.h>
+#include <net/sock.h>
+#include <net/af_rxrpc.h>
+#include <net/ip.h>
+#include <net/route.h>
+#include "ar-internal.h"
+
+static DEFINE_HASHTABLE(rxrpc_peer_hash, 10);
+static DEFINE_SPINLOCK(rxrpc_peer_hash_lock);
+
+/*
+ * Hash a peer key.
+ */
+static unsigned long rxrpc_peer_hash_key(struct rxrpc_local *local,
+					 const struct sockaddr_rxrpc *srx)
+{
+	const u16 *p;
+	unsigned int i, size;
+	unsigned long hash_key;
+
+	_enter("");
+
+	hash_key = (unsigned long)local / __alignof__(*local);
+	hash_key += srx->transport_type;
+	hash_key += srx->transport_len;
+	hash_key += srx->transport.family;
+
+	switch (srx->transport.family) {
+	case AF_INET:
+		hash_key += (u16 __force)srx->transport.sin.sin_port;
+		size = sizeof(srx->transport.sin.sin_addr);
+		p = (u16 *)&srx->transport.sin.sin_addr;
+		break;
+	}
+
+	/* Step through the peer address in 16-bit portions for speed */
+	for (i = 0; i < size; i += sizeof(*p), p++)
+		hash_key += *p;
+
+	_leave(" 0x%lx", hash_key);
+	return hash_key;
+}
+
+/*
+ * Compare a peer to a key.  Return -ve, 0 or +ve to indicate less than, same
+ * or greater than.
+ *
+ * Unfortunately, the primitives in linux/hashtable.h don't allow for sorted
+ * buckets and mid-bucket insertion, so we don't make full use of this
+ * information at this point.
+ */
+static long rxrpc_peer_cmp_key(const struct rxrpc_peer *peer,
+			       struct rxrpc_local *local,
+			       const struct sockaddr_rxrpc *srx,
+			       unsigned long hash_key)
+{
+	long diff;
+
+	diff = ((peer->hash_key - hash_key) ?:
+		((unsigned long)peer->local - (unsigned long)local) ?:
+		(peer->srx.transport_type - srx->transport_type) ?:
+		(peer->srx.transport_len - srx->transport_len) ?:
+		(peer->srx.transport.family - srx->transport.family));
+	if (diff != 0)
+		return diff;
+
+	switch (srx->transport.family) {
+	case AF_INET:
+		return ((u16 __force)peer->srx.transport.sin.sin_port -
+			(u16 __force)srx->transport.sin.sin_port) ?:
+			memcmp(&peer->srx.transport.sin.sin_addr,
+			       &srx->transport.sin.sin_addr,
+			       sizeof(struct in_addr));
+	default:
+		BUG();
+	}
+}
+
+/*
+ * Look up a remote transport endpoint for the specified address using RCU.
+ */
+static struct rxrpc_peer *__rxrpc_lookup_peer_rcu(
+	struct rxrpc_local *local,
+	const struct sockaddr_rxrpc *srx,
+	unsigned long hash_key)
+{
+	struct rxrpc_peer *peer;
+
+	hash_for_each_possible_rcu(rxrpc_peer_hash, peer, hash_link, hash_key) {
+		if (rxrpc_peer_cmp_key(peer, local, srx, hash_key) == 0) {
+			if (atomic_read(&peer->usage) == 0)
+				return NULL;
+			return peer;
+		}
+	}
+
+	return NULL;
+}
+
+/*
+ * Look up a remote transport endpoint for the specified address using RCU.
+ */
+struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *local,
+					 const struct sockaddr_rxrpc *srx)
+{
+	struct rxrpc_peer *peer;
+	unsigned long hash_key = rxrpc_peer_hash_key(local, srx);
+
+	peer = __rxrpc_lookup_peer_rcu(local, srx, hash_key);
+	if (peer) {
+		switch (srx->transport.family) {
+		case AF_INET:
+			_net("PEER %d {%d,%u,%pI4+%hu}",
+			     peer->debug_id,
+			     peer->srx.transport_type,
+			     peer->srx.transport.family,
+			     &peer->srx.transport.sin.sin_addr,
+			     ntohs(peer->srx.transport.sin.sin_port));
+			break;
+		}
+
+		_leave(" = %p {u=%d}", peer, atomic_read(&peer->usage));
+	}
+	return peer;
+}
+
+/*
+ * assess the MTU size for the network interface through which this peer is
+ * reached
+ */
+static void rxrpc_assess_MTU_size(struct rxrpc_peer *peer)
+{
+	struct rtable *rt;
+	struct flowi4 fl4;
+
+	peer->if_mtu = 1500;
+
+	rt = ip_route_output_ports(&init_net, &fl4, NULL,
+				   peer->srx.transport.sin.sin_addr.s_addr, 0,
+				   htons(7000), htons(7001),
+				   IPPROTO_UDP, 0, 0);
+	if (IS_ERR(rt)) {
+		_leave(" [route err %ld]", PTR_ERR(rt));
+		return;
+	}
+
+	peer->if_mtu = dst_mtu(&rt->dst);
+	dst_release(&rt->dst);
+
+	_leave(" [if_mtu %u]", peer->if_mtu);
+}
+
+/*
+ * Allocate a peer.
+ */
+struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp)
+{
+	struct rxrpc_peer *peer;
+
+	_enter("");
+
+	peer = kzalloc(sizeof(struct rxrpc_peer), gfp);
+	if (peer) {
+		atomic_set(&peer->usage, 1);
+		peer->local = local;
+		INIT_HLIST_HEAD(&peer->error_targets);
+		INIT_WORK(&peer->error_distributor,
+			  &rxrpc_peer_error_distributor);
+		spin_lock_init(&peer->lock);
+		peer->debug_id = atomic_inc_return(&rxrpc_debug_id);
+	}
+
+	_leave(" = %p", peer);
+	return peer;
+}
+
+/*
+ * Set up a new peer.
+ */
+static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_local *local,
+					    struct sockaddr_rxrpc *srx,
+					    unsigned long hash_key,
+					    gfp_t gfp)
+{
+	struct rxrpc_peer *peer;
+
+	_enter("");
+
+	peer = rxrpc_alloc_peer(local, gfp);
+	if (peer) {
+		peer->hash_key = hash_key;
+		memcpy(&peer->srx, srx, sizeof(*srx));
+
+		rxrpc_assess_MTU_size(peer);
+		peer->mtu = peer->if_mtu;
+
+		if (srx->transport.family == AF_INET) {
+			peer->hdrsize = sizeof(struct iphdr);
+			switch (srx->transport_type) {
+			case SOCK_DGRAM:
+				peer->hdrsize += sizeof(struct udphdr);
+				break;
+			default:
+				BUG();
+				break;
+			}
+		} else {
+			BUG();
+		}
+
+		peer->hdrsize += sizeof(struct rxrpc_wire_header);
+		peer->maxdata = peer->mtu - peer->hdrsize;
+	}
+
+	_leave(" = %p", peer);
+	return peer;
+}
+
+/*
+ * obtain a remote transport endpoint for the specified address
+ */
+struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local,
+				     struct sockaddr_rxrpc *srx, gfp_t gfp)
+{
+	struct rxrpc_peer *peer, *candidate;
+	unsigned long hash_key = rxrpc_peer_hash_key(local, srx);
+
+	_enter("{%d,%d,%pI4+%hu}",
+	       srx->transport_type,
+	       srx->transport_len,
+	       &srx->transport.sin.sin_addr,
+	       ntohs(srx->transport.sin.sin_port));
+
+	/* search the peer list first */
+	rcu_read_lock();
+	peer = __rxrpc_lookup_peer_rcu(local, srx, hash_key);
+	if (peer && !rxrpc_get_peer_maybe(peer))
+		peer = NULL;
+	rcu_read_unlock();
+
+	if (!peer) {
+		/* The peer is not yet present in hash - create a candidate
+		 * for a new record and then redo the search.
+		 */
+		candidate = rxrpc_create_peer(local, srx, hash_key, gfp);
+		if (!candidate) {
+			_leave(" = NULL [nomem]");
+			return NULL;
+		}
+
+		spin_lock(&rxrpc_peer_hash_lock);
+
+		/* Need to check that we aren't racing with someone else */
+		peer = __rxrpc_lookup_peer_rcu(local, srx, hash_key);
+		if (peer && !rxrpc_get_peer_maybe(peer))
+			peer = NULL;
+		if (!peer)
+			hash_add_rcu(rxrpc_peer_hash,
+				     &candidate->hash_link, hash_key);
+
+		spin_unlock(&rxrpc_peer_hash_lock);
+
+		if (peer)
+			kfree(candidate);
+		else
+			peer = candidate;
+	}
+
+	_net("PEER %d {%d,%pI4+%hu}",
+	     peer->debug_id,
+	     peer->srx.transport_type,
+	     &peer->srx.transport.sin.sin_addr,
+	     ntohs(peer->srx.transport.sin.sin_port));
+
+	_leave(" = %p {u=%d}", peer, atomic_read(&peer->usage));
+	return peer;
+}
+
+/*
+ * Discard a ref on a remote peer record.
+ */
+void __rxrpc_put_peer(struct rxrpc_peer *peer)
+{
+	ASSERT(hlist_empty(&peer->error_targets));
+
+	spin_lock(&rxrpc_peer_hash_lock);
+	hash_del_rcu(&peer->hash_link);
+	spin_unlock(&rxrpc_peer_hash_lock);
+
+	kfree_rcu(peer, rcu);
+}
diff --git a/net/rxrpc/ar-proc.c b/net/rxrpc/proc.c
similarity index 100%
rename from net/rxrpc/ar-proc.c
rename to net/rxrpc/proc.c
diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/recvmsg.c
similarity index 100%
rename from net/rxrpc/ar-recvmsg.c
rename to net/rxrpc/recvmsg.c
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index d4da538..36a6340 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -1164,9 +1164,7 @@
 	/* pin the cipher we need so that the crypto layer doesn't invoke
 	 * keventd to go get it */
 	rxkad_ci = crypto_alloc_skcipher("pcbc(fcrypt)", 0, CRYPTO_ALG_ASYNC);
-	if (IS_ERR(rxkad_ci))
-		return PTR_ERR(rxkad_ci);
-	return 0;
+	return PTR_ERR_OR_ZERO(rxkad_ci);
 }
 
 /*
diff --git a/net/rxrpc/ar-security.c b/net/rxrpc/security.c
similarity index 100%
rename from net/rxrpc/ar-security.c
rename to net/rxrpc/security.c
diff --git a/net/rxrpc/ar-skbuff.c b/net/rxrpc/skbuff.c
similarity index 100%
rename from net/rxrpc/ar-skbuff.c
rename to net/rxrpc/skbuff.c
diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c
index d20ed57..a99690a 100644
--- a/net/rxrpc/sysctl.c
+++ b/net/rxrpc/sysctl.c
@@ -18,6 +18,7 @@
 static const unsigned int zero = 0;
 static const unsigned int one = 1;
 static const unsigned int four = 4;
+static const unsigned int thirtytwo = 32;
 static const unsigned int n_65535 = 65535;
 static const unsigned int n_max_acks = RXRPC_MAXACKS;
 
@@ -100,6 +101,15 @@
 
 	/* Non-time values */
 	{
+		.procname	= "max_backlog",
+		.data		= &rxrpc_max_backlog,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= (void *)&four,
+		.extra2		= (void *)&thirtytwo,
+	},
+	{
 		.procname	= "rx_window_size",
 		.data		= &rxrpc_rx_window_size,
 		.maxlen		= sizeof(unsigned int),
diff --git a/net/rxrpc/ar-transport.c b/net/rxrpc/transport.c
similarity index 94%
rename from net/rxrpc/ar-transport.c
rename to net/rxrpc/transport.c
index a1b6518..24c7121 100644
--- a/net/rxrpc/ar-transport.c
+++ b/net/rxrpc/transport.c
@@ -49,26 +49,11 @@
 		trans->bundles = RB_ROOT;
 		trans->client_conns = RB_ROOT;
 		trans->server_conns = RB_ROOT;
-		skb_queue_head_init(&trans->error_queue);
 		spin_lock_init(&trans->client_lock);
 		rwlock_init(&trans->conn_lock);
 		atomic_set(&trans->usage, 1);
 		trans->conn_idcounter = peer->srx.srx_service << 16;
 		trans->debug_id = atomic_inc_return(&rxrpc_debug_id);
-
-		if (peer->srx.transport.family == AF_INET) {
-			switch (peer->srx.transport_type) {
-			case SOCK_DGRAM:
-				INIT_WORK(&trans->error_handler,
-					  rxrpc_UDP_error_handler);
-				break;
-			default:
-				BUG();
-				break;
-			}
-		} else {
-			BUG();
-		}
 	}
 
 	_leave(" = %p", trans);
@@ -121,7 +106,7 @@
 	usage = atomic_read(&trans->usage);
 
 	rxrpc_get_local(trans->local);
-	atomic_inc(&trans->peer->usage);
+	rxrpc_get_peer(trans->peer);
 	list_add_tail(&trans->link, &rxrpc_transports);
 	write_unlock_bh(&rxrpc_transport_lock);
 	new = "new";
@@ -210,8 +195,6 @@
 {
 	_net("DESTROY TRANS %d", trans->debug_id);
 
-	rxrpc_purge_queue(&trans->error_queue);
-
 	rxrpc_put_local(trans->local);
 	rxrpc_put_peer(trans->peer);
 	kfree(trans);
diff --git a/net/rxrpc/utils.c b/net/rxrpc/utils.c
new file mode 100644
index 0000000..f28122a
--- /dev/null
+++ b/net/rxrpc/utils.c
@@ -0,0 +1,41 @@
+/* Utility routines
+ *
+ * Copyright (C) 2015 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/ip.h>
+#include <linux/udp.h>
+#include "ar-internal.h"
+
+/*
+ * Set up an RxRPC address from a socket buffer.
+ */
+void rxrpc_get_addr_from_skb(struct rxrpc_local *local,
+			     const struct sk_buff *skb,
+			     struct sockaddr_rxrpc *srx)
+{
+	memset(srx, 0, sizeof(*srx));
+	srx->transport_type = local->srx.transport_type;
+	srx->transport.family = local->srx.transport.family;
+
+	/* Can we see an ipv4 UDP packet on an ipv6 UDP socket?  and vice
+	 * versa?
+	 */
+	switch (srx->transport.family) {
+	case AF_INET:
+		srx->transport.sin.sin_port = udp_hdr(skb)->source;
+		srx->transport_len = sizeof(struct sockaddr_in);
+		memcpy(&srx->transport.sin.sin_addr, &ip_hdr(skb)->saddr,
+		       sizeof(struct in_addr));
+		break;
+
+	default:
+		BUG();
+	}
+}
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 336774a..f8c61d2 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -224,8 +224,8 @@
 }
 EXPORT_SYMBOL(tcf_hash_search);
 
-int tcf_hash_check(struct tc_action_net *tn, u32 index, struct tc_action *a,
-		   int bind)
+bool tcf_hash_check(struct tc_action_net *tn, u32 index, struct tc_action *a,
+		    int bind)
 {
 	struct tcf_hashinfo *hinfo = tn->hinfo;
 	struct tcf_common *p = NULL;
@@ -235,9 +235,9 @@
 		p->tcfc_refcnt++;
 		a->priv = p;
 		a->hinfo = hinfo;
-		return 1;
+		return true;
 	}
-	return 0;
+	return false;
 }
 EXPORT_SYMBOL(tcf_hash_check);
 
@@ -283,10 +283,11 @@
 	p->tcfc_index = index ? index : tcf_hash_new_index(tn);
 	p->tcfc_tm.install = jiffies;
 	p->tcfc_tm.lastuse = jiffies;
+	p->tcfc_tm.firstuse = 0;
 	if (est) {
 		err = gen_new_estimator(&p->tcfc_bstats, p->cpu_bstats,
 					&p->tcfc_rate_est,
-					&p->tcfc_lock, est);
+					&p->tcfc_lock, NULL, est);
 		if (err) {
 			free_percpu(p->cpu_qstats);
 			goto err2;
@@ -503,8 +504,8 @@
 }
 EXPORT_SYMBOL(tcf_action_dump_1);
 
-int
-tcf_action_dump(struct sk_buff *skb, struct list_head *actions, int bind, int ref)
+int tcf_action_dump(struct sk_buff *skb, struct list_head *actions,
+		    int bind, int ref)
 {
 	struct tc_action *a;
 	int err = -EINVAL;
@@ -670,7 +671,7 @@
 	if (err < 0)
 		goto errout;
 
-	if (gnet_stats_copy_basic(&d, p->cpu_bstats, &p->tcfc_bstats) < 0 ||
+	if (gnet_stats_copy_basic(NULL, &d, p->cpu_bstats, &p->tcfc_bstats) < 0 ||
 	    gnet_stats_copy_rate_est(&d, &p->tcfc_bstats,
 				     &p->tcfc_rate_est) < 0 ||
 	    gnet_stats_copy_queue(&d, p->cpu_qstats,
@@ -687,9 +688,9 @@
 	return -1;
 }
 
-static int
-tca_get_fill(struct sk_buff *skb, struct list_head *actions, u32 portid, u32 seq,
-	     u16 flags, int event, int bind, int ref)
+static int tca_get_fill(struct sk_buff *skb, struct list_head *actions,
+			u32 portid, u32 seq, u16 flags, int event, int bind,
+			int ref)
 {
 	struct tcamsg *t;
 	struct nlmsghdr *nlh;
@@ -730,7 +731,8 @@
 	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (!skb)
 		return -ENOBUFS;
-	if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, event, 0, 0) <= 0) {
+	if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, event,
+			 0, 0) <= 0) {
 		kfree_skb(skb);
 		return -EINVAL;
 	}
@@ -838,7 +840,8 @@
 	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);
+	nlh = nlmsg_put(skb, portid, n->nlmsg_seq, RTM_DELACTION,
+			sizeof(*t), 0);
 	if (!nlh)
 		goto out_module_put;
 	t = nlmsg_data(nlh);
@@ -1001,7 +1004,8 @@
 	u32 portid = skb ? NETLINK_CB(skb).portid : 0;
 	int ret = 0, ovr = 0;
 
-	if ((n->nlmsg_type != RTM_GETACTION) && !netlink_capable(skb, CAP_NET_ADMIN))
+	if ((n->nlmsg_type != RTM_GETACTION) &&
+	    !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	ret = nlmsg_parse(n, sizeof(struct tcamsg), tca, TCA_ACT_MAX, NULL);
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index c7123e0..f7b6cf4 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -154,10 +154,7 @@
 	if (ret)
 		goto nla_put_failure;
 
-	tm.install = jiffies_to_clock_t(jiffies - prog->tcf_tm.install);
-	tm.lastuse = jiffies_to_clock_t(jiffies - prog->tcf_tm.lastuse);
-	tm.expires = jiffies_to_clock_t(prog->tcf_tm.expires);
-
+	tcf_tm_dump(&tm, &prog->tcf_tm);
 	if (nla_put_64bit(skb, TCA_ACT_BPF_TM, sizeof(tm), &tm,
 			  TCA_ACT_BPF_PAD))
 		goto nla_put_failure;
@@ -172,7 +169,8 @@
 static const struct nla_policy act_bpf_policy[TCA_ACT_BPF_MAX + 1] = {
 	[TCA_ACT_BPF_PARMS]	= { .len = sizeof(struct tc_act_bpf) },
 	[TCA_ACT_BPF_FD]	= { .type = NLA_U32 },
-	[TCA_ACT_BPF_NAME]	= { .type = NLA_NUL_STRING, .len = ACT_BPF_NAME_LEN },
+	[TCA_ACT_BPF_NAME]	= { .type = NLA_NUL_STRING,
+				    .len = ACT_BPF_NAME_LEN },
 	[TCA_ACT_BPF_OPS_LEN]	= { .type = NLA_U16 },
 	[TCA_ACT_BPF_OPS]	= { .type = NLA_BINARY,
 				    .len = sizeof(struct sock_filter) * BPF_MAXINSNS },
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index 2ba700c..35a5270 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -44,7 +44,7 @@
 	int proto;
 
 	spin_lock(&ca->tcf_lock);
-	ca->tcf_tm.lastuse = jiffies;
+	tcf_lastuse_update(&ca->tcf_tm);
 	bstats_update(&ca->tcf_bstats, skb);
 
 	if (skb->protocol == htons(ETH_P_IP)) {
@@ -160,9 +160,7 @@
 	if (nla_put(skb, TCA_CONNMARK_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
 
-	t.install = jiffies_to_clock_t(jiffies - ci->tcf_tm.install);
-	t.lastuse = jiffies_to_clock_t(jiffies - ci->tcf_tm.lastuse);
-	t.expires = jiffies_to_clock_t(ci->tcf_tm.expires);
+	tcf_tm_dump(&t, &ci->tcf_tm);
 	if (nla_put_64bit(skb, TCA_CONNMARK_TM, sizeof(t), &t,
 			  TCA_CONNMARK_PAD))
 		goto nla_put_failure;
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 28e934e..dcd9aba 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -501,7 +501,7 @@
 	u32 update_flags;
 
 	spin_lock(&p->tcf_lock);
-	p->tcf_tm.lastuse = jiffies;
+	tcf_lastuse_update(&p->tcf_tm);
 	bstats_update(&p->tcf_bstats, skb);
 	action = p->tcf_action;
 	update_flags = p->update_flags;
@@ -546,9 +546,8 @@
 
 	if (nla_put(skb, TCA_CSUM_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
-	t.install = jiffies_to_clock_t(jiffies - p->tcf_tm.install);
-	t.lastuse = jiffies_to_clock_t(jiffies - p->tcf_tm.lastuse);
-	t.expires = jiffies_to_clock_t(p->tcf_tm.expires);
+
+	tcf_tm_dump(&t, &p->tcf_tm);
 	if (nla_put_64bit(skb, TCA_CSUM_TM, sizeof(t), &t, TCA_CSUM_PAD))
 		goto nla_put_failure;
 
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index ec5cc84..19058a7 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -162,7 +162,8 @@
 	tm->lastuse = lastuse;
 }
 
-static int tcf_gact_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
+static int tcf_gact_dump(struct sk_buff *skb, struct tc_action *a,
+			 int bind, int ref)
 {
 	unsigned char *b = skb_tail_pointer(skb);
 	struct tcf_gact *gact = a->priv;
@@ -188,9 +189,7 @@
 			goto nla_put_failure;
 	}
 #endif
-	t.install = jiffies_to_clock_t(jiffies - gact->tcf_tm.install);
-	t.lastuse = jiffies_to_clock_t(jiffies - gact->tcf_tm.lastuse);
-	t.expires = jiffies_to_clock_t(gact->tcf_tm.expires);
+	tcf_tm_dump(&t, &gact->tcf_tm);
 	if (nla_put_64bit(skb, TCA_GACT_TM, sizeof(t), &t, TCA_GACT_PAD))
 		goto nla_put_failure;
 	return skb->len;
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 658046d..b7fa969 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -423,7 +423,8 @@
 	u16 ife_type = 0;
 	u8 *daddr = NULL;
 	u8 *saddr = NULL;
-	int ret = 0, exists = 0;
+	bool exists = false;
+	int ret = 0;
 	int err;
 
 	err = nla_parse_nested(tb, TCA_IFE_MAX, nla, ife_policy);
@@ -553,9 +554,7 @@
 	if (nla_put(skb, TCA_IFE_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
 
-	t.install = jiffies_to_clock_t(jiffies - ife->tcf_tm.install);
-	t.lastuse = jiffies_to_clock_t(jiffies - ife->tcf_tm.lastuse);
-	t.expires = jiffies_to_clock_t(ife->tcf_tm.expires);
+	tcf_tm_dump(&t, &ife->tcf_tm);
 	if (nla_put_64bit(skb, TCA_IFE_TM, sizeof(t), &t, TCA_IFE_PAD))
 		goto nla_put_failure;
 
@@ -623,7 +622,7 @@
 
 	spin_lock(&ife->tcf_lock);
 	bstats_update(&ife->tcf_bstats, skb);
-	ife->tcf_tm.lastuse = jiffies;
+	tcf_lastuse_update(&ife->tcf_tm);
 	spin_unlock(&ife->tcf_lock);
 
 	ifehdrln = ntohs(ifehdrln);
@@ -711,7 +710,7 @@
 
 	spin_lock(&ife->tcf_lock);
 	bstats_update(&ife->tcf_bstats, skb);
-	ife->tcf_tm.lastuse = jiffies;
+	tcf_lastuse_update(&ife->tcf_tm);
 
 	if (!metalen) {		/* no metadata to send */
 		/* abuse overlimits to count when we allow packet
@@ -802,7 +801,7 @@
 	pr_info_ratelimited("unknown failure(policy neither de/encode\n");
 	spin_lock(&ife->tcf_lock);
 	bstats_update(&ife->tcf_bstats, skb);
-	ife->tcf_tm.lastuse = jiffies;
+	tcf_lastuse_update(&ife->tcf_tm);
 	ife->tcf_qstats.drops++;
 	spin_unlock(&ife->tcf_lock);
 
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 9f002ad..6148e32 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -34,7 +34,8 @@
 
 static int xt_net_id;
 
-static int ipt_init_target(struct xt_entry_target *t, char *table, unsigned int hook)
+static int ipt_init_target(struct xt_entry_target *t, char *table,
+			   unsigned int hook)
 {
 	struct xt_tgchk_param par;
 	struct xt_target *target;
@@ -96,7 +97,8 @@
 	struct tcf_ipt *ipt;
 	struct xt_entry_target *td, *t;
 	char *tname;
-	int ret = 0, err, exists = 0;
+	bool exists = false;
+	int ret = 0, err;
 	u32 hook = 0;
 	u32 index = 0;
 
@@ -212,7 +214,7 @@
 
 	spin_lock(&ipt->tcf_lock);
 
-	ipt->tcf_tm.lastuse = jiffies;
+	tcf_lastuse_update(&ipt->tcf_tm);
 	bstats_update(&ipt->tcf_bstats, skb);
 
 	/* yes, we have to worry about both in and out dev
@@ -242,7 +244,7 @@
 	default:
 		net_notice_ratelimited("tc filter: Bogus netfilter code %d assume ACCEPT\n",
 				       ret);
-		result = TC_POLICE_OK;
+		result = TC_ACT_OK;
 		break;
 	}
 	spin_unlock(&ipt->tcf_lock);
@@ -250,7 +252,8 @@
 
 }
 
-static int tcf_ipt_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
+static int tcf_ipt_dump(struct sk_buff *skb, struct tc_action *a, int bind,
+			int ref)
 {
 	unsigned char *b = skb_tail_pointer(skb);
 	struct tcf_ipt *ipt = a->priv;
@@ -277,11 +280,11 @@
 	    nla_put(skb, TCA_IPT_CNT, sizeof(struct tc_cnt), &c) ||
 	    nla_put_string(skb, TCA_IPT_TABLE, ipt->tcfi_tname))
 		goto nla_put_failure;
-	tm.install = jiffies_to_clock_t(jiffies - ipt->tcf_tm.install);
-	tm.lastuse = jiffies_to_clock_t(jiffies - ipt->tcf_tm.lastuse);
-	tm.expires = jiffies_to_clock_t(ipt->tcf_tm.expires);
+
+	tcf_tm_dump(&tm, &ipt->tcf_tm);
 	if (nla_put_64bit(skb, TCA_IPT_TM, sizeof(tm), &tm, TCA_IPT_PAD))
 		goto nla_put_failure;
+
 	kfree(t);
 	return skb->len;
 
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 128942b..5b135d3 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -62,7 +62,8 @@
 	struct tc_mirred *parm;
 	struct tcf_mirred *m;
 	struct net_device *dev;
-	int ret, ok_push = 0, exists = 0;
+	int ret, ok_push = 0;
+	bool exists = false;
 
 	if (nla == NULL)
 		return -EINVAL;
@@ -157,7 +158,6 @@
 	u32 at;
 
 	tcf_lastuse_update(&m->tcf_tm);
-
 	bstats_cpu_update(this_cpu_ptr(m->common.cpu_bstats), skb);
 
 	rcu_read_lock();
@@ -219,9 +219,8 @@
 
 	if (nla_put(skb, TCA_MIRRED_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
-	t.install = jiffies_to_clock_t(jiffies - m->tcf_tm.install);
-	t.lastuse = jiffies_to_clock_t(jiffies - m->tcf_tm.lastuse);
-	t.expires = jiffies_to_clock_t(m->tcf_tm.expires);
+
+	tcf_tm_dump(&t, &m->tcf_tm);
 	if (nla_put_64bit(skb, TCA_MIRRED_TM, sizeof(t), &t, TCA_MIRRED_PAD))
 		goto nla_put_failure;
 	return skb->len;
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index c0a879f..06ccb03 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -103,7 +103,7 @@
 
 	spin_lock(&p->tcf_lock);
 
-	p->tcf_tm.lastuse = jiffies;
+	tcf_lastuse_update(&p->tcf_tm);
 	old_addr = p->old_addr;
 	new_addr = p->new_addr;
 	mask = p->mask;
@@ -264,9 +264,8 @@
 
 	if (nla_put(skb, TCA_NAT_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
-	t.install = jiffies_to_clock_t(jiffies - p->tcf_tm.install);
-	t.lastuse = jiffies_to_clock_t(jiffies - p->tcf_tm.lastuse);
-	t.expires = jiffies_to_clock_t(p->tcf_tm.expires);
+
+	tcf_tm_dump(&t, &p->tcf_tm);
 	if (nla_put_64bit(skb, TCA_NAT_TM, sizeof(t), &t, TCA_NAT_PAD))
 		goto nla_put_failure;
 
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index c6e18f2..82d3c14 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -121,7 +121,7 @@
 
 	spin_lock(&p->tcf_lock);
 
-	p->tcf_tm.lastuse = jiffies;
+	tcf_lastuse_update(&p->tcf_tm);
 
 	if (p->tcfp_nkeys > 0) {
 		struct tc_pedit_key *tkey = p->tcfp_keys;
@@ -200,11 +200,11 @@
 
 	if (nla_put(skb, TCA_PEDIT_PARMS, s, opt))
 		goto nla_put_failure;
-	t.install = jiffies_to_clock_t(jiffies - p->tcf_tm.install);
-	t.lastuse = jiffies_to_clock_t(jiffies - p->tcf_tm.lastuse);
-	t.expires = jiffies_to_clock_t(p->tcf_tm.expires);
+
+	tcf_tm_dump(&t, &p->tcf_tm);
 	if (nla_put_64bit(skb, TCA_PEDIT_TM, sizeof(t), &t, TCA_PEDIT_PAD))
 		goto nla_put_failure;
+
 	kfree(opt);
 	return skb->len;
 
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index b884dae..1e8ede3 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -38,7 +38,7 @@
 	bool			peak_present;
 };
 #define to_police(pc)	\
-	container_of(pc, struct tcf_police, common)
+	container_of(pc->priv, struct tcf_police, common)
 
 #define POL_TAB_MASK     15
 
@@ -115,18 +115,16 @@
 	[TCA_POLICE_RESULT]	= { .type = NLA_U32 },
 };
 
-static int tcf_act_police_locate(struct net *net, struct nlattr *nla,
-				 struct nlattr *est, struct tc_action *a,
-				 int ovr, int bind)
+static int tcf_act_police_init(struct net *net, struct nlattr *nla,
+			       struct nlattr *est, struct tc_action *a,
+			       int ovr, int bind)
 {
-	unsigned int h;
 	int ret = 0, err;
 	struct nlattr *tb[TCA_POLICE_MAX + 1];
 	struct tc_police *parm;
 	struct tcf_police *police;
 	struct qdisc_rate_table *R_tab = NULL, *P_tab = NULL;
 	struct tc_action_net *tn = net_generic(net, police_net_id);
-	struct tcf_hashinfo *hinfo = tn->hinfo;
 	int size;
 
 	if (nla == NULL)
@@ -145,7 +143,7 @@
 
 	if (parm->index) {
 		if (tcf_hash_search(tn, a, parm->index)) {
-			police = to_police(a->priv);
+			police = to_police(a);
 			if (bind) {
 				police->tcf_bindcnt += 1;
 				police->tcf_refcnt += 1;
@@ -156,16 +154,15 @@
 			/* not replacing */
 			return -EEXIST;
 		}
+	} else {
+		ret = tcf_hash_create(tn, parm->index, NULL, a,
+				      sizeof(*police), bind, false);
+		if (ret)
+			return ret;
+		ret = ACT_P_CREATED;
 	}
 
-	police = kzalloc(sizeof(*police), GFP_KERNEL);
-	if (police == NULL)
-		return -ENOMEM;
-	ret = ACT_P_CREATED;
-	police->tcf_refcnt = 1;
-	spin_lock_init(&police->tcf_lock);
-	if (bind)
-		police->tcf_bindcnt = 1;
+	police = to_police(a);
 override:
 	if (parm->rate.rate) {
 		err = -ENOMEM;
@@ -185,7 +182,8 @@
 	if (est) {
 		err = gen_replace_estimator(&police->tcf_bstats, NULL,
 					    &police->tcf_rate_est,
-					    &police->tcf_lock, est);
+					    &police->tcf_lock,
+					    NULL, est);
 		if (err)
 			goto failure_unlock;
 	} else if (tb[TCA_POLICE_AVRATE] &&
@@ -237,16 +235,8 @@
 		return ret;
 
 	police->tcfp_t_c = ktime_get_ns();
-	police->tcf_index = parm->index ? parm->index :
-		tcf_hash_new_index(tn);
-	police->tcf_tm.install = jiffies;
-	police->tcf_tm.lastuse = jiffies;
-	h = tcf_hash(police->tcf_index, POL_TAB_MASK);
-	spin_lock_bh(&hinfo->lock);
-	hlist_add_head(&police->tcf_head, &hinfo->htab[h]);
-	spin_unlock_bh(&hinfo->lock);
+	tcf_hash_insert(tn, a);
 
-	a->priv = police;
 	return ret;
 
 failure_unlock:
@@ -255,7 +245,7 @@
 	qdisc_put_rtab(P_tab);
 	qdisc_put_rtab(R_tab);
 	if (ret == ACT_P_CREATED)
-		kfree(police);
+		tcf_hash_cleanup(a, est);
 	return err;
 }
 
@@ -347,6 +337,7 @@
 
 	t.install = jiffies_to_clock_t(jiffies - police->tcf_tm.install);
 	t.lastuse = jiffies_to_clock_t(jiffies - police->tcf_tm.lastuse);
+	t.firstuse = jiffies_to_clock_t(jiffies - police->tcf_tm.firstuse);
 	t.expires = jiffies_to_clock_t(police->tcf_tm.expires);
 	if (nla_put_64bit(skb, TCA_POLICE_TM, sizeof(t), &t, TCA_POLICE_PAD))
 		goto nla_put_failure;
@@ -375,7 +366,7 @@
 	.owner		=	THIS_MODULE,
 	.act		=	tcf_act_police,
 	.dump		=	tcf_act_police_dump,
-	.init		=	tcf_act_police_locate,
+	.init		=	tcf_act_police_init,
 	.walk		=	tcf_act_police_walker,
 	.lookup		=	tcf_police_search,
 };
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index e42f8da..318328d3 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -35,7 +35,7 @@
 	struct tcf_defact *d = a->priv;
 
 	spin_lock(&d->tcf_lock);
-	d->tcf_tm.lastuse = jiffies;
+	tcf_lastuse_update(&d->tcf_tm);
 	bstats_update(&d->tcf_bstats, skb);
 
 	/* print policy string followed by _ then packet count
@@ -86,8 +86,9 @@
 	struct nlattr *tb[TCA_DEF_MAX + 1];
 	struct tc_defact *parm;
 	struct tcf_defact *d;
+	bool exists = false;
+	int ret = 0, err;
 	char *defdata;
-	int ret = 0, err, exists = 0;
 
 	if (nla == NULL)
 		return -EINVAL;
@@ -158,9 +159,8 @@
 	if (nla_put(skb, TCA_DEF_PARMS, sizeof(opt), &opt) ||
 	    nla_put_string(skb, TCA_DEF_DATA, d->tcfd_defdata))
 		goto nla_put_failure;
-	t.install = jiffies_to_clock_t(jiffies - d->tcf_tm.install);
-	t.lastuse = jiffies_to_clock_t(jiffies - d->tcf_tm.lastuse);
-	t.expires = jiffies_to_clock_t(d->tcf_tm.expires);
+
+	tcf_tm_dump(&t, &d->tcf_tm);
 	if (nla_put_64bit(skb, TCA_DEF_TM, sizeof(t), &t, TCA_DEF_PAD))
 		goto nla_put_failure;
 	return skb->len;
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index e928802..53d1486 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -37,7 +37,7 @@
 	struct tcf_skbedit *d = a->priv;
 
 	spin_lock(&d->tcf_lock);
-	d->tcf_tm.lastuse = jiffies;
+	tcf_lastuse_update(&d->tcf_tm);
 	bstats_update(&d->tcf_bstats, skb);
 
 	if (d->flags & SKBEDIT_F_PRIORITY)
@@ -69,7 +69,8 @@
 	struct tcf_skbedit *d;
 	u32 flags = 0, *priority = NULL, *mark = NULL;
 	u16 *queue_mapping = NULL;
-	int ret = 0, err, exists = 0;
+	bool exists = false;
+	int ret = 0, err;
 
 	if (nla == NULL)
 		return -EINVAL;
@@ -168,9 +169,8 @@
 	    nla_put(skb, TCA_SKBEDIT_MARK, sizeof(d->mark),
 		    &d->mark))
 		goto nla_put_failure;
-	t.install = jiffies_to_clock_t(jiffies - d->tcf_tm.install);
-	t.lastuse = jiffies_to_clock_t(jiffies - d->tcf_tm.lastuse);
-	t.expires = jiffies_to_clock_t(d->tcf_tm.expires);
+
+	tcf_tm_dump(&t, &d->tcf_tm);
 	if (nla_put_64bit(skb, TCA_SKBEDIT_TM, sizeof(t), &t, TCA_SKBEDIT_PAD))
 		goto nla_put_failure;
 	return skb->len;
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index ac4adc8..db9b7ed 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -31,7 +31,7 @@
 	int err;
 
 	spin_lock(&v->tcf_lock);
-	v->tcf_tm.lastuse = jiffies;
+	tcf_lastuse_update(&v->tcf_tm);
 	bstats_update(&v->tcf_bstats, skb);
 	action = v->tcf_action;
 
@@ -77,8 +77,8 @@
 	int action;
 	__be16 push_vid = 0;
 	__be16 push_proto = 0;
-	int ret = 0, exists = 0;
-	int err;
+	bool exists = false;
+	int ret = 0, err;
 
 	if (!nla)
 		return -EINVAL;
@@ -179,12 +179,11 @@
 
 	if (v->tcfv_action == TCA_VLAN_ACT_PUSH &&
 	    (nla_put_u16(skb, TCA_VLAN_PUSH_VLAN_ID, v->tcfv_push_vid) ||
-	     nla_put_be16(skb, TCA_VLAN_PUSH_VLAN_PROTOCOL, v->tcfv_push_proto)))
+	     nla_put_be16(skb, TCA_VLAN_PUSH_VLAN_PROTOCOL,
+			  v->tcfv_push_proto)))
 		goto nla_put_failure;
 
-	t.install = jiffies_to_clock_t(jiffies - v->tcf_tm.install);
-	t.lastuse = jiffies_to_clock_t(jiffies - v->tcf_tm.lastuse);
-	t.expires = jiffies_to_clock_t(v->tcf_tm.expires);
+	tcf_tm_dump(&t, &v->tcf_tm);
 	if (nla_put_64bit(skb, TCA_VLAN_TM, sizeof(t), &t, TCA_VLAN_PAD))
 		goto nla_put_failure;
 	return skb->len;
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index a75864d..843a716 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -103,6 +103,17 @@
 			  struct nlmsghdr *n, struct tcf_proto *tp,
 			  unsigned long fh, int event);
 
+static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb,
+				 struct nlmsghdr *n,
+				 struct tcf_proto __rcu **chain, int event)
+{
+	struct tcf_proto __rcu **it_chain;
+	struct tcf_proto *tp;
+
+	for (it_chain = chain; (tp = rtnl_dereference(*it_chain)) != NULL;
+	     it_chain = &tp->next)
+		tfilter_notify(net, oskb, n, tp, 0, event);
+}
 
 /* Select new prio value from the range, managed by kernel. */
 
@@ -156,11 +167,23 @@
 	cl = 0;
 
 	if (prio == 0) {
-		/* If no priority is given, user wants we allocated it. */
-		if (n->nlmsg_type != RTM_NEWTFILTER ||
-		    !(n->nlmsg_flags & NLM_F_CREATE))
+		switch (n->nlmsg_type) {
+		case RTM_DELTFILTER:
+			if (protocol || t->tcm_handle || tca[TCA_KIND])
+				return -ENOENT;
+			break;
+		case RTM_NEWTFILTER:
+			/* If no priority is provided by the user,
+			 * we allocate one.
+			 */
+			if (n->nlmsg_flags & NLM_F_CREATE) {
+				prio = TC_H_MAKE(0x80000000U, 0U);
+				break;
+			}
+			/* fall-through */
+		default:
 			return -ENOENT;
-		prio = TC_H_MAKE(0x80000000U, 0U);
+		}
 	}
 
 	/* Find head of filter chain. */
@@ -200,6 +223,12 @@
 	err = -EINVAL;
 	if (chain == NULL)
 		goto errout;
+	if (n->nlmsg_type == RTM_DELTFILTER && prio == 0) {
+		tfilter_notify_chain(net, skb, n, chain, RTM_DELTFILTER);
+		tcf_destroy_chain(chain);
+		err = 0;
+		goto errout;
+	}
 
 	/* Check the chain for existence of proto-tcf with this priority */
 	for (back = chain;
@@ -351,8 +380,9 @@
 	return err;
 }
 
-static int tcf_fill_node(struct net *net, struct sk_buff *skb, struct tcf_proto *tp,
-			 unsigned long fh, u32 portid, u32 seq, u16 flags, int event)
+static int tcf_fill_node(struct net *net, struct sk_buff *skb,
+			 struct tcf_proto *tp, unsigned long fh, u32 portid,
+			 u32 seq, u16 flags, int event)
 {
 	struct tcmsg *tcm;
 	struct nlmsghdr  *nlh;
@@ -474,9 +504,11 @@
 		    TC_H_MIN(tcm->tcm_info) != tp->protocol)
 			continue;
 		if (t > s_t)
-			memset(&cb->args[1], 0, sizeof(cb->args)-sizeof(cb->args[0]));
+			memset(&cb->args[1], 0,
+			       sizeof(cb->args)-sizeof(cb->args[0]));
 		if (cb->args[1] == 0) {
-			if (tcf_fill_node(net, skb, tp, 0, NETLINK_CB(cb->skb).portid,
+			if (tcf_fill_node(net, skb, tp, 0,
+					  NETLINK_CB(cb->skb).portid,
 					  cb->nlh->nlmsg_seq, NLM_F_MULTI,
 					  RTM_NEWTFILTER) <= 0)
 				break;
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 730aaca..5060801 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -66,6 +66,7 @@
 	struct fl_flow_key key;
 	struct list_head list;
 	u32 handle;
+	u32 flags;
 	struct rcu_head	rcu;
 };
 
@@ -123,6 +124,9 @@
 	struct fl_flow_key skb_key;
 	struct fl_flow_key skb_mkey;
 
+	if (!atomic_read(&head->ht.nelems))
+		return -1;
+
 	fl_clear_masked_range(&skb_key, &head->mask);
 	skb_key.indev_ifindex = skb->skb_iif;
 	/* skb_flow_dissect() does not set n_proto in case an unknown protocol,
@@ -136,7 +140,7 @@
 	f = rhashtable_lookup_fast(&head->ht,
 				   fl_key_get_start(&skb_mkey, &head->mask),
 				   head->ht_params);
-	if (f) {
+	if (f && !tc_skip_sw(f->flags)) {
 		*res = f->res;
 		return tcf_exts_exec(skb, &f->exts, res);
 	}
@@ -171,7 +175,7 @@
 	struct tc_cls_flower_offload offload = {0};
 	struct tc_to_netdev tc;
 
-	if (!tc_should_offload(dev, 0))
+	if (!tc_should_offload(dev, tp, 0))
 		return;
 
 	offload.command = TC_CLSFLOWER_DESTROY;
@@ -183,19 +187,20 @@
 	dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, &tc);
 }
 
-static void fl_hw_replace_filter(struct tcf_proto *tp,
-				 struct flow_dissector *dissector,
-				 struct fl_flow_key *mask,
-				 struct fl_flow_key *key,
-				 struct tcf_exts *actions,
-				 unsigned long cookie, u32 flags)
+static int fl_hw_replace_filter(struct tcf_proto *tp,
+				struct flow_dissector *dissector,
+				struct fl_flow_key *mask,
+				struct fl_flow_key *key,
+				struct tcf_exts *actions,
+				unsigned long cookie, u32 flags)
 {
 	struct net_device *dev = tp->q->dev_queue->dev;
 	struct tc_cls_flower_offload offload = {0};
 	struct tc_to_netdev tc;
+	int err;
 
-	if (!tc_should_offload(dev, flags))
-		return;
+	if (!tc_should_offload(dev, tp, flags))
+		return tc_skip_sw(flags) ? -EINVAL : 0;
 
 	offload.command = TC_CLSFLOWER_REPLACE;
 	offload.cookie = cookie;
@@ -207,7 +212,12 @@
 	tc.type = TC_SETUP_CLSFLOWER;
 	tc.cls_flower = &offload;
 
-	dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, &tc);
+	err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, &tc);
+
+	if (tc_skip_sw(flags))
+		return err;
+
+	return 0;
 }
 
 static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f)
@@ -216,7 +226,7 @@
 	struct tc_cls_flower_offload offload = {0};
 	struct tc_to_netdev tc;
 
-	if (!tc_should_offload(dev, 0))
+	if (!tc_should_offload(dev, tp, 0))
 		return;
 
 	offload.command = TC_CLSFLOWER_STATS;
@@ -524,7 +534,6 @@
 	struct cls_fl_filter *fnew;
 	struct nlattr *tb[TCA_FLOWER_MAX + 1];
 	struct fl_flow_mask mask = {};
-	u32 flags = 0;
 	int err;
 
 	if (!tca[TCA_OPTIONS])
@@ -552,8 +561,14 @@
 	}
 	fnew->handle = handle;
 
-	if (tb[TCA_FLOWER_FLAGS])
-		flags = nla_get_u32(tb[TCA_FLOWER_FLAGS]);
+	if (tb[TCA_FLOWER_FLAGS]) {
+		fnew->flags = nla_get_u32(tb[TCA_FLOWER_FLAGS]);
+
+		if (!tc_flags_valid(fnew->flags)) {
+			err = -EINVAL;
+			goto errout;
+		}
+	}
 
 	err = fl_set_parms(net, tp, fnew, &mask, base, tb, tca[TCA_RATE], ovr);
 	if (err)
@@ -563,19 +578,23 @@
 	if (err)
 		goto errout;
 
-	err = rhashtable_insert_fast(&head->ht, &fnew->ht_node,
-				     head->ht_params);
+	if (!tc_skip_sw(fnew->flags)) {
+		err = rhashtable_insert_fast(&head->ht, &fnew->ht_node,
+					     head->ht_params);
+		if (err)
+			goto errout;
+	}
+
+	err = fl_hw_replace_filter(tp,
+				   &head->dissector,
+				   &mask.key,
+				   &fnew->key,
+				   &fnew->exts,
+				   (unsigned long)fnew,
+				   fnew->flags);
 	if (err)
 		goto errout;
 
-	fl_hw_replace_filter(tp,
-			     &head->dissector,
-			     &mask.key,
-			     &fnew->key,
-			     &fnew->exts,
-			     (unsigned long)fnew,
-			     flags);
-
 	if (fold) {
 		rhashtable_remove_fast(&head->ht, &fold->ht_node,
 				       head->ht_params);
@@ -734,6 +753,8 @@
 				  sizeof(key->tp.dst))))
 		goto nla_put_failure;
 
+	nla_put_u32(skb, TCA_FLOWER_FLAGS, f->flags);
+
 	if (tcf_exts_dump(skb, &f->exts))
 		goto nla_put_failure;
 
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 079b43b..ffe593e 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -440,7 +440,7 @@
 	offload.type = TC_SETUP_CLSU32;
 	offload.cls_u32 = &u32_offload;
 
-	if (tc_should_offload(dev, 0)) {
+	if (tc_should_offload(dev, tp, 0)) {
 		offload.cls_u32->command = TC_CLSU32_DELETE_KNODE;
 		offload.cls_u32->knode.handle = handle;
 		dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle,
@@ -457,20 +457,21 @@
 	struct tc_to_netdev offload;
 	int err;
 
+	if (!tc_should_offload(dev, tp, flags))
+		return tc_skip_sw(flags) ? -EINVAL : 0;
+
 	offload.type = TC_SETUP_CLSU32;
 	offload.cls_u32 = &u32_offload;
 
-	if (tc_should_offload(dev, flags)) {
-		offload.cls_u32->command = TC_CLSU32_NEW_HNODE;
-		offload.cls_u32->hnode.divisor = h->divisor;
-		offload.cls_u32->hnode.handle = h->handle;
-		offload.cls_u32->hnode.prio = h->prio;
+	offload.cls_u32->command = TC_CLSU32_NEW_HNODE;
+	offload.cls_u32->hnode.divisor = h->divisor;
+	offload.cls_u32->hnode.handle = h->handle;
+	offload.cls_u32->hnode.prio = h->prio;
 
-		err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle,
-						    tp->protocol, &offload);
-		if (tc_skip_sw(flags))
-			return err;
-	}
+	err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle,
+					    tp->protocol, &offload);
+	if (tc_skip_sw(flags))
+		return err;
 
 	return 0;
 }
@@ -484,7 +485,7 @@
 	offload.type = TC_SETUP_CLSU32;
 	offload.cls_u32 = &u32_offload;
 
-	if (tc_should_offload(dev, 0)) {
+	if (tc_should_offload(dev, tp, 0)) {
 		offload.cls_u32->command = TC_CLSU32_DELETE_HNODE;
 		offload.cls_u32->hnode.divisor = h->divisor;
 		offload.cls_u32->hnode.handle = h->handle;
@@ -507,27 +508,28 @@
 	offload.type = TC_SETUP_CLSU32;
 	offload.cls_u32 = &u32_offload;
 
-	if (tc_should_offload(dev, flags)) {
-		offload.cls_u32->command = TC_CLSU32_REPLACE_KNODE;
-		offload.cls_u32->knode.handle = n->handle;
-		offload.cls_u32->knode.fshift = n->fshift;
-#ifdef CONFIG_CLS_U32_MARK
-		offload.cls_u32->knode.val = n->val;
-		offload.cls_u32->knode.mask = n->mask;
-#else
-		offload.cls_u32->knode.val = 0;
-		offload.cls_u32->knode.mask = 0;
-#endif
-		offload.cls_u32->knode.sel = &n->sel;
-		offload.cls_u32->knode.exts = &n->exts;
-		if (n->ht_down)
-			offload.cls_u32->knode.link_handle = n->ht_down->handle;
+	if (!tc_should_offload(dev, tp, flags))
+		return tc_skip_sw(flags) ? -EINVAL : 0;
 
-		err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle,
-						    tp->protocol, &offload);
-		if (tc_skip_sw(flags))
-			return err;
-	}
+	offload.cls_u32->command = TC_CLSU32_REPLACE_KNODE;
+	offload.cls_u32->knode.handle = n->handle;
+	offload.cls_u32->knode.fshift = n->fshift;
+#ifdef CONFIG_CLS_U32_MARK
+	offload.cls_u32->knode.val = n->val;
+	offload.cls_u32->knode.mask = n->mask;
+#else
+	offload.cls_u32->knode.val = 0;
+	offload.cls_u32->knode.mask = 0;
+#endif
+	offload.cls_u32->knode.sel = &n->sel;
+	offload.cls_u32->knode.exts = &n->exts;
+	if (n->ht_down)
+		offload.cls_u32->knode.link_handle = n->ht_down->handle;
+
+	err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle,
+					    tp->protocol, &offload);
+	if (tc_skip_sw(flags))
+		return err;
 
 	return 0;
 }
@@ -863,7 +865,7 @@
 	if (tb[TCA_U32_FLAGS]) {
 		flags = nla_get_u32(tb[TCA_U32_FLAGS]);
 		if (!tc_flags_valid(flags))
-			return err;
+			return -EINVAL;
 	}
 
 	n = (struct tc_u_knode *)*arg;
@@ -921,11 +923,17 @@
 		ht->divisor = divisor;
 		ht->handle = handle;
 		ht->prio = tp->prio;
+
+		err = u32_replace_hw_hnode(tp, ht, flags);
+		if (err) {
+			kfree(ht);
+			return err;
+		}
+
 		RCU_INIT_POINTER(ht->next, tp_c->hlist);
 		rcu_assign_pointer(tp_c->hlist, ht);
 		*arg = (unsigned long)ht;
 
-		u32_replace_hw_hnode(tp, ht, flags);
 		return 0;
 	}
 
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index ddf047d..12ebde8 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -95,8 +95,6 @@
      Expected action: do not backoff, but wait until queue will clear.
    NET_XMIT_CN	 	- probably this packet enqueued, but another one dropped.
      Expected action: backoff or ignore
-   NET_XMIT_POLICED	- dropped by police.
-     Expected action: backoff or error to real-time apps.
 
    Auxiliary routines:
 
@@ -583,7 +581,6 @@
 						 timer);
 
 	rcu_read_lock();
-	qdisc_unthrottled(wd->qdisc);
 	__netif_schedule(qdisc_root(wd->qdisc));
 	rcu_read_unlock();
 
@@ -598,15 +595,12 @@
 }
 EXPORT_SYMBOL(qdisc_watchdog_init);
 
-void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires, bool throttle)
+void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires)
 {
 	if (test_bit(__QDISC_STATE_DEACTIVATED,
 		     &qdisc_root_sleeping(wd->qdisc)->state))
 		return;
 
-	if (throttle)
-		qdisc_throttled(wd->qdisc);
-
 	if (wd->last_expires == expires)
 		return;
 
@@ -620,7 +614,6 @@
 void qdisc_watchdog_cancel(struct qdisc_watchdog *wd)
 {
 	hrtimer_cancel(&wd->timer);
-	qdisc_unthrottled(wd->qdisc);
 }
 EXPORT_SYMBOL(qdisc_watchdog_cancel);
 
@@ -982,7 +975,7 @@
 			rcu_assign_pointer(sch->stab, stab);
 		}
 		if (tca[TCA_RATE]) {
-			spinlock_t *root_lock;
+			seqcount_t *running;
 
 			err = -EOPNOTSUPP;
 			if (sch->flags & TCQ_F_MQROOT)
@@ -991,14 +984,15 @@
 			if ((sch->parent != TC_H_ROOT) &&
 			    !(sch->flags & TCQ_F_INGRESS) &&
 			    (!p || !(p->flags & TCQ_F_MQROOT)))
-				root_lock = qdisc_root_sleeping_lock(sch);
+				running = qdisc_root_sleeping_running(sch);
 			else
-				root_lock = qdisc_lock(sch);
+				running = &sch->running;
 
 			err = gen_new_estimator(&sch->bstats,
 						sch->cpu_bstats,
 						&sch->rate_est,
-						root_lock,
+						NULL,
+						running,
 						tca[TCA_RATE]);
 			if (err)
 				goto err_out4;
@@ -1061,7 +1055,8 @@
 		gen_replace_estimator(&sch->bstats,
 				      sch->cpu_bstats,
 				      &sch->rate_est,
-				      qdisc_root_sleeping_lock(sch),
+				      NULL,
+				      qdisc_root_sleeping_running(sch),
 				      tca[TCA_RATE]);
 	}
 out:
@@ -1369,8 +1364,7 @@
 		goto nla_put_failure;
 
 	if (gnet_stats_start_copy_compat(skb, TCA_STATS2, TCA_STATS, TCA_XSTATS,
-					 qdisc_root_sleeping_lock(q), &d,
-					 TCA_PAD) < 0)
+					 NULL, &d, TCA_PAD) < 0)
 		goto nla_put_failure;
 
 	if (q->ops->dump_stats && q->ops->dump_stats(q, &d) < 0)
@@ -1381,7 +1375,8 @@
 		cpu_qstats = q->cpu_qstats;
 	}
 
-	if (gnet_stats_copy_basic(&d, cpu_bstats, &q->bstats) < 0 ||
+	if (gnet_stats_copy_basic(qdisc_root_sleeping_running(q),
+				  &d, cpu_bstats, &q->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(&d, &q->bstats, &q->rate_est) < 0 ||
 	    gnet_stats_copy_queue(&d, cpu_qstats, &q->qstats, qlen) < 0)
 		goto nla_put_failure;
@@ -1684,8 +1679,7 @@
 		goto nla_put_failure;
 
 	if (gnet_stats_start_copy_compat(skb, TCA_STATS2, TCA_STATS, TCA_XSTATS,
-					 qdisc_root_sleeping_lock(q), &d,
-					 TCA_PAD) < 0)
+					 NULL, &d, TCA_PAD) < 0)
 		goto nla_put_failure;
 
 	if (cl_ops->dump_stats && cl_ops->dump_stats(q, cl, &d) < 0)
diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index 1911af3..e04ea69 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -363,10 +363,10 @@
 	struct atm_flow_data *flow;
 	struct tcf_result res;
 	int result;
-	int ret = NET_XMIT_POLICED;
+	int ret = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
 
 	pr_debug("atm_tc_enqueue(skb %p,sch %p,[qdisc %p])\n", skb, sch, p);
-	result = TC_POLICE_OK;	/* be nice to gcc */
+	result = TC_ACT_OK;	/* be nice to gcc */
 	flow = NULL;
 	if (TC_H_MAJ(skb->priority) != sch->handle ||
 	    !(flow = (struct atm_flow_data *)atm_tc_get(sch, skb->priority))) {
@@ -403,7 +403,7 @@
 		case TC_ACT_SHOT:
 			kfree_skb(skb);
 			goto drop;
-		case TC_POLICE_RECLASSIFY:
+		case TC_ACT_RECLASSIFY:
 			if (flow->excess)
 				flow = flow->excess;
 			else
@@ -519,20 +519,6 @@
 	return p->link.q->ops->peek(p->link.q);
 }
 
-static unsigned int atm_tc_drop(struct Qdisc *sch)
-{
-	struct atm_qdisc_data *p = qdisc_priv(sch);
-	struct atm_flow_data *flow;
-	unsigned int len;
-
-	pr_debug("atm_tc_drop(sch %p,[qdisc %p])\n", sch, p);
-	list_for_each_entry(flow, &p->flows, list) {
-		if (flow->q->ops->drop && (len = flow->q->ops->drop(flow->q)))
-			return len;
-	}
-	return 0;
-}
-
 static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct atm_qdisc_data *p = qdisc_priv(sch);
@@ -637,7 +623,8 @@
 {
 	struct atm_flow_data *flow = (struct atm_flow_data *)arg;
 
-	if (gnet_stats_copy_basic(d, NULL, &flow->bstats) < 0 ||
+	if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
+				  d, NULL, &flow->bstats) < 0 ||
 	    gnet_stats_copy_queue(d, NULL, &flow->qstats, flow->q->q.qlen) < 0)
 		return -1;
 
@@ -671,7 +658,6 @@
 	.enqueue	= atm_tc_enqueue,
 	.dequeue	= atm_tc_dequeue,
 	.peek		= atm_tc_peek,
-	.drop		= atm_tc_drop,
 	.init		= atm_tc_init,
 	.reset		= atm_tc_reset,
 	.destroy	= atm_tc_destroy,
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index baafddf..a29fd81 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -80,10 +80,6 @@
 	unsigned char		priority;	/* class priority */
 	unsigned char		priority2;	/* priority to be used after overlimit */
 	unsigned char		ewma_log;	/* time constant for idle time calculation */
-	unsigned char		ovl_strategy;
-#ifdef CONFIG_NET_CLS_ACT
-	unsigned char		police;
-#endif
 
 	u32			defmap;
 
@@ -94,10 +90,6 @@
 	u32			avpkt;
 	struct qdisc_rate_table	*R_tab;
 
-	/* Overlimit strategy parameters */
-	void			(*overlimit)(struct cbq_class *cl);
-	psched_tdiff_t		penalty;
-
 	/* General scheduler (WRR) parameters */
 	long			allot;
 	long			quantum;	/* Allotment per WRR round */
@@ -353,7 +345,7 @@
 {
 	int toplevel = q->toplevel;
 
-	if (toplevel > cl->level && !(qdisc_is_throttled(cl->q))) {
+	if (toplevel > cl->level) {
 		psched_time_t now = psched_get_time();
 
 		do {
@@ -382,9 +374,6 @@
 		return ret;
 	}
 
-#ifdef CONFIG_NET_CLS_ACT
-	cl->q->__parent = sch;
-#endif
 	ret = qdisc_enqueue(skb, cl->q);
 	if (ret == NET_XMIT_SUCCESS) {
 		sch->q.qlen++;
@@ -402,11 +391,8 @@
 	return ret;
 }
 
-/* Overlimit actions */
-
-/* TC_CBQ_OVL_CLASSIC: (default) penalize leaf class by adding offtime */
-
-static void cbq_ovl_classic(struct cbq_class *cl)
+/* Overlimit action: penalize leaf class by adding offtime */
+static void cbq_overlimit(struct cbq_class *cl)
 {
 	struct cbq_sched_data *q = qdisc_priv(cl->qdisc);
 	psched_tdiff_t delay = cl->undertime - q->now;
@@ -456,99 +442,6 @@
 	}
 }
 
-/* TC_CBQ_OVL_RCLASSIC: penalize by offtime classes in hierarchy, when
- * they go overlimit
- */
-
-static void cbq_ovl_rclassic(struct cbq_class *cl)
-{
-	struct cbq_sched_data *q = qdisc_priv(cl->qdisc);
-	struct cbq_class *this = cl;
-
-	do {
-		if (cl->level > q->toplevel) {
-			cl = NULL;
-			break;
-		}
-	} while ((cl = cl->borrow) != NULL);
-
-	if (cl == NULL)
-		cl = this;
-	cbq_ovl_classic(cl);
-}
-
-/* TC_CBQ_OVL_DELAY: delay until it will go to underlimit */
-
-static void cbq_ovl_delay(struct cbq_class *cl)
-{
-	struct cbq_sched_data *q = qdisc_priv(cl->qdisc);
-	psched_tdiff_t delay = cl->undertime - q->now;
-
-	if (test_bit(__QDISC_STATE_DEACTIVATED,
-		     &qdisc_root_sleeping(cl->qdisc)->state))
-		return;
-
-	if (!cl->delayed) {
-		psched_time_t sched = q->now;
-		ktime_t expires;
-
-		delay += cl->offtime;
-		if (cl->avgidle < 0)
-			delay -= (-cl->avgidle) - ((-cl->avgidle) >> cl->ewma_log);
-		if (cl->avgidle < cl->minidle)
-			cl->avgidle = cl->minidle;
-		cl->undertime = q->now + delay;
-
-		if (delay > 0) {
-			sched += delay + cl->penalty;
-			cl->penalized = sched;
-			cl->cpriority = TC_CBQ_MAXPRIO;
-			q->pmask |= (1<<TC_CBQ_MAXPRIO);
-
-			expires = ns_to_ktime(PSCHED_TICKS2NS(sched));
-			if (hrtimer_try_to_cancel(&q->delay_timer) &&
-			    ktime_to_ns(ktime_sub(
-					hrtimer_get_expires(&q->delay_timer),
-					expires)) > 0)
-				hrtimer_set_expires(&q->delay_timer, expires);
-			hrtimer_restart(&q->delay_timer);
-			cl->delayed = 1;
-			cl->xstats.overactions++;
-			return;
-		}
-		delay = 1;
-	}
-	if (q->wd_expires == 0 || q->wd_expires > delay)
-		q->wd_expires = delay;
-}
-
-/* TC_CBQ_OVL_LOWPRIO: penalize class by lowering its priority band */
-
-static void cbq_ovl_lowprio(struct cbq_class *cl)
-{
-	struct cbq_sched_data *q = qdisc_priv(cl->qdisc);
-
-	cl->penalized = q->now + cl->penalty;
-
-	if (cl->cpriority != cl->priority2) {
-		cl->cpriority = cl->priority2;
-		q->pmask |= (1<<cl->cpriority);
-		cl->xstats.overactions++;
-	}
-	cbq_ovl_classic(cl);
-}
-
-/* TC_CBQ_OVL_DROP: penalize class by dropping */
-
-static void cbq_ovl_drop(struct cbq_class *cl)
-{
-	if (cl->q->ops->drop)
-		if (cl->q->ops->drop(cl->q))
-			cl->qdisc->q.qlen--;
-	cl->xstats.overactions++;
-	cbq_ovl_classic(cl);
-}
-
 static psched_tdiff_t cbq_undelay_prio(struct cbq_sched_data *q, int prio,
 				       psched_time_t now)
 {
@@ -620,45 +513,10 @@
 		hrtimer_start(&q->delay_timer, time, HRTIMER_MODE_ABS_PINNED);
 	}
 
-	qdisc_unthrottled(sch);
 	__netif_schedule(qdisc_root(sch));
 	return HRTIMER_NORESTART;
 }
 
-#ifdef CONFIG_NET_CLS_ACT
-static int cbq_reshape_fail(struct sk_buff *skb, struct Qdisc *child)
-{
-	struct Qdisc *sch = child->__parent;
-	struct cbq_sched_data *q = qdisc_priv(sch);
-	struct cbq_class *cl = q->rx_class;
-
-	q->rx_class = NULL;
-
-	if (cl && (cl = cbq_reclassify(skb, cl)) != NULL) {
-		int ret;
-
-		cbq_mark_toplevel(q, cl);
-
-		q->rx_class = cl;
-		cl->q->__parent = sch;
-
-		ret = qdisc_enqueue(skb, cl->q);
-		if (ret == NET_XMIT_SUCCESS) {
-			sch->q.qlen++;
-			if (!cl->next_alive)
-				cbq_activate_class(cl);
-			return 0;
-		}
-		if (net_xmit_drop_count(ret))
-			qdisc_qstats_drop(sch);
-		return 0;
-	}
-
-	qdisc_qstats_drop(sch);
-	return -1;
-}
-#endif
-
 /*
  * It is mission critical procedure.
  *
@@ -807,7 +665,7 @@
 		cl = cl->borrow;
 		if (!cl) {
 			this_cl->qstats.overlimits++;
-			this_cl->overlimit(this_cl);
+			cbq_overlimit(this_cl);
 			return NULL;
 		}
 		if (cl->level > q->toplevel)
@@ -960,7 +818,6 @@
 		if (skb) {
 			qdisc_bstats_update(sch, skb);
 			sch->q.qlen--;
-			qdisc_unthrottled(sch);
 			return skb;
 		}
 
@@ -1166,31 +1023,6 @@
 	}
 }
 
-static unsigned int cbq_drop(struct Qdisc *sch)
-{
-	struct cbq_sched_data *q = qdisc_priv(sch);
-	struct cbq_class *cl, *cl_head;
-	int prio;
-	unsigned int len;
-
-	for (prio = TC_CBQ_MAXPRIO; prio >= 0; prio--) {
-		cl_head = q->active[prio];
-		if (!cl_head)
-			continue;
-
-		cl = cl_head;
-		do {
-			if (cl->q->ops->drop && (len = cl->q->ops->drop(cl->q))) {
-				sch->q.qlen--;
-				if (!cl->q->q.qlen)
-					cbq_deactivate_class(cl);
-				return len;
-			}
-		} while ((cl = cl->next_alive) != cl_head);
-	}
-	return 0;
-}
-
 static void
 cbq_reset(struct Qdisc *sch)
 {
@@ -1280,50 +1112,6 @@
 	return 0;
 }
 
-static int cbq_set_overlimit(struct cbq_class *cl, struct tc_cbq_ovl *ovl)
-{
-	switch (ovl->strategy) {
-	case TC_CBQ_OVL_CLASSIC:
-		cl->overlimit = cbq_ovl_classic;
-		break;
-	case TC_CBQ_OVL_DELAY:
-		cl->overlimit = cbq_ovl_delay;
-		break;
-	case TC_CBQ_OVL_LOWPRIO:
-		if (ovl->priority2 - 1 >= TC_CBQ_MAXPRIO ||
-		    ovl->priority2 - 1 <= cl->priority)
-			return -EINVAL;
-		cl->priority2 = ovl->priority2 - 1;
-		cl->overlimit = cbq_ovl_lowprio;
-		break;
-	case TC_CBQ_OVL_DROP:
-		cl->overlimit = cbq_ovl_drop;
-		break;
-	case TC_CBQ_OVL_RCLASSIC:
-		cl->overlimit = cbq_ovl_rclassic;
-		break;
-	default:
-		return -EINVAL;
-	}
-	cl->penalty = ovl->penalty;
-	return 0;
-}
-
-#ifdef CONFIG_NET_CLS_ACT
-static int cbq_set_police(struct cbq_class *cl, struct tc_cbq_police *p)
-{
-	cl->police = p->police;
-
-	if (cl->q->handle) {
-		if (p->police == TC_POLICE_RECLASSIFY)
-			cl->q->reshape_fail = cbq_reshape_fail;
-		else
-			cl->q->reshape_fail = NULL;
-	}
-	return 0;
-}
-#endif
-
 static int cbq_set_fopt(struct cbq_class *cl, struct tc_cbq_fopt *fopt)
 {
 	cbq_change_defmap(cl, fopt->split, fopt->defmap, fopt->defchange);
@@ -1375,8 +1163,6 @@
 	q->link.priority = TC_CBQ_MAXPRIO - 1;
 	q->link.priority2 = TC_CBQ_MAXPRIO - 1;
 	q->link.cpriority = TC_CBQ_MAXPRIO - 1;
-	q->link.ovl_strategy = TC_CBQ_OVL_CLASSIC;
-	q->link.overlimit = cbq_ovl_classic;
 	q->link.allot = psched_mtu(qdisc_dev(sch));
 	q->link.quantum = q->link.allot;
 	q->link.weight = q->link.R_tab->rate.rate;
@@ -1463,24 +1249,6 @@
 	return -1;
 }
 
-static int cbq_dump_ovl(struct sk_buff *skb, struct cbq_class *cl)
-{
-	unsigned char *b = skb_tail_pointer(skb);
-	struct tc_cbq_ovl opt;
-
-	opt.strategy = cl->ovl_strategy;
-	opt.priority2 = cl->priority2 + 1;
-	opt.pad = 0;
-	opt.penalty = cl->penalty;
-	if (nla_put(skb, TCA_CBQ_OVL_STRATEGY, sizeof(opt), &opt))
-		goto nla_put_failure;
-	return skb->len;
-
-nla_put_failure:
-	nlmsg_trim(skb, b);
-	return -1;
-}
-
 static int cbq_dump_fopt(struct sk_buff *skb, struct cbq_class *cl)
 {
 	unsigned char *b = skb_tail_pointer(skb);
@@ -1500,36 +1268,11 @@
 	return -1;
 }
 
-#ifdef CONFIG_NET_CLS_ACT
-static int cbq_dump_police(struct sk_buff *skb, struct cbq_class *cl)
-{
-	unsigned char *b = skb_tail_pointer(skb);
-	struct tc_cbq_police opt;
-
-	if (cl->police) {
-		opt.police = cl->police;
-		opt.__res1 = 0;
-		opt.__res2 = 0;
-		if (nla_put(skb, TCA_CBQ_POLICE, sizeof(opt), &opt))
-			goto nla_put_failure;
-	}
-	return skb->len;
-
-nla_put_failure:
-	nlmsg_trim(skb, b);
-	return -1;
-}
-#endif
-
 static int cbq_dump_attr(struct sk_buff *skb, struct cbq_class *cl)
 {
 	if (cbq_dump_lss(skb, cl) < 0 ||
 	    cbq_dump_rate(skb, cl) < 0 ||
 	    cbq_dump_wrr(skb, cl) < 0 ||
-	    cbq_dump_ovl(skb, cl) < 0 ||
-#ifdef CONFIG_NET_CLS_ACT
-	    cbq_dump_police(skb, cl) < 0 ||
-#endif
 	    cbq_dump_fopt(skb, cl) < 0)
 		return -1;
 	return 0;
@@ -1600,7 +1343,8 @@
 	if (cl->undertime != PSCHED_PASTPERFECT)
 		cl->xstats.undertime = cl->undertime - q->now;
 
-	if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 ||
+	if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
+				  d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
 	    gnet_stats_copy_queue(d, NULL, &cl->qstats, cl->q->q.qlen) < 0)
 		return -1;
@@ -1618,11 +1362,6 @@
 					&pfifo_qdisc_ops, cl->common.classid);
 		if (new == NULL)
 			return -ENOBUFS;
-	} else {
-#ifdef CONFIG_NET_CLS_ACT
-		if (cl->police == TC_POLICE_RECLASSIFY)
-			new->reshape_fail = cbq_reshape_fail;
-#endif
 	}
 
 	*old = qdisc_replace(sch, new, &cl->q);
@@ -1735,6 +1474,9 @@
 	if (err < 0)
 		return err;
 
+	if (tb[TCA_CBQ_OVL_STRATEGY] || tb[TCA_CBQ_POLICE])
+		return -EOPNOTSUPP;
+
 	if (cl) {
 		/* Check parent */
 		if (parentid) {
@@ -1755,7 +1497,8 @@
 		if (tca[TCA_RATE]) {
 			err = gen_replace_estimator(&cl->bstats, NULL,
 						    &cl->rate_est,
-						    qdisc_root_sleeping_lock(sch),
+						    NULL,
+						    qdisc_root_sleeping_running(sch),
 						    tca[TCA_RATE]);
 			if (err) {
 				qdisc_put_rtab(rtab);
@@ -1782,14 +1525,6 @@
 			cbq_set_wrr(cl, nla_data(tb[TCA_CBQ_WRROPT]));
 		}
 
-		if (tb[TCA_CBQ_OVL_STRATEGY])
-			cbq_set_overlimit(cl, nla_data(tb[TCA_CBQ_OVL_STRATEGY]));
-
-#ifdef CONFIG_NET_CLS_ACT
-		if (tb[TCA_CBQ_POLICE])
-			cbq_set_police(cl, nla_data(tb[TCA_CBQ_POLICE]));
-#endif
-
 		if (tb[TCA_CBQ_FOPT])
 			cbq_set_fopt(cl, nla_data(tb[TCA_CBQ_FOPT]));
 
@@ -1848,7 +1583,8 @@
 
 	if (tca[TCA_RATE]) {
 		err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est,
-					qdisc_root_sleeping_lock(sch),
+					NULL,
+					qdisc_root_sleeping_running(sch),
 					tca[TCA_RATE]);
 		if (err) {
 			kfree(cl);
@@ -1884,13 +1620,6 @@
 		cl->maxidle = q->link.maxidle;
 	if (cl->avpkt == 0)
 		cl->avpkt = q->link.avpkt;
-	cl->overlimit = cbq_ovl_classic;
-	if (tb[TCA_CBQ_OVL_STRATEGY])
-		cbq_set_overlimit(cl, nla_data(tb[TCA_CBQ_OVL_STRATEGY]));
-#ifdef CONFIG_NET_CLS_ACT
-	if (tb[TCA_CBQ_POLICE])
-		cbq_set_police(cl, nla_data(tb[TCA_CBQ_POLICE]));
-#endif
 	if (tb[TCA_CBQ_FOPT])
 		cbq_set_fopt(cl, nla_data(tb[TCA_CBQ_FOPT]));
 	sch_tree_unlock(sch);
@@ -2035,7 +1764,6 @@
 	.enqueue	=	cbq_enqueue,
 	.dequeue	=	cbq_dequeue,
 	.peek		=	qdisc_peek_dequeued,
-	.drop		=	cbq_drop,
 	.init		=	cbq_init,
 	.reset		=	cbq_reset,
 	.destroy	=	cbq_destroy,
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index 0a08c86..789b69e 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -365,22 +365,6 @@
 	return skb;
 }
 
-static unsigned int choke_drop(struct Qdisc *sch)
-{
-	struct choke_sched_data *q = qdisc_priv(sch);
-	unsigned int len;
-
-	len = qdisc_queue_drop(sch);
-	if (len > 0)
-		q->stats.other++;
-	else {
-		if (!red_is_idling(&q->vars))
-			red_start_of_idle_period(&q->vars);
-	}
-
-	return len;
-}
-
 static void choke_reset(struct Qdisc *sch)
 {
 	struct choke_sched_data *q = qdisc_priv(sch);
@@ -391,11 +375,11 @@
 		q->head = (q->head + 1) & q->tab_mask;
 		if (!skb)
 			continue;
-		qdisc_qstats_backlog_dec(sch, skb);
-		--sch->q.qlen;
-		qdisc_drop(skb, sch);
+		rtnl_qdisc_drop(skb, sch);
 	}
 
+	sch->q.qlen = 0;
+	sch->qstats.backlog = 0;
 	memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *));
 	q->head = q->tail = 0;
 	red_restart(&q->vars);
@@ -471,7 +455,7 @@
 				dropped += qdisc_pkt_len(skb);
 				qdisc_qstats_backlog_dec(sch, skb);
 				--sch->q.qlen;
-				qdisc_drop(skb, sch);
+				rtnl_qdisc_drop(skb, sch);
 			}
 			qdisc_tree_reduce_backlog(sch, oqlen - sch->q.qlen, dropped);
 			q->head = 0;
@@ -569,7 +553,6 @@
 	.enqueue	=	choke_enqueue,
 	.dequeue	=	choke_dequeue,
 	.peek		=	choke_peek_head,
-	.drop		=	choke_drop,
 	.init		=	choke_init,
 	.destroy	=	choke_destroy,
 	.reset		=	choke_reset,
diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c
index dddf3bb..c5bc424 100644
--- a/net/sched/sch_codel.c
+++ b/net/sched/sch_codel.c
@@ -174,7 +174,7 @@
 
 		dropped += qdisc_pkt_len(skb);
 		qdisc_qstats_backlog_dec(sch, skb);
-		qdisc_drop(skb, sch);
+		rtnl_qdisc_drop(skb, sch);
 	}
 	qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped);
 
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index a63e879..22609e4 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -91,7 +91,8 @@
 		if (tca[TCA_RATE]) {
 			err = gen_replace_estimator(&cl->bstats, NULL,
 						    &cl->rate_est,
-						    qdisc_root_sleeping_lock(sch),
+						    NULL,
+						    qdisc_root_sleeping_running(sch),
 						    tca[TCA_RATE]);
 			if (err)
 				return err;
@@ -119,7 +120,8 @@
 
 	if (tca[TCA_RATE]) {
 		err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est,
-					    qdisc_root_sleeping_lock(sch),
+					    NULL,
+					    qdisc_root_sleeping_running(sch),
 					    tca[TCA_RATE]);
 		if (err) {
 			qdisc_destroy(cl->qdisc);
@@ -279,7 +281,8 @@
 	if (qlen)
 		xstats.deficit = cl->deficit;
 
-	if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 ||
+	if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
+				  d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
 	    gnet_stats_copy_queue(d, NULL, &cl->qdisc->qstats, qlen) < 0)
 		return -1;
@@ -375,6 +378,7 @@
 		cl->deficit = cl->quantum;
 	}
 
+	qdisc_qstats_backlog_inc(sch, skb);
 	sch->q.qlen++;
 	return err;
 }
@@ -407,6 +411,7 @@
 
 			bstats_update(&cl->bstats, skb);
 			qdisc_bstats_update(sch, skb);
+			qdisc_qstats_backlog_dec(sch, skb);
 			sch->q.qlen--;
 			return skb;
 		}
@@ -418,26 +423,6 @@
 	return NULL;
 }
 
-static unsigned int drr_drop(struct Qdisc *sch)
-{
-	struct drr_sched *q = qdisc_priv(sch);
-	struct drr_class *cl;
-	unsigned int len;
-
-	list_for_each_entry(cl, &q->active, alist) {
-		if (cl->qdisc->ops->drop) {
-			len = cl->qdisc->ops->drop(cl->qdisc);
-			if (len > 0) {
-				sch->q.qlen--;
-				if (cl->qdisc->q.qlen == 0)
-					list_del(&cl->alist);
-				return len;
-			}
-		}
-	}
-	return 0;
-}
-
 static int drr_init_qdisc(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct drr_sched *q = qdisc_priv(sch);
@@ -463,6 +448,7 @@
 			qdisc_reset(cl->qdisc);
 		}
 	}
+	sch->qstats.backlog = 0;
 	sch->q.qlen = 0;
 }
 
@@ -506,7 +492,6 @@
 	.enqueue	= drr_enqueue,
 	.dequeue	= drr_dequeue,
 	.peek		= qdisc_peek_dequeued,
-	.drop		= drr_drop,
 	.init		= drr_init_qdisc,
 	.reset		= drr_reset_qdisc,
 	.destroy	= drr_destroy_qdisc,
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index 34b4dda..b9ba5f6 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -320,23 +320,6 @@
 	return p->q->ops->peek(p->q);
 }
 
-static unsigned int dsmark_drop(struct Qdisc *sch)
-{
-	struct dsmark_qdisc_data *p = qdisc_priv(sch);
-	unsigned int len;
-
-	pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p);
-
-	if (p->q->ops->drop == NULL)
-		return 0;
-
-	len = p->q->ops->drop(p->q);
-	if (len)
-		sch->q.qlen--;
-
-	return len;
-}
-
 static int dsmark_init(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct dsmark_qdisc_data *p = qdisc_priv(sch);
@@ -489,7 +472,6 @@
 	.enqueue	=	dsmark_enqueue,
 	.dequeue	=	dsmark_dequeue,
 	.peek		=	dsmark_peek,
-	.drop		=	dsmark_drop,
 	.init		=	dsmark_init,
 	.reset		=	dsmark_reset,
 	.destroy	=	dsmark_destroy,
diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c
index 2177eac..dea70e3 100644
--- a/net/sched/sch_fifo.c
+++ b/net/sched/sch_fifo.c
@@ -24,7 +24,7 @@
 	if (likely(sch->qstats.backlog + qdisc_pkt_len(skb) <= sch->limit))
 		return qdisc_enqueue_tail(skb, sch);
 
-	return qdisc_reshape_fail(skb, sch);
+	return qdisc_drop(skb, sch);
 }
 
 static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch)
@@ -32,7 +32,7 @@
 	if (likely(skb_queue_len(&sch->q) < sch->limit))
 		return qdisc_enqueue_tail(skb, sch);
 
-	return qdisc_reshape_fail(skb, sch);
+	return qdisc_drop(skb, sch);
 }
 
 static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch)
@@ -99,7 +99,6 @@
 	.enqueue	=	pfifo_enqueue,
 	.dequeue	=	qdisc_dequeue_head,
 	.peek		=	qdisc_peek_head,
-	.drop		=	qdisc_queue_drop,
 	.init		=	fifo_init,
 	.reset		=	qdisc_reset_queue,
 	.change		=	fifo_init,
@@ -114,7 +113,6 @@
 	.enqueue	=	bfifo_enqueue,
 	.dequeue	=	qdisc_dequeue_head,
 	.peek		=	qdisc_peek_head,
-	.drop		=	qdisc_queue_drop,
 	.init		=	fifo_init,
 	.reset		=	qdisc_reset_queue,
 	.change		=	fifo_init,
@@ -129,7 +127,6 @@
 	.enqueue	=	pfifo_tail_enqueue,
 	.dequeue	=	qdisc_dequeue_head,
 	.peek		=	qdisc_peek_head,
-	.drop		=	qdisc_queue_drop_head,
 	.init		=	fifo_init,
 	.reset		=	qdisc_reset_queue,
 	.change		=	fifo_init,
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 3c6a47d..6eb0667 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -445,8 +445,7 @@
 		if (!head->first) {
 			if (q->time_next_delayed_flow != ~0ULL)
 				qdisc_watchdog_schedule_ns(&q->watchdog,
-							   q->time_next_delayed_flow,
-							   false);
+							   q->time_next_delayed_flow);
 			return NULL;
 		}
 	}
@@ -515,17 +514,25 @@
 	return skb;
 }
 
+static void fq_flow_purge(struct fq_flow *flow)
+{
+	rtnl_kfree_skbs(flow->head, flow->tail);
+	flow->head = NULL;
+	flow->qlen = 0;
+}
+
 static void fq_reset(struct Qdisc *sch)
 {
 	struct fq_sched_data *q = qdisc_priv(sch);
 	struct rb_root *root;
-	struct sk_buff *skb;
 	struct rb_node *p;
 	struct fq_flow *f;
 	unsigned int idx;
 
-	while ((skb = fq_dequeue_head(sch, &q->internal)) != NULL)
-		kfree_skb(skb);
+	sch->q.qlen = 0;
+	sch->qstats.backlog = 0;
+
+	fq_flow_purge(&q->internal);
 
 	if (!q->fq_root)
 		return;
@@ -536,8 +543,7 @@
 			f = container_of(p, struct fq_flow, fq_node);
 			rb_erase(p, root);
 
-			while ((skb = fq_dequeue_head(sch, f)) != NULL)
-				kfree_skb(skb);
+			fq_flow_purge(f);
 
 			kmem_cache_free(fq_flow_cachep, f);
 		}
@@ -738,7 +744,7 @@
 		if (!skb)
 			break;
 		drop_len += qdisc_pkt_len(skb);
-		kfree_skb(skb);
+		rtnl_kfree_skbs(skb, skb);
 		drop_count++;
 	}
 	qdisc_tree_reduce_backlog(sch, drop_count, drop_len);
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 6883a89..2dc0a84 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -184,21 +184,13 @@
 	return idx;
 }
 
-static unsigned int fq_codel_qdisc_drop(struct Qdisc *sch)
-{
-	unsigned int prev_backlog;
-
-	prev_backlog = sch->qstats.backlog;
-	fq_codel_drop(sch, 1U);
-	return prev_backlog - sch->qstats.backlog;
-}
-
 static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 {
 	struct fq_codel_sched_data *q = qdisc_priv(sch);
 	unsigned int idx, prev_backlog, prev_qlen;
 	struct fq_codel_flow *flow;
 	int uninitialized_var(ret);
+	unsigned int pkt_len;
 	bool memory_limited;
 
 	idx = fq_codel_classify(skb, sch, &ret);
@@ -230,6 +222,8 @@
 	prev_backlog = sch->qstats.backlog;
 	prev_qlen = sch->q.qlen;
 
+	/* save this packet length as it might be dropped by fq_codel_drop() */
+	pkt_len = qdisc_pkt_len(skb);
 	/* fq_codel_drop() is quite expensive, as it performs a linear search
 	 * in q->backlogs[] to find a fat flow.
 	 * So instead of dropping a single packet, drop half of its backlog
@@ -237,14 +231,23 @@
 	 */
 	ret = fq_codel_drop(sch, q->drop_batch_size);
 
-	q->drop_overlimit += prev_qlen - sch->q.qlen;
+	prev_qlen -= sch->q.qlen;
+	prev_backlog -= sch->qstats.backlog;
+	q->drop_overlimit += prev_qlen;
 	if (memory_limited)
-		q->drop_overmemory += prev_qlen - sch->q.qlen;
-	/* As we dropped packet(s), better let upper stack know this */
-	qdisc_tree_reduce_backlog(sch, prev_qlen - sch->q.qlen,
-				  prev_backlog - sch->qstats.backlog);
+		q->drop_overmemory += prev_qlen;
 
-	return ret == idx ? NET_XMIT_CN : NET_XMIT_SUCCESS;
+	/* As we dropped packet(s), better let upper stack know this.
+	 * If we dropped a packet for this flow, return NET_XMIT_CN,
+	 * but in this case, our parents wont increase their backlogs.
+	 */
+	if (ret == idx) {
+		qdisc_tree_reduce_backlog(sch, prev_qlen - 1,
+					  prev_backlog - pkt_len);
+		return NET_XMIT_CN;
+	}
+	qdisc_tree_reduce_backlog(sch, prev_qlen, prev_backlog);
+	return NET_XMIT_SUCCESS;
 }
 
 /* This is the specific function called from codel_dequeue()
@@ -333,6 +336,12 @@
 	return skb;
 }
 
+static void fq_codel_flow_purge(struct fq_codel_flow *flow)
+{
+	rtnl_kfree_skbs(flow->head, flow->tail);
+	flow->head = NULL;
+}
+
 static void fq_codel_reset(struct Qdisc *sch)
 {
 	struct fq_codel_sched_data *q = qdisc_priv(sch);
@@ -343,18 +352,13 @@
 	for (i = 0; i < q->flows_cnt; i++) {
 		struct fq_codel_flow *flow = q->flows + i;
 
-		while (flow->head) {
-			struct sk_buff *skb = dequeue_head(flow);
-
-			qdisc_qstats_backlog_dec(sch, skb);
-			kfree_skb(skb);
-		}
-
+		fq_codel_flow_purge(flow);
 		INIT_LIST_HEAD(&flow->flowchain);
 		codel_vars_init(&flow->cvars);
 	}
 	memset(q->backlogs, 0, q->flows_cnt * sizeof(u32));
 	sch->q.qlen = 0;
+	sch->qstats.backlog = 0;
 	q->memory_usage = 0;
 }
 
@@ -430,7 +434,7 @@
 		struct sk_buff *skb = fq_codel_dequeue(sch);
 
 		q->cstats.drop_len += qdisc_pkt_len(skb);
-		kfree_skb(skb);
+		rtnl_kfree_skbs(skb, skb);
 		q->cstats.drop_count++;
 	}
 	qdisc_tree_reduce_backlog(sch, q->cstats.drop_count, q->cstats.drop_len);
@@ -566,11 +570,13 @@
 	st.qdisc_stats.memory_usage  = q->memory_usage;
 	st.qdisc_stats.drop_overmemory = q->drop_overmemory;
 
+	sch_tree_lock(sch);
 	list_for_each(pos, &q->new_flows)
 		st.qdisc_stats.new_flows_len++;
 
 	list_for_each(pos, &q->old_flows)
 		st.qdisc_stats.old_flows_len++;
+	sch_tree_unlock(sch);
 
 	return gnet_stats_copy_app(d, &st, sizeof(st));
 }
@@ -624,7 +630,7 @@
 
 	if (idx < q->flows_cnt) {
 		const struct fq_codel_flow *flow = &q->flows[idx];
-		const struct sk_buff *skb = flow->head;
+		const struct sk_buff *skb;
 
 		memset(&xstats, 0, sizeof(xstats));
 		xstats.type = TCA_FQ_CODEL_XSTATS_CLASS;
@@ -642,14 +648,19 @@
 				codel_time_to_us(delta) :
 				-codel_time_to_us(-delta);
 		}
-		while (skb) {
-			qs.qlen++;
-			skb = skb->next;
+		if (flow->head) {
+			sch_tree_lock(sch);
+			skb = flow->head;
+			while (skb) {
+				qs.qlen++;
+				skb = skb->next;
+			}
+			sch_tree_unlock(sch);
 		}
 		qs.backlog = q->backlogs[idx];
 		qs.drops = flow->dropped;
 	}
-	if (gnet_stats_copy_queue(d, NULL, &qs, 0) < 0)
+	if (gnet_stats_copy_queue(d, NULL, &qs, qs.qlen) < 0)
 		return -1;
 	if (idx < q->flows_cnt)
 		return gnet_stats_copy_app(d, &xstats, sizeof(xstats));
@@ -697,7 +708,6 @@
 	.enqueue	=	fq_codel_enqueue,
 	.dequeue	=	fq_codel_dequeue,
 	.peek		=	qdisc_peek_dequeued,
-	.drop		=	fq_codel_qdisc_drop,
 	.init		=	fq_codel_init,
 	.reset		=	fq_codel_reset,
 	.destroy	=	fq_codel_destroy,
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 269dd71..773b632 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -49,6 +49,7 @@
 {
 	q->gso_skb = skb;
 	q->qstats.requeues++;
+	qdisc_qstats_backlog_inc(q, skb);
 	q->q.qlen++;	/* it's still part of the queue */
 	__netif_schedule(q);
 
@@ -92,6 +93,7 @@
 		txq = skb_get_tx_queue(txq->dev, skb);
 		if (!netif_xmit_frozen_or_stopped(txq)) {
 			q->gso_skb = NULL;
+			qdisc_qstats_backlog_dec(q, skb);
 			q->q.qlen--;
 		} else
 			skb = NULL;
@@ -110,7 +112,7 @@
 
 /*
  * Transmit possibly several skbs, and handle the return status as
- * required. Holding the __QDISC___STATE_RUNNING bit guarantees that
+ * required. Owning running seqcount bit guarantees that
  * only one CPU can execute this function.
  *
  * Returns to the caller:
@@ -163,7 +165,7 @@
 /*
  * NOTE: Called under qdisc_lock(q) with locally disabled BH.
  *
- * __QDISC___STATE_RUNNING guarantees only one CPU can process
+ * running seqcount guarantees only one CPU can process
  * this qdisc at a time. qdisc_lock(q) serializes queue accesses for
  * this queue.
  *
@@ -379,6 +381,7 @@
 	.list		=	LIST_HEAD_INIT(noop_qdisc.list),
 	.q.lock		=	__SPIN_LOCK_UNLOCKED(noop_qdisc.q.lock),
 	.dev_queue	=	&noop_netdev_queue,
+	.running	=	SEQCNT_ZERO(noop_qdisc.running),
 	.busylock	=	__SPIN_LOCK_UNLOCKED(noop_qdisc.busylock),
 };
 EXPORT_SYMBOL(noop_qdisc);
@@ -490,7 +493,7 @@
 	struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
 
 	for (prio = 0; prio < PFIFO_FAST_BANDS; prio++)
-		__qdisc_reset_queue(qdisc, band2list(priv, prio));
+		__qdisc_reset_queue(band2list(priv, prio));
 
 	priv->bitmap = 0;
 	qdisc->qstats.backlog = 0;
@@ -537,6 +540,7 @@
 EXPORT_SYMBOL(pfifo_fast_ops);
 
 static struct lock_class_key qdisc_tx_busylock;
+static struct lock_class_key qdisc_running_key;
 
 struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 			  const struct Qdisc_ops *ops)
@@ -570,6 +574,10 @@
 	lockdep_set_class(&sch->busylock,
 			  dev->qdisc_tx_busylock ?: &qdisc_tx_busylock);
 
+	seqcount_init(&sch->running);
+	lockdep_set_class(&sch->running,
+			  dev->qdisc_running_key ?: &qdisc_running_key);
+
 	sch->ops = ops;
 	sch->enqueue = ops->enqueue;
 	sch->dequeue = ops->dequeue;
diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index 8010510..b5fb63c7 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -276,40 +276,6 @@
 	return NULL;
 }
 
-static unsigned int gred_drop(struct Qdisc *sch)
-{
-	struct sk_buff *skb;
-	struct gred_sched *t = qdisc_priv(sch);
-
-	skb = qdisc_dequeue_tail(sch);
-	if (skb) {
-		unsigned int len = qdisc_pkt_len(skb);
-		struct gred_sched_data *q;
-		u16 dp = tc_index_to_dp(skb);
-
-		if (dp >= t->DPs || (q = t->tab[dp]) == NULL) {
-			net_warn_ratelimited("GRED: Unable to relocate VQ 0x%x while dropping, screwing up backlog\n",
-					     tc_index_to_dp(skb));
-		} else {
-			q->backlog -= len;
-			q->stats.other++;
-
-			if (gred_wred_mode(t)) {
-				if (!sch->qstats.backlog)
-					red_start_of_idle_period(&t->wred_set);
-			} else {
-				if (!q->backlog)
-					red_start_of_idle_period(&q->vars);
-			}
-		}
-
-		qdisc_drop(skb, sch);
-		return len;
-	}
-
-	return 0;
-}
-
 static void gred_reset(struct Qdisc *sch)
 {
 	int i;
@@ -623,7 +589,6 @@
 	.enqueue	=	gred_enqueue,
 	.dequeue	=	gred_dequeue,
 	.peek		=	qdisc_peek_head,
-	.drop		=	gred_drop,
 	.init		=	gred_init,
 	.reset		=	gred_reset,
 	.destroy	=	gred_destroy,
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index d783d7c..bd08c36 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1015,11 +1015,10 @@
 		cur_time = psched_get_time();
 
 		if (tca[TCA_RATE]) {
-			spinlock_t *lock = qdisc_root_sleeping_lock(sch);
-
 			err = gen_replace_estimator(&cl->bstats, NULL,
 						    &cl->rate_est,
-						    lock,
+						    NULL,
+						    qdisc_root_sleeping_running(sch),
 						    tca[TCA_RATE]);
 			if (err)
 				return err;
@@ -1068,7 +1067,8 @@
 
 	if (tca[TCA_RATE]) {
 		err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est,
-					qdisc_root_sleeping_lock(sch),
+					NULL,
+					qdisc_root_sleeping_running(sch),
 					tca[TCA_RATE]);
 		if (err) {
 			kfree(cl);
@@ -1373,7 +1373,7 @@
 	xstats.work    = cl->cl_total;
 	xstats.rtwork  = cl->cl_cumul;
 
-	if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 ||
+	if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
 	    gnet_stats_copy_queue(d, NULL, &cl->qstats, cl->qdisc->q.qlen) < 0)
 		return -1;
@@ -1529,6 +1529,7 @@
 	q->eligible = RB_ROOT;
 	INIT_LIST_HEAD(&q->droplist);
 	qdisc_watchdog_cancel(&q->watchdog);
+	sch->qstats.backlog = 0;
 	sch->q.qlen = 0;
 }
 
@@ -1559,14 +1560,6 @@
 	struct hfsc_sched *q = qdisc_priv(sch);
 	unsigned char *b = skb_tail_pointer(skb);
 	struct tc_hfsc_qopt qopt;
-	struct hfsc_class *cl;
-	unsigned int i;
-
-	sch->qstats.backlog = 0;
-	for (i = 0; i < q->clhash.hashsize; i++) {
-		hlist_for_each_entry(cl, &q->clhash.hash[i], cl_common.hnode)
-			sch->qstats.backlog += cl->qdisc->qstats.backlog;
-	}
 
 	qopt.defcls = q->defcls;
 	if (nla_put(skb, TCA_OPTIONS, sizeof(qopt), &qopt))
@@ -1604,6 +1597,7 @@
 	if (cl->qdisc->q.qlen == 1)
 		set_active(cl, qdisc_pkt_len(skb));
 
+	qdisc_qstats_backlog_inc(sch, skb);
 	sch->q.qlen++;
 
 	return NET_XMIT_SUCCESS;
@@ -1670,38 +1664,13 @@
 		set_passive(cl);
 	}
 
-	qdisc_unthrottled(sch);
 	qdisc_bstats_update(sch, skb);
+	qdisc_qstats_backlog_dec(sch, skb);
 	sch->q.qlen--;
 
 	return skb;
 }
 
-static unsigned int
-hfsc_drop(struct Qdisc *sch)
-{
-	struct hfsc_sched *q = qdisc_priv(sch);
-	struct hfsc_class *cl;
-	unsigned int len;
-
-	list_for_each_entry(cl, &q->droplist, dlist) {
-		if (cl->qdisc->ops->drop != NULL &&
-		    (len = cl->qdisc->ops->drop(cl->qdisc)) > 0) {
-			if (cl->qdisc->q.qlen == 0) {
-				update_vf(cl, 0, 0);
-				set_passive(cl);
-			} else {
-				list_move_tail(&cl->dlist, &q->droplist);
-			}
-			cl->qstats.drops++;
-			qdisc_qstats_drop(sch);
-			sch->q.qlen--;
-			return len;
-		}
-	}
-	return 0;
-}
-
 static const struct Qdisc_class_ops hfsc_class_ops = {
 	.change		= hfsc_change_class,
 	.delete		= hfsc_delete_class,
@@ -1728,7 +1697,6 @@
 	.enqueue	= hfsc_enqueue,
 	.dequeue	= hfsc_dequeue,
 	.peek		= qdisc_peek_dequeued,
-	.drop		= hfsc_drop,
 	.cl_ops		= &hfsc_class_ops,
 	.priv_size	= sizeof(struct hfsc_sched),
 	.owner		= THIS_MODULE
diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c
index 13d6f83..c44593b 100644
--- a/net/sched/sch_hhf.c
+++ b/net/sched/sch_hhf.c
@@ -368,15 +368,6 @@
 	return bucket - q->buckets;
 }
 
-static unsigned int hhf_qdisc_drop(struct Qdisc *sch)
-{
-	unsigned int prev_backlog;
-
-	prev_backlog = sch->qstats.backlog;
-	hhf_drop(sch);
-	return prev_backlog - sch->qstats.backlog;
-}
-
 static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 {
 	struct hhf_sched_data *q = qdisc_priv(sch);
@@ -473,7 +464,7 @@
 	struct sk_buff *skb;
 
 	while ((skb = hhf_dequeue(sch)) != NULL)
-		kfree_skb(skb);
+		rtnl_kfree_skbs(skb, skb);
 }
 
 static void *hhf_zalloc(size_t sz)
@@ -583,7 +574,7 @@
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = hhf_dequeue(sch);
 
-		kfree_skb(skb);
+		rtnl_kfree_skbs(skb, skb);
 	}
 	qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen,
 				  prev_backlog - sch->qstats.backlog);
@@ -709,7 +700,6 @@
 	.enqueue	=	hhf_enqueue,
 	.dequeue	=	hhf_dequeue,
 	.peek		=	qdisc_peek_dequeued,
-	.drop		=	hhf_qdisc_drop,
 	.init		=	hhf_init,
 	.reset		=	hhf_reset,
 	.destroy	=	hhf_destroy,
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index d4b4218..a454605 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -889,7 +889,6 @@
 	if (skb != NULL) {
 ok:
 		qdisc_bstats_update(sch, skb);
-		qdisc_unthrottled(sch);
 		qdisc_qstats_backlog_dec(sch, skb);
 		sch->q.qlen--;
 		return skb;
@@ -929,38 +928,13 @@
 	}
 	qdisc_qstats_overlimit(sch);
 	if (likely(next_event > q->now))
-		qdisc_watchdog_schedule_ns(&q->watchdog, next_event, true);
+		qdisc_watchdog_schedule_ns(&q->watchdog, next_event);
 	else
 		schedule_work(&q->work);
 fin:
 	return skb;
 }
 
-/* try to drop from each class (by prio) until one succeed */
-static unsigned int htb_drop(struct Qdisc *sch)
-{
-	struct htb_sched *q = qdisc_priv(sch);
-	int prio;
-
-	for (prio = TC_HTB_NUMPRIO - 1; prio >= 0; prio--) {
-		struct list_head *p;
-		list_for_each(p, q->drops + prio) {
-			struct htb_class *cl = list_entry(p, struct htb_class,
-							  un.leaf.drop_list);
-			unsigned int len;
-			if (cl->un.leaf.q->ops->drop &&
-			    (len = cl->un.leaf.q->ops->drop(cl->un.leaf.q))) {
-				sch->qstats.backlog -= len;
-				sch->q.qlen--;
-				if (!cl->un.leaf.q->q.qlen)
-					htb_deactivate(q, cl);
-				return len;
-			}
-		}
-	}
-	return 0;
-}
-
 /* reset all classes */
 /* always caled under BH & queue lock */
 static void htb_reset(struct Qdisc *sch)
@@ -983,7 +957,7 @@
 		}
 	}
 	qdisc_watchdog_cancel(&q->watchdog);
-	__skb_queue_purge(&q->direct_queue);
+	__qdisc_reset_queue(&q->direct_queue);
 	sch->q.qlen = 0;
 	sch->qstats.backlog = 0;
 	memset(q->hlevel, 0, sizeof(q->hlevel));
@@ -1141,7 +1115,8 @@
 	cl->xstats.tokens = PSCHED_NS2TICKS(cl->tokens);
 	cl->xstats.ctokens = PSCHED_NS2TICKS(cl->ctokens);
 
-	if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 ||
+	if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
+				  d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, NULL, &cl->rate_est) < 0 ||
 	    gnet_stats_copy_queue(d, NULL, &cl->qstats, qlen) < 0)
 		return -1;
@@ -1256,7 +1231,7 @@
 			htb_destroy_class(sch, cl);
 	}
 	qdisc_class_hash_destroy(&q->clhash);
-	__skb_queue_purge(&q->direct_queue);
+	__qdisc_reset_queue(&q->direct_queue);
 }
 
 static int htb_delete(struct Qdisc *sch, unsigned long arg)
@@ -1395,7 +1370,8 @@
 		if (htb_rate_est || tca[TCA_RATE]) {
 			err = gen_new_estimator(&cl->bstats, NULL,
 						&cl->rate_est,
-						qdisc_root_sleeping_lock(sch),
+						NULL,
+						qdisc_root_sleeping_running(sch),
 						tca[TCA_RATE] ? : &est.nla);
 			if (err) {
 				kfree(cl);
@@ -1457,11 +1433,10 @@
 			parent->children++;
 	} else {
 		if (tca[TCA_RATE]) {
-			spinlock_t *lock = qdisc_root_sleeping_lock(sch);
-
 			err = gen_replace_estimator(&cl->bstats, NULL,
 						    &cl->rate_est,
-						    lock,
+						    NULL,
+						    qdisc_root_sleeping_running(sch),
 						    tca[TCA_RATE]);
 			if (err)
 				return err;
@@ -1599,7 +1574,6 @@
 	.enqueue	=	htb_enqueue,
 	.dequeue	=	htb_dequeue,
 	.peek		=	qdisc_peek_dequeued,
-	.drop		=	htb_drop,
 	.init		=	htb_init,
 	.reset		=	htb_reset,
 	.destroy	=	htb_destroy,
diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c
index 10adbc6..8fe6999 100644
--- a/net/sched/sch_ingress.c
+++ b/net/sched/sch_ingress.c
@@ -27,6 +27,11 @@
 	return TC_H_MIN(classid) + 1;
 }
 
+static bool ingress_cl_offload(u32 classid)
+{
+	return true;
+}
+
 static unsigned long ingress_bind_filter(struct Qdisc *sch,
 					 unsigned long parent, u32 classid)
 {
@@ -86,6 +91,7 @@
 	.put		=	ingress_put,
 	.walk		=	ingress_walk,
 	.tcf_chain	=	ingress_find_tcf,
+	.tcf_cl_offload	=	ingress_cl_offload,
 	.bind_tcf	=	ingress_bind_filter,
 	.unbind_tcf	=	ingress_put,
 };
@@ -110,6 +116,11 @@
 	}
 }
 
+static bool clsact_cl_offload(u32 classid)
+{
+	return TC_H_MIN(classid) == TC_H_MIN(TC_H_MIN_INGRESS);
+}
+
 static unsigned long clsact_bind_filter(struct Qdisc *sch,
 					unsigned long parent, u32 classid)
 {
@@ -158,6 +169,7 @@
 	.put		=	ingress_put,
 	.walk		=	ingress_walk,
 	.tcf_chain	=	clsact_find_tcf,
+	.tcf_cl_offload	=	clsact_cl_offload,
 	.bind_tcf	=	clsact_bind_filter,
 	.unbind_tcf	=	ingress_put,
 };
diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index 56a77b8..b943982 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -199,7 +199,7 @@
 	struct netdev_queue *dev_queue = mq_queue_get(sch, cl);
 
 	sch = dev_queue->qdisc_sleeping;
-	if (gnet_stats_copy_basic(d, NULL, &sch->bstats) < 0 ||
+	if (gnet_stats_copy_basic(&sch->running, d, NULL, &sch->bstats) < 0 ||
 	    gnet_stats_copy_queue(d, NULL, &sch->qstats, sch->q.qlen) < 0)
 		return -1;
 	return 0;
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index b8002ce..549c663 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -342,7 +342,8 @@
 		 * hold here is the look on dev_queue->qdisc_sleeping
 		 * also acquired below.
 		 */
-		spin_unlock_bh(d->lock);
+		if (d->lock)
+			spin_unlock_bh(d->lock);
 
 		for (i = tc.offset; i < tc.offset + tc.count; i++) {
 			struct netdev_queue *q = netdev_get_tx_queue(dev, i);
@@ -359,15 +360,17 @@
 			spin_unlock_bh(qdisc_lock(qdisc));
 		}
 		/* Reclaim root sleeping lock before completing stats */
-		spin_lock_bh(d->lock);
-		if (gnet_stats_copy_basic(d, NULL, &bstats) < 0 ||
+		if (d->lock)
+			spin_lock_bh(d->lock);
+		if (gnet_stats_copy_basic(NULL, d, NULL, &bstats) < 0 ||
 		    gnet_stats_copy_queue(d, NULL, &qstats, qlen) < 0)
 			return -1;
 	} else {
 		struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl);
 
 		sch = dev_queue->qdisc_sleeping;
-		if (gnet_stats_copy_basic(d, NULL, &sch->bstats) < 0 ||
+		if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
+					  d, NULL, &sch->bstats) < 0 ||
 		    gnet_stats_copy_queue(d, NULL,
 					  &sch->qstats, sch->q.qlen) < 0)
 			return -1;
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index bcdd54b..5ea9330 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -151,27 +151,6 @@
 
 }
 
-static unsigned int multiq_drop(struct Qdisc *sch)
-{
-	struct multiq_sched_data *q = qdisc_priv(sch);
-	int band;
-	unsigned int len;
-	struct Qdisc *qdisc;
-
-	for (band = q->bands - 1; band >= 0; band--) {
-		qdisc = q->queues[band];
-		if (qdisc->ops->drop) {
-			len = qdisc->ops->drop(qdisc);
-			if (len != 0) {
-				sch->q.qlen--;
-				return len;
-			}
-		}
-	}
-	return 0;
-}
-
-
 static void
 multiq_reset(struct Qdisc *sch)
 {
@@ -356,7 +335,8 @@
 	struct Qdisc *cl_q;
 
 	cl_q = q->queues[cl - 1];
-	if (gnet_stats_copy_basic(d, NULL, &cl_q->bstats) < 0 ||
+	if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
+				  d, NULL, &cl_q->bstats) < 0 ||
 	    gnet_stats_copy_queue(d, NULL, &cl_q->qstats, cl_q->q.qlen) < 0)
 		return -1;
 
@@ -415,7 +395,6 @@
 	.enqueue	=	multiq_enqueue,
 	.dequeue	=	multiq_dequeue,
 	.peek		=	multiq_peek,
-	.drop		=	multiq_drop,
 	.init		=	multiq_init,
 	.reset		=	multiq_reset,
 	.destroy	=	multiq_destroy,
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 205bed0..e271967 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -368,9 +368,7 @@
 		struct sk_buff *skb = netem_rb_to_skb(p);
 
 		rb_erase(p, &q->t_root);
-		skb->next = NULL;
-		skb->prev = NULL;
-		kfree_skb(skb);
+		rtnl_kfree_skbs(skb, skb);
 	}
 }
 
@@ -407,7 +405,7 @@
 	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
 
 	if (IS_ERR_OR_NULL(segs)) {
-		qdisc_reshape_fail(skb, sch);
+		qdisc_drop(skb, sch);
 		return NULL;
 	}
 	consume_skb(skb);
@@ -499,7 +497,7 @@
 	}
 
 	if (unlikely(skb_queue_len(&sch->q) >= sch->limit))
-		return qdisc_reshape_fail(skb, sch);
+		return qdisc_drop(skb, sch);
 
 	qdisc_qstats_backlog_inc(sch, skb);
 
@@ -576,50 +574,17 @@
 	return NET_XMIT_SUCCESS;
 }
 
-static unsigned int netem_drop(struct Qdisc *sch)
-{
-	struct netem_sched_data *q = qdisc_priv(sch);
-	unsigned int len;
-
-	len = qdisc_queue_drop(sch);
-
-	if (!len) {
-		struct rb_node *p = rb_first(&q->t_root);
-
-		if (p) {
-			struct sk_buff *skb = netem_rb_to_skb(p);
-
-			rb_erase(p, &q->t_root);
-			sch->q.qlen--;
-			skb->next = NULL;
-			skb->prev = NULL;
-			qdisc_qstats_backlog_dec(sch, skb);
-			kfree_skb(skb);
-		}
-	}
-	if (!len && q->qdisc && q->qdisc->ops->drop)
-	    len = q->qdisc->ops->drop(q->qdisc);
-	if (len)
-		qdisc_qstats_drop(sch);
-
-	return len;
-}
-
 static struct sk_buff *netem_dequeue(struct Qdisc *sch)
 {
 	struct netem_sched_data *q = qdisc_priv(sch);
 	struct sk_buff *skb;
 	struct rb_node *p;
 
-	if (qdisc_is_throttled(sch))
-		return NULL;
-
 tfifo_dequeue:
 	skb = __skb_dequeue(&sch->q);
 	if (skb) {
 		qdisc_qstats_backlog_dec(sch, skb);
 deliver:
-		qdisc_unthrottled(sch);
 		qdisc_bstats_update(sch, skb);
 		return skb;
 	}
@@ -1143,7 +1108,6 @@
 	.enqueue	=	netem_enqueue,
 	.dequeue	=	netem_dequeue,
 	.peek		=	qdisc_peek_dequeued,
-	.drop		=	netem_drop,
 	.init		=	netem_init,
 	.reset		=	netem_reset,
 	.destroy	=	netem_destroy,
diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c
index 71ae3b9..912a46a 100644
--- a/net/sched/sch_pie.c
+++ b/net/sched/sch_pie.c
@@ -234,7 +234,7 @@
 
 		dropped += qdisc_pkt_len(skb);
 		qdisc_qstats_backlog_dec(sch, skb);
-		qdisc_drop(skb, sch);
+		rtnl_qdisc_drop(skb, sch);
 	}
 	qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped);
 
diff --git a/net/sched/sch_plug.c b/net/sched/sch_plug.c
index 5abfe44..a12cd37 100644
--- a/net/sched/sch_plug.c
+++ b/net/sched/sch_plug.c
@@ -64,6 +64,8 @@
 	 */
 	bool unplug_indefinite;
 
+	bool throttled;
+
 	/* Queue Limit in bytes */
 	u32 limit;
 
@@ -96,14 +98,14 @@
 		return qdisc_enqueue_tail(skb, sch);
 	}
 
-	return qdisc_reshape_fail(skb, sch);
+	return qdisc_drop(skb, sch);
 }
 
 static struct sk_buff *plug_dequeue(struct Qdisc *sch)
 {
 	struct plug_sched_data *q = qdisc_priv(sch);
 
-	if (qdisc_is_throttled(sch))
+	if (q->throttled)
 		return NULL;
 
 	if (!q->unplug_indefinite) {
@@ -111,7 +113,7 @@
 			/* No more packets to dequeue. Block the queue
 			 * and wait for the next release command.
 			 */
-			qdisc_throttled(sch);
+			q->throttled = true;
 			return NULL;
 		}
 		q->pkts_to_release--;
@@ -141,7 +143,7 @@
 		q->limit = ctl->limit;
 	}
 
-	qdisc_throttled(sch);
+	q->throttled = true;
 	return 0;
 }
 
@@ -173,7 +175,7 @@
 		q->pkts_last_epoch = q->pkts_current_epoch;
 		q->pkts_current_epoch = 0;
 		if (q->unplug_indefinite)
-			qdisc_throttled(sch);
+			q->throttled = true;
 		q->unplug_indefinite = false;
 		break;
 	case TCQ_PLUG_RELEASE_ONE:
@@ -182,7 +184,7 @@
 		 */
 		q->pkts_to_release += q->pkts_last_epoch;
 		q->pkts_last_epoch = 0;
-		qdisc_unthrottled(sch);
+		q->throttled = false;
 		netif_schedule_queue(sch->dev_queue);
 		break;
 	case TCQ_PLUG_RELEASE_INDEFINITE:
@@ -190,7 +192,7 @@
 		q->pkts_to_release = 0;
 		q->pkts_last_epoch = 0;
 		q->pkts_current_epoch = 0;
-		qdisc_unthrottled(sch);
+		q->throttled = false;
 		netif_schedule_queue(sch->dev_queue);
 		break;
 	case TCQ_PLUG_LIMIT:
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index fee1b15..de49268 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -85,6 +85,7 @@
 
 	ret = qdisc_enqueue(skb, qdisc);
 	if (ret == NET_XMIT_SUCCESS) {
+		qdisc_qstats_backlog_inc(sch, skb);
 		sch->q.qlen++;
 		return NET_XMIT_SUCCESS;
 	}
@@ -117,6 +118,7 @@
 		struct sk_buff *skb = qdisc_dequeue_peeked(qdisc);
 		if (skb) {
 			qdisc_bstats_update(sch, skb);
+			qdisc_qstats_backlog_dec(sch, skb);
 			sch->q.qlen--;
 			return skb;
 		}
@@ -125,24 +127,6 @@
 
 }
 
-static unsigned int prio_drop(struct Qdisc *sch)
-{
-	struct prio_sched_data *q = qdisc_priv(sch);
-	int prio;
-	unsigned int len;
-	struct Qdisc *qdisc;
-
-	for (prio = q->bands-1; prio >= 0; prio--) {
-		qdisc = q->queues[prio];
-		if (qdisc->ops->drop && (len = qdisc->ops->drop(qdisc)) != 0) {
-			sch->q.qlen--;
-			return len;
-		}
-	}
-	return 0;
-}
-
-
 static void
 prio_reset(struct Qdisc *sch)
 {
@@ -151,6 +135,7 @@
 
 	for (prio = 0; prio < q->bands; prio++)
 		qdisc_reset(q->queues[prio]);
+	sch->qstats.backlog = 0;
 	sch->q.qlen = 0;
 }
 
@@ -319,7 +304,8 @@
 	struct Qdisc *cl_q;
 
 	cl_q = q->queues[cl - 1];
-	if (gnet_stats_copy_basic(d, NULL, &cl_q->bstats) < 0 ||
+	if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
+				  d, NULL, &cl_q->bstats) < 0 ||
 	    gnet_stats_copy_queue(d, NULL, &cl_q->qstats, cl_q->q.qlen) < 0)
 		return -1;
 
@@ -378,7 +364,6 @@
 	.enqueue	=	prio_enqueue,
 	.dequeue	=	prio_dequeue,
 	.peek		=	prio_peek,
-	.drop		=	prio_drop,
 	.init		=	prio_init,
 	.reset		=	prio_reset,
 	.destroy	=	prio_destroy,
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 8d2d8d9..0427fa8 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -460,7 +460,8 @@
 		if (tca[TCA_RATE]) {
 			err = gen_replace_estimator(&cl->bstats, NULL,
 						    &cl->rate_est,
-						    qdisc_root_sleeping_lock(sch),
+						    NULL,
+						    qdisc_root_sleeping_running(sch),
 						    tca[TCA_RATE]);
 			if (err)
 				return err;
@@ -486,7 +487,8 @@
 	if (tca[TCA_RATE]) {
 		err = gen_new_estimator(&cl->bstats, NULL,
 					&cl->rate_est,
-					qdisc_root_sleeping_lock(sch),
+					NULL,
+					qdisc_root_sleeping_running(sch),
 					tca[TCA_RATE]);
 		if (err)
 			goto destroy_class;
@@ -663,7 +665,8 @@
 	xstats.weight = cl->agg->class_weight;
 	xstats.lmax = cl->agg->lmax;
 
-	if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 ||
+	if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
+				  d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
 	    gnet_stats_copy_queue(d, NULL,
 				  &cl->qdisc->qstats, cl->qdisc->q.qlen) < 0)
@@ -1235,8 +1238,10 @@
 			 cl->agg->lmax, qdisc_pkt_len(skb), cl->common.classid);
 		err = qfq_change_agg(sch, cl, cl->agg->class_weight,
 				     qdisc_pkt_len(skb));
-		if (err)
-			return err;
+		if (err) {
+			cl->qstats.drops++;
+			return qdisc_drop(skb, sch);
+		}
 	}
 
 	err = qdisc_enqueue(skb, cl->qdisc);
@@ -1420,52 +1425,6 @@
 		qfq_deactivate_class(q, cl);
 }
 
-static unsigned int qfq_drop_from_slot(struct qfq_sched *q,
-				       struct hlist_head *slot)
-{
-	struct qfq_aggregate *agg;
-	struct qfq_class *cl;
-	unsigned int len;
-
-	hlist_for_each_entry(agg, slot, next) {
-		list_for_each_entry(cl, &agg->active, alist) {
-
-			if (!cl->qdisc->ops->drop)
-				continue;
-
-			len = cl->qdisc->ops->drop(cl->qdisc);
-			if (len > 0) {
-				if (cl->qdisc->q.qlen == 0)
-					qfq_deactivate_class(q, cl);
-
-				return len;
-			}
-		}
-	}
-	return 0;
-}
-
-static unsigned int qfq_drop(struct Qdisc *sch)
-{
-	struct qfq_sched *q = qdisc_priv(sch);
-	struct qfq_group *grp;
-	unsigned int i, j, len;
-
-	for (i = 0; i <= QFQ_MAX_INDEX; i++) {
-		grp = &q->groups[i];
-		for (j = 0; j < QFQ_MAX_SLOTS; j++) {
-			len = qfq_drop_from_slot(q, &grp->slots[j]);
-			if (len > 0) {
-				sch->q.qlen--;
-				return len;
-			}
-		}
-
-	}
-
-	return 0;
-}
-
 static int qfq_init_qdisc(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct qfq_sched *q = qdisc_priv(sch);
@@ -1560,7 +1519,6 @@
 	.enqueue	= qfq_enqueue,
 	.dequeue	= qfq_dequeue,
 	.peek		= qdisc_peek_dequeued,
-	.drop		= qfq_drop,
 	.init		= qfq_init_qdisc,
 	.reset		= qfq_reset_qdisc,
 	.destroy	= qfq_destroy_qdisc,
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 8c0508c..a0d5753 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -97,6 +97,7 @@
 
 	ret = qdisc_enqueue(skb, child);
 	if (likely(ret == NET_XMIT_SUCCESS)) {
+		qdisc_qstats_backlog_inc(sch, skb);
 		sch->q.qlen++;
 	} else if (net_xmit_drop_count(ret)) {
 		q->stats.pdrop++;
@@ -118,6 +119,7 @@
 	skb = child->dequeue(child);
 	if (skb) {
 		qdisc_bstats_update(sch, skb);
+		qdisc_qstats_backlog_dec(sch, skb);
 		sch->q.qlen--;
 	} else {
 		if (!red_is_idling(&q->vars))
@@ -134,30 +136,12 @@
 	return child->ops->peek(child);
 }
 
-static unsigned int red_drop(struct Qdisc *sch)
-{
-	struct red_sched_data *q = qdisc_priv(sch);
-	struct Qdisc *child = q->qdisc;
-	unsigned int len;
-
-	if (child->ops->drop && (len = child->ops->drop(child)) > 0) {
-		q->stats.other++;
-		qdisc_qstats_drop(sch);
-		sch->q.qlen--;
-		return len;
-	}
-
-	if (!red_is_idling(&q->vars))
-		red_start_of_idle_period(&q->vars);
-
-	return 0;
-}
-
 static void red_reset(struct Qdisc *sch)
 {
 	struct red_sched_data *q = qdisc_priv(sch);
 
 	qdisc_reset(q->qdisc);
+	sch->qstats.backlog = 0;
 	sch->q.qlen = 0;
 	red_restart(&q->vars);
 }
@@ -361,7 +345,6 @@
 	.enqueue	=	red_enqueue,
 	.dequeue	=	red_dequeue,
 	.peek		=	red_peek,
-	.drop		=	red_drop,
 	.init		=	red_init,
 	.reset		=	red_reset,
 	.destroy	=	red_destroy,
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 498f0a2..57d118b 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -520,7 +520,7 @@
 	struct sk_buff *skb;
 
 	while ((skb = sfq_dequeue(sch)) != NULL)
-		kfree_skb(skb);
+		rtnl_kfree_skbs(skb, skb);
 }
 
 /*
@@ -896,7 +896,6 @@
 	.enqueue	=	sfq_enqueue,
 	.dequeue	=	sfq_dequeue,
 	.peek		=	qdisc_peek_dequeued,
-	.drop		=	sfq_drop,
 	.init		=	sfq_init,
 	.reset		=	sfq_reset,
 	.destroy	=	sfq_destroy,
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 83b90b5..c12df84 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -166,7 +166,7 @@
 	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
 
 	if (IS_ERR_OR_NULL(segs))
-		return qdisc_reshape_fail(skb, sch);
+		return qdisc_drop(skb, sch);
 
 	nb = 0;
 	while (segs) {
@@ -198,7 +198,7 @@
 	if (qdisc_pkt_len(skb) > q->max_size) {
 		if (skb_is_gso(skb) && skb_gso_mac_seglen(skb) <= q->max_size)
 			return tbf_segment(skb, sch);
-		return qdisc_reshape_fail(skb, sch);
+		return qdisc_drop(skb, sch);
 	}
 	ret = qdisc_enqueue(skb, q->qdisc);
 	if (ret != NET_XMIT_SUCCESS) {
@@ -207,22 +207,11 @@
 		return ret;
 	}
 
+	qdisc_qstats_backlog_inc(sch, skb);
 	sch->q.qlen++;
 	return NET_XMIT_SUCCESS;
 }
 
-static unsigned int tbf_drop(struct Qdisc *sch)
-{
-	struct tbf_sched_data *q = qdisc_priv(sch);
-	unsigned int len = 0;
-
-	if (q->qdisc->ops->drop && (len = q->qdisc->ops->drop(q->qdisc)) != 0) {
-		sch->q.qlen--;
-		qdisc_qstats_drop(sch);
-	}
-	return len;
-}
-
 static bool tbf_peak_present(const struct tbf_sched_data *q)
 {
 	return q->peak.rate_bytes_ps;
@@ -263,15 +252,14 @@
 			q->t_c = now;
 			q->tokens = toks;
 			q->ptokens = ptoks;
+			qdisc_qstats_backlog_dec(sch, skb);
 			sch->q.qlen--;
-			qdisc_unthrottled(sch);
 			qdisc_bstats_update(sch, skb);
 			return skb;
 		}
 
 		qdisc_watchdog_schedule_ns(&q->watchdog,
-					   now + max_t(long, -toks, -ptoks),
-					   true);
+					   now + max_t(long, -toks, -ptoks));
 
 		/* Maybe we have a shorter packet in the queue,
 		   which can be sent now. It sounds cool,
@@ -294,6 +282,7 @@
 	struct tbf_sched_data *q = qdisc_priv(sch);
 
 	qdisc_reset(q->qdisc);
+	sch->qstats.backlog = 0;
 	sch->q.qlen = 0;
 	q->t_c = ktime_get_ns();
 	q->tokens = q->buffer;
@@ -555,7 +544,6 @@
 	.enqueue	=	tbf_enqueue,
 	.dequeue	=	tbf_dequeue,
 	.peek		=	qdisc_peek_dequeued,
-	.drop		=	tbf_drop,
 	.init		=	tbf_init,
 	.reset		=	tbf_reset,
 	.destroy	=	tbf_destroy,
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 40022ee..3b56ae5 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1479,7 +1479,8 @@
 		INIT_HLIST_HEAD(&sctp_port_hashtable[i].chain);
 	}
 
-	if (sctp_transport_hashtable_init())
+	status = sctp_transport_hashtable_init();
+	if (status)
 		goto err_thash_alloc;
 
 	pr_info("Hash tables configured (bind %d/%d)\n", sctp_port_hashsize,
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index aa37122..12d4519 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -806,8 +806,10 @@
 
 		/* Set the RCV_SHUTDOWN flag when a SHUTDOWN is received. */
 		if (sctp_state(asoc, SHUTDOWN_RECEIVED) &&
-		    sctp_sstate(sk, ESTABLISHED))
+		    sctp_sstate(sk, ESTABLISHED)) {
+			sk->sk_state = SCTP_SS_CLOSING;
 			sk->sk_shutdown |= RCV_SHUTDOWN;
+		}
 	}
 
 	if (sctp_state(asoc, COOKIE_WAIT)) {
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 712fb23..cdabbd8 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4195,6 +4195,7 @@
 		return;
 
 	if (how & SEND_SHUTDOWN) {
+		sk->sk_state = SCTP_SS_CLOSING;
 		ep = sctp_sk(sk)->ep;
 		if (!list_empty(&ep->asocs)) {
 			asoc = list_entry(ep->asocs.next,
@@ -7566,10 +7567,13 @@
 	/* If the association on the newsk is already closed before accept()
 	 * is called, set RCV_SHUTDOWN flag.
 	 */
-	if (sctp_state(assoc, CLOSED) && sctp_style(newsk, TCP))
+	if (sctp_state(assoc, CLOSED) && sctp_style(newsk, TCP)) {
+		newsk->sk_state = SCTP_SS_CLOSED;
 		newsk->sk_shutdown |= RCV_SHUTDOWN;
+	} else {
+		newsk->sk_state = SCTP_SS_ESTABLISHED;
+	}
 
-	newsk->sk_state = SCTP_SS_ESTABLISHED;
 	release_sock(newsk);
 }
 
diff --git a/net/tipc/Makefile b/net/tipc/Makefile
index 57e460b..31b9f9c 100644
--- a/net/tipc/Makefile
+++ b/net/tipc/Makefile
@@ -6,7 +6,7 @@
 
 tipc-y	+= addr.o bcast.o bearer.o \
 	   core.o link.o discover.o msg.o  \
-	   name_distr.o  subscr.o name_table.o net.o  \
+	   name_distr.o  subscr.o monitor.o name_table.o net.o  \
 	   netlink.o netlink_compat.o node.o socket.o eth_media.o \
 	   server.o socket.o
 
diff --git a/net/tipc/addr.h b/net/tipc/addr.h
index 93f7c98..64f4004 100644
--- a/net/tipc/addr.h
+++ b/net/tipc/addr.h
@@ -73,4 +73,5 @@
 int tipc_in_scope(u32 domain, u32 addr);
 int tipc_addr_scope(u32 domain);
 char *tipc_addr_string_fill(char *string, u32 addr);
+
 #endif
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index 6f11c62..9a70e1d 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -1,7 +1,7 @@
 /*
  * net/tipc/bearer.c: TIPC bearer code
  *
- * Copyright (c) 1996-2006, 2013-2014, Ericsson AB
+ * Copyright (c) 1996-2006, 2013-2016, Ericsson AB
  * Copyright (c) 2004-2006, 2010-2013, Wind River Systems
  * All rights reserved.
  *
@@ -39,6 +39,7 @@
 #include "bearer.h"
 #include "link.h"
 #include "discover.h"
+#include "monitor.h"
 #include "bcast.h"
 #include "netlink.h"
 
@@ -313,6 +314,10 @@
 	rcu_assign_pointer(tn->bearer_list[bearer_id], b);
 	if (skb)
 		tipc_bearer_xmit_skb(net, bearer_id, skb, &b->bcast_addr);
+
+	if (tipc_mon_create(net, bearer_id))
+		return -ENOMEM;
+
 	pr_info("Enabled bearer <%s>, discovery domain %s, priority %u\n",
 		name,
 		tipc_addr_string_fill(addr_string, disc_domain), priority);
@@ -348,6 +353,7 @@
 		tipc_disc_delete(b->link_req);
 	RCU_INIT_POINTER(tn->bearer_list[bearer_id], NULL);
 	kfree_rcu(b, rcu);
+	tipc_mon_delete(net, bearer_id);
 }
 
 int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b,
diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h
index f686e41..0d337c7 100644
--- a/net/tipc/bearer.h
+++ b/net/tipc/bearer.h
@@ -1,7 +1,7 @@
 /*
  * net/tipc/bearer.h: Include file for TIPC bearer code
  *
- * Copyright (c) 1996-2006, 2013-2014, Ericsson AB
+ * Copyright (c) 1996-2006, 2013-2016, Ericsson AB
  * Copyright (c) 2005, 2010-2011, Wind River Systems
  * All rights reserved.
  *
diff --git a/net/tipc/core.c b/net/tipc/core.c
index fe1b062..236b043 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -57,6 +57,7 @@
 
 	tn->net_id = 4711;
 	tn->own_addr = 0;
+	tn->mon_threshold = TIPC_DEF_MON_THRESHOLD;
 	get_random_bytes(&tn->random, sizeof(int));
 	INIT_LIST_HEAD(&tn->node_list);
 	spin_lock_init(&tn->node_list_lock);
diff --git a/net/tipc/core.h b/net/tipc/core.h
index eff58dc..a1845fb 100644
--- a/net/tipc/core.h
+++ b/net/tipc/core.h
@@ -66,11 +66,13 @@
 struct tipc_link;
 struct tipc_name_table;
 struct tipc_server;
+struct tipc_monitor;
 
 #define TIPC_MOD_VER "2.0.0"
 
-#define NODE_HTABLE_SIZE   512
-#define MAX_BEARERS	   3
+#define NODE_HTABLE_SIZE       512
+#define MAX_BEARERS	         3
+#define TIPC_DEF_MON_THRESHOLD  32
 
 extern int tipc_net_id __read_mostly;
 extern int sysctl_tipc_rmem[3] __read_mostly;
@@ -88,6 +90,10 @@
 	u32 num_nodes;
 	u32 num_links;
 
+	/* Neighbor monitoring list */
+	struct tipc_monitor *monitors[MAX_BEARERS];
+	int mon_threshold;
+
 	/* Bearer list */
 	struct tipc_bearer __rcu *bearer_list[MAX_BEARERS + 1];
 
@@ -126,6 +132,11 @@
 	return &tipc_net(net)->node_list;
 }
 
+static inline unsigned int tipc_hashfn(u32 addr)
+{
+	return addr & (NODE_HTABLE_SIZE - 1);
+}
+
 static inline u16 mod(u16 x)
 {
 	return x & 0xffffu;
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 7059c94..03f8bdf 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -42,6 +42,7 @@
 #include "name_distr.h"
 #include "discover.h"
 #include "netlink.h"
+#include "monitor.h"
 
 #include <linux/pkt_sched.h>
 
@@ -87,7 +88,6 @@
  * @peer_bearer_id: bearer id used by link's peer endpoint
  * @bearer_id: local bearer id used by link
  * @tolerance: minimum link continuity loss needed to reset link [in ms]
- * @keepalive_intv: link keepalive timer interval
  * @abort_limit: # of unacknowledged continuity probes needed to reset link
  * @state: current state of link FSM
  * @peer_caps: bitmap describing capabilities of peer node
@@ -96,6 +96,7 @@
  * @pmsg: convenience pointer to "proto_msg" field
  * @priority: current link priority
  * @net_plane: current link network plane ('A' through 'H')
+ * @mon_state: cookie with information needed by link monitor
  * @backlog_limit: backlog queue congestion thresholds (indexed by importance)
  * @exp_msg_count: # of tunnelled messages expected during link changeover
  * @reset_rcv_checkpt: seq # of last acknowledged message at time of link reset
@@ -131,7 +132,6 @@
 	u32 peer_bearer_id;
 	u32 bearer_id;
 	u32 tolerance;
-	unsigned long keepalive_intv;
 	u32 abort_limit;
 	u32 state;
 	u16 peer_caps;
@@ -140,6 +140,7 @@
 	char if_name[TIPC_MAX_IF_NAME];
 	u32 priority;
 	char net_plane;
+	struct tipc_mon_state mon_state;
 	u16 rst_cnt;
 
 	/* Failover/synch */
@@ -710,18 +711,25 @@
 	bool setup = false;
 	u16 bc_snt = l->bc_sndlink->snd_nxt - 1;
 	u16 bc_acked = l->bc_rcvlink->acked;
-
-	link_profile_stats(l);
+	struct tipc_mon_state *mstate = &l->mon_state;
 
 	switch (l->state) {
 	case LINK_ESTABLISHED:
 	case LINK_SYNCHING:
-		if (l->silent_intv_cnt > l->abort_limit)
-			return tipc_link_fsm_evt(l, LINK_FAILURE_EVT);
 		mtyp = STATE_MSG;
+		link_profile_stats(l);
+		tipc_mon_get_state(l->net, l->addr, mstate, l->bearer_id);
+		if (mstate->reset || (l->silent_intv_cnt > l->abort_limit))
+			return tipc_link_fsm_evt(l, LINK_FAILURE_EVT);
 		state = bc_acked != bc_snt;
-		probe = l->silent_intv_cnt;
-		l->silent_intv_cnt++;
+		state |= l->bc_rcvlink->rcv_unacked;
+		state |= l->rcv_unacked;
+		state |= !skb_queue_empty(&l->transmq);
+		state |= !skb_queue_empty(&l->deferdq);
+		probe = mstate->probing;
+		probe |= l->silent_intv_cnt;
+		if (probe || mstate->monitoring)
+			l->silent_intv_cnt++;
 		break;
 	case LINK_RESET:
 		setup = l->rst_cnt++ <= 4;
@@ -832,6 +840,7 @@
 	l->stats.recv_info = 0;
 	l->stale_count = 0;
 	l->bc_peer_is_up = false;
+	memset(&l->mon_state, 0, sizeof(l->mon_state));
 	tipc_link_reset_stats(l);
 }
 
@@ -1240,6 +1249,9 @@
 	struct tipc_msg *hdr;
 	struct sk_buff_head *dfq = &l->deferdq;
 	bool node_up = link_is_up(l->bc_rcvlink);
+	struct tipc_mon_state *mstate = &l->mon_state;
+	int dlen = 0;
+	void *data;
 
 	/* Don't send protocol message during reset or link failover */
 	if (tipc_link_is_blocked(l))
@@ -1252,12 +1264,13 @@
 		rcvgap = buf_seqno(skb_peek(dfq)) - l->rcv_nxt;
 
 	skb = tipc_msg_create(LINK_PROTOCOL, mtyp, INT_H_SIZE,
-			      TIPC_MAX_IF_NAME, l->addr,
+			      tipc_max_domain_size, l->addr,
 			      tipc_own_addr(l->net), 0, 0, 0);
 	if (!skb)
 		return;
 
 	hdr = buf_msg(skb);
+	data = msg_data(hdr);
 	msg_set_session(hdr, l->session);
 	msg_set_bearer_id(hdr, l->bearer_id);
 	msg_set_net_plane(hdr, l->net_plane);
@@ -1273,14 +1286,18 @@
 
 	if (mtyp == STATE_MSG) {
 		msg_set_seq_gap(hdr, rcvgap);
-		msg_set_size(hdr, INT_H_SIZE);
 		msg_set_probe(hdr, probe);
+		tipc_mon_prep(l->net, data, &dlen, mstate, l->bearer_id);
+		msg_set_size(hdr, INT_H_SIZE + dlen);
+		skb_trim(skb, INT_H_SIZE + dlen);
 		l->stats.sent_states++;
 		l->rcv_unacked = 0;
 	} else {
 		/* RESET_MSG or ACTIVATE_MSG */
 		msg_set_max_pkt(hdr, l->advertised_mtu);
-		strcpy(msg_data(hdr), l->if_name);
+		strcpy(data, l->if_name);
+		msg_set_size(hdr, INT_H_SIZE + TIPC_MAX_IF_NAME);
+		skb_trim(skb, INT_H_SIZE + TIPC_MAX_IF_NAME);
 	}
 	if (probe)
 		l->stats.sent_probes++;
@@ -1373,7 +1390,9 @@
 	u16 peers_tol = msg_link_tolerance(hdr);
 	u16 peers_prio = msg_linkprio(hdr);
 	u16 rcv_nxt = l->rcv_nxt;
+	u16 dlen = msg_data_sz(hdr);
 	int mtyp = msg_type(hdr);
+	void *data;
 	char *if_name;
 	int rc = 0;
 
@@ -1383,6 +1402,10 @@
 	if (tipc_own_addr(l->net) > msg_prevnode(hdr))
 		l->net_plane = msg_net_plane(hdr);
 
+	skb_linearize(skb);
+	hdr = buf_msg(skb);
+	data = msg_data(hdr);
+
 	switch (mtyp) {
 	case RESET_MSG:
 
@@ -1393,8 +1416,6 @@
 		/* fall thru' */
 
 	case ACTIVATE_MSG:
-		skb_linearize(skb);
-		hdr = buf_msg(skb);
 
 		/* Complete own link name with peer's interface name */
 		if_name =  strrchr(l->name, ':') + 1;
@@ -1402,7 +1423,7 @@
 			break;
 		if (msg_data_sz(hdr) < TIPC_MAX_IF_NAME)
 			break;
-		strncpy(if_name, msg_data(hdr),	TIPC_MAX_IF_NAME);
+		strncpy(if_name, data, TIPC_MAX_IF_NAME);
 
 		/* Update own tolerance if peer indicates a non-zero value */
 		if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL))
@@ -1450,6 +1471,8 @@
 				rc = TIPC_LINK_UP_EVT;
 			break;
 		}
+		tipc_mon_rcv(l->net, data, dlen, l->addr,
+			     &l->mon_state, l->bearer_id);
 
 		/* Send NACK if peer has sent pkts we haven't received yet */
 		if (more(peers_snd_nxt, rcv_nxt) && !tipc_link_is_synching(l))
diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c
new file mode 100644
index 0000000..0d489e8
--- /dev/null
+++ b/net/tipc/monitor.c
@@ -0,0 +1,651 @@
+/*
+ * net/tipc/monitor.c
+ *
+ * Copyright (c) 2016, 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.
+ */
+
+#include "core.h"
+#include "addr.h"
+#include "monitor.h"
+
+#define MAX_MON_DOMAIN       64
+#define MON_TIMEOUT          120000
+#define MAX_PEER_DOWN_EVENTS 4
+
+/* struct tipc_mon_domain: domain record to be transferred between peers
+ * @len: actual size of domain record
+ * @gen: current generation of sender's domain
+ * @ack_gen: most recent generation of self's domain acked by peer
+ * @member_cnt: number of domain member nodes described in this record
+ * @up_map: bit map indicating which of the members the sender considers up
+ * @members: identity of the domain members
+ */
+struct tipc_mon_domain {
+	u16 len;
+	u16 gen;
+	u16 ack_gen;
+	u16 member_cnt;
+	u64 up_map;
+	u32 members[MAX_MON_DOMAIN];
+};
+
+/* struct tipc_peer: state of a peer node and its domain
+ * @addr: tipc node identity of peer
+ * @head_map: shows which other nodes currently consider peer 'up'
+ * @domain: most recent domain record from peer
+ * @hash: position in hashed lookup list
+ * @list: position in linked list, in circular ascending order by 'addr'
+ * @applied: number of reported domain members applied on this monitor list
+ * @is_up: peer is up as seen from this node
+ * @is_head: peer is assigned domain head as seen from this node
+ * @is_local: peer is in local domain and should be continuously monitored
+ * @down_cnt: - numbers of other peers which have reported this on lost
+ */
+struct tipc_peer {
+	u32 addr;
+	struct tipc_mon_domain *domain;
+	struct hlist_node hash;
+	struct list_head list;
+	u8 applied;
+	u8 down_cnt;
+	bool is_up;
+	bool is_head;
+	bool is_local;
+};
+
+struct tipc_monitor {
+	struct hlist_head peers[NODE_HTABLE_SIZE];
+	int peer_cnt;
+	struct tipc_peer *self;
+	rwlock_t lock;
+	struct tipc_mon_domain cache;
+	u16 list_gen;
+	u16 dom_gen;
+	struct net *net;
+	struct timer_list timer;
+	unsigned long timer_intv;
+};
+
+static struct tipc_monitor *tipc_monitor(struct net *net, int bearer_id)
+{
+	return tipc_net(net)->monitors[bearer_id];
+}
+
+const int tipc_max_domain_size = sizeof(struct tipc_mon_domain);
+
+/* dom_rec_len(): actual length of domain record for transport
+ */
+static int dom_rec_len(struct tipc_mon_domain *dom, u16 mcnt)
+{
+	return ((void *)&dom->members - (void *)dom) + (mcnt * sizeof(u32));
+}
+
+/* dom_size() : calculate size of own domain based on number of peers
+ */
+static int dom_size(int peers)
+{
+	int i = 0;
+
+	while ((i * i) < peers)
+		i++;
+	return i < MAX_MON_DOMAIN ? i : MAX_MON_DOMAIN;
+}
+
+static void map_set(u64 *up_map, int i, unsigned int v)
+{
+	*up_map &= ~(1ULL << i);
+	*up_map |= ((u64)v << i);
+}
+
+static int map_get(u64 up_map, int i)
+{
+	return (up_map & (1 << i)) >> i;
+}
+
+static struct tipc_peer *peer_prev(struct tipc_peer *peer)
+{
+	return list_last_entry(&peer->list, struct tipc_peer, list);
+}
+
+static struct tipc_peer *peer_nxt(struct tipc_peer *peer)
+{
+	return list_first_entry(&peer->list, struct tipc_peer, list);
+}
+
+static struct tipc_peer *peer_head(struct tipc_peer *peer)
+{
+	while (!peer->is_head)
+		peer = peer_prev(peer);
+	return peer;
+}
+
+static struct tipc_peer *get_peer(struct tipc_monitor *mon, u32 addr)
+{
+	struct tipc_peer *peer;
+	unsigned int thash = tipc_hashfn(addr);
+
+	hlist_for_each_entry(peer, &mon->peers[thash], hash) {
+		if (peer->addr == addr)
+			return peer;
+	}
+	return NULL;
+}
+
+static struct tipc_peer *get_self(struct net *net, int bearer_id)
+{
+	struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+
+	return mon->self;
+}
+
+static inline bool tipc_mon_is_active(struct net *net, struct tipc_monitor *mon)
+{
+	struct tipc_net *tn = tipc_net(net);
+
+	return mon->peer_cnt > tn->mon_threshold;
+}
+
+/* mon_identify_lost_members() : - identify amd mark potentially lost members
+ */
+static void mon_identify_lost_members(struct tipc_peer *peer,
+				      struct tipc_mon_domain *dom_bef,
+				      int applied_bef)
+{
+	struct tipc_peer *member = peer;
+	struct tipc_mon_domain *dom_aft = peer->domain;
+	int applied_aft = peer->applied;
+	int i;
+
+	for (i = 0; i < applied_bef; i++) {
+		member = peer_nxt(member);
+
+		/* Do nothing if self or peer already see member as down */
+		if (!member->is_up || !map_get(dom_bef->up_map, i))
+			continue;
+
+		/* Loss of local node must be detected by active probing */
+		if (member->is_local)
+			continue;
+
+		/* Start probing if member was removed from applied domain */
+		if (!applied_aft || (applied_aft < i)) {
+			member->down_cnt = 1;
+			continue;
+		}
+
+		/* Member loss is confirmed if it is still in applied domain */
+		if (!map_get(dom_aft->up_map, i))
+			member->down_cnt++;
+	}
+}
+
+/* mon_apply_domain() : match a peer's domain record against monitor list
+ */
+static void mon_apply_domain(struct tipc_monitor *mon,
+			     struct tipc_peer *peer)
+{
+	struct tipc_mon_domain *dom = peer->domain;
+	struct tipc_peer *member;
+	u32 addr;
+	int i;
+
+	if (!dom || !peer->is_up)
+		return;
+
+	/* Scan across domain members and match against monitor list */
+	peer->applied = 0;
+	member = peer_nxt(peer);
+	for (i = 0; i < dom->member_cnt; i++) {
+		addr = dom->members[i];
+		if (addr != member->addr)
+			return;
+		peer->applied++;
+		member = peer_nxt(member);
+	}
+}
+
+/* mon_update_local_domain() : update after peer addition/removal/up/down
+ */
+static void mon_update_local_domain(struct tipc_monitor *mon)
+{
+	struct tipc_peer *self = mon->self;
+	struct tipc_mon_domain *cache = &mon->cache;
+	struct tipc_mon_domain *dom = self->domain;
+	struct tipc_peer *peer = self;
+	u64 prev_up_map = dom->up_map;
+	u16 member_cnt, i;
+	bool diff;
+
+	/* Update local domain size based on current size of cluster */
+	member_cnt = dom_size(mon->peer_cnt) - 1;
+	self->applied = member_cnt;
+
+	/* Update native and cached outgoing local domain records */
+	dom->len = dom_rec_len(dom, member_cnt);
+	diff = dom->member_cnt != member_cnt;
+	dom->member_cnt = member_cnt;
+	for (i = 0; i < member_cnt; i++) {
+		peer = peer_nxt(peer);
+		diff |= dom->members[i] != peer->addr;
+		dom->members[i] = peer->addr;
+		map_set(&dom->up_map, i, peer->is_up);
+		cache->members[i] = htonl(peer->addr);
+	}
+	diff |= dom->up_map != prev_up_map;
+	if (!diff)
+		return;
+	dom->gen = ++mon->dom_gen;
+	cache->len = htons(dom->len);
+	cache->gen = htons(dom->gen);
+	cache->member_cnt = htons(member_cnt);
+	cache->up_map = cpu_to_be64(dom->up_map);
+	mon_apply_domain(mon, self);
+}
+
+/* mon_update_neighbors() : update preceding neighbors of added/removed peer
+ */
+static void mon_update_neighbors(struct tipc_monitor *mon,
+				 struct tipc_peer *peer)
+{
+	int dz, i;
+
+	dz = dom_size(mon->peer_cnt);
+	for (i = 0; i < dz; i++) {
+		mon_apply_domain(mon, peer);
+		peer = peer_prev(peer);
+	}
+}
+
+/* mon_assign_roles() : reassign peer roles after a network change
+ * The monitor list is consistent at this stage; i.e., each peer is monitoring
+ * a set of domain members as matched between domain record and the monitor list
+ */
+static void mon_assign_roles(struct tipc_monitor *mon, struct tipc_peer *head)
+{
+	struct tipc_peer *peer = peer_nxt(head);
+	struct tipc_peer *self = mon->self;
+	int i = 0;
+
+	for (; peer != self; peer = peer_nxt(peer)) {
+		peer->is_local = false;
+
+		/* Update domain member */
+		if (i++ < head->applied) {
+			peer->is_head = false;
+			if (head == self)
+				peer->is_local = true;
+			continue;
+		}
+		/* Assign next domain head */
+		if (!peer->is_up)
+			continue;
+		if (peer->is_head)
+			break;
+		head = peer;
+		head->is_head = true;
+		i = 0;
+	}
+	mon->list_gen++;
+}
+
+void tipc_mon_remove_peer(struct net *net, u32 addr, int bearer_id)
+{
+	struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+	struct tipc_peer *self = get_self(net, bearer_id);
+	struct tipc_peer *peer, *prev, *head;
+
+	write_lock_bh(&mon->lock);
+	peer = get_peer(mon, addr);
+	if (!peer)
+		goto exit;
+	prev = peer_prev(peer);
+	list_del(&peer->list);
+	hlist_del(&peer->hash);
+	kfree(peer->domain);
+	kfree(peer);
+	mon->peer_cnt--;
+	head = peer_head(prev);
+	if (head == self)
+		mon_update_local_domain(mon);
+	mon_update_neighbors(mon, prev);
+
+	/* Revert to full-mesh monitoring if we reach threshold */
+	if (!tipc_mon_is_active(net, mon)) {
+		list_for_each_entry(peer, &self->list, list) {
+			kfree(peer->domain);
+			peer->domain = NULL;
+			peer->applied = 0;
+		}
+	}
+	mon_assign_roles(mon, head);
+exit:
+	write_unlock_bh(&mon->lock);
+}
+
+static bool tipc_mon_add_peer(struct tipc_monitor *mon, u32 addr,
+			      struct tipc_peer **peer)
+{
+	struct tipc_peer *self = mon->self;
+	struct tipc_peer *cur, *prev, *p;
+
+	p = kzalloc(sizeof(*p), GFP_ATOMIC);
+	*peer = p;
+	if (!p)
+		return false;
+	p->addr = addr;
+
+	/* Add new peer to lookup list */
+	INIT_LIST_HEAD(&p->list);
+	hlist_add_head(&p->hash, &mon->peers[tipc_hashfn(addr)]);
+
+	/* Sort new peer into iterator list, in ascending circular order */
+	prev = self;
+	list_for_each_entry(cur, &self->list, list) {
+		if ((addr > prev->addr) && (addr < cur->addr))
+			break;
+		if (((addr < cur->addr) || (addr > prev->addr)) &&
+		    (prev->addr > cur->addr))
+			break;
+		prev = cur;
+	}
+	list_add_tail(&p->list, &cur->list);
+	mon->peer_cnt++;
+	mon_update_neighbors(mon, p);
+	return true;
+}
+
+void tipc_mon_peer_up(struct net *net, u32 addr, int bearer_id)
+{
+	struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+	struct tipc_peer *self = get_self(net, bearer_id);
+	struct tipc_peer *peer, *head;
+
+	write_lock_bh(&mon->lock);
+	peer = get_peer(mon, addr);
+	if (!peer && !tipc_mon_add_peer(mon, addr, &peer))
+		goto exit;
+	peer->is_up = true;
+	head = peer_head(peer);
+	if (head == self)
+		mon_update_local_domain(mon);
+	mon_assign_roles(mon, head);
+exit:
+	write_unlock_bh(&mon->lock);
+}
+
+void tipc_mon_peer_down(struct net *net, u32 addr, int bearer_id)
+{
+	struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+	struct tipc_peer *self = get_self(net, bearer_id);
+	struct tipc_peer *peer, *head;
+	struct tipc_mon_domain *dom;
+	int applied;
+
+	write_lock_bh(&mon->lock);
+	peer = get_peer(mon, addr);
+	if (!peer) {
+		pr_warn("Mon: unknown link %x/%u DOWN\n", addr, bearer_id);
+		goto exit;
+	}
+	applied = peer->applied;
+	peer->applied = 0;
+	dom = peer->domain;
+	peer->domain = NULL;
+	if (peer->is_head)
+		mon_identify_lost_members(peer, dom, applied);
+	kfree(dom);
+	peer->is_up = false;
+	peer->is_head = false;
+	peer->is_local = false;
+	peer->down_cnt = 0;
+	head = peer_head(peer);
+	if (head == self)
+		mon_update_local_domain(mon);
+	mon_assign_roles(mon, head);
+exit:
+	write_unlock_bh(&mon->lock);
+}
+
+/* tipc_mon_rcv - process monitor domain event message
+ */
+void tipc_mon_rcv(struct net *net, void *data, u16 dlen, u32 addr,
+		  struct tipc_mon_state *state, int bearer_id)
+{
+	struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+	struct tipc_mon_domain *arrv_dom = data;
+	struct tipc_mon_domain dom_bef;
+	struct tipc_mon_domain *dom;
+	struct tipc_peer *peer;
+	u16 new_member_cnt = ntohs(arrv_dom->member_cnt);
+	int new_dlen = dom_rec_len(arrv_dom, new_member_cnt);
+	u16 new_gen = ntohs(arrv_dom->gen);
+	u16 acked_gen = ntohs(arrv_dom->ack_gen);
+	bool probing = state->probing;
+	int i, applied_bef;
+
+	state->probing = false;
+	if (!dlen)
+		return;
+
+	/* Sanity check received domain record */
+	if ((dlen < new_dlen) || ntohs(arrv_dom->len) != new_dlen) {
+		pr_warn_ratelimited("Received illegal domain record\n");
+		return;
+	}
+
+	/* Synch generation numbers with peer if link just came up */
+	if (!state->synched) {
+		state->peer_gen = new_gen - 1;
+		state->acked_gen = acked_gen;
+		state->synched = true;
+	}
+
+	if (more(acked_gen, state->acked_gen))
+		state->acked_gen = acked_gen;
+
+	/* Drop duplicate unless we are waiting for a probe response */
+	if (!more(new_gen, state->peer_gen) && !probing)
+		return;
+
+	write_lock_bh(&mon->lock);
+	peer = get_peer(mon, addr);
+	if (!peer || !peer->is_up)
+		goto exit;
+
+	/* Peer is confirmed, stop any ongoing probing */
+	peer->down_cnt = 0;
+
+	/* Task is done for duplicate record */
+	if (!more(new_gen, state->peer_gen))
+		goto exit;
+
+	state->peer_gen = new_gen;
+
+	/* Cache current domain record for later use */
+	dom_bef.member_cnt = 0;
+	dom = peer->domain;
+	if (dom)
+		memcpy(&dom_bef, dom, dom->len);
+
+	/* Transform and store received domain record */
+	if (!dom || (dom->len < new_dlen)) {
+		kfree(dom);
+		dom = kmalloc(new_dlen, GFP_ATOMIC);
+		peer->domain = dom;
+		if (!dom)
+			goto exit;
+	}
+	dom->len = new_dlen;
+	dom->gen = new_gen;
+	dom->member_cnt = new_member_cnt;
+	dom->up_map = be64_to_cpu(arrv_dom->up_map);
+	for (i = 0; i < new_member_cnt; i++)
+		dom->members[i] = ntohl(arrv_dom->members[i]);
+
+	/* Update peers affected by this domain record */
+	applied_bef = peer->applied;
+	mon_apply_domain(mon, peer);
+	mon_identify_lost_members(peer, &dom_bef, applied_bef);
+	mon_assign_roles(mon, peer_head(peer));
+exit:
+	write_unlock_bh(&mon->lock);
+}
+
+void tipc_mon_prep(struct net *net, void *data, int *dlen,
+		   struct tipc_mon_state *state, int bearer_id)
+{
+	struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+	struct tipc_mon_domain *dom = data;
+	u16 gen = mon->dom_gen;
+	u16 len;
+
+	if (!tipc_mon_is_active(net, mon))
+		return;
+
+	/* Send only a dummy record with ack if peer has acked our last sent */
+	if (likely(state->acked_gen == gen)) {
+		len = dom_rec_len(dom, 0);
+		*dlen = len;
+		dom->len = htons(len);
+		dom->gen = htons(gen);
+		dom->ack_gen = htons(state->peer_gen);
+		dom->member_cnt = 0;
+		return;
+	}
+	/* Send the full record */
+	read_lock_bh(&mon->lock);
+	len = ntohs(mon->cache.len);
+	*dlen = len;
+	memcpy(data, &mon->cache, len);
+	read_unlock_bh(&mon->lock);
+	dom->ack_gen = htons(state->peer_gen);
+}
+
+void tipc_mon_get_state(struct net *net, u32 addr,
+			struct tipc_mon_state *state,
+			int bearer_id)
+{
+	struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+	struct tipc_peer *peer;
+
+	/* Used cached state if table has not changed */
+	if (!state->probing &&
+	    (state->list_gen == mon->list_gen) &&
+	    (state->acked_gen == mon->dom_gen))
+		return;
+
+	read_lock_bh(&mon->lock);
+	peer = get_peer(mon, addr);
+	if (peer) {
+		state->probing = state->acked_gen != mon->dom_gen;
+		state->probing |= peer->down_cnt;
+		state->reset |= peer->down_cnt >= MAX_PEER_DOWN_EVENTS;
+		state->monitoring = peer->is_local;
+		state->monitoring |= peer->is_head;
+		state->list_gen = mon->list_gen;
+	}
+	read_unlock_bh(&mon->lock);
+}
+
+static void mon_timeout(unsigned long m)
+{
+	struct tipc_monitor *mon = (void *)m;
+	struct tipc_peer *self;
+	int best_member_cnt = dom_size(mon->peer_cnt) - 1;
+
+	write_lock_bh(&mon->lock);
+	self = mon->self;
+	if (self && (best_member_cnt != self->applied)) {
+		mon_update_local_domain(mon);
+		mon_assign_roles(mon, self);
+	}
+	write_unlock_bh(&mon->lock);
+	mod_timer(&mon->timer, jiffies + mon->timer_intv);
+}
+
+int tipc_mon_create(struct net *net, int bearer_id)
+{
+	struct tipc_net *tn = tipc_net(net);
+	struct tipc_monitor *mon;
+	struct tipc_peer *self;
+	struct tipc_mon_domain *dom;
+
+	if (tn->monitors[bearer_id])
+		return 0;
+
+	mon = kzalloc(sizeof(*mon), GFP_ATOMIC);
+	self = kzalloc(sizeof(*self), GFP_ATOMIC);
+	dom = kzalloc(sizeof(*dom), GFP_ATOMIC);
+	if (!mon || !self || !dom) {
+		kfree(mon);
+		kfree(self);
+		kfree(dom);
+		return -ENOMEM;
+	}
+	tn->monitors[bearer_id] = mon;
+	rwlock_init(&mon->lock);
+	mon->net = net;
+	mon->peer_cnt = 1;
+	mon->self = self;
+	self->domain = dom;
+	self->addr = tipc_own_addr(net);
+	self->is_up = true;
+	self->is_head = true;
+	INIT_LIST_HEAD(&self->list);
+	setup_timer(&mon->timer, mon_timeout, (unsigned long)mon);
+	mon->timer_intv = msecs_to_jiffies(MON_TIMEOUT + (tn->random & 0xffff));
+	mod_timer(&mon->timer, jiffies + mon->timer_intv);
+	return 0;
+}
+
+void tipc_mon_delete(struct net *net, int bearer_id)
+{
+	struct tipc_net *tn = tipc_net(net);
+	struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
+	struct tipc_peer *self = get_self(net, bearer_id);
+	struct tipc_peer *peer, *tmp;
+
+	write_lock_bh(&mon->lock);
+	tn->monitors[bearer_id] = NULL;
+	list_for_each_entry_safe(peer, tmp, &self->list, list) {
+		list_del(&peer->list);
+		hlist_del(&peer->hash);
+		kfree(peer->domain);
+		kfree(peer);
+	}
+	mon->self = NULL;
+	write_unlock_bh(&mon->lock);
+	del_timer_sync(&mon->timer);
+	kfree(self->domain);
+	kfree(self);
+	kfree(mon);
+}
diff --git a/net/tipc/monitor.h b/net/tipc/monitor.h
new file mode 100644
index 0000000..598459c
--- /dev/null
+++ b/net/tipc/monitor.h
@@ -0,0 +1,73 @@
+/*
+ * net/tipc/monitor.h
+ *
+ * Copyright (c) 2015, 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_MONITOR_H
+#define _TIPC_MONITOR_H
+
+/* struct tipc_mon_state: link instance's cache of monitor list and domain state
+ * @list_gen: current generation of this node's monitor list
+ * @gen: current generation of this node's local domain
+ * @peer_gen: most recent domain generation received from peer
+ * @acked_gen: most recent generation of self's domain acked by peer
+ * @monitoring: this peer endpoint should continuously monitored
+ * @probing: peer endpoint should be temporarily probed for potential loss
+ * @synched: domain record's generation has been synched with peer after reset
+ */
+struct tipc_mon_state {
+	u16 list_gen;
+	u16 peer_gen;
+	u16 acked_gen;
+	bool monitoring :1;
+	bool probing    :1;
+	bool reset      :1;
+	bool synched    :1;
+};
+
+int tipc_mon_create(struct net *net, int bearer_id);
+void tipc_mon_delete(struct net *net, int bearer_id);
+
+void tipc_mon_peer_up(struct net *net, u32 addr, int bearer_id);
+void tipc_mon_peer_down(struct net *net, u32 addr, int bearer_id);
+void tipc_mon_prep(struct net *net, void *data, int *dlen,
+		   struct tipc_mon_state *state, int bearer_id);
+void tipc_mon_rcv(struct net *net, void *data, u16 dlen, u32 addr,
+		  struct tipc_mon_state *state, int bearer_id);
+void tipc_mon_get_state(struct net *net, u32 addr,
+			struct tipc_mon_state *state,
+			int bearer_id);
+void tipc_mon_remove_peer(struct net *net, u32 addr, int bearer_id);
+
+extern const int tipc_max_domain_size;
+#endif
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index f795b1d..3ad9fab 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -604,7 +604,8 @@
 
 	link_info.dest = nla_get_flag(link[TIPC_NLA_LINK_DEST]);
 	link_info.up = htonl(nla_get_flag(link[TIPC_NLA_LINK_UP]));
-	strcpy(link_info.str, nla_data(link[TIPC_NLA_LINK_NAME]));
+	nla_strlcpy(link_info.str, nla_data(link[TIPC_NLA_LINK_NAME]),
+		    TIPC_MAX_LINK_NAME);
 
 	return tipc_add_tlv(msg->rep, TIPC_TLV_LINK_INFO,
 			    &link_info, sizeof(link_info));
diff --git a/net/tipc/node.c b/net/tipc/node.c
index e01e2c71..a3fc0a3 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -40,6 +40,7 @@
 #include "name_distr.h"
 #include "socket.h"
 #include "bcast.h"
+#include "monitor.h"
 #include "discover.h"
 #include "netlink.h"
 
@@ -205,17 +206,6 @@
 	return caps;
 }
 
-/*
- * A trivial power-of-two bitmask technique is used for speed, since this
- * operation is done for every incoming TIPC packet. The number of hash table
- * entries has been chosen so that no hash chain exceeds 8 nodes and will
- * usually be much smaller (typically only a single node).
- */
-static unsigned int tipc_hashfn(u32 addr)
-{
-	return addr & (NODE_HTABLE_SIZE - 1);
-}
-
 static void tipc_node_kref_release(struct kref *kref)
 {
 	struct tipc_node *n = container_of(kref, struct tipc_node, kref);
@@ -279,6 +269,7 @@
 	u32 addr = 0;
 	u32 flags = n->action_flags;
 	u32 link_id = 0;
+	u32 bearer_id;
 	struct list_head *publ_list;
 
 	if (likely(!flags)) {
@@ -288,6 +279,7 @@
 
 	addr = n->addr;
 	link_id = n->link_id;
+	bearer_id = link_id & 0xffff;
 	publ_list = &n->publ_list;
 
 	n->action_flags &= ~(TIPC_NOTIFY_NODE_DOWN | TIPC_NOTIFY_NODE_UP |
@@ -301,13 +293,16 @@
 	if (flags & TIPC_NOTIFY_NODE_UP)
 		tipc_named_node_up(net, addr);
 
-	if (flags & TIPC_NOTIFY_LINK_UP)
+	if (flags & TIPC_NOTIFY_LINK_UP) {
+		tipc_mon_peer_up(net, addr, bearer_id);
 		tipc_nametbl_publish(net, TIPC_LINK_STATE, addr, addr,
 				     TIPC_NODE_SCOPE, link_id, addr);
-
-	if (flags & TIPC_NOTIFY_LINK_DOWN)
+	}
+	if (flags & TIPC_NOTIFY_LINK_DOWN) {
+		tipc_mon_peer_down(net, addr, bearer_id);
 		tipc_nametbl_withdraw(net, TIPC_LINK_STATE, addr,
 				      link_id, addr);
+	}
 }
 
 struct tipc_node *tipc_node_create(struct net *net, u32 addr, u16 capabilities)
@@ -378,14 +373,13 @@
 {
 	unsigned long tol = tipc_link_tolerance(l);
 	unsigned long intv = ((tol / 4) > 500) ? 500 : tol / 4;
-	unsigned long keepalive_intv = msecs_to_jiffies(intv);
 
 	/* Link with lowest tolerance determines timer interval */
-	if (keepalive_intv < n->keepalive_intv)
-		n->keepalive_intv = keepalive_intv;
+	if (intv < n->keepalive_intv)
+		n->keepalive_intv = intv;
 
-	/* Ensure link's abort limit corresponds to current interval */
-	tipc_link_set_abort_limit(l, tol / jiffies_to_msecs(n->keepalive_intv));
+	/* Ensure link's abort limit corresponds to current tolerance */
+	tipc_link_set_abort_limit(l, tol / n->keepalive_intv);
 }
 
 static void tipc_node_delete(struct tipc_node *node)
@@ -526,7 +520,7 @@
 		if (rc & TIPC_LINK_DOWN_EVT)
 			tipc_node_link_down(n, bearer_id, false);
 	}
-	mod_timer(&n->timer, jiffies + n->keepalive_intv);
+	mod_timer(&n->timer, jiffies + msecs_to_jiffies(n->keepalive_intv));
 }
 
 /**
@@ -692,6 +686,7 @@
 	struct tipc_link *l = le->link;
 	struct tipc_media_addr *maddr;
 	struct sk_buff_head xmitq;
+	int old_bearer_id = bearer_id;
 
 	if (!l)
 		return;
@@ -711,6 +706,8 @@
 		tipc_link_fsm_evt(l, LINK_RESET_EVT);
 	}
 	tipc_node_write_unlock(n);
+	if (delete)
+		tipc_mon_remove_peer(n->net, n->addr, old_bearer_id);
 	tipc_bearer_xmit(n->net, bearer_id, &xmitq, maddr);
 	tipc_sk_rcv(n->net, &le->inputq);
 }
@@ -735,6 +732,7 @@
 	bool accept_addr = false;
 	bool reset = true;
 	char *if_name;
+	unsigned long intv;
 
 	*dupl_addr = false;
 	*respond = false;
@@ -840,9 +838,11 @@
 		le->link = l;
 		n->link_cnt++;
 		tipc_node_calculate_timer(n, l);
-		if (n->link_cnt == 1)
-			if (!mod_timer(&n->timer, jiffies + n->keepalive_intv))
+		if (n->link_cnt == 1) {
+			intv = jiffies + msecs_to_jiffies(n->keepalive_intv);
+			if (!mod_timer(&n->timer, intv))
 				tipc_node_get(n);
+		}
 	}
 	memcpy(&le->maddr, maddr, sizeof(*maddr));
 exit:
@@ -950,7 +950,7 @@
 			state = SELF_UP_PEER_UP;
 			break;
 		case SELF_LOST_CONTACT_EVT:
-			state = SELF_DOWN_PEER_LEAVING;
+			state = SELF_DOWN_PEER_DOWN;
 			break;
 		case SELF_ESTABL_CONTACT_EVT:
 		case PEER_LOST_CONTACT_EVT:
@@ -969,7 +969,7 @@
 			state = SELF_UP_PEER_UP;
 			break;
 		case PEER_LOST_CONTACT_EVT:
-			state = SELF_LEAVING_PEER_DOWN;
+			state = SELF_DOWN_PEER_DOWN;
 			break;
 		case SELF_LOST_CONTACT_EVT:
 		case PEER_ESTABL_CONTACT_EVT:
diff --git a/net/wireless/core.c b/net/wireless/core.c
index d25c82b..39d9abd 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -363,8 +363,6 @@
 	WARN_ON(ops->remain_on_channel && !ops->cancel_remain_on_channel);
 	WARN_ON(ops->tdls_channel_switch && !ops->tdls_cancel_channel_switch);
 	WARN_ON(ops->add_tx_ts && !ops->del_tx_ts);
-	WARN_ON(ops->set_tx_power && !ops->get_tx_power);
-	WARN_ON(ops->set_antenna && !ops->get_antenna);
 
 	alloc_size = sizeof(*rdev) + sizeof_priv;
 
@@ -750,6 +748,36 @@
 		nl80211_send_reg_change_event(&request);
 	}
 
+	/* Check that nobody globally advertises any capabilities they do not
+	 * advertise on all possible interface types.
+	 */
+	if (wiphy->extended_capabilities_len &&
+	    wiphy->num_iftype_ext_capab &&
+	    wiphy->iftype_ext_capab) {
+		u8 supported_on_all, j;
+		const struct wiphy_iftype_ext_capab *capab;
+
+		capab = wiphy->iftype_ext_capab;
+		for (j = 0; j < wiphy->extended_capabilities_len; j++) {
+			if (capab[0].extended_capabilities_len > j)
+				supported_on_all =
+					capab[0].extended_capabilities[j];
+			else
+				supported_on_all = 0x00;
+			for (i = 1; i < wiphy->num_iftype_ext_capab; i++) {
+				if (j >= capab[i].extended_capabilities_len) {
+					supported_on_all = 0x00;
+					break;
+				}
+				supported_on_all &=
+					capab[i].extended_capabilities[j];
+			}
+			if (WARN_ON(wiphy->extended_capabilities[j] &
+				    ~supported_on_all))
+				break;
+		}
+	}
+
 	rdev->wiphy.registered = true;
 	rtnl_unlock();
 
diff --git a/net/wireless/core.h b/net/wireless/core.h
index 025b7a5..a4d547f 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -214,7 +214,7 @@
 			size_t req_ie_len;
 			size_t resp_ie_len;
 			struct cfg80211_bss *bss;
-			u16 status;
+			int status; /* -1 = failed; 0..65535 = status code */
 		} cr;
 		struct {
 			const u8 *req_ie;
@@ -374,7 +374,7 @@
 void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
 			       const u8 *req_ie, size_t req_ie_len,
 			       const u8 *resp_ie, size_t resp_ie_len,
-			       u16 status, bool wextev,
+			       int status, bool wextev,
 			       struct cfg80211_bss *bss);
 void __cfg80211_disconnected(struct net_device *dev, const u8 *ie,
 			     size_t ie_len, u16 reason, bool from_ap);
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index d759901..c503e96 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -167,6 +167,7 @@
 
 	if (attrs[NL80211_ATTR_IFINDEX]) {
 		int ifindex = nla_get_u32(attrs[NL80211_ATTR_IFINDEX]);
+
 		netdev = __dev_get_by_index(netns, ifindex);
 		if (netdev) {
 			if (netdev->ieee80211_ptr)
@@ -731,6 +732,7 @@
 
 	if (tb[NL80211_KEY_DEFAULT_TYPES]) {
 		struct nlattr *kdt[NUM_NL80211_KEY_DEFAULT_TYPES];
+
 		err = nla_parse_nested(kdt, NUM_NL80211_KEY_DEFAULT_TYPES - 1,
 				       tb[NL80211_KEY_DEFAULT_TYPES],
 				       nl80211_key_default_policy);
@@ -1264,7 +1266,7 @@
 struct nl80211_dump_wiphy_state {
 	s64 filter_wiphy;
 	long start;
-	long split_start, band_start, chan_start;
+	long split_start, band_start, chan_start, capa_start;
 	bool split;
 };
 
@@ -1382,6 +1384,7 @@
 		    rdev->ops->get_antenna) {
 			u32 tx_ant = 0, rx_ant = 0;
 			int res;
+
 			res = rdev_get_antenna(rdev, &tx_ant, &rx_ant);
 			if (!res) {
 				if (nla_put_u32(msg,
@@ -1761,6 +1764,47 @@
 			nla_nest_end(msg, nested);
 		}
 
+		state->split_start++;
+		break;
+	case 13:
+		if (rdev->wiphy.num_iftype_ext_capab &&
+		    rdev->wiphy.iftype_ext_capab) {
+			struct nlattr *nested_ext_capab, *nested;
+
+			nested = nla_nest_start(msg,
+						NL80211_ATTR_IFTYPE_EXT_CAPA);
+			if (!nested)
+				goto nla_put_failure;
+
+			for (i = state->capa_start;
+			     i < rdev->wiphy.num_iftype_ext_capab; i++) {
+				const struct wiphy_iftype_ext_capab *capab;
+
+				capab = &rdev->wiphy.iftype_ext_capab[i];
+
+				nested_ext_capab = nla_nest_start(msg, i);
+				if (!nested_ext_capab ||
+				    nla_put_u32(msg, NL80211_ATTR_IFTYPE,
+						capab->iftype) ||
+				    nla_put(msg, NL80211_ATTR_EXT_CAPA,
+					    capab->extended_capabilities_len,
+					    capab->extended_capabilities) ||
+				    nla_put(msg, NL80211_ATTR_EXT_CAPA_MASK,
+					    capab->extended_capabilities_len,
+					    capab->extended_capabilities_mask))
+					goto nla_put_failure;
+
+				nla_nest_end(msg, nested_ext_capab);
+				if (state->split)
+					break;
+			}
+			nla_nest_end(msg, nested);
+			if (i < rdev->wiphy.num_iftype_ext_capab) {
+				state->capa_start = i + 1;
+				break;
+			}
+		}
+
 		/* done */
 		state->split_start = 0;
 		break;
@@ -2116,7 +2160,6 @@
 	return rdev_set_wds_peer(rdev, dev, bssid);
 }
 
-
 static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info)
 {
 	struct cfg80211_registered_device *rdev;
@@ -2251,6 +2294,7 @@
 	if (info->attrs[NL80211_ATTR_WIPHY_ANTENNA_TX] &&
 	    info->attrs[NL80211_ATTR_WIPHY_ANTENNA_RX]) {
 		u32 tx_ant, rx_ant;
+
 		if ((!rdev->wiphy.available_antennas_tx &&
 		     !rdev->wiphy.available_antennas_rx) ||
 		    !rdev->ops->set_antenna)
@@ -2919,6 +2963,7 @@
 	pairwise = !!mac_addr;
 	if (info->attrs[NL80211_ATTR_KEY_TYPE]) {
 		u32 kt = nla_get_u32(info->attrs[NL80211_ATTR_KEY_TYPE]);
+
 		if (kt >= NUM_NL80211_KEYTYPES)
 			return -EINVAL;
 		if (kt != NL80211_KEYTYPE_GROUP &&
@@ -3962,7 +4007,6 @@
 		sta_idx++;
 	}
 
-
  out:
 	cb->args[2] = sta_idx;
 	err = skb->len;
@@ -4763,7 +4807,6 @@
 		path_idx++;
 	}
 
-
  out:
 	cb->args[2] = path_idx;
 	err = skb->len;
@@ -5053,7 +5096,6 @@
 	enum nl80211_user_reg_hint_type user_reg_hint_type;
 	u32 owner_nlportid;
 
-
 	/*
 	 * You should only get this when cfg80211 hasn't yet initialized
 	 * completely when built-in to the kernel right between the time
@@ -5262,7 +5304,6 @@
 	}								    \
 } while (0)
 
-
 	if (!info->attrs[NL80211_ATTR_MESH_CONFIG])
 		return -EINVAL;
 	if (nla_parse_nested(tb, NL80211_MESHCONF_ATTR_MAX,
@@ -5409,7 +5450,6 @@
 		 IEEE80211_PATH_METRIC_VENDOR :
 		 IEEE80211_PATH_METRIC_AIRTIME;
 
-
 	if (tb[NL80211_MESH_SETUP_IE]) {
 		struct nlattr *ieattr =
 			tb[NL80211_MESH_SETUP_IE];
@@ -5796,10 +5836,8 @@
 		}
 	}
 
-	r = set_regdom(rd, REGD_SOURCE_CRDA);
-	/* set_regdom took ownership */
-	rd = NULL;
-
+	/* set_regdom takes ownership of rd */
+	return set_regdom(rd, REGD_SOURCE_CRDA);
  bad_reg:
 	kfree(rd);
 	return r;
@@ -6033,6 +6071,7 @@
 		/* all channels */
 		for (band = 0; band < NUM_NL80211_BANDS; band++) {
 			int j;
+
 			if (!wiphy->bands[band])
 				continue;
 			for (j = 0; j < wiphy->bands[band]->n_channels; j++) {
@@ -6442,6 +6481,7 @@
 		/* all channels */
 		for (band = 0; band < NUM_NL80211_BANDS; band++) {
 			int j;
+
 			if (!wiphy->bands[band])
 				continue;
 			for (j = 0; j < wiphy->bands[band]->n_channels; j++) {
@@ -6511,7 +6551,7 @@
 				       nla_data(ssid), nla_len(ssid));
 				request->match_sets[i].ssid.ssid_len =
 					nla_len(ssid);
-				/* special attribute - old implemenation w/a */
+				/* special attribute - old implementation w/a */
 				request->match_sets[i].rssi_thold =
 					default_match_rssi;
 				rssi = tb[NL80211_SCHED_SCAN_MATCH_ATTR_RSSI];
@@ -7204,6 +7244,7 @@
 	if (key.idx >= 0) {
 		int i;
 		bool ok = false;
+
 		for (i = 0; i < rdev->wiphy.n_cipher_suites; i++) {
 			if (key.p.cipher == rdev->wiphy.cipher_suites[i]) {
 				ok = true;
@@ -7282,6 +7323,7 @@
 
 	if (info->attrs[NL80211_ATTR_CONTROL_PORT_ETHERTYPE]) {
 		u16 proto;
+
 		proto = nla_get_u16(
 			info->attrs[NL80211_ATTR_CONTROL_PORT_ETHERTYPE]);
 		settings->control_port_ethertype = cpu_to_be16(proto);
@@ -8435,6 +8477,7 @@
 	for (i = 0; i < rates_len; i++) {
 		int rate = (rates[i] & 0x7f) * 5;
 		int ridx;
+
 		for (ridx = 0; ridx < sband->n_bitrates; ridx++) {
 			struct ieee80211_rate *srate =
 				&sband->bitrates[ridx];
@@ -8743,7 +8786,6 @@
 		if (params.wait < NL80211_MIN_REMAIN_ON_CHANNEL_TIME ||
 		    params.wait > rdev->wiphy.max_remain_on_channel_duration)
 			return -EINVAL;
-
 	}
 
 	params.offchan = info->attrs[NL80211_ATTR_OFFCHANNEL_TX_OK];
@@ -10590,7 +10632,6 @@
 }
 EXPORT_SYMBOL_GPL(cfg80211_vendor_cmd_reply);
 
-
 static int nl80211_set_qos_map(struct sk_buff *skb,
 			       struct genl_info *info)
 {
@@ -10945,7 +10986,7 @@
 		.cmd = NL80211_CMD_SET_WIPHY,
 		.doit = nl80211_set_wiphy,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_RTNL,
 	},
 	{
@@ -10961,7 +11002,7 @@
 		.cmd = NL80211_CMD_SET_INTERFACE,
 		.doit = nl80211_set_interface,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -10969,7 +11010,7 @@
 		.cmd = NL80211_CMD_NEW_INTERFACE,
 		.doit = nl80211_new_interface,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -10977,7 +11018,7 @@
 		.cmd = NL80211_CMD_DEL_INTERFACE,
 		.doit = nl80211_del_interface,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -10985,7 +11026,7 @@
 		.cmd = NL80211_CMD_GET_KEY,
 		.doit = nl80211_get_key,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -10993,7 +11034,7 @@
 		.cmd = NL80211_CMD_SET_KEY,
 		.doit = nl80211_set_key,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL |
 				  NL80211_FLAG_CLEAR_SKB,
@@ -11002,7 +11043,7 @@
 		.cmd = NL80211_CMD_NEW_KEY,
 		.doit = nl80211_new_key,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL |
 				  NL80211_FLAG_CLEAR_SKB,
@@ -11011,14 +11052,14 @@
 		.cmd = NL80211_CMD_DEL_KEY,
 		.doit = nl80211_del_key,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
 	{
 		.cmd = NL80211_CMD_SET_BEACON,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.doit = nl80211_set_beacon,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -11026,7 +11067,7 @@
 	{
 		.cmd = NL80211_CMD_START_AP,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.doit = nl80211_start_ap,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -11034,7 +11075,7 @@
 	{
 		.cmd = NL80211_CMD_STOP_AP,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.doit = nl80211_stop_ap,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -11051,7 +11092,7 @@
 		.cmd = NL80211_CMD_SET_STATION,
 		.doit = nl80211_set_station,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11059,7 +11100,7 @@
 		.cmd = NL80211_CMD_NEW_STATION,
 		.doit = nl80211_new_station,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11067,7 +11108,7 @@
 		.cmd = NL80211_CMD_DEL_STATION,
 		.doit = nl80211_del_station,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11076,7 +11117,7 @@
 		.doit = nl80211_get_mpath,
 		.dumpit = nl80211_dump_mpath,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11085,7 +11126,7 @@
 		.doit = nl80211_get_mpp,
 		.dumpit = nl80211_dump_mpp,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11093,7 +11134,7 @@
 		.cmd = NL80211_CMD_SET_MPATH,
 		.doit = nl80211_set_mpath,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11101,7 +11142,7 @@
 		.cmd = NL80211_CMD_NEW_MPATH,
 		.doit = nl80211_new_mpath,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11109,7 +11150,7 @@
 		.cmd = NL80211_CMD_DEL_MPATH,
 		.doit = nl80211_del_mpath,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11117,7 +11158,7 @@
 		.cmd = NL80211_CMD_SET_BSS,
 		.doit = nl80211_set_bss,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11156,7 +11197,7 @@
 		.cmd = NL80211_CMD_SET_MESH_CONFIG,
 		.doit = nl80211_update_mesh_config,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11164,7 +11205,7 @@
 		.cmd = NL80211_CMD_TRIGGER_SCAN,
 		.doit = nl80211_trigger_scan,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11172,7 +11213,7 @@
 		.cmd = NL80211_CMD_ABORT_SCAN,
 		.doit = nl80211_abort_scan,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11185,7 +11226,7 @@
 		.cmd = NL80211_CMD_START_SCHED_SCAN,
 		.doit = nl80211_start_sched_scan,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11193,7 +11234,7 @@
 		.cmd = NL80211_CMD_STOP_SCHED_SCAN,
 		.doit = nl80211_stop_sched_scan,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11201,7 +11242,7 @@
 		.cmd = NL80211_CMD_AUTHENTICATE,
 		.doit = nl80211_authenticate,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL |
 				  NL80211_FLAG_CLEAR_SKB,
@@ -11210,7 +11251,7 @@
 		.cmd = NL80211_CMD_ASSOCIATE,
 		.doit = nl80211_associate,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11218,7 +11259,7 @@
 		.cmd = NL80211_CMD_DEAUTHENTICATE,
 		.doit = nl80211_deauthenticate,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11226,7 +11267,7 @@
 		.cmd = NL80211_CMD_DISASSOCIATE,
 		.doit = nl80211_disassociate,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11234,7 +11275,7 @@
 		.cmd = NL80211_CMD_JOIN_IBSS,
 		.doit = nl80211_join_ibss,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11242,7 +11283,7 @@
 		.cmd = NL80211_CMD_LEAVE_IBSS,
 		.doit = nl80211_leave_ibss,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11252,7 +11293,7 @@
 		.doit = nl80211_testmode_do,
 		.dumpit = nl80211_testmode_dump,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11261,7 +11302,7 @@
 		.cmd = NL80211_CMD_CONNECT,
 		.doit = nl80211_connect,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11269,7 +11310,7 @@
 		.cmd = NL80211_CMD_DISCONNECT,
 		.doit = nl80211_disconnect,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11277,7 +11318,7 @@
 		.cmd = NL80211_CMD_SET_WIPHY_NETNS,
 		.doit = nl80211_wiphy_netns,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11290,7 +11331,7 @@
 		.cmd = NL80211_CMD_SET_PMKSA,
 		.doit = nl80211_setdel_pmksa,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11298,7 +11339,7 @@
 		.cmd = NL80211_CMD_DEL_PMKSA,
 		.doit = nl80211_setdel_pmksa,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11306,7 +11347,7 @@
 		.cmd = NL80211_CMD_FLUSH_PMKSA,
 		.doit = nl80211_flush_pmksa,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11314,7 +11355,7 @@
 		.cmd = NL80211_CMD_REMAIN_ON_CHANNEL,
 		.doit = nl80211_remain_on_channel,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11322,7 +11363,7 @@
 		.cmd = NL80211_CMD_CANCEL_REMAIN_ON_CHANNEL,
 		.doit = nl80211_cancel_remain_on_channel,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11330,7 +11371,7 @@
 		.cmd = NL80211_CMD_SET_TX_BITRATE_MASK,
 		.doit = nl80211_set_tx_bitrate_mask,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11338,7 +11379,7 @@
 		.cmd = NL80211_CMD_REGISTER_FRAME,
 		.doit = nl80211_register_mgmt,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11346,7 +11387,7 @@
 		.cmd = NL80211_CMD_FRAME,
 		.doit = nl80211_tx_mgmt,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11354,7 +11395,7 @@
 		.cmd = NL80211_CMD_FRAME_WAIT_CANCEL,
 		.doit = nl80211_tx_mgmt_cancel_wait,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11362,7 +11403,7 @@
 		.cmd = NL80211_CMD_SET_POWER_SAVE,
 		.doit = nl80211_set_power_save,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11378,7 +11419,7 @@
 		.cmd = NL80211_CMD_SET_CQM,
 		.doit = nl80211_set_cqm,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11386,7 +11427,7 @@
 		.cmd = NL80211_CMD_SET_CHANNEL,
 		.doit = nl80211_set_channel,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11394,7 +11435,7 @@
 		.cmd = NL80211_CMD_SET_WDS_PEER,
 		.doit = nl80211_set_wds_peer,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11402,7 +11443,7 @@
 		.cmd = NL80211_CMD_JOIN_MESH,
 		.doit = nl80211_join_mesh,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11410,7 +11451,7 @@
 		.cmd = NL80211_CMD_LEAVE_MESH,
 		.doit = nl80211_leave_mesh,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11418,7 +11459,7 @@
 		.cmd = NL80211_CMD_JOIN_OCB,
 		.doit = nl80211_join_ocb,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11426,7 +11467,7 @@
 		.cmd = NL80211_CMD_LEAVE_OCB,
 		.doit = nl80211_leave_ocb,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11443,7 +11484,7 @@
 		.cmd = NL80211_CMD_SET_WOWLAN,
 		.doit = nl80211_set_wowlan,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11452,7 +11493,7 @@
 		.cmd = NL80211_CMD_SET_REKEY_OFFLOAD,
 		.doit = nl80211_set_rekey_data,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL |
 				  NL80211_FLAG_CLEAR_SKB,
@@ -11461,7 +11502,7 @@
 		.cmd = NL80211_CMD_TDLS_MGMT,
 		.doit = nl80211_tdls_mgmt,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11469,7 +11510,7 @@
 		.cmd = NL80211_CMD_TDLS_OPER,
 		.doit = nl80211_tdls_oper,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11477,7 +11518,7 @@
 		.cmd = NL80211_CMD_UNEXPECTED_FRAME,
 		.doit = nl80211_register_unexpected_frame,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11485,7 +11526,7 @@
 		.cmd = NL80211_CMD_PROBE_CLIENT,
 		.doit = nl80211_probe_client,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11493,7 +11534,7 @@
 		.cmd = NL80211_CMD_REGISTER_BEACONS,
 		.doit = nl80211_register_beacons,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11501,7 +11542,7 @@
 		.cmd = NL80211_CMD_SET_NOACK_MAP,
 		.doit = nl80211_set_noack_map,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11509,7 +11550,7 @@
 		.cmd = NL80211_CMD_START_P2P_DEVICE,
 		.doit = nl80211_start_p2p_device,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11517,7 +11558,7 @@
 		.cmd = NL80211_CMD_STOP_P2P_DEVICE,
 		.doit = nl80211_stop_p2p_device,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11525,7 +11566,7 @@
 		.cmd = NL80211_CMD_SET_MCAST_RATE,
 		.doit = nl80211_set_mcast_rate,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11533,7 +11574,7 @@
 		.cmd = NL80211_CMD_SET_MAC_ACL,
 		.doit = nl80211_set_mac_acl,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11541,7 +11582,7 @@
 		.cmd = NL80211_CMD_RADAR_DETECT,
 		.doit = nl80211_start_radar_detection,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11554,7 +11595,7 @@
 		.cmd = NL80211_CMD_UPDATE_FT_IES,
 		.doit = nl80211_update_ft_ies,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11562,7 +11603,7 @@
 		.cmd = NL80211_CMD_CRIT_PROTOCOL_START,
 		.doit = nl80211_crit_protocol_start,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11570,7 +11611,7 @@
 		.cmd = NL80211_CMD_CRIT_PROTOCOL_STOP,
 		.doit = nl80211_crit_protocol_stop,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11585,7 +11626,7 @@
 		.cmd = NL80211_CMD_SET_COALESCE,
 		.doit = nl80211_set_coalesce,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11593,7 +11634,7 @@
 		.cmd = NL80211_CMD_CHANNEL_SWITCH,
 		.doit = nl80211_channel_switch,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11602,7 +11643,7 @@
 		.doit = nl80211_vendor_cmd,
 		.dumpit = nl80211_vendor_cmd_dump,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11610,7 +11651,7 @@
 		.cmd = NL80211_CMD_SET_QOS_MAP,
 		.doit = nl80211_set_qos_map,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11618,7 +11659,7 @@
 		.cmd = NL80211_CMD_ADD_TX_TS,
 		.doit = nl80211_add_tx_ts,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11626,7 +11667,7 @@
 		.cmd = NL80211_CMD_DEL_TX_TS,
 		.doit = nl80211_del_tx_ts,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11634,7 +11675,7 @@
 		.cmd = NL80211_CMD_TDLS_CHANNEL_SWITCH,
 		.doit = nl80211_tdls_channel_switch,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -11642,7 +11683,7 @@
 		.cmd = NL80211_CMD_TDLS_CANCEL_CHANNEL_SWITCH,
 		.doit = nl80211_tdls_cancel_channel_switch,
 		.policy = nl80211_policy,
-		.flags = GENL_ADMIN_PERM,
+		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
@@ -12092,7 +12133,7 @@
 				 struct net_device *netdev, const u8 *bssid,
 				 const u8 *req_ie, size_t req_ie_len,
 				 const u8 *resp_ie, size_t resp_ie_len,
-				 u16 status, gfp_t gfp)
+				 int status, gfp_t gfp)
 {
 	struct sk_buff *msg;
 	void *hdr;
@@ -12110,7 +12151,10 @@
 	if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) ||
 	    nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex) ||
 	    (bssid && nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, bssid)) ||
-	    nla_put_u16(msg, NL80211_ATTR_STATUS_CODE, status) ||
+	    nla_put_u16(msg, NL80211_ATTR_STATUS_CODE,
+			status < 0 ? WLAN_STATUS_UNSPECIFIED_FAILURE :
+			status) ||
+	    (status < 0 && nla_put_flag(msg, NL80211_ATTR_TIMED_OUT)) ||
 	    (req_ie &&
 	     nla_put(msg, NL80211_ATTR_REQ_IE, req_ie_len, req_ie)) ||
 	    (resp_ie &&
@@ -12126,7 +12170,6 @@
  nla_put_failure:
 	genlmsg_cancel(msg, hdr);
 	nlmsg_free(msg);
-
 }
 
 void nl80211_send_roamed(struct cfg80211_registered_device *rdev,
@@ -12165,7 +12208,6 @@
  nla_put_failure:
 	genlmsg_cancel(msg, hdr);
 	nlmsg_free(msg);
-
 }
 
 void nl80211_send_disconnected(struct cfg80211_registered_device *rdev,
@@ -12203,7 +12245,6 @@
  nla_put_failure:
 	genlmsg_cancel(msg, hdr);
 	nlmsg_free(msg);
-
 }
 
 void nl80211_send_ibss_bssid(struct cfg80211_registered_device *rdev,
@@ -13545,7 +13586,6 @@
 	if (hdr)
 		genlmsg_cancel(msg, hdr);
 	nlmsg_free(msg);
-
 }
 EXPORT_SYMBOL(cfg80211_crit_proto_stopped);
 
diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h
index 84d4edf..a63f402 100644
--- a/net/wireless/nl80211.h
+++ b/net/wireless/nl80211.h
@@ -55,7 +55,7 @@
 				 struct net_device *netdev, const u8 *bssid,
 				 const u8 *req_ie, size_t req_ie_len,
 				 const u8 *resp_ie, size_t resp_ie_len,
-				 u16 status, gfp_t gfp);
+				 int status, gfp_t gfp);
 void nl80211_send_roamed(struct cfg80211_registered_device *rdev,
 			 struct net_device *netdev, const u8 *bssid,
 			 const u8 *req_ie, size_t req_ie_len,
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index 584fdc3..add6824 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -244,9 +244,7 @@
 		if (cfg80211_conn_do_work(wdev)) {
 			__cfg80211_connect_result(
 					wdev->netdev, bssid,
-					NULL, 0, NULL, 0,
-					WLAN_STATUS_UNSPECIFIED_FAILURE,
-					false, NULL);
+					NULL, 0, NULL, 0, -1, false, NULL);
 		}
 		wdev_unlock(wdev);
 	}
@@ -648,7 +646,7 @@
 void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
 			       const u8 *req_ie, size_t req_ie_len,
 			       const u8 *resp_ie, size_t resp_ie_len,
-			       u16 status, bool wextev,
+			       int status, bool wextev,
 			       struct cfg80211_bss *bss)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
@@ -757,7 +755,7 @@
 void cfg80211_connect_bss(struct net_device *dev, const u8 *bssid,
 			  struct cfg80211_bss *bss, const u8 *req_ie,
 			  size_t req_ie_len, const u8 *resp_ie,
-			  size_t resp_ie_len, u16 status, gfp_t gfp)
+			  size_t resp_ie_len, int status, gfp_t gfp)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c
index 6250b1c..dbb2738e 100644
--- a/net/wireless/wext-core.c
+++ b/net/wireless/wext-core.c
@@ -958,8 +958,29 @@
 			return private(dev, iwr, cmd, info, handler);
 	}
 	/* Old driver API : call driver ioctl handler */
-	if (dev->netdev_ops->ndo_do_ioctl)
-		return dev->netdev_ops->ndo_do_ioctl(dev, ifr, cmd);
+	if (dev->netdev_ops->ndo_do_ioctl) {
+#ifdef CONFIG_COMPAT
+		if (info->flags & IW_REQUEST_FLAG_COMPAT) {
+			int ret = 0;
+			struct iwreq iwr_lcl;
+			struct compat_iw_point *iwp_compat = (void *) &iwr->u.data;
+
+			memcpy(&iwr_lcl, iwr, sizeof(struct iwreq));
+			iwr_lcl.u.data.pointer = compat_ptr(iwp_compat->pointer);
+			iwr_lcl.u.data.length = iwp_compat->length;
+			iwr_lcl.u.data.flags = iwp_compat->flags;
+
+			ret = dev->netdev_ops->ndo_do_ioctl(dev, (void *) &iwr_lcl, cmd);
+
+			iwp_compat->pointer = ptr_to_compat(iwr_lcl.u.data.pointer);
+			iwp_compat->length = iwr_lcl.u.data.length;
+			iwp_compat->flags = iwr_lcl.u.data.flags;
+
+			return ret;
+		} else
+#endif
+			return dev->netdev_ops->ndo_do_ioctl(dev, ifr, cmd);
+	}
 	return -EOPNOTSUPP;
 }
 
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 6750595..4904ced 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -2454,6 +2454,7 @@
 
 # Check for git id commit length and improperly formed commit descriptions
 		if ($in_commit_log && !$commit_log_possible_stack_dump &&
+		    $line !~ /^\s*(?:Link|Patchwork|http|BugLink):/i &&
 		    ($line =~ /\bcommit\s+[0-9a-f]{5,}\b/i ||
 		     ($line =~ /\b[0-9a-f]{12,40}\b/i &&
 		      $line !~ /[\<\[][0-9a-f]{12,40}[\>\]]/i &&
diff --git a/security/keys/compat.c b/security/keys/compat.c
index c8783b3..36c80bf 100644
--- a/security/keys/compat.c
+++ b/security/keys/compat.c
@@ -134,7 +134,7 @@
 
 	case KEYCTL_DH_COMPUTE:
 		return keyctl_dh_compute(compat_ptr(arg2), compat_ptr(arg3),
-					 arg4);
+					 arg4, compat_ptr(arg5));
 
 	default:
 		return -EOPNOTSUPP;
diff --git a/security/keys/dh.c b/security/keys/dh.c
index 880505a..531ed2e 100644
--- a/security/keys/dh.c
+++ b/security/keys/dh.c
@@ -78,7 +78,8 @@
 }
 
 long keyctl_dh_compute(struct keyctl_dh_params __user *params,
-		       char __user *buffer, size_t buflen)
+		       char __user *buffer, size_t buflen,
+		       void __user *reserved)
 {
 	long ret;
 	MPI base, private, prime, result;
@@ -97,6 +98,11 @@
 		goto out;
 	}
 
+	if (reserved) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	keylen = mpi_from_key(pcopy.prime, buflen, &prime);
 	if (keylen < 0 || !prime) {
 		/* buflen == 0 may be used to query the required buffer size,
diff --git a/security/keys/internal.h b/security/keys/internal.h
index 8ec7a52..a705a7d 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -260,10 +260,11 @@
 
 #ifdef CONFIG_KEY_DH_OPERATIONS
 extern long keyctl_dh_compute(struct keyctl_dh_params __user *, char __user *,
-			      size_t);
+			      size_t, void __user *);
 #else
 static inline long keyctl_dh_compute(struct keyctl_dh_params __user *params,
-				     char __user *buffer, size_t buflen)
+				     char __user *buffer, size_t buflen,
+				     void __user *reserved)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
index 3b135a0..d580ad0 100644
--- a/security/keys/keyctl.c
+++ b/security/keys/keyctl.c
@@ -1688,8 +1688,8 @@
 
 	case KEYCTL_DH_COMPUTE:
 		return keyctl_dh_compute((struct keyctl_dh_params __user *) arg2,
-					 (char __user *) arg3,
-					 (size_t) arg4);
+					 (char __user *) arg3, (size_t) arg4,
+					 (void __user *) arg5);
 
 	default:
 		return -EOPNOTSUPP;
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 9a0d144..94089fc 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -365,8 +365,11 @@
 
 #define IS_SKL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa170)
 #define IS_SKL_LP(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x9d70)
+#define IS_KBL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa171)
+#define IS_KBL_LP(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x9d71)
 #define IS_BXT(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x5a98)
-#define IS_SKL_PLUS(pci) (IS_SKL(pci) || IS_SKL_LP(pci) || IS_BXT(pci))
+#define IS_SKL_PLUS(pci) (IS_SKL(pci) || IS_SKL_LP(pci) || IS_BXT(pci)) || \
+			IS_KBL(pci) || IS_KBL_LP(pci)
 
 static char *driver_short_names[] = {
 	[AZX_DRIVER_ICH] = "HDA Intel",
@@ -2181,6 +2184,12 @@
 	/* Sunrise Point-LP */
 	{ PCI_DEVICE(0x8086, 0x9d70),
 	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_SKYLAKE },
+	/* Kabylake */
+	{ PCI_DEVICE(0x8086, 0xa171),
+	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_SKYLAKE },
+	/* Kabylake-LP */
+	{ PCI_DEVICE(0x8086, 0x9d71),
+	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_SKYLAKE },
 	/* Broxton-P(Apollolake) */
 	{ PCI_DEVICE(0x8086, 0x5a98),
 	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_BROXTON },
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index d53c25e..0fe18ed 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -346,6 +346,9 @@
 	case 0x10ec0234:
 	case 0x10ec0274:
 	case 0x10ec0294:
+	case 0x10ec0700:
+	case 0x10ec0701:
+	case 0x10ec0703:
 		alc_update_coef_idx(codec, 0x10, 1<<15, 0);
 		break;
 	case 0x10ec0662:
@@ -2655,6 +2658,7 @@
 	ALC269_TYPE_ALC256,
 	ALC269_TYPE_ALC225,
 	ALC269_TYPE_ALC294,
+	ALC269_TYPE_ALC700,
 };
 
 /*
@@ -2686,6 +2690,7 @@
 	case ALC269_TYPE_ALC256:
 	case ALC269_TYPE_ALC225:
 	case ALC269_TYPE_ALC294:
+	case ALC269_TYPE_ALC700:
 		ssids = alc269_ssids;
 		break;
 	default:
@@ -3618,13 +3623,20 @@
 static void alc_headset_mode_unplugged(struct hda_codec *codec)
 {
 	static struct coef_fw coef0255[] = {
-		WRITE_COEF(0x1b, 0x0c0b), /* LDO and MISC control */
 		WRITE_COEF(0x45, 0xd089), /* UAJ function set to menual mode */
 		UPDATE_COEFEX(0x57, 0x05, 1<<14, 0), /* Direct Drive HP Amp control(Set to verb control)*/
 		WRITE_COEF(0x06, 0x6104), /* Set MIC2 Vref gate with HP */
 		WRITE_COEFEX(0x57, 0x03, 0x8aa6), /* Direct Drive HP Amp control */
 		{}
 	};
+	static struct coef_fw coef0255_1[] = {
+		WRITE_COEF(0x1b, 0x0c0b), /* LDO and MISC control */
+		{}
+	};
+	static struct coef_fw coef0256[] = {
+		WRITE_COEF(0x1b, 0x0c4b), /* LDO and MISC control */
+		{}
+	};
 	static struct coef_fw coef0233[] = {
 		WRITE_COEF(0x1b, 0x0c0b),
 		WRITE_COEF(0x45, 0xc429),
@@ -3677,7 +3689,11 @@
 
 	switch (codec->core.vendor_id) {
 	case 0x10ec0255:
+		alc_process_coef_fw(codec, coef0255_1);
+		alc_process_coef_fw(codec, coef0255);
+		break;
 	case 0x10ec0256:
+		alc_process_coef_fw(codec, coef0256);
 		alc_process_coef_fw(codec, coef0255);
 		break;
 	case 0x10ec0233:
@@ -3896,6 +3912,12 @@
 		WRITE_COEFEX(0x57, 0x03, 0x8ea6),
 		{}
 	};
+	static struct coef_fw coef0256[] = {
+		WRITE_COEF(0x45, 0xd489), /* Set to CTIA type */
+		WRITE_COEF(0x1b, 0x0c6b),
+		WRITE_COEFEX(0x57, 0x03, 0x8ea6),
+		{}
+	};
 	static struct coef_fw coef0233[] = {
 		WRITE_COEF(0x45, 0xd429),
 		WRITE_COEF(0x1b, 0x0c2b),
@@ -3936,9 +3958,11 @@
 
 	switch (codec->core.vendor_id) {
 	case 0x10ec0255:
-	case 0x10ec0256:
 		alc_process_coef_fw(codec, coef0255);
 		break;
+	case 0x10ec0256:
+		alc_process_coef_fw(codec, coef0256);
+		break;
 	case 0x10ec0233:
 	case 0x10ec0283:
 		alc_process_coef_fw(codec, coef0233);
@@ -3978,6 +4002,12 @@
 		WRITE_COEFEX(0x57, 0x03, 0x8ea6),
 		{}
 	};
+	static struct coef_fw coef0256[] = {
+		WRITE_COEF(0x45, 0xe489), /* Set to OMTP Type */
+		WRITE_COEF(0x1b, 0x0c6b),
+		WRITE_COEFEX(0x57, 0x03, 0x8ea6),
+		{}
+	};
 	static struct coef_fw coef0233[] = {
 		WRITE_COEF(0x45, 0xe429),
 		WRITE_COEF(0x1b, 0x0c2b),
@@ -4018,9 +4048,11 @@
 
 	switch (codec->core.vendor_id) {
 	case 0x10ec0255:
-	case 0x10ec0256:
 		alc_process_coef_fw(codec, coef0255);
 		break;
+	case 0x10ec0256:
+		alc_process_coef_fw(codec, coef0256);
+		break;
 	case 0x10ec0233:
 	case 0x10ec0283:
 		alc_process_coef_fw(codec, coef0233);
@@ -4266,7 +4298,7 @@
 static void alc255_set_default_jack_type(struct hda_codec *codec)
 {
 	/* Set to iphone type */
-	static struct coef_fw fw[] = {
+	static struct coef_fw alc255fw[] = {
 		WRITE_COEF(0x1b, 0x880b),
 		WRITE_COEF(0x45, 0xd089),
 		WRITE_COEF(0x1b, 0x080b),
@@ -4274,7 +4306,22 @@
 		WRITE_COEF(0x1b, 0x0c0b),
 		{}
 	};
-	alc_process_coef_fw(codec, fw);
+	static struct coef_fw alc256fw[] = {
+		WRITE_COEF(0x1b, 0x884b),
+		WRITE_COEF(0x45, 0xd089),
+		WRITE_COEF(0x1b, 0x084b),
+		WRITE_COEF(0x46, 0x0004),
+		WRITE_COEF(0x1b, 0x0c4b),
+		{}
+	};
+	switch (codec->core.vendor_id) {
+	case 0x10ec0255:
+		alc_process_coef_fw(codec, alc255fw);
+		break;
+	case 0x10ec0256:
+		alc_process_coef_fw(codec, alc256fw);
+		break;
+	}
 	msleep(30);
 }
 
@@ -5587,6 +5634,7 @@
 	SND_PCI_QUIRK(0x17aa, 0x2218, "Thinkpad X1 Carbon 2nd", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x2223, "ThinkPad T550", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x2226, "ThinkPad X250", ALC292_FIXUP_TPT440_DOCK),
+	SND_PCI_QUIRK(0x17aa, 0x2231, "Thinkpad T560", ALC292_FIXUP_TPT460),
 	SND_PCI_QUIRK(0x17aa, 0x2233, "Thinkpad", ALC292_FIXUP_TPT460),
 	SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
 	SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
@@ -5775,6 +5823,10 @@
 		{0x12, 0x90a60180},
 		{0x14, 0x90170130},
 		{0x21, 0x02211040}),
+	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell Inspiron 5565", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x12, 0x90a60180},
+		{0x14, 0x90170120},
+		{0x21, 0x02211030}),
 	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
 		{0x12, 0x90a60160},
 		{0x14, 0x90170120},
@@ -6053,6 +6105,14 @@
 	case 0x10ec0294:
 		spec->codec_variant = ALC269_TYPE_ALC294;
 		break;
+	case 0x10ec0700:
+	case 0x10ec0701:
+	case 0x10ec0703:
+		spec->codec_variant = ALC269_TYPE_ALC700;
+		spec->gen.mixer_nid = 0; /* ALC700 does not have any loopback mixer path */
+		alc_update_coef_idx(codec, 0x4a, 0, 1 << 15); /* Combo jack auto trigger control */
+		break;
+
 	}
 
 	if (snd_hda_codec_read(codec, 0x51, 0, AC_VERB_PARAMETERS, 0) == 0x10ec5505) {
@@ -7008,6 +7068,9 @@
 	HDA_CODEC_ENTRY(0x10ec0670, "ALC670", patch_alc662),
 	HDA_CODEC_ENTRY(0x10ec0671, "ALC671", patch_alc662),
 	HDA_CODEC_ENTRY(0x10ec0680, "ALC680", patch_alc680),
+	HDA_CODEC_ENTRY(0x10ec0700, "ALC700", patch_alc269),
+	HDA_CODEC_ENTRY(0x10ec0701, "ALC701", patch_alc269),
+	HDA_CODEC_ENTRY(0x10ec0703, "ALC703", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0867, "ALC891", patch_alc882),
 	HDA_CODEC_ENTRY(0x10ec0880, "ALC880", patch_alc880),
 	HDA_CODEC_ENTRY(0x10ec0882, "ALC882", patch_alc882),
diff --git a/tools/testing/selftests/net/reuseport_bpf.c b/tools/testing/selftests/net/reuseport_bpf.c
index 96ba386..4a82174 100644
--- a/tools/testing/selftests/net/reuseport_bpf.c
+++ b/tools/testing/selftests/net/reuseport_bpf.c
@@ -111,9 +111,9 @@
 	memset(&attr, 0, sizeof(attr));
 	attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
 	attr.insn_cnt = ARRAY_SIZE(prog);
-	attr.insns = (uint64_t)prog;
-	attr.license = (uint64_t)bpf_license;
-	attr.log_buf = (uint64_t)bpf_log_buf;
+	attr.insns = (unsigned long) &prog;
+	attr.license = (unsigned long) &bpf_license;
+	attr.log_buf = (unsigned long) &bpf_log_buf;
 	attr.log_size = sizeof(bpf_log_buf);
 	attr.log_level = 1;
 	attr.kern_version = 0;
@@ -351,8 +351,8 @@
 	memset(&eprog, 0, sizeof(eprog));
 	eprog.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
 	eprog.insn_cnt = ARRAY_SIZE(ecode);
-	eprog.insns = (uint64_t)ecode;
-	eprog.license = (uint64_t)bpf_license;
+	eprog.insns = (unsigned long) &ecode;
+	eprog.license = (unsigned long) &bpf_license;
 	eprog.kern_version = 0;
 
 	memset(&cprog, 0, sizeof(cprog));
diff --git a/tools/virtio/ringtest/Makefile b/tools/virtio/ringtest/Makefile
index 6ba7455..50e086c 100644
--- a/tools/virtio/ringtest/Makefile
+++ b/tools/virtio/ringtest/Makefile
@@ -1,6 +1,6 @@
 all:
 
-all: ring virtio_ring_0_9 virtio_ring_poll virtio_ring_inorder
+all: ring virtio_ring_0_9 virtio_ring_poll virtio_ring_inorder ptr_ring
 
 CFLAGS += -Wall
 CFLAGS += -pthread -O2 -ggdb
@@ -8,6 +8,7 @@
 
 main.o: main.c main.h
 ring.o: ring.c main.h
+ptr_ring.o: ptr_ring.c main.h ../../../include/linux/ptr_ring.h
 virtio_ring_0_9.o: virtio_ring_0_9.c main.h
 virtio_ring_poll.o: virtio_ring_poll.c virtio_ring_0_9.c main.h
 virtio_ring_inorder.o: virtio_ring_inorder.c virtio_ring_0_9.c main.h
@@ -15,11 +16,13 @@
 virtio_ring_0_9: virtio_ring_0_9.o main.o
 virtio_ring_poll: virtio_ring_poll.o main.o
 virtio_ring_inorder: virtio_ring_inorder.o main.o
+ptr_ring: ptr_ring.o main.o
 clean:
 	-rm main.o
 	-rm ring.o ring
 	-rm virtio_ring_0_9.o virtio_ring_0_9
 	-rm virtio_ring_poll.o virtio_ring_poll
 	-rm virtio_ring_inorder.o virtio_ring_inorder
+	-rm ptr_ring.o ptr_ring
 
 .PHONY: all clean
diff --git a/tools/virtio/ringtest/ptr_ring.c b/tools/virtio/ringtest/ptr_ring.c
new file mode 100644
index 0000000..74abd74
--- /dev/null
+++ b/tools/virtio/ringtest/ptr_ring.c
@@ -0,0 +1,192 @@
+#define _GNU_SOURCE
+#include "main.h"
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <pthread.h>
+#include <malloc.h>
+#include <assert.h>
+#include <errno.h>
+#include <limits.h>
+
+#define SMP_CACHE_BYTES 64
+#define cache_line_size() SMP_CACHE_BYTES
+#define ____cacheline_aligned_in_smp __attribute__ ((aligned (SMP_CACHE_BYTES)))
+#define unlikely(x)    (__builtin_expect(!!(x), 0))
+#define ALIGN(x, a) (((x) + (a) - 1) / (a) * (a))
+typedef pthread_spinlock_t  spinlock_t;
+
+typedef int gfp_t;
+static void *kzalloc(unsigned size, gfp_t gfp)
+{
+	void *p = memalign(64, size);
+	if (!p)
+		return p;
+	memset(p, 0, size);
+
+	return p;
+}
+
+static void kfree(void *p)
+{
+	if (p)
+		free(p);
+}
+
+static void spin_lock_init(spinlock_t *lock)
+{
+	int r = pthread_spin_init(lock, 0);
+	assert(!r);
+}
+
+static void spin_lock(spinlock_t *lock)
+{
+	int ret = pthread_spin_lock(lock);
+	assert(!ret);
+}
+
+static void spin_unlock(spinlock_t *lock)
+{
+	int ret = pthread_spin_unlock(lock);
+	assert(!ret);
+}
+
+static void spin_lock_bh(spinlock_t *lock)
+{
+	spin_lock(lock);
+}
+
+static void spin_unlock_bh(spinlock_t *lock)
+{
+	spin_unlock(lock);
+}
+
+static void spin_lock_irq(spinlock_t *lock)
+{
+	spin_lock(lock);
+}
+
+static void spin_unlock_irq(spinlock_t *lock)
+{
+	spin_unlock(lock);
+}
+
+static void spin_lock_irqsave(spinlock_t *lock, unsigned long f)
+{
+	spin_lock(lock);
+}
+
+static void spin_unlock_irqrestore(spinlock_t *lock, unsigned long f)
+{
+	spin_unlock(lock);
+}
+
+#include "../../../include/linux/ptr_ring.h"
+
+static unsigned long long headcnt, tailcnt;
+static struct ptr_ring array ____cacheline_aligned_in_smp;
+
+/* implemented by ring */
+void alloc_ring(void)
+{
+	int ret = ptr_ring_init(&array, ring_size, 0);
+	assert(!ret);
+}
+
+/* guest side */
+int add_inbuf(unsigned len, void *buf, void *datap)
+{
+	int ret;
+
+	ret = __ptr_ring_produce(&array, buf);
+	if (ret >= 0) {
+		ret = 0;
+		headcnt++;
+	}
+
+	return ret;
+}
+
+/*
+ * ptr_ring API provides no way for producer to find out whether a given
+ * buffer was consumed.  Our tests merely require that a successful get_buf
+ * implies that add_inbuf succeed in the past, and that add_inbuf will succeed,
+ * fake it accordingly.
+ */
+void *get_buf(unsigned *lenp, void **bufp)
+{
+	void *datap;
+
+	if (tailcnt == headcnt || __ptr_ring_full(&array))
+		datap = NULL;
+	else {
+		datap = "Buffer\n";
+		++tailcnt;
+	}
+
+	return datap;
+}
+
+void poll_used(void)
+{
+	void *b;
+
+	do {
+		if (tailcnt == headcnt || __ptr_ring_full(&array)) {
+			b = NULL;
+			barrier();
+		} else {
+			b = "Buffer\n";
+		}
+	} while (!b);
+}
+
+void disable_call()
+{
+	assert(0);
+}
+
+bool enable_call()
+{
+	assert(0);
+}
+
+void kick_available(void)
+{
+	assert(0);
+}
+
+/* host side */
+void disable_kick()
+{
+	assert(0);
+}
+
+bool enable_kick()
+{
+	assert(0);
+}
+
+void poll_avail(void)
+{
+	void *b;
+
+	do {
+		barrier();
+		b = __ptr_ring_peek(&array);
+	} while (!b);
+}
+
+bool use_buf(unsigned *lenp, void **bufp)
+{
+	void *ptr;
+
+	ptr = __ptr_ring_consume(&array);
+
+	return ptr;
+}
+
+void call_used(void)
+{
+	assert(0);
+}
diff --git a/virt/kvm/arm/hyp/vgic-v2-sr.c b/virt/kvm/arm/hyp/vgic-v2-sr.c
index a3f12b3..3a3a699 100644
--- a/virt/kvm/arm/hyp/vgic-v2-sr.c
+++ b/virt/kvm/arm/hyp/vgic-v2-sr.c
@@ -100,12 +100,11 @@
 		if (!(vcpu->arch.vgic_cpu.live_lrs & (1UL << i)))
 			continue;
 
-		if (cpu_if->vgic_elrsr & (1UL << i)) {
+		if (cpu_if->vgic_elrsr & (1UL << i))
 			cpu_if->vgic_lr[i] &= ~GICH_LR_STATE;
-			continue;
-		}
+		else
+			cpu_if->vgic_lr[i] = readl_relaxed(base + GICH_LR0 + (i * 4));
 
-		cpu_if->vgic_lr[i] = readl_relaxed(base + GICH_LR0 + (i * 4));
 		writel_relaxed(0, base + GICH_LR0 + (i * 4));
 	}
 }
diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c
index 059595e..9f6fab7 100644
--- a/virt/kvm/arm/vgic/vgic-mmio.c
+++ b/virt/kvm/arm/vgic/vgic-mmio.c
@@ -191,10 +191,8 @@
 	 * other thread sync back the IRQ.
 	 */
 	while (irq->vcpu && /* IRQ may have state in an LR somewhere */
-	       irq->vcpu->cpu != -1) { /* VCPU thread is running */
-		BUG_ON(irq->intid < VGIC_NR_PRIVATE_IRQS);
+	       irq->vcpu->cpu != -1) /* VCPU thread is running */
 		cond_resched_lock(&irq->irq_lock);
-	}
 
 	irq->active = new_active_state;
 	if (new_active_state)
diff --git a/virt/kvm/arm/vgic/vgic-v2.c b/virt/kvm/arm/vgic/vgic-v2.c
index 8ad42c2..e31405e 100644
--- a/virt/kvm/arm/vgic/vgic-v2.c
+++ b/virt/kvm/arm/vgic/vgic-v2.c
@@ -112,11 +112,15 @@
 			}
 		}
 
-		/* Clear soft pending state when level IRQs have been acked */
-		if (irq->config == VGIC_CONFIG_LEVEL &&
-		    !(val & GICH_LR_PENDING_BIT)) {
-			irq->soft_pending = false;
-			irq->pending = irq->line_level;
+		/*
+		 * Clear soft pending state when level irqs have been acked.
+		 * Always regenerate the pending state.
+		 */
+		if (irq->config == VGIC_CONFIG_LEVEL) {
+			if (!(val & GICH_LR_PENDING_BIT))
+				irq->soft_pending = false;
+
+			irq->pending = irq->line_level || irq->soft_pending;
 		}
 
 		spin_unlock(&irq->irq_lock);
diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c
index 336a461..346b4ad 100644
--- a/virt/kvm/arm/vgic/vgic-v3.c
+++ b/virt/kvm/arm/vgic/vgic-v3.c
@@ -101,11 +101,15 @@
 			}
 		}
 
-		/* Clear soft pending state when level irqs have been acked */
-		if (irq->config == VGIC_CONFIG_LEVEL &&
-		    !(val & ICH_LR_PENDING_BIT)) {
-			irq->soft_pending = false;
-			irq->pending = irq->line_level;
+		/*
+		 * Clear soft pending state when level irqs have been acked.
+		 * Always regenerate the pending state.
+		 */
+		if (irq->config == VGIC_CONFIG_LEVEL) {
+			if (!(val & ICH_LR_PENDING_BIT))
+				irq->soft_pending = false;
+
+			irq->pending = irq->line_level || irq->soft_pending;
 		}
 
 		spin_unlock(&irq->irq_lock);
diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c
index fe84e1a..8db197b 100644
--- a/virt/kvm/irqchip.c
+++ b/virt/kvm/irqchip.c
@@ -40,7 +40,7 @@
 
 	irq_rt = srcu_dereference_check(kvm->irq_routing, &kvm->irq_srcu,
 					lockdep_is_held(&kvm->irq_lock));
-	if (gsi < irq_rt->nr_rt_entries) {
+	if (irq_rt && gsi < irq_rt->nr_rt_entries) {
 		hlist_for_each_entry(e, &irq_rt->map[gsi], link) {
 			entries[n] = *e;
 			++n;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 37af230..02e98f3 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2935,7 +2935,7 @@
 	case KVM_SET_GSI_ROUTING: {
 		struct kvm_irq_routing routing;
 		struct kvm_irq_routing __user *urouting;
-		struct kvm_irq_routing_entry *entries;
+		struct kvm_irq_routing_entry *entries = NULL;
 
 		r = -EFAULT;
 		if (copy_from_user(&routing, argp, sizeof(routing)))
@@ -2945,15 +2945,17 @@
 			goto out;
 		if (routing.flags)
 			goto out;
-		r = -ENOMEM;
-		entries = vmalloc(routing.nr * sizeof(*entries));
-		if (!entries)
-			goto out;
-		r = -EFAULT;
-		urouting = argp;
-		if (copy_from_user(entries, urouting->entries,
-				   routing.nr * sizeof(*entries)))
-			goto out_free_irq_routing;
+		if (routing.nr) {
+			r = -ENOMEM;
+			entries = vmalloc(routing.nr * sizeof(*entries));
+			if (!entries)
+				goto out;
+			r = -EFAULT;
+			urouting = argp;
+			if (copy_from_user(entries, urouting->entries,
+					   routing.nr * sizeof(*entries)))
+				goto out_free_irq_routing;
+		}
 		r = kvm_set_irq_routing(kvm, entries, routing.nr,
 					routing.flags);
 out_free_irq_routing: