diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-events b/Documentation/ABI/testing/sysfs-bus-event_source-devices-events
new file mode 100644
index 0000000..0adeb52
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-events
@@ -0,0 +1,62 @@
+What:		/sys/devices/cpu/events/
+		/sys/devices/cpu/events/branch-misses
+		/sys/devices/cpu/events/cache-references
+		/sys/devices/cpu/events/cache-misses
+		/sys/devices/cpu/events/stalled-cycles-frontend
+		/sys/devices/cpu/events/branch-instructions
+		/sys/devices/cpu/events/stalled-cycles-backend
+		/sys/devices/cpu/events/instructions
+		/sys/devices/cpu/events/cpu-cycles
+
+Date:		2013/01/08
+
+Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
+
+Description:	Generic performance monitoring events
+
+		A collection of performance monitoring events that may be
+		supported by many/most CPUs. These events can be monitored
+		using the 'perf(1)' tool.
+
+		The contents of each file would look like:
+
+			event=0xNNNN
+
+		where 'N' is a hex digit and the number '0xNNNN' shows the
+		"raw code" for the perf event identified by the file's
+		"basename".
+
+
+What: 		/sys/devices/cpu/events/PM_LD_MISS_L1
+		/sys/devices/cpu/events/PM_LD_REF_L1
+		/sys/devices/cpu/events/PM_CYC
+		/sys/devices/cpu/events/PM_BRU_FIN
+		/sys/devices/cpu/events/PM_GCT_NOSLOT_CYC
+		/sys/devices/cpu/events/PM_BRU_MPRED
+		/sys/devices/cpu/events/PM_INST_CMPL
+		/sys/devices/cpu/events/PM_CMPLU_STALL
+
+Date:		2013/01/08
+
+Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
+		Linux Powerpc mailing list <linuxppc-dev@ozlabs.org>
+
+Description:	POWER-systems specific performance monitoring events
+
+		A collection of performance monitoring events that may be
+		supported by the POWER CPU. These events can be monitored
+		using the 'perf(1)' tool.
+
+		These events may not be supported by other CPUs.
+
+		The contents of each file would look like:
+
+			event=0xNNNN
+
+		where 'N' is a hex digit and the number '0xNNNN' shows the
+		"raw code" for the perf event identified by the file's
+		"basename".
+
+		Further, multiple terms like 'event=0xNNNN' can be specified
+		and separated with comma. All available terms are defined in
+		the /sys/bus/event_source/devices/<dev>/format file.
diff --git a/Documentation/atomic_ops.txt b/Documentation/atomic_ops.txt
index 27f2b21..d9ca5be 100644
--- a/Documentation/atomic_ops.txt
+++ b/Documentation/atomic_ops.txt
@@ -253,6 +253,8 @@
 the given new value.  It returns the old value that the atomic variable v had
 just before the operation.
 
+atomic_xchg requires explicit memory barriers around the operation.
+
 	int atomic_cmpxchg(atomic_t *v, int old, int new);
 
 This performs an atomic compare exchange operation on the atomic value v,
diff --git a/Documentation/device-mapper/dm-raid.txt b/Documentation/device-mapper/dm-raid.txt
index 728c38c..56fb62b 100644
--- a/Documentation/device-mapper/dm-raid.txt
+++ b/Documentation/device-mapper/dm-raid.txt
@@ -141,3 +141,4 @@
 1.2.0	Handle creation of arrays that contain failed devices.
 1.3.0	Added support for RAID 10
 1.3.1	Allow device replacement/rebuild for RAID 10
+1.3.2   Fix/improve redundancy checking for RAID10
diff --git a/Documentation/devicetree/bindings/pinctrl/atmel,at91-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/atmel,at91-pinctrl.txt
index 3a26812..bc50899 100644
--- a/Documentation/devicetree/bindings/pinctrl/atmel,at91-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/atmel,at91-pinctrl.txt
@@ -81,7 +81,8 @@
 Required properties for pin configuration node:
 - atmel,pins: 4 integers array, represents a group of pins mux and config
   setting. The format is atmel,pins = <PIN_BANK PIN_BANK_NUM PERIPH CONFIG>.
-  The PERIPH 0 means gpio.
+  The PERIPH 0 means gpio, PERIPH 1 is periph A, PERIPH 2 is periph B...
+  PIN_BANK 0 is pioA, PIN_BANK 1 is pioB...
 
 Bits used for CONFIG:
 PULL_UP		(1 << 0): indicate this pin need a pull up.
@@ -126,7 +127,7 @@
 		pinctrl_dbgu: dbgu-0 {
 			atmel,pins =
 				<1 14 0x1 0x0	/* PB14 periph A */
-				 1 15 0x1 0x1>;	/* PB15 periph with pullup */
+				 1 15 0x1 0x1>;	/* PB15 periph A with pullup */
 		};
 	};
 };
diff --git a/Documentation/hid/hid-sensor.txt b/Documentation/hid/hid-sensor.txt
old mode 100755
new mode 100644
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 363e348..6c72381 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2438,7 +2438,7 @@
 			real-time workloads.  It can also improve energy
 			efficiency for asymmetric multiprocessors.
 
-	rcu_nocbs_poll	[KNL,BOOT]
+	rcu_nocb_poll	[KNL,BOOT]
 			Rather than requiring that offloaded CPUs
 			(specified by rcu_nocbs= above) explicitly
 			awaken the corresponding "rcuoN" kthreads,
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index 3c4e1b3..fa5d8a9 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -1685,6 +1685,7 @@
 
 	xchg();
 	cmpxchg();
+	atomic_xchg();
 	atomic_cmpxchg();
 	atomic_inc_return();
 	atomic_dec_return();
diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt
index 6f51fed..53d6a3c 100644
--- a/Documentation/trace/ftrace.txt
+++ b/Documentation/trace/ftrace.txt
@@ -1842,6 +1842,89 @@
  # cat buffer_size_kb
 85
 
+Snapshot
+--------
+CONFIG_TRACER_SNAPSHOT makes a generic snapshot feature
+available to all non latency tracers. (Latency tracers which
+record max latency, such as "irqsoff" or "wakeup", can't use
+this feature, since those are already using the snapshot
+mechanism internally.)
+
+Snapshot preserves a current trace buffer at a particular point
+in time without stopping tracing. Ftrace swaps the current
+buffer with a spare buffer, and tracing continues in the new
+current (=previous spare) buffer.
+
+The following debugfs files in "tracing" are related to this
+feature:
+
+  snapshot:
+
+	This is used to take a snapshot and to read the output
+	of the snapshot. Echo 1 into this file to allocate a
+	spare buffer and to take a snapshot (swap), then read
+	the snapshot from this file in the same format as
+	"trace" (described above in the section "The File
+	System"). Both reads snapshot and tracing are executable
+	in parallel. When the spare buffer is allocated, echoing
+	0 frees it, and echoing else (positive) values clear the
+	snapshot contents.
+	More details are shown in the table below.
+
+	status\input  |     0      |     1      |    else    |
+	--------------+------------+------------+------------+
+	not allocated |(do nothing)| alloc+swap |   EINVAL   |
+	--------------+------------+------------+------------+
+	allocated     |    free    |    swap    |   clear    |
+	--------------+------------+------------+------------+
+
+Here is an example of using the snapshot feature.
+
+ # echo 1 > events/sched/enable
+ # echo 1 > snapshot
+ # cat snapshot
+# tracer: nop
+#
+# entries-in-buffer/entries-written: 71/71   #P:8
+#
+#                              _-----=> irqs-off
+#                             / _----=> need-resched
+#                            | / _---=> hardirq/softirq
+#                            || / _--=> preempt-depth
+#                            ||| /     delay
+#           TASK-PID   CPU#  ||||    TIMESTAMP  FUNCTION
+#              | |       |   ||||       |         |
+          <idle>-0     [005] d...  2440.603828: sched_switch: prev_comm=swapper/5 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=snapshot-test-2 next_pid=2242 next_prio=120
+           sleep-2242  [005] d...  2440.603846: sched_switch: prev_comm=snapshot-test-2 prev_pid=2242 prev_prio=120 prev_state=R ==> next_comm=kworker/5:1 next_pid=60 next_prio=120
+[...]
+          <idle>-0     [002] d...  2440.707230: sched_switch: prev_comm=swapper/2 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=snapshot-test-2 next_pid=2229 next_prio=120
+
+ # cat trace
+# tracer: nop
+#
+# entries-in-buffer/entries-written: 77/77   #P:8
+#
+#                              _-----=> irqs-off
+#                             / _----=> need-resched
+#                            | / _---=> hardirq/softirq
+#                            || / _--=> preempt-depth
+#                            ||| /     delay
+#           TASK-PID   CPU#  ||||    TIMESTAMP  FUNCTION
+#              | |       |   ||||       |         |
+          <idle>-0     [007] d...  2440.707395: sched_switch: prev_comm=swapper/7 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=snapshot-test-2 next_pid=2243 next_prio=120
+ snapshot-test-2-2229  [002] d...  2440.707438: sched_switch: prev_comm=snapshot-test-2 prev_pid=2229 prev_prio=120 prev_state=S ==> next_comm=swapper/2 next_pid=0 next_prio=120
+[...]
+
+
+If you try to use this snapshot feature when current tracer is
+one of the latency tracers, you will get the following results.
+
+ # echo wakeup > current_tracer
+ # echo 1 > snapshot
+bash: echo: write error: Device or resource busy
+ # cat snapshot
+cat: snapshot: Device or resource busy
+
 -----------
 
 More details can be found in the source code, in the
diff --git a/Documentation/x86/boot.txt b/Documentation/x86/boot.txt
index 406d82d..b443f1d 100644
--- a/Documentation/x86/boot.txt
+++ b/Documentation/x86/boot.txt
@@ -57,6 +57,10 @@
 Protocol 2.11:	(Kernel 3.6) Added a field for offset of EFI handover
 		protocol entry point.
 
+Protocol 2.12:	(Kernel 3.8) Added the xloadflags field and extension fields
+	 	to struct boot_params for for loading bzImage and ramdisk
+		above 4G in 64bit.
+
 **** MEMORY LAYOUT
 
 The traditional memory map for the kernel loader, used for Image or
@@ -182,7 +186,7 @@
 0230/4	2.05+	kernel_alignment Physical addr alignment required for kernel
 0234/1	2.05+	relocatable_kernel Whether kernel is relocatable or not
 0235/1	2.10+	min_alignment	Minimum alignment, as a power of two
-0236/2	N/A	pad3		Unused
+0236/2	2.12+	xloadflags	Boot protocol option flags
 0238/4	2.06+	cmdline_size	Maximum size of the kernel command line
 023C/4	2.07+	hardware_subarch Hardware subarchitecture
 0240/8	2.07+	hardware_subarch_data Subarchitecture-specific data
@@ -386,6 +390,7 @@
 	F  Special		(0xFF = undefined)
        10  Reserved
        11  Minimal Linux Bootloader <http://sebastian-plotz.blogspot.de>
+       12  OVMF UEFI virtualization stack
 
   Please contact <hpa@zytor.com> if you need a bootloader ID
   value assigned.
@@ -582,6 +587,27 @@
   misaligned kernel.  Therefore, a loader should typically try each
   power-of-two alignment from kernel_alignment down to this alignment.
 
+Field name:     xloadflags
+Type:           read
+Offset/size:    0x236/2
+Protocol:       2.12+
+
+  This field is a bitmask.
+
+  Bit 0 (read):	XLF_KERNEL_64
+	- If 1, this kernel has the legacy 64-bit entry point at 0x200.
+
+  Bit 1 (read): XLF_CAN_BE_LOADED_ABOVE_4G
+        - If 1, kernel/boot_params/cmdline/ramdisk can be above 4G.
+
+  Bit 2 (read):	XLF_EFI_HANDOVER_32
+	- If 1, the kernel supports the 32-bit EFI handoff entry point
+          given at handover_offset.
+
+  Bit 3 (read): XLF_EFI_HANDOVER_64
+	- If 1, the kernel supports the 64-bit EFI handoff entry point
+          given at handover_offset + 0x200.
+
 Field name:	cmdline_size
 Type:		read
 Offset/size:	0x238/4
diff --git a/Documentation/x86/zero-page.txt b/Documentation/x86/zero-page.txt
index cf5437d..199f453 100644
--- a/Documentation/x86/zero-page.txt
+++ b/Documentation/x86/zero-page.txt
@@ -19,6 +19,9 @@
 090/010	ALL	hd1_info	hd1 disk parameter, OBSOLETE!!
 0A0/010	ALL	sys_desc_table	System description table (struct sys_desc_table)
 0B0/010	ALL	olpc_ofw_header	OLPC's OpenFirmware CIF and friends
+0C0/004	ALL	ext_ramdisk_image ramdisk_image high 32bits
+0C4/004	ALL	ext_ramdisk_size  ramdisk_size high 32bits
+0C8/004	ALL	ext_cmd_line_ptr  cmd_line_ptr high 32bits
 140/080	ALL	edid_info	Video mode setup (struct edid_info)
 1C0/020	ALL	efi_info	EFI 32 information (struct efi_info)
 1E0/004	ALL	alk_mem_k	Alternative mem check, in KB
@@ -27,6 +30,7 @@
 1E9/001	ALL	eddbuf_entries	Number of entries in eddbuf (below)
 1EA/001	ALL	edd_mbr_sig_buf_entries	Number of entries in edd_mbr_sig_buffer
 				(below)
+1EF/001	ALL	sentinel	Used to detect broken bootloaders
 290/040	ALL	edd_mbr_sig_buffer EDD MBR signatures
 2D0/A00	ALL	e820_map	E820 memory map table
 				(array of struct e820entry)
diff --git a/MAINTAINERS b/MAINTAINERS
index 8ae709e..3b95564 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1303,7 +1303,7 @@
 F:	include/linux/async_tx.h
 
 AT24 EEPROM DRIVER
-M:	Wolfram Sang <w.sang@pengutronix.de>
+M:	Wolfram Sang <wsa@the-dreams.de>
 L:	linux-i2c@vger.kernel.org
 S:	Maintained
 F:	drivers/misc/eeprom/at24.c
@@ -1489,7 +1489,7 @@
 M:	Haavard Skinnemoen <hskinnemoen@gmail.com>
 M:	Hans-Christian Egtvedt <egtvedt@samfundet.no>
 W:	http://www.atmel.com/products/AVR32/
-W:	http://avr32linux.org/
+W:	http://mirror.egtvedt.no/avr32linux.org/
 W:	http://avrfreaks.net/
 S:	Maintained
 F:	arch/avr32/
@@ -2966,7 +2966,7 @@
 F:	drivers/net/ethernet/i825xx/eexpress.*
 
 ETHERNET BRIDGE
-M:	Stephen Hemminger <shemminger@vyatta.com>
+M:	Stephen Hemminger <stephen@networkplumber.org>
 L:	bridge@lists.linux-foundation.org
 L:	netdev@vger.kernel.org
 W:	http://www.linuxfoundation.org/en/Net:Bridge
@@ -3757,12 +3757,11 @@
 F:	drivers/i2c/i2c-stub.c
 
 I2C SUBSYSTEM
-M:	Wolfram Sang <w.sang@pengutronix.de>
+M:	Wolfram Sang <wsa@the-dreams.de>
 M:	"Ben Dooks (embedded platforms)" <ben-linux@fluff.org>
 L:	linux-i2c@vger.kernel.org
 W:	http://i2c.wiki.kernel.org/
-T:	quilt kernel.org/pub/linux/kernel/people/jdelvare/linux-2.6/jdelvare-i2c/
-T:	git git://git.pengutronix.de/git/wsa/linux.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/wsa/linux.git
 S:	Maintained
 F:	Documentation/i2c/
 F:	drivers/i2c/
@@ -4905,7 +4904,7 @@
 
 MARVELL GIGABIT ETHERNET DRIVERS (skge/sky2)
 M:	Mirko Lindner <mlindner@marvell.com>
-M:	Stephen Hemminger <shemminger@vyatta.com>
+M:	Stephen Hemminger <stephen@networkplumber.org>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/ethernet/marvell/sk*
@@ -5180,7 +5179,7 @@
 F:	drivers/infiniband/hw/nes/
 
 NETEM NETWORK EMULATOR
-M:	Stephen Hemminger <shemminger@vyatta.com>
+M:	Stephen Hemminger <stephen@networkplumber.org>
 L:	netem@lists.linux-foundation.org
 S:	Maintained
 F:	net/sched/sch_netem.c
@@ -5778,15 +5777,6 @@
 S:	Maintained
 F:	drivers/i2c/muxes/i2c-mux-pca9541.c
 
-PCA9564/PCA9665 I2C BUS DRIVER
-M:	Wolfram Sang <w.sang@pengutronix.de>
-L:	linux-i2c@vger.kernel.org
-S:	Maintained
-F:	drivers/i2c/algos/i2c-algo-pca.c
-F:	drivers/i2c/busses/i2c-pca-*
-F:	include/linux/i2c-algo-pca.h
-F:	include/linux/i2c-pca-platform.h
-
 PCDP - PRIMARY CONSOLE AND DEBUG PORT
 M:	Khalid Aziz <khalid@gonehiking.org>
 S:	Maintained
@@ -7088,7 +7078,7 @@
 F:	sound/
 
 SOUND - SOC LAYER / DYNAMIC AUDIO POWER MANAGEMENT (ASoC)
-M:	Liam Girdwood <lrg@ti.com>
+M:	Liam Girdwood <lgirdwood@gmail.com>
 M:	Mark Brown <broonie@opensource.wolfsonmicro.com>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound.git
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
diff --git a/Makefile b/Makefile
index 2cd4c6b..d69266c 100644
--- a/Makefile
+++ b/Makefile
@@ -1,8 +1,8 @@
 VERSION = 3
 PATCHLEVEL = 8
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
-NAME = Terrified Chipmunk
+EXTRAVERSION =
+NAME = Unicycling Gorilla
 
 # *DOCUMENTATION*
 # To see a list of typical targets execute "make help"
diff --git a/arch/Kconfig b/arch/Kconfig
index 7f8f281..97fb7d0 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -76,6 +76,15 @@
 	depends on KPROBES && HAVE_OPTPROBES
 	depends on !PREEMPT
 
+config KPROBES_ON_FTRACE
+	def_bool y
+	depends on KPROBES && HAVE_KPROBES_ON_FTRACE
+	depends on DYNAMIC_FTRACE_WITH_REGS
+	help
+	 If function tracer is enabled and the arch supports full
+	 passing of pt_regs to function tracing, then kprobes can
+	 optimize on top of function tracing.
+
 config UPROBES
 	bool "Transparent user-space probes (EXPERIMENTAL)"
 	depends on UPROBE_EVENT && PERF_EVENTS
@@ -158,6 +167,9 @@
 config HAVE_OPTPROBES
 	bool
 
+config HAVE_KPROBES_ON_FTRACE
+	bool
+
 config HAVE_NMI_WATCHDOG
 	bool
 #
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index 9d5904c..9b504af 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -5,7 +5,6 @@
 	select HAVE_IDE
 	select HAVE_OPROFILE
 	select HAVE_SYSCALL_WRAPPERS
-	select HAVE_IRQ_WORK
 	select HAVE_PCSPKR_PLATFORM
 	select HAVE_PERF_EVENTS
 	select HAVE_DMA_ATTRS
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 67874b8..9bbe760 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -36,7 +36,6 @@
 	select HAVE_GENERIC_HARDIRQS
 	select HAVE_HW_BREAKPOINT if (PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7))
 	select HAVE_IDE if PCI || ISA || PCMCIA
-	select HAVE_IRQ_WORK
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZMA
 	select HAVE_KERNEL_LZO
diff --git a/arch/arm/boot/dts/armada-370-db.dts b/arch/arm/boot/dts/armada-370-db.dts
index 0004402..9b82fac 100644
--- a/arch/arm/boot/dts/armada-370-db.dts
+++ b/arch/arm/boot/dts/armada-370-db.dts
@@ -26,7 +26,7 @@
 
 	memory {
 		device_type = "memory";
-		reg = <0x00000000 0x20000000>; /* 512 MB */
+		reg = <0x00000000 0x40000000>; /* 1 GB */
 	};
 
 	soc {
diff --git a/arch/arm/boot/dts/armada-xp-mv78230.dtsi b/arch/arm/boot/dts/armada-xp-mv78230.dtsi
index 271855a..e041f42 100644
--- a/arch/arm/boot/dts/armada-xp-mv78230.dtsi
+++ b/arch/arm/boot/dts/armada-xp-mv78230.dtsi
@@ -50,27 +50,25 @@
 		};
 
 		gpio0: gpio@d0018100 {
-			compatible = "marvell,armadaxp-gpio";
-			reg = <0xd0018100 0x40>,
-			    <0xd0018800 0x30>;
+			compatible = "marvell,orion-gpio";
+			reg = <0xd0018100 0x40>;
 			ngpios = <32>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupts-cells = <2>;
-			interrupts = <16>, <17>, <18>, <19>;
+			interrupts = <82>, <83>, <84>, <85>;
 		};
 
 		gpio1: gpio@d0018140 {
-			compatible = "marvell,armadaxp-gpio";
-			reg = <0xd0018140 0x40>,
-			    <0xd0018840 0x30>;
+			compatible = "marvell,orion-gpio";
+			reg = <0xd0018140 0x40>;
 			ngpios = <17>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupts-cells = <2>;
-			interrupts = <20>, <21>, <22>;
+			interrupts = <87>, <88>, <89>;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/armada-xp-mv78260.dtsi b/arch/arm/boot/dts/armada-xp-mv78260.dtsi
index 1c1937d..9e23bd8 100644
--- a/arch/arm/boot/dts/armada-xp-mv78260.dtsi
+++ b/arch/arm/boot/dts/armada-xp-mv78260.dtsi
@@ -51,39 +51,36 @@
 		};
 
 		gpio0: gpio@d0018100 {
-			compatible = "marvell,armadaxp-gpio";
-			reg = <0xd0018100 0x40>,
-			    <0xd0018800 0x30>;
+			compatible = "marvell,orion-gpio";
+			reg = <0xd0018100 0x40>;
 			ngpios = <32>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupts-cells = <2>;
-			interrupts = <16>, <17>, <18>, <19>;
+			interrupts = <82>, <83>, <84>, <85>;
 		};
 
 		gpio1: gpio@d0018140 {
-			compatible = "marvell,armadaxp-gpio";
-			reg = <0xd0018140 0x40>,
-			    <0xd0018840 0x30>;
+			compatible = "marvell,orion-gpio";
+			reg = <0xd0018140 0x40>;
 			ngpios = <32>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupts-cells = <2>;
-			interrupts = <20>, <21>, <22>, <23>;
+			interrupts = <87>, <88>, <89>, <90>;
 		};
 
 		gpio2: gpio@d0018180 {
-			compatible = "marvell,armadaxp-gpio";
-			reg = <0xd0018180 0x40>,
-			    <0xd0018870 0x30>;
+			compatible = "marvell,orion-gpio";
+			reg = <0xd0018180 0x40>;
 			ngpios = <3>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupts-cells = <2>;
-			interrupts = <24>;
+			interrupts = <91>;
 		};
 
 		ethernet@d0034000 {
diff --git a/arch/arm/boot/dts/armada-xp-mv78460.dtsi b/arch/arm/boot/dts/armada-xp-mv78460.dtsi
index 4905cf3..9659661 100644
--- a/arch/arm/boot/dts/armada-xp-mv78460.dtsi
+++ b/arch/arm/boot/dts/armada-xp-mv78460.dtsi
@@ -66,39 +66,36 @@
 		};
 
 		gpio0: gpio@d0018100 {
-			compatible = "marvell,armadaxp-gpio";
-			reg = <0xd0018100 0x40>,
-			    <0xd0018800 0x30>;
+			compatible = "marvell,orion-gpio";
+			reg = <0xd0018100 0x40>;
 			ngpios = <32>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupts-cells = <2>;
-			interrupts = <16>, <17>, <18>, <19>;
+			interrupts = <82>, <83>, <84>, <85>;
 		};
 
 		gpio1: gpio@d0018140 {
-			compatible = "marvell,armadaxp-gpio";
-			reg = <0xd0018140 0x40>,
-			    <0xd0018840 0x30>;
+			compatible = "marvell,orion-gpio";
+			reg = <0xd0018140 0x40>;
 			ngpios = <32>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupts-cells = <2>;
-			interrupts = <20>, <21>, <22>, <23>;
+			interrupts = <87>, <88>, <89>, <90>;
 		};
 
 		gpio2: gpio@d0018180 {
-			compatible = "marvell,armadaxp-gpio";
-			reg = <0xd0018180 0x40>,
-			    <0xd0018870 0x30>;
+			compatible = "marvell,orion-gpio";
+			reg = <0xd0018180 0x40>;
 			ngpios = <3>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupts-cells = <2>;
-			interrupts = <24>;
+			interrupts = <91>;
 		};
 
 		ethernet@d0034000 {
diff --git a/arch/arm/boot/dts/at91rm9200.dtsi b/arch/arm/boot/dts/at91rm9200.dtsi
index e154f24..222047f 100644
--- a/arch/arm/boot/dts/at91rm9200.dtsi
+++ b/arch/arm/boot/dts/at91rm9200.dtsi
@@ -336,8 +336,8 @@
 
 	i2c@0 {
 		compatible = "i2c-gpio";
-		gpios = <&pioA 23 0 /* sda */
-			 &pioA 24 0 /* scl */
+		gpios = <&pioA 25 0 /* sda */
+			 &pioA 26 0 /* scl */
 			>;
 		i2c-gpio,sda-open-drain;
 		i2c-gpio,scl-open-drain;
diff --git a/arch/arm/boot/dts/at91sam9x5.dtsi b/arch/arm/boot/dts/at91sam9x5.dtsi
index 3a47cf9..8ecca69 100644
--- a/arch/arm/boot/dts/at91sam9x5.dtsi
+++ b/arch/arm/boot/dts/at91sam9x5.dtsi
@@ -143,6 +143,11 @@
 						atmel,pins =
 							<0 3 0x1 0x0>;	/* PA3 periph A */
 					};
+
+					pinctrl_usart0_sck: usart0_sck-0 {
+						atmel,pins =
+							<0 4 0x1 0x0>;	/* PA4 periph A */
+					};
 				};
 
 				usart1 {
@@ -154,12 +159,17 @@
 
 					pinctrl_usart1_rts: usart1_rts-0 {
 						atmel,pins =
-							<3 27 0x3 0x0>;	/* PC27 periph C */
+							<2 27 0x3 0x0>;	/* PC27 periph C */
 					};
 
 					pinctrl_usart1_cts: usart1_cts-0 {
 						atmel,pins =
-							<3 28 0x3 0x0>;	/* PC28 periph C */
+							<2 28 0x3 0x0>;	/* PC28 periph C */
+					};
+
+					pinctrl_usart1_sck: usart1_sck-0 {
+						atmel,pins =
+							<2 28 0x3 0x0>;	/* PC29 periph C */
 					};
 				};
 
@@ -172,46 +182,56 @@
 
 					pinctrl_uart2_rts: uart2_rts-0 {
 						atmel,pins =
-							<0 0 0x2 0x0>;	/* PB0 periph B */
+							<1 0 0x2 0x0>;	/* PB0 periph B */
 					};
 
 					pinctrl_uart2_cts: uart2_cts-0 {
 						atmel,pins =
-							<0 1 0x2 0x0>;	/* PB1 periph B */
+							<1 1 0x2 0x0>;	/* PB1 periph B */
+					};
+
+					pinctrl_usart2_sck: usart2_sck-0 {
+						atmel,pins =
+							<1 2 0x2 0x0>;	/* PB2 periph B */
 					};
 				};
 
 				usart3 {
 					pinctrl_uart3: usart3-0 {
 						atmel,pins =
-							<3 23 0x2 0x1	/* PC22 periph B with pullup */
-							 3 23 0x2 0x0>;	/* PC23 periph B */
+							<2 23 0x2 0x1	/* PC22 periph B with pullup */
+							 2 23 0x2 0x0>;	/* PC23 periph B */
 					};
 
 					pinctrl_usart3_rts: usart3_rts-0 {
 						atmel,pins =
-							<3 24 0x2 0x0>;	/* PC24 periph B */
+							<2 24 0x2 0x0>;	/* PC24 periph B */
 					};
 
 					pinctrl_usart3_cts: usart3_cts-0 {
 						atmel,pins =
-							<3 25 0x2 0x0>;	/* PC25 periph B */
+							<2 25 0x2 0x0>;	/* PC25 periph B */
+					};
+
+					pinctrl_usart3_sck: usart3_sck-0 {
+						atmel,pins =
+							<2 26 0x2 0x0>;	/* PC26 periph B */
 					};
 				};
 
 				uart0 {
 					pinctrl_uart0: uart0-0 {
 						atmel,pins =
-							<3 8 0x3 0x0	/* PC8 periph C */
-							 3 9 0x3 0x1>;	/* PC9 periph C with pullup */
+							<2 8 0x3 0x0	/* PC8 periph C */
+							 2 9 0x3 0x1>;	/* PC9 periph C with pullup */
 					};
 				};
 
 				uart1 {
 					pinctrl_uart1: uart1-0 {
 						atmel,pins =
-							<3 16 0x3 0x0	/* PC16 periph C */
-							 3 17 0x3 0x1>;	/* PC17 periph C with pullup */
+							<2 16 0x3 0x0	/* PC16 periph C */
+							 2 17 0x3 0x1>;	/* PC17 periph C with pullup */
 					};
 				};
 
@@ -240,14 +260,14 @@
 
 					pinctrl_macb0_rmii_mii: macb0_rmii_mii-0 {
 						atmel,pins =
-							<1 8 0x1 0x0	/* PA8 periph A */
-							 1 11 0x1 0x0	/* PA11 periph A */
-							 1 12 0x1 0x0	/* PA12 periph A */
-							 1 13 0x1 0x0	/* PA13 periph A */
-							 1 14 0x1 0x0	/* PA14 periph A */
-							 1 15 0x1 0x0	/* PA15 periph A */
-							 1 16 0x1 0x0	/* PA16 periph A */
-							 1 17 0x1 0x0>;	/* PA17 periph A */
+							<1 8 0x1 0x0	/* PB8 periph A */
+							 1 11 0x1 0x0	/* PB11 periph A */
+							 1 12 0x1 0x0	/* PB12 periph A */
+							 1 13 0x1 0x0	/* PB13 periph A */
+							 1 14 0x1 0x0	/* PB14 periph A */
+							 1 15 0x1 0x0	/* PB15 periph A */
+							 1 16 0x1 0x0	/* PB16 periph A */
+							 1 17 0x1 0x0>;	/* PB17 periph A */
 					};
 				};
 
diff --git a/arch/arm/boot/dts/cros5250-common.dtsi b/arch/arm/boot/dts/cros5250-common.dtsi
index fddd174..46c0980 100644
--- a/arch/arm/boot/dts/cros5250-common.dtsi
+++ b/arch/arm/boot/dts/cros5250-common.dtsi
@@ -96,8 +96,8 @@
 		fifo-depth = <0x80>;
 		card-detect-delay = <200>;
 		samsung,dw-mshc-ciu-div = <3>;
-		samsung,dw-mshc-sdr-timing = <2 3 3>;
-		samsung,dw-mshc-ddr-timing = <1 2 3>;
+		samsung,dw-mshc-sdr-timing = <2 3>;
+		samsung,dw-mshc-ddr-timing = <1 2>;
 
 		slot@0 {
 			reg = <0>;
@@ -120,8 +120,8 @@
 		fifo-depth = <0x80>;
 		card-detect-delay = <200>;
 		samsung,dw-mshc-ciu-div = <3>;
-		samsung,dw-mshc-sdr-timing = <2 3 3>;
-		samsung,dw-mshc-ddr-timing = <1 2 3>;
+		samsung,dw-mshc-sdr-timing = <2 3>;
+		samsung,dw-mshc-ddr-timing = <1 2>;
 
 		slot@0 {
 			reg = <0>;
@@ -141,8 +141,8 @@
 		fifo-depth = <0x80>;
 		card-detect-delay = <200>;
 		samsung,dw-mshc-ciu-div = <3>;
-		samsung,dw-mshc-sdr-timing = <2 3 3>;
-		samsung,dw-mshc-ddr-timing = <1 2 3>;
+		samsung,dw-mshc-sdr-timing = <2 3>;
+		samsung,dw-mshc-ddr-timing = <1 2>;
 
 		slot@0 {
 			reg = <0>;
diff --git a/arch/arm/boot/dts/dove-cubox.dts b/arch/arm/boot/dts/dove-cubox.dts
index fed7d3f..cdee96f 100644
--- a/arch/arm/boot/dts/dove-cubox.dts
+++ b/arch/arm/boot/dts/dove-cubox.dts
@@ -26,10 +26,15 @@
 };
 
 &uart0 { status = "okay"; };
-&sdio0 { status = "okay"; };
 &sata0 { status = "okay"; };
 &i2c0 { status = "okay"; };
 
+&sdio0 {
+	status = "okay";
+	/* sdio0 card detect is connected to wrong pin on CuBox */
+	cd-gpios = <&gpio0 12 1>;
+};
+
 &spi0 {
 	status = "okay";
 
@@ -42,9 +47,14 @@
 };
 
 &pinctrl {
-	pinctrl-0 = <&pmx_gpio_18>;
+	pinctrl-0 = <&pmx_gpio_12 &pmx_gpio_18>;
 	pinctrl-names = "default";
 
+	pmx_gpio_12: pmx-gpio-12 {
+		marvell,pins = "mpp12";
+		marvell,function = "gpio";
+	};
+
 	pmx_gpio_18: pmx-gpio-18 {
 		marvell,pins = "mpp18";
 		marvell,function = "gpio";
diff --git a/arch/arm/boot/dts/exynos5250-smdk5250.dts b/arch/arm/boot/dts/exynos5250-smdk5250.dts
index 942d576..e05b18f 100644
--- a/arch/arm/boot/dts/exynos5250-smdk5250.dts
+++ b/arch/arm/boot/dts/exynos5250-smdk5250.dts
@@ -115,8 +115,8 @@
 		fifo-depth = <0x80>;
 		card-detect-delay = <200>;
 		samsung,dw-mshc-ciu-div = <3>;
-		samsung,dw-mshc-sdr-timing = <2 3 3>;
-		samsung,dw-mshc-ddr-timing = <1 2 3>;
+		samsung,dw-mshc-sdr-timing = <2 3>;
+		samsung,dw-mshc-ddr-timing = <1 2>;
 
 		slot@0 {
 			reg = <0>;
@@ -139,8 +139,8 @@
 		fifo-depth = <0x80>;
 		card-detect-delay = <200>;
 		samsung,dw-mshc-ciu-div = <3>;
-		samsung,dw-mshc-sdr-timing = <2 3 3>;
-		samsung,dw-mshc-ddr-timing = <1 2 3>;
+		samsung,dw-mshc-sdr-timing = <2 3>;
+		samsung,dw-mshc-ddr-timing = <1 2>;
 
 		slot@0 {
 			reg = <0>;
diff --git a/arch/arm/boot/dts/kirkwood-ns2-common.dtsi b/arch/arm/boot/dts/kirkwood-ns2-common.dtsi
index 9bc6785..77d21ab 100644
--- a/arch/arm/boot/dts/kirkwood-ns2-common.dtsi
+++ b/arch/arm/boot/dts/kirkwood-ns2-common.dtsi
@@ -1,4 +1,5 @@
 /include/ "kirkwood.dtsi"
+/include/ "kirkwood-6281.dtsi"
 
 / {
 	chosen {
@@ -6,6 +7,21 @@
 	};
 
 	ocp@f1000000 {
+		pinctrl: pinctrl@10000 {
+			pinctrl-0 = < &pmx_spi &pmx_twsi0 &pmx_uart0
+					&pmx_ns2_sata0 &pmx_ns2_sata1>;
+			pinctrl-names = "default";
+
+			pmx_ns2_sata0: pmx-ns2-sata0 {
+				marvell,pins = "mpp21";
+				marvell,function = "sata0";
+			};
+			pmx_ns2_sata1: pmx-ns2-sata1 {
+				marvell,pins = "mpp20";
+				marvell,function = "sata1";
+			};
+		};
+
 		serial@12000 {
 			clock-frequency = <166666667>;
 			status = "okay";
diff --git a/arch/arm/boot/dts/kirkwood.dtsi b/arch/arm/boot/dts/kirkwood.dtsi
index 110d6cb..d6ab442 100644
--- a/arch/arm/boot/dts/kirkwood.dtsi
+++ b/arch/arm/boot/dts/kirkwood.dtsi
@@ -36,6 +36,7 @@
 			reg = <0x10100 0x40>;
 			ngpios = <32>;
 			interrupt-controller;
+			#interrupt-cells = <2>;
 			interrupts = <35>, <36>, <37>, <38>;
 		};
 
@@ -46,6 +47,7 @@
 			reg = <0x10140 0x40>;
 			ngpios = <18>;
 			interrupt-controller;
+			#interrupt-cells = <2>;
 			interrupts = <39>, <40>, <41>;
 		};
 
diff --git a/arch/arm/boot/dts/kizbox.dts b/arch/arm/boot/dts/kizbox.dts
index e8814fe..b4dc3ed 100644
--- a/arch/arm/boot/dts/kizbox.dts
+++ b/arch/arm/boot/dts/kizbox.dts
@@ -48,6 +48,8 @@
 
 			macb0: ethernet@fffc4000 {
 				phy-mode = "mii";
+				pinctrl-0 = <&pinctrl_macb_rmii
+				             &pinctrl_macb_rmii_mii_alt>;
 				status = "okay";
 			};
 
diff --git a/arch/arm/boot/dts/sunxi.dtsi b/arch/arm/boot/dts/sunxi.dtsi
index 8bbc2bf..8b36abe 100644
--- a/arch/arm/boot/dts/sunxi.dtsi
+++ b/arch/arm/boot/dts/sunxi.dtsi
@@ -60,19 +60,21 @@
 		};
 
 		uart0: uart@01c28000 {
-			compatible = "ns8250";
+			compatible = "snps,dw-apb-uart";
 			reg = <0x01c28000 0x400>;
 			interrupts = <1>;
 			reg-shift = <2>;
+			reg-io-width = <4>;
 			clock-frequency = <24000000>;
 			status = "disabled";
 		};
 
 		uart1: uart@01c28400 {
-			compatible = "ns8250";
+			compatible = "snps,dw-apb-uart";
 			reg = <0x01c28400 0x400>;
 			interrupts = <2>;
 			reg-shift = <2>;
+			reg-io-width = <4>;
 			clock-frequency = <24000000>;
 			status = "disabled";
 		};
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
index 1fc405a..cf8071a 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
@@ -45,7 +45,6 @@
 			reg = <1>;
 		};
 
-/* A7s disabled till big.LITTLE patches are available...
 		cpu2: cpu@2 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a7";
@@ -63,7 +62,6 @@
 			compatible = "arm,cortex-a7";
 			reg = <0x102>;
 		};
-*/
 	};
 
 	memory@80000000 {
diff --git a/arch/arm/common/gic.c b/arch/arm/common/gic.c
index 36ae03a..87dfa90 100644
--- a/arch/arm/common/gic.c
+++ b/arch/arm/common/gic.c
@@ -351,6 +351,25 @@
 	irq_set_chained_handler(irq, gic_handle_cascade_irq);
 }
 
+static u8 gic_get_cpumask(struct gic_chip_data *gic)
+{
+	void __iomem *base = gic_data_dist_base(gic);
+	u32 mask, i;
+
+	for (i = mask = 0; i < 32; i += 4) {
+		mask = readl_relaxed(base + GIC_DIST_TARGET + i);
+		mask |= mask >> 16;
+		mask |= mask >> 8;
+		if (mask)
+			break;
+	}
+
+	if (!mask)
+		pr_crit("GIC CPU mask not found - kernel will fail to boot.\n");
+
+	return mask;
+}
+
 static void __init gic_dist_init(struct gic_chip_data *gic)
 {
 	unsigned int i;
@@ -369,7 +388,9 @@
 	/*
 	 * Set all global interrupts to this CPU only.
 	 */
-	cpumask = readl_relaxed(base + GIC_DIST_TARGET + 0);
+	cpumask = gic_get_cpumask(gic);
+	cpumask |= cpumask << 8;
+	cpumask |= cpumask << 16;
 	for (i = 32; i < gic_irqs; i += 4)
 		writel_relaxed(cpumask, base + GIC_DIST_TARGET + i * 4 / 4);
 
@@ -400,7 +421,7 @@
 	 * Get what the GIC says our CPU mask is.
 	 */
 	BUG_ON(cpu >= NR_GIC_CPU_IF);
-	cpu_mask = readl_relaxed(dist_base + GIC_DIST_TARGET + 0);
+	cpu_mask = gic_get_cpumask(gic);
 	gic_cpu_map[cpu] = cpu_mask;
 
 	/*
diff --git a/arch/arm/configs/at91_dt_defconfig b/arch/arm/configs/at91_dt_defconfig
index b175577..1ea9590 100644
--- a/arch/arm/configs/at91_dt_defconfig
+++ b/arch/arm/configs/at91_dt_defconfig
@@ -19,6 +19,7 @@
 CONFIG_SOC_AT91SAM9263=y
 CONFIG_SOC_AT91SAM9G45=y
 CONFIG_SOC_AT91SAM9X5=y
+CONFIG_SOC_AT91SAM9N12=y
 CONFIG_MACH_AT91SAM_DT=y
 CONFIG_AT91_PROGRAMMABLE_CLOCKS=y
 CONFIG_AT91_TIMER_HZ=128
@@ -31,7 +32,7 @@
 CONFIG_ZBOOT_ROM_BSS=0x0
 CONFIG_ARM_APPENDED_DTB=y
 CONFIG_ARM_ATAG_DTB_COMPAT=y
-CONFIG_CMDLINE="mem=128M console=ttyS0,115200 initrd=0x21100000,25165824 root=/dev/ram0 rw"
+CONFIG_CMDLINE="console=ttyS0,115200 initrd=0x21100000,25165824 root=/dev/ram0 rw"
 CONFIG_KEXEC=y
 CONFIG_AUTO_ZRELADDR=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index 73cf03a..1c4df27 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -37,7 +37,7 @@
  */
 #define PAGE_OFFSET		UL(CONFIG_PAGE_OFFSET)
 #define TASK_SIZE		(UL(CONFIG_PAGE_OFFSET) - UL(0x01000000))
-#define TASK_UNMAPPED_BASE	(UL(CONFIG_PAGE_OFFSET) / 3)
+#define TASK_UNMAPPED_BASE	ALIGN(TASK_SIZE / 3, SZ_16M)
 
 /*
  * The maximum size of a 26-bit user space task.
diff --git a/arch/arm/include/asm/smp_scu.h b/arch/arm/include/asm/smp_scu.h
index 4eb6d00..86dff32 100644
--- a/arch/arm/include/asm/smp_scu.h
+++ b/arch/arm/include/asm/smp_scu.h
@@ -7,8 +7,14 @@
 
 #ifndef __ASSEMBLER__
 unsigned int scu_get_core_count(void __iomem *);
-void scu_enable(void __iomem *);
 int scu_power_mode(void __iomem *, unsigned int);
+
+#ifdef CONFIG_SMP
+void scu_enable(void __iomem *scu_base);
+#else
+static inline void scu_enable(void __iomem *scu_base) {}
+#endif
+
 #endif
 
 #endif
diff --git a/arch/arm/kernel/debug.S b/arch/arm/kernel/debug.S
index 6809200..14f7c3b 100644
--- a/arch/arm/kernel/debug.S
+++ b/arch/arm/kernel/debug.S
@@ -100,12 +100,14 @@
 		b	1b
 ENDPROC(printch)
 
+#ifdef CONFIG_MMU
 ENTRY(debug_ll_addr)
 		addruart r2, r3, ip
 		str	r2, [r0]
 		str	r3, [r1]
 		mov	pc, lr
 ENDPROC(debug_ll_addr)
+#endif
 
 #else
 
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 4eee351..486a15a 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -246,6 +246,7 @@
 
 	/*
 	 * Then map boot params address in r2 if specified.
+	 * We map 2 sections in case the ATAGs/DTB crosses a section boundary.
 	 */
 	mov	r0, r2, lsr #SECTION_SHIFT
 	movs	r0, r0, lsl #SECTION_SHIFT
@@ -253,6 +254,8 @@
 	addne	r3, r3, #PAGE_OFFSET
 	addne	r3, r4, r3, lsr #(SECTION_SHIFT - PMD_ORDER)
 	orrne	r6, r7, r0
+	strne	r6, [r3], #1 << PMD_ORDER
+	addne	r6, r6, #1 << SECTION_SHIFT
 	strne	r6, [r3]
 
 #ifdef CONFIG_DEBUG_LL
@@ -331,7 +334,7 @@
 	 * as it has already been validated by the primary processor.
 	 */
 #ifdef CONFIG_ARM_VIRT_EXT
-	bl	__hyp_stub_install
+	bl	__hyp_stub_install_secondary
 #endif
 	safe_svcmode_maskall r9
 
diff --git a/arch/arm/kernel/hyp-stub.S b/arch/arm/kernel/hyp-stub.S
index 65b2417..1315c4c 100644
--- a/arch/arm/kernel/hyp-stub.S
+++ b/arch/arm/kernel/hyp-stub.S
@@ -99,7 +99,7 @@
 	 * immediately.
 	 */
 	compare_cpu_mode_with_primary	r4, r5, r6, r7
-	bxne	lr
+	movne	pc, lr
 
 	/*
 	 * Once we have given up on one CPU, we do not try to install the
@@ -111,7 +111,7 @@
 	 */
 
 	cmp	r4, #HYP_MODE
-	bxne	lr			@ give up if the CPU is not in HYP mode
+	movne	pc, lr			@ give up if the CPU is not in HYP mode
 
 /*
  * Configure HSCTLR to set correct exception endianness/instruction set
@@ -120,7 +120,8 @@
  * Eventually, CPU-specific code might be needed -- assume not for now
  *
  * This code relies on the "eret" instruction to synchronize the
- * various coprocessor accesses.
+ * various coprocessor accesses. This is done when we switch to SVC
+ * (see safe_svcmode_maskall).
  */
 	@ Now install the hypervisor stub:
 	adr	r7, __hyp_stub_vectors
@@ -155,14 +156,7 @@
 1:
 #endif
 
-	bic	r7, r4, #MODE_MASK
-	orr	r7, r7, #SVC_MODE
-THUMB(	orr	r7, r7, #PSR_T_BIT	)
-	msr	spsr_cxsf, r7		@ This is SPSR_hyp.
-
-	__MSR_ELR_HYP(14)		@ msr elr_hyp, lr
-	__ERET				@ return, switching to SVC mode
-					@ The boot CPU mode is left in r4.
+	bx	lr			@ The boot CPU mode is left in r4.
 ENDPROC(__hyp_stub_install_secondary)
 
 __hyp_stub_do_trap:
@@ -200,7 +194,7 @@
 	@ fall through
 ENTRY(__hyp_set_vectors)
 	__HVC(0)
-	bx	lr
+	mov	pc, lr
 ENDPROC(__hyp_set_vectors)
 
 #ifndef ZIMAGE
diff --git a/arch/arm/kernel/smp_scu.c b/arch/arm/kernel/smp_scu.c
index b9f015e..45eac87 100644
--- a/arch/arm/kernel/smp_scu.c
+++ b/arch/arm/kernel/smp_scu.c
@@ -75,7 +75,7 @@
 int scu_power_mode(void __iomem *scu_base, unsigned int mode)
 {
 	unsigned int val;
-	int cpu = cpu_logical_map(smp_processor_id());
+	int cpu = MPIDR_AFFINITY_LEVEL(cpu_logical_map(smp_processor_id()), 0);
 
 	if (mode > 3 || mode == 1 || cpu > 3)
 		return -EINVAL;
diff --git a/arch/arm/mach-at91/setup.c b/arch/arm/mach-at91/setup.c
index 9ee866c..4b67847 100644
--- a/arch/arm/mach-at91/setup.c
+++ b/arch/arm/mach-at91/setup.c
@@ -105,6 +105,8 @@
 	switch (socid) {
 	case ARCH_ID_AT91RM9200:
 		at91_soc_initdata.type = AT91_SOC_RM9200;
+		if (at91_soc_initdata.subtype == AT91_SOC_SUBTYPE_NONE)
+			at91_soc_initdata.subtype = AT91_SOC_RM9200_BGA;
 		at91_boot_soc = at91rm9200_soc;
 		break;
 
diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig
index e103c29..85afb03 100644
--- a/arch/arm/mach-exynos/Kconfig
+++ b/arch/arm/mach-exynos/Kconfig
@@ -414,7 +414,7 @@
 	select CPU_EXYNOS4210
 	select HAVE_SAMSUNG_KEYPAD if INPUT_KEYBOARD
 	select PINCTRL
-	select PINCTRL_EXYNOS4
+	select PINCTRL_EXYNOS
 	select USE_OF
 	help
 	  Machine support for Samsung Exynos4 machine with device tree enabled.
diff --git a/arch/arm/mach-highbank/highbank.c b/arch/arm/mach-highbank/highbank.c
index 981dc1e..e6c0612 100644
--- a/arch/arm/mach-highbank/highbank.c
+++ b/arch/arm/mach-highbank/highbank.c
@@ -28,6 +28,7 @@
 
 #include <asm/arch_timer.h>
 #include <asm/cacheflush.h>
+#include <asm/cputype.h>
 #include <asm/smp_plat.h>
 #include <asm/smp_twd.h>
 #include <asm/hardware/arm_timer.h>
@@ -59,7 +60,7 @@
 
 void highbank_set_cpu_jump(int cpu, void *jump_addr)
 {
-	cpu = cpu_logical_map(cpu);
+	cpu = MPIDR_AFFINITY_LEVEL(cpu_logical_map(cpu), 0);
 	writel(virt_to_phys(jump_addr), HB_JUMP_TABLE_VIRT(cpu));
 	__cpuc_flush_dcache_area(HB_JUMP_TABLE_VIRT(cpu), 16);
 	outer_clean_range(HB_JUMP_TABLE_PHYS(cpu),
diff --git a/arch/arm/mach-highbank/sysregs.h b/arch/arm/mach-highbank/sysregs.h
index 70af9d1..5995df7 100644
--- a/arch/arm/mach-highbank/sysregs.h
+++ b/arch/arm/mach-highbank/sysregs.h
@@ -37,7 +37,7 @@
 
 static inline void highbank_set_core_pwr(void)
 {
-	int cpu = cpu_logical_map(smp_processor_id());
+	int cpu = MPIDR_AFFINITY_LEVEL(cpu_logical_map(smp_processor_id()), 0);
 	if (scu_base_addr)
 		scu_power_mode(scu_base_addr, SCU_PM_POWEROFF);
 	else
@@ -46,7 +46,7 @@
 
 static inline void highbank_clear_core_pwr(void)
 {
-	int cpu = cpu_logical_map(smp_processor_id());
+	int cpu = MPIDR_AFFINITY_LEVEL(cpu_logical_map(smp_processor_id()), 0);
 	if (scu_base_addr)
 		scu_power_mode(scu_base_addr, SCU_PM_NORMAL);
 	else
diff --git a/arch/arm/mach-imx/Kconfig b/arch/arm/mach-imx/Kconfig
index 3e628fd..0a2349d 100644
--- a/arch/arm/mach-imx/Kconfig
+++ b/arch/arm/mach-imx/Kconfig
@@ -851,6 +851,7 @@
 	select HAVE_CAN_FLEXCAN if CAN
 	select HAVE_IMX_GPC
 	select HAVE_IMX_MMDC
+	select HAVE_IMX_SRC
 	select HAVE_SMP
 	select MFD_SYSCON
 	select PINCTRL
diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c
index 7f2c10c..c0c4e72 100644
--- a/arch/arm/mach-imx/clk-imx6q.c
+++ b/arch/arm/mach-imx/clk-imx6q.c
@@ -436,6 +436,9 @@
 	for (i = 0; i < ARRAY_SIZE(clks_init_on); i++)
 		clk_prepare_enable(clk[clks_init_on[i]]);
 
+	/* Set initial power mode */
+	imx6q_set_lpm(WAIT_CLOCKED);
+
 	np = of_find_compatible_node(NULL, NULL, "fsl,imx6q-gpt");
 	base = of_iomap(np, 0);
 	WARN_ON(!base);
diff --git a/arch/arm/mach-imx/common.h b/arch/arm/mach-imx/common.h
index 7191ab4..fa36fb8 100644
--- a/arch/arm/mach-imx/common.h
+++ b/arch/arm/mach-imx/common.h
@@ -142,6 +142,7 @@
 extern void imx6q_clock_map_io(void);
 
 extern void imx_cpu_die(unsigned int cpu);
+extern int imx_cpu_kill(unsigned int cpu);
 
 #ifdef CONFIG_PM
 extern void imx6q_pm_init(void);
diff --git a/arch/arm/mach-imx/devices/platform-imx-fb.c b/arch/arm/mach-imx/devices/platform-imx-fb.c
index 10b0ed3..25a47c6 100644
--- a/arch/arm/mach-imx/devices/platform-imx-fb.c
+++ b/arch/arm/mach-imx/devices/platform-imx-fb.c
@@ -54,7 +54,7 @@
 			.flags = IORESOURCE_IRQ,
 		},
 	};
-	return imx_add_platform_device_dmamask("imx-fb", 0,
+	return imx_add_platform_device_dmamask(data->devid, 0,
 			res, ARRAY_SIZE(res),
 			pdata, sizeof(*pdata), DMA_BIT_MASK(32));
 }
diff --git a/arch/arm/mach-imx/hotplug.c b/arch/arm/mach-imx/hotplug.c
index 3dec962..7bc5fe1 100644
--- a/arch/arm/mach-imx/hotplug.c
+++ b/arch/arm/mach-imx/hotplug.c
@@ -46,9 +46,11 @@
 void imx_cpu_die(unsigned int cpu)
 {
 	cpu_enter_lowpower();
-	imx_enable_cpu(cpu, false);
+	cpu_do_idle();
+}
 
-	/* spin here until hardware takes it down */
-	while (1)
-		;
+int imx_cpu_kill(unsigned int cpu)
+{
+	imx_enable_cpu(cpu, false);
+	return 1;
 }
diff --git a/arch/arm/mach-imx/iram_alloc.c b/arch/arm/mach-imx/iram_alloc.c
index 6c80424..e05cf40 100644
--- a/arch/arm/mach-imx/iram_alloc.c
+++ b/arch/arm/mach-imx/iram_alloc.c
@@ -22,8 +22,7 @@
 #include <linux/module.h>
 #include <linux/spinlock.h>
 #include <linux/genalloc.h>
-
-#include "iram.h"
+#include "linux/platform_data/imx-iram.h"
 
 static unsigned long iram_phys_base;
 static void __iomem *iram_virt_base;
diff --git a/arch/arm/mach-imx/platsmp.c b/arch/arm/mach-imx/platsmp.c
index 3777b80..66fae88 100644
--- a/arch/arm/mach-imx/platsmp.c
+++ b/arch/arm/mach-imx/platsmp.c
@@ -92,5 +92,6 @@
 	.smp_boot_secondary	= imx_boot_secondary,
 #ifdef CONFIG_HOTPLUG_CPU
 	.cpu_die		= imx_cpu_die,
+	.cpu_kill		= imx_cpu_kill,
 #endif
 };
diff --git a/arch/arm/mach-imx/pm-imx6q.c b/arch/arm/mach-imx/pm-imx6q.c
index a17543d..ee42d20 100644
--- a/arch/arm/mach-imx/pm-imx6q.c
+++ b/arch/arm/mach-imx/pm-imx6q.c
@@ -41,6 +41,7 @@
 		cpu_suspend(0, imx6q_suspend_finish);
 		imx_smp_prepare();
 		imx_gpc_post_resume();
+		imx6q_set_lpm(WAIT_CLOCKED);
 		break;
 	default:
 		return -EINVAL;
diff --git a/arch/arm/mach-integrator/pci_v3.c b/arch/arm/mach-integrator/pci_v3.c
index be50e79..e7fcea7 100644
--- a/arch/arm/mach-integrator/pci_v3.c
+++ b/arch/arm/mach-integrator/pci_v3.c
@@ -475,13 +475,12 @@
 {
 	int ret = 0;
 
+	if (!ap_syscon_base)
+		return -EINVAL;
+
 	if (nr == 0) {
 		sys->mem_offset = PHYS_PCI_MEM_BASE;
 		ret = pci_v3_setup_resources(sys);
-		/* Remap the Integrator system controller */
-		ap_syscon_base = ioremap(INTEGRATOR_SC_BASE, 0x100);
-		if (!ap_syscon_base)
-			return -EINVAL;
 	}
 
 	return ret;
@@ -497,6 +496,13 @@
 	unsigned int temp;
 	int ret;
 
+	/* Remap the Integrator system controller */
+	ap_syscon_base = ioremap(INTEGRATOR_SC_BASE, 0x100);
+	if (!ap_syscon_base) {
+		pr_err("unable to remap the AP syscon for PCIv3\n");
+		return;
+	}
+
 	pcibios_min_mem = 0x00100000;
 
 	/*
diff --git a/arch/arm/mach-kirkwood/board-ns2.c b/arch/arm/mach-kirkwood/board-ns2.c
index 8821720..f4632a8 100644
--- a/arch/arm/mach-kirkwood/board-ns2.c
+++ b/arch/arm/mach-kirkwood/board-ns2.c
@@ -18,47 +18,11 @@
 #include <linux/gpio.h>
 #include <linux/of.h>
 #include "common.h"
-#include "mpp.h"
 
 static struct mv643xx_eth_platform_data ns2_ge00_data = {
 	.phy_addr	= MV643XX_ETH_PHY_ADDR(8),
 };
 
-static unsigned int ns2_mpp_config[] __initdata = {
-	MPP0_SPI_SCn,
-	MPP1_SPI_MOSI,
-	MPP2_SPI_SCK,
-	MPP3_SPI_MISO,
-	MPP4_NF_IO6,
-	MPP5_NF_IO7,
-	MPP6_SYSRST_OUTn,
-	MPP7_GPO,		/* Fan speed (bit 1) */
-	MPP8_TW0_SDA,
-	MPP9_TW0_SCK,
-	MPP10_UART0_TXD,
-	MPP11_UART0_RXD,
-	MPP12_GPO,		/* Red led */
-	MPP14_GPIO,		/* USB fuse */
-	MPP16_GPIO,		/* SATA 0 power */
-	MPP17_GPIO,		/* SATA 1 power */
-	MPP18_NF_IO0,
-	MPP19_NF_IO1,
-	MPP20_SATA1_ACTn,
-	MPP21_SATA0_ACTn,
-	MPP22_GPIO,		/* Fan speed (bit 0) */
-	MPP23_GPIO,		/* Fan power */
-	MPP24_GPIO,		/* USB mode select */
-	MPP25_GPIO,		/* Fan rotation fail */
-	MPP26_GPIO,		/* USB device vbus */
-	MPP28_GPIO,		/* USB enable host vbus */
-	MPP29_GPIO,		/* Blue led (slow register) */
-	MPP30_GPIO,		/* Blue led (command register) */
-	MPP31_GPIO,		/* Board power off */
-	MPP32_GPIO,		/* Power button (0 = Released, 1 = Pushed) */
-	MPP33_GPO,		/* Fan speed (bit 2) */
-	0
-};
-
 #define NS2_GPIO_POWER_OFF	31
 
 static void ns2_power_off(void)
@@ -71,8 +35,6 @@
 	/*
 	 * Basic setup. Needs to be called early.
 	 */
-	kirkwood_mpp_conf(ns2_mpp_config);
-
 	if (of_machine_is_compatible("lacie,netspace_lite_v2") ||
 	    of_machine_is_compatible("lacie,netspace_mini_v2"))
 		ns2_ge00_data.phy_addr = MV643XX_ETH_PHY_ADDR(0);
diff --git a/arch/arm/mach-mvebu/Makefile b/arch/arm/mach-mvebu/Makefile
index 5dcb369..99df4df 100644
--- a/arch/arm/mach-mvebu/Makefile
+++ b/arch/arm/mach-mvebu/Makefile
@@ -1,6 +1,8 @@
 ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/$(src)/include \
 	-I$(srctree)/arch/arm/plat-orion/include
 
+AFLAGS_coherency_ll.o		:= -Wa,-march=armv7-a
+
 obj-y += system-controller.o
 obj-$(CONFIG_MACH_ARMADA_370_XP) += armada-370-xp.o irq-armada-370-xp.o addr-map.o coherency.o coherency_ll.o pmsu.o
 obj-$(CONFIG_SMP)                += platsmp.o headsmp.o
diff --git a/arch/arm/mach-omap2/board-omap4panda.c b/arch/arm/mach-omap2/board-omap4panda.c
index 5c8e9ce..769c1fe 100644
--- a/arch/arm/mach-omap2/board-omap4panda.c
+++ b/arch/arm/mach-omap2/board-omap4panda.c
@@ -397,6 +397,12 @@
 		  OMAP_PULL_ENA),
 	OMAP4_MUX(ABE_MCBSP1_FSX, OMAP_MUX_MODE0 | OMAP_PIN_INPUT),
 
+	/* UART2 - BT/FM/GPS shared transport */
+	OMAP4_MUX(UART2_CTS,	OMAP_PIN_INPUT	| OMAP_MUX_MODE0),
+	OMAP4_MUX(UART2_RTS,	OMAP_PIN_OUTPUT	| OMAP_MUX_MODE0),
+	OMAP4_MUX(UART2_RX,	OMAP_PIN_INPUT	| OMAP_MUX_MODE0),
+	OMAP4_MUX(UART2_TX,	OMAP_PIN_OUTPUT	| OMAP_MUX_MODE0),
+
 	{ .reg_offset = OMAP_MUX_TERMINATOR },
 };
 
diff --git a/arch/arm/mach-omap2/cclock2420_data.c b/arch/arm/mach-omap2/cclock2420_data.c
index 7e5febe..ab7e952 100644
--- a/arch/arm/mach-omap2/cclock2420_data.c
+++ b/arch/arm/mach-omap2/cclock2420_data.c
@@ -1935,6 +1935,8 @@
 			omap2_init_clk_hw_omap_clocks(c->lk.clk);
 	}
 
+	omap2xxx_clkt_vps_late_init();
+
 	omap2_clk_disable_autoidle_all();
 
 	omap2_clk_enable_init_clocks(enable_init_clks,
diff --git a/arch/arm/mach-omap2/cclock2430_data.c b/arch/arm/mach-omap2/cclock2430_data.c
index eda079b..eb3dab6 100644
--- a/arch/arm/mach-omap2/cclock2430_data.c
+++ b/arch/arm/mach-omap2/cclock2430_data.c
@@ -2050,6 +2050,8 @@
 			omap2_init_clk_hw_omap_clocks(c->lk.clk);
 	}
 
+	omap2xxx_clkt_vps_late_init();
+
 	omap2_clk_disable_autoidle_all();
 
 	omap2_clk_enable_init_clocks(enable_init_clks,
diff --git a/arch/arm/mach-omap2/cclock44xx_data.c b/arch/arm/mach-omap2/cclock44xx_data.c
index 5789a5e..a2cc046 100644
--- a/arch/arm/mach-omap2/cclock44xx_data.c
+++ b/arch/arm/mach-omap2/cclock44xx_data.c
@@ -2026,14 +2026,13 @@
 	 * On OMAP4460 the ABE DPLL fails to turn on if in idle low-power
 	 * state when turning the ABE clock domain. Workaround this by
 	 * locking the ABE DPLL on boot.
+	 * Lock the ABE DPLL in any case to avoid issues with audio.
 	 */
-	if (cpu_is_omap446x()) {
-		rc = clk_set_parent(&abe_dpll_refclk_mux_ck, &sys_32k_ck);
-		if (!rc)
-			rc = clk_set_rate(&dpll_abe_ck, OMAP4_DPLL_ABE_DEFFREQ);
-		if (rc)
-			pr_err("%s: failed to configure ABE DPLL!\n", __func__);
-	}
+	rc = clk_set_parent(&abe_dpll_refclk_mux_ck, &sys_32k_ck);
+	if (!rc)
+		rc = clk_set_rate(&dpll_abe_ck, OMAP4_DPLL_ABE_DEFFREQ);
+	if (rc)
+		pr_err("%s: failed to configure ABE DPLL!\n", __func__);
 
 	return 0;
 }
diff --git a/arch/arm/mach-omap2/devices.c b/arch/arm/mach-omap2/devices.c
index 5e304d0..626f3ea 100644
--- a/arch/arm/mach-omap2/devices.c
+++ b/arch/arm/mach-omap2/devices.c
@@ -639,7 +639,7 @@
 	return cnt;
 }
 
-static void omap_init_ocp2scp(void)
+static void __init omap_init_ocp2scp(void)
 {
 	struct omap_hwmod	*oh;
 	struct platform_device	*pdev;
diff --git a/arch/arm/mach-omap2/drm.c b/arch/arm/mach-omap2/drm.c
index 4c7566c..2a2cfa8 100644
--- a/arch/arm/mach-omap2/drm.c
+++ b/arch/arm/mach-omap2/drm.c
@@ -25,6 +25,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/platform_data/omap_drm.h>
 
+#include "soc.h"
 #include "omap_device.h"
 #include "omap_hwmod.h"
 
@@ -56,7 +57,7 @@
 			oh->name);
 	}
 
-	platform_data.omaprev = GET_OMAP_REVISION();
+	platform_data.omaprev = GET_OMAP_TYPE;
 
 	return platform_device_register(&omap_drm_device);
 
diff --git a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
index 129d508..793f54a 100644
--- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
@@ -2132,8 +2132,12 @@
 	 * currently reset very early during boot, before I2C is
 	 * available, so it doesn't seem that we have any choice in
 	 * the kernel other than to avoid resetting it.
+	 *
+	 * Also, McPDM needs to be configured to NO_IDLE mode when it
+	 * is in used otherwise vital clocks will be gated which
+	 * results 'slow motion' audio playback.
 	 */
-	.flags		= HWMOD_EXT_OPT_MAIN_CLK,
+	.flags		= HWMOD_EXT_OPT_MAIN_CLK | HWMOD_SWSUP_SIDLE,
 	.mpu_irqs	= omap44xx_mcpdm_irqs,
 	.sdma_reqs	= omap44xx_mcpdm_sdma_reqs,
 	.main_clk	= "mcpdm_fck",
diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c
index 691aa67..b8ad6e6 100644
--- a/arch/arm/mach-omap2/timer.c
+++ b/arch/arm/mach-omap2/timer.c
@@ -165,15 +165,11 @@
 	struct device_node *np;
 
 	for_each_matching_node(np, match) {
-		if (!of_device_is_available(np)) {
-			of_node_put(np);
+		if (!of_device_is_available(np))
 			continue;
-		}
 
-		if (property && !of_get_property(np, property, NULL)) {
-			of_node_put(np);
+		if (property && !of_get_property(np, property, NULL))
 			continue;
-		}
 
 		of_add_property(np, &device_disabled);
 		return np;
diff --git a/arch/arm/mach-realview/include/mach/irqs-eb.h b/arch/arm/mach-realview/include/mach/irqs-eb.h
index d6b5073..4475423 100644
--- a/arch/arm/mach-realview/include/mach/irqs-eb.h
+++ b/arch/arm/mach-realview/include/mach/irqs-eb.h
@@ -115,7 +115,7 @@
 /*
  * Only define NR_IRQS if less than NR_IRQS_EB
  */
-#define NR_IRQS_EB		(IRQ_EB_GIC_START + 96)
+#define NR_IRQS_EB		(IRQ_EB_GIC_START + 128)
 
 #if defined(CONFIG_MACH_REALVIEW_EB) \
 	&& (!defined(NR_IRQS) || (NR_IRQS < NR_IRQS_EB))
diff --git a/arch/arm/mach-s3c64xx/mach-crag6410-module.c b/arch/arm/mach-s3c64xx/mach-crag6410-module.c
index 553059f..755c0bb 100644
--- a/arch/arm/mach-s3c64xx/mach-crag6410-module.c
+++ b/arch/arm/mach-s3c64xx/mach-crag6410-module.c
@@ -47,7 +47,7 @@
 		.bus_num	= 0,
 		.chip_select	= 0,
 		.mode		= SPI_MODE_0,
-		.irq		= S3C_EINT(5),
+		.irq		= S3C_EINT(4),
 		.controller_data = &wm0010_spi_csinfo,
 		.platform_data = &wm0010_pdata,
 	},
diff --git a/arch/arm/mach-s3c64xx/pm.c b/arch/arm/mach-s3c64xx/pm.c
index 7feb426..d2e1a16 100644
--- a/arch/arm/mach-s3c64xx/pm.c
+++ b/arch/arm/mach-s3c64xx/pm.c
@@ -338,8 +338,10 @@
 	for (i = 0; i < ARRAY_SIZE(s3c64xx_pm_domains); i++)
 		pm_genpd_init(&s3c64xx_pm_domains[i]->pd, NULL, false);
 
+#ifdef CONFIG_S3C_DEV_FB
 	if (dev_get_platdata(&s3c_device_fb.dev))
 		pm_genpd_add_device(&s3c64xx_pm_f.pd, &s3c_device_fb.dev);
+#endif
 
 	return 0;
 }
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 6b2fb87..dda3904 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -640,7 +640,7 @@
 
 	if (is_coherent || nommu())
 		addr = __alloc_simple_buffer(dev, size, gfp, &page);
-	else if (gfp & GFP_ATOMIC)
+	else if (!(gfp & __GFP_WAIT))
 		addr = __alloc_from_pool(size, &page);
 	else if (!IS_ENABLED(CONFIG_CMA))
 		addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, caller);
@@ -774,25 +774,27 @@
 	size_t size, enum dma_data_direction dir,
 	void (*op)(const void *, size_t, int))
 {
+	unsigned long pfn;
+	size_t left = size;
+
+	pfn = page_to_pfn(page) + offset / PAGE_SIZE;
+	offset %= PAGE_SIZE;
+
 	/*
 	 * A single sg entry may refer to multiple physically contiguous
 	 * pages.  But we still need to process highmem pages individually.
 	 * If highmem is not configured then the bulk of this loop gets
 	 * optimized out.
 	 */
-	size_t left = size;
 	do {
 		size_t len = left;
 		void *vaddr;
 
+		page = pfn_to_page(pfn);
+
 		if (PageHighMem(page)) {
-			if (len + offset > PAGE_SIZE) {
-				if (offset >= PAGE_SIZE) {
-					page += offset / PAGE_SIZE;
-					offset %= PAGE_SIZE;
-				}
+			if (len + offset > PAGE_SIZE)
 				len = PAGE_SIZE - offset;
-			}
 			vaddr = kmap_high_get(page);
 			if (vaddr) {
 				vaddr += offset;
@@ -809,7 +811,7 @@
 			op(vaddr, len, dir);
 		}
 		offset = 0;
-		page++;
+		pfn++;
 		left -= len;
 	} while (left);
 }
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 9f06102..ce328c7 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -283,7 +283,7 @@
 	},
 	[MT_MEMORY_SO] = {
 		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
-				L_PTE_MT_UNCACHED,
+				L_PTE_MT_UNCACHED | L_PTE_XN,
 		.prot_l1   = PMD_TYPE_TABLE,
 		.prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_S |
 				PMD_SECT_UNCACHED | PMD_SECT_XN,
diff --git a/arch/arm/plat-versatile/headsmp.S b/arch/arm/plat-versatile/headsmp.S
index dd703ef..b178d44 100644
--- a/arch/arm/plat-versatile/headsmp.S
+++ b/arch/arm/plat-versatile/headsmp.S
@@ -20,7 +20,7 @@
  */
 ENTRY(versatile_secondary_startup)
 	mrc	p15, 0, r0, c0, c0, 5
-	and	r0, r0, #15
+	bic	r0, #0xff000000
 	adr	r4, 1f
 	ldmia	r4, {r5, r6}
 	sub	r4, r4, r5
diff --git a/arch/arm/vfp/entry.S b/arch/arm/vfp/entry.S
index cc926c9..323ce1a 100644
--- a/arch/arm/vfp/entry.S
+++ b/arch/arm/vfp/entry.S
@@ -22,7 +22,7 @@
 @  IRQs disabled.
 @
 ENTRY(do_vfp)
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPT_COUNT
 	ldr	r4, [r10, #TI_PREEMPT]	@ get preempt count
 	add	r11, r4, #1		@ increment it
 	str	r11, [r10, #TI_PREEMPT]
@@ -35,7 +35,7 @@
 ENDPROC(do_vfp)
 
 ENTRY(vfp_null_entry)
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPT_COUNT
 	get_thread_info	r10
 	ldr	r4, [r10, #TI_PREEMPT]	@ get preempt count
 	sub	r11, r4, #1		@ decrement it
@@ -53,7 +53,7 @@
 
 	__INIT
 ENTRY(vfp_testing_entry)
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPT_COUNT
 	get_thread_info	r10
 	ldr	r4, [r10, #TI_PREEMPT]	@ get preempt count
 	sub	r11, r4, #1		@ decrement it
diff --git a/arch/arm/vfp/vfphw.S b/arch/arm/vfp/vfphw.S
index ea0349f..dd5e56f 100644
--- a/arch/arm/vfp/vfphw.S
+++ b/arch/arm/vfp/vfphw.S
@@ -168,7 +168,7 @@
 					@ else it's one 32-bit instruction, so
 					@ always subtract 4 from the following
 					@ instruction address.
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPT_COUNT
 	get_thread_info	r10
 	ldr	r4, [r10, #TI_PREEMPT]	@ get preempt count
 	sub	r11, r4, #1		@ decrement it
@@ -192,7 +192,7 @@
 	@ not recognised by VFP
 
 	DBGSTR	"not VFP"
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPT_COUNT
 	get_thread_info	r10
 	ldr	r4, [r10, #TI_PREEMPT]	@ get preempt count
 	sub	r11, r4, #1		@ decrement it
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index f8f362a..75e915b 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -21,7 +21,6 @@
 	select HAVE_GENERIC_DMA_COHERENT
 	select HAVE_GENERIC_HARDIRQS
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS
-	select HAVE_IRQ_WORK
 	select HAVE_MEMBLOCK
 	select HAVE_PERF_EVENTS
 	select IRQ_DOMAIN
diff --git a/arch/avr32/include/asm/dma-mapping.h b/arch/avr32/include/asm/dma-mapping.h
index aaf5199..b3d18f9 100644
--- a/arch/avr32/include/asm/dma-mapping.h
+++ b/arch/avr32/include/asm/dma-mapping.h
@@ -336,4 +336,14 @@
 #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
 #define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
 
+/* drivers/base/dma-mapping.c */
+extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
+			   void *cpu_addr, dma_addr_t dma_addr, size_t size);
+extern int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
+				  void *cpu_addr, dma_addr_t dma_addr,
+				  size_t size);
+
+#define dma_mmap_coherent(d, v, c, h, s) dma_common_mmap(d, v, c, h, s)
+#define dma_get_sgtable(d, t, v, h, s) dma_common_get_sgtable(d, t, v, h, s)
+
 #endif /* __ASM_AVR32_DMA_MAPPING_H */
diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig
index b6f3ad5..67e4aaa 100644
--- a/arch/blackfin/Kconfig
+++ b/arch/blackfin/Kconfig
@@ -24,7 +24,6 @@
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	select HAVE_IDE
-	select HAVE_IRQ_WORK
 	select HAVE_KERNEL_GZIP if RAMKERNEL
 	select HAVE_KERNEL_BZIP2 if RAMKERNEL
 	select HAVE_KERNEL_LZMA if RAMKERNEL
@@ -38,7 +37,6 @@
 	select HAVE_GENERIC_HARDIRQS
 	select GENERIC_ATOMIC64
 	select GENERIC_IRQ_PROBE
-	select IRQ_PER_CPU if SMP
 	select USE_GENERIC_SMP_HELPERS if SMP
 	select HAVE_NMI_WATCHDOG if NMI_WATCHDOG
 	select GENERIC_SMP_IDLE_THREAD
diff --git a/arch/blackfin/include/asm/dma-mapping.h b/arch/blackfin/include/asm/dma-mapping.h
index bbf4610..054d9ec 100644
--- a/arch/blackfin/include/asm/dma-mapping.h
+++ b/arch/blackfin/include/asm/dma-mapping.h
@@ -154,4 +154,14 @@
 	_dma_sync((dma_addr_t)vaddr, size, dir);
 }
 
+/* drivers/base/dma-mapping.c */
+extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
+			   void *cpu_addr, dma_addr_t dma_addr, size_t size);
+extern int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
+				  void *cpu_addr, dma_addr_t dma_addr,
+				  size_t size);
+
+#define dma_mmap_coherent(d, v, c, h, s) dma_common_mmap(d, v, c, h, s)
+#define dma_get_sgtable(d, t, v, h, s) dma_common_get_sgtable(d, t, v, h, s)
+
 #endif				/* _BLACKFIN_DMA_MAPPING_H */
diff --git a/arch/c6x/include/asm/dma-mapping.h b/arch/c6x/include/asm/dma-mapping.h
index 3c69406..88bd0d8 100644
--- a/arch/c6x/include/asm/dma-mapping.h
+++ b/arch/c6x/include/asm/dma-mapping.h
@@ -89,4 +89,19 @@
 #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent((d), (s), (h), (f))
 #define dma_free_noncoherent(d, s, v, h)  dma_free_coherent((d), (s), (v), (h))
 
+/* Not supported for now */
+static inline int dma_mmap_coherent(struct device *dev,
+				    struct vm_area_struct *vma, void *cpu_addr,
+				    dma_addr_t dma_addr, size_t size)
+{
+	return -EINVAL;
+}
+
+static inline int dma_get_sgtable(struct device *dev, struct sg_table *sgt,
+				  void *cpu_addr, dma_addr_t dma_addr,
+				  size_t size)
+{
+	return -EINVAL;
+}
+
 #endif	/* _ASM_C6X_DMA_MAPPING_H */
diff --git a/arch/cris/include/asm/dma-mapping.h b/arch/cris/include/asm/dma-mapping.h
index 8588b2c..2f0f654 100644
--- a/arch/cris/include/asm/dma-mapping.h
+++ b/arch/cris/include/asm/dma-mapping.h
@@ -158,5 +158,15 @@
 {
 }
 
+/* drivers/base/dma-mapping.c */
+extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
+			   void *cpu_addr, dma_addr_t dma_addr, size_t size);
+extern int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
+				  void *cpu_addr, dma_addr_t dma_addr,
+				  size_t size);
+
+#define dma_mmap_coherent(d, v, c, h, s) dma_common_mmap(d, v, c, h, s)
+#define dma_get_sgtable(d, t, v, h, s) dma_common_get_sgtable(d, t, v, h, s)
+
 
 #endif
diff --git a/arch/frv/Kconfig b/arch/frv/Kconfig
index 9d26264..17df48f 100644
--- a/arch/frv/Kconfig
+++ b/arch/frv/Kconfig
@@ -3,7 +3,6 @@
 	default y
 	select HAVE_IDE
 	select HAVE_ARCH_TRACEHOOK
-	select HAVE_IRQ_WORK
 	select HAVE_PERF_EVENTS
 	select HAVE_UID16
 	select HAVE_GENERIC_HARDIRQS
diff --git a/arch/frv/include/asm/dma-mapping.h b/arch/frv/include/asm/dma-mapping.h
index dfb8110..1746a2b 100644
--- a/arch/frv/include/asm/dma-mapping.h
+++ b/arch/frv/include/asm/dma-mapping.h
@@ -132,4 +132,19 @@
 	flush_write_buffers();
 }
 
+/* Not supported for now */
+static inline int dma_mmap_coherent(struct device *dev,
+				    struct vm_area_struct *vma, void *cpu_addr,
+				    dma_addr_t dma_addr, size_t size)
+{
+	return -EINVAL;
+}
+
+static inline int dma_get_sgtable(struct device *dev, struct sg_table *sgt,
+				  void *cpu_addr, dma_addr_t dma_addr,
+				  size_t size)
+{
+	return -EINVAL;
+}
+
 #endif  /* _ASM_DMA_MAPPING_H */
diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig
index 0744f7d..e4decc6 100644
--- a/arch/hexagon/Kconfig
+++ b/arch/hexagon/Kconfig
@@ -12,9 +12,7 @@
 	# select ARCH_WANT_OPTIONAL_GPIOLIB
 	# select ARCH_REQUIRE_GPIOLIB
 	# select HAVE_CLK
-	# select IRQ_PER_CPU
 	# select GENERIC_PENDING_IRQ if SMP
-	select HAVE_IRQ_WORK
 	select GENERIC_ATOMIC64
 	select HAVE_PERF_EVENTS
 	select HAVE_GENERIC_HARDIRQS
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 3279646..00c2e88 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -29,7 +29,6 @@
 	select ARCH_DISCARD_MEMBLOCK
 	select GENERIC_IRQ_PROBE
 	select GENERIC_PENDING_IRQ if SMP
-	select IRQ_PER_CPU
 	select GENERIC_IRQ_SHOW
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
diff --git a/arch/m68k/include/asm/dma-mapping.h b/arch/m68k/include/asm/dma-mapping.h
index 3e6b844..292805f 100644
--- a/arch/m68k/include/asm/dma-mapping.h
+++ b/arch/m68k/include/asm/dma-mapping.h
@@ -115,4 +115,14 @@
 #include <asm-generic/dma-mapping-broken.h>
 #endif
 
+/* drivers/base/dma-mapping.c */
+extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
+			   void *cpu_addr, dma_addr_t dma_addr, size_t size);
+extern int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
+				  void *cpu_addr, dma_addr_t dma_addr,
+				  size_t size);
+
+#define dma_mmap_coherent(d, v, c, h, s) dma_common_mmap(d, v, c, h, s)
+#define dma_get_sgtable(d, t, v, h, s) dma_common_get_sgtable(d, t, v, h, s)
+
 #endif  /* _M68K_DMA_MAPPING_H */
diff --git a/arch/m68k/include/asm/processor.h b/arch/m68k/include/asm/processor.h
index ae700f4..b0768a6 100644
--- a/arch/m68k/include/asm/processor.h
+++ b/arch/m68k/include/asm/processor.h
@@ -130,7 +130,6 @@
 #define start_thread(_regs, _pc, _usp)                  \
 do {                                                    \
 	(_regs)->pc = (_pc);                            \
-	((struct switch_stack *)(_regs))[-1].a6 = 0;    \
 	setframeformat(_regs);                          \
 	if (current->mm)                                \
 		(_regs)->d5 = current->mm->start_data;  \
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 2ac626a..9becc44 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -4,7 +4,6 @@
 	select HAVE_GENERIC_DMA_COHERENT
 	select HAVE_IDE
 	select HAVE_OPROFILE
-	select HAVE_IRQ_WORK
 	select HAVE_PERF_EVENTS
 	select PERF_USE_VMALLOC
 	select HAVE_ARCH_KGDB
@@ -2161,7 +2160,6 @@
 config SMP
 	bool "Multi-Processing support"
 	depends on SYS_SUPPORTS_SMP
-	select IRQ_PER_CPU
 	select USE_GENERIC_SMP_HELPERS
 	help
 	  This enables support for systems with more than one CPU. If you have
diff --git a/arch/mips/bcm47xx/Kconfig b/arch/mips/bcm47xx/Kconfig
index d7af29f..ba61192 100644
--- a/arch/mips/bcm47xx/Kconfig
+++ b/arch/mips/bcm47xx/Kconfig
@@ -8,8 +8,10 @@
 	select SSB_DRIVER_EXTIF
 	select SSB_EMBEDDED
 	select SSB_B43_PCI_BRIDGE if PCI
+	select SSB_DRIVER_PCICORE if PCI
 	select SSB_PCICORE_HOSTMODE if PCI
 	select SSB_DRIVER_GPIO
+	select GPIOLIB
 	default y
 	help
 	 Add support for old Broadcom BCM47xx boards with Sonics Silicon Backplane support.
@@ -25,6 +27,7 @@
 	select BCMA_HOST_PCI if PCI
 	select BCMA_DRIVER_PCI_HOSTMODE if PCI
 	select BCMA_DRIVER_GPIO
+	select GPIOLIB
 	default y
 	help
 	 Add support for new Broadcom BCM47xx boards with Broadcom specific Advanced Microcontroller Bus.
diff --git a/arch/mips/cavium-octeon/executive/cvmx-l2c.c b/arch/mips/cavium-octeon/executive/cvmx-l2c.c
index 9f883bf..33b7214 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-l2c.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-l2c.c
@@ -30,6 +30,7 @@
  * measurement, and debugging facilities.
  */
 
+#include <linux/compiler.h>
 #include <linux/irqflags.h>
 #include <asm/octeon/cvmx.h>
 #include <asm/octeon/cvmx-l2c.h>
@@ -285,22 +286,22 @@
  */
 static void fault_in(uint64_t addr, int len)
 {
-	volatile char *ptr;
-	volatile char dummy;
+	char *ptr;
+
 	/*
 	 * Adjust addr and length so we get all cache lines even for
 	 * small ranges spanning two cache lines.
 	 */
 	len += addr & CVMX_CACHE_LINE_MASK;
 	addr &= ~CVMX_CACHE_LINE_MASK;
-	ptr = (volatile char *)cvmx_phys_to_ptr(addr);
+	ptr = cvmx_phys_to_ptr(addr);
 	/*
 	 * Invalidate L1 cache to make sure all loads result in data
 	 * being in L2.
 	 */
 	CVMX_DCACHE_INVALIDATE;
 	while (len > 0) {
-		dummy += *ptr;
+		ACCESS_ONCE(*ptr);
 		len -= CVMX_CACHE_LINE_SIZE;
 		ptr += CVMX_CACHE_LINE_SIZE;
 	}
diff --git a/arch/mips/include/asm/dsp.h b/arch/mips/include/asm/dsp.h
index e9bfc08..7bfad05 100644
--- a/arch/mips/include/asm/dsp.h
+++ b/arch/mips/include/asm/dsp.h
@@ -16,7 +16,7 @@
 #include <asm/mipsregs.h>
 
 #define DSP_DEFAULT	0x00000000
-#define DSP_MASK	0x3ff
+#define DSP_MASK	0x3f
 
 #define __enable_dsp_hazard()						\
 do {									\
diff --git a/arch/mips/include/asm/inst.h b/arch/mips/include/asm/inst.h
index ab84064..33c34adb 100644
--- a/arch/mips/include/asm/inst.h
+++ b/arch/mips/include/asm/inst.h
@@ -353,6 +353,7 @@
 	struct u_format u_format;
 	struct c_format c_format;
 	struct r_format r_format;
+	struct p_format p_format;
 	struct f_format f_format;
 	struct ma_format ma_format;
 	struct b_format b_format;
diff --git a/arch/mips/include/asm/mach-pnx833x/war.h b/arch/mips/include/asm/mach-pnx833x/war.h
index edaa06d..e410df4 100644
--- a/arch/mips/include/asm/mach-pnx833x/war.h
+++ b/arch/mips/include/asm/mach-pnx833x/war.h
@@ -21,4 +21,4 @@
 #define R10000_LLSC_WAR			0
 #define MIPS34K_MISSED_ITLB_WAR		0
 
-#endif /* __ASM_MIPS_MACH_PNX8550_WAR_H */
+#endif /* __ASM_MIPS_MACH_PNX833X_WAR_H */
diff --git a/arch/mips/include/asm/pgtable-64.h b/arch/mips/include/asm/pgtable-64.h
index c631910..013d5f7 100644
--- a/arch/mips/include/asm/pgtable-64.h
+++ b/arch/mips/include/asm/pgtable-64.h
@@ -230,6 +230,7 @@
 #else
 #define pte_pfn(x)		((unsigned long)((x).pte >> _PFN_SHIFT))
 #define pfn_pte(pfn, prot)	__pte(((pfn) << _PFN_SHIFT) | pgprot_val(prot))
+#define pfn_pmd(pfn, prot)	__pmd(((pfn) << _PFN_SHIFT) | pgprot_val(prot))
 #endif
 
 #define __pgd_offset(address)	pgd_index(address)
diff --git a/arch/mips/include/uapi/asm/Kbuild b/arch/mips/include/uapi/asm/Kbuild
index a1a0452..77d4fb3 100644
--- a/arch/mips/include/uapi/asm/Kbuild
+++ b/arch/mips/include/uapi/asm/Kbuild
@@ -3,6 +3,7 @@
 
 header-y += auxvec.h
 header-y += bitsperlong.h
+header-y += break.h
 header-y += byteorder.h
 header-y += cachectl.h
 header-y += errno.h
diff --git a/arch/mips/include/asm/break.h b/arch/mips/include/uapi/asm/break.h
similarity index 100%
rename from arch/mips/include/asm/break.h
rename to arch/mips/include/uapi/asm/break.h
diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c
index 6a2d758..83fa146 100644
--- a/arch/mips/kernel/ftrace.c
+++ b/arch/mips/kernel/ftrace.c
@@ -25,6 +25,12 @@
 #define MCOUNT_OFFSET_INSNS 4
 #endif
 
+/* Arch override because MIPS doesn't need to run this from stop_machine() */
+void arch_ftrace_update_code(int command)
+{
+	ftrace_modify_all_code(command);
+}
+
 /*
  * Check if the address is in kernel space
  *
@@ -89,6 +95,24 @@
 	return 0;
 }
 
+#ifndef CONFIG_64BIT
+static int ftrace_modify_code_2(unsigned long ip, unsigned int new_code1,
+				unsigned int new_code2)
+{
+	int faulted;
+
+	safe_store_code(new_code1, ip, faulted);
+	if (unlikely(faulted))
+		return -EFAULT;
+	ip += 4;
+	safe_store_code(new_code2, ip, faulted);
+	if (unlikely(faulted))
+		return -EFAULT;
+	flush_icache_range(ip, ip + 8); /* original ip + 12 */
+	return 0;
+}
+#endif
+
 /*
  * The details about the calling site of mcount on MIPS
  *
@@ -131,8 +155,18 @@
 	 * needed.
 	 */
 	new = in_kernel_space(ip) ? INSN_NOP : INSN_B_1F;
-
+#ifdef CONFIG_64BIT
 	return ftrace_modify_code(ip, new);
+#else
+	/*
+	 * On 32 bit MIPS platforms, gcc adds a stack adjust
+	 * instruction in the delay slot after the branch to
+	 * mcount and expects mcount to restore the sp on return.
+	 * This is based on a legacy API and does nothing but
+	 * waste instructions so it's being removed at runtime.
+	 */
+	return ftrace_modify_code_2(ip, new, INSN_NOP);
+#endif
 }
 
 int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
diff --git a/arch/mips/kernel/mcount.S b/arch/mips/kernel/mcount.S
index 4c968e7..1658676 100644
--- a/arch/mips/kernel/mcount.S
+++ b/arch/mips/kernel/mcount.S
@@ -46,9 +46,8 @@
 	PTR_L	a5, PT_R9(sp)
 	PTR_L	a6, PT_R10(sp)
 	PTR_L	a7, PT_R11(sp)
-	PTR_ADDIU	sp, PT_SIZE
 #else
-	PTR_ADDIU	sp, (PT_SIZE + 8)
+	PTR_ADDIU	sp, PT_SIZE
 #endif
 .endm
 
@@ -69,7 +68,9 @@
 	.globl _mcount
 _mcount:
 	b	ftrace_stub
-	 nop
+	addiu sp,sp,8
+
+	/* When tracing is activated, it calls ftrace_caller+8 (aka here) */
 	lw	t1, function_trace_stop
 	bnez	t1, ftrace_stub
 	 nop
diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c
index eec690a..147cec1 100644
--- a/arch/mips/kernel/vpe.c
+++ b/arch/mips/kernel/vpe.c
@@ -705,7 +705,7 @@
 
 			printk(KERN_WARNING
 			       "VPE loader: TC %d is already in use.\n",
-                               t->index);
+			       v->tc->index);
 			return -ENOEXEC;
 		}
 	} else {
diff --git a/arch/mips/lantiq/irq.c b/arch/mips/lantiq/irq.c
index f36acd1..a7935bf 100644
--- a/arch/mips/lantiq/irq.c
+++ b/arch/mips/lantiq/irq.c
@@ -408,7 +408,7 @@
 #endif
 
 	/* tell oprofile which irq to use */
-	cp0_perfcount_irq = LTQ_PERF_IRQ;
+	cp0_perfcount_irq = irq_create_mapping(ltq_domain, LTQ_PERF_IRQ);
 
 	/*
 	 * if the timer irq is not one of the mips irqs we need to
diff --git a/arch/mips/lib/delay.c b/arch/mips/lib/delay.c
index dc81ca8..288f795 100644
--- a/arch/mips/lib/delay.c
+++ b/arch/mips/lib/delay.c
@@ -21,7 +21,7 @@
 	"	.set	noreorder				\n"
 	"	.align	3					\n"
 	"1:	bnez	%0, 1b					\n"
-#if __SIZEOF_LONG__ == 4
+#if BITS_PER_LONG == 32
 	"	subu	%0, 1					\n"
 #else
 	"	dsubu	%0, 1					\n"
diff --git a/arch/mips/mm/ioremap.c b/arch/mips/mm/ioremap.c
index 7657fd2..cacfd31 100644
--- a/arch/mips/mm/ioremap.c
+++ b/arch/mips/mm/ioremap.c
@@ -190,9 +190,3 @@
 
 EXPORT_SYMBOL(__ioremap);
 EXPORT_SYMBOL(__iounmap);
-
-int __virt_addr_valid(const volatile void *kaddr)
-{
-	return pfn_valid(PFN_DOWN(virt_to_phys(kaddr)));
-}
-EXPORT_SYMBOL_GPL(__virt_addr_valid);
diff --git a/arch/mips/mm/mmap.c b/arch/mips/mm/mmap.c
index d9be754..7e5fe27 100644
--- a/arch/mips/mm/mmap.c
+++ b/arch/mips/mm/mmap.c
@@ -192,3 +192,9 @@
 
 	return ret;
 }
+
+int __virt_addr_valid(const volatile void *kaddr)
+{
+	return pfn_valid(PFN_DOWN(virt_to_phys(kaddr)));
+}
+EXPORT_SYMBOL_GPL(__virt_addr_valid);
diff --git a/arch/mips/netlogic/xlr/setup.c b/arch/mips/netlogic/xlr/setup.c
index 4e7f49d..c5ce699 100644
--- a/arch/mips/netlogic/xlr/setup.c
+++ b/arch/mips/netlogic/xlr/setup.c
@@ -193,8 +193,11 @@
 
 void __init prom_init(void)
 {
-	int i, *argv, *envp;		/* passed as 32 bit ptrs */
+	int *argv, *envp;		/* passed as 32 bit ptrs */
 	struct psb_info *prom_infop;
+#ifdef CONFIG_SMP
+	int i;
+#endif
 
 	/* truncate to 32 bit and sign extend all args */
 	argv = (int *)(long)(int)fw_arg1;
diff --git a/arch/mips/pci/pci-ar71xx.c b/arch/mips/pci/pci-ar71xx.c
index 1552522..6eaa4f2 100644
--- a/arch/mips/pci/pci-ar71xx.c
+++ b/arch/mips/pci/pci-ar71xx.c
@@ -24,7 +24,7 @@
 #include <asm/mach-ath79/pci.h>
 
 #define AR71XX_PCI_MEM_BASE	0x10000000
-#define AR71XX_PCI_MEM_SIZE	0x08000000
+#define AR71XX_PCI_MEM_SIZE	0x07000000
 
 #define AR71XX_PCI_WIN0_OFFS		0x10000000
 #define AR71XX_PCI_WIN1_OFFS		0x11000000
diff --git a/arch/mips/pci/pci-ar724x.c b/arch/mips/pci/pci-ar724x.c
index 86d77a6..c11c75b 100644
--- a/arch/mips/pci/pci-ar724x.c
+++ b/arch/mips/pci/pci-ar724x.c
@@ -21,7 +21,7 @@
 #define AR724X_PCI_CTRL_SIZE	0x100
 
 #define AR724X_PCI_MEM_BASE	0x10000000
-#define AR724X_PCI_MEM_SIZE	0x08000000
+#define AR724X_PCI_MEM_SIZE	0x04000000
 
 #define AR724X_PCI_REG_RESET		0x18
 #define AR724X_PCI_REG_INT_STATUS	0x4c
diff --git a/arch/mn10300/include/asm/dma-mapping.h b/arch/mn10300/include/asm/dma-mapping.h
index c1be439..a18abfc 100644
--- a/arch/mn10300/include/asm/dma-mapping.h
+++ b/arch/mn10300/include/asm/dma-mapping.h
@@ -168,4 +168,19 @@
 	mn10300_dcache_flush_inv();
 }
 
+/* Not supported for now */
+static inline int dma_mmap_coherent(struct device *dev,
+				    struct vm_area_struct *vma, void *cpu_addr,
+				    dma_addr_t dma_addr, size_t size)
+{
+	return -EINVAL;
+}
+
+static inline int dma_get_sgtable(struct device *dev, struct sg_table *sgt,
+				  void *cpu_addr, dma_addr_t dma_addr,
+				  size_t size)
+{
+	return -EINVAL;
+}
+
 #endif
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index b77feff..a32e34e 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -9,14 +9,12 @@
 	select RTC_DRV_GENERIC
 	select INIT_ALL_POSSIBLE
 	select BUG
-	select HAVE_IRQ_WORK
 	select HAVE_PERF_EVENTS
 	select GENERIC_ATOMIC64 if !64BIT
 	select HAVE_GENERIC_HARDIRQS
 	select BROKEN_RODATA
 	select GENERIC_IRQ_PROBE
 	select GENERIC_PCI_IOMAP
-	select IRQ_PER_CPU
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_STRNCPY_FROM_USER
diff --git a/arch/parisc/include/asm/dma-mapping.h b/arch/parisc/include/asm/dma-mapping.h
index 467bbd5..106b395 100644
--- a/arch/parisc/include/asm/dma-mapping.h
+++ b/arch/parisc/include/asm/dma-mapping.h
@@ -238,4 +238,19 @@
 /* At the moment, we panic on error for IOMMU resource exaustion */
 #define dma_mapping_error(dev, x)	0
 
+/* This API cannot be supported on PA-RISC */
+static inline int dma_mmap_coherent(struct device *dev,
+				    struct vm_area_struct *vma, void *cpu_addr,
+				    dma_addr_t dma_addr, size_t size)
+{
+	return -EINVAL;
+}
+
+static inline int dma_get_sgtable(struct device *dev, struct sg_table *sgt,
+				  void *cpu_addr, dma_addr_t dma_addr,
+				  size_t size)
+{
+	return -EINVAL;
+}
+
 #endif
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 17903f1..561ccca 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -118,14 +118,12 @@
 	select HAVE_SYSCALL_WRAPPERS if PPC64
 	select GENERIC_ATOMIC64 if PPC32
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
-	select HAVE_IRQ_WORK
 	select HAVE_PERF_EVENTS
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS && PPC_BOOK3S_64
 	select HAVE_GENERIC_HARDIRQS
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select SPARSE_IRQ
-	select IRQ_PER_CPU
 	select IRQ_DOMAIN
 	select GENERIC_IRQ_SHOW
 	select GENERIC_IRQ_SHOW_LEVEL
diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index 9710be3..136bba6 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -11,6 +11,7 @@
 
 #include <linux/types.h>
 #include <asm/hw_irq.h>
+#include <linux/device.h>
 
 #define MAX_HWEVENTS		8
 #define MAX_EVENT_ALTERNATIVES	8
@@ -35,6 +36,7 @@
 	void		(*disable_pmc)(unsigned int pmc, unsigned long mmcr[]);
 	int		(*limited_pmc_event)(u64 event_id);
 	u32		flags;
+	const struct attribute_group	**attr_groups;
 	int		n_generic;
 	int		*generic_events;
 	int		(*cache_events)[PERF_COUNT_HW_CACHE_MAX]
@@ -109,3 +111,27 @@
  * If an event_id is not subject to the constraint expressed by a particular
  * field, then it will have 0 in both the mask and value for that field.
  */
+
+extern ssize_t power_events_sysfs_show(struct device *dev,
+				struct device_attribute *attr, char *page);
+
+/*
+ * EVENT_VAR() is same as PMU_EVENT_VAR with a suffix.
+ *
+ * Having a suffix allows us to have aliases in sysfs - eg: the generic
+ * event 'cpu-cycles' can have two entries in sysfs: 'cpu-cycles' and
+ * 'PM_CYC' where the latter is the name by which the event is known in
+ * POWER CPU specification.
+ */
+#define	EVENT_VAR(_id, _suffix)		event_attr_##_id##_suffix
+#define	EVENT_PTR(_id, _suffix)		&EVENT_VAR(_id, _suffix).attr.attr
+
+#define	EVENT_ATTR(_name, _id, _suffix)					\
+	PMU_EVENT_ATTR(_name, EVENT_VAR(_id, _suffix), PME_PM_##_id,	\
+			power_events_sysfs_show)
+
+#define	GENERIC_EVENT_ATTR(_name, _id)	EVENT_ATTR(_name, _id, _g)
+#define	GENERIC_EVENT_PTR(_id)		EVENT_PTR(_id, _g)
+
+#define	POWER_EVENT_ATTR(_name, _id)	EVENT_ATTR(PM_##_name, _id, _p)
+#define	POWER_EVENT_PTR(_id)		EVENT_PTR(_id, _p)
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index d22e73e..e514de5 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -439,6 +439,8 @@
 ret_from_kernel_thread:
 	REST_NVGPRS(r1)
 	bl	schedule_tail
+	li	r3,0
+	stw	r3,0(r1)
 	mtlr	r14
 	mr	r3,r15
 	PPC440EP_ERR42
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index a0ca42f..ac05701 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -664,6 +664,19 @@
 	ld	r4,TI_FLAGS(r9)
 	andi.	r0,r4,_TIF_NEED_RESCHED
 	bne	1b
+
+	/*
+	 * arch_local_irq_restore() from preempt_schedule_irq above may
+	 * enable hard interrupt but we really should disable interrupts
+	 * when we return from the interrupt, and so that we don't get
+	 * interrupted after loading SRR0/1.
+	 */
+#ifdef CONFIG_PPC_BOOK3E
+	wrteei	0
+#else
+	ld	r10,PACAKMSR(r13) /* Get kernel MSR without EE */
+	mtmsrd	r10,1		  /* Update machine state */
+#endif /* CONFIG_PPC_BOOK3E */
 #endif /* CONFIG_PREEMPT */
 
 	.globl	fast_exc_return_irq
diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c
index c470a40..a7bc752 100644
--- a/arch/powerpc/kernel/kgdb.c
+++ b/arch/powerpc/kernel/kgdb.c
@@ -154,12 +154,12 @@
 static int kgdb_singlestep(struct pt_regs *regs)
 {
 	struct thread_info *thread_info, *exception_thread_info;
-	struct thread_info *backup_current_thread_info = \
-		(struct thread_info *)kmalloc(sizeof(struct thread_info), GFP_KERNEL);
+	struct thread_info *backup_current_thread_info;
 
 	if (user_mode(regs))
 		return 0;
 
+	backup_current_thread_info = (struct thread_info *)kmalloc(sizeof(struct thread_info), GFP_KERNEL);
 	/*
 	 * On Book E and perhaps other processors, singlestep is handled on
 	 * the critical exception stack.  This causes current_thread_info()
@@ -185,6 +185,7 @@
 		/* Restore current_thread_info lastly. */
 		memcpy(exception_thread_info, backup_current_thread_info, sizeof *thread_info);
 
+	kfree(backup_current_thread_info);
 	return 1;
 }
 
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 2e04b37..89b0f58 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -495,10 +495,15 @@
 	set_dec(DECREMENTER_MAX);
 
 	/* Some implementations of hotplug will get timer interrupts while
-	 * offline, just ignore these
+	 * offline, just ignore these and we also need to set
+	 * decrementers_next_tb as MAX to make sure __check_irq_replay
+	 * don't replay timer interrupt when return, otherwise we'll trap
+	 * here infinitely :(
 	 */
-	if (!cpu_online(smp_processor_id()))
+	if (!cpu_online(smp_processor_id())) {
+		*next_tb = ~(u64)0;
 		return;
+	}
 
 	/* Conditionally hard-enable interrupts now that the DEC has been
 	 * bumped to its maximum value
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index b0855e5..9d9cddc 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -39,6 +39,7 @@
 #define OP_31_XOP_TRAP      4
 #define OP_31_XOP_LWZX      23
 #define OP_31_XOP_TRAP_64   68
+#define OP_31_XOP_DCBF      86
 #define OP_31_XOP_LBZX      87
 #define OP_31_XOP_STWX      151
 #define OP_31_XOP_STBX      215
@@ -374,6 +375,7 @@
 			emulated = kvmppc_emulate_mtspr(vcpu, sprn, rs);
 			break;
 
+		case OP_31_XOP_DCBF:
 		case OP_31_XOP_DCBI:
 			/* Do nothing. The guest is performing dcbi because
 			 * hardware DMA is not snooped by the dcache, but
diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S
index 5658508..7443481 100644
--- a/arch/powerpc/mm/hash_low_64.S
+++ b/arch/powerpc/mm/hash_low_64.S
@@ -115,11 +115,13 @@
 	sldi	r29,r5,SID_SHIFT - VPN_SHIFT
 	rldicl  r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT - VPN_SHIFT)
 	or	r29,r28,r29
-
-	/* Calculate hash value for primary slot and store it in r28 */
-	rldicl	r5,r5,0,25		/* vsid & 0x0000007fffffffff */
-	rldicl	r0,r3,64-12,48		/* (ea >> 12) & 0xffff */
-	xor	r28,r5,r0
+	/*
+	 * Calculate hash value for primary slot and store it in r28
+	 * r3 = va, r5 = vsid
+	 * r0 = (va >> 12) & ((1ul << (28 - 12)) -1)
+	 */
+	rldicl	r0,r3,64-12,48
+	xor	r28,r5,r0		/* hash */
 	b	4f
 
 3:	/* Calc vpn and put it in r29 */
@@ -130,11 +132,12 @@
 	/*
 	 * calculate hash value for primary slot and
 	 * store it in r28 for 1T segment
+	 * r3 = va, r5 = vsid
 	 */
-	rldic	r28,r5,25,25		/* (vsid << 25) & 0x7fffffffff */
-	clrldi	r5,r5,40		/* vsid & 0xffffff */
-	rldicl	r0,r3,64-12,36		/* (ea >> 12) & 0xfffffff */
-	xor	r28,r28,r5
+	sldi	r28,r5,25		/* vsid << 25 */
+	/* r0 =  (va >> 12) & ((1ul << (40 - 12)) -1) */
+	rldicl	r0,r3,64-12,36
+	xor	r28,r28,r5		/* vsid ^ ( vsid << 25) */
 	xor	r28,r28,r0		/* hash */
 
 	/* Convert linux PTE bits into HW equivalents */
@@ -407,11 +410,13 @@
 	 */
 	rldicl  r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT - VPN_SHIFT)
 	or	r29,r28,r29
-
-	/* Calculate hash value for primary slot and store it in r28 */
-	rldicl	r5,r5,0,25		/* vsid & 0x0000007fffffffff */
-	rldicl	r0,r3,64-12,48		/* (ea >> 12) & 0xffff */
-	xor	r28,r5,r0
+	/*
+	 * Calculate hash value for primary slot and store it in r28
+	 * r3 = va, r5 = vsid
+	 * r0 = (va >> 12) & ((1ul << (28 - 12)) -1)
+	 */
+	rldicl	r0,r3,64-12,48
+	xor	r28,r5,r0		/* hash */
 	b	4f
 
 3:	/* Calc vpn and put it in r29 */
@@ -426,11 +431,12 @@
 	/*
 	 * Calculate hash value for primary slot and
 	 * store it in r28  for 1T segment
+	 * r3 = va, r5 = vsid
 	 */
-	rldic	r28,r5,25,25		/* (vsid << 25) & 0x7fffffffff */
-	clrldi	r5,r5,40		/* vsid & 0xffffff */
-	rldicl	r0,r3,64-12,36		/* (ea >> 12) & 0xfffffff */
-	xor	r28,r28,r5
+	sldi	r28,r5,25		/* vsid << 25 */
+	/* r0 = (va >> 12) & ((1ul << (40 - 12)) -1) */
+	rldicl	r0,r3,64-12,36
+	xor	r28,r28,r5		/* vsid ^ ( vsid << 25) */
 	xor	r28,r28,r0		/* hash */
 
 	/* Convert linux PTE bits into HW equivalents */
@@ -752,25 +758,27 @@
 	rldicl  r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT - VPN_SHIFT)
 	or	r29,r28,r29
 
-	/* Calculate hash value for primary slot and store it in r28 */
-	rldicl	r5,r5,0,25		/* vsid & 0x0000007fffffffff */
-	rldicl	r0,r3,64-16,52		/* (ea >> 16) & 0xfff */
-	xor	r28,r5,r0
+	/* Calculate hash value for primary slot and store it in r28
+	 * r3 = va, r5 = vsid
+	 * r0 = (va >> 16) & ((1ul << (28 - 16)) -1)
+	 */
+	rldicl	r0,r3,64-16,52
+	xor	r28,r5,r0		/* hash */
 	b	4f
 
 3:	/* Calc vpn and put it in r29 */
 	sldi	r29,r5,SID_SHIFT_1T - VPN_SHIFT
 	rldicl  r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT_1T - VPN_SHIFT)
 	or	r29,r28,r29
-
 	/*
 	 * calculate hash value for primary slot and
 	 * store it in r28 for 1T segment
+	 * r3 = va, r5 = vsid
 	 */
-	rldic	r28,r5,25,25		/* (vsid << 25) & 0x7fffffffff */
-	clrldi	r5,r5,40		/* vsid & 0xffffff */
-	rldicl	r0,r3,64-16,40		/* (ea >> 16) & 0xffffff */
-	xor	r28,r28,r5
+	sldi	r28,r5,25		/* vsid << 25 */
+	/* r0 = (va >> 16) & ((1ul << (40 - 16)) -1) */
+	rldicl	r0,r3,64-16,40
+	xor	r28,r28,r5		/* vsid ^ ( vsid << 25) */
 	xor	r28,r28,r0		/* hash */
 
 	/* Convert linux PTE bits into HW equivalents */
diff --git a/arch/powerpc/oprofile/op_model_power4.c b/arch/powerpc/oprofile/op_model_power4.c
index 315f949..f444b94 100644
--- a/arch/powerpc/oprofile/op_model_power4.c
+++ b/arch/powerpc/oprofile/op_model_power4.c
@@ -52,7 +52,7 @@
 	for (pmc = 0; pmc < 4; pmc++) {
 		psel = mmcr1 & (OPROFILE_PM_PMCSEL_MSK
 				<< (OPROFILE_MAX_PMC_NUM - pmc)
-				* OPROFILE_MAX_PMC_NUM);
+				* OPROFILE_PMSEL_FIELD_WIDTH);
 		psel = (psel >> ((OPROFILE_MAX_PMC_NUM - pmc)
 				 * OPROFILE_PMSEL_FIELD_WIDTH)) & ~1ULL;
 		unit = mmcr1 & (OPROFILE_PM_UNIT_MSK
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index aa2465e..fa476d5 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -1305,6 +1305,16 @@
 	return event->hw.idx;
 }
 
+ssize_t power_events_sysfs_show(struct device *dev,
+				struct device_attribute *attr, char *page)
+{
+	struct perf_pmu_events_attr *pmu_attr;
+
+	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
+
+	return sprintf(page, "event=0x%02llx\n", pmu_attr->id);
+}
+
 struct pmu power_pmu = {
 	.pmu_enable	= power_pmu_enable,
 	.pmu_disable	= power_pmu_disable,
@@ -1537,6 +1547,8 @@
 	pr_info("%s performance monitor hardware support registered\n",
 		pmu->name);
 
+	power_pmu.attr_groups = ppmu->attr_groups;
+
 #ifdef MSR_HV
 	/*
 	 * Use FCHV to ignore kernel events if MSR.HV is set.
diff --git a/arch/powerpc/perf/power7-pmu.c b/arch/powerpc/perf/power7-pmu.c
index 2ee01e3..b554879 100644
--- a/arch/powerpc/perf/power7-pmu.c
+++ b/arch/powerpc/perf/power7-pmu.c
@@ -51,6 +51,18 @@
 #define MMCR1_PMCSEL_MSK	0xff
 
 /*
+ * Power7 event codes.
+ */
+#define	PME_PM_CYC			0x1e
+#define	PME_PM_GCT_NOSLOT_CYC		0x100f8
+#define	PME_PM_CMPLU_STALL		0x4000a
+#define	PME_PM_INST_CMPL		0x2
+#define	PME_PM_LD_REF_L1		0xc880
+#define	PME_PM_LD_MISS_L1		0x400f0
+#define	PME_PM_BRU_FIN			0x10068
+#define	PME_PM_BRU_MPRED		0x400f6
+
+/*
  * Layout of constraint bits:
  * 6666555555555544444444443333333333222222222211111111110000000000
  * 3210987654321098765432109876543210987654321098765432109876543210
@@ -307,14 +319,14 @@
 }
 
 static int power7_generic_events[] = {
-	[PERF_COUNT_HW_CPU_CYCLES] = 0x1e,
-	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x100f8, /* GCT_NOSLOT_CYC */
-	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x4000a,  /* CMPLU_STALL */
-	[PERF_COUNT_HW_INSTRUCTIONS] = 2,
-	[PERF_COUNT_HW_CACHE_REFERENCES] = 0xc880,	/* LD_REF_L1_LSU*/
-	[PERF_COUNT_HW_CACHE_MISSES] = 0x400f0,		/* LD_MISS_L1	*/
-	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x10068,	/* BRU_FIN	*/
-	[PERF_COUNT_HW_BRANCH_MISSES] = 0x400f6,	/* BR_MPRED	*/
+	[PERF_COUNT_HW_CPU_CYCLES] =			PME_PM_CYC,
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =	PME_PM_GCT_NOSLOT_CYC,
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =	PME_PM_CMPLU_STALL,
+	[PERF_COUNT_HW_INSTRUCTIONS] =			PME_PM_INST_CMPL,
+	[PERF_COUNT_HW_CACHE_REFERENCES] =		PME_PM_LD_REF_L1,
+	[PERF_COUNT_HW_CACHE_MISSES] =			PME_PM_LD_MISS_L1,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] =		PME_PM_BRU_FIN,
+	[PERF_COUNT_HW_BRANCH_MISSES] =			PME_PM_BRU_MPRED,
 };
 
 #define C(x)	PERF_COUNT_HW_CACHE_##x
@@ -362,6 +374,57 @@
 	},
 };
 
+
+GENERIC_EVENT_ATTR(cpu-cycles,			CYC);
+GENERIC_EVENT_ATTR(stalled-cycles-frontend,	GCT_NOSLOT_CYC);
+GENERIC_EVENT_ATTR(stalled-cycles-backend,	CMPLU_STALL);
+GENERIC_EVENT_ATTR(instructions,		INST_CMPL);
+GENERIC_EVENT_ATTR(cache-references,		LD_REF_L1);
+GENERIC_EVENT_ATTR(cache-misses,		LD_MISS_L1);
+GENERIC_EVENT_ATTR(branch-instructions,		BRU_FIN);
+GENERIC_EVENT_ATTR(branch-misses,		BRU_MPRED);
+
+POWER_EVENT_ATTR(CYC,				CYC);
+POWER_EVENT_ATTR(GCT_NOSLOT_CYC,		GCT_NOSLOT_CYC);
+POWER_EVENT_ATTR(CMPLU_STALL,			CMPLU_STALL);
+POWER_EVENT_ATTR(INST_CMPL,			INST_CMPL);
+POWER_EVENT_ATTR(LD_REF_L1,			LD_REF_L1);
+POWER_EVENT_ATTR(LD_MISS_L1,			LD_MISS_L1);
+POWER_EVENT_ATTR(BRU_FIN,			BRU_FIN)
+POWER_EVENT_ATTR(BRU_MPRED,			BRU_MPRED);
+
+static struct attribute *power7_events_attr[] = {
+	GENERIC_EVENT_PTR(CYC),
+	GENERIC_EVENT_PTR(GCT_NOSLOT_CYC),
+	GENERIC_EVENT_PTR(CMPLU_STALL),
+	GENERIC_EVENT_PTR(INST_CMPL),
+	GENERIC_EVENT_PTR(LD_REF_L1),
+	GENERIC_EVENT_PTR(LD_MISS_L1),
+	GENERIC_EVENT_PTR(BRU_FIN),
+	GENERIC_EVENT_PTR(BRU_MPRED),
+
+	POWER_EVENT_PTR(CYC),
+	POWER_EVENT_PTR(GCT_NOSLOT_CYC),
+	POWER_EVENT_PTR(CMPLU_STALL),
+	POWER_EVENT_PTR(INST_CMPL),
+	POWER_EVENT_PTR(LD_REF_L1),
+	POWER_EVENT_PTR(LD_MISS_L1),
+	POWER_EVENT_PTR(BRU_FIN),
+	POWER_EVENT_PTR(BRU_MPRED),
+	NULL
+};
+
+
+static struct attribute_group power7_pmu_events_group = {
+	.name = "events",
+	.attrs = power7_events_attr,
+};
+
+static const struct attribute_group *power7_pmu_attr_groups[] = {
+	&power7_pmu_events_group,
+	NULL,
+};
+
 static struct power_pmu power7_pmu = {
 	.name			= "POWER7",
 	.n_counter		= 6,
@@ -373,6 +436,7 @@
 	.get_alternatives	= power7_get_alternatives,
 	.disable_pmc		= power7_disable_pmc,
 	.flags			= PPMU_ALT_SIPR,
+	.attr_groups		= power7_pmu_attr_groups,
 	.n_generic		= ARRAY_SIZE(power7_generic_events),
 	.generic_events		= power7_generic_events,
 	.cache_events		= &power7_cache_events,
diff --git a/arch/powerpc/platforms/pasemi/cpufreq.c b/arch/powerpc/platforms/pasemi/cpufreq.c
index 95d0017..890f30e 100644
--- a/arch/powerpc/platforms/pasemi/cpufreq.c
+++ b/arch/powerpc/platforms/pasemi/cpufreq.c
@@ -236,6 +236,13 @@
 
 static int pas_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 {
+	/*
+	 * We don't support CPU hotplug. Don't unmap after the system
+	 * has already made it to a running state.
+	 */
+	if (system_state != SYSTEM_BOOTING)
+		return 0;
+
 	if (sdcasr_mapbase)
 		iounmap(sdcasr_mapbase);
 	if (sdcpwr_mapbase)
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index b5ea38c..c15ba7d 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -78,7 +78,6 @@
 	select HAVE_KVM if 64BIT
 	select HAVE_ARCH_TRACEHOOK
 	select INIT_ALL_POSSIBLE
-	select HAVE_IRQ_WORK
 	select HAVE_PERF_EVENTS
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select HAVE_DEBUG_KMEMLEAK
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index c1d7930..098adbb 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -1365,6 +1365,18 @@
 	__pmd_idte(address, pmdp);
 }
 
+#define __HAVE_ARCH_PMDP_SET_WRPROTECT
+static inline void pmdp_set_wrprotect(struct mm_struct *mm,
+				      unsigned long address, pmd_t *pmdp)
+{
+	pmd_t pmd = *pmdp;
+
+	if (pmd_write(pmd)) {
+		__pmd_idte(address, pmdp);
+		set_pmd_at(mm, address, pmdp, pmd_wrprotect(pmd));
+	}
+}
+
 static inline pmd_t mk_pmd_phys(unsigned long physpage, pgprot_t pgprot)
 {
 	pmd_t __pmd;
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index a5f4f5a..0aa98db 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -120,6 +120,9 @@
 	nsecs = ktime_to_ns(ktime_add(timespec_to_ktime(ts), expires));
 	do_div(nsecs, 125);
 	S390_lowcore.clock_comparator = sched_clock_base_cc + (nsecs << 9);
+	/* Program the maximum value if we have an overflow (== year 2042) */
+	if (unlikely(S390_lowcore.clock_comparator < sched_clock_base_cc))
+		S390_lowcore.clock_comparator = -1ULL;
 	set_clock_comparator(S390_lowcore.clock_comparator);
 	return 0;
 }
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index babc2b8..9c833c5 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -11,7 +11,6 @@
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_DMA_API_DEBUG
 	select HAVE_DMA_ATTRS
-	select HAVE_IRQ_WORK
 	select HAVE_PERF_EVENTS
 	select HAVE_DEBUG_BUGVERBOSE
 	select ARCH_HAVE_CUSTOM_GPIO_H
@@ -91,9 +90,6 @@
 config GENERIC_HWEIGHT
 	def_bool y
 
-config IRQ_PER_CPU
-	def_bool y
-
 config GENERIC_GPIO
 	def_bool n
 
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 9f2edb5..9bff3db 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -23,7 +23,6 @@
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select RTC_CLASS
 	select RTC_DRV_M48T59
-	select HAVE_IRQ_WORK
 	select HAVE_DMA_ATTRS
 	select HAVE_DMA_API_DEBUG
 	select HAVE_ARCH_JUMP_LABEL
@@ -61,6 +60,7 @@
 	select HAVE_MEMBLOCK
 	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_SYSCALL_WRAPPERS
+	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_SYSCALL_TRACEPOINTS
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 7870be0..08fcce90 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -71,7 +71,6 @@
 #define PMD_PADDR	_AC(0xfffffffe,UL)
 #define PMD_PADDR_SHIFT	_AC(11,UL)
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define PMD_ISHUGE	_AC(0x00000001,UL)
 
 /* This is the PMD layout when PMD_ISHUGE is set.  With 4MB huge
@@ -86,7 +85,6 @@
 #define PMD_HUGE_ACCESSED	_AC(0x00000080,UL)
 #define PMD_HUGE_EXEC		_AC(0x00000040,UL)
 #define PMD_HUGE_SPLITTING	_AC(0x00000020,UL)
-#endif
 
 /* PGDs point to PMD tables which are 8K aligned.  */
 #define PGD_PADDR	_AC(0xfffffffc,UL)
@@ -628,6 +626,12 @@
 	return pte_val(pte) & _PAGE_SPECIAL;
 }
 
+static inline int pmd_large(pmd_t pmd)
+{
+	return (pmd_val(pmd) & (PMD_ISHUGE | PMD_HUGE_PRESENT)) ==
+		(PMD_ISHUGE | PMD_HUGE_PRESENT);
+}
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 static inline int pmd_young(pmd_t pmd)
 {
@@ -646,12 +650,6 @@
 	return val >> (PAGE_SHIFT - PMD_PADDR_SHIFT);
 }
 
-static inline int pmd_large(pmd_t pmd)
-{
-	return (pmd_val(pmd) & (PMD_ISHUGE | PMD_HUGE_PRESENT)) ==
-		(PMD_ISHUGE | PMD_HUGE_PRESENT);
-}
-
 static inline int pmd_trans_splitting(pmd_t pmd)
 {
 	return (pmd_val(pmd) & (PMD_ISHUGE|PMD_HUGE_SPLITTING)) ==
diff --git a/arch/sparc/kernel/sbus.c b/arch/sparc/kernel/sbus.c
index 1271b3a..be5bdf9 100644
--- a/arch/sparc/kernel/sbus.c
+++ b/arch/sparc/kernel/sbus.c
@@ -554,10 +554,8 @@
 	regs = pr->phys_addr;
 
 	iommu = kzalloc(sizeof(*iommu), GFP_ATOMIC);
-	if (!iommu)
-		goto fatal_memory_error;
 	strbuf = kzalloc(sizeof(*strbuf), GFP_ATOMIC);
-	if (!strbuf)
+	if (!iommu || !strbuf)
 		goto fatal_memory_error;
 
 	op->dev.archdata.iommu = iommu;
@@ -656,6 +654,8 @@
 	return;
 
 fatal_memory_error:
+	kfree(iommu);
+	kfree(strbuf);
 	prom_printf("sbus_iommu_init: Fatal memory allocation error.\n");
 }
 
diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c
index 42c55df..01ee23d 100644
--- a/arch/sparc/mm/gup.c
+++ b/arch/sparc/mm/gup.c
@@ -66,6 +66,56 @@
 	return 1;
 }
 
+static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
+			unsigned long end, int write, struct page **pages,
+			int *nr)
+{
+	struct page *head, *page, *tail;
+	u32 mask;
+	int refs;
+
+	mask = PMD_HUGE_PRESENT;
+	if (write)
+		mask |= PMD_HUGE_WRITE;
+	if ((pmd_val(pmd) & mask) != mask)
+		return 0;
+
+	refs = 0;
+	head = pmd_page(pmd);
+	page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
+	tail = page;
+	do {
+		VM_BUG_ON(compound_head(page) != head);
+		pages[*nr] = page;
+		(*nr)++;
+		page++;
+		refs++;
+	} while (addr += PAGE_SIZE, addr != end);
+
+	if (!page_cache_add_speculative(head, refs)) {
+		*nr -= refs;
+		return 0;
+	}
+
+	if (unlikely(pmd_val(pmd) != pmd_val(*pmdp))) {
+		*nr -= refs;
+		while (refs--)
+			put_page(head);
+		return 0;
+	}
+
+	/* Any tail page need their mapcount reference taken before we
+	 * return.
+	 */
+	while (refs--) {
+		if (PageTail(tail))
+			get_huge_page_tail(tail);
+		tail++;
+	}
+
+	return 1;
+}
+
 static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 		int write, struct page **pages, int *nr)
 {
@@ -77,9 +127,14 @@
 		pmd_t pmd = *pmdp;
 
 		next = pmd_addr_end(addr, end);
-		if (pmd_none(pmd))
+		if (pmd_none(pmd) || pmd_trans_splitting(pmd))
 			return 0;
-		if (!gup_pte_range(pmd, addr, next, write, pages, nr))
+		if (unlikely(pmd_large(pmd))) {
+			if (!gup_huge_pmd(pmdp, pmd, addr, next,
+					  write, pages, nr))
+				return 0;
+		} else if (!gup_pte_range(pmd, addr, next, write,
+					  pages, nr))
 			return 0;
 	} while (pmdp++, addr = next, addr != end);
 
diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig
index 875d008..1bb7ad4 100644
--- a/arch/tile/Kconfig
+++ b/arch/tile/Kconfig
@@ -140,6 +140,8 @@
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
+
 menu "Tilera-specific configuration"
 
 config NR_CPUS
diff --git a/arch/tile/include/asm/io.h b/arch/tile/include/asm/io.h
index 2a9b293..3167291 100644
--- a/arch/tile/include/asm/io.h
+++ b/arch/tile/include/asm/io.h
@@ -250,7 +250,9 @@
 #define iowrite32 writel
 #define iowrite64 writeq
 
-static inline void memset_io(void *dst, int val, size_t len)
+#if CHIP_HAS_MMIO() || defined(CONFIG_PCI)
+
+static inline void memset_io(volatile void *dst, int val, size_t len)
 {
 	int x;
 	BUG_ON((unsigned long)dst & 0x3);
@@ -277,6 +279,8 @@
 		writel(*(u32 *)(src + x), dst + x);
 }
 
+#endif
+
 /*
  * The Tile architecture does not support IOPORT, even with PCI.
  * Unfortunately we can't yet simply not declare these methods,
diff --git a/arch/tile/include/asm/irqflags.h b/arch/tile/include/asm/irqflags.h
index b4e96fe..241c0bb 100644
--- a/arch/tile/include/asm/irqflags.h
+++ b/arch/tile/include/asm/irqflags.h
@@ -18,32 +18,20 @@
 #include <arch/interrupts.h>
 #include <arch/chip.h>
 
-#if !defined(__tilegx__) && defined(__ASSEMBLY__)
-
 /*
  * The set of interrupts we want to allow when interrupts are nominally
  * disabled.  The remainder are effectively "NMI" interrupts from
  * the point of view of the generic Linux code.  Note that synchronous
  * interrupts (aka "non-queued") are not blocked by the mask in any case.
  */
-#if CHIP_HAS_AUX_PERF_COUNTERS()
-#define LINUX_MASKABLE_INTERRUPTS_HI \
-	(~(INT_MASK_HI(INT_PERF_COUNT) | INT_MASK_HI(INT_AUX_PERF_COUNT)))
-#else
-#define LINUX_MASKABLE_INTERRUPTS_HI \
-	(~(INT_MASK_HI(INT_PERF_COUNT)))
-#endif
-
-#else
-
-#if CHIP_HAS_AUX_PERF_COUNTERS()
 #define LINUX_MASKABLE_INTERRUPTS \
-	(~(INT_MASK(INT_PERF_COUNT) | INT_MASK(INT_AUX_PERF_COUNT)))
-#else
-#define LINUX_MASKABLE_INTERRUPTS \
-	(~(INT_MASK(INT_PERF_COUNT)))
-#endif
+	(~((_AC(1,ULL) << INT_PERF_COUNT) | (_AC(1,ULL) << INT_AUX_PERF_COUNT)))
 
+#if CHIP_HAS_SPLIT_INTR_MASK()
+/* The same macro, but for the two 32-bit SPRs separately. */
+#define LINUX_MASKABLE_INTERRUPTS_LO (-1)
+#define LINUX_MASKABLE_INTERRUPTS_HI \
+	(~((1 << (INT_PERF_COUNT - 32)) | (1 << (INT_AUX_PERF_COUNT - 32))))
 #endif
 
 #ifndef __ASSEMBLY__
@@ -126,7 +114,7 @@
  * to know our current state.
  */
 DECLARE_PER_CPU(unsigned long long, interrupts_enabled_mask);
-#define INITIAL_INTERRUPTS_ENABLED INT_MASK(INT_MEM_ERROR)
+#define INITIAL_INTERRUPTS_ENABLED (1ULL << INT_MEM_ERROR)
 
 /* Disable interrupts. */
 #define arch_local_irq_disable() \
@@ -165,7 +153,7 @@
 
 /* Prevent the given interrupt from being enabled next time we enable irqs. */
 #define arch_local_irq_mask(interrupt) \
-	(__get_cpu_var(interrupts_enabled_mask) &= ~INT_MASK(interrupt))
+	(__get_cpu_var(interrupts_enabled_mask) &= ~(1ULL << (interrupt)))
 
 /* Prevent the given interrupt from being enabled immediately. */
 #define arch_local_irq_mask_now(interrupt) do { \
@@ -175,7 +163,7 @@
 
 /* Allow the given interrupt to be enabled next time we enable irqs. */
 #define arch_local_irq_unmask(interrupt) \
-	(__get_cpu_var(interrupts_enabled_mask) |= INT_MASK(interrupt))
+	(__get_cpu_var(interrupts_enabled_mask) |= (1ULL << (interrupt)))
 
 /* Allow the given interrupt to be enabled immediately, if !irqs_disabled. */
 #define arch_local_irq_unmask_now(interrupt) do { \
@@ -250,7 +238,7 @@
 /* Disable interrupts. */
 #define IRQ_DISABLE(tmp0, tmp1)					\
 	{							\
-	 movei  tmp0, -1;					\
+	 movei  tmp0, LINUX_MASKABLE_INTERRUPTS_LO;		\
 	 moveli tmp1, lo16(LINUX_MASKABLE_INTERRUPTS_HI)	\
 	};							\
 	{							\
diff --git a/arch/tile/include/uapi/arch/interrupts_32.h b/arch/tile/include/uapi/arch/interrupts_32.h
index 96b5710..2efe3f6 100644
--- a/arch/tile/include/uapi/arch/interrupts_32.h
+++ b/arch/tile/include/uapi/arch/interrupts_32.h
@@ -15,6 +15,7 @@
 #ifndef __ARCH_INTERRUPTS_H__
 #define __ARCH_INTERRUPTS_H__
 
+#ifndef __KERNEL__
 /** Mask for an interrupt. */
 /* Note: must handle breaking interrupts into high and low words manually. */
 #define INT_MASK_LO(intno) (1 << (intno))
@@ -23,6 +24,7 @@
 #ifndef __ASSEMBLER__
 #define INT_MASK(intno) (1ULL << (intno))
 #endif
+#endif
 
 
 /** Where a given interrupt executes */
@@ -92,216 +94,216 @@
 
 #ifndef __ASSEMBLER__
 #define QUEUED_INTERRUPTS ( \
-    INT_MASK(INT_MEM_ERROR) | \
-    INT_MASK(INT_DMATLB_MISS) | \
-    INT_MASK(INT_DMATLB_ACCESS) | \
-    INT_MASK(INT_SNITLB_MISS) | \
-    INT_MASK(INT_SN_NOTIFY) | \
-    INT_MASK(INT_SN_FIREWALL) | \
-    INT_MASK(INT_IDN_FIREWALL) | \
-    INT_MASK(INT_UDN_FIREWALL) | \
-    INT_MASK(INT_TILE_TIMER) | \
-    INT_MASK(INT_IDN_TIMER) | \
-    INT_MASK(INT_UDN_TIMER) | \
-    INT_MASK(INT_DMA_NOTIFY) | \
-    INT_MASK(INT_IDN_CA) | \
-    INT_MASK(INT_UDN_CA) | \
-    INT_MASK(INT_IDN_AVAIL) | \
-    INT_MASK(INT_UDN_AVAIL) | \
-    INT_MASK(INT_PERF_COUNT) | \
-    INT_MASK(INT_INTCTRL_3) | \
-    INT_MASK(INT_INTCTRL_2) | \
-    INT_MASK(INT_INTCTRL_1) | \
-    INT_MASK(INT_INTCTRL_0) | \
-    INT_MASK(INT_BOOT_ACCESS) | \
-    INT_MASK(INT_WORLD_ACCESS) | \
-    INT_MASK(INT_I_ASID) | \
-    INT_MASK(INT_D_ASID) | \
-    INT_MASK(INT_DMA_ASID) | \
-    INT_MASK(INT_SNI_ASID) | \
-    INT_MASK(INT_DMA_CPL) | \
-    INT_MASK(INT_SN_CPL) | \
-    INT_MASK(INT_DOUBLE_FAULT) | \
-    INT_MASK(INT_AUX_PERF_COUNT) | \
+    (1ULL << INT_MEM_ERROR) | \
+    (1ULL << INT_DMATLB_MISS) | \
+    (1ULL << INT_DMATLB_ACCESS) | \
+    (1ULL << INT_SNITLB_MISS) | \
+    (1ULL << INT_SN_NOTIFY) | \
+    (1ULL << INT_SN_FIREWALL) | \
+    (1ULL << INT_IDN_FIREWALL) | \
+    (1ULL << INT_UDN_FIREWALL) | \
+    (1ULL << INT_TILE_TIMER) | \
+    (1ULL << INT_IDN_TIMER) | \
+    (1ULL << INT_UDN_TIMER) | \
+    (1ULL << INT_DMA_NOTIFY) | \
+    (1ULL << INT_IDN_CA) | \
+    (1ULL << INT_UDN_CA) | \
+    (1ULL << INT_IDN_AVAIL) | \
+    (1ULL << INT_UDN_AVAIL) | \
+    (1ULL << INT_PERF_COUNT) | \
+    (1ULL << INT_INTCTRL_3) | \
+    (1ULL << INT_INTCTRL_2) | \
+    (1ULL << INT_INTCTRL_1) | \
+    (1ULL << INT_INTCTRL_0) | \
+    (1ULL << INT_BOOT_ACCESS) | \
+    (1ULL << INT_WORLD_ACCESS) | \
+    (1ULL << INT_I_ASID) | \
+    (1ULL << INT_D_ASID) | \
+    (1ULL << INT_DMA_ASID) | \
+    (1ULL << INT_SNI_ASID) | \
+    (1ULL << INT_DMA_CPL) | \
+    (1ULL << INT_SN_CPL) | \
+    (1ULL << INT_DOUBLE_FAULT) | \
+    (1ULL << INT_AUX_PERF_COUNT) | \
     0)
 #define NONQUEUED_INTERRUPTS ( \
-    INT_MASK(INT_ITLB_MISS) | \
-    INT_MASK(INT_ILL) | \
-    INT_MASK(INT_GPV) | \
-    INT_MASK(INT_SN_ACCESS) | \
-    INT_MASK(INT_IDN_ACCESS) | \
-    INT_MASK(INT_UDN_ACCESS) | \
-    INT_MASK(INT_IDN_REFILL) | \
-    INT_MASK(INT_UDN_REFILL) | \
-    INT_MASK(INT_IDN_COMPLETE) | \
-    INT_MASK(INT_UDN_COMPLETE) | \
-    INT_MASK(INT_SWINT_3) | \
-    INT_MASK(INT_SWINT_2) | \
-    INT_MASK(INT_SWINT_1) | \
-    INT_MASK(INT_SWINT_0) | \
-    INT_MASK(INT_UNALIGN_DATA) | \
-    INT_MASK(INT_DTLB_MISS) | \
-    INT_MASK(INT_DTLB_ACCESS) | \
-    INT_MASK(INT_SN_STATIC_ACCESS) | \
+    (1ULL << INT_ITLB_MISS) | \
+    (1ULL << INT_ILL) | \
+    (1ULL << INT_GPV) | \
+    (1ULL << INT_SN_ACCESS) | \
+    (1ULL << INT_IDN_ACCESS) | \
+    (1ULL << INT_UDN_ACCESS) | \
+    (1ULL << INT_IDN_REFILL) | \
+    (1ULL << INT_UDN_REFILL) | \
+    (1ULL << INT_IDN_COMPLETE) | \
+    (1ULL << INT_UDN_COMPLETE) | \
+    (1ULL << INT_SWINT_3) | \
+    (1ULL << INT_SWINT_2) | \
+    (1ULL << INT_SWINT_1) | \
+    (1ULL << INT_SWINT_0) | \
+    (1ULL << INT_UNALIGN_DATA) | \
+    (1ULL << INT_DTLB_MISS) | \
+    (1ULL << INT_DTLB_ACCESS) | \
+    (1ULL << INT_SN_STATIC_ACCESS) | \
     0)
 #define CRITICAL_MASKED_INTERRUPTS ( \
-    INT_MASK(INT_MEM_ERROR) | \
-    INT_MASK(INT_DMATLB_MISS) | \
-    INT_MASK(INT_DMATLB_ACCESS) | \
-    INT_MASK(INT_SNITLB_MISS) | \
-    INT_MASK(INT_SN_NOTIFY) | \
-    INT_MASK(INT_SN_FIREWALL) | \
-    INT_MASK(INT_IDN_FIREWALL) | \
-    INT_MASK(INT_UDN_FIREWALL) | \
-    INT_MASK(INT_TILE_TIMER) | \
-    INT_MASK(INT_IDN_TIMER) | \
-    INT_MASK(INT_UDN_TIMER) | \
-    INT_MASK(INT_DMA_NOTIFY) | \
-    INT_MASK(INT_IDN_CA) | \
-    INT_MASK(INT_UDN_CA) | \
-    INT_MASK(INT_IDN_AVAIL) | \
-    INT_MASK(INT_UDN_AVAIL) | \
-    INT_MASK(INT_PERF_COUNT) | \
-    INT_MASK(INT_INTCTRL_3) | \
-    INT_MASK(INT_INTCTRL_2) | \
-    INT_MASK(INT_INTCTRL_1) | \
-    INT_MASK(INT_INTCTRL_0) | \
-    INT_MASK(INT_AUX_PERF_COUNT) | \
+    (1ULL << INT_MEM_ERROR) | \
+    (1ULL << INT_DMATLB_MISS) | \
+    (1ULL << INT_DMATLB_ACCESS) | \
+    (1ULL << INT_SNITLB_MISS) | \
+    (1ULL << INT_SN_NOTIFY) | \
+    (1ULL << INT_SN_FIREWALL) | \
+    (1ULL << INT_IDN_FIREWALL) | \
+    (1ULL << INT_UDN_FIREWALL) | \
+    (1ULL << INT_TILE_TIMER) | \
+    (1ULL << INT_IDN_TIMER) | \
+    (1ULL << INT_UDN_TIMER) | \
+    (1ULL << INT_DMA_NOTIFY) | \
+    (1ULL << INT_IDN_CA) | \
+    (1ULL << INT_UDN_CA) | \
+    (1ULL << INT_IDN_AVAIL) | \
+    (1ULL << INT_UDN_AVAIL) | \
+    (1ULL << INT_PERF_COUNT) | \
+    (1ULL << INT_INTCTRL_3) | \
+    (1ULL << INT_INTCTRL_2) | \
+    (1ULL << INT_INTCTRL_1) | \
+    (1ULL << INT_INTCTRL_0) | \
+    (1ULL << INT_AUX_PERF_COUNT) | \
     0)
 #define CRITICAL_UNMASKED_INTERRUPTS ( \
-    INT_MASK(INT_ITLB_MISS) | \
-    INT_MASK(INT_ILL) | \
-    INT_MASK(INT_GPV) | \
-    INT_MASK(INT_SN_ACCESS) | \
-    INT_MASK(INT_IDN_ACCESS) | \
-    INT_MASK(INT_UDN_ACCESS) | \
-    INT_MASK(INT_IDN_REFILL) | \
-    INT_MASK(INT_UDN_REFILL) | \
-    INT_MASK(INT_IDN_COMPLETE) | \
-    INT_MASK(INT_UDN_COMPLETE) | \
-    INT_MASK(INT_SWINT_3) | \
-    INT_MASK(INT_SWINT_2) | \
-    INT_MASK(INT_SWINT_1) | \
-    INT_MASK(INT_SWINT_0) | \
-    INT_MASK(INT_UNALIGN_DATA) | \
-    INT_MASK(INT_DTLB_MISS) | \
-    INT_MASK(INT_DTLB_ACCESS) | \
-    INT_MASK(INT_BOOT_ACCESS) | \
-    INT_MASK(INT_WORLD_ACCESS) | \
-    INT_MASK(INT_I_ASID) | \
-    INT_MASK(INT_D_ASID) | \
-    INT_MASK(INT_DMA_ASID) | \
-    INT_MASK(INT_SNI_ASID) | \
-    INT_MASK(INT_DMA_CPL) | \
-    INT_MASK(INT_SN_CPL) | \
-    INT_MASK(INT_DOUBLE_FAULT) | \
-    INT_MASK(INT_SN_STATIC_ACCESS) | \
+    (1ULL << INT_ITLB_MISS) | \
+    (1ULL << INT_ILL) | \
+    (1ULL << INT_GPV) | \
+    (1ULL << INT_SN_ACCESS) | \
+    (1ULL << INT_IDN_ACCESS) | \
+    (1ULL << INT_UDN_ACCESS) | \
+    (1ULL << INT_IDN_REFILL) | \
+    (1ULL << INT_UDN_REFILL) | \
+    (1ULL << INT_IDN_COMPLETE) | \
+    (1ULL << INT_UDN_COMPLETE) | \
+    (1ULL << INT_SWINT_3) | \
+    (1ULL << INT_SWINT_2) | \
+    (1ULL << INT_SWINT_1) | \
+    (1ULL << INT_SWINT_0) | \
+    (1ULL << INT_UNALIGN_DATA) | \
+    (1ULL << INT_DTLB_MISS) | \
+    (1ULL << INT_DTLB_ACCESS) | \
+    (1ULL << INT_BOOT_ACCESS) | \
+    (1ULL << INT_WORLD_ACCESS) | \
+    (1ULL << INT_I_ASID) | \
+    (1ULL << INT_D_ASID) | \
+    (1ULL << INT_DMA_ASID) | \
+    (1ULL << INT_SNI_ASID) | \
+    (1ULL << INT_DMA_CPL) | \
+    (1ULL << INT_SN_CPL) | \
+    (1ULL << INT_DOUBLE_FAULT) | \
+    (1ULL << INT_SN_STATIC_ACCESS) | \
     0)
 #define MASKABLE_INTERRUPTS ( \
-    INT_MASK(INT_MEM_ERROR) | \
-    INT_MASK(INT_IDN_REFILL) | \
-    INT_MASK(INT_UDN_REFILL) | \
-    INT_MASK(INT_IDN_COMPLETE) | \
-    INT_MASK(INT_UDN_COMPLETE) | \
-    INT_MASK(INT_DMATLB_MISS) | \
-    INT_MASK(INT_DMATLB_ACCESS) | \
-    INT_MASK(INT_SNITLB_MISS) | \
-    INT_MASK(INT_SN_NOTIFY) | \
-    INT_MASK(INT_SN_FIREWALL) | \
-    INT_MASK(INT_IDN_FIREWALL) | \
-    INT_MASK(INT_UDN_FIREWALL) | \
-    INT_MASK(INT_TILE_TIMER) | \
-    INT_MASK(INT_IDN_TIMER) | \
-    INT_MASK(INT_UDN_TIMER) | \
-    INT_MASK(INT_DMA_NOTIFY) | \
-    INT_MASK(INT_IDN_CA) | \
-    INT_MASK(INT_UDN_CA) | \
-    INT_MASK(INT_IDN_AVAIL) | \
-    INT_MASK(INT_UDN_AVAIL) | \
-    INT_MASK(INT_PERF_COUNT) | \
-    INT_MASK(INT_INTCTRL_3) | \
-    INT_MASK(INT_INTCTRL_2) | \
-    INT_MASK(INT_INTCTRL_1) | \
-    INT_MASK(INT_INTCTRL_0) | \
-    INT_MASK(INT_AUX_PERF_COUNT) | \
+    (1ULL << INT_MEM_ERROR) | \
+    (1ULL << INT_IDN_REFILL) | \
+    (1ULL << INT_UDN_REFILL) | \
+    (1ULL << INT_IDN_COMPLETE) | \
+    (1ULL << INT_UDN_COMPLETE) | \
+    (1ULL << INT_DMATLB_MISS) | \
+    (1ULL << INT_DMATLB_ACCESS) | \
+    (1ULL << INT_SNITLB_MISS) | \
+    (1ULL << INT_SN_NOTIFY) | \
+    (1ULL << INT_SN_FIREWALL) | \
+    (1ULL << INT_IDN_FIREWALL) | \
+    (1ULL << INT_UDN_FIREWALL) | \
+    (1ULL << INT_TILE_TIMER) | \
+    (1ULL << INT_IDN_TIMER) | \
+    (1ULL << INT_UDN_TIMER) | \
+    (1ULL << INT_DMA_NOTIFY) | \
+    (1ULL << INT_IDN_CA) | \
+    (1ULL << INT_UDN_CA) | \
+    (1ULL << INT_IDN_AVAIL) | \
+    (1ULL << INT_UDN_AVAIL) | \
+    (1ULL << INT_PERF_COUNT) | \
+    (1ULL << INT_INTCTRL_3) | \
+    (1ULL << INT_INTCTRL_2) | \
+    (1ULL << INT_INTCTRL_1) | \
+    (1ULL << INT_INTCTRL_0) | \
+    (1ULL << INT_AUX_PERF_COUNT) | \
     0)
 #define UNMASKABLE_INTERRUPTS ( \
-    INT_MASK(INT_ITLB_MISS) | \
-    INT_MASK(INT_ILL) | \
-    INT_MASK(INT_GPV) | \
-    INT_MASK(INT_SN_ACCESS) | \
-    INT_MASK(INT_IDN_ACCESS) | \
-    INT_MASK(INT_UDN_ACCESS) | \
-    INT_MASK(INT_SWINT_3) | \
-    INT_MASK(INT_SWINT_2) | \
-    INT_MASK(INT_SWINT_1) | \
-    INT_MASK(INT_SWINT_0) | \
-    INT_MASK(INT_UNALIGN_DATA) | \
-    INT_MASK(INT_DTLB_MISS) | \
-    INT_MASK(INT_DTLB_ACCESS) | \
-    INT_MASK(INT_BOOT_ACCESS) | \
-    INT_MASK(INT_WORLD_ACCESS) | \
-    INT_MASK(INT_I_ASID) | \
-    INT_MASK(INT_D_ASID) | \
-    INT_MASK(INT_DMA_ASID) | \
-    INT_MASK(INT_SNI_ASID) | \
-    INT_MASK(INT_DMA_CPL) | \
-    INT_MASK(INT_SN_CPL) | \
-    INT_MASK(INT_DOUBLE_FAULT) | \
-    INT_MASK(INT_SN_STATIC_ACCESS) | \
+    (1ULL << INT_ITLB_MISS) | \
+    (1ULL << INT_ILL) | \
+    (1ULL << INT_GPV) | \
+    (1ULL << INT_SN_ACCESS) | \
+    (1ULL << INT_IDN_ACCESS) | \
+    (1ULL << INT_UDN_ACCESS) | \
+    (1ULL << INT_SWINT_3) | \
+    (1ULL << INT_SWINT_2) | \
+    (1ULL << INT_SWINT_1) | \
+    (1ULL << INT_SWINT_0) | \
+    (1ULL << INT_UNALIGN_DATA) | \
+    (1ULL << INT_DTLB_MISS) | \
+    (1ULL << INT_DTLB_ACCESS) | \
+    (1ULL << INT_BOOT_ACCESS) | \
+    (1ULL << INT_WORLD_ACCESS) | \
+    (1ULL << INT_I_ASID) | \
+    (1ULL << INT_D_ASID) | \
+    (1ULL << INT_DMA_ASID) | \
+    (1ULL << INT_SNI_ASID) | \
+    (1ULL << INT_DMA_CPL) | \
+    (1ULL << INT_SN_CPL) | \
+    (1ULL << INT_DOUBLE_FAULT) | \
+    (1ULL << INT_SN_STATIC_ACCESS) | \
     0)
 #define SYNC_INTERRUPTS ( \
-    INT_MASK(INT_ITLB_MISS) | \
-    INT_MASK(INT_ILL) | \
-    INT_MASK(INT_GPV) | \
-    INT_MASK(INT_SN_ACCESS) | \
-    INT_MASK(INT_IDN_ACCESS) | \
-    INT_MASK(INT_UDN_ACCESS) | \
-    INT_MASK(INT_IDN_REFILL) | \
-    INT_MASK(INT_UDN_REFILL) | \
-    INT_MASK(INT_IDN_COMPLETE) | \
-    INT_MASK(INT_UDN_COMPLETE) | \
-    INT_MASK(INT_SWINT_3) | \
-    INT_MASK(INT_SWINT_2) | \
-    INT_MASK(INT_SWINT_1) | \
-    INT_MASK(INT_SWINT_0) | \
-    INT_MASK(INT_UNALIGN_DATA) | \
-    INT_MASK(INT_DTLB_MISS) | \
-    INT_MASK(INT_DTLB_ACCESS) | \
-    INT_MASK(INT_SN_STATIC_ACCESS) | \
+    (1ULL << INT_ITLB_MISS) | \
+    (1ULL << INT_ILL) | \
+    (1ULL << INT_GPV) | \
+    (1ULL << INT_SN_ACCESS) | \
+    (1ULL << INT_IDN_ACCESS) | \
+    (1ULL << INT_UDN_ACCESS) | \
+    (1ULL << INT_IDN_REFILL) | \
+    (1ULL << INT_UDN_REFILL) | \
+    (1ULL << INT_IDN_COMPLETE) | \
+    (1ULL << INT_UDN_COMPLETE) | \
+    (1ULL << INT_SWINT_3) | \
+    (1ULL << INT_SWINT_2) | \
+    (1ULL << INT_SWINT_1) | \
+    (1ULL << INT_SWINT_0) | \
+    (1ULL << INT_UNALIGN_DATA) | \
+    (1ULL << INT_DTLB_MISS) | \
+    (1ULL << INT_DTLB_ACCESS) | \
+    (1ULL << INT_SN_STATIC_ACCESS) | \
     0)
 #define NON_SYNC_INTERRUPTS ( \
-    INT_MASK(INT_MEM_ERROR) | \
-    INT_MASK(INT_DMATLB_MISS) | \
-    INT_MASK(INT_DMATLB_ACCESS) | \
-    INT_MASK(INT_SNITLB_MISS) | \
-    INT_MASK(INT_SN_NOTIFY) | \
-    INT_MASK(INT_SN_FIREWALL) | \
-    INT_MASK(INT_IDN_FIREWALL) | \
-    INT_MASK(INT_UDN_FIREWALL) | \
-    INT_MASK(INT_TILE_TIMER) | \
-    INT_MASK(INT_IDN_TIMER) | \
-    INT_MASK(INT_UDN_TIMER) | \
-    INT_MASK(INT_DMA_NOTIFY) | \
-    INT_MASK(INT_IDN_CA) | \
-    INT_MASK(INT_UDN_CA) | \
-    INT_MASK(INT_IDN_AVAIL) | \
-    INT_MASK(INT_UDN_AVAIL) | \
-    INT_MASK(INT_PERF_COUNT) | \
-    INT_MASK(INT_INTCTRL_3) | \
-    INT_MASK(INT_INTCTRL_2) | \
-    INT_MASK(INT_INTCTRL_1) | \
-    INT_MASK(INT_INTCTRL_0) | \
-    INT_MASK(INT_BOOT_ACCESS) | \
-    INT_MASK(INT_WORLD_ACCESS) | \
-    INT_MASK(INT_I_ASID) | \
-    INT_MASK(INT_D_ASID) | \
-    INT_MASK(INT_DMA_ASID) | \
-    INT_MASK(INT_SNI_ASID) | \
-    INT_MASK(INT_DMA_CPL) | \
-    INT_MASK(INT_SN_CPL) | \
-    INT_MASK(INT_DOUBLE_FAULT) | \
-    INT_MASK(INT_AUX_PERF_COUNT) | \
+    (1ULL << INT_MEM_ERROR) | \
+    (1ULL << INT_DMATLB_MISS) | \
+    (1ULL << INT_DMATLB_ACCESS) | \
+    (1ULL << INT_SNITLB_MISS) | \
+    (1ULL << INT_SN_NOTIFY) | \
+    (1ULL << INT_SN_FIREWALL) | \
+    (1ULL << INT_IDN_FIREWALL) | \
+    (1ULL << INT_UDN_FIREWALL) | \
+    (1ULL << INT_TILE_TIMER) | \
+    (1ULL << INT_IDN_TIMER) | \
+    (1ULL << INT_UDN_TIMER) | \
+    (1ULL << INT_DMA_NOTIFY) | \
+    (1ULL << INT_IDN_CA) | \
+    (1ULL << INT_UDN_CA) | \
+    (1ULL << INT_IDN_AVAIL) | \
+    (1ULL << INT_UDN_AVAIL) | \
+    (1ULL << INT_PERF_COUNT) | \
+    (1ULL << INT_INTCTRL_3) | \
+    (1ULL << INT_INTCTRL_2) | \
+    (1ULL << INT_INTCTRL_1) | \
+    (1ULL << INT_INTCTRL_0) | \
+    (1ULL << INT_BOOT_ACCESS) | \
+    (1ULL << INT_WORLD_ACCESS) | \
+    (1ULL << INT_I_ASID) | \
+    (1ULL << INT_D_ASID) | \
+    (1ULL << INT_DMA_ASID) | \
+    (1ULL << INT_SNI_ASID) | \
+    (1ULL << INT_DMA_CPL) | \
+    (1ULL << INT_SN_CPL) | \
+    (1ULL << INT_DOUBLE_FAULT) | \
+    (1ULL << INT_AUX_PERF_COUNT) | \
     0)
 #endif /* !__ASSEMBLER__ */
 #endif /* !__ARCH_INTERRUPTS_H__ */
diff --git a/arch/tile/include/uapi/arch/interrupts_64.h b/arch/tile/include/uapi/arch/interrupts_64.h
index 5bb58b2..13c9f91 100644
--- a/arch/tile/include/uapi/arch/interrupts_64.h
+++ b/arch/tile/include/uapi/arch/interrupts_64.h
@@ -15,6 +15,7 @@
 #ifndef __ARCH_INTERRUPTS_H__
 #define __ARCH_INTERRUPTS_H__
 
+#ifndef __KERNEL__
 /** Mask for an interrupt. */
 #ifdef __ASSEMBLER__
 /* Note: must handle breaking interrupts into high and low words manually. */
@@ -22,6 +23,7 @@
 #else
 #define INT_MASK(intno) (1ULL << (intno))
 #endif
+#endif
 
 
 /** Where a given interrupt executes */
@@ -85,192 +87,192 @@
 
 #ifndef __ASSEMBLER__
 #define QUEUED_INTERRUPTS ( \
-    INT_MASK(INT_MEM_ERROR) | \
-    INT_MASK(INT_IDN_COMPLETE) | \
-    INT_MASK(INT_UDN_COMPLETE) | \
-    INT_MASK(INT_IDN_FIREWALL) | \
-    INT_MASK(INT_UDN_FIREWALL) | \
-    INT_MASK(INT_TILE_TIMER) | \
-    INT_MASK(INT_AUX_TILE_TIMER) | \
-    INT_MASK(INT_IDN_TIMER) | \
-    INT_MASK(INT_UDN_TIMER) | \
-    INT_MASK(INT_IDN_AVAIL) | \
-    INT_MASK(INT_UDN_AVAIL) | \
-    INT_MASK(INT_IPI_3) | \
-    INT_MASK(INT_IPI_2) | \
-    INT_MASK(INT_IPI_1) | \
-    INT_MASK(INT_IPI_0) | \
-    INT_MASK(INT_PERF_COUNT) | \
-    INT_MASK(INT_AUX_PERF_COUNT) | \
-    INT_MASK(INT_INTCTRL_3) | \
-    INT_MASK(INT_INTCTRL_2) | \
-    INT_MASK(INT_INTCTRL_1) | \
-    INT_MASK(INT_INTCTRL_0) | \
-    INT_MASK(INT_BOOT_ACCESS) | \
-    INT_MASK(INT_WORLD_ACCESS) | \
-    INT_MASK(INT_I_ASID) | \
-    INT_MASK(INT_D_ASID) | \
-    INT_MASK(INT_DOUBLE_FAULT) | \
+    (1ULL << INT_MEM_ERROR) | \
+    (1ULL << INT_IDN_COMPLETE) | \
+    (1ULL << INT_UDN_COMPLETE) | \
+    (1ULL << INT_IDN_FIREWALL) | \
+    (1ULL << INT_UDN_FIREWALL) | \
+    (1ULL << INT_TILE_TIMER) | \
+    (1ULL << INT_AUX_TILE_TIMER) | \
+    (1ULL << INT_IDN_TIMER) | \
+    (1ULL << INT_UDN_TIMER) | \
+    (1ULL << INT_IDN_AVAIL) | \
+    (1ULL << INT_UDN_AVAIL) | \
+    (1ULL << INT_IPI_3) | \
+    (1ULL << INT_IPI_2) | \
+    (1ULL << INT_IPI_1) | \
+    (1ULL << INT_IPI_0) | \
+    (1ULL << INT_PERF_COUNT) | \
+    (1ULL << INT_AUX_PERF_COUNT) | \
+    (1ULL << INT_INTCTRL_3) | \
+    (1ULL << INT_INTCTRL_2) | \
+    (1ULL << INT_INTCTRL_1) | \
+    (1ULL << INT_INTCTRL_0) | \
+    (1ULL << INT_BOOT_ACCESS) | \
+    (1ULL << INT_WORLD_ACCESS) | \
+    (1ULL << INT_I_ASID) | \
+    (1ULL << INT_D_ASID) | \
+    (1ULL << INT_DOUBLE_FAULT) | \
     0)
 #define NONQUEUED_INTERRUPTS ( \
-    INT_MASK(INT_SINGLE_STEP_3) | \
-    INT_MASK(INT_SINGLE_STEP_2) | \
-    INT_MASK(INT_SINGLE_STEP_1) | \
-    INT_MASK(INT_SINGLE_STEP_0) | \
-    INT_MASK(INT_ITLB_MISS) | \
-    INT_MASK(INT_ILL) | \
-    INT_MASK(INT_GPV) | \
-    INT_MASK(INT_IDN_ACCESS) | \
-    INT_MASK(INT_UDN_ACCESS) | \
-    INT_MASK(INT_SWINT_3) | \
-    INT_MASK(INT_SWINT_2) | \
-    INT_MASK(INT_SWINT_1) | \
-    INT_MASK(INT_SWINT_0) | \
-    INT_MASK(INT_ILL_TRANS) | \
-    INT_MASK(INT_UNALIGN_DATA) | \
-    INT_MASK(INT_DTLB_MISS) | \
-    INT_MASK(INT_DTLB_ACCESS) | \
+    (1ULL << INT_SINGLE_STEP_3) | \
+    (1ULL << INT_SINGLE_STEP_2) | \
+    (1ULL << INT_SINGLE_STEP_1) | \
+    (1ULL << INT_SINGLE_STEP_0) | \
+    (1ULL << INT_ITLB_MISS) | \
+    (1ULL << INT_ILL) | \
+    (1ULL << INT_GPV) | \
+    (1ULL << INT_IDN_ACCESS) | \
+    (1ULL << INT_UDN_ACCESS) | \
+    (1ULL << INT_SWINT_3) | \
+    (1ULL << INT_SWINT_2) | \
+    (1ULL << INT_SWINT_1) | \
+    (1ULL << INT_SWINT_0) | \
+    (1ULL << INT_ILL_TRANS) | \
+    (1ULL << INT_UNALIGN_DATA) | \
+    (1ULL << INT_DTLB_MISS) | \
+    (1ULL << INT_DTLB_ACCESS) | \
     0)
 #define CRITICAL_MASKED_INTERRUPTS ( \
-    INT_MASK(INT_MEM_ERROR) | \
-    INT_MASK(INT_SINGLE_STEP_3) | \
-    INT_MASK(INT_SINGLE_STEP_2) | \
-    INT_MASK(INT_SINGLE_STEP_1) | \
-    INT_MASK(INT_SINGLE_STEP_0) | \
-    INT_MASK(INT_IDN_COMPLETE) | \
-    INT_MASK(INT_UDN_COMPLETE) | \
-    INT_MASK(INT_IDN_FIREWALL) | \
-    INT_MASK(INT_UDN_FIREWALL) | \
-    INT_MASK(INT_TILE_TIMER) | \
-    INT_MASK(INT_AUX_TILE_TIMER) | \
-    INT_MASK(INT_IDN_TIMER) | \
-    INT_MASK(INT_UDN_TIMER) | \
-    INT_MASK(INT_IDN_AVAIL) | \
-    INT_MASK(INT_UDN_AVAIL) | \
-    INT_MASK(INT_IPI_3) | \
-    INT_MASK(INT_IPI_2) | \
-    INT_MASK(INT_IPI_1) | \
-    INT_MASK(INT_IPI_0) | \
-    INT_MASK(INT_PERF_COUNT) | \
-    INT_MASK(INT_AUX_PERF_COUNT) | \
-    INT_MASK(INT_INTCTRL_3) | \
-    INT_MASK(INT_INTCTRL_2) | \
-    INT_MASK(INT_INTCTRL_1) | \
-    INT_MASK(INT_INTCTRL_0) | \
+    (1ULL << INT_MEM_ERROR) | \
+    (1ULL << INT_SINGLE_STEP_3) | \
+    (1ULL << INT_SINGLE_STEP_2) | \
+    (1ULL << INT_SINGLE_STEP_1) | \
+    (1ULL << INT_SINGLE_STEP_0) | \
+    (1ULL << INT_IDN_COMPLETE) | \
+    (1ULL << INT_UDN_COMPLETE) | \
+    (1ULL << INT_IDN_FIREWALL) | \
+    (1ULL << INT_UDN_FIREWALL) | \
+    (1ULL << INT_TILE_TIMER) | \
+    (1ULL << INT_AUX_TILE_TIMER) | \
+    (1ULL << INT_IDN_TIMER) | \
+    (1ULL << INT_UDN_TIMER) | \
+    (1ULL << INT_IDN_AVAIL) | \
+    (1ULL << INT_UDN_AVAIL) | \
+    (1ULL << INT_IPI_3) | \
+    (1ULL << INT_IPI_2) | \
+    (1ULL << INT_IPI_1) | \
+    (1ULL << INT_IPI_0) | \
+    (1ULL << INT_PERF_COUNT) | \
+    (1ULL << INT_AUX_PERF_COUNT) | \
+    (1ULL << INT_INTCTRL_3) | \
+    (1ULL << INT_INTCTRL_2) | \
+    (1ULL << INT_INTCTRL_1) | \
+    (1ULL << INT_INTCTRL_0) | \
     0)
 #define CRITICAL_UNMASKED_INTERRUPTS ( \
-    INT_MASK(INT_ITLB_MISS) | \
-    INT_MASK(INT_ILL) | \
-    INT_MASK(INT_GPV) | \
-    INT_MASK(INT_IDN_ACCESS) | \
-    INT_MASK(INT_UDN_ACCESS) | \
-    INT_MASK(INT_SWINT_3) | \
-    INT_MASK(INT_SWINT_2) | \
-    INT_MASK(INT_SWINT_1) | \
-    INT_MASK(INT_SWINT_0) | \
-    INT_MASK(INT_ILL_TRANS) | \
-    INT_MASK(INT_UNALIGN_DATA) | \
-    INT_MASK(INT_DTLB_MISS) | \
-    INT_MASK(INT_DTLB_ACCESS) | \
-    INT_MASK(INT_BOOT_ACCESS) | \
-    INT_MASK(INT_WORLD_ACCESS) | \
-    INT_MASK(INT_I_ASID) | \
-    INT_MASK(INT_D_ASID) | \
-    INT_MASK(INT_DOUBLE_FAULT) | \
+    (1ULL << INT_ITLB_MISS) | \
+    (1ULL << INT_ILL) | \
+    (1ULL << INT_GPV) | \
+    (1ULL << INT_IDN_ACCESS) | \
+    (1ULL << INT_UDN_ACCESS) | \
+    (1ULL << INT_SWINT_3) | \
+    (1ULL << INT_SWINT_2) | \
+    (1ULL << INT_SWINT_1) | \
+    (1ULL << INT_SWINT_0) | \
+    (1ULL << INT_ILL_TRANS) | \
+    (1ULL << INT_UNALIGN_DATA) | \
+    (1ULL << INT_DTLB_MISS) | \
+    (1ULL << INT_DTLB_ACCESS) | \
+    (1ULL << INT_BOOT_ACCESS) | \
+    (1ULL << INT_WORLD_ACCESS) | \
+    (1ULL << INT_I_ASID) | \
+    (1ULL << INT_D_ASID) | \
+    (1ULL << INT_DOUBLE_FAULT) | \
     0)
 #define MASKABLE_INTERRUPTS ( \
-    INT_MASK(INT_MEM_ERROR) | \
-    INT_MASK(INT_SINGLE_STEP_3) | \
-    INT_MASK(INT_SINGLE_STEP_2) | \
-    INT_MASK(INT_SINGLE_STEP_1) | \
-    INT_MASK(INT_SINGLE_STEP_0) | \
-    INT_MASK(INT_IDN_COMPLETE) | \
-    INT_MASK(INT_UDN_COMPLETE) | \
-    INT_MASK(INT_IDN_FIREWALL) | \
-    INT_MASK(INT_UDN_FIREWALL) | \
-    INT_MASK(INT_TILE_TIMER) | \
-    INT_MASK(INT_AUX_TILE_TIMER) | \
-    INT_MASK(INT_IDN_TIMER) | \
-    INT_MASK(INT_UDN_TIMER) | \
-    INT_MASK(INT_IDN_AVAIL) | \
-    INT_MASK(INT_UDN_AVAIL) | \
-    INT_MASK(INT_IPI_3) | \
-    INT_MASK(INT_IPI_2) | \
-    INT_MASK(INT_IPI_1) | \
-    INT_MASK(INT_IPI_0) | \
-    INT_MASK(INT_PERF_COUNT) | \
-    INT_MASK(INT_AUX_PERF_COUNT) | \
-    INT_MASK(INT_INTCTRL_3) | \
-    INT_MASK(INT_INTCTRL_2) | \
-    INT_MASK(INT_INTCTRL_1) | \
-    INT_MASK(INT_INTCTRL_0) | \
+    (1ULL << INT_MEM_ERROR) | \
+    (1ULL << INT_SINGLE_STEP_3) | \
+    (1ULL << INT_SINGLE_STEP_2) | \
+    (1ULL << INT_SINGLE_STEP_1) | \
+    (1ULL << INT_SINGLE_STEP_0) | \
+    (1ULL << INT_IDN_COMPLETE) | \
+    (1ULL << INT_UDN_COMPLETE) | \
+    (1ULL << INT_IDN_FIREWALL) | \
+    (1ULL << INT_UDN_FIREWALL) | \
+    (1ULL << INT_TILE_TIMER) | \
+    (1ULL << INT_AUX_TILE_TIMER) | \
+    (1ULL << INT_IDN_TIMER) | \
+    (1ULL << INT_UDN_TIMER) | \
+    (1ULL << INT_IDN_AVAIL) | \
+    (1ULL << INT_UDN_AVAIL) | \
+    (1ULL << INT_IPI_3) | \
+    (1ULL << INT_IPI_2) | \
+    (1ULL << INT_IPI_1) | \
+    (1ULL << INT_IPI_0) | \
+    (1ULL << INT_PERF_COUNT) | \
+    (1ULL << INT_AUX_PERF_COUNT) | \
+    (1ULL << INT_INTCTRL_3) | \
+    (1ULL << INT_INTCTRL_2) | \
+    (1ULL << INT_INTCTRL_1) | \
+    (1ULL << INT_INTCTRL_0) | \
     0)
 #define UNMASKABLE_INTERRUPTS ( \
-    INT_MASK(INT_ITLB_MISS) | \
-    INT_MASK(INT_ILL) | \
-    INT_MASK(INT_GPV) | \
-    INT_MASK(INT_IDN_ACCESS) | \
-    INT_MASK(INT_UDN_ACCESS) | \
-    INT_MASK(INT_SWINT_3) | \
-    INT_MASK(INT_SWINT_2) | \
-    INT_MASK(INT_SWINT_1) | \
-    INT_MASK(INT_SWINT_0) | \
-    INT_MASK(INT_ILL_TRANS) | \
-    INT_MASK(INT_UNALIGN_DATA) | \
-    INT_MASK(INT_DTLB_MISS) | \
-    INT_MASK(INT_DTLB_ACCESS) | \
-    INT_MASK(INT_BOOT_ACCESS) | \
-    INT_MASK(INT_WORLD_ACCESS) | \
-    INT_MASK(INT_I_ASID) | \
-    INT_MASK(INT_D_ASID) | \
-    INT_MASK(INT_DOUBLE_FAULT) | \
+    (1ULL << INT_ITLB_MISS) | \
+    (1ULL << INT_ILL) | \
+    (1ULL << INT_GPV) | \
+    (1ULL << INT_IDN_ACCESS) | \
+    (1ULL << INT_UDN_ACCESS) | \
+    (1ULL << INT_SWINT_3) | \
+    (1ULL << INT_SWINT_2) | \
+    (1ULL << INT_SWINT_1) | \
+    (1ULL << INT_SWINT_0) | \
+    (1ULL << INT_ILL_TRANS) | \
+    (1ULL << INT_UNALIGN_DATA) | \
+    (1ULL << INT_DTLB_MISS) | \
+    (1ULL << INT_DTLB_ACCESS) | \
+    (1ULL << INT_BOOT_ACCESS) | \
+    (1ULL << INT_WORLD_ACCESS) | \
+    (1ULL << INT_I_ASID) | \
+    (1ULL << INT_D_ASID) | \
+    (1ULL << INT_DOUBLE_FAULT) | \
     0)
 #define SYNC_INTERRUPTS ( \
-    INT_MASK(INT_SINGLE_STEP_3) | \
-    INT_MASK(INT_SINGLE_STEP_2) | \
-    INT_MASK(INT_SINGLE_STEP_1) | \
-    INT_MASK(INT_SINGLE_STEP_0) | \
-    INT_MASK(INT_IDN_COMPLETE) | \
-    INT_MASK(INT_UDN_COMPLETE) | \
-    INT_MASK(INT_ITLB_MISS) | \
-    INT_MASK(INT_ILL) | \
-    INT_MASK(INT_GPV) | \
-    INT_MASK(INT_IDN_ACCESS) | \
-    INT_MASK(INT_UDN_ACCESS) | \
-    INT_MASK(INT_SWINT_3) | \
-    INT_MASK(INT_SWINT_2) | \
-    INT_MASK(INT_SWINT_1) | \
-    INT_MASK(INT_SWINT_0) | \
-    INT_MASK(INT_ILL_TRANS) | \
-    INT_MASK(INT_UNALIGN_DATA) | \
-    INT_MASK(INT_DTLB_MISS) | \
-    INT_MASK(INT_DTLB_ACCESS) | \
+    (1ULL << INT_SINGLE_STEP_3) | \
+    (1ULL << INT_SINGLE_STEP_2) | \
+    (1ULL << INT_SINGLE_STEP_1) | \
+    (1ULL << INT_SINGLE_STEP_0) | \
+    (1ULL << INT_IDN_COMPLETE) | \
+    (1ULL << INT_UDN_COMPLETE) | \
+    (1ULL << INT_ITLB_MISS) | \
+    (1ULL << INT_ILL) | \
+    (1ULL << INT_GPV) | \
+    (1ULL << INT_IDN_ACCESS) | \
+    (1ULL << INT_UDN_ACCESS) | \
+    (1ULL << INT_SWINT_3) | \
+    (1ULL << INT_SWINT_2) | \
+    (1ULL << INT_SWINT_1) | \
+    (1ULL << INT_SWINT_0) | \
+    (1ULL << INT_ILL_TRANS) | \
+    (1ULL << INT_UNALIGN_DATA) | \
+    (1ULL << INT_DTLB_MISS) | \
+    (1ULL << INT_DTLB_ACCESS) | \
     0)
 #define NON_SYNC_INTERRUPTS ( \
-    INT_MASK(INT_MEM_ERROR) | \
-    INT_MASK(INT_IDN_FIREWALL) | \
-    INT_MASK(INT_UDN_FIREWALL) | \
-    INT_MASK(INT_TILE_TIMER) | \
-    INT_MASK(INT_AUX_TILE_TIMER) | \
-    INT_MASK(INT_IDN_TIMER) | \
-    INT_MASK(INT_UDN_TIMER) | \
-    INT_MASK(INT_IDN_AVAIL) | \
-    INT_MASK(INT_UDN_AVAIL) | \
-    INT_MASK(INT_IPI_3) | \
-    INT_MASK(INT_IPI_2) | \
-    INT_MASK(INT_IPI_1) | \
-    INT_MASK(INT_IPI_0) | \
-    INT_MASK(INT_PERF_COUNT) | \
-    INT_MASK(INT_AUX_PERF_COUNT) | \
-    INT_MASK(INT_INTCTRL_3) | \
-    INT_MASK(INT_INTCTRL_2) | \
-    INT_MASK(INT_INTCTRL_1) | \
-    INT_MASK(INT_INTCTRL_0) | \
-    INT_MASK(INT_BOOT_ACCESS) | \
-    INT_MASK(INT_WORLD_ACCESS) | \
-    INT_MASK(INT_I_ASID) | \
-    INT_MASK(INT_D_ASID) | \
-    INT_MASK(INT_DOUBLE_FAULT) | \
+    (1ULL << INT_MEM_ERROR) | \
+    (1ULL << INT_IDN_FIREWALL) | \
+    (1ULL << INT_UDN_FIREWALL) | \
+    (1ULL << INT_TILE_TIMER) | \
+    (1ULL << INT_AUX_TILE_TIMER) | \
+    (1ULL << INT_IDN_TIMER) | \
+    (1ULL << INT_UDN_TIMER) | \
+    (1ULL << INT_IDN_AVAIL) | \
+    (1ULL << INT_UDN_AVAIL) | \
+    (1ULL << INT_IPI_3) | \
+    (1ULL << INT_IPI_2) | \
+    (1ULL << INT_IPI_1) | \
+    (1ULL << INT_IPI_0) | \
+    (1ULL << INT_PERF_COUNT) | \
+    (1ULL << INT_AUX_PERF_COUNT) | \
+    (1ULL << INT_INTCTRL_3) | \
+    (1ULL << INT_INTCTRL_2) | \
+    (1ULL << INT_INTCTRL_1) | \
+    (1ULL << INT_INTCTRL_0) | \
+    (1ULL << INT_BOOT_ACCESS) | \
+    (1ULL << INT_WORLD_ACCESS) | \
+    (1ULL << INT_I_ASID) | \
+    (1ULL << INT_D_ASID) | \
+    (1ULL << INT_DOUBLE_FAULT) | \
     0)
 #endif /* !__ASSEMBLER__ */
 #endif /* !__ARCH_INTERRUPTS_H__ */
diff --git a/arch/tile/kernel/intvec_64.S b/arch/tile/kernel/intvec_64.S
index 54bc9a6..4ea0809 100644
--- a/arch/tile/kernel/intvec_64.S
+++ b/arch/tile/kernel/intvec_64.S
@@ -1035,7 +1035,9 @@
 	/* Ensure that the syscall number is within the legal range. */
 	{
 	 moveli r20, hw2(sys_call_table)
+#ifdef CONFIG_COMPAT
 	 blbs   r30, .Lcompat_syscall
+#endif
 	}
 	{
 	 cmpltu r21, TREG_SYSCALL_NR_NAME, r21
@@ -1093,6 +1095,7 @@
 	 j      .Lresume_userspace   /* jump into middle of interrupt_return */
 	}
 
+#ifdef CONFIG_COMPAT
 .Lcompat_syscall:
 	/*
 	 * Load the base of the compat syscall table in r20, and
@@ -1117,6 +1120,7 @@
 	{ move r15, r4; addxi r4, r4, 0 }
 	{ move r16, r5; addxi r5, r5, 0 }
 	j .Lload_syscall_pointer
+#endif
 
 .Linvalid_syscall:
 	/* Report an invalid syscall back to the user program */
diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c
index 0e5661e..caf93ae 100644
--- a/arch/tile/kernel/process.c
+++ b/arch/tile/kernel/process.c
@@ -159,7 +159,7 @@
 int copy_thread(unsigned long clone_flags, unsigned long sp,
 		unsigned long arg, struct task_struct *p)
 {
-	struct pt_regs *childregs = task_pt_regs(p), *regs = current_pt_regs();
+	struct pt_regs *childregs = task_pt_regs(p);
 	unsigned long ksp;
 	unsigned long *callee_regs;
 
diff --git a/arch/tile/kernel/reboot.c b/arch/tile/kernel/reboot.c
index baa3d90..d1b5c91 100644
--- a/arch/tile/kernel/reboot.c
+++ b/arch/tile/kernel/reboot.c
@@ -16,6 +16,7 @@
 #include <linux/reboot.h>
 #include <linux/smp.h>
 #include <linux/pm.h>
+#include <linux/export.h>
 #include <asm/page.h>
 #include <asm/setup.h>
 #include <hv/hypervisor.h>
@@ -49,3 +50,4 @@
 
 /* No interesting distinction to be made here. */
 void (*pm_power_off)(void) = NULL;
+EXPORT_SYMBOL(pm_power_off);
diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c
index 6a649a4..d1e15f7 100644
--- a/arch/tile/kernel/setup.c
+++ b/arch/tile/kernel/setup.c
@@ -31,6 +31,7 @@
 #include <linux/timex.h>
 #include <linux/hugetlb.h>
 #include <linux/start_kernel.h>
+#include <linux/screen_info.h>
 #include <asm/setup.h>
 #include <asm/sections.h>
 #include <asm/cacheflush.h>
@@ -49,6 +50,10 @@
 /* Chip information */
 char chip_model[64] __write_once;
 
+#ifdef CONFIG_VT
+struct screen_info screen_info;
+#endif
+
 struct pglist_data node_data[MAX_NUMNODES] __read_mostly;
 EXPORT_SYMBOL(node_data);
 
diff --git a/arch/tile/kernel/stack.c b/arch/tile/kernel/stack.c
index b2f44c2..ed258b8 100644
--- a/arch/tile/kernel/stack.c
+++ b/arch/tile/kernel/stack.c
@@ -112,7 +112,7 @@
 		       p->pc, p->sp, p->ex1);
 		p = NULL;
 	}
-	if (!kbt->profile || (INT_MASK(p->faultnum) & QUEUED_INTERRUPTS) == 0)
+	if (!kbt->profile || ((1ULL << p->faultnum) & QUEUED_INTERRUPTS) == 0)
 		return p;
 	return NULL;
 }
@@ -484,6 +484,7 @@
 {
 	save_stack_trace_tsk(NULL, trace);
 }
+EXPORT_SYMBOL_GPL(save_stack_trace);
 
 #endif
 
diff --git a/arch/tile/lib/cacheflush.c b/arch/tile/lib/cacheflush.c
index db4fb89..8f8ad81 100644
--- a/arch/tile/lib/cacheflush.c
+++ b/arch/tile/lib/cacheflush.c
@@ -12,6 +12,7 @@
  *   more details.
  */
 
+#include <linux/export.h>
 #include <asm/page.h>
 #include <asm/cacheflush.h>
 #include <arch/icache.h>
@@ -165,3 +166,4 @@
 	__insn_mtspr(SPR_DSTREAM_PF, old_dstream_pf);
 #endif
 }
+EXPORT_SYMBOL_GPL(finv_buffer_remote);
diff --git a/arch/tile/lib/cpumask.c b/arch/tile/lib/cpumask.c
index fdc4036..75947ed 100644
--- a/arch/tile/lib/cpumask.c
+++ b/arch/tile/lib/cpumask.c
@@ -16,6 +16,7 @@
 #include <linux/ctype.h>
 #include <linux/errno.h>
 #include <linux/smp.h>
+#include <linux/export.h>
 
 /*
  * Allow cropping out bits beyond the end of the array.
@@ -50,3 +51,4 @@
 	} while (*bp != '\0' && *bp != '\n');
 	return 0;
 }
+EXPORT_SYMBOL(bitmap_parselist_crop);
diff --git a/arch/tile/lib/exports.c b/arch/tile/lib/exports.c
index dd5f0a3..4385cb6 100644
--- a/arch/tile/lib/exports.c
+++ b/arch/tile/lib/exports.c
@@ -55,6 +55,8 @@
 EXPORT_SYMBOL(hv_dev_close);
 EXPORT_SYMBOL(hv_sysconf);
 EXPORT_SYMBOL(hv_confstr);
+EXPORT_SYMBOL(hv_get_rtc);
+EXPORT_SYMBOL(hv_set_rtc);
 
 /* libgcc.a */
 uint32_t __udivsi3(uint32_t dividend, uint32_t divisor);
diff --git a/arch/tile/mm/homecache.c b/arch/tile/mm/homecache.c
index 5f7868d..1ae9119 100644
--- a/arch/tile/mm/homecache.c
+++ b/arch/tile/mm/homecache.c
@@ -408,6 +408,7 @@
 		__set_pte(ptep, pte_set_home(pteval, home));
 	}
 }
+EXPORT_SYMBOL(homecache_change_page_home);
 
 struct page *homecache_alloc_pages(gfp_t gfp_mask,
 				   unsigned int order, int home)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 79795af..a257049 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -28,7 +28,6 @@
 	select HAVE_OPROFILE
 	select HAVE_PCSPKR_PLATFORM
 	select HAVE_PERF_EVENTS
-	select HAVE_IRQ_WORK
 	select HAVE_IOREMAP_PROT
 	select HAVE_KPROBES
 	select HAVE_MEMBLOCK
@@ -40,10 +39,12 @@
 	select HAVE_DMA_CONTIGUOUS if !SWIOTLB
 	select HAVE_KRETPROBES
 	select HAVE_OPTPROBES
+	select HAVE_KPROBES_ON_FTRACE
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FENTRY if X86_64
 	select HAVE_C_RECORDMCOUNT
 	select HAVE_DYNAMIC_FTRACE
+	select HAVE_DYNAMIC_FTRACE_WITH_REGS
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_GRAPH_FP_TEST
@@ -2138,6 +2139,7 @@
 config OLPC_XO1_SCI
 	bool "OLPC XO-1 SCI extras"
 	depends on OLPC && OLPC_XO1_PM
+	depends on INPUT=y
 	select POWER_SUPPLY
 	select GPIO_CS5535
 	select MFD_CORE
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index ccce0ed..379814b 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -71,7 +71,7 @@
 $(obj)/bzImage: asflags-y  := $(SVGA_MODE)
 
 quiet_cmd_image = BUILD   $@
-cmd_image = $(obj)/tools/build $(obj)/setup.bin $(obj)/vmlinux.bin > $@
+cmd_image = $(obj)/tools/build $(obj)/setup.bin $(obj)/vmlinux.bin $(obj)/zoffset.h > $@
 
 $(obj)/bzImage: $(obj)/setup.bin $(obj)/vmlinux.bin $(obj)/tools/build FORCE
 	$(call if_changed,image)
@@ -92,7 +92,7 @@
 $(obj)/voffset.h: vmlinux FORCE
 	$(call if_changed,voffset)
 
-sed-zoffset := -e 's/^\([0-9a-fA-F]*\) . \(startup_32\|input_data\|_end\|z_.*\)$$/\#define ZO_\2 0x\1/p'
+sed-zoffset := -e 's/^\([0-9a-fA-F]*\) . \(startup_32\|startup_64\|efi_pe_entry\|efi_stub_entry\|input_data\|_end\|z_.*\)$$/\#define ZO_\2 0x\1/p'
 
 quiet_cmd_zoffset = ZOFFSET $@
       cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 18e329c..f8fa411 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -256,10 +256,10 @@
 	int i;
 	struct setup_data *data;
 
-	data = (struct setup_data *)params->hdr.setup_data;
+	data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
 
 	while (data && data->next)
-		data = (struct setup_data *)data->next;
+		data = (struct setup_data *)(unsigned long)data->next;
 
 	status = efi_call_phys5(sys_table->boottime->locate_handle,
 				EFI_LOCATE_BY_PROTOCOL, &pci_proto,
@@ -295,16 +295,18 @@
 		if (!pci)
 			continue;
 
+#ifdef CONFIG_X86_64
 		status = efi_call_phys4(pci->attributes, pci,
 					EfiPciIoAttributeOperationGet, 0,
 					&attributes);
-
+#else
+		status = efi_call_phys5(pci->attributes, pci,
+					EfiPciIoAttributeOperationGet, 0, 0,
+					&attributes);
+#endif
 		if (status != EFI_SUCCESS)
 			continue;
 
-		if (!(attributes & EFI_PCI_IO_ATTRIBUTE_EMBEDDED_ROM))
-			continue;
-
 		if (!pci->romimage || !pci->romsize)
 			continue;
 
@@ -345,9 +347,9 @@
 		memcpy(rom->romdata, pci->romimage, pci->romsize);
 
 		if (data)
-			data->next = (uint64_t)rom;
+			data->next = (unsigned long)rom;
 		else
-			params->hdr.setup_data = (uint64_t)rom;
+			params->hdr.setup_data = (unsigned long)rom;
 
 		data = (struct setup_data *)rom;
 
@@ -432,10 +434,9 @@
 			 * Once we've found a GOP supporting ConOut,
 			 * don't bother looking any further.
 			 */
+			first_gop = gop;
 			if (conout_found)
 				break;
-
-			first_gop = gop;
 		}
 	}
 
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index aa4aaf1..1e3184f 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -35,11 +35,11 @@
 #ifdef CONFIG_EFI_STUB
 	jmp	preferred_addr
 
-	.balign	0x10
 	/*
 	 * We don't need the return address, so set up the stack so
-	 * efi_main() can find its arugments.
+	 * efi_main() can find its arguments.
 	 */
+ENTRY(efi_pe_entry)
 	add	$0x4, %esp
 
 	call	make_boot_params
@@ -50,8 +50,10 @@
 	pushl	%eax
 	pushl	%esi
 	pushl	%ecx
+	sub	$0x4, %esp
 
-	.org 0x30,0x90
+ENTRY(efi_stub_entry)
+	add	$0x4, %esp
 	call	efi_main
 	cmpl	$0, %eax
 	movl	%eax, %esi
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 2c4b171..f5d1aaa 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -201,12 +201,12 @@
 	 */
 #ifdef CONFIG_EFI_STUB
 	/*
-	 * The entry point for the PE/COFF executable is 0x210, so only
-	 * legacy boot loaders will execute this jmp.
+	 * The entry point for the PE/COFF executable is efi_pe_entry, so
+	 * only legacy boot loaders will execute this jmp.
 	 */
 	jmp	preferred_addr
 
-	.org 0x210
+ENTRY(efi_pe_entry)
 	mov	%rcx, %rdi
 	mov	%rdx, %rsi
 	pushq	%rdi
@@ -218,7 +218,7 @@
 	popq	%rsi
 	popq	%rdi
 
-	.org 0x230,0x90
+ENTRY(efi_stub_entry)
 	call	efi_main
 	movq	%rax,%rsi
 	cmpq	$0,%rax
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index 8c132a6..944ce59 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -21,6 +21,7 @@
 #include <asm/e820.h>
 #include <asm/page_types.h>
 #include <asm/setup.h>
+#include <asm/bootparam.h>
 #include "boot.h"
 #include "voffset.h"
 #include "zoffset.h"
@@ -255,6 +256,9 @@
 	# header, from the old boot sector.
 
 	.section ".header", "a"
+	.globl	sentinel
+sentinel:	.byte 0xff, 0xff        /* Used to detect broken loaders */
+
 	.globl	hdr
 hdr:
 setup_sects:	.byte 0			/* Filled in by build.c */
@@ -279,7 +283,7 @@
 	# Part 2 of the header, from the old setup.S
 
 		.ascii	"HdrS"		# header signature
-		.word	0x020b		# header version number (>= 0x0105)
+		.word	0x020c		# header version number (>= 0x0105)
 					# or else old loadlin-1.5 will fail)
 		.globl realmode_swtch
 realmode_swtch:	.word	0, 0		# default_switch, SETUPSEG
@@ -297,13 +301,7 @@
 
 # flags, unused bits must be zero (RFU) bit within loadflags
 loadflags:
-LOADED_HIGH	= 1			# If set, the kernel is loaded high
-CAN_USE_HEAP	= 0x80			# If set, the loader also has set
-					# heap_end_ptr to tell how much
-					# space behind setup.S can be used for
-					# heap purposes.
-					# Only the loader knows what is free
-		.byte	LOADED_HIGH
+		.byte	LOADED_HIGH	# The kernel is to be loaded high
 
 setup_move_size: .word  0x8000		# size to move, when setup is not
 					# loaded at 0x90000. We will move setup
@@ -369,7 +367,23 @@
 relocatable_kernel:    .byte 0
 #endif
 min_alignment:		.byte MIN_KERNEL_ALIGN_LG2	# minimum alignment
-pad3:			.word 0
+
+xloadflags:
+#ifdef CONFIG_X86_64
+# define XLF0 XLF_KERNEL_64			/* 64-bit kernel */
+#else
+# define XLF0 0
+#endif
+#ifdef CONFIG_EFI_STUB
+# ifdef CONFIG_X86_64
+#  define XLF23 XLF_EFI_HANDOVER_64		/* 64-bit EFI handover ok */
+# else
+#  define XLF23 XLF_EFI_HANDOVER_32		/* 32-bit EFI handover ok */
+# endif
+#else
+# define XLF23 0
+#endif
+			.word XLF0 | XLF23
 
 cmdline_size:   .long   COMMAND_LINE_SIZE-1     #length of the command line,
                                                 #added with boot protocol
@@ -397,8 +411,13 @@
 #define INIT_SIZE VO_INIT_SIZE
 #endif
 init_size:		.long INIT_SIZE		# kernel initialization size
-handover_offset:	.long 0x30		# offset to the handover
+handover_offset:
+#ifdef CONFIG_EFI_STUB
+  			.long 0x30		# offset to the handover
 						# protocol entry point
+#else
+			.long 0
+#endif
 
 # End of setup header #####################################################
 
diff --git a/arch/x86/boot/setup.ld b/arch/x86/boot/setup.ld
index 03c0683..96a6c75 100644
--- a/arch/x86/boot/setup.ld
+++ b/arch/x86/boot/setup.ld
@@ -13,7 +13,7 @@
 	.bstext		: { *(.bstext) }
 	.bsdata		: { *(.bsdata) }
 
-	. = 497;
+	. = 495;
 	.header		: { *(.header) }
 	.entrytext	: { *(.entrytext) }
 	.inittext	: { *(.inittext) }
diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c
index 4b8e165..94c5446 100644
--- a/arch/x86/boot/tools/build.c
+++ b/arch/x86/boot/tools/build.c
@@ -52,6 +52,10 @@
 
 #define PECOFF_RELOC_RESERVE 0x20
 
+unsigned long efi_stub_entry;
+unsigned long efi_pe_entry;
+unsigned long startup_64;
+
 /*----------------------------------------------------------------------*/
 
 static const u32 crctab32[] = {
@@ -132,7 +136,7 @@
 
 static void usage(void)
 {
-	die("Usage: build setup system [> image]");
+	die("Usage: build setup system [zoffset.h] [> image]");
 }
 
 #ifdef CONFIG_EFI_STUB
@@ -206,30 +210,54 @@
 	 */
 	put_unaligned_le32(file_sz - 512, &buf[pe_header + 0x1c]);
 
-#ifdef CONFIG_X86_32
 	/*
-	 * Address of entry point.
-	 *
-	 * The EFI stub entry point is +16 bytes from the start of
-	 * the .text section.
+	 * Address of entry point for PE/COFF executable
 	 */
-	put_unaligned_le32(text_start + 16, &buf[pe_header + 0x28]);
-#else
-	/*
-	 * Address of entry point. startup_32 is at the beginning and
-	 * the 64-bit entry point (startup_64) is always 512 bytes
-	 * after. The EFI stub entry point is 16 bytes after that, as
-	 * the first instruction allows legacy loaders to jump over
-	 * the EFI stub initialisation
-	 */
-	put_unaligned_le32(text_start + 528, &buf[pe_header + 0x28]);
-#endif /* CONFIG_X86_32 */
+	put_unaligned_le32(text_start + efi_pe_entry, &buf[pe_header + 0x28]);
 
 	update_pecoff_section_header(".text", text_start, text_sz);
 }
 
 #endif /* CONFIG_EFI_STUB */
 
+
+/*
+ * Parse zoffset.h and find the entry points. We could just #include zoffset.h
+ * but that would mean tools/build would have to be rebuilt every time. It's
+ * not as if parsing it is hard...
+ */
+#define PARSE_ZOFS(p, sym) do { \
+	if (!strncmp(p, "#define ZO_" #sym " ", 11+sizeof(#sym)))	\
+		sym = strtoul(p + 11 + sizeof(#sym), NULL, 16);		\
+} while (0)
+
+static void parse_zoffset(char *fname)
+{
+	FILE *file;
+	char *p;
+	int c;
+
+	file = fopen(fname, "r");
+	if (!file)
+		die("Unable to open `%s': %m", fname);
+	c = fread(buf, 1, sizeof(buf) - 1, file);
+	if (ferror(file))
+		die("read-error on `zoffset.h'");
+	buf[c] = 0;
+
+	p = (char *)buf;
+
+	while (p && *p) {
+		PARSE_ZOFS(p, efi_stub_entry);
+		PARSE_ZOFS(p, efi_pe_entry);
+		PARSE_ZOFS(p, startup_64);
+
+		p = strchr(p, '\n');
+		while (p && (*p == '\r' || *p == '\n'))
+			p++;
+	}
+}
+
 int main(int argc, char ** argv)
 {
 	unsigned int i, sz, setup_sectors;
@@ -241,7 +269,19 @@
 	void *kernel;
 	u32 crc = 0xffffffffUL;
 
-	if (argc != 3)
+	/* Defaults for old kernel */
+#ifdef CONFIG_X86_32
+	efi_pe_entry = 0x10;
+	efi_stub_entry = 0x30;
+#else
+	efi_pe_entry = 0x210;
+	efi_stub_entry = 0x230;
+	startup_64 = 0x200;
+#endif
+
+	if (argc == 4)
+		parse_zoffset(argv[3]);
+	else if (argc != 3)
 		usage();
 
 	/* Copy the setup code */
@@ -299,6 +339,11 @@
 
 #ifdef CONFIG_EFI_STUB
 	update_pecoff_text(setup_sectors * 512, sz + i + ((sys_size * 16) - sz));
+
+#ifdef CONFIG_X86_64 /* Yes, this is really how we defined it :( */
+	efi_stub_entry -= 0x200;
+#endif
+	put_unaligned_le32(efi_stub_entry, &buf[0x264]);
 #endif
 
 	crc = partial_crc32(buf, i, crc);
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 102ff7c..142c4ce 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -207,7 +207,7 @@
 	testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
 	jnz ia32_ret_from_sys_call
 	TRACE_IRQS_ON
-	sti
+	ENABLE_INTERRUPTS(CLBR_NONE)
 	movl %eax,%esi		/* second arg, syscall return value */
 	cmpl $-MAX_ERRNO,%eax	/* is it an error ? */
 	jbe 1f
@@ -217,7 +217,7 @@
 	call __audit_syscall_exit
 	movq RAX-ARGOFFSET(%rsp),%rax	/* reload syscall return value */
 	movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi
-	cli
+	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
 	testl %edi,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
 	jz \exit
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 2d9075e..93fe929 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -167,6 +167,7 @@
 #define X86_FEATURE_TBM		(6*32+21) /* trailing bit manipulations */
 #define X86_FEATURE_TOPOEXT	(6*32+22) /* topology extensions CPUID leafs */
 #define X86_FEATURE_PERFCTR_CORE (6*32+23) /* core performance counter extensions */
+#define X86_FEATURE_PERFCTR_NB  (6*32+24) /* NB performance counter extensions */
 
 /*
  * Auxiliary flags: Linux defined - For features scattered in various
@@ -309,6 +310,7 @@
 #define cpu_has_hypervisor	boot_cpu_has(X86_FEATURE_HYPERVISOR)
 #define cpu_has_pclmulqdq	boot_cpu_has(X86_FEATURE_PCLMULQDQ)
 #define cpu_has_perfctr_core	boot_cpu_has(X86_FEATURE_PERFCTR_CORE)
+#define cpu_has_perfctr_nb	boot_cpu_has(X86_FEATURE_PERFCTR_NB)
 #define cpu_has_cx8		boot_cpu_has(X86_FEATURE_CX8)
 #define cpu_has_cx16		boot_cpu_has(X86_FEATURE_CX16)
 #define cpu_has_eager_fpu	boot_cpu_has(X86_FEATURE_EAGER_FPU)
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 6e8fdf5..28677c5 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -94,6 +94,7 @@
 #endif /* CONFIG_X86_32 */
 
 extern int add_efi_memmap;
+extern unsigned long x86_efi_facility;
 extern void efi_set_executable(efi_memory_desc_t *md, bool executable);
 extern int efi_memblock_x86_reserve_range(void);
 extern void efi_call_phys_prelog(void);
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index 9a25b52..86cb51e 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -44,7 +44,6 @@
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 #define ARCH_SUPPORTS_FTRACE_OPS 1
-#define ARCH_SUPPORTS_FTRACE_SAVE_REGS
 #endif
 
 #ifndef __ASSEMBLY__
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index ecdfee6..f4076af 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -3,6 +3,90 @@
 
 #include <uapi/asm/mce.h>
 
+/*
+ * Machine Check support for x86
+ */
+
+/* MCG_CAP register defines */
+#define MCG_BANKCNT_MASK	0xff         /* Number of Banks */
+#define MCG_CTL_P		(1ULL<<8)    /* MCG_CTL register available */
+#define MCG_EXT_P		(1ULL<<9)    /* Extended registers available */
+#define MCG_CMCI_P		(1ULL<<10)   /* CMCI supported */
+#define MCG_EXT_CNT_MASK	0xff0000     /* Number of Extended registers */
+#define MCG_EXT_CNT_SHIFT	16
+#define MCG_EXT_CNT(c)		(((c) & MCG_EXT_CNT_MASK) >> MCG_EXT_CNT_SHIFT)
+#define MCG_SER_P		(1ULL<<24)   /* MCA recovery/new status bits */
+
+/* MCG_STATUS register defines */
+#define MCG_STATUS_RIPV  (1ULL<<0)   /* restart ip valid */
+#define MCG_STATUS_EIPV  (1ULL<<1)   /* ip points to correct instruction */
+#define MCG_STATUS_MCIP  (1ULL<<2)   /* machine check in progress */
+
+/* MCi_STATUS register defines */
+#define MCI_STATUS_VAL   (1ULL<<63)  /* valid error */
+#define MCI_STATUS_OVER  (1ULL<<62)  /* previous errors lost */
+#define MCI_STATUS_UC    (1ULL<<61)  /* uncorrected error */
+#define MCI_STATUS_EN    (1ULL<<60)  /* error enabled */
+#define MCI_STATUS_MISCV (1ULL<<59)  /* misc error reg. valid */
+#define MCI_STATUS_ADDRV (1ULL<<58)  /* addr reg. valid */
+#define MCI_STATUS_PCC   (1ULL<<57)  /* processor context corrupt */
+#define MCI_STATUS_S	 (1ULL<<56)  /* Signaled machine check */
+#define MCI_STATUS_AR	 (1ULL<<55)  /* Action required */
+#define MCACOD		  0xffff     /* MCA Error Code */
+
+/* Architecturally defined codes from SDM Vol. 3B Chapter 15 */
+#define MCACOD_SCRUB	0x00C0	/* 0xC0-0xCF Memory Scrubbing */
+#define MCACOD_SCRUBMSK	0xfff0
+#define MCACOD_L3WB	0x017A	/* L3 Explicit Writeback */
+#define MCACOD_DATA	0x0134	/* Data Load */
+#define MCACOD_INSTR	0x0150	/* Instruction Fetch */
+
+/* MCi_MISC register defines */
+#define MCI_MISC_ADDR_LSB(m)	((m) & 0x3f)
+#define MCI_MISC_ADDR_MODE(m)	(((m) >> 6) & 7)
+#define  MCI_MISC_ADDR_SEGOFF	0	/* segment offset */
+#define  MCI_MISC_ADDR_LINEAR	1	/* linear address */
+#define  MCI_MISC_ADDR_PHYS	2	/* physical address */
+#define  MCI_MISC_ADDR_MEM	3	/* memory address */
+#define  MCI_MISC_ADDR_GENERIC	7	/* generic */
+
+/* CTL2 register defines */
+#define MCI_CTL2_CMCI_EN		(1ULL << 30)
+#define MCI_CTL2_CMCI_THRESHOLD_MASK	0x7fffULL
+
+#define MCJ_CTX_MASK		3
+#define MCJ_CTX(flags)		((flags) & MCJ_CTX_MASK)
+#define MCJ_CTX_RANDOM		0    /* inject context: random */
+#define MCJ_CTX_PROCESS		0x1  /* inject context: process */
+#define MCJ_CTX_IRQ		0x2  /* inject context: IRQ */
+#define MCJ_NMI_BROADCAST	0x4  /* do NMI broadcasting */
+#define MCJ_EXCEPTION		0x8  /* raise as exception */
+#define MCJ_IRQ_BRAODCAST	0x10 /* do IRQ broadcasting */
+
+#define MCE_OVERFLOW 0		/* bit 0 in flags means overflow */
+
+/* Software defined banks */
+#define MCE_EXTENDED_BANK	128
+#define MCE_THERMAL_BANK	(MCE_EXTENDED_BANK + 0)
+#define K8_MCE_THRESHOLD_BASE   (MCE_EXTENDED_BANK + 1)
+
+#define MCE_LOG_LEN 32
+#define MCE_LOG_SIGNATURE	"MACHINECHECK"
+
+/*
+ * This structure contains all data related to the MCE log.  Also
+ * carries a signature to make it easier to find from external
+ * debugging tools.  Each entry is only valid when its finished flag
+ * is set.
+ */
+struct mce_log {
+	char signature[12]; /* "MACHINECHECK" */
+	unsigned len;	    /* = MCE_LOG_LEN */
+	unsigned next;
+	unsigned flags;
+	unsigned recordlen;	/* length of struct mce */
+	struct mce entry[MCE_LOG_LEN];
+};
 
 struct mca_config {
 	bool dont_log_ce;
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 4fabcdf..57cb634 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -29,8 +29,13 @@
 #define ARCH_PERFMON_EVENTSEL_INV			(1ULL << 23)
 #define ARCH_PERFMON_EVENTSEL_CMASK			0xFF000000ULL
 
-#define AMD_PERFMON_EVENTSEL_GUESTONLY			(1ULL << 40)
-#define AMD_PERFMON_EVENTSEL_HOSTONLY			(1ULL << 41)
+#define AMD64_EVENTSEL_INT_CORE_ENABLE			(1ULL << 36)
+#define AMD64_EVENTSEL_GUESTONLY			(1ULL << 40)
+#define AMD64_EVENTSEL_HOSTONLY				(1ULL << 41)
+
+#define AMD64_EVENTSEL_INT_CORE_SEL_SHIFT		37
+#define AMD64_EVENTSEL_INT_CORE_SEL_MASK		\
+	(0xFULL << AMD64_EVENTSEL_INT_CORE_SEL_SHIFT)
 
 #define AMD64_EVENTSEL_EVENT	\
 	(ARCH_PERFMON_EVENTSEL_EVENT | (0x0FULL << 32))
@@ -46,8 +51,12 @@
 #define AMD64_RAW_EVENT_MASK		\
 	(X86_RAW_EVENT_MASK          |  \
 	 AMD64_EVENTSEL_EVENT)
+#define AMD64_RAW_EVENT_MASK_NB		\
+	(AMD64_EVENTSEL_EVENT        |  \
+	 ARCH_PERFMON_EVENTSEL_UMASK)
 #define AMD64_NUM_COUNTERS				4
 #define AMD64_NUM_COUNTERS_CORE				6
+#define AMD64_NUM_COUNTERS_NB				4
 
 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL		0x3c
 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK		(0x00 << 8)
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 5199db2..1c1a955 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -142,6 +142,11 @@
 	return (pmd_val(pmd) & PTE_PFN_MASK) >> PAGE_SHIFT;
 }
 
+static inline unsigned long pud_pfn(pud_t pud)
+{
+	return (pud_val(pud) & PTE_PFN_MASK) >> PAGE_SHIFT;
+}
+
 #define pte_page(pte)	pfn_to_page(pte_pfn(pte))
 
 static inline int pmd_large(pmd_t pte)
diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h
index b47c2a8..062921e 100644
--- a/arch/x86/include/asm/uv/uv.h
+++ b/arch/x86/include/asm/uv/uv.h
@@ -16,7 +16,7 @@
 extern const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
 						 struct mm_struct *mm,
 						 unsigned long start,
-						 unsigned end,
+						 unsigned long end,
 						 unsigned int cpu);
 
 #else	/* X86_UV */
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index 92862cd..c15ddaf 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -1,6 +1,31 @@
 #ifndef _ASM_X86_BOOTPARAM_H
 #define _ASM_X86_BOOTPARAM_H
 
+/* setup_data types */
+#define SETUP_NONE			0
+#define SETUP_E820_EXT			1
+#define SETUP_DTB			2
+#define SETUP_PCI			3
+
+/* ram_size flags */
+#define RAMDISK_IMAGE_START_MASK	0x07FF
+#define RAMDISK_PROMPT_FLAG		0x8000
+#define RAMDISK_LOAD_FLAG		0x4000
+
+/* loadflags */
+#define LOADED_HIGH	(1<<0)
+#define QUIET_FLAG	(1<<5)
+#define KEEP_SEGMENTS	(1<<6)
+#define CAN_USE_HEAP	(1<<7)
+
+/* xloadflags */
+#define XLF_KERNEL_64			(1<<0)
+#define XLF_CAN_BE_LOADED_ABOVE_4G	(1<<1)
+#define XLF_EFI_HANDOVER_32		(1<<2)
+#define XLF_EFI_HANDOVER_64		(1<<3)
+
+#ifndef __ASSEMBLY__
+
 #include <linux/types.h>
 #include <linux/screen_info.h>
 #include <linux/apm_bios.h>
@@ -9,12 +34,6 @@
 #include <asm/ist.h>
 #include <video/edid.h>
 
-/* setup data types */
-#define SETUP_NONE			0
-#define SETUP_E820_EXT			1
-#define SETUP_DTB			2
-#define SETUP_PCI			3
-
 /* extensible setup data list node */
 struct setup_data {
 	__u64 next;
@@ -28,9 +47,6 @@
 	__u16	root_flags;
 	__u32	syssize;
 	__u16	ram_size;
-#define RAMDISK_IMAGE_START_MASK	0x07FF
-#define RAMDISK_PROMPT_FLAG		0x8000
-#define RAMDISK_LOAD_FLAG		0x4000
 	__u16	vid_mode;
 	__u16	root_dev;
 	__u16	boot_flag;
@@ -42,10 +58,6 @@
 	__u16	kernel_version;
 	__u8	type_of_loader;
 	__u8	loadflags;
-#define LOADED_HIGH	(1<<0)
-#define QUIET_FLAG	(1<<5)
-#define KEEP_SEGMENTS	(1<<6)
-#define CAN_USE_HEAP	(1<<7)
 	__u16	setup_move_size;
 	__u32	code32_start;
 	__u32	ramdisk_image;
@@ -58,7 +70,8 @@
 	__u32	initrd_addr_max;
 	__u32	kernel_alignment;
 	__u8	relocatable_kernel;
-	__u8	_pad2[3];
+	__u8	min_alignment;
+	__u16	xloadflags;
 	__u32	cmdline_size;
 	__u32	hardware_subarch;
 	__u64	hardware_subarch_data;
@@ -106,7 +119,10 @@
 	__u8  hd1_info[16];	/* obsolete! */		/* 0x090 */
 	struct sys_desc_table sys_desc_table;		/* 0x0a0 */
 	struct olpc_ofw_header olpc_ofw_header;		/* 0x0b0 */
-	__u8  _pad4[128];				/* 0x0c0 */
+	__u32 ext_ramdisk_image;			/* 0x0c0 */
+	__u32 ext_ramdisk_size;				/* 0x0c4 */
+	__u32 ext_cmd_line_ptr;				/* 0x0c8 */
+	__u8  _pad4[116];				/* 0x0cc */
 	struct edid_info edid_info;			/* 0x140 */
 	struct efi_info efi_info;			/* 0x1c0 */
 	__u32 alt_mem_k;				/* 0x1e0 */
@@ -115,7 +131,20 @@
 	__u8  eddbuf_entries;				/* 0x1e9 */
 	__u8  edd_mbr_sig_buf_entries;			/* 0x1ea */
 	__u8  kbd_status;				/* 0x1eb */
-	__u8  _pad6[5];					/* 0x1ec */
+	__u8  _pad5[3];					/* 0x1ec */
+	/*
+	 * The sentinel is set to a nonzero value (0xff) in header.S.
+	 *
+	 * A bootloader is supposed to only take setup_header and put
+	 * it into a clean boot_params buffer. If it turns out that
+	 * it is clumsy or too generous with the buffer, it most
+	 * probably will pick up the sentinel variable too. The fact
+	 * that this variable then is still 0xff will let kernel
+	 * know that some variables in boot_params are invalid and
+	 * kernel should zero out certain portions of boot_params.
+	 */
+	__u8  sentinel;					/* 0x1ef */
+	__u8  _pad6[1];					/* 0x1f0 */
 	struct setup_header hdr;    /* setup header */	/* 0x1f1 */
 	__u8  _pad7[0x290-0x1f1-sizeof(struct setup_header)];
 	__u32 edd_mbr_sig_buffer[EDD_MBR_SIG_MAX];	/* 0x290 */
@@ -134,6 +163,6 @@
 	X86_NR_SUBARCHS,
 };
 
-
+#endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_X86_BOOTPARAM_H */
diff --git a/arch/x86/include/uapi/asm/mce.h b/arch/x86/include/uapi/asm/mce.h
index 58c8298..a0eab85 100644
--- a/arch/x86/include/uapi/asm/mce.h
+++ b/arch/x86/include/uapi/asm/mce.h
@@ -4,66 +4,6 @@
 #include <linux/types.h>
 #include <asm/ioctls.h>
 
-/*
- * Machine Check support for x86
- */
-
-/* MCG_CAP register defines */
-#define MCG_BANKCNT_MASK	0xff         /* Number of Banks */
-#define MCG_CTL_P		(1ULL<<8)    /* MCG_CTL register available */
-#define MCG_EXT_P		(1ULL<<9)    /* Extended registers available */
-#define MCG_CMCI_P		(1ULL<<10)   /* CMCI supported */
-#define MCG_EXT_CNT_MASK	0xff0000     /* Number of Extended registers */
-#define MCG_EXT_CNT_SHIFT	16
-#define MCG_EXT_CNT(c)		(((c) & MCG_EXT_CNT_MASK) >> MCG_EXT_CNT_SHIFT)
-#define MCG_SER_P	 	(1ULL<<24)   /* MCA recovery/new status bits */
-
-/* MCG_STATUS register defines */
-#define MCG_STATUS_RIPV  (1ULL<<0)   /* restart ip valid */
-#define MCG_STATUS_EIPV  (1ULL<<1)   /* ip points to correct instruction */
-#define MCG_STATUS_MCIP  (1ULL<<2)   /* machine check in progress */
-
-/* MCi_STATUS register defines */
-#define MCI_STATUS_VAL   (1ULL<<63)  /* valid error */
-#define MCI_STATUS_OVER  (1ULL<<62)  /* previous errors lost */
-#define MCI_STATUS_UC    (1ULL<<61)  /* uncorrected error */
-#define MCI_STATUS_EN    (1ULL<<60)  /* error enabled */
-#define MCI_STATUS_MISCV (1ULL<<59)  /* misc error reg. valid */
-#define MCI_STATUS_ADDRV (1ULL<<58)  /* addr reg. valid */
-#define MCI_STATUS_PCC   (1ULL<<57)  /* processor context corrupt */
-#define MCI_STATUS_S	 (1ULL<<56)  /* Signaled machine check */
-#define MCI_STATUS_AR	 (1ULL<<55)  /* Action required */
-#define MCACOD		  0xffff     /* MCA Error Code */
-
-/* Architecturally defined codes from SDM Vol. 3B Chapter 15 */
-#define MCACOD_SCRUB	0x00C0	/* 0xC0-0xCF Memory Scrubbing */
-#define MCACOD_SCRUBMSK	0xfff0
-#define MCACOD_L3WB	0x017A	/* L3 Explicit Writeback */
-#define MCACOD_DATA	0x0134	/* Data Load */
-#define MCACOD_INSTR	0x0150	/* Instruction Fetch */
-
-/* MCi_MISC register defines */
-#define MCI_MISC_ADDR_LSB(m)	((m) & 0x3f)
-#define MCI_MISC_ADDR_MODE(m)	(((m) >> 6) & 7)
-#define  MCI_MISC_ADDR_SEGOFF	0	/* segment offset */
-#define  MCI_MISC_ADDR_LINEAR	1	/* linear address */
-#define  MCI_MISC_ADDR_PHYS	2	/* physical address */
-#define  MCI_MISC_ADDR_MEM	3	/* memory address */
-#define  MCI_MISC_ADDR_GENERIC	7	/* generic */
-
-/* CTL2 register defines */
-#define MCI_CTL2_CMCI_EN		(1ULL << 30)
-#define MCI_CTL2_CMCI_THRESHOLD_MASK	0x7fffULL
-
-#define MCJ_CTX_MASK		3
-#define MCJ_CTX(flags)		((flags) & MCJ_CTX_MASK)
-#define MCJ_CTX_RANDOM		0    /* inject context: random */
-#define MCJ_CTX_PROCESS		0x1  /* inject context: process */
-#define MCJ_CTX_IRQ		0x2  /* inject context: IRQ */
-#define MCJ_NMI_BROADCAST	0x4  /* do NMI broadcasting */
-#define MCJ_EXCEPTION		0x8  /* raise as exception */
-#define MCJ_IRQ_BRAODCAST	0x10 /* do IRQ broadcasting */
-
 /* Fields are zero when not available */
 struct mce {
 	__u64 status;
@@ -87,35 +27,8 @@
 	__u64 mcgcap;	/* MCGCAP MSR: machine check capabilities of CPU */
 };
 
-/*
- * This structure contains all data related to the MCE log.  Also
- * carries a signature to make it easier to find from external
- * debugging tools.  Each entry is only valid when its finished flag
- * is set.
- */
-
-#define MCE_LOG_LEN 32
-
-struct mce_log {
-	char signature[12]; /* "MACHINECHECK" */
-	unsigned len;	    /* = MCE_LOG_LEN */
-	unsigned next;
-	unsigned flags;
-	unsigned recordlen;	/* length of struct mce */
-	struct mce entry[MCE_LOG_LEN];
-};
-
-#define MCE_OVERFLOW 0		/* bit 0 in flags means overflow */
-
-#define MCE_LOG_SIGNATURE	"MACHINECHECK"
-
 #define MCE_GET_RECORD_LEN   _IOR('M', 1, int)
 #define MCE_GET_LOG_LEN      _IOR('M', 2, int)
 #define MCE_GETCLEAR_FLAGS   _IOR('M', 3, int)
 
-/* Software defined banks */
-#define MCE_EXTENDED_BANK	128
-#define MCE_THERMAL_BANK	MCE_EXTENDED_BANK + 0
-#define K8_MCE_THRESHOLD_BASE      (MCE_EXTENDED_BANK + 1)
-
 #endif /* _UAPI_ASM_X86_MCE_H */
diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h
index 433a59f..075a402 100644
--- a/arch/x86/include/uapi/asm/msr-index.h
+++ b/arch/x86/include/uapi/asm/msr-index.h
@@ -194,6 +194,8 @@
 /* Fam 15h MSRs */
 #define MSR_F15H_PERF_CTL		0xc0010200
 #define MSR_F15H_PERF_CTR		0xc0010201
+#define MSR_F15H_NB_PERF_CTL		0xc0010240
+#define MSR_F15H_NB_PERF_CTR		0xc0010241
 
 /* Fam 10h MSRs */
 #define MSR_FAM10H_MMIO_CONF_BASE	0xc0010058
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 34e923a..ac3b3d0 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -65,8 +65,7 @@
 obj-$(CONFIG_KEXEC)		+= machine_kexec_$(BITS).o
 obj-$(CONFIG_KEXEC)		+= relocate_kernel_$(BITS).o crash.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump_$(BITS).o
-obj-$(CONFIG_KPROBES)		+= kprobes.o
-obj-$(CONFIG_OPTPROBES)		+= kprobes-opt.o
+obj-y				+= kprobes/
 obj-$(CONFIG_MODULES)		+= module.o
 obj-$(CONFIG_DOUBLEFAULT) 	+= doublefault_32.o
 obj-$(CONFIG_KGDB)		+= kgdb.o
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index e03a1e1..562a76d 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -20,18 +20,19 @@
 }
 early_param("x2apic_phys", set_x2apic_phys_mode);
 
+static bool x2apic_fadt_phys(void)
+{
+	if ((acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID) &&
+		(acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL)) {
+		printk(KERN_DEBUG "System requires x2apic physical mode\n");
+		return true;
+	}
+	return false;
+}
+
 static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 {
-	if (x2apic_phys)
-		return x2apic_enabled();
-	else if ((acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID) &&
-		(acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL) &&
-		x2apic_enabled()) {
-		printk(KERN_DEBUG "System requires x2apic physical mode\n");
-		return 1;
-	}
-	else
-		return 0;
+	return x2apic_enabled() && (x2apic_phys || x2apic_fadt_phys());
 }
 
 static void
@@ -82,7 +83,7 @@
 
 static int x2apic_phys_probe(void)
 {
-	if (x2apic_mode && x2apic_phys)
+	if (x2apic_mode && (x2apic_phys || x2apic_fadt_phys()))
 		return 1;
 
 	return apic == &apic_x2apic_phys;
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index fe9edec..84c1309c 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -298,8 +298,7 @@
 			 unsigned int);
 };
 
-#ifdef CONFIG_AMD_NB
-
+#if defined(CONFIG_AMD_NB) && defined(CONFIG_SYSFS)
 /*
  * L3 cache descriptors
  */
@@ -524,9 +523,9 @@
 static struct _cache_attr subcaches =
 	__ATTR(subcaches, 0644, show_subcaches, store_subcaches);
 
-#else	/* CONFIG_AMD_NB */
+#else
 #define amd_init_l3_cache(x, y)
-#endif /* CONFIG_AMD_NB */
+#endif  /* CONFIG_AMD_NB && CONFIG_SYSFS */
 
 static int
 __cpuinit cpuid4_cache_lookup_regs(int index,
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 6774c17..bf0f01a 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -829,7 +829,7 @@
 	} else {
 		hwc->config_base = x86_pmu_config_addr(hwc->idx);
 		hwc->event_base  = x86_pmu_event_addr(hwc->idx);
-		hwc->event_base_rdpmc = hwc->idx;
+		hwc->event_base_rdpmc = x86_pmu_rdpmc_index(hwc->idx);
 	}
 }
 
@@ -1310,11 +1310,6 @@
 	.attrs = NULL,
 };
 
-struct perf_pmu_events_attr {
-	struct device_attribute attr;
-	u64 id;
-};
-
 /*
  * Remove all undefined events (x86_pmu.event_map(id) == 0)
  * out of events_attr attributes.
@@ -1348,11 +1343,9 @@
 #define EVENT_VAR(_id)  event_attr_##_id
 #define EVENT_PTR(_id) &event_attr_##_id.attr.attr
 
-#define EVENT_ATTR(_name, _id)					\
-static struct perf_pmu_events_attr EVENT_VAR(_id) = {		\
-	.attr = __ATTR(_name, 0444, events_sysfs_show, NULL),	\
-	.id   =  PERF_COUNT_HW_##_id,				\
-};
+#define EVENT_ATTR(_name, _id)						\
+	PMU_EVENT_ATTR(_name, EVENT_VAR(_id), PERF_COUNT_HW_##_id,	\
+			events_sysfs_show)
 
 EVENT_ATTR(cpu-cycles,			CPU_CYCLES		);
 EVENT_ATTR(instructions,		INSTRUCTIONS		);
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 115c1ea..7f5c75c 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -325,6 +325,8 @@
 	int		(*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign);
 	unsigned	eventsel;
 	unsigned	perfctr;
+	int		(*addr_offset)(int index, bool eventsel);
+	int		(*rdpmc_index)(int index);
 	u64		(*event_map)(int);
 	int		max_events;
 	int		num_counters;
@@ -446,28 +448,21 @@
 
 u64 x86_perf_event_update(struct perf_event *event);
 
-static inline int x86_pmu_addr_offset(int index)
-{
-	int offset;
-
-	/* offset = X86_FEATURE_PERFCTR_CORE ? index << 1 : index */
-	alternative_io(ASM_NOP2,
-		       "shll $1, %%eax",
-		       X86_FEATURE_PERFCTR_CORE,
-		       "=a" (offset),
-		       "a"  (index));
-
-	return offset;
-}
-
 static inline unsigned int x86_pmu_config_addr(int index)
 {
-	return x86_pmu.eventsel + x86_pmu_addr_offset(index);
+	return x86_pmu.eventsel + (x86_pmu.addr_offset ?
+				   x86_pmu.addr_offset(index, true) : index);
 }
 
 static inline unsigned int x86_pmu_event_addr(int index)
 {
-	return x86_pmu.perfctr + x86_pmu_addr_offset(index);
+	return x86_pmu.perfctr + (x86_pmu.addr_offset ?
+				  x86_pmu.addr_offset(index, false) : index);
+}
+
+static inline int x86_pmu_rdpmc_index(int index)
+{
+	return x86_pmu.rdpmc_index ? x86_pmu.rdpmc_index(index) : index;
 }
 
 int x86_setup_perfctr(struct perf_event *event);
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index c93bc4e..dfdab42 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -132,21 +132,102 @@
 	return amd_perfmon_event_map[hw_event];
 }
 
-static int amd_pmu_hw_config(struct perf_event *event)
+static struct event_constraint *amd_nb_event_constraint;
+
+/*
+ * Previously calculated offsets
+ */
+static unsigned int event_offsets[X86_PMC_IDX_MAX] __read_mostly;
+static unsigned int count_offsets[X86_PMC_IDX_MAX] __read_mostly;
+static unsigned int rdpmc_indexes[X86_PMC_IDX_MAX] __read_mostly;
+
+/*
+ * Legacy CPUs:
+ *   4 counters starting at 0xc0010000 each offset by 1
+ *
+ * CPUs with core performance counter extensions:
+ *   6 counters starting at 0xc0010200 each offset by 2
+ *
+ * CPUs with north bridge performance counter extensions:
+ *   4 additional counters starting at 0xc0010240 each offset by 2
+ *   (indexed right above either one of the above core counters)
+ */
+static inline int amd_pmu_addr_offset(int index, bool eventsel)
 {
-	int ret;
+	int offset, first, base;
 
-	/* pass precise event sampling to ibs: */
-	if (event->attr.precise_ip && get_ibs_caps())
-		return -ENOENT;
+	if (!index)
+		return index;
 
-	ret = x86_pmu_hw_config(event);
+	if (eventsel)
+		offset = event_offsets[index];
+	else
+		offset = count_offsets[index];
+
+	if (offset)
+		return offset;
+
+	if (amd_nb_event_constraint &&
+	    test_bit(index, amd_nb_event_constraint->idxmsk)) {
+		/*
+		 * calculate the offset of NB counters with respect to
+		 * base eventsel or perfctr
+		 */
+
+		first = find_first_bit(amd_nb_event_constraint->idxmsk,
+				       X86_PMC_IDX_MAX);
+
+		if (eventsel)
+			base = MSR_F15H_NB_PERF_CTL - x86_pmu.eventsel;
+		else
+			base = MSR_F15H_NB_PERF_CTR - x86_pmu.perfctr;
+
+		offset = base + ((index - first) << 1);
+	} else if (!cpu_has_perfctr_core)
+		offset = index;
+	else
+		offset = index << 1;
+
+	if (eventsel)
+		event_offsets[index] = offset;
+	else
+		count_offsets[index] = offset;
+
+	return offset;
+}
+
+static inline int amd_pmu_rdpmc_index(int index)
+{
+	int ret, first;
+
+	if (!index)
+		return index;
+
+	ret = rdpmc_indexes[index];
+
 	if (ret)
 		return ret;
 
-	if (has_branch_stack(event))
-		return -EOPNOTSUPP;
+	if (amd_nb_event_constraint &&
+	    test_bit(index, amd_nb_event_constraint->idxmsk)) {
+		/*
+		 * according to the mnual, ECX value of the NB counters is
+		 * the index of the NB counter (0, 1, 2 or 3) plus 6
+		 */
 
+		first = find_first_bit(amd_nb_event_constraint->idxmsk,
+				       X86_PMC_IDX_MAX);
+		ret = index - first + 6;
+	} else
+		ret = index;
+
+	rdpmc_indexes[index] = ret;
+
+	return ret;
+}
+
+static int amd_core_hw_config(struct perf_event *event)
+{
 	if (event->attr.exclude_host && event->attr.exclude_guest)
 		/*
 		 * When HO == GO == 1 the hardware treats that as GO == HO == 0
@@ -156,14 +237,37 @@
 		event->hw.config &= ~(ARCH_PERFMON_EVENTSEL_USR |
 				      ARCH_PERFMON_EVENTSEL_OS);
 	else if (event->attr.exclude_host)
-		event->hw.config |= AMD_PERFMON_EVENTSEL_GUESTONLY;
+		event->hw.config |= AMD64_EVENTSEL_GUESTONLY;
 	else if (event->attr.exclude_guest)
-		event->hw.config |= AMD_PERFMON_EVENTSEL_HOSTONLY;
+		event->hw.config |= AMD64_EVENTSEL_HOSTONLY;
 
-	if (event->attr.type != PERF_TYPE_RAW)
-		return 0;
+	return 0;
+}
 
-	event->hw.config |= event->attr.config & AMD64_RAW_EVENT_MASK;
+/*
+ * NB counters do not support the following event select bits:
+ *   Host/Guest only
+ *   Counter mask
+ *   Invert counter mask
+ *   Edge detect
+ *   OS/User mode
+ */
+static int amd_nb_hw_config(struct perf_event *event)
+{
+	/* for NB, we only allow system wide counting mode */
+	if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
+		return -EINVAL;
+
+	if (event->attr.exclude_user || event->attr.exclude_kernel ||
+	    event->attr.exclude_host || event->attr.exclude_guest)
+		return -EINVAL;
+
+	event->hw.config &= ~(ARCH_PERFMON_EVENTSEL_USR |
+			      ARCH_PERFMON_EVENTSEL_OS);
+
+	if (event->hw.config & ~(AMD64_RAW_EVENT_MASK_NB |
+				 ARCH_PERFMON_EVENTSEL_INT))
+		return -EINVAL;
 
 	return 0;
 }
@@ -181,6 +285,11 @@
 	return (hwc->config & 0xe0) == 0xe0;
 }
 
+static inline int amd_is_perfctr_nb_event(struct hw_perf_event *hwc)
+{
+	return amd_nb_event_constraint && amd_is_nb_event(hwc);
+}
+
 static inline int amd_has_nb(struct cpu_hw_events *cpuc)
 {
 	struct amd_nb *nb = cpuc->amd_nb;
@@ -188,20 +297,37 @@
 	return nb && nb->nb_id != -1;
 }
 
-static void amd_put_event_constraints(struct cpu_hw_events *cpuc,
-				      struct perf_event *event)
+static int amd_pmu_hw_config(struct perf_event *event)
 {
-	struct hw_perf_event *hwc = &event->hw;
+	int ret;
+
+	/* pass precise event sampling to ibs: */
+	if (event->attr.precise_ip && get_ibs_caps())
+		return -ENOENT;
+
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
+	ret = x86_pmu_hw_config(event);
+	if (ret)
+		return ret;
+
+	if (event->attr.type == PERF_TYPE_RAW)
+		event->hw.config |= event->attr.config & AMD64_RAW_EVENT_MASK;
+
+	if (amd_is_perfctr_nb_event(&event->hw))
+		return amd_nb_hw_config(event);
+
+	return amd_core_hw_config(event);
+}
+
+static void __amd_put_nb_event_constraints(struct cpu_hw_events *cpuc,
+					   struct perf_event *event)
+{
 	struct amd_nb *nb = cpuc->amd_nb;
 	int i;
 
 	/*
-	 * only care about NB events
-	 */
-	if (!(amd_has_nb(cpuc) && amd_is_nb_event(hwc)))
-		return;
-
-	/*
 	 * need to scan whole list because event may not have
 	 * been assigned during scheduling
 	 *
@@ -215,6 +341,19 @@
 	}
 }
 
+static void amd_nb_interrupt_hw_config(struct hw_perf_event *hwc)
+{
+	int core_id = cpu_data(smp_processor_id()).cpu_core_id;
+
+	/* deliver interrupts only to this core */
+	if (hwc->config & ARCH_PERFMON_EVENTSEL_INT) {
+		hwc->config |= AMD64_EVENTSEL_INT_CORE_ENABLE;
+		hwc->config &= ~AMD64_EVENTSEL_INT_CORE_SEL_MASK;
+		hwc->config |= (u64)(core_id) <<
+			AMD64_EVENTSEL_INT_CORE_SEL_SHIFT;
+	}
+}
+
  /*
   * AMD64 NorthBridge events need special treatment because
   * counter access needs to be synchronized across all cores
@@ -247,24 +386,24 @@
   *
   * Given that resources are allocated (cmpxchg), they must be
   * eventually freed for others to use. This is accomplished by
-  * calling amd_put_event_constraints().
+  * calling __amd_put_nb_event_constraints()
   *
   * Non NB events are not impacted by this restriction.
   */
 static struct event_constraint *
-amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
+__amd_get_nb_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
+			       struct event_constraint *c)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	struct amd_nb *nb = cpuc->amd_nb;
-	struct perf_event *old = NULL;
-	int max = x86_pmu.num_counters;
-	int i, j, k = -1;
+	struct perf_event *old;
+	int idx, new = -1;
 
-	/*
-	 * if not NB event or no NB, then no constraints
-	 */
-	if (!(amd_has_nb(cpuc) && amd_is_nb_event(hwc)))
-		return &unconstrained;
+	if (!c)
+		c = &unconstrained;
+
+	if (cpuc->is_fake)
+		return c;
 
 	/*
 	 * detect if already present, if so reuse
@@ -276,48 +415,36 @@
 	 * because of successive calls to x86_schedule_events() from
 	 * hw_perf_group_sched_in() without hw_perf_enable()
 	 */
-	for (i = 0; i < max; i++) {
-		/*
-		 * keep track of first free slot
-		 */
-		if (k == -1 && !nb->owners[i])
-			k = i;
+	for_each_set_bit(idx, c->idxmsk, x86_pmu.num_counters) {
+		if (new == -1 || hwc->idx == idx)
+			/* assign free slot, prefer hwc->idx */
+			old = cmpxchg(nb->owners + idx, NULL, event);
+		else if (nb->owners[idx] == event)
+			/* event already present */
+			old = event;
+		else
+			continue;
+
+		if (old && old != event)
+			continue;
+
+		/* reassign to this slot */
+		if (new != -1)
+			cmpxchg(nb->owners + new, event, NULL);
+		new = idx;
 
 		/* already present, reuse */
-		if (nb->owners[i] == event)
-			goto done;
-	}
-	/*
-	 * not present, so grab a new slot
-	 * starting either at:
-	 */
-	if (hwc->idx != -1) {
-		/* previous assignment */
-		i = hwc->idx;
-	} else if (k != -1) {
-		/* start from free slot found */
-		i = k;
-	} else {
-		/*
-		 * event not found, no slot found in
-		 * first pass, try again from the
-		 * beginning
-		 */
-		i = 0;
-	}
-	j = i;
-	do {
-		old = cmpxchg(nb->owners+i, NULL, event);
-		if (!old)
+		if (old == event)
 			break;
-		if (++i == max)
-			i = 0;
-	} while (i != j);
-done:
-	if (!old)
-		return &nb->event_constraints[i];
+	}
 
-	return &emptyconstraint;
+	if (new == -1)
+		return &emptyconstraint;
+
+	if (amd_is_perfctr_nb_event(hwc))
+		amd_nb_interrupt_hw_config(hwc);
+
+	return &nb->event_constraints[new];
 }
 
 static struct amd_nb *amd_alloc_nb(int cpu)
@@ -364,7 +491,7 @@
 	struct amd_nb *nb;
 	int i, nb_id;
 
-	cpuc->perf_ctr_virt_mask = AMD_PERFMON_EVENTSEL_HOSTONLY;
+	cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY;
 
 	if (boot_cpu_data.x86_max_cores < 2)
 		return;
@@ -407,6 +534,26 @@
 	}
 }
 
+static struct event_constraint *
+amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
+{
+	/*
+	 * if not NB event or no NB, then no constraints
+	 */
+	if (!(amd_has_nb(cpuc) && amd_is_nb_event(&event->hw)))
+		return &unconstrained;
+
+	return __amd_get_nb_event_constraints(cpuc, event,
+					      amd_nb_event_constraint);
+}
+
+static void amd_put_event_constraints(struct cpu_hw_events *cpuc,
+				      struct perf_event *event)
+{
+	if (amd_has_nb(cpuc) && amd_is_nb_event(&event->hw))
+		__amd_put_nb_event_constraints(cpuc, event);
+}
+
 PMU_FORMAT_ATTR(event,	"config:0-7,32-35");
 PMU_FORMAT_ATTR(umask,	"config:8-15"	);
 PMU_FORMAT_ATTR(edge,	"config:18"	);
@@ -496,6 +643,9 @@
 static struct event_constraint amd_f15_PMC50 = EVENT_CONSTRAINT(0, 0x3F, 0);
 static struct event_constraint amd_f15_PMC53 = EVENT_CONSTRAINT(0, 0x38, 0);
 
+static struct event_constraint amd_NBPMC96 = EVENT_CONSTRAINT(0, 0x3C0, 0);
+static struct event_constraint amd_NBPMC74 = EVENT_CONSTRAINT(0, 0xF0, 0);
+
 static struct event_constraint *
 amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *event)
 {
@@ -561,8 +711,8 @@
 			return &amd_f15_PMC20;
 		}
 	case AMD_EVENT_NB:
-		/* not yet implemented */
-		return &emptyconstraint;
+		return __amd_get_nb_event_constraints(cpuc, event,
+						      amd_nb_event_constraint);
 	default:
 		return &emptyconstraint;
 	}
@@ -587,6 +737,8 @@
 	.schedule_events	= x86_schedule_events,
 	.eventsel		= MSR_K7_EVNTSEL0,
 	.perfctr		= MSR_K7_PERFCTR0,
+	.addr_offset            = amd_pmu_addr_offset,
+	.rdpmc_index		= amd_pmu_rdpmc_index,
 	.event_map		= amd_pmu_event_map,
 	.max_events		= ARRAY_SIZE(amd_perfmon_event_map),
 	.num_counters		= AMD64_NUM_COUNTERS,
@@ -608,7 +760,7 @@
 
 static int setup_event_constraints(void)
 {
-	if (boot_cpu_data.x86 >= 0x15)
+	if (boot_cpu_data.x86 == 0x15)
 		x86_pmu.get_event_constraints = amd_get_event_constraints_f15h;
 	return 0;
 }
@@ -638,6 +790,23 @@
 	return 0;
 }
 
+static int setup_perfctr_nb(void)
+{
+	if (!cpu_has_perfctr_nb)
+		return -ENODEV;
+
+	x86_pmu.num_counters += AMD64_NUM_COUNTERS_NB;
+
+	if (cpu_has_perfctr_core)
+		amd_nb_event_constraint = &amd_NBPMC96;
+	else
+		amd_nb_event_constraint = &amd_NBPMC74;
+
+	printk(KERN_INFO "perf: AMD northbridge performance counters detected\n");
+
+	return 0;
+}
+
 __init int amd_pmu_init(void)
 {
 	/* Performance-monitoring supported from K7 and later: */
@@ -648,6 +817,7 @@
 
 	setup_event_constraints();
 	setup_perfctr_core();
+	setup_perfctr_nb();
 
 	/* Events are common for all AMDs */
 	memcpy(hw_cache_event_ids, amd_hw_cache_event_ids,
@@ -678,7 +848,7 @@
 	 * SVM is disabled the Guest-only bits still gets set and the counter
 	 * will not count anything.
 	 */
-	cpuc->perf_ctr_virt_mask = AMD_PERFMON_EVENTSEL_HOSTONLY;
+	cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY;
 
 	/* Reload all events */
 	x86_pmu_disable_all();
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 93b9e11..4914e94 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2019,7 +2019,10 @@
 		break;
 
 	case 28: /* Atom */
-	case 54: /* Cedariew */
+	case 38: /* Lincroft */
+	case 39: /* Penwell */
+	case 53: /* Cloverview */
+	case 54: /* Cedarview */
 		memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
@@ -2084,6 +2087,7 @@
 		pr_cont("SandyBridge events, ");
 		break;
 	case 58: /* IvyBridge */
+	case 62: /* IvyBridge EP */
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs,
diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c
index f2af39f..4820c23 100644
--- a/arch/x86/kernel/cpu/perf_event_p6.c
+++ b/arch/x86/kernel/cpu/perf_event_p6.c
@@ -19,7 +19,7 @@
 
 };
 
-static __initconst u64 p6_hw_cache_event_ids
+static u64 p6_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
 				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 07a7a04..cb3c591 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1781,6 +1781,7 @@
 	 * Leave room for the "copied" frame
 	 */
 	subq $(5*8), %rsp
+	CFI_ADJUST_CFA_OFFSET 5*8
 
 	/* Copy the stack frame to the Saved frame */
 	.rept 5
@@ -1863,10 +1864,8 @@
 nmi_swapgs:
 	SWAPGS_UNSAFE_STACK
 nmi_restore:
-	RESTORE_ALL 8
-
-	/* Pop the extra iret frame */
-	addq $(5*8), %rsp
+	/* Pop the extra iret frame at once */
+	RESTORE_ALL 6*8
 
 	/* Clear the NMI executing stack variable */
 	movq $0, 5*8(%rsp)
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 8e7f655..c8932c7 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -300,6 +300,12 @@
 	leal -__PAGE_OFFSET(%ecx),%esp
 
 default_entry:
+#define CR0_STATE	(X86_CR0_PE | X86_CR0_MP | X86_CR0_ET | \
+			 X86_CR0_NE | X86_CR0_WP | X86_CR0_AM | \
+			 X86_CR0_PG)
+	movl $(CR0_STATE & ~X86_CR0_PG),%eax
+	movl %eax,%cr0
+
 /*
  *	New page tables may be in 4Mbyte page mode and may
  *	be using the global pages. 
@@ -364,8 +370,7 @@
  */
 	movl $pa(initial_page_table), %eax
 	movl %eax,%cr3		/* set the page table pointer.. */
-	movl %cr0,%eax
-	orl  $X86_CR0_PG,%eax
+	movl $CR0_STATE,%eax
 	movl %eax,%cr0		/* ..and set paging (PG) bit */
 	ljmp $__BOOT_CS,$1f	/* Clear prefetch and normalize %eip */
 1:
diff --git a/arch/x86/kernel/kprobes/Makefile b/arch/x86/kernel/kprobes/Makefile
new file mode 100644
index 0000000..0d33169
--- /dev/null
+++ b/arch/x86/kernel/kprobes/Makefile
@@ -0,0 +1,7 @@
+#
+# Makefile for kernel probes
+#
+
+obj-$(CONFIG_KPROBES)		+= core.o
+obj-$(CONFIG_OPTPROBES)		+= opt.o
+obj-$(CONFIG_KPROBES_ON_FTRACE)	+= ftrace.o
diff --git a/arch/x86/kernel/kprobes-common.h b/arch/x86/kernel/kprobes/common.h
similarity index 90%
rename from arch/x86/kernel/kprobes-common.h
rename to arch/x86/kernel/kprobes/common.h
index 3230b68..2e9d4b5 100644
--- a/arch/x86/kernel/kprobes-common.h
+++ b/arch/x86/kernel/kprobes/common.h
@@ -99,4 +99,15 @@
 	return addr;
 }
 #endif
+
+#ifdef CONFIG_KPROBES_ON_FTRACE
+extern int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
+			   struct kprobe_ctlblk *kcb);
+#else
+static inline int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
+				  struct kprobe_ctlblk *kcb)
+{
+	return 0;
+}
+#endif
 #endif
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes/core.c
similarity index 93%
rename from arch/x86/kernel/kprobes.c
rename to arch/x86/kernel/kprobes/core.c
index 57916c0..e124554 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -58,7 +58,7 @@
 #include <asm/insn.h>
 #include <asm/debugreg.h>
 
-#include "kprobes-common.h"
+#include "common.h"
 
 void jprobe_return_end(void);
 
@@ -78,7 +78,7 @@
 	 * Groups, and some special opcodes can not boost.
 	 * This is non-const and volatile to keep gcc from statically
 	 * optimizing it out, as variable_test_bit makes gcc think only
-	 * *(unsigned long*) is used. 
+	 * *(unsigned long*) is used.
 	 */
 static volatile u32 twobyte_is_boostable[256 / 32] = {
 	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f          */
@@ -117,7 +117,7 @@
 	struct __arch_relative_insn {
 		u8 op;
 		s32 raddr;
-	} __attribute__((packed)) *insn;
+	} __packed *insn;
 
 	insn = (struct __arch_relative_insn *)from;
 	insn->raddr = (s32)((long)(to) - ((long)(from) + 5));
@@ -541,23 +541,6 @@
 	return 1;
 }
 
-#ifdef KPROBES_CAN_USE_FTRACE
-static void __kprobes skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-				      struct kprobe_ctlblk *kcb)
-{
-	/*
-	 * Emulate singlestep (and also recover regs->ip)
-	 * as if there is a 5byte nop
-	 */
-	regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE;
-	if (unlikely(p->post_handler)) {
-		kcb->kprobe_status = KPROBE_HIT_SSDONE;
-		p->post_handler(p, regs, 0);
-	}
-	__this_cpu_write(current_kprobe, NULL);
-}
-#endif
-
 /*
  * Interrupts are disabled on entry as trap3 is an interrupt gate and they
  * remain disabled throughout this function.
@@ -616,13 +599,8 @@
 	} else if (kprobe_running()) {
 		p = __this_cpu_read(current_kprobe);
 		if (p->break_handler && p->break_handler(p, regs)) {
-#ifdef KPROBES_CAN_USE_FTRACE
-			if (kprobe_ftrace(p)) {
-				skip_singlestep(p, regs, kcb);
-				return 1;
-			}
-#endif
-			setup_singlestep(p, regs, kcb, 0);
+			if (!skip_singlestep(p, regs, kcb))
+				setup_singlestep(p, regs, kcb, 0);
 			return 1;
 		}
 	} /* else: not a kprobe fault; let the kernel handle it */
@@ -1075,50 +1053,6 @@
 	return 0;
 }
 
-#ifdef KPROBES_CAN_USE_FTRACE
-/* Ftrace callback handler for kprobes */
-void __kprobes kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
-				     struct ftrace_ops *ops, struct pt_regs *regs)
-{
-	struct kprobe *p;
-	struct kprobe_ctlblk *kcb;
-	unsigned long flags;
-
-	/* Disable irq for emulating a breakpoint and avoiding preempt */
-	local_irq_save(flags);
-
-	p = get_kprobe((kprobe_opcode_t *)ip);
-	if (unlikely(!p) || kprobe_disabled(p))
-		goto end;
-
-	kcb = get_kprobe_ctlblk();
-	if (kprobe_running()) {
-		kprobes_inc_nmissed_count(p);
-	} else {
-		/* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */
-		regs->ip = ip + sizeof(kprobe_opcode_t);
-
-		__this_cpu_write(current_kprobe, p);
-		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
-		if (!p->pre_handler || !p->pre_handler(p, regs))
-			skip_singlestep(p, regs, kcb);
-		/*
-		 * If pre_handler returns !0, it sets regs->ip and
-		 * resets current kprobe.
-		 */
-	}
-end:
-	local_irq_restore(flags);
-}
-
-int __kprobes arch_prepare_kprobe_ftrace(struct kprobe *p)
-{
-	p->ainsn.insn = NULL;
-	p->ainsn.boostable = -1;
-	return 0;
-}
-#endif
-
 int __init arch_init_kprobes(void)
 {
 	return arch_init_optprobes();
diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c
new file mode 100644
index 0000000..23ef5c5
--- /dev/null
+++ b/arch/x86/kernel/kprobes/ftrace.c
@@ -0,0 +1,93 @@
+/*
+ * Dynamic Ftrace based Kprobes Optimization
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) Hitachi Ltd., 2012
+ */
+#include <linux/kprobes.h>
+#include <linux/ptrace.h>
+#include <linux/hardirq.h>
+#include <linux/preempt.h>
+#include <linux/ftrace.h>
+
+#include "common.h"
+
+static int __skip_singlestep(struct kprobe *p, struct pt_regs *regs,
+			     struct kprobe_ctlblk *kcb)
+{
+	/*
+	 * Emulate singlestep (and also recover regs->ip)
+	 * as if there is a 5byte nop
+	 */
+	regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE;
+	if (unlikely(p->post_handler)) {
+		kcb->kprobe_status = KPROBE_HIT_SSDONE;
+		p->post_handler(p, regs, 0);
+	}
+	__this_cpu_write(current_kprobe, NULL);
+	return 1;
+}
+
+int __kprobes skip_singlestep(struct kprobe *p, struct pt_regs *regs,
+			      struct kprobe_ctlblk *kcb)
+{
+	if (kprobe_ftrace(p))
+		return __skip_singlestep(p, regs, kcb);
+	else
+		return 0;
+}
+
+/* Ftrace callback handler for kprobes */
+void __kprobes kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
+				     struct ftrace_ops *ops, struct pt_regs *regs)
+{
+	struct kprobe *p;
+	struct kprobe_ctlblk *kcb;
+	unsigned long flags;
+
+	/* Disable irq for emulating a breakpoint and avoiding preempt */
+	local_irq_save(flags);
+
+	p = get_kprobe((kprobe_opcode_t *)ip);
+	if (unlikely(!p) || kprobe_disabled(p))
+		goto end;
+
+	kcb = get_kprobe_ctlblk();
+	if (kprobe_running()) {
+		kprobes_inc_nmissed_count(p);
+	} else {
+		/* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */
+		regs->ip = ip + sizeof(kprobe_opcode_t);
+
+		__this_cpu_write(current_kprobe, p);
+		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+		if (!p->pre_handler || !p->pre_handler(p, regs))
+			__skip_singlestep(p, regs, kcb);
+		/*
+		 * If pre_handler returns !0, it sets regs->ip and
+		 * resets current kprobe.
+		 */
+	}
+end:
+	local_irq_restore(flags);
+}
+
+int __kprobes arch_prepare_kprobe_ftrace(struct kprobe *p)
+{
+	p->ainsn.insn = NULL;
+	p->ainsn.boostable = -1;
+	return 0;
+}
diff --git a/arch/x86/kernel/kprobes-opt.c b/arch/x86/kernel/kprobes/opt.c
similarity index 99%
rename from arch/x86/kernel/kprobes-opt.c
rename to arch/x86/kernel/kprobes/opt.c
index c5e410e..76dc6f0 100644
--- a/arch/x86/kernel/kprobes-opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -37,7 +37,7 @@
 #include <asm/insn.h>
 #include <asm/debugreg.h>
 
-#include "kprobes-common.h"
+#include "common.h"
 
 unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr)
 {
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index a7c5661..4929502 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -174,6 +174,9 @@
 	unsigned int cpu;
 	struct cpuinfo_x86 *c;
 
+	if (!capable(CAP_SYS_RAWIO))
+		return -EPERM;
+
 	cpu = iminor(file->f_path.dentry->d_inode);
 	if (cpu >= nr_cpu_ids || !cpu_online(cpu))
 		return -ENXIO;	/* No such CPU */
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 0f5dec5..872079a 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -56,7 +56,7 @@
 EXPORT_SYMBOL(x86_dma_fallback_dev);
 
 /* Number of entries preallocated for DMA-API debugging */
-#define PREALLOC_DMA_DEBUG_ENTRIES       32768
+#define PREALLOC_DMA_DEBUG_ENTRIES       65536
 
 int dma_set_mask(struct device *dev, u64 mask)
 {
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 4e8ba39..76fa1e9 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -584,7 +584,7 @@
 			break;
 
 		case BOOT_EFI:
-			if (efi_enabled)
+			if (efi_enabled(EFI_RUNTIME_SERVICES))
 				efi.reset_system(reboot_mode ?
 						 EFI_RESET_WARM :
 						 EFI_RESET_COLD,
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 00f6c14..8b24289 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -807,15 +807,15 @@
 #ifdef CONFIG_EFI
 	if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
 		     "EL32", 4)) {
-		efi_enabled = 1;
-		efi_64bit = false;
+		set_bit(EFI_BOOT, &x86_efi_facility);
 	} else if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
 		     "EL64", 4)) {
-		efi_enabled = 1;
-		efi_64bit = true;
+		set_bit(EFI_BOOT, &x86_efi_facility);
+		set_bit(EFI_64BIT, &x86_efi_facility);
 	}
-	if (efi_enabled && efi_memblock_x86_reserve_range())
-		efi_enabled = 0;
+
+	if (efi_enabled(EFI_BOOT))
+		efi_memblock_x86_reserve_range();
 #endif
 
 	x86_init.oem.arch_setup();
@@ -888,7 +888,7 @@
 
 	finish_e820_parsing();
 
-	if (efi_enabled)
+	if (efi_enabled(EFI_BOOT))
 		efi_init();
 
 	dmi_scan_machine();
@@ -971,7 +971,7 @@
 	 * The EFI specification says that boot service code won't be called
 	 * after ExitBootServices(). This is, in fact, a lie.
 	 */
-	if (efi_enabled)
+	if (efi_enabled(EFI_MEMMAP))
 		efi_reserve_boot_services();
 
 	/* preallocate 4k for mptable mpc */
@@ -1114,7 +1114,7 @@
 
 #ifdef CONFIG_VT
 #if defined(CONFIG_VGA_CONSOLE)
-	if (!efi_enabled || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY))
+	if (!efi_enabled(EFI_BOOT) || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY))
 		conswitchp = &vga_con;
 #elif defined(CONFIG_DUMMY_CONSOLE)
 	conswitchp = &dummy_con;
@@ -1131,14 +1131,14 @@
 	register_refined_jiffies(CLOCK_TICK_RATE);
 
 #ifdef CONFIG_EFI
-	/* Once setup is done above, disable efi_enabled on mismatched
-	 * firmware/kernel archtectures since there is no support for
-	 * runtime services.
+	/* Once setup is done above, unmap the EFI memory map on
+	 * mismatched firmware/kernel archtectures since there is no
+	 * support for runtime services.
 	 */
-	if (efi_enabled && IS_ENABLED(CONFIG_X86_64) != efi_64bit) {
+	if (efi_enabled(EFI_BOOT) &&
+	    IS_ENABLED(CONFIG_X86_64) != efi_enabled(EFI_64BIT)) {
 		pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n");
 		efi_unmap_memmap();
-		efi_enabled = 0;
 	}
 #endif
 }
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index c71025b..0ba4cfb 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -680,8 +680,10 @@
 		if (auprobe->insn[i] == 0x66)
 			continue;
 
-		if (auprobe->insn[i] == 0x90)
+		if (auprobe->insn[i] == 0x90) {
+			regs->ip += i + 1;
 			return true;
+		}
 
 		break;
 	}
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 027088f..fb674fd 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -748,13 +748,15 @@
 				return;
 		}
 #endif
+		/* Kernel addresses are always protection faults: */
+		if (address >= TASK_SIZE)
+			error_code |= PF_PROT;
 
-		if (unlikely(show_unhandled_signals))
+		if (likely(show_unhandled_signals))
 			show_signal_msg(regs, error_code, address, tsk);
 
-		/* Kernel addresses are always protection faults: */
 		tsk->thread.cr2		= address;
-		tsk->thread.error_code	= error_code | (address >= TASK_SIZE);
+		tsk->thread.error_code	= error_code;
 		tsk->thread.trap_nr	= X86_TRAP_PF;
 
 		force_sig_info_fault(SIGSEGV, si_code, address, tsk, 0);
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 2ead3c8..75c9a6a 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -831,6 +831,9 @@
 	if (pud_none(*pud))
 		return 0;
 
+	if (pud_large(*pud))
+		return pfn_valid(pud_pfn(*pud));
+
 	pmd = pmd_offset(pud, addr);
 	if (pmd_none(*pmd))
 		return 0;
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index ad443914..928bf83 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -51,9 +51,6 @@
 
 #define EFI_DEBUG	1
 
-int efi_enabled;
-EXPORT_SYMBOL(efi_enabled);
-
 struct efi __read_mostly efi = {
 	.mps        = EFI_INVALID_TABLE_ADDR,
 	.acpi       = EFI_INVALID_TABLE_ADDR,
@@ -69,19 +66,28 @@
 
 struct efi_memory_map memmap;
 
-bool efi_64bit;
-
 static struct efi efi_phys __initdata;
 static efi_system_table_t efi_systab __initdata;
 
 static inline bool efi_is_native(void)
 {
-	return IS_ENABLED(CONFIG_X86_64) == efi_64bit;
+	return IS_ENABLED(CONFIG_X86_64) == efi_enabled(EFI_64BIT);
 }
 
+unsigned long x86_efi_facility;
+
+/*
+ * Returns 1 if 'facility' is enabled, 0 otherwise.
+ */
+int efi_enabled(int facility)
+{
+	return test_bit(facility, &x86_efi_facility) != 0;
+}
+EXPORT_SYMBOL(efi_enabled);
+
 static int __init setup_noefi(char *arg)
 {
-	efi_enabled = 0;
+	clear_bit(EFI_RUNTIME_SERVICES, &x86_efi_facility);
 	return 0;
 }
 early_param("noefi", setup_noefi);
@@ -426,6 +432,7 @@
 
 void __init efi_unmap_memmap(void)
 {
+	clear_bit(EFI_MEMMAP, &x86_efi_facility);
 	if (memmap.map) {
 		early_iounmap(memmap.map, memmap.nr_map * memmap.desc_size);
 		memmap.map = NULL;
@@ -460,7 +467,7 @@
 
 static int __init efi_systab_init(void *phys)
 {
-	if (efi_64bit) {
+	if (efi_enabled(EFI_64BIT)) {
 		efi_system_table_64_t *systab64;
 		u64 tmp = 0;
 
@@ -552,7 +559,7 @@
 	void *config_tables, *tablep;
 	int i, sz;
 
-	if (efi_64bit)
+	if (efi_enabled(EFI_64BIT))
 		sz = sizeof(efi_config_table_64_t);
 	else
 		sz = sizeof(efi_config_table_32_t);
@@ -572,7 +579,7 @@
 		efi_guid_t guid;
 		unsigned long table;
 
-		if (efi_64bit) {
+		if (efi_enabled(EFI_64BIT)) {
 			u64 table64;
 			guid = ((efi_config_table_64_t *)tablep)->guid;
 			table64 = ((efi_config_table_64_t *)tablep)->table;
@@ -684,7 +691,6 @@
 	if (boot_params.efi_info.efi_systab_hi ||
 	    boot_params.efi_info.efi_memmap_hi) {
 		pr_info("Table located above 4GB, disabling EFI.\n");
-		efi_enabled = 0;
 		return;
 	}
 	efi_phys.systab = (efi_system_table_t *)boot_params.efi_info.efi_systab;
@@ -694,10 +700,10 @@
 			  ((__u64)boot_params.efi_info.efi_systab_hi<<32));
 #endif
 
-	if (efi_systab_init(efi_phys.systab)) {
-		efi_enabled = 0;
+	if (efi_systab_init(efi_phys.systab))
 		return;
-	}
+
+	set_bit(EFI_SYSTEM_TABLES, &x86_efi_facility);
 
 	/*
 	 * Show what we know for posterity
@@ -715,10 +721,10 @@
 		efi.systab->hdr.revision >> 16,
 		efi.systab->hdr.revision & 0xffff, vendor);
 
-	if (efi_config_init(efi.systab->tables, efi.systab->nr_tables)) {
-		efi_enabled = 0;
+	if (efi_config_init(efi.systab->tables, efi.systab->nr_tables))
 		return;
-	}
+
+	set_bit(EFI_CONFIG_TABLES, &x86_efi_facility);
 
 	/*
 	 * Note: We currently don't support runtime services on an EFI
@@ -727,15 +733,17 @@
 
 	if (!efi_is_native())
 		pr_info("No EFI runtime due to 32/64-bit mismatch with kernel\n");
-	else if (efi_runtime_init()) {
-		efi_enabled = 0;
-		return;
+	else {
+		if (efi_runtime_init())
+			return;
+		set_bit(EFI_RUNTIME_SERVICES, &x86_efi_facility);
 	}
 
-	if (efi_memmap_init()) {
-		efi_enabled = 0;
+	if (efi_memmap_init())
 		return;
-	}
+
+	set_bit(EFI_MEMMAP, &x86_efi_facility);
+
 #ifdef CONFIG_X86_32
 	if (efi_is_native()) {
 		x86_platform.get_wallclock = efi_get_time;
@@ -941,7 +949,7 @@
 	 *
 	 * Call EFI services through wrapper functions.
 	 */
-	efi.runtime_version = efi_systab.fw_revision;
+	efi.runtime_version = efi_systab.hdr.revision;
 	efi.get_time = virt_efi_get_time;
 	efi.set_time = virt_efi_set_time;
 	efi.get_wakeup_time = virt_efi_get_wakeup_time;
@@ -969,6 +977,9 @@
 	efi_memory_desc_t *md;
 	void *p;
 
+	if (!efi_enabled(EFI_MEMMAP))
+		return 0;
+
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
 		md = p;
 		if ((md->phys_addr <= phys_addr) &&
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 95fd505..2b20038 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -38,7 +38,7 @@
 #include <asm/cacheflush.h>
 #include <asm/fixmap.h>
 
-static pgd_t save_pgd __initdata;
+static pgd_t *save_pgd __initdata;
 static unsigned long efi_flags __initdata;
 
 static void __init early_code_mapping_set_exec(int executable)
@@ -61,12 +61,20 @@
 void __init efi_call_phys_prelog(void)
 {
 	unsigned long vaddress;
+	int pgd;
+	int n_pgds;
 
 	early_code_mapping_set_exec(1);
 	local_irq_save(efi_flags);
-	vaddress = (unsigned long)__va(0x0UL);
-	save_pgd = *pgd_offset_k(0x0UL);
-	set_pgd(pgd_offset_k(0x0UL), *pgd_offset_k(vaddress));
+
+	n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT), PGDIR_SIZE);
+	save_pgd = kmalloc(n_pgds * sizeof(pgd_t), GFP_KERNEL);
+
+	for (pgd = 0; pgd < n_pgds; pgd++) {
+		save_pgd[pgd] = *pgd_offset_k(pgd * PGDIR_SIZE);
+		vaddress = (unsigned long)__va(pgd * PGDIR_SIZE);
+		set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), *pgd_offset_k(vaddress));
+	}
 	__flush_tlb_all();
 }
 
@@ -75,7 +83,11 @@
 	/*
 	 * After the lock is released, the original page table is restored.
 	 */
-	set_pgd(pgd_offset_k(0x0UL), save_pgd);
+	int pgd;
+	int n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE);
+	for (pgd = 0; pgd < n_pgds; pgd++)
+		set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), save_pgd[pgd]);
+	kfree(save_pgd);
 	__flush_tlb_all();
 	local_irq_restore(efi_flags);
 	early_code_mapping_set_exec(0);
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index b8b3a37..dbbdca5 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -1034,7 +1034,8 @@
  * globally purge translation cache of a virtual address or all TLB's
  * @cpumask: mask of all cpu's in which the address is to be removed
  * @mm: mm_struct containing virtual address range
- * @va: virtual address to be removed (or TLB_FLUSH_ALL for all TLB's on cpu)
+ * @start: start virtual address to be removed from TLB
+ * @end: end virtual address to be remove from TLB
  * @cpu: the current cpu
  *
  * This is the entry point for initiating any UV global TLB shootdown.
@@ -1056,7 +1057,7 @@
  */
 const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
 				struct mm_struct *mm, unsigned long start,
-				unsigned end, unsigned int cpu)
+				unsigned long end, unsigned int cpu)
 {
 	int locals = 0;
 	int remotes = 0;
@@ -1113,7 +1114,10 @@
 
 	record_send_statistics(stat, locals, hubs, remotes, bau_desc);
 
-	bau_desc->payload.address = start;
+	if (!end || (end - start) <= PAGE_SIZE)
+		bau_desc->payload.address = start;
+	else
+		bau_desc->payload.address = TLB_FLUSH_ALL;
 	bau_desc->payload.sending_cpu = cpu;
 	/*
 	 * uv_flush_send_and_wait returns 0 if all cpu's were messaged,
diff --git a/arch/x86/tools/insn_sanity.c b/arch/x86/tools/insn_sanity.c
index cc2f8c1..872eb60 100644
--- a/arch/x86/tools/insn_sanity.c
+++ b/arch/x86/tools/insn_sanity.c
@@ -55,7 +55,7 @@
 static void usage(const char *err)
 {
 	if (err)
-		fprintf(stderr, "Error: %s\n\n", err);
+		fprintf(stderr, "%s: Error: %s\n\n", prog, err);
 	fprintf(stderr, "Usage: %s [-y|-n|-v] [-s seed[,no]] [-m max] [-i input]\n", prog);
 	fprintf(stderr, "\t-y	64bit mode\n");
 	fprintf(stderr, "\t-n	32bit mode\n");
@@ -269,7 +269,13 @@
 		insns++;
 	}
 
-	fprintf(stdout, "%s: decoded and checked %d %s instructions with %d errors (seed:0x%x)\n", (errors) ? "Failure" : "Success", insns, (input_file) ? "given" : "random", errors, seed);
+	fprintf(stdout, "%s: %s: decoded and checked %d %s instructions with %d errors (seed:0x%x)\n",
+		prog,
+		(errors) ? "Failure" : "Success",
+		insns,
+		(input_file) ? "given" : "random",
+		errors,
+		seed);
 
 	return errors ? 1 : 0;
 }
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index 5a1847d..79d67bd 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -814,12 +814,14 @@
 	read_relocs(fp);
 	if (show_absolute_syms) {
 		print_absolute_symbols();
-		return 0;
+		goto out;
 	}
 	if (show_absolute_relocs) {
 		print_absolute_relocs();
-		return 0;
+		goto out;
 	}
 	emit_relocs(as_text, use_real_mode);
+out:
+	fclose(fp);
 	return 0;
 }
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 138e566..e0140923 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1517,72 +1517,51 @@
 #endif
 }
 
-#ifdef CONFIG_XEN_PVHVM
-#define HVM_SHARED_INFO_ADDR 0xFE700000UL
-static struct shared_info *xen_hvm_shared_info;
-static unsigned long xen_hvm_sip_phys;
-static int xen_major, xen_minor;
-
-static void xen_hvm_connect_shared_info(unsigned long pfn)
+void __ref xen_hvm_init_shared_info(void)
 {
+	int cpu;
 	struct xen_add_to_physmap xatp;
+	static struct shared_info *shared_info_page = 0;
 
+	if (!shared_info_page)
+		shared_info_page = (struct shared_info *)
+			extend_brk(PAGE_SIZE, PAGE_SIZE);
 	xatp.domid = DOMID_SELF;
 	xatp.idx = 0;
 	xatp.space = XENMAPSPACE_shared_info;
-	xatp.gpfn = pfn;
+	xatp.gpfn = __pa(shared_info_page) >> PAGE_SHIFT;
 	if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp))
 		BUG();
 
-}
-static void __init xen_hvm_set_shared_info(struct shared_info *sip)
-{
-	int cpu;
-
-	HYPERVISOR_shared_info = sip;
+	HYPERVISOR_shared_info = (struct shared_info *)shared_info_page;
 
 	/* xen_vcpu is a pointer to the vcpu_info struct in the shared_info
 	 * page, we use it in the event channel upcall and in some pvclock
 	 * related functions. We don't need the vcpu_info placement
 	 * optimizations because we don't use any pv_mmu or pv_irq op on
-	 * HVM. */
-	for_each_online_cpu(cpu)
+	 * HVM.
+	 * When xen_hvm_init_shared_info is run at boot time only vcpu 0 is
+	 * online but xen_hvm_init_shared_info is run at resume time too and
+	 * in that case multiple vcpus might be online. */
+	for_each_online_cpu(cpu) {
 		per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
-}
-
-/* Reconnect the shared_info pfn to a (new) mfn */
-void xen_hvm_resume_shared_info(void)
-{
-	xen_hvm_connect_shared_info(xen_hvm_sip_phys >> PAGE_SHIFT);
-}
-
-/* Xen tools prior to Xen 4 do not provide a E820_Reserved area for guest usage.
- * On these old tools the shared info page will be placed in E820_Ram.
- * Xen 4 provides a E820_Reserved area at 0xFC000000, and this code expects
- * that nothing is mapped up to HVM_SHARED_INFO_ADDR.
- * Xen 4.3+ provides an explicit 1MB area at HVM_SHARED_INFO_ADDR which is used
- * here for the shared info page. */
-static void __init xen_hvm_init_shared_info(void)
-{
-	if (xen_major < 4) {
-		xen_hvm_shared_info = extend_brk(PAGE_SIZE, PAGE_SIZE);
-		xen_hvm_sip_phys = __pa(xen_hvm_shared_info);
-	} else {
-		xen_hvm_sip_phys = HVM_SHARED_INFO_ADDR;
-		set_fixmap(FIX_PARAVIRT_BOOTMAP, xen_hvm_sip_phys);
-		xen_hvm_shared_info =
-		(struct shared_info *)fix_to_virt(FIX_PARAVIRT_BOOTMAP);
 	}
-	xen_hvm_connect_shared_info(xen_hvm_sip_phys >> PAGE_SHIFT);
-	xen_hvm_set_shared_info(xen_hvm_shared_info);
 }
 
+#ifdef CONFIG_XEN_PVHVM
 static void __init init_hvm_pv_info(void)
 {
-	uint32_t ecx, edx, pages, msr, base;
+	int major, minor;
+	uint32_t eax, ebx, ecx, edx, pages, msr, base;
 	u64 pfn;
 
 	base = xen_cpuid_base();
+	cpuid(base + 1, &eax, &ebx, &ecx, &edx);
+
+	major = eax >> 16;
+	minor = eax & 0xffff;
+	printk(KERN_INFO "Xen version %d.%d.\n", major, minor);
+
 	cpuid(base + 2, &pages, &msr, &ecx, &edx);
 
 	pfn = __pa(hypercall_page);
@@ -1633,22 +1612,12 @@
 
 static bool __init xen_hvm_platform(void)
 {
-	uint32_t eax, ebx, ecx, edx, base;
-
 	if (xen_pv_domain())
 		return false;
 
-	base = xen_cpuid_base();
-	if (!base)
+	if (!xen_cpuid_base())
 		return false;
 
-	cpuid(base + 1, &eax, &ebx, &ecx, &edx);
-
-	xen_major = eax >> 16;
-	xen_minor = eax & 0xffff;
-
-	printk(KERN_INFO "Xen version %d.%d.\n", xen_major, xen_minor);
-
 	return true;
 }
 
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index ae8a00c..45329c8 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -30,7 +30,7 @@
 {
 #ifdef CONFIG_XEN_PVHVM
 	int cpu;
-	xen_hvm_resume_shared_info();
+	xen_hvm_init_shared_info();
 	xen_callback_vector();
 	xen_unplug_emulated_devices();
 	if (xen_feature(XENFEAT_hvm_safe_pvclock)) {
diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S
index f9643fc..33ca6e4 100644
--- a/arch/x86/xen/xen-asm_32.S
+++ b/arch/x86/xen/xen-asm_32.S
@@ -89,11 +89,11 @@
 	 */
 #ifdef CONFIG_SMP
 	GET_THREAD_INFO(%eax)
-	movl TI_cpu(%eax), %eax
-	movl __per_cpu_offset(,%eax,4), %eax
-	mov xen_vcpu(%eax), %eax
+	movl %ss:TI_cpu(%eax), %eax
+	movl %ss:__per_cpu_offset(,%eax,4), %eax
+	mov %ss:xen_vcpu(%eax), %eax
 #else
-	movl xen_vcpu, %eax
+	movl %ss:xen_vcpu, %eax
 #endif
 
 	/* check IF state we're restoring */
@@ -106,11 +106,11 @@
 	 * resuming the code, so we don't have to be worried about
 	 * being preempted to another CPU.
 	 */
-	setz XEN_vcpu_info_mask(%eax)
+	setz %ss:XEN_vcpu_info_mask(%eax)
 xen_iret_start_crit:
 
 	/* check for unmasked and pending */
-	cmpw $0x0001, XEN_vcpu_info_pending(%eax)
+	cmpw $0x0001, %ss:XEN_vcpu_info_pending(%eax)
 
 	/*
 	 * If there's something pending, mask events again so we can
@@ -118,7 +118,7 @@
 	 * touch XEN_vcpu_info_mask.
 	 */
 	jne 1f
-	movb $1, XEN_vcpu_info_mask(%eax)
+	movb $1, %ss:XEN_vcpu_info_mask(%eax)
 
 1:	popl %eax
 
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index d2e73d1..a95b417 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -40,7 +40,7 @@
 void xen_vcpu_restore(void);
 
 void xen_callback_vector(void);
-void xen_hvm_resume_shared_info(void);
+void xen_hvm_init_shared_info(void);
 void xen_unplug_emulated_devices(void);
 
 void __init xen_build_dynamic_phys_to_machine(void);
diff --git a/arch/xtensa/include/asm/dma-mapping.h b/arch/xtensa/include/asm/dma-mapping.h
index 4acb5feb..172a02a 100644
--- a/arch/xtensa/include/asm/dma-mapping.h
+++ b/arch/xtensa/include/asm/dma-mapping.h
@@ -170,4 +170,19 @@
 	consistent_sync(vaddr, size, direction);
 }
 
+/* Not supported for now */
+static inline int dma_mmap_coherent(struct device *dev,
+				    struct vm_area_struct *vma, void *cpu_addr,
+				    dma_addr_t dma_addr, size_t size)
+{
+	return -EINVAL;
+}
+
+static inline int dma_get_sgtable(struct device *dev, struct sg_table *sgt,
+				  void *cpu_addr, dma_addr_t dma_addr,
+				  size_t size)
+{
+	return -EINVAL;
+}
+
 #endif	/* _XTENSA_DMA_MAPPING_H */
diff --git a/block/genhd.c b/block/genhd.c
index 9a289d7..3993ebf 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -35,6 +35,8 @@
 
 static struct device_type disk_type;
 
+static void disk_check_events(struct disk_events *ev,
+			      unsigned int *clearing_ptr);
 static void disk_alloc_events(struct gendisk *disk);
 static void disk_add_events(struct gendisk *disk);
 static void disk_del_events(struct gendisk *disk);
@@ -1549,6 +1551,7 @@
 	const struct block_device_operations *bdops = disk->fops;
 	struct disk_events *ev = disk->ev;
 	unsigned int pending;
+	unsigned int clearing = mask;
 
 	if (!ev) {
 		/* for drivers still using the old ->media_changed method */
@@ -1558,34 +1561,53 @@
 		return 0;
 	}
 
-	/* tell the workfn about the events being cleared */
+	disk_block_events(disk);
+
+	/*
+	 * store the union of mask and ev->clearing on the stack so that the
+	 * race with disk_flush_events does not cause ambiguity (ev->clearing
+	 * can still be modified even if events are blocked).
+	 */
 	spin_lock_irq(&ev->lock);
-	ev->clearing |= mask;
+	clearing |= ev->clearing;
+	ev->clearing = 0;
 	spin_unlock_irq(&ev->lock);
 
-	/* uncondtionally schedule event check and wait for it to finish */
-	disk_block_events(disk);
-	queue_delayed_work(system_freezable_wq, &ev->dwork, 0);
-	flush_delayed_work(&ev->dwork);
-	__disk_unblock_events(disk, false);
+	disk_check_events(ev, &clearing);
+	/*
+	 * if ev->clearing is not 0, the disk_flush_events got called in the
+	 * middle of this function, so we want to run the workfn without delay.
+	 */
+	__disk_unblock_events(disk, ev->clearing ? true : false);
 
 	/* then, fetch and clear pending events */
 	spin_lock_irq(&ev->lock);
-	WARN_ON_ONCE(ev->clearing & mask);	/* cleared by workfn */
 	pending = ev->pending & mask;
 	ev->pending &= ~mask;
 	spin_unlock_irq(&ev->lock);
+	WARN_ON_ONCE(clearing & mask);
 
 	return pending;
 }
 
+/*
+ * Separate this part out so that a different pointer for clearing_ptr can be
+ * passed in for disk_clear_events.
+ */
 static void disk_events_workfn(struct work_struct *work)
 {
 	struct delayed_work *dwork = to_delayed_work(work);
 	struct disk_events *ev = container_of(dwork, struct disk_events, dwork);
+
+	disk_check_events(ev, &ev->clearing);
+}
+
+static void disk_check_events(struct disk_events *ev,
+			      unsigned int *clearing_ptr)
+{
 	struct gendisk *disk = ev->disk;
 	char *envp[ARRAY_SIZE(disk_uevents) + 1] = { };
-	unsigned int clearing = ev->clearing;
+	unsigned int clearing = *clearing_ptr;
 	unsigned int events;
 	unsigned long intv;
 	int nr_events = 0, i;
@@ -1598,7 +1620,7 @@
 
 	events &= ~ev->pending;
 	ev->pending |= events;
-	ev->clearing &= ~clearing;
+	*clearing_ptr &= ~clearing;
 
 	intv = disk_events_poll_jiffies(disk);
 	if (!ev->block && intv)
diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c
index 00a7836..46f80e2 100644
--- a/drivers/acpi/apei/apei-base.c
+++ b/drivers/acpi/apei/apei-base.c
@@ -590,6 +590,9 @@
 	if (bit_width == 32 && bit_offset == 0 && (*paddr & 0x03) == 0 &&
 	    *access_bit_width < 32)
 		*access_bit_width = 32;
+	else if (bit_width == 64 && bit_offset == 0 && (*paddr & 0x07) == 0 &&
+	    *access_bit_width < 64)
+		*access_bit_width = 64;
 
 	if ((bit_width + bit_offset) > *access_bit_width) {
 		pr_warning(FW_BUG APEI_PFX
diff --git a/drivers/acpi/apei/cper.c b/drivers/acpi/apei/cper.c
index e6defd8..1e5d8a4 100644
--- a/drivers/acpi/apei/cper.c
+++ b/drivers/acpi/apei/cper.c
@@ -29,6 +29,7 @@
 #include <linux/time.h>
 #include <linux/cper.h>
 #include <linux/acpi.h>
+#include <linux/pci.h>
 #include <linux/aer.h>
 
 /*
@@ -249,6 +250,10 @@
 static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie,
 			    const struct acpi_hest_generic_data *gdata)
 {
+#ifdef CONFIG_ACPI_APEI_PCIEAER
+	struct pci_dev *dev;
+#endif
+
 	if (pcie->validation_bits & CPER_PCIE_VALID_PORT_TYPE)
 		printk("%s""port_type: %d, %s\n", pfx, pcie->port_type,
 		       pcie->port_type < ARRAY_SIZE(cper_pcie_port_type_strs) ?
@@ -281,10 +286,18 @@
 	"%s""bridge: secondary_status: 0x%04x, control: 0x%04x\n",
 	pfx, pcie->bridge.secondary_status, pcie->bridge.control);
 #ifdef CONFIG_ACPI_APEI_PCIEAER
-	if (pcie->validation_bits & CPER_PCIE_VALID_AER_INFO) {
-		struct aer_capability_regs *aer_regs = (void *)pcie->aer_info;
-		cper_print_aer(pfx, gdata->error_severity, aer_regs);
+	dev = pci_get_domain_bus_and_slot(pcie->device_id.segment,
+			pcie->device_id.bus, pcie->device_id.function);
+	if (!dev) {
+		pr_err("PCI AER Cannot get PCI device %04x:%02x:%02x.%d\n",
+			pcie->device_id.segment, pcie->device_id.bus,
+			pcie->device_id.slot, pcie->device_id.function);
+		return;
 	}
+	if (pcie->validation_bits & CPER_PCIE_VALID_AER_INFO)
+		cper_print_aer(pfx, dev, gdata->error_severity,
+				(struct aer_capability_regs *) pcie->aer_info);
+	pci_dev_put(dev);
 #endif
 }
 
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 3ff2678..bd22f86 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -250,7 +250,7 @@
 		return acpi_rsdp;
 #endif
 
-	if (efi_enabled) {
+	if (efi_enabled(EFI_CONFIG_TABLES)) {
 		if (efi.acpi20 != EFI_INVALID_TABLE_ADDR)
 			return efi.acpi20;
 		else if (efi.acpi != EFI_INVALID_TABLE_ADDR)
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index f1a5da4..ed9a1cc 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -958,6 +958,9 @@
 		return -EINVAL;
 	}
 
+	if (!dev)
+		return -EINVAL;
+
 	dev->cpu = pr->id;
 
 	if (max_cstate == 0)
@@ -1149,6 +1152,7 @@
 		}
 
 		/* Populate Updated C-state information */
+		acpi_processor_get_power_info(pr);
 		acpi_processor_setup_cpuidle_states(pr);
 
 		/* Enable all cpuidle devices */
diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c
index 836bfe0..53e7ac9 100644
--- a/drivers/acpi/processor_perflib.c
+++ b/drivers/acpi/processor_perflib.c
@@ -340,6 +340,13 @@
 	if ((boot_cpu_data.x86 == 0x10 && boot_cpu_data.x86_model < 10)
 	    || boot_cpu_data.x86 == 0x11) {
 		rdmsr(MSR_AMD_PSTATE_DEF_BASE + index, lo, hi);
+		/*
+		 * MSR C001_0064+:
+		 * Bit 63: PstateEn. Read-write. If set, the P-state is valid.
+		 */
+		if (!(hi & BIT(31)))
+			return;
+
 		fid = lo & 0x3f;
 		did = (lo >> 6) & 7;
 		if (boot_cpu_data.x86 == 0x10)
diff --git a/drivers/atm/iphase.h b/drivers/atm/iphase.h
index 6a0955e..53ecac5 100644
--- a/drivers/atm/iphase.h
+++ b/drivers/atm/iphase.h
@@ -636,82 +636,82 @@
 #define SEG_BASE IPHASE5575_FRAG_CONTROL_REG_BASE  
 #define REASS_BASE IPHASE5575_REASS_CONTROL_REG_BASE  
 
-typedef volatile u_int  freg_t;
+typedef volatile u_int	ffreg_t;
 typedef u_int   rreg_t;
 
 typedef struct _ffredn_t {
-        freg_t  idlehead_high;  /* Idle cell header (high)              */
-        freg_t  idlehead_low;   /* Idle cell header (low)               */
-        freg_t  maxrate;        /* Maximum rate                         */
-        freg_t  stparms;        /* Traffic Management Parameters        */
-        freg_t  abrubr_abr;     /* ABRUBR Priority Byte 1, TCR Byte 0   */
-        freg_t  rm_type;        /*                                      */
-        u_int   filler5[0x17 - 0x06];
-        freg_t  cmd_reg;        /* Command register                     */
-        u_int   filler18[0x20 - 0x18];
-        freg_t  cbr_base;       /* CBR Pointer Base                     */
-        freg_t  vbr_base;       /* VBR Pointer Base                     */
-        freg_t  abr_base;       /* ABR Pointer Base                     */
-        freg_t  ubr_base;       /* UBR Pointer Base                     */
-        u_int   filler24;
-        freg_t  vbrwq_base;     /* VBR Wait Queue Base                  */
-        freg_t  abrwq_base;     /* ABR Wait Queue Base                  */
-        freg_t  ubrwq_base;     /* UBR Wait Queue Base                  */
-        freg_t  vct_base;       /* Main VC Table Base                   */
-        freg_t  vcte_base;      /* Extended Main VC Table Base          */
-        u_int   filler2a[0x2C - 0x2A];
-        freg_t  cbr_tab_beg;    /* CBR Table Begin                      */
-        freg_t  cbr_tab_end;    /* CBR Table End                        */
-        freg_t  cbr_pointer;    /* CBR Pointer                          */
-        u_int   filler2f[0x30 - 0x2F];
-        freg_t  prq_st_adr;     /* Packet Ready Queue Start Address     */
-        freg_t  prq_ed_adr;     /* Packet Ready Queue End Address       */
-        freg_t  prq_rd_ptr;     /* Packet Ready Queue read pointer      */
-        freg_t  prq_wr_ptr;     /* Packet Ready Queue write pointer     */
-        freg_t  tcq_st_adr;     /* Transmit Complete Queue Start Address*/
-        freg_t  tcq_ed_adr;     /* Transmit Complete Queue End Address  */
-        freg_t  tcq_rd_ptr;     /* Transmit Complete Queue read pointer */
-        freg_t  tcq_wr_ptr;     /* Transmit Complete Queue write pointer*/
-        u_int   filler38[0x40 - 0x38];
-        freg_t  queue_base;     /* Base address for PRQ and TCQ         */
-        freg_t  desc_base;      /* Base address of descriptor table     */
-        u_int   filler42[0x45 - 0x42];
-        freg_t  mode_reg_0;     /* Mode register 0                      */
-        freg_t  mode_reg_1;     /* Mode register 1                      */
-        freg_t  intr_status_reg;/* Interrupt Status register            */
-        freg_t  mask_reg;       /* Mask Register                        */
-        freg_t  cell_ctr_high1; /* Total cell transfer count (high)     */
-        freg_t  cell_ctr_lo1;   /* Total cell transfer count (low)      */
-        freg_t  state_reg;      /* Status register                      */
-        u_int   filler4c[0x58 - 0x4c];
-        freg_t  curr_desc_num;  /* Contains the current descriptor num  */
-        freg_t  next_desc;      /* Next descriptor                      */
-        freg_t  next_vc;        /* Next VC                              */
-        u_int   filler5b[0x5d - 0x5b];
-        freg_t  present_slot_cnt;/* Present slot count                  */
-        u_int   filler5e[0x6a - 0x5e];
-        freg_t  new_desc_num;   /* New descriptor number                */
-        freg_t  new_vc;         /* New VC                               */
-        freg_t  sched_tbl_ptr;  /* Schedule table pointer               */
-        freg_t  vbrwq_wptr;     /* VBR wait queue write pointer         */
-        freg_t  vbrwq_rptr;     /* VBR wait queue read pointer          */
-        freg_t  abrwq_wptr;     /* ABR wait queue write pointer         */
-        freg_t  abrwq_rptr;     /* ABR wait queue read pointer          */
-        freg_t  ubrwq_wptr;     /* UBR wait queue write pointer         */
-        freg_t  ubrwq_rptr;     /* UBR wait queue read pointer          */
-        freg_t  cbr_vc;         /* CBR VC                               */
-        freg_t  vbr_sb_vc;      /* VBR SB VC                            */
-        freg_t  abr_sb_vc;      /* ABR SB VC                            */
-        freg_t  ubr_sb_vc;      /* UBR SB VC                            */
-        freg_t  vbr_next_link;  /* VBR next link                        */
-        freg_t  abr_next_link;  /* ABR next link                        */
-        freg_t  ubr_next_link;  /* UBR next link                        */
-        u_int   filler7a[0x7c-0x7a];
-        freg_t  out_rate_head;  /* Out of rate head                     */
-        u_int   filler7d[0xca-0x7d]; /* pad out to full address space   */
-        freg_t  cell_ctr_high1_nc;/* Total cell transfer count (high)   */
-        freg_t  cell_ctr_lo1_nc;/* Total cell transfer count (low)      */
-        u_int   fillercc[0x100-0xcc]; /* pad out to full address space   */
+	ffreg_t	idlehead_high;	/* Idle cell header (high)		*/
+	ffreg_t	idlehead_low;	/* Idle cell header (low)		*/
+	ffreg_t	maxrate;	/* Maximum rate				*/
+	ffreg_t	stparms;	/* Traffic Management Parameters	*/
+	ffreg_t	abrubr_abr;	/* ABRUBR Priority Byte 1, TCR Byte 0	*/
+	ffreg_t	rm_type;	/*					*/
+	u_int	filler5[0x17 - 0x06];
+	ffreg_t	cmd_reg;	/* Command register			*/
+	u_int	filler18[0x20 - 0x18];
+	ffreg_t	cbr_base;	/* CBR Pointer Base			*/
+	ffreg_t	vbr_base;	/* VBR Pointer Base			*/
+	ffreg_t	abr_base;	/* ABR Pointer Base			*/
+	ffreg_t	ubr_base;	/* UBR Pointer Base			*/
+	u_int	filler24;
+	ffreg_t	vbrwq_base;	/* VBR Wait Queue Base			*/
+	ffreg_t	abrwq_base;	/* ABR Wait Queue Base			*/
+	ffreg_t	ubrwq_base;	/* UBR Wait Queue Base			*/
+	ffreg_t	vct_base;	/* Main VC Table Base			*/
+	ffreg_t	vcte_base;	/* Extended Main VC Table Base		*/
+	u_int	filler2a[0x2C - 0x2A];
+	ffreg_t	cbr_tab_beg;	/* CBR Table Begin			*/
+	ffreg_t	cbr_tab_end;	/* CBR Table End			*/
+	ffreg_t	cbr_pointer;	/* CBR Pointer				*/
+	u_int	filler2f[0x30 - 0x2F];
+	ffreg_t	prq_st_adr;	/* Packet Ready Queue Start Address	*/
+	ffreg_t	prq_ed_adr;	/* Packet Ready Queue End Address	*/
+	ffreg_t	prq_rd_ptr;	/* Packet Ready Queue read pointer	*/
+	ffreg_t	prq_wr_ptr;	/* Packet Ready Queue write pointer	*/
+	ffreg_t	tcq_st_adr;	/* Transmit Complete Queue Start Address*/
+	ffreg_t	tcq_ed_adr;	/* Transmit Complete Queue End Address	*/
+	ffreg_t	tcq_rd_ptr;	/* Transmit Complete Queue read pointer */
+	ffreg_t	tcq_wr_ptr;	/* Transmit Complete Queue write pointer*/
+	u_int	filler38[0x40 - 0x38];
+	ffreg_t	queue_base;	/* Base address for PRQ and TCQ		*/
+	ffreg_t	desc_base;	/* Base address of descriptor table	*/
+	u_int	filler42[0x45 - 0x42];
+	ffreg_t	mode_reg_0;	/* Mode register 0			*/
+	ffreg_t	mode_reg_1;	/* Mode register 1			*/
+	ffreg_t	intr_status_reg;/* Interrupt Status register		*/
+	ffreg_t	mask_reg;	/* Mask Register			*/
+	ffreg_t	cell_ctr_high1; /* Total cell transfer count (high)	*/
+	ffreg_t	cell_ctr_lo1;	/* Total cell transfer count (low)	*/
+	ffreg_t	state_reg;	/* Status register			*/
+	u_int	filler4c[0x58 - 0x4c];
+	ffreg_t	curr_desc_num;	/* Contains the current descriptor num	*/
+	ffreg_t	next_desc;	/* Next descriptor			*/
+	ffreg_t	next_vc;	/* Next VC				*/
+	u_int	filler5b[0x5d - 0x5b];
+	ffreg_t	present_slot_cnt;/* Present slot count			*/
+	u_int	filler5e[0x6a - 0x5e];
+	ffreg_t	new_desc_num;	/* New descriptor number		*/
+	ffreg_t	new_vc;		/* New VC				*/
+	ffreg_t	sched_tbl_ptr;	/* Schedule table pointer		*/
+	ffreg_t	vbrwq_wptr;	/* VBR wait queue write pointer		*/
+	ffreg_t	vbrwq_rptr;	/* VBR wait queue read pointer		*/
+	ffreg_t	abrwq_wptr;	/* ABR wait queue write pointer		*/
+	ffreg_t	abrwq_rptr;	/* ABR wait queue read pointer		*/
+	ffreg_t	ubrwq_wptr;	/* UBR wait queue write pointer		*/
+	ffreg_t	ubrwq_rptr;	/* UBR wait queue read pointer		*/
+	ffreg_t	cbr_vc;		/* CBR VC				*/
+	ffreg_t	vbr_sb_vc;	/* VBR SB VC				*/
+	ffreg_t	abr_sb_vc;	/* ABR SB VC				*/
+	ffreg_t	ubr_sb_vc;	/* UBR SB VC				*/
+	ffreg_t	vbr_next_link;	/* VBR next link			*/
+	ffreg_t	abr_next_link;	/* ABR next link			*/
+	ffreg_t	ubr_next_link;	/* UBR next link			*/
+	u_int	filler7a[0x7c-0x7a];
+	ffreg_t	out_rate_head;	/* Out of rate head			*/
+	u_int	filler7d[0xca-0x7d]; /* pad out to full address space	*/
+	ffreg_t	cell_ctr_high1_nc;/* Total cell transfer count (high)	*/
+	ffreg_t	cell_ctr_lo1_nc;/* Total cell transfer count (low)	*/
+	u_int	fillercc[0x100-0xcc]; /* pad out to full address space	 */
 } ffredn_t;
 
 typedef struct _rfredn_t {
diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c
index 46a213a..d9a6c94 100644
--- a/drivers/base/regmap/regmap-debugfs.c
+++ b/drivers/base/regmap/regmap-debugfs.c
@@ -121,8 +121,6 @@
 		c->max = p - 1;
 		list_add_tail(&c->list,
 			      &map->debugfs_off_cache);
-	} else {
-		return base;
 	}
 
 	/*
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index 42d5cb0..f00b059 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -1106,7 +1106,7 @@
  * @val_count: Number of registers to write
  *
  * This function is intended to be used for writing a large block of
- * data to be device either in single transfer or multiple transfer.
+ * data to the device either in single transfer or multiple transfer.
  *
  * A value of zero will be returned on success, a negative errno will
  * be returned in error cases.
diff --git a/drivers/bcma/bcma_private.h b/drivers/bcma/bcma_private.h
index 19e3fbf..cb0c454 100644
--- a/drivers/bcma/bcma_private.h
+++ b/drivers/bcma/bcma_private.h
@@ -94,11 +94,16 @@
 #ifdef CONFIG_BCMA_DRIVER_GPIO
 /* driver_gpio.c */
 int bcma_gpio_init(struct bcma_drv_cc *cc);
+int bcma_gpio_unregister(struct bcma_drv_cc *cc);
 #else
 static inline int bcma_gpio_init(struct bcma_drv_cc *cc)
 {
 	return -ENOTSUPP;
 }
+static inline int bcma_gpio_unregister(struct bcma_drv_cc *cc)
+{
+	return 0;
+}
 #endif /* CONFIG_BCMA_DRIVER_GPIO */
 
 #endif
diff --git a/drivers/bcma/driver_chipcommon_nflash.c b/drivers/bcma/driver_chipcommon_nflash.c
index dbda91e..1f0b83e 100644
--- a/drivers/bcma/driver_chipcommon_nflash.c
+++ b/drivers/bcma/driver_chipcommon_nflash.c
@@ -21,7 +21,7 @@
 	struct bcma_bus *bus = cc->core->bus;
 
 	if (bus->chipinfo.id != BCMA_CHIP_ID_BCM4706 &&
-	    cc->core->id.rev != 0x38) {
+	    cc->core->id.rev != 38) {
 		bcma_err(bus, "NAND flash on unsupported board!\n");
 		return -ENOTSUPP;
 	}
diff --git a/drivers/bcma/driver_gpio.c b/drivers/bcma/driver_gpio.c
index 9a6f585..71f755c 100644
--- a/drivers/bcma/driver_gpio.c
+++ b/drivers/bcma/driver_gpio.c
@@ -96,3 +96,8 @@
 
 	return gpiochip_add(chip);
 }
+
+int bcma_gpio_unregister(struct bcma_drv_cc *cc)
+{
+	return gpiochip_remove(&cc->gpio);
+}
diff --git a/drivers/bcma/main.c b/drivers/bcma/main.c
index 4a92f64..324f9de 100644
--- a/drivers/bcma/main.c
+++ b/drivers/bcma/main.c
@@ -268,6 +268,13 @@
 void bcma_bus_unregister(struct bcma_bus *bus)
 {
 	struct bcma_device *cores[3];
+	int err;
+
+	err = bcma_gpio_unregister(&bus->drv_cc);
+	if (err == -EBUSY)
+		bcma_err(bus, "Some GPIOs are still in use.\n");
+	else if (err)
+		bcma_err(bus, "Can not unregister GPIO driver: %i\n", err);
 
 	cores[0] = bcma_find_core(bus, BCMA_CORE_MIPS_74K);
 	cores[1] = bcma_find_core(bus, BCMA_CORE_PCIE);
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index f58a4a4..2b8303a 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -168,7 +168,7 @@
 }
 
 /* must hold resource->req_lock */
-static void start_new_tl_epoch(struct drbd_tconn *tconn)
+void start_new_tl_epoch(struct drbd_tconn *tconn)
 {
 	/* no point closing an epoch, if it is empty, anyways. */
 	if (tconn->current_tle_writes == 0)
diff --git a/drivers/block/drbd/drbd_req.h b/drivers/block/drbd/drbd_req.h
index 016de6b..c08d229 100644
--- a/drivers/block/drbd/drbd_req.h
+++ b/drivers/block/drbd/drbd_req.h
@@ -267,6 +267,7 @@
 	int error;
 };
 
+extern void start_new_tl_epoch(struct drbd_tconn *tconn);
 extern void drbd_req_destroy(struct kref *kref);
 extern void _req_may_be_done(struct drbd_request *req,
 		struct bio_and_error *m);
diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c
index 53bf618..0fe220c 100644
--- a/drivers/block/drbd/drbd_state.c
+++ b/drivers/block/drbd/drbd_state.c
@@ -931,6 +931,7 @@
 	enum drbd_state_rv rv = SS_SUCCESS;
 	enum sanitize_state_warnings ssw;
 	struct after_state_chg_work *ascw;
+	bool did_remote, should_do_remote;
 
 	os = drbd_read_state(mdev);
 
@@ -981,11 +982,17 @@
 	    (os.disk != D_DISKLESS && ns.disk == D_DISKLESS))
 		atomic_inc(&mdev->local_cnt);
 
+	did_remote = drbd_should_do_remote(mdev->state);
 	mdev->state.i = ns.i;
+	should_do_remote = drbd_should_do_remote(mdev->state);
 	mdev->tconn->susp = ns.susp;
 	mdev->tconn->susp_nod = ns.susp_nod;
 	mdev->tconn->susp_fen = ns.susp_fen;
 
+	/* put replicated vs not-replicated requests in seperate epochs */
+	if (did_remote != should_do_remote)
+		start_new_tl_epoch(mdev->tconn);
+
 	if (os.disk == D_ATTACHING && ns.disk >= D_NEGOTIATING)
 		drbd_print_uuids(mdev, "attached to UUIDs");
 
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 9694dd9..3fd1009 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -626,12 +626,13 @@
 		}
 	}
 
-	if (cmdto_cnt && !test_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags)) {
+	if (cmdto_cnt) {
 		print_tags(port->dd, "timed out", tagaccum, cmdto_cnt);
-
-		mtip_restart_port(port);
+		if (!test_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags)) {
+			mtip_restart_port(port);
+			wake_up_interruptible(&port->svc_wait);
+		}
 		clear_bit(MTIP_PF_EH_ACTIVE_BIT, &port->flags);
-		wake_up_interruptible(&port->svc_wait);
 	}
 
 	if (port->ic_pause_timer) {
@@ -3887,7 +3888,12 @@
 	 * Delete our gendisk structure. This also removes the device
 	 * from /dev
 	 */
-	del_gendisk(dd->disk);
+	if (dd->disk) {
+		if (dd->disk->queue)
+			del_gendisk(dd->disk);
+		else
+			put_disk(dd->disk);
+	}
 
 	spin_lock(&rssd_index_lock);
 	ida_remove(&rssd_index_ida, dd->index);
@@ -3921,7 +3927,13 @@
 		"Shutting down %s ...\n", dd->disk->disk_name);
 
 	/* Delete our gendisk structure, and cleanup the blk queue. */
-	del_gendisk(dd->disk);
+	if (dd->disk) {
+		if (dd->disk->queue)
+			del_gendisk(dd->disk);
+		else
+			put_disk(dd->disk);
+	}
+
 
 	spin_lock(&rssd_index_lock);
 	ida_remove(&rssd_index_ida, dd->index);
diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c
index 564156a..5814deb 100644
--- a/drivers/block/sunvdc.c
+++ b/drivers/block/sunvdc.c
@@ -461,7 +461,7 @@
 	int op_len, err;
 	void *req_buf;
 
-	if (!(((u64)1 << ((u64)op - 1)) & port->operations))
+	if (!(((u64)1 << (u64)op) & port->operations))
 		return -EOPNOTSUPP;
 
 	switch (op) {
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index 74374fb..5ac841f 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -161,10 +161,12 @@
 static void make_response(struct xen_blkif *blkif, u64 id,
 			  unsigned short op, int st);
 
-#define foreach_grant(pos, rbtree, node) \
-	for ((pos) = container_of(rb_first((rbtree)), typeof(*(pos)), node); \
+#define foreach_grant_safe(pos, n, rbtree, node) \
+	for ((pos) = container_of(rb_first((rbtree)), typeof(*(pos)), node), \
+	     (n) = rb_next(&(pos)->node); \
 	     &(pos)->node != NULL; \
-	     (pos) = container_of(rb_next(&(pos)->node), typeof(*(pos)), node))
+	     (pos) = container_of(n, typeof(*(pos)), node), \
+	     (n) = (&(pos)->node != NULL) ? rb_next(&(pos)->node) : NULL)
 
 
 static void add_persistent_gnt(struct rb_root *root,
@@ -217,10 +219,11 @@
 	struct gnttab_unmap_grant_ref unmap[BLKIF_MAX_SEGMENTS_PER_REQUEST];
 	struct page *pages[BLKIF_MAX_SEGMENTS_PER_REQUEST];
 	struct persistent_gnt *persistent_gnt;
+	struct rb_node *n;
 	int ret = 0;
 	int segs_to_unmap = 0;
 
-	foreach_grant(persistent_gnt, root, node) {
+	foreach_grant_safe(persistent_gnt, n, root, node) {
 		BUG_ON(persistent_gnt->handle ==
 			BLKBACK_INVALID_HANDLE);
 		gnttab_set_unmap_op(&unmap[segs_to_unmap],
@@ -230,9 +233,6 @@
 			persistent_gnt->handle);
 
 		pages[segs_to_unmap] = persistent_gnt->page;
-		rb_erase(&persistent_gnt->node, root);
-		kfree(persistent_gnt);
-		num--;
 
 		if (++segs_to_unmap == BLKIF_MAX_SEGMENTS_PER_REQUEST ||
 			!rb_next(&persistent_gnt->node)) {
@@ -241,6 +241,10 @@
 			BUG_ON(ret);
 			segs_to_unmap = 0;
 		}
+
+		rb_erase(&persistent_gnt->node, root);
+		kfree(persistent_gnt);
+		num--;
 	}
 	BUG_ON(num != 0);
 }
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 96e9b00..11043c1 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -792,6 +792,7 @@
 {
 	struct llist_node *all_gnts;
 	struct grant *persistent_gnt;
+	struct llist_node *n;
 
 	/* Prevent new requests being issued until we fix things up. */
 	spin_lock_irq(&info->io_lock);
@@ -804,7 +805,7 @@
 	/* Remove all persistent grants */
 	if (info->persistent_gnts_c) {
 		all_gnts = llist_del_all(&info->persistent_gnts);
-		llist_for_each_entry(persistent_gnt, all_gnts, node) {
+		llist_for_each_entry_safe(persistent_gnt, n, all_gnts, node) {
 			gnttab_end_foreign_access(persistent_gnt->gref, 0, 0UL);
 			__free_page(pfn_to_page(persistent_gnt->pfn));
 			kfree(persistent_gnt);
@@ -835,7 +836,7 @@
 static void blkif_completion(struct blk_shadow *s, struct blkfront_info *info,
 			     struct blkif_response *bret)
 {
-	int i;
+	int i = 0;
 	struct bio_vec *bvec;
 	struct req_iterator iter;
 	unsigned long flags;
@@ -852,7 +853,8 @@
 		 */
 		rq_for_each_segment(bvec, s->request, iter) {
 			BUG_ON((bvec->bv_offset + bvec->bv_len) > PAGE_SIZE);
-			i = offset >> PAGE_SHIFT;
+			if (bvec->bv_offset < offset)
+				i++;
 			BUG_ON(i >= s->req.u.rw.nr_segments);
 			shared_data = kmap_atomic(
 				pfn_to_page(s->grants_used[i]->pfn));
@@ -861,7 +863,7 @@
 				bvec->bv_len);
 			bvec_kunmap_irq(bvec_data, &flags);
 			kunmap_atomic(shared_data);
-			offset += bvec->bv_len;
+			offset = bvec->bv_offset + bvec->bv_len;
 		}
 	}
 	/* Add the persistent grant into the list of free grants */
diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c
index b00000e..33c9a44 100644
--- a/drivers/bluetooth/ath3k.c
+++ b/drivers/bluetooth/ath3k.c
@@ -77,10 +77,15 @@
 	{ USB_DEVICE(0x0CF3, 0x311D) },
 	{ USB_DEVICE(0x13d3, 0x3375) },
 	{ USB_DEVICE(0x04CA, 0x3005) },
+	{ USB_DEVICE(0x04CA, 0x3006) },
+	{ USB_DEVICE(0x04CA, 0x3008) },
 	{ USB_DEVICE(0x13d3, 0x3362) },
 	{ USB_DEVICE(0x0CF3, 0xE004) },
 	{ USB_DEVICE(0x0930, 0x0219) },
 	{ USB_DEVICE(0x0489, 0xe057) },
+	{ USB_DEVICE(0x13d3, 0x3393) },
+	{ USB_DEVICE(0x0489, 0xe04e) },
+	{ USB_DEVICE(0x0489, 0xe056) },
 
 	/* Atheros AR5BBU12 with sflash firmware */
 	{ USB_DEVICE(0x0489, 0xE02C) },
@@ -104,10 +109,15 @@
 	{ USB_DEVICE(0x0cf3, 0x311D), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3375), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3005), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x04ca, 0x3006), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x04ca, 0x3008), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0cf3, 0xe004), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0489, 0xe057), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x13d3, 0x3393), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x0489, 0xe04e), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x0489, 0xe056), .driver_info = BTUSB_ATH3012 },
 
 	/* Atheros AR5BBU22 with sflash firmware */
 	{ USB_DEVICE(0x0489, 0xE03C), .driver_info = BTUSB_ATH3012 },
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index a1d4ede..7e351e3 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -135,10 +135,15 @@
 	{ USB_DEVICE(0x0cf3, 0x311d), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3375), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3005), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x04ca, 0x3006), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x04ca, 0x3008), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0cf3, 0xe004), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0489, 0xe057), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x13d3, 0x3393), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x0489, 0xe04e), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x0489, 0xe056), .driver_info = BTUSB_ATH3012 },
 
 	/* Atheros AR5BBU12 with sflash firmware */
 	{ USB_DEVICE(0x0489, 0xe02c), .driver_info = BTUSB_IGNORE },
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 684b0d5..ee4dbea 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -2062,7 +2062,8 @@
 	/* Disable interrupts for vqs */
 	vdev->config->reset(vdev);
 	/* Finish up work that's lined up */
-	cancel_work_sync(&portdev->control_work);
+	if (use_multiport(portdev))
+		cancel_work_sync(&portdev->control_work);
 
 	list_for_each_entry_safe(port, port2, &portdev->ports, list)
 		unplug_port(port);
diff --git a/drivers/clk/mvebu/clk-cpu.c b/drivers/clk/mvebu/clk-cpu.c
index ff004578..9dd2551 100644
--- a/drivers/clk/mvebu/clk-cpu.c
+++ b/drivers/clk/mvebu/clk-cpu.c
@@ -124,7 +124,7 @@
 
 	clks = kzalloc(ncpus * sizeof(*clks), GFP_KERNEL);
 	if (WARN_ON(!clks))
-		return;
+		goto clks_out;
 
 	for_each_node_by_type(dn, "cpu") {
 		struct clk_init_data init;
@@ -134,11 +134,11 @@
 		int cpu, err;
 
 		if (WARN_ON(!clk_name))
-			return;
+			goto bail_out;
 
 		err = of_property_read_u32(dn, "reg", &cpu);
 		if (WARN_ON(err))
-			return;
+			goto bail_out;
 
 		sprintf(clk_name, "cpu%d", cpu);
 		parent_clk = of_clk_get(node, 0);
@@ -167,6 +167,9 @@
 	return;
 bail_out:
 	kfree(clks);
+	while(ncpus--)
+		kfree(cpuclk[ncpus].clk_name);
+clks_out:
 	kfree(cpuclk);
 }
 
diff --git a/drivers/cpufreq/Kconfig.x86 b/drivers/cpufreq/Kconfig.x86
index 934854a..7227cd7 100644
--- a/drivers/cpufreq/Kconfig.x86
+++ b/drivers/cpufreq/Kconfig.x86
@@ -106,7 +106,7 @@
 config X86_POWERNOW_K8
 	tristate "AMD Opteron/Athlon64 PowerNow!"
 	select CPU_FREQ_TABLE
-	depends on ACPI && ACPI_PROCESSOR
+	depends on ACPI && ACPI_PROCESSOR && X86_ACPI_CPUFREQ
 	help
 	  This adds the CPUFreq driver for K8/early Opteron/Athlon64 processors.
 	  Support for K10 and newer processors is now in acpi-cpufreq.
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index 0d048f6..7b0d49d 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -1030,4 +1030,11 @@
 late_initcall(acpi_cpufreq_init);
 module_exit(acpi_cpufreq_exit);
 
+static const struct x86_cpu_id acpi_cpufreq_ids[] = {
+	X86_FEATURE_MATCH(X86_FEATURE_ACPI),
+	X86_FEATURE_MATCH(X86_FEATURE_HW_PSTATE),
+	{}
+};
+MODULE_DEVICE_TABLE(x86cpu, acpi_cpufreq_ids);
+
 MODULE_ALIAS("acpi");
diff --git a/drivers/cpufreq/cpufreq-cpu0.c b/drivers/cpufreq/cpufreq-cpu0.c
index 52bf36d..debc5a7 100644
--- a/drivers/cpufreq/cpufreq-cpu0.c
+++ b/drivers/cpufreq/cpufreq-cpu0.c
@@ -71,12 +71,15 @@
 	}
 
 	if (cpu_reg) {
+		rcu_read_lock();
 		opp = opp_find_freq_ceil(cpu_dev, &freq_Hz);
 		if (IS_ERR(opp)) {
+			rcu_read_unlock();
 			pr_err("failed to find OPP for %ld\n", freq_Hz);
 			return PTR_ERR(opp);
 		}
 		volt = opp_get_voltage(opp);
+		rcu_read_unlock();
 		tol = volt * voltage_tolerance / 100;
 		volt_old = regulator_get_voltage(cpu_reg);
 	}
@@ -236,12 +239,14 @@
 		 */
 		for (i = 0; freq_table[i].frequency != CPUFREQ_TABLE_END; i++)
 			;
+		rcu_read_lock();
 		opp = opp_find_freq_exact(cpu_dev,
 				freq_table[0].frequency * 1000, true);
 		min_uV = opp_get_voltage(opp);
 		opp = opp_find_freq_exact(cpu_dev,
 				freq_table[i-1].frequency * 1000, true);
 		max_uV = opp_get_voltage(opp);
+		rcu_read_unlock();
 		ret = regulator_set_voltage_time(cpu_reg, min_uV, max_uV);
 		if (ret > 0)
 			transition_latency += ret * 1000;
diff --git a/drivers/cpufreq/omap-cpufreq.c b/drivers/cpufreq/omap-cpufreq.c
index 1f3417a..97102b0 100644
--- a/drivers/cpufreq/omap-cpufreq.c
+++ b/drivers/cpufreq/omap-cpufreq.c
@@ -110,13 +110,16 @@
 	freq = ret;
 
 	if (mpu_reg) {
+		rcu_read_lock();
 		opp = opp_find_freq_ceil(mpu_dev, &freq);
 		if (IS_ERR(opp)) {
+			rcu_read_unlock();
 			dev_err(mpu_dev, "%s: unable to find MPU OPP for %d\n",
 				__func__, freqs.new);
 			return -EINVAL;
 		}
 		volt = opp_get_voltage(opp);
+		rcu_read_unlock();
 		tol = volt * OPP_TOLERANCE / 100;
 		volt_old = regulator_get_voltage(mpu_reg);
 	}
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 53766f3..3b36797 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -994,6 +994,11 @@
  * @freq:	The frequency given to target function
  * @flags:	Flags handed from devfreq framework.
  *
+ * Locking: This function must be called under rcu_read_lock(). opp is a rcu
+ * protected pointer. The reason for the same is that the opp pointer which is
+ * returned will remain valid for use with opp_get_{voltage, freq} only while
+ * under the locked area. The pointer returned must be used prior to unlocking
+ * with rcu_read_unlock() to maintain the integrity of the pointer.
  */
 struct opp *devfreq_recommended_opp(struct device *dev, unsigned long *freq,
 				    u32 flags)
diff --git a/drivers/devfreq/exynos4_bus.c b/drivers/devfreq/exynos4_bus.c
index 80c745e..46d94e9 100644
--- a/drivers/devfreq/exynos4_bus.c
+++ b/drivers/devfreq/exynos4_bus.c
@@ -73,6 +73,16 @@
 #define EX4210_LV_NUM	(LV_2 + 1)
 #define EX4x12_LV_NUM	(LV_4 + 1)
 
+/**
+ * struct busfreq_opp_info - opp information for bus
+ * @rate:	Frequency in hertz
+ * @volt:	Voltage in microvolts corresponding to this OPP
+ */
+struct busfreq_opp_info {
+	unsigned long rate;
+	unsigned long volt;
+};
+
 struct busfreq_data {
 	enum exynos4_busf_type type;
 	struct device *dev;
@@ -80,7 +90,7 @@
 	bool disabled;
 	struct regulator *vdd_int;
 	struct regulator *vdd_mif; /* Exynos4412/4212 only */
-	struct opp *curr_opp;
+	struct busfreq_opp_info curr_oppinfo;
 	struct exynos4_ppmu dmc[2];
 
 	struct notifier_block pm_notifier;
@@ -296,13 +306,14 @@
 };
 
 
-static int exynos4210_set_busclk(struct busfreq_data *data, struct opp *opp)
+static int exynos4210_set_busclk(struct busfreq_data *data,
+				 struct busfreq_opp_info *oppi)
 {
 	unsigned int index;
 	unsigned int tmp;
 
 	for (index = LV_0; index < EX4210_LV_NUM; index++)
-		if (opp_get_freq(opp) == exynos4210_busclk_table[index].clk)
+		if (oppi->rate == exynos4210_busclk_table[index].clk)
 			break;
 
 	if (index == EX4210_LV_NUM)
@@ -361,13 +372,14 @@
 	return 0;
 }
 
-static int exynos4x12_set_busclk(struct busfreq_data *data, struct opp *opp)
+static int exynos4x12_set_busclk(struct busfreq_data *data,
+				 struct busfreq_opp_info *oppi)
 {
 	unsigned int index;
 	unsigned int tmp;
 
 	for (index = LV_0; index < EX4x12_LV_NUM; index++)
-		if (opp_get_freq(opp) == exynos4x12_mifclk_table[index].clk)
+		if (oppi->rate == exynos4x12_mifclk_table[index].clk)
 			break;
 
 	if (index == EX4x12_LV_NUM)
@@ -576,11 +588,12 @@
 	return -EINVAL;
 }
 
-static int exynos4_bus_setvolt(struct busfreq_data *data, struct opp *opp,
-			       struct opp *oldopp)
+static int exynos4_bus_setvolt(struct busfreq_data *data,
+			       struct busfreq_opp_info *oppi,
+			       struct busfreq_opp_info *oldoppi)
 {
 	int err = 0, tmp;
-	unsigned long volt = opp_get_voltage(opp);
+	unsigned long volt = oppi->volt;
 
 	switch (data->type) {
 	case TYPE_BUSF_EXYNOS4210:
@@ -595,11 +608,11 @@
 		if (err)
 			break;
 
-		tmp = exynos4x12_get_intspec(opp_get_freq(opp));
+		tmp = exynos4x12_get_intspec(oppi->rate);
 		if (tmp < 0) {
 			err = tmp;
 			regulator_set_voltage(data->vdd_mif,
-					      opp_get_voltage(oldopp),
+					      oldoppi->volt,
 					      MAX_SAFEVOLT);
 			break;
 		}
@@ -609,7 +622,7 @@
 		/*  Try to recover */
 		if (err)
 			regulator_set_voltage(data->vdd_mif,
-					      opp_get_voltage(oldopp),
+					      oldoppi->volt,
 					      MAX_SAFEVOLT);
 		break;
 	default:
@@ -626,17 +639,26 @@
 	struct platform_device *pdev = container_of(dev, struct platform_device,
 						    dev);
 	struct busfreq_data *data = platform_get_drvdata(pdev);
-	struct opp *opp = devfreq_recommended_opp(dev, _freq, flags);
-	unsigned long freq = opp_get_freq(opp);
-	unsigned long old_freq = opp_get_freq(data->curr_opp);
+	struct opp *opp;
+	unsigned long freq;
+	unsigned long old_freq = data->curr_oppinfo.rate;
+	struct busfreq_opp_info	new_oppinfo;
 
-	if (IS_ERR(opp))
+	rcu_read_lock();
+	opp = devfreq_recommended_opp(dev, _freq, flags);
+	if (IS_ERR(opp)) {
+		rcu_read_unlock();
 		return PTR_ERR(opp);
+	}
+	new_oppinfo.rate = opp_get_freq(opp);
+	new_oppinfo.volt = opp_get_voltage(opp);
+	rcu_read_unlock();
+	freq = new_oppinfo.rate;
 
 	if (old_freq == freq)
 		return 0;
 
-	dev_dbg(dev, "targetting %lukHz %luuV\n", freq, opp_get_voltage(opp));
+	dev_dbg(dev, "targetting %lukHz %luuV\n", freq, new_oppinfo.volt);
 
 	mutex_lock(&data->lock);
 
@@ -644,17 +666,18 @@
 		goto out;
 
 	if (old_freq < freq)
-		err = exynos4_bus_setvolt(data, opp, data->curr_opp);
+		err = exynos4_bus_setvolt(data, &new_oppinfo,
+					  &data->curr_oppinfo);
 	if (err)
 		goto out;
 
 	if (old_freq != freq) {
 		switch (data->type) {
 		case TYPE_BUSF_EXYNOS4210:
-			err = exynos4210_set_busclk(data, opp);
+			err = exynos4210_set_busclk(data, &new_oppinfo);
 			break;
 		case TYPE_BUSF_EXYNOS4x12:
-			err = exynos4x12_set_busclk(data, opp);
+			err = exynos4x12_set_busclk(data, &new_oppinfo);
 			break;
 		default:
 			err = -EINVAL;
@@ -664,11 +687,12 @@
 		goto out;
 
 	if (old_freq > freq)
-		err = exynos4_bus_setvolt(data, opp, data->curr_opp);
+		err = exynos4_bus_setvolt(data, &new_oppinfo,
+					  &data->curr_oppinfo);
 	if (err)
 		goto out;
 
-	data->curr_opp = opp;
+	data->curr_oppinfo = new_oppinfo;
 out:
 	mutex_unlock(&data->lock);
 	return err;
@@ -702,7 +726,7 @@
 
 	exynos4_read_ppmu(data);
 	busier_dmc = exynos4_get_busier_dmc(data);
-	stat->current_frequency = opp_get_freq(data->curr_opp);
+	stat->current_frequency = data->curr_oppinfo.rate;
 
 	if (busier_dmc)
 		addr = S5P_VA_DMC1;
@@ -933,6 +957,7 @@
 	struct busfreq_data *data = container_of(this, struct busfreq_data,
 						 pm_notifier);
 	struct opp *opp;
+	struct busfreq_opp_info	new_oppinfo;
 	unsigned long maxfreq = ULONG_MAX;
 	int err = 0;
 
@@ -943,18 +968,29 @@
 
 		data->disabled = true;
 
+		rcu_read_lock();
 		opp = opp_find_freq_floor(data->dev, &maxfreq);
+		if (IS_ERR(opp)) {
+			rcu_read_unlock();
+			dev_err(data->dev, "%s: unable to find a min freq\n",
+				__func__);
+			return PTR_ERR(opp);
+		}
+		new_oppinfo.rate = opp_get_freq(opp);
+		new_oppinfo.volt = opp_get_voltage(opp);
+		rcu_read_unlock();
 
-		err = exynos4_bus_setvolt(data, opp, data->curr_opp);
+		err = exynos4_bus_setvolt(data, &new_oppinfo,
+					  &data->curr_oppinfo);
 		if (err)
 			goto unlock;
 
 		switch (data->type) {
 		case TYPE_BUSF_EXYNOS4210:
-			err = exynos4210_set_busclk(data, opp);
+			err = exynos4210_set_busclk(data, &new_oppinfo);
 			break;
 		case TYPE_BUSF_EXYNOS4x12:
-			err = exynos4x12_set_busclk(data, opp);
+			err = exynos4x12_set_busclk(data, &new_oppinfo);
 			break;
 		default:
 			err = -EINVAL;
@@ -962,7 +998,7 @@
 		if (err)
 			goto unlock;
 
-		data->curr_opp = opp;
+		data->curr_oppinfo = new_oppinfo;
 unlock:
 		mutex_unlock(&data->lock);
 		if (err)
@@ -1027,13 +1063,17 @@
 		}
 	}
 
+	rcu_read_lock();
 	opp = opp_find_freq_floor(dev, &exynos4_devfreq_profile.initial_freq);
 	if (IS_ERR(opp)) {
+		rcu_read_unlock();
 		dev_err(dev, "Invalid initial frequency %lu kHz.\n",
 			exynos4_devfreq_profile.initial_freq);
 		return PTR_ERR(opp);
 	}
-	data->curr_opp = opp;
+	data->curr_oppinfo.rate = opp_get_freq(opp);
+	data->curr_oppinfo.volt = opp_get_voltage(opp);
+	rcu_read_unlock();
 
 	platform_set_drvdata(pdev, data);
 
diff --git a/drivers/dma/imx-dma.c b/drivers/dma/imx-dma.c
index dbf0e6f..a7dcf78 100644
--- a/drivers/dma/imx-dma.c
+++ b/drivers/dma/imx-dma.c
@@ -684,9 +684,8 @@
 			break;
 		}
 
-		imxdmac->hw_chaining = 1;
-		if (!imxdma_hw_chain(imxdmac))
-			return -EINVAL;
+		imxdmac->hw_chaining = 0;
+
 		imxdmac->ccr_from_device = (mode | IMX_DMA_TYPE_FIFO) |
 			((IMX_DMA_MEMSIZE_32 | IMX_DMA_TYPE_LINEAR) << 2) |
 			CCR_REN;
diff --git a/drivers/dma/ioat/dma_v3.c b/drivers/dma/ioat/dma_v3.c
index e5fc944..3e9d669 100644
--- a/drivers/dma/ioat/dma_v3.c
+++ b/drivers/dma/ioat/dma_v3.c
@@ -951,7 +951,7 @@
 			goto free_resources;
 		}
 	}
-	dma_sync_single_for_device(dev, dest_dma, PAGE_SIZE, DMA_TO_DEVICE);
+	dma_sync_single_for_device(dev, dest_dma, PAGE_SIZE, DMA_FROM_DEVICE);
 
 	/* skip validate if the capability is not present */
 	if (!dma_has_cap(DMA_XOR_VAL, dma_chan->device->cap_mask))
diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c
index c39e61b..3cad856 100644
--- a/drivers/dma/tegra20-apb-dma.c
+++ b/drivers/dma/tegra20-apb-dma.c
@@ -266,6 +266,7 @@
 		if (async_tx_test_ack(&dma_desc->txd)) {
 			list_del(&dma_desc->node);
 			spin_unlock_irqrestore(&tdc->lock, flags);
+			dma_desc->txd.flags = 0;
 			return dma_desc;
 		}
 	}
@@ -1050,7 +1051,9 @@
 					TEGRA_APBDMA_AHBSEQ_WRAP_SHIFT;
 	ahb_seq |= TEGRA_APBDMA_AHBSEQ_BUS_WIDTH_32;
 
-	csr |= TEGRA_APBDMA_CSR_FLOW | TEGRA_APBDMA_CSR_IE_EOC;
+	csr |= TEGRA_APBDMA_CSR_FLOW;
+	if (flags & DMA_PREP_INTERRUPT)
+		csr |= TEGRA_APBDMA_CSR_IE_EOC;
 	csr |= tdc->dma_sconfig.slave_id << TEGRA_APBDMA_CSR_REQ_SEL_SHIFT;
 
 	apb_seq |= TEGRA_APBDMA_APBSEQ_WRAP_WORD_1;
@@ -1095,7 +1098,8 @@
 		mem += len;
 	}
 	sg_req->last_sg = true;
-	dma_desc->txd.flags = 0;
+	if (flags & DMA_CTRL_ACK)
+		dma_desc->txd.flags = DMA_CTRL_ACK;
 
 	/*
 	 * Make sure that mode should not be conflicting with currently
diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index 281f566..d1e9eb1 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -340,7 +340,7 @@
 	/*
 	 * Alocate and fill the csrow/channels structs
 	 */
-	mci->csrows = kcalloc(sizeof(*mci->csrows), tot_csrows, GFP_KERNEL);
+	mci->csrows = kcalloc(tot_csrows, sizeof(*mci->csrows), GFP_KERNEL);
 	if (!mci->csrows)
 		goto error;
 	for (row = 0; row < tot_csrows; row++) {
@@ -351,7 +351,7 @@
 		csr->csrow_idx = row;
 		csr->mci = mci;
 		csr->nr_channels = tot_channels;
-		csr->channels = kcalloc(sizeof(*csr->channels), tot_channels,
+		csr->channels = kcalloc(tot_channels, sizeof(*csr->channels),
 					GFP_KERNEL);
 		if (!csr->channels)
 			goto error;
@@ -369,7 +369,7 @@
 	/*
 	 * Allocate and fill the dimm structs
 	 */
-	mci->dimms  = kcalloc(sizeof(*mci->dimms), tot_dimms, GFP_KERNEL);
+	mci->dimms  = kcalloc(tot_dimms, sizeof(*mci->dimms), GFP_KERNEL);
 	if (!mci->dimms)
 		goto error;
 
diff --git a/drivers/edac/edac_pci_sysfs.c b/drivers/edac/edac_pci_sysfs.c
index dc6e905..0056c4d 100644
--- a/drivers/edac/edac_pci_sysfs.c
+++ b/drivers/edac/edac_pci_sysfs.c
@@ -256,7 +256,7 @@
 	struct edac_pci_dev_attribute *edac_pci_dev;
 	edac_pci_dev = (struct edac_pci_dev_attribute *)attr;
 
-	if (edac_pci_dev->show)
+	if (edac_pci_dev->store)
 		return edac_pci_dev->store(edac_pci_dev->value, buffer, count);
 	return -EIO;
 }
diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c
index fd3ae62..982f1f5 100644
--- a/drivers/firmware/dmi_scan.c
+++ b/drivers/firmware/dmi_scan.c
@@ -471,7 +471,7 @@
 	char __iomem *p, *q;
 	int rc;
 
-	if (efi_enabled) {
+	if (efi_enabled(EFI_CONFIG_TABLES)) {
 		if (efi.smbios == EFI_INVALID_TABLE_ADDR)
 			goto error;
 
diff --git a/drivers/firmware/efivars.c b/drivers/firmware/efivars.c
index 7b1c374..f5596db 100644
--- a/drivers/firmware/efivars.c
+++ b/drivers/firmware/efivars.c
@@ -674,7 +674,7 @@
 		err = -EACCES;
 		break;
 	case EFI_NOT_FOUND:
-		err = -ENOENT;
+		err = -EIO;
 		break;
 	default:
 		err = -EINVAL;
@@ -793,6 +793,7 @@
 		spin_unlock(&efivars->lock);
 		efivar_unregister(var);
 		drop_nlink(inode);
+		d_delete(file->f_dentry);
 		dput(file->f_dentry);
 
 	} else {
@@ -994,7 +995,7 @@
 		list_del(&var->list);
 		spin_unlock(&efivars->lock);
 		efivar_unregister(var);
-		drop_nlink(dir);
+		drop_nlink(dentry->d_inode);
 		dput(dentry);
 		return 0;
 	}
@@ -1782,7 +1783,7 @@
 	printk(KERN_INFO "EFI Variables Facility v%s %s\n", EFIVARS_VERSION,
 	       EFIVARS_DATE);
 
-	if (!efi_enabled)
+	if (!efi_enabled(EFI_RUNTIME_SERVICES))
 		return 0;
 
 	/* For now we'll register the efi directory at /sys/firmware/efi */
@@ -1822,7 +1823,7 @@
 static void __exit
 efivars_exit(void)
 {
-	if (efi_enabled) {
+	if (efi_enabled(EFI_RUNTIME_SERVICES)) {
 		unregister_efivars(&__efivars);
 		kobject_put(efi_kobj);
 	}
diff --git a/drivers/firmware/iscsi_ibft_find.c b/drivers/firmware/iscsi_ibft_find.c
index 4da4eb9..2224f1d 100644
--- a/drivers/firmware/iscsi_ibft_find.c
+++ b/drivers/firmware/iscsi_ibft_find.c
@@ -99,7 +99,7 @@
 	/* iBFT 1.03 section 1.4.3.1 mandates that UEFI machines will
 	 * only use ACPI for this */
 
-	if (!efi_enabled)
+	if (!efi_enabled(EFI_BOOT))
 		find_ibft_in_mem();
 
 	if (ibft_addr) {
diff --git a/drivers/gpu/drm/exynos/Kconfig b/drivers/gpu/drm/exynos/Kconfig
index 1d1f1e5..046bcda 100644
--- a/drivers/gpu/drm/exynos/Kconfig
+++ b/drivers/gpu/drm/exynos/Kconfig
@@ -24,7 +24,7 @@
 
 config DRM_EXYNOS_FIMD
 	bool "Exynos DRM FIMD"
-	depends on DRM_EXYNOS && !FB_S3C
+	depends on DRM_EXYNOS && !FB_S3C && !ARCH_MULTIPLATFORM
 	help
 	  Choose this option if you want to use Exynos FIMD for DRM.
 
@@ -48,7 +48,7 @@
 
 config DRM_EXYNOS_IPP
 	bool "Exynos DRM IPP"
-	depends on DRM_EXYNOS
+	depends on DRM_EXYNOS && !ARCH_MULTIPLATFORM
 	help
 	  Choose this option if you want to use IPP feature for DRM.
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_connector.c b/drivers/gpu/drm/exynos/exynos_drm_connector.c
index ab37437..4c5b685 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_connector.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_connector.c
@@ -18,7 +18,6 @@
 #include "exynos_drm_drv.h"
 #include "exynos_drm_encoder.h"
 
-#define MAX_EDID 256
 #define to_exynos_connector(x)	container_of(x, struct exynos_drm_connector,\
 				drm_connector)
 
@@ -96,7 +95,9 @@
 					to_exynos_connector(connector);
 	struct exynos_drm_manager *manager = exynos_connector->manager;
 	struct exynos_drm_display_ops *display_ops = manager->display_ops;
-	unsigned int count;
+	struct edid *edid = NULL;
+	unsigned int count = 0;
+	int ret;
 
 	DRM_DEBUG_KMS("%s\n", __FILE__);
 
@@ -114,27 +115,21 @@
 	 * because lcd panel has only one mode.
 	 */
 	if (display_ops->get_edid) {
-		int ret;
-		void *edid;
-
-		edid = kzalloc(MAX_EDID, GFP_KERNEL);
-		if (!edid) {
-			DRM_ERROR("failed to allocate edid\n");
-			return 0;
+		edid = display_ops->get_edid(manager->dev, connector);
+		if (IS_ERR_OR_NULL(edid)) {
+			ret = PTR_ERR(edid);
+			edid = NULL;
+			DRM_ERROR("Panel operation get_edid failed %d\n", ret);
+			goto out;
 		}
 
-		ret = display_ops->get_edid(manager->dev, connector,
-						edid, MAX_EDID);
-		if (ret < 0) {
-			DRM_ERROR("failed to get edid data.\n");
-			kfree(edid);
-			edid = NULL;
-			return 0;
+		count = drm_add_edid_modes(connector, edid);
+		if (count < 0) {
+			DRM_ERROR("Add edid modes failed %d\n", count);
+			goto out;
 		}
 
 		drm_mode_connector_update_edid_property(connector, edid);
-		count = drm_add_edid_modes(connector, edid);
-		kfree(edid);
 	} else {
 		struct exynos_drm_panel_info *panel;
 		struct drm_display_mode *mode = drm_mode_create(connector->dev);
@@ -161,6 +156,8 @@
 		count = 1;
 	}
 
+out:
+	kfree(edid);
 	return count;
 }
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c b/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c
index 9df9771..ba0a3aa 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c
@@ -19,6 +19,7 @@
 struct exynos_drm_dmabuf_attachment {
 	struct sg_table sgt;
 	enum dma_data_direction dir;
+	bool is_mapped;
 };
 
 static int exynos_gem_attach_dma_buf(struct dma_buf *dmabuf,
@@ -72,17 +73,10 @@
 
 	DRM_DEBUG_PRIME("%s\n", __FILE__);
 
-	if (WARN_ON(dir == DMA_NONE))
-		return ERR_PTR(-EINVAL);
-
 	/* just return current sgt if already requested. */
-	if (exynos_attach->dir == dir)
+	if (exynos_attach->dir == dir && exynos_attach->is_mapped)
 		return &exynos_attach->sgt;
 
-	/* reattaching is not allowed. */
-	if (WARN_ON(exynos_attach->dir != DMA_NONE))
-		return ERR_PTR(-EBUSY);
-
 	buf = gem_obj->buffer;
 	if (!buf) {
 		DRM_ERROR("buffer is null.\n");
@@ -107,13 +101,17 @@
 		wr = sg_next(wr);
 	}
 
-	nents = dma_map_sg(attach->dev, sgt->sgl, sgt->orig_nents, dir);
-	if (!nents) {
-		DRM_ERROR("failed to map sgl with iommu.\n");
-		sgt = ERR_PTR(-EIO);
-		goto err_unlock;
+	if (dir != DMA_NONE) {
+		nents = dma_map_sg(attach->dev, sgt->sgl, sgt->orig_nents, dir);
+		if (!nents) {
+			DRM_ERROR("failed to map sgl with iommu.\n");
+			sg_free_table(sgt);
+			sgt = ERR_PTR(-EIO);
+			goto err_unlock;
+		}
 	}
 
+	exynos_attach->is_mapped = true;
 	exynos_attach->dir = dir;
 	attach->priv = exynos_attach;
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h
index b9e51bc..4606fac7 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h
@@ -148,8 +148,8 @@
 struct exynos_drm_display_ops {
 	enum exynos_drm_output_type type;
 	bool (*is_connected)(struct device *dev);
-	int (*get_edid)(struct device *dev, struct drm_connector *connector,
-				u8 *edid, int len);
+	struct edid *(*get_edid)(struct device *dev,
+			struct drm_connector *connector);
 	void *(*get_panel)(struct device *dev);
 	int (*check_timing)(struct device *dev, void *timing);
 	int (*power_on)(struct device *dev, int mode);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
index 36c3905..9a4c08e 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
@@ -324,7 +324,7 @@
 	g2d_userptr = NULL;
 }
 
-dma_addr_t *g2d_userptr_get_dma_addr(struct drm_device *drm_dev,
+static dma_addr_t *g2d_userptr_get_dma_addr(struct drm_device *drm_dev,
 					unsigned long userptr,
 					unsigned long size,
 					struct drm_file *filp,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_hdmi.c b/drivers/gpu/drm/exynos/exynos_drm_hdmi.c
index 850e995..2864453 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_hdmi.c
@@ -108,18 +108,17 @@
 	return false;
 }
 
-static int drm_hdmi_get_edid(struct device *dev,
-		struct drm_connector *connector, u8 *edid, int len)
+static struct edid *drm_hdmi_get_edid(struct device *dev,
+			struct drm_connector *connector)
 {
 	struct drm_hdmi_context *ctx = to_context(dev);
 
 	DRM_DEBUG_KMS("%s\n", __FILE__);
 
 	if (hdmi_ops && hdmi_ops->get_edid)
-		return hdmi_ops->get_edid(ctx->hdmi_ctx->ctx, connector, edid,
-					  len);
+		return hdmi_ops->get_edid(ctx->hdmi_ctx->ctx, connector);
 
-	return 0;
+	return NULL;
 }
 
 static int drm_hdmi_check_timing(struct device *dev, void *timing)
diff --git a/drivers/gpu/drm/exynos/exynos_drm_hdmi.h b/drivers/gpu/drm/exynos/exynos_drm_hdmi.h
index 784a7e9..d80516f 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_hdmi.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_hdmi.h
@@ -30,8 +30,8 @@
 struct exynos_hdmi_ops {
 	/* display */
 	bool (*is_connected)(void *ctx);
-	int (*get_edid)(void *ctx, struct drm_connector *connector,
-			u8 *edid, int len);
+	struct edid *(*get_edid)(void *ctx,
+			struct drm_connector *connector);
 	int (*check_timing)(void *ctx, void *timing);
 	int (*power_on)(void *ctx, int mode);
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_ipp.c b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
index 0bda964..1a55635 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_ipp.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
@@ -869,7 +869,7 @@
 	}
 }
 
-void ipp_handle_cmd_work(struct device *dev,
+static void ipp_handle_cmd_work(struct device *dev,
 		struct exynos_drm_ippdrv *ippdrv,
 		struct drm_exynos_ipp_cmd_work *cmd_work,
 		struct drm_exynos_ipp_cmd_node *c_node)
diff --git a/drivers/gpu/drm/exynos/exynos_drm_rotator.c b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
index e9e83ef..f976e29 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_rotator.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
@@ -734,7 +734,7 @@
 	return 0;
 }
 
-struct rot_limit_table rot_limit_tbl = {
+static struct rot_limit_table rot_limit_tbl = {
 	.ycbcr420_2p = {
 		.min_w = 32,
 		.min_h = 32,
@@ -751,7 +751,7 @@
 	},
 };
 
-struct platform_device_id rotator_driver_ids[] = {
+static struct platform_device_id rotator_driver_ids[] = {
 	{
 		.name		= "exynos-rot",
 		.driver_data	= (unsigned long)&rot_limit_tbl,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
index d0ca3c4..13ccbd4 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
@@ -98,10 +98,12 @@
 	return ctx->connected ? true : false;
 }
 
-static int vidi_get_edid(struct device *dev, struct drm_connector *connector,
-				u8 *edid, int len)
+static struct edid *vidi_get_edid(struct device *dev,
+			struct drm_connector *connector)
 {
 	struct vidi_context *ctx = get_vidi_context(dev);
+	struct edid *edid;
+	int edid_len;
 
 	DRM_DEBUG_KMS("%s\n", __FILE__);
 
@@ -111,13 +113,18 @@
 	 */
 	if (!ctx->raw_edid) {
 		DRM_DEBUG_KMS("raw_edid is null.\n");
-		return -EFAULT;
+		return ERR_PTR(-EFAULT);
 	}
 
-	memcpy(edid, ctx->raw_edid, min((1 + ctx->raw_edid->extensions)
-					* EDID_LENGTH, len));
+	edid_len = (1 + ctx->raw_edid->extensions) * EDID_LENGTH;
+	edid = kzalloc(edid_len, GFP_KERNEL);
+	if (!edid) {
+		DRM_DEBUG_KMS("failed to allocate edid\n");
+		return ERR_PTR(-ENOMEM);
+	}
 
-	return 0;
+	memcpy(edid, ctx->raw_edid, edid_len);
+	return edid;
 }
 
 static void *vidi_get_panel(struct device *dev)
@@ -514,7 +521,6 @@
 	struct exynos_drm_manager *manager;
 	struct exynos_drm_display_ops *display_ops;
 	struct drm_exynos_vidi_connection *vidi = data;
-	struct edid *raw_edid;
 	int edid_len;
 
 	DRM_DEBUG_KMS("%s\n", __FILE__);
@@ -551,11 +557,11 @@
 	}
 
 	if (vidi->connection) {
-		if (!vidi->edid) {
-			DRM_DEBUG_KMS("edid data is null.\n");
+		struct edid *raw_edid  = (struct edid *)(uint32_t)vidi->edid;
+		if (!drm_edid_is_valid(raw_edid)) {
+			DRM_DEBUG_KMS("edid data is invalid.\n");
 			return -EINVAL;
 		}
-		raw_edid = (struct edid *)(uint32_t)vidi->edid;
 		edid_len = (1 + raw_edid->extensions) * EDID_LENGTH;
 		ctx->raw_edid = kzalloc(edid_len, GFP_KERNEL);
 		if (!ctx->raw_edid) {
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index 41ff79d..fbab3c4 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -34,7 +34,6 @@
 #include <linux/regulator/consumer.h>
 #include <linux/io.h>
 #include <linux/of_gpio.h>
-#include <plat/gpio-cfg.h>
 
 #include <drm/exynos_drm.h>
 
@@ -98,8 +97,7 @@
 
 	void __iomem			*regs;
 	void				*parent_ctx;
-	int				external_irq;
-	int				internal_irq;
+	int				irq;
 
 	struct i2c_client		*ddc_port;
 	struct i2c_client		*hdmiphy_port;
@@ -1391,8 +1389,7 @@
 	return hdata->hpd;
 }
 
-static int hdmi_get_edid(void *ctx, struct drm_connector *connector,
-				u8 *edid, int len)
+static struct edid *hdmi_get_edid(void *ctx, struct drm_connector *connector)
 {
 	struct edid *raw_edid;
 	struct hdmi_context *hdata = ctx;
@@ -1400,22 +1397,18 @@
 	DRM_DEBUG_KMS("[%d] %s\n", __LINE__, __func__);
 
 	if (!hdata->ddc_port)
-		return -ENODEV;
+		return ERR_PTR(-ENODEV);
 
 	raw_edid = drm_get_edid(connector, hdata->ddc_port->adapter);
-	if (raw_edid) {
-		hdata->dvi_mode = !drm_detect_hdmi_monitor(raw_edid);
-		memcpy(edid, raw_edid, min((1 + raw_edid->extensions)
-					* EDID_LENGTH, len));
-		DRM_DEBUG_KMS("%s : width[%d] x height[%d]\n",
-			(hdata->dvi_mode ? "dvi monitor" : "hdmi monitor"),
-			raw_edid->width_cm, raw_edid->height_cm);
-		kfree(raw_edid);
-	} else {
-		return -ENODEV;
-	}
+	if (!raw_edid)
+		return ERR_PTR(-ENODEV);
 
-	return 0;
+	hdata->dvi_mode = !drm_detect_hdmi_monitor(raw_edid);
+	DRM_DEBUG_KMS("%s : width[%d] x height[%d]\n",
+		(hdata->dvi_mode ? "dvi monitor" : "hdmi monitor"),
+		raw_edid->width_cm, raw_edid->height_cm);
+
+	return raw_edid;
 }
 
 static int hdmi_v13_check_timing(struct fb_videomode *check_timing)
@@ -1652,16 +1645,16 @@
 
 	/* resetting HDMI core */
 	hdmi_reg_writemask(hdata, reg,  0, HDMI_CORE_SW_RSTOUT);
-	mdelay(10);
+	usleep_range(10000, 12000);
 	hdmi_reg_writemask(hdata, reg, ~0, HDMI_CORE_SW_RSTOUT);
-	mdelay(10);
+	usleep_range(10000, 12000);
 }
 
 static void hdmi_conf_init(struct hdmi_context *hdata)
 {
 	struct hdmi_infoframe infoframe;
 
-	/* disable HPD interrupts */
+	/* disable HPD interrupts from HDMI IP block, use GPIO instead */
 	hdmi_reg_writemask(hdata, HDMI_INTC_CON, 0, HDMI_INTC_EN_GLOBAL |
 		HDMI_INTC_EN_HPD_PLUG | HDMI_INTC_EN_HPD_UNPLUG);
 
@@ -1779,7 +1772,7 @@
 		u32 val = hdmi_reg_read(hdata, HDMI_V13_PHY_STATUS);
 		if (val & HDMI_PHY_STATUS_READY)
 			break;
-		mdelay(1);
+		usleep_range(1000, 2000);
 	}
 	/* steady state not achieved */
 	if (tries == 0) {
@@ -1946,7 +1939,7 @@
 		u32 val = hdmi_reg_read(hdata, HDMI_PHY_STATUS_0);
 		if (val & HDMI_PHY_STATUS_READY)
 			break;
-		mdelay(1);
+		usleep_range(1000, 2000);
 	}
 	/* steady state not achieved */
 	if (tries == 0) {
@@ -1998,9 +1991,9 @@
 
 	/* reset hdmiphy */
 	hdmi_reg_writemask(hdata, reg, ~0, HDMI_PHY_SW_RSTOUT);
-	mdelay(10);
+	usleep_range(10000, 12000);
 	hdmi_reg_writemask(hdata, reg,  0, HDMI_PHY_SW_RSTOUT);
-	mdelay(10);
+	usleep_range(10000, 12000);
 }
 
 static void hdmiphy_poweron(struct hdmi_context *hdata)
@@ -2048,7 +2041,7 @@
 		return;
 	}
 
-	mdelay(10);
+	usleep_range(10000, 12000);
 
 	/* operation mode */
 	operation[0] = 0x1f;
@@ -2170,6 +2163,13 @@
 
 	DRM_DEBUG_KMS("[%d] %s\n", __LINE__, __func__);
 
+	mutex_lock(&hdata->hdmi_mutex);
+	if (!hdata->powered) {
+		mutex_unlock(&hdata->hdmi_mutex);
+		return;
+	}
+	mutex_unlock(&hdata->hdmi_mutex);
+
 	hdmi_conf_apply(hdata);
 }
 
@@ -2265,7 +2265,7 @@
 	.dpms		= hdmi_dpms,
 };
 
-static irqreturn_t hdmi_external_irq_thread(int irq, void *arg)
+static irqreturn_t hdmi_irq_thread(int irq, void *arg)
 {
 	struct exynos_drm_hdmi_context *ctx = arg;
 	struct hdmi_context *hdata = ctx->ctx;
@@ -2280,31 +2280,6 @@
 	return IRQ_HANDLED;
 }
 
-static irqreturn_t hdmi_internal_irq_thread(int irq, void *arg)
-{
-	struct exynos_drm_hdmi_context *ctx = arg;
-	struct hdmi_context *hdata = ctx->ctx;
-	u32 intc_flag;
-
-	intc_flag = hdmi_reg_read(hdata, HDMI_INTC_FLAG);
-	/* clearing flags for HPD plug/unplug */
-	if (intc_flag & HDMI_INTC_FLAG_HPD_UNPLUG) {
-		DRM_DEBUG_KMS("unplugged\n");
-		hdmi_reg_writemask(hdata, HDMI_INTC_FLAG, ~0,
-			HDMI_INTC_FLAG_HPD_UNPLUG);
-	}
-	if (intc_flag & HDMI_INTC_FLAG_HPD_PLUG) {
-		DRM_DEBUG_KMS("plugged\n");
-		hdmi_reg_writemask(hdata, HDMI_INTC_FLAG, ~0,
-			HDMI_INTC_FLAG_HPD_PLUG);
-	}
-
-	if (ctx->drm_dev)
-		drm_helper_hpd_irq_event(ctx->drm_dev);
-
-	return IRQ_HANDLED;
-}
-
 static int hdmi_resources_init(struct hdmi_context *hdata)
 {
 	struct device *dev = hdata->dev;
@@ -2555,39 +2530,24 @@
 
 	hdata->hdmiphy_port = hdmi_hdmiphy;
 
-	hdata->external_irq = gpio_to_irq(hdata->hpd_gpio);
-	if (hdata->external_irq < 0) {
-		DRM_ERROR("failed to get GPIO external irq\n");
-		ret = hdata->external_irq;
-		goto err_hdmiphy;
-	}
-
-	hdata->internal_irq = platform_get_irq(pdev, 0);
-	if (hdata->internal_irq < 0) {
-		DRM_ERROR("failed to get platform internal irq\n");
-		ret = hdata->internal_irq;
+	hdata->irq = gpio_to_irq(hdata->hpd_gpio);
+	if (hdata->irq < 0) {
+		DRM_ERROR("failed to get GPIO irq\n");
+		ret = hdata->irq;
 		goto err_hdmiphy;
 	}
 
 	hdata->hpd = gpio_get_value(hdata->hpd_gpio);
 
-	ret = request_threaded_irq(hdata->external_irq, NULL,
-			hdmi_external_irq_thread, IRQF_TRIGGER_RISING |
+	ret = request_threaded_irq(hdata->irq, NULL,
+			hdmi_irq_thread, IRQF_TRIGGER_RISING |
 			IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
-			"hdmi_external", drm_hdmi_ctx);
+			"hdmi", drm_hdmi_ctx);
 	if (ret) {
-		DRM_ERROR("failed to register hdmi external interrupt\n");
+		DRM_ERROR("failed to register hdmi interrupt\n");
 		goto err_hdmiphy;
 	}
 
-	ret = request_threaded_irq(hdata->internal_irq, NULL,
-			hdmi_internal_irq_thread, IRQF_ONESHOT,
-			"hdmi_internal", drm_hdmi_ctx);
-	if (ret) {
-		DRM_ERROR("failed to register hdmi internal interrupt\n");
-		goto err_free_irq;
-	}
-
 	/* Attach HDMI Driver to common hdmi. */
 	exynos_hdmi_drv_attach(drm_hdmi_ctx);
 
@@ -2598,8 +2558,6 @@
 
 	return 0;
 
-err_free_irq:
-	free_irq(hdata->external_irq, drm_hdmi_ctx);
 err_hdmiphy:
 	i2c_del_driver(&hdmiphy_driver);
 err_ddc:
@@ -2617,8 +2575,7 @@
 
 	pm_runtime_disable(dev);
 
-	free_irq(hdata->internal_irq, hdata);
-	free_irq(hdata->external_irq, hdata);
+	free_irq(hdata->irq, hdata);
 
 
 	/* hdmiphy i2c driver */
@@ -2637,8 +2594,7 @@
 
 	DRM_DEBUG_KMS("[%d] %s\n", __LINE__, __func__);
 
-	disable_irq(hdata->internal_irq);
-	disable_irq(hdata->external_irq);
+	disable_irq(hdata->irq);
 
 	hdata->hpd = false;
 	if (ctx->drm_dev)
@@ -2663,8 +2619,7 @@
 
 	hdata->hpd = gpio_get_value(hdata->hpd_gpio);
 
-	enable_irq(hdata->external_irq);
-	enable_irq(hdata->internal_irq);
+	enable_irq(hdata->irq);
 
 	if (!pm_runtime_suspended(dev)) {
 		DRM_DEBUG_KMS("%s : Already resumed\n", __func__);
diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c
index c187ea3..c414584 100644
--- a/drivers/gpu/drm/exynos/exynos_mixer.c
+++ b/drivers/gpu/drm/exynos/exynos_mixer.c
@@ -600,7 +600,7 @@
 		/* waiting until VP_SRESET_PROCESSING is 0 */
 		if (~vp_reg_read(res, VP_SRESET) & VP_SRESET_PROCESSING)
 			break;
-		mdelay(10);
+		usleep_range(10000, 12000);
 	}
 	WARN(tries == 0, "failed to reset Video Processor\n");
 }
@@ -776,6 +776,13 @@
 
 	DRM_DEBUG_KMS("[%d] %s, win: %d\n", __LINE__, __func__, win);
 
+	mutex_lock(&mixer_ctx->mixer_mutex);
+	if (!mixer_ctx->powered) {
+		mutex_unlock(&mixer_ctx->mixer_mutex);
+		return;
+	}
+	mutex_unlock(&mixer_ctx->mixer_mutex);
+
 	if (win > 1 && mixer_ctx->vp_enabled)
 		vp_video_buffer(mixer_ctx, win);
 	else
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 7944d3015..9d4a2c2 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -30,6 +30,7 @@
 #include <linux/debugfs.h>
 #include <linux/slab.h>
 #include <linux/export.h>
+#include <generated/utsrelease.h>
 #include <drm/drmP.h>
 #include "intel_drv.h"
 #include "intel_ringbuffer.h"
@@ -690,6 +691,7 @@
 
 	seq_printf(m, "Time: %ld s %ld us\n", error->time.tv_sec,
 		   error->time.tv_usec);
+	seq_printf(m, "Kernel: " UTS_RELEASE);
 	seq_printf(m, "PCI ID: 0x%04x\n", dev->pci_device);
 	seq_printf(m, "EIR: 0x%08x\n", error->eir);
 	seq_printf(m, "IER: 0x%08x\n", error->ier);
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index b401788..59afb7e 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -533,6 +533,7 @@
 #define MI_MODE		0x0209c
 # define VS_TIMER_DISPATCH				(1 << 6)
 # define MI_FLUSH_ENABLE				(1 << 12)
+# define ASYNC_FLIP_PERF_DISABLE			(1 << 14)
 
 #define GEN6_GT_MODE	0x20d0
 #define   GEN6_GT_MODE_HI				(1 << 9)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index ae253e0..42ff97d 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -505,13 +505,25 @@
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int ret = init_ring_common(ring);
 
-	if (INTEL_INFO(dev)->gen > 3) {
+	if (INTEL_INFO(dev)->gen > 3)
 		I915_WRITE(MI_MODE, _MASKED_BIT_ENABLE(VS_TIMER_DISPATCH));
-		if (IS_GEN7(dev))
-			I915_WRITE(GFX_MODE_GEN7,
-				   _MASKED_BIT_DISABLE(GFX_TLB_INVALIDATE_ALWAYS) |
-				   _MASKED_BIT_ENABLE(GFX_REPLAY_MODE));
-	}
+
+	/* We need to disable the AsyncFlip performance optimisations in order
+	 * to use MI_WAIT_FOR_EVENT within the CS. It should already be
+	 * programmed to '1' on all products.
+	 */
+	if (INTEL_INFO(dev)->gen >= 6)
+		I915_WRITE(MI_MODE, _MASKED_BIT_ENABLE(ASYNC_FLIP_PERF_DISABLE));
+
+	/* Required for the hardware to program scanline values for waiting */
+	if (INTEL_INFO(dev)->gen == 6)
+		I915_WRITE(GFX_MODE,
+			   _MASKED_BIT_ENABLE(GFX_TLB_INVALIDATE_ALWAYS));
+
+	if (IS_GEN7(dev))
+		I915_WRITE(GFX_MODE_GEN7,
+			   _MASKED_BIT_DISABLE(GFX_TLB_INVALIDATE_ALWAYS) |
+			   _MASKED_BIT_ENABLE(GFX_REPLAY_MODE));
 
 	if (INTEL_INFO(dev)->gen >= 5) {
 		ret = init_pipe_control(ring);
diff --git a/drivers/gpu/drm/nouveau/core/core/falcon.c b/drivers/gpu/drm/nouveau/core/core/falcon.c
index 6b0843c..e05c157 100644
--- a/drivers/gpu/drm/nouveau/core/core/falcon.c
+++ b/drivers/gpu/drm/nouveau/core/core/falcon.c
@@ -73,8 +73,11 @@
 	nv_debug(falcon, "data limit: %d\n", falcon->data.limit);
 
 	/* wait for 'uc halted' to be signalled before continuing */
-	if (falcon->secret) {
-		nv_wait(falcon, 0x008, 0x00000010, 0x00000010);
+	if (falcon->secret && falcon->version < 4) {
+		if (!falcon->version)
+			nv_wait(falcon, 0x008, 0x00000010, 0x00000010);
+		else
+			nv_wait(falcon, 0x180, 0x80000000, 0);
 		nv_wo32(falcon, 0x004, 0x00000010);
 	}
 
diff --git a/drivers/gpu/drm/nouveau/core/core/subdev.c b/drivers/gpu/drm/nouveau/core/core/subdev.c
index f74c30a..48f0637 100644
--- a/drivers/gpu/drm/nouveau/core/core/subdev.c
+++ b/drivers/gpu/drm/nouveau/core/core/subdev.c
@@ -99,7 +99,7 @@
 	if (ret)
 		return ret;
 
-	mutex_init(&subdev->mutex);
+	__mutex_init(&subdev->mutex, subname, &oclass->lock_class_key);
 	subdev->name = subname;
 
 	if (parent) {
diff --git a/drivers/gpu/drm/nouveau/core/include/core/object.h b/drivers/gpu/drm/nouveau/core/include/core/object.h
index 5982935..106bb19 100644
--- a/drivers/gpu/drm/nouveau/core/include/core/object.h
+++ b/drivers/gpu/drm/nouveau/core/include/core/object.h
@@ -50,10 +50,13 @@
 
 extern struct nouveau_ofuncs nouveau_object_ofuncs;
 
+/* Don't allocate dynamically, because lockdep needs lock_class_keys to be in
+ * ".data". */
 struct nouveau_oclass {
 	u32 handle;
-	struct nouveau_ofuncs *ofuncs;
-	struct nouveau_omthds *omthds;
+	struct nouveau_ofuncs * const ofuncs;
+	struct nouveau_omthds * const omthds;
+	struct lock_class_key lock_class_key;
 };
 
 #define nv_oclass(o)    nv_object(o)->oclass
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/base.c b/drivers/gpu/drm/nouveau/core/subdev/fb/base.c
index d6d1600..d62045f 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/base.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/base.c
@@ -86,8 +86,8 @@
 			return ret;
 	}
 
-	if (!nouveau_mm_initialised(&pfb->tags) && tags) {
-		ret = nouveau_mm_init(&pfb->tags, 0, ++tags, 1);
+	if (!nouveau_mm_initialised(&pfb->tags)) {
+		ret = nouveau_mm_init(&pfb->tags, 0, tags ? ++tags : 0, 1);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/nv50.c b/drivers/gpu/drm/nouveau/core/subdev/fb/nv50.c
index 487cb8c..eac236e 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/nv50.c
@@ -99,7 +99,7 @@
 	struct nouveau_bios *bios = nouveau_bios(device);
 	const u32 rsvd_head = ( 256 * 1024) >> 12; /* vga memory */
 	const u32 rsvd_tail = (1024 * 1024) >> 12; /* vbios etc */
-	u32 size;
+	u32 size, tags = 0;
 	int ret;
 
 	pfb->ram.size = nv_rd32(pfb, 0x10020c);
@@ -140,10 +140,11 @@
 			return ret;
 
 		pfb->ram.ranks = (nv_rd32(pfb, 0x100200) & 0x4) ? 2 : 1;
+		tags = nv_rd32(pfb, 0x100320);
 		break;
 	}
 
-	return nv_rd32(pfb, 0x100320);
+	return tags;
 }
 
 static int
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 69d7b1d..1699a90 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -28,6 +28,7 @@
  */
 
 #include <core/engine.h>
+#include <linux/swiotlb.h>
 
 #include <subdev/fb.h>
 #include <subdev/vm.h>
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 8b090f1..5e7aef2 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -245,6 +245,8 @@
 	return 0;
 }
 
+static struct lock_class_key drm_client_lock_class_key;
+
 static int
 nouveau_drm_load(struct drm_device *dev, unsigned long flags)
 {
@@ -256,6 +258,7 @@
 	ret = nouveau_cli_create(pdev, "DRM", sizeof(*drm), (void**)&drm);
 	if (ret)
 		return ret;
+	lockdep_set_class(&drm->client.mutex, &drm_client_lock_class_key);
 
 	dev->dev_private = drm;
 	drm->dev = dev;
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 4d0e60a..a2d478e 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -1313,14 +1313,18 @@
 				if (!(tmp & EVERGREEN_CRTC_BLANK_DATA_EN)) {
 					radeon_wait_for_vblank(rdev, i);
 					tmp |= EVERGREEN_CRTC_BLANK_DATA_EN;
+					WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 1);
 					WREG32(EVERGREEN_CRTC_BLANK_CONTROL + crtc_offsets[i], tmp);
+					WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 0);
 				}
 			} else {
 				tmp = RREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i]);
 				if (!(tmp & EVERGREEN_CRTC_DISP_READ_REQUEST_DISABLE)) {
 					radeon_wait_for_vblank(rdev, i);
 					tmp |= EVERGREEN_CRTC_DISP_READ_REQUEST_DISABLE;
+					WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 1);
 					WREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i], tmp);
+					WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 0);
 				}
 			}
 			/* wait for the next frame */
@@ -1345,6 +1349,8 @@
 		blackout &= ~BLACKOUT_MODE_MASK;
 		WREG32(MC_SHARED_BLACKOUT_CNTL, blackout | 1);
 	}
+	/* wait for the MC to settle */
+	udelay(100);
 }
 
 void evergreen_mc_resume(struct radeon_device *rdev, struct evergreen_mc_save *save)
@@ -1378,11 +1384,15 @@
 			if (ASIC_IS_DCE6(rdev)) {
 				tmp = RREG32(EVERGREEN_CRTC_BLANK_CONTROL + crtc_offsets[i]);
 				tmp |= EVERGREEN_CRTC_BLANK_DATA_EN;
+				WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 1);
 				WREG32(EVERGREEN_CRTC_BLANK_CONTROL + crtc_offsets[i], tmp);
+				WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 0);
 			} else {
 				tmp = RREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i]);
 				tmp &= ~EVERGREEN_CRTC_DISP_READ_REQUEST_DISABLE;
+				WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 1);
 				WREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i], tmp);
+				WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 0);
 			}
 			/* wait for the next frame */
 			frame_count = radeon_get_vblank_counter(rdev, i);
@@ -2036,9 +2046,20 @@
 	WREG32(HDP_ADDR_CONFIG, gb_addr_config);
 	WREG32(DMA_TILING_CONFIG, gb_addr_config);
 
-	tmp = gb_addr_config & NUM_PIPES_MASK;
-	tmp = r6xx_remap_render_backend(rdev, tmp, rdev->config.evergreen.max_backends,
-					EVERGREEN_MAX_BACKENDS, disabled_rb_mask);
+	if ((rdev->config.evergreen.max_backends == 1) &&
+	    (rdev->flags & RADEON_IS_IGP)) {
+		if ((disabled_rb_mask & 3) == 1) {
+			/* RB0 disabled, RB1 enabled */
+			tmp = 0x11111111;
+		} else {
+			/* RB1 disabled, RB0 enabled */
+			tmp = 0x00000000;
+		}
+	} else {
+		tmp = gb_addr_config & NUM_PIPES_MASK;
+		tmp = r6xx_remap_render_backend(rdev, tmp, rdev->config.evergreen.max_backends,
+						EVERGREEN_MAX_BACKENDS, disabled_rb_mask);
+	}
 	WREG32(GB_BACKEND_MAP, tmp);
 
 	WREG32(CGTS_SYS_TCC_DISABLE, 0);
diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index 7a44566..ee4cff5 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -2909,14 +2909,14 @@
 				return -EINVAL;
 			}
 			if (tiled) {
-				dst_offset = ib[idx+1];
+				dst_offset = radeon_get_ib_value(p, idx+1);
 				dst_offset <<= 8;
 
 				ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
 				p->idx += count + 7;
 			} else {
-				dst_offset = ib[idx+1];
-				dst_offset |= ((u64)(ib[idx+2] & 0xff)) << 32;
+				dst_offset = radeon_get_ib_value(p, idx+1);
+				dst_offset |= ((u64)(radeon_get_ib_value(p, idx+2) & 0xff)) << 32;
 
 				ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
 				ib[idx+2] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
@@ -2954,12 +2954,12 @@
 							DRM_ERROR("bad L2T, frame to fields DMA_PACKET_COPY\n");
 							return -EINVAL;
 						}
-						dst_offset = ib[idx+1];
+						dst_offset = radeon_get_ib_value(p, idx+1);
 						dst_offset <<= 8;
-						dst2_offset = ib[idx+2];
+						dst2_offset = radeon_get_ib_value(p, idx+2);
 						dst2_offset <<= 8;
-						src_offset = ib[idx+8];
-						src_offset |= ((u64)(ib[idx+9] & 0xff)) << 32;
+						src_offset = radeon_get_ib_value(p, idx+8);
+						src_offset |= ((u64)(radeon_get_ib_value(p, idx+9) & 0xff)) << 32;
 						if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
 							dev_warn(p->dev, "DMA L2T, frame to fields src buffer too small (%llu %lu)\n",
 								 src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
@@ -3014,12 +3014,12 @@
 							DRM_ERROR("bad L2T, broadcast DMA_PACKET_COPY\n");
 							return -EINVAL;
 						}
-						dst_offset = ib[idx+1];
+						dst_offset = radeon_get_ib_value(p, idx+1);
 						dst_offset <<= 8;
-						dst2_offset = ib[idx+2];
+						dst2_offset = radeon_get_ib_value(p, idx+2);
 						dst2_offset <<= 8;
-						src_offset = ib[idx+8];
-						src_offset |= ((u64)(ib[idx+9] & 0xff)) << 32;
+						src_offset = radeon_get_ib_value(p, idx+8);
+						src_offset |= ((u64)(radeon_get_ib_value(p, idx+9) & 0xff)) << 32;
 						if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
 							dev_warn(p->dev, "DMA L2T, broadcast src buffer too small (%llu %lu)\n",
 								 src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
@@ -3046,22 +3046,22 @@
 						/* detile bit */
 						if (idx_value & (1 << 31)) {
 							/* tiled src, linear dst */
-							src_offset = ib[idx+1];
+							src_offset = radeon_get_ib_value(p, idx+1);
 							src_offset <<= 8;
 							ib[idx+1] += (u32)(src_reloc->lobj.gpu_offset >> 8);
 
-							dst_offset = ib[idx+7];
-							dst_offset |= ((u64)(ib[idx+8] & 0xff)) << 32;
+							dst_offset = radeon_get_ib_value(p, idx+7);
+							dst_offset |= ((u64)(radeon_get_ib_value(p, idx+8) & 0xff)) << 32;
 							ib[idx+7] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
 							ib[idx+8] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
 						} else {
 							/* linear src, tiled dst */
-							src_offset = ib[idx+7];
-							src_offset |= ((u64)(ib[idx+8] & 0xff)) << 32;
+							src_offset = radeon_get_ib_value(p, idx+7);
+							src_offset |= ((u64)(radeon_get_ib_value(p, idx+8) & 0xff)) << 32;
 							ib[idx+7] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
 							ib[idx+8] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
 
-							dst_offset = ib[idx+1];
+							dst_offset = radeon_get_ib_value(p, idx+1);
 							dst_offset <<= 8;
 							ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
 						}
@@ -3098,12 +3098,12 @@
 							DRM_ERROR("bad L2T, broadcast DMA_PACKET_COPY\n");
 							return -EINVAL;
 						}
-						dst_offset = ib[idx+1];
+						dst_offset = radeon_get_ib_value(p, idx+1);
 						dst_offset <<= 8;
-						dst2_offset = ib[idx+2];
+						dst2_offset = radeon_get_ib_value(p, idx+2);
 						dst2_offset <<= 8;
-						src_offset = ib[idx+8];
-						src_offset |= ((u64)(ib[idx+9] & 0xff)) << 32;
+						src_offset = radeon_get_ib_value(p, idx+8);
+						src_offset |= ((u64)(radeon_get_ib_value(p, idx+9) & 0xff)) << 32;
 						if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
 							dev_warn(p->dev, "DMA L2T, broadcast src buffer too small (%llu %lu)\n",
 								 src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
@@ -3135,22 +3135,22 @@
 						/* detile bit */
 						if (idx_value & (1 << 31)) {
 							/* tiled src, linear dst */
-							src_offset = ib[idx+1];
+							src_offset = radeon_get_ib_value(p, idx+1);
 							src_offset <<= 8;
 							ib[idx+1] += (u32)(src_reloc->lobj.gpu_offset >> 8);
 
-							dst_offset = ib[idx+7];
-							dst_offset |= ((u64)(ib[idx+8] & 0xff)) << 32;
+							dst_offset = radeon_get_ib_value(p, idx+7);
+							dst_offset |= ((u64)(radeon_get_ib_value(p, idx+8) & 0xff)) << 32;
 							ib[idx+7] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
 							ib[idx+8] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
 						} else {
 							/* linear src, tiled dst */
-							src_offset = ib[idx+7];
-							src_offset |= ((u64)(ib[idx+8] & 0xff)) << 32;
+							src_offset = radeon_get_ib_value(p, idx+7);
+							src_offset |= ((u64)(radeon_get_ib_value(p, idx+8) & 0xff)) << 32;
 							ib[idx+7] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
 							ib[idx+8] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
 
-							dst_offset = ib[idx+1];
+							dst_offset = radeon_get_ib_value(p, idx+1);
 							dst_offset <<= 8;
 							ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
 						}
@@ -3176,10 +3176,10 @@
 					switch (misc) {
 					case 0:
 						/* L2L, byte */
-						src_offset = ib[idx+2];
-						src_offset |= ((u64)(ib[idx+4] & 0xff)) << 32;
-						dst_offset = ib[idx+1];
-						dst_offset |= ((u64)(ib[idx+3] & 0xff)) << 32;
+						src_offset = radeon_get_ib_value(p, idx+2);
+						src_offset |= ((u64)(radeon_get_ib_value(p, idx+4) & 0xff)) << 32;
+						dst_offset = radeon_get_ib_value(p, idx+1);
+						dst_offset |= ((u64)(radeon_get_ib_value(p, idx+3) & 0xff)) << 32;
 						if ((src_offset + count) > radeon_bo_size(src_reloc->robj)) {
 							dev_warn(p->dev, "DMA L2L, byte src buffer too small (%llu %lu)\n",
 								 src_offset + count, radeon_bo_size(src_reloc->robj));
@@ -3216,12 +3216,12 @@
 							DRM_ERROR("bad L2L, dw, broadcast DMA_PACKET_COPY\n");
 							return -EINVAL;
 						}
-						dst_offset = ib[idx+1];
-						dst_offset |= ((u64)(ib[idx+4] & 0xff)) << 32;
-						dst2_offset = ib[idx+2];
-						dst2_offset |= ((u64)(ib[idx+5] & 0xff)) << 32;
-						src_offset = ib[idx+3];
-						src_offset |= ((u64)(ib[idx+6] & 0xff)) << 32;
+						dst_offset = radeon_get_ib_value(p, idx+1);
+						dst_offset |= ((u64)(radeon_get_ib_value(p, idx+4) & 0xff)) << 32;
+						dst2_offset = radeon_get_ib_value(p, idx+2);
+						dst2_offset |= ((u64)(radeon_get_ib_value(p, idx+5) & 0xff)) << 32;
+						src_offset = radeon_get_ib_value(p, idx+3);
+						src_offset |= ((u64)(radeon_get_ib_value(p, idx+6) & 0xff)) << 32;
 						if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
 							dev_warn(p->dev, "DMA L2L, dw, broadcast src buffer too small (%llu %lu)\n",
 								 src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
@@ -3251,10 +3251,10 @@
 					}
 				} else {
 					/* L2L, dw */
-					src_offset = ib[idx+2];
-					src_offset |= ((u64)(ib[idx+4] & 0xff)) << 32;
-					dst_offset = ib[idx+1];
-					dst_offset |= ((u64)(ib[idx+3] & 0xff)) << 32;
+					src_offset = radeon_get_ib_value(p, idx+2);
+					src_offset |= ((u64)(radeon_get_ib_value(p, idx+4) & 0xff)) << 32;
+					dst_offset = radeon_get_ib_value(p, idx+1);
+					dst_offset |= ((u64)(radeon_get_ib_value(p, idx+3) & 0xff)) << 32;
 					if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
 						dev_warn(p->dev, "DMA L2L, dw src buffer too small (%llu %lu)\n",
 							 src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
@@ -3279,8 +3279,8 @@
 				DRM_ERROR("bad DMA_PACKET_CONSTANT_FILL\n");
 				return -EINVAL;
 			}
-			dst_offset = ib[idx+1];
-			dst_offset |= ((u64)(ib[idx+3] & 0x00ff0000)) << 16;
+			dst_offset = radeon_get_ib_value(p, idx+1);
+			dst_offset |= ((u64)(radeon_get_ib_value(p, idx+3) & 0x00ff0000)) << 16;
 			if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) {
 				dev_warn(p->dev, "DMA constant fill buffer too small (%llu %lu)\n",
 					 dst_offset, radeon_bo_size(dst_reloc->robj));
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 59acabb..835992d 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -1216,7 +1216,7 @@
 int cayman_dma_resume(struct radeon_device *rdev)
 {
 	struct radeon_ring *ring;
-	u32 rb_cntl, dma_cntl;
+	u32 rb_cntl, dma_cntl, ib_cntl;
 	u32 rb_bufsz;
 	u32 reg_offset, wb_offset;
 	int i, r;
@@ -1265,7 +1265,11 @@
 		WREG32(DMA_RB_BASE + reg_offset, ring->gpu_addr >> 8);
 
 		/* enable DMA IBs */
-		WREG32(DMA_IB_CNTL + reg_offset, DMA_IB_ENABLE | CMD_VMID_FORCE);
+		ib_cntl = DMA_IB_ENABLE | CMD_VMID_FORCE;
+#ifdef __BIG_ENDIAN
+		ib_cntl |= DMA_IB_SWAP_ENABLE;
+#endif
+		WREG32(DMA_IB_CNTL + reg_offset, ib_cntl);
 
 		dma_cntl = RREG32(DMA_CNTL + reg_offset);
 		dma_cntl &= ~CTXEMPTY_INT_ENABLE;
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 3cb9d60..becb03e 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -1462,12 +1462,15 @@
 			      u32 disabled_rb_mask)
 {
 	u32 rendering_pipe_num, rb_num_width, req_rb_num;
-	u32 pipe_rb_ratio, pipe_rb_remain;
+	u32 pipe_rb_ratio, pipe_rb_remain, tmp;
 	u32 data = 0, mask = 1 << (max_rb_num - 1);
 	unsigned i, j;
 
 	/* mask out the RBs that don't exist on that asic */
-	disabled_rb_mask |= (0xff << max_rb_num) & 0xff;
+	tmp = disabled_rb_mask | ((0xff << max_rb_num) & 0xff);
+	/* make sure at least one RB is available */
+	if ((tmp & 0xff) != 0xff)
+		disabled_rb_mask = tmp;
 
 	rendering_pipe_num = 1 << tiling_pipe_num;
 	req_rb_num = total_max_rb_num - r600_count_pipe_bits(disabled_rb_mask);
@@ -2313,7 +2316,7 @@
 int r600_dma_resume(struct radeon_device *rdev)
 {
 	struct radeon_ring *ring = &rdev->ring[R600_RING_TYPE_DMA_INDEX];
-	u32 rb_cntl, dma_cntl;
+	u32 rb_cntl, dma_cntl, ib_cntl;
 	u32 rb_bufsz;
 	int r;
 
@@ -2353,7 +2356,11 @@
 	WREG32(DMA_RB_BASE, ring->gpu_addr >> 8);
 
 	/* enable DMA IBs */
-	WREG32(DMA_IB_CNTL, DMA_IB_ENABLE);
+	ib_cntl = DMA_IB_ENABLE;
+#ifdef __BIG_ENDIAN
+	ib_cntl |= DMA_IB_SWAP_ENABLE;
+#endif
+	WREG32(DMA_IB_CNTL, ib_cntl);
 
 	dma_cntl = RREG32(DMA_CNTL);
 	dma_cntl &= ~CTXEMPTY_INT_ENABLE;
diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index 69ec24a..9b2512b 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -2623,14 +2623,14 @@
 				return -EINVAL;
 			}
 			if (tiled) {
-				dst_offset = ib[idx+1];
+				dst_offset = radeon_get_ib_value(p, idx+1);
 				dst_offset <<= 8;
 
 				ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
 				p->idx += count + 5;
 			} else {
-				dst_offset = ib[idx+1];
-				dst_offset |= ((u64)(ib[idx+2] & 0xff)) << 32;
+				dst_offset = radeon_get_ib_value(p, idx+1);
+				dst_offset |= ((u64)(radeon_get_ib_value(p, idx+2) & 0xff)) << 32;
 
 				ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
 				ib[idx+2] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
@@ -2658,32 +2658,32 @@
 				/* detile bit */
 				if (idx_value & (1 << 31)) {
 					/* tiled src, linear dst */
-					src_offset = ib[idx+1];
+					src_offset = radeon_get_ib_value(p, idx+1);
 					src_offset <<= 8;
 					ib[idx+1] += (u32)(src_reloc->lobj.gpu_offset >> 8);
 
-					dst_offset = ib[idx+5];
-					dst_offset |= ((u64)(ib[idx+6] & 0xff)) << 32;
+					dst_offset = radeon_get_ib_value(p, idx+5);
+					dst_offset |= ((u64)(radeon_get_ib_value(p, idx+6) & 0xff)) << 32;
 					ib[idx+5] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
 					ib[idx+6] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
 				} else {
 					/* linear src, tiled dst */
-					src_offset = ib[idx+5];
-					src_offset |= ((u64)(ib[idx+6] & 0xff)) << 32;
+					src_offset = radeon_get_ib_value(p, idx+5);
+					src_offset |= ((u64)(radeon_get_ib_value(p, idx+6) & 0xff)) << 32;
 					ib[idx+5] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
 					ib[idx+6] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
 
-					dst_offset = ib[idx+1];
+					dst_offset = radeon_get_ib_value(p, idx+1);
 					dst_offset <<= 8;
 					ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
 				}
 				p->idx += 7;
 			} else {
 				if (p->family >= CHIP_RV770) {
-					src_offset = ib[idx+2];
-					src_offset |= ((u64)(ib[idx+4] & 0xff)) << 32;
-					dst_offset = ib[idx+1];
-					dst_offset |= ((u64)(ib[idx+3] & 0xff)) << 32;
+					src_offset = radeon_get_ib_value(p, idx+2);
+					src_offset |= ((u64)(radeon_get_ib_value(p, idx+4) & 0xff)) << 32;
+					dst_offset = radeon_get_ib_value(p, idx+1);
+					dst_offset |= ((u64)(radeon_get_ib_value(p, idx+3) & 0xff)) << 32;
 
 					ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
 					ib[idx+2] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
@@ -2691,10 +2691,10 @@
 					ib[idx+4] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
 					p->idx += 5;
 				} else {
-					src_offset = ib[idx+2];
-					src_offset |= ((u64)(ib[idx+3] & 0xff)) << 32;
-					dst_offset = ib[idx+1];
-					dst_offset |= ((u64)(ib[idx+3] & 0xff0000)) << 16;
+					src_offset = radeon_get_ib_value(p, idx+2);
+					src_offset |= ((u64)(radeon_get_ib_value(p, idx+3) & 0xff)) << 32;
+					dst_offset = radeon_get_ib_value(p, idx+1);
+					dst_offset |= ((u64)(radeon_get_ib_value(p, idx+3) & 0xff0000)) << 16;
 
 					ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
 					ib[idx+2] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
@@ -2724,8 +2724,8 @@
 				DRM_ERROR("bad DMA_PACKET_WRITE\n");
 				return -EINVAL;
 			}
-			dst_offset = ib[idx+1];
-			dst_offset |= ((u64)(ib[idx+3] & 0x00ff0000)) << 16;
+			dst_offset = radeon_get_ib_value(p, idx+1);
+			dst_offset |= ((u64)(radeon_get_ib_value(p, idx+3) & 0x00ff0000)) << 16;
 			if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) {
 				dev_warn(p->dev, "DMA constant fill buffer too small (%llu %lu)\n",
 					 dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index 9056faf..0b202c0 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -1445,7 +1445,7 @@
 	.vm = {
 		.init = &cayman_vm_init,
 		.fini = &cayman_vm_fini,
-		.pt_ring_index = R600_RING_TYPE_DMA_INDEX,
+		.pt_ring_index = RADEON_RING_TYPE_GFX_INDEX,
 		.set_page = &cayman_vm_set_page,
 	},
 	.ring = {
@@ -1572,7 +1572,7 @@
 	.vm = {
 		.init = &cayman_vm_init,
 		.fini = &cayman_vm_fini,
-		.pt_ring_index = R600_RING_TYPE_DMA_INDEX,
+		.pt_ring_index = RADEON_RING_TYPE_GFX_INDEX,
 		.set_page = &cayman_vm_set_page,
 	},
 	.ring = {
@@ -1699,7 +1699,7 @@
 	.vm = {
 		.init = &si_vm_init,
 		.fini = &si_vm_fini,
-		.pt_ring_index = R600_RING_TYPE_DMA_INDEX,
+		.pt_ring_index = RADEON_RING_TYPE_GFX_INDEX,
 		.set_page = &si_vm_set_page,
 	},
 	.ring = {
diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c
index 33a56a0..3e403bd 100644
--- a/drivers/gpu/drm/radeon/radeon_combios.c
+++ b/drivers/gpu/drm/radeon/radeon_combios.c
@@ -2470,6 +2470,14 @@
 								   1),
 								  ATOM_DEVICE_CRT1_SUPPORT);
 				}
+				/* RV100 board with external TDMS bit mis-set.
+				 * Actually uses internal TMDS, clear the bit.
+				 */
+				if (dev->pdev->device == 0x5159 &&
+				    dev->pdev->subsystem_vendor == 0x1014 &&
+				    dev->pdev->subsystem_device == 0x029A) {
+					tmp &= ~(1 << 4);
+				}
 				if ((tmp >> 4) & 0x1) {
 					devices |= ATOM_DEVICE_DFP2_SUPPORT;
 					radeon_add_legacy_encoder(dev,
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 469661f..5407459 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -286,6 +286,8 @@
 			    p->chunks[p->chunk_ib_idx].kpage[1] == NULL) {
 				kfree(p->chunks[p->chunk_ib_idx].kpage[0]);
 				kfree(p->chunks[p->chunk_ib_idx].kpage[1]);
+				p->chunks[p->chunk_ib_idx].kpage[0] = NULL;
+				p->chunks[p->chunk_ib_idx].kpage[1] = NULL;
 				return -ENOMEM;
 			}
 		}
diff --git a/drivers/gpu/drm/radeon/radeon_cursor.c b/drivers/gpu/drm/radeon/radeon_cursor.c
index ad6df62..0d67674 100644
--- a/drivers/gpu/drm/radeon/radeon_cursor.c
+++ b/drivers/gpu/drm/radeon/radeon_cursor.c
@@ -241,7 +241,8 @@
 		y = 0;
 	}
 
-	if (ASIC_IS_AVIVO(rdev)) {
+	/* fixed on DCE6 and newer */
+	if (ASIC_IS_AVIVO(rdev) && !ASIC_IS_DCE6(rdev)) {
 		int i = 0;
 		struct drm_crtc *crtc_p;
 
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index edfc54e..0d6562b 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -429,7 +429,8 @@
 {
 	uint32_t reg;
 
-	if (efi_enabled && rdev->pdev->subsystem_vendor == PCI_VENDOR_ID_APPLE)
+	if (efi_enabled(EFI_BOOT) &&
+	    rdev->pdev->subsystem_vendor == PCI_VENDOR_ID_APPLE)
 		return false;
 
 	/* first check CRTCs */
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index 1da2386..05c96fa 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -1115,14 +1115,16 @@
 	}
 
 	radeon_fb = kzalloc(sizeof(*radeon_fb), GFP_KERNEL);
-	if (radeon_fb == NULL)
+	if (radeon_fb == NULL) {
+		drm_gem_object_unreference_unlocked(obj);
 		return ERR_PTR(-ENOMEM);
+	}
 
 	ret = radeon_framebuffer_init(dev, radeon_fb, mode_cmd, obj);
 	if (ret) {
 		kfree(radeon_fb);
 		drm_gem_object_unreference_unlocked(obj);
-		return NULL;
+		return ERR_PTR(ret);
 	}
 
 	return &radeon_fb->base;
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index 2430d80..cd72062 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -377,6 +377,9 @@
 {
 	int r;
 
+	/* make sure we aren't trying to allocate more space than there is on the ring */
+	if (ndw > (ring->ring_size / 4))
+		return -ENOMEM;
 	/* Align requested size with padding so unlock_commit can
 	 * pad safely */
 	ndw = (ndw + ring->align_mask) & ~ring->align_mask;
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 1d8ff2f..93f760e 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -38,6 +38,7 @@
 #include <drm/radeon_drm.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
+#include <linux/swiotlb.h>
 #include "radeon_reg.h"
 #include "radeon.h"
 
diff --git a/drivers/gpu/drm/radeon/reg_srcs/cayman b/drivers/gpu/drm/radeon/reg_srcs/cayman
index 0f656b1..a072fa8 100644
--- a/drivers/gpu/drm/radeon/reg_srcs/cayman
+++ b/drivers/gpu/drm/radeon/reg_srcs/cayman
@@ -1,5 +1,6 @@
 cayman 0x9400
 0x0000802C GRBM_GFX_INDEX
+0x00008040 WAIT_UNTIL
 0x000084FC CP_STRMOUT_CNTL
 0x000085F0 CP_COHER_CNTL
 0x000085F4 CP_COHER_SIZE
diff --git a/drivers/gpu/drm/radeon/rv515.c b/drivers/gpu/drm/radeon/rv515.c
index 2bb6d0e..435ed35 100644
--- a/drivers/gpu/drm/radeon/rv515.c
+++ b/drivers/gpu/drm/radeon/rv515.c
@@ -336,6 +336,8 @@
 				WREG32(R600_CITF_CNTL, blackout);
 		}
 	}
+	/* wait for the MC to settle */
+	udelay(100);
 }
 
 void rv515_mc_resume(struct radeon_device *rdev, struct rv515_mc_save *save)
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 44420fc..8be35c8 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -429,7 +429,7 @@
 	struct ttm_bo_device *bdev = bo->bdev;
 	struct ttm_bo_driver *driver = bdev->driver;
 
-	fbo = kzalloc(sizeof(*fbo), GFP_KERNEL);
+	fbo = kmalloc(sizeof(*fbo), GFP_KERNEL);
 	if (!fbo)
 		return -ENOMEM;
 
@@ -448,7 +448,12 @@
 	fbo->vm_node = NULL;
 	atomic_set(&fbo->cpu_writers, 0);
 
-	fbo->sync_obj = driver->sync_obj_ref(bo->sync_obj);
+	spin_lock(&bdev->fence_lock);
+	if (bo->sync_obj)
+		fbo->sync_obj = driver->sync_obj_ref(bo->sync_obj);
+	else
+		fbo->sync_obj = NULL;
+	spin_unlock(&bdev->fence_lock);
 	kref_init(&fbo->list_kref);
 	kref_init(&fbo->kref);
 	fbo->destroy = &ttm_transfered_destroy;
@@ -661,13 +666,11 @@
 		 */
 
 		set_bit(TTM_BO_PRIV_FLAG_MOVING, &bo->priv_flags);
-
-		/* ttm_buffer_object_transfer accesses bo->sync_obj */
-		ret = ttm_buffer_object_transfer(bo, &ghost_obj);
 		spin_unlock(&bdev->fence_lock);
 		if (tmp_obj)
 			driver->sync_obj_unref(&tmp_obj);
 
+		ret = ttm_buffer_object_transfer(bo, &ghost_obj);
 		if (ret)
 			return ret;
 
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 4dfa605..34e2547 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -306,6 +306,9 @@
 #define USB_VENDOR_ID_EZKEY		0x0518
 #define USB_DEVICE_ID_BTC_8193		0x0002
 
+#define USB_VENDOR_ID_FORMOSA          0x147a
+#define USB_DEVICE_ID_FORMOSA_IR_RECEIVER      0xe03e
+
 #define USB_VENDOR_ID_FREESCALE		0x15A2
 #define USB_DEVICE_ID_FREESCALE_MX28	0x004F
 
diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c
index 12e4fdc..e766b56 100644
--- a/drivers/hid/i2c-hid/i2c-hid.c
+++ b/drivers/hid/i2c-hid/i2c-hid.c
@@ -540,13 +540,24 @@
 {
 	struct i2c_client *client = hid->driver_data;
 	int report_id = buf[0];
+	int ret;
 
 	if (report_type == HID_INPUT_REPORT)
 		return -EINVAL;
 
-	return i2c_hid_set_report(client,
+	if (report_id) {
+		buf++;
+		count--;
+	}
+
+	ret = i2c_hid_set_report(client,
 				report_type == HID_FEATURE_REPORT ? 0x03 : 0x02,
 				report_id, buf, count);
+
+	if (report_id && ret >= 0)
+		ret++; /* add report_id to the number of transfered bytes */
+
+	return ret;
 }
 
 static int i2c_hid_parse(struct hid_device *hid)
diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c
index ac9e352..e0e6abf 100644
--- a/drivers/hid/usbhid/hid-quirks.c
+++ b/drivers/hid/usbhid/hid-quirks.c
@@ -70,6 +70,7 @@
 	{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_AXIS_295, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_DMI, USB_DEVICE_ID_DMI_ENC, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_ELO, USB_DEVICE_ID_ELO_TS2700, HID_QUIRK_NOGET },
+	{ USB_VENDOR_ID_FORMOSA, USB_DEVICE_ID_FORMOSA_IR_RECEIVER, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_FREESCALE, USB_DEVICE_ID_FREESCALE_MX28, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_MGE, USB_DEVICE_ID_MGE_UPS, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_NOVATEK, USB_DEVICE_ID_NOVATEK_MOUSE, HID_QUIRK_NO_INIT_REPORTS },
diff --git a/drivers/i2c/busses/i2c-designware-core.c b/drivers/i2c/busses/i2c-designware-core.c
index cbba7db..f5258c2 100644
--- a/drivers/i2c/busses/i2c-designware-core.c
+++ b/drivers/i2c/busses/i2c-designware-core.c
@@ -34,6 +34,7 @@
 #include <linux/io.h>
 #include <linux/pm_runtime.h>
 #include <linux/delay.h>
+#include <linux/module.h>
 #include "i2c-designware-core.h"
 
 /*
@@ -725,3 +726,6 @@
 	return dw_readl(dev, DW_IC_COMP_PARAM_1);
 }
 EXPORT_SYMBOL_GPL(i2c_dw_read_comp_param);
+
+MODULE_DESCRIPTION("Synopsys DesignWare I2C bus adapter core");
+MODULE_LICENSE("GPL");
diff --git a/drivers/i2c/busses/i2c-mxs.c b/drivers/i2c/busses/i2c-mxs.c
index 1b1a936..d6abaf2 100644
--- a/drivers/i2c/busses/i2c-mxs.c
+++ b/drivers/i2c/busses/i2c-mxs.c
@@ -127,7 +127,7 @@
 	struct device *dev;
 	void __iomem *regs;
 	struct completion cmd_complete;
-	u32 cmd_err;
+	int cmd_err;
 	struct i2c_adapter adapter;
 	const struct mxs_i2c_speed_config *speed;
 
@@ -316,7 +316,7 @@
 	if (msg->len == 0)
 		return -EINVAL;
 
-	init_completion(&i2c->cmd_complete);
+	INIT_COMPLETION(i2c->cmd_complete);
 	i2c->cmd_err = 0;
 
 	ret = mxs_i2c_dma_setup_xfer(adap, msg, flags);
@@ -473,6 +473,8 @@
 	i2c->dev = dev;
 	i2c->speed = &mxs_i2c_95kHz_config;
 
+	init_completion(&i2c->cmd_complete);
+
 	if (dev->of_node) {
 		err = mxs_i2c_get_ofdata(i2c);
 		if (err)
diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c
index 20d41bf..4cc2f05 100644
--- a/drivers/i2c/busses/i2c-omap.c
+++ b/drivers/i2c/busses/i2c-omap.c
@@ -803,7 +803,7 @@
 			if (stat & OMAP_I2C_STAT_AL) {
 				dev_err(dev->dev, "Arbitration lost\n");
 				dev->cmd_err |= OMAP_I2C_STAT_AL;
-				omap_i2c_ack_stat(dev, OMAP_I2C_STAT_NACK);
+				omap_i2c_ack_stat(dev, OMAP_I2C_STAT_AL);
 			}
 
 			return -EIO;
@@ -963,7 +963,7 @@
 				i2c_omap_errata_i207(dev, stat);
 
 			omap_i2c_ack_stat(dev, OMAP_I2C_STAT_RDR);
-			break;
+			continue;
 		}
 
 		if (stat & OMAP_I2C_STAT_RRDY) {
@@ -989,7 +989,7 @@
 				break;
 
 			omap_i2c_ack_stat(dev, OMAP_I2C_STAT_XDR);
-			break;
+			continue;
 		}
 
 		if (stat & OMAP_I2C_STAT_XRDY) {
diff --git a/drivers/i2c/busses/i2c-sirf.c b/drivers/i2c/busses/i2c-sirf.c
index 3f1818b..e03381a 100644
--- a/drivers/i2c/busses/i2c-sirf.c
+++ b/drivers/i2c/busses/i2c-sirf.c
@@ -12,6 +12,7 @@
 #include <linux/slab.h>
 #include <linux/platform_device.h>
 #include <linux/i2c.h>
+#include <linux/of_i2c.h>
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/io.h>
@@ -328,6 +329,7 @@
 	adap->algo = &i2c_sirfsoc_algo;
 	adap->algo_data = siic;
 
+	adap->dev.of_node = pdev->dev.of_node;
 	adap->dev.parent = &pdev->dev;
 	adap->nr = pdev->id;
 
@@ -371,6 +373,8 @@
 
 	clk_disable(clk);
 
+	of_i2c_register_devices(adap);
+
 	dev_info(&pdev->dev, " I2C adapter ready to operate\n");
 
 	return 0;
diff --git a/drivers/i2c/muxes/i2c-mux-pinctrl.c b/drivers/i2c/muxes/i2c-mux-pinctrl.c
index 1e44d04..a43c0ce 100644
--- a/drivers/i2c/muxes/i2c-mux-pinctrl.c
+++ b/drivers/i2c/muxes/i2c-mux-pinctrl.c
@@ -167,7 +167,7 @@
 	}
 
 	mux->busses = devm_kzalloc(&pdev->dev,
-				   sizeof(mux->busses) * mux->pdata->bus_count,
+				   sizeof(*mux->busses) * mux->pdata->bus_count,
 				   GFP_KERNEL);
 	if (!mux->busses) {
 		dev_err(&pdev->dev, "Cannot allocate busses\n");
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 4ba384f..2df9414 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -448,8 +448,6 @@
 	else
 		on_each_cpu(__setup_broadcast_timer, (void *)true, 1);
 
-	register_cpu_notifier(&cpu_hotplug_notifier);
-
 	pr_debug(PREFIX "v" INTEL_IDLE_VERSION
 		" model 0x%X\n", boot_cpu_data.x86_model);
 
@@ -612,6 +610,7 @@
 			return retval;
 		}
 	}
+	register_cpu_notifier(&cpu_hotplug_notifier);
 
 	return 0;
 }
diff --git a/drivers/infiniband/hw/qib/qib_qp.c b/drivers/infiniband/hw/qib/qib_qp.c
index 4850d03..3527509 100644
--- a/drivers/infiniband/hw/qib/qib_qp.c
+++ b/drivers/infiniband/hw/qib/qib_qp.c
@@ -263,20 +263,15 @@
 		struct qib_qp __rcu **qpp;
 
 		qpp = &dev->qp_table[n];
-		q = rcu_dereference_protected(*qpp,
-			lockdep_is_held(&dev->qpt_lock));
-		for (; q; qpp = &q->next) {
+		for (; (q = rcu_dereference_protected(*qpp,
+				lockdep_is_held(&dev->qpt_lock))) != NULL;
+				qpp = &q->next)
 			if (q == qp) {
 				atomic_dec(&qp->refcount);
 				*qpp = qp->next;
 				rcu_assign_pointer(qp->next, NULL);
-				q = rcu_dereference_protected(*qpp,
-					lockdep_is_held(&dev->qpt_lock));
 				break;
 			}
-			q = rcu_dereference_protected(*qpp,
-				lockdep_is_held(&dev->qpt_lock));
-		}
 	}
 
 	spin_unlock_irqrestore(&dev->qpt_lock, flags);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 03103d2..67b0c1d 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -741,6 +741,9 @@
 
 	tx_req->mapping = addr;
 
+	skb_orphan(skb);
+	skb_dst_drop(skb);
+
 	rc = post_send(priv, tx, tx->tx_head & (ipoib_sendq_size - 1),
 		       addr, skb->len);
 	if (unlikely(rc)) {
@@ -752,9 +755,6 @@
 		dev->trans_start = jiffies;
 		++tx->tx_head;
 
-		skb_orphan(skb);
-		skb_dst_drop(skb);
-
 		if (++priv->tx_outstanding == ipoib_sendq_size) {
 			ipoib_dbg(priv, "TX ring 0x%x full, stopping kernel net queue\n",
 				  tx->qp->qp_num);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index a1bca70..2cfa76f 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -600,6 +600,9 @@
 		netif_stop_queue(dev);
 	}
 
+	skb_orphan(skb);
+	skb_dst_drop(skb);
+
 	rc = post_send(priv, priv->tx_head & (ipoib_sendq_size - 1),
 		       address->ah, qpn, tx_req, phead, hlen);
 	if (unlikely(rc)) {
@@ -615,9 +618,6 @@
 
 		address->last_send = priv->tx_head;
 		++priv->tx_head;
-
-		skb_orphan(skb);
-		skb_dst_drop(skb);
 	}
 
 	if (unlikely(priv->tx_outstanding > MAX_SEND_CQE))
diff --git a/drivers/input/input.c b/drivers/input/input.c
index ce01332f..c044699 100644
--- a/drivers/input/input.c
+++ b/drivers/input/input.c
@@ -1785,12 +1785,13 @@
  * its driver (or binding fails). Once managed input device is allocated,
  * it is ready to be set up and registered in the same fashion as regular
  * input device. There are no special devm_input_device_[un]register()
- * variants, regular ones work with both managed and unmanaged devices.
+ * variants, regular ones work with both managed and unmanaged devices,
+ * should you need them. In most cases however, managed input device need
+ * not be explicitly unregistered or freed.
  *
  * NOTE: the owner device is set up as parent of input device and users
  * should not override it.
  */
-
 struct input_dev *devm_input_allocate_device(struct device *dev)
 {
 	struct input_dev *input;
@@ -2004,6 +2005,17 @@
  * Once device has been successfully registered it can be unregistered
  * with input_unregister_device(); input_free_device() should not be
  * called in this case.
+ *
+ * Note that this function is also used to register managed input devices
+ * (ones allocated with devm_input_allocate_device()). Such managed input
+ * devices need not be explicitly unregistered or freed, their tear down
+ * is controlled by the devres infrastructure. It is also worth noting
+ * that tear down of managed input devices is internally a 2-step process:
+ * registered managed input device is first unregistered, but stays in
+ * memory and can still handle input_event() calls (although events will
+ * not be delivered anywhere). The freeing of managed input device will
+ * happen later, when devres stack is unwound to the point where device
+ * allocation was made.
  */
 int input_register_device(struct input_dev *dev)
 {
diff --git a/drivers/input/joystick/analog.c b/drivers/input/joystick/analog.c
index 358cd7e..7cd74e2 100644
--- a/drivers/input/joystick/analog.c
+++ b/drivers/input/joystick/analog.c
@@ -162,7 +162,7 @@
 #define GET_TIME(x)	do { x = get_cycles(); } while (0)
 #define DELTA(x,y)	((y)-(x))
 #define TIME_NAME	"PCC"
-#elif defined(CONFIG_MN10300)
+#elif defined(CONFIG_MN10300) || defined(CONFIG_TILE)
 #define GET_TIME(x)	do { x = get_cycles(); } while (0)
 #define DELTA(x, y)	((x) - (y))
 #define TIME_NAME	"TSC"
diff --git a/drivers/input/keyboard/lm8323.c b/drivers/input/keyboard/lm8323.c
index 93c8126..0de23f4 100644
--- a/drivers/input/keyboard/lm8323.c
+++ b/drivers/input/keyboard/lm8323.c
@@ -398,7 +398,7 @@
 			lm8323_configure(lm);
 		}
 		for (i = 0; i < LM8323_NUM_PWMS; i++) {
-			if (ints & (1 << (INT_PWM1 + i))) {
+			if (ints & (INT_PWM1 << i)) {
 				dev_vdbg(&lm->client->dev,
 					 "pwm%d engine completed\n", i);
 				pwm_done(&lm->pwm[i]);
diff --git a/drivers/input/tablet/wacom_sys.c b/drivers/input/tablet/wacom_sys.c
index f92d34f..aaf23ae 100644
--- a/drivers/input/tablet/wacom_sys.c
+++ b/drivers/input/tablet/wacom_sys.c
@@ -553,10 +553,10 @@
 	if (!rep_data)
 		return error;
 
-	rep_data[0] = report_id;
-	rep_data[1] = mode;
-
 	do {
+		rep_data[0] = report_id;
+		rep_data[1] = mode;
+
 		error = wacom_set_report(intf, WAC_HID_FEATURE_REPORT,
 		                         report_id, rep_data, length, 1);
 		if (error >= 0)
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 81837b0..faf10ba 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -975,6 +975,38 @@
 }
 
 /*
+ * Family15h Model 10h-1fh erratum 746 (IOMMU Logging May Stall Translations)
+ * Workaround:
+ *     BIOS should disable L2B micellaneous clock gating by setting
+ *     L2_L2B_CK_GATE_CONTROL[CKGateL2BMiscDisable](D0F2xF4_x90[2]) = 1b
+ */
+static void __init amd_iommu_erratum_746_workaround(struct amd_iommu *iommu)
+{
+	u32 value;
+
+	if ((boot_cpu_data.x86 != 0x15) ||
+	    (boot_cpu_data.x86_model < 0x10) ||
+	    (boot_cpu_data.x86_model > 0x1f))
+		return;
+
+	pci_write_config_dword(iommu->dev, 0xf0, 0x90);
+	pci_read_config_dword(iommu->dev, 0xf4, &value);
+
+	if (value & BIT(2))
+		return;
+
+	/* Select NB indirect register 0x90 and enable writing */
+	pci_write_config_dword(iommu->dev, 0xf0, 0x90 | (1 << 8));
+
+	pci_write_config_dword(iommu->dev, 0xf4, value | 0x4);
+	pr_info("AMD-Vi: Applying erratum 746 workaround for IOMMU at %s\n",
+		dev_name(&iommu->dev->dev));
+
+	/* Clear the enable writing bit */
+	pci_write_config_dword(iommu->dev, 0xf0, 0x90);
+}
+
+/*
  * This function clues the initialization function for one IOMMU
  * together and also allocates the command buffer and programs the
  * hardware. It does NOT enable the IOMMU. This is done afterwards.
@@ -1172,6 +1204,8 @@
 			iommu->stored_l2[i] = iommu_read_l2(iommu, i);
 	}
 
+	amd_iommu_erratum_746_workaround(iommu);
+
 	return pci_enable_device(iommu->dev);
 }
 
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index b9d0911..eca2801 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -4234,6 +4234,21 @@
 	.pgsize_bitmap	= INTEL_IOMMU_PGSIZES,
 };
 
+static void quirk_iommu_g4x_gfx(struct pci_dev *dev)
+{
+	/* G4x/GM45 integrated gfx dmar support is totally busted. */
+	printk(KERN_INFO "DMAR: Disabling IOMMU for graphics on this chipset\n");
+	dmar_map_gfx = 0;
+}
+
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2a40, quirk_iommu_g4x_gfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e00, quirk_iommu_g4x_gfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e10, quirk_iommu_g4x_gfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e20, quirk_iommu_g4x_gfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e30, quirk_iommu_g4x_gfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e40, quirk_iommu_g4x_gfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e90, quirk_iommu_g4x_gfx);
+
 static void quirk_iommu_rwbf(struct pci_dev *dev)
 {
 	/*
@@ -4242,12 +4257,6 @@
 	 */
 	printk(KERN_INFO "DMAR: Forcing write-buffer flush capability\n");
 	rwbf_quirk = 1;
-
-	/* https://bugzilla.redhat.com/show_bug.cgi?id=538163 */
-	if (dev->revision == 0x07) {
-		printk(KERN_INFO "DMAR: Disabling IOMMU for graphics on this chipset\n");
-		dmar_map_gfx = 0;
-	}
 }
 
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2a40, quirk_iommu_rwbf);
diff --git a/drivers/isdn/gigaset/capi.c b/drivers/isdn/gigaset/capi.c
index 68452b7..03a0a01 100644
--- a/drivers/isdn/gigaset/capi.c
+++ b/drivers/isdn/gigaset/capi.c
@@ -248,6 +248,8 @@
 		CAPIMSG_APPID(data), CAPIMSG_MSGID(data), l,
 		CAPIMSG_CONTROL(data));
 	l -= 12;
+	if (l <= 0)
+		return;
 	dbgline = kmalloc(3 * l, GFP_ATOMIC);
 	if (!dbgline)
 		return;
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 3d8984e..9e58dbd 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -340,24 +340,22 @@
 }
 
 /*
- * validate_rebuild_devices
+ * validate_raid_redundancy
  * @rs
  *
- * Determine if the devices specified for rebuild can result in a valid
- * usable array that is capable of rebuilding the given devices.
+ * Determine if there are enough devices in the array that haven't
+ * failed (or are being rebuilt) to form a usable array.
  *
  * Returns: 0 on success, -EINVAL on failure.
  */
-static int validate_rebuild_devices(struct raid_set *rs)
+static int validate_raid_redundancy(struct raid_set *rs)
 {
 	unsigned i, rebuild_cnt = 0;
 	unsigned rebuilds_per_group, copies, d;
 
-	if (!(rs->print_flags & DMPF_REBUILD))
-		return 0;
-
 	for (i = 0; i < rs->md.raid_disks; i++)
-		if (!test_bit(In_sync, &rs->dev[i].rdev.flags))
+		if (!test_bit(In_sync, &rs->dev[i].rdev.flags) ||
+		    !rs->dev[i].rdev.sb_page)
 			rebuild_cnt++;
 
 	switch (rs->raid_type->level) {
@@ -393,27 +391,24 @@
 		 *          A    A    B    B    C
 		 *          C    D    D    E    E
 		 */
-		rebuilds_per_group = 0;
 		for (i = 0; i < rs->md.raid_disks * copies; i++) {
+			if (!(i % copies))
+				rebuilds_per_group = 0;
 			d = i % rs->md.raid_disks;
-			if (!test_bit(In_sync, &rs->dev[d].rdev.flags) &&
+			if ((!rs->dev[d].rdev.sb_page ||
+			     !test_bit(In_sync, &rs->dev[d].rdev.flags)) &&
 			    (++rebuilds_per_group >= copies))
 				goto too_many;
-			if (!((i + 1) % copies))
-				rebuilds_per_group = 0;
 		}
 		break;
 	default:
-		DMERR("The rebuild parameter is not supported for %s",
-		      rs->raid_type->name);
-		rs->ti->error = "Rebuild not supported for this RAID type";
-		return -EINVAL;
+		if (rebuild_cnt)
+			return -EINVAL;
 	}
 
 	return 0;
 
 too_many:
-	rs->ti->error = "Too many rebuild devices specified";
 	return -EINVAL;
 }
 
@@ -664,9 +659,6 @@
 	}
 	rs->md.dev_sectors = sectors_per_dev;
 
-	if (validate_rebuild_devices(rs))
-		return -EINVAL;
-
 	/* Assume there are no metadata devices until the drives are parsed */
 	rs->md.persistent = 0;
 	rs->md.external = 1;
@@ -995,28 +987,10 @@
 static int analyse_superblocks(struct dm_target *ti, struct raid_set *rs)
 {
 	int ret;
-	unsigned redundancy = 0;
 	struct raid_dev *dev;
 	struct md_rdev *rdev, *tmp, *freshest;
 	struct mddev *mddev = &rs->md;
 
-	switch (rs->raid_type->level) {
-	case 1:
-		redundancy = rs->md.raid_disks - 1;
-		break;
-	case 4:
-	case 5:
-	case 6:
-		redundancy = rs->raid_type->parity_devs;
-		break;
-	case 10:
-		redundancy = raid10_md_layout_to_copies(mddev->layout) - 1;
-		break;
-	default:
-		ti->error = "Unknown RAID type";
-		return -EINVAL;
-	}
-
 	freshest = NULL;
 	rdev_for_each_safe(rdev, tmp, mddev) {
 		/*
@@ -1045,44 +1019,43 @@
 			break;
 		default:
 			dev = container_of(rdev, struct raid_dev, rdev);
-			if (redundancy--) {
-				if (dev->meta_dev)
-					dm_put_device(ti, dev->meta_dev);
+			if (dev->meta_dev)
+				dm_put_device(ti, dev->meta_dev);
 
-				dev->meta_dev = NULL;
-				rdev->meta_bdev = NULL;
+			dev->meta_dev = NULL;
+			rdev->meta_bdev = NULL;
 
-				if (rdev->sb_page)
-					put_page(rdev->sb_page);
+			if (rdev->sb_page)
+				put_page(rdev->sb_page);
 
-				rdev->sb_page = NULL;
+			rdev->sb_page = NULL;
 
-				rdev->sb_loaded = 0;
+			rdev->sb_loaded = 0;
 
-				/*
-				 * We might be able to salvage the data device
-				 * even though the meta device has failed.  For
-				 * now, we behave as though '- -' had been
-				 * set for this device in the table.
-				 */
-				if (dev->data_dev)
-					dm_put_device(ti, dev->data_dev);
+			/*
+			 * We might be able to salvage the data device
+			 * even though the meta device has failed.  For
+			 * now, we behave as though '- -' had been
+			 * set for this device in the table.
+			 */
+			if (dev->data_dev)
+				dm_put_device(ti, dev->data_dev);
 
-				dev->data_dev = NULL;
-				rdev->bdev = NULL;
+			dev->data_dev = NULL;
+			rdev->bdev = NULL;
 
-				list_del(&rdev->same_set);
-
-				continue;
-			}
-			ti->error = "Failed to load superblock";
-			return ret;
+			list_del(&rdev->same_set);
 		}
 	}
 
 	if (!freshest)
 		return 0;
 
+	if (validate_raid_redundancy(rs)) {
+		rs->ti->error = "Insufficient redundancy to activate array";
+		return -EINVAL;
+	}
+
 	/*
 	 * Validation of the freshest device provides the source of
 	 * validation for the remaining devices.
@@ -1432,7 +1405,7 @@
 
 static struct target_type raid_target = {
 	.name = "raid",
-	.version = {1, 4, 0},
+	.version = {1, 4, 1},
 	.module = THIS_MODULE,
 	.ctr = raid_ctr,
 	.dtr = raid_dtr,
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 675ae52..5409607 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -2746,19 +2746,9 @@
 	return 0;
 }
 
-/*
- * A thin device always inherits its queue limits from its pool.
- */
-static void thin_io_hints(struct dm_target *ti, struct queue_limits *limits)
-{
-	struct thin_c *tc = ti->private;
-
-	*limits = bdev_get_queue(tc->pool_dev->bdev)->limits;
-}
-
 static struct target_type thin_target = {
 	.name = "thin",
-	.version = {1, 6, 0},
+	.version = {1, 7, 0},
 	.module	= THIS_MODULE,
 	.ctr = thin_ctr,
 	.dtr = thin_dtr,
@@ -2767,7 +2757,6 @@
 	.postsuspend = thin_postsuspend,
 	.status = thin_status,
 	.iterate_devices = thin_iterate_devices,
-	.io_hints = thin_io_hints,
 };
 
 /*----------------------------------------------------------------*/
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index c72e4d5..314a0e2 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1188,6 +1188,7 @@
 {
 	struct dm_target *ti;
 	sector_t len;
+	unsigned num_requests;
 
 	do {
 		ti = dm_table_find_target(ci->map, ci->sector);
@@ -1200,7 +1201,8 @@
 		 * reconfiguration might also have changed that since the
 		 * check was performed.
 		 */
-		if (!get_num_requests || !get_num_requests(ti))
+		num_requests = get_num_requests ? get_num_requests(ti) : 0;
+		if (!num_requests)
 			return -EOPNOTSUPP;
 
 		if (is_split_required && !is_split_required(ti))
@@ -1208,7 +1210,7 @@
 		else
 			len = min(ci->sector_count, max_io_len(ci->sector, ti));
 
-		__issue_target_requests(ci, ti, ti->num_discard_requests, len);
+		__issue_target_requests(ci, ti, num_requests, len);
 
 		ci->sector += len;
 	} while (ci->sector_count -= len);
diff --git a/drivers/media/dvb-core/dvb_frontend.c b/drivers/media/dvb-core/dvb_frontend.c
index 49d9504..0223ad2 100644
--- a/drivers/media/dvb-core/dvb_frontend.c
+++ b/drivers/media/dvb-core/dvb_frontend.c
@@ -1820,7 +1820,7 @@
 	struct dvb_frontend *fe = dvbdev->priv;
 	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	struct dvb_frontend_private *fepriv = fe->frontend_priv;
-	int err = -ENOTTY;
+	int err = -EOPNOTSUPP;
 
 	dev_dbg(fe->dvb->device, "%s: (%d)\n", __func__, _IOC_NR(cmd));
 	if (fepriv->exit != DVB_FE_NO_EXIT)
@@ -1938,7 +1938,7 @@
 		}
 
 	} else
-		err = -ENOTTY;
+		err = -EOPNOTSUPP;
 
 out:
 	kfree(tvp);
@@ -2071,7 +2071,7 @@
 	struct dvb_frontend *fe = dvbdev->priv;
 	struct dvb_frontend_private *fepriv = fe->frontend_priv;
 	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
-	int err = -ENOTTY;
+	int err = -EOPNOTSUPP;
 
 	switch (cmd) {
 	case FE_GET_INFO: {
diff --git a/drivers/media/platform/coda.c b/drivers/media/platform/coda.c
index 1cf8293..4a980e0 100644
--- a/drivers/media/platform/coda.c
+++ b/drivers/media/platform/coda.c
@@ -23,8 +23,8 @@
 #include <linux/slab.h>
 #include <linux/videodev2.h>
 #include <linux/of.h>
+#include <linux/platform_data/imx-iram.h>
 
-#include <mach/iram.h>
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-ioctl.h>
diff --git a/drivers/media/radio/radio-keene.c b/drivers/media/radio/radio-keene.c
index e10e525..296941a 100644
--- a/drivers/media/radio/radio-keene.c
+++ b/drivers/media/radio/radio-keene.c
@@ -374,6 +374,7 @@
 	radio->vdev.ioctl_ops = &usb_keene_ioctl_ops;
 	radio->vdev.lock = &radio->lock;
 	radio->vdev.release = video_device_release_empty;
+	radio->vdev.vfl_dir = VFL_DIR_TX;
 
 	radio->usbdev = interface_to_usbdev(intf);
 	radio->intf = intf;
diff --git a/drivers/media/radio/radio-si4713.c b/drivers/media/radio/radio-si4713.c
index a082e40..1507c9d 100644
--- a/drivers/media/radio/radio-si4713.c
+++ b/drivers/media/radio/radio-si4713.c
@@ -250,6 +250,7 @@
 	.name			= "radio-si4713",
 	.release		= video_device_release,
 	.ioctl_ops		= &radio_si4713_ioctl_ops,
+	.vfl_dir		= VFL_DIR_TX,
 };
 
 /* Platform driver interface */
diff --git a/drivers/media/radio/radio-wl1273.c b/drivers/media/radio/radio-wl1273.c
index c48be19..cabbe3a 100644
--- a/drivers/media/radio/radio-wl1273.c
+++ b/drivers/media/radio/radio-wl1273.c
@@ -1971,6 +1971,7 @@
 	.ioctl_ops		= &wl1273_ioctl_ops,
 	.name			= WL1273_FM_DRIVER_NAME,
 	.release		= wl1273_vdev_release,
+	.vfl_dir		= VFL_DIR_TX,
 };
 
 static int wl1273_fm_radio_remove(struct platform_device *pdev)
diff --git a/drivers/media/radio/wl128x/fmdrv_v4l2.c b/drivers/media/radio/wl128x/fmdrv_v4l2.c
index 048de45..0a8ee8f 100644
--- a/drivers/media/radio/wl128x/fmdrv_v4l2.c
+++ b/drivers/media/radio/wl128x/fmdrv_v4l2.c
@@ -518,6 +518,16 @@
 	.ioctl_ops = &fm_drv_ioctl_ops,
 	.name = FM_DRV_NAME,
 	.release = video_device_release,
+	/*
+	 * To ensure both the tuner and modulator ioctls are accessible we
+	 * set the vfl_dir to M2M to indicate this.
+	 *
+	 * It is not really a mem2mem device of course, but it can both receive
+	 * and transmit using the same radio device. It's the only radio driver
+	 * that does this and it should really be split in two radio devices,
+	 * but that would affect applications using this driver.
+	 */
+	.vfl_dir = VFL_DIR_M2M,
 };
 
 int fm_v4l2_init_video_device(struct fmdev *fmdev, int radio_nr)
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index 47ad4e2..ff553ba 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -237,6 +237,7 @@
 	depends on I2C=y && GPIOLIB
 	select MFD_CORE
 	select REGMAP_I2C
+	select REGMAP_IRQ
 	select IRQ_DOMAIN
 	help
 	  if you say yes here you get support for the TPS65910 series of
diff --git a/drivers/mfd/ab8500-core.c b/drivers/mfd/ab8500-core.c
index e1650ba..4778bb1 100644
--- a/drivers/mfd/ab8500-core.c
+++ b/drivers/mfd/ab8500-core.c
@@ -19,6 +19,7 @@
 #include <linux/mfd/core.h>
 #include <linux/mfd/abx500.h>
 #include <linux/mfd/abx500/ab8500.h>
+#include <linux/mfd/abx500/ab8500-bm.h>
 #include <linux/mfd/dbx500-prcmu.h>
 #include <linux/regulator/ab8500.h>
 #include <linux/of.h>
diff --git a/drivers/mfd/arizona-core.c b/drivers/mfd/arizona-core.c
index bc8a3ed..222c03a 100644
--- a/drivers/mfd/arizona-core.c
+++ b/drivers/mfd/arizona-core.c
@@ -239,7 +239,12 @@
 		return ret;
 	}
 
-	regcache_sync(arizona->regmap);
+	ret = regcache_sync(arizona->regmap);
+	if (ret != 0) {
+		dev_err(arizona->dev, "Failed to restore register cache\n");
+		regulator_disable(arizona->dcvdd);
+		return ret;
+	}
 
 	return 0;
 }
diff --git a/drivers/mfd/arizona-irq.c b/drivers/mfd/arizona-irq.c
index 74713bf..2bec5f0 100644
--- a/drivers/mfd/arizona-irq.c
+++ b/drivers/mfd/arizona-irq.c
@@ -176,14 +176,7 @@
 		aod = &wm5102_aod;
 		irq = &wm5102_irq;
 
-		switch (arizona->rev) {
-		case 0:
-		case 1:
-			ctrlif_error = false;
-			break;
-		default:
-			break;
-		}
+		ctrlif_error = false;
 		break;
 #endif
 #ifdef CONFIG_MFD_WM5110
@@ -191,14 +184,7 @@
 		aod = &wm5110_aod;
 		irq = &wm5110_irq;
 
-		switch (arizona->rev) {
-		case 0:
-		case 1:
-			ctrlif_error = false;
-			break;
-		default:
-			break;
-		}
+		ctrlif_error = false;
 		break;
 #endif
 	default:
diff --git a/drivers/mfd/da9052-i2c.c b/drivers/mfd/da9052-i2c.c
index ac74a4d..885e567 100644
--- a/drivers/mfd/da9052-i2c.c
+++ b/drivers/mfd/da9052-i2c.c
@@ -27,6 +27,66 @@
 #include <linux/of_device.h>
 #endif
 
+/* I2C safe register check */
+static inline bool i2c_safe_reg(unsigned char reg)
+{
+	switch (reg) {
+	case DA9052_STATUS_A_REG:
+	case DA9052_STATUS_B_REG:
+	case DA9052_STATUS_C_REG:
+	case DA9052_STATUS_D_REG:
+	case DA9052_ADC_RES_L_REG:
+	case DA9052_ADC_RES_H_REG:
+	case DA9052_VDD_RES_REG:
+	case DA9052_ICHG_AV_REG:
+	case DA9052_TBAT_RES_REG:
+	case DA9052_ADCIN4_RES_REG:
+	case DA9052_ADCIN5_RES_REG:
+	case DA9052_ADCIN6_RES_REG:
+	case DA9052_TJUNC_RES_REG:
+	case DA9052_TSI_X_MSB_REG:
+	case DA9052_TSI_Y_MSB_REG:
+	case DA9052_TSI_LSB_REG:
+	case DA9052_TSI_Z_MSB_REG:
+		return true;
+	default:
+		return false;
+	}
+}
+
+/*
+ * There is an issue with DA9052 and DA9053_AA/BA/BB PMIC where the PMIC
+ * gets lockup up or fails to respond following a system reset.
+ * This fix is to follow any read or write with a dummy read to a safe
+ * register.
+ */
+int da9052_i2c_fix(struct da9052 *da9052, unsigned char reg)
+{
+	int val;
+
+	switch (da9052->chip_id) {
+	case DA9052:
+	case DA9053_AA:
+	case DA9053_BA:
+	case DA9053_BB:
+		/* A dummy read to a safe register address. */
+	if (!i2c_safe_reg(reg))
+			return regmap_read(da9052->regmap,
+					   DA9052_PARK_REGISTER,
+					   &val);
+		break;
+	default:
+		/*
+		 * For other chips parking of I2C register
+		 * to a safe place is not required.
+		 */
+		break;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(da9052_i2c_fix);
+
 static int da9052_i2c_enable_multiwrite(struct da9052 *da9052)
 {
 	int reg_val, ret;
@@ -83,6 +143,7 @@
 
 	da9052->dev = &client->dev;
 	da9052->chip_irq = client->irq;
+	da9052->fix_io = da9052_i2c_fix;
 
 	i2c_set_clientdata(client, da9052);
 
diff --git a/drivers/mfd/db8500-prcmu.c b/drivers/mfd/db8500-prcmu.c
index dc8826d..268f45d4 100644
--- a/drivers/mfd/db8500-prcmu.c
+++ b/drivers/mfd/db8500-prcmu.c
@@ -2524,7 +2524,7 @@
 
 		for (n = 0; n < NUM_PRCMU_WAKEUPS; n++) {
 			if (ev & prcmu_irq_bit[n])
-				generic_handle_irq(IRQ_PRCMU_BASE + n);
+				generic_handle_irq(irq_find_mapping(db8500_irq_domain, n));
 		}
 		r = true;
 		break;
@@ -2737,13 +2737,14 @@
 }
 
 static struct irq_domain_ops db8500_irq_ops = {
-        .map    = db8500_irq_map,
-        .xlate  = irq_domain_xlate_twocell,
+	.map    = db8500_irq_map,
+	.xlate  = irq_domain_xlate_twocell,
 };
 
 static int db8500_irq_init(struct device_node *np)
 {
-	int irq_base = -1;
+	int irq_base = 0;
+	int i;
 
 	/* In the device tree case, just take some IRQs */
 	if (!np)
@@ -2758,6 +2759,10 @@
 		return -ENOSYS;
 	}
 
+	/* All wakeups will be used, so create mappings for all */
+	for (i = 0; i < NUM_PRCMU_WAKEUPS; i++)
+		irq_create_mapping(db8500_irq_domain, i);
+
 	return 0;
 }
 
diff --git a/drivers/mfd/max77686.c b/drivers/mfd/max77686.c
index f6878f8..4d73963 100644
--- a/drivers/mfd/max77686.c
+++ b/drivers/mfd/max77686.c
@@ -93,15 +93,6 @@
 	if (max77686 == NULL)
 		return -ENOMEM;
 
-	max77686->regmap = regmap_init_i2c(i2c, &max77686_regmap_config);
-	if (IS_ERR(max77686->regmap)) {
-		ret = PTR_ERR(max77686->regmap);
-		dev_err(max77686->dev, "Failed to allocate register map: %d\n",
-				ret);
-		kfree(max77686);
-		return ret;
-	}
-
 	i2c_set_clientdata(i2c, max77686);
 	max77686->dev = &i2c->dev;
 	max77686->i2c = i2c;
@@ -111,6 +102,15 @@
 	max77686->irq_gpio = pdata->irq_gpio;
 	max77686->irq = i2c->irq;
 
+	max77686->regmap = regmap_init_i2c(i2c, &max77686_regmap_config);
+	if (IS_ERR(max77686->regmap)) {
+		ret = PTR_ERR(max77686->regmap);
+		dev_err(max77686->dev, "Failed to allocate register map: %d\n",
+				ret);
+		kfree(max77686);
+		return ret;
+	}
+
 	if (regmap_read(max77686->regmap,
 			 MAX77686_REG_DEVICE_ID, &data) < 0) {
 		dev_err(max77686->dev,
diff --git a/drivers/mfd/max77693.c b/drivers/mfd/max77693.c
index cc5155e..9e60fed 100644
--- a/drivers/mfd/max77693.c
+++ b/drivers/mfd/max77693.c
@@ -114,35 +114,37 @@
 	u8 reg_data;
 	int ret = 0;
 
+	if (!pdata) {
+		dev_err(&i2c->dev, "No platform data found.\n");
+		return -EINVAL;
+	}
+
 	max77693 = devm_kzalloc(&i2c->dev,
 			sizeof(struct max77693_dev), GFP_KERNEL);
 	if (max77693 == NULL)
 		return -ENOMEM;
 
-	max77693->regmap = devm_regmap_init_i2c(i2c, &max77693_regmap_config);
-	if (IS_ERR(max77693->regmap)) {
-		ret = PTR_ERR(max77693->regmap);
-		dev_err(max77693->dev,"failed to allocate register map: %d\n",
-				ret);
-		goto err_regmap;
-	}
-
 	i2c_set_clientdata(i2c, max77693);
 	max77693->dev = &i2c->dev;
 	max77693->i2c = i2c;
 	max77693->irq = i2c->irq;
 	max77693->type = id->driver_data;
 
-	if (!pdata)
-		goto err_regmap;
+	max77693->regmap = devm_regmap_init_i2c(i2c, &max77693_regmap_config);
+	if (IS_ERR(max77693->regmap)) {
+		ret = PTR_ERR(max77693->regmap);
+		dev_err(max77693->dev, "failed to allocate register map: %d\n",
+				ret);
+		return ret;
+	}
 
 	max77693->wakeup = pdata->wakeup;
 
-	if (max77693_read_reg(max77693->regmap,
-				MAX77693_PMIC_REG_PMIC_ID2, &reg_data) < 0) {
+	ret = max77693_read_reg(max77693->regmap, MAX77693_PMIC_REG_PMIC_ID2,
+				&reg_data);
+	if (ret < 0) {
 		dev_err(max77693->dev, "device not found on this channel\n");
-		ret = -ENODEV;
-		goto err_regmap;
+		return ret;
 	} else
 		dev_info(max77693->dev, "device ID: 0x%x\n", reg_data);
 
@@ -163,7 +165,7 @@
 		ret = PTR_ERR(max77693->regmap_muic);
 		dev_err(max77693->dev,
 			"failed to allocate register map: %d\n", ret);
-		goto err_regmap;
+		goto err_regmap_muic;
 	}
 
 	ret = max77693_irq_init(max77693);
@@ -184,9 +186,9 @@
 err_mfd:
 	max77693_irq_exit(max77693);
 err_irq:
+err_regmap_muic:
 	i2c_unregister_device(max77693->muic);
 	i2c_unregister_device(max77693->haptic);
-err_regmap:
 	return ret;
 }
 
diff --git a/drivers/mfd/pcf50633-core.c b/drivers/mfd/pcf50633-core.c
index 64803f1..d115673 100644
--- a/drivers/mfd/pcf50633-core.c
+++ b/drivers/mfd/pcf50633-core.c
@@ -208,6 +208,8 @@
 	if (!pcf)
 		return -ENOMEM;
 
+	i2c_set_clientdata(client, pcf);
+	pcf->dev = &client->dev;
 	pcf->pdata = pdata;
 
 	mutex_init(&pcf->lock);
@@ -219,9 +221,6 @@
 		return ret;
 	}
 
-	i2c_set_clientdata(client, pcf);
-	pcf->dev = &client->dev;
-
 	version = pcf50633_reg_read(pcf, 0);
 	variant = pcf50633_reg_read(pcf, 1);
 	if (version < 0 || variant < 0) {
diff --git a/drivers/mfd/rtl8411.c b/drivers/mfd/rtl8411.c
index 89f046c..3d3b4ad 100644
--- a/drivers/mfd/rtl8411.c
+++ b/drivers/mfd/rtl8411.c
@@ -112,6 +112,21 @@
 			BPP_LDO_POWB, BPP_LDO_SUSPEND);
 }
 
+static int rtl8411_switch_output_voltage(struct rtsx_pcr *pcr, u8 voltage)
+{
+	u8 mask, val;
+
+	mask = (BPP_REG_TUNED18 << BPP_TUNED18_SHIFT_8411) | BPP_PAD_MASK;
+	if (voltage == OUTPUT_3V3)
+		val = (BPP_ASIC_3V3 << BPP_TUNED18_SHIFT_8411) | BPP_PAD_3V3;
+	else if (voltage == OUTPUT_1V8)
+		val = (BPP_ASIC_1V8 << BPP_TUNED18_SHIFT_8411) | BPP_PAD_1V8;
+	else
+		return -EINVAL;
+
+	return rtsx_pci_write_register(pcr, LDO_CTL, mask, val);
+}
+
 static unsigned int rtl8411_cd_deglitch(struct rtsx_pcr *pcr)
 {
 	unsigned int card_exist;
@@ -163,6 +178,18 @@
 	return card_exist;
 }
 
+static int rtl8411_conv_clk_and_div_n(int input, int dir)
+{
+	int output;
+
+	if (dir == CLK_TO_DIV_N)
+		output = input * 4 / 5 - 2;
+	else
+		output = (input + 2) * 5 / 4;
+
+	return output;
+}
+
 static const struct pcr_ops rtl8411_pcr_ops = {
 	.extra_init_hw = rtl8411_extra_init_hw,
 	.optimize_phy = NULL,
@@ -172,7 +199,9 @@
 	.disable_auto_blink = rtl8411_disable_auto_blink,
 	.card_power_on = rtl8411_card_power_on,
 	.card_power_off = rtl8411_card_power_off,
+	.switch_output_voltage = rtl8411_switch_output_voltage,
 	.cd_deglitch = rtl8411_cd_deglitch,
+	.conv_clk_and_div_n = rtl8411_conv_clk_and_div_n,
 };
 
 /* SD Pull Control Enable:
diff --git a/drivers/mfd/rts5209.c b/drivers/mfd/rts5209.c
index 283a4f1..98fe0f3 100644
--- a/drivers/mfd/rts5209.c
+++ b/drivers/mfd/rts5209.c
@@ -144,6 +144,25 @@
 	return rtsx_pci_send_cmd(pcr, 100);
 }
 
+static int rts5209_switch_output_voltage(struct rtsx_pcr *pcr, u8 voltage)
+{
+	int err;
+
+	if (voltage == OUTPUT_3V3) {
+		err = rtsx_pci_write_phy_register(pcr, 0x08, 0x4FC0 | 0x24);
+		if (err < 0)
+			return err;
+	} else if (voltage == OUTPUT_1V8) {
+		err = rtsx_pci_write_phy_register(pcr, 0x08, 0x4C40 | 0x24);
+		if (err < 0)
+			return err;
+	} else {
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static const struct pcr_ops rts5209_pcr_ops = {
 	.extra_init_hw = rts5209_extra_init_hw,
 	.optimize_phy = rts5209_optimize_phy,
@@ -153,7 +172,9 @@
 	.disable_auto_blink = rts5209_disable_auto_blink,
 	.card_power_on = rts5209_card_power_on,
 	.card_power_off = rts5209_card_power_off,
+	.switch_output_voltage = rts5209_switch_output_voltage,
 	.cd_deglitch = NULL,
+	.conv_clk_and_div_n = NULL,
 };
 
 /* SD Pull Control Enable:
diff --git a/drivers/mfd/rts5229.c b/drivers/mfd/rts5229.c
index b9dbab2..29d889c 100644
--- a/drivers/mfd/rts5229.c
+++ b/drivers/mfd/rts5229.c
@@ -114,6 +114,25 @@
 	return rtsx_pci_send_cmd(pcr, 100);
 }
 
+static int rts5229_switch_output_voltage(struct rtsx_pcr *pcr, u8 voltage)
+{
+	int err;
+
+	if (voltage == OUTPUT_3V3) {
+		err = rtsx_pci_write_phy_register(pcr, 0x08, 0x4FC0 | 0x24);
+		if (err < 0)
+			return err;
+	} else if (voltage == OUTPUT_1V8) {
+		err = rtsx_pci_write_phy_register(pcr, 0x08, 0x4C40 | 0x24);
+		if (err < 0)
+			return err;
+	} else {
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static const struct pcr_ops rts5229_pcr_ops = {
 	.extra_init_hw = rts5229_extra_init_hw,
 	.optimize_phy = rts5229_optimize_phy,
@@ -123,7 +142,9 @@
 	.disable_auto_blink = rts5229_disable_auto_blink,
 	.card_power_on = rts5229_card_power_on,
 	.card_power_off = rts5229_card_power_off,
+	.switch_output_voltage = rts5229_switch_output_voltage,
 	.cd_deglitch = NULL,
+	.conv_clk_and_div_n = NULL,
 };
 
 /* SD Pull Control Enable:
diff --git a/drivers/mfd/rtsx_pcr.c b/drivers/mfd/rtsx_pcr.c
index 7a7b0bd..9fc5700 100644
--- a/drivers/mfd/rtsx_pcr.c
+++ b/drivers/mfd/rtsx_pcr.c
@@ -630,7 +630,10 @@
 	if (clk == pcr->cur_clock)
 		return 0;
 
-	N = (u8)(clk - 2);
+	if (pcr->ops->conv_clk_and_div_n)
+		N = (u8)pcr->ops->conv_clk_and_div_n(clk, CLK_TO_DIV_N);
+	else
+		N = (u8)(clk - 2);
 	if ((clk <= 2) || (N > max_N))
 		return -EINVAL;
 
@@ -641,7 +644,14 @@
 	/* Make sure that the SSC clock div_n is equal or greater than min_N */
 	div = CLK_DIV_1;
 	while ((N < min_N) && (div < max_div)) {
-		N = (N + 2) * 2 - 2;
+		if (pcr->ops->conv_clk_and_div_n) {
+			int dbl_clk = pcr->ops->conv_clk_and_div_n(N,
+					DIV_N_TO_CLK) * 2;
+			N = (u8)pcr->ops->conv_clk_and_div_n(dbl_clk,
+					CLK_TO_DIV_N);
+		} else {
+			N = (N + 2) * 2 - 2;
+		}
 		div++;
 	}
 	dev_dbg(&(pcr->pci->dev), "N = %d, div = %d\n", N, div);
@@ -703,6 +713,15 @@
 }
 EXPORT_SYMBOL_GPL(rtsx_pci_card_power_off);
 
+int rtsx_pci_switch_output_voltage(struct rtsx_pcr *pcr, u8 voltage)
+{
+	if (pcr->ops->switch_output_voltage)
+		return pcr->ops->switch_output_voltage(pcr, voltage);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_switch_output_voltage);
+
 unsigned int rtsx_pci_card_exist(struct rtsx_pcr *pcr)
 {
 	unsigned int val;
@@ -767,10 +786,10 @@
 
 	spin_unlock_irqrestore(&pcr->lock, flags);
 
-	if (card_detect & SD_EXIST)
+	if ((card_detect & SD_EXIST) && pcr->slots[RTSX_SD_CARD].card_event)
 		pcr->slots[RTSX_SD_CARD].card_event(
 				pcr->slots[RTSX_SD_CARD].p_dev);
-	if (card_detect & MS_EXIST)
+	if ((card_detect & MS_EXIST) && pcr->slots[RTSX_MS_CARD].card_event)
 		pcr->slots[RTSX_MS_CARD].card_event(
 				pcr->slots[RTSX_MS_CARD].p_dev);
 }
diff --git a/drivers/mfd/tc3589x.c b/drivers/mfd/tc3589x.c
index a06d66b..ecc092c 100644
--- a/drivers/mfd/tc3589x.c
+++ b/drivers/mfd/tc3589x.c
@@ -219,25 +219,18 @@
 }
 
 static struct irq_domain_ops tc3589x_irq_ops = {
-        .map    = tc3589x_irq_map,
+	.map    = tc3589x_irq_map,
 	.unmap  = tc3589x_irq_unmap,
-        .xlate  = irq_domain_xlate_twocell,
+	.xlate  = irq_domain_xlate_twocell,
 };
 
 static int tc3589x_irq_init(struct tc3589x *tc3589x, struct device_node *np)
 {
 	int base = tc3589x->irq_base;
 
-	if (base) {
-		tc3589x->domain = irq_domain_add_legacy(
-			NULL, TC3589x_NR_INTERNAL_IRQS, base,
-			0, &tc3589x_irq_ops, tc3589x);
-	}
-	else {
-		tc3589x->domain = irq_domain_add_linear(
-			np, TC3589x_NR_INTERNAL_IRQS,
-			&tc3589x_irq_ops, tc3589x);
-	}
+	tc3589x->domain = irq_domain_add_simple(
+		np, TC3589x_NR_INTERNAL_IRQS, base,
+		&tc3589x_irq_ops, tc3589x);
 
 	if (!tc3589x->domain) {
 		dev_err(tc3589x->dev, "Failed to create irqdomain\n");
diff --git a/drivers/mfd/twl4030-power.c b/drivers/mfd/twl4030-power.c
index 4dae241..dd362c1 100644
--- a/drivers/mfd/twl4030-power.c
+++ b/drivers/mfd/twl4030-power.c
@@ -159,7 +159,7 @@
 static int twl4030_write_script(u8 address, struct twl4030_ins *script,
 				       int len)
 {
-	int err;
+	int err = -EINVAL;
 
 	for (; len; len--, address++, script++) {
 		if (len == 1) {
diff --git a/drivers/mfd/vexpress-config.c b/drivers/mfd/vexpress-config.c
index fae15d8..3c1723aa 100644
--- a/drivers/mfd/vexpress-config.c
+++ b/drivers/mfd/vexpress-config.c
@@ -67,6 +67,7 @@
 
 	return bridge;
 }
+EXPORT_SYMBOL(vexpress_config_bridge_register);
 
 void vexpress_config_bridge_unregister(struct vexpress_config_bridge *bridge)
 {
@@ -83,6 +84,7 @@
 	while (!list_empty(&__bridge.transactions))
 		cpu_relax();
 }
+EXPORT_SYMBOL(vexpress_config_bridge_unregister);
 
 
 struct vexpress_config_func {
@@ -142,6 +144,7 @@
 
 	return func;
 }
+EXPORT_SYMBOL(__vexpress_config_func_get);
 
 void vexpress_config_func_put(struct vexpress_config_func *func)
 {
@@ -149,7 +152,7 @@
 	of_node_put(func->bridge->node);
 	kfree(func);
 }
-
+EXPORT_SYMBOL(vexpress_config_func_put);
 
 struct vexpress_config_trans {
 	struct vexpress_config_func *func;
@@ -229,6 +232,7 @@
 
 	complete(&trans->completion);
 }
+EXPORT_SYMBOL(vexpress_config_complete);
 
 int vexpress_config_wait(struct vexpress_config_trans *trans)
 {
@@ -236,7 +240,7 @@
 
 	return trans->status;
 }
-
+EXPORT_SYMBOL(vexpress_config_wait);
 
 int vexpress_config_read(struct vexpress_config_func *func, int offset,
 		u32 *data)
diff --git a/drivers/mfd/vexpress-sysreg.c b/drivers/mfd/vexpress-sysreg.c
index e5d8f63..77048b1 100644
--- a/drivers/mfd/vexpress-sysreg.c
+++ b/drivers/mfd/vexpress-sysreg.c
@@ -313,19 +313,11 @@
 }
 
 
-void __init vexpress_sysreg_early_init(void __iomem *base)
+void __init vexpress_sysreg_setup(struct device_node *node)
 {
-	struct device_node *node = of_find_compatible_node(NULL, NULL,
-			"arm,vexpress-sysreg");
-
-	if (node)
-		base = of_iomap(node, 0);
-
-	if (WARN_ON(!base))
+	if (WARN_ON(!vexpress_sysreg_base))
 		return;
 
-	vexpress_sysreg_base = base;
-
 	if (readl(vexpress_sysreg_base + SYS_MISC) & SYS_MISC_MASTERSITE)
 		vexpress_master_site = VEXPRESS_SITE_DB2;
 	else
@@ -336,9 +328,23 @@
 	WARN_ON(!vexpress_sysreg_config_bridge);
 }
 
+void __init vexpress_sysreg_early_init(void __iomem *base)
+{
+	vexpress_sysreg_base = base;
+	vexpress_sysreg_setup(NULL);
+}
+
 void __init vexpress_sysreg_of_early_init(void)
 {
-	vexpress_sysreg_early_init(NULL);
+	struct device_node *node = of_find_compatible_node(NULL, NULL,
+			"arm,vexpress-sysreg");
+
+	if (node) {
+		vexpress_sysreg_base = of_iomap(node, 0);
+		vexpress_sysreg_setup(node);
+	} else {
+		pr_info("vexpress-sysreg: No Device Tree node found.");
+	}
 }
 
 
@@ -426,9 +432,11 @@
 		return -EBUSY;
 	}
 
-	if (!vexpress_sysreg_base)
+	if (!vexpress_sysreg_base) {
 		vexpress_sysreg_base = devm_ioremap(&pdev->dev, res->start,
 				resource_size(res));
+		vexpress_sysreg_setup(pdev->dev.of_node);
+	}
 
 	if (!vexpress_sysreg_base) {
 		dev_err(&pdev->dev, "Failed to obtain base address!\n");
diff --git a/drivers/mfd/wm5102-tables.c b/drivers/mfd/wm5102-tables.c
index 088872a..1133a64 100644
--- a/drivers/mfd/wm5102-tables.c
+++ b/drivers/mfd/wm5102-tables.c
@@ -1882,7 +1882,7 @@
 	}
 }
 
-#define WM5102_MAX_REGISTER 0x1a8fff
+#define WM5102_MAX_REGISTER 0x1a9800
 
 const struct regmap_config wm5102_spi_regmap = {
 	.reg_bits = 32,
diff --git a/drivers/mmc/host/mvsdio.c b/drivers/mmc/host/mvsdio.c
index de4c20b..f8dd361 100644
--- a/drivers/mmc/host/mvsdio.c
+++ b/drivers/mmc/host/mvsdio.c
@@ -50,8 +50,6 @@
 	struct timer_list timer;
 	struct mmc_host *mmc;
 	struct device *dev;
-	struct resource *res;
-	int irq;
 	struct clk *clk;
 	int gpio_card_detect;
 	int gpio_write_protect;
@@ -718,10 +716,6 @@
 	if (!r || irq < 0 || !mvsd_data)
 		return -ENXIO;
 
-	r = request_mem_region(r->start, SZ_1K, DRIVER_NAME);
-	if (!r)
-		return -EBUSY;
-
 	mmc = mmc_alloc_host(sizeof(struct mvsd_host), &pdev->dev);
 	if (!mmc) {
 		ret = -ENOMEM;
@@ -731,8 +725,8 @@
 	host = mmc_priv(mmc);
 	host->mmc = mmc;
 	host->dev = &pdev->dev;
-	host->res = r;
 	host->base_clock = mvsd_data->clock / 2;
+	host->clk = ERR_PTR(-EINVAL);
 
 	mmc->ops = &mvsd_ops;
 
@@ -752,7 +746,7 @@
 
 	spin_lock_init(&host->lock);
 
-	host->base = ioremap(r->start, SZ_4K);
+	host->base = devm_request_and_ioremap(&pdev->dev, r);
 	if (!host->base) {
 		ret = -ENOMEM;
 		goto out;
@@ -765,44 +759,45 @@
 
 	mvsd_power_down(host);
 
-	ret = request_irq(irq, mvsd_irq, 0, DRIVER_NAME, host);
+	ret = devm_request_irq(&pdev->dev, irq, mvsd_irq, 0, DRIVER_NAME, host);
 	if (ret) {
 		pr_err("%s: cannot assign irq %d\n", DRIVER_NAME, irq);
 		goto out;
-	} else
-		host->irq = irq;
+	}
 
 	/* Not all platforms can gate the clock, so it is not
 	   an error if the clock does not exists. */
-	host->clk = clk_get(&pdev->dev, NULL);
-	if (!IS_ERR(host->clk)) {
+	host->clk = devm_clk_get(&pdev->dev, NULL);
+	if (!IS_ERR(host->clk))
 		clk_prepare_enable(host->clk);
-	}
 
 	if (mvsd_data->gpio_card_detect) {
-		ret = gpio_request(mvsd_data->gpio_card_detect,
-				   DRIVER_NAME " cd");
+		ret = devm_gpio_request_one(&pdev->dev,
+					    mvsd_data->gpio_card_detect,
+					    GPIOF_IN, DRIVER_NAME " cd");
 		if (ret == 0) {
-			gpio_direction_input(mvsd_data->gpio_card_detect);
 			irq = gpio_to_irq(mvsd_data->gpio_card_detect);
-			ret = request_irq(irq, mvsd_card_detect_irq,
-					  IRQ_TYPE_EDGE_RISING | IRQ_TYPE_EDGE_FALLING,
-					  DRIVER_NAME " cd", host);
+			ret = devm_request_irq(&pdev->dev, irq,
+					       mvsd_card_detect_irq,
+					       IRQ_TYPE_EDGE_RISING |
+					       IRQ_TYPE_EDGE_FALLING,
+					       DRIVER_NAME " cd", host);
 			if (ret == 0)
 				host->gpio_card_detect =
 					mvsd_data->gpio_card_detect;
 			else
-				gpio_free(mvsd_data->gpio_card_detect);
+				devm_gpio_free(&pdev->dev,
+					       mvsd_data->gpio_card_detect);
 		}
 	}
 	if (!host->gpio_card_detect)
 		mmc->caps |= MMC_CAP_NEEDS_POLL;
 
 	if (mvsd_data->gpio_write_protect) {
-		ret = gpio_request(mvsd_data->gpio_write_protect,
-				   DRIVER_NAME " wp");
+		ret = devm_gpio_request_one(&pdev->dev,
+					    mvsd_data->gpio_write_protect,
+					    GPIOF_IN, DRIVER_NAME " wp");
 		if (ret == 0) {
-			gpio_direction_input(mvsd_data->gpio_write_protect);
 			host->gpio_write_protect =
 				mvsd_data->gpio_write_protect;
 		}
@@ -824,26 +819,11 @@
 	return 0;
 
 out:
-	if (host) {
-		if (host->irq)
-			free_irq(host->irq, host);
-		if (host->gpio_card_detect) {
-			free_irq(gpio_to_irq(host->gpio_card_detect), host);
-			gpio_free(host->gpio_card_detect);
-		}
-		if (host->gpio_write_protect)
-			gpio_free(host->gpio_write_protect);
-		if (host->base)
-			iounmap(host->base);
-	}
-	if (r)
-		release_resource(r);
-	if (mmc)
-		if (!IS_ERR_OR_NULL(host->clk)) {
+	if (mmc) {
+		if (!IS_ERR(host->clk))
 			clk_disable_unprepare(host->clk);
-			clk_put(host->clk);
-		}
 		mmc_free_host(mmc);
+	}
 
 	return ret;
 }
@@ -852,28 +832,16 @@
 {
 	struct mmc_host *mmc = platform_get_drvdata(pdev);
 
-	if (mmc) {
-		struct mvsd_host *host = mmc_priv(mmc);
+	struct mvsd_host *host = mmc_priv(mmc);
 
-		if (host->gpio_card_detect) {
-			free_irq(gpio_to_irq(host->gpio_card_detect), host);
-			gpio_free(host->gpio_card_detect);
-		}
-		mmc_remove_host(mmc);
-		free_irq(host->irq, host);
-		if (host->gpio_write_protect)
-			gpio_free(host->gpio_write_protect);
-		del_timer_sync(&host->timer);
-		mvsd_power_down(host);
-		iounmap(host->base);
-		release_resource(host->res);
+	mmc_remove_host(mmc);
+	del_timer_sync(&host->timer);
+	mvsd_power_down(host);
 
-		if (!IS_ERR(host->clk)) {
-			clk_disable_unprepare(host->clk);
-			clk_put(host->clk);
-		}
-		mmc_free_host(mmc);
-	}
+	if (!IS_ERR(host->clk))
+		clk_disable_unprepare(host->clk);
+	mmc_free_host(mmc);
+
 	platform_set_drvdata(pdev, NULL);
 	return 0;
 }
diff --git a/drivers/mmc/host/rtsx_pci_sdmmc.c b/drivers/mmc/host/rtsx_pci_sdmmc.c
index 571915d..f74b5ad 100644
--- a/drivers/mmc/host/rtsx_pci_sdmmc.c
+++ b/drivers/mmc/host/rtsx_pci_sdmmc.c
@@ -1060,26 +1060,6 @@
 	return 0;
 }
 
-static int sd_change_bank_voltage(struct realtek_pci_sdmmc *host, u8 voltage)
-{
-	struct rtsx_pcr *pcr = host->pcr;
-	int err;
-
-	if (voltage == SD_IO_3V3) {
-		err = rtsx_pci_write_phy_register(pcr, 0x08, 0x4FC0 | 0x24);
-		if (err < 0)
-			return err;
-	} else if (voltage == SD_IO_1V8) {
-		err = rtsx_pci_write_phy_register(pcr, 0x08, 0x4C40 | 0x24);
-		if (err < 0)
-			return err;
-	} else {
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
 static int sdmmc_switch_voltage(struct mmc_host *mmc, struct mmc_ios *ios)
 {
 	struct realtek_pci_sdmmc *host = mmc_priv(mmc);
@@ -1098,11 +1078,11 @@
 	rtsx_pci_start_run(pcr);
 
 	if (ios->signal_voltage == MMC_SIGNAL_VOLTAGE_330)
-		voltage = SD_IO_3V3;
+		voltage = OUTPUT_3V3;
 	else
-		voltage = SD_IO_1V8;
+		voltage = OUTPUT_1V8;
 
-	if (voltage == SD_IO_1V8) {
+	if (voltage == OUTPUT_1V8) {
 		err = rtsx_pci_write_register(pcr,
 				SD30_DRIVE_SEL, 0x07, DRIVER_TYPE_B);
 		if (err < 0)
@@ -1113,11 +1093,11 @@
 			goto out;
 	}
 
-	err = sd_change_bank_voltage(host, voltage);
+	err = rtsx_pci_switch_output_voltage(pcr, voltage);
 	if (err < 0)
 		goto out;
 
-	if (voltage == SD_IO_1V8) {
+	if (voltage == OUTPUT_1V8) {
 		err = sd_wait_voltage_stable_2(host);
 		if (err < 0)
 			goto out;
diff --git a/drivers/mtd/devices/Kconfig b/drivers/mtd/devices/Kconfig
index 27f80cd..46dcb54 100644
--- a/drivers/mtd/devices/Kconfig
+++ b/drivers/mtd/devices/Kconfig
@@ -272,6 +272,7 @@
 	tristate "M-Systems Disk-On-Chip G3"
 	select BCH
 	select BCH_CONST_PARAMS
+	select BITREVERSE
 	---help---
 	  This provides an MTD device driver for the M-Systems DiskOnChip
 	  G3 devices.
diff --git a/drivers/mtd/maps/physmap_of.c b/drivers/mtd/maps/physmap_of.c
index 67cc73c..7901d72 100644
--- a/drivers/mtd/maps/physmap_of.c
+++ b/drivers/mtd/maps/physmap_of.c
@@ -170,7 +170,7 @@
 	resource_size_t res_size;
 	struct mtd_part_parser_data ppdata;
 	bool map_indirect;
-	const char *mtd_name;
+	const char *mtd_name = NULL;
 
 	match = of_match_device(of_flash_match, &dev->dev);
 	if (!match)
diff --git a/drivers/mtd/nand/bcm47xxnflash/ops_bcm4706.c b/drivers/mtd/nand/bcm47xxnflash/ops_bcm4706.c
index 86c9a79..595de40 100644
--- a/drivers/mtd/nand/bcm47xxnflash/ops_bcm4706.c
+++ b/drivers/mtd/nand/bcm47xxnflash/ops_bcm4706.c
@@ -17,8 +17,8 @@
 #include "bcm47xxnflash.h"
 
 /* Broadcom uses 1'000'000 but it seems to be too many. Tests on WNDR4500 has
- * shown 164 retries as maxiumum. */
-#define NFLASH_READY_RETRIES		1000
+ * shown ~1000 retries as maxiumum. */
+#define NFLASH_READY_RETRIES		10000
 
 #define NFLASH_SECTOR_SIZE		512
 
diff --git a/drivers/mtd/nand/davinci_nand.c b/drivers/mtd/nand/davinci_nand.c
index 3502606..feae55c 100644
--- a/drivers/mtd/nand/davinci_nand.c
+++ b/drivers/mtd/nand/davinci_nand.c
@@ -523,7 +523,7 @@
 static const struct of_device_id davinci_nand_of_match[] = {
 	{.compatible = "ti,davinci-nand", },
 	{},
-}
+};
 MODULE_DEVICE_TABLE(of, davinci_nand_of_match);
 
 static struct davinci_nand_pdata
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index 8323ac9..3766682 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -2857,8 +2857,11 @@
 	int i;
 	int val;
 
-	/* ONFI need to be probed in 8 bits mode */
-	WARN_ON(chip->options & NAND_BUSWIDTH_16);
+	/* ONFI need to be probed in 8 bits mode, and 16 bits should be selected with NAND_BUSWIDTH_AUTO */
+	if (chip->options & NAND_BUSWIDTH_16) {
+		pr_err("Trying ONFI probe in 16 bits mode, aborting !\n");
+		return 0;
+	}
 	/* Try ONFI for unknown chip or LP */
 	chip->cmdfunc(mtd, NAND_CMD_READID, 0x20, -1);
 	if (chip->read_byte(mtd) != 'O' || chip->read_byte(mtd) != 'N' ||
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 1877ed7..1c9e09f 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -1053,6 +1053,7 @@
 		pr_info("%s: Setting primary slave to None.\n",
 			bond->dev->name);
 		bond->primary_slave = NULL;
+		memset(bond->params.primary, 0, sizeof(bond->params.primary));
 		bond_select_active_slave(bond);
 		goto out;
 	}
diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c
index 5233b8f..2282b1a 100644
--- a/drivers/net/can/c_can/c_can.c
+++ b/drivers/net/can/c_can/c_can.c
@@ -488,8 +488,12 @@
 
 	priv->write_reg(priv, C_CAN_IFACE(MASK1_REG, iface),
 			IFX_WRITE_LOW_16BIT(mask));
+
+	/* According to C_CAN documentation, the reserved bit
+	 * in IFx_MASK2 register is fixed 1
+	 */
 	priv->write_reg(priv, C_CAN_IFACE(MASK2_REG, iface),
-			IFX_WRITE_HIGH_16BIT(mask));
+			IFX_WRITE_HIGH_16BIT(mask) | BIT(13));
 
 	priv->write_reg(priv, C_CAN_IFACE(ARB1_REG, iface),
 			IFX_WRITE_LOW_16BIT(id));
@@ -960,7 +964,7 @@
 		break;
 	case LEC_ACK_ERROR:
 		netdev_dbg(dev, "ack error\n");
-		cf->data[2] |= (CAN_ERR_PROT_LOC_ACK |
+		cf->data[3] |= (CAN_ERR_PROT_LOC_ACK |
 				CAN_ERR_PROT_LOC_ACK_DEL);
 		break;
 	case LEC_BIT1_ERROR:
@@ -973,7 +977,7 @@
 		break;
 	case LEC_CRC_ERROR:
 		netdev_dbg(dev, "CRC error\n");
-		cf->data[2] |= (CAN_ERR_PROT_LOC_CRC_SEQ |
+		cf->data[3] |= (CAN_ERR_PROT_LOC_CRC_SEQ |
 				CAN_ERR_PROT_LOC_CRC_DEL);
 		break;
 	default:
diff --git a/drivers/net/can/pch_can.c b/drivers/net/can/pch_can.c
index 7d17485..5c314a9 100644
--- a/drivers/net/can/pch_can.c
+++ b/drivers/net/can/pch_can.c
@@ -560,7 +560,7 @@
 		stats->rx_errors++;
 		break;
 	case PCH_CRC_ERR:
-		cf->data[2] |= CAN_ERR_PROT_LOC_CRC_SEQ |
+		cf->data[3] |= CAN_ERR_PROT_LOC_CRC_SEQ |
 			       CAN_ERR_PROT_LOC_CRC_DEL;
 		priv->can.can_stats.bus_error++;
 		stats->rx_errors++;
diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c
index f898c63..300581b 100644
--- a/drivers/net/can/ti_hecc.c
+++ b/drivers/net/can/ti_hecc.c
@@ -746,12 +746,12 @@
 		}
 		if (err_status & HECC_CANES_CRCE) {
 			hecc_set_bit(priv, HECC_CANES, HECC_CANES_CRCE);
-			cf->data[2] |= CAN_ERR_PROT_LOC_CRC_SEQ |
+			cf->data[3] |= CAN_ERR_PROT_LOC_CRC_SEQ |
 					CAN_ERR_PROT_LOC_CRC_DEL;
 		}
 		if (err_status & HECC_CANES_ACKE) {
 			hecc_set_bit(priv, HECC_CANES, HECC_CANES_ACKE);
-			cf->data[2] |= CAN_ERR_PROT_LOC_ACK |
+			cf->data[3] |= CAN_ERR_PROT_LOC_ACK |
 					CAN_ERR_PROT_LOC_ACK_DEL;
 		}
 	}
diff --git a/drivers/net/ethernet/3com/3c574_cs.c b/drivers/net/ethernet/3com/3c574_cs.c
index 66df936..ffd8de2 100644
--- a/drivers/net/ethernet/3com/3c574_cs.c
+++ b/drivers/net/ethernet/3com/3c574_cs.c
@@ -432,7 +432,7 @@
 	netdev_info(dev, "%s at io %#3lx, irq %d, hw_addr %pM\n",
 		    cardname, dev->base_addr, dev->irq, dev->dev_addr);
 	netdev_info(dev, " %dK FIFO split %s Rx:Tx, %sMII interface.\n",
-		    8 << config & Ram_size,
+		    8 << (config & Ram_size),
 		    ram_split[(config & Ram_split) >> Ram_split_shift],
 		    config & Autoselect ? "autoselect " : "");
 
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index 56d3f69..0035c01 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -21,7 +21,7 @@
 
 #include "atl1c.h"
 
-#define ATL1C_DRV_VERSION "1.0.1.0-NAPI"
+#define ATL1C_DRV_VERSION "1.0.1.1-NAPI"
 char atl1c_driver_name[] = "atl1c";
 char atl1c_driver_version[] = ATL1C_DRV_VERSION;
 
@@ -1652,6 +1652,7 @@
 	u16 num_alloc = 0;
 	u16 rfd_next_to_use, next_next;
 	struct atl1c_rx_free_desc *rfd_desc;
+	dma_addr_t mapping;
 
 	next_next = rfd_next_to_use = rfd_ring->next_to_use;
 	if (++next_next == rfd_ring->count)
@@ -1678,9 +1679,18 @@
 		ATL1C_SET_BUFFER_STATE(buffer_info, ATL1C_BUFFER_BUSY);
 		buffer_info->skb = skb;
 		buffer_info->length = adapter->rx_buffer_len;
-		buffer_info->dma = pci_map_single(pdev, vir_addr,
+		mapping = pci_map_single(pdev, vir_addr,
 						buffer_info->length,
 						PCI_DMA_FROMDEVICE);
+		if (unlikely(pci_dma_mapping_error(pdev, mapping))) {
+			dev_kfree_skb(skb);
+			buffer_info->skb = NULL;
+			buffer_info->length = 0;
+			ATL1C_SET_BUFFER_STATE(buffer_info, ATL1C_BUFFER_FREE);
+			netif_warn(adapter, rx_err, adapter->netdev, "RX pci_map_single failed");
+			break;
+		}
+		buffer_info->dma = mapping;
 		ATL1C_SET_PCIMAP_TYPE(buffer_info, ATL1C_PCIMAP_SINGLE,
 			ATL1C_PCIMAP_FROMDEVICE);
 		rfd_desc->buffer_addr = cpu_to_le64(buffer_info->dma);
@@ -2015,7 +2025,29 @@
 	return 0;
 }
 
-static void atl1c_tx_map(struct atl1c_adapter *adapter,
+static void atl1c_tx_rollback(struct atl1c_adapter *adpt,
+			      struct atl1c_tpd_desc *first_tpd,
+			      enum atl1c_trans_queue type)
+{
+	struct atl1c_tpd_ring *tpd_ring = &adpt->tpd_ring[type];
+	struct atl1c_buffer *buffer_info;
+	struct atl1c_tpd_desc *tpd;
+	u16 first_index, index;
+
+	first_index = first_tpd - (struct atl1c_tpd_desc *)tpd_ring->desc;
+	index = first_index;
+	while (index != tpd_ring->next_to_use) {
+		tpd = ATL1C_TPD_DESC(tpd_ring, index);
+		buffer_info = &tpd_ring->buffer_info[index];
+		atl1c_clean_buffer(adpt->pdev, buffer_info, 0);
+		memset(tpd, 0, sizeof(struct atl1c_tpd_desc));
+		if (++index == tpd_ring->count)
+			index = 0;
+	}
+	tpd_ring->next_to_use = first_index;
+}
+
+static int atl1c_tx_map(struct atl1c_adapter *adapter,
 		      struct sk_buff *skb, struct atl1c_tpd_desc *tpd,
 			enum atl1c_trans_queue type)
 {
@@ -2040,7 +2072,10 @@
 		buffer_info->length = map_len;
 		buffer_info->dma = pci_map_single(adapter->pdev,
 					skb->data, hdr_len, PCI_DMA_TODEVICE);
-		ATL1C_SET_BUFFER_STATE(buffer_info, ATL1C_BUFFER_BUSY);
+		if (unlikely(pci_dma_mapping_error(adapter->pdev,
+						   buffer_info->dma)))
+			goto err_dma;
+
 		ATL1C_SET_PCIMAP_TYPE(buffer_info, ATL1C_PCIMAP_SINGLE,
 			ATL1C_PCIMAP_TODEVICE);
 		mapped_len += map_len;
@@ -2062,6 +2097,10 @@
 		buffer_info->dma =
 			pci_map_single(adapter->pdev, skb->data + mapped_len,
 					buffer_info->length, PCI_DMA_TODEVICE);
+		if (unlikely(pci_dma_mapping_error(adapter->pdev,
+						   buffer_info->dma)))
+			goto err_dma;
+
 		ATL1C_SET_BUFFER_STATE(buffer_info, ATL1C_BUFFER_BUSY);
 		ATL1C_SET_PCIMAP_TYPE(buffer_info, ATL1C_PCIMAP_SINGLE,
 			ATL1C_PCIMAP_TODEVICE);
@@ -2083,6 +2122,9 @@
 						    frag, 0,
 						    buffer_info->length,
 						    DMA_TO_DEVICE);
+		if (dma_mapping_error(&adapter->pdev->dev, buffer_info->dma))
+			goto err_dma;
+
 		ATL1C_SET_BUFFER_STATE(buffer_info, ATL1C_BUFFER_BUSY);
 		ATL1C_SET_PCIMAP_TYPE(buffer_info, ATL1C_PCIMAP_PAGE,
 			ATL1C_PCIMAP_TODEVICE);
@@ -2095,6 +2137,13 @@
 	/* The last buffer info contain the skb address,
 	   so it will be free after unmap */
 	buffer_info->skb = skb;
+
+	return 0;
+
+err_dma:
+	buffer_info->dma = 0;
+	buffer_info->length = 0;
+	return -1;
 }
 
 static void atl1c_tx_queue(struct atl1c_adapter *adapter, struct sk_buff *skb,
@@ -2157,10 +2206,18 @@
 	if (skb_network_offset(skb) != ETH_HLEN)
 		tpd->word1 |= 1 << TPD_ETH_TYPE_SHIFT; /* Ethernet frame */
 
-	atl1c_tx_map(adapter, skb, tpd, type);
-	atl1c_tx_queue(adapter, skb, tpd, type);
+	if (atl1c_tx_map(adapter, skb, tpd, type) < 0) {
+		netif_info(adapter, tx_done, adapter->netdev,
+			   "tx-skb droppted due to dma error\n");
+		/* roll back tpd/buffer */
+		atl1c_tx_rollback(adapter, tpd, type);
+		spin_unlock_irqrestore(&adapter->tx_lock, flags);
+		dev_kfree_skb(skb);
+	} else {
+		atl1c_tx_queue(adapter, skb, tpd, type);
+		spin_unlock_irqrestore(&adapter->tx_lock, flags);
+	}
 
-	spin_unlock_irqrestore(&adapter->tx_lock, flags);
 	return NETDEV_TX_OK;
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index f771ddf..a5edac8 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -504,13 +504,11 @@
 		skb_shinfo(skb)->gso_size = bnx2x_set_lro_mss(bp,
 					tpa_info->parsing_flags, len_on_bd);
 
-		/* set for GRO */
-		if (fp->mode == TPA_MODE_GRO)
-			skb_shinfo(skb)->gso_type =
-			    (GET_FLAG(tpa_info->parsing_flags,
-				      PARSING_FLAGS_OVER_ETHERNET_PROTOCOL) ==
-						PRS_FLAG_OVERETH_IPV6) ?
-				SKB_GSO_TCPV6 : SKB_GSO_TCPV4;
+		skb_shinfo(skb)->gso_type =
+			(GET_FLAG(tpa_info->parsing_flags,
+				  PARSING_FLAGS_OVER_ETHERNET_PROTOCOL) ==
+			 PRS_FLAG_OVERETH_IPV6) ?
+			SKB_GSO_TCPV6 : SKB_GSO_TCPV4;
 	}
 
 
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 78ea90c..bdb0869 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -1283,14 +1283,26 @@
 	return tg3_writephy(tp, MII_TG3_AUX_CTRL, set | reg);
 }
 
-#define TG3_PHY_AUXCTL_SMDSP_ENABLE(tp) \
-	tg3_phy_auxctl_write((tp), MII_TG3_AUXCTL_SHDWSEL_AUXCTL, \
-			     MII_TG3_AUXCTL_ACTL_SMDSP_ENA | \
-			     MII_TG3_AUXCTL_ACTL_TX_6DB)
+static int tg3_phy_toggle_auxctl_smdsp(struct tg3 *tp, bool enable)
+{
+	u32 val;
+	int err;
 
-#define TG3_PHY_AUXCTL_SMDSP_DISABLE(tp) \
-	tg3_phy_auxctl_write((tp), MII_TG3_AUXCTL_SHDWSEL_AUXCTL, \
-			     MII_TG3_AUXCTL_ACTL_TX_6DB);
+	err = tg3_phy_auxctl_read(tp, MII_TG3_AUXCTL_SHDWSEL_AUXCTL, &val);
+
+	if (err)
+		return err;
+	if (enable)
+
+		val |= MII_TG3_AUXCTL_ACTL_SMDSP_ENA;
+	else
+		val &= ~MII_TG3_AUXCTL_ACTL_SMDSP_ENA;
+
+	err = tg3_phy_auxctl_write((tp), MII_TG3_AUXCTL_SHDWSEL_AUXCTL,
+				   val | MII_TG3_AUXCTL_ACTL_TX_6DB);
+
+	return err;
+}
 
 static int tg3_bmcr_reset(struct tg3 *tp)
 {
@@ -2223,7 +2235,7 @@
 
 	otp = tp->phy_otp;
 
-	if (TG3_PHY_AUXCTL_SMDSP_ENABLE(tp))
+	if (tg3_phy_toggle_auxctl_smdsp(tp, true))
 		return;
 
 	phy = ((otp & TG3_OTP_AGCTGT_MASK) >> TG3_OTP_AGCTGT_SHIFT);
@@ -2248,7 +2260,7 @@
 	      ((otp & TG3_OTP_RCOFF_MASK) >> TG3_OTP_RCOFF_SHIFT);
 	tg3_phydsp_write(tp, MII_TG3_DSP_EXP97, phy);
 
-	TG3_PHY_AUXCTL_SMDSP_DISABLE(tp);
+	tg3_phy_toggle_auxctl_smdsp(tp, false);
 }
 
 static void tg3_phy_eee_adjust(struct tg3 *tp, u32 current_link_up)
@@ -2284,9 +2296,9 @@
 
 	if (!tp->setlpicnt) {
 		if (current_link_up == 1 &&
-		   !TG3_PHY_AUXCTL_SMDSP_ENABLE(tp)) {
+		   !tg3_phy_toggle_auxctl_smdsp(tp, true)) {
 			tg3_phydsp_write(tp, MII_TG3_DSP_TAP26, 0x0000);
-			TG3_PHY_AUXCTL_SMDSP_DISABLE(tp);
+			tg3_phy_toggle_auxctl_smdsp(tp, false);
 		}
 
 		val = tr32(TG3_CPMU_EEE_MODE);
@@ -2302,11 +2314,11 @@
 	    (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 ||
 	     GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719 ||
 	     tg3_flag(tp, 57765_CLASS)) &&
-	    !TG3_PHY_AUXCTL_SMDSP_ENABLE(tp)) {
+	    !tg3_phy_toggle_auxctl_smdsp(tp, true)) {
 		val = MII_TG3_DSP_TAP26_ALNOKO |
 		      MII_TG3_DSP_TAP26_RMRXSTO;
 		tg3_phydsp_write(tp, MII_TG3_DSP_TAP26, val);
-		TG3_PHY_AUXCTL_SMDSP_DISABLE(tp);
+		tg3_phy_toggle_auxctl_smdsp(tp, false);
 	}
 
 	val = tr32(TG3_CPMU_EEE_MODE);
@@ -2450,7 +2462,7 @@
 		tg3_writephy(tp, MII_CTRL1000,
 			     CTL1000_AS_MASTER | CTL1000_ENABLE_MASTER);
 
-		err = TG3_PHY_AUXCTL_SMDSP_ENABLE(tp);
+		err = tg3_phy_toggle_auxctl_smdsp(tp, true);
 		if (err)
 			return err;
 
@@ -2471,7 +2483,7 @@
 	tg3_writephy(tp, MII_TG3_DSP_ADDRESS, 0x8200);
 	tg3_writephy(tp, MII_TG3_DSP_CONTROL, 0x0000);
 
-	TG3_PHY_AUXCTL_SMDSP_DISABLE(tp);
+	tg3_phy_toggle_auxctl_smdsp(tp, false);
 
 	tg3_writephy(tp, MII_CTRL1000, phy9_orig);
 
@@ -2572,10 +2584,10 @@
 
 out:
 	if ((tp->phy_flags & TG3_PHYFLG_ADC_BUG) &&
-	    !TG3_PHY_AUXCTL_SMDSP_ENABLE(tp)) {
+	    !tg3_phy_toggle_auxctl_smdsp(tp, true)) {
 		tg3_phydsp_write(tp, 0x201f, 0x2aaa);
 		tg3_phydsp_write(tp, 0x000a, 0x0323);
-		TG3_PHY_AUXCTL_SMDSP_DISABLE(tp);
+		tg3_phy_toggle_auxctl_smdsp(tp, false);
 	}
 
 	if (tp->phy_flags & TG3_PHYFLG_5704_A0_BUG) {
@@ -2584,14 +2596,14 @@
 	}
 
 	if (tp->phy_flags & TG3_PHYFLG_BER_BUG) {
-		if (!TG3_PHY_AUXCTL_SMDSP_ENABLE(tp)) {
+		if (!tg3_phy_toggle_auxctl_smdsp(tp, true)) {
 			tg3_phydsp_write(tp, 0x000a, 0x310b);
 			tg3_phydsp_write(tp, 0x201f, 0x9506);
 			tg3_phydsp_write(tp, 0x401f, 0x14e2);
-			TG3_PHY_AUXCTL_SMDSP_DISABLE(tp);
+			tg3_phy_toggle_auxctl_smdsp(tp, false);
 		}
 	} else if (tp->phy_flags & TG3_PHYFLG_JITTER_BUG) {
-		if (!TG3_PHY_AUXCTL_SMDSP_ENABLE(tp)) {
+		if (!tg3_phy_toggle_auxctl_smdsp(tp, true)) {
 			tg3_writephy(tp, MII_TG3_DSP_ADDRESS, 0x000a);
 			if (tp->phy_flags & TG3_PHYFLG_ADJUST_TRIM) {
 				tg3_writephy(tp, MII_TG3_DSP_RW_PORT, 0x110b);
@@ -2600,7 +2612,7 @@
 			} else
 				tg3_writephy(tp, MII_TG3_DSP_RW_PORT, 0x010b);
 
-			TG3_PHY_AUXCTL_SMDSP_DISABLE(tp);
+			tg3_phy_toggle_auxctl_smdsp(tp, false);
 		}
 	}
 
@@ -4009,7 +4021,7 @@
 	tw32(TG3_CPMU_EEE_MODE,
 	     tr32(TG3_CPMU_EEE_MODE) & ~TG3_CPMU_EEEMD_LPI_ENABLE);
 
-	err = TG3_PHY_AUXCTL_SMDSP_ENABLE(tp);
+	err = tg3_phy_toggle_auxctl_smdsp(tp, true);
 	if (!err) {
 		u32 err2;
 
@@ -4042,7 +4054,7 @@
 						 MII_TG3_DSP_CH34TP2_HIBW01);
 		}
 
-		err2 = TG3_PHY_AUXCTL_SMDSP_DISABLE(tp);
+		err2 = tg3_phy_toggle_auxctl_smdsp(tp, false);
 		if (!err)
 			err = err2;
 	}
@@ -6950,6 +6962,9 @@
 	int i;
 	struct tg3 *tp = netdev_priv(dev);
 
+	if (tg3_irq_sync(tp))
+		return;
+
 	for (i = 0; i < tp->irq_cnt; i++)
 		tg3_interrupt(tp->napi[i].irq_vec, &tp->napi[i]);
 }
@@ -16367,6 +16382,7 @@
 	tp->pm_cap = pm_cap;
 	tp->rx_mode = TG3_DEF_RX_MODE;
 	tp->tx_mode = TG3_DEF_TX_MODE;
+	tp->irq_sync = 1;
 
 	if (tg3_debug > 0)
 		tp->msg_enable = tg3_debug;
diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index a9b0830..b9d4bb9 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -693,6 +693,11 @@
 		 * get notified when new packets arrive.
 		 */
 		macb_writel(bp, IER, MACB_RX_INT_FLAGS);
+
+		/* Packets received while interrupts were disabled */
+		status = macb_readl(bp, RSR);
+		if (unlikely(status))
+			napi_reschedule(napi);
 	}
 
 	/* TODO: Handle errors */
diff --git a/drivers/net/ethernet/calxeda/xgmac.c b/drivers/net/ethernet/calxeda/xgmac.c
index b407043..f7f0290 100644
--- a/drivers/net/ethernet/calxeda/xgmac.c
+++ b/drivers/net/ethernet/calxeda/xgmac.c
@@ -548,6 +548,10 @@
 		return -1;
 	}
 
+	/* All frames should fit into a single buffer */
+	if (!(status & RXDESC_FIRST_SEG) || !(status & RXDESC_LAST_SEG))
+		return -1;
+
 	/* Check if packet has checksum already */
 	if ((status & RXDESC_FRAME_TYPE) && (status & RXDESC_EXT_STATUS) &&
 		!(ext_status & RXDESC_IP_PAYLOAD_MASK))
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index f0718e1..c306df7 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -1994,9 +1994,20 @@
 {
 	const struct port_info *pi = netdev_priv(dev);
 	struct adapter *adap = pi->adapter;
+	struct sge_rspq *q;
+	int i;
+	int r = 0;
 
-	return set_rxq_intr_params(adap, &adap->sge.ethrxq[pi->first_qset].rspq,
-			c->rx_coalesce_usecs, c->rx_max_coalesced_frames);
+	for (i = pi->first_qset; i < pi->first_qset + pi->nqsets; i++) {
+		q = &adap->sge.ethrxq[i].rspq;
+		r = set_rxq_intr_params(adap, q, c->rx_coalesce_usecs,
+			c->rx_max_coalesced_frames);
+		if (r) {
+			dev_err(&dev->dev, "failed to set coalesce %d\n", r);
+			break;
+		}
+	}
+	return r;
 }
 
 static int get_coalesce(struct net_device *dev, struct ethtool_coalesce *c)
diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index 4eba17b..f1b3df1 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -36,13 +36,13 @@
 
 #define DRV_VER			"4.4.161.0u"
 #define DRV_NAME		"be2net"
-#define BE_NAME			"ServerEngines BladeEngine2 10Gbps NIC"
-#define BE3_NAME		"ServerEngines BladeEngine3 10Gbps NIC"
-#define OC_NAME			"Emulex OneConnect 10Gbps NIC"
+#define BE_NAME			"Emulex BladeEngine2"
+#define BE3_NAME		"Emulex BladeEngine3"
+#define OC_NAME			"Emulex OneConnect"
 #define OC_NAME_BE		OC_NAME	"(be3)"
 #define OC_NAME_LANCER		OC_NAME "(Lancer)"
 #define OC_NAME_SH		OC_NAME "(Skyhawk)"
-#define DRV_DESC		"ServerEngines BladeEngine 10Gbps NIC Driver"
+#define DRV_DESC		"Emulex OneConnect 10Gbps NIC Driver"
 
 #define BE_VENDOR_ID 		0x19a2
 #define EMULEX_VENDOR_ID	0x10df
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 5c99570..4d6f3c5 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -25,7 +25,7 @@
 MODULE_VERSION(DRV_VER);
 MODULE_DEVICE_TABLE(pci, be_dev_ids);
 MODULE_DESCRIPTION(DRV_DESC " " DRV_VER);
-MODULE_AUTHOR("ServerEngines Corporation");
+MODULE_AUTHOR("Emulex Corporation");
 MODULE_LICENSE("GPL");
 
 static unsigned int num_vfs;
diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h
index 02a12b6..4dab6fc 100644
--- a/drivers/net/ethernet/intel/e1000e/defines.h
+++ b/drivers/net/ethernet/intel/e1000e/defines.h
@@ -232,6 +232,7 @@
 #define E1000_CTRL_FRCDPX   0x00001000  /* Force Duplex */
 #define E1000_CTRL_LANPHYPC_OVERRIDE 0x00010000 /* SW control of LANPHYPC */
 #define E1000_CTRL_LANPHYPC_VALUE    0x00020000 /* SW value of LANPHYPC */
+#define E1000_CTRL_MEHE     0x00080000  /* Memory Error Handling Enable */
 #define E1000_CTRL_SWDPIN0  0x00040000  /* SWDPIN 0 value */
 #define E1000_CTRL_SWDPIN1  0x00080000  /* SWDPIN 1 value */
 #define E1000_CTRL_SWDPIO0  0x00400000  /* SWDPIN 0 Input or output */
@@ -389,6 +390,12 @@
 
 #define E1000_PBS_16K E1000_PBA_16K
 
+/* Uncorrectable/correctable ECC Error counts and enable bits */
+#define E1000_PBECCSTS_CORR_ERR_CNT_MASK	0x000000FF
+#define E1000_PBECCSTS_UNCORR_ERR_CNT_MASK	0x0000FF00
+#define E1000_PBECCSTS_UNCORR_ERR_CNT_SHIFT	8
+#define E1000_PBECCSTS_ECC_ENABLE		0x00010000
+
 #define IFS_MAX       80
 #define IFS_MIN       40
 #define IFS_RATIO     4
@@ -408,6 +415,7 @@
 #define E1000_ICR_RXSEQ         0x00000008 /* Rx sequence error */
 #define E1000_ICR_RXDMT0        0x00000010 /* Rx desc min. threshold (0) */
 #define E1000_ICR_RXT0          0x00000080 /* Rx timer intr (ring 0) */
+#define E1000_ICR_ECCER         0x00400000 /* Uncorrectable ECC Error */
 #define E1000_ICR_INT_ASSERTED  0x80000000 /* If this bit asserted, the driver should claim the interrupt */
 #define E1000_ICR_RXQ0          0x00100000 /* Rx Queue 0 Interrupt */
 #define E1000_ICR_RXQ1          0x00200000 /* Rx Queue 1 Interrupt */
@@ -443,6 +451,7 @@
 #define E1000_IMS_RXSEQ     E1000_ICR_RXSEQ     /* Rx sequence error */
 #define E1000_IMS_RXDMT0    E1000_ICR_RXDMT0    /* Rx desc min. threshold */
 #define E1000_IMS_RXT0      E1000_ICR_RXT0      /* Rx timer intr */
+#define E1000_IMS_ECCER     E1000_ICR_ECCER     /* Uncorrectable ECC Error */
 #define E1000_IMS_RXQ0      E1000_ICR_RXQ0      /* Rx Queue 0 Interrupt */
 #define E1000_IMS_RXQ1      E1000_ICR_RXQ1      /* Rx Queue 1 Interrupt */
 #define E1000_IMS_TXQ0      E1000_ICR_TXQ0      /* Tx Queue 0 Interrupt */
diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index 6782a2e..7e95f22 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -309,6 +309,8 @@
 
 	struct napi_struct napi;
 
+	unsigned int uncorr_errors;	/* uncorrectable ECC errors */
+	unsigned int corr_errors;	/* correctable ECC errors */
 	unsigned int restart_queue;
 	u32 txd_cmd;
 
diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c
index f95bc6e..fd4772a 100644
--- a/drivers/net/ethernet/intel/e1000e/ethtool.c
+++ b/drivers/net/ethernet/intel/e1000e/ethtool.c
@@ -108,6 +108,8 @@
 	E1000_STAT("dropped_smbus", stats.mgpdc),
 	E1000_STAT("rx_dma_failed", rx_dma_failed),
 	E1000_STAT("tx_dma_failed", tx_dma_failed),
+	E1000_STAT("uncorr_ecc_errors", uncorr_errors),
+	E1000_STAT("corr_ecc_errors", corr_errors),
 };
 
 #define E1000_GLOBAL_STATS_LEN	ARRAY_SIZE(e1000_gstrings_stats)
diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h
index cf21777..b88676f 100644
--- a/drivers/net/ethernet/intel/e1000e/hw.h
+++ b/drivers/net/ethernet/intel/e1000e/hw.h
@@ -77,6 +77,7 @@
 #define E1000_POEMB	E1000_PHY_CTRL	/* PHY OEM Bits */
 	E1000_PBA      = 0x01000, /* Packet Buffer Allocation - RW */
 	E1000_PBS      = 0x01008, /* Packet Buffer Size */
+	E1000_PBECCSTS = 0x0100C, /* Packet Buffer ECC Status - RW */
 	E1000_EEMNGCTL = 0x01010, /* MNG EEprom Control */
 	E1000_EEWR     = 0x0102C, /* EEPROM Write Register - RW */
 	E1000_FLOP     = 0x0103C, /* FLASH Opcode Register */
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index 9763365..24d9f61 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -3624,6 +3624,17 @@
 	if (hw->mac.type == e1000_ich8lan)
 		reg |= (E1000_RFCTL_IPV6_EX_DIS | E1000_RFCTL_NEW_IPV6_EXT_DIS);
 	ew32(RFCTL, reg);
+
+	/* Enable ECC on Lynxpoint */
+	if (hw->mac.type == e1000_pch_lpt) {
+		reg = er32(PBECCSTS);
+		reg |= E1000_PBECCSTS_ECC_ENABLE;
+		ew32(PBECCSTS, reg);
+
+		reg = er32(CTRL);
+		reg |= E1000_CTRL_MEHE;
+		ew32(CTRL, reg);
+	}
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index fbf75fd..643c883 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -1678,6 +1678,23 @@
 			mod_timer(&adapter->watchdog_timer, jiffies + 1);
 	}
 
+	/* Reset on uncorrectable ECC error */
+	if ((icr & E1000_ICR_ECCER) && (hw->mac.type == e1000_pch_lpt)) {
+		u32 pbeccsts = er32(PBECCSTS);
+
+		adapter->corr_errors +=
+		    pbeccsts & E1000_PBECCSTS_CORR_ERR_CNT_MASK;
+		adapter->uncorr_errors +=
+		    (pbeccsts & E1000_PBECCSTS_UNCORR_ERR_CNT_MASK) >>
+		    E1000_PBECCSTS_UNCORR_ERR_CNT_SHIFT;
+
+		/* Do the reset outside of interrupt context */
+		schedule_work(&adapter->reset_task);
+
+		/* return immediately since reset is imminent */
+		return IRQ_HANDLED;
+	}
+
 	if (napi_schedule_prep(&adapter->napi)) {
 		adapter->total_tx_bytes = 0;
 		adapter->total_tx_packets = 0;
@@ -1741,6 +1758,23 @@
 			mod_timer(&adapter->watchdog_timer, jiffies + 1);
 	}
 
+	/* Reset on uncorrectable ECC error */
+	if ((icr & E1000_ICR_ECCER) && (hw->mac.type == e1000_pch_lpt)) {
+		u32 pbeccsts = er32(PBECCSTS);
+
+		adapter->corr_errors +=
+		    pbeccsts & E1000_PBECCSTS_CORR_ERR_CNT_MASK;
+		adapter->uncorr_errors +=
+		    (pbeccsts & E1000_PBECCSTS_UNCORR_ERR_CNT_MASK) >>
+		    E1000_PBECCSTS_UNCORR_ERR_CNT_SHIFT;
+
+		/* Do the reset outside of interrupt context */
+		schedule_work(&adapter->reset_task);
+
+		/* return immediately since reset is imminent */
+		return IRQ_HANDLED;
+	}
+
 	if (napi_schedule_prep(&adapter->napi)) {
 		adapter->total_tx_bytes = 0;
 		adapter->total_tx_packets = 0;
@@ -2104,6 +2138,8 @@
 	if (adapter->msix_entries) {
 		ew32(EIAC_82574, adapter->eiac_mask & E1000_EIAC_MASK_82574);
 		ew32(IMS, adapter->eiac_mask | E1000_IMS_OTHER | E1000_IMS_LSC);
+	} else if (hw->mac.type == e1000_pch_lpt) {
+		ew32(IMS, IMS_ENABLE_MASK | E1000_IMS_ECCER);
 	} else {
 		ew32(IMS, IMS_ENABLE_MASK);
 	}
@@ -4251,6 +4287,16 @@
 	adapter->stats.mgptc += er32(MGTPTC);
 	adapter->stats.mgprc += er32(MGTPRC);
 	adapter->stats.mgpdc += er32(MGTPDC);
+
+	/* Correctable ECC Errors */
+	if (hw->mac.type == e1000_pch_lpt) {
+		u32 pbeccsts = er32(PBECCSTS);
+		adapter->corr_errors +=
+		    pbeccsts & E1000_PBECCSTS_CORR_ERR_CNT_MASK;
+		adapter->uncorr_errors +=
+		    (pbeccsts & E1000_PBECCSTS_UNCORR_ERR_CNT_MASK) >>
+		    E1000_PBECCSTS_UNCORR_ERR_CNT_SHIFT;
+	}
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ixgbe/Makefile b/drivers/net/ethernet/intel/ixgbe/Makefile
index f3a632b..687c83d 100644
--- a/drivers/net/ethernet/intel/ixgbe/Makefile
+++ b/drivers/net/ethernet/intel/ixgbe/Makefile
@@ -32,7 +32,7 @@
 
 obj-$(CONFIG_IXGBE) += ixgbe.o
 
-ixgbe-objs := ixgbe_main.o ixgbe_common.o ixgbe_ethtool.o ixgbe_debugfs.o\
+ixgbe-objs := ixgbe_main.o ixgbe_common.o ixgbe_ethtool.o \
               ixgbe_82599.o ixgbe_82598.o ixgbe_phy.o ixgbe_sriov.o \
               ixgbe_mbx.o ixgbe_x540.o ixgbe_lib.o ixgbe_ptp.o
 
@@ -40,4 +40,5 @@
                               ixgbe_dcb_82599.o ixgbe_dcb_nl.o
 
 ixgbe-$(CONFIG_IXGBE_HWMON) += ixgbe_sysfs.o
+ixgbe-$(CONFIG_DEBUG_FS) += ixgbe_debugfs.o
 ixgbe-$(CONFIG_FCOE:m=y) += ixgbe_fcoe.o
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c
index 50aa546..3504686 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c
@@ -24,9 +24,6 @@
   Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
 
 *******************************************************************************/
-
-#ifdef CONFIG_DEBUG_FS
-
 #include <linux/debugfs.h>
 #include <linux/module.h>
 
@@ -277,5 +274,3 @@
 {
 	debugfs_remove_recursive(ixgbe_dbg_root);
 }
-
-#endif /* CONFIG_DEBUG_FS */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 20a5af6..b3e3294 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -1401,6 +1401,7 @@
 	/* set gso_size to avoid messing up TCP MSS */
 	skb_shinfo(skb)->gso_size = DIV_ROUND_UP((skb->len - hdr_len),
 						 IXGBE_CB(skb)->append_cnt);
+	skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
 }
 
 static void ixgbe_update_rsc_stats(struct ixgbe_ring *rx_ring,
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
index 1a751c9..bb9256a 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
@@ -660,11 +660,11 @@
 		break;
 	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
 		tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_L4_V1;
-		tsync_rx_mtrl = IXGBE_RXMTRL_V1_SYNC_MSG;
+		tsync_rx_mtrl |= IXGBE_RXMTRL_V1_SYNC_MSG;
 		break;
 	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
 		tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_L4_V1;
-		tsync_rx_mtrl = IXGBE_RXMTRL_V1_DELAY_REQ_MSG;
+		tsync_rx_mtrl |= IXGBE_RXMTRL_V1_DELAY_REQ_MSG;
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 2b799f4..6771b69 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -630,10 +630,15 @@
 		ring->tx_csum++;
 	}
 
-	/* Copy dst mac address to wqe */
-	ethh = (struct ethhdr *)skb->data;
-	tx_desc->ctrl.srcrb_flags16[0] = get_unaligned((__be16 *)ethh->h_dest);
-	tx_desc->ctrl.imm = get_unaligned((__be32 *)(ethh->h_dest + 2));
+	if (mlx4_is_mfunc(mdev->dev) || priv->validate_loopback) {
+		/* Copy dst mac address to wqe. This allows loopback in eSwitch,
+		 * so that VFs and PF can communicate with each other
+		 */
+		ethh = (struct ethhdr *)skb->data;
+		tx_desc->ctrl.srcrb_flags16[0] = get_unaligned((__be16 *)ethh->h_dest);
+		tx_desc->ctrl.imm = get_unaligned((__be32 *)(ethh->h_dest + 2));
+	}
+
 	/* Handle LSO (TSO) packets */
 	if (lso_header_size) {
 		/* Mark opcode as LSO */
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index e1bafff..5163af3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -380,7 +380,7 @@
 		}
 	}
 
-	if ((dev_cap->flags &
+	if ((dev->caps.flags &
 	    (MLX4_DEV_CAP_FLAG_64B_CQE | MLX4_DEV_CAP_FLAG_64B_EQE)) &&
 	    mlx4_is_master(dev))
 		dev->caps.function_caps |= MLX4_FUNC_CAP_64B_EQE_CQE;
@@ -1790,15 +1790,8 @@
 	int i;
 
 	if (msi_x) {
-		/* In multifunction mode each function gets 2 msi-X vectors
-		 * one for data path completions anf the other for asynch events
-		 * or command completions */
-		if (mlx4_is_mfunc(dev)) {
-			nreq = 2;
-		} else {
-			nreq = min_t(int, dev->caps.num_eqs -
-				     dev->caps.reserved_eqs, nreq);
-		}
+		nreq = min_t(int, dev->caps.num_eqs - dev->caps.reserved_eqs,
+			     nreq);
 
 		entries = kcalloc(nreq, sizeof *entries, GFP_KERNEL);
 		if (!entries)
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c
index bc165f4..695667d 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c
@@ -144,7 +144,7 @@
 					 buffrag->length, PCI_DMA_TODEVICE);
 			buffrag->dma = 0ULL;
 		}
-		for (j = 0; j < cmd_buf->frag_count; j++) {
+		for (j = 1; j < cmd_buf->frag_count; j++) {
 			buffrag++;
 			if (buffrag->dma) {
 				pci_unmap_page(adapter->pdev, buffrag->dma,
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
index 6098fd4a..69e321a 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
@@ -1963,10 +1963,12 @@
 	while (--i >= 0) {
 		nf = &pbuf->frag_array[i+1];
 		pci_unmap_page(pdev, nf->dma, nf->length, PCI_DMA_TODEVICE);
+		nf->dma = 0ULL;
 	}
 
 	nf = &pbuf->frag_array[0];
 	pci_unmap_single(pdev, nf->dma, skb_headlen(skb), PCI_DMA_TODEVICE);
+	nf->dma = 0ULL;
 
 out_err:
 	return -ENOMEM;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
index 6f82812..09aa310 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
@@ -986,8 +986,13 @@
 	th->seq = htonl(seq_number);
 	length = skb->len;
 
-	if (adapter->flags & QLCNIC_FW_LRO_MSS_CAP)
+	if (adapter->flags & QLCNIC_FW_LRO_MSS_CAP) {
 		skb_shinfo(skb)->gso_size = qlcnic_get_lro_sts_mss(sts_data1);
+		if (skb->protocol == htons(ETH_P_IPV6))
+			skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
+		else
+			skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
+	}
 
 	if (vid != 0xffff)
 		__vlan_hwaccel_put_tag(skb, vid);
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index ed96f30..998974f 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -450,7 +450,6 @@
 #define PWM_EN				(1 << 22)
 #define RXDV_GATED_EN			(1 << 19)
 #define EARLY_TALLY_EN			(1 << 16)
-#define FORCE_CLK			(1 << 15) /* force clock request */
 };
 
 enum rtl_register_content {
@@ -514,7 +513,6 @@
 	PMEnable	= (1 << 0),	/* Power Management Enable */
 
 	/* Config2 register p. 25 */
-	ClkReqEn	= (1 << 7),	/* Clock Request Enable */
 	MSIEnable	= (1 << 5),	/* 8169 only. Reserved in the 8168. */
 	PCI_Clock_66MHz = 0x01,
 	PCI_Clock_33MHz = 0x00,
@@ -535,7 +533,6 @@
 	Spi_en		= (1 << 3),
 	LanWake		= (1 << 1),	/* LanWake enable/disable */
 	PMEStatus	= (1 << 0),	/* PME status can be reset by PCI RST# */
-	ASPM_en		= (1 << 0),	/* ASPM enable */
 
 	/* TBICSR p.28 */
 	TBIReset	= 0x80000000,
@@ -684,7 +681,6 @@
 	RTL_FEATURE_WOL		= (1 << 0),
 	RTL_FEATURE_MSI		= (1 << 1),
 	RTL_FEATURE_GMII	= (1 << 2),
-	RTL_FEATURE_FW_LOADED	= (1 << 3),
 };
 
 struct rtl8169_counters {
@@ -1826,8 +1822,6 @@
 
 	if (opts2 & RxVlanTag)
 		__vlan_hwaccel_put_tag(skb, swab16(opts2 & 0xffff));
-
-	desc->opts2 = 0;
 }
 
 static int rtl8169_gset_tbi(struct net_device *dev, struct ethtool_cmd *cmd)
@@ -2391,10 +2385,8 @@
 	struct rtl_fw *rtl_fw = tp->rtl_fw;
 
 	/* TODO: release firmware once rtl_phy_write_fw signals failures. */
-	if (!IS_ERR_OR_NULL(rtl_fw)) {
+	if (!IS_ERR_OR_NULL(rtl_fw))
 		rtl_phy_write_fw(tp, rtl_fw);
-		tp->features |= RTL_FEATURE_FW_LOADED;
-	}
 }
 
 static void rtl_apply_firmware_cond(struct rtl8169_private *tp, u8 reg, u16 val)
@@ -2405,31 +2397,6 @@
 		rtl_apply_firmware(tp);
 }
 
-static void r810x_aldps_disable(struct rtl8169_private *tp)
-{
-	rtl_writephy(tp, 0x1f, 0x0000);
-	rtl_writephy(tp, 0x18, 0x0310);
-	msleep(100);
-}
-
-static void r810x_aldps_enable(struct rtl8169_private *tp)
-{
-	if (!(tp->features & RTL_FEATURE_FW_LOADED))
-		return;
-
-	rtl_writephy(tp, 0x1f, 0x0000);
-	rtl_writephy(tp, 0x18, 0x8310);
-}
-
-static void r8168_aldps_enable_1(struct rtl8169_private *tp)
-{
-	if (!(tp->features & RTL_FEATURE_FW_LOADED))
-		return;
-
-	rtl_writephy(tp, 0x1f, 0x0000);
-	rtl_w1w0_phy(tp, 0x15, 0x1000, 0x0000);
-}
-
 static void rtl8169s_hw_phy_config(struct rtl8169_private *tp)
 {
 	static const struct phy_reg phy_reg_init[] = {
@@ -3220,8 +3187,6 @@
 	rtl_w1w0_phy(tp, 0x10, 0x0000, 0x0400);
 	rtl_writephy(tp, 0x1f, 0x0000);
 
-	r8168_aldps_enable_1(tp);
-
 	/* Broken BIOS workaround: feed GigaMAC registers with MAC address. */
 	rtl_rar_exgmac_set(tp, tp->dev->dev_addr);
 }
@@ -3296,8 +3261,6 @@
 	rtl_writephy(tp, 0x05, 0x8b85);
 	rtl_w1w0_phy(tp, 0x06, 0x4000, 0x0000);
 	rtl_writephy(tp, 0x1f, 0x0000);
-
-	r8168_aldps_enable_1(tp);
 }
 
 static void rtl8168f_2_hw_phy_config(struct rtl8169_private *tp)
@@ -3305,8 +3268,6 @@
 	rtl_apply_firmware(tp);
 
 	rtl8168f_hw_phy_config(tp);
-
-	r8168_aldps_enable_1(tp);
 }
 
 static void rtl8411_hw_phy_config(struct rtl8169_private *tp)
@@ -3404,8 +3365,6 @@
 	rtl_w1w0_phy(tp, 0x19, 0x0000, 0x0001);
 	rtl_w1w0_phy(tp, 0x10, 0x0000, 0x0400);
 	rtl_writephy(tp, 0x1f, 0x0000);
-
-	r8168_aldps_enable_1(tp);
 }
 
 static void rtl8168g_1_hw_phy_config(struct rtl8169_private *tp)
@@ -3491,19 +3450,21 @@
 	};
 
 	/* Disable ALDPS before ram code */
-	r810x_aldps_disable(tp);
+	rtl_writephy(tp, 0x1f, 0x0000);
+	rtl_writephy(tp, 0x18, 0x0310);
+	msleep(100);
 
 	rtl_apply_firmware(tp);
 
 	rtl_writephy_batch(tp, phy_reg_init, ARRAY_SIZE(phy_reg_init));
-
-	r810x_aldps_enable(tp);
 }
 
 static void rtl8402_hw_phy_config(struct rtl8169_private *tp)
 {
 	/* Disable ALDPS before setting firmware */
-	r810x_aldps_disable(tp);
+	rtl_writephy(tp, 0x1f, 0x0000);
+	rtl_writephy(tp, 0x18, 0x0310);
+	msleep(20);
 
 	rtl_apply_firmware(tp);
 
@@ -3513,8 +3474,6 @@
 	rtl_writephy(tp, 0x10, 0x401f);
 	rtl_writephy(tp, 0x19, 0x7030);
 	rtl_writephy(tp, 0x1f, 0x0000);
-
-	r810x_aldps_enable(tp);
 }
 
 static void rtl8106e_hw_phy_config(struct rtl8169_private *tp)
@@ -3527,7 +3486,9 @@
 	};
 
 	/* Disable ALDPS before ram code */
-	r810x_aldps_disable(tp);
+	rtl_writephy(tp, 0x1f, 0x0000);
+	rtl_writephy(tp, 0x18, 0x0310);
+	msleep(100);
 
 	rtl_apply_firmware(tp);
 
@@ -3535,8 +3496,6 @@
 	rtl_writephy_batch(tp, phy_reg_init, ARRAY_SIZE(phy_reg_init));
 
 	rtl_eri_write(tp, 0x1d0, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC);
-
-	r810x_aldps_enable(tp);
 }
 
 static void rtl_hw_phy_config(struct net_device *dev)
@@ -5053,6 +5012,8 @@
 
 	RTL_W8(MaxTxPacketSize, EarlySize);
 
+	rtl_disable_clock_request(pdev);
+
 	RTL_W32(TxConfig, RTL_R32(TxConfig) | TXCFG_AUTO_FIFO);
 	RTL_W8(MCU, RTL_R8(MCU) & ~NOW_IS_OOB);
 
@@ -5061,8 +5022,7 @@
 
 	RTL_W8(DLLPR, RTL_R8(DLLPR) | PFM_EN);
 	RTL_W32(MISC, RTL_R32(MISC) | PWM_EN);
-	RTL_W8(Config5, (RTL_R8(Config5) & ~Spi_en) | ASPM_en);
-	RTL_W8(Config2, RTL_R8(Config2) | ClkReqEn);
+	RTL_W8(Config5, RTL_R8(Config5) & ~Spi_en);
 }
 
 static void rtl_hw_start_8168f(struct rtl8169_private *tp)
@@ -5087,12 +5047,13 @@
 
 	RTL_W8(MaxTxPacketSize, EarlySize);
 
+	rtl_disable_clock_request(pdev);
+
 	RTL_W32(TxConfig, RTL_R32(TxConfig) | TXCFG_AUTO_FIFO);
 	RTL_W8(MCU, RTL_R8(MCU) & ~NOW_IS_OOB);
 	RTL_W8(DLLPR, RTL_R8(DLLPR) | PFM_EN);
-	RTL_W32(MISC, RTL_R32(MISC) | PWM_EN | FORCE_CLK);
-	RTL_W8(Config5, (RTL_R8(Config5) & ~Spi_en) | ASPM_en);
-	RTL_W8(Config2, RTL_R8(Config2) | ClkReqEn);
+	RTL_W32(MISC, RTL_R32(MISC) | PWM_EN);
+	RTL_W8(Config5, RTL_R8(Config5) & ~Spi_en);
 }
 
 static void rtl_hw_start_8168f_1(struct rtl8169_private *tp)
@@ -5149,10 +5110,8 @@
 	rtl_w1w0_eri(tp, 0xdc, ERIAR_MASK_0001, 0x01, 0x00, ERIAR_EXGMAC);
 
 	RTL_W8(ChipCmd, CmdTxEnb | CmdRxEnb);
-	RTL_W32(MISC, (RTL_R32(MISC) | FORCE_CLK) & ~RXDV_GATED_EN);
+	RTL_W32(MISC, RTL_R32(MISC) & ~RXDV_GATED_EN);
 	RTL_W8(MaxTxPacketSize, EarlySize);
-	RTL_W8(Config5, RTL_R8(Config5) | ASPM_en);
-	RTL_W8(Config2, RTL_R8(Config2) | ClkReqEn);
 
 	rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC);
 	rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC);
@@ -5368,9 +5327,6 @@
 
 	RTL_W8(MCU, RTL_R8(MCU) | EN_NDP | EN_OOB_RESET);
 	RTL_W8(DLLPR, RTL_R8(DLLPR) | PFM_EN);
-	RTL_W8(Config5, RTL_R8(Config5) | ASPM_en);
-	RTL_W8(Config2, RTL_R8(Config2) | ClkReqEn);
-	RTL_W32(MISC, RTL_R32(MISC) | FORCE_CLK);
 
 	rtl_ephy_init(tp, e_info_8105e_1, ARRAY_SIZE(e_info_8105e_1));
 }
@@ -5396,9 +5352,6 @@
 
 	RTL_W32(TxConfig, RTL_R32(TxConfig) | TXCFG_AUTO_FIFO);
 	RTL_W8(MCU, RTL_R8(MCU) & ~NOW_IS_OOB);
-	RTL_W8(Config5, RTL_R8(Config5) | ASPM_en);
-	RTL_W8(Config2, RTL_R8(Config2) | ClkReqEn);
-	RTL_W32(MISC, RTL_R32(MISC) | FORCE_CLK);
 
 	rtl_ephy_init(tp, e_info_8402, ARRAY_SIZE(e_info_8402));
 
@@ -5420,10 +5373,7 @@
 	/* Force LAN exit from ASPM if Rx/Tx are not idle */
 	RTL_W32(FuncEvent, RTL_R32(FuncEvent) | 0x002800);
 
-	RTL_W32(MISC,
-		(RTL_R32(MISC) | DISABLE_LAN_EN | FORCE_CLK) & ~EARLY_TALLY_EN);
-	RTL_W8(Config5, RTL_R8(Config5) | ASPM_en);
-	RTL_W8(Config2, RTL_R8(Config2) | ClkReqEn);
+	RTL_W32(MISC, (RTL_R32(MISC) | DISABLE_LAN_EN) & ~EARLY_TALLY_EN);
 	RTL_W8(MCU, RTL_R8(MCU) | EN_NDP | EN_OOB_RESET);
 	RTL_W8(DLLPR, RTL_R8(DLLPR) & ~PFM_EN);
 }
@@ -6064,8 +6014,6 @@
 			    !(status & (RxRWT | RxFOVF)) &&
 			    (dev->features & NETIF_F_RXALL))
 				goto process_pkt;
-
-			rtl8169_mark_to_asic(desc, rx_buf_sz);
 		} else {
 			struct sk_buff *skb;
 			dma_addr_t addr;
@@ -6086,16 +6034,14 @@
 			if (unlikely(rtl8169_fragmented_frame(status))) {
 				dev->stats.rx_dropped++;
 				dev->stats.rx_length_errors++;
-				rtl8169_mark_to_asic(desc, rx_buf_sz);
-				continue;
+				goto release_descriptor;
 			}
 
 			skb = rtl8169_try_rx_copy(tp->Rx_databuff[entry],
 						  tp, pkt_size, addr);
-			rtl8169_mark_to_asic(desc, rx_buf_sz);
 			if (!skb) {
 				dev->stats.rx_dropped++;
-				continue;
+				goto release_descriptor;
 			}
 
 			rtl8169_rx_csum(skb, status);
@@ -6111,13 +6057,10 @@
 			tp->rx_stats.bytes += pkt_size;
 			u64_stats_update_end(&tp->rx_stats.syncp);
 		}
-
-		/* Work around for AMD plateform. */
-		if ((desc->opts2 & cpu_to_le32(0xfffe000)) &&
-		    (tp->mac_version == RTL_GIGA_MAC_VER_05)) {
-			desc->opts2 = 0;
-			cur_rx++;
-		}
+release_descriptor:
+		desc->opts2 = 0;
+		wmb();
+		rtl8169_mark_to_asic(desc, rx_buf_sz);
 	}
 
 	count = cur_rx - tp->cur_rx;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index f07c061..b75f4b2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -69,7 +69,7 @@
 
 #undef STMMAC_XMIT_DEBUG
 /*#define STMMAC_XMIT_DEBUG*/
-#ifdef STMMAC_TX_DEBUG
+#ifdef STMMAC_XMIT_DEBUG
 #define TX_DBG(fmt, args...)  printk(fmt, ## args)
 #else
 #define TX_DBG(fmt, args...)  do { } while (0)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index 0376a5e..0b9829f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -188,8 +188,6 @@
 		goto bus_register_fail;
 	}
 
-	priv->mii = new_bus;
-
 	found = 0;
 	for (addr = 0; addr < PHY_MAX_ADDR; addr++) {
 		struct phy_device *phydev = new_bus->phy_map[addr];
@@ -237,8 +235,14 @@
 		}
 	}
 
-	if (!found)
+	if (!found) {
 		pr_warning("%s: No PHY found\n", ndev->name);
+		mdiobus_unregister(new_bus);
+		mdiobus_free(new_bus);
+		return -ENODEV;
+	}
+
+	priv->mii = new_bus;
 
 	return 0;
 
diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c
index 7992b3e..78ace59 100644
--- a/drivers/net/ethernet/via/via-rhine.c
+++ b/drivers/net/ethernet/via/via-rhine.c
@@ -1801,7 +1801,7 @@
 					 rp->tx_skbuff[entry]->len,
 					 PCI_DMA_TODEVICE);
 		}
-		dev_kfree_skb_irq(rp->tx_skbuff[entry]);
+		dev_kfree_skb(rp->tx_skbuff[entry]);
 		rp->tx_skbuff[entry] = NULL;
 		entry = (++rp->dirty_tx) % TX_RING_SIZE;
 	}
@@ -2010,11 +2010,7 @@
 	if (intr_status & IntrPCIErr)
 		netif_warn(rp, hw, dev, "PCI error\n");
 
-	napi_disable(&rp->napi);
-	rhine_irq_disable(rp);
-	/* Slow and safe. Consider __napi_schedule as a replacement ? */
-	napi_enable(&rp->napi);
-	napi_schedule(&rp->napi);
+	iowrite16(RHINE_EVENT & 0xffff, rp->base + IntrEnable);
 
 out_unlock:
 	mutex_unlock(&rp->task_lock);
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 5fd6f46..e6fe0d8 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -84,7 +84,7 @@
 };
 
 struct netvsc_device_info {
-	unsigned char mac_adr[6];
+	unsigned char mac_adr[ETH_ALEN];
 	bool link_state;	/* 0 - link up, 1 - link down */
 	int  ring_size;
 };
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index f825a62..8264f0e 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -349,7 +349,7 @@
 	struct net_device_context *ndevctx = netdev_priv(ndev);
 	struct hv_device *hdev =  ndevctx->device_ctx;
 	struct sockaddr *addr = p;
-	char save_adr[14];
+	char save_adr[ETH_ALEN];
 	unsigned char save_aatype;
 	int err;
 
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index 81f8f9e..fcbf680 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -77,6 +77,11 @@
 
 	skb_orphan(skb);
 
+	/* Before queueing this packet to netif_rx(),
+	 * make sure dst is refcounted.
+	 */
+	skb_dst_force(skb);
+
 	skb->protocol = eth_type_trans(skb, dev);
 
 	/* it's OK to use per_cpu_ptr() because BHs are off */
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 68a43fe..d3fb97d 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -822,7 +822,10 @@
 
 static size_t macvlan_get_size(const struct net_device *dev)
 {
-	return nla_total_size(4);
+	return (0
+		+ nla_total_size(4) /* IFLA_MACVLAN_MODE */
+		+ nla_total_size(2) /* IFLA_MACVLAN_FLAGS */
+		);
 }
 
 static int macvlan_fill_info(struct sk_buff *skb,
diff --git a/drivers/net/phy/icplus.c b/drivers/net/phy/icplus.c
index d5199cb..b5ddd50 100644
--- a/drivers/net/phy/icplus.c
+++ b/drivers/net/phy/icplus.c
@@ -36,8 +36,9 @@
 
 /* IP101A/G - IP1001 */
 #define IP10XX_SPEC_CTRL_STATUS		16	/* Spec. Control Register */
+#define IP1001_RXPHASE_SEL		(1<<0)	/* Add delay on RX_CLK */
+#define IP1001_TXPHASE_SEL		(1<<1)	/* Add delay on TX_CLK */
 #define IP1001_SPEC_CTRL_STATUS_2	20	/* IP1001 Spec. Control Reg 2 */
-#define IP1001_PHASE_SEL_MASK		3	/* IP1001 RX/TXPHASE_SEL */
 #define IP1001_APS_ON			11	/* IP1001 APS Mode  bit */
 #define IP101A_G_APS_ON			2	/* IP101A/G APS Mode bit */
 #define IP101A_G_IRQ_CONF_STATUS	0x11	/* Conf Info IRQ & Status Reg */
@@ -138,19 +139,24 @@
 	if (c < 0)
 		return c;
 
-	/* INTR pin used: speed/link/duplex will cause an interrupt */
-	c = phy_write(phydev, IP101A_G_IRQ_CONF_STATUS, IP101A_G_IRQ_DEFAULT);
-	if (c < 0)
-		return c;
+	if ((phydev->interface == PHY_INTERFACE_MODE_RGMII) ||
+	    (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID) ||
+	    (phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID) ||
+	    (phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID)) {
 
-	if (phydev->interface == PHY_INTERFACE_MODE_RGMII) {
-		/* Additional delay (2ns) used to adjust RX clock phase
-		 * at RGMII interface */
 		c = phy_read(phydev, IP10XX_SPEC_CTRL_STATUS);
 		if (c < 0)
 			return c;
 
-		c |= IP1001_PHASE_SEL_MASK;
+		c &= ~(IP1001_RXPHASE_SEL | IP1001_TXPHASE_SEL);
+
+		if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID)
+			c |= (IP1001_RXPHASE_SEL | IP1001_TXPHASE_SEL);
+		else if (phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID)
+			c |= IP1001_RXPHASE_SEL;
+		else if (phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID)
+			c |= IP1001_TXPHASE_SEL;
+
 		c = phy_write(phydev, IP10XX_SPEC_CTRL_STATUS, c);
 		if (c < 0)
 			return c;
@@ -167,6 +173,11 @@
 	if (c < 0)
 		return c;
 
+	/* INTR pin used: speed/link/duplex will cause an interrupt */
+	c = phy_write(phydev, IP101A_G_IRQ_CONF_STATUS, IP101A_G_IRQ_DEFAULT);
+	if (c < 0)
+		return c;
+
 	/* Enable Auto Power Saving mode */
 	c = phy_read(phydev, IP10XX_SPEC_CTRL_STATUS);
 	c |= IP101A_G_APS_ON;
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 5d2a3f2..22dec9c 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -353,15 +353,6 @@
 	int err;
 	int temp;
 
-	/* Enable Fiber/Copper auto selection */
-	temp = phy_read(phydev, MII_M1111_PHY_EXT_SR);
-	temp &= ~MII_M1111_HWCFG_FIBER_COPPER_AUTO;
-	phy_write(phydev, MII_M1111_PHY_EXT_SR, temp);
-
-	temp = phy_read(phydev, MII_BMCR);
-	temp |= BMCR_RESET;
-	phy_write(phydev, MII_BMCR, temp);
-
 	if ((phydev->interface == PHY_INTERFACE_MODE_RGMII) ||
 	    (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID) ||
 	    (phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID) ||
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index af372d0..2917a86 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -109,11 +109,11 @@
 	unsigned char	addr[FLT_EXACT_COUNT][ETH_ALEN];
 };
 
-/* 1024 is probably a high enough limit: modern hypervisors seem to support on
- * the order of 100-200 CPUs so this leaves us some breathing space if we want
- * to match a queue per guest CPU.
- */
-#define MAX_TAP_QUEUES 1024
+/* DEFAULT_MAX_NUM_RSS_QUEUES were choosed to let the rx/tx queues allocated for
+ * the netdevice to be fit in one page. So we can make sure the success of
+ * memory allocation. TODO: increase the limit. */
+#define MAX_TAP_QUEUES DEFAULT_MAX_NUM_RSS_QUEUES
+#define MAX_TAP_FLOWS  4096
 
 #define TUN_FLOW_EXPIRE (3 * HZ)
 
@@ -185,6 +185,8 @@
 	unsigned long ageing_time;
 	unsigned int numdisabled;
 	struct list_head disabled;
+	void *security;
+	u32 flow_count;
 };
 
 static inline u32 tun_hashfn(u32 rxhash)
@@ -218,6 +220,7 @@
 		e->queue_index = queue_index;
 		e->tun = tun;
 		hlist_add_head_rcu(&e->hash_link, head);
+		++tun->flow_count;
 	}
 	return e;
 }
@@ -228,6 +231,7 @@
 		  e->rxhash, e->queue_index);
 	hlist_del_rcu(&e->hash_link);
 	kfree_rcu(e, rcu);
+	--tun->flow_count;
 }
 
 static void tun_flow_flush(struct tun_struct *tun)
@@ -294,11 +298,12 @@
 }
 
 static void tun_flow_update(struct tun_struct *tun, u32 rxhash,
-			    u16 queue_index)
+			    struct tun_file *tfile)
 {
 	struct hlist_head *head;
 	struct tun_flow_entry *e;
 	unsigned long delay = tun->ageing_time;
+	u16 queue_index = tfile->queue_index;
 
 	if (!rxhash)
 		return;
@@ -307,7 +312,9 @@
 
 	rcu_read_lock();
 
-	if (tun->numqueues == 1)
+	/* We may get a very small possibility of OOO during switching, not
+	 * worth to optimize.*/
+	if (tun->numqueues == 1 || tfile->detached)
 		goto unlock;
 
 	e = tun_flow_find(head, rxhash);
@@ -317,7 +324,8 @@
 		e->updated = jiffies;
 	} else {
 		spin_lock_bh(&tun->lock);
-		if (!tun_flow_find(head, rxhash))
+		if (!tun_flow_find(head, rxhash) &&
+		    tun->flow_count < MAX_TAP_FLOWS)
 			tun_flow_create(tun, head, rxhash, queue_index);
 
 		if (!timer_pending(&tun->flow_gc_timer))
@@ -406,21 +414,21 @@
 
 	tun = rtnl_dereference(tfile->tun);
 
-	if (tun) {
+	if (tun && !tfile->detached) {
 		u16 index = tfile->queue_index;
 		BUG_ON(index >= tun->numqueues);
 		dev = tun->dev;
 
 		rcu_assign_pointer(tun->tfiles[index],
 				   tun->tfiles[tun->numqueues - 1]);
-		rcu_assign_pointer(tfile->tun, NULL);
 		ntfile = rtnl_dereference(tun->tfiles[index]);
 		ntfile->queue_index = index;
 
 		--tun->numqueues;
-		if (clean)
+		if (clean) {
+			rcu_assign_pointer(tfile->tun, NULL);
 			sock_put(&tfile->sk);
-		else
+		} else
 			tun_disable_queue(tun, tfile);
 
 		synchronize_net();
@@ -434,10 +442,13 @@
 	}
 
 	if (clean) {
-		if (tun && tun->numqueues == 0 && tun->numdisabled == 0 &&
-		    !(tun->flags & TUN_PERSIST))
-			if (tun->dev->reg_state == NETREG_REGISTERED)
+		if (tun && tun->numqueues == 0 && tun->numdisabled == 0) {
+			netif_carrier_off(tun->dev);
+
+			if (!(tun->flags & TUN_PERSIST) &&
+			    tun->dev->reg_state == NETREG_REGISTERED)
 				unregister_netdevice(tun->dev);
+		}
 
 		BUG_ON(!test_bit(SOCK_EXTERNALLY_ALLOCATED,
 				 &tfile->socket.flags));
@@ -465,6 +476,10 @@
 		rcu_assign_pointer(tfile->tun, NULL);
 		--tun->numqueues;
 	}
+	list_for_each_entry(tfile, &tun->disabled, next) {
+		wake_up_all(&tfile->wq.wait);
+		rcu_assign_pointer(tfile->tun, NULL);
+	}
 	BUG_ON(tun->numqueues != 0);
 
 	synchronize_net();
@@ -490,8 +505,12 @@
 	struct tun_file *tfile = file->private_data;
 	int err;
 
+	err = security_tun_dev_attach(tfile->socket.sk, tun->security);
+	if (err < 0)
+		goto out;
+
 	err = -EINVAL;
-	if (rtnl_dereference(tfile->tun))
+	if (rtnl_dereference(tfile->tun) && !tfile->detached)
 		goto out;
 
 	err = -EBUSY;
@@ -1190,7 +1209,7 @@
 	tun->dev->stats.rx_packets++;
 	tun->dev->stats.rx_bytes += len;
 
-	tun_flow_update(tun, rxhash, tfile->queue_index);
+	tun_flow_update(tun, rxhash, tfile);
 	return total_len;
 }
 
@@ -1373,6 +1392,7 @@
 
 	BUG_ON(!(list_empty(&tun->disabled)));
 	tun_flow_uninit(tun);
+	security_tun_dev_free_security(tun->security);
 	free_netdev(dev);
 }
 
@@ -1562,7 +1582,7 @@
 
 		if (tun_not_capable(tun))
 			return -EPERM;
-		err = security_tun_dev_attach(tfile->socket.sk);
+		err = security_tun_dev_open(tun->security);
 		if (err < 0)
 			return err;
 
@@ -1577,6 +1597,8 @@
 	else {
 		char *name;
 		unsigned long flags = 0;
+		int queues = ifr->ifr_flags & IFF_MULTI_QUEUE ?
+			     MAX_TAP_QUEUES : 1;
 
 		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 			return -EPERM;
@@ -1600,8 +1622,8 @@
 			name = ifr->ifr_name;
 
 		dev = alloc_netdev_mqs(sizeof(struct tun_struct), name,
-				       tun_setup,
-				       MAX_TAP_QUEUES, MAX_TAP_QUEUES);
+				       tun_setup, queues, queues);
+
 		if (!dev)
 			return -ENOMEM;
 
@@ -1619,7 +1641,9 @@
 
 		spin_lock_init(&tun->lock);
 
-		security_tun_dev_post_create(&tfile->sk);
+		err = security_tun_dev_alloc_security(&tun->security);
+		if (err < 0)
+			goto err_free_dev;
 
 		tun_net_init(dev);
 
@@ -1644,10 +1668,10 @@
 		    device_create_file(&tun->dev->dev, &dev_attr_owner) ||
 		    device_create_file(&tun->dev->dev, &dev_attr_group))
 			pr_err("Failed to create tun sysfs files\n");
-
-		netif_carrier_on(tun->dev);
 	}
 
+	netif_carrier_on(tun->dev);
+
 	tun_debug(KERN_INFO, tun, "tun_set_iff\n");
 
 	if (ifr->ifr_flags & IFF_NO_PI)
@@ -1789,19 +1813,24 @@
 
 	if (ifr->ifr_flags & IFF_ATTACH_QUEUE) {
 		tun = tfile->detached;
-		if (!tun)
+		if (!tun) {
 			ret = -EINVAL;
-		else
-			ret = tun_attach(tun, file);
+			goto unlock;
+		}
+		ret = security_tun_dev_attach_queue(tun->security);
+		if (ret < 0)
+			goto unlock;
+		ret = tun_attach(tun, file);
 	} else if (ifr->ifr_flags & IFF_DETACH_QUEUE) {
 		tun = rtnl_dereference(tfile->tun);
-		if (!tun || !(tun->flags & TUN_TAP_MQ))
+		if (!tun || !(tun->flags & TUN_TAP_MQ) || tfile->detached)
 			ret = -EINVAL;
 		else
 			__tun_detach(tfile, false);
 	} else
 		ret = -EINVAL;
 
+unlock:
 	rtnl_unlock();
 	return ret;
 }
diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c
index 42f51c7..248d2dc 100644
--- a/drivers/net/usb/cdc_mbim.c
+++ b/drivers/net/usb/cdc_mbim.c
@@ -374,6 +374,21 @@
 	.tx_fixup = cdc_mbim_tx_fixup,
 };
 
+/* MBIM and NCM devices should not need a ZLP after NTBs with
+ * dwNtbOutMaxSize length. This driver_info is for the exceptional
+ * devices requiring it anyway, allowing them to be supported without
+ * forcing the performance penalty on all the sane devices.
+ */
+static const struct driver_info cdc_mbim_info_zlp = {
+	.description = "CDC MBIM",
+	.flags = FLAG_NO_SETINT | FLAG_MULTI_PACKET | FLAG_WWAN | FLAG_SEND_ZLP,
+	.bind = cdc_mbim_bind,
+	.unbind = cdc_mbim_unbind,
+	.manage_power = cdc_mbim_manage_power,
+	.rx_fixup = cdc_mbim_rx_fixup,
+	.tx_fixup = cdc_mbim_tx_fixup,
+};
+
 static const struct usb_device_id mbim_devs[] = {
 	/* This duplicate NCM entry is intentional. MBIM devices can
 	 * be disguised as NCM by default, and this is necessary to
@@ -385,6 +400,10 @@
 	{ USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_NCM, USB_CDC_PROTO_NONE),
 	  .driver_info = (unsigned long)&cdc_mbim_info,
 	},
+	/* Sierra Wireless MC7710 need ZLPs */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x68a2, USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE),
+	  .driver_info = (unsigned long)&cdc_mbim_info_zlp,
+	},
 	{ USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE),
 	  .driver_info = (unsigned long)&cdc_mbim_info,
 	},
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 71b6e92..00d3b2d 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -435,6 +435,13 @@
 		len -= temp;
 	}
 
+	/* some buggy devices have an IAD but no CDC Union */
+	if (!ctx->union_desc && intf->intf_assoc && intf->intf_assoc->bInterfaceCount == 2) {
+		ctx->control = intf;
+		ctx->data = usb_ifnum_to_if(dev->udev, intf->cur_altsetting->desc.bInterfaceNumber + 1);
+		dev_dbg(&intf->dev, "CDC Union missing - got slave from IAD\n");
+	}
+
 	/* check if we got everything */
 	if ((ctx->control == NULL) || (ctx->data == NULL) ||
 	    ((!ctx->mbim_desc) && ((ctx->ether_desc == NULL) || (ctx->control != intf))))
@@ -497,7 +504,8 @@
 error2:
 	usb_set_intfdata(ctx->control, NULL);
 	usb_set_intfdata(ctx->data, NULL);
-	usb_driver_release_interface(driver, ctx->data);
+	if (ctx->data != ctx->control)
+		usb_driver_release_interface(driver, ctx->data);
 error:
 	cdc_ncm_free((struct cdc_ncm_ctx *)dev->data[0]);
 	dev->data[0] = 0;
@@ -1155,6 +1163,20 @@
 	.tx_fixup = cdc_ncm_tx_fixup,
 };
 
+/* Same as wwan_info, but with FLAG_NOARP  */
+static const struct driver_info wwan_noarp_info = {
+	.description = "Mobile Broadband Network Device (NO ARP)",
+	.flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET
+			| FLAG_WWAN | FLAG_NOARP,
+	.bind = cdc_ncm_bind,
+	.unbind = cdc_ncm_unbind,
+	.check_connect = cdc_ncm_check_connect,
+	.manage_power = usbnet_manage_power,
+	.status = cdc_ncm_status,
+	.rx_fixup = cdc_ncm_rx_fixup,
+	.tx_fixup = cdc_ncm_tx_fixup,
+};
+
 static const struct usb_device_id cdc_devs[] = {
 	/* Ericsson MBM devices like F5521gw */
 	{ .match_flags = USB_DEVICE_ID_MATCH_INT_INFO
@@ -1193,6 +1215,16 @@
 	{ USB_VENDOR_AND_INTERFACE_INFO(0x12d1, 0xff, 0x02, 0x46),
 	  .driver_info = (unsigned long)&wwan_info,
 	},
+	{ USB_VENDOR_AND_INTERFACE_INFO(0x12d1, 0xff, 0x02, 0x76),
+	  .driver_info = (unsigned long)&wwan_info,
+	},
+
+	/* Infineon(now Intel) HSPA Modem platform */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x1519, 0x0443,
+		USB_CLASS_COMM,
+		USB_CDC_SUBCLASS_NCM, USB_CDC_PROTO_NONE),
+	  .driver_info = (unsigned long)&wwan_noarp_info,
+	},
 
 	/* Generic CDC-NCM devices */
 	{ USB_INTERFACE_INFO(USB_CLASS_COMM,
diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c
index 3f554c1..d7e9944 100644
--- a/drivers/net/usb/dm9601.c
+++ b/drivers/net/usb/dm9601.c
@@ -45,6 +45,12 @@
 #define DM_MCAST_ADDR	0x16	/* 8 bytes */
 #define DM_GPR_CTRL	0x1e
 #define DM_GPR_DATA	0x1f
+#define DM_CHIP_ID	0x2c
+#define DM_MODE_CTRL	0x91	/* only on dm9620 */
+
+/* chip id values */
+#define ID_DM9601	0
+#define ID_DM9620	1
 
 #define DM_MAX_MCAST	64
 #define DM_MCAST_SIZE	8
@@ -53,7 +59,6 @@
 #define DM_RX_OVERHEAD	7	/* 3 byte header + 4 byte crc tail */
 #define DM_TIMEOUT	1000
 
-
 static int dm_read(struct usbnet *dev, u8 reg, u16 length, void *data)
 {
 	int err;
@@ -84,32 +89,23 @@
 
 static int dm_write_reg(struct usbnet *dev, u8 reg, u8 value)
 {
-	return usbnet_write_cmd(dev, DM_WRITE_REGS,
+	return usbnet_write_cmd(dev, DM_WRITE_REG,
 				USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
 				value, reg, NULL, 0);
 }
 
-static void dm_write_async_helper(struct usbnet *dev, u8 reg, u8 value,
-				  u16 length, void *data)
+static void dm_write_async(struct usbnet *dev, u8 reg, u16 length, void *data)
 {
 	usbnet_write_cmd_async(dev, DM_WRITE_REGS,
 			       USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
-			       value, reg, data, length);
-}
-
-static void dm_write_async(struct usbnet *dev, u8 reg, u16 length, void *data)
-{
-	netdev_dbg(dev->net, "dm_write_async() reg=0x%02x length=%d\n", reg, length);
-
-	dm_write_async_helper(dev, reg, 0, length, data);
+			       0, reg, data, length);
 }
 
 static void dm_write_reg_async(struct usbnet *dev, u8 reg, u8 value)
 {
-	netdev_dbg(dev->net, "dm_write_reg_async() reg=0x%02x value=0x%02x\n",
-		   reg, value);
-
-	dm_write_async_helper(dev, reg, value, 0, NULL);
+	usbnet_write_cmd_async(dev, DM_WRITE_REG,
+			       USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
+			       value, reg, NULL, 0);
 }
 
 static int dm_read_shared_word(struct usbnet *dev, int phy, u8 reg, __le16 *value)
@@ -358,7 +354,7 @@
 static int dm9601_bind(struct usbnet *dev, struct usb_interface *intf)
 {
 	int ret;
-	u8 mac[ETH_ALEN];
+	u8 mac[ETH_ALEN], id;
 
 	ret = usbnet_get_endpoints(dev, intf);
 	if (ret)
@@ -399,6 +395,24 @@
 		__dm9601_set_mac_address(dev);
 	}
 
+	if (dm_read_reg(dev, DM_CHIP_ID, &id) < 0) {
+		netdev_err(dev->net, "Error reading chip ID\n");
+		ret = -ENODEV;
+		goto out;
+	}
+
+	/* put dm9620 devices in dm9601 mode */
+	if (id == ID_DM9620) {
+		u8 mode;
+
+		if (dm_read_reg(dev, DM_MODE_CTRL, &mode) < 0) {
+			netdev_err(dev->net, "Error reading MODE_CTRL\n");
+			ret = -ENODEV;
+			goto out;
+		}
+		dm_write_reg(dev, DM_MODE_CTRL, mode & 0x7f);
+	}
+
 	/* power up phy */
 	dm_write_reg(dev, DM_GPR_CTRL, 1);
 	dm_write_reg(dev, DM_GPR_DATA, 0);
@@ -581,6 +595,10 @@
 	 USB_DEVICE(0x0a46, 0x9000),	/* DM9000E */
 	 .driver_info = (unsigned long)&dm9601_info,
 	 },
+	{
+	 USB_DEVICE(0x0a46, 0x9620),	/* DM9620 USB to Fast Ethernet Adapter */
+	 .driver_info = (unsigned long)&dm9601_info,
+	 },
 	{},			// END
 };
 
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 6a1ca50..19d9035 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -351,6 +351,10 @@
 		USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, USB_CLASS_VENDOR_SPEC, 1, 57),
 		.driver_info        = (unsigned long)&qmi_wwan_info,
 	},
+	{	/* HUAWEI_INTERFACE_NDIS_CONTROL_QUALCOMM */
+		USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, USB_CLASS_VENDOR_SPEC, 0x01, 0x69),
+		.driver_info        = (unsigned long)&qmi_wwan_info,
+	},
 
 	/* 2. Combined interface devices matching on class+protocol */
 	{	/* Huawei E367 and possibly others in "Windows mode" */
@@ -361,6 +365,14 @@
 		USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, USB_CLASS_VENDOR_SPEC, 1, 17),
 		.driver_info        = (unsigned long)&qmi_wwan_info,
 	},
+	{	/* HUAWEI_NDIS_SINGLE_INTERFACE_VDF */
+		USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, USB_CLASS_VENDOR_SPEC, 0x01, 0x37),
+		.driver_info        = (unsigned long)&qmi_wwan_info,
+	},
+	{	/* HUAWEI_INTERFACE_NDIS_HW_QUALCOMM */
+		USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, USB_CLASS_VENDOR_SPEC, 0x01, 0x67),
+		.driver_info        = (unsigned long)&qmi_wwan_info,
+	},
 	{	/* Pantech UML290, P4200 and more */
 		USB_VENDOR_AND_INTERFACE_INFO(0x106c, USB_CLASS_VENDOR_SPEC, 0xf0, 0xff),
 		.driver_info        = (unsigned long)&qmi_wwan_info,
@@ -399,6 +411,7 @@
 	},
 
 	/* 3. Combined interface devices matching on interface number */
+	{QMI_FIXED_INTF(0x0408, 0xea42, 4)},	/* Yota / Megafon M100-1 */
 	{QMI_FIXED_INTF(0x12d1, 0x140c, 1)},	/* Huawei E173 */
 	{QMI_FIXED_INTF(0x19d2, 0x0002, 1)},
 	{QMI_FIXED_INTF(0x19d2, 0x0012, 1)},
@@ -433,6 +446,7 @@
 	{QMI_FIXED_INTF(0x19d2, 0x0199, 1)},	/* ZTE MF820S */
 	{QMI_FIXED_INTF(0x19d2, 0x0200, 1)},
 	{QMI_FIXED_INTF(0x19d2, 0x0257, 3)},	/* ZTE MF821 */
+	{QMI_FIXED_INTF(0x19d2, 0x0265, 4)},	/* ONDA MT8205 4G LTE */
 	{QMI_FIXED_INTF(0x19d2, 0x0284, 4)},	/* ZTE MF880 */
 	{QMI_FIXED_INTF(0x19d2, 0x0326, 4)},	/* ZTE MF821D */
 	{QMI_FIXED_INTF(0x19d2, 0x1008, 4)},	/* ZTE (Vodafone) K3570-Z */
@@ -459,6 +473,8 @@
 	{QMI_FIXED_INTF(0x1199, 0x68a2, 19)},	/* Sierra Wireless MC7710 in QMI mode */
 	{QMI_FIXED_INTF(0x1199, 0x901c, 8)},    /* Sierra Wireless EM7700 */
 	{QMI_FIXED_INTF(0x1bbb, 0x011e, 4)},	/* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */
+	{QMI_FIXED_INTF(0x2357, 0x0201, 4)},	/* TP-LINK HSUPA Modem MA180 */
+	{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)},	/* Telit LE920 */
 
 	/* 4. Gobi 1000 devices */
 	{QMI_GOBI1K_DEVICE(0x05c6, 0x9212)},	/* Acer Gobi Modem Device */
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 3d4bf01..5e33606 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -380,6 +380,12 @@
 	unsigned long		lockflags;
 	size_t			size = dev->rx_urb_size;
 
+	/* prevent rx skb allocation when error ratio is high */
+	if (test_bit(EVENT_RX_KILL, &dev->flags)) {
+		usb_free_urb(urb);
+		return -ENOLINK;
+	}
+
 	skb = __netdev_alloc_skb_ip_align(dev->net, size, flags);
 	if (!skb) {
 		netif_dbg(dev, rx_err, dev->net, "no rx skb\n");
@@ -539,6 +545,17 @@
 		break;
 	}
 
+	/* stop rx if packet error rate is high */
+	if (++dev->pkt_cnt > 30) {
+		dev->pkt_cnt = 0;
+		dev->pkt_err = 0;
+	} else {
+		if (state == rx_cleanup)
+			dev->pkt_err++;
+		if (dev->pkt_err > 20)
+			set_bit(EVENT_RX_KILL, &dev->flags);
+	}
+
 	state = defer_bh(dev, skb, &dev->rxq, state);
 
 	if (urb) {
@@ -791,6 +808,11 @@
 		   (dev->driver_info->flags & FLAG_FRAMING_AX) ? "ASIX" :
 		   "simple");
 
+	/* reset rx error state */
+	dev->pkt_cnt = 0;
+	dev->pkt_err = 0;
+	clear_bit(EVENT_RX_KILL, &dev->flags);
+
 	// delay posting reads until we're fully open
 	tasklet_schedule (&dev->bh);
 	if (info->manage_power) {
@@ -1103,13 +1125,11 @@
 	if (info->tx_fixup) {
 		skb = info->tx_fixup (dev, skb, GFP_ATOMIC);
 		if (!skb) {
-			if (netif_msg_tx_err(dev)) {
-				netif_dbg(dev, tx_err, dev->net, "can't tx_fixup skb\n");
-				goto drop;
-			} else {
-				/* cdc_ncm collected packet; waits for more */
+			/* packet collected; minidriver waiting for more */
+			if (info->flags & FLAG_MULTI_PACKET)
 				goto not_drop;
-			}
+			netif_dbg(dev, tx_err, dev->net, "can't tx_fixup skb\n");
+			goto drop;
 		}
 	}
 	length = skb->len;
@@ -1254,6 +1274,9 @@
 		}
 	}
 
+	/* restart RX again after disabling due to high error rate */
+	clear_bit(EVENT_RX_KILL, &dev->flags);
+
 	// waiting for all pending urbs to complete?
 	if (dev->wait) {
 		if ((dev->txq.qlen + dev->rxq.qlen + dev->done.qlen) == 0) {
@@ -1448,6 +1471,10 @@
 		if ((dev->driver_info->flags & FLAG_WWAN) != 0)
 			strcpy(net->name, "wwan%d");
 
+		/* devices that cannot do ARP */
+		if ((dev->driver_info->flags & FLAG_NOARP) != 0)
+			net->flags |= IFF_NOARP;
+
 		/* maybe the remote can't receive an Ethernet MTU */
 		if (net->mtu > (dev->hard_mtu - net->hard_header_len))
 			net->mtu = dev->hard_mtu - net->hard_header_len;
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index a6fcf15..35c00c5 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -26,6 +26,7 @@
 #include <linux/scatterlist.h>
 #include <linux/if_vlan.h>
 #include <linux/slab.h>
+#include <linux/cpu.h>
 
 static int napi_weight = 128;
 module_param(napi_weight, int, 0444);
@@ -123,6 +124,12 @@
 
 	/* Does the affinity hint is set for virtqueues? */
 	bool affinity_hint_set;
+
+	/* Per-cpu variable to show the mapping from CPU to virtqueue */
+	int __percpu *vq_index;
+
+	/* CPU hot plug notifier */
+	struct notifier_block nb;
 };
 
 struct skb_vnet_hdr {
@@ -1013,32 +1020,75 @@
 	return 0;
 }
 
-static void virtnet_set_affinity(struct virtnet_info *vi, bool set)
+static void virtnet_clean_affinity(struct virtnet_info *vi, long hcpu)
 {
 	int i;
+	int cpu;
+
+	if (vi->affinity_hint_set) {
+		for (i = 0; i < vi->max_queue_pairs; i++) {
+			virtqueue_set_affinity(vi->rq[i].vq, -1);
+			virtqueue_set_affinity(vi->sq[i].vq, -1);
+		}
+
+		vi->affinity_hint_set = false;
+	}
+
+	i = 0;
+	for_each_online_cpu(cpu) {
+		if (cpu == hcpu) {
+			*per_cpu_ptr(vi->vq_index, cpu) = -1;
+		} else {
+			*per_cpu_ptr(vi->vq_index, cpu) =
+				++i % vi->curr_queue_pairs;
+		}
+	}
+}
+
+static void virtnet_set_affinity(struct virtnet_info *vi)
+{
+	int i;
+	int cpu;
 
 	/* In multiqueue mode, when the number of cpu is equal to the number of
 	 * queue pairs, we let the queue pairs to be private to one cpu by
 	 * setting the affinity hint to eliminate the contention.
 	 */
-	if ((vi->curr_queue_pairs == 1 ||
-	     vi->max_queue_pairs != num_online_cpus()) && set) {
-		if (vi->affinity_hint_set)
-			set = false;
-		else
-			return;
+	if (vi->curr_queue_pairs == 1 ||
+	    vi->max_queue_pairs != num_online_cpus()) {
+		virtnet_clean_affinity(vi, -1);
+		return;
 	}
 
-	for (i = 0; i < vi->max_queue_pairs; i++) {
-		int cpu = set ? i : -1;
+	i = 0;
+	for_each_online_cpu(cpu) {
 		virtqueue_set_affinity(vi->rq[i].vq, cpu);
 		virtqueue_set_affinity(vi->sq[i].vq, cpu);
+		*per_cpu_ptr(vi->vq_index, cpu) = i;
+		i++;
 	}
 
-	if (set)
-		vi->affinity_hint_set = true;
-	else
-		vi->affinity_hint_set = false;
+	vi->affinity_hint_set = true;
+}
+
+static int virtnet_cpu_callback(struct notifier_block *nfb,
+			        unsigned long action, void *hcpu)
+{
+	struct virtnet_info *vi = container_of(nfb, struct virtnet_info, nb);
+
+	switch(action & ~CPU_TASKS_FROZEN) {
+	case CPU_ONLINE:
+	case CPU_DOWN_FAILED:
+	case CPU_DEAD:
+		virtnet_set_affinity(vi);
+		break;
+	case CPU_DOWN_PREPARE:
+		virtnet_clean_affinity(vi, (long)hcpu);
+		break;
+	default:
+		break;
+	}
+	return NOTIFY_OK;
 }
 
 static void virtnet_get_ringparam(struct net_device *dev,
@@ -1082,13 +1132,15 @@
 	if (queue_pairs > vi->max_queue_pairs)
 		return -EINVAL;
 
+	get_online_cpus();
 	err = virtnet_set_queues(vi, queue_pairs);
 	if (!err) {
 		netif_set_real_num_tx_queues(dev, queue_pairs);
 		netif_set_real_num_rx_queues(dev, queue_pairs);
 
-		virtnet_set_affinity(vi, true);
+		virtnet_set_affinity(vi);
 	}
+	put_online_cpus();
 
 	return err;
 }
@@ -1127,12 +1179,19 @@
 
 /* To avoid contending a lock hold by a vcpu who would exit to host, select the
  * txq based on the processor id.
- * TODO: handle cpu hotplug.
  */
 static u16 virtnet_select_queue(struct net_device *dev, struct sk_buff *skb)
 {
-	int txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) :
-		  smp_processor_id();
+	int txq;
+	struct virtnet_info *vi = netdev_priv(dev);
+
+	if (skb_rx_queue_recorded(skb)) {
+		txq = skb_get_rx_queue(skb);
+	} else {
+		txq = *__this_cpu_ptr(vi->vq_index);
+		if (txq == -1)
+			txq = 0;
+	}
 
 	while (unlikely(txq >= dev->real_num_tx_queues))
 		txq -= dev->real_num_tx_queues;
@@ -1248,7 +1307,7 @@
 {
 	struct virtio_device *vdev = vi->vdev;
 
-	virtnet_set_affinity(vi, false);
+	virtnet_clean_affinity(vi, -1);
 
 	vdev->config->del_vqs(vdev);
 
@@ -1371,7 +1430,10 @@
 	if (ret)
 		goto err_free;
 
-	virtnet_set_affinity(vi, true);
+	get_online_cpus();
+	virtnet_set_affinity(vi);
+	put_online_cpus();
+
 	return 0;
 
 err_free:
@@ -1453,6 +1515,10 @@
 	if (vi->stats == NULL)
 		goto free;
 
+	vi->vq_index = alloc_percpu(int);
+	if (vi->vq_index == NULL)
+		goto free_stats;
+
 	mutex_init(&vi->config_lock);
 	vi->config_enable = true;
 	INIT_WORK(&vi->config_work, virtnet_config_changed_work);
@@ -1476,7 +1542,7 @@
 	/* Allocate/initialize the rx/tx queues, and invoke find_vqs */
 	err = init_vqs(vi);
 	if (err)
-		goto free_stats;
+		goto free_index;
 
 	netif_set_real_num_tx_queues(dev, 1);
 	netif_set_real_num_rx_queues(dev, 1);
@@ -1499,6 +1565,13 @@
 		}
 	}
 
+	vi->nb.notifier_call = &virtnet_cpu_callback;
+	err = register_hotcpu_notifier(&vi->nb);
+	if (err) {
+		pr_debug("virtio_net: registering cpu notifier failed\n");
+		goto free_recv_bufs;
+	}
+
 	/* Assume link up if device can't report link status,
 	   otherwise get link status from config. */
 	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_STATUS)) {
@@ -1520,6 +1593,8 @@
 free_vqs:
 	cancel_delayed_work_sync(&vi->refill);
 	virtnet_del_vqs(vi);
+free_index:
+	free_percpu(vi->vq_index);
 free_stats:
 	free_percpu(vi->stats);
 free:
@@ -1543,6 +1618,8 @@
 {
 	struct virtnet_info *vi = vdev->priv;
 
+	unregister_hotcpu_notifier(&vi->nb);
+
 	/* Prevent config work handler from accessing the device. */
 	mutex_lock(&vi->config_lock);
 	vi->config_enable = false;
@@ -1554,6 +1631,7 @@
 
 	flush_work(&vi->config_work);
 
+	free_percpu(vi->vq_index);
 	free_percpu(vi->stats);
 	free_netdev(vi->dev);
 }
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index dc8913c..12c6440 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -154,8 +154,7 @@
 	if (ret & 1) { /* Link is up. */
 		printk(KERN_INFO "%s: NIC Link is Up %d Mbps\n",
 		       adapter->netdev->name, adapter->link_speed);
-		if (!netif_carrier_ok(adapter->netdev))
-			netif_carrier_on(adapter->netdev);
+		netif_carrier_on(adapter->netdev);
 
 		if (affectTxQueue) {
 			for (i = 0; i < adapter->num_tx_queues; i++)
@@ -165,8 +164,7 @@
 	} else {
 		printk(KERN_INFO "%s: NIC Link is Down\n",
 		       adapter->netdev->name);
-		if (netif_carrier_ok(adapter->netdev))
-			netif_carrier_off(adapter->netdev);
+		netif_carrier_off(adapter->netdev);
 
 		if (affectTxQueue) {
 			for (i = 0; i < adapter->num_tx_queues; i++)
@@ -3061,6 +3059,7 @@
 	netif_set_real_num_tx_queues(adapter->netdev, adapter->num_tx_queues);
 	netif_set_real_num_rx_queues(adapter->netdev, adapter->num_rx_queues);
 
+	netif_carrier_off(netdev);
 	err = register_netdev(netdev);
 
 	if (err) {
diff --git a/drivers/net/wireless/ath/ath9k/ar9003_calib.c b/drivers/net/wireless/ath/ath9k/ar9003_calib.c
index 8b0d8dc..56317b0 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_calib.c
+++ b/drivers/net/wireless/ath/ath9k/ar9003_calib.c
@@ -976,6 +976,8 @@
 					  AR_PHY_CL_TAB_1,
 					  AR_PHY_CL_TAB_2 };
 
+	ar9003_hw_set_chain_masks(ah, ah->caps.rx_chainmask, ah->caps.tx_chainmask);
+
 	if (rtt) {
 		if (!ar9003_hw_rtt_restore(ah, chan))
 			run_rtt_cal = true;
diff --git a/drivers/net/wireless/ath/ath9k/ar9003_phy.c b/drivers/net/wireless/ath/ath9k/ar9003_phy.c
index ce19c09..3afc24b 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_phy.c
+++ b/drivers/net/wireless/ath/ath9k/ar9003_phy.c
@@ -586,32 +586,19 @@
 	ath9k_hw_synth_delay(ah, chan, synthDelay);
 }
 
-static void ar9003_hw_set_chain_masks(struct ath_hw *ah, u8 rx, u8 tx)
+void ar9003_hw_set_chain_masks(struct ath_hw *ah, u8 rx, u8 tx)
 {
-	switch (rx) {
-	case 0x5:
+	if (ah->caps.tx_chainmask == 5 || ah->caps.rx_chainmask == 5)
 		REG_SET_BIT(ah, AR_PHY_ANALOG_SWAP,
 			    AR_PHY_SWAP_ALT_CHAIN);
-	case 0x3:
-	case 0x1:
-	case 0x2:
-	case 0x7:
-		REG_WRITE(ah, AR_PHY_RX_CHAINMASK, rx);
-		REG_WRITE(ah, AR_PHY_CAL_CHAINMASK, rx);
-		break;
-	default:
-		break;
-	}
+
+	REG_WRITE(ah, AR_PHY_RX_CHAINMASK, rx);
+	REG_WRITE(ah, AR_PHY_CAL_CHAINMASK, rx);
 
 	if ((ah->caps.hw_caps & ATH9K_HW_CAP_APM) && (tx == 0x7))
-		REG_WRITE(ah, AR_SELFGEN_MASK, 0x3);
-	else
-		REG_WRITE(ah, AR_SELFGEN_MASK, tx);
+		tx = 3;
 
-	if (tx == 0x5) {
-		REG_SET_BIT(ah, AR_PHY_ANALOG_SWAP,
-			    AR_PHY_SWAP_ALT_CHAIN);
-	}
+	REG_WRITE(ah, AR_SELFGEN_MASK, tx);
 }
 
 /*
diff --git a/drivers/net/wireless/ath/ath9k/ath9k.h b/drivers/net/wireless/ath/ath9k/ath9k.h
index 86e26a1..42794c5 100644
--- a/drivers/net/wireless/ath/ath9k/ath9k.h
+++ b/drivers/net/wireless/ath/ath9k/ath9k.h
@@ -317,7 +317,6 @@
 	u32 *rxlink;
 	u32 num_pkts;
 	unsigned int rxfilter;
-	spinlock_t rxbuflock;
 	struct list_head rxbuf;
 	struct ath_descdma rxdma;
 	struct ath_buf *rx_bufptr;
@@ -328,7 +327,6 @@
 
 int ath_startrecv(struct ath_softc *sc);
 bool ath_stoprecv(struct ath_softc *sc);
-void ath_flushrecv(struct ath_softc *sc);
 u32 ath_calcrxfilter(struct ath_softc *sc);
 int ath_rx_init(struct ath_softc *sc, int nbufs);
 void ath_rx_cleanup(struct ath_softc *sc);
@@ -646,7 +644,6 @@
 enum sc_op_flags {
 	SC_OP_INVALID,
 	SC_OP_BEACONS,
-	SC_OP_RXFLUSH,
 	SC_OP_ANI_RUN,
 	SC_OP_PRIM_STA_VIF,
 	SC_OP_HW_RESET,
diff --git a/drivers/net/wireless/ath/ath9k/beacon.c b/drivers/net/wireless/ath/ath9k/beacon.c
index 531fffd..2ca355e 100644
--- a/drivers/net/wireless/ath/ath9k/beacon.c
+++ b/drivers/net/wireless/ath/ath9k/beacon.c
@@ -147,6 +147,7 @@
 				 skb->len, DMA_TO_DEVICE);
 		dev_kfree_skb_any(skb);
 		bf->bf_buf_addr = 0;
+		bf->bf_mpdu = NULL;
 	}
 
 	skb = ieee80211_beacon_get(hw, vif);
@@ -359,7 +360,6 @@
 		return;
 
 	bf = ath9k_beacon_generate(sc->hw, vif);
-	WARN_ON(!bf);
 
 	if (sc->beacon.bmisscnt != 0) {
 		ath_dbg(common, BSTUCK, "resume beacon xmit after %u misses\n",
diff --git a/drivers/net/wireless/ath/ath9k/debug.c b/drivers/net/wireless/ath/ath9k/debug.c
index 13ff9ed..e585fc8 100644
--- a/drivers/net/wireless/ath/ath9k/debug.c
+++ b/drivers/net/wireless/ath/ath9k/debug.c
@@ -861,7 +861,6 @@
 	RXS_ERR("RX-LENGTH-ERR", rx_len_err);
 	RXS_ERR("RX-OOM-ERR", rx_oom_err);
 	RXS_ERR("RX-RATE-ERR", rx_rate_err);
-	RXS_ERR("RX-DROP-RXFLUSH", rx_drop_rxflush);
 	RXS_ERR("RX-TOO-MANY-FRAGS", rx_too_many_frags_err);
 
 	PHY_ERR("UNDERRUN ERR", ATH9K_PHYERR_UNDERRUN);
diff --git a/drivers/net/wireless/ath/ath9k/debug.h b/drivers/net/wireless/ath/ath9k/debug.h
index 375c3b4..6df2ab6 100644
--- a/drivers/net/wireless/ath/ath9k/debug.h
+++ b/drivers/net/wireless/ath/ath9k/debug.h
@@ -216,7 +216,6 @@
  * @rx_oom_err:  No. of frames dropped due to OOM issues.
  * @rx_rate_err:  No. of frames dropped due to rate errors.
  * @rx_too_many_frags_err:  Frames dropped due to too-many-frags received.
- * @rx_drop_rxflush: No. of frames dropped due to RX-FLUSH.
  * @rx_beacons:  No. of beacons received.
  * @rx_frags:  No. of rx-fragements received.
  */
@@ -235,7 +234,6 @@
 	u32 rx_oom_err;
 	u32 rx_rate_err;
 	u32 rx_too_many_frags_err;
-	u32 rx_drop_rxflush;
 	u32 rx_beacons;
 	u32 rx_frags;
 };
diff --git a/drivers/net/wireless/ath/ath9k/htc_hst.c b/drivers/net/wireless/ath/ath9k/htc_hst.c
index 4a9570d..aac4a40 100644
--- a/drivers/net/wireless/ath/ath9k/htc_hst.c
+++ b/drivers/net/wireless/ath/ath9k/htc_hst.c
@@ -344,6 +344,8 @@
 			endpoint->ep_callbacks.tx(endpoint->ep_callbacks.priv,
 						  skb, htc_hdr->endpoint_id,
 						  txok);
+		} else {
+			kfree_skb(skb);
 		}
 	}
 
diff --git a/drivers/net/wireless/ath/ath9k/hw.h b/drivers/net/wireless/ath/ath9k/hw.h
index 7f1a8e9..9d26fc5 100644
--- a/drivers/net/wireless/ath/ath9k/hw.h
+++ b/drivers/net/wireless/ath/ath9k/hw.h
@@ -1066,6 +1066,7 @@
 int ar9003_paprd_init_table(struct ath_hw *ah);
 bool ar9003_paprd_is_done(struct ath_hw *ah);
 bool ar9003_is_paprd_enabled(struct ath_hw *ah);
+void ar9003_hw_set_chain_masks(struct ath_hw *ah, u8 rx, u8 tx);
 
 /* Hardware family op attach helpers */
 void ar5008_hw_attach_phy_ops(struct ath_hw *ah);
diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c
index be30a9a..dd91f8f 100644
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -182,7 +182,7 @@
 	ath_start_ani(sc);
 }
 
-static bool ath_prepare_reset(struct ath_softc *sc, bool retry_tx, bool flush)
+static bool ath_prepare_reset(struct ath_softc *sc, bool retry_tx)
 {
 	struct ath_hw *ah = sc->sc_ah;
 	bool ret = true;
@@ -202,14 +202,6 @@
 	if (!ath_drain_all_txq(sc, retry_tx))
 		ret = false;
 
-	if (!flush) {
-		if (ah->caps.hw_caps & ATH9K_HW_CAP_EDMA)
-			ath_rx_tasklet(sc, 1, true);
-		ath_rx_tasklet(sc, 1, false);
-	} else {
-		ath_flushrecv(sc);
-	}
-
 	return ret;
 }
 
@@ -262,11 +254,11 @@
 	struct ath_common *common = ath9k_hw_common(ah);
 	struct ath9k_hw_cal_data *caldata = NULL;
 	bool fastcc = true;
-	bool flush = false;
 	int r;
 
 	__ath_cancel_work(sc);
 
+	tasklet_disable(&sc->intr_tq);
 	spin_lock_bh(&sc->sc_pcu_lock);
 
 	if (!(sc->hw->conf.flags & IEEE80211_CONF_OFFCHANNEL)) {
@@ -276,11 +268,10 @@
 
 	if (!hchan) {
 		fastcc = false;
-		flush = true;
 		hchan = ah->curchan;
 	}
 
-	if (!ath_prepare_reset(sc, retry_tx, flush))
+	if (!ath_prepare_reset(sc, retry_tx))
 		fastcc = false;
 
 	ath_dbg(common, CONFIG, "Reset to %u MHz, HT40: %d fastcc: %d\n",
@@ -302,6 +293,8 @@
 
 out:
 	spin_unlock_bh(&sc->sc_pcu_lock);
+	tasklet_enable(&sc->intr_tq);
+
 	return r;
 }
 
@@ -804,7 +797,7 @@
 		ath9k_hw_cfg_gpio_input(ah, ah->led_pin);
 	}
 
-	ath_prepare_reset(sc, false, true);
+	ath_prepare_reset(sc, false);
 
 	if (sc->rx.frag) {
 		dev_kfree_skb_any(sc->rx.frag);
@@ -1833,6 +1826,9 @@
 
 static bool validate_antenna_mask(struct ath_hw *ah, u32 val)
 {
+	if (AR_SREV_9300_20_OR_LATER(ah))
+		return true;
+
 	switch (val & 0x7) {
 	case 0x1:
 	case 0x3:
diff --git a/drivers/net/wireless/ath/ath9k/recv.c b/drivers/net/wireless/ath/ath9k/recv.c
index d4df98a..90752f2 100644
--- a/drivers/net/wireless/ath/ath9k/recv.c
+++ b/drivers/net/wireless/ath/ath9k/recv.c
@@ -254,8 +254,6 @@
 
 static void ath_edma_start_recv(struct ath_softc *sc)
 {
-	spin_lock_bh(&sc->rx.rxbuflock);
-
 	ath9k_hw_rxena(sc->sc_ah);
 
 	ath_rx_addbuffer_edma(sc, ATH9K_RX_QUEUE_HP,
@@ -267,8 +265,6 @@
 	ath_opmode_init(sc);
 
 	ath9k_hw_startpcureceive(sc->sc_ah, !!(sc->hw->conf.flags & IEEE80211_CONF_OFFCHANNEL));
-
-	spin_unlock_bh(&sc->rx.rxbuflock);
 }
 
 static void ath_edma_stop_recv(struct ath_softc *sc)
@@ -285,8 +281,6 @@
 	int error = 0;
 
 	spin_lock_init(&sc->sc_pcu_lock);
-	spin_lock_init(&sc->rx.rxbuflock);
-	clear_bit(SC_OP_RXFLUSH, &sc->sc_flags);
 
 	common->rx_bufsize = IEEE80211_MAX_MPDU_LEN / 2 +
 			     sc->sc_ah->caps.rx_status_len;
@@ -447,7 +441,6 @@
 		return 0;
 	}
 
-	spin_lock_bh(&sc->rx.rxbuflock);
 	if (list_empty(&sc->rx.rxbuf))
 		goto start_recv;
 
@@ -468,26 +461,31 @@
 	ath_opmode_init(sc);
 	ath9k_hw_startpcureceive(ah, !!(sc->hw->conf.flags & IEEE80211_CONF_OFFCHANNEL));
 
-	spin_unlock_bh(&sc->rx.rxbuflock);
-
 	return 0;
 }
 
+static void ath_flushrecv(struct ath_softc *sc)
+{
+	if (sc->sc_ah->caps.hw_caps & ATH9K_HW_CAP_EDMA)
+		ath_rx_tasklet(sc, 1, true);
+	ath_rx_tasklet(sc, 1, false);
+}
+
 bool ath_stoprecv(struct ath_softc *sc)
 {
 	struct ath_hw *ah = sc->sc_ah;
 	bool stopped, reset = false;
 
-	spin_lock_bh(&sc->rx.rxbuflock);
 	ath9k_hw_abortpcurecv(ah);
 	ath9k_hw_setrxfilter(ah, 0);
 	stopped = ath9k_hw_stopdmarecv(ah, &reset);
 
+	ath_flushrecv(sc);
+
 	if (sc->sc_ah->caps.hw_caps & ATH9K_HW_CAP_EDMA)
 		ath_edma_stop_recv(sc);
 	else
 		sc->rx.rxlink = NULL;
-	spin_unlock_bh(&sc->rx.rxbuflock);
 
 	if (!(ah->ah_flags & AH_UNPLUGGED) &&
 	    unlikely(!stopped)) {
@@ -499,15 +497,6 @@
 	return stopped && !reset;
 }
 
-void ath_flushrecv(struct ath_softc *sc)
-{
-	set_bit(SC_OP_RXFLUSH, &sc->sc_flags);
-	if (sc->sc_ah->caps.hw_caps & ATH9K_HW_CAP_EDMA)
-		ath_rx_tasklet(sc, 1, true);
-	ath_rx_tasklet(sc, 1, false);
-	clear_bit(SC_OP_RXFLUSH, &sc->sc_flags);
-}
-
 static bool ath_beacon_dtim_pending_cab(struct sk_buff *skb)
 {
 	/* Check whether the Beacon frame has DTIM indicating buffered bc/mc */
@@ -744,6 +733,7 @@
 			return NULL;
 	}
 
+	list_del(&bf->list);
 	if (!bf->bf_mpdu)
 		return bf;
 
@@ -1059,16 +1049,12 @@
 		dma_type = DMA_FROM_DEVICE;
 
 	qtype = hp ? ATH9K_RX_QUEUE_HP : ATH9K_RX_QUEUE_LP;
-	spin_lock_bh(&sc->rx.rxbuflock);
 
 	tsf = ath9k_hw_gettsf64(ah);
 	tsf_lower = tsf & 0xffffffff;
 
 	do {
 		bool decrypt_error = false;
-		/* If handling rx interrupt and flush is in progress => exit */
-		if (test_bit(SC_OP_RXFLUSH, &sc->sc_flags) && (flush == 0))
-			break;
 
 		memset(&rs, 0, sizeof(rs));
 		if (edma)
@@ -1111,15 +1097,6 @@
 
 		ath_debug_stat_rx(sc, &rs);
 
-		/*
-		 * If we're asked to flush receive queue, directly
-		 * chain it back at the queue without processing it.
-		 */
-		if (test_bit(SC_OP_RXFLUSH, &sc->sc_flags)) {
-			RX_STAT_INC(rx_drop_rxflush);
-			goto requeue_drop_frag;
-		}
-
 		memset(rxs, 0, sizeof(struct ieee80211_rx_status));
 
 		rxs->mactime = (tsf & ~0xffffffffULL) | rs.rs_tstamp;
@@ -1254,19 +1231,18 @@
 			sc->rx.frag = NULL;
 		}
 requeue:
+		list_add_tail(&bf->list, &sc->rx.rxbuf);
+		if (flush)
+			continue;
+
 		if (edma) {
-			list_add_tail(&bf->list, &sc->rx.rxbuf);
 			ath_rx_edma_buf_link(sc, qtype);
 		} else {
-			list_move_tail(&bf->list, &sc->rx.rxbuf);
 			ath_rx_buf_link(sc, bf);
-			if (!flush)
-				ath9k_hw_rxena(ah);
+			ath9k_hw_rxena(ah);
 		}
 	} while (1);
 
-	spin_unlock_bh(&sc->rx.rxbuflock);
-
 	if (!(ah->imask & ATH9K_INT_RXEOL)) {
 		ah->imask |= (ATH9K_INT_RXEOL | ATH9K_INT_RXORN);
 		ath9k_hw_set_interrupts(ah);
diff --git a/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c b/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c
index 1fbd8ec..e5fd209 100644
--- a/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c
+++ b/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c
@@ -36,6 +36,7 @@
 #include "debug.h"
 
 #define N_TX_QUEUES	4 /* #tx queues on mac80211<->driver interface */
+#define BRCMS_FLUSH_TIMEOUT	500 /* msec */
 
 /* Flags we support */
 #define MAC_FILTERS (FIF_PROMISC_IN_BSS | \
@@ -708,16 +709,29 @@
 	wiphy_rfkill_set_hw_state(wl->pub->ieee_hw->wiphy, blocked);
 }
 
+static bool brcms_tx_flush_completed(struct brcms_info *wl)
+{
+	bool result;
+
+	spin_lock_bh(&wl->lock);
+	result = brcms_c_tx_flush_completed(wl->wlc);
+	spin_unlock_bh(&wl->lock);
+	return result;
+}
+
 static void brcms_ops_flush(struct ieee80211_hw *hw, bool drop)
 {
 	struct brcms_info *wl = hw->priv;
+	int ret;
 
 	no_printk("%s: drop = %s\n", __func__, drop ? "true" : "false");
 
-	/* wait for packet queue and dma fifos to run empty */
-	spin_lock_bh(&wl->lock);
-	brcms_c_wait_for_tx_completion(wl->wlc, drop);
-	spin_unlock_bh(&wl->lock);
+	ret = wait_event_timeout(wl->tx_flush_wq,
+				 brcms_tx_flush_completed(wl),
+				 msecs_to_jiffies(BRCMS_FLUSH_TIMEOUT));
+
+	brcms_dbg_mac80211(wl->wlc->hw->d11core,
+			   "ret=%d\n", jiffies_to_msecs(ret));
 }
 
 static const struct ieee80211_ops brcms_ops = {
@@ -772,6 +786,7 @@
 
  done:
 	spin_unlock_bh(&wl->lock);
+	wake_up(&wl->tx_flush_wq);
 }
 
 /*
@@ -1020,6 +1035,8 @@
 
 	atomic_set(&wl->callbacks, 0);
 
+	init_waitqueue_head(&wl->tx_flush_wq);
+
 	/* setup the bottom half handler */
 	tasklet_init(&wl->tasklet, brcms_dpc, (unsigned long) wl);
 
@@ -1407,9 +1424,10 @@
 #endif
 	t->ms = ms;
 	t->periodic = (bool) periodic;
-	t->set = true;
-
-	atomic_inc(&t->wl->callbacks);
+	if (!t->set) {
+		t->set = true;
+		atomic_inc(&t->wl->callbacks);
+	}
 
 	ieee80211_queue_delayed_work(hw, &t->dly_wrk, msecs_to_jiffies(ms));
 }
@@ -1608,13 +1626,3 @@
 	spin_lock_bh(&wl->lock);
 	return blocked;
 }
-
-/*
- * precondition: perimeter lock has been acquired
- */
-void brcms_msleep(struct brcms_info *wl, uint ms)
-{
-	spin_unlock_bh(&wl->lock);
-	msleep(ms);
-	spin_lock_bh(&wl->lock);
-}
diff --git a/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.h b/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.h
index 9358bd5..947ccac 100644
--- a/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.h
+++ b/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.h
@@ -68,6 +68,8 @@
 	spinlock_t lock;	/* per-device perimeter lock */
 	spinlock_t isr_lock;	/* per-device ISR synchronization lock */
 
+	/* tx flush */
+	wait_queue_head_t tx_flush_wq;
 
 	/* timer related fields */
 	atomic_t callbacks;	/* # outstanding callback functions */
@@ -100,7 +102,6 @@
 extern void brcms_free_timer(struct brcms_timer *timer);
 extern void brcms_add_timer(struct brcms_timer *timer, uint ms, int periodic);
 extern bool brcms_del_timer(struct brcms_timer *timer);
-extern void brcms_msleep(struct brcms_info *wl, uint ms);
 extern void brcms_dpc(unsigned long data);
 extern void brcms_timer(struct brcms_timer *t);
 extern void brcms_fatal_error(struct brcms_info *wl);
diff --git a/drivers/net/wireless/brcm80211/brcmsmac/main.c b/drivers/net/wireless/brcm80211/brcmsmac/main.c
index 17594de..8b58390 100644
--- a/drivers/net/wireless/brcm80211/brcmsmac/main.c
+++ b/drivers/net/wireless/brcm80211/brcmsmac/main.c
@@ -1027,7 +1027,6 @@
 static bool
 brcms_b_txstatus(struct brcms_hardware *wlc_hw, bool bound, bool *fatal)
 {
-	bool morepending = false;
 	struct bcma_device *core;
 	struct tx_status txstatus, *txs;
 	u32 s1, s2;
@@ -1041,23 +1040,20 @@
 	txs = &txstatus;
 	core = wlc_hw->d11core;
 	*fatal = false;
-	s1 = bcma_read32(core, D11REGOFFS(frmtxstatus));
-	while (!(*fatal)
-	       && (s1 & TXS_V)) {
-		/* !give others some time to run! */
-		if (n >= max_tx_num) {
-			morepending = true;
-			break;
-		}
 
+	while (n < max_tx_num) {
+		s1 = bcma_read32(core, D11REGOFFS(frmtxstatus));
 		if (s1 == 0xffffffff) {
 			brcms_err(core, "wl%d: %s: dead chip\n", wlc_hw->unit,
 				  __func__);
 			*fatal = true;
 			return false;
 		}
-		s2 = bcma_read32(core, D11REGOFFS(frmtxstatus2));
+		/* only process when valid */
+		if (!(s1 & TXS_V))
+			break;
 
+		s2 = bcma_read32(core, D11REGOFFS(frmtxstatus2));
 		txs->status = s1 & TXS_STATUS_MASK;
 		txs->frameid = (s1 & TXS_FID_MASK) >> TXS_FID_SHIFT;
 		txs->sequence = s2 & TXS_SEQ_MASK;
@@ -1065,15 +1061,12 @@
 		txs->lasttxtime = 0;
 
 		*fatal = brcms_c_dotxstatus(wlc_hw->wlc, txs);
-
-		s1 = bcma_read32(core, D11REGOFFS(frmtxstatus));
+		if (*fatal == true)
+			return false;
 		n++;
 	}
 
-	if (*fatal)
-		return false;
-
-	return morepending;
+	return n >= max_tx_num;
 }
 
 static void brcms_c_tbtt(struct brcms_c_info *wlc)
@@ -7518,25 +7511,16 @@
 	return wlc->band->bandunit;
 }
 
-void brcms_c_wait_for_tx_completion(struct brcms_c_info *wlc, bool drop)
+bool brcms_c_tx_flush_completed(struct brcms_c_info *wlc)
 {
-	int timeout = 20;
 	int i;
 
 	/* Kick DMA to send any pending AMPDU */
 	for (i = 0; i < ARRAY_SIZE(wlc->hw->di); i++)
 		if (wlc->hw->di[i])
-			dma_txflush(wlc->hw->di[i]);
+			dma_kick_tx(wlc->hw->di[i]);
 
-	/* wait for queue and DMA fifos to run dry */
-	while (brcms_txpktpendtot(wlc) > 0) {
-		brcms_msleep(wlc->wl, 1);
-
-		if (--timeout == 0)
-			break;
-	}
-
-	WARN_ON_ONCE(timeout == 0);
+	return !brcms_txpktpendtot(wlc);
 }
 
 void brcms_c_set_beacon_listen_interval(struct brcms_c_info *wlc, u8 interval)
diff --git a/drivers/net/wireless/brcm80211/brcmsmac/pub.h b/drivers/net/wireless/brcm80211/brcmsmac/pub.h
index 4fb2834..b0f14b7 100644
--- a/drivers/net/wireless/brcm80211/brcmsmac/pub.h
+++ b/drivers/net/wireless/brcm80211/brcmsmac/pub.h
@@ -314,8 +314,6 @@
 extern void brcms_c_scan_start(struct brcms_c_info *wlc);
 extern void brcms_c_scan_stop(struct brcms_c_info *wlc);
 extern int brcms_c_get_curband(struct brcms_c_info *wlc);
-extern void brcms_c_wait_for_tx_completion(struct brcms_c_info *wlc,
-					   bool drop);
 extern int brcms_c_set_channel(struct brcms_c_info *wlc, u16 channel);
 extern int brcms_c_set_rate_limit(struct brcms_c_info *wlc, u16 srl, u16 lrl);
 extern void brcms_c_get_current_rateset(struct brcms_c_info *wlc,
@@ -332,5 +330,6 @@
 extern int brcms_c_get_tx_power(struct brcms_c_info *wlc);
 extern bool brcms_c_check_radio_disabled(struct brcms_c_info *wlc);
 extern void brcms_c_mute(struct brcms_c_info *wlc, bool on);
+extern bool brcms_c_tx_flush_completed(struct brcms_c_info *wlc);
 
 #endif				/* _BRCM_PUB_H_ */
diff --git a/drivers/net/wireless/iwlegacy/common.c b/drivers/net/wireless/iwlegacy/common.c
index 7e16d10..90b8970 100644
--- a/drivers/net/wireless/iwlegacy/common.c
+++ b/drivers/net/wireless/iwlegacy/common.c
@@ -3958,17 +3958,21 @@
 
 	memset(&il->staging, 0, sizeof(il->staging));
 
-	if (!il->vif) {
+	switch (il->iw_mode) {
+	case NL80211_IFTYPE_UNSPECIFIED:
 		il->staging.dev_type = RXON_DEV_TYPE_ESS;
-	} else if (il->vif->type == NL80211_IFTYPE_STATION) {
+		break;
+	case NL80211_IFTYPE_STATION:
 		il->staging.dev_type = RXON_DEV_TYPE_ESS;
 		il->staging.filter_flags = RXON_FILTER_ACCEPT_GRP_MSK;
-	} else if (il->vif->type == NL80211_IFTYPE_ADHOC) {
+		break;
+	case NL80211_IFTYPE_ADHOC:
 		il->staging.dev_type = RXON_DEV_TYPE_IBSS;
 		il->staging.flags = RXON_FLG_SHORT_PREAMBLE_MSK;
 		il->staging.filter_flags =
 		    RXON_FILTER_BCON_AWARE_MSK | RXON_FILTER_ACCEPT_GRP_MSK;
-	} else {
+		break;
+	default:
 		IL_ERR("Unsupported interface type %d\n", il->vif->type);
 		return;
 	}
@@ -4550,8 +4554,7 @@
 EXPORT_SYMBOL(il_mac_add_interface);
 
 static void
-il_teardown_interface(struct il_priv *il, struct ieee80211_vif *vif,
-		      bool mode_change)
+il_teardown_interface(struct il_priv *il, struct ieee80211_vif *vif)
 {
 	lockdep_assert_held(&il->mutex);
 
@@ -4560,9 +4563,7 @@
 		il_force_scan_end(il);
 	}
 
-	if (!mode_change)
-		il_set_mode(il);
-
+	il_set_mode(il);
 }
 
 void
@@ -4575,8 +4576,8 @@
 
 	WARN_ON(il->vif != vif);
 	il->vif = NULL;
-
-	il_teardown_interface(il, vif, false);
+	il->iw_mode = NL80211_IFTYPE_UNSPECIFIED;
+	il_teardown_interface(il, vif);
 	memset(il->bssid, 0, ETH_ALEN);
 
 	D_MAC80211("leave\n");
@@ -4685,18 +4686,10 @@
 	}
 
 	/* success */
-	il_teardown_interface(il, vif, true);
 	vif->type = newtype;
 	vif->p2p = false;
-	err = il_set_mode(il);
-	WARN_ON(err);
-	/*
-	 * We've switched internally, but submitting to the
-	 * device may have failed for some reason. Mask this
-	 * error, because otherwise mac80211 will not switch
-	 * (and set the interface type back) and we'll be
-	 * out of sync with it.
-	 */
+	il->iw_mode = newtype;
+	il_teardown_interface(il, vif);
 	err = 0;
 
 out:
diff --git a/drivers/net/wireless/iwlwifi/dvm/tx.c b/drivers/net/wireless/iwlwifi/dvm/tx.c
index a790599..2797964 100644
--- a/drivers/net/wireless/iwlwifi/dvm/tx.c
+++ b/drivers/net/wireless/iwlwifi/dvm/tx.c
@@ -1079,6 +1079,8 @@
 {
 	u16 status = le16_to_cpu(tx_resp->status.status);
 
+	info->flags &= ~IEEE80211_TX_CTL_AMPDU;
+
 	info->status.rates[0].count = tx_resp->failure_frame + 1;
 	info->flags |= iwl_tx_status_to_mac80211(status);
 	iwlagn_hwrate_to_tx_control(priv, le32_to_cpu(tx_resp->rate_n_flags),
@@ -1151,6 +1153,13 @@
 			next_reclaimed = ssn;
 		}
 
+		if (tid != IWL_TID_NON_QOS) {
+			priv->tid_data[sta_id][tid].next_reclaimed =
+				next_reclaimed;
+			IWL_DEBUG_TX_REPLY(priv, "Next reclaimed packet:%d\n",
+						  next_reclaimed);
+		}
+
 		iwl_trans_reclaim(priv->trans, txq_id, ssn, &skbs);
 
 		iwlagn_check_ratid_empty(priv, sta_id, tid);
@@ -1201,28 +1210,11 @@
 			if (!is_agg)
 				iwlagn_non_agg_tx_status(priv, ctx, hdr->addr1);
 
-			/*
-			 * W/A for FW bug - the seq_ctl isn't updated when the
-			 * queues are flushed. Fetch it from the packet itself
-			 */
-			if (!is_agg && status == TX_STATUS_FAIL_FIFO_FLUSHED) {
-				next_reclaimed = le16_to_cpu(hdr->seq_ctrl);
-				next_reclaimed =
-					SEQ_TO_SN(next_reclaimed + 0x10);
-			}
-
 			is_offchannel_skb =
 				(info->flags & IEEE80211_TX_CTL_TX_OFFCHAN);
 			freed++;
 		}
 
-		if (tid != IWL_TID_NON_QOS) {
-			priv->tid_data[sta_id][tid].next_reclaimed =
-				next_reclaimed;
-			IWL_DEBUG_TX_REPLY(priv, "Next reclaimed packet:%d\n",
-					   next_reclaimed);
-		}
-
 		WARN_ON(!is_agg && freed != 1);
 
 		/*
diff --git a/drivers/net/wireless/mwifiex/cfg80211.c b/drivers/net/wireless/mwifiex/cfg80211.c
index efe525b..cdb11b3 100644
--- a/drivers/net/wireless/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/mwifiex/cfg80211.c
@@ -1459,7 +1459,7 @@
 	struct cfg80211_ssid req_ssid;
 	int ret, auth_type = 0;
 	struct cfg80211_bss *bss = NULL;
-	u8 is_scanning_required = 0, config_bands = 0;
+	u8 is_scanning_required = 0;
 
 	memset(&req_ssid, 0, sizeof(struct cfg80211_ssid));
 
@@ -1478,19 +1478,6 @@
 	/* disconnect before try to associate */
 	mwifiex_deauthenticate(priv, NULL);
 
-	if (channel) {
-		if (mode == NL80211_IFTYPE_STATION) {
-			if (channel->band == IEEE80211_BAND_2GHZ)
-				config_bands = BAND_B | BAND_G | BAND_GN;
-			else
-				config_bands = BAND_A | BAND_AN;
-
-			if (!((config_bands | priv->adapter->fw_bands) &
-			      ~priv->adapter->fw_bands))
-				priv->adapter->config_bands = config_bands;
-		}
-	}
-
 	/* As this is new association, clear locally stored
 	 * keys and security related flags */
 	priv->sec_info.wpa_enabled = false;
@@ -1707,7 +1694,7 @@
 
 		if (cfg80211_get_chandef_type(&params->chandef) !=
 						NL80211_CHAN_NO_HT)
-			config_bands |= BAND_GN;
+			config_bands |= BAND_G | BAND_GN;
 	} else {
 		if (cfg80211_get_chandef_type(&params->chandef) ==
 						NL80211_CHAN_NO_HT)
diff --git a/drivers/net/wireless/mwifiex/pcie.c b/drivers/net/wireless/mwifiex/pcie.c
index 13fbc4e..b879e13 100644
--- a/drivers/net/wireless/mwifiex/pcie.c
+++ b/drivers/net/wireless/mwifiex/pcie.c
@@ -161,7 +161,7 @@
 
 	if (pdev) {
 		card = (struct pcie_service_card *) pci_get_drvdata(pdev);
-		if (!card || card->adapter) {
+		if (!card || !card->adapter) {
 			pr_err("Card or adapter structure is not valid\n");
 			return 0;
 		}
diff --git a/drivers/net/wireless/mwifiex/scan.c b/drivers/net/wireless/mwifiex/scan.c
index 9189a32..973a9d9 100644
--- a/drivers/net/wireless/mwifiex/scan.c
+++ b/drivers/net/wireless/mwifiex/scan.c
@@ -1563,7 +1563,7 @@
 		dev_err(adapter->dev, "SCAN_RESP: too many AP returned (%d)\n",
 			scan_rsp->number_of_sets);
 		ret = -1;
-		goto done;
+		goto check_next_scan;
 	}
 
 	bytes_left = le16_to_cpu(scan_rsp->bss_descript_size);
@@ -1634,7 +1634,8 @@
 		if (!beacon_size || beacon_size > bytes_left) {
 			bss_info += bytes_left;
 			bytes_left = 0;
-			return -1;
+			ret = -1;
+			goto check_next_scan;
 		}
 
 		/* Initialize the current working beacon pointer for this BSS
@@ -1690,7 +1691,7 @@
 				dev_err(priv->adapter->dev,
 					"%s: bytes left < IE length\n",
 					__func__);
-				goto done;
+				goto check_next_scan;
 			}
 			if (element_id == WLAN_EID_DS_PARAMS) {
 				channel = *(current_ptr + sizeof(struct ieee_types_header));
@@ -1753,6 +1754,7 @@
 		}
 	}
 
+check_next_scan:
 	spin_lock_irqsave(&adapter->scan_pending_q_lock, flags);
 	if (list_empty(&adapter->scan_pending_q)) {
 		spin_unlock_irqrestore(&adapter->scan_pending_q_lock, flags);
@@ -1813,7 +1815,6 @@
 		}
 	}
 
-done:
 	return ret;
 }
 
diff --git a/drivers/net/wireless/mwifiex/sta_ioctl.c b/drivers/net/wireless/mwifiex/sta_ioctl.c
index 60e88b5..f542bb8 100644
--- a/drivers/net/wireless/mwifiex/sta_ioctl.c
+++ b/drivers/net/wireless/mwifiex/sta_ioctl.c
@@ -283,6 +283,20 @@
 		if (ret)
 			goto done;
 
+		if (bss_desc) {
+			u8 config_bands = 0;
+
+			if (mwifiex_band_to_radio_type((u8) bss_desc->bss_band)
+			    == HostCmd_SCAN_RADIO_TYPE_BG)
+				config_bands = BAND_B | BAND_G | BAND_GN;
+			else
+				config_bands = BAND_A | BAND_AN;
+
+			if (!((config_bands | adapter->fw_bands) &
+			      ~adapter->fw_bands))
+				adapter->config_bands = config_bands;
+		}
+
 		ret = mwifiex_check_network_compatibility(priv, bss_desc);
 		if (ret)
 			goto done;
diff --git a/drivers/net/wireless/mwl8k.c b/drivers/net/wireless/mwl8k.c
index 83564d3..a00a03e 100644
--- a/drivers/net/wireless/mwl8k.c
+++ b/drivers/net/wireless/mwl8k.c
@@ -318,20 +318,20 @@
 #define MWL8K_STA(_sta) ((struct mwl8k_sta *)&((_sta)->drv_priv))
 
 static const struct ieee80211_channel mwl8k_channels_24[] = {
-	{ .center_freq = 2412, .hw_value = 1, },
-	{ .center_freq = 2417, .hw_value = 2, },
-	{ .center_freq = 2422, .hw_value = 3, },
-	{ .center_freq = 2427, .hw_value = 4, },
-	{ .center_freq = 2432, .hw_value = 5, },
-	{ .center_freq = 2437, .hw_value = 6, },
-	{ .center_freq = 2442, .hw_value = 7, },
-	{ .center_freq = 2447, .hw_value = 8, },
-	{ .center_freq = 2452, .hw_value = 9, },
-	{ .center_freq = 2457, .hw_value = 10, },
-	{ .center_freq = 2462, .hw_value = 11, },
-	{ .center_freq = 2467, .hw_value = 12, },
-	{ .center_freq = 2472, .hw_value = 13, },
-	{ .center_freq = 2484, .hw_value = 14, },
+	{ .band = IEEE80211_BAND_2GHZ, .center_freq = 2412, .hw_value = 1, },
+	{ .band = IEEE80211_BAND_2GHZ, .center_freq = 2417, .hw_value = 2, },
+	{ .band = IEEE80211_BAND_2GHZ, .center_freq = 2422, .hw_value = 3, },
+	{ .band = IEEE80211_BAND_2GHZ, .center_freq = 2427, .hw_value = 4, },
+	{ .band = IEEE80211_BAND_2GHZ, .center_freq = 2432, .hw_value = 5, },
+	{ .band = IEEE80211_BAND_2GHZ, .center_freq = 2437, .hw_value = 6, },
+	{ .band = IEEE80211_BAND_2GHZ, .center_freq = 2442, .hw_value = 7, },
+	{ .band = IEEE80211_BAND_2GHZ, .center_freq = 2447, .hw_value = 8, },
+	{ .band = IEEE80211_BAND_2GHZ, .center_freq = 2452, .hw_value = 9, },
+	{ .band = IEEE80211_BAND_2GHZ, .center_freq = 2457, .hw_value = 10, },
+	{ .band = IEEE80211_BAND_2GHZ, .center_freq = 2462, .hw_value = 11, },
+	{ .band = IEEE80211_BAND_2GHZ, .center_freq = 2467, .hw_value = 12, },
+	{ .band = IEEE80211_BAND_2GHZ, .center_freq = 2472, .hw_value = 13, },
+	{ .band = IEEE80211_BAND_2GHZ, .center_freq = 2484, .hw_value = 14, },
 };
 
 static const struct ieee80211_rate mwl8k_rates_24[] = {
@@ -352,10 +352,10 @@
 };
 
 static const struct ieee80211_channel mwl8k_channels_50[] = {
-	{ .center_freq = 5180, .hw_value = 36, },
-	{ .center_freq = 5200, .hw_value = 40, },
-	{ .center_freq = 5220, .hw_value = 44, },
-	{ .center_freq = 5240, .hw_value = 48, },
+	{ .band = IEEE80211_BAND_5GHZ, .center_freq = 5180, .hw_value = 36, },
+	{ .band = IEEE80211_BAND_5GHZ, .center_freq = 5200, .hw_value = 40, },
+	{ .band = IEEE80211_BAND_5GHZ, .center_freq = 5220, .hw_value = 44, },
+	{ .band = IEEE80211_BAND_5GHZ, .center_freq = 5240, .hw_value = 48, },
 };
 
 static const struct ieee80211_rate mwl8k_rates_50[] = {
diff --git a/drivers/net/wireless/rtlwifi/Kconfig b/drivers/net/wireless/rtlwifi/Kconfig
index 21b1bbb..b80bc46 100644
--- a/drivers/net/wireless/rtlwifi/Kconfig
+++ b/drivers/net/wireless/rtlwifi/Kconfig
@@ -57,12 +57,12 @@
 
 config RTLWIFI
 	tristate
-	depends on RTL8192CE || RTL8192CU || RTL8192SE || RTL8192DE
+	depends on RTL8192CE || RTL8192CU || RTL8192SE || RTL8192DE || RTL8723AE
 	default m
 
 config RTLWIFI_DEBUG
 	bool "Additional debugging output"
-	depends on RTL8192CE || RTL8192CU || RTL8192SE || RTL8192DE
+	depends on RTL8192CE || RTL8192CU || RTL8192SE || RTL8192DE || RTL8723AE
 	default y
 
 config RTL8192C_COMMON
diff --git a/drivers/net/wireless/rtlwifi/base.c b/drivers/net/wireless/rtlwifi/base.c
index 4494d13..0f8b051 100644
--- a/drivers/net/wireless/rtlwifi/base.c
+++ b/drivers/net/wireless/rtlwifi/base.c
@@ -1004,7 +1004,8 @@
 					 is_tx ? "Tx" : "Rx");
 
 				if (is_tx) {
-					rtl_lps_leave(hw);
+					schedule_work(&rtlpriv->
+						      works.lps_leave_work);
 					ppsc->last_delaylps_stamp_jiffies =
 					    jiffies;
 				}
@@ -1014,7 +1015,7 @@
 		}
 	} else if (ETH_P_ARP == ether_type) {
 		if (is_tx) {
-			rtl_lps_leave(hw);
+			schedule_work(&rtlpriv->works.lps_leave_work);
 			ppsc->last_delaylps_stamp_jiffies = jiffies;
 		}
 
@@ -1024,7 +1025,7 @@
 			 "802.1X %s EAPOL pkt!!\n", is_tx ? "Tx" : "Rx");
 
 		if (is_tx) {
-			rtl_lps_leave(hw);
+			schedule_work(&rtlpriv->works.lps_leave_work);
 			ppsc->last_delaylps_stamp_jiffies = jiffies;
 		}
 
diff --git a/drivers/net/wireless/rtlwifi/usb.c b/drivers/net/wireless/rtlwifi/usb.c
index f2ecdeb..1535efd 100644
--- a/drivers/net/wireless/rtlwifi/usb.c
+++ b/drivers/net/wireless/rtlwifi/usb.c
@@ -542,8 +542,8 @@
 	WARN_ON(skb_queue_empty(&rx_queue));
 	while (!skb_queue_empty(&rx_queue)) {
 		_skb = skb_dequeue(&rx_queue);
-		_rtl_usb_rx_process_agg(hw, skb);
-		ieee80211_rx_irqsafe(hw, skb);
+		_rtl_usb_rx_process_agg(hw, _skb);
+		ieee80211_rx_irqsafe(hw, _skb);
 	}
 }
 
diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
index 94b79c3..9d7f172 100644
--- a/drivers/net/xen-netback/common.h
+++ b/drivers/net/xen-netback/common.h
@@ -151,6 +151,9 @@
 /* Notify xenvif that ring now has space to send an skb to the frontend */
 void xenvif_notify_tx_completion(struct xenvif *vif);
 
+/* Prevent the device from generating any further traffic. */
+void xenvif_carrier_off(struct xenvif *vif);
+
 /* Returns number of ring slots required to send an skb to the frontend */
 unsigned int xen_netbk_count_skb_slots(struct xenvif *vif, struct sk_buff *skb);
 
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index b7d41f8..b8c5193 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -343,17 +343,22 @@
 	return err;
 }
 
-void xenvif_disconnect(struct xenvif *vif)
+void xenvif_carrier_off(struct xenvif *vif)
 {
 	struct net_device *dev = vif->dev;
-	if (netif_carrier_ok(dev)) {
-		rtnl_lock();
-		netif_carrier_off(dev); /* discard queued packets */
-		if (netif_running(dev))
-			xenvif_down(vif);
-		rtnl_unlock();
-		xenvif_put(vif);
-	}
+
+	rtnl_lock();
+	netif_carrier_off(dev); /* discard queued packets */
+	if (netif_running(dev))
+		xenvif_down(vif);
+	rtnl_unlock();
+	xenvif_put(vif);
+}
+
+void xenvif_disconnect(struct xenvif *vif)
+{
+	if (netif_carrier_ok(vif->dev))
+		xenvif_carrier_off(vif);
 
 	atomic_dec(&vif->refcnt);
 	wait_event(vif->waiting_to_free, atomic_read(&vif->refcnt) == 0);
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index f2d6b78..2b9520c 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -147,7 +147,8 @@
 	atomic_dec(&netbk->netfront_count);
 }
 
-static void xen_netbk_idx_release(struct xen_netbk *netbk, u16 pending_idx);
+static void xen_netbk_idx_release(struct xen_netbk *netbk, u16 pending_idx,
+				  u8 status);
 static void make_tx_response(struct xenvif *vif,
 			     struct xen_netif_tx_request *txp,
 			     s8       st);
@@ -879,7 +880,7 @@
 
 	do {
 		make_tx_response(vif, txp, XEN_NETIF_RSP_ERROR);
-		if (cons >= end)
+		if (cons == end)
 			break;
 		txp = RING_GET_REQUEST(&vif->tx, cons++);
 	} while (1);
@@ -888,6 +889,13 @@
 	xenvif_put(vif);
 }
 
+static void netbk_fatal_tx_err(struct xenvif *vif)
+{
+	netdev_err(vif->dev, "fatal error; disabling device\n");
+	xenvif_carrier_off(vif);
+	xenvif_put(vif);
+}
+
 static int netbk_count_requests(struct xenvif *vif,
 				struct xen_netif_tx_request *first,
 				struct xen_netif_tx_request *txp,
@@ -901,19 +909,22 @@
 
 	do {
 		if (frags >= work_to_do) {
-			netdev_dbg(vif->dev, "Need more frags\n");
+			netdev_err(vif->dev, "Need more frags\n");
+			netbk_fatal_tx_err(vif);
 			return -frags;
 		}
 
 		if (unlikely(frags >= MAX_SKB_FRAGS)) {
-			netdev_dbg(vif->dev, "Too many frags\n");
+			netdev_err(vif->dev, "Too many frags\n");
+			netbk_fatal_tx_err(vif);
 			return -frags;
 		}
 
 		memcpy(txp, RING_GET_REQUEST(&vif->tx, cons + frags),
 		       sizeof(*txp));
 		if (txp->size > first->size) {
-			netdev_dbg(vif->dev, "Frags galore\n");
+			netdev_err(vif->dev, "Frag is bigger than frame.\n");
+			netbk_fatal_tx_err(vif);
 			return -frags;
 		}
 
@@ -921,8 +932,9 @@
 		frags++;
 
 		if (unlikely((txp->offset + txp->size) > PAGE_SIZE)) {
-			netdev_dbg(vif->dev, "txp->offset: %x, size: %u\n",
+			netdev_err(vif->dev, "txp->offset: %x, size: %u\n",
 				 txp->offset, txp->size);
+			netbk_fatal_tx_err(vif);
 			return -frags;
 		}
 	} while ((txp++)->flags & XEN_NETTXF_more_data);
@@ -966,7 +978,7 @@
 		pending_idx = netbk->pending_ring[index];
 		page = xen_netbk_alloc_page(netbk, skb, pending_idx);
 		if (!page)
-			return NULL;
+			goto err;
 
 		gop->source.u.ref = txp->gref;
 		gop->source.domid = vif->domid;
@@ -988,6 +1000,17 @@
 	}
 
 	return gop;
+err:
+	/* Unwind, freeing all pages and sending error responses. */
+	while (i-- > start) {
+		xen_netbk_idx_release(netbk, frag_get_pending_idx(&frags[i]),
+				      XEN_NETIF_RSP_ERROR);
+	}
+	/* The head too, if necessary. */
+	if (start)
+		xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_ERROR);
+
+	return NULL;
 }
 
 static int xen_netbk_tx_check_gop(struct xen_netbk *netbk,
@@ -996,30 +1019,20 @@
 {
 	struct gnttab_copy *gop = *gopp;
 	u16 pending_idx = *((u16 *)skb->data);
-	struct pending_tx_info *pending_tx_info = netbk->pending_tx_info;
-	struct xenvif *vif = pending_tx_info[pending_idx].vif;
-	struct xen_netif_tx_request *txp;
 	struct skb_shared_info *shinfo = skb_shinfo(skb);
 	int nr_frags = shinfo->nr_frags;
 	int i, err, start;
 
 	/* Check status of header. */
 	err = gop->status;
-	if (unlikely(err)) {
-		pending_ring_idx_t index;
-		index = pending_index(netbk->pending_prod++);
-		txp = &pending_tx_info[pending_idx].req;
-		make_tx_response(vif, txp, XEN_NETIF_RSP_ERROR);
-		netbk->pending_ring[index] = pending_idx;
-		xenvif_put(vif);
-	}
+	if (unlikely(err))
+		xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_ERROR);
 
 	/* Skip first skb fragment if it is on same page as header fragment. */
 	start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx);
 
 	for (i = start; i < nr_frags; i++) {
 		int j, newerr;
-		pending_ring_idx_t index;
 
 		pending_idx = frag_get_pending_idx(&shinfo->frags[i]);
 
@@ -1028,16 +1041,12 @@
 		if (likely(!newerr)) {
 			/* Had a previous error? Invalidate this fragment. */
 			if (unlikely(err))
-				xen_netbk_idx_release(netbk, pending_idx);
+				xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_OKAY);
 			continue;
 		}
 
 		/* Error on this fragment: respond to client with an error. */
-		txp = &netbk->pending_tx_info[pending_idx].req;
-		make_tx_response(vif, txp, XEN_NETIF_RSP_ERROR);
-		index = pending_index(netbk->pending_prod++);
-		netbk->pending_ring[index] = pending_idx;
-		xenvif_put(vif);
+		xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_ERROR);
 
 		/* Not the first error? Preceding frags already invalidated. */
 		if (err)
@@ -1045,10 +1054,10 @@
 
 		/* First error: invalidate header and preceding fragments. */
 		pending_idx = *((u16 *)skb->data);
-		xen_netbk_idx_release(netbk, pending_idx);
+		xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_OKAY);
 		for (j = start; j < i; j++) {
 			pending_idx = frag_get_pending_idx(&shinfo->frags[j]);
-			xen_netbk_idx_release(netbk, pending_idx);
+			xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_OKAY);
 		}
 
 		/* Remember the error: invalidate all subsequent fragments. */
@@ -1082,7 +1091,7 @@
 
 		/* Take an extra reference to offset xen_netbk_idx_release */
 		get_page(netbk->mmap_pages[pending_idx]);
-		xen_netbk_idx_release(netbk, pending_idx);
+		xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_OKAY);
 	}
 }
 
@@ -1095,7 +1104,8 @@
 
 	do {
 		if (unlikely(work_to_do-- <= 0)) {
-			netdev_dbg(vif->dev, "Missing extra info\n");
+			netdev_err(vif->dev, "Missing extra info\n");
+			netbk_fatal_tx_err(vif);
 			return -EBADR;
 		}
 
@@ -1104,8 +1114,9 @@
 		if (unlikely(!extra.type ||
 			     extra.type >= XEN_NETIF_EXTRA_TYPE_MAX)) {
 			vif->tx.req_cons = ++cons;
-			netdev_dbg(vif->dev,
+			netdev_err(vif->dev,
 				   "Invalid extra type: %d\n", extra.type);
+			netbk_fatal_tx_err(vif);
 			return -EINVAL;
 		}
 
@@ -1121,13 +1132,15 @@
 			     struct xen_netif_extra_info *gso)
 {
 	if (!gso->u.gso.size) {
-		netdev_dbg(vif->dev, "GSO size must not be zero.\n");
+		netdev_err(vif->dev, "GSO size must not be zero.\n");
+		netbk_fatal_tx_err(vif);
 		return -EINVAL;
 	}
 
 	/* Currently only TCPv4 S.O. is supported. */
 	if (gso->u.gso.type != XEN_NETIF_GSO_TYPE_TCPV4) {
-		netdev_dbg(vif->dev, "Bad GSO type %d.\n", gso->u.gso.type);
+		netdev_err(vif->dev, "Bad GSO type %d.\n", gso->u.gso.type);
+		netbk_fatal_tx_err(vif);
 		return -EINVAL;
 	}
 
@@ -1264,9 +1277,25 @@
 
 		/* Get a netif from the list with work to do. */
 		vif = poll_net_schedule_list(netbk);
+		/* This can sometimes happen because the test of
+		 * list_empty(net_schedule_list) at the top of the
+		 * loop is unlocked.  Just go back and have another
+		 * look.
+		 */
 		if (!vif)
 			continue;
 
+		if (vif->tx.sring->req_prod - vif->tx.req_cons >
+		    XEN_NETIF_TX_RING_SIZE) {
+			netdev_err(vif->dev,
+				   "Impossible number of requests. "
+				   "req_prod %d, req_cons %d, size %ld\n",
+				   vif->tx.sring->req_prod, vif->tx.req_cons,
+				   XEN_NETIF_TX_RING_SIZE);
+			netbk_fatal_tx_err(vif);
+			continue;
+		}
+
 		RING_FINAL_CHECK_FOR_REQUESTS(&vif->tx, work_to_do);
 		if (!work_to_do) {
 			xenvif_put(vif);
@@ -1294,17 +1323,14 @@
 			work_to_do = xen_netbk_get_extras(vif, extras,
 							  work_to_do);
 			idx = vif->tx.req_cons;
-			if (unlikely(work_to_do < 0)) {
-				netbk_tx_err(vif, &txreq, idx);
+			if (unlikely(work_to_do < 0))
 				continue;
-			}
 		}
 
 		ret = netbk_count_requests(vif, &txreq, txfrags, work_to_do);
-		if (unlikely(ret < 0)) {
-			netbk_tx_err(vif, &txreq, idx - ret);
+		if (unlikely(ret < 0))
 			continue;
-		}
+
 		idx += ret;
 
 		if (unlikely(txreq.size < ETH_HLEN)) {
@@ -1316,11 +1342,11 @@
 
 		/* No crossing a page as the payload mustn't fragment. */
 		if (unlikely((txreq.offset + txreq.size) > PAGE_SIZE)) {
-			netdev_dbg(vif->dev,
+			netdev_err(vif->dev,
 				   "txreq.offset: %x, size: %u, end: %lu\n",
 				   txreq.offset, txreq.size,
 				   (txreq.offset&~PAGE_MASK) + txreq.size);
-			netbk_tx_err(vif, &txreq, idx);
+			netbk_fatal_tx_err(vif);
 			continue;
 		}
 
@@ -1348,8 +1374,8 @@
 			gso = &extras[XEN_NETIF_EXTRA_TYPE_GSO - 1];
 
 			if (netbk_set_skb_gso(vif, skb, gso)) {
+				/* Failure in netbk_set_skb_gso is fatal. */
 				kfree_skb(skb);
-				netbk_tx_err(vif, &txreq, idx);
 				continue;
 			}
 		}
@@ -1448,7 +1474,7 @@
 			txp->size -= data_len;
 		} else {
 			/* Schedule a response immediately. */
-			xen_netbk_idx_release(netbk, pending_idx);
+			xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_OKAY);
 		}
 
 		if (txp->flags & XEN_NETTXF_csum_blank)
@@ -1500,7 +1526,8 @@
 	xen_netbk_tx_submit(netbk);
 }
 
-static void xen_netbk_idx_release(struct xen_netbk *netbk, u16 pending_idx)
+static void xen_netbk_idx_release(struct xen_netbk *netbk, u16 pending_idx,
+				  u8 status)
 {
 	struct xenvif *vif;
 	struct pending_tx_info *pending_tx_info;
@@ -1514,7 +1541,7 @@
 
 	vif = pending_tx_info->vif;
 
-	make_tx_response(vif, &pending_tx_info->req, XEN_NETIF_RSP_OKAY);
+	make_tx_response(vif, &pending_tx_info->req, status);
 
 	index = pending_index(netbk->pending_prod++);
 	netbk->pending_ring[index] = pending_idx;
diff --git a/drivers/pci/pcie/aer/aerdrv_errprint.c b/drivers/pci/pcie/aer/aerdrv_errprint.c
index 3ea5173..5ab1425 100644
--- a/drivers/pci/pcie/aer/aerdrv_errprint.c
+++ b/drivers/pci/pcie/aer/aerdrv_errprint.c
@@ -23,6 +23,9 @@
 
 #include "aerdrv.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/ras.h>
+
 #define AER_AGENT_RECEIVER		0
 #define AER_AGENT_REQUESTER		1
 #define AER_AGENT_COMPLETER		2
@@ -121,12 +124,11 @@
 	"Transmitter ID"
 };
 
-static void __aer_print_error(const char *prefix,
+static void __aer_print_error(struct pci_dev *dev,
 			      struct aer_err_info *info)
 {
 	int i, status;
 	const char *errmsg = NULL;
-
 	status = (info->status & ~info->mask);
 
 	for (i = 0; i < 32; i++) {
@@ -141,26 +143,22 @@
 				aer_uncorrectable_error_string[i] : NULL;
 
 		if (errmsg)
-			printk("%s""   [%2d] %-22s%s\n", prefix, i, errmsg,
+			dev_err(&dev->dev, "   [%2d] %-22s%s\n", i, errmsg,
 				info->first_error == i ? " (First)" : "");
 		else
-			printk("%s""   [%2d] Unknown Error Bit%s\n", prefix, i,
-				info->first_error == i ? " (First)" : "");
+			dev_err(&dev->dev, "   [%2d] Unknown Error Bit%s\n",
+				i, info->first_error == i ? " (First)" : "");
 	}
 }
 
 void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
 {
 	int id = ((dev->bus->number << 8) | dev->devfn);
-	char prefix[44];
-
-	snprintf(prefix, sizeof(prefix), "%s%s %s: ",
-		 (info->severity == AER_CORRECTABLE) ? KERN_WARNING : KERN_ERR,
-		 dev_driver_string(&dev->dev), dev_name(&dev->dev));
 
 	if (info->status == 0) {
-		printk("%s""PCIe Bus Error: severity=%s, type=Unaccessible, "
-			"id=%04x(Unregistered Agent ID)\n", prefix,
+		dev_err(&dev->dev,
+			"PCIe Bus Error: severity=%s, type=Unaccessible, "
+			"id=%04x(Unregistered Agent ID)\n",
 			aer_error_severity_string[info->severity], id);
 	} else {
 		int layer, agent;
@@ -168,22 +166,24 @@
 		layer = AER_GET_LAYER_ERROR(info->severity, info->status);
 		agent = AER_GET_AGENT(info->severity, info->status);
 
-		printk("%s""PCIe Bus Error: severity=%s, type=%s, id=%04x(%s)\n",
-			prefix, aer_error_severity_string[info->severity],
+		dev_err(&dev->dev,
+			"PCIe Bus Error: severity=%s, type=%s, id=%04x(%s)\n",
+			aer_error_severity_string[info->severity],
 			aer_error_layer[layer], id, aer_agent_string[agent]);
 
-		printk("%s""  device [%04x:%04x] error status/mask=%08x/%08x\n",
-			prefix, dev->vendor, dev->device,
+		dev_err(&dev->dev,
+			"  device [%04x:%04x] error status/mask=%08x/%08x\n",
+			dev->vendor, dev->device,
 			info->status, info->mask);
 
-		__aer_print_error(prefix, info);
+		__aer_print_error(dev, info);
 
 		if (info->tlp_header_valid) {
 			unsigned char *tlp = (unsigned char *) &info->tlp;
-			printk("%s""  TLP Header:"
+			dev_err(&dev->dev, "  TLP Header:"
 				" %02x%02x%02x%02x %02x%02x%02x%02x"
 				" %02x%02x%02x%02x %02x%02x%02x%02x\n",
-				prefix, *(tlp + 3), *(tlp + 2), *(tlp + 1), *tlp,
+				*(tlp + 3), *(tlp + 2), *(tlp + 1), *tlp,
 				*(tlp + 7), *(tlp + 6), *(tlp + 5), *(tlp + 4),
 				*(tlp + 11), *(tlp + 10), *(tlp + 9),
 				*(tlp + 8), *(tlp + 15), *(tlp + 14),
@@ -192,8 +192,11 @@
 	}
 
 	if (info->id && info->error_dev_num > 1 && info->id == id)
-		printk("%s""  Error of this Agent(%04x) is reported first\n",
-			prefix, id);
+		dev_err(&dev->dev,
+			   "  Error of this Agent(%04x) is reported first\n",
+			id);
+	trace_aer_event(dev_name(&dev->dev), (info->status & ~info->mask),
+			info->severity);
 }
 
 void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info)
@@ -217,7 +220,7 @@
 }
 EXPORT_SYMBOL_GPL(cper_severity_to_aer);
 
-void cper_print_aer(const char *prefix, int cper_severity,
+void cper_print_aer(const char *prefix, struct pci_dev *dev, int cper_severity,
 		    struct aer_capability_regs *aer)
 {
 	int aer_severity, layer, agent, status_strs_size, tlp_header_valid = 0;
@@ -239,25 +242,27 @@
 	}
 	layer = AER_GET_LAYER_ERROR(aer_severity, status);
 	agent = AER_GET_AGENT(aer_severity, status);
-	printk("%s""aer_status: 0x%08x, aer_mask: 0x%08x\n",
-	       prefix, status, mask);
+	dev_err(&dev->dev, "aer_status: 0x%08x, aer_mask: 0x%08x\n",
+	       status, mask);
 	cper_print_bits(prefix, status, status_strs, status_strs_size);
-	printk("%s""aer_layer=%s, aer_agent=%s\n", prefix,
+	dev_err(&dev->dev, "aer_layer=%s, aer_agent=%s\n",
 	       aer_error_layer[layer], aer_agent_string[agent]);
 	if (aer_severity != AER_CORRECTABLE)
-		printk("%s""aer_uncor_severity: 0x%08x\n",
-		       prefix, aer->uncor_severity);
+		dev_err(&dev->dev, "aer_uncor_severity: 0x%08x\n",
+		       aer->uncor_severity);
 	if (tlp_header_valid) {
 		const unsigned char *tlp;
 		tlp = (const unsigned char *)&aer->header_log;
-		printk("%s""aer_tlp_header:"
+		dev_err(&dev->dev, "aer_tlp_header:"
 			" %02x%02x%02x%02x %02x%02x%02x%02x"
 			" %02x%02x%02x%02x %02x%02x%02x%02x\n",
-			prefix, *(tlp + 3), *(tlp + 2), *(tlp + 1), *tlp,
+			*(tlp + 3), *(tlp + 2), *(tlp + 1), *tlp,
 			*(tlp + 7), *(tlp + 6), *(tlp + 5), *(tlp + 4),
 			*(tlp + 11), *(tlp + 10), *(tlp + 9),
 			*(tlp + 8), *(tlp + 15), *(tlp + 14),
 			*(tlp + 13), *(tlp + 12));
 	}
+	trace_aer_event(dev_name(&dev->dev), (status & ~mask),
+			aer_severity);
 }
 #endif
diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c
index 7c0fd92..84954a7 100644
--- a/drivers/pci/remove.c
+++ b/drivers/pci/remove.c
@@ -19,6 +19,8 @@
 
 static void pci_stop_dev(struct pci_dev *dev)
 {
+	pci_pme_active(dev, false);
+
 	if (dev->is_added) {
 		pci_proc_detach_device(dev);
 		pci_remove_sysfs_dev_files(dev);
diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig
index c31aeb0..a5f3c8c 100644
--- a/drivers/pinctrl/Kconfig
+++ b/drivers/pinctrl/Kconfig
@@ -181,12 +181,11 @@
 
 config PINCTRL_SAMSUNG
 	bool
-	depends on OF && GPIOLIB
 	select PINMUX
 	select PINCONF
 
-config PINCTRL_EXYNOS4
-	bool "Pinctrl driver data for Exynos4 SoC"
+config PINCTRL_EXYNOS
+	bool "Pinctrl driver data for Samsung EXYNOS SoCs"
 	depends on OF && GPIOLIB
 	select PINCTRL_SAMSUNG
 
diff --git a/drivers/pinctrl/Makefile b/drivers/pinctrl/Makefile
index fc4606f..6e87e52 100644
--- a/drivers/pinctrl/Makefile
+++ b/drivers/pinctrl/Makefile
@@ -36,7 +36,7 @@
 obj-$(CONFIG_PINCTRL_U300)	+= pinctrl-u300.o
 obj-$(CONFIG_PINCTRL_COH901)	+= pinctrl-coh901.o
 obj-$(CONFIG_PINCTRL_SAMSUNG)	+= pinctrl-samsung.o
-obj-$(CONFIG_PINCTRL_EXYNOS4)	+= pinctrl-exynos.o
+obj-$(CONFIG_PINCTRL_EXYNOS)	+= pinctrl-exynos.o
 obj-$(CONFIG_PINCTRL_EXYNOS5440)	+= pinctrl-exynos5440.o
 obj-$(CONFIG_PINCTRL_XWAY)	+= pinctrl-xway.o
 obj-$(CONFIG_PINCTRL_LANTIQ)	+= pinctrl-lantiq.o
diff --git a/drivers/pinctrl/mvebu/pinctrl-dove.c b/drivers/pinctrl/mvebu/pinctrl-dove.c
index 69aba36..428ea96 100644
--- a/drivers/pinctrl/mvebu/pinctrl-dove.c
+++ b/drivers/pinctrl/mvebu/pinctrl-dove.c
@@ -588,7 +588,7 @@
 {
 	const struct of_device_id *match =
 		of_match_device(dove_pinctrl_of_match, &pdev->dev);
-	pdev->dev.platform_data = match->data;
+	pdev->dev.platform_data = (void *)match->data;
 
 	/*
 	 * General MPP Configuration Register is part of pdma registers.
diff --git a/drivers/pinctrl/mvebu/pinctrl-kirkwood.c b/drivers/pinctrl/mvebu/pinctrl-kirkwood.c
index f12084e..cdd483d 100644
--- a/drivers/pinctrl/mvebu/pinctrl-kirkwood.c
+++ b/drivers/pinctrl/mvebu/pinctrl-kirkwood.c
@@ -66,9 +66,9 @@
 		MPP_VAR_FUNCTION(0x5, "sata0", "act",    V(0, 1, 1, 1, 1, 0)),
 		MPP_VAR_FUNCTION(0xb, "lcd", "vsync",    V(0, 0, 0, 0, 1, 0))),
 	MPP_MODE(6,
-		MPP_VAR_FUNCTION(0x0, "sysrst", "out",   V(1, 1, 1, 1, 1, 1)),
-		MPP_VAR_FUNCTION(0x1, "spi", "mosi",     V(1, 1, 1, 1, 1, 1)),
-		MPP_VAR_FUNCTION(0x2, "ptp", "trig",     V(1, 1, 1, 1, 0, 0))),
+		MPP_VAR_FUNCTION(0x1, "sysrst", "out",   V(1, 1, 1, 1, 1, 1)),
+		MPP_VAR_FUNCTION(0x2, "spi", "mosi",     V(1, 1, 1, 1, 1, 1)),
+		MPP_VAR_FUNCTION(0x3, "ptp", "trig",     V(1, 1, 1, 1, 0, 0))),
 	MPP_MODE(7,
 		MPP_VAR_FUNCTION(0x0, "gpo", NULL,       V(1, 1, 1, 1, 1, 1)),
 		MPP_VAR_FUNCTION(0x1, "pex", "rsto",     V(1, 1, 1, 1, 0, 1)),
@@ -458,7 +458,7 @@
 {
 	const struct of_device_id *match =
 		of_match_device(kirkwood_pinctrl_of_match, &pdev->dev);
-	pdev->dev.platform_data = match->data;
+	pdev->dev.platform_data = (void *)match->data;
 	return mvebu_pinctrl_probe(pdev);
 }
 
diff --git a/drivers/pinctrl/pinctrl-exynos5440.c b/drivers/pinctrl/pinctrl-exynos5440.c
index de05b64..1427299 100644
--- a/drivers/pinctrl/pinctrl-exynos5440.c
+++ b/drivers/pinctrl/pinctrl-exynos5440.c
@@ -599,7 +599,7 @@
 }
 
 /* parse the pin numbers listed in the 'samsung,exynos5440-pins' property */
-static int __init exynos5440_pinctrl_parse_dt_pins(struct platform_device *pdev,
+static int exynos5440_pinctrl_parse_dt_pins(struct platform_device *pdev,
 			struct device_node *cfg_np, unsigned int **pin_list,
 			unsigned int *npins)
 {
@@ -630,7 +630,7 @@
  * Parse the information about all the available pin groups and pin functions
  * from device node of the pin-controller.
  */
-static int __init exynos5440_pinctrl_parse_dt(struct platform_device *pdev,
+static int exynos5440_pinctrl_parse_dt(struct platform_device *pdev,
 				struct exynos5440_pinctrl_priv_data *priv)
 {
 	struct device *dev = &pdev->dev;
@@ -723,7 +723,7 @@
 }
 
 /* register the pinctrl interface with the pinctrl subsystem */
-static int __init exynos5440_pinctrl_register(struct platform_device *pdev,
+static int exynos5440_pinctrl_register(struct platform_device *pdev,
 				struct exynos5440_pinctrl_priv_data *priv)
 {
 	struct device *dev = &pdev->dev;
@@ -798,7 +798,7 @@
 }
 
 /* register the gpiolib interface with the gpiolib subsystem */
-static int __init exynos5440_gpiolib_register(struct platform_device *pdev,
+static int exynos5440_gpiolib_register(struct platform_device *pdev,
 				struct exynos5440_pinctrl_priv_data *priv)
 {
 	struct gpio_chip *gc;
@@ -831,7 +831,7 @@
 }
 
 /* unregister the gpiolib interface with the gpiolib subsystem */
-static int __init exynos5440_gpiolib_unregister(struct platform_device *pdev,
+static int exynos5440_gpiolib_unregister(struct platform_device *pdev,
 				struct exynos5440_pinctrl_priv_data *priv)
 {
 	int ret = gpiochip_remove(priv->gc);
diff --git a/drivers/pinctrl/pinctrl-mxs.c b/drivers/pinctrl/pinctrl-mxs.c
index dd227d2..23af9f1 100644
--- a/drivers/pinctrl/pinctrl-mxs.c
+++ b/drivers/pinctrl/pinctrl-mxs.c
@@ -146,7 +146,7 @@
 static void mxs_dt_free_map(struct pinctrl_dev *pctldev,
 			    struct pinctrl_map *map, unsigned num_maps)
 {
-	int i;
+	u32 i;
 
 	for (i = 0; i < num_maps; i++) {
 		if (map[i].type == PIN_MAP_TYPE_MUX_GROUP)
@@ -203,7 +203,7 @@
 	void __iomem *reg;
 	u8 bank, shift;
 	u16 pin;
-	int i;
+	u32 i;
 
 	for (i = 0; i < g->npins; i++) {
 		bank = PINID_TO_BANK(g->pins[i]);
@@ -256,7 +256,7 @@
 	void __iomem *reg;
 	u8 ma, vol, pull, bank, shift;
 	u16 pin;
-	int i;
+	u32 i;
 
 	ma = CONFIG_TO_MA(config);
 	vol = CONFIG_TO_VOL(config);
@@ -345,8 +345,7 @@
 	const char *propname = "fsl,pinmux-ids";
 	char *group;
 	int length = strlen(np->name) + SUFFIX_LEN;
-	int i;
-	u32 val;
+	u32 val, i;
 
 	group = devm_kzalloc(&pdev->dev, length, GFP_KERNEL);
 	if (!group)
diff --git a/drivers/pinctrl/pinctrl-nomadik.c b/drivers/pinctrl/pinctrl-nomadik.c
index 1bb16ff..5767b18 100644
--- a/drivers/pinctrl/pinctrl-nomadik.c
+++ b/drivers/pinctrl/pinctrl-nomadik.c
@@ -676,7 +676,7 @@
 }
 EXPORT_SYMBOL(nmk_gpio_set_mode);
 
-static int nmk_prcm_gpiocr_get_mode(struct pinctrl_dev *pctldev, int gpio)
+static int __maybe_unused nmk_prcm_gpiocr_get_mode(struct pinctrl_dev *pctldev, int gpio)
 {
 	int i;
 	u16 reg;
diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c
index f6a360b..5c32e88 100644
--- a/drivers/pinctrl/pinctrl-single.c
+++ b/drivers/pinctrl/pinctrl-single.c
@@ -30,7 +30,6 @@
 #define PCS_MUX_BITS_NAME		"pinctrl-single,bits"
 #define PCS_REG_NAME_LEN		((sizeof(unsigned long) * 2) + 1)
 #define PCS_OFF_DISABLED		~0U
-#define PCS_MAX_GPIO_VALUES		2
 
 /**
  * struct pcs_pingroup - pingroups for a function
@@ -78,16 +77,6 @@
 };
 
 /**
- * struct pcs_gpio_range - pinctrl gpio range
- * @range:	subrange of the GPIO number space
- * @gpio_func:	gpio function value in the pinmux register
- */
-struct pcs_gpio_range {
-	struct pinctrl_gpio_range range;
-	int gpio_func;
-};
-
-/**
  * struct pcs_data - wrapper for data needed by pinctrl framework
  * @pa:		pindesc array
  * @cur:	index to current element
@@ -414,26 +403,9 @@
 }
 
 static int pcs_request_gpio(struct pinctrl_dev *pctldev,
-			    struct pinctrl_gpio_range *range, unsigned pin)
+			struct pinctrl_gpio_range *range, unsigned offset)
 {
-	struct pcs_device *pcs = pinctrl_dev_get_drvdata(pctldev);
-	struct pcs_gpio_range *gpio = NULL;
-	int end, mux_bytes;
-	unsigned data;
-
-	gpio = container_of(range, struct pcs_gpio_range, range);
-	end = range->pin_base + range->npins - 1;
-	if (pin < range->pin_base || pin > end) {
-		dev_err(pctldev->dev,
-			"pin %d isn't in the range of %d to %d\n",
-			pin, range->pin_base, end);
-		return -EINVAL;
-	}
-	mux_bytes = pcs->width / BITS_PER_BYTE;
-	data = pcs->read(pcs->base + pin * mux_bytes) & ~pcs->fmask;
-	data |= gpio->gpio_func;
-	pcs->write(data, pcs->base + pin * mux_bytes);
-	return 0;
+	return -ENOTSUPP;
 }
 
 static struct pinmux_ops pcs_pinmux_ops = {
@@ -907,49 +879,6 @@
 
 static struct of_device_id pcs_of_match[];
 
-static int pcs_add_gpio_range(struct device_node *node, struct pcs_device *pcs)
-{
-	struct pcs_gpio_range *gpio;
-	struct device_node *child;
-	struct resource r;
-	const char name[] = "pinctrl-single";
-	u32 gpiores[PCS_MAX_GPIO_VALUES];
-	int ret, i = 0, mux_bytes = 0;
-
-	for_each_child_of_node(node, child) {
-		ret = of_address_to_resource(child, 0, &r);
-		if (ret < 0)
-			continue;
-		memset(gpiores, 0, sizeof(u32) * PCS_MAX_GPIO_VALUES);
-		ret = of_property_read_u32_array(child, "pinctrl-single,gpio",
-						 gpiores, PCS_MAX_GPIO_VALUES);
-		if (ret < 0)
-			continue;
-		gpio = devm_kzalloc(pcs->dev, sizeof(*gpio), GFP_KERNEL);
-		if (!gpio) {
-			dev_err(pcs->dev, "failed to allocate pcs gpio\n");
-			return -ENOMEM;
-		}
-		gpio->range.name = devm_kzalloc(pcs->dev, sizeof(name),
-						GFP_KERNEL);
-		if (!gpio->range.name) {
-			dev_err(pcs->dev, "failed to allocate range name\n");
-			return -ENOMEM;
-		}
-		memcpy((char *)gpio->range.name, name, sizeof(name));
-
-		gpio->range.id = i++;
-		gpio->range.base = gpiores[0];
-		gpio->gpio_func = gpiores[1];
-		mux_bytes = pcs->width / BITS_PER_BYTE;
-		gpio->range.pin_base = (r.start - pcs->res->start) / mux_bytes;
-		gpio->range.npins = (r.end - r.start) / mux_bytes + 1;
-
-		pinctrl_add_gpio_range(pcs->pctl, &gpio->range);
-	}
-	return 0;
-}
-
 static int pcs_probe(struct platform_device *pdev)
 {
 	struct device_node *np = pdev->dev.of_node;
@@ -1046,10 +975,6 @@
 		goto free;
 	}
 
-	ret = pcs_add_gpio_range(np, pcs);
-	if (ret < 0)
-		goto free;
-
 	dev_info(pcs->dev, "%i pins at pa %p size %u\n",
 		 pcs->desc.npins, pcs->base, pcs->size);
 
diff --git a/drivers/pinctrl/pinctrl-sirf.c b/drivers/pinctrl/pinctrl-sirf.c
index 498b2ba..d02498b 100644
--- a/drivers/pinctrl/pinctrl-sirf.c
+++ b/drivers/pinctrl/pinctrl-sirf.c
@@ -1246,6 +1246,22 @@
 	return of_iomap(np, 0);
 }
 
+static int sirfsoc_gpio_of_xlate(struct gpio_chip *gc,
+       const struct of_phandle_args *gpiospec,
+       u32 *flags)
+{
+       if (gpiospec->args[0] > SIRFSOC_GPIO_NO_OF_BANKS * SIRFSOC_GPIO_BANK_SIZE)
+               return -EINVAL;
+
+       if (gc != &sgpio_bank[gpiospec->args[0] / SIRFSOC_GPIO_BANK_SIZE].chip.gc)
+               return -EINVAL;
+
+       if (flags)
+               *flags = gpiospec->args[1];
+
+       return gpiospec->args[0] % SIRFSOC_GPIO_BANK_SIZE;
+}
+
 static int sirfsoc_pinmux_probe(struct platform_device *pdev)
 {
 	int ret;
@@ -1736,6 +1752,8 @@
 		bank->chip.gc.ngpio = SIRFSOC_GPIO_BANK_SIZE;
 		bank->chip.gc.label = kstrdup(np->full_name, GFP_KERNEL);
 		bank->chip.gc.of_node = np;
+		bank->chip.gc.of_xlate = sirfsoc_gpio_of_xlate;
+		bank->chip.gc.of_gpio_n_cells = 2;
 		bank->chip.regs = regs;
 		bank->id = i;
 		bank->is_marco = is_marco;
diff --git a/drivers/platform/x86/ibm_rtl.c b/drivers/platform/x86/ibm_rtl.c
index 7481146..97c2be1 100644
--- a/drivers/platform/x86/ibm_rtl.c
+++ b/drivers/platform/x86/ibm_rtl.c
@@ -244,7 +244,7 @@
 	if (force)
 		pr_warn("module loaded by force\n");
 	/* first ensure that we are running on IBM HW */
-	else if (efi_enabled || !dmi_check_system(ibm_rtl_dmi_table))
+	else if (efi_enabled(EFI_BOOT) || !dmi_check_system(ibm_rtl_dmi_table))
 		return -ENODEV;
 
 	/* Get the address for the Extended BIOS Data Area */
diff --git a/drivers/platform/x86/samsung-laptop.c b/drivers/platform/x86/samsung-laptop.c
index 71623a2..d1f03005 100644
--- a/drivers/platform/x86/samsung-laptop.c
+++ b/drivers/platform/x86/samsung-laptop.c
@@ -26,6 +26,7 @@
 #include <linux/seq_file.h>
 #include <linux/debugfs.h>
 #include <linux/ctype.h>
+#include <linux/efi.h>
 #include <acpi/video.h>
 
 /*
@@ -1544,6 +1545,9 @@
 	struct samsung_laptop *samsung;
 	int ret;
 
+	if (efi_enabled(EFI_BOOT))
+		return -ENODEV;
+
 	quirks = &samsung_unknown;
 	if (!force && !dmi_check_system(samsung_dmi_table))
 		return -ENODEV;
diff --git a/drivers/regulator/dbx500-prcmu.c b/drivers/regulator/dbx500-prcmu.c
index 261f3d2..89bd2fa 100644
--- a/drivers/regulator/dbx500-prcmu.c
+++ b/drivers/regulator/dbx500-prcmu.c
@@ -14,6 +14,7 @@
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
+#include <linux/module.h>
 
 #include "dbx500-prcmu.h"
 
diff --git a/drivers/regulator/max77686.c b/drivers/regulator/max77686.c
index b85040c..cca18a3 100644
--- a/drivers/regulator/max77686.c
+++ b/drivers/regulator/max77686.c
@@ -379,9 +379,10 @@
 };
 
 #ifdef CONFIG_OF
-static int max77686_pmic_dt_parse_pdata(struct max77686_dev *iodev,
+static int max77686_pmic_dt_parse_pdata(struct platform_device *pdev,
 					struct max77686_platform_data *pdata)
 {
+	struct max77686_dev *iodev = dev_get_drvdata(pdev->dev.parent);
 	struct device_node *pmic_np, *regulators_np;
 	struct max77686_regulator_data *rdata;
 	struct of_regulator_match rmatch;
@@ -390,15 +391,15 @@
 	pmic_np = iodev->dev->of_node;
 	regulators_np = of_find_node_by_name(pmic_np, "voltage-regulators");
 	if (!regulators_np) {
-		dev_err(iodev->dev, "could not find regulators sub-node\n");
+		dev_err(&pdev->dev, "could not find regulators sub-node\n");
 		return -EINVAL;
 	}
 
 	pdata->num_regulators = ARRAY_SIZE(regulators);
-	rdata = devm_kzalloc(iodev->dev, sizeof(*rdata) *
+	rdata = devm_kzalloc(&pdev->dev, sizeof(*rdata) *
 			     pdata->num_regulators, GFP_KERNEL);
 	if (!rdata) {
-		dev_err(iodev->dev,
+		dev_err(&pdev->dev,
 			"could not allocate memory for regulator data\n");
 		return -ENOMEM;
 	}
@@ -407,7 +408,7 @@
 		rmatch.name = regulators[i].name;
 		rmatch.init_data = NULL;
 		rmatch.of_node = NULL;
-		of_regulator_match(iodev->dev, regulators_np, &rmatch, 1);
+		of_regulator_match(&pdev->dev, regulators_np, &rmatch, 1);
 		rdata[i].initdata = rmatch.init_data;
 		rdata[i].of_node = rmatch.of_node;
 	}
@@ -417,7 +418,7 @@
 	return 0;
 }
 #else
-static int max77686_pmic_dt_parse_pdata(struct max77686_dev *iodev,
+static int max77686_pmic_dt_parse_pdata(struct platform_device *pdev,
 					struct max77686_platform_data *pdata)
 {
 	return 0;
@@ -440,7 +441,7 @@
 	}
 
 	if (iodev->dev->of_node) {
-		ret = max77686_pmic_dt_parse_pdata(iodev, pdata);
+		ret = max77686_pmic_dt_parse_pdata(pdev, pdata);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/regulator/max8907-regulator.c b/drivers/regulator/max8907-regulator.c
index d1a7751..d40cf7f 100644
--- a/drivers/regulator/max8907-regulator.c
+++ b/drivers/regulator/max8907-regulator.c
@@ -237,8 +237,7 @@
 		return -EINVAL;
 	}
 
-	ret = of_regulator_match(pdev->dev.parent, regulators,
-				 max8907_matches,
+	ret = of_regulator_match(&pdev->dev, regulators, max8907_matches,
 				 ARRAY_SIZE(max8907_matches));
 	if (ret < 0) {
 		dev_err(&pdev->dev, "Error parsing regulator init data: %d\n",
diff --git a/drivers/regulator/max8997.c b/drivers/regulator/max8997.c
index 02be7fc..836908c 100644
--- a/drivers/regulator/max8997.c
+++ b/drivers/regulator/max8997.c
@@ -934,7 +934,7 @@
 };
 
 #ifdef CONFIG_OF
-static int max8997_pmic_dt_parse_dvs_gpio(struct max8997_dev *iodev,
+static int max8997_pmic_dt_parse_dvs_gpio(struct platform_device *pdev,
 			struct max8997_platform_data *pdata,
 			struct device_node *pmic_np)
 {
@@ -944,7 +944,7 @@
 		gpio = of_get_named_gpio(pmic_np,
 					"max8997,pmic-buck125-dvs-gpios", i);
 		if (!gpio_is_valid(gpio)) {
-			dev_err(iodev->dev, "invalid gpio[%d]: %d\n", i, gpio);
+			dev_err(&pdev->dev, "invalid gpio[%d]: %d\n", i, gpio);
 			return -EINVAL;
 		}
 		pdata->buck125_gpios[i] = gpio;
@@ -952,22 +952,23 @@
 	return 0;
 }
 
-static int max8997_pmic_dt_parse_pdata(struct max8997_dev *iodev,
+static int max8997_pmic_dt_parse_pdata(struct platform_device *pdev,
 					struct max8997_platform_data *pdata)
 {
+	struct max8997_dev *iodev = dev_get_drvdata(pdev->dev.parent);
 	struct device_node *pmic_np, *regulators_np, *reg_np;
 	struct max8997_regulator_data *rdata;
 	unsigned int i, dvs_voltage_nr = 1, ret;
 
 	pmic_np = iodev->dev->of_node;
 	if (!pmic_np) {
-		dev_err(iodev->dev, "could not find pmic sub-node\n");
+		dev_err(&pdev->dev, "could not find pmic sub-node\n");
 		return -ENODEV;
 	}
 
 	regulators_np = of_find_node_by_name(pmic_np, "regulators");
 	if (!regulators_np) {
-		dev_err(iodev->dev, "could not find regulators sub-node\n");
+		dev_err(&pdev->dev, "could not find regulators sub-node\n");
 		return -EINVAL;
 	}
 
@@ -976,11 +977,10 @@
 	for_each_child_of_node(regulators_np, reg_np)
 		pdata->num_regulators++;
 
-	rdata = devm_kzalloc(iodev->dev, sizeof(*rdata) *
+	rdata = devm_kzalloc(&pdev->dev, sizeof(*rdata) *
 				pdata->num_regulators, GFP_KERNEL);
 	if (!rdata) {
-		dev_err(iodev->dev, "could not allocate memory for "
-						"regulator data\n");
+		dev_err(&pdev->dev, "could not allocate memory for regulator data\n");
 		return -ENOMEM;
 	}
 
@@ -991,14 +991,14 @@
 				break;
 
 		if (i == ARRAY_SIZE(regulators)) {
-			dev_warn(iodev->dev, "don't know how to configure "
-				"regulator %s\n", reg_np->name);
+			dev_warn(&pdev->dev, "don't know how to configure regulator %s\n",
+				 reg_np->name);
 			continue;
 		}
 
 		rdata->id = i;
-		rdata->initdata = of_get_regulator_init_data(
-						iodev->dev, reg_np);
+		rdata->initdata = of_get_regulator_init_data(&pdev->dev,
+							     reg_np);
 		rdata->reg_node = reg_np;
 		rdata++;
 	}
@@ -1014,7 +1014,7 @@
 
 	if (pdata->buck1_gpiodvs || pdata->buck2_gpiodvs ||
 						pdata->buck5_gpiodvs) {
-		ret = max8997_pmic_dt_parse_dvs_gpio(iodev, pdata, pmic_np);
+		ret = max8997_pmic_dt_parse_dvs_gpio(pdev, pdata, pmic_np);
 		if (ret)
 			return -EINVAL;
 
@@ -1025,8 +1025,7 @@
 		} else {
 			if (pdata->buck125_default_idx >= 8) {
 				pdata->buck125_default_idx = 0;
-				dev_info(iodev->dev, "invalid value for "
-				"default dvs index, using 0 instead\n");
+				dev_info(&pdev->dev, "invalid value for default dvs index, using 0 instead\n");
 			}
 		}
 
@@ -1040,28 +1039,28 @@
 	if (of_property_read_u32_array(pmic_np,
 				"max8997,pmic-buck1-dvs-voltage",
 				pdata->buck1_voltage, dvs_voltage_nr)) {
-		dev_err(iodev->dev, "buck1 voltages not specified\n");
+		dev_err(&pdev->dev, "buck1 voltages not specified\n");
 		return -EINVAL;
 	}
 
 	if (of_property_read_u32_array(pmic_np,
 				"max8997,pmic-buck2-dvs-voltage",
 				pdata->buck2_voltage, dvs_voltage_nr)) {
-		dev_err(iodev->dev, "buck2 voltages not specified\n");
+		dev_err(&pdev->dev, "buck2 voltages not specified\n");
 		return -EINVAL;
 	}
 
 	if (of_property_read_u32_array(pmic_np,
 				"max8997,pmic-buck5-dvs-voltage",
 				pdata->buck5_voltage, dvs_voltage_nr)) {
-		dev_err(iodev->dev, "buck5 voltages not specified\n");
+		dev_err(&pdev->dev, "buck5 voltages not specified\n");
 		return -EINVAL;
 	}
 
 	return 0;
 }
 #else
-static int max8997_pmic_dt_parse_pdata(struct max8997_dev *iodev,
+static int max8997_pmic_dt_parse_pdata(struct platform_device *pdev,
 					struct max8997_platform_data *pdata)
 {
 	return 0;
@@ -1085,7 +1084,7 @@
 	}
 
 	if (iodev->dev->of_node) {
-		ret = max8997_pmic_dt_parse_pdata(iodev, pdata);
+		ret = max8997_pmic_dt_parse_pdata(pdev, pdata);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/regulator/max8998.c b/drivers/regulator/max8998.c
index 1f0df40..0a8dd1c 100644
--- a/drivers/regulator/max8998.c
+++ b/drivers/regulator/max8998.c
@@ -65,7 +65,7 @@
 	.min = 2800000,	.step = 100000,	.max = 3100000,
 };
 static const struct voltage_map_desc ldo10_voltage_map_desc = {
-	.min = 95000,	.step = 50000,	.max = 1300000,
+	.min = 950000,	.step = 50000,	.max = 1300000,
 };
 static const struct voltage_map_desc ldo1213_voltage_map_desc = {
 	.min = 800000,	.step = 100000,	.max = 3300000,
diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c
index 6f68491..66ca769 100644
--- a/drivers/regulator/of_regulator.c
+++ b/drivers/regulator/of_regulator.c
@@ -120,6 +120,12 @@
 	if (!dev || !node)
 		return -EINVAL;
 
+	for (i = 0; i < num_matches; i++) {
+		struct of_regulator_match *match = &matches[i];
+		match->init_data = NULL;
+		match->of_node = NULL;
+	}
+
 	for_each_child_of_node(node, child) {
 		name = of_get_property(child,
 					"regulator-compatible", NULL);
diff --git a/drivers/regulator/s2mps11.c b/drivers/regulator/s2mps11.c
index bd062a2..cd9ea2e 100644
--- a/drivers/regulator/s2mps11.c
+++ b/drivers/regulator/s2mps11.c
@@ -174,9 +174,9 @@
 	.min_uV		= S2MPS11_BUCK_MIN2,			\
 	.uV_step	= S2MPS11_BUCK_STEP2,			\
 	.n_voltages	= S2MPS11_BUCK_N_VOLTAGES,		\
-	.vsel_reg	= S2MPS11_REG_B9CTRL2,			\
+	.vsel_reg	= S2MPS11_REG_B10CTRL2,			\
 	.vsel_mask	= S2MPS11_BUCK_VSEL_MASK,		\
-	.enable_reg	= S2MPS11_REG_B9CTRL1,			\
+	.enable_reg	= S2MPS11_REG_B10CTRL1,			\
 	.enable_mask	= S2MPS11_ENABLE_MASK			\
 }
 
diff --git a/drivers/regulator/tps65217-regulator.c b/drivers/regulator/tps65217-regulator.c
index 73dce76..df39518 100644
--- a/drivers/regulator/tps65217-regulator.c
+++ b/drivers/regulator/tps65217-regulator.c
@@ -305,8 +305,8 @@
 	if (!regs)
 		return NULL;
 
-	count = of_regulator_match(pdev->dev.parent, regs,
-				reg_matches, TPS65217_NUM_REGULATOR);
+	count = of_regulator_match(&pdev->dev, regs, reg_matches,
+				   TPS65217_NUM_REGULATOR);
 	of_node_put(regs);
 	if ((count < 0) || (count > TPS65217_NUM_REGULATOR))
 		return NULL;
diff --git a/drivers/regulator/tps65910-regulator.c b/drivers/regulator/tps65910-regulator.c
index 59c3770..b0e4c0b 100644
--- a/drivers/regulator/tps65910-regulator.c
+++ b/drivers/regulator/tps65910-regulator.c
@@ -998,7 +998,7 @@
 		return NULL;
 	}
 
-	ret = of_regulator_match(pdev->dev.parent, regulators, matches, count);
+	ret = of_regulator_match(&pdev->dev, regulators, matches, count);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "Error parsing regulator init data: %d\n",
 			ret);
diff --git a/drivers/regulator/tps80031-regulator.c b/drivers/regulator/tps80031-regulator.c
index b15d711..9019d0e 100644
--- a/drivers/regulator/tps80031-regulator.c
+++ b/drivers/regulator/tps80031-regulator.c
@@ -728,7 +728,7 @@
 			}
 		}
 		rdev = regulator_register(&ri->rinfo->desc, &config);
-		if (IS_ERR_OR_NULL(rdev)) {
+		if (IS_ERR(rdev)) {
 			dev_err(&pdev->dev,
 				"register regulator failed %s\n",
 					ri->rinfo->desc.name);
diff --git a/drivers/rtc/rtc-isl1208.c b/drivers/rtc/rtc-isl1208.c
index afb7cfa..c016ad8 100644
--- a/drivers/rtc/rtc-isl1208.c
+++ b/drivers/rtc/rtc-isl1208.c
@@ -506,6 +506,7 @@
 {
 	unsigned long timeout = jiffies + msecs_to_jiffies(1000);
 	struct i2c_client *client = data;
+	struct rtc_device *rtc = i2c_get_clientdata(client);
 	int handled = 0, sr, err;
 
 	/*
@@ -528,6 +529,8 @@
 	if (sr & ISL1208_REG_SR_ALM) {
 		dev_dbg(&client->dev, "alarm!\n");
 
+		rtc_update_irq(rtc, 1, RTC_IRQF | RTC_AF);
+
 		/* Clear the alarm */
 		sr &= ~ISL1208_REG_SR_ALM;
 		sr = i2c_smbus_write_byte_data(client, ISL1208_REG_SR, sr);
diff --git a/drivers/rtc/rtc-pl031.c b/drivers/rtc/rtc-pl031.c
index 08378e3..81c5077 100644
--- a/drivers/rtc/rtc-pl031.c
+++ b/drivers/rtc/rtc-pl031.c
@@ -44,6 +44,7 @@
 #define RTC_YMR		0x34	/* Year match register */
 #define RTC_YLR		0x38	/* Year data load register */
 
+#define RTC_CR_EN	(1 << 0)	/* counter enable bit */
 #define RTC_CR_CWEN	(1 << 26)	/* Clockwatch enable bit */
 
 #define RTC_TCR_EN	(1 << 1) /* Periodic timer enable bit */
@@ -320,7 +321,7 @@
 	struct pl031_local *ldata;
 	struct pl031_vendor_data *vendor = id->data;
 	struct rtc_class_ops *ops = &vendor->ops;
-	unsigned long time;
+	unsigned long time, data;
 
 	ret = amba_request_regions(adev, NULL);
 	if (ret)
@@ -345,10 +346,13 @@
 	dev_dbg(&adev->dev, "designer ID = 0x%02x\n", amba_manf(adev));
 	dev_dbg(&adev->dev, "revision = 0x%01x\n", amba_rev(adev));
 
+	data = readl(ldata->base + RTC_CR);
 	/* Enable the clockwatch on ST Variants */
 	if (vendor->clockwatch)
-		writel(readl(ldata->base + RTC_CR) | RTC_CR_CWEN,
-		       ldata->base + RTC_CR);
+		data |= RTC_CR_CWEN;
+	else
+		data |= RTC_CR_EN;
+	writel(data, ldata->base + RTC_CR);
 
 	/*
 	 * On ST PL031 variants, the RTC reset value does not provide correct
diff --git a/drivers/rtc/rtc-vt8500.c b/drivers/rtc/rtc-vt8500.c
index 00c930f..2730533 100644
--- a/drivers/rtc/rtc-vt8500.c
+++ b/drivers/rtc/rtc-vt8500.c
@@ -137,7 +137,7 @@
 		return -EINVAL;
 	}
 
-	writel((bin2bcd(tm->tm_year - 100) << DATE_YEAR_S)
+	writel((bin2bcd(tm->tm_year % 100) << DATE_YEAR_S)
 		| (bin2bcd(tm->tm_mon + 1) << DATE_MONTH_S)
 		| (bin2bcd(tm->tm_mday))
 		| ((tm->tm_year >= 200) << DATE_CENTURY_S),
diff --git a/drivers/scsi/isci/init.c b/drivers/scsi/isci/init.c
index d73fdcf..2839baa 100644
--- a/drivers/scsi/isci/init.c
+++ b/drivers/scsi/isci/init.c
@@ -633,7 +633,7 @@
 		return -ENOMEM;
 	pci_set_drvdata(pdev, pci_info);
 
-	if (efi_enabled)
+	if (efi_enabled(EFI_RUNTIME_SERVICES))
 		orom = isci_get_efi_var(pdev);
 
 	if (!orom)
diff --git a/drivers/ssb/driver_gpio.c b/drivers/ssb/driver_gpio.c
index 97ac0a3..eb27530 100644
--- a/drivers/ssb/driver_gpio.c
+++ b/drivers/ssb/driver_gpio.c
@@ -174,3 +174,15 @@
 
 	return -1;
 }
+
+int ssb_gpio_unregister(struct ssb_bus *bus)
+{
+	if (ssb_chipco_available(&bus->chipco) ||
+	    ssb_extif_available(&bus->extif)) {
+		return gpiochip_remove(&bus->gpio);
+	} else {
+		SSB_WARN_ON(1);
+	}
+
+	return -1;
+}
diff --git a/drivers/ssb/main.c b/drivers/ssb/main.c
index 772ad9b..24dc331 100644
--- a/drivers/ssb/main.c
+++ b/drivers/ssb/main.c
@@ -443,6 +443,15 @@
 
 void ssb_bus_unregister(struct ssb_bus *bus)
 {
+	int err;
+
+	err = ssb_gpio_unregister(bus);
+	if (err == -EBUSY)
+		ssb_dprintk(KERN_ERR PFX "Some GPIOs are still in use.\n");
+	else if (err)
+		ssb_dprintk(KERN_ERR PFX
+			    "Can not unregister GPIO driver: %i\n", err);
+
 	ssb_buses_lock();
 	ssb_devices_unregister(bus);
 	list_del(&bus->list);
diff --git a/drivers/ssb/ssb_private.h b/drivers/ssb/ssb_private.h
index 6c10b66..da38305 100644
--- a/drivers/ssb/ssb_private.h
+++ b/drivers/ssb/ssb_private.h
@@ -252,11 +252,16 @@
 
 #ifdef CONFIG_SSB_DRIVER_GPIO
 extern int ssb_gpio_init(struct ssb_bus *bus);
+extern int ssb_gpio_unregister(struct ssb_bus *bus);
 #else /* CONFIG_SSB_DRIVER_GPIO */
 static inline int ssb_gpio_init(struct ssb_bus *bus)
 {
 	return -ENOTSUPP;
 }
+static inline int ssb_gpio_unregister(struct ssb_bus *bus)
+{
+	return 0;
+}
 #endif /* CONFIG_SSB_DRIVER_GPIO */
 
 #endif /* LINUX_SSB_PRIVATE_H_ */
diff --git a/drivers/staging/iio/trigger/Kconfig b/drivers/staging/iio/trigger/Kconfig
index 7d32075..d44d3ad 100644
--- a/drivers/staging/iio/trigger/Kconfig
+++ b/drivers/staging/iio/trigger/Kconfig
@@ -21,7 +21,6 @@
 config IIO_SYSFS_TRIGGER
 	tristate "SYSFS trigger"
 	depends on SYSFS
-	depends on HAVE_IRQ_WORK
 	select IRQ_WORK
 	help
 	  Provides support for using SYSFS entry as IIO triggers.
diff --git a/drivers/staging/omapdrm/Kconfig b/drivers/staging/omapdrm/Kconfig
index b724a41..09f65dc 100644
--- a/drivers/staging/omapdrm/Kconfig
+++ b/drivers/staging/omapdrm/Kconfig
@@ -3,8 +3,8 @@
 	tristate "OMAP DRM"
 	depends on DRM && !CONFIG_FB_OMAP2
 	depends on ARCH_OMAP2PLUS || ARCH_MULTIPLATFORM
+	depends on OMAP2_DSS
 	select DRM_KMS_HELPER
-	select OMAP2_DSS
 	select FB_SYS_FILLRECT
 	select FB_SYS_COPYAREA
 	select FB_SYS_IMAGEBLIT
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index e269510..f2aa754 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -941,6 +941,8 @@
 
 int se_dev_set_fabric_max_sectors(struct se_device *dev, u32 fabric_max_sectors)
 {
+	int block_size = dev->dev_attrib.block_size;
+
 	if (dev->export_count) {
 		pr_err("dev[%p]: Unable to change SE Device"
 			" fabric_max_sectors while export_count is %d\n",
@@ -978,8 +980,12 @@
 	/*
 	 * Align max_sectors down to PAGE_SIZE to follow transport_allocate_data_tasks()
 	 */
+	if (!block_size) {
+		block_size = 512;
+		pr_warn("Defaulting to 512 for zero block_size\n");
+	}
 	fabric_max_sectors = se_dev_align_max_sectors(fabric_max_sectors,
-						      dev->dev_attrib.block_size);
+						      block_size);
 
 	dev->dev_attrib.fabric_max_sectors = fabric_max_sectors;
 	pr_debug("dev[%p]: SE Device max_sectors changed to %u\n",
diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c
index 810263d..c57bbbc 100644
--- a/drivers/target/target_core_fabric_configfs.c
+++ b/drivers/target/target_core_fabric_configfs.c
@@ -754,6 +754,11 @@
 		return -EFAULT;
 	}
 
+	if (!(dev->dev_flags & DF_CONFIGURED)) {
+		pr_err("se_device not configured yet, cannot port link\n");
+		return -ENODEV;
+	}
+
 	tpg_ci = &lun_ci->ci_parent->ci_group->cg_item;
 	se_tpg = container_of(to_config_group(tpg_ci),
 				struct se_portal_group, tpg_group);
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index 26a6d18..a664c66 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -58,11 +58,10 @@
 	buf[7] = dev->dev_attrib.block_size & 0xff;
 
 	rbuf = transport_kmap_data_sg(cmd);
-	if (!rbuf)
-		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-
-	memcpy(rbuf, buf, min_t(u32, sizeof(buf), cmd->data_length));
-	transport_kunmap_data_sg(cmd);
+	if (rbuf) {
+		memcpy(rbuf, buf, min_t(u32, sizeof(buf), cmd->data_length));
+		transport_kunmap_data_sg(cmd);
+	}
 
 	target_complete_cmd(cmd, GOOD);
 	return 0;
@@ -97,11 +96,10 @@
 		buf[14] = 0x80;
 
 	rbuf = transport_kmap_data_sg(cmd);
-	if (!rbuf)
-		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-
-	memcpy(rbuf, buf, min_t(u32, sizeof(buf), cmd->data_length));
-	transport_kunmap_data_sg(cmd);
+	if (rbuf) {
+		memcpy(rbuf, buf, min_t(u32, sizeof(buf), cmd->data_length));
+		transport_kunmap_data_sg(cmd);
+	}
 
 	target_complete_cmd(cmd, GOOD);
 	return 0;
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index 84f9e96..2d88f08 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -641,11 +641,10 @@
 
 out:
 	rbuf = transport_kmap_data_sg(cmd);
-	if (!rbuf)
-		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-
-	memcpy(rbuf, buf, min_t(u32, sizeof(buf), cmd->data_length));
-	transport_kunmap_data_sg(cmd);
+	if (rbuf) {
+		memcpy(rbuf, buf, min_t(u32, sizeof(buf), cmd->data_length));
+		transport_kunmap_data_sg(cmd);
+	}
 
 	if (!ret)
 		target_complete_cmd(cmd, GOOD);
@@ -851,7 +850,7 @@
 {
 	struct se_device *dev = cmd->se_dev;
 	char *cdb = cmd->t_task_cdb;
-	unsigned char *buf, *map_buf;
+	unsigned char buf[SE_MODE_PAGE_BUF], *rbuf;
 	int type = dev->transport->get_device_type(dev);
 	int ten = (cmd->t_task_cdb[0] == MODE_SENSE_10);
 	bool dbd = !!(cdb[1] & 0x08);
@@ -863,26 +862,8 @@
 	int ret;
 	int i;
 
-	map_buf = transport_kmap_data_sg(cmd);
-	if (!map_buf)
-		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-	/*
-	 * If SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC is not set, then we
-	 * know we actually allocated a full page.  Otherwise, if the
-	 * data buffer is too small, allocate a temporary buffer so we
-	 * don't have to worry about overruns in all our INQUIRY
-	 * emulation handling.
-	 */
-	if (cmd->data_length < SE_MODE_PAGE_BUF &&
-	    (cmd->se_cmd_flags & SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC)) {
-		buf = kzalloc(SE_MODE_PAGE_BUF, GFP_KERNEL);
-		if (!buf) {
-			transport_kunmap_data_sg(cmd);
-			return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-		}
-	} else {
-		buf = map_buf;
-	}
+	memset(buf, 0, SE_MODE_PAGE_BUF);
+
 	/*
 	 * Skip over MODE DATA LENGTH + MEDIUM TYPE fields to byte 3 for
 	 * MODE_SENSE_10 and byte 2 for MODE_SENSE (6).
@@ -934,8 +915,6 @@
 	if (page == 0x3f) {
 		if (subpage != 0x00 && subpage != 0xff) {
 			pr_warn("MODE_SENSE: Invalid subpage code: 0x%02x\n", subpage);
-			kfree(buf);
-			transport_kunmap_data_sg(cmd);
 			return TCM_INVALID_CDB_FIELD;
 		}
 
@@ -972,7 +951,6 @@
 		pr_err("MODE SENSE: unimplemented page/subpage: 0x%02x/0x%02x\n",
 		       page, subpage);
 
-	transport_kunmap_data_sg(cmd);
 	return TCM_UNKNOWN_MODE_PAGE;
 
 set_length:
@@ -981,12 +959,12 @@
 	else
 		buf[0] = length - 1;
 
-	if (buf != map_buf) {
-		memcpy(map_buf, buf, cmd->data_length);
-		kfree(buf);
+	rbuf = transport_kmap_data_sg(cmd);
+	if (rbuf) {
+		memcpy(rbuf, buf, min_t(u32, SE_MODE_PAGE_BUF, cmd->data_length));
+		transport_kunmap_data_sg(cmd);
 	}
 
-	transport_kunmap_data_sg(cmd);
 	target_complete_cmd(cmd, GOOD);
 	return 0;
 }
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 4225d5e..8e64adf 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -39,6 +39,7 @@
 #include <asm/unaligned.h>
 #include <linux/platform_device.h>
 #include <linux/workqueue.h>
+#include <linux/pm_runtime.h>
 
 #include <linux/usb.h>
 #include <linux/usb/hcd.h>
@@ -1025,6 +1026,49 @@
 	return retval;
 }
 
+/*
+ * usb_hcd_start_port_resume - a root-hub port is sending a resume signal
+ * @bus: the bus which the root hub belongs to
+ * @portnum: the port which is being resumed
+ *
+ * HCDs should call this function when they know that a resume signal is
+ * being sent to a root-hub port.  The root hub will be prevented from
+ * going into autosuspend until usb_hcd_end_port_resume() is called.
+ *
+ * The bus's private lock must be held by the caller.
+ */
+void usb_hcd_start_port_resume(struct usb_bus *bus, int portnum)
+{
+	unsigned bit = 1 << portnum;
+
+	if (!(bus->resuming_ports & bit)) {
+		bus->resuming_ports |= bit;
+		pm_runtime_get_noresume(&bus->root_hub->dev);
+	}
+}
+EXPORT_SYMBOL_GPL(usb_hcd_start_port_resume);
+
+/*
+ * usb_hcd_end_port_resume - a root-hub port has stopped sending a resume signal
+ * @bus: the bus which the root hub belongs to
+ * @portnum: the port which is being resumed
+ *
+ * HCDs should call this function when they know that a resume signal has
+ * stopped being sent to a root-hub port.  The root hub will be allowed to
+ * autosuspend again.
+ *
+ * The bus's private lock must be held by the caller.
+ */
+void usb_hcd_end_port_resume(struct usb_bus *bus, int portnum)
+{
+	unsigned bit = 1 << portnum;
+
+	if (bus->resuming_ports & bit) {
+		bus->resuming_ports &= ~bit;
+		pm_runtime_put_noidle(&bus->root_hub->dev);
+	}
+}
+EXPORT_SYMBOL_GPL(usb_hcd_end_port_resume);
 
 /*-------------------------------------------------------------------------*/
 
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 957ed2c..cbf7168 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -2838,6 +2838,23 @@
 EXPORT_SYMBOL_GPL(usb_enable_ltm);
 
 #ifdef	CONFIG_USB_SUSPEND
+/*
+ * usb_disable_function_remotewakeup - disable usb3.0
+ * device's function remote wakeup
+ * @udev: target device
+ *
+ * Assume there's only one function on the USB 3.0
+ * device and disable remote wake for the first
+ * interface. FIXME if the interface association
+ * descriptor shows there's more than one function.
+ */
+static int usb_disable_function_remotewakeup(struct usb_device *udev)
+{
+	return usb_control_msg(udev, usb_sndctrlpipe(udev, 0),
+				USB_REQ_CLEAR_FEATURE, USB_RECIP_INTERFACE,
+				USB_INTRF_FUNC_SUSPEND,	0, NULL, 0,
+				USB_CTRL_SET_TIMEOUT);
+}
 
 /*
  * usb_port_suspend - suspend a usb device's upstream port
@@ -2955,12 +2972,19 @@
 		dev_dbg(hub->intfdev, "can't suspend port %d, status %d\n",
 				port1, status);
 		/* paranoia:  "should not happen" */
-		if (udev->do_remote_wakeup)
-			(void) usb_control_msg(udev, usb_sndctrlpipe(udev, 0),
-				USB_REQ_CLEAR_FEATURE, USB_RECIP_DEVICE,
-				USB_DEVICE_REMOTE_WAKEUP, 0,
-				NULL, 0,
-				USB_CTRL_SET_TIMEOUT);
+		if (udev->do_remote_wakeup) {
+			if (!hub_is_superspeed(hub->hdev)) {
+				(void) usb_control_msg(udev,
+						usb_sndctrlpipe(udev, 0),
+						USB_REQ_CLEAR_FEATURE,
+						USB_RECIP_DEVICE,
+						USB_DEVICE_REMOTE_WAKEUP, 0,
+						NULL, 0,
+						USB_CTRL_SET_TIMEOUT);
+			} else
+				(void) usb_disable_function_remotewakeup(udev);
+
+		}
 
 		/* Try to enable USB2 hardware LPM again */
 		if (udev->usb2_hw_lpm_capable == 1)
@@ -3052,20 +3076,30 @@
 	 * udev->reset_resume
 	 */
 	} else if (udev->actconfig && !udev->reset_resume) {
-		le16_to_cpus(&devstatus);
-		if (devstatus & (1 << USB_DEVICE_REMOTE_WAKEUP)) {
-			status = usb_control_msg(udev,
-					usb_sndctrlpipe(udev, 0),
-					USB_REQ_CLEAR_FEATURE,
+		if (!hub_is_superspeed(udev->parent)) {
+			le16_to_cpus(&devstatus);
+			if (devstatus & (1 << USB_DEVICE_REMOTE_WAKEUP))
+				status = usb_control_msg(udev,
+						usb_sndctrlpipe(udev, 0),
+						USB_REQ_CLEAR_FEATURE,
 						USB_RECIP_DEVICE,
-					USB_DEVICE_REMOTE_WAKEUP, 0,
-					NULL, 0,
-					USB_CTRL_SET_TIMEOUT);
-			if (status)
-				dev_dbg(&udev->dev,
-					"disable remote wakeup, status %d\n",
-					status);
+						USB_DEVICE_REMOTE_WAKEUP, 0,
+						NULL, 0,
+						USB_CTRL_SET_TIMEOUT);
+		} else {
+			status = usb_get_status(udev, USB_RECIP_INTERFACE, 0,
+					&devstatus);
+			le16_to_cpus(&devstatus);
+			if (!status && devstatus & (USB_INTRF_STAT_FUNC_RW_CAP
+					| USB_INTRF_STAT_FUNC_RW))
+				status =
+					usb_disable_function_remotewakeup(udev);
 		}
+
+		if (status)
+			dev_dbg(&udev->dev,
+				"disable remote wakeup, status %d\n",
+				status);
 		status = 0;
 	}
 	return status;
diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c
index 09537b2..b416a3f 100644
--- a/drivers/usb/host/ehci-hcd.c
+++ b/drivers/usb/host/ehci-hcd.c
@@ -797,6 +797,7 @@
 			ehci->reset_done[i] = jiffies + msecs_to_jiffies(25);
 			set_bit(i, &ehci->resuming_ports);
 			ehci_dbg (ehci, "port %d remote wakeup\n", i + 1);
+			usb_hcd_start_port_resume(&hcd->self, i);
 			mod_timer(&hcd->rh_timer, ehci->reset_done[i]);
 		}
 	}
diff --git a/drivers/usb/host/ehci-hub.c b/drivers/usb/host/ehci-hub.c
index 4ccb97c..4d3b294 100644
--- a/drivers/usb/host/ehci-hub.c
+++ b/drivers/usb/host/ehci-hub.c
@@ -649,7 +649,11 @@
 			status = STS_PCD;
 		}
 	}
-	/* FIXME autosuspend idle root hubs */
+
+	/* If a resume is in progress, make sure it can finish */
+	if (ehci->resuming_ports)
+		mod_timer(&hcd->rh_timer, jiffies + msecs_to_jiffies(25));
+
 	spin_unlock_irqrestore (&ehci->lock, flags);
 	return status ? retval : 0;
 }
@@ -851,6 +855,7 @@
 				/* resume signaling for 20 msec */
 				ehci->reset_done[wIndex] = jiffies
 						+ msecs_to_jiffies(20);
+				usb_hcd_start_port_resume(&hcd->self, wIndex);
 				/* check the port again */
 				mod_timer(&ehci_to_hcd(ehci)->rh_timer,
 						ehci->reset_done[wIndex]);
@@ -862,6 +867,7 @@
 				clear_bit(wIndex, &ehci->suspended_ports);
 				set_bit(wIndex, &ehci->port_c_suspend);
 				ehci->reset_done[wIndex] = 0;
+				usb_hcd_end_port_resume(&hcd->self, wIndex);
 
 				/* stop resume signaling */
 				temp = ehci_readl(ehci, status_reg);
@@ -950,6 +956,7 @@
 			ehci->reset_done[wIndex] = 0;
 			if (temp & PORT_PE)
 				set_bit(wIndex, &ehci->port_c_suspend);
+			usb_hcd_end_port_resume(&hcd->self, wIndex);
 		}
 
 		if (temp & PORT_OC)
diff --git a/drivers/usb/host/ehci-q.c b/drivers/usb/host/ehci-q.c
index 3d98902..fd252f0 100644
--- a/drivers/usb/host/ehci-q.c
+++ b/drivers/usb/host/ehci-q.c
@@ -1197,17 +1197,26 @@
 	if (ehci->async_iaa || ehci->async_unlinking)
 		return;
 
-	/* Do all the waiting QHs at once */
-	ehci->async_iaa = ehci->async_unlink;
-	ehci->async_unlink = NULL;
-
 	/* If the controller isn't running, we don't have to wait for it */
 	if (unlikely(ehci->rh_state < EHCI_RH_RUNNING)) {
+
+		/* Do all the waiting QHs */
+		ehci->async_iaa = ehci->async_unlink;
+		ehci->async_unlink = NULL;
+
 		if (!nested)		/* Avoid recursion */
 			end_unlink_async(ehci);
 
 	/* Otherwise start a new IAA cycle */
 	} else if (likely(ehci->rh_state == EHCI_RH_RUNNING)) {
+		struct ehci_qh		*qh;
+
+		/* Do only the first waiting QH (nVidia bug?) */
+		qh = ehci->async_unlink;
+		ehci->async_iaa = qh;
+		ehci->async_unlink = qh->unlink_next;
+		qh->unlink_next = NULL;
+
 		/* Make sure the unlinks are all visible to the hardware */
 		wmb();
 
@@ -1255,34 +1264,35 @@
 	}
 }
 
+static void start_unlink_async(struct ehci_hcd *ehci, struct ehci_qh *qh);
+
 static void unlink_empty_async(struct ehci_hcd *ehci)
 {
-	struct ehci_qh		*qh, *next;
-	bool			stopped = (ehci->rh_state < EHCI_RH_RUNNING);
+	struct ehci_qh		*qh;
+	struct ehci_qh		*qh_to_unlink = NULL;
 	bool			check_unlinks_later = false;
+	int			count = 0;
 
-	/* Unlink all the async QHs that have been empty for a timer cycle */
-	next = ehci->async->qh_next.qh;
-	while (next) {
-		qh = next;
-		next = qh->qh_next.qh;
-
+	/* Find the last async QH which has been empty for a timer cycle */
+	for (qh = ehci->async->qh_next.qh; qh; qh = qh->qh_next.qh) {
 		if (list_empty(&qh->qtd_list) &&
 				qh->qh_state == QH_STATE_LINKED) {
-			if (!stopped && qh->unlink_cycle ==
-					ehci->async_unlink_cycle)
+			++count;
+			if (qh->unlink_cycle == ehci->async_unlink_cycle)
 				check_unlinks_later = true;
 			else
-				single_unlink_async(ehci, qh);
+				qh_to_unlink = qh;
 		}
 	}
 
-	/* Start a new IAA cycle if any QHs are waiting for it */
-	if (ehci->async_unlink)
-		start_iaa_cycle(ehci, false);
+	/* If nothing else is being unlinked, unlink the last empty QH */
+	if (!ehci->async_iaa && !ehci->async_unlink && qh_to_unlink) {
+		start_unlink_async(ehci, qh_to_unlink);
+		--count;
+	}
 
-	/* QHs that haven't been empty for long enough will be handled later */
-	if (check_unlinks_later) {
+	/* Other QHs will be handled later */
+	if (count > 0) {
 		ehci_enable_event(ehci, EHCI_HRTIMER_ASYNC_UNLINKS, true);
 		++ehci->async_unlink_cycle;
 	}
diff --git a/drivers/usb/host/ehci-sched.c b/drivers/usb/host/ehci-sched.c
index 69ebee7..b476daf 100644
--- a/drivers/usb/host/ehci-sched.c
+++ b/drivers/usb/host/ehci-sched.c
@@ -213,7 +213,7 @@
 }
 
 static const unsigned char
-max_tt_usecs[] = { 125, 125, 125, 125, 125, 125, 30, 0 };
+max_tt_usecs[] = { 125, 125, 125, 125, 125, 125, 125, 25 };
 
 /* carryover low/fullspeed bandwidth that crosses uframe boundries */
 static inline void carryover_tt_bandwidth(unsigned short tt_usecs[8])
@@ -2212,11 +2212,11 @@
 	}
 	ehci->now_frame = now_frame;
 
+	frame = ehci->last_iso_frame;
 	for (;;) {
 		union ehci_shadow	q, *q_p;
 		__hc32			type, *hw_p;
 
-		frame = ehci->last_iso_frame;
 restart:
 		/* scan each element in frame's queue for completions */
 		q_p = &ehci->pshadow [frame];
@@ -2321,6 +2321,9 @@
 		/* Stop when we have reached the current frame */
 		if (frame == now_frame)
 			break;
-		ehci->last_iso_frame = (frame + 1) & fmask;
+
+		/* The last frame may still have active siTDs */
+		ehci->last_iso_frame = frame;
+		frame = (frame + 1) & fmask;
 	}
 }
diff --git a/drivers/usb/host/ehci-timer.c b/drivers/usb/host/ehci-timer.c
index 20dbdcb..f904071 100644
--- a/drivers/usb/host/ehci-timer.c
+++ b/drivers/usb/host/ehci-timer.c
@@ -113,14 +113,15 @@
 
 	if (want != actual) {
 
-		/* Poll again later, but give up after about 20 ms */
-		if (ehci->ASS_poll_count++ < 20) {
-			ehci_enable_event(ehci, EHCI_HRTIMER_POLL_ASS, true);
-			return;
-		}
-		ehci_dbg(ehci, "Waited too long for the async schedule status (%x/%x), giving up\n",
-				want, actual);
+		/* Poll again later */
+		ehci_enable_event(ehci, EHCI_HRTIMER_POLL_ASS, true);
+		++ehci->ASS_poll_count;
+		return;
 	}
+
+	if (ehci->ASS_poll_count > 20)
+		ehci_dbg(ehci, "ASS poll count reached %d\n",
+				ehci->ASS_poll_count);
 	ehci->ASS_poll_count = 0;
 
 	/* The status is up-to-date; restart or stop the schedule as needed */
@@ -159,14 +160,14 @@
 
 	if (want != actual) {
 
-		/* Poll again later, but give up after about 20 ms */
-		if (ehci->PSS_poll_count++ < 20) {
-			ehci_enable_event(ehci, EHCI_HRTIMER_POLL_PSS, true);
-			return;
-		}
-		ehci_dbg(ehci, "Waited too long for the periodic schedule status (%x/%x), giving up\n",
-				want, actual);
+		/* Poll again later */
+		ehci_enable_event(ehci, EHCI_HRTIMER_POLL_PSS, true);
+		return;
 	}
+
+	if (ehci->PSS_poll_count > 20)
+		ehci_dbg(ehci, "PSS poll count reached %d\n",
+				ehci->PSS_poll_count);
 	ehci->PSS_poll_count = 0;
 
 	/* The status is up-to-date; restart or stop the schedule as needed */
diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c
index a3b6d71..4c338ec 100644
--- a/drivers/usb/host/pci-quirks.c
+++ b/drivers/usb/host/pci-quirks.c
@@ -780,6 +780,7 @@
 				"defaulting to EHCI.\n");
 		dev_warn(&xhci_pdev->dev,
 				"USB 3.0 devices will work at USB 2.0 speeds.\n");
+		usb_disable_xhci_ports(xhci_pdev);
 		return;
 	}
 
diff --git a/drivers/usb/host/uhci-hub.c b/drivers/usb/host/uhci-hub.c
index 768d542..15d1322 100644
--- a/drivers/usb/host/uhci-hub.c
+++ b/drivers/usb/host/uhci-hub.c
@@ -116,6 +116,7 @@
 		}
 	}
 	clear_bit(port, &uhci->resuming_ports);
+	usb_hcd_end_port_resume(&uhci_to_hcd(uhci)->self, port);
 }
 
 /* Wait for the UHCI controller in HP's iLO2 server management chip.
@@ -167,6 +168,8 @@
 				set_bit(port, &uhci->resuming_ports);
 				uhci->ports_timeout = jiffies +
 						msecs_to_jiffies(25);
+				usb_hcd_start_port_resume(
+						&uhci_to_hcd(uhci)->self, port);
 
 				/* Make sure we see the port again
 				 * after the resuming period is over. */
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 59fb5c6..7f76a49 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -1698,7 +1698,7 @@
 				faked_port_index + 1);
 		if (slot_id && xhci->devs[slot_id])
 			xhci_ring_device(xhci, slot_id);
-		if (bus_state->port_remote_wakeup && (1 << faked_port_index)) {
+		if (bus_state->port_remote_wakeup & (1 << faked_port_index)) {
 			bus_state->port_remote_wakeup &=
 				~(1 << faked_port_index);
 			xhci_test_and_clear_bit(xhci, port_array,
@@ -2589,6 +2589,8 @@
 				(trb_comp_code != COMP_STALL &&
 					trb_comp_code != COMP_BABBLE))
 				xhci_urb_free_priv(xhci, urb_priv);
+			else
+				kfree(urb_priv);
 
 			usb_hcd_unlink_urb_from_ep(bus_to_hcd(urb->dev->bus), urb);
 			if ((urb->actual_length != urb->transfer_buffer_length &&
@@ -3108,7 +3110,7 @@
 	 * running_total.
 	 */
 	packets_transferred = (running_total + trb_buff_len) /
-		usb_endpoint_maxp(&urb->ep->desc);
+		GET_MAX_PACKET(usb_endpoint_maxp(&urb->ep->desc));
 
 	if ((total_packet_count - packets_transferred) > 31)
 		return 31 << 17;
@@ -3642,7 +3644,8 @@
 		td_len = urb->iso_frame_desc[i].length;
 		td_remain_len = td_len;
 		total_packet_count = DIV_ROUND_UP(td_len,
-				usb_endpoint_maxp(&urb->ep->desc));
+				GET_MAX_PACKET(
+					usb_endpoint_maxp(&urb->ep->desc)));
 		/* A zero-length transfer still involves at least one packet. */
 		if (total_packet_count == 0)
 			total_packet_count++;
@@ -3664,9 +3667,11 @@
 		td = urb_priv->td[i];
 		for (j = 0; j < trbs_per_td; j++) {
 			u32 remainder = 0;
-			field = TRB_TBC(burst_count) | TRB_TLBPC(residue);
+			field = 0;
 
 			if (first_trb) {
+				field = TRB_TBC(burst_count) |
+					TRB_TLBPC(residue);
 				/* Queue the isoc TRB */
 				field |= TRB_TYPE(TRB_ISOC);
 				/* Assume URB_ISO_ASAP is set */
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index f14736f..edc0f0d 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -60,6 +60,7 @@
 	{ USB_DEVICE(0x0FCF, 0x1003) }, /* Dynastream ANT development board */
 	{ USB_DEVICE(0x0FCF, 0x1004) }, /* Dynastream ANT2USB */
 	{ USB_DEVICE(0x0FCF, 0x1006) }, /* Dynastream ANT development board */
+	{ USB_DEVICE(0x0FDE, 0xCA05) }, /* OWL Wireless Electricity Monitor CM-160 */
 	{ USB_DEVICE(0x10A6, 0xAA26) }, /* Knock-off DCU-11 cable */
 	{ USB_DEVICE(0x10AB, 0x10C5) }, /* Siemens MC60 Cable */
 	{ USB_DEVICE(0x10B5, 0xAC70) }, /* Nokia CA-42 USB */
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index ba68835..90ceef1 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -584,6 +584,7 @@
 	/*
 	 * ELV devices:
 	 */
+	{ USB_DEVICE(FTDI_ELV_VID, FTDI_ELV_WS300_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_ELV_USR_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_ELV_MSM1_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_ELV_KL100_PID) },
@@ -670,6 +671,7 @@
 	{ USB_DEVICE(FTDI_VID, XSENS_CONVERTER_5_PID) },
 	{ USB_DEVICE(FTDI_VID, XSENS_CONVERTER_6_PID) },
 	{ USB_DEVICE(FTDI_VID, XSENS_CONVERTER_7_PID) },
+	{ USB_DEVICE(FTDI_VID, FTDI_OMNI1509) },
 	{ USB_DEVICE(MOBILITY_VID, MOBILITY_USB_SERIAL_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_ACTIVE_ROBOTS_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_MHAM_KW_PID) },
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index fa5d560..9d359e1 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -147,6 +147,11 @@
 #define XSENS_CONVERTER_6_PID	0xD38E
 #define XSENS_CONVERTER_7_PID	0xD38F
 
+/**
+ * Zolix (www.zolix.com.cb) product ids
+ */
+#define FTDI_OMNI1509			0xD491	/* Omni1509 embedded USB-serial */
+
 /*
  * NDI (www.ndigital.com) product ids
  */
@@ -204,7 +209,7 @@
 
 /*
  * ELV USB devices submitted by Christian Abt of ELV (www.elv.de).
- * All of these devices use FTDI's vendor ID (0x0403).
+ * Almost all of these devices use FTDI's vendor ID (0x0403).
  * Further IDs taken from ELV Windows .inf file.
  *
  * The previously included PID for the UO 100 module was incorrect.
@@ -212,6 +217,8 @@
  *
  * Armin Laeuger originally sent the PID for the UM 100 module.
  */
+#define FTDI_ELV_VID	0x1B1F	/* ELV AG */
+#define FTDI_ELV_WS300_PID	0xC006	/* eQ3 WS 300 PC II */
 #define FTDI_ELV_USR_PID	0xE000	/* ELV Universal-Sound-Recorder */
 #define FTDI_ELV_MSM1_PID	0xE001	/* ELV Mini-Sound-Modul */
 #define FTDI_ELV_KL100_PID	0xE002	/* ELV Kfz-Leistungsmesser KL 100 */
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 0d9dac9..567bc77 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -242,6 +242,7 @@
 #define TELIT_PRODUCT_CC864_DUAL		0x1005
 #define TELIT_PRODUCT_CC864_SINGLE		0x1006
 #define TELIT_PRODUCT_DE910_DUAL		0x1010
+#define TELIT_PRODUCT_LE920			0x1200
 
 /* ZTE PRODUCTS */
 #define ZTE_VENDOR_ID				0x19d2
@@ -453,6 +454,10 @@
 #define TPLINK_VENDOR_ID			0x2357
 #define TPLINK_PRODUCT_MA180			0x0201
 
+/* Changhong products */
+#define CHANGHONG_VENDOR_ID			0x2077
+#define CHANGHONG_PRODUCT_CH690			0x7001
+
 /* some devices interfaces need special handling due to a number of reasons */
 enum option_blacklist_reason {
 		OPTION_BLACKLIST_NONE = 0,
@@ -534,6 +539,11 @@
 	.reserved = BIT(3) | BIT(4),
 };
 
+static const struct option_blacklist_info telit_le920_blacklist = {
+	.sendsetup = BIT(0),
+	.reserved = BIT(1) | BIT(5),
+};
+
 static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_COLT) },
 	{ USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_RICOLA) },
@@ -784,6 +794,8 @@
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_CC864_DUAL) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_CC864_SINGLE) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_DE910_DUAL) },
+	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920),
+		.driver_info = (kernel_ulong_t)&telit_le920_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MF622, 0xff, 0xff, 0xff) }, /* ZTE WCDMA products */
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0002, 0xff, 0xff, 0xff),
 		.driver_info = (kernel_ulong_t)&net_intf1_blacklist },
@@ -1318,6 +1330,7 @@
 	{ USB_DEVICE(PETATEL_VENDOR_ID, PETATEL_PRODUCT_NP10T) },
 	{ USB_DEVICE(TPLINK_VENDOR_ID, TPLINK_PRODUCT_MA180),
 	  .driver_info = (kernel_ulong_t)&net_intf4_blacklist },
+	{ USB_DEVICE(CHANGHONG_VENDOR_ID, CHANGHONG_PRODUCT_CH690) },
 	{ } /* Terminating entry */
 };
 MODULE_DEVICE_TABLE(usb, option_ids);
diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c
index aa148c2..2466254 100644
--- a/drivers/usb/serial/qcserial.c
+++ b/drivers/usb/serial/qcserial.c
@@ -53,6 +53,7 @@
 	{DEVICE_G1K(0x05c6, 0x9221)},	/* Generic Gobi QDL device */
 	{DEVICE_G1K(0x05c6, 0x9231)},	/* Generic Gobi QDL device */
 	{DEVICE_G1K(0x1f45, 0x0001)},	/* Unknown Gobi QDL device */
+	{DEVICE_G1K(0x1bc7, 0x900e)},	/* Telit Gobi QDL device */
 
 	/* Gobi 2000 devices */
 	{USB_DEVICE(0x1410, 0xa010)},	/* Novatel Gobi 2000 QDL device */
diff --git a/drivers/usb/storage/initializers.c b/drivers/usb/storage/initializers.c
index 105d900..16b0bf0 100644
--- a/drivers/usb/storage/initializers.c
+++ b/drivers/usb/storage/initializers.c
@@ -92,8 +92,8 @@
 	return 0;
 }
 
-/* This places the HUAWEI E220 devices in multi-port mode */
-int usb_stor_huawei_e220_init(struct us_data *us)
+/* This places the HUAWEI usb dongles in multi-port mode */
+static int usb_stor_huawei_feature_init(struct us_data *us)
 {
 	int result;
 
@@ -104,3 +104,75 @@
 	US_DEBUGP("Huawei mode set result is %d\n", result);
 	return 0;
 }
+
+/*
+ * It will send a scsi switch command called rewind' to huawei dongle.
+ * When the dongle receives this command at the first time,
+ * it will reboot immediately. After rebooted, it will ignore this command.
+ * So it is  unnecessary to read its response.
+ */
+static int usb_stor_huawei_scsi_init(struct us_data *us)
+{
+	int result = 0;
+	int act_len = 0;
+	struct bulk_cb_wrap *bcbw = (struct bulk_cb_wrap *) us->iobuf;
+	char rewind_cmd[] = {0x11, 0x06, 0x20, 0x00, 0x00, 0x01, 0x01, 0x00,
+			0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00};
+
+	bcbw->Signature = cpu_to_le32(US_BULK_CB_SIGN);
+	bcbw->Tag = 0;
+	bcbw->DataTransferLength = 0;
+	bcbw->Flags = bcbw->Lun = 0;
+	bcbw->Length = sizeof(rewind_cmd);
+	memset(bcbw->CDB, 0, sizeof(bcbw->CDB));
+	memcpy(bcbw->CDB, rewind_cmd, sizeof(rewind_cmd));
+
+	result = usb_stor_bulk_transfer_buf(us, us->send_bulk_pipe, bcbw,
+					US_BULK_CB_WRAP_LEN, &act_len);
+	US_DEBUGP("transfer actual length=%d, result=%d\n", act_len, result);
+	return result;
+}
+
+/*
+ * It tries to find the supported Huawei USB dongles.
+ * In Huawei, they assign the following product IDs
+ * for all of their mobile broadband dongles,
+ * including the new dongles in the future.
+ * So if the product ID is not included in this list,
+ * it means it is not Huawei's mobile broadband dongles.
+ */
+static int usb_stor_huawei_dongles_pid(struct us_data *us)
+{
+	struct usb_interface_descriptor *idesc;
+	int idProduct;
+
+	idesc = &us->pusb_intf->cur_altsetting->desc;
+	idProduct = us->pusb_dev->descriptor.idProduct;
+	/* The first port is CDROM,
+	 * means the dongle in the single port mode,
+	 * and a switch command is required to be sent. */
+	if (idesc && idesc->bInterfaceNumber == 0) {
+		if ((idProduct == 0x1001)
+			|| (idProduct == 0x1003)
+			|| (idProduct == 0x1004)
+			|| (idProduct >= 0x1401 && idProduct <= 0x1500)
+			|| (idProduct >= 0x1505 && idProduct <= 0x1600)
+			|| (idProduct >= 0x1c02 && idProduct <= 0x2202)) {
+			return 1;
+		}
+	}
+	return 0;
+}
+
+int usb_stor_huawei_init(struct us_data *us)
+{
+	int result = 0;
+
+	if (usb_stor_huawei_dongles_pid(us)) {
+		if (us->pusb_dev->descriptor.idProduct >= 0x1446)
+			result = usb_stor_huawei_scsi_init(us);
+		else
+			result = usb_stor_huawei_feature_init(us);
+	}
+	return result;
+}
diff --git a/drivers/usb/storage/initializers.h b/drivers/usb/storage/initializers.h
index 529327f..5376d4f 100644
--- a/drivers/usb/storage/initializers.h
+++ b/drivers/usb/storage/initializers.h
@@ -46,5 +46,5 @@
  * flash reader */
 int usb_stor_ucr61s2b_init(struct us_data *us);
 
-/* This places the HUAWEI E220 devices in multi-port mode */
-int usb_stor_huawei_e220_init(struct us_data *us);
+/* This places the HUAWEI usb dongles in multi-port mode */
+int usb_stor_huawei_init(struct us_data *us);
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index d305a5a..72923b5 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -1527,335 +1527,10 @@
 /* Reported by fangxiaozhi <huananhu@huawei.com>
  * This brings the HUAWEI data card devices into multi-port mode
  */
-UNUSUAL_DEV(  0x12d1, 0x1001, 0x0000, 0x0000,
+UNUSUAL_VENDOR_INTF(0x12d1, 0x08, 0x06, 0x50,
 		"HUAWEI MOBILE",
 		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1003, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1004, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1401, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1402, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1403, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1404, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1405, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1406, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1407, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1408, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1409, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x140A, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x140B, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x140C, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x140D, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x140E, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x140F, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1410, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1411, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1412, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1413, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1414, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1415, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1416, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1417, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1418, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1419, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x141A, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x141B, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x141C, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x141D, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x141E, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x141F, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1420, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1421, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1422, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1423, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1424, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1425, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1426, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1427, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1428, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1429, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x142A, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x142B, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x142C, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x142D, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x142E, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x142F, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1430, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1431, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1432, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1433, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1434, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1435, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1436, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1437, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1438, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x1439, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x143A, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x143B, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x143C, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x143D, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x143E, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
-		0),
-UNUSUAL_DEV(  0x12d1, 0x143F, 0x0000, 0x0000,
-		"HUAWEI MOBILE",
-		"Mass Storage",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init,
+		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_init,
 		0),
 
 /* Reported by Vilius Bilinkevicius <vilisas AT xxx DOT lt) */
diff --git a/drivers/usb/storage/usb.c b/drivers/usb/storage/usb.c
index 31b3e1a..cf09b6b 100644
--- a/drivers/usb/storage/usb.c
+++ b/drivers/usb/storage/usb.c
@@ -120,6 +120,17 @@
 	.useTransport = use_transport,	\
 }
 
+#define UNUSUAL_VENDOR_INTF(idVendor, cl, sc, pr, \
+		vendor_name, product_name, use_protocol, use_transport, \
+		init_function, Flags) \
+{ \
+	.vendorName = vendor_name,	\
+	.productName = product_name,	\
+	.useProtocol = use_protocol,	\
+	.useTransport = use_transport,	\
+	.initFunction = init_function,	\
+}
+
 static struct us_unusual_dev us_unusual_dev_list[] = {
 #	include "unusual_devs.h"
 	{ }		/* Terminating entry */
@@ -131,6 +142,7 @@
 #undef UNUSUAL_DEV
 #undef COMPLIANT_DEV
 #undef USUAL_DEV
+#undef UNUSUAL_VENDOR_INTF
 
 #ifdef CONFIG_LOCKDEP
 
diff --git a/drivers/usb/storage/usual-tables.c b/drivers/usb/storage/usual-tables.c
index b78a526..5ef8ce7 100644
--- a/drivers/usb/storage/usual-tables.c
+++ b/drivers/usb/storage/usual-tables.c
@@ -41,6 +41,20 @@
 #define USUAL_DEV(useProto, useTrans) \
 { USB_INTERFACE_INFO(USB_CLASS_MASS_STORAGE, useProto, useTrans) }
 
+/* Define the device is matched with Vendor ID and interface descriptors */
+#define UNUSUAL_VENDOR_INTF(id_vendor, cl, sc, pr, \
+			vendorName, productName, useProtocol, useTransport, \
+			initFunction, flags) \
+{ \
+	.match_flags = USB_DEVICE_ID_MATCH_INT_INFO \
+				| USB_DEVICE_ID_MATCH_VENDOR, \
+	.idVendor    = (id_vendor), \
+	.bInterfaceClass = (cl), \
+	.bInterfaceSubClass = (sc), \
+	.bInterfaceProtocol = (pr), \
+	.driver_info = (flags) \
+}
+
 struct usb_device_id usb_storage_usb_ids[] = {
 #	include "unusual_devs.h"
 	{ }		/* Terminating entry */
@@ -50,6 +64,7 @@
 #undef UNUSUAL_DEV
 #undef COMPLIANT_DEV
 #undef USUAL_DEV
+#undef UNUSUAL_VENDOR_INTF
 
 /*
  * The table of devices to ignore
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index ebd08b2..959b1cd 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -165,12 +165,16 @@
 }
 
 /* Caller must have TX VQ lock */
-static void tx_poll_start(struct vhost_net *net, struct socket *sock)
+static int tx_poll_start(struct vhost_net *net, struct socket *sock)
 {
+	int ret;
+
 	if (unlikely(net->tx_poll_state != VHOST_NET_POLL_STOPPED))
-		return;
-	vhost_poll_start(net->poll + VHOST_NET_VQ_TX, sock->file);
-	net->tx_poll_state = VHOST_NET_POLL_STARTED;
+		return 0;
+	ret = vhost_poll_start(net->poll + VHOST_NET_VQ_TX, sock->file);
+	if (!ret)
+		net->tx_poll_state = VHOST_NET_POLL_STARTED;
+	return ret;
 }
 
 /* In case of DMA done not in order in lower device driver for some reason.
@@ -642,20 +646,23 @@
 		vhost_poll_stop(n->poll + VHOST_NET_VQ_RX);
 }
 
-static void vhost_net_enable_vq(struct vhost_net *n,
+static int vhost_net_enable_vq(struct vhost_net *n,
 				struct vhost_virtqueue *vq)
 {
 	struct socket *sock;
+	int ret;
 
 	sock = rcu_dereference_protected(vq->private_data,
 					 lockdep_is_held(&vq->mutex));
 	if (!sock)
-		return;
+		return 0;
 	if (vq == n->vqs + VHOST_NET_VQ_TX) {
 		n->tx_poll_state = VHOST_NET_POLL_STOPPED;
-		tx_poll_start(n, sock);
+		ret = tx_poll_start(n, sock);
 	} else
-		vhost_poll_start(n->poll + VHOST_NET_VQ_RX, sock->file);
+		ret = vhost_poll_start(n->poll + VHOST_NET_VQ_RX, sock->file);
+
+	return ret;
 }
 
 static struct socket *vhost_net_stop_vq(struct vhost_net *n,
@@ -827,15 +834,18 @@
 			r = PTR_ERR(ubufs);
 			goto err_ubufs;
 		}
-		oldubufs = vq->ubufs;
-		vq->ubufs = ubufs;
+
 		vhost_net_disable_vq(n, vq);
 		rcu_assign_pointer(vq->private_data, sock);
-		vhost_net_enable_vq(n, vq);
-
 		r = vhost_init_used(vq);
 		if (r)
-			goto err_vq;
+			goto err_used;
+		r = vhost_net_enable_vq(n, vq);
+		if (r)
+			goto err_used;
+
+		oldubufs = vq->ubufs;
+		vq->ubufs = ubufs;
 
 		n->tx_packets = 0;
 		n->tx_zcopy_err = 0;
@@ -859,6 +869,11 @@
 	mutex_unlock(&n->dev.mutex);
 	return 0;
 
+err_used:
+	rcu_assign_pointer(vq->private_data, oldsock);
+	vhost_net_enable_vq(n, vq);
+	if (ubufs)
+		vhost_ubuf_put_and_wait(ubufs);
 err_ubufs:
 	fput(sock->file);
 err_vq:
diff --git a/drivers/vhost/tcm_vhost.c b/drivers/vhost/tcm_vhost.c
index b20df5c..22321cf 100644
--- a/drivers/vhost/tcm_vhost.c
+++ b/drivers/vhost/tcm_vhost.c
@@ -575,10 +575,8 @@
 
 	/* Must use ioctl VHOST_SCSI_SET_ENDPOINT */
 	tv_tpg = vs->vs_tpg;
-	if (unlikely(!tv_tpg)) {
-		pr_err("%s endpoint not set\n", __func__);
+	if (unlikely(!tv_tpg))
 		return;
-	}
 
 	mutex_lock(&vq->mutex);
 	vhost_disable_notify(&vs->dev, vq);
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 34389f7..9759249 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -77,26 +77,38 @@
 	init_poll_funcptr(&poll->table, vhost_poll_func);
 	poll->mask = mask;
 	poll->dev = dev;
+	poll->wqh = NULL;
 
 	vhost_work_init(&poll->work, fn);
 }
 
 /* Start polling a file. We add ourselves to file's wait queue. The caller must
  * keep a reference to a file until after vhost_poll_stop is called. */
-void vhost_poll_start(struct vhost_poll *poll, struct file *file)
+int vhost_poll_start(struct vhost_poll *poll, struct file *file)
 {
 	unsigned long mask;
+	int ret = 0;
 
 	mask = file->f_op->poll(file, &poll->table);
 	if (mask)
 		vhost_poll_wakeup(&poll->wait, 0, 0, (void *)mask);
+	if (mask & POLLERR) {
+		if (poll->wqh)
+			remove_wait_queue(poll->wqh, &poll->wait);
+		ret = -EINVAL;
+	}
+
+	return ret;
 }
 
 /* Stop polling a file. After this function returns, it becomes safe to drop the
  * file reference. You must also flush afterwards. */
 void vhost_poll_stop(struct vhost_poll *poll)
 {
-	remove_wait_queue(poll->wqh, &poll->wait);
+	if (poll->wqh) {
+		remove_wait_queue(poll->wqh, &poll->wait);
+		poll->wqh = NULL;
+	}
 }
 
 static bool vhost_work_seq_done(struct vhost_dev *dev, struct vhost_work *work,
@@ -792,7 +804,7 @@
 		fput(filep);
 
 	if (pollstart && vq->handle_kick)
-		vhost_poll_start(&vq->poll, vq->kick);
+		r = vhost_poll_start(&vq->poll, vq->kick);
 
 	mutex_unlock(&vq->mutex);
 
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 2639c58..17261e2 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -42,7 +42,7 @@
 
 void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t fn,
 		     unsigned long mask, struct vhost_dev *dev);
-void vhost_poll_start(struct vhost_poll *poll, struct file *file);
+int vhost_poll_start(struct vhost_poll *poll, struct file *file);
 void vhost_poll_stop(struct vhost_poll *poll);
 void vhost_poll_flush(struct vhost_poll *poll);
 void vhost_poll_queue(struct vhost_poll *poll);
diff --git a/drivers/video/imxfb.c b/drivers/video/imxfb.c
index 1252678..0abf2bf 100644
--- a/drivers/video/imxfb.c
+++ b/drivers/video/imxfb.c
@@ -139,6 +139,7 @@
 	struct clk		*clk_ahb;
 	struct clk		*clk_per;
 	enum imxfb_type		devtype;
+	bool			enabled;
 
 	/*
 	 * These are the addresses we mapped
@@ -536,6 +537,10 @@
 
 static void imxfb_enable_controller(struct imxfb_info *fbi)
 {
+
+	if (fbi->enabled)
+		return;
+
 	pr_debug("Enabling LCD controller\n");
 
 	writel(fbi->screen_dma, fbi->regs + LCDC_SSA);
@@ -556,6 +561,7 @@
 	clk_prepare_enable(fbi->clk_ipg);
 	clk_prepare_enable(fbi->clk_ahb);
 	clk_prepare_enable(fbi->clk_per);
+	fbi->enabled = true;
 
 	if (fbi->backlight_power)
 		fbi->backlight_power(1);
@@ -565,6 +571,9 @@
 
 static void imxfb_disable_controller(struct imxfb_info *fbi)
 {
+	if (!fbi->enabled)
+		return;
+
 	pr_debug("Disabling LCD controller\n");
 
 	if (fbi->backlight_power)
@@ -575,6 +584,7 @@
 	clk_disable_unprepare(fbi->clk_per);
 	clk_disable_unprepare(fbi->clk_ipg);
 	clk_disable_unprepare(fbi->clk_ahb);
+	fbi->enabled = false;
 
 	writel(0, fbi->regs + LCDC_RMCR);
 }
@@ -729,6 +739,8 @@
 
 	memset(fbi, 0, sizeof(struct imxfb_info));
 
+	fbi->devtype = pdev->id_entry->driver_data;
+
 	strlcpy(info->fix.id, IMX_NAME, sizeof(info->fix.id));
 
 	info->fix.type			= FB_TYPE_PACKED_PIXELS;
@@ -789,7 +801,6 @@
 		return -ENOMEM;
 
 	fbi = info->par;
-	fbi->devtype = pdev->id_entry->driver_data;
 
 	if (!fb_mode)
 		fb_mode = pdata->mode[0].mode.name;
diff --git a/drivers/video/omap2/dss/dss_features.c b/drivers/video/omap2/dss/dss_features.c
index 18688c1..d7d66ef 100644
--- a/drivers/video/omap2/dss/dss_features.c
+++ b/drivers/video/omap2/dss/dss_features.c
@@ -538,6 +538,7 @@
 	FEAT_ALPHA_FIXED_ZORDER,
 	FEAT_FIFO_MERGE,
 	FEAT_OMAP3_DSI_FIFO_BUG,
+	FEAT_DPI_USES_VDDS_DSI,
 };
 
 static const enum dss_feat_id omap4430_es1_0_dss_feat_list[] = {
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 0be4df3..74d77df 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -840,7 +840,7 @@
 
 	if (irq == -1) {
 		irq = xen_allocate_irq_dynamic();
-		if (irq == -1)
+		if (irq < 0)
 			goto out;
 
 		irq_set_chip_and_handler_name(irq, &xen_dynamic_chip,
@@ -944,7 +944,7 @@
 
 	if (irq == -1) {
 		irq = xen_allocate_irq_dynamic();
-		if (irq == -1)
+		if (irq < 0)
 			goto out;
 
 		irq_set_chip_and_handler_name(irq, &xen_percpu_chip,
diff --git a/drivers/xen/pcpu.c b/drivers/xen/pcpu.c
index 067fcfa..5a27a45 100644
--- a/drivers/xen/pcpu.c
+++ b/drivers/xen/pcpu.c
@@ -278,8 +278,7 @@
 	 * Only those at cpu present map has its sys interface.
 	 */
 	if (info->flags & XEN_PCPU_FLAGS_INVALID) {
-		if (pcpu)
-			unregister_and_remove_pcpu(pcpu);
+		unregister_and_remove_pcpu(pcpu);
 		return 0;
 	}
 
diff --git a/drivers/xen/xen-pciback/pciback_ops.c b/drivers/xen/xen-pciback/pciback_ops.c
index 97f5d26..37c1f82 100644
--- a/drivers/xen/xen-pciback/pciback_ops.c
+++ b/drivers/xen/xen-pciback/pciback_ops.c
@@ -135,7 +135,6 @@
 			 struct pci_dev *dev, struct xen_pci_op *op)
 {
 	struct xen_pcibk_dev_data *dev_data;
-	int otherend = pdev->xdev->otherend_id;
 	int status;
 
 	if (unlikely(verbose_request))
@@ -144,8 +143,9 @@
 	status = pci_enable_msi(dev);
 
 	if (status) {
-		printk(KERN_ERR "error enable msi for guest %x status %x\n",
-			otherend, status);
+		pr_warn_ratelimited(DRV_NAME ": %s: error enabling MSI for guest %u: err %d\n",
+				    pci_name(dev), pdev->xdev->otherend_id,
+				    status);
 		op->value = 0;
 		return XEN_PCI_ERR_op_failed;
 	}
@@ -223,10 +223,10 @@
 						pci_name(dev), i,
 						op->msix_entries[i].vector);
 		}
-	} else {
-		printk(KERN_WARNING DRV_NAME ": %s: failed to enable MSI-X: err %d!\n",
-			pci_name(dev), result);
-	}
+	} else
+		pr_warn_ratelimited(DRV_NAME ": %s: error enabling MSI-X for guest %u: err %d!\n",
+				    pci_name(dev), pdev->xdev->otherend_id,
+				    result);
 	kfree(entries);
 
 	op->value = result;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 521e9d4..5a3327b 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3997,7 +3997,7 @@
 	 * We make the other tasks wait for the flush only when we can flush
 	 * all things.
 	 */
-	if (ret && flush == BTRFS_RESERVE_FLUSH_ALL) {
+	if (ret && flush != BTRFS_RESERVE_NO_FLUSH) {
 		flushing = true;
 		space_info->flush = 1;
 	}
@@ -4534,7 +4534,7 @@
 	unsigned nr_extents = 0;
 	int extra_reserve = 0;
 	enum btrfs_reserve_flush_enum flush = BTRFS_RESERVE_FLUSH_ALL;
-	int ret;
+	int ret = 0;
 	bool delalloc_lock = true;
 
 	/* If we are a free space inode we need to not flush since we will be in
@@ -4579,20 +4579,18 @@
 	csum_bytes = BTRFS_I(inode)->csum_bytes;
 	spin_unlock(&BTRFS_I(inode)->lock);
 
-	if (root->fs_info->quota_enabled) {
+	if (root->fs_info->quota_enabled)
 		ret = btrfs_qgroup_reserve(root, num_bytes +
 					   nr_extents * root->leafsize);
-		if (ret) {
-			spin_lock(&BTRFS_I(inode)->lock);
-			calc_csum_metadata_size(inode, num_bytes, 0);
-			spin_unlock(&BTRFS_I(inode)->lock);
-			if (delalloc_lock)
-				mutex_unlock(&BTRFS_I(inode)->delalloc_mutex);
-			return ret;
-		}
-	}
 
-	ret = reserve_metadata_bytes(root, block_rsv, to_reserve, flush);
+	/*
+	 * ret != 0 here means the qgroup reservation failed, we go straight to
+	 * the shared error handling then.
+	 */
+	if (ret == 0)
+		ret = reserve_metadata_bytes(root, block_rsv,
+					     to_reserve, flush);
+
 	if (ret) {
 		u64 to_free = 0;
 		unsigned dropped;
@@ -5560,7 +5558,7 @@
 	int empty_cluster = 2 * 1024 * 1024;
 	struct btrfs_space_info *space_info;
 	int loop = 0;
-	int index = 0;
+	int index = __get_raid_index(data);
 	int alloc_type = (data & BTRFS_BLOCK_GROUP_DATA) ?
 		RESERVE_ALLOC_NO_ACCOUNT : RESERVE_ALLOC;
 	bool found_uncached_bg = false;
@@ -6788,11 +6786,13 @@
 						       &wc->flags[level]);
 			if (ret < 0) {
 				btrfs_tree_unlock_rw(eb, path->locks[level]);
+				path->locks[level] = 0;
 				return ret;
 			}
 			BUG_ON(wc->refs[level] == 0);
 			if (wc->refs[level] == 1) {
 				btrfs_tree_unlock_rw(eb, path->locks[level]);
+				path->locks[level] = 0;
 				return 1;
 			}
 		}
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index f169d6b..fdb7a8d 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -171,6 +171,10 @@
 	if (test_bit(EXTENT_FLAG_COMPRESSED, &prev->flags))
 		return 0;
 
+	if (test_bit(EXTENT_FLAG_LOGGING, &prev->flags) ||
+	    test_bit(EXTENT_FLAG_LOGGING, &next->flags))
+		return 0;
+
 	if (extent_map_end(prev) == next->start &&
 	    prev->flags == next->flags &&
 	    prev->bdev == next->bdev &&
@@ -255,7 +259,8 @@
 	if (!em)
 		goto out;
 
-	list_move(&em->list, &tree->modified_extents);
+	if (!test_bit(EXTENT_FLAG_LOGGING, &em->flags))
+		list_move(&em->list, &tree->modified_extents);
 	em->generation = gen;
 	clear_bit(EXTENT_FLAG_PINNED, &em->flags);
 	em->mod_start = em->start;
@@ -280,6 +285,13 @@
 
 }
 
+void clear_em_logging(struct extent_map_tree *tree, struct extent_map *em)
+{
+	clear_bit(EXTENT_FLAG_LOGGING, &em->flags);
+	if (em->in_tree)
+		try_merge_map(tree, em);
+}
+
 /**
  * add_extent_mapping - add new extent map to the extent tree
  * @tree:	tree to insert new map in
diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h
index 922943c..c6598c8 100644
--- a/fs/btrfs/extent_map.h
+++ b/fs/btrfs/extent_map.h
@@ -69,6 +69,7 @@
 int __init extent_map_init(void);
 void extent_map_exit(void);
 int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len, u64 gen);
+void clear_em_logging(struct extent_map_tree *tree, struct extent_map *em);
 struct extent_map *search_extent_mapping(struct extent_map_tree *tree,
 					 u64 start, u64 len);
 #endif
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index bd38cef..94aa53b 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -460,8 +460,8 @@
 		if (!contig)
 			offset = page_offset(bvec->bv_page) + bvec->bv_offset;
 
-		if (!contig && (offset >= ordered->file_offset + ordered->len ||
-		    offset < ordered->file_offset)) {
+		if (offset >= ordered->file_offset + ordered->len ||
+		    offset < ordered->file_offset) {
 			unsigned long bytes_left;
 			sums->len = this_sum_bytes;
 			this_sum_bytes = 0;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 77061bf..aeb8446 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -293,15 +293,24 @@
 	struct btrfs_key key;
 	struct btrfs_ioctl_defrag_range_args range;
 	int num_defrag;
+	int index;
+	int ret;
 
 	/* get the inode */
 	key.objectid = defrag->root;
 	btrfs_set_key_type(&key, BTRFS_ROOT_ITEM_KEY);
 	key.offset = (u64)-1;
+
+	index = srcu_read_lock(&fs_info->subvol_srcu);
+
 	inode_root = btrfs_read_fs_root_no_name(fs_info, &key);
 	if (IS_ERR(inode_root)) {
-		kmem_cache_free(btrfs_inode_defrag_cachep, defrag);
-		return PTR_ERR(inode_root);
+		ret = PTR_ERR(inode_root);
+		goto cleanup;
+	}
+	if (btrfs_root_refs(&inode_root->root_item) == 0) {
+		ret = -ENOENT;
+		goto cleanup;
 	}
 
 	key.objectid = defrag->ino;
@@ -309,9 +318,10 @@
 	key.offset = 0;
 	inode = btrfs_iget(fs_info->sb, &key, inode_root, NULL);
 	if (IS_ERR(inode)) {
-		kmem_cache_free(btrfs_inode_defrag_cachep, defrag);
-		return PTR_ERR(inode);
+		ret = PTR_ERR(inode);
+		goto cleanup;
 	}
+	srcu_read_unlock(&fs_info->subvol_srcu, index);
 
 	/* do a chunk of defrag */
 	clear_bit(BTRFS_INODE_IN_DEFRAG, &BTRFS_I(inode)->runtime_flags);
@@ -346,6 +356,10 @@
 
 	iput(inode);
 	return 0;
+cleanup:
+	srcu_read_unlock(&fs_info->subvol_srcu, index);
+	kmem_cache_free(btrfs_inode_defrag_cachep, defrag);
+	return ret;
 }
 
 /*
@@ -1594,9 +1608,10 @@
 		if (err < 0 && num_written > 0)
 			num_written = err;
 	}
-out:
+
 	if (sync)
 		atomic_dec(&BTRFS_I(inode)->sync_writers);
+out:
 	sb_end_write(inode->i_sb);
 	current->backing_dev_info = NULL;
 	return num_written ? num_written : err;
@@ -2241,6 +2256,7 @@
 	if (lockend <= lockstart)
 		lockend = lockstart + root->sectorsize;
 
+	lockend--;
 	len = lockend - lockstart + 1;
 
 	len = max_t(u64, len, root->sectorsize);
@@ -2307,9 +2323,12 @@
 					}
 				}
 
-				*offset = start;
-				free_extent_map(em);
-				break;
+				if (!test_bit(EXTENT_FLAG_PREALLOC,
+					      &em->flags)) {
+					*offset = start;
+					free_extent_map(em);
+					break;
+				}
 			}
 		}
 
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 59ea2e4..0be7a87 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -1862,11 +1862,13 @@
 {
 	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
 	struct btrfs_free_space *info;
-	int ret = 0;
+	int ret;
+	bool re_search = false;
 
 	spin_lock(&ctl->tree_lock);
 
 again:
+	ret = 0;
 	if (!bytes)
 		goto out_lock;
 
@@ -1879,17 +1881,17 @@
 		info = tree_search_offset(ctl, offset_to_bitmap(ctl, offset),
 					  1, 0);
 		if (!info) {
-			/* the tree logging code might be calling us before we
-			 * have fully loaded the free space rbtree for this
-			 * block group.  So it is possible the entry won't
-			 * be in the rbtree yet at all.  The caching code
-			 * will make sure not to put it in the rbtree if
-			 * the logging code has pinned it.
+			/*
+			 * If we found a partial bit of our free space in a
+			 * bitmap but then couldn't find the other part this may
+			 * be a problem, so WARN about it.
 			 */
+			WARN_ON(re_search);
 			goto out_lock;
 		}
 	}
 
+	re_search = false;
 	if (!info->bitmap) {
 		unlink_free_space(ctl, info);
 		if (offset == info->offset) {
@@ -1935,8 +1937,10 @@
 	}
 
 	ret = remove_from_bitmap(ctl, info, &offset, &bytes);
-	if (ret == -EAGAIN)
+	if (ret == -EAGAIN) {
+		re_search = true;
 		goto again;
+	}
 	BUG_ON(ret); /* logic error */
 out_lock:
 	spin_unlock(&ctl->tree_lock);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 16d9e8e..cc93b23 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -88,7 +88,7 @@
 	[S_IFLNK >> S_SHIFT]	= BTRFS_FT_SYMLINK,
 };
 
-static int btrfs_setsize(struct inode *inode, loff_t newsize);
+static int btrfs_setsize(struct inode *inode, struct iattr *attr);
 static int btrfs_truncate(struct inode *inode);
 static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent);
 static noinline int cow_file_range(struct inode *inode,
@@ -2478,6 +2478,18 @@
 				continue;
 			}
 			nr_truncate++;
+
+			/* 1 for the orphan item deletion. */
+			trans = btrfs_start_transaction(root, 1);
+			if (IS_ERR(trans)) {
+				ret = PTR_ERR(trans);
+				goto out;
+			}
+			ret = btrfs_orphan_add(trans, inode);
+			btrfs_end_transaction(trans, root);
+			if (ret)
+				goto out;
+
 			ret = btrfs_truncate(inode);
 		} else {
 			nr_unlink++;
@@ -3665,6 +3677,7 @@
 				block_end - cur_offset, 0);
 		if (IS_ERR(em)) {
 			err = PTR_ERR(em);
+			em = NULL;
 			break;
 		}
 		last_byte = min(extent_map_end(em), block_end);
@@ -3748,16 +3761,27 @@
 	return err;
 }
 
-static int btrfs_setsize(struct inode *inode, loff_t newsize)
+static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_trans_handle *trans;
 	loff_t oldsize = i_size_read(inode);
+	loff_t newsize = attr->ia_size;
+	int mask = attr->ia_valid;
 	int ret;
 
 	if (newsize == oldsize)
 		return 0;
 
+	/*
+	 * The regular truncate() case without ATTR_CTIME and ATTR_MTIME is a
+	 * special case where we need to update the times despite not having
+	 * these flags set.  For all other operations the VFS set these flags
+	 * explicitly if it wants a timestamp update.
+	 */
+	if (newsize != oldsize && (!(mask & (ATTR_CTIME | ATTR_MTIME))))
+		inode->i_ctime = inode->i_mtime = current_fs_time(inode->i_sb);
+
 	if (newsize > oldsize) {
 		truncate_pagecache(inode, oldsize, newsize);
 		ret = btrfs_cont_expand(inode, oldsize, newsize);
@@ -3783,9 +3807,34 @@
 			set_bit(BTRFS_INODE_ORDERED_DATA_CLOSE,
 				&BTRFS_I(inode)->runtime_flags);
 
+		/*
+		 * 1 for the orphan item we're going to add
+		 * 1 for the orphan item deletion.
+		 */
+		trans = btrfs_start_transaction(root, 2);
+		if (IS_ERR(trans))
+			return PTR_ERR(trans);
+
+		/*
+		 * We need to do this in case we fail at _any_ point during the
+		 * actual truncate.  Once we do the truncate_setsize we could
+		 * invalidate pages which forces any outstanding ordered io to
+		 * be instantly completed which will give us extents that need
+		 * to be truncated.  If we fail to get an orphan inode down we
+		 * could have left over extents that were never meant to live,
+		 * so we need to garuntee from this point on that everything
+		 * will be consistent.
+		 */
+		ret = btrfs_orphan_add(trans, inode);
+		btrfs_end_transaction(trans, root);
+		if (ret)
+			return ret;
+
 		/* we don't support swapfiles, so vmtruncate shouldn't fail */
 		truncate_setsize(inode, newsize);
 		ret = btrfs_truncate(inode);
+		if (ret && inode->i_nlink)
+			btrfs_orphan_del(NULL, inode);
 	}
 
 	return ret;
@@ -3805,7 +3854,7 @@
 		return err;
 
 	if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) {
-		err = btrfs_setsize(inode, attr->ia_size);
+		err = btrfs_setsize(inode, attr);
 		if (err)
 			return err;
 	}
@@ -5572,10 +5621,13 @@
 		return em;
 	if (em) {
 		/*
-		 * if our em maps to a hole, there might
-		 * actually be delalloc bytes behind it
+		 * if our em maps to
+		 * -  a hole or
+		 * -  a pre-alloc extent,
+		 * there might actually be delalloc bytes behind it.
 		 */
-		if (em->block_start != EXTENT_MAP_HOLE)
+		if (em->block_start != EXTENT_MAP_HOLE &&
+		    !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
 			return em;
 		else
 			hole_em = em;
@@ -5657,6 +5709,8 @@
 			 */
 			em->block_start = hole_em->block_start;
 			em->block_len = hole_len;
+			if (test_bit(EXTENT_FLAG_PREALLOC, &hole_em->flags))
+				set_bit(EXTENT_FLAG_PREALLOC, &em->flags);
 		} else {
 			em->start = range_start;
 			em->len = found;
@@ -6915,11 +6969,9 @@
 
 	/*
 	 * 1 for the truncate slack space
-	 * 1 for the orphan item we're going to add
-	 * 1 for the orphan item deletion
 	 * 1 for updating the inode.
 	 */
-	trans = btrfs_start_transaction(root, 4);
+	trans = btrfs_start_transaction(root, 2);
 	if (IS_ERR(trans)) {
 		err = PTR_ERR(trans);
 		goto out;
@@ -6930,12 +6982,6 @@
 				      min_size);
 	BUG_ON(ret);
 
-	ret = btrfs_orphan_add(trans, inode);
-	if (ret) {
-		btrfs_end_transaction(trans, root);
-		goto out;
-	}
-
 	/*
 	 * setattr is responsible for setting the ordered_data_close flag,
 	 * but that is only tested during the last file release.  That
@@ -7004,12 +7050,6 @@
 		ret = btrfs_orphan_del(trans, inode);
 		if (ret)
 			err = ret;
-	} else if (ret && inode->i_nlink > 0) {
-		/*
-		 * Failed to do the truncate, remove us from the in memory
-		 * orphan list.
-		 */
-		ret = btrfs_orphan_del(NULL, inode);
 	}
 
 	if (trans) {
@@ -7531,41 +7571,61 @@
  */
 int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput)
 {
-	struct list_head *head = &root->fs_info->delalloc_inodes;
 	struct btrfs_inode *binode;
 	struct inode *inode;
 	struct btrfs_delalloc_work *work, *next;
 	struct list_head works;
+	struct list_head splice;
 	int ret = 0;
 
 	if (root->fs_info->sb->s_flags & MS_RDONLY)
 		return -EROFS;
 
 	INIT_LIST_HEAD(&works);
-
+	INIT_LIST_HEAD(&splice);
+again:
 	spin_lock(&root->fs_info->delalloc_lock);
-	while (!list_empty(head)) {
-		binode = list_entry(head->next, struct btrfs_inode,
+	list_splice_init(&root->fs_info->delalloc_inodes, &splice);
+	while (!list_empty(&splice)) {
+		binode = list_entry(splice.next, struct btrfs_inode,
 				    delalloc_inodes);
+
+		list_del_init(&binode->delalloc_inodes);
+
 		inode = igrab(&binode->vfs_inode);
 		if (!inode)
-			list_del_init(&binode->delalloc_inodes);
+			continue;
+
+		list_add_tail(&binode->delalloc_inodes,
+			      &root->fs_info->delalloc_inodes);
 		spin_unlock(&root->fs_info->delalloc_lock);
-		if (inode) {
-			work = btrfs_alloc_delalloc_work(inode, 0, delay_iput);
-			if (!work) {
-				ret = -ENOMEM;
-				goto out;
-			}
-			list_add_tail(&work->list, &works);
-			btrfs_queue_worker(&root->fs_info->flush_workers,
-					   &work->work);
+
+		work = btrfs_alloc_delalloc_work(inode, 0, delay_iput);
+		if (unlikely(!work)) {
+			ret = -ENOMEM;
+			goto out;
 		}
+		list_add_tail(&work->list, &works);
+		btrfs_queue_worker(&root->fs_info->flush_workers,
+				   &work->work);
+
 		cond_resched();
 		spin_lock(&root->fs_info->delalloc_lock);
 	}
 	spin_unlock(&root->fs_info->delalloc_lock);
 
+	list_for_each_entry_safe(work, next, &works, list) {
+		list_del_init(&work->list);
+		btrfs_wait_and_free_delalloc_work(work);
+	}
+
+	spin_lock(&root->fs_info->delalloc_lock);
+	if (!list_empty(&root->fs_info->delalloc_inodes)) {
+		spin_unlock(&root->fs_info->delalloc_lock);
+		goto again;
+	}
+	spin_unlock(&root->fs_info->delalloc_lock);
+
 	/* the filemap_flush will queue IO into the worker threads, but
 	 * we have to make sure the IO is actually started and that
 	 * ordered extents get created before we return
@@ -7578,11 +7638,18 @@
 		    atomic_read(&root->fs_info->async_delalloc_pages) == 0));
 	}
 	atomic_dec(&root->fs_info->async_submit_draining);
+	return 0;
 out:
 	list_for_each_entry_safe(work, next, &works, list) {
 		list_del_init(&work->list);
 		btrfs_wait_and_free_delalloc_work(work);
 	}
+
+	if (!list_empty_careful(&splice)) {
+		spin_lock(&root->fs_info->delalloc_lock);
+		list_splice_tail(&splice, &root->fs_info->delalloc_inodes);
+		spin_unlock(&root->fs_info->delalloc_lock);
+	}
 	return ret;
 }
 
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 4b45167..338f259 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -515,7 +515,6 @@
 
 	BUG_ON(ret);
 
-	d_instantiate(dentry, btrfs_lookup_dentry(dir, dentry));
 fail:
 	if (async_transid) {
 		*async_transid = trans->transid;
@@ -525,6 +524,10 @@
 	}
 	if (err && !ret)
 		ret = err;
+
+	if (!ret)
+		d_instantiate(dentry, btrfs_lookup_dentry(dir, dentry));
+
 	return ret;
 }
 
@@ -1339,7 +1342,8 @@
 	if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running,
 			1)) {
 		pr_info("btrfs: dev add/delete/balance/replace/resize operation in progress\n");
-		return -EINPROGRESS;
+		mnt_drop_write_file(file);
+		return -EINVAL;
 	}
 
 	mutex_lock(&root->fs_info->volume_mutex);
@@ -1362,6 +1366,7 @@
 		printk(KERN_INFO "btrfs: resizing devid %llu\n",
 		       (unsigned long long)devid);
 	}
+
 	device = btrfs_find_device(root->fs_info, devid, NULL, NULL);
 	if (!device) {
 		printk(KERN_INFO "btrfs: resizer unable to find device %llu\n",
@@ -1369,9 +1374,10 @@
 		ret = -EINVAL;
 		goto out_free;
 	}
-	if (device->fs_devices && device->fs_devices->seeding) {
+
+	if (!device->writeable) {
 		printk(KERN_INFO "btrfs: resizer unable to apply on "
-		       "seeding device %llu\n",
+		       "readonly device %llu\n",
 		       (unsigned long long)devid);
 		ret = -EINVAL;
 		goto out_free;
@@ -1443,8 +1449,8 @@
 	kfree(vol_args);
 out:
 	mutex_unlock(&root->fs_info->volume_mutex);
-	mnt_drop_write_file(file);
 	atomic_set(&root->fs_info->mutually_exclusive_operation_running, 0);
+	mnt_drop_write_file(file);
 	return ret;
 }
 
@@ -2095,13 +2101,13 @@
 		err = inode_permission(inode, MAY_WRITE | MAY_EXEC);
 		if (err)
 			goto out_dput;
-
-		/* check if subvolume may be deleted by a non-root user */
-		err = btrfs_may_delete(dir, dentry, 1);
-		if (err)
-			goto out_dput;
 	}
 
+	/* check if subvolume may be deleted by a user */
+	err = btrfs_may_delete(dir, dentry, 1);
+	if (err)
+		goto out_dput;
+
 	if (btrfs_ino(inode) != BTRFS_FIRST_FREE_OBJECTID) {
 		err = -EINVAL;
 		goto out_dput;
@@ -2183,19 +2189,20 @@
 	struct btrfs_ioctl_defrag_range_args *range;
 	int ret;
 
-	if (btrfs_root_readonly(root))
-		return -EROFS;
+	ret = mnt_want_write_file(file);
+	if (ret)
+		return ret;
 
 	if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running,
 			1)) {
 		pr_info("btrfs: dev add/delete/balance/replace/resize operation in progress\n");
-		return -EINPROGRESS;
+		mnt_drop_write_file(file);
+		return -EINVAL;
 	}
-	ret = mnt_want_write_file(file);
-	if (ret) {
-		atomic_set(&root->fs_info->mutually_exclusive_operation_running,
-			   0);
-		return ret;
+
+	if (btrfs_root_readonly(root)) {
+		ret = -EROFS;
+		goto out;
 	}
 
 	switch (inode->i_mode & S_IFMT) {
@@ -2247,8 +2254,8 @@
 		ret = -EINVAL;
 	}
 out:
-	mnt_drop_write_file(file);
 	atomic_set(&root->fs_info->mutually_exclusive_operation_running, 0);
+	mnt_drop_write_file(file);
 	return ret;
 }
 
@@ -2263,7 +2270,7 @@
 	if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running,
 			1)) {
 		pr_info("btrfs: dev add/delete/balance/replace/resize operation in progress\n");
-		return -EINPROGRESS;
+		return -EINVAL;
 	}
 
 	mutex_lock(&root->fs_info->volume_mutex);
@@ -2300,7 +2307,7 @@
 			1)) {
 		pr_info("btrfs: dev add/delete/balance/replace/resize operation in progress\n");
 		mnt_drop_write_file(file);
-		return -EINPROGRESS;
+		return -EINVAL;
 	}
 
 	mutex_lock(&root->fs_info->volume_mutex);
@@ -2316,8 +2323,8 @@
 	kfree(vol_args);
 out:
 	mutex_unlock(&root->fs_info->volume_mutex);
-	mnt_drop_write_file(file);
 	atomic_set(&root->fs_info->mutually_exclusive_operation_running, 0);
+	mnt_drop_write_file(file);
 	return ret;
 }
 
@@ -3437,8 +3444,8 @@
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_ioctl_balance_args *bargs;
 	struct btrfs_balance_control *bctl;
+	bool need_unlock; /* for mut. excl. ops lock */
 	int ret;
-	int need_to_clear_lock = 0;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -3447,14 +3454,61 @@
 	if (ret)
 		return ret;
 
-	mutex_lock(&fs_info->volume_mutex);
+again:
+	if (!atomic_xchg(&fs_info->mutually_exclusive_operation_running, 1)) {
+		mutex_lock(&fs_info->volume_mutex);
+		mutex_lock(&fs_info->balance_mutex);
+		need_unlock = true;
+		goto locked;
+	}
+
+	/*
+	 * mut. excl. ops lock is locked.  Three possibilites:
+	 *   (1) some other op is running
+	 *   (2) balance is running
+	 *   (3) balance is paused -- special case (think resume)
+	 */
 	mutex_lock(&fs_info->balance_mutex);
+	if (fs_info->balance_ctl) {
+		/* this is either (2) or (3) */
+		if (!atomic_read(&fs_info->balance_running)) {
+			mutex_unlock(&fs_info->balance_mutex);
+			if (!mutex_trylock(&fs_info->volume_mutex))
+				goto again;
+			mutex_lock(&fs_info->balance_mutex);
+
+			if (fs_info->balance_ctl &&
+			    !atomic_read(&fs_info->balance_running)) {
+				/* this is (3) */
+				need_unlock = false;
+				goto locked;
+			}
+
+			mutex_unlock(&fs_info->balance_mutex);
+			mutex_unlock(&fs_info->volume_mutex);
+			goto again;
+		} else {
+			/* this is (2) */
+			mutex_unlock(&fs_info->balance_mutex);
+			ret = -EINPROGRESS;
+			goto out;
+		}
+	} else {
+		/* this is (1) */
+		mutex_unlock(&fs_info->balance_mutex);
+		pr_info("btrfs: dev add/delete/balance/replace/resize operation in progress\n");
+		ret = -EINVAL;
+		goto out;
+	}
+
+locked:
+	BUG_ON(!atomic_read(&fs_info->mutually_exclusive_operation_running));
 
 	if (arg) {
 		bargs = memdup_user(arg, sizeof(*bargs));
 		if (IS_ERR(bargs)) {
 			ret = PTR_ERR(bargs);
-			goto out;
+			goto out_unlock;
 		}
 
 		if (bargs->flags & BTRFS_BALANCE_RESUME) {
@@ -3474,13 +3528,10 @@
 		bargs = NULL;
 	}
 
-	if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running,
-			1)) {
-		pr_info("btrfs: dev add/delete/balance/replace/resize operation in progress\n");
+	if (fs_info->balance_ctl) {
 		ret = -EINPROGRESS;
 		goto out_bargs;
 	}
-	need_to_clear_lock = 1;
 
 	bctl = kzalloc(sizeof(*bctl), GFP_NOFS);
 	if (!bctl) {
@@ -3501,11 +3552,17 @@
 	}
 
 do_balance:
-	ret = btrfs_balance(bctl, bargs);
 	/*
-	 * bctl is freed in __cancel_balance or in free_fs_info if
-	 * restriper was paused all the way until unmount
+	 * Ownership of bctl and mutually_exclusive_operation_running
+	 * goes to to btrfs_balance.  bctl is freed in __cancel_balance,
+	 * or, if restriper was paused all the way until unmount, in
+	 * free_fs_info.  mutually_exclusive_operation_running is
+	 * cleared in __cancel_balance.
 	 */
+	need_unlock = false;
+
+	ret = btrfs_balance(bctl, bargs);
+
 	if (arg) {
 		if (copy_to_user(arg, bargs, sizeof(*bargs)))
 			ret = -EFAULT;
@@ -3513,12 +3570,12 @@
 
 out_bargs:
 	kfree(bargs);
-out:
-	if (need_to_clear_lock)
-		atomic_set(&root->fs_info->mutually_exclusive_operation_running,
-			   0);
+out_unlock:
 	mutex_unlock(&fs_info->balance_mutex);
 	mutex_unlock(&fs_info->volume_mutex);
+	if (need_unlock)
+		atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
+out:
 	mnt_drop_write_file(file);
 	return ret;
 }
@@ -3698,6 +3755,11 @@
 		goto drop_write;
 	}
 
+	if (!sa->qgroupid) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	trans = btrfs_join_transaction(root);
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index f107312..e5ed567 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -836,9 +836,16 @@
 	 * if the disk i_size is already at the inode->i_size, or
 	 * this ordered extent is inside the disk i_size, we're done
 	 */
-	if (disk_i_size == i_size || offset <= disk_i_size) {
+	if (disk_i_size == i_size)
 		goto out;
-	}
+
+	/*
+	 * We still need to update disk_i_size if outstanding_isize is greater
+	 * than disk_i_size.
+	 */
+	if (offset <= disk_i_size &&
+	    (!ordered || ordered->outstanding_isize <= disk_i_size))
+		goto out;
 
 	/*
 	 * walk backward from this ordered extent to disk_i_size.
@@ -870,7 +877,7 @@
 			break;
 		if (test->file_offset >= i_size)
 			break;
-		if (test->file_offset >= disk_i_size) {
+		if (entry_end(test) > disk_i_size) {
 			/*
 			 * we don't update disk_i_size now, so record this
 			 * undealt i_size. Or we will not know the real
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index fe9d02c..a5c8562 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -379,6 +379,13 @@
 
 		ret = add_relation_rb(fs_info, found_key.objectid,
 				      found_key.offset);
+		if (ret == -ENOENT) {
+			printk(KERN_WARNING
+				"btrfs: orphan qgroup relation 0x%llx->0x%llx\n",
+				(unsigned long long)found_key.objectid,
+				(unsigned long long)found_key.offset);
+			ret = 0;	/* ignore the error */
+		}
 		if (ret)
 			goto out;
 next2:
@@ -956,17 +963,28 @@
 			struct btrfs_fs_info *fs_info, u64 qgroupid)
 {
 	struct btrfs_root *quota_root;
+	struct btrfs_qgroup *qgroup;
 	int ret = 0;
 
 	quota_root = fs_info->quota_root;
 	if (!quota_root)
 		return -EINVAL;
 
+	/* check if there are no relations to this qgroup */
+	spin_lock(&fs_info->qgroup_lock);
+	qgroup = find_qgroup_rb(fs_info, qgroupid);
+	if (qgroup) {
+		if (!list_empty(&qgroup->groups) || !list_empty(&qgroup->members)) {
+			spin_unlock(&fs_info->qgroup_lock);
+			return -EBUSY;
+		}
+	}
+	spin_unlock(&fs_info->qgroup_lock);
+
 	ret = del_qgroup_item(trans, quota_root, qgroupid);
 
 	spin_lock(&fs_info->qgroup_lock);
 	del_qgroup_rb(quota_root->fs_info, qgroupid);
-
 	spin_unlock(&fs_info->qgroup_lock);
 
 	return ret;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index bdbb94f..67783e0 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -580,20 +580,29 @@
 	int corrected = 0;
 	struct btrfs_key key;
 	struct inode *inode = NULL;
+	struct btrfs_fs_info *fs_info;
 	u64 end = offset + PAGE_SIZE - 1;
 	struct btrfs_root *local_root;
+	int srcu_index;
 
 	key.objectid = root;
 	key.type = BTRFS_ROOT_ITEM_KEY;
 	key.offset = (u64)-1;
-	local_root = btrfs_read_fs_root_no_name(fixup->root->fs_info, &key);
-	if (IS_ERR(local_root))
+
+	fs_info = fixup->root->fs_info;
+	srcu_index = srcu_read_lock(&fs_info->subvol_srcu);
+
+	local_root = btrfs_read_fs_root_no_name(fs_info, &key);
+	if (IS_ERR(local_root)) {
+		srcu_read_unlock(&fs_info->subvol_srcu, srcu_index);
 		return PTR_ERR(local_root);
+	}
 
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.objectid = inum;
 	key.offset = 0;
-	inode = btrfs_iget(fixup->root->fs_info->sb, &key, local_root, NULL);
+	inode = btrfs_iget(fs_info->sb, &key, local_root, NULL);
+	srcu_read_unlock(&fs_info->subvol_srcu, srcu_index);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
 
@@ -606,7 +615,6 @@
 	}
 
 	if (PageUptodate(page)) {
-		struct btrfs_fs_info *fs_info;
 		if (PageDirty(page)) {
 			/*
 			 * we need to write the data to the defect sector. the
@@ -3180,18 +3188,25 @@
 	u64 physical_for_dev_replace;
 	u64 len;
 	struct btrfs_fs_info *fs_info = nocow_ctx->sctx->dev_root->fs_info;
+	int srcu_index;
 
 	key.objectid = root;
 	key.type = BTRFS_ROOT_ITEM_KEY;
 	key.offset = (u64)-1;
+
+	srcu_index = srcu_read_lock(&fs_info->subvol_srcu);
+
 	local_root = btrfs_read_fs_root_no_name(fs_info, &key);
-	if (IS_ERR(local_root))
+	if (IS_ERR(local_root)) {
+		srcu_read_unlock(&fs_info->subvol_srcu, srcu_index);
 		return PTR_ERR(local_root);
+	}
 
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.objectid = inum;
 	key.offset = 0;
 	inode = btrfs_iget(fs_info->sb, &key, local_root, NULL);
+	srcu_read_unlock(&fs_info->subvol_srcu, srcu_index);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
 
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 5445454..321b7fb 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -1814,8 +1814,10 @@
 			(unsigned long)nce->ino);
 	if (!nce_head) {
 		nce_head = kmalloc(sizeof(*nce_head), GFP_NOFS);
-		if (!nce_head)
+		if (!nce_head) {
+			kfree(nce);
 			return -ENOMEM;
+		}
 		INIT_LIST_HEAD(nce_head);
 
 		ret = radix_tree_insert(&sctx->name_cache, nce->ino, nce_head);
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 99545df..d8982e9 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -267,7 +267,7 @@
 			     function, line, errstr);
 		return;
 	}
-	trans->transaction->aborted = errno;
+	ACCESS_ONCE(trans->transaction->aborted) = errno;
 	__btrfs_std_error(root->fs_info, function, line, errno, NULL);
 }
 /*
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 87fac9a..fc03aa6 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -333,12 +333,14 @@
 					  &root->fs_info->trans_block_rsv,
 					  num_bytes, flush);
 		if (ret)
-			return ERR_PTR(ret);
+			goto reserve_fail;
 	}
 again:
 	h = kmem_cache_alloc(btrfs_trans_handle_cachep, GFP_NOFS);
-	if (!h)
-		return ERR_PTR(-ENOMEM);
+	if (!h) {
+		ret = -ENOMEM;
+		goto alloc_fail;
+	}
 
 	/*
 	 * If we are JOIN_NOLOCK we're already committing a transaction and
@@ -365,11 +367,7 @@
 	if (ret < 0) {
 		/* We must get the transaction if we are JOIN_NOLOCK. */
 		BUG_ON(type == TRANS_JOIN_NOLOCK);
-
-		if (type < TRANS_JOIN_NOLOCK)
-			sb_end_intwrite(root->fs_info->sb);
-		kmem_cache_free(btrfs_trans_handle_cachep, h);
-		return ERR_PTR(ret);
+		goto join_fail;
 	}
 
 	cur_trans = root->fs_info->running_transaction;
@@ -410,6 +408,19 @@
 	if (!current->journal_info && type != TRANS_USERSPACE)
 		current->journal_info = h;
 	return h;
+
+join_fail:
+	if (type < TRANS_JOIN_NOLOCK)
+		sb_end_intwrite(root->fs_info->sb);
+	kmem_cache_free(btrfs_trans_handle_cachep, h);
+alloc_fail:
+	if (num_bytes)
+		btrfs_block_rsv_release(root, &root->fs_info->trans_block_rsv,
+					num_bytes);
+reserve_fail:
+	if (qgroup_reserved)
+		btrfs_qgroup_free(root, qgroup_reserved);
+	return ERR_PTR(ret);
 }
 
 struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root,
@@ -1468,7 +1479,8 @@
 		goto cleanup_transaction;
 	}
 
-	if (cur_trans->aborted) {
+	/* Stop the commit early if ->aborted is set */
+	if (unlikely(ACCESS_ONCE(cur_trans->aborted))) {
 		ret = cur_trans->aborted;
 		goto cleanup_transaction;
 	}
@@ -1574,6 +1586,11 @@
 	wait_event(cur_trans->writer_wait,
 		   atomic_read(&cur_trans->num_writers) == 1);
 
+	/* ->aborted might be set after the previous check, so check it */
+	if (unlikely(ACCESS_ONCE(cur_trans->aborted))) {
+		ret = cur_trans->aborted;
+		goto cleanup_transaction;
+	}
 	/*
 	 * the reloc mutex makes sure that we stop
 	 * the balancing code from coming in and moving
@@ -1657,6 +1674,17 @@
 		goto cleanup_transaction;
 	}
 
+	/*
+	 * The tasks which save the space cache and inode cache may also
+	 * update ->aborted, check it.
+	 */
+	if (unlikely(ACCESS_ONCE(cur_trans->aborted))) {
+		ret = cur_trans->aborted;
+		mutex_unlock(&root->fs_info->tree_log_mutex);
+		mutex_unlock(&root->fs_info->reloc_mutex);
+		goto cleanup_transaction;
+	}
+
 	btrfs_prepare_extent_commit(trans, root);
 
 	cur_trans = root->fs_info->running_transaction;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 83186c7..9027bb1 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3357,6 +3357,11 @@
 	if (skip_csum)
 		return 0;
 
+	if (em->compress_type) {
+		csum_offset = 0;
+		csum_len = block_len;
+	}
+
 	/* block start is already adjusted for the file extent offset. */
 	ret = btrfs_lookup_csums_range(log->fs_info->csum_root,
 				       em->block_start + csum_offset,
@@ -3410,13 +3415,13 @@
 		em = list_entry(extents.next, struct extent_map, list);
 
 		list_del_init(&em->list);
-		clear_bit(EXTENT_FLAG_LOGGING, &em->flags);
 
 		/*
 		 * If we had an error we just need to delete everybody from our
 		 * private list.
 		 */
 		if (ret) {
+			clear_em_logging(tree, em);
 			free_extent_map(em);
 			continue;
 		}
@@ -3424,8 +3429,9 @@
 		write_unlock(&tree->lock);
 
 		ret = log_one_extent(trans, inode, root, em, path);
-		free_extent_map(em);
 		write_lock(&tree->lock);
+		clear_em_logging(tree, em);
+		free_extent_map(em);
 	}
 	WARN_ON(!list_empty(&extents));
 	write_unlock(&tree->lock);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 5cce6aa..5cbb7f4 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1431,7 +1431,7 @@
 		}
 	} else {
 		ret = btrfs_get_bdev_and_sb(device_path,
-					    FMODE_READ | FMODE_EXCL,
+					    FMODE_WRITE | FMODE_EXCL,
 					    root->fs_info->bdev_holder, 0,
 					    &bdev, &bh);
 		if (ret)
@@ -1556,7 +1556,8 @@
 	ret = 0;
 
 	/* Notify udev that device has changed */
-	btrfs_kobject_uevent(bdev, KOBJ_CHANGE);
+	if (bdev)
+		btrfs_kobject_uevent(bdev, KOBJ_CHANGE);
 
 error_brelse:
 	brelse(bh);
@@ -2614,7 +2615,14 @@
 	cache = btrfs_lookup_block_group(fs_info, chunk_offset);
 	chunk_used = btrfs_block_group_used(&cache->item);
 
-	user_thresh = div_factor_fine(cache->key.offset, bargs->usage);
+	if (bargs->usage == 0)
+		user_thresh = 0;
+	else if (bargs->usage > 100)
+		user_thresh = cache->key.offset;
+	else
+		user_thresh = div_factor_fine(cache->key.offset,
+					      bargs->usage);
+
 	if (chunk_used < user_thresh)
 		ret = 0;
 
@@ -2959,6 +2967,8 @@
 	unset_balance_control(fs_info);
 	ret = del_balance_item(fs_info->tree_root);
 	BUG_ON(ret);
+
+	atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
 }
 
 void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, int lock,
@@ -3138,8 +3148,10 @@
 out:
 	if (bctl->flags & BTRFS_BALANCE_RESUME)
 		__cancel_balance(fs_info);
-	else
+	else {
 		kfree(bctl);
+		atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
+	}
 	return ret;
 }
 
@@ -3156,7 +3168,6 @@
 		ret = btrfs_balance(fs_info->balance_ctl, NULL);
 	}
 
-	atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
 	mutex_unlock(&fs_info->balance_mutex);
 	mutex_unlock(&fs_info->volume_mutex);
 
@@ -3179,7 +3190,6 @@
 		return 0;
 	}
 
-	WARN_ON(atomic_xchg(&fs_info->mutually_exclusive_operation_running, 1));
 	tsk = kthread_run(balance_kthread, fs_info, "btrfs-balance");
 	if (IS_ERR(tsk))
 		return PTR_ERR(tsk);
@@ -3233,6 +3243,8 @@
 	btrfs_balance_sys(leaf, item, &disk_bargs);
 	btrfs_disk_balance_args_to_cpu(&bctl->sys, &disk_bargs);
 
+	WARN_ON(atomic_xchg(&fs_info->mutually_exclusive_operation_running, 1));
+
 	mutex_lock(&fs_info->volume_mutex);
 	mutex_lock(&fs_info->balance_mutex);
 
@@ -3496,7 +3508,7 @@
 	{ 1, 1, 2, 2, 2, 2 /* raid1 */ },
 	{ 1, 2, 1, 1, 1, 2 /* dup */ },
 	{ 1, 1, 0, 2, 1, 1 /* raid0 */ },
-	{ 1, 1, 0, 1, 1, 1 /* single */ },
+	{ 1, 1, 1, 1, 1, 1 /* single */ },
 };
 
 static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index ce5cbd7..210fce2 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -226,6 +226,8 @@
 compose_mount_options_err:
 	kfree(mountdata);
 	mountdata = ERR_PTR(rc);
+	kfree(*devname);
+	*devname = NULL;
 	goto compose_mount_options_out;
 }
 
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 17c3643..12b3da3 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -1917,7 +1917,7 @@
 	}
 	case AF_INET6: {
 		struct sockaddr_in6 *saddr6 = (struct sockaddr_in6 *)srcaddr;
-		struct sockaddr_in6 *vaddr6 = (struct sockaddr_in6 *)&rhs;
+		struct sockaddr_in6 *vaddr6 = (struct sockaddr_in6 *)rhs;
 		return ipv6_addr_equal(&saddr6->sin6_addr, &vaddr6->sin6_addr);
 	}
 	default:
diff --git a/fs/dlm/user.c b/fs/dlm/user.c
index 7ff4985..911649a 100644
--- a/fs/dlm/user.c
+++ b/fs/dlm/user.c
@@ -503,11 +503,11 @@
 #endif
 		return -EINVAL;
 
-#ifdef CONFIG_COMPAT
-	if (count > sizeof(struct dlm_write_request32) + DLM_RESNAME_MAXLEN)
-#else
+	/*
+	 * can't compare against COMPAT/dlm_write_request32 because
+	 * we don't yet know if is64bit is zero
+	 */
 	if (count > sizeof(struct dlm_write_request) + DLM_RESNAME_MAXLEN)
-#endif
 		return -EINVAL;
 
 	kbuf = kzalloc(count + 1, GFP_NOFS);
diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index b906ed1..9802de0 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -281,6 +281,7 @@
 {
 	struct gfs2_sbd *sdp = gl->gl_sbd;
 	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
+	int lvb_needs_unlock = 0;
 	int error;
 
 	if (gl->gl_lksb.sb_lkid == 0) {
@@ -294,8 +295,12 @@
 	gfs2_update_request_times(gl);
 
 	/* don't want to skip dlm_unlock writing the lvb when lock is ex */
+
+	if (gl->gl_lksb.sb_lvbptr && (gl->gl_state == LM_ST_EXCLUSIVE))
+		lvb_needs_unlock = 1;
+
 	if (test_bit(SDF_SKIP_DLM_UNLOCK, &sdp->sd_flags) &&
-	    gl->gl_lksb.sb_lvbptr && (gl->gl_state != LM_ST_EXCLUSIVE)) {
+	    !lvb_needs_unlock) {
 		gfs2_glock_free(gl);
 		return;
 	}
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index dd057bc..fc8dc20 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -177,11 +177,31 @@
 	return mnt;
 }
 
+static int
+nfs_namespace_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+{
+	if (NFS_FH(dentry->d_inode)->size != 0)
+		return nfs_getattr(mnt, dentry, stat);
+	generic_fillattr(dentry->d_inode, stat);
+	return 0;
+}
+
+static int
+nfs_namespace_setattr(struct dentry *dentry, struct iattr *attr)
+{
+	if (NFS_FH(dentry->d_inode)->size != 0)
+		return nfs_setattr(dentry, attr);
+	return -EACCES;
+}
+
 const struct inode_operations nfs_mountpoint_inode_operations = {
 	.getattr	= nfs_getattr,
+	.setattr	= nfs_setattr,
 };
 
 const struct inode_operations nfs_referral_inode_operations = {
+	.getattr	= nfs_namespace_getattr,
+	.setattr	= nfs_namespace_setattr,
 };
 
 static void nfs_expire_automounts(struct work_struct *work)
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index acc3472..2e9779b 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -236,11 +236,10 @@
 	error = nfs4_discover_server_trunking(clp, &old);
 	if (error < 0)
 		goto error;
+	nfs_put_client(clp);
 	if (clp != old) {
 		clp->cl_preserve_clid = true;
-		nfs_put_client(clp);
 		clp = old;
-		atomic_inc(&clp->cl_count);
 	}
 
 	return clp;
@@ -306,7 +305,7 @@
 		.clientid	= new->cl_clientid,
 		.confirm	= new->cl_confirm,
 	};
-	int status;
+	int status = -NFS4ERR_STALE_CLIENTID;
 
 	spin_lock(&nn->nfs_client_lock);
 	list_for_each_entry_safe(pos, n, &nn->nfs_client_list, cl_share_link) {
@@ -332,40 +331,33 @@
 
 		if (prev)
 			nfs_put_client(prev);
+		prev = pos;
 
 		status = nfs4_proc_setclientid_confirm(pos, &clid, cred);
-		if (status == 0) {
+		switch (status) {
+		case -NFS4ERR_STALE_CLIENTID:
+			break;
+		case 0:
 			nfs4_swap_callback_idents(pos, new);
 
-			nfs_put_client(pos);
+			prev = NULL;
 			*result = pos;
 			dprintk("NFS: <-- %s using nfs_client = %p ({%d})\n",
 				__func__, pos, atomic_read(&pos->cl_count));
-			return 0;
-		}
-		if (status != -NFS4ERR_STALE_CLIENTID) {
-			nfs_put_client(pos);
-			dprintk("NFS: <-- %s status = %d, no result\n",
-				__func__, status);
-			return status;
+		default:
+			goto out;
 		}
 
 		spin_lock(&nn->nfs_client_lock);
-		prev = pos;
 	}
+	spin_unlock(&nn->nfs_client_lock);
 
-	/*
-	 * No matching nfs_client found.  This should be impossible,
-	 * because the new nfs_client has already been added to
-	 * nfs_client_list by nfs_get_client().
-	 *
-	 * Don't BUG(), since the caller is holding a mutex.
-	 */
+	/* No match found. The server lost our clientid */
+out:
 	if (prev)
 		nfs_put_client(prev);
-	spin_unlock(&nn->nfs_client_lock);
-	pr_err("NFS: %s Error: no matching nfs_client found\n", __func__);
-	return -NFS4ERR_STALE_CLIENTID;
+	dprintk("NFS: <-- %s status = %d\n", __func__, status);
+	return status;
 }
 
 #ifdef CONFIG_NFS_V4_1
@@ -432,7 +424,7 @@
 {
 	struct nfs_net *nn = net_generic(new->cl_net, nfs_net_id);
 	struct nfs_client *pos, *n, *prev = NULL;
-	int error;
+	int status = -NFS4ERR_STALE_CLIENTID;
 
 	spin_lock(&nn->nfs_client_lock);
 	list_for_each_entry_safe(pos, n, &nn->nfs_client_list, cl_share_link) {
@@ -448,14 +440,17 @@
 				nfs_put_client(prev);
 			prev = pos;
 
-			error = nfs_wait_client_init_complete(pos);
-			if (error < 0) {
+			nfs4_schedule_lease_recovery(pos);
+			status = nfs_wait_client_init_complete(pos);
+			if (status < 0) {
 				nfs_put_client(pos);
 				spin_lock(&nn->nfs_client_lock);
 				continue;
 			}
-
+			status = pos->cl_cons_state;
 			spin_lock(&nn->nfs_client_lock);
+			if (status < 0)
+				continue;
 		}
 
 		if (pos->rpc_ops != new->rpc_ops)
@@ -473,6 +468,7 @@
 		if (!nfs4_match_serverowners(pos, new))
 			continue;
 
+		atomic_inc(&pos->cl_count);
 		spin_unlock(&nn->nfs_client_lock);
 		dprintk("NFS: <-- %s using nfs_client = %p ({%d})\n",
 			__func__, pos, atomic_read(&pos->cl_count));
@@ -481,16 +477,10 @@
 		return 0;
 	}
 
-	/*
-	 * No matching nfs_client found.  This should be impossible,
-	 * because the new nfs_client has already been added to
-	 * nfs_client_list by nfs_get_client().
-	 *
-	 * Don't BUG(), since the caller is holding a mutex.
-	 */
+	/* No matching nfs_client found. */
 	spin_unlock(&nn->nfs_client_lock);
-	pr_err("NFS: %s Error: no matching nfs_client found\n", __func__);
-	return -NFS4ERR_STALE_CLIENTID;
+	dprintk("NFS: <-- %s status = %d\n", __func__, status);
+	return status;
 }
 #endif	/* CONFIG_NFS_V4_1 */
 
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 9448c57..e61f68d 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -136,16 +136,11 @@
 	clp->cl_confirm = clid.confirm;
 
 	status = nfs40_walk_client_list(clp, result, cred);
-	switch (status) {
-	case -NFS4ERR_STALE_CLIENTID:
-		set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
-	case 0:
+	if (status == 0) {
 		/* Sustain the lease, even if it's empty.  If the clientid4
 		 * goes stale it's of no use for trunking discovery. */
 		nfs4_schedule_state_renewal(*result);
-		break;
 	}
-
 out:
 	return status;
 }
@@ -1863,6 +1858,7 @@
 	case -ETIMEDOUT:
 	case -EAGAIN:
 		ssleep(1);
+	case -NFS4ERR_STALE_CLIENTID:
 		dprintk("NFS: %s after status %d, retrying\n",
 			__func__, status);
 		goto again;
@@ -2022,8 +2018,18 @@
 	nfs4_begin_drain_session(clp);
 	cred = nfs4_get_exchange_id_cred(clp);
 	status = nfs4_proc_destroy_session(clp->cl_session, cred);
-	if (status && status != -NFS4ERR_BADSESSION &&
-	    status != -NFS4ERR_DEADSESSION) {
+	switch (status) {
+	case 0:
+	case -NFS4ERR_BADSESSION:
+	case -NFS4ERR_DEADSESSION:
+		break;
+	case -NFS4ERR_BACK_CHAN_BUSY:
+	case -NFS4ERR_DELAY:
+		set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
+		status = 0;
+		ssleep(1);
+		goto out;
+	default:
 		status = nfs4_recovery_handle_error(clp, status);
 		goto out;
 	}
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 2e7e8c8..b056b16 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2589,27 +2589,23 @@
 	struct nfs_server *server;
 	struct dentry *mntroot = ERR_PTR(-ENOMEM);
 	struct nfs_subversion *nfs_mod = NFS_SB(data->sb)->nfs_client->cl_nfs_mod;
-	int error;
 
-	dprintk("--> nfs_xdev_mount_common()\n");
+	dprintk("--> nfs_xdev_mount()\n");
 
 	mount_info.mntfh = mount_info.cloned->fh;
 
 	/* create a new volume representation */
 	server = nfs_mod->rpc_ops->clone_server(NFS_SB(data->sb), data->fh, data->fattr, data->authflavor);
-	if (IS_ERR(server)) {
-		error = PTR_ERR(server);
-		goto out_err;
-	}
 
-	mntroot = nfs_fs_mount_common(server, flags, dev_name, &mount_info, nfs_mod);
-	dprintk("<-- nfs_xdev_mount_common() = 0\n");
-out:
+	if (IS_ERR(server))
+		mntroot = ERR_CAST(server);
+	else
+		mntroot = nfs_fs_mount_common(server, flags,
+				dev_name, &mount_info, nfs_mod);
+
+	dprintk("<-- nfs_xdev_mount() = %ld\n",
+			IS_ERR(mntroot) ? PTR_ERR(mntroot) : 0L);
 	return mntroot;
-
-out_err:
-	dprintk("<-- nfs_xdev_mount_common() = %d [error]\n", error);
-	goto out;
 }
 
 #if IS_ENABLED(CONFIG_NFS_V4)
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index fdb1807..f385935 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -664,8 +664,11 @@
 	if (ret < 0)
 		printk(KERN_ERR "NILFS: GC failed during preparation: "
 			"cannot read source blocks: err=%d\n", ret);
-	else
+	else {
+		if (nilfs_sb_need_update(nilfs))
+			set_nilfs_discontinued(nilfs);
 		ret = nilfs_clean_segments(inode->i_sb, argv, kbufs);
+	}
 
 	nilfs_remove_all_gcinodes(nilfs);
 	clear_nilfs_gc_running(nilfs);
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 4111a40..5f707e5 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -86,11 +86,11 @@
 	}
 
 	if (ioend->io_iocb) {
+		inode_dio_done(ioend->io_inode);
 		if (ioend->io_isasync) {
 			aio_complete(ioend->io_iocb, ioend->io_error ?
 					ioend->io_error : ioend->io_result, 0);
 		}
-		inode_dio_done(ioend->io_inode);
 	}
 
 	mempool_free(ioend, xfs_ioend_pool);
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index 0e92d12..cdb2d33 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -4680,9 +4680,6 @@
 			return error;
 	}
 
-	if (bma->flags & XFS_BMAPI_STACK_SWITCH)
-		bma->stack_switch = 1;
-
 	error = xfs_bmap_alloc(bma);
 	if (error)
 		return error;
@@ -4956,6 +4953,9 @@
 	bma.flist = flist;
 	bma.firstblock = firstblock;
 
+	if (flags & XFS_BMAPI_STACK_SWITCH)
+		bma.stack_switch = 1;
+
 	while (bno < end && n < *nmap) {
 		inhole = eof || bma.got.br_startoff > bno;
 		wasdelay = !inhole && isnullstartblock(bma.got.br_startblock);
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 56d1614..fbbb9eb 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -487,6 +487,7 @@
 	struct rb_node		*parent;
 	xfs_buf_t		*bp;
 	xfs_daddr_t		blkno = map[0].bm_bn;
+	xfs_daddr_t		eofs;
 	int			numblks = 0;
 	int			i;
 
@@ -498,6 +499,23 @@
 	ASSERT(!(numbytes < (1 << btp->bt_sshift)));
 	ASSERT(!(BBTOB(blkno) & (xfs_off_t)btp->bt_smask));
 
+	/*
+	 * Corrupted block numbers can get through to here, unfortunately, so we
+	 * have to check that the buffer falls within the filesystem bounds.
+	 */
+	eofs = XFS_FSB_TO_BB(btp->bt_mount, btp->bt_mount->m_sb.sb_dblocks);
+	if (blkno >= eofs) {
+		/*
+		 * XXX (dgc): we should really be returning EFSCORRUPTED here,
+		 * but none of the higher level infrastructure supports
+		 * returning a specific error on buffer lookup failures.
+		 */
+		xfs_alert(btp->bt_mount,
+			  "%s: Block out of range: block 0x%llx, EOFS 0x%llx ",
+			  __func__, blkno, eofs);
+		return NULL;
+	}
+
 	/* get tree root */
 	pag = xfs_perag_get(btp->bt_mount,
 				xfs_daddr_to_agno(btp->bt_mount, blkno));
@@ -1487,6 +1505,8 @@
 	while (!list_empty(&btp->bt_lru)) {
 		bp = list_first_entry(&btp->bt_lru, struct xfs_buf, b_lru);
 		if (atomic_read(&bp->b_hold) > 1) {
+			trace_xfs_buf_wait_buftarg(bp, _RET_IP_);
+			list_move_tail(&bp->b_lru, &btp->bt_lru);
 			spin_unlock(&btp->bt_lru_lock);
 			delay(100);
 			goto restart;
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 77b0975..3f9949f 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -652,7 +652,10 @@
 
 	/*
 	 * If the buf item isn't tracking any data, free it, otherwise drop the
-	 * reference we hold to it.
+	 * reference we hold to it. If we are aborting the transaction, this may
+	 * be the only reference to the buf item, so we free it anyway
+	 * regardless of whether it is dirty or not. A dirty abort implies a
+	 * shutdown, anyway.
 	 */
 	clean = 1;
 	for (i = 0; i < bip->bli_format_count; i++) {
@@ -664,7 +667,12 @@
 	}
 	if (clean)
 		xfs_buf_item_relse(bp);
-	else
+	else if (aborted) {
+		if (atomic_dec_and_test(&bip->bli_refcount)) {
+			ASSERT(XFS_FORCED_SHUTDOWN(lip->li_mountp));
+			xfs_buf_item_relse(bp);
+		}
+	} else
 		atomic_dec(&bip->bli_refcount);
 
 	if (!hold)
diff --git a/fs/xfs/xfs_dfrag.c b/fs/xfs/xfs_dfrag.c
index d0e9c74..a8bd26b 100644
--- a/fs/xfs/xfs_dfrag.c
+++ b/fs/xfs/xfs_dfrag.c
@@ -246,10 +246,10 @@
 		goto out_unlock;
 	}
 
-	error = -filemap_write_and_wait(VFS_I(ip)->i_mapping);
+	error = -filemap_write_and_wait(VFS_I(tip)->i_mapping);
 	if (error)
 		goto out_unlock;
-	truncate_pagecache_range(VFS_I(ip), 0, -1);
+	truncate_pagecache_range(VFS_I(tip), 0, -1);
 
 	/* Verify O_DIRECT for ftmp */
 	if (VN_CACHED(VFS_I(tip)) != 0) {
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index add06b4..364818e 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -351,6 +351,15 @@
 		}
 		if (shift)
 			alloc_blocks >>= shift;
+
+		/*
+		 * If we are still trying to allocate more space than is
+		 * available, squash the prealloc hard. This can happen if we
+		 * have a large file on a small filesystem and the above
+		 * lowspace thresholds are smaller than MAXEXTLEN.
+		 */
+		while (alloc_blocks >= freesp)
+			alloc_blocks >>= 4;
 	}
 
 	if (alloc_blocks < mp->m_writeio_blocks)
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index da50846..7d6df7c 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -658,7 +658,7 @@
 		return;
 	}
 	/* quietly fail */
-	xfs_buf_ioerror(bp, EFSCORRUPTED);
+	xfs_buf_ioerror(bp, EWRONGFS);
 }
 
 static void
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 2e137d4..16a8129 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -341,6 +341,7 @@
 DEFINE_BUF_EVENT(xfs_buf_item_iodone);
 DEFINE_BUF_EVENT(xfs_buf_item_iodone_async);
 DEFINE_BUF_EVENT(xfs_buf_error_relse);
+DEFINE_BUF_EVENT(xfs_buf_wait_buftarg);
 DEFINE_BUF_EVENT(xfs_trans_read_buf_io);
 DEFINE_BUF_EVENT(xfs_trans_read_buf_shut);
 
diff --git a/include/linux/aer.h b/include/linux/aer.h
index 544abdb..ec10e1b 100644
--- a/include/linux/aer.h
+++ b/include/linux/aer.h
@@ -49,8 +49,8 @@
 }
 #endif
 
-extern void cper_print_aer(const char *prefix, int cper_severity,
-			   struct aer_capability_regs *aer);
+extern void cper_print_aer(const char *prefix, struct pci_dev *dev,
+			   int cper_severity, struct aer_capability_regs *aer);
 extern int cper_severity_to_aer(int cper_severity);
 extern void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn,
 			      int severity);
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 8b84916..7a9498a 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -618,18 +618,30 @@
 #endif
 
 /*
- * We play games with efi_enabled so that the compiler will, if possible, remove
- * EFI-related code altogether.
+ * We play games with efi_enabled so that the compiler will, if
+ * possible, remove EFI-related code altogether.
  */
+#define EFI_BOOT		0	/* Were we booted from EFI? */
+#define EFI_SYSTEM_TABLES	1	/* Can we use EFI system tables? */
+#define EFI_CONFIG_TABLES	2	/* Can we use EFI config tables? */
+#define EFI_RUNTIME_SERVICES	3	/* Can we use runtime services? */
+#define EFI_MEMMAP		4	/* Can we use EFI memory map? */
+#define EFI_64BIT		5	/* Is the firmware 64-bit? */
+
 #ifdef CONFIG_EFI
 # ifdef CONFIG_X86
-   extern int efi_enabled;
-   extern bool efi_64bit;
+extern int efi_enabled(int facility);
 # else
-#  define efi_enabled 1
+static inline int efi_enabled(int facility)
+{
+	return 1;
+}
 # endif
 #else
-# define efi_enabled 0
+static inline int efi_enabled(int facility)
+{
+	return 0;
+}
 #endif
 
 /*
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 92691d8..e5ca8ef 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -74,7 +74,7 @@
  * SAVE_REGS - The ftrace_ops wants regs saved at each function called
  *            and passed to the callback. If this flag is set, but the
  *            architecture does not support passing regs
- *            (ARCH_SUPPORTS_FTRACE_SAVE_REGS is not defined), then the
+ *            (CONFIG_DYNAMIC_FTRACE_WITH_REGS is not defined), then the
  *            ftrace_ops will fail to register, unless the next flag
  *            is set.
  * SAVE_REGS_IF_SUPPORTED - This is the same as SAVE_REGS, but if the
@@ -418,7 +418,7 @@
 #endif
 
 #ifndef FTRACE_REGS_ADDR
-#ifdef ARCH_SUPPORTS_FTRACE_SAVE_REGS
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 # define FTRACE_REGS_ADDR ((unsigned long)ftrace_regs_caller)
 #else
 # define FTRACE_REGS_ADDR FTRACE_ADDR
@@ -480,7 +480,7 @@
  */
 extern int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr);
 
-#ifdef ARCH_SUPPORTS_FTRACE_SAVE_REGS
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 /**
  * ftrace_modify_call - convert from one addr to another (no nop)
  * @rec: the mcount call site record
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index a3d4895..13a54d0 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -49,7 +49,6 @@
 	unsigned char		flags;
 	unsigned char		preempt_count;
 	int			pid;
-	int			padding;
 };
 
 #define FTRACE_MAX_EVENT						\
@@ -84,6 +83,9 @@
 	long			idx;
 
 	cpumask_var_t		started;
+
+	/* it's true when current open file is snapshot */
+	bool			snapshot;
 };
 
 enum trace_iter_flags {
@@ -272,7 +274,7 @@
 extern int trace_add_event_call(struct ftrace_event_call *call);
 extern void trace_remove_event_call(struct ftrace_event_call *call);
 
-#define is_signed_type(type)	(((type)(-1)) < 0)
+#define is_signed_type(type)	(((type)(-1)) < (type)0)
 
 int trace_set_clr_event(const char *system, const char *event, int set);
 
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index 7105d5c..29eb805 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -180,10 +180,10 @@
 
 #define nmi_enter()						\
 	do {							\
+		lockdep_off();					\
 		ftrace_nmi_enter();				\
 		BUG_ON(in_nmi());				\
 		add_preempt_count(NMI_OFFSET + HARDIRQ_OFFSET);	\
-		lockdep_off();					\
 		rcu_nmi_enter();				\
 		trace_hardirq_enter();				\
 	} while (0)
@@ -192,10 +192,10 @@
 	do {							\
 		trace_hardirq_exit();				\
 		rcu_nmi_exit();					\
-		lockdep_on();					\
 		BUG_ON(!in_nmi());				\
 		sub_preempt_count(NMI_OFFSET + HARDIRQ_OFFSET);	\
 		ftrace_nmi_exit();				\
+		lockdep_on();					\
 	} while (0)
 
 #endif /* LINUX_HARDIRQ_H */
diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h
index 6a9e8f5..f5dbce5 100644
--- a/include/linux/irq_work.h
+++ b/include/linux/irq_work.h
@@ -3,6 +3,20 @@
 
 #include <linux/llist.h>
 
+/*
+ * An entry can be in one of four states:
+ *
+ * free	     NULL, 0 -> {claimed}       : free to be used
+ * claimed   NULL, 3 -> {pending}       : claimed to be enqueued
+ * pending   next, 3 -> {busy}          : queued, pending callback
+ * busy      NULL, 2 -> {free, claimed} : callback in progress, can be claimed
+ */
+
+#define IRQ_WORK_PENDING	1UL
+#define IRQ_WORK_BUSY		2UL
+#define IRQ_WORK_FLAGS		3UL
+#define IRQ_WORK_LAZY		4UL /* Doesn't want IPI, wait for tick */
+
 struct irq_work {
 	unsigned long flags;
 	struct llist_node llnode;
@@ -16,8 +30,14 @@
 	work->func = func;
 }
 
-bool irq_work_queue(struct irq_work *work);
+void irq_work_queue(struct irq_work *work);
 void irq_work_run(void);
 void irq_work_sync(struct irq_work *work);
 
+#ifdef CONFIG_IRQ_WORK
+bool irq_work_needs_cpu(void);
+#else
+static bool irq_work_needs_cpu(void) { return false; }
+#endif
+
 #endif /* _LINUX_IRQ_WORK_H */
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 23755ba..4b6ef4d 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -49,16 +49,6 @@
 #define KPROBE_REENTER		0x00000004
 #define KPROBE_HIT_SSDONE	0x00000008
 
-/*
- * If function tracer is enabled and the arch supports full
- * passing of pt_regs to function tracing, then kprobes can
- * optimize on top of function tracing.
- */
-#if defined(CONFIG_FUNCTION_TRACER) && defined(ARCH_SUPPORTS_FTRACE_SAVE_REGS) \
-	&& defined(ARCH_SUPPORTS_KPROBES_ON_FTRACE)
-# define KPROBES_CAN_USE_FTRACE
-#endif
-
 /* Attach to insert probes on any functions which should be ignored*/
 #define __kprobes	__attribute__((__section__(".kprobes.text")))
 
@@ -316,7 +306,7 @@
 #endif
 
 #endif /* CONFIG_OPTPROBES */
-#ifdef KPROBES_CAN_USE_FTRACE
+#ifdef CONFIG_KPROBES_ON_FTRACE
 extern void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 				  struct ftrace_ops *ops, struct pt_regs *regs);
 extern int arch_prepare_kprobe_ftrace(struct kprobe *p);
diff --git a/include/linux/llist.h b/include/linux/llist.h
index a5199f6..d0ab98f 100644
--- a/include/linux/llist.h
+++ b/include/linux/llist.h
@@ -125,6 +125,31 @@
 	     (pos) = llist_entry((pos)->member.next, typeof(*(pos)), member))
 
 /**
+ * llist_for_each_entry_safe - iterate safely against remove over some entries
+ * of lock-less list of given type.
+ * @pos:	the type * to use as a loop cursor.
+ * @n:		another type * to use as a temporary storage.
+ * @node:	the fist entry of deleted list entries.
+ * @member:	the name of the llist_node with the struct.
+ *
+ * In general, some entries of the lock-less list can be traversed
+ * safely only after being removed from list, so start with an entry
+ * instead of list head. This variant allows removal of entries
+ * as we iterate.
+ *
+ * If being used on entries deleted from lock-less list directly, the
+ * traverse order is from the newest to the oldest added entry.  If
+ * you want to traverse from the oldest to the newest, you must
+ * reverse the order by yourself before traversing.
+ */
+#define llist_for_each_entry_safe(pos, n, node, member)		\
+	for ((pos) = llist_entry((node), typeof(*(pos)), member),	\
+	     (n) = (pos)->member.next;					\
+	     &(pos)->member != NULL;					\
+	     (pos) = llist_entry(n, typeof(*(pos)), member),		\
+	     (n) = (&(pos)->member != NULL) ? (pos)->member.next : NULL)
+
+/**
  * llist_empty - tests whether a lock-less list is empty
  * @head:	the list to test
  *
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 0108a56..28bd5fa 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -429,7 +429,7 @@
  * the slab_mutex must be held when looping through those caches
  */
 #define for_each_memcg_cache_index(_idx)	\
-	for ((_idx) = 0; i < memcg_limited_groups_array_size; (_idx)++)
+	for ((_idx) = 0; (_idx) < memcg_limited_groups_array_size; (_idx)++)
 
 static inline bool memcg_kmem_enabled(void)
 {
diff --git a/include/linux/mfd/abx500.h b/include/linux/mfd/abx500.h
index 2138bd3..e53dcfe 100644
--- a/include/linux/mfd/abx500.h
+++ b/include/linux/mfd/abx500.h
@@ -272,8 +272,6 @@
 	const struct abx500_fg_parameters *fg_params;
 };
 
-extern struct abx500_bm_data ab8500_bm_data;
-
 enum {
 	NTC_EXTERNAL = 0,
 	NTC_INTERNAL,
diff --git a/include/linux/mfd/abx500/ab8500-bm.h b/include/linux/mfd/abx500/ab8500-bm.h
index 44310c9..9bd037d 100644
--- a/include/linux/mfd/abx500/ab8500-bm.h
+++ b/include/linux/mfd/abx500/ab8500-bm.h
@@ -422,7 +422,10 @@
 struct ab8500_btemp;
 struct ab8500_gpadc;
 struct ab8500_fg;
+
 #ifdef CONFIG_AB8500_BM
+extern struct abx500_bm_data ab8500_bm_data;
+
 void ab8500_fg_reinit(void);
 void ab8500_charger_usb_state_changed(u8 bm_usb_state, u16 mA);
 struct ab8500_btemp *ab8500_btemp_get(void);
@@ -434,31 +437,7 @@
 int ab8500_fg_inst_curr_done(struct ab8500_fg *di);
 
 #else
-int ab8500_fg_inst_curr_done(struct ab8500_fg *di)
-{
-}
-static void ab8500_fg_reinit(void)
-{
-}
-static void ab8500_charger_usb_state_changed(u8 bm_usb_state, u16 mA)
-{
-}
-static struct ab8500_btemp *ab8500_btemp_get(void)
-{
-	return NULL;
-}
-static int ab8500_btemp_get_batctrl_temp(struct ab8500_btemp *btemp)
-{
-	return 0;
-}
-struct ab8500_fg *ab8500_fg_get(void)
-{
-	return NULL;
-}
-static int ab8500_fg_inst_curr_blocking(struct ab8500_fg *dev)
-{
-	return -ENODEV;
-}
+static struct abx500_bm_data ab8500_bm_data;
 
 static inline int ab8500_fg_inst_curr_start(struct ab8500_fg *di)
 {
diff --git a/include/linux/mfd/da9052/da9052.h b/include/linux/mfd/da9052/da9052.h
index 86dd93d..786d02e 100644
--- a/include/linux/mfd/da9052/da9052.h
+++ b/include/linux/mfd/da9052/da9052.h
@@ -99,6 +99,9 @@
 	u8 chip_id;
 
 	int chip_irq;
+
+	/* SOC I/O transfer related fixes for DA9052/53 */
+	int (*fix_io) (struct da9052 *da9052, unsigned char reg);
 };
 
 /* ADC API */
@@ -113,32 +116,87 @@
 	ret = regmap_read(da9052->regmap, reg, &val);
 	if (ret < 0)
 		return ret;
+
+	if (da9052->fix_io) {
+		ret = da9052->fix_io(da9052, reg);
+		if (ret < 0)
+			return ret;
+	}
+
 	return val;
 }
 
 static inline int da9052_reg_write(struct da9052 *da9052, unsigned char reg,
 				    unsigned char val)
 {
-	return regmap_write(da9052->regmap, reg, val);
+	int ret;
+
+	ret = regmap_write(da9052->regmap, reg, val);
+	if (ret < 0)
+		return ret;
+
+	if (da9052->fix_io) {
+		ret = da9052->fix_io(da9052, reg);
+		if (ret < 0)
+			return ret;
+	}
+
+	return ret;
 }
 
 static inline int da9052_group_read(struct da9052 *da9052, unsigned char reg,
 				     unsigned reg_cnt, unsigned char *val)
 {
-	return regmap_bulk_read(da9052->regmap, reg, val, reg_cnt);
+	int ret;
+
+	ret = regmap_bulk_read(da9052->regmap, reg, val, reg_cnt);
+	if (ret < 0)
+		return ret;
+
+	if (da9052->fix_io) {
+		ret = da9052->fix_io(da9052, reg);
+		if (ret < 0)
+			return ret;
+	}
+
+	return ret;
 }
 
 static inline int da9052_group_write(struct da9052 *da9052, unsigned char reg,
 				      unsigned reg_cnt, unsigned char *val)
 {
-	return regmap_raw_write(da9052->regmap, reg, val, reg_cnt);
+	int ret;
+
+	ret = regmap_raw_write(da9052->regmap, reg, val, reg_cnt);
+	if (ret < 0)
+		return ret;
+
+	if (da9052->fix_io) {
+		ret = da9052->fix_io(da9052, reg);
+		if (ret < 0)
+			return ret;
+	}
+
+	return ret;
 }
 
 static inline int da9052_reg_update(struct da9052 *da9052, unsigned char reg,
 				     unsigned char bit_mask,
 				     unsigned char reg_val)
 {
-	return regmap_update_bits(da9052->regmap, reg, bit_mask, reg_val);
+	int ret;
+
+	ret = regmap_update_bits(da9052->regmap, reg, bit_mask, reg_val);
+	if (ret < 0)
+		return ret;
+
+	if (da9052->fix_io) {
+		ret = da9052->fix_io(da9052, reg);
+		if (ret < 0)
+			return ret;
+	}
+
+	return ret;
 }
 
 int da9052_device_init(struct da9052 *da9052, u8 chip_id);
diff --git a/include/linux/mfd/da9052/reg.h b/include/linux/mfd/da9052/reg.h
index b97f730..c4dd3a8 100644
--- a/include/linux/mfd/da9052/reg.h
+++ b/include/linux/mfd/da9052/reg.h
@@ -34,6 +34,9 @@
 #define DA9052_STATUS_C_REG		3
 #define DA9052_STATUS_D_REG		4
 
+/* PARK REGISTER */
+#define DA9052_PARK_REGISTER		DA9052_STATUS_D_REG
+
 /* EVENT REGISTERS */
 #define DA9052_EVENT_A_REG		5
 #define DA9052_EVENT_B_REG		6
diff --git a/include/linux/mfd/rtsx_common.h b/include/linux/mfd/rtsx_common.h
index a8d393e..2b13970 100644
--- a/include/linux/mfd/rtsx_common.h
+++ b/include/linux/mfd/rtsx_common.h
@@ -38,6 +38,9 @@
 #define RTSX_SD_CARD			0
 #define RTSX_MS_CARD			1
 
+#define CLK_TO_DIV_N			0
+#define DIV_N_TO_CLK			1
+
 struct platform_device;
 
 struct rtsx_slot {
diff --git a/include/linux/mfd/rtsx_pci.h b/include/linux/mfd/rtsx_pci.h
index 060b721..4b117a3 100644
--- a/include/linux/mfd/rtsx_pci.h
+++ b/include/linux/mfd/rtsx_pci.h
@@ -158,10 +158,9 @@
 #define SG_TRANS_DATA		(0x02 << 4)
 #define SG_LINK_DESC		(0x03 << 4)
 
-/* SD bank voltage */
-#define SD_IO_3V3		0
-#define SD_IO_1V8		1
-
+/* Output voltage */
+#define OUTPUT_3V3		0
+#define OUTPUT_1V8		1
 
 /* Card Clock Enable Register */
 #define SD_CLK_EN			0x04
@@ -201,6 +200,20 @@
 #define CHANGE_CLK			0x01
 
 /* LDO_CTL */
+#define BPP_ASIC_1V7			0x00
+#define BPP_ASIC_1V8			0x01
+#define BPP_ASIC_1V9			0x02
+#define BPP_ASIC_2V0			0x03
+#define BPP_ASIC_2V7			0x04
+#define BPP_ASIC_2V8			0x05
+#define BPP_ASIC_3V2			0x06
+#define BPP_ASIC_3V3			0x07
+#define BPP_REG_TUNED18			0x07
+#define BPP_TUNED18_SHIFT_8402		5
+#define BPP_TUNED18_SHIFT_8411		4
+#define BPP_PAD_MASK			0x04
+#define BPP_PAD_3V3			0x04
+#define BPP_PAD_1V8			0x00
 #define BPP_LDO_POWB			0x03
 #define BPP_LDO_ON			0x00
 #define BPP_LDO_SUSPEND			0x02
@@ -688,7 +701,10 @@
 	int		(*disable_auto_blink)(struct rtsx_pcr *pcr);
 	int		(*card_power_on)(struct rtsx_pcr *pcr, int card);
 	int		(*card_power_off)(struct rtsx_pcr *pcr, int card);
+	int		(*switch_output_voltage)(struct rtsx_pcr *pcr,
+						u8 voltage);
 	unsigned int	(*cd_deglitch)(struct rtsx_pcr *pcr);
+	int		(*conv_clk_and_div_n)(int clk, int dir);
 };
 
 enum PDEV_STAT  {PDEV_STAT_IDLE, PDEV_STAT_RUN};
@@ -783,6 +799,7 @@
 		u8 ssc_depth, bool initial_mode, bool double_clk, bool vpclk);
 int rtsx_pci_card_power_on(struct rtsx_pcr *pcr, int card);
 int rtsx_pci_card_power_off(struct rtsx_pcr *pcr, int card);
+int rtsx_pci_switch_output_voltage(struct rtsx_pcr *pcr, u8 voltage);
 unsigned int rtsx_pci_card_exist(struct rtsx_pcr *pcr);
 void rtsx_pci_complete_unfinished_transfer(struct rtsx_pcr *pcr);
 
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index bc823c4..deca874 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -151,7 +151,7 @@
  * Therefore notifier chains can only be traversed when either
  *
  * 1. mmap_sem is held.
- * 2. One of the reverse map locks is held (i_mmap_mutex or anon_vma->mutex).
+ * 2. One of the reverse map locks is held (i_mmap_mutex or anon_vma->rwsem).
  * 3. No other concurrent thread can access the list (release)
  */
 struct mmu_notifier {
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 6bfb2faa..e47ee46 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -135,16 +135,21 @@
 		struct { /* software */
 			struct hrtimer	hrtimer;
 		};
+		struct { /* tracepoint */
+			struct task_struct	*tp_target;
+			/* for tp_event->class */
+			struct list_head	tp_list;
+		};
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 		struct { /* breakpoint */
-			struct arch_hw_breakpoint	info;
-			struct list_head		bp_list;
 			/*
 			 * Crufty hack to avoid the chicken and egg
 			 * problem hw_breakpoint has with context
 			 * creation and event initalization.
 			 */
 			struct task_struct		*bp_target;
+			struct arch_hw_breakpoint	info;
+			struct list_head		bp_list;
 		};
 #endif
 	};
@@ -817,6 +822,17 @@
 } while (0)
 
 
+struct perf_pmu_events_attr {
+	struct device_attribute attr;
+	u64 id;
+};
+
+#define PMU_EVENT_ATTR(_name, _var, _id, _show)				\
+static struct perf_pmu_events_attr _var = {				\
+	.attr = __ATTR(_name, 0444, _show, NULL),			\
+	.id   =  _id,							\
+};
+
 #define PMU_FORMAT_ATTR(_name, _format)					\
 static ssize_t								\
 _name##_show(struct device *dev,					\
diff --git a/arch/arm/mach-imx/iram.h b/include/linux/platform_data/imx-iram.h
similarity index 100%
rename from arch/arm/mach-imx/iram.h
rename to include/linux/platform_data/imx-iram.h
diff --git a/include/linux/printk.h b/include/linux/printk.h
index 9afc01e..86c4b62 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -98,9 +98,6 @@
 extern asmlinkage __printf(1, 2)
 void early_printk(const char *fmt, ...);
 
-extern int printk_needs_cpu(int cpu);
-extern void printk_tick(void);
-
 #ifdef CONFIG_PRINTK
 asmlinkage __printf(5, 0)
 int vprintk_emit(int facility, int level,
diff --git a/include/linux/profile.h b/include/linux/profile.h
index a0fc322..2112390 100644
--- a/include/linux/profile.h
+++ b/include/linux/profile.h
@@ -82,9 +82,6 @@
 int profile_event_register(enum profile_type, struct notifier_block * n);
 int profile_event_unregister(enum profile_type, struct notifier_block * n);
 
-int register_timer_hook(int (*hook)(struct pt_regs *));
-void unregister_timer_hook(int (*hook)(struct pt_regs *));
-
 struct pt_regs;
 
 #else
@@ -135,16 +132,6 @@
 #define profile_handoff_task(a) (0)
 #define profile_munmap(a) do { } while (0)
 
-static inline int register_timer_hook(int (*hook)(struct pt_regs *))
-{
-	return -ENOSYS;
-}
-
-static inline void unregister_timer_hook(int (*hook)(struct pt_regs *))
-{
-	return;
-}
-
 #endif /* CONFIG_PROFILING */
 
 #endif /* _LINUX_PROFILE_H */
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 275aa3f..b758ce1 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -53,7 +53,10 @@
 extern void rcutorture_record_test_transition(void);
 extern void rcutorture_record_progress(unsigned long vernum);
 extern void do_trace_rcu_torture_read(char *rcutorturename,
-				      struct rcu_head *rhp);
+				      struct rcu_head *rhp,
+				      unsigned long secs,
+				      unsigned long c_old,
+				      unsigned long c);
 #else
 static inline void rcutorture_record_test_transition(void)
 {
@@ -63,9 +66,13 @@
 }
 #ifdef CONFIG_RCU_TRACE
 extern void do_trace_rcu_torture_read(char *rcutorturename,
-				      struct rcu_head *rhp);
+				      struct rcu_head *rhp,
+				      unsigned long secs,
+				      unsigned long c_old,
+				      unsigned long c);
 #else
-#define do_trace_rcu_torture_read(rcutorturename, rhp) do { } while (0)
+#define do_trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \
+	do { } while (0)
 #endif
 #endif
 
@@ -749,7 +756,7 @@
  * preemptible RCU implementations (TREE_PREEMPT_RCU and TINY_PREEMPT_RCU)
  * in CONFIG_PREEMPT kernel builds, RCU read-side critical sections may
  * be preempted, but explicit blocking is illegal.  Finally, in preemptible
- * RCU implementations in real-time (CONFIG_PREEMPT_RT) kernel builds,
+ * RCU implementations in real-time (with -rt patchset) kernel builds,
  * RCU read-side critical sections may be preempted and they may also
  * block, but only when acquiring spinlocks that are subject to priority
  * inheritance.
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 519777e..1342e69 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -167,6 +167,7 @@
 unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu);
 unsigned long ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu);
 unsigned long ring_buffer_dropped_events_cpu(struct ring_buffer *buffer, int cpu);
+unsigned long ring_buffer_read_events_cpu(struct ring_buffer *buffer, int cpu);
 
 u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu);
 void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer,
diff --git a/include/linux/security.h b/include/linux/security.h
index 0f6afc6..eee7478 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -989,17 +989,29 @@
  *	tells the LSM to decrement the number of secmark labeling rules loaded
  * @req_classify_flow:
  *	Sets the flow's sid to the openreq sid.
+ * @tun_dev_alloc_security:
+ *	This hook allows a module to allocate a security structure for a TUN
+ *	device.
+ *	@security pointer to a security structure pointer.
+ *	Returns a zero on success, negative values on failure.
+ * @tun_dev_free_security:
+ *	This hook allows a module to free the security structure for a TUN
+ *	device.
+ *	@security pointer to the TUN device's security structure
  * @tun_dev_create:
  *	Check permissions prior to creating a new TUN device.
- * @tun_dev_post_create:
- *	This hook allows a module to update or allocate a per-socket security
- *	structure.
- *	@sk contains the newly created sock structure.
+ * @tun_dev_attach_queue:
+ *	Check permissions prior to attaching to a TUN device queue.
+ *	@security pointer to the TUN device's security structure.
  * @tun_dev_attach:
- *	Check permissions prior to attaching to a persistent TUN device.  This
- *	hook can also be used by the module to update any security state
+ *	This hook can be used by the module to update any security state
  *	associated with the TUN device's sock structure.
  *	@sk contains the existing sock structure.
+ *	@security pointer to the TUN device's security structure.
+ * @tun_dev_open:
+ *	This hook can be used by the module to update any security state
+ *	associated with the TUN device's security structure.
+ *	@security pointer to the TUN devices's security structure.
  *
  * Security hooks for XFRM operations.
  *
@@ -1620,9 +1632,12 @@
 	void (*secmark_refcount_inc) (void);
 	void (*secmark_refcount_dec) (void);
 	void (*req_classify_flow) (const struct request_sock *req, struct flowi *fl);
-	int (*tun_dev_create)(void);
-	void (*tun_dev_post_create)(struct sock *sk);
-	int (*tun_dev_attach)(struct sock *sk);
+	int (*tun_dev_alloc_security) (void **security);
+	void (*tun_dev_free_security) (void *security);
+	int (*tun_dev_create) (void);
+	int (*tun_dev_attach_queue) (void *security);
+	int (*tun_dev_attach) (struct sock *sk, void *security);
+	int (*tun_dev_open) (void *security);
 #endif	/* CONFIG_SECURITY_NETWORK */
 
 #ifdef CONFIG_SECURITY_NETWORK_XFRM
@@ -2566,9 +2581,12 @@
 int security_secmark_relabel_packet(u32 secid);
 void security_secmark_refcount_inc(void);
 void security_secmark_refcount_dec(void);
+int security_tun_dev_alloc_security(void **security);
+void security_tun_dev_free_security(void *security);
 int security_tun_dev_create(void);
-void security_tun_dev_post_create(struct sock *sk);
-int security_tun_dev_attach(struct sock *sk);
+int security_tun_dev_attach_queue(void *security);
+int security_tun_dev_attach(struct sock *sk, void *security);
+int security_tun_dev_open(void *security);
 
 #else	/* CONFIG_SECURITY_NETWORK */
 static inline int security_unix_stream_connect(struct sock *sock,
@@ -2733,16 +2751,31 @@
 {
 }
 
+static inline int security_tun_dev_alloc_security(void **security)
+{
+	return 0;
+}
+
+static inline void security_tun_dev_free_security(void *security)
+{
+}
+
 static inline int security_tun_dev_create(void)
 {
 	return 0;
 }
 
-static inline void security_tun_dev_post_create(struct sock *sk)
+static inline int security_tun_dev_attach_queue(void *security)
 {
+	return 0;
 }
 
-static inline int security_tun_dev_attach(struct sock *sk)
+static inline int security_tun_dev_attach(struct sock *sk, void *security)
+{
+	return 0;
+}
+
+static inline int security_tun_dev_open(void *security)
 {
 	return 0;
 }
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index 6eb691b..04f4121 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -151,30 +151,14 @@
  * Checks debug_lockdep_rcu_enabled() to prevent false positives during boot
  * and while lockdep is disabled.
  *
- * Note that if the CPU is in the idle loop from an RCU point of view
- * (ie: that we are in the section between rcu_idle_enter() and
- * rcu_idle_exit()) then srcu_read_lock_held() returns false even if
- * the CPU did an srcu_read_lock().  The reason for this is that RCU
- * ignores CPUs that are in such a section, considering these as in
- * extended quiescent state, so such a CPU is effectively never in an
- * RCU read-side critical section regardless of what RCU primitives it
- * invokes.  This state of affairs is required --- we need to keep an
- * RCU-free window in idle where the CPU may possibly enter into low
- * power mode. This way we can notice an extended quiescent state to
- * other CPUs that started a grace period. Otherwise we would delay any
- * grace period as long as we run in the idle task.
- *
- * Similarly, we avoid claiming an SRCU read lock held if the current
- * CPU is offline.
+ * Note that SRCU is based on its own statemachine and it doesn't
+ * relies on normal RCU, it can be called from the CPU which
+ * is in the idle loop from an RCU point of view or offline.
  */
 static inline int srcu_read_lock_held(struct srcu_struct *sp)
 {
 	if (!debug_lockdep_rcu_enabled())
 		return 1;
-	if (rcu_is_cpu_idle())
-		return 0;
-	if (!rcu_lockdep_current_cpu_online())
-		return 0;
 	return lock_is_held(&sp->dep_map);
 }
 
@@ -236,8 +220,6 @@
 	int retval = __srcu_read_lock(sp);
 
 	rcu_lock_acquire(&(sp)->dep_map);
-	rcu_lockdep_assert(!rcu_is_cpu_idle(),
-			   "srcu_read_lock() used illegally while idle");
 	return retval;
 }
 
@@ -251,8 +233,6 @@
 static inline void srcu_read_unlock(struct srcu_struct *sp, int idx)
 	__releases(sp)
 {
-	rcu_lockdep_assert(!rcu_is_cpu_idle(),
-			   "srcu_read_unlock() used illegally while idle");
 	rcu_lock_release(&(sp)->dep_map);
 	__srcu_read_unlock(sp, idx);
 }
diff --git a/include/linux/tick.h b/include/linux/tick.h
index 1a6567b..553272e 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -8,6 +8,8 @@
 
 #include <linux/clockchips.h>
 #include <linux/irqflags.h>
+#include <linux/percpu.h>
+#include <linux/hrtimer.h>
 
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
 
@@ -122,13 +124,26 @@
 #endif /* !CONFIG_GENERIC_CLOCKEVENTS */
 
 # ifdef CONFIG_NO_HZ
+DECLARE_PER_CPU(struct tick_sched, tick_cpu_sched);
+
+static inline int tick_nohz_tick_stopped(void)
+{
+	return __this_cpu_read(tick_cpu_sched.tick_stopped);
+}
+
 extern void tick_nohz_idle_enter(void);
 extern void tick_nohz_idle_exit(void);
 extern void tick_nohz_irq_exit(void);
 extern ktime_t tick_nohz_get_sleep_length(void);
 extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time);
 extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time);
-# else
+
+# else /* !CONFIG_NO_HZ */
+static inline int tick_nohz_tick_stopped(void)
+{
+	return 0;
+}
+
 static inline void tick_nohz_idle_enter(void) { }
 static inline void tick_nohz_idle_exit(void) { }
 
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index 4f628a6..02b83db 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -35,13 +35,20 @@
 # include <asm/uprobes.h>
 #endif
 
+#define UPROBE_HANDLER_REMOVE		1
+#define UPROBE_HANDLER_MASK		1
+
+enum uprobe_filter_ctx {
+	UPROBE_FILTER_REGISTER,
+	UPROBE_FILTER_UNREGISTER,
+	UPROBE_FILTER_MMAP,
+};
+
 struct uprobe_consumer {
 	int (*handler)(struct uprobe_consumer *self, struct pt_regs *regs);
-	/*
-	 * filter is optional; If a filter exists, handler is run
-	 * if and only if filter returns true.
-	 */
-	bool (*filter)(struct uprobe_consumer *self, struct task_struct *task);
+	bool (*filter)(struct uprobe_consumer *self,
+				enum uprobe_filter_ctx ctx,
+				struct mm_struct *mm);
 
 	struct uprobe_consumer *next;
 };
@@ -94,6 +101,7 @@
 extern int __weak set_orig_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr);
 extern bool __weak is_swbp_insn(uprobe_opcode_t *insn);
 extern int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc);
+extern int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool);
 extern void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc);
 extern int uprobe_mmap(struct vm_area_struct *vma);
 extern void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end);
@@ -117,6 +125,11 @@
 {
 	return -ENOSYS;
 }
+static inline int
+uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool add)
+{
+	return -ENOSYS;
+}
 static inline void
 uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc)
 {
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 689b14b..4d22d0f 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -357,6 +357,8 @@
 	int bandwidth_int_reqs;		/* number of Interrupt requests */
 	int bandwidth_isoc_reqs;	/* number of Isoc. requests */
 
+	unsigned resuming_ports;	/* bit array: resuming root-hub ports */
+
 #if defined(CONFIG_USB_MON) || defined(CONFIG_USB_MON_MODULE)
 	struct mon_bus *mon_bus;	/* non-null when associated */
 	int monitored;			/* non-zero when monitored */
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index 608050b..0a78df5 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -430,6 +430,9 @@
 extern void usb_wakeup_notification(struct usb_device *hdev,
 		unsigned int portnum);
 
+extern void usb_hcd_start_port_resume(struct usb_bus *bus, int portnum);
+extern void usb_hcd_end_port_resume(struct usb_bus *bus, int portnum);
+
 /* The D0/D1 toggle bits ... USE WITH CAUTION (they're almost hcd-internal) */
 #define usb_gettoggle(dev, ep, out) (((dev)->toggle[out] >> (ep)) & 1)
 #define	usb_dotoggle(dev, ep, out)  ((dev)->toggle[out] ^= (1 << (ep)))
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index bd45eb7..0e5ac93 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -33,6 +33,7 @@
 	wait_queue_head_t	*wait;
 	struct mutex		phy_mutex;
 	unsigned char		suspend_count;
+	unsigned char		pkt_cnt, pkt_err;
 
 	/* i/o info: pipes etc */
 	unsigned		in, out;
@@ -70,6 +71,7 @@
 #		define EVENT_DEV_OPEN	7
 #		define EVENT_DEVICE_REPORT_IDLE	8
 #		define EVENT_NO_RUNTIME_PM	9
+#		define EVENT_RX_KILL	10
 };
 
 static inline struct usb_driver *driver_of(struct usb_interface *intf)
@@ -107,6 +109,7 @@
  */
 #define FLAG_MULTI_PACKET	0x2000
 #define FLAG_RX_ASSEMBLE	0x4000	/* rx packets may span >1 frames */
+#define FLAG_NOARP		0x8000	/* device can't do ARP */
 
 	/* init device ... can sleep, or cause probe() failure */
 	int	(*bind)(struct usbnet *, struct usb_interface *);
diff --git a/include/net/ip.h b/include/net/ip.h
index 0707fb9..a68f838 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -143,6 +143,8 @@
 extern int		ip4_datagram_connect(struct sock *sk, 
 					     struct sockaddr *uaddr, int addr_len);
 
+extern void ip4_datagram_release_cb(struct sock *sk);
+
 struct ip_reply_arg {
 	struct kvec iov[1];   
 	int	    flags;
diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h
index d8f5b9f..e98aeb3 100644
--- a/include/net/netfilter/nf_conntrack_core.h
+++ b/include/net/netfilter/nf_conntrack_core.h
@@ -31,6 +31,8 @@
 extern int nf_conntrack_proto_init(struct net *net);
 extern void nf_conntrack_proto_fini(struct net *net);
 
+extern void nf_conntrack_cleanup_end(void);
+
 extern bool
 nf_ct_get_tuple(const struct sk_buff *skb,
 		unsigned int nhoff,
diff --git a/include/net/transp_v6.h b/include/net/transp_v6.h
index 498433d..938b7fd 100644
--- a/include/net/transp_v6.h
+++ b/include/net/transp_v6.h
@@ -34,17 +34,17 @@
 						      struct sockaddr *uaddr,
 						      int addr_len);
 
-extern int			datagram_recv_ctl(struct sock *sk,
-						  struct msghdr *msg,
-						  struct sk_buff *skb);
+extern int			ip6_datagram_recv_ctl(struct sock *sk,
+						      struct msghdr *msg,
+						      struct sk_buff *skb);
 
-extern int			datagram_send_ctl(struct net *net,
-						  struct sock *sk,
-						  struct msghdr *msg,
-						  struct flowi6 *fl6,
-						  struct ipv6_txoptions *opt,
-						  int *hlimit, int *tclass,
-						  int *dontfrag);
+extern int			ip6_datagram_send_ctl(struct net *net,
+						      struct sock *sk,
+						      struct msghdr *msg,
+						      struct flowi6 *fl6,
+						      struct ipv6_txoptions *opt,
+						      int *hlimit, int *tclass,
+						      int *dontfrag);
 
 #define		LOOPBACK4_IPV6		cpu_to_be32(0x7f000006)
 
diff --git a/include/trace/events/ras.h b/include/trace/events/ras.h
new file mode 100644
index 0000000..88b8783
--- /dev/null
+++ b/include/trace/events/ras.h
@@ -0,0 +1,77 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM ras
+
+#if !defined(_TRACE_AER_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_AER_H
+
+#include <linux/tracepoint.h>
+#include <linux/edac.h>
+
+
+/*
+ * PCIe AER Trace event
+ *
+ * These events are generated when hardware detects a corrected or
+ * uncorrected event on a PCIe device. The event report has
+ * the following structure:
+ *
+ * char * dev_name -	The name of the slot where the device resides
+ *			([domain:]bus:device.function).
+ * u32 status -		Either the correctable or uncorrectable register
+ *			indicating what error or errors have been seen
+ * u8 severity -	error severity 0:NONFATAL 1:FATAL 2:CORRECTED
+ */
+
+#define aer_correctable_errors		\
+	{BIT(0),	"Receiver Error"},		\
+	{BIT(6),	"Bad TLP"},			\
+	{BIT(7),	"Bad DLLP"},			\
+	{BIT(8),	"RELAY_NUM Rollover"},		\
+	{BIT(12),	"Replay Timer Timeout"},	\
+	{BIT(13),	"Advisory Non-Fatal"}
+
+#define aer_uncorrectable_errors		\
+	{BIT(4),	"Data Link Protocol"},		\
+	{BIT(12),	"Poisoned TLP"},		\
+	{BIT(13),	"Flow Control Protocol"},	\
+	{BIT(14),	"Completion Timeout"},		\
+	{BIT(15),	"Completer Abort"},		\
+	{BIT(16),	"Unexpected Completion"},	\
+	{BIT(17),	"Receiver Overflow"},		\
+	{BIT(18),	"Malformed TLP"},		\
+	{BIT(19),	"ECRC"},			\
+	{BIT(20),	"Unsupported Request"}
+
+TRACE_EVENT(aer_event,
+	TP_PROTO(const char *dev_name,
+		 const u32 status,
+		 const u8 severity),
+
+	TP_ARGS(dev_name, status, severity),
+
+	TP_STRUCT__entry(
+		__string(	dev_name,	dev_name	)
+		__field(	u32,		status		)
+		__field(	u8,		severity	)
+	),
+
+	TP_fast_assign(
+		__assign_str(dev_name, dev_name);
+		__entry->status		= status;
+		__entry->severity	= severity;
+	),
+
+	TP_printk("%s PCIe Bus Error: severity=%s, %s\n",
+		__get_str(dev_name),
+		__entry->severity == HW_EVENT_ERR_CORRECTED ? "Corrected" :
+			__entry->severity == HW_EVENT_ERR_FATAL ?
+			"Fatal" : "Uncorrected",
+		__entry->severity == HW_EVENT_ERR_CORRECTED ?
+		__print_flags(__entry->status, "|", aer_correctable_errors) :
+		__print_flags(__entry->status, "|", aer_uncorrectable_errors))
+);
+
+#endif /* _TRACE_AER_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index d4f559b..1918e83 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -44,8 +44,10 @@
  * of a new grace period or the end of an old grace period ("cpustart"
  * and "cpuend", respectively), a CPU passing through a quiescent
  * state ("cpuqs"), a CPU coming online or going offline ("cpuonl"
- * and "cpuofl", respectively), and a CPU being kicked for being too
- * long in dyntick-idle mode ("kick").
+ * and "cpuofl", respectively), a CPU being kicked for being too
+ * long in dyntick-idle mode ("kick"), a CPU accelerating its new
+ * callbacks to RCU_NEXT_READY_TAIL ("AccReadyCB"), and a CPU
+ * accelerating its new callbacks to RCU_WAIT_TAIL ("AccWaitCB").
  */
 TRACE_EVENT(rcu_grace_period,
 
@@ -393,7 +395,7 @@
  */
 TRACE_EVENT(rcu_batch_start,
 
-	TP_PROTO(char *rcuname, long qlen_lazy, long qlen, int blimit),
+	TP_PROTO(char *rcuname, long qlen_lazy, long qlen, long blimit),
 
 	TP_ARGS(rcuname, qlen_lazy, qlen, blimit),
 
@@ -401,7 +403,7 @@
 		__field(char *, rcuname)
 		__field(long, qlen_lazy)
 		__field(long, qlen)
-		__field(int, blimit)
+		__field(long, blimit)
 	),
 
 	TP_fast_assign(
@@ -411,7 +413,7 @@
 		__entry->blimit = blimit;
 	),
 
-	TP_printk("%s CBs=%ld/%ld bl=%d",
+	TP_printk("%s CBs=%ld/%ld bl=%ld",
 		  __entry->rcuname, __entry->qlen_lazy, __entry->qlen,
 		  __entry->blimit)
 );
@@ -523,22 +525,30 @@
  */
 TRACE_EVENT(rcu_torture_read,
 
-	TP_PROTO(char *rcutorturename, struct rcu_head *rhp),
+	TP_PROTO(char *rcutorturename, struct rcu_head *rhp,
+		 unsigned long secs, unsigned long c_old, unsigned long c),
 
-	TP_ARGS(rcutorturename, rhp),
+	TP_ARGS(rcutorturename, rhp, secs, c_old, c),
 
 	TP_STRUCT__entry(
 		__field(char *, rcutorturename)
 		__field(struct rcu_head *, rhp)
+		__field(unsigned long, secs)
+		__field(unsigned long, c_old)
+		__field(unsigned long, c)
 	),
 
 	TP_fast_assign(
 		__entry->rcutorturename = rcutorturename;
 		__entry->rhp = rhp;
+		__entry->secs = secs;
+		__entry->c_old = c_old;
+		__entry->c = c;
 	),
 
-	TP_printk("%s torture read %p",
-		  __entry->rcutorturename, __entry->rhp)
+	TP_printk("%s torture read %p %luus c: %lu %lu",
+		  __entry->rcutorturename, __entry->rhp,
+		  __entry->secs, __entry->c_old, __entry->c)
 );
 
 /*
@@ -608,7 +618,8 @@
 #define trace_rcu_invoke_kfree_callback(rcuname, rhp, offset) do { } while (0)
 #define trace_rcu_batch_end(rcuname, callbacks_invoked, cb, nr, iit, risk) \
 	do { } while (0)
-#define trace_rcu_torture_read(rcutorturename, rhp) do { } while (0)
+#define trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \
+	do { } while (0)
 #define trace_rcu_barrier(name, s, cpu, cnt, done) do { } while (0)
 
 #endif /* #else #ifdef CONFIG_RCU_TRACE */
diff --git a/include/uapi/linux/auto_fs.h b/include/uapi/linux/auto_fs.h
index 77cdba9..bb991df 100644
--- a/include/uapi/linux/auto_fs.h
+++ b/include/uapi/linux/auto_fs.h
@@ -28,25 +28,16 @@
 #define AUTOFS_MIN_PROTO_VERSION	AUTOFS_PROTO_VERSION
 
 /*
- * Architectures where both 32- and 64-bit binaries can be executed
- * on 64-bit kernels need this.  This keeps the structure format
- * uniform, and makes sure the wait_queue_token isn't too big to be
- * passed back down to the kernel.
- *
- * This assumes that on these architectures:
- * mode     32 bit    64 bit
- * -------------------------
- * int      32 bit    32 bit
- * long     32 bit    64 bit
- *
- * If so, 32-bit user-space code should be backwards compatible.
+ * The wait_queue_token (autofs_wqt_t) is part of a structure which is passed
+ * back to the kernel via ioctl from userspace. On architectures where 32- and
+ * 64-bit userspace binaries can be executed it's important that the size of
+ * autofs_wqt_t stays constant between 32- and 64-bit Linux kernels so that we
+ * do not break the binary ABI interface by changing the structure size.
  */
-
-#if defined(__sparc__) || defined(__mips__) || defined(__x86_64__) \
- || defined(__powerpc__) || defined(__s390__)
-typedef unsigned int autofs_wqt_t;
-#else
+#if defined(__ia64__) || defined(__alpha__) /* pure 64bit architectures */
 typedef unsigned long autofs_wqt_t;
+#else
+typedef unsigned int autofs_wqt_t;
 #endif
 
 /* Packet types */
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 4f63c05..9fa9c62 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -579,7 +579,8 @@
 	 *	{ u32			size;
 	 *	  char                  data[size];}&& PERF_SAMPLE_RAW
 	 *
-	 *	{ u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK
+	 *	{ u64                   nr;
+	 *        { u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK
 	 *
 	 * 	{ u64			abi; # enum perf_sample_regs_abi
 	 * 	  u64			regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER
diff --git a/include/uapi/linux/usb/ch9.h b/include/uapi/linux/usb/ch9.h
index 5059847..f738e25 100644
--- a/include/uapi/linux/usb/ch9.h
+++ b/include/uapi/linux/usb/ch9.h
@@ -152,6 +152,12 @@
 #define USB_INTRF_FUNC_SUSPEND_LP	(1 << (8 + 0))
 #define USB_INTRF_FUNC_SUSPEND_RW	(1 << (8 + 1))
 
+/*
+ * Interface status, Figure 9-5 USB 3.0 spec
+ */
+#define USB_INTRF_STAT_FUNC_RW_CAP     1
+#define USB_INTRF_STAT_FUNC_RW         2
+
 #define USB_ENDPOINT_HALT		0	/* IN/OUT will STALL */
 
 /* Bit array elements as returned by the USB_REQ_GET_STATUS request. */
diff --git a/init/Kconfig b/init/Kconfig
index ccb9f8f..7000d96 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -20,12 +20,8 @@
 	bool
 	depends on !UML
 
-config HAVE_IRQ_WORK
-	bool
-
 config IRQ_WORK
 	bool
-	depends on HAVE_IRQ_WORK
 
 config BUILDTIME_EXTABLE_SORT
 	bool
@@ -474,7 +470,7 @@
 
 config TREE_PREEMPT_RCU
 	bool "Preemptible tree-based hierarchical RCU"
-	depends on PREEMPT && SMP
+	depends on PREEMPT
 	help
 	  This option selects the RCU implementation that is
 	  designed for very large SMP systems with hundreds or
@@ -482,6 +478,8 @@
 	  is also required.  It also scales down nicely to
 	  smaller systems.
 
+	  Select this option if you are unsure.
+
 config TINY_RCU
 	bool "UP-only small-memory-footprint RCU"
 	depends on !PREEMPT && !SMP
@@ -507,6 +505,14 @@
 	  This option enables preemptible-RCU code that is common between
 	  the TREE_PREEMPT_RCU and TINY_PREEMPT_RCU implementations.
 
+config RCU_STALL_COMMON
+	def_bool ( TREE_RCU || TREE_PREEMPT_RCU || RCU_TRACE )
+	help
+	  This option enables RCU CPU stall code that is common between
+	  the TINY and TREE variants of RCU.  The purpose is to allow
+	  the tiny variants to disable RCU CPU stall warnings, while
+	  making these warnings mandatory for the tree variants.
+
 config CONTEXT_TRACKING
        bool
 
@@ -1284,6 +1290,7 @@
 config PRINTK
 	default y
 	bool "Enable support for printk" if EXPERT
+	select IRQ_WORK
 	help
 	  This option enables normal printk support. Removing it
 	  eliminates most of the message strings from the kernel image
diff --git a/init/main.c b/init/main.c
index 92d728a..cee4b5c 100644
--- a/init/main.c
+++ b/init/main.c
@@ -604,7 +604,7 @@
 	pidmap_init();
 	anon_vma_init();
 #ifdef CONFIG_X86
-	if (efi_enabled)
+	if (efi_enabled(EFI_RUNTIME_SERVICES))
 		efi_enter_virtual_mode();
 #endif
 	thread_info_cache_init();
@@ -632,7 +632,7 @@
 	acpi_early_init(); /* before LAPIC and SMP init */
 	sfi_init_late();
 
-	if (efi_enabled) {
+	if (efi_enabled(EFI_RUNTIME_SERVICES)) {
 		efi_late_init();
 		efi_free_boot_services();
 	}
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index 74f68f4..65349f0 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -1,3 +1,19 @@
+/*
+ * Context tracking: Probe on high level context boundaries such as kernel
+ * and userspace. This includes syscalls and exceptions entry/exit.
+ *
+ * This is used by RCU to remove its dependency on the timer tick while a CPU
+ * runs in userspace.
+ *
+ *  Started by Frederic Weisbecker:
+ *
+ * Copyright (C) 2012 Red Hat, Inc., Frederic Weisbecker <fweisbec@redhat.com>
+ *
+ * Many thanks to Gilad Ben-Yossef, Paul McKenney, Ingo Molnar, Andrew Morton,
+ * Steven Rostedt, Peter Zijlstra for suggestions and improvements.
+ *
+ */
+
 #include <linux/context_tracking.h>
 #include <linux/kvm_host.h>
 #include <linux/rcupdate.h>
@@ -11,6 +27,15 @@
 #endif
 };
 
+/**
+ * user_enter - Inform the context tracking that the CPU is going to
+ *              enter userspace mode.
+ *
+ * This function must be called right before we switch from the kernel
+ * to userspace, when it's guaranteed the remaining kernel instructions
+ * to execute won't use any RCU read side critical section because this
+ * function sets RCU in extended quiescent state.
+ */
 void user_enter(void)
 {
 	unsigned long flags;
@@ -26,11 +51,19 @@
 	if (in_interrupt())
 		return;
 
+	/* Kernel threads aren't supposed to go to userspace */
 	WARN_ON_ONCE(!current->mm);
 
 	local_irq_save(flags);
 	if (__this_cpu_read(context_tracking.active) &&
 	    __this_cpu_read(context_tracking.state) != IN_USER) {
+		/*
+		 * At this stage, only low level arch entry code remains and
+		 * then we'll run in userspace. We can assume there won't be
+		 * any RCU read-side critical section until the next call to
+		 * user_exit() or rcu_irq_enter(). Let's remove RCU's dependency
+		 * on the tick.
+		 */
 		vtime_user_enter(current);
 		rcu_user_enter();
 		__this_cpu_write(context_tracking.state, IN_USER);
@@ -38,23 +71,31 @@
 	local_irq_restore(flags);
 }
 
+
+/**
+ * user_exit - Inform the context tracking that the CPU is
+ *             exiting userspace mode and entering the kernel.
+ *
+ * This function must be called after we entered the kernel from userspace
+ * before any use of RCU read side critical section. This potentially include
+ * any high level kernel code like syscalls, exceptions, signal handling, etc...
+ *
+ * This call supports re-entrancy. This way it can be called from any exception
+ * handler without needing to know if we came from userspace or not.
+ */
 void user_exit(void)
 {
 	unsigned long flags;
 
-	/*
-	 * Some contexts may involve an exception occuring in an irq,
-	 * leading to that nesting:
-	 * rcu_irq_enter() rcu_user_exit() rcu_user_exit() rcu_irq_exit()
-	 * This would mess up the dyntick_nesting count though. And rcu_irq_*()
-	 * helpers are enough to protect RCU uses inside the exception. So
-	 * just return immediately if we detect we are in an IRQ.
-	 */
 	if (in_interrupt())
 		return;
 
 	local_irq_save(flags);
 	if (__this_cpu_read(context_tracking.state) == IN_USER) {
+		/*
+		 * We are going to run code that may use RCU. Inform
+		 * RCU core about that (ie: we may need the tick again).
+		 */
 		rcu_user_exit();
 		vtime_user_exit(current);
 		__this_cpu_write(context_tracking.state, IN_KERNEL);
@@ -80,6 +121,20 @@
 }
 EXPORT_SYMBOL_GPL(guest_exit);
 
+
+/**
+ * context_tracking_task_switch - context switch the syscall callbacks
+ * @prev: the task that is being switched out
+ * @next: the task that is being switched in
+ *
+ * The context tracking uses the syscall slow path to implement its user-kernel
+ * boundaries probes on syscalls. This way it doesn't impact the syscall fast
+ * path on CPUs that don't do context tracking.
+ *
+ * But we need to clear the flag on the previous task because it may later
+ * migrate to some CPU that doesn't do the context tracking. As such the TIF
+ * flag may not be desired there.
+ */
 void context_tracking_task_switch(struct task_struct *prev,
 			     struct task_struct *next)
 {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 301079d..5c75791 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -908,6 +908,15 @@
 }
 
 /*
+ * Initialize event state based on the perf_event_attr::disabled.
+ */
+static inline void perf_event__state_init(struct perf_event *event)
+{
+	event->state = event->attr.disabled ? PERF_EVENT_STATE_OFF :
+					      PERF_EVENT_STATE_INACTIVE;
+}
+
+/*
  * Called at perf_event creation and when events are attached/detached from a
  * group.
  */
@@ -6162,11 +6171,14 @@
 
 	if (task) {
 		event->attach_state = PERF_ATTACH_TASK;
+
+		if (attr->type == PERF_TYPE_TRACEPOINT)
+			event->hw.tp_target = task;
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 		/*
 		 * hw_breakpoint is a bit difficult here..
 		 */
-		if (attr->type == PERF_TYPE_BREAKPOINT)
+		else if (attr->type == PERF_TYPE_BREAKPOINT)
 			event->hw.bp_target = task;
 #endif
 	}
@@ -6179,8 +6191,7 @@
 	event->overflow_handler	= overflow_handler;
 	event->overflow_handler_context = context;
 
-	if (attr->disabled)
-		event->state = PERF_EVENT_STATE_OFF;
+	perf_event__state_init(event);
 
 	pmu = NULL;
 
@@ -6609,9 +6620,17 @@
 
 		mutex_lock(&gctx->mutex);
 		perf_remove_from_context(group_leader);
+
+		/*
+		 * Removing from the context ends up with disabled
+		 * event. What we want here is event in the initial
+		 * startup state, ready to be add into new context.
+		 */
+		perf_event__state_init(group_leader);
 		list_for_each_entry(sibling, &group_leader->sibling_list,
 				    group_entry) {
 			perf_remove_from_context(sibling);
+			perf_event__state_init(sibling);
 			put_ctx(gctx);
 		}
 		mutex_unlock(&gctx->mutex);
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index fe8a916..a64f8ae 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -676,7 +676,7 @@
  err_alloc:
 	for_each_possible_cpu(err_cpu) {
 		for (i = 0; i < TYPE_MAX; i++)
-			kfree(per_cpu(nr_task_bp_pinned[i], cpu));
+			kfree(per_cpu(nr_task_bp_pinned[i], err_cpu));
 		if (err_cpu == cpu)
 			break;
 	}
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index dea7acf..a567c8c 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -27,6 +27,7 @@
 #include <linux/pagemap.h>	/* read_mapping_page */
 #include <linux/slab.h>
 #include <linux/sched.h>
+#include <linux/export.h>
 #include <linux/rmap.h>		/* anon_vma_prepare */
 #include <linux/mmu_notifier.h>	/* set_pte_at_notify */
 #include <linux/swap.h>		/* try_to_free_swap */
@@ -41,58 +42,31 @@
 #define MAX_UPROBE_XOL_SLOTS		UINSNS_PER_PAGE
 
 static struct rb_root uprobes_tree = RB_ROOT;
+/*
+ * allows us to skip the uprobe_mmap if there are no uprobe events active
+ * at this time.  Probably a fine grained per inode count is better?
+ */
+#define no_uprobe_events()	RB_EMPTY_ROOT(&uprobes_tree)
 
 static DEFINE_SPINLOCK(uprobes_treelock);	/* serialize rbtree access */
 
 #define UPROBES_HASH_SZ	13
-
-/*
- * We need separate register/unregister and mmap/munmap lock hashes because
- * of mmap_sem nesting.
- *
- * uprobe_register() needs to install probes on (potentially) all processes
- * and thus needs to acquire multiple mmap_sems (consequtively, not
- * concurrently), whereas uprobe_mmap() is called while holding mmap_sem
- * for the particular process doing the mmap.
- *
- * uprobe_register()->register_for_each_vma() needs to drop/acquire mmap_sem
- * because of lock order against i_mmap_mutex. This means there's a hole in
- * the register vma iteration where a mmap() can happen.
- *
- * Thus uprobe_register() can race with uprobe_mmap() and we can try and
- * install a probe where one is already installed.
- */
-
-/* serialize (un)register */
-static struct mutex uprobes_mutex[UPROBES_HASH_SZ];
-
-#define uprobes_hash(v)		(&uprobes_mutex[((unsigned long)(v)) % UPROBES_HASH_SZ])
-
 /* serialize uprobe->pending_list */
 static struct mutex uprobes_mmap_mutex[UPROBES_HASH_SZ];
 #define uprobes_mmap_hash(v)	(&uprobes_mmap_mutex[((unsigned long)(v)) % UPROBES_HASH_SZ])
 
 static struct percpu_rw_semaphore dup_mmap_sem;
 
-/*
- * uprobe_events allows us to skip the uprobe_mmap if there are no uprobe
- * events active at this time.  Probably a fine grained per inode count is
- * better?
- */
-static atomic_t uprobe_events = ATOMIC_INIT(0);
-
 /* Have a copy of original instruction */
 #define UPROBE_COPY_INSN	0
-/* Dont run handlers when first register/ last unregister in progress*/
-#define UPROBE_RUN_HANDLER	1
 /* Can skip singlestep */
-#define UPROBE_SKIP_SSTEP	2
+#define UPROBE_SKIP_SSTEP	1
 
 struct uprobe {
 	struct rb_node		rb_node;	/* node in the rb tree */
 	atomic_t		ref;
+	struct rw_semaphore	register_rwsem;
 	struct rw_semaphore	consumer_rwsem;
-	struct mutex		copy_mutex;	/* TODO: kill me and UPROBE_COPY_INSN */
 	struct list_head	pending_list;
 	struct uprobe_consumer	*consumers;
 	struct inode		*inode;		/* Also hold a ref to inode */
@@ -430,9 +404,6 @@
 	u = __insert_uprobe(uprobe);
 	spin_unlock(&uprobes_treelock);
 
-	/* For now assume that the instruction need not be single-stepped */
-	__set_bit(UPROBE_SKIP_SSTEP, &uprobe->flags);
-
 	return u;
 }
 
@@ -452,8 +423,10 @@
 
 	uprobe->inode = igrab(inode);
 	uprobe->offset = offset;
+	init_rwsem(&uprobe->register_rwsem);
 	init_rwsem(&uprobe->consumer_rwsem);
-	mutex_init(&uprobe->copy_mutex);
+	/* For now assume that the instruction need not be single-stepped */
+	__set_bit(UPROBE_SKIP_SSTEP, &uprobe->flags);
 
 	/* add to uprobes_tree, sorted on inode:offset */
 	cur_uprobe = insert_uprobe(uprobe);
@@ -463,38 +436,17 @@
 		kfree(uprobe);
 		uprobe = cur_uprobe;
 		iput(inode);
-	} else {
-		atomic_inc(&uprobe_events);
 	}
 
 	return uprobe;
 }
 
-static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs)
-{
-	struct uprobe_consumer *uc;
-
-	if (!test_bit(UPROBE_RUN_HANDLER, &uprobe->flags))
-		return;
-
-	down_read(&uprobe->consumer_rwsem);
-	for (uc = uprobe->consumers; uc; uc = uc->next) {
-		if (!uc->filter || uc->filter(uc, current))
-			uc->handler(uc, regs);
-	}
-	up_read(&uprobe->consumer_rwsem);
-}
-
-/* Returns the previous consumer */
-static struct uprobe_consumer *
-consumer_add(struct uprobe *uprobe, struct uprobe_consumer *uc)
+static void consumer_add(struct uprobe *uprobe, struct uprobe_consumer *uc)
 {
 	down_write(&uprobe->consumer_rwsem);
 	uc->next = uprobe->consumers;
 	uprobe->consumers = uc;
 	up_write(&uprobe->consumer_rwsem);
-
-	return uc->next;
 }
 
 /*
@@ -588,7 +540,8 @@
 	if (test_bit(UPROBE_COPY_INSN, &uprobe->flags))
 		return ret;
 
-	mutex_lock(&uprobe->copy_mutex);
+	/* TODO: move this into _register, until then we abuse this sem. */
+	down_write(&uprobe->consumer_rwsem);
 	if (test_bit(UPROBE_COPY_INSN, &uprobe->flags))
 		goto out;
 
@@ -612,7 +565,30 @@
 	set_bit(UPROBE_COPY_INSN, &uprobe->flags);
 
  out:
-	mutex_unlock(&uprobe->copy_mutex);
+	up_write(&uprobe->consumer_rwsem);
+
+	return ret;
+}
+
+static inline bool consumer_filter(struct uprobe_consumer *uc,
+				   enum uprobe_filter_ctx ctx, struct mm_struct *mm)
+{
+	return !uc->filter || uc->filter(uc, ctx, mm);
+}
+
+static bool filter_chain(struct uprobe *uprobe,
+			 enum uprobe_filter_ctx ctx, struct mm_struct *mm)
+{
+	struct uprobe_consumer *uc;
+	bool ret = false;
+
+	down_read(&uprobe->consumer_rwsem);
+	for (uc = uprobe->consumers; uc; uc = uc->next) {
+		ret = consumer_filter(uc, ctx, mm);
+		if (ret)
+			break;
+	}
+	up_read(&uprobe->consumer_rwsem);
 
 	return ret;
 }
@@ -624,16 +600,6 @@
 	bool first_uprobe;
 	int ret;
 
-	/*
-	 * If probe is being deleted, unregister thread could be done with
-	 * the vma-rmap-walk through. Adding a probe now can be fatal since
-	 * nobody will be able to cleanup. Also we could be from fork or
-	 * mremap path, where the probe might have already been inserted.
-	 * Hence behave as if probe already existed.
-	 */
-	if (!uprobe->consumers)
-		return 0;
-
 	ret = prepare_uprobe(uprobe, vma->vm_file, mm, vaddr);
 	if (ret)
 		return ret;
@@ -658,14 +624,14 @@
 static int
 remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vaddr)
 {
-	/* can happen if uprobe_register() fails */
-	if (!test_bit(MMF_HAS_UPROBES, &mm->flags))
-		return 0;
-
 	set_bit(MMF_RECALC_UPROBES, &mm->flags);
 	return set_orig_insn(&uprobe->arch, mm, vaddr);
 }
 
+static inline bool uprobe_is_active(struct uprobe *uprobe)
+{
+	return !RB_EMPTY_NODE(&uprobe->rb_node);
+}
 /*
  * There could be threads that have already hit the breakpoint. They
  * will recheck the current insn and restart if find_uprobe() fails.
@@ -673,12 +639,15 @@
  */
 static void delete_uprobe(struct uprobe *uprobe)
 {
+	if (WARN_ON(!uprobe_is_active(uprobe)))
+		return;
+
 	spin_lock(&uprobes_treelock);
 	rb_erase(&uprobe->rb_node, &uprobes_tree);
 	spin_unlock(&uprobes_treelock);
+	RB_CLEAR_NODE(&uprobe->rb_node); /* for uprobe_is_active() */
 	iput(uprobe->inode);
 	put_uprobe(uprobe);
-	atomic_dec(&uprobe_events);
 }
 
 struct map_info {
@@ -764,8 +733,10 @@
 	return curr;
 }
 
-static int register_for_each_vma(struct uprobe *uprobe, bool is_register)
+static int
+register_for_each_vma(struct uprobe *uprobe, struct uprobe_consumer *new)
 {
+	bool is_register = !!new;
 	struct map_info *info;
 	int err = 0;
 
@@ -794,10 +765,16 @@
 		    vaddr_to_offset(vma, info->vaddr) != uprobe->offset)
 			goto unlock;
 
-		if (is_register)
-			err = install_breakpoint(uprobe, mm, vma, info->vaddr);
-		else
-			err |= remove_breakpoint(uprobe, mm, info->vaddr);
+		if (is_register) {
+			/* consult only the "caller", new consumer. */
+			if (consumer_filter(new,
+					UPROBE_FILTER_REGISTER, mm))
+				err = install_breakpoint(uprobe, mm, vma, info->vaddr);
+		} else if (test_bit(MMF_HAS_UPROBES, &mm->flags)) {
+			if (!filter_chain(uprobe,
+					UPROBE_FILTER_UNREGISTER, mm))
+				err |= remove_breakpoint(uprobe, mm, info->vaddr);
+		}
 
  unlock:
 		up_write(&mm->mmap_sem);
@@ -810,17 +787,23 @@
 	return err;
 }
 
-static int __uprobe_register(struct uprobe *uprobe)
+static int __uprobe_register(struct uprobe *uprobe, struct uprobe_consumer *uc)
 {
-	return register_for_each_vma(uprobe, true);
+	consumer_add(uprobe, uc);
+	return register_for_each_vma(uprobe, uc);
 }
 
-static void __uprobe_unregister(struct uprobe *uprobe)
+static void __uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc)
 {
-	if (!register_for_each_vma(uprobe, false))
-		delete_uprobe(uprobe);
+	int err;
 
+	if (!consumer_del(uprobe, uc))	/* WARN? */
+		return;
+
+	err = register_for_each_vma(uprobe, NULL);
 	/* TODO : cant unregister? schedule a worker thread */
+	if (!uprobe->consumers && !err)
+		delete_uprobe(uprobe);
 }
 
 /*
@@ -845,31 +828,59 @@
 	struct uprobe *uprobe;
 	int ret;
 
-	if (!inode || !uc || uc->next)
-		return -EINVAL;
-
+	/* Racy, just to catch the obvious mistakes */
 	if (offset > i_size_read(inode))
 		return -EINVAL;
 
-	ret = 0;
-	mutex_lock(uprobes_hash(inode));
+ retry:
 	uprobe = alloc_uprobe(inode, offset);
-
-	if (!uprobe) {
-		ret = -ENOMEM;
-	} else if (!consumer_add(uprobe, uc)) {
-		ret = __uprobe_register(uprobe);
-		if (ret) {
-			uprobe->consumers = NULL;
-			__uprobe_unregister(uprobe);
-		} else {
-			set_bit(UPROBE_RUN_HANDLER, &uprobe->flags);
-		}
+	if (!uprobe)
+		return -ENOMEM;
+	/*
+	 * We can race with uprobe_unregister()->delete_uprobe().
+	 * Check uprobe_is_active() and retry if it is false.
+	 */
+	down_write(&uprobe->register_rwsem);
+	ret = -EAGAIN;
+	if (likely(uprobe_is_active(uprobe))) {
+		ret = __uprobe_register(uprobe, uc);
+		if (ret)
+			__uprobe_unregister(uprobe, uc);
 	}
+	up_write(&uprobe->register_rwsem);
+	put_uprobe(uprobe);
 
-	mutex_unlock(uprobes_hash(inode));
-	if (uprobe)
-		put_uprobe(uprobe);
+	if (unlikely(ret == -EAGAIN))
+		goto retry;
+	return ret;
+}
+EXPORT_SYMBOL_GPL(uprobe_register);
+
+/*
+ * uprobe_apply - unregister a already registered probe.
+ * @inode: the file in which the probe has to be removed.
+ * @offset: offset from the start of the file.
+ * @uc: consumer which wants to add more or remove some breakpoints
+ * @add: add or remove the breakpoints
+ */
+int uprobe_apply(struct inode *inode, loff_t offset,
+			struct uprobe_consumer *uc, bool add)
+{
+	struct uprobe *uprobe;
+	struct uprobe_consumer *con;
+	int ret = -ENOENT;
+
+	uprobe = find_uprobe(inode, offset);
+	if (!uprobe)
+		return ret;
+
+	down_write(&uprobe->register_rwsem);
+	for (con = uprobe->consumers; con && con != uc ; con = con->next)
+		;
+	if (con)
+		ret = register_for_each_vma(uprobe, add ? uc : NULL);
+	up_write(&uprobe->register_rwsem);
+	put_uprobe(uprobe);
 
 	return ret;
 }
@@ -884,25 +895,42 @@
 {
 	struct uprobe *uprobe;
 
-	if (!inode || !uc)
-		return;
-
 	uprobe = find_uprobe(inode, offset);
 	if (!uprobe)
 		return;
 
-	mutex_lock(uprobes_hash(inode));
+	down_write(&uprobe->register_rwsem);
+	__uprobe_unregister(uprobe, uc);
+	up_write(&uprobe->register_rwsem);
+	put_uprobe(uprobe);
+}
+EXPORT_SYMBOL_GPL(uprobe_unregister);
 
-	if (consumer_del(uprobe, uc)) {
-		if (!uprobe->consumers) {
-			__uprobe_unregister(uprobe);
-			clear_bit(UPROBE_RUN_HANDLER, &uprobe->flags);
-		}
+static int unapply_uprobe(struct uprobe *uprobe, struct mm_struct *mm)
+{
+	struct vm_area_struct *vma;
+	int err = 0;
+
+	down_read(&mm->mmap_sem);
+	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+		unsigned long vaddr;
+		loff_t offset;
+
+		if (!valid_vma(vma, false) ||
+		    vma->vm_file->f_mapping->host != uprobe->inode)
+			continue;
+
+		offset = (loff_t)vma->vm_pgoff << PAGE_SHIFT;
+		if (uprobe->offset <  offset ||
+		    uprobe->offset >= offset + vma->vm_end - vma->vm_start)
+			continue;
+
+		vaddr = offset_to_vaddr(vma, uprobe->offset);
+		err |= remove_breakpoint(uprobe, mm, vaddr);
 	}
+	up_read(&mm->mmap_sem);
 
-	mutex_unlock(uprobes_hash(inode));
-	if (uprobe)
-		put_uprobe(uprobe);
+	return err;
 }
 
 static struct rb_node *
@@ -979,7 +1007,7 @@
 	struct uprobe *uprobe, *u;
 	struct inode *inode;
 
-	if (!atomic_read(&uprobe_events) || !valid_vma(vma, true))
+	if (no_uprobe_events() || !valid_vma(vma, true))
 		return 0;
 
 	inode = vma->vm_file->f_mapping->host;
@@ -988,9 +1016,14 @@
 
 	mutex_lock(uprobes_mmap_hash(inode));
 	build_probe_list(inode, vma, vma->vm_start, vma->vm_end, &tmp_list);
-
+	/*
+	 * We can race with uprobe_unregister(), this uprobe can be already
+	 * removed. But in this case filter_chain() must return false, all
+	 * consumers have gone away.
+	 */
 	list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) {
-		if (!fatal_signal_pending(current)) {
+		if (!fatal_signal_pending(current) &&
+		    filter_chain(uprobe, UPROBE_FILTER_MMAP, vma->vm_mm)) {
 			unsigned long vaddr = offset_to_vaddr(vma, uprobe->offset);
 			install_breakpoint(uprobe, vma->vm_mm, vma, vaddr);
 		}
@@ -1025,7 +1058,7 @@
  */
 void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end)
 {
-	if (!atomic_read(&uprobe_events) || !valid_vma(vma, false))
+	if (no_uprobe_events() || !valid_vma(vma, false))
 		return;
 
 	if (!atomic_read(&vma->vm_mm->mm_users)) /* called by mmput() ? */
@@ -1042,22 +1075,14 @@
 /* Slot allocation for XOL */
 static int xol_add_vma(struct xol_area *area)
 {
-	struct mm_struct *mm;
-	int ret;
-
-	area->page = alloc_page(GFP_HIGHUSER);
-	if (!area->page)
-		return -ENOMEM;
-
-	ret = -EALREADY;
-	mm = current->mm;
+	struct mm_struct *mm = current->mm;
+	int ret = -EALREADY;
 
 	down_write(&mm->mmap_sem);
 	if (mm->uprobes_state.xol_area)
 		goto fail;
 
 	ret = -ENOMEM;
-
 	/* Try to map as high as possible, this is only a hint. */
 	area->vaddr = get_unmapped_area(NULL, TASK_SIZE - PAGE_SIZE, PAGE_SIZE, 0, 0);
 	if (area->vaddr & ~PAGE_MASK) {
@@ -1073,54 +1098,53 @@
 	smp_wmb();	/* pairs with get_xol_area() */
 	mm->uprobes_state.xol_area = area;
 	ret = 0;
-
-fail:
+ fail:
 	up_write(&mm->mmap_sem);
-	if (ret)
-		__free_page(area->page);
 
 	return ret;
 }
 
-static struct xol_area *get_xol_area(struct mm_struct *mm)
-{
-	struct xol_area *area;
-
-	area = mm->uprobes_state.xol_area;
-	smp_read_barrier_depends();	/* pairs with wmb in xol_add_vma() */
-
-	return area;
-}
-
 /*
- * xol_alloc_area - Allocate process's xol_area.
- * This area will be used for storing instructions for execution out of
- * line.
+ * get_xol_area - Allocate process's xol_area if necessary.
+ * This area will be used for storing instructions for execution out of line.
  *
  * Returns the allocated area or NULL.
  */
-static struct xol_area *xol_alloc_area(void)
+static struct xol_area *get_xol_area(void)
 {
+	struct mm_struct *mm = current->mm;
 	struct xol_area *area;
 
+	area = mm->uprobes_state.xol_area;
+	if (area)
+		goto ret;
+
 	area = kzalloc(sizeof(*area), GFP_KERNEL);
 	if (unlikely(!area))
-		return NULL;
+		goto out;
 
 	area->bitmap = kzalloc(BITS_TO_LONGS(UINSNS_PER_PAGE) * sizeof(long), GFP_KERNEL);
-
 	if (!area->bitmap)
-		goto fail;
+		goto free_area;
+
+	area->page = alloc_page(GFP_HIGHUSER);
+	if (!area->page)
+		goto free_bitmap;
 
 	init_waitqueue_head(&area->wq);
 	if (!xol_add_vma(area))
 		return area;
 
-fail:
+	__free_page(area->page);
+ free_bitmap:
 	kfree(area->bitmap);
+ free_area:
 	kfree(area);
-
-	return get_xol_area(current->mm);
+ out:
+	area = mm->uprobes_state.xol_area;
+ ret:
+	smp_read_barrier_depends();     /* pairs with wmb in xol_add_vma() */
+	return area;
 }
 
 /*
@@ -1186,33 +1210,26 @@
 }
 
 /*
- * xol_get_insn_slot - If was not allocated a slot, then
- * allocate a slot.
+ * xol_get_insn_slot - allocate a slot for xol.
  * Returns the allocated slot address or 0.
  */
-static unsigned long xol_get_insn_slot(struct uprobe *uprobe, unsigned long slot_addr)
+static unsigned long xol_get_insn_slot(struct uprobe *uprobe)
 {
 	struct xol_area *area;
 	unsigned long offset;
+	unsigned long xol_vaddr;
 	void *vaddr;
 
-	area = get_xol_area(current->mm);
-	if (!area) {
-		area = xol_alloc_area();
-		if (!area)
-			return 0;
-	}
-	current->utask->xol_vaddr = xol_take_insn_slot(area);
-
-	/*
-	 * Initialize the slot if xol_vaddr points to valid
-	 * instruction slot.
-	 */
-	if (unlikely(!current->utask->xol_vaddr))
+	area = get_xol_area();
+	if (!area)
 		return 0;
 
-	current->utask->vaddr = slot_addr;
-	offset = current->utask->xol_vaddr & ~PAGE_MASK;
+	xol_vaddr = xol_take_insn_slot(area);
+	if (unlikely(!xol_vaddr))
+		return 0;
+
+	/* Initialize the slot */
+	offset = xol_vaddr & ~PAGE_MASK;
 	vaddr = kmap_atomic(area->page);
 	memcpy(vaddr + offset, uprobe->arch.insn, MAX_UINSN_BYTES);
 	kunmap_atomic(vaddr);
@@ -1222,7 +1239,7 @@
 	 */
 	flush_dcache_page(area->page);
 
-	return current->utask->xol_vaddr;
+	return xol_vaddr;
 }
 
 /*
@@ -1240,8 +1257,7 @@
 		return;
 
 	slot_addr = tsk->utask->xol_vaddr;
-
-	if (unlikely(!slot_addr || IS_ERR_VALUE(slot_addr)))
+	if (unlikely(!slot_addr))
 		return;
 
 	area = tsk->mm->uprobes_state.xol_area;
@@ -1303,33 +1319,48 @@
 }
 
 /*
- * Allocate a uprobe_task object for the task.
- * Called when the thread hits a breakpoint for the first time.
+ * Allocate a uprobe_task object for the task if if necessary.
+ * Called when the thread hits a breakpoint.
  *
  * Returns:
  * - pointer to new uprobe_task on success
  * - NULL otherwise
  */
-static struct uprobe_task *add_utask(void)
+static struct uprobe_task *get_utask(void)
 {
-	struct uprobe_task *utask;
-
-	utask = kzalloc(sizeof *utask, GFP_KERNEL);
-	if (unlikely(!utask))
-		return NULL;
-
-	current->utask = utask;
-	return utask;
+	if (!current->utask)
+		current->utask = kzalloc(sizeof(struct uprobe_task), GFP_KERNEL);
+	return current->utask;
 }
 
 /* Prepare to single-step probed instruction out of line. */
 static int
-pre_ssout(struct uprobe *uprobe, struct pt_regs *regs, unsigned long vaddr)
+pre_ssout(struct uprobe *uprobe, struct pt_regs *regs, unsigned long bp_vaddr)
 {
-	if (xol_get_insn_slot(uprobe, vaddr) && !arch_uprobe_pre_xol(&uprobe->arch, regs))
-		return 0;
+	struct uprobe_task *utask;
+	unsigned long xol_vaddr;
+	int err;
 
-	return -EFAULT;
+	utask = get_utask();
+	if (!utask)
+		return -ENOMEM;
+
+	xol_vaddr = xol_get_insn_slot(uprobe);
+	if (!xol_vaddr)
+		return -ENOMEM;
+
+	utask->xol_vaddr = xol_vaddr;
+	utask->vaddr = bp_vaddr;
+
+	err = arch_uprobe_pre_xol(&uprobe->arch, regs);
+	if (unlikely(err)) {
+		xol_free_insn_slot(current);
+		return err;
+	}
+
+	utask->active_uprobe = uprobe;
+	utask->state = UTASK_SSTEP;
+	return 0;
 }
 
 /*
@@ -1391,6 +1422,7 @@
 		 * This is not strictly accurate, we can race with
 		 * uprobe_unregister() and see the already removed
 		 * uprobe if delete_uprobe() was not yet called.
+		 * Or this uprobe can be filtered out.
 		 */
 		if (vma_has_uprobes(vma, vma->vm_start, vma->vm_end))
 			return;
@@ -1452,13 +1484,33 @@
 	return uprobe;
 }
 
+static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs)
+{
+	struct uprobe_consumer *uc;
+	int remove = UPROBE_HANDLER_REMOVE;
+
+	down_read(&uprobe->register_rwsem);
+	for (uc = uprobe->consumers; uc; uc = uc->next) {
+		int rc = uc->handler(uc, regs);
+
+		WARN(rc & ~UPROBE_HANDLER_MASK,
+			"bad rc=0x%x from %pf()\n", rc, uc->handler);
+		remove &= rc;
+	}
+
+	if (remove && uprobe->consumers) {
+		WARN_ON(!uprobe_is_active(uprobe));
+		unapply_uprobe(uprobe, current->mm);
+	}
+	up_read(&uprobe->register_rwsem);
+}
+
 /*
  * Run handler and ask thread to singlestep.
  * Ensure all non-fatal signals cannot interrupt thread while it singlesteps.
  */
 static void handle_swbp(struct pt_regs *regs)
 {
-	struct uprobe_task *utask;
 	struct uprobe *uprobe;
 	unsigned long bp_vaddr;
 	int uninitialized_var(is_swbp);
@@ -1483,6 +1535,10 @@
 		}
 		return;
 	}
+
+	/* change it in advance for ->handler() and restart */
+	instruction_pointer_set(regs, bp_vaddr);
+
 	/*
 	 * TODO: move copy_insn/etc into _register and remove this hack.
 	 * After we hit the bp, _unregister + _register can install the
@@ -1490,32 +1546,16 @@
 	 */
 	smp_rmb(); /* pairs with wmb() in install_breakpoint() */
 	if (unlikely(!test_bit(UPROBE_COPY_INSN, &uprobe->flags)))
-		goto restart;
-
-	utask = current->utask;
-	if (!utask) {
-		utask = add_utask();
-		/* Cannot allocate; re-execute the instruction. */
-		if (!utask)
-			goto restart;
-	}
+		goto out;
 
 	handler_chain(uprobe, regs);
 	if (can_skip_sstep(uprobe, regs))
 		goto out;
 
-	if (!pre_ssout(uprobe, regs, bp_vaddr)) {
-		utask->active_uprobe = uprobe;
-		utask->state = UTASK_SSTEP;
+	if (!pre_ssout(uprobe, regs, bp_vaddr))
 		return;
-	}
 
-restart:
-	/*
-	 * cannot singlestep; cannot skip instruction;
-	 * re-execute the instruction.
-	 */
-	instruction_pointer_set(regs, bp_vaddr);
+	/* can_skip_sstep() succeeded, or restart if can't singlestep */
 out:
 	put_uprobe(uprobe);
 }
@@ -1609,10 +1649,8 @@
 {
 	int i;
 
-	for (i = 0; i < UPROBES_HASH_SZ; i++) {
-		mutex_init(&uprobes_mutex[i]);
+	for (i = 0; i < UPROBES_HASH_SZ; i++)
 		mutex_init(&uprobes_mmap_mutex[i]);
-	}
 
 	if (percpu_init_rwsem(&dup_mmap_sem))
 		return -ENOMEM;
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 02115d9..fa17855 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1525,6 +1525,7 @@
 out:
 	irq_put_desc_unlock(desc, flags);
 }
+EXPORT_SYMBOL_GPL(enable_percpu_irq);
 
 void disable_percpu_irq(unsigned int irq)
 {
@@ -1538,6 +1539,7 @@
 	irq_percpu_disable(desc, cpu);
 	irq_put_desc_unlock(desc, flags);
 }
+EXPORT_SYMBOL_GPL(disable_percpu_irq);
 
 /*
  * Internal function to unregister a percpu irqaction.
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 611cd60..7b5f012 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -80,13 +80,11 @@
 
 	/*
 	 * All handlers must agree on IRQF_SHARED, so we test just the
-	 * first. Check for action->next as well.
+	 * first.
 	 */
 	action = desc->action;
 	if (!action || !(action->flags & IRQF_SHARED) ||
-	    (action->flags & __IRQF_TIMER) ||
-	    (action->handler(irq, action->dev_id) == IRQ_HANDLED) ||
-	    !action->next)
+	    (action->flags & __IRQF_TIMER))
 		goto out;
 
 	/* Already running on another processor */
@@ -104,6 +102,7 @@
 	do {
 		if (handle_irq_event(desc) == IRQ_HANDLED)
 			ret = IRQ_HANDLED;
+		/* Make sure that there is still a valid action */
 		action = desc->action;
 	} while ((desc->istate & IRQS_PENDING) && action);
 	desc->istate &= ~IRQS_POLL_INPROGRESS;
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index 1588e3b..55fcce6 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -12,37 +12,36 @@
 #include <linux/percpu.h>
 #include <linux/hardirq.h>
 #include <linux/irqflags.h>
+#include <linux/sched.h>
+#include <linux/tick.h>
+#include <linux/cpu.h>
+#include <linux/notifier.h>
 #include <asm/processor.h>
 
-/*
- * An entry can be in one of four states:
- *
- * free	     NULL, 0 -> {claimed}       : free to be used
- * claimed   NULL, 3 -> {pending}       : claimed to be enqueued
- * pending   next, 3 -> {busy}          : queued, pending callback
- * busy      NULL, 2 -> {free, claimed} : callback in progress, can be claimed
- */
-
-#define IRQ_WORK_PENDING	1UL
-#define IRQ_WORK_BUSY		2UL
-#define IRQ_WORK_FLAGS		3UL
 
 static DEFINE_PER_CPU(struct llist_head, irq_work_list);
+static DEFINE_PER_CPU(int, irq_work_raised);
 
 /*
  * Claim the entry so that no one else will poke at it.
  */
 static bool irq_work_claim(struct irq_work *work)
 {
-	unsigned long flags, nflags;
+	unsigned long flags, oflags, nflags;
 
+	/*
+	 * Start with our best wish as a premise but only trust any
+	 * flag value after cmpxchg() result.
+	 */
+	flags = work->flags & ~IRQ_WORK_PENDING;
 	for (;;) {
-		flags = work->flags;
-		if (flags & IRQ_WORK_PENDING)
-			return false;
 		nflags = flags | IRQ_WORK_FLAGS;
-		if (cmpxchg(&work->flags, flags, nflags) == flags)
+		oflags = cmpxchg(&work->flags, flags, nflags);
+		if (oflags == flags)
 			break;
+		if (oflags & IRQ_WORK_PENDING)
+			return false;
+		flags = oflags;
 		cpu_relax();
 	}
 
@@ -57,57 +56,69 @@
 }
 
 /*
- * Queue the entry and raise the IPI if needed.
- */
-static void __irq_work_queue(struct irq_work *work)
-{
-	bool empty;
-
-	preempt_disable();
-
-	empty = llist_add(&work->llnode, &__get_cpu_var(irq_work_list));
-	/* The list was empty, raise self-interrupt to start processing. */
-	if (empty)
-		arch_irq_work_raise();
-
-	preempt_enable();
-}
-
-/*
- * Enqueue the irq_work @entry, returns true on success, failure when the
- * @entry was already enqueued by someone else.
+ * Enqueue the irq_work @entry unless it's already pending
+ * somewhere.
  *
  * Can be re-enqueued while the callback is still in progress.
  */
-bool irq_work_queue(struct irq_work *work)
+void irq_work_queue(struct irq_work *work)
 {
-	if (!irq_work_claim(work)) {
-		/*
-		 * Already enqueued, can't do!
-		 */
-		return false;
+	/* Only queue if not already pending */
+	if (!irq_work_claim(work))
+		return;
+
+	/* Queue the entry and raise the IPI if needed. */
+	preempt_disable();
+
+	llist_add(&work->llnode, &__get_cpu_var(irq_work_list));
+
+	/*
+	 * If the work is not "lazy" or the tick is stopped, raise the irq
+	 * work interrupt (if supported by the arch), otherwise, just wait
+	 * for the next tick.
+	 */
+	if (!(work->flags & IRQ_WORK_LAZY) || tick_nohz_tick_stopped()) {
+		if (!this_cpu_cmpxchg(irq_work_raised, 0, 1))
+			arch_irq_work_raise();
 	}
 
-	__irq_work_queue(work);
-	return true;
+	preempt_enable();
 }
 EXPORT_SYMBOL_GPL(irq_work_queue);
 
-/*
- * Run the irq_work entries on this cpu. Requires to be ran from hardirq
- * context with local IRQs disabled.
- */
-void irq_work_run(void)
+bool irq_work_needs_cpu(void)
 {
+	struct llist_head *this_list;
+
+	this_list = &__get_cpu_var(irq_work_list);
+	if (llist_empty(this_list))
+		return false;
+
+	/* All work should have been flushed before going offline */
+	WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));
+
+	return true;
+}
+
+static void __irq_work_run(void)
+{
+	unsigned long flags;
 	struct irq_work *work;
 	struct llist_head *this_list;
 	struct llist_node *llnode;
 
+
+	/*
+	 * Reset the "raised" state right before we check the list because
+	 * an NMI may enqueue after we find the list empty from the runner.
+	 */
+	__this_cpu_write(irq_work_raised, 0);
+	barrier();
+
 	this_list = &__get_cpu_var(irq_work_list);
 	if (llist_empty(this_list))
 		return;
 
-	BUG_ON(!in_irq());
 	BUG_ON(!irqs_disabled());
 
 	llnode = llist_del_all(this_list);
@@ -119,16 +130,31 @@
 		/*
 		 * Clear the PENDING bit, after this point the @work
 		 * can be re-used.
+		 * Make it immediately visible so that other CPUs trying
+		 * to claim that work don't rely on us to handle their data
+		 * while we are in the middle of the func.
 		 */
-		work->flags = IRQ_WORK_BUSY;
+		flags = work->flags & ~IRQ_WORK_PENDING;
+		xchg(&work->flags, flags);
+
 		work->func(work);
 		/*
 		 * Clear the BUSY bit and return to the free state if
 		 * no-one else claimed it meanwhile.
 		 */
-		(void)cmpxchg(&work->flags, IRQ_WORK_BUSY, 0);
+		(void)cmpxchg(&work->flags, flags, flags & ~IRQ_WORK_BUSY);
 	}
 }
+
+/*
+ * Run the irq_work entries on this cpu. Requires to be ran from hardirq
+ * context with local IRQs disabled.
+ */
+void irq_work_run(void)
+{
+	BUG_ON(!in_irq());
+	__irq_work_run();
+}
 EXPORT_SYMBOL_GPL(irq_work_run);
 
 /*
@@ -143,3 +169,35 @@
 		cpu_relax();
 }
 EXPORT_SYMBOL_GPL(irq_work_sync);
+
+#ifdef CONFIG_HOTPLUG_CPU
+static int irq_work_cpu_notify(struct notifier_block *self,
+			       unsigned long action, void *hcpu)
+{
+	long cpu = (long)hcpu;
+
+	switch (action) {
+	case CPU_DYING:
+		/* Called from stop_machine */
+		if (WARN_ON_ONCE(cpu != smp_processor_id()))
+			break;
+		__irq_work_run();
+		break;
+	default:
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block cpu_notify;
+
+static __init int irq_work_init_cpu_notifier(void)
+{
+	cpu_notify.notifier_call = irq_work_cpu_notify;
+	cpu_notify.priority = 0;
+	register_cpu_notifier(&cpu_notify);
+	return 0;
+}
+device_initcall(irq_work_init_cpu_notifier);
+
+#endif /* CONFIG_HOTPLUG_CPU */
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 098f396..f423c3e 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -919,7 +919,7 @@
 }
 #endif /* CONFIG_OPTPROBES */
 
-#ifdef KPROBES_CAN_USE_FTRACE
+#ifdef CONFIG_KPROBES_ON_FTRACE
 static struct ftrace_ops kprobe_ftrace_ops __read_mostly = {
 	.func = kprobe_ftrace_handler,
 	.flags = FTRACE_OPS_FL_SAVE_REGS,
@@ -964,7 +964,7 @@
 			   (unsigned long)p->addr, 1, 0);
 	WARN(ret < 0, "Failed to disarm kprobe-ftrace at %p (%d)\n", p->addr, ret);
 }
-#else	/* !KPROBES_CAN_USE_FTRACE */
+#else	/* !CONFIG_KPROBES_ON_FTRACE */
 #define prepare_kprobe(p)	arch_prepare_kprobe(p)
 #define arm_kprobe_ftrace(p)	do {} while (0)
 #define disarm_kprobe_ftrace(p)	do {} while (0)
@@ -1414,12 +1414,12 @@
 	 */
 	ftrace_addr = ftrace_location((unsigned long)p->addr);
 	if (ftrace_addr) {
-#ifdef KPROBES_CAN_USE_FTRACE
+#ifdef CONFIG_KPROBES_ON_FTRACE
 		/* Given address is not on the instruction boundary */
 		if ((unsigned long)p->addr != ftrace_addr)
 			return -EILSEQ;
 		p->flags |= KPROBE_FLAG_FTRACE;
-#else	/* !KPROBES_CAN_USE_FTRACE */
+#else	/* !CONFIG_KPROBES_ON_FTRACE */
 		return -EINVAL;
 #endif
 	}
diff --git a/kernel/pid.c b/kernel/pid.c
index de9af60..f2c6a68 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -331,7 +331,7 @@
 	return pid;
 
 out_unlock:
-	spin_unlock(&pidmap_lock);
+	spin_unlock_irq(&pidmap_lock);
 out_free:
 	while (++i <= ns->level)
 		free_pidmap(pid->numbers + i);
diff --git a/kernel/printk.c b/kernel/printk.c
index 357f714..f24633a 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -42,6 +42,7 @@
 #include <linux/notifier.h>
 #include <linux/rculist.h>
 #include <linux/poll.h>
+#include <linux/irq_work.h>
 
 #include <asm/uaccess.h>
 
@@ -87,12 +88,6 @@
 struct console *console_drivers;
 EXPORT_SYMBOL_GPL(console_drivers);
 
-#ifdef CONFIG_LOCKDEP
-static struct lockdep_map console_lock_dep_map = {
-	.name = "console_lock"
-};
-#endif
-
 /*
  * This is used for debugging the mess that is the VT code by
  * keeping track if we have the console semaphore held. It's
@@ -1924,7 +1919,6 @@
 		return;
 	console_locked = 1;
 	console_may_schedule = 1;
-	mutex_acquire(&console_lock_dep_map, 0, 0, _RET_IP_);
 }
 EXPORT_SYMBOL(console_lock);
 
@@ -1946,7 +1940,6 @@
 	}
 	console_locked = 1;
 	console_may_schedule = 0;
-	mutex_acquire(&console_lock_dep_map, 0, 1, _RET_IP_);
 	return 1;
 }
 EXPORT_SYMBOL(console_trylock);
@@ -1967,30 +1960,32 @@
 static DEFINE_PER_CPU(int, printk_pending);
 static DEFINE_PER_CPU(char [PRINTK_BUF_SIZE], printk_sched_buf);
 
-void printk_tick(void)
+static void wake_up_klogd_work_func(struct irq_work *irq_work)
 {
-	if (__this_cpu_read(printk_pending)) {
-		int pending = __this_cpu_xchg(printk_pending, 0);
-		if (pending & PRINTK_PENDING_SCHED) {
-			char *buf = __get_cpu_var(printk_sched_buf);
-			printk(KERN_WARNING "[sched_delayed] %s", buf);
-		}
-		if (pending & PRINTK_PENDING_WAKEUP)
-			wake_up_interruptible(&log_wait);
+	int pending = __this_cpu_xchg(printk_pending, 0);
+
+	if (pending & PRINTK_PENDING_SCHED) {
+		char *buf = __get_cpu_var(printk_sched_buf);
+		printk(KERN_WARNING "[sched_delayed] %s", buf);
 	}
+
+	if (pending & PRINTK_PENDING_WAKEUP)
+		wake_up_interruptible(&log_wait);
 }
 
-int printk_needs_cpu(int cpu)
-{
-	if (cpu_is_offline(cpu))
-		printk_tick();
-	return __this_cpu_read(printk_pending);
-}
+static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = {
+	.func = wake_up_klogd_work_func,
+	.flags = IRQ_WORK_LAZY,
+};
 
 void wake_up_klogd(void)
 {
-	if (waitqueue_active(&log_wait))
+	preempt_disable();
+	if (waitqueue_active(&log_wait)) {
 		this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP);
+		irq_work_queue(&__get_cpu_var(wake_up_klogd_work));
+	}
+	preempt_enable();
 }
 
 static void console_cont_flush(char *text, size_t size)
@@ -2107,7 +2102,6 @@
 		local_irq_restore(flags);
 	}
 	console_locked = 0;
-	mutex_release(&console_lock_dep_map, 1, _RET_IP_);
 
 	/* Release the exclusive_console once it is used */
 	if (unlikely(exclusive_console))
@@ -2471,6 +2465,7 @@
 	va_end(args);
 
 	__this_cpu_or(printk_pending, PRINTK_PENDING_SCHED);
+	irq_work_queue(&__get_cpu_var(wake_up_klogd_work));
 	local_irq_restore(flags);
 
 	return r;
diff --git a/kernel/profile.c b/kernel/profile.c
index 1f39181..dc3384e 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -37,9 +37,6 @@
 #define NR_PROFILE_HIT		(PAGE_SIZE/sizeof(struct profile_hit))
 #define NR_PROFILE_GRP		(NR_PROFILE_HIT/PROFILE_GRPSZ)
 
-/* Oprofile timer tick hook */
-static int (*timer_hook)(struct pt_regs *) __read_mostly;
-
 static atomic_t *prof_buffer;
 static unsigned long prof_len, prof_shift;
 
@@ -208,25 +205,6 @@
 }
 EXPORT_SYMBOL_GPL(profile_event_unregister);
 
-int register_timer_hook(int (*hook)(struct pt_regs *))
-{
-	if (timer_hook)
-		return -EBUSY;
-	timer_hook = hook;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(register_timer_hook);
-
-void unregister_timer_hook(int (*hook)(struct pt_regs *))
-{
-	WARN_ON(hook != timer_hook);
-	timer_hook = NULL;
-	/* make sure all CPUs see the NULL hook */
-	synchronize_sched();  /* Allow ongoing interrupts to complete. */
-}
-EXPORT_SYMBOL_GPL(unregister_timer_hook);
-
-
 #ifdef CONFIG_SMP
 /*
  * Each cpu has a pair of open-addressed hashtables for pending
@@ -436,8 +414,6 @@
 {
 	struct pt_regs *regs = get_irq_regs();
 
-	if (type == CPU_PROFILING && timer_hook)
-		timer_hook(regs);
 	if (!user_mode(regs) && prof_cpu_mask != NULL &&
 	    cpumask_test_cpu(smp_processor_id(), prof_cpu_mask))
 		profile_hit(type, (void *)profile_pc(regs));
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 6cbeaae..acbd284 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -712,6 +712,12 @@
 					     kiov->iov_len, kiov->iov_base);
 }
 
+/*
+ * This is declared in linux/regset.h and defined in machine-dependent
+ * code.  We put the export here, near the primary machine-neutral use,
+ * to ensure no machine forgets it.
+ */
+EXPORT_SYMBOL_GPL(task_user_regset_view);
 #endif
 
 int ptrace_request(struct task_struct *child, long request,
diff --git a/kernel/rcu.h b/kernel/rcu.h
index 20dfba5..7f8e759 100644
--- a/kernel/rcu.h
+++ b/kernel/rcu.h
@@ -111,4 +111,11 @@
 
 extern int rcu_expedited;
 
+#ifdef CONFIG_RCU_STALL_COMMON
+
+extern int rcu_cpu_stall_suppress;
+int rcu_jiffies_till_stall_check(void);
+
+#endif /* #ifdef CONFIG_RCU_STALL_COMMON */
+
 #endif /* __LINUX_RCU_H */
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index a2cf761..48ab703 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -404,11 +404,65 @@
 #endif /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 
 #if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU) || defined(CONFIG_RCU_TRACE)
-void do_trace_rcu_torture_read(char *rcutorturename, struct rcu_head *rhp)
+void do_trace_rcu_torture_read(char *rcutorturename, struct rcu_head *rhp,
+			       unsigned long secs,
+			       unsigned long c_old, unsigned long c)
 {
-	trace_rcu_torture_read(rcutorturename, rhp);
+	trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c);
 }
 EXPORT_SYMBOL_GPL(do_trace_rcu_torture_read);
 #else
-#define do_trace_rcu_torture_read(rcutorturename, rhp) do { } while (0)
+#define do_trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \
+	do { } while (0)
 #endif
+
+#ifdef CONFIG_RCU_STALL_COMMON
+
+#ifdef CONFIG_PROVE_RCU
+#define RCU_STALL_DELAY_DELTA	       (5 * HZ)
+#else
+#define RCU_STALL_DELAY_DELTA	       0
+#endif
+
+int rcu_cpu_stall_suppress __read_mostly; /* 1 = suppress stall warnings. */
+int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT;
+
+module_param(rcu_cpu_stall_suppress, int, 0644);
+module_param(rcu_cpu_stall_timeout, int, 0644);
+
+int rcu_jiffies_till_stall_check(void)
+{
+	int till_stall_check = ACCESS_ONCE(rcu_cpu_stall_timeout);
+
+	/*
+	 * Limit check must be consistent with the Kconfig limits
+	 * for CONFIG_RCU_CPU_STALL_TIMEOUT.
+	 */
+	if (till_stall_check < 3) {
+		ACCESS_ONCE(rcu_cpu_stall_timeout) = 3;
+		till_stall_check = 3;
+	} else if (till_stall_check > 300) {
+		ACCESS_ONCE(rcu_cpu_stall_timeout) = 300;
+		till_stall_check = 300;
+	}
+	return till_stall_check * HZ + RCU_STALL_DELAY_DELTA;
+}
+
+static int rcu_panic(struct notifier_block *this, unsigned long ev, void *ptr)
+{
+	rcu_cpu_stall_suppress = 1;
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block rcu_panic_block = {
+	.notifier_call = rcu_panic,
+};
+
+static int __init check_cpu_stall_init(void)
+{
+	atomic_notifier_chain_register(&panic_notifier_list, &rcu_panic_block);
+	return 0;
+}
+early_initcall(check_cpu_stall_init);
+
+#endif /* #ifdef CONFIG_RCU_STALL_COMMON */
diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
index e7dce58..a0714a5 100644
--- a/kernel/rcutiny.c
+++ b/kernel/rcutiny.c
@@ -51,10 +51,10 @@
 		       void (*func)(struct rcu_head *rcu),
 		       struct rcu_ctrlblk *rcp);
 
-#include "rcutiny_plugin.h"
-
 static long long rcu_dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
 
+#include "rcutiny_plugin.h"
+
 /* Common code for rcu_idle_enter() and rcu_irq_exit(), see kernel/rcutree.c. */
 static void rcu_idle_enter_common(long long newval)
 {
@@ -193,7 +193,7 @@
  * interrupts don't count, we must be running at the first interrupt
  * level.
  */
-int rcu_is_cpu_rrupt_from_idle(void)
+static int rcu_is_cpu_rrupt_from_idle(void)
 {
 	return rcu_dynticks_nesting <= 1;
 }
@@ -205,6 +205,7 @@
  */
 static int rcu_qsctr_help(struct rcu_ctrlblk *rcp)
 {
+	reset_cpu_stall_ticks(rcp);
 	if (rcp->rcucblist != NULL &&
 	    rcp->donetail != rcp->curtail) {
 		rcp->donetail = rcp->curtail;
@@ -251,6 +252,7 @@
  */
 void rcu_check_callbacks(int cpu, int user)
 {
+	check_cpu_stalls();
 	if (user || rcu_is_cpu_rrupt_from_idle())
 		rcu_sched_qs(cpu);
 	else if (!in_softirq())
diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h
index f85016a..8a23300 100644
--- a/kernel/rcutiny_plugin.h
+++ b/kernel/rcutiny_plugin.h
@@ -33,6 +33,9 @@
 	struct rcu_head **donetail;	/* ->next pointer of last "done" CB. */
 	struct rcu_head **curtail;	/* ->next pointer of last CB. */
 	RCU_TRACE(long qlen);		/* Number of pending CBs. */
+	RCU_TRACE(unsigned long gp_start); /* Start time for stalls. */
+	RCU_TRACE(unsigned long ticks_this_gp); /* Statistic for stalls. */
+	RCU_TRACE(unsigned long jiffies_stall); /* Jiffies at next stall. */
 	RCU_TRACE(char *name);		/* Name of RCU type. */
 };
 
@@ -54,6 +57,51 @@
 EXPORT_SYMBOL_GPL(rcu_scheduler_active);
 #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
+#ifdef CONFIG_RCU_TRACE
+
+static void check_cpu_stall(struct rcu_ctrlblk *rcp)
+{
+	unsigned long j;
+	unsigned long js;
+
+	if (rcu_cpu_stall_suppress)
+		return;
+	rcp->ticks_this_gp++;
+	j = jiffies;
+	js = rcp->jiffies_stall;
+	if (*rcp->curtail && ULONG_CMP_GE(j, js)) {
+		pr_err("INFO: %s stall on CPU (%lu ticks this GP) idle=%llx (t=%lu jiffies q=%ld)\n",
+		       rcp->name, rcp->ticks_this_gp, rcu_dynticks_nesting,
+		       jiffies - rcp->gp_start, rcp->qlen);
+		dump_stack();
+	}
+	if (*rcp->curtail && ULONG_CMP_GE(j, js))
+		rcp->jiffies_stall = jiffies +
+			3 * rcu_jiffies_till_stall_check() + 3;
+	else if (ULONG_CMP_GE(j, js))
+		rcp->jiffies_stall = jiffies + rcu_jiffies_till_stall_check();
+}
+
+static void check_cpu_stall_preempt(void);
+
+#endif /* #ifdef CONFIG_RCU_TRACE */
+
+static void reset_cpu_stall_ticks(struct rcu_ctrlblk *rcp)
+{
+#ifdef CONFIG_RCU_TRACE
+	rcp->ticks_this_gp = 0;
+	rcp->gp_start = jiffies;
+	rcp->jiffies_stall = jiffies + rcu_jiffies_till_stall_check();
+#endif /* #ifdef CONFIG_RCU_TRACE */
+}
+
+static void check_cpu_stalls(void)
+{
+	RCU_TRACE(check_cpu_stall(&rcu_bh_ctrlblk));
+	RCU_TRACE(check_cpu_stall(&rcu_sched_ctrlblk));
+	RCU_TRACE(check_cpu_stall_preempt());
+}
+
 #ifdef CONFIG_TINY_PREEMPT_RCU
 
 #include <linux/delay.h>
@@ -448,6 +496,7 @@
 		/* Official start of GP. */
 		rcu_preempt_ctrlblk.gpnum++;
 		RCU_TRACE(rcu_preempt_ctrlblk.n_grace_periods++);
+		reset_cpu_stall_ticks(&rcu_preempt_ctrlblk.rcb);
 
 		/* Any blocked RCU readers block new GP. */
 		if (rcu_preempt_blocked_readers_any())
@@ -1054,4 +1103,11 @@
 MODULE_DESCRIPTION("Read-Copy Update tracing for tiny implementation");
 MODULE_LICENSE("GPL");
 
+static void check_cpu_stall_preempt(void)
+{
+#ifdef CONFIG_TINY_PREEMPT_RCU
+	check_cpu_stall(&rcu_preempt_ctrlblk.rcb);
+#endif /* #ifdef CONFIG_TINY_PREEMPT_RCU */
+}
+
 #endif /* #ifdef CONFIG_RCU_TRACE */
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 31dea01..e1f3a8c 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -46,6 +46,7 @@
 #include <linux/stat.h>
 #include <linux/srcu.h>
 #include <linux/slab.h>
+#include <linux/trace_clock.h>
 #include <asm/byteorder.h>
 
 MODULE_LICENSE("GPL");
@@ -207,6 +208,20 @@
 #define rcu_can_boost() 0
 #endif /* #else #if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU) */
 
+#ifdef CONFIG_RCU_TRACE
+static u64 notrace rcu_trace_clock_local(void)
+{
+	u64 ts = trace_clock_local();
+	unsigned long __maybe_unused ts_rem = do_div(ts, NSEC_PER_USEC);
+	return ts;
+}
+#else /* #ifdef CONFIG_RCU_TRACE */
+static u64 notrace rcu_trace_clock_local(void)
+{
+	return 0ULL;
+}
+#endif /* #else #ifdef CONFIG_RCU_TRACE */
+
 static unsigned long shutdown_time;	/* jiffies to system shutdown. */
 static unsigned long boost_starttime;	/* jiffies of next boost test start. */
 DEFINE_MUTEX(boost_mutex);		/* protect setting boost_starttime */
@@ -845,7 +860,7 @@
 		/* Wait for the next test interval. */
 		oldstarttime = boost_starttime;
 		while (ULONG_CMP_LT(jiffies, oldstarttime)) {
-			schedule_timeout_uninterruptible(1);
+			schedule_timeout_interruptible(oldstarttime - jiffies);
 			rcu_stutter_wait("rcu_torture_boost");
 			if (kthread_should_stop() ||
 			    fullstop != FULLSTOP_DONTSTOP)
@@ -1028,7 +1043,6 @@
 		return;
 	if (atomic_xchg(&beenhere, 1) != 0)
 		return;
-	do_trace_rcu_torture_read(cur_ops->name, (struct rcu_head *)~0UL);
 	ftrace_dump(DUMP_ALL);
 }
 
@@ -1042,13 +1056,16 @@
 {
 	int idx;
 	int completed;
+	int completed_end;
 	static DEFINE_RCU_RANDOM(rand);
 	static DEFINE_SPINLOCK(rand_lock);
 	struct rcu_torture *p;
 	int pipe_count;
+	unsigned long long ts;
 
 	idx = cur_ops->readlock();
 	completed = cur_ops->completed();
+	ts = rcu_trace_clock_local();
 	p = rcu_dereference_check(rcu_torture_current,
 				  rcu_read_lock_bh_held() ||
 				  rcu_read_lock_sched_held() ||
@@ -1058,7 +1075,6 @@
 		cur_ops->readunlock(idx);
 		return;
 	}
-	do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu);
 	if (p->rtort_mbtest == 0)
 		atomic_inc(&n_rcu_torture_mberror);
 	spin_lock(&rand_lock);
@@ -1071,10 +1087,14 @@
 		/* Should not happen, but... */
 		pipe_count = RCU_TORTURE_PIPE_LEN;
 	}
-	if (pipe_count > 1)
+	completed_end = cur_ops->completed();
+	if (pipe_count > 1) {
+		do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, ts,
+					  completed, completed_end);
 		rcutorture_trace_dump();
+	}
 	__this_cpu_inc(rcu_torture_count[pipe_count]);
-	completed = cur_ops->completed() - completed;
+	completed = completed_end - completed;
 	if (completed > RCU_TORTURE_PIPE_LEN) {
 		/* Should not happen, but... */
 		completed = RCU_TORTURE_PIPE_LEN;
@@ -1094,11 +1114,13 @@
 rcu_torture_reader(void *arg)
 {
 	int completed;
+	int completed_end;
 	int idx;
 	DEFINE_RCU_RANDOM(rand);
 	struct rcu_torture *p;
 	int pipe_count;
 	struct timer_list t;
+	unsigned long long ts;
 
 	VERBOSE_PRINTK_STRING("rcu_torture_reader task started");
 	set_user_nice(current, 19);
@@ -1112,6 +1134,7 @@
 		}
 		idx = cur_ops->readlock();
 		completed = cur_ops->completed();
+		ts = rcu_trace_clock_local();
 		p = rcu_dereference_check(rcu_torture_current,
 					  rcu_read_lock_bh_held() ||
 					  rcu_read_lock_sched_held() ||
@@ -1122,7 +1145,6 @@
 			schedule_timeout_interruptible(HZ);
 			continue;
 		}
-		do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu);
 		if (p->rtort_mbtest == 0)
 			atomic_inc(&n_rcu_torture_mberror);
 		cur_ops->read_delay(&rand);
@@ -1132,10 +1154,14 @@
 			/* Should not happen, but... */
 			pipe_count = RCU_TORTURE_PIPE_LEN;
 		}
-		if (pipe_count > 1)
+		completed_end = cur_ops->completed();
+		if (pipe_count > 1) {
+			do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu,
+						  ts, completed, completed_end);
 			rcutorture_trace_dump();
+		}
 		__this_cpu_inc(rcu_torture_count[pipe_count]);
-		completed = cur_ops->completed() - completed;
+		completed = completed_end - completed;
 		if (completed > RCU_TORTURE_PIPE_LEN) {
 			/* Should not happen, but... */
 			completed = RCU_TORTURE_PIPE_LEN;
@@ -1301,19 +1327,35 @@
 				set_cpus_allowed_ptr(reader_tasks[i],
 						     shuffle_tmp_mask);
 	}
-
 	if (fakewriter_tasks) {
 		for (i = 0; i < nfakewriters; i++)
 			if (fakewriter_tasks[i])
 				set_cpus_allowed_ptr(fakewriter_tasks[i],
 						     shuffle_tmp_mask);
 	}
-
 	if (writer_task)
 		set_cpus_allowed_ptr(writer_task, shuffle_tmp_mask);
-
 	if (stats_task)
 		set_cpus_allowed_ptr(stats_task, shuffle_tmp_mask);
+	if (stutter_task)
+		set_cpus_allowed_ptr(stutter_task, shuffle_tmp_mask);
+	if (fqs_task)
+		set_cpus_allowed_ptr(fqs_task, shuffle_tmp_mask);
+	if (shutdown_task)
+		set_cpus_allowed_ptr(shutdown_task, shuffle_tmp_mask);
+#ifdef CONFIG_HOTPLUG_CPU
+	if (onoff_task)
+		set_cpus_allowed_ptr(onoff_task, shuffle_tmp_mask);
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+	if (stall_task)
+		set_cpus_allowed_ptr(stall_task, shuffle_tmp_mask);
+	if (barrier_cbs_tasks)
+		for (i = 0; i < n_barrier_cbs; i++)
+			if (barrier_cbs_tasks[i])
+				set_cpus_allowed_ptr(barrier_cbs_tasks[i],
+						     shuffle_tmp_mask);
+	if (barrier_task)
+		set_cpus_allowed_ptr(barrier_task, shuffle_tmp_mask);
 
 	if (rcu_idle_cpu == -1)
 		rcu_idle_cpu = num_online_cpus() - 1;
@@ -1749,7 +1791,7 @@
 	barrier_cbs_wq =
 		kzalloc(n_barrier_cbs * sizeof(barrier_cbs_wq[0]),
 			GFP_KERNEL);
-	if (barrier_cbs_tasks == NULL || barrier_cbs_wq == 0)
+	if (barrier_cbs_tasks == NULL || !barrier_cbs_wq)
 		return -ENOMEM;
 	for (i = 0; i < n_barrier_cbs; i++) {
 		init_waitqueue_head(&barrier_cbs_wq[i]);
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index e441b77..5b8ad82 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -105,7 +105,7 @@
  * The rcu_scheduler_active variable transitions from zero to one just
  * before the first task is spawned.  So when this variable is zero, RCU
  * can assume that there is but one task, allowing RCU to (for example)
- * optimized synchronize_sched() to a simple barrier().  When this variable
+ * optimize synchronize_sched() to a simple barrier().  When this variable
  * is one, RCU must actually do all the hard work required to detect real
  * grace periods.  This variable is also used to suppress boot-time false
  * positives from lockdep-RCU error checking.
@@ -217,12 +217,6 @@
 module_param(qhimark, long, 0444);
 module_param(qlowmark, long, 0444);
 
-int rcu_cpu_stall_suppress __read_mostly; /* 1 = suppress stall warnings. */
-int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT;
-
-module_param(rcu_cpu_stall_suppress, int, 0644);
-module_param(rcu_cpu_stall_timeout, int, 0644);
-
 static ulong jiffies_till_first_fqs = RCU_JIFFIES_TILL_FORCE_QS;
 static ulong jiffies_till_next_fqs = RCU_JIFFIES_TILL_FORCE_QS;
 
@@ -305,17 +299,27 @@
 }
 
 /*
- * Does the current CPU require a yet-as-unscheduled grace period?
+ * Does the current CPU require a not-yet-started grace period?
+ * The caller must have disabled interrupts to prevent races with
+ * normal callback registry.
  */
 static int
 cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp)
 {
-	struct rcu_head **ntp;
+	int i;
 
-	ntp = rdp->nxttail[RCU_DONE_TAIL +
-			   (ACCESS_ONCE(rsp->completed) != rdp->completed)];
-	return rdp->nxttail[RCU_DONE_TAIL] && ntp && *ntp &&
-	       !rcu_gp_in_progress(rsp);
+	if (rcu_gp_in_progress(rsp))
+		return 0;  /* No, a grace period is already in progress. */
+	if (!rdp->nxttail[RCU_NEXT_TAIL])
+		return 0;  /* No, this is a no-CBs (or offline) CPU. */
+	if (*rdp->nxttail[RCU_NEXT_READY_TAIL])
+		return 1;  /* Yes, this CPU has newly registered callbacks. */
+	for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++)
+		if (rdp->nxttail[i - 1] != rdp->nxttail[i] &&
+		    ULONG_CMP_LT(ACCESS_ONCE(rsp->completed),
+				 rdp->nxtcompleted[i]))
+			return 1;  /* Yes, CBs for future grace period. */
+	return 0; /* No grace period needed. */
 }
 
 /*
@@ -336,7 +340,7 @@
 static void rcu_eqs_enter_common(struct rcu_dynticks *rdtp, long long oldval,
 				bool user)
 {
-	trace_rcu_dyntick("Start", oldval, 0);
+	trace_rcu_dyntick("Start", oldval, rdtp->dynticks_nesting);
 	if (!user && !is_idle_task(current)) {
 		struct task_struct *idle = idle_task(smp_processor_id());
 
@@ -727,7 +731,7 @@
  * interrupt from idle, return true.  The caller must have at least
  * disabled preemption.
  */
-int rcu_is_cpu_rrupt_from_idle(void)
+static int rcu_is_cpu_rrupt_from_idle(void)
 {
 	return __get_cpu_var(rcu_dynticks).dynticks_nesting <= 1;
 }
@@ -793,28 +797,10 @@
 	return 0;
 }
 
-static int jiffies_till_stall_check(void)
-{
-	int till_stall_check = ACCESS_ONCE(rcu_cpu_stall_timeout);
-
-	/*
-	 * Limit check must be consistent with the Kconfig limits
-	 * for CONFIG_RCU_CPU_STALL_TIMEOUT.
-	 */
-	if (till_stall_check < 3) {
-		ACCESS_ONCE(rcu_cpu_stall_timeout) = 3;
-		till_stall_check = 3;
-	} else if (till_stall_check > 300) {
-		ACCESS_ONCE(rcu_cpu_stall_timeout) = 300;
-		till_stall_check = 300;
-	}
-	return till_stall_check * HZ + RCU_STALL_DELAY_DELTA;
-}
-
 static void record_gp_stall_check_time(struct rcu_state *rsp)
 {
 	rsp->gp_start = jiffies;
-	rsp->jiffies_stall = jiffies + jiffies_till_stall_check();
+	rsp->jiffies_stall = jiffies + rcu_jiffies_till_stall_check();
 }
 
 /*
@@ -857,7 +843,7 @@
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		return;
 	}
-	rsp->jiffies_stall = jiffies + 3 * jiffies_till_stall_check() + 3;
+	rsp->jiffies_stall = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 
 	/*
@@ -935,7 +921,7 @@
 	raw_spin_lock_irqsave(&rnp->lock, flags);
 	if (ULONG_CMP_GE(jiffies, rsp->jiffies_stall))
 		rsp->jiffies_stall = jiffies +
-				     3 * jiffies_till_stall_check() + 3;
+				     3 * rcu_jiffies_till_stall_check() + 3;
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 
 	set_need_resched();  /* kick ourselves to get things going. */
@@ -966,12 +952,6 @@
 	}
 }
 
-static int rcu_panic(struct notifier_block *this, unsigned long ev, void *ptr)
-{
-	rcu_cpu_stall_suppress = 1;
-	return NOTIFY_DONE;
-}
-
 /**
  * rcu_cpu_stall_reset - prevent further stall warnings in current grace period
  *
@@ -989,15 +969,6 @@
 		rsp->jiffies_stall = jiffies + ULONG_MAX / 2;
 }
 
-static struct notifier_block rcu_panic_block = {
-	.notifier_call = rcu_panic,
-};
-
-static void __init check_cpu_stall_init(void)
-{
-	atomic_notifier_chain_register(&panic_notifier_list, &rcu_panic_block);
-}
-
 /*
  * Update CPU-local rcu_data state to record the newly noticed grace period.
  * This is used both when we started the grace period and when we notice
@@ -1071,6 +1042,145 @@
 }
 
 /*
+ * Determine the value that ->completed will have at the end of the
+ * next subsequent grace period.  This is used to tag callbacks so that
+ * a CPU can invoke callbacks in a timely fashion even if that CPU has
+ * been dyntick-idle for an extended period with callbacks under the
+ * influence of RCU_FAST_NO_HZ.
+ *
+ * The caller must hold rnp->lock with interrupts disabled.
+ */
+static unsigned long rcu_cbs_completed(struct rcu_state *rsp,
+				       struct rcu_node *rnp)
+{
+	/*
+	 * If RCU is idle, we just wait for the next grace period.
+	 * But we can only be sure that RCU is idle if we are looking
+	 * at the root rcu_node structure -- otherwise, a new grace
+	 * period might have started, but just not yet gotten around
+	 * to initializing the current non-root rcu_node structure.
+	 */
+	if (rcu_get_root(rsp) == rnp && rnp->gpnum == rnp->completed)
+		return rnp->completed + 1;
+
+	/*
+	 * Otherwise, wait for a possible partial grace period and
+	 * then the subsequent full grace period.
+	 */
+	return rnp->completed + 2;
+}
+
+/*
+ * If there is room, assign a ->completed number to any callbacks on
+ * this CPU that have not already been assigned.  Also accelerate any
+ * callbacks that were previously assigned a ->completed number that has
+ * since proven to be too conservative, which can happen if callbacks get
+ * assigned a ->completed number while RCU is idle, but with reference to
+ * a non-root rcu_node structure.  This function is idempotent, so it does
+ * not hurt to call it repeatedly.
+ *
+ * The caller must hold rnp->lock with interrupts disabled.
+ */
+static void rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
+			       struct rcu_data *rdp)
+{
+	unsigned long c;
+	int i;
+
+	/* If the CPU has no callbacks, nothing to do. */
+	if (!rdp->nxttail[RCU_NEXT_TAIL] || !*rdp->nxttail[RCU_DONE_TAIL])
+		return;
+
+	/*
+	 * Starting from the sublist containing the callbacks most
+	 * recently assigned a ->completed number and working down, find the
+	 * first sublist that is not assignable to an upcoming grace period.
+	 * Such a sublist has something in it (first two tests) and has
+	 * a ->completed number assigned that will complete sooner than
+	 * the ->completed number for newly arrived callbacks (last test).
+	 *
+	 * The key point is that any later sublist can be assigned the
+	 * same ->completed number as the newly arrived callbacks, which
+	 * means that the callbacks in any of these later sublist can be
+	 * grouped into a single sublist, whether or not they have already
+	 * been assigned a ->completed number.
+	 */
+	c = rcu_cbs_completed(rsp, rnp);
+	for (i = RCU_NEXT_TAIL - 1; i > RCU_DONE_TAIL; i--)
+		if (rdp->nxttail[i] != rdp->nxttail[i - 1] &&
+		    !ULONG_CMP_GE(rdp->nxtcompleted[i], c))
+			break;
+
+	/*
+	 * If there are no sublist for unassigned callbacks, leave.
+	 * At the same time, advance "i" one sublist, so that "i" will
+	 * index into the sublist where all the remaining callbacks should
+	 * be grouped into.
+	 */
+	if (++i >= RCU_NEXT_TAIL)
+		return;
+
+	/*
+	 * Assign all subsequent callbacks' ->completed number to the next
+	 * full grace period and group them all in the sublist initially
+	 * indexed by "i".
+	 */
+	for (; i <= RCU_NEXT_TAIL; i++) {
+		rdp->nxttail[i] = rdp->nxttail[RCU_NEXT_TAIL];
+		rdp->nxtcompleted[i] = c;
+	}
+
+	/* Trace depending on how much we were able to accelerate. */
+	if (!*rdp->nxttail[RCU_WAIT_TAIL])
+		trace_rcu_grace_period(rsp->name, rdp->gpnum, "AccWaitCB");
+	else
+		trace_rcu_grace_period(rsp->name, rdp->gpnum, "AccReadyCB");
+}
+
+/*
+ * Move any callbacks whose grace period has completed to the
+ * RCU_DONE_TAIL sublist, then compact the remaining sublists and
+ * assign ->completed numbers to any callbacks in the RCU_NEXT_TAIL
+ * sublist.  This function is idempotent, so it does not hurt to
+ * invoke it repeatedly.  As long as it is not invoked -too- often...
+ *
+ * The caller must hold rnp->lock with interrupts disabled.
+ */
+static void rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
+			    struct rcu_data *rdp)
+{
+	int i, j;
+
+	/* If the CPU has no callbacks, nothing to do. */
+	if (!rdp->nxttail[RCU_NEXT_TAIL] || !*rdp->nxttail[RCU_DONE_TAIL])
+		return;
+
+	/*
+	 * Find all callbacks whose ->completed numbers indicate that they
+	 * are ready to invoke, and put them into the RCU_DONE_TAIL sublist.
+	 */
+	for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++) {
+		if (ULONG_CMP_LT(rnp->completed, rdp->nxtcompleted[i]))
+			break;
+		rdp->nxttail[RCU_DONE_TAIL] = rdp->nxttail[i];
+	}
+	/* Clean up any sublist tail pointers that were misordered above. */
+	for (j = RCU_WAIT_TAIL; j < i; j++)
+		rdp->nxttail[j] = rdp->nxttail[RCU_DONE_TAIL];
+
+	/* Copy down callbacks to fill in empty sublists. */
+	for (j = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++, j++) {
+		if (rdp->nxttail[j] == rdp->nxttail[RCU_NEXT_TAIL])
+			break;
+		rdp->nxttail[j] = rdp->nxttail[i];
+		rdp->nxtcompleted[j] = rdp->nxtcompleted[i];
+	}
+
+	/* Classify any remaining callbacks. */
+	rcu_accelerate_cbs(rsp, rnp, rdp);
+}
+
+/*
  * Advance this CPU's callbacks, but only if the current grace period
  * has ended.  This may be called only from the CPU to whom the rdp
  * belongs.  In addition, the corresponding leaf rcu_node structure's
@@ -1080,12 +1190,15 @@
 __rcu_process_gp_end(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp)
 {
 	/* Did another grace period end? */
-	if (rdp->completed != rnp->completed) {
+	if (rdp->completed == rnp->completed) {
 
-		/* Advance callbacks.  No harm if list empty. */
-		rdp->nxttail[RCU_DONE_TAIL] = rdp->nxttail[RCU_WAIT_TAIL];
-		rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_READY_TAIL];
-		rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+		/* No, so just accelerate recent callbacks. */
+		rcu_accelerate_cbs(rsp, rnp, rdp);
+
+	} else {
+
+		/* Advance callbacks. */
+		rcu_advance_cbs(rsp, rnp, rdp);
 
 		/* Remember that we saw this grace-period completion. */
 		rdp->completed = rnp->completed;
@@ -1392,17 +1505,10 @@
 	/*
 	 * Because there is no grace period in progress right now,
 	 * any callbacks we have up to this point will be satisfied
-	 * by the next grace period.  So promote all callbacks to be
-	 * handled after the end of the next grace period.  If the
-	 * CPU is not yet aware of the end of the previous grace period,
-	 * we need to allow for the callback advancement that will
-	 * occur when it does become aware.  Deadlock prevents us from
-	 * making it aware at this point: We cannot acquire a leaf
-	 * rcu_node ->lock while holding the root rcu_node ->lock.
+	 * by the next grace period.  So this is a good place to
+	 * assign a grace period number to recently posted callbacks.
 	 */
-	rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
-	if (rdp->completed == rsp->completed)
-		rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+	rcu_accelerate_cbs(rsp, rnp, rdp);
 
 	rsp->gp_flags = RCU_GP_FLAG_INIT;
 	raw_spin_unlock(&rnp->lock); /* Interrupts remain disabled. */
@@ -1527,7 +1633,7 @@
 		 * This GP can't end until cpu checks in, so all of our
 		 * callbacks can be processed during the next GP.
 		 */
-		rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+		rcu_accelerate_cbs(rsp, rnp, rdp);
 
 		rcu_report_qs_rnp(mask, rsp, rnp, flags); /* rlses rnp->lock */
 	}
@@ -1779,7 +1885,7 @@
 	long bl, count, count_lazy;
 	int i;
 
-	/* If no callbacks are ready, just return.*/
+	/* If no callbacks are ready, just return. */
 	if (!cpu_has_callbacks_ready_to_invoke(rdp)) {
 		trace_rcu_batch_start(rsp->name, rdp->qlen_lazy, rdp->qlen, 0);
 		trace_rcu_batch_end(rsp->name, 0, !!ACCESS_ONCE(rdp->nxtlist),
@@ -2008,19 +2114,19 @@
 
 	WARN_ON_ONCE(rdp->beenonline == 0);
 
-	/*
-	 * Advance callbacks in response to end of earlier grace
-	 * period that some other CPU ended.
-	 */
+	/* Handle the end of a grace period that some other CPU ended.  */
 	rcu_process_gp_end(rsp, rdp);
 
 	/* Update RCU state based on any recent quiescent states. */
 	rcu_check_quiescent_state(rsp, rdp);
 
 	/* Does this CPU require a not-yet-started grace period? */
+	local_irq_save(flags);
 	if (cpu_needs_another_gp(rsp, rdp)) {
-		raw_spin_lock_irqsave(&rcu_get_root(rsp)->lock, flags);
+		raw_spin_lock(&rcu_get_root(rsp)->lock); /* irqs disabled. */
 		rcu_start_gp(rsp, flags);  /* releases above lock */
+	} else {
+		local_irq_restore(flags);
 	}
 
 	/* If there are callbacks ready, invoke them. */
@@ -2719,9 +2825,6 @@
 	rdp->dynticks = &per_cpu(rcu_dynticks, cpu);
 	WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != DYNTICK_TASK_EXIT_IDLE);
 	WARN_ON_ONCE(atomic_read(&rdp->dynticks->dynticks) != 1);
-#ifdef CONFIG_RCU_USER_QS
-	WARN_ON_ONCE(rdp->dynticks->in_user);
-#endif
 	rdp->cpu = cpu;
 	rdp->rsp = rsp;
 	rcu_boot_init_nocb_percpu_data(rdp);
@@ -2938,6 +3041,10 @@
 
 	BUILD_BUG_ON(MAX_RCU_LVLS > ARRAY_SIZE(buf));  /* Fix buf[] init! */
 
+	/* Silence gcc 4.8 warning about array index out of range. */
+	if (rcu_num_lvls > RCU_NUM_LVLS)
+		panic("rcu_init_one: rcu_num_lvls overflow");
+
 	/* Initialize the level-tracking arrays. */
 
 	for (i = 0; i < rcu_num_lvls; i++)
@@ -3074,7 +3181,6 @@
 	cpu_notifier(rcu_cpu_notify, 0);
 	for_each_online_cpu(cpu)
 		rcu_cpu_notify(NULL, CPU_UP_PREPARE, (void *)(long)cpu);
-	check_cpu_stall_init();
 }
 
 #include "rcutree_plugin.h"
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 4b69291..c896b50 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -102,10 +102,6 @@
 				    /* idle-period nonlazy_posted snapshot. */
 	int tick_nohz_enabled_snap; /* Previously seen value from sysfs. */
 #endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */
-#ifdef CONFIG_RCU_USER_QS
-	bool ignore_user_qs;	    /* Treat userspace as extended QS or not */
-	bool in_user;		    /* Is the CPU in userland from RCU POV? */
-#endif
 };
 
 /* RCU's kthread states for tracing. */
@@ -282,6 +278,8 @@
 	 */
 	struct rcu_head *nxtlist;
 	struct rcu_head **nxttail[RCU_NEXT_SIZE];
+	unsigned long	nxtcompleted[RCU_NEXT_SIZE];
+					/* grace periods for sublists. */
 	long		qlen_lazy;	/* # of lazy queued callbacks */
 	long		qlen;		/* # of queued callbacks, incl lazy */
 	long		qlen_last_fqs_check;
@@ -343,11 +341,6 @@
 
 #define RCU_JIFFIES_TILL_FORCE_QS	 3	/* for rsp->jiffies_force_qs */
 
-#ifdef CONFIG_PROVE_RCU
-#define RCU_STALL_DELAY_DELTA	       (5 * HZ)
-#else
-#define RCU_STALL_DELAY_DELTA	       0
-#endif
 #define RCU_STALL_RAT_DELAY		2	/* Allow other CPUs time */
 						/*  to take at least one */
 						/*  scheduling clock irq */
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index f6e5ec2..c1cc7e1 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -40,8 +40,7 @@
 #ifdef CONFIG_RCU_NOCB_CPU
 static cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */
 static bool have_rcu_nocb_mask;	    /* Was rcu_nocb_mask allocated? */
-static bool rcu_nocb_poll;	    /* Offload kthread are to poll. */
-module_param(rcu_nocb_poll, bool, 0444);
+static bool __read_mostly rcu_nocb_poll;    /* Offload kthread are to poll. */
 static char __initdata nocb_buf[NR_CPUS * 5];
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU */
 
@@ -2159,6 +2158,13 @@
 }
 __setup("rcu_nocbs=", rcu_nocb_setup);
 
+static int __init parse_rcu_nocb_poll(char *arg)
+{
+	rcu_nocb_poll = 1;
+	return 0;
+}
+early_param("rcu_nocb_poll", parse_rcu_nocb_poll);
+
 /* Is the specified CPU a no-CPUs CPU? */
 static bool is_nocb_cpu(int cpu)
 {
@@ -2366,10 +2372,11 @@
 	for (;;) {
 		/* If not polling, wait for next batch of callbacks. */
 		if (!rcu_nocb_poll)
-			wait_event(rdp->nocb_wq, rdp->nocb_head);
+			wait_event_interruptible(rdp->nocb_wq, rdp->nocb_head);
 		list = ACCESS_ONCE(rdp->nocb_head);
 		if (!list) {
 			schedule_timeout_interruptible(1);
+			flush_signals(current);
 			continue;
 		}
 
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 2cd3c1b..7ae4c4c 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -222,8 +222,8 @@
 			cfs_rq->runnable_load_avg);
 	SEQ_printf(m, "  .%-30s: %lld\n", "blocked_load_avg",
 			cfs_rq->blocked_load_avg);
-	SEQ_printf(m, "  .%-30s: %ld\n", "tg_load_avg",
-			atomic64_read(&cfs_rq->tg->load_avg));
+	SEQ_printf(m, "  .%-30s: %lld\n", "tg_load_avg",
+			(unsigned long long)atomic64_read(&cfs_rq->tg->load_avg));
 	SEQ_printf(m, "  .%-30s: %lld\n", "tg_load_contrib",
 			cfs_rq->tg_load_contrib);
 	SEQ_printf(m, "  .%-30s: %d\n", "tg_runnable_contrib",
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ed18c74..7a33e59 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2661,7 +2661,7 @@
 	hrtimer_cancel(&cfs_b->slack_timer);
 }
 
-static void unthrottle_offline_cfs_rqs(struct rq *rq)
+static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
 {
 	struct cfs_rq *cfs_rq;
 
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index fb0f77e..127a2c4 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -568,7 +568,7 @@
 static int do_balance_runtime(struct rt_rq *rt_rq)
 {
 	struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
-	struct root_domain *rd = cpu_rq(smp_processor_id())->rd;
+	struct root_domain *rd = rq_of_rt_rq(rt_rq)->rd;
 	int i, weight, more = 0;
 	u64 rt_period;
 
diff --git a/kernel/smp.c b/kernel/smp.c
index 29dd40a..69f38bd 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -33,6 +33,7 @@
 	struct call_single_data	csd;
 	atomic_t		refs;
 	cpumask_var_t		cpumask;
+	cpumask_var_t		cpumask_ipi;
 };
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_function_data, cfd_data);
@@ -56,6 +57,9 @@
 		if (!zalloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL,
 				cpu_to_node(cpu)))
 			return notifier_from_errno(-ENOMEM);
+		if (!zalloc_cpumask_var_node(&cfd->cpumask_ipi, GFP_KERNEL,
+				cpu_to_node(cpu)))
+			return notifier_from_errno(-ENOMEM);
 		break;
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -65,6 +69,7 @@
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
 		free_cpumask_var(cfd->cpumask);
+		free_cpumask_var(cfd->cpumask_ipi);
 		break;
 #endif
 	};
@@ -526,6 +531,12 @@
 		return;
 	}
 
+	/*
+	 * After we put an entry into the list, data->cpumask
+	 * may be cleared again when another CPU sends another IPI for
+	 * a SMP function call, so data->cpumask will be zero.
+	 */
+	cpumask_copy(data->cpumask_ipi, data->cpumask);
 	raw_spin_lock_irqsave(&call_function.lock, flags);
 	/*
 	 * Place entry at the _HEAD_ of the list, so that any cpu still
@@ -549,7 +560,7 @@
 	smp_mb();
 
 	/* Send a message to all CPUs in the map */
-	arch_send_call_function_ipi_mask(data->cpumask);
+	arch_send_call_function_ipi_mask(data->cpumask_ipi);
 
 	/* Optionally wait for the CPUs to complete */
 	if (wait)
diff --git a/kernel/srcu.c b/kernel/srcu.c
index 2b85982..01d5ccb 100644
--- a/kernel/srcu.c
+++ b/kernel/srcu.c
@@ -282,12 +282,8 @@
  */
 void cleanup_srcu_struct(struct srcu_struct *sp)
 {
-	int sum;
-
-	sum = srcu_readers_active(sp);
-	WARN_ON(sum);  /* Leakage unless caller handles error. */
-	if (sum != 0)
-		return;
+	if (WARN_ON(srcu_readers_active(sp)))
+		return; /* Leakage unless caller handles error. */
 	free_percpu(sp->per_cpu_ref);
 	sp->per_cpu_ref = NULL;
 }
@@ -302,9 +298,8 @@
 {
 	int idx;
 
+	idx = ACCESS_ONCE(sp->completed) & 0x1;
 	preempt_disable();
-	idx = rcu_dereference_index_check(sp->completed,
-					  rcu_read_lock_sched_held()) & 0x1;
 	ACCESS_ONCE(this_cpu_ptr(sp->per_cpu_ref)->c[idx]) += 1;
 	smp_mb(); /* B */  /* Avoid leaking the critical section. */
 	ACCESS_ONCE(this_cpu_ptr(sp->per_cpu_ref)->seq[idx]) += 1;
@@ -321,10 +316,8 @@
  */
 void __srcu_read_unlock(struct srcu_struct *sp, int idx)
 {
-	preempt_disable();
 	smp_mb(); /* C */  /* Avoid leaking the critical section. */
-	ACCESS_ONCE(this_cpu_ptr(sp->per_cpu_ref)->c[idx]) -= 1;
-	preempt_enable();
+	this_cpu_dec(sp->per_cpu_ref->c[idx]);
 }
 EXPORT_SYMBOL_GPL(__srcu_read_unlock);
 
@@ -423,6 +416,7 @@
 			   !lock_is_held(&rcu_sched_lock_map),
 			   "Illegal synchronize_srcu() in same-type SRCU (or RCU) read-side critical section");
 
+	might_sleep();
 	init_completion(&rcu.completion);
 
 	head->next = NULL;
@@ -455,10 +449,12 @@
  * synchronize_srcu - wait for prior SRCU read-side critical-section completion
  * @sp: srcu_struct with which to synchronize.
  *
- * Flip the completed counter, and wait for the old count to drain to zero.
- * As with classic RCU, the updater must use some separate means of
- * synchronizing concurrent updates.  Can block; must be called from
- * process context.
+ * Wait for the count to drain to zero of both indexes. To avoid the
+ * possible starvation of synchronize_srcu(), it waits for the count of
+ * the index=((->completed & 1) ^ 1) to drain to zero at first,
+ * and then flip the completed and wait for the count of the other index.
+ *
+ * Can block; must be called from process context.
  *
  * Note that it is illegal to call synchronize_srcu() from the corresponding
  * SRCU read-side critical section; doing so will result in deadlock.
@@ -480,12 +476,11 @@
  * Wait for an SRCU grace period to elapse, but be more aggressive about
  * spinning rather than blocking when waiting.
  *
- * Note that it is illegal to call this function while holding any lock
- * that is acquired by a CPU-hotplug notifier.  It is also illegal to call
- * synchronize_srcu_expedited() from the corresponding SRCU read-side
- * critical section; doing so will result in deadlock.  However, it is
- * perfectly legal to call synchronize_srcu_expedited() on one srcu_struct
- * from some other srcu_struct's read-side critical section, as long as
+ * Note that it is also illegal to call synchronize_srcu_expedited()
+ * from the corresponding SRCU read-side critical section;
+ * doing so will result in deadlock.  However, it is perfectly legal
+ * to call synchronize_srcu_expedited() on one srcu_struct from some
+ * other srcu_struct's read-side critical section, as long as
  * the resulting graph of srcu_structs is acyclic.
  */
 void synchronize_srcu_expedited(struct srcu_struct *sp)
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 46dfb6d..314b9ee 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -20,6 +20,7 @@
 #include <linux/profile.h>
 #include <linux/sched.h>
 #include <linux/module.h>
+#include <linux/irq_work.h>
 
 #include <asm/irq_regs.h>
 
@@ -28,7 +29,7 @@
 /*
  * Per cpu nohz control structure
  */
-static DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched);
+DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched);
 
 /*
  * The time, when the last jiffy update happened. Protected by jiffies_lock.
@@ -331,8 +332,8 @@
 		time_delta = timekeeping_max_deferment();
 	} while (read_seqretry(&jiffies_lock, seq));
 
-	if (rcu_needs_cpu(cpu, &rcu_delta_jiffies) || printk_needs_cpu(cpu) ||
-	    arch_needs_cpu(cpu)) {
+	if (rcu_needs_cpu(cpu, &rcu_delta_jiffies) ||
+	    arch_needs_cpu(cpu) || irq_work_needs_cpu()) {
 		next_jiffies = last_jiffies + 1;
 		delta_jiffies = 1;
 	} else {
diff --git a/kernel/timer.c b/kernel/timer.c
index 3e13baf..dbf7a78 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1352,7 +1352,6 @@
 	account_process_tick(p, user_tick);
 	run_local_timers();
 	rcu_check_callbacks(cpu, user_tick);
-	printk_tick();
 #ifdef CONFIG_IRQ_WORK
 	if (in_irq())
 		irq_work_run();
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 5d89335..3656756 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -39,6 +39,9 @@
 	help
 	  See Documentation/trace/ftrace-design.txt
 
+config HAVE_DYNAMIC_FTRACE_WITH_REGS
+	bool
+
 config HAVE_FTRACE_MCOUNT_RECORD
 	bool
 	help
@@ -250,6 +253,16 @@
 	help
 	  Basic tracer to catch the syscall entry and exit events.
 
+config TRACER_SNAPSHOT
+	bool "Create a snapshot trace buffer"
+	select TRACER_MAX_TRACE
+	help
+	  Allow tracing users to take snapshot of the current buffer using the
+	  ftrace interface, e.g.:
+
+	      echo 1 > /sys/kernel/debug/tracing/snapshot
+	      cat snapshot
+
 config TRACE_BRANCH_PROFILING
 	bool
 	select GENERIC_TRACER
@@ -434,6 +447,11 @@
 	  were made. If so, it runs stop_machine (stops all CPUS)
 	  and modifies the code to jump over the call to ftrace.
 
+config DYNAMIC_FTRACE_WITH_REGS
+	def_bool y
+	depends on DYNAMIC_FTRACE
+	depends on HAVE_DYNAMIC_FTRACE_WITH_REGS
+
 config FUNCTION_PROFILER
 	bool "Kernel function profiler"
 	depends on FUNCTION_TRACER
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index c0bd030..71259e2 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -147,7 +147,7 @@
 		return;
 
 	local_irq_save(flags);
-	buf = per_cpu_ptr(bt->msg_data, smp_processor_id());
+	buf = this_cpu_ptr(bt->msg_data);
 	va_start(args, fmt);
 	n = vscnprintf(buf, BLK_TN_MAX_MSG, fmt, args);
 	va_end(args);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 41473b4..ce8c3d6 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -111,6 +111,26 @@
 #define ftrace_ops_list_func ((ftrace_func_t)ftrace_ops_no_ops)
 #endif
 
+/*
+ * Traverse the ftrace_global_list, invoking all entries.  The reason that we
+ * can use rcu_dereference_raw() is that elements removed from this list
+ * are simply leaked, so there is no need to interact with a grace-period
+ * mechanism.  The rcu_dereference_raw() calls are needed to handle
+ * concurrent insertions into the ftrace_global_list.
+ *
+ * Silly Alpha and silly pointer-speculation compiler optimizations!
+ */
+#define do_for_each_ftrace_op(op, list)			\
+	op = rcu_dereference_raw(list);			\
+	do
+
+/*
+ * Optimized for just a single item in the list (as that is the normal case).
+ */
+#define while_for_each_ftrace_op(op)				\
+	while (likely(op = rcu_dereference_raw((op)->next)) &&	\
+	       unlikely((op) != &ftrace_list_end))
+
 /**
  * ftrace_nr_registered_ops - return number of ops registered
  *
@@ -132,29 +152,21 @@
 	return cnt;
 }
 
-/*
- * Traverse the ftrace_global_list, invoking all entries.  The reason that we
- * can use rcu_dereference_raw() is that elements removed from this list
- * are simply leaked, so there is no need to interact with a grace-period
- * mechanism.  The rcu_dereference_raw() calls are needed to handle
- * concurrent insertions into the ftrace_global_list.
- *
- * Silly Alpha and silly pointer-speculation compiler optimizations!
- */
 static void
 ftrace_global_list_func(unsigned long ip, unsigned long parent_ip,
 			struct ftrace_ops *op, struct pt_regs *regs)
 {
-	if (unlikely(trace_recursion_test(TRACE_GLOBAL_BIT)))
+	int bit;
+
+	bit = trace_test_and_set_recursion(TRACE_GLOBAL_START, TRACE_GLOBAL_MAX);
+	if (bit < 0)
 		return;
 
-	trace_recursion_set(TRACE_GLOBAL_BIT);
-	op = rcu_dereference_raw(ftrace_global_list); /*see above*/
-	while (op != &ftrace_list_end) {
+	do_for_each_ftrace_op(op, ftrace_global_list) {
 		op->func(ip, parent_ip, op, regs);
-		op = rcu_dereference_raw(op->next); /*see above*/
-	};
-	trace_recursion_clear(TRACE_GLOBAL_BIT);
+	} while_for_each_ftrace_op(op);
+
+	trace_clear_recursion(bit);
 }
 
 static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip,
@@ -221,10 +233,24 @@
 	 * registered callers.
 	 */
 	if (ftrace_global_list == &ftrace_list_end ||
-	    ftrace_global_list->next == &ftrace_list_end)
+	    ftrace_global_list->next == &ftrace_list_end) {
 		func = ftrace_global_list->func;
-	else
+		/*
+		 * As we are calling the function directly.
+		 * If it does not have recursion protection,
+		 * the function_trace_op needs to be updated
+		 * accordingly.
+		 */
+		if (ftrace_global_list->flags & FTRACE_OPS_FL_RECURSION_SAFE)
+			global_ops.flags |= FTRACE_OPS_FL_RECURSION_SAFE;
+		else
+			global_ops.flags &= ~FTRACE_OPS_FL_RECURSION_SAFE;
+	} else {
 		func = ftrace_global_list_func;
+		/* The list has its own recursion protection. */
+		global_ops.flags |= FTRACE_OPS_FL_RECURSION_SAFE;
+	}
+
 
 	/* If we filter on pids, update to use the pid function */
 	if (!list_empty(&ftrace_pids)) {
@@ -337,7 +363,7 @@
 	if ((ops->flags & FL_GLOBAL_CONTROL_MASK) == FL_GLOBAL_CONTROL_MASK)
 		return -EINVAL;
 
-#ifndef ARCH_SUPPORTS_FTRACE_SAVE_REGS
+#ifndef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 	/*
 	 * If the ftrace_ops specifies SAVE_REGS, then it only can be used
 	 * if the arch supports it, or SAVE_REGS_IF_SUPPORTED is also set.
@@ -4090,14 +4116,11 @@
 	 */
 	preempt_disable_notrace();
 	trace_recursion_set(TRACE_CONTROL_BIT);
-	op = rcu_dereference_raw(ftrace_control_list);
-	while (op != &ftrace_list_end) {
+	do_for_each_ftrace_op(op, ftrace_control_list) {
 		if (!ftrace_function_local_disabled(op) &&
 		    ftrace_ops_test(op, ip))
 			op->func(ip, parent_ip, op, regs);
-
-		op = rcu_dereference_raw(op->next);
-	};
+	} while_for_each_ftrace_op(op);
 	trace_recursion_clear(TRACE_CONTROL_BIT);
 	preempt_enable_notrace();
 }
@@ -4112,27 +4135,26 @@
 		       struct ftrace_ops *ignored, struct pt_regs *regs)
 {
 	struct ftrace_ops *op;
+	int bit;
 
 	if (function_trace_stop)
 		return;
 
-	if (unlikely(trace_recursion_test(TRACE_INTERNAL_BIT)))
+	bit = trace_test_and_set_recursion(TRACE_LIST_START, TRACE_LIST_MAX);
+	if (bit < 0)
 		return;
 
-	trace_recursion_set(TRACE_INTERNAL_BIT);
 	/*
 	 * Some of the ops may be dynamically allocated,
 	 * they must be freed after a synchronize_sched().
 	 */
 	preempt_disable_notrace();
-	op = rcu_dereference_raw(ftrace_ops_list);
-	while (op != &ftrace_list_end) {
+	do_for_each_ftrace_op(op, ftrace_ops_list) {
 		if (ftrace_ops_test(op, ip))
 			op->func(ip, parent_ip, op, regs);
-		op = rcu_dereference_raw(op->next);
-	};
+	} while_for_each_ftrace_op(op);
 	preempt_enable_notrace();
-	trace_recursion_clear(TRACE_INTERNAL_BIT);
+	trace_clear_recursion(bit);
 }
 
 /*
@@ -4143,8 +4165,8 @@
  * Archs are to support both the regs and ftrace_ops at the same time.
  * If they support ftrace_ops, it is assumed they support regs.
  * If call backs want to use regs, they must either check for regs
- * being NULL, or ARCH_SUPPORTS_FTRACE_SAVE_REGS.
- * Note, ARCH_SUPPORT_SAVE_REGS expects a full regs to be saved.
+ * being NULL, or CONFIG_DYNAMIC_FTRACE_WITH_REGS.
+ * Note, CONFIG_DYNAMIC_FTRACE_WITH_REGS expects a full regs to be saved.
  * An architecture can pass partial regs with ftrace_ops and still
  * set the ARCH_SUPPORT_FTARCE_OPS.
  */
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index ce8514fe..7244acd 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3,8 +3,10 @@
  *
  * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com>
  */
+#include <linux/ftrace_event.h>
 #include <linux/ring_buffer.h>
 #include <linux/trace_clock.h>
+#include <linux/trace_seq.h>
 #include <linux/spinlock.h>
 #include <linux/debugfs.h>
 #include <linux/uaccess.h>
@@ -21,7 +23,6 @@
 #include <linux/fs.h>
 
 #include <asm/local.h>
-#include "trace.h"
 
 static void update_pages_handler(struct work_struct *work);
 
@@ -2432,41 +2433,76 @@
 
 #ifdef CONFIG_TRACING
 
-#define TRACE_RECURSIVE_DEPTH 16
+/*
+ * The lock and unlock are done within a preempt disable section.
+ * The current_context per_cpu variable can only be modified
+ * by the current task between lock and unlock. But it can
+ * be modified more than once via an interrupt. To pass this
+ * information from the lock to the unlock without having to
+ * access the 'in_interrupt()' functions again (which do show
+ * a bit of overhead in something as critical as function tracing,
+ * we use a bitmask trick.
+ *
+ *  bit 0 =  NMI context
+ *  bit 1 =  IRQ context
+ *  bit 2 =  SoftIRQ context
+ *  bit 3 =  normal context.
+ *
+ * This works because this is the order of contexts that can
+ * preempt other contexts. A SoftIRQ never preempts an IRQ
+ * context.
+ *
+ * When the context is determined, the corresponding bit is
+ * checked and set (if it was set, then a recursion of that context
+ * happened).
+ *
+ * On unlock, we need to clear this bit. To do so, just subtract
+ * 1 from the current_context and AND it to itself.
+ *
+ * (binary)
+ *  101 - 1 = 100
+ *  101 & 100 = 100 (clearing bit zero)
+ *
+ *  1010 - 1 = 1001
+ *  1010 & 1001 = 1000 (clearing bit 1)
+ *
+ * The least significant bit can be cleared this way, and it
+ * just so happens that it is the same bit corresponding to
+ * the current context.
+ */
+static DEFINE_PER_CPU(unsigned int, current_context);
 
-/* Keep this code out of the fast path cache */
-static noinline void trace_recursive_fail(void)
+static __always_inline int trace_recursive_lock(void)
 {
-	/* Disable all tracing before we do anything else */
-	tracing_off_permanent();
+	unsigned int val = this_cpu_read(current_context);
+	int bit;
 
-	printk_once(KERN_WARNING "Tracing recursion: depth[%ld]:"
-		    "HC[%lu]:SC[%lu]:NMI[%lu]\n",
-		    trace_recursion_buffer(),
-		    hardirq_count() >> HARDIRQ_SHIFT,
-		    softirq_count() >> SOFTIRQ_SHIFT,
-		    in_nmi());
+	if (in_interrupt()) {
+		if (in_nmi())
+			bit = 0;
+		else if (in_irq())
+			bit = 1;
+		else
+			bit = 2;
+	} else
+		bit = 3;
 
-	WARN_ON_ONCE(1);
+	if (unlikely(val & (1 << bit)))
+		return 1;
+
+	val |= (1 << bit);
+	this_cpu_write(current_context, val);
+
+	return 0;
 }
 
-static inline int trace_recursive_lock(void)
+static __always_inline void trace_recursive_unlock(void)
 {
-	trace_recursion_inc();
+	unsigned int val = this_cpu_read(current_context);
 
-	if (likely(trace_recursion_buffer() < TRACE_RECURSIVE_DEPTH))
-		return 0;
-
-	trace_recursive_fail();
-
-	return -1;
-}
-
-static inline void trace_recursive_unlock(void)
-{
-	WARN_ON_ONCE(!trace_recursion_buffer());
-
-	trace_recursion_dec();
+	val--;
+	val &= this_cpu_read(current_context);
+	this_cpu_write(current_context, val);
 }
 
 #else
@@ -3067,6 +3103,24 @@
 EXPORT_SYMBOL_GPL(ring_buffer_dropped_events_cpu);
 
 /**
+ * ring_buffer_read_events_cpu - get the number of events successfully read
+ * @buffer: The ring buffer
+ * @cpu: The per CPU buffer to get the number of events read
+ */
+unsigned long
+ring_buffer_read_events_cpu(struct ring_buffer *buffer, int cpu)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+
+	if (!cpumask_test_cpu(cpu, buffer->cpumask))
+		return 0;
+
+	cpu_buffer = buffer->buffers[cpu];
+	return cpu_buffer->read;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_read_events_cpu);
+
+/**
  * ring_buffer_entries - get the number of entries in a buffer
  * @buffer: The ring buffer
  *
@@ -3425,7 +3479,7 @@
 	/* check for end of page padding */
 	if ((iter->head >= rb_page_size(iter->head_page)) &&
 	    (iter->head_page != cpu_buffer->commit_page))
-		rb_advance_iter(iter);
+		rb_inc_iter(iter);
 }
 
 static int rb_lost_events(struct ring_buffer_per_cpu *cpu_buffer)
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 4d2e4af..c2e2c23 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -250,7 +250,7 @@
 static struct tracer		*trace_types __read_mostly;
 
 /* current_trace points to the tracer that is currently active */
-static struct tracer		*current_trace __read_mostly;
+static struct tracer		*current_trace __read_mostly = &nop_trace;
 
 /*
  * trace_types_lock is used to protect the trace_types list.
@@ -710,10 +710,13 @@
 		return;
 
 	WARN_ON_ONCE(!irqs_disabled());
-	if (!current_trace->use_max_tr) {
-		WARN_ON_ONCE(1);
+
+	if (!current_trace->allocated_snapshot) {
+		/* Only the nop tracer should hit this when disabling */
+		WARN_ON_ONCE(current_trace != &nop_trace);
 		return;
 	}
+
 	arch_spin_lock(&ftrace_max_lock);
 
 	tr->buffer = max_tr.buffer;
@@ -740,10 +743,8 @@
 		return;
 
 	WARN_ON_ONCE(!irqs_disabled());
-	if (!current_trace->use_max_tr) {
-		WARN_ON_ONCE(1);
+	if (WARN_ON_ONCE(!current_trace->allocated_snapshot))
 		return;
-	}
 
 	arch_spin_lock(&ftrace_max_lock);
 
@@ -863,10 +864,13 @@
 
 		current_trace = type;
 
-		/* If we expanded the buffers, make sure the max is expanded too */
-		if (ring_buffer_expanded && type->use_max_tr)
-			ring_buffer_resize(max_tr.buffer, trace_buf_size,
-						RING_BUFFER_ALL_CPUS);
+		if (type->use_max_tr) {
+			/* If we expanded the buffers, make sure the max is expanded too */
+			if (ring_buffer_expanded)
+				ring_buffer_resize(max_tr.buffer, trace_buf_size,
+						   RING_BUFFER_ALL_CPUS);
+			type->allocated_snapshot = true;
+		}
 
 		/* the test is responsible for initializing and enabling */
 		pr_info("Testing tracer %s: ", type->name);
@@ -882,10 +886,14 @@
 		/* Only reset on passing, to avoid touching corrupted buffers */
 		tracing_reset_online_cpus(tr);
 
-		/* Shrink the max buffer again */
-		if (ring_buffer_expanded && type->use_max_tr)
-			ring_buffer_resize(max_tr.buffer, 1,
-						RING_BUFFER_ALL_CPUS);
+		if (type->use_max_tr) {
+			type->allocated_snapshot = false;
+
+			/* Shrink the max buffer again */
+			if (ring_buffer_expanded)
+				ring_buffer_resize(max_tr.buffer, 1,
+						   RING_BUFFER_ALL_CPUS);
+		}
 
 		printk(KERN_CONT "PASSED\n");
 	}
@@ -923,6 +931,9 @@
 {
 	struct ring_buffer *buffer = tr->buffer;
 
+	if (!buffer)
+		return;
+
 	ring_buffer_record_disable(buffer);
 
 	/* Make sure all commits have finished */
@@ -937,6 +948,9 @@
 	struct ring_buffer *buffer = tr->buffer;
 	int cpu;
 
+	if (!buffer)
+		return;
+
 	ring_buffer_record_disable(buffer);
 
 	/* Make sure all commits have finished */
@@ -1168,7 +1182,6 @@
 
 	entry->preempt_count		= pc & 0xff;
 	entry->pid			= (tsk) ? tsk->pid : 0;
-	entry->padding			= 0;
 	entry->flags =
 #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT
 		(irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) |
@@ -1336,7 +1349,7 @@
 	 */
 	preempt_disable_notrace();
 
-	use_stack = ++__get_cpu_var(ftrace_stack_reserve);
+	use_stack = __this_cpu_inc_return(ftrace_stack_reserve);
 	/*
 	 * We don't need any atomic variables, just a barrier.
 	 * If an interrupt comes in, we don't care, because it would
@@ -1390,7 +1403,7 @@
  out:
 	/* Again, don't let gcc optimize things here */
 	barrier();
-	__get_cpu_var(ftrace_stack_reserve)--;
+	__this_cpu_dec(ftrace_stack_reserve);
 	preempt_enable_notrace();
 
 }
@@ -1518,7 +1531,6 @@
 static char *get_trace_buf(void)
 {
 	struct trace_buffer_struct *percpu_buffer;
-	struct trace_buffer_struct *buffer;
 
 	/*
 	 * If we have allocated per cpu buffers, then we do not
@@ -1536,9 +1548,7 @@
 	if (!percpu_buffer)
 		return NULL;
 
-	buffer = per_cpu_ptr(percpu_buffer, smp_processor_id());
-
-	return buffer->buffer;
+	return this_cpu_ptr(&percpu_buffer->buffer[0]);
 }
 
 static int alloc_percpu_trace_buffer(void)
@@ -1943,21 +1953,27 @@
 static void *s_start(struct seq_file *m, loff_t *pos)
 {
 	struct trace_iterator *iter = m->private;
-	static struct tracer *old_tracer;
 	int cpu_file = iter->cpu_file;
 	void *p = NULL;
 	loff_t l = 0;
 	int cpu;
 
-	/* copy the tracer to avoid using a global lock all around */
+	/*
+	 * copy the tracer to avoid using a global lock all around.
+	 * iter->trace is a copy of current_trace, the pointer to the
+	 * name may be used instead of a strcmp(), as iter->trace->name
+	 * will point to the same string as current_trace->name.
+	 */
 	mutex_lock(&trace_types_lock);
-	if (unlikely(old_tracer != current_trace && current_trace)) {
-		old_tracer = current_trace;
+	if (unlikely(current_trace && iter->trace->name != current_trace->name))
 		*iter->trace = *current_trace;
-	}
 	mutex_unlock(&trace_types_lock);
 
-	atomic_inc(&trace_record_cmdline_disabled);
+	if (iter->snapshot && iter->trace->use_max_tr)
+		return ERR_PTR(-EBUSY);
+
+	if (!iter->snapshot)
+		atomic_inc(&trace_record_cmdline_disabled);
 
 	if (*pos != iter->pos) {
 		iter->ent = NULL;
@@ -1996,7 +2012,11 @@
 {
 	struct trace_iterator *iter = m->private;
 
-	atomic_dec(&trace_record_cmdline_disabled);
+	if (iter->snapshot && iter->trace->use_max_tr)
+		return;
+
+	if (!iter->snapshot)
+		atomic_dec(&trace_record_cmdline_disabled);
 	trace_access_unlock(iter->cpu_file);
 	trace_event_read_unlock();
 }
@@ -2081,8 +2101,7 @@
 	unsigned long total;
 	const char *name = "preemption";
 
-	if (type)
-		name = type->name;
+	name = type->name;
 
 	get_total_entries(tr, &total, &entries);
 
@@ -2431,7 +2450,7 @@
 };
 
 static struct trace_iterator *
-__tracing_open(struct inode *inode, struct file *file)
+__tracing_open(struct inode *inode, struct file *file, bool snapshot)
 {
 	long cpu_file = (long) inode->i_private;
 	struct trace_iterator *iter;
@@ -2458,16 +2477,16 @@
 	if (!iter->trace)
 		goto fail;
 
-	if (current_trace)
-		*iter->trace = *current_trace;
+	*iter->trace = *current_trace;
 
 	if (!zalloc_cpumask_var(&iter->started, GFP_KERNEL))
 		goto fail;
 
-	if (current_trace && current_trace->print_max)
+	if (current_trace->print_max || snapshot)
 		iter->tr = &max_tr;
 	else
 		iter->tr = &global_trace;
+	iter->snapshot = snapshot;
 	iter->pos = -1;
 	mutex_init(&iter->mutex);
 	iter->cpu_file = cpu_file;
@@ -2484,8 +2503,9 @@
 	if (trace_clocks[trace_clock_id].in_ns)
 		iter->iter_flags |= TRACE_FILE_TIME_IN_NS;
 
-	/* stop the trace while dumping */
-	tracing_stop();
+	/* stop the trace while dumping if we are not opening "snapshot" */
+	if (!iter->snapshot)
+		tracing_stop();
 
 	if (iter->cpu_file == TRACE_PIPE_ALL_CPU) {
 		for_each_tracing_cpu(cpu) {
@@ -2548,8 +2568,9 @@
 	if (iter->trace && iter->trace->close)
 		iter->trace->close(iter);
 
-	/* reenable tracing if it was previously enabled */
-	tracing_start();
+	if (!iter->snapshot)
+		/* reenable tracing if it was previously enabled */
+		tracing_start();
 	mutex_unlock(&trace_types_lock);
 
 	mutex_destroy(&iter->mutex);
@@ -2577,7 +2598,7 @@
 	}
 
 	if (file->f_mode & FMODE_READ) {
-		iter = __tracing_open(inode, file);
+		iter = __tracing_open(inode, file, false);
 		if (IS_ERR(iter))
 			ret = PTR_ERR(iter);
 		else if (trace_flags & TRACE_ITER_LATENCY_FMT)
@@ -3015,10 +3036,7 @@
 	int r;
 
 	mutex_lock(&trace_types_lock);
-	if (current_trace)
-		r = sprintf(buf, "%s\n", current_trace->name);
-	else
-		r = sprintf(buf, "\n");
+	r = sprintf(buf, "%s\n", current_trace->name);
 	mutex_unlock(&trace_types_lock);
 
 	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
@@ -3184,6 +3202,7 @@
 	static struct trace_option_dentry *topts;
 	struct trace_array *tr = &global_trace;
 	struct tracer *t;
+	bool had_max_tr;
 	int ret = 0;
 
 	mutex_lock(&trace_types_lock);
@@ -3208,9 +3227,21 @@
 		goto out;
 
 	trace_branch_disable();
-	if (current_trace && current_trace->reset)
+	if (current_trace->reset)
 		current_trace->reset(tr);
-	if (current_trace && current_trace->use_max_tr) {
+
+	had_max_tr = current_trace->allocated_snapshot;
+	current_trace = &nop_trace;
+
+	if (had_max_tr && !t->use_max_tr) {
+		/*
+		 * We need to make sure that the update_max_tr sees that
+		 * current_trace changed to nop_trace to keep it from
+		 * swapping the buffers after we resize it.
+		 * The update_max_tr is called from interrupts disabled
+		 * so a synchronized_sched() is sufficient.
+		 */
+		synchronize_sched();
 		/*
 		 * We don't free the ring buffer. instead, resize it because
 		 * The max_tr ring buffer has some state (e.g. ring->clock) and
@@ -3218,18 +3249,19 @@
 		 */
 		ring_buffer_resize(max_tr.buffer, 1, RING_BUFFER_ALL_CPUS);
 		set_buffer_entries(&max_tr, 1);
+		tracing_reset_online_cpus(&max_tr);
+		current_trace->allocated_snapshot = false;
 	}
 	destroy_trace_option_files(topts);
 
-	current_trace = &nop_trace;
-
 	topts = create_trace_option_files(t);
-	if (t->use_max_tr) {
+	if (t->use_max_tr && !had_max_tr) {
 		/* we need to make per cpu buffer sizes equivalent */
 		ret = resize_buffer_duplicate_size(&max_tr, &global_trace,
 						   RING_BUFFER_ALL_CPUS);
 		if (ret < 0)
 			goto out;
+		t->allocated_snapshot = true;
 	}
 
 	if (t->init) {
@@ -3337,8 +3369,7 @@
 		ret = -ENOMEM;
 		goto fail;
 	}
-	if (current_trace)
-		*iter->trace = *current_trace;
+	*iter->trace = *current_trace;
 
 	if (!alloc_cpumask_var(&iter->started, GFP_KERNEL)) {
 		ret = -ENOMEM;
@@ -3478,7 +3509,6 @@
 		  size_t cnt, loff_t *ppos)
 {
 	struct trace_iterator *iter = filp->private_data;
-	static struct tracer *old_tracer;
 	ssize_t sret;
 
 	/* return any leftover data */
@@ -3490,10 +3520,8 @@
 
 	/* copy the tracer to avoid using a global lock all around */
 	mutex_lock(&trace_types_lock);
-	if (unlikely(old_tracer != current_trace && current_trace)) {
-		old_tracer = current_trace;
+	if (unlikely(iter->trace->name != current_trace->name))
 		*iter->trace = *current_trace;
-	}
 	mutex_unlock(&trace_types_lock);
 
 	/*
@@ -3649,7 +3677,6 @@
 		.ops		= &tracing_pipe_buf_ops,
 		.spd_release	= tracing_spd_release_pipe,
 	};
-	static struct tracer *old_tracer;
 	ssize_t ret;
 	size_t rem;
 	unsigned int i;
@@ -3659,10 +3686,8 @@
 
 	/* copy the tracer to avoid using a global lock all around */
 	mutex_lock(&trace_types_lock);
-	if (unlikely(old_tracer != current_trace && current_trace)) {
-		old_tracer = current_trace;
+	if (unlikely(iter->trace->name != current_trace->name))
 		*iter->trace = *current_trace;
-	}
 	mutex_unlock(&trace_types_lock);
 
 	mutex_lock(&iter->mutex);
@@ -4038,8 +4063,7 @@
 	 * Reset the buffer so that it doesn't have incomparable timestamps.
 	 */
 	tracing_reset_online_cpus(&global_trace);
-	if (max_tr.buffer)
-		tracing_reset_online_cpus(&max_tr);
+	tracing_reset_online_cpus(&max_tr);
 
 	mutex_unlock(&trace_types_lock);
 
@@ -4055,6 +4079,87 @@
 	return single_open(file, tracing_clock_show, NULL);
 }
 
+#ifdef CONFIG_TRACER_SNAPSHOT
+static int tracing_snapshot_open(struct inode *inode, struct file *file)
+{
+	struct trace_iterator *iter;
+	int ret = 0;
+
+	if (file->f_mode & FMODE_READ) {
+		iter = __tracing_open(inode, file, true);
+		if (IS_ERR(iter))
+			ret = PTR_ERR(iter);
+	}
+	return ret;
+}
+
+static ssize_t
+tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt,
+		       loff_t *ppos)
+{
+	unsigned long val;
+	int ret;
+
+	ret = tracing_update_buffers();
+	if (ret < 0)
+		return ret;
+
+	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+	if (ret)
+		return ret;
+
+	mutex_lock(&trace_types_lock);
+
+	if (current_trace->use_max_tr) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	switch (val) {
+	case 0:
+		if (current_trace->allocated_snapshot) {
+			/* free spare buffer */
+			ring_buffer_resize(max_tr.buffer, 1,
+					   RING_BUFFER_ALL_CPUS);
+			set_buffer_entries(&max_tr, 1);
+			tracing_reset_online_cpus(&max_tr);
+			current_trace->allocated_snapshot = false;
+		}
+		break;
+	case 1:
+		if (!current_trace->allocated_snapshot) {
+			/* allocate spare buffer */
+			ret = resize_buffer_duplicate_size(&max_tr,
+					&global_trace, RING_BUFFER_ALL_CPUS);
+			if (ret < 0)
+				break;
+			current_trace->allocated_snapshot = true;
+		}
+
+		local_irq_disable();
+		/* Now, we're going to swap */
+		update_max_tr(&global_trace, current, smp_processor_id());
+		local_irq_enable();
+		break;
+	default:
+		if (current_trace->allocated_snapshot)
+			tracing_reset_online_cpus(&max_tr);
+		else
+			ret = -EINVAL;
+		break;
+	}
+
+	if (ret >= 0) {
+		*ppos += cnt;
+		ret = cnt;
+	}
+out:
+	mutex_unlock(&trace_types_lock);
+	return ret;
+}
+#endif /* CONFIG_TRACER_SNAPSHOT */
+
+
 static const struct file_operations tracing_max_lat_fops = {
 	.open		= tracing_open_generic,
 	.read		= tracing_max_lat_read,
@@ -4111,6 +4216,16 @@
 	.write		= tracing_clock_write,
 };
 
+#ifdef CONFIG_TRACER_SNAPSHOT
+static const struct file_operations snapshot_fops = {
+	.open		= tracing_snapshot_open,
+	.read		= seq_read,
+	.write		= tracing_snapshot_write,
+	.llseek		= tracing_seek,
+	.release	= tracing_release,
+};
+#endif /* CONFIG_TRACER_SNAPSHOT */
+
 struct ftrace_buffer_info {
 	struct trace_array	*tr;
 	void			*spare;
@@ -4415,6 +4530,9 @@
 	cnt = ring_buffer_dropped_events_cpu(tr->buffer, cpu);
 	trace_seq_printf(s, "dropped events: %ld\n", cnt);
 
+	cnt = ring_buffer_read_events_cpu(tr->buffer, cpu);
+	trace_seq_printf(s, "read events: %ld\n", cnt);
+
 	count = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->len);
 
 	kfree(s);
@@ -4491,7 +4609,7 @@
 
 static struct dentry *d_percpu;
 
-struct dentry *tracing_dentry_percpu(void)
+static struct dentry *tracing_dentry_percpu(void)
 {
 	static int once;
 	struct dentry *d_tracer;
@@ -4907,6 +5025,11 @@
 			&ftrace_update_tot_cnt, &tracing_dyn_info_fops);
 #endif
 
+#ifdef CONFIG_TRACER_SNAPSHOT
+	trace_create_file("snapshot", 0644, d_tracer,
+			  (void *) TRACE_PIPE_ALL_CPU, &snapshot_fops);
+#endif
+
 	create_trace_options_dir();
 
 	for_each_tracing_cpu(cpu)
@@ -5015,6 +5138,7 @@
 	if (disable_tracing)
 		ftrace_kill();
 
+	/* Simulate the iterator */
 	trace_init_global_iter(&iter);
 
 	for_each_tracing_cpu(cpu) {
@@ -5026,10 +5150,6 @@
 	/* don't look at user memory in panic mode */
 	trace_flags &= ~TRACE_ITER_SYM_USEROBJ;
 
-	/* Simulate the iterator */
-	iter.tr = &global_trace;
-	iter.trace = current_trace;
-
 	switch (oops_dump_mode) {
 	case DUMP_ALL:
 		iter.cpu_file = TRACE_PIPE_ALL_CPU;
@@ -5174,7 +5294,7 @@
 	init_irq_work(&trace_work_wakeup, trace_wake_up);
 
 	register_tracer(&nop_trace);
-	current_trace = &nop_trace;
+
 	/* All seems OK, enable tracing */
 	tracing_disabled = 0;
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index c75d798..57d7e53 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -287,20 +287,62 @@
 	struct tracer_flags	*flags;
 	bool			print_max;
 	bool			use_max_tr;
+	bool			allocated_snapshot;
 };
 
 
 /* Only current can touch trace_recursion */
-#define trace_recursion_inc() do { (current)->trace_recursion++; } while (0)
-#define trace_recursion_dec() do { (current)->trace_recursion--; } while (0)
 
-/* Ring buffer has the 10 LSB bits to count */
-#define trace_recursion_buffer() ((current)->trace_recursion & 0x3ff)
+/*
+ * For function tracing recursion:
+ *  The order of these bits are important.
+ *
+ *  When function tracing occurs, the following steps are made:
+ *   If arch does not support a ftrace feature:
+ *    call internal function (uses INTERNAL bits) which calls...
+ *   If callback is registered to the "global" list, the list
+ *    function is called and recursion checks the GLOBAL bits.
+ *    then this function calls...
+ *   The function callback, which can use the FTRACE bits to
+ *    check for recursion.
+ *
+ * Now if the arch does not suppport a feature, and it calls
+ * the global list function which calls the ftrace callback
+ * all three of these steps will do a recursion protection.
+ * There's no reason to do one if the previous caller already
+ * did. The recursion that we are protecting against will
+ * go through the same steps again.
+ *
+ * To prevent the multiple recursion checks, if a recursion
+ * bit is set that is higher than the MAX bit of the current
+ * check, then we know that the check was made by the previous
+ * caller, and we can skip the current check.
+ */
+enum {
+	TRACE_BUFFER_BIT,
+	TRACE_BUFFER_NMI_BIT,
+	TRACE_BUFFER_IRQ_BIT,
+	TRACE_BUFFER_SIRQ_BIT,
 
-/* for function tracing recursion */
-#define TRACE_INTERNAL_BIT		(1<<11)
-#define TRACE_GLOBAL_BIT		(1<<12)
-#define TRACE_CONTROL_BIT		(1<<13)
+	/* Start of function recursion bits */
+	TRACE_FTRACE_BIT,
+	TRACE_FTRACE_NMI_BIT,
+	TRACE_FTRACE_IRQ_BIT,
+	TRACE_FTRACE_SIRQ_BIT,
+
+	/* GLOBAL_BITs must be greater than FTRACE_BITs */
+	TRACE_GLOBAL_BIT,
+	TRACE_GLOBAL_NMI_BIT,
+	TRACE_GLOBAL_IRQ_BIT,
+	TRACE_GLOBAL_SIRQ_BIT,
+
+	/* INTERNAL_BITs must be greater than GLOBAL_BITs */
+	TRACE_INTERNAL_BIT,
+	TRACE_INTERNAL_NMI_BIT,
+	TRACE_INTERNAL_IRQ_BIT,
+	TRACE_INTERNAL_SIRQ_BIT,
+
+	TRACE_CONTROL_BIT,
 
 /*
  * Abuse of the trace_recursion.
@@ -309,11 +351,77 @@
  * was called in irq context but we have irq tracing off. Since this
  * can only be modified by current, we can reuse trace_recursion.
  */
-#define TRACE_IRQ_BIT			(1<<13)
+	TRACE_IRQ_BIT,
+};
 
-#define trace_recursion_set(bit)	do { (current)->trace_recursion |= (bit); } while (0)
-#define trace_recursion_clear(bit)	do { (current)->trace_recursion &= ~(bit); } while (0)
-#define trace_recursion_test(bit)	((current)->trace_recursion & (bit))
+#define trace_recursion_set(bit)	do { (current)->trace_recursion |= (1<<(bit)); } while (0)
+#define trace_recursion_clear(bit)	do { (current)->trace_recursion &= ~(1<<(bit)); } while (0)
+#define trace_recursion_test(bit)	((current)->trace_recursion & (1<<(bit)))
+
+#define TRACE_CONTEXT_BITS	4
+
+#define TRACE_FTRACE_START	TRACE_FTRACE_BIT
+#define TRACE_FTRACE_MAX	((1 << (TRACE_FTRACE_START + TRACE_CONTEXT_BITS)) - 1)
+
+#define TRACE_GLOBAL_START	TRACE_GLOBAL_BIT
+#define TRACE_GLOBAL_MAX	((1 << (TRACE_GLOBAL_START + TRACE_CONTEXT_BITS)) - 1)
+
+#define TRACE_LIST_START	TRACE_INTERNAL_BIT
+#define TRACE_LIST_MAX		((1 << (TRACE_LIST_START + TRACE_CONTEXT_BITS)) - 1)
+
+#define TRACE_CONTEXT_MASK	TRACE_LIST_MAX
+
+static __always_inline int trace_get_context_bit(void)
+{
+	int bit;
+
+	if (in_interrupt()) {
+		if (in_nmi())
+			bit = 0;
+
+		else if (in_irq())
+			bit = 1;
+		else
+			bit = 2;
+	} else
+		bit = 3;
+
+	return bit;
+}
+
+static __always_inline int trace_test_and_set_recursion(int start, int max)
+{
+	unsigned int val = current->trace_recursion;
+	int bit;
+
+	/* A previous recursion check was made */
+	if ((val & TRACE_CONTEXT_MASK) > max)
+		return 0;
+
+	bit = trace_get_context_bit() + start;
+	if (unlikely(val & (1 << bit)))
+		return -1;
+
+	val |= 1 << bit;
+	current->trace_recursion = val;
+	barrier();
+
+	return bit;
+}
+
+static __always_inline void trace_clear_recursion(int bit)
+{
+	unsigned int val = current->trace_recursion;
+
+	if (!bit)
+		return;
+
+	bit = 1 << bit;
+	val &= ~bit;
+
+	barrier();
+	current->trace_recursion = val;
+}
 
 #define TRACE_PIPE_ALL_CPU	-1
 
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index 3947835..aa8f5f4 100644
--- a/kernel/trace/trace_clock.c
+++ b/kernel/trace/trace_clock.c
@@ -21,8 +21,6 @@
 #include <linux/ktime.h>
 #include <linux/trace_clock.h>
 
-#include "trace.h"
-
 /*
  * trace_clock_local(): the simplest and least coherent tracing clock.
  *
@@ -44,6 +42,7 @@
 
 	return clock;
 }
+EXPORT_SYMBOL_GPL(trace_clock_local);
 
 /*
  * trace_clock(): 'between' trace clock. Not completely serialized,
@@ -86,7 +85,7 @@
 	local_irq_save(flags);
 
 	this_cpu = raw_smp_processor_id();
-	now = cpu_clock(this_cpu);
+	now = sched_clock_cpu(this_cpu);
 	/*
 	 * If in an NMI context then dont risk lockups and return the
 	 * cpu_clock() time:
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 880073d..57e9b28 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -116,7 +116,6 @@
 	__common_field(unsigned char, flags);
 	__common_field(unsigned char, preempt_count);
 	__common_field(int, pid);
-	__common_field(int, padding);
 
 	return ret;
 }
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 8e3ad80..6011525 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -47,34 +47,6 @@
 	tracing_reset_online_cpus(tr);
 }
 
-static void
-function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip,
-				 struct ftrace_ops *op, struct pt_regs *pt_regs)
-{
-	struct trace_array *tr = func_trace;
-	struct trace_array_cpu *data;
-	unsigned long flags;
-	long disabled;
-	int cpu;
-	int pc;
-
-	if (unlikely(!ftrace_function_enabled))
-		return;
-
-	pc = preempt_count();
-	preempt_disable_notrace();
-	local_save_flags(flags);
-	cpu = raw_smp_processor_id();
-	data = tr->data[cpu];
-	disabled = atomic_inc_return(&data->disabled);
-
-	if (likely(disabled == 1))
-		trace_function(tr, ip, parent_ip, flags, pc);
-
-	atomic_dec(&data->disabled);
-	preempt_enable_notrace();
-}
-
 /* Our option */
 enum {
 	TRACE_FUNC_OPT_STACK	= 0x1,
@@ -85,34 +57,34 @@
 static void
 function_trace_call(unsigned long ip, unsigned long parent_ip,
 		    struct ftrace_ops *op, struct pt_regs *pt_regs)
-
 {
 	struct trace_array *tr = func_trace;
 	struct trace_array_cpu *data;
 	unsigned long flags;
-	long disabled;
+	int bit;
 	int cpu;
 	int pc;
 
 	if (unlikely(!ftrace_function_enabled))
 		return;
 
-	/*
-	 * Need to use raw, since this must be called before the
-	 * recursive protection is performed.
-	 */
-	local_irq_save(flags);
-	cpu = raw_smp_processor_id();
-	data = tr->data[cpu];
-	disabled = atomic_inc_return(&data->disabled);
+	pc = preempt_count();
+	preempt_disable_notrace();
 
-	if (likely(disabled == 1)) {
-		pc = preempt_count();
+	bit = trace_test_and_set_recursion(TRACE_FTRACE_START, TRACE_FTRACE_MAX);
+	if (bit < 0)
+		goto out;
+
+	cpu = smp_processor_id();
+	data = tr->data[cpu];
+	if (!atomic_read(&data->disabled)) {
+		local_save_flags(flags);
 		trace_function(tr, ip, parent_ip, flags, pc);
 	}
+	trace_clear_recursion(bit);
 
-	atomic_dec(&data->disabled);
-	local_irq_restore(flags);
+ out:
+	preempt_enable_notrace();
 }
 
 static void
@@ -185,11 +157,6 @@
 {
 	ftrace_function_enabled = 0;
 
-	if (trace_flags & TRACE_ITER_PREEMPTONLY)
-		trace_ops.func = function_trace_call_preempt_only;
-	else
-		trace_ops.func = function_trace_call;
-
 	if (func_flags.val & TRACE_FUNC_OPT_STACK)
 		register_ftrace_function(&trace_stack_ops);
 	else
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 4edb4b7..39ada66 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -47,6 +47,8 @@
 #define TRACE_GRAPH_PRINT_ABS_TIME	0x20
 #define TRACE_GRAPH_PRINT_IRQS		0x40
 
+static unsigned int max_depth;
+
 static struct tracer_opt trace_opts[] = {
 	/* Display overruns? (for self-debug purpose) */
 	{ TRACER_OPT(funcgraph-overrun, TRACE_GRAPH_PRINT_OVERRUN) },
@@ -189,10 +191,16 @@
 
 	ftrace_pop_return_trace(&trace, &ret, frame_pointer);
 	trace.rettime = trace_clock_local();
-	ftrace_graph_return(&trace);
 	barrier();
 	current->curr_ret_stack--;
 
+	/*
+	 * The trace should run after decrementing the ret counter
+	 * in case an interrupt were to come in. We don't want to
+	 * lose the interrupt if max_depth is set.
+	 */
+	ftrace_graph_return(&trace);
+
 	if (unlikely(!ret)) {
 		ftrace_graph_stop();
 		WARN_ON(1);
@@ -250,8 +258,9 @@
 		return 0;
 
 	/* trace it when it is-nested-in or is a function enabled. */
-	if (!(trace->depth || ftrace_graph_addr(trace->func)) ||
-	      ftrace_graph_ignore_irqs())
+	if ((!(trace->depth || ftrace_graph_addr(trace->func)) ||
+	     ftrace_graph_ignore_irqs()) ||
+	    (max_depth && trace->depth >= max_depth))
 		return 0;
 
 	local_irq_save(flags);
@@ -1457,6 +1466,59 @@
 #endif
 };
 
+
+static ssize_t
+graph_depth_write(struct file *filp, const char __user *ubuf, size_t cnt,
+		  loff_t *ppos)
+{
+	unsigned long val;
+	int ret;
+
+	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+	if (ret)
+		return ret;
+
+	max_depth = val;
+
+	*ppos += cnt;
+
+	return cnt;
+}
+
+static ssize_t
+graph_depth_read(struct file *filp, char __user *ubuf, size_t cnt,
+		 loff_t *ppos)
+{
+	char buf[15]; /* More than enough to hold UINT_MAX + "\n"*/
+	int n;
+
+	n = sprintf(buf, "%d\n", max_depth);
+
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, n);
+}
+
+static const struct file_operations graph_depth_fops = {
+	.open		= tracing_open_generic,
+	.write		= graph_depth_write,
+	.read		= graph_depth_read,
+	.llseek		= generic_file_llseek,
+};
+
+static __init int init_graph_debugfs(void)
+{
+	struct dentry *d_tracer;
+
+	d_tracer = tracing_init_dentry();
+	if (!d_tracer)
+		return 0;
+
+	trace_create_file("max_graph_depth", 0644, d_tracer,
+			  NULL, &graph_depth_fops);
+
+	return 0;
+}
+fs_initcall(init_graph_debugfs);
+
 static __init int init_graph_trace(void)
 {
 	max_bytes_for_cpu = snprintf(NULL, 0, "%d", nr_cpu_ids - 1);
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 9337086..5c7e09d 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -66,7 +66,6 @@
 #define TP_FLAG_TRACE		1
 #define TP_FLAG_PROFILE		2
 #define TP_FLAG_REGISTERED	4
-#define TP_FLAG_UPROBE		8
 
 
 /* data_rloc: data relative location, compatible with u32 */
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 4762316..51c819c 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -415,7 +415,8 @@
 	 * The ftrace infrastructure should provide the recursion
 	 * protection. If not, this will crash the kernel!
 	 */
-	trace_selftest_recursion_cnt++;
+	if (trace_selftest_recursion_cnt++ > 10)
+		return;
 	DYN_FTRACE_TEST_NAME();
 }
 
@@ -452,7 +453,6 @@
 	char *func_name;
 	int len;
 	int ret;
-	int cnt;
 
 	/* The previous test PASSED */
 	pr_cont("PASSED\n");
@@ -510,19 +510,10 @@
 
 	unregister_ftrace_function(&test_recsafe_probe);
 
-	/*
-	 * If arch supports all ftrace features, and no other task
-	 * was on the list, we should be fine.
-	 */
-	if (!ftrace_nr_registered_ops() && !FTRACE_FORCE_LIST_FUNC)
-		cnt = 2; /* Should have recursed */
-	else
-		cnt = 1;
-
 	ret = -1;
-	if (trace_selftest_recursion_cnt != cnt) {
-		pr_cont("*callback not called expected %d times (%d)* ",
-			cnt, trace_selftest_recursion_cnt);
+	if (trace_selftest_recursion_cnt != 2) {
+		pr_cont("*callback not called expected 2 times (%d)* ",
+			trace_selftest_recursion_cnt);
 		goto out;
 	}
 
@@ -568,7 +559,7 @@
 	int ret;
 	int supported = 0;
 
-#ifdef ARCH_SUPPORTS_FTRACE_SAVE_REGS
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 	supported = 1;
 #endif
 
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 7609dd6..5329e13e 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -77,7 +77,7 @@
 	return syscalls_metadata[nr];
 }
 
-enum print_line_t
+static enum print_line_t
 print_syscall_enter(struct trace_iterator *iter, int flags,
 		    struct trace_event *event)
 {
@@ -130,7 +130,7 @@
 	return TRACE_TYPE_HANDLED;
 }
 
-enum print_line_t
+static enum print_line_t
 print_syscall_exit(struct trace_iterator *iter, int flags,
 		   struct trace_event *event)
 {
@@ -270,7 +270,7 @@
 	return ret;
 }
 
-void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id)
+static void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 {
 	struct syscall_trace_enter *entry;
 	struct syscall_metadata *sys_data;
@@ -305,7 +305,7 @@
 		trace_current_buffer_unlock_commit(buffer, event, 0, 0);
 }
 
-void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
+static void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 {
 	struct syscall_trace_exit *entry;
 	struct syscall_metadata *sys_data;
@@ -337,7 +337,7 @@
 		trace_current_buffer_unlock_commit(buffer, event, 0, 0);
 }
 
-int reg_event_syscall_enter(struct ftrace_event_call *call)
+static int reg_event_syscall_enter(struct ftrace_event_call *call)
 {
 	int ret = 0;
 	int num;
@@ -356,7 +356,7 @@
 	return ret;
 }
 
-void unreg_event_syscall_enter(struct ftrace_event_call *call)
+static void unreg_event_syscall_enter(struct ftrace_event_call *call)
 {
 	int num;
 
@@ -371,7 +371,7 @@
 	mutex_unlock(&syscall_trace_lock);
 }
 
-int reg_event_syscall_exit(struct ftrace_event_call *call)
+static int reg_event_syscall_exit(struct ftrace_event_call *call)
 {
 	int ret = 0;
 	int num;
@@ -390,7 +390,7 @@
 	return ret;
 }
 
-void unreg_event_syscall_exit(struct ftrace_event_call *call)
+static void unreg_event_syscall_exit(struct ftrace_event_call *call)
 {
 	int num;
 
@@ -459,7 +459,7 @@
 	return (unsigned long)sys_call_table[nr];
 }
 
-int __init init_ftrace_syscalls(void)
+static int __init init_ftrace_syscalls(void)
 {
 	struct syscall_metadata *meta;
 	unsigned long addr;
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index c86e6d4..8dad2a9 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -28,20 +28,21 @@
 
 #define UPROBE_EVENT_SYSTEM	"uprobes"
 
+struct trace_uprobe_filter {
+	rwlock_t		rwlock;
+	int			nr_systemwide;
+	struct list_head	perf_events;
+};
+
 /*
  * uprobe event core functions
  */
-struct trace_uprobe;
-struct uprobe_trace_consumer {
-	struct uprobe_consumer		cons;
-	struct trace_uprobe		*tu;
-};
-
 struct trace_uprobe {
 	struct list_head		list;
 	struct ftrace_event_class	class;
 	struct ftrace_event_call	call;
-	struct uprobe_trace_consumer	*consumer;
+	struct trace_uprobe_filter	filter;
+	struct uprobe_consumer		consumer;
 	struct inode			*inode;
 	char				*filename;
 	unsigned long			offset;
@@ -64,6 +65,18 @@
 
 static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs);
 
+static inline void init_trace_uprobe_filter(struct trace_uprobe_filter *filter)
+{
+	rwlock_init(&filter->rwlock);
+	filter->nr_systemwide = 0;
+	INIT_LIST_HEAD(&filter->perf_events);
+}
+
+static inline bool uprobe_filter_is_empty(struct trace_uprobe_filter *filter)
+{
+	return !filter->nr_systemwide && list_empty(&filter->perf_events);
+}
+
 /*
  * Allocate new trace_uprobe and initialize it (including uprobes).
  */
@@ -92,6 +105,8 @@
 		goto error;
 
 	INIT_LIST_HEAD(&tu->list);
+	tu->consumer.handler = uprobe_dispatcher;
+	init_trace_uprobe_filter(&tu->filter);
 	return tu;
 
 error:
@@ -253,12 +268,18 @@
 	if (ret)
 		goto fail_address_parse;
 
+	inode = igrab(path.dentry->d_inode);
+	path_put(&path);
+
+	if (!inode || !S_ISREG(inode->i_mode)) {
+		ret = -EINVAL;
+		goto fail_address_parse;
+	}
+
 	ret = kstrtoul(arg, 0, &offset);
 	if (ret)
 		goto fail_address_parse;
 
-	inode = igrab(path.dentry->d_inode);
-
 	argc -= 2;
 	argv += 2;
 
@@ -356,7 +377,7 @@
 	if (inode)
 		iput(inode);
 
-	pr_info("Failed to parse address.\n");
+	pr_info("Failed to parse address or file.\n");
 
 	return ret;
 }
@@ -465,7 +486,7 @@
 };
 
 /* uprobe handler */
-static void uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs)
+static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs)
 {
 	struct uprobe_trace_entry_head *entry;
 	struct ring_buffer_event *event;
@@ -475,8 +496,6 @@
 	unsigned long irq_flags;
 	struct ftrace_event_call *call = &tu->call;
 
-	tu->nhit++;
-
 	local_save_flags(irq_flags);
 	pc = preempt_count();
 
@@ -485,16 +504,18 @@
 	event = trace_current_buffer_lock_reserve(&buffer, call->event.type,
 						  size, irq_flags, pc);
 	if (!event)
-		return;
+		return 0;
 
 	entry = ring_buffer_event_data(event);
-	entry->ip = uprobe_get_swbp_addr(task_pt_regs(current));
+	entry->ip = instruction_pointer(task_pt_regs(current));
 	data = (u8 *)&entry[1];
 	for (i = 0; i < tu->nr_args; i++)
 		call_fetch(&tu->args[i].fetch, regs, data + tu->args[i].offset);
 
 	if (!filter_current_check_discard(buffer, call, entry, event))
 		trace_buffer_unlock_commit(buffer, event, irq_flags, pc);
+
+	return 0;
 }
 
 /* Event entry printers */
@@ -533,42 +554,43 @@
 	return TRACE_TYPE_PARTIAL_LINE;
 }
 
-static int probe_event_enable(struct trace_uprobe *tu, int flag)
+static inline bool is_trace_uprobe_enabled(struct trace_uprobe *tu)
 {
-	struct uprobe_trace_consumer *utc;
+	return tu->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE);
+}
+
+typedef bool (*filter_func_t)(struct uprobe_consumer *self,
+				enum uprobe_filter_ctx ctx,
+				struct mm_struct *mm);
+
+static int
+probe_event_enable(struct trace_uprobe *tu, int flag, filter_func_t filter)
+{
 	int ret = 0;
 
-	if (!tu->inode || tu->consumer)
+	if (is_trace_uprobe_enabled(tu))
 		return -EINTR;
 
-	utc = kzalloc(sizeof(struct uprobe_trace_consumer), GFP_KERNEL);
-	if (!utc)
-		return -EINTR;
-
-	utc->cons.handler = uprobe_dispatcher;
-	utc->cons.filter = NULL;
-	ret = uprobe_register(tu->inode, tu->offset, &utc->cons);
-	if (ret) {
-		kfree(utc);
-		return ret;
-	}
+	WARN_ON(!uprobe_filter_is_empty(&tu->filter));
 
 	tu->flags |= flag;
-	utc->tu = tu;
-	tu->consumer = utc;
+	tu->consumer.filter = filter;
+	ret = uprobe_register(tu->inode, tu->offset, &tu->consumer);
+	if (ret)
+		tu->flags &= ~flag;
 
-	return 0;
+	return ret;
 }
 
 static void probe_event_disable(struct trace_uprobe *tu, int flag)
 {
-	if (!tu->inode || !tu->consumer)
+	if (!is_trace_uprobe_enabled(tu))
 		return;
 
-	uprobe_unregister(tu->inode, tu->offset, &tu->consumer->cons);
+	WARN_ON(!uprobe_filter_is_empty(&tu->filter));
+
+	uprobe_unregister(tu->inode, tu->offset, &tu->consumer);
 	tu->flags &= ~flag;
-	kfree(tu->consumer);
-	tu->consumer = NULL;
 }
 
 static int uprobe_event_define_fields(struct ftrace_event_call *event_call)
@@ -642,8 +664,96 @@
 }
 
 #ifdef CONFIG_PERF_EVENTS
+static bool
+__uprobe_perf_filter(struct trace_uprobe_filter *filter, struct mm_struct *mm)
+{
+	struct perf_event *event;
+
+	if (filter->nr_systemwide)
+		return true;
+
+	list_for_each_entry(event, &filter->perf_events, hw.tp_list) {
+		if (event->hw.tp_target->mm == mm)
+			return true;
+	}
+
+	return false;
+}
+
+static inline bool
+uprobe_filter_event(struct trace_uprobe *tu, struct perf_event *event)
+{
+	return __uprobe_perf_filter(&tu->filter, event->hw.tp_target->mm);
+}
+
+static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event)
+{
+	bool done;
+
+	write_lock(&tu->filter.rwlock);
+	if (event->hw.tp_target) {
+		/*
+		 * event->parent != NULL means copy_process(), we can avoid
+		 * uprobe_apply(). current->mm must be probed and we can rely
+		 * on dup_mmap() which preserves the already installed bp's.
+		 *
+		 * attr.enable_on_exec means that exec/mmap will install the
+		 * breakpoints we need.
+		 */
+		done = tu->filter.nr_systemwide ||
+			event->parent || event->attr.enable_on_exec ||
+			uprobe_filter_event(tu, event);
+		list_add(&event->hw.tp_list, &tu->filter.perf_events);
+	} else {
+		done = tu->filter.nr_systemwide;
+		tu->filter.nr_systemwide++;
+	}
+	write_unlock(&tu->filter.rwlock);
+
+	if (!done)
+		uprobe_apply(tu->inode, tu->offset, &tu->consumer, true);
+
+	return 0;
+}
+
+static int uprobe_perf_close(struct trace_uprobe *tu, struct perf_event *event)
+{
+	bool done;
+
+	write_lock(&tu->filter.rwlock);
+	if (event->hw.tp_target) {
+		list_del(&event->hw.tp_list);
+		done = tu->filter.nr_systemwide ||
+			(event->hw.tp_target->flags & PF_EXITING) ||
+			uprobe_filter_event(tu, event);
+	} else {
+		tu->filter.nr_systemwide--;
+		done = tu->filter.nr_systemwide;
+	}
+	write_unlock(&tu->filter.rwlock);
+
+	if (!done)
+		uprobe_apply(tu->inode, tu->offset, &tu->consumer, false);
+
+	return 0;
+}
+
+static bool uprobe_perf_filter(struct uprobe_consumer *uc,
+				enum uprobe_filter_ctx ctx, struct mm_struct *mm)
+{
+	struct trace_uprobe *tu;
+	int ret;
+
+	tu = container_of(uc, struct trace_uprobe, consumer);
+	read_lock(&tu->filter.rwlock);
+	ret = __uprobe_perf_filter(&tu->filter, mm);
+	read_unlock(&tu->filter.rwlock);
+
+	return ret;
+}
+
 /* uprobe profile handler */
-static void uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs)
+static int uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs)
 {
 	struct ftrace_event_call *call = &tu->call;
 	struct uprobe_trace_entry_head *entry;
@@ -652,11 +762,14 @@
 	int size, __size, i;
 	int rctx;
 
+	if (!uprobe_perf_filter(&tu->consumer, 0, current->mm))
+		return UPROBE_HANDLER_REMOVE;
+
 	__size = sizeof(*entry) + tu->size;
 	size = ALIGN(__size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
 	if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, "profile buffer not large enough"))
-		return;
+		return 0;
 
 	preempt_disable();
 
@@ -664,7 +777,7 @@
 	if (!entry)
 		goto out;
 
-	entry->ip = uprobe_get_swbp_addr(task_pt_regs(current));
+	entry->ip = instruction_pointer(task_pt_regs(current));
 	data = (u8 *)&entry[1];
 	for (i = 0; i < tu->nr_args; i++)
 		call_fetch(&tu->args[i].fetch, regs, data + tu->args[i].offset);
@@ -674,6 +787,7 @@
 
  out:
 	preempt_enable();
+	return 0;
 }
 #endif	/* CONFIG_PERF_EVENTS */
 
@@ -684,7 +798,7 @@
 
 	switch (type) {
 	case TRACE_REG_REGISTER:
-		return probe_event_enable(tu, TP_FLAG_TRACE);
+		return probe_event_enable(tu, TP_FLAG_TRACE, NULL);
 
 	case TRACE_REG_UNREGISTER:
 		probe_event_disable(tu, TP_FLAG_TRACE);
@@ -692,11 +806,18 @@
 
 #ifdef CONFIG_PERF_EVENTS
 	case TRACE_REG_PERF_REGISTER:
-		return probe_event_enable(tu, TP_FLAG_PROFILE);
+		return probe_event_enable(tu, TP_FLAG_PROFILE, uprobe_perf_filter);
 
 	case TRACE_REG_PERF_UNREGISTER:
 		probe_event_disable(tu, TP_FLAG_PROFILE);
 		return 0;
+
+	case TRACE_REG_PERF_OPEN:
+		return uprobe_perf_open(tu, data);
+
+	case TRACE_REG_PERF_CLOSE:
+		return uprobe_perf_close(tu, data);
+
 #endif
 	default:
 		return 0;
@@ -706,22 +827,20 @@
 
 static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs)
 {
-	struct uprobe_trace_consumer *utc;
 	struct trace_uprobe *tu;
+	int ret = 0;
 
-	utc = container_of(con, struct uprobe_trace_consumer, cons);
-	tu = utc->tu;
-	if (!tu || tu->consumer != utc)
-		return 0;
+	tu = container_of(con, struct trace_uprobe, consumer);
+	tu->nhit++;
 
 	if (tu->flags & TP_FLAG_TRACE)
-		uprobe_trace_func(tu, regs);
+		ret |= uprobe_trace_func(tu, regs);
 
 #ifdef CONFIG_PERF_EVENTS
 	if (tu->flags & TP_FLAG_PROFILE)
-		uprobe_perf_func(tu, regs);
+		ret |= uprobe_perf_func(tu, regs);
 #endif
-	return 0;
+	return ret;
 }
 
 static struct trace_event_functions uprobe_funcs = {
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 67604e5..a1714c8 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -605,61 +605,6 @@
 
 	 For more details, see Documentation/lockdep-design.txt.
 
-config PROVE_RCU
-	bool "RCU debugging: prove RCU correctness"
-	depends on PROVE_LOCKING
-	default n
-	help
-	 This feature enables lockdep extensions that check for correct
-	 use of RCU APIs.  This is currently under development.  Say Y
-	 if you want to debug RCU usage or help work on the PROVE_RCU
-	 feature.
-
-	 Say N if you are unsure.
-
-config PROVE_RCU_REPEATEDLY
-	bool "RCU debugging: don't disable PROVE_RCU on first splat"
-	depends on PROVE_RCU
-	default n
-	help
-	 By itself, PROVE_RCU will disable checking upon issuing the
-	 first warning (or "splat").  This feature prevents such
-	 disabling, allowing multiple RCU-lockdep warnings to be printed
-	 on a single reboot.
-
-	 Say Y to allow multiple RCU-lockdep warnings per boot.
-
-	 Say N if you are unsure.
-
-config PROVE_RCU_DELAY
-	bool "RCU debugging: preemptible RCU race provocation"
-	depends on DEBUG_KERNEL && PREEMPT_RCU
-	default n
-	help
-	 There is a class of races that involve an unlikely preemption
-	 of __rcu_read_unlock() just after ->rcu_read_lock_nesting has
-	 been set to INT_MIN.  This feature inserts a delay at that
-	 point to increase the probability of these races.
-
-	 Say Y to increase probability of preemption of __rcu_read_unlock().
-
-	 Say N if you are unsure.
-
-config SPARSE_RCU_POINTER
-	bool "RCU debugging: sparse-based checks for pointer usage"
-	default n
-	help
-	 This feature enables the __rcu sparse annotation for
-	 RCU-protected pointers.  This annotation will cause sparse
-	 to flag any non-RCU used of annotated pointers.  This can be
-	 helpful when debugging RCU usage.  Please note that this feature
-	 is not intended to enforce code cleanliness; it is instead merely
-	 a debugging aid.
-
-	 Say Y to make sparse flag questionable use of RCU-protected pointers
-
-	 Say N if you are unsure.
-
 config LOCKDEP
 	bool
 	depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
@@ -937,6 +882,63 @@
 	  BOOT_PRINTK_DELAY also may cause LOCKUP_DETECTOR to detect
 	  what it believes to be lockup conditions.
 
+menu "RCU Debugging"
+
+config PROVE_RCU
+	bool "RCU debugging: prove RCU correctness"
+	depends on PROVE_LOCKING
+	default n
+	help
+	 This feature enables lockdep extensions that check for correct
+	 use of RCU APIs.  This is currently under development.  Say Y
+	 if you want to debug RCU usage or help work on the PROVE_RCU
+	 feature.
+
+	 Say N if you are unsure.
+
+config PROVE_RCU_REPEATEDLY
+	bool "RCU debugging: don't disable PROVE_RCU on first splat"
+	depends on PROVE_RCU
+	default n
+	help
+	 By itself, PROVE_RCU will disable checking upon issuing the
+	 first warning (or "splat").  This feature prevents such
+	 disabling, allowing multiple RCU-lockdep warnings to be printed
+	 on a single reboot.
+
+	 Say Y to allow multiple RCU-lockdep warnings per boot.
+
+	 Say N if you are unsure.
+
+config PROVE_RCU_DELAY
+	bool "RCU debugging: preemptible RCU race provocation"
+	depends on DEBUG_KERNEL && PREEMPT_RCU
+	default n
+	help
+	 There is a class of races that involve an unlikely preemption
+	 of __rcu_read_unlock() just after ->rcu_read_lock_nesting has
+	 been set to INT_MIN.  This feature inserts a delay at that
+	 point to increase the probability of these races.
+
+	 Say Y to increase probability of preemption of __rcu_read_unlock().
+
+	 Say N if you are unsure.
+
+config SPARSE_RCU_POINTER
+	bool "RCU debugging: sparse-based checks for pointer usage"
+	default n
+	help
+	 This feature enables the __rcu sparse annotation for
+	 RCU-protected pointers.  This annotation will cause sparse
+	 to flag any non-RCU used of annotated pointers.  This can be
+	 helpful when debugging RCU usage.  Please note that this feature
+	 is not intended to enforce code cleanliness; it is instead merely
+	 a debugging aid.
+
+	 Say Y to make sparse flag questionable use of RCU-protected pointers
+
+	 Say N if you are unsure.
+
 config RCU_TORTURE_TEST
 	tristate "torture tests for RCU"
 	depends on DEBUG_KERNEL
@@ -970,7 +972,7 @@
 
 config RCU_CPU_STALL_TIMEOUT
 	int "RCU CPU stall timeout in seconds"
-	depends on TREE_RCU || TREE_PREEMPT_RCU
+	depends on RCU_STALL_COMMON
 	range 3 300
 	default 21
 	help
@@ -1008,6 +1010,7 @@
 config RCU_TRACE
 	bool "Enable tracing for RCU"
 	depends on DEBUG_KERNEL
+	select TRACE_CLOCK
 	help
 	  This option provides tracing in RCU which presents stats
 	  in debugfs for debugging RCU implementation.
@@ -1015,6 +1018,8 @@
 	  Say Y here if you want to enable RCU tracing
 	  Say N if you are unsure.
 
+endmenu # "RCU Debugging"
+
 config KPROBES_SANITY_TEST
 	bool "Kprobes sanity tests"
 	depends on DEBUG_KERNEL
diff --git a/lib/digsig.c b/lib/digsig.c
index 8c0e629..dc2be7e 100644
--- a/lib/digsig.c
+++ b/lib/digsig.c
@@ -162,6 +162,8 @@
 	memset(out1, 0, head);
 	memcpy(out1 + head, p, l);
 
+	kfree(p);
+
 	err = pkcs_1_v1_5_decode_emsa(out1, len, mblen, out2, &len);
 	if (err)
 		goto err;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 6001ee6..b5783d8 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1257,6 +1257,10 @@
 	if (flags & FOLL_WRITE && !pmd_write(*pmd))
 		goto out;
 
+	/* Avoid dumping huge zero page */
+	if ((flags & FOLL_DUMP) && is_huge_zero_pmd(*pmd))
+		return ERR_PTR(-EFAULT);
+
 	page = pmd_page(*pmd);
 	VM_BUG_ON(!PageHead(page));
 	if (flags & FOLL_TOUCH) {
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 4f3ea0b..546db81 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3033,6 +3033,7 @@
 		if (!huge_pte_none(huge_ptep_get(ptep))) {
 			pte = huge_ptep_get_and_clear(mm, address, ptep);
 			pte = pte_mkhuge(pte_modify(pte, newprot));
+			pte = arch_make_huge_pte(pte, vma, NULL, 0);
 			set_huge_pte_at(mm, address, ptep, pte);
 			pages++;
 		}
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 09255ec..fbb60b1 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3030,7 +3030,9 @@
 	if (memcg) {
 		s->memcg_params->memcg = memcg;
 		s->memcg_params->root_cache = root_cache;
-	}
+	} else
+		s->memcg_params->is_root_cache = true;
+
 	return 0;
 }
 
diff --git a/mm/migrate.c b/mm/migrate.c
index c387786..2fd8b4af 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -160,8 +160,10 @@
 	if (is_write_migration_entry(entry))
 		pte = pte_mkwrite(pte);
 #ifdef CONFIG_HUGETLB_PAGE
-	if (PageHuge(new))
+	if (PageHuge(new)) {
 		pte = pte_mkhuge(pte);
+		pte = arch_make_huge_pte(pte, vma, new, 0);
+	}
 #endif
 	flush_cache_page(vma, addr, pte_pfn(pte));
 	set_pte_at(mm, addr, ptep, pte);
diff --git a/mm/mlock.c b/mm/mlock.c
index f0b9ce5..c9bd528 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -517,11 +517,11 @@
 static int do_mlockall(int flags)
 {
 	struct vm_area_struct * vma, * prev = NULL;
-	unsigned int def_flags = 0;
 
 	if (flags & MCL_FUTURE)
-		def_flags = VM_LOCKED;
-	current->mm->def_flags = def_flags;
+		current->mm->def_flags |= VM_LOCKED;
+	else
+		current->mm->def_flags &= ~VM_LOCKED;
 	if (flags == MCL_FUTURE)
 		goto out;
 
diff --git a/mm/mmap.c b/mm/mmap.c
index 5dee4a0..09da0b2 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2944,7 +2944,7 @@
  * vma in this mm is backed by the same anon_vma or address_space.
  *
  * We can take all the locks in random order because the VM code
- * taking i_mmap_mutex or anon_vma->mutex outside the mmap_sem never
+ * taking i_mmap_mutex or anon_vma->rwsem outside the mmap_sem never
  * takes more than one of them in a row. Secondly we're protected
  * against a concurrent mm_take_all_locks() by the mm_all_locks_mutex.
  *
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 42d18e4..d1107ad 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -774,6 +774,10 @@
 	set_pageblock_migratetype(page, MIGRATE_CMA);
 	__free_pages(page, pageblock_order);
 	totalram_pages += pageblock_nr_pages;
+#ifdef CONFIG_HIGHMEM
+	if (PageHighMem(page))
+		totalhigh_pages += pageblock_nr_pages;
+#endif
 }
 #endif
 
@@ -4417,10 +4421,11 @@
  * round what is now in bits to nearest long in bits, then return it in
  * bytes.
  */
-static unsigned long __init usemap_size(unsigned long zonesize)
+static unsigned long __init usemap_size(unsigned long zone_start_pfn, unsigned long zonesize)
 {
 	unsigned long usemapsize;
 
+	zonesize += zone_start_pfn & (pageblock_nr_pages-1);
 	usemapsize = roundup(zonesize, pageblock_nr_pages);
 	usemapsize = usemapsize >> pageblock_order;
 	usemapsize *= NR_PAGEBLOCK_BITS;
@@ -4430,17 +4435,19 @@
 }
 
 static void __init setup_usemap(struct pglist_data *pgdat,
-				struct zone *zone, unsigned long zonesize)
+				struct zone *zone,
+				unsigned long zone_start_pfn,
+				unsigned long zonesize)
 {
-	unsigned long usemapsize = usemap_size(zonesize);
+	unsigned long usemapsize = usemap_size(zone_start_pfn, zonesize);
 	zone->pageblock_flags = NULL;
 	if (usemapsize)
 		zone->pageblock_flags = alloc_bootmem_node_nopanic(pgdat,
 								   usemapsize);
 }
 #else
-static inline void setup_usemap(struct pglist_data *pgdat,
-				struct zone *zone, unsigned long zonesize) {}
+static inline void setup_usemap(struct pglist_data *pgdat, struct zone *zone,
+				unsigned long zone_start_pfn, unsigned long zonesize) {}
 #endif /* CONFIG_SPARSEMEM */
 
 #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
@@ -4591,7 +4598,7 @@
 			continue;
 
 		set_pageblock_order();
-		setup_usemap(pgdat, zone, size);
+		setup_usemap(pgdat, zone, zone_start_pfn, size);
 		ret = init_currently_empty_zone(zone, zone_start_pfn,
 						size, MEMMAP_EARLY);
 		BUG_ON(ret);
diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index 8e1d89d..5539215 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -440,7 +440,7 @@
 	/* this is an hash collision with the temporary selected node. Choose
 	 * the one with the lowest address
 	 */
-	if ((tmp_max == max) &&
+	if ((tmp_max == max) && max_orig_node &&
 	    (batadv_compare_eth(candidate->orig, max_orig_node->orig) > 0))
 		goto out;
 
@@ -738,6 +738,7 @@
 	struct arphdr *arphdr;
 	struct ethhdr *ethhdr;
 	__be32 ip_src, ip_dst;
+	uint8_t *hw_src, *hw_dst;
 	uint16_t type = 0;
 
 	/* pull the ethernet header */
@@ -777,9 +778,23 @@
 	ip_src = batadv_arp_ip_src(skb, hdr_size);
 	ip_dst = batadv_arp_ip_dst(skb, hdr_size);
 	if (ipv4_is_loopback(ip_src) || ipv4_is_multicast(ip_src) ||
-	    ipv4_is_loopback(ip_dst) || ipv4_is_multicast(ip_dst))
+	    ipv4_is_loopback(ip_dst) || ipv4_is_multicast(ip_dst) ||
+	    ipv4_is_zeronet(ip_src) || ipv4_is_lbcast(ip_src) ||
+	    ipv4_is_zeronet(ip_dst) || ipv4_is_lbcast(ip_dst))
 		goto out;
 
+	hw_src = batadv_arp_hw_src(skb, hdr_size);
+	if (is_zero_ether_addr(hw_src) || is_multicast_ether_addr(hw_src))
+		goto out;
+
+	/* we don't care about the destination MAC address in ARP requests */
+	if (arphdr->ar_op != htons(ARPOP_REQUEST)) {
+		hw_dst = batadv_arp_hw_dst(skb, hdr_size);
+		if (is_zero_ether_addr(hw_dst) ||
+		    is_multicast_ether_addr(hw_dst))
+			goto out;
+	}
+
 	type = ntohs(arphdr->ar_op);
 out:
 	return type;
@@ -1012,6 +1027,8 @@
 	 */
 	ret = !batadv_is_my_client(bat_priv, hw_dst);
 out:
+	if (ret)
+		kfree_skb(skb);
 	/* if ret == false -> packet has to be delivered to the interface */
 	return ret;
 }
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 25bfce0..4925a02 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -249,12 +249,12 @@
 	__u8 reason = hci_proto_disconn_ind(conn);
 
 	switch (conn->type) {
-	case ACL_LINK:
-		hci_acl_disconn(conn, reason);
-		break;
 	case AMP_LINK:
 		hci_amp_disconn(conn, reason);
 		break;
+	default:
+		hci_acl_disconn(conn, reason);
+		break;
 	}
 }
 
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 596660d..0f78e34 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -2810,14 +2810,6 @@
 	if (conn) {
 		hci_conn_enter_active_mode(conn, BT_POWER_FORCE_ACTIVE_OFF);
 
-		hci_dev_lock(hdev);
-		if (test_bit(HCI_MGMT, &hdev->dev_flags) &&
-		    !test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags))
-			mgmt_device_connected(hdev, &conn->dst, conn->type,
-					      conn->dst_type, 0, NULL, 0,
-					      conn->dev_class);
-		hci_dev_unlock(hdev);
-
 		/* Send to upper protocol */
 		l2cap_recv_acldata(conn, skb, flags);
 		return;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 705078a..81b4448 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -2688,7 +2688,7 @@
 	if (ev->opcode != HCI_OP_NOP)
 		del_timer(&hdev->cmd_timer);
 
-	if (ev->ncmd) {
+	if (ev->ncmd && !test_bit(HCI_RESET, &hdev->flags)) {
 		atomic_set(&hdev->cmd_cnt, 1);
 		if (!skb_queue_empty(&hdev->cmd_q))
 			queue_work(hdev->workqueue, &hdev->cmd_work);
diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c
index b2bcbe2..a7352ff 100644
--- a/net/bluetooth/hidp/core.c
+++ b/net/bluetooth/hidp/core.c
@@ -931,7 +931,7 @@
 	hid->version = req->version;
 	hid->country = req->country;
 
-	strncpy(hid->name, req->name, 128);
+	strncpy(hid->name, req->name, sizeof(req->name) - 1);
 
 	snprintf(hid->phys, sizeof(hid->phys), "%pMR",
 		 &bt_sk(session->ctrl_sock->sk)->src);
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 2c78208..22e6583 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -3727,6 +3727,17 @@
 static int l2cap_connect_req(struct l2cap_conn *conn,
 			     struct l2cap_cmd_hdr *cmd, u8 *data)
 {
+	struct hci_dev *hdev = conn->hcon->hdev;
+	struct hci_conn *hcon = conn->hcon;
+
+	hci_dev_lock(hdev);
+	if (test_bit(HCI_MGMT, &hdev->dev_flags) &&
+	    !test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &hcon->flags))
+		mgmt_device_connected(hdev, &hcon->dst, hcon->type,
+				      hcon->dst_type, 0, NULL, 0,
+				      hcon->dev_class);
+	hci_dev_unlock(hdev);
+
 	l2cap_connect(conn, cmd, data, L2CAP_CONN_RSP, 0);
 	return 0;
 }
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 531a93d..57f250c 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -352,7 +352,7 @@
 
 	case BT_CONNECTED:
 	case BT_CONFIG:
-		if (sco_pi(sk)->conn) {
+		if (sco_pi(sk)->conn->hcon) {
 			sk->sk_state = BT_DISCONN;
 			sco_sock_set_timer(sk, SCO_DISCONN_TIMEOUT);
 			hci_conn_put(sco_pi(sk)->conn->hcon);
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 68a9587..5abefb1 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -859,6 +859,19 @@
 
 	skb_pull(skb, sizeof(code));
 
+	/*
+	 * The SMP context must be initialized for all other PDUs except
+	 * pairing and security requests. If we get any other PDU when
+	 * not initialized simply disconnect (done if this function
+	 * returns an error).
+	 */
+	if (code != SMP_CMD_PAIRING_REQ && code != SMP_CMD_SECURITY_REQ &&
+	    !conn->smp_chan) {
+		BT_ERR("Unexpected SMP command 0x%02x. Disconnecting.", code);
+		kfree_skb(skb);
+		return -ENOTSUPP;
+	}
+
 	switch (code) {
 	case SMP_CMD_PAIRING_REQ:
 		reason = smp_cmd_pairing_req(conn, skb);
diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c
index 7f884e3..8660ea3 100644
--- a/net/bridge/br_stp_bpdu.c
+++ b/net/bridge/br_stp_bpdu.c
@@ -16,6 +16,7 @@
 #include <linux/etherdevice.h>
 #include <linux/llc.h>
 #include <linux/slab.h>
+#include <linux/pkt_sched.h>
 #include <net/net_namespace.h>
 #include <net/llc.h>
 #include <net/llc_pdu.h>
@@ -40,6 +41,7 @@
 
 	skb->dev = p->dev;
 	skb->protocol = htons(ETH_P_802_2);
+	skb->priority = TC_PRIO_CONTROL;
 
 	skb_reserve(skb, LLC_RESERVE);
 	memcpy(__skb_put(skb, length), data, length);
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 0337e2b..368f9c3 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -187,7 +187,7 @@
 		skb_queue_walk(queue, skb) {
 			*peeked = skb->peeked;
 			if (flags & MSG_PEEK) {
-				if (*off >= skb->len) {
+				if (*off >= skb->len && skb->len) {
 					*off -= skb->len;
 					continue;
 				}
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index b29dacf..e6e1cbe 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -1781,10 +1781,13 @@
 			return -EFAULT;
 		i += len;
 		mutex_lock(&pktgen_thread_lock);
-		pktgen_add_device(t, f);
+		ret = pktgen_add_device(t, f);
 		mutex_unlock(&pktgen_thread_lock);
-		ret = count;
-		sprintf(pg_result, "OK: add_device=%s", f);
+		if (!ret) {
+			ret = count;
+			sprintf(pg_result, "OK: add_device=%s", f);
+		} else
+			sprintf(pg_result, "ERROR: can not add device %s", f);
 		goto out;
 	}
 
diff --git a/net/core/request_sock.c b/net/core/request_sock.c
index c31d9e8..4425148 100644
--- a/net/core/request_sock.c
+++ b/net/core/request_sock.c
@@ -186,8 +186,6 @@
 	struct fastopen_queue *fastopenq =
 	    inet_csk(lsk)->icsk_accept_queue.fastopenq;
 
-	BUG_ON(!spin_is_locked(&sk->sk_lock.slock) && !sock_owned_by_user(sk));
-
 	tcp_sk(sk)->fastopen_rsk = NULL;
 	spin_lock_bh(&fastopenq->lock);
 	fastopenq->qlen--;
diff --git a/net/core/scm.c b/net/core/scm.c
index 57fb1ee..905dcc6 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -35,6 +35,7 @@
 #include <net/sock.h>
 #include <net/compat.h>
 #include <net/scm.h>
+#include <net/cls_cgroup.h>
 
 
 /*
@@ -302,8 +303,10 @@
 		}
 		/* Bump the usage count and install the file. */
 		sock = sock_from_file(fp[i], &err);
-		if (sock)
+		if (sock) {
 			sock_update_netprioidx(sock->sk, current);
+			sock_update_classid(sock->sk, current);
+		}
 		fd_install(new_fd, get_file(fp[i]));
 	}
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 3ab989b..32443eb 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -683,7 +683,7 @@
 	new->network_header	= old->network_header;
 	new->mac_header		= old->mac_header;
 	new->inner_transport_header = old->inner_transport_header;
-	new->inner_network_header = old->inner_transport_header;
+	new->inner_network_header = old->inner_network_header;
 	skb_dst_copy(new, old);
 	new->rxhash		= old->rxhash;
 	new->ooo_okay		= old->ooo_okay;
@@ -1649,7 +1649,7 @@
 
 static struct page *linear_to_page(struct page *page, unsigned int *len,
 				   unsigned int *offset,
-				   struct sk_buff *skb, struct sock *sk)
+				   struct sock *sk)
 {
 	struct page_frag *pfrag = sk_page_frag(sk);
 
@@ -1682,14 +1682,14 @@
 static bool spd_fill_page(struct splice_pipe_desc *spd,
 			  struct pipe_inode_info *pipe, struct page *page,
 			  unsigned int *len, unsigned int offset,
-			  struct sk_buff *skb, bool linear,
+			  bool linear,
 			  struct sock *sk)
 {
 	if (unlikely(spd->nr_pages == MAX_SKB_FRAGS))
 		return true;
 
 	if (linear) {
-		page = linear_to_page(page, len, &offset, skb, sk);
+		page = linear_to_page(page, len, &offset, sk);
 		if (!page)
 			return true;
 	}
@@ -1706,23 +1706,9 @@
 	return false;
 }
 
-static inline void __segment_seek(struct page **page, unsigned int *poff,
-				  unsigned int *plen, unsigned int off)
-{
-	unsigned long n;
-
-	*poff += off;
-	n = *poff / PAGE_SIZE;
-	if (n)
-		*page = nth_page(*page, n);
-
-	*poff = *poff % PAGE_SIZE;
-	*plen -= off;
-}
-
 static bool __splice_segment(struct page *page, unsigned int poff,
 			     unsigned int plen, unsigned int *off,
-			     unsigned int *len, struct sk_buff *skb,
+			     unsigned int *len,
 			     struct splice_pipe_desc *spd, bool linear,
 			     struct sock *sk,
 			     struct pipe_inode_info *pipe)
@@ -1737,23 +1723,19 @@
 	}
 
 	/* ignore any bits we already processed */
-	if (*off) {
-		__segment_seek(&page, &poff, &plen, *off);
-		*off = 0;
-	}
+	poff += *off;
+	plen -= *off;
+	*off = 0;
 
 	do {
 		unsigned int flen = min(*len, plen);
 
-		/* the linear region may spread across several pages  */
-		flen = min_t(unsigned int, flen, PAGE_SIZE - poff);
-
-		if (spd_fill_page(spd, pipe, page, &flen, poff, skb, linear, sk))
+		if (spd_fill_page(spd, pipe, page, &flen, poff,
+				  linear, sk))
 			return true;
-
-		__segment_seek(&page, &poff, &plen, flen);
+		poff += flen;
+		plen -= flen;
 		*len -= flen;
-
 	} while (*len && plen);
 
 	return false;
@@ -1777,7 +1759,7 @@
 	if (__splice_segment(virt_to_page(skb->data),
 			     (unsigned long) skb->data & (PAGE_SIZE - 1),
 			     skb_headlen(skb),
-			     offset, len, skb, spd,
+			     offset, len, spd,
 			     skb_head_is_locked(skb),
 			     sk, pipe))
 		return true;
@@ -1790,7 +1772,7 @@
 
 		if (__splice_segment(skb_frag_page(f),
 				     f->page_offset, skb_frag_size(f),
-				     offset, len, skb, spd, false, sk, pipe))
+				     offset, len, spd, false, sk, pipe))
 			return true;
 	}
 
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index a0d8392..a69b4e4 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -269,7 +269,11 @@
 	skb->network_header += ah_hlen;
 	memcpy(skb_network_header(skb), work_iph, ihl);
 	__skb_pull(skb, ah_hlen + ihl);
-	skb_set_transport_header(skb, -ihl);
+
+	if (x->props.mode == XFRM_MODE_TUNNEL)
+		skb_reset_transport_header(skb);
+	else
+		skb_set_transport_header(skb, -ihl);
 out:
 	kfree(AH_SKB_CB(skb)->tmp);
 	xfrm_input_resume(skb, err);
@@ -381,7 +385,10 @@
 	skb->network_header += ah_hlen;
 	memcpy(skb_network_header(skb), work_iph, ihl);
 	__skb_pull(skb, ah_hlen + ihl);
-	skb_set_transport_header(skb, -ihl);
+	if (x->props.mode == XFRM_MODE_TUNNEL)
+		skb_reset_transport_header(skb);
+	else
+		skb_set_transport_header(skb, -ihl);
 
 	err = nexthdr;
 
@@ -413,9 +420,12 @@
 	if (!x)
 		return;
 
-	if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
+	if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) {
+		atomic_inc(&flow_cache_genid);
+		rt_genid_bump(net);
+
 		ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_AH, 0);
-	else
+	} else
 		ipv4_redirect(skb, net, 0, 0, IPPROTO_AH, 0);
 	xfrm_state_put(x);
 }
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 9547a273..ded146b 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -928,24 +928,25 @@
 static int arp_rcv(struct sk_buff *skb, struct net_device *dev,
 		   struct packet_type *pt, struct net_device *orig_dev)
 {
-	struct arphdr *arp;
+	const struct arphdr *arp;
+
+	if (dev->flags & IFF_NOARP ||
+	    skb->pkt_type == PACKET_OTHERHOST ||
+	    skb->pkt_type == PACKET_LOOPBACK)
+		goto freeskb;
+
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (!skb)
+		goto out_of_mem;
 
 	/* ARP header, plus 2 device addresses, plus 2 IP addresses.  */
 	if (!pskb_may_pull(skb, arp_hdr_len(dev)))
 		goto freeskb;
 
 	arp = arp_hdr(skb);
-	if (arp->ar_hln != dev->addr_len ||
-	    dev->flags & IFF_NOARP ||
-	    skb->pkt_type == PACKET_OTHERHOST ||
-	    skb->pkt_type == PACKET_LOOPBACK ||
-	    arp->ar_pln != 4)
+	if (arp->ar_hln != dev->addr_len || arp->ar_pln != 4)
 		goto freeskb;
 
-	skb = skb_share_check(skb, GFP_ATOMIC);
-	if (skb == NULL)
-		goto out_of_mem;
-
 	memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb));
 
 	return NF_HOOK(NFPROTO_ARP, NF_ARP_IN, skb, dev, NULL, arp_process);
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index 424fafb..b28e863 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -85,3 +85,28 @@
 	return err;
 }
 EXPORT_SYMBOL(ip4_datagram_connect);
+
+void ip4_datagram_release_cb(struct sock *sk)
+{
+	const struct inet_sock *inet = inet_sk(sk);
+	const struct ip_options_rcu *inet_opt;
+	__be32 daddr = inet->inet_daddr;
+	struct flowi4 fl4;
+	struct rtable *rt;
+
+	if (! __sk_dst_get(sk) || __sk_dst_check(sk, 0))
+		return;
+
+	rcu_read_lock();
+	inet_opt = rcu_dereference(inet->inet_opt);
+	if (inet_opt && inet_opt->opt.srr)
+		daddr = inet_opt->opt.faddr;
+	rt = ip_route_output_ports(sock_net(sk), &fl4, sk, daddr,
+				   inet->inet_saddr, inet->inet_dport,
+				   inet->inet_sport, sk->sk_protocol,
+				   RT_CONN_FLAGS(sk), sk->sk_bound_dev_if);
+	if (!IS_ERR(rt))
+		__sk_dst_set(sk, &rt->dst);
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(ip4_datagram_release_cb);
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index b61e9de..3b4f0cd 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -346,7 +346,10 @@
 
 	pskb_trim(skb, skb->len - alen - padlen - 2);
 	__skb_pull(skb, hlen);
-	skb_set_transport_header(skb, -ihl);
+	if (x->props.mode == XFRM_MODE_TUNNEL)
+		skb_reset_transport_header(skb);
+	else
+		skb_set_transport_header(skb, -ihl);
 
 	err = nexthdr[1];
 
@@ -499,9 +502,12 @@
 	if (!x)
 		return;
 
-	if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
+	if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) {
+		atomic_inc(&flow_cache_genid);
+		rt_genid_bump(net);
+
 		ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ESP, 0);
-	else
+	} else
 		ipv4_redirect(skb, net, 0, 0, IPPROTO_ESP, 0);
 	xfrm_state_put(x);
 }
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 303012a..e81b1ca 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -963,8 +963,12 @@
 			ptr--;
 		}
 		if (tunnel->parms.o_flags&GRE_CSUM) {
+			int offset = skb_transport_offset(skb);
+
 			*ptr = 0;
-			*(__sum16 *)ptr = ip_compute_csum((void *)(iph+1), skb->len - sizeof(struct iphdr));
+			*(__sum16 *)ptr = csum_fold(skb_checksum(skb, offset,
+								 skb->len - offset,
+								 0));
 		}
 	}
 
diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c
index d3ab47e..9a46dae 100644
--- a/net/ipv4/ipcomp.c
+++ b/net/ipv4/ipcomp.c
@@ -47,9 +47,12 @@
 	if (!x)
 		return;
 
-	if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
+	if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) {
+		atomic_inc(&flow_cache_genid);
+		rt_genid_bump(net);
+
 		ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_COMP, 0);
-	else
+	} else
 		ipv4_redirect(skb, net, 0, 0, IPPROTO_COMP, 0);
 	xfrm_state_put(x);
 }
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 8f3d054..6f9c072 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -738,6 +738,7 @@
 	.recvmsg =	ping_recvmsg,
 	.bind =		ping_bind,
 	.backlog_rcv =	ping_queue_rcv_skb,
+	.release_cb =	ip4_datagram_release_cb,
 	.hash =		ping_v4_hash,
 	.unhash =	ping_v4_unhash,
 	.get_port =	ping_v4_get_port,
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 73d1e4d..6f08991 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -894,6 +894,7 @@
 	.recvmsg	   = raw_recvmsg,
 	.bind		   = raw_bind,
 	.backlog_rcv	   = raw_rcv_skb,
+	.release_cb	   = ip4_datagram_release_cb,
 	.hash		   = raw_hash_sk,
 	.unhash		   = raw_unhash_sk,
 	.obj_size	   = sizeof(struct raw_sock),
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 844a9ef..a0fcc47 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -912,6 +912,9 @@
 	struct dst_entry *dst = &rt->dst;
 	struct fib_result res;
 
+	if (dst_metric_locked(dst, RTAX_MTU))
+		return;
+
 	if (dst->dev->mtu < mtu)
 		return;
 
@@ -962,7 +965,7 @@
 }
 EXPORT_SYMBOL_GPL(ipv4_update_pmtu);
 
-void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
+static void __ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 {
 	const struct iphdr *iph = (const struct iphdr *) skb->data;
 	struct flowi4 fl4;
@@ -975,6 +978,53 @@
 		ip_rt_put(rt);
 	}
 }
+
+void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
+{
+	const struct iphdr *iph = (const struct iphdr *) skb->data;
+	struct flowi4 fl4;
+	struct rtable *rt;
+	struct dst_entry *dst;
+	bool new = false;
+
+	bh_lock_sock(sk);
+	rt = (struct rtable *) __sk_dst_get(sk);
+
+	if (sock_owned_by_user(sk) || !rt) {
+		__ipv4_sk_update_pmtu(skb, sk, mtu);
+		goto out;
+	}
+
+	__build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0);
+
+	if (!__sk_dst_check(sk, 0)) {
+		rt = ip_route_output_flow(sock_net(sk), &fl4, sk);
+		if (IS_ERR(rt))
+			goto out;
+
+		new = true;
+	}
+
+	__ip_rt_update_pmtu((struct rtable *) rt->dst.path, &fl4, mtu);
+
+	dst = dst_check(&rt->dst, 0);
+	if (!dst) {
+		if (new)
+			dst_release(&rt->dst);
+
+		rt = ip_route_output_flow(sock_net(sk), &fl4, sk);
+		if (IS_ERR(rt))
+			goto out;
+
+		new = true;
+	}
+
+	if (new)
+		__sk_dst_set(sk, &rt->dst);
+
+out:
+	bh_unlock_sock(sk);
+}
 EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu);
 
 void ipv4_redirect(struct sk_buff *skb, struct net *net,
@@ -1120,7 +1170,7 @@
 	if (!mtu || time_after_eq(jiffies, rt->dst.expires))
 		mtu = dst_metric_raw(dst, RTAX_MTU);
 
-	if (mtu && rt_is_output_route(rt))
+	if (mtu)
 		return mtu;
 
 	mtu = dst->dev->mtu;
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 291f2ed..cdf2e70 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -310,6 +310,12 @@
 {
 	int cnt; /* increase in packets */
 	unsigned int delta = 0;
+	u32 snd_cwnd = tp->snd_cwnd;
+
+	if (unlikely(!snd_cwnd)) {
+		pr_err_once("snd_cwnd is nul, please report this bug.\n");
+		snd_cwnd = 1U;
+	}
 
 	/* RFC3465: ABC Slow start
 	 * Increase only after a full MSS of bytes is acked
@@ -324,7 +330,7 @@
 	if (sysctl_tcp_max_ssthresh > 0 && tp->snd_cwnd > sysctl_tcp_max_ssthresh)
 		cnt = sysctl_tcp_max_ssthresh >> 1;	/* limited slow start */
 	else
-		cnt = tp->snd_cwnd;			/* exponential increase */
+		cnt = snd_cwnd;				/* exponential increase */
 
 	/* RFC3465: ABC
 	 * We MAY increase by 2 if discovered delayed ack
@@ -334,11 +340,11 @@
 	tp->bytes_acked = 0;
 
 	tp->snd_cwnd_cnt += cnt;
-	while (tp->snd_cwnd_cnt >= tp->snd_cwnd) {
-		tp->snd_cwnd_cnt -= tp->snd_cwnd;
+	while (tp->snd_cwnd_cnt >= snd_cwnd) {
+		tp->snd_cwnd_cnt -= snd_cwnd;
 		delta++;
 	}
-	tp->snd_cwnd = min(tp->snd_cwnd + delta, tp->snd_cwnd_clamp);
+	tp->snd_cwnd = min(snd_cwnd + delta, tp->snd_cwnd_clamp);
 }
 EXPORT_SYMBOL_GPL(tcp_slow_start);
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 18f97ca..ad70a96 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3504,6 +3504,11 @@
 		}
 	} else {
 		if (!(flag & FLAG_DATA_ACKED) && (tp->frto_counter == 1)) {
+			if (!tcp_packets_in_flight(tp)) {
+				tcp_enter_frto_loss(sk, 2, flag);
+				return true;
+			}
+
 			/* Prevent sending of new data. */
 			tp->snd_cwnd = min(tp->snd_cwnd,
 					   tcp_packets_in_flight(tp));
@@ -5649,8 +5654,7 @@
 	 * the remote receives only the retransmitted (regular) SYNs: either
 	 * the original SYN-data or the corresponding SYN-ACK is lost.
 	 */
-	syn_drop = (cookie->len <= 0 && data &&
-		    inet_csk(sk)->icsk_retransmits);
+	syn_drop = (cookie->len <= 0 && data && tp->total_retrans);
 
 	tcp_fastopen_cache_set(sk, mss, cookie, syn_drop);
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 54139fa..eadb693 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -369,11 +369,10 @@
 	 * We do take care of PMTU discovery (RFC1191) special case :
 	 * we can receive locally generated ICMP messages while socket is held.
 	 */
-	if (sock_owned_by_user(sk) &&
-	    type != ICMP_DEST_UNREACH &&
-	    code != ICMP_FRAG_NEEDED)
-		NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS);
-
+	if (sock_owned_by_user(sk)) {
+		if (!(type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED))
+			NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS);
+	}
 	if (sk->sk_state == TCP_CLOSE)
 		goto out;
 
@@ -497,6 +496,7 @@
 		 * errors returned from accept().
 		 */
 		inet_csk_reqsk_queue_drop(sk, req, prev);
+		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
 		goto out;
 
 	case TCP_SYN_SENT:
@@ -1501,8 +1501,10 @@
 	 * clogging syn queue with openreqs with exponentially increasing
 	 * timeout.
 	 */
-	if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1)
+	if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) {
+		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
 		goto drop;
+	}
 
 	req = inet_reqsk_alloc(&tcp_request_sock_ops);
 	if (!req)
@@ -1667,6 +1669,7 @@
 drop_and_free:
 	reqsk_free(req);
 drop:
+	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
 	return 0;
 }
 EXPORT_SYMBOL(tcp_v4_conn_request);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 79c8dbe..1f4d405 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1952,6 +1952,7 @@
 	.recvmsg	   = udp_recvmsg,
 	.sendpage	   = udp_sendpage,
 	.backlog_rcv	   = __udp_queue_rcv_skb,
+	.release_cb	   = ip4_datagram_release_cb,
 	.hash		   = udp_lib_hash,
 	.unhash		   = udp_lib_unhash,
 	.rehash		   = udp_v4_rehash,
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 420e563..1b5d8cb 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1660,6 +1660,7 @@
 	if (dev->addr_len != IEEE802154_ADDR_LEN)
 		return -1;
 	memcpy(eui, dev->dev_addr, 8);
+	eui[0] ^= 2;
 	return 0;
 }
 
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index ecc35b9..3842331 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -472,7 +472,10 @@
 	skb->network_header += ah_hlen;
 	memcpy(skb_network_header(skb), work_iph, hdr_len);
 	__skb_pull(skb, ah_hlen + hdr_len);
-	skb_set_transport_header(skb, -hdr_len);
+	if (x->props.mode == XFRM_MODE_TUNNEL)
+		skb_reset_transport_header(skb);
+	else
+		skb_set_transport_header(skb, -hdr_len);
 out:
 	kfree(AH_SKB_CB(skb)->tmp);
 	xfrm_input_resume(skb, err);
@@ -593,9 +596,13 @@
 
 	skb->network_header += ah_hlen;
 	memcpy(skb_network_header(skb), work_iph, hdr_len);
-	skb->transport_header = skb->network_header;
 	__skb_pull(skb, ah_hlen + hdr_len);
 
+	if (x->props.mode == XFRM_MODE_TUNNEL)
+		skb_reset_transport_header(skb);
+	else
+		skb_set_transport_header(skb, -hdr_len);
+
 	err = nexthdr;
 
 out_free:
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 8edf260..7a778b9 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -380,7 +380,7 @@
 		if (skb->protocol == htons(ETH_P_IPV6)) {
 			sin->sin6_addr = ipv6_hdr(skb)->saddr;
 			if (np->rxopt.all)
-				datagram_recv_ctl(sk, msg, skb);
+				ip6_datagram_recv_ctl(sk, msg, skb);
 			if (ipv6_addr_type(&sin->sin6_addr) & IPV6_ADDR_LINKLOCAL)
 				sin->sin6_scope_id = IP6CB(skb)->iif;
 		} else {
@@ -468,7 +468,8 @@
 }
 
 
-int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb)
+int ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg,
+			  struct sk_buff *skb)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct inet6_skb_parm *opt = IP6CB(skb);
@@ -597,11 +598,12 @@
 	}
 	return 0;
 }
+EXPORT_SYMBOL_GPL(ip6_datagram_recv_ctl);
 
-int datagram_send_ctl(struct net *net, struct sock *sk,
-		      struct msghdr *msg, struct flowi6 *fl6,
-		      struct ipv6_txoptions *opt,
-		      int *hlimit, int *tclass, int *dontfrag)
+int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
+			  struct msghdr *msg, struct flowi6 *fl6,
+			  struct ipv6_txoptions *opt,
+			  int *hlimit, int *tclass, int *dontfrag)
 {
 	struct in6_pktinfo *src_info;
 	struct cmsghdr *cmsg;
@@ -871,4 +873,4 @@
 exit_f:
 	return err;
 }
-EXPORT_SYMBOL_GPL(datagram_send_ctl);
+EXPORT_SYMBOL_GPL(ip6_datagram_send_ctl);
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 282f372..40ffd72 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -300,7 +300,10 @@
 
 	pskb_trim(skb, skb->len - alen - padlen - 2);
 	__skb_pull(skb, hlen);
-	skb_set_transport_header(skb, -hdr_len);
+	if (x->props.mode == XFRM_MODE_TUNNEL)
+		skb_reset_transport_header(skb);
+	else
+		skb_set_transport_header(skb, -hdr_len);
 
 	err = nexthdr[1];
 
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index b4a9fd5..fff5bdd 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -81,10 +81,22 @@
 	return net->ipv6.icmp_sk[smp_processor_id()];
 }
 
+static void icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+		       u8 type, u8 code, int offset, __be32 info)
+{
+	struct net *net = dev_net(skb->dev);
+
+	if (type == ICMPV6_PKT_TOOBIG)
+		ip6_update_pmtu(skb, net, info, 0, 0);
+	else if (type == NDISC_REDIRECT)
+		ip6_redirect(skb, net, 0, 0);
+}
+
 static int icmpv6_rcv(struct sk_buff *skb);
 
 static const struct inet6_protocol icmpv6_protocol = {
 	.handler	=	icmpv6_rcv,
+	.err_handler	=	icmpv6_err,
 	.flags		=	INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
 };
 
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 29124b7..d6de4b4 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -365,8 +365,8 @@
 		msg.msg_control = (void*)(fl->opt+1);
 		memset(&flowi6, 0, sizeof(flowi6));
 
-		err = datagram_send_ctl(net, sk, &msg, &flowi6, fl->opt, &junk,
-					&junk, &junk);
+		err = ip6_datagram_send_ctl(net, sk, &msg, &flowi6, fl->opt,
+					    &junk, &junk, &junk);
 		if (err)
 			goto done;
 		err = -EINVAL;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index c727e47..131dd09 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -960,7 +960,7 @@
 	int ret;
 
 	if (!ip6_tnl_xmit_ctl(t))
-		return -1;
+		goto tx_err;
 
 	switch (skb->protocol) {
 	case htons(ETH_P_IP):
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 5552d13..0c7c03d 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1213,10 +1213,10 @@
 		if (dst_allfrag(rt->dst.path))
 			cork->flags |= IPCORK_ALLFRAG;
 		cork->length = 0;
-		exthdrlen = (opt ? opt->opt_flen : 0) - rt->rt6i_nfheader_len;
+		exthdrlen = (opt ? opt->opt_flen : 0);
 		length += exthdrlen;
 		transhdrlen += exthdrlen;
-		dst_exthdrlen = rt->dst.header_len;
+		dst_exthdrlen = rt->dst.header_len - rt->rt6i_nfheader_len;
 	} else {
 		rt = (struct rt6_info *)cork->dst;
 		fl6 = &inet->cork.fl.u.ip6;
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 26dcdec..8fd154e 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1710,6 +1710,9 @@
 			return -EINVAL;
 		if (get_user(v, (u32 __user *)optval))
 			return -EFAULT;
+		/* "pim6reg%u" should not exceed 16 bytes (IFNAMSIZ) */
+		if (v != RT_TABLE_DEFAULT && v >= 100000000)
+			return -EINVAL;
 		if (sk == mrt->mroute6_sk)
 			return -EBUSY;
 
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index ee94d31..d1e2e8e 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -476,8 +476,8 @@
 		msg.msg_controllen = optlen;
 		msg.msg_control = (void*)(opt+1);
 
-		retv = datagram_send_ctl(net, sk, &msg, &fl6, opt, &junk, &junk,
-					 &junk);
+		retv = ip6_datagram_send_ctl(net, sk, &msg, &fl6, opt, &junk,
+					     &junk, &junk);
 		if (retv)
 			goto done;
 update:
@@ -1002,7 +1002,7 @@
 		release_sock(sk);
 
 		if (skb) {
-			int err = datagram_recv_ctl(sk, &msg, skb);
+			int err = ip6_datagram_recv_ctl(sk, &msg, skb);
 			kfree_skb(skb);
 			if (err)
 				return err;
diff --git a/net/ipv6/netfilter/ip6t_NPT.c b/net/ipv6/netfilter/ip6t_NPT.c
index 7302b0b..83acc14 100644
--- a/net/ipv6/netfilter/ip6t_NPT.c
+++ b/net/ipv6/netfilter/ip6t_NPT.c
@@ -9,6 +9,7 @@
 #include <linux/module.h>
 #include <linux/skbuff.h>
 #include <linux/ipv6.h>
+#include <net/ipv6.h>
 #include <linux/netfilter.h>
 #include <linux/netfilter_ipv6.h>
 #include <linux/netfilter_ipv6/ip6t_NPT.h>
@@ -18,11 +19,20 @@
 {
 	struct ip6t_npt_tginfo *npt = par->targinfo;
 	__wsum src_sum = 0, dst_sum = 0;
+	struct in6_addr pfx;
 	unsigned int i;
 
 	if (npt->src_pfx_len > 64 || npt->dst_pfx_len > 64)
 		return -EINVAL;
 
+	/* Ensure that LSB of prefix is zero */
+	ipv6_addr_prefix(&pfx, &npt->src_pfx.in6, npt->src_pfx_len);
+	if (!ipv6_addr_equal(&pfx, &npt->src_pfx.in6))
+		return -EINVAL;
+	ipv6_addr_prefix(&pfx, &npt->dst_pfx.in6, npt->dst_pfx_len);
+	if (!ipv6_addr_equal(&pfx, &npt->dst_pfx.in6))
+		return -EINVAL;
+
 	for (i = 0; i < ARRAY_SIZE(npt->src_pfx.in6.s6_addr16); i++) {
 		src_sum = csum_add(src_sum,
 				(__force __wsum)npt->src_pfx.in6.s6_addr16[i]);
@@ -30,7 +40,7 @@
 				(__force __wsum)npt->dst_pfx.in6.s6_addr16[i]);
 	}
 
-	npt->adjustment = (__force __sum16) csum_sub(src_sum, dst_sum);
+	npt->adjustment = ~csum_fold(csum_sub(src_sum, dst_sum));
 	return 0;
 }
 
@@ -51,7 +61,7 @@
 
 		idx = i / 32;
 		addr->s6_addr32[idx] &= mask;
-		addr->s6_addr32[idx] |= npt->dst_pfx.in6.s6_addr32[idx];
+		addr->s6_addr32[idx] |= ~mask & npt->dst_pfx.in6.s6_addr32[idx];
 	}
 
 	if (pfx_len <= 48)
@@ -66,8 +76,8 @@
 			return false;
 	}
 
-	sum = (__force __sum16) csum_add((__force __wsum)addr->s6_addr16[idx],
-			 npt->adjustment);
+	sum = ~csum_fold(csum_add(csum_unfold((__force __sum16)addr->s6_addr16[idx]),
+				  csum_unfold(npt->adjustment)));
 	if (sum == CSUM_MANGLED_0)
 		sum = 0;
 	*(__force __sum16 *)&addr->s6_addr16[idx] = sum;
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 6cd29b1..70fa814 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -507,7 +507,7 @@
 	sock_recv_ts_and_drops(msg, sk, skb);
 
 	if (np->rxopt.all)
-		datagram_recv_ctl(sk, msg, skb);
+		ip6_datagram_recv_ctl(sk, msg, skb);
 
 	err = copied;
 	if (flags & MSG_TRUNC)
@@ -822,8 +822,8 @@
 		memset(opt, 0, sizeof(struct ipv6_txoptions));
 		opt->tot_len = sizeof(struct ipv6_txoptions);
 
-		err = datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt,
-					&hlimit, &tclass, &dontfrag);
+		err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt,
+					    &hlimit, &tclass, &dontfrag);
 		if (err < 0) {
 			fl6_sock_release(flowlabel);
 			return err;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index e229a3b..363d8b7 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -928,7 +928,7 @@
 	dst_hold(&rt->dst);
 	read_unlock_bh(&table->tb6_lock);
 
-	if (!rt->n && !(rt->rt6i_flags & RTF_NONEXTHOP))
+	if (!rt->n && !(rt->rt6i_flags & (RTF_NONEXTHOP | RTF_LOCAL)))
 		nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr);
 	else if (!(rt->dst.flags & DST_HOST))
 		nrt = rt6_alloc_clone(rt, &fl6->daddr);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 93825dd..4f435371 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -423,6 +423,7 @@
 		}
 
 		inet_csk_reqsk_queue_drop(sk, req, prev);
+		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
 		goto out;
 
 	case TCP_SYN_SENT:
@@ -958,8 +959,10 @@
 			goto drop;
 	}
 
-	if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1)
+	if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) {
+		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
 		goto drop;
+	}
 
 	req = inet6_reqsk_alloc(&tcp6_request_sock_ops);
 	if (req == NULL)
@@ -1108,6 +1111,7 @@
 drop_and_free:
 	reqsk_free(req);
 drop:
+	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
 	return 0; /* don't send reset */
 }
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index dfaa29b..fb08329 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -443,7 +443,7 @@
 			ip_cmsg_recv(msg, skb);
 	} else {
 		if (np->rxopt.all)
-			datagram_recv_ctl(sk, msg, skb);
+			ip6_datagram_recv_ctl(sk, msg, skb);
 	}
 
 	err = copied;
@@ -1153,8 +1153,8 @@
 		memset(opt, 0, sizeof(struct ipv6_txoptions));
 		opt->tot_len = sizeof(*opt);
 
-		err = datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt,
-					&hlimit, &tclass, &dontfrag);
+		err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt,
+					    &hlimit, &tclass, &dontfrag);
 		if (err < 0) {
 			fl6_sock_release(flowlabel);
 			return err;
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 1a9f372..2ac884d 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -168,6 +168,51 @@
 
 }
 
+/* Lookup the tunnel socket, possibly involving the fs code if the socket is
+ * owned by userspace.  A struct sock returned from this function must be
+ * released using l2tp_tunnel_sock_put once you're done with it.
+ */
+struct sock *l2tp_tunnel_sock_lookup(struct l2tp_tunnel *tunnel)
+{
+	int err = 0;
+	struct socket *sock = NULL;
+	struct sock *sk = NULL;
+
+	if (!tunnel)
+		goto out;
+
+	if (tunnel->fd >= 0) {
+		/* Socket is owned by userspace, who might be in the process
+		 * of closing it.  Look the socket up using the fd to ensure
+		 * consistency.
+		 */
+		sock = sockfd_lookup(tunnel->fd, &err);
+		if (sock)
+			sk = sock->sk;
+	} else {
+		/* Socket is owned by kernelspace */
+		sk = tunnel->sock;
+	}
+
+out:
+	return sk;
+}
+EXPORT_SYMBOL_GPL(l2tp_tunnel_sock_lookup);
+
+/* Drop a reference to a tunnel socket obtained via. l2tp_tunnel_sock_put */
+void l2tp_tunnel_sock_put(struct sock *sk)
+{
+	struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk);
+	if (tunnel) {
+		if (tunnel->fd >= 0) {
+			/* Socket is owned by userspace */
+			sockfd_put(sk->sk_socket);
+		}
+		sock_put(sk);
+	}
+}
+EXPORT_SYMBOL_GPL(l2tp_tunnel_sock_put);
+
 /* Lookup a session by id in the global session list
  */
 static struct l2tp_session *l2tp_session_find_2(struct net *net, u32 session_id)
@@ -1123,8 +1168,6 @@
 	struct udphdr *uh;
 	struct inet_sock *inet;
 	__wsum csum;
-	int old_headroom;
-	int new_headroom;
 	int headroom;
 	int uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(struct udphdr) : 0;
 	int udp_len;
@@ -1136,16 +1179,12 @@
 	 */
 	headroom = NET_SKB_PAD + sizeof(struct iphdr) +
 		uhlen + hdr_len;
-	old_headroom = skb_headroom(skb);
 	if (skb_cow_head(skb, headroom)) {
 		kfree_skb(skb);
 		return NET_XMIT_DROP;
 	}
 
-	new_headroom = skb_headroom(skb);
 	skb_orphan(skb);
-	skb->truesize += new_headroom - old_headroom;
-
 	/* Setup L2TP header */
 	session->build_header(session, __skb_push(skb, hdr_len));
 
@@ -1607,6 +1646,7 @@
 	tunnel->old_sk_destruct = sk->sk_destruct;
 	sk->sk_destruct = &l2tp_tunnel_destruct;
 	tunnel->sock = sk;
+	tunnel->fd = fd;
 	lockdep_set_class_and_name(&sk->sk_lock.slock, &l2tp_socket_class, "l2tp_sock");
 
 	sk->sk_allocation = GFP_ATOMIC;
@@ -1642,24 +1682,32 @@
  */
 int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel)
 {
-	int err = 0;
-	struct socket *sock = tunnel->sock ? tunnel->sock->sk_socket : NULL;
+	int err = -EBADF;
+	struct socket *sock = NULL;
+	struct sock *sk = NULL;
+
+	sk = l2tp_tunnel_sock_lookup(tunnel);
+	if (!sk)
+		goto out;
+
+	sock = sk->sk_socket;
+	BUG_ON(!sock);
 
 	/* Force the tunnel socket to close. This will eventually
 	 * cause the tunnel to be deleted via the normal socket close
 	 * mechanisms when userspace closes the tunnel socket.
 	 */
-	if (sock != NULL) {
-		err = inet_shutdown(sock, 2);
+	err = inet_shutdown(sock, 2);
 
-		/* If the tunnel's socket was created by the kernel,
-		 * close the socket here since the socket was not
-		 * created by userspace.
-		 */
-		if (sock->file == NULL)
-			err = inet_release(sock);
-	}
+	/* If the tunnel's socket was created by the kernel,
+	 * close the socket here since the socket was not
+	 * created by userspace.
+	 */
+	if (sock->file == NULL)
+		err = inet_release(sock);
 
+	l2tp_tunnel_sock_put(sk);
+out:
 	return err;
 }
 EXPORT_SYMBOL_GPL(l2tp_tunnel_delete);
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 56d583e..e62204c 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -188,7 +188,8 @@
 	int (*recv_payload_hook)(struct sk_buff *skb);
 	void (*old_sk_destruct)(struct sock *);
 	struct sock		*sock;		/* Parent socket */
-	int			fd;
+	int			fd;		/* Parent fd, if tunnel socket
+						 * was created by userspace */
 
 	uint8_t			priv[0];	/* private data */
 };
@@ -228,6 +229,8 @@
 	return tunnel;
 }
 
+extern struct sock *l2tp_tunnel_sock_lookup(struct l2tp_tunnel *tunnel);
+extern void l2tp_tunnel_sock_put(struct sock *sk);
 extern struct l2tp_session *l2tp_session_find(struct net *net, struct l2tp_tunnel *tunnel, u32 session_id);
 extern struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth);
 extern struct l2tp_session *l2tp_session_find_by_ifname(struct net *net, char *ifname);
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 9275471..8ee4a86 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -554,8 +554,8 @@
 		memset(opt, 0, sizeof(struct ipv6_txoptions));
 		opt->tot_len = sizeof(struct ipv6_txoptions);
 
-		err = datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt,
-					&hlimit, &tclass, &dontfrag);
+		err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt,
+					    &hlimit, &tclass, &dontfrag);
 		if (err < 0) {
 			fl6_sock_release(flowlabel);
 			return err;
@@ -646,7 +646,7 @@
 			    struct msghdr *msg, size_t len, int noblock,
 			    int flags, int *addr_len)
 {
-	struct inet_sock *inet = inet_sk(sk);
+	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct sockaddr_l2tpip6 *lsa = (struct sockaddr_l2tpip6 *)msg->msg_name;
 	size_t copied = 0;
 	int err = -EOPNOTSUPP;
@@ -688,8 +688,8 @@
 			lsa->l2tp_scope_id = IP6CB(skb)->iif;
 	}
 
-	if (inet->cmsg_flags)
-		ip_cmsg_recv(msg, skb);
+	if (np->rxopt.all)
+		ip6_datagram_recv_ctl(sk, msg, skb);
 
 	if (flags & MSG_TRUNC)
 		copied = skb->len;
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 286366e..716605c 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -388,8 +388,6 @@
 	struct l2tp_session *session;
 	struct l2tp_tunnel *tunnel;
 	struct pppol2tp_session *ps;
-	int old_headroom;
-	int new_headroom;
 	int uhlen, headroom;
 
 	if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED))
@@ -408,7 +406,6 @@
 	if (tunnel == NULL)
 		goto abort_put_sess;
 
-	old_headroom = skb_headroom(skb);
 	uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(struct udphdr) : 0;
 	headroom = NET_SKB_PAD +
 		   sizeof(struct iphdr) + /* IP header */
@@ -418,9 +415,6 @@
 	if (skb_cow_head(skb, headroom))
 		goto abort_put_sess_tun;
 
-	new_headroom = skb_headroom(skb);
-	skb->truesize += new_headroom - old_headroom;
-
 	/* Setup PPP header */
 	__skb_push(skb, sizeof(ppph));
 	skb->data[0] = ppph[0];
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 47e0aca..0479c64 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -164,7 +164,17 @@
 			sta = sta_info_get(sdata, mac_addr);
 		else
 			sta = sta_info_get_bss(sdata, mac_addr);
-		if (!sta) {
+		/*
+		 * The ASSOC test makes sure the driver is ready to
+		 * receive the key. When wpa_supplicant has roamed
+		 * using FT, it attempts to set the key before
+		 * association has completed, this rejects that attempt
+		 * so it will set the key again after assocation.
+		 *
+		 * TODO: accept the key if we have a station entry and
+		 *       add it to the device after the station.
+		 */
+		if (!sta || !test_sta_flag(sta, WLAN_STA_ASSOC)) {
 			ieee80211_key_free(sdata->local, key);
 			err = -ENOENT;
 			goto out_unlock;
@@ -1994,7 +2004,8 @@
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 
-	memcpy(sdata->vif.bss_conf.mcast_rate, rate, sizeof(rate));
+	memcpy(sdata->vif.bss_conf.mcast_rate, rate,
+	       sizeof(int) * IEEE80211_NUM_BANDS);
 
 	return 0;
 }
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 8563b9a..2ed065c 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1358,10 +1358,8 @@
 void ieee80211_sched_scan_stopped_work(struct work_struct *work);
 
 /* off-channel helpers */
-void ieee80211_offchannel_stop_vifs(struct ieee80211_local *local,
-				    bool offchannel_ps_enable);
-void ieee80211_offchannel_return(struct ieee80211_local *local,
-				 bool offchannel_ps_disable);
+void ieee80211_offchannel_stop_vifs(struct ieee80211_local *local);
+void ieee80211_offchannel_return(struct ieee80211_local *local);
 void ieee80211_roc_setup(struct ieee80211_local *local);
 void ieee80211_start_next_roc(struct ieee80211_local *local);
 void ieee80211_roc_purge(struct ieee80211_sub_if_data *sdata);
diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c
index 47aeee2..2659e42 100644
--- a/net/mac80211/mesh_hwmp.c
+++ b/net/mac80211/mesh_hwmp.c
@@ -215,6 +215,7 @@
 	skb->priority = 7;
 
 	info->control.vif = &sdata->vif;
+	info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING;
 	ieee80211_set_qos_hdr(sdata, skb);
 }
 
@@ -246,11 +247,13 @@
 		return -EAGAIN;
 
 	skb = dev_alloc_skb(local->tx_headroom +
+			    IEEE80211_ENCRYPT_HEADROOM +
+			    IEEE80211_ENCRYPT_TAILROOM +
 			    hdr_len +
 			    2 + 15 /* PERR IE */);
 	if (!skb)
 		return -1;
-	skb_reserve(skb, local->tx_headroom);
+	skb_reserve(skb, local->tx_headroom + IEEE80211_ENCRYPT_HEADROOM);
 	mgmt = (struct ieee80211_mgmt *) skb_put(skb, hdr_len);
 	memset(mgmt, 0, hdr_len);
 	mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT |
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index a355292..5107248 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -3400,6 +3400,7 @@
 
 	ret = 0;
 
+out:
 	while (!cfg80211_chandef_usable(sdata->local->hw.wiphy, chandef,
 					IEEE80211_CHAN_DISABLED)) {
 		if (WARN_ON(chandef->width == NL80211_CHAN_WIDTH_20_NOHT)) {
@@ -3408,14 +3409,13 @@
 			goto out;
 		}
 
-		ret = chandef_downgrade(chandef);
+		ret |= chandef_downgrade(chandef);
 	}
 
 	if (chandef->width != vht_chandef.width)
 		sdata_info(sdata,
-			   "local regulatory prevented using AP HT/VHT configuration, downgraded\n");
+			   "capabilities/regulatory prevented using AP HT/VHT configuration, downgraded\n");
 
-out:
 	WARN_ON_ONCE(!cfg80211_chandef_valid(chandef));
 	return ret;
 }
@@ -3529,8 +3529,11 @@
 	 */
 	ret = ieee80211_vif_use_channel(sdata, &chandef,
 					IEEE80211_CHANCTX_SHARED);
-	while (ret && chandef.width != NL80211_CHAN_WIDTH_20_NOHT)
+	while (ret && chandef.width != NL80211_CHAN_WIDTH_20_NOHT) {
 		ifmgd->flags |= chandef_downgrade(&chandef);
+		ret = ieee80211_vif_use_channel(sdata, &chandef,
+						IEEE80211_CHANCTX_SHARED);
+	}
 	return ret;
 }
 
diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c
index a5379ae..a3ad4c3 100644
--- a/net/mac80211/offchannel.c
+++ b/net/mac80211/offchannel.c
@@ -102,8 +102,7 @@
 	ieee80211_sta_reset_conn_monitor(sdata);
 }
 
-void ieee80211_offchannel_stop_vifs(struct ieee80211_local *local,
-				    bool offchannel_ps_enable)
+void ieee80211_offchannel_stop_vifs(struct ieee80211_local *local)
 {
 	struct ieee80211_sub_if_data *sdata;
 
@@ -134,8 +133,7 @@
 
 		if (sdata->vif.type != NL80211_IFTYPE_MONITOR) {
 			netif_tx_stop_all_queues(sdata->dev);
-			if (offchannel_ps_enable &&
-			    (sdata->vif.type == NL80211_IFTYPE_STATION) &&
+			if (sdata->vif.type == NL80211_IFTYPE_STATION &&
 			    sdata->u.mgd.associated)
 				ieee80211_offchannel_ps_enable(sdata);
 		}
@@ -143,8 +141,7 @@
 	mutex_unlock(&local->iflist_mtx);
 }
 
-void ieee80211_offchannel_return(struct ieee80211_local *local,
-				 bool offchannel_ps_disable)
+void ieee80211_offchannel_return(struct ieee80211_local *local)
 {
 	struct ieee80211_sub_if_data *sdata;
 
@@ -163,11 +160,9 @@
 			continue;
 
 		/* Tell AP we're back */
-		if (offchannel_ps_disable &&
-		    sdata->vif.type == NL80211_IFTYPE_STATION) {
-			if (sdata->u.mgd.associated)
-				ieee80211_offchannel_ps_disable(sdata);
-		}
+		if (sdata->vif.type == NL80211_IFTYPE_STATION &&
+		    sdata->u.mgd.associated)
+			ieee80211_offchannel_ps_disable(sdata);
 
 		if (sdata->vif.type != NL80211_IFTYPE_MONITOR) {
 			/*
@@ -385,7 +380,7 @@
 			local->tmp_channel = NULL;
 			ieee80211_hw_config(local, 0);
 
-			ieee80211_offchannel_return(local, true);
+			ieee80211_offchannel_return(local);
 		}
 
 		ieee80211_recalc_idle(local);
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index d59fc68..bf82e69 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -292,7 +292,7 @@
 	if (!was_hw_scan) {
 		ieee80211_configure_filter(local);
 		drv_sw_scan_complete(local);
-		ieee80211_offchannel_return(local, true);
+		ieee80211_offchannel_return(local);
 	}
 
 	ieee80211_recalc_idle(local);
@@ -341,7 +341,7 @@
 	local->next_scan_state = SCAN_DECISION;
 	local->scan_channel_idx = 0;
 
-	ieee80211_offchannel_stop_vifs(local, true);
+	ieee80211_offchannel_stop_vifs(local);
 
 	ieee80211_configure_filter(local);
 
@@ -678,12 +678,8 @@
 	local->scan_channel = NULL;
 	ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL);
 
-	/*
-	 * Re-enable vifs and beaconing.  Leave PS
-	 * in off-channel state..will put that back
-	 * on-channel at the end of scanning.
-	 */
-	ieee80211_offchannel_return(local, false);
+	/* disable PS */
+	ieee80211_offchannel_return(local);
 
 	*next_delay = HZ / 5;
 	/* afterwards, resume scan & go to next channel */
@@ -693,8 +689,7 @@
 static void ieee80211_scan_state_resume(struct ieee80211_local *local,
 					unsigned long *next_delay)
 {
-	/* PS already is in off-channel mode */
-	ieee80211_offchannel_stop_vifs(local, false);
+	ieee80211_offchannel_stop_vifs(local);
 
 	if (local->ops->flush) {
 		drv_flush(local, false);
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index e9eadc4..467c1d1 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1673,10 +1673,13 @@
 			chanctx_conf =
 				rcu_dereference(tmp_sdata->vif.chanctx_conf);
 	}
-	if (!chanctx_conf)
-		goto fail_rcu;
 
-	chan = chanctx_conf->def.chan;
+	if (chanctx_conf)
+		chan = chanctx_conf->def.chan;
+	else if (!local->use_chanctx)
+		chan = local->_oper_channel;
+	else
+		goto fail_rcu;
 
 	/*
 	 * Frame injection is not allowed if beaconing is not allowed
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index 746048b..ae8ec6f 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -61,14 +61,27 @@
 	return 1;
 }
 
+static void sctp_nat_csum(struct sk_buff *skb, sctp_sctphdr_t *sctph,
+			  unsigned int sctphoff)
+{
+	__u32 crc32;
+	struct sk_buff *iter;
+
+	crc32 = sctp_start_cksum((__u8 *)sctph, skb_headlen(skb) - sctphoff);
+	skb_walk_frags(skb, iter)
+		crc32 = sctp_update_cksum((u8 *) iter->data,
+					  skb_headlen(iter), crc32);
+	sctph->checksum = sctp_end_cksum(crc32);
+
+	skb->ip_summed = CHECKSUM_UNNECESSARY;
+}
+
 static int
 sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
 		  struct ip_vs_conn *cp, struct ip_vs_iphdr *iph)
 {
 	sctp_sctphdr_t *sctph;
 	unsigned int sctphoff = iph->len;
-	struct sk_buff *iter;
-	__be32 crc32;
 
 #ifdef CONFIG_IP_VS_IPV6
 	if (cp->af == AF_INET6 && iph->fragoffs)
@@ -92,13 +105,7 @@
 	sctph = (void *) skb_network_header(skb) + sctphoff;
 	sctph->source = cp->vport;
 
-	/* Calculate the checksum */
-	crc32 = sctp_start_cksum((u8 *) sctph, skb_headlen(skb) - sctphoff);
-	skb_walk_frags(skb, iter)
-		crc32 = sctp_update_cksum((u8 *) iter->data, skb_headlen(iter),
-				          crc32);
-	crc32 = sctp_end_cksum(crc32);
-	sctph->checksum = crc32;
+	sctp_nat_csum(skb, sctph, sctphoff);
 
 	return 1;
 }
@@ -109,8 +116,6 @@
 {
 	sctp_sctphdr_t *sctph;
 	unsigned int sctphoff = iph->len;
-	struct sk_buff *iter;
-	__be32 crc32;
 
 #ifdef CONFIG_IP_VS_IPV6
 	if (cp->af == AF_INET6 && iph->fragoffs)
@@ -134,13 +139,7 @@
 	sctph = (void *) skb_network_header(skb) + sctphoff;
 	sctph->dest = cp->dport;
 
-	/* Calculate the checksum */
-	crc32 = sctp_start_cksum((u8 *) sctph, skb_headlen(skb) - sctphoff);
-	skb_walk_frags(skb, iter)
-		crc32 = sctp_update_cksum((u8 *) iter->data, skb_headlen(iter),
-					  crc32);
-	crc32 = sctp_end_cksum(crc32);
-	sctph->checksum = crc32;
+	sctp_nat_csum(skb, sctph, sctphoff);
 
 	return 1;
 }
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index effa10c..44fd10c 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -1795,6 +1795,8 @@
 					     GFP_KERNEL);
 			if (!tinfo->buf)
 				goto outtinfo;
+		} else {
+			tinfo->buf = NULL;
 		}
 		tinfo->id = id;
 
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 016d95e..e4a0c4f 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1376,11 +1376,12 @@
 	synchronize_net();
 	nf_conntrack_proto_fini(net);
 	nf_conntrack_cleanup_net(net);
+}
 
-	if (net_eq(net, &init_net)) {
-		RCU_INIT_POINTER(nf_ct_destroy, NULL);
-		nf_conntrack_cleanup_init_net();
-	}
+void nf_conntrack_cleanup_end(void)
+{
+	RCU_INIT_POINTER(nf_ct_destroy, NULL);
+	nf_conntrack_cleanup_init_net();
 }
 
 void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls)
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 363285d..e7185c68 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -575,6 +575,7 @@
 static void __exit nf_conntrack_standalone_fini(void)
 {
 	unregister_pernet_subsys(&nf_conntrack_net_ops);
+	nf_conntrack_cleanup_end();
 }
 
 module_init(nf_conntrack_standalone_init);
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 8d987c3..7b3a9e5 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -345,19 +345,27 @@
 }
 EXPORT_SYMBOL_GPL(xt_find_revision);
 
-static char *textify_hooks(char *buf, size_t size, unsigned int mask)
+static char *
+textify_hooks(char *buf, size_t size, unsigned int mask, uint8_t nfproto)
 {
-	static const char *const names[] = {
+	static const char *const inetbr_names[] = {
 		"PREROUTING", "INPUT", "FORWARD",
 		"OUTPUT", "POSTROUTING", "BROUTING",
 	};
-	unsigned int i;
+	static const char *const arp_names[] = {
+		"INPUT", "FORWARD", "OUTPUT",
+	};
+	const char *const *names;
+	unsigned int i, max;
 	char *p = buf;
 	bool np = false;
 	int res;
 
+	names = (nfproto == NFPROTO_ARP) ? arp_names : inetbr_names;
+	max   = (nfproto == NFPROTO_ARP) ? ARRAY_SIZE(arp_names) :
+	                                   ARRAY_SIZE(inetbr_names);
 	*p = '\0';
-	for (i = 0; i < ARRAY_SIZE(names); ++i) {
+	for (i = 0; i < max; ++i) {
 		if (!(mask & (1 << i)))
 			continue;
 		res = snprintf(p, size, "%s%s", np ? "/" : "", names[i]);
@@ -402,8 +410,10 @@
 		pr_err("%s_tables: %s match: used from hooks %s, but only "
 		       "valid from %s\n",
 		       xt_prefix[par->family], par->match->name,
-		       textify_hooks(used, sizeof(used), par->hook_mask),
-		       textify_hooks(allow, sizeof(allow), par->match->hooks));
+		       textify_hooks(used, sizeof(used), par->hook_mask,
+		                     par->family),
+		       textify_hooks(allow, sizeof(allow), par->match->hooks,
+		                     par->family));
 		return -EINVAL;
 	}
 	if (par->match->proto && (par->match->proto != proto || inv_proto)) {
@@ -575,8 +585,10 @@
 		pr_err("%s_tables: %s target: used from hooks %s, but only "
 		       "usable from %s\n",
 		       xt_prefix[par->family], par->target->name,
-		       textify_hooks(used, sizeof(used), par->hook_mask),
-		       textify_hooks(allow, sizeof(allow), par->target->hooks));
+		       textify_hooks(used, sizeof(used), par->hook_mask,
+		                     par->family),
+		       textify_hooks(allow, sizeof(allow), par->target->hooks,
+		                     par->family));
 		return -EINVAL;
 	}
 	if (par->target->proto && (par->target->proto != proto || inv_proto)) {
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index 2a08430..bde009e 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -109,7 +109,7 @@
 	struct xt_ct_target_info *info = par->targinfo;
 	struct nf_conntrack_tuple t;
 	struct nf_conn *ct;
-	int ret;
+	int ret = -EOPNOTSUPP;
 
 	if (info->flags & ~XT_CT_NOTRACK)
 		return -EINVAL;
@@ -247,7 +247,7 @@
 	struct xt_ct_target_info_v1 *info = par->targinfo;
 	struct nf_conntrack_tuple t;
 	struct nf_conn *ct;
-	int ret;
+	int ret = -EOPNOTSUPP;
 
 	if (info->flags & ~XT_CT_NOTRACK)
 		return -EINVAL;
diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c
index a9327e2..670cbc3 100644
--- a/net/openvswitch/vport-netdev.c
+++ b/net/openvswitch/vport-netdev.c
@@ -35,10 +35,11 @@
 /* Must be called with rcu_read_lock. */
 static void netdev_port_receive(struct vport *vport, struct sk_buff *skb)
 {
-	if (unlikely(!vport)) {
-		kfree_skb(skb);
-		return;
-	}
+	if (unlikely(!vport))
+		goto error;
+
+	if (unlikely(skb_warn_if_lro(skb)))
+		goto error;
 
 	/* Make our own copy of the packet.  Otherwise we will mangle the
 	 * packet for anyone who came before us (e.g. tcpdump via AF_PACKET).
@@ -50,6 +51,10 @@
 
 	skb_push(skb, ETH_HLEN);
 	ovs_vport_receive(vport, skb);
+	return;
+
+error:
+	kfree_skb(skb);
 }
 
 /* Called with rcu_read_lock and bottom-halves disabled. */
@@ -169,9 +174,6 @@
 		goto error;
 	}
 
-	if (unlikely(skb_warn_if_lro(skb)))
-		goto error;
-
 	skb->dev = netdev_vport->dev;
 	len = skb->len;
 	dev_queue_xmit(skb);
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index e639645..c111bd0 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2361,13 +2361,15 @@
 
 	packet_flush_mclist(sk);
 
-	memset(&req_u, 0, sizeof(req_u));
-
-	if (po->rx_ring.pg_vec)
+	if (po->rx_ring.pg_vec) {
+		memset(&req_u, 0, sizeof(req_u));
 		packet_set_ring(sk, &req_u, 1, 0);
+	}
 
-	if (po->tx_ring.pg_vec)
+	if (po->tx_ring.pg_vec) {
+		memset(&req_u, 0, sizeof(req_u));
 		packet_set_ring(sk, &req_u, 1, 1);
+	}
 
 	fanout_release(sk);
 
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 51561ea..79e8ed4 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1135,9 +1135,9 @@
 	memset(&opt, 0, sizeof(opt));
 
 	opt.rate.rate = cl->rate.rate_bps >> 3;
-	opt.buffer = cl->buffer;
+	opt.buffer = PSCHED_NS2TICKS(cl->buffer);
 	opt.ceil.rate = cl->ceil.rate_bps >> 3;
-	opt.cbuffer = cl->cbuffer;
+	opt.cbuffer = PSCHED_NS2TICKS(cl->cbuffer);
 	opt.quantum = cl->quantum;
 	opt.prio = cl->prio;
 	opt.level = cl->level;
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 298c0dd..3d2acc7 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -438,18 +438,18 @@
 		if (q->rate) {
 			struct sk_buff_head *list = &sch->q;
 
-			delay += packet_len_2_sched_time(skb->len, q);
-
 			if (!skb_queue_empty(list)) {
 				/*
-				 * Last packet in queue is reference point (now).
-				 * First packet in queue is already in flight,
-				 * calculate this time bonus and substract
+				 * Last packet in queue is reference point (now),
+				 * calculate this time bonus and subtract
 				 * from delay.
 				 */
-				delay -= now - netem_skb_cb(skb_peek(list))->time_to_send;
+				delay -= netem_skb_cb(skb_peek_tail(list))->time_to_send - now;
+				delay = max_t(psched_tdiff_t, 0, delay);
 				now = netem_skb_cb(skb_peek_tail(list))->time_to_send;
 			}
+
+			delay += packet_len_2_sched_time(skb->len, q);
 		}
 
 		cb->time_to_send = now + delay;
diff --git a/net/sctp/Kconfig b/net/sctp/Kconfig
index 7521d94..cf48528 100644
--- a/net/sctp/Kconfig
+++ b/net/sctp/Kconfig
@@ -3,8 +3,8 @@
 #
 
 menuconfig IP_SCTP
-	tristate "The SCTP Protocol (EXPERIMENTAL)"
-	depends on INET && EXPERIMENTAL
+	tristate "The SCTP Protocol"
+	depends on INET
 	depends on IPV6 || IPV6=n
 	select CRYPTO
 	select CRYPTO_HMAC
diff --git a/net/sctp/auth.c b/net/sctp/auth.c
index 159b9bc..d8420ae 100644
--- a/net/sctp/auth.c
+++ b/net/sctp/auth.c
@@ -71,7 +71,7 @@
 		return;
 
 	if (atomic_dec_and_test(&key->refcnt)) {
-		kfree(key);
+		kzfree(key);
 		SCTP_DBG_OBJCNT_DEC(keys);
 	}
 }
diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c
index 17a001b..1a9c5fb 100644
--- a/net/sctp/endpointola.c
+++ b/net/sctp/endpointola.c
@@ -249,6 +249,8 @@
 /* Final destructor for endpoint.  */
 static void sctp_endpoint_destroy(struct sctp_endpoint *ep)
 {
+	int i;
+
 	SCTP_ASSERT(ep->base.dead, "Endpoint is not dead", return);
 
 	/* Free up the HMAC transform. */
@@ -271,6 +273,9 @@
 	sctp_inq_free(&ep->base.inqueue);
 	sctp_bind_addr_free(&ep->base.bind_addr);
 
+	for (i = 0; i < SCTP_HOW_MANY_SECRETS; ++i)
+		memset(&ep->secret_key[i], 0, SCTP_SECRET_SIZE);
+
 	/* Remove and free the port */
 	if (sctp_sk(ep->base.sk)->bind_hash)
 		sctp_put_port(ep->base.sk);
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index f3f0f4d..391a245 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -326,9 +326,10 @@
 	 */
 	rcu_read_lock();
 	list_for_each_entry_rcu(laddr, &bp->address_list, list) {
-		if (!laddr->valid && laddr->state != SCTP_ADDR_SRC)
+		if (!laddr->valid)
 			continue;
-		if ((laddr->a.sa.sa_family == AF_INET6) &&
+		if ((laddr->state == SCTP_ADDR_SRC) &&
+		    (laddr->a.sa.sa_family == AF_INET6) &&
 		    (scope <= sctp_scope(&laddr->a))) {
 			bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a);
 			if (!baddr || (matchlen < bmatchlen)) {
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index 379c81d..9bcdbd0 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -224,7 +224,7 @@
 
 /* Free the outqueue structure and any related pending chunks.
  */
-void sctp_outq_teardown(struct sctp_outq *q)
+static void __sctp_outq_teardown(struct sctp_outq *q)
 {
 	struct sctp_transport *transport;
 	struct list_head *lchunk, *temp;
@@ -277,8 +277,6 @@
 		sctp_chunk_free(chunk);
 	}
 
-	q->error = 0;
-
 	/* Throw away any leftover control chunks. */
 	list_for_each_entry_safe(chunk, tmp, &q->control_chunk_list, list) {
 		list_del_init(&chunk->list);
@@ -286,11 +284,17 @@
 	}
 }
 
+void sctp_outq_teardown(struct sctp_outq *q)
+{
+	__sctp_outq_teardown(q);
+	sctp_outq_init(q->asoc, q);
+}
+
 /* Free the outqueue structure and any related pending chunks.  */
 void sctp_outq_free(struct sctp_outq *q)
 {
 	/* Throw away leftover chunks. */
-	sctp_outq_teardown(q);
+	__sctp_outq_teardown(q);
 
 	/* If we were kmalloc()'d, free the memory.  */
 	if (q->malloced)
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 618ec7e..5131fcf 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -1779,8 +1779,10 @@
 
 	/* Update the content of current association. */
 	sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc));
-	sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl));
 	sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev));
+	sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE,
+			SCTP_STATE(SCTP_STATE_ESTABLISHED));
+	sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl));
 	return SCTP_DISPOSITION_CONSUME;
 
 nomem_ev:
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 9e65758..cedd9bf 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -3390,7 +3390,7 @@
 
 	ret = sctp_auth_set_key(sctp_sk(sk)->ep, asoc, authkey);
 out:
-	kfree(authkey);
+	kzfree(authkey);
 	return ret;
 }
 
diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index 043889a..bf3c6e8 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -366,7 +366,11 @@
 
 void sctp_sysctl_net_unregister(struct net *net)
 {
+	struct ctl_table *table;
+
+	table = net->sctp.sysctl_header->ctl_table_arg;
 	unregister_net_sysctl_table(net->sctp.sysctl_header);
+	kfree(table);
 }
 
 static struct ctl_table_header * sctp_sysctl_header;
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index bfa3171..fb20f25 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -98,9 +98,25 @@
 	list_add(&task->u.tk_wait.timer_list, &queue->timer_list.list);
 }
 
+static void rpc_rotate_queue_owner(struct rpc_wait_queue *queue)
+{
+	struct list_head *q = &queue->tasks[queue->priority];
+	struct rpc_task *task;
+
+	if (!list_empty(q)) {
+		task = list_first_entry(q, struct rpc_task, u.tk_wait.list);
+		if (task->tk_owner == queue->owner)
+			list_move_tail(&task->u.tk_wait.list, q);
+	}
+}
+
 static void rpc_set_waitqueue_priority(struct rpc_wait_queue *queue, int priority)
 {
-	queue->priority = priority;
+	if (queue->priority != priority) {
+		/* Fairness: rotate the list when changing priority */
+		rpc_rotate_queue_owner(queue);
+		queue->priority = priority;
+	}
 }
 
 static void rpc_set_waitqueue_owner(struct rpc_wait_queue *queue, pid_t pid)
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 0a148c9..0f679df 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -465,7 +465,7 @@
 }
 
 /*
- * See net/ipv6/datagram.c : datagram_recv_ctl
+ * See net/ipv6/datagram.c : ip6_datagram_recv_ctl
  */
 static int svc_udp_get_dest_address6(struct svc_rqst *rqstp,
 				     struct cmsghdr *cmh)
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 01592d7..45f1618 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -1358,7 +1358,7 @@
 						  &iwe, IW_EV_UINT_LEN);
 	}
 
-	buf = kmalloc(30, GFP_ATOMIC);
+	buf = kmalloc(31, GFP_ATOMIC);
 	if (buf) {
 		memset(&iwe, 0, sizeof(iwe));
 		iwe.cmd = IWEVCUSTOM;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 41eabc4..07c5857 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2656,7 +2656,7 @@
 		WARN_ON(!hlist_empty(&net->xfrm.policy_inexact[dir]));
 
 		htab = &net->xfrm.policy_bydst[dir];
-		sz = (htab->hmask + 1);
+		sz = (htab->hmask + 1) * sizeof(struct hlist_head);
 		WARN_ON(!hlist_empty(htab->table));
 		xfrm_hash_free(htab->table, sz);
 	}
diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c
index 765f6fe..35754cc 100644
--- a/net/xfrm/xfrm_replay.c
+++ b/net/xfrm/xfrm_replay.c
@@ -242,11 +242,13 @@
 	u32 diff;
 	struct xfrm_replay_state_esn *replay_esn = x->replay_esn;
 	u32 seq = ntohl(net_seq);
-	u32 pos = (replay_esn->seq - 1) % replay_esn->replay_window;
+	u32 pos;
 
 	if (!replay_esn->replay_window)
 		return;
 
+	pos = (replay_esn->seq - 1) % replay_esn->replay_window;
+
 	if (seq > replay_esn->seq) {
 		diff = seq - replay_esn->seq;
 
diff --git a/samples/Kconfig b/samples/Kconfig
index 7b6792a..6181c2c 100644
--- a/samples/Kconfig
+++ b/samples/Kconfig
@@ -5,12 +5,6 @@
 
 if SAMPLES
 
-config SAMPLE_TRACEPOINTS
-	tristate "Build tracepoints examples -- loadable modules only"
-	depends on TRACEPOINTS && m
-	help
-	  This build tracepoints example modules.
-
 config SAMPLE_TRACE_EVENTS
 	tristate "Build trace_events examples -- loadable modules only"
 	depends on EVENT_TRACING && m
diff --git a/samples/Makefile b/samples/Makefile
index 5ef08bb..1a60c62 100644
--- a/samples/Makefile
+++ b/samples/Makefile
@@ -1,4 +1,4 @@
 # Makefile for Linux samples code
 
-obj-$(CONFIG_SAMPLES)	+= kobject/ kprobes/ tracepoints/ trace_events/ \
+obj-$(CONFIG_SAMPLES)	+= kobject/ kprobes/ trace_events/ \
 			   hw_breakpoint/ kfifo/ kdb/ hidraw/ rpmsg/ seccomp/
diff --git a/samples/seccomp/Makefile b/samples/seccomp/Makefile
index bbbd276..7203e66 100644
--- a/samples/seccomp/Makefile
+++ b/samples/seccomp/Makefile
@@ -19,6 +19,7 @@
 
 # Try to match the kernel target.
 ifndef CONFIG_64BIT
+ifndef CROSS_COMPILE
 
 # s390 has -m31 flag to build 31 bit binaries
 ifndef CONFIG_S390
@@ -35,6 +36,7 @@
 HOSTLOADLIBES_bpf-fancy += $(MFLAG)
 HOSTLOADLIBES_dropper += $(MFLAG)
 endif
+endif
 
 # Tell kbuild to always build the programs
 always := $(hostprogs-y)
diff --git a/samples/tracepoints/Makefile b/samples/tracepoints/Makefile
deleted file mode 100644
index 36479ad..0000000
--- a/samples/tracepoints/Makefile
+++ /dev/null
@@ -1,6 +0,0 @@
-# builds the tracepoint example kernel modules;
-# then to use one (as root):  insmod <module_name.ko>
-
-obj-$(CONFIG_SAMPLE_TRACEPOINTS) += tracepoint-sample.o
-obj-$(CONFIG_SAMPLE_TRACEPOINTS) += tracepoint-probe-sample.o
-obj-$(CONFIG_SAMPLE_TRACEPOINTS) += tracepoint-probe-sample2.o
diff --git a/samples/tracepoints/tp-samples-trace.h b/samples/tracepoints/tp-samples-trace.h
deleted file mode 100644
index 4d46be9..0000000
--- a/samples/tracepoints/tp-samples-trace.h
+++ /dev/null
@@ -1,11 +0,0 @@
-#ifndef _TP_SAMPLES_TRACE_H
-#define _TP_SAMPLES_TRACE_H
-
-#include <linux/proc_fs.h>	/* for struct inode and struct file */
-#include <linux/tracepoint.h>
-
-DECLARE_TRACE(subsys_event,
-	TP_PROTO(struct inode *inode, struct file *file),
-	TP_ARGS(inode, file));
-DECLARE_TRACE_NOARGS(subsys_eventb);
-#endif
diff --git a/samples/tracepoints/tracepoint-probe-sample.c b/samples/tracepoints/tracepoint-probe-sample.c
deleted file mode 100644
index 744c0b9..0000000
--- a/samples/tracepoints/tracepoint-probe-sample.c
+++ /dev/null
@@ -1,57 +0,0 @@
-/*
- * tracepoint-probe-sample.c
- *
- * sample tracepoint probes.
- */
-
-#include <linux/module.h>
-#include <linux/file.h>
-#include <linux/dcache.h>
-#include "tp-samples-trace.h"
-
-/*
- * Here the caller only guarantees locking for struct file and struct inode.
- * Locking must therefore be done in the probe to use the dentry.
- */
-static void probe_subsys_event(void *ignore,
-			       struct inode *inode, struct file *file)
-{
-	path_get(&file->f_path);
-	dget(file->f_path.dentry);
-	printk(KERN_INFO "Event is encountered with filename %s\n",
-		file->f_path.dentry->d_name.name);
-	dput(file->f_path.dentry);
-	path_put(&file->f_path);
-}
-
-static void probe_subsys_eventb(void *ignore)
-{
-	printk(KERN_INFO "Event B is encountered\n");
-}
-
-static int __init tp_sample_trace_init(void)
-{
-	int ret;
-
-	ret = register_trace_subsys_event(probe_subsys_event, NULL);
-	WARN_ON(ret);
-	ret = register_trace_subsys_eventb(probe_subsys_eventb, NULL);
-	WARN_ON(ret);
-
-	return 0;
-}
-
-module_init(tp_sample_trace_init);
-
-static void __exit tp_sample_trace_exit(void)
-{
-	unregister_trace_subsys_eventb(probe_subsys_eventb, NULL);
-	unregister_trace_subsys_event(probe_subsys_event, NULL);
-	tracepoint_synchronize_unregister();
-}
-
-module_exit(tp_sample_trace_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Mathieu Desnoyers");
-MODULE_DESCRIPTION("Tracepoint Probes Samples");
diff --git a/samples/tracepoints/tracepoint-probe-sample2.c b/samples/tracepoints/tracepoint-probe-sample2.c
deleted file mode 100644
index 9fcf990..0000000
--- a/samples/tracepoints/tracepoint-probe-sample2.c
+++ /dev/null
@@ -1,44 +0,0 @@
-/*
- * tracepoint-probe-sample2.c
- *
- * 2nd sample tracepoint probes.
- */
-
-#include <linux/module.h>
-#include <linux/fs.h>
-#include "tp-samples-trace.h"
-
-/*
- * Here the caller only guarantees locking for struct file and struct inode.
- * Locking must therefore be done in the probe to use the dentry.
- */
-static void probe_subsys_event(void *ignore,
-			       struct inode *inode, struct file *file)
-{
-	printk(KERN_INFO "Event is encountered with inode number %lu\n",
-		inode->i_ino);
-}
-
-static int __init tp_sample_trace_init(void)
-{
-	int ret;
-
-	ret = register_trace_subsys_event(probe_subsys_event, NULL);
-	WARN_ON(ret);
-
-	return 0;
-}
-
-module_init(tp_sample_trace_init);
-
-static void __exit tp_sample_trace_exit(void)
-{
-	unregister_trace_subsys_event(probe_subsys_event, NULL);
-	tracepoint_synchronize_unregister();
-}
-
-module_exit(tp_sample_trace_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Mathieu Desnoyers");
-MODULE_DESCRIPTION("Tracepoint Probes Samples");
diff --git a/samples/tracepoints/tracepoint-sample.c b/samples/tracepoints/tracepoint-sample.c
deleted file mode 100644
index f4d89e0..0000000
--- a/samples/tracepoints/tracepoint-sample.c
+++ /dev/null
@@ -1,57 +0,0 @@
-/* tracepoint-sample.c
- *
- * Executes a tracepoint when /proc/tracepoint-sample is opened.
- *
- * (C) Copyright 2007 Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
- *
- * This file is released under the GPLv2.
- * See the file COPYING for more details.
- */
-
-#include <linux/module.h>
-#include <linux/sched.h>
-#include <linux/proc_fs.h>
-#include "tp-samples-trace.h"
-
-DEFINE_TRACE(subsys_event);
-DEFINE_TRACE(subsys_eventb);
-
-struct proc_dir_entry *pentry_sample;
-
-static int my_open(struct inode *inode, struct file *file)
-{
-	int i;
-
-	trace_subsys_event(inode, file);
-	for (i = 0; i < 10; i++)
-		trace_subsys_eventb();
-	return -EPERM;
-}
-
-static const struct file_operations mark_ops = {
-	.open = my_open,
-	.llseek = noop_llseek,
-};
-
-static int __init sample_init(void)
-{
-	printk(KERN_ALERT "sample init\n");
-	pentry_sample = proc_create("tracepoint-sample", 0444, NULL,
-		&mark_ops);
-	if (!pentry_sample)
-		return -EPERM;
-	return 0;
-}
-
-static void __exit sample_exit(void)
-{
-	printk(KERN_ALERT "sample exit\n");
-	remove_proc_entry("tracepoint-sample", NULL);
-}
-
-module_init(sample_init)
-module_exit(sample_exit)
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Mathieu Desnoyers");
-MODULE_DESCRIPTION("Tracepoint sample");
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 4d2c7df..2bb08a9 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -230,12 +230,12 @@
 our $Member	= qr{->$Ident|\.$Ident|\[[^]]*\]};
 our $Lval	= qr{$Ident(?:$Member)*};
 
-our $Float_hex	= qr{(?i:0x[0-9a-f]+p-?[0-9]+[fl]?)};
-our $Float_dec	= qr{(?i:((?:[0-9]+\.[0-9]*|[0-9]*\.[0-9]+)(?:e-?[0-9]+)?[fl]?))};
-our $Float_int	= qr{(?i:[0-9]+e-?[0-9]+[fl]?)};
+our $Float_hex	= qr{(?i)0x[0-9a-f]+p-?[0-9]+[fl]?};
+our $Float_dec	= qr{(?i)(?:[0-9]+\.[0-9]*|[0-9]*\.[0-9]+)(?:e-?[0-9]+)?[fl]?};
+our $Float_int	= qr{(?i)[0-9]+e-?[0-9]+[fl]?};
 our $Float	= qr{$Float_hex|$Float_dec|$Float_int};
-our $Constant	= qr{(?:$Float|(?i:(?:0x[0-9a-f]+|[0-9]+)[ul]*))};
-our $Assignment	= qr{(?:\*\=|/=|%=|\+=|-=|<<=|>>=|&=|\^=|\|=|=)};
+our $Constant	= qr{$Float|(?i)(?:0x[0-9a-f]+|[0-9]+)[ul]*};
+our $Assignment	= qr{\*\=|/=|%=|\+=|-=|<<=|>>=|&=|\^=|\|=|=};
 our $Compare    = qr{<=|>=|==|!=|<|>};
 our $Operators	= qr{
 			<=|>=|==|!=|
diff --git a/security/capability.c b/security/capability.c
index 0fe5a02..5797750 100644
--- a/security/capability.c
+++ b/security/capability.c
@@ -709,16 +709,31 @@
 {
 }
 
+static int cap_tun_dev_alloc_security(void **security)
+{
+	return 0;
+}
+
+static void cap_tun_dev_free_security(void *security)
+{
+}
+
 static int cap_tun_dev_create(void)
 {
 	return 0;
 }
 
-static void cap_tun_dev_post_create(struct sock *sk)
+static int cap_tun_dev_attach_queue(void *security)
 {
+	return 0;
 }
 
-static int cap_tun_dev_attach(struct sock *sk)
+static int cap_tun_dev_attach(struct sock *sk, void *security)
+{
+	return 0;
+}
+
+static int cap_tun_dev_open(void *security)
 {
 	return 0;
 }
@@ -1050,8 +1065,11 @@
 	set_to_cap_if_null(ops, secmark_refcount_inc);
 	set_to_cap_if_null(ops, secmark_refcount_dec);
 	set_to_cap_if_null(ops, req_classify_flow);
+	set_to_cap_if_null(ops, tun_dev_alloc_security);
+	set_to_cap_if_null(ops, tun_dev_free_security);
 	set_to_cap_if_null(ops, tun_dev_create);
-	set_to_cap_if_null(ops, tun_dev_post_create);
+	set_to_cap_if_null(ops, tun_dev_open);
+	set_to_cap_if_null(ops, tun_dev_attach_queue);
 	set_to_cap_if_null(ops, tun_dev_attach);
 #endif	/* CONFIG_SECURITY_NETWORK */
 #ifdef CONFIG_SECURITY_NETWORK_XFRM
diff --git a/security/security.c b/security/security.c
index daa97f4..7b88c6a 100644
--- a/security/security.c
+++ b/security/security.c
@@ -1254,24 +1254,42 @@
 }
 EXPORT_SYMBOL(security_secmark_refcount_dec);
 
+int security_tun_dev_alloc_security(void **security)
+{
+	return security_ops->tun_dev_alloc_security(security);
+}
+EXPORT_SYMBOL(security_tun_dev_alloc_security);
+
+void security_tun_dev_free_security(void *security)
+{
+	security_ops->tun_dev_free_security(security);
+}
+EXPORT_SYMBOL(security_tun_dev_free_security);
+
 int security_tun_dev_create(void)
 {
 	return security_ops->tun_dev_create();
 }
 EXPORT_SYMBOL(security_tun_dev_create);
 
-void security_tun_dev_post_create(struct sock *sk)
+int security_tun_dev_attach_queue(void *security)
 {
-	return security_ops->tun_dev_post_create(sk);
+	return security_ops->tun_dev_attach_queue(security);
 }
-EXPORT_SYMBOL(security_tun_dev_post_create);
+EXPORT_SYMBOL(security_tun_dev_attach_queue);
 
-int security_tun_dev_attach(struct sock *sk)
+int security_tun_dev_attach(struct sock *sk, void *security)
 {
-	return security_ops->tun_dev_attach(sk);
+	return security_ops->tun_dev_attach(sk, security);
 }
 EXPORT_SYMBOL(security_tun_dev_attach);
 
+int security_tun_dev_open(void *security)
+{
+	return security_ops->tun_dev_open(security);
+}
+EXPORT_SYMBOL(security_tun_dev_open);
+
 #endif	/* CONFIG_SECURITY_NETWORK */
 
 #ifdef CONFIG_SECURITY_NETWORK_XFRM
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 61a5336..ef26e96 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -4399,6 +4399,24 @@
 	fl->flowi_secid = req->secid;
 }
 
+static int selinux_tun_dev_alloc_security(void **security)
+{
+	struct tun_security_struct *tunsec;
+
+	tunsec = kzalloc(sizeof(*tunsec), GFP_KERNEL);
+	if (!tunsec)
+		return -ENOMEM;
+	tunsec->sid = current_sid();
+
+	*security = tunsec;
+	return 0;
+}
+
+static void selinux_tun_dev_free_security(void *security)
+{
+	kfree(security);
+}
+
 static int selinux_tun_dev_create(void)
 {
 	u32 sid = current_sid();
@@ -4414,8 +4432,17 @@
 			    NULL);
 }
 
-static void selinux_tun_dev_post_create(struct sock *sk)
+static int selinux_tun_dev_attach_queue(void *security)
 {
+	struct tun_security_struct *tunsec = security;
+
+	return avc_has_perm(current_sid(), tunsec->sid, SECCLASS_TUN_SOCKET,
+			    TUN_SOCKET__ATTACH_QUEUE, NULL);
+}
+
+static int selinux_tun_dev_attach(struct sock *sk, void *security)
+{
+	struct tun_security_struct *tunsec = security;
 	struct sk_security_struct *sksec = sk->sk_security;
 
 	/* we don't currently perform any NetLabel based labeling here and it
@@ -4425,20 +4452,19 @@
 	 * cause confusion to the TUN user that had no idea network labeling
 	 * protocols were being used */
 
-	/* see the comments in selinux_tun_dev_create() about why we don't use
-	 * the sockcreate SID here */
-
-	sksec->sid = current_sid();
+	sksec->sid = tunsec->sid;
 	sksec->sclass = SECCLASS_TUN_SOCKET;
+
+	return 0;
 }
 
-static int selinux_tun_dev_attach(struct sock *sk)
+static int selinux_tun_dev_open(void *security)
 {
-	struct sk_security_struct *sksec = sk->sk_security;
+	struct tun_security_struct *tunsec = security;
 	u32 sid = current_sid();
 	int err;
 
-	err = avc_has_perm(sid, sksec->sid, SECCLASS_TUN_SOCKET,
+	err = avc_has_perm(sid, tunsec->sid, SECCLASS_TUN_SOCKET,
 			   TUN_SOCKET__RELABELFROM, NULL);
 	if (err)
 		return err;
@@ -4446,8 +4472,7 @@
 			   TUN_SOCKET__RELABELTO, NULL);
 	if (err)
 		return err;
-
-	sksec->sid = sid;
+	tunsec->sid = sid;
 
 	return 0;
 }
@@ -5642,9 +5667,12 @@
 	.secmark_refcount_inc =		selinux_secmark_refcount_inc,
 	.secmark_refcount_dec =		selinux_secmark_refcount_dec,
 	.req_classify_flow =		selinux_req_classify_flow,
+	.tun_dev_alloc_security =	selinux_tun_dev_alloc_security,
+	.tun_dev_free_security =	selinux_tun_dev_free_security,
 	.tun_dev_create =		selinux_tun_dev_create,
-	.tun_dev_post_create = 		selinux_tun_dev_post_create,
+	.tun_dev_attach_queue =		selinux_tun_dev_attach_queue,
 	.tun_dev_attach =		selinux_tun_dev_attach,
+	.tun_dev_open =			selinux_tun_dev_open,
 
 #ifdef CONFIG_SECURITY_NETWORK_XFRM
 	.xfrm_policy_alloc_security =	selinux_xfrm_policy_alloc,
diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h
index df2de54..14d04e6 100644
--- a/security/selinux/include/classmap.h
+++ b/security/selinux/include/classmap.h
@@ -150,6 +150,6 @@
 	    NULL } },
 	{ "kernel_service", { "use_as_override", "create_files_as", NULL } },
 	{ "tun_socket",
-	  { COMMON_SOCK_PERMS, NULL } },
+	  { COMMON_SOCK_PERMS, "attach_queue", NULL } },
 	{ NULL }
   };
diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h
index 26c7eee..aa47bca 100644
--- a/security/selinux/include/objsec.h
+++ b/security/selinux/include/objsec.h
@@ -110,6 +110,10 @@
 	u16 sclass;			/* sock security class */
 };
 
+struct tun_security_struct {
+	u32 sid;			/* SID for the tun device sockets */
+};
+
 struct key_security_struct {
 	u32 sid;	/* SID of key */
 };
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 0b6aeba..c78286f 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -656,29 +656,43 @@
 #define get_azx_dev(substream) (substream->runtime->private_data)
 
 #ifdef CONFIG_X86
-static void __mark_pages_wc(struct azx *chip, void *addr, size_t size, bool on)
+static void __mark_pages_wc(struct azx *chip, struct snd_dma_buffer *dmab, bool on)
 {
+	int pages;
+
 	if (azx_snoop(chip))
 		return;
-	if (addr && size) {
-		int pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	if (!dmab || !dmab->area || !dmab->bytes)
+		return;
+
+#ifdef CONFIG_SND_DMA_SGBUF
+	if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_SG) {
+		struct snd_sg_buf *sgbuf = dmab->private_data;
 		if (on)
-			set_memory_wc((unsigned long)addr, pages);
+			set_pages_array_wc(sgbuf->page_table, sgbuf->pages);
 		else
-			set_memory_wb((unsigned long)addr, pages);
+			set_pages_array_wb(sgbuf->page_table, sgbuf->pages);
+		return;
 	}
+#endif
+
+	pages = (dmab->bytes + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	if (on)
+		set_memory_wc((unsigned long)dmab->area, pages);
+	else
+		set_memory_wb((unsigned long)dmab->area, pages);
 }
 
 static inline void mark_pages_wc(struct azx *chip, struct snd_dma_buffer *buf,
 				 bool on)
 {
-	__mark_pages_wc(chip, buf->area, buf->bytes, on);
+	__mark_pages_wc(chip, buf, on);
 }
 static inline void mark_runtime_wc(struct azx *chip, struct azx_dev *azx_dev,
-				   struct snd_pcm_runtime *runtime, bool on)
+				   struct snd_pcm_substream *substream, bool on)
 {
 	if (azx_dev->wc_marked != on) {
-		__mark_pages_wc(chip, runtime->dma_area, runtime->dma_bytes, on);
+		__mark_pages_wc(chip, snd_pcm_get_dma_buf(substream), on);
 		azx_dev->wc_marked = on;
 	}
 }
@@ -689,7 +703,7 @@
 {
 }
 static inline void mark_runtime_wc(struct azx *chip, struct azx_dev *azx_dev,
-				   struct snd_pcm_runtime *runtime, bool on)
+				   struct snd_pcm_substream *substream, bool on)
 {
 }
 #endif
@@ -1968,11 +1982,10 @@
 {
 	struct azx_pcm *apcm = snd_pcm_substream_chip(substream);
 	struct azx *chip = apcm->chip;
-	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct azx_dev *azx_dev = get_azx_dev(substream);
 	int ret;
 
-	mark_runtime_wc(chip, azx_dev, runtime, false);
+	mark_runtime_wc(chip, azx_dev, substream, false);
 	azx_dev->bufsize = 0;
 	azx_dev->period_bytes = 0;
 	azx_dev->format_val = 0;
@@ -1980,7 +1993,7 @@
 					params_buffer_bytes(hw_params));
 	if (ret < 0)
 		return ret;
-	mark_runtime_wc(chip, azx_dev, runtime, true);
+	mark_runtime_wc(chip, azx_dev, substream, true);
 	return ret;
 }
 
@@ -1989,7 +2002,6 @@
 	struct azx_pcm *apcm = snd_pcm_substream_chip(substream);
 	struct azx_dev *azx_dev = get_azx_dev(substream);
 	struct azx *chip = apcm->chip;
-	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct hda_pcm_stream *hinfo = apcm->hinfo[substream->stream];
 
 	/* reset BDL address */
@@ -2002,7 +2014,7 @@
 
 	snd_hda_codec_cleanup(apcm->codec, hinfo, substream);
 
-	mark_runtime_wc(chip, azx_dev, runtime, false);
+	mark_runtime_wc(chip, azx_dev, substream, false);
 	return snd_pcm_lib_free_pages(substream);
 }
 
@@ -3613,13 +3625,12 @@
 	/* 5 Series/3400 */
 	{ PCI_DEVICE(0x8086, 0x3b56),
 	  .driver_data = AZX_DRIVER_SCH | AZX_DCAPS_INTEL_PCH },
-	/* SCH */
+	/* Poulsbo */
 	{ PCI_DEVICE(0x8086, 0x811b),
-	  .driver_data = AZX_DRIVER_SCH | AZX_DCAPS_SCH_SNOOP |
-	  AZX_DCAPS_BUFSIZE | AZX_DCAPS_POSFIX_LPIB }, /* Poulsbo */
+	  .driver_data = AZX_DRIVER_SCH | AZX_DCAPS_INTEL_PCH_NOPM },
+	/* Oaktrail */
 	{ PCI_DEVICE(0x8086, 0x080a),
-	  .driver_data = AZX_DRIVER_SCH | AZX_DCAPS_SCH_SNOOP |
-	  AZX_DCAPS_BUFSIZE | AZX_DCAPS_POSFIX_LPIB }, /* Oaktrail */
+	  .driver_data = AZX_DRIVER_SCH | AZX_DCAPS_INTEL_PCH_NOPM },
 	/* ICH */
 	{ PCI_DEVICE(0x8086, 0x2668),
 	  .driver_data = AZX_DRIVER_ICH | AZX_DCAPS_OLD_SSYNC |
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index cf38861..5faaad2 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -4694,6 +4694,7 @@
 	SND_PCI_QUIRK(0x1584, 0x9077, "Uniwill P53", ALC880_FIXUP_VOL_KNOB),
 	SND_PCI_QUIRK(0x161f, 0x203d, "W810", ALC880_FIXUP_W810),
 	SND_PCI_QUIRK(0x161f, 0x205d, "Medion Rim 2150", ALC880_FIXUP_MEDION_RIM),
+	SND_PCI_QUIRK(0x1631, 0xe011, "PB 13201056", ALC880_FIXUP_6ST),
 	SND_PCI_QUIRK(0x1734, 0x107c, "FSC F1734", ALC880_FIXUP_F1734),
 	SND_PCI_QUIRK(0x1734, 0x1094, "FSC Amilo M1451G", ALC880_FIXUP_FUJITSU),
 	SND_PCI_QUIRK(0x1734, 0x10ac, "FSC AMILO Xi 1526", ALC880_FIXUP_F1734),
@@ -5708,6 +5709,7 @@
 };
 
 static const struct snd_pci_quirk alc268_fixup_tbl[] = {
+	SND_PCI_QUIRK(0x1025, 0x015b, "Acer AOA 150 (ZG5)", ALC268_FIXUP_INV_DMIC),
 	/* below is codec SSID since multiple Toshiba laptops have the
 	 * same PCI SSID 1179:ff00
 	 */
diff --git a/sound/soc/codecs/arizona.c b/sound/soc/codecs/arizona.c
index 1d8bb59..ef62c43 100644
--- a/sound/soc/codecs/arizona.c
+++ b/sound/soc/codecs/arizona.c
@@ -685,7 +685,7 @@
 	}
 	sr_val = i;
 
-	lrclk = snd_soc_params_to_bclk(params) / params_rate(params);
+	lrclk = rates[bclk] / params_rate(params);
 
 	arizona_aif_dbg(dai, "BCLK %dHz LRCLK %dHz\n",
 			rates[bclk], rates[bclk] / lrclk);
@@ -1082,6 +1082,9 @@
 			id, ret);
 	}
 
+	regmap_update_bits(arizona->regmap, fll->base + 1,
+			   ARIZONA_FLL1_FREERUN, 0);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(arizona_init_fll);
diff --git a/sound/soc/codecs/wm2200.c b/sound/soc/codecs/wm2200.c
index e6cefe1..d8c65f5 100644
--- a/sound/soc/codecs/wm2200.c
+++ b/sound/soc/codecs/wm2200.c
@@ -1019,8 +1019,6 @@
 	"EQR",
 	"LHPF1",
 	"LHPF2",
-	"LHPF3",
-	"LHPF4",
 	"DSP1.1",
 	"DSP1.2",
 	"DSP1.3",
@@ -1053,7 +1051,6 @@
 	0x25,
 	0x50,   /* EQ */
 	0x51,
-	0x52,
 	0x60,   /* LHPF1 */
 	0x61,   /* LHPF2 */
 	0x68,   /* DSP1 */
diff --git a/sound/soc/codecs/wm5102.c b/sound/soc/codecs/wm5102.c
index 7a9048d..1440b3f 100644
--- a/sound/soc/codecs/wm5102.c
+++ b/sound/soc/codecs/wm5102.c
@@ -896,8 +896,7 @@
 
 static const struct soc_enum wm5102_aec_loopback =
 	SOC_VALUE_ENUM_SINGLE(ARIZONA_DAC_AEC_CONTROL_1,
-			      ARIZONA_AEC_LOOPBACK_SRC_SHIFT,
-			      ARIZONA_AEC_LOOPBACK_SRC_MASK,
+			      ARIZONA_AEC_LOOPBACK_SRC_SHIFT, 0xf,
 			      ARRAY_SIZE(wm5102_aec_loopback_texts),
 			      wm5102_aec_loopback_texts,
 			      wm5102_aec_loopback_values);
diff --git a/sound/soc/codecs/wm5110.c b/sound/soc/codecs/wm5110.c
index ae80c8c..7a09096 100644
--- a/sound/soc/codecs/wm5110.c
+++ b/sound/soc/codecs/wm5110.c
@@ -344,8 +344,7 @@
 
 static const struct soc_enum wm5110_aec_loopback =
 	SOC_VALUE_ENUM_SINGLE(ARIZONA_DAC_AEC_CONTROL_1,
-			      ARIZONA_AEC_LOOPBACK_SRC_SHIFT,
-			      ARIZONA_AEC_LOOPBACK_SRC_MASK,
+			      ARIZONA_AEC_LOOPBACK_SRC_SHIFT, 0xf,
 			      ARRAY_SIZE(wm5110_aec_loopback_texts),
 			      wm5110_aec_loopback_texts,
 			      wm5110_aec_loopback_values);
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index 7b198c3..b6b6548 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -324,7 +324,7 @@
 
 		if (reg) {
 			buf = kmemdup(region->data, le32_to_cpu(region->len),
-				      GFP_KERNEL);
+				      GFP_KERNEL | GFP_DMA);
 			if (!buf) {
 				adsp_err(dsp, "Out of memory\n");
 				return -ENOMEM;
@@ -396,7 +396,7 @@
 	hdr = (void*)&firmware->data[0];
 	if (memcmp(hdr->magic, "WMDR", 4) != 0) {
 		adsp_err(dsp, "%s: invalid magic\n", file);
-		return -EINVAL;
+		goto out_fw;
 	}
 
 	adsp_dbg(dsp, "%s: v%d.%d.%d\n", file,
@@ -439,7 +439,7 @@
 
 		if (reg) {
 			buf = kmemdup(blk->data, le32_to_cpu(blk->len),
-				      GFP_KERNEL);
+				      GFP_KERNEL | GFP_DMA);
 			if (!buf) {
 				adsp_err(dsp, "Out of memory\n");
 				return -ENOMEM;
diff --git a/sound/soc/fsl/imx-pcm-dma.c b/sound/soc/fsl/imx-pcm-dma.c
index bf363d8..500f8ce 100644
--- a/sound/soc/fsl/imx-pcm-dma.c
+++ b/sound/soc/fsl/imx-pcm-dma.c
@@ -154,26 +154,7 @@
 	.pcm_free	= imx_pcm_free,
 };
 
-static int imx_soc_platform_probe(struct platform_device *pdev)
+int imx_pcm_dma_init(struct platform_device *pdev)
 {
 	return snd_soc_register_platform(&pdev->dev, &imx_soc_platform_mx2);
 }
-
-static int imx_soc_platform_remove(struct platform_device *pdev)
-{
-	snd_soc_unregister_platform(&pdev->dev);
-	return 0;
-}
-
-static struct platform_driver imx_pcm_driver = {
-	.driver = {
-			.name = "imx-pcm-audio",
-			.owner = THIS_MODULE,
-	},
-	.probe = imx_soc_platform_probe,
-	.remove = imx_soc_platform_remove,
-};
-
-module_platform_driver(imx_pcm_driver);
-MODULE_LICENSE("GPL");
-MODULE_ALIAS("platform:imx-pcm-audio");
diff --git a/sound/soc/fsl/imx-pcm-fiq.c b/sound/soc/fsl/imx-pcm-fiq.c
index 5ec362a..920f945 100644
--- a/sound/soc/fsl/imx-pcm-fiq.c
+++ b/sound/soc/fsl/imx-pcm-fiq.c
@@ -281,7 +281,7 @@
 	.pcm_free	= imx_pcm_fiq_free,
 };
 
-static int imx_soc_platform_probe(struct platform_device *pdev)
+int imx_pcm_fiq_init(struct platform_device *pdev)
 {
 	struct imx_ssi *ssi = platform_get_drvdata(pdev);
 	int ret;
@@ -314,23 +314,3 @@
 
 	return ret;
 }
-
-static int imx_soc_platform_remove(struct platform_device *pdev)
-{
-	snd_soc_unregister_platform(&pdev->dev);
-	return 0;
-}
-
-static struct platform_driver imx_pcm_driver = {
-	.driver = {
-			.name = "imx-fiq-pcm-audio",
-			.owner = THIS_MODULE,
-	},
-
-	.probe = imx_soc_platform_probe,
-	.remove = imx_soc_platform_remove,
-};
-
-module_platform_driver(imx_pcm_driver);
-
-MODULE_LICENSE("GPL");
diff --git a/sound/soc/fsl/imx-pcm.c b/sound/soc/fsl/imx-pcm.c
index d5cd9ef..0d0625b 100644
--- a/sound/soc/fsl/imx-pcm.c
+++ b/sound/soc/fsl/imx-pcm.c
@@ -104,6 +104,38 @@
 }
 EXPORT_SYMBOL_GPL(imx_pcm_free);
 
+static int imx_pcm_probe(struct platform_device *pdev)
+{
+	if (strcmp(pdev->id_entry->name, "imx-fiq-pcm-audio") == 0)
+		return imx_pcm_fiq_init(pdev);
+
+	return imx_pcm_dma_init(pdev);
+}
+
+static int imx_pcm_remove(struct platform_device *pdev)
+{
+	snd_soc_unregister_platform(&pdev->dev);
+	return 0;
+}
+
+static struct platform_device_id imx_pcm_devtype[] = {
+	{ .name = "imx-pcm-audio", },
+	{ .name = "imx-fiq-pcm-audio", },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(platform, imx_pcm_devtype);
+
+static struct platform_driver imx_pcm_driver = {
+	.driver = {
+			.name = "imx-pcm",
+			.owner = THIS_MODULE,
+	},
+	.id_table = imx_pcm_devtype,
+	.probe = imx_pcm_probe,
+	.remove = imx_pcm_remove,
+};
+module_platform_driver(imx_pcm_driver);
+
 MODULE_DESCRIPTION("Freescale i.MX PCM driver");
 MODULE_AUTHOR("Sascha Hauer <s.hauer@pengutronix.de>");
 MODULE_LICENSE("GPL");
diff --git a/sound/soc/fsl/imx-pcm.h b/sound/soc/fsl/imx-pcm.h
index 83c0ed7..5ae13a1 100644
--- a/sound/soc/fsl/imx-pcm.h
+++ b/sound/soc/fsl/imx-pcm.h
@@ -30,4 +30,22 @@
 int imx_pcm_new(struct snd_soc_pcm_runtime *rtd);
 void imx_pcm_free(struct snd_pcm *pcm);
 
+#ifdef CONFIG_SND_SOC_IMX_PCM_DMA
+int imx_pcm_dma_init(struct platform_device *pdev);
+#else
+static inline int imx_pcm_dma_init(struct platform_device *pdev)
+{
+	return -ENODEV;
+}
+#endif
+
+#ifdef CONFIG_SND_SOC_IMX_PCM_FIQ
+int imx_pcm_fiq_init(struct platform_device *pdev);
+#else
+static inline int imx_pcm_fiq_init(struct platform_device *pdev)
+{
+	return -ENODEV;
+}
+#endif
+
 #endif /* _IMX_PCM_H */
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 1e36bc8..258acad 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -1023,7 +1023,7 @@
 
 	if (SND_SOC_DAPM_EVENT_ON(event)) {
 		if (w->invert & SND_SOC_DAPM_REGULATOR_BYPASS) {
-			ret = regulator_allow_bypass(w->regulator, true);
+			ret = regulator_allow_bypass(w->regulator, false);
 			if (ret != 0)
 				dev_warn(w->dapm->dev,
 					 "ASoC: Failed to bypass %s: %d\n",
@@ -1033,7 +1033,7 @@
 		return regulator_enable(w->regulator);
 	} else {
 		if (w->invert & SND_SOC_DAPM_REGULATOR_BYPASS) {
-			ret = regulator_allow_bypass(w->regulator, false);
+			ret = regulator_allow_bypass(w->regulator, true);
 			if (ret != 0)
 				dev_warn(w->dapm->dev,
 					 "ASoC: Failed to unbypass %s: %d\n",
@@ -3039,6 +3039,14 @@
 				w->name, ret);
 			return NULL;
 		}
+
+		if (w->invert & SND_SOC_DAPM_REGULATOR_BYPASS) {
+			ret = regulator_allow_bypass(w->regulator, true);
+			if (ret != 0)
+				dev_warn(w->dapm->dev,
+					 "ASoC: Failed to unbypass %s: %d\n",
+					 w->name, ret);
+		}
 		break;
 	case snd_soc_dapm_clock_supply:
 #ifdef CONFIG_CLKDEV_LOOKUP
diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
index ed4d89c..e90daf8 100644
--- a/sound/usb/mixer.c
+++ b/sound/usb/mixer.c
@@ -1331,16 +1331,23 @@
 		}
 		channels = (hdr->bLength - 7) / csize - 1;
 		bmaControls = hdr->bmaControls;
+		if (hdr->bLength < 7 + csize) {
+			snd_printk(KERN_ERR "usbaudio: unit %u: "
+				   "invalid UAC_FEATURE_UNIT descriptor\n",
+				   unitid);
+			return -EINVAL;
+		}
 	} else {
 		struct uac2_feature_unit_descriptor *ftr = _ftr;
 		csize = 4;
 		channels = (hdr->bLength - 6) / 4 - 1;
 		bmaControls = ftr->bmaControls;
-	}
-
-	if (hdr->bLength < 7 || !csize || hdr->bLength < 7 + csize) {
-		snd_printk(KERN_ERR "usbaudio: unit %u: invalid UAC_FEATURE_UNIT descriptor\n", unitid);
-		return -EINVAL;
+		if (hdr->bLength < 6 + csize) {
+			snd_printk(KERN_ERR "usbaudio: unit %u: "
+				   "invalid UAC_FEATURE_UNIT descriptor\n",
+				   unitid);
+			return -EINVAL;
+		}
 	}
 
 	/* parse the source unit */
diff --git a/tools/Makefile b/tools/Makefile
index 1f9a529..798fa0e 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -15,7 +15,7 @@
 	@echo '  x86_energy_perf_policy - Intel energy policy tool'
 	@echo ''
 	@echo 'You can do:'
-	@echo ' $$ make -C tools/<tool>_install'
+	@echo ' $$ make -C tools/ <tool>_install'
 	@echo ''
 	@echo '  from the kernel command line to build and install one of'
 	@echo '  the tools above'
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 5a824e3..82b0606 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -13,8 +13,7 @@
  * GNU Lesser General Public License for more details.
  *
  * You should have received a copy of the GNU Lesser General Public
- * License along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
  *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  *
@@ -1224,6 +1223,34 @@
 	return 0;
 }
 
+static unsigned int type_size(const char *name)
+{
+	/* This covers all FIELD_IS_STRING types. */
+	static struct {
+		const char *type;
+		unsigned int size;
+	} table[] = {
+		{ "u8",   1 },
+		{ "u16",  2 },
+		{ "u32",  4 },
+		{ "u64",  8 },
+		{ "s8",   1 },
+		{ "s16",  2 },
+		{ "s32",  4 },
+		{ "s64",  8 },
+		{ "char", 1 },
+		{ },
+	};
+	int i;
+
+	for (i = 0; table[i].type; i++) {
+		if (!strcmp(table[i].type, name))
+			return table[i].size;
+	}
+
+	return 0;
+}
+
 static int event_read_fields(struct event_format *event, struct format_field **fields)
 {
 	struct format_field *field = NULL;
@@ -1233,6 +1260,8 @@
 	int count = 0;
 
 	do {
+		unsigned int size_dynamic = 0;
+
 		type = read_token(&token);
 		if (type == EVENT_NEWLINE) {
 			free_token(token);
@@ -1391,6 +1420,7 @@
 				field->type = new_type;
 				strcat(field->type, " ");
 				strcat(field->type, field->name);
+				size_dynamic = type_size(field->name);
 				free_token(field->name);
 				strcat(field->type, brackets);
 				field->name = token;
@@ -1463,7 +1493,8 @@
 			if (read_expect_type(EVENT_ITEM, &token))
 				goto fail;
 
-			/* add signed type */
+			if (strtoul(token, NULL, 0))
+				field->flags |= FIELD_IS_SIGNED;
 
 			free_token(token);
 			if (read_expected(EVENT_OP, ";") < 0)
@@ -1478,10 +1509,14 @@
 		if (field->flags & FIELD_IS_ARRAY) {
 			if (field->arraylen)
 				field->elementsize = field->size / field->arraylen;
+			else if (field->flags & FIELD_IS_DYNAMIC)
+				field->elementsize = size_dynamic;
 			else if (field->flags & FIELD_IS_STRING)
 				field->elementsize = 1;
-			else
-				field->elementsize = event->pevent->long_size;
+			else if (field->flags & FIELD_IS_LONG)
+				field->elementsize = event->pevent ?
+						     event->pevent->long_size :
+						     sizeof(long);
 		} else
 			field->elementsize = field->size;
 
@@ -1785,6 +1820,8 @@
 		   strcmp(token, "/") == 0 ||
 		   strcmp(token, "<") == 0 ||
 		   strcmp(token, ">") == 0 ||
+		   strcmp(token, "<=") == 0 ||
+		   strcmp(token, ">=") == 0 ||
 		   strcmp(token, "==") == 0 ||
 		   strcmp(token, "!=") == 0) {
 
@@ -2481,7 +2518,7 @@
 
 	free_token(token);
 	arg = alloc_arg();
-	if (!field) {
+	if (!arg) {
 		do_warning("%s: not enough memory!", __func__);
 		*tok = NULL;
 		return EVENT_ERROR;
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 24a4bba..7be7e89 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -13,8 +13,7 @@
  * GNU Lesser General Public License for more details.
  *
  * You should have received a copy of the GNU Lesser General Public
- * License along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
  *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
diff --git a/tools/lib/traceevent/event-utils.h b/tools/lib/traceevent/event-utils.h
index bc07500..e76c9ac 100644
--- a/tools/lib/traceevent/event-utils.h
+++ b/tools/lib/traceevent/event-utils.h
@@ -13,8 +13,7 @@
  * GNU Lesser General Public License for more details.
  *
  * You should have received a copy of the GNU Lesser General Public
- * License along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
  *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index 5ea4326..2500e75 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -13,8 +13,7 @@
  * GNU Lesser General Public License for more details.
  *
  * You should have received a copy of the GNU Lesser General Public
- * License along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
  *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
diff --git a/tools/lib/traceevent/parse-utils.c b/tools/lib/traceevent/parse-utils.c
index f023a13..bba701c 100644
--- a/tools/lib/traceevent/parse-utils.c
+++ b/tools/lib/traceevent/parse-utils.c
@@ -1,3 +1,22 @@
+/*
+ * Copyright (C) 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * 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 Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
diff --git a/tools/lib/traceevent/trace-seq.c b/tools/lib/traceevent/trace-seq.c
index b1ccc92..a57db80 100644
--- a/tools/lib/traceevent/trace-seq.c
+++ b/tools/lib/traceevent/trace-seq.c
@@ -13,8 +13,7 @@
  * GNU Lesser General Public License for more details.
  *
  * You should have received a copy of the GNU Lesser General Public
- * License along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
  *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile
index ef6d22e..eb30044 100644
--- a/tools/perf/Documentation/Makefile
+++ b/tools/perf/Documentation/Makefile
@@ -222,10 +222,14 @@
 #install-html: html
 #	'$(SHELL_PATH_SQ)' ./install-webdoc.sh $(DESTDIR)$(htmldir)
 
+ifneq ($(MAKECMDGOALS),clean)
+ifneq ($(MAKECMDGOALS),tags)
 $(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
 	$(QUIET_SUBDIR0)../ $(QUIET_SUBDIR1) $(OUTPUT)PERF-VERSION-FILE
 
 -include $(OUTPUT)PERF-VERSION-FILE
+endif
+endif
 
 #
 # Determine "include::" file references in asciidoc files.
diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index c8ffd9f..5ad07ef4 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -61,11 +61,13 @@
 
 --stdio:: Use the stdio interface.
 
---tui:: Use the TUI interface Use of --tui requires a tty, if one is not
+--tui:: Use the TUI interface. Use of --tui requires a tty, if one is not
 	present, as when piping to other commands, the stdio interface is
 	used. This interfaces starts by centering on the line with more
 	samples, TAB/UNTAB cycles through the lines with more samples.
 
+--gtk:: Use the GTK interface.
+
 -C::
 --cpu:: Only report samples for the list of CPUs provided. Multiple CPUs can
 	be provided as a comma-separated list with no space: 0,1. Ranges of
@@ -88,6 +90,9 @@
 --objdump=<path>::
         Path to objdump binary.
 
+--skip-missing::
+	Skip symbols that cannot be annotated.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1]
diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt
index c105770..e9a8349 100644
--- a/tools/perf/Documentation/perf-buildid-cache.txt
+++ b/tools/perf/Documentation/perf-buildid-cache.txt
@@ -24,6 +24,13 @@
 -r::
 --remove=::
         Remove specified file from the cache.
+-M::
+--missing=:: 
+	List missing build ids in the cache for the specified file.
+-u::
+--update::
+	Update specified file of the cache. It can be used to update kallsyms
+	kernel dso to vmlinux in order to support annotation.
 -v::
 --verbose::
 	Be more verbose.
diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt
index 194f37d..5b3123d 100644
--- a/tools/perf/Documentation/perf-diff.txt
+++ b/tools/perf/Documentation/perf-diff.txt
@@ -22,10 +22,6 @@
 
 OPTIONS
 -------
--M::
---displacement::
-        Show position displacement relative to baseline.
-
 -D::
 --dump-raw-trace::
         Dump raw trace in ASCII.
diff --git a/tools/perf/Documentation/perf-evlist.txt b/tools/perf/Documentation/perf-evlist.txt
index 1521734..1ceb370 100644
--- a/tools/perf/Documentation/perf-evlist.txt
+++ b/tools/perf/Documentation/perf-evlist.txt
@@ -28,6 +28,10 @@
 --verbose=::
 	Show all fields.
 
+-g::
+--group::
+	Show event group information.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-list[1],
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index f4d91be..02284a0 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -57,11 +57,44 @@
 
 -s::
 --sort=::
-	Sort by key(s): pid, comm, dso, symbol, parent, srcline.
+	Sort histogram entries by given key(s) - multiple keys can be specified
+	in CSV format.  Following sort keys are available:
+	pid, comm, dso, symbol, parent, cpu, srcline.
+
+	Each key has following meaning:
+
+	- comm: command (name) of the task which can be read via /proc/<pid>/comm
+	- pid: command and tid of the task
+	- dso: name of library or module executed at the time of sample
+	- symbol: name of function executed at the time of sample
+	- parent: name of function matched to the parent regex filter. Unmatched
+	entries are displayed as "[other]".
+	- cpu: cpu number the task ran at the time of sample
+	- srcline: filename and line number executed at the time of sample.  The
+	DWARF debuggin info must be provided.
+
+	By default, comm, dso and symbol keys are used.
+	(i.e. --sort comm,dso,symbol)
+
+	If --branch-stack option is used, following sort keys are also
+	available:
+	dso_from, dso_to, symbol_from, symbol_to, mispredict.
+
+	- dso_from: name of library or module branched from
+	- dso_to: name of library or module branched to
+	- symbol_from: name of function branched from
+	- symbol_to: name of function branched to
+	- mispredict: "N" for predicted branch, "Y" for mispredicted branch
+
+	And default sort keys are changed to comm, dso_from, symbol_from, dso_to
+	and symbol_to, see '--branch-stack'.
 
 -p::
 --parent=<regex>::
-        regex filter to identify parent, see: '--sort parent'
+        A regex filter to identify parent. The parent is a caller of this
+	function and searched through the callchain, thus it requires callchain
+	information recorded. The pattern is in the exteneded regex format and
+	defaults to "\^sys_|^do_page_fault", see '--sort parent'.
 
 -x::
 --exclude-other::
@@ -74,7 +107,6 @@
 
 -t::
 --field-separator=::
-
 	Use a special separator character and don't pad with spaces, replacing
 	all occurrences of this separator in symbol names (and other output)
 	with a '.' character, that thus it's the only non valid separator.
@@ -171,6 +203,9 @@
 --objdump=<path>::
         Path to objdump binary.
 
+--group::
+	Show event group information together.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-annotate[1]
diff --git a/tools/perf/Documentation/perf-script-python.txt b/tools/perf/Documentation/perf-script-python.txt
index a4027f2..9f1f054 100644
--- a/tools/perf/Documentation/perf-script-python.txt
+++ b/tools/perf/Documentation/perf-script-python.txt
@@ -336,7 +336,6 @@
 ----
 root@tropicana:~# perf script -l
 List of available trace scripts:
-  workqueue-stats                      workqueue stats (ins/exe/create/destroy)
   wakeup-latency                       system-wide min/max/avg wakeup latency
   rw-by-file <comm>                    r/w activity for a program, by file
   rw-by-pid                            system-wide r/w activity
@@ -402,7 +401,6 @@
 ----
 root@tropicana:~# perf script -l
 List of available trace scripts:
-  workqueue-stats                      workqueue stats (ins/exe/create/destroy)
   wakeup-latency                       system-wide min/max/avg wakeup latency
   rw-by-file <comm>                    r/w activity for a program, by file
   rw-by-pid                            system-wide r/w activity
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index cf0c310..faf4f4f 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -114,6 +114,17 @@
 
 perf stat --repeat 10 --null --sync --pre 'make -s O=defconfig-build/clean' -- make -s -j64 O=defconfig-build/ bzImage
 
+-I msecs::
+--interval-print msecs::
+	Print count deltas every N milliseconds (minimum: 100ms)
+	example: perf stat -I 1000 -e cycles -a sleep 5
+
+--aggr-socket::
+Aggregate counts per processor socket for system-wide mode measurements.  This
+is a useful mode to detect imbalance between sockets.  To enable this mode,
+use --aggr-socket in addition to -a. (system-wide).  The output includes the
+socket number and the number of online processors on that socket. This is
+useful to gauge the amount of aggregation.
 
 EXAMPLES
 --------
diff --git a/tools/perf/Documentation/perf-test.txt b/tools/perf/Documentation/perf-test.txt
index b24ac40..d1d3e5121 100644
--- a/tools/perf/Documentation/perf-test.txt
+++ b/tools/perf/Documentation/perf-test.txt
@@ -23,6 +23,10 @@
 
 OPTIONS
 -------
+-s::
+--skip::
+	Tests to skip (comma separater numeric list).
+
 -v::
 --verbose::
 	Be more verbose.
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 5b80d84..a414bc9 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -60,7 +60,7 @@
 
 -i::
 --inherit::
-	Child tasks inherit counters, only makes sens with -p option.
+	Child tasks do not inherit counters.
 
 -k <path>::
 --vmlinux=<path>::
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 8ab05e54..a2108ca 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -47,10 +47,11 @@
 # backtrace post unwind.
 #
 # Define NO_BACKTRACE if you do not want stack backtrace debug feature
+#
+# Define NO_LIBNUMA if you do not want numa perf benchmark
 
 $(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
 	@$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
--include $(OUTPUT)PERF-VERSION-FILE
 
 uname_M := $(shell uname -m 2>/dev/null || echo not)
 
@@ -148,13 +149,25 @@
 MKDIR = mkdir
 FIND = find
 INSTALL = install
+FLEX = flex
+BISON= bison
 
 # sparse is architecture-neutral, which means that we need to tell it
 # explicitly what architecture to check for. Fix this up for yours..
 SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__
 
+ifneq ($(MAKECMDGOALS),clean)
+ifneq ($(MAKECMDGOALS),tags)
 -include config/feature-tests.mak
 
+ifeq ($(call get-executable,$(FLEX)),)
+	dummy := $(error Error: $(FLEX) is missing on this system, please install it)
+endif
+
+ifeq ($(call get-executable,$(BISON)),)
+	dummy := $(error Error: $(BISON) is missing on this system, please install it)
+endif
+
 ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -fstack-protector-all,-fstack-protector-all),y)
 	CFLAGS := $(CFLAGS) -fstack-protector-all
 endif
@@ -206,6 +219,8 @@
 	EXTLIBS := $(filter-out -lpthread,$(EXTLIBS))
 	BASIC_CFLAGS += -I.
 endif
+endif # MAKECMDGOALS != tags
+endif # MAKECMDGOALS != clean
 
 # Guard against environment variables
 BUILTIN_OBJS =
@@ -230,11 +245,19 @@
 LIBTRACEEVENT = $(TE_PATH)libtraceevent.a
 TE_LIB := -L$(TE_PATH) -ltraceevent
 
+export LIBTRACEEVENT
+
+# python extension build directories
+PYTHON_EXTBUILD     := $(OUTPUT)python_ext_build/
+PYTHON_EXTBUILD_LIB := $(PYTHON_EXTBUILD)lib/
+PYTHON_EXTBUILD_TMP := $(PYTHON_EXTBUILD)tmp/
+export PYTHON_EXTBUILD_LIB PYTHON_EXTBUILD_TMP
+
+python-clean := rm -rf $(PYTHON_EXTBUILD) $(OUTPUT)python/perf.so
+
 PYTHON_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources)
 PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py
 
-export LIBTRACEEVENT
-
 $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS)
 	$(QUIET_GEN)CFLAGS='$(BASIC_CFLAGS)' $(PYTHON_WORD) util/setup.py \
 	  --quiet build_ext; \
@@ -269,20 +292,17 @@
 
 export PERL_PATH
 
-FLEX = flex
-BISON= bison
-
 $(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c
 	$(QUIET_FLEX)$(FLEX) --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) -t util/parse-events.l > $(OUTPUT)util/parse-events-flex.c
 
 $(OUTPUT)util/parse-events-bison.c: util/parse-events.y
-	$(QUIET_BISON)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $(OUTPUT)util/parse-events-bison.c
+	$(QUIET_BISON)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $(OUTPUT)util/parse-events-bison.c -p parse_events_
 
 $(OUTPUT)util/pmu-flex.c: util/pmu.l $(OUTPUT)util/pmu-bison.c
 	$(QUIET_FLEX)$(FLEX) --header-file=$(OUTPUT)util/pmu-flex.h -t util/pmu.l > $(OUTPUT)util/pmu-flex.c
 
 $(OUTPUT)util/pmu-bison.c: util/pmu.y
-	$(QUIET_BISON)$(BISON) -v util/pmu.y -d -o $(OUTPUT)util/pmu-bison.c
+	$(QUIET_BISON)$(BISON) -v util/pmu.y -d -o $(OUTPUT)util/pmu-bison.c -p perf_pmu_
 
 $(OUTPUT)util/parse-events.o: $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c
 $(OUTPUT)util/pmu.o: $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c
@@ -378,8 +398,11 @@
 LIB_H += util/intlist.h
 LIB_H += util/perf_regs.h
 LIB_H += util/unwind.h
-LIB_H += ui/helpline.h
 LIB_H += util/vdso.h
+LIB_H += ui/helpline.h
+LIB_H += ui/progress.h
+LIB_H += ui/util.h
+LIB_H += ui/ui.h
 
 LIB_OBJS += $(OUTPUT)util/abspath.o
 LIB_OBJS += $(OUTPUT)util/alias.o
@@ -453,6 +476,7 @@
 LIB_OBJS += $(OUTPUT)ui/setup.o
 LIB_OBJS += $(OUTPUT)ui/helpline.o
 LIB_OBJS += $(OUTPUT)ui/progress.o
+LIB_OBJS += $(OUTPUT)ui/util.o
 LIB_OBJS += $(OUTPUT)ui/hist.o
 LIB_OBJS += $(OUTPUT)ui/stdio/hist.o
 
@@ -471,7 +495,8 @@
 LIB_OBJS += $(OUTPUT)tests/evsel-roundtrip-name.o
 LIB_OBJS += $(OUTPUT)tests/evsel-tp-sched.o
 LIB_OBJS += $(OUTPUT)tests/pmu.o
-LIB_OBJS += $(OUTPUT)tests/util.o
+LIB_OBJS += $(OUTPUT)tests/hists_link.o
+LIB_OBJS += $(OUTPUT)tests/python-use.o
 
 BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
 BUILTIN_OBJS += $(OUTPUT)builtin-bench.o
@@ -510,14 +535,13 @@
 #
 # Platform specific tweaks
 #
+ifneq ($(MAKECMDGOALS),clean)
+ifneq ($(MAKECMDGOALS),tags)
 
 # We choose to avoid "if .. else if .. else .. endif endif"
 # because maintaining the nesting to match is a pain.  If
 # we had "elif" things would have been much nicer...
 
--include config.mak.autogen
--include config.mak
-
 ifdef NO_LIBELF
 	NO_DWARF := 1
 	NO_DEMANGLE := 1
@@ -557,6 +581,11 @@
 endif # SOURCE_LIBELF
 endif # NO_LIBELF
 
+# There's only x86 (both 32 and 64) support for CFI unwind so far
+ifneq ($(ARCH),x86)
+	NO_LIBUNWIND := 1
+endif
+
 ifndef NO_LIBUNWIND
 # for linking with debug library, run like:
 # make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/
@@ -646,7 +675,6 @@
 		LIB_OBJS += $(OUTPUT)ui/browsers/hists.o
 		LIB_OBJS += $(OUTPUT)ui/browsers/map.o
 		LIB_OBJS += $(OUTPUT)ui/browsers/scripts.o
-		LIB_OBJS += $(OUTPUT)ui/util.o
 		LIB_OBJS += $(OUTPUT)ui/tui/setup.o
 		LIB_OBJS += $(OUTPUT)ui/tui/util.o
 		LIB_OBJS += $(OUTPUT)ui/tui/helpline.o
@@ -655,9 +683,6 @@
 		LIB_H += ui/browsers/map.h
 		LIB_H += ui/keysyms.h
 		LIB_H += ui/libslang.h
-		LIB_H += ui/progress.h
-		LIB_H += ui/util.h
-		LIB_H += ui/ui.h
 	endif
 endif
 
@@ -673,14 +698,12 @@
 		BASIC_CFLAGS += $(shell pkg-config --cflags gtk+-2.0 2>/dev/null)
 		EXTLIBS += $(shell pkg-config --libs gtk+-2.0 2>/dev/null)
 		LIB_OBJS += $(OUTPUT)ui/gtk/browser.o
+		LIB_OBJS += $(OUTPUT)ui/gtk/hists.o
 		LIB_OBJS += $(OUTPUT)ui/gtk/setup.o
 		LIB_OBJS += $(OUTPUT)ui/gtk/util.o
 		LIB_OBJS += $(OUTPUT)ui/gtk/helpline.o
 		LIB_OBJS += $(OUTPUT)ui/gtk/progress.o
-		# Make sure that it'd be included only once.
-		ifeq ($(findstring -DNEWT_SUPPORT,$(BASIC_CFLAGS)),)
-			LIB_OBJS += $(OUTPUT)ui/util.o
-		endif
+		LIB_OBJS += $(OUTPUT)ui/gtk/annotate.o
 	endif
 endif
 
@@ -707,7 +730,7 @@
 define disable-python_code
   BASIC_CFLAGS += -DNO_LIBPYTHON
   $(if $(1),$(warning No $(1) was found))
-  $(warning Python support won't be built)
+  $(warning Python support will not be built)
 endef
 
 override PYTHON := \
@@ -715,19 +738,10 @@
 
 ifndef PYTHON
   $(call disable-python,python interpreter)
-  python-clean :=
 else
 
   PYTHON_WORD := $(call shell-wordify,$(PYTHON))
 
-  # python extension build directories
-  PYTHON_EXTBUILD     := $(OUTPUT)python_ext_build/
-  PYTHON_EXTBUILD_LIB := $(PYTHON_EXTBUILD)lib/
-  PYTHON_EXTBUILD_TMP := $(PYTHON_EXTBUILD)tmp/
-  export PYTHON_EXTBUILD_LIB PYTHON_EXTBUILD_TMP
-
-  python-clean := rm -rf $(PYTHON_EXTBUILD) $(OUTPUT)python/perf.so
-
   ifdef NO_LIBPYTHON
     $(call disable-python)
   else
@@ -839,10 +853,24 @@
        endif
 endif
 
+ifndef NO_LIBNUMA
+	FLAGS_LIBNUMA = $(ALL_CFLAGS) $(ALL_LDFLAGS) -lnuma
+	ifneq ($(call try-cc,$(SOURCE_LIBNUMA),$(FLAGS_LIBNUMA),libnuma),y)
+		msg := $(warning No numa.h found, disables 'perf bench numa mem' benchmark, please install numa-libs-devel or libnuma-dev);
+	else
+		BASIC_CFLAGS += -DLIBNUMA_SUPPORT
+		BUILTIN_OBJS += $(OUTPUT)bench/numa.o
+		EXTLIBS += -lnuma
+	endif
+endif
+
 ifdef ASCIIDOC8
 	export ASCIIDOC8
 endif
 
+endif # MAKECMDGOALS != tags
+endif # MAKECMDGOALS != clean
+
 # Shell quote (do not use $(call) to accommodate ancient setups);
 
 ETC_PERFCONFIG_SQ = $(subst ','\'',$(ETC_PERFCONFIG))
@@ -884,7 +912,7 @@
 	$(STRIP) $(STRIP_OPTS) $(PROGRAMS) $(OUTPUT)perf
 
 $(OUTPUT)perf.o: perf.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -DPERF_VERSION='"$(PERF_VERSION)"' \
+	$(QUIET_CC)$(CC) -include $(OUTPUT)PERF-VERSION-FILE \
 		'-DPERF_HTML_PATH="$(htmldir_SQ)"' \
 		$(ALL_CFLAGS) -c $(filter %.c,$^) -o $@
 
@@ -948,7 +976,13 @@
 
 $(OUTPUT)tests/attr.o: tests/attr.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \
-		'-DBINDIR="$(bindir_SQ)"' \
+		'-DBINDIR="$(bindir_SQ)"' -DPYTHON='"$(PYTHON_WORD)"' \
+		$<
+
+$(OUTPUT)tests/python-use.o: tests/python-use.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \
+		-DPYTHONPATH='"$(OUTPUT)python"' \
+		-DPYTHON='"$(PYTHON_WORD)"' \
 		$<
 
 $(OUTPUT)util/config.o: util/config.c $(OUTPUT)PERF-CFLAGS
@@ -1099,7 +1133,7 @@
 endif
 perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir))
 
-install: all try-install-man
+install-bin: all
 	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'
 	$(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)'
 	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'
@@ -1120,6 +1154,8 @@
 	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'
 	$(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'
 
+install: install-bin try-install-man
+
 install-python_ext:
 	$(PYTHON_WORD) util/setup.py --quiet install --root='/$(DESTDIR_SQ)'
 
diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c
index 3e975cb..aacef07 100644
--- a/tools/perf/arch/common.c
+++ b/tools/perf/arch/common.c
@@ -155,6 +155,7 @@
 		if (lookup_path(buf))
 			goto out;
 		free(buf);
+		buf = NULL;
 	}
 
 	if (!strcmp(arch, "arm"))
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index 8f89998..a5223e6 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -1,6 +1,7 @@
 #ifndef BENCH_H
 #define BENCH_H
 
+extern int bench_numa(int argc, const char **argv, const char *prefix);
 extern int bench_sched_messaging(int argc, const char **argv, const char *prefix);
 extern int bench_sched_pipe(int argc, const char **argv, const char *prefix);
 extern int bench_mem_memcpy(int argc, const char **argv,
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
new file mode 100644
index 0000000..30d1c32
--- /dev/null
+++ b/tools/perf/bench/numa.c
@@ -0,0 +1,1731 @@
+/*
+ * numa.c
+ *
+ * numa: Simulate NUMA-sensitive workload and measure their NUMA performance
+ */
+
+#include "../perf.h"
+#include "../builtin.h"
+#include "../util/util.h"
+#include "../util/parse-options.h"
+
+#include "bench.h"
+
+#include <errno.h>
+#include <sched.h>
+#include <stdio.h>
+#include <assert.h>
+#include <malloc.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <pthread.h>
+#include <sys/mman.h>
+#include <sys/time.h>
+#include <sys/wait.h>
+#include <sys/prctl.h>
+#include <sys/types.h>
+
+#include <numa.h>
+#include <numaif.h>
+
+/*
+ * Regular printout to the terminal, supressed if -q is specified:
+ */
+#define tprintf(x...) do { if (g && g->p.show_details >= 0) printf(x); } while (0)
+
+/*
+ * Debug printf:
+ */
+#define dprintf(x...) do { if (g && g->p.show_details >= 1) printf(x); } while (0)
+
+struct thread_data {
+	int			curr_cpu;
+	cpu_set_t		bind_cpumask;
+	int			bind_node;
+	u8			*process_data;
+	int			process_nr;
+	int			thread_nr;
+	int			task_nr;
+	unsigned int		loops_done;
+	u64			val;
+	u64			runtime_ns;
+	pthread_mutex_t		*process_lock;
+};
+
+/* Parameters set by options: */
+
+struct params {
+	/* Startup synchronization: */
+	bool			serialize_startup;
+
+	/* Task hierarchy: */
+	int			nr_proc;
+	int			nr_threads;
+
+	/* Working set sizes: */
+	const char		*mb_global_str;
+	const char		*mb_proc_str;
+	const char		*mb_proc_locked_str;
+	const char		*mb_thread_str;
+
+	double			mb_global;
+	double			mb_proc;
+	double			mb_proc_locked;
+	double			mb_thread;
+
+	/* Access patterns to the working set: */
+	bool			data_reads;
+	bool			data_writes;
+	bool			data_backwards;
+	bool			data_zero_memset;
+	bool			data_rand_walk;
+	u32			nr_loops;
+	u32			nr_secs;
+	u32			sleep_usecs;
+
+	/* Working set initialization: */
+	bool			init_zero;
+	bool			init_random;
+	bool			init_cpu0;
+
+	/* Misc options: */
+	int			show_details;
+	int			run_all;
+	int			thp;
+
+	long			bytes_global;
+	long			bytes_process;
+	long			bytes_process_locked;
+	long			bytes_thread;
+
+	int			nr_tasks;
+	bool			show_quiet;
+
+	bool			show_convergence;
+	bool			measure_convergence;
+
+	int			perturb_secs;
+	int			nr_cpus;
+	int			nr_nodes;
+
+	/* Affinity options -C and -N: */
+	char			*cpu_list_str;
+	char			*node_list_str;
+};
+
+
+/* Global, read-writable area, accessible to all processes and threads: */
+
+struct global_info {
+	u8			*data;
+
+	pthread_mutex_t		startup_mutex;
+	int			nr_tasks_started;
+
+	pthread_mutex_t		startup_done_mutex;
+
+	pthread_mutex_t		start_work_mutex;
+	int			nr_tasks_working;
+
+	pthread_mutex_t		stop_work_mutex;
+	u64			bytes_done;
+
+	struct thread_data	*threads;
+
+	/* Convergence latency measurement: */
+	bool			all_converged;
+	bool			stop_work;
+
+	int			print_once;
+
+	struct params		p;
+};
+
+static struct global_info	*g = NULL;
+
+static int parse_cpus_opt(const struct option *opt, const char *arg, int unset);
+static int parse_nodes_opt(const struct option *opt, const char *arg, int unset);
+
+struct params p0;
+
+static const struct option options[] = {
+	OPT_INTEGER('p', "nr_proc"	, &p0.nr_proc,		"number of processes"),
+	OPT_INTEGER('t', "nr_threads"	, &p0.nr_threads,	"number of threads per process"),
+
+	OPT_STRING('G', "mb_global"	, &p0.mb_global_str,	"MB", "global  memory (MBs)"),
+	OPT_STRING('P', "mb_proc"	, &p0.mb_proc_str,	"MB", "process memory (MBs)"),
+	OPT_STRING('L', "mb_proc_locked", &p0.mb_proc_locked_str,"MB", "process serialized/locked memory access (MBs), <= process_memory"),
+	OPT_STRING('T', "mb_thread"	, &p0.mb_thread_str,	"MB", "thread  memory (MBs)"),
+
+	OPT_UINTEGER('l', "nr_loops"	, &p0.nr_loops,		"max number of loops to run"),
+	OPT_UINTEGER('s', "nr_secs"	, &p0.nr_secs,		"max number of seconds to run"),
+	OPT_UINTEGER('u', "usleep"	, &p0.sleep_usecs,	"usecs to sleep per loop iteration"),
+
+	OPT_BOOLEAN('R', "data_reads"	, &p0.data_reads,	"access the data via writes (can be mixed with -W)"),
+	OPT_BOOLEAN('W', "data_writes"	, &p0.data_writes,	"access the data via writes (can be mixed with -R)"),
+	OPT_BOOLEAN('B', "data_backwards", &p0.data_backwards,	"access the data backwards as well"),
+	OPT_BOOLEAN('Z', "data_zero_memset", &p0.data_zero_memset,"access the data via glibc bzero only"),
+	OPT_BOOLEAN('r', "data_rand_walk", &p0.data_rand_walk,	"access the data with random (32bit LFSR) walk"),
+
+
+	OPT_BOOLEAN('z', "init_zero"	, &p0.init_zero,	"bzero the initial allocations"),
+	OPT_BOOLEAN('I', "init_random"	, &p0.init_random,	"randomize the contents of the initial allocations"),
+	OPT_BOOLEAN('0', "init_cpu0"	, &p0.init_cpu0,	"do the initial allocations on CPU#0"),
+	OPT_INTEGER('x', "perturb_secs", &p0.perturb_secs,	"perturb thread 0/0 every X secs, to test convergence stability"),
+
+	OPT_INCR   ('d', "show_details"	, &p0.show_details,	"Show details"),
+	OPT_INCR   ('a', "all"		, &p0.run_all,		"Run all tests in the suite"),
+	OPT_INTEGER('H', "thp"		, &p0.thp,		"MADV_NOHUGEPAGE < 0 < MADV_HUGEPAGE"),
+	OPT_BOOLEAN('c', "show_convergence", &p0.show_convergence, "show convergence details"),
+	OPT_BOOLEAN('m', "measure_convergence",	&p0.measure_convergence, "measure convergence latency"),
+	OPT_BOOLEAN('q', "quiet"	, &p0.show_quiet,	"bzero the initial allocations"),
+	OPT_BOOLEAN('S', "serialize-startup", &p0.serialize_startup,"serialize thread startup"),
+
+	/* Special option string parsing callbacks: */
+        OPT_CALLBACK('C', "cpus", NULL, "cpu[,cpu2,...cpuN]",
+			"bind the first N tasks to these specific cpus (the rest is unbound)",
+			parse_cpus_opt),
+        OPT_CALLBACK('M', "memnodes", NULL, "node[,node2,...nodeN]",
+			"bind the first N tasks to these specific memory nodes (the rest is unbound)",
+			parse_nodes_opt),
+	OPT_END()
+};
+
+static const char * const bench_numa_usage[] = {
+	"perf bench numa <options>",
+	NULL
+};
+
+static const char * const numa_usage[] = {
+	"perf bench numa mem [<options>]",
+	NULL
+};
+
+static cpu_set_t bind_to_cpu(int target_cpu)
+{
+	cpu_set_t orig_mask, mask;
+	int ret;
+
+	ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask);
+	BUG_ON(ret);
+
+	CPU_ZERO(&mask);
+
+	if (target_cpu == -1) {
+		int cpu;
+
+		for (cpu = 0; cpu < g->p.nr_cpus; cpu++)
+			CPU_SET(cpu, &mask);
+	} else {
+		BUG_ON(target_cpu < 0 || target_cpu >= g->p.nr_cpus);
+		CPU_SET(target_cpu, &mask);
+	}
+
+	ret = sched_setaffinity(0, sizeof(mask), &mask);
+	BUG_ON(ret);
+
+	return orig_mask;
+}
+
+static cpu_set_t bind_to_node(int target_node)
+{
+	int cpus_per_node = g->p.nr_cpus/g->p.nr_nodes;
+	cpu_set_t orig_mask, mask;
+	int cpu;
+	int ret;
+
+	BUG_ON(cpus_per_node*g->p.nr_nodes != g->p.nr_cpus);
+	BUG_ON(!cpus_per_node);
+
+	ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask);
+	BUG_ON(ret);
+
+	CPU_ZERO(&mask);
+
+	if (target_node == -1) {
+		for (cpu = 0; cpu < g->p.nr_cpus; cpu++)
+			CPU_SET(cpu, &mask);
+	} else {
+		int cpu_start = (target_node + 0) * cpus_per_node;
+		int cpu_stop  = (target_node + 1) * cpus_per_node;
+
+		BUG_ON(cpu_stop > g->p.nr_cpus);
+
+		for (cpu = cpu_start; cpu < cpu_stop; cpu++)
+			CPU_SET(cpu, &mask);
+	}
+
+	ret = sched_setaffinity(0, sizeof(mask), &mask);
+	BUG_ON(ret);
+
+	return orig_mask;
+}
+
+static void bind_to_cpumask(cpu_set_t mask)
+{
+	int ret;
+
+	ret = sched_setaffinity(0, sizeof(mask), &mask);
+	BUG_ON(ret);
+}
+
+static void mempol_restore(void)
+{
+	int ret;
+
+	ret = set_mempolicy(MPOL_DEFAULT, NULL, g->p.nr_nodes-1);
+
+	BUG_ON(ret);
+}
+
+static void bind_to_memnode(int node)
+{
+	unsigned long nodemask;
+	int ret;
+
+	if (node == -1)
+		return;
+
+	BUG_ON(g->p.nr_nodes > (int)sizeof(nodemask));
+	nodemask = 1L << node;
+
+	ret = set_mempolicy(MPOL_BIND, &nodemask, sizeof(nodemask)*8);
+	dprintf("binding to node %d, mask: %016lx => %d\n", node, nodemask, ret);
+
+	BUG_ON(ret);
+}
+
+#define HPSIZE (2*1024*1024)
+
+#define set_taskname(fmt...)				\
+do {							\
+	char name[20];					\
+							\
+	snprintf(name, 20, fmt);			\
+	prctl(PR_SET_NAME, name);			\
+} while (0)
+
+static u8 *alloc_data(ssize_t bytes0, int map_flags,
+		      int init_zero, int init_cpu0, int thp, int init_random)
+{
+	cpu_set_t orig_mask;
+	ssize_t bytes;
+	u8 *buf;
+	int ret;
+
+	if (!bytes0)
+		return NULL;
+
+	/* Allocate and initialize all memory on CPU#0: */
+	if (init_cpu0) {
+		orig_mask = bind_to_node(0);
+		bind_to_memnode(0);
+	}
+
+	bytes = bytes0 + HPSIZE;
+
+	buf = (void *)mmap(0, bytes, PROT_READ|PROT_WRITE, MAP_ANON|map_flags, -1, 0);
+	BUG_ON(buf == (void *)-1);
+
+	if (map_flags == MAP_PRIVATE) {
+		if (thp > 0) {
+			ret = madvise(buf, bytes, MADV_HUGEPAGE);
+			if (ret && !g->print_once) {
+				g->print_once = 1;
+				printf("WARNING: Could not enable THP - do: 'echo madvise > /sys/kernel/mm/transparent_hugepage/enabled'\n");
+			}
+		}
+		if (thp < 0) {
+			ret = madvise(buf, bytes, MADV_NOHUGEPAGE);
+			if (ret && !g->print_once) {
+				g->print_once = 1;
+				printf("WARNING: Could not disable THP: run a CONFIG_TRANSPARENT_HUGEPAGE kernel?\n");
+			}
+		}
+	}
+
+	if (init_zero) {
+		bzero(buf, bytes);
+	} else {
+		/* Initialize random contents, different in each word: */
+		if (init_random) {
+			u64 *wbuf = (void *)buf;
+			long off = rand();
+			long i;
+
+			for (i = 0; i < bytes/8; i++)
+				wbuf[i] = i + off;
+		}
+	}
+
+	/* Align to 2MB boundary: */
+	buf = (void *)(((unsigned long)buf + HPSIZE-1) & ~(HPSIZE-1));
+
+	/* Restore affinity: */
+	if (init_cpu0) {
+		bind_to_cpumask(orig_mask);
+		mempol_restore();
+	}
+
+	return buf;
+}
+
+static void free_data(void *data, ssize_t bytes)
+{
+	int ret;
+
+	if (!data)
+		return;
+
+	ret = munmap(data, bytes);
+	BUG_ON(ret);
+}
+
+/*
+ * Create a shared memory buffer that can be shared between processes, zeroed:
+ */
+static void * zalloc_shared_data(ssize_t bytes)
+{
+	return alloc_data(bytes, MAP_SHARED, 1, g->p.init_cpu0,  g->p.thp, g->p.init_random);
+}
+
+/*
+ * Create a shared memory buffer that can be shared between processes:
+ */
+static void * setup_shared_data(ssize_t bytes)
+{
+	return alloc_data(bytes, MAP_SHARED, 0, g->p.init_cpu0,  g->p.thp, g->p.init_random);
+}
+
+/*
+ * Allocate process-local memory - this will either be shared between
+ * threads of this process, or only be accessed by this thread:
+ */
+static void * setup_private_data(ssize_t bytes)
+{
+	return alloc_data(bytes, MAP_PRIVATE, 0, g->p.init_cpu0,  g->p.thp, g->p.init_random);
+}
+
+/*
+ * Return a process-shared (global) mutex:
+ */
+static void init_global_mutex(pthread_mutex_t *mutex)
+{
+	pthread_mutexattr_t attr;
+
+	pthread_mutexattr_init(&attr);
+	pthread_mutexattr_setpshared(&attr, PTHREAD_PROCESS_SHARED);
+	pthread_mutex_init(mutex, &attr);
+}
+
+static int parse_cpu_list(const char *arg)
+{
+	p0.cpu_list_str = strdup(arg);
+
+	dprintf("got CPU list: {%s}\n", p0.cpu_list_str);
+
+	return 0;
+}
+
+static void parse_setup_cpu_list(void)
+{
+	struct thread_data *td;
+	char *str0, *str;
+	int t;
+
+	if (!g->p.cpu_list_str)
+		return;
+
+	dprintf("g->p.nr_tasks: %d\n", g->p.nr_tasks);
+
+	str0 = str = strdup(g->p.cpu_list_str);
+	t = 0;
+
+	BUG_ON(!str);
+
+	tprintf("# binding tasks to CPUs:\n");
+	tprintf("#  ");
+
+	while (true) {
+		int bind_cpu, bind_cpu_0, bind_cpu_1;
+		char *tok, *tok_end, *tok_step, *tok_len, *tok_mul;
+		int bind_len;
+		int step;
+		int mul;
+
+		tok = strsep(&str, ",");
+		if (!tok)
+			break;
+
+		tok_end = strstr(tok, "-");
+
+		dprintf("\ntoken: {%s}, end: {%s}\n", tok, tok_end);
+		if (!tok_end) {
+			/* Single CPU specified: */
+			bind_cpu_0 = bind_cpu_1 = atol(tok);
+		} else {
+			/* CPU range specified (for example: "5-11"): */
+			bind_cpu_0 = atol(tok);
+			bind_cpu_1 = atol(tok_end + 1);
+		}
+
+		step = 1;
+		tok_step = strstr(tok, "#");
+		if (tok_step) {
+			step = atol(tok_step + 1);
+			BUG_ON(step <= 0 || step >= g->p.nr_cpus);
+		}
+
+		/*
+		 * Mask length.
+		 * Eg: "--cpus 8_4-16#4" means: '--cpus 8_4,12_4,16_4',
+		 * where the _4 means the next 4 CPUs are allowed.
+		 */
+		bind_len = 1;
+		tok_len = strstr(tok, "_");
+		if (tok_len) {
+			bind_len = atol(tok_len + 1);
+			BUG_ON(bind_len <= 0 || bind_len > g->p.nr_cpus);
+		}
+
+		/* Multiplicator shortcut, "0x8" is a shortcut for: "0,0,0,0,0,0,0,0" */
+		mul = 1;
+		tok_mul = strstr(tok, "x");
+		if (tok_mul) {
+			mul = atol(tok_mul + 1);
+			BUG_ON(mul <= 0);
+		}
+
+		dprintf("CPUs: %d_%d-%d#%dx%d\n", bind_cpu_0, bind_len, bind_cpu_1, step, mul);
+
+		BUG_ON(bind_cpu_0 < 0 || bind_cpu_0 >= g->p.nr_cpus);
+		BUG_ON(bind_cpu_1 < 0 || bind_cpu_1 >= g->p.nr_cpus);
+		BUG_ON(bind_cpu_0 > bind_cpu_1);
+
+		for (bind_cpu = bind_cpu_0; bind_cpu <= bind_cpu_1; bind_cpu += step) {
+			int i;
+
+			for (i = 0; i < mul; i++) {
+				int cpu;
+
+				if (t >= g->p.nr_tasks) {
+					printf("\n# NOTE: ignoring bind CPUs starting at CPU#%d\n #", bind_cpu);
+					goto out;
+				}
+				td = g->threads + t;
+
+				if (t)
+					tprintf(",");
+				if (bind_len > 1) {
+					tprintf("%2d/%d", bind_cpu, bind_len);
+				} else {
+					tprintf("%2d", bind_cpu);
+				}
+
+				CPU_ZERO(&td->bind_cpumask);
+				for (cpu = bind_cpu; cpu < bind_cpu+bind_len; cpu++) {
+					BUG_ON(cpu < 0 || cpu >= g->p.nr_cpus);
+					CPU_SET(cpu, &td->bind_cpumask);
+				}
+				t++;
+			}
+		}
+	}
+out:
+
+	tprintf("\n");
+
+	if (t < g->p.nr_tasks)
+		printf("# NOTE: %d tasks bound, %d tasks unbound\n", t, g->p.nr_tasks - t);
+
+	free(str0);
+}
+
+static int parse_cpus_opt(const struct option *opt __maybe_unused,
+			  const char *arg, int unset __maybe_unused)
+{
+	if (!arg)
+		return -1;
+
+	return parse_cpu_list(arg);
+}
+
+static int parse_node_list(const char *arg)
+{
+	p0.node_list_str = strdup(arg);
+
+	dprintf("got NODE list: {%s}\n", p0.node_list_str);
+
+	return 0;
+}
+
+static void parse_setup_node_list(void)
+{
+	struct thread_data *td;
+	char *str0, *str;
+	int t;
+
+	if (!g->p.node_list_str)
+		return;
+
+	dprintf("g->p.nr_tasks: %d\n", g->p.nr_tasks);
+
+	str0 = str = strdup(g->p.node_list_str);
+	t = 0;
+
+	BUG_ON(!str);
+
+	tprintf("# binding tasks to NODEs:\n");
+	tprintf("# ");
+
+	while (true) {
+		int bind_node, bind_node_0, bind_node_1;
+		char *tok, *tok_end, *tok_step, *tok_mul;
+		int step;
+		int mul;
+
+		tok = strsep(&str, ",");
+		if (!tok)
+			break;
+
+		tok_end = strstr(tok, "-");
+
+		dprintf("\ntoken: {%s}, end: {%s}\n", tok, tok_end);
+		if (!tok_end) {
+			/* Single NODE specified: */
+			bind_node_0 = bind_node_1 = atol(tok);
+		} else {
+			/* NODE range specified (for example: "5-11"): */
+			bind_node_0 = atol(tok);
+			bind_node_1 = atol(tok_end + 1);
+		}
+
+		step = 1;
+		tok_step = strstr(tok, "#");
+		if (tok_step) {
+			step = atol(tok_step + 1);
+			BUG_ON(step <= 0 || step >= g->p.nr_nodes);
+		}
+
+		/* Multiplicator shortcut, "0x8" is a shortcut for: "0,0,0,0,0,0,0,0" */
+		mul = 1;
+		tok_mul = strstr(tok, "x");
+		if (tok_mul) {
+			mul = atol(tok_mul + 1);
+			BUG_ON(mul <= 0);
+		}
+
+		dprintf("NODEs: %d-%d #%d\n", bind_node_0, bind_node_1, step);
+
+		BUG_ON(bind_node_0 < 0 || bind_node_0 >= g->p.nr_nodes);
+		BUG_ON(bind_node_1 < 0 || bind_node_1 >= g->p.nr_nodes);
+		BUG_ON(bind_node_0 > bind_node_1);
+
+		for (bind_node = bind_node_0; bind_node <= bind_node_1; bind_node += step) {
+			int i;
+
+			for (i = 0; i < mul; i++) {
+				if (t >= g->p.nr_tasks) {
+					printf("\n# NOTE: ignoring bind NODEs starting at NODE#%d\n", bind_node);
+					goto out;
+				}
+				td = g->threads + t;
+
+				if (!t)
+					tprintf(" %2d", bind_node);
+				else
+					tprintf(",%2d", bind_node);
+
+				td->bind_node = bind_node;
+				t++;
+			}
+		}
+	}
+out:
+
+	tprintf("\n");
+
+	if (t < g->p.nr_tasks)
+		printf("# NOTE: %d tasks mem-bound, %d tasks unbound\n", t, g->p.nr_tasks - t);
+
+	free(str0);
+}
+
+static int parse_nodes_opt(const struct option *opt __maybe_unused,
+			  const char *arg, int unset __maybe_unused)
+{
+	if (!arg)
+		return -1;
+
+	return parse_node_list(arg);
+
+	return 0;
+}
+
+#define BIT(x) (1ul << x)
+
+static inline uint32_t lfsr_32(uint32_t lfsr)
+{
+	const uint32_t taps = BIT(1) | BIT(5) | BIT(6) | BIT(31);
+	return (lfsr>>1) ^ ((0x0u - (lfsr & 0x1u)) & taps);
+}
+
+/*
+ * Make sure there's real data dependency to RAM (when read
+ * accesses are enabled), so the compiler, the CPU and the
+ * kernel (KSM, zero page, etc.) cannot optimize away RAM
+ * accesses:
+ */
+static inline u64 access_data(u64 *data __attribute__((unused)), u64 val)
+{
+	if (g->p.data_reads)
+		val += *data;
+	if (g->p.data_writes)
+		*data = val + 1;
+	return val;
+}
+
+/*
+ * The worker process does two types of work, a forwards going
+ * loop and a backwards going loop.
+ *
+ * We do this so that on multiprocessor systems we do not create
+ * a 'train' of processing, with highly synchronized processes,
+ * skewing the whole benchmark.
+ */
+static u64 do_work(u8 *__data, long bytes, int nr, int nr_max, int loop, u64 val)
+{
+	long words = bytes/sizeof(u64);
+	u64 *data = (void *)__data;
+	long chunk_0, chunk_1;
+	u64 *d0, *d, *d1;
+	long off;
+	long i;
+
+	BUG_ON(!data && words);
+	BUG_ON(data && !words);
+
+	if (!data)
+		return val;
+
+	/* Very simple memset() work variant: */
+	if (g->p.data_zero_memset && !g->p.data_rand_walk) {
+		bzero(data, bytes);
+		return val;
+	}
+
+	/* Spread out by PID/TID nr and by loop nr: */
+	chunk_0 = words/nr_max;
+	chunk_1 = words/g->p.nr_loops;
+	off = nr*chunk_0 + loop*chunk_1;
+
+	while (off >= words)
+		off -= words;
+
+	if (g->p.data_rand_walk) {
+		u32 lfsr = nr + loop + val;
+		int j;
+
+		for (i = 0; i < words/1024; i++) {
+			long start, end;
+
+			lfsr = lfsr_32(lfsr);
+
+			start = lfsr % words;
+			end = min(start + 1024, words-1);
+
+			if (g->p.data_zero_memset) {
+				bzero(data + start, (end-start) * sizeof(u64));
+			} else {
+				for (j = start; j < end; j++)
+					val = access_data(data + j, val);
+			}
+		}
+	} else if (!g->p.data_backwards || (nr + loop) & 1) {
+
+		d0 = data + off;
+		d  = data + off + 1;
+		d1 = data + words;
+
+		/* Process data forwards: */
+		for (;;) {
+			if (unlikely(d >= d1))
+				d = data;
+			if (unlikely(d == d0))
+				break;
+
+			val = access_data(d, val);
+
+			d++;
+		}
+	} else {
+		/* Process data backwards: */
+
+		d0 = data + off;
+		d  = data + off - 1;
+		d1 = data + words;
+
+		/* Process data forwards: */
+		for (;;) {
+			if (unlikely(d < data))
+				d = data + words-1;
+			if (unlikely(d == d0))
+				break;
+
+			val = access_data(d, val);
+
+			d--;
+		}
+	}
+
+	return val;
+}
+
+static void update_curr_cpu(int task_nr, unsigned long bytes_worked)
+{
+	unsigned int cpu;
+
+	cpu = sched_getcpu();
+
+	g->threads[task_nr].curr_cpu = cpu;
+	prctl(0, bytes_worked);
+}
+
+#define MAX_NR_NODES	64
+
+/*
+ * Count the number of nodes a process's threads
+ * are spread out on.
+ *
+ * A count of 1 means that the process is compressed
+ * to a single node. A count of g->p.nr_nodes means it's
+ * spread out on the whole system.
+ */
+static int count_process_nodes(int process_nr)
+{
+	char node_present[MAX_NR_NODES] = { 0, };
+	int nodes;
+	int n, t;
+
+	for (t = 0; t < g->p.nr_threads; t++) {
+		struct thread_data *td;
+		int task_nr;
+		int node;
+
+		task_nr = process_nr*g->p.nr_threads + t;
+		td = g->threads + task_nr;
+
+		node = numa_node_of_cpu(td->curr_cpu);
+		node_present[node] = 1;
+	}
+
+	nodes = 0;
+
+	for (n = 0; n < MAX_NR_NODES; n++)
+		nodes += node_present[n];
+
+	return nodes;
+}
+
+/*
+ * Count the number of distinct process-threads a node contains.
+ *
+ * A count of 1 means that the node contains only a single
+ * process. If all nodes on the system contain at most one
+ * process then we are well-converged.
+ */
+static int count_node_processes(int node)
+{
+	int processes = 0;
+	int t, p;
+
+	for (p = 0; p < g->p.nr_proc; p++) {
+		for (t = 0; t < g->p.nr_threads; t++) {
+			struct thread_data *td;
+			int task_nr;
+			int n;
+
+			task_nr = p*g->p.nr_threads + t;
+			td = g->threads + task_nr;
+
+			n = numa_node_of_cpu(td->curr_cpu);
+			if (n == node) {
+				processes++;
+				break;
+			}
+		}
+	}
+
+	return processes;
+}
+
+static void calc_convergence_compression(int *strong)
+{
+	unsigned int nodes_min, nodes_max;
+	int p;
+
+	nodes_min = -1;
+	nodes_max =  0;
+
+	for (p = 0; p < g->p.nr_proc; p++) {
+		unsigned int nodes = count_process_nodes(p);
+
+		nodes_min = min(nodes, nodes_min);
+		nodes_max = max(nodes, nodes_max);
+	}
+
+	/* Strong convergence: all threads compress on a single node: */
+	if (nodes_min == 1 && nodes_max == 1) {
+		*strong = 1;
+	} else {
+		*strong = 0;
+		tprintf(" {%d-%d}", nodes_min, nodes_max);
+	}
+}
+
+static void calc_convergence(double runtime_ns_max, double *convergence)
+{
+	unsigned int loops_done_min, loops_done_max;
+	int process_groups;
+	int nodes[MAX_NR_NODES];
+	int distance;
+	int nr_min;
+	int nr_max;
+	int strong;
+	int sum;
+	int nr;
+	int node;
+	int cpu;
+	int t;
+
+	if (!g->p.show_convergence && !g->p.measure_convergence)
+		return;
+
+	for (node = 0; node < g->p.nr_nodes; node++)
+		nodes[node] = 0;
+
+	loops_done_min = -1;
+	loops_done_max = 0;
+
+	for (t = 0; t < g->p.nr_tasks; t++) {
+		struct thread_data *td = g->threads + t;
+		unsigned int loops_done;
+
+		cpu = td->curr_cpu;
+
+		/* Not all threads have written it yet: */
+		if (cpu < 0)
+			continue;
+
+		node = numa_node_of_cpu(cpu);
+
+		nodes[node]++;
+
+		loops_done = td->loops_done;
+		loops_done_min = min(loops_done, loops_done_min);
+		loops_done_max = max(loops_done, loops_done_max);
+	}
+
+	nr_max = 0;
+	nr_min = g->p.nr_tasks;
+	sum = 0;
+
+	for (node = 0; node < g->p.nr_nodes; node++) {
+		nr = nodes[node];
+		nr_min = min(nr, nr_min);
+		nr_max = max(nr, nr_max);
+		sum += nr;
+	}
+	BUG_ON(nr_min > nr_max);
+
+	BUG_ON(sum > g->p.nr_tasks);
+
+	if (0 && (sum < g->p.nr_tasks))
+		return;
+
+	/*
+	 * Count the number of distinct process groups present
+	 * on nodes - when we are converged this will decrease
+	 * to g->p.nr_proc:
+	 */
+	process_groups = 0;
+
+	for (node = 0; node < g->p.nr_nodes; node++) {
+		int processes = count_node_processes(node);
+
+		nr = nodes[node];
+		tprintf(" %2d/%-2d", nr, processes);
+
+		process_groups += processes;
+	}
+
+	distance = nr_max - nr_min;
+
+	tprintf(" [%2d/%-2d]", distance, process_groups);
+
+	tprintf(" l:%3d-%-3d (%3d)",
+		loops_done_min, loops_done_max, loops_done_max-loops_done_min);
+
+	if (loops_done_min && loops_done_max) {
+		double skew = 1.0 - (double)loops_done_min/loops_done_max;
+
+		tprintf(" [%4.1f%%]", skew * 100.0);
+	}
+
+	calc_convergence_compression(&strong);
+
+	if (strong && process_groups == g->p.nr_proc) {
+		if (!*convergence) {
+			*convergence = runtime_ns_max;
+			tprintf(" (%6.1fs converged)\n", *convergence/1e9);
+			if (g->p.measure_convergence) {
+				g->all_converged = true;
+				g->stop_work = true;
+			}
+		}
+	} else {
+		if (*convergence) {
+			tprintf(" (%6.1fs de-converged)", runtime_ns_max/1e9);
+			*convergence = 0;
+		}
+		tprintf("\n");
+	}
+}
+
+static void show_summary(double runtime_ns_max, int l, double *convergence)
+{
+	tprintf("\r #  %5.1f%%  [%.1f mins]",
+		(double)(l+1)/g->p.nr_loops*100.0, runtime_ns_max/1e9 / 60.0);
+
+	calc_convergence(runtime_ns_max, convergence);
+
+	if (g->p.show_details >= 0)
+		fflush(stdout);
+}
+
+static void *worker_thread(void *__tdata)
+{
+	struct thread_data *td = __tdata;
+	struct timeval start0, start, stop, diff;
+	int process_nr = td->process_nr;
+	int thread_nr = td->thread_nr;
+	unsigned long last_perturbance;
+	int task_nr = td->task_nr;
+	int details = g->p.show_details;
+	int first_task, last_task;
+	double convergence = 0;
+	u64 val = td->val;
+	double runtime_ns_max;
+	u8 *global_data;
+	u8 *process_data;
+	u8 *thread_data;
+	u64 bytes_done;
+	long work_done;
+	u32 l;
+
+	bind_to_cpumask(td->bind_cpumask);
+	bind_to_memnode(td->bind_node);
+
+	set_taskname("thread %d/%d", process_nr, thread_nr);
+
+	global_data = g->data;
+	process_data = td->process_data;
+	thread_data = setup_private_data(g->p.bytes_thread);
+
+	bytes_done = 0;
+
+	last_task = 0;
+	if (process_nr == g->p.nr_proc-1 && thread_nr == g->p.nr_threads-1)
+		last_task = 1;
+
+	first_task = 0;
+	if (process_nr == 0 && thread_nr == 0)
+		first_task = 1;
+
+	if (details >= 2) {
+		printf("#  thread %2d / %2d global mem: %p, process mem: %p, thread mem: %p\n",
+			process_nr, thread_nr, global_data, process_data, thread_data);
+	}
+
+	if (g->p.serialize_startup) {
+		pthread_mutex_lock(&g->startup_mutex);
+		g->nr_tasks_started++;
+		pthread_mutex_unlock(&g->startup_mutex);
+
+		/* Here we will wait for the main process to start us all at once: */
+		pthread_mutex_lock(&g->start_work_mutex);
+		g->nr_tasks_working++;
+
+		/* Last one wake the main process: */
+		if (g->nr_tasks_working == g->p.nr_tasks)
+			pthread_mutex_unlock(&g->startup_done_mutex);
+
+		pthread_mutex_unlock(&g->start_work_mutex);
+	}
+
+	gettimeofday(&start0, NULL);
+
+	start = stop = start0;
+	last_perturbance = start.tv_sec;
+
+	for (l = 0; l < g->p.nr_loops; l++) {
+		start = stop;
+
+		if (g->stop_work)
+			break;
+
+		val += do_work(global_data,  g->p.bytes_global,  process_nr, g->p.nr_proc,	l, val);
+		val += do_work(process_data, g->p.bytes_process, thread_nr,  g->p.nr_threads,	l, val);
+		val += do_work(thread_data,  g->p.bytes_thread,  0,          1,		l, val);
+
+		if (g->p.sleep_usecs) {
+			pthread_mutex_lock(td->process_lock);
+			usleep(g->p.sleep_usecs);
+			pthread_mutex_unlock(td->process_lock);
+		}
+		/*
+		 * Amount of work to be done under a process-global lock:
+		 */
+		if (g->p.bytes_process_locked) {
+			pthread_mutex_lock(td->process_lock);
+			val += do_work(process_data, g->p.bytes_process_locked, thread_nr,  g->p.nr_threads,	l, val);
+			pthread_mutex_unlock(td->process_lock);
+		}
+
+		work_done = g->p.bytes_global + g->p.bytes_process +
+			    g->p.bytes_process_locked + g->p.bytes_thread;
+
+		update_curr_cpu(task_nr, work_done);
+		bytes_done += work_done;
+
+		if (details < 0 && !g->p.perturb_secs && !g->p.measure_convergence && !g->p.nr_secs)
+			continue;
+
+		td->loops_done = l;
+
+		gettimeofday(&stop, NULL);
+
+		/* Check whether our max runtime timed out: */
+		if (g->p.nr_secs) {
+			timersub(&stop, &start0, &diff);
+			if (diff.tv_sec >= g->p.nr_secs) {
+				g->stop_work = true;
+				break;
+			}
+		}
+
+		/* Update the summary at most once per second: */
+		if (start.tv_sec == stop.tv_sec)
+			continue;
+
+		/*
+		 * Perturb the first task's equilibrium every g->p.perturb_secs seconds,
+		 * by migrating to CPU#0:
+		 */
+		if (first_task && g->p.perturb_secs && (int)(stop.tv_sec - last_perturbance) >= g->p.perturb_secs) {
+			cpu_set_t orig_mask;
+			int target_cpu;
+			int this_cpu;
+
+			last_perturbance = stop.tv_sec;
+
+			/*
+			 * Depending on where we are running, move into
+			 * the other half of the system, to create some
+			 * real disturbance:
+			 */
+			this_cpu = g->threads[task_nr].curr_cpu;
+			if (this_cpu < g->p.nr_cpus/2)
+				target_cpu = g->p.nr_cpus-1;
+			else
+				target_cpu = 0;
+
+			orig_mask = bind_to_cpu(target_cpu);
+
+			/* Here we are running on the target CPU already */
+			if (details >= 1)
+				printf(" (injecting perturbalance, moved to CPU#%d)\n", target_cpu);
+
+			bind_to_cpumask(orig_mask);
+		}
+
+		if (details >= 3) {
+			timersub(&stop, &start, &diff);
+			runtime_ns_max = diff.tv_sec * 1000000000;
+			runtime_ns_max += diff.tv_usec * 1000;
+
+			if (details >= 0) {
+				printf(" #%2d / %2d: %14.2lf nsecs/op [val: %016lx]\n",
+					process_nr, thread_nr, runtime_ns_max / bytes_done, val);
+			}
+			fflush(stdout);
+		}
+		if (!last_task)
+			continue;
+
+		timersub(&stop, &start0, &diff);
+		runtime_ns_max = diff.tv_sec * 1000000000ULL;
+		runtime_ns_max += diff.tv_usec * 1000ULL;
+
+		show_summary(runtime_ns_max, l, &convergence);
+	}
+
+	gettimeofday(&stop, NULL);
+	timersub(&stop, &start0, &diff);
+	td->runtime_ns = diff.tv_sec * 1000000000ULL;
+	td->runtime_ns += diff.tv_usec * 1000ULL;
+
+	free_data(thread_data, g->p.bytes_thread);
+
+	pthread_mutex_lock(&g->stop_work_mutex);
+	g->bytes_done += bytes_done;
+	pthread_mutex_unlock(&g->stop_work_mutex);
+
+	return NULL;
+}
+
+/*
+ * A worker process starts a couple of threads:
+ */
+static void worker_process(int process_nr)
+{
+	pthread_mutex_t process_lock;
+	struct thread_data *td;
+	pthread_t *pthreads;
+	u8 *process_data;
+	int task_nr;
+	int ret;
+	int t;
+
+	pthread_mutex_init(&process_lock, NULL);
+	set_taskname("process %d", process_nr);
+
+	/*
+	 * Pick up the memory policy and the CPU binding of our first thread,
+	 * so that we initialize memory accordingly:
+	 */
+	task_nr = process_nr*g->p.nr_threads;
+	td = g->threads + task_nr;
+
+	bind_to_memnode(td->bind_node);
+	bind_to_cpumask(td->bind_cpumask);
+
+	pthreads = zalloc(g->p.nr_threads * sizeof(pthread_t));
+	process_data = setup_private_data(g->p.bytes_process);
+
+	if (g->p.show_details >= 3) {
+		printf(" # process %2d global mem: %p, process mem: %p\n",
+			process_nr, g->data, process_data);
+	}
+
+	for (t = 0; t < g->p.nr_threads; t++) {
+		task_nr = process_nr*g->p.nr_threads + t;
+		td = g->threads + task_nr;
+
+		td->process_data = process_data;
+		td->process_nr   = process_nr;
+		td->thread_nr    = t;
+		td->task_nr	 = task_nr;
+		td->val          = rand();
+		td->curr_cpu	 = -1;
+		td->process_lock = &process_lock;
+
+		ret = pthread_create(pthreads + t, NULL, worker_thread, td);
+		BUG_ON(ret);
+	}
+
+	for (t = 0; t < g->p.nr_threads; t++) {
+                ret = pthread_join(pthreads[t], NULL);
+		BUG_ON(ret);
+	}
+
+	free_data(process_data, g->p.bytes_process);
+	free(pthreads);
+}
+
+static void print_summary(void)
+{
+	if (g->p.show_details < 0)
+		return;
+
+	printf("\n ###\n");
+	printf(" # %d %s will execute (on %d nodes, %d CPUs):\n",
+		g->p.nr_tasks, g->p.nr_tasks == 1 ? "task" : "tasks", g->p.nr_nodes, g->p.nr_cpus);
+	printf(" #      %5dx %5ldMB global  shared mem operations\n",
+			g->p.nr_loops, g->p.bytes_global/1024/1024);
+	printf(" #      %5dx %5ldMB process shared mem operations\n",
+			g->p.nr_loops, g->p.bytes_process/1024/1024);
+	printf(" #      %5dx %5ldMB thread  local  mem operations\n",
+			g->p.nr_loops, g->p.bytes_thread/1024/1024);
+
+	printf(" ###\n");
+
+	printf("\n ###\n"); fflush(stdout);
+}
+
+static void init_thread_data(void)
+{
+	ssize_t size = sizeof(*g->threads)*g->p.nr_tasks;
+	int t;
+
+	g->threads = zalloc_shared_data(size);
+
+	for (t = 0; t < g->p.nr_tasks; t++) {
+		struct thread_data *td = g->threads + t;
+		int cpu;
+
+		/* Allow all nodes by default: */
+		td->bind_node = -1;
+
+		/* Allow all CPUs by default: */
+		CPU_ZERO(&td->bind_cpumask);
+		for (cpu = 0; cpu < g->p.nr_cpus; cpu++)
+			CPU_SET(cpu, &td->bind_cpumask);
+	}
+}
+
+static void deinit_thread_data(void)
+{
+	ssize_t size = sizeof(*g->threads)*g->p.nr_tasks;
+
+	free_data(g->threads, size);
+}
+
+static int init(void)
+{
+	g = (void *)alloc_data(sizeof(*g), MAP_SHARED, 1, 0, 0 /* THP */, 0);
+
+	/* Copy over options: */
+	g->p = p0;
+
+	g->p.nr_cpus = numa_num_configured_cpus();
+
+	g->p.nr_nodes = numa_max_node() + 1;
+
+	/* char array in count_process_nodes(): */
+	BUG_ON(g->p.nr_nodes > MAX_NR_NODES || g->p.nr_nodes < 0);
+
+	if (g->p.show_quiet && !g->p.show_details)
+		g->p.show_details = -1;
+
+	/* Some memory should be specified: */
+	if (!g->p.mb_global_str && !g->p.mb_proc_str && !g->p.mb_thread_str)
+		return -1;
+
+	if (g->p.mb_global_str) {
+		g->p.mb_global = atof(g->p.mb_global_str);
+		BUG_ON(g->p.mb_global < 0);
+	}
+
+	if (g->p.mb_proc_str) {
+		g->p.mb_proc = atof(g->p.mb_proc_str);
+		BUG_ON(g->p.mb_proc < 0);
+	}
+
+	if (g->p.mb_proc_locked_str) {
+		g->p.mb_proc_locked = atof(g->p.mb_proc_locked_str);
+		BUG_ON(g->p.mb_proc_locked < 0);
+		BUG_ON(g->p.mb_proc_locked > g->p.mb_proc);
+	}
+
+	if (g->p.mb_thread_str) {
+		g->p.mb_thread = atof(g->p.mb_thread_str);
+		BUG_ON(g->p.mb_thread < 0);
+	}
+
+	BUG_ON(g->p.nr_threads <= 0);
+	BUG_ON(g->p.nr_proc <= 0);
+
+	g->p.nr_tasks = g->p.nr_proc*g->p.nr_threads;
+
+	g->p.bytes_global		= g->p.mb_global	*1024L*1024L;
+	g->p.bytes_process		= g->p.mb_proc		*1024L*1024L;
+	g->p.bytes_process_locked	= g->p.mb_proc_locked	*1024L*1024L;
+	g->p.bytes_thread		= g->p.mb_thread	*1024L*1024L;
+
+	g->data = setup_shared_data(g->p.bytes_global);
+
+	/* Startup serialization: */
+	init_global_mutex(&g->start_work_mutex);
+	init_global_mutex(&g->startup_mutex);
+	init_global_mutex(&g->startup_done_mutex);
+	init_global_mutex(&g->stop_work_mutex);
+
+	init_thread_data();
+
+	tprintf("#\n");
+	parse_setup_cpu_list();
+	parse_setup_node_list();
+	tprintf("#\n");
+
+	print_summary();
+
+	return 0;
+}
+
+static void deinit(void)
+{
+	free_data(g->data, g->p.bytes_global);
+	g->data = NULL;
+
+	deinit_thread_data();
+
+	free_data(g, sizeof(*g));
+	g = NULL;
+}
+
+/*
+ * Print a short or long result, depending on the verbosity setting:
+ */
+static void print_res(const char *name, double val,
+		      const char *txt_unit, const char *txt_short, const char *txt_long)
+{
+	if (!name)
+		name = "main,";
+
+	if (g->p.show_quiet)
+		printf(" %-30s %15.3f, %-15s %s\n", name, val, txt_unit, txt_short);
+	else
+		printf(" %14.3f %s\n", val, txt_long);
+}
+
+static int __bench_numa(const char *name)
+{
+	struct timeval start, stop, diff;
+	u64 runtime_ns_min, runtime_ns_sum;
+	pid_t *pids, pid, wpid;
+	double delta_runtime;
+	double runtime_avg;
+	double runtime_sec_max;
+	double runtime_sec_min;
+	int wait_stat;
+	double bytes;
+	int i, t;
+
+	if (init())
+		return -1;
+
+	pids = zalloc(g->p.nr_proc * sizeof(*pids));
+	pid = -1;
+
+	/* All threads try to acquire it, this way we can wait for them to start up: */
+	pthread_mutex_lock(&g->start_work_mutex);
+
+	if (g->p.serialize_startup) {
+		tprintf(" #\n");
+		tprintf(" # Startup synchronization: ..."); fflush(stdout);
+	}
+
+	gettimeofday(&start, NULL);
+
+	for (i = 0; i < g->p.nr_proc; i++) {
+		pid = fork();
+		dprintf(" # process %2d: PID %d\n", i, pid);
+
+		BUG_ON(pid < 0);
+		if (!pid) {
+			/* Child process: */
+			worker_process(i);
+
+			exit(0);
+		}
+		pids[i] = pid;
+
+	}
+	/* Wait for all the threads to start up: */
+	while (g->nr_tasks_started != g->p.nr_tasks)
+		usleep(1000);
+
+	BUG_ON(g->nr_tasks_started != g->p.nr_tasks);
+
+	if (g->p.serialize_startup) {
+		double startup_sec;
+
+		pthread_mutex_lock(&g->startup_done_mutex);
+
+		/* This will start all threads: */
+		pthread_mutex_unlock(&g->start_work_mutex);
+
+		/* This mutex is locked - the last started thread will wake us: */
+		pthread_mutex_lock(&g->startup_done_mutex);
+
+		gettimeofday(&stop, NULL);
+
+		timersub(&stop, &start, &diff);
+
+		startup_sec = diff.tv_sec * 1000000000.0;
+		startup_sec += diff.tv_usec * 1000.0;
+		startup_sec /= 1e9;
+
+		tprintf(" threads initialized in %.6f seconds.\n", startup_sec);
+		tprintf(" #\n");
+
+		start = stop;
+		pthread_mutex_unlock(&g->startup_done_mutex);
+	} else {
+		gettimeofday(&start, NULL);
+	}
+
+	/* Parent process: */
+
+
+	for (i = 0; i < g->p.nr_proc; i++) {
+		wpid = waitpid(pids[i], &wait_stat, 0);
+		BUG_ON(wpid < 0);
+		BUG_ON(!WIFEXITED(wait_stat));
+
+	}
+
+	runtime_ns_sum = 0;
+	runtime_ns_min = -1LL;
+
+	for (t = 0; t < g->p.nr_tasks; t++) {
+		u64 thread_runtime_ns = g->threads[t].runtime_ns;
+
+		runtime_ns_sum += thread_runtime_ns;
+		runtime_ns_min = min(thread_runtime_ns, runtime_ns_min);
+	}
+
+	gettimeofday(&stop, NULL);
+	timersub(&stop, &start, &diff);
+
+	BUG_ON(bench_format != BENCH_FORMAT_DEFAULT);
+
+	tprintf("\n ###\n");
+	tprintf("\n");
+
+	runtime_sec_max = diff.tv_sec * 1000000000.0;
+	runtime_sec_max += diff.tv_usec * 1000.0;
+	runtime_sec_max /= 1e9;
+
+	runtime_sec_min = runtime_ns_min/1e9;
+
+	bytes = g->bytes_done;
+	runtime_avg = (double)runtime_ns_sum / g->p.nr_tasks / 1e9;
+
+	if (g->p.measure_convergence) {
+		print_res(name, runtime_sec_max,
+			"secs,", "NUMA-convergence-latency", "secs latency to NUMA-converge");
+	}
+
+	print_res(name, runtime_sec_max,
+		"secs,", "runtime-max/thread",	"secs slowest (max) thread-runtime");
+
+	print_res(name, runtime_sec_min,
+		"secs,", "runtime-min/thread",	"secs fastest (min) thread-runtime");
+
+	print_res(name, runtime_avg,
+		"secs,", "runtime-avg/thread",	"secs average thread-runtime");
+
+	delta_runtime = (runtime_sec_max - runtime_sec_min)/2.0;
+	print_res(name, delta_runtime / runtime_sec_max * 100.0,
+		"%,", "spread-runtime/thread",	"% difference between max/avg runtime");
+
+	print_res(name, bytes / g->p.nr_tasks / 1e9,
+		"GB,", "data/thread",		"GB data processed, per thread");
+
+	print_res(name, bytes / 1e9,
+		"GB,", "data-total",		"GB data processed, total");
+
+	print_res(name, runtime_sec_max * 1e9 / (bytes / g->p.nr_tasks),
+		"nsecs,", "runtime/byte/thread","nsecs/byte/thread runtime");
+
+	print_res(name, bytes / g->p.nr_tasks / 1e9 / runtime_sec_max,
+		"GB/sec,", "thread-speed",	"GB/sec/thread speed");
+
+	print_res(name, bytes / runtime_sec_max / 1e9,
+		"GB/sec,", "total-speed",	"GB/sec total speed");
+
+	free(pids);
+
+	deinit();
+
+	return 0;
+}
+
+#define MAX_ARGS 50
+
+static int command_size(const char **argv)
+{
+	int size = 0;
+
+	while (*argv) {
+		size++;
+		argv++;
+	}
+
+	BUG_ON(size >= MAX_ARGS);
+
+	return size;
+}
+
+static void init_params(struct params *p, const char *name, int argc, const char **argv)
+{
+	int i;
+
+	printf("\n # Running %s \"perf bench numa", name);
+
+	for (i = 0; i < argc; i++)
+		printf(" %s", argv[i]);
+
+	printf("\"\n");
+
+	memset(p, 0, sizeof(*p));
+
+	/* Initialize nonzero defaults: */
+
+	p->serialize_startup		= 1;
+	p->data_reads			= true;
+	p->data_writes			= true;
+	p->data_backwards		= true;
+	p->data_rand_walk		= true;
+	p->nr_loops			= -1;
+	p->init_random			= true;
+}
+
+static int run_bench_numa(const char *name, const char **argv)
+{
+	int argc = command_size(argv);
+
+	init_params(&p0, name, argc, argv);
+	argc = parse_options(argc, argv, options, bench_numa_usage, 0);
+	if (argc)
+		goto err;
+
+	if (__bench_numa(name))
+		goto err;
+
+	return 0;
+
+err:
+	usage_with_options(numa_usage, options);
+	return -1;
+}
+
+#define OPT_BW_RAM		"-s",  "20", "-zZq",    "--thp", " 1", "--no-data_rand_walk"
+#define OPT_BW_RAM_NOTHP	OPT_BW_RAM,		"--thp", "-1"
+
+#define OPT_CONV		"-s", "100", "-zZ0qcm", "--thp", " 1"
+#define OPT_CONV_NOTHP		OPT_CONV,		"--thp", "-1"
+
+#define OPT_BW			"-s",  "20", "-zZ0q",   "--thp", " 1"
+#define OPT_BW_NOTHP		OPT_BW,			"--thp", "-1"
+
+/*
+ * The built-in test-suite executed by "perf bench numa -a".
+ *
+ * (A minimum of 4 nodes and 16 GB of RAM is recommended.)
+ */
+static const char *tests[][MAX_ARGS] = {
+   /* Basic single-stream NUMA bandwidth measurements: */
+   { "RAM-bw-local,",	  "mem",  "-p",  "1",  "-t",  "1", "-P", "1024",
+			  "-C" ,   "0", "-M",   "0", OPT_BW_RAM },
+   { "RAM-bw-local-NOTHP,",
+			  "mem",  "-p",  "1",  "-t",  "1", "-P", "1024",
+			  "-C" ,   "0", "-M",   "0", OPT_BW_RAM_NOTHP },
+   { "RAM-bw-remote,",	  "mem",  "-p",  "1",  "-t",  "1", "-P", "1024",
+			  "-C" ,   "0", "-M",   "1", OPT_BW_RAM },
+
+   /* 2-stream NUMA bandwidth measurements: */
+   { "RAM-bw-local-2x,",  "mem",  "-p",  "2",  "-t",  "1", "-P", "1024",
+			   "-C", "0,2", "-M", "0x2", OPT_BW_RAM },
+   { "RAM-bw-remote-2x,", "mem",  "-p",  "2",  "-t",  "1", "-P", "1024",
+		 	   "-C", "0,2", "-M", "1x2", OPT_BW_RAM },
+
+   /* Cross-stream NUMA bandwidth measurement: */
+   { "RAM-bw-cross,",     "mem",  "-p",  "2",  "-t",  "1", "-P", "1024",
+		 	   "-C", "0,8", "-M", "1,0", OPT_BW_RAM },
+
+   /* Convergence latency measurements: */
+   { " 1x3-convergence,", "mem",  "-p",  "1", "-t",  "3", "-P",  "512", OPT_CONV },
+   { " 1x4-convergence,", "mem",  "-p",  "1", "-t",  "4", "-P",  "512", OPT_CONV },
+   { " 1x6-convergence,", "mem",  "-p",  "1", "-t",  "6", "-P", "1020", OPT_CONV },
+   { " 2x3-convergence,", "mem",  "-p",  "3", "-t",  "3", "-P", "1020", OPT_CONV },
+   { " 3x3-convergence,", "mem",  "-p",  "3", "-t",  "3", "-P", "1020", OPT_CONV },
+   { " 4x4-convergence,", "mem",  "-p",  "4", "-t",  "4", "-P",  "512", OPT_CONV },
+   { " 4x4-convergence-NOTHP,",
+			  "mem",  "-p",  "4", "-t",  "4", "-P",  "512", OPT_CONV_NOTHP },
+   { " 4x6-convergence,", "mem",  "-p",  "4", "-t",  "6", "-P", "1020", OPT_CONV },
+   { " 4x8-convergence,", "mem",  "-p",  "4", "-t",  "8", "-P",  "512", OPT_CONV },
+   { " 8x4-convergence,", "mem",  "-p",  "8", "-t",  "4", "-P",  "512", OPT_CONV },
+   { " 8x4-convergence-NOTHP,",
+			  "mem",  "-p",  "8", "-t",  "4", "-P",  "512", OPT_CONV_NOTHP },
+   { " 3x1-convergence,", "mem",  "-p",  "3", "-t",  "1", "-P",  "512", OPT_CONV },
+   { " 4x1-convergence,", "mem",  "-p",  "4", "-t",  "1", "-P",  "512", OPT_CONV },
+   { " 8x1-convergence,", "mem",  "-p",  "8", "-t",  "1", "-P",  "512", OPT_CONV },
+   { "16x1-convergence,", "mem",  "-p", "16", "-t",  "1", "-P",  "256", OPT_CONV },
+   { "32x1-convergence,", "mem",  "-p", "32", "-t",  "1", "-P",  "128", OPT_CONV },
+
+   /* Various NUMA process/thread layout bandwidth measurements: */
+   { " 2x1-bw-process,",  "mem",  "-p",  "2", "-t",  "1", "-P", "1024", OPT_BW },
+   { " 3x1-bw-process,",  "mem",  "-p",  "3", "-t",  "1", "-P", "1024", OPT_BW },
+   { " 4x1-bw-process,",  "mem",  "-p",  "4", "-t",  "1", "-P", "1024", OPT_BW },
+   { " 8x1-bw-process,",  "mem",  "-p",  "8", "-t",  "1", "-P", " 512", OPT_BW },
+   { " 8x1-bw-process-NOTHP,",
+			  "mem",  "-p",  "8", "-t",  "1", "-P", " 512", OPT_BW_NOTHP },
+   { "16x1-bw-process,",  "mem",  "-p", "16", "-t",  "1", "-P",  "256", OPT_BW },
+
+   { " 4x1-bw-thread,",	  "mem",  "-p",  "1", "-t",  "4", "-T",  "256", OPT_BW },
+   { " 8x1-bw-thread,",	  "mem",  "-p",  "1", "-t",  "8", "-T",  "256", OPT_BW },
+   { "16x1-bw-thread,",   "mem",  "-p",  "1", "-t", "16", "-T",  "128", OPT_BW },
+   { "32x1-bw-thread,",   "mem",  "-p",  "1", "-t", "32", "-T",   "64", OPT_BW },
+
+   { " 2x3-bw-thread,",	  "mem",  "-p",  "2", "-t",  "3", "-P",  "512", OPT_BW },
+   { " 4x4-bw-thread,",	  "mem",  "-p",  "4", "-t",  "4", "-P",  "512", OPT_BW },
+   { " 4x6-bw-thread,",	  "mem",  "-p",  "4", "-t",  "6", "-P",  "512", OPT_BW },
+   { " 4x8-bw-thread,",	  "mem",  "-p",  "4", "-t",  "8", "-P",  "512", OPT_BW },
+   { " 4x8-bw-thread-NOTHP,",
+			  "mem",  "-p",  "4", "-t",  "8", "-P",  "512", OPT_BW_NOTHP },
+   { " 3x3-bw-thread,",	  "mem",  "-p",  "3", "-t",  "3", "-P",  "512", OPT_BW },
+   { " 5x5-bw-thread,",	  "mem",  "-p",  "5", "-t",  "5", "-P",  "512", OPT_BW },
+
+   { "2x16-bw-thread,",   "mem",  "-p",  "2", "-t", "16", "-P",  "512", OPT_BW },
+   { "1x32-bw-thread,",   "mem",  "-p",  "1", "-t", "32", "-P", "2048", OPT_BW },
+
+   { "numa02-bw,",	  "mem",  "-p",  "1", "-t", "32", "-T",   "32", OPT_BW },
+   { "numa02-bw-NOTHP,",  "mem",  "-p",  "1", "-t", "32", "-T",   "32", OPT_BW_NOTHP },
+   { "numa01-bw-thread,", "mem",  "-p",  "2", "-t", "16", "-T",  "192", OPT_BW },
+   { "numa01-bw-thread-NOTHP,",
+			  "mem",  "-p",  "2", "-t", "16", "-T",  "192", OPT_BW_NOTHP },
+};
+
+static int bench_all(void)
+{
+	int nr = ARRAY_SIZE(tests);
+	int ret;
+	int i;
+
+	ret = system("echo ' #'; echo ' # Running test on: '$(uname -a); echo ' #'");
+	BUG_ON(ret < 0);
+
+	for (i = 0; i < nr; i++) {
+		if (run_bench_numa(tests[i][0], tests[i] + 1))
+			return -1;
+	}
+
+	printf("\n");
+
+	return 0;
+}
+
+int bench_numa(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+	init_params(&p0, "main,", argc, argv);
+	argc = parse_options(argc, argv, options, bench_numa_usage, 0);
+	if (argc)
+		goto err;
+
+	if (p0.run_all)
+		return bench_all();
+
+	if (__bench_numa(NULL))
+		goto err;
+
+	return 0;
+
+err:
+	usage_with_options(numa_usage, options);
+	return -1;
+}
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index dc870cf..2e6961e 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -34,9 +34,10 @@
 
 struct perf_annotate {
 	struct perf_tool tool;
-	bool	   force, use_tui, use_stdio;
+	bool	   force, use_tui, use_stdio, use_gtk;
 	bool	   full_paths;
 	bool	   print_line;
+	bool	   skip_missing;
 	const char *sym_hist_filter;
 	const char *cpu_list;
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
@@ -138,9 +139,22 @@
 			continue;
 		}
 
-		if (use_browser > 0) {
+		if (use_browser == 2) {
+			int ret;
+
+			ret = hist_entry__gtk_annotate(he, evidx, NULL);
+			if (!ret || !ann->skip_missing)
+				return;
+
+			/* skip missing symbols */
+			nd = rb_next(nd);
+		} else if (use_browser == 1) {
 			key = hist_entry__tui_annotate(he, evidx, NULL);
 			switch (key) {
+			case -1:
+				if (!ann->skip_missing)
+					return;
+				/* fall through */
 			case K_RIGHT:
 				next = rb_next(nd);
 				break;
@@ -224,6 +238,10 @@
 		ui__error("The %s file has no samples!\n", session->filename);
 		goto out_delete;
 	}
+
+	if (use_browser == 2)
+		perf_gtk__show_annotations();
+
 out_delete:
 	/*
 	 * Speed up the exit process, for large files this can
@@ -270,6 +288,7 @@
 		    "be more verbose (show symbol address, etc)"),
 	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
 		    "dump raw trace in ASCII"),
+	OPT_BOOLEAN(0, "gtk", &annotate.use_gtk, "Use the GTK interface"),
 	OPT_BOOLEAN(0, "tui", &annotate.use_tui, "Use the TUI interface"),
 	OPT_BOOLEAN(0, "stdio", &annotate.use_stdio, "Use the stdio interface"),
 	OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
@@ -280,6 +299,8 @@
 		    "print matching source lines (may be slow)"),
 	OPT_BOOLEAN('P', "full-paths", &annotate.full_paths,
 		    "Don't shorten the displayed pathnames"),
+	OPT_BOOLEAN(0, "skip-missing", &annotate.skip_missing,
+		    "Skip symbols that cannot be annotated"),
 	OPT_STRING('C', "cpu", &annotate.cpu_list, "cpu", "list of cpus to profile"),
 	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
 		   "Look for files with symbols relative to this directory"),
@@ -300,6 +321,8 @@
 		use_browser = 0;
 	else if (annotate.use_tui)
 		use_browser = 1;
+	else if (annotate.use_gtk)
+		use_browser = 2;
 
 	setup_browser(true);
 
@@ -309,7 +332,8 @@
 	if (symbol__init() < 0)
 		return -1;
 
-	setup_sorting(annotate_usage, options);
+	if (setup_sorting() < 0)
+		usage_with_options(annotate_usage, options);
 
 	if (argc) {
 		/*
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index cae9a5f..77298bf 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -35,6 +35,18 @@
 /* sentinel: easy for help */
 #define suite_all { "all", "Test all benchmark suites", NULL }
 
+#ifdef LIBNUMA_SUPPORT
+static struct bench_suite numa_suites[] = {
+	{ "mem",
+	  "Benchmark for NUMA workloads",
+	  bench_numa },
+	suite_all,
+	{ NULL,
+	  NULL,
+	  NULL                  }
+};
+#endif
+
 static struct bench_suite sched_suites[] = {
 	{ "messaging",
 	  "Benchmark for scheduler and IPC mechanisms",
@@ -68,6 +80,11 @@
 };
 
 static struct bench_subsys subsystems[] = {
+#ifdef LIBNUMA_SUPPORT
+	{ "numa",
+	  "NUMA scheduling and MM behavior",
+	  numa_suites },
+#endif
 	{ "sched",
 	  "scheduler and IPC mechanism",
 	  sched_suites },
@@ -159,6 +176,7 @@
 		printf("# Running %s/%s benchmark...\n",
 		       subsys->name,
 		       suites[i].name);
+		fflush(stdout);
 
 		argv[1] = suites[i].name;
 		suites[i].fn(1, argv, NULL);
@@ -225,6 +243,7 @@
 				printf("# Running %s/%s benchmark...\n",
 				       subsystems[i].name,
 				       subsystems[i].suites[j].name);
+			fflush(stdout);
 			status = subsystems[i].suites[j].fn(argc - 1,
 							    argv + 1, prefix);
 			goto end;
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index fae8b25..c96c8fa 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -14,6 +14,7 @@
 #include "util/parse-options.h"
 #include "util/strlist.h"
 #include "util/build-id.h"
+#include "util/session.h"
 #include "util/symbol.h"
 
 static int build_id_cache__add_file(const char *filename, const char *debugdir)
@@ -58,19 +59,89 @@
 	return err;
 }
 
+static bool dso__missing_buildid_cache(struct dso *dso, int parm __maybe_unused)
+{
+	char filename[PATH_MAX];
+	u8 build_id[BUILD_ID_SIZE];
+
+	if (dso__build_id_filename(dso, filename, sizeof(filename)) &&
+	    filename__read_build_id(filename, build_id,
+				    sizeof(build_id)) != sizeof(build_id)) {
+		if (errno == ENOENT)
+			return false;
+
+		pr_warning("Problems with %s file, consider removing it from the cache\n", 
+			   filename);
+	} else if (memcmp(dso->build_id, build_id, sizeof(dso->build_id))) {
+		pr_warning("Problems with %s file, consider removing it from the cache\n", 
+			   filename);
+	}
+
+	return true;
+}
+
+static int build_id_cache__fprintf_missing(const char *filename, bool force, FILE *fp)
+{
+	struct perf_session *session = perf_session__new(filename, O_RDONLY,
+							 force, false, NULL);
+	if (session == NULL)
+		return -1;
+
+	perf_session__fprintf_dsos_buildid(session, fp, dso__missing_buildid_cache, 0);
+	perf_session__delete(session);
+
+	return 0;
+}
+
+static int build_id_cache__update_file(const char *filename,
+				       const char *debugdir)
+{
+	u8 build_id[BUILD_ID_SIZE];
+	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+
+	int err;
+
+	if (filename__read_build_id(filename, &build_id, sizeof(build_id)) < 0) {
+		pr_debug("Couldn't read a build-id in %s\n", filename);
+		return -1;
+	}
+
+	build_id__sprintf(build_id, sizeof(build_id), sbuild_id);
+	err = build_id_cache__remove_s(sbuild_id, debugdir);
+	if (!err) {
+		err = build_id_cache__add_s(sbuild_id, debugdir, filename,
+					    false, false);
+	}
+	if (verbose)
+		pr_info("Updating %s %s: %s\n", sbuild_id, filename,
+			err ? "FAIL" : "Ok");
+
+	return err;
+}
+
 int cmd_buildid_cache(int argc, const char **argv,
 		      const char *prefix __maybe_unused)
 {
 	struct strlist *list;
 	struct str_node *pos;
+	int ret = 0;
+	bool force = false;
 	char debugdir[PATH_MAX];
 	char const *add_name_list_str = NULL,
-		   *remove_name_list_str = NULL;
+		   *remove_name_list_str = NULL,
+		   *missing_filename = NULL,
+		   *update_name_list_str = NULL;
+
 	const struct option buildid_cache_options[] = {
 	OPT_STRING('a', "add", &add_name_list_str,
 		   "file list", "file(s) to add"),
 	OPT_STRING('r', "remove", &remove_name_list_str, "file list",
 		    "file(s) to remove"),
+	OPT_STRING('M', "missing", &missing_filename, "file",
+		   "to find missing build ids in the cache"),
+	OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
+	OPT_STRING('u', "update", &update_name_list_str, "file list",
+		    "file(s) to update"),
 	OPT_INCR('v', "verbose", &verbose, "be more verbose"),
 	OPT_END()
 	};
@@ -125,5 +196,26 @@
 		}
 	}
 
-	return 0;
+	if (missing_filename)
+		ret = build_id_cache__fprintf_missing(missing_filename, force, stdout);
+
+	if (update_name_list_str) {
+		list = strlist__new(true, update_name_list_str);
+		if (list) {
+			strlist__for_each(pos, list)
+				if (build_id_cache__update_file(pos->s, debugdir)) {
+					if (errno == ENOENT) {
+						pr_debug("%s wasn't in the cache\n",
+							 pos->s);
+						continue;
+					}
+					pr_warning("Couldn't update %s: %s\n",
+						   pos->s, strerror(errno));
+				}
+
+			strlist__delete(list);
+		}
+	}
+
+	return ret;
 }
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index a82d99f..e74366a 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -44,23 +44,26 @@
 	return fprintf(fp, "%s\n", sbuild_id);
 }
 
+static bool dso__skip_buildid(struct dso *dso, int with_hits)
+{
+	return with_hits && !dso->hit;
+}
+
 static int perf_session__list_build_ids(bool force, bool with_hits)
 {
 	struct perf_session *session;
 
 	symbol__elf_init();
+	/*
+	 * See if this is an ELF file first:
+	 */
+	if (filename__fprintf_build_id(input_name, stdout))
+		goto out;
 
 	session = perf_session__new(input_name, O_RDONLY, force, false,
 				    &build_id__mark_dso_hit_ops);
 	if (session == NULL)
 		return -1;
-
-	/*
-	 * See if this is an ELF file first:
-	 */
-	if (filename__fprintf_build_id(session->filename, stdout))
-		goto out;
-
 	/*
 	 * in pipe-mode, the only way to get the buildids is to parse
 	 * the record stream. Buildids are stored as RECORD_HEADER_BUILD_ID
@@ -68,9 +71,9 @@
 	if (with_hits || session->fd_pipe)
 		perf_session__process_events(session, &build_id__mark_dso_hit_ops);
 
-	perf_session__fprintf_dsos_buildid(session, stdout, with_hits);
-out:
+	perf_session__fprintf_dsos_buildid(session, stdout, dso__skip_buildid, with_hits);
 	perf_session__delete(session);
+out:
 	return 0;
 }
 
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 93b852f..d207a97 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -23,7 +23,6 @@
 		  *input_new = "perf.data";
 static char	  diff__default_sort_order[] = "dso,symbol";
 static bool  force;
-static bool show_displacement;
 static bool show_period;
 static bool show_formula;
 static bool show_baseline_only;
@@ -146,58 +145,47 @@
 	return -EINVAL;
 }
 
-static double get_period_percent(struct hist_entry *he, u64 period)
+double perf_diff__period_percent(struct hist_entry *he, u64 period)
 {
 	u64 total = he->hists->stats.total_period;
 	return (period * 100.0) / total;
 }
 
-double perf_diff__compute_delta(struct hist_entry *he)
+double perf_diff__compute_delta(struct hist_entry *he, struct hist_entry *pair)
 {
-	struct hist_entry *pair = hist_entry__next_pair(he);
-	double new_percent = get_period_percent(he, he->stat.period);
-	double old_percent = pair ? get_period_percent(pair, pair->stat.period) : 0.0;
+	double new_percent = perf_diff__period_percent(he, he->stat.period);
+	double old_percent = perf_diff__period_percent(pair, pair->stat.period);
 
 	he->diff.period_ratio_delta = new_percent - old_percent;
 	he->diff.computed = true;
 	return he->diff.period_ratio_delta;
 }
 
-double perf_diff__compute_ratio(struct hist_entry *he)
+double perf_diff__compute_ratio(struct hist_entry *he, struct hist_entry *pair)
 {
-	struct hist_entry *pair = hist_entry__next_pair(he);
 	double new_period = he->stat.period;
-	double old_period = pair ? pair->stat.period : 0;
+	double old_period = pair->stat.period;
 
 	he->diff.computed = true;
-	he->diff.period_ratio = pair ? (new_period / old_period) : 0;
+	he->diff.period_ratio = new_period / old_period;
 	return he->diff.period_ratio;
 }
 
-s64 perf_diff__compute_wdiff(struct hist_entry *he)
+s64 perf_diff__compute_wdiff(struct hist_entry *he, struct hist_entry *pair)
 {
-	struct hist_entry *pair = hist_entry__next_pair(he);
 	u64 new_period = he->stat.period;
-	u64 old_period = pair ? pair->stat.period : 0;
+	u64 old_period = pair->stat.period;
 
 	he->diff.computed = true;
-
-	if (!pair)
-		he->diff.wdiff = 0;
-	else
-		he->diff.wdiff = new_period * compute_wdiff_w2 -
-				 old_period * compute_wdiff_w1;
+	he->diff.wdiff = new_period * compute_wdiff_w2 -
+			 old_period * compute_wdiff_w1;
 
 	return he->diff.wdiff;
 }
 
-static int formula_delta(struct hist_entry *he, char *buf, size_t size)
+static int formula_delta(struct hist_entry *he, struct hist_entry *pair,
+			 char *buf, size_t size)
 {
-	struct hist_entry *pair = hist_entry__next_pair(he);
-
-	if (!pair)
-		return -1;
-
 	return scnprintf(buf, size,
 			 "(%" PRIu64 " * 100 / %" PRIu64 ") - "
 			 "(%" PRIu64 " * 100 / %" PRIu64 ")",
@@ -205,41 +193,36 @@
 			  pair->stat.period, pair->hists->stats.total_period);
 }
 
-static int formula_ratio(struct hist_entry *he, char *buf, size_t size)
+static int formula_ratio(struct hist_entry *he, struct hist_entry *pair,
+			 char *buf, size_t size)
 {
-	struct hist_entry *pair = hist_entry__next_pair(he);
 	double new_period = he->stat.period;
-	double old_period = pair ? pair->stat.period : 0;
-
-	if (!pair)
-		return -1;
+	double old_period = pair->stat.period;
 
 	return scnprintf(buf, size, "%.0F / %.0F", new_period, old_period);
 }
 
-static int formula_wdiff(struct hist_entry *he, char *buf, size_t size)
+static int formula_wdiff(struct hist_entry *he, struct hist_entry *pair,
+			 char *buf, size_t size)
 {
-	struct hist_entry *pair = hist_entry__next_pair(he);
 	u64 new_period = he->stat.period;
-	u64 old_period = pair ? pair->stat.period : 0;
-
-	if (!pair)
-		return -1;
+	u64 old_period = pair->stat.period;
 
 	return scnprintf(buf, size,
 		  "(%" PRIu64 " * " "%" PRId64 ") - (%" PRIu64 " * " "%" PRId64 ")",
 		  new_period, compute_wdiff_w2, old_period, compute_wdiff_w1);
 }
 
-int perf_diff__formula(char *buf, size_t size, struct hist_entry *he)
+int perf_diff__formula(struct hist_entry *he, struct hist_entry *pair,
+		       char *buf, size_t size)
 {
 	switch (compute) {
 	case COMPUTE_DELTA:
-		return formula_delta(he, buf, size);
+		return formula_delta(he, pair, buf, size);
 	case COMPUTE_RATIO:
-		return formula_ratio(he, buf, size);
+		return formula_ratio(he, pair, buf, size);
 	case COMPUTE_WEIGHTED_DIFF:
-		return formula_wdiff(he, buf, size);
+		return formula_wdiff(he, pair, buf, size);
 	default:
 		BUG_ON(1);
 	}
@@ -292,48 +275,6 @@
 	.ordering_requires_timestamps = true,
 };
 
-static void insert_hist_entry_by_name(struct rb_root *root,
-				      struct hist_entry *he)
-{
-	struct rb_node **p = &root->rb_node;
-	struct rb_node *parent = NULL;
-	struct hist_entry *iter;
-
-	while (*p != NULL) {
-		parent = *p;
-		iter = rb_entry(parent, struct hist_entry, rb_node);
-		if (hist_entry__cmp(he, iter) < 0)
-			p = &(*p)->rb_left;
-		else
-			p = &(*p)->rb_right;
-	}
-
-	rb_link_node(&he->rb_node, parent, p);
-	rb_insert_color(&he->rb_node, root);
-}
-
-static void hists__name_resort(struct hists *self, bool sort)
-{
-	unsigned long position = 1;
-	struct rb_root tmp = RB_ROOT;
-	struct rb_node *next = rb_first(&self->entries);
-
-	while (next != NULL) {
-		struct hist_entry *n = rb_entry(next, struct hist_entry, rb_node);
-
-		next = rb_next(&n->rb_node);
-		n->position = position++;
-
-		if (sort) {
-			rb_erase(&n->rb_node, &self->entries);
-			insert_hist_entry_by_name(&tmp, n);
-		}
-	}
-
-	if (sort)
-		self->entries = tmp;
-}
-
 static struct perf_evsel *evsel_match(struct perf_evsel *evsel,
 				      struct perf_evlist *evlist)
 {
@@ -346,34 +287,34 @@
 	return NULL;
 }
 
-static void perf_evlist__resort_hists(struct perf_evlist *evlist, bool name)
+static void perf_evlist__collapse_resort(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
 
 	list_for_each_entry(evsel, &evlist->entries, node) {
 		struct hists *hists = &evsel->hists;
 
-		hists__output_resort(hists);
-
-		/*
-		 * The hists__name_resort only sets possition
-		 * if name is false.
-		 */
-		if (name || ((!name) && show_displacement))
-			hists__name_resort(hists, name);
+		hists__collapse_resort(hists);
 	}
 }
 
 static void hists__baseline_only(struct hists *hists)
 {
-	struct rb_node *next = rb_first(&hists->entries);
+	struct rb_root *root;
+	struct rb_node *next;
 
+	if (sort__need_collapse)
+		root = &hists->entries_collapsed;
+	else
+		root = hists->entries_in;
+
+	next = rb_first(root);
 	while (next != NULL) {
-		struct hist_entry *he = rb_entry(next, struct hist_entry, rb_node);
+		struct hist_entry *he = rb_entry(next, struct hist_entry, rb_node_in);
 
-		next = rb_next(&he->rb_node);
+		next = rb_next(&he->rb_node_in);
 		if (!hist_entry__next_pair(he)) {
-			rb_erase(&he->rb_node, &hists->entries);
+			rb_erase(&he->rb_node_in, root);
 			hist_entry__free(he);
 		}
 	}
@@ -385,18 +326,21 @@
 
 	while (next != NULL) {
 		struct hist_entry *he = rb_entry(next, struct hist_entry, rb_node);
+		struct hist_entry *pair = hist_entry__next_pair(he);
 
 		next = rb_next(&he->rb_node);
+		if (!pair)
+			continue;
 
 		switch (compute) {
 		case COMPUTE_DELTA:
-			perf_diff__compute_delta(he);
+			perf_diff__compute_delta(he, pair);
 			break;
 		case COMPUTE_RATIO:
-			perf_diff__compute_ratio(he);
+			perf_diff__compute_ratio(he, pair);
 			break;
 		case COMPUTE_WEIGHTED_DIFF:
-			perf_diff__compute_wdiff(he);
+			perf_diff__compute_wdiff(he, pair);
 			break;
 		default:
 			BUG_ON(1);
@@ -470,19 +414,30 @@
 
 static void hists__compute_resort(struct hists *hists)
 {
-	struct rb_root tmp = RB_ROOT;
-	struct rb_node *next = rb_first(&hists->entries);
+	struct rb_root *root;
+	struct rb_node *next;
+
+	if (sort__need_collapse)
+		root = &hists->entries_collapsed;
+	else
+		root = hists->entries_in;
+
+	hists->entries = RB_ROOT;
+	next = rb_first(root);
+
+	hists->nr_entries = 0;
+	hists->stats.total_period = 0;
+	hists__reset_col_len(hists);
 
 	while (next != NULL) {
-		struct hist_entry *he = rb_entry(next, struct hist_entry, rb_node);
+		struct hist_entry *he;
 
-		next = rb_next(&he->rb_node);
+		he = rb_entry(next, struct hist_entry, rb_node_in);
+		next = rb_next(&he->rb_node_in);
 
-		rb_erase(&he->rb_node, &hists->entries);
-		insert_hist_entry_by_compute(&tmp, he, compute);
+		insert_hist_entry_by_compute(&hists->entries, he, compute);
+		hists__inc_nr_entries(hists, he);
 	}
-
-	hists->entries = tmp;
 }
 
 static void hists__process(struct hists *old, struct hists *new)
@@ -497,6 +452,8 @@
 	if (sort_compute) {
 		hists__precompute(new);
 		hists__compute_resort(new);
+	} else {
+		hists__output_resort(new);
 	}
 
 	hists__fprintf(new, true, 0, 0, stdout);
@@ -528,8 +485,8 @@
 	evlist_old = older->evlist;
 	evlist_new = newer->evlist;
 
-	perf_evlist__resort_hists(evlist_old, true);
-	perf_evlist__resort_hists(evlist_new, false);
+	perf_evlist__collapse_resort(evlist_old);
+	perf_evlist__collapse_resort(evlist_new);
 
 	list_for_each_entry(evsel, &evlist_new->entries, node) {
 		struct perf_evsel *evsel_old;
@@ -562,8 +519,6 @@
 static const struct option options[] = {
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show symbol address, etc)"),
-	OPT_BOOLEAN('M', "displacement", &show_displacement,
-		    "Show position displacement relative to baseline"),
 	OPT_BOOLEAN('b', "baseline-only", &show_baseline_only,
 		    "Show only items with match in baseline"),
 	OPT_CALLBACK('c', "compute", &compute,
@@ -597,40 +552,32 @@
 
 static void ui_init(void)
 {
-	perf_hpp__init();
-
-	/* No overhead column. */
-	perf_hpp__column_enable(PERF_HPP__OVERHEAD, false);
-
 	/*
-	 * Display baseline/delta/ratio/displacement/
+	 * Display baseline/delta/ratio
 	 * formula/periods columns.
 	 */
-	perf_hpp__column_enable(PERF_HPP__BASELINE, true);
+	perf_hpp__column_enable(PERF_HPP__BASELINE);
 
 	switch (compute) {
 	case COMPUTE_DELTA:
-		perf_hpp__column_enable(PERF_HPP__DELTA, true);
+		perf_hpp__column_enable(PERF_HPP__DELTA);
 		break;
 	case COMPUTE_RATIO:
-		perf_hpp__column_enable(PERF_HPP__RATIO, true);
+		perf_hpp__column_enable(PERF_HPP__RATIO);
 		break;
 	case COMPUTE_WEIGHTED_DIFF:
-		perf_hpp__column_enable(PERF_HPP__WEIGHTED_DIFF, true);
+		perf_hpp__column_enable(PERF_HPP__WEIGHTED_DIFF);
 		break;
 	default:
 		BUG_ON(1);
 	};
 
-	if (show_displacement)
-		perf_hpp__column_enable(PERF_HPP__DISPL, true);
-
 	if (show_formula)
-		perf_hpp__column_enable(PERF_HPP__FORMULA, true);
+		perf_hpp__column_enable(PERF_HPP__FORMULA);
 
 	if (show_period) {
-		perf_hpp__column_enable(PERF_HPP__PERIOD, true);
-		perf_hpp__column_enable(PERF_HPP__PERIOD_BASELINE, true);
+		perf_hpp__column_enable(PERF_HPP__PERIOD);
+		perf_hpp__column_enable(PERF_HPP__PERIOD_BASELINE);
 	}
 }
 
@@ -658,7 +605,9 @@
 
 	ui_init();
 
-	setup_sorting(diff_usage, options);
+	if (setup_sorting() < 0)
+		usage_with_options(diff_usage, options);
+
 	setup_pager();
 
 	sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso", NULL);
diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c
index c20f1dc..05bd9df 100644
--- a/tools/perf/builtin-evlist.c
+++ b/tools/perf/builtin-evlist.c
@@ -15,39 +15,6 @@
 #include "util/parse-options.h"
 #include "util/session.h"
 
-struct perf_attr_details {
-	bool freq;
-	bool verbose;
-};
-
-static int comma_printf(bool *first, const char *fmt, ...)
-{
-	va_list args;
-	int ret = 0;
-
-	if (!*first) {
-		ret += printf(",");
-	} else {
-		ret += printf(":");
-		*first = false;
-	}
-
-	va_start(args, fmt);
-	ret += vprintf(fmt, args);
-	va_end(args);
-	return ret;
-}
-
-static int __if_print(bool *first, const char *field, u64 value)
-{
-	if (value == 0)
-		return 0;
-
-	return comma_printf(first, " %s: %" PRIu64, field, value);
-}
-
-#define if_print(field) __if_print(&first, #field, pos->attr.field)
-
 static int __cmd_evlist(const char *file_name, struct perf_attr_details *details)
 {
 	struct perf_session *session;
@@ -57,52 +24,8 @@
 	if (session == NULL)
 		return -ENOMEM;
 
-	list_for_each_entry(pos, &session->evlist->entries, node) {
-		bool first = true;
-
-		printf("%s", perf_evsel__name(pos));
-
-		if (details->verbose || details->freq) {
-			comma_printf(&first, " sample_freq=%" PRIu64,
-				     (u64)pos->attr.sample_freq);
-		}
-
-		if (details->verbose) {
-			if_print(type);
-			if_print(config);
-			if_print(config1);
-			if_print(config2);
-			if_print(size);
-			if_print(sample_type);
-			if_print(read_format);
-			if_print(disabled);
-			if_print(inherit);
-			if_print(pinned);
-			if_print(exclusive);
-			if_print(exclude_user);
-			if_print(exclude_kernel);
-			if_print(exclude_hv);
-			if_print(exclude_idle);
-			if_print(mmap);
-			if_print(comm);
-			if_print(freq);
-			if_print(inherit_stat);
-			if_print(enable_on_exec);
-			if_print(task);
-			if_print(watermark);
-			if_print(precise_ip);
-			if_print(mmap_data);
-			if_print(sample_id_all);
-			if_print(exclude_host);
-			if_print(exclude_guest);
-			if_print(__reserved_1);
-			if_print(wakeup_events);
-			if_print(bp_type);
-			if_print(branch_sample_type);
-		}
-
-		putchar('\n');
-	}
+	list_for_each_entry(pos, &session->evlist->entries, node)
+		perf_evsel__fprintf(pos, details, stdout);
 
 	perf_session__delete(session);
 	return 0;
@@ -116,6 +39,8 @@
 	OPT_BOOLEAN('F', "freq", &details.freq, "Show the sample frequency"),
 	OPT_BOOLEAN('v', "verbose", &details.verbose,
 		    "Show all event attr details"),
+	OPT_BOOLEAN('g', "group", &details.event_group,
+		    "Show event group information"),
 	OPT_END()
 	};
 	const char * const evlist_usage[] = {
@@ -127,5 +52,10 @@
 	if (argc)
 		usage_with_options(evlist_usage, options);
 
+	if (details.event_group && (details.verbose || details.freq)) {
+		pr_err("--group option is not compatible with other options\n");
+		usage_with_options(evlist_usage, options);
+	}
+
 	return __cmd_evlist(input_name, &details);
 }
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 0b4b796..46878da 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -17,6 +17,7 @@
 #include "util/debug.h"
 
 #include <linux/rbtree.h>
+#include <linux/string.h>
 
 struct alloc_stat;
 typedef int (*sort_fn_t)(struct alloc_stat *, struct alloc_stat *);
@@ -340,7 +341,7 @@
 			   int n_lines, int is_caller)
 {
 	struct rb_node *next;
-	struct machine *machine;
+	struct machine *machine = &session->machines.host;
 
 	printf("%.102s\n", graph_dotted_line);
 	printf(" %-34s |",  is_caller ? "Callsite": "Alloc Ptr");
@@ -349,11 +350,6 @@
 
 	next = rb_first(root);
 
-	machine = perf_session__find_host_machine(session);
-	if (!machine) {
-		pr_err("__print_result: couldn't find kernel information\n");
-		return;
-	}
 	while (next && n_lines--) {
 		struct alloc_stat *data = rb_entry(next, struct alloc_stat,
 						   node);
@@ -614,8 +610,7 @@
 	&pingpong_sort_dimension,
 };
 
-#define NUM_AVAIL_SORTS	\
-	(int)(sizeof(avail_sorts) / sizeof(struct sort_dimension *))
+#define NUM_AVAIL_SORTS	((int)ARRAY_SIZE(avail_sorts))
 
 static int sort_dimension__add(const char *tok, struct list_head *list)
 {
@@ -624,12 +619,11 @@
 
 	for (i = 0; i < NUM_AVAIL_SORTS; i++) {
 		if (!strcmp(avail_sorts[i]->name, tok)) {
-			sort = malloc(sizeof(*sort));
+			sort = memdup(avail_sorts[i], sizeof(*avail_sorts[i]));
 			if (!sort) {
-				pr_err("%s: malloc failed\n", __func__);
+				pr_err("%s: memdup failed\n", __func__);
 				return -1;
 			}
-			memcpy(sort, avail_sorts[i], sizeof(*sort));
 			list_add_tail(&sort->list, list);
 			return 0;
 		}
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index ca3f80e..37a769d 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -973,8 +973,7 @@
 
 int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused)
 {
-	const char *file_name;
-
+	const char *file_name = NULL;
 	const struct option kvm_options[] = {
 		OPT_STRING('i', "input", &file_name, "file",
 			   "Input file name"),
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index f3151d3..774c907 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -224,130 +224,28 @@
 
 static int perf_record__open(struct perf_record *rec)
 {
+	char msg[512];
 	struct perf_evsel *pos;
 	struct perf_evlist *evlist = rec->evlist;
 	struct perf_session *session = rec->session;
 	struct perf_record_opts *opts = &rec->opts;
 	int rc = 0;
 
-	/*
-	 * Set the evsel leader links before we configure attributes,
-	 * since some might depend on this info.
-	 */
-	if (opts->group)
-		perf_evlist__set_leader(evlist);
-
-	perf_evlist__config_attrs(evlist, opts);
+	perf_evlist__config(evlist, opts);
 
 	list_for_each_entry(pos, &evlist->entries, node) {
-		struct perf_event_attr *attr = &pos->attr;
-		/*
-		 * Check if parse_single_tracepoint_event has already asked for
-		 * PERF_SAMPLE_TIME.
-		 *
-		 * XXX this is kludgy but short term fix for problems introduced by
-		 * eac23d1c that broke 'perf script' by having different sample_types
-		 * when using multiple tracepoint events when we use a perf binary
-		 * that tries to use sample_id_all on an older kernel.
-		 *
-		 * We need to move counter creation to perf_session, support
-		 * different sample_types, etc.
-		 */
-		bool time_needed = attr->sample_type & PERF_SAMPLE_TIME;
-
-fallback_missing_features:
-		if (opts->exclude_guest_missing)
-			attr->exclude_guest = attr->exclude_host = 0;
-retry_sample_id:
-		attr->sample_id_all = opts->sample_id_all_missing ? 0 : 1;
 try_again:
 		if (perf_evsel__open(pos, evlist->cpus, evlist->threads) < 0) {
-			int err = errno;
-
-			if (err == EPERM || err == EACCES) {
-				ui__error_paranoid();
-				rc = -err;
-				goto out;
-			} else if (err ==  ENODEV && opts->target.cpu_list) {
-				pr_err("No such device - did you specify"
-				       " an out-of-range profile CPU?\n");
-				rc = -err;
-				goto out;
-			} else if (err == EINVAL) {
-				if (!opts->exclude_guest_missing &&
-				    (attr->exclude_guest || attr->exclude_host)) {
-					pr_debug("Old kernel, cannot exclude "
-						 "guest or host samples.\n");
-					opts->exclude_guest_missing = true;
-					goto fallback_missing_features;
-				} else if (!opts->sample_id_all_missing) {
-					/*
-					 * Old kernel, no attr->sample_id_type_all field
-					 */
-					opts->sample_id_all_missing = true;
-					if (!opts->sample_time && !opts->raw_samples && !time_needed)
-						attr->sample_type &= ~PERF_SAMPLE_TIME;
-
-					goto retry_sample_id;
-				}
-			}
-
-			/*
-			 * If it's cycles then fall back to hrtimer
-			 * based cpu-clock-tick sw counter, which
-			 * is always available even if no PMU support.
-			 *
-			 * PPC returns ENXIO until 2.6.37 (behavior changed
-			 * with commit b0a873e).
-			 */
-			if ((err == ENOENT || err == ENXIO)
-					&& attr->type == PERF_TYPE_HARDWARE
-					&& attr->config == PERF_COUNT_HW_CPU_CYCLES) {
-
+			if (perf_evsel__fallback(pos, errno, msg, sizeof(msg))) {
 				if (verbose)
-					ui__warning("The cycles event is not supported, "
-						    "trying to fall back to cpu-clock-ticks\n");
-				attr->type = PERF_TYPE_SOFTWARE;
-				attr->config = PERF_COUNT_SW_CPU_CLOCK;
-				if (pos->name) {
-					free(pos->name);
-					pos->name = NULL;
-				}
+					ui__warning("%s\n", msg);
 				goto try_again;
 			}
 
-			if (err == ENOENT) {
-				ui__error("The %s event is not supported.\n",
-					  perf_evsel__name(pos));
-				rc = -err;
-				goto out;
-			} else if ((err == EOPNOTSUPP) && (attr->precise_ip)) {
-				ui__error("\'precise\' request may not be supported. "
-					  "Try removing 'p' modifier\n");
-				rc = -err;
-				goto out;
-			}
-
-			printf("\n");
-			error("sys_perf_event_open() syscall returned with %d "
-			      "(%s) for event %s. /bin/dmesg may provide "
-			      "additional information.\n",
-			      err, strerror(err), perf_evsel__name(pos));
-
-#if defined(__i386__) || defined(__x86_64__)
-			if (attr->type == PERF_TYPE_HARDWARE &&
-			    err == EOPNOTSUPP) {
-				pr_err("No hardware sampling interrupt available."
-				       " No APIC? If so then you can boot the kernel"
-				       " with the \"lapic\" boot parameter to"
-				       " force-enable it.\n");
-				rc = -err;
-				goto out;
-			}
-#endif
-
-			pr_err("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
-			rc = -err;
+			rc = -errno;
+			perf_evsel__open_strerror(pos, &opts->target,
+						  errno, msg, sizeof(msg));
+			ui__error("%s\n", msg);
 			goto out;
 		}
 	}
@@ -430,10 +328,6 @@
 {
 	int err;
 	struct perf_tool *tool = data;
-
-	if (machine__is_host(machine))
-		return;
-
 	/*
 	 *As for guest kernel when processing subcommand record&report,
 	 *we arrange module mmap prior to guest kernel mmap and trigger
@@ -592,6 +486,9 @@
 		goto out_delete_session;
 	}
 
+	if (!evsel_list->nr_groups)
+		perf_header__clear_feat(&session->header, HEADER_GROUP_DESC);
+
 	/*
 	 * perf_session__delete(session) will be called at perf_record__exit()
 	 */
@@ -618,12 +515,7 @@
 
 	rec->post_processing_offset = lseek(output, 0, SEEK_CUR);
 
-	machine = perf_session__find_host_machine(session);
-	if (!machine) {
-		pr_err("Couldn't find native kernel information.\n");
-		err = -1;
-		goto out_delete_session;
-	}
+	machine = &session->machines.host;
 
 	if (opts->pipe_output) {
 		err = perf_event__synthesize_attrs(tool, session,
@@ -676,9 +568,10 @@
 		       "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
 		       "Check /proc/modules permission or run as root.\n");
 
-	if (perf_guest)
-		perf_session__process_machines(session, tool,
-					       perf_event__synthesize_guest_os);
+	if (perf_guest) {
+		machines__process_guests(&session->machines,
+					 perf_event__synthesize_guest_os, tool);
+	}
 
 	if (!opts->target.system_wide)
 		err = perf_event__synthesize_thread_map(tool, evsel_list->threads,
@@ -875,11 +768,10 @@
 }
 #endif /* LIBUNWIND_SUPPORT */
 
-static int
-parse_callchain_opt(const struct option *opt __maybe_unused, const char *arg,
-		    int unset)
+int record_parse_callchain_opt(const struct option *opt,
+			       const char *arg, int unset)
 {
-	struct perf_record *rec = (struct perf_record *)opt->value;
+	struct perf_record_opts *opts = opt->value;
 	char *tok, *name, *saveptr = NULL;
 	char *buf;
 	int ret = -1;
@@ -905,7 +797,7 @@
 		/* Framepointer style */
 		if (!strncmp(name, "fp", sizeof("fp"))) {
 			if (!strtok_r(NULL, ",", &saveptr)) {
-				rec->opts.call_graph = CALLCHAIN_FP;
+				opts->call_graph = CALLCHAIN_FP;
 				ret = 0;
 			} else
 				pr_err("callchain: No more arguments "
@@ -918,20 +810,20 @@
 			const unsigned long default_stack_dump_size = 8192;
 
 			ret = 0;
-			rec->opts.call_graph = CALLCHAIN_DWARF;
-			rec->opts.stack_dump_size = default_stack_dump_size;
+			opts->call_graph = CALLCHAIN_DWARF;
+			opts->stack_dump_size = default_stack_dump_size;
 
 			tok = strtok_r(NULL, ",", &saveptr);
 			if (tok) {
 				unsigned long size = 0;
 
 				ret = get_stack_size(tok, &size);
-				rec->opts.stack_dump_size = size;
+				opts->stack_dump_size = size;
 			}
 
 			if (!ret)
 				pr_debug("callchain: stack dump size %d\n",
-					 rec->opts.stack_dump_size);
+					 opts->stack_dump_size);
 #endif /* LIBUNWIND_SUPPORT */
 		} else {
 			pr_err("callchain: Unknown -g option "
@@ -944,7 +836,7 @@
 	free(buf);
 
 	if (!ret)
-		pr_debug("callchain: type %d\n", rec->opts.call_graph);
+		pr_debug("callchain: type %d\n", opts->call_graph);
 
 	return ret;
 }
@@ -982,9 +874,9 @@
 #define CALLCHAIN_HELP "do call-graph (stack chain/backtrace) recording: "
 
 #ifdef LIBUNWIND_SUPPORT
-static const char callchain_help[] = CALLCHAIN_HELP "[fp] dwarf";
+const char record_callchain_help[] = CALLCHAIN_HELP "[fp] dwarf";
 #else
-static const char callchain_help[] = CALLCHAIN_HELP "[fp]";
+const char record_callchain_help[] = CALLCHAIN_HELP "[fp]";
 #endif
 
 /*
@@ -1028,9 +920,9 @@
 		     "number of mmap data pages"),
 	OPT_BOOLEAN(0, "group", &record.opts.group,
 		    "put the counters into a counter group"),
-	OPT_CALLBACK_DEFAULT('g', "call-graph", &record, "mode[,dump_size]",
-			     callchain_help, &parse_callchain_opt,
-			     "fp"),
+	OPT_CALLBACK_DEFAULT('g', "call-graph", &record.opts,
+			     "mode[,dump_size]", record_callchain_help,
+			     &record_parse_callchain_opt, "fp"),
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show counter open errors, etc)"),
 	OPT_BOOLEAN('q', "quiet", &quiet, "don't print any message"),
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index fc25100..96b5a7f 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -8,6 +8,7 @@
 #include "builtin.h"
 
 #include "util/util.h"
+#include "util/cache.h"
 
 #include "util/annotate.h"
 #include "util/color.h"
@@ -54,6 +55,16 @@
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
 
+static int perf_report_config(const char *var, const char *value, void *cb)
+{
+	if (!strcmp(var, "report.group")) {
+		symbol_conf.event_group = perf_config_bool(var, value);
+		return 0;
+	}
+
+	return perf_default_config(var, value, cb);
+}
+
 static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
 					struct addr_location *al,
 					struct perf_sample *sample,
@@ -299,6 +310,21 @@
 	char unit;
 	unsigned long nr_samples = self->stats.nr_events[PERF_RECORD_SAMPLE];
 	u64 nr_events = self->stats.total_period;
+	struct perf_evsel *evsel = hists_to_evsel(self);
+	char buf[512];
+	size_t size = sizeof(buf);
+
+	if (symbol_conf.event_group && evsel->nr_members > 1) {
+		struct perf_evsel *pos;
+
+		perf_evsel__group_desc(evsel, buf, size);
+		evname = buf;
+
+		for_each_group_member(pos, evsel) {
+			nr_samples += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE];
+			nr_events += pos->hists.stats.total_period;
+		}
+	}
 
 	nr_samples = convert_unit(nr_samples, &unit);
 	ret = fprintf(fp, "# Samples: %lu%c", nr_samples, unit);
@@ -319,6 +345,10 @@
 		struct hists *hists = &pos->hists;
 		const char *evname = perf_evsel__name(pos);
 
+		if (symbol_conf.event_group &&
+		    !perf_evsel__is_group_leader(pos))
+			continue;
+
 		hists__fprintf_nr_sample_events(hists, evname, stdout);
 		hists__fprintf(hists, true, 0, 0, stdout);
 		fprintf(stdout, "\n\n");
@@ -372,7 +402,7 @@
 	if (ret)
 		goto out_delete;
 
-	kernel_map = session->host_machine.vmlinux_maps[MAP__FUNCTION];
+	kernel_map = session->machines.host.vmlinux_maps[MAP__FUNCTION];
 	kernel_kmap = map__kmap(kernel_map);
 	if (kernel_map == NULL ||
 	    (kernel_map->dso->hit &&
@@ -416,8 +446,16 @@
 			hists->symbol_filter_str = rep->symbol_filter_str;
 
 		hists__collapse_resort(hists);
-		hists__output_resort(hists);
 		nr_samples += hists->stats.nr_events[PERF_RECORD_SAMPLE];
+
+		/* Non-group events are considered as leader */
+		if (symbol_conf.event_group &&
+		    !perf_evsel__is_group_leader(pos)) {
+			struct hists *leader_hists = &pos->leader->hists;
+
+			hists__match(leader_hists, hists);
+			hists__link(leader_hists, hists);
+		}
 	}
 
 	if (nr_samples == 0) {
@@ -425,11 +463,22 @@
 		goto out_delete;
 	}
 
+	list_for_each_entry(pos, &session->evlist->entries, node)
+		hists__output_resort(&pos->hists);
+
 	if (use_browser > 0) {
 		if (use_browser == 1) {
-			perf_evlist__tui_browse_hists(session->evlist, help,
-						      NULL,
-						      &session->header.env);
+			ret = perf_evlist__tui_browse_hists(session->evlist,
+							help,
+							NULL,
+							&session->header.env);
+			/*
+			 * Usually "ret" is the last pressed key, and we only
+			 * care if the key notifies us to switch data file.
+			 */
+			if (ret != K_SWITCH_INPUT_DATA)
+				ret = 0;
+
 		} else if (use_browser == 2) {
 			perf_evlist__gtk_browse_hists(session->evlist, help,
 						      NULL);
@@ -595,8 +644,8 @@
 	OPT_BOOLEAN(0, "stdio", &report.use_stdio,
 		    "Use the stdio interface"),
 	OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
-		   "sort by key(s): pid, comm, dso, symbol, parent, dso_to,"
-		   " dso_from, symbol_to, symbol_from, mispredict"),
+		   "sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline,"
+		   " dso_to, dso_from, symbol_to, symbol_from, mispredict"),
 	OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization,
 		    "Show sample percentage for different cpu modes"),
 	OPT_STRING('p', "parent", &parent_pattern, "regex",
@@ -638,6 +687,8 @@
 		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
 	OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
 		    "Show a column with the sum of periods"),
+	OPT_BOOLEAN(0, "group", &symbol_conf.event_group,
+		    "Show event group information together"),
 	OPT_CALLBACK_NOOPT('b', "branch-stack", &sort__branch_mode, "",
 		    "use branch records for histogram filling", parse_branch_mode),
 	OPT_STRING(0, "objdump", &objdump_path, "path",
@@ -645,6 +696,8 @@
 	OPT_END()
 	};
 
+	perf_config(perf_report_config, NULL);
+
 	argc = parse_options(argc, argv, options, report_usage, 0);
 
 	if (report.use_stdio)
@@ -663,6 +716,16 @@
 		else
 			input_name = "perf.data";
 	}
+
+	if (strcmp(input_name, "-") != 0)
+		setup_browser(true);
+	else {
+		use_browser = 0;
+		perf_hpp__column_enable(PERF_HPP__OVERHEAD);
+		perf_hpp__init();
+	}
+
+repeat:
 	session = perf_session__new(input_name, O_RDONLY,
 				    report.force, false, &report.tool);
 	if (session == NULL)
@@ -688,14 +751,8 @@
 
 	}
 
-	if (strcmp(input_name, "-") != 0)
-		setup_browser(true);
-	else {
-		use_browser = 0;
-		perf_hpp__init();
-	}
-
-	setup_sorting(report_usage, options);
+	if (setup_sorting() < 0)
+		usage_with_options(report_usage, options);
 
 	/*
 	 * Only in the newt browser we are doing integrated annotation,
@@ -763,6 +820,12 @@
 	}
 
 	ret = __cmd_report(&report);
+	if (ret == K_SWITCH_INPUT_DATA) {
+		perf_session__delete(session);
+		goto repeat;
+	} else
+		ret = 0;
+
 error:
 	perf_session__delete(session);
 	return ret;
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index cc28b85..1382294 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -1475,9 +1475,9 @@
 			goto out_delete;
 		}
 
-		sched->nr_events      = session->hists.stats.nr_events[0];
-		sched->nr_lost_events = session->hists.stats.total_lost;
-		sched->nr_lost_chunks = session->hists.stats.nr_events[PERF_RECORD_LOST];
+		sched->nr_events      = session->stats.nr_events[0];
+		sched->nr_lost_events = session->stats.total_lost;
+		sched->nr_lost_chunks = session->stats.nr_events[PERF_RECORD_LOST];
 	}
 
 	if (destroy)
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index b363e7b..92d4658 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -692,7 +692,7 @@
 			    const char *arg, int unset __maybe_unused)
 {
 	char *tok;
-	int i, imax = sizeof(all_output_options) / sizeof(struct output_option);
+	int i, imax = ARRAY_SIZE(all_output_options);
 	int j;
 	int rc = 0;
 	char *str = strdup(arg);
@@ -909,18 +909,6 @@
 	return NULL;
 }
 
-static char *ltrim(char *str)
-{
-	int len = strlen(str);
-
-	while (len && isspace(*str)) {
-		len--;
-		str++;
-	}
-
-	return str;
-}
-
 static int read_script_info(struct script_desc *desc, const char *filename)
 {
 	char line[BUFSIZ], *p;
@@ -1487,7 +1475,8 @@
 			return -1;
 	}
 
-	perf_session__fprintf_info(session, stdout, show_full_info);
+	if (!script_name && !generate_script_lang)
+		perf_session__fprintf_info(session, stdout, show_full_info);
 
 	if (!no_callchain)
 		symbol_conf.use_callchain = true;
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index c247fac..9984876 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -65,6 +65,11 @@
 #define CNTR_NOT_SUPPORTED	"<not supported>"
 #define CNTR_NOT_COUNTED	"<not counted>"
 
+static void print_stat(int argc, const char **argv);
+static void print_counter_aggr(struct perf_evsel *counter, char *prefix);
+static void print_counter(struct perf_evsel *counter, char *prefix);
+static void print_aggr_socket(char *prefix);
+
 static struct perf_evlist	*evsel_list;
 
 static struct perf_target	target = {
@@ -75,6 +80,7 @@
 static bool			no_inherit			= false;
 static bool			scale				=  true;
 static bool			no_aggr				= false;
+static bool			aggr_socket			= false;
 static pid_t			child_pid			= -1;
 static bool			null_run			=  false;
 static int			detailed_run			=  0;
@@ -87,6 +93,9 @@
 static const char		*pre_cmd			= NULL;
 static const char		*post_cmd			= NULL;
 static bool			sync_run			= false;
+static unsigned int		interval			= 0;
+static struct timespec		ref_time;
+static struct cpu_map		*sock_map;
 
 static volatile int done = 0;
 
@@ -94,6 +103,28 @@
 	struct stats	  res_stats[3];
 };
 
+static inline void diff_timespec(struct timespec *r, struct timespec *a,
+				 struct timespec *b)
+{
+	r->tv_sec = a->tv_sec - b->tv_sec;
+	if (a->tv_nsec < b->tv_nsec) {
+		r->tv_nsec = a->tv_nsec + 1000000000L - b->tv_nsec;
+		r->tv_sec--;
+	} else {
+		r->tv_nsec = a->tv_nsec - b->tv_nsec ;
+	}
+}
+
+static inline struct cpu_map *perf_evsel__cpus(struct perf_evsel *evsel)
+{
+	return (evsel->cpus && !target.cpu_list) ? evsel->cpus : evsel_list->cpus;
+}
+
+static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel)
+{
+	return perf_evsel__cpus(evsel)->nr;
+}
+
 static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
 {
 	evsel->priv = zalloc(sizeof(struct perf_stat));
@@ -106,14 +137,27 @@
 	evsel->priv = NULL;
 }
 
-static inline struct cpu_map *perf_evsel__cpus(struct perf_evsel *evsel)
+static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel)
 {
-	return (evsel->cpus && !target.cpu_list) ? evsel->cpus : evsel_list->cpus;
+	void *addr;
+	size_t sz;
+
+	sz = sizeof(*evsel->counts) +
+	     (perf_evsel__nr_cpus(evsel) * sizeof(struct perf_counts_values));
+
+	addr = zalloc(sz);
+	if (!addr)
+		return -ENOMEM;
+
+	evsel->prev_raw_counts =  addr;
+
+	return 0;
 }
 
-static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel)
+static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
 {
-	return perf_evsel__cpus(evsel)->nr;
+	free(evsel->prev_raw_counts);
+	evsel->prev_raw_counts = NULL;
 }
 
 static struct stats runtime_nsecs_stats[MAX_NR_CPUS];
@@ -132,8 +176,6 @@
 static int create_perf_stat_counter(struct perf_evsel *evsel)
 {
 	struct perf_event_attr *attr = &evsel->attr;
-	bool exclude_guest_missing = false;
-	int ret;
 
 	if (scale)
 		attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
@@ -141,38 +183,16 @@
 
 	attr->inherit = !no_inherit;
 
-retry:
-	if (exclude_guest_missing)
-		evsel->attr.exclude_guest = evsel->attr.exclude_host = 0;
-
-	if (perf_target__has_cpu(&target)) {
-		ret = perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel));
-		if (ret)
-			goto check_ret;
-		return 0;
-	}
+	if (perf_target__has_cpu(&target))
+		return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel));
 
 	if (!perf_target__has_task(&target) &&
-	    !perf_evsel__is_group_member(evsel)) {
+	    perf_evsel__is_group_leader(evsel)) {
 		attr->disabled = 1;
 		attr->enable_on_exec = 1;
 	}
 
-	ret = perf_evsel__open_per_thread(evsel, evsel_list->threads);
-	if (!ret)
-		return 0;
-	/* fall through */
-check_ret:
-	if (ret && errno == EINVAL) {
-		if (!exclude_guest_missing &&
-		    (evsel->attr.exclude_guest || evsel->attr.exclude_host)) {
-			pr_debug("Old kernel, cannot exclude "
-				 "guest or host samples.\n");
-			exclude_guest_missing = true;
-			goto retry;
-		}
-	}
-	return ret;
+	return perf_evsel__open_per_thread(evsel, evsel_list->threads);
 }
 
 /*
@@ -269,15 +289,79 @@
 	return 0;
 }
 
+static void print_interval(void)
+{
+	static int num_print_interval;
+	struct perf_evsel *counter;
+	struct perf_stat *ps;
+	struct timespec ts, rs;
+	char prefix[64];
+
+	if (no_aggr) {
+		list_for_each_entry(counter, &evsel_list->entries, node) {
+			ps = counter->priv;
+			memset(ps->res_stats, 0, sizeof(ps->res_stats));
+			read_counter(counter);
+		}
+	} else {
+		list_for_each_entry(counter, &evsel_list->entries, node) {
+			ps = counter->priv;
+			memset(ps->res_stats, 0, sizeof(ps->res_stats));
+			read_counter_aggr(counter);
+		}
+	}
+	clock_gettime(CLOCK_MONOTONIC, &ts);
+	diff_timespec(&rs, &ts, &ref_time);
+	sprintf(prefix, "%6lu.%09lu%s", rs.tv_sec, rs.tv_nsec, csv_sep);
+
+	if (num_print_interval == 0 && !csv_output) {
+		if (aggr_socket)
+			fprintf(output, "#           time socket cpus             counts events\n");
+		else if (no_aggr)
+			fprintf(output, "#           time CPU                 counts events\n");
+		else
+			fprintf(output, "#           time             counts events\n");
+	}
+
+	if (++num_print_interval == 25)
+		num_print_interval = 0;
+
+	if (aggr_socket)
+		print_aggr_socket(prefix);
+	else if (no_aggr) {
+		list_for_each_entry(counter, &evsel_list->entries, node)
+			print_counter(counter, prefix);
+	} else {
+		list_for_each_entry(counter, &evsel_list->entries, node)
+			print_counter_aggr(counter, prefix);
+	}
+}
+
 static int __run_perf_stat(int argc __maybe_unused, const char **argv)
 {
+	char msg[512];
 	unsigned long long t0, t1;
 	struct perf_evsel *counter;
+	struct timespec ts;
 	int status = 0;
 	int child_ready_pipe[2], go_pipe[2];
 	const bool forks = (argc > 0);
 	char buf;
 
+	if (interval) {
+		ts.tv_sec  = interval / 1000;
+		ts.tv_nsec = (interval % 1000) * 1000000;
+	} else {
+		ts.tv_sec  = 1;
+		ts.tv_nsec = 0;
+	}
+
+	if (aggr_socket
+	    && cpu_map__build_socket_map(evsel_list->cpus, &sock_map)) {
+		perror("cannot build socket map");
+		return -1;
+	}
+
 	if (forks && (pipe(child_ready_pipe) < 0 || pipe(go_pipe) < 0)) {
 		perror("failed to create pipes");
 		return -1;
@@ -348,20 +432,13 @@
 				continue;
 			}
 
-			if (errno == EPERM || errno == EACCES) {
-				error("You may not have permission to collect %sstats.\n"
-				      "\t Consider tweaking"
-				      " /proc/sys/kernel/perf_event_paranoid or running as root.",
-				      target.system_wide ? "system-wide " : "");
-			} else {
-				error("open_counter returned with %d (%s). "
-				      "/bin/dmesg may provide additional information.\n",
-				       errno, strerror(errno));
-			}
+			perf_evsel__open_strerror(counter, &target,
+						  errno, msg, sizeof(msg));
+			ui__error("%s\n", msg);
+
 			if (child_pid != -1)
 				kill(child_pid, SIGTERM);
 
-			pr_err("Not all events could be opened.\n");
 			return -1;
 		}
 		counter->supported = true;
@@ -377,14 +454,25 @@
 	 * Enable counters and exec the command:
 	 */
 	t0 = rdclock();
+	clock_gettime(CLOCK_MONOTONIC, &ref_time);
 
 	if (forks) {
 		close(go_pipe[1]);
+		if (interval) {
+			while (!waitpid(child_pid, &status, WNOHANG)) {
+				nanosleep(&ts, NULL);
+				print_interval();
+			}
+		}
 		wait(&status);
 		if (WIFSIGNALED(status))
 			psignal(WTERMSIG(status), argv[0]);
 	} else {
-		while(!done) sleep(1);
+		while (!done) {
+			nanosleep(&ts, NULL);
+			if (interval)
+				print_interval();
+		}
 	}
 
 	t1 = rdclock();
@@ -454,13 +542,21 @@
 	print_noise_pct(stddev_stats(&ps->res_stats[0]), avg);
 }
 
-static void nsec_printout(int cpu, struct perf_evsel *evsel, double avg)
+static void nsec_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
 {
 	double msecs = avg / 1e6;
 	char cpustr[16] = { '\0', };
 	const char *fmt = csv_output ? "%s%.6f%s%s" : "%s%18.6f%s%-25s";
 
-	if (no_aggr)
+	if (aggr_socket)
+		sprintf(cpustr, "S%*d%s%*d%s",
+			csv_output ? 0 : -5,
+			cpu,
+			csv_sep,
+			csv_output ? 0 : 4,
+			nr,
+			csv_sep);
+	else if (no_aggr)
 		sprintf(cpustr, "CPU%*d%s",
 			csv_output ? 0 : -4,
 			perf_evsel__cpus(evsel)->map[cpu], csv_sep);
@@ -470,7 +566,7 @@
 	if (evsel->cgrp)
 		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
 
-	if (csv_output)
+	if (csv_output || interval)
 		return;
 
 	if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK))
@@ -659,7 +755,7 @@
 	fprintf(output, " of all LL-cache hits   ");
 }
 
-static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
+static void abs_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
 {
 	double total, ratio = 0.0;
 	char cpustr[16] = { '\0', };
@@ -672,7 +768,15 @@
 	else
 		fmt = "%s%18.0f%s%-25s";
 
-	if (no_aggr)
+	if (aggr_socket)
+		sprintf(cpustr, "S%*d%s%*d%s",
+			csv_output ? 0 : -5,
+			cpu,
+			csv_sep,
+			csv_output ? 0 : 4,
+			nr,
+			csv_sep);
+	else if (no_aggr)
 		sprintf(cpustr, "CPU%*d%s",
 			csv_output ? 0 : -4,
 			perf_evsel__cpus(evsel)->map[cpu], csv_sep);
@@ -684,12 +788,11 @@
 	if (evsel->cgrp)
 		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
 
-	if (csv_output)
+	if (csv_output || interval)
 		return;
 
 	if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
 		total = avg_stats(&runtime_cycles_stats[cpu]);
-
 		if (total)
 			ratio = avg / total;
 
@@ -779,16 +882,83 @@
 	}
 }
 
+static void print_aggr_socket(char *prefix)
+{
+	struct perf_evsel *counter;
+	u64 ena, run, val;
+	int cpu, s, s2, sock, nr;
+
+	if (!sock_map)
+		return;
+
+	for (s = 0; s < sock_map->nr; s++) {
+		sock = cpu_map__socket(sock_map, s);
+		list_for_each_entry(counter, &evsel_list->entries, node) {
+			val = ena = run = 0;
+			nr = 0;
+			for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+				s2 = cpu_map__get_socket(evsel_list->cpus, cpu);
+				if (s2 != sock)
+					continue;
+				val += counter->counts->cpu[cpu].val;
+				ena += counter->counts->cpu[cpu].ena;
+				run += counter->counts->cpu[cpu].run;
+				nr++;
+			}
+			if (prefix)
+				fprintf(output, "%s", prefix);
+
+			if (run == 0 || ena == 0) {
+				fprintf(output, "S%*d%s%*d%s%*s%s%*s",
+					csv_output ? 0 : -5,
+					s,
+					csv_sep,
+					csv_output ? 0 : 4,
+					nr,
+					csv_sep,
+					csv_output ? 0 : 18,
+					counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
+					csv_sep,
+					csv_output ? 0 : -24,
+					perf_evsel__name(counter));
+				if (counter->cgrp)
+					fprintf(output, "%s%s",
+						csv_sep, counter->cgrp->name);
+
+				fputc('\n', output);
+				continue;
+			}
+
+			if (nsec_counter(counter))
+				nsec_printout(sock, nr, counter, val);
+			else
+				abs_printout(sock, nr, counter, val);
+
+			if (!csv_output) {
+				print_noise(counter, 1.0);
+
+				if (run != ena)
+					fprintf(output, "  (%.2f%%)",
+						100.0 * run / ena);
+			}
+			fputc('\n', output);
+		}
+	}
+}
+
 /*
  * Print out the results of a single counter:
  * aggregated counts in system-wide mode
  */
-static void print_counter_aggr(struct perf_evsel *counter)
+static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 {
 	struct perf_stat *ps = counter->priv;
 	double avg = avg_stats(&ps->res_stats[0]);
 	int scaled = counter->counts->scaled;
 
+	if (prefix)
+		fprintf(output, "%s", prefix);
+
 	if (scaled == -1) {
 		fprintf(output, "%*s%s%*s",
 			csv_output ? 0 : 18,
@@ -805,9 +975,9 @@
 	}
 
 	if (nsec_counter(counter))
-		nsec_printout(-1, counter, avg);
+		nsec_printout(-1, 0, counter, avg);
 	else
-		abs_printout(-1, counter, avg);
+		abs_printout(-1, 0, counter, avg);
 
 	print_noise(counter, avg);
 
@@ -831,7 +1001,7 @@
  * Print out the results of a single counter:
  * does not use aggregated count in system-wide
  */
-static void print_counter(struct perf_evsel *counter)
+static void print_counter(struct perf_evsel *counter, char *prefix)
 {
 	u64 ena, run, val;
 	int cpu;
@@ -840,6 +1010,10 @@
 		val = counter->counts->cpu[cpu].val;
 		ena = counter->counts->cpu[cpu].ena;
 		run = counter->counts->cpu[cpu].run;
+
+		if (prefix)
+			fprintf(output, "%s", prefix);
+
 		if (run == 0 || ena == 0) {
 			fprintf(output, "CPU%*d%s%*s%s%*s",
 				csv_output ? 0 : -4,
@@ -859,9 +1033,9 @@
 		}
 
 		if (nsec_counter(counter))
-			nsec_printout(cpu, counter, val);
+			nsec_printout(cpu, 0, counter, val);
 		else
-			abs_printout(cpu, counter, val);
+			abs_printout(cpu, 0, counter, val);
 
 		if (!csv_output) {
 			print_noise(counter, 1.0);
@@ -899,12 +1073,14 @@
 		fprintf(output, ":\n\n");
 	}
 
-	if (no_aggr) {
+	if (aggr_socket)
+		print_aggr_socket(NULL);
+	else if (no_aggr) {
 		list_for_each_entry(counter, &evsel_list->entries, node)
-			print_counter(counter);
+			print_counter(counter, NULL);
 	} else {
 		list_for_each_entry(counter, &evsel_list->entries, node)
-			print_counter_aggr(counter);
+			print_counter_aggr(counter, NULL);
 	}
 
 	if (!csv_output) {
@@ -925,7 +1101,7 @@
 
 static void skip_signal(int signo)
 {
-	if(child_pid == -1)
+	if ((child_pid == -1) || interval)
 		done = 1;
 
 	signr = signo;
@@ -1145,6 +1321,9 @@
 			"command to run prior to the measured command"),
 	OPT_STRING(0, "post", &post_cmd, "command",
 			"command to run after to the measured command"),
+	OPT_UINTEGER('I', "interval-print", &interval,
+		    "print counts at regular interval in ms (>= 100)"),
+	OPT_BOOLEAN(0, "aggr-socket", &aggr_socket, "aggregate counts per processor socket"),
 	OPT_END()
 	};
 	const char * const stat_usage[] = {
@@ -1231,6 +1410,14 @@
 		usage_with_options(stat_usage, options);
 	}
 
+	if (aggr_socket) {
+		if (!perf_target__has_cpu(&target)) {
+			fprintf(stderr, "--aggr-socket only available in system-wide mode (-a)\n");
+			usage_with_options(stat_usage, options);
+		}
+		no_aggr = true;
+	}
+
 	if (add_default_attributes())
 		goto out;
 
@@ -1245,12 +1432,23 @@
 		usage_with_options(stat_usage, options);
 		return -1;
 	}
+	if (interval && interval < 100) {
+		pr_err("print interval must be >= 100ms\n");
+		usage_with_options(stat_usage, options);
+		return -1;
+	}
 
 	list_for_each_entry(pos, &evsel_list->entries, node) {
 		if (perf_evsel__alloc_stat_priv(pos) < 0 ||
 		    perf_evsel__alloc_counts(pos, perf_evsel__nr_cpus(pos)) < 0)
 			goto out_free_fd;
 	}
+	if (interval) {
+		list_for_each_entry(pos, &evsel_list->entries, node) {
+			if (perf_evsel__alloc_prev_raw_counts(pos) < 0)
+				goto out_free_fd;
+		}
+	}
 
 	/*
 	 * We dont want to block the signals - that would cause
@@ -1260,6 +1458,7 @@
 	 */
 	atexit(sig_atexit);
 	signal(SIGINT,  skip_signal);
+	signal(SIGCHLD, skip_signal);
 	signal(SIGALRM, skip_signal);
 	signal(SIGABRT, skip_signal);
 
@@ -1272,11 +1471,14 @@
 		status = run_perf_stat(argc, argv);
 	}
 
-	if (status != -1)
+	if (status != -1 && !interval)
 		print_stat(argc, argv);
 out_free_fd:
-	list_for_each_entry(pos, &evsel_list->entries, node)
+	list_for_each_entry(pos, &evsel_list->entries, node) {
 		perf_evsel__free_stat_priv(pos);
+		perf_evsel__free_counts(pos);
+		perf_evsel__free_prev_raw_counts(pos);
+	}
 	perf_evlist__delete_maps(evsel_list);
 out:
 	perf_evlist__delete(evsel_list);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index c9ff395..72f6eb7 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -68,27 +68,7 @@
 #include <linux/unistd.h>
 #include <linux/types.h>
 
-void get_term_dimensions(struct winsize *ws)
-{
-	char *s = getenv("LINES");
-
-	if (s != NULL) {
-		ws->ws_row = atoi(s);
-		s = getenv("COLUMNS");
-		if (s != NULL) {
-			ws->ws_col = atoi(s);
-			if (ws->ws_row && ws->ws_col)
-				return;
-		}
-	}
-#ifdef TIOCGWINSZ
-	if (ioctl(1, TIOCGWINSZ, ws) == 0 &&
-	    ws->ws_row && ws->ws_col)
-		return;
-#endif
-	ws->ws_row = 25;
-	ws->ws_col = 80;
-}
+static volatile int done;
 
 static void perf_top__update_print_entries(struct perf_top *top)
 {
@@ -453,8 +433,10 @@
 	return 0;
 }
 
-static void perf_top__handle_keypress(struct perf_top *top, int c)
+static bool perf_top__handle_keypress(struct perf_top *top, int c)
 {
+	bool ret = true;
+
 	if (!perf_top__key_mapped(top, c)) {
 		struct pollfd stdin_poll = { .fd = 0, .events = POLLIN };
 		struct termios tc, save;
@@ -475,7 +457,7 @@
 
 		tcsetattr(0, TCSAFLUSH, &save);
 		if (!perf_top__key_mapped(top, c))
-			return;
+			return ret;
 	}
 
 	switch (c) {
@@ -537,7 +519,8 @@
 			printf("exiting.\n");
 			if (top->dump_symtab)
 				perf_session__fprintf_dsos(top->session, stderr);
-			exit(0);
+			ret = false;
+			break;
 		case 's':
 			perf_top__prompt_symbol(top, "Enter details symbol");
 			break;
@@ -560,6 +543,8 @@
 		default:
 			break;
 	}
+
+	return ret;
 }
 
 static void perf_top__sort_new_samples(void *arg)
@@ -596,13 +581,12 @@
 	 * via --uid.
 	 */
 	list_for_each_entry(pos, &top->evlist->entries, node)
-		pos->hists.uid_filter_str = top->target.uid_str;
+		pos->hists.uid_filter_str = top->record_opts.target.uid_str;
 
 	perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
 				      &top->session->header.env);
 
-	exit_browser(0);
-	exit(0);
+	done = 1;
 	return NULL;
 }
 
@@ -626,7 +610,7 @@
 	/* trash return*/
 	getc(stdin);
 
-	while (1) {
+	while (!done) {
 		perf_top__print_sym_table(top);
 		/*
 		 * Either timeout expired or we got an EINTR due to SIGWINCH,
@@ -640,15 +624,14 @@
 				continue;
 			/* Fall trhu */
 		default:
-			goto process_hotkey;
+			c = getc(stdin);
+			tcsetattr(0, TCSAFLUSH, &save);
+
+			if (perf_top__handle_keypress(top, c))
+				goto repeat;
+			done = 1;
 		}
 	}
-process_hotkey:
-	c = getc(stdin);
-	tcsetattr(0, TCSAFLUSH, &save);
-
-	perf_top__handle_keypress(top, c);
-	goto repeat;
 
 	return NULL;
 }
@@ -716,7 +699,7 @@
 		static struct intlist *seen;
 
 		if (!seen)
-			seen = intlist__new();
+			seen = intlist__new(NULL);
 
 		if (!intlist__has_entry(seen, event->ip.pid)) {
 			pr_err("Can't find guest [%d]'s kernel information\n",
@@ -727,8 +710,8 @@
 	}
 
 	if (!machine) {
-		pr_err("%u unprocessable samples recorded.",
-		       top->session->hists.stats.nr_unprocessable_samples++);
+		pr_err("%u unprocessable samples recorded.\r",
+		       top->session->stats.nr_unprocessable_samples++);
 		return;
 	}
 
@@ -847,13 +830,13 @@
 			++top->us_samples;
 			if (top->hide_user_symbols)
 				continue;
-			machine = perf_session__find_host_machine(session);
+			machine = &session->machines.host;
 			break;
 		case PERF_RECORD_MISC_KERNEL:
 			++top->kernel_samples;
 			if (top->hide_kernel_symbols)
 				continue;
-			machine = perf_session__find_host_machine(session);
+			machine = &session->machines.host;
 			break;
 		case PERF_RECORD_MISC_GUEST_KERNEL:
 			++top->guest_kernel_samples;
@@ -878,7 +861,7 @@
 			hists__inc_nr_events(&evsel->hists, event->header.type);
 			machine__process_event(machine, event);
 		} else
-			++session->hists.stats.nr_unknown_events;
+			++session->stats.nr_unknown_events;
 	}
 }
 
@@ -890,123 +873,42 @@
 		perf_top__mmap_read_idx(top, i);
 }
 
-static void perf_top__start_counters(struct perf_top *top)
+static int perf_top__start_counters(struct perf_top *top)
 {
+	char msg[512];
 	struct perf_evsel *counter;
 	struct perf_evlist *evlist = top->evlist;
+	struct perf_record_opts *opts = &top->record_opts;
 
-	if (top->group)
-		perf_evlist__set_leader(evlist);
+	perf_evlist__config(evlist, opts);
 
 	list_for_each_entry(counter, &evlist->entries, node) {
-		struct perf_event_attr *attr = &counter->attr;
-
-		attr->sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID;
-
-		if (top->freq) {
-			attr->sample_type |= PERF_SAMPLE_PERIOD;
-			attr->freq	  = 1;
-			attr->sample_freq = top->freq;
-		}
-
-		if (evlist->nr_entries > 1) {
-			attr->sample_type |= PERF_SAMPLE_ID;
-			attr->read_format |= PERF_FORMAT_ID;
-		}
-
-		if (perf_target__has_cpu(&top->target))
-			attr->sample_type |= PERF_SAMPLE_CPU;
-
-		if (symbol_conf.use_callchain)
-			attr->sample_type |= PERF_SAMPLE_CALLCHAIN;
-
-		attr->mmap = 1;
-		attr->comm = 1;
-		attr->inherit = top->inherit;
-fallback_missing_features:
-		if (top->exclude_guest_missing)
-			attr->exclude_guest = attr->exclude_host = 0;
-retry_sample_id:
-		attr->sample_id_all = top->sample_id_all_missing ? 0 : 1;
 try_again:
 		if (perf_evsel__open(counter, top->evlist->cpus,
 				     top->evlist->threads) < 0) {
-			int err = errno;
-
-			if (err == EPERM || err == EACCES) {
-				ui__error_paranoid();
-				goto out_err;
-			} else if (err == EINVAL) {
-				if (!top->exclude_guest_missing &&
-				    (attr->exclude_guest || attr->exclude_host)) {
-					pr_debug("Old kernel, cannot exclude "
-						 "guest or host samples.\n");
-					top->exclude_guest_missing = true;
-					goto fallback_missing_features;
-				} else if (!top->sample_id_all_missing) {
-					/*
-					 * Old kernel, no attr->sample_id_type_all field
-					 */
-					top->sample_id_all_missing = true;
-					goto retry_sample_id;
-				}
-			}
-			/*
-			 * If it's cycles then fall back to hrtimer
-			 * based cpu-clock-tick sw counter, which
-			 * is always available even if no PMU support:
-			 */
-			if ((err == ENOENT || err == ENXIO) &&
-			    (attr->type == PERF_TYPE_HARDWARE) &&
-			    (attr->config == PERF_COUNT_HW_CPU_CYCLES)) {
-
+			if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) {
 				if (verbose)
-					ui__warning("Cycles event not supported,\n"
-						    "trying to fall back to cpu-clock-ticks\n");
-
-				attr->type = PERF_TYPE_SOFTWARE;
-				attr->config = PERF_COUNT_SW_CPU_CLOCK;
-				if (counter->name) {
-					free(counter->name);
-					counter->name = NULL;
-				}
+					ui__warning("%s\n", msg);
 				goto try_again;
 			}
 
-			if (err == ENOENT) {
-				ui__error("The %s event is not supported.\n",
-					  perf_evsel__name(counter));
-				goto out_err;
-			} else if (err == EMFILE) {
-				ui__error("Too many events are opened.\n"
-					    "Try again after reducing the number of events\n");
-				goto out_err;
-			} else if ((err == EOPNOTSUPP) && (attr->precise_ip)) {
-				ui__error("\'precise\' request may not be supported. "
-					  "Try removing 'p' modifier\n");
-				goto out_err;
-			}
-
-			ui__error("The sys_perf_event_open() syscall "
-				    "returned with %d (%s).  /bin/dmesg "
-				    "may provide additional information.\n"
-				    "No CONFIG_PERF_EVENTS=y kernel support "
-				    "configured?\n", err, strerror(err));
+			perf_evsel__open_strerror(counter, &opts->target,
+						  errno, msg, sizeof(msg));
+			ui__error("%s\n", msg);
 			goto out_err;
 		}
 	}
 
-	if (perf_evlist__mmap(evlist, top->mmap_pages, false) < 0) {
+	if (perf_evlist__mmap(evlist, opts->mmap_pages, false) < 0) {
 		ui__error("Failed to mmap with %d (%s)\n",
 			    errno, strerror(errno));
 		goto out_err;
 	}
 
-	return;
+	return 0;
 
 out_err:
-	exit_browser(0);
-	exit(0);
+	return -1;
 }
 
 static int perf_top__setup_sample_type(struct perf_top *top)
@@ -1016,7 +918,7 @@
 			ui__error("Selected -g but \"sym\" not present in --sort/-s.");
 			return -EINVAL;
 		}
-	} else if (!top->dont_use_callchains && callchain_param.mode != CHAIN_NONE) {
+	} else if (callchain_param.mode != CHAIN_NONE) {
 		if (callchain_register_param(&callchain_param) < 0) {
 			ui__error("Can't register callchain params.\n");
 			return -EINVAL;
@@ -1028,6 +930,7 @@
 
 static int __cmd_top(struct perf_top *top)
 {
+	struct perf_record_opts *opts = &top->record_opts;
 	pthread_t thread;
 	int ret;
 	/*
@@ -1042,26 +945,42 @@
 	if (ret)
 		goto out_delete;
 
-	if (perf_target__has_task(&top->target))
+	if (perf_target__has_task(&opts->target))
 		perf_event__synthesize_thread_map(&top->tool, top->evlist->threads,
 						  perf_event__process,
-						  &top->session->host_machine);
+						  &top->session->machines.host);
 	else
 		perf_event__synthesize_threads(&top->tool, perf_event__process,
-					       &top->session->host_machine);
-	perf_top__start_counters(top);
+					       &top->session->machines.host);
+
+	ret = perf_top__start_counters(top);
+	if (ret)
+		goto out_delete;
+
 	top->session->evlist = top->evlist;
 	perf_session__set_id_hdr_size(top->session);
 
+	/*
+	 * When perf is starting the traced process, all the events (apart from
+	 * group members) have enable_on_exec=1 set, so don't spoil it by
+	 * prematurely enabling them.
+	 *
+	 * XXX 'top' still doesn't start workloads like record, trace, but should,
+	 * so leave the check here.
+	 */
+        if (!perf_target__none(&opts->target))
+                perf_evlist__enable(top->evlist);
+
 	/* Wait for a minimal set of events before starting the snapshot */
 	poll(top->evlist->pollfd, top->evlist->nr_fds, 100);
 
 	perf_top__mmap_read(top);
 
+	ret = -1;
 	if (pthread_create(&thread, NULL, (use_browser > 0 ? display_thread_tui :
 							    display_thread), top)) {
 		ui__error("Could not create display thread.\n");
-		exit(-1);
+		goto out_delete;
 	}
 
 	if (top->realtime_prio) {
@@ -1070,11 +989,11 @@
 		param.sched_priority = top->realtime_prio;
 		if (sched_setscheduler(0, SCHED_FIFO, &param)) {
 			ui__error("Could not set realtime priority.\n");
-			exit(-1);
+			goto out_delete;
 		}
 	}
 
-	while (1) {
+	while (!done) {
 		u64 hits = top->samples;
 
 		perf_top__mmap_read(top);
@@ -1083,126 +1002,67 @@
 			ret = poll(top->evlist->pollfd, top->evlist->nr_fds, 100);
 	}
 
+	ret = 0;
 out_delete:
 	perf_session__delete(top->session);
 	top->session = NULL;
 
-	return 0;
+	return ret;
 }
 
 static int
 parse_callchain_opt(const struct option *opt, const char *arg, int unset)
 {
-	struct perf_top *top = (struct perf_top *)opt->value;
-	char *tok, *tok2;
-	char *endptr;
-
 	/*
 	 * --no-call-graph
 	 */
-	if (unset) {
-		top->dont_use_callchains = true;
+	if (unset)
 		return 0;
-	}
 
 	symbol_conf.use_callchain = true;
 
-	if (!arg)
-		return 0;
-
-	tok = strtok((char *)arg, ",");
-	if (!tok)
-		return -1;
-
-	/* get the output mode */
-	if (!strncmp(tok, "graph", strlen(arg)))
-		callchain_param.mode = CHAIN_GRAPH_ABS;
-
-	else if (!strncmp(tok, "flat", strlen(arg)))
-		callchain_param.mode = CHAIN_FLAT;
-
-	else if (!strncmp(tok, "fractal", strlen(arg)))
-		callchain_param.mode = CHAIN_GRAPH_REL;
-
-	else if (!strncmp(tok, "none", strlen(arg))) {
-		callchain_param.mode = CHAIN_NONE;
-		symbol_conf.use_callchain = false;
-
-		return 0;
-	} else
-		return -1;
-
-	/* get the min percentage */
-	tok = strtok(NULL, ",");
-	if (!tok)
-		goto setup;
-
-	callchain_param.min_percent = strtod(tok, &endptr);
-	if (tok == endptr)
-		return -1;
-
-	/* get the print limit */
-	tok2 = strtok(NULL, ",");
-	if (!tok2)
-		goto setup;
-
-	if (tok2[0] != 'c') {
-		callchain_param.print_limit = strtod(tok2, &endptr);
-		tok2 = strtok(NULL, ",");
-		if (!tok2)
-			goto setup;
-	}
-
-	/* get the call chain order */
-	if (!strcmp(tok2, "caller"))
-		callchain_param.order = ORDER_CALLER;
-	else if (!strcmp(tok2, "callee"))
-		callchain_param.order = ORDER_CALLEE;
-	else
-		return -1;
-setup:
-	if (callchain_register_param(&callchain_param) < 0) {
-		fprintf(stderr, "Can't register callchain params\n");
-		return -1;
-	}
-	return 0;
+	return record_parse_callchain_opt(opt, arg, unset);
 }
 
 int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 {
-	struct perf_evsel *pos;
 	int status;
 	char errbuf[BUFSIZ];
 	struct perf_top top = {
 		.count_filter	     = 5,
 		.delay_secs	     = 2,
-		.freq		     = 4000, /* 4 KHz */
-		.mmap_pages	     = 128,
-		.sym_pcnt_filter     = 5,
-		.target		     = {
-			.uses_mmap   = true,
+		.record_opts = {
+			.mmap_pages	= UINT_MAX,
+			.user_freq	= UINT_MAX,
+			.user_interval	= ULLONG_MAX,
+			.freq		= 4000, /* 4 KHz */
+			.target		     = {
+				.uses_mmap   = true,
+			},
 		},
+		.sym_pcnt_filter     = 5,
 	};
-	char callchain_default_opt[] = "fractal,0.5,callee";
+	struct perf_record_opts *opts = &top.record_opts;
+	struct perf_target *target = &opts->target;
 	const struct option options[] = {
 	OPT_CALLBACK('e', "event", &top.evlist, "event",
 		     "event selector. use 'perf list' to list available events",
 		     parse_events_option),
-	OPT_INTEGER('c', "count", &top.default_interval,
-		    "event period to sample"),
-	OPT_STRING('p', "pid", &top.target.pid, "pid",
+	OPT_U64('c', "count", &opts->user_interval, "event period to sample"),
+	OPT_STRING('p', "pid", &target->pid, "pid",
 		    "profile events on existing process id"),
-	OPT_STRING('t', "tid", &top.target.tid, "tid",
+	OPT_STRING('t', "tid", &target->tid, "tid",
 		    "profile events on existing thread id"),
-	OPT_BOOLEAN('a', "all-cpus", &top.target.system_wide,
+	OPT_BOOLEAN('a', "all-cpus", &target->system_wide,
 			    "system-wide collection from all CPUs"),
-	OPT_STRING('C', "cpu", &top.target.cpu_list, "cpu",
+	OPT_STRING('C', "cpu", &target->cpu_list, "cpu",
 		    "list of cpus to monitor"),
 	OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
 		   "file", "vmlinux pathname"),
 	OPT_BOOLEAN('K', "hide_kernel_symbols", &top.hide_kernel_symbols,
 		    "hide kernel symbols"),
-	OPT_UINTEGER('m', "mmap-pages", &top.mmap_pages, "number of mmap data pages"),
+	OPT_UINTEGER('m', "mmap-pages", &opts->mmap_pages,
+		     "number of mmap data pages"),
 	OPT_INTEGER('r', "realtime", &top.realtime_prio,
 		    "collect data with this RT SCHED_FIFO priority"),
 	OPT_INTEGER('d', "delay", &top.delay_secs,
@@ -1211,16 +1071,14 @@
 			    "dump the symbol table used for profiling"),
 	OPT_INTEGER('f', "count-filter", &top.count_filter,
 		    "only display functions with more events than this"),
-	OPT_BOOLEAN('g', "group", &top.group,
+	OPT_BOOLEAN('g', "group", &opts->group,
 			    "put the counters into a counter group"),
-	OPT_BOOLEAN('i', "inherit", &top.inherit,
-		    "child tasks inherit counters"),
+	OPT_BOOLEAN('i', "no-inherit", &opts->no_inherit,
+		    "child tasks do not inherit counters"),
 	OPT_STRING(0, "sym-annotate", &top.sym_filter, "symbol name",
 		    "symbol to annotate"),
-	OPT_BOOLEAN('z', "zero", &top.zero,
-		    "zero history across updates"),
-	OPT_INTEGER('F', "freq", &top.freq,
-		    "profile at this frequency"),
+	OPT_BOOLEAN('z', "zero", &top.zero, "zero history across updates"),
+	OPT_UINTEGER('F', "freq", &opts->user_freq, "profile at this frequency"),
 	OPT_INTEGER('E', "entries", &top.print_entries,
 		    "display this many functions"),
 	OPT_BOOLEAN('U', "hide_user_symbols", &top.hide_user_symbols,
@@ -1233,10 +1091,9 @@
 		   "sort by key(s): pid, comm, dso, symbol, parent"),
 	OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples,
 		    "Show a column with the number of samples"),
-	OPT_CALLBACK_DEFAULT('G', "call-graph", &top, "output_type,min_percent, call_order",
-		     "Display callchains using output_type (graph, flat, fractal, or none), min percent threshold and callchain order. "
-		     "Default: fractal,0.5,callee", &parse_callchain_opt,
-		     callchain_default_opt),
+	OPT_CALLBACK_DEFAULT('G', "call-graph", &top.record_opts,
+			     "mode[,dump_size]", record_callchain_help,
+			     &parse_callchain_opt, "fp"),
 	OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
 		    "Show a column with the sum of periods"),
 	OPT_STRING(0, "dsos", &symbol_conf.dso_list_str, "dso[,dso...]",
@@ -1251,7 +1108,7 @@
 		    "Display raw encoding of assembly instructions (default)"),
 	OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style",
 		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
-	OPT_STRING('u', "uid", &top.target.uid_str, "user", "user to profile"),
+	OPT_STRING('u', "uid", &target->uid_str, "user", "user to profile"),
 	OPT_END()
 	};
 	const char * const top_usage[] = {
@@ -1272,7 +1129,8 @@
 	if (sort_order == default_sort_order)
 		sort_order = "dso,symbol";
 
-	setup_sorting(top_usage, options);
+	if (setup_sorting() < 0)
+		usage_with_options(top_usage, options);
 
 	if (top.use_stdio)
 		use_browser = 0;
@@ -1281,33 +1139,33 @@
 
 	setup_browser(false);
 
-	status = perf_target__validate(&top.target);
+	status = perf_target__validate(target);
 	if (status) {
-		perf_target__strerror(&top.target, status, errbuf, BUFSIZ);
+		perf_target__strerror(target, status, errbuf, BUFSIZ);
 		ui__warning("%s", errbuf);
 	}
 
-	status = perf_target__parse_uid(&top.target);
+	status = perf_target__parse_uid(target);
 	if (status) {
 		int saved_errno = errno;
 
-		perf_target__strerror(&top.target, status, errbuf, BUFSIZ);
+		perf_target__strerror(target, status, errbuf, BUFSIZ);
 		ui__error("%s", errbuf);
 
 		status = -saved_errno;
 		goto out_delete_evlist;
 	}
 
-	if (perf_target__none(&top.target))
-		top.target.system_wide = true;
+	if (perf_target__none(target))
+		target->system_wide = true;
 
-	if (perf_evlist__create_maps(top.evlist, &top.target) < 0)
+	if (perf_evlist__create_maps(top.evlist, target) < 0)
 		usage_with_options(top_usage, options);
 
 	if (!top.evlist->nr_entries &&
 	    perf_evlist__add_default(top.evlist) < 0) {
 		ui__error("Not enough memory for event selector list\n");
-		return -ENOMEM;
+		goto out_delete_maps;
 	}
 
 	symbol_conf.nr_events = top.evlist->nr_entries;
@@ -1315,24 +1173,22 @@
 	if (top.delay_secs < 1)
 		top.delay_secs = 1;
 
+	if (opts->user_interval != ULLONG_MAX)
+		opts->default_interval = opts->user_interval;
+	if (opts->user_freq != UINT_MAX)
+		opts->freq = opts->user_freq;
+
 	/*
 	 * User specified count overrides default frequency.
 	 */
-	if (top.default_interval)
-		top.freq = 0;
-	else if (top.freq) {
-		top.default_interval = top.freq;
+	if (opts->default_interval)
+		opts->freq = 0;
+	else if (opts->freq) {
+		opts->default_interval = opts->freq;
 	} else {
 		ui__error("frequency and count are zero, aborting\n");
-		exit(EXIT_FAILURE);
-	}
-
-	list_for_each_entry(pos, &top.evlist->entries, node) {
-		/*
-		 * Fill in the ones not specifically initialized via -c:
-		 */
-		if (!pos->attr.sample_period)
-			pos->attr.sample_period = top.default_interval;
+		status = -EINVAL;
+		goto out_delete_maps;
 	}
 
 	top.sym_evsel = perf_evlist__first(top.evlist);
@@ -1365,6 +1221,8 @@
 
 	status = __cmd_top(&top);
 
+out_delete_maps:
+	perf_evlist__delete_maps(top.evlist);
 out_delete_evlist:
 	perf_evlist__delete(top.evlist);
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 7932ffa..d222d7f 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -455,7 +455,7 @@
 		goto out_delete_evlist;
 	}
 
-	perf_evlist__config_attrs(evlist, &trace->opts);
+	perf_evlist__config(evlist, &trace->opts);
 
 	signal(SIGCHLD, sig_handler);
 	signal(SIGINT, sig_handler);
diff --git a/tools/perf/config/feature-tests.mak b/tools/perf/config/feature-tests.mak
index f5ac774..b4eabb4 100644
--- a/tools/perf/config/feature-tests.mak
+++ b/tools/perf/config/feature-tests.mak
@@ -225,3 +225,14 @@
 	return on_exit(NULL, NULL);
 }
 endef
+
+define SOURCE_LIBNUMA
+#include <numa.h>
+#include <numaif.h>
+
+int main(void)
+{
+	numa_available();
+	return 0;
+}
+endef
\ No newline at end of file
diff --git a/tools/perf/config/utilities.mak b/tools/perf/config/utilities.mak
index e541312..8ef3bd3 100644
--- a/tools/perf/config/utilities.mak
+++ b/tools/perf/config/utilities.mak
@@ -13,7 +13,7 @@
 # what should replace a newline when escaping
 # newlines; the default is a bizarre string.
 #
-nl-escape = $(or $(1),m822df3020w6a44id34bt574ctac44eb9f4n)
+nl-escape = $(if $(1),$(1),m822df3020w6a44id34bt574ctac44eb9f4n)
 
 # escape-nl
 #
@@ -173,9 +173,9 @@
 # Usage: absolute-executable-path-or-empty = $(call get-executable-or-default,variable,default)
 #
 define get-executable-or-default
-$(if $($(1)),$(call _ge_attempt,$($(1)),$(1)),$(call _ge_attempt,$(2)))
+$(if $($(1)),$(call _ge_attempt,$($(1)),$(1)),$(call _ge_attempt,$(2),$(1)))
 endef
-_ge_attempt = $(or $(get-executable),$(_gea_warn),$(call _gea_err,$(2)))
+_ge_attempt = $(if $(get-executable),$(get-executable),$(_gea_warn)$(call _gea_err,$(2)))
 _gea_warn = $(warning The path '$(1)' is not executable.)
 _gea_err  = $(if $(1),$(error Please set '$(1)' appropriately))
 
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 0f661fb..095b882 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -328,14 +328,23 @@
 	if (S_ISFIFO(st.st_mode) || S_ISSOCK(st.st_mode))
 		return 0;
 
+	status = 1;
 	/* Check for ENOSPC and EIO errors.. */
-	if (fflush(stdout))
-		die("write failure on standard output: %s", strerror(errno));
-	if (ferror(stdout))
-		die("unknown write failure on standard output");
-	if (fclose(stdout))
-		die("close failed on standard output: %s", strerror(errno));
-	return 0;
+	if (fflush(stdout)) {
+		fprintf(stderr, "write failure on standard output: %s", strerror(errno));
+		goto out;
+	}
+	if (ferror(stdout)) {
+		fprintf(stderr, "unknown write failure on standard output");
+		goto out;
+	}
+	if (fclose(stdout)) {
+		fprintf(stderr, "close failed on standard output: %s", strerror(errno));
+		goto out;
+	}
+	status = 0;
+out:
+	return status;
 }
 
 static void handle_internal_command(int argc, const char **argv)
@@ -467,7 +476,8 @@
 		cmd += 5;
 		argv[0] = cmd;
 		handle_internal_command(argc, argv);
-		die("cannot handle %s internally", cmd);
+		fprintf(stderr, "cannot handle %s internally", cmd);
+		goto out;
 	}
 
 	/* Look for flags.. */
@@ -485,7 +495,7 @@
 		printf("\n usage: %s\n\n", perf_usage_string);
 		list_common_cmds_help();
 		printf("\n %s\n\n", perf_more_info_string);
-		exit(1);
+		goto out;
 	}
 	cmd = argv[0];
 
@@ -517,7 +527,7 @@
 			fprintf(stderr, "Expansion of alias '%s' failed; "
 				"'%s' is not a perf-command\n",
 				cmd, argv[0]);
-			exit(1);
+			goto out;
 		}
 		if (!done_help) {
 			cmd = argv[0] = help_unknown_cmd(cmd);
@@ -528,6 +538,6 @@
 
 	fprintf(stderr, "Failed to run command '%s': %s\n",
 		cmd, strerror(errno));
-
+out:
 	return 1;
 }
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 2c340e7..c2206c8 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -1,10 +1,6 @@
 #ifndef _PERF_PERF_H
 #define _PERF_PERF_H
 
-struct winsize;
-
-void get_term_dimensions(struct winsize *ws);
-
 #include <asm/unistd.h>
 
 #if defined(__i386__)
@@ -107,32 +103,6 @@
 #include "util/types.h"
 #include <stdbool.h>
 
-struct perf_mmap {
-	void			*base;
-	int			mask;
-	unsigned int		prev;
-};
-
-static inline unsigned int perf_mmap__read_head(struct perf_mmap *mm)
-{
-	struct perf_event_mmap_page *pc = mm->base;
-	int head = pc->data_head;
-	rmb();
-	return head;
-}
-
-static inline void perf_mmap__write_tail(struct perf_mmap *md,
-					 unsigned long tail)
-{
-	struct perf_event_mmap_page *pc = md->base;
-
-	/*
-	 * ensure all reads are done before we write the tail out.
-	 */
-	/* mb(); */
-	pc->data_tail = tail;
-}
-
 /*
  * prctl(PR_TASK_PERF_EVENTS_DISABLE) will (cheaply) disable all
  * counters in the current task.
@@ -237,8 +207,6 @@
 	bool	     raw_samples;
 	bool	     sample_address;
 	bool	     sample_time;
-	bool	     sample_id_all_missing;
-	bool	     exclude_guest_missing;
 	bool	     period;
 	unsigned int freq;
 	unsigned int mmap_pages;
diff --git a/tools/perf/scripts/perl/bin/workqueue-stats-record b/tools/perf/scripts/perl/bin/workqueue-stats-record
deleted file mode 100644
index 8edda90..0000000
--- a/tools/perf/scripts/perl/bin/workqueue-stats-record
+++ /dev/null
@@ -1,2 +0,0 @@
-#!/bin/bash
-perf record -e workqueue:workqueue_creation -e workqueue:workqueue_destruction -e workqueue:workqueue_execution -e workqueue:workqueue_insertion $@
diff --git a/tools/perf/scripts/perl/bin/workqueue-stats-report b/tools/perf/scripts/perl/bin/workqueue-stats-report
deleted file mode 100644
index 6d91411..0000000
--- a/tools/perf/scripts/perl/bin/workqueue-stats-report
+++ /dev/null
@@ -1,3 +0,0 @@
-#!/bin/bash
-# description: workqueue stats (ins/exe/create/destroy)
-perf script $@ -s "$PERF_EXEC_PATH"/scripts/perl/workqueue-stats.pl
diff --git a/tools/perf/scripts/perl/rwtop.pl b/tools/perf/scripts/perl/rwtop.pl
index 4bb3ecd..8b20787 100644
--- a/tools/perf/scripts/perl/rwtop.pl
+++ b/tools/perf/scripts/perl/rwtop.pl
@@ -17,6 +17,7 @@
 use lib "./Perf-Trace-Util/lib";
 use Perf::Trace::Core;
 use Perf::Trace::Util;
+use POSIX qw/SIGALRM SA_RESTART/;
 
 my $default_interval = 3;
 my $nlines = 20;
@@ -90,7 +91,10 @@
 
 sub trace_begin
 {
-    $SIG{ALRM} = \&set_print_pending;
+    my $sa = POSIX::SigAction->new(\&set_print_pending);
+    $sa->flags(SA_RESTART);
+    $sa->safe(1);
+    POSIX::sigaction(SIGALRM, $sa) or die "Can't set SIGALRM handler: $!\n";
     alarm 1;
 }
 
diff --git a/tools/perf/scripts/perl/workqueue-stats.pl b/tools/perf/scripts/perl/workqueue-stats.pl
deleted file mode 100644
index a8eaff5..0000000
--- a/tools/perf/scripts/perl/workqueue-stats.pl
+++ /dev/null
@@ -1,129 +0,0 @@
-#!/usr/bin/perl -w
-# (c) 2009, Tom Zanussi <tzanussi@gmail.com>
-# Licensed under the terms of the GNU GPL License version 2
-
-# Displays workqueue stats
-#
-# Usage:
-#
-#   perf record -c 1 -f -a -R -e workqueue:workqueue_creation -e
-#     workqueue:workqueue_destruction -e workqueue:workqueue_execution
-#     -e workqueue:workqueue_insertion
-#
-#   perf script -p -s tools/perf/scripts/perl/workqueue-stats.pl
-
-use 5.010000;
-use strict;
-use warnings;
-
-use lib "$ENV{'PERF_EXEC_PATH'}/scripts/perl/Perf-Trace-Util/lib";
-use lib "./Perf-Trace-Util/lib";
-use Perf::Trace::Core;
-use Perf::Trace::Util;
-
-my @cpus;
-
-sub workqueue::workqueue_destruction
-{
-    my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm,
-	$thread_comm, $thread_pid) = @_;
-
-    $cpus[$common_cpu]{$thread_pid}{destroyed}++;
-    $cpus[$common_cpu]{$thread_pid}{comm} = $thread_comm;
-}
-
-sub workqueue::workqueue_creation
-{
-    my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm,
-	$thread_comm, $thread_pid, $cpu) = @_;
-
-    $cpus[$common_cpu]{$thread_pid}{created}++;
-    $cpus[$common_cpu]{$thread_pid}{comm} = $thread_comm;
-}
-
-sub workqueue::workqueue_execution
-{
-    my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm,
-	$thread_comm, $thread_pid, $func) = @_;
-
-    $cpus[$common_cpu]{$thread_pid}{executed}++;
-    $cpus[$common_cpu]{$thread_pid}{comm} = $thread_comm;
-}
-
-sub workqueue::workqueue_insertion
-{
-    my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm,
-	$thread_comm, $thread_pid, $func) = @_;
-
-    $cpus[$common_cpu]{$thread_pid}{inserted}++;
-    $cpus[$common_cpu]{$thread_pid}{comm} = $thread_comm;
-}
-
-sub trace_end
-{
-    print "workqueue work stats:\n\n";
-    my $cpu = 0;
-    printf("%3s %6s %6s\t%-20s\n", "cpu", "ins", "exec", "name");
-    printf("%3s %6s %6s\t%-20s\n", "---", "---", "----", "----");
-    foreach my $pidhash (@cpus) {
-	while ((my $pid, my $wqhash) = each %$pidhash) {
-	    my $ins = $$wqhash{'inserted'} || 0;
-	    my $exe = $$wqhash{'executed'} || 0;
-	    my $comm = $$wqhash{'comm'} || "";
-	    if ($ins || $exe) {
-		printf("%3u %6u %6u\t%-20s\n", $cpu, $ins, $exe, $comm);
-	    }
-	}
-	$cpu++;
-    }
-
-    $cpu = 0;
-    print "\nworkqueue lifecycle stats:\n\n";
-    printf("%3s %6s %6s\t%-20s\n", "cpu", "created", "destroyed", "name");
-    printf("%3s %6s %6s\t%-20s\n", "---", "-------", "---------", "----");
-    foreach my $pidhash (@cpus) {
-	while ((my $pid, my $wqhash) = each %$pidhash) {
-	    my $created = $$wqhash{'created'} || 0;
-	    my $destroyed = $$wqhash{'destroyed'} || 0;
-	    my $comm = $$wqhash{'comm'} || "";
-	    if ($created || $destroyed) {
-		printf("%3u %6u %6u\t%-20s\n", $cpu, $created, $destroyed,
-		       $comm);
-	    }
-	}
-	$cpu++;
-    }
-
-    print_unhandled();
-}
-
-my %unhandled;
-
-sub print_unhandled
-{
-    if ((scalar keys %unhandled) == 0) {
-	return;
-    }
-
-    print "\nunhandled events:\n\n";
-
-    printf("%-40s  %10s\n", "event", "count");
-    printf("%-40s  %10s\n", "----------------------------------------",
-	   "-----------");
-
-    foreach my $event_name (keys %unhandled) {
-	printf("%-40s  %10d\n", $event_name, $unhandled{$event_name});
-    }
-}
-
-sub trace_unhandled
-{
-    my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm) = @_;
-
-    $unhandled{$event_name}++;
-}
diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c
index 25638a9..bdcceb8 100644
--- a/tools/perf/tests/attr.c
+++ b/tools/perf/tests/attr.c
@@ -19,6 +19,11 @@
  * permissions. All the event text files are stored there.
  */
 
+/*
+ * Powerpc needs __SANE_USERSPACE_TYPES__ before <linux/types.h> to select
+ * 'int-ll64.h' and avoid compile warnings when printing __u64 with %llu.
+ */
+#define __SANE_USERSPACE_TYPES__
 #include <stdlib.h>
 #include <stdio.h>
 #include <inttypes.h>
@@ -33,8 +38,6 @@
 
 extern int verbose;
 
-bool test_attr__enabled;
-
 static char *dir;
 
 void test_attr__init(void)
@@ -146,7 +149,7 @@
 {
 	char cmd[3*PATH_MAX];
 
-	snprintf(cmd, 3*PATH_MAX, "python %s/attr.py -d %s/attr/ -p %s %s",
+	snprintf(cmd, 3*PATH_MAX, PYTHON " %s/attr.py -d %s/attr/ -p %s %s",
 		 d, d, perf, verbose ? "-v" : "");
 
 	return system(cmd);
diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py
index e702b82..2f629ca 100644
--- a/tools/perf/tests/attr.py
+++ b/tools/perf/tests/attr.py
@@ -68,7 +68,7 @@
             self[key] = val
 
     def __init__(self, name, data, base):
-        log.info("    Event %s" % name);
+        log.debug("    Event %s" % name);
         self.name  = name;
         self.group = ''
         self.add(base)
@@ -97,6 +97,14 @@
                 return False
         return True
 
+    def diff(self, other):
+        for t in Event.terms:
+            if not self.has_key(t) or not other.has_key(t):
+                continue
+            if not self.compare_data(self[t], other[t]):
+		log.warning("expected %s=%s, got %s" % (t, self[t], other[t]))
+                
+
 # Test file description needs to have following sections:
 # [config]
 #   - just single instance in file
@@ -113,7 +121,7 @@
         parser = ConfigParser.SafeConfigParser()
         parser.read(path)
 
-        log.warning("running '%s'" % path)
+        log.debug("running '%s'" % path)
 
         self.path     = path
         self.test_dir = options.test_dir
@@ -128,7 +136,7 @@
 
         self.expect   = {}
         self.result   = {}
-        log.info("  loading expected events");
+        log.debug("  loading expected events");
         self.load_events(path, self.expect)
 
     def is_event(self, name):
@@ -164,7 +172,7 @@
               self.perf, self.command, tempdir, self.args)
         ret = os.WEXITSTATUS(os.system(cmd))
 
-        log.info("  running '%s' ret %d " % (cmd, ret))
+        log.warning("  running '%s' ret %d " % (cmd, ret))
 
         if ret != int(self.ret):
             raise Unsup(self)
@@ -172,7 +180,7 @@
     def compare(self, expect, result):
         match = {}
 
-        log.info("  compare");
+        log.debug("  compare");
 
         # For each expected event find all matching
         # events in result. Fail if there's not any.
@@ -187,10 +195,11 @@
                 else:
                     log.debug("    ->FAIL");
 
-            log.info("    match: [%s] matches %s" % (exp_name, str(exp_list)))
+            log.debug("    match: [%s] matches %s" % (exp_name, str(exp_list)))
 
             # we did not any matching event - fail
             if (not exp_list):
+		exp_event.diff(res_event)
                 raise Fail(self, 'match failure');
 
             match[exp_name] = exp_list
@@ -208,10 +217,10 @@
                 if res_group not in match[group]:
                     raise Fail(self, 'group failure')
 
-                log.info("    group: [%s] matches group leader %s" %
+                log.debug("    group: [%s] matches group leader %s" %
                          (exp_name, str(match[group])))
 
-        log.info("  matched")
+        log.debug("  matched")
 
     def resolve_groups(self, events):
         for name, event in events.items():
@@ -233,7 +242,7 @@
             self.run_cmd(tempdir);
 
             # load events expectation for the test
-            log.info("  loading result events");
+            log.debug("  loading result events");
             for f in glob.glob(tempdir + '/event*'):
                 self.load_events(f, self.result);
 
diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record
index f1485d8..5bc3880 100644
--- a/tools/perf/tests/attr/base-record
+++ b/tools/perf/tests/attr/base-record
@@ -7,7 +7,7 @@
 config=0
 sample_period=4000
 sample_type=263
-read_format=7
+read_format=0
 disabled=1
 inherit=1
 pinned=0
diff --git a/tools/perf/tests/attr/test-record-group b/tools/perf/tests/attr/test-record-group
index a6599e9..57739ca 100644
--- a/tools/perf/tests/attr/test-record-group
+++ b/tools/perf/tests/attr/test-record-group
@@ -6,12 +6,14 @@
 fd=1
 group_fd=-1
 sample_type=327
+read_format=4
 
 [event-2:base-record]
 fd=2
 group_fd=1
 config=1
 sample_type=327
+read_format=4
 mmap=0
 comm=0
 enable_on_exec=0
diff --git a/tools/perf/tests/attr/test-record-group1 b/tools/perf/tests/attr/test-record-group1
index 5a8359d..c5548d0 100644
--- a/tools/perf/tests/attr/test-record-group1
+++ b/tools/perf/tests/attr/test-record-group1
@@ -1,11 +1,12 @@
 [config]
 command = record
-args    = -e '{cycles,instructions}' kill >/tmp/krava 2>&1
+args    = -e '{cycles,instructions}' kill >/dev/null 2>&1
 
 [event-1:base-record]
 fd=1
 group_fd=-1
 sample_type=327
+read_format=4
 
 [event-2:base-record]
 fd=2
@@ -13,6 +14,7 @@
 type=0
 config=1
 sample_type=327
+read_format=4
 mmap=0
 comm=0
 enable_on_exec=0
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 186f675..acb98e0 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -4,6 +4,7 @@
  * Builtin regression testing command: ever growing number of sanity tests
  */
 #include "builtin.h"
+#include "intlist.h"
 #include "tests.h"
 #include "debug.h"
 #include "color.h"
@@ -69,6 +70,14 @@
 		.func = test__attr,
 	},
 	{
+		.desc = "Test matching and linking mutliple hists",
+		.func = test__hists_link,
+	},
+	{
+		.desc = "Try 'use perf' in python, checking link problems",
+		.func = test__python_use,
+	},
+	{
 		.func = NULL,
 	},
 };
@@ -97,7 +106,7 @@
 	return false;
 }
 
-static int __cmd_test(int argc, const char *argv[])
+static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 {
 	int i = 0;
 	int width = 0;
@@ -118,13 +127,28 @@
 			continue;
 
 		pr_info("%2d: %-*s:", i, width, tests[curr].desc);
+
+		if (intlist__find(skiplist, i)) {
+			color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (user override)\n");
+			continue;
+		}
+
 		pr_debug("\n--- start ---\n");
 		err = tests[curr].func();
 		pr_debug("---- end ----\n%s:", tests[curr].desc);
-		if (err)
-			color_fprintf(stderr, PERF_COLOR_RED, " FAILED!\n");
-		else
+
+		switch (err) {
+		case TEST_OK:
 			pr_info(" Ok\n");
+			break;
+		case TEST_SKIP:
+			color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip\n");
+			break;
+		case TEST_FAIL:
+		default:
+			color_fprintf(stderr, PERF_COLOR_RED, " FAILED!\n");
+			break;
+		}
 	}
 
 	return 0;
@@ -152,11 +176,14 @@
 	"perf test [<options>] [{list <test-name-fragment>|[<test-name-fragments>|<test-numbers>]}]",
 	NULL,
 	};
+	const char *skip = NULL;
 	const struct option test_options[] = {
+	OPT_STRING('s', "skip", &skip, "tests", "tests to skip"),
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show symbol address, etc)"),
 	OPT_END()
 	};
+	struct intlist *skiplist = NULL;
 
 	argc = parse_options(argc, argv, test_options, test_usage, 0);
 	if (argc >= 1 && !strcmp(argv[0], "list"))
@@ -169,5 +196,8 @@
 	if (symbol__init() < 0)
 		return -1;
 
-	return __cmd_test(argc, argv);
+	if (skip != NULL)
+		skiplist = intlist__new(skip);
+
+	return __cmd_test(argc, argv, skiplist);
 }
diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c
index e61fc82..0fd99a9 100644
--- a/tools/perf/tests/evsel-roundtrip-name.c
+++ b/tools/perf/tests/evsel-roundtrip-name.c
@@ -22,7 +22,7 @@
 			for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) {
 				__perf_evsel__hw_cache_type_op_res_name(type, op, i,
 									name, sizeof(name));
-				err = parse_events(evlist, name, 0);
+				err = parse_events(evlist, name);
 				if (err)
 					ret = err;
 			}
@@ -70,7 +70,7 @@
                 return -ENOMEM;
 
 	for (i = 0; i < nr_names; ++i) {
-		err = parse_events(evlist, names[i], 0);
+		err = parse_events(evlist, names[i]);
 		if (err) {
 			pr_debug("failed to parse event '%s', err %d\n",
 				 names[i], err);
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
new file mode 100644
index 0000000..1be64a6
--- /dev/null
+++ b/tools/perf/tests/hists_link.c
@@ -0,0 +1,500 @@
+#include "perf.h"
+#include "tests.h"
+#include "debug.h"
+#include "symbol.h"
+#include "sort.h"
+#include "evsel.h"
+#include "evlist.h"
+#include "machine.h"
+#include "thread.h"
+#include "parse-events.h"
+
+static struct {
+	u32 pid;
+	const char *comm;
+} fake_threads[] = {
+	{ 100, "perf" },
+	{ 200, "perf" },
+	{ 300, "bash" },
+};
+
+static struct {
+	u32 pid;
+	u64 start;
+	const char *filename;
+} fake_mmap_info[] = {
+	{ 100, 0x40000, "perf" },
+	{ 100, 0x50000, "libc" },
+	{ 100, 0xf0000, "[kernel]" },
+	{ 200, 0x40000, "perf" },
+	{ 200, 0x50000, "libc" },
+	{ 200, 0xf0000, "[kernel]" },
+	{ 300, 0x40000, "bash" },
+	{ 300, 0x50000, "libc" },
+	{ 300, 0xf0000, "[kernel]" },
+};
+
+struct fake_sym {
+	u64 start;
+	u64 length;
+	const char *name;
+};
+
+static struct fake_sym perf_syms[] = {
+	{ 700, 100, "main" },
+	{ 800, 100, "run_command" },
+	{ 900, 100, "cmd_record" },
+};
+
+static struct fake_sym bash_syms[] = {
+	{ 700, 100, "main" },
+	{ 800, 100, "xmalloc" },
+	{ 900, 100, "xfree" },
+};
+
+static struct fake_sym libc_syms[] = {
+	{ 700, 100, "malloc" },
+	{ 800, 100, "free" },
+	{ 900, 100, "realloc" },
+};
+
+static struct fake_sym kernel_syms[] = {
+	{ 700, 100, "schedule" },
+	{ 800, 100, "page_fault" },
+	{ 900, 100, "sys_perf_event_open" },
+};
+
+static struct {
+	const char *dso_name;
+	struct fake_sym *syms;
+	size_t nr_syms;
+} fake_symbols[] = {
+	{ "perf", perf_syms, ARRAY_SIZE(perf_syms) },
+	{ "bash", bash_syms, ARRAY_SIZE(bash_syms) },
+	{ "libc", libc_syms, ARRAY_SIZE(libc_syms) },
+	{ "[kernel]", kernel_syms, ARRAY_SIZE(kernel_syms) },
+};
+
+static struct machine *setup_fake_machine(struct machines *machines)
+{
+	struct machine *machine = machines__find(machines, HOST_KERNEL_ID);
+	size_t i;
+
+	if (machine == NULL) {
+		pr_debug("Not enough memory for machine setup\n");
+		return NULL;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(fake_threads); i++) {
+		struct thread *thread;
+
+		thread = machine__findnew_thread(machine, fake_threads[i].pid);
+		if (thread == NULL)
+			goto out;
+
+		thread__set_comm(thread, fake_threads[i].comm);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(fake_mmap_info); i++) {
+		union perf_event fake_mmap_event = {
+			.mmap = {
+				.header = { .misc = PERF_RECORD_MISC_USER, },
+				.pid = fake_mmap_info[i].pid,
+				.start = fake_mmap_info[i].start,
+				.len = 0x1000ULL,
+				.pgoff = 0ULL,
+			},
+		};
+
+		strcpy(fake_mmap_event.mmap.filename,
+		       fake_mmap_info[i].filename);
+
+		machine__process_mmap_event(machine, &fake_mmap_event);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(fake_symbols); i++) {
+		size_t k;
+		struct dso *dso;
+
+		dso = __dsos__findnew(&machine->user_dsos,
+				      fake_symbols[i].dso_name);
+		if (dso == NULL)
+			goto out;
+
+		/* emulate dso__load() */
+		dso__set_loaded(dso, MAP__FUNCTION);
+
+		for (k = 0; k < fake_symbols[i].nr_syms; k++) {
+			struct symbol *sym;
+			struct fake_sym *fsym = &fake_symbols[i].syms[k];
+
+			sym = symbol__new(fsym->start, fsym->length,
+					  STB_GLOBAL, fsym->name);
+			if (sym == NULL)
+				goto out;
+
+			symbols__insert(&dso->symbols[MAP__FUNCTION], sym);
+		}
+	}
+
+	return machine;
+
+out:
+	pr_debug("Not enough memory for machine setup\n");
+	machine__delete_threads(machine);
+	machine__delete(machine);
+	return NULL;
+}
+
+struct sample {
+	u32 pid;
+	u64 ip;
+	struct thread *thread;
+	struct map *map;
+	struct symbol *sym;
+};
+
+static struct sample fake_common_samples[] = {
+	/* perf [kernel] schedule() */
+	{ .pid = 100, .ip = 0xf0000 + 700, },
+	/* perf [perf]   main() */
+	{ .pid = 200, .ip = 0x40000 + 700, },
+	/* perf [perf]   cmd_record() */
+	{ .pid = 200, .ip = 0x40000 + 900, },
+	/* bash [bash]   xmalloc() */
+	{ .pid = 300, .ip = 0x40000 + 800, },
+	/* bash [libc]   malloc() */
+	{ .pid = 300, .ip = 0x50000 + 700, },
+};
+
+static struct sample fake_samples[][5] = {
+	{
+		/* perf [perf]   run_command() */
+		{ .pid = 100, .ip = 0x40000 + 800, },
+		/* perf [libc]   malloc() */
+		{ .pid = 100, .ip = 0x50000 + 700, },
+		/* perf [kernel] page_fault() */
+		{ .pid = 100, .ip = 0xf0000 + 800, },
+		/* perf [kernel] sys_perf_event_open() */
+		{ .pid = 200, .ip = 0xf0000 + 900, },
+		/* bash [libc]   free() */
+		{ .pid = 300, .ip = 0x50000 + 800, },
+	},
+	{
+		/* perf [libc]   free() */
+		{ .pid = 200, .ip = 0x50000 + 800, },
+		/* bash [libc]   malloc() */
+		{ .pid = 300, .ip = 0x50000 + 700, }, /* will be merged */
+		/* bash [bash]   xfee() */
+		{ .pid = 300, .ip = 0x40000 + 900, },
+		/* bash [libc]   realloc() */
+		{ .pid = 300, .ip = 0x50000 + 900, },
+		/* bash [kernel] page_fault() */
+		{ .pid = 300, .ip = 0xf0000 + 800, },
+	},
+};
+
+static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
+{
+	struct perf_evsel *evsel;
+	struct addr_location al;
+	struct hist_entry *he;
+	struct perf_sample sample = { .cpu = 0, };
+	size_t i = 0, k;
+
+	/*
+	 * each evsel will have 10 samples - 5 common and 5 distinct.
+	 * However the second evsel also has a collapsed entry for
+	 * "bash [libc] malloc" so total 9 entries will be in the tree.
+	 */
+	list_for_each_entry(evsel, &evlist->entries, node) {
+		for (k = 0; k < ARRAY_SIZE(fake_common_samples); k++) {
+			const union perf_event event = {
+				.ip = {
+					.header = {
+						.misc = PERF_RECORD_MISC_USER,
+					},
+					.pid = fake_common_samples[k].pid,
+					.ip  = fake_common_samples[k].ip,
+				},
+			};
+
+			if (perf_event__preprocess_sample(&event, machine, &al,
+							  &sample, 0) < 0)
+				goto out;
+
+			he = __hists__add_entry(&evsel->hists, &al, NULL, 1);
+			if (he == NULL)
+				goto out;
+
+			fake_common_samples[k].thread = al.thread;
+			fake_common_samples[k].map = al.map;
+			fake_common_samples[k].sym = al.sym;
+		}
+
+		for (k = 0; k < ARRAY_SIZE(fake_samples[i]); k++) {
+			const union perf_event event = {
+				.ip = {
+					.header = {
+						.misc = PERF_RECORD_MISC_USER,
+					},
+					.pid = fake_samples[i][k].pid,
+					.ip  = fake_samples[i][k].ip,
+				},
+			};
+
+			if (perf_event__preprocess_sample(&event, machine, &al,
+							  &sample, 0) < 0)
+				goto out;
+
+			he = __hists__add_entry(&evsel->hists, &al, NULL, 1);
+			if (he == NULL)
+				goto out;
+
+			fake_samples[i][k].thread = al.thread;
+			fake_samples[i][k].map = al.map;
+			fake_samples[i][k].sym = al.sym;
+		}
+		i++;
+	}
+
+	return 0;
+
+out:
+	pr_debug("Not enough memory for adding a hist entry\n");
+	return -1;
+}
+
+static int find_sample(struct sample *samples, size_t nr_samples,
+		       struct thread *t, struct map *m, struct symbol *s)
+{
+	while (nr_samples--) {
+		if (samples->thread == t && samples->map == m &&
+		    samples->sym == s)
+			return 1;
+		samples++;
+	}
+	return 0;
+}
+
+static int __validate_match(struct hists *hists)
+{
+	size_t count = 0;
+	struct rb_root *root;
+	struct rb_node *node;
+
+	/*
+	 * Only entries from fake_common_samples should have a pair.
+	 */
+	if (sort__need_collapse)
+		root = &hists->entries_collapsed;
+	else
+		root = hists->entries_in;
+
+	node = rb_first(root);
+	while (node) {
+		struct hist_entry *he;
+
+		he = rb_entry(node, struct hist_entry, rb_node_in);
+
+		if (hist_entry__has_pairs(he)) {
+			if (find_sample(fake_common_samples,
+					ARRAY_SIZE(fake_common_samples),
+					he->thread, he->ms.map, he->ms.sym)) {
+				count++;
+			} else {
+				pr_debug("Can't find the matched entry\n");
+				return -1;
+			}
+		}
+
+		node = rb_next(node);
+	}
+
+	if (count != ARRAY_SIZE(fake_common_samples)) {
+		pr_debug("Invalid count for matched entries: %zd of %zd\n",
+			 count, ARRAY_SIZE(fake_common_samples));
+		return -1;
+	}
+
+	return 0;
+}
+
+static int validate_match(struct hists *leader, struct hists *other)
+{
+	return __validate_match(leader) || __validate_match(other);
+}
+
+static int __validate_link(struct hists *hists, int idx)
+{
+	size_t count = 0;
+	size_t count_pair = 0;
+	size_t count_dummy = 0;
+	struct rb_root *root;
+	struct rb_node *node;
+
+	/*
+	 * Leader hists (idx = 0) will have dummy entries from other,
+	 * and some entries will have no pair.  However every entry
+	 * in other hists should have (dummy) pair.
+	 */
+	if (sort__need_collapse)
+		root = &hists->entries_collapsed;
+	else
+		root = hists->entries_in;
+
+	node = rb_first(root);
+	while (node) {
+		struct hist_entry *he;
+
+		he = rb_entry(node, struct hist_entry, rb_node_in);
+
+		if (hist_entry__has_pairs(he)) {
+			if (!find_sample(fake_common_samples,
+					 ARRAY_SIZE(fake_common_samples),
+					 he->thread, he->ms.map, he->ms.sym) &&
+			    !find_sample(fake_samples[idx],
+					 ARRAY_SIZE(fake_samples[idx]),
+					 he->thread, he->ms.map, he->ms.sym)) {
+				count_dummy++;
+			}
+			count_pair++;
+		} else if (idx) {
+			pr_debug("A entry from the other hists should have pair\n");
+			return -1;
+		}
+
+		count++;
+		node = rb_next(node);
+	}
+
+	/*
+	 * Note that we have a entry collapsed in the other (idx = 1) hists.
+	 */
+	if (idx == 0) {
+		if (count_dummy != ARRAY_SIZE(fake_samples[1]) - 1) {
+			pr_debug("Invalid count of dummy entries: %zd of %zd\n",
+				 count_dummy, ARRAY_SIZE(fake_samples[1]) - 1);
+			return -1;
+		}
+		if (count != count_pair + ARRAY_SIZE(fake_samples[0])) {
+			pr_debug("Invalid count of total leader entries: %zd of %zd\n",
+				 count, count_pair + ARRAY_SIZE(fake_samples[0]));
+			return -1;
+		}
+	} else {
+		if (count != count_pair) {
+			pr_debug("Invalid count of total other entries: %zd of %zd\n",
+				 count, count_pair);
+			return -1;
+		}
+		if (count_dummy > 0) {
+			pr_debug("Other hists should not have dummy entries: %zd\n",
+				 count_dummy);
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
+static int validate_link(struct hists *leader, struct hists *other)
+{
+	return __validate_link(leader, 0) || __validate_link(other, 1);
+}
+
+static void print_hists(struct hists *hists)
+{
+	int i = 0;
+	struct rb_root *root;
+	struct rb_node *node;
+
+	if (sort__need_collapse)
+		root = &hists->entries_collapsed;
+	else
+		root = hists->entries_in;
+
+	pr_info("----- %s --------\n", __func__);
+	node = rb_first(root);
+	while (node) {
+		struct hist_entry *he;
+
+		he = rb_entry(node, struct hist_entry, rb_node_in);
+
+		pr_info("%2d: entry: %-8s [%-8s] %20s: period = %"PRIu64"\n",
+			i, he->thread->comm, he->ms.map->dso->short_name,
+			he->ms.sym->name, he->stat.period);
+
+		i++;
+		node = rb_next(node);
+	}
+}
+
+int test__hists_link(void)
+{
+	int err = -1;
+	struct machines machines;
+	struct machine *machine = NULL;
+	struct perf_evsel *evsel, *first;
+        struct perf_evlist *evlist = perf_evlist__new(NULL, NULL);
+
+	if (evlist == NULL)
+                return -ENOMEM;
+
+	err = parse_events(evlist, "cpu-clock");
+	if (err)
+		goto out;
+	err = parse_events(evlist, "task-clock");
+	if (err)
+		goto out;
+
+	/* default sort order (comm,dso,sym) will be used */
+	if (setup_sorting() < 0)
+		goto out;
+
+	machines__init(&machines);
+
+	/* setup threads/dso/map/symbols also */
+	machine = setup_fake_machine(&machines);
+	if (!machine)
+		goto out;
+
+	if (verbose > 1)
+		machine__fprintf(machine, stderr);
+
+	/* process sample events */
+	err = add_hist_entries(evlist, machine);
+	if (err < 0)
+		goto out;
+
+	list_for_each_entry(evsel, &evlist->entries, node) {
+		hists__collapse_resort(&evsel->hists);
+
+		if (verbose > 2)
+			print_hists(&evsel->hists);
+	}
+
+	first = perf_evlist__first(evlist);
+	evsel = perf_evlist__last(evlist);
+
+	/* match common entries */
+	hists__match(&first->hists, &evsel->hists);
+	err = validate_match(&first->hists, &evsel->hists);
+	if (err)
+		goto out;
+
+	/* link common and/or dummy entries */
+	hists__link(&first->hists, &evsel->hists);
+	err = validate_link(&first->hists, &evsel->hists);
+	if (err)
+		goto out;
+
+	err = 0;
+
+out:
+	/* tear down everything */
+	perf_evlist__delete(evlist);
+	machines__exit(&machines);
+
+	return err;
+}
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index e174681..cdd5075 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -22,36 +22,16 @@
 	struct thread_map *threads;
 	struct cpu_map *cpus;
 	struct perf_evlist *evlist;
-	struct perf_event_attr attr = {
-		.type		= PERF_TYPE_TRACEPOINT,
-		.read_format	= PERF_FORMAT_ID,
-		.sample_type	= PERF_SAMPLE_ID,
-		.watermark	= 0,
-	};
 	cpu_set_t cpu_set;
 	const char *syscall_names[] = { "getsid", "getppid", "getpgrp",
 					"getpgid", };
 	pid_t (*syscalls[])(void) = { (void *)getsid, getppid, getpgrp,
 				      (void*)getpgid };
 #define nsyscalls ARRAY_SIZE(syscall_names)
-	int ids[nsyscalls];
 	unsigned int nr_events[nsyscalls],
 		     expected_nr_events[nsyscalls], i, j;
 	struct perf_evsel *evsels[nsyscalls], *evsel;
 
-	for (i = 0; i < nsyscalls; ++i) {
-		char name[64];
-
-		snprintf(name, sizeof(name), "sys_enter_%s", syscall_names[i]);
-		ids[i] = trace_event__id(name);
-		if (ids[i] < 0) {
-			pr_debug("Is debugfs mounted on /sys/kernel/debug?\n");
-			return -1;
-		}
-		nr_events[i] = 0;
-		expected_nr_events[i] = random() % 257;
-	}
-
 	threads = thread_map__new(-1, getpid(), UINT_MAX);
 	if (threads == NULL) {
 		pr_debug("thread_map__new\n");
@@ -79,18 +59,19 @@
 		goto out_free_cpus;
 	}
 
-	/* anonymous union fields, can't be initialized above */
-	attr.wakeup_events = 1;
-	attr.sample_period = 1;
-
 	for (i = 0; i < nsyscalls; ++i) {
-		attr.config = ids[i];
-		evsels[i] = perf_evsel__new(&attr, i);
+		char name[64];
+
+		snprintf(name, sizeof(name), "sys_enter_%s", syscall_names[i]);
+		evsels[i] = perf_evsel__newtp("syscalls", name, i);
 		if (evsels[i] == NULL) {
 			pr_debug("perf_evsel__new\n");
 			goto out_free_evlist;
 		}
 
+		evsels[i]->attr.wakeup_events = 1;
+		perf_evsel__set_sample_id(evsels[i]);
+
 		perf_evlist__add(evlist, evsels[i]);
 
 		if (perf_evsel__open(evsels[i], cpus, threads) < 0) {
@@ -99,6 +80,9 @@
 				 strerror(errno));
 			goto out_close_fd;
 		}
+
+		nr_events[i] = 0;
+		expected_nr_events[i] = 1 + rand() % 127;
 	}
 
 	if (perf_evlist__mmap(evlist, 128, true) < 0) {
@@ -128,6 +112,7 @@
 			goto out_munmap;
 		}
 
+		err = -1;
 		evsel = perf_evlist__id2evsel(evlist, sample.id);
 		if (evsel == NULL) {
 			pr_debug("event with id %" PRIu64
@@ -137,16 +122,17 @@
 		nr_events[evsel->idx]++;
 	}
 
+	err = 0;
 	list_for_each_entry(evsel, &evlist->entries, node) {
 		if (nr_events[evsel->idx] != expected_nr_events[evsel->idx]) {
 			pr_debug("expected %d %s events, got %d\n",
 				 expected_nr_events[evsel->idx],
 				 perf_evsel__name(evsel), nr_events[evsel->idx]);
+			err = -1;
 			goto out_munmap;
 		}
 	}
 
-	err = 0;
 out_munmap:
 	perf_evlist__munmap(evlist);
 out_close_fd:
diff --git a/tools/perf/tests/open-syscall-all-cpus.c b/tools/perf/tests/open-syscall-all-cpus.c
index 31072ab..b0657a9 100644
--- a/tools/perf/tests/open-syscall-all-cpus.c
+++ b/tools/perf/tests/open-syscall-all-cpus.c
@@ -7,20 +7,12 @@
 int test__open_syscall_event_on_all_cpus(void)
 {
 	int err = -1, fd, cpu;
-	struct thread_map *threads;
 	struct cpu_map *cpus;
 	struct perf_evsel *evsel;
-	struct perf_event_attr attr;
 	unsigned int nr_open_calls = 111, i;
 	cpu_set_t cpu_set;
-	int id = trace_event__id("sys_enter_open");
+	struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX);
 
-	if (id < 0) {
-		pr_debug("is debugfs mounted on /sys/kernel/debug?\n");
-		return -1;
-	}
-
-	threads = thread_map__new(-1, getpid(), UINT_MAX);
 	if (threads == NULL) {
 		pr_debug("thread_map__new\n");
 		return -1;
@@ -32,15 +24,11 @@
 		goto out_thread_map_delete;
 	}
 
-
 	CPU_ZERO(&cpu_set);
 
-	memset(&attr, 0, sizeof(attr));
-	attr.type = PERF_TYPE_TRACEPOINT;
-	attr.config = id;
-	evsel = perf_evsel__new(&attr, 0);
+	evsel = perf_evsel__newtp("syscalls", "sys_enter_open", 0);
 	if (evsel == NULL) {
-		pr_debug("perf_evsel__new\n");
+		pr_debug("is debugfs mounted on /sys/kernel/debug?\n");
 		goto out_thread_map_delete;
 	}
 
@@ -110,6 +98,7 @@
 		}
 	}
 
+	perf_evsel__free_counts(evsel);
 out_close_fd:
 	perf_evsel__close_fd(evsel, 1, threads->nr);
 out_evsel_delete:
diff --git a/tools/perf/tests/open-syscall.c b/tools/perf/tests/open-syscall.c
index 98be8b5..befc067 100644
--- a/tools/perf/tests/open-syscall.c
+++ b/tools/perf/tests/open-syscall.c
@@ -6,29 +6,18 @@
 int test__open_syscall_event(void)
 {
 	int err = -1, fd;
-	struct thread_map *threads;
 	struct perf_evsel *evsel;
-	struct perf_event_attr attr;
 	unsigned int nr_open_calls = 111, i;
-	int id = trace_event__id("sys_enter_open");
+	struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX);
 
-	if (id < 0) {
-		pr_debug("is debugfs mounted on /sys/kernel/debug?\n");
-		return -1;
-	}
-
-	threads = thread_map__new(-1, getpid(), UINT_MAX);
 	if (threads == NULL) {
 		pr_debug("thread_map__new\n");
 		return -1;
 	}
 
-	memset(&attr, 0, sizeof(attr));
-	attr.type = PERF_TYPE_TRACEPOINT;
-	attr.config = id;
-	evsel = perf_evsel__new(&attr, 0);
+	evsel = perf_evsel__newtp("syscalls", "sys_enter_open", 0);
 	if (evsel == NULL) {
-		pr_debug("perf_evsel__new\n");
+		pr_debug("is debugfs mounted on /sys/kernel/debug?\n");
 		goto out_thread_map_delete;
 	}
 
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 32ee478..c5636f3 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -3,6 +3,7 @@
 #include "evsel.h"
 #include "evlist.h"
 #include "sysfs.h"
+#include "debugfs.h"
 #include "tests.h"
 #include <linux/hw_breakpoint.h>
 
@@ -22,6 +23,7 @@
 	struct perf_evsel *evsel = perf_evlist__first(evlist);
 
 	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 0 == evlist->nr_groups);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->attr.type);
 	TEST_ASSERT_VAL("wrong sample_type",
 		PERF_TP_SAMPLE_TYPE == evsel->attr.sample_type);
@@ -34,6 +36,7 @@
 	struct perf_evsel *evsel;
 
 	TEST_ASSERT_VAL("wrong number of entries", evlist->nr_entries > 1);
+	TEST_ASSERT_VAL("wrong number of groups", 0 == evlist->nr_groups);
 
 	list_for_each_entry(evsel, &evlist->entries, node) {
 		TEST_ASSERT_VAL("wrong type",
@@ -463,10 +466,10 @@
 
 static int test__checkterms_simple(struct list_head *terms)
 {
-	struct parse_events__term *term;
+	struct parse_events_term *term;
 
 	/* config=10 */
-	term = list_entry(terms->next, struct parse_events__term, list);
+	term = list_entry(terms->next, struct parse_events_term, list);
 	TEST_ASSERT_VAL("wrong type term",
 			term->type_term == PARSE_EVENTS__TERM_TYPE_CONFIG);
 	TEST_ASSERT_VAL("wrong type val",
@@ -475,7 +478,7 @@
 	TEST_ASSERT_VAL("wrong config", !term->config);
 
 	/* config1 */
-	term = list_entry(term->list.next, struct parse_events__term, list);
+	term = list_entry(term->list.next, struct parse_events_term, list);
 	TEST_ASSERT_VAL("wrong type term",
 			term->type_term == PARSE_EVENTS__TERM_TYPE_CONFIG1);
 	TEST_ASSERT_VAL("wrong type val",
@@ -484,7 +487,7 @@
 	TEST_ASSERT_VAL("wrong config", !term->config);
 
 	/* config2=3 */
-	term = list_entry(term->list.next, struct parse_events__term, list);
+	term = list_entry(term->list.next, struct parse_events_term, list);
 	TEST_ASSERT_VAL("wrong type term",
 			term->type_term == PARSE_EVENTS__TERM_TYPE_CONFIG2);
 	TEST_ASSERT_VAL("wrong type val",
@@ -493,7 +496,7 @@
 	TEST_ASSERT_VAL("wrong config", !term->config);
 
 	/* umask=1*/
-	term = list_entry(term->list.next, struct parse_events__term, list);
+	term = list_entry(term->list.next, struct parse_events_term, list);
 	TEST_ASSERT_VAL("wrong type term",
 			term->type_term == PARSE_EVENTS__TERM_TYPE_USER);
 	TEST_ASSERT_VAL("wrong type val",
@@ -509,6 +512,7 @@
 	struct perf_evsel *evsel, *leader;
 
 	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups);
 
 	/* instructions:k */
 	evsel = leader = perf_evlist__first(evlist);
@@ -521,7 +525,9 @@
 	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
-	TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel));
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
 
 	/* cycles:upp */
 	evsel = perf_evsel__next(evsel);
@@ -536,6 +542,7 @@
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 2);
 	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
 
 	return 0;
 }
@@ -545,6 +552,7 @@
 	struct perf_evsel *evsel, *leader;
 
 	TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups);
 
 	/* faults + :ku modifier */
 	evsel = leader = perf_evlist__first(evlist);
@@ -557,7 +565,9 @@
 	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
-	TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel));
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
 
 	/* cache-references + :u modifier */
 	evsel = perf_evsel__next(evsel);
@@ -567,10 +577,11 @@
 	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
 	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
 	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
-	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
 	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
 
 	/* cycles:k */
 	evsel = perf_evsel__next(evsel);
@@ -583,7 +594,7 @@
 	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
-	TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel));
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
 
 	return 0;
 }
@@ -593,6 +604,7 @@
 	struct perf_evsel *evsel, *leader;
 
 	TEST_ASSERT_VAL("wrong number of entries", 5 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 2 == evlist->nr_groups);
 
 	/* group1 syscalls:sys_enter_open:H */
 	evsel = leader = perf_evlist__first(evlist);
@@ -606,9 +618,11 @@
 	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
-	TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel));
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
 	TEST_ASSERT_VAL("wrong group name",
 		!strcmp(leader->group_name, "group1"));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
 
 	/* group1 cycles:kppp */
 	evsel = perf_evsel__next(evsel);
@@ -624,6 +638,7 @@
 	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 3);
 	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
 	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
 
 	/* group2 cycles + G modifier */
 	evsel = leader = perf_evsel__next(evsel);
@@ -636,9 +651,11 @@
 	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
-	TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel));
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
 	TEST_ASSERT_VAL("wrong group name",
 		!strcmp(leader->group_name, "group2"));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
 
 	/* group2 1:3 + G modifier */
 	evsel = perf_evsel__next(evsel);
@@ -651,6 +668,7 @@
 	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
 	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
 
 	/* instructions:u */
 	evsel = perf_evsel__next(evsel);
@@ -663,7 +681,7 @@
 	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
-	TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel));
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
 
 	return 0;
 }
@@ -673,6 +691,7 @@
 	struct perf_evsel *evsel, *leader;
 
 	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups);
 
 	/* cycles:u + p */
 	evsel = leader = perf_evlist__first(evlist);
@@ -687,7 +706,9 @@
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 1);
 	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
-	TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel));
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
 
 	/* instructions:kp + p */
 	evsel = perf_evsel__next(evsel);
@@ -702,6 +723,7 @@
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 2);
 	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
 
 	return 0;
 }
@@ -711,6 +733,7 @@
 	struct perf_evsel *evsel, *leader;
 
 	TEST_ASSERT_VAL("wrong number of entries", 5 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 2 == evlist->nr_groups);
 
 	/* cycles + G */
 	evsel = leader = perf_evlist__first(evlist);
@@ -724,7 +747,9 @@
 	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
 	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
-	TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel));
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
 
 	/* instructions + G */
 	evsel = perf_evsel__next(evsel);
@@ -738,6 +763,7 @@
 	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
 	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
 
 	/* cycles:G */
 	evsel = leader = perf_evsel__next(evsel);
@@ -751,7 +777,9 @@
 	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
 	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
-	TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel));
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
 
 	/* instructions:G */
 	evsel = perf_evsel__next(evsel);
@@ -765,6 +793,7 @@
 	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
 	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
 
 	/* cycles */
 	evsel = perf_evsel__next(evsel);
@@ -777,18 +806,235 @@
 	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
-	TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel));
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
 
 	return 0;
 }
 
-struct test__event_st {
+static int test__group_gh1(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel, *leader;
+
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups);
+
+	/* cycles + :H group modifier */
+	evsel = leader = perf_evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+
+	/* cache-misses:G + :H group modifier */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+
+	return 0;
+}
+
+static int test__group_gh2(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel, *leader;
+
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups);
+
+	/* cycles + :G group modifier */
+	evsel = leader = perf_evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+
+	/* cache-misses:H + :G group modifier */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+
+	return 0;
+}
+
+static int test__group_gh3(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel, *leader;
+
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups);
+
+	/* cycles:G + :u group modifier */
+	evsel = leader = perf_evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+
+	/* cache-misses:H + :u group modifier */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+
+	return 0;
+}
+
+static int test__group_gh4(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel, *leader;
+
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+	TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups);
+
+	/* cycles:G + :uG group modifier */
+	evsel = leader = perf_evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+	TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel));
+	TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0);
+
+	/* cache-misses:H + :uG group modifier */
+	evsel = perf_evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+	TEST_ASSERT_VAL("wrong config",
+			PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config);
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+	TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1);
+
+	return 0;
+}
+
+static int count_tracepoints(void)
+{
+	char events_path[PATH_MAX];
+	struct dirent *events_ent;
+	DIR *events_dir;
+	int cnt = 0;
+
+	scnprintf(events_path, PATH_MAX, "%s/tracing/events",
+		  debugfs_find_mountpoint());
+
+	events_dir = opendir(events_path);
+
+	TEST_ASSERT_VAL("Can't open events dir", events_dir);
+
+	while ((events_ent = readdir(events_dir))) {
+		char sys_path[PATH_MAX];
+		struct dirent *sys_ent;
+		DIR *sys_dir;
+
+		if (!strcmp(events_ent->d_name, ".")
+		    || !strcmp(events_ent->d_name, "..")
+		    || !strcmp(events_ent->d_name, "enable")
+		    || !strcmp(events_ent->d_name, "header_event")
+		    || !strcmp(events_ent->d_name, "header_page"))
+			continue;
+
+		scnprintf(sys_path, PATH_MAX, "%s/%s",
+			  events_path, events_ent->d_name);
+
+		sys_dir = opendir(sys_path);
+		TEST_ASSERT_VAL("Can't open sys dir", sys_dir);
+
+		while ((sys_ent = readdir(sys_dir))) {
+			if (!strcmp(sys_ent->d_name, ".")
+			    || !strcmp(sys_ent->d_name, "..")
+			    || !strcmp(sys_ent->d_name, "enable")
+			    || !strcmp(sys_ent->d_name, "filter"))
+				continue;
+
+			cnt++;
+		}
+
+		closedir(sys_dir);
+	}
+
+	closedir(events_dir);
+	return cnt;
+}
+
+static int test__all_tracepoints(struct perf_evlist *evlist)
+{
+	TEST_ASSERT_VAL("wrong events count",
+			count_tracepoints() == evlist->nr_entries);
+
+	return test__checkevent_tracepoint_multi(evlist);
+}
+
+struct evlist_test {
 	const char *name;
 	__u32 type;
 	int (*check)(struct perf_evlist *evlist);
 };
 
-static struct test__event_st test__events[] = {
+static struct evlist_test test__events[] = {
 	[0] = {
 		.name  = "syscalls:sys_enter_open",
 		.check = test__checkevent_tracepoint,
@@ -921,9 +1167,29 @@
 		.name  = "{cycles,instructions}:G,{cycles:G,instructions:G},cycles",
 		.check = test__group5,
 	},
+	[33] = {
+		.name  = "*:*",
+		.check = test__all_tracepoints,
+	},
+	[34] = {
+		.name  = "{cycles,cache-misses:G}:H",
+		.check = test__group_gh1,
+	},
+	[35] = {
+		.name  = "{cycles,cache-misses:H}:G",
+		.check = test__group_gh2,
+	},
+	[36] = {
+		.name  = "{cycles:G,cache-misses:H}:u",
+		.check = test__group_gh3,
+	},
+	[37] = {
+		.name  = "{cycles:G,cache-misses:H}:uG",
+		.check = test__group_gh4,
+	},
 };
 
-static struct test__event_st test__events_pmu[] = {
+static struct evlist_test test__events_pmu[] = {
 	[0] = {
 		.name  = "cpu/config=10,config1,config2=3,period=1000/u",
 		.check = test__checkevent_pmu,
@@ -934,20 +1200,20 @@
 	},
 };
 
-struct test__term {
+struct terms_test {
 	const char *str;
 	__u32 type;
 	int (*check)(struct list_head *terms);
 };
 
-static struct test__term test__terms[] = {
+static struct terms_test test__terms[] = {
 	[0] = {
 		.str   = "config=10,config1,config2=3,umask=1",
 		.check = test__checkterms_simple,
 	},
 };
 
-static int test_event(struct test__event_st *e)
+static int test_event(struct evlist_test *e)
 {
 	struct perf_evlist *evlist;
 	int ret;
@@ -956,7 +1222,7 @@
 	if (evlist == NULL)
 		return -ENOMEM;
 
-	ret = parse_events(evlist, e->name, 0);
+	ret = parse_events(evlist, e->name);
 	if (ret) {
 		pr_debug("failed to parse event '%s', err %d\n",
 			 e->name, ret);
@@ -969,13 +1235,13 @@
 	return ret;
 }
 
-static int test_events(struct test__event_st *events, unsigned cnt)
+static int test_events(struct evlist_test *events, unsigned cnt)
 {
 	int ret1, ret2 = 0;
 	unsigned i;
 
 	for (i = 0; i < cnt; i++) {
-		struct test__event_st *e = &events[i];
+		struct evlist_test *e = &events[i];
 
 		pr_debug("running test %d '%s'\n", i, e->name);
 		ret1 = test_event(e);
@@ -986,7 +1252,7 @@
 	return ret2;
 }
 
-static int test_term(struct test__term *t)
+static int test_term(struct terms_test *t)
 {
 	struct list_head *terms;
 	int ret;
@@ -1010,13 +1276,13 @@
 	return ret;
 }
 
-static int test_terms(struct test__term *terms, unsigned cnt)
+static int test_terms(struct terms_test *terms, unsigned cnt)
 {
 	int ret = 0;
 	unsigned i;
 
 	for (i = 0; i < cnt; i++) {
-		struct test__term *t = &terms[i];
+		struct terms_test *t = &terms[i];
 
 		pr_debug("running test %d '%s'\n", i, t->str);
 		ret = test_term(t);
@@ -1067,7 +1333,7 @@
 
 	while (!ret && (ent = readdir(dir))) {
 #define MAX_NAME 100
-		struct test__event_st e;
+		struct evlist_test e;
 		char name[MAX_NAME];
 
 		if (!strcmp(ent->d_name, ".") ||
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 70e0d44..1e8e512 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -96,22 +96,22 @@
 	err = perf_evlist__prepare_workload(evlist, &opts, argv);
 	if (err < 0) {
 		pr_debug("Couldn't run the workload!\n");
-		goto out_delete_evlist;
+		goto out_delete_maps;
 	}
 
 	/*
 	 * Config the evsels, setting attr->comm on the first one, etc.
 	 */
 	evsel = perf_evlist__first(evlist);
-	evsel->attr.sample_type |= PERF_SAMPLE_CPU;
-	evsel->attr.sample_type |= PERF_SAMPLE_TID;
-	evsel->attr.sample_type |= PERF_SAMPLE_TIME;
-	perf_evlist__config_attrs(evlist, &opts);
+	perf_evsel__set_sample_bit(evsel, CPU);
+	perf_evsel__set_sample_bit(evsel, TID);
+	perf_evsel__set_sample_bit(evsel, TIME);
+	perf_evlist__config(evlist, &opts);
 
 	err = sched__get_first_possible_cpu(evlist->workload.pid, &cpu_mask);
 	if (err < 0) {
 		pr_debug("sched__get_first_possible_cpu: %s\n", strerror(errno));
-		goto out_delete_evlist;
+		goto out_delete_maps;
 	}
 
 	cpu = err;
@@ -121,7 +121,7 @@
 	 */
 	if (sched_setaffinity(evlist->workload.pid, cpu_mask_size, &cpu_mask) < 0) {
 		pr_debug("sched_setaffinity: %s\n", strerror(errno));
-		goto out_delete_evlist;
+		goto out_delete_maps;
 	}
 
 	/*
@@ -131,7 +131,7 @@
 	err = perf_evlist__open(evlist);
 	if (err < 0) {
 		pr_debug("perf_evlist__open: %s\n", strerror(errno));
-		goto out_delete_evlist;
+		goto out_delete_maps;
 	}
 
 	/*
@@ -142,7 +142,7 @@
 	err = perf_evlist__mmap(evlist, opts.mmap_pages, false);
 	if (err < 0) {
 		pr_debug("perf_evlist__mmap: %s\n", strerror(errno));
-		goto out_delete_evlist;
+		goto out_delete_maps;
 	}
 
 	/*
@@ -305,6 +305,8 @@
 	}
 out_err:
 	perf_evlist__munmap(evlist);
+out_delete_maps:
+	perf_evlist__delete_maps(evlist);
 out_delete_evlist:
 	perf_evlist__delete(evlist);
 out:
diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c
index a5f3798..12b322f 100644
--- a/tools/perf/tests/pmu.c
+++ b/tools/perf/tests/pmu.c
@@ -19,10 +19,8 @@
 	{ "krava23", "config2:28-29,38\n", },
 };
 
-#define TEST_FORMATS_CNT (sizeof(test_formats) / sizeof(struct test_format))
-
 /* Simulated users input. */
-static struct parse_events__term test_terms[] = {
+static struct parse_events_term test_terms[] = {
 	{
 		.config    = (char *) "krava01",
 		.val.num   = 15,
@@ -78,7 +76,6 @@
 		.type_term = PARSE_EVENTS__TERM_TYPE_USER,
 	},
 };
-#define TERMS_CNT (sizeof(test_terms) / sizeof(struct parse_events__term))
 
 /*
  * Prepare format directory data, exported by kernel
@@ -93,7 +90,7 @@
 	if (!mkdtemp(dir))
 		return NULL;
 
-	for (i = 0; i < TEST_FORMATS_CNT; i++) {
+	for (i = 0; i < ARRAY_SIZE(test_formats); i++) {
 		static char name[PATH_MAX];
 		struct test_format *format = &test_formats[i];
 		FILE *file;
@@ -130,14 +127,12 @@
 	static LIST_HEAD(terms);
 	unsigned int i;
 
-	for (i = 0; i < TERMS_CNT; i++)
+	for (i = 0; i < ARRAY_SIZE(test_terms); i++)
 		list_add_tail(&test_terms[i].list, &terms);
 
 	return &terms;
 }
 
-#undef TERMS_CNT
-
 int test__pmu(void)
 {
 	char *format = test_format_dir_get();
diff --git a/tools/perf/tests/python-use.c b/tools/perf/tests/python-use.c
new file mode 100644
index 0000000..7760277
--- /dev/null
+++ b/tools/perf/tests/python-use.c
@@ -0,0 +1,23 @@
+/*
+ * Just test if we can load the python binding.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include "tests.h"
+
+extern int verbose;
+
+int test__python_use(void)
+{
+	char *cmd;
+	int ret;
+
+	if (asprintf(&cmd, "echo \"import sys ; sys.path.append('%s'); import perf\" | %s %s",
+		     PYTHONPATH, PYTHON, verbose ? "" : "2> /dev/null") < 0)
+		return -1;
+
+	ret = system(cmd) ? -1 : 0;
+	free(cmd);
+	return ret;
+}
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index fc121ed..5de0be1 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -1,6 +1,12 @@
 #ifndef TESTS_H
 #define TESTS_H
 
+enum {
+	TEST_OK   =  0,
+	TEST_FAIL = -1,
+	TEST_SKIP = -2,
+};
+
 /* Tests */
 int test__vmlinux_matches_kallsyms(void);
 int test__open_syscall_event(void);
@@ -15,8 +21,7 @@
 int test__attr(void);
 int test__dso_data(void);
 int test__parse_events(void);
-
-/* Util */
-int trace_event__id(const char *evname);
+int test__hists_link(void);
+int test__python_use(void);
 
 #endif /* TESTS_H */
diff --git a/tools/perf/tests/util.c b/tools/perf/tests/util.c
deleted file mode 100644
index 748f2e8..0000000
--- a/tools/perf/tests/util.c
+++ /dev/null
@@ -1,30 +0,0 @@
-#include <stdio.h>
-#include <unistd.h>
-#include <stdlib.h>
-#include <sys/types.h>
-#include <sys/stat.h>
-#include <fcntl.h>
-#include "tests.h"
-#include "debugfs.h"
-
-int trace_event__id(const char *evname)
-{
-	char *filename;
-	int err = -1, fd;
-
-	if (asprintf(&filename,
-		     "%s/syscalls/%s/id",
-		     tracing_events_path, evname) < 0)
-		return -1;
-
-	fd = open(filename, O_RDONLY);
-	if (fd >= 0) {
-		char id[16];
-		if (read(fd, id, sizeof(id)) > 0)
-			err = atoi(id);
-		close(fd);
-	}
-
-	free(filename);
-	return err;
-}
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index 0d1cdbe..7b4c4d2 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -44,7 +44,7 @@
 	 */
 	if (machine__create_kernel_maps(&kallsyms) < 0) {
 		pr_debug("machine__create_kernel_maps ");
-		return -1;
+		goto out;
 	}
 
 	/*
@@ -101,7 +101,8 @@
 	 */
 	if (machine__load_vmlinux_path(&vmlinux, type,
 				       vmlinux_matches_kallsyms_filter) <= 0) {
-		pr_debug("machine__load_vmlinux_path ");
+		pr_debug("Couldn't find a vmlinux that matches the kernel running on this machine, skipping test\n");
+		err = TEST_SKIP;
 		goto out;
 	}
 
@@ -226,5 +227,7 @@
 			map__fprintf(pos, stderr);
 	}
 out:
+	machine__exit(&kallsyms);
+	machine__exit(&vmlinux);
 	return err;
 }
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index 4aeb7d5..809ea463 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -273,6 +273,8 @@
 {
 	pthread_mutex_lock(&ui__lock);
 	ui_helpline__pop();
+	free(browser->helpline);
+	browser->helpline = NULL;
 	pthread_mutex_unlock(&ui__lock);
 }
 
@@ -471,7 +473,7 @@
 	return row;
 }
 
-static struct ui_browser__colorset {
+static struct ui_browser_colorset {
 	const char *name, *fg, *bg;
 	int colorset;
 } ui_browser__colorsets[] = {
@@ -706,7 +708,7 @@
 	perf_config(ui_browser__color_config, NULL);
 
 	while (ui_browser__colorsets[i].name) {
-		struct ui_browser__colorset *c = &ui_browser__colorsets[i++];
+		struct ui_browser_colorset *c = &ui_browser__colorsets[i++];
 		sltt_set_color(c->colorset, c->name, c->fg, c->bg);
 	}
 
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 5dab3ca..7dca155 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -182,6 +182,16 @@
 		ab->selection = dl;
 }
 
+static bool disasm_line__is_valid_jump(struct disasm_line *dl, struct symbol *sym)
+{
+	if (!dl || !dl->ins || !ins__is_jump(dl->ins)
+	    || !disasm_line__has_offset(dl)
+	    || dl->ops.target.offset >= symbol__size(sym))
+		return false;
+
+	return true;
+}
+
 static void annotate_browser__draw_current_jump(struct ui_browser *browser)
 {
 	struct annotate_browser *ab = container_of(browser, struct annotate_browser, b);
@@ -195,8 +205,7 @@
 	if (strstr(sym->name, "@plt"))
 		return;
 
-	if (!cursor || !cursor->ins || !ins__is_jump(cursor->ins) ||
-	    !disasm_line__has_offset(cursor))
+	if (!disasm_line__is_valid_jump(cursor, sym))
 		return;
 
 	target = ab->offsets[cursor->ops.target.offset];
@@ -788,17 +797,9 @@
 		struct disasm_line *dl = browser->offsets[offset], *dlt;
 		struct browser_disasm_line *bdlt;
 
-		if (!dl || !dl->ins || !ins__is_jump(dl->ins) ||
-		    !disasm_line__has_offset(dl))
+		if (!disasm_line__is_valid_jump(dl, sym))
 			continue;
 
-		if (dl->ops.target.offset >= size) {
-			ui__error("jump to after symbol!\n"
-				  "size: %zx, jump target: %" PRIx64,
-				  size, dl->ops.target.offset);
-			continue;
-		}
-
 		dlt = browser->offsets[dl->ops.target.offset];
 		/*
  		 * FIXME: Oops, no jump target? Buggy disassembler? Or do we
@@ -921,11 +922,11 @@
 
 #define ANNOTATE_CFG(n) \
 	{ .name = #n, .value = &annotate_browser__opts.n, }
-	
+
 /*
  * Keep the entries sorted, they are bsearch'ed
  */
-static struct annotate__config {
+static struct annotate_config {
 	const char *name;
 	bool *value;
 } annotate__configs[] = {
@@ -939,7 +940,7 @@
 
 static int annotate_config__cmp(const void *name, const void *cfgp)
 {
-	const struct annotate__config *cfg = cfgp;
+	const struct annotate_config *cfg = cfgp;
 
 	return strcmp(name, cfg->name);
 }
@@ -947,7 +948,7 @@
 static int annotate__config(const char *var, const char *value,
 			    void *data __maybe_unused)
 {
-	struct annotate__config *cfg;
+	struct annotate_config *cfg;
 	const char *name;
 
 	if (prefixcmp(var, "annotate.") != 0)
@@ -955,7 +956,7 @@
 
 	name = var + 9;
 	cfg = bsearch(name, annotate__configs, ARRAY_SIZE(annotate__configs),
-		      sizeof(struct annotate__config), annotate_config__cmp);
+		      sizeof(struct annotate_config), annotate_config__cmp);
 
 	if (cfg == NULL)
 		return -1;
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index ccc4bd1..aa22704 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -567,26 +567,128 @@
 	return row - first_row;
 }
 
-#define HPP__COLOR_FN(_name, _field)					\
-static int hist_browser__hpp_color_ ## _name(struct perf_hpp *hpp,	\
-					     struct hist_entry *he)	\
-{									\
-	struct hists *hists = he->hists;				\
-	double percent = 100.0 * he->stat._field / hists->stats.total_period; \
-	*(double *)hpp->ptr = percent;					\
-	return scnprintf(hpp->buf, hpp->size, "%6.2f%%", percent);	\
+struct hpp_arg {
+	struct ui_browser *b;
+	char folded_sign;
+	bool current_entry;
+};
+
+static int __hpp__color_callchain(struct hpp_arg *arg)
+{
+	if (!symbol_conf.use_callchain)
+		return 0;
+
+	slsmg_printf("%c ", arg->folded_sign);
+	return 2;
 }
 
-HPP__COLOR_FN(overhead, period)
-HPP__COLOR_FN(overhead_sys, period_sys)
-HPP__COLOR_FN(overhead_us, period_us)
-HPP__COLOR_FN(overhead_guest_sys, period_guest_sys)
-HPP__COLOR_FN(overhead_guest_us, period_guest_us)
+static int __hpp__color_fmt(struct perf_hpp *hpp, struct hist_entry *he,
+			    u64 (*get_field)(struct hist_entry *),
+			    int (*callchain_cb)(struct hpp_arg *))
+{
+	int ret = 0;
+	double percent = 0.0;
+	struct hists *hists = he->hists;
+	struct hpp_arg *arg = hpp->ptr;
 
-#undef HPP__COLOR_FN
+	if (hists->stats.total_period)
+		percent = 100.0 * get_field(he) / hists->stats.total_period;
+
+	ui_browser__set_percent_color(arg->b, percent, arg->current_entry);
+
+	if (callchain_cb)
+		ret += callchain_cb(arg);
+
+	ret += scnprintf(hpp->buf, hpp->size, "%6.2f%%", percent);
+	slsmg_printf("%s", hpp->buf);
+
+	if (symbol_conf.event_group) {
+		int prev_idx, idx_delta;
+		struct perf_evsel *evsel = hists_to_evsel(hists);
+		struct hist_entry *pair;
+		int nr_members = evsel->nr_members;
+
+		if (nr_members <= 1)
+			goto out;
+
+		prev_idx = perf_evsel__group_idx(evsel);
+
+		list_for_each_entry(pair, &he->pairs.head, pairs.node) {
+			u64 period = get_field(pair);
+			u64 total = pair->hists->stats.total_period;
+
+			if (!total)
+				continue;
+
+			evsel = hists_to_evsel(pair->hists);
+			idx_delta = perf_evsel__group_idx(evsel) - prev_idx - 1;
+
+			while (idx_delta--) {
+				/*
+				 * zero-fill group members in the middle which
+				 * have no sample
+				 */
+				ui_browser__set_percent_color(arg->b, 0.0,
+							arg->current_entry);
+				ret += scnprintf(hpp->buf, hpp->size,
+						 " %6.2f%%", 0.0);
+				slsmg_printf("%s", hpp->buf);
+			}
+
+			percent = 100.0 * period / total;
+			ui_browser__set_percent_color(arg->b, percent,
+						      arg->current_entry);
+			ret += scnprintf(hpp->buf, hpp->size,
+					 " %6.2f%%", percent);
+			slsmg_printf("%s", hpp->buf);
+
+			prev_idx = perf_evsel__group_idx(evsel);
+		}
+
+		idx_delta = nr_members - prev_idx - 1;
+
+		while (idx_delta--) {
+			/*
+			 * zero-fill group members at last which have no sample
+			 */
+			ui_browser__set_percent_color(arg->b, 0.0,
+						      arg->current_entry);
+			ret += scnprintf(hpp->buf, hpp->size,
+					 " %6.2f%%", 0.0);
+			slsmg_printf("%s", hpp->buf);
+		}
+	}
+out:
+	if (!arg->current_entry || !arg->b->navkeypressed)
+		ui_browser__set_color(arg->b, HE_COLORSET_NORMAL);
+
+	return ret;
+}
+
+#define __HPP_COLOR_PERCENT_FN(_type, _field, _cb)			\
+static u64 __hpp_get_##_field(struct hist_entry *he)			\
+{									\
+	return he->stat._field;						\
+}									\
+									\
+static int hist_browser__hpp_color_##_type(struct perf_hpp *hpp,	\
+					   struct hist_entry *he)	\
+{									\
+	return __hpp__color_fmt(hpp, he, __hpp_get_##_field, _cb);	\
+}
+
+__HPP_COLOR_PERCENT_FN(overhead, period, __hpp__color_callchain)
+__HPP_COLOR_PERCENT_FN(overhead_sys, period_sys, NULL)
+__HPP_COLOR_PERCENT_FN(overhead_us, period_us, NULL)
+__HPP_COLOR_PERCENT_FN(overhead_guest_sys, period_guest_sys, NULL)
+__HPP_COLOR_PERCENT_FN(overhead_guest_us, period_guest_us, NULL)
+
+#undef __HPP_COLOR_PERCENT_FN
 
 void hist_browser__init_hpp(void)
 {
+	perf_hpp__column_enable(PERF_HPP__OVERHEAD);
+
 	perf_hpp__init();
 
 	perf_hpp__format[PERF_HPP__OVERHEAD].color =
@@ -606,13 +708,13 @@
 				    unsigned short row)
 {
 	char s[256];
-	double percent;
-	int i, printed = 0;
+	int printed = 0;
 	int width = browser->b.width;
 	char folded_sign = ' ';
 	bool current_entry = ui_browser__is_current_entry(&browser->b, row);
 	off_t row_offset = entry->row_offset;
 	bool first = true;
+	struct perf_hpp_fmt *fmt;
 
 	if (current_entry) {
 		browser->he_selection = entry;
@@ -625,41 +727,30 @@
 	}
 
 	if (row_offset == 0) {
+		struct hpp_arg arg = {
+			.b 		= &browser->b,
+			.folded_sign	= folded_sign,
+			.current_entry	= current_entry,
+		};
 		struct perf_hpp hpp = {
 			.buf		= s,
 			.size		= sizeof(s),
+			.ptr		= &arg,
 		};
 
 		ui_browser__gotorc(&browser->b, row, 0);
 
-		for (i = 0; i < PERF_HPP__MAX_INDEX; i++) {
-			if (!perf_hpp__format[i].cond)
-				continue;
-
+		perf_hpp__for_each_format(fmt) {
 			if (!first) {
 				slsmg_printf("  ");
 				width -= 2;
 			}
 			first = false;
 
-			if (perf_hpp__format[i].color) {
-				hpp.ptr = &percent;
-				/* It will set percent for us. See HPP__COLOR_FN above. */
-				width -= perf_hpp__format[i].color(&hpp, entry);
-
-				ui_browser__set_percent_color(&browser->b, percent, current_entry);
-
-				if (i == PERF_HPP__OVERHEAD && symbol_conf.use_callchain) {
-					slsmg_printf("%c ", folded_sign);
-					width -= 2;
-				}
-
-				slsmg_printf("%s", s);
-
-				if (!current_entry || !browser->b.navkeypressed)
-					ui_browser__set_color(&browser->b, HE_COLORSET_NORMAL);
+			if (fmt->color) {
+				width -= fmt->color(&hpp, entry);
 			} else {
-				width -= perf_hpp__format[i].entry(&hpp, entry);
+				width -= fmt->entry(&hpp, entry);
 				slsmg_printf("%s", s);
 			}
 		}
@@ -1098,6 +1189,21 @@
 	const struct thread *thread = hists->thread_filter;
 	unsigned long nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE];
 	u64 nr_events = hists->stats.total_period;
+	struct perf_evsel *evsel = hists_to_evsel(hists);
+	char buf[512];
+	size_t buflen = sizeof(buf);
+
+	if (symbol_conf.event_group && evsel->nr_members > 1) {
+		struct perf_evsel *pos;
+
+		perf_evsel__group_desc(evsel, buf, buflen);
+		ev_name = buf;
+
+		for_each_group_member(pos, evsel) {
+			nr_samples += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE];
+			nr_events += pos->hists.stats.total_period;
+		}
+	}
 
 	nr_samples = convert_unit(nr_samples, &unit);
 	printed = scnprintf(bf, size,
@@ -1135,6 +1241,96 @@
 	return timer == NULL;
 }
 
+/*
+ * Only runtime switching of perf data file will make "input_name" point
+ * to a malloced buffer. So add "is_input_name_malloced" flag to decide
+ * whether we need to call free() for current "input_name" during the switch.
+ */
+static bool is_input_name_malloced = false;
+
+static int switch_data_file(void)
+{
+	char *pwd, *options[32], *abs_path[32], *tmp;
+	DIR *pwd_dir;
+	int nr_options = 0, choice = -1, ret = -1;
+	struct dirent *dent;
+
+	pwd = getenv("PWD");
+	if (!pwd)
+		return ret;
+
+	pwd_dir = opendir(pwd);
+	if (!pwd_dir)
+		return ret;
+
+	memset(options, 0, sizeof(options));
+	memset(options, 0, sizeof(abs_path));
+
+	while ((dent = readdir(pwd_dir))) {
+		char path[PATH_MAX];
+		u64 magic;
+		char *name = dent->d_name;
+		FILE *file;
+
+		if (!(dent->d_type == DT_REG))
+			continue;
+
+		snprintf(path, sizeof(path), "%s/%s", pwd, name);
+
+		file = fopen(path, "r");
+		if (!file)
+			continue;
+
+		if (fread(&magic, 1, 8, file) < 8)
+			goto close_file_and_continue;
+
+		if (is_perf_magic(magic)) {
+			options[nr_options] = strdup(name);
+			if (!options[nr_options])
+				goto close_file_and_continue;
+
+			abs_path[nr_options] = strdup(path);
+			if (!abs_path[nr_options]) {
+				free(options[nr_options]);
+				ui__warning("Can't search all data files due to memory shortage.\n");
+				fclose(file);
+				break;
+			}
+
+			nr_options++;
+		}
+
+close_file_and_continue:
+		fclose(file);
+		if (nr_options >= 32) {
+			ui__warning("Too many perf data files in PWD!\n"
+				    "Only the first 32 files will be listed.\n");
+			break;
+		}
+	}
+	closedir(pwd_dir);
+
+	if (nr_options) {
+		choice = ui__popup_menu(nr_options, options);
+		if (choice < nr_options && choice >= 0) {
+			tmp = strdup(abs_path[choice]);
+			if (tmp) {
+				if (is_input_name_malloced)
+					free((void *)input_name);
+				input_name = tmp;
+				is_input_name_malloced = true;
+				ret = 0;
+			} else
+				ui__warning("Data switch failed due to memory shortage!\n");
+		}
+	}
+
+	free_popup_options(options, nr_options);
+	free_popup_options(abs_path, nr_options);
+	return ret;
+}
+
+
 static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 				    const char *helpline, const char *ev_name,
 				    bool left_exits,
@@ -1169,7 +1365,8 @@
 		int choice = 0,
 		    annotate = -2, zoom_dso = -2, zoom_thread = -2,
 		    annotate_f = -2, annotate_t = -2, browse_map = -2;
-		int scripts_comm = -2, scripts_symbol = -2, scripts_all = -2;
+		int scripts_comm = -2, scripts_symbol = -2,
+		    scripts_all = -2, switch_data = -2;
 
 		nr_options = 0;
 
@@ -1226,6 +1423,10 @@
 			if (is_report_browser(hbt))
 				goto do_scripts;
 			continue;
+		case 's':
+			if (is_report_browser(hbt))
+				goto do_data_switch;
+			continue;
 		case K_F1:
 		case 'h':
 		case '?':
@@ -1245,6 +1446,7 @@
 					"d             Zoom into current DSO\n"
 					"t             Zoom into current Thread\n"
 					"r             Run available scripts('perf report' only)\n"
+					"s             Switch to another data file in PWD ('perf report' only)\n"
 					"P             Print histograms to perf.hist.N\n"
 					"V             Verbose (DSO names in callchains, etc)\n"
 					"/             Filter symbol by name");
@@ -1352,6 +1554,9 @@
 		if (asprintf(&options[nr_options], "Run scripts for all samples") > 0)
 			scripts_all = nr_options++;
 
+		if (is_report_browser(hbt) && asprintf(&options[nr_options],
+				"Switch to another data file in PWD") > 0)
+			switch_data = nr_options++;
 add_exit_option:
 		options[nr_options++] = (char *)"Exit";
 retry_popup_menu:
@@ -1462,6 +1667,16 @@
 
 			script_browse(script_opt);
 		}
+		/* Switch to another data file */
+		else if (choice == switch_data) {
+do_data_switch:
+			if (!switch_data_file()) {
+				key = K_SWITCH_INPUT_DATA;
+				break;
+			} else
+				ui__warning("Won't switch the data files due to\n"
+					"no valid data file get selected!\n");
+		}
 	}
 out_free_stack:
 	pstack__delete(fstack);
@@ -1494,6 +1709,16 @@
 	ui_browser__set_color(browser, current_entry ? HE_COLORSET_SELECTED :
 						       HE_COLORSET_NORMAL);
 
+	if (symbol_conf.event_group && evsel->nr_members > 1) {
+		struct perf_evsel *pos;
+
+		ev_name = perf_evsel__group_name(evsel);
+
+		for_each_group_member(pos, evsel) {
+			nr_events += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE];
+		}
+	}
+
 	nr_events = convert_unit(nr_events, &unit);
 	printed = scnprintf(bf, sizeof(bf), "%lu%c%s%s", nr_events,
 			   unit, unit == ' ' ? "" : " ", ev_name);
@@ -1578,6 +1803,7 @@
 						"Do you really want to exit?"))
 					continue;
 				/* Fall thru */
+			case K_SWITCH_INPUT_DATA:
 			case 'q':
 			case CTRL('c'):
 				goto out;
@@ -1604,8 +1830,19 @@
 	return key;
 }
 
+static bool filter_group_entries(struct ui_browser *self __maybe_unused,
+				 void *entry)
+{
+	struct perf_evsel *evsel = list_entry(entry, struct perf_evsel, node);
+
+	if (symbol_conf.event_group && !perf_evsel__is_group_leader(evsel))
+		return true;
+
+	return false;
+}
+
 static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist,
-					   const char *help,
+					   int nr_entries, const char *help,
 					   struct hist_browser_timer *hbt,
 					   struct perf_session_env *env)
 {
@@ -1616,7 +1853,8 @@
 			.refresh    = ui_browser__list_head_refresh,
 			.seek	    = ui_browser__list_head_seek,
 			.write	    = perf_evsel_menu__write,
-			.nr_entries = evlist->nr_entries,
+			.filter	    = filter_group_entries,
+			.nr_entries = nr_entries,
 			.priv	    = evlist,
 		},
 		.env = env,
@@ -1632,20 +1870,37 @@
 			menu.b.width = line_len;
 	}
 
-	return perf_evsel_menu__run(&menu, evlist->nr_entries, help, hbt);
+	return perf_evsel_menu__run(&menu, nr_entries, help, hbt);
 }
 
 int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
 				  struct hist_browser_timer *hbt,
 				  struct perf_session_env *env)
 {
-	if (evlist->nr_entries == 1) {
+	int nr_entries = evlist->nr_entries;
+
+single_entry:
+	if (nr_entries == 1) {
 		struct perf_evsel *first = list_entry(evlist->entries.next,
 						      struct perf_evsel, node);
 		const char *ev_name = perf_evsel__name(first);
-		return perf_evsel__hists_browse(first, evlist->nr_entries, help,
+
+		return perf_evsel__hists_browse(first, nr_entries, help,
 						ev_name, false, hbt, env);
 	}
 
-	return __perf_evlist__tui_browse_hists(evlist, help, hbt, env);
+	if (symbol_conf.event_group) {
+		struct perf_evsel *pos;
+
+		nr_entries = 0;
+		list_for_each_entry(pos, &evlist->entries, node)
+			if (perf_evsel__is_group_leader(pos))
+				nr_entries++;
+
+		if (nr_entries == 1)
+			goto single_entry;
+	}
+
+	return __perf_evlist__tui_browse_hists(evlist, nr_entries, help,
+					       hbt, env);
 }
diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c
new file mode 100644
index 0000000..7d8dc58
--- /dev/null
+++ b/tools/perf/ui/gtk/annotate.c
@@ -0,0 +1,229 @@
+#include "gtk.h"
+#include "util/debug.h"
+#include "util/annotate.h"
+#include "ui/helpline.h"
+
+
+enum {
+	ANN_COL__PERCENT,
+	ANN_COL__OFFSET,
+	ANN_COL__LINE,
+
+	MAX_ANN_COLS
+};
+
+static const char *const col_names[] = {
+	"Overhead",
+	"Offset",
+	"Line"
+};
+
+static int perf_gtk__get_percent(char *buf, size_t size, struct symbol *sym,
+				 struct disasm_line *dl, int evidx)
+{
+	struct sym_hist *symhist;
+	double percent = 0.0;
+	const char *markup;
+	int ret = 0;
+
+	strcpy(buf, "");
+
+	if (dl->offset == (s64) -1)
+		return 0;
+
+	symhist = annotation__histogram(symbol__annotation(sym), evidx);
+	if (!symhist->addr[dl->offset])
+		return 0;
+
+	percent = 100.0 * symhist->addr[dl->offset] / symhist->sum;
+
+	markup = perf_gtk__get_percent_color(percent);
+	if (markup)
+		ret += scnprintf(buf, size, "%s", markup);
+	ret += scnprintf(buf + ret, size - ret, "%6.2f%%", percent);
+	if (markup)
+		ret += scnprintf(buf + ret, size - ret, "</span>");
+
+	return ret;
+}
+
+static int perf_gtk__get_offset(char *buf, size_t size, struct symbol *sym,
+				struct map *map, struct disasm_line *dl)
+{
+	u64 start = map__rip_2objdump(map, sym->start);
+
+	strcpy(buf, "");
+
+	if (dl->offset == (s64) -1)
+		return 0;
+
+	return scnprintf(buf, size, "%"PRIx64, start + dl->offset);
+}
+
+static int perf_gtk__get_line(char *buf, size_t size, struct disasm_line *dl)
+{
+	int ret = 0;
+	char *line = g_markup_escape_text(dl->line, -1);
+	const char *markup = "<span fgcolor='gray'>";
+
+	strcpy(buf, "");
+
+	if (!line)
+		return 0;
+
+	if (dl->offset != (s64) -1)
+		markup = NULL;
+
+	if (markup)
+		ret += scnprintf(buf, size, "%s", markup);
+	ret += scnprintf(buf + ret, size - ret, "%s", line);
+	if (markup)
+		ret += scnprintf(buf + ret, size - ret, "</span>");
+
+	g_free(line);
+	return ret;
+}
+
+static int perf_gtk__annotate_symbol(GtkWidget *window, struct symbol *sym,
+				struct map *map, int evidx,
+				struct hist_browser_timer *hbt __maybe_unused)
+{
+	struct disasm_line *pos, *n;
+	struct annotation *notes;
+	GType col_types[MAX_ANN_COLS];
+	GtkCellRenderer *renderer;
+	GtkListStore *store;
+	GtkWidget *view;
+	int i;
+	char s[512];
+
+	notes = symbol__annotation(sym);
+
+	for (i = 0; i < MAX_ANN_COLS; i++) {
+		col_types[i] = G_TYPE_STRING;
+	}
+	store = gtk_list_store_newv(MAX_ANN_COLS, col_types);
+
+	view = gtk_tree_view_new();
+	renderer = gtk_cell_renderer_text_new();
+
+	for (i = 0; i < MAX_ANN_COLS; i++) {
+		gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
+					-1, col_names[i], renderer, "markup",
+					i, NULL);
+	}
+
+	gtk_tree_view_set_model(GTK_TREE_VIEW(view), GTK_TREE_MODEL(store));
+	g_object_unref(GTK_TREE_MODEL(store));
+
+	list_for_each_entry(pos, &notes->src->source, node) {
+		GtkTreeIter iter;
+
+		gtk_list_store_append(store, &iter);
+
+		if (perf_gtk__get_percent(s, sizeof(s), sym, pos, evidx))
+			gtk_list_store_set(store, &iter, ANN_COL__PERCENT, s, -1);
+		if (perf_gtk__get_offset(s, sizeof(s), sym, map, pos))
+			gtk_list_store_set(store, &iter, ANN_COL__OFFSET, s, -1);
+		if (perf_gtk__get_line(s, sizeof(s), pos))
+			gtk_list_store_set(store, &iter, ANN_COL__LINE, s, -1);
+	}
+
+	gtk_container_add(GTK_CONTAINER(window), view);
+
+	list_for_each_entry_safe(pos, n, &notes->src->source, node) {
+		list_del(&pos->node);
+		disasm_line__free(pos);
+	}
+
+	return 0;
+}
+
+int symbol__gtk_annotate(struct symbol *sym, struct map *map, int evidx,
+			 struct hist_browser_timer *hbt)
+{
+	GtkWidget *window;
+	GtkWidget *notebook;
+	GtkWidget *scrolled_window;
+	GtkWidget *tab_label;
+
+	if (map->dso->annotate_warned)
+		return -1;
+
+	if (symbol__annotate(sym, map, 0) < 0) {
+		ui__error("%s", ui_helpline__current);
+		return -1;
+	}
+
+	if (perf_gtk__is_active_context(pgctx)) {
+		window = pgctx->main_window;
+		notebook = pgctx->notebook;
+	} else {
+		GtkWidget *vbox;
+		GtkWidget *infobar;
+		GtkWidget *statbar;
+
+		signal(SIGSEGV, perf_gtk__signal);
+		signal(SIGFPE,  perf_gtk__signal);
+		signal(SIGINT,  perf_gtk__signal);
+		signal(SIGQUIT, perf_gtk__signal);
+		signal(SIGTERM, perf_gtk__signal);
+
+		window = gtk_window_new(GTK_WINDOW_TOPLEVEL);
+		gtk_window_set_title(GTK_WINDOW(window), "perf annotate");
+
+		g_signal_connect(window, "delete_event", gtk_main_quit, NULL);
+
+		pgctx = perf_gtk__activate_context(window);
+		if (!pgctx)
+			return -1;
+
+		vbox = gtk_vbox_new(FALSE, 0);
+		notebook = gtk_notebook_new();
+		pgctx->notebook = notebook;
+
+		gtk_box_pack_start(GTK_BOX(vbox), notebook, TRUE, TRUE, 0);
+
+		infobar = perf_gtk__setup_info_bar();
+		if (infobar) {
+			gtk_box_pack_start(GTK_BOX(vbox), infobar,
+					   FALSE, FALSE, 0);
+		}
+
+		statbar = perf_gtk__setup_statusbar();
+		gtk_box_pack_start(GTK_BOX(vbox), statbar, FALSE, FALSE, 0);
+
+		gtk_container_add(GTK_CONTAINER(window), vbox);
+	}
+
+	scrolled_window = gtk_scrolled_window_new(NULL, NULL);
+	tab_label = gtk_label_new(sym->name);
+
+	gtk_scrolled_window_set_policy(GTK_SCROLLED_WINDOW(scrolled_window),
+				       GTK_POLICY_AUTOMATIC,
+				       GTK_POLICY_AUTOMATIC);
+
+	gtk_notebook_append_page(GTK_NOTEBOOK(notebook), scrolled_window,
+				 tab_label);
+
+	perf_gtk__annotate_symbol(scrolled_window, sym, map, evidx, hbt);
+	return 0;
+}
+
+void perf_gtk__show_annotations(void)
+{
+	GtkWidget *window;
+
+	if (!perf_gtk__is_active_context(pgctx))
+		return;
+
+	window = pgctx->main_window;
+	gtk_widget_show_all(window);
+
+	perf_gtk__resize_window(window);
+	gtk_window_set_position(GTK_WINDOW(window), GTK_WIN_POS_CENTER);
+
+	gtk_main();
+
+	perf_gtk__deactivate_context(&pgctx);
+}
diff --git a/tools/perf/ui/gtk/browser.c b/tools/perf/ui/gtk/browser.c
index 253b621..c95012c 100644
--- a/tools/perf/ui/gtk/browser.c
+++ b/tools/perf/ui/gtk/browser.c
@@ -8,15 +8,13 @@
 
 #include <signal.h>
 
-#define MAX_COLUMNS			32
-
-static void perf_gtk__signal(int sig)
+void perf_gtk__signal(int sig)
 {
 	perf_gtk__exit(false);
 	psignal(sig, "perf");
 }
 
-static void perf_gtk__resize_window(GtkWidget *window)
+void perf_gtk__resize_window(GtkWidget *window)
 {
 	GdkRectangle rect;
 	GdkScreen *screen;
@@ -36,7 +34,7 @@
 	gtk_window_resize(GTK_WINDOW(window), width, height);
 }
 
-static const char *perf_gtk__get_percent_color(double percent)
+const char *perf_gtk__get_percent_color(double percent)
 {
 	if (percent >= MIN_RED)
 		return "<span fgcolor='red'>";
@@ -45,155 +43,8 @@
 	return NULL;
 }
 
-#define HPP__COLOR_FN(_name, _field)						\
-static int perf_gtk__hpp_color_ ## _name(struct perf_hpp *hpp,			\
-					 struct hist_entry *he)			\
-{										\
-	struct hists *hists = he->hists;					\
-	double percent = 100.0 * he->stat._field / hists->stats.total_period;	\
-	const char *markup;							\
-	int ret = 0;								\
-										\
-	markup = perf_gtk__get_percent_color(percent);				\
-	if (markup)								\
-		ret += scnprintf(hpp->buf, hpp->size, "%s", markup);		\
-	ret += scnprintf(hpp->buf + ret, hpp->size - ret, "%6.2f%%", percent); 	\
-	if (markup)								\
-		ret += scnprintf(hpp->buf + ret, hpp->size - ret, "</span>"); 	\
-										\
-	return ret;								\
-}
-
-HPP__COLOR_FN(overhead, period)
-HPP__COLOR_FN(overhead_sys, period_sys)
-HPP__COLOR_FN(overhead_us, period_us)
-HPP__COLOR_FN(overhead_guest_sys, period_guest_sys)
-HPP__COLOR_FN(overhead_guest_us, period_guest_us)
-
-#undef HPP__COLOR_FN
-
-void perf_gtk__init_hpp(void)
-{
-	perf_hpp__init();
-
-	perf_hpp__format[PERF_HPP__OVERHEAD].color =
-				perf_gtk__hpp_color_overhead;
-	perf_hpp__format[PERF_HPP__OVERHEAD_SYS].color =
-				perf_gtk__hpp_color_overhead_sys;
-	perf_hpp__format[PERF_HPP__OVERHEAD_US].color =
-				perf_gtk__hpp_color_overhead_us;
-	perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_SYS].color =
-				perf_gtk__hpp_color_overhead_guest_sys;
-	perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_US].color =
-				perf_gtk__hpp_color_overhead_guest_us;
-}
-
-static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists)
-{
-	GType col_types[MAX_COLUMNS];
-	GtkCellRenderer *renderer;
-	struct sort_entry *se;
-	GtkListStore *store;
-	struct rb_node *nd;
-	GtkWidget *view;
-	int i, col_idx;
-	int nr_cols;
-	char s[512];
-
-	struct perf_hpp hpp = {
-		.buf		= s,
-		.size		= sizeof(s),
-	};
-
-	nr_cols = 0;
-
-	for (i = 0; i < PERF_HPP__MAX_INDEX; i++) {
-		if (!perf_hpp__format[i].cond)
-			continue;
-
-		col_types[nr_cols++] = G_TYPE_STRING;
-	}
-
-	list_for_each_entry(se, &hist_entry__sort_list, list) {
-		if (se->elide)
-			continue;
-
-		col_types[nr_cols++] = G_TYPE_STRING;
-	}
-
-	store = gtk_list_store_newv(nr_cols, col_types);
-
-	view = gtk_tree_view_new();
-
-	renderer = gtk_cell_renderer_text_new();
-
-	col_idx = 0;
-
-	for (i = 0; i < PERF_HPP__MAX_INDEX; i++) {
-		if (!perf_hpp__format[i].cond)
-			continue;
-
-		perf_hpp__format[i].header(&hpp);
-
-		gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
-							    -1, s,
-							    renderer, "markup",
-							    col_idx++, NULL);
-	}
-
-	list_for_each_entry(se, &hist_entry__sort_list, list) {
-		if (se->elide)
-			continue;
-
-		gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
-							    -1, se->se_header,
-							    renderer, "text",
-							    col_idx++, NULL);
-	}
-
-	gtk_tree_view_set_model(GTK_TREE_VIEW(view), GTK_TREE_MODEL(store));
-
-	g_object_unref(GTK_TREE_MODEL(store));
-
-	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
-		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
-		GtkTreeIter iter;
-
-		if (h->filtered)
-			continue;
-
-		gtk_list_store_append(store, &iter);
-
-		col_idx = 0;
-
-		for (i = 0; i < PERF_HPP__MAX_INDEX; i++) {
-			if (!perf_hpp__format[i].cond)
-				continue;
-
-			if (perf_hpp__format[i].color)
-				perf_hpp__format[i].color(&hpp, h);
-			else
-				perf_hpp__format[i].entry(&hpp, h);
-
-			gtk_list_store_set(store, &iter, col_idx++, s, -1);
-		}
-
-		list_for_each_entry(se, &hist_entry__sort_list, list) {
-			if (se->elide)
-				continue;
-
-			se->se_snprintf(h, s, ARRAY_SIZE(s),
-					hists__col_len(hists, se->se_width_idx));
-
-			gtk_list_store_set(store, &iter, col_idx++, s, -1);
-		}
-	}
-
-	gtk_container_add(GTK_CONTAINER(window), view);
-}
-
 #ifdef HAVE_GTK_INFO_BAR
-static GtkWidget *perf_gtk__setup_info_bar(void)
+GtkWidget *perf_gtk__setup_info_bar(void)
 {
 	GtkWidget *info_bar;
 	GtkWidget *label;
@@ -220,7 +71,7 @@
 }
 #endif
 
-static GtkWidget *perf_gtk__setup_statusbar(void)
+GtkWidget *perf_gtk__setup_statusbar(void)
 {
 	GtkWidget *stbar;
 	unsigned ctxid;
@@ -234,79 +85,3 @@
 
 	return stbar;
 }
-
-int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
-				  const char *help,
-				  struct hist_browser_timer *hbt __maybe_unused)
-{
-	struct perf_evsel *pos;
-	GtkWidget *vbox;
-	GtkWidget *notebook;
-	GtkWidget *info_bar;
-	GtkWidget *statbar;
-	GtkWidget *window;
-
-	signal(SIGSEGV, perf_gtk__signal);
-	signal(SIGFPE,  perf_gtk__signal);
-	signal(SIGINT,  perf_gtk__signal);
-	signal(SIGQUIT, perf_gtk__signal);
-	signal(SIGTERM, perf_gtk__signal);
-
-	window = gtk_window_new(GTK_WINDOW_TOPLEVEL);
-
-	gtk_window_set_title(GTK_WINDOW(window), "perf report");
-
-	g_signal_connect(window, "delete_event", gtk_main_quit, NULL);
-
-	pgctx = perf_gtk__activate_context(window);
-	if (!pgctx)
-		return -1;
-
-	vbox = gtk_vbox_new(FALSE, 0);
-
-	notebook = gtk_notebook_new();
-
-	list_for_each_entry(pos, &evlist->entries, node) {
-		struct hists *hists = &pos->hists;
-		const char *evname = perf_evsel__name(pos);
-		GtkWidget *scrolled_window;
-		GtkWidget *tab_label;
-
-		scrolled_window = gtk_scrolled_window_new(NULL, NULL);
-
-		gtk_scrolled_window_set_policy(GTK_SCROLLED_WINDOW(scrolled_window),
-							GTK_POLICY_AUTOMATIC,
-							GTK_POLICY_AUTOMATIC);
-
-		perf_gtk__show_hists(scrolled_window, hists);
-
-		tab_label = gtk_label_new(evname);
-
-		gtk_notebook_append_page(GTK_NOTEBOOK(notebook), scrolled_window, tab_label);
-	}
-
-	gtk_box_pack_start(GTK_BOX(vbox), notebook, TRUE, TRUE, 0);
-
-	info_bar = perf_gtk__setup_info_bar();
-	if (info_bar)
-		gtk_box_pack_start(GTK_BOX(vbox), info_bar, FALSE, FALSE, 0);
-
-	statbar = perf_gtk__setup_statusbar();
-	gtk_box_pack_start(GTK_BOX(vbox), statbar, FALSE, FALSE, 0);
-
-	gtk_container_add(GTK_CONTAINER(window), vbox);
-
-	gtk_widget_show_all(window);
-
-	perf_gtk__resize_window(window);
-
-	gtk_window_set_position(GTK_WINDOW(window), GTK_WIN_POS_CENTER);
-
-	ui_helpline__push(help);
-
-	gtk_main();
-
-	perf_gtk__deactivate_context(&pgctx);
-
-	return 0;
-}
diff --git a/tools/perf/ui/gtk/gtk.h b/tools/perf/ui/gtk/gtk.h
index 856320e..3d96785 100644
--- a/tools/perf/ui/gtk/gtk.h
+++ b/tools/perf/ui/gtk/gtk.h
@@ -10,6 +10,7 @@
 
 struct perf_gtk_context {
 	GtkWidget *main_window;
+	GtkWidget *notebook;
 
 #ifdef HAVE_GTK_INFO_BAR
 	GtkWidget *info_bar;
@@ -33,7 +34,14 @@
 void perf_gtk__init_progress(void);
 void perf_gtk__init_hpp(void);
 
-#ifndef HAVE_GTK_INFO_BAR
+void perf_gtk__signal(int sig);
+void perf_gtk__resize_window(GtkWidget *window);
+const char *perf_gtk__get_percent_color(double percent);
+GtkWidget *perf_gtk__setup_statusbar(void);
+
+#ifdef HAVE_GTK_INFO_BAR
+GtkWidget *perf_gtk__setup_info_bar(void);
+#else
 static inline GtkWidget *perf_gtk__setup_info_bar(void)
 {
 	return NULL;
diff --git a/tools/perf/ui/gtk/helpline.c b/tools/perf/ui/gtk/helpline.c
index 5db4432..3388cbd 100644
--- a/tools/perf/ui/gtk/helpline.c
+++ b/tools/perf/ui/gtk/helpline.c
@@ -24,17 +24,7 @@
 			   pgctx->statbar_ctx_id, msg);
 }
 
-static struct ui_helpline gtk_helpline_fns = {
-	.pop	= gtk_helpline_pop,
-	.push	= gtk_helpline_push,
-};
-
-void perf_gtk__init_helpline(void)
-{
-	helpline_fns = &gtk_helpline_fns;
-}
-
-int perf_gtk__show_helpline(const char *fmt, va_list ap)
+static int gtk_helpline_show(const char *fmt, va_list ap)
 {
 	int ret;
 	char *ptr;
@@ -54,3 +44,14 @@
 
 	return ret;
 }
+
+static struct ui_helpline gtk_helpline_fns = {
+	.pop	= gtk_helpline_pop,
+	.push	= gtk_helpline_push,
+	.show	= gtk_helpline_show,
+};
+
+void perf_gtk__init_helpline(void)
+{
+	helpline_fns = &gtk_helpline_fns;
+}
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
new file mode 100644
index 0000000..1e764a8
--- /dev/null
+++ b/tools/perf/ui/gtk/hists.c
@@ -0,0 +1,312 @@
+#include "../evlist.h"
+#include "../cache.h"
+#include "../evsel.h"
+#include "../sort.h"
+#include "../hist.h"
+#include "../helpline.h"
+#include "gtk.h"
+
+#define MAX_COLUMNS			32
+
+static int __percent_color_snprintf(char *buf, size_t size, double percent)
+{
+	int ret = 0;
+	const char *markup;
+
+	markup = perf_gtk__get_percent_color(percent);
+	if (markup)
+		ret += scnprintf(buf, size, markup);
+
+	ret += scnprintf(buf + ret, size - ret, " %6.2f%%", percent);
+
+	if (markup)
+		ret += scnprintf(buf + ret, size - ret, "</span>");
+
+	return ret;
+}
+
+
+static int __hpp__color_fmt(struct perf_hpp *hpp, struct hist_entry *he,
+			    u64 (*get_field)(struct hist_entry *))
+{
+	int ret;
+	double percent = 0.0;
+	struct hists *hists = he->hists;
+
+	if (hists->stats.total_period)
+		percent = 100.0 * get_field(he) / hists->stats.total_period;
+
+	ret = __percent_color_snprintf(hpp->buf, hpp->size, percent);
+
+	if (symbol_conf.event_group) {
+		int prev_idx, idx_delta;
+		struct perf_evsel *evsel = hists_to_evsel(hists);
+		struct hist_entry *pair;
+		int nr_members = evsel->nr_members;
+
+		if (nr_members <= 1)
+			return ret;
+
+		prev_idx = perf_evsel__group_idx(evsel);
+
+		list_for_each_entry(pair, &he->pairs.head, pairs.node) {
+			u64 period = get_field(pair);
+			u64 total = pair->hists->stats.total_period;
+
+			evsel = hists_to_evsel(pair->hists);
+			idx_delta = perf_evsel__group_idx(evsel) - prev_idx - 1;
+
+			while (idx_delta--) {
+				/*
+				 * zero-fill group members in the middle which
+				 * have no sample
+				 */
+				ret += __percent_color_snprintf(hpp->buf + ret,
+								hpp->size - ret,
+								0.0);
+			}
+
+			percent = 100.0 * period / total;
+			ret += __percent_color_snprintf(hpp->buf + ret,
+							hpp->size - ret,
+							percent);
+
+			prev_idx = perf_evsel__group_idx(evsel);
+		}
+
+		idx_delta = nr_members - prev_idx - 1;
+
+		while (idx_delta--) {
+			/*
+			 * zero-fill group members at last which have no sample
+			 */
+			ret += __percent_color_snprintf(hpp->buf + ret,
+							hpp->size - ret,
+							0.0);
+		}
+	}
+	return ret;
+}
+
+#define __HPP_COLOR_PERCENT_FN(_type, _field)					\
+static u64 he_get_##_field(struct hist_entry *he)				\
+{										\
+	return he->stat._field;							\
+}										\
+										\
+static int perf_gtk__hpp_color_##_type(struct perf_hpp *hpp,			\
+				       struct hist_entry *he)			\
+{										\
+	return __hpp__color_fmt(hpp, he, he_get_##_field);			\
+}
+
+__HPP_COLOR_PERCENT_FN(overhead, period)
+__HPP_COLOR_PERCENT_FN(overhead_sys, period_sys)
+__HPP_COLOR_PERCENT_FN(overhead_us, period_us)
+__HPP_COLOR_PERCENT_FN(overhead_guest_sys, period_guest_sys)
+__HPP_COLOR_PERCENT_FN(overhead_guest_us, period_guest_us)
+
+#undef __HPP_COLOR_PERCENT_FN
+
+
+void perf_gtk__init_hpp(void)
+{
+	perf_hpp__column_enable(PERF_HPP__OVERHEAD);
+
+	perf_hpp__init();
+
+	perf_hpp__format[PERF_HPP__OVERHEAD].color =
+				perf_gtk__hpp_color_overhead;
+	perf_hpp__format[PERF_HPP__OVERHEAD_SYS].color =
+				perf_gtk__hpp_color_overhead_sys;
+	perf_hpp__format[PERF_HPP__OVERHEAD_US].color =
+				perf_gtk__hpp_color_overhead_us;
+	perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_SYS].color =
+				perf_gtk__hpp_color_overhead_guest_sys;
+	perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_US].color =
+				perf_gtk__hpp_color_overhead_guest_us;
+}
+
+static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists)
+{
+	struct perf_hpp_fmt *fmt;
+	GType col_types[MAX_COLUMNS];
+	GtkCellRenderer *renderer;
+	struct sort_entry *se;
+	GtkListStore *store;
+	struct rb_node *nd;
+	GtkWidget *view;
+	int col_idx;
+	int nr_cols;
+	char s[512];
+
+	struct perf_hpp hpp = {
+		.buf		= s,
+		.size		= sizeof(s),
+		.ptr		= hists_to_evsel(hists),
+	};
+
+	nr_cols = 0;
+
+	perf_hpp__for_each_format(fmt)
+		col_types[nr_cols++] = G_TYPE_STRING;
+
+	list_for_each_entry(se, &hist_entry__sort_list, list) {
+		if (se->elide)
+			continue;
+
+		col_types[nr_cols++] = G_TYPE_STRING;
+	}
+
+	store = gtk_list_store_newv(nr_cols, col_types);
+
+	view = gtk_tree_view_new();
+
+	renderer = gtk_cell_renderer_text_new();
+
+	col_idx = 0;
+
+	perf_hpp__for_each_format(fmt) {
+		fmt->header(&hpp);
+
+		gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
+							    -1, ltrim(s),
+							    renderer, "markup",
+							    col_idx++, NULL);
+	}
+
+	list_for_each_entry(se, &hist_entry__sort_list, list) {
+		if (se->elide)
+			continue;
+
+		gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
+							    -1, se->se_header,
+							    renderer, "text",
+							    col_idx++, NULL);
+	}
+
+	gtk_tree_view_set_model(GTK_TREE_VIEW(view), GTK_TREE_MODEL(store));
+
+	g_object_unref(GTK_TREE_MODEL(store));
+
+	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+		GtkTreeIter iter;
+
+		if (h->filtered)
+			continue;
+
+		gtk_list_store_append(store, &iter);
+
+		col_idx = 0;
+
+		perf_hpp__for_each_format(fmt) {
+			if (fmt->color)
+				fmt->color(&hpp, h);
+			else
+				fmt->entry(&hpp, h);
+
+			gtk_list_store_set(store, &iter, col_idx++, s, -1);
+		}
+
+		list_for_each_entry(se, &hist_entry__sort_list, list) {
+			if (se->elide)
+				continue;
+
+			se->se_snprintf(h, s, ARRAY_SIZE(s),
+					hists__col_len(hists, se->se_width_idx));
+
+			gtk_list_store_set(store, &iter, col_idx++, s, -1);
+		}
+	}
+
+	gtk_container_add(GTK_CONTAINER(window), view);
+}
+
+int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
+				  const char *help,
+				  struct hist_browser_timer *hbt __maybe_unused)
+{
+	struct perf_evsel *pos;
+	GtkWidget *vbox;
+	GtkWidget *notebook;
+	GtkWidget *info_bar;
+	GtkWidget *statbar;
+	GtkWidget *window;
+
+	signal(SIGSEGV, perf_gtk__signal);
+	signal(SIGFPE,  perf_gtk__signal);
+	signal(SIGINT,  perf_gtk__signal);
+	signal(SIGQUIT, perf_gtk__signal);
+	signal(SIGTERM, perf_gtk__signal);
+
+	window = gtk_window_new(GTK_WINDOW_TOPLEVEL);
+
+	gtk_window_set_title(GTK_WINDOW(window), "perf report");
+
+	g_signal_connect(window, "delete_event", gtk_main_quit, NULL);
+
+	pgctx = perf_gtk__activate_context(window);
+	if (!pgctx)
+		return -1;
+
+	vbox = gtk_vbox_new(FALSE, 0);
+
+	notebook = gtk_notebook_new();
+
+	gtk_box_pack_start(GTK_BOX(vbox), notebook, TRUE, TRUE, 0);
+
+	info_bar = perf_gtk__setup_info_bar();
+	if (info_bar)
+		gtk_box_pack_start(GTK_BOX(vbox), info_bar, FALSE, FALSE, 0);
+
+	statbar = perf_gtk__setup_statusbar();
+	gtk_box_pack_start(GTK_BOX(vbox), statbar, FALSE, FALSE, 0);
+
+	gtk_container_add(GTK_CONTAINER(window), vbox);
+
+	list_for_each_entry(pos, &evlist->entries, node) {
+		struct hists *hists = &pos->hists;
+		const char *evname = perf_evsel__name(pos);
+		GtkWidget *scrolled_window;
+		GtkWidget *tab_label;
+		char buf[512];
+		size_t size = sizeof(buf);
+
+		if (symbol_conf.event_group) {
+			if (!perf_evsel__is_group_leader(pos))
+				continue;
+
+			if (pos->nr_members > 1) {
+				perf_evsel__group_desc(pos, buf, size);
+				evname = buf;
+			}
+		}
+
+		scrolled_window = gtk_scrolled_window_new(NULL, NULL);
+
+		gtk_scrolled_window_set_policy(GTK_SCROLLED_WINDOW(scrolled_window),
+							GTK_POLICY_AUTOMATIC,
+							GTK_POLICY_AUTOMATIC);
+
+		perf_gtk__show_hists(scrolled_window, hists);
+
+		tab_label = gtk_label_new(evname);
+
+		gtk_notebook_append_page(GTK_NOTEBOOK(notebook), scrolled_window, tab_label);
+	}
+
+	gtk_widget_show_all(window);
+
+	perf_gtk__resize_window(window);
+
+	gtk_window_set_position(GTK_WINDOW(window), GTK_WIN_POS_CENTER);
+
+	ui_helpline__push(help);
+
+	gtk_main();
+
+	perf_gtk__deactivate_context(&pgctx);
+
+	return 0;
+}
diff --git a/tools/perf/ui/helpline.c b/tools/perf/ui/helpline.c
index a49bcf3..700fb3c 100644
--- a/tools/perf/ui/helpline.c
+++ b/tools/perf/ui/helpline.c
@@ -16,9 +16,16 @@
 {
 }
 
+static int nop_helpline__show(const char *fmt __maybe_unused,
+			       va_list ap __maybe_unused)
+{
+	return 0;
+}
+
 static struct ui_helpline default_helpline_fns = {
 	.pop	= nop_helpline__pop,
 	.push	= nop_helpline__push,
+	.show	= nop_helpline__show,
 };
 
 struct ui_helpline *helpline_fns = &default_helpline_fns;
@@ -59,3 +66,8 @@
 	ui_helpline__pop();
 	ui_helpline__push(msg);
 }
+
+int ui_helpline__vshow(const char *fmt, va_list ap)
+{
+	return helpline_fns->show(fmt, ap);
+}
diff --git a/tools/perf/ui/helpline.h b/tools/perf/ui/helpline.h
index baa28a4..46181f4 100644
--- a/tools/perf/ui/helpline.h
+++ b/tools/perf/ui/helpline.h
@@ -9,6 +9,7 @@
 struct ui_helpline {
 	void (*pop)(void);
 	void (*push)(const char *msg);
+	int  (*show)(const char *fmt, va_list ap);
 };
 
 extern struct ui_helpline *helpline_fns;
@@ -20,28 +21,9 @@
 void ui_helpline__vpush(const char *fmt, va_list ap);
 void ui_helpline__fpush(const char *fmt, ...);
 void ui_helpline__puts(const char *msg);
+int  ui_helpline__vshow(const char *fmt, va_list ap);
 
 extern char ui_helpline__current[512];
-
-#ifdef NEWT_SUPPORT
 extern char ui_helpline__last_msg[];
-int ui_helpline__show_help(const char *format, va_list ap);
-#else
-static inline int ui_helpline__show_help(const char *format __maybe_unused,
-					 va_list ap __maybe_unused)
-{
-	return 0;
-}
-#endif /* NEWT_SUPPORT */
-
-#ifdef GTK2_SUPPORT
-int perf_gtk__show_helpline(const char *format, va_list ap);
-#else
-static inline int perf_gtk__show_helpline(const char *format __maybe_unused,
-					  va_list ap __maybe_unused)
-{
-	return 0;
-}
-#endif /* GTK2_SUPPORT */
 
 #endif /* _PERF_UI_HELPLINE_H_ */
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index aa84130..d671e63 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -3,151 +3,163 @@
 #include "../util/hist.h"
 #include "../util/util.h"
 #include "../util/sort.h"
-
+#include "../util/evsel.h"
 
 /* hist period print (hpp) functions */
-static int hpp__header_overhead(struct perf_hpp *hpp)
-{
-	return scnprintf(hpp->buf, hpp->size, "Overhead");
-}
 
-static int hpp__width_overhead(struct perf_hpp *hpp __maybe_unused)
-{
-	return 8;
-}
+typedef int (*hpp_snprint_fn)(char *buf, size_t size, const char *fmt, ...);
 
-static int hpp__color_overhead(struct perf_hpp *hpp, struct hist_entry *he)
+static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
+		      u64 (*get_field)(struct hist_entry *),
+		      const char *fmt, hpp_snprint_fn print_fn,
+		      bool fmt_percent)
 {
+	int ret;
 	struct hists *hists = he->hists;
-	double percent = 100.0 * he->stat.period / hists->stats.total_period;
 
-	return percent_color_snprintf(hpp->buf, hpp->size, " %6.2f%%", percent);
+	if (fmt_percent) {
+		double percent = 0.0;
+
+		if (hists->stats.total_period)
+			percent = 100.0 * get_field(he) /
+				  hists->stats.total_period;
+
+		ret = print_fn(hpp->buf, hpp->size, fmt, percent);
+	} else
+		ret = print_fn(hpp->buf, hpp->size, fmt, get_field(he));
+
+	if (symbol_conf.event_group) {
+		int prev_idx, idx_delta;
+		struct perf_evsel *evsel = hists_to_evsel(hists);
+		struct hist_entry *pair;
+		int nr_members = evsel->nr_members;
+
+		if (nr_members <= 1)
+			return ret;
+
+		prev_idx = perf_evsel__group_idx(evsel);
+
+		list_for_each_entry(pair, &he->pairs.head, pairs.node) {
+			u64 period = get_field(pair);
+			u64 total = pair->hists->stats.total_period;
+
+			if (!total)
+				continue;
+
+			evsel = hists_to_evsel(pair->hists);
+			idx_delta = perf_evsel__group_idx(evsel) - prev_idx - 1;
+
+			while (idx_delta--) {
+				/*
+				 * zero-fill group members in the middle which
+				 * have no sample
+				 */
+				ret += print_fn(hpp->buf + ret, hpp->size - ret,
+						fmt, 0);
+			}
+
+			if (fmt_percent)
+				ret += print_fn(hpp->buf + ret, hpp->size - ret,
+						fmt, 100.0 * period / total);
+			else
+				ret += print_fn(hpp->buf + ret, hpp->size - ret,
+						fmt, period);
+
+			prev_idx = perf_evsel__group_idx(evsel);
+		}
+
+		idx_delta = nr_members - prev_idx - 1;
+
+		while (idx_delta--) {
+			/*
+			 * zero-fill group members at last which have no sample
+			 */
+			ret += print_fn(hpp->buf + ret, hpp->size - ret,
+					fmt, 0);
+		}
+	}
+	return ret;
 }
 
-static int hpp__entry_overhead(struct perf_hpp *hpp, struct hist_entry *he)
-{
-	struct hists *hists = he->hists;
-	double percent = 100.0 * he->stat.period / hists->stats.total_period;
-	const char *fmt = symbol_conf.field_sep ? "%.2f" : " %6.2f%%";
-
-	return scnprintf(hpp->buf, hpp->size, fmt, percent);
+#define __HPP_HEADER_FN(_type, _str, _min_width, _unit_width) 		\
+static int hpp__header_##_type(struct perf_hpp *hpp)			\
+{									\
+	int len = _min_width;						\
+									\
+	if (symbol_conf.event_group) {					\
+		struct perf_evsel *evsel = hpp->ptr;			\
+									\
+		len = max(len, evsel->nr_members * _unit_width);	\
+	}								\
+	return scnprintf(hpp->buf, hpp->size, "%*s", len, _str);	\
 }
 
-static int hpp__header_overhead_sys(struct perf_hpp *hpp)
-{
-	const char *fmt = symbol_conf.field_sep ? "%s" : "%7s";
-
-	return scnprintf(hpp->buf, hpp->size, fmt, "sys");
+#define __HPP_WIDTH_FN(_type, _min_width, _unit_width) 			\
+static int hpp__width_##_type(struct perf_hpp *hpp __maybe_unused)	\
+{									\
+	int len = _min_width;						\
+									\
+	if (symbol_conf.event_group) {					\
+		struct perf_evsel *evsel = hpp->ptr;			\
+									\
+		len = max(len, evsel->nr_members * _unit_width);	\
+	}								\
+	return len;							\
 }
 
-static int hpp__width_overhead_sys(struct perf_hpp *hpp __maybe_unused)
-{
-	return 7;
+#define __HPP_COLOR_PERCENT_FN(_type, _field)					\
+static u64 he_get_##_field(struct hist_entry *he)				\
+{										\
+	return he->stat._field;							\
+}										\
+										\
+static int hpp__color_##_type(struct perf_hpp *hpp, struct hist_entry *he) 	\
+{										\
+	return __hpp__fmt(hpp, he, he_get_##_field, " %6.2f%%",			\
+			  (hpp_snprint_fn)percent_color_snprintf, true);	\
 }
 
-static int hpp__color_overhead_sys(struct perf_hpp *hpp, struct hist_entry *he)
-{
-	struct hists *hists = he->hists;
-	double percent = 100.0 * he->stat.period_sys / hists->stats.total_period;
-
-	return percent_color_snprintf(hpp->buf, hpp->size, "%6.2f%%", percent);
+#define __HPP_ENTRY_PERCENT_FN(_type, _field)					\
+static int hpp__entry_##_type(struct perf_hpp *hpp, struct hist_entry *he) 	\
+{										\
+	const char *fmt = symbol_conf.field_sep ? " %.2f" : " %6.2f%%";		\
+	return __hpp__fmt(hpp, he, he_get_##_field, fmt,			\
+			  scnprintf, true);					\
 }
 
-static int hpp__entry_overhead_sys(struct perf_hpp *hpp, struct hist_entry *he)
-{
-	struct hists *hists = he->hists;
-	double percent = 100.0 * he->stat.period_sys / hists->stats.total_period;
-	const char *fmt = symbol_conf.field_sep ? "%.2f" : "%6.2f%%";
-
-	return scnprintf(hpp->buf, hpp->size, fmt, percent);
+#define __HPP_ENTRY_RAW_FN(_type, _field)					\
+static u64 he_get_raw_##_field(struct hist_entry *he)				\
+{										\
+	return he->stat._field;							\
+}										\
+										\
+static int hpp__entry_##_type(struct perf_hpp *hpp, struct hist_entry *he) 	\
+{										\
+	const char *fmt = symbol_conf.field_sep ? " %"PRIu64 : " %11"PRIu64;	\
+	return __hpp__fmt(hpp, he, he_get_raw_##_field, fmt, scnprintf, false);	\
 }
 
-static int hpp__header_overhead_us(struct perf_hpp *hpp)
-{
-	const char *fmt = symbol_conf.field_sep ? "%s" : "%7s";
+#define HPP_PERCENT_FNS(_type, _str, _field, _min_width, _unit_width)	\
+__HPP_HEADER_FN(_type, _str, _min_width, _unit_width)			\
+__HPP_WIDTH_FN(_type, _min_width, _unit_width)				\
+__HPP_COLOR_PERCENT_FN(_type, _field)					\
+__HPP_ENTRY_PERCENT_FN(_type, _field)
 
-	return scnprintf(hpp->buf, hpp->size, fmt, "user");
-}
+#define HPP_RAW_FNS(_type, _str, _field, _min_width, _unit_width)	\
+__HPP_HEADER_FN(_type, _str, _min_width, _unit_width)			\
+__HPP_WIDTH_FN(_type, _min_width, _unit_width)				\
+__HPP_ENTRY_RAW_FN(_type, _field)
 
-static int hpp__width_overhead_us(struct perf_hpp *hpp __maybe_unused)
-{
-	return 7;
-}
 
-static int hpp__color_overhead_us(struct perf_hpp *hpp, struct hist_entry *he)
-{
-	struct hists *hists = he->hists;
-	double percent = 100.0 * he->stat.period_us / hists->stats.total_period;
+HPP_PERCENT_FNS(overhead, "Overhead", period, 8, 8)
+HPP_PERCENT_FNS(overhead_sys, "sys", period_sys, 8, 8)
+HPP_PERCENT_FNS(overhead_us, "usr", period_us, 8, 8)
+HPP_PERCENT_FNS(overhead_guest_sys, "guest sys", period_guest_sys, 9, 8)
+HPP_PERCENT_FNS(overhead_guest_us, "guest usr", period_guest_us, 9, 8)
 
-	return percent_color_snprintf(hpp->buf, hpp->size, "%6.2f%%", percent);
-}
+HPP_RAW_FNS(samples, "Samples", nr_events, 12, 12)
+HPP_RAW_FNS(period, "Period", period, 12, 12)
 
-static int hpp__entry_overhead_us(struct perf_hpp *hpp, struct hist_entry *he)
-{
-	struct hists *hists = he->hists;
-	double percent = 100.0 * he->stat.period_us / hists->stats.total_period;
-	const char *fmt = symbol_conf.field_sep ? "%.2f" : "%6.2f%%";
-
-	return scnprintf(hpp->buf, hpp->size, fmt, percent);
-}
-
-static int hpp__header_overhead_guest_sys(struct perf_hpp *hpp)
-{
-	return scnprintf(hpp->buf, hpp->size, "guest sys");
-}
-
-static int hpp__width_overhead_guest_sys(struct perf_hpp *hpp __maybe_unused)
-{
-	return 9;
-}
-
-static int hpp__color_overhead_guest_sys(struct perf_hpp *hpp,
-					 struct hist_entry *he)
-{
-	struct hists *hists = he->hists;
-	double percent = 100.0 * he->stat.period_guest_sys / hists->stats.total_period;
-
-	return percent_color_snprintf(hpp->buf, hpp->size, " %6.2f%% ", percent);
-}
-
-static int hpp__entry_overhead_guest_sys(struct perf_hpp *hpp,
-					 struct hist_entry *he)
-{
-	struct hists *hists = he->hists;
-	double percent = 100.0 * he->stat.period_guest_sys / hists->stats.total_period;
-	const char *fmt = symbol_conf.field_sep ? "%.2f" : " %6.2f%% ";
-
-	return scnprintf(hpp->buf, hpp->size, fmt, percent);
-}
-
-static int hpp__header_overhead_guest_us(struct perf_hpp *hpp)
-{
-	return scnprintf(hpp->buf, hpp->size, "guest usr");
-}
-
-static int hpp__width_overhead_guest_us(struct perf_hpp *hpp __maybe_unused)
-{
-	return 9;
-}
-
-static int hpp__color_overhead_guest_us(struct perf_hpp *hpp,
-					struct hist_entry *he)
-{
-	struct hists *hists = he->hists;
-	double percent = 100.0 * he->stat.period_guest_us / hists->stats.total_period;
-
-	return percent_color_snprintf(hpp->buf, hpp->size, " %6.2f%% ", percent);
-}
-
-static int hpp__entry_overhead_guest_us(struct perf_hpp *hpp,
-					struct hist_entry *he)
-{
-	struct hists *hists = he->hists;
-	double percent = 100.0 * he->stat.period_guest_us / hists->stats.total_period;
-	const char *fmt = symbol_conf.field_sep ? "%.2f" : " %6.2f%% ";
-
-	return scnprintf(hpp->buf, hpp->size, fmt, percent);
-}
 
 static int hpp__header_baseline(struct perf_hpp *hpp)
 {
@@ -179,7 +191,7 @@
 {
 	double percent = baseline_percent(he);
 
-	if (hist_entry__has_pairs(he))
+	if (hist_entry__has_pairs(he) || symbol_conf.field_sep)
 		return percent_color_snprintf(hpp->buf, hpp->size, " %6.2f%%", percent);
 	else
 		return scnprintf(hpp->buf, hpp->size, "        ");
@@ -196,44 +208,6 @@
 		return scnprintf(hpp->buf, hpp->size, "            ");
 }
 
-static int hpp__header_samples(struct perf_hpp *hpp)
-{
-	const char *fmt = symbol_conf.field_sep ? "%s" : "%11s";
-
-	return scnprintf(hpp->buf, hpp->size, fmt, "Samples");
-}
-
-static int hpp__width_samples(struct perf_hpp *hpp __maybe_unused)
-{
-	return 11;
-}
-
-static int hpp__entry_samples(struct perf_hpp *hpp, struct hist_entry *he)
-{
-	const char *fmt = symbol_conf.field_sep ? "%" PRIu64 : "%11" PRIu64;
-
-	return scnprintf(hpp->buf, hpp->size, fmt, he->stat.nr_events);
-}
-
-static int hpp__header_period(struct perf_hpp *hpp)
-{
-	const char *fmt = symbol_conf.field_sep ? "%s" : "%12s";
-
-	return scnprintf(hpp->buf, hpp->size, fmt, "Period");
-}
-
-static int hpp__width_period(struct perf_hpp *hpp __maybe_unused)
-{
-	return 12;
-}
-
-static int hpp__entry_period(struct perf_hpp *hpp, struct hist_entry *he)
-{
-	const char *fmt = symbol_conf.field_sep ? "%" PRIu64 : "%12" PRIu64;
-
-	return scnprintf(hpp->buf, hpp->size, fmt, he->stat.period);
-}
-
 static int hpp__header_period_baseline(struct perf_hpp *hpp)
 {
 	const char *fmt = symbol_conf.field_sep ? "%s" : "%12s";
@@ -254,6 +228,7 @@
 
 	return scnprintf(hpp->buf, hpp->size, fmt, period);
 }
+
 static int hpp__header_delta(struct perf_hpp *hpp)
 {
 	const char *fmt = symbol_conf.field_sep ? "%s" : "%7s";
@@ -268,14 +243,18 @@
 
 static int hpp__entry_delta(struct perf_hpp *hpp, struct hist_entry *he)
 {
+	struct hist_entry *pair = hist_entry__next_pair(he);
 	const char *fmt = symbol_conf.field_sep ? "%s" : "%7.7s";
 	char buf[32] = " ";
-	double diff;
+	double diff = 0.0;
 
-	if (he->diff.computed)
-		diff = he->diff.period_ratio_delta;
-	else
-		diff = perf_diff__compute_delta(he);
+	if (pair) {
+		if (he->diff.computed)
+			diff = he->diff.period_ratio_delta;
+		else
+			diff = perf_diff__compute_delta(he, pair);
+	} else
+		diff = perf_diff__period_percent(he, he->stat.period);
 
 	if (fabs(diff) >= 0.01)
 		scnprintf(buf, sizeof(buf), "%+4.2F%%", diff);
@@ -297,14 +276,17 @@
 
 static int hpp__entry_ratio(struct perf_hpp *hpp, struct hist_entry *he)
 {
+	struct hist_entry *pair = hist_entry__next_pair(he);
 	const char *fmt = symbol_conf.field_sep ? "%s" : "%14s";
 	char buf[32] = " ";
-	double ratio;
+	double ratio = 0.0;
 
-	if (he->diff.computed)
-		ratio = he->diff.period_ratio;
-	else
-		ratio = perf_diff__compute_ratio(he);
+	if (pair) {
+		if (he->diff.computed)
+			ratio = he->diff.period_ratio;
+		else
+			ratio = perf_diff__compute_ratio(he, pair);
+	}
 
 	if (ratio > 0.0)
 		scnprintf(buf, sizeof(buf), "%+14.6F", ratio);
@@ -326,14 +308,17 @@
 
 static int hpp__entry_wdiff(struct perf_hpp *hpp, struct hist_entry *he)
 {
+	struct hist_entry *pair = hist_entry__next_pair(he);
 	const char *fmt = symbol_conf.field_sep ? "%s" : "%14s";
 	char buf[32] = " ";
-	s64 wdiff;
+	s64 wdiff = 0;
 
-	if (he->diff.computed)
-		wdiff = he->diff.wdiff;
-	else
-		wdiff = perf_diff__compute_wdiff(he);
+	if (pair) {
+		if (he->diff.computed)
+			wdiff = he->diff.wdiff;
+		else
+			wdiff = perf_diff__compute_wdiff(he, pair);
+	}
 
 	if (wdiff != 0)
 		scnprintf(buf, sizeof(buf), "%14ld", wdiff);
@@ -341,30 +326,6 @@
 	return scnprintf(hpp->buf, hpp->size, fmt, buf);
 }
 
-static int hpp__header_displ(struct perf_hpp *hpp)
-{
-	return scnprintf(hpp->buf, hpp->size, "Displ.");
-}
-
-static int hpp__width_displ(struct perf_hpp *hpp __maybe_unused)
-{
-	return 6;
-}
-
-static int hpp__entry_displ(struct perf_hpp *hpp,
-			    struct hist_entry *he)
-{
-	struct hist_entry *pair = hist_entry__next_pair(he);
-	long displacement = pair ? pair->position - he->position : 0;
-	const char *fmt = symbol_conf.field_sep ? "%s" : "%6.6s";
-	char buf[32] = " ";
-
-	if (displacement)
-		scnprintf(buf, sizeof(buf), "%+4ld", displacement);
-
-	return scnprintf(hpp->buf, hpp->size, fmt, buf);
-}
-
 static int hpp__header_formula(struct perf_hpp *hpp)
 {
 	const char *fmt = symbol_conf.field_sep ? "%s" : "%70s";
@@ -379,67 +340,91 @@
 
 static int hpp__entry_formula(struct perf_hpp *hpp, struct hist_entry *he)
 {
+	struct hist_entry *pair = hist_entry__next_pair(he);
 	const char *fmt = symbol_conf.field_sep ? "%s" : "%-70s";
 	char buf[96] = " ";
 
-	perf_diff__formula(buf, sizeof(buf), he);
+	if (pair)
+		perf_diff__formula(he, pair, buf, sizeof(buf));
+
 	return scnprintf(hpp->buf, hpp->size, fmt, buf);
 }
 
-#define HPP__COLOR_PRINT_FNS(_name)		\
-	.header	= hpp__header_ ## _name,		\
-	.width	= hpp__width_ ## _name,		\
-	.color	= hpp__color_ ## _name,		\
-	.entry	= hpp__entry_ ## _name
+#define HPP__COLOR_PRINT_FNS(_name)			\
+	{						\
+		.header	= hpp__header_ ## _name,	\
+		.width	= hpp__width_ ## _name,		\
+		.color	= hpp__color_ ## _name,		\
+		.entry	= hpp__entry_ ## _name		\
+	}
 
-#define HPP__PRINT_FNS(_name)			\
-	.header	= hpp__header_ ## _name,		\
-	.width	= hpp__width_ ## _name,		\
-	.entry	= hpp__entry_ ## _name
+#define HPP__PRINT_FNS(_name)				\
+	{						\
+		.header	= hpp__header_ ## _name,	\
+		.width	= hpp__width_ ## _name,		\
+		.entry	= hpp__entry_ ## _name		\
+	}
 
 struct perf_hpp_fmt perf_hpp__format[] = {
-	{ .cond = false, HPP__COLOR_PRINT_FNS(baseline) },
-	{ .cond = true,  HPP__COLOR_PRINT_FNS(overhead) },
-	{ .cond = false, HPP__COLOR_PRINT_FNS(overhead_sys) },
-	{ .cond = false, HPP__COLOR_PRINT_FNS(overhead_us) },
-	{ .cond = false, HPP__COLOR_PRINT_FNS(overhead_guest_sys) },
-	{ .cond = false, HPP__COLOR_PRINT_FNS(overhead_guest_us) },
-	{ .cond = false, HPP__PRINT_FNS(samples) },
-	{ .cond = false, HPP__PRINT_FNS(period) },
-	{ .cond = false, HPP__PRINT_FNS(period_baseline) },
-	{ .cond = false, HPP__PRINT_FNS(delta) },
-	{ .cond = false, HPP__PRINT_FNS(ratio) },
-	{ .cond = false, HPP__PRINT_FNS(wdiff) },
-	{ .cond = false, HPP__PRINT_FNS(displ) },
-	{ .cond = false, HPP__PRINT_FNS(formula) }
+	HPP__COLOR_PRINT_FNS(baseline),
+	HPP__COLOR_PRINT_FNS(overhead),
+	HPP__COLOR_PRINT_FNS(overhead_sys),
+	HPP__COLOR_PRINT_FNS(overhead_us),
+	HPP__COLOR_PRINT_FNS(overhead_guest_sys),
+	HPP__COLOR_PRINT_FNS(overhead_guest_us),
+	HPP__PRINT_FNS(samples),
+	HPP__PRINT_FNS(period),
+	HPP__PRINT_FNS(period_baseline),
+	HPP__PRINT_FNS(delta),
+	HPP__PRINT_FNS(ratio),
+	HPP__PRINT_FNS(wdiff),
+	HPP__PRINT_FNS(formula)
 };
 
+LIST_HEAD(perf_hpp__list);
+
+
 #undef HPP__COLOR_PRINT_FNS
 #undef HPP__PRINT_FNS
 
+#undef HPP_PERCENT_FNS
+#undef HPP_RAW_FNS
+
+#undef __HPP_HEADER_FN
+#undef __HPP_WIDTH_FN
+#undef __HPP_COLOR_PERCENT_FN
+#undef __HPP_ENTRY_PERCENT_FN
+#undef __HPP_ENTRY_RAW_FN
+
+
 void perf_hpp__init(void)
 {
 	if (symbol_conf.show_cpu_utilization) {
-		perf_hpp__format[PERF_HPP__OVERHEAD_SYS].cond = true;
-		perf_hpp__format[PERF_HPP__OVERHEAD_US].cond = true;
+		perf_hpp__column_enable(PERF_HPP__OVERHEAD_SYS);
+		perf_hpp__column_enable(PERF_HPP__OVERHEAD_US);
 
 		if (perf_guest) {
-			perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_SYS].cond = true;
-			perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_US].cond = true;
+			perf_hpp__column_enable(PERF_HPP__OVERHEAD_GUEST_SYS);
+			perf_hpp__column_enable(PERF_HPP__OVERHEAD_GUEST_US);
 		}
 	}
 
 	if (symbol_conf.show_nr_samples)
-		perf_hpp__format[PERF_HPP__SAMPLES].cond = true;
+		perf_hpp__column_enable(PERF_HPP__SAMPLES);
 
 	if (symbol_conf.show_total_period)
-		perf_hpp__format[PERF_HPP__PERIOD].cond = true;
+		perf_hpp__column_enable(PERF_HPP__PERIOD);
 }
 
-void perf_hpp__column_enable(unsigned col, bool enable)
+void perf_hpp__column_register(struct perf_hpp_fmt *format)
+{
+	list_add_tail(&format->list, &perf_hpp__list);
+}
+
+void perf_hpp__column_enable(unsigned col)
 {
 	BUG_ON(col >= PERF_HPP__MAX_INDEX);
-	perf_hpp__format[col].cond = enable;
+	perf_hpp__column_register(&perf_hpp__format[col]);
 }
 
 static inline void advance_hpp(struct perf_hpp *hpp, int inc)
@@ -452,27 +437,29 @@
 				bool color)
 {
 	const char *sep = symbol_conf.field_sep;
+	struct perf_hpp_fmt *fmt;
 	char *start = hpp->buf;
-	int i, ret;
+	int ret;
 	bool first = true;
 
 	if (symbol_conf.exclude_other && !he->parent)
 		return 0;
 
-	for (i = 0; i < PERF_HPP__MAX_INDEX; i++) {
-		if (!perf_hpp__format[i].cond)
-			continue;
-
+	perf_hpp__for_each_format(fmt) {
+		/*
+		 * If there's no field_sep, we still need
+		 * to display initial '  '.
+		 */
 		if (!sep || !first) {
 			ret = scnprintf(hpp->buf, hpp->size, "%s", sep ?: "  ");
 			advance_hpp(hpp, ret);
+		} else
 			first = false;
-		}
 
-		if (color && perf_hpp__format[i].color)
-			ret = perf_hpp__format[i].color(hpp, he);
+		if (color && fmt->color)
+			ret = fmt->color(hpp, he);
 		else
-			ret = perf_hpp__format[i].entry(hpp, he);
+			ret = fmt->entry(hpp, he);
 
 		advance_hpp(hpp, ret);
 	}
@@ -504,16 +491,18 @@
  */
 unsigned int hists__sort_list_width(struct hists *hists)
 {
+	struct perf_hpp_fmt *fmt;
 	struct sort_entry *se;
-	int i, ret = 0;
+	int i = 0, ret = 0;
+	struct perf_hpp dummy_hpp = {
+		.ptr	= hists_to_evsel(hists),
+	};
 
-	for (i = 0; i < PERF_HPP__MAX_INDEX; i++) {
-		if (!perf_hpp__format[i].cond)
-			continue;
+	perf_hpp__for_each_format(fmt) {
 		if (i)
 			ret += 2;
 
-		ret += perf_hpp__format[i].width(NULL);
+		ret += fmt->width(&dummy_hpp);
 	}
 
 	list_for_each_entry(se, &hist_entry__sort_list, list)
diff --git a/tools/perf/ui/keysyms.h b/tools/perf/ui/keysyms.h
index 809eca5..65092d5 100644
--- a/tools/perf/ui/keysyms.h
+++ b/tools/perf/ui/keysyms.h
@@ -23,5 +23,6 @@
 #define K_TIMER	 -1
 #define K_ERROR	 -2
 #define K_RESIZE -3
+#define K_SWITCH_INPUT_DATA -4
 
 #endif /* _PERF_KEYSYMS_H_ */
diff --git a/tools/perf/ui/setup.c b/tools/perf/ui/setup.c
index ebb4cc1..ae6a789 100644
--- a/tools/perf/ui/setup.c
+++ b/tools/perf/ui/setup.c
@@ -8,7 +8,7 @@
 
 void setup_browser(bool fallback_to_pager)
 {
-	if (!isatty(1) || dump_trace)
+	if (use_browser < 2 && (!isatty(1) || dump_trace))
 		use_browser = 0;
 
 	/* default to TUI */
@@ -30,6 +30,7 @@
 		if (fallback_to_pager)
 			setup_pager();
 
+		perf_hpp__column_enable(PERF_HPP__OVERHEAD);
 		perf_hpp__init();
 		break;
 	}
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index f0ee204..ff1f60c 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -3,6 +3,7 @@
 #include "../../util/util.h"
 #include "../../util/hist.h"
 #include "../../util/sort.h"
+#include "../../util/evsel.h"
 
 
 static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin)
@@ -335,17 +336,19 @@
 size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		      int max_cols, FILE *fp)
 {
+	struct perf_hpp_fmt *fmt;
 	struct sort_entry *se;
 	struct rb_node *nd;
 	size_t ret = 0;
 	unsigned int width;
 	const char *sep = symbol_conf.field_sep;
 	const char *col_width = symbol_conf.col_width_list_str;
-	int idx, nr_rows = 0;
+	int nr_rows = 0;
 	char bf[96];
 	struct perf_hpp dummy_hpp = {
 		.buf	= bf,
 		.size	= sizeof(bf),
+		.ptr	= hists_to_evsel(hists),
 	};
 	bool first = true;
 
@@ -355,16 +358,14 @@
 		goto print_entries;
 
 	fprintf(fp, "# ");
-	for (idx = 0; idx < PERF_HPP__MAX_INDEX; idx++) {
-		if (!perf_hpp__format[idx].cond)
-			continue;
 
+	perf_hpp__for_each_format(fmt) {
 		if (!first)
 			fprintf(fp, "%s", sep ?: "  ");
 		else
 			first = false;
 
-		perf_hpp__format[idx].header(&dummy_hpp);
+		fmt->header(&dummy_hpp);
 		fprintf(fp, "%s", bf);
 	}
 
@@ -400,18 +401,16 @@
 	first = true;
 
 	fprintf(fp, "# ");
-	for (idx = 0; idx < PERF_HPP__MAX_INDEX; idx++) {
-		unsigned int i;
 
-		if (!perf_hpp__format[idx].cond)
-			continue;
+	perf_hpp__for_each_format(fmt) {
+		unsigned int i;
 
 		if (!first)
 			fprintf(fp, "%s", sep ?: "  ");
 		else
 			first = false;
 
-		width = perf_hpp__format[idx].width(&dummy_hpp);
+		width = fmt->width(&dummy_hpp);
 		for (i = 0; i < width; i++)
 			fprintf(fp, ".");
 	}
@@ -462,7 +461,7 @@
 	return ret;
 }
 
-size_t hists__fprintf_nr_events(struct hists *hists, FILE *fp)
+size_t events_stats__fprintf(struct events_stats *stats, FILE *fp)
 {
 	int i;
 	size_t ret = 0;
@@ -470,7 +469,7 @@
 	for (i = 0; i < PERF_RECORD_HEADER_MAX; ++i) {
 		const char *name;
 
-		if (hists->stats.nr_events[i] == 0)
+		if (stats->nr_events[i] == 0)
 			continue;
 
 		name = perf_event__name(i);
@@ -478,7 +477,7 @@
 			continue;
 
 		ret += fprintf(fp, "%16s events: %10d\n", name,
-			       hists->stats.nr_events[i]);
+			       stats->nr_events[i]);
 	}
 
 	return ret;
diff --git a/tools/perf/ui/tui/helpline.c b/tools/perf/ui/tui/helpline.c
index 2884d2f..1c8b9af 100644
--- a/tools/perf/ui/tui/helpline.c
+++ b/tools/perf/ui/tui/helpline.c
@@ -8,6 +8,8 @@
 #include "../ui.h"
 #include "../libslang.h"
 
+char ui_helpline__last_msg[1024];
+
 static void tui_helpline__pop(void)
 {
 }
@@ -23,20 +25,7 @@
 	strncpy(ui_helpline__current, msg, sz)[sz - 1] = '\0';
 }
 
-struct ui_helpline tui_helpline_fns = {
-	.pop	= tui_helpline__pop,
-	.push	= tui_helpline__push,
-};
-
-void ui_helpline__init(void)
-{
-	helpline_fns = &tui_helpline_fns;
-	ui_helpline__puts(" ");
-}
-
-char ui_helpline__last_msg[1024];
-
-int ui_helpline__show_help(const char *format, va_list ap)
+static int tui_helpline__show(const char *format, va_list ap)
 {
 	int ret;
 	static int backlog;
@@ -55,3 +44,15 @@
 
 	return ret;
 }
+
+struct ui_helpline tui_helpline_fns = {
+	.pop	= tui_helpline__pop,
+	.push	= tui_helpline__push,
+	.show	= tui_helpline__show,
+};
+
+void ui_helpline__init(void)
+{
+	helpline_fns = &tui_helpline_fns;
+	ui_helpline__puts(" ");
+}
diff --git a/tools/perf/ui/util.c b/tools/perf/ui/util.c
index 4f98977..e3e0a96 100644
--- a/tools/perf/ui/util.c
+++ b/tools/perf/ui/util.c
@@ -52,7 +52,6 @@
 	return ret;
 }
 
-
 /**
  * perf_error__register - Register error logging functions
  * @eops: The pointer to error logging function struct
diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN
index 6aa34e5..055fef3 100755
--- a/tools/perf/util/PERF-VERSION-GEN
+++ b/tools/perf/util/PERF-VERSION-GEN
@@ -26,13 +26,13 @@
 
 if test -r $GVF
 then
-	VC=$(sed -e 's/^PERF_VERSION = //' <$GVF)
+	VC=$(sed -e 's/^#define PERF_VERSION "\(.*\)"/\1/' <$GVF)
 else
 	VC=unset
 fi
 test "$VN" = "$VC" || {
 	echo >&2 "PERF_VERSION = $VN"
-	echo "PERF_VERSION = $VN" >$GVF
+	echo "#define PERF_VERSION \"$VN\"" >$GVF
 }
 
 
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 07aaeea..d33fe93 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -809,7 +809,7 @@
 		pr_err("Can't annotate %s:\n\n"
 		       "No vmlinux file%s\nwas found in the path.\n\n"
 		       "Please use:\n\n"
-		       "  perf buildid-cache -av vmlinux\n\n"
+		       "  perf buildid-cache -vu vmlinux\n\n"
 		       "or:\n\n"
 		       "  --vmlinux vmlinux\n",
 		       sym->name, build_id_msg ?: "");
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 8eec943..c422440 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -6,6 +6,7 @@
 #include "types.h"
 #include "symbol.h"
 #include "hist.h"
+#include "sort.h"
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include <pthread.h>
@@ -154,6 +155,29 @@
 }
 #endif
 
+#ifdef GTK2_SUPPORT
+int symbol__gtk_annotate(struct symbol *sym, struct map *map, int evidx,
+			 struct hist_browser_timer *hbt);
+
+static inline int hist_entry__gtk_annotate(struct hist_entry *he, int evidx,
+					   struct hist_browser_timer *hbt)
+{
+	return symbol__gtk_annotate(he->ms.sym, he->ms.map, evidx, hbt);
+}
+
+void perf_gtk__show_annotations(void);
+#else
+static inline int hist_entry__gtk_annotate(struct hist_entry *he __maybe_unused,
+					   int evidx __maybe_unused,
+					   struct hist_browser_timer *hbt
+					   __maybe_unused)
+{
+	return 0;
+}
+
+static inline void perf_gtk__show_annotations(void) {}
+#endif
+
 extern const char	*disassembler_style;
 
 #endif	/* __PERF_ANNOTATE_H */
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index d3b3f5d..42b6a63 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -444,7 +444,7 @@
 	struct callchain_cursor_node *node = *cursor->last;
 
 	if (!node) {
-		node = calloc(sizeof(*node), 1);
+		node = calloc(1, sizeof(*node));
 		if (!node)
 			return -ENOMEM;
 
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index eb34057..3ee9f67 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -143,4 +143,9 @@
 	cursor->curr = cursor->curr->next;
 	cursor->pos++;
 }
+
+struct option;
+
+int record_parse_callchain_opt(const struct option *opt, const char *arg, int unset);
+extern const char record_callchain_help[];
 #endif	/* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 2b32ffa..f817046 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -1,4 +1,5 @@
 #include "util.h"
+#include "sysfs.h"
 #include "../perf.h"
 #include "cpumap.h"
 #include <assert.h>
@@ -201,3 +202,56 @@
 {
 	free(map);
 }
+
+int cpu_map__get_socket(struct cpu_map *map, int idx)
+{
+	FILE *fp;
+	const char *mnt;
+	char path[PATH_MAX];
+	int cpu, ret;
+
+	if (idx > map->nr)
+		return -1;
+
+	cpu = map->map[idx];
+
+	mnt = sysfs_find_mountpoint();
+	if (!mnt)
+		return -1;
+
+	sprintf(path,
+		"%s/devices/system/cpu/cpu%d/topology/physical_package_id",
+		mnt, cpu);
+
+	fp = fopen(path, "r");
+	if (!fp)
+		return -1;
+	ret = fscanf(fp, "%d", &cpu);
+	fclose(fp);
+	return ret == 1 ? cpu : -1;
+}
+
+int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp)
+{
+	struct cpu_map *sock;
+	int nr = cpus->nr;
+	int cpu, s1, s2;
+
+	sock = calloc(1, sizeof(*sock) + nr * sizeof(int));
+	if (!sock)
+		return -1;
+
+	for (cpu = 0; cpu < nr; cpu++) {
+		s1 = cpu_map__get_socket(cpus, cpu);
+		for (s2 = 0; s2 < sock->nr; s2++) {
+			if (s1 == sock->map[s2])
+				break;
+		}
+		if (s2 == sock->nr) {
+			sock->map[sock->nr] = s1;
+			sock->nr++;
+		}
+	}
+	*sockp = sock;
+	return 0;
+}
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 2f68a3b..161b007 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -14,6 +14,15 @@
 void cpu_map__delete(struct cpu_map *map);
 struct cpu_map *cpu_map__read(FILE *file);
 size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp);
+int cpu_map__get_socket(struct cpu_map *map, int idx);
+int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp);
+
+static inline int cpu_map__socket(struct cpu_map *sock, int s)
+{
+	if (!sock || s > sock->nr || s < 0)
+		return 0;
+	return sock->map[s];
+}
 
 static inline int cpu_map__nr(const struct cpu_map *map)
 {
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 03f830b..399e74c 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -23,10 +23,8 @@
 
 	if (verbose >= level) {
 		va_start(args, fmt);
-		if (use_browser == 1)
-			ret = ui_helpline__show_help(fmt, args);
-		else if (use_browser == 2)
-			ret = perf_gtk__show_helpline(fmt, args);
+		if (use_browser >= 1)
+			ui_helpline__vshow(fmt, args);
 		else
 			ret = vfprintf(stderr, fmt, args);
 		va_end(args);
@@ -49,28 +47,6 @@
 	return ret;
 }
 
-#if !defined(NEWT_SUPPORT) && !defined(GTK2_SUPPORT)
-int ui__warning(const char *format, ...)
-{
-	va_list args;
-
-	va_start(args, format);
-	vfprintf(stderr, format, args);
-	va_end(args);
-	return 0;
-}
-#endif
-
-int ui__error_paranoid(void)
-{
-	return ui__error("Permission error - are you root?\n"
-		    "Consider tweaking /proc/sys/kernel/perf_event_paranoid:\n"
-		    " -1 - Not paranoid at all\n"
-		    "  0 - Disallow raw tracepoint access for unpriv\n"
-		    "  1 - Disallow cpu events for unpriv\n"
-		    "  2 - Disallow kernel profiling for unpriv\n");
-}
-
 void trace_event(union perf_event *event)
 {
 	unsigned char *raw_event = (void *)event;
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 83e8d23..efbd988 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -5,6 +5,8 @@
 #include <stdbool.h>
 #include "event.h"
 #include "../ui/helpline.h"
+#include "../ui/progress.h"
+#include "../ui/util.h"
 
 extern int verbose;
 extern bool quiet, dump_trace;
@@ -12,39 +14,7 @@
 int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2)));
 void trace_event(union perf_event *event);
 
-struct ui_progress;
-struct perf_error_ops;
-
-#if defined(NEWT_SUPPORT) || defined(GTK2_SUPPORT)
-
-#include "../ui/progress.h"
 int ui__error(const char *format, ...) __attribute__((format(printf, 1, 2)));
-#include "../ui/util.h"
-
-#else
-
-static inline void ui_progress__update(u64 curr __maybe_unused,
-				       u64 total __maybe_unused,
-				       const char *title __maybe_unused) {}
-static inline void ui_progress__finish(void) {}
-
-#define ui__error(format, arg...) ui__warning(format, ##arg)
-
-static inline int
-perf_error__register(struct perf_error_ops *eops __maybe_unused)
-{
-	return 0;
-}
-
-static inline int
-perf_error__unregister(struct perf_error_ops *eops __maybe_unused)
-{
-	return 0;
-}
-
-#endif /* NEWT_SUPPORT || GTK2_SUPPORT */
-
 int ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2)));
-int ui__error_paranoid(void);
 
 #endif	/* __PERF_DEBUG_H */
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index d6d9a46..6f7d5a9 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -539,13 +539,13 @@
 }
 
 size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
-			       bool with_hits)
+			       bool (skip)(struct dso *dso, int parm), int parm)
 {
 	struct dso *pos;
 	size_t ret = 0;
 
 	list_for_each_entry(pos, head, node) {
-		if (with_hits && !pos->hit)
+		if (skip && skip(pos, parm))
 			continue;
 		ret += dso__fprintf_buildid(pos, fp);
 		ret += fprintf(fp, " %s\n", pos->long_name);
@@ -583,7 +583,7 @@
 	if (dso->short_name != dso->long_name)
 		ret += fprintf(fp, "%s, ", dso->long_name);
 	ret += fprintf(fp, "%s, %sloaded, ", map_type__name[type],
-		       dso->loaded ? "" : "NOT ");
+		       dso__loaded(dso, type) ? "" : "NOT ");
 	ret += dso__fprintf_buildid(dso, fp);
 	ret += fprintf(fp, ")\n");
 	for (nd = rb_first(&dso->symbols[type]); nd; nd = rb_next(nd)) {
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index e032769..450199a 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -138,7 +138,7 @@
 bool __dsos__read_build_ids(struct list_head *head, bool with_hits);
 
 size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
-			       bool with_hits);
+			       bool (skip)(struct dso *dso, int parm), int parm);
 size_t __dsos__fprintf(struct list_head *head, FILE *fp);
 
 size_t dso__fprintf_buildid(struct dso *dso, FILE *fp);
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 3cf2c3e..5cd13d7 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -476,8 +476,10 @@
 		}
 	}
 
-	if (kallsyms__parse(filename, &args, find_symbol_cb) <= 0)
+	if (kallsyms__parse(filename, &args, find_symbol_cb) <= 0) {
+		free(event);
 		return -ENOENT;
+	}
 
 	map = machine->vmlinux_maps[MAP__FUNCTION];
 	size = snprintf(event->mmap.filename, sizeof(event->mmap.filename),
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 7052934..bc4ad79 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -49,10 +49,16 @@
 	return evlist;
 }
 
-void perf_evlist__config_attrs(struct perf_evlist *evlist,
-			       struct perf_record_opts *opts)
+void perf_evlist__config(struct perf_evlist *evlist,
+			struct perf_record_opts *opts)
 {
 	struct perf_evsel *evsel;
+	/*
+	 * Set the evsel leader links before we configure attributes,
+	 * since some might depend on this info.
+	 */
+	if (opts->group)
+		perf_evlist__set_leader(evlist);
 
 	if (evlist->cpus->map[0] < 0)
 		opts->no_inherit = true;
@@ -61,7 +67,7 @@
 		perf_evsel__config(evsel, opts);
 
 		if (evlist->nr_entries > 1)
-			evsel->attr.sample_type |= PERF_SAMPLE_ID;
+			perf_evsel__set_sample_id(evsel);
 	}
 }
 
@@ -111,18 +117,21 @@
 	struct perf_evsel *evsel, *leader;
 
 	leader = list_entry(list->next, struct perf_evsel, node);
-	leader->leader = NULL;
+	evsel = list_entry(list->prev, struct perf_evsel, node);
+
+	leader->nr_members = evsel->idx - leader->idx + 1;
 
 	list_for_each_entry(evsel, list, node) {
-		if (evsel != leader)
-			evsel->leader = leader;
+		evsel->leader = leader;
 	}
 }
 
 void perf_evlist__set_leader(struct perf_evlist *evlist)
 {
-	if (evlist->nr_entries)
+	if (evlist->nr_entries) {
+		evlist->nr_groups = evlist->nr_entries > 1 ? 1 : 0;
 		__perf_evlist__set_leader(&evlist->entries);
+	}
 }
 
 int perf_evlist__add_default(struct perf_evlist *evlist)
@@ -222,7 +231,7 @@
 
 	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
 		list_for_each_entry(pos, &evlist->entries, node) {
-			if (perf_evsel__is_group_member(pos))
+			if (!perf_evsel__is_group_leader(pos))
 				continue;
 			for (thread = 0; thread < evlist->threads->nr; thread++)
 				ioctl(FD(pos, cpu, thread),
@@ -238,7 +247,7 @@
 
 	for (cpu = 0; cpu < cpu_map__nr(evlist->cpus); cpu++) {
 		list_for_each_entry(pos, &evlist->entries, node) {
-			if (perf_evsel__is_group_member(pos))
+			if (!perf_evsel__is_group_leader(pos))
 				continue;
 			for (thread = 0; thread < evlist->threads->nr; thread++)
 				ioctl(FD(pos, cpu, thread),
@@ -366,7 +375,7 @@
 		if ((old & md->mask) + size != ((old + size) & md->mask)) {
 			unsigned int offset = old;
 			unsigned int len = min(sizeof(*event), size), cpy;
-			void *dst = &evlist->event_copy;
+			void *dst = &md->event_copy;
 
 			do {
 				cpy = min(md->mask + 1 - (offset & md->mask), len);
@@ -376,7 +385,7 @@
 				len -= cpy;
 			} while (len);
 
-			event = &evlist->event_copy;
+			event = &md->event_copy;
 		}
 
 		old += size;
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 56003f7..2dd07bd 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -17,10 +17,18 @@
 #define PERF_EVLIST__HLIST_BITS 8
 #define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS)
 
+struct perf_mmap {
+	void		 *base;
+	int		 mask;
+	unsigned int	 prev;
+	union perf_event event_copy;
+};
+
 struct perf_evlist {
 	struct list_head entries;
 	struct hlist_head heads[PERF_EVLIST__HLIST_SIZE];
 	int		 nr_entries;
+	int		 nr_groups;
 	int		 nr_fds;
 	int		 nr_mmaps;
 	int		 mmap_len;
@@ -29,7 +37,6 @@
 		pid_t	pid;
 	} workload;
 	bool		 overwrite;
-	union perf_event event_copy;
 	struct perf_mmap *mmap;
 	struct pollfd	 *pollfd;
 	struct thread_map *threads;
@@ -76,8 +83,8 @@
 
 int perf_evlist__open(struct perf_evlist *evlist);
 
-void perf_evlist__config_attrs(struct perf_evlist *evlist,
-			       struct perf_record_opts *opts);
+void perf_evlist__config(struct perf_evlist *evlist,
+			 struct perf_record_opts *opts);
 
 int perf_evlist__prepare_workload(struct perf_evlist *evlist,
 				  struct perf_record_opts *opts,
@@ -135,4 +142,25 @@
 }
 
 size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp);
+
+static inline unsigned int perf_mmap__read_head(struct perf_mmap *mm)
+{
+	struct perf_event_mmap_page *pc = mm->base;
+	int head = pc->data_head;
+	rmb();
+	return head;
+}
+
+static inline void perf_mmap__write_tail(struct perf_mmap *md,
+					 unsigned long tail)
+{
+	struct perf_event_mmap_page *pc = md->base;
+
+	/*
+	 * ensure all reads are done before we write the tail out.
+	 */
+	/* mb(); */
+	pc->data_tail = tail;
+}
+
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 1b16dd1..9c82f98f 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -22,6 +22,11 @@
 #include <linux/perf_event.h>
 #include "perf_regs.h"
 
+static struct {
+	bool sample_id_all;
+	bool exclude_guest;
+} perf_missing_features;
+
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 
 static int __perf_evsel__sample_size(u64 sample_type)
@@ -50,11 +55,36 @@
 	pthread_mutex_init(&hists->lock, NULL);
 }
 
+void __perf_evsel__set_sample_bit(struct perf_evsel *evsel,
+				  enum perf_event_sample_format bit)
+{
+	if (!(evsel->attr.sample_type & bit)) {
+		evsel->attr.sample_type |= bit;
+		evsel->sample_size += sizeof(u64);
+	}
+}
+
+void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel,
+				    enum perf_event_sample_format bit)
+{
+	if (evsel->attr.sample_type & bit) {
+		evsel->attr.sample_type &= ~bit;
+		evsel->sample_size -= sizeof(u64);
+	}
+}
+
+void perf_evsel__set_sample_id(struct perf_evsel *evsel)
+{
+	perf_evsel__set_sample_bit(evsel, ID);
+	evsel->attr.read_format |= PERF_FORMAT_ID;
+}
+
 void perf_evsel__init(struct perf_evsel *evsel,
 		      struct perf_event_attr *attr, int idx)
 {
 	evsel->idx	   = idx;
 	evsel->attr	   = *attr;
+	evsel->leader	   = evsel;
 	INIT_LIST_HEAD(&evsel->node);
 	hists__init(&evsel->hists);
 	evsel->sample_size = __perf_evsel__sample_size(attr->sample_type);
@@ -404,6 +434,31 @@
 	return evsel->name ?: "unknown";
 }
 
+const char *perf_evsel__group_name(struct perf_evsel *evsel)
+{
+	return evsel->group_name ?: "anon group";
+}
+
+int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size)
+{
+	int ret;
+	struct perf_evsel *pos;
+	const char *group_name = perf_evsel__group_name(evsel);
+
+	ret = scnprintf(buf, size, "%s", group_name);
+
+	ret += scnprintf(buf + ret, size - ret, " { %s",
+			 perf_evsel__name(evsel));
+
+	for_each_group_member(pos, evsel)
+		ret += scnprintf(buf + ret, size - ret, ", %s",
+				 perf_evsel__name(pos));
+
+	ret += scnprintf(buf + ret, size - ret, " }");
+
+	return ret;
+}
+
 /*
  * The enable_on_exec/disabled value strategy:
  *
@@ -438,13 +493,11 @@
 	struct perf_event_attr *attr = &evsel->attr;
 	int track = !evsel->idx; /* only the first counter needs these */
 
-	attr->sample_id_all = opts->sample_id_all_missing ? 0 : 1;
+	attr->sample_id_all = perf_missing_features.sample_id_all ? 0 : 1;
 	attr->inherit	    = !opts->no_inherit;
-	attr->read_format   = PERF_FORMAT_TOTAL_TIME_ENABLED |
-			      PERF_FORMAT_TOTAL_TIME_RUNNING |
-			      PERF_FORMAT_ID;
 
-	attr->sample_type  |= PERF_SAMPLE_IP | PERF_SAMPLE_TID;
+	perf_evsel__set_sample_bit(evsel, IP);
+	perf_evsel__set_sample_bit(evsel, TID);
 
 	/*
 	 * We default some events to a 1 default interval. But keep
@@ -453,7 +506,7 @@
 	if (!attr->sample_period || (opts->user_freq != UINT_MAX &&
 				     opts->user_interval != ULLONG_MAX)) {
 		if (opts->freq) {
-			attr->sample_type	|= PERF_SAMPLE_PERIOD;
+			perf_evsel__set_sample_bit(evsel, PERIOD);
 			attr->freq		= 1;
 			attr->sample_freq	= opts->freq;
 		} else {
@@ -468,16 +521,16 @@
 		attr->inherit_stat = 1;
 
 	if (opts->sample_address) {
-		attr->sample_type	|= PERF_SAMPLE_ADDR;
+		perf_evsel__set_sample_bit(evsel, ADDR);
 		attr->mmap_data = track;
 	}
 
 	if (opts->call_graph) {
-		attr->sample_type	|= PERF_SAMPLE_CALLCHAIN;
+		perf_evsel__set_sample_bit(evsel, CALLCHAIN);
 
 		if (opts->call_graph == CALLCHAIN_DWARF) {
-			attr->sample_type |= PERF_SAMPLE_REGS_USER |
-					     PERF_SAMPLE_STACK_USER;
+			perf_evsel__set_sample_bit(evsel, REGS_USER);
+			perf_evsel__set_sample_bit(evsel, STACK_USER);
 			attr->sample_regs_user = PERF_REGS_MASK;
 			attr->sample_stack_user = opts->stack_dump_size;
 			attr->exclude_callchain_user = 1;
@@ -485,20 +538,20 @@
 	}
 
 	if (perf_target__has_cpu(&opts->target))
-		attr->sample_type	|= PERF_SAMPLE_CPU;
+		perf_evsel__set_sample_bit(evsel, CPU);
 
 	if (opts->period)
-		attr->sample_type	|= PERF_SAMPLE_PERIOD;
+		perf_evsel__set_sample_bit(evsel, PERIOD);
 
-	if (!opts->sample_id_all_missing &&
+	if (!perf_missing_features.sample_id_all &&
 	    (opts->sample_time || !opts->no_inherit ||
 	     perf_target__has_cpu(&opts->target)))
-		attr->sample_type	|= PERF_SAMPLE_TIME;
+		perf_evsel__set_sample_bit(evsel, TIME);
 
 	if (opts->raw_samples) {
-		attr->sample_type	|= PERF_SAMPLE_TIME;
-		attr->sample_type	|= PERF_SAMPLE_RAW;
-		attr->sample_type	|= PERF_SAMPLE_CPU;
+		perf_evsel__set_sample_bit(evsel, TIME);
+		perf_evsel__set_sample_bit(evsel, RAW);
+		perf_evsel__set_sample_bit(evsel, CPU);
 	}
 
 	if (opts->no_delay) {
@@ -506,7 +559,7 @@
 		attr->wakeup_events = 1;
 	}
 	if (opts->branch_stack) {
-		attr->sample_type	|= PERF_SAMPLE_BRANCH_STACK;
+		perf_evsel__set_sample_bit(evsel, BRANCH_STACK);
 		attr->branch_sample_type = opts->branch_stack;
 	}
 
@@ -519,14 +572,14 @@
 	 * Disabling only independent events or group leaders,
 	 * keeping group members enabled.
 	 */
-	if (!perf_evsel__is_group_member(evsel))
+	if (perf_evsel__is_group_leader(evsel))
 		attr->disabled = 1;
 
 	/*
 	 * Setting enable_on_exec for independent events and
 	 * group leaders for traced executed by perf.
 	 */
-	if (perf_target__none(&opts->target) && !perf_evsel__is_group_member(evsel))
+	if (perf_target__none(&opts->target) && perf_evsel__is_group_leader(evsel))
 		attr->enable_on_exec = 1;
 }
 
@@ -612,6 +665,11 @@
 		}
 }
 
+void perf_evsel__free_counts(struct perf_evsel *evsel)
+{
+	free(evsel->counts);
+}
+
 void perf_evsel__exit(struct perf_evsel *evsel)
 {
 	assert(list_empty(&evsel->node));
@@ -631,6 +689,28 @@
 	free(evsel);
 }
 
+static inline void compute_deltas(struct perf_evsel *evsel,
+				  int cpu,
+				  struct perf_counts_values *count)
+{
+	struct perf_counts_values tmp;
+
+	if (!evsel->prev_raw_counts)
+		return;
+
+	if (cpu == -1) {
+		tmp = evsel->prev_raw_counts->aggr;
+		evsel->prev_raw_counts->aggr = *count;
+	} else {
+		tmp = evsel->prev_raw_counts->cpu[cpu];
+		evsel->prev_raw_counts->cpu[cpu] = *count;
+	}
+
+	count->val = count->val - tmp.val;
+	count->ena = count->ena - tmp.ena;
+	count->run = count->run - tmp.run;
+}
+
 int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
 			      int cpu, int thread, bool scale)
 {
@@ -646,6 +726,8 @@
 	if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) < 0)
 		return -errno;
 
+	compute_deltas(evsel, cpu, &count);
+
 	if (scale) {
 		if (count.run == 0)
 			count.val = 0;
@@ -684,6 +766,8 @@
 		}
 	}
 
+	compute_deltas(evsel, -1, aggr);
+
 	evsel->counts->scaled = 0;
 	if (scale) {
 		if (aggr->run == 0) {
@@ -707,7 +791,7 @@
 	struct perf_evsel *leader = evsel->leader;
 	int fd;
 
-	if (!perf_evsel__is_group_member(evsel))
+	if (perf_evsel__is_group_leader(evsel))
 		return -1;
 
 	/*
@@ -738,6 +822,13 @@
 		pid = evsel->cgrp->fd;
 	}
 
+fallback_missing_features:
+	if (perf_missing_features.exclude_guest)
+		evsel->attr.exclude_guest = evsel->attr.exclude_host = 0;
+retry_sample_id:
+	if (perf_missing_features.sample_id_all)
+		evsel->attr.sample_id_all = 0;
+
 	for (cpu = 0; cpu < cpus->nr; cpu++) {
 
 		for (thread = 0; thread < threads->nr; thread++) {
@@ -754,13 +845,26 @@
 								     group_fd, flags);
 			if (FD(evsel, cpu, thread) < 0) {
 				err = -errno;
-				goto out_close;
+				goto try_fallback;
 			}
 		}
 	}
 
 	return 0;
 
+try_fallback:
+	if (err != -EINVAL || cpu > 0 || thread > 0)
+		goto out_close;
+
+	if (!perf_missing_features.exclude_guest &&
+	    (evsel->attr.exclude_guest || evsel->attr.exclude_host)) {
+		perf_missing_features.exclude_guest = true;
+		goto fallback_missing_features;
+	} else if (!perf_missing_features.sample_id_all) {
+		perf_missing_features.sample_id_all = true;
+		goto retry_sample_id;
+	}
+
 out_close:
 	do {
 		while (--thread >= 0) {
@@ -1205,3 +1309,225 @@
 
 	return 0;
 }
+
+static int comma_fprintf(FILE *fp, bool *first, const char *fmt, ...)
+{
+	va_list args;
+	int ret = 0;
+
+	if (!*first) {
+		ret += fprintf(fp, ",");
+	} else {
+		ret += fprintf(fp, ":");
+		*first = false;
+	}
+
+	va_start(args, fmt);
+	ret += vfprintf(fp, fmt, args);
+	va_end(args);
+	return ret;
+}
+
+static int __if_fprintf(FILE *fp, bool *first, const char *field, u64 value)
+{
+	if (value == 0)
+		return 0;
+
+	return comma_fprintf(fp, first, " %s: %" PRIu64, field, value);
+}
+
+#define if_print(field) printed += __if_fprintf(fp, &first, #field, evsel->attr.field)
+
+struct bit_names {
+	int bit;
+	const char *name;
+};
+
+static int bits__fprintf(FILE *fp, const char *field, u64 value,
+			 struct bit_names *bits, bool *first)
+{
+	int i = 0, printed = comma_fprintf(fp, first, " %s: ", field);
+	bool first_bit = true;
+
+	do {
+		if (value & bits[i].bit) {
+			printed += fprintf(fp, "%s%s", first_bit ? "" : "|", bits[i].name);
+			first_bit = false;
+		}
+	} while (bits[++i].name != NULL);
+
+	return printed;
+}
+
+static int sample_type__fprintf(FILE *fp, bool *first, u64 value)
+{
+#define bit_name(n) { PERF_SAMPLE_##n, #n }
+	struct bit_names bits[] = {
+		bit_name(IP), bit_name(TID), bit_name(TIME), bit_name(ADDR),
+		bit_name(READ), bit_name(CALLCHAIN), bit_name(ID), bit_name(CPU),
+		bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW),
+		bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER),
+		{ .name = NULL, }
+	};
+#undef bit_name
+	return bits__fprintf(fp, "sample_type", value, bits, first);
+}
+
+static int read_format__fprintf(FILE *fp, bool *first, u64 value)
+{
+#define bit_name(n) { PERF_FORMAT_##n, #n }
+	struct bit_names bits[] = {
+		bit_name(TOTAL_TIME_ENABLED), bit_name(TOTAL_TIME_RUNNING),
+		bit_name(ID), bit_name(GROUP),
+		{ .name = NULL, }
+	};
+#undef bit_name
+	return bits__fprintf(fp, "read_format", value, bits, first);
+}
+
+int perf_evsel__fprintf(struct perf_evsel *evsel,
+			struct perf_attr_details *details, FILE *fp)
+{
+	bool first = true;
+	int printed = 0;
+
+	if (details->event_group) {
+		struct perf_evsel *pos;
+
+		if (!perf_evsel__is_group_leader(evsel))
+			return 0;
+
+		if (evsel->nr_members > 1)
+			printed += fprintf(fp, "%s{", evsel->group_name ?: "");
+
+		printed += fprintf(fp, "%s", perf_evsel__name(evsel));
+		for_each_group_member(pos, evsel)
+			printed += fprintf(fp, ",%s", perf_evsel__name(pos));
+
+		if (evsel->nr_members > 1)
+			printed += fprintf(fp, "}");
+		goto out;
+	}
+
+	printed += fprintf(fp, "%s", perf_evsel__name(evsel));
+
+	if (details->verbose || details->freq) {
+		printed += comma_fprintf(fp, &first, " sample_freq=%" PRIu64,
+					 (u64)evsel->attr.sample_freq);
+	}
+
+	if (details->verbose) {
+		if_print(type);
+		if_print(config);
+		if_print(config1);
+		if_print(config2);
+		if_print(size);
+		printed += sample_type__fprintf(fp, &first, evsel->attr.sample_type);
+		if (evsel->attr.read_format)
+			printed += read_format__fprintf(fp, &first, evsel->attr.read_format);
+		if_print(disabled);
+		if_print(inherit);
+		if_print(pinned);
+		if_print(exclusive);
+		if_print(exclude_user);
+		if_print(exclude_kernel);
+		if_print(exclude_hv);
+		if_print(exclude_idle);
+		if_print(mmap);
+		if_print(comm);
+		if_print(freq);
+		if_print(inherit_stat);
+		if_print(enable_on_exec);
+		if_print(task);
+		if_print(watermark);
+		if_print(precise_ip);
+		if_print(mmap_data);
+		if_print(sample_id_all);
+		if_print(exclude_host);
+		if_print(exclude_guest);
+		if_print(__reserved_1);
+		if_print(wakeup_events);
+		if_print(bp_type);
+		if_print(branch_sample_type);
+	}
+out:
+	fputc('\n', fp);
+	return ++printed;
+}
+
+bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
+			  char *msg, size_t msgsize)
+{
+	if ((err == ENOENT || err == ENXIO) &&
+	    evsel->attr.type   == PERF_TYPE_HARDWARE &&
+	    evsel->attr.config == PERF_COUNT_HW_CPU_CYCLES) {
+		/*
+		 * If it's cycles then fall back to hrtimer based
+		 * cpu-clock-tick sw counter, which is always available even if
+		 * no PMU support.
+		 *
+		 * PPC returns ENXIO until 2.6.37 (behavior changed with commit
+		 * b0a873e).
+		 */
+		scnprintf(msg, msgsize, "%s",
+"The cycles event is not supported, trying to fall back to cpu-clock-ticks");
+
+		evsel->attr.type   = PERF_TYPE_SOFTWARE;
+		evsel->attr.config = PERF_COUNT_SW_CPU_CLOCK;
+
+		free(evsel->name);
+		evsel->name = NULL;
+		return true;
+	}
+
+	return false;
+}
+
+int perf_evsel__open_strerror(struct perf_evsel *evsel,
+			      struct perf_target *target,
+			      int err, char *msg, size_t size)
+{
+	switch (err) {
+	case EPERM:
+	case EACCES:
+		return scnprintf(msg, size, "%s",
+		 "You may not have permission to collect %sstats.\n"
+		 "Consider tweaking /proc/sys/kernel/perf_event_paranoid:\n"
+		 " -1 - Not paranoid at all\n"
+		 "  0 - Disallow raw tracepoint access for unpriv\n"
+		 "  1 - Disallow cpu events for unpriv\n"
+		 "  2 - Disallow kernel profiling for unpriv",
+				 target->system_wide ? "system-wide " : "");
+	case ENOENT:
+		return scnprintf(msg, size, "The %s event is not supported.",
+				 perf_evsel__name(evsel));
+	case EMFILE:
+		return scnprintf(msg, size, "%s",
+			 "Too many events are opened.\n"
+			 "Try again after reducing the number of events.");
+	case ENODEV:
+		if (target->cpu_list)
+			return scnprintf(msg, size, "%s",
+	 "No such device - did you specify an out-of-range profile CPU?\n");
+		break;
+	case EOPNOTSUPP:
+		if (evsel->attr.precise_ip)
+			return scnprintf(msg, size, "%s",
+	"\'precise\' request may not be supported. Try removing 'p' modifier.");
+#if defined(__i386__) || defined(__x86_64__)
+		if (evsel->attr.type == PERF_TYPE_HARDWARE)
+			return scnprintf(msg, size, "%s",
+	"No hardware sampling interrupt available.\n"
+	"No APIC? If so then you can boot the kernel with the \"lapic\" boot parameter to force-enable it.");
+#endif
+		break;
+	default:
+		break;
+	}
+
+	return scnprintf(msg, size,
+	"The sys_perf_event_open() syscall returned with %d (%s) for event (%s).  \n"
+	"/bin/dmesg may provide additional information.\n"
+	"No CONFIG_PERF_EVENTS=y kernel support configured?\n",
+			 err, strerror(err), perf_evsel__name(evsel));
+}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 3d2b801..52021c3 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -53,6 +53,7 @@
 	struct xyarray		*sample_id;
 	u64			*id;
 	struct perf_counts	*counts;
+	struct perf_counts	*prev_raw_counts;
 	int			idx;
 	u32			ids;
 	struct hists		hists;
@@ -73,10 +74,13 @@
 	bool 			needs_swap;
 	/* parse modifier helper */
 	int			exclude_GH;
+	int			nr_members;
 	struct perf_evsel	*leader;
 	char			*group_name;
 };
 
+#define hists_to_evsel(h) container_of(h, struct perf_evsel, hists)
+
 struct cpu_map;
 struct thread_map;
 struct perf_evlist;
@@ -110,14 +114,30 @@
 int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result,
 					    char *bf, size_t size);
 const char *perf_evsel__name(struct perf_evsel *evsel);
+const char *perf_evsel__group_name(struct perf_evsel *evsel);
+int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size);
 
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
 int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus);
 void perf_evsel__free_fd(struct perf_evsel *evsel);
 void perf_evsel__free_id(struct perf_evsel *evsel);
+void perf_evsel__free_counts(struct perf_evsel *evsel);
 void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 
+void __perf_evsel__set_sample_bit(struct perf_evsel *evsel,
+				  enum perf_event_sample_format bit);
+void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel,
+				    enum perf_event_sample_format bit);
+
+#define perf_evsel__set_sample_bit(evsel, bit) \
+	__perf_evsel__set_sample_bit(evsel, PERF_SAMPLE_##bit)
+
+#define perf_evsel__reset_sample_bit(evsel, bit) \
+	__perf_evsel__reset_sample_bit(evsel, PERF_SAMPLE_##bit)
+
+void perf_evsel__set_sample_id(struct perf_evsel *evsel);
+
 int perf_evsel__set_filter(struct perf_evsel *evsel, int ncpus, int nthreads,
 			   const char *filter);
 
@@ -226,8 +246,34 @@
 	return list_entry(evsel->node.next, struct perf_evsel, node);
 }
 
-static inline bool perf_evsel__is_group_member(const struct perf_evsel *evsel)
+static inline bool perf_evsel__is_group_leader(const struct perf_evsel *evsel)
 {
-	return evsel->leader != NULL;
+	return evsel->leader == evsel;
 }
+
+struct perf_attr_details {
+	bool freq;
+	bool verbose;
+	bool event_group;
+};
+
+int perf_evsel__fprintf(struct perf_evsel *evsel,
+			struct perf_attr_details *details, FILE *fp);
+
+bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
+			  char *msg, size_t msgsize);
+int perf_evsel__open_strerror(struct perf_evsel *evsel,
+			      struct perf_target *target,
+			      int err, char *msg, size_t size);
+
+static inline int perf_evsel__group_idx(struct perf_evsel *evsel)
+{
+	return evsel->idx - evsel->leader->idx;
+}
+
+#define for_each_group_member(_evsel, _leader) 					\
+for ((_evsel) = list_entry((_leader)->node.next, struct perf_evsel, node); 	\
+     (_evsel) && (_evsel)->leader == (_leader);					\
+     (_evsel) = list_entry((_evsel)->node.next, struct perf_evsel, node))
+
 #endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index b7da463..f4bfd79 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -148,7 +148,7 @@
 	u32 len;
 	char *buf;
 
-	sz = read(fd, &len, sizeof(len));
+	sz = readn(fd, &len, sizeof(len));
 	if (sz < (ssize_t)sizeof(len))
 		return NULL;
 
@@ -159,7 +159,7 @@
 	if (!buf)
 		return NULL;
 
-	ret = read(fd, buf, len);
+	ret = readn(fd, buf, len);
 	if (ret == (ssize_t)len) {
 		/*
 		 * strings are padded by zeroes
@@ -287,12 +287,12 @@
 	struct perf_session *session = container_of(header,
 			struct perf_session, header);
 	struct rb_node *nd;
-	int err = machine__write_buildid_table(&session->host_machine, fd);
+	int err = machine__write_buildid_table(&session->machines.host, fd);
 
 	if (err)
 		return err;
 
-	for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
 		err = machine__write_buildid_table(pos, fd);
 		if (err)
@@ -313,7 +313,8 @@
 	if (is_kallsyms) {
 		if (symbol_conf.kptr_restrict) {
 			pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n");
-			return 0;
+			err = 0;
+			goto out_free;
 		}
 		realname = (char *) name;
 	} else
@@ -448,9 +449,9 @@
 	if (mkdir(debugdir, 0755) != 0 && errno != EEXIST)
 		return -1;
 
-	ret = machine__cache_build_ids(&session->host_machine, debugdir);
+	ret = machine__cache_build_ids(&session->machines.host, debugdir);
 
-	for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
 		ret |= machine__cache_build_ids(pos, debugdir);
 	}
@@ -467,9 +468,9 @@
 static bool perf_session__read_build_ids(struct perf_session *session, bool with_hits)
 {
 	struct rb_node *nd;
-	bool ret = machine__read_build_ids(&session->host_machine, with_hits);
+	bool ret = machine__read_build_ids(&session->machines.host, with_hits);
 
-	for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
 		ret |= machine__read_build_ids(pos, with_hits);
 	}
@@ -954,6 +955,7 @@
 	}
 
 	fclose(fp);
+	fp = NULL;
 
 	ret = do_write(fd, &mem_total, sizeof(u64));
 	if (ret)
@@ -980,7 +982,8 @@
 	ret = do_write_string(fd, buf);
 done:
 	free(buf);
-	fclose(fp);
+	if (fp)
+		fclose(fp);
 	return ret;
 }
 
@@ -1051,16 +1054,25 @@
 	struct perf_pmu *pmu = NULL;
 	off_t offset = lseek(fd, 0, SEEK_CUR);
 	__u32 pmu_num = 0;
+	int ret;
 
 	/* write real pmu_num later */
-	do_write(fd, &pmu_num, sizeof(pmu_num));
+	ret = do_write(fd, &pmu_num, sizeof(pmu_num));
+	if (ret < 0)
+		return ret;
 
 	while ((pmu = perf_pmu__scan(pmu))) {
 		if (!pmu->name)
 			continue;
 		pmu_num++;
-		do_write(fd, &pmu->type, sizeof(pmu->type));
-		do_write_string(fd, pmu->name);
+
+		ret = do_write(fd, &pmu->type, sizeof(pmu->type));
+		if (ret < 0)
+			return ret;
+
+		ret = do_write_string(fd, pmu->name);
+		if (ret < 0)
+			return ret;
 	}
 
 	if (pwrite(fd, &pmu_num, sizeof(pmu_num), offset) != sizeof(pmu_num)) {
@@ -1073,6 +1085,52 @@
 }
 
 /*
+ * File format:
+ *
+ * struct group_descs {
+ *	u32	nr_groups;
+ *	struct group_desc {
+ *		char	name[];
+ *		u32	leader_idx;
+ *		u32	nr_members;
+ *	}[nr_groups];
+ * };
+ */
+static int write_group_desc(int fd, struct perf_header *h __maybe_unused,
+			    struct perf_evlist *evlist)
+{
+	u32 nr_groups = evlist->nr_groups;
+	struct perf_evsel *evsel;
+	int ret;
+
+	ret = do_write(fd, &nr_groups, sizeof(nr_groups));
+	if (ret < 0)
+		return ret;
+
+	list_for_each_entry(evsel, &evlist->entries, node) {
+		if (perf_evsel__is_group_leader(evsel) &&
+		    evsel->nr_members > 1) {
+			const char *name = evsel->group_name ?: "{anon_group}";
+			u32 leader_idx = evsel->idx;
+			u32 nr_members = evsel->nr_members;
+
+			ret = do_write_string(fd, name);
+			if (ret < 0)
+				return ret;
+
+			ret = do_write(fd, &leader_idx, sizeof(leader_idx));
+			if (ret < 0)
+				return ret;
+
+			ret = do_write(fd, &nr_members, sizeof(nr_members));
+			if (ret < 0)
+				return ret;
+		}
+	}
+	return 0;
+}
+
+/*
  * default get_cpuid(): nothing gets recorded
  * actual implementation must be in arch/$(ARCH)/util/header.c
  */
@@ -1209,14 +1267,14 @@
 	size_t msz;
 
 	/* number of events */
-	ret = read(fd, &nre, sizeof(nre));
+	ret = readn(fd, &nre, sizeof(nre));
 	if (ret != (ssize_t)sizeof(nre))
 		goto error;
 
 	if (ph->needs_swap)
 		nre = bswap_32(nre);
 
-	ret = read(fd, &sz, sizeof(sz));
+	ret = readn(fd, &sz, sizeof(sz));
 	if (ret != (ssize_t)sizeof(sz))
 		goto error;
 
@@ -1244,7 +1302,7 @@
 		 * must read entire on-file attr struct to
 		 * sync up with layout.
 		 */
-		ret = read(fd, buf, sz);
+		ret = readn(fd, buf, sz);
 		if (ret != (ssize_t)sz)
 			goto error;
 
@@ -1253,7 +1311,7 @@
 
 		memcpy(&evsel->attr, buf, msz);
 
-		ret = read(fd, &nr, sizeof(nr));
+		ret = readn(fd, &nr, sizeof(nr));
 		if (ret != (ssize_t)sizeof(nr))
 			goto error;
 
@@ -1274,7 +1332,7 @@
 		evsel->id = id;
 
 		for (j = 0 ; j < nr; j++) {
-			ret = read(fd, id, sizeof(*id));
+			ret = readn(fd, id, sizeof(*id));
 			if (ret != (ssize_t)sizeof(*id))
 				goto error;
 			if (ph->needs_swap)
@@ -1435,6 +1493,31 @@
 	fprintf(fp, "# pmu mappings: unable to read\n");
 }
 
+static void print_group_desc(struct perf_header *ph, int fd __maybe_unused,
+			     FILE *fp)
+{
+	struct perf_session *session;
+	struct perf_evsel *evsel;
+	u32 nr = 0;
+
+	session = container_of(ph, struct perf_session, header);
+
+	list_for_each_entry(evsel, &session->evlist->entries, node) {
+		if (perf_evsel__is_group_leader(evsel) &&
+		    evsel->nr_members > 1) {
+			fprintf(fp, "# group: %s{%s", evsel->group_name ?: "",
+				perf_evsel__name(evsel));
+
+			nr = evsel->nr_members - 1;
+		} else if (nr) {
+			fprintf(fp, ",%s", perf_evsel__name(evsel));
+
+			if (--nr == 0)
+				fprintf(fp, "}\n");
+		}
+	}
+}
+
 static int __event_process_build_id(struct build_id_event *bev,
 				    char *filename,
 				    struct perf_session *session)
@@ -1506,14 +1589,14 @@
 	while (offset < limit) {
 		ssize_t len;
 
-		if (read(input, &old_bev, sizeof(old_bev)) != sizeof(old_bev))
+		if (readn(input, &old_bev, sizeof(old_bev)) != sizeof(old_bev))
 			return -1;
 
 		if (header->needs_swap)
 			perf_event_header__bswap(&old_bev.header);
 
 		len = old_bev.header.size - sizeof(old_bev);
-		if (read(input, filename, len) != len)
+		if (readn(input, filename, len) != len)
 			return -1;
 
 		bev.header = old_bev.header;
@@ -1548,14 +1631,14 @@
 	while (offset < limit) {
 		ssize_t len;
 
-		if (read(input, &bev, sizeof(bev)) != sizeof(bev))
+		if (readn(input, &bev, sizeof(bev)) != sizeof(bev))
 			goto out;
 
 		if (header->needs_swap)
 			perf_event_header__bswap(&bev.header);
 
 		len = bev.header.size - sizeof(bev);
-		if (read(input, filename, len) != len)
+		if (readn(input, filename, len) != len)
 			goto out;
 		/*
 		 * The a1645ce1 changeset:
@@ -1641,7 +1724,7 @@
 	size_t ret;
 	u32 nr;
 
-	ret = read(fd, &nr, sizeof(nr));
+	ret = readn(fd, &nr, sizeof(nr));
 	if (ret != sizeof(nr))
 		return -1;
 
@@ -1650,7 +1733,7 @@
 
 	ph->env.nr_cpus_online = nr;
 
-	ret = read(fd, &nr, sizeof(nr));
+	ret = readn(fd, &nr, sizeof(nr));
 	if (ret != sizeof(nr))
 		return -1;
 
@@ -1684,7 +1767,7 @@
 	uint64_t mem;
 	size_t ret;
 
-	ret = read(fd, &mem, sizeof(mem));
+	ret = readn(fd, &mem, sizeof(mem));
 	if (ret != sizeof(mem))
 		return -1;
 
@@ -1756,7 +1839,7 @@
 	u32 nr, i;
 	struct strbuf sb;
 
-	ret = read(fd, &nr, sizeof(nr));
+	ret = readn(fd, &nr, sizeof(nr));
 	if (ret != sizeof(nr))
 		return -1;
 
@@ -1792,7 +1875,7 @@
 	char *str;
 	struct strbuf sb;
 
-	ret = read(fd, &nr, sizeof(nr));
+	ret = readn(fd, &nr, sizeof(nr));
 	if (ret != sizeof(nr))
 		return -1;
 
@@ -1813,7 +1896,7 @@
 	}
 	ph->env.sibling_cores = strbuf_detach(&sb, NULL);
 
-	ret = read(fd, &nr, sizeof(nr));
+	ret = readn(fd, &nr, sizeof(nr));
 	if (ret != sizeof(nr))
 		return -1;
 
@@ -1850,7 +1933,7 @@
 	struct strbuf sb;
 
 	/* nr nodes */
-	ret = read(fd, &nr, sizeof(nr));
+	ret = readn(fd, &nr, sizeof(nr));
 	if (ret != sizeof(nr))
 		goto error;
 
@@ -1862,15 +1945,15 @@
 
 	for (i = 0; i < nr; i++) {
 		/* node number */
-		ret = read(fd, &node, sizeof(node));
+		ret = readn(fd, &node, sizeof(node));
 		if (ret != sizeof(node))
 			goto error;
 
-		ret = read(fd, &mem_total, sizeof(u64));
+		ret = readn(fd, &mem_total, sizeof(u64));
 		if (ret != sizeof(u64))
 			goto error;
 
-		ret = read(fd, &mem_free, sizeof(u64));
+		ret = readn(fd, &mem_free, sizeof(u64));
 		if (ret != sizeof(u64))
 			goto error;
 
@@ -1909,7 +1992,7 @@
 	u32 type;
 	struct strbuf sb;
 
-	ret = read(fd, &pmu_num, sizeof(pmu_num));
+	ret = readn(fd, &pmu_num, sizeof(pmu_num));
 	if (ret != sizeof(pmu_num))
 		return -1;
 
@@ -1925,7 +2008,7 @@
 	strbuf_init(&sb, 128);
 
 	while (pmu_num) {
-		if (read(fd, &type, sizeof(type)) != sizeof(type))
+		if (readn(fd, &type, sizeof(type)) != sizeof(type))
 			goto error;
 		if (ph->needs_swap)
 			type = bswap_32(type);
@@ -1949,6 +2032,98 @@
 	return -1;
 }
 
+static int process_group_desc(struct perf_file_section *section __maybe_unused,
+			      struct perf_header *ph, int fd,
+			      void *data __maybe_unused)
+{
+	size_t ret = -1;
+	u32 i, nr, nr_groups;
+	struct perf_session *session;
+	struct perf_evsel *evsel, *leader = NULL;
+	struct group_desc {
+		char *name;
+		u32 leader_idx;
+		u32 nr_members;
+	} *desc;
+
+	if (readn(fd, &nr_groups, sizeof(nr_groups)) != sizeof(nr_groups))
+		return -1;
+
+	if (ph->needs_swap)
+		nr_groups = bswap_32(nr_groups);
+
+	ph->env.nr_groups = nr_groups;
+	if (!nr_groups) {
+		pr_debug("group desc not available\n");
+		return 0;
+	}
+
+	desc = calloc(nr_groups, sizeof(*desc));
+	if (!desc)
+		return -1;
+
+	for (i = 0; i < nr_groups; i++) {
+		desc[i].name = do_read_string(fd, ph);
+		if (!desc[i].name)
+			goto out_free;
+
+		if (readn(fd, &desc[i].leader_idx, sizeof(u32)) != sizeof(u32))
+			goto out_free;
+
+		if (readn(fd, &desc[i].nr_members, sizeof(u32)) != sizeof(u32))
+			goto out_free;
+
+		if (ph->needs_swap) {
+			desc[i].leader_idx = bswap_32(desc[i].leader_idx);
+			desc[i].nr_members = bswap_32(desc[i].nr_members);
+		}
+	}
+
+	/*
+	 * Rebuild group relationship based on the group_desc
+	 */
+	session = container_of(ph, struct perf_session, header);
+	session->evlist->nr_groups = nr_groups;
+
+	i = nr = 0;
+	list_for_each_entry(evsel, &session->evlist->entries, node) {
+		if (evsel->idx == (int) desc[i].leader_idx) {
+			evsel->leader = evsel;
+			/* {anon_group} is a dummy name */
+			if (strcmp(desc[i].name, "{anon_group}"))
+				evsel->group_name = desc[i].name;
+			evsel->nr_members = desc[i].nr_members;
+
+			if (i >= nr_groups || nr > 0) {
+				pr_debug("invalid group desc\n");
+				goto out_free;
+			}
+
+			leader = evsel;
+			nr = evsel->nr_members - 1;
+			i++;
+		} else if (nr) {
+			/* This is a group member */
+			evsel->leader = leader;
+
+			nr--;
+		}
+	}
+
+	if (i != nr_groups || nr != 0) {
+		pr_debug("invalid group desc\n");
+		goto out_free;
+	}
+
+	ret = 0;
+out_free:
+	while ((int) --i >= 0)
+		free(desc[i].name);
+	free(desc);
+
+	return ret;
+}
+
 struct feature_ops {
 	int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist);
 	void (*print)(struct perf_header *h, int fd, FILE *fp);
@@ -1988,6 +2163,7 @@
 	FEAT_OPF(HEADER_NUMA_TOPOLOGY,	numa_topology),
 	FEAT_OPA(HEADER_BRANCH_STACK,	branch_stack),
 	FEAT_OPP(HEADER_PMU_MAPPINGS,	pmu_mappings),
+	FEAT_OPP(HEADER_GROUP_DESC,	group_desc),
 };
 
 struct header_print_data {
@@ -2077,7 +2253,7 @@
 	if (!nr_sections)
 		return 0;
 
-	feat_sec = p = calloc(sizeof(*feat_sec), nr_sections);
+	feat_sec = p = calloc(nr_sections, sizeof(*feat_sec));
 	if (feat_sec == NULL)
 		return -ENOMEM;
 
@@ -2249,7 +2425,7 @@
 	if (!nr_sections)
 		return 0;
 
-	feat_sec = sec = calloc(sizeof(*feat_sec), nr_sections);
+	feat_sec = sec = calloc(nr_sections, sizeof(*feat_sec));
 	if (!feat_sec)
 		return -1;
 
@@ -2912,16 +3088,22 @@
 				 session->repipe);
 	padding = PERF_ALIGN(size_read, sizeof(u64)) - size_read;
 
-	if (read(session->fd, buf, padding) < 0)
-		die("reading input file");
+	if (readn(session->fd, buf, padding) < 0) {
+		pr_err("%s: reading input file", __func__);
+		return -1;
+	}
 	if (session->repipe) {
 		int retw = write(STDOUT_FILENO, buf, padding);
-		if (retw <= 0 || retw != padding)
-			die("repiping tracing data padding");
+		if (retw <= 0 || retw != padding) {
+			pr_err("%s: repiping tracing data padding", __func__);
+			return -1;
+		}
 	}
 
-	if (size_read + padding != size)
-		die("tracing data size mismatch");
+	if (size_read + padding != size) {
+		pr_err("%s: tracing data size mismatch", __func__);
+		return -1;
+	}
 
 	perf_evlist__prepare_tracepoint_events(session->evlist,
 					       session->pevent);
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 20f0344..c9fc55c 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -29,6 +29,7 @@
 	HEADER_NUMA_TOPOLOGY,
 	HEADER_BRANCH_STACK,
 	HEADER_PMU_MAPPINGS,
+	HEADER_GROUP_DESC,
 	HEADER_LAST_FEATURE,
 	HEADER_FEAT_BITS	= 256,
 };
@@ -79,6 +80,7 @@
 	char			*numa_nodes;
 	int			nr_pmu_mappings;
 	char			*pmu_mappings;
+	int			nr_groups;
 };
 
 struct perf_header {
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index cb17e2a..f855941 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -4,6 +4,7 @@
 #include "hist.h"
 #include "session.h"
 #include "sort.h"
+#include "evsel.h"
 #include <math.h>
 
 static bool hists__filter_entry_by_dso(struct hists *hists,
@@ -82,6 +83,9 @@
 		hists__new_col_len(hists, HISTC_DSO, len);
 	}
 
+	if (h->parent)
+		hists__new_col_len(hists, HISTC_PARENT, h->parent->namelen);
+
 	if (h->branch_info) {
 		int symlen;
 		/*
@@ -242,6 +246,14 @@
 
 		if (he->ms.map)
 			he->ms.map->referenced = true;
+
+		if (he->branch_info) {
+			if (he->branch_info->from.map)
+				he->branch_info->from.map->referenced = true;
+			if (he->branch_info->to.map)
+				he->branch_info->to.map->referenced = true;
+		}
+
 		if (symbol_conf.use_callchain)
 			callchain_init(he->callchain);
 
@@ -251,7 +263,7 @@
 	return he;
 }
 
-static void hists__inc_nr_entries(struct hists *hists, struct hist_entry *h)
+void hists__inc_nr_entries(struct hists *hists, struct hist_entry *h)
 {
 	if (!h->filtered) {
 		hists__calc_col_len(hists, h);
@@ -285,7 +297,13 @@
 		parent = *p;
 		he = rb_entry(parent, struct hist_entry, rb_node_in);
 
-		cmp = hist_entry__cmp(entry, he);
+		/*
+		 * Make sure that it receives arguments in a same order as
+		 * hist_entry__collapse() so that we can use an appropriate
+		 * function when searching an entry regardless which sort
+		 * keys were used.
+		 */
+		cmp = hist_entry__cmp(he, entry);
 
 		if (!cmp) {
 			he_stat__add_period(&he->stat, period);
@@ -523,6 +541,62 @@
  * reverse the map, sort on period.
  */
 
+static int period_cmp(u64 period_a, u64 period_b)
+{
+	if (period_a > period_b)
+		return 1;
+	if (period_a < period_b)
+		return -1;
+	return 0;
+}
+
+static int hist_entry__sort_on_period(struct hist_entry *a,
+				      struct hist_entry *b)
+{
+	int ret;
+	int i, nr_members;
+	struct perf_evsel *evsel;
+	struct hist_entry *pair;
+	u64 *periods_a, *periods_b;
+
+	ret = period_cmp(a->stat.period, b->stat.period);
+	if (ret || !symbol_conf.event_group)
+		return ret;
+
+	evsel = hists_to_evsel(a->hists);
+	nr_members = evsel->nr_members;
+	if (nr_members <= 1)
+		return ret;
+
+	periods_a = zalloc(sizeof(periods_a) * nr_members);
+	periods_b = zalloc(sizeof(periods_b) * nr_members);
+
+	if (!periods_a || !periods_b)
+		goto out;
+
+	list_for_each_entry(pair, &a->pairs.head, pairs.node) {
+		evsel = hists_to_evsel(pair->hists);
+		periods_a[perf_evsel__group_idx(evsel)] = pair->stat.period;
+	}
+
+	list_for_each_entry(pair, &b->pairs.head, pairs.node) {
+		evsel = hists_to_evsel(pair->hists);
+		periods_b[perf_evsel__group_idx(evsel)] = pair->stat.period;
+	}
+
+	for (i = 1; i < nr_members; i++) {
+		ret = period_cmp(periods_a[i], periods_b[i]);
+		if (ret)
+			break;
+	}
+
+out:
+	free(periods_a);
+	free(periods_b);
+
+	return ret;
+}
+
 static void __hists__insert_output_entry(struct rb_root *entries,
 					 struct hist_entry *he,
 					 u64 min_callchain_hits)
@@ -539,7 +613,7 @@
 		parent = *p;
 		iter = rb_entry(parent, struct hist_entry, rb_node);
 
-		if (he->stat.period > iter->stat.period)
+		if (hist_entry__sort_on_period(he, iter) > 0)
 			p = &(*p)->rb_left;
 		else
 			p = &(*p)->rb_right;
@@ -711,25 +785,38 @@
 	return symbol__annotate(he->ms.sym, he->ms.map, privsize);
 }
 
+void events_stats__inc(struct events_stats *stats, u32 type)
+{
+	++stats->nr_events[0];
+	++stats->nr_events[type];
+}
+
 void hists__inc_nr_events(struct hists *hists, u32 type)
 {
-	++hists->stats.nr_events[0];
-	++hists->stats.nr_events[type];
+	events_stats__inc(&hists->stats, type);
 }
 
 static struct hist_entry *hists__add_dummy_entry(struct hists *hists,
 						 struct hist_entry *pair)
 {
-	struct rb_node **p = &hists->entries.rb_node;
+	struct rb_root *root;
+	struct rb_node **p;
 	struct rb_node *parent = NULL;
 	struct hist_entry *he;
 	int cmp;
 
+	if (sort__need_collapse)
+		root = &hists->entries_collapsed;
+	else
+		root = hists->entries_in;
+
+	p = &root->rb_node;
+
 	while (*p != NULL) {
 		parent = *p;
-		he = rb_entry(parent, struct hist_entry, rb_node);
+		he = rb_entry(parent, struct hist_entry, rb_node_in);
 
-		cmp = hist_entry__cmp(pair, he);
+		cmp = hist_entry__collapse(he, pair);
 
 		if (!cmp)
 			goto out;
@@ -744,8 +831,8 @@
 	if (he) {
 		memset(&he->stat, 0, sizeof(he->stat));
 		he->hists = hists;
-		rb_link_node(&he->rb_node, parent, p);
-		rb_insert_color(&he->rb_node, &hists->entries);
+		rb_link_node(&he->rb_node_in, parent, p);
+		rb_insert_color(&he->rb_node_in, root);
 		hists__inc_nr_entries(hists, he);
 	}
 out:
@@ -755,11 +842,16 @@
 static struct hist_entry *hists__find_entry(struct hists *hists,
 					    struct hist_entry *he)
 {
-	struct rb_node *n = hists->entries.rb_node;
+	struct rb_node *n;
+
+	if (sort__need_collapse)
+		n = hists->entries_collapsed.rb_node;
+	else
+		n = hists->entries_in->rb_node;
 
 	while (n) {
-		struct hist_entry *iter = rb_entry(n, struct hist_entry, rb_node);
-		int64_t cmp = hist_entry__cmp(he, iter);
+		struct hist_entry *iter = rb_entry(n, struct hist_entry, rb_node_in);
+		int64_t cmp = hist_entry__collapse(iter, he);
 
 		if (cmp < 0)
 			n = n->rb_left;
@@ -777,15 +869,21 @@
  */
 void hists__match(struct hists *leader, struct hists *other)
 {
+	struct rb_root *root;
 	struct rb_node *nd;
 	struct hist_entry *pos, *pair;
 
-	for (nd = rb_first(&leader->entries); nd; nd = rb_next(nd)) {
-		pos  = rb_entry(nd, struct hist_entry, rb_node);
+	if (sort__need_collapse)
+		root = &leader->entries_collapsed;
+	else
+		root = leader->entries_in;
+
+	for (nd = rb_first(root); nd; nd = rb_next(nd)) {
+		pos  = rb_entry(nd, struct hist_entry, rb_node_in);
 		pair = hists__find_entry(other, pos);
 
 		if (pair)
-			hist__entry_add_pair(pos, pair);
+			hist_entry__add_pair(pair, pos);
 	}
 }
 
@@ -796,17 +894,23 @@
  */
 int hists__link(struct hists *leader, struct hists *other)
 {
+	struct rb_root *root;
 	struct rb_node *nd;
 	struct hist_entry *pos, *pair;
 
-	for (nd = rb_first(&other->entries); nd; nd = rb_next(nd)) {
-		pos = rb_entry(nd, struct hist_entry, rb_node);
+	if (sort__need_collapse)
+		root = &other->entries_collapsed;
+	else
+		root = other->entries_in;
+
+	for (nd = rb_first(root); nd; nd = rb_next(nd)) {
+		pos = rb_entry(nd, struct hist_entry, rb_node_in);
 
 		if (!hist_entry__has_pairs(pos)) {
 			pair = hists__add_dummy_entry(leader, pos);
 			if (pair == NULL)
 				return -1;
-			hist__entry_add_pair(pair, pos);
+			hist_entry__add_pair(pos, pair);
 		}
 	}
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 8b091a5..3862468 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -96,8 +96,10 @@
 				   bool zap_kernel);
 void hists__output_recalc_col_len(struct hists *hists, int max_rows);
 
+void hists__inc_nr_entries(struct hists *hists, struct hist_entry *h);
 void hists__inc_nr_events(struct hists *self, u32 type);
-size_t hists__fprintf_nr_events(struct hists *self, FILE *fp);
+void events_stats__inc(struct events_stats *stats, u32 type);
+size_t events_stats__fprintf(struct events_stats *stats, FILE *fp);
 
 size_t hists__fprintf(struct hists *self, bool show_header, int max_rows,
 		      int max_cols, FILE *fp);
@@ -126,13 +128,19 @@
 };
 
 struct perf_hpp_fmt {
-	bool cond;
 	int (*header)(struct perf_hpp *hpp);
 	int (*width)(struct perf_hpp *hpp);
 	int (*color)(struct perf_hpp *hpp, struct hist_entry *he);
 	int (*entry)(struct perf_hpp *hpp, struct hist_entry *he);
+
+	struct list_head list;
 };
 
+extern struct list_head perf_hpp__list;
+
+#define perf_hpp__for_each_format(format) \
+	list_for_each_entry(format, &perf_hpp__list, list)
+
 extern struct perf_hpp_fmt perf_hpp__format[];
 
 enum {
@@ -148,14 +156,14 @@
 	PERF_HPP__DELTA,
 	PERF_HPP__RATIO,
 	PERF_HPP__WEIGHTED_DIFF,
-	PERF_HPP__DISPL,
 	PERF_HPP__FORMULA,
 
 	PERF_HPP__MAX_INDEX
 };
 
 void perf_hpp__init(void);
-void perf_hpp__column_enable(unsigned col, bool enable);
+void perf_hpp__column_register(struct perf_hpp_fmt *format);
+void perf_hpp__column_enable(unsigned col);
 int hist_entry__period_snprintf(struct perf_hpp *hpp, struct hist_entry *he,
 				bool color);
 
@@ -219,8 +227,10 @@
 
 unsigned int hists__sort_list_width(struct hists *self);
 
-double perf_diff__compute_delta(struct hist_entry *he);
-double perf_diff__compute_ratio(struct hist_entry *he);
-s64 perf_diff__compute_wdiff(struct hist_entry *he);
-int perf_diff__formula(char *buf, size_t size, struct hist_entry *he);
+double perf_diff__compute_delta(struct hist_entry *he, struct hist_entry *pair);
+double perf_diff__compute_ratio(struct hist_entry *he, struct hist_entry *pair);
+s64 perf_diff__compute_wdiff(struct hist_entry *he, struct hist_entry *pair);
+int perf_diff__formula(struct hist_entry *he, struct hist_entry *pair,
+		       char *buf, size_t size);
+double perf_diff__period_percent(struct hist_entry *he, u64 period);
 #endif	/* __PERF_HIST_H */
diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h
index a55d8cf0..45cf10a 100644
--- a/tools/perf/util/include/linux/bitops.h
+++ b/tools/perf/util/include/linux/bitops.h
@@ -14,6 +14,7 @@
 #define BITS_TO_LONGS(nr)       DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
 #define BITS_TO_U64(nr)         DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u64))
 #define BITS_TO_U32(nr)         DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32))
+#define BITS_TO_BYTES(nr)       DIV_ROUND_UP(nr, BITS_PER_BYTE)
 
 #define for_each_set_bit(bit, addr, size) \
 	for ((bit) = find_first_bit((addr), (size));		\
diff --git a/tools/perf/util/intlist.c b/tools/perf/util/intlist.c
index 9d07400..11a8d86 100644
--- a/tools/perf/util/intlist.c
+++ b/tools/perf/util/intlist.c
@@ -59,16 +59,40 @@
 
 struct int_node *intlist__find(struct intlist *ilist, int i)
 {
-	struct int_node *node = NULL;
-	struct rb_node *rb_node = rblist__find(&ilist->rblist, (void *)((long)i));
+	struct int_node *node;
+	struct rb_node *rb_node;
 
+	if (ilist == NULL)
+		return NULL;
+
+	node = NULL;
+	rb_node = rblist__find(&ilist->rblist, (void *)((long)i));
 	if (rb_node)
 		node = container_of(rb_node, struct int_node, rb_node);
 
 	return node;
 }
 
-struct intlist *intlist__new(void)
+static int intlist__parse_list(struct intlist *ilist, const char *s)
+{
+	char *sep;
+	int err;
+
+	do {
+		long value = strtol(s, &sep, 10);
+		err = -EINVAL;
+		if (*sep != ',' && *sep != '\0')
+			break;
+		err = intlist__add(ilist, value);
+		if (err)
+			break;
+		s = sep + 1;
+	} while (*sep != '\0');
+
+	return err;
+}
+
+struct intlist *intlist__new(const char *slist)
 {
 	struct intlist *ilist = malloc(sizeof(*ilist));
 
@@ -77,9 +101,15 @@
 		ilist->rblist.node_cmp    = intlist__node_cmp;
 		ilist->rblist.node_new    = intlist__node_new;
 		ilist->rblist.node_delete = intlist__node_delete;
+
+		if (slist && intlist__parse_list(ilist, slist))
+			goto out_delete;
 	}
 
 	return ilist;
+out_delete:
+	intlist__delete(ilist);
+	return NULL;
 }
 
 void intlist__delete(struct intlist *ilist)
diff --git a/tools/perf/util/intlist.h b/tools/perf/util/intlist.h
index 6d63ab9..62351da 100644
--- a/tools/perf/util/intlist.h
+++ b/tools/perf/util/intlist.h
@@ -15,7 +15,7 @@
 	struct rblist rblist;
 };
 
-struct intlist *intlist__new(void);
+struct intlist *intlist__new(const char *slist);
 void intlist__delete(struct intlist *ilist);
 
 void intlist__remove(struct intlist *ilist, struct int_node *in);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 1f09d05..efdb38e 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1,10 +1,15 @@
+#include "callchain.h"
 #include "debug.h"
 #include "event.h"
+#include "evsel.h"
+#include "hist.h"
 #include "machine.h"
 #include "map.h"
+#include "sort.h"
 #include "strlist.h"
 #include "thread.h"
 #include <stdbool.h>
+#include "unwind.h"
 
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 {
@@ -48,6 +53,29 @@
 	}
 }
 
+void machine__delete_dead_threads(struct machine *machine)
+{
+	struct thread *n, *t;
+
+	list_for_each_entry_safe(t, n, &machine->dead_threads, node) {
+		list_del(&t->node);
+		thread__delete(t);
+	}
+}
+
+void machine__delete_threads(struct machine *machine)
+{
+	struct rb_node *nd = rb_first(&machine->threads);
+
+	while (nd) {
+		struct thread *t = rb_entry(nd, struct thread, rb_node);
+
+		rb_erase(&t->rb_node, &machine->threads);
+		nd = rb_next(nd);
+		thread__delete(t);
+	}
+}
+
 void machine__exit(struct machine *machine)
 {
 	map_groups__exit(&machine->kmaps);
@@ -63,10 +91,22 @@
 	free(machine);
 }
 
-struct machine *machines__add(struct rb_root *machines, pid_t pid,
+void machines__init(struct machines *machines)
+{
+	machine__init(&machines->host, "", HOST_KERNEL_ID);
+	machines->guests = RB_ROOT;
+}
+
+void machines__exit(struct machines *machines)
+{
+	machine__exit(&machines->host);
+	/* XXX exit guest */
+}
+
+struct machine *machines__add(struct machines *machines, pid_t pid,
 			      const char *root_dir)
 {
-	struct rb_node **p = &machines->rb_node;
+	struct rb_node **p = &machines->guests.rb_node;
 	struct rb_node *parent = NULL;
 	struct machine *pos, *machine = malloc(sizeof(*machine));
 
@@ -88,18 +128,21 @@
 	}
 
 	rb_link_node(&machine->rb_node, parent, p);
-	rb_insert_color(&machine->rb_node, machines);
+	rb_insert_color(&machine->rb_node, &machines->guests);
 
 	return machine;
 }
 
-struct machine *machines__find(struct rb_root *machines, pid_t pid)
+struct machine *machines__find(struct machines *machines, pid_t pid)
 {
-	struct rb_node **p = &machines->rb_node;
+	struct rb_node **p = &machines->guests.rb_node;
 	struct rb_node *parent = NULL;
 	struct machine *machine;
 	struct machine *default_machine = NULL;
 
+	if (pid == HOST_KERNEL_ID)
+		return &machines->host;
+
 	while (*p != NULL) {
 		parent = *p;
 		machine = rb_entry(parent, struct machine, rb_node);
@@ -116,7 +159,7 @@
 	return default_machine;
 }
 
-struct machine *machines__findnew(struct rb_root *machines, pid_t pid)
+struct machine *machines__findnew(struct machines *machines, pid_t pid)
 {
 	char path[PATH_MAX];
 	const char *root_dir = "";
@@ -150,12 +193,12 @@
 	return machine;
 }
 
-void machines__process(struct rb_root *machines,
-		       machine__process_t process, void *data)
+void machines__process_guests(struct machines *machines,
+			      machine__process_t process, void *data)
 {
 	struct rb_node *nd;
 
-	for (nd = rb_first(machines); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
 		process(pos, data);
 	}
@@ -175,12 +218,14 @@
 	return bf;
 }
 
-void machines__set_id_hdr_size(struct rb_root *machines, u16 id_hdr_size)
+void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size)
 {
 	struct rb_node *node;
 	struct machine *machine;
 
-	for (node = rb_first(machines); node; node = rb_next(node)) {
+	machines->host.id_hdr_size = id_hdr_size;
+
+	for (node = rb_first(&machines->guests); node; node = rb_next(node)) {
 		machine = rb_entry(node, struct machine, rb_node);
 		machine->id_hdr_size = id_hdr_size;
 	}
@@ -264,6 +309,537 @@
 	return 0;
 }
 
+struct map *machine__new_module(struct machine *machine, u64 start,
+				const char *filename)
+{
+	struct map *map;
+	struct dso *dso = __dsos__findnew(&machine->kernel_dsos, filename);
+
+	if (dso == NULL)
+		return NULL;
+
+	map = map__new2(start, dso, MAP__FUNCTION);
+	if (map == NULL)
+		return NULL;
+
+	if (machine__is_host(machine))
+		dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE;
+	else
+		dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE;
+	map_groups__insert(&machine->kmaps, map);
+	return map;
+}
+
+size_t machines__fprintf_dsos(struct machines *machines, FILE *fp)
+{
+	struct rb_node *nd;
+	size_t ret = __dsos__fprintf(&machines->host.kernel_dsos, fp) +
+		     __dsos__fprintf(&machines->host.user_dsos, fp);
+
+	for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+		ret += __dsos__fprintf(&pos->kernel_dsos, fp);
+		ret += __dsos__fprintf(&pos->user_dsos, fp);
+	}
+
+	return ret;
+}
+
+size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp,
+				     bool (skip)(struct dso *dso, int parm), int parm)
+{
+	return __dsos__fprintf_buildid(&machine->kernel_dsos, fp, skip, parm) +
+	       __dsos__fprintf_buildid(&machine->user_dsos, fp, skip, parm);
+}
+
+size_t machines__fprintf_dsos_buildid(struct machines *machines, FILE *fp,
+				     bool (skip)(struct dso *dso, int parm), int parm)
+{
+	struct rb_node *nd;
+	size_t ret = machine__fprintf_dsos_buildid(&machines->host, fp, skip, parm);
+
+	for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+		ret += machine__fprintf_dsos_buildid(pos, fp, skip, parm);
+	}
+	return ret;
+}
+
+size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp)
+{
+	int i;
+	size_t printed = 0;
+	struct dso *kdso = machine->vmlinux_maps[MAP__FUNCTION]->dso;
+
+	if (kdso->has_build_id) {
+		char filename[PATH_MAX];
+		if (dso__build_id_filename(kdso, filename, sizeof(filename)))
+			printed += fprintf(fp, "[0] %s\n", filename);
+	}
+
+	for (i = 0; i < vmlinux_path__nr_entries; ++i)
+		printed += fprintf(fp, "[%d] %s\n",
+				   i + kdso->has_build_id, vmlinux_path[i]);
+
+	return printed;
+}
+
+size_t machine__fprintf(struct machine *machine, FILE *fp)
+{
+	size_t ret = 0;
+	struct rb_node *nd;
+
+	for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) {
+		struct thread *pos = rb_entry(nd, struct thread, rb_node);
+
+		ret += thread__fprintf(pos, fp);
+	}
+
+	return ret;
+}
+
+static struct dso *machine__get_kernel(struct machine *machine)
+{
+	const char *vmlinux_name = NULL;
+	struct dso *kernel;
+
+	if (machine__is_host(machine)) {
+		vmlinux_name = symbol_conf.vmlinux_name;
+		if (!vmlinux_name)
+			vmlinux_name = "[kernel.kallsyms]";
+
+		kernel = dso__kernel_findnew(machine, vmlinux_name,
+					     "[kernel]",
+					     DSO_TYPE_KERNEL);
+	} else {
+		char bf[PATH_MAX];
+
+		if (machine__is_default_guest(machine))
+			vmlinux_name = symbol_conf.default_guest_vmlinux_name;
+		if (!vmlinux_name)
+			vmlinux_name = machine__mmap_name(machine, bf,
+							  sizeof(bf));
+
+		kernel = dso__kernel_findnew(machine, vmlinux_name,
+					     "[guest.kernel]",
+					     DSO_TYPE_GUEST_KERNEL);
+	}
+
+	if (kernel != NULL && (!kernel->has_build_id))
+		dso__read_running_kernel_build_id(kernel, machine);
+
+	return kernel;
+}
+
+struct process_args {
+	u64 start;
+};
+
+static int symbol__in_kernel(void *arg, const char *name,
+			     char type __maybe_unused, u64 start)
+{
+	struct process_args *args = arg;
+
+	if (strchr(name, '['))
+		return 0;
+
+	args->start = start;
+	return 1;
+}
+
+/* Figure out the start address of kernel map from /proc/kallsyms */
+static u64 machine__get_kernel_start_addr(struct machine *machine)
+{
+	const char *filename;
+	char path[PATH_MAX];
+	struct process_args args;
+
+	if (machine__is_host(machine)) {
+		filename = "/proc/kallsyms";
+	} else {
+		if (machine__is_default_guest(machine))
+			filename = (char *)symbol_conf.default_guest_kallsyms;
+		else {
+			sprintf(path, "%s/proc/kallsyms", machine->root_dir);
+			filename = path;
+		}
+	}
+
+	if (symbol__restricted_filename(filename, "/proc/kallsyms"))
+		return 0;
+
+	if (kallsyms__parse(filename, &args, symbol__in_kernel) <= 0)
+		return 0;
+
+	return args.start;
+}
+
+int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
+{
+	enum map_type type;
+	u64 start = machine__get_kernel_start_addr(machine);
+
+	for (type = 0; type < MAP__NR_TYPES; ++type) {
+		struct kmap *kmap;
+
+		machine->vmlinux_maps[type] = map__new2(start, kernel, type);
+		if (machine->vmlinux_maps[type] == NULL)
+			return -1;
+
+		machine->vmlinux_maps[type]->map_ip =
+			machine->vmlinux_maps[type]->unmap_ip =
+				identity__map_ip;
+		kmap = map__kmap(machine->vmlinux_maps[type]);
+		kmap->kmaps = &machine->kmaps;
+		map_groups__insert(&machine->kmaps,
+				   machine->vmlinux_maps[type]);
+	}
+
+	return 0;
+}
+
+void machine__destroy_kernel_maps(struct machine *machine)
+{
+	enum map_type type;
+
+	for (type = 0; type < MAP__NR_TYPES; ++type) {
+		struct kmap *kmap;
+
+		if (machine->vmlinux_maps[type] == NULL)
+			continue;
+
+		kmap = map__kmap(machine->vmlinux_maps[type]);
+		map_groups__remove(&machine->kmaps,
+				   machine->vmlinux_maps[type]);
+		if (kmap->ref_reloc_sym) {
+			/*
+			 * ref_reloc_sym is shared among all maps, so free just
+			 * on one of them.
+			 */
+			if (type == MAP__FUNCTION) {
+				free((char *)kmap->ref_reloc_sym->name);
+				kmap->ref_reloc_sym->name = NULL;
+				free(kmap->ref_reloc_sym);
+			}
+			kmap->ref_reloc_sym = NULL;
+		}
+
+		map__delete(machine->vmlinux_maps[type]);
+		machine->vmlinux_maps[type] = NULL;
+	}
+}
+
+int machines__create_guest_kernel_maps(struct machines *machines)
+{
+	int ret = 0;
+	struct dirent **namelist = NULL;
+	int i, items = 0;
+	char path[PATH_MAX];
+	pid_t pid;
+	char *endp;
+
+	if (symbol_conf.default_guest_vmlinux_name ||
+	    symbol_conf.default_guest_modules ||
+	    symbol_conf.default_guest_kallsyms) {
+		machines__create_kernel_maps(machines, DEFAULT_GUEST_KERNEL_ID);
+	}
+
+	if (symbol_conf.guestmount) {
+		items = scandir(symbol_conf.guestmount, &namelist, NULL, NULL);
+		if (items <= 0)
+			return -ENOENT;
+		for (i = 0; i < items; i++) {
+			if (!isdigit(namelist[i]->d_name[0])) {
+				/* Filter out . and .. */
+				continue;
+			}
+			pid = (pid_t)strtol(namelist[i]->d_name, &endp, 10);
+			if ((*endp != '\0') ||
+			    (endp == namelist[i]->d_name) ||
+			    (errno == ERANGE)) {
+				pr_debug("invalid directory (%s). Skipping.\n",
+					 namelist[i]->d_name);
+				continue;
+			}
+			sprintf(path, "%s/%s/proc/kallsyms",
+				symbol_conf.guestmount,
+				namelist[i]->d_name);
+			ret = access(path, R_OK);
+			if (ret) {
+				pr_debug("Can't access file %s\n", path);
+				goto failure;
+			}
+			machines__create_kernel_maps(machines, pid);
+		}
+failure:
+		free(namelist);
+	}
+
+	return ret;
+}
+
+void machines__destroy_kernel_maps(struct machines *machines)
+{
+	struct rb_node *next = rb_first(&machines->guests);
+
+	machine__destroy_kernel_maps(&machines->host);
+
+	while (next) {
+		struct machine *pos = rb_entry(next, struct machine, rb_node);
+
+		next = rb_next(&pos->rb_node);
+		rb_erase(&pos->rb_node, &machines->guests);
+		machine__delete(pos);
+	}
+}
+
+int machines__create_kernel_maps(struct machines *machines, pid_t pid)
+{
+	struct machine *machine = machines__findnew(machines, pid);
+
+	if (machine == NULL)
+		return -1;
+
+	return machine__create_kernel_maps(machine);
+}
+
+int machine__load_kallsyms(struct machine *machine, const char *filename,
+			   enum map_type type, symbol_filter_t filter)
+{
+	struct map *map = machine->vmlinux_maps[type];
+	int ret = dso__load_kallsyms(map->dso, filename, map, filter);
+
+	if (ret > 0) {
+		dso__set_loaded(map->dso, type);
+		/*
+		 * Since /proc/kallsyms will have multiple sessions for the
+		 * kernel, with modules between them, fixup the end of all
+		 * sections.
+		 */
+		__map_groups__fixup_end(&machine->kmaps, type);
+	}
+
+	return ret;
+}
+
+int machine__load_vmlinux_path(struct machine *machine, enum map_type type,
+			       symbol_filter_t filter)
+{
+	struct map *map = machine->vmlinux_maps[type];
+	int ret = dso__load_vmlinux_path(map->dso, map, filter);
+
+	if (ret > 0) {
+		dso__set_loaded(map->dso, type);
+		map__reloc_vmlinux(map);
+	}
+
+	return ret;
+}
+
+static void map_groups__fixup_end(struct map_groups *mg)
+{
+	int i;
+	for (i = 0; i < MAP__NR_TYPES; ++i)
+		__map_groups__fixup_end(mg, i);
+}
+
+static char *get_kernel_version(const char *root_dir)
+{
+	char version[PATH_MAX];
+	FILE *file;
+	char *name, *tmp;
+	const char *prefix = "Linux version ";
+
+	sprintf(version, "%s/proc/version", root_dir);
+	file = fopen(version, "r");
+	if (!file)
+		return NULL;
+
+	version[0] = '\0';
+	tmp = fgets(version, sizeof(version), file);
+	fclose(file);
+
+	name = strstr(version, prefix);
+	if (!name)
+		return NULL;
+	name += strlen(prefix);
+	tmp = strchr(name, ' ');
+	if (tmp)
+		*tmp = '\0';
+
+	return strdup(name);
+}
+
+static int map_groups__set_modules_path_dir(struct map_groups *mg,
+				const char *dir_name)
+{
+	struct dirent *dent;
+	DIR *dir = opendir(dir_name);
+	int ret = 0;
+
+	if (!dir) {
+		pr_debug("%s: cannot open %s dir\n", __func__, dir_name);
+		return -1;
+	}
+
+	while ((dent = readdir(dir)) != NULL) {
+		char path[PATH_MAX];
+		struct stat st;
+
+		/*sshfs might return bad dent->d_type, so we have to stat*/
+		snprintf(path, sizeof(path), "%s/%s", dir_name, dent->d_name);
+		if (stat(path, &st))
+			continue;
+
+		if (S_ISDIR(st.st_mode)) {
+			if (!strcmp(dent->d_name, ".") ||
+			    !strcmp(dent->d_name, ".."))
+				continue;
+
+			ret = map_groups__set_modules_path_dir(mg, path);
+			if (ret < 0)
+				goto out;
+		} else {
+			char *dot = strrchr(dent->d_name, '.'),
+			     dso_name[PATH_MAX];
+			struct map *map;
+			char *long_name;
+
+			if (dot == NULL || strcmp(dot, ".ko"))
+				continue;
+			snprintf(dso_name, sizeof(dso_name), "[%.*s]",
+				 (int)(dot - dent->d_name), dent->d_name);
+
+			strxfrchar(dso_name, '-', '_');
+			map = map_groups__find_by_name(mg, MAP__FUNCTION,
+						       dso_name);
+			if (map == NULL)
+				continue;
+
+			long_name = strdup(path);
+			if (long_name == NULL) {
+				ret = -1;
+				goto out;
+			}
+			dso__set_long_name(map->dso, long_name);
+			map->dso->lname_alloc = 1;
+			dso__kernel_module_get_build_id(map->dso, "");
+		}
+	}
+
+out:
+	closedir(dir);
+	return ret;
+}
+
+static int machine__set_modules_path(struct machine *machine)
+{
+	char *version;
+	char modules_path[PATH_MAX];
+
+	version = get_kernel_version(machine->root_dir);
+	if (!version)
+		return -1;
+
+	snprintf(modules_path, sizeof(modules_path), "%s/lib/modules/%s/kernel",
+		 machine->root_dir, version);
+	free(version);
+
+	return map_groups__set_modules_path_dir(&machine->kmaps, modules_path);
+}
+
+static int machine__create_modules(struct machine *machine)
+{
+	char *line = NULL;
+	size_t n;
+	FILE *file;
+	struct map *map;
+	const char *modules;
+	char path[PATH_MAX];
+
+	if (machine__is_default_guest(machine))
+		modules = symbol_conf.default_guest_modules;
+	else {
+		sprintf(path, "%s/proc/modules", machine->root_dir);
+		modules = path;
+	}
+
+	if (symbol__restricted_filename(path, "/proc/modules"))
+		return -1;
+
+	file = fopen(modules, "r");
+	if (file == NULL)
+		return -1;
+
+	while (!feof(file)) {
+		char name[PATH_MAX];
+		u64 start;
+		char *sep;
+		int line_len;
+
+		line_len = getline(&line, &n, file);
+		if (line_len < 0)
+			break;
+
+		if (!line)
+			goto out_failure;
+
+		line[--line_len] = '\0'; /* \n */
+
+		sep = strrchr(line, 'x');
+		if (sep == NULL)
+			continue;
+
+		hex2u64(sep + 1, &start);
+
+		sep = strchr(line, ' ');
+		if (sep == NULL)
+			continue;
+
+		*sep = '\0';
+
+		snprintf(name, sizeof(name), "[%s]", line);
+		map = machine__new_module(machine, start, name);
+		if (map == NULL)
+			goto out_delete_line;
+		dso__kernel_module_get_build_id(map->dso, machine->root_dir);
+	}
+
+	free(line);
+	fclose(file);
+
+	return machine__set_modules_path(machine);
+
+out_delete_line:
+	free(line);
+out_failure:
+	return -1;
+}
+
+int machine__create_kernel_maps(struct machine *machine)
+{
+	struct dso *kernel = machine__get_kernel(machine);
+
+	if (kernel == NULL ||
+	    __machine__create_kernel_maps(machine, kernel) < 0)
+		return -1;
+
+	if (symbol_conf.use_modules && machine__create_modules(machine) < 0) {
+		if (machine__is_host(machine))
+			pr_debug("Problems creating module maps, "
+				 "continuing anyway...\n");
+		else
+			pr_debug("Problems creating module maps for guest %d, "
+				 "continuing anyway...\n", machine->pid);
+	}
+
+	/*
+	 * Now that we have all the maps created, just set the ->end of them:
+	 */
+	map_groups__fixup_end(&machine->kmaps);
+	return 0;
+}
+
 static void machine__set_kernel_mmap_len(struct machine *machine,
 					 union perf_event *event)
 {
@@ -462,3 +1038,189 @@
 
 	return ret;
 }
+
+void machine__remove_thread(struct machine *machine, struct thread *th)
+{
+	machine->last_match = NULL;
+	rb_erase(&th->rb_node, &machine->threads);
+	/*
+	 * We may have references to this thread, for instance in some hist_entry
+	 * instances, so just move them to a separate list.
+	 */
+	list_add_tail(&th->node, &machine->dead_threads);
+}
+
+static bool symbol__match_parent_regex(struct symbol *sym)
+{
+	if (sym->name && !regexec(&parent_regex, sym->name, 0, NULL, 0))
+		return 1;
+
+	return 0;
+}
+
+static const u8 cpumodes[] = {
+	PERF_RECORD_MISC_USER,
+	PERF_RECORD_MISC_KERNEL,
+	PERF_RECORD_MISC_GUEST_USER,
+	PERF_RECORD_MISC_GUEST_KERNEL
+};
+#define NCPUMODES (sizeof(cpumodes)/sizeof(u8))
+
+static void ip__resolve_ams(struct machine *machine, struct thread *thread,
+			    struct addr_map_symbol *ams,
+			    u64 ip)
+{
+	struct addr_location al;
+	size_t i;
+	u8 m;
+
+	memset(&al, 0, sizeof(al));
+
+	for (i = 0; i < NCPUMODES; i++) {
+		m = cpumodes[i];
+		/*
+		 * We cannot use the header.misc hint to determine whether a
+		 * branch stack address is user, kernel, guest, hypervisor.
+		 * Branches may straddle the kernel/user/hypervisor boundaries.
+		 * Thus, we have to try consecutively until we find a match
+		 * or else, the symbol is unknown
+		 */
+		thread__find_addr_location(thread, machine, m, MAP__FUNCTION,
+				ip, &al, NULL);
+		if (al.sym)
+			goto found;
+	}
+found:
+	ams->addr = ip;
+	ams->al_addr = al.addr;
+	ams->sym = al.sym;
+	ams->map = al.map;
+}
+
+struct branch_info *machine__resolve_bstack(struct machine *machine,
+					    struct thread *thr,
+					    struct branch_stack *bs)
+{
+	struct branch_info *bi;
+	unsigned int i;
+
+	bi = calloc(bs->nr, sizeof(struct branch_info));
+	if (!bi)
+		return NULL;
+
+	for (i = 0; i < bs->nr; i++) {
+		ip__resolve_ams(machine, thr, &bi[i].to, bs->entries[i].to);
+		ip__resolve_ams(machine, thr, &bi[i].from, bs->entries[i].from);
+		bi[i].flags = bs->entries[i].flags;
+	}
+	return bi;
+}
+
+static int machine__resolve_callchain_sample(struct machine *machine,
+					     struct thread *thread,
+					     struct ip_callchain *chain,
+					     struct symbol **parent)
+
+{
+	u8 cpumode = PERF_RECORD_MISC_USER;
+	unsigned int i;
+	int err;
+
+	callchain_cursor_reset(&callchain_cursor);
+
+	if (chain->nr > PERF_MAX_STACK_DEPTH) {
+		pr_warning("corrupted callchain. skipping...\n");
+		return 0;
+	}
+
+	for (i = 0; i < chain->nr; i++) {
+		u64 ip;
+		struct addr_location al;
+
+		if (callchain_param.order == ORDER_CALLEE)
+			ip = chain->ips[i];
+		else
+			ip = chain->ips[chain->nr - i - 1];
+
+		if (ip >= PERF_CONTEXT_MAX) {
+			switch (ip) {
+			case PERF_CONTEXT_HV:
+				cpumode = PERF_RECORD_MISC_HYPERVISOR;
+				break;
+			case PERF_CONTEXT_KERNEL:
+				cpumode = PERF_RECORD_MISC_KERNEL;
+				break;
+			case PERF_CONTEXT_USER:
+				cpumode = PERF_RECORD_MISC_USER;
+				break;
+			default:
+				pr_debug("invalid callchain context: "
+					 "%"PRId64"\n", (s64) ip);
+				/*
+				 * It seems the callchain is corrupted.
+				 * Discard all.
+				 */
+				callchain_cursor_reset(&callchain_cursor);
+				return 0;
+			}
+			continue;
+		}
+
+		al.filtered = false;
+		thread__find_addr_location(thread, machine, cpumode,
+					   MAP__FUNCTION, ip, &al, NULL);
+		if (al.sym != NULL) {
+			if (sort__has_parent && !*parent &&
+			    symbol__match_parent_regex(al.sym))
+				*parent = al.sym;
+			if (!symbol_conf.use_callchain)
+				break;
+		}
+
+		err = callchain_cursor_append(&callchain_cursor,
+					      ip, al.map, al.sym);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int unwind_entry(struct unwind_entry *entry, void *arg)
+{
+	struct callchain_cursor *cursor = arg;
+	return callchain_cursor_append(cursor, entry->ip,
+				       entry->map, entry->sym);
+}
+
+int machine__resolve_callchain(struct machine *machine,
+			       struct perf_evsel *evsel,
+			       struct thread *thread,
+			       struct perf_sample *sample,
+			       struct symbol **parent)
+
+{
+	int ret;
+
+	callchain_cursor_reset(&callchain_cursor);
+
+	ret = machine__resolve_callchain_sample(machine, thread,
+						sample->callchain, parent);
+	if (ret)
+		return ret;
+
+	/* Can we do dwarf post unwind? */
+	if (!((evsel->attr.sample_type & PERF_SAMPLE_REGS_USER) &&
+	      (evsel->attr.sample_type & PERF_SAMPLE_STACK_USER)))
+		return 0;
+
+	/* Bail out if nothing was captured. */
+	if ((!sample->user_regs.regs) ||
+	    (!sample->user_stack.size))
+		return 0;
+
+	return unwind__get_entries(unwind_entry, &callchain_cursor, machine,
+				   thread, evsel->attr.sample_regs_user,
+				   sample);
+
+}
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index b7cde74..5ac5892 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -47,23 +47,32 @@
 
 typedef void (*machine__process_t)(struct machine *machine, void *data);
 
-void machines__process(struct rb_root *machines,
-		       machine__process_t process, void *data);
+struct machines {
+	struct machine host;
+	struct rb_root guests;
+};
 
-struct machine *machines__add(struct rb_root *machines, pid_t pid,
+void machines__init(struct machines *machines);
+void machines__exit(struct machines *machines);
+
+void machines__process_guests(struct machines *machines,
+			      machine__process_t process, void *data);
+
+struct machine *machines__add(struct machines *machines, pid_t pid,
 			      const char *root_dir);
-struct machine *machines__find_host(struct rb_root *machines);
-struct machine *machines__find(struct rb_root *machines, pid_t pid);
-struct machine *machines__findnew(struct rb_root *machines, pid_t pid);
+struct machine *machines__find_host(struct machines *machines);
+struct machine *machines__find(struct machines *machines, pid_t pid);
+struct machine *machines__findnew(struct machines *machines, pid_t pid);
 
-void machines__set_id_hdr_size(struct rb_root *machines, u16 id_hdr_size);
+void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size);
 char *machine__mmap_name(struct machine *machine, char *bf, size_t size);
 
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid);
 void machine__exit(struct machine *machine);
+void machine__delete_dead_threads(struct machine *machine);
+void machine__delete_threads(struct machine *machine);
 void machine__delete(struct machine *machine);
 
-
 struct branch_info *machine__resolve_bstack(struct machine *machine,
 					    struct thread *thread,
 					    struct branch_stack *bs);
@@ -129,19 +138,19 @@
 int machine__load_vmlinux_path(struct machine *machine, enum map_type type,
 			       symbol_filter_t filter);
 
-size_t machine__fprintf_dsos_buildid(struct machine *machine,
-				     FILE *fp, bool with_hits);
-size_t machines__fprintf_dsos(struct rb_root *machines, FILE *fp);
-size_t machines__fprintf_dsos_buildid(struct rb_root *machines,
-				      FILE *fp, bool with_hits);
+size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp,
+				     bool (skip)(struct dso *dso, int parm), int parm);
+size_t machines__fprintf_dsos(struct machines *machines, FILE *fp);
+size_t machines__fprintf_dsos_buildid(struct machines *machines, FILE *fp,
+				     bool (skip)(struct dso *dso, int parm), int parm);
 
 void machine__destroy_kernel_maps(struct machine *machine);
 int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel);
 int machine__create_kernel_maps(struct machine *machine);
 
-int machines__create_kernel_maps(struct rb_root *machines, pid_t pid);
-int machines__create_guest_kernel_maps(struct rb_root *machines);
-void machines__destroy_guest_kernel_maps(struct rb_root *machines);
+int machines__create_kernel_maps(struct machines *machines, pid_t pid);
+int machines__create_guest_kernel_maps(struct machines *machines);
+void machines__destroy_kernel_maps(struct machines *machines);
 
 size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp);
 
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 0328d45..6fcb9de 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -11,6 +11,7 @@
 #include "strlist.h"
 #include "vdso.h"
 #include "build-id.h"
+#include <linux/string.h>
 
 const char *map_type__name[MAP__NR_TYPES] = {
 	[MAP__FUNCTION] = "Functions",
@@ -19,7 +20,8 @@
 
 static inline int is_anon_memory(const char *filename)
 {
-	return strcmp(filename, "//anon") == 0;
+	return !strcmp(filename, "//anon") ||
+	       !strcmp(filename, "/anon_hugepage (deleted)");
 }
 
 static inline int is_no_dso_memory(const char *filename)
@@ -28,29 +30,29 @@
 	       !strcmp(filename, "[heap]");
 }
 
-void map__init(struct map *self, enum map_type type,
+void map__init(struct map *map, enum map_type type,
 	       u64 start, u64 end, u64 pgoff, struct dso *dso)
 {
-	self->type     = type;
-	self->start    = start;
-	self->end      = end;
-	self->pgoff    = pgoff;
-	self->dso      = dso;
-	self->map_ip   = map__map_ip;
-	self->unmap_ip = map__unmap_ip;
-	RB_CLEAR_NODE(&self->rb_node);
-	self->groups   = NULL;
-	self->referenced = false;
-	self->erange_warned = false;
+	map->type     = type;
+	map->start    = start;
+	map->end      = end;
+	map->pgoff    = pgoff;
+	map->dso      = dso;
+	map->map_ip   = map__map_ip;
+	map->unmap_ip = map__unmap_ip;
+	RB_CLEAR_NODE(&map->rb_node);
+	map->groups   = NULL;
+	map->referenced = false;
+	map->erange_warned = false;
 }
 
 struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 		     u64 pgoff, u32 pid, char *filename,
 		     enum map_type type)
 {
-	struct map *self = malloc(sizeof(*self));
+	struct map *map = malloc(sizeof(*map));
 
-	if (self != NULL) {
+	if (map != NULL) {
 		char newfilename[PATH_MAX];
 		struct dso *dso;
 		int anon, no_dso, vdso;
@@ -73,10 +75,10 @@
 		if (dso == NULL)
 			goto out_delete;
 
-		map__init(self, type, start, start + len, pgoff, dso);
+		map__init(map, type, start, start + len, pgoff, dso);
 
 		if (anon || no_dso) {
-			self->map_ip = self->unmap_ip = identity__map_ip;
+			map->map_ip = map->unmap_ip = identity__map_ip;
 
 			/*
 			 * Set memory without DSO as loaded. All map__find_*
@@ -84,12 +86,12 @@
 			 * unnecessary map__load warning.
 			 */
 			if (no_dso)
-				dso__set_loaded(dso, self->type);
+				dso__set_loaded(dso, map->type);
 		}
 	}
-	return self;
+	return map;
 out_delete:
-	free(self);
+	free(map);
 	return NULL;
 }
 
@@ -112,48 +114,48 @@
 	return map;
 }
 
-void map__delete(struct map *self)
+void map__delete(struct map *map)
 {
-	free(self);
+	free(map);
 }
 
-void map__fixup_start(struct map *self)
+void map__fixup_start(struct map *map)
 {
-	struct rb_root *symbols = &self->dso->symbols[self->type];
+	struct rb_root *symbols = &map->dso->symbols[map->type];
 	struct rb_node *nd = rb_first(symbols);
 	if (nd != NULL) {
 		struct symbol *sym = rb_entry(nd, struct symbol, rb_node);
-		self->start = sym->start;
+		map->start = sym->start;
 	}
 }
 
-void map__fixup_end(struct map *self)
+void map__fixup_end(struct map *map)
 {
-	struct rb_root *symbols = &self->dso->symbols[self->type];
+	struct rb_root *symbols = &map->dso->symbols[map->type];
 	struct rb_node *nd = rb_last(symbols);
 	if (nd != NULL) {
 		struct symbol *sym = rb_entry(nd, struct symbol, rb_node);
-		self->end = sym->end;
+		map->end = sym->end;
 	}
 }
 
 #define DSO__DELETED "(deleted)"
 
-int map__load(struct map *self, symbol_filter_t filter)
+int map__load(struct map *map, symbol_filter_t filter)
 {
-	const char *name = self->dso->long_name;
+	const char *name = map->dso->long_name;
 	int nr;
 
-	if (dso__loaded(self->dso, self->type))
+	if (dso__loaded(map->dso, map->type))
 		return 0;
 
-	nr = dso__load(self->dso, self, filter);
+	nr = dso__load(map->dso, map, filter);
 	if (nr < 0) {
-		if (self->dso->has_build_id) {
+		if (map->dso->has_build_id) {
 			char sbuild_id[BUILD_ID_SIZE * 2 + 1];
 
-			build_id__sprintf(self->dso->build_id,
-					  sizeof(self->dso->build_id),
+			build_id__sprintf(map->dso->build_id,
+					  sizeof(map->dso->build_id),
 					  sbuild_id);
 			pr_warning("%s with build id %s not found",
 				   name, sbuild_id);
@@ -183,43 +185,36 @@
 	 * Only applies to the kernel, as its symtabs aren't relative like the
 	 * module ones.
 	 */
-	if (self->dso->kernel)
-		map__reloc_vmlinux(self);
+	if (map->dso->kernel)
+		map__reloc_vmlinux(map);
 
 	return 0;
 }
 
-struct symbol *map__find_symbol(struct map *self, u64 addr,
+struct symbol *map__find_symbol(struct map *map, u64 addr,
 				symbol_filter_t filter)
 {
-	if (map__load(self, filter) < 0)
+	if (map__load(map, filter) < 0)
 		return NULL;
 
-	return dso__find_symbol(self->dso, self->type, addr);
+	return dso__find_symbol(map->dso, map->type, addr);
 }
 
-struct symbol *map__find_symbol_by_name(struct map *self, const char *name,
+struct symbol *map__find_symbol_by_name(struct map *map, const char *name,
 					symbol_filter_t filter)
 {
-	if (map__load(self, filter) < 0)
+	if (map__load(map, filter) < 0)
 		return NULL;
 
-	if (!dso__sorted_by_name(self->dso, self->type))
-		dso__sort_by_name(self->dso, self->type);
+	if (!dso__sorted_by_name(map->dso, map->type))
+		dso__sort_by_name(map->dso, map->type);
 
-	return dso__find_symbol_by_name(self->dso, self->type, name);
+	return dso__find_symbol_by_name(map->dso, map->type, name);
 }
 
-struct map *map__clone(struct map *self)
+struct map *map__clone(struct map *map)
 {
-	struct map *map = malloc(sizeof(*self));
-
-	if (!map)
-		return NULL;
-
-	memcpy(map, self, sizeof(*self));
-
-	return map;
+	return memdup(map, sizeof(*map));
 }
 
 int map__overlap(struct map *l, struct map *r)
@@ -236,10 +231,10 @@
 	return 0;
 }
 
-size_t map__fprintf(struct map *self, FILE *fp)
+size_t map__fprintf(struct map *map, FILE *fp)
 {
 	return fprintf(fp, " %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s\n",
-		       self->start, self->end, self->pgoff, self->dso->name);
+		       map->start, map->end, map->pgoff, map->dso->name);
 }
 
 size_t map__fprintf_dsoname(struct map *map, FILE *fp)
@@ -527,9 +522,9 @@
 	return ip - (s64)map->pgoff;
 }
 
-void map__reloc_vmlinux(struct map *self)
+void map__reloc_vmlinux(struct map *map)
 {
-	struct kmap *kmap = map__kmap(self);
+	struct kmap *kmap = map__kmap(map);
 	s64 reloc;
 
 	if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->unrelocated_addr)
@@ -541,9 +536,9 @@
 	if (!reloc)
 		return;
 
-	self->map_ip   = map__reloc_map_ip;
-	self->unmap_ip = map__reloc_unmap_ip;
-	self->pgoff    = reloc;
+	map->map_ip   = map__reloc_map_ip;
+	map->unmap_ip = map__reloc_unmap_ip;
+	map->pgoff    = reloc;
 }
 
 void maps__insert(struct rb_root *maps, struct map *map)
@@ -566,9 +561,9 @@
 	rb_insert_color(&map->rb_node, maps);
 }
 
-void maps__remove(struct rb_root *self, struct map *map)
+void maps__remove(struct rb_root *maps, struct map *map)
 {
-	rb_erase(&map->rb_node, self);
+	rb_erase(&map->rb_node, maps);
 }
 
 struct map *maps__find(struct rb_root *maps, u64 ip)
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index bcb39e2..a887f2c 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -57,9 +57,9 @@
 	struct machine	 *machine;
 };
 
-static inline struct kmap *map__kmap(struct map *self)
+static inline struct kmap *map__kmap(struct map *map)
 {
-	return (struct kmap *)(self + 1);
+	return (struct kmap *)(map + 1);
 }
 
 static inline u64 map__map_ip(struct map *map, u64 ip)
@@ -85,27 +85,27 @@
 
 typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym);
 
-void map__init(struct map *self, enum map_type type,
+void map__init(struct map *map, enum map_type type,
 	       u64 start, u64 end, u64 pgoff, struct dso *dso);
 struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 		     u64 pgoff, u32 pid, char *filename,
 		     enum map_type type);
 struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
-void map__delete(struct map *self);
-struct map *map__clone(struct map *self);
+void map__delete(struct map *map);
+struct map *map__clone(struct map *map);
 int map__overlap(struct map *l, struct map *r);
-size_t map__fprintf(struct map *self, FILE *fp);
+size_t map__fprintf(struct map *map, FILE *fp);
 size_t map__fprintf_dsoname(struct map *map, FILE *fp);
 
-int map__load(struct map *self, symbol_filter_t filter);
-struct symbol *map__find_symbol(struct map *self,
+int map__load(struct map *map, symbol_filter_t filter);
+struct symbol *map__find_symbol(struct map *map,
 				u64 addr, symbol_filter_t filter);
-struct symbol *map__find_symbol_by_name(struct map *self, const char *name,
+struct symbol *map__find_symbol_by_name(struct map *map, const char *name,
 					symbol_filter_t filter);
-void map__fixup_start(struct map *self);
-void map__fixup_end(struct map *self);
+void map__fixup_start(struct map *map);
+void map__fixup_end(struct map *map);
 
-void map__reloc_vmlinux(struct map *self);
+void map__reloc_vmlinux(struct map *map);
 
 size_t __map_groups__fprintf_maps(struct map_groups *mg,
 				  enum map_type type, int verbose, FILE *fp);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 2d8d53be..c84f48c 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -380,8 +380,8 @@
 	return 0;
 }
 
-static int add_tracepoint_multi(struct list_head **list, int *idx,
-				char *sys_name, char *evt_name)
+static int add_tracepoint_multi_event(struct list_head **list, int *idx,
+				      char *sys_name, char *evt_name)
 {
 	char evt_path[MAXPATHLEN];
 	struct dirent *evt_ent;
@@ -408,6 +408,47 @@
 		ret = add_tracepoint(list, idx, sys_name, evt_ent->d_name);
 	}
 
+	closedir(evt_dir);
+	return ret;
+}
+
+static int add_tracepoint_event(struct list_head **list, int *idx,
+				char *sys_name, char *evt_name)
+{
+	return strpbrk(evt_name, "*?") ?
+	       add_tracepoint_multi_event(list, idx, sys_name, evt_name) :
+	       add_tracepoint(list, idx, sys_name, evt_name);
+}
+
+static int add_tracepoint_multi_sys(struct list_head **list, int *idx,
+				    char *sys_name, char *evt_name)
+{
+	struct dirent *events_ent;
+	DIR *events_dir;
+	int ret = 0;
+
+	events_dir = opendir(tracing_events_path);
+	if (!events_dir) {
+		perror("Can't open event dir");
+		return -1;
+	}
+
+	while (!ret && (events_ent = readdir(events_dir))) {
+		if (!strcmp(events_ent->d_name, ".")
+		    || !strcmp(events_ent->d_name, "..")
+		    || !strcmp(events_ent->d_name, "enable")
+		    || !strcmp(events_ent->d_name, "header_event")
+		    || !strcmp(events_ent->d_name, "header_page"))
+			continue;
+
+		if (!strglobmatch(events_ent->d_name, sys_name))
+			continue;
+
+		ret = add_tracepoint_event(list, idx, events_ent->d_name,
+					   evt_name);
+	}
+
+	closedir(events_dir);
 	return ret;
 }
 
@@ -420,9 +461,10 @@
 	if (ret)
 		return ret;
 
-	return strpbrk(event, "*?") ?
-	       add_tracepoint_multi(list, idx, sys, event) :
-	       add_tracepoint(list, idx, sys, event);
+	if (strpbrk(sys, "*?"))
+		return add_tracepoint_multi_sys(list, idx, sys, event);
+	else
+		return add_tracepoint_event(list, idx, sys, event);
 }
 
 static int
@@ -492,7 +534,7 @@
 }
 
 static int config_term(struct perf_event_attr *attr,
-		       struct parse_events__term *term)
+		       struct parse_events_term *term)
 {
 #define CHECK_TYPE_VAL(type)					\
 do {								\
@@ -537,7 +579,7 @@
 static int config_attr(struct perf_event_attr *attr,
 		       struct list_head *head, int fail)
 {
-	struct parse_events__term *term;
+	struct parse_events_term *term;
 
 	list_for_each_entry(term, head, list)
 		if (config_term(attr, term) && fail)
@@ -563,14 +605,14 @@
 	return add_event(list, idx, &attr, NULL);
 }
 
-static int parse_events__is_name_term(struct parse_events__term *term)
+static int parse_events__is_name_term(struct parse_events_term *term)
 {
 	return term->type_term == PARSE_EVENTS__TERM_TYPE_NAME;
 }
 
 static char *pmu_event_name(struct list_head *head_terms)
 {
-	struct parse_events__term *term;
+	struct parse_events_term *term;
 
 	list_for_each_entry(term, head_terms, list)
 		if (parse_events__is_name_term(term))
@@ -657,14 +699,6 @@
 	int exclude = eu | ek | eh;
 	int exclude_GH = evsel ? evsel->exclude_GH : 0;
 
-	/*
-	 * We are here for group and 'GH' was not set as event
-	 * modifier and whatever event/group modifier override
-	 * default 'GH' setup.
-	 */
-	if (evsel && !exclude_GH)
-		eH = eG = 0;
-
 	memset(mod, 0, sizeof(*mod));
 
 	while (*str) {
@@ -814,7 +848,7 @@
  */
 int parse_events_terms(struct list_head *terms, const char *str)
 {
-	struct parse_events_data__terms data = {
+	struct parse_events_terms data = {
 		.terms = NULL,
 	};
 	int ret;
@@ -830,10 +864,9 @@
 	return ret;
 }
 
-int parse_events(struct perf_evlist *evlist, const char *str,
-		 int unset __maybe_unused)
+int parse_events(struct perf_evlist *evlist, const char *str)
 {
-	struct parse_events_data__events data = {
+	struct parse_events_evlist data = {
 		.list = LIST_HEAD_INIT(data.list),
 		.idx  = evlist->nr_entries,
 	};
@@ -843,6 +876,7 @@
 	if (!ret) {
 		int entries = data.idx - evlist->nr_entries;
 		perf_evlist__splice_list_tail(evlist, &data.list, entries);
+		evlist->nr_groups += data.nr_groups;
 		return 0;
 	}
 
@@ -858,7 +892,7 @@
 			int unset __maybe_unused)
 {
 	struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
-	int ret = parse_events(evlist, str, unset);
+	int ret = parse_events(evlist, str);
 
 	if (ret) {
 		fprintf(stderr, "invalid or unsupported event: '%s'\n", str);
@@ -1121,16 +1155,16 @@
 	print_tracepoint_events(NULL, NULL, name_only);
 }
 
-int parse_events__is_hardcoded_term(struct parse_events__term *term)
+int parse_events__is_hardcoded_term(struct parse_events_term *term)
 {
 	return term->type_term != PARSE_EVENTS__TERM_TYPE_USER;
 }
 
-static int new_term(struct parse_events__term **_term, int type_val,
+static int new_term(struct parse_events_term **_term, int type_val,
 		    int type_term, char *config,
 		    char *str, u64 num)
 {
-	struct parse_events__term *term;
+	struct parse_events_term *term;
 
 	term = zalloc(sizeof(*term));
 	if (!term)
@@ -1156,21 +1190,21 @@
 	return 0;
 }
 
-int parse_events__term_num(struct parse_events__term **term,
+int parse_events_term__num(struct parse_events_term **term,
 			   int type_term, char *config, u64 num)
 {
 	return new_term(term, PARSE_EVENTS__TERM_TYPE_NUM, type_term,
 			config, NULL, num);
 }
 
-int parse_events__term_str(struct parse_events__term **term,
+int parse_events_term__str(struct parse_events_term **term,
 			   int type_term, char *config, char *str)
 {
 	return new_term(term, PARSE_EVENTS__TERM_TYPE_STR, type_term,
 			config, str, 0);
 }
 
-int parse_events__term_sym_hw(struct parse_events__term **term,
+int parse_events_term__sym_hw(struct parse_events_term **term,
 			      char *config, unsigned idx)
 {
 	struct event_symbol *sym;
@@ -1188,8 +1222,8 @@
 				(char *) "event", (char *) sym->symbol, 0);
 }
 
-int parse_events__term_clone(struct parse_events__term **new,
-			     struct parse_events__term *term)
+int parse_events_term__clone(struct parse_events_term **new,
+			     struct parse_events_term *term)
 {
 	return new_term(new, term->type_val, term->type_term, term->config,
 			term->val.str, term->val.num);
@@ -1197,7 +1231,7 @@
 
 void parse_events__free_terms(struct list_head *terms)
 {
-	struct parse_events__term *term, *h;
+	struct parse_events_term *term, *h;
 
 	list_for_each_entry_safe(term, h, terms, list)
 		free(term);
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index b7af80b..8a48593 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -29,8 +29,7 @@
 
 extern int parse_events_option(const struct option *opt, const char *str,
 			       int unset);
-extern int parse_events(struct perf_evlist *evlist, const char *str,
-			int unset);
+extern int parse_events(struct perf_evlist *evlist, const char *str);
 extern int parse_events_terms(struct list_head *terms, const char *str);
 extern int parse_filter(const struct option *opt, const char *str, int unset);
 
@@ -51,7 +50,7 @@
 	PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE,
 };
 
-struct parse_events__term {
+struct parse_events_term {
 	char *config;
 	union {
 		char *str;
@@ -62,24 +61,25 @@
 	struct list_head list;
 };
 
-struct parse_events_data__events {
+struct parse_events_evlist {
 	struct list_head list;
 	int idx;
+	int nr_groups;
 };
 
-struct parse_events_data__terms {
+struct parse_events_terms {
 	struct list_head *terms;
 };
 
-int parse_events__is_hardcoded_term(struct parse_events__term *term);
-int parse_events__term_num(struct parse_events__term **_term,
+int parse_events__is_hardcoded_term(struct parse_events_term *term);
+int parse_events_term__num(struct parse_events_term **_term,
 			   int type_term, char *config, u64 num);
-int parse_events__term_str(struct parse_events__term **_term,
+int parse_events_term__str(struct parse_events_term **_term,
 			   int type_term, char *config, char *str);
-int parse_events__term_sym_hw(struct parse_events__term **term,
+int parse_events_term__sym_hw(struct parse_events_term **term,
 			      char *config, unsigned idx);
-int parse_events__term_clone(struct parse_events__term **new,
-			     struct parse_events__term *term);
+int parse_events_term__clone(struct parse_events_term **new,
+			     struct parse_events_term *term);
 void parse_events__free_terms(struct list_head *terms);
 int parse_events__modifier_event(struct list_head *list, char *str, bool add);
 int parse_events__modifier_group(struct list_head *list, char *event_mod);
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 0f9914a..afc44c1 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -1,5 +1,4 @@
 %pure-parser
-%name-prefix "parse_events_"
 %parse-param {void *_data}
 %parse-param {void *scanner}
 %lex-param {void* scanner}
@@ -23,6 +22,14 @@
 		YYABORT; \
 } while (0)
 
+static inc_group_count(struct list_head *list,
+		       struct parse_events_evlist *data)
+{
+	/* Count groups only have more than 1 members */
+	if (!list_is_last(list->next, list))
+		data->nr_groups++;
+}
+
 %}
 
 %token PE_START_EVENTS PE_START_TERMS
@@ -68,7 +75,7 @@
 	char *str;
 	u64 num;
 	struct list_head *head;
-	struct parse_events__term *term;
+	struct parse_events_term *term;
 }
 %%
 
@@ -79,7 +86,7 @@
 
 start_events: groups
 {
-	struct parse_events_data__events *data = _data;
+	struct parse_events_evlist *data = _data;
 
 	parse_events_update_lists($1, &data->list);
 }
@@ -123,6 +130,7 @@
 {
 	struct list_head *list = $3;
 
+	inc_group_count(list, _data);
 	parse_events__set_leader($1, list);
 	$$ = list;
 }
@@ -131,6 +139,7 @@
 {
 	struct list_head *list = $2;
 
+	inc_group_count(list, _data);
 	parse_events__set_leader(NULL, list);
 	$$ = list;
 }
@@ -186,7 +195,7 @@
 event_pmu:
 PE_NAME '/' event_config '/'
 {
-	struct parse_events_data__events *data = _data;
+	struct parse_events_evlist *data = _data;
 	struct list_head *list = NULL;
 
 	ABORT_ON(parse_events_add_pmu(&list, &data->idx, $1, $3));
@@ -202,7 +211,7 @@
 event_legacy_symbol:
 value_sym '/' event_config '/'
 {
-	struct parse_events_data__events *data = _data;
+	struct parse_events_evlist *data = _data;
 	struct list_head *list = NULL;
 	int type = $1 >> 16;
 	int config = $1 & 255;
@@ -215,7 +224,7 @@
 |
 value_sym sep_slash_dc
 {
-	struct parse_events_data__events *data = _data;
+	struct parse_events_evlist *data = _data;
 	struct list_head *list = NULL;
 	int type = $1 >> 16;
 	int config = $1 & 255;
@@ -228,7 +237,7 @@
 event_legacy_cache:
 PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT
 {
-	struct parse_events_data__events *data = _data;
+	struct parse_events_evlist *data = _data;
 	struct list_head *list = NULL;
 
 	ABORT_ON(parse_events_add_cache(&list, &data->idx, $1, $3, $5));
@@ -237,7 +246,7 @@
 |
 PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT
 {
-	struct parse_events_data__events *data = _data;
+	struct parse_events_evlist *data = _data;
 	struct list_head *list = NULL;
 
 	ABORT_ON(parse_events_add_cache(&list, &data->idx, $1, $3, NULL));
@@ -246,7 +255,7 @@
 |
 PE_NAME_CACHE_TYPE
 {
-	struct parse_events_data__events *data = _data;
+	struct parse_events_evlist *data = _data;
 	struct list_head *list = NULL;
 
 	ABORT_ON(parse_events_add_cache(&list, &data->idx, $1, NULL, NULL));
@@ -256,7 +265,7 @@
 event_legacy_mem:
 PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc
 {
-	struct parse_events_data__events *data = _data;
+	struct parse_events_evlist *data = _data;
 	struct list_head *list = NULL;
 
 	ABORT_ON(parse_events_add_breakpoint(&list, &data->idx,
@@ -266,7 +275,7 @@
 |
 PE_PREFIX_MEM PE_VALUE sep_dc
 {
-	struct parse_events_data__events *data = _data;
+	struct parse_events_evlist *data = _data;
 	struct list_head *list = NULL;
 
 	ABORT_ON(parse_events_add_breakpoint(&list, &data->idx,
@@ -277,7 +286,7 @@
 event_legacy_tracepoint:
 PE_NAME ':' PE_NAME
 {
-	struct parse_events_data__events *data = _data;
+	struct parse_events_evlist *data = _data;
 	struct list_head *list = NULL;
 
 	ABORT_ON(parse_events_add_tracepoint(&list, &data->idx, $1, $3));
@@ -287,7 +296,7 @@
 event_legacy_numeric:
 PE_VALUE ':' PE_VALUE
 {
-	struct parse_events_data__events *data = _data;
+	struct parse_events_evlist *data = _data;
 	struct list_head *list = NULL;
 
 	ABORT_ON(parse_events_add_numeric(&list, &data->idx, (u32)$1, $3, NULL));
@@ -297,7 +306,7 @@
 event_legacy_raw:
 PE_RAW
 {
-	struct parse_events_data__events *data = _data;
+	struct parse_events_evlist *data = _data;
 	struct list_head *list = NULL;
 
 	ABORT_ON(parse_events_add_numeric(&list, &data->idx,
@@ -307,7 +316,7 @@
 
 start_terms: event_config
 {
-	struct parse_events_data__terms *data = _data;
+	struct parse_events_terms *data = _data;
 	data->terms = $1;
 }
 
@@ -315,7 +324,7 @@
 event_config ',' event_term
 {
 	struct list_head *head = $1;
-	struct parse_events__term *term = $3;
+	struct parse_events_term *term = $3;
 
 	ABORT_ON(!head);
 	list_add_tail(&term->list, head);
@@ -325,7 +334,7 @@
 event_term
 {
 	struct list_head *head = malloc(sizeof(*head));
-	struct parse_events__term *term = $1;
+	struct parse_events_term *term = $1;
 
 	ABORT_ON(!head);
 	INIT_LIST_HEAD(head);
@@ -336,70 +345,70 @@
 event_term:
 PE_NAME '=' PE_NAME
 {
-	struct parse_events__term *term;
+	struct parse_events_term *term;
 
-	ABORT_ON(parse_events__term_str(&term, PARSE_EVENTS__TERM_TYPE_USER,
+	ABORT_ON(parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER,
 					$1, $3));
 	$$ = term;
 }
 |
 PE_NAME '=' PE_VALUE
 {
-	struct parse_events__term *term;
+	struct parse_events_term *term;
 
-	ABORT_ON(parse_events__term_num(&term, PARSE_EVENTS__TERM_TYPE_USER,
+	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
 					$1, $3));
 	$$ = term;
 }
 |
 PE_NAME '=' PE_VALUE_SYM_HW
 {
-	struct parse_events__term *term;
+	struct parse_events_term *term;
 	int config = $3 & 255;
 
-	ABORT_ON(parse_events__term_sym_hw(&term, $1, config));
+	ABORT_ON(parse_events_term__sym_hw(&term, $1, config));
 	$$ = term;
 }
 |
 PE_NAME
 {
-	struct parse_events__term *term;
+	struct parse_events_term *term;
 
-	ABORT_ON(parse_events__term_num(&term, PARSE_EVENTS__TERM_TYPE_USER,
+	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
 					$1, 1));
 	$$ = term;
 }
 |
 PE_VALUE_SYM_HW
 {
-	struct parse_events__term *term;
+	struct parse_events_term *term;
 	int config = $1 & 255;
 
-	ABORT_ON(parse_events__term_sym_hw(&term, NULL, config));
+	ABORT_ON(parse_events_term__sym_hw(&term, NULL, config));
 	$$ = term;
 }
 |
 PE_TERM '=' PE_NAME
 {
-	struct parse_events__term *term;
+	struct parse_events_term *term;
 
-	ABORT_ON(parse_events__term_str(&term, (int)$1, NULL, $3));
+	ABORT_ON(parse_events_term__str(&term, (int)$1, NULL, $3));
 	$$ = term;
 }
 |
 PE_TERM '=' PE_VALUE
 {
-	struct parse_events__term *term;
+	struct parse_events_term *term;
 
-	ABORT_ON(parse_events__term_num(&term, (int)$1, NULL, $3));
+	ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, $3));
 	$$ = term;
 }
 |
 PE_TERM
 {
-	struct parse_events__term *term;
+	struct parse_events_term *term;
 
-	ABORT_ON(parse_events__term_num(&term, (int)$1, NULL, 1));
+	ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1));
 	$$ = term;
 }
 
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 9bdc60c..4c6f9c4 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1,4 +1,3 @@
-
 #include <linux/list.h>
 #include <sys/types.h>
 #include <sys/stat.h>
@@ -11,6 +10,19 @@
 #include "parse-events.h"
 #include "cpumap.h"
 
+struct perf_pmu_alias {
+	char *name;
+	struct list_head terms;
+	struct list_head list;
+};
+
+struct perf_pmu_format {
+	char *name;
+	int value;
+	DECLARE_BITMAP(bits, PERF_PMU_FORMAT_BITS);
+	struct list_head list;
+};
+
 #define EVENT_SOURCE_DEVICE_PATH "/bus/event_source/devices/"
 
 int perf_pmu_parse(struct list_head *list, char *name);
@@ -85,7 +97,7 @@
 
 static int perf_pmu__new_alias(struct list_head *list, char *name, FILE *file)
 {
-	struct perf_pmu__alias *alias;
+	struct perf_pmu_alias *alias;
 	char buf[256];
 	int ret;
 
@@ -172,15 +184,15 @@
 	return 0;
 }
 
-static int pmu_alias_terms(struct perf_pmu__alias *alias,
+static int pmu_alias_terms(struct perf_pmu_alias *alias,
 			   struct list_head *terms)
 {
-	struct parse_events__term *term, *clone;
+	struct parse_events_term *term, *clone;
 	LIST_HEAD(list);
 	int ret;
 
 	list_for_each_entry(term, &alias->terms, list) {
-		ret = parse_events__term_clone(&clone, term);
+		ret = parse_events_term__clone(&clone, term);
 		if (ret) {
 			parse_events__free_terms(&list);
 			return ret;
@@ -360,10 +372,10 @@
 	return pmu_lookup(name);
 }
 
-static struct perf_pmu__format*
+static struct perf_pmu_format *
 pmu_find_format(struct list_head *formats, char *name)
 {
-	struct perf_pmu__format *format;
+	struct perf_pmu_format *format;
 
 	list_for_each_entry(format, formats, list)
 		if (!strcmp(format->name, name))
@@ -403,9 +415,9 @@
  */
 static int pmu_config_term(struct list_head *formats,
 			   struct perf_event_attr *attr,
-			   struct parse_events__term *term)
+			   struct parse_events_term *term)
 {
-	struct perf_pmu__format *format;
+	struct perf_pmu_format *format;
 	__u64 *vp;
 
 	/*
@@ -450,7 +462,7 @@
 			   struct perf_event_attr *attr,
 			   struct list_head *head_terms)
 {
-	struct parse_events__term *term;
+	struct parse_events_term *term;
 
 	list_for_each_entry(term, head_terms, list)
 		if (pmu_config_term(formats, attr, term))
@@ -471,10 +483,10 @@
 	return perf_pmu__config_terms(&pmu->format, attr, head_terms);
 }
 
-static struct perf_pmu__alias *pmu_find_alias(struct perf_pmu *pmu,
-					      struct parse_events__term *term)
+static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
+					     struct parse_events_term *term)
 {
-	struct perf_pmu__alias *alias;
+	struct perf_pmu_alias *alias;
 	char *name;
 
 	if (parse_events__is_hardcoded_term(term))
@@ -507,8 +519,8 @@
  */
 int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms)
 {
-	struct parse_events__term *term, *h;
-	struct perf_pmu__alias *alias;
+	struct parse_events_term *term, *h;
+	struct perf_pmu_alias *alias;
 	int ret;
 
 	list_for_each_entry_safe(term, h, head_terms, list) {
@@ -527,7 +539,7 @@
 int perf_pmu__new_format(struct list_head *list, char *name,
 			 int config, unsigned long *bits)
 {
-	struct perf_pmu__format *format;
+	struct perf_pmu_format *format;
 
 	format = zalloc(sizeof(*format));
 	if (!format)
@@ -548,7 +560,7 @@
 	if (!to)
 		to = from;
 
-	memset(bits, 0, BITS_TO_LONGS(PERF_PMU_FORMAT_BITS));
+	memset(bits, 0, BITS_TO_BYTES(PERF_PMU_FORMAT_BITS));
 	for (b = from; b <= to; b++)
 		set_bit(b, bits);
 }
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index a313ed7..32fe55b 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -12,19 +12,6 @@
 
 #define PERF_PMU_FORMAT_BITS 64
 
-struct perf_pmu__format {
-	char *name;
-	int value;
-	DECLARE_BITMAP(bits, PERF_PMU_FORMAT_BITS);
-	struct list_head list;
-};
-
-struct perf_pmu__alias {
-	char *name;
-	struct list_head terms;
-	struct list_head list;
-};
-
 struct perf_pmu {
 	char *name;
 	__u32 type;
@@ -42,7 +29,7 @@
 			   struct list_head *head_terms);
 int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms);
 struct list_head *perf_pmu__alias(struct perf_pmu *pmu,
-				struct list_head *head_terms);
+				  struct list_head *head_terms);
 int perf_pmu_wrap(void);
 void perf_pmu_error(struct list_head *list, char *name, char const *msg);
 
diff --git a/tools/perf/util/pmu.y b/tools/perf/util/pmu.y
index ec89804..bfd7e850 100644
--- a/tools/perf/util/pmu.y
+++ b/tools/perf/util/pmu.y
@@ -1,5 +1,4 @@
 
-%name-prefix "perf_pmu_"
 %parse-param {struct list_head *format}
 %parse-param {char *name}
 
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 1daf5c1..be03293 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -413,12 +413,12 @@
 				   dwarf_diename(vr_die), dwarf_diename(&type));
 			return -EINVAL;
 		}
+		if (die_get_real_type(&type, &type) == NULL) {
+			pr_warning("Failed to get a type"
+				   " information.\n");
+			return -ENOENT;
+		}
 		if (ret == DW_TAG_pointer_type) {
-			if (die_get_real_type(&type, &type) == NULL) {
-				pr_warning("Failed to get a type"
-					   " information.\n");
-				return -ENOENT;
-			}
 			while (*ref_ptr)
 				ref_ptr = &(*ref_ptr)->next;
 			/* Add new reference with offset +0 */
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index c40c2d3..64536a9 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -18,4 +18,5 @@
 util/debugfs.c
 util/rblist.c
 util/strlist.c
+util/sysfs.c
 ../../lib/rbtree.c
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index a2657fd..925e0c3 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -1045,3 +1045,12 @@
 	if (PyErr_Occurred())
 		PyErr_SetString(PyExc_ImportError, "perf: Init failed!");
 }
+
+/*
+ * Dummy, to avoid dragging all the test_attr infrastructure in the python
+ * binding.
+ */
+void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
+                     int fd, int group_fd, unsigned long flags)
+{
+}
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index f80605e..eacec85 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -292,6 +292,7 @@
 	ns = nsecs - s * NSECS_PER_SEC;
 
 	scripting_context->event_data = data;
+	scripting_context->pevent = evsel->tp_format->pevent;
 
 	ENTER;
 	SAVETMPS;
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 14683df..e87aa5d 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -265,6 +265,7 @@
 	ns = nsecs - s * NSECS_PER_SEC;
 
 	scripting_context->event_data = data;
+	scripting_context->pevent = evsel->tp_format->pevent;
 
 	context = PyCObject_FromVoidPtr(scripting_context, NULL);
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index ce6f511..bd85280b 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -16,7 +16,6 @@
 #include "cpumap.h"
 #include "event-parse.h"
 #include "perf_regs.h"
-#include "unwind.h"
 #include "vdso.h"
 
 static int perf_session__open(struct perf_session *self, bool force)
@@ -87,13 +86,12 @@
 {
 	u16 id_hdr_size = perf_evlist__id_hdr_size(session->evlist);
 
-	session->host_machine.id_hdr_size = id_hdr_size;
 	machines__set_id_hdr_size(&session->machines, id_hdr_size);
 }
 
 int perf_session__create_kernel_maps(struct perf_session *self)
 {
-	int ret = machine__create_kernel_maps(&self->host_machine);
+	int ret = machine__create_kernel_maps(&self->machines.host);
 
 	if (ret >= 0)
 		ret = machines__create_guest_kernel_maps(&self->machines);
@@ -102,8 +100,7 @@
 
 static void perf_session__destroy_kernel_maps(struct perf_session *self)
 {
-	machine__destroy_kernel_maps(&self->host_machine);
-	machines__destroy_guest_kernel_maps(&self->machines);
+	machines__destroy_kernel_maps(&self->machines);
 }
 
 struct perf_session *perf_session__new(const char *filename, int mode,
@@ -128,22 +125,11 @@
 		goto out;
 
 	memcpy(self->filename, filename, len);
-	/*
-	 * On 64bit we can mmap the data file in one go. No need for tiny mmap
-	 * slices. On 32bit we use 32MB.
-	 */
-#if BITS_PER_LONG == 64
-	self->mmap_window = ULLONG_MAX;
-#else
-	self->mmap_window = 32 * 1024 * 1024ULL;
-#endif
-	self->machines = RB_ROOT;
 	self->repipe = repipe;
 	INIT_LIST_HEAD(&self->ordered_samples.samples);
 	INIT_LIST_HEAD(&self->ordered_samples.sample_cache);
 	INIT_LIST_HEAD(&self->ordered_samples.to_free);
-	machine__init(&self->host_machine, "", HOST_KERNEL_ID);
-	hists__init(&self->hists);
+	machines__init(&self->machines);
 
 	if (mode == O_RDONLY) {
 		if (perf_session__open(self, force) < 0)
@@ -171,37 +157,30 @@
 	return NULL;
 }
 
-static void machine__delete_dead_threads(struct machine *machine)
-{
-	struct thread *n, *t;
-
-	list_for_each_entry_safe(t, n, &machine->dead_threads, node) {
-		list_del(&t->node);
-		thread__delete(t);
-	}
-}
-
 static void perf_session__delete_dead_threads(struct perf_session *session)
 {
-	machine__delete_dead_threads(&session->host_machine);
-}
-
-static void machine__delete_threads(struct machine *self)
-{
-	struct rb_node *nd = rb_first(&self->threads);
-
-	while (nd) {
-		struct thread *t = rb_entry(nd, struct thread, rb_node);
-
-		rb_erase(&t->rb_node, &self->threads);
-		nd = rb_next(nd);
-		thread__delete(t);
-	}
+	machine__delete_dead_threads(&session->machines.host);
 }
 
 static void perf_session__delete_threads(struct perf_session *session)
 {
-	machine__delete_threads(&session->host_machine);
+	machine__delete_threads(&session->machines.host);
+}
+
+static void perf_session_env__delete(struct perf_session_env *env)
+{
+	free(env->hostname);
+	free(env->os_release);
+	free(env->version);
+	free(env->arch);
+	free(env->cpu_desc);
+	free(env->cpuid);
+
+	free(env->cmdline);
+	free(env->sibling_cores);
+	free(env->sibling_threads);
+	free(env->numa_nodes);
+	free(env->pmu_mappings);
 }
 
 void perf_session__delete(struct perf_session *self)
@@ -209,198 +188,13 @@
 	perf_session__destroy_kernel_maps(self);
 	perf_session__delete_dead_threads(self);
 	perf_session__delete_threads(self);
-	machine__exit(&self->host_machine);
+	perf_session_env__delete(&self->header.env);
+	machines__exit(&self->machines);
 	close(self->fd);
 	free(self);
 	vdso__exit();
 }
 
-void machine__remove_thread(struct machine *self, struct thread *th)
-{
-	self->last_match = NULL;
-	rb_erase(&th->rb_node, &self->threads);
-	/*
-	 * We may have references to this thread, for instance in some hist_entry
-	 * instances, so just move them to a separate list.
-	 */
-	list_add_tail(&th->node, &self->dead_threads);
-}
-
-static bool symbol__match_parent_regex(struct symbol *sym)
-{
-	if (sym->name && !regexec(&parent_regex, sym->name, 0, NULL, 0))
-		return 1;
-
-	return 0;
-}
-
-static const u8 cpumodes[] = {
-	PERF_RECORD_MISC_USER,
-	PERF_RECORD_MISC_KERNEL,
-	PERF_RECORD_MISC_GUEST_USER,
-	PERF_RECORD_MISC_GUEST_KERNEL
-};
-#define NCPUMODES (sizeof(cpumodes)/sizeof(u8))
-
-static void ip__resolve_ams(struct machine *self, struct thread *thread,
-			    struct addr_map_symbol *ams,
-			    u64 ip)
-{
-	struct addr_location al;
-	size_t i;
-	u8 m;
-
-	memset(&al, 0, sizeof(al));
-
-	for (i = 0; i < NCPUMODES; i++) {
-		m = cpumodes[i];
-		/*
-		 * We cannot use the header.misc hint to determine whether a
-		 * branch stack address is user, kernel, guest, hypervisor.
-		 * Branches may straddle the kernel/user/hypervisor boundaries.
-		 * Thus, we have to try consecutively until we find a match
-		 * or else, the symbol is unknown
-		 */
-		thread__find_addr_location(thread, self, m, MAP__FUNCTION,
-				ip, &al, NULL);
-		if (al.sym)
-			goto found;
-	}
-found:
-	ams->addr = ip;
-	ams->al_addr = al.addr;
-	ams->sym = al.sym;
-	ams->map = al.map;
-}
-
-struct branch_info *machine__resolve_bstack(struct machine *self,
-					    struct thread *thr,
-					    struct branch_stack *bs)
-{
-	struct branch_info *bi;
-	unsigned int i;
-
-	bi = calloc(bs->nr, sizeof(struct branch_info));
-	if (!bi)
-		return NULL;
-
-	for (i = 0; i < bs->nr; i++) {
-		ip__resolve_ams(self, thr, &bi[i].to, bs->entries[i].to);
-		ip__resolve_ams(self, thr, &bi[i].from, bs->entries[i].from);
-		bi[i].flags = bs->entries[i].flags;
-	}
-	return bi;
-}
-
-static int machine__resolve_callchain_sample(struct machine *machine,
-					     struct thread *thread,
-					     struct ip_callchain *chain,
-					     struct symbol **parent)
-
-{
-	u8 cpumode = PERF_RECORD_MISC_USER;
-	unsigned int i;
-	int err;
-
-	callchain_cursor_reset(&callchain_cursor);
-
-	if (chain->nr > PERF_MAX_STACK_DEPTH) {
-		pr_warning("corrupted callchain. skipping...\n");
-		return 0;
-	}
-
-	for (i = 0; i < chain->nr; i++) {
-		u64 ip;
-		struct addr_location al;
-
-		if (callchain_param.order == ORDER_CALLEE)
-			ip = chain->ips[i];
-		else
-			ip = chain->ips[chain->nr - i - 1];
-
-		if (ip >= PERF_CONTEXT_MAX) {
-			switch (ip) {
-			case PERF_CONTEXT_HV:
-				cpumode = PERF_RECORD_MISC_HYPERVISOR;
-				break;
-			case PERF_CONTEXT_KERNEL:
-				cpumode = PERF_RECORD_MISC_KERNEL;
-				break;
-			case PERF_CONTEXT_USER:
-				cpumode = PERF_RECORD_MISC_USER;
-				break;
-			default:
-				pr_debug("invalid callchain context: "
-					 "%"PRId64"\n", (s64) ip);
-				/*
-				 * It seems the callchain is corrupted.
-				 * Discard all.
-				 */
-				callchain_cursor_reset(&callchain_cursor);
-				return 0;
-			}
-			continue;
-		}
-
-		al.filtered = false;
-		thread__find_addr_location(thread, machine, cpumode,
-					   MAP__FUNCTION, ip, &al, NULL);
-		if (al.sym != NULL) {
-			if (sort__has_parent && !*parent &&
-			    symbol__match_parent_regex(al.sym))
-				*parent = al.sym;
-			if (!symbol_conf.use_callchain)
-				break;
-		}
-
-		err = callchain_cursor_append(&callchain_cursor,
-					      ip, al.map, al.sym);
-		if (err)
-			return err;
-	}
-
-	return 0;
-}
-
-static int unwind_entry(struct unwind_entry *entry, void *arg)
-{
-	struct callchain_cursor *cursor = arg;
-	return callchain_cursor_append(cursor, entry->ip,
-				       entry->map, entry->sym);
-}
-
-int machine__resolve_callchain(struct machine *machine,
-			       struct perf_evsel *evsel,
-			       struct thread *thread,
-			       struct perf_sample *sample,
-			       struct symbol **parent)
-
-{
-	int ret;
-
-	callchain_cursor_reset(&callchain_cursor);
-
-	ret = machine__resolve_callchain_sample(machine, thread,
-						sample->callchain, parent);
-	if (ret)
-		return ret;
-
-	/* Can we do dwarf post unwind? */
-	if (!((evsel->attr.sample_type & PERF_SAMPLE_REGS_USER) &&
-	      (evsel->attr.sample_type & PERF_SAMPLE_STACK_USER)))
-		return 0;
-
-	/* Bail out if nothing was captured. */
-	if ((!sample->user_regs.regs) ||
-	    (!sample->user_stack.size))
-		return 0;
-
-	return unwind__get_entries(unwind_entry, &callchain_cursor, machine,
-				   thread, evsel->attr.sample_regs_user,
-				   sample);
-
-}
-
 static int process_event_synth_tracing_data_stub(union perf_event *event
 						 __maybe_unused,
 						 struct perf_session *session
@@ -1027,7 +821,7 @@
 		return perf_session__findnew_machine(session, pid);
 	}
 
-	return perf_session__find_host_machine(session);
+	return &session->machines.host;
 }
 
 static int perf_session_deliver_event(struct perf_session *session,
@@ -1065,11 +859,11 @@
 	case PERF_RECORD_SAMPLE:
 		dump_sample(evsel, event, sample);
 		if (evsel == NULL) {
-			++session->hists.stats.nr_unknown_id;
+			++session->stats.nr_unknown_id;
 			return 0;
 		}
 		if (machine == NULL) {
-			++session->hists.stats.nr_unprocessable_samples;
+			++session->stats.nr_unprocessable_samples;
 			return 0;
 		}
 		return tool->sample(tool, event, sample, evsel, machine);
@@ -1083,7 +877,7 @@
 		return tool->exit(tool, event, sample, machine);
 	case PERF_RECORD_LOST:
 		if (tool->lost == perf_event__process_lost)
-			session->hists.stats.total_lost += event->lost.lost;
+			session->stats.total_lost += event->lost.lost;
 		return tool->lost(tool, event, sample, machine);
 	case PERF_RECORD_READ:
 		return tool->read(tool, event, sample, evsel, machine);
@@ -1092,7 +886,7 @@
 	case PERF_RECORD_UNTHROTTLE:
 		return tool->unthrottle(tool, event, sample, machine);
 	default:
-		++session->hists.stats.nr_unknown_events;
+		++session->stats.nr_unknown_events;
 		return -1;
 	}
 }
@@ -1106,8 +900,8 @@
 
 	if (!ip_callchain__valid(sample->callchain, event)) {
 		pr_debug("call-chain problem with event, skipping it.\n");
-		++session->hists.stats.nr_invalid_chains;
-		session->hists.stats.total_invalid_chains += sample->period;
+		++session->stats.nr_invalid_chains;
+		session->stats.total_invalid_chains += sample->period;
 		return -EINVAL;
 	}
 	return 0;
@@ -1165,7 +959,7 @@
 	if (event->header.type >= PERF_RECORD_HEADER_MAX)
 		return -EINVAL;
 
-	hists__inc_nr_events(&session->hists, event->header.type);
+	events_stats__inc(&session->stats, event->header.type);
 
 	if (event->header.type >= PERF_RECORD_USER_TYPE_START)
 		return perf_session__process_user_event(session, event, tool, file_offset);
@@ -1201,7 +995,7 @@
 
 struct thread *perf_session__findnew(struct perf_session *session, pid_t pid)
 {
-	return machine__findnew_thread(&session->host_machine, pid);
+	return machine__findnew_thread(&session->machines.host, pid);
 }
 
 static struct thread *perf_session__register_idle_thread(struct perf_session *self)
@@ -1220,39 +1014,39 @@
 					    const struct perf_tool *tool)
 {
 	if (tool->lost == perf_event__process_lost &&
-	    session->hists.stats.nr_events[PERF_RECORD_LOST] != 0) {
+	    session->stats.nr_events[PERF_RECORD_LOST] != 0) {
 		ui__warning("Processed %d events and lost %d chunks!\n\n"
 			    "Check IO/CPU overload!\n\n",
-			    session->hists.stats.nr_events[0],
-			    session->hists.stats.nr_events[PERF_RECORD_LOST]);
+			    session->stats.nr_events[0],
+			    session->stats.nr_events[PERF_RECORD_LOST]);
 	}
 
-	if (session->hists.stats.nr_unknown_events != 0) {
+	if (session->stats.nr_unknown_events != 0) {
 		ui__warning("Found %u unknown events!\n\n"
 			    "Is this an older tool processing a perf.data "
 			    "file generated by a more recent tool?\n\n"
 			    "If that is not the case, consider "
 			    "reporting to linux-kernel@vger.kernel.org.\n\n",
-			    session->hists.stats.nr_unknown_events);
+			    session->stats.nr_unknown_events);
 	}
 
-	if (session->hists.stats.nr_unknown_id != 0) {
+	if (session->stats.nr_unknown_id != 0) {
 		ui__warning("%u samples with id not present in the header\n",
-			    session->hists.stats.nr_unknown_id);
+			    session->stats.nr_unknown_id);
 	}
 
- 	if (session->hists.stats.nr_invalid_chains != 0) {
+ 	if (session->stats.nr_invalid_chains != 0) {
  		ui__warning("Found invalid callchains!\n\n"
  			    "%u out of %u events were discarded for this reason.\n\n"
  			    "Consider reporting to linux-kernel@vger.kernel.org.\n\n",
- 			    session->hists.stats.nr_invalid_chains,
- 			    session->hists.stats.nr_events[PERF_RECORD_SAMPLE]);
+ 			    session->stats.nr_invalid_chains,
+ 			    session->stats.nr_events[PERF_RECORD_SAMPLE]);
  	}
 
-	if (session->hists.stats.nr_unprocessable_samples != 0) {
+	if (session->stats.nr_unprocessable_samples != 0) {
 		ui__warning("%u unprocessable samples recorded.\n"
 			    "Do you have a KVM guest running and not using 'perf kvm'?\n",
-			    session->hists.stats.nr_unprocessable_samples);
+			    session->stats.nr_unprocessable_samples);
 	}
 }
 
@@ -1369,6 +1163,18 @@
 	return event;
 }
 
+/*
+ * On 64bit we can mmap the data file in one go. No need for tiny mmap
+ * slices. On 32bit we use 32MB.
+ */
+#if BITS_PER_LONG == 64
+#define MMAP_SIZE ULLONG_MAX
+#define NUM_MMAPS 1
+#else
+#define MMAP_SIZE (32 * 1024 * 1024ULL)
+#define NUM_MMAPS 128
+#endif
+
 int __perf_session__process_events(struct perf_session *session,
 				   u64 data_offset, u64 data_size,
 				   u64 file_size, struct perf_tool *tool)
@@ -1376,7 +1182,7 @@
 	u64 head, page_offset, file_offset, file_pos, progress_next;
 	int err, mmap_prot, mmap_flags, map_idx = 0;
 	size_t	mmap_size;
-	char *buf, *mmaps[8];
+	char *buf, *mmaps[NUM_MMAPS];
 	union perf_event *event;
 	uint32_t size;
 
@@ -1391,7 +1197,7 @@
 
 	progress_next = file_size / 16;
 
-	mmap_size = session->mmap_window;
+	mmap_size = MMAP_SIZE;
 	if (mmap_size > file_size)
 		mmap_size = file_size;
 
@@ -1526,16 +1332,13 @@
 
 size_t perf_session__fprintf_dsos(struct perf_session *self, FILE *fp)
 {
-	return __dsos__fprintf(&self->host_machine.kernel_dsos, fp) +
-	       __dsos__fprintf(&self->host_machine.user_dsos, fp) +
-	       machines__fprintf_dsos(&self->machines, fp);
+	return machines__fprintf_dsos(&self->machines, fp);
 }
 
 size_t perf_session__fprintf_dsos_buildid(struct perf_session *self, FILE *fp,
-					  bool with_hits)
+					  bool (skip)(struct dso *dso, int parm), int parm)
 {
-	size_t ret = machine__fprintf_dsos_buildid(&self->host_machine, fp, with_hits);
-	return ret + machines__fprintf_dsos_buildid(&self->machines, fp, with_hits);
+	return machines__fprintf_dsos_buildid(&self->machines, fp, skip, parm);
 }
 
 size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
@@ -1543,11 +1346,11 @@
 	struct perf_evsel *pos;
 	size_t ret = fprintf(fp, "Aggregated stats:\n");
 
-	ret += hists__fprintf_nr_events(&session->hists, fp);
+	ret += events_stats__fprintf(&session->stats, fp);
 
 	list_for_each_entry(pos, &session->evlist->entries, node) {
 		ret += fprintf(fp, "%s stats:\n", perf_evsel__name(pos));
-		ret += hists__fprintf_nr_events(&pos->hists, fp);
+		ret += events_stats__fprintf(&pos->hists.stats, fp);
 	}
 
 	return ret;
@@ -1559,7 +1362,7 @@
 	 * FIXME: Here we have to actually print all the machines in this
 	 * session, not just the host...
 	 */
-	return machine__fprintf(&session->host_machine, fp);
+	return machine__fprintf(&session->machines.host, fp);
 }
 
 void perf_session__remove_thread(struct perf_session *session,
@@ -1568,10 +1371,10 @@
 	/*
 	 * FIXME: This one makes no sense, we need to remove the thread from
 	 * the machine it belongs to, perf_session can have many machines, so
-	 * doing it always on ->host_machine is wrong.  Fix when auditing all
+	 * doing it always on ->machines.host is wrong.  Fix when auditing all
 	 * the 'perf kvm' code.
 	 */
-	machine__remove_thread(&session->host_machine, th);
+	machine__remove_thread(&session->machines.host, th);
 }
 
 struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index cea133a..b5c0847 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -30,16 +30,10 @@
 struct perf_session {
 	struct perf_header	header;
 	unsigned long		size;
-	unsigned long		mmap_window;
-	struct machine		host_machine;
-	struct rb_root		machines;
+	struct machines		machines;
 	struct perf_evlist	*evlist;
 	struct pevent		*pevent;
-	/*
-	 * FIXME: Need to split this up further, we need global
-	 *	  stats + per event stats.
-	 */
-	struct hists		hists;
+	struct events_stats	stats;
 	int			fd;
 	bool			fd_pipe;
 	bool			repipe;
@@ -54,7 +48,7 @@
 struct perf_session *perf_session__new(const char *filename, int mode,
 				       bool force, bool repipe,
 				       struct perf_tool *tool);
-void perf_session__delete(struct perf_session *self);
+void perf_session__delete(struct perf_session *session);
 
 void perf_event_header__bswap(struct perf_event_header *self);
 
@@ -81,43 +75,24 @@
 void perf_session__remove_thread(struct perf_session *self, struct thread *th);
 
 static inline
-struct machine *perf_session__find_host_machine(struct perf_session *self)
-{
-	return &self->host_machine;
-}
-
-static inline
 struct machine *perf_session__find_machine(struct perf_session *self, pid_t pid)
 {
-	if (pid == HOST_KERNEL_ID)
-		return &self->host_machine;
 	return machines__find(&self->machines, pid);
 }
 
 static inline
 struct machine *perf_session__findnew_machine(struct perf_session *self, pid_t pid)
 {
-	if (pid == HOST_KERNEL_ID)
-		return &self->host_machine;
 	return machines__findnew(&self->machines, pid);
 }
 
-static inline
-void perf_session__process_machines(struct perf_session *self,
-				    struct perf_tool *tool,
-				    machine__process_t process)
-{
-	process(&self->host_machine, tool);
-	return machines__process(&self->machines, process, tool);
-}
-
 struct thread *perf_session__findnew(struct perf_session *self, pid_t pid);
 size_t perf_session__fprintf(struct perf_session *self, FILE *fp);
 
 size_t perf_session__fprintf_dsos(struct perf_session *self, FILE *fp);
 
-size_t perf_session__fprintf_dsos_buildid(struct perf_session *self,
-					  FILE *fp, bool with_hits);
+size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp,
+					  bool (fn)(struct dso *dso, int parm), int parm);
 
 size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp);
 
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index cfd1c0f..d41926c 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -60,7 +60,7 @@
 static int hist_entry__thread_snprintf(struct hist_entry *self, char *bf,
 				       size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%*s:%5d", width,
+	return repsep_snprintf(bf, size, "%*s:%5d", width - 6,
 			      self->thread->comm ?: "", self->thread->pid);
 }
 
@@ -97,6 +97,16 @@
 	return repsep_snprintf(bf, size, "%*s", width, self->thread->comm);
 }
 
+struct sort_entry sort_comm = {
+	.se_header	= "Command",
+	.se_cmp		= sort__comm_cmp,
+	.se_collapse	= sort__comm_collapse,
+	.se_snprintf	= hist_entry__comm_snprintf,
+	.se_width_idx	= HISTC_COMM,
+};
+
+/* --sort dso */
+
 static int64_t _sort__dso_cmp(struct map *map_l, struct map *map_r)
 {
 	struct dso *dso_l = map_l ? map_l->dso : NULL;
@@ -117,40 +127,12 @@
 	return strcmp(dso_name_l, dso_name_r);
 }
 
-struct sort_entry sort_comm = {
-	.se_header	= "Command",
-	.se_cmp		= sort__comm_cmp,
-	.se_collapse	= sort__comm_collapse,
-	.se_snprintf	= hist_entry__comm_snprintf,
-	.se_width_idx	= HISTC_COMM,
-};
-
-/* --sort dso */
-
 static int64_t
 sort__dso_cmp(struct hist_entry *left, struct hist_entry *right)
 {
 	return _sort__dso_cmp(left->ms.map, right->ms.map);
 }
 
-
-static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r,
-			      u64 ip_l, u64 ip_r)
-{
-	if (!sym_l || !sym_r)
-		return cmp_null(sym_l, sym_r);
-
-	if (sym_l == sym_r)
-		return 0;
-
-	if (sym_l)
-		ip_l = sym_l->start;
-	if (sym_r)
-		ip_r = sym_r->start;
-
-	return (int64_t)(ip_r - ip_l);
-}
-
 static int _hist_entry__dso_snprintf(struct map *map, char *bf,
 				     size_t size, unsigned int width)
 {
@@ -169,9 +151,43 @@
 	return _hist_entry__dso_snprintf(self->ms.map, bf, size, width);
 }
 
+struct sort_entry sort_dso = {
+	.se_header	= "Shared Object",
+	.se_cmp		= sort__dso_cmp,
+	.se_snprintf	= hist_entry__dso_snprintf,
+	.se_width_idx	= HISTC_DSO,
+};
+
+/* --sort symbol */
+
+static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r)
+{
+	u64 ip_l, ip_r;
+
+	if (!sym_l || !sym_r)
+		return cmp_null(sym_l, sym_r);
+
+	if (sym_l == sym_r)
+		return 0;
+
+	ip_l = sym_l->start;
+	ip_r = sym_r->start;
+
+	return (int64_t)(ip_r - ip_l);
+}
+
+static int64_t
+sort__sym_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	if (!left->ms.sym && !right->ms.sym)
+		return right->level - left->level;
+
+	return _sort__sym_cmp(left->ms.sym, right->ms.sym);
+}
+
 static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
 				     u64 ip, char level, char *bf, size_t size,
-				     unsigned int width __maybe_unused)
+				     unsigned int width)
 {
 	size_t ret = 0;
 
@@ -197,43 +213,13 @@
 	return ret;
 }
 
-
-struct sort_entry sort_dso = {
-	.se_header	= "Shared Object",
-	.se_cmp		= sort__dso_cmp,
-	.se_snprintf	= hist_entry__dso_snprintf,
-	.se_width_idx	= HISTC_DSO,
-};
-
 static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf,
-				    size_t size,
-				    unsigned int width __maybe_unused)
+				    size_t size, unsigned int width)
 {
 	return _hist_entry__sym_snprintf(self->ms.map, self->ms.sym, self->ip,
 					 self->level, bf, size, width);
 }
 
-/* --sort symbol */
-static int64_t
-sort__sym_cmp(struct hist_entry *left, struct hist_entry *right)
-{
-	u64 ip_l, ip_r;
-
-	if (!left->ms.sym && !right->ms.sym)
-		return right->level - left->level;
-
-	if (!left->ms.sym || !right->ms.sym)
-		return cmp_null(left->ms.sym, right->ms.sym);
-
-	if (left->ms.sym == right->ms.sym)
-		return 0;
-
-	ip_l = left->ms.sym->start;
-	ip_r = right->ms.sym->start;
-
-	return _sort__sym_cmp(left->ms.sym, right->ms.sym, ip_l, ip_r);
-}
-
 struct sort_entry sort_sym = {
 	.se_header	= "Symbol",
 	.se_cmp		= sort__sym_cmp,
@@ -253,7 +239,7 @@
 					size_t size,
 					unsigned int width __maybe_unused)
 {
-	FILE *fp;
+	FILE *fp = NULL;
 	char cmd[PATH_MAX + 2], *path = self->srcline, *nl;
 	size_t line_len;
 
@@ -274,7 +260,6 @@
 
 	if (getline(&path, &line_len, fp) < 0 || !line_len)
 		goto out_ip;
-	fclose(fp);
 	self->srcline = strdup(path);
 	if (self->srcline == NULL)
 		goto out_ip;
@@ -284,8 +269,12 @@
 		*nl = '\0';
 	path = self->srcline;
 out_path:
+	if (fp)
+		pclose(fp);
 	return repsep_snprintf(bf, size, "%s", path);
 out_ip:
+	if (fp)
+		pclose(fp);
 	return repsep_snprintf(bf, size, "%-#*llx", BITS_PER_LONG / 4, self->ip);
 }
 
@@ -335,7 +324,7 @@
 static int hist_entry__cpu_snprintf(struct hist_entry *self, char *bf,
 				       size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%-*d", width, self->cpu);
+	return repsep_snprintf(bf, size, "%*d", width, self->cpu);
 }
 
 struct sort_entry sort_cpu = {
@@ -345,6 +334,8 @@
 	.se_width_idx	= HISTC_CPU,
 };
 
+/* sort keys for branch stacks */
+
 static int64_t
 sort__dso_from_cmp(struct hist_entry *left, struct hist_entry *right)
 {
@@ -359,13 +350,6 @@
 					 bf, size, width);
 }
 
-struct sort_entry sort_dso_from = {
-	.se_header	= "Source Shared Object",
-	.se_cmp		= sort__dso_from_cmp,
-	.se_snprintf	= hist_entry__dso_from_snprintf,
-	.se_width_idx	= HISTC_DSO_FROM,
-};
-
 static int64_t
 sort__dso_to_cmp(struct hist_entry *left, struct hist_entry *right)
 {
@@ -389,8 +373,7 @@
 	if (!from_l->sym && !from_r->sym)
 		return right->level - left->level;
 
-	return _sort__sym_cmp(from_l->sym, from_r->sym, from_l->addr,
-			     from_r->addr);
+	return _sort__sym_cmp(from_l->sym, from_r->sym);
 }
 
 static int64_t
@@ -402,12 +385,11 @@
 	if (!to_l->sym && !to_r->sym)
 		return right->level - left->level;
 
-	return _sort__sym_cmp(to_l->sym, to_r->sym, to_l->addr, to_r->addr);
+	return _sort__sym_cmp(to_l->sym, to_r->sym);
 }
 
 static int hist_entry__sym_from_snprintf(struct hist_entry *self, char *bf,
-					size_t size,
-					unsigned int width __maybe_unused)
+					 size_t size, unsigned int width)
 {
 	struct addr_map_symbol *from = &self->branch_info->from;
 	return _hist_entry__sym_snprintf(from->map, from->sym, from->addr,
@@ -416,8 +398,7 @@
 }
 
 static int hist_entry__sym_to_snprintf(struct hist_entry *self, char *bf,
-				       size_t size,
-				       unsigned int width __maybe_unused)
+				       size_t size, unsigned int width)
 {
 	struct addr_map_symbol *to = &self->branch_info->to;
 	return _hist_entry__sym_snprintf(to->map, to->sym, to->addr,
@@ -425,6 +406,13 @@
 
 }
 
+struct sort_entry sort_dso_from = {
+	.se_header	= "Source Shared Object",
+	.se_cmp		= sort__dso_from_cmp,
+	.se_snprintf	= hist_entry__dso_from_snprintf,
+	.se_width_idx	= HISTC_DSO_FROM,
+};
+
 struct sort_entry sort_dso_to = {
 	.se_header	= "Target Shared Object",
 	.se_cmp		= sort__dso_to_cmp,
@@ -484,30 +472,40 @@
 
 #define DIM(d, n, func) [d] = { .name = n, .entry = &(func) }
 
-static struct sort_dimension sort_dimensions[] = {
+static struct sort_dimension common_sort_dimensions[] = {
 	DIM(SORT_PID, "pid", sort_thread),
 	DIM(SORT_COMM, "comm", sort_comm),
 	DIM(SORT_DSO, "dso", sort_dso),
-	DIM(SORT_DSO_FROM, "dso_from", sort_dso_from),
-	DIM(SORT_DSO_TO, "dso_to", sort_dso_to),
 	DIM(SORT_SYM, "symbol", sort_sym),
-	DIM(SORT_SYM_TO, "symbol_from", sort_sym_from),
-	DIM(SORT_SYM_FROM, "symbol_to", sort_sym_to),
 	DIM(SORT_PARENT, "parent", sort_parent),
 	DIM(SORT_CPU, "cpu", sort_cpu),
-	DIM(SORT_MISPREDICT, "mispredict", sort_mispredict),
 	DIM(SORT_SRCLINE, "srcline", sort_srcline),
 };
 
+#undef DIM
+
+#define DIM(d, n, func) [d - __SORT_BRANCH_STACK] = { .name = n, .entry = &(func) }
+
+static struct sort_dimension bstack_sort_dimensions[] = {
+	DIM(SORT_DSO_FROM, "dso_from", sort_dso_from),
+	DIM(SORT_DSO_TO, "dso_to", sort_dso_to),
+	DIM(SORT_SYM_FROM, "symbol_from", sort_sym_from),
+	DIM(SORT_SYM_TO, "symbol_to", sort_sym_to),
+	DIM(SORT_MISPREDICT, "mispredict", sort_mispredict),
+};
+
+#undef DIM
+
 int sort_dimension__add(const char *tok)
 {
 	unsigned int i;
 
-	for (i = 0; i < ARRAY_SIZE(sort_dimensions); i++) {
-		struct sort_dimension *sd = &sort_dimensions[i];
+	for (i = 0; i < ARRAY_SIZE(common_sort_dimensions); i++) {
+		struct sort_dimension *sd = &common_sort_dimensions[i];
 
 		if (strncasecmp(tok, sd->name, strlen(tok)))
 			continue;
+
 		if (sd->entry == &sort_parent) {
 			int ret = regcomp(&parent_regex, parent_pattern, REG_EXTENDED);
 			if (ret) {
@@ -518,9 +516,7 @@
 				return -EINVAL;
 			}
 			sort__has_parent = 1;
-		} else if (sd->entry == &sort_sym ||
-			   sd->entry == &sort_sym_from ||
-			   sd->entry == &sort_sym_to) {
+		} else if (sd->entry == &sort_sym) {
 			sort__has_sym = 1;
 		}
 
@@ -530,52 +526,69 @@
 		if (sd->entry->se_collapse)
 			sort__need_collapse = 1;
 
-		if (list_empty(&hist_entry__sort_list)) {
-			if (!strcmp(sd->name, "pid"))
-				sort__first_dimension = SORT_PID;
-			else if (!strcmp(sd->name, "comm"))
-				sort__first_dimension = SORT_COMM;
-			else if (!strcmp(sd->name, "dso"))
-				sort__first_dimension = SORT_DSO;
-			else if (!strcmp(sd->name, "symbol"))
-				sort__first_dimension = SORT_SYM;
-			else if (!strcmp(sd->name, "parent"))
-				sort__first_dimension = SORT_PARENT;
-			else if (!strcmp(sd->name, "cpu"))
-				sort__first_dimension = SORT_CPU;
-			else if (!strcmp(sd->name, "symbol_from"))
-				sort__first_dimension = SORT_SYM_FROM;
-			else if (!strcmp(sd->name, "symbol_to"))
-				sort__first_dimension = SORT_SYM_TO;
-			else if (!strcmp(sd->name, "dso_from"))
-				sort__first_dimension = SORT_DSO_FROM;
-			else if (!strcmp(sd->name, "dso_to"))
-				sort__first_dimension = SORT_DSO_TO;
-			else if (!strcmp(sd->name, "mispredict"))
-				sort__first_dimension = SORT_MISPREDICT;
-		}
+		if (list_empty(&hist_entry__sort_list))
+			sort__first_dimension = i;
 
 		list_add_tail(&sd->entry->list, &hist_entry__sort_list);
 		sd->taken = 1;
 
 		return 0;
 	}
+
+	for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) {
+		struct sort_dimension *sd = &bstack_sort_dimensions[i];
+
+		if (strncasecmp(tok, sd->name, strlen(tok)))
+			continue;
+
+		if (sort__branch_mode != 1)
+			return -EINVAL;
+
+		if (sd->entry == &sort_sym_from || sd->entry == &sort_sym_to)
+			sort__has_sym = 1;
+
+		if (sd->taken)
+			return 0;
+
+		if (sd->entry->se_collapse)
+			sort__need_collapse = 1;
+
+		if (list_empty(&hist_entry__sort_list))
+			sort__first_dimension = i + __SORT_BRANCH_STACK;
+
+		list_add_tail(&sd->entry->list, &hist_entry__sort_list);
+		sd->taken = 1;
+
+		return 0;
+	}
+
 	return -ESRCH;
 }
 
-void setup_sorting(const char * const usagestr[], const struct option *opts)
+int setup_sorting(void)
 {
 	char *tmp, *tok, *str = strdup(sort_order);
+	int ret = 0;
+
+	if (str == NULL) {
+		error("Not enough memory to setup sort keys");
+		return -ENOMEM;
+	}
 
 	for (tok = strtok_r(str, ", ", &tmp);
 			tok; tok = strtok_r(NULL, ", ", &tmp)) {
-		if (sort_dimension__add(tok) < 0) {
+		ret = sort_dimension__add(tok);
+		if (ret == -EINVAL) {
+			error("Invalid --sort key: `%s'", tok);
+			break;
+		} else if (ret == -ESRCH) {
 			error("Unknown --sort key: `%s'", tok);
-			usage_with_options(usagestr, opts);
+			break;
 		}
 	}
 
 	free(str);
+	return ret;
 }
 
 void sort_entry__setup_elide(struct sort_entry *self, struct strlist *list,
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index b4e8c3b..b13e56f 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -55,9 +55,6 @@
 struct hist_entry_diff {
 	bool	computed;
 
-	/* PERF_HPP__DISPL */
-	int	displacement;
-
 	/* PERF_HPP__DELTA */
 	double	period_ratio_delta;
 
@@ -118,25 +115,29 @@
 	return NULL;
 }
 
-static inline void hist__entry_add_pair(struct hist_entry *he,
+static inline void hist_entry__add_pair(struct hist_entry *he,
 					struct hist_entry *pair)
 {
 	list_add_tail(&he->pairs.head, &pair->pairs.node);
 }
 
 enum sort_type {
+	/* common sort keys */
 	SORT_PID,
 	SORT_COMM,
 	SORT_DSO,
 	SORT_SYM,
 	SORT_PARENT,
 	SORT_CPU,
-	SORT_DSO_FROM,
+	SORT_SRCLINE,
+
+	/* branch stack specific sort keys */
+	__SORT_BRANCH_STACK,
+	SORT_DSO_FROM = __SORT_BRANCH_STACK,
 	SORT_DSO_TO,
 	SORT_SYM_FROM,
 	SORT_SYM_TO,
 	SORT_MISPREDICT,
-	SORT_SRCLINE,
 };
 
 /*
@@ -159,7 +160,7 @@
 extern struct sort_entry sort_thread;
 extern struct list_head hist_entry__sort_list;
 
-void setup_sorting(const char * const usagestr[], const struct option *opts);
+int setup_sorting(void);
 extern int sort_dimension__add(const char *);
 void sort_entry__setup_elide(struct sort_entry *self, struct strlist *list,
 			     const char *list_name, FILE *fp);
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index 346707d..29c7b2c 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -332,6 +332,24 @@
 }
 
 /**
+ * ltrim - Removes leading whitespace from @s.
+ * @s: The string to be stripped.
+ *
+ * Return pointer to the first non-whitespace character in @s.
+ */
+char *ltrim(char *s)
+{
+	int len = strlen(s);
+
+	while (len && isspace(*s)) {
+		len--;
+		s++;
+	}
+
+	return s;
+}
+
+/**
  * rtrim - Removes trailing whitespace from @s.
  * @s: The string to be stripped.
  *
diff --git a/tools/perf/util/strlist.c b/tools/perf/util/strlist.c
index 155d8b7..55433aa4 100644
--- a/tools/perf/util/strlist.c
+++ b/tools/perf/util/strlist.c
@@ -35,11 +35,11 @@
 	return NULL;
 }
 
-static void str_node__delete(struct str_node *self, bool dupstr)
+static void str_node__delete(struct str_node *snode, bool dupstr)
 {
 	if (dupstr)
-		free((void *)self->s);
-	free(self);
+		free((void *)snode->s);
+	free(snode);
 }
 
 static
@@ -59,12 +59,12 @@
 	return strcmp(snode->s, str);
 }
 
-int strlist__add(struct strlist *self, const char *new_entry)
+int strlist__add(struct strlist *slist, const char *new_entry)
 {
-	return rblist__add_node(&self->rblist, new_entry);
+	return rblist__add_node(&slist->rblist, new_entry);
 }
 
-int strlist__load(struct strlist *self, const char *filename)
+int strlist__load(struct strlist *slist, const char *filename)
 {
 	char entry[1024];
 	int err;
@@ -80,7 +80,7 @@
 			continue;
 		entry[len - 1] = '\0';
 
-		err = strlist__add(self, entry);
+		err = strlist__add(slist, entry);
 		if (err != 0)
 			goto out;
 	}
@@ -107,56 +107,56 @@
 	return snode;
 }
 
-static int strlist__parse_list_entry(struct strlist *self, const char *s)
+static int strlist__parse_list_entry(struct strlist *slist, const char *s)
 {
 	if (strncmp(s, "file://", 7) == 0)
-		return strlist__load(self, s + 7);
+		return strlist__load(slist, s + 7);
 
-	return strlist__add(self, s);
+	return strlist__add(slist, s);
 }
 
-int strlist__parse_list(struct strlist *self, const char *s)
+int strlist__parse_list(struct strlist *slist, const char *s)
 {
 	char *sep;
 	int err;
 
 	while ((sep = strchr(s, ',')) != NULL) {
 		*sep = '\0';
-		err = strlist__parse_list_entry(self, s);
+		err = strlist__parse_list_entry(slist, s);
 		*sep = ',';
 		if (err != 0)
 			return err;
 		s = sep + 1;
 	}
 
-	return *s ? strlist__parse_list_entry(self, s) : 0;
+	return *s ? strlist__parse_list_entry(slist, s) : 0;
 }
 
-struct strlist *strlist__new(bool dupstr, const char *slist)
+struct strlist *strlist__new(bool dupstr, const char *list)
 {
-	struct strlist *self = malloc(sizeof(*self));
+	struct strlist *slist = malloc(sizeof(*slist));
 
-	if (self != NULL) {
-		rblist__init(&self->rblist);
-		self->rblist.node_cmp    = strlist__node_cmp;
-		self->rblist.node_new    = strlist__node_new;
-		self->rblist.node_delete = strlist__node_delete;
+	if (slist != NULL) {
+		rblist__init(&slist->rblist);
+		slist->rblist.node_cmp    = strlist__node_cmp;
+		slist->rblist.node_new    = strlist__node_new;
+		slist->rblist.node_delete = strlist__node_delete;
 
-		self->dupstr	 = dupstr;
-		if (slist && strlist__parse_list(self, slist) != 0)
+		slist->dupstr	 = dupstr;
+		if (slist && strlist__parse_list(slist, list) != 0)
 			goto out_error;
 	}
 
-	return self;
+	return slist;
 out_error:
-	free(self);
+	free(slist);
 	return NULL;
 }
 
-void strlist__delete(struct strlist *self)
+void strlist__delete(struct strlist *slist)
 {
-	if (self != NULL)
-		rblist__delete(&self->rblist);
+	if (slist != NULL)
+		rblist__delete(&slist->rblist);
 }
 
 struct str_node *strlist__entry(const struct strlist *slist, unsigned int idx)
diff --git a/tools/perf/util/strlist.h b/tools/perf/util/strlist.h
index dd9f922..5c7f870 100644
--- a/tools/perf/util/strlist.h
+++ b/tools/perf/util/strlist.h
@@ -17,34 +17,34 @@
 };
 
 struct strlist *strlist__new(bool dupstr, const char *slist);
-void strlist__delete(struct strlist *self);
+void strlist__delete(struct strlist *slist);
 
-void strlist__remove(struct strlist *self, struct str_node *sn);
-int strlist__load(struct strlist *self, const char *filename);
-int strlist__add(struct strlist *self, const char *str);
+void strlist__remove(struct strlist *slist, struct str_node *sn);
+int strlist__load(struct strlist *slist, const char *filename);
+int strlist__add(struct strlist *slist, const char *str);
 
-struct str_node *strlist__entry(const struct strlist *self, unsigned int idx);
-struct str_node *strlist__find(struct strlist *self, const char *entry);
+struct str_node *strlist__entry(const struct strlist *slist, unsigned int idx);
+struct str_node *strlist__find(struct strlist *slist, const char *entry);
 
-static inline bool strlist__has_entry(struct strlist *self, const char *entry)
+static inline bool strlist__has_entry(struct strlist *slist, const char *entry)
 {
-	return strlist__find(self, entry) != NULL;
+	return strlist__find(slist, entry) != NULL;
 }
 
-static inline bool strlist__empty(const struct strlist *self)
+static inline bool strlist__empty(const struct strlist *slist)
 {
-	return rblist__empty(&self->rblist);
+	return rblist__empty(&slist->rblist);
 }
 
-static inline unsigned int strlist__nr_entries(const struct strlist *self)
+static inline unsigned int strlist__nr_entries(const struct strlist *slist)
 {
-	return rblist__nr_entries(&self->rblist);
+	return rblist__nr_entries(&slist->rblist);
 }
 
 /* For strlist iteration */
-static inline struct str_node *strlist__first(struct strlist *self)
+static inline struct str_node *strlist__first(struct strlist *slist)
 {
-	struct rb_node *rn = rb_first(&self->rblist.entries);
+	struct rb_node *rn = rb_first(&slist->rblist.entries);
 	return rn ? rb_entry(rn, struct str_node, rb_node) : NULL;
 }
 static inline struct str_node *strlist__next(struct str_node *sn)
@@ -59,21 +59,21 @@
 /**
  * strlist_for_each      - iterate over a strlist
  * @pos:	the &struct str_node to use as a loop cursor.
- * @self:	the &struct strlist for loop.
+ * @slist:	the &struct strlist for loop.
  */
-#define strlist__for_each(pos, self)	\
-	for (pos = strlist__first(self); pos; pos = strlist__next(pos))
+#define strlist__for_each(pos, slist)	\
+	for (pos = strlist__first(slist); pos; pos = strlist__next(pos))
 
 /**
  * strlist_for_each_safe - iterate over a strlist safe against removal of
  *                         str_node
  * @pos:	the &struct str_node to use as a loop cursor.
  * @n:		another &struct str_node to use as temporary storage.
- * @self:	the &struct strlist for loop.
+ * @slist:	the &struct strlist for loop.
  */
-#define strlist__for_each_safe(pos, n, self)	\
-	for (pos = strlist__first(self), n = strlist__next(pos); pos;\
+#define strlist__for_each_safe(pos, n, slist)	\
+	for (pos = strlist__first(slist), n = strlist__next(pos); pos;\
 	     pos = n, n = strlist__next(n))
 
-int strlist__parse_list(struct strlist *self, const char *s);
+int strlist__parse_list(struct strlist *slist, const char *s);
 #endif /* __PERF_STRLIST_H */
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index db0cc92..54efcb5 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -1,6 +1,3 @@
-#include <libelf.h>
-#include <gelf.h>
-#include <elf.h>
 #include <fcntl.h>
 #include <stdio.h>
 #include <errno.h>
@@ -718,6 +715,17 @@
 					sym.st_value);
 			used_opd = true;
 		}
+		/*
+		 * When loading symbols in a data mapping, ABS symbols (which
+		 * has a value of SHN_ABS in its st_shndx) failed at
+		 * elf_getscn().  And it marks the loading as a failure so
+		 * already loaded symbols cannot be fixed up.
+		 *
+		 * I'm not sure what should be done. Just ignore them for now.
+		 * - Namhyung Kim
+		 */
+		if (sym.st_shndx == SHN_ABS)
+			continue;
 
 		sec = elf_getscn(runtime_ss->elf, sym.st_shndx);
 		if (!sec)
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index 259f8f2..a7390cd 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -1,6 +1,5 @@
 #include "symbol.h"
 
-#include <elf.h>
 #include <stdio.h>
 #include <fcntl.h>
 #include <string.h>
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 295f8d4..e6432d8 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -28,8 +28,8 @@
 				symbol_filter_t filter);
 static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
 			symbol_filter_t filter);
-static int vmlinux_path__nr_entries;
-static char **vmlinux_path;
+int vmlinux_path__nr_entries;
+char **vmlinux_path;
 
 struct symbol_conf symbol_conf = {
 	.exclude_other	  = true,
@@ -202,13 +202,6 @@
 	curr->end = ~0ULL;
 }
 
-static void map_groups__fixup_end(struct map_groups *mg)
-{
-	int i;
-	for (i = 0; i < MAP__NR_TYPES; ++i)
-		__map_groups__fixup_end(mg, i);
-}
-
 struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name)
 {
 	size_t namelen = strlen(name) + 1;
@@ -652,8 +645,8 @@
 	return count + moved;
 }
 
-static bool symbol__restricted_filename(const char *filename,
-					const char *restricted_filename)
+bool symbol__restricted_filename(const char *filename,
+				 const char *restricted_filename)
 {
 	bool restricted = false;
 
@@ -775,10 +768,6 @@
 	else
 		machine = NULL;
 
-	name = malloc(PATH_MAX);
-	if (!name)
-		return -1;
-
 	dso->adjust_symbols = 0;
 
 	if (strncmp(dso->name, "/tmp/perf-", 10) == 0) {
@@ -802,6 +791,10 @@
 	if (machine)
 		root_dir = machine->root_dir;
 
+	name = malloc(PATH_MAX);
+	if (!name)
+		return -1;
+
 	/* Iterate over candidate debug images.
 	 * Keep track of "interesting" ones (those which have a symtab, dynsym,
 	 * and/or opd section) for processing.
@@ -887,200 +880,6 @@
 	return NULL;
 }
 
-static int map_groups__set_modules_path_dir(struct map_groups *mg,
-				const char *dir_name)
-{
-	struct dirent *dent;
-	DIR *dir = opendir(dir_name);
-	int ret = 0;
-
-	if (!dir) {
-		pr_debug("%s: cannot open %s dir\n", __func__, dir_name);
-		return -1;
-	}
-
-	while ((dent = readdir(dir)) != NULL) {
-		char path[PATH_MAX];
-		struct stat st;
-
-		/*sshfs might return bad dent->d_type, so we have to stat*/
-		snprintf(path, sizeof(path), "%s/%s", dir_name, dent->d_name);
-		if (stat(path, &st))
-			continue;
-
-		if (S_ISDIR(st.st_mode)) {
-			if (!strcmp(dent->d_name, ".") ||
-			    !strcmp(dent->d_name, ".."))
-				continue;
-
-			ret = map_groups__set_modules_path_dir(mg, path);
-			if (ret < 0)
-				goto out;
-		} else {
-			char *dot = strrchr(dent->d_name, '.'),
-			     dso_name[PATH_MAX];
-			struct map *map;
-			char *long_name;
-
-			if (dot == NULL || strcmp(dot, ".ko"))
-				continue;
-			snprintf(dso_name, sizeof(dso_name), "[%.*s]",
-				 (int)(dot - dent->d_name), dent->d_name);
-
-			strxfrchar(dso_name, '-', '_');
-			map = map_groups__find_by_name(mg, MAP__FUNCTION,
-						       dso_name);
-			if (map == NULL)
-				continue;
-
-			long_name = strdup(path);
-			if (long_name == NULL) {
-				ret = -1;
-				goto out;
-			}
-			dso__set_long_name(map->dso, long_name);
-			map->dso->lname_alloc = 1;
-			dso__kernel_module_get_build_id(map->dso, "");
-		}
-	}
-
-out:
-	closedir(dir);
-	return ret;
-}
-
-static char *get_kernel_version(const char *root_dir)
-{
-	char version[PATH_MAX];
-	FILE *file;
-	char *name, *tmp;
-	const char *prefix = "Linux version ";
-
-	sprintf(version, "%s/proc/version", root_dir);
-	file = fopen(version, "r");
-	if (!file)
-		return NULL;
-
-	version[0] = '\0';
-	tmp = fgets(version, sizeof(version), file);
-	fclose(file);
-
-	name = strstr(version, prefix);
-	if (!name)
-		return NULL;
-	name += strlen(prefix);
-	tmp = strchr(name, ' ');
-	if (tmp)
-		*tmp = '\0';
-
-	return strdup(name);
-}
-
-static int machine__set_modules_path(struct machine *machine)
-{
-	char *version;
-	char modules_path[PATH_MAX];
-
-	version = get_kernel_version(machine->root_dir);
-	if (!version)
-		return -1;
-
-	snprintf(modules_path, sizeof(modules_path), "%s/lib/modules/%s/kernel",
-		 machine->root_dir, version);
-	free(version);
-
-	return map_groups__set_modules_path_dir(&machine->kmaps, modules_path);
-}
-
-struct map *machine__new_module(struct machine *machine, u64 start,
-				const char *filename)
-{
-	struct map *map;
-	struct dso *dso = __dsos__findnew(&machine->kernel_dsos, filename);
-
-	if (dso == NULL)
-		return NULL;
-
-	map = map__new2(start, dso, MAP__FUNCTION);
-	if (map == NULL)
-		return NULL;
-
-	if (machine__is_host(machine))
-		dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE;
-	else
-		dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE;
-	map_groups__insert(&machine->kmaps, map);
-	return map;
-}
-
-static int machine__create_modules(struct machine *machine)
-{
-	char *line = NULL;
-	size_t n;
-	FILE *file;
-	struct map *map;
-	const char *modules;
-	char path[PATH_MAX];
-
-	if (machine__is_default_guest(machine))
-		modules = symbol_conf.default_guest_modules;
-	else {
-		sprintf(path, "%s/proc/modules", machine->root_dir);
-		modules = path;
-	}
-
-	if (symbol__restricted_filename(path, "/proc/modules"))
-		return -1;
-
-	file = fopen(modules, "r");
-	if (file == NULL)
-		return -1;
-
-	while (!feof(file)) {
-		char name[PATH_MAX];
-		u64 start;
-		char *sep;
-		int line_len;
-
-		line_len = getline(&line, &n, file);
-		if (line_len < 0)
-			break;
-
-		if (!line)
-			goto out_failure;
-
-		line[--line_len] = '\0'; /* \n */
-
-		sep = strrchr(line, 'x');
-		if (sep == NULL)
-			continue;
-
-		hex2u64(sep + 1, &start);
-
-		sep = strchr(line, ' ');
-		if (sep == NULL)
-			continue;
-
-		*sep = '\0';
-
-		snprintf(name, sizeof(name), "[%s]", line);
-		map = machine__new_module(machine, start, name);
-		if (map == NULL)
-			goto out_delete_line;
-		dso__kernel_module_get_build_id(map->dso, machine->root_dir);
-	}
-
-	free(line);
-	fclose(file);
-
-	return machine__set_modules_path(machine);
-
-out_delete_line:
-	free(line);
-out_failure:
-	return -1;
-}
-
 int dso__load_vmlinux(struct dso *dso, struct map *map,
 		      const char *vmlinux, symbol_filter_t filter)
 {
@@ -1124,8 +923,10 @@
 	filename = dso__build_id_filename(dso, NULL, 0);
 	if (filename != NULL) {
 		err = dso__load_vmlinux(dso, map, filename, filter);
-		if (err > 0)
+		if (err > 0) {
+			dso->lname_alloc = 1;
 			goto out;
+		}
 		free(filename);
 	}
 
@@ -1133,6 +934,7 @@
 		err = dso__load_vmlinux(dso, map, vmlinux_path[i], filter);
 		if (err > 0) {
 			dso__set_long_name(dso, strdup(vmlinux_path[i]));
+			dso->lname_alloc = 1;
 			break;
 		}
 	}
@@ -1172,6 +974,7 @@
 		if (err > 0) {
 			dso__set_long_name(dso,
 					   strdup(symbol_conf.vmlinux_name));
+			dso->lname_alloc = 1;
 			goto out_fixup;
 		}
 		return err;
@@ -1300,195 +1103,6 @@
 	return err;
 }
 
-size_t machines__fprintf_dsos(struct rb_root *machines, FILE *fp)
-{
-	struct rb_node *nd;
-	size_t ret = 0;
-
-	for (nd = rb_first(machines); nd; nd = rb_next(nd)) {
-		struct machine *pos = rb_entry(nd, struct machine, rb_node);
-		ret += __dsos__fprintf(&pos->kernel_dsos, fp);
-		ret += __dsos__fprintf(&pos->user_dsos, fp);
-	}
-
-	return ret;
-}
-
-size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp,
-				     bool with_hits)
-{
-	return __dsos__fprintf_buildid(&machine->kernel_dsos, fp, with_hits) +
-	       __dsos__fprintf_buildid(&machine->user_dsos, fp, with_hits);
-}
-
-size_t machines__fprintf_dsos_buildid(struct rb_root *machines,
-				      FILE *fp, bool with_hits)
-{
-	struct rb_node *nd;
-	size_t ret = 0;
-
-	for (nd = rb_first(machines); nd; nd = rb_next(nd)) {
-		struct machine *pos = rb_entry(nd, struct machine, rb_node);
-		ret += machine__fprintf_dsos_buildid(pos, fp, with_hits);
-	}
-	return ret;
-}
-
-static struct dso *machine__get_kernel(struct machine *machine)
-{
-	const char *vmlinux_name = NULL;
-	struct dso *kernel;
-
-	if (machine__is_host(machine)) {
-		vmlinux_name = symbol_conf.vmlinux_name;
-		if (!vmlinux_name)
-			vmlinux_name = "[kernel.kallsyms]";
-
-		kernel = dso__kernel_findnew(machine, vmlinux_name,
-					     "[kernel]",
-					     DSO_TYPE_KERNEL);
-	} else {
-		char bf[PATH_MAX];
-
-		if (machine__is_default_guest(machine))
-			vmlinux_name = symbol_conf.default_guest_vmlinux_name;
-		if (!vmlinux_name)
-			vmlinux_name = machine__mmap_name(machine, bf,
-							  sizeof(bf));
-
-		kernel = dso__kernel_findnew(machine, vmlinux_name,
-					     "[guest.kernel]",
-					     DSO_TYPE_GUEST_KERNEL);
-	}
-
-	if (kernel != NULL && (!kernel->has_build_id))
-		dso__read_running_kernel_build_id(kernel, machine);
-
-	return kernel;
-}
-
-struct process_args {
-	u64 start;
-};
-
-static int symbol__in_kernel(void *arg, const char *name,
-			     char type __maybe_unused, u64 start)
-{
-	struct process_args *args = arg;
-
-	if (strchr(name, '['))
-		return 0;
-
-	args->start = start;
-	return 1;
-}
-
-/* Figure out the start address of kernel map from /proc/kallsyms */
-static u64 machine__get_kernel_start_addr(struct machine *machine)
-{
-	const char *filename;
-	char path[PATH_MAX];
-	struct process_args args;
-
-	if (machine__is_host(machine)) {
-		filename = "/proc/kallsyms";
-	} else {
-		if (machine__is_default_guest(machine))
-			filename = (char *)symbol_conf.default_guest_kallsyms;
-		else {
-			sprintf(path, "%s/proc/kallsyms", machine->root_dir);
-			filename = path;
-		}
-	}
-
-	if (symbol__restricted_filename(filename, "/proc/kallsyms"))
-		return 0;
-
-	if (kallsyms__parse(filename, &args, symbol__in_kernel) <= 0)
-		return 0;
-
-	return args.start;
-}
-
-int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
-{
-	enum map_type type;
-	u64 start = machine__get_kernel_start_addr(machine);
-
-	for (type = 0; type < MAP__NR_TYPES; ++type) {
-		struct kmap *kmap;
-
-		machine->vmlinux_maps[type] = map__new2(start, kernel, type);
-		if (machine->vmlinux_maps[type] == NULL)
-			return -1;
-
-		machine->vmlinux_maps[type]->map_ip =
-			machine->vmlinux_maps[type]->unmap_ip =
-				identity__map_ip;
-		kmap = map__kmap(machine->vmlinux_maps[type]);
-		kmap->kmaps = &machine->kmaps;
-		map_groups__insert(&machine->kmaps,
-				   machine->vmlinux_maps[type]);
-	}
-
-	return 0;
-}
-
-void machine__destroy_kernel_maps(struct machine *machine)
-{
-	enum map_type type;
-
-	for (type = 0; type < MAP__NR_TYPES; ++type) {
-		struct kmap *kmap;
-
-		if (machine->vmlinux_maps[type] == NULL)
-			continue;
-
-		kmap = map__kmap(machine->vmlinux_maps[type]);
-		map_groups__remove(&machine->kmaps,
-				   machine->vmlinux_maps[type]);
-		if (kmap->ref_reloc_sym) {
-			/*
-			 * ref_reloc_sym is shared among all maps, so free just
-			 * on one of them.
-			 */
-			if (type == MAP__FUNCTION) {
-				free((char *)kmap->ref_reloc_sym->name);
-				kmap->ref_reloc_sym->name = NULL;
-				free(kmap->ref_reloc_sym);
-			}
-			kmap->ref_reloc_sym = NULL;
-		}
-
-		map__delete(machine->vmlinux_maps[type]);
-		machine->vmlinux_maps[type] = NULL;
-	}
-}
-
-int machine__create_kernel_maps(struct machine *machine)
-{
-	struct dso *kernel = machine__get_kernel(machine);
-
-	if (kernel == NULL ||
-	    __machine__create_kernel_maps(machine, kernel) < 0)
-		return -1;
-
-	if (symbol_conf.use_modules && machine__create_modules(machine) < 0) {
-		if (machine__is_host(machine))
-			pr_debug("Problems creating module maps, "
-				 "continuing anyway...\n");
-		else
-			pr_debug("Problems creating module maps for guest %d, "
-				 "continuing anyway...\n", machine->pid);
-	}
-
-	/*
-	 * Now that we have all the maps created, just set the ->end of them:
-	 */
-	map_groups__fixup_end(&machine->kmaps);
-	return 0;
-}
-
 static void vmlinux_path__exit(void)
 {
 	while (--vmlinux_path__nr_entries >= 0) {
@@ -1549,25 +1163,6 @@
 	return -1;
 }
 
-size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp)
-{
-	int i;
-	size_t printed = 0;
-	struct dso *kdso = machine->vmlinux_maps[MAP__FUNCTION]->dso;
-
-	if (kdso->has_build_id) {
-		char filename[PATH_MAX];
-		if (dso__build_id_filename(kdso, filename, sizeof(filename)))
-			printed += fprintf(fp, "[0] %s\n", filename);
-	}
-
-	for (i = 0; i < vmlinux_path__nr_entries; ++i)
-		printed += fprintf(fp, "[%d] %s\n",
-				   i + kdso->has_build_id, vmlinux_path[i]);
-
-	return printed;
-}
-
 static int setup_list(struct strlist **list, const char *list_str,
 		      const char *list_name)
 {
@@ -1671,108 +1266,3 @@
 	symbol_conf.sym_list = symbol_conf.dso_list = symbol_conf.comm_list = NULL;
 	symbol_conf.initialized = false;
 }
-
-int machines__create_kernel_maps(struct rb_root *machines, pid_t pid)
-{
-	struct machine *machine = machines__findnew(machines, pid);
-
-	if (machine == NULL)
-		return -1;
-
-	return machine__create_kernel_maps(machine);
-}
-
-int machines__create_guest_kernel_maps(struct rb_root *machines)
-{
-	int ret = 0;
-	struct dirent **namelist = NULL;
-	int i, items = 0;
-	char path[PATH_MAX];
-	pid_t pid;
-	char *endp;
-
-	if (symbol_conf.default_guest_vmlinux_name ||
-	    symbol_conf.default_guest_modules ||
-	    symbol_conf.default_guest_kallsyms) {
-		machines__create_kernel_maps(machines, DEFAULT_GUEST_KERNEL_ID);
-	}
-
-	if (symbol_conf.guestmount) {
-		items = scandir(symbol_conf.guestmount, &namelist, NULL, NULL);
-		if (items <= 0)
-			return -ENOENT;
-		for (i = 0; i < items; i++) {
-			if (!isdigit(namelist[i]->d_name[0])) {
-				/* Filter out . and .. */
-				continue;
-			}
-			pid = (pid_t)strtol(namelist[i]->d_name, &endp, 10);
-			if ((*endp != '\0') ||
-			    (endp == namelist[i]->d_name) ||
-			    (errno == ERANGE)) {
-				pr_debug("invalid directory (%s). Skipping.\n",
-					 namelist[i]->d_name);
-				continue;
-			}
-			sprintf(path, "%s/%s/proc/kallsyms",
-				symbol_conf.guestmount,
-				namelist[i]->d_name);
-			ret = access(path, R_OK);
-			if (ret) {
-				pr_debug("Can't access file %s\n", path);
-				goto failure;
-			}
-			machines__create_kernel_maps(machines, pid);
-		}
-failure:
-		free(namelist);
-	}
-
-	return ret;
-}
-
-void machines__destroy_guest_kernel_maps(struct rb_root *machines)
-{
-	struct rb_node *next = rb_first(machines);
-
-	while (next) {
-		struct machine *pos = rb_entry(next, struct machine, rb_node);
-
-		next = rb_next(&pos->rb_node);
-		rb_erase(&pos->rb_node, machines);
-		machine__delete(pos);
-	}
-}
-
-int machine__load_kallsyms(struct machine *machine, const char *filename,
-			   enum map_type type, symbol_filter_t filter)
-{
-	struct map *map = machine->vmlinux_maps[type];
-	int ret = dso__load_kallsyms(map->dso, filename, map, filter);
-
-	if (ret > 0) {
-		dso__set_loaded(map->dso, type);
-		/*
-		 * Since /proc/kallsyms will have multiple sessions for the
-		 * kernel, with modules between them, fixup the end of all
-		 * sections.
-		 */
-		__map_groups__fixup_end(&machine->kmaps, type);
-	}
-
-	return ret;
-}
-
-int machine__load_vmlinux_path(struct machine *machine, enum map_type type,
-			       symbol_filter_t filter)
-{
-	struct map *map = machine->vmlinux_maps[type];
-	int ret = dso__load_vmlinux_path(map->dso, map, filter);
-
-	if (ret > 0) {
-		dso__set_loaded(map->dso, type);
-		map__reloc_vmlinux(map);
-	}
-
-	return ret;
-}
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index de68f98..b62ca37 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -16,8 +16,8 @@
 #ifdef LIBELF_SUPPORT
 #include <libelf.h>
 #include <gelf.h>
-#include <elf.h>
 #endif
+#include <elf.h>
 
 #include "dso.h"
 
@@ -96,7 +96,8 @@
 			initialized,
 			kptr_restrict,
 			annotate_asm_raw,
-			annotate_src;
+			annotate_src,
+			event_group;
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,
@@ -120,6 +121,8 @@
 };
 
 extern struct symbol_conf symbol_conf;
+extern int vmlinux_path__nr_entries;
+extern char **vmlinux_path;
 
 static inline void *symbol__priv(struct symbol *sym)
 {
@@ -223,6 +226,8 @@
 size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp);
 size_t symbol__fprintf(struct symbol *sym, FILE *fp);
 bool symbol_type__is_a(char symbol_type, enum map_type map_type);
+bool symbol__restricted_filename(const char *filename,
+				 const char *restricted_filename);
 
 int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 		  struct symsrc *runtime_ss, symbol_filter_t filter,
diff --git a/tools/perf/util/sysfs.c b/tools/perf/util/sysfs.c
index 48c6902..f71e9ea 100644
--- a/tools/perf/util/sysfs.c
+++ b/tools/perf/util/sysfs.c
@@ -8,7 +8,7 @@
 };
 
 static int sysfs_found;
-char sysfs_mountpoint[PATH_MAX];
+char sysfs_mountpoint[PATH_MAX + 1];
 
 static int sysfs_valid_mountpoint(const char *sysfs)
 {
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index df59623..632e40e 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -54,10 +54,10 @@
 	return self->comm_len;
 }
 
-static size_t thread__fprintf(struct thread *self, FILE *fp)
+size_t thread__fprintf(struct thread *thread, FILE *fp)
 {
-	return fprintf(fp, "Thread %d %s\n", self->pid, self->comm) +
-	       map_groups__fprintf(&self->mg, verbose, fp);
+	return fprintf(fp, "Thread %d %s\n", thread->pid, thread->comm) +
+	       map_groups__fprintf(&thread->mg, verbose, fp);
 }
 
 void thread__insert_map(struct thread *self, struct map *map)
@@ -84,17 +84,3 @@
 			return -ENOMEM;
 	return 0;
 }
-
-size_t machine__fprintf(struct machine *machine, FILE *fp)
-{
-	size_t ret = 0;
-	struct rb_node *nd;
-
-	for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) {
-		struct thread *pos = rb_entry(nd, struct thread, rb_node);
-
-		ret += thread__fprintf(pos, fp);
-	}
-
-	return ret;
-}
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index f2fa17c..5ad2664 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -30,6 +30,7 @@
 int thread__comm_len(struct thread *self);
 void thread__insert_map(struct thread *self, struct map *map);
 int thread__fork(struct thread *self, struct thread *parent);
+size_t thread__fprintf(struct thread *thread, FILE *fp);
 
 static inline struct map *thread__find_map(struct thread *self,
 					   enum map_type type, u64 addr)
diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c
index 884dde9..54d37a4 100644
--- a/tools/perf/util/top.c
+++ b/tools/perf/util/top.c
@@ -26,6 +26,8 @@
 	float samples_per_sec = top->samples / top->delay_secs;
 	float ksamples_per_sec = top->kernel_samples / top->delay_secs;
 	float esamples_percent = (100.0 * top->exact_samples) / top->samples;
+	struct perf_record_opts *opts = &top->record_opts;
+	struct perf_target *target = &opts->target;
 	size_t ret = 0;
 
 	if (!perf_guest) {
@@ -61,31 +63,31 @@
 		struct perf_evsel *first = perf_evlist__first(top->evlist);
 		ret += SNPRINTF(bf + ret, size - ret, "%" PRIu64 "%s ",
 				(uint64_t)first->attr.sample_period,
-				top->freq ? "Hz" : "");
+				opts->freq ? "Hz" : "");
 	}
 
 	ret += SNPRINTF(bf + ret, size - ret, "%s", perf_evsel__name(top->sym_evsel));
 
 	ret += SNPRINTF(bf + ret, size - ret, "], ");
 
-	if (top->target.pid)
+	if (target->pid)
 		ret += SNPRINTF(bf + ret, size - ret, " (target_pid: %s",
-				top->target.pid);
-	else if (top->target.tid)
+				target->pid);
+	else if (target->tid)
 		ret += SNPRINTF(bf + ret, size - ret, " (target_tid: %s",
-				top->target.tid);
-	else if (top->target.uid_str != NULL)
+				target->tid);
+	else if (target->uid_str != NULL)
 		ret += SNPRINTF(bf + ret, size - ret, " (uid: %s",
-				top->target.uid_str);
+				target->uid_str);
 	else
 		ret += SNPRINTF(bf + ret, size - ret, " (all");
 
-	if (top->target.cpu_list)
+	if (target->cpu_list)
 		ret += SNPRINTF(bf + ret, size - ret, ", CPU%s: %s)",
 				top->evlist->cpus->nr > 1 ? "s" : "",
-				top->target.cpu_list);
+				target->cpu_list);
 	else {
-		if (top->target.tid)
+		if (target->tid)
 			ret += SNPRINTF(bf + ret, size - ret, ")");
 		else
 			ret += SNPRINTF(bf + ret, size - ret, ", %d CPU%s)",
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index 86ff1b1..7ebf357 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -14,7 +14,7 @@
 struct perf_top {
 	struct perf_tool   tool;
 	struct perf_evlist *evlist;
-	struct perf_target target;
+	struct perf_record_opts record_opts;
 	/*
 	 * Symbols will be added here in perf_event__process_sample and will
 	 * get out after decayed.
@@ -24,24 +24,16 @@
 	u64		   exact_samples;
 	u64		   guest_us_samples, guest_kernel_samples;
 	int		   print_entries, count_filter, delay_secs;
-	int		   freq;
 	bool		   hide_kernel_symbols, hide_user_symbols, zero;
 	bool		   use_tui, use_stdio;
 	bool		   sort_has_symbols;
-	bool		   dont_use_callchains;
 	bool		   kptr_restrict_warned;
 	bool		   vmlinux_warned;
-	bool		   inherit;
-	bool		   group;
-	bool		   sample_id_all_missing;
-	bool		   exclude_guest_missing;
 	bool		   dump_symtab;
 	struct hist_entry  *sym_filter_entry;
 	struct perf_evsel  *sym_evsel;
 	struct perf_session *session;
 	struct winsize	   winsize;
-	unsigned int	   mmap_pages;
-	int		   default_interval;
 	int		   realtime_prio;
 	int		   sym_pcnt_filter;
 	const char	   *sym_filter;
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 5906e84..805d1f5 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -12,6 +12,8 @@
  */
 unsigned int page_size;
 
+bool test_attr__enabled;
+
 bool perf_host  = true;
 bool perf_guest = false;
 
@@ -218,3 +220,25 @@
 #else
 void dump_stack(void) {}
 #endif
+
+void get_term_dimensions(struct winsize *ws)
+{
+	char *s = getenv("LINES");
+
+	if (s != NULL) {
+		ws->ws_row = atoi(s);
+		s = getenv("COLUMNS");
+		if (s != NULL) {
+			ws->ws_col = atoi(s);
+			if (ws->ws_row && ws->ws_col)
+				return;
+		}
+	}
+#ifdef TIOCGWINSZ
+	if (ioctl(1, TIOCGWINSZ, ws) == 0 &&
+	    ws->ws_row && ws->ws_col)
+		return;
+#endif
+	ws->ws_row = 25;
+	ws->ws_col = 80;
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index c233091..09b4c26 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -265,10 +265,14 @@
 size_t hex_width(u64 v);
 int hex2u64(const char *ptr, u64 *val);
 
+char *ltrim(char *s);
 char *rtrim(char *s);
 
 void dump_stack(void);
 
 extern unsigned int page_size;
 
+struct winsize;
+void get_term_dimensions(struct winsize *ws);
+
 #endif
diff --git a/tools/vm/.gitignore b/tools/vm/.gitignore
new file mode 100644
index 0000000..44f095f
--- /dev/null
+++ b/tools/vm/.gitignore
@@ -0,0 +1,2 @@
+slabinfo
+page-types