LSK 16.06 v4.4-android

-----BEGIN PGP SIGNATURE----- Version: GnuPG v1 iQEcBAABAgAGBQJXen1sAAoJECTWi3JdVIfQs24H/R+WU/3VvkdnYUlls693TRIV 5npbyI08tZBJ8DBqheioT2wOTqf94scXTXoloD69ZFQ7UZR/Ow05NknWN8h73SpS pfCIjGLubxbqKqwnzz4jJolZR3xuz+3P+6b8oEi0psRXuACrrlbOFhdP2N5d55q8 P+bykwa9hDTKZLBu0KP0EWpba6+K7PSToqRtF37qrLDJ9s4ZHstb/AFzhxPNuSSO Kf88IDFdNaLMUzEuM3+khZ439hQ/ddz/IK0o4wGJ32uLxqBboN93NfrTH/MeiNRy H5zmiYtShcDeHs+UQ2RfxpRurQ/nIt4Xs7QOF01hzFOeGz53q2eT4y7zb4zCKxY= =jVYG -----END PGP SIGNATURE----- Merge tag 'lsk-v4.4-16.06-android' LSK 16.06 v4.4-android * tag 'lsk-v4.4-16.06-android': (447 commits) Linux 4.4.14 netfilter: x_tables: introduce and use xt_copy_counters_from_user netfilter: x_tables: do compat validation via translate_table netfilter: x_tables: xt_compat_match_from_user doesn't need a retval netfilter: ip6_tables: simplify translate_compat_table args netfilter: ip_tables: simplify translate_compat_table args netfilter: arp_tables: simplify translate_compat_table args netfilter: x_tables: don't reject valid target size on some architectures netfilter: x_tables: validate all offsets and sizes in a rule netfilter: x_tables: check for bogus target offset netfilter: x_tables: check standard target size too netfilter: x_tables: add compat version of xt_check_entry_offsets netfilter: x_tables: assert minimum target size netfilter: x_tables: kill check_entry helper netfilter: x_tables: add and use xt_check_entry_offsets netfilter: x_tables: validate targets of jumps netfilter: x_tables: don't move to non-existent next rule drm/core: Do not preserve framebuffer on rmfb, v4. crypto: qat - fix adf_ctl_drv.c:undefined reference to adf_init_pf_wq netfilter: x_tables: fix unconditional helper ...
2026-06-07 22:14:04 +02:00 · 2016-07-05 18:36:47 +08:00 · 2016-07-05 18:36:47 +08:00 · 234718be61
commit 234718be61
parent 6330e362bd fb8ebda5d9
450 changed files with 16277 additions and 8082 deletions
--- a/Documentation/ABI/testing/sysfs-bus-coresight-devices-etb10
+++ b/Documentation/ABI/testing/sysfs-bus-coresight-devices-etb10
@ -6,13 +6,6 @@ Description:	(RW) Add/remove a sink from a trace path.  There can be multiple
 		source for a single sink.
 		ex: echo 1 > /sys/bus/coresight/devices/20010000.etb/enable_sink

-What:		/sys/bus/coresight/devices/<memory_map>.etb/status
-Date:		November 2014
-KernelVersion:	3.19
-Contact:	Mathieu Poirier <mathieu.poirier@linaro.org>
-Description:	(R) List various control and status registers.  The specific
-		layout and content is driver specific.
-
 What:		/sys/bus/coresight/devices/<memory_map>.etb/trigger_cntr
 Date:		November 2014
 KernelVersion:	3.19
@ -22,3 +15,65 @@ Description:	(RW) Disables write access to the Trace RAM by stopping the
 		following the trigger event. The number of 32-bit words written
 		into the Trace RAM following the trigger event is equal to the
 		value stored in this register+1 (from ARM ETB-TRM).
+
+What:		/sys/bus/coresight/devices/<memory_map>.etb/mgmt/rdp
+Date:		March 2016
+KernelVersion:	4.7
+Contact:	Mathieu Poirier <mathieu.poirier@linaro.org>
+Description:	(R) Defines the depth, in words, of the trace RAM in powers of
+		2.  The value is read directly from HW register RDP, 0x004.
+
+What:		/sys/bus/coresight/devices/<memory_map>.etb/mgmt/sts
+Date:		March 2016
+KernelVersion:	4.7
+Contact:	Mathieu Poirier <mathieu.poirier@linaro.org>
+Description:	(R) Shows the value held by the ETB status register.  The value
+		is read directly from HW register STS, 0x00C.
+
+What:		/sys/bus/coresight/devices/<memory_map>.etb/mgmt/rrp
+Date:		March 2016
+KernelVersion:	4.7
+Contact:	Mathieu Poirier <mathieu.poirier@linaro.org>
+Description:	(R) Shows the value held by the ETB RAM Read Pointer register
+		that is used to read entries from the Trace RAM over the APB
+		interface.  The value is read directly from HW register RRP,
+		0x014.
+
+What:		/sys/bus/coresight/devices/<memory_map>.etb/mgmt/rwp
+Date:		March 2016
+KernelVersion:	4.7
+Contact:	Mathieu Poirier <mathieu.poirier@linaro.org>
+Description:	(R) Shows the value held by the ETB RAM Write Pointer register
+		that is used to sets the write pointer to write entries from
+		the CoreSight bus into the Trace RAM. The value is read directly
+		from HW register RWP, 0x018.
+
+What:		/sys/bus/coresight/devices/<memory_map>.etb/mgmt/trg
+Date:		March 2016
+KernelVersion:	4.7
+Contact:	Mathieu Poirier <mathieu.poirier@linaro.org>
+Description:	(R) Similar to "trigger_cntr" above except that this value is
+		read directly from HW register TRG, 0x01C.
+
+What:		/sys/bus/coresight/devices/<memory_map>.etb/mgmt/ctl
+Date:		March 2016
+KernelVersion:	4.7
+Contact:	Mathieu Poirier <mathieu.poirier@linaro.org>
+Description:	(R) Shows the value held by the ETB Control register. The value
+		is read directly from HW register CTL, 0x020.
+
+What:		/sys/bus/coresight/devices/<memory_map>.etb/mgmt/ffsr
+Date:		March 2016
+KernelVersion:	4.7
+Contact:	Mathieu Poirier <mathieu.poirier@linaro.org>
+Description:	(R) Shows the value held by the ETB Formatter and Flush Status
+		register.  The value is read directly from HW register FFSR,
+		0x300.
+
+What:		/sys/bus/coresight/devices/<memory_map>.etb/mgmt/ffcr
+Date:		March 2016
+KernelVersion:	4.7
+Contact:	Mathieu Poirier <mathieu.poirier@linaro.org>
+Description:	(R) Shows the value held by the ETB Formatter and Flush Control
+		register.  The value is read directly from HW register FFCR,
+		0x304.
--- a/Documentation/ABI/testing/sysfs-bus-coresight-devices-etm4x
+++ b/Documentation/ABI/testing/sysfs-bus-coresight-devices-etm4x
@ -359,6 +359,19 @@ Contact:	Mathieu Poirier <mathieu.poirier@linaro.org>
 Description:	(R) Print the content of the Peripheral ID3 Register
 		(0xFEC).  The value is taken directly from the HW.

+What:		/sys/bus/coresight/devices/<memory_map>.etm/mgmt/trcconfig
+Date:		February 2016
+KernelVersion:	4.07
+Contact:	Mathieu Poirier <mathieu.poirier@linaro.org>
+Description:	(R) Print the content of the trace configuration register
+		(0x010) as currently set by SW.
+
+What:		/sys/bus/coresight/devices/<memory_map>.etm/mgmt/trctraceid
+Date:		February 2016
+KernelVersion:	4.07
+Contact:	Mathieu Poirier <mathieu.poirier@linaro.org>
+Description:	(R) Print the content of the trace ID register (0x040).
+
 What:		/sys/bus/coresight/devices/<memory_map>.etm/trcidr/trcidr0
 Date:		April 2015
 KernelVersion:	4.01
--- a/Documentation/ABI/testing/sysfs-bus-coresight-devices-stm
+++ b/Documentation/ABI/testing/sysfs-bus-coresight-devices-stm
@ -0,0 +1,53 @@
+What:		/sys/bus/coresight/devices/<memory_map>.stm/enable_source
+Date:		April 2016
+KernelVersion:	4.7
+Contact:	Mathieu Poirier <mathieu.poirier@linaro.org>
+Description:	(RW) Enable/disable tracing on this specific trace macrocell.
+		Enabling the trace macrocell implies it has been configured
+		properly and a sink has been identified for it.  The path
+		of coresight components linking the source to the sink is
+		configured and managed automatically by the coresight framework.
+
+What:		/sys/bus/coresight/devices/<memory_map>.stm/hwevent_enable
+Date:		April 2016
+KernelVersion:	4.7
+Contact:	Mathieu Poirier <mathieu.poirier@linaro.org>
+Description:	(RW) Provides access to the HW event enable register, used in
+		conjunction with HW event bank select register.
+
+What:		/sys/bus/coresight/devices/<memory_map>.stm/hwevent_select
+Date:		April 2016
+KernelVersion:	4.7
+Contact:	Mathieu Poirier <mathieu.poirier@linaro.org>
+Description:	(RW) Gives access to the HW event block select register
+		(STMHEBSR) in order to configure up to 256 channels.  Used in
+		conjunction with "hwevent_enable" register as described above.
+
+What:		/sys/bus/coresight/devices/<memory_map>.stm/port_enable
+Date:		April 2016
+KernelVersion:	4.7
+Contact:	Mathieu Poirier <mathieu.poirier@linaro.org>
+Description:	(RW) Provides access to the stimulus port enable register
+		(STMSPER).  Used in conjunction with "port_select" described
+		below.
+
+What:		/sys/bus/coresight/devices/<memory_map>.stm/port_select
+Date:		April 2016
+KernelVersion:	4.7
+Contact:	Mathieu Poirier <mathieu.poirier@linaro.org>
+Description:	(RW) Used to determine which bank of stimulus port bit in
+		register STMSPER (see above) apply to.
+
+What:		/sys/bus/coresight/devices/<memory_map>.stm/status
+Date:		April 2016
+KernelVersion:	4.7
+Contact:	Mathieu Poirier <mathieu.poirier@linaro.org>
+Description:	(R) List various control and status registers.  The specific
+		layout and content is driver specific.
+
+What:		/sys/bus/coresight/devices/<memory_map>.stm/traceid
+Date:		April 2016
+KernelVersion:	4.7
+Contact:	Mathieu Poirier <mathieu.poirier@linaro.org>
+Description:	(RW) Holds the trace ID that will appear in the trace stream
+		coming from this trace entity.
--- a/Documentation/ABI/testing/sysfs-bus-coresight-devices-tmc
+++ b/Documentation/ABI/testing/sysfs-bus-coresight-devices-tmc
@ -6,3 +6,80 @@ Description:	(RW) Disables write access to the Trace RAM by stopping the
 		formatter after a defined number of words have been stored
 		following the trigger event. Additional interface for this
 		driver are expected to be added as it matures.
+
+What:           /sys/bus/coresight/devices/<memory_map>.tmc/mgmt/rsz
+Date:           March 2016
+KernelVersion:  4.7
+Contact:        Mathieu Poirier <mathieu.poirier@linaro.org>
+Description:    (R) Defines the size, in 32-bit words, of the local RAM buffer.
+                The value is read directly from HW register RSZ, 0x004.
+
+What:           /sys/bus/coresight/devices/<memory_map>.tmc/mgmt/sts
+Date:           March 2016
+KernelVersion:  4.7
+Contact:        Mathieu Poirier <mathieu.poirier@linaro.org>
+Description:	(R) Shows the value held by the TMC status register.  The value
+                is read directly from HW register STS, 0x00C.
+
+What:		/sys/bus/coresight/devices/<memory_map>.tmc/mgmt/rrp
+Date:		March 2016
+KernelVersion:	4.7
+Contact:	Mathieu Poirier <mathieu.poirier@linaro.org>
+Description:	(R) Shows the value held by the TMC RAM Read Pointer register
+		that is used to read entries from the Trace RAM over the APB
+		interface.  The value is read directly from HW register RRP,
+		0x014.
+
+What:		/sys/bus/coresight/devices/<memory_map>.tmc/mgmt/rwp
+Date:		March 2016
+KernelVersion:	4.7
+Contact:	Mathieu Poirier <mathieu.poirier@linaro.org>
+Description:	(R) Shows the value held by the TMC RAM Write Pointer register
+		that is used to sets the write pointer to write entries from
+		the CoreSight bus into the Trace RAM. The value is read directly
+		from HW register RWP, 0x018.
+
+What:		/sys/bus/coresight/devices/<memory_map>.tmc/mgmt/trg
+Date:		March 2016
+KernelVersion:	4.7
+Contact:	Mathieu Poirier <mathieu.poirier@linaro.org>
+Description:	(R) Similar to "trigger_cntr" above except that this value is
+		read directly from HW register TRG, 0x01C.
+
+What:		/sys/bus/coresight/devices/<memory_map>.tmc/mgmt/ctl
+Date:		March 2016
+KernelVersion:	4.7
+Contact:	Mathieu Poirier <mathieu.poirier@linaro.org>
+Description:	(R) Shows the value held by the TMC Control register. The value
+		is read directly from HW register CTL, 0x020.
+
+What:		/sys/bus/coresight/devices/<memory_map>.tmc/mgmt/ffsr
+Date:		March 2016
+KernelVersion:	4.7
+Contact:	Mathieu Poirier <mathieu.poirier@linaro.org>
+Description:	(R) Shows the value held by the TMC Formatter and Flush Status
+		register.  The value is read directly from HW register FFSR,
+		0x300.
+
+What:		/sys/bus/coresight/devices/<memory_map>.tmc/mgmt/ffcr
+Date:		March 2016
+KernelVersion:	4.7
+Contact:	Mathieu Poirier <mathieu.poirier@linaro.org>
+Description:	(R) Shows the value held by the TMC Formatter and Flush Control
+		register.  The value is read directly from HW register FFCR,
+		0x304.
+
+What:		/sys/bus/coresight/devices/<memory_map>.tmc/mgmt/mode
+Date:		March 2016
+KernelVersion:	4.7
+Contact:	Mathieu Poirier <mathieu.poirier@linaro.org>
+Description:	(R) Shows the value held by the TMC Mode register, which
+		indicate the mode the device has been configured to enact.  The
+		The value is read directly from the MODE register, 0x028.
+
+What:		/sys/bus/coresight/devices/<memory_map>.tmc/mgmt/devid
+Date:		March 2016
+KernelVersion:	4.7
+Contact:	Mathieu Poirier <mathieu.poirier@linaro.org>
+Description:	(R) Indicates the capabilities of the Coresight TMC.
+		The value is read directly from the DEVID register, 0xFC8,
--- a/Documentation/ABI/testing/sysfs-class-stm
+++ b/Documentation/ABI/testing/sysfs-class-stm
@ -12,3 +12,13 @@ KernelVersion:	4.3
 Contact:	Alexander Shishkin <alexander.shishkin@linux.intel.com>
 Description:
 		Shows the number of channels per master on this STM device.
+
+What:		/sys/class/stm/<stm>/hw_override
+Date:		March 2016
+KernelVersion:	4.7
+Contact:	Alexander Shishkin <alexander.shishkin@linux.intel.com>
+Description:
+		Reads as 0 if master numbers in the STP stream produced by
+		this stm device will match the master numbers assigned by
+		the software or 1 if the stm hardware overrides software
+		assigned masters.
--- a/Documentation/devicetree/bindings/clock/imx35-clock.txt
+++ b/Documentation/devicetree/bindings/clock/imx35-clock.txt
@ -94,6 +94,7 @@ clocks and IDs.
 	csi_sel			79
 	iim_gate		80
 	gpu2d_gate		81
+	ckli_gate		82

 Examples:

--- a/Documentation/serial/tty.txt
+++ b/Documentation/serial/tty.txt
@ -213,9 +213,6 @@ TTY_IO_ERROR		If set, causes all subsequent userspace read/write

 TTY_OTHER_CLOSED	Device is a pty and the other side has closed.

-TTY_OTHER_DONE		Device is a pty and the other side has closed and
-			all pending input processing has been completed.
-
 TTY_NO_WRITE_SPLIT	Prevent driver from splitting up writes into
 			smaller chunks.

--- a/Documentation/sysctl/fs.txt
+++ b/Documentation/sysctl/fs.txt
@ -32,6 +32,8 @@ Currently, these files are in /proc/sys/fs:
 - nr_open
 - overflowuid
 - overflowgid
+- pipe-user-pages-hard
+- pipe-user-pages-soft
 - protected_hardlinks
 - protected_symlinks
 - suid_dumpable
@ -159,6 +161,27 @@ The default is 65534.

 ==============================================================

+pipe-user-pages-hard:
+
+Maximum total number of pages a non-privileged user may allocate for pipes.
+Once this limit is reached, no new pipes may be allocated until usage goes
+below the limit again. When set to 0, no limit is applied, which is the default
+setting.
+
+==============================================================
+
+pipe-user-pages-soft:
+
+Maximum total number of pages a non-privileged user may allocate for pipes
+before the pipe size gets limited to a single page. Once this limit is reached,
+new pipes will be limited to a single page in size for this user in order to
+limit total memory usage, and trying to increase them using fcntl() will be
+denied until usage goes below the limit again. The default value allows to
+allocate up to 1024 pipes at their default size. When set to 0, no limit is
+applied.
+
+==============================================================
+
 protected_hardlinks:

 A long-standing class of security issues is the hardlink-based
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@ -58,6 +58,8 @@ show up in /proc/sys/kernel:
 - panic_on_stackoverflow
 - panic_on_unrecovered_nmi
 - panic_on_warn
+- perf_cpu_time_max_percent
+- perf_event_paranoid
 - pid_max
 - powersave-nap               [ PPC only ]
 - printk
@ -624,6 +626,19 @@ allowed to execute.

 ==============================================================

+perf_event_paranoid:
+
+Controls use of the performance events system by unprivileged
+users (without CAP_SYS_ADMIN).  The default value is 3 if
+CONFIG_SECURITY_PERF_EVENTS_RESTRICT is set, or 1 otherwise.
+
+ -1: Allow use of (almost) all events by all users
+>=0: Disallow raw tracepoint access by users without CAP_IOC_LOCK
+>=1: Disallow CPU event access by users without CAP_SYS_ADMIN
+>=2: Disallow kernel profiling by users without CAP_SYS_ADMIN
+>=3: Disallow all event access by users without CAP_SYS_ADMIN
+
+==============================================================

 pid_max:

--- a/Documentation/trace/coresight.txt
+++ b/Documentation/trace/coresight.txt
@ -190,8 +190,8 @@ expected to be accessed and controlled using those entries.
 Last but not least, "struct module *owner" is expected to be set to reflect
 the information carried in "THIS_MODULE".

-How to use
----------
+How to use the tracer modules
+-----------------------------

 Before trace collection can start, a coresight sink needs to be identify.
 There is no limit on the amount of sinks (nor sources) that can be enabled at
@ -297,3 +297,36 @@ Info                                    Tracing enabled
 Instruction     13570831        0x8026B584      E28DD00C        false   ADD      sp,sp,#0xc
 Instruction     0       0x8026B588      E8BD8000        true    LDM      sp!,{pc}
 Timestamp                                       Timestamp: 17107041535
+
+How to use the STM module
+-------------------------
+
+Using the System Trace Macrocell module is the same as the tracers - the only
+difference is that clients are driving the trace capture rather
+than the program flow through the code.
+
+As with any other CoreSight component, specifics about the STM tracer can be
+found in sysfs with more information on each entry being found in [1]:
+
+root@genericarmv8:~# ls /sys/bus/coresight/devices/20100000.stm
+enable_source   hwevent_select  port_enable     subsystem       uevent
+hwevent_enable  mgmt            port_select     traceid
+root@genericarmv8:~#
+
+Like any other source a sink needs to be identified and the STM enabled before
+being used:
+
+root@genericarmv8:~# echo 1 > /sys/bus/coresight/devices/20010000.etf/enable_sink
+root@genericarmv8:~# echo 1 > /sys/bus/coresight/devices/20100000.stm/enable_source
+
+From there user space applications can request and use channels using the devfs
+interface provided for that purpose by the generic STM API:
+
+root@genericarmv8:~# ls -l /dev/20100000.stm
+crw-------    1 root     root       10,  61 Jan  3 18:11 /dev/20100000.stm
+root@genericarmv8:~#
+
+Details on how to use the generic STM API can be found here [2].
+
+[1]. Documentation/ABI/testing/sysfs-bus-coresight-devices-stm
+[2]. Documentation/trace/stm.txt
--- a/5
+++ b/5
@ -1007,6 +1007,10 @@ F:	drivers/hwtracing/coresight/*
 F:	Documentation/trace/coresight.txt
 F:	Documentation/devicetree/bindings/arm/coresight.txt
 F:	Documentation/ABI/testing/sysfs-bus-coresight-devices-*
+F:	tools/perf/arch/arm/util/pmu.c
+F:	tools/perf/arch/arm/util/auxtrace.c
+F:	tools/perf/arch/arm/util/cs_etm.c
+F:	tools/perf/arch/arm/util/cs_etm.h

 ARM/CORGI MACHINE SUPPORT
 M:	Richard Purdie <rpurdie@rpsys.net>
@ -9356,6 +9360,7 @@ F:	drivers/mmc/host/dw_mmc*
 SYSTEM TRACE MODULE CLASS
 M:	Alexander Shishkin <alexander.shishkin@linux.intel.com>
 S:	Maintained
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/ash/stm.git
 F:	Documentation/trace/stm.txt
 F:	drivers/hwtracing/stm/
 F:	include/linux/stm.h
--- a/9
+++ b/9
@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 4
-SUBLEVEL = 11
+SUBLEVEL = 14
 EXTRAVERSION =
 NAME = Blurry Fish Butt

@ -376,7 +376,7 @@ AFLAGS_MODULE   =
 LDFLAGS_MODULE  =
 CFLAGS_KERNEL	=
 AFLAGS_KERNEL	=
-CFLAGS_GCOV	= -fprofile-arcs -ftest-coverage
+CFLAGS_GCOV	= -fprofile-arcs -ftest-coverage -fno-tree-loop-im


 # Use USERINCLUDE when you must reference the UAPI directories only.
@ -694,9 +694,10 @@ KBUILD_CFLAGS += $(call cc-option, -mno-global-merge,)
 KBUILD_CFLAGS += $(call cc-option, -fcatch-undefined-behavior)
 else

-# This warning generated too much noise in a regular build.
-# Use make W=1 to enable this warning (see scripts/Makefile.build)
+# These warnings generated too much noise in a regular build.
+# Use make W=1 to enable them (see scripts/Makefile.build)
 KBUILD_CFLAGS += $(call cc-disable-warning, unused-but-set-variable)
+KBUILD_CFLAGS += $(call cc-disable-warning, unused-const-variable)
 endif

 ifdef CONFIG_FRAME_POINTER
--- a/android/configs/android-base.cfg
+++ b/android/configs/android-base.cfg
@ -57,6 +57,7 @@ CONFIG_IP_NF_MANGLE=y
 CONFIG_IP_NF_MATCH_AH=y
 CONFIG_IP_NF_MATCH_ECN=y
 CONFIG_IP_NF_MATCH_TTL=y
+CONFIG_IP_NF_NAT=y
 CONFIG_IP_NF_RAW=y
 CONFIG_IP_NF_SECURITY=y
 CONFIG_IP_NF_TARGET_MASQUERADE=y
@ -138,15 +139,16 @@ CONFIG_PPP_BSDCOMP=y
 CONFIG_PPP_DEFLATE=y
 CONFIG_PPP_MPPE=y
 CONFIG_PREEMPT=y
+CONFIG_QUOTA=y
 CONFIG_RESOURCE_COUNTERS=y
 CONFIG_RTC_CLASS=y
 CONFIG_RT_GROUP_SCHED=y
 CONFIG_SECURITY=y
 CONFIG_SECURITY_NETWORK=y
+CONFIG_SECURITY_PERF_EVENTS_RESTRICT=y
 CONFIG_SECURITY_SELINUX=y
 CONFIG_SETEND_EMULATION=y
 CONFIG_STAGING=y
-CONFIG_SWITCH=y
 CONFIG_SWP_EMULATION=y
 CONFIG_SYNC=y
 CONFIG_TUN=y
--- a/android/configs/android-recommended.cfg
+++ b/android/configs/android-recommended.cfg
@ -119,7 +119,6 @@ CONFIG_TIMER_STATS=y
 CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
 CONFIG_UHID=y
-CONFIG_UID_STAT=y
 CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_HIDDEV=y
--- a/arch/arm/boot/dts/armada-385-linksys.dtsi
+++ b/arch/arm/boot/dts/armada-385-linksys.dtsi
@ -245,7 +245,7 @@ button@1 {
 		button@2 {
 			label = "Factory Reset Button";
 			linux,code = <KEY_RESTART>;
-			gpios = <&gpio1 15 GPIO_ACTIVE_LOW>;
+			gpios = <&gpio0 29 GPIO_ACTIVE_LOW>;
 		};
 	};

@ -260,7 +260,7 @@ power {
 		};

 		sata {
-			gpios = <&gpio1 22 GPIO_ACTIVE_HIGH>;
+			gpios = <&gpio1 22 GPIO_ACTIVE_LOW>;
 			default-state = "off";
 		};
 	};
@ -313,7 +313,7 @@ port@5 {

 &pinctrl {
 	keys_pin: keys-pin {
-		marvell,pins = "mpp24", "mpp47";
+		marvell,pins = "mpp24", "mpp29";
 		marvell,function = "gpio";
 	};

--- a/arch/arm/boot/dts/armada-xp-linksys-mamba.dts
+++ b/arch/arm/boot/dts/armada-xp-linksys-mamba.dts
@ -304,13 +304,13 @@ gpio_keys {
 		button@1 {
 			label = "WPS";
 			linux,code = <KEY_WPS_BUTTON>;
-			gpios = <&gpio1 0 GPIO_ACTIVE_HIGH>;
+			gpios = <&gpio1 0 GPIO_ACTIVE_LOW>;
 		};

 		button@2 {
 			label = "Factory Reset Button";
 			linux,code = <KEY_RESTART>;
-			gpios = <&gpio1 1 GPIO_ACTIVE_HIGH>;
+			gpios = <&gpio1 1 GPIO_ACTIVE_LOW>;
 		};
 	};

--- a/arch/arm/boot/dts/exynos4210-trats.dts
+++ b/arch/arm/boot/dts/exynos4210-trats.dts
@ -298,6 +298,8 @@ max8997_pmic@66 {
 		compatible = "maxim,max8997-pmic";

 		reg = <0x66>;
+		interrupt-parent = <&gpx0>;
+		interrupts = <7 0>;

 		max8997,pmic-buck1-uses-gpio-dvs;
 		max8997,pmic-buck2-uses-gpio-dvs;
--- a/arch/arm/boot/dts/sama5d2-pinfunc.h
+++ b/arch/arm/boot/dts/sama5d2-pinfunc.h
@ -837,8 +837,8 @@
 #define PIN_PD23__ISC_FIELD		PINMUX_PIN(PIN_PD23, 6, 4)
 #define PIN_PD24			120
 #define PIN_PD24__GPIO			PINMUX_PIN(PIN_PD24, 0, 0)
-#define PIN_PD24__UTXD2			PINMUX_PIN(PIN_PD23, 1, 2)
-#define PIN_PD24__FLEXCOM4_IO3		PINMUX_PIN(PIN_PD23, 3, 3)
+#define PIN_PD24__UTXD2			PINMUX_PIN(PIN_PD24, 1, 2)
+#define PIN_PD24__FLEXCOM4_IO3		PINMUX_PIN(PIN_PD24, 3, 3)
 #define PIN_PD25			121
 #define PIN_PD25__GPIO			PINMUX_PIN(PIN_PD25, 0, 0)
 #define PIN_PD25__SPI1_SPCK		PINMUX_PIN(PIN_PD25, 1, 3)
--- a/arch/arm/include/asm/mach/mmc.h
+++ b/arch/arm/include/asm/mach/mmc.h
@ -1,28 +0,0 @@
-/*
- *  arch/arm/include/asm/mach/mmc.h
- */
-#ifndef ASMARM_MACH_MMC_H
-#define ASMARM_MACH_MMC_H
-
-#include <linux/mmc/host.h>
-#include <linux/mmc/card.h>
-#include <linux/mmc/sdio_func.h>
-
-struct embedded_sdio_data {
-        struct sdio_cis cis;
-        struct sdio_cccr cccr;
-        struct sdio_embedded_func *funcs;
-        int num_funcs;
-};
-
-struct mmc_platform_data {
-	unsigned int ocr_mask;			/* available voltages */
-	int built_in;				/* built-in device flag */
-	int card_present;			/* card detect state */
-	u32 (*translate_vdd)(struct device *, unsigned int);
-	unsigned int (*status)(struct device *);
-	struct embedded_sdio_data *embedded_sdio;
-	int (*register_status_notify)(void (*callback)(int card_present, void *dev_id), void *dev_id);
-};
-
-#endif
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@ -733,8 +733,8 @@ static int vfp_set(struct task_struct *target,
 	if (ret)
 		return ret;

-	vfp_flush_hwstate(thread);
 	thread->vfpstate.hard = new_vfp;
+	vfp_flush_hwstate(thread);

 	return 0;
 }
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@ -886,11 +886,14 @@ static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache
 	VM_BUG_ON(pmd_present(*pmd) && pmd_pfn(*pmd) != pmd_pfn(*new_pmd));

 	old_pmd = *pmd;
-	kvm_set_pmd(pmd, *new_pmd);
-	if (pmd_present(old_pmd))
+	if (pmd_present(old_pmd)) {
+		pmd_clear(pmd);
 		kvm_tlb_flush_vmid_ipa(kvm, addr);
-	else
+	} else {
 		get_page(virt_to_page(pmd));
+	}
+
+	kvm_set_pmd(pmd, *new_pmd);
 	return 0;
 }

@ -939,12 +942,14 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,

 	/* Create 2nd stage page table mapping - Level 3 */
 	old_pte = *pte;
-	kvm_set_pte(pte, *new_pte);
-	if (pte_present(old_pte))
+	if (pte_present(old_pte)) {
+		kvm_set_pte(pte, __pte(0));
 		kvm_tlb_flush_vmid_ipa(kvm, addr);
-	else
+	} else {
 		get_page(virt_to_page(pte));
+	}

+	kvm_set_pte(pte, *new_pte);
 	return 0;
 }

--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@ -116,7 +116,7 @@ dtbs: prepare scripts
 dtbs_install:
 	$(Q)$(MAKE) $(dtbinst)=$(boot)/dts

-Image.gz-dtb: vmlinux scripts dtbs
+Image-dtb Image.gz-dtb: vmlinux scripts dtbs
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@

 PHONY += vdso_install
--- a/arch/arm64/boot/.gitignore
+++ b/arch/arm64/boot/.gitignore
@ -1,3 +1,4 @@
 Image
+Image-dtb
 Image.gz
 Image.gz-dtb
--- a/arch/arm64/boot/Makefile
+++ b/arch/arm64/boot/Makefile
@ -32,6 +32,9 @@ $(obj)/Image: vmlinux FORCE
 $(obj)/Image.bz2: $(obj)/Image FORCE
 	$(call if_changed,bzip2)

+$(obj)/Image-dtb: $(obj)/Image $(DTB_OBJS) FORCE
+	$(call if_changed,cat)
+
 $(obj)/Image.gz: $(obj)/Image FORCE
 	$(call if_changed,gzip)

--- a/arch/arm64/boot/dts/arm/juno.dts
+++ b/arch/arm64/boot/dts/arm/juno.dts
@ -143,5 +143,310 @@ pmu_a53 {
 				     <&A53_3>;
 	};

+	etr@20070000 {
+		compatible = "arm,coresight-tmc", "arm,primecell";
+		reg = <0 0x20070000 0 0x1000>;
+
+		clocks = <&soc_smc50mhz>;
+		clock-names = "apb_pclk";
+		port {
+			etr_in_port: endpoint {
+				slave-mode;
+				remote-endpoint = <&replicator_out_port1>;
+			};
+		};
+	};
+
+	tpiu@20030000 {
+		compatible = "arm,coresight-tpiu", "arm,primecell";
+		reg = <0 0x20030000 0 0x1000>;
+
+		clocks = <&soc_smc50mhz>;
+		clock-names = "apb_pclk";
+		port {
+			tpiu_in_port: endpoint {
+				slave-mode;
+				remote-endpoint = <&replicator_out_port0>;
+			};
+		};
+	};
+
+	replicator@20020000 {
+		/* non-configurable replicators don't show up on the
+		 * AMBA bus.  As such no need to add "arm,primecell".
+		 */
+		compatible = "arm,coresight-replicator";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* replicator output ports */
+			port@0 {
+				reg = <0>;
+				replicator_out_port0: endpoint {
+					remote-endpoint = <&tpiu_in_port>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+				replicator_out_port1: endpoint {
+					remote-endpoint = <&etr_in_port>;
+				};
+			};
+
+			/* replicator input port */
+			port@2 {
+				reg = <0>;
+				replicator_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&etf_out_port>;
+				};
+			};
+		};
+	};
+
+	etf@20010000 {
+		compatible = "arm,coresight-tmc", "arm,primecell";
+		reg = <0 0x20010000 0 0x1000>;
+
+		clocks = <&soc_smc50mhz>;
+		clock-names = "apb_pclk";
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* input port */
+			port@0 {
+				reg = <0>;
+				etf_in_port: endpoint {
+					slave-mode;
+					remote-endpoint =
+						<&main_funnel_out_port>;
+				};
+			};
+
+			/* output port */
+			port@1 {
+				reg = <0>;
+				etf_out_port: endpoint {
+					remote-endpoint =
+						<&replicator_in_port0>;
+				};
+			};
+		};
+	};
+
+	main_funnel@20040000 {
+		compatible = "arm,coresight-funnel", "arm,primecell";
+		reg = <0 0x20040000 0 0x1000>;
+
+		clocks = <&soc_smc50mhz>;
+		clock-names = "apb_pclk";
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+				main_funnel_out_port: endpoint {
+					remote-endpoint =
+						<&etf_in_port>;
+				};
+			};
+
+			port@1 {
+				reg = <0>;
+				main_funnel_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint =
+						<&A72_57_funnel_out_port>;
+				};
+			};
+
+			port@2 {
+				reg = <1>;
+				main_funnel_in_port1: endpoint {
+					slave-mode;
+					remote-endpoint = <&A53_funnel_out_port>;
+				};
+			};
+
+		};
+	};
+
+	A72_57_funnel@220c0000 {
+		compatible = "arm,coresight-funnel", "arm,primecell";
+		reg = <0 0x220c0000 0 0x1000>;
+
+		clocks = <&soc_smc50mhz>;
+		clock-names = "apb_pclk";
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+				A72_57_funnel_out_port: endpoint {
+					remote-endpoint =
+						<&main_funnel_in_port0>;
+				};
+			};
+
+			port@1 {
+				reg = <0>;
+				A72_57_funnel_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint =
+							<&A72_57_etm0_out_port>;
+				};
+			};
+
+			port@2 {
+				reg = <1>;
+				A72_57_funnel_in_port1: endpoint {
+					slave-mode;
+					remote-endpoint =
+							<&A72_57_etm1_out_port>;
+				};
+			};
+		};
+	};
+
+	A53_funnel@220c0000 {
+		compatible = "arm,coresight-funnel", "arm,primecell";
+		reg = <0 0x230c0000 0 0x1000>;
+
+		clocks = <&soc_smc50mhz>;
+		clock-names = "apb_pclk";
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+				A53_funnel_out_port: endpoint {
+					remote-endpoint =
+						<&main_funnel_in_port1>;
+				};
+			};
+
+			port@1 {
+				reg = <0>;
+				A53_funnel_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&A53_etm0_out_port>;
+				};
+			};
+
+			port@2 {
+				reg = <1>;
+				A53_funnel_in_port1: endpoint {
+					slave-mode;
+					remote-endpoint = <&A53_etm1_out_port>;
+				};
+			};
+			port@3 {
+				reg = <2>;
+				A53_funnel_in_port2: endpoint {
+					slave-mode;
+					remote-endpoint = <&A53_etm2_out_port>;
+				};
+			};
+			port@4 {
+				reg = <3>;
+				A53_funnel_in_port3: endpoint {
+					slave-mode;
+					remote-endpoint = <&A53_etm3_out_port>;
+				};
+			};
+		};
+	};
+
+	etm@22040000 {
+		compatible = "arm,coresight-etm4x", "arm,primecell";
+		reg = <0 0x22040000 0 0x1000>;
+
+		cpu = <&A57_0>;
+		clocks = <&soc_smc50mhz>;
+		clock-names = "apb_pclk";
+		port {
+			A72_57_etm0_out_port: endpoint {
+				remote-endpoint = <&A72_57_funnel_in_port0>;
+			};
+		};
+	};
+
+	etm@22140000 {
+		compatible = "arm,coresight-etm4x", "arm,primecell";
+		reg = <0 0x22140000 0 0x1000>;
+
+		cpu = <&A57_1>;
+		clocks = <&soc_smc50mhz>;
+		clock-names = "apb_pclk";
+		port {
+			A72_57_etm1_out_port: endpoint {
+				remote-endpoint = <&A72_57_funnel_in_port1>;
+			};
+		};
+	};
+
+	etm@23040000 {
+		compatible = "arm,coresight-etm4x", "arm,primecell";
+		reg = <0 0x23040000 0 0x1000>;
+
+		cpu = <&A53_0>;
+		clocks = <&soc_smc50mhz>;
+		clock-names = "apb_pclk";
+		port {
+			A53_etm0_out_port: endpoint {
+				remote-endpoint = <&A53_funnel_in_port0>;
+			};
+		};
+	};
+
+	etm@23140000 {
+		compatible = "arm,coresight-etm4x", "arm,primecell";
+		reg = <0 0x23140000 0 0x1000>;
+
+		cpu = <&A53_1>;
+		clocks = <&soc_smc50mhz>;
+		clock-names = "apb_pclk";
+		port {
+			A53_etm1_out_port: endpoint {
+				remote-endpoint = <&A53_funnel_in_port1>;
+			};
+		};
+	};
+
+	etm@23240000 {
+		compatible = "arm,coresight-etm4x", "arm,primecell";
+		reg = <0 0x23240000 0 0x1000>;
+
+		cpu = <&A53_2>;
+		clocks = <&soc_smc50mhz>;
+		clock-names = "apb_pclk";
+		port {
+			A53_etm2_out_port: endpoint {
+				remote-endpoint = <&A53_funnel_in_port2>;
+			};
+		};
+	};
+
+	etm@23340000 {
+		compatible = "arm,coresight-etm4x", "arm,primecell";
+		reg = <0 0x23340000 0 0x1000>;
+
+		cpu = <&A53_3>;
+		clocks = <&soc_smc50mhz>;
+		clock-names = "apb_pclk";
+		port {
+			A53_etm3_out_port: endpoint {
+				remote-endpoint = <&A53_funnel_in_port3>;
+			};
+		};
+	};
+
 	#include "juno-base.dtsi"
 };
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@ -160,14 +160,14 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm,
 #define STACK_RND_MASK			(0x3ffff >> (PAGE_SHIFT - 12))
 #endif

-#ifdef CONFIG_COMPAT
-
 #ifdef __AARCH64EB__
 #define COMPAT_ELF_PLATFORM		("v8b")
 #else
 #define COMPAT_ELF_PLATFORM		("v8l")
 #endif

+#ifdef CONFIG_COMPAT
+
 #define COMPAT_ELF_ET_DYN_BASE		(2 * TASK_SIZE_32 / 3)

 /* AArch32 registers. */
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@ -133,7 +133,6 @@
 * Section
 */
 #define PMD_SECT_VALID		(_AT(pmdval_t, 1) << 0)
-#define PMD_SECT_PROT_NONE	(_AT(pmdval_t, 1) << 58)
 #define PMD_SECT_USER		(_AT(pmdval_t, 1) << 6)		/* AP[1] */
 #define PMD_SECT_RDONLY		(_AT(pmdval_t, 1) << 7)		/* AP[2] */
 #define PMD_SECT_S		(_AT(pmdval_t, 3) << 8)
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@ -348,6 +348,7 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
 #endif /* CONFIG_HAVE_RCU_TABLE_FREE */
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */

+#define pmd_present(pmd)	pte_present(pmd_pte(pmd))
 #define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
 #define pmd_young(pmd)		pte_young(pmd_pte(pmd))
 #define pmd_wrprotect(pmd)	pte_pmd(pte_wrprotect(pmd_pte(pmd)))
@ -357,7 +358,7 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
 #define pmd_mkclean(pmd)       pte_pmd(pte_mkclean(pmd_pte(pmd)))
 #define pmd_mkdirty(pmd)	pte_pmd(pte_mkdirty(pmd_pte(pmd)))
 #define pmd_mkyoung(pmd)	pte_pmd(pte_mkyoung(pmd_pte(pmd)))
-#define pmd_mknotpresent(pmd)	(__pmd(pmd_val(pmd) & ~PMD_TYPE_MASK))
+#define pmd_mknotpresent(pmd)	(__pmd(pmd_val(pmd) & ~PMD_SECT_VALID))

 #define __HAVE_ARCH_PMD_WRITE
 #define pmd_write(pmd)		pte_write(pmd_pte(pmd))
@ -396,7 +397,6 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 				     unsigned long size, pgprot_t vma_prot);

 #define pmd_none(pmd)		(!pmd_val(pmd))
-#define pmd_present(pmd)	(pmd_val(pmd))

 #define pmd_bad(pmd)		(!(pmd_val(pmd) & 2))

@ -595,6 +595,21 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 }

 #ifdef CONFIG_ARM64_HW_AFDBM
+#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+extern int ptep_set_access_flags(struct vm_area_struct *vma,
+				 unsigned long address, pte_t *ptep,
+				 pte_t entry, int dirty);
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
+static inline int pmdp_set_access_flags(struct vm_area_struct *vma,
+					unsigned long address, pmd_t *pmdp,
+					pmd_t entry, int dirty)
+{
+	return ptep_set_access_flags(vma, address, (pte_t *)pmdp, pmd_pte(entry), dirty);
+}
+#endif
+
 /*
 * Atomic pte/pmd modifications.
 */
@ -647,9 +662,9 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 }

 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-#define __HAVE_ARCH_PMDP_GET_AND_CLEAR
-static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm,
-				       unsigned long address, pmd_t *pmdp)
+#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
+static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
+					    unsigned long address, pmd_t *pmdp)
 {
 	return pte_pmd(ptep_get_and_clear(mm, address, (pte_t *)pmdp));
 }
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@ -22,6 +22,8 @@

 #include <linux/bitops.h>
 #include <linux/bug.h>
+#include <linux/compat.h>
+#include <linux/elf.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/personality.h>
@ -85,7 +87,8 @@ static const char *const compat_hwcap_str[] = {
 	"idivt",
 	"vfpd32",
 	"lpae",
-	"evtstrm"
+	"evtstrm",
+	NULL
 };

 static const char *const compat_hwcap2_str[] = {
@ -101,6 +104,7 @@ static const char *const compat_hwcap2_str[] = {
 static int c_show(struct seq_file *m, void *v)
 {
 	int i, j;
+	bool compat = personality(current->personality) == PER_LINUX32;

 	for_each_online_cpu(i) {
 		struct cpuinfo_arm64 *cpuinfo = &per_cpu(cpu_data, i);
@ -112,6 +116,9 @@ static int c_show(struct seq_file *m, void *v)
 		 * "processor".  Give glibc what it expects.
 		 */
 		seq_printf(m, "processor\t: %d\n", i);
+		if (compat)
+			seq_printf(m, "model name\t: ARMv8 Processor rev %d (%s)\n",
+				   MIDR_REVISION(midr), COMPAT_ELF_PLATFORM);

 		seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
 			   loops_per_jiffy / (500000UL/HZ),
@ -124,7 +131,7 @@ static int c_show(struct seq_file *m, void *v)
 		 * software which does already (at least for 32-bit).
 		 */
 		seq_puts(m, "Features\t:");
-		if (personality(current->personality) == PER_LINUX32) {
+		if (compat) {
 #ifdef CONFIG_COMPAT
 			for (j = 0; compat_hwcap_str[j]; j++)
 				if (compat_elf_hwcap & (1 << j))
--- a/arch/arm64/kvm/inject_fault.c
+++ b/arch/arm64/kvm/inject_fault.c
@ -130,7 +130,7 @@ static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr
 		esr |= (ESR_ELx_EC_IABT_CUR << ESR_ELx_EC_SHIFT);

 	if (!is_iabt)
-		esr |= ESR_ELx_EC_DABT_LOW;
+		esr |= ESR_ELx_EC_DABT_LOW << ESR_ELx_EC_SHIFT;

 	vcpu_sys_reg(vcpu, ESR_EL1) = esr | ESR_ELx_FSC_EXTABT;
 }
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@ -81,6 +81,56 @@ void show_pte(struct mm_struct *mm, unsigned long addr)
 	printk("\n");
 }

+#ifdef CONFIG_ARM64_HW_AFDBM
+/*
+ * This function sets the access flags (dirty, accessed), as well as write
+ * permission, and only to a more permissive setting.
+ *
+ * It needs to cope with hardware update of the accessed/dirty state by other
+ * agents in the system and can safely skip the __sync_icache_dcache() call as,
+ * like set_pte_at(), the PTE is never changed from no-exec to exec here.
+ *
+ * Returns whether or not the PTE actually changed.
+ */
+int ptep_set_access_flags(struct vm_area_struct *vma,
+			  unsigned long address, pte_t *ptep,
+			  pte_t entry, int dirty)
+{
+	pteval_t old_pteval;
+	unsigned int tmp;
+
+	if (pte_same(*ptep, entry))
+		return 0;
+
+	/* only preserve the access flags and write permission */
+	pte_val(entry) &= PTE_AF | PTE_WRITE | PTE_DIRTY;
+
+	/*
+	 * PTE_RDONLY is cleared by default in the asm below, so set it in
+	 * back if necessary (read-only or clean PTE).
+	 */
+	if (!pte_write(entry) || !pte_sw_dirty(entry))
+		pte_val(entry) |= PTE_RDONLY;
+
+	/*
+	 * Setting the flags must be done atomically to avoid racing with the
+	 * hardware update of the access/dirty state.
+	 */
+	asm volatile("//	ptep_set_access_flags\n"
+	"	prfm	pstl1strm, %2\n"
+	"1:	ldxr	%0, %2\n"
+	"	and	%0, %0, %3		// clear PTE_RDONLY\n"
+	"	orr	%0, %0, %4		// set flags\n"
+	"	stxr	%w1, %0, %2\n"
+	"	cbnz	%w1, 1b\n"
+	: "=&r" (old_pteval), "=&r" (tmp), "+Q" (pte_val(*ptep))
+	: "L" (~PTE_RDONLY), "r" (pte_val(entry)));
+
+	flush_tlb_fix_spurious_fault(vma, address);
+	return 1;
+}
+#endif
+
 /*
 * The kernel tried to access some page that wasn't present.
 */
--- a/arch/mips/ath79/early_printk.c
+++ b/arch/mips/ath79/early_printk.c
@ -31,13 +31,15 @@ static inline void prom_putchar_wait(void __iomem *reg, u32 mask, u32 val)
 	} while (1);
 }

+#define BOTH_EMPTY (UART_LSR_TEMT | UART_LSR_THRE)
+
 static void prom_putchar_ar71xx(unsigned char ch)
 {
 	void __iomem *base = (void __iomem *)(KSEG1ADDR(AR71XX_UART_BASE));

-	prom_putchar_wait(base + UART_LSR * 4, UART_LSR_THRE, UART_LSR_THRE);
+	prom_putchar_wait(base + UART_LSR * 4, BOTH_EMPTY, BOTH_EMPTY);
 	__raw_writel(ch, base + UART_TX * 4);
-	prom_putchar_wait(base + UART_LSR * 4, UART_LSR_THRE, UART_LSR_THRE);
+	prom_putchar_wait(base + UART_LSR * 4, BOTH_EMPTY, BOTH_EMPTY);
 }

 static void prom_putchar_ar933x(unsigned char ch)
--- a/arch/mips/include/asm/asmmacro.h
+++ b/arch/mips/include/asm/asmmacro.h
@ -298,21 +298,21 @@
 	.set	pop
 	.endm

-	.macro	copy_u_w	ws, n
+	.macro	copy_s_w	ws, n
 	.set	push
 	.set	mips32r2
 	.set	fp=64
 	.set	msa
-	copy_u.w $1, $w\ws[\n]
+	copy_s.w $1, $w\ws[\n]
 	.set	pop
 	.endm

-	.macro	copy_u_d	ws, n
+	.macro	copy_s_d	ws, n
 	.set	push
 	.set	mips64r2
 	.set	fp=64
 	.set	msa
-	copy_u.d $1, $w\ws[\n]
+	copy_s.d $1, $w\ws[\n]
 	.set	pop
 	.endm

@ -346,8 +346,8 @@
 #define STH_MSA_INSN		0x5800081f
 #define STW_MSA_INSN		0x5800082f
 #define STD_MSA_INSN		0x5800083f
-#define COPY_UW_MSA_INSN	0x58f00056
-#define COPY_UD_MSA_INSN	0x58f80056
+#define COPY_SW_MSA_INSN	0x58b00056
+#define COPY_SD_MSA_INSN	0x58b80056
 #define INSERT_W_MSA_INSN	0x59300816
 #define INSERT_D_MSA_INSN	0x59380816
 #else
@ -361,8 +361,8 @@
 #define STH_MSA_INSN		0x78000825
 #define STW_MSA_INSN		0x78000826
 #define STD_MSA_INSN		0x78000827
-#define COPY_UW_MSA_INSN	0x78f00059
-#define COPY_UD_MSA_INSN	0x78f80059
+#define COPY_SW_MSA_INSN	0x78b00059
+#define COPY_SD_MSA_INSN	0x78b80059
 #define INSERT_W_MSA_INSN	0x79300819
 #define INSERT_D_MSA_INSN	0x79380819
 #endif
@ -393,7 +393,7 @@
 	.set	push
 	.set	noat
 	SET_HARDFLOAT
-	addu	$1, \base, \off
+	PTR_ADDU $1, \base, \off
 	.word	LDB_MSA_INSN | (\wd << 6)
 	.set	pop
 	.endm
@ -402,7 +402,7 @@
 	.set	push
 	.set	noat
 	SET_HARDFLOAT
-	addu	$1, \base, \off
+	PTR_ADDU $1, \base, \off
 	.word	LDH_MSA_INSN | (\wd << 6)
 	.set	pop
 	.endm
@ -411,7 +411,7 @@
 	.set	push
 	.set	noat
 	SET_HARDFLOAT
-	addu	$1, \base, \off
+	PTR_ADDU $1, \base, \off
 	.word	LDW_MSA_INSN | (\wd << 6)
 	.set	pop
 	.endm
@ -420,7 +420,7 @@
 	.set	push
 	.set	noat
 	SET_HARDFLOAT
-	addu	$1, \base, \off
+	PTR_ADDU $1, \base, \off
 	.word	LDD_MSA_INSN | (\wd << 6)
 	.set	pop
 	.endm
@ -429,7 +429,7 @@
 	.set	push
 	.set	noat
 	SET_HARDFLOAT
-	addu	$1, \base, \off
+	PTR_ADDU $1, \base, \off
 	.word	STB_MSA_INSN | (\wd << 6)
 	.set	pop
 	.endm
@ -438,7 +438,7 @@
 	.set	push
 	.set	noat
 	SET_HARDFLOAT
-	addu	$1, \base, \off
+	PTR_ADDU $1, \base, \off
 	.word	STH_MSA_INSN | (\wd << 6)
 	.set	pop
 	.endm
@ -447,7 +447,7 @@
 	.set	push
 	.set	noat
 	SET_HARDFLOAT
-	addu	$1, \base, \off
+	PTR_ADDU $1, \base, \off
 	.word	STW_MSA_INSN | (\wd << 6)
 	.set	pop
 	.endm
@ -456,26 +456,26 @@
 	.set	push
 	.set	noat
 	SET_HARDFLOAT
-	addu	$1, \base, \off
+	PTR_ADDU $1, \base, \off
 	.word	STD_MSA_INSN | (\wd << 6)
 	.set	pop
 	.endm

-	.macro	copy_u_w	ws, n
+	.macro	copy_s_w	ws, n
 	.set	push
 	.set	noat
 	SET_HARDFLOAT
 	.insn
-	.word	COPY_UW_MSA_INSN | (\n << 16) | (\ws << 11)
+	.word	COPY_SW_MSA_INSN | (\n << 16) | (\ws << 11)
 	.set	pop
 	.endm

-	.macro	copy_u_d	ws, n
+	.macro	copy_s_d	ws, n
 	.set	push
 	.set	noat
 	SET_HARDFLOAT
 	.insn
-	.word	COPY_UD_MSA_INSN | (\n << 16) | (\ws << 11)
+	.word	COPY_SD_MSA_INSN | (\n << 16) | (\ws << 11)
 	.set	pop
 	.endm

--- a/arch/mips/include/asm/cacheflush.h
+++ b/arch/mips/include/asm/cacheflush.h
@ -51,7 +51,6 @@ extern void (*flush_cache_range)(struct vm_area_struct *vma,
 	unsigned long start, unsigned long end);
 extern void (*flush_cache_page)(struct vm_area_struct *vma, unsigned long page, unsigned long pfn);
 extern void __flush_dcache_page(struct page *page);
-extern void __flush_icache_page(struct vm_area_struct *vma, struct page *page);

 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 static inline void flush_dcache_page(struct page *page)
@ -77,11 +76,6 @@ static inline void flush_anon_page(struct vm_area_struct *vma,
 static inline void flush_icache_page(struct vm_area_struct *vma,
 	struct page *page)
 {
-	if (!cpu_has_ic_fills_f_dc && (vma->vm_flags & VM_EXEC) &&
-	    Page_dcache_dirty(page)) {
-		__flush_icache_page(vma, page);
-		ClearPageDcacheDirty(page);
-	}
 }

 extern void (*flush_icache_range)(unsigned long start, unsigned long end);
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@ -784,7 +784,7 @@ extern enum emulation_result kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu,

 uint32_t kvm_mips_read_count(struct kvm_vcpu *vcpu);
 void kvm_mips_write_count(struct kvm_vcpu *vcpu, uint32_t count);
-void kvm_mips_write_compare(struct kvm_vcpu *vcpu, uint32_t compare);
+void kvm_mips_write_compare(struct kvm_vcpu *vcpu, uint32_t compare, bool ack);
 void kvm_mips_init_count(struct kvm_vcpu *vcpu);
 int kvm_mips_set_count_ctl(struct kvm_vcpu *vcpu, s64 count_ctl);
 int kvm_mips_set_count_resume(struct kvm_vcpu *vcpu, s64 count_resume);
--- a/arch/mips/include/asm/msa.h
+++ b/arch/mips/include/asm/msa.h
@ -147,6 +147,19 @@ static inline void restore_msa(struct task_struct *t)
 		_restore_msa(t);
 }

+static inline void init_msa_upper(void)
+{
+	/*
+	 * Check cpu_has_msa only if it's a constant. This will allow the
+	 * compiler to optimise out code for CPUs without MSA without adding
+	 * an extra redundant check for CPUs with MSA.
+	 */
+	if (__builtin_constant_p(cpu_has_msa) && !cpu_has_msa)
+		return;
+
+	_init_msa_upper();
+}
+
 #ifdef TOOLCHAIN_SUPPORTS_MSA

 #define __BUILD_MSA_CTL_REG(name, cs)				\
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@ -127,10 +127,14 @@ do {									\
 	}								\
 } while(0)

+static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep, pte_t pteval);
+
 #if defined(CONFIG_PHYS_ADDR_T_64BIT) && defined(CONFIG_CPU_MIPS32)

 #define pte_none(pte)		(!(((pte).pte_high) & ~_PAGE_GLOBAL))
 #define pte_present(pte)	((pte).pte_low & _PAGE_PRESENT)
+#define pte_no_exec(pte)	((pte).pte_low & _PAGE_NO_EXEC)

 static inline void set_pte(pte_t *ptep, pte_t pte)
 {
@ -148,7 +152,6 @@ static inline void set_pte(pte_t *ptep, pte_t pte)
 			buddy->pte_high |= _PAGE_GLOBAL;
 	}
 }
-#define set_pte_at(mm, addr, ptep, pteval) set_pte(ptep, pteval)

 static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
@ -166,6 +169,7 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *pt

 #define pte_none(pte)		(!(pte_val(pte) & ~_PAGE_GLOBAL))
 #define pte_present(pte)	(pte_val(pte) & _PAGE_PRESENT)
+#define pte_no_exec(pte)	(pte_val(pte) & _PAGE_NO_EXEC)

 /*
 * Certain architectures need to do special things when pte's
@ -218,7 +222,6 @@ static inline void set_pte(pte_t *ptep, pte_t pteval)
 	}
 #endif
 }
-#define set_pte_at(mm, addr, ptep, pteval) set_pte(ptep, pteval)

 static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
@ -234,6 +237,22 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *pt
 }
 #endif

+static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep, pte_t pteval)
+{
+	extern void __update_cache(unsigned long address, pte_t pte);
+
+	if (!pte_present(pteval))
+		goto cache_sync_done;
+
+	if (pte_present(*ptep) && (pte_pfn(*ptep) == pte_pfn(pteval)))
+		goto cache_sync_done;
+
+	__update_cache(addr, pteval);
+cache_sync_done:
+	set_pte(ptep, pteval);
+}
+
 /*
 * (pmds are folded into puds so this doesn't get actually called,
 * but the define is needed for a generic inline function.)
@ -430,15 +449,12 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)

 extern void __update_tlb(struct vm_area_struct *vma, unsigned long address,
 	pte_t pte);
-extern void __update_cache(struct vm_area_struct *vma, unsigned long address,
-	pte_t pte);

 static inline void update_mmu_cache(struct vm_area_struct *vma,
 	unsigned long address, pte_t *ptep)
 {
 	pte_t pte = *ptep;
 	__update_tlb(vma, address, pte);
-	__update_cache(vma, address, pte);
 }

 static inline void update_mmu_cache_pmd(struct vm_area_struct *vma,
--- a/arch/mips/include/asm/processor.h
+++ b/arch/mips/include/asm/processor.h
@ -45,7 +45,7 @@ extern unsigned int vced_count, vcei_count;
 * User space process size: 2GB. This is hardcoded into a few places,
 * so don't change it unless you know what you are doing.
 */
-#define TASK_SIZE	0x7fff8000UL
+#define TASK_SIZE	0x80000000UL
 #endif

 #define STACK_TOP_MAX	TASK_SIZE
--- a/arch/mips/include/asm/switch_to.h
+++ b/arch/mips/include/asm/switch_to.h
@ -105,7 +105,7 @@ do {									\
 	__clear_software_ll_bit();					\
 	if (cpu_has_userlocal)						\
 		write_c0_userlocal(task_thread_info(next)->tp_value);	\
-	__restore_watch();						\
+	__restore_watch(next);						\
 	(last) = resume(prev, next, task_thread_info(next));		\
 } while (0)

--- a/arch/mips/include/asm/watch.h
+++ b/arch/mips/include/asm/watch.h
@ -12,21 +12,21 @@

 #include <asm/mipsregs.h>

-void mips_install_watch_registers(void);
+void mips_install_watch_registers(struct task_struct *t);
 void mips_read_watch_registers(void);
 void mips_clear_watch_registers(void);
 void mips_probe_watch_registers(struct cpuinfo_mips *c);

 #ifdef CONFIG_HARDWARE_WATCHPOINTS
-#define __restore_watch() do {						\
+#define __restore_watch(task) do {					\
 	if (unlikely(test_bit(TIF_LOAD_WATCH,				\
-			      &current_thread_info()->flags))) {	\
-		mips_install_watch_registers();				\
+			      &task_thread_info(task)->flags))) {	\
+		mips_install_watch_registers(task);			\
 	}								\
 } while (0)

 #else
-#define __restore_watch() do {} while (0)
+#define __restore_watch(task) do {} while (0)
 #endif

 #endif /* _ASM_WATCH_H */
--- a/arch/mips/include/uapi/asm/siginfo.h
+++ b/arch/mips/include/uapi/asm/siginfo.h
@ -28,7 +28,7 @@

 #define __ARCH_SIGSYS

-#include <uapi/asm-generic/siginfo.h>
+#include <asm-generic/siginfo.h>

 /* We can't use generic siginfo_t, because our si_code and si_errno are swapped */
 typedef struct siginfo {
@ -42,13 +42,13 @@ typedef struct siginfo {

 		/* kill() */
 		struct {
-			pid_t _pid;		/* sender's pid */
+			__kernel_pid_t _pid;	/* sender's pid */
 			__ARCH_SI_UID_T _uid;	/* sender's uid */
 		} _kill;

 		/* POSIX.1b timers */
 		struct {
-			timer_t _tid;		/* timer id */
+			__kernel_timer_t _tid;	/* timer id */
 			int _overrun;		/* overrun count */
 			char _pad[sizeof( __ARCH_SI_UID_T) - sizeof(int)];
 			sigval_t _sigval;	/* same as below */
@ -57,26 +57,26 @@ typedef struct siginfo {

 		/* POSIX.1b signals */
 		struct {
-			pid_t _pid;		/* sender's pid */
+			__kernel_pid_t _pid;	/* sender's pid */
 			__ARCH_SI_UID_T _uid;	/* sender's uid */
 			sigval_t _sigval;
 		} _rt;

 		/* SIGCHLD */
 		struct {
-			pid_t _pid;		/* which child */
+			__kernel_pid_t _pid;	/* which child */
 			__ARCH_SI_UID_T _uid;	/* sender's uid */
 			int _status;		/* exit code */
-			clock_t _utime;
-			clock_t _stime;
+			__kernel_clock_t _utime;
+			__kernel_clock_t _stime;
 		} _sigchld;

 		/* IRIX SIGCHLD */
 		struct {
-			pid_t _pid;		/* which child */
-			clock_t _utime;
+			__kernel_pid_t _pid;	/* which child */
+			__kernel_clock_t _utime;
 			int _status;		/* exit code */
-			clock_t _stime;
+			__kernel_clock_t _stime;
 		} _irix_sigchld;

 		/* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
@ -118,6 +118,4 @@ typedef struct siginfo {
 #define SI_TIMER __SI_CODE(__SI_TIMER, -3) /* sent by timer expiration */
 #define SI_MESGQ __SI_CODE(__SI_MESGQ, -4) /* sent by real time mesq state change */

-#include <asm-generic/siginfo.h>
-
 #endif /* _UAPI_ASM_SIGINFO_H */
--- a/arch/mips/kernel/mips-r2-to-r6-emul.c
+++ b/arch/mips/kernel/mips-r2-to-r6-emul.c
@ -28,6 +28,7 @@
 #include <asm/inst.h>
 #include <asm/mips-r2-to-r6-emul.h>
 #include <asm/local.h>
+#include <asm/mipsregs.h>
 #include <asm/ptrace.h>
 #include <asm/uaccess.h>

@ -1251,10 +1252,10 @@ int mipsr2_decoder(struct pt_regs *regs, u32 inst, unsigned long *fcr31)
 			"	j	10b\n"
 			"	.previous\n"
 			"	.section	__ex_table,\"a\"\n"
-			"	.word	1b,8b\n"
-			"	.word	2b,8b\n"
-			"	.word	3b,8b\n"
-			"	.word	4b,8b\n"
+			STR(PTR) " 1b,8b\n"
+			STR(PTR) " 2b,8b\n"
+			STR(PTR) " 3b,8b\n"
+			STR(PTR) " 4b,8b\n"
 			"	.previous\n"
 			"	.set	pop\n"
 			: "+&r"(rt), "=&r"(rs),
@ -1326,10 +1327,10 @@ int mipsr2_decoder(struct pt_regs *regs, u32 inst, unsigned long *fcr31)
 			"	j	10b\n"
 			"       .previous\n"
 			"	.section	__ex_table,\"a\"\n"
-			"	.word	1b,8b\n"
-			"	.word	2b,8b\n"
-			"	.word	3b,8b\n"
-			"	.word	4b,8b\n"
+			STR(PTR) " 1b,8b\n"
+			STR(PTR) " 2b,8b\n"
+			STR(PTR) " 3b,8b\n"
+			STR(PTR) " 4b,8b\n"
 			"	.previous\n"
 			"	.set	pop\n"
 			: "+&r"(rt), "=&r"(rs),
@ -1397,10 +1398,10 @@ int mipsr2_decoder(struct pt_regs *regs, u32 inst, unsigned long *fcr31)
 			"	j	9b\n"
 			"	.previous\n"
 			"	.section        __ex_table,\"a\"\n"
-			"	.word	1b,8b\n"
-			"	.word	2b,8b\n"
-			"	.word	3b,8b\n"
-			"	.word	4b,8b\n"
+			STR(PTR) " 1b,8b\n"
+			STR(PTR) " 2b,8b\n"
+			STR(PTR) " 3b,8b\n"
+			STR(PTR) " 4b,8b\n"
 			"	.previous\n"
 			"	.set	pop\n"
 			: "+&r"(rt), "=&r"(rs),
@ -1467,10 +1468,10 @@ int mipsr2_decoder(struct pt_regs *regs, u32 inst, unsigned long *fcr31)
 			"	j	9b\n"
 			"	.previous\n"
 			"	.section        __ex_table,\"a\"\n"
-			"	.word	1b,8b\n"
-			"	.word	2b,8b\n"
-			"	.word	3b,8b\n"
-			"	.word	4b,8b\n"
+			STR(PTR) " 1b,8b\n"
+			STR(PTR) " 2b,8b\n"
+			STR(PTR) " 3b,8b\n"
+			STR(PTR) " 4b,8b\n"
 			"	.previous\n"
 			"	.set	pop\n"
 			: "+&r"(rt), "=&r"(rs),
@ -1582,14 +1583,14 @@ int mipsr2_decoder(struct pt_regs *regs, u32 inst, unsigned long *fcr31)
 			"	j	9b\n"
 			"	.previous\n"
 			"	.section        __ex_table,\"a\"\n"
-			"	.word	1b,8b\n"
-			"	.word	2b,8b\n"
-			"	.word	3b,8b\n"
-			"	.word	4b,8b\n"
-			"	.word	5b,8b\n"
-			"	.word	6b,8b\n"
-			"	.word	7b,8b\n"
-			"	.word	0b,8b\n"
+			STR(PTR) " 1b,8b\n"
+			STR(PTR) " 2b,8b\n"
+			STR(PTR) " 3b,8b\n"
+			STR(PTR) " 4b,8b\n"
+			STR(PTR) " 5b,8b\n"
+			STR(PTR) " 6b,8b\n"
+			STR(PTR) " 7b,8b\n"
+			STR(PTR) " 0b,8b\n"
 			"	.previous\n"
 			"	.set	pop\n"
 			: "+&r"(rt), "=&r"(rs),
@ -1701,14 +1702,14 @@ int mipsr2_decoder(struct pt_regs *regs, u32 inst, unsigned long *fcr31)
 			"	j      9b\n"
 			"	.previous\n"
 			"	.section        __ex_table,\"a\"\n"
-			"	.word  1b,8b\n"
-			"	.word  2b,8b\n"
-			"	.word  3b,8b\n"
-			"	.word  4b,8b\n"
-			"	.word  5b,8b\n"
-			"	.word  6b,8b\n"
-			"	.word  7b,8b\n"
-			"	.word  0b,8b\n"
+			STR(PTR) " 1b,8b\n"
+			STR(PTR) " 2b,8b\n"
+			STR(PTR) " 3b,8b\n"
+			STR(PTR) " 4b,8b\n"
+			STR(PTR) " 5b,8b\n"
+			STR(PTR) " 6b,8b\n"
+			STR(PTR) " 7b,8b\n"
+			STR(PTR) " 0b,8b\n"
 			"	.previous\n"
 			"	.set    pop\n"
 			: "+&r"(rt), "=&r"(rs),
@ -1820,14 +1821,14 @@ int mipsr2_decoder(struct pt_regs *regs, u32 inst, unsigned long *fcr31)
 			"	j	9b\n"
 			"	.previous\n"
 			"	.section        __ex_table,\"a\"\n"
-			"	.word	1b,8b\n"
-			"	.word	2b,8b\n"
-			"	.word	3b,8b\n"
-			"	.word	4b,8b\n"
-			"	.word	5b,8b\n"
-			"	.word	6b,8b\n"
-			"	.word	7b,8b\n"
-			"	.word	0b,8b\n"
+			STR(PTR) " 1b,8b\n"
+			STR(PTR) " 2b,8b\n"
+			STR(PTR) " 3b,8b\n"
+			STR(PTR) " 4b,8b\n"
+			STR(PTR) " 5b,8b\n"
+			STR(PTR) " 6b,8b\n"
+			STR(PTR) " 7b,8b\n"
+			STR(PTR) " 0b,8b\n"
 			"	.previous\n"
 			"	.set	pop\n"
 			: "+&r"(rt), "=&r"(rs),
@ -1938,14 +1939,14 @@ int mipsr2_decoder(struct pt_regs *regs, u32 inst, unsigned long *fcr31)
 			"       j	9b\n"
 			"       .previous\n"
 			"       .section        __ex_table,\"a\"\n"
-			"       .word	1b,8b\n"
-			"       .word	2b,8b\n"
-			"       .word	3b,8b\n"
-			"       .word	4b,8b\n"
-			"       .word	5b,8b\n"
-			"       .word	6b,8b\n"
-			"       .word	7b,8b\n"
-			"       .word	0b,8b\n"
+			STR(PTR) " 1b,8b\n"
+			STR(PTR) " 2b,8b\n"
+			STR(PTR) " 3b,8b\n"
+			STR(PTR) " 4b,8b\n"
+			STR(PTR) " 5b,8b\n"
+			STR(PTR) " 6b,8b\n"
+			STR(PTR) " 7b,8b\n"
+			STR(PTR) " 0b,8b\n"
 			"       .previous\n"
 			"       .set	pop\n"
 			: "+&r"(rt), "=&r"(rs),
@ -2000,7 +2001,7 @@ int mipsr2_decoder(struct pt_regs *regs, u32 inst, unsigned long *fcr31)
 			"j	2b\n"
 			".previous\n"
 			".section        __ex_table,\"a\"\n"
-			".word  1b, 3b\n"
+			STR(PTR) " 1b,3b\n"
 			".previous\n"
 			: "=&r"(res), "+&r"(err)
 			: "r"(vaddr), "i"(SIGSEGV)
@ -2058,7 +2059,7 @@ int mipsr2_decoder(struct pt_regs *regs, u32 inst, unsigned long *fcr31)
 			"j	2b\n"
 			".previous\n"
 			".section        __ex_table,\"a\"\n"
-			".word	1b, 3b\n"
+			STR(PTR) " 1b,3b\n"
 			".previous\n"
 			: "+&r"(res), "+&r"(err)
 			: "r"(vaddr), "i"(SIGSEGV));
@ -2119,7 +2120,7 @@ int mipsr2_decoder(struct pt_regs *regs, u32 inst, unsigned long *fcr31)
 			"j	2b\n"
 			".previous\n"
 			".section        __ex_table,\"a\"\n"
-			".word  1b, 3b\n"
+			STR(PTR) " 1b,3b\n"
 			".previous\n"
 			: "=&r"(res), "+&r"(err)
 			: "r"(vaddr), "i"(SIGSEGV)
@ -2182,7 +2183,7 @@ int mipsr2_decoder(struct pt_regs *regs, u32 inst, unsigned long *fcr31)
 			"j	2b\n"
 			".previous\n"
 			".section        __ex_table,\"a\"\n"
-			".word	1b, 3b\n"
+			STR(PTR) " 1b,3b\n"
 			".previous\n"
 			: "+&r"(res), "+&r"(err)
 			: "r"(vaddr), "i"(SIGSEGV));
--- a/arch/mips/kernel/pm.c
+++ b/arch/mips/kernel/pm.c
@ -56,7 +56,7 @@ static void mips_cpu_restore(void)
 		write_c0_userlocal(current_thread_info()->tp_value);

 	/* Restore watch registers */
-	__restore_watch();
+	__restore_watch(current);
 }

 /**
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@ -457,7 +457,7 @@ unsigned long notrace unwind_stack_by_address(unsigned long stack_page,
 		    *sp + sizeof(*regs) <= stack_page + THREAD_SIZE - 32) {
 			regs = (struct pt_regs *)*sp;
 			pc = regs->cp0_epc;
-			if (__kernel_text_address(pc)) {
+			if (!user_mode(regs) && __kernel_text_address(pc)) {
 				*sp = regs->regs[29];
 				*ra = regs->regs[31];
 				return pc;
@ -603,6 +603,9 @@ int mips_set_process_fp_mode(struct task_struct *task, unsigned int value)
 	if (!(value & PR_FP_MODE_FR) && cpu_has_fpu && cpu_has_mips_r6)
 		return -EOPNOTSUPP;

+	/* Proceed with the mode switch */
+	preempt_disable();
+
 	/* Save FP & vector context, then disable FPU & MSA */
 	if (task->signal == current->signal)
 		lose_fpu(1);
@ -661,6 +664,7 @@ int mips_set_process_fp_mode(struct task_struct *task, unsigned int value)

 	/* Allow threads to use FP again */
 	atomic_set(&task->mm->context.fp_mode_switching, 0);
+	preempt_enable();

 	return 0;
 }
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@ -57,8 +57,7 @@ static void init_fp_ctx(struct task_struct *target)
 	/* Begin with data registers set to all 1s... */
 	memset(&target->thread.fpu.fpr, ~0, sizeof(target->thread.fpu.fpr));

-	/* ...and FCSR zeroed */
-	target->thread.fpu.fcr31 = 0;
+	/* FCSR has been preset by `mips_set_personality_nan'.  */

 	/*
 	 * Record that the target has "used" math, such that the context
@ -79,6 +78,22 @@ void ptrace_disable(struct task_struct *child)
 	clear_tsk_thread_flag(child, TIF_LOAD_WATCH);
 }

+/*
+ * Poke at FCSR according to its mask.  Don't set the cause bits as
+ * this is currently not handled correctly in FP context restoration
+ * and will cause an oops if a corresponding enable bit is set.
+ */
+static void ptrace_setfcr31(struct task_struct *child, u32 value)
+{
+	u32 fcr31;
+	u32 mask;
+
+	value &= ~FPU_CSR_ALL_X;
+	fcr31 = child->thread.fpu.fcr31;
+	mask = boot_cpu_data.fpu_msk31;
+	child->thread.fpu.fcr31 = (value & ~mask) | (fcr31 & mask);
+}
+
 /*
 * Read a general register set.	 We always use the 64-bit format, even
 * for 32-bit kernels and for 32-bit processes on a 64-bit kernel.
@ -159,9 +174,7 @@ int ptrace_setfpregs(struct task_struct *child, __u32 __user *data)
 {
 	union fpureg *fregs;
 	u64 fpr_val;
-	u32 fcr31;
 	u32 value;
-	u32 mask;
 	int i;

 	if (!access_ok(VERIFY_READ, data, 33 * 8))
@ -176,9 +189,7 @@ int ptrace_setfpregs(struct task_struct *child, __u32 __user *data)
 	}

 	__get_user(value, data + 64);
-	fcr31 = child->thread.fpu.fcr31;
-	mask = boot_cpu_data.fpu_msk31;
-	child->thread.fpu.fcr31 = (value & ~mask) | (fcr31 & mask);
+	ptrace_setfcr31(child, value);

 	/* FIR may not be written.  */

@ -808,7 +819,7 @@ long arch_ptrace(struct task_struct *child, long request,
 			break;
 #endif
 		case FPC_CSR:
-			child->thread.fpu.fcr31 = data & ~FPU_CSR_ALL_X;
+			ptrace_setfcr31(child, data);
 			break;
 		case DSP_BASE ... DSP_BASE + 5: {
 			dspreg_t *dregs;
--- a/arch/mips/kernel/r4k_fpu.S
+++ b/arch/mips/kernel/r4k_fpu.S
@ -244,17 +244,17 @@ LEAF(\name)
 	.set	push
 	.set	noat
 #ifdef CONFIG_64BIT
-	copy_u_d \wr, 1
+	copy_s_d \wr, 1
 	EX sd	$1, \off(\base)
 #elif defined(CONFIG_CPU_LITTLE_ENDIAN)
-	copy_u_w \wr, 2
+	copy_s_w \wr, 2
 	EX sw	$1, \off(\base)
-	copy_u_w \wr, 3
+	copy_s_w \wr, 3
 	EX sw	$1, (\off+4)(\base)
 #else /* CONFIG_CPU_BIG_ENDIAN */
-	copy_u_w \wr, 2
+	copy_s_w \wr, 2
 	EX sw	$1, (\off+4)(\base)
-	copy_u_w \wr, 3
+	copy_s_w \wr, 3
 	EX sw	$1, \off(\base)
 #endif
 	.set	pop
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@ -706,6 +706,9 @@ static void __init arch_mem_init(char **cmdline_p)
 	for_each_memblock(reserved, reg)
 		if (reg->size != 0)
 			reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
+
+	reserve_bootmem_region(__pa_symbol(&__nosave_begin),
+			__pa_symbol(&__nosave_end)); /* Reserve for hibernation */
 }

 static void __init resource_init(void)
--- a/arch/mips/kernel/signal.c
+++ b/arch/mips/kernel/signal.c
@ -195,6 +195,9 @@ static int restore_msa_extcontext(void __user *buf, unsigned int size)
 	unsigned int csr;
 	int i, err;

+	if (!config_enabled(CONFIG_CPU_HAS_MSA))
+		return SIGSYS;
+
 	if (size != sizeof(*msa))
 		return -EINVAL;

@ -398,8 +401,8 @@ int protected_restore_fp_context(void __user *sc)
 	}

 fp_done:
-	if (used & USED_EXTCONTEXT)
-		err |= restore_extcontext(sc_to_extcontext(sc));
+	if (!err && (used & USED_EXTCONTEXT))
+		err = restore_extcontext(sc_to_extcontext(sc));

 	return err ?: sig;
 }
@ -767,15 +770,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 	sigset_t *oldset = sigmask_to_save();
 	int ret;
 	struct mips_abi *abi = current->thread.abi;
-#ifdef CONFIG_CPU_MICROMIPS
-	void *vdso;
-	unsigned long tmp = (unsigned long)current->mm->context.vdso;
-
-	set_isa16_mode(tmp);
-	vdso = (void *)tmp;
-#else
 	void *vdso = current->mm->context.vdso;
-#endif

 	if (regs->regs[0]) {
 		switch(regs->regs[2]) {
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@ -144,7 +144,7 @@ static void show_backtrace(struct task_struct *task, const struct pt_regs *regs)
 	if (!task)
 		task = current;

-	if (raw_show_trace || !__kernel_text_address(pc)) {
+	if (raw_show_trace || user_mode(regs) || !__kernel_text_address(pc)) {
 		show_raw_backtrace(sp);
 		return;
 	}
@ -1241,7 +1241,7 @@ static int enable_restore_fp_context(int msa)
 		err = init_fpu();
 		if (msa && !err) {
 			enable_msa();
-			_init_msa_upper();
+			init_msa_upper();
 			set_thread_flag(TIF_USEDMSA);
 			set_thread_flag(TIF_MSA_CTX_LIVE);
 		}
@ -1304,7 +1304,7 @@ static int enable_restore_fp_context(int msa)
 	 */
 	prior_msa = test_and_set_thread_flag(TIF_MSA_CTX_LIVE);
 	if (!prior_msa && was_fpu_owner) {
-		_init_msa_upper();
+		init_msa_upper();

 		goto out;
 	}
@ -1321,7 +1321,7 @@ static int enable_restore_fp_context(int msa)
 		 * of each vector register such that it cannot see data left
 		 * behind by another task.
 		 */
-		_init_msa_upper();
+		init_msa_upper();
 	} else {
 		/* We need to restore the vector context. */
 		restore_msa(current);
--- a/arch/mips/kernel/watch.c
+++ b/arch/mips/kernel/watch.c
@ -15,10 +15,9 @@
 * Install the watch registers for the current thread.	A maximum of
 * four registers are installed although the machine may have more.
 */
-void mips_install_watch_registers(void)
+void mips_install_watch_registers(struct task_struct *t)
 {
-	struct mips3264_watch_reg_state *watches =
-		&current->thread.watch.mips3264;
+	struct mips3264_watch_reg_state *watches = &t->thread.watch.mips3264;
 	switch (current_cpu_data.watch_reg_use_cnt) {
 	default:
 		BUG();
--- a/arch/mips/kvm/emulate.c
+++ b/arch/mips/kvm/emulate.c
@ -302,12 +302,31 @@ static inline ktime_t kvm_mips_count_time(struct kvm_vcpu *vcpu)
 */
 static uint32_t kvm_mips_read_count_running(struct kvm_vcpu *vcpu, ktime_t now)
 {
-	ktime_t expires;
+	struct mips_coproc *cop0 = vcpu->arch.cop0;
+	ktime_t expires, threshold;
+	uint32_t count, compare;
 	int running;

-	/* Is the hrtimer pending? */
+	/* Calculate the biased and scaled guest CP0_Count */
+	count = vcpu->arch.count_bias + kvm_mips_ktime_to_count(vcpu, now);
+	compare = kvm_read_c0_guest_compare(cop0);
+
+	/*
+	 * Find whether CP0_Count has reached the closest timer interrupt. If
+	 * not, we shouldn't inject it.
+	 */
+	if ((int32_t)(count - compare) < 0)
+		return count;
+
+	/*
+	 * The CP0_Count we're going to return has already reached the closest
+	 * timer interrupt. Quickly check if it really is a new interrupt by
+	 * looking at whether the interval until the hrtimer expiry time is
+	 * less than 1/4 of the timer period.
+	 */
 	expires = hrtimer_get_expires(&vcpu->arch.comparecount_timer);
-	if (ktime_compare(now, expires) >= 0) {
+	threshold = ktime_add_ns(now, vcpu->arch.count_period / 4);
+	if (ktime_before(expires, threshold)) {
 		/*
 		 * Cancel it while we handle it so there's no chance of
 		 * interference with the timeout handler.
@ -329,8 +348,7 @@ static uint32_t kvm_mips_read_count_running(struct kvm_vcpu *vcpu, ktime_t now)
 		}
 	}

-	/* Return the biased and scaled guest CP0_Count */
-	return vcpu->arch.count_bias + kvm_mips_ktime_to_count(vcpu, now);
+	return count;
 }

 /**
@ -419,32 +437,6 @@ static void kvm_mips_resume_hrtimer(struct kvm_vcpu *vcpu,
 	hrtimer_start(&vcpu->arch.comparecount_timer, expire, HRTIMER_MODE_ABS);
 }

-/**
- * kvm_mips_update_hrtimer() - Update next expiry time of hrtimer.
- * @vcpu:	Virtual CPU.
- *
- * Recalculates and updates the expiry time of the hrtimer. This can be used
- * after timer parameters have been altered which do not depend on the time that
- * the change occurs (in those cases kvm_mips_freeze_hrtimer() and
- * kvm_mips_resume_hrtimer() are used directly).
- *
- * It is guaranteed that no timer interrupts will be lost in the process.
- *
- * Assumes !kvm_mips_count_disabled(@vcpu) (guest CP0_Count timer is running).
- */
-static void kvm_mips_update_hrtimer(struct kvm_vcpu *vcpu)
-{
-	ktime_t now;
-	uint32_t count;
-
-	/*
-	 * freeze_hrtimer takes care of a timer interrupts <= count, and
-	 * resume_hrtimer the hrtimer takes care of a timer interrupts > count.
-	 */
-	now = kvm_mips_freeze_hrtimer(vcpu, &count);
-	kvm_mips_resume_hrtimer(vcpu, now, count);
-}
-
 /**
 * kvm_mips_write_count() - Modify the count and update timer.
 * @vcpu:	Virtual CPU.
@ -540,23 +532,42 @@ int kvm_mips_set_count_hz(struct kvm_vcpu *vcpu, s64 count_hz)
 * kvm_mips_write_compare() - Modify compare and update timer.
 * @vcpu:	Virtual CPU.
 * @compare:	New CP0_Compare value.
+ * @ack:	Whether to acknowledge timer interrupt.
 *
 * Update CP0_Compare to a new value and update the timeout.
+ * If @ack, atomically acknowledge any pending timer interrupt, otherwise ensure
+ * any pending timer interrupt is preserved.
 */
-void kvm_mips_write_compare(struct kvm_vcpu *vcpu, uint32_t compare)
+void kvm_mips_write_compare(struct kvm_vcpu *vcpu, uint32_t compare, bool ack)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
+	int dc;
+	u32 old_compare = kvm_read_c0_guest_compare(cop0);
+	ktime_t now;
+	uint32_t count;

 	/* if unchanged, must just be an ack */
-	if (kvm_read_c0_guest_compare(cop0) == compare)
+	if (old_compare == compare) {
+		if (!ack)
+			return;
+		kvm_mips_callbacks->dequeue_timer_int(vcpu);
+		kvm_write_c0_guest_compare(cop0, compare);
 		return;
+	}
+
+	/* freeze_hrtimer() takes care of timer interrupts <= count */
+	dc = kvm_mips_count_disabled(vcpu);
+	if (!dc)
+		now = kvm_mips_freeze_hrtimer(vcpu, &count);
+
+	if (ack)
+		kvm_mips_callbacks->dequeue_timer_int(vcpu);

-	/* Update compare */
 	kvm_write_c0_guest_compare(cop0, compare);

-	/* Update timeout if count enabled */
-	if (!kvm_mips_count_disabled(vcpu))
-		kvm_mips_update_hrtimer(vcpu);
+	/* resume_hrtimer() takes care of timer interrupts > count */
+	if (!dc)
+		kvm_mips_resume_hrtimer(vcpu, now, count);
 }

 /**
@ -1095,9 +1106,9 @@ enum emulation_result kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc,

 				/* If we are writing to COMPARE */
 				/* Clear pending timer interrupt, if any */
-				kvm_mips_callbacks->dequeue_timer_int(vcpu);
 				kvm_mips_write_compare(vcpu,
-						       vcpu->arch.gprs[rt]);
+						       vcpu->arch.gprs[rt],
+						       true);
 			} else if ((rd == MIPS_CP0_STATUS) && (sel == 0)) {
 				unsigned int old_val, val, change;

--- a/arch/mips/kvm/trap_emul.c
+++ b/arch/mips/kvm/trap_emul.c
@ -547,7 +547,7 @@ static int kvm_trap_emul_set_one_reg(struct kvm_vcpu *vcpu,
 		kvm_mips_write_count(vcpu, v);
 		break;
 	case KVM_REG_MIPS_CP0_COMPARE:
-		kvm_mips_write_compare(vcpu, v);
+		kvm_mips_write_compare(vcpu, v, false);
 		break;
 	case KVM_REG_MIPS_CP0_CAUSE:
 		/*
--- a/arch/mips/lib/ashldi3.c
+++ b/arch/mips/lib/ashldi3.c
@ -2,7 +2,7 @@

 #include "libgcc.h"

-long long __ashldi3(long long u, word_type b)
+long long notrace __ashldi3(long long u, word_type b)
 {
 	DWunion uu, w;
 	word_type bm;
--- a/arch/mips/lib/ashrdi3.c
+++ b/arch/mips/lib/ashrdi3.c
@ -2,7 +2,7 @@

 #include "libgcc.h"

-long long __ashrdi3(long long u, word_type b)
+long long notrace __ashrdi3(long long u, word_type b)
 {
 	DWunion uu, w;
 	word_type bm;
--- a/arch/mips/lib/bswapdi.c
+++ b/arch/mips/lib/bswapdi.c
@ -1,6 +1,6 @@
 #include <linux/module.h>

-unsigned long long __bswapdi2(unsigned long long u)
+unsigned long long notrace __bswapdi2(unsigned long long u)
 {
 	return (((u) & 0xff00000000000000ull) >> 56) |
 	       (((u) & 0x00ff000000000000ull) >> 40) |
--- a/arch/mips/lib/bswapsi.c
+++ b/arch/mips/lib/bswapsi.c
@ -1,6 +1,6 @@
 #include <linux/module.h>

-unsigned int __bswapsi2(unsigned int u)
+unsigned int notrace __bswapsi2(unsigned int u)
 {
 	return (((u) & 0xff000000) >> 24) |
 	       (((u) & 0x00ff0000) >>  8) |
--- a/arch/mips/lib/cmpdi2.c
+++ b/arch/mips/lib/cmpdi2.c
@ -2,7 +2,7 @@

 #include "libgcc.h"

-word_type __cmpdi2(long long a, long long b)
+word_type notrace __cmpdi2(long long a, long long b)
 {
 	const DWunion au = {
 		.ll = a
--- a/arch/mips/lib/lshrdi3.c
+++ b/arch/mips/lib/lshrdi3.c
@ -2,7 +2,7 @@

 #include "libgcc.h"

-long long __lshrdi3(long long u, word_type b)
+long long notrace __lshrdi3(long long u, word_type b)
 {
 	DWunion uu, w;
 	word_type bm;
--- a/arch/mips/lib/ucmpdi2.c
+++ b/arch/mips/lib/ucmpdi2.c
@ -2,7 +2,7 @@

 #include "libgcc.h"

-word_type __ucmpdi2(unsigned long long a, unsigned long long b)
+word_type notrace __ucmpdi2(unsigned long long a, unsigned long long b)
 {
 	const DWunion au = {.ll = a};
 	const DWunion bu = {.ll = b};
--- a/arch/mips/loongson64/loongson-3/numa.c
+++ b/arch/mips/loongson64/loongson-3/numa.c
@ -213,10 +213,10 @@ static void __init node_mem_init(unsigned int node)
 		BOOTMEM_DEFAULT);

 	if (node == 0 && node_end_pfn(0) >= (0xffffffff >> PAGE_SHIFT)) {
-		/* Reserve 0xff800000~0xffffffff for RS780E integrated GPU */
+		/* Reserve 0xfe000000~0xffffffff for RS780E integrated GPU */
 		reserve_bootmem_node(NODE_DATA(node),
-				(node_addrspace_offset | 0xff800000),
-				8 << 20, BOOTMEM_DEFAULT);
+				(node_addrspace_offset | 0xfe000000),
+				32 << 20, BOOTMEM_DEFAULT);
 	}

 	sparse_memory_present_with_active_regions(node);
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@ -445,9 +445,11 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 	case spec_op:
 		switch (insn.r_format.func) {
 		case jalr_op:
-			regs->regs[insn.r_format.rd] =
-				regs->cp0_epc + dec_insn.pc_inc +
-				dec_insn.next_pc_inc;
+			if (insn.r_format.rd != 0) {
+				regs->regs[insn.r_format.rd] =
+					regs->cp0_epc + dec_insn.pc_inc +
+					dec_insn.next_pc_inc;
+			}
 			/* Fall through */
 		case jr_op:
 			/* For R6, JR already emulated in jalr_op */
--- a/arch/mips/mm/cache.c
+++ b/arch/mips/mm/cache.c
@ -16,6 +16,7 @@
 #include <linux/mm.h>

 #include <asm/cacheflush.h>
+#include <asm/highmem.h>
 #include <asm/processor.h>
 #include <asm/cpu.h>
 #include <asm/cpu-features.h>
@ -83,8 +84,6 @@ void __flush_dcache_page(struct page *page)
 	struct address_space *mapping = page_mapping(page);
 	unsigned long addr;

-	if (PageHighMem(page))
-		return;
 	if (mapping && !mapping_mapped(mapping)) {
 		SetPageDcacheDirty(page);
 		return;
@ -95,8 +94,15 @@ void __flush_dcache_page(struct page *page)
 	 * case is for exec env/arg pages and those are %99 certainly going to
 	 * get faulted into the tlb (and thus flushed) anyways.
 	 */
-	addr = (unsigned long) page_address(page);
+	if (PageHighMem(page))
+		addr = (unsigned long)kmap_atomic(page);
+	else
+		addr = (unsigned long)page_address(page);
+
 	flush_data_cache_page(addr);
+
+	if (PageHighMem(page))
+		__kunmap_atomic((void *)addr);
 }

 EXPORT_SYMBOL(__flush_dcache_page);
@ -119,33 +125,28 @@ void __flush_anon_page(struct page *page, unsigned long vmaddr)

 EXPORT_SYMBOL(__flush_anon_page);

-void __flush_icache_page(struct vm_area_struct *vma, struct page *page)
-{
-	unsigned long addr;
-
-	if (PageHighMem(page))
-		return;
-
-	addr = (unsigned long) page_address(page);
-	flush_data_cache_page(addr);
-}
-EXPORT_SYMBOL_GPL(__flush_icache_page);
-
-void __update_cache(struct vm_area_struct *vma, unsigned long address,
-	pte_t pte)
+void __update_cache(unsigned long address, pte_t pte)
 {
 	struct page *page;
 	unsigned long pfn, addr;
-	int exec = (vma->vm_flags & VM_EXEC) && !cpu_has_ic_fills_f_dc;
+	int exec = !pte_no_exec(pte) && !cpu_has_ic_fills_f_dc;

 	pfn = pte_pfn(pte);
 	if (unlikely(!pfn_valid(pfn)))
 		return;
 	page = pfn_to_page(pfn);
-	if (page_mapping(page) && Page_dcache_dirty(page)) {
-		addr = (unsigned long) page_address(page);
+	if (Page_dcache_dirty(page)) {
+		if (PageHighMem(page))
+			addr = (unsigned long)kmap_atomic(page);
+		else
+			addr = (unsigned long)page_address(page);
+
 		if (exec || pages_do_alias(addr, address & PAGE_MASK))
 			flush_data_cache_page(addr);
+
+		if (PageHighMem(page))
+			__kunmap_atomic((void *)addr);
+
 		ClearPageDcacheDirty(page);
 	}
 }
--- a/arch/mips/vdso/Makefile
+++ b/arch/mips/vdso/Makefile
@ -5,10 +5,12 @@ obj-vdso-y := elf.o gettimeofday.o sigreturn.o
 ccflags-vdso := \
 	$(filter -I%,$(KBUILD_CFLAGS)) \
 	$(filter -E%,$(KBUILD_CFLAGS)) \
+	$(filter -mmicromips,$(KBUILD_CFLAGS)) \
 	$(filter -march=%,$(KBUILD_CFLAGS))
 cflags-vdso := $(ccflags-vdso) \
 	$(filter -W%,$(filter-out -Wa$(comma)%,$(KBUILD_CFLAGS))) \
-	-O2 -g -fPIC -fno-common -fno-builtin -G 0 -DDISABLE_BRANCH_PROFILING \
+	-O2 -g -fPIC -fno-strict-aliasing -fno-common -fno-builtin -G 0 \
+	-DDISABLE_BRANCH_PROFILING \
 	$(call cc-option, -fno-stack-protector)
 aflags-vdso := $(ccflags-vdso) \
 	$(filter -I%,$(KBUILD_CFLAGS)) \
--- a/arch/parisc/kernel/unaligned.c
+++ b/arch/parisc/kernel/unaligned.c
@ -666,7 +666,7 @@ void handle_unaligned(struct pt_regs *regs)
 		break;
 	}

-	if (modify && R1(regs->iir))
+	if (ret == 0 && modify && R1(regs->iir))
 		regs->gr[R1(regs->iir)] = newbase;


@ -677,6 +677,14 @@ void handle_unaligned(struct pt_regs *regs)

 	if (ret)
 	{
+		/*
+		 * The unaligned handler failed.
+		 * If we were called by __get_user() or __put_user() jump
+		 * to it's exception fixup handler instead of crashing.
+		 */
+		if (!user_mode(regs) && fixup_exception(regs))
+			return;
+
 		printk(KERN_CRIT "Unaligned handler failed, ret = %d\n", ret);
 		die_if_kernel("Unaligned data reference", regs, 28);

--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@ -707,7 +707,7 @@
 #define   MMCR0_FCWAIT	0x00000002UL /* freeze counter in WAIT state */
 #define   MMCR0_FCHV	0x00000001UL /* freeze conditions in hypervisor mode */
 #define SPRN_MMCR1	798
-#define SPRN_MMCR2	769
+#define SPRN_MMCR2	785
 #define SPRN_MMCRA	0x312
 #define   MMCRA_SDSYNC	0x80000000UL /* SDAR synced with SIAR */
 #define   MMCRA_SDAR_DCACHE_MISS 0x40000000UL
@ -744,13 +744,13 @@
 #define SPRN_PMC6	792
 #define SPRN_PMC7	793
 #define SPRN_PMC8	794
-#define SPRN_SIAR	780
-#define SPRN_SDAR	781
 #define SPRN_SIER	784
 #define   SIER_SIPR		0x2000000	/* Sampled MSR_PR */
 #define   SIER_SIHV		0x1000000	/* Sampled MSR_HV */
 #define   SIER_SIAR_VALID	0x0400000	/* SIAR contents valid */
 #define   SIER_SDAR_VALID	0x0200000	/* SDAR contents valid */
+#define SPRN_SIAR	796
+#define SPRN_SDAR	797
 #define SPRN_TACR	888
 #define SPRN_TCSCR	889
 #define SPRN_CSIGR	890
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@ -1072,7 +1072,7 @@ void eeh_add_device_early(struct pci_dn *pdn)
 	struct pci_controller *phb;
 	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);

-	if (!edev || !eeh_enabled())
+	if (!edev)
 		return;

 	if (!eeh_has_flag(EEH_PROBE_MODE_DEVTREE))
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@ -166,6 +166,16 @@ static void *eeh_dev_save_state(void *data, void *userdata)
 	if (!edev)
 		return NULL;

+	/*
+	 * We cannot access the config space on some adapters.
+	 * Otherwise, it will cause fenced PHB. We don't save
+	 * the content in their config space and will restore
+	 * from the initial config space saved when the EEH
+	 * device is created.
+	 */
+	if (edev->pe && (edev->pe->state & EEH_PE_CFG_RESTRICTED))
+		return NULL;
+
 	pdev = eeh_dev_to_pci_dev(edev);
 	if (!pdev)
 		return NULL;
@ -305,6 +315,19 @@ static void *eeh_dev_restore_state(void *data, void *userdata)
 	if (!edev)
 		return NULL;

+	/*
+	 * The content in the config space isn't saved because
+	 * the blocked config space on some adapters. We have
+	 * to restore the initial saved config space when the
+	 * EEH device is created.
+	 */
+	if (edev->pe && (edev->pe->state & EEH_PE_CFG_RESTRICTED)) {
+		if (list_is_last(&edev->list, &edev->pe->edevs))
+			eeh_pe_restore_bars(edev->pe);
+
+		return NULL;
+	}
+
 	pdev = eeh_dev_to_pci_dev(edev);
 	if (!pdev)
 		return NULL;
@ -504,9 +527,6 @@ int eeh_pe_reset_and_recover(struct eeh_pe *pe)
 	/* Save states */
 	eeh_pe_dev_traverse(pe, eeh_dev_save_state, NULL);

-	/* Report error */
-	eeh_pe_dev_traverse(pe, eeh_report_error, &result);
-
 	/* Issue reset */
 	ret = eeh_reset_pe(pe);
 	if (ret) {
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@ -962,11 +962,6 @@ hv_facility_unavailable_relon_trampoline:
 #endif
 	STD_RELON_EXCEPTION_PSERIES(0x5700, 0x1700, altivec_assist)

-	/* Other future vectors */
-	.align	7
-	.globl	__end_interrupts
-__end_interrupts:
-
 	.align	7
 system_call_entry:
 	b	system_call_common
@ -1253,6 +1248,17 @@ __end_handlers:
 	STD_RELON_EXCEPTION_PSERIES_OOL(0xf60, facility_unavailable)
 	STD_RELON_EXCEPTION_HV_OOL(0xf80, hv_facility_unavailable)

+	/*
+	 * The __end_interrupts marker must be past the out-of-line (OOL)
+	 * handlers, so that they are copied to real address 0x100 when running
+	 * a relocatable kernel. This ensures they can be reached from the short
+	 * trampoline handlers (like 0x4f00, 0x4f20, etc.) which branch
+	 * directly, without using LOAD_HANDLER().
+	 */
+	.align	7
+	.globl	__end_interrupts
+__end_interrupts:
+
 #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
 /*
 * Data area reserved for FWNMI option.
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@ -655,6 +655,7 @@ unsigned char ibm_architecture_vec[] = {
 	W(0xffff0000), W(0x003e0000),	/* POWER6 */
 	W(0xffff0000), W(0x003f0000),	/* POWER7 */
 	W(0xffff0000), W(0x004b0000),	/* POWER8E */
+	W(0xffff0000), W(0x004c0000),   /* POWER8NVL */
 	W(0xffff0000), W(0x004d0000),	/* POWER8 */
 	W(0xffffffff), W(0x0f000004),	/* all 2.07-compliant */
 	W(0xffffffff), W(0x0f000003),	/* all 2.06-compliant */
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@ -615,29 +615,50 @@ static int pseries_eeh_configure_bridge(struct eeh_pe *pe)
 {
 	int config_addr;
 	int ret;
+	/* Waiting 0.2s maximum before skipping configuration */
+	int max_wait = 200;

 	/* Figure out the PE address */
 	config_addr = pe->config_addr;
 	if (pe->addr)
 		config_addr = pe->addr;

-	/* Use new configure-pe function, if supported */
-	if (ibm_configure_pe != RTAS_UNKNOWN_SERVICE) {
-		ret = rtas_call(ibm_configure_pe, 3, 1, NULL,
-				config_addr, BUID_HI(pe->phb->buid),
-				BUID_LO(pe->phb->buid));
-	} else if (ibm_configure_bridge != RTAS_UNKNOWN_SERVICE) {
-		ret = rtas_call(ibm_configure_bridge, 3, 1, NULL,
-				config_addr, BUID_HI(pe->phb->buid),
-				BUID_LO(pe->phb->buid));
-	} else {
-		return -EFAULT;
+	while (max_wait > 0) {
+		/* Use new configure-pe function, if supported */
+		if (ibm_configure_pe != RTAS_UNKNOWN_SERVICE) {
+			ret = rtas_call(ibm_configure_pe, 3, 1, NULL,
+					config_addr, BUID_HI(pe->phb->buid),
+					BUID_LO(pe->phb->buid));
+		} else if (ibm_configure_bridge != RTAS_UNKNOWN_SERVICE) {
+			ret = rtas_call(ibm_configure_bridge, 3, 1, NULL,
+					config_addr, BUID_HI(pe->phb->buid),
+					BUID_LO(pe->phb->buid));
+		} else {
+			return -EFAULT;
+		}
+
+		if (!ret)
+			return ret;
+
+		/*
+		 * If RTAS returns a delay value that's above 100ms, cut it
+		 * down to 100ms in case firmware made a mistake.  For more
+		 * on how these delay values work see rtas_busy_delay_time
+		 */
+		if (ret > RTAS_EXTENDED_DELAY_MIN+2 &&
+		    ret <= RTAS_EXTENDED_DELAY_MAX)
+			ret = RTAS_EXTENDED_DELAY_MIN+2;
+
+		max_wait -= rtas_busy_delay_time(ret);
+
+		if (max_wait < 0)
+			break;
+
+		rtas_busy_delay(ret);
 	}

-	if (ret)
-		pr_warn("%s: Unable to configure bridge PHB#%d-PE#%x (%d)\n",
-			__func__, pe->phb->global_number, pe->addr, ret);
-
+	pr_warn("%s: Unable to configure bridge PHB#%d-PE#%x (%d)\n",
+		__func__, pe->phb->global_number, pe->addr, ret);
 	return ret;
 }

--- a/arch/s390/net/bpf_jit.h
+++ b/arch/s390/net/bpf_jit.h
@ -37,7 +37,7 @@ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
 *	      |		      |     |
 *	      +---------------+     |
 *	      | 8 byte skbp   |     |
- * R15+170 -> +---------------+     |
+ * R15+176 -> +---------------+     |
 *	      | 8 byte hlen   |     |
 * R15+168 -> +---------------+     |
 *	      | 4 byte align  |     |
@ -58,7 +58,7 @@ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
 #define STK_OFF		(STK_SPACE - STK_160_UNUSED)
 #define STK_OFF_TMP	160	/* Offset of tmp buffer on stack */
 #define STK_OFF_HLEN	168	/* Offset of SKB header length on stack */
-#define STK_OFF_SKBP	170	/* Offset of SKB pointer on stack */
+#define STK_OFF_SKBP	176	/* Offset of SKB pointer on stack */

 #define STK_OFF_R6	(160 - 11 * 8)	/* Offset of r6 on stack */
 #define STK_OFF_TCCNT	(160 - 12 * 8)	/* Offset of tail_call_cnt on stack */
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@ -45,7 +45,7 @@ struct bpf_jit {
 	int labels[1];		/* Labels for local jumps */
 };

-#define BPF_SIZE_MAX	0x7ffff	/* Max size for program (20 bit signed displ) */
+#define BPF_SIZE_MAX	0xffff	/* Max size for program (16 bit branches) */

 #define SEEN_SKB	1	/* skb access */
 #define SEEN_MEM	2	/* use mem[] for temporary storage */
@ -446,7 +446,7 @@ static void bpf_jit_prologue(struct bpf_jit *jit, bool is_classic)
 		emit_load_skb_data_hlen(jit);
 	if (jit->seen & SEEN_SKB_CHANGE)
 		/* stg %b1,ST_OFF_SKBP(%r0,%r15) */
-		EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0, REG_15,
+		EMIT6_DISP_LH(0xe3000000, 0x0024, BPF_REG_1, REG_0, REG_15,
 			      STK_OFF_SKBP);
 	/* Clear A (%b0) and X (%b7) registers for converted BPF programs */
 	if (is_classic) {
--- a/arch/sparc/include/asm/head_64.h
+++ b/arch/sparc/include/asm/head_64.h
@ -15,6 +15,10 @@

 #define	PTREGS_OFF	(STACK_BIAS + STACKFRAME_SZ)

+#define	RTRAP_PSTATE		(PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_IE)
+#define	RTRAP_PSTATE_IRQOFF	(PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV)
+#define RTRAP_PSTATE_AG_IRQOFF	(PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_AG)
+
 #define __CHEETAH_ID	0x003e0014
 #define __JALAPENO_ID	0x003e0016
 #define __SERRANO_ID	0x003e0022
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@ -375,7 +375,7 @@ static inline pgprot_t pgprot_noncached(pgprot_t prot)
 #define pgprot_noncached pgprot_noncached

 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-static inline pte_t pte_mkhuge(pte_t pte)
+static inline unsigned long __pte_huge_mask(void)
 {
 	unsigned long mask;

@ -390,8 +390,19 @@ static inline pte_t pte_mkhuge(pte_t pte)
 	: "=r" (mask)
 	: "i" (_PAGE_SZHUGE_4U), "i" (_PAGE_SZHUGE_4V));

-	return __pte(pte_val(pte) | mask);
+	return mask;
 }
+
+static inline pte_t pte_mkhuge(pte_t pte)
+{
+	return __pte(pte_val(pte) | __pte_huge_mask());
+}
+
+static inline bool is_hugetlb_pte(pte_t pte)
+{
+	return !!(pte_val(pte) & __pte_huge_mask());
+}
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 static inline pmd_t pmd_mkhuge(pmd_t pmd)
 {
@ -403,6 +414,11 @@ static inline pmd_t pmd_mkhuge(pmd_t pmd)
 	return __pmd(pte_val(pte));
 }
 #endif
+#else
+static inline bool is_hugetlb_pte(pte_t pte)
+{
+	return false;
+}
 #endif

 static inline pte_t pte_mkdirty(pte_t pte)
@ -865,6 +881,19 @@ static inline unsigned long pud_pfn(pud_t pud)
 void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
 		   pte_t *ptep, pte_t orig, int fullmm);

+static void maybe_tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
+				pte_t *ptep, pte_t orig, int fullmm)
+{
+	/* It is more efficient to let flush_tlb_kernel_range()
+	 * handle init_mm tlb flushes.
+	 *
+	 * SUN4V NOTE: _PAGE_VALID is the same value in both the SUN4U
+	 *             and SUN4V pte layout, so this inline test is fine.
+	 */
+	if (likely(mm != &init_mm) && pte_accessible(mm, orig))
+		tlb_batch_add(mm, vaddr, ptep, orig, fullmm);
+}
+
 #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
 static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
 					    unsigned long addr,
@ -881,15 +910,7 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 	pte_t orig = *ptep;

 	*ptep = pte;
-
-	/* It is more efficient to let flush_tlb_kernel_range()
-	 * handle init_mm tlb flushes.
-	 *
-	 * SUN4V NOTE: _PAGE_VALID is the same value in both the SUN4U
-	 *             and SUN4V pte layout, so this inline test is fine.
-	 */
-	if (likely(mm != &init_mm) && pte_accessible(mm, orig))
-		tlb_batch_add(mm, addr, ptep, orig, fullmm);
+	maybe_tlb_batch_add(mm, addr, ptep, orig, fullmm);
 }

 #define set_pte_at(mm,addr,ptep,pte)	\
--- a/arch/sparc/include/asm/tlbflush_64.h
+++ b/arch/sparc/include/asm/tlbflush_64.h
@ -8,6 +8,7 @@
 #define TLB_BATCH_NR	192

 struct tlb_batch {
+	bool huge;
 	struct mm_struct *mm;
 	unsigned long tlb_nr;
 	unsigned long active;
@ -16,7 +17,7 @@ struct tlb_batch {

 void flush_tsb_kernel_range(unsigned long start, unsigned long end);
 void flush_tsb_user(struct tlb_batch *tb);
-void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr);
+void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr, bool huge);

 /* TLB flush operations. */

--- a/arch/sparc/include/asm/ttable.h
+++ b/arch/sparc/include/asm/ttable.h
@ -589,8 +589,8 @@ user_rtt_fill_64bit:					\
 	 restored;					\
 	nop; nop; nop; nop; nop; nop;			\
 	nop; nop; nop; nop; nop;			\
-	ba,a,pt	%xcc, user_rtt_fill_fixup;		\
-	ba,a,pt	%xcc, user_rtt_fill_fixup;		\
+	ba,a,pt	%xcc, user_rtt_fill_fixup_dax;		\
+	ba,a,pt	%xcc, user_rtt_fill_fixup_mna;		\
 	ba,a,pt	%xcc, user_rtt_fill_fixup;


@ -652,8 +652,8 @@ user_rtt_fill_32bit:					\
 	 restored;					\
 	nop; nop; nop; nop; nop;			\
 	nop; nop; nop;					\
-	ba,a,pt	%xcc, user_rtt_fill_fixup;		\
-	ba,a,pt	%xcc, user_rtt_fill_fixup;		\
+	ba,a,pt	%xcc, user_rtt_fill_fixup_dax;		\
+	ba,a,pt	%xcc, user_rtt_fill_fixup_mna;		\
 	ba,a,pt	%xcc, user_rtt_fill_fixup;


--- a/arch/sparc/kernel/Makefile
+++ b/arch/sparc/kernel/Makefile
@ -21,6 +21,7 @@ CFLAGS_REMOVE_perf_event.o := -pg
 CFLAGS_REMOVE_pcr.o := -pg
 endif

+obj-$(CONFIG_SPARC64)   += urtt_fill.o
 obj-$(CONFIG_SPARC32)   += entry.o wof.o wuf.o
 obj-$(CONFIG_SPARC32)   += etrap_32.o
 obj-$(CONFIG_SPARC32)   += rtrap_32.o
--- a/arch/sparc/kernel/cherrs.S
+++ b/arch/sparc/kernel/cherrs.S
@ -214,8 +214,7 @@ do_dcpe_tl1_nonfatal:	/* Ok we may use interrupt globals safely. */
 	subcc		%g1, %g2, %g1		! Next cacheline
 	bge,pt		%icc, 1b
 	 nop
-	ba,pt		%xcc, dcpe_icpe_tl1_common
-	 nop
+	ba,a,pt		%xcc, dcpe_icpe_tl1_common

 do_dcpe_tl1_fatal:
 	sethi		%hi(1f), %g7
@ -224,8 +223,7 @@ do_dcpe_tl1_fatal:
 	mov		0x2, %o0
 	call		cheetah_plus_parity_error
 	 add		%sp, PTREGS_OFF, %o1
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		do_dcpe_tl1,.-do_dcpe_tl1

 	.globl		do_icpe_tl1
@ -259,8 +257,7 @@ do_icpe_tl1_nonfatal:	/* Ok we may use interrupt globals safely. */
 	subcc		%g1, %g2, %g1
 	bge,pt		%icc, 1b
 	 nop
-	ba,pt		%xcc, dcpe_icpe_tl1_common
-	 nop
+	ba,a,pt		%xcc, dcpe_icpe_tl1_common

 do_icpe_tl1_fatal:
 	sethi		%hi(1f), %g7
@ -269,8 +266,7 @@ do_icpe_tl1_fatal:
 	mov		0x3, %o0
 	call		cheetah_plus_parity_error
 	 add		%sp, PTREGS_OFF, %o1
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		do_icpe_tl1,.-do_icpe_tl1
 	
 	.type		dcpe_icpe_tl1_common,#function
@ -456,7 +452,7 @@ __cheetah_log_error:
 	 cmp		%g2, 0x63
 	be		c_cee
 	 nop
-	ba,pt		%xcc, c_deferred
+	ba,a,pt		%xcc, c_deferred
 	.size		__cheetah_log_error,.-__cheetah_log_error

 	/* Cheetah FECC trap handling, we get here from tl{0,1}_fecc
--- a/arch/sparc/kernel/entry.S
+++ b/arch/sparc/kernel/entry.S
@ -948,7 +948,24 @@ linux_syscall_trace:
 	cmp	%o0, 0
 	bne	3f
 	 mov	-ENOSYS, %o0
+
+	/* Syscall tracing can modify the registers.  */
+	ld	[%sp + STACKFRAME_SZ + PT_G1], %g1
+	sethi	%hi(sys_call_table), %l7
+	ld	[%sp + STACKFRAME_SZ + PT_I0], %i0
+	or	%l7, %lo(sys_call_table), %l7
+	ld	[%sp + STACKFRAME_SZ + PT_I1], %i1
+	ld	[%sp + STACKFRAME_SZ + PT_I2], %i2
+	ld	[%sp + STACKFRAME_SZ + PT_I3], %i3
+	ld	[%sp + STACKFRAME_SZ + PT_I4], %i4
+	ld	[%sp + STACKFRAME_SZ + PT_I5], %i5
+	cmp	%g1, NR_syscalls
+	bgeu	3f
+	 mov	-ENOSYS, %o0
+
+	sll	%g1, 2, %l4
 	mov	%i0, %o0
+	ld	[%l7 + %l4], %l7
 	mov	%i1, %o1
 	mov	%i2, %o2
 	mov	%i3, %o3
--- a/arch/sparc/kernel/fpu_traps.S
+++ b/arch/sparc/kernel/fpu_traps.S
@ -100,8 +100,8 @@ do_fpdis:
 	fmuld		%f0, %f2, %f26
 	faddd		%f0, %f2, %f28
 	fmuld		%f0, %f2, %f30
-	b,pt		%xcc, fpdis_exit
-	 nop
+	ba,a,pt		%xcc, fpdis_exit
+
 2:	andcc		%g5, FPRS_DU, %g0
 	bne,pt		%icc, 3f
 	 fzero		%f32
@ -144,8 +144,8 @@ do_fpdis:
 	fmuld		%f32, %f34, %f58
 	faddd		%f32, %f34, %f60
 	fmuld		%f32, %f34, %f62
-	ba,pt		%xcc, fpdis_exit
-	 nop
+	ba,a,pt		%xcc, fpdis_exit
+
 3:	mov		SECONDARY_CONTEXT, %g3
 	add		%g6, TI_FPREGS, %g1

@ -197,8 +197,7 @@ fpdis_exit2:
 fp_other_bounce:
 	call		do_fpother
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		fp_other_bounce,.-fp_other_bounce

 	.align		32
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@ -461,9 +461,8 @@ sun4v_chip_type:
 	subcc	%g3, 1, %g3
 	bne,pt	%xcc, 41b
 	add	%g1, 1, %g1
-	mov	SUN4V_CHIP_SPARC64X, %g4
 	ba,pt	%xcc, 5f
-	nop
+	 mov	SUN4V_CHIP_SPARC64X, %g4

 49:
 	mov	SUN4V_CHIP_UNKNOWN, %g4
@ -548,8 +547,7 @@ sun4u_init:
 	stxa		%g0, [%g7] ASI_DMMU
 	membar	#Sync

-	ba,pt		%xcc, sun4u_continue
-	 nop
+	ba,a,pt		%xcc, sun4u_continue

 sun4v_init:
 	/* Set ctx 0 */
@ -560,14 +558,12 @@ sun4v_init:
 	mov		SECONDARY_CONTEXT, %g7
 	stxa		%g0, [%g7] ASI_MMU
 	membar		#Sync
-	ba,pt		%xcc, niagara_tlb_fixup
-	 nop
+	ba,a,pt		%xcc, niagara_tlb_fixup

 sun4u_continue:
 	BRANCH_IF_ANY_CHEETAH(g1, g7, cheetah_tlb_fixup)

-	ba,pt	%xcc, spitfire_tlb_fixup
-	 nop
+	ba,a,pt	%xcc, spitfire_tlb_fixup

 niagara_tlb_fixup:
 	mov	3, %g2		/* Set TLB type to hypervisor. */
@ -639,8 +635,7 @@ niagara_patch:
 	call	hypervisor_patch_cachetlbops
 	 nop

-	ba,pt	%xcc, tlb_fixup_done
-	 nop
+	ba,a,pt	%xcc, tlb_fixup_done

 cheetah_tlb_fixup:
 	mov	2, %g2		/* Set TLB type to cheetah+. */
@ -659,8 +654,7 @@ cheetah_tlb_fixup:
 	call	cheetah_patch_cachetlbops
 	 nop

-	ba,pt	%xcc, tlb_fixup_done
-	 nop
+	ba,a,pt	%xcc, tlb_fixup_done

 spitfire_tlb_fixup:
 	/* Set TLB type to spitfire. */
@ -782,8 +776,7 @@ setup_trap_table:
 	call	%o1
 	 add	%sp, (2047 + 128), %o0

-	ba,pt	%xcc, 2f
-	 nop
+	ba,a,pt	%xcc, 2f

 1:	sethi	%hi(sparc64_ttable_tl0), %o0
 	set	prom_set_trap_table_name, %g2
@ -822,8 +815,7 @@ setup_trap_table:

 	BRANCH_IF_ANY_CHEETAH(o2, o3, 1f)

-	ba,pt	%xcc, 2f
-	 nop
+	ba,a,pt	%xcc, 2f

 	/* Disable STICK_INT interrupts. */
 1:
--- a/arch/sparc/kernel/misctrap.S
+++ b/arch/sparc/kernel/misctrap.S
@ -18,8 +18,7 @@ __do_privact:
 109:	or		%g7, %lo(109b), %g7
 	call		do_privact
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		__do_privact,.-__do_privact

 	.type		do_mna,#function
@ -46,8 +45,7 @@ do_mna:
 	mov		%l5, %o2
 	call		mem_address_unaligned
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		do_mna,.-do_mna

 	.type		do_lddfmna,#function
@ -65,8 +63,7 @@ do_lddfmna:
 	mov		%l5, %o2
 	call		handle_lddfmna
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		do_lddfmna,.-do_lddfmna

 	.type		do_stdfmna,#function
@ -84,8 +81,7 @@ do_stdfmna:
 	mov		%l5, %o2
 	call		handle_stdfmna
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		do_stdfmna,.-do_stdfmna

 	.type		breakpoint_trap,#function
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@ -994,6 +994,23 @@ void pcibios_set_master(struct pci_dev *dev)
 	/* No special bus mastering setup handling */
 }

+#ifdef CONFIG_PCI_IOV
+int pcibios_add_device(struct pci_dev *dev)
+{
+	struct pci_dev *pdev;
+
+	/* Add sriov arch specific initialization here.
+	 * Copy dev_archdata from PF to VF
+	 */
+	if (dev->is_virtfn) {
+		pdev = dev->physfn;
+		memcpy(&dev->dev.archdata, &pdev->dev.archdata,
+		       sizeof(struct dev_archdata));
+	}
+	return 0;
+}
+#endif /* CONFIG_PCI_IOV */
+
 static int __init pcibios_init(void)
 {
 	pci_dfl_cache_line_size = 64 >> 2;
--- a/arch/sparc/kernel/rtrap_64.S
+++ b/arch/sparc/kernel/rtrap_64.S
@ -14,10 +14,6 @@
 #include <asm/visasm.h>
 #include <asm/processor.h>

-#define		RTRAP_PSTATE		(PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_IE)
-#define		RTRAP_PSTATE_IRQOFF	(PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV)
-#define		RTRAP_PSTATE_AG_IRQOFF	(PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_AG)
-
 #ifdef CONFIG_CONTEXT_TRACKING
 # define SCHEDULE_USER schedule_user
 #else
@ -242,52 +238,17 @@ rt_continue:	ldx			[%sp + PTREGS_OFF + PT_V9_G1], %g1
 		 wrpr			%g1, %cwp
 		ba,a,pt			%xcc, user_rtt_fill_64bit

+user_rtt_fill_fixup_dax:
+		ba,pt	%xcc, user_rtt_fill_fixup_common
+		 mov	1, %g3
+
+user_rtt_fill_fixup_mna:
+		ba,pt	%xcc, user_rtt_fill_fixup_common
+		 mov	2, %g3
+
 user_rtt_fill_fixup:
-		rdpr	%cwp, %g1
-		add	%g1, 1, %g1
-		wrpr	%g1, 0x0, %cwp
-
-		rdpr	%wstate, %g2
-		sll	%g2, 3, %g2
-		wrpr	%g2, 0x0, %wstate
-
-		/* We know %canrestore and %otherwin are both zero.  */
-
-		sethi	%hi(sparc64_kern_pri_context), %g2
-		ldx	[%g2 + %lo(sparc64_kern_pri_context)], %g2
-		mov	PRIMARY_CONTEXT, %g1
-
-661:		stxa	%g2, [%g1] ASI_DMMU
-		.section .sun4v_1insn_patch, "ax"
-		.word	661b
-		stxa	%g2, [%g1] ASI_MMU
-		.previous
-
-		sethi	%hi(KERNBASE), %g1
-		flush	%g1
-
-		or	%g4, FAULT_CODE_WINFIXUP, %g4
-		stb	%g4, [%g6 + TI_FAULT_CODE]
-		stx	%g5, [%g6 + TI_FAULT_ADDR]
-
-		mov	%g6, %l1
-		wrpr	%g0, 0x0, %tl
-
-661:		nop
-		.section		.sun4v_1insn_patch, "ax"
-		.word			661b
-		SET_GL(0)
-		.previous
-
-		wrpr	%g0, RTRAP_PSTATE, %pstate
-
-		mov	%l1, %g6
-		ldx	[%g6 + TI_TASK], %g4
-		LOAD_PER_CPU_BASE(%g5, %g6, %g1, %g2, %g3)
-		call	do_sparc64_fault
-		 add	%sp, PTREGS_OFF, %o0
-		ba,pt	%xcc, rtrap
-		 nop
+		ba,pt	%xcc, user_rtt_fill_fixup_common
+		 clr	%g3

 user_rtt_pre_restore:
 		add			%g1, 1, %g1
--- a/arch/sparc/kernel/signal32.c
+++ b/arch/sparc/kernel/signal32.c
@ -138,12 +138,24 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
 	return 0;
 }

+/* Checks if the fp is valid.  We always build signal frames which are
+ * 16-byte aligned, therefore we can always enforce that the restore
+ * frame has that property as well.
+ */
+static bool invalid_frame_pointer(void __user *fp, int fplen)
+{
+	if ((((unsigned long) fp) & 15) ||
+	    ((unsigned long)fp) > 0x100000000ULL - fplen)
+		return true;
+	return false;
+}
+
 void do_sigreturn32(struct pt_regs *regs)
 {
 	struct signal_frame32 __user *sf;
 	compat_uptr_t fpu_save;
 	compat_uptr_t rwin_save;
-	unsigned int psr;
+	unsigned int psr, ufp;
 	unsigned pc, npc;
 	sigset_t set;
 	compat_sigset_t seta;
@ -158,11 +170,16 @@ void do_sigreturn32(struct pt_regs *regs)
 	sf = (struct signal_frame32 __user *) regs->u_regs[UREG_FP];

 	/* 1. Make sure we are not getting garbage from the user */
-	if (!access_ok(VERIFY_READ, sf, sizeof(*sf)) ||
-	    (((unsigned long) sf) & 3))
+	if (invalid_frame_pointer(sf, sizeof(*sf)))
 		goto segv;

-	if (get_user(pc, &sf->info.si_regs.pc) ||
+	if (get_user(ufp, &sf->info.si_regs.u_regs[UREG_FP]))
+		goto segv;
+
+	if (ufp & 0x7)
+		goto segv;
+
+	if (__get_user(pc, &sf->info.si_regs.pc) ||
 	    __get_user(npc, &sf->info.si_regs.npc))
 		goto segv;

@ -227,7 +244,7 @@ void do_sigreturn32(struct pt_regs *regs)
 asmlinkage void do_rt_sigreturn32(struct pt_regs *regs)
 {
 	struct rt_signal_frame32 __user *sf;
-	unsigned int psr, pc, npc;
+	unsigned int psr, pc, npc, ufp;
 	compat_uptr_t fpu_save;
 	compat_uptr_t rwin_save;
 	sigset_t set;
@ -242,11 +259,16 @@ asmlinkage void do_rt_sigreturn32(struct pt_regs *regs)
 	sf = (struct rt_signal_frame32 __user *) regs->u_regs[UREG_FP];

 	/* 1. Make sure we are not getting garbage from the user */
-	if (!access_ok(VERIFY_READ, sf, sizeof(*sf)) ||
-	    (((unsigned long) sf) & 3))
+	if (invalid_frame_pointer(sf, sizeof(*sf)))
 		goto segv;

-	if (get_user(pc, &sf->regs.pc) || 
+	if (get_user(ufp, &sf->regs.u_regs[UREG_FP]))
+		goto segv;
+
+	if (ufp & 0x7)
+		goto segv;
+
+	if (__get_user(pc, &sf->regs.pc) ||
 	    __get_user(npc, &sf->regs.npc))
 		goto segv;

@ -307,14 +329,6 @@ asmlinkage void do_rt_sigreturn32(struct pt_regs *regs)
 	force_sig(SIGSEGV, current);
 }

-/* Checks if the fp is valid */
-static int invalid_frame_pointer(void __user *fp, int fplen)
-{
-	if ((((unsigned long) fp) & 7) || ((unsigned long)fp) > 0x100000000ULL - fplen)
-		return 1;
-	return 0;
-}
-
 static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, unsigned long framesize)
 {
 	unsigned long sp;
--- a/arch/sparc/kernel/signal_32.c
+++ b/arch/sparc/kernel/signal_32.c
@ -60,10 +60,22 @@ struct rt_signal_frame {
 #define SF_ALIGNEDSZ  (((sizeof(struct signal_frame) + 7) & (~7)))
 #define RT_ALIGNEDSZ  (((sizeof(struct rt_signal_frame) + 7) & (~7)))

+/* Checks if the fp is valid.  We always build signal frames which are
+ * 16-byte aligned, therefore we can always enforce that the restore
+ * frame has that property as well.
+ */
+static inline bool invalid_frame_pointer(void __user *fp, int fplen)
+{
+	if ((((unsigned long) fp) & 15) || !__access_ok((unsigned long)fp, fplen))
+		return true;
+
+	return false;
+}
+
 asmlinkage void do_sigreturn(struct pt_regs *regs)
 {
+	unsigned long up_psr, pc, npc, ufp;
 	struct signal_frame __user *sf;
-	unsigned long up_psr, pc, npc;
 	sigset_t set;
 	__siginfo_fpu_t __user *fpu_save;
 	__siginfo_rwin_t __user *rwin_save;
@ -77,10 +89,13 @@ asmlinkage void do_sigreturn(struct pt_regs *regs)
 	sf = (struct signal_frame __user *) regs->u_regs[UREG_FP];

 	/* 1. Make sure we are not getting garbage from the user */
-	if (!access_ok(VERIFY_READ, sf, sizeof(*sf)))
+	if (!invalid_frame_pointer(sf, sizeof(*sf)))
 		goto segv_and_exit;

-	if (((unsigned long) sf) & 3)
+	if (get_user(ufp, &sf->info.si_regs.u_regs[UREG_FP]))
+		goto segv_and_exit;
+
+	if (ufp & 0x7)
 		goto segv_and_exit;

 	err = __get_user(pc,  &sf->info.si_regs.pc);
@ -127,7 +142,7 @@ asmlinkage void do_sigreturn(struct pt_regs *regs)
 asmlinkage void do_rt_sigreturn(struct pt_regs *regs)
 {
 	struct rt_signal_frame __user *sf;
-	unsigned int psr, pc, npc;
+	unsigned int psr, pc, npc, ufp;
 	__siginfo_fpu_t __user *fpu_save;
 	__siginfo_rwin_t __user *rwin_save;
 	sigset_t set;
@ -135,8 +150,13 @@ asmlinkage void do_rt_sigreturn(struct pt_regs *regs)

 	synchronize_user_stack();
 	sf = (struct rt_signal_frame __user *) regs->u_regs[UREG_FP];
-	if (!access_ok(VERIFY_READ, sf, sizeof(*sf)) ||
-	    (((unsigned long) sf) & 0x03))
+	if (!invalid_frame_pointer(sf, sizeof(*sf)))
+		goto segv;
+
+	if (get_user(ufp, &sf->regs.u_regs[UREG_FP]))
+		goto segv;
+
+	if (ufp & 0x7)
 		goto segv;

 	err = __get_user(pc, &sf->regs.pc);
@ -178,15 +198,6 @@ asmlinkage void do_rt_sigreturn(struct pt_regs *regs)
 	force_sig(SIGSEGV, current);
 }

-/* Checks if the fp is valid */
-static inline int invalid_frame_pointer(void __user *fp, int fplen)
-{
-	if ((((unsigned long) fp) & 7) || !__access_ok((unsigned long)fp, fplen))
-		return 1;
-
-	return 0;
-}
-
 static inline void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, unsigned long framesize)
 {
 	unsigned long sp = regs->u_regs[UREG_FP];
--- a/arch/sparc/kernel/signal_64.c
+++ b/arch/sparc/kernel/signal_64.c
@ -52,7 +52,7 @@ asmlinkage void sparc64_set_context(struct pt_regs *regs)
 	unsigned char fenab;
 	int err;

-	flush_user_windows();
+	synchronize_user_stack();
 	if (get_thread_wsaved()					||
 	    (((unsigned long)ucp) & (sizeof(unsigned long)-1))	||
 	    (!__access_ok(ucp, sizeof(*ucp))))
@ -234,6 +234,17 @@ asmlinkage void sparc64_get_context(struct pt_regs *regs)
 	goto out;
 }

+/* Checks if the fp is valid.  We always build rt signal frames which
+ * are 16-byte aligned, therefore we can always enforce that the
+ * restore frame has that property as well.
+ */
+static bool invalid_frame_pointer(void __user *fp)
+{
+	if (((unsigned long) fp) & 15)
+		return true;
+	return false;
+}
+
 struct rt_signal_frame {
 	struct sparc_stackf	ss;
 	siginfo_t		info;
@ -246,8 +257,8 @@ struct rt_signal_frame {

 void do_rt_sigreturn(struct pt_regs *regs)
 {
+	unsigned long tpc, tnpc, tstate, ufp;
 	struct rt_signal_frame __user *sf;
-	unsigned long tpc, tnpc, tstate;
 	__siginfo_fpu_t __user *fpu_save;
 	__siginfo_rwin_t __user *rwin_save;
 	sigset_t set;
@ -261,10 +272,16 @@ void do_rt_sigreturn(struct pt_regs *regs)
 		(regs->u_regs [UREG_FP] + STACK_BIAS);

 	/* 1. Make sure we are not getting garbage from the user */
-	if (((unsigned long) sf) & 3)
+	if (invalid_frame_pointer(sf))
 		goto segv;

-	err = get_user(tpc, &sf->regs.tpc);
+	if (get_user(ufp, &sf->regs.u_regs[UREG_FP]))
+		goto segv;
+
+	if ((ufp + STACK_BIAS) & 0x7)
+		goto segv;
+
+	err = __get_user(tpc, &sf->regs.tpc);
 	err |= __get_user(tnpc, &sf->regs.tnpc);
 	if (test_thread_flag(TIF_32BIT)) {
 		tpc &= 0xffffffff;
@ -308,14 +325,6 @@ void do_rt_sigreturn(struct pt_regs *regs)
 	force_sig(SIGSEGV, current);
 }

-/* Checks if the fp is valid */
-static int invalid_frame_pointer(void __user *fp)
-{
-	if (((unsigned long) fp) & 15)
-		return 1;
-	return 0;
-}
-
 static inline void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, unsigned long framesize)
 {
 	unsigned long sp = regs->u_regs[UREG_FP] + STACK_BIAS;
--- a/arch/sparc/kernel/sigutil_32.c
+++ b/arch/sparc/kernel/sigutil_32.c
@ -48,6 +48,10 @@ int save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
 int restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
 {
 	int err;
+
+	if (((unsigned long) fpu) & 3)
+		return -EFAULT;
+
 #ifdef CONFIG_SMP
 	if (test_tsk_thread_flag(current, TIF_USEDFPU))
 		regs->psr &= ~PSR_EF;
@ -97,7 +101,10 @@ int restore_rwin_state(__siginfo_rwin_t __user *rp)
 	struct thread_info *t = current_thread_info();
 	int i, wsaved, err;

-	__get_user(wsaved, &rp->wsaved);
+	if (((unsigned long) rp) & 3)
+		return -EFAULT;
+
+	get_user(wsaved, &rp->wsaved);
 	if (wsaved > NSWINS)
 		return -EFAULT;

--- a/arch/sparc/kernel/sigutil_64.c
+++ b/arch/sparc/kernel/sigutil_64.c
@ -37,7 +37,10 @@ int restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
 	unsigned long fprs;
 	int err;

-	err = __get_user(fprs, &fpu->si_fprs);
+	if (((unsigned long) fpu) & 7)
+		return -EFAULT;
+
+	err = get_user(fprs, &fpu->si_fprs);
 	fprs_write(0);
 	regs->tstate &= ~TSTATE_PEF;
 	if (fprs & FPRS_DL)
@ -72,7 +75,10 @@ int restore_rwin_state(__siginfo_rwin_t __user *rp)
 	struct thread_info *t = current_thread_info();
 	int i, wsaved, err;

-	__get_user(wsaved, &rp->wsaved);
+	if (((unsigned long) rp) & 7)
+		return -EFAULT;
+
+	get_user(wsaved, &rp->wsaved);
 	if (wsaved > NSWINS)
 		return -EFAULT;

--- a/arch/sparc/kernel/spiterrs.S
+++ b/arch/sparc/kernel/spiterrs.S
@ -85,8 +85,7 @@ __spitfire_cee_trap_continue:
 	ba,pt		%xcc, etraptl1
 	 rd		%pc, %g7

-	ba,pt		%xcc, 2f
-	 nop
+	ba,a,pt		%xcc, 2f

 1:	ba,pt		%xcc, etrap_irq
 	 rd		%pc, %g7
@ -100,8 +99,7 @@ __spitfire_cee_trap_continue:
 	mov		%l5, %o2
 	call		spitfire_access_error
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		__spitfire_access_error,.-__spitfire_access_error

 	/* This is the trap handler entry point for ECC correctable
@ -179,8 +177,7 @@ __spitfire_data_access_exception_tl1:
 	mov		%l5, %o2
 	call		spitfire_data_access_exception_tl1
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		__spitfire_data_access_exception_tl1,.-__spitfire_data_access_exception_tl1

 	.type		__spitfire_data_access_exception,#function
@ -200,8 +197,7 @@ __spitfire_data_access_exception:
 	mov		%l5, %o2
 	call		spitfire_data_access_exception
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		__spitfire_data_access_exception,.-__spitfire_data_access_exception

 	.type		__spitfire_insn_access_exception_tl1,#function
@ -220,8 +216,7 @@ __spitfire_insn_access_exception_tl1:
 	mov		%l5, %o2
 	call		spitfire_insn_access_exception_tl1
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		__spitfire_insn_access_exception_tl1,.-__spitfire_insn_access_exception_tl1

 	.type		__spitfire_insn_access_exception,#function
@ -240,6 +235,5 @@ __spitfire_insn_access_exception:
 	mov		%l5, %o2
 	call		spitfire_insn_access_exception
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		__spitfire_insn_access_exception,.-__spitfire_insn_access_exception
--- a/arch/sparc/kernel/syscalls.S
+++ b/arch/sparc/kernel/syscalls.S
@ -158,7 +158,25 @@ linux_syscall_trace32:
 	 add	%sp, PTREGS_OFF, %o0
 	brnz,pn	%o0, 3f
 	 mov	-ENOSYS, %o0
+
+	/* Syscall tracing can modify the registers.  */
+	ldx	[%sp + PTREGS_OFF + PT_V9_G1], %g1
+	sethi	%hi(sys_call_table32), %l7
+	ldx	[%sp + PTREGS_OFF + PT_V9_I0], %i0
+	or	%l7, %lo(sys_call_table32), %l7
+	ldx	[%sp + PTREGS_OFF + PT_V9_I1], %i1
+	ldx	[%sp + PTREGS_OFF + PT_V9_I2], %i2
+	ldx	[%sp + PTREGS_OFF + PT_V9_I3], %i3
+	ldx	[%sp + PTREGS_OFF + PT_V9_I4], %i4
+	ldx	[%sp + PTREGS_OFF + PT_V9_I5], %i5
+
+	cmp	%g1, NR_syscalls
+	bgeu,pn	%xcc, 3f
+	 mov	-ENOSYS, %o0
+
+	sll	%g1, 2, %l4
 	srl	%i0, 0, %o0
+	lduw	[%l7 + %l4], %l7
 	srl	%i4, 0, %o4
 	srl	%i1, 0, %o1
 	srl	%i2, 0, %o2
@ -170,7 +188,25 @@ linux_syscall_trace:
 	 add	%sp, PTREGS_OFF, %o0
 	brnz,pn	%o0, 3f
 	 mov	-ENOSYS, %o0
+
+	/* Syscall tracing can modify the registers.  */
+	ldx	[%sp + PTREGS_OFF + PT_V9_G1], %g1
+	sethi	%hi(sys_call_table64), %l7
+	ldx	[%sp + PTREGS_OFF + PT_V9_I0], %i0
+	or	%l7, %lo(sys_call_table64), %l7
+	ldx	[%sp + PTREGS_OFF + PT_V9_I1], %i1
+	ldx	[%sp + PTREGS_OFF + PT_V9_I2], %i2
+	ldx	[%sp + PTREGS_OFF + PT_V9_I3], %i3
+	ldx	[%sp + PTREGS_OFF + PT_V9_I4], %i4
+	ldx	[%sp + PTREGS_OFF + PT_V9_I5], %i5
+
+	cmp	%g1, NR_syscalls
+	bgeu,pn	%xcc, 3f
+	 mov	-ENOSYS, %o0
+
+	sll	%g1, 2, %l4
 	mov	%i0, %o0
+	lduw	[%l7 + %l4], %l7
 	mov	%i1, %o1
 	mov	%i2, %o2
 	mov	%i3, %o3
--- a/arch/sparc/kernel/urtt_fill.S
+++ b/arch/sparc/kernel/urtt_fill.S
@ -0,0 +1,98 @@
+#include <asm/thread_info.h>
+#include <asm/trap_block.h>
+#include <asm/spitfire.h>
+#include <asm/ptrace.h>
+#include <asm/head.h>
+
+		.text
+		.align	8
+		.globl	user_rtt_fill_fixup_common
+user_rtt_fill_fixup_common:
+		rdpr	%cwp, %g1
+		add	%g1, 1, %g1
+		wrpr	%g1, 0x0, %cwp
+
+		rdpr	%wstate, %g2
+		sll	%g2, 3, %g2
+		wrpr	%g2, 0x0, %wstate
+
+		/* We know %canrestore and %otherwin are both zero.  */
+
+		sethi	%hi(sparc64_kern_pri_context), %g2
+		ldx	[%g2 + %lo(sparc64_kern_pri_context)], %g2
+		mov	PRIMARY_CONTEXT, %g1
+
+661:		stxa	%g2, [%g1] ASI_DMMU
+		.section .sun4v_1insn_patch, "ax"
+		.word	661b
+		stxa	%g2, [%g1] ASI_MMU
+		.previous
+
+		sethi	%hi(KERNBASE), %g1
+		flush	%g1
+
+		mov	%g4, %l4
+		mov	%g5, %l5
+		brnz,pn	%g3, 1f
+		 mov	%g3, %l3
+
+		or	%g4, FAULT_CODE_WINFIXUP, %g4
+		stb	%g4, [%g6 + TI_FAULT_CODE]
+		stx	%g5, [%g6 + TI_FAULT_ADDR]
+1:
+		mov	%g6, %l1
+		wrpr	%g0, 0x0, %tl
+
+661:		nop
+		.section		.sun4v_1insn_patch, "ax"
+		.word			661b
+		SET_GL(0)
+		.previous
+
+		wrpr	%g0, RTRAP_PSTATE, %pstate
+
+		mov	%l1, %g6
+		ldx	[%g6 + TI_TASK], %g4
+		LOAD_PER_CPU_BASE(%g5, %g6, %g1, %g2, %g3)
+
+		brnz,pn	%l3, 1f
+		 nop
+
+		call	do_sparc64_fault
+		 add	%sp, PTREGS_OFF, %o0
+		ba,pt	%xcc, rtrap
+		 nop
+
+1:		cmp	%g3, 2
+		bne,pn	%xcc, 2f
+		 nop
+
+		sethi	%hi(tlb_type), %g1
+		lduw	[%g1 + %lo(tlb_type)], %g1
+		cmp	%g1, 3
+		bne,pt	%icc, 1f
+		 add	%sp, PTREGS_OFF, %o0
+		mov	%l4, %o2
+		call	sun4v_do_mna
+		 mov	%l5, %o1
+		ba,a,pt	%xcc, rtrap
+1:		mov	%l4, %o1
+		mov	%l5, %o2
+		call	mem_address_unaligned
+		 nop
+		ba,a,pt	%xcc, rtrap
+
+2:		sethi	%hi(tlb_type), %g1
+		mov	%l4, %o1
+		lduw	[%g1 + %lo(tlb_type)], %g1
+		mov	%l5, %o2
+		cmp	%g1, 3
+		bne,pt	%icc, 1f
+		 add	%sp, PTREGS_OFF, %o0
+		call	sun4v_data_access_exception
+		 nop
+		ba,a,pt	%xcc, rtrap
+
+1:		call	spitfire_data_access_exception
+		 nop
+		ba,a,pt	%xcc, rtrap
--- a/arch/sparc/kernel/utrap.S
+++ b/arch/sparc/kernel/utrap.S
@ -11,8 +11,7 @@ utrap_trap:		/* %g3=handler,%g4=level */
 	mov		%l4, %o1
        call		bad_trap
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap

 invoke_utrap:
 	sllx		%g3, 3, %g3
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@ -33,6 +33,10 @@ ENTRY(_start)
 jiffies = jiffies_64;
 #endif

+#ifdef CONFIG_SPARC64
+ASSERT((swapper_tsb == 0x0000000000408000), "Error: sparc64 early assembler too large")
+#endif
+
 SECTIONS
 {
 #ifdef CONFIG_SPARC64
--- a/arch/sparc/kernel/winfixup.S
+++ b/arch/sparc/kernel/winfixup.S
@ -32,8 +32,7 @@ fill_fixup:
 	 rd	%pc, %g7
 	call	do_sparc64_fault
 	 add	%sp, PTREGS_OFF, %o0
-	ba,pt	%xcc, rtrap
-	 nop
+	ba,a,pt	%xcc, rtrap

 	/* Be very careful about usage of the trap globals here.
 	 * You cannot touch %g5 as that has the fault information.
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@ -176,17 +176,31 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t entry)
 {
 	int i;
+	pte_t orig[2];
+	unsigned long nptes;

 	if (!pte_present(*ptep) && pte_present(entry))
 		mm->context.huge_pte_count++;

 	addr &= HPAGE_MASK;
-	for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) {
-		set_pte_at(mm, addr, ptep, entry);
+
+	nptes = 1 << HUGETLB_PAGE_ORDER;
+	orig[0] = *ptep;
+	orig[1] = *(ptep + nptes / 2);
+	for (i = 0; i < nptes; i++) {
+		*ptep = entry;
 		ptep++;
 		addr += PAGE_SIZE;
 		pte_val(entry) += PAGE_SIZE;
 	}
+
+	/* Issue TLB flush at REAL_HPAGE_SIZE boundaries */
+	addr -= REAL_HPAGE_SIZE;
+	ptep -= nptes / 2;
+	maybe_tlb_batch_add(mm, addr, ptep, orig[1], 0);
+	addr -= REAL_HPAGE_SIZE;
+	ptep -= nptes / 2;
+	maybe_tlb_batch_add(mm, addr, ptep, orig[0], 0);
 }

 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
@ -194,19 +208,28 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 {
 	pte_t entry;
 	int i;
+	unsigned long nptes;

 	entry = *ptep;
 	if (pte_present(entry))
 		mm->context.huge_pte_count--;

 	addr &= HPAGE_MASK;
-
-	for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) {
-		pte_clear(mm, addr, ptep);
+	nptes = 1 << HUGETLB_PAGE_ORDER;
+	for (i = 0; i < nptes; i++) {
+		*ptep = __pte(0UL);
 		addr += PAGE_SIZE;
 		ptep++;
 	}

+	/* Issue TLB flush at REAL_HPAGE_SIZE boundaries */
+	addr -= REAL_HPAGE_SIZE;
+	ptep -= nptes / 2;
+	maybe_tlb_batch_add(mm, addr, ptep, entry, 0);
+	addr -= REAL_HPAGE_SIZE;
+	ptep -= nptes / 2;
+	maybe_tlb_batch_add(mm, addr, ptep, entry, 0);
+
 	return entry;
 }

--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@ -324,18 +324,6 @@ static void __update_mmu_tsb_insert(struct mm_struct *mm, unsigned long tsb_inde
 	tsb_insert(tsb, tag, tte);
 }

-#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-static inline bool is_hugetlb_pte(pte_t pte)
-{
-	if ((tlb_type == hypervisor &&
-	     (pte_val(pte) & _PAGE_SZALL_4V) == _PAGE_SZHUGE_4V) ||
-	    (tlb_type != hypervisor &&
-	     (pte_val(pte) & _PAGE_SZALL_4U) == _PAGE_SZHUGE_4U))
-		return true;
-	return false;
-}
-#endif
-
 void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep)
 {
 	struct mm_struct *mm;
@ -1267,13 +1255,6 @@ static int __init numa_parse_mdesc(void)
 	int i, j, err, count;
 	u64 node;

-	/* Some sane defaults for numa latency values */
-	for (i = 0; i < MAX_NUMNODES; i++) {
-		for (j = 0; j < MAX_NUMNODES; j++)
-			numa_latency[i][j] = (i == j) ?
-				LOCAL_DISTANCE : REMOTE_DISTANCE;
-	}
-
 	node = mdesc_node_by_name(md, MDESC_NODE_NULL, "latency-groups");
 	if (node == MDESC_NODE_NULL) {
 		mdesc_release(md);
@ -1369,10 +1350,18 @@ static int __init numa_parse_sun4u(void)

 static int __init bootmem_init_numa(void)
 {
+	int i, j;
 	int err = -1;

 	numadbg("bootmem_init_numa()\n");

+	/* Some sane defaults for numa latency values */
+	for (i = 0; i < MAX_NUMNODES; i++) {
+		for (j = 0; j < MAX_NUMNODES; j++)
+			numa_latency[i][j] = (i == j) ?
+				LOCAL_DISTANCE : REMOTE_DISTANCE;
+	}
+
 	if (numa_enabled) {
 		if (tlb_type == hypervisor)
 			err = numa_parse_mdesc();
@ -2832,9 +2821,10 @@ void hugetlb_setup(struct pt_regs *regs)
 	 * the Data-TLB for huge pages.
 	 */
 	if (tlb_type == cheetah_plus) {
+		bool need_context_reload = false;
 		unsigned long ctx;

-		spin_lock(&ctx_alloc_lock);
+		spin_lock_irq(&ctx_alloc_lock);
 		ctx = mm->context.sparc64_ctx_val;
 		ctx &= ~CTX_PGSZ_MASK;
 		ctx |= CTX_PGSZ_BASE << CTX_PGSZ0_SHIFT;
@ -2853,9 +2843,12 @@ void hugetlb_setup(struct pt_regs *regs)
 			 * also executing in this address space.
 			 */
 			mm->context.sparc64_ctx_val = ctx;
-			on_each_cpu(context_reload, mm, 0);
+			need_context_reload = true;
 		}
-		spin_unlock(&ctx_alloc_lock);
+		spin_unlock_irq(&ctx_alloc_lock);
+
+		if (need_context_reload)
+			on_each_cpu(context_reload, mm, 0);
 	}
 }
 #endif
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@ -67,7 +67,7 @@ void arch_leave_lazy_mmu_mode(void)
 }

 static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr,
-			      bool exec)
+			      bool exec, bool huge)
 {
 	struct tlb_batch *tb = &get_cpu_var(tlb_batch);
 	unsigned long nr;
@ -84,13 +84,21 @@ static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr,
 	}

 	if (!tb->active) {
-		flush_tsb_user_page(mm, vaddr);
+		flush_tsb_user_page(mm, vaddr, huge);
 		global_flush_tlb_page(mm, vaddr);
 		goto out;
 	}

-	if (nr == 0)
+	if (nr == 0) {
 		tb->mm = mm;
+		tb->huge = huge;
+	}
+
+	if (tb->huge != huge) {
+		flush_tlb_pending();
+		tb->huge = huge;
+		nr = 0;
+	}

 	tb->vaddrs[nr] = vaddr;
 	tb->tlb_nr = ++nr;
@ -104,6 +112,8 @@ static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr,
 void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
 		   pte_t *ptep, pte_t orig, int fullmm)
 {
+	bool huge = is_hugetlb_pte(orig);
+
 	if (tlb_type != hypervisor &&
 	    pte_dirty(orig)) {
 		unsigned long paddr, pfn = pte_pfn(orig);
@ -129,7 +139,7 @@ void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,

 no_cache_flush:
 	if (!fullmm)
-		tlb_batch_add_one(mm, vaddr, pte_exec(orig));
+		tlb_batch_add_one(mm, vaddr, pte_exec(orig), huge);
 }

 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@ -145,7 +155,7 @@ static void tlb_batch_pmd_scan(struct mm_struct *mm, unsigned long vaddr,
 		if (pte_val(*pte) & _PAGE_VALID) {
 			bool exec = pte_exec(*pte);

-			tlb_batch_add_one(mm, vaddr, exec);
+			tlb_batch_add_one(mm, vaddr, exec, false);
 		}
 		pte++;
 		vaddr += PAGE_SIZE;
@ -185,8 +195,9 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 			pte_t orig_pte = __pte(pmd_val(orig));
 			bool exec = pte_exec(orig_pte);

-			tlb_batch_add_one(mm, addr, exec);
-			tlb_batch_add_one(mm, addr + REAL_HPAGE_SIZE, exec);
+			tlb_batch_add_one(mm, addr, exec, true);
+			tlb_batch_add_one(mm, addr + REAL_HPAGE_SIZE, exec,
+					true);
 		} else {
 			tlb_batch_pmd_scan(mm, addr, orig);
 		}
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@ -76,14 +76,15 @@ void flush_tsb_user(struct tlb_batch *tb)

 	spin_lock_irqsave(&mm->context.lock, flags);

-	base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb;
-	nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries;
-	if (tlb_type == cheetah_plus || tlb_type == hypervisor)
-		base = __pa(base);
-	__flush_tsb_one(tb, PAGE_SHIFT, base, nentries);
-
+	if (!tb->huge) {
+		base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb;
+		nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries;
+		if (tlb_type == cheetah_plus || tlb_type == hypervisor)
+			base = __pa(base);
+		__flush_tsb_one(tb, PAGE_SHIFT, base, nentries);
+	}
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-	if (mm->context.tsb_block[MM_TSB_HUGE].tsb) {
+	if (tb->huge && mm->context.tsb_block[MM_TSB_HUGE].tsb) {
 		base = (unsigned long) mm->context.tsb_block[MM_TSB_HUGE].tsb;
 		nentries = mm->context.tsb_block[MM_TSB_HUGE].tsb_nentries;
 		if (tlb_type == cheetah_plus || tlb_type == hypervisor)
@ -94,20 +95,21 @@ void flush_tsb_user(struct tlb_batch *tb)
 	spin_unlock_irqrestore(&mm->context.lock, flags);
 }

-void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr)
+void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr, bool huge)
 {
 	unsigned long nentries, base, flags;

 	spin_lock_irqsave(&mm->context.lock, flags);

-	base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb;
-	nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries;
-	if (tlb_type == cheetah_plus || tlb_type == hypervisor)
-		base = __pa(base);
-	__flush_tsb_one_entry(base, vaddr, PAGE_SHIFT, nentries);
-
+	if (!huge) {
+		base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb;
+		nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries;
+		if (tlb_type == cheetah_plus || tlb_type == hypervisor)
+			base = __pa(base);
+		__flush_tsb_one_entry(base, vaddr, PAGE_SHIFT, nentries);
+	}
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-	if (mm->context.tsb_block[MM_TSB_HUGE].tsb) {
+	if (huge && mm->context.tsb_block[MM_TSB_HUGE].tsb) {
 		base = (unsigned long) mm->context.tsb_block[MM_TSB_HUGE].tsb;
 		nentries = mm->context.tsb_block[MM_TSB_HUGE].tsb_nentries;
 		if (tlb_type == cheetah_plus || tlb_type == hypervisor)
--- a/arch/x86/kernel/cpu/perf_event_intel_pt.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_pt.c
@ -694,6 +694,7 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf,

 	/* clear STOP and INT from current entry */
 	buf->topa_index[buf->stop_pos]->stop = 0;
+	buf->topa_index[buf->stop_pos]->intr = 0;
 	buf->topa_index[buf->intr_pos]->intr = 0;

 	/* how many pages till the STOP marker */
@ -718,6 +719,7 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf,
 	buf->intr_pos = idx;

 	buf->topa_index[buf->stop_pos]->stop = 1;
+	buf->topa_index[buf->stop_pos]->intr = 1;
 	buf->topa_index[buf->intr_pos]->intr = 1;

 	return 0;
--- a/Show More
+++ b/Show More