Merge branch 'timers/core' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip into remove-local-timers

225 files changed, 4221 insertions, 1866 deletions

diff --git a/Documentation/devicetree/bindings/timer/lsi,zevio-timer.txt b/Documentation/devicetree/bindings/timer/lsi,zevio-timer.txt
new file mode 100644
index 000000000000..b2d07ad90e9a
--- /dev/null
+++ b/Documentation/devicetree/bindings/timer/lsi,zevio-timer.txt
@@ -0,0 +1,33 @@
+TI-NSPIRE timer
+
+Required properties:
+
+- compatible : should be "lsi,zevio-timer".
+- reg : The physical base address and size of the timer (always first).
+- clocks: phandle to the source clock.
+
+Optional properties:
+
+- interrupts : The interrupt number of the first timer.
+- reg : The interrupt acknowledgement registers
+	(always after timer base address)
+
+If any of the optional properties are not given, the timer is added as a
+clock-source only.
+
+Example:
+
+timer {
+	compatible = "lsi,zevio-timer";
+	reg = <0x900D0000 0x1000>, <0x900A0020 0x8>;
+	interrupts = <19>;
+	clocks = <&timer_clk>;
+};
+
+Example (no clock-events):
+
+timer {
+	compatible = "lsi,zevio-timer";
+	reg = <0x900D0000 0x1000>;
+	clocks = <&timer_clk>;
+};
diff --git a/Documentation/kernel-per-CPU-kthreads.txt b/Documentation/kernel-per-CPU-kthreads.txt
new file mode 100644
index 000000000000..cbf7ae412da4
--- /dev/null
+++ b/Documentation/kernel-per-CPU-kthreads.txt
@@ -0,0 +1,202 @@
+REDUCING OS JITTER DUE TO PER-CPU KTHREADS
+
+This document lists per-CPU kthreads in the Linux kernel and presents
+options to control their OS jitter.  Note that non-per-CPU kthreads are
+not listed here.  To reduce OS jitter from non-per-CPU kthreads, bind
+them to a "housekeeping" CPU dedicated to such work.
+
+
+REFERENCES
+
+o	Documentation/IRQ-affinity.txt:  Binding interrupts to sets of CPUs.
+
+o	Documentation/cgroups:  Using cgroups to bind tasks to sets of CPUs.
+
+o	man taskset:  Using the taskset command to bind tasks to sets
+	of CPUs.
+
+o	man sched_setaffinity:  Using the sched_setaffinity() system
+	call to bind tasks to sets of CPUs.
+
+o	/sys/devices/system/cpu/cpuN/online:  Control CPU N's hotplug state,
+	writing "0" to offline and "1" to online.
+
+o	In order to locate kernel-generated OS jitter on CPU N:
+
+		cd /sys/kernel/debug/tracing
+		echo 1 > max_graph_depth # Increase the "1" for more detail
+		echo function_graph > current_tracer
+		# run workload
+		cat per_cpu/cpuN/trace
+
+
+KTHREADS
+
+Name: ehca_comp/%u
+Purpose: Periodically process Infiniband-related work.
+To reduce its OS jitter, do any of the following:
+1.	Don't use eHCA Infiniband hardware, instead choosing hardware
+	that does not require per-CPU kthreads.  This will prevent these
+	kthreads from being created in the first place.  (This will
+	work for most people, as this hardware, though important, is
+	relatively old and is produced in relatively low unit volumes.)
+2.	Do all eHCA-Infiniband-related work on other CPUs, including
+	interrupts.
+3.	Rework the eHCA driver so that its per-CPU kthreads are
+	provisioned only on selected CPUs.
+
+
+Name: irq/%d-%s
+Purpose: Handle threaded interrupts.
+To reduce its OS jitter, do the following:
+1.	Use irq affinity to force the irq threads to execute on
+	some other CPU.
+
+Name: kcmtpd_ctr_%d
+Purpose: Handle Bluetooth work.
+To reduce its OS jitter, do one of the following:
+1.	Don't use Bluetooth, in which case these kthreads won't be
+	created in the first place.
+2.	Use irq affinity to force Bluetooth-related interrupts to
+	occur on some other CPU and furthermore initiate all
+	Bluetooth activity on some other CPU.
+
+Name: ksoftirqd/%u
+Purpose: Execute softirq handlers when threaded or when under heavy load.
+To reduce its OS jitter, each softirq vector must be handled
+separately as follows:
+TIMER_SOFTIRQ:  Do all of the following:
+1.	To the extent possible, keep the CPU out of the kernel when it
+	is non-idle, for example, by avoiding system calls and by forcing
+	both kernel threads and interrupts to execute elsewhere.
+2.	Build with CONFIG_HOTPLUG_CPU=y.  After boot completes, force
+	the CPU offline, then bring it back online.  This forces
+	recurring timers to migrate elsewhere.	If you are concerned
+	with multiple CPUs, force them all offline before bringing the
+	first one back online.  Once you have onlined the CPUs in question,
+	do not offline any other CPUs, because doing so could force the
+	timer back onto one of the CPUs in question.
+NET_TX_SOFTIRQ and NET_RX_SOFTIRQ:  Do all of the following:
+1.	Force networking interrupts onto other CPUs.
+2.	Initiate any network I/O on other CPUs.
+3.	Once your application has started, prevent CPU-hotplug operations
+	from being initiated from tasks that might run on the CPU to
+	be de-jittered.  (It is OK to force this CPU offline and then
+	bring it back online before you start your application.)
+BLOCK_SOFTIRQ:  Do all of the following:
+1.	Force block-device interrupts onto some other CPU.
+2.	Initiate any block I/O on other CPUs.
+3.	Once your application has started, prevent CPU-hotplug operations
+	from being initiated from tasks that might run on the CPU to
+	be de-jittered.  (It is OK to force this CPU offline and then
+	bring it back online before you start your application.)
+BLOCK_IOPOLL_SOFTIRQ:  Do all of the following:
+1.	Force block-device interrupts onto some other CPU.
+2.	Initiate any block I/O and block-I/O polling on other CPUs.
+3.	Once your application has started, prevent CPU-hotplug operations
+	from being initiated from tasks that might run on the CPU to
+	be de-jittered.  (It is OK to force this CPU offline and then
+	bring it back online before you start your application.)
+TASKLET_SOFTIRQ: Do one or more of the following:
+1.	Avoid use of drivers that use tasklets.  (Such drivers will contain
+	calls to things like tasklet_schedule().)
+2.	Convert all drivers that you must use from tasklets to workqueues.
+3.	Force interrupts for drivers using tasklets onto other CPUs,
+	and also do I/O involving these drivers on other CPUs.
+SCHED_SOFTIRQ: Do all of the following:
+1.	Avoid sending scheduler IPIs to the CPU to be de-jittered,
+	for example, ensure that at most one runnable kthread is present
+	on that CPU.  If a thread that expects to run on the de-jittered
+	CPU awakens, the scheduler will send an IPI that can result in
+	a subsequent SCHED_SOFTIRQ.
+2.	Build with CONFIG_RCU_NOCB_CPU=y, CONFIG_RCU_NOCB_CPU_ALL=y,
+	CONFIG_NO_HZ_FULL=y, and, in addition, ensure that the CPU
+	to be de-jittered is marked as an adaptive-ticks CPU using the
+	"nohz_full=" boot parameter.  This reduces the number of
+	scheduler-clock interrupts that the de-jittered CPU receives,
+	minimizing its chances of being selected to do the load balancing
+	work that runs in SCHED_SOFTIRQ context.
+3.	To the extent possible, keep the CPU out of the kernel when it
+	is non-idle, for example, by avoiding system calls and by
+	forcing both kernel threads and interrupts to execute elsewhere.
+	This further reduces the number of scheduler-clock interrupts
+	received by the de-jittered CPU.
+HRTIMER_SOFTIRQ:  Do all of the following:
+1.	To the extent possible, keep the CPU out of the kernel when it
+	is non-idle.  For example, avoid system calls and force both
+	kernel threads and interrupts to execute elsewhere.
+2.	Build with CONFIG_HOTPLUG_CPU=y.  Once boot completes, force the
+	CPU offline, then bring it back online.  This forces recurring
+	timers to migrate elsewhere.  If you are concerned with multiple
+	CPUs, force them all offline before bringing the first one
+	back online.  Once you have onlined the CPUs in question, do not
+	offline any other CPUs, because doing so could force the timer
+	back onto one of the CPUs in question.
+RCU_SOFTIRQ:  Do at least one of the following:
+1.	Offload callbacks and keep the CPU in either dyntick-idle or
+	adaptive-ticks state by doing all of the following:
+	a.	Build with CONFIG_RCU_NOCB_CPU=y, CONFIG_RCU_NOCB_CPU_ALL=y,
+		CONFIG_NO_HZ_FULL=y, and, in addition ensure that the CPU
+		to be de-jittered is marked as an adaptive-ticks CPU using
+		the "nohz_full=" boot parameter.  Bind the rcuo kthreads
+		to housekeeping CPUs, which can tolerate OS jitter.
+	b.	To the extent possible, keep the CPU out of the kernel
+		when it is non-idle, for example, by avoiding system
+		calls and by forcing both kernel threads and interrupts
+		to execute elsewhere.
+2.	Enable RCU to do its processing remotely via dyntick-idle by
+	doing all of the following:
+	a.	Build with CONFIG_NO_HZ=y and CONFIG_RCU_FAST_NO_HZ=y.
+	b.	Ensure that the CPU goes idle frequently, allowing other
+		CPUs to detect that it has passed through an RCU quiescent
+		state.	If the kernel is built with CONFIG_NO_HZ_FULL=y,
+		userspace execution also allows other CPUs to detect that
+		the CPU in question has passed through a quiescent state.
+	c.	To the extent possible, keep the CPU out of the kernel
+		when it is non-idle, for example, by avoiding system
+		calls and by forcing both kernel threads and interrupts
+		to execute elsewhere.
+
+Name: rcuc/%u
+Purpose: Execute RCU callbacks in CONFIG_RCU_BOOST=y kernels.
+To reduce its OS jitter, do at least one of the following:
+1.	Build the kernel with CONFIG_PREEMPT=n.  This prevents these
+	kthreads from being created in the first place, and also obviates
+	the need for RCU priority boosting.  This approach is feasible
+	for workloads that do not require high degrees of responsiveness.
+2.	Build the kernel with CONFIG_RCU_BOOST=n.  This prevents these
+	kthreads from being created in the first place.  This approach
+	is feasible only if your workload never requires RCU priority
+	boosting, for example, if you ensure frequent idle time on all
+	CPUs that might execute within the kernel.
+3.	Build with CONFIG_RCU_NOCB_CPU=y and CONFIG_RCU_NOCB_CPU_ALL=y,
+	which offloads all RCU callbacks to kthreads that can be moved
+	off of CPUs susceptible to OS jitter.  This approach prevents the
+	rcuc/%u kthreads from having any work to do, so that they are
+	never awakened.
+4.	Ensure that the CPU never enters the kernel, and, in particular,
+	avoid initiating any CPU hotplug operations on this CPU.  This is
+	another way of preventing any callbacks from being queued on the
+	CPU, again preventing the rcuc/%u kthreads from having any work
+	to do.
+
+Name: rcuob/%d, rcuop/%d, and rcuos/%d
+Purpose: Offload RCU callbacks from the corresponding CPU.
+To reduce its OS jitter, do at least one of the following:
+1.	Use affinity, cgroups, or other mechanism to force these kthreads
+	to execute on some other CPU.
+2.	Build with CONFIG_RCU_NOCB_CPUS=n, which will prevent these
+	kthreads from being created in the first place.  However, please
+	note that this will not eliminate OS jitter, but will instead
+	shift it to RCU_SOFTIRQ.
+
+Name: watchdog/%u
+Purpose: Detect software lockups on each CPU.
+To reduce its OS jitter, do at least one of the following:
+1.	Build with CONFIG_LOCKUP_DETECTOR=n, which will prevent these
+	kthreads from being created in the first place.
+2.	Echo a zero to /proc/sys/kernel/watchdog to disable the
+	watchdog timer.
+3.	Echo a large number of /proc/sys/kernel/watchdog_thresh in
+	order to reduce the frequency of OS jitter due to the watchdog
+	timer down to a level that is acceptable for your workload.
diff --git a/arch/Kconfig b/arch/Kconfig
index dd0e8eb8042f..a4429bcd609e 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -213,6 +213,9 @@ config USE_GENERIC_SMP_HELPERS
 config GENERIC_SMP_IDLE_THREAD
        bool
 
+config GENERIC_IDLE_POLL_SETUP
+       bool
+
 # Select if arch init_task initializer is different to init/init_task.c
 config ARCH_INIT_TASK
        bool
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index d423d58f938d..53d3a356f61f 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -14,6 +14,7 @@ config ARM
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
 	select GENERIC_PCI_IOMAP
+	select GENERIC_SCHED_CLOCK
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_IDLE_POLL_SETUP
 	select GENERIC_STRNCPY_FROM_USER
@@ -38,6 +39,7 @@ config ARM
 	select HAVE_GENERIC_HARDIRQS
 	select HAVE_HW_BREAKPOINT if (PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7))
 	select HAVE_IDE if PCI || ISA || PCMCIA
+	select HAVE_IRQ_TIME_ACCOUNTING
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZMA
 	select HAVE_KERNEL_LZO
@@ -488,7 +490,7 @@ config ARCH_IXP4XX
 config ARCH_DOVE
 	bool "Marvell Dove"
 	select ARCH_REQUIRE_GPIOLIB
-	select CPU_V7
+	select CPU_PJ4
 	select GENERIC_CLOCKEVENTS
 	select MIGHT_HAVE_PCI
 	select PINCTRL
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 47374085befd..1ba358ba16b8 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -309,7 +309,7 @@ define archhelp
   echo  '  Image         - Uncompressed kernel image (arch/$(ARCH)/boot/Image)'
   echo  '* xipImage      - XIP kernel image, if configured (arch/$(ARCH)/boot/xipImage)'
   echo  '  uImage        - U-Boot wrapped zImage'
-  echo  '  bootpImage    - Combined zImage and initial RAM disk' 
+  echo  '  bootpImage    - Combined zImage and initial RAM disk'
   echo  '                  (supply initrd image via make variable INITRD=<path>)'
   echo  '* dtbs          - Build device tree blobs for enabled boards'
   echo  '  install       - Install uncompressed kernel'
diff --git a/arch/arm/common/mcpm_platsmp.c b/arch/arm/common/mcpm_platsmp.c
index 52b88d81b7bb..3caed0db6986 100644
--- a/arch/arm/common/mcpm_platsmp.c
+++ b/arch/arm/common/mcpm_platsmp.c
@@ -15,8 +15,6 @@
 #include <linux/smp.h>
 #include <linux/spinlock.h>
 
-#include <linux/irqchip/arm-gic.h>
-
 #include <asm/mcpm.h>
 #include <asm/smp.h>
 #include <asm/smp_plat.h>
@@ -49,7 +47,6 @@ static int __cpuinit mcpm_boot_secondary(unsigned int cpu, struct task_struct *i
 static void __cpuinit mcpm_secondary_init(unsigned int cpu)
 {
 	mcpm_cpu_powered_up();
-	gic_secondary_init(0);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/arm/common/timer-sp.c b/arch/arm/common/timer-sp.c
index ddc740769601..023ee63827a2 100644
--- a/arch/arm/common/timer-sp.c
+++ b/arch/arm/common/timer-sp.c
@@ -28,8 +28,8 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
+#include <linux/sched_clock.h>
 
-#include <asm/sched_clock.h>
 #include <asm/hardware/arm_timer.h>
 #include <asm/hardware/timer-sp.h>
 
diff --git a/arch/arm/include/asm/cmpxchg.h b/arch/arm/include/asm/cmpxchg.h
index 7eb18c1d8d6c..4f009c10540d 100644
--- a/arch/arm/include/asm/cmpxchg.h
+++ b/arch/arm/include/asm/cmpxchg.h
@@ -233,15 +233,15 @@ static inline unsigned long __cmpxchg_local(volatile void *ptr,
 	((__typeof__(*(ptr)))atomic64_cmpxchg(container_of((ptr),	\
 						atomic64_t,		\
 						counter),		\
-					      (unsigned long)(o),	\
-					      (unsigned long)(n)))
+					      (unsigned long long)(o),	\
+					      (unsigned long long)(n)))
 
 #define cmpxchg64_local(ptr, o, n)					\
 	((__typeof__(*(ptr)))local64_cmpxchg(container_of((ptr),	\
 						local64_t,		\
 						a),			\
-					     (unsigned long)(o),	\
-					     (unsigned long)(n)))
+					     (unsigned long long)(o),	\
+					     (unsigned long long)(n)))
 
 #endif	/* __LINUX_ARM_ARCH__ >= 6 */
 
diff --git a/arch/arm/include/asm/sched_clock.h b/arch/arm/include/asm/sched_clock.h
index 3d520ddca61b..2389b71a8e7c 100644
--- a/arch/arm/include/asm/sched_clock.h
+++ b/arch/arm/include/asm/sched_clock.h
@@ -1,16 +1,4 @@
-/*
- * sched_clock.h: support for extending counters to full 64-bit ns counter
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
+/* You shouldn't include this file. Use linux/sched_clock.h instead.
+ * Temporary file until all asm/sched_clock.h users are gone
  */
-#ifndef ASM_SCHED_CLOCK
-#define ASM_SCHED_CLOCK
-
-extern void sched_clock_postinit(void);
-extern void setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate);
-
-extern unsigned long long (*sched_clock_func)(void);
-
-#endif
+#include <linux/sched_clock.h>
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 5f3338eacad2..97cb0576d07c 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -16,7 +16,7 @@ CFLAGS_REMOVE_return_address.o = -pg
 # Object file lists.
 
 obj-y		:= elf.o entry-armv.o entry-common.o irq.o opcodes.o \
-		   process.o ptrace.o return_address.o sched_clock.o \
+		   process.o ptrace.o return_address.o \
 		   setup.o signal.o stacktrace.o sys_arm.o time.o traps.o
 
 obj-$(CONFIG_ATAGS)		+= atags_parse.o
diff --git a/arch/arm/kernel/arch_timer.c b/arch/arm/kernel/arch_timer.c
index 59dcdced6e30..221f07b11ccb 100644
--- a/arch/arm/kernel/arch_timer.c
+++ b/arch/arm/kernel/arch_timer.c
@@ -11,9 +11,9 @@
 #include <linux/init.h>
 #include <linux/types.h>
 #include <linux/errno.h>
+#include <linux/sched_clock.h>
 
 #include <asm/delay.h>
-#include <asm/sched_clock.h>
 
 #include <clocksource/arm_arch_timer.h>
 
diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c
index abff4e9aaee0..98aee3258398 100644
--- a/arch/arm/kernel/time.c
+++ b/arch/arm/kernel/time.c
@@ -24,9 +24,9 @@
 #include <linux/timer.h>
 #include <linux/clocksource.h>
 #include <linux/irq.h>
+#include <linux/sched_clock.h>
 
 #include <asm/thread_info.h>
-#include <asm/sched_clock.h>
 #include <asm/stacktrace.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/time.h>
@@ -120,6 +120,4 @@ void __init time_init(void)
 		machine_desc->init_time();
 	else
 		clocksource_of_init();
-
-	sched_clock_postinit();
 }
diff --git a/arch/arm/mach-davinci/time.c b/arch/arm/mach-davinci/time.c
index bad361ec1666..7a55b5c95971 100644
--- a/arch/arm/mach-davinci/time.c
+++ b/arch/arm/mach-davinci/time.c
@@ -18,8 +18,8 @@
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/platform_device.h>
+#include <linux/sched_clock.h>
 
-#include <asm/sched_clock.h>
 #include <asm/mach/irq.h>
 #include <asm/mach/time.h>
 
diff --git a/arch/arm/mach-imx/time.c b/arch/arm/mach-imx/time.c
index fea91313678b..cd46529e9eaa 100644
--- a/arch/arm/mach-imx/time.c
+++ b/arch/arm/mach-imx/time.c
@@ -26,8 +26,8 @@
 #include <linux/clockchips.h>
 #include <linux/clk.h>
 #include <linux/err.h>
+#include <linux/sched_clock.h>
 
-#include <asm/sched_clock.h>
 #include <asm/mach/time.h>
 
 #include "common.h"
diff --git a/arch/arm/mach-integrator/integrator_ap.c b/arch/arm/mach-integrator/integrator_ap.c
index b23c8e4f28e8..aa4346227c41 100644
--- a/arch/arm/mach-integrator/integrator_ap.c
+++ b/arch/arm/mach-integrator/integrator_ap.c
@@ -41,6 +41,7 @@
 #include <linux/stat.h>
 #include <linux/sys_soc.h>
 #include <linux/termios.h>
+#include <linux/sched_clock.h>
 #include <video/vga.h>
 
 #include <mach/hardware.h>
@@ -49,7 +50,6 @@
 #include <asm/setup.h>
 #include <asm/param.h>		/* HZ */
 #include <asm/mach-types.h>
-#include <asm/sched_clock.h>
 
 #include <mach/lm.h>
 #include <mach/irqs.h>
diff --git a/arch/arm/mach-ixp4xx/common.c b/arch/arm/mach-ixp4xx/common.c
index 6600cff6bd92..58307cff1f18 100644
--- a/arch/arm/mach-ixp4xx/common.c
+++ b/arch/arm/mach-ixp4xx/common.c
@@ -30,6 +30,7 @@
 #include <linux/export.h>
 #include <linux/gpio.h>
 #include <linux/cpu.h>
+#include <linux/sched_clock.h>
 
 #include <mach/udc.h>
 #include <mach/hardware.h>
@@ -38,7 +39,6 @@
 #include <asm/pgtable.h>
 #include <asm/page.h>
 #include <asm/irq.h>
-#include <asm/sched_clock.h>
 #include <asm/system_misc.h>
 
 #include <asm/mach/map.h>
diff --git a/arch/arm/mach-mmp/time.c b/arch/arm/mach-mmp/time.c
index 86a18b3d252e..7ac41e83cfef 100644
--- a/arch/arm/mach-mmp/time.c
+++ b/arch/arm/mach-mmp/time.c
@@ -28,8 +28,8 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
+#include <linux/sched_clock.h>
 
-#include <asm/sched_clock.h>
 #include <mach/addr-map.h>
 #include <mach/regs-timers.h>
 #include <mach/regs-apbc.h>
diff --git a/arch/arm/mach-msm/timer.c b/arch/arm/mach-msm/timer.c
index 284313f3e02c..b6418fd5fe0d 100644
--- a/arch/arm/mach-msm/timer.c
+++ b/arch/arm/mach-msm/timer.c
@@ -23,10 +23,10 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
+#include <linux/sched_clock.h>
 
 #include <asm/mach/time.h>
 #include <asm/localtimer.h>
-#include <asm/sched_clock.h>
 
 #include "common.h"
 
diff --git a/arch/arm/mach-omap1/time.c b/arch/arm/mach-omap1/time.c
index 726ec23d29c7..80603d2fef77 100644
--- a/arch/arm/mach-omap1/time.c
+++ b/arch/arm/mach-omap1/time.c
@@ -43,9 +43,9 @@
 #include <linux/clocksource.h>
 #include <linux/clockchips.h>
 #include <linux/io.h>
+#include <linux/sched_clock.h>
 
 #include <asm/irq.h>
-#include <asm/sched_clock.h>
 
 #include <mach/hardware.h>
 #include <asm/mach/irq.h>
diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c
index f8b23b8040d9..4c069b0cab21 100644
--- a/arch/arm/mach-omap2/timer.c
+++ b/arch/arm/mach-omap2/timer.c
@@ -41,10 +41,10 @@
 #include <linux/of_irq.h>
 #include <linux/platform_device.h>
 #include <linux/platform_data/dmtimer-omap.h>
+#include <linux/sched_clock.h>
 
 #include <asm/mach/time.h>
 #include <asm/smp_twd.h>
-#include <asm/sched_clock.h>
 
 #include "omap_hwmod.h"
 #include "omap_device.h"
diff --git a/arch/arm/mach-pxa/time.c b/arch/arm/mach-pxa/time.c
index 8f1ee92aea30..9aa852a8fab9 100644
--- a/arch/arm/mach-pxa/time.c
+++ b/arch/arm/mach-pxa/time.c
@@ -16,11 +16,11 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/clockchips.h>
+#include <linux/sched_clock.h>
 
 #include <asm/div64.h>
 #include <asm/mach/irq.h>
 #include <asm/mach/time.h>
-#include <asm/sched_clock.h>
 #include <mach/regs-ost.h>
 #include <mach/irqs.h>
 
diff --git a/arch/arm/mach-sa1100/time.c b/arch/arm/mach-sa1100/time.c
index a59a13a665a6..713c86cd3d64 100644
--- a/arch/arm/mach-sa1100/time.c
+++ b/arch/arm/mach-sa1100/time.c
@@ -14,9 +14,9 @@
 #include <linux/irq.h>
 #include <linux/timex.h>
 #include <linux/clockchips.h>
+#include <linux/sched_clock.h>
 
 #include <asm/mach/time.h>
-#include <asm/sched_clock.h>
 #include <mach/hardware.h>
 #include <mach/irqs.h>
 
diff --git a/arch/arm/mach-u300/timer.c b/arch/arm/mach-u300/timer.c
index d9e73209c9b8..af771b76fe1c 100644
--- a/arch/arm/mach-u300/timer.c
+++ b/arch/arm/mach-u300/timer.c
@@ -18,12 +18,12 @@
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/irq.h>
+#include <linux/sched_clock.h>
 
 #include <mach/hardware.h>
 #include <mach/irqs.h>
 
 /* Generic stuff */
-#include <asm/sched_clock.h>
 #include <asm/mach/map.h>
 #include <asm/mach/time.h>
 
diff --git a/arch/arm/plat-iop/time.c b/arch/arm/plat-iop/time.c
index 837a2d52e9db..29606bd75f3f 100644
--- a/arch/arm/plat-iop/time.c
+++ b/arch/arm/plat-iop/time.c
@@ -22,9 +22,9 @@
 #include <linux/clocksource.h>
 #include <linux/clockchips.h>
 #include <linux/export.h>
+#include <linux/sched_clock.h>
 #include <mach/hardware.h>
 #include <asm/irq.h>
-#include <asm/sched_clock.h>
 #include <asm/uaccess.h>
 #include <asm/mach/irq.h>
 #include <asm/mach/time.h>
diff --git a/arch/arm/plat-omap/counter_32k.c b/arch/arm/plat-omap/counter_32k.c
index 5b0b86bb34bb..d9bc98eb2a6b 100644
--- a/arch/arm/plat-omap/counter_32k.c
+++ b/arch/arm/plat-omap/counter_32k.c
@@ -18,9 +18,9 @@
 #include <linux/err.h>
 #include <linux/io.h>
 #include <linux/clocksource.h>
+#include <linux/sched_clock.h>
 
 #include <asm/mach/time.h>
-#include <asm/sched_clock.h>
 
 #include <plat/counter-32k.h>
 
diff --git a/arch/arm/plat-orion/time.c b/arch/arm/plat-orion/time.c
index 5d5ac0f05422..9d2b2ac74938 100644
--- a/arch/arm/plat-orion/time.c
+++ b/arch/arm/plat-orion/time.c
@@ -16,7 +16,7 @@
 #include <linux/clockchips.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
-#include <asm/sched_clock.h>
+#include <linux/sched_clock.h>
 
 /*
  * MBus bridge block registers.
diff --git a/arch/arm/plat-samsung/samsung-time.c b/arch/arm/plat-samsung/samsung-time.c
index f899cbc9b288..2957075ca836 100644
--- a/arch/arm/plat-samsung/samsung-time.c
+++ b/arch/arm/plat-samsung/samsung-time.c
@@ -15,12 +15,12 @@
 #include <linux/clk.h>
 #include <linux/clockchips.h>
 #include <linux/platform_device.h>
+#include <linux/sched_clock.h>
 
 #include <asm/smp_twd.h>
 #include <asm/mach/time.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
-#include <asm/sched_clock.h>
 
 #include <mach/map.h>
 #include <plat/devs.h>
diff --git a/arch/arm/plat-versatile/sched-clock.c b/arch/arm/plat-versatile/sched-clock.c
index b33b74c87232..51b109e3b6c3 100644
--- a/arch/arm/plat-versatile/sched-clock.c
+++ b/arch/arm/plat-versatile/sched-clock.c
@@ -20,8 +20,8 @@
  */
 #include <linux/kernel.h>
 #include <linux/io.h>
+#include <linux/sched_clock.h>
 
-#include <asm/sched_clock.h>
 #include <plat/sched_clock.h>
 
 static void __iomem *ctr;
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index d30042e39974..13609e01f4b7 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -152,11 +152,12 @@ int xen_unmap_domain_mfn_range(struct vm_area_struct *vma,
 }
 EXPORT_SYMBOL_GPL(xen_unmap_domain_mfn_range);
 
-static int __init xen_secondary_init(unsigned int cpu)
+static void __init xen_percpu_init(void *unused)
 {
 	struct vcpu_register_vcpu_info info;
 	struct vcpu_info *vcpup;
 	int err;
+	int cpu = get_cpu();
 
 	pr_info("Xen: initializing cpu%d\n", cpu);
 	vcpup = per_cpu_ptr(xen_vcpu_info, cpu);
@@ -165,14 +166,10 @@ static int __init xen_secondary_init(unsigned int cpu)
 	info.offset = offset_in_page(vcpup);
 
 	err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, cpu, &info);
-	if (err) {
-		pr_debug("register_vcpu_info failed: err=%d\n", err);
-	} else {
-		/* This cpu is using the registered vcpu info, even if
-		   later ones fail to. */
-		per_cpu(xen_vcpu, cpu) = vcpup;
-	}
-	return 0;
+	BUG_ON(err);
+	per_cpu(xen_vcpu, cpu) = vcpup;
+
+	enable_percpu_irq(xen_events_irq, 0);
 }
 
 static void xen_restart(char str, const char *cmd)
@@ -208,7 +205,6 @@ static int __init xen_guest_init(void)
 	const char *version = NULL;
 	const char *xen_prefix = "xen,xen-";
 	struct resource res;
-	int i;
 
 	node = of_find_compatible_node(NULL, NULL, "xen,xen");
 	if (!node) {
@@ -265,19 +261,23 @@ static int __init xen_guest_init(void)
 			                       sizeof(struct vcpu_info));
 	if (xen_vcpu_info == NULL)
 		return -ENOMEM;
-	for_each_online_cpu(i)
-		xen_secondary_init(i);
 
 	gnttab_init();
 	if (!xen_initial_domain())
 		xenbus_probe(NULL);
 
+	return 0;
+}
+core_initcall(xen_guest_init);
+
+static int __init xen_pm_init(void)
+{
 	pm_power_off = xen_power_off;
 	arm_pm_restart = xen_restart;
 
 	return 0;
 }
-core_initcall(xen_guest_init);
+subsys_initcall(xen_pm_init);
 
 static irqreturn_t xen_arm_callback(int irq, void *arg)
 {
@@ -285,11 +285,6 @@ static irqreturn_t xen_arm_callback(int irq, void *arg)
 	return IRQ_HANDLED;
 }
 
-static __init void xen_percpu_enable_events(void *unused)
-{
-	enable_percpu_irq(xen_events_irq, 0);
-}
-
 static int __init xen_init_events(void)
 {
 	if (!xen_domain() || xen_events_irq < 0)
@@ -303,7 +298,7 @@ static int __init xen_init_events(void)
 		return -EINVAL;
 	}
 
-	on_each_cpu(xen_percpu_enable_events, NULL, 0);
+	on_each_cpu(xen_percpu_init, NULL, 0);
 
 	return 0;
 }
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index cad060f288cf..6507dabdd5dd 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -245,7 +245,7 @@ config SMP
 
 config IRQSTACKS
 	bool "Use separate kernel stacks when processing interrupts"
-	default n
+	default y
 	help
 	  If you say Y here the kernel will use separate kernel stacks
 	  for handling hard and soft interrupts.  This can help avoid
diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile
index 2f967cc6649e..197690068f88 100644
--- a/arch/parisc/Makefile
+++ b/arch/parisc/Makefile
@@ -23,24 +23,21 @@ NM		= sh $(srctree)/arch/parisc/nm
 CHECKFLAGS	+= -D__hppa__=1
 LIBGCC		= $(shell $(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name)
 
-MACHINE		:= $(shell uname -m)
-NATIVE		:= $(if $(filter parisc%,$(MACHINE)),1,0)
-
 ifdef CONFIG_64BIT
 UTS_MACHINE	:= parisc64
 CHECKFLAGS	+= -D__LP64__=1 -m64
-WIDTH		:= 64
+CC_ARCHES	= hppa64
 else # 32-bit
-WIDTH		:=
+CC_ARCHES	= hppa hppa2.0 hppa1.1
 endif
 
-# attempt to help out folks who are cross-compiling
-ifeq ($(NATIVE),1)
-CROSS_COMPILE	:= hppa$(WIDTH)-linux-
-else
- ifeq ($(CROSS_COMPILE),)
- CROSS_COMPILE	:= hppa$(WIDTH)-linux-gnu-
- endif
+ifneq ($(SUBARCH),$(UTS_MACHINE))
+	ifeq ($(CROSS_COMPILE),)
+		CC_SUFFIXES = linux linux-gnu unknown-linux-gnu
+		CROSS_COMPILE := $(call cc-cross-prefix, \
+			$(foreach a,$(CC_ARCHES), \
+			$(foreach s,$(CC_SUFFIXES),$(a)-$(s)-)))
+	endif
 endif
 
 OBJCOPY_FLAGS =-O binary -R .note -R .comment -S
diff --git a/arch/parisc/include/asm/hardirq.h b/arch/parisc/include/asm/hardirq.h
index 12373c4dabab..c19f7138ba48 100644
--- a/arch/parisc/include/asm/hardirq.h
+++ b/arch/parisc/include/asm/hardirq.h
@@ -11,10 +11,18 @@
 #include <linux/threads.h>
 #include <linux/irq.h>
 
+#ifdef CONFIG_IRQSTACKS
+#define __ARCH_HAS_DO_SOFTIRQ
+#endif
+
 typedef struct {
 	unsigned int __softirq_pending;
 #ifdef CONFIG_DEBUG_STACKOVERFLOW
 	unsigned int kernel_stack_usage;
+#ifdef CONFIG_IRQSTACKS
+	unsigned int irq_stack_usage;
+	unsigned int irq_stack_counter;
+#endif
 #endif
 #ifdef CONFIG_SMP
 	unsigned int irq_resched_count;
@@ -28,6 +36,7 @@ DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
 #define __ARCH_IRQ_STAT
 #define __IRQ_STAT(cpu, member) (irq_stat[cpu].member)
 #define inc_irq_stat(member)	this_cpu_inc(irq_stat.member)
+#define __inc_irq_stat(member)	__this_cpu_inc(irq_stat.member)
 #define local_softirq_pending()	this_cpu_read(irq_stat.__softirq_pending)
 
 #define __ARCH_SET_SOFTIRQ_PENDING
diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h
index 064015547d1e..cfbc43929cf6 100644
--- a/arch/parisc/include/asm/processor.h
+++ b/arch/parisc/include/asm/processor.h
@@ -63,10 +63,13 @@
  */
 #ifdef __KERNEL__
 
+#include <linux/spinlock_types.h>
+
 #define IRQ_STACK_SIZE      (4096 << 2) /* 16k irq stack size */
 
 union irq_stack_union {
 	unsigned long stack[IRQ_STACK_SIZE/sizeof(unsigned long)];
+	raw_spinlock_t lock;
 };
 
 DECLARE_PER_CPU(union irq_stack_union, irq_stack_union);
diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S
index 4bb96ad9b0b1..ae27cb6ce19a 100644
--- a/arch/parisc/kernel/entry.S
+++ b/arch/parisc/kernel/entry.S
@@ -452,9 +452,41 @@
 	L2_ptep		\pgd,\pte,\index,\va,\fault
 	.endm
 
+	/* Acquire pa_dbit_lock lock. */
+	.macro		dbit_lock	spc,tmp,tmp1
+#ifdef CONFIG_SMP
+	cmpib,COND(=),n	0,\spc,2f
+	load32		PA(pa_dbit_lock),\tmp
+1:	LDCW		0(\tmp),\tmp1
+	cmpib,COND(=)	0,\tmp1,1b
+	nop
+2:
+#endif
+	.endm
+
+	/* Release pa_dbit_lock lock without reloading lock address. */
+	.macro		dbit_unlock0	spc,tmp
+#ifdef CONFIG_SMP
+	or,COND(=)	%r0,\spc,%r0
+	stw             \spc,0(\tmp)
+#endif
+	.endm
+
+	/* Release pa_dbit_lock lock. */
+	.macro		dbit_unlock1	spc,tmp
+#ifdef CONFIG_SMP
+	load32		PA(pa_dbit_lock),\tmp
+	dbit_unlock0	\spc,\tmp
+#endif
+	.endm
+
 	/* Set the _PAGE_ACCESSED bit of the PTE.  Be clever and
 	 * don't needlessly dirty the cache line if it was already set */
-	.macro		update_ptep	ptep,pte,tmp,tmp1
+	.macro		update_ptep	spc,ptep,pte,tmp,tmp1
+#ifdef CONFIG_SMP
+	or,COND(=)	%r0,\spc,%r0
+	LDREG		0(\ptep),\pte
+#endif
 	ldi		_PAGE_ACCESSED,\tmp1
 	or		\tmp1,\pte,\tmp
 	and,COND(<>)	\tmp1,\pte,%r0
@@ -463,7 +495,11 @@
 
 	/* Set the dirty bit (and accessed bit).  No need to be
 	 * clever, this is only used from the dirty fault */
-	.macro		update_dirty	ptep,pte,tmp
+	.macro		update_dirty	spc,ptep,pte,tmp
+#ifdef CONFIG_SMP
+	or,COND(=)	%r0,\spc,%r0
+	LDREG		0(\ptep),\pte
+#endif
 	ldi		_PAGE_ACCESSED|_PAGE_DIRTY,\tmp
 	or		\tmp,\pte,\pte
 	STREG		\pte,0(\ptep)
@@ -1111,11 +1147,13 @@ dtlb_miss_20w:
 
 	L3_ptep		ptp,pte,t0,va,dtlb_check_alias_20w
 
-	update_ptep	ptp,pte,t0,t1
+	dbit_lock	spc,t0,t1
+	update_ptep	spc,ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 	
 	idtlbt          pte,prot
+	dbit_unlock1	spc,t0
 
 	rfir
 	nop
@@ -1135,11 +1173,13 @@ nadtlb_miss_20w:
 
 	L3_ptep		ptp,pte,t0,va,nadtlb_check_alias_20w
 
-	update_ptep	ptp,pte,t0,t1
+	dbit_lock	spc,t0,t1
+	update_ptep	spc,ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
 	idtlbt          pte,prot
+	dbit_unlock1	spc,t0
 
 	rfir
 	nop
@@ -1161,7 +1201,8 @@ dtlb_miss_11:
 
 	L2_ptep		ptp,pte,t0,va,dtlb_check_alias_11
 
-	update_ptep	ptp,pte,t0,t1
+	dbit_lock	spc,t0,t1
+	update_ptep	spc,ptp,pte,t0,t1
 
 	make_insert_tlb_11	spc,pte,prot
 
@@ -1172,6 +1213,7 @@ dtlb_miss_11:
 	idtlbp		prot,(%sr1,va)
 
 	mtsp		t0, %sr1	/* Restore sr1 */
+	dbit_unlock1	spc,t0
 
 	rfir
 	nop
@@ -1192,7 +1234,8 @@ nadtlb_miss_11:
 
 	L2_ptep		ptp,pte,t0,va,nadtlb_check_alias_11
 
-	update_ptep	ptp,pte,t0,t1
+	dbit_lock	spc,t0,t1
+	update_ptep	spc,ptp,pte,t0,t1
 
 	make_insert_tlb_11	spc,pte,prot
 
@@ -1204,6 +1247,7 @@ nadtlb_miss_11:
 	idtlbp		prot,(%sr1,va)
 
 	mtsp		t0, %sr1	/* Restore sr1 */
+	dbit_unlock1	spc,t0
 
 	rfir
 	nop
@@ -1224,13 +1268,15 @@ dtlb_miss_20:
 
 	L2_ptep		ptp,pte,t0,va,dtlb_check_alias_20
 
-	update_ptep	ptp,pte,t0,t1
+	dbit_lock	spc,t0,t1
+	update_ptep	spc,ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
 	f_extend	pte,t0
 
 	idtlbt          pte,prot
+	dbit_unlock1	spc,t0
 
 	rfir
 	nop
@@ -1250,13 +1296,15 @@ nadtlb_miss_20:
 
 	L2_ptep		ptp,pte,t0,va,nadtlb_check_alias_20
 
-	update_ptep	ptp,pte,t0,t1
+	dbit_lock	spc,t0,t1
+	update_ptep	spc,ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
 	f_extend	pte,t0
 	
         idtlbt          pte,prot
+	dbit_unlock1	spc,t0
 
 	rfir
 	nop
@@ -1357,11 +1405,13 @@ itlb_miss_20w:
 
 	L3_ptep		ptp,pte,t0,va,itlb_fault
 
-	update_ptep	ptp,pte,t0,t1
+	dbit_lock	spc,t0,t1
+	update_ptep	spc,ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 	
 	iitlbt          pte,prot
+	dbit_unlock1	spc,t0
 
 	rfir
 	nop
@@ -1379,11 +1429,13 @@ naitlb_miss_20w:
 
 	L3_ptep		ptp,pte,t0,va,naitlb_check_alias_20w
 
-	update_ptep	ptp,pte,t0,t1
+	dbit_lock	spc,t0,t1
+	update_ptep	spc,ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
 	iitlbt          pte,prot
+	dbit_unlock1	spc,t0
 
 	rfir
 	nop
@@ -1405,7 +1457,8 @@ itlb_miss_11:
 
 	L2_ptep		ptp,pte,t0,va,itlb_fault
 
-	update_ptep	ptp,pte,t0,t1
+	dbit_lock	spc,t0,t1
+	update_ptep	spc,ptp,pte,t0,t1
 
 	make_insert_tlb_11	spc,pte,prot
 
@@ -1416,6 +1469,7 @@ itlb_miss_11:
 	iitlbp		prot,(%sr1,va)
 
 	mtsp		t0, %sr1	/* Restore sr1 */
+	dbit_unlock1	spc,t0
 
 	rfir
 	nop
@@ -1427,7 +1481,8 @@ naitlb_miss_11:
 
 	L2_ptep		ptp,pte,t0,va,naitlb_check_alias_11
 
-	update_ptep	ptp,pte,t0,t1
+	dbit_lock	spc,t0,t1
+	update_ptep	spc,ptp,pte,t0,t1
 
 	make_insert_tlb_11	spc,pte,prot
 
@@ -1438,6 +1493,7 @@ naitlb_miss_11:
 	iitlbp		prot,(%sr1,va)
 
 	mtsp		t0, %sr1	/* Restore sr1 */
+	dbit_unlock1	spc,t0
 
 	rfir
 	nop
@@ -1459,13 +1515,15 @@ itlb_miss_20:
 
 	L2_ptep		ptp,pte,t0,va,itlb_fault
 
-	update_ptep	ptp,pte,t0,t1
+	dbit_lock	spc,t0,t1
+	update_ptep	spc,ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
 	f_extend	pte,t0	
 
 	iitlbt          pte,prot
+	dbit_unlock1	spc,t0
 
 	rfir
 	nop
@@ -1477,13 +1535,15 @@ naitlb_miss_20:
 
 	L2_ptep		ptp,pte,t0,va,naitlb_check_alias_20
 
-	update_ptep	ptp,pte,t0,t1
+	dbit_lock	spc,t0,t1
+	update_ptep	spc,ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
 	f_extend	pte,t0
 
 	iitlbt          pte,prot
+	dbit_unlock1	spc,t0
 
 	rfir
 	nop
@@ -1507,29 +1567,13 @@ dbit_trap_20w:
 
 	L3_ptep		ptp,pte,t0,va,dbit_fault
 
-#ifdef CONFIG_SMP
-	cmpib,COND(=),n        0,spc,dbit_nolock_20w
-	load32		PA(pa_dbit_lock),t0
-
-dbit_spin_20w:
-	LDCW		0(t0),t1
-	cmpib,COND(=)         0,t1,dbit_spin_20w
-	nop
-
-dbit_nolock_20w:
-#endif
-	update_dirty	ptp,pte,t1
+	dbit_lock	spc,t0,t1
+	update_dirty	spc,ptp,pte,t1
 
 	make_insert_tlb	spc,pte,prot
 		
 	idtlbt          pte,prot
-#ifdef CONFIG_SMP
-	cmpib,COND(=),n        0,spc,dbit_nounlock_20w
-	ldi             1,t1
-	stw             t1,0(t0)
-
-dbit_nounlock_20w:
-#endif
+	dbit_unlock0	spc,t0
 
 	rfir
 	nop
@@ -1543,18 +1587,8 @@ dbit_trap_11:
 
 	L2_ptep		ptp,pte,t0,va,dbit_fault
 
-#ifdef CONFIG_SMP
-	cmpib,COND(=),n        0,spc,dbit_nolock_11
-	load32		PA(pa_dbit_lock),t0
-
-dbit_spin_11:
-	LDCW		0(t0),t1
-	cmpib,=         0,t1,dbit_spin_11
-	nop
-
-dbit_nolock_11:
-#endif
-	update_dirty	ptp,pte,t1
+	dbit_lock	spc,t0,t1
+	update_dirty	spc,ptp,pte,t1
 
 	make_insert_tlb_11	spc,pte,prot
 
@@ -1565,13 +1599,7 @@ dbit_nolock_11:
 	idtlbp		prot,(%sr1,va)
 
 	mtsp            t1, %sr1     /* Restore sr1 */
-#ifdef CONFIG_SMP
-	cmpib,COND(=),n        0,spc,dbit_nounlock_11
-	ldi             1,t1
-	stw             t1,0(t0)
-
-dbit_nounlock_11:
-#endif
+	dbit_unlock0	spc,t0
 
 	rfir
 	nop
@@ -1583,32 +1611,15 @@ dbit_trap_20:
 
 	L2_ptep		ptp,pte,t0,va,dbit_fault
 
-#ifdef CONFIG_SMP
-	cmpib,COND(=),n        0,spc,dbit_nolock_20
-	load32		PA(pa_dbit_lock),t0
-
-dbit_spin_20:
-	LDCW		0(t0),t1
-	cmpib,=         0,t1,dbit_spin_20
-	nop
-
-dbit_nolock_20:
-#endif
-	update_dirty	ptp,pte,t1
+	dbit_lock	spc,t0,t1
+	update_dirty	spc,ptp,pte,t1
 
 	make_insert_tlb	spc,pte,prot
 
 	f_extend	pte,t1
 	
         idtlbt          pte,prot
-
-#ifdef CONFIG_SMP
-	cmpib,COND(=),n        0,spc,dbit_nounlock_20
-	ldi             1,t1
-	stw             t1,0(t0)
-
-dbit_nounlock_20:
-#endif
+	dbit_unlock0	spc,t0
 
 	rfir
 	nop
diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c
index e255db0bb761..55237a70e197 100644
--- a/arch/parisc/kernel/irq.c
+++ b/arch/parisc/kernel/irq.c
@@ -166,22 +166,32 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 	seq_printf(p, "%*s: ", prec, "STK");
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", irq_stats(j)->kernel_stack_usage);
-	seq_printf(p, "  Kernel stack usage\n");
+	seq_puts(p, "  Kernel stack usage\n");
+# ifdef CONFIG_IRQSTACKS
+	seq_printf(p, "%*s: ", prec, "IST");
+	for_each_online_cpu(j)
+		seq_printf(p, "%10u ", irq_stats(j)->irq_stack_usage);
+	seq_puts(p, "  Interrupt stack usage\n");
+	seq_printf(p, "%*s: ", prec, "ISC");
+	for_each_online_cpu(j)
+		seq_printf(p, "%10u ", irq_stats(j)->irq_stack_counter);
+	seq_puts(p, "  Interrupt stack usage counter\n");
+# endif
 #endif
 #ifdef CONFIG_SMP
 	seq_printf(p, "%*s: ", prec, "RES");
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", irq_stats(j)->irq_resched_count);
-	seq_printf(p, "  Rescheduling interrupts\n");
+	seq_puts(p, "  Rescheduling interrupts\n");
 	seq_printf(p, "%*s: ", prec, "CAL");
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", irq_stats(j)->irq_call_count);
-	seq_printf(p, "  Function call interrupts\n");
+	seq_puts(p, "  Function call interrupts\n");
 #endif
 	seq_printf(p, "%*s: ", prec, "TLB");
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", irq_stats(j)->irq_tlb_count);
-	seq_printf(p, "  TLB shootdowns\n");
+	seq_puts(p, "  TLB shootdowns\n");
 	return 0;
 }
 
@@ -378,6 +388,7 @@ static inline void stack_overflow_check(struct pt_regs *regs)
 	unsigned long sp = regs->gr[30];
 	unsigned long stack_usage;
 	unsigned int *last_usage;
+	int cpu = smp_processor_id();
 
 	/* if sr7 != 0, we interrupted a userspace process which we do not want
 	 * to check for stack overflow. We will only check the kernel stack. */
@@ -386,7 +397,31 @@ static inline void stack_overflow_check(struct pt_regs *regs)
 
 	/* calculate kernel stack usage */
 	stack_usage = sp - stack_start;
-	last_usage = &per_cpu(irq_stat.kernel_stack_usage, smp_processor_id());
+#ifdef CONFIG_IRQSTACKS
+	if (likely(stack_usage <= THREAD_SIZE))
+		goto check_kernel_stack; /* found kernel stack */
+
+	/* check irq stack usage */
+	stack_start = (unsigned long) &per_cpu(irq_stack_union, cpu).stack;
+	stack_usage = sp - stack_start;
+
+	last_usage = &per_cpu(irq_stat.irq_stack_usage, cpu);
+	if (unlikely(stack_usage > *last_usage))
+		*last_usage = stack_usage;
+
+	if (likely(stack_usage < (IRQ_STACK_SIZE - STACK_MARGIN)))
+		return;
+
+	pr_emerg("stackcheck: %s will most likely overflow irq stack "
+		 "(sp:%lx, stk bottom-top:%lx-%lx)\n",
+		current->comm, sp, stack_start, stack_start + IRQ_STACK_SIZE);
+	goto panic_check;
+
+check_kernel_stack:
+#endif
+
+	/* check kernel stack usage */
+	last_usage = &per_cpu(irq_stat.kernel_stack_usage, cpu);
 
 	if (unlikely(stack_usage > *last_usage))
 		*last_usage = stack_usage;
@@ -398,31 +433,69 @@ static inline void stack_overflow_check(struct pt_regs *regs)
 		 "(sp:%lx, stk bottom-top:%lx-%lx)\n",
 		current->comm, sp, stack_start, stack_start + THREAD_SIZE);
 
+#ifdef CONFIG_IRQSTACKS
+panic_check:
+#endif
 	if (sysctl_panic_on_stackoverflow)
 		panic("low stack detected by irq handler - check messages\n");
 #endif
 }
 
 #ifdef CONFIG_IRQSTACKS
-DEFINE_PER_CPU(union irq_stack_union, irq_stack_union);
+DEFINE_PER_CPU(union irq_stack_union, irq_stack_union) = {
+		.lock = __RAW_SPIN_LOCK_UNLOCKED((irq_stack_union).lock)
+	};
 
 static void execute_on_irq_stack(void *func, unsigned long param1)
 {
-	unsigned long *irq_stack_start;
+	union irq_stack_union *union_ptr;
 	unsigned long irq_stack;
-	int cpu = smp_processor_id();
+	raw_spinlock_t *irq_stack_in_use;
 
-	irq_stack_start = &per_cpu(irq_stack_union, cpu).stack[0];
-	irq_stack = (unsigned long) irq_stack_start;
-	irq_stack = ALIGN(irq_stack, 16); /* align for stack frame usage */
+	union_ptr = &per_cpu(irq_stack_union, smp_processor_id());
+	irq_stack = (unsigned long) &union_ptr->stack;
+	irq_stack = ALIGN(irq_stack + sizeof(irq_stack_union.lock),
+			 64); /* align for stack frame usage */
 
-	BUG_ON(*irq_stack_start); /* report bug if we were called recursive. */
-	*irq_stack_start = 1;
+	/* We may be called recursive. If we are already using the irq stack,
+	 * just continue to use it. Use spinlocks to serialize
+	 * the irq stack usage.
+	 */
+	irq_stack_in_use = &union_ptr->lock;
+	if (!raw_spin_trylock(irq_stack_in_use)) {
+		void (*direct_call)(unsigned long p1) = func;
+
+		/* We are using the IRQ stack already.
+		 * Do direct call on current stack. */
+		direct_call(param1);
+		return;
+	}
 
 	/* This is where we switch to the IRQ stack. */
 	call_on_stack(param1, func, irq_stack);
 
-	*irq_stack_start = 0;
+	__inc_irq_stat(irq_stack_counter);
+
+	/* free up irq stack usage. */
+	do_raw_spin_unlock(irq_stack_in_use);
+}
+
+asmlinkage void do_softirq(void)
+{
+	__u32 pending;
+	unsigned long flags;
+
+	if (in_interrupt())
+		return;
+
+	local_irq_save(flags);
+
+	pending = local_softirq_pending();
+
+	if (pending)
+		execute_on_irq_stack(__do_softirq, 0);
+
+	local_irq_restore(flags);
 }
 #endif /* CONFIG_IRQSTACKS */
 
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index ce939ac8622b..1c965642068b 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -1069,7 +1069,7 @@ void flush_tlb_all(void)
 {
 	int do_recycle;
 
-	inc_irq_stat(irq_tlb_count);
+	__inc_irq_stat(irq_tlb_count);
 	do_recycle = 0;
 	spin_lock(&sid_lock);
 	if (dirty_space_ids > RECYCLE_THRESHOLD) {
@@ -1090,7 +1090,7 @@ void flush_tlb_all(void)
 #else
 void flush_tlb_all(void)
 {
-	inc_irq_stat(irq_tlb_count);
+	__inc_irq_stat(irq_tlb_count);
 	spin_lock(&sid_lock);
 	flush_tlb_all_local(NULL);
 	recycle_sids();
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index 5416e28a7538..863d877e0b5f 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -262,8 +262,31 @@ config PPC_EARLY_DEBUG_OPAL_HVSI
 	  Select this to enable early debugging for the PowerNV platform
 	  using an "hvsi" console
 
+config PPC_EARLY_DEBUG_MEMCONS
+	bool "In memory console"
+	help
+	  Select this to enable early debugging using an in memory console.
+	  This console provides input and output buffers stored within the
+	  kernel BSS and should be safe to select on any system. A debugger
+	  can then be used to read kernel output or send input to the console.
 endchoice
 
+config PPC_MEMCONS_OUTPUT_SIZE
+	int "In memory console output buffer size"
+	depends on PPC_EARLY_DEBUG_MEMCONS
+	default 4096
+	help
+	  Selects the size of the output buffer (in bytes) of the in memory
+	  console.
+
+config PPC_MEMCONS_INPUT_SIZE
+	int "In memory console input buffer size"
+	depends on PPC_EARLY_DEBUG_MEMCONS
+	default 128
+	help
+	  Selects the size of the input buffer (in bytes) of the in memory
+	  console.
+
 config PPC_EARLY_DEBUG_OPAL
 	def_bool y
 	depends on PPC_EARLY_DEBUG_OPAL_RAW || PPC_EARLY_DEBUG_OPAL_HVSI
diff --git a/arch/powerpc/include/asm/context_tracking.h b/arch/powerpc/include/asm/context_tracking.h
new file mode 100644
index 000000000000..b6f5a33b8ee2
--- /dev/null
+++ b/arch/powerpc/include/asm/context_tracking.h
@@ -0,0 +1,10 @@
+#ifndef _ASM_POWERPC_CONTEXT_TRACKING_H
+#define _ASM_POWERPC_CONTEXT_TRACKING_H
+
+#ifdef CONFIG_CONTEXT_TRACKING
+#define SCHEDULE_USER bl	.schedule_user
+#else
+#define SCHEDULE_USER bl	.schedule
+#endif
+
+#endif
diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h
index 0df54646f968..681bc0314b6b 100644
--- a/arch/powerpc/include/asm/firmware.h
+++ b/arch/powerpc/include/asm/firmware.h
@@ -52,6 +52,7 @@
 #define FW_FEATURE_BEST_ENERGY	ASM_CONST(0x0000000080000000)
 #define FW_FEATURE_TYPE1_AFFINITY ASM_CONST(0x0000000100000000)
 #define FW_FEATURE_PRRN		ASM_CONST(0x0000000200000000)
+#define FW_FEATURE_OPALv3	ASM_CONST(0x0000000400000000)
 
 #ifndef __ASSEMBLY__
 
@@ -69,7 +70,8 @@ enum {
 		FW_FEATURE_SET_MODE | FW_FEATURE_BEST_ENERGY |
 		FW_FEATURE_TYPE1_AFFINITY | FW_FEATURE_PRRN,
 	FW_FEATURE_PSERIES_ALWAYS = 0,
-	FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL | FW_FEATURE_OPALv2,
+	FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL | FW_FEATURE_OPALv2 |
+		FW_FEATURE_OPALv3,
 	FW_FEATURE_POWERNV_ALWAYS = 0,
 	FW_FEATURE_PS3_POSSIBLE = FW_FEATURE_LPAR | FW_FEATURE_PS3_LV1,
 	FW_FEATURE_PS3_ALWAYS = FW_FEATURE_LPAR | FW_FEATURE_PS3_LV1,
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index d615b28dda82..ba713f166fa5 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -96,11 +96,12 @@ static inline bool arch_irqs_disabled(void)
 #endif
 
 #define hard_irq_disable()	do {			\
+	u8 _was_enabled = get_paca()->soft_enabled;	\
 	__hard_irq_disable();				\
-	if (local_paca->soft_enabled)			\
-		trace_hardirqs_off();			\
 	get_paca()->soft_enabled = 0;			\
 	get_paca()->irq_happened |= PACA_IRQ_HARD_DIS;	\
+	if (_was_enabled)				\
+		trace_hardirqs_off();			\
 } while(0)
 
 static inline bool lazy_irq_pending(void)
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index b6c8b58b1d76..cbb9305ab15a 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -243,7 +243,8 @@ enum OpalMCE_TlbErrorType {
 
 enum OpalThreadStatus {
 	OPAL_THREAD_INACTIVE = 0x0,
-	OPAL_THREAD_STARTED = 0x1
+	OPAL_THREAD_STARTED = 0x1,
+	OPAL_THREAD_UNAVAILABLE = 0x2 /* opal-v3 */
 };
 
 enum OpalPciBusCompare {
@@ -563,6 +564,8 @@ extern void opal_nvram_init(void);
 
 extern int opal_machine_check(struct pt_regs *regs);
 
+extern void opal_shutdown(void);
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* __OPAL_H */
diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h
index 91acb12bac92..b66ae722a8e9 100644
--- a/arch/powerpc/include/asm/pgalloc-64.h
+++ b/arch/powerpc/include/asm/pgalloc-64.h
@@ -186,7 +186,7 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
 
 static inline pgtable_t pmd_pgtable(pmd_t pmd)
 {
-	return (pgtable_t)(pmd_val(pmd) & -sizeof(pte_t)*PTRS_PER_PTE);
+	return (pgtable_t)(pmd_val(pmd) & ~PMD_MASKED_BITS);
 }
 
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
diff --git a/arch/powerpc/include/asm/pte-hash64-64k.h b/arch/powerpc/include/asm/pte-hash64-64k.h
index 3e13e23e4fdf..d836d945068d 100644
--- a/arch/powerpc/include/asm/pte-hash64-64k.h
+++ b/arch/powerpc/include/asm/pte-hash64-64k.h
@@ -47,7 +47,7 @@
  * generic accessors and iterators here
  */
 #define __real_pte(e,p) 	((real_pte_t) { \
-			(e), ((e) & _PAGE_COMBO) ? \
+			(e), (pte_val(e) & _PAGE_COMBO) ? \
 				(pte_val(*((p) + PTRS_PER_PTE))) : 0 })
 #define __rpte_to_hidx(r,index)	((pte_val((r).pte) & _PAGE_COMBO) ? \
         (((r).hidx >> ((index)<<2)) & 0xf) : ((pte_val((r).pte) >> 12) & 0xf))
diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h
index a8bc2bb4adc9..34fd70488d83 100644
--- a/arch/powerpc/include/asm/rtas.h
+++ b/arch/powerpc/include/asm/rtas.h
@@ -264,6 +264,8 @@ extern void rtas_progress(char *s, unsigned short hex);
 extern void rtas_initialize(void);
 extern int rtas_suspend_cpu(struct rtas_suspend_me_data *data);
 extern int rtas_suspend_last_cpu(struct rtas_suspend_me_data *data);
+extern int rtas_online_cpus_mask(cpumask_var_t cpus);
+extern int rtas_offline_cpus_mask(cpumask_var_t cpus);
 extern int rtas_ibm_suspend_me(struct rtas_args *);
 
 struct rtc_time;
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index 8ceea14d6fe4..ba7b1973866e 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -97,7 +97,7 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_PERFMON_CTXSW	6	/* perfmon needs ctxsw calls */
 #define TIF_SYSCALL_AUDIT	7	/* syscall auditing active */
 #define TIF_SINGLESTEP		8	/* singlestepping active */
-#define TIF_MEMDIE		9	/* is terminating due to OOM killer */
+#define TIF_NOHZ		9	/* in adaptive nohz mode */
 #define TIF_SECCOMP		10	/* secure computing */
 #define TIF_RESTOREALL		11	/* Restore all regs (implies NOERROR) */
 #define TIF_NOERROR		12	/* Force successful syscall return */
@@ -106,6 +106,7 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_SYSCALL_TRACEPOINT	15	/* syscall tracepoint instrumentation */
 #define TIF_EMULATE_STACK_STORE	16	/* Is an instruction emulation
 						for stack store? */
+#define TIF_MEMDIE		17	/* is terminating due to OOM killer */
 
 /* as above, but as bit values */
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
@@ -124,8 +125,10 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_UPROBE		(1<<TIF_UPROBE)
 #define _TIF_SYSCALL_TRACEPOINT	(1<<TIF_SYSCALL_TRACEPOINT)
 #define _TIF_EMULATE_STACK_STORE	(1<<TIF_EMULATE_STACK_STORE)
+#define _TIF_NOHZ		(1<<TIF_NOHZ)
 #define _TIF_SYSCALL_T_OR_A	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
-				 _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT)
+				 _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \
+				 _TIF_NOHZ)
 
 #define _TIF_USER_WORK_MASK	(_TIF_SIGPENDING | _TIF_NEED_RESCHED | \
 				 _TIF_NOTIFY_RESUME | _TIF_UPROBE)
diff --git a/arch/powerpc/include/asm/udbg.h b/arch/powerpc/include/asm/udbg.h
index 5a7510e9d09d..dc590919f8eb 100644
--- a/arch/powerpc/include/asm/udbg.h
+++ b/arch/powerpc/include/asm/udbg.h
@@ -52,6 +52,7 @@ extern void __init udbg_init_40x_realmode(void);
 extern void __init udbg_init_cpm(void);
 extern void __init udbg_init_usbgecko(void);
 extern void __init udbg_init_wsp(void);
+extern void __init udbg_init_memcons(void);
 extern void __init udbg_init_ehv_bc(void);
 extern void __init udbg_init_ps3gelic(void);
 extern void __init udbg_init_debug_opal_raw(void);
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index e514de57a125..d22e73e4618b 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -439,8 +439,6 @@ ret_from_fork:
 ret_from_kernel_thread:
 	REST_NVGPRS(r1)
 	bl	schedule_tail
-	li	r3,0
-	stw	r3,0(r1)
 	mtlr	r14
 	mr	r3,r15
 	PPC440EP_ERR42
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 915fbb4fc2fe..51cfb8fc301f 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -33,6 +33,7 @@
 #include <asm/irqflags.h>
 #include <asm/ftrace.h>
 #include <asm/hw_irq.h>
+#include <asm/context_tracking.h>
 
 /*
  * System calls.
@@ -376,8 +377,6 @@ _GLOBAL(ret_from_fork)
 _GLOBAL(ret_from_kernel_thread)
 	bl	.schedule_tail
 	REST_NVGPRS(r1)
-	li	r3,0
-	std	r3,0(r1)
 	ld	r14, 0(r14)
 	mtlr	r14
 	mr	r3,r15
@@ -634,7 +633,7 @@ _GLOBAL(ret_from_except_lite)
 	andi.	r0,r4,_TIF_NEED_RESCHED
 	beq	1f
 	bl	.restore_interrupts
-	bl	.schedule
+	SCHEDULE_USER
 	b	.ret_from_except_lite
 
 1:	bl	.save_nvgprs
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 42a756eec9ff..645170a07ada 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -489,7 +489,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 	 */
 
 	mfspr	r14,SPRN_DBSR		/* check single-step/branch taken */
-	andis.	r15,r14,DBSR_IC@h
+	andis.	r15,r14,(DBSR_IC|DBSR_BT)@h
 	beq+	1f
 
 	LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e)
@@ -500,7 +500,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 	bge+	cr1,1f
 
 	/* here it looks like we got an inappropriate debug exception. */
-	lis	r14,DBSR_IC@h		/* clear the IC event */
+	lis	r14,(DBSR_IC|DBSR_BT)@h		/* clear the event */
 	rlwinm	r11,r11,0,~MSR_DE	/* clear DE in the CSRR1 value */
 	mtspr	SPRN_DBSR,r14
 	mtspr	SPRN_CSRR1,r11
@@ -555,7 +555,7 @@ kernel_dbg_exc:
 	 */
 
 	mfspr	r14,SPRN_DBSR		/* check single-step/branch taken */
-	andis.	r15,r14,DBSR_IC@h
+	andis.	r15,r14,(DBSR_IC|DBSR_BT)@h
 	beq+	1f
 
 	LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e)
@@ -566,7 +566,7 @@ kernel_dbg_exc:
 	bge+	cr1,1f
 
 	/* here it looks like we got an inappropriate debug exception. */
-	lis	r14,DBSR_IC@h		/* clear the IC event */
+	lis	r14,(DBSR_IC|DBSR_BT)@h		/* clear the event */
 	rlwinm	r11,r11,0,~MSR_DE	/* clear DE in the DSRR1 value */
 	mtspr	SPRN_DBSR,r14
 	mtspr	SPRN_DSRR1,r11
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index 466a2908bb63..611acdf30096 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -17,6 +17,7 @@
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/cpu.h>
+#include <linux/hardirq.h>
 
 #include <asm/page.h>
 #include <asm/current.h>
@@ -335,10 +336,13 @@ void default_machine_kexec(struct kimage *image)
 	pr_debug("kexec: Starting switchover sequence.\n");
 
 	/* switch to a staticly allocated stack.  Based on irq stack code.
+	 * We setup preempt_count to avoid using VMX in memcpy.
 	 * XXX: the task struct will likely be invalid once we do the copy!
 	 */
 	kexec_stack.thread_info.task = current_thread_info()->task;
 	kexec_stack.thread_info.flags = 0;
+	kexec_stack.thread_info.preempt_count = HARDIRQ_OFFSET;
+	kexec_stack.thread_info.cpu = current_thread_info()->cpu;
 
 	/* We need a static PACA, too; copy this CPU's PACA over and switch to
 	 * it.  Also poison per_cpu_offset to catch anyone using non-static
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 19e096bd0e73..e469f30e6eeb 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -657,6 +657,17 @@ _GLOBAL(__ucmpdi2)
 	li	r3,2
 	blr
 
+_GLOBAL(__bswapdi2)
+	rotlwi  r9,r4,8
+	rotlwi  r10,r3,8
+	rlwimi  r9,r4,24,0,7
+	rlwimi  r10,r3,24,0,7
+	rlwimi  r9,r4,24,16,23
+	rlwimi  r10,r3,24,16,23
+	mr      r3,r9
+	mr      r4,r10
+	blr
+
 _GLOBAL(abs)
 	srawi	r4,r3,31
 	xor	r3,r3,r4
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 5cfa8008693b..6820e45f557b 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -234,6 +234,17 @@ _GLOBAL(__flush_dcache_icache)
 	isync
 	blr
 
+_GLOBAL(__bswapdi2)
+	srdi	r8,r3,32
+	rlwinm	r7,r3,8,0xffffffff
+	rlwimi	r7,r3,24,0,7
+	rlwinm	r9,r8,8,0xffffffff
+	rlwimi	r7,r3,24,16,23
+	rlwimi	r9,r8,24,0,7
+	rlwimi	r9,r8,24,16,23
+	sldi	r7,r7,32
+	or	r3,r7,r9
+	blr
 
 #if defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_MAPLE)
 /*
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index f5c5c90799a7..6053f037ef0a 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -359,7 +359,6 @@ static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp,
 				      enum pci_mmap_state mmap_state,
 				      int write_combine)
 {
-	unsigned long prot = pgprot_val(protection);
 
 	/* Write combine is always 0 on non-memory space mappings. On
 	 * memory space, if the user didn't pass 1, we check for a
@@ -376,9 +375,9 @@ static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp,
 
 	/* XXX would be nice to have a way to ask for write-through */
 	if (write_combine)
-		return pgprot_noncached_wc(prot);
+		return pgprot_noncached_wc(protection);
 	else
-		return pgprot_noncached(prot);
+		return pgprot_noncached(protection);
 }
 
 /*
diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
index 78b8766fd79e..c29666586998 100644
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -143,7 +143,8 @@ EXPORT_SYMBOL(__lshrdi3);
 int __ucmpdi2(unsigned long long, unsigned long long);
 EXPORT_SYMBOL(__ucmpdi2);
 #endif
-
+long long __bswapdi2(long long);
+EXPORT_SYMBOL(__bswapdi2);
 EXPORT_SYMBOL(memcpy);
 EXPORT_SYMBOL(memset);
 EXPORT_SYMBOL(memmove);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index ceb4e7b62cf4..a902723fdc69 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -339,6 +339,13 @@ static void set_debug_reg_defaults(struct thread_struct *thread)
 
 static void prime_debug_regs(struct thread_struct *thread)
 {
+	/*
+	 * We could have inherited MSR_DE from userspace, since
+	 * it doesn't get cleared on exception entry.  Make sure
+	 * MSR_DE is clear before we enable any debug events.
+	 */
+	mtmsr(mfmsr() & ~MSR_DE);
+
 	mtspr(SPRN_IAC1, thread->iac1);
 	mtspr(SPRN_IAC2, thread->iac2);
 #if CONFIG_PPC_ADV_DEBUG_IACS > 2
@@ -971,6 +978,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 	 * do some house keeping and then return from the fork or clone
 	 * system call, using the stack frame created above.
 	 */
+	((unsigned long *)sp)[0] = 0;
 	sp -= sizeof(struct pt_regs);
 	kregs = (struct pt_regs *) sp;
 	sp -= STACK_FRAME_OVERHEAD;
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 3b14d320e69f..98c2fc198712 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -32,6 +32,7 @@
 #include <trace/syscall.h>
 #include <linux/hw_breakpoint.h>
 #include <linux/perf_event.h>
+#include <linux/context_tracking.h>
 
 #include <asm/uaccess.h>
 #include <asm/page.h>
@@ -1788,6 +1789,8 @@ long do_syscall_trace_enter(struct pt_regs *regs)
 {
 	long ret = 0;
 
+	user_exit();
+
 	secure_computing_strict(regs->gpr[0]);
 
 	if (test_thread_flag(TIF_SYSCALL_TRACE) &&
@@ -1832,4 +1835,6 @@ void do_syscall_trace_leave(struct pt_regs *regs)
 	step = test_thread_flag(TIF_SINGLESTEP);
 	if (step || test_thread_flag(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall_exit(regs, step);
+
+	user_enter();
 }
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 1fd6e7b2f390..52add6f3e201 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -19,6 +19,7 @@
 #include <linux/init.h>
 #include <linux/capability.h>
 #include <linux/delay.h>
+#include <linux/cpu.h>
 #include <linux/smp.h>
 #include <linux/completion.h>
 #include <linux/cpumask.h>
@@ -807,6 +808,95 @@ static void rtas_percpu_suspend_me(void *info)
 	__rtas_suspend_cpu((struct rtas_suspend_me_data *)info, 1);
 }
 
+enum rtas_cpu_state {
+	DOWN,
+	UP,
+};
+
+#ifndef CONFIG_SMP
+static int rtas_cpu_state_change_mask(enum rtas_cpu_state state,
+				cpumask_var_t cpus)
+{
+	if (!cpumask_empty(cpus)) {
+		cpumask_clear(cpus);
+		return -EINVAL;
+	} else
+		return 0;
+}
+#else
+/* On return cpumask will be altered to indicate CPUs changed.
+ * CPUs with states changed will be set in the mask,
+ * CPUs with status unchanged will be unset in the mask. */
+static int rtas_cpu_state_change_mask(enum rtas_cpu_state state,
+				cpumask_var_t cpus)
+{
+	int cpu;
+	int cpuret = 0;
+	int ret = 0;
+
+	if (cpumask_empty(cpus))
+		return 0;
+
+	for_each_cpu(cpu, cpus) {
+		switch (state) {
+		case DOWN:
+			cpuret = cpu_down(cpu);
+			break;
+		case UP:
+			cpuret = cpu_up(cpu);
+			break;
+		}
+		if (cpuret) {
+			pr_debug("%s: cpu_%s for cpu#%d returned %d.\n",
+					__func__,
+					((state == UP) ? "up" : "down"),
+					cpu, cpuret);
+			if (!ret)
+				ret = cpuret;
+			if (state == UP) {
+				/* clear bits for unchanged cpus, return */
+				cpumask_shift_right(cpus, cpus, cpu);
+				cpumask_shift_left(cpus, cpus, cpu);
+				break;
+			} else {
+				/* clear bit for unchanged cpu, continue */
+				cpumask_clear_cpu(cpu, cpus);
+			}
+		}
+	}
+
+	return ret;
+}
+#endif
+
+int rtas_online_cpus_mask(cpumask_var_t cpus)
+{
+	int ret;
+
+	ret = rtas_cpu_state_change_mask(UP, cpus);
+
+	if (ret) {
+		cpumask_var_t tmp_mask;
+
+		if (!alloc_cpumask_var(&tmp_mask, GFP_TEMPORARY))
+			return ret;
+
+		/* Use tmp_mask to preserve cpus mask from first failure */
+		cpumask_copy(tmp_mask, cpus);
+		rtas_offline_cpus_mask(tmp_mask);
+		free_cpumask_var(tmp_mask);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(rtas_online_cpus_mask);
+
+int rtas_offline_cpus_mask(cpumask_var_t cpus)
+{
+	return rtas_cpu_state_change_mask(DOWN, cpus);
+}
+EXPORT_SYMBOL(rtas_offline_cpus_mask);
+
 int rtas_ibm_suspend_me(struct rtas_args *args)
 {
 	long state;
@@ -814,6 +904,8 @@ int rtas_ibm_suspend_me(struct rtas_args *args)
 	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
 	struct rtas_suspend_me_data data;
 	DECLARE_COMPLETION_ONSTACK(done);
+	cpumask_var_t offline_mask;
+	int cpuret;
 
 	if (!rtas_service_present("ibm,suspend-me"))
 		return -ENOSYS;
@@ -837,11 +929,24 @@ int rtas_ibm_suspend_me(struct rtas_args *args)
 		return 0;
 	}
 
+	if (!alloc_cpumask_var(&offline_mask, GFP_TEMPORARY))
+		return -ENOMEM;
+
 	atomic_set(&data.working, 0);
 	atomic_set(&data.done, 0);
 	atomic_set(&data.error, 0);
 	data.token = rtas_token("ibm,suspend-me");
 	data.complete = &done;
+
+	/* All present CPUs must be online */
+	cpumask_andnot(offline_mask, cpu_present_mask, cpu_online_mask);
+	cpuret = rtas_online_cpus_mask(offline_mask);
+	if (cpuret) {
+		pr_err("%s: Could not bring present CPUs online.\n", __func__);
+		atomic_set(&data.error, cpuret);
+		goto out;
+	}
+
 	stop_topology_update();
 
 	/* Call function on all CPUs.  One of us will make the
@@ -857,6 +962,14 @@ int rtas_ibm_suspend_me(struct rtas_args *args)
 
 	start_topology_update();
 
+	/* Take down CPUs not online prior to suspend */
+	cpuret = rtas_offline_cpus_mask(offline_mask);
+	if (cpuret)
+		pr_warn("%s: Could not restore CPUs to offline state.\n",
+				__func__);
+
+out:
+	free_cpumask_var(offline_mask);
 	return atomic_read(&data.error);
 }
 #else /* CONFIG_PPC_PSERIES */
diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c
index 5b3022470126..2f3cdb01506d 100644
--- a/arch/powerpc/kernel/rtas_flash.c
+++ b/arch/powerpc/kernel/rtas_flash.c
@@ -89,6 +89,7 @@
 
 /* Array sizes */
 #define VALIDATE_BUF_SIZE 4096    
+#define VALIDATE_MSG_LEN  256
 #define RTAS_MSG_MAXLEN   64
 
 /* Quirk - RTAS requires 4k list length and block size */
@@ -466,7 +467,7 @@ static void validate_flash(struct rtas_validate_flash_t *args_buf)
 }
 
 static int get_validate_flash_msg(struct rtas_validate_flash_t *args_buf, 
-		                   char *msg)
+		                   char *msg, int msglen)
 {
 	int n;
 
@@ -474,7 +475,8 @@ static int get_validate_flash_msg(struct rtas_validate_flash_t *args_buf,
 		n = sprintf(msg, "%d\n", args_buf->update_results);
 		if ((args_buf->update_results >= VALIDATE_CUR_UNKNOWN) ||
 		    (args_buf->update_results == VALIDATE_TMP_UPDATE))
-			n += sprintf(msg + n, "%s\n", args_buf->buf);
+			n += snprintf(msg + n, msglen - n, "%s\n",
+					args_buf->buf);
 	} else {
 		n = sprintf(msg, "%d\n", args_buf->status);
 	}
@@ -486,11 +488,11 @@ static ssize_t validate_flash_read(struct file *file, char __user *buf,
 {
 	struct rtas_validate_flash_t *const args_buf =
 		&rtas_validate_flash_data;
-	char msg[RTAS_MSG_MAXLEN];
+	char msg[VALIDATE_MSG_LEN];
 	int msglen;
 
 	mutex_lock(&rtas_validate_flash_mutex);
-	msglen = get_validate_flash_msg(args_buf, msg);
+	msglen = get_validate_flash_msg(args_buf, msg, VALIDATE_MSG_LEN);
 	mutex_unlock(&rtas_validate_flash_mutex);
 
 	return simple_read_from_buffer(buf, count, ppos, msg, msglen);
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index cf12eae02de5..577a8aa69c6e 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -13,6 +13,7 @@
 #include <linux/signal.h>
 #include <linux/uprobes.h>
 #include <linux/key.h>
+#include <linux/context_tracking.h>
 #include <asm/hw_breakpoint.h>
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
@@ -24,7 +25,7 @@
  * through debug.exception-trace sysctl.
  */
 
-int show_unhandled_signals = 0;
+int show_unhandled_signals = 1;
 
 /*
  * Allocate space for the signal frame
@@ -159,6 +160,8 @@ static int do_signal(struct pt_regs *regs)
 
 void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags)
 {
+	user_exit();
+
 	if (thread_info_flags & _TIF_UPROBE)
 		uprobe_notify_resume(regs);
 
@@ -169,4 +172,6 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags)
 		clear_thread_flag(TIF_NOTIFY_RESUME);
 		tracehook_notify_resume(regs);
 	}
+
+	user_enter();
 }
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 83efa2f7d926..a7a648f6b750 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -35,6 +35,7 @@
 #include <linux/kdebug.h>
 #include <linux/debugfs.h>
 #include <linux/ratelimit.h>
+#include <linux/context_tracking.h>
 
 #include <asm/emulated_ops.h>
 #include <asm/pgtable.h>
@@ -667,6 +668,7 @@ int machine_check_generic(struct pt_regs *regs)
 
 void machine_check_exception(struct pt_regs *regs)
 {
+	enum ctx_state prev_state = exception_enter();
 	int recover = 0;
 
 	__get_cpu_var(irq_stat).mce_exceptions++;
@@ -683,7 +685,7 @@ void machine_check_exception(struct pt_regs *regs)
 		recover = cur_cpu_spec->machine_check(regs);
 
 	if (recover > 0)
-		return;
+		goto bail;
 
 #if defined(CONFIG_8xx) && defined(CONFIG_PCI)
 	/* the qspan pci read routines can cause machine checks -- Cort
@@ -693,20 +695,23 @@ void machine_check_exception(struct pt_regs *regs)
 	 * -- BenH
 	 */
 	bad_page_fault(regs, regs->dar, SIGBUS);
-	return;
+	goto bail;
 #endif
 
 	if (debugger_fault_handler(regs))
-		return;
+		goto bail;
 
 	if (check_io_access(regs))
-		return;
+		goto bail;
 
 	die("Machine check", regs, SIGBUS);
 
 	/* Must die if the interrupt is not recoverable */
 	if (!(regs->msr & MSR_RI))
 		panic("Unrecoverable Machine check");
+
+bail:
+	exception_exit(prev_state);
 }
 
 void SMIException(struct pt_regs *regs)
@@ -716,20 +721,29 @@ void SMIException(struct pt_regs *regs)
 
 void unknown_exception(struct pt_regs *regs)
 {
+	enum ctx_state prev_state = exception_enter();
+
 	printk("Bad trap at PC: %lx, SR: %lx, vector=%lx\n",
 	       regs->nip, regs->msr, regs->trap);
 
 	_exception(SIGTRAP, regs, 0, 0);
+
+	exception_exit(prev_state);
 }
 
 void instruction_breakpoint_exception(struct pt_regs *regs)
 {
+	enum ctx_state prev_state = exception_enter();
+
 	if (notify_die(DIE_IABR_MATCH, "iabr_match", regs, 5,
 					5, SIGTRAP) == NOTIFY_STOP)
-		return;
+		goto bail;
 	if (debugger_iabr_match(regs))
-		return;
+		goto bail;
 	_exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
+
+bail:
+	exception_exit(prev_state);
 }
 
 void RunModeException(struct pt_regs *regs)
@@ -739,15 +753,20 @@ void RunModeException(struct pt_regs *regs)
 
 void __kprobes single_step_exception(struct pt_regs *regs)
 {
+	enum ctx_state prev_state = exception_enter();
+
 	clear_single_step(regs);
 
 	if (notify_die(DIE_SSTEP, "single_step", regs, 5,
 					5, SIGTRAP) == NOTIFY_STOP)
-		return;
+		goto bail;
 	if (debugger_sstep(regs))
-		return;
+		goto bail;
 
 	_exception(SIGTRAP, regs, TRAP_TRACE, regs->nip);
+
+bail:
+	exception_exit(prev_state);
 }
 
 /*
@@ -1005,6 +1024,7 @@ int is_valid_bugaddr(unsigned long addr)
 
 void __kprobes program_check_exception(struct pt_regs *regs)
 {
+	enum ctx_state prev_state = exception_enter();
 	unsigned int reason = get_reason(regs);
 	extern int do_mathemu(struct pt_regs *regs);
 
@@ -1014,26 +1034,26 @@ void __kprobes program_check_exception(struct pt_regs *regs)
 	if (reason & REASON_FP) {
 		/* IEEE FP exception */
 		parse_fpe(regs);
-		return;
+		goto bail;
 	}
 	if (reason & REASON_TRAP) {
 		/* Debugger is first in line to stop recursive faults in
 		 * rcu_lock, notify_die, or atomic_notifier_call_chain */
 		if (debugger_bpt(regs))
-			return;
+			goto bail;
 
 		/* trap exception */
 		if (notify_die(DIE_BPT, "breakpoint", regs, 5, 5, SIGTRAP)
 				== NOTIFY_STOP)
-			return;
+			goto bail;
 
 		if (!(regs->msr & MSR_PR) &&  /* not user-mode */
 		    report_bug(regs->nip, regs) == BUG_TRAP_TYPE_WARN) {
 			regs->nip += 4;
-			return;
+			goto bail;
 		}
 		_exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
-		return;
+		goto bail;
 	}
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	if (reason & REASON_TM) {
@@ -1049,7 +1069,7 @@ void __kprobes program_check_exception(struct pt_regs *regs)
 		if (!user_mode(regs) &&
 		    report_bug(regs->nip, regs) == BUG_TRAP_TYPE_WARN) {
 			regs->nip += 4;
-			return;
+			goto bail;
 		}
 		/* If usermode caused this, it's done something illegal and
 		 * gets a SIGILL slap on the wrist.  We call it an illegal
@@ -1059,7 +1079,7 @@ void __kprobes program_check_exception(struct pt_regs *regs)
 		 */
 		if (user_mode(regs)) {
 			_exception(SIGILL, regs, ILL_ILLOPN, regs->nip);
-			return;
+			goto bail;
 		} else {
 			printk(KERN_EMERG "Unexpected TM Bad Thing exception "
 			       "at %lx (msr 0x%x)\n", regs->nip, reason);
@@ -1083,16 +1103,16 @@ void __kprobes program_check_exception(struct pt_regs *regs)
 	switch (do_mathemu(regs)) {
 	case 0:
 		emulate_single_step(regs);
-		return;
+		goto bail;
 	case 1: {
 			int code = 0;
 			code = __parse_fpscr(current->thread.fpscr.val);
 			_exception(SIGFPE, regs, code, regs->nip);
-			return;
+			goto bail;
 		}
 	case -EFAULT:
 		_exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip);
-		return;
+		goto bail;
 	}
 	/* fall through on any other errors */
 #endif /* CONFIG_MATH_EMULATION */
@@ -1103,10 +1123,10 @@ void __kprobes program_check_exception(struct pt_regs *regs)
 		case 0:
 			regs->nip += 4;
 			emulate_single_step(regs);
-			return;
+			goto bail;
 		case -EFAULT:
 			_exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip);
-			return;
+			goto bail;
 		}
 	}
 
@@ -1114,10 +1134,14 @@ void __kprobes program_check_exception(struct pt_regs *regs)
 		_exception(SIGILL, regs, ILL_PRVOPC, regs->nip);
 	else
 		_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
+
+bail:
+	exception_exit(prev_state);
 }
 
 void alignment_exception(struct pt_regs *regs)
 {
+	enum ctx_state prev_state = exception_enter();
 	int sig, code, fixed = 0;
 
 	/* We restore the interrupt state now */
@@ -1131,7 +1155,7 @@ void alignment_exception(struct pt_regs *regs)
 	if (fixed == 1) {
 		regs->nip += 4;	/* skip over emulated instruction */
 		emulate_single_step(regs);
-		return;
+		goto bail;
 	}
 
 	/* Operand address was bad */
@@ -1146,6 +1170,9 @@ void alignment_exception(struct pt_regs *regs)
 		_exception(sig, regs, code, regs->dar);
 	else
 		bad_page_fault(regs, regs->dar, sig);
+
+bail:
+	exception_exit(prev_state);
 }
 
 void StackOverflow(struct pt_regs *regs)
@@ -1174,23 +1201,32 @@ void trace_syscall(struct pt_regs *regs)
 
 void kernel_fp_unavailable_exception(struct pt_regs *regs)
 {
+	enum ctx_state prev_state = exception_enter();
+
 	printk(KERN_EMERG "Unrecoverable FP Unavailable Exception "
 			  "%lx at %lx\n", regs->trap, regs->nip);
 	die("Unrecoverable FP Unavailable Exception", regs, SIGABRT);
+
+	exception_exit(prev_state);
 }
 
 void altivec_unavailable_exception(struct pt_regs *regs)
 {
+	enum ctx_state prev_state = exception_enter();
+
 	if (user_mode(regs)) {
 		/* A user program has executed an altivec instruction,
 		   but this kernel doesn't support altivec. */
 		_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
-		return;
+		goto bail;
 	}
 
 	printk(KERN_EMERG "Unrecoverable VMX/Altivec Unavailable Exception "
 			"%lx at %lx\n", regs->trap, regs->nip);
 	die("Unrecoverable VMX/Altivec Unavailable Exception", regs, SIGABRT);
+
+bail:
+	exception_exit(prev_state);
 }
 
 void vsx_unavailable_exception(struct pt_regs *regs)
diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c
index 13b867093499..9d3fdcd66290 100644
--- a/arch/powerpc/kernel/udbg.c
+++ b/arch/powerpc/kernel/udbg.c
@@ -64,6 +64,9 @@ void __init udbg_early_init(void)
 	udbg_init_usbgecko();
 #elif defined(CONFIG_PPC_EARLY_DEBUG_WSP)
 	udbg_init_wsp();
+#elif defined(CONFIG_PPC_EARLY_DEBUG_MEMCONS)
+	/* In memory console */
+	udbg_init_memcons();
 #elif defined(CONFIG_PPC_EARLY_DEBUG_EHV_BC)
 	udbg_init_ehv_bc();
 #elif defined(CONFIG_PPC_EARLY_DEBUG_PS3GELIC)
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 229951ffc351..8726779e1409 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -32,6 +32,7 @@
 #include <linux/perf_event.h>
 #include <linux/magic.h>
 #include <linux/ratelimit.h>
+#include <linux/context_tracking.h>
 
 #include <asm/firmware.h>
 #include <asm/page.h>
@@ -196,6 +197,7 @@ static int mm_fault_error(struct pt_regs *regs, unsigned long addr, int fault)
 int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 			    unsigned long error_code)
 {
+	enum ctx_state prev_state = exception_enter();
 	struct vm_area_struct * vma;
 	struct mm_struct *mm = current->mm;
 	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
@@ -204,6 +206,7 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 	int trap = TRAP(regs);
  	int is_exec = trap == 0x400;
 	int fault;
+	int rc = 0;
 
 #if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE))
 	/*
@@ -230,28 +233,30 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 	 * look at it
 	 */
 	if (error_code & ICSWX_DSI_UCT) {
-		int rc = acop_handle_fault(regs, address, error_code);
+		rc = acop_handle_fault(regs, address, error_code);
 		if (rc)
-			return rc;
+			goto bail;
 	}
 #endif /* CONFIG_PPC_ICSWX */
 
 	if (notify_page_fault(regs))
-		return 0;
+		goto bail;
 
 	if (unlikely(debugger_fault_handler(regs)))
-		return 0;
+		goto bail;
 
 	/* On a kernel SLB miss we can only check for a valid exception entry */
-	if (!user_mode(regs) && (address >= TASK_SIZE))
-		return SIGSEGV;
+	if (!user_mode(regs) && (address >= TASK_SIZE)) {
+		rc = SIGSEGV;
+		goto bail;
+	}
 
 #if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE) || \
 			     defined(CONFIG_PPC_BOOK3S_64))
   	if (error_code & DSISR_DABRMATCH) {
 		/* breakpoint match */
 		do_break(regs, address, error_code);
-		return 0;
+		goto bail;
 	}
 #endif
 
@@ -260,8 +265,10 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 		local_irq_enable();
 
 	if (in_atomic() || mm == NULL) {
-		if (!user_mode(regs))
-			return SIGSEGV;
+		if (!user_mode(regs)) {
+			rc = SIGSEGV;
+			goto bail;
+		}
 		/* in_atomic() in user mode is really bad,
 		   as is current->mm == NULL. */
 		printk(KERN_EMERG "Page fault in user mode with "
@@ -417,9 +424,11 @@ good_area:
 	 */
 	fault = handle_mm_fault(mm, vma, address, flags);
 	if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) {
-		int rc = mm_fault_error(regs, address, fault);
+		rc = mm_fault_error(regs, address, fault);
 		if (rc >= MM_FAULT_RETURN)
-			return rc;
+			goto bail;
+		else
+			rc = 0;
 	}
 
 	/*
@@ -454,7 +463,7 @@ good_area:
 	}
 
 	up_read(&mm->mmap_sem);
-	return 0;
+	goto bail;
 
 bad_area:
 	up_read(&mm->mmap_sem);
@@ -463,7 +472,7 @@ bad_area_nosemaphore:
 	/* User mode accesses cause a SIGSEGV */
 	if (user_mode(regs)) {
 		_exception(SIGSEGV, regs, code, address);
-		return 0;
+		goto bail;
 	}
 
 	if (is_exec && (error_code & DSISR_PROTFAULT))
@@ -471,7 +480,11 @@ bad_area_nosemaphore:
 				   " page (%lx) - exploit attempt? (uid: %d)\n",
 				   address, from_kuid(&init_user_ns, current_uid()));
 
-	return SIGSEGV;
+	rc = SIGSEGV;
+
+bail:
+	exception_exit(prev_state);
+	return rc;
 
 }
 
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 88ac0eeaadde..e303a6d74e3a 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -33,6 +33,7 @@
 #include <linux/init.h>
 #include <linux/signal.h>
 #include <linux/memblock.h>
+#include <linux/context_tracking.h>
 
 #include <asm/processor.h>
 #include <asm/pgtable.h>
@@ -954,6 +955,7 @@ void hash_failure_debug(unsigned long ea, unsigned long access,
  */
 int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 {
+	enum ctx_state prev_state = exception_enter();
 	pgd_t *pgdir;
 	unsigned long vsid;
 	struct mm_struct *mm;
@@ -973,7 +975,8 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 		mm = current->mm;
 		if (! mm) {
 			DBG_LOW(" user region with no mm !\n");
-			return 1;
+			rc = 1;
+			goto bail;
 		}
 		psize = get_slice_psize(mm, ea);
 		ssize = user_segment_size(ea);
@@ -992,19 +995,23 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 		/* Not a valid range
 		 * Send the problem up to do_page_fault 
 		 */
-		return 1;
+		rc = 1;
+		goto bail;
 	}
 	DBG_LOW(" mm=%p, mm->pgdir=%p, vsid=%016lx\n", mm, mm->pgd, vsid);
 
 	/* Bad address. */
 	if (!vsid) {
 		DBG_LOW("Bad address!\n");
-		return 1;
+		rc = 1;
+		goto bail;
 	}
 	/* Get pgdir */
 	pgdir = mm->pgd;
-	if (pgdir == NULL)
-		return 1;
+	if (pgdir == NULL) {
+		rc = 1;
+		goto bail;
+	}
 
 	/* Check CPU locality */
 	tmp = cpumask_of(smp_processor_id());
@@ -1027,7 +1034,8 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 	ptep = find_linux_pte_or_hugepte(pgdir, ea, &hugeshift);
 	if (ptep == NULL || !pte_present(*ptep)) {
 		DBG_LOW(" no PTE !\n");
-		return 1;
+		rc = 1;
+		goto bail;
 	}
 
 	/* Add _PAGE_PRESENT to the required access perm */
@@ -1038,13 +1046,16 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 	 */
 	if (access & ~pte_val(*ptep)) {
 		DBG_LOW(" no access !\n");
-		return 1;
+		rc = 1;
+		goto bail;
 	}
 
 #ifdef CONFIG_HUGETLB_PAGE
-	if (hugeshift)
-		return __hash_page_huge(ea, access, vsid, ptep, trap, local,
+	if (hugeshift) {
+		rc = __hash_page_huge(ea, access, vsid, ptep, trap, local,
 					ssize, hugeshift, psize);
+		goto bail;
+	}
 #endif /* CONFIG_HUGETLB_PAGE */
 
 #ifndef CONFIG_PPC_64K_PAGES
@@ -1124,6 +1135,9 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 		pte_val(*(ptep + PTRS_PER_PTE)));
 #endif
 	DBG_LOW(" -> rc=%d\n", rc);
+
+bail:
+	exception_exit(prev_state);
 	return rc;
 }
 EXPORT_SYMBOL_GPL(hash_page);
@@ -1259,6 +1273,8 @@ void flush_hash_range(unsigned long number, int local)
  */
 void low_hash_fault(struct pt_regs *regs, unsigned long address, int rc)
 {
+	enum ctx_state prev_state = exception_enter();
+
 	if (user_mode(regs)) {
 #ifdef CONFIG_PPC_SUBPAGE_PROT
 		if (rc == -2)
@@ -1268,6 +1284,8 @@ void low_hash_fault(struct pt_regs *regs, unsigned long address, int rc)
 			_exception(SIGBUS, regs, BUS_ADRERR, address);
 	} else
 		bad_page_fault(regs, address, SIGBUS);
+
+	exception_exit(prev_state);
 }
 
 long hpte_insert_repeating(unsigned long hash, unsigned long vpn,
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index c2787bf779ca..a90b9c458990 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -215,7 +215,8 @@ static void __meminit vmemmap_create_mapping(unsigned long start,
 					     unsigned long phys)
 {
 	int  mapped = htab_bolt_mapping(start, start + page_size, phys,
-					PAGE_KERNEL, mmu_vmemmap_psize,
+					pgprot_val(PAGE_KERNEL),
+					mmu_vmemmap_psize,
 					mmu_kernel_ssize);
 	BUG_ON(mapped < 0);
 }
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index c627843c5b2e..426180b84978 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -13,11 +13,13 @@
 #include <linux/perf_event.h>
 #include <linux/percpu.h>
 #include <linux/hardirq.h>
+#include <linux/uaccess.h>
 #include <asm/reg.h>
 #include <asm/pmc.h>
 #include <asm/machdep.h>
 #include <asm/firmware.h>
 #include <asm/ptrace.h>
+#include <asm/code-patching.h>
 
 #define BHRB_MAX_ENTRIES	32
 #define BHRB_TARGET		0x0000000000000002
@@ -100,6 +102,10 @@ static inline int siar_valid(struct pt_regs *regs)
 	return 1;
 }
 
+static inline void power_pmu_bhrb_enable(struct perf_event *event) {}
+static inline void power_pmu_bhrb_disable(struct perf_event *event) {}
+void power_pmu_flush_branch_stack(void) {}
+static inline void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) {}
 #endif /* CONFIG_PPC32 */
 
 static bool regs_use_siar(struct pt_regs *regs)
@@ -308,6 +314,159 @@ static inline int siar_valid(struct pt_regs *regs)
 	return 1;
 }
 
+
+/* Reset all possible BHRB entries */
+static void power_pmu_bhrb_reset(void)
+{
+	asm volatile(PPC_CLRBHRB);
+}
+
+static void power_pmu_bhrb_enable(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+
+	if (!ppmu->bhrb_nr)
+		return;
+
+	/* Clear BHRB if we changed task context to avoid data leaks */
+	if (event->ctx->task && cpuhw->bhrb_context != event->ctx) {
+		power_pmu_bhrb_reset();
+		cpuhw->bhrb_context = event->ctx;
+	}
+	cpuhw->bhrb_users++;
+}
+
+static void power_pmu_bhrb_disable(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+
+	if (!ppmu->bhrb_nr)
+		return;
+
+	cpuhw->bhrb_users--;
+	WARN_ON_ONCE(cpuhw->bhrb_users < 0);
+
+	if (!cpuhw->disabled && !cpuhw->bhrb_users) {
+		/* BHRB cannot be turned off when other
+		 * events are active on the PMU.
+		 */
+
+		/* avoid stale pointer */
+		cpuhw->bhrb_context = NULL;
+	}
+}
+
+/* Called from ctxsw to prevent one process's branch entries to
+ * mingle with the other process's entries during context switch.
+ */
+void power_pmu_flush_branch_stack(void)
+{
+	if (ppmu->bhrb_nr)
+		power_pmu_bhrb_reset();
+}
+/* Calculate the to address for a branch */
+static __u64 power_pmu_bhrb_to(u64 addr)
+{
+	unsigned int instr;
+	int ret;
+	__u64 target;
+
+	if (is_kernel_addr(addr))
+		return branch_target((unsigned int *)addr);
+
+	/* Userspace: need copy instruction here then translate it */
+	pagefault_disable();
+	ret = __get_user_inatomic(instr, (unsigned int __user *)addr);
+	if (ret) {
+		pagefault_enable();
+		return 0;
+	}
+	pagefault_enable();
+
+	target = branch_target(&instr);
+	if ((!target) || (instr & BRANCH_ABSOLUTE))
+		return target;
+
+	/* Translate relative branch target from kernel to user address */
+	return target - (unsigned long)&instr + addr;
+}
+
+/* Processing BHRB entries */
+void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw)
+{
+	u64 val;
+	u64 addr;
+	int r_index, u_index, pred;
+
+	r_index = 0;
+	u_index = 0;
+	while (r_index < ppmu->bhrb_nr) {
+		/* Assembly read function */
+		val = read_bhrb(r_index++);
+		if (!val)
+			/* Terminal marker: End of valid BHRB entries */
+			break;
+		else {
+			addr = val & BHRB_EA;
+			pred = val & BHRB_PREDICTION;
+
+			if (!addr)
+				/* invalid entry */
+				continue;
+
+			/* Branches are read most recent first (ie. mfbhrb 0 is
+			 * the most recent branch).
+			 * There are two types of valid entries:
+			 * 1) a target entry which is the to address of a
+			 *    computed goto like a blr,bctr,btar.  The next
+			 *    entry read from the bhrb will be branch
+			 *    corresponding to this target (ie. the actual
+			 *    blr/bctr/btar instruction).
+			 * 2) a from address which is an actual branch.  If a
+			 *    target entry proceeds this, then this is the
+			 *    matching branch for that target.  If this is not
+			 *    following a target entry, then this is a branch
+			 *    where the target is given as an immediate field
+			 *    in the instruction (ie. an i or b form branch).
+			 *    In this case we need to read the instruction from
+			 *    memory to determine the target/to address.
+			 */
+
+			if (val & BHRB_TARGET) {
+				/* Target branches use two entries
+				 * (ie. computed gotos/XL form)
+				 */
+				cpuhw->bhrb_entries[u_index].to = addr;
+				cpuhw->bhrb_entries[u_index].mispred = pred;
+				cpuhw->bhrb_entries[u_index].predicted = ~pred;
+
+				/* Get from address in next entry */
+				val = read_bhrb(r_index++);
+				addr = val & BHRB_EA;
+				if (val & BHRB_TARGET) {
+					/* Shouldn't have two targets in a
+					   row.. Reset index and try again */
+					r_index--;
+					addr = 0;
+				}
+				cpuhw->bhrb_entries[u_index].from = addr;
+			} else {
+				/* Branches to immediate field 
+				   (ie I or B form) */
+				cpuhw->bhrb_entries[u_index].from = addr;
+				cpuhw->bhrb_entries[u_index].to =
+					power_pmu_bhrb_to(addr);
+				cpuhw->bhrb_entries[u_index].mispred = pred;
+				cpuhw->bhrb_entries[u_index].predicted = ~pred;
+			}
+			u_index++;
+
+		}
+	}
+	cpuhw->bhrb_stack.nr = u_index;
+	return;
+}
+
 #endif /* CONFIG_PPC64 */
 
 static void perf_event_interrupt(struct pt_regs *regs);
@@ -904,47 +1063,6 @@ static int collect_events(struct perf_event *group, int max_count,
 	return n;
 }
 
-/* Reset all possible BHRB entries */
-static void power_pmu_bhrb_reset(void)
-{
-	asm volatile(PPC_CLRBHRB);
-}
-
-void power_pmu_bhrb_enable(struct perf_event *event)
-{
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
-
-	if (!ppmu->bhrb_nr)
-		return;
-
-	/* Clear BHRB if we changed task context to avoid data leaks */
-	if (event->ctx->task && cpuhw->bhrb_context != event->ctx) {
-		power_pmu_bhrb_reset();
-		cpuhw->bhrb_context = event->ctx;
-	}
-	cpuhw->bhrb_users++;
-}
-
-void power_pmu_bhrb_disable(struct perf_event *event)
-{
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
-
-	if (!ppmu->bhrb_nr)
-		return;
-
-	cpuhw->bhrb_users--;
-	WARN_ON_ONCE(cpuhw->bhrb_users < 0);
-
-	if (!cpuhw->disabled && !cpuhw->bhrb_users) {
-		/* BHRB cannot be turned off when other
-		 * events are active on the PMU.
-		 */
-
-		/* avoid stale pointer */
-		cpuhw->bhrb_context = NULL;
-	}
-}
-
 /*
  * Add a event to the PMU.
  * If all events are not already frozen, then we disable and
@@ -1180,15 +1298,6 @@ int power_pmu_commit_txn(struct pmu *pmu)
 	return 0;
 }
 
-/* Called from ctxsw to prevent one process's branch entries to
- * mingle with the other process's entries during context switch.
- */
-void power_pmu_flush_branch_stack(void)
-{
-	if (ppmu->bhrb_nr)
-		power_pmu_bhrb_reset();
-}
-
 /*
  * Return 1 if we might be able to put event on a limited PMC,
  * or 0 if not.
@@ -1458,77 +1567,6 @@ struct pmu power_pmu = {
 	.flush_branch_stack = power_pmu_flush_branch_stack,
 };
 
-/* Processing BHRB entries */
-void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw)
-{
-	u64 val;
-	u64 addr;
-	int r_index, u_index, target, pred;
-
-	r_index = 0;
-	u_index = 0;
-	while (r_index < ppmu->bhrb_nr) {
-		/* Assembly read function */
-		val = read_bhrb(r_index);
-
-		/* Terminal marker: End of valid BHRB entries */
-		if (val == 0) {
-			break;
-		} else {
-			/* BHRB field break up */
-			addr = val & BHRB_EA;
-			pred = val & BHRB_PREDICTION;
-			target = val & BHRB_TARGET;
-
-			/* Probable Missed entry: Not applicable for POWER8 */
-			if ((addr == 0) && (target == 0) && (pred == 1)) {
-				r_index++;
-				continue;
-			}
-
-			/* Real Missed entry: Power8 based missed entry */
-			if ((addr == 0) && (target == 1) && (pred == 1)) {
-				r_index++;
-				continue;
-			}
-
-			/* Reserved condition: Not a valid entry  */
-			if ((addr == 0) && (target == 1) && (pred == 0)) {
-				r_index++;
-				continue;
-			}
-
-			/* Is a target address */
-			if (val & BHRB_TARGET) {
-				/* First address cannot be a target address */
-				if (r_index == 0) {
-					r_index++;
-					continue;
-				}
-
-				/* Update target address for the previous entry */
-				cpuhw->bhrb_entries[u_index - 1].to = addr;
-				cpuhw->bhrb_entries[u_index - 1].mispred = pred;
-				cpuhw->bhrb_entries[u_index - 1].predicted = ~pred;
-
-				/* Dont increment u_index */
-				r_index++;
-			} else {
-				/* Update address, flags for current entry */
-				cpuhw->bhrb_entries[u_index].from = addr;
-				cpuhw->bhrb_entries[u_index].mispred = pred;
-				cpuhw->bhrb_entries[u_index].predicted = ~pred;
-
-				/* Successfully popullated one entry */
-				u_index++;
-				r_index++;
-			}
-		}
-	}
-	cpuhw->bhrb_stack.nr = u_index;
-	return;
-}
-
 /*
  * A counter has overflowed; update its count and record
  * things if requested.  Note that interrupts are hard-disabled
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index a881232a3cce..b62aab3e22ec 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -128,7 +128,7 @@ config PPC_RTAS_DAEMON
 
 config RTAS_PROC
 	bool "Proc interface to RTAS"
-	depends on PPC_RTAS
+	depends on PPC_RTAS && PROC_FS
 	default y
 
 config RTAS_FLASH
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index ade4463226c6..628c564ceadb 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -15,6 +15,7 @@
 #include <linux/of.h>
 #include <linux/of_platform.h>
 #include <linux/interrupt.h>
+#include <linux/slab.h>
 #include <asm/opal.h>
 #include <asm/firmware.h>
 
@@ -28,6 +29,8 @@ struct opal {
 static struct device_node *opal_node;
 static DEFINE_SPINLOCK(opal_write_lock);
 extern u64 opal_mc_secondary_handler[];
+static unsigned int *opal_irqs;
+static unsigned int opal_irq_count;
 
 int __init early_init_dt_scan_opal(unsigned long node,
 				   const char *uname, int depth, void *data)
@@ -53,7 +56,11 @@ int __init early_init_dt_scan_opal(unsigned long node,
 		 opal.entry, entryp, entrysz);
 
 	powerpc_firmware_features |= FW_FEATURE_OPAL;
-	if (of_flat_dt_is_compatible(node, "ibm,opal-v2")) {
+	if (of_flat_dt_is_compatible(node, "ibm,opal-v3")) {
+		powerpc_firmware_features |= FW_FEATURE_OPALv2;
+		powerpc_firmware_features |= FW_FEATURE_OPALv3;
+		printk("OPAL V3 detected !\n");
+	} else if (of_flat_dt_is_compatible(node, "ibm,opal-v2")) {
 		powerpc_firmware_features |= FW_FEATURE_OPALv2;
 		printk("OPAL V2 detected !\n");
 	} else {
@@ -144,6 +151,13 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
 				rc == OPAL_BUSY_EVENT || rc == OPAL_SUCCESS)) {
 		len = total_len;
 		rc = opal_console_write(vtermno, &len, data);
+
+		/* Closed or other error drop */
+		if (rc != OPAL_SUCCESS && rc != OPAL_BUSY &&
+		    rc != OPAL_BUSY_EVENT) {
+			written = total_len;
+			break;
+		}
 		if (rc == OPAL_SUCCESS) {
 			total_len -= len;
 			data += len;
@@ -316,6 +330,8 @@ static int __init opal_init(void)
 	irqs = of_get_property(opal_node, "opal-interrupts", &irqlen);
 	pr_debug("opal: Found %d interrupts reserved for OPAL\n",
 		 irqs ? (irqlen / 4) : 0);
+	opal_irq_count = irqlen / 4;
+	opal_irqs = kzalloc(opal_irq_count * sizeof(unsigned int), GFP_KERNEL);
 	for (i = 0; irqs && i < (irqlen / 4); i++, irqs++) {
 		unsigned int hwirq = be32_to_cpup(irqs);
 		unsigned int irq = irq_create_mapping(NULL, hwirq);
@@ -327,7 +343,19 @@ static int __init opal_init(void)
 		if (rc)
 			pr_warning("opal: Error %d requesting irq %d"
 				   " (0x%x)\n", rc, irq, hwirq);
+		opal_irqs[i] = irq;
 	}
 	return 0;
 }
 subsys_initcall(opal_init);
+
+void opal_shutdown(void)
+{
+	unsigned int i;
+
+	for (i = 0; i < opal_irq_count; i++) {
+		if (opal_irqs[i])
+			free_irq(opal_irqs[i], 0);
+		opal_irqs[i] = 0;
+	}
+}
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 1da578b7c1bf..3937aaae5bc4 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1048,6 +1048,12 @@ static u32 pnv_ioda_bdfn_to_pe(struct pnv_phb *phb, struct pci_bus *bus,
 	return phb->ioda.pe_rmap[(bus->number << 8) | devfn];
 }
 
+static void pnv_pci_ioda_shutdown(struct pnv_phb *phb)
+{
+	opal_pci_reset(phb->opal_id, OPAL_PCI_IODA_TABLE_RESET,
+		       OPAL_ASSERT_RESET);
+}
+
 void __init pnv_pci_init_ioda_phb(struct device_node *np, int ioda_type)
 {
 	struct pci_controller *hose;
@@ -1178,6 +1184,9 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np, int ioda_type)
 	/* Setup TCEs */
 	phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup;
 
+	/* Setup shutdown function for kexec */
+	phb->shutdown = pnv_pci_ioda_shutdown;
+
 	/* Setup MSI support */
 	pnv_pci_init_ioda_msis(phb);
 
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 55dfca844ddf..163bd7422f1c 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -450,6 +450,18 @@ static void pnv_pci_dma_dev_setup(struct pci_dev *pdev)
 		pnv_pci_dma_fallback_setup(hose, pdev);
 }
 
+void pnv_pci_shutdown(void)
+{
+	struct pci_controller *hose;
+
+	list_for_each_entry(hose, &hose_list, list_node) {
+		struct pnv_phb *phb = hose->private_data;
+
+		if (phb && phb->shutdown)
+			phb->shutdown(phb);
+	}
+}
+
 /* Fixup wrong class code in p7ioc and p8 root complex */
 static void pnv_p7ioc_rc_quirk(struct pci_dev *dev)
 {
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 48dc4bb856a1..25d76c4df50b 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -86,6 +86,7 @@ struct pnv_phb {
 	void (*dma_dev_setup)(struct pnv_phb *phb, struct pci_dev *pdev);
 	void (*fixup_phb)(struct pci_controller *hose);
 	u32 (*bdfn_to_pe)(struct pnv_phb *phb, struct pci_bus *bus, u32 devfn);
+	void (*shutdown)(struct pnv_phb *phb);
 
 	union {
 		struct {
@@ -158,4 +159,5 @@ extern void pnv_pci_init_ioda_hub(struct device_node *np);
 extern void pnv_pci_init_ioda2_phb(struct device_node *np);
 extern void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl,
 					u64 *startp, u64 *endp);
+
 #endif /* __POWERNV_PCI_H */
diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h
index 8a9df7f9667e..a1c6f83fc391 100644
--- a/arch/powerpc/platforms/powernv/powernv.h
+++ b/arch/powerpc/platforms/powernv/powernv.h
@@ -9,8 +9,10 @@ static inline void pnv_smp_init(void) { }
 
 #ifdef CONFIG_PCI
 extern void pnv_pci_init(void);
+extern void pnv_pci_shutdown(void);
 #else
 static inline void pnv_pci_init(void) { }
+static inline void pnv_pci_shutdown(void) { }
 #endif
 
 #endif /* _POWERNV_H */
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index db1ad1c8f68f..d4459bfc92f7 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -78,7 +78,9 @@ static void pnv_show_cpuinfo(struct seq_file *m)
 	if (root)
 		model = of_get_property(root, "model", NULL);
 	seq_printf(m, "machine\t\t: PowerNV %s\n", model);
-	if (firmware_has_feature(FW_FEATURE_OPALv2))
+	if (firmware_has_feature(FW_FEATURE_OPALv3))
+		seq_printf(m, "firmware\t: OPAL v3\n");
+	else if (firmware_has_feature(FW_FEATURE_OPALv2))
 		seq_printf(m, "firmware\t: OPAL v2\n");
 	else if (firmware_has_feature(FW_FEATURE_OPAL))
 		seq_printf(m, "firmware\t: OPAL v1\n");
@@ -126,6 +128,17 @@ static void pnv_progress(char *s, unsigned short hex)
 {
 }
 
+static void pnv_shutdown(void)
+{
+	/* Let the PCI code clear up IODA tables */
+	pnv_pci_shutdown();
+
+	/* And unregister all OPAL interrupts so they don't fire
+	 * up while we kexec
+	 */
+	opal_shutdown();
+}
+
 #ifdef CONFIG_KEXEC
 static void pnv_kexec_cpu_down(int crash_shutdown, int secondary)
 {
@@ -187,6 +200,7 @@ define_machine(powernv) {
 	.init_IRQ		= pnv_init_IRQ,
 	.show_cpuinfo		= pnv_show_cpuinfo,
 	.progress		= pnv_progress,
+	.machine_shutdown	= pnv_shutdown,
 	.power_save             = power7_idle,
 	.calibrate_decr		= generic_calibrate_decr,
 #ifdef CONFIG_KEXEC
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index 6a3ecca5b725..88c9459c3e07 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -71,18 +71,68 @@ int pnv_smp_kick_cpu(int nr)
 
 	BUG_ON(nr < 0 || nr >= NR_CPUS);
 
-	/* On OPAL v2 the CPU are still spinning inside OPAL itself,
-	 * get them back now
+	/*
+	 * If we already started or OPALv2 is not supported, we just
+	 * kick the CPU via the PACA
 	 */
-	if (!paca[nr].cpu_start && firmware_has_feature(FW_FEATURE_OPALv2)) {
-		pr_devel("OPAL: Starting CPU %d (HW 0x%x)...\n", nr, pcpu);
-		rc = opal_start_cpu(pcpu, start_here);
+	if (paca[nr].cpu_start || !firmware_has_feature(FW_FEATURE_OPALv2))
+		goto kick;
+
+	/*
+	 * At this point, the CPU can either be spinning on the way in
+	 * from kexec or be inside OPAL waiting to be started for the
+	 * first time. OPAL v3 allows us to query OPAL to know if it
+	 * has the CPUs, so we do that
+	 */
+	if (firmware_has_feature(FW_FEATURE_OPALv3)) {
+		uint8_t status;
+
+		rc = opal_query_cpu_status(pcpu, &status);
 		if (rc != OPAL_SUCCESS) {
-			pr_warn("OPAL Error %ld starting CPU %d\n",
+			pr_warn("OPAL Error %ld querying CPU %d state\n",
 				rc, nr);
 			return -ENODEV;
 		}
+
+		/*
+		 * Already started, just kick it, probably coming from
+		 * kexec and spinning
+		 */
+		if (status == OPAL_THREAD_STARTED)
+			goto kick;
+
+		/*
+		 * Available/inactive, let's kick it
+		 */
+		if (status == OPAL_THREAD_INACTIVE) {
+			pr_devel("OPAL: Starting CPU %d (HW 0x%x)...\n",
+				 nr, pcpu);
+			rc = opal_start_cpu(pcpu, start_here);
+			if (rc != OPAL_SUCCESS) {
+				pr_warn("OPAL Error %ld starting CPU %d\n",
+					rc, nr);
+				return -ENODEV;
+			}
+		} else {
+			/*
+			 * An unavailable CPU (or any other unknown status)
+			 * shouldn't be started. It should also
+			 * not be in the possible map but currently it can
+			 * happen
+			 */
+			pr_devel("OPAL: CPU %d (HW 0x%x) is unavailable"
+				 " (status %d)...\n", nr, pcpu, status);
+			return -ENODEV;
+		}
+	} else {
+		/*
+		 * On OPAL v2, we just kick it and hope for the best,
+		 * we must not test the error from opal_start_cpu() or
+		 * we would fail to get CPUs from kexec.
+		 */
+		opal_start_cpu(pcpu, start_here);
 	}
+ kick:
 	return smp_generic_kick_cpu(nr);
 }
 
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 9a0941bc4d31..023b288f895b 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -18,6 +18,7 @@ config PPC_PSERIES
 	select PPC_PCI_CHOICE if EXPERT
 	select ZLIB_DEFLATE
 	select PPC_DOORBELL
+	select HAVE_CONTEXT_TRACKING
 	default y
 
 config PPC_SPLPAR
diff --git a/arch/powerpc/platforms/pseries/suspend.c b/arch/powerpc/platforms/pseries/suspend.c
index 47226e04126d..5f997e79d570 100644
--- a/arch/powerpc/platforms/pseries/suspend.c
+++ b/arch/powerpc/platforms/pseries/suspend.c
@@ -16,6 +16,7 @@
   * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
   */
 
+#include <linux/cpu.h>
 #include <linux/delay.h>
 #include <linux/suspend.h>
 #include <linux/stat.h>
@@ -126,11 +127,15 @@ static ssize_t store_hibernate(struct device *dev,
 			       struct device_attribute *attr,
 			       const char *buf, size_t count)
 {
+	cpumask_var_t offline_mask;
 	int rc;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
+	if (!alloc_cpumask_var(&offline_mask, GFP_TEMPORARY))
+		return -ENOMEM;
+
 	stream_id = simple_strtoul(buf, NULL, 16);
 
 	do {
@@ -140,15 +145,32 @@ static ssize_t store_hibernate(struct device *dev,
 	} while (rc == -EAGAIN);
 
 	if (!rc) {
+		/* All present CPUs must be online */
+		cpumask_andnot(offline_mask, cpu_present_mask,
+				cpu_online_mask);
+		rc = rtas_online_cpus_mask(offline_mask);
+		if (rc) {
+			pr_err("%s: Could not bring present CPUs online.\n",
+					__func__);
+			goto out;
+		}
+
 		stop_topology_update();
 		rc = pm_suspend(PM_SUSPEND_MEM);
 		start_topology_update();
+
+		/* Take down CPUs not online prior to suspend */
+		if (!rtas_offline_cpus_mask(offline_mask))
+			pr_warn("%s: Could not restore CPUs to offline "
+					"state.\n", __func__);
 	}
 
 	stream_id = 0;
 
 	if (!rc)
 		rc = count;
+out:
+	free_cpumask_var(offline_mask);
 	return rc;
 }
 
diff --git a/arch/powerpc/platforms/wsp/ics.c b/arch/powerpc/platforms/wsp/ics.c
index 97fe82ee8633..2d3b1dd9571d 100644
--- a/arch/powerpc/platforms/wsp/ics.c
+++ b/arch/powerpc/platforms/wsp/ics.c
@@ -361,7 +361,7 @@ static int wsp_chip_set_affinity(struct irq_data *d,
 	xive = xive_set_server(xive, get_irq_server(ics, hw_irq));
 	wsp_ics_set_xive(ics, hw_irq, xive);
 
-	return 0;
+	return IRQ_SET_MASK_OK;
 }
 
 static struct irq_chip wsp_irq_chip = {
diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile
index b0a518e97599..99464a7bdb3b 100644
--- a/arch/powerpc/sysdev/Makefile
+++ b/arch/powerpc/sysdev/Makefile
@@ -64,6 +64,8 @@ endif
 
 obj-$(CONFIG_PPC_SCOM)		+= scom.o
 
+obj-$(CONFIG_PPC_EARLY_DEBUG_MEMCONS)	+= udbg_memcons.o
+
 subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
 
 obj-$(CONFIG_PPC_XICS)		+= xics/
diff --git a/arch/powerpc/sysdev/ehv_pic.c b/arch/powerpc/sysdev/ehv_pic.c
index 6e0e1005227f..9cd0e60716fe 100644
--- a/arch/powerpc/sysdev/ehv_pic.c
+++ b/arch/powerpc/sysdev/ehv_pic.c
@@ -81,7 +81,7 @@ int ehv_pic_set_affinity(struct irq_data *d, const struct cpumask *dest,
 	ev_int_set_config(src, config, prio, cpuid);
 	spin_unlock_irqrestore(&ehv_pic_lock, flags);
 
-	return 0;
+	return IRQ_SET_MASK_OK;
 }
 
 static unsigned int ehv_pic_type_to_vecpri(unsigned int type)
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index ee21b5e71aec..0a13ecb270c7 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -836,7 +836,7 @@ int mpic_set_affinity(struct irq_data *d, const struct cpumask *cpumask,
 			       mpic_physmask(mask));
 	}
 
-	return 0;
+	return IRQ_SET_MASK_OK;
 }
 
 static unsigned int mpic_type_to_vecpri(struct mpic *mpic, unsigned int type)
diff --git a/arch/powerpc/sysdev/udbg_memcons.c b/arch/powerpc/sysdev/udbg_memcons.c
new file mode 100644
index 000000000000..ce5a7b489e4b
--- /dev/null
+++ b/arch/powerpc/sysdev/udbg_memcons.c
@@ -0,0 +1,105 @@
+/*
+ * A udbg backend which logs messages and reads input from in memory
+ * buffers.
+ *
+ * The console output can be read from memcons_output which is a
+ * circular buffer whose next write position is stored in memcons.output_pos.
+ *
+ * Input may be passed by writing into the memcons_input buffer when it is
+ * empty. The input buffer is empty when both input_pos == input_start and
+ * *input_start == '\0'.
+ *
+ * Copyright (C) 2003-2005 Anton Blanchard and Milton Miller, IBM Corp
+ * Copyright (C) 2013 Alistair Popple, IBM Corp
+ *
+ *      This program is free software; you can redistribute it and/or
+ *      modify it under the terms of the GNU General Public License
+ *      as published by the Free Software Foundation; either version
+ *      2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <asm/barrier.h>
+#include <asm/page.h>
+#include <asm/processor.h>
+#include <asm/udbg.h>
+
+struct memcons {
+	char *output_start;
+	char *output_pos;
+	char *output_end;
+	char *input_start;
+	char *input_pos;
+	char *input_end;
+};
+
+static char memcons_output[CONFIG_PPC_MEMCONS_OUTPUT_SIZE];
+static char memcons_input[CONFIG_PPC_MEMCONS_INPUT_SIZE];
+
+struct memcons memcons = {
+	.output_start = memcons_output,
+	.output_pos = memcons_output,
+	.output_end = &memcons_output[CONFIG_PPC_MEMCONS_OUTPUT_SIZE],
+	.input_start = memcons_input,
+	.input_pos = memcons_input,
+	.input_end = &memcons_input[CONFIG_PPC_MEMCONS_INPUT_SIZE],
+};
+
+void memcons_putc(char c)
+{
+	char *new_output_pos;
+
+	*memcons.output_pos = c;
+	wmb();
+	new_output_pos = memcons.output_pos + 1;
+	if (new_output_pos >= memcons.output_end)
+		new_output_pos = memcons.output_start;
+
+	memcons.output_pos = new_output_pos;
+}
+
+int memcons_getc_poll(void)
+{
+	char c;
+	char *new_input_pos;
+
+	if (*memcons.input_pos) {
+		c = *memcons.input_pos;
+
+		new_input_pos = memcons.input_pos + 1;
+		if (new_input_pos >= memcons.input_end)
+			new_input_pos = memcons.input_start;
+		else if (*new_input_pos == '\0')
+			new_input_pos = memcons.input_start;
+
+		*memcons.input_pos = '\0';
+		wmb();
+		memcons.input_pos = new_input_pos;
+		return c;
+	}
+
+	return -1;
+}
+
+int memcons_getc(void)
+{
+	int c;
+
+	while (1) {
+		c = memcons_getc_poll();
+		if (c == -1)
+			cpu_relax();
+		else
+			break;
+	}
+
+	return c;
+}
+
+void udbg_init_memcons(void)
+{
+	udbg_putc = memcons_putc;
+	udbg_getc = memcons_getc;
+	udbg_getc_poll = memcons_getc_poll;
+}
diff --git a/arch/powerpc/sysdev/xics/ics-opal.c b/arch/powerpc/sysdev/xics/ics-opal.c
index f7e8609df0d5..39d72212655e 100644
--- a/arch/powerpc/sysdev/xics/ics-opal.c
+++ b/arch/powerpc/sysdev/xics/ics-opal.c
@@ -148,7 +148,7 @@ static int ics_opal_set_affinity(struct irq_data *d,
 		       __func__, d->irq, hw_irq, server, rc);
 		return -1;
 	}
-	return 0;
+	return IRQ_SET_MASK_OK;
 }
 
 static struct irq_chip ics_opal_irq_chip = {
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 6a154a91c7e7..685692c94f05 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -108,7 +108,6 @@ config X86
 	select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC)
 	select GENERIC_TIME_VSYSCALL if X86_64
 	select KTIME_SCALAR if X86_32
-	select ALWAYS_USE_PERSISTENT_CLOCK
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
 	select HAVE_CONTEXT_TRACKING if X86_64
diff --git a/arch/x86/include/asm/mc146818rtc.h b/arch/x86/include/asm/mc146818rtc.h
index d354fb781c57..a55c7efcc4ed 100644
--- a/arch/x86/include/asm/mc146818rtc.h
+++ b/arch/x86/include/asm/mc146818rtc.h
@@ -95,8 +95,8 @@ static inline unsigned char current_lock_cmos_reg(void)
 unsigned char rtc_cmos_read(unsigned char addr);
 void rtc_cmos_write(unsigned char val, unsigned char addr);
 
-extern int mach_set_rtc_mmss(unsigned long nowtime);
-extern unsigned long mach_get_cmos_time(void);
+extern int mach_set_rtc_mmss(const struct timespec *now);
+extern void mach_get_cmos_time(struct timespec *now);
 
 #define RTC_IRQ 8
 
diff --git a/arch/x86/include/asm/mrst-vrtc.h b/arch/x86/include/asm/mrst-vrtc.h
index 73668abdbedf..1e69a75412a4 100644
--- a/arch/x86/include/asm/mrst-vrtc.h
+++ b/arch/x86/include/asm/mrst-vrtc.h
@@ -3,7 +3,7 @@
 
 extern unsigned char vrtc_cmos_read(unsigned char reg);
 extern void vrtc_cmos_write(unsigned char val, unsigned char reg);
-extern unsigned long vrtc_get_time(void);
-extern int vrtc_set_mmss(unsigned long nowtime);
+extern void vrtc_get_time(struct timespec *now);
+extern int vrtc_set_mmss(const struct timespec *now);
 
 #endif
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index d8d99222b36a..828a1565ba57 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -142,6 +142,8 @@ struct x86_cpuinit_ops {
 	void (*fixup_cpu_id)(struct cpuinfo_x86 *c, int node);
 };
 
+struct timespec;
+
 /**
  * struct x86_platform_ops - platform specific runtime functions
  * @calibrate_tsc:		calibrate TSC
@@ -156,8 +158,8 @@ struct x86_cpuinit_ops {
  */
 struct x86_platform_ops {
 	unsigned long (*calibrate_tsc)(void);
-	unsigned long (*get_wallclock)(void);
-	int (*set_wallclock)(unsigned long nowtime);
+	void (*get_wallclock)(struct timespec *ts);
+	int (*set_wallclock)(const struct timespec *ts);
 	void (*iommu_shutdown)(void);
 	bool (*is_untracked_pat_range)(u64 start, u64 end);
 	void (*nmi_init)(void);
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index d2c381280e3c..0db81ab511cc 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -48,10 +48,9 @@ static struct pvclock_wall_clock wall_clock;
  * have elapsed since the hypervisor wrote the data. So we try to account for
  * that with system time
  */
-static unsigned long kvm_get_wallclock(void)
+static void kvm_get_wallclock(struct timespec *now)
 {
 	struct pvclock_vcpu_time_info *vcpu_time;
-	struct timespec ts;
 	int low, high;
 	int cpu;
 
@@ -64,14 +63,12 @@ static unsigned long kvm_get_wallclock(void)
 	cpu = smp_processor_id();
 
 	vcpu_time = &hv_clock[cpu].pvti;
-	pvclock_read_wallclock(&wall_clock, vcpu_time, &ts);
+	pvclock_read_wallclock(&wall_clock, vcpu_time, now);
 
 	preempt_enable();
-
-	return ts.tv_sec;
 }
 
-static int kvm_set_wallclock(unsigned long now)
+static int kvm_set_wallclock(const struct timespec *now)
 {
 	return -1;
 }
diff --git a/arch/x86/kernel/microcode_intel_early.c b/arch/x86/kernel/microcode_intel_early.c
index d893e8ed8ac9..2e9e12871c2b 100644
--- a/arch/x86/kernel/microcode_intel_early.c
+++ b/arch/x86/kernel/microcode_intel_early.c
@@ -487,6 +487,7 @@ static inline void show_saved_mc(void)
 #endif
 
 #if defined(CONFIG_MICROCODE_INTEL_EARLY) && defined(CONFIG_HOTPLUG_CPU)
+static DEFINE_MUTEX(x86_cpu_microcode_mutex);
 /*
  * Save this mc into mc_saved_data. So it will be loaded early when a CPU is
  * hot added or resumes.
@@ -507,7 +508,7 @@ int save_mc_for_early(u8 *mc)
 	 * Hold hotplug lock so mc_saved_data is not accessed by a CPU in
 	 * hotplug.
 	 */
-	cpu_hotplug_driver_lock();
+	mutex_lock(&x86_cpu_microcode_mutex);
 
 	mc_saved_count_init = mc_saved_data.mc_saved_count;
 	mc_saved_count = mc_saved_data.mc_saved_count;
@@ -544,7 +545,7 @@ int save_mc_for_early(u8 *mc)
 	}
 
 out:
-	cpu_hotplug_driver_unlock();
+	mutex_unlock(&x86_cpu_microcode_mutex);
 
 	return ret;
 }
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 607af0d4d5ef..4e7a37ff03ab 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -312,6 +312,8 @@ void arch_cpu_idle(void)
 {
 	if (cpuidle_idle_call())
 		x86_idle();
+	else
+		local_irq_enable();
 }
 
 /*
@@ -368,9 +370,6 @@ void amd_e400_remove_cpu(int cpu)
  */
 static void amd_e400_idle(void)
 {
-	if (need_resched())
-		return;
-
 	if (!amd_e400_c1e_detected) {
 		u32 lo, hi;
 
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 198eb201ed3b..0aa29394ed6f 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -38,8 +38,9 @@ EXPORT_SYMBOL(rtc_lock);
  * jump to the next second precisely 500 ms later. Check the Motorola
  * MC146818A or Dallas DS12887 data sheet for details.
  */
-int mach_set_rtc_mmss(unsigned long nowtime)
+int mach_set_rtc_mmss(const struct timespec *now)
 {
+	unsigned long nowtime = now->tv_sec;
 	struct rtc_time tm;
 	int retval = 0;
 
@@ -58,7 +59,7 @@ int mach_set_rtc_mmss(unsigned long nowtime)
 	return retval;
 }
 
-unsigned long mach_get_cmos_time(void)
+void mach_get_cmos_time(struct timespec *now)
 {
 	unsigned int status, year, mon, day, hour, min, sec, century = 0;
 	unsigned long flags;
@@ -107,7 +108,8 @@ unsigned long mach_get_cmos_time(void)
 	} else
 		year += CMOS_YEARS_OFFS;
 
-	return mktime(year, mon, day, hour, min, sec);
+	now->tv_sec = mktime(year, mon, day, hour, min, sec);
+	now->tv_nsec = 0;
 }
 
 /* Routines for accessing the CMOS RAM/RTC. */
@@ -135,18 +137,13 @@ EXPORT_SYMBOL(rtc_cmos_write);
 
 int update_persistent_clock(struct timespec now)
 {
-	return x86_platform.set_wallclock(now.tv_sec);
+	return x86_platform.set_wallclock(&now);
 }
 
 /* not static: needed by APM */
 void read_persistent_clock(struct timespec *ts)
 {
-	unsigned long retval;
-
-	retval = x86_platform.get_wallclock();
-
-	ts->tv_sec = retval;
-	ts->tv_nsec = 0;
+	x86_platform.get_wallclock(ts);
 }
 
 
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 7114c63f047d..8424d5adcfa2 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -882,9 +882,9 @@ int lguest_setup_irq(unsigned int irq)
  * It would be far better for everyone if the Guest had its own clock, but
  * until then the Host gives us the time on every interrupt.
  */
-static unsigned long lguest_get_wallclock(void)
+static void lguest_get_wallclock(struct timespec *now)
 {
-	return lguest_data.time.tv_sec;
+	*now = lguest_data.time;
 }
 
 /*
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index fdc5dca14fb3..eaac1743def7 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -359,7 +359,17 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 }
 
 /*
- * would have hole in the middle or ends, and only ram parts will be mapped.
+ * We need to iterate through the E820 memory map and create direct mappings
+ * for only E820_RAM and E820_KERN_RESERVED regions. We cannot simply
+ * create direct mappings for all pfns from [0 to max_low_pfn) and
+ * [4GB to max_pfn) because of possible memory holes in high addresses
+ * that cannot be marked as UC by fixed/variable range MTRRs.
+ * Depending on the alignment of E820 ranges, this may possibly result
+ * in using smaller size (i.e. 4K instead of 2M or 1G) page tables.
+ *
+ * init_mem_mapping() calls init_range_memory_mapping() with big range.
+ * That range would have hole in the middle or ends, and only ram parts
+ * will be mapped in init_range_memory_mapping().
  */
 static unsigned long __init init_range_memory_mapping(
 					   unsigned long r_start,
@@ -419,6 +429,13 @@ void __init init_mem_mapping(void)
 	max_pfn_mapped = 0; /* will get exact value next */
 	min_pfn_mapped = real_end >> PAGE_SHIFT;
 	last_start = start = real_end;
+
+	/*
+	 * We start from the top (end of memory) and go to the bottom.
+	 * The memblock_find_in_range() gets us a block of RAM from the
+	 * end of RAM in [min_pfn_mapped, max_pfn_mapped) used as new pages
+	 * for page table.
+	 */
 	while (last_start > ISA_END_ADDRESS) {
 		if (last_start > step_size) {
 			start = round_down(last_start - 1, step_size);
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 55856b2310d3..dd3b82530145 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -352,8 +352,9 @@ static efi_status_t __init phys_efi_get_time(efi_time_t *tm,
 	return status;
 }
 
-int efi_set_rtc_mmss(unsigned long nowtime)
+int efi_set_rtc_mmss(const struct timespec *now)
 {
+	unsigned long nowtime = now->tv_sec;
 	efi_status_t 	status;
 	efi_time_t 	eft;
 	efi_time_cap_t 	cap;
@@ -388,7 +389,7 @@ int efi_set_rtc_mmss(unsigned long nowtime)
 	return 0;
 }
 
-unsigned long efi_get_time(void)
+void efi_get_time(struct timespec *now)
 {
 	efi_status_t status;
 	efi_time_t eft;
@@ -398,8 +399,9 @@ unsigned long efi_get_time(void)
 	if (status != EFI_SUCCESS)
 		pr_err("Oops: efitime: can't read time!\n");
 
-	return mktime(eft.year, eft.month, eft.day, eft.hour,
-		      eft.minute, eft.second);
+	now->tv_sec = mktime(eft.year, eft.month, eft.day, eft.hour,
+			     eft.minute, eft.second);
+	now->tv_nsec = 0;
 }
 
 /*
diff --git a/arch/x86/platform/mrst/vrtc.c b/arch/x86/platform/mrst/vrtc.c
index d62b0a3b5c14..5e355b134ba4 100644
--- a/arch/x86/platform/mrst/vrtc.c
+++ b/arch/x86/platform/mrst/vrtc.c
@@ -56,7 +56,7 @@ void vrtc_cmos_write(unsigned char val, unsigned char reg)
 }
 EXPORT_SYMBOL_GPL(vrtc_cmos_write);
 
-unsigned long vrtc_get_time(void)
+void vrtc_get_time(struct timespec *now)
 {
 	u8 sec, min, hour, mday, mon;
 	unsigned long flags;
@@ -82,17 +82,18 @@ unsigned long vrtc_get_time(void)
 	printk(KERN_INFO "vRTC: sec: %d min: %d hour: %d day: %d "
 		"mon: %d year: %d\n", sec, min, hour, mday, mon, year);
 
-	return mktime(year, mon, mday, hour, min, sec);
+	now->tv_sec = mktime(year, mon, mday, hour, min, sec);
+	now->tv_nsec = 0;
 }
 
-int vrtc_set_mmss(unsigned long nowtime)
+int vrtc_set_mmss(const struct timespec *now)
 {
 	unsigned long flags;
 	struct rtc_time tm;
 	int year;
 	int retval = 0;
 
-	rtc_time_to_tm(nowtime, &tm);
+	rtc_time_to_tm(now->tv_sec, &tm);
 	if (!rtc_valid_tm(&tm) && tm.tm_year >= 72) {
 		/*
 		 * tm.year is the number of years since 1900, and the
@@ -110,7 +111,7 @@ int vrtc_set_mmss(unsigned long nowtime)
 	} else {
 		printk(KERN_ERR
 		       "%s: Invalid vRTC value: write of %lx to vRTC failed\n",
-			__FUNCTION__, nowtime);
+			__FUNCTION__, now->tv_sec);
 		retval = -EINVAL;
 	}
 	return retval;
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 3d88bfdf9e1c..a1947ac2da82 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -191,32 +191,25 @@ static void xen_read_wallclock(struct timespec *ts)
 	put_cpu_var(xen_vcpu);
 }
 
-static unsigned long xen_get_wallclock(void)
+static void xen_get_wallclock(struct timespec *now)
 {
-	struct timespec ts;
-
-	xen_read_wallclock(&ts);
-	return ts.tv_sec;
+	xen_read_wallclock(now);
 }
 
-static int xen_set_wallclock(unsigned long now)
+static int xen_set_wallclock(const struct timespec *now)
 {
 	struct xen_platform_op op;
-	int rc;
 
 	/* do nothing for domU */
 	if (!xen_initial_domain())
 		return -1;
 
 	op.cmd = XENPF_settime;
-	op.u.settime.secs = now;
-	op.u.settime.nsecs = 0;
+	op.u.settime.secs = now->tv_sec;
+	op.u.settime.nsecs = now->tv_nsec;
 	op.u.settime.system_time = xen_clocksource_read();
 
-	rc = HYPERVISOR_dom0_op(&op);
-	WARN(rc != 0, "XENPF_settime failed: now=%ld\n", now);
-
-	return rc;
+	return HYPERVISOR_dom0_op(&op);
 }
 
 static struct clocksource xen_clocksource __read_mostly = {
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index ca63104136e0..d6d314027b5d 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -55,6 +55,39 @@
 #define	SECTOR_SHIFT	9
 #define	SECTOR_SIZE	(1ULL << SECTOR_SHIFT)
 
+/*
+ * Increment the given counter and return its updated value.
+ * If the counter is already 0 it will not be incremented.
+ * If the counter is already at its maximum value returns
+ * -EINVAL without updating it.
+ */
+static int atomic_inc_return_safe(atomic_t *v)
+{
+	unsigned int counter;
+
+	counter = (unsigned int)__atomic_add_unless(v, 1, 0);
+	if (counter <= (unsigned int)INT_MAX)
+		return (int)counter;
+
+	atomic_dec(v);
+
+	return -EINVAL;
+}
+
+/* Decrement the counter.  Return the resulting value, or -EINVAL */
+static int atomic_dec_return_safe(atomic_t *v)
+{
+	int counter;
+
+	counter = atomic_dec_return(v);
+	if (counter >= 0)
+		return counter;
+
+	atomic_inc(v);
+
+	return -EINVAL;
+}
+
 #define RBD_DRV_NAME "rbd"
 #define RBD_DRV_NAME_LONG "rbd (rados block device)"
 
@@ -100,21 +133,20 @@
  * block device image metadata (in-memory version)
  */
 struct rbd_image_header {
-	/* These four fields never change for a given rbd image */
+	/* These six fields never change for a given rbd image */
 	char *object_prefix;
-	u64 features;
 	__u8 obj_order;
 	__u8 crypt_type;
 	__u8 comp_type;
+	u64 stripe_unit;
+	u64 stripe_count;
+	u64 features;		/* Might be changeable someday? */
 
 	/* The remaining fields need to be updated occasionally */
 	u64 image_size;
 	struct ceph_snap_context *snapc;
-	char *snap_names;
-	u64 *snap_sizes;
-
-	u64 stripe_unit;
-	u64 stripe_count;
+	char *snap_names;	/* format 1 only */
+	u64 *snap_sizes;	/* format 1 only */
 };
 
 /*
@@ -225,6 +257,7 @@ struct rbd_obj_request {
 		};
 	};
 	struct page		**copyup_pages;
+	u32			copyup_page_count;
 
 	struct ceph_osd_request	*osd_req;
 
@@ -257,6 +290,7 @@ struct rbd_img_request {
 		struct rbd_obj_request	*obj_request;	/* obj req initiator */
 	};
 	struct page		**copyup_pages;
+	u32			copyup_page_count;
 	spinlock_t		completion_lock;/* protects next_completion */
 	u32			next_completion;
 	rbd_img_callback_t	callback;
@@ -311,6 +345,7 @@ struct rbd_device {
 
 	struct rbd_spec		*parent_spec;
 	u64			parent_overlap;
+	atomic_t		parent_ref;
 	struct rbd_device	*parent;
 
 	/* protects updating the header */
@@ -359,7 +394,8 @@ static ssize_t rbd_add(struct bus_type *bus, const char *buf,
 		       size_t count);
 static ssize_t rbd_remove(struct bus_type *bus, const char *buf,
 			  size_t count);
-static int rbd_dev_image_probe(struct rbd_device *rbd_dev);
+static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping);
+static void rbd_spec_put(struct rbd_spec *spec);
 
 static struct bus_attribute rbd_bus_attrs[] = {
 	__ATTR(add, S_IWUSR, NULL, rbd_add),
@@ -426,7 +462,8 @@ static void rbd_img_parent_read(struct rbd_obj_request *obj_request);
 static void rbd_dev_remove_parent(struct rbd_device *rbd_dev);
 
 static int rbd_dev_refresh(struct rbd_device *rbd_dev);
-static int rbd_dev_v2_refresh(struct rbd_device *rbd_dev);
+static int rbd_dev_v2_header_onetime(struct rbd_device *rbd_dev);
+static int rbd_dev_v2_header_info(struct rbd_device *rbd_dev);
 static const char *rbd_dev_v2_snap_name(struct rbd_device *rbd_dev,
 					u64 snap_id);
 static int _rbd_dev_v2_snap_size(struct rbd_device *rbd_dev, u64 snap_id,
@@ -726,88 +763,123 @@ static bool rbd_dev_ondisk_valid(struct rbd_image_header_ondisk *ondisk)
 }
 
 /*
- * Create a new header structure, translate header format from the on-disk
- * header.
+ * Fill an rbd image header with information from the given format 1
+ * on-disk header.
  */
-static int rbd_header_from_disk(struct rbd_image_header *header,
+static int rbd_header_from_disk(struct rbd_device *rbd_dev,
 				 struct rbd_image_header_ondisk *ondisk)
 {
+	struct rbd_image_header *header = &rbd_dev->header;
+	bool first_time = header->object_prefix == NULL;
+	struct ceph_snap_context *snapc;
+	char *object_prefix = NULL;
+	char *snap_names = NULL;
+	u64 *snap_sizes = NULL;
 	u32 snap_count;
-	size_t len;
 	size_t size;
+	int ret = -ENOMEM;
 	u32 i;
 
-	memset(header, 0, sizeof (*header));
+	/* Allocate this now to avoid having to handle failure below */
 
-	snap_count = le32_to_cpu(ondisk->snap_count);
+	if (first_time) {
+		size_t len;
 
-	len = strnlen(ondisk->object_prefix, sizeof (ondisk->object_prefix));
-	header->object_prefix = kmalloc(len + 1, GFP_KERNEL);
-	if (!header->object_prefix)
-		return -ENOMEM;
-	memcpy(header->object_prefix, ondisk->object_prefix, len);
-	header->object_prefix[len] = '\0';
+		len = strnlen(ondisk->object_prefix,
+				sizeof (ondisk->object_prefix));
+		object_prefix = kmalloc(len + 1, GFP_KERNEL);
+		if (!object_prefix)
+			return -ENOMEM;
+		memcpy(object_prefix, ondisk->object_prefix, len);
+		object_prefix[len] = '\0';
+	}
 
+	/* Allocate the snapshot context and fill it in */
+
+	snap_count = le32_to_cpu(ondisk->snap_count);
+	snapc = ceph_create_snap_context(snap_count, GFP_KERNEL);
+	if (!snapc)
+		goto out_err;
+	snapc->seq = le64_to_cpu(ondisk->snap_seq);
 	if (snap_count) {
+		struct rbd_image_snap_ondisk *snaps;
 		u64 snap_names_len = le64_to_cpu(ondisk->snap_names_len);
 
-		/* Save a copy of the snapshot names */
+		/* We'll keep a copy of the snapshot names... */
 
-		if (snap_names_len > (u64) SIZE_MAX)
-			return -EIO;
-		header->snap_names = kmalloc(snap_names_len, GFP_KERNEL);
-		if (!header->snap_names)
+		if (snap_names_len > (u64)SIZE_MAX)
+			goto out_2big;
+		snap_names = kmalloc(snap_names_len, GFP_KERNEL);
+		if (!snap_names)
 			goto out_err;
+
+		/* ...as well as the array of their sizes. */
+
+		size = snap_count * sizeof (*header->snap_sizes);
+		snap_sizes = kmalloc(size, GFP_KERNEL);
+		if (!snap_sizes)
+			goto out_err;
+
 		/*
-		 * Note that rbd_dev_v1_header_read() guarantees
-		 * the ondisk buffer we're working with has
+		 * Copy the names, and fill in each snapshot's id
+		 * and size.
+		 *
+		 * Note that rbd_dev_v1_header_info() guarantees the
+		 * ondisk buffer we're working with has
 		 * snap_names_len bytes beyond the end of the
 		 * snapshot id array, this memcpy() is safe.
 		 */
-		memcpy(header->snap_names, &ondisk->snaps[snap_count],
-			snap_names_len);
+		memcpy(snap_names, &ondisk->snaps[snap_count], snap_names_len);
+		snaps = ondisk->snaps;
+		for (i = 0; i < snap_count; i++) {
+			snapc->snaps[i] = le64_to_cpu(snaps[i].id);
+			snap_sizes[i] = le64_to_cpu(snaps[i].image_size);
+		}
+	}
 
-		/* Record each snapshot's size */
+	/* We won't fail any more, fill in the header */
 
-		size = snap_count * sizeof (*header->snap_sizes);
-		header->snap_sizes = kmalloc(size, GFP_KERNEL);
-		if (!header->snap_sizes)
-			goto out_err;
-		for (i = 0; i < snap_count; i++)
-			header->snap_sizes[i] =
-				le64_to_cpu(ondisk->snaps[i].image_size);
+	down_write(&rbd_dev->header_rwsem);
+	if (first_time) {
+		header->object_prefix = object_prefix;
+		header->obj_order = ondisk->options.order;
+		header->crypt_type = ondisk->options.crypt_type;
+		header->comp_type = ondisk->options.comp_type;
+		/* The rest aren't used for format 1 images */
+		header->stripe_unit = 0;
+		header->stripe_count = 0;
+		header->features = 0;
 	} else {
-		header->snap_names = NULL;
-		header->snap_sizes = NULL;
+		ceph_put_snap_context(header->snapc);
+		kfree(header->snap_names);
+		kfree(header->snap_sizes);
 	}
 
-	header->features = 0;	/* No features support in v1 images */
-	header->obj_order = ondisk->options.order;
-	header->crypt_type = ondisk->options.crypt_type;
-	header->comp_type = ondisk->options.comp_type;
-
-	/* Allocate and fill in the snapshot context */
+	/* The remaining fields always get updated (when we refresh) */
 
 	header->image_size = le64_to_cpu(ondisk->image_size);
+	header->snapc = snapc;
+	header->snap_names = snap_names;
+	header->snap_sizes = snap_sizes;
 
-	header->snapc = ceph_create_snap_context(snap_count, GFP_KERNEL);
-	if (!header->snapc)
-		goto out_err;
-	header->snapc->seq = le64_to_cpu(ondisk->snap_seq);
-	for (i = 0; i < snap_count; i++)
-		header->snapc->snaps[i] = le64_to_cpu(ondisk->snaps[i].id);
+	/* Make sure mapping size is consistent with header info */
 
-	return 0;
+	if (rbd_dev->spec->snap_id == CEPH_NOSNAP || first_time)
+		if (rbd_dev->mapping.size != header->image_size)
+			rbd_dev->mapping.size = header->image_size;
+
+	up_write(&rbd_dev->header_rwsem);
 
+	return 0;
+out_2big:
+	ret = -EIO;
 out_err:
-	kfree(header->snap_sizes);
-	header->snap_sizes = NULL;
-	kfree(header->snap_names);
-	header->snap_names = NULL;
-	kfree(header->object_prefix);
-	header->object_prefix = NULL;
+	kfree(snap_sizes);
+	kfree(snap_names);
+	ceph_put_snap_context(snapc);
+	kfree(object_prefix);
 
-	return -ENOMEM;
+	return ret;
 }
 
 static const char *_rbd_dev_v1_snap_name(struct rbd_device *rbd_dev, u32 which)
@@ -934,20 +1006,11 @@ static int rbd_snap_features(struct rbd_device *rbd_dev, u64 snap_id,
 
 static int rbd_dev_mapping_set(struct rbd_device *rbd_dev)
 {
-	const char *snap_name = rbd_dev->spec->snap_name;
-	u64 snap_id;
+	u64 snap_id = rbd_dev->spec->snap_id;
 	u64 size = 0;
 	u64 features = 0;
 	int ret;
 
-	if (strcmp(snap_name, RBD_SNAP_HEAD_NAME)) {
-		snap_id = rbd_snap_id_by_name(rbd_dev, snap_name);
-		if (snap_id == CEPH_NOSNAP)
-			return -ENOENT;
-	} else {
-		snap_id = CEPH_NOSNAP;
-	}
-
 	ret = rbd_snap_size(rbd_dev, snap_id, &size);
 	if (ret)
 		return ret;
@@ -958,11 +1021,6 @@ static int rbd_dev_mapping_set(struct rbd_device *rbd_dev)
 	rbd_dev->mapping.size = size;
 	rbd_dev->mapping.features = features;
 
-	/* If we are mapping a snapshot it must be marked read-only */
-
-	if (snap_id != CEPH_NOSNAP)
-		rbd_dev->mapping.read_only = true;
-
 	return 0;
 }
 
@@ -970,14 +1028,6 @@ static void rbd_dev_mapping_clear(struct rbd_device *rbd_dev)
 {
 	rbd_dev->mapping.size = 0;
 	rbd_dev->mapping.features = 0;
-	rbd_dev->mapping.read_only = true;
-}
-
-static void rbd_dev_clear_mapping(struct rbd_device *rbd_dev)
-{
-	rbd_dev->mapping.size = 0;
-	rbd_dev->mapping.features = 0;
-	rbd_dev->mapping.read_only = true;
 }
 
 static const char *rbd_segment_name(struct rbd_device *rbd_dev, u64 offset)
@@ -1342,20 +1392,18 @@ static void rbd_obj_request_put(struct rbd_obj_request *obj_request)
 	kref_put(&obj_request->kref, rbd_obj_request_destroy);
 }
 
-static void rbd_img_request_get(struct rbd_img_request *img_request)
-{
-	dout("%s: img %p (was %d)\n", __func__, img_request,
-		atomic_read(&img_request->kref.refcount));
-	kref_get(&img_request->kref);
-}
-
+static bool img_request_child_test(struct rbd_img_request *img_request);
+static void rbd_parent_request_destroy(struct kref *kref);
 static void rbd_img_request_destroy(struct kref *kref);
 static void rbd_img_request_put(struct rbd_img_request *img_request)
 {
 	rbd_assert(img_request != NULL);
 	dout("%s: img %p (was %d)\n", __func__, img_request,
 		atomic_read(&img_request->kref.refcount));
-	kref_put(&img_request->kref, rbd_img_request_destroy);
+	if (img_request_child_test(img_request))
+		kref_put(&img_request->kref, rbd_parent_request_destroy);
+	else
+		kref_put(&img_request->kref, rbd_img_request_destroy);
 }
 
 static inline void rbd_img_obj_request_add(struct rbd_img_request *img_request,
@@ -1472,6 +1520,12 @@ static void img_request_child_set(struct rbd_img_request *img_request)
 	smp_mb();
 }
 
+static void img_request_child_clear(struct rbd_img_request *img_request)
+{
+	clear_bit(IMG_REQ_CHILD, &img_request->flags);
+	smp_mb();
+}
+
 static bool img_request_child_test(struct rbd_img_request *img_request)
 {
 	smp_mb();
@@ -1484,6 +1538,12 @@ static void img_request_layered_set(struct rbd_img_request *img_request)
 	smp_mb();
 }
 
+static void img_request_layered_clear(struct rbd_img_request *img_request)
+{
+	clear_bit(IMG_REQ_LAYERED, &img_request->flags);
+	smp_mb();
+}
+
 static bool img_request_layered_test(struct rbd_img_request *img_request)
 {
 	smp_mb();
@@ -1827,6 +1887,74 @@ static void rbd_obj_request_destroy(struct kref *kref)
 	kmem_cache_free(rbd_obj_request_cache, obj_request);
 }
 
+/* It's OK to call this for a device with no parent */
+
+static void rbd_spec_put(struct rbd_spec *spec);
+static void rbd_dev_unparent(struct rbd_device *rbd_dev)
+{
+	rbd_dev_remove_parent(rbd_dev);
+	rbd_spec_put(rbd_dev->parent_spec);
+	rbd_dev->parent_spec = NULL;
+	rbd_dev->parent_overlap = 0;
+}
+
+/*
+ * Parent image reference counting is used to determine when an
+ * image's parent fields can be safely torn down--after there are no
+ * more in-flight requests to the parent image.  When the last
+ * reference is dropped, cleaning them up is safe.
+ */
+static void rbd_dev_parent_put(struct rbd_device *rbd_dev)
+{
+	int counter;
+
+	if (!rbd_dev->parent_spec)
+		return;
+
+	counter = atomic_dec_return_safe(&rbd_dev->parent_ref);
+	if (counter > 0)
+		return;
+
+	/* Last reference; clean up parent data structures */
+
+	if (!counter)
+		rbd_dev_unparent(rbd_dev);
+	else
+		rbd_warn(rbd_dev, "parent reference underflow\n");
+}
+
+/*
+ * If an image has a non-zero parent overlap, get a reference to its
+ * parent.
+ *
+ * We must get the reference before checking for the overlap to
+ * coordinate properly with zeroing the parent overlap in
+ * rbd_dev_v2_parent_info() when an image gets flattened.  We
+ * drop it again if there is no overlap.
+ *
+ * Returns true if the rbd device has a parent with a non-zero
+ * overlap and a reference for it was successfully taken, or
+ * false otherwise.
+ */
+static bool rbd_dev_parent_get(struct rbd_device *rbd_dev)
+{
+	int counter;
+
+	if (!rbd_dev->parent_spec)
+		return false;
+
+	counter = atomic_inc_return_safe(&rbd_dev->parent_ref);
+	if (counter > 0 && rbd_dev->parent_overlap)
+		return true;
+
+	/* Image was flattened, but parent is not yet torn down */
+
+	if (counter < 0)
+		rbd_warn(rbd_dev, "parent reference overflow\n");
+
+	return false;
+}
+
 /*
  * Caller is responsible for filling in the list of object requests
  * that comprises the image request, and the Linux request pointer
@@ -1835,8 +1963,7 @@ static void rbd_obj_request_destroy(struct kref *kref)
 static struct rbd_img_request *rbd_img_request_create(
 					struct rbd_device *rbd_dev,
 					u64 offset, u64 length,
-					bool write_request,
-					bool child_request)
+					bool write_request)
 {
 	struct rbd_img_request *img_request;
 
@@ -1861,9 +1988,7 @@ static struct rbd_img_request *rbd_img_request_create(
 	} else {
 		img_request->snap_id = rbd_dev->spec->snap_id;
 	}
-	if (child_request)
-		img_request_child_set(img_request);
-	if (rbd_dev->parent_spec)
+	if (rbd_dev_parent_get(rbd_dev))
 		img_request_layered_set(img_request);
 	spin_lock_init(&img_request->completion_lock);
 	img_request->next_completion = 0;
@@ -1873,9 +1998,6 @@ static struct rbd_img_request *rbd_img_request_create(
 	INIT_LIST_HEAD(&img_request->obj_requests);
 	kref_init(&img_request->kref);
 
-	rbd_img_request_get(img_request);	/* Avoid a warning */
-	rbd_img_request_put(img_request);	/* TEMPORARY */
-
 	dout("%s: rbd_dev %p %s %llu/%llu -> img %p\n", __func__, rbd_dev,
 		write_request ? "write" : "read", offset, length,
 		img_request);
@@ -1897,15 +2019,54 @@ static void rbd_img_request_destroy(struct kref *kref)
 		rbd_img_obj_request_del(img_request, obj_request);
 	rbd_assert(img_request->obj_request_count == 0);
 
+	if (img_request_layered_test(img_request)) {
+		img_request_layered_clear(img_request);
+		rbd_dev_parent_put(img_request->rbd_dev);
+	}
+
 	if (img_request_write_test(img_request))
 		ceph_put_snap_context(img_request->snapc);
 
-	if (img_request_child_test(img_request))
-		rbd_obj_request_put(img_request->obj_request);
-
 	kmem_cache_free(rbd_img_request_cache, img_request);
 }
 
+static struct rbd_img_request *rbd_parent_request_create(
+					struct rbd_obj_request *obj_request,
+					u64 img_offset, u64 length)
+{
+	struct rbd_img_request *parent_request;
+	struct rbd_device *rbd_dev;
+
+	rbd_assert(obj_request->img_request);
+	rbd_dev = obj_request->img_request->rbd_dev;
+
+	parent_request = rbd_img_request_create(rbd_dev->parent,
+						img_offset, length, false);
+	if (!parent_request)
+		return NULL;
+
+	img_request_child_set(parent_request);
+	rbd_obj_request_get(obj_request);
+	parent_request->obj_request = obj_request;
+
+	return parent_request;
+}
+
+static void rbd_parent_request_destroy(struct kref *kref)
+{
+	struct rbd_img_request *parent_request;
+	struct rbd_obj_request *orig_request;
+
+	parent_request = container_of(kref, struct rbd_img_request, kref);
+	orig_request = parent_request->obj_request;
+
+	parent_request->obj_request = NULL;
+	rbd_obj_request_put(orig_request);
+	img_request_child_clear(parent_request);
+
+	rbd_img_request_destroy(kref);
+}
+
 static bool rbd_img_obj_end_request(struct rbd_obj_request *obj_request)
 {
 	struct rbd_img_request *img_request;
@@ -2114,7 +2275,7 @@ rbd_img_obj_copyup_callback(struct rbd_obj_request *obj_request)
 {
 	struct rbd_img_request *img_request;
 	struct rbd_device *rbd_dev;
-	u64 length;
+	struct page **pages;
 	u32 page_count;
 
 	rbd_assert(obj_request->type == OBJ_REQUEST_BIO);
@@ -2124,12 +2285,14 @@ rbd_img_obj_copyup_callback(struct rbd_obj_request *obj_request)
 
 	rbd_dev = img_request->rbd_dev;
 	rbd_assert(rbd_dev);
-	length = (u64)1 << rbd_dev->header.obj_order;
-	page_count = (u32)calc_pages_for(0, length);
 
-	rbd_assert(obj_request->copyup_pages);
-	ceph_release_page_vector(obj_request->copyup_pages, page_count);
+	pages = obj_request->copyup_pages;
+	rbd_assert(pages != NULL);
 	obj_request->copyup_pages = NULL;
+	page_count = obj_request->copyup_page_count;
+	rbd_assert(page_count);
+	obj_request->copyup_page_count = 0;
+	ceph_release_page_vector(pages, page_count);
 
 	/*
 	 * We want the transfer count to reflect the size of the
@@ -2153,9 +2316,11 @@ rbd_img_obj_parent_read_full_callback(struct rbd_img_request *img_request)
 	struct ceph_osd_client *osdc;
 	struct rbd_device *rbd_dev;
 	struct page **pages;
-	int result;
-	u64 obj_size;
-	u64 xferred;
+	u32 page_count;
+	int img_result;
+	u64 parent_length;
+	u64 offset;
+	u64 length;
 
 	rbd_assert(img_request_child_test(img_request));
 
@@ -2164,46 +2329,74 @@ rbd_img_obj_parent_read_full_callback(struct rbd_img_request *img_request)
 	pages = img_request->copyup_pages;
 	rbd_assert(pages != NULL);
 	img_request->copyup_pages = NULL;
+	page_count = img_request->copyup_page_count;
+	rbd_assert(page_count);
+	img_request->copyup_page_count = 0;
 
 	orig_request = img_request->obj_request;
 	rbd_assert(orig_request != NULL);
-	rbd_assert(orig_request->type == OBJ_REQUEST_BIO);
-	result = img_request->result;
-	obj_size = img_request->length;
-	xferred = img_request->xferred;
+	rbd_assert(obj_request_type_valid(orig_request->type));
+	img_result = img_request->result;
+	parent_length = img_request->length;
+	rbd_assert(parent_length == img_request->xferred);
+	rbd_img_request_put(img_request);
 
-	rbd_dev = img_request->rbd_dev;
+	rbd_assert(orig_request->img_request);
+	rbd_dev = orig_request->img_request->rbd_dev;
 	rbd_assert(rbd_dev);
-	rbd_assert(obj_size == (u64)1 << rbd_dev->header.obj_order);
 
-	rbd_img_request_put(img_request);
+	/*
+	 * If the overlap has become 0 (most likely because the
+	 * image has been flattened) we need to free the pages
+	 * and re-submit the original write request.
+	 */
+	if (!rbd_dev->parent_overlap) {
+		struct ceph_osd_client *osdc;
 
-	if (result)
-		goto out_err;
+		ceph_release_page_vector(pages, page_count);
+		osdc = &rbd_dev->rbd_client->client->osdc;
+		img_result = rbd_obj_request_submit(osdc, orig_request);
+		if (!img_result)
+			return;
+	}
 
-	/* Allocate the new copyup osd request for the original request */
+	if (img_result)
+		goto out_err;
 
-	result = -ENOMEM;
-	rbd_assert(!orig_request->osd_req);
+	/*
+	 * The original osd request is of no use to use any more.
+	 * We need a new one that can hold the two ops in a copyup
+	 * request.  Allocate the new copyup osd request for the
+	 * original request, and release the old one.
+	 */
+	img_result = -ENOMEM;
 	osd_req = rbd_osd_req_create_copyup(orig_request);
 	if (!osd_req)
 		goto out_err;
+	rbd_osd_req_destroy(orig_request->osd_req);
 	orig_request->osd_req = osd_req;
 	orig_request->copyup_pages = pages;
+	orig_request->copyup_page_count = page_count;
 
 	/* Initialize the copyup op */
 
 	osd_req_op_cls_init(osd_req, 0, CEPH_OSD_OP_CALL, "rbd", "copyup");
-	osd_req_op_cls_request_data_pages(osd_req, 0, pages, obj_size, 0,
+	osd_req_op_cls_request_data_pages(osd_req, 0, pages, parent_length, 0,
 						false, false);
 
 	/* Then the original write request op */
 
+	offset = orig_request->offset;
+	length = orig_request->length;
 	osd_req_op_extent_init(osd_req, 1, CEPH_OSD_OP_WRITE,
-					orig_request->offset,
-					orig_request->length, 0, 0);
-	osd_req_op_extent_osd_data_bio(osd_req, 1, orig_request->bio_list,
-					orig_request->length);
+					offset, length, 0, 0);
+	if (orig_request->type == OBJ_REQUEST_BIO)
+		osd_req_op_extent_osd_data_bio(osd_req, 1,
+					orig_request->bio_list, length);
+	else
+		osd_req_op_extent_osd_data_pages(osd_req, 1,
+					orig_request->pages, length,
+					offset & ~PAGE_MASK, false, false);
 
 	rbd_osd_req_format_write(orig_request);
 
@@ -2211,13 +2404,13 @@ rbd_img_obj_parent_read_full_callback(struct rbd_img_request *img_request)
 
 	orig_request->callback = rbd_img_obj_copyup_callback;
 	osdc = &rbd_dev->rbd_client->client->osdc;
-	result = rbd_obj_request_submit(osdc, orig_request);
-	if (!result)
+	img_result = rbd_obj_request_submit(osdc, orig_request);
+	if (!img_result)
 		return;
 out_err:
 	/* Record the error code and complete the request */
 
-	orig_request->result = result;
+	orig_request->result = img_result;
 	orig_request->xferred = 0;
 	obj_request_done_set(orig_request);
 	rbd_obj_request_complete(orig_request);
@@ -2249,7 +2442,7 @@ static int rbd_img_obj_parent_read_full(struct rbd_obj_request *obj_request)
 	int result;
 
 	rbd_assert(obj_request_img_data_test(obj_request));
-	rbd_assert(obj_request->type == OBJ_REQUEST_BIO);
+	rbd_assert(obj_request_type_valid(obj_request->type));
 
 	img_request = obj_request->img_request;
 	rbd_assert(img_request != NULL);
@@ -2257,15 +2450,6 @@ static int rbd_img_obj_parent_read_full(struct rbd_obj_request *obj_request)
 	rbd_assert(rbd_dev->parent != NULL);
 
 	/*
-	 * First things first.  The original osd request is of no
-	 * use to use any more, we'll need a new one that can hold
-	 * the two ops in a copyup request.  We'll get that later,
-	 * but for now we can release the old one.
-	 */
-	rbd_osd_req_destroy(obj_request->osd_req);
-	obj_request->osd_req = NULL;
-
-	/*
 	 * Determine the byte range covered by the object in the
 	 * child image to which the original request was to be sent.
 	 */
@@ -2295,18 +2479,16 @@ static int rbd_img_obj_parent_read_full(struct rbd_obj_request *obj_request)
 	}
 
 	result = -ENOMEM;
-	parent_request = rbd_img_request_create(rbd_dev->parent,
-						img_offset, length,
-						false, true);
+	parent_request = rbd_parent_request_create(obj_request,
+						img_offset, length);
 	if (!parent_request)
 		goto out_err;
-	rbd_obj_request_get(obj_request);
-	parent_request->obj_request = obj_request;
 
 	result = rbd_img_request_fill(parent_request, OBJ_REQUEST_PAGES, pages);
 	if (result)
 		goto out_err;
 	parent_request->copyup_pages = pages;
+	parent_request->copyup_page_count = page_count;
 
 	parent_request->callback = rbd_img_obj_parent_read_full_callback;
 	result = rbd_img_request_submit(parent_request);
@@ -2314,6 +2496,7 @@ static int rbd_img_obj_parent_read_full(struct rbd_obj_request *obj_request)
 		return 0;
 
 	parent_request->copyup_pages = NULL;
+	parent_request->copyup_page_count = 0;
 	parent_request->obj_request = NULL;
 	rbd_obj_request_put(obj_request);
 out_err:
@@ -2331,6 +2514,7 @@ out_err:
 static void rbd_img_obj_exists_callback(struct rbd_obj_request *obj_request)
 {
 	struct rbd_obj_request *orig_request;
+	struct rbd_device *rbd_dev;
 	int result;
 
 	rbd_assert(!obj_request_img_data_test(obj_request));
@@ -2353,8 +2537,21 @@ static void rbd_img_obj_exists_callback(struct rbd_obj_request *obj_request)
 		obj_request->xferred, obj_request->length);
 	rbd_obj_request_put(obj_request);
 
-	rbd_assert(orig_request);
-	rbd_assert(orig_request->img_request);
+	/*
+	 * If the overlap has become 0 (most likely because the
+	 * image has been flattened) we need to free the pages
+	 * and re-submit the original write request.
+	 */
+	rbd_dev = orig_request->img_request->rbd_dev;
+	if (!rbd_dev->parent_overlap) {
+		struct ceph_osd_client *osdc;
+
+		rbd_obj_request_put(orig_request);
+		osdc = &rbd_dev->rbd_client->client->osdc;
+		result = rbd_obj_request_submit(osdc, orig_request);
+		if (!result)
+			return;
+	}
 
 	/*
 	 * Our only purpose here is to determine whether the object
@@ -2512,14 +2709,36 @@ static void rbd_img_parent_read_callback(struct rbd_img_request *img_request)
 	struct rbd_obj_request *obj_request;
 	struct rbd_device *rbd_dev;
 	u64 obj_end;
+	u64 img_xferred;
+	int img_result;
 
 	rbd_assert(img_request_child_test(img_request));
 
+	/* First get what we need from the image request and release it */
+
 	obj_request = img_request->obj_request;
+	img_xferred = img_request->xferred;
+	img_result = img_request->result;
+	rbd_img_request_put(img_request);
+
+	/*
+	 * If the overlap has become 0 (most likely because the
+	 * image has been flattened) we need to re-submit the
+	 * original request.
+	 */
 	rbd_assert(obj_request);
 	rbd_assert(obj_request->img_request);
+	rbd_dev = obj_request->img_request->rbd_dev;
+	if (!rbd_dev->parent_overlap) {
+		struct ceph_osd_client *osdc;
+
+		osdc = &rbd_dev->rbd_client->client->osdc;
+		img_result = rbd_obj_request_submit(osdc, obj_request);
+		if (!img_result)
+			return;
+	}
 
-	obj_request->result = img_request->result;
+	obj_request->result = img_result;
 	if (obj_request->result)
 		goto out;
 
@@ -2532,7 +2751,6 @@ static void rbd_img_parent_read_callback(struct rbd_img_request *img_request)
 	 */
 	rbd_assert(obj_request->img_offset < U64_MAX - obj_request->length);
 	obj_end = obj_request->img_offset + obj_request->length;
-	rbd_dev = obj_request->img_request->rbd_dev;
 	if (obj_end > rbd_dev->parent_overlap) {
 		u64 xferred = 0;
 
@@ -2540,43 +2758,39 @@ static void rbd_img_parent_read_callback(struct rbd_img_request *img_request)
 			xferred = rbd_dev->parent_overlap -
 					obj_request->img_offset;
 
-		obj_request->xferred = min(img_request->xferred, xferred);
+		obj_request->xferred = min(img_xferred, xferred);
 	} else {
-		obj_request->xferred = img_request->xferred;
+		obj_request->xferred = img_xferred;
 	}
 out:
-	rbd_img_request_put(img_request);
 	rbd_img_obj_request_read_callback(obj_request);
 	rbd_obj_request_complete(obj_request);
 }
 
 static void rbd_img_parent_read(struct rbd_obj_request *obj_request)
 {
-	struct rbd_device *rbd_dev;
 	struct rbd_img_request *img_request;
 	int result;
 
 	rbd_assert(obj_request_img_data_test(obj_request));
 	rbd_assert(obj_request->img_request != NULL);
 	rbd_assert(obj_request->result == (s32) -ENOENT);
-	rbd_assert(obj_request->type == OBJ_REQUEST_BIO);
+	rbd_assert(obj_request_type_valid(obj_request->type));
 
-	rbd_dev = obj_request->img_request->rbd_dev;
-	rbd_assert(rbd_dev->parent != NULL);
 	/* rbd_read_finish(obj_request, obj_request->length); */
-	img_request = rbd_img_request_create(rbd_dev->parent,
+	img_request = rbd_parent_request_create(obj_request,
 						obj_request->img_offset,
-						obj_request->length,
-						false, true);
+						obj_request->length);
 	result = -ENOMEM;
 	if (!img_request)
 		goto out_err;
 
-	rbd_obj_request_get(obj_request);
-	img_request->obj_request = obj_request;
-
-	result = rbd_img_request_fill(img_request, OBJ_REQUEST_BIO,
-					obj_request->bio_list);
+	if (obj_request->type == OBJ_REQUEST_BIO)
+		result = rbd_img_request_fill(img_request, OBJ_REQUEST_BIO,
+						obj_request->bio_list);
+	else
+		result = rbd_img_request_fill(img_request, OBJ_REQUEST_PAGES,
+						obj_request->pages);
 	if (result)
 		goto out_err;
 
@@ -2626,6 +2840,7 @@ out:
 static void rbd_watch_cb(u64 ver, u64 notify_id, u8 opcode, void *data)
 {
 	struct rbd_device *rbd_dev = (struct rbd_device *)data;
+	int ret;
 
 	if (!rbd_dev)
 		return;
@@ -2633,7 +2848,9 @@ static void rbd_watch_cb(u64 ver, u64 notify_id, u8 opcode, void *data)
 	dout("%s: \"%s\" notify_id %llu opcode %u\n", __func__,
 		rbd_dev->header_name, (unsigned long long)notify_id,
 		(unsigned int)opcode);
-	(void)rbd_dev_refresh(rbd_dev);
+	ret = rbd_dev_refresh(rbd_dev);
+	if (ret)
+		rbd_warn(rbd_dev, ": header refresh error (%d)\n", ret);
 
 	rbd_obj_notify_ack(rbd_dev, notify_id);
 }
@@ -2642,7 +2859,7 @@ static void rbd_watch_cb(u64 ver, u64 notify_id, u8 opcode, void *data)
  * Request sync osd watch/unwatch.  The value of "start" determines
  * whether a watch request is being initiated or torn down.
  */
-static int rbd_dev_header_watch_sync(struct rbd_device *rbd_dev, int start)
+static int rbd_dev_header_watch_sync(struct rbd_device *rbd_dev, bool start)
 {
 	struct ceph_osd_client *osdc = &rbd_dev->rbd_client->client->osdc;
 	struct rbd_obj_request *obj_request;
@@ -2676,7 +2893,7 @@ static int rbd_dev_header_watch_sync(struct rbd_device *rbd_dev, int start)
 					rbd_dev->watch_request->osd_req);
 
 	osd_req_op_watch_init(obj_request->osd_req, 0, CEPH_OSD_OP_WATCH,
-				rbd_dev->watch_event->cookie, 0, start);
+				rbd_dev->watch_event->cookie, 0, start ? 1 : 0);
 	rbd_osd_req_format_write(obj_request);
 
 	ret = rbd_obj_request_submit(osdc, obj_request);
@@ -2869,9 +3086,16 @@ static void rbd_request_fn(struct request_queue *q)
 			goto end_request;	/* Shouldn't happen */
 		}
 
+		result = -EIO;
+		if (offset + length > rbd_dev->mapping.size) {
+			rbd_warn(rbd_dev, "beyond EOD (%llu~%llu > %llu)\n",
+				offset, length, rbd_dev->mapping.size);
+			goto end_request;
+		}
+
 		result = -ENOMEM;
 		img_request = rbd_img_request_create(rbd_dev, offset, length,
-							write_request, false);
+							write_request);
 		if (!img_request)
 			goto end_request;
 
@@ -3022,17 +3246,11 @@ out:
 }
 
 /*
- * Read the complete header for the given rbd device.
- *
- * Returns a pointer to a dynamically-allocated buffer containing
- * the complete and validated header.  Caller can pass the address
- * of a variable that will be filled in with the version of the
- * header object at the time it was read.
- *
- * Returns a pointer-coded errno if a failure occurs.
+ * Read the complete header for the given rbd device.  On successful
+ * return, the rbd_dev->header field will contain up-to-date
+ * information about the image.
  */
-static struct rbd_image_header_ondisk *
-rbd_dev_v1_header_read(struct rbd_device *rbd_dev)
+static int rbd_dev_v1_header_info(struct rbd_device *rbd_dev)
 {
 	struct rbd_image_header_ondisk *ondisk = NULL;
 	u32 snap_count = 0;
@@ -3057,22 +3275,22 @@ rbd_dev_v1_header_read(struct rbd_device *rbd_dev)
 		size += names_size;
 		ondisk = kmalloc(size, GFP_KERNEL);
 		if (!ondisk)
-			return ERR_PTR(-ENOMEM);
+			return -ENOMEM;
 
 		ret = rbd_obj_read_sync(rbd_dev, rbd_dev->header_name,
 				       0, size, ondisk);
 		if (ret < 0)
-			goto out_err;
+			goto out;
 		if ((size_t)ret < size) {
 			ret = -ENXIO;
 			rbd_warn(rbd_dev, "short header read (want %zd got %d)",
 				size, ret);
-			goto out_err;
+			goto out;
 		}
 		if (!rbd_dev_ondisk_valid(ondisk)) {
 			ret = -ENXIO;
 			rbd_warn(rbd_dev, "invalid header");
-			goto out_err;
+			goto out;
 		}
 
 		names_size = le64_to_cpu(ondisk->snap_names_len);
@@ -3080,85 +3298,13 @@ rbd_dev_v1_header_read(struct rbd_device *rbd_dev)
 		snap_count = le32_to_cpu(ondisk->snap_count);
 	} while (snap_count != want_count);
 
-	return ondisk;
-
-out_err:
-	kfree(ondisk);
-
-	return ERR_PTR(ret);
-}
-
-/*
- * reload the ondisk the header
- */
-static int rbd_read_header(struct rbd_device *rbd_dev,
-			   struct rbd_image_header *header)
-{
-	struct rbd_image_header_ondisk *ondisk;
-	int ret;
-
-	ondisk = rbd_dev_v1_header_read(rbd_dev);
-	if (IS_ERR(ondisk))
-		return PTR_ERR(ondisk);
-	ret = rbd_header_from_disk(header, ondisk);
+	ret = rbd_header_from_disk(rbd_dev, ondisk);
+out:
 	kfree(ondisk);
 
 	return ret;
 }
 
-static void rbd_update_mapping_size(struct rbd_device *rbd_dev)
-{
-	if (rbd_dev->spec->snap_id != CEPH_NOSNAP)
-		return;
-
-	if (rbd_dev->mapping.size != rbd_dev->header.image_size) {
-		sector_t size;
-
-		rbd_dev->mapping.size = rbd_dev->header.image_size;
-		size = (sector_t)rbd_dev->mapping.size / SECTOR_SIZE;
-		dout("setting size to %llu sectors", (unsigned long long)size);
-		set_capacity(rbd_dev->disk, size);
-	}
-}
-
-/*
- * only read the first part of the ondisk header, without the snaps info
- */
-static int rbd_dev_v1_refresh(struct rbd_device *rbd_dev)
-{
-	int ret;
-	struct rbd_image_header h;
-
-	ret = rbd_read_header(rbd_dev, &h);
-	if (ret < 0)
-		return ret;
-
-	down_write(&rbd_dev->header_rwsem);
-
-	/* Update image size, and check for resize of mapped image */
-	rbd_dev->header.image_size = h.image_size;
-	rbd_update_mapping_size(rbd_dev);
-
-	/* rbd_dev->header.object_prefix shouldn't change */
-	kfree(rbd_dev->header.snap_sizes);
-	kfree(rbd_dev->header.snap_names);
-	/* osd requests may still refer to snapc */
-	ceph_put_snap_context(rbd_dev->header.snapc);
-
-	rbd_dev->header.image_size = h.image_size;
-	rbd_dev->header.snapc = h.snapc;
-	rbd_dev->header.snap_names = h.snap_names;
-	rbd_dev->header.snap_sizes = h.snap_sizes;
-	/* Free the extra copy of the object prefix */
-	if (strcmp(rbd_dev->header.object_prefix, h.object_prefix))
-		rbd_warn(rbd_dev, "object prefix changed (ignoring)");
-	kfree(h.object_prefix);
-
-	up_write(&rbd_dev->header_rwsem);
-
-	return ret;
-}
-
 /*
  * Clear the rbd device's EXISTS flag if the snapshot it's mapped to
  * has disappeared from the (just updated) snapshot context.
@@ -3180,26 +3326,29 @@ static void rbd_exists_validate(struct rbd_device *rbd_dev)
 
 static int rbd_dev_refresh(struct rbd_device *rbd_dev)
 {
-	u64 image_size;
+	u64 mapping_size;
 	int ret;
 
 	rbd_assert(rbd_image_format_valid(rbd_dev->image_format));
-	image_size = rbd_dev->header.image_size;
+	mapping_size = rbd_dev->mapping.size;
 	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
 	if (rbd_dev->image_format == 1)
-		ret = rbd_dev_v1_refresh(rbd_dev);
+		ret = rbd_dev_v1_header_info(rbd_dev);
 	else
-		ret = rbd_dev_v2_refresh(rbd_dev);
+		ret = rbd_dev_v2_header_info(rbd_dev);
 
 	/* If it's a mapped snapshot, validate its EXISTS flag */
 
 	rbd_exists_validate(rbd_dev);
 	mutex_unlock(&ctl_mutex);
-	if (ret)
-		rbd_warn(rbd_dev, "got notification but failed to "
-			   " update snaps: %d\n", ret);
-	if (image_size != rbd_dev->header.image_size)
+	if (mapping_size != rbd_dev->mapping.size) {
+		sector_t size;
+
+		size = (sector_t)rbd_dev->mapping.size / SECTOR_SIZE;
+		dout("setting size to %llu sectors", (unsigned long long)size);
+		set_capacity(rbd_dev->disk, size);
 		revalidate_disk(rbd_dev->disk);
+	}
 
 	return ret;
 }
@@ -3403,6 +3552,8 @@ static ssize_t rbd_image_refresh(struct device *dev,
 	int ret;
 
 	ret = rbd_dev_refresh(rbd_dev);
+	if (ret)
+		rbd_warn(rbd_dev, ": manual header refresh error (%d)\n", ret);
 
 	return ret < 0 ? ret : size;
 }
@@ -3501,6 +3652,7 @@ static struct rbd_device *rbd_dev_create(struct rbd_client *rbdc,
 
 	spin_lock_init(&rbd_dev->lock);
 	rbd_dev->flags = 0;
+	atomic_set(&rbd_dev->parent_ref, 0);
 	INIT_LIST_HEAD(&rbd_dev->node);
 	init_rwsem(&rbd_dev->header_rwsem);
 
@@ -3650,6 +3802,7 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev)
 	__le64 snapid;
 	void *p;
 	void *end;
+	u64 pool_id;
 	char *image_id;
 	u64 overlap;
 	int ret;
@@ -3680,18 +3833,37 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev)
 	p = reply_buf;
 	end = reply_buf + ret;
 	ret = -ERANGE;
-	ceph_decode_64_safe(&p, end, parent_spec->pool_id, out_err);
-	if (parent_spec->pool_id == CEPH_NOPOOL)
+	ceph_decode_64_safe(&p, end, pool_id, out_err);
+	if (pool_id == CEPH_NOPOOL) {
+		/*
+		 * Either the parent never existed, or we have
+		 * record of it but the image got flattened so it no
+		 * longer has a parent.  When the parent of a
+		 * layered image disappears we immediately set the
+		 * overlap to 0.  The effect of this is that all new
+		 * requests will be treated as if the image had no
+		 * parent.
+		 */
+		if (rbd_dev->parent_overlap) {
+			rbd_dev->parent_overlap = 0;
+			smp_mb();
+			rbd_dev_parent_put(rbd_dev);
+			pr_info("%s: clone image has been flattened\n",
+				rbd_dev->disk->disk_name);
+		}
+
 		goto out;	/* No parent?  No problem. */
+	}
 
 	/* The ceph file layout needs to fit pool id in 32 bits */
 
 	ret = -EIO;
-	if (parent_spec->pool_id > (u64)U32_MAX) {
+	if (pool_id > (u64)U32_MAX) {
 		rbd_warn(NULL, "parent pool id too large (%llu > %u)\n",
-			(unsigned long long)parent_spec->pool_id, U32_MAX);
+			(unsigned long long)pool_id, U32_MAX);
 		goto out_err;
 	}
+	parent_spec->pool_id = pool_id;
 
 	image_id = ceph_extract_encoded_string(&p, end, NULL, GFP_KERNEL);
 	if (IS_ERR(image_id)) {
@@ -3702,9 +3874,14 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev)
 	ceph_decode_64_safe(&p, end, parent_spec->snap_id, out_err);
 	ceph_decode_64_safe(&p, end, overlap, out_err);
 
-	rbd_dev->parent_overlap = overlap;
-	rbd_dev->parent_spec = parent_spec;
-	parent_spec = NULL;	/* rbd_dev now owns this */
+	if (overlap) {
+		rbd_spec_put(rbd_dev->parent_spec);
+		rbd_dev->parent_spec = parent_spec;
+		parent_spec = NULL;	/* rbd_dev now owns this */
+		rbd_dev->parent_overlap = overlap;
+	} else {
+		rbd_warn(rbd_dev, "ignoring parent of clone with overlap 0\n");
+	}
 out:
 	ret = 0;
 out_err:
@@ -4002,6 +4179,7 @@ static int rbd_dev_v2_snap_context(struct rbd_device *rbd_dev)
 	for (i = 0; i < snap_count; i++)
 		snapc->snaps[i] = ceph_decode_64(&p);
 
+	ceph_put_snap_context(rbd_dev->header.snapc);
 	rbd_dev->header.snapc = snapc;
 
 	dout("  snap context seq = %llu, snap_count = %u\n",
@@ -4053,21 +4231,56 @@ out:
 	return snap_name;
 }
 
-static int rbd_dev_v2_refresh(struct rbd_device *rbd_dev)
+static int rbd_dev_v2_header_info(struct rbd_device *rbd_dev)
 {
+	bool first_time = rbd_dev->header.object_prefix == NULL;
 	int ret;
 
 	down_write(&rbd_dev->header_rwsem);
 
+	if (first_time) {
+		ret = rbd_dev_v2_header_onetime(rbd_dev);
+		if (ret)
+			goto out;
+	}
+
+	/*
+	 * If the image supports layering, get the parent info.  We
+	 * need to probe the first time regardless.  Thereafter we
+	 * only need to if there's a parent, to see if it has
+	 * disappeared due to the mapped image getting flattened.
+	 */
+	if (rbd_dev->header.features & RBD_FEATURE_LAYERING &&
+			(first_time || rbd_dev->parent_spec)) {
+		bool warn;
+
+		ret = rbd_dev_v2_parent_info(rbd_dev);
+		if (ret)
+			goto out;
+
+		/*
+		 * Print a warning if this is the initial probe and
+		 * the image has a parent.  Don't print it if the
+		 * image now being probed is itself a parent.  We
+		 * can tell at this point because we won't know its
+		 * pool name yet (just its pool id).
+		 */
+		warn = rbd_dev->parent_spec && rbd_dev->spec->pool_name;
+		if (first_time && warn)
+			rbd_warn(rbd_dev, "WARNING: kernel layering "
+					"is EXPERIMENTAL!");
+	}
+
 	ret = rbd_dev_v2_image_size(rbd_dev);
 	if (ret)
 		goto out;
-	rbd_update_mapping_size(rbd_dev);
+
+	if (rbd_dev->spec->snap_id == CEPH_NOSNAP)
+		if (rbd_dev->mapping.size != rbd_dev->header.image_size)
+			rbd_dev->mapping.size = rbd_dev->header.image_size;
 
 	ret = rbd_dev_v2_snap_context(rbd_dev);
 	dout("rbd_dev_v2_snap_context returned %d\n", ret);
-	if (ret)
-		goto out;
 out:
 	up_write(&rbd_dev->header_rwsem);
 
@@ -4490,10 +4703,10 @@ static void rbd_dev_unprobe(struct rbd_device *rbd_dev)
 {
 	struct rbd_image_header	*header;
 
-	rbd_dev_remove_parent(rbd_dev);
-	rbd_spec_put(rbd_dev->parent_spec);
-	rbd_dev->parent_spec = NULL;
-	rbd_dev->parent_overlap = 0;
+	/* Drop parent reference unless it's already been done (or none) */
+
+	if (rbd_dev->parent_overlap)
+		rbd_dev_parent_put(rbd_dev);
 
 	/* Free dynamic fields from the header, then zero it out */
 
@@ -4505,72 +4718,22 @@ static void rbd_dev_unprobe(struct rbd_device *rbd_dev)
 	memset(header, 0, sizeof (*header));
 }
 
-static int rbd_dev_v1_probe(struct rbd_device *rbd_dev)
+static int rbd_dev_v2_header_onetime(struct rbd_device *rbd_dev)
 {
 	int ret;
 
-	/* Populate rbd image metadata */
-
-	ret = rbd_read_header(rbd_dev, &rbd_dev->header);
-	if (ret < 0)
-		goto out_err;
-
-	/* Version 1 images have no parent (no layering) */
-
-	rbd_dev->parent_spec = NULL;
-	rbd_dev->parent_overlap = 0;
-
-	dout("discovered version 1 image, header name is %s\n",
-		rbd_dev->header_name);
-
-	return 0;
-
-out_err:
-	kfree(rbd_dev->header_name);
-	rbd_dev->header_name = NULL;
-	kfree(rbd_dev->spec->image_id);
-	rbd_dev->spec->image_id = NULL;
-
-	return ret;
-}
-
-static int rbd_dev_v2_probe(struct rbd_device *rbd_dev)
-{
-	int ret;
-
-	ret = rbd_dev_v2_image_size(rbd_dev);
-	if (ret)
-		goto out_err;
-
-	/* Get the object prefix (a.k.a. block_name) for the image */
-
 	ret = rbd_dev_v2_object_prefix(rbd_dev);
 	if (ret)
 		goto out_err;
 
-	/* Get the and check features for the image */
-
+	/*
+	 * Get the and check features for the image.  Currently the
+	 * features are assumed to never change.
+	 */
 	ret = rbd_dev_v2_features(rbd_dev);
 	if (ret)
 		goto out_err;
 
-	/* If the image supports layering, get the parent info */
-
-	if (rbd_dev->header.features & RBD_FEATURE_LAYERING) {
-		ret = rbd_dev_v2_parent_info(rbd_dev);
-		if (ret)
-			goto out_err;
-
-		/*
-		 * Don't print a warning for parent images.  We can
-		 * tell this point because we won't know its pool
-		 * name yet (just its pool id).
-		 */
-		if (rbd_dev->spec->pool_name)
-			rbd_warn(rbd_dev, "WARNING: kernel layering "
-					"is EXPERIMENTAL!");
-	}
-
 	/* If the image supports fancy striping, get its parameters */
 
 	if (rbd_dev->header.features & RBD_FEATURE_STRIPINGV2) {
@@ -4578,28 +4741,11 @@ static int rbd_dev_v2_probe(struct rbd_device *rbd_dev)
 		if (ret < 0)
 			goto out_err;
 	}
-
-	/* crypto and compression type aren't (yet) supported for v2 images */
-
-	rbd_dev->header.crypt_type = 0;
-	rbd_dev->header.comp_type = 0;
-
-	/* Get the snapshot context, plus the header version */
-
-	ret = rbd_dev_v2_snap_context(rbd_dev);
-	if (ret)
-		goto out_err;
-
-	dout("discovered version 2 image, header name is %s\n",
-		rbd_dev->header_name);
+	/* No support for crypto and compression type format 2 images */
 
 	return 0;
 out_err:
-	rbd_dev->parent_overlap = 0;
-	rbd_spec_put(rbd_dev->parent_spec);
-	rbd_dev->parent_spec = NULL;
-	kfree(rbd_dev->header_name);
-	rbd_dev->header_name = NULL;
+	rbd_dev->header.features = 0;
 	kfree(rbd_dev->header.object_prefix);
 	rbd_dev->header.object_prefix = NULL;
 
@@ -4628,15 +4774,16 @@ static int rbd_dev_probe_parent(struct rbd_device *rbd_dev)
 	if (!parent)
 		goto out_err;
 
-	ret = rbd_dev_image_probe(parent);
+	ret = rbd_dev_image_probe(parent, false);
 	if (ret < 0)
 		goto out_err;
 	rbd_dev->parent = parent;
+	atomic_set(&rbd_dev->parent_ref, 1);
 
 	return 0;
 out_err:
 	if (parent) {
-		rbd_spec_put(rbd_dev->parent_spec);
+		rbd_dev_unparent(rbd_dev);
 		kfree(rbd_dev->header_name);
 		rbd_dev_destroy(parent);
 	} else {
@@ -4651,10 +4798,6 @@ static int rbd_dev_device_setup(struct rbd_device *rbd_dev)
 {
 	int ret;
 
-	ret = rbd_dev_mapping_set(rbd_dev);
-	if (ret)
-		return ret;
-
 	/* generate unique id: find highest unique id, add one */
 	rbd_dev_id_get(rbd_dev);
 
@@ -4676,13 +4819,17 @@ static int rbd_dev_device_setup(struct rbd_device *rbd_dev)
 	if (ret)
 		goto err_out_blkdev;
 
-	ret = rbd_bus_add_dev(rbd_dev);
+	ret = rbd_dev_mapping_set(rbd_dev);
 	if (ret)
 		goto err_out_disk;
+	set_capacity(rbd_dev->disk, rbd_dev->mapping.size / SECTOR_SIZE);
+
+	ret = rbd_bus_add_dev(rbd_dev);
+	if (ret)
+		goto err_out_mapping;
 
 	/* Everything's ready.  Announce the disk to the world. */
 
-	set_capacity(rbd_dev->disk, rbd_dev->mapping.size / SECTOR_SIZE);
 	set_bit(RBD_DEV_FLAG_EXISTS, &rbd_dev->flags);
 	add_disk(rbd_dev->disk);
 
@@ -4691,6 +4838,8 @@ static int rbd_dev_device_setup(struct rbd_device *rbd_dev)
 
 	return ret;
 
+err_out_mapping:
+	rbd_dev_mapping_clear(rbd_dev);
 err_out_disk:
 	rbd_free_disk(rbd_dev);
 err_out_blkdev:
@@ -4731,12 +4880,7 @@ static int rbd_dev_header_name(struct rbd_device *rbd_dev)
 
 static void rbd_dev_image_release(struct rbd_device *rbd_dev)
 {
-	int ret;
-
 	rbd_dev_unprobe(rbd_dev);
-	ret = rbd_dev_header_watch_sync(rbd_dev, 0);
-	if (ret)
-		rbd_warn(rbd_dev, "failed to cancel watch event (%d)\n", ret);
 	kfree(rbd_dev->header_name);
 	rbd_dev->header_name = NULL;
 	rbd_dev->image_format = 0;
@@ -4748,10 +4892,11 @@ static void rbd_dev_image_release(struct rbd_device *rbd_dev)
 
 /*
  * Probe for the existence of the header object for the given rbd
- * device.  For format 2 images this includes determining the image
- * id.
+ * device.  If this image is the one being mapped (i.e., not a
+ * parent), initiate a watch on its header object before using that
+ * object to get detailed information about the rbd image.
  */
-static int rbd_dev_image_probe(struct rbd_device *rbd_dev)
+static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping)
 {
 	int ret;
 	int tmp;
@@ -4771,14 +4916,16 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev)
 	if (ret)
 		goto err_out_format;
 
-	ret = rbd_dev_header_watch_sync(rbd_dev, 1);
-	if (ret)
-		goto out_header_name;
+	if (mapping) {
+		ret = rbd_dev_header_watch_sync(rbd_dev, true);
+		if (ret)
+			goto out_header_name;
+	}
 
 	if (rbd_dev->image_format == 1)
-		ret = rbd_dev_v1_probe(rbd_dev);
+		ret = rbd_dev_v1_header_info(rbd_dev);
 	else
-		ret = rbd_dev_v2_probe(rbd_dev);
+		ret = rbd_dev_v2_header_info(rbd_dev);
 	if (ret)
 		goto err_out_watch;
 
@@ -4787,15 +4934,22 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev)
 		goto err_out_probe;
 
 	ret = rbd_dev_probe_parent(rbd_dev);
-	if (!ret)
-		return 0;
+	if (ret)
+		goto err_out_probe;
+
+	dout("discovered format %u image, header name is %s\n",
+		rbd_dev->image_format, rbd_dev->header_name);
 
+	return 0;
 err_out_probe:
 	rbd_dev_unprobe(rbd_dev);
 err_out_watch:
-	tmp = rbd_dev_header_watch_sync(rbd_dev, 0);
-	if (tmp)
-		rbd_warn(rbd_dev, "unable to tear down watch request\n");
+	if (mapping) {
+		tmp = rbd_dev_header_watch_sync(rbd_dev, false);
+		if (tmp)
+			rbd_warn(rbd_dev, "unable to tear down "
+					"watch request (%d)\n", tmp);
+	}
 out_header_name:
 	kfree(rbd_dev->header_name);
 	rbd_dev->header_name = NULL;
@@ -4819,6 +4973,7 @@ static ssize_t rbd_add(struct bus_type *bus,
 	struct rbd_spec *spec = NULL;
 	struct rbd_client *rbdc;
 	struct ceph_osd_client *osdc;
+	bool read_only;
 	int rc = -ENOMEM;
 
 	if (!try_module_get(THIS_MODULE))
@@ -4828,6 +4983,9 @@ static ssize_t rbd_add(struct bus_type *bus,
 	rc = rbd_add_parse_args(buf, &ceph_opts, &rbd_opts, &spec);
 	if (rc < 0)
 		goto err_out_module;
+	read_only = rbd_opts->read_only;
+	kfree(rbd_opts);
+	rbd_opts = NULL;	/* done with this */
 
 	rbdc = rbd_get_client(ceph_opts);
 	if (IS_ERR(rbdc)) {
@@ -4858,14 +5016,16 @@ static ssize_t rbd_add(struct bus_type *bus,
 	rbdc = NULL;		/* rbd_dev now owns this */
 	spec = NULL;		/* rbd_dev now owns this */
 
-	rbd_dev->mapping.read_only = rbd_opts->read_only;
-	kfree(rbd_opts);
-	rbd_opts = NULL;	/* done with this */
-
-	rc = rbd_dev_image_probe(rbd_dev);
+	rc = rbd_dev_image_probe(rbd_dev, true);
 	if (rc < 0)
 		goto err_out_rbd_dev;
 
+	/* If we are mapping a snapshot it must be marked read-only */
+
+	if (rbd_dev->spec->snap_id != CEPH_NOSNAP)
+		read_only = true;
+	rbd_dev->mapping.read_only = read_only;
+
 	rc = rbd_dev_device_setup(rbd_dev);
 	if (!rc)
 		return count;
@@ -4911,7 +5071,7 @@ static void rbd_dev_device_release(struct device *dev)
 
 	rbd_free_disk(rbd_dev);
 	clear_bit(RBD_DEV_FLAG_EXISTS, &rbd_dev->flags);
-	rbd_dev_clear_mapping(rbd_dev);
+	rbd_dev_mapping_clear(rbd_dev);
 	unregister_blkdev(rbd_dev->major, rbd_dev->name);
 	rbd_dev->major = 0;
 	rbd_dev_id_put(rbd_dev);
@@ -4978,10 +5138,13 @@ static ssize_t rbd_remove(struct bus_type *bus,
 	spin_unlock_irq(&rbd_dev->lock);
 	if (ret < 0)
 		goto done;
-	ret = count;
 	rbd_bus_del_dev(rbd_dev);
+	ret = rbd_dev_header_watch_sync(rbd_dev, false);
+	if (ret)
+		rbd_warn(rbd_dev, "failed to cancel watch event (%d)\n", ret);
 	rbd_dev_image_release(rbd_dev);
 	module_put(THIS_MODULE);
+	ret = count;
 done:
 	mutex_unlock(&ctl_mutex);
 
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index f151c6cf27c3..0a04257edf65 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -85,3 +85,8 @@ config CLKSRC_SAMSUNG_PWM
 	  Samsung S3C, S5P and Exynos SoCs, replacing an earlier driver
 	  for all devicetree enabled platforms. This driver will be
 	  needed only on systems that do not have the Exynos MCT available.
+
+config VF_PIT_TIMER
+	bool
+	help
+	  Support for Period Interrupt Timer on Freescale Vybrid Family SoCs.
diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile
index 8d979c72aa94..9ba8b4d867e3 100644
--- a/drivers/clocksource/Makefile
+++ b/drivers/clocksource/Makefile
@@ -22,10 +22,13 @@ obj-$(CONFIG_ARCH_PRIMA2)	+= timer-prima2.o
 obj-$(CONFIG_SUN4I_TIMER)	+= sun4i_timer.o
 obj-$(CONFIG_ARCH_TEGRA)	+= tegra20_timer.o
 obj-$(CONFIG_VT8500_TIMER)	+= vt8500_timer.o
+obj-$(CONFIG_ARCH_NSPIRE)	+= zevio-timer.o
 obj-$(CONFIG_ARCH_BCM)		+= bcm_kona_timer.o
 obj-$(CONFIG_CADENCE_TTC_TIMER)	+= cadence_ttc_timer.o
 obj-$(CONFIG_CLKSRC_EXYNOS_MCT)	+= exynos_mct.o
 obj-$(CONFIG_CLKSRC_SAMSUNG_PWM)	+= samsung_pwm_timer.o
+obj-$(CONFIG_VF_PIT_TIMER)	+= vf_pit_timer.o
 
 obj-$(CONFIG_ARM_ARCH_TIMER)		+= arm_arch_timer.o
 obj-$(CONFIG_CLKSRC_METAG_GENERIC)	+= metag_generic.o
+obj-$(CONFIG_ARCH_HAS_TICK_BROADCAST)	+= dummy_timer.o
diff --git a/drivers/clocksource/bcm2835_timer.c b/drivers/clocksource/bcm2835_timer.c
index 766611d29945..07ea7ce900dc 100644
--- a/drivers/clocksource/bcm2835_timer.c
+++ b/drivers/clocksource/bcm2835_timer.c
@@ -28,8 +28,8 @@
 #include <linux/of_platform.h>
 #include <linux/slab.h>
 #include <linux/string.h>
+#include <linux/sched_clock.h>
 
-#include <asm/sched_clock.h>
 #include <asm/irq.h>
 
 #define REG_CONTROL	0x00
diff --git a/drivers/clocksource/clksrc-dbx500-prcmu.c b/drivers/clocksource/clksrc-dbx500-prcmu.c
index 54f3d119d99c..0a7fb2440e29 100644
--- a/drivers/clocksource/clksrc-dbx500-prcmu.c
+++ b/drivers/clocksource/clksrc-dbx500-prcmu.c
@@ -14,8 +14,7 @@
  */
 #include <linux/clockchips.h>
 #include <linux/clksrc-dbx500-prcmu.h>
-
-#include <asm/sched_clock.h>
+#include <linux/sched_clock.h>
 
 #define RATE_32K		32768
 
diff --git a/drivers/clocksource/dummy_timer.c b/drivers/clocksource/dummy_timer.c
new file mode 100644
index 000000000000..1f55f9620338
--- /dev/null
+++ b/drivers/clocksource/dummy_timer.c
@@ -0,0 +1,69 @@
+/*
+ *  linux/drivers/clocksource/dummy_timer.c
+ *
+ *  Copyright (C) 2013 ARM Ltd.
+ *  All Rights Reserved
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/clockchips.h>
+#include <linux/cpu.h>
+#include <linux/init.h>
+#include <linux/percpu.h>
+#include <linux/cpumask.h>
+
+static DEFINE_PER_CPU(struct clock_event_device, dummy_timer_evt);
+
+static void dummy_timer_set_mode(enum clock_event_mode mode,
+			   struct clock_event_device *evt)
+{
+	/*
+	 * Core clockevents code will call this when exchanging timer devices.
+	 * We don't need to do anything here.
+	 */
+}
+
+static void __cpuinit dummy_timer_setup(void)
+{
+	int cpu = smp_processor_id();
+	struct clock_event_device *evt = __this_cpu_ptr(&dummy_timer_evt);
+
+	evt->name	= "dummy_timer";
+	evt->features	= CLOCK_EVT_FEAT_PERIODIC |
+			  CLOCK_EVT_FEAT_ONESHOT |
+			  CLOCK_EVT_FEAT_DUMMY;
+	evt->rating	= 100;
+	evt->set_mode	= dummy_timer_set_mode;
+	evt->cpumask	= cpumask_of(cpu);
+
+	clockevents_register_device(evt);
+}
+
+static int __cpuinit dummy_timer_cpu_notify(struct notifier_block *self,
+				      unsigned long action, void *hcpu)
+{
+	if ((action & ~CPU_TASKS_FROZEN) == CPU_STARTING)
+		dummy_timer_setup();
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block dummy_timer_cpu_nb __cpuinitdata = {
+	.notifier_call = dummy_timer_cpu_notify,
+};
+
+static int __init dummy_timer_register(void)
+{
+	int err = register_cpu_notifier(&dummy_timer_cpu_nb);
+	if (err)
+		return err;
+
+	/* We won't get a call on the boot CPU, so register immediately */
+	if (num_possible_cpus() > 1)
+		dummy_timer_setup();
+
+	return 0;
+}
+early_initcall(dummy_timer_register);
diff --git a/drivers/clocksource/dw_apb_timer.c b/drivers/clocksource/dw_apb_timer.c
index 8c2a35f26d9b..e54ca1062d8e 100644
--- a/drivers/clocksource/dw_apb_timer.c
+++ b/drivers/clocksource/dw_apb_timer.c
@@ -387,15 +387,3 @@ cycle_t dw_apb_clocksource_read(struct dw_apb_clocksource *dw_cs)
 {
 	return (cycle_t)~apbt_readl(&dw_cs->timer, APBTMR_N_CURRENT_VALUE);
 }
-
-/**
- * dw_apb_clocksource_unregister() - unregister and free a clocksource.
- *
- * @dw_cs:	The clocksource to unregister/free.
- */
-void dw_apb_clocksource_unregister(struct dw_apb_clocksource *dw_cs)
-{
-	clocksource_unregister(&dw_cs->cs);
-
-	kfree(dw_cs);
-}
diff --git a/drivers/clocksource/dw_apb_timer_of.c b/drivers/clocksource/dw_apb_timer_of.c
index ab09ed3742ee..d9a1e8d51751 100644
--- a/drivers/clocksource/dw_apb_timer_of.c
+++ b/drivers/clocksource/dw_apb_timer_of.c
@@ -20,9 +20,7 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
-
-#include <asm/mach/time.h>
-#include <asm/sched_clock.h>
+#include <linux/sched_clock.h>
 
 static void timer_get_base_and_rate(struct device_node *np,
 				    void __iomem **base, u32 *rate)
@@ -44,7 +42,7 @@ static void add_clockevent(struct device_node *event_timer)
 	u32 irq, rate;
 
 	irq = irq_of_parse_and_map(event_timer, 0);
-	if (irq == NO_IRQ)
+	if (irq == 0)
 		panic("No IRQ for clock event timer");
 
 	timer_get_base_and_rate(event_timer, &iobase, &rate);
diff --git a/drivers/clocksource/mxs_timer.c b/drivers/clocksource/mxs_timer.c
index 02af4204af86..0f5e65f74dc3 100644
--- a/drivers/clocksource/mxs_timer.c
+++ b/drivers/clocksource/mxs_timer.c
@@ -29,9 +29,9 @@
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/stmp_device.h>
+#include <linux/sched_clock.h>
 
 #include <asm/mach/time.h>
-#include <asm/sched_clock.h>
 
 /*
  * There are 2 versions of the timrot on Freescale MXS-based SoCs.
diff --git a/drivers/clocksource/nomadik-mtu.c b/drivers/clocksource/nomadik-mtu.c
index e405531e1cc5..8864c17841c8 100644
--- a/drivers/clocksource/nomadik-mtu.c
+++ b/drivers/clocksource/nomadik-mtu.c
@@ -18,8 +18,8 @@
 #include <linux/delay.h>
 #include <linux/err.h>
 #include <linux/platform_data/clocksource-nomadik-mtu.h>
+#include <linux/sched_clock.h>
 #include <asm/mach/time.h>
-#include <asm/sched_clock.h>
 
 /*
  * The MTU device hosts four different counters, with 4 set of
diff --git a/drivers/clocksource/samsung_pwm_timer.c b/drivers/clocksource/samsung_pwm_timer.c
index 0234c8d2c8f2..584b5472eea3 100644
--- a/drivers/clocksource/samsung_pwm_timer.c
+++ b/drivers/clocksource/samsung_pwm_timer.c
@@ -21,10 +21,10 @@
 #include <linux/of_irq.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
+#include <linux/sched_clock.h>
 
 #include <clocksource/samsung_pwm.h>
 
-#include <asm/sched_clock.h>
 
 /*
  * Clocksource driver
diff --git a/drivers/clocksource/tegra20_timer.c b/drivers/clocksource/tegra20_timer.c
index ae877b021b54..93961703b887 100644
--- a/drivers/clocksource/tegra20_timer.c
+++ b/drivers/clocksource/tegra20_timer.c
@@ -26,10 +26,10 @@
 #include <linux/io.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
+#include <linux/sched_clock.h>
 
 #include <asm/mach/time.h>
 #include <asm/smp_twd.h>
-#include <asm/sched_clock.h>
 
 #define RTC_SECONDS            0x08
 #define RTC_SHADOW_SECONDS     0x0c
diff --git a/drivers/clocksource/time-armada-370-xp.c b/drivers/clocksource/time-armada-370-xp.c
index 47a673070d70..efdca3263afe 100644
--- a/drivers/clocksource/time-armada-370-xp.c
+++ b/drivers/clocksource/time-armada-370-xp.c
@@ -27,8 +27,8 @@
 #include <linux/of_address.h>
 #include <linux/irq.h>
 #include <linux/module.h>
+#include <linux/sched_clock.h>
 
-#include <asm/sched_clock.h>
 #include <asm/localtimer.h>
 #include <linux/percpu.h>
 /*
diff --git a/drivers/clocksource/timer-marco.c b/drivers/clocksource/timer-marco.c
index 97738dbf3e3b..e5dc9129ca26 100644
--- a/drivers/clocksource/timer-marco.c
+++ b/drivers/clocksource/timer-marco.c
@@ -17,7 +17,7 @@
 #include <linux/of.h>
 #include <linux/of_irq.h>
 #include <linux/of_address.h>
-#include <asm/sched_clock.h>
+#include <linux/sched_clock.h>
 #include <asm/localtimer.h>
 #include <asm/mach/time.h>
 
diff --git a/drivers/clocksource/timer-prima2.c b/drivers/clocksource/timer-prima2.c
index 760882665d7a..ef3cfb269d8b 100644
--- a/drivers/clocksource/timer-prima2.c
+++ b/drivers/clocksource/timer-prima2.c
@@ -18,7 +18,7 @@
 #include <linux/of.h>
 #include <linux/of_irq.h>
 #include <linux/of_address.h>
-#include <asm/sched_clock.h>
+#include <linux/sched_clock.h>
 #include <asm/mach/time.h>
 
 #define SIRFSOC_TIMER_COUNTER_LO	0x0000
diff --git a/drivers/clocksource/vf_pit_timer.c b/drivers/clocksource/vf_pit_timer.c
new file mode 100644
index 000000000000..587e0202a70b
--- /dev/null
+++ b/drivers/clocksource/vf_pit_timer.c
@@ -0,0 +1,194 @@
+/*
+ * Copyright 2012-2013 Freescale Semiconductor, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/clockchips.h>
+#include <linux/clk.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/sched_clock.h>
+
+/*
+ * Each pit takes 0x10 Bytes register space
+ */
+#define PITMCR		0x00
+#define PIT0_OFFSET	0x100
+#define PITn_OFFSET(n)	(PIT0_OFFSET + 0x10 * (n))
+#define PITLDVAL	0x00
+#define PITCVAL		0x04
+#define PITTCTRL	0x08
+#define PITTFLG		0x0c
+
+#define PITMCR_MDIS	(0x1 << 1)
+
+#define PITTCTRL_TEN	(0x1 << 0)
+#define PITTCTRL_TIE	(0x1 << 1)
+#define PITCTRL_CHN	(0x1 << 2)
+
+#define PITTFLG_TIF	0x1
+
+static void __iomem *clksrc_base;
+static void __iomem *clkevt_base;
+static unsigned long cycle_per_jiffy;
+
+static inline void pit_timer_enable(void)
+{
+	__raw_writel(PITTCTRL_TEN | PITTCTRL_TIE, clkevt_base + PITTCTRL);
+}
+
+static inline void pit_timer_disable(void)
+{
+	__raw_writel(0, clkevt_base + PITTCTRL);
+}
+
+static inline void pit_irq_acknowledge(void)
+{
+	__raw_writel(PITTFLG_TIF, clkevt_base + PITTFLG);
+}
+
+static unsigned int pit_read_sched_clock(void)
+{
+	return __raw_readl(clksrc_base + PITCVAL);
+}
+
+static int __init pit_clocksource_init(unsigned long rate)
+{
+	/* set the max load value and start the clock source counter */
+	__raw_writel(0, clksrc_base + PITTCTRL);
+	__raw_writel(~0UL, clksrc_base + PITLDVAL);
+	__raw_writel(PITTCTRL_TEN, clksrc_base + PITTCTRL);
+
+	setup_sched_clock(pit_read_sched_clock, 32, rate);
+	return clocksource_mmio_init(clksrc_base + PITCVAL, "vf-pit", rate,
+			300, 32, clocksource_mmio_readl_down);
+}
+
+static int pit_set_next_event(unsigned long delta,
+				struct clock_event_device *unused)
+{
+	/*
+	 * set a new value to PITLDVAL register will not restart the timer,
+	 * to abort the current cycle and start a timer period with the new
+	 * value, the timer must be disabled and enabled again.
+	 * and the PITLAVAL should be set to delta minus one according to pit
+	 * hardware requirement.
+	 */
+	pit_timer_disable();
+	__raw_writel(delta - 1, clkevt_base + PITLDVAL);
+	pit_timer_enable();
+
+	return 0;
+}
+
+static void pit_set_mode(enum clock_event_mode mode,
+				struct clock_event_device *evt)
+{
+	switch (mode) {
+	case CLOCK_EVT_MODE_PERIODIC:
+		pit_set_next_event(cycle_per_jiffy, evt);
+		break;
+	default:
+		break;
+	}
+}
+
+static irqreturn_t pit_timer_interrupt(int irq, void *dev_id)
+{
+	struct clock_event_device *evt = dev_id;
+
+	pit_irq_acknowledge();
+
+	/*
+	 * pit hardware doesn't support oneshot, it will generate an interrupt
+	 * and reload the counter value from PITLDVAL when PITCVAL reach zero,
+	 * and start the counter again. So software need to disable the timer
+	 * to stop the counter loop in ONESHOT mode.
+	 */
+	if (likely(evt->mode == CLOCK_EVT_MODE_ONESHOT))
+		pit_timer_disable();
+
+	evt->event_handler(evt);
+
+	return IRQ_HANDLED;
+}
+
+static struct clock_event_device clockevent_pit = {
+	.name		= "VF pit timer",
+	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
+	.set_mode	= pit_set_mode,
+	.set_next_event	= pit_set_next_event,
+	.rating		= 300,
+};
+
+static struct irqaction pit_timer_irq = {
+	.name		= "VF pit timer",
+	.flags		= IRQF_TIMER | IRQF_IRQPOLL,
+	.handler	= pit_timer_interrupt,
+	.dev_id		= &clockevent_pit,
+};
+
+static int __init pit_clockevent_init(unsigned long rate, int irq)
+{
+	__raw_writel(0, clkevt_base + PITTCTRL);
+	__raw_writel(PITTFLG_TIF, clkevt_base + PITTFLG);
+
+	BUG_ON(setup_irq(irq, &pit_timer_irq));
+
+	clockevent_pit.cpumask = cpumask_of(0);
+	clockevent_pit.irq = irq;
+	/*
+	 * The value for the LDVAL register trigger is calculated as:
+	 * LDVAL trigger = (period / clock period) - 1
+	 * The pit is a 32-bit down count timer, when the conter value
+	 * reaches 0, it will generate an interrupt, thus the minimal
+	 * LDVAL trigger value is 1. And then the min_delta is
+	 * minimal LDVAL trigger value + 1, and the max_delta is full 32-bit.
+	 */
+	clockevents_config_and_register(&clockevent_pit, rate, 2, 0xffffffff);
+
+	return 0;
+}
+
+static void __init pit_timer_init(struct device_node *np)
+{
+	struct clk *pit_clk;
+	void __iomem *timer_base;
+	unsigned long clk_rate;
+	int irq;
+
+	timer_base = of_iomap(np, 0);
+	BUG_ON(!timer_base);
+
+	/*
+	 * PIT0 and PIT1 can be chained to build a 64-bit timer,
+	 * so choose PIT2 as clocksource, PIT3 as clockevent device,
+	 * and leave PIT0 and PIT1 unused for anyone else who needs them.
+	 */
+	clksrc_base = timer_base + PITn_OFFSET(2);
+	clkevt_base = timer_base + PITn_OFFSET(3);
+
+	irq = irq_of_parse_and_map(np, 0);
+	BUG_ON(irq <= 0);
+
+	pit_clk = of_clk_get(np, 0);
+	BUG_ON(IS_ERR(pit_clk));
+
+	BUG_ON(clk_prepare_enable(pit_clk));
+
+	clk_rate = clk_get_rate(pit_clk);
+	cycle_per_jiffy = clk_rate / (HZ);
+
+	/* enable the pit module */
+	__raw_writel(~PITMCR_MDIS, timer_base + PITMCR);
+
+	BUG_ON(pit_clocksource_init(clk_rate));
+
+	pit_clockevent_init(clk_rate, irq);
+}
+CLOCKSOURCE_OF_DECLARE(vf610, "fsl,vf610-pit", pit_timer_init);
diff --git a/drivers/clocksource/zevio-timer.c b/drivers/clocksource/zevio-timer.c
new file mode 100644
index 000000000000..ca81809d159d
--- /dev/null
+++ b/drivers/clocksource/zevio-timer.c
@@ -0,0 +1,215 @@
+/*
+ *  linux/drivers/clocksource/zevio-timer.c
+ *
+ *  Copyright (C) 2013 Daniel Tang <tangrs@tangrs.id.au>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2, as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/clk.h>
+#include <linux/clockchips.h>
+#include <linux/cpumask.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+
+#define IO_CURRENT_VAL	0x00
+#define IO_DIVIDER	0x04
+#define IO_CONTROL	0x08
+
+#define IO_TIMER1	0x00
+#define IO_TIMER2	0x0C
+
+#define IO_MATCH_BEGIN	0x18
+#define IO_MATCH(x)	(IO_MATCH_BEGIN + ((x) << 2))
+
+#define IO_INTR_STS	0x00
+#define IO_INTR_ACK	0x00
+#define IO_INTR_MSK	0x04
+
+#define CNTL_STOP_TIMER	(1 << 4)
+#define CNTL_RUN_TIMER	(0 << 4)
+
+#define CNTL_INC	(1 << 3)
+#define CNTL_DEC	(0 << 3)
+
+#define CNTL_TOZERO	0
+#define CNTL_MATCH(x)	((x) + 1)
+#define CNTL_FOREVER	7
+
+/* There are 6 match registers but we only use one. */
+#define TIMER_MATCH	0
+
+#define TIMER_INTR_MSK	(1 << (TIMER_MATCH))
+#define TIMER_INTR_ALL	0x3F
+
+struct zevio_timer {
+	void __iomem *base;
+	void __iomem *timer1, *timer2;
+	void __iomem *interrupt_regs;
+
+	struct clk *clk;
+	struct clock_event_device clkevt;
+	struct irqaction clkevt_irq;
+
+	char clocksource_name[64];
+	char clockevent_name[64];
+};
+
+static int zevio_timer_set_event(unsigned long delta,
+				 struct clock_event_device *dev)
+{
+	struct zevio_timer *timer = container_of(dev, struct zevio_timer,
+						 clkevt);
+
+	writel(delta, timer->timer1 + IO_CURRENT_VAL);
+	writel(CNTL_RUN_TIMER | CNTL_DEC | CNTL_MATCH(TIMER_MATCH),
+			timer->timer1 + IO_CONTROL);
+
+	return 0;
+}
+
+static void zevio_timer_set_mode(enum clock_event_mode mode,
+				 struct clock_event_device *dev)
+{
+	struct zevio_timer *timer = container_of(dev, struct zevio_timer,
+						 clkevt);
+
+	switch (mode) {
+	case CLOCK_EVT_MODE_RESUME:
+	case CLOCK_EVT_MODE_ONESHOT:
+		/* Enable timer interrupts */
+		writel(TIMER_INTR_MSK, timer->interrupt_regs + IO_INTR_MSK);
+		writel(TIMER_INTR_ALL, timer->interrupt_regs + IO_INTR_ACK);
+		break;
+	case CLOCK_EVT_MODE_SHUTDOWN:
+	case CLOCK_EVT_MODE_UNUSED:
+		/* Disable timer interrupts */
+		writel(0, timer->interrupt_regs + IO_INTR_MSK);
+		writel(TIMER_INTR_ALL, timer->interrupt_regs + IO_INTR_ACK);
+		/* Stop timer */
+		writel(CNTL_STOP_TIMER, timer->timer1 + IO_CONTROL);
+		break;
+	case CLOCK_EVT_MODE_PERIODIC:
+	default:
+		/* Unsupported */
+		break;
+	}
+}
+
+static irqreturn_t zevio_timer_interrupt(int irq, void *dev_id)
+{
+	struct zevio_timer *timer = dev_id;
+	u32 intr;
+
+	intr = readl(timer->interrupt_regs + IO_INTR_ACK);
+	if (!(intr & TIMER_INTR_MSK))
+		return IRQ_NONE;
+
+	writel(TIMER_INTR_MSK, timer->interrupt_regs + IO_INTR_ACK);
+	writel(CNTL_STOP_TIMER, timer->timer1 + IO_CONTROL);
+
+	if (timer->clkevt.event_handler)
+		timer->clkevt.event_handler(&timer->clkevt);
+
+	return IRQ_HANDLED;
+}
+
+static int __init zevio_timer_add(struct device_node *node)
+{
+	struct zevio_timer *timer;
+	struct resource res;
+	int irqnr, ret;
+
+	timer = kzalloc(sizeof(*timer), GFP_KERNEL);
+	if (!timer)
+		return -ENOMEM;
+
+	timer->base = of_iomap(node, 0);
+	if (!timer->base) {
+		ret = -EINVAL;
+		goto error_free;
+	}
+	timer->timer1 = timer->base + IO_TIMER1;
+	timer->timer2 = timer->base + IO_TIMER2;
+
+	timer->clk = of_clk_get(node, 0);
+	if (IS_ERR(timer->clk)) {
+		ret = PTR_ERR(timer->clk);
+		pr_err("Timer clock not found! (error %d)\n", ret);
+		goto error_unmap;
+	}
+
+	timer->interrupt_regs = of_iomap(node, 1);
+	irqnr = irq_of_parse_and_map(node, 0);
+
+	of_address_to_resource(node, 0, &res);
+	scnprintf(timer->clocksource_name, sizeof(timer->clocksource_name),
+			"%llx.%s_clocksource",
+			(unsigned long long)res.start, node->name);
+
+	scnprintf(timer->clockevent_name, sizeof(timer->clockevent_name),
+			"%llx.%s_clockevent",
+			(unsigned long long)res.start, node->name);
+
+	if (timer->interrupt_regs && irqnr) {
+		timer->clkevt.name		= timer->clockevent_name;
+		timer->clkevt.set_next_event	= zevio_timer_set_event;
+		timer->clkevt.set_mode		= zevio_timer_set_mode;
+		timer->clkevt.rating		= 200;
+		timer->clkevt.cpumask		= cpu_all_mask;
+		timer->clkevt.features		= CLOCK_EVT_FEAT_ONESHOT;
+		timer->clkevt.irq		= irqnr;
+
+		writel(CNTL_STOP_TIMER, timer->timer1 + IO_CONTROL);
+		writel(0, timer->timer1 + IO_DIVIDER);
+
+		/* Start with timer interrupts disabled */
+		writel(0, timer->interrupt_regs + IO_INTR_MSK);
+		writel(TIMER_INTR_ALL, timer->interrupt_regs + IO_INTR_ACK);
+
+		/* Interrupt to occur when timer value matches 0 */
+		writel(0, timer->base + IO_MATCH(TIMER_MATCH));
+
+		timer->clkevt_irq.name		= timer->clockevent_name;
+		timer->clkevt_irq.handler	= zevio_timer_interrupt;
+		timer->clkevt_irq.dev_id	= timer;
+		timer->clkevt_irq.flags		= IRQF_TIMER | IRQF_IRQPOLL;
+
+		setup_irq(irqnr, &timer->clkevt_irq);
+
+		clockevents_config_and_register(&timer->clkevt,
+				clk_get_rate(timer->clk), 0x0001, 0xffff);
+		pr_info("Added %s as clockevent\n", timer->clockevent_name);
+	}
+
+	writel(CNTL_STOP_TIMER, timer->timer2 + IO_CONTROL);
+	writel(0, timer->timer2 + IO_CURRENT_VAL);
+	writel(0, timer->timer2 + IO_DIVIDER);
+	writel(CNTL_RUN_TIMER | CNTL_FOREVER | CNTL_INC,
+			timer->timer2 + IO_CONTROL);
+
+	clocksource_mmio_init(timer->timer2 + IO_CURRENT_VAL,
+			timer->clocksource_name,
+			clk_get_rate(timer->clk),
+			200, 16,
+			clocksource_mmio_readw_up);
+
+	pr_info("Added %s as clocksource\n", timer->clocksource_name);
+
+	return 0;
+error_unmap:
+	iounmap(timer->base);
+error_free:
+	kfree(timer);
+	return ret;
+}
+
+CLOCKSOURCE_OF_DECLARE(zevio_timer, "lsi,zevio-timer", zevio_timer_add);
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index 3a8f7e6db295..e7e92429d10f 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -78,6 +78,10 @@ void drm_warn_on_modeset_not_all_locked(struct drm_device *dev)
 {
 	struct drm_crtc *crtc;
 
+	/* Locking is currently fubar in the panic handler. */
+	if (oops_in_progress)
+		return;
+
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head)
 		WARN_ON(!mutex_is_locked(&crtc->mutex));
 
@@ -246,6 +250,7 @@ char *drm_get_connector_status_name(enum drm_connector_status status)
 	else
 		return "unknown";
 }
+EXPORT_SYMBOL(drm_get_connector_status_name);
 
 /**
  * drm_mode_object_get - allocate a new modeset identifier
diff --git a/drivers/gpu/drm/drm_crtc_helper.c b/drivers/gpu/drm/drm_crtc_helper.c
index e974f9309b72..ed1334e27c33 100644
--- a/drivers/gpu/drm/drm_crtc_helper.c
+++ b/drivers/gpu/drm/drm_crtc_helper.c
@@ -121,6 +121,7 @@ int drm_helper_probe_single_connector_modes(struct drm_connector *connector,
 		connector->helper_private;
 	int count = 0;
 	int mode_flags = 0;
+	bool verbose_prune = true;
 
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", connector->base.id,
 			drm_get_connector_name(connector));
@@ -149,6 +150,7 @@ int drm_helper_probe_single_connector_modes(struct drm_connector *connector,
 		DRM_DEBUG_KMS("[CONNECTOR:%d:%s] disconnected\n",
 			connector->base.id, drm_get_connector_name(connector));
 		drm_mode_connector_update_edid_property(connector, NULL);
+		verbose_prune = false;
 		goto prune;
 	}
 
@@ -182,7 +184,7 @@ int drm_helper_probe_single_connector_modes(struct drm_connector *connector,
 	}
 
 prune:
-	drm_mode_prune_invalid(dev, &connector->modes, true);
+	drm_mode_prune_invalid(dev, &connector->modes, verbose_prune);
 
 	if (list_empty(&connector->modes))
 		return 0;
@@ -1005,12 +1007,20 @@ static void output_poll_execute(struct work_struct *work)
 			continue;
 
 		connector->status = connector->funcs->detect(connector, false);
-		DRM_DEBUG_KMS("[CONNECTOR:%d:%s] status updated from %d to %d\n",
-			      connector->base.id,
-			      drm_get_connector_name(connector),
-			      old_status, connector->status);
-		if (old_status != connector->status)
+		if (old_status != connector->status) {
+			const char *old, *new;
+
+			old = drm_get_connector_status_name(old_status);
+			new = drm_get_connector_status_name(connector->status);
+
+			DRM_DEBUG_KMS("[CONNECTOR:%d:%s] "
+				      "status updated from %s to %s\n",
+				      connector->base.id,
+				      drm_get_connector_name(connector),
+				      old, new);
+
 			changed = true;
+		}
 	}
 
 	mutex_unlock(&dev->mode_config.mutex);
@@ -1083,10 +1093,11 @@ void drm_helper_hpd_irq_event(struct drm_device *dev)
 		old_status = connector->status;
 
 		connector->status = connector->funcs->detect(connector, false);
-		DRM_DEBUG_KMS("[CONNECTOR:%d:%s] status updated from %d to %d\n",
+		DRM_DEBUG_KMS("[CONNECTOR:%d:%s] status updated from %s to %s\n",
 			      connector->base.id,
 			      drm_get_connector_name(connector),
-			      old_status, connector->status);
+			      drm_get_connector_status_name(old_status),
+			      drm_get_connector_status_name(connector->status));
 		if (old_status != connector->status)
 			changed = true;
 	}
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 8d4f29075af5..9cc247f55502 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -57,7 +57,7 @@ static int drm_version(struct drm_device *dev, void *data,
 		       struct drm_file *file_priv);
 
 #define DRM_IOCTL_DEF(ioctl, _func, _flags) \
-	[DRM_IOCTL_NR(ioctl)] = {.cmd = ioctl, .func = _func, .flags = _flags, .cmd_drv = 0}
+	[DRM_IOCTL_NR(ioctl)] = {.cmd = ioctl, .func = _func, .flags = _flags, .cmd_drv = 0, .name = #ioctl}
 
 /** Ioctl table */
 static const struct drm_ioctl_desc drm_ioctls[] = {
@@ -375,7 +375,7 @@ long drm_ioctl(struct file *filp,
 {
 	struct drm_file *file_priv = filp->private_data;
 	struct drm_device *dev;
-	const struct drm_ioctl_desc *ioctl;
+	const struct drm_ioctl_desc *ioctl = NULL;
 	drm_ioctl_t *func;
 	unsigned int nr = DRM_IOCTL_NR(cmd);
 	int retcode = -EINVAL;
@@ -392,11 +392,6 @@ long drm_ioctl(struct file *filp,
 	atomic_inc(&dev->counts[_DRM_STAT_IOCTLS]);
 	++file_priv->ioctl_count;
 
-	DRM_DEBUG("pid=%d, cmd=0x%02x, nr=0x%02x, dev 0x%lx, auth=%d\n",
-		  task_pid_nr(current), cmd, nr,
-		  (long)old_encode_dev(file_priv->minor->device),
-		  file_priv->authenticated);
-
 	if ((nr >= DRM_CORE_IOCTL_COUNT) &&
 	    ((nr < DRM_COMMAND_BASE) || (nr >= DRM_COMMAND_END)))
 		goto err_i1;
@@ -417,6 +412,11 @@ long drm_ioctl(struct file *filp,
 	} else
 		goto err_i1;
 
+	DRM_DEBUG("pid=%d, dev=0x%lx, auth=%d, %s\n",
+		  task_pid_nr(current),
+		  (long)old_encode_dev(file_priv->minor->device),
+		  file_priv->authenticated, ioctl->name);
+
 	/* Do not trust userspace, use our own definition */
 	func = ioctl->func;
 	/* is there a local override? */
@@ -471,6 +471,12 @@ long drm_ioctl(struct file *filp,
 	}
 
       err_i1:
+	if (!ioctl)
+		DRM_DEBUG("invalid iotcl: pid=%d, dev=0x%lx, auth=%d, cmd=0x%02x, nr=0x%02x\n",
+			  task_pid_nr(current),
+			  (long)old_encode_dev(file_priv->minor->device),
+			  file_priv->authenticated, cmd, nr);
+
 	if (kdata != stack_kdata)
 		kfree(kdata);
 	atomic_dec(&dev->ioctl_count);
diff --git a/drivers/gpu/drm/drm_encoder_slave.c b/drivers/gpu/drm/drm_encoder_slave.c
index 48c52f7df4e6..0cfb60f54766 100644
--- a/drivers/gpu/drm/drm_encoder_slave.c
+++ b/drivers/gpu/drm/drm_encoder_slave.c
@@ -54,16 +54,12 @@ int drm_i2c_encoder_init(struct drm_device *dev,
 			 struct i2c_adapter *adap,
 			 const struct i2c_board_info *info)
 {
-	char modalias[sizeof(I2C_MODULE_PREFIX)
-		      + I2C_NAME_SIZE];
 	struct module *module = NULL;
 	struct i2c_client *client;
 	struct drm_i2c_encoder_driver *encoder_drv;
 	int err = 0;
 
-	snprintf(modalias, sizeof(modalias),
-		 "%s%s", I2C_MODULE_PREFIX, info->type);
-	request_module(modalias);
+	request_module("%s%s", I2C_MODULE_PREFIX, info->type);
 
 	client = i2c_new_device(adap, info);
 	if (!client) {
diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c
index db1e2d6f90d7..07cf99cc8862 100644
--- a/drivers/gpu/drm/drm_mm.c
+++ b/drivers/gpu/drm/drm_mm.c
@@ -755,33 +755,35 @@ void drm_mm_debug_table(struct drm_mm *mm, const char *prefix)
 EXPORT_SYMBOL(drm_mm_debug_table);
 
 #if defined(CONFIG_DEBUG_FS)
-int drm_mm_dump_table(struct seq_file *m, struct drm_mm *mm)
+static unsigned long drm_mm_dump_hole(struct seq_file *m, struct drm_mm_node *entry)
 {
-	struct drm_mm_node *entry;
-	unsigned long total_used = 0, total_free = 0, total = 0;
 	unsigned long hole_start, hole_end, hole_size;
 
-	hole_start = drm_mm_hole_node_start(&mm->head_node);
-	hole_end = drm_mm_hole_node_end(&mm->head_node);
-	hole_size = hole_end - hole_start;
-	if (hole_size)
+	if (entry->hole_follows) {
+		hole_start = drm_mm_hole_node_start(entry);
+		hole_end = drm_mm_hole_node_end(entry);
+		hole_size = hole_end - hole_start;
 		seq_printf(m, "0x%08lx-0x%08lx: 0x%08lx: free\n",
 				hole_start, hole_end, hole_size);
-	total_free += hole_size;
+		return hole_size;
+	}
+
+	return 0;
+}
+
+int drm_mm_dump_table(struct seq_file *m, struct drm_mm *mm)
+{
+	struct drm_mm_node *entry;
+	unsigned long total_used = 0, total_free = 0, total = 0;
+
+	total_free += drm_mm_dump_hole(m, &mm->head_node);
 
 	drm_mm_for_each_node(entry, mm) {
 		seq_printf(m, "0x%08lx-0x%08lx: 0x%08lx: used\n",
 				entry->start, entry->start + entry->size,
 				entry->size);
 		total_used += entry->size;
-		if (entry->hole_follows) {
-			hole_start = drm_mm_hole_node_start(entry);
-			hole_end = drm_mm_hole_node_end(entry);
-			hole_size = hole_end - hole_start;
-			seq_printf(m, "0x%08lx-0x%08lx: 0x%08lx: free\n",
-					hole_start, hole_end, hole_size);
-			total_free += hole_size;
-		}
+		total_free += drm_mm_dump_hole(m, entry);
 	}
 	total = total_free + total_used;
 
diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index faa79df02648..a371ff865a88 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -1143,6 +1143,7 @@ bool drm_mode_parse_command_line_for_connector(const char *mode_option,
 				was_digit = false;
 			} else
 				goto done;
+			break;
 		case '0' ... '9':
 			was_digit = true;
 			break;
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 6be940effefd..6165535d15f0 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1045,6 +1045,8 @@ static int __wait_seqno(struct intel_ring_buffer *ring, u32 seqno,
 	if (timeout) {
 		struct timespec sleep_time = timespec_sub(now, before);
 		*timeout = timespec_sub(*timeout, sleep_time);
+		if (!timespec_valid(timeout)) /* i.e. negative time remains */
+			set_normalized_timespec(timeout, 0, 0);
 	}
 
 	switch (end) {
@@ -1053,8 +1055,6 @@ static int __wait_seqno(struct intel_ring_buffer *ring, u32 seqno,
 	case -ERESTARTSYS: /* Signal */
 		return (int)end;
 	case 0: /* Timeout */
-		if (timeout)
-			set_normalized_timespec(timeout, 0, 0);
 		return -ETIME;
 	default: /* Completed */
 		WARN_ON(end < 0); /* We're not aware of other errors */
@@ -2377,10 +2377,8 @@ i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	mutex_unlock(&dev->struct_mutex);
 
 	ret = __wait_seqno(ring, seqno, reset_counter, true, timeout);
-	if (timeout) {
-		WARN_ON(!timespec_valid(timeout));
+	if (timeout)
 		args->timeout_ns = timespec_to_ns(timeout);
-	}
 	return ret;
 
 out:
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index dca614de71b6..bdb0d7717bc7 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -709,15 +709,6 @@ static inline size_t gen6_get_stolen_size(u16 snb_gmch_ctl)
 	return snb_gmch_ctl << 25; /* 32 MB units */
 }
 
-static inline size_t gen7_get_stolen_size(u16 snb_gmch_ctl)
-{
-	static const int stolen_decoder[] = {
-		0, 0, 0, 0, 0, 32, 48, 64, 128, 256, 96, 160, 224, 352};
-	snb_gmch_ctl >>= IVB_GMCH_GMS_SHIFT;
-	snb_gmch_ctl &= IVB_GMCH_GMS_MASK;
-	return stolen_decoder[snb_gmch_ctl] << 20;
-}
-
 static int gen6_gmch_probe(struct drm_device *dev,
 			   size_t *gtt_total,
 			   size_t *stolen,
@@ -747,11 +738,7 @@ static int gen6_gmch_probe(struct drm_device *dev,
 	pci_read_config_word(dev->pdev, SNB_GMCH_CTRL, &snb_gmch_ctl);
 	gtt_size = gen6_get_total_gtt_size(snb_gmch_ctl);
 
-	if (IS_GEN7(dev) && !IS_VALLEYVIEW(dev))
-		*stolen = gen7_get_stolen_size(snb_gmch_ctl);
-	else
-		*stolen = gen6_get_stolen_size(snb_gmch_ctl);
-
+	*stolen = gen6_get_stolen_size(snb_gmch_ctl);
 	*gtt_total = (gtt_size / sizeof(gen6_gtt_pte_t)) << PAGE_SHIFT;
 
 	/* For Modern GENs the PTEs and register space are split in the BAR */
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 83f9c26e1adb..2d6b62e42daf 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -46,8 +46,6 @@
 #define    SNB_GMCH_GGMS_MASK	0x3
 #define    SNB_GMCH_GMS_SHIFT   3 /* Graphics Mode Select */
 #define    SNB_GMCH_GMS_MASK    0x1f
-#define    IVB_GMCH_GMS_SHIFT   4
-#define    IVB_GMCH_GMS_MASK    0xf
 
 
 /* PCI config space */
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index 26a0a570f92e..fb961bb81903 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1265,6 +1265,8 @@ static void intel_ddi_pre_enable(struct intel_encoder *intel_encoder)
 		intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON);
 		intel_dp_start_link_train(intel_dp);
 		intel_dp_complete_link_train(intel_dp);
+		if (port != PORT_A)
+			intel_dp_stop_link_train(intel_dp);
 	}
 }
 
@@ -1326,6 +1328,9 @@ static void intel_enable_ddi(struct intel_encoder *intel_encoder)
 	} else if (type == INTEL_OUTPUT_EDP) {
 		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 
+		if (port == PORT_A)
+			intel_dp_stop_link_train(intel_dp);
+
 		ironlake_edp_backlight_on(intel_dp);
 	}
 
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index fb2fbc1e08b9..3d704b706a8d 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -702,6 +702,9 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 	/* Walk through all bpp values. Luckily they're all nicely spaced with 2
 	 * bpc in between. */
 	bpp = min_t(int, 8*3, pipe_config->pipe_bpp);
+	if (is_edp(intel_dp) && dev_priv->edp.bpp)
+		bpp = min_t(int, bpp, dev_priv->edp.bpp);
+
 	for (; bpp >= 6*3; bpp -= 2*3) {
 		mode_rate = intel_dp_link_required(target_clock, bpp);
 
@@ -739,6 +742,7 @@ found:
 	intel_dp->link_bw = bws[clock];
 	intel_dp->lane_count = lane_count;
 	adjusted_mode->clock = drm_dp_bw_code_to_link_rate(intel_dp->link_bw);
+	pipe_config->pipe_bpp = bpp;
 	pipe_config->pixel_target_clock = target_clock;
 
 	DRM_DEBUG_KMS("DP link bw %02x lane count %d clock %d bpp %d\n",
@@ -751,20 +755,6 @@ found:
 			       target_clock, adjusted_mode->clock,
 			       &pipe_config->dp_m_n);
 
-	/*
-	 * XXX: We have a strange regression where using the vbt edp bpp value
-	 * for the link bw computation results in black screens, the panel only
-	 * works when we do the computation at the usual 24bpp (but still
-	 * requires us to use 18bpp). Until that's fully debugged, stay
-	 * bug-for-bug compatible with the old code.
-	 */
-	if (is_edp(intel_dp) && dev_priv->edp.bpp) {
-		DRM_DEBUG_KMS("clamping display bpc (was %d) to eDP (%d)\n",
-			      bpp, dev_priv->edp.bpp);
-		bpp = min_t(int, bpp, dev_priv->edp.bpp);
-	}
-	pipe_config->pipe_bpp = bpp;
-
 	return true;
 }
 
@@ -1389,6 +1379,7 @@ static void intel_enable_dp(struct intel_encoder *encoder)
 	ironlake_edp_panel_on(intel_dp);
 	ironlake_edp_panel_vdd_off(intel_dp, true);
 	intel_dp_complete_link_train(intel_dp);
+	intel_dp_stop_link_train(intel_dp);
 	ironlake_edp_backlight_on(intel_dp);
 }
 
@@ -1711,10 +1702,9 @@ intel_dp_set_link_train(struct intel_dp *intel_dp,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	enum port port = intel_dig_port->port;
 	int ret;
-	uint32_t temp;
 
 	if (HAS_DDI(dev)) {
-		temp = I915_READ(DP_TP_CTL(port));
+		uint32_t temp = I915_READ(DP_TP_CTL(port));
 
 		if (dp_train_pat & DP_LINK_SCRAMBLING_DISABLE)
 			temp |= DP_TP_CTL_SCRAMBLE_DISABLE;
@@ -1724,18 +1714,6 @@ intel_dp_set_link_train(struct intel_dp *intel_dp,
 		temp &= ~DP_TP_CTL_LINK_TRAIN_MASK;
 		switch (dp_train_pat & DP_TRAINING_PATTERN_MASK) {
 		case DP_TRAINING_PATTERN_DISABLE:
-
-			if (port != PORT_A) {
-				temp |= DP_TP_CTL_LINK_TRAIN_IDLE;
-				I915_WRITE(DP_TP_CTL(port), temp);
-
-				if (wait_for((I915_READ(DP_TP_STATUS(port)) &
-					      DP_TP_STATUS_IDLE_DONE), 1))
-					DRM_ERROR("Timed out waiting for DP idle patterns\n");
-
-				temp &= ~DP_TP_CTL_LINK_TRAIN_MASK;
-			}
-
 			temp |= DP_TP_CTL_LINK_TRAIN_NORMAL;
 
 			break;
@@ -1811,6 +1789,37 @@ intel_dp_set_link_train(struct intel_dp *intel_dp,
 	return true;
 }
 
+static void intel_dp_set_idle_link_train(struct intel_dp *intel_dp)
+{
+	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+	struct drm_device *dev = intel_dig_port->base.base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	enum port port = intel_dig_port->port;
+	uint32_t val;
+
+	if (!HAS_DDI(dev))
+		return;
+
+	val = I915_READ(DP_TP_CTL(port));
+	val &= ~DP_TP_CTL_LINK_TRAIN_MASK;
+	val |= DP_TP_CTL_LINK_TRAIN_IDLE;
+	I915_WRITE(DP_TP_CTL(port), val);
+
+	/*
+	 * On PORT_A we can have only eDP in SST mode. There the only reason
+	 * we need to set idle transmission mode is to work around a HW issue
+	 * where we enable the pipe while not in idle link-training mode.
+	 * In this case there is requirement to wait for a minimum number of
+	 * idle patterns to be sent.
+	 */
+	if (port == PORT_A)
+		return;
+
+	if (wait_for((I915_READ(DP_TP_STATUS(port)) & DP_TP_STATUS_IDLE_DONE),
+		     1))
+		DRM_ERROR("Timed out waiting for DP idle patterns\n");
+}
+
 /* Enable corresponding port and start training pattern 1 */
 void
 intel_dp_start_link_train(struct intel_dp *intel_dp)
@@ -1953,10 +1962,19 @@ intel_dp_complete_link_train(struct intel_dp *intel_dp)
 		++tries;
 	}
 
+	intel_dp_set_idle_link_train(intel_dp);
+
+	intel_dp->DP = DP;
+
 	if (channel_eq)
 		DRM_DEBUG_KMS("Channel EQ done. DP Training successful\n");
 
-	intel_dp_set_link_train(intel_dp, DP, DP_TRAINING_PATTERN_DISABLE);
+}
+
+void intel_dp_stop_link_train(struct intel_dp *intel_dp)
+{
+	intel_dp_set_link_train(intel_dp, intel_dp->DP,
+				DP_TRAINING_PATTERN_DISABLE);
 }
 
 static void
@@ -2164,6 +2182,7 @@ intel_dp_check_link_status(struct intel_dp *intel_dp)
 			      drm_get_encoder_name(&intel_encoder->base));
 		intel_dp_start_link_train(intel_dp);
 		intel_dp_complete_link_train(intel_dp);
+		intel_dp_stop_link_train(intel_dp);
 	}
 }
 
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index b5b6d19e6dd3..624a9e6b8d71 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -499,6 +499,7 @@ extern void intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 extern void intel_dp_init_link_config(struct intel_dp *intel_dp);
 extern void intel_dp_start_link_train(struct intel_dp *intel_dp);
 extern void intel_dp_complete_link_train(struct intel_dp *intel_dp);
+extern void intel_dp_stop_link_train(struct intel_dp *intel_dp);
 extern void intel_dp_sink_dpms(struct intel_dp *intel_dp, int mode);
 extern void intel_dp_encoder_destroy(struct drm_encoder *encoder);
 extern void intel_dp_check_link_status(struct intel_dp *intel_dp);
diff --git a/drivers/gpu/drm/i915/intel_fb.c b/drivers/gpu/drm/i915/intel_fb.c
index 0e19e575a1b4..6b7c3ca2c035 100644
--- a/drivers/gpu/drm/i915/intel_fb.c
+++ b/drivers/gpu/drm/i915/intel_fb.c
@@ -262,10 +262,22 @@ void intel_fbdev_fini(struct drm_device *dev)
 void intel_fbdev_set_suspend(struct drm_device *dev, int state)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
-	if (!dev_priv->fbdev)
+	struct intel_fbdev *ifbdev = dev_priv->fbdev;
+	struct fb_info *info;
+
+	if (!ifbdev)
 		return;
 
-	fb_set_suspend(dev_priv->fbdev->helper.fbdev, state);
+	info = ifbdev->helper.fbdev;
+
+	/* On resume from hibernation: If the object is shmemfs backed, it has
+	 * been restored from swap. If the object is stolen however, it will be
+	 * full of whatever garbage was left in there.
+	 */
+	if (!state && ifbdev->ifb.obj->stolen)
+		memset_io(info->screen_base, 0, info->screen_size);
+
+	fb_set_suspend(info, state);
 }
 
 MODULE_LICENSE("GPL and additional rights");
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index de3b0dc5658b..aa01128ff192 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -1301,17 +1301,17 @@ static void valleyview_update_wm(struct drm_device *dev)
 
 	vlv_update_drain_latency(dev);
 
-	if (g4x_compute_wm0(dev, 0,
+	if (g4x_compute_wm0(dev, PIPE_A,
 			    &valleyview_wm_info, latency_ns,
 			    &valleyview_cursor_wm_info, latency_ns,
 			    &planea_wm, &cursora_wm))
-		enabled |= 1;
+		enabled |= 1 << PIPE_A;
 
-	if (g4x_compute_wm0(dev, 1,
+	if (g4x_compute_wm0(dev, PIPE_B,
 			    &valleyview_wm_info, latency_ns,
 			    &valleyview_cursor_wm_info, latency_ns,
 			    &planeb_wm, &cursorb_wm))
-		enabled |= 2;
+		enabled |= 1 << PIPE_B;
 
 	if (single_plane_enabled(enabled) &&
 	    g4x_compute_srwm(dev, ffs(enabled) - 1,
@@ -1357,17 +1357,17 @@ static void g4x_update_wm(struct drm_device *dev)
 	int plane_sr, cursor_sr;
 	unsigned int enabled = 0;
 
-	if (g4x_compute_wm0(dev, 0,
+	if (g4x_compute_wm0(dev, PIPE_A,
 			    &g4x_wm_info, latency_ns,
 			    &g4x_cursor_wm_info, latency_ns,
 			    &planea_wm, &cursora_wm))
-		enabled |= 1;
+		enabled |= 1 << PIPE_A;
 
-	if (g4x_compute_wm0(dev, 1,
+	if (g4x_compute_wm0(dev, PIPE_B,
 			    &g4x_wm_info, latency_ns,
 			    &g4x_cursor_wm_info, latency_ns,
 			    &planeb_wm, &cursorb_wm))
-		enabled |= 2;
+		enabled |= 1 << PIPE_B;
 
 	if (single_plane_enabled(enabled) &&
 	    g4x_compute_srwm(dev, ffs(enabled) - 1,
@@ -1716,7 +1716,7 @@ static void ironlake_update_wm(struct drm_device *dev)
 	unsigned int enabled;
 
 	enabled = 0;
-	if (g4x_compute_wm0(dev, 0,
+	if (g4x_compute_wm0(dev, PIPE_A,
 			    &ironlake_display_wm_info,
 			    ILK_LP0_PLANE_LATENCY,
 			    &ironlake_cursor_wm_info,
@@ -1727,10 +1727,10 @@ static void ironlake_update_wm(struct drm_device *dev)
 		DRM_DEBUG_KMS("FIFO watermarks For pipe A -"
 			      " plane %d, " "cursor: %d\n",
 			      plane_wm, cursor_wm);
-		enabled |= 1;
+		enabled |= 1 << PIPE_A;
 	}
 
-	if (g4x_compute_wm0(dev, 1,
+	if (g4x_compute_wm0(dev, PIPE_B,
 			    &ironlake_display_wm_info,
 			    ILK_LP0_PLANE_LATENCY,
 			    &ironlake_cursor_wm_info,
@@ -1741,7 +1741,7 @@ static void ironlake_update_wm(struct drm_device *dev)
 		DRM_DEBUG_KMS("FIFO watermarks For pipe B -"
 			      " plane %d, cursor: %d\n",
 			      plane_wm, cursor_wm);
-		enabled |= 2;
+		enabled |= 1 << PIPE_B;
 	}
 
 	/*
@@ -1801,7 +1801,7 @@ static void sandybridge_update_wm(struct drm_device *dev)
 	unsigned int enabled;
 
 	enabled = 0;
-	if (g4x_compute_wm0(dev, 0,
+	if (g4x_compute_wm0(dev, PIPE_A,
 			    &sandybridge_display_wm_info, latency,
 			    &sandybridge_cursor_wm_info, latency,
 			    &plane_wm, &cursor_wm)) {
@@ -1812,10 +1812,10 @@ static void sandybridge_update_wm(struct drm_device *dev)
 		DRM_DEBUG_KMS("FIFO watermarks For pipe A -"
 			      " plane %d, " "cursor: %d\n",
 			      plane_wm, cursor_wm);
-		enabled |= 1;
+		enabled |= 1 << PIPE_A;
 	}
 
-	if (g4x_compute_wm0(dev, 1,
+	if (g4x_compute_wm0(dev, PIPE_B,
 			    &sandybridge_display_wm_info, latency,
 			    &sandybridge_cursor_wm_info, latency,
 			    &plane_wm, &cursor_wm)) {
@@ -1826,7 +1826,7 @@ static void sandybridge_update_wm(struct drm_device *dev)
 		DRM_DEBUG_KMS("FIFO watermarks For pipe B -"
 			      " plane %d, cursor: %d\n",
 			      plane_wm, cursor_wm);
-		enabled |= 2;
+		enabled |= 1 << PIPE_B;
 	}
 
 	/*
@@ -1904,7 +1904,7 @@ static void ivybridge_update_wm(struct drm_device *dev)
 	unsigned int enabled;
 
 	enabled = 0;
-	if (g4x_compute_wm0(dev, 0,
+	if (g4x_compute_wm0(dev, PIPE_A,
 			    &sandybridge_display_wm_info, latency,
 			    &sandybridge_cursor_wm_info, latency,
 			    &plane_wm, &cursor_wm)) {
@@ -1915,10 +1915,10 @@ static void ivybridge_update_wm(struct drm_device *dev)
 		DRM_DEBUG_KMS("FIFO watermarks For pipe A -"
 			      " plane %d, " "cursor: %d\n",
 			      plane_wm, cursor_wm);
-		enabled |= 1;
+		enabled |= 1 << PIPE_A;
 	}
 
-	if (g4x_compute_wm0(dev, 1,
+	if (g4x_compute_wm0(dev, PIPE_B,
 			    &sandybridge_display_wm_info, latency,
 			    &sandybridge_cursor_wm_info, latency,
 			    &plane_wm, &cursor_wm)) {
@@ -1929,10 +1929,10 @@ static void ivybridge_update_wm(struct drm_device *dev)
 		DRM_DEBUG_KMS("FIFO watermarks For pipe B -"
 			      " plane %d, cursor: %d\n",
 			      plane_wm, cursor_wm);
-		enabled |= 2;
+		enabled |= 1 << PIPE_B;
 	}
 
-	if (g4x_compute_wm0(dev, 2,
+	if (g4x_compute_wm0(dev, PIPE_C,
 			    &sandybridge_display_wm_info, latency,
 			    &sandybridge_cursor_wm_info, latency,
 			    &plane_wm, &cursor_wm)) {
@@ -1943,7 +1943,7 @@ static void ivybridge_update_wm(struct drm_device *dev)
 		DRM_DEBUG_KMS("FIFO watermarks For pipe C -"
 			      " plane %d, cursor: %d\n",
 			      plane_wm, cursor_wm);
-		enabled |= 3;
+		enabled |= 1 << PIPE_C;
 	}
 
 	/*
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index f9889658329b..77b8a45fb10a 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -46,29 +46,26 @@ static void mga_crtc_load_lut(struct drm_crtc *crtc)
 
 static inline void mga_wait_vsync(struct mga_device *mdev)
 {
-	unsigned int count = 0;
+	unsigned long timeout = jiffies + HZ/10;
 	unsigned int status = 0;
 
 	do {
 		status = RREG32(MGAREG_Status);
-		count++;
-	} while ((status & 0x08) && (count < 250000));
-	count = 0;
+	} while ((status & 0x08) && time_before(jiffies, timeout));
+	timeout = jiffies + HZ/10;
 	status = 0;
 	do {
 		status = RREG32(MGAREG_Status);
-		count++;
-	} while (!(status & 0x08) && (count < 250000));
+	} while (!(status & 0x08) && time_before(jiffies, timeout));
 }
 
 static inline void mga_wait_busy(struct mga_device *mdev)
 {
-	unsigned int count = 0;
+	unsigned long timeout = jiffies + HZ;
 	unsigned int status = 0;
 	do {
 		status = RREG8(MGAREG_Status + 2);
-		count++;
-	} while ((status & 0x01) && (count < 500000));
+	} while ((status & 0x01) && time_before(jiffies, timeout));
 }
 
 /*
@@ -189,12 +186,12 @@ static int mga_g200wb_set_plls(struct mga_device *mdev, long clock)
 		WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
 		tmp = RREG8(DAC_DATA);
 		tmp |= MGA1064_PIX_CLK_CTL_CLK_DIS;
-		WREG_DAC(MGA1064_PIX_CLK_CTL_CLK_DIS, tmp);
+		WREG8(DAC_DATA, tmp);
 
 		WREG8(DAC_INDEX, MGA1064_REMHEADCTL);
 		tmp = RREG8(DAC_DATA);
 		tmp |= MGA1064_REMHEADCTL_CLKDIS;
-		WREG_DAC(MGA1064_REMHEADCTL, tmp);
+		WREG8(DAC_DATA, tmp);
 
 		/* select PLL Set C */
 		tmp = RREG8(MGAREG_MEM_MISC_READ);
@@ -204,7 +201,7 @@ static int mga_g200wb_set_plls(struct mga_device *mdev, long clock)
 		WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
 		tmp = RREG8(DAC_DATA);
 		tmp |= MGA1064_PIX_CLK_CTL_CLK_POW_DOWN | 0x80;
-		WREG_DAC(MGA1064_PIX_CLK_CTL, tmp);
+		WREG8(DAC_DATA, tmp);
 
 		udelay(500);
 
@@ -212,7 +209,7 @@ static int mga_g200wb_set_plls(struct mga_device *mdev, long clock)
 		WREG8(DAC_INDEX, MGA1064_VREF_CTL);
 		tmp = RREG8(DAC_DATA);
 		tmp &= ~0x04;
-		WREG_DAC(MGA1064_VREF_CTL, tmp);
+		WREG8(DAC_DATA, tmp);
 
 		udelay(50);
 
@@ -236,13 +233,13 @@ static int mga_g200wb_set_plls(struct mga_device *mdev, long clock)
 		tmp = RREG8(DAC_DATA);
 		tmp &= ~MGA1064_PIX_CLK_CTL_SEL_MSK;
 		tmp |= MGA1064_PIX_CLK_CTL_SEL_PLL;
-		WREG_DAC(MGA1064_PIX_CLK_CTL, tmp);
+		WREG8(DAC_DATA, tmp);
 
 		WREG8(DAC_INDEX, MGA1064_REMHEADCTL);
 		tmp = RREG8(DAC_DATA);
 		tmp &= ~MGA1064_REMHEADCTL_CLKSL_MSK;
 		tmp |= MGA1064_REMHEADCTL_CLKSL_PLL;
-		WREG_DAC(MGA1064_REMHEADCTL, tmp);
+		WREG8(DAC_DATA, tmp);
 
 		/* reset dotclock rate bit */
 		WREG8(MGAREG_SEQ_INDEX, 1);
@@ -253,7 +250,7 @@ static int mga_g200wb_set_plls(struct mga_device *mdev, long clock)
 		WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
 		tmp = RREG8(DAC_DATA);
 		tmp &= ~MGA1064_PIX_CLK_CTL_CLK_DIS;
-		WREG_DAC(MGA1064_PIX_CLK_CTL, tmp);
+		WREG8(DAC_DATA, tmp);
 
 		vcount = RREG8(MGAREG_VCOUNT);
 
@@ -318,7 +315,7 @@ static int mga_g200ev_set_plls(struct mga_device *mdev, long clock)
 	WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
 	tmp = RREG8(DAC_DATA);
 	tmp |= MGA1064_PIX_CLK_CTL_CLK_DIS;
-	WREG_DAC(MGA1064_PIX_CLK_CTL_CLK_DIS, tmp);
+	WREG8(DAC_DATA, tmp);
 
 	tmp = RREG8(MGAREG_MEM_MISC_READ);
 	tmp |= 0x3 << 2;
@@ -326,12 +323,12 @@ static int mga_g200ev_set_plls(struct mga_device *mdev, long clock)
 
 	WREG8(DAC_INDEX, MGA1064_PIX_PLL_STAT);
 	tmp = RREG8(DAC_DATA);
-	WREG_DAC(MGA1064_PIX_PLL_STAT, tmp & ~0x40);
+	WREG8(DAC_DATA, tmp & ~0x40);
 
 	WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
 	tmp = RREG8(DAC_DATA);
 	tmp |= MGA1064_PIX_CLK_CTL_CLK_POW_DOWN;
-	WREG_DAC(MGA1064_PIX_CLK_CTL, tmp);
+	WREG8(DAC_DATA, tmp);
 
 	WREG_DAC(MGA1064_EV_PIX_PLLC_M, m);
 	WREG_DAC(MGA1064_EV_PIX_PLLC_N, n);
@@ -342,7 +339,7 @@ static int mga_g200ev_set_plls(struct mga_device *mdev, long clock)
 	WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
 	tmp = RREG8(DAC_DATA);
 	tmp &= ~MGA1064_PIX_CLK_CTL_CLK_POW_DOWN;
-	WREG_DAC(MGA1064_PIX_CLK_CTL, tmp);
+	WREG8(DAC_DATA, tmp);
 
 	udelay(500);
 
@@ -350,11 +347,11 @@ static int mga_g200ev_set_plls(struct mga_device *mdev, long clock)
 	tmp = RREG8(DAC_DATA);
 	tmp &= ~MGA1064_PIX_CLK_CTL_SEL_MSK;
 	tmp |= MGA1064_PIX_CLK_CTL_SEL_PLL;
-	WREG_DAC(MGA1064_PIX_CLK_CTL, tmp);
+	WREG8(DAC_DATA, tmp);
 
 	WREG8(DAC_INDEX, MGA1064_PIX_PLL_STAT);
 	tmp = RREG8(DAC_DATA);
-	WREG_DAC(MGA1064_PIX_PLL_STAT, tmp | 0x40);
+	WREG8(DAC_DATA, tmp | 0x40);
 
 	tmp = RREG8(MGAREG_MEM_MISC_READ);
 	tmp |= (0x3 << 2);
@@ -363,7 +360,7 @@ static int mga_g200ev_set_plls(struct mga_device *mdev, long clock)
 	WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
 	tmp = RREG8(DAC_DATA);
 	tmp &= ~MGA1064_PIX_CLK_CTL_CLK_DIS;
-	WREG_DAC(MGA1064_PIX_CLK_CTL, tmp);
+	WREG8(DAC_DATA, tmp);
 
 	return 0;
 }
@@ -416,7 +413,7 @@ static int mga_g200eh_set_plls(struct mga_device *mdev, long clock)
 		WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
 		tmp = RREG8(DAC_DATA);
 		tmp |= MGA1064_PIX_CLK_CTL_CLK_DIS;
-		WREG_DAC(MGA1064_PIX_CLK_CTL_CLK_DIS, tmp);
+		WREG8(DAC_DATA, tmp);
 
 		tmp = RREG8(MGAREG_MEM_MISC_READ);
 		tmp |= 0x3 << 2;
@@ -425,7 +422,7 @@ static int mga_g200eh_set_plls(struct mga_device *mdev, long clock)
 		WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
 		tmp = RREG8(DAC_DATA);
 		tmp |= MGA1064_PIX_CLK_CTL_CLK_POW_DOWN;
-		WREG_DAC(MGA1064_PIX_CLK_CTL, tmp);
+		WREG8(DAC_DATA, tmp);
 
 		udelay(500);
 
@@ -439,13 +436,13 @@ static int mga_g200eh_set_plls(struct mga_device *mdev, long clock)
 		tmp = RREG8(DAC_DATA);
 		tmp &= ~MGA1064_PIX_CLK_CTL_SEL_MSK;
 		tmp |= MGA1064_PIX_CLK_CTL_SEL_PLL;
-		WREG_DAC(MGA1064_PIX_CLK_CTL, tmp);
+		WREG8(DAC_DATA, tmp);
 
 		WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
 		tmp = RREG8(DAC_DATA);
 		tmp &= ~MGA1064_PIX_CLK_CTL_CLK_DIS;
 		tmp &= ~MGA1064_PIX_CLK_CTL_CLK_POW_DOWN;
-		WREG_DAC(MGA1064_PIX_CLK_CTL, tmp);
+		WREG8(DAC_DATA, tmp);
 
 		vcount = RREG8(MGAREG_VCOUNT);
 
@@ -515,12 +512,12 @@ static int mga_g200er_set_plls(struct mga_device *mdev, long clock)
 	WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
 	tmp = RREG8(DAC_DATA);
 	tmp |= MGA1064_PIX_CLK_CTL_CLK_DIS;
-	WREG_DAC(MGA1064_PIX_CLK_CTL_CLK_DIS, tmp);
+	WREG8(DAC_DATA, tmp);
 
 	WREG8(DAC_INDEX, MGA1064_REMHEADCTL);
 	tmp = RREG8(DAC_DATA);
 	tmp |= MGA1064_REMHEADCTL_CLKDIS;
-	WREG_DAC(MGA1064_REMHEADCTL, tmp);
+	WREG8(DAC_DATA, tmp);
 
 	tmp = RREG8(MGAREG_MEM_MISC_READ);
 	tmp |= (0x3<<2) | 0xc0;
@@ -530,7 +527,7 @@ static int mga_g200er_set_plls(struct mga_device *mdev, long clock)
 	tmp = RREG8(DAC_DATA);
 	tmp &= ~MGA1064_PIX_CLK_CTL_CLK_DIS;
 	tmp |= MGA1064_PIX_CLK_CTL_CLK_POW_DOWN;
-	WREG_DAC(MGA1064_PIX_CLK_CTL, tmp);
+	WREG8(DAC_DATA, tmp);
 
 	udelay(500);
 
@@ -657,12 +654,26 @@ static void mga_g200wb_commit(struct drm_crtc *crtc)
 	WREG_DAC(MGA1064_GEN_IO_DATA, tmp);
 }
 
-
+/*
+   This is how the framebuffer base address is stored in g200 cards:
+   * Assume @offset is the gpu_addr variable of the framebuffer object
+   * Then addr is the number of _pixels_ (not bytes) from the start of
+     VRAM to the first pixel we want to display. (divided by 2 for 32bit
+     framebuffers)
+   * addr is stored in the CRTCEXT0, CRTCC and CRTCD registers
+   addr<20> -> CRTCEXT0<6>
+   addr<19-16> -> CRTCEXT0<3-0>
+   addr<15-8> -> CRTCC<7-0>
+   addr<7-0> -> CRTCD<7-0>
+   CRTCEXT0 has to be programmed last to trigger an update and make the
+   new addr variable take effect.
+ */
 void mga_set_start_address(struct drm_crtc *crtc, unsigned offset)
 {
 	struct mga_device *mdev = crtc->dev->dev_private;
 	u32 addr;
 	int count;
+	u8 crtcext0;
 
 	while (RREG8(0x1fda) & 0x08);
 	while (!(RREG8(0x1fda) & 0x08));
@@ -670,10 +681,17 @@ void mga_set_start_address(struct drm_crtc *crtc, unsigned offset)
 	count = RREG8(MGAREG_VCOUNT) + 2;
 	while (RREG8(MGAREG_VCOUNT) < count);
 
-	addr = offset >> 2;
+	WREG8(MGAREG_CRTCEXT_INDEX, 0);
+	crtcext0 = RREG8(MGAREG_CRTCEXT_DATA);
+	crtcext0 &= 0xB0;
+	addr = offset / 8;
+	/* Can't store addresses any higher than that...
+	   but we also don't have more than 16MB of memory, so it should be fine. */
+	WARN_ON(addr > 0x1fffff);
+	crtcext0 |= (!!(addr & (1<<20)))<<6;
 	WREG_CRT(0x0d, (u8)(addr & 0xff));
 	WREG_CRT(0x0c, (u8)(addr >> 8) & 0xff);
-	WREG_CRT(0xaf, (u8)(addr >> 16) & 0xf);
+	WREG_ECRT(0x0, ((u8)(addr >> 16) & 0xf) | crtcext0);
 }
 
 
@@ -829,11 +847,7 @@ static int mga_crtc_mode_set(struct drm_crtc *crtc,
 
 
 	for (i = 0; i < sizeof(dacvalue); i++) {
-		if ((i <= 0x03) ||
-		    (i == 0x07) ||
-		    (i == 0x0b) ||
-		    (i == 0x0f) ||
-		    ((i >= 0x13) && (i <= 0x17)) ||
+		if ((i <= 0x17) ||
 		    (i == 0x1b) ||
 		    (i == 0x1c) ||
 		    ((i >= 0x1f) && (i <= 0x29)) ||
diff --git a/drivers/lguest/page_tables.c b/drivers/lguest/page_tables.c
index 699187ab3800..5b9ac32801c7 100644
--- a/drivers/lguest/page_tables.c
+++ b/drivers/lguest/page_tables.c
@@ -1002,6 +1002,7 @@ void guest_set_pgd(struct lguest *lg, unsigned long gpgdir, u32 idx)
 			kill_guest(&lg->cpus[0],
 				   "Cannot populate switcher mapping");
 		}
+		lg->pgdirs[pgdir].last_host_cpu = -1;
 	}
 }
 
diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c
index 375c109607ff..f4f3038c1df0 100644
--- a/drivers/mmc/host/mmci.c
+++ b/drivers/mmc/host/mmci.c
@@ -1130,6 +1130,7 @@ static void mmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	struct variant_data *variant = host->variant;
 	u32 pwr = 0;
 	unsigned long flags;
+	int ret;
 
 	pm_runtime_get_sync(mmc_dev(mmc));
 
@@ -1161,8 +1162,12 @@ static void mmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 		break;
 	case MMC_POWER_ON:
 		if (!IS_ERR(mmc->supply.vqmmc) &&
-		    !regulator_is_enabled(mmc->supply.vqmmc))
-			regulator_enable(mmc->supply.vqmmc);
+		    !regulator_is_enabled(mmc->supply.vqmmc)) {
+			ret = regulator_enable(mmc->supply.vqmmc);
+			if (ret < 0)
+				dev_err(mmc_dev(mmc),
+					"failed to enable vqmmc regulator\n");
+		}
 
 		pwr |= MCI_PWR_ON;
 		break;
diff --git a/drivers/net/caif/Kconfig b/drivers/net/caif/Kconfig
index 7ffc756131a2..547098086773 100644
--- a/drivers/net/caif/Kconfig
+++ b/drivers/net/caif/Kconfig
@@ -43,7 +43,7 @@ config CAIF_HSI
 
 config CAIF_VIRTIO
 	tristate "CAIF virtio transport driver"
-	depends on CAIF
+	depends on CAIF && HAS_DMA
 	select VHOST_RING
 	select VIRTIO
 	select GENERIC_ALLOCATOR
diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c
index de570a8f8967..072c6f14e8fc 100644
--- a/drivers/net/ethernet/3com/3c59x.c
+++ b/drivers/net/ethernet/3com/3c59x.c
@@ -632,7 +632,6 @@ struct vortex_private {
 		pm_state_valid:1,				/* pci_dev->saved_config_space has sane contents */
 		open:1,
 		medialock:1,
-		must_free_region:1,				/* Flag: if zero, Cardbus owns the I/O region */
 		large_frames:1,			/* accept large frames */
 		handling_irq:1;			/* private in_irq indicator */
 	/* {get|set}_wol operations are already serialized by rtnl.
@@ -1012,6 +1011,12 @@ static int vortex_init_one(struct pci_dev *pdev,
 	if (rc < 0)
 		goto out;
 
+	rc = pci_request_regions(pdev, DRV_NAME);
+	if (rc < 0) {
+		pci_disable_device(pdev);
+		goto out;
+	}
+
 	unit = vortex_cards_found;
 
 	if (global_use_mmio < 0 && (unit >= MAX_UNITS || use_mmio[unit] < 0)) {
@@ -1027,6 +1032,7 @@ static int vortex_init_one(struct pci_dev *pdev,
 	if (!ioaddr) /* If mapping fails, fall-back to BAR 0... */
 		ioaddr = pci_iomap(pdev, 0, 0);
 	if (!ioaddr) {
+		pci_release_regions(pdev);
 		pci_disable_device(pdev);
 		rc = -ENOMEM;
 		goto out;
@@ -1036,6 +1042,7 @@ static int vortex_init_one(struct pci_dev *pdev,
 			   ent->driver_data, unit);
 	if (rc < 0) {
 		pci_iounmap(pdev, ioaddr);
+		pci_release_regions(pdev);
 		pci_disable_device(pdev);
 		goto out;
 	}
@@ -1178,11 +1185,6 @@ static int vortex_probe1(struct device *gendev, void __iomem *ioaddr, int irq,
 
 	/* PCI-only startup logic */
 	if (pdev) {
-		/* EISA resources already marked, so only PCI needs to do this here */
-		/* Ignore return value, because Cardbus drivers already allocate for us */
-		if (request_region(dev->base_addr, vci->io_size, print_name) != NULL)
-			vp->must_free_region = 1;
-
 		/* enable bus-mastering if necessary */
 		if (vci->flags & PCI_USES_MASTER)
 			pci_set_master(pdev);
@@ -1220,7 +1222,7 @@ static int vortex_probe1(struct device *gendev, void __iomem *ioaddr, int irq,
 					   &vp->rx_ring_dma);
 	retval = -ENOMEM;
 	if (!vp->rx_ring)
-		goto free_region;
+		goto free_device;
 
 	vp->tx_ring = (struct boom_tx_desc *)(vp->rx_ring + RX_RING_SIZE);
 	vp->tx_ring_dma = vp->rx_ring_dma + sizeof(struct boom_rx_desc) * RX_RING_SIZE;
@@ -1484,9 +1486,7 @@ free_ring:
 							+ sizeof(struct boom_tx_desc) * TX_RING_SIZE,
 						vp->rx_ring,
 						vp->rx_ring_dma);
-free_region:
-	if (vp->must_free_region)
-		release_region(dev->base_addr, vci->io_size);
+free_device:
 	free_netdev(dev);
 	pr_err(PFX "vortex_probe1 fails.  Returns %d\n", retval);
 out:
@@ -3254,8 +3254,9 @@ static void vortex_remove_one(struct pci_dev *pdev)
 							+ sizeof(struct boom_tx_desc) * TX_RING_SIZE,
 						vp->rx_ring,
 						vp->rx_ring_dma);
-	if (vp->must_free_region)
-		release_region(dev->base_addr, vp->io_size);
+
+	pci_release_regions(pdev);
+
 	free_netdev(dev);
 }
 
diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index ce4a030d3d0c..07f7ef05c3f2 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -3236,9 +3236,10 @@ bnad_init(struct bnad *bnad,
 
 	sprintf(bnad->wq_name, "%s_wq_%d", BNAD_NAME, bnad->id);
 	bnad->work_q = create_singlethread_workqueue(bnad->wq_name);
-
-	if (!bnad->work_q)
+	if (!bnad->work_q) {
+		iounmap(bnad->bar0);
 		return -ENOMEM;
+	}
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/cadence/Kconfig b/drivers/net/ethernet/cadence/Kconfig
index 1194446f859a..768285ec10f4 100644
--- a/drivers/net/ethernet/cadence/Kconfig
+++ b/drivers/net/ethernet/cadence/Kconfig
@@ -22,7 +22,7 @@ if NET_CADENCE
 
 config ARM_AT91_ETHER
 	tristate "AT91RM9200 Ethernet support"
-	depends on GENERIC_HARDIRQS
+	depends on GENERIC_HARDIRQS && HAS_DMA
 	select NET_CORE
 	select MACB
 	---help---
@@ -31,6 +31,7 @@ config ARM_AT91_ETHER
 
 config MACB
 	tristate "Cadence MACB/GEM support"
+	depends on HAS_DMA
 	select PHYLIB
 	---help---
 	  The Cadence MACB ethernet interface is found on many Atmel AT32 and
diff --git a/drivers/net/ethernet/calxeda/Kconfig b/drivers/net/ethernet/calxeda/Kconfig
index aba435c3d4ae..184a063bed5f 100644
--- a/drivers/net/ethernet/calxeda/Kconfig
+++ b/drivers/net/ethernet/calxeda/Kconfig
@@ -1,6 +1,6 @@
 config NET_CALXEDA_XGMAC
 	tristate "Calxeda 1G/10G XGMAC Ethernet driver"
-	depends on HAS_IOMEM
+	depends on HAS_IOMEM && HAS_DMA
 	select CRC32
 	help
 	  This is the driver for the XGMAC Ethernet IP block found on Calxeda
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index aff0310a778b..ca9825ca88c9 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -87,6 +87,8 @@
 #define FEC_QUIRK_HAS_GBIT		(1 << 3)
 /* Controller has extend desc buffer */
 #define FEC_QUIRK_HAS_BUFDESC_EX	(1 << 4)
+/* Controller has hardware checksum support */
+#define FEC_QUIRK_HAS_CSUM		(1 << 5)
 
 static struct platform_device_id fec_devtype[] = {
 	{
@@ -105,7 +107,7 @@ static struct platform_device_id fec_devtype[] = {
 	}, {
 		.name = "imx6q-fec",
 		.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
-				FEC_QUIRK_HAS_BUFDESC_EX,
+				FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM,
 	}, {
 		.name = "mvf-fec",
 		.driver_data = FEC_QUIRK_ENET_MAC,
@@ -1744,6 +1746,8 @@ static const struct net_device_ops fec_netdev_ops = {
 static int fec_enet_init(struct net_device *ndev)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
+	const struct platform_device_id *id_entry =
+				platform_get_device_id(fep->pdev);
 	struct bufdesc *cbd_base;
 
 	/* Allocate memory for buffer descriptors. */
@@ -1775,12 +1779,14 @@ static int fec_enet_init(struct net_device *ndev)
 	writel(FEC_RX_DISABLED_IMASK, fep->hwp + FEC_IMASK);
 	netif_napi_add(ndev, &fep->napi, fec_enet_rx_napi, FEC_NAPI_WEIGHT);
 
-	/* enable hw accelerator */
-	ndev->features |= (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM
-			| NETIF_F_RXCSUM);
-	ndev->hw_features |= (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM
-			| NETIF_F_RXCSUM);
-	fep->csum_flags |= FLAG_RX_CSUM_ENABLED;
+	if (id_entry->driver_data & FEC_QUIRK_HAS_CSUM) {
+		/* enable hw accelerator */
+		ndev->features |= (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM
+				| NETIF_F_RXCSUM);
+		ndev->hw_features |= (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM
+				| NETIF_F_RXCSUM);
+		fep->csum_flags |= FLAG_RX_CSUM_ENABLED;
+	}
 
 	fec_restart(ndev, 0);
 
diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index 4989481c19f0..d300a0c0eafc 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -359,10 +359,26 @@ static int emac_reset(struct emac_instance *dev)
 	}
 
 #ifdef CONFIG_PPC_DCR_NATIVE
-	/* Enable internal clock source */
-	if (emac_has_feature(dev, EMAC_FTR_460EX_PHY_CLK_FIX))
-		dcri_clrset(SDR0, SDR0_ETH_CFG,
-			    0, SDR0_ETH_CFG_ECS << dev->cell_index);
+	/*
+	 * PPC460EX/GT Embedded Processor Advanced User's Manual
+	 * section 28.10.1 Mode Register 0 (EMACx_MR0) states:
+	 * Note: The PHY must provide a TX Clk in order to perform a soft reset
+	 * of the EMAC. If none is present, select the internal clock
+	 * (SDR0_ETH_CFG[EMACx_PHY_CLK] = 1).
+	 * After a soft reset, select the external clock.
+	 */
+	if (emac_has_feature(dev, EMAC_FTR_460EX_PHY_CLK_FIX)) {
+		if (dev->phy_address == 0xffffffff &&
+		    dev->phy_map == 0xffffffff) {
+			/* No PHY: select internal loop clock before reset */
+			dcri_clrset(SDR0, SDR0_ETH_CFG,
+				    0, SDR0_ETH_CFG_ECS << dev->cell_index);
+		} else {
+			/* PHY present: select external clock before reset */
+			dcri_clrset(SDR0, SDR0_ETH_CFG,
+				    SDR0_ETH_CFG_ECS << dev->cell_index, 0);
+		}
+	}
 #endif
 
 	out_be32(&p->mr0, EMAC_MR0_SRST);
@@ -370,10 +386,14 @@ static int emac_reset(struct emac_instance *dev)
 		--n;
 
 #ifdef CONFIG_PPC_DCR_NATIVE
-	 /* Enable external clock source */
-	if (emac_has_feature(dev, EMAC_FTR_460EX_PHY_CLK_FIX))
-		dcri_clrset(SDR0, SDR0_ETH_CFG,
-			    SDR0_ETH_CFG_ECS << dev->cell_index, 0);
+	if (emac_has_feature(dev, EMAC_FTR_460EX_PHY_CLK_FIX)) {
+		if (dev->phy_address == 0xffffffff &&
+		    dev->phy_map == 0xffffffff) {
+			/* No PHY: restore external clock source after reset */
+			dcri_clrset(SDR0, SDR0_ETH_CFG,
+				    SDR0_ETH_CFG_ECS << dev->cell_index, 0);
+		}
+	}
 #endif
 
 	if (n) {
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_resources.c b/drivers/net/ethernet/mellanox/mlx4/en_resources.c
index 91f2b2c43c12..d3f508697a3d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_resources.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_resources.c
@@ -60,7 +60,7 @@ void mlx4_en_fill_qp_context(struct mlx4_en_priv *priv, int size, int stride,
 	context->pri_path.sched_queue = 0x83 | (priv->port - 1) << 6;
 	if (user_prio >= 0) {
 		context->pri_path.sched_queue |= user_prio << 3;
-		context->pri_path.feup = 1 << 6;
+		context->pri_path.feup = MLX4_FEUP_FORCE_ETH_UP;
 	}
 	context->pri_path.counter_index = 0xff;
 	context->cqn_send = cpu_to_be32(cqn);
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index b147bdd40768..58a8e535d698 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -131,7 +131,9 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags)
 		[2] = "RSS XOR Hash Function support",
 		[3] = "Device manage flow steering support",
 		[4] = "Automatic MAC reassignment support",
-		[5] = "Time stamping support"
+		[5] = "Time stamping support",
+		[6] = "VST (control vlan insertion/stripping) support",
+		[7] = "FSM (MAC anti-spoofing) support"
 	};
 	int i;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index e12e0d2e0ee0..1157f028a90f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -372,24 +372,29 @@ static int update_vport_qp_param(struct mlx4_dev *dev,
 		if (MLX4_QP_ST_RC == qp_type)
 			return -EINVAL;
 
+		/* force strip vlan by clear vsd */
+		qpc->param3 &= ~cpu_to_be32(MLX4_STRIP_VLAN);
+		if (0 != vp_oper->state.default_vlan) {
+			qpc->pri_path.vlan_control =
+				MLX4_VLAN_CTRL_ETH_TX_BLOCK_TAGGED |
+				MLX4_VLAN_CTRL_ETH_RX_BLOCK_PRIO_TAGGED |
+				MLX4_VLAN_CTRL_ETH_RX_BLOCK_UNTAGGED;
+		} else { /* priority tagged */
+			qpc->pri_path.vlan_control =
+				MLX4_VLAN_CTRL_ETH_TX_BLOCK_TAGGED |
+				MLX4_VLAN_CTRL_ETH_RX_BLOCK_TAGGED;
+		}
+
+		qpc->pri_path.fvl_rx |= MLX4_FVL_RX_FORCE_ETH_VLAN;
 		qpc->pri_path.vlan_index = vp_oper->vlan_idx;
-		qpc->pri_path.fl = (1 << 6) | (1 << 2); /* set cv bit and hide_cqe_vlan bit*/
-		qpc->pri_path.feup |= 1 << 3; /* set fvl bit */
+		qpc->pri_path.fl |= MLX4_FL_CV | MLX4_FL_ETH_HIDE_CQE_VLAN;
+		qpc->pri_path.feup |= MLX4_FEUP_FORCE_ETH_UP | MLX4_FVL_FORCE_ETH_VLAN;
 		qpc->pri_path.sched_queue &= 0xC7;
 		qpc->pri_path.sched_queue |= (vp_oper->state.default_qos) << 3;
-		mlx4_dbg(dev, "qp %d  port %d Q 0x%x set vlan to %d vidx %d feup %x fl %x\n",
-			 be32_to_cpu(qpc->local_qpn) & 0xffffff, port,
-			 (int)(qpc->pri_path.sched_queue), vp_oper->state.default_vlan,
-			 vp_oper->vlan_idx, (int)(qpc->pri_path.feup),
-			 (int)(qpc->pri_path.fl));
 	}
 	if (vp_oper->state.spoofchk) {
-		qpc->pri_path.feup |= 1 << 5; /* set fsm bit */;
+		qpc->pri_path.feup |= MLX4_FSM_FORCE_ETH_SRC_MAC;
 		qpc->pri_path.grh_mylmc = (0x80 & qpc->pri_path.grh_mylmc) + vp_oper->mac_idx;
-		mlx4_dbg(dev, "spoof qp %d  port %d feup  0x%x, myLmc 0x%x mindx %d\n",
-			 be32_to_cpu(qpc->local_qpn) & 0xffffff, port,
-			 (int)qpc->pri_path.feup, (int)qpc->pri_path.grh_mylmc,
-			 vp_oper->mac_idx);
 	}
 	return 0;
 }
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
index 90c253b145ef..019c5f78732e 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
@@ -429,6 +429,7 @@ struct qlcnic_hardware_context {
 
 	u16 port_type;
 	u16 board_type;
+	u16 supported_type;
 
 	u16 link_speed;
 	u16 link_duplex;
@@ -1514,6 +1515,7 @@ void qlcnic_create_diag_entries(struct qlcnic_adapter *adapter);
 void qlcnic_remove_diag_entries(struct qlcnic_adapter *adapter);
 void qlcnic_82xx_add_sysfs(struct qlcnic_adapter *adapter);
 void qlcnic_82xx_remove_sysfs(struct qlcnic_adapter *adapter);
+int qlcnic_82xx_get_settings(struct qlcnic_adapter *, struct ethtool_cmd *);
 
 int qlcnicvf_config_bridged_mode(struct qlcnic_adapter *, u32);
 int qlcnicvf_config_led(struct qlcnic_adapter *, u32, u32);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
index ea790a93ee7c..b4ff1e35a11d 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
@@ -696,15 +696,14 @@ u32 qlcnic_83xx_mac_rcode(struct qlcnic_adapter *adapter)
 	return 1;
 }
 
-u32 qlcnic_83xx_mbx_poll(struct qlcnic_adapter *adapter)
+u32 qlcnic_83xx_mbx_poll(struct qlcnic_adapter *adapter, u32 *wait_time)
 {
 	u32 data;
-	unsigned long wait_time = 0;
 	struct qlcnic_hardware_context *ahw = adapter->ahw;
 	/* wait for mailbox completion */
 	do {
 		data = QLCRDX(ahw, QLCNIC_FW_MBX_CTRL);
-		if (++wait_time > QLCNIC_MBX_TIMEOUT) {
+		if (++(*wait_time) > QLCNIC_MBX_TIMEOUT) {
 			data = QLCNIC_RCODE_TIMEOUT;
 			break;
 		}
@@ -720,8 +719,8 @@ int qlcnic_83xx_mbx_op(struct qlcnic_adapter *adapter,
 	u16 opcode;
 	u8 mbx_err_code;
 	unsigned long flags;
-	u32 rsp, mbx_val, fw_data, rsp_num, mbx_cmd;
 	struct qlcnic_hardware_context *ahw = adapter->ahw;
+	u32 rsp, mbx_val, fw_data, rsp_num, mbx_cmd, wait_time = 0;
 
 	opcode = LSW(cmd->req.arg[0]);
 	if (!test_bit(QLC_83XX_MBX_READY, &adapter->ahw->idc.status)) {
@@ -754,15 +753,13 @@ int qlcnic_83xx_mbx_op(struct qlcnic_adapter *adapter,
 	/* Signal FW about the impending command */
 	QLCWRX(ahw, QLCNIC_HOST_MBX_CTRL, QLCNIC_SET_OWNER);
 poll:
-	rsp = qlcnic_83xx_mbx_poll(adapter);
+	rsp = qlcnic_83xx_mbx_poll(adapter, &wait_time);
 	if (rsp != QLCNIC_RCODE_TIMEOUT) {
 		/* Get the FW response data */
 		fw_data = readl(QLCNIC_MBX_FW(ahw, 0));
 		if (fw_data &  QLCNIC_MBX_ASYNC_EVENT) {
 			__qlcnic_83xx_process_aen(adapter);
-			mbx_val = QLCRDX(ahw, QLCNIC_HOST_MBX_CTRL);
-			if (mbx_val)
-				goto poll;
+			goto poll;
 		}
 		mbx_err_code = QLCNIC_MBX_STATUS(fw_data);
 		rsp_num = QLCNIC_MBX_NUM_REGS(fw_data);
@@ -1276,11 +1273,13 @@ out:
 	return err;
 }
 
-static int qlcnic_83xx_diag_alloc_res(struct net_device *netdev, int test)
+static int qlcnic_83xx_diag_alloc_res(struct net_device *netdev, int test,
+				      int num_sds_ring)
 {
 	struct qlcnic_adapter *adapter = netdev_priv(netdev);
 	struct qlcnic_host_sds_ring *sds_ring;
 	struct qlcnic_host_rds_ring *rds_ring;
+	u16 adapter_state = adapter->is_up;
 	u8 ring;
 	int ret;
 
@@ -1304,6 +1303,10 @@ static int qlcnic_83xx_diag_alloc_res(struct net_device *netdev, int test)
 	ret = qlcnic_fw_create_ctx(adapter);
 	if (ret) {
 		qlcnic_detach(adapter);
+		if (adapter_state == QLCNIC_ADAPTER_UP_MAGIC) {
+			adapter->max_sds_rings = num_sds_ring;
+			qlcnic_attach(adapter);
+		}
 		netif_device_attach(netdev);
 		return ret;
 	}
@@ -1596,7 +1599,8 @@ int qlcnic_83xx_loopback_test(struct net_device *netdev, u8 mode)
 	if (test_and_set_bit(__QLCNIC_RESETTING, &adapter->state))
 		return -EBUSY;
 
-	ret = qlcnic_83xx_diag_alloc_res(netdev, QLCNIC_LOOPBACK_TEST);
+	ret = qlcnic_83xx_diag_alloc_res(netdev, QLCNIC_LOOPBACK_TEST,
+					 max_sds_rings);
 	if (ret)
 		goto fail_diag_alloc;
 
@@ -2830,6 +2834,23 @@ int qlcnic_83xx_test_link(struct qlcnic_adapter *adapter)
 			break;
 		}
 		config = cmd.rsp.arg[3];
+		if (QLC_83XX_SFP_PRESENT(config)) {
+			switch (ahw->module_type) {
+			case LINKEVENT_MODULE_OPTICAL_UNKNOWN:
+			case LINKEVENT_MODULE_OPTICAL_SRLR:
+			case LINKEVENT_MODULE_OPTICAL_LRM:
+			case LINKEVENT_MODULE_OPTICAL_SFP_1G:
+				ahw->supported_type = PORT_FIBRE;
+				break;
+			case LINKEVENT_MODULE_TWINAX_UNSUPPORTED_CABLE:
+			case LINKEVENT_MODULE_TWINAX_UNSUPPORTED_CABLELEN:
+			case LINKEVENT_MODULE_TWINAX:
+				ahw->supported_type = PORT_TP;
+				break;
+			default:
+				ahw->supported_type = PORT_OTHER;
+			}
+		}
 		if (config & 1)
 			err = 1;
 	}
@@ -2838,7 +2859,8 @@ out:
 	return config;
 }
 
-int qlcnic_83xx_get_settings(struct qlcnic_adapter *adapter)
+int qlcnic_83xx_get_settings(struct qlcnic_adapter *adapter,
+			     struct ethtool_cmd *ecmd)
 {
 	u32 config = 0;
 	int status = 0;
@@ -2851,6 +2873,54 @@ int qlcnic_83xx_get_settings(struct qlcnic_adapter *adapter)
 	ahw->module_type = QLC_83XX_SFP_MODULE_TYPE(config);
 	/* hard code until there is a way to get it from flash */
 	ahw->board_type = QLCNIC_BRDTYPE_83XX_10G;
+
+	if (netif_running(adapter->netdev) && ahw->has_link_events) {
+		ethtool_cmd_speed_set(ecmd, ahw->link_speed);
+		ecmd->duplex = ahw->link_duplex;
+		ecmd->autoneg = ahw->link_autoneg;
+	} else {
+		ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
+		ecmd->duplex = DUPLEX_UNKNOWN;
+		ecmd->autoneg = AUTONEG_DISABLE;
+	}
+
+	if (ahw->port_type == QLCNIC_XGBE) {
+		ecmd->supported = SUPPORTED_1000baseT_Full;
+		ecmd->advertising = ADVERTISED_1000baseT_Full;
+	} else {
+		ecmd->supported = (SUPPORTED_10baseT_Half |
+				   SUPPORTED_10baseT_Full |
+				   SUPPORTED_100baseT_Half |
+				   SUPPORTED_100baseT_Full |
+				   SUPPORTED_1000baseT_Half |
+				   SUPPORTED_1000baseT_Full);
+		ecmd->advertising = (ADVERTISED_100baseT_Half |
+				     ADVERTISED_100baseT_Full |
+				     ADVERTISED_1000baseT_Half |
+				     ADVERTISED_1000baseT_Full);
+	}
+
+	switch (ahw->supported_type) {
+	case PORT_FIBRE:
+		ecmd->supported |= SUPPORTED_FIBRE;
+		ecmd->advertising |= ADVERTISED_FIBRE;
+		ecmd->port = PORT_FIBRE;
+		ecmd->transceiver = XCVR_EXTERNAL;
+		break;
+	case PORT_TP:
+		ecmd->supported |= SUPPORTED_TP;
+		ecmd->advertising |= ADVERTISED_TP;
+		ecmd->port = PORT_TP;
+		ecmd->transceiver = XCVR_INTERNAL;
+		break;
+	default:
+		ecmd->supported |= SUPPORTED_FIBRE;
+		ecmd->advertising |= ADVERTISED_FIBRE;
+		ecmd->port = PORT_OTHER;
+		ecmd->transceiver = XCVR_EXTERNAL;
+		break;
+	}
+	ecmd->phy_address = ahw->physical_port;
 	return status;
 }
 
@@ -3046,7 +3116,8 @@ int qlcnic_83xx_interrupt_test(struct net_device *netdev)
 	if (test_and_set_bit(__QLCNIC_RESETTING, &adapter->state))
 		return -EIO;
 
-	ret = qlcnic_83xx_diag_alloc_res(netdev, QLCNIC_INTERRUPT_TEST);
+	ret = qlcnic_83xx_diag_alloc_res(netdev, QLCNIC_INTERRUPT_TEST,
+					 max_sds_rings);
 	if (ret)
 		goto fail_diag_irq;
 
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h
index 1f1d85e6f2af..f5db67fc9f55 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h
@@ -603,7 +603,7 @@ int qlcnic_83xx_get_vnic_pf_info(struct qlcnic_adapter *, struct qlcnic_info *);
 
 void qlcnic_83xx_get_minidump_template(struct qlcnic_adapter *);
 void qlcnic_83xx_get_stats(struct qlcnic_adapter *adapter, u64 *data);
-int qlcnic_83xx_get_settings(struct qlcnic_adapter *);
+int qlcnic_83xx_get_settings(struct qlcnic_adapter *, struct ethtool_cmd *);
 int qlcnic_83xx_set_settings(struct qlcnic_adapter *, struct ethtool_cmd *);
 void qlcnic_83xx_get_pauseparam(struct qlcnic_adapter *,
 				struct ethtool_pauseparam *);
@@ -620,7 +620,7 @@ int qlcnic_83xx_flash_test(struct qlcnic_adapter *);
 int qlcnic_83xx_enable_flash_write(struct qlcnic_adapter *);
 int qlcnic_83xx_disable_flash_write(struct qlcnic_adapter *);
 u32 qlcnic_83xx_mac_rcode(struct qlcnic_adapter *);
-u32 qlcnic_83xx_mbx_poll(struct qlcnic_adapter *);
+u32 qlcnic_83xx_mbx_poll(struct qlcnic_adapter *, u32 *);
 void qlcnic_83xx_enable_mbx_poll(struct qlcnic_adapter *);
 void qlcnic_83xx_disable_mbx_poll(struct qlcnic_adapter *);
 #endif
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
index ab1d8d99cbd5..c67d1eb35e8f 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
@@ -435,10 +435,6 @@ static void qlcnic_83xx_idc_attach_driver(struct qlcnic_adapter *adapter)
 	}
 done:
 	netif_device_attach(netdev);
-	if (netif_running(netdev)) {
-		netif_carrier_on(netdev);
-		netif_wake_queue(netdev);
-	}
 }
 
 static int qlcnic_83xx_idc_enter_failed_state(struct qlcnic_adapter *adapter,
@@ -642,15 +638,21 @@ static int qlcnic_83xx_idc_reattach_driver(struct qlcnic_adapter *adapter)
 
 static void qlcnic_83xx_idc_update_idc_params(struct qlcnic_adapter *adapter)
 {
+	struct qlcnic_hardware_context *ahw = adapter->ahw;
+
 	qlcnic_83xx_idc_update_drv_presence_reg(adapter, 1, 1);
-	clear_bit(__QLCNIC_RESETTING, &adapter->state);
 	set_bit(QLC_83XX_MBX_READY, &adapter->ahw->idc.status);
 	qlcnic_83xx_idc_update_audit_reg(adapter, 0, 1);
 	set_bit(QLC_83XX_MODULE_LOADED, &adapter->ahw->idc.status);
-	adapter->ahw->idc.quiesce_req = 0;
-	adapter->ahw->idc.delay = QLC_83XX_IDC_FW_POLL_DELAY;
-	adapter->ahw->idc.err_code = 0;
-	adapter->ahw->idc.collect_dump = 0;
+
+	ahw->idc.quiesce_req = 0;
+	ahw->idc.delay = QLC_83XX_IDC_FW_POLL_DELAY;
+	ahw->idc.err_code = 0;
+	ahw->idc.collect_dump = 0;
+	ahw->reset_context = 0;
+	adapter->tx_timeo_cnt = 0;
+
+	clear_bit(__QLCNIC_RESETTING, &adapter->state);
 }
 
 /**
@@ -851,6 +853,7 @@ static int qlcnic_83xx_idc_ready_state(struct qlcnic_adapter *adapter)
 	/* Check for soft reset request */
 	if (ahw->reset_context &&
 	    !(val & QLC_83XX_IDC_DISABLE_FW_RESET_RECOVERY)) {
+		adapter->ahw->reset_context = 0;
 		qlcnic_83xx_idc_tx_soft_reset(adapter);
 		return ret;
 	}
@@ -914,6 +917,7 @@ static int qlcnic_83xx_idc_need_quiesce_state(struct qlcnic_adapter *adapter)
 static int qlcnic_83xx_idc_failed_state(struct qlcnic_adapter *adapter)
 {
 	dev_err(&adapter->pdev->dev, "%s: please restart!!\n", __func__);
+	clear_bit(__QLCNIC_RESETTING, &adapter->state);
 	adapter->ahw->idc.err_code = -EIO;
 
 	return 0;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
index 08efb4635007..f67652de5a63 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
@@ -131,12 +131,13 @@ static const char qlcnic_83xx_rx_stats_strings[][ETH_GSTRING_LEN] = {
 	"ctx_lro_pkt_cnt",
 	"ctx_ip_csum_error",
 	"ctx_rx_pkts_wo_ctx",
-	"ctx_rx_pkts_dropped_wo_sts",
+	"ctx_rx_pkts_drop_wo_sds_on_card",
+	"ctx_rx_pkts_drop_wo_sds_on_host",
 	"ctx_rx_osized_pkts",
 	"ctx_rx_pkts_dropped_wo_rds",
 	"ctx_rx_unexpected_mcast_pkts",
 	"ctx_invalid_mac_address",
-	"ctx_rx_rds_ring_prim_attemoted",
+	"ctx_rx_rds_ring_prim_attempted",
 	"ctx_rx_rds_ring_prim_success",
 	"ctx_num_lro_flows_added",
 	"ctx_num_lro_flows_removed",
@@ -251,6 +252,18 @@ static int
 qlcnic_get_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
 {
 	struct qlcnic_adapter *adapter = netdev_priv(dev);
+
+	if (qlcnic_82xx_check(adapter))
+		return qlcnic_82xx_get_settings(adapter, ecmd);
+	else if (qlcnic_83xx_check(adapter))
+		return qlcnic_83xx_get_settings(adapter, ecmd);
+
+	return -EIO;
+}
+
+int qlcnic_82xx_get_settings(struct qlcnic_adapter *adapter,
+			     struct ethtool_cmd *ecmd)
+{
 	struct qlcnic_hardware_context *ahw = adapter->ahw;
 	u32 speed, reg;
 	int check_sfp_module = 0;
@@ -276,10 +289,7 @@ qlcnic_get_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
 
 	} else if (adapter->ahw->port_type == QLCNIC_XGBE) {
 		u32 val = 0;
-		if (qlcnic_83xx_check(adapter))
-			qlcnic_83xx_get_settings(adapter);
-		else
-			val = QLCRD32(adapter, QLCNIC_PORT_MODE_ADDR);
+		val = QLCRD32(adapter, QLCNIC_PORT_MODE_ADDR);
 
 		if (val == QLCNIC_PORT_MODE_802_3_AP) {
 			ecmd->supported = SUPPORTED_1000baseT_Full;
@@ -289,16 +299,13 @@ qlcnic_get_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
 			ecmd->advertising = ADVERTISED_10000baseT_Full;
 		}
 
-		if (netif_running(dev) && adapter->ahw->has_link_events) {
-			if (qlcnic_82xx_check(adapter)) {
-				reg = QLCRD32(adapter,
-					      P3P_LINK_SPEED_REG(pcifn));
-				speed = P3P_LINK_SPEED_VAL(pcifn, reg);
-				ahw->link_speed = speed * P3P_LINK_SPEED_MHZ;
-			}
-			ethtool_cmd_speed_set(ecmd, adapter->ahw->link_speed);
-			ecmd->autoneg = adapter->ahw->link_autoneg;
-			ecmd->duplex = adapter->ahw->link_duplex;
+		if (netif_running(adapter->netdev) && ahw->has_link_events) {
+			reg = QLCRD32(adapter, P3P_LINK_SPEED_REG(pcifn));
+			speed = P3P_LINK_SPEED_VAL(pcifn, reg);
+			ahw->link_speed = speed * P3P_LINK_SPEED_MHZ;
+			ethtool_cmd_speed_set(ecmd, ahw->link_speed);
+			ecmd->autoneg = ahw->link_autoneg;
+			ecmd->duplex = ahw->link_duplex;
 			goto skip;
 		}
 
@@ -340,8 +347,8 @@ skip:
 	case QLCNIC_BRDTYPE_P3P_10G_SFP_QT:
 		ecmd->advertising |= ADVERTISED_TP;
 		ecmd->supported |= SUPPORTED_TP;
-		check_sfp_module = netif_running(dev) &&
-				   adapter->ahw->has_link_events;
+		check_sfp_module = netif_running(adapter->netdev) &&
+				   ahw->has_link_events;
 	case QLCNIC_BRDTYPE_P3P_10G_XFP:
 		ecmd->supported |= SUPPORTED_FIBRE;
 		ecmd->advertising |= ADVERTISED_FIBRE;
@@ -355,8 +362,8 @@ skip:
 			ecmd->advertising |=
 				(ADVERTISED_FIBRE | ADVERTISED_TP);
 			ecmd->port = PORT_FIBRE;
-			check_sfp_module = netif_running(dev) &&
-					   adapter->ahw->has_link_events;
+			check_sfp_module = netif_running(adapter->netdev) &&
+					   ahw->has_link_events;
 		} else {
 			ecmd->autoneg = AUTONEG_ENABLE;
 			ecmd->supported |= (SUPPORTED_TP | SUPPORTED_Autoneg);
@@ -365,13 +372,6 @@ skip:
 			ecmd->port = PORT_TP;
 		}
 		break;
-	case QLCNIC_BRDTYPE_83XX_10G:
-		ecmd->autoneg = AUTONEG_DISABLE;
-		ecmd->supported |= (SUPPORTED_FIBRE | SUPPORTED_TP);
-		ecmd->advertising |= (ADVERTISED_FIBRE | ADVERTISED_TP);
-		ecmd->port = PORT_FIBRE;
-		check_sfp_module = netif_running(dev) && ahw->has_link_events;
-		break;
 	default:
 		dev_err(&adapter->pdev->dev, "Unsupported board model %d\n",
 			adapter->ahw->board_type);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h
index 95b1b5732838..b6818f4356b9 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h
@@ -134,7 +134,7 @@ struct qlcnic_mailbox_metadata {
 
 #define QLCNIC_SET_OWNER        1
 #define QLCNIC_CLR_OWNER        0
-#define QLCNIC_MBX_TIMEOUT      10000
+#define QLCNIC_MBX_TIMEOUT      5000
 
 #define QLCNIC_MBX_RSP_OK	1
 #define QLCNIC_MBX_PORT_RSP_OK	0x1a
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index 264d5a4f8153..8fb836d4129f 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -37,24 +37,24 @@ MODULE_PARM_DESC(qlcnic_mac_learn,
 		 "Mac Filter (0=learning is disabled, 1=Driver learning is enabled, 2=FDB learning is enabled)");
 
 int qlcnic_use_msi = 1;
-MODULE_PARM_DESC(use_msi, "MSI interrupt (0=disabled, 1=enabled");
+MODULE_PARM_DESC(use_msi, "MSI interrupt (0=disabled, 1=enabled)");
 module_param_named(use_msi, qlcnic_use_msi, int, 0444);
 
 int qlcnic_use_msi_x = 1;
-MODULE_PARM_DESC(use_msi_x, "MSI-X interrupt (0=disabled, 1=enabled");
+MODULE_PARM_DESC(use_msi_x, "MSI-X interrupt (0=disabled, 1=enabled)");
 module_param_named(use_msi_x, qlcnic_use_msi_x, int, 0444);
 
 int qlcnic_auto_fw_reset = 1;
-MODULE_PARM_DESC(auto_fw_reset, "Auto firmware reset (0=disabled, 1=enabled");
+MODULE_PARM_DESC(auto_fw_reset, "Auto firmware reset (0=disabled, 1=enabled)");
 module_param_named(auto_fw_reset, qlcnic_auto_fw_reset, int, 0644);
 
 int qlcnic_load_fw_file;
-MODULE_PARM_DESC(load_fw_file, "Load firmware from (0=flash, 1=file");
+MODULE_PARM_DESC(load_fw_file, "Load firmware from (0=flash, 1=file)");
 module_param_named(load_fw_file, qlcnic_load_fw_file, int, 0444);
 
 int qlcnic_config_npars;
 module_param(qlcnic_config_npars, int, 0444);
-MODULE_PARM_DESC(qlcnic_config_npars, "Configure NPARs (0=disabled, 1=enabled");
+MODULE_PARM_DESC(qlcnic_config_npars, "Configure NPARs (0=disabled, 1=enabled)");
 
 static int qlcnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent);
 static void qlcnic_remove(struct pci_dev *pdev);
@@ -308,6 +308,23 @@ int qlcnic_read_mac_addr(struct qlcnic_adapter *adapter)
 	return 0;
 }
 
+static void qlcnic_delete_adapter_mac(struct qlcnic_adapter *adapter)
+{
+	struct qlcnic_mac_list_s *cur;
+	struct list_head *head;
+
+	list_for_each(head, &adapter->mac_list) {
+		cur = list_entry(head, struct qlcnic_mac_list_s, list);
+		if (!memcmp(adapter->mac_addr, cur->mac_addr, ETH_ALEN)) {
+			qlcnic_sre_macaddr_change(adapter, cur->mac_addr,
+						  0, QLCNIC_MAC_DEL);
+			list_del(&cur->list);
+			kfree(cur);
+			return;
+		}
+	}
+}
+
 static int qlcnic_set_mac(struct net_device *netdev, void *p)
 {
 	struct qlcnic_adapter *adapter = netdev_priv(netdev);
@@ -322,11 +339,15 @@ static int qlcnic_set_mac(struct net_device *netdev, void *p)
 	if (!is_valid_ether_addr(addr->sa_data))
 		return -EINVAL;
 
+	if (!memcmp(adapter->mac_addr, addr->sa_data, ETH_ALEN))
+		return 0;
+
 	if (test_bit(__QLCNIC_DEV_UP, &adapter->state)) {
 		netif_device_detach(netdev);
 		qlcnic_napi_disable(adapter);
 	}
 
+	qlcnic_delete_adapter_mac(adapter);
 	memcpy(adapter->mac_addr, addr->sa_data, netdev->addr_len);
 	memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
 	qlcnic_set_multi(adapter->netdev);
@@ -2481,12 +2502,17 @@ static void qlcnic_tx_timeout(struct net_device *netdev)
 	if (test_bit(__QLCNIC_RESETTING, &adapter->state))
 		return;
 
-	dev_err(&netdev->dev, "transmit timeout, resetting.\n");
-
-	if (++adapter->tx_timeo_cnt >= QLCNIC_MAX_TX_TIMEOUTS)
-		adapter->need_fw_reset = 1;
-	else
+	if (++adapter->tx_timeo_cnt >= QLCNIC_MAX_TX_TIMEOUTS) {
+		netdev_info(netdev, "Tx timeout, reset the adapter.\n");
+		if (qlcnic_82xx_check(adapter))
+			adapter->need_fw_reset = 1;
+		else if (qlcnic_83xx_check(adapter))
+			qlcnic_83xx_idc_request_reset(adapter,
+						      QLCNIC_FORCE_FW_DUMP_KEY);
+	} else {
+		netdev_info(netdev, "Tx timeout, reset adapter context.\n");
 		adapter->ahw->reset_context = 1;
+	}
 }
 
 static struct net_device_stats *qlcnic_get_stats(struct net_device *netdev)
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
index 44d547d78b84..3869c3864deb 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
@@ -280,9 +280,9 @@ void qlcnic_sriov_cleanup(struct qlcnic_adapter *adapter)
 static int qlcnic_sriov_post_bc_msg(struct qlcnic_adapter *adapter, u32 *hdr,
 				    u32 *pay, u8 pci_func, u8 size)
 {
+	u32 rsp, mbx_val, fw_data, rsp_num, mbx_cmd, val, wait_time = 0;
 	struct qlcnic_hardware_context *ahw = adapter->ahw;
 	unsigned long flags;
-	u32 rsp, mbx_val, fw_data, rsp_num, mbx_cmd, val;
 	u16 opcode;
 	u8 mbx_err_code;
 	int i, j;
@@ -330,15 +330,13 @@ static int qlcnic_sriov_post_bc_msg(struct qlcnic_adapter *adapter, u32 *hdr,
 	 * assume something is wrong.
 	 */
 poll:
-	rsp = qlcnic_83xx_mbx_poll(adapter);
+	rsp = qlcnic_83xx_mbx_poll(adapter, &wait_time);
 	if (rsp != QLCNIC_RCODE_TIMEOUT) {
 		/* Get the FW response data */
 		fw_data = readl(QLCNIC_MBX_FW(ahw, 0));
 		if (fw_data &  QLCNIC_MBX_ASYNC_EVENT) {
 			__qlcnic_83xx_process_aen(adapter);
-			mbx_val = QLCRDX(ahw, QLCNIC_HOST_MBX_CTRL);
-			if (mbx_val)
-				goto poll;
+			goto poll;
 		}
 		mbx_err_code = QLCNIC_MBX_STATUS(fw_data);
 		rsp_num = QLCNIC_MBX_NUM_REGS(fw_data);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
index c81be2da119b..1a66ccded235 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
@@ -1133,9 +1133,6 @@ static int qlcnic_sriov_validate_linkevent(struct qlcnic_vf_info *vf,
 	if ((cmd->req.arg[1] >> 16) != vf->rx_ctx_id)
 		return -EINVAL;
 
-	if (!(cmd->req.arg[1] & BIT_8))
-		return -EINVAL;
-
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
index 87463bc701a6..50235d201592 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
@@ -1106,6 +1106,7 @@ static int ql_get_next_chunk(struct ql_adapter *qdev, struct rx_ring *rx_ring,
 		if (pci_dma_mapping_error(qdev->pdev, map)) {
 			__free_pages(rx_ring->pg_chunk.page,
 					qdev->lbq_buf_order);
+			rx_ring->pg_chunk.page = NULL;
 			netif_err(qdev, drv, qdev->ndev,
 				  "PCI mapping failed.\n");
 			return -ENOMEM;
@@ -2777,6 +2778,12 @@ static void ql_free_lbq_buffers(struct ql_adapter *qdev, struct rx_ring *rx_ring
 			curr_idx = 0;
 
 	}
+	if (rx_ring->pg_chunk.page) {
+		pci_unmap_page(qdev->pdev, rx_ring->pg_chunk.map,
+			ql_lbq_block_size(qdev), PCI_DMA_FROMDEVICE);
+		put_page(rx_ring->pg_chunk.page);
+		rx_ring->pg_chunk.page = NULL;
+	}
 }
 
 static void ql_free_sbq_buffers(struct ql_adapter *qdev, struct rx_ring *rx_ring)
diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig
index f695a50bac47..43c1f3223322 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Kconfig
+++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig
@@ -1,6 +1,6 @@
 config STMMAC_ETH
 	tristate "STMicroelectronics 10/100/1000 Ethernet driver"
-	depends on HAS_IOMEM
+	depends on HAS_IOMEM && HAS_DMA
 	select NET_CORE
 	select MII
 	select PHYLIB
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index d5a141c7c4e7..1c502bb0c916 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -229,7 +229,8 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb)
 	}
 
 	if (port->passthru)
-		vlan = list_first_entry(&port->vlans, struct macvlan_dev, list);
+		vlan = list_first_or_null_rcu(&port->vlans,
+					      struct macvlan_dev, list);
 	else
 		vlan = macvlan_hash_lookup(port, eth->h_dest);
 	if (vlan == NULL)
@@ -814,7 +815,7 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
 	if (err < 0)
 		goto upper_dev_unlink;
 
-	list_add_tail(&vlan->list, &port->vlans);
+	list_add_tail_rcu(&vlan->list, &port->vlans);
 	netif_stacked_transfer_operstate(lowerdev, dev);
 
 	return 0;
@@ -842,7 +843,7 @@ void macvlan_dellink(struct net_device *dev, struct list_head *head)
 {
 	struct macvlan_dev *vlan = netdev_priv(dev);
 
-	list_del(&vlan->list);
+	list_del_rcu(&vlan->list);
 	unregister_netdevice_queue(dev, head);
 	netdev_upper_dev_unlink(vlan->lowerdev, dev);
 }
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 3c23fdc27bf0..655bb25eed2b 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -28,7 +28,7 @@
 #include <linux/slab.h>
 #include <linux/cpu.h>
 
-static int napi_weight = 128;
+static int napi_weight = NAPI_POLL_WEIGHT;
 module_param(napi_weight, int, 0444);
 
 static bool csum = true, gso = true;
diff --git a/drivers/net/wireless/ath/ath5k/base.c b/drivers/net/wireless/ath/ath5k/base.c
index 9b20d9ee2719..7f702fe3ecc2 100644
--- a/drivers/net/wireless/ath/ath5k/base.c
+++ b/drivers/net/wireless/ath/ath5k/base.c
@@ -2369,6 +2369,9 @@ ath5k_tx_complete_poll_work(struct work_struct *work)
 	int i;
 	bool needreset = false;
 
+	if (!test_bit(ATH_STAT_STARTED, ah->status))
+		return;
+
 	mutex_lock(&ah->lock);
 
 	for (i = 0; i < ARRAY_SIZE(ah->txqs); i++) {
@@ -2676,6 +2679,7 @@ done:
 	mmiowb();
 	mutex_unlock(&ah->lock);
 
+	set_bit(ATH_STAT_STARTED, ah->status);
 	ieee80211_queue_delayed_work(ah->hw, &ah->tx_complete_work,
 			msecs_to_jiffies(ATH5K_TX_COMPLETE_POLL_INT));
 
@@ -2737,6 +2741,7 @@ void ath5k_stop(struct ieee80211_hw *hw)
 
 	ath5k_stop_tasklets(ah);
 
+	clear_bit(ATH_STAT_STARTED, ah->status);
 	cancel_delayed_work_sync(&ah->tx_complete_work);
 
 	if (!ath5k_modparam_no_hw_rfkill_switch)
diff --git a/drivers/net/wireless/ath/ath9k/Kconfig b/drivers/net/wireless/ath/ath9k/Kconfig
index 17507dc8a1e7..f3dc124c60c7 100644
--- a/drivers/net/wireless/ath/ath9k/Kconfig
+++ b/drivers/net/wireless/ath/ath9k/Kconfig
@@ -17,7 +17,7 @@ config ATH9K_BTCOEX_SUPPORT
 
 config ATH9K
 	tristate "Atheros 802.11n wireless cards support"
-	depends on MAC80211
+	depends on MAC80211 && HAS_DMA
 	select ATH9K_HW
 	select MAC80211_LEDS
 	select LEDS_CLASS
diff --git a/drivers/net/wireless/ath/ath9k/ar9565_1p0_initvals.h b/drivers/net/wireless/ath/ath9k/ar9565_1p0_initvals.h
index 0c2ac0c6dc89..e85a8b076c22 100644
--- a/drivers/net/wireless/ath/ath9k/ar9565_1p0_initvals.h
+++ b/drivers/net/wireless/ath/ath9k/ar9565_1p0_initvals.h
@@ -233,9 +233,9 @@ static const u32 ar9565_1p0_baseband_core[][2] = {
 	{0x00009d10, 0x01834061},
 	{0x00009d14, 0x00c00400},
 	{0x00009d18, 0x00000000},
-	{0x00009e08, 0x0078230c},
-	{0x00009e24, 0x990bb515},
-	{0x00009e28, 0x126f0000},
+	{0x00009e08, 0x0038230c},
+	{0x00009e24, 0x9907b515},
+	{0x00009e28, 0x126f0600},
 	{0x00009e30, 0x06336f77},
 	{0x00009e34, 0x6af6532f},
 	{0x00009e38, 0x0cc80c00},
@@ -337,7 +337,7 @@ static const u32 ar9565_1p0_baseband_core[][2] = {
 
 static const u32 ar9565_1p0_baseband_postamble[][5] = {
 	/* Addr      5G_HT20     5G_HT40     2G_HT40     2G_HT20   */
-	{0x00009810, 0xd00a8005, 0xd00a8005, 0xd00a8005, 0xd00a800d},
+	{0x00009810, 0xd00a8005, 0xd00a8005, 0xd00a8005, 0xd00a8009},
 	{0x00009820, 0x206a022e, 0x206a022e, 0x206a012e, 0x206a01ae},
 	{0x00009824, 0x5ac640d0, 0x5ac640d0, 0x5ac640d0, 0x63c640da},
 	{0x00009828, 0x06903081, 0x06903081, 0x06903881, 0x09143c81},
@@ -345,9 +345,9 @@ static const u32 ar9565_1p0_baseband_postamble[][5] = {
 	{0x00009830, 0x0000059c, 0x0000059c, 0x0000059c, 0x0000059c},
 	{0x00009c00, 0x000000c4, 0x000000c4, 0x000000c4, 0x000000c4},
 	{0x00009e00, 0x0372111a, 0x0372111a, 0x037216a0, 0x037216a0},
-	{0x00009e04, 0x00802020, 0x00802020, 0x00802020, 0x00802020},
-	{0x00009e0c, 0x6c4000e2, 0x6d4000e2, 0x6d4000e2, 0x6c4000d8},
-	{0x00009e10, 0x7ec88d2e, 0x7ec88d2e, 0x7ec84d2e, 0x7ec86d2e},
+	{0x00009e04, 0x00802020, 0x00802020, 0x00142020, 0x00142020},
+	{0x00009e0c, 0x6c4000e2, 0x6d4000e2, 0x6d4000e2, 0x6c4000e2},
+	{0x00009e10, 0x7ec88d2e, 0x7ec88d2e, 0x7ec84d2e, 0x7ec84d2e},
 	{0x00009e14, 0x37b95d5e, 0x37b9605e, 0x3379605e, 0x33795d5e},
 	{0x00009e18, 0x00000000, 0x00000000, 0x00000000, 0x00000000},
 	{0x00009e1c, 0x0001cf9c, 0x0001cf9c, 0x00021f9c, 0x00021f9c},
@@ -450,6 +450,8 @@ static const u32 ar9565_1p0_soc_postamble[][5] = {
 
 static const u32 ar9565_1p0_Common_rx_gain_table[][2] = {
 	/* Addr      allmodes  */
+	{0x00004050, 0x00300300},
+	{0x0000406c, 0x00100000},
 	{0x0000a000, 0x00010000},
 	{0x0000a004, 0x00030002},
 	{0x0000a008, 0x00050004},
@@ -498,27 +500,27 @@ static const u32 ar9565_1p0_Common_rx_gain_table[][2] = {
 	{0x0000a0b4, 0x00000000},
 	{0x0000a0b8, 0x00000000},
 	{0x0000a0bc, 0x00000000},
-	{0x0000a0c0, 0x001f0000},
-	{0x0000a0c4, 0x01000101},
-	{0x0000a0c8, 0x011e011f},
-	{0x0000a0cc, 0x011c011d},
-	{0x0000a0d0, 0x02030204},
-	{0x0000a0d4, 0x02010202},
-	{0x0000a0d8, 0x021f0200},
-	{0x0000a0dc, 0x0302021e},
-	{0x0000a0e0, 0x03000301},
-	{0x0000a0e4, 0x031e031f},
-	{0x0000a0e8, 0x0402031d},
-	{0x0000a0ec, 0x04000401},
-	{0x0000a0f0, 0x041e041f},
-	{0x0000a0f4, 0x0502041d},
-	{0x0000a0f8, 0x05000501},
-	{0x0000a0fc, 0x051e051f},
-	{0x0000a100, 0x06010602},
-	{0x0000a104, 0x061f0600},
-	{0x0000a108, 0x061d061e},
-	{0x0000a10c, 0x07020703},
-	{0x0000a110, 0x07000701},
+	{0x0000a0c0, 0x00bf00a0},
+	{0x0000a0c4, 0x11a011a1},
+	{0x0000a0c8, 0x11be11bf},
+	{0x0000a0cc, 0x11bc11bd},
+	{0x0000a0d0, 0x22632264},
+	{0x0000a0d4, 0x22612262},
+	{0x0000a0d8, 0x227f2260},
+	{0x0000a0dc, 0x4322227e},
+	{0x0000a0e0, 0x43204321},
+	{0x0000a0e4, 0x433e433f},
+	{0x0000a0e8, 0x4462433d},
+	{0x0000a0ec, 0x44604461},
+	{0x0000a0f0, 0x447e447f},
+	{0x0000a0f4, 0x5582447d},
+	{0x0000a0f8, 0x55805581},
+	{0x0000a0fc, 0x559e559f},
+	{0x0000a100, 0x66816682},
+	{0x0000a104, 0x669f6680},
+	{0x0000a108, 0x669d669e},
+	{0x0000a10c, 0x77627763},
+	{0x0000a110, 0x77607761},
 	{0x0000a114, 0x00000000},
 	{0x0000a118, 0x00000000},
 	{0x0000a11c, 0x00000000},
@@ -530,27 +532,27 @@ static const u32 ar9565_1p0_Common_rx_gain_table[][2] = {
 	{0x0000a134, 0x00000000},
 	{0x0000a138, 0x00000000},
 	{0x0000a13c, 0x00000000},
-	{0x0000a140, 0x001f0000},
-	{0x0000a144, 0x01000101},
-	{0x0000a148, 0x011e011f},
-	{0x0000a14c, 0x011c011d},
-	{0x0000a150, 0x02030204},
-	{0x0000a154, 0x02010202},
-	{0x0000a158, 0x021f0200},
-	{0x0000a15c, 0x0302021e},
-	{0x0000a160, 0x03000301},
-	{0x0000a164, 0x031e031f},
-	{0x0000a168, 0x0402031d},
-	{0x0000a16c, 0x04000401},
-	{0x0000a170, 0x041e041f},
-	{0x0000a174, 0x0502041d},
-	{0x0000a178, 0x05000501},
-	{0x0000a17c, 0x051e051f},
-	{0x0000a180, 0x06010602},
-	{0x0000a184, 0x061f0600},
-	{0x0000a188, 0x061d061e},
-	{0x0000a18c, 0x07020703},
-	{0x0000a190, 0x07000701},
+	{0x0000a140, 0x00bf00a0},
+	{0x0000a144, 0x11a011a1},
+	{0x0000a148, 0x11be11bf},
+	{0x0000a14c, 0x11bc11bd},
+	{0x0000a150, 0x22632264},
+	{0x0000a154, 0x22612262},
+	{0x0000a158, 0x227f2260},
+	{0x0000a15c, 0x4322227e},
+	{0x0000a160, 0x43204321},
+	{0x0000a164, 0x433e433f},
+	{0x0000a168, 0x4462433d},
+	{0x0000a16c, 0x44604461},
+	{0x0000a170, 0x447e447f},
+	{0x0000a174, 0x5582447d},
+	{0x0000a178, 0x55805581},
+	{0x0000a17c, 0x559e559f},
+	{0x0000a180, 0x66816682},
+	{0x0000a184, 0x669f6680},
+	{0x0000a188, 0x669d669e},
+	{0x0000a18c, 0x77e677e7},
+	{0x0000a190, 0x77e477e5},
 	{0x0000a194, 0x00000000},
 	{0x0000a198, 0x00000000},
 	{0x0000a19c, 0x00000000},
@@ -770,7 +772,7 @@ static const u32 ar9565_1p0_Modes_lowest_ob_db_tx_gain_table[][5] = {
 
 static const u32 ar9565_1p0_pciephy_clkreq_disable_L1[][2] = {
 	/* Addr      allmodes  */
-	{0x00018c00, 0x18213ede},
+	{0x00018c00, 0x18212ede},
 	{0x00018c04, 0x000801d8},
 	{0x00018c08, 0x0003780c},
 };
@@ -889,8 +891,8 @@ static const u32 ar9565_1p0_common_wo_xlna_rx_gain_table[][2] = {
 	{0x0000a180, 0x66816682},
 	{0x0000a184, 0x669f6680},
 	{0x0000a188, 0x669d669e},
-	{0x0000a18c, 0x77627763},
-	{0x0000a190, 0x77607761},
+	{0x0000a18c, 0x77e677e7},
+	{0x0000a190, 0x77e477e5},
 	{0x0000a194, 0x00000000},
 	{0x0000a198, 0x00000000},
 	{0x0000a19c, 0x00000000},
@@ -1114,7 +1116,7 @@ static const u32 ar9565_1p0_modes_high_ob_db_tx_gain_table[][5] = {
 	{0x0000a2e0, 0xffecec00, 0xffecec00, 0xfd339c84, 0xfd339c84},
 	{0x0000a2e4, 0xfc0f0000, 0xfc0f0000, 0xfec3e000, 0xfec3e000},
 	{0x0000a2e8, 0xfc100000, 0xfc100000, 0xfffc0000, 0xfffc0000},
-	{0x0000a410, 0x000050d9, 0x000050d9, 0x000050d9, 0x000050d9},
+	{0x0000a410, 0x000050d9, 0x000050d9, 0x000050df, 0x000050df},
 	{0x0000a500, 0x00002220, 0x00002220, 0x00000000, 0x00000000},
 	{0x0000a504, 0x06002223, 0x06002223, 0x04000002, 0x04000002},
 	{0x0000a508, 0x0b022220, 0x0b022220, 0x08000004, 0x08000004},
@@ -1140,13 +1142,13 @@ static const u32 ar9565_1p0_modes_high_ob_db_tx_gain_table[][5] = {
 	{0x0000a558, 0x69027f56, 0x69027f56, 0x53001ce5, 0x53001ce5},
 	{0x0000a55c, 0x6d029f56, 0x6d029f56, 0x57001ce9, 0x57001ce9},
 	{0x0000a560, 0x73049f56, 0x73049f56, 0x5b001ceb, 0x5b001ceb},
-	{0x0000a564, 0x7804ff56, 0x7804ff56, 0x5d001eec, 0x5d001eec},
-	{0x0000a568, 0x7804ff56, 0x7804ff56, 0x5d001eec, 0x5d001eec},
-	{0x0000a56c, 0x7804ff56, 0x7804ff56, 0x5d001eec, 0x5d001eec},
-	{0x0000a570, 0x7804ff56, 0x7804ff56, 0x5d001eec, 0x5d001eec},
-	{0x0000a574, 0x7804ff56, 0x7804ff56, 0x5d001eec, 0x5d001eec},
-	{0x0000a578, 0x7804ff56, 0x7804ff56, 0x5d001eec, 0x5d001eec},
-	{0x0000a57c, 0x7804ff56, 0x7804ff56, 0x5d001eec, 0x5d001eec},
+	{0x0000a564, 0x7804ff56, 0x7804ff56, 0x60001cf0, 0x60001cf0},
+	{0x0000a568, 0x7804ff56, 0x7804ff56, 0x61001cf1, 0x61001cf1},
+	{0x0000a56c, 0x7804ff56, 0x7804ff56, 0x62001cf2, 0x62001cf2},
+	{0x0000a570, 0x7804ff56, 0x7804ff56, 0x63001cf3, 0x63001cf3},
+	{0x0000a574, 0x7804ff56, 0x7804ff56, 0x64001cf4, 0x64001cf4},
+	{0x0000a578, 0x7804ff56, 0x7804ff56, 0x66001ff6, 0x66001ff6},
+	{0x0000a57c, 0x7804ff56, 0x7804ff56, 0x66001ff6, 0x66001ff6},
 	{0x0000a600, 0x00000000, 0x00000000, 0x00000000, 0x00000000},
 	{0x0000a604, 0x00000000, 0x00000000, 0x00000000, 0x00000000},
 	{0x0000a608, 0x00000000, 0x00000000, 0x00000000, 0x00000000},
@@ -1174,7 +1176,7 @@ static const u32 ar9565_1p0_modes_high_power_tx_gain_table[][5] = {
 	{0x0000a2e0, 0xffecec00, 0xffecec00, 0xfd339c84, 0xfd339c84},
 	{0x0000a2e4, 0xfc0f0000, 0xfc0f0000, 0xfec3e000, 0xfec3e000},
 	{0x0000a2e8, 0xfc100000, 0xfc100000, 0xfffc0000, 0xfffc0000},
-	{0x0000a410, 0x000050d9, 0x000050d9, 0x000050d9, 0x000050d9},
+	{0x0000a410, 0x000050d9, 0x000050d9, 0x000050df, 0x000050df},
 	{0x0000a500, 0x00002220, 0x00002220, 0x00000000, 0x00000000},
 	{0x0000a504, 0x06002223, 0x06002223, 0x04000002, 0x04000002},
 	{0x0000a508, 0x0a022220, 0x0a022220, 0x08000004, 0x08000004},
@@ -1200,13 +1202,13 @@ static const u32 ar9565_1p0_modes_high_power_tx_gain_table[][5] = {
 	{0x0000a558, 0x66027f56, 0x66027f56, 0x4c001ce5, 0x4c001ce5},
 	{0x0000a55c, 0x6a029f56, 0x6a029f56, 0x50001ce9, 0x50001ce9},
 	{0x0000a560, 0x70049f56, 0x70049f56, 0x54001ceb, 0x54001ceb},
-	{0x0000a564, 0x7504ff56, 0x7504ff56, 0x56001eec, 0x56001eec},
-	{0x0000a568, 0x7504ff56, 0x7504ff56, 0x56001eec, 0x56001eec},
-	{0x0000a56c, 0x7504ff56, 0x7504ff56, 0x56001eec, 0x56001eec},
-	{0x0000a570, 0x7504ff56, 0x7504ff56, 0x56001eec, 0x56001eec},
-	{0x0000a574, 0x7504ff56, 0x7504ff56, 0x56001eec, 0x56001eec},
-	{0x0000a578, 0x7504ff56, 0x7504ff56, 0x56001eec, 0x56001eec},
-	{0x0000a57c, 0x7504ff56, 0x7504ff56, 0x56001eec, 0x56001eec},
+	{0x0000a564, 0x7504ff56, 0x7504ff56, 0x59001cf0, 0x59001cf0},
+	{0x0000a568, 0x7504ff56, 0x7504ff56, 0x5a001cf1, 0x5a001cf1},
+	{0x0000a56c, 0x7504ff56, 0x7504ff56, 0x5b001cf2, 0x5b001cf2},
+	{0x0000a570, 0x7504ff56, 0x7504ff56, 0x5c001cf3, 0x5c001cf3},
+	{0x0000a574, 0x7504ff56, 0x7504ff56, 0x5d001cf4, 0x5d001cf4},
+	{0x0000a578, 0x7504ff56, 0x7504ff56, 0x5f001ff6, 0x5f001ff6},
+	{0x0000a57c, 0x7504ff56, 0x7504ff56, 0x5f001ff6, 0x5f001ff6},
 	{0x0000a600, 0x00000000, 0x00000000, 0x00000000, 0x00000000},
 	{0x0000a604, 0x00000000, 0x00000000, 0x00000000, 0x00000000},
 	{0x0000a608, 0x00000000, 0x00000000, 0x00000000, 0x00000000},
diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c
index 6963862a1872..a18414b5948b 100644
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -227,13 +227,13 @@ static bool ath_complete_reset(struct ath_softc *sc, bool start)
 		if (!test_bit(SC_OP_BEACONS, &sc->sc_flags))
 			goto work;
 
-		ath9k_set_beacon(sc);
-
 		if (ah->opmode == NL80211_IFTYPE_STATION &&
 		    test_bit(SC_OP_PRIM_STA_VIF, &sc->sc_flags)) {
 			spin_lock_irqsave(&sc->sc_pm_lock, flags);
 			sc->ps_flags |= PS_BEACON_SYNC | PS_WAIT_FOR_BEACON;
 			spin_unlock_irqrestore(&sc->sc_pm_lock, flags);
+		} else {
+			ath9k_set_beacon(sc);
 		}
 	work:
 		ath_restart_work(sc);
@@ -1332,6 +1332,7 @@ static int ath9k_sta_add(struct ieee80211_hw *hw,
 	struct ath_common *common = ath9k_hw_common(sc->sc_ah);
 	struct ath_node *an = (struct ath_node *) sta->drv_priv;
 	struct ieee80211_key_conf ps_key = { };
+	int key;
 
 	ath_node_attach(sc, sta, vif);
 
@@ -1339,7 +1340,9 @@ static int ath9k_sta_add(struct ieee80211_hw *hw,
 	    vif->type != NL80211_IFTYPE_AP_VLAN)
 		return 0;
 
-	an->ps_key = ath_key_config(common, vif, sta, &ps_key);
+	key = ath_key_config(common, vif, sta, &ps_key);
+	if (key > 0)
+		an->ps_key = key;
 
 	return 0;
 }
@@ -1356,6 +1359,7 @@ static void ath9k_del_ps_key(struct ath_softc *sc,
 	    return;
 
 	ath_key_delete(common, &ps_key);
+	an->ps_key = 0;
 }
 
 static int ath9k_sta_remove(struct ieee80211_hw *hw,
diff --git a/drivers/net/wireless/b43/dma.c b/drivers/net/wireless/b43/dma.c
index 523355b87659..f7c70b3a6ea9 100644
--- a/drivers/net/wireless/b43/dma.c
+++ b/drivers/net/wireless/b43/dma.c
@@ -1728,6 +1728,25 @@ drop_recycle_buffer:
 	sync_descbuffer_for_device(ring, dmaaddr, ring->rx_buffersize);
 }
 
+void b43_dma_handle_rx_overflow(struct b43_dmaring *ring)
+{
+	int current_slot, previous_slot;
+
+	B43_WARN_ON(ring->tx);
+
+	/* Device has filled all buffers, drop all packets and let TCP
+	 * decrease speed.
+	 * Decrement RX index by one will let the device to see all slots
+	 * as free again
+	 */
+	/*
+	*TODO: How to increase rx_drop in mac80211?
+	*/
+	current_slot = ring->ops->get_current_rxslot(ring);
+	previous_slot = prev_slot(ring, current_slot);
+	ring->ops->set_current_rxslot(ring, previous_slot);
+}
+
 void b43_dma_rx(struct b43_dmaring *ring)
 {
 	const struct b43_dma_ops *ops = ring->ops;
diff --git a/drivers/net/wireless/b43/dma.h b/drivers/net/wireless/b43/dma.h
index 9fdd1983079c..df8c8cdcbdb5 100644
--- a/drivers/net/wireless/b43/dma.h
+++ b/drivers/net/wireless/b43/dma.h
@@ -9,7 +9,7 @@
 /* DMA-Interrupt reasons. */
 #define B43_DMAIRQ_FATALMASK	((1 << 10) | (1 << 11) | (1 << 12) \
 					 | (1 << 14) | (1 << 15))
-#define B43_DMAIRQ_NONFATALMASK	(1 << 13)
+#define B43_DMAIRQ_RDESC_UFLOW		(1 << 13)
 #define B43_DMAIRQ_RX_DONE		(1 << 16)
 
 /*** 32-bit DMA Engine. ***/
@@ -295,6 +295,8 @@ int b43_dma_tx(struct b43_wldev *dev,
 void b43_dma_handle_txstatus(struct b43_wldev *dev,
 			     const struct b43_txstatus *status);
 
+void b43_dma_handle_rx_overflow(struct b43_dmaring *ring);
+
 void b43_dma_rx(struct b43_dmaring *ring);
 
 void b43_dma_direct_fifo_rx(struct b43_wldev *dev,
diff --git a/drivers/net/wireless/b43/main.c b/drivers/net/wireless/b43/main.c
index d377f77d30b5..6dd07e2ec595 100644
--- a/drivers/net/wireless/b43/main.c
+++ b/drivers/net/wireless/b43/main.c
@@ -1902,30 +1902,18 @@ static void b43_do_interrupt_thread(struct b43_wldev *dev)
 		}
 	}
 
-	if (unlikely(merged_dma_reason & (B43_DMAIRQ_FATALMASK |
-					  B43_DMAIRQ_NONFATALMASK))) {
-		if (merged_dma_reason & B43_DMAIRQ_FATALMASK) {
-			b43err(dev->wl, "Fatal DMA error: "
-			       "0x%08X, 0x%08X, 0x%08X, "
-			       "0x%08X, 0x%08X, 0x%08X\n",
-			       dma_reason[0], dma_reason[1],
-			       dma_reason[2], dma_reason[3],
-			       dma_reason[4], dma_reason[5]);
-			b43err(dev->wl, "This device does not support DMA "
+	if (unlikely(merged_dma_reason & (B43_DMAIRQ_FATALMASK))) {
+		b43err(dev->wl,
+			"Fatal DMA error: 0x%08X, 0x%08X, 0x%08X, 0x%08X, 0x%08X, 0x%08X\n",
+			dma_reason[0], dma_reason[1],
+			dma_reason[2], dma_reason[3],
+			dma_reason[4], dma_reason[5]);
+		b43err(dev->wl, "This device does not support DMA "
 			       "on your system. It will now be switched to PIO.\n");
-			/* Fall back to PIO transfers if we get fatal DMA errors! */
-			dev->use_pio = true;
-			b43_controller_restart(dev, "DMA error");
-			return;
-		}
-		if (merged_dma_reason & B43_DMAIRQ_NONFATALMASK) {
-			b43err(dev->wl, "DMA error: "
-			       "0x%08X, 0x%08X, 0x%08X, "
-			       "0x%08X, 0x%08X, 0x%08X\n",
-			       dma_reason[0], dma_reason[1],
-			       dma_reason[2], dma_reason[3],
-			       dma_reason[4], dma_reason[5]);
-		}
+		/* Fall back to PIO transfers if we get fatal DMA errors! */
+		dev->use_pio = true;
+		b43_controller_restart(dev, "DMA error");
+		return;
 	}
 
 	if (unlikely(reason & B43_IRQ_UCODE_DEBUG))
@@ -1944,6 +1932,11 @@ static void b43_do_interrupt_thread(struct b43_wldev *dev)
 		handle_irq_noise(dev);
 
 	/* Check the DMA reason registers for received data. */
+	if (dma_reason[0] & B43_DMAIRQ_RDESC_UFLOW) {
+		if (B43_DEBUG)
+			b43warn(dev->wl, "RX descriptor underrun\n");
+		b43_dma_handle_rx_overflow(dev->dma.rx_ring);
+	}
 	if (dma_reason[0] & B43_DMAIRQ_RX_DONE) {
 		if (b43_using_pio_transfers(dev))
 			b43_pio_rx(dev->pio.rx_queue);
@@ -2001,7 +1994,7 @@ static irqreturn_t b43_do_interrupt(struct b43_wldev *dev)
 		return IRQ_NONE;
 
 	dev->dma_reason[0] = b43_read32(dev, B43_MMIO_DMA0_REASON)
-	    & 0x0001DC00;
+	    & 0x0001FC00;
 	dev->dma_reason[1] = b43_read32(dev, B43_MMIO_DMA1_REASON)
 	    & 0x0000DC00;
 	dev->dma_reason[2] = b43_read32(dev, B43_MMIO_DMA2_REASON)
@@ -3130,7 +3123,7 @@ static int b43_chip_init(struct b43_wldev *dev)
 		b43_write32(dev, 0x018C, 0x02000000);
 	}
 	b43_write32(dev, B43_MMIO_GEN_IRQ_REASON, 0x00004000);
-	b43_write32(dev, B43_MMIO_DMA0_IRQ_MASK, 0x0001DC00);
+	b43_write32(dev, B43_MMIO_DMA0_IRQ_MASK, 0x0001FC00);
 	b43_write32(dev, B43_MMIO_DMA1_IRQ_MASK, 0x0000DC00);
 	b43_write32(dev, B43_MMIO_DMA2_IRQ_MASK, 0x0000DC00);
 	b43_write32(dev, B43_MMIO_DMA3_IRQ_MASK, 0x0001DC00);
diff --git a/drivers/net/wireless/iwlegacy/4965-mac.c b/drivers/net/wireless/iwlegacy/4965-mac.c
index b8f82e688c72..9a95045c97b6 100644
--- a/drivers/net/wireless/iwlegacy/4965-mac.c
+++ b/drivers/net/wireless/iwlegacy/4965-mac.c
@@ -5741,8 +5741,7 @@ il4965_mac_setup_register(struct il_priv *il, u32 max_probe_length)
 	hw->flags =
 	    IEEE80211_HW_SIGNAL_DBM | IEEE80211_HW_AMPDU_AGGREGATION |
 	    IEEE80211_HW_NEED_DTIM_BEFORE_ASSOC | IEEE80211_HW_SPECTRUM_MGMT |
-	    IEEE80211_HW_REPORTS_TX_ACK_STATUS | IEEE80211_HW_SUPPORTS_PS |
-	    IEEE80211_HW_SUPPORTS_DYNAMIC_PS;
+	    IEEE80211_HW_SUPPORTS_PS | IEEE80211_HW_SUPPORTS_DYNAMIC_PS;
 	if (il->cfg->sku & IL_SKU_N)
 		hw->flags |=
 		    IEEE80211_HW_SUPPORTS_DYNAMIC_SMPS |
diff --git a/drivers/net/wireless/mwifiex/cfg80211.c b/drivers/net/wireless/mwifiex/cfg80211.c
index d3c8ece980d8..e42b266a023a 100644
--- a/drivers/net/wireless/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/mwifiex/cfg80211.c
@@ -2234,9 +2234,6 @@ int mwifiex_del_virtual_intf(struct wiphy *wiphy, struct wireless_dev *wdev)
 	if (wdev->netdev->reg_state == NETREG_REGISTERED)
 		unregister_netdevice(wdev->netdev);
 
-	if (wdev->netdev->reg_state == NETREG_UNREGISTERED)
-		free_netdev(wdev->netdev);
-
 	/* Clear the priv in adapter */
 	priv->netdev = NULL;
 
diff --git a/drivers/net/wireless/mwifiex/cmdevt.c b/drivers/net/wireless/mwifiex/cmdevt.c
index 74db0d24a579..26755d9acb55 100644
--- a/drivers/net/wireless/mwifiex/cmdevt.c
+++ b/drivers/net/wireless/mwifiex/cmdevt.c
@@ -1191,6 +1191,7 @@ mwifiex_process_hs_config(struct mwifiex_adapter *adapter)
 	adapter->if_ops.wakeup(adapter);
 	adapter->hs_activated = false;
 	adapter->is_hs_configured = false;
+	adapter->is_suspended = false;
 	mwifiex_hs_activated_event(mwifiex_get_priv(adapter,
 						    MWIFIEX_BSS_ROLE_ANY),
 				   false);
diff --git a/drivers/net/wireless/mwifiex/main.c b/drivers/net/wireless/mwifiex/main.c
index 121443a0f2a1..2eb88ea9acf7 100644
--- a/drivers/net/wireless/mwifiex/main.c
+++ b/drivers/net/wireless/mwifiex/main.c
@@ -655,6 +655,7 @@ void mwifiex_init_priv_params(struct mwifiex_private *priv,
 						struct net_device *dev)
 {
 	dev->netdev_ops = &mwifiex_netdev_ops;
+	dev->destructor = free_netdev;
 	/* Initialize private structure */
 	priv->current_key_index = 0;
 	priv->media_connected = false;
diff --git a/drivers/net/wireless/mwifiex/sta_ioctl.c b/drivers/net/wireless/mwifiex/sta_ioctl.c
index 311d0b26b81c..1a8a19dbd635 100644
--- a/drivers/net/wireless/mwifiex/sta_ioctl.c
+++ b/drivers/net/wireless/mwifiex/sta_ioctl.c
@@ -96,7 +96,7 @@ int mwifiex_request_set_multicast_list(struct mwifiex_private *priv,
 	} else {
 		/* Multicast */
 		priv->curr_pkt_filter &= ~HostCmd_ACT_MAC_PROMISCUOUS_ENABLE;
-		if (mcast_list->mode == MWIFIEX_MULTICAST_MODE) {
+		if (mcast_list->mode == MWIFIEX_ALL_MULTI_MODE) {
 			dev_dbg(priv->adapter->dev,
 				"info: Enabling All Multicast!\n");
 			priv->curr_pkt_filter |=
@@ -108,20 +108,11 @@ int mwifiex_request_set_multicast_list(struct mwifiex_private *priv,
 				dev_dbg(priv->adapter->dev,
 					"info: Set multicast list=%d\n",
 				       mcast_list->num_multicast_addr);
-				/* Set multicast addresses to firmware */
-				if (old_pkt_filter == priv->curr_pkt_filter) {
-					/* Send request to firmware */
-					ret = mwifiex_send_cmd_async(priv,
-						HostCmd_CMD_MAC_MULTICAST_ADR,
-						HostCmd_ACT_GEN_SET, 0,
-						mcast_list);
-				} else {
-					/* Send request to firmware */
-					ret = mwifiex_send_cmd_async(priv,
-						HostCmd_CMD_MAC_MULTICAST_ADR,
-						HostCmd_ACT_GEN_SET, 0,
-						mcast_list);
-				}
+				/* Send multicast addresses to firmware */
+				ret = mwifiex_send_cmd_async(priv,
+					HostCmd_CMD_MAC_MULTICAST_ADR,
+					HostCmd_ACT_GEN_SET, 0,
+					mcast_list);
 			}
 		}
 	}
diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index 0c81915b1997..b9838130a7b0 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -20,7 +20,6 @@ if RTC_CLASS
 config RTC_HCTOSYS
 	bool "Set system time from RTC on startup and resume"
 	default y
-	depends on !ALWAYS_USE_PERSISTENT_CLOCK
 	help
 	  If you say yes here, the system time (wall clock) will be set using
 	  the value read from a specified RTC device. This is useful to avoid
@@ -29,7 +28,6 @@ config RTC_HCTOSYS
 config RTC_SYSTOHC
 	bool "Set the RTC time based on NTP synchronization"
 	default y
-	depends on !ALWAYS_USE_PERSISTENT_CLOCK
 	help
 	  If you say yes here, the system time (wall clock) will be stored
 	  in the RTC specified by RTC_HCTOSYS_DEVICE approximately every 11
diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c
index 787bd2c22bca..380387a47b1d 100644
--- a/drivers/spi/spi-atmel.c
+++ b/drivers/spi/spi-atmel.c
@@ -526,13 +526,17 @@ static void atmel_spi_next_xfer_pio(struct spi_master *master,
 	}
 
 	if (xfer->tx_buf)
-		spi_writel(as, TDR, *(u8 *)(xfer->tx_buf));
+		if (xfer->bits_per_word > 8)
+			spi_writel(as, TDR, *(u16 *)(xfer->tx_buf));
+		else
+			spi_writel(as, TDR, *(u8 *)(xfer->tx_buf));
 	else
 		spi_writel(as, TDR, 0);
 
 	dev_dbg(master->dev.parent,
-		"  start pio xfer %p: len %u tx %p rx %p\n",
-		xfer, xfer->len, xfer->tx_buf, xfer->rx_buf);
+		"  start pio xfer %p: len %u tx %p rx %p bitpw %d\n",
+		xfer, xfer->len, xfer->tx_buf, xfer->rx_buf,
+		xfer->bits_per_word);
 
 	/* Enable relevant interrupts */
 	spi_writel(as, IER, SPI_BIT(RDRF) | SPI_BIT(OVRES));
@@ -950,21 +954,39 @@ atmel_spi_pump_pio_data(struct atmel_spi *as, struct spi_transfer *xfer)
 {
 	u8		*txp;
 	u8		*rxp;
+	u16		*txp16;
+	u16		*rxp16;
 	unsigned long	xfer_pos = xfer->len - as->current_remaining_bytes;
 
 	if (xfer->rx_buf) {
-		rxp = ((u8 *)xfer->rx_buf) + xfer_pos;
-		*rxp = spi_readl(as, RDR);
+		if (xfer->bits_per_word > 8) {
+			rxp16 = (u16 *)(((u8 *)xfer->rx_buf) + xfer_pos);
+			*rxp16 = spi_readl(as, RDR);
+		} else {
+			rxp = ((u8 *)xfer->rx_buf) + xfer_pos;
+			*rxp = spi_readl(as, RDR);
+		}
 	} else {
 		spi_readl(as, RDR);
 	}
-
-	as->current_remaining_bytes--;
+	if (xfer->bits_per_word > 8) {
+		as->current_remaining_bytes -= 2;
+		if (as->current_remaining_bytes < 0)
+			as->current_remaining_bytes = 0;
+	} else {
+		as->current_remaining_bytes--;
+	}
 
 	if (as->current_remaining_bytes) {
 		if (xfer->tx_buf) {
-			txp = ((u8 *)xfer->tx_buf) + xfer_pos + 1;
-			spi_writel(as, TDR, *txp);
+			if (xfer->bits_per_word > 8) {
+				txp16 = (u16 *)(((u8 *)xfer->tx_buf)
+							+ xfer_pos + 2);
+				spi_writel(as, TDR, *txp16);
+			} else {
+				txp = ((u8 *)xfer->tx_buf) + xfer_pos + 1;
+				spi_writel(as, TDR, *txp);
+			}
 		} else {
 			spi_writel(as, TDR, 0);
 		}
@@ -1378,9 +1400,16 @@ static int atmel_spi_transfer(struct spi_device *spi, struct spi_message *msg)
 			}
 		}
 
+		if (xfer->bits_per_word > 8) {
+			if (xfer->len % 2) {
+				dev_dbg(&spi->dev, "buffer len should be 16 bits aligned\n");
+				return -EINVAL;
+			}
+		}
+
 		/* FIXME implement these protocol options!! */
-		if (xfer->speed_hz) {
-			dev_dbg(&spi->dev, "no protocol options yet\n");
+		if (xfer->speed_hz < spi->max_speed_hz) {
+			dev_dbg(&spi->dev, "can't change speed in transfer\n");
 			return -ENOPROTOOPT;
 		}
 
diff --git a/drivers/spi/spi-davinci.c b/drivers/spi/spi-davinci.c
index 2e8f24a1fb95..50b13c9b1ab6 100644
--- a/drivers/spi/spi-davinci.c
+++ b/drivers/spi/spi-davinci.c
@@ -784,7 +784,7 @@ static const struct of_device_id davinci_spi_of_match[] = {
 	},
 	{ },
 };
-MODULE_DEVICE_TABLE(of, davini_spi_of_match);
+MODULE_DEVICE_TABLE(of, davinci_spi_of_match);
 
 /**
  * spi_davinci_get_pdata - Get platform data from DTS binding
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 163fd802b7ac..32b7bb111eb6 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -334,7 +334,7 @@ struct spi_device *spi_alloc_device(struct spi_master *master)
 	spi->dev.parent = &master->dev;
 	spi->dev.bus = &spi_bus_type;
 	spi->dev.release = spidev_release;
-	spi->cs_gpio = -EINVAL;
+	spi->cs_gpio = -ENOENT;
 	device_initialize(&spi->dev);
 	return spi;
 }
@@ -1067,8 +1067,11 @@ static int of_spi_register_master(struct spi_master *master)
 	nb = of_gpio_named_count(np, "cs-gpios");
 	master->num_chipselect = max(nb, (int)master->num_chipselect);
 
-	if (nb < 1)
+	/* Return error only for an incorrectly formed cs-gpios property */
+	if (nb == 0 || nb == -ENOENT)
 		return 0;
+	else if (nb < 0)
+		return nb;
 
 	cs = devm_kzalloc(&master->dev,
 			  sizeof(int) * master->num_chipselect,
@@ -1079,7 +1082,7 @@ static int of_spi_register_master(struct spi_master *master)
 		return -ENOMEM;
 
 	for (i = 0; i < master->num_chipselect; i++)
-		cs[i] = -EINVAL;
+		cs[i] = -ENOENT;
 
 	for (i = 0; i < nb; i++)
 		cs[i] = of_get_named_gpio(np, "cs-gpios", i);
diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c
index bff0775e258c..5174ebac288d 100644
--- a/drivers/vhost/vringh.c
+++ b/drivers/vhost/vringh.c
@@ -3,6 +3,7 @@
  *
  * Since these may be in userspace, we use (inline) accessors.
  */
+#include <linux/module.h>
 #include <linux/vringh.h>
 #include <linux/virtio_ring.h>
 #include <linux/kernel.h>
@@ -1005,3 +1006,5 @@ int vringh_need_notify_kern(struct vringh *vrh)
 	return __vringh_need_notify(vrh, getu16_kern);
 }
 EXPORT_SYMBOL(vringh_need_notify_kern);
+
+MODULE_LICENSE("GPL");
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 0aabb344b02e..5aae3d12d400 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -209,7 +209,6 @@ typedef struct ext4_io_end {
 	ssize_t			size;		/* size of the extent */
 	struct kiocb		*iocb;		/* iocb struct for AIO */
 	int			result;		/* error value for AIO */
-	atomic_t		count;		/* reference counter */
 } ext4_io_end_t;
 
 struct ext4_io_submit {
@@ -2651,14 +2650,11 @@ extern int ext4_move_extents(struct file *o_filp, struct file *d_filp,
 
 /* page-io.c */
 extern int __init ext4_init_pageio(void);
+extern void ext4_add_complete_io(ext4_io_end_t *io_end);
 extern void ext4_exit_pageio(void);
 extern void ext4_ioend_shutdown(struct inode *);
+extern void ext4_free_io_end(ext4_io_end_t *io);
 extern ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags);
-extern ext4_io_end_t *ext4_get_io_end(ext4_io_end_t *io_end);
-extern int ext4_put_io_end(ext4_io_end_t *io_end);
-extern void ext4_put_io_end_defer(ext4_io_end_t *io_end);
-extern void ext4_io_submit_init(struct ext4_io_submit *io,
-				struct writeback_control *wbc);
 extern void ext4_end_io_work(struct work_struct *work);
 extern void ext4_io_submit(struct ext4_io_submit *io);
 extern int ext4_bio_write_page(struct ext4_io_submit *io,
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 107936db244e..bc0f1910b9cf 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -3642,7 +3642,7 @@ int ext4_find_delalloc_range(struct inode *inode,
 {
 	struct extent_status es;
 
-	ext4_es_find_delayed_extent(inode, lblk_start, &es);
+	ext4_es_find_delayed_extent_range(inode, lblk_start, lblk_end, &es);
 	if (es.es_len == 0)
 		return 0; /* there is no delay extent in this tree */
 	else if (es.es_lblk <= lblk_start &&
@@ -4608,9 +4608,10 @@ static int ext4_find_delayed_extent(struct inode *inode,
 	struct extent_status es;
 	ext4_lblk_t block, next_del;
 
-	ext4_es_find_delayed_extent(inode, newes->es_lblk, &es);
-
 	if (newes->es_pblk == 0) {
+		ext4_es_find_delayed_extent_range(inode, newes->es_lblk,
+				newes->es_lblk + newes->es_len - 1, &es);
+
 		/*
 		 * No extent in extent-tree contains block @newes->es_pblk,
 		 * then the block may stay in 1)a hole or 2)delayed-extent.
@@ -4630,7 +4631,7 @@ static int ext4_find_delayed_extent(struct inode *inode,
 	}
 
 	block = newes->es_lblk + newes->es_len;
-	ext4_es_find_delayed_extent(inode, block, &es);
+	ext4_es_find_delayed_extent_range(inode, block, EXT_MAX_BLOCKS, &es);
 	if (es.es_len == 0)
 		next_del = EXT_MAX_BLOCKS;
 	else
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index fe3337a85ede..e6941e622d31 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -232,14 +232,16 @@ static struct extent_status *__es_tree_search(struct rb_root *root,
 }
 
 /*
- * ext4_es_find_delayed_extent: find the 1st delayed extent covering @es->lblk
- * if it exists, otherwise, the next extent after @es->lblk.
+ * ext4_es_find_delayed_extent_range: find the 1st delayed extent covering
+ * @es->lblk if it exists, otherwise, the next extent after @es->lblk.
  *
  * @inode: the inode which owns delayed extents
  * @lblk: the offset where we start to search
+ * @end: the offset where we stop to search
  * @es: delayed extent that we found
  */
-void ext4_es_find_delayed_extent(struct inode *inode, ext4_lblk_t lblk,
+void ext4_es_find_delayed_extent_range(struct inode *inode,
+				 ext4_lblk_t lblk, ext4_lblk_t end,
 				 struct extent_status *es)
 {
 	struct ext4_es_tree *tree = NULL;
@@ -247,7 +249,8 @@ void ext4_es_find_delayed_extent(struct inode *inode, ext4_lblk_t lblk,
 	struct rb_node *node;
 
 	BUG_ON(es == NULL);
-	trace_ext4_es_find_delayed_extent_enter(inode, lblk);
+	BUG_ON(end < lblk);
+	trace_ext4_es_find_delayed_extent_range_enter(inode, lblk);
 
 	read_lock(&EXT4_I(inode)->i_es_lock);
 	tree = &EXT4_I(inode)->i_es_tree;
@@ -270,6 +273,10 @@ out:
 	if (es1 && !ext4_es_is_delayed(es1)) {
 		while ((node = rb_next(&es1->rb_node)) != NULL) {
 			es1 = rb_entry(node, struct extent_status, rb_node);
+			if (es1->es_lblk > end) {
+				es1 = NULL;
+				break;
+			}
 			if (ext4_es_is_delayed(es1))
 				break;
 		}
@@ -285,7 +292,7 @@ out:
 	read_unlock(&EXT4_I(inode)->i_es_lock);
 
 	ext4_es_lru_add(inode);
-	trace_ext4_es_find_delayed_extent_exit(inode, es);
+	trace_ext4_es_find_delayed_extent_range_exit(inode, es);
 }
 
 static struct extent_status *
diff --git a/fs/ext4/extents_status.h b/fs/ext4/extents_status.h
index d8e2d4dc311e..f740eb03b707 100644
--- a/fs/ext4/extents_status.h
+++ b/fs/ext4/extents_status.h
@@ -62,7 +62,8 @@ extern int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
 				 unsigned long long status);
 extern int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
 				 ext4_lblk_t len);
-extern void ext4_es_find_delayed_extent(struct inode *inode, ext4_lblk_t lblk,
+extern void ext4_es_find_delayed_extent_range(struct inode *inode,
+					ext4_lblk_t lblk, ext4_lblk_t end,
 					struct extent_status *es);
 extern int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk,
 				 struct extent_status *es);
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 4959e29573b6..b1b4d51b5d86 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -465,7 +465,7 @@ static loff_t ext4_seek_data(struct file *file, loff_t offset, loff_t maxsize)
 		 * If there is a delay extent at this offset,
 		 * it will be as a data.
 		 */
-		ext4_es_find_delayed_extent(inode, last, &es);
+		ext4_es_find_delayed_extent_range(inode, last, last, &es);
 		if (es.es_len != 0 && in_range(last, es.es_lblk, es.es_len)) {
 			if (last != start)
 				dataoff = last << blkbits;
@@ -548,7 +548,7 @@ static loff_t ext4_seek_hole(struct file *file, loff_t offset, loff_t maxsize)
 		 * If there is a delay extent at this offset,
 		 * we will skip this extent.
 		 */
-		ext4_es_find_delayed_extent(inode, last, &es);
+		ext4_es_find_delayed_extent_range(inode, last, last, &es);
 		if (es.es_len != 0 && in_range(last, es.es_lblk, es.es_len)) {
 			last = es.es_lblk + es.es_len;
 			holeoff = last << blkbits;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 0723774bdfb5..d6382b89ecbd 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1488,10 +1488,7 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd,
 	struct ext4_io_submit io_submit;
 
 	BUG_ON(mpd->next_page <= mpd->first_page);
-	ext4_io_submit_init(&io_submit, mpd->wbc);
-	io_submit.io_end = ext4_init_io_end(inode, GFP_NOFS);
-	if (!io_submit.io_end)
-		return -ENOMEM;
+	memset(&io_submit, 0, sizeof(io_submit));
 	/*
 	 * We need to start from the first_page to the next_page - 1
 	 * to make sure we also write the mapped dirty buffer_heads.
@@ -1579,8 +1576,6 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd,
 		pagevec_release(&pvec);
 	}
 	ext4_io_submit(&io_submit);
-	/* Drop io_end reference we got from init */
-	ext4_put_io_end_defer(io_submit.io_end);
 	return ret;
 }
 
@@ -2239,16 +2234,9 @@ static int ext4_writepage(struct page *page,
 		 */
 		return __ext4_journalled_writepage(page, len);
 
-	ext4_io_submit_init(&io_submit, wbc);
-	io_submit.io_end = ext4_init_io_end(inode, GFP_NOFS);
-	if (!io_submit.io_end) {
-		redirty_page_for_writepage(wbc, page);
-		return -ENOMEM;
-	}
+	memset(&io_submit, 0, sizeof(io_submit));
 	ret = ext4_bio_write_page(&io_submit, page, len, wbc);
 	ext4_io_submit(&io_submit);
-	/* Drop io_end reference we got from init */
-	ext4_put_io_end_defer(io_submit.io_end);
 	return ret;
 }
 
@@ -3079,13 +3067,9 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
 	struct inode *inode = file_inode(iocb->ki_filp);
         ext4_io_end_t *io_end = iocb->private;
 
-	/* if not async direct IO just return */
-	if (!io_end) {
-		inode_dio_done(inode);
-		if (is_async)
-			aio_complete(iocb, ret, 0);
-		return;
-	}
+	/* if not async direct IO or dio with 0 bytes write, just return */
+	if (!io_end || !size)
+		goto out;
 
 	ext_debug("ext4_end_io_dio(): io_end 0x%p "
 		  "for inode %lu, iocb 0x%p, offset %llu, size %zd\n",
@@ -3093,13 +3077,25 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
 		  size);
 
 	iocb->private = NULL;
+
+	/* if not aio dio with unwritten extents, just free io and return */
+	if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
+		ext4_free_io_end(io_end);
+out:
+		inode_dio_done(inode);
+		if (is_async)
+			aio_complete(iocb, ret, 0);
+		return;
+	}
+
 	io_end->offset = offset;
 	io_end->size = size;
 	if (is_async) {
 		io_end->iocb = iocb;
 		io_end->result = ret;
 	}
-	ext4_put_io_end_defer(io_end);
+
+	ext4_add_complete_io(io_end);
 }
 
 /*
@@ -3133,7 +3129,6 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 	get_block_t *get_block_func = NULL;
 	int dio_flags = 0;
 	loff_t final_size = offset + count;
-	ext4_io_end_t *io_end = NULL;
 
 	/* Use the old path for reads and writes beyond i_size. */
 	if (rw != WRITE || final_size > inode->i_size)
@@ -3172,16 +3167,13 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 	iocb->private = NULL;
 	ext4_inode_aio_set(inode, NULL);
 	if (!is_sync_kiocb(iocb)) {
-		io_end = ext4_init_io_end(inode, GFP_NOFS);
+		ext4_io_end_t *io_end = ext4_init_io_end(inode, GFP_NOFS);
 		if (!io_end) {
 			ret = -ENOMEM;
 			goto retake_lock;
 		}
 		io_end->flag |= EXT4_IO_END_DIRECT;
-		/*
-		 * Grab reference for DIO. Will be dropped in ext4_end_io_dio()
-		 */
-		iocb->private = ext4_get_io_end(io_end);
+		iocb->private = io_end;
 		/*
 		 * we save the io structure for current async direct
 		 * IO, so that later ext4_map_blocks() could flag the
@@ -3205,27 +3197,26 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 				   NULL,
 				   dio_flags);
 
+	if (iocb->private)
+		ext4_inode_aio_set(inode, NULL);
 	/*
-	 * Put our reference to io_end. This can free the io_end structure e.g.
-	 * in sync IO case or in case of error. It can even perform extent
-	 * conversion if all bios we submitted finished before we got here.
-	 * Note that in that case iocb->private can be already set to NULL
-	 * here.
+	 * The io_end structure takes a reference to the inode, that
+	 * structure needs to be destroyed and the reference to the
+	 * inode need to be dropped, when IO is complete, even with 0
+	 * byte write, or failed.
+	 *
+	 * In the successful AIO DIO case, the io_end structure will
+	 * be destroyed and the reference to the inode will be dropped
+	 * after the end_io call back function is called.
+	 *
+	 * In the case there is 0 byte write, or error case, since VFS
+	 * direct IO won't invoke the end_io call back function, we
+	 * need to free the end_io structure here.
 	 */
-	if (io_end) {
-		ext4_inode_aio_set(inode, NULL);
-		ext4_put_io_end(io_end);
-		/*
-		 * In case of error or no write ext4_end_io_dio() was not
-		 * called so we have to put iocb's reference.
-		 */
-		if (ret <= 0 && ret != -EIOCBQUEUED) {
-			WARN_ON(iocb->private != io_end);
-			ext4_put_io_end(io_end);
-			iocb->private = NULL;
-		}
-	}
-	if (ret > 0 && !overwrite && ext4_test_inode_state(inode,
+	if (ret != -EIOCBQUEUED && ret <= 0 && iocb->private) {
+		ext4_free_io_end(iocb->private);
+		iocb->private = NULL;
+	} else if (ret > 0 && !overwrite && ext4_test_inode_state(inode,
 						EXT4_STATE_DIO_UNWRITTEN)) {
 		int err;
 		/*
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index b1ed9e07434b..def84082a9a9 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2105,7 +2105,11 @@ repeat:
 		group = ac->ac_g_ex.fe_group;
 
 		for (i = 0; i < ngroups; group++, i++) {
-			if (group == ngroups)
+			/*
+			 * Artificially restricted ngroups for non-extent
+			 * files makes group > ngroups possible on first loop.
+			 */
+			if (group >= ngroups)
 				group = 0;
 
 			/* This now checks without needing the buddy page */
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 19599bded62a..4acf1f78881b 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -62,28 +62,15 @@ void ext4_ioend_shutdown(struct inode *inode)
 		cancel_work_sync(&EXT4_I(inode)->i_unwritten_work);
 }
 
-static void ext4_release_io_end(ext4_io_end_t *io_end)
+void ext4_free_io_end(ext4_io_end_t *io)
 {
-	BUG_ON(!list_empty(&io_end->list));
-	BUG_ON(io_end->flag & EXT4_IO_END_UNWRITTEN);
-
-	if (atomic_dec_and_test(&EXT4_I(io_end->inode)->i_ioend_count))
-		wake_up_all(ext4_ioend_wq(io_end->inode));
-	if (io_end->flag & EXT4_IO_END_DIRECT)
-		inode_dio_done(io_end->inode);
-	if (io_end->iocb)
-		aio_complete(io_end->iocb, io_end->result, 0);
-	kmem_cache_free(io_end_cachep, io_end);
-}
-
-static void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end)
-{
-	struct inode *inode = io_end->inode;
+	BUG_ON(!io);
+	BUG_ON(!list_empty(&io->list));
+	BUG_ON(io->flag & EXT4_IO_END_UNWRITTEN);
 
-	io_end->flag &= ~EXT4_IO_END_UNWRITTEN;
-	/* Wake up anyone waiting on unwritten extent conversion */
-	if (atomic_dec_and_test(&EXT4_I(inode)->i_unwritten))
-		wake_up_all(ext4_ioend_wq(inode));
+	if (atomic_dec_and_test(&EXT4_I(io->inode)->i_ioend_count))
+		wake_up_all(ext4_ioend_wq(io->inode));
+	kmem_cache_free(io_end_cachep, io);
 }
 
 /* check a range of space and convert unwritten extents to written. */
@@ -106,8 +93,13 @@ static int ext4_end_io(ext4_io_end_t *io)
 			 "(inode %lu, offset %llu, size %zd, error %d)",
 			 inode->i_ino, offset, size, ret);
 	}
-	ext4_clear_io_unwritten_flag(io);
-	ext4_release_io_end(io);
+	/* Wake up anyone waiting on unwritten extent conversion */
+	if (atomic_dec_and_test(&EXT4_I(inode)->i_unwritten))
+		wake_up_all(ext4_ioend_wq(inode));
+	if (io->flag & EXT4_IO_END_DIRECT)
+		inode_dio_done(inode);
+	if (io->iocb)
+		aio_complete(io->iocb, io->result, 0);
 	return ret;
 }
 
@@ -138,7 +130,7 @@ static void dump_completed_IO(struct inode *inode)
 }
 
 /* Add the io_end to per-inode completed end_io list. */
-static void ext4_add_complete_io(ext4_io_end_t *io_end)
+void ext4_add_complete_io(ext4_io_end_t *io_end)
 {
 	struct ext4_inode_info *ei = EXT4_I(io_end->inode);
 	struct workqueue_struct *wq;
@@ -175,6 +167,8 @@ static int ext4_do_flush_completed_IO(struct inode *inode)
 		err = ext4_end_io(io);
 		if (unlikely(!ret && err))
 			ret = err;
+		io->flag &= ~EXT4_IO_END_UNWRITTEN;
+		ext4_free_io_end(io);
 	}
 	return ret;
 }
@@ -206,43 +200,10 @@ ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags)
 		atomic_inc(&EXT4_I(inode)->i_ioend_count);
 		io->inode = inode;
 		INIT_LIST_HEAD(&io->list);
-		atomic_set(&io->count, 1);
 	}
 	return io;
 }
 
-void ext4_put_io_end_defer(ext4_io_end_t *io_end)
-{
-	if (atomic_dec_and_test(&io_end->count)) {
-		if (!(io_end->flag & EXT4_IO_END_UNWRITTEN) || !io_end->size) {
-			ext4_release_io_end(io_end);
-			return;
-		}
-		ext4_add_complete_io(io_end);
-	}
-}
-
-int ext4_put_io_end(ext4_io_end_t *io_end)
-{
-	int err = 0;
-
-	if (atomic_dec_and_test(&io_end->count)) {
-		if (io_end->flag & EXT4_IO_END_UNWRITTEN) {
-			err = ext4_convert_unwritten_extents(io_end->inode,
-						io_end->offset, io_end->size);
-			ext4_clear_io_unwritten_flag(io_end);
-		}
-		ext4_release_io_end(io_end);
-	}
-	return err;
-}
-
-ext4_io_end_t *ext4_get_io_end(ext4_io_end_t *io_end)
-{
-	atomic_inc(&io_end->count);
-	return io_end;
-}
-
 /*
  * Print an buffer I/O error compatible with the fs/buffer.c.  This
  * provides compatibility with dmesg scrapers that look for a specific
@@ -325,7 +286,12 @@ static void ext4_end_bio(struct bio *bio, int error)
 			     bi_sector >> (inode->i_blkbits - 9));
 	}
 
-	ext4_put_io_end_defer(io_end);
+	if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
+		ext4_free_io_end(io_end);
+		return;
+	}
+
+	ext4_add_complete_io(io_end);
 }
 
 void ext4_io_submit(struct ext4_io_submit *io)
@@ -339,37 +305,40 @@ void ext4_io_submit(struct ext4_io_submit *io)
 		bio_put(io->io_bio);
 	}
 	io->io_bio = NULL;
-}
-
-void ext4_io_submit_init(struct ext4_io_submit *io,
-			 struct writeback_control *wbc)
-{
-	io->io_op = (wbc->sync_mode == WB_SYNC_ALL ?  WRITE_SYNC : WRITE);
-	io->io_bio = NULL;
+	io->io_op = 0;
 	io->io_end = NULL;
 }
 
-static int io_submit_init_bio(struct ext4_io_submit *io,
-			      struct buffer_head *bh)
+static int io_submit_init(struct ext4_io_submit *io,
+			  struct inode *inode,
+			  struct writeback_control *wbc,
+			  struct buffer_head *bh)
 {
+	ext4_io_end_t *io_end;
+	struct page *page = bh->b_page;
 	int nvecs = bio_get_nr_vecs(bh->b_bdev);
 	struct bio *bio;
 
+	io_end = ext4_init_io_end(inode, GFP_NOFS);
+	if (!io_end)
+		return -ENOMEM;
 	bio = bio_alloc(GFP_NOIO, min(nvecs, BIO_MAX_PAGES));
 	bio->bi_sector = bh->b_blocknr * (bh->b_size >> 9);
 	bio->bi_bdev = bh->b_bdev;
+	bio->bi_private = io->io_end = io_end;
 	bio->bi_end_io = ext4_end_bio;
-	bio->bi_private = ext4_get_io_end(io->io_end);
-	if (!io->io_end->size)
-		io->io_end->offset = (bh->b_page->index << PAGE_CACHE_SHIFT)
-				     + bh_offset(bh);
+
+	io_end->offset = (page->index << PAGE_CACHE_SHIFT) + bh_offset(bh);
+
 	io->io_bio = bio;
+	io->io_op = (wbc->sync_mode == WB_SYNC_ALL ?  WRITE_SYNC : WRITE);
 	io->io_next_block = bh->b_blocknr;
 	return 0;
 }
 
 static int io_submit_add_bh(struct ext4_io_submit *io,
 			    struct inode *inode,
+			    struct writeback_control *wbc,
 			    struct buffer_head *bh)
 {
 	ext4_io_end_t *io_end;
@@ -380,18 +349,18 @@ submit_and_retry:
 		ext4_io_submit(io);
 	}
 	if (io->io_bio == NULL) {
-		ret = io_submit_init_bio(io, bh);
+		ret = io_submit_init(io, inode, wbc, bh);
 		if (ret)
 			return ret;
 	}
-	ret = bio_add_page(io->io_bio, bh->b_page, bh->b_size, bh_offset(bh));
-	if (ret != bh->b_size)
-		goto submit_and_retry;
 	io_end = io->io_end;
 	if (test_clear_buffer_uninit(bh))
 		ext4_set_io_unwritten_flag(inode, io_end);
-	io_end->size += bh->b_size;
+	io->io_end->size += bh->b_size;
 	io->io_next_block++;
+	ret = bio_add_page(io->io_bio, bh->b_page, bh->b_size, bh_offset(bh));
+	if (ret != bh->b_size)
+		goto submit_and_retry;
 	return 0;
 }
 
@@ -463,7 +432,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 	do {
 		if (!buffer_async_write(bh))
 			continue;
-		ret = io_submit_add_bh(io, inode, bh);
+		ret = io_submit_add_bh(io, inode, wbc, bh);
 		if (ret) {
 			/*
 			 * We only get here on ENOMEM.  Not much else
diff --git a/fs/timerfd.c b/fs/timerfd.c
index 32b644f03690..929312180dd0 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -8,6 +8,7 @@
  *
  */
 
+#include <linux/alarmtimer.h>
 #include <linux/file.h>
 #include <linux/poll.h>
 #include <linux/init.h>
@@ -26,7 +27,10 @@
 #include <linux/rcupdate.h>
 
 struct timerfd_ctx {
-	struct hrtimer tmr;
+	union {
+		struct hrtimer tmr;
+		struct alarm alarm;
+	} t;
 	ktime_t tintv;
 	ktime_t moffs;
 	wait_queue_head_t wqh;
@@ -41,14 +45,19 @@ struct timerfd_ctx {
 static LIST_HEAD(cancel_list);
 static DEFINE_SPINLOCK(cancel_lock);
 
+static inline bool isalarm(struct timerfd_ctx *ctx)
+{
+	return ctx->clockid == CLOCK_REALTIME_ALARM ||
+		ctx->clockid == CLOCK_BOOTTIME_ALARM;
+}
+
 /*
  * This gets called when the timer event triggers. We set the "expired"
  * flag, but we do not re-arm the timer (in case it's necessary,
  * tintv.tv64 != 0) until the timer is accessed.
  */
-static enum hrtimer_restart timerfd_tmrproc(struct hrtimer *htmr)
+static void timerfd_triggered(struct timerfd_ctx *ctx)
 {
-	struct timerfd_ctx *ctx = container_of(htmr, struct timerfd_ctx, tmr);
 	unsigned long flags;
 
 	spin_lock_irqsave(&ctx->wqh.lock, flags);
@@ -56,10 +65,25 @@ static enum hrtimer_restart timerfd_tmrproc(struct hrtimer *htmr)
 	ctx->ticks++;
 	wake_up_locked(&ctx->wqh);
 	spin_unlock_irqrestore(&ctx->wqh.lock, flags);
+}
 
+static enum hrtimer_restart timerfd_tmrproc(struct hrtimer *htmr)
+{
+	struct timerfd_ctx *ctx = container_of(htmr, struct timerfd_ctx,
+					       t.tmr);
+	timerfd_triggered(ctx);
 	return HRTIMER_NORESTART;
 }
 
+static enum alarmtimer_restart timerfd_alarmproc(struct alarm *alarm,
+	ktime_t now)
+{
+	struct timerfd_ctx *ctx = container_of(alarm, struct timerfd_ctx,
+					       t.alarm);
+	timerfd_triggered(ctx);
+	return ALARMTIMER_NORESTART;
+}
+
 /*
  * Called when the clock was set to cancel the timers in the cancel
  * list. This will wake up processes waiting on these timers. The
@@ -107,8 +131,9 @@ static bool timerfd_canceled(struct timerfd_ctx *ctx)
 
 static void timerfd_setup_cancel(struct timerfd_ctx *ctx, int flags)
 {
-	if (ctx->clockid == CLOCK_REALTIME && (flags & TFD_TIMER_ABSTIME) &&
-	    (flags & TFD_TIMER_CANCEL_ON_SET)) {
+	if ((ctx->clockid == CLOCK_REALTIME ||
+	     ctx->clockid == CLOCK_REALTIME_ALARM) &&
+	    (flags & TFD_TIMER_ABSTIME) && (flags & TFD_TIMER_CANCEL_ON_SET)) {
 		if (!ctx->might_cancel) {
 			ctx->might_cancel = true;
 			spin_lock(&cancel_lock);
@@ -124,7 +149,11 @@ static ktime_t timerfd_get_remaining(struct timerfd_ctx *ctx)
 {
 	ktime_t remaining;
 
-	remaining = hrtimer_expires_remaining(&ctx->tmr);
+	if (isalarm(ctx))
+		remaining = alarm_expires_remaining(&ctx->t.alarm);
+	else
+		remaining = hrtimer_expires_remaining(&ctx->t.tmr);
+
 	return remaining.tv64 < 0 ? ktime_set(0, 0): remaining;
 }
 
@@ -142,11 +171,28 @@ static int timerfd_setup(struct timerfd_ctx *ctx, int flags,
 	ctx->expired = 0;
 	ctx->ticks = 0;
 	ctx->tintv = timespec_to_ktime(ktmr->it_interval);
-	hrtimer_init(&ctx->tmr, clockid, htmode);
-	hrtimer_set_expires(&ctx->tmr, texp);
-	ctx->tmr.function = timerfd_tmrproc;
+
+	if (isalarm(ctx)) {
+		alarm_init(&ctx->t.alarm,
+			   ctx->clockid == CLOCK_REALTIME_ALARM ?
+			   ALARM_REALTIME : ALARM_BOOTTIME,
+			   timerfd_alarmproc);
+	} else {
+		hrtimer_init(&ctx->t.tmr, clockid, htmode);
+		hrtimer_set_expires(&ctx->t.tmr, texp);
+		ctx->t.tmr.function = timerfd_tmrproc;
+	}
+
 	if (texp.tv64 != 0) {
-		hrtimer_start(&ctx->tmr, texp, htmode);
+		if (isalarm(ctx)) {
+			if (flags & TFD_TIMER_ABSTIME)
+				alarm_start(&ctx->t.alarm, texp);
+			else
+				alarm_start_relative(&ctx->t.alarm, texp);
+		} else {
+			hrtimer_start(&ctx->t.tmr, texp, htmode);
+		}
+
 		if (timerfd_canceled(ctx))
 			return -ECANCELED;
 	}
@@ -158,7 +204,11 @@ static int timerfd_release(struct inode *inode, struct file *file)
 	struct timerfd_ctx *ctx = file->private_data;
 
 	timerfd_remove_cancel(ctx);
-	hrtimer_cancel(&ctx->tmr);
+
+	if (isalarm(ctx))
+		alarm_cancel(&ctx->t.alarm);
+	else
+		hrtimer_cancel(&ctx->t.tmr);
 	kfree_rcu(ctx, rcu);
 	return 0;
 }
@@ -215,9 +265,15 @@ static ssize_t timerfd_read(struct file *file, char __user *buf, size_t count,
 			 * callback to avoid DoS attacks specifying a very
 			 * short timer period.
 			 */
-			ticks += hrtimer_forward_now(&ctx->tmr,
-						     ctx->tintv) - 1;
-			hrtimer_restart(&ctx->tmr);
+			if (isalarm(ctx)) {
+				ticks += alarm_forward_now(
+					&ctx->t.alarm, ctx->tintv) - 1;
+				alarm_restart(&ctx->t.alarm);
+			} else {
+				ticks += hrtimer_forward_now(&ctx->t.tmr,
+							     ctx->tintv) - 1;
+				hrtimer_restart(&ctx->t.tmr);
+			}
 		}
 		ctx->expired = 0;
 		ctx->ticks = 0;
@@ -259,7 +315,9 @@ SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags)
 
 	if ((flags & ~TFD_CREATE_FLAGS) ||
 	    (clockid != CLOCK_MONOTONIC &&
-	     clockid != CLOCK_REALTIME))
+	     clockid != CLOCK_REALTIME &&
+	     clockid != CLOCK_REALTIME_ALARM &&
+	     clockid != CLOCK_BOOTTIME_ALARM))
 		return -EINVAL;
 
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
@@ -268,7 +326,15 @@ SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags)
 
 	init_waitqueue_head(&ctx->wqh);
 	ctx->clockid = clockid;
-	hrtimer_init(&ctx->tmr, clockid, HRTIMER_MODE_ABS);
+
+	if (isalarm(ctx))
+		alarm_init(&ctx->t.alarm,
+			   ctx->clockid == CLOCK_REALTIME_ALARM ?
+			   ALARM_REALTIME : ALARM_BOOTTIME,
+			   timerfd_alarmproc);
+	else
+		hrtimer_init(&ctx->t.tmr, clockid, HRTIMER_MODE_ABS);
+
 	ctx->moffs = ktime_get_monotonic_offset();
 
 	ufd = anon_inode_getfd("[timerfd]", &timerfd_fops, ctx,
@@ -305,8 +371,14 @@ static int do_timerfd_settime(int ufd, int flags,
 	 */
 	for (;;) {
 		spin_lock_irq(&ctx->wqh.lock);
-		if (hrtimer_try_to_cancel(&ctx->tmr) >= 0)
-			break;
+
+		if (isalarm(ctx)) {
+			if (alarm_try_to_cancel(&ctx->t.alarm) >= 0)
+				break;
+		} else {
+			if (hrtimer_try_to_cancel(&ctx->t.tmr) >= 0)
+				break;
+		}
 		spin_unlock_irq(&ctx->wqh.lock);
 		cpu_relax();
 	}
@@ -317,8 +389,12 @@ static int do_timerfd_settime(int ufd, int flags,
 	 * We do not update "ticks" and "expired" since the timer will be
 	 * re-programmed again in the following timerfd_setup() call.
 	 */
-	if (ctx->expired && ctx->tintv.tv64)
-		hrtimer_forward_now(&ctx->tmr, ctx->tintv);
+	if (ctx->expired && ctx->tintv.tv64) {
+		if (isalarm(ctx))
+			alarm_forward_now(&ctx->t.alarm, ctx->tintv);
+		else
+			hrtimer_forward_now(&ctx->t.tmr, ctx->tintv);
+	}
 
 	old->it_value = ktime_to_timespec(timerfd_get_remaining(ctx));
 	old->it_interval = ktime_to_timespec(ctx->tintv);
@@ -345,9 +421,18 @@ static int do_timerfd_gettime(int ufd, struct itimerspec *t)
 	spin_lock_irq(&ctx->wqh.lock);
 	if (ctx->expired && ctx->tintv.tv64) {
 		ctx->expired = 0;
-		ctx->ticks +=
-			hrtimer_forward_now(&ctx->tmr, ctx->tintv) - 1;
-		hrtimer_restart(&ctx->tmr);
+
+		if (isalarm(ctx)) {
+			ctx->ticks +=
+				alarm_forward_now(
+					&ctx->t.alarm, ctx->tintv) - 1;
+			alarm_restart(&ctx->t.alarm);
+		} else {
+			ctx->ticks +=
+				hrtimer_forward_now(&ctx->t.tmr, ctx->tintv)
+				- 1;
+			hrtimer_restart(&ctx->t.tmr);
+		}
 	}
 	t->it_value = ktime_to_timespec(timerfd_get_remaining(ctx));
 	t->it_interval = ktime_to_timespec(ctx->tintv);
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 61196592152e..63d17ee9eb48 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -316,6 +316,7 @@ struct drm_ioctl_desc {
 	int flags;
 	drm_ioctl_t *func;
 	unsigned int cmd_drv;
+	const char *name;
 };
 
 /**
@@ -324,7 +325,7 @@ struct drm_ioctl_desc {
  */
 
 #define DRM_IOCTL_DEF_DRV(ioctl, _func, _flags)			\
-	[DRM_IOCTL_NR(DRM_##ioctl)] = {.cmd = DRM_##ioctl, .func = _func, .flags = _flags, .cmd_drv = DRM_IOCTL_##ioctl}
+	[DRM_IOCTL_NR(DRM_##ioctl)] = {.cmd = DRM_##ioctl, .func = _func, .flags = _flags, .cmd_drv = DRM_IOCTL_##ioctl, .name = #ioctl}
 
 struct drm_magic_entry {
 	struct list_head head;
diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h
index 8230b46fdd73..471f276ce8f7 100644
--- a/include/drm/drm_fb_helper.h
+++ b/include/drm/drm_fb_helper.h
@@ -50,13 +50,14 @@ struct drm_fb_helper_surface_size {
 
 /**
  * struct drm_fb_helper_funcs - driver callbacks for the fbdev emulation library
- * @gamma_set: - Set the given gamma lut register on the given crtc.
- * @gamma_get: - Read the given gamma lut register on the given crtc, used to
- * 		 save the current lut when force-restoring the fbdev for e.g.
- * 		 kdbg.
- * @fb_probe: - Driver callback to allocate and initialize the fbdev info
- * 		structure. Futhermore it also needs to allocate the drm
- * 		framebuffer used to back the fbdev.
+ * @gamma_set: Set the given gamma lut register on the given crtc.
+ * @gamma_get: Read the given gamma lut register on the given crtc, used to
+ *             save the current lut when force-restoring the fbdev for e.g.
+ *             kdbg.
+ * @fb_probe: Driver callback to allocate and initialize the fbdev info
+ *            structure. Futhermore it also needs to allocate the drm
+ *            framebuffer used to back the fbdev.
+ * @initial_config: Setup an initial fbdev display configuration
  *
  * Driver callbacks used by the fbdev emulation helper library.
  */
diff --git a/include/linux/alarmtimer.h b/include/linux/alarmtimer.h
index 9069694e70eb..a899402a5a0e 100644
--- a/include/linux/alarmtimer.h
+++ b/include/linux/alarmtimer.h
@@ -44,10 +44,14 @@ struct alarm {
 void alarm_init(struct alarm *alarm, enum alarmtimer_type type,
 		enum alarmtimer_restart (*function)(struct alarm *, ktime_t));
 int alarm_start(struct alarm *alarm, ktime_t start);
+int alarm_start_relative(struct alarm *alarm, ktime_t start);
+void alarm_restart(struct alarm *alarm);
 int alarm_try_to_cancel(struct alarm *alarm);
 int alarm_cancel(struct alarm *alarm);
 
 u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval);
+u64 alarm_forward_now(struct alarm *alarm, ktime_t interval);
+ktime_t alarm_expires_remaining(const struct alarm *alarm);
 
 /* Provide way to access the rtc device being used by alarmtimers */
 struct rtc_device *alarmtimer_get_rtcdev(void);
diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h
index 963d71431388..0857922e8ad0 100644
--- a/include/linux/clockchips.h
+++ b/include/linux/clockchips.h
@@ -30,6 +30,7 @@ enum clock_event_nofitiers {
 #include <linux/notifier.h>
 
 struct clock_event_device;
+struct module;
 
 /* Clock event mode commands */
 enum clock_event_mode {
@@ -83,6 +84,7 @@ enum clock_event_mode {
  * @irq:		IRQ number (only for non CPU local devices)
  * @cpumask:		cpumask to indicate for which CPUs this device works
  * @list:		list head for the management code
+ * @owner:		module reference
  */
 struct clock_event_device {
 	void			(*event_handler)(struct clock_event_device *);
@@ -112,6 +114,7 @@ struct clock_event_device {
 	int			irq;
 	const struct cpumask	*cpumask;
 	struct list_head	list;
+	struct module		*owner;
 } ____cacheline_aligned;
 
 /*
@@ -138,6 +141,7 @@ static inline unsigned long div_sc(unsigned long ticks, unsigned long nsec,
 extern u64 clockevent_delta2ns(unsigned long latch,
 			       struct clock_event_device *evt);
 extern void clockevents_register_device(struct clock_event_device *dev);
+extern int clockevents_unbind_device(struct clock_event_device *ced, int cpu);
 
 extern void clockevents_config(struct clock_event_device *dev, u32 freq);
 extern void clockevents_config_and_register(struct clock_event_device *dev,
@@ -150,7 +154,6 @@ extern void clockevents_exchange_device(struct clock_event_device *old,
 					struct clock_event_device *new);
 extern void clockevents_set_mode(struct clock_event_device *dev,
 				 enum clock_event_mode mode);
-extern int clockevents_register_notifier(struct notifier_block *nb);
 extern int clockevents_program_event(struct clock_event_device *dev,
 				     ktime_t expires, bool force);
 
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index 7279b94c01da..2f39a4911668 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -21,6 +21,7 @@
 /* clocksource cycle base type */
 typedef u64 cycle_t;
 struct clocksource;
+struct module;
 
 #ifdef CONFIG_ARCH_CLOCKSOURCE_DATA
 #include <asm/clocksource.h>
@@ -162,6 +163,7 @@ extern u64 timecounter_cyc2time(struct timecounter *tc,
  * @suspend:		suspend function for the clocksource, if necessary
  * @resume:		resume function for the clocksource, if necessary
  * @cycle_last:		most recent cycle counter value seen by ::read()
+ * @owner:		module reference, must be set by clocksource in modules
  */
 struct clocksource {
 	/*
@@ -195,6 +197,7 @@ struct clocksource {
 	cycle_t cs_last;
 	cycle_t wd_last;
 #endif
+	struct module *owner;
 } ____cacheline_aligned;
 
 /*
@@ -279,7 +282,7 @@ static inline s64 clocksource_cyc2ns(cycle_t cycles, u32 mult, u32 shift)
 
 
 extern int clocksource_register(struct clocksource*);
-extern void clocksource_unregister(struct clocksource*);
+extern int clocksource_unregister(struct clocksource*);
 extern void clocksource_touch_watchdog(void);
 extern struct clocksource* clocksource_get_next(void);
 extern void clocksource_change_rating(struct clocksource *cs, int rating);
@@ -321,7 +324,7 @@ static inline void __clocksource_updatefreq_khz(struct clocksource *cs, u32 khz)
 }
 
 
-extern void timekeeping_notify(struct clocksource *clock);
+extern int timekeeping_notify(struct clocksource *clock);
 
 extern cycle_t clocksource_mmio_readl_up(struct clocksource *);
 extern cycle_t clocksource_mmio_readl_down(struct clocksource *);
diff --git a/include/linux/dw_apb_timer.h b/include/linux/dw_apb_timer.h
index dd755ce2a5eb..b1cd9597c241 100644
--- a/include/linux/dw_apb_timer.h
+++ b/include/linux/dw_apb_timer.h
@@ -51,7 +51,6 @@ dw_apb_clocksource_init(unsigned rating, const char *name, void __iomem *base,
 void dw_apb_clocksource_register(struct dw_apb_clocksource *dw_cs);
 void dw_apb_clocksource_start(struct dw_apb_clocksource *dw_cs);
 cycle_t dw_apb_clocksource_read(struct dw_apb_clocksource *dw_cs);
-void dw_apb_clocksource_unregister(struct dw_apb_clocksource *dw_cs);
 
 extern void dw_apb_timer_init(void);
 #endif /* __DW_APB_TIMER_H__ */
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 2bc0ad78d058..0068bba6f8b6 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -594,8 +594,8 @@ extern u64 efi_mem_attribute (unsigned long phys_addr, unsigned long size);
 extern int __init efi_uart_console_only (void);
 extern void efi_initialize_iomem_resources(struct resource *code_resource,
 		struct resource *data_resource, struct resource *bss_resource);
-extern unsigned long efi_get_time(void);
-extern int efi_set_rtc_mmss(unsigned long nowtime);
+extern void efi_get_time(struct timespec *now);
+extern int efi_set_rtc_mmss(const struct timespec *now);
 extern void efi_reserve_boot_services(void);
 extern struct efi_memory_map memmap;
 
diff --git a/include/linux/journal-head.h b/include/linux/journal-head.h
index 13a3da25ff07..98cd41bb39c8 100644
--- a/include/linux/journal-head.h
+++ b/include/linux/journal-head.h
@@ -30,15 +30,19 @@ struct journal_head {
 
 	/*
 	 * Journalling list for this buffer [jbd_lock_bh_state()]
+	 * NOTE: We *cannot* combine this with b_modified into a bitfield
+	 * as gcc would then (which the C standard allows but which is
+	 * very unuseful) make 64-bit accesses to the bitfield and clobber
+	 * b_jcount if its update races with bitfield modification.
 	 */
-	unsigned b_jlist:4;
+	unsigned b_jlist;
 
 	/*
 	 * This flag signals the buffer has been modified by
 	 * the currently running transaction
 	 * [jbd_lock_bh_state()]
 	 */
-	unsigned b_modified:1;
+	unsigned b_modified;
 
 	/*
 	 * Copy of the buffer data frozen for writing to the log.
diff --git a/include/linux/ktime.h b/include/linux/ktime.h
index bbca12804d12..fc66b301b648 100644
--- a/include/linux/ktime.h
+++ b/include/linux/ktime.h
@@ -229,7 +229,8 @@ static inline ktime_t timespec_to_ktime(const struct timespec ts)
 static inline ktime_t timeval_to_ktime(const struct timeval tv)
 {
 	return (ktime_t) { .tv = { .sec = (s32)tv.tv_sec,
-				   .nsec = (s32)tv.tv_usec * 1000 } };
+				   .nsec = (s32)(tv.tv_usec *
+						 NSEC_PER_USEC) } };
 }
 
 /**
@@ -320,12 +321,12 @@ static inline s64 ktime_us_delta(const ktime_t later, const ktime_t earlier)
 
 static inline ktime_t ktime_add_us(const ktime_t kt, const u64 usec)
 {
-	return ktime_add_ns(kt, usec * 1000);
+	return ktime_add_ns(kt, usec * NSEC_PER_USEC);
 }
 
 static inline ktime_t ktime_sub_us(const ktime_t kt, const u64 usec)
 {
-	return ktime_sub_ns(kt, usec * 1000);
+	return ktime_sub_ns(kt, usec * NSEC_PER_USEC);
 }
 
 extern ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs);
@@ -338,7 +339,8 @@ extern ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs);
  *
  * Returns true if there was a successful conversion, false if kt was 0.
  */
-static inline bool ktime_to_timespec_cond(const ktime_t kt, struct timespec *ts)
+static inline __must_check bool ktime_to_timespec_cond(const ktime_t kt,
+						       struct timespec *ts)
 {
 	if (kt.tv64) {
 		*ts = ktime_to_timespec(kt);
diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h
index 67f46ad6920a..352eec9df1b8 100644
--- a/include/linux/mlx4/qp.h
+++ b/include/linux/mlx4/qp.h
@@ -126,7 +126,7 @@ struct mlx4_rss_context {
 
 struct mlx4_qp_path {
 	u8			fl;
-	u8			reserved1[1];
+	u8			vlan_control;
 	u8			disable_pkey_check;
 	u8			pkey_index;
 	u8			counter_index;
@@ -141,11 +141,32 @@ struct mlx4_qp_path {
 	u8			sched_queue;
 	u8			vlan_index;
 	u8			feup;
-	u8			reserved3;
+	u8			fvl_rx;
 	u8			reserved4[2];
 	u8			dmac[6];
 };
 
+enum { /* fl */
+	MLX4_FL_CV      = 1 << 6,
+	MLX4_FL_ETH_HIDE_CQE_VLAN       = 1 << 2
+};
+enum { /* vlan_control */
+	MLX4_VLAN_CTRL_ETH_TX_BLOCK_TAGGED	= 1 << 6,
+	MLX4_VLAN_CTRL_ETH_RX_BLOCK_TAGGED	= 1 << 2,
+	MLX4_VLAN_CTRL_ETH_RX_BLOCK_PRIO_TAGGED	= 1 << 1, /* 802.1p priority tag */
+	MLX4_VLAN_CTRL_ETH_RX_BLOCK_UNTAGGED	= 1 << 0
+};
+
+enum { /* feup */
+	MLX4_FEUP_FORCE_ETH_UP          = 1 << 6, /* force Eth UP */
+	MLX4_FSM_FORCE_ETH_SRC_MAC      = 1 << 5, /* force Source MAC */
+	MLX4_FVL_FORCE_ETH_VLAN         = 1 << 3  /* force Eth vlan */
+};
+
+enum { /* fvl_rx */
+	MLX4_FVL_RX_FORCE_ETH_VLAN      = 1 << 0 /* enforce Eth rx vlan */
+};
+
 struct mlx4_qp_context {
 	__be32			flags;
 	__be32			pd;
@@ -185,6 +206,10 @@ struct mlx4_qp_context {
 	u32			reserved5[10];
 };
 
+enum { /* param3 */
+	MLX4_STRIP_VLAN = 1 << 30
+};
+
 /* Which firmware version adds support for NEC (NoErrorCompletion) bit */
 #define MLX4_FW_VER_WQE_CTRL_NEC mlx4_fw_ver(2, 2, 232)
 
diff --git a/include/linux/sched_clock.h b/include/linux/sched_clock.h
new file mode 100644
index 000000000000..fa7922c80a41
--- /dev/null
+++ b/include/linux/sched_clock.h
@@ -0,0 +1,21 @@
+/*
+ * sched_clock.h: support for extending counters to full 64-bit ns counter
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef LINUX_SCHED_CLOCK
+#define LINUX_SCHED_CLOCK
+
+#ifdef CONFIG_GENERIC_SCHED_CLOCK
+extern void sched_clock_postinit(void);
+#else
+static inline void sched_clock_postinit(void) { }
+#endif
+
+extern void setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate);
+
+extern unsigned long long (*sched_clock_func)(void);
+
+#endif
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 733eb5ee31c5..6ff26c8db7b9 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -57,7 +57,7 @@ extern struct bus_type spi_bus_type;
  * @modalias: Name of the driver to use with this device, or an alias
  *	for that name.  This appears in the sysfs "modalias" attribute
  *	for driver coldplugging, and in uevents used for hotplugging
- * @cs_gpio: gpio number of the chipselect line (optional, -EINVAL when
+ * @cs_gpio: gpio number of the chipselect line (optional, -ENOENT when
  *	when not using a GPIO line)
  *
  * A @spi_device is used to interchange data between an SPI slave
@@ -266,7 +266,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv)
  *	queue so the subsystem notifies the driver that it may relax the
  *	hardware by issuing this call
  * @cs_gpios: Array of GPIOs to use as chip select lines; one per CS
- *	number. Any individual value may be -EINVAL for CS lines that
+ *	number. Any individual value may be -ENOENT for CS lines that
  *	are not GPIOs (driven by the SPI controller itself).
  *
  * Each SPI master controller can communicate with one or more @spi_device
diff --git a/include/linux/time.h b/include/linux/time.h
index 22d81b3c955b..d5d229b2e5af 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -117,14 +117,10 @@ static inline bool timespec_valid_strict(const struct timespec *ts)
 
 extern bool persistent_clock_exist;
 
-#ifdef ALWAYS_USE_PERSISTENT_CLOCK
-#define has_persistent_clock()	true
-#else
 static inline bool has_persistent_clock(void)
 {
 	return persistent_clock_exist;
 }
-#endif
 
 extern void read_persistent_clock(struct timespec *ts);
 extern void read_boot_clock(struct timespec *ts);
diff --git a/include/net/sock.h b/include/net/sock.h
index 5c97b0fc5623..66772cf8c3c5 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -866,6 +866,18 @@ struct inet_hashinfo;
 struct raw_hashinfo;
 struct module;
 
+/*
+ * caches using SLAB_DESTROY_BY_RCU should let .next pointer from nulls nodes
+ * un-modified. Special care is taken when initializing object to zero.
+ */
+static inline void sk_prot_clear_nulls(struct sock *sk, int size)
+{
+	if (offsetof(struct sock, sk_node.next) != 0)
+		memset(sk, 0, offsetof(struct sock, sk_node.next));
+	memset(&sk->sk_node.pprev, 0,
+	       size - offsetof(struct sock, sk_node.pprev));
+}
+
 /* Networking protocol blocks we attach to sockets.
  * socket layer -> transport layer interface
  * transport -> network interface is defined by struct inet_proto
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index d0e686402df8..8ee15b97cd38 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -2139,7 +2139,7 @@ TRACE_EVENT(ext4_es_remove_extent,
 		  __entry->lblk, __entry->len)
 );
 
-TRACE_EVENT(ext4_es_find_delayed_extent_enter,
+TRACE_EVENT(ext4_es_find_delayed_extent_range_enter,
 	TP_PROTO(struct inode *inode, ext4_lblk_t lblk),
 
 	TP_ARGS(inode, lblk),
@@ -2161,7 +2161,7 @@ TRACE_EVENT(ext4_es_find_delayed_extent_enter,
 		  (unsigned long) __entry->ino, __entry->lblk)
 );
 
-TRACE_EVENT(ext4_es_find_delayed_extent_exit,
+TRACE_EVENT(ext4_es_find_delayed_extent_range_exit,
 	TP_PROTO(struct inode *inode, struct extent_status *es),
 
 	TP_ARGS(inode, es),
diff --git a/init/Kconfig b/init/Kconfig
index 9d3a7887a6d3..1a3f93329a67 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -757,6 +757,9 @@ config LOG_BUF_SHIFT
 config HAVE_UNSTABLE_SCHED_CLOCK
 	bool
 
+config GENERIC_SCHED_CLOCK
+	bool
+
 #
 # For architectures that want to enable the support for NUMA-affine scheduler
 # balancing logic:
diff --git a/init/main.c b/init/main.c
index 9484f4ba88d0..bef4a6ac7c76 100644
--- a/init/main.c
+++ b/init/main.c
@@ -74,6 +74,7 @@
 #include <linux/ptrace.h>
 #include <linux/blkdev.h>
 #include <linux/elevator.h>
+#include <linux/sched_clock.h>
 
 #include <asm/io.h>
 #include <asm/bugs.h>
@@ -555,6 +556,7 @@ asmlinkage void __init start_kernel(void)
 	softirq_init();
 	timekeeping_init();
 	time_init();
+	sched_clock_postinit();
 	profile_init();
 	call_function_init();
 	WARN(!irqs_disabled(), "Interrupts were enabled early\n");
diff --git a/kernel/cpu/idle.c b/kernel/cpu/idle.c
index 8b86c0c68edf..d5585f5e038e 100644
--- a/kernel/cpu/idle.c
+++ b/kernel/cpu/idle.c
@@ -40,11 +40,13 @@ __setup("hlt", cpu_idle_nopoll_setup);
 
 static inline int cpu_idle_poll(void)
 {
+	rcu_idle_enter();
 	trace_cpu_idle_rcuidle(0, smp_processor_id());
 	local_irq_enable();
 	while (!need_resched())
 		cpu_relax();
 	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
+	rcu_idle_exit();
 	return 1;
 }
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 6b41c1899a8b..9dc297faf7c0 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4394,6 +4394,64 @@ perf_event_read_event(struct perf_event *event,
 	perf_output_end(&handle);
 }
 
+typedef int  (perf_event_aux_match_cb)(struct perf_event *event, void *data);
+typedef void (perf_event_aux_output_cb)(struct perf_event *event, void *data);
+
+static void
+perf_event_aux_ctx(struct perf_event_context *ctx,
+		   perf_event_aux_match_cb match,
+		   perf_event_aux_output_cb output,
+		   void *data)
+{
+	struct perf_event *event;
+
+	list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
+		if (event->state < PERF_EVENT_STATE_INACTIVE)
+			continue;
+		if (!event_filter_match(event))
+			continue;
+		if (match(event, data))
+			output(event, data);
+	}
+}
+
+static void
+perf_event_aux(perf_event_aux_match_cb match,
+	       perf_event_aux_output_cb output,
+	       void *data,
+	       struct perf_event_context *task_ctx)
+{
+	struct perf_cpu_context *cpuctx;
+	struct perf_event_context *ctx;
+	struct pmu *pmu;
+	int ctxn;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(pmu, &pmus, entry) {
+		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
+		if (cpuctx->unique_pmu != pmu)
+			goto next;
+		perf_event_aux_ctx(&cpuctx->ctx, match, output, data);
+		if (task_ctx)
+			goto next;
+		ctxn = pmu->task_ctx_nr;
+		if (ctxn < 0)
+			goto next;
+		ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
+		if (ctx)
+			perf_event_aux_ctx(ctx, match, output, data);
+next:
+		put_cpu_ptr(pmu->pmu_cpu_context);
+	}
+
+	if (task_ctx) {
+		preempt_disable();
+		perf_event_aux_ctx(task_ctx, match, output, data);
+		preempt_enable();
+	}
+	rcu_read_unlock();
+}
+
 /*
  * task tracking -- fork/exit
  *
@@ -4416,8 +4474,9 @@ struct perf_task_event {
 };
 
 static void perf_event_task_output(struct perf_event *event,
-				     struct perf_task_event *task_event)
+				   void *data)
 {
+	struct perf_task_event *task_event = data;
 	struct perf_output_handle handle;
 	struct perf_sample_data	sample;
 	struct task_struct *task = task_event->task;
@@ -4445,62 +4504,11 @@ out:
 	task_event->event_id.header.size = size;
 }
 
-static int perf_event_task_match(struct perf_event *event)
-{
-	if (event->state < PERF_EVENT_STATE_INACTIVE)
-		return 0;
-
-	if (!event_filter_match(event))
-		return 0;
-
-	if (event->attr.comm || event->attr.mmap ||
-	    event->attr.mmap_data || event->attr.task)
-		return 1;
-
-	return 0;
-}
-
-static void perf_event_task_ctx(struct perf_event_context *ctx,
-				  struct perf_task_event *task_event)
+static int perf_event_task_match(struct perf_event *event,
+				 void *data __maybe_unused)
 {
-	struct perf_event *event;
-
-	list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
-		if (perf_event_task_match(event))
-			perf_event_task_output(event, task_event);
-	}
-}
-
-static void perf_event_task_event(struct perf_task_event *task_event)
-{
-	struct perf_cpu_context *cpuctx;
-	struct perf_event_context *ctx;
-	struct pmu *pmu;
-	int ctxn;
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(pmu, &pmus, entry) {
-		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
-		if (cpuctx->unique_pmu != pmu)
-			goto next;
-		perf_event_task_ctx(&cpuctx->ctx, task_event);
-
-		ctx = task_event->task_ctx;
-		if (!ctx) {
-			ctxn = pmu->task_ctx_nr;
-			if (ctxn < 0)
-				goto next;
-			ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
-			if (ctx)
-				perf_event_task_ctx(ctx, task_event);
-		}
-next:
-		put_cpu_ptr(pmu->pmu_cpu_context);
-	}
-	if (task_event->task_ctx)
-		perf_event_task_ctx(task_event->task_ctx, task_event);
-
-	rcu_read_unlock();
+	return event->attr.comm || event->attr.mmap ||
+	       event->attr.mmap_data || event->attr.task;
 }
 
 static void perf_event_task(struct task_struct *task,
@@ -4531,7 +4539,10 @@ static void perf_event_task(struct task_struct *task,
 		},
 	};
 
-	perf_event_task_event(&task_event);
+	perf_event_aux(perf_event_task_match,
+		       perf_event_task_output,
+		       &task_event,
+		       task_ctx);
 }
 
 void perf_event_fork(struct task_struct *task)
@@ -4557,8 +4568,9 @@ struct perf_comm_event {
 };
 
 static void perf_event_comm_output(struct perf_event *event,
-				     struct perf_comm_event *comm_event)
+				   void *data)
 {
+	struct perf_comm_event *comm_event = data;
 	struct perf_output_handle handle;
 	struct perf_sample_data sample;
 	int size = comm_event->event_id.header.size;
@@ -4585,39 +4597,16 @@ out:
 	comm_event->event_id.header.size = size;
 }
 
-static int perf_event_comm_match(struct perf_event *event)
-{
-	if (event->state < PERF_EVENT_STATE_INACTIVE)
-		return 0;
-
-	if (!event_filter_match(event))
-		return 0;
-
-	if (event->attr.comm)
-		return 1;
-
-	return 0;
-}
-
-static void perf_event_comm_ctx(struct perf_event_context *ctx,
-				  struct perf_comm_event *comm_event)
+static int perf_event_comm_match(struct perf_event *event,
+				 void *data __maybe_unused)
 {
-	struct perf_event *event;
-
-	list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
-		if (perf_event_comm_match(event))
-			perf_event_comm_output(event, comm_event);
-	}
+	return event->attr.comm;
 }
 
 static void perf_event_comm_event(struct perf_comm_event *comm_event)
 {
-	struct perf_cpu_context *cpuctx;
-	struct perf_event_context *ctx;
 	char comm[TASK_COMM_LEN];
 	unsigned int size;
-	struct pmu *pmu;
-	int ctxn;
 
 	memset(comm, 0, sizeof(comm));
 	strlcpy(comm, comm_event->task->comm, sizeof(comm));
@@ -4627,24 +4616,11 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event)
 	comm_event->comm_size = size;
 
 	comm_event->event_id.header.size = sizeof(comm_event->event_id) + size;
-	rcu_read_lock();
-	list_for_each_entry_rcu(pmu, &pmus, entry) {
-		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
-		if (cpuctx->unique_pmu != pmu)
-			goto next;
-		perf_event_comm_ctx(&cpuctx->ctx, comm_event);
 
-		ctxn = pmu->task_ctx_nr;
-		if (ctxn < 0)
-			goto next;
-
-		ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
-		if (ctx)
-			perf_event_comm_ctx(ctx, comm_event);
-next:
-		put_cpu_ptr(pmu->pmu_cpu_context);
-	}
-	rcu_read_unlock();
+	perf_event_aux(perf_event_comm_match,
+		       perf_event_comm_output,
+		       comm_event,
+		       NULL);
 }
 
 void perf_event_comm(struct task_struct *task)
@@ -4706,8 +4682,9 @@ struct perf_mmap_event {
 };
 
 static void perf_event_mmap_output(struct perf_event *event,
-				     struct perf_mmap_event *mmap_event)
+				   void *data)
 {
+	struct perf_mmap_event *mmap_event = data;
 	struct perf_output_handle handle;
 	struct perf_sample_data sample;
 	int size = mmap_event->event_id.header.size;
@@ -4734,46 +4711,24 @@ out:
 }
 
 static int perf_event_mmap_match(struct perf_event *event,
-				   struct perf_mmap_event *mmap_event,
-				   int executable)
-{
-	if (event->state < PERF_EVENT_STATE_INACTIVE)
-		return 0;
-
-	if (!event_filter_match(event))
-		return 0;
-
-	if ((!executable && event->attr.mmap_data) ||
-	    (executable && event->attr.mmap))
-		return 1;
-
-	return 0;
-}
-
-static void perf_event_mmap_ctx(struct perf_event_context *ctx,
-				  struct perf_mmap_event *mmap_event,
-				  int executable)
+				 void *data)
 {
-	struct perf_event *event;
+	struct perf_mmap_event *mmap_event = data;
+	struct vm_area_struct *vma = mmap_event->vma;
+	int executable = vma->vm_flags & VM_EXEC;
 
-	list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
-		if (perf_event_mmap_match(event, mmap_event, executable))
-			perf_event_mmap_output(event, mmap_event);
-	}
+	return (!executable && event->attr.mmap_data) ||
+	       (executable && event->attr.mmap);
 }
 
 static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
 {
-	struct perf_cpu_context *cpuctx;
-	struct perf_event_context *ctx;
 	struct vm_area_struct *vma = mmap_event->vma;
 	struct file *file = vma->vm_file;
 	unsigned int size;
 	char tmp[16];
 	char *buf = NULL;
 	const char *name;
-	struct pmu *pmu;
-	int ctxn;
 
 	memset(tmp, 0, sizeof(tmp));
 
@@ -4829,27 +4784,10 @@ got_name:
 
 	mmap_event->event_id.header.size = sizeof(mmap_event->event_id) + size;
 
-	rcu_read_lock();
-	list_for_each_entry_rcu(pmu, &pmus, entry) {
-		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
-		if (cpuctx->unique_pmu != pmu)
-			goto next;
-		perf_event_mmap_ctx(&cpuctx->ctx, mmap_event,
-					vma->vm_flags & VM_EXEC);
-
-		ctxn = pmu->task_ctx_nr;
-		if (ctxn < 0)
-			goto next;
-
-		ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
-		if (ctx) {
-			perf_event_mmap_ctx(ctx, mmap_event,
-					vma->vm_flags & VM_EXEC);
-		}
-next:
-		put_cpu_ptr(pmu->pmu_cpu_context);
-	}
-	rcu_read_unlock();
+	perf_event_aux(perf_event_mmap_match,
+		       perf_event_mmap_output,
+		       mmap_event,
+		       NULL);
 
 	kfree(buf);
 }
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index e4c07b0692bb..70f27e89012b 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -12,11 +12,6 @@ config CLOCKSOURCE_WATCHDOG
 config ARCH_CLOCKSOURCE_DATA
 	bool
 
-# Platforms has a persistent clock
-config ALWAYS_USE_PERSISTENT_CLOCK
-	bool
-	default n
-
 # Timekeeping vsyscall support
 config GENERIC_TIME_VSYSCALL
 	bool
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index ff7d9d2ab504..9250130646f5 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -4,6 +4,8 @@ obj-y += timeconv.o posix-clock.o alarmtimer.o
 obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD)		+= clockevents.o
 obj-$(CONFIG_GENERIC_CLOCKEVENTS)		+= tick-common.o
 obj-$(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST)	+= tick-broadcast.o
+obj-$(CONFIG_GENERIC_SCHED_CLOCK)		+= sched_clock.o
 obj-$(CONFIG_TICK_ONESHOT)			+= tick-oneshot.o
 obj-$(CONFIG_TICK_ONESHOT)			+= tick-sched.o
 obj-$(CONFIG_TIMER_STATS)			+= timer_stats.o
+obj-$(CONFIG_DEBUG_FS)				+= timekeeping_debug.o
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index f11d83b12949..eec50fcef9e4 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -199,6 +199,13 @@ static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer)
 
 }
 
+ktime_t alarm_expires_remaining(const struct alarm *alarm)
+{
+	struct alarm_base *base = &alarm_bases[alarm->type];
+	return ktime_sub(alarm->node.expires, base->gettime());
+}
+EXPORT_SYMBOL_GPL(alarm_expires_remaining);
+
 #ifdef CONFIG_RTC_CLASS
 /**
  * alarmtimer_suspend - Suspend time callback
@@ -303,9 +310,10 @@ void alarm_init(struct alarm *alarm, enum alarmtimer_type type,
 	alarm->type = type;
 	alarm->state = ALARMTIMER_STATE_INACTIVE;
 }
+EXPORT_SYMBOL_GPL(alarm_init);
 
 /**
- * alarm_start - Sets an alarm to fire
+ * alarm_start - Sets an absolute alarm to fire
  * @alarm: ptr to alarm to set
  * @start: time to run the alarm
  */
@@ -323,6 +331,34 @@ int alarm_start(struct alarm *alarm, ktime_t start)
 	spin_unlock_irqrestore(&base->lock, flags);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(alarm_start);
+
+/**
+ * alarm_start_relative - Sets a relative alarm to fire
+ * @alarm: ptr to alarm to set
+ * @start: time relative to now to run the alarm
+ */
+int alarm_start_relative(struct alarm *alarm, ktime_t start)
+{
+	struct alarm_base *base = &alarm_bases[alarm->type];
+
+	start = ktime_add(start, base->gettime());
+	return alarm_start(alarm, start);
+}
+EXPORT_SYMBOL_GPL(alarm_start_relative);
+
+void alarm_restart(struct alarm *alarm)
+{
+	struct alarm_base *base = &alarm_bases[alarm->type];
+	unsigned long flags;
+
+	spin_lock_irqsave(&base->lock, flags);
+	hrtimer_set_expires(&alarm->timer, alarm->node.expires);
+	hrtimer_restart(&alarm->timer);
+	alarmtimer_enqueue(base, alarm);
+	spin_unlock_irqrestore(&base->lock, flags);
+}
+EXPORT_SYMBOL_GPL(alarm_restart);
 
 /**
  * alarm_try_to_cancel - Tries to cancel an alarm timer
@@ -344,6 +380,7 @@ int alarm_try_to_cancel(struct alarm *alarm)
 	spin_unlock_irqrestore(&base->lock, flags);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(alarm_try_to_cancel);
 
 
 /**
@@ -361,6 +398,7 @@ int alarm_cancel(struct alarm *alarm)
 		cpu_relax();
 	}
 }
+EXPORT_SYMBOL_GPL(alarm_cancel);
 
 
 u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval)
@@ -393,8 +431,15 @@ u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval)
 	alarm->node.expires = ktime_add(alarm->node.expires, interval);
 	return overrun;
 }
+EXPORT_SYMBOL_GPL(alarm_forward);
 
+u64 alarm_forward_now(struct alarm *alarm, ktime_t interval)
+{
+	struct alarm_base *base = &alarm_bases[alarm->type];
 
+	return alarm_forward(alarm, base->gettime(), interval);
+}
+EXPORT_SYMBOL_GPL(alarm_forward_now);
 
 
 /**
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index c6d6400ee137..38959c866789 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -15,20 +15,23 @@
 #include <linux/hrtimer.h>
 #include <linux/init.h>
 #include <linux/module.h>
-#include <linux/notifier.h>
 #include <linux/smp.h>
+#include <linux/device.h>
 
 #include "tick-internal.h"
 
 /* The registered clock event devices */
 static LIST_HEAD(clockevent_devices);
 static LIST_HEAD(clockevents_released);
-
-/* Notification for clock events */
-static RAW_NOTIFIER_HEAD(clockevents_chain);
-
 /* Protection for the above */
 static DEFINE_RAW_SPINLOCK(clockevents_lock);
+/* Protection for unbind operations */
+static DEFINE_MUTEX(clockevents_mutex);
+
+struct ce_unbind {
+	struct clock_event_device *ce;
+	int res;
+};
 
 /**
  * clockevents_delta2ns - Convert a latch value (device ticks) to nanoseconds
@@ -232,47 +235,107 @@ int clockevents_program_event(struct clock_event_device *dev, ktime_t expires,
 	return (rc && force) ? clockevents_program_min_delta(dev) : rc;
 }
 
-/**
- * clockevents_register_notifier - register a clock events change listener
+/*
+ * Called after a notify add to make devices available which were
+ * released from the notifier call.
  */
-int clockevents_register_notifier(struct notifier_block *nb)
+static void clockevents_notify_released(void)
 {
-	unsigned long flags;
-	int ret;
+	struct clock_event_device *dev;
 
-	raw_spin_lock_irqsave(&clockevents_lock, flags);
-	ret = raw_notifier_chain_register(&clockevents_chain, nb);
-	raw_spin_unlock_irqrestore(&clockevents_lock, flags);
+	while (!list_empty(&clockevents_released)) {
+		dev = list_entry(clockevents_released.next,
+				 struct clock_event_device, list);
+		list_del(&dev->list);
+		list_add(&dev->list, &clockevent_devices);
+		tick_check_new_device(dev);
+	}
+}
 
-	return ret;
+/*
+ * Try to install a replacement clock event device
+ */
+static int clockevents_replace(struct clock_event_device *ced)
+{
+	struct clock_event_device *dev, *newdev = NULL;
+
+	list_for_each_entry(dev, &clockevent_devices, list) {
+		if (dev == ced || dev->mode != CLOCK_EVT_MODE_UNUSED)
+			continue;
+
+		if (!tick_check_replacement(newdev, dev))
+			continue;
+
+		if (!try_module_get(dev->owner))
+			continue;
+
+		if (newdev)
+			module_put(newdev->owner);
+		newdev = dev;
+	}
+	if (newdev) {
+		tick_install_replacement(newdev);
+		list_del_init(&ced->list);
+	}
+	return newdev ? 0 : -EBUSY;
 }
 
 /*
- * Notify about a clock event change. Called with clockevents_lock
- * held.
+ * Called with clockevents_mutex and clockevents_lock held
  */
-static void clockevents_do_notify(unsigned long reason, void *dev)
+static int __clockevents_try_unbind(struct clock_event_device *ced, int cpu)
 {
-	raw_notifier_call_chain(&clockevents_chain, reason, dev);
+	/* Fast track. Device is unused */
+	if (ced->mode == CLOCK_EVT_MODE_UNUSED) {
+		list_del_init(&ced->list);
+		return 0;
+	}
+
+	return ced == per_cpu(tick_cpu_device, cpu).evtdev ? -EAGAIN : -EBUSY;
 }
 
 /*
- * Called after a notify add to make devices available which were
- * released from the notifier call.
+ * SMP function call to unbind a device
  */
-static void clockevents_notify_released(void)
+static void __clockevents_unbind(void *arg)
 {
-	struct clock_event_device *dev;
+	struct ce_unbind *cu = arg;
+	int res;
+
+	raw_spin_lock(&clockevents_lock);
+	res = __clockevents_try_unbind(cu->ce, smp_processor_id());
+	if (res == -EAGAIN)
+		res = clockevents_replace(cu->ce);
+	cu->res = res;
+	raw_spin_unlock(&clockevents_lock);
+}
 
-	while (!list_empty(&clockevents_released)) {
-		dev = list_entry(clockevents_released.next,
-				 struct clock_event_device, list);
-		list_del(&dev->list);
-		list_add(&dev->list, &clockevent_devices);
-		clockevents_do_notify(CLOCK_EVT_NOTIFY_ADD, dev);
-	}
+/*
+ * Issues smp function call to unbind a per cpu device. Called with
+ * clockevents_mutex held.
+ */
+static int clockevents_unbind(struct clock_event_device *ced, int cpu)
+{
+	struct ce_unbind cu = { .ce = ced, .res = -ENODEV };
+
+	smp_call_function_single(cpu, __clockevents_unbind, &cu, 1);
+	return cu.res;
 }
 
+/*
+ * Unbind a clockevents device.
+ */
+int clockevents_unbind_device(struct clock_event_device *ced, int cpu)
+{
+	int ret;
+
+	mutex_lock(&clockevents_mutex);
+	ret = clockevents_unbind(ced, cpu);
+	mutex_unlock(&clockevents_mutex);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(clockevents_unbind);
+
 /**
  * clockevents_register_device - register a clock event device
  * @dev:	device to register
@@ -290,7 +353,7 @@ void clockevents_register_device(struct clock_event_device *dev)
 	raw_spin_lock_irqsave(&clockevents_lock, flags);
 
 	list_add(&dev->list, &clockevent_devices);
-	clockevents_do_notify(CLOCK_EVT_NOTIFY_ADD, dev);
+	tick_check_new_device(dev);
 	clockevents_notify_released();
 
 	raw_spin_unlock_irqrestore(&clockevents_lock, flags);
@@ -386,6 +449,7 @@ void clockevents_exchange_device(struct clock_event_device *old,
 	 * released list and do a notify add later.
 	 */
 	if (old) {
+		module_put(old->owner);
 		clockevents_set_mode(old, CLOCK_EVT_MODE_UNUSED);
 		list_del(&old->list);
 		list_add(&old->list, &clockevents_released);
@@ -433,10 +497,36 @@ void clockevents_notify(unsigned long reason, void *arg)
 	int cpu;
 
 	raw_spin_lock_irqsave(&clockevents_lock, flags);
-	clockevents_do_notify(reason, arg);
 
 	switch (reason) {
+	case CLOCK_EVT_NOTIFY_BROADCAST_ON:
+	case CLOCK_EVT_NOTIFY_BROADCAST_OFF:
+	case CLOCK_EVT_NOTIFY_BROADCAST_FORCE:
+		tick_broadcast_on_off(reason, arg);
+		break;
+
+	case CLOCK_EVT_NOTIFY_BROADCAST_ENTER:
+	case CLOCK_EVT_NOTIFY_BROADCAST_EXIT:
+		tick_broadcast_oneshot_control(reason);
+		break;
+
+	case CLOCK_EVT_NOTIFY_CPU_DYING:
+		tick_handover_do_timer(arg);
+		break;
+
+	case CLOCK_EVT_NOTIFY_SUSPEND:
+		tick_suspend();
+		tick_suspend_broadcast();
+		break;
+
+	case CLOCK_EVT_NOTIFY_RESUME:
+		tick_resume();
+		break;
+
 	case CLOCK_EVT_NOTIFY_CPU_DEAD:
+		tick_shutdown_broadcast_oneshot(arg);
+		tick_shutdown_broadcast(arg);
+		tick_shutdown(arg);
 		/*
 		 * Unregister the clock event devices which were
 		 * released from the users in the notify chain.
@@ -462,4 +552,123 @@ void clockevents_notify(unsigned long reason, void *arg)
 	raw_spin_unlock_irqrestore(&clockevents_lock, flags);
 }
 EXPORT_SYMBOL_GPL(clockevents_notify);
+
+#ifdef CONFIG_SYSFS
+struct bus_type clockevents_subsys = {
+	.name		= "clockevents",
+	.dev_name       = "clockevent",
+};
+
+static DEFINE_PER_CPU(struct device, tick_percpu_dev);
+static struct tick_device *tick_get_tick_dev(struct device *dev);
+
+static ssize_t sysfs_show_current_tick_dev(struct device *dev,
+					   struct device_attribute *attr,
+					   char *buf)
+{
+	struct tick_device *td;
+	ssize_t count = 0;
+
+	raw_spin_lock_irq(&clockevents_lock);
+	td = tick_get_tick_dev(dev);
+	if (td && td->evtdev)
+		count = snprintf(buf, PAGE_SIZE, "%s\n", td->evtdev->name);
+	raw_spin_unlock_irq(&clockevents_lock);
+	return count;
+}
+static DEVICE_ATTR(current_device, 0444, sysfs_show_current_tick_dev, NULL);
+
+/* We don't support the abomination of removable broadcast devices */
+static ssize_t sysfs_unbind_tick_dev(struct device *dev,
+				     struct device_attribute *attr,
+				     const char *buf, size_t count)
+{
+	char name[CS_NAME_LEN];
+	size_t ret = sysfs_get_uname(buf, name, count);
+	struct clock_event_device *ce;
+
+	if (ret < 0)
+		return ret;
+
+	ret = -ENODEV;
+	mutex_lock(&clockevents_mutex);
+	raw_spin_lock_irq(&clockevents_lock);
+	list_for_each_entry(ce, &clockevent_devices, list) {
+		if (!strcmp(ce->name, name)) {
+			ret = __clockevents_try_unbind(ce, dev->id);
+			break;
+		}
+	}
+	raw_spin_unlock_irq(&clockevents_lock);
+	/*
+	 * We hold clockevents_mutex, so ce can't go away
+	 */
+	if (ret == -EAGAIN)
+		ret = clockevents_unbind(ce, dev->id);
+	mutex_unlock(&clockevents_mutex);
+	return ret ? ret : count;
+}
+static DEVICE_ATTR(unbind_device, 0200, NULL, sysfs_unbind_tick_dev);
+
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+static struct device tick_bc_dev = {
+	.init_name	= "broadcast",
+	.id		= 0,
+	.bus		= &clockevents_subsys,
+};
+
+static struct tick_device *tick_get_tick_dev(struct device *dev)
+{
+	return dev == &tick_bc_dev ? tick_get_broadcast_device() :
+		&per_cpu(tick_cpu_device, dev->id);
+}
+
+static __init int tick_broadcast_init_sysfs(void)
+{
+	int err = device_register(&tick_bc_dev);
+
+	if (!err)
+		err = device_create_file(&tick_bc_dev, &dev_attr_current_device);
+	return err;
+}
+#else
+static struct tick_device *tick_get_tick_dev(struct device *dev)
+{
+	return &per_cpu(tick_cpu_device, dev->id);
+}
+static inline int tick_broadcast_init_sysfs(void) { return 0; }
 #endif
+
+static int __init tick_init_sysfs(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct device *dev = &per_cpu(tick_percpu_dev, cpu);
+		int err;
+
+		dev->id = cpu;
+		dev->bus = &clockevents_subsys;
+		err = device_register(dev);
+		if (!err)
+			err = device_create_file(dev, &dev_attr_current_device);
+		if (!err)
+			err = device_create_file(dev, &dev_attr_unbind_device);
+		if (err)
+			return err;
+	}
+	return tick_broadcast_init_sysfs();
+}
+
+static int __init clockevents_init_sysfs(void)
+{
+	int err = subsys_system_register(&clockevents_subsys, NULL);
+
+	if (!err)
+		err = tick_init_sysfs();
+	return err;
+}
+device_initcall(clockevents_init_sysfs);
+#endif /* SYSFS */
+
+#endif /* GENERIC_CLOCK_EVENTS */
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index c9583382141a..e713ef7d19a7 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -31,6 +31,8 @@
 #include <linux/tick.h>
 #include <linux/kthread.h>
 
+#include "tick-internal.h"
+
 void timecounter_init(struct timecounter *tc,
 		      const struct cyclecounter *cc,
 		      u64 start_tstamp)
@@ -174,7 +176,7 @@ clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 maxsec)
 static struct clocksource *curr_clocksource;
 static LIST_HEAD(clocksource_list);
 static DEFINE_MUTEX(clocksource_mutex);
-static char override_name[32];
+static char override_name[CS_NAME_LEN];
 static int finished_booting;
 
 #ifdef CONFIG_CLOCKSOURCE_WATCHDOG
@@ -388,28 +390,17 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs)
 
 static void clocksource_dequeue_watchdog(struct clocksource *cs)
 {
-	struct clocksource *tmp;
 	unsigned long flags;
 
 	spin_lock_irqsave(&watchdog_lock, flags);
-	if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) {
-		/* cs is a watched clocksource. */
-		list_del_init(&cs->wd_list);
-	} else if (cs == watchdog) {
-		/* Reset watchdog cycles */
-		clocksource_reset_watchdog();
-		/* Current watchdog is removed. Find an alternative. */
-		watchdog = NULL;
-		list_for_each_entry(tmp, &clocksource_list, list) {
-			if (tmp == cs || tmp->flags & CLOCK_SOURCE_MUST_VERIFY)
-				continue;
-			if (!watchdog || tmp->rating > watchdog->rating)
-				watchdog = tmp;
+	if (cs != watchdog) {
+		if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) {
+			/* cs is a watched clocksource. */
+			list_del_init(&cs->wd_list);
+			/* Check if the watchdog timer needs to be stopped. */
+			clocksource_stop_watchdog();
 		}
 	}
-	cs->flags &= ~CLOCK_SOURCE_WATCHDOG;
-	/* Check if the watchdog timer needs to be stopped. */
-	clocksource_stop_watchdog();
 	spin_unlock_irqrestore(&watchdog_lock, flags);
 }
 
@@ -439,6 +430,11 @@ static int clocksource_watchdog_kthread(void *data)
 	return 0;
 }
 
+static bool clocksource_is_watchdog(struct clocksource *cs)
+{
+	return cs == watchdog;
+}
+
 #else /* CONFIG_CLOCKSOURCE_WATCHDOG */
 
 static void clocksource_enqueue_watchdog(struct clocksource *cs)
@@ -450,6 +446,7 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs)
 static inline void clocksource_dequeue_watchdog(struct clocksource *cs) { }
 static inline void clocksource_resume_watchdog(void) { }
 static inline int clocksource_watchdog_kthread(void *data) { return 0; }
+static bool clocksource_is_watchdog(struct clocksource *cs) { return false; }
 
 #endif /* CONFIG_CLOCKSOURCE_WATCHDOG */
 
@@ -553,24 +550,42 @@ static u64 clocksource_max_deferment(struct clocksource *cs)
 
 #ifndef CONFIG_ARCH_USES_GETTIMEOFFSET
 
-/**
- * clocksource_select - Select the best clocksource available
- *
- * Private function. Must hold clocksource_mutex when called.
- *
- * Select the clocksource with the best rating, or the clocksource,
- * which is selected by userspace override.
- */
-static void clocksource_select(void)
+static struct clocksource *clocksource_find_best(bool oneshot, bool skipcur)
 {
-	struct clocksource *best, *cs;
+	struct clocksource *cs;
 
 	if (!finished_booting || list_empty(&clocksource_list))
+		return NULL;
+
+	/*
+	 * We pick the clocksource with the highest rating. If oneshot
+	 * mode is active, we pick the highres valid clocksource with
+	 * the best rating.
+	 */
+	list_for_each_entry(cs, &clocksource_list, list) {
+		if (skipcur && cs == curr_clocksource)
+			continue;
+		if (oneshot && !(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES))
+			continue;
+		return cs;
+	}
+	return NULL;
+}
+
+static void __clocksource_select(bool skipcur)
+{
+	bool oneshot = tick_oneshot_mode_active();
+	struct clocksource *best, *cs;
+
+	/* Find the best suitable clocksource */
+	best = clocksource_find_best(oneshot, skipcur);
+	if (!best)
 		return;
-	/* First clocksource on the list has the best rating. */
-	best = list_first_entry(&clocksource_list, struct clocksource, list);
+
 	/* Check for the override clocksource. */
 	list_for_each_entry(cs, &clocksource_list, list) {
+		if (skipcur && cs == curr_clocksource)
+			continue;
 		if (strcmp(cs->name, override_name) != 0)
 			continue;
 		/*
@@ -578,8 +593,7 @@ static void clocksource_select(void)
 		 * capable clocksource if the tick code is in oneshot
 		 * mode (highres or nohz)
 		 */
-		if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) &&
-		    tick_oneshot_mode_active()) {
+		if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) && oneshot) {
 			/* Override clocksource cannot be used. */
 			printk(KERN_WARNING "Override clocksource %s is not "
 			       "HRT compatible. Cannot switch while in "
@@ -590,16 +604,35 @@ static void clocksource_select(void)
 			best = cs;
 		break;
 	}
-	if (curr_clocksource != best) {
-		printk(KERN_INFO "Switching to clocksource %s\n", best->name);
+
+	if (curr_clocksource != best && !timekeeping_notify(best)) {
+		pr_info("Switched to clocksource %s\n", best->name);
 		curr_clocksource = best;
-		timekeeping_notify(curr_clocksource);
 	}
 }
 
+/**
+ * clocksource_select - Select the best clocksource available
+ *
+ * Private function. Must hold clocksource_mutex when called.
+ *
+ * Select the clocksource with the best rating, or the clocksource,
+ * which is selected by userspace override.
+ */
+static void clocksource_select(void)
+{
+	return __clocksource_select(false);
+}
+
+static void clocksource_select_fallback(void)
+{
+	return __clocksource_select(true);
+}
+
 #else /* !CONFIG_ARCH_USES_GETTIMEOFFSET */
 
 static inline void clocksource_select(void) { }
+static inline void clocksource_select_fallback(void) { }
 
 #endif
 
@@ -772,17 +805,42 @@ void clocksource_change_rating(struct clocksource *cs, int rating)
 }
 EXPORT_SYMBOL(clocksource_change_rating);
 
+/*
+ * Unbind clocksource @cs. Called with clocksource_mutex held
+ */
+static int clocksource_unbind(struct clocksource *cs)
+{
+	/*
+	 * I really can't convince myself to support this on hardware
+	 * designed by lobotomized monkeys.
+	 */
+	if (clocksource_is_watchdog(cs))
+		return -EBUSY;
+
+	if (cs == curr_clocksource) {
+		/* Select and try to install a replacement clock source */
+		clocksource_select_fallback();
+		if (curr_clocksource == cs)
+			return -EBUSY;
+	}
+	clocksource_dequeue_watchdog(cs);
+	list_del_init(&cs->list);
+	return 0;
+}
+
 /**
  * clocksource_unregister - remove a registered clocksource
  * @cs:	clocksource to be unregistered
  */
-void clocksource_unregister(struct clocksource *cs)
+int clocksource_unregister(struct clocksource *cs)
 {
+	int ret = 0;
+
 	mutex_lock(&clocksource_mutex);
-	clocksource_dequeue_watchdog(cs);
-	list_del(&cs->list);
-	clocksource_select();
+	if (!list_empty(&cs->list))
+		ret = clocksource_unbind(cs);
 	mutex_unlock(&clocksource_mutex);
+	return ret;
 }
 EXPORT_SYMBOL(clocksource_unregister);
 
@@ -808,6 +866,23 @@ sysfs_show_current_clocksources(struct device *dev,
 	return count;
 }
 
+size_t sysfs_get_uname(const char *buf, char *dst, size_t cnt)
+{
+	size_t ret = cnt;
+
+	/* strings from sysfs write are not 0 terminated! */
+	if (!cnt || cnt >= CS_NAME_LEN)
+		return -EINVAL;
+
+	/* strip of \n: */
+	if (buf[cnt-1] == '\n')
+		cnt--;
+	if (cnt > 0)
+		memcpy(dst, buf, cnt);
+	dst[cnt] = 0;
+	return ret;
+}
+
 /**
  * sysfs_override_clocksource - interface for manually overriding clocksource
  * @dev:	unused
@@ -822,22 +897,13 @@ static ssize_t sysfs_override_clocksource(struct device *dev,
 					  struct device_attribute *attr,
 					  const char *buf, size_t count)
 {
-	size_t ret = count;
-
-	/* strings from sysfs write are not 0 terminated! */
-	if (count >= sizeof(override_name))
-		return -EINVAL;
-
-	/* strip of \n: */
-	if (buf[count-1] == '\n')
-		count--;
+	size_t ret;
 
 	mutex_lock(&clocksource_mutex);
 
-	if (count > 0)
-		memcpy(override_name, buf, count);
-	override_name[count] = 0;
-	clocksource_select();
+	ret = sysfs_get_uname(buf, override_name, count);
+	if (ret >= 0)
+		clocksource_select();
 
 	mutex_unlock(&clocksource_mutex);
 
@@ -845,6 +911,40 @@ static ssize_t sysfs_override_clocksource(struct device *dev,
 }
 
 /**
+ * sysfs_unbind_current_clocksource - interface for manually unbinding clocksource
+ * @dev:	unused
+ * @attr:	unused
+ * @buf:	unused
+ * @count:	length of buffer
+ *
+ * Takes input from sysfs interface for manually unbinding a clocksource.
+ */
+static ssize_t sysfs_unbind_clocksource(struct device *dev,
+					struct device_attribute *attr,
+					const char *buf, size_t count)
+{
+	struct clocksource *cs;
+	char name[CS_NAME_LEN];
+	size_t ret;
+
+	ret = sysfs_get_uname(buf, name, count);
+	if (ret < 0)
+		return ret;
+
+	ret = -ENODEV;
+	mutex_lock(&clocksource_mutex);
+	list_for_each_entry(cs, &clocksource_list, list) {
+		if (strcmp(cs->name, name))
+			continue;
+		ret = clocksource_unbind(cs);
+		break;
+	}
+	mutex_unlock(&clocksource_mutex);
+
+	return ret ? ret : count;
+}
+
+/**
  * sysfs_show_available_clocksources - sysfs interface for listing clocksource
  * @dev:	unused
  * @attr:	unused
@@ -886,6 +986,8 @@ sysfs_show_available_clocksources(struct device *dev,
 static DEVICE_ATTR(current_clocksource, 0644, sysfs_show_current_clocksources,
 		   sysfs_override_clocksource);
 
+static DEVICE_ATTR(unbind_clocksource, 0200, NULL, sysfs_unbind_clocksource);
+
 static DEVICE_ATTR(available_clocksource, 0444,
 		   sysfs_show_available_clocksources, NULL);
 
@@ -910,6 +1012,9 @@ static int __init init_clocksource_sysfs(void)
 				&device_clocksource,
 				&dev_attr_current_clocksource);
 	if (!error)
+		error = device_create_file(&device_clocksource,
+					   &dev_attr_unbind_clocksource);
+	if (!error)
 		error = device_create_file(
 				&device_clocksource,
 				&dev_attr_available_clocksource);
diff --git a/arch/arm/kernel/sched_clock.c b/kernel/time/sched_clock.c
index e8edcaa0e432..a326f27d7f09 100644
--- a/arch/arm/kernel/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -13,8 +13,7 @@
 #include <linux/sched.h>
 #include <linux/syscore_ops.h>
 #include <linux/timer.h>
-
-#include <asm/sched_clock.h>
+#include <linux/sched_clock.h>
 
 struct clock_data {
 	u64 epoch_ns;
@@ -24,7 +23,6 @@ struct clock_data {
 	u32 mult;
 	u32 shift;
 	bool suspended;
-	bool needs_suspend;
 };
 
 static void sched_clock_poll(unsigned long wrap_ticks);
@@ -51,10 +49,11 @@ static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift)
 	return (cyc * mult) >> shift;
 }
 
-static unsigned long long notrace cyc_to_sched_clock(u32 cyc, u32 mask)
+static unsigned long long notrace sched_clock_32(void)
 {
 	u64 epoch_ns;
 	u32 epoch_cyc;
+	u32 cyc;
 
 	if (cd.suspended)
 		return cd.epoch_ns;
@@ -73,7 +72,9 @@ static unsigned long long notrace cyc_to_sched_clock(u32 cyc, u32 mask)
 		smp_rmb();
 	} while (epoch_cyc != cd.epoch_cyc_copy);
 
-	return epoch_ns + cyc_to_ns((cyc - epoch_cyc) & mask, cd.mult, cd.shift);
+	cyc = read_sched_clock();
+	cyc = (cyc - epoch_cyc) & sched_clock_mask;
+	return epoch_ns + cyc_to_ns(cyc, cd.mult, cd.shift);
 }
 
 /*
@@ -165,12 +166,6 @@ void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate)
 	pr_debug("Registered %pF as sched_clock source\n", read);
 }
 
-static unsigned long long notrace sched_clock_32(void)
-{
-	u32 cyc = read_sched_clock();
-	return cyc_to_sched_clock(cyc, sched_clock_mask);
-}
-
 unsigned long long __read_mostly (*sched_clock_func)(void) = sched_clock_32;
 
 unsigned long long notrace sched_clock(void)
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 206bbfb34e09..d067c01586f5 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -19,6 +19,7 @@
 #include <linux/profile.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
+#include <linux/module.h>
 
 #include "tick-internal.h"
 
@@ -64,17 +65,34 @@ static void tick_broadcast_start_periodic(struct clock_event_device *bc)
 /*
  * Check, if the device can be utilized as broadcast device:
  */
-int tick_check_broadcast_device(struct clock_event_device *dev)
+static bool tick_check_broadcast_device(struct clock_event_device *curdev,
+					struct clock_event_device *newdev)
+{
+	if ((newdev->features & CLOCK_EVT_FEAT_DUMMY) ||
+	    (newdev->features & CLOCK_EVT_FEAT_C3STOP))
+		return false;
+
+	if (tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT &&
+	    !(newdev->features & CLOCK_EVT_FEAT_ONESHOT))
+		return false;
+
+	return !curdev || newdev->rating > curdev->rating;
+}
+
+/*
+ * Conditionally install/replace broadcast device
+ */
+void tick_install_broadcast_device(struct clock_event_device *dev)
 {
 	struct clock_event_device *cur = tick_broadcast_device.evtdev;
 
-	if ((dev->features & CLOCK_EVT_FEAT_DUMMY) ||
-	    (tick_broadcast_device.evtdev &&
-	     tick_broadcast_device.evtdev->rating >= dev->rating) ||
-	     (dev->features & CLOCK_EVT_FEAT_C3STOP))
-		return 0;
+	if (!tick_check_broadcast_device(cur, dev))
+		return;
+
+	if (!try_module_get(dev->owner))
+		return;
 
-	clockevents_exchange_device(tick_broadcast_device.evtdev, dev);
+	clockevents_exchange_device(cur, dev);
 	if (cur)
 		cur->event_handler = clockevents_handle_noop;
 	tick_broadcast_device.evtdev = dev;
@@ -90,7 +108,6 @@ int tick_check_broadcast_device(struct clock_event_device *dev)
 	 */
 	if (dev->features & CLOCK_EVT_FEAT_ONESHOT)
 		tick_clock_notify();
-	return 1;
 }
 
 /*
@@ -786,11 +803,11 @@ bool tick_broadcast_oneshot_available(void)
 
 void __init tick_broadcast_init(void)
 {
-	alloc_cpumask_var(&tick_broadcast_mask, GFP_NOWAIT);
-	alloc_cpumask_var(&tmpmask, GFP_NOWAIT);
+	zalloc_cpumask_var(&tick_broadcast_mask, GFP_NOWAIT);
+	zalloc_cpumask_var(&tmpmask, GFP_NOWAIT);
 #ifdef CONFIG_TICK_ONESHOT
-	alloc_cpumask_var(&tick_broadcast_oneshot_mask, GFP_NOWAIT);
-	alloc_cpumask_var(&tick_broadcast_pending_mask, GFP_NOWAIT);
-	alloc_cpumask_var(&tick_broadcast_force_mask, GFP_NOWAIT);
+	zalloc_cpumask_var(&tick_broadcast_oneshot_mask, GFP_NOWAIT);
+	zalloc_cpumask_var(&tick_broadcast_pending_mask, GFP_NOWAIT);
+	zalloc_cpumask_var(&tick_broadcast_force_mask, GFP_NOWAIT);
 #endif
 }
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 5d3fb100bc06..edd45f64162f 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -18,6 +18,7 @@
 #include <linux/percpu.h>
 #include <linux/profile.h>
 #include <linux/sched.h>
+#include <linux/module.h>
 
 #include <asm/irq_regs.h>
 
@@ -33,7 +34,6 @@ DEFINE_PER_CPU(struct tick_device, tick_cpu_device);
 ktime_t tick_next_period;
 ktime_t tick_period;
 int tick_do_timer_cpu __read_mostly = TICK_DO_TIMER_BOOT;
-static DEFINE_RAW_SPINLOCK(tick_device_lock);
 
 /*
  * Debugging: see timer_list.c
@@ -205,17 +205,75 @@ static void tick_setup_device(struct tick_device *td,
 		tick_setup_oneshot(newdev, handler, next_event);
 }
 
+void tick_install_replacement(struct clock_event_device *newdev)
+{
+	struct tick_device *td = &__get_cpu_var(tick_cpu_device);
+	int cpu = smp_processor_id();
+
+	clockevents_exchange_device(td->evtdev, newdev);
+	tick_setup_device(td, newdev, cpu, cpumask_of(cpu));
+	if (newdev->features & CLOCK_EVT_FEAT_ONESHOT)
+		tick_oneshot_notify();
+}
+
+static bool tick_check_percpu(struct clock_event_device *curdev,
+			      struct clock_event_device *newdev, int cpu)
+{
+	if (!cpumask_test_cpu(cpu, newdev->cpumask))
+		return false;
+	if (cpumask_equal(newdev->cpumask, cpumask_of(cpu)))
+		return true;
+	/* Check if irq affinity can be set */
+	if (newdev->irq >= 0 && !irq_can_set_affinity(newdev->irq))
+		return false;
+	/* Prefer an existing cpu local device */
+	if (curdev && cpumask_equal(curdev->cpumask, cpumask_of(cpu)))
+		return false;
+	return true;
+}
+
+static bool tick_check_preferred(struct clock_event_device *curdev,
+				 struct clock_event_device *newdev)
+{
+	/* Prefer oneshot capable device */
+	if (!(newdev->features & CLOCK_EVT_FEAT_ONESHOT)) {
+		if (curdev && (curdev->features & CLOCK_EVT_FEAT_ONESHOT))
+			return false;
+		if (tick_oneshot_mode_active())
+			return false;
+	}
+
+	/*
+	 * Use the higher rated one, but prefer a CPU local device with a lower
+	 * rating than a non-CPU local device
+	 */
+	return !curdev ||
+		newdev->rating > curdev->rating ||
+	       !cpumask_equal(curdev->cpumask, newdev->cpumask);
+}
+
+/*
+ * Check whether the new device is a better fit than curdev. curdev
+ * can be NULL !
+ */
+bool tick_check_replacement(struct clock_event_device *curdev,
+			    struct clock_event_device *newdev)
+{
+	if (tick_check_percpu(curdev, newdev, smp_processor_id()))
+		return false;
+
+	return tick_check_preferred(curdev, newdev);
+}
+
 /*
- * Check, if the new registered device should be used.
+ * Check, if the new registered device should be used. Called with
+ * clockevents_lock held and interrupts disabled.
  */
-static int tick_check_new_device(struct clock_event_device *newdev)
+void tick_check_new_device(struct clock_event_device *newdev)
 {
 	struct clock_event_device *curdev;
 	struct tick_device *td;
-	int cpu, ret = NOTIFY_OK;
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&tick_device_lock, flags);
+	int cpu;
 
 	cpu = smp_processor_id();
 	if (!cpumask_test_cpu(cpu, newdev->cpumask))
@@ -225,40 +283,15 @@ static int tick_check_new_device(struct clock_event_device *newdev)
 	curdev = td->evtdev;
 
 	/* cpu local device ? */
-	if (!cpumask_equal(newdev->cpumask, cpumask_of(cpu))) {
-
-		/*
-		 * If the cpu affinity of the device interrupt can not
-		 * be set, ignore it.
-		 */
-		if (!irq_can_set_affinity(newdev->irq))
-			goto out_bc;
+	if (!tick_check_percpu(curdev, newdev, cpu))
+		goto out_bc;
 
-		/*
-		 * If we have a cpu local device already, do not replace it
-		 * by a non cpu local device
-		 */
-		if (curdev && cpumask_equal(curdev->cpumask, cpumask_of(cpu)))
-			goto out_bc;
-	}
+	/* Preference decision */
+	if (!tick_check_preferred(curdev, newdev))
+		goto out_bc;
 
-	/*
-	 * If we have an active device, then check the rating and the oneshot
-	 * feature.
-	 */
-	if (curdev) {
-		/*
-		 * Prefer one shot capable devices !
-		 */
-		if ((curdev->features & CLOCK_EVT_FEAT_ONESHOT) &&
-		    !(newdev->features & CLOCK_EVT_FEAT_ONESHOT))
-			goto out_bc;
-		/*
-		 * Check the rating
-		 */
-		if (curdev->rating >= newdev->rating)
-			goto out_bc;
-	}
+	if (!try_module_get(newdev->owner))
+		return;
 
 	/*
 	 * Replace the eventually existing device by the new
@@ -273,20 +306,13 @@ static int tick_check_new_device(struct clock_event_device *newdev)
 	tick_setup_device(td, newdev, cpu, cpumask_of(cpu));
 	if (newdev->features & CLOCK_EVT_FEAT_ONESHOT)
 		tick_oneshot_notify();
-
-	raw_spin_unlock_irqrestore(&tick_device_lock, flags);
-	return NOTIFY_STOP;
+	return;
 
 out_bc:
 	/*
 	 * Can the new device be used as a broadcast device ?
 	 */
-	if (tick_check_broadcast_device(newdev))
-		ret = NOTIFY_STOP;
-
-	raw_spin_unlock_irqrestore(&tick_device_lock, flags);
-
-	return ret;
+	tick_install_broadcast_device(newdev);
 }
 
 /*
@@ -294,7 +320,7 @@ out_bc:
  *
  * Called with interrupts disabled.
  */
-static void tick_handover_do_timer(int *cpup)
+void tick_handover_do_timer(int *cpup)
 {
 	if (*cpup == tick_do_timer_cpu) {
 		int cpu = cpumask_first(cpu_online_mask);
@@ -311,13 +337,11 @@ static void tick_handover_do_timer(int *cpup)
  * access the hardware device itself.
  * We just set the mode and remove it from the lists.
  */
-static void tick_shutdown(unsigned int *cpup)
+void tick_shutdown(unsigned int *cpup)
 {
 	struct tick_device *td = &per_cpu(tick_cpu_device, *cpup);
 	struct clock_event_device *dev = td->evtdev;
-	unsigned long flags;
 
-	raw_spin_lock_irqsave(&tick_device_lock, flags);
 	td->mode = TICKDEV_MODE_PERIODIC;
 	if (dev) {
 		/*
@@ -329,26 +353,20 @@ static void tick_shutdown(unsigned int *cpup)
 		dev->event_handler = clockevents_handle_noop;
 		td->evtdev = NULL;
 	}
-	raw_spin_unlock_irqrestore(&tick_device_lock, flags);
 }
 
-static void tick_suspend(void)
+void tick_suspend(void)
 {
 	struct tick_device *td = &__get_cpu_var(tick_cpu_device);
-	unsigned long flags;
 
-	raw_spin_lock_irqsave(&tick_device_lock, flags);
 	clockevents_shutdown(td->evtdev);
-	raw_spin_unlock_irqrestore(&tick_device_lock, flags);
 }
 
-static void tick_resume(void)
+void tick_resume(void)
 {
 	struct tick_device *td = &__get_cpu_var(tick_cpu_device);
-	unsigned long flags;
 	int broadcast = tick_resume_broadcast();
 
-	raw_spin_lock_irqsave(&tick_device_lock, flags);
 	clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_RESUME);
 
 	if (!broadcast) {
@@ -357,68 +375,12 @@ static void tick_resume(void)
 		else
 			tick_resume_oneshot();
 	}
-	raw_spin_unlock_irqrestore(&tick_device_lock, flags);
 }
 
-/*
- * Notification about clock event devices
- */
-static int tick_notify(struct notifier_block *nb, unsigned long reason,
-			       void *dev)
-{
-	switch (reason) {
-
-	case CLOCK_EVT_NOTIFY_ADD:
-		return tick_check_new_device(dev);
-
-	case CLOCK_EVT_NOTIFY_BROADCAST_ON:
-	case CLOCK_EVT_NOTIFY_BROADCAST_OFF:
-	case CLOCK_EVT_NOTIFY_BROADCAST_FORCE:
-		tick_broadcast_on_off(reason, dev);
-		break;
-
-	case CLOCK_EVT_NOTIFY_BROADCAST_ENTER:
-	case CLOCK_EVT_NOTIFY_BROADCAST_EXIT:
-		tick_broadcast_oneshot_control(reason);
-		break;
-
-	case CLOCK_EVT_NOTIFY_CPU_DYING:
-		tick_handover_do_timer(dev);
-		break;
-
-	case CLOCK_EVT_NOTIFY_CPU_DEAD:
-		tick_shutdown_broadcast_oneshot(dev);
-		tick_shutdown_broadcast(dev);
-		tick_shutdown(dev);
-		break;
-
-	case CLOCK_EVT_NOTIFY_SUSPEND:
-		tick_suspend();
-		tick_suspend_broadcast();
-		break;
-
-	case CLOCK_EVT_NOTIFY_RESUME:
-		tick_resume();
-		break;
-
-	default:
-		break;
-	}
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block tick_notifier = {
-	.notifier_call = tick_notify,
-};
-
 /**
  * tick_init - initialize the tick control
- *
- * Register the notifier with the clockevents framework
  */
 void __init tick_init(void)
 {
-	clockevents_register_notifier(&tick_notifier);
 	tick_broadcast_init();
 }
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index f0299eae4602..bc906cad709b 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -6,6 +6,8 @@
 
 extern seqlock_t jiffies_lock;
 
+#define CS_NAME_LEN	32
+
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BUILD
 
 #define TICK_DO_TIMER_NONE	-1
@@ -18,9 +20,19 @@ extern int tick_do_timer_cpu __read_mostly;
 
 extern void tick_setup_periodic(struct clock_event_device *dev, int broadcast);
 extern void tick_handle_periodic(struct clock_event_device *dev);
+extern void tick_check_new_device(struct clock_event_device *dev);
+extern void tick_handover_do_timer(int *cpup);
+extern void tick_shutdown(unsigned int *cpup);
+extern void tick_suspend(void);
+extern void tick_resume(void);
+extern bool tick_check_replacement(struct clock_event_device *curdev,
+				   struct clock_event_device *newdev);
+extern void tick_install_replacement(struct clock_event_device *dev);
 
 extern void clockevents_shutdown(struct clock_event_device *dev);
 
+extern size_t sysfs_get_uname(const char *buf, char *dst, size_t cnt);
+
 /*
  * NO_HZ / high resolution timer shared code
  */
@@ -90,7 +102,7 @@ static inline bool tick_broadcast_oneshot_available(void) { return false; }
  */
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 extern int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu);
-extern int tick_check_broadcast_device(struct clock_event_device *dev);
+extern void tick_install_broadcast_device(struct clock_event_device *dev);
 extern int tick_is_broadcast_device(struct clock_event_device *dev);
 extern void tick_broadcast_on_off(unsigned long reason, int *oncpu);
 extern void tick_shutdown_broadcast(unsigned int *cpup);
@@ -102,9 +114,8 @@ tick_set_periodic_handler(struct clock_event_device *dev, int broadcast);
 
 #else /* !BROADCAST */
 
-static inline int tick_check_broadcast_device(struct clock_event_device *dev)
+static inline void tick_install_broadcast_device(struct clock_event_device *dev)
 {
-	return 0;
 }
 
 static inline int tick_is_broadcast_device(struct clock_event_device *dev)
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index bc67d4245e1d..f4208138fbf4 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -717,6 +717,7 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
 	if (unlikely(!cpu_online(cpu))) {
 		if (cpu == tick_do_timer_cpu)
 			tick_do_timer_cpu = TICK_DO_TIMER_NONE;
+		return false;
 	}
 
 	if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
@@ -1168,7 +1169,7 @@ void tick_cancel_sched_timer(int cpu)
 		hrtimer_cancel(&ts->sched_timer);
 # endif
 
-	ts->nohz_mode = NOHZ_MODE_INACTIVE;
+	memset(ts, 0, sizeof(*ts));
 }
 #endif
 
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 98cd470bbe49..838fc0777b68 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -25,6 +25,7 @@
 
 #include "tick-internal.h"
 #include "ntp_internal.h"
+#include "timekeeping_internal.h"
 
 static struct timekeeper timekeeper;
 static DEFINE_RAW_SPINLOCK(timekeeper_lock);
@@ -627,11 +628,20 @@ static int change_clocksource(void *data)
 	write_seqcount_begin(&timekeeper_seq);
 
 	timekeeping_forward_now(tk);
-	if (!new->enable || new->enable(new) == 0) {
-		old = tk->clock;
-		tk_setup_internals(tk, new);
-		if (old->disable)
-			old->disable(old);
+	/*
+	 * If the cs is in module, get a module reference. Succeeds
+	 * for built-in code (owner == NULL) as well.
+	 */
+	if (try_module_get(new->owner)) {
+		if (!new->enable || new->enable(new) == 0) {
+			old = tk->clock;
+			tk_setup_internals(tk, new);
+			if (old->disable)
+				old->disable(old);
+			module_put(old->owner);
+		} else {
+			module_put(new->owner);
+		}
 	}
 	timekeeping_update(tk, true, true);
 
@@ -648,14 +658,15 @@ static int change_clocksource(void *data)
  * This function is called from clocksource.c after a new, better clock
  * source has been registered. The caller holds the clocksource_mutex.
  */
-void timekeeping_notify(struct clocksource *clock)
+int timekeeping_notify(struct clocksource *clock)
 {
 	struct timekeeper *tk = &timekeeper;
 
 	if (tk->clock == clock)
-		return;
+		return 0;
 	stop_machine(change_clocksource, clock, NULL);
 	tick_clock_notify();
+	return tk->clock == clock ? 0 : -1;
 }
 
 /**
@@ -841,6 +852,7 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk,
 	tk_xtime_add(tk, delta);
 	tk_set_wall_to_mono(tk, timespec_sub(tk->wall_to_monotonic, *delta));
 	tk_set_sleep_time(tk, timespec_add(tk->total_sleep_time, *delta));
+	tk_debug_account_sleep_time(delta);
 }
 
 /**
diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c
new file mode 100644
index 000000000000..802433a4f5eb
--- /dev/null
+++ b/kernel/time/timekeeping_debug.c
@@ -0,0 +1,72 @@
+/*
+ * debugfs file to track time spent in suspend
+ *
+ * Copyright (c) 2011, Google, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/debugfs.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/seq_file.h>
+#include <linux/time.h>
+
+static unsigned int sleep_time_bin[32] = {0};
+
+static int tk_debug_show_sleep_time(struct seq_file *s, void *data)
+{
+	unsigned int bin;
+	seq_puts(s, "      time (secs)        count\n");
+	seq_puts(s, "------------------------------\n");
+	for (bin = 0; bin < 32; bin++) {
+		if (sleep_time_bin[bin] == 0)
+			continue;
+		seq_printf(s, "%10u - %-10u %4u\n",
+			bin ? 1 << (bin - 1) : 0, 1 << bin,
+				sleep_time_bin[bin]);
+	}
+	return 0;
+}
+
+static int tk_debug_sleep_time_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, tk_debug_show_sleep_time, NULL);
+}
+
+static const struct file_operations tk_debug_sleep_time_fops = {
+	.open		= tk_debug_sleep_time_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int __init tk_debug_sleep_time_init(void)
+{
+	struct dentry *d;
+
+	d = debugfs_create_file("sleep_time", 0444, NULL, NULL,
+		&tk_debug_sleep_time_fops);
+	if (!d) {
+		pr_err("Failed to create sleep_time debug file\n");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+late_initcall(tk_debug_sleep_time_init);
+
+void tk_debug_account_sleep_time(struct timespec *t)
+{
+	sleep_time_bin[fls(t->tv_sec)]++;
+}
+
diff --git a/kernel/time/timekeeping_internal.h b/kernel/time/timekeeping_internal.h
new file mode 100644
index 000000000000..13323ea08ffa
--- /dev/null
+++ b/kernel/time/timekeeping_internal.h
@@ -0,0 +1,14 @@
+#ifndef _TIMEKEEPING_INTERNAL_H
+#define _TIMEKEEPING_INTERNAL_H
+/*
+ * timekeeping debug functions
+ */
+#include <linux/time.h>
+
+#ifdef CONFIG_DEBUG_FS
+extern void tk_debug_account_sleep_time(struct timespec *t);
+#else
+#define tk_debug_account_sleep_time(x)
+#endif
+
+#endif /* _TIMEKEEPING_INTERNAL_H */
diff --git a/kernel/timer.c b/kernel/timer.c
index a860bba34412..15ffdb3f1948 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1539,12 +1539,12 @@ static int __cpuinit init_timers_cpu(int cpu)
 			boot_done = 1;
 			base = &boot_tvec_bases;
 		}
+		spin_lock_init(&base->lock);
 		tvec_base_done[cpu] = 1;
 	} else {
 		base = per_cpu(tvec_bases, cpu);
 	}
 
-	spin_lock_init(&base->lock);
 
 	for (j = 0; j < TVN_SIZE; j++) {
 		INIT_LIST_HEAD(base->tv5.vec + j);
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index a6361178de5a..e1b653f7e1ca 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -750,7 +750,11 @@ static int filter_set_pred(struct event_filter *filter,
 
 static void __free_preds(struct event_filter *filter)
 {
+	int i;
+
 	if (filter->preds) {
+		for (i = 0; i < filter->n_preds; i++)
+			kfree(filter->preds[i].ops);
 		kfree(filter->preds);
 		filter->preds = NULL;
 	}
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 636d45fe69b3..9f46e98ba8f2 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -35,7 +35,7 @@ struct trace_probe {
 	const char		*symbol;	/* symbol name */
 	struct ftrace_event_class	class;
 	struct ftrace_event_call	call;
-	struct ftrace_event_file	**files;
+	struct ftrace_event_file * __rcu *files;
 	ssize_t			size;		/* trace entry size */
 	unsigned int		nr_args;
 	struct probe_arg	args[];
@@ -185,9 +185,14 @@ static struct trace_probe *find_trace_probe(const char *event,
 
 static int trace_probe_nr_files(struct trace_probe *tp)
 {
-	struct ftrace_event_file **file = tp->files;
+	struct ftrace_event_file **file;
 	int ret = 0;
 
+	/*
+	 * Since all tp->files updater is protected by probe_enable_lock,
+	 * we don't need to lock an rcu_read_lock.
+	 */
+	file = rcu_dereference_raw(tp->files);
 	if (file)
 		while (*(file++))
 			ret++;
@@ -209,9 +214,10 @@ enable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
 	mutex_lock(&probe_enable_lock);
 
 	if (file) {
-		struct ftrace_event_file **new, **old = tp->files;
+		struct ftrace_event_file **new, **old;
 		int n = trace_probe_nr_files(tp);
 
+		old = rcu_dereference_raw(tp->files);
 		/* 1 is for new one and 1 is for stopper */
 		new = kzalloc((n + 2) * sizeof(struct ftrace_event_file *),
 			      GFP_KERNEL);
@@ -251,11 +257,17 @@ enable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
 static int
 trace_probe_file_index(struct trace_probe *tp, struct ftrace_event_file *file)
 {
+	struct ftrace_event_file **files;
 	int i;
 
-	if (tp->files) {
-		for (i = 0; tp->files[i]; i++)
-			if (tp->files[i] == file)
+	/*
+	 * Since all tp->files updater is protected by probe_enable_lock,
+	 * we don't need to lock an rcu_read_lock.
+	 */
+	files = rcu_dereference_raw(tp->files);
+	if (files) {
+		for (i = 0; files[i]; i++)
+			if (files[i] == file)
 				return i;
 	}
 
@@ -274,10 +286,11 @@ disable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
 	mutex_lock(&probe_enable_lock);
 
 	if (file) {
-		struct ftrace_event_file **new, **old = tp->files;
+		struct ftrace_event_file **new, **old;
 		int n = trace_probe_nr_files(tp);
 		int i, j;
 
+		old = rcu_dereference_raw(tp->files);
 		if (n == 0 || trace_probe_file_index(tp, file) < 0) {
 			ret = -EINVAL;
 			goto out_unlock;
@@ -872,9 +885,16 @@ __kprobe_trace_func(struct trace_probe *tp, struct pt_regs *regs,
 static __kprobes void
 kprobe_trace_func(struct trace_probe *tp, struct pt_regs *regs)
 {
-	struct ftrace_event_file **file = tp->files;
+	/*
+	 * Note: preempt is already disabled around the kprobe handler.
+	 * However, we still need an smp_read_barrier_depends() corresponding
+	 * to smp_wmb() in rcu_assign_pointer() to access the pointer.
+	 */
+	struct ftrace_event_file **file = rcu_dereference_raw(tp->files);
+
+	if (unlikely(!file))
+		return;
 
-	/* Note: preempt is already disabled around the kprobe handler */
 	while (*file) {
 		__kprobe_trace_func(tp, regs, *file);
 		file++;
@@ -925,9 +945,16 @@ static __kprobes void
 kretprobe_trace_func(struct trace_probe *tp, struct kretprobe_instance *ri,
 		     struct pt_regs *regs)
 {
-	struct ftrace_event_file **file = tp->files;
+	/*
+	 * Note: preempt is already disabled around the kprobe handler.
+	 * However, we still need an smp_read_barrier_depends() corresponding
+	 * to smp_wmb() in rcu_assign_pointer() to access the pointer.
+	 */
+	struct ftrace_event_file **file = rcu_dereference_raw(tp->files);
+
+	if (unlikely(!file))
+		return;
 
-	/* Note: preempt is already disabled around the kprobe handler */
 	while (*file) {
 		__kretprobe_trace_func(tp, ri, regs, *file);
 		file++;
@@ -935,7 +962,7 @@ kretprobe_trace_func(struct trace_probe *tp, struct kretprobe_instance *ri,
 }
 
 /* Event entry printers */
-enum print_line_t
+static enum print_line_t
 print_kprobe_event(struct trace_iterator *iter, int flags,
 		   struct trace_event *event)
 {
@@ -971,7 +998,7 @@ partial:
 	return TRACE_TYPE_PARTIAL_LINE;
 }
 
-enum print_line_t
+static enum print_line_t
 print_kretprobe_event(struct trace_iterator *iter, int flags,
 		      struct trace_event *event)
 {
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 4aa9f5bc6b2d..1ae602809efb 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -4311,6 +4311,12 @@ bool current_is_workqueue_rescuer(void)
  * no synchronization around this function and the test result is
  * unreliable and only useful as advisory hints or for debugging.
  *
+ * If @cpu is WORK_CPU_UNBOUND, the test is performed on the local CPU.
+ * Note that both per-cpu and unbound workqueues may be associated with
+ * multiple pool_workqueues which have separate congested states.  A
+ * workqueue being congested on one CPU doesn't mean the workqueue is also
+ * contested on other CPUs / NUMA nodes.
+ *
  * RETURNS:
  * %true if congested, %false otherwise.
  */
@@ -4321,6 +4327,9 @@ bool workqueue_congested(int cpu, struct workqueue_struct *wq)
 
 	rcu_read_lock_sched();
 
+	if (cpu == WORK_CPU_UNBOUND)
+		cpu = smp_processor_id();
+
 	if (!(wq->flags & WQ_UNBOUND))
 		pwq = per_cpu_ptr(wq->cpu_pwqs, cpu);
 	else
diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index 8e15d966d9b0..239992021b1d 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -837,6 +837,19 @@ bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv,
 
 	dat_entry = batadv_dat_entry_hash_find(bat_priv, ip_dst);
 	if (dat_entry) {
+		/* If the ARP request is destined for a local client the local
+		 * client will answer itself. DAT would only generate a
+		 * duplicate packet.
+		 *
+		 * Moreover, if the soft-interface is enslaved into a bridge, an
+		 * additional DAT answer may trigger kernel warnings about
+		 * a packet coming from the wrong port.
+		 */
+		if (batadv_is_my_client(bat_priv, dat_entry->mac_addr)) {
+			ret = true;
+			goto out;
+		}
+
 		skb_new = arp_create(ARPOP_REPLY, ETH_P_ARP, ip_src,
 				     bat_priv->soft_iface, ip_dst, hw_src,
 				     dat_entry->mac_addr, hw_src);
diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index 3e30a0f1b908..1240f07ad31d 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -163,14 +163,22 @@ void batadv_mesh_free(struct net_device *soft_iface)
 	batadv_vis_quit(bat_priv);
 
 	batadv_gw_node_purge(bat_priv);
-	batadv_originator_free(bat_priv);
 	batadv_nc_free(bat_priv);
+	batadv_dat_free(bat_priv);
+	batadv_bla_free(bat_priv);
 
+	/* Free the TT and the originator tables only after having terminated
+	 * all the other depending components which may use these structures for
+	 * their purposes.
+	 */
 	batadv_tt_free(bat_priv);
 
-	batadv_bla_free(bat_priv);
-
-	batadv_dat_free(bat_priv);
+	/* Since the originator table clean up routine is accessing the TT
+	 * tables as well, it has to be invoked after the TT tables have been
+	 * freed and marked as empty. This ensures that no cleanup RCU callbacks
+	 * accessing the TT data are scheduled for later execution.
+	 */
+	batadv_originator_free(bat_priv);
 
 	free_percpu(bat_priv->bat_counters);
 
@@ -475,7 +483,7 @@ static int batadv_param_set_ra(const char *val, const struct kernel_param *kp)
 	char *algo_name = (char *)val;
 	size_t name_len = strlen(algo_name);
 
-	if (algo_name[name_len - 1] == '\n')
+	if (name_len > 0 && algo_name[name_len - 1] == '\n')
 		algo_name[name_len - 1] = '\0';
 
 	bat_algo_ops = batadv_algo_get(algo_name);
diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c
index f7c54305a918..e84629ece9b7 100644
--- a/net/batman-adv/network-coding.c
+++ b/net/batman-adv/network-coding.c
@@ -1514,6 +1514,7 @@ batadv_nc_skb_decode_packet(struct batadv_priv *bat_priv, struct sk_buff *skb,
 	struct ethhdr *ethhdr, ethhdr_tmp;
 	uint8_t *orig_dest, ttl, ttvn;
 	unsigned int coding_len;
+	int err;
 
 	/* Save headers temporarily */
 	memcpy(&coded_packet_tmp, skb->data, sizeof(coded_packet_tmp));
@@ -1568,8 +1569,11 @@ batadv_nc_skb_decode_packet(struct batadv_priv *bat_priv, struct sk_buff *skb,
 			 coding_len);
 
 	/* Resize decoded skb if decoded with larger packet */
-	if (nc_packet->skb->len > coding_len + h_size)
-		pskb_trim_rcsum(skb, coding_len + h_size);
+	if (nc_packet->skb->len > coding_len + h_size) {
+		err = pskb_trim_rcsum(skb, coding_len + h_size);
+		if (err)
+			return NULL;
+	}
 
 	/* Create decoded unicast packet */
 	unicast_packet = (struct batadv_unicast_packet *)skb->data;
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index a3395fdfbd4f..d5953b87918c 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -1204,6 +1204,7 @@ void ceph_osdc_unregister_linger_request(struct ceph_osd_client *osdc,
 	mutex_lock(&osdc->request_mutex);
 	if (req->r_linger) {
 		__unregister_linger_request(osdc, req);
+		req->r_linger = 0;
 		ceph_osdc_put_request(req);
 	}
 	mutex_unlock(&osdc->request_mutex);
@@ -2120,7 +2121,9 @@ int ceph_osdc_start_request(struct ceph_osd_client *osdc,
 	down_read(&osdc->map_sem);
 	mutex_lock(&osdc->request_mutex);
 	__register_request(osdc, req);
-	WARN_ON(req->r_sent);
+	req->r_sent = 0;
+	req->r_got_reply = 0;
+	req->r_completed = 0;
 	rc = __map_request(osdc, req, 0);
 	if (rc < 0) {
 		if (nofail) {
diff --git a/net/core/sock.c b/net/core/sock.c
index d4f4cea726e7..6ba327da79e1 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1217,18 +1217,6 @@ static void sock_copy(struct sock *nsk, const struct sock *osk)
 #endif
 }
 
-/*
- * caches using SLAB_DESTROY_BY_RCU should let .next pointer from nulls nodes
- * un-modified. Special care is taken when initializing object to zero.
- */
-static inline void sk_prot_clear_nulls(struct sock *sk, int size)
-{
-	if (offsetof(struct sock, sk_node.next) != 0)
-		memset(sk, 0, offsetof(struct sock, sk_node.next));
-	memset(&sk->sk_node.pprev, 0,
-	       size - offsetof(struct sock, sk_node.pprev));
-}
-
 void sk_prot_clear_portaddr_nulls(struct sock *sk, int size)
 {
 	unsigned long nulls1, nulls2;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 147abf5275aa..4bcabf3ab4ca 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -84,7 +84,7 @@ int sysctl_ip_default_ttl __read_mostly = IPDEFTTL;
 EXPORT_SYMBOL(sysctl_ip_default_ttl);
 
 /* Generate a checksum for an outgoing IP datagram. */
-__inline__ void ip_send_check(struct iphdr *iph)
+void ip_send_check(struct iphdr *iph)
 {
 	iph->check = 0;
 	iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index d3ddd8400354..ecd60733e5e2 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1081,6 +1081,7 @@ static int ip6gre_tunnel_ioctl(struct net_device *dev,
 		}
 		if (t == NULL)
 			t = netdev_priv(dev);
+		memset(&p, 0, sizeof(p));
 		ip6gre_tnl_parm_to_user(&p, &t->parms);
 		if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
 			err = -EFAULT;
@@ -1128,6 +1129,7 @@ static int ip6gre_tunnel_ioctl(struct net_device *dev,
 		if (t) {
 			err = 0;
 
+			memset(&p, 0, sizeof(p));
 			ip6gre_tnl_parm_to_user(&p, &t->parms);
 			if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
 				err = -EFAULT;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 71167069b394..0a17ed9eaf39 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1890,6 +1890,17 @@ void tcp6_proc_exit(struct net *net)
 }
 #endif
 
+static void tcp_v6_clear_sk(struct sock *sk, int size)
+{
+	struct inet_sock *inet = inet_sk(sk);
+
+	/* we do not want to clear pinet6 field, because of RCU lookups */
+	sk_prot_clear_nulls(sk, offsetof(struct inet_sock, pinet6));
+
+	size -= offsetof(struct inet_sock, pinet6) + sizeof(inet->pinet6);
+	memset(&inet->pinet6 + 1, 0, size);
+}
+
 struct proto tcpv6_prot = {
 	.name			= "TCPv6",
 	.owner			= THIS_MODULE,
@@ -1933,6 +1944,7 @@ struct proto tcpv6_prot = {
 #ifdef CONFIG_MEMCG_KMEM
 	.proto_cgroup		= tcp_proto_cgroup,
 #endif
+	.clear_sk		= tcp_v6_clear_sk,
 };
 
 static const struct inet6_protocol tcpv6_protocol = {
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index d4defdd44937..42923b14dfa6 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1432,6 +1432,17 @@ void udp6_proc_exit(struct net *net) {
 }
 #endif /* CONFIG_PROC_FS */
 
+void udp_v6_clear_sk(struct sock *sk, int size)
+{
+	struct inet_sock *inet = inet_sk(sk);
+
+	/* we do not want to clear pinet6 field, because of RCU lookups */
+	sk_prot_clear_portaddr_nulls(sk, offsetof(struct inet_sock, pinet6));
+
+	size -= offsetof(struct inet_sock, pinet6) + sizeof(inet->pinet6);
+	memset(&inet->pinet6 + 1, 0, size);
+}
+
 /* ------------------------------------------------------------------------ */
 
 struct proto udpv6_prot = {
@@ -1462,7 +1473,7 @@ struct proto udpv6_prot = {
 	.compat_setsockopt = compat_udpv6_setsockopt,
 	.compat_getsockopt = compat_udpv6_getsockopt,
 #endif
-	.clear_sk	   = sk_prot_clear_portaddr_nulls,
+	.clear_sk	   = udp_v6_clear_sk,
 };
 
 static struct inet_protosw udpv6_protosw = {
diff --git a/net/ipv6/udp_impl.h b/net/ipv6/udp_impl.h
index d7571046bfc4..4691ed50a928 100644
--- a/net/ipv6/udp_impl.h
+++ b/net/ipv6/udp_impl.h
@@ -31,6 +31,8 @@ extern int	udpv6_recvmsg(struct kiocb *iocb, struct sock *sk,
 extern int	udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb);
 extern void	udpv6_destroy_sock(struct sock *sk);
 
+extern void udp_v6_clear_sk(struct sock *sk, int size);
+
 #ifdef CONFIG_PROC_FS
 extern int	udp6_seq_show(struct seq_file *seq, void *v);
 #endif
diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c
index 1d08e21d9f69..dfcc4be46898 100644
--- a/net/ipv6/udplite.c
+++ b/net/ipv6/udplite.c
@@ -56,7 +56,7 @@ struct proto udplitev6_prot = {
 	.compat_setsockopt = compat_udpv6_setsockopt,
 	.compat_getsockopt = compat_udpv6_getsockopt,
 #endif
-	.clear_sk	   = sk_prot_clear_portaddr_nulls,
+	.clear_sk	   = udp_v6_clear_sk,
 };
 
 static struct inet_protosw udplite6_protosw = {
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 4ef7bdb65440..23ed03d786c8 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -103,8 +103,10 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 	dev_hold(dev);
 
 	xdst->u.rt6.rt6i_idev = in6_dev_get(dev);
-	if (!xdst->u.rt6.rt6i_idev)
+	if (!xdst->u.rt6.rt6i_idev) {
+		dev_put(dev);
 		return -ENODEV;
+	}
 
 	rt6_transfer_peer(&xdst->u.rt6, rt);