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

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>;
+};

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.

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

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

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'

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

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>
 

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 */
 

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>

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

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>
 

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();
 }

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>
 

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"

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>

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>

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>

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"
 

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>

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"

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>
 

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>
 

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>
 

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>

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>
 

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.

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>

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;

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;
 }

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

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

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

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);

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

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 */
 

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();

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

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

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,

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)

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 */

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,

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))

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;

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)

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);

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

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

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

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

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

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)
 /*

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);
 }
 
 /*

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);

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;

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();
 }

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 */

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);

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();
 }

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)

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)

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;
 
 }
 

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,

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);
 }

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

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

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;
+	}
+}

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);
 

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)
 {

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 */

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 */

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

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);
 }
 

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

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;
 }
 

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 = {

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/

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)

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)

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;
+}

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 = {

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

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
 

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

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);

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;
 }

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;
 }

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;
 

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);
 }
 
 

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;
 }
 
 /*

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);

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;
 }
 
 /*

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;

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 = {

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.

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

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

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
 

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);