Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (163 commits)
  tracing: Fix compile issue for trace_sched_wakeup.c
  [S390] hardirq: remove pointless header file includes
  [IA64] Move local_softirq_pending() definition
  perf, powerpc: Fix power_pmu_event_init to not use event->ctx
  ftrace: Remove recursion between recordmcount and scripts/mod/empty
  jump_label: Add COND_STMT(), reducer wrappery
  perf: Optimize sw events
  perf: Use jump_labels to optimize the scheduler hooks
  jump_label: Add atomic_t interface
  jump_label: Use more consistent naming
  perf, hw_breakpoint: Fix crash in hw_breakpoint creation
  perf: Find task before event alloc
  perf: Fix task refcount bugs
  perf: Fix group moving
  irq_work: Add generic hardirq context callbacks
  perf_events: Fix transaction recovery in group_sched_in()
  perf_events: Fix bogus AMD64 generic TLB events
  perf_events: Fix bogus context time tracking
  tracing: Remove parent recording in latency tracer graph options
  tracing: Use one prologue for the preempt irqs off tracer function tracers
  ...

Documentation/kprobes.txt

@@ -542,9 +542,11 @@ Kprobes does not use mutexes or allocate memory except during
 registration and unregistration.
 
 Probe handlers are run with preemption disabled.  Depending on the
-architecture, handlers may also run with interrupts disabled.  In any
+architecture and optimization state, handlers may also run with
-case, your handler should not yield the CPU (e.g., by attempting to
+interrupts disabled (e.g., kretprobe handlers and optimized kprobe
-acquire a semaphore).
+handlers run without interrupt disabled on x86/x86-64).  In any case,
+your handler should not yield the CPU (e.g., by attempting to acquire
+a semaphore).
 
 Since a return probe is implemented by replacing the return
 address with the trampoline's address, stack backtraces and calls

Makefile

@@ -568,6 +568,12 @@ endif
 
 ifdef CONFIG_FUNCTION_TRACER
 KBUILD_CFLAGS	+= -pg
+ifdef CONFIG_DYNAMIC_FTRACE
+	ifdef CONFIG_HAVE_C_RECORDMCOUNT
+		BUILD_C_RECORDMCOUNT := y
+		export BUILD_C_RECORDMCOUNT
+	endif
+endif
 endif
 
 # We trigger additional mismatches with less inlining
@@ -591,6 +597,11 @@ KBUILD_CFLAGS	+= $(call cc-option,-fno-strict-overflow)
 # conserve stack if available
 KBUILD_CFLAGS   += $(call cc-option,-fconserve-stack)
 
+# check for 'asm goto'
+ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC)), y)
+	KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO
+endif
+
 # Add user supplied CPPFLAGS, AFLAGS and CFLAGS as the last assignments
 # But warn user when we do so
 warn-assign = \

arch/Kconfig

@@ -158,4 +158,7 @@ config HAVE_PERF_EVENTS_NMI
 	  subsystem.  Also has support for calculating CPU cycle events
 	  to determine how many clock cycles in a given period.
 
+config HAVE_ARCH_JUMP_LABEL
+	bool
+
 source "kernel/gcov/Kconfig"

arch/alpha/Kconfig

@@ -9,6 +9,7 @@ config ALPHA
 	select HAVE_IDE
 	select HAVE_OPROFILE
 	select HAVE_SYSCALL_WRAPPERS
+	select HAVE_IRQ_WORK
 	select HAVE_PERF_EVENTS
 	select HAVE_DMA_ATTRS
 	help

arch/alpha/include/asm/perf_event.h

@@ -1,11 +1,6 @@
 #ifndef __ASM_ALPHA_PERF_EVENT_H
 #define __ASM_ALPHA_PERF_EVENT_H
 
-/* Alpha only supports software events through this interface. */
-extern void set_perf_event_pending(void);
-
-#define PERF_EVENT_INDEX_OFFSET 0
-
 #ifdef CONFIG_PERF_EVENTS
 extern void init_hw_perf_events(void);
 #else

arch/alpha/kernel/perf_event.c

@@ -307,7 +307,7 @@ again:
 			     new_raw_count) != prev_raw_count)
 		goto again;
 
-	delta = (new_raw_count  - (prev_raw_count & alpha_pmu->pmc_count_mask[idx])) + ovf;
+	delta = (new_raw_count - (prev_raw_count & alpha_pmu->pmc_count_mask[idx])) + ovf;
 
 	/* It is possible on very rare occasions that the PMC has overflowed
 	 * but the interrupt is yet to come.  Detect and fix this situation.
@@ -402,14 +402,13 @@ static void maybe_change_configuration(struct cpu_hw_events *cpuc)
 		struct hw_perf_event *hwc = &pe->hw;
 		int idx = hwc->idx;
 
-		if (cpuc->current_idx[j] != PMC_NO_INDEX) {
+		if (cpuc->current_idx[j] == PMC_NO_INDEX) {
-			cpuc->idx_mask |= (1<<cpuc->current_idx[j]);
+			alpha_perf_event_set_period(pe, hwc, idx);
-			continue;
+			cpuc->current_idx[j] = idx;
 		}
 
-		alpha_perf_event_set_period(pe, hwc, idx);
+		if (!(hwc->state & PERF_HES_STOPPED))
-		cpuc->current_idx[j] = idx;
+			cpuc->idx_mask |= (1<<cpuc->current_idx[j]);
-		cpuc->idx_mask |= (1<<cpuc->current_idx[j]);
 	}
 	cpuc->config = cpuc->event[0]->hw.config_base;
 }
@@ -420,12 +419,13 @@ static void maybe_change_configuration(struct cpu_hw_events *cpuc)
  *  - this function is called from outside this module via the pmu struct
  *    returned from perf event initialisation.
  */
-static int alpha_pmu_enable(struct perf_event *event)
+static int alpha_pmu_add(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
 	int n0;
 	int ret;
-	unsigned long flags;
+	unsigned long irq_flags;
 
 	/*
 	 * The Sparc code has the IRQ disable first followed by the perf
@@ -435,8 +435,8 @@ static int alpha_pmu_enable(struct perf_event *event)
 	 * nevertheless we disable the PMCs first to enable a potential
 	 * final PMI to occur before we disable interrupts.
 	 */
-	perf_disable();
+	perf_pmu_disable(event->pmu);
-	local_irq_save(flags);
+	local_irq_save(irq_flags);
 
 	/* Default to error to be returned */
 	ret = -EAGAIN;
@@ -455,8 +455,12 @@ static int alpha_pmu_enable(struct perf_event *event)
 		}
 	}
 
-	local_irq_restore(flags);
+	hwc->state = PERF_HES_UPTODATE;
-	perf_enable();
+	if (!(flags & PERF_EF_START))
+		hwc->state |= PERF_HES_STOPPED;
+
+	local_irq_restore(irq_flags);
+	perf_pmu_enable(event->pmu);
 
 	return ret;
 }
@@ -467,15 +471,15 @@ static int alpha_pmu_enable(struct perf_event *event)
  *  - this function is called from outside this module via the pmu struct
  *    returned from perf event initialisation.
  */
-static void alpha_pmu_disable(struct perf_event *event)
+static void alpha_pmu_del(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
-	unsigned long flags;
+	unsigned long irq_flags;
 	int j;
 
-	perf_disable();
+	perf_pmu_disable(event->pmu);
-	local_irq_save(flags);
+	local_irq_save(irq_flags);
 
 	for (j = 0; j < cpuc->n_events; j++) {
 		if (event == cpuc->event[j]) {
@@ -501,8 +505,8 @@ static void alpha_pmu_disable(struct perf_event *event)
 		}
 	}
 
-	local_irq_restore(flags);
+	local_irq_restore(irq_flags);
-	perf_enable();
+	perf_pmu_enable(event->pmu);
 }
 
 
@@ -514,13 +518,44 @@ static void alpha_pmu_read(struct perf_event *event)
 }
 
 
-static void alpha_pmu_unthrottle(struct perf_event *event)
+static void alpha_pmu_stop(struct perf_event *event, int flags)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
+	if (!(hwc->state & PERF_HES_STOPPED)) {
+		cpuc->idx_mask &= ~(1UL<<hwc->idx);
+		hwc->state |= PERF_HES_STOPPED;
+	}
+
+	if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
+		alpha_perf_event_update(event, hwc, hwc->idx, 0);
+		hwc->state |= PERF_HES_UPTODATE;
+	}
+
+	if (cpuc->enabled)
+		wrperfmon(PERFMON_CMD_DISABLE, (1UL<<hwc->idx));
+}
+
+
+static void alpha_pmu_start(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED)))
+		return;
+
+	if (flags & PERF_EF_RELOAD) {
+		WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
+		alpha_perf_event_set_period(event, hwc, hwc->idx);
+	}
+
+	hwc->state = 0;
+
 	cpuc->idx_mask |= 1UL<<hwc->idx;
-	wrperfmon(PERFMON_CMD_ENABLE, (1UL<<hwc->idx));
+	if (cpuc->enabled)
+		wrperfmon(PERFMON_CMD_ENABLE, (1UL<<hwc->idx));
 }
 
 
@@ -642,39 +677,36 @@ static int __hw_perf_event_init(struct perf_event *event)
 	return 0;
 }
 
-static const struct pmu pmu = {
-	.enable		= alpha_pmu_enable,
-	.disable	= alpha_pmu_disable,
-	.read		= alpha_pmu_read,
-	.unthrottle	= alpha_pmu_unthrottle,
-};
-
-
 /*
  * Main entry point to initialise a HW performance event.
  */
-const struct pmu *hw_perf_event_init(struct perf_event *event)
+static int alpha_pmu_event_init(struct perf_event *event)
 {
 	int err;
 
+	switch (event->attr.type) {
+	case PERF_TYPE_RAW:
+	case PERF_TYPE_HARDWARE:
+	case PERF_TYPE_HW_CACHE:
+		break;
+
+	default:
+		return -ENOENT;
+	}
+
 	if (!alpha_pmu)
-		return ERR_PTR(-ENODEV);
+		return -ENODEV;
 
 	/* Do the real initialisation work. */
 	err = __hw_perf_event_init(event);
 
-	if (err)
+	return err;
-		return ERR_PTR(err);
-
-	return &pmu;
 }
 
-
-
 /*
  * Main entry point - enable HW performance counters.
  */
-void hw_perf_enable(void)
+static void alpha_pmu_enable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
@@ -700,7 +732,7 @@ void hw_perf_enable(void)
  * Main entry point - disable HW performance counters.
  */
 
-void hw_perf_disable(void)
+static void alpha_pmu_disable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
@@ -713,6 +745,17 @@ void hw_perf_disable(void)
 	wrperfmon(PERFMON_CMD_DISABLE, cpuc->idx_mask);
 }
 
+static struct pmu pmu = {
+	.pmu_enable	= alpha_pmu_enable,
+	.pmu_disable	= alpha_pmu_disable,
+	.event_init	= alpha_pmu_event_init,
+	.add		= alpha_pmu_add,
+	.del		= alpha_pmu_del,
+	.start		= alpha_pmu_start,
+	.stop		= alpha_pmu_stop,
+	.read		= alpha_pmu_read,
+};
+
 
 /*
  * Main entry point - don't know when this is called but it
@@ -766,7 +809,7 @@ static void alpha_perf_event_irq_handler(unsigned long la_ptr,
 	wrperfmon(PERFMON_CMD_DISABLE, cpuc->idx_mask);
 
 	/* la_ptr is the counter that overflowed. */
-	if (unlikely(la_ptr >= perf_max_events)) {
+	if (unlikely(la_ptr >= alpha_pmu->num_pmcs)) {
 		/* This should never occur! */
 		irq_err_count++;
 		pr_warning("PMI: silly index %ld\n", la_ptr);
@@ -807,7 +850,7 @@ static void alpha_perf_event_irq_handler(unsigned long la_ptr,
 			/* Interrupts coming too quickly; "throttle" the
 			 * counter, i.e., disable it for a little while.
 			 */
-			cpuc->idx_mask &= ~(1UL<<idx);
+			alpha_pmu_stop(event, 0);
 		}
 	}
 	wrperfmon(PERFMON_CMD_ENABLE, cpuc->idx_mask);
@@ -837,6 +880,7 @@ void __init init_hw_perf_events(void)
 
 	/* And set up PMU specification */
 	alpha_pmu = &ev67_pmu;
-	perf_max_events = alpha_pmu->num_pmcs;
+
+	perf_pmu_register(&pmu);
 }
 

arch/alpha/kernel/time.c

@@ -41,7 +41,7 @@
 #include <linux/init.h>
 #include <linux/bcd.h>
 #include <linux/profile.h>
-#include <linux/perf_event.h>
+#include <linux/irq_work.h>
 
 #include <asm/uaccess.h>
 #include <asm/io.h>
@@ -83,25 +83,25 @@ static struct {
 
 unsigned long est_cycle_freq;
 
-#ifdef CONFIG_PERF_EVENTS
+#ifdef CONFIG_IRQ_WORK
 
-DEFINE_PER_CPU(u8, perf_event_pending);
+DEFINE_PER_CPU(u8, irq_work_pending);
 
-#define set_perf_event_pending_flag()  __get_cpu_var(perf_event_pending) = 1
+#define set_irq_work_pending_flag()  __get_cpu_var(irq_work_pending) = 1
-#define test_perf_event_pending()      __get_cpu_var(perf_event_pending)
+#define test_irq_work_pending()      __get_cpu_var(irq_work_pending)
-#define clear_perf_event_pending()     __get_cpu_var(perf_event_pending) = 0
+#define clear_irq_work_pending()     __get_cpu_var(irq_work_pending) = 0
 
-void set_perf_event_pending(void)
+void set_irq_work_pending(void)
 {
-	set_perf_event_pending_flag();
+	set_irq_work_pending_flag();
 }
 
-#else  /* CONFIG_PERF_EVENTS */
+#else  /* CONFIG_IRQ_WORK */
 
-#define test_perf_event_pending()      0
+#define test_irq_work_pending()      0
-#define clear_perf_event_pending()
+#define clear_irq_work_pending()
 
-#endif /* CONFIG_PERF_EVENTS */
+#endif /* CONFIG_IRQ_WORK */
 
 
 static inline __u32 rpcc(void)
@@ -191,9 +191,9 @@ irqreturn_t timer_interrupt(int irq, void *dev)
 
 	write_sequnlock(&xtime_lock);
 
-	if (test_perf_event_pending()) {
+	if (test_irq_work_pending()) {
-		clear_perf_event_pending();
+		clear_irq_work_pending();
-		perf_event_do_pending();
+		irq_work_run();
 	}
 
 #ifndef CONFIG_SMP

arch/arm/Kconfig

@@ -23,6 +23,7 @@ config ARM
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZO
 	select HAVE_KERNEL_LZMA
+	select HAVE_IRQ_WORK
 	select HAVE_PERF_EVENTS
 	select PERF_USE_VMALLOC
 	select HAVE_REGS_AND_STACK_ACCESS_API

arch/arm/include/asm/perf_event.h

@@ -12,18 +12,6 @@
 #ifndef __ARM_PERF_EVENT_H__
 #define __ARM_PERF_EVENT_H__
 
-/*
- * NOP: on *most* (read: all supported) ARM platforms, the performance
- * counter interrupts are regular interrupts and not an NMI. This
- * means that when we receive the interrupt we can call
- * perf_event_do_pending() that handles all of the work with
- * interrupts disabled.
- */
-static inline void
-set_perf_event_pending(void)
-{
-}
-
 /* ARM performance counters start from 1 (in the cp15 accesses) so use the
  * same indexes here for consistency. */
 #define PERF_EVENT_INDEX_OFFSET 1

arch/arm/kernel/perf_event.c

@@ -123,6 +123,12 @@ armpmu_get_max_events(void)
 }
 EXPORT_SYMBOL_GPL(armpmu_get_max_events);
 
+int perf_num_counters(void)
+{
+	return armpmu_get_max_events();
+}
+EXPORT_SYMBOL_GPL(perf_num_counters);
+
 #define HW_OP_UNSUPPORTED		0xFFFF
 
 #define C(_x) \
@@ -220,27 +226,6 @@ again:
 	return new_raw_count;
 }
 
-static void
-armpmu_disable(struct perf_event *event)
-{
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-	struct hw_perf_event *hwc = &event->hw;
-	int idx = hwc->idx;
-
-	WARN_ON(idx < 0);
-
-	clear_bit(idx, cpuc->active_mask);
-	armpmu->disable(hwc, idx);
-
-	barrier();
-
-	armpmu_event_update(event, hwc, idx);
-	cpuc->events[idx] = NULL;
-	clear_bit(idx, cpuc->used_mask);
-
-	perf_event_update_userpage(event);
-}
-
 static void
 armpmu_read(struct perf_event *event)
 {
@@ -254,13 +239,44 @@ armpmu_read(struct perf_event *event)
 }
 
 static void
-armpmu_unthrottle(struct perf_event *event)
+armpmu_stop(struct perf_event *event, int flags)
 {
 	struct hw_perf_event *hwc = &event->hw;
 
+	if (!armpmu)
+		return;
+
+	/*
+	 * ARM pmu always has to update the counter, so ignore
+	 * PERF_EF_UPDATE, see comments in armpmu_start().
+	 */
+	if (!(hwc->state & PERF_HES_STOPPED)) {
+		armpmu->disable(hwc, hwc->idx);
+		barrier(); /* why? */
+		armpmu_event_update(event, hwc, hwc->idx);
+		hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
+	}
+}
+
+static void
+armpmu_start(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (!armpmu)
+		return;
+
+	/*
+	 * ARM pmu always has to reprogram the period, so ignore
+	 * PERF_EF_RELOAD, see the comment below.
+	 */
+	if (flags & PERF_EF_RELOAD)
+		WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
+
+	hwc->state = 0;
 	/*
 	 * Set the period again. Some counters can't be stopped, so when we
-	 * were throttled we simply disabled the IRQ source and the counter
+	 * were stopped we simply disabled the IRQ source and the counter
 	 * may have been left counting. If we don't do this step then we may
 	 * get an interrupt too soon or *way* too late if the overflow has
 	 * happened since disabling.
@@ -269,14 +285,33 @@ armpmu_unthrottle(struct perf_event *event)
 	armpmu->enable(hwc, hwc->idx);
 }
 
+static void
+armpmu_del(struct perf_event *event, int flags)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+
+	WARN_ON(idx < 0);
+
+	clear_bit(idx, cpuc->active_mask);
+	armpmu_stop(event, PERF_EF_UPDATE);
+	cpuc->events[idx] = NULL;
+	clear_bit(idx, cpuc->used_mask);
+
+	perf_event_update_userpage(event);
+}
+
 static int
-armpmu_enable(struct perf_event *event)
+armpmu_add(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx;
 	int err = 0;
 
+	perf_pmu_disable(event->pmu);
+
 	/* If we don't have a space for the counter then finish early. */
 	idx = armpmu->get_event_idx(cpuc, hwc);
 	if (idx < 0) {
@@ -293,25 +328,19 @@ armpmu_enable(struct perf_event *event)
 	cpuc->events[idx] = event;
 	set_bit(idx, cpuc->active_mask);
 
-	/* Set the period for the event. */
+	hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
-	armpmu_event_set_period(event, hwc, idx);
+	if (flags & PERF_EF_START)
-
+		armpmu_start(event, PERF_EF_RELOAD);
-	/* Enable the event. */
-	armpmu->enable(hwc, idx);
 
 	/* Propagate our changes to the userspace mapping. */
 	perf_event_update_userpage(event);
 
 out:
+	perf_pmu_enable(event->pmu);
 	return err;
 }
 
-static struct pmu pmu = {
+static struct pmu pmu;
-	.enable	    = armpmu_enable,
-	.disable    = armpmu_disable,
-	.unthrottle = armpmu_unthrottle,
-	.read	    = armpmu_read,
-};
 
 static int
 validate_event(struct cpu_hw_events *cpuc,
@@ -491,20 +520,29 @@ __hw_perf_event_init(struct perf_event *event)
 	return err;
 }
 
-const struct pmu *
+static int armpmu_event_init(struct perf_event *event)
-hw_perf_event_init(struct perf_event *event)
 {
 	int err = 0;
 
+	switch (event->attr.type) {
+	case PERF_TYPE_RAW:
+	case PERF_TYPE_HARDWARE:
+	case PERF_TYPE_HW_CACHE:
+		break;
+
+	default:
+		return -ENOENT;
+	}
+
 	if (!armpmu)
-		return ERR_PTR(-ENODEV);
+		return -ENODEV;
 
 	event->destroy = hw_perf_event_destroy;
 
 	if (!atomic_inc_not_zero(&active_events)) {
-		if (atomic_read(&active_events) > perf_max_events) {
+		if (atomic_read(&active_events) > armpmu->num_events) {
 			atomic_dec(&active_events);
-			return ERR_PTR(-ENOSPC);
+			return -ENOSPC;
 		}
 
 		mutex_lock(&pmu_reserve_mutex);
@@ -518,17 +556,16 @@ hw_perf_event_init(struct perf_event *event)
 	}
 
 	if (err)
-		return ERR_PTR(err);
+		return err;
 
 	err = __hw_perf_event_init(event);
 	if (err)
 		hw_perf_event_destroy(event);
 
-	return err ? ERR_PTR(err) : &pmu;
+	return err;
 }
 
-void
+static void armpmu_enable(struct pmu *pmu)
-hw_perf_enable(void)
 {
 	/* Enable all of the perf events on hardware. */
 	int idx;
@@ -549,13 +586,23 @@ hw_perf_enable(void)
 	armpmu->start();
 }
 
-void
+static void armpmu_disable(struct pmu *pmu)
-hw_perf_disable(void)
 {
 	if (armpmu)
 		armpmu->stop();
 }
 
+static struct pmu pmu = {
+	.pmu_enable	= armpmu_enable,
+	.pmu_disable	= armpmu_disable,
+	.event_init	= armpmu_event_init,
+	.add		= armpmu_add,
+	.del		= armpmu_del,
+	.start		= armpmu_start,
+	.stop		= armpmu_stop,
+	.read		= armpmu_read,
+};
+
 /*
  * ARMv6 Performance counter handling code.
  *
@@ -1045,7 +1092,7 @@ armv6pmu_handle_irq(int irq_num,
 	 * platforms that can have the PMU interrupts raised as an NMI, this
 	 * will not work.
 	 */
-	perf_event_do_pending();
+	irq_work_run();
 
 	return IRQ_HANDLED;
 }
@@ -2021,7 +2068,7 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
 	 * platforms that can have the PMU interrupts raised as an NMI, this
 	 * will not work.
 	 */
-	perf_event_do_pending();
+	irq_work_run();
 
 	return IRQ_HANDLED;
 }
@@ -2389,7 +2436,7 @@ xscale1pmu_handle_irq(int irq_num, void *dev)
 			armpmu->disable(hwc, idx);
 	}
 
-	perf_event_do_pending();
+	irq_work_run();
 
 	/*
 	 * Re-enable the PMU.
@@ -2716,7 +2763,7 @@ xscale2pmu_handle_irq(int irq_num, void *dev)
 			armpmu->disable(hwc, idx);
 	}
 
-	perf_event_do_pending();
+	irq_work_run();
 
 	/*
 	 * Re-enable the PMU.
@@ -2933,14 +2980,12 @@ init_hw_perf_events(void)
 			armpmu = &armv6pmu;
 			memcpy(armpmu_perf_cache_map, armv6_perf_cache_map,
 					sizeof(armv6_perf_cache_map));
-			perf_max_events	= armv6pmu.num_events;
 			break;
 		case 0xB020:	/* ARM11mpcore */
 			armpmu = &armv6mpcore_pmu;
 			memcpy(armpmu_perf_cache_map,
 			       armv6mpcore_perf_cache_map,
 			       sizeof(armv6mpcore_perf_cache_map));
-			perf_max_events = armv6mpcore_pmu.num_events;
 			break;
 		case 0xC080:	/* Cortex-A8 */
 			armv7pmu.id = ARM_PERF_PMU_ID_CA8;
@@ -2952,7 +2997,6 @@ init_hw_perf_events(void)
 			/* Reset PMNC and read the nb of CNTx counters
 			    supported */
 			armv7pmu.num_events = armv7_reset_read_pmnc();
-			perf_max_events = armv7pmu.num_events;
 			break;
 		case 0xC090:	/* Cortex-A9 */
 			armv7pmu.id = ARM_PERF_PMU_ID_CA9;
@@ -2964,7 +3008,6 @@ init_hw_perf_events(void)
 			/* Reset PMNC and read the nb of CNTx counters
 			    supported */
 			armv7pmu.num_events = armv7_reset_read_pmnc();
-			perf_max_events = armv7pmu.num_events;
 			break;
 		}
 	/* Intel CPUs [xscale]. */
@@ -2975,13 +3018,11 @@ init_hw_perf_events(void)
 			armpmu = &xscale1pmu;
 			memcpy(armpmu_perf_cache_map, xscale_perf_cache_map,
 					sizeof(xscale_perf_cache_map));
-			perf_max_events	= xscale1pmu.num_events;
 			break;
 		case 2:
 			armpmu = &xscale2pmu;
 			memcpy(armpmu_perf_cache_map, xscale_perf_cache_map,
 					sizeof(xscale_perf_cache_map));
-			perf_max_events	= xscale2pmu.num_events;
 			break;
 		}
 	}
@@ -2991,9 +3032,10 @@ init_hw_perf_events(void)
 				arm_pmu_names[armpmu->id], armpmu->num_events);
 	} else {
 		pr_info("no hardware support available\n");
-		perf_max_events = -1;
 	}
 
+	perf_pmu_register(&pmu);
+
 	return 0;
 }
 arch_initcall(init_hw_perf_events);
@@ -3001,13 +3043,6 @@ arch_initcall(init_hw_perf_events);
 /*
  * Callchain handling code.
  */
-static inline void
-callchain_store(struct perf_callchain_entry *entry,
-		u64 ip)
-{
-	if (entry->nr < PERF_MAX_STACK_DEPTH)
-		entry->ip[entry->nr++] = ip;
-}
 
 /*
  * The registers we're interested in are at the end of the variable
@@ -3039,7 +3074,7 @@ user_backtrace(struct frame_tail *tail,
 	if (__copy_from_user_inatomic(&buftail, tail, sizeof(buftail)))
 		return NULL;
 
-	callchain_store(entry, buftail.lr);
+	perf_callchain_store(entry, buftail.lr);
 
 	/*
 	 * Frame pointers should strictly progress back up the stack
@@ -3051,16 +3086,11 @@ user_backtrace(struct frame_tail *tail,
 	return buftail.fp - 1;
 }
 
-static void
+void
-perf_callchain_user(struct pt_regs *regs,
+perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
-		    struct perf_callchain_entry *entry)
 {
 	struct frame_tail *tail;
 
-	callchain_store(entry, PERF_CONTEXT_USER);
-
-	if (!user_mode(regs))
-		regs = task_pt_regs(current);
 
 	tail = (struct frame_tail *)regs->ARM_fp - 1;
 
@@ -3078,56 +3108,18 @@ callchain_trace(struct stackframe *fr,
 		void *data)
 {
 	struct perf_callchain_entry *entry = data;
-	callchain_store(entry, fr->pc);
+	perf_callchain_store(entry, fr->pc);
 	return 0;
 }
 
-static void
+void
-perf_callchain_kernel(struct pt_regs *regs,
+perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
-		      struct perf_callchain_entry *entry)
 {
 	struct stackframe fr;
 
-	callchain_store(entry, PERF_CONTEXT_KERNEL);
 	fr.fp = regs->ARM_fp;
 	fr.sp = regs->ARM_sp;
 	fr.lr = regs->ARM_lr;
 	fr.pc = regs->ARM_pc;
 	walk_stackframe(&fr, callchain_trace, entry);
 }
-
-static void
-perf_do_callchain(struct pt_regs *regs,
-		  struct perf_callchain_entry *entry)
-{
-	int is_user;
-
-	if (!regs)
-		return;
-
-	is_user = user_mode(regs);
-
-	if (!current || !current->pid)
-		return;
-
-	if (is_user && current->state != TASK_RUNNING)
-		return;
-
-	if (!is_user)
-		perf_callchain_kernel(regs, entry);
-
-	if (current->mm)
-		perf_callchain_user(regs, entry);
-}
-
-static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_irq_entry);
-
-struct perf_callchain_entry *
-perf_callchain(struct pt_regs *regs)
-{
-	struct perf_callchain_entry *entry = &__get_cpu_var(pmc_irq_entry);
-
-	entry->nr = 0;
-	perf_do_callchain(regs, entry);
-	return entry;
-}

arch/arm/oprofile/Makefile

@@ -6,4 +6,8 @@ DRIVER_OBJS = $(addprefix ../../../drivers/oprofile/, \
 		oprofilefs.o oprofile_stats.o \
 		timer_int.o )
 
+ifeq ($(CONFIG_HW_PERF_EVENTS),y)
+DRIVER_OBJS += $(addprefix ../../../drivers/oprofile/, oprofile_perf.o)
+endif
+
 oprofile-y				:= $(DRIVER_OBJS) common.o

arch/arm/oprofile/common.c

@@ -25,139 +25,10 @@
 #include <asm/ptrace.h>
 
 #ifdef CONFIG_HW_PERF_EVENTS
-/*
+char *op_name_from_perf_id(void)
- * Per performance monitor configuration as set via oprofilefs.
- */
-struct op_counter_config {
-	unsigned long count;
-	unsigned long enabled;
-	unsigned long event;
-	unsigned long unit_mask;
-	unsigned long kernel;
-	unsigned long user;
-	struct perf_event_attr attr;
-};
-
-static int op_arm_enabled;
-static DEFINE_MUTEX(op_arm_mutex);
-
-static struct op_counter_config *counter_config;
-static struct perf_event **perf_events[nr_cpumask_bits];
-static int perf_num_counters;
-
-/*
- * Overflow callback for oprofile.
- */
-static void op_overflow_handler(struct perf_event *event, int unused,
-			struct perf_sample_data *data, struct pt_regs *regs)
 {
-	int id;
+	enum arm_perf_pmu_ids id = armpmu_get_pmu_id();
-	u32 cpu = smp_processor_id();
 
-	for (id = 0; id < perf_num_counters; ++id)
-		if (perf_events[cpu][id] == event)
-			break;
-
-	if (id != perf_num_counters)
-		oprofile_add_sample(regs, id);
-	else
-		pr_warning("oprofile: ignoring spurious overflow "
-				"on cpu %u\n", cpu);
-}
-
-/*
- * Called by op_arm_setup to create perf attributes to mirror the oprofile
- * settings in counter_config. Attributes are created as `pinned' events and
- * so are permanently scheduled on the PMU.
- */
-static void op_perf_setup(void)
-{
-	int i;
-	u32 size = sizeof(struct perf_event_attr);
-	struct perf_event_attr *attr;
-
-	for (i = 0; i < perf_num_counters; ++i) {
-		attr = &counter_config[i].attr;
-		memset(attr, 0, size);
-		attr->type		= PERF_TYPE_RAW;
-		attr->size		= size;
-		attr->config		= counter_config[i].event;
-		attr->sample_period	= counter_config[i].count;
-		attr->pinned		= 1;
-	}
-}
-
-static int op_create_counter(int cpu, int event)
-{
-	int ret = 0;
-	struct perf_event *pevent;
-
-	if (!counter_config[event].enabled || (perf_events[cpu][event] != NULL))
-		return ret;
-
-	pevent = perf_event_create_kernel_counter(&counter_config[event].attr,
-						  cpu, -1,
-						  op_overflow_handler);
-
-	if (IS_ERR(pevent)) {
-		ret = PTR_ERR(pevent);
-	} else if (pevent->state != PERF_EVENT_STATE_ACTIVE) {
-		perf_event_release_kernel(pevent);
-		pr_warning("oprofile: failed to enable event %d "
-				"on CPU %d\n", event, cpu);
-		ret = -EBUSY;
-	} else {
-		perf_events[cpu][event] = pevent;
-	}
-
-	return ret;
-}
-
-static void op_destroy_counter(int cpu, int event)
-{
-	struct perf_event *pevent = perf_events[cpu][event];
-
-	if (pevent) {
-		perf_event_release_kernel(pevent);
-		perf_events[cpu][event] = NULL;
-	}
-}
-
-/*
- * Called by op_arm_start to create active perf events based on the
- * perviously configured attributes.
- */
-static int op_perf_start(void)
-{
-	int cpu, event, ret = 0;
-
-	for_each_online_cpu(cpu) {
-		for (event = 0; event < perf_num_counters; ++event) {
-			ret = op_create_counter(cpu, event);
-			if (ret)
-				goto out;
-		}
-	}
-
-out:
-	return ret;
-}
-
-/*
- * Called by op_arm_stop at the end of a profiling run.
- */
-static void op_perf_stop(void)
-{
-	int cpu, event;
-
-	for_each_online_cpu(cpu)
-		for (event = 0; event < perf_num_counters; ++event)
-			op_destroy_counter(cpu, event);
-}
-
-
-static char *op_name_from_perf_id(enum arm_perf_pmu_ids id)
-{
 	switch (id) {
 	case ARM_PERF_PMU_ID_XSCALE1:
 		return "arm/xscale1";
@@ -176,116 +47,6 @@ static char *op_name_from_perf_id(enum arm_perf_pmu_ids id)
 	}
 }
 
-static int op_arm_create_files(struct super_block *sb, struct dentry *root)
-{
-	unsigned int i;
-
-	for (i = 0; i < perf_num_counters; i++) {
-		struct dentry *dir;
-		char buf[4];
-
-		snprintf(buf, sizeof buf, "%d", i);
-		dir = oprofilefs_mkdir(sb, root, buf);
-		oprofilefs_create_ulong(sb, dir, "enabled", &counter_config[i].enabled);
-		oprofilefs_create_ulong(sb, dir, "event", &counter_config[i].event);
-		oprofilefs_create_ulong(sb, dir, "count", &counter_config[i].count);
-		oprofilefs_create_ulong(sb, dir, "unit_mask", &counter_config[i].unit_mask);
-		oprofilefs_create_ulong(sb, dir, "kernel", &counter_config[i].kernel);
-		oprofilefs_create_ulong(sb, dir, "user", &counter_config[i].user);
-	}
-
-	return 0;
-}
-
-static int op_arm_setup(void)
-{
-	spin_lock(&oprofilefs_lock);
-	op_perf_setup();
-	spin_unlock(&oprofilefs_lock);
-	return 0;
-}
-
-static int op_arm_start(void)
-{
-	int ret = -EBUSY;
-
-	mutex_lock(&op_arm_mutex);
-	if (!op_arm_enabled) {
-		ret = 0;
-		op_perf_start();
-		op_arm_enabled = 1;
-	}
-	mutex_unlock(&op_arm_mutex);
-	return ret;
-}
-
-static void op_arm_stop(void)
-{
-	mutex_lock(&op_arm_mutex);
-	if (op_arm_enabled)
-		op_perf_stop();
-	op_arm_enabled = 0;
-	mutex_unlock(&op_arm_mutex);
-}
-
-#ifdef CONFIG_PM
-static int op_arm_suspend(struct platform_device *dev, pm_message_t state)
-{
-	mutex_lock(&op_arm_mutex);
-	if (op_arm_enabled)
-		op_perf_stop();
-	mutex_unlock(&op_arm_mutex);
-	return 0;
-}
-
-static int op_arm_resume(struct platform_device *dev)
-{
-	mutex_lock(&op_arm_mutex);
-	if (op_arm_enabled && op_perf_start())
-		op_arm_enabled = 0;
-	mutex_unlock(&op_arm_mutex);
-	return 0;
-}
-
-static struct platform_driver oprofile_driver = {
-	.driver		= {
-		.name		= "arm-oprofile",
-	},
-	.resume		= op_arm_resume,
-	.suspend	= op_arm_suspend,
-};
-
-static struct platform_device *oprofile_pdev;
-
-static int __init init_driverfs(void)
-{
-	int ret;
-
-	ret = platform_driver_register(&oprofile_driver);
-	if (ret)
-		goto out;
-
-	oprofile_pdev =	platform_device_register_simple(
-				oprofile_driver.driver.name, 0, NULL, 0);
-	if (IS_ERR(oprofile_pdev)) {
-		ret = PTR_ERR(oprofile_pdev);
-		platform_driver_unregister(&oprofile_driver);
-	}
-
-out:
-	return ret;
-}
-
-static void  exit_driverfs(void)
-{
-	platform_device_unregister(oprofile_pdev);
-	platform_driver_unregister(&oprofile_driver);
-}
-#else
-static int __init init_driverfs(void) { return 0; }
-#define exit_driverfs() do { } while (0)
-#endif /* CONFIG_PM */
-
 static int report_trace(struct stackframe *frame, void *d)
 {
 	unsigned int *depth = d;
@@ -350,74 +111,14 @@ static void arm_backtrace(struct pt_regs * const regs, unsigned int depth)
 
 int __init oprofile_arch_init(struct oprofile_operations *ops)
 {
-	int cpu, ret = 0;
-
-	perf_num_counters = armpmu_get_max_events();
-
-	counter_config = kcalloc(perf_num_counters,
-			sizeof(struct op_counter_config), GFP_KERNEL);
-
-	if (!counter_config) {
-		pr_info("oprofile: failed to allocate %d "
-				"counters\n", perf_num_counters);
-		return -ENOMEM;
-	}
-
-	ret = init_driverfs();
-	if (ret) {
-		kfree(counter_config);
-		counter_config = NULL;
-		return ret;
-	}
-
-	for_each_possible_cpu(cpu) {
-		perf_events[cpu] = kcalloc(perf_num_counters,
-				sizeof(struct perf_event *), GFP_KERNEL);
-		if (!perf_events[cpu]) {
-			pr_info("oprofile: failed to allocate %d perf events "
-					"for cpu %d\n", perf_num_counters, cpu);
-			while (--cpu >= 0)
-				kfree(perf_events[cpu]);
-			return -ENOMEM;
-		}
-	}
-
 	ops->backtrace		= arm_backtrace;
-	ops->create_files	= op_arm_create_files;
-	ops->setup		= op_arm_setup;
-	ops->start		= op_arm_start;
-	ops->stop		= op_arm_stop;
-	ops->shutdown		= op_arm_stop;
-	ops->cpu_type		= op_name_from_perf_id(armpmu_get_pmu_id());
 
-	if (!ops->cpu_type)
+	return oprofile_perf_init(ops);
-		ret = -ENODEV;
-	else
-		pr_info("oprofile: using %s\n", ops->cpu_type);
-
-	return ret;
 }
 
-void oprofile_arch_exit(void)
+void __exit oprofile_arch_exit(void)
 {
-	int cpu, id;
+	oprofile_perf_exit();
-	struct perf_event *event;
-
-	if (*perf_events) {
-		for_each_possible_cpu(cpu) {
-			for (id = 0; id < perf_num_counters; ++id) {
-				event = perf_events[cpu][id];
-				if (event != NULL)
-					perf_event_release_kernel(event);
-			}
-			kfree(perf_events[cpu]);
-		}
-	}
-
-	if (counter_config) {
-		kfree(counter_config);
-		exit_driverfs();
-	}
 }
 #else
 int __init oprofile_arch_init(struct oprofile_operations *ops)
@@ -425,5 +126,5 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
 	pr_info("oprofile: hardware counters not available\n");
 	return -ENODEV;
 }
-void oprofile_arch_exit(void) {}
+void __exit oprofile_arch_exit(void) {}
 #endif /* CONFIG_HW_PERF_EVENTS */

arch/frv/Kconfig

@@ -7,6 +7,7 @@ config FRV
 	default y
 	select HAVE_IDE
 	select HAVE_ARCH_TRACEHOOK
+	select HAVE_IRQ_WORK
 	select HAVE_PERF_EVENTS
 
 config ZONE_DMA

arch/frv/lib/Makefile

@@ -5,4 +5,4 @@
 lib-y := \
 	__ashldi3.o __lshrdi3.o __muldi3.o __ashrdi3.o __negdi2.o __ucmpdi2.o \
 	checksum.o memcpy.o memset.o atomic-ops.o atomic64-ops.o \
-	outsl_ns.o outsl_sw.o insl_ns.o insl_sw.o cache.o perf_event.o
+	outsl_ns.o outsl_sw.o insl_ns.o insl_sw.o cache.o

arch/frv/lib/perf_event.c

@@ -1,19 +0,0 @@
-/* Performance event handling
- *
- * Copyright (C) 2009 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public Licence
- * as published by the Free Software Foundation; either version
- * 2 of the Licence, or (at your option) any later version.
- */
-
-#include <linux/perf_event.h>
-
-/*
- * mark the performance event as pending
- */
-void set_perf_event_pending(void)
-{
-}

arch/ia64/include/asm/hardirq.h

@@ -6,12 +6,6 @@
  *	David Mosberger-Tang <davidm@hpl.hp.com>
  */
 
-
-#include <linux/threads.h>
-#include <linux/irq.h>
-
-#include <asm/processor.h>
-
 /*
  * No irq_cpustat_t for IA-64.  The data is held in the per-CPU data structure.
  */
@@ -20,6 +14,11 @@
 
 #define local_softirq_pending()		(local_cpu_data->softirq_pending)
 
+#include <linux/threads.h>
+#include <linux/irq.h>
+
+#include <asm/processor.h>
+
 extern void __iomem *ipi_base_addr;
 
 void ack_bad_irq(unsigned int irq);

arch/parisc/Kconfig

@@ -16,6 +16,7 @@ config PARISC
 	select RTC_DRV_GENERIC
 	select INIT_ALL_POSSIBLE
 	select BUG
+	select HAVE_IRQ_WORK
 	select HAVE_PERF_EVENTS
 	select GENERIC_ATOMIC64 if !64BIT
 	help

arch/parisc/include/asm/perf_event.h

@@ -1,7 +1,6 @@
 #ifndef __ASM_PARISC_PERF_EVENT_H
 #define __ASM_PARISC_PERF_EVENT_H
 
-/* parisc only supports software events through this interface. */
+/* Empty, just to avoid compiling error */
-static inline void set_perf_event_pending(void) { }
 
 #endif /* __ASM_PARISC_PERF_EVENT_H */

arch/powerpc/Kconfig

@@ -138,6 +138,7 @@ config PPC
 	select HAVE_OPROFILE
 	select HAVE_SYSCALL_WRAPPERS if PPC64
 	select GENERIC_ATOMIC64 if PPC32
+	select HAVE_IRQ_WORK
 	select HAVE_PERF_EVENTS
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS && PPC_BOOK3S_64

arch/powerpc/include/asm/paca.h

@@ -129,7 +129,7 @@ struct paca_struct {
 	u8 soft_enabled;		/* irq soft-enable flag */
 	u8 hard_enabled;		/* set if irqs are enabled in MSR */
 	u8 io_sync;			/* writel() needs spin_unlock sync */
-	u8 perf_event_pending;		/* PM interrupt while soft-disabled */
+	u8 irq_work_pending;		/* IRQ_WORK interrupt while soft-disable */
 
 	/* Stuff for accurate time accounting */
 	u64 user_time;			/* accumulated usermode TB ticks */

arch/powerpc/kernel/perf_callchain.c

@@ -23,18 +23,6 @@
 #include "ppc32.h"
 #endif
 
-/*
- * Store another value in a callchain_entry.
- */
-static inline void callchain_store(struct perf_callchain_entry *entry, u64 ip)
-{
-	unsigned int nr = entry->nr;
-
-	if (nr < PERF_MAX_STACK_DEPTH) {
-		entry->ip[nr] = ip;
-		entry->nr = nr + 1;
-	}
-}
 
 /*
  * Is sp valid as the address of the next kernel stack frame after prev_sp?
@@ -58,8 +46,8 @@ static int valid_next_sp(unsigned long sp, unsigned long prev_sp)
 	return 0;
 }
 
-static void perf_callchain_kernel(struct pt_regs *regs,
+void
-				  struct perf_callchain_entry *entry)
+perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
 	unsigned long sp, next_sp;
 	unsigned long next_ip;
@@ -69,8 +57,7 @@ static void perf_callchain_kernel(struct pt_regs *regs,
 
 	lr = regs->link;
 	sp = regs->gpr[1];
-	callchain_store(entry, PERF_CONTEXT_KERNEL);
+	perf_callchain_store(entry, regs->nip);
-	callchain_store(entry, regs->nip);
 
 	if (!validate_sp(sp, current, STACK_FRAME_OVERHEAD))
 		return;
@@ -89,7 +76,7 @@ static void perf_callchain_kernel(struct pt_regs *regs,
 			next_ip = regs->nip;
 			lr = regs->link;
 			level = 0;
-			callchain_store(entry, PERF_CONTEXT_KERNEL);
+			perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
 
 		} else {
 			if (level == 0)
@@ -111,7 +98,7 @@ static void perf_callchain_kernel(struct pt_regs *regs,
 			++level;
 		}
 
-		callchain_store(entry, next_ip);
+		perf_callchain_store(entry, next_ip);
 		if (!valid_next_sp(next_sp, sp))
 			return;
 		sp = next_sp;
@@ -233,8 +220,8 @@ static int sane_signal_64_frame(unsigned long sp)
 		puc == (unsigned long) &sf->uc;
 }
 
-static void perf_callchain_user_64(struct pt_regs *regs,
+static void perf_callchain_user_64(struct perf_callchain_entry *entry,
-				   struct perf_callchain_entry *entry)
+				   struct pt_regs *regs)
 {
 	unsigned long sp, next_sp;
 	unsigned long next_ip;
@@ -246,8 +233,7 @@ static void perf_callchain_user_64(struct pt_regs *regs,
 	next_ip = regs->nip;
 	lr = regs->link;
 	sp = regs->gpr[1];
-	callchain_store(entry, PERF_CONTEXT_USER);
+	perf_callchain_store(entry, next_ip);
-	callchain_store(entry, next_ip);
 
 	for (;;) {
 		fp = (unsigned long __user *) sp;
@@ -276,14 +262,14 @@ static void perf_callchain_user_64(struct pt_regs *regs,
 			    read_user_stack_64(&uregs[PT_R1], &sp))
 				return;
 			level = 0;
-			callchain_store(entry, PERF_CONTEXT_USER);
+			perf_callchain_store(entry, PERF_CONTEXT_USER);
-			callchain_store(entry, next_ip);
+			perf_callchain_store(entry, next_ip);
 			continue;
 		}
 
 		if (level == 0)
 			next_ip = lr;
-		callchain_store(entry, next_ip);
+		perf_callchain_store(entry, next_ip);
 		++level;
 		sp = next_sp;
 	}
@@ -315,8 +301,8 @@ static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret)
 	return __get_user_inatomic(*ret, ptr);
 }
 
-static inline void perf_callchain_user_64(struct pt_regs *regs,
+static inline void perf_callchain_user_64(struct perf_callchain_entry *entry,
-					  struct perf_callchain_entry *entry)
+					  struct pt_regs *regs)
 {
 }
 
@@ -435,8 +421,8 @@ static unsigned int __user *signal_frame_32_regs(unsigned int sp,
 	return mctx->mc_gregs;
 }
 
-static void perf_callchain_user_32(struct pt_regs *regs,
+static void perf_callchain_user_32(struct perf_callchain_entry *entry,
-				   struct perf_callchain_entry *entry)
+				   struct pt_regs *regs)
 {
 	unsigned int sp, next_sp;
 	unsigned int next_ip;
@@ -447,8 +433,7 @@ static void perf_callchain_user_32(struct pt_regs *regs,
 	next_ip = regs->nip;
 	lr = regs->link;
 	sp = regs->gpr[1];
-	callchain_store(entry, PERF_CONTEXT_USER);
+	perf_callchain_store(entry, next_ip);
-	callchain_store(entry, next_ip);
 
 	while (entry->nr < PERF_MAX_STACK_DEPTH) {
 		fp = (unsigned int __user *) (unsigned long) sp;
@@ -470,45 +455,24 @@ static void perf_callchain_user_32(struct pt_regs *regs,
 			    read_user_stack_32(&uregs[PT_R1], &sp))
 				return;
 			level = 0;
-			callchain_store(entry, PERF_CONTEXT_USER);
+			perf_callchain_store(entry, PERF_CONTEXT_USER);
-			callchain_store(entry, next_ip);
+			perf_callchain_store(entry, next_ip);
 			continue;
 		}
 
 		if (level == 0)
 			next_ip = lr;
-		callchain_store(entry, next_ip);
+		perf_callchain_store(entry, next_ip);
 		++level;
 		sp = next_sp;
 	}
 }
 
-/*
+void
- * Since we can't get PMU interrupts inside a PMU interrupt handler,
+perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
- * we don't need separate irq and nmi entries here.
- */
-static DEFINE_PER_CPU(struct perf_callchain_entry, cpu_perf_callchain);
-
-struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
 {
-	struct perf_callchain_entry *entry = &__get_cpu_var(cpu_perf_callchain);
+	if (current_is_64bit())
-
+		perf_callchain_user_64(entry, regs);
-	entry->nr = 0;
+	else
-
+		perf_callchain_user_32(entry, regs);
-	if (!user_mode(regs)) {
-		perf_callchain_kernel(regs, entry);
-		if (current->mm)
-			regs = task_pt_regs(current);
-		else
-			regs = NULL;
-	}
-
-	if (regs) {
-		if (current_is_64bit())
-			perf_callchain_user_64(regs, entry);
-		else
-			perf_callchain_user_32(regs, entry);
-	}
-
-	return entry;
 }

arch/powerpc/kernel/perf_event.c

@@ -402,6 +402,9 @@ static void power_pmu_read(struct perf_event *event)
 {
 	s64 val, delta, prev;
 
+	if (event->hw.state & PERF_HES_STOPPED)
+		return;
+
 	if (!event->hw.idx)
 		return;
 	/*
@@ -517,7 +520,7 @@ static void write_mmcr0(struct cpu_hw_events *cpuhw, unsigned long mmcr0)
  * Disable all events to prevent PMU interrupts and to allow
  * events to be added or removed.
  */
-void hw_perf_disable(void)
+static void power_pmu_disable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw;
 	unsigned long flags;
@@ -565,7 +568,7 @@ void hw_perf_disable(void)
  * If we were previously disabled and events were added, then
  * put the new config on the PMU.
  */
-void hw_perf_enable(void)
+static void power_pmu_enable(struct pmu *pmu)
 {
 	struct perf_event *event;
 	struct cpu_hw_events *cpuhw;
@@ -672,6 +675,8 @@ void hw_perf_enable(void)
 		}
 		local64_set(&event->hw.prev_count, val);
 		event->hw.idx = idx;
+		if (event->hw.state & PERF_HES_STOPPED)
+			val = 0;
 		write_pmc(idx, val);
 		perf_event_update_userpage(event);
 	}
@@ -727,7 +732,7 @@ static int collect_events(struct perf_event *group, int max_count,
  * re-enable the PMU in order to get hw_perf_enable to do the
  * actual work of reconfiguring the PMU.
  */
-static int power_pmu_enable(struct perf_event *event)
+static int power_pmu_add(struct perf_event *event, int ef_flags)
 {
 	struct cpu_hw_events *cpuhw;
 	unsigned long flags;
@@ -735,7 +740,7 @@ static int power_pmu_enable(struct perf_event *event)
 	int ret = -EAGAIN;
 
 	local_irq_save(flags);
-	perf_disable();
+	perf_pmu_disable(event->pmu);
 
 	/*
 	 * Add the event to the list (if there is room)
@@ -749,6 +754,9 @@ static int power_pmu_enable(struct perf_event *event)
 	cpuhw->events[n0] = event->hw.config;
 	cpuhw->flags[n0] = event->hw.event_base;
 
+	if (!(ef_flags & PERF_EF_START))
+		event->hw.state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
+
 	/*
 	 * If group events scheduling transaction was started,
 	 * skip the schedulability test here, it will be peformed
@@ -769,7 +777,7 @@ nocheck:
 
 	ret = 0;
  out:
-	perf_enable();
+	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 	return ret;
 }
@@ -777,14 +785,14 @@ nocheck:
 /*
  * Remove a event from the PMU.
  */
-static void power_pmu_disable(struct perf_event *event)
+static void power_pmu_del(struct perf_event *event, int ef_flags)
 {
 	struct cpu_hw_events *cpuhw;
 	long i;
 	unsigned long flags;
 
 	local_irq_save(flags);
-	perf_disable();
+	perf_pmu_disable(event->pmu);
 
 	power_pmu_read(event);
 
@@ -821,34 +829,60 @@ static void power_pmu_disable(struct perf_event *event)
 		cpuhw->mmcr[0] &= ~(MMCR0_PMXE | MMCR0_FCECE);
 	}
 
-	perf_enable();
+	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 }
 
 /*
- * Re-enable interrupts on a event after they were throttled
+ * POWER-PMU does not support disabling individual counters, hence
- * because they were coming too fast.
+ * program their cycle counter to their max value and ignore the interrupts.
  */
-static void power_pmu_unthrottle(struct perf_event *event)
+
+static void power_pmu_start(struct perf_event *event, int ef_flags)
+{
+	unsigned long flags;
+	s64 left;
+
+	if (!event->hw.idx || !event->hw.sample_period)
+		return;
+
+	if (!(event->hw.state & PERF_HES_STOPPED))
+		return;
+
+	if (ef_flags & PERF_EF_RELOAD)
+		WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));
+
+	local_irq_save(flags);
+	perf_pmu_disable(event->pmu);
+
+	event->hw.state = 0;
+	left = local64_read(&event->hw.period_left);
+	write_pmc(event->hw.idx, left);
+
+	perf_event_update_userpage(event);
+	perf_pmu_enable(event->pmu);
+	local_irq_restore(flags);
+}
+
+static void power_pmu_stop(struct perf_event *event, int ef_flags)
 {
-	s64 val, left;
 	unsigned long flags;
 
 	if (!event->hw.idx || !event->hw.sample_period)
 		return;
+
+	if (event->hw.state & PERF_HES_STOPPED)
+		return;
+
 	local_irq_save(flags);
-	perf_disable();
+	perf_pmu_disable(event->pmu);
+
 	power_pmu_read(event);
-	left = event->hw.sample_period;
+	event->hw.state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
-	event->hw.last_period = left;
+	write_pmc(event->hw.idx, 0);
-	val = 0;
+
-	if (left < 0x80000000L)
-		val = 0x80000000L - left;
-	write_pmc(event->hw.idx, val);
-	local64_set(&event->hw.prev_count, val);
-	local64_set(&event->hw.period_left, left);
 	perf_event_update_userpage(event);
-	perf_enable();
+	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 }
 
@@ -857,10 +891,11 @@ static void power_pmu_unthrottle(struct perf_event *event)
  * Set the flag to make pmu::enable() not perform the
  * schedulability test, it will be performed at commit time
  */
-void power_pmu_start_txn(const struct pmu *pmu)
+void power_pmu_start_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
+	perf_pmu_disable(pmu);
 	cpuhw->group_flag |= PERF_EVENT_TXN;
 	cpuhw->n_txn_start = cpuhw->n_events;
 }
@@ -870,11 +905,12 @@ void power_pmu_start_txn(const struct pmu *pmu)
  * Clear the flag and pmu::enable() will perform the
  * schedulability test.
  */
-void power_pmu_cancel_txn(const struct pmu *pmu)
+void power_pmu_cancel_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
 	cpuhw->group_flag &= ~PERF_EVENT_TXN;
+	perf_pmu_enable(pmu);
 }
 
 /*
@@ -882,7 +918,7 @@ void power_pmu_cancel_txn(const struct pmu *pmu)
  * Perform the group schedulability test as a whole
  * Return 0 if success
  */
-int power_pmu_commit_txn(const struct pmu *pmu)
+int power_pmu_commit_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw;
 	long i, n;
@@ -901,19 +937,10 @@ int power_pmu_commit_txn(const struct pmu *pmu)
 		cpuhw->event[i]->hw.config = cpuhw->events[i];
 
 	cpuhw->group_flag &= ~PERF_EVENT_TXN;
+	perf_pmu_enable(pmu);
 	return 0;
 }
 
-struct pmu power_pmu = {
-	.enable		= power_pmu_enable,
-	.disable	= power_pmu_disable,
-	.read		= power_pmu_read,
-	.unthrottle	= power_pmu_unthrottle,
-	.start_txn	= power_pmu_start_txn,
-	.cancel_txn	= power_pmu_cancel_txn,
-	.commit_txn	= power_pmu_commit_txn,
-};
-
 /*
  * Return 1 if we might be able to put event on a limited PMC,
  * or 0 if not.
@@ -1014,7 +1041,7 @@ static int hw_perf_cache_event(u64 config, u64 *eventp)
 	return 0;
 }
 
-const struct pmu *hw_perf_event_init(struct perf_event *event)
+static int power_pmu_event_init(struct perf_event *event)
 {
 	u64 ev;
 	unsigned long flags;
@@ -1026,25 +1053,27 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 	struct cpu_hw_events *cpuhw;
 
 	if (!ppmu)
-		return ERR_PTR(-ENXIO);
+		return -ENOENT;
+
 	switch (event->attr.type) {
 	case PERF_TYPE_HARDWARE:
 		ev = event->attr.config;
 		if (ev >= ppmu->n_generic || ppmu->generic_events[ev] == 0)
-			return ERR_PTR(-EOPNOTSUPP);
+			return -EOPNOTSUPP;
 		ev = ppmu->generic_events[ev];
 		break;
 	case PERF_TYPE_HW_CACHE:
 		err = hw_perf_cache_event(event->attr.config, &ev);
 		if (err)
-			return ERR_PTR(err);
+			return err;
 		break;
 	case PERF_TYPE_RAW:
 		ev = event->attr.config;
 		break;
 	default:
-		return ERR_PTR(-EINVAL);
+		return -ENOENT;
 	}
+
 	event->hw.config_base = ev;
 	event->hw.idx = 0;
 
@@ -1063,7 +1092,7 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 	 * XXX we should check if the task is an idle task.
 	 */
 	flags = 0;
-	if (event->ctx->task)
+	if (event->attach_state & PERF_ATTACH_TASK)
 		flags |= PPMU_ONLY_COUNT_RUN;
 
 	/*
@@ -1081,7 +1110,7 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 			 */
 			ev = normal_pmc_alternative(ev, flags);
 			if (!ev)
-				return ERR_PTR(-EINVAL);
+				return -EINVAL;
 		}
 	}
 
@@ -1095,19 +1124,19 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 		n = collect_events(event->group_leader, ppmu->n_counter - 1,
 				   ctrs, events, cflags);
 		if (n < 0)
-			return ERR_PTR(-EINVAL);
+			return -EINVAL;
 	}
 	events[n] = ev;
 	ctrs[n] = event;
 	cflags[n] = flags;
 	if (check_excludes(ctrs, cflags, n, 1))
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	cpuhw = &get_cpu_var(cpu_hw_events);
 	err = power_check_constraints(cpuhw, events, cflags, n + 1);
 	put_cpu_var(cpu_hw_events);
 	if (err)
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	event->hw.config = events[n];
 	event->hw.event_base = cflags[n];
@@ -1132,11 +1161,23 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 	}
 	event->destroy = hw_perf_event_destroy;
 
-	if (err)
+	return err;
-		return ERR_PTR(err);
-	return &power_pmu;
 }
 
+struct pmu power_pmu = {
+	.pmu_enable	= power_pmu_enable,
+	.pmu_disable	= power_pmu_disable,
+	.event_init	= power_pmu_event_init,
+	.add		= power_pmu_add,
+	.del		= power_pmu_del,
+	.start		= power_pmu_start,
+	.stop		= power_pmu_stop,
+	.read		= power_pmu_read,
+	.start_txn	= power_pmu_start_txn,
+	.cancel_txn	= power_pmu_cancel_txn,
+	.commit_txn	= power_pmu_commit_txn,
+};
+
 /*
  * A counter has overflowed; update its count and record
  * things if requested.  Note that interrupts are hard-disabled
@@ -1149,6 +1190,11 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 	s64 prev, delta, left;
 	int record = 0;
 
+	if (event->hw.state & PERF_HES_STOPPED) {
+		write_pmc(event->hw.idx, 0);
+		return;
+	}
+
 	/* we don't have to worry about interrupts here */
 	prev = local64_read(&event->hw.prev_count);
 	delta = (val - prev) & 0xfffffffful;
@@ -1171,6 +1217,11 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 			val = 0x80000000LL - left;
 	}
 
+	write_pmc(event->hw.idx, val);
+	local64_set(&event->hw.prev_count, val);
+	local64_set(&event->hw.period_left, left);
+	perf_event_update_userpage(event);
+
 	/*
 	 * Finally record data if requested.
 	 */
@@ -1183,23 +1234,9 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 		if (event->attr.sample_type & PERF_SAMPLE_ADDR)
 			perf_get_data_addr(regs, &data.addr);
 
-		if (perf_event_overflow(event, nmi, &data, regs)) {
+		if (perf_event_overflow(event, nmi, &data, regs))
-			/*
+			power_pmu_stop(event, 0);
-			 * Interrupts are coming too fast - throttle them
-			 * by setting the event to 0, so it will be
-			 * at least 2^30 cycles until the next interrupt
-			 * (assuming each event counts at most 2 counts
-			 * per cycle).
-			 */
-			val = 0;
-			left = ~0ULL >> 1;
-		}
 	}
-
-	write_pmc(event->hw.idx, val);
-	local64_set(&event->hw.prev_count, val);
-	local64_set(&event->hw.period_left, left);
-	perf_event_update_userpage(event);
 }
 
 /*
@@ -1342,6 +1379,7 @@ int register_power_pmu(struct power_pmu *pmu)
 		freeze_events_kernel = MMCR0_FCHV;
 #endif /* CONFIG_PPC64 */
 
+	perf_pmu_register(&power_pmu);
 	perf_cpu_notifier(power_pmu_notifier);
 
 	return 0;

arch/powerpc/kernel/perf_event_fsl_emb.c

@@ -156,6 +156,9 @@ static void fsl_emb_pmu_read(struct perf_event *event)
 {
 	s64 val, delta, prev;
 
+	if (event->hw.state & PERF_HES_STOPPED)
+		return;
+
 	/*
 	 * Performance monitor interrupts come even when interrupts
 	 * are soft-disabled, as long as interrupts are hard-enabled.
@@ -177,7 +180,7 @@ static void fsl_emb_pmu_read(struct perf_event *event)
  * Disable all events to prevent PMU interrupts and to allow
  * events to be added or removed.
  */
-void hw_perf_disable(void)
+static void fsl_emb_pmu_disable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw;
 	unsigned long flags;
@@ -216,7 +219,7 @@ void hw_perf_disable(void)
  * If we were previously disabled and events were added, then
  * put the new config on the PMU.
  */
-void hw_perf_enable(void)
+static void fsl_emb_pmu_enable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw;
 	unsigned long flags;
@@ -262,8 +265,8 @@ static int collect_events(struct perf_event *group, int max_count,
 	return n;
 }
 
-/* perf must be disabled, context locked on entry */
+/* context locked on entry */
-static int fsl_emb_pmu_enable(struct perf_event *event)
+static int fsl_emb_pmu_add(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuhw;
 	int ret = -EAGAIN;
@@ -271,6 +274,7 @@ static int fsl_emb_pmu_enable(struct perf_event *event)
 	u64 val;
 	int i;
 
+	perf_pmu_disable(event->pmu);
 	cpuhw = &get_cpu_var(cpu_hw_events);
 
 	if (event->hw.config & FSL_EMB_EVENT_RESTRICTED)
@@ -301,6 +305,12 @@ static int fsl_emb_pmu_enable(struct perf_event *event)
 			val = 0x80000000L - left;
 	}
 	local64_set(&event->hw.prev_count, val);
+
+	if (!(flags & PERF_EF_START)) {
+		event->hw.state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
+		val = 0;
+	}
+
 	write_pmc(i, val);
 	perf_event_update_userpage(event);
 
@@ -310,15 +320,17 @@ static int fsl_emb_pmu_enable(struct perf_event *event)
 	ret = 0;
  out:
 	put_cpu_var(cpu_hw_events);
+	perf_pmu_enable(event->pmu);
 	return ret;
 }
 
-/* perf must be disabled, context locked on entry */
+/* context locked on entry */
-static void fsl_emb_pmu_disable(struct perf_event *event)
+static void fsl_emb_pmu_del(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuhw;
 	int i = event->hw.idx;
 
+	perf_pmu_disable(event->pmu);
 	if (i < 0)
 		goto out;
 
@@ -346,45 +358,58 @@ static void fsl_emb_pmu_disable(struct perf_event *event)
 	cpuhw->n_events--;
 
  out:
+	perf_pmu_enable(event->pmu);
 	put_cpu_var(cpu_hw_events);
 }
 
-/*
+static void fsl_emb_pmu_start(struct perf_event *event, int ef_flags)
- * Re-enable interrupts on a event after they were throttled
+{
- * because they were coming too fast.
+	unsigned long flags;
- *
+	s64 left;
- * Context is locked on entry, but perf is not disabled.
+
- */
+	if (event->hw.idx < 0 || !event->hw.sample_period)
-static void fsl_emb_pmu_unthrottle(struct perf_event *event)
+		return;
+
+	if (!(event->hw.state & PERF_HES_STOPPED))
+		return;
+
+	if (ef_flags & PERF_EF_RELOAD)
+		WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));
+
+	local_irq_save(flags);
+	perf_pmu_disable(event->pmu);
+
+	event->hw.state = 0;
+	left = local64_read(&event->hw.period_left);
+	write_pmc(event->hw.idx, left);
+
+	perf_event_update_userpage(event);
+	perf_pmu_enable(event->pmu);
+	local_irq_restore(flags);
+}
+
+static void fsl_emb_pmu_stop(struct perf_event *event, int ef_flags)
 {
-	s64 val, left;
 	unsigned long flags;
 
 	if (event->hw.idx < 0 || !event->hw.sample_period)
 		return;
+
+	if (event->hw.state & PERF_HES_STOPPED)
+		return;
+
 	local_irq_save(flags);
-	perf_disable();
+	perf_pmu_disable(event->pmu);
+
 	fsl_emb_pmu_read(event);
-	left = event->hw.sample_period;
+	event->hw.state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
-	event->hw.last_period = left;
+	write_pmc(event->hw.idx, 0);
-	val = 0;
+
-	if (left < 0x80000000L)
-		val = 0x80000000L - left;
-	write_pmc(event->hw.idx, val);
-	local64_set(&event->hw.prev_count, val);
-	local64_set(&event->hw.period_left, left);
 	perf_event_update_userpage(event);
-	perf_enable();
+	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 }
 
-static struct pmu fsl_emb_pmu = {
-	.enable		= fsl_emb_pmu_enable,
-	.disable	= fsl_emb_pmu_disable,
-	.read		= fsl_emb_pmu_read,
-	.unthrottle	= fsl_emb_pmu_unthrottle,
-};
-
 /*
  * Release the PMU if this is the last perf_event.
  */
@@ -428,7 +453,7 @@ static int hw_perf_cache_event(u64 config, u64 *eventp)
 	return 0;
 }
 
-const struct pmu *hw_perf_event_init(struct perf_event *event)
+static int fsl_emb_pmu_event_init(struct perf_event *event)
 {
 	u64 ev;
 	struct perf_event *events[MAX_HWEVENTS];
@@ -441,14 +466,14 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 	case PERF_TYPE_HARDWARE:
 		ev = event->attr.config;
 		if (ev >= ppmu->n_generic || ppmu->generic_events[ev] == 0)
-			return ERR_PTR(-EOPNOTSUPP);
+			return -EOPNOTSUPP;
 		ev = ppmu->generic_events[ev];
 		break;
 
 	case PERF_TYPE_HW_CACHE:
 		err = hw_perf_cache_event(event->attr.config, &ev);
 		if (err)
-			return ERR_PTR(err);
+			return err;
 		break;
 
 	case PERF_TYPE_RAW:
@@ -456,12 +481,12 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 		break;
 
 	default:
-		return ERR_PTR(-EINVAL);
+		return -ENOENT;
 	}
 
 	event->hw.config = ppmu->xlate_event(ev);
 	if (!(event->hw.config & FSL_EMB_EVENT_VALID))
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	/*
 	 * If this is in a group, check if it can go on with all the
@@ -473,7 +498,7 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 		n = collect_events(event->group_leader,
 		                   ppmu->n_counter - 1, events);
 		if (n < 0)
-			return ERR_PTR(-EINVAL);
+			return -EINVAL;
 	}
 
 	if (event->hw.config & FSL_EMB_EVENT_RESTRICTED) {
@@ -484,7 +509,7 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 		}
 
 		if (num_restricted >= ppmu->n_restricted)
-			return ERR_PTR(-EINVAL);
+			return -EINVAL;
 	}
 
 	event->hw.idx = -1;
@@ -497,7 +522,7 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 	if (event->attr.exclude_kernel)
 		event->hw.config_base |= PMLCA_FCS;
 	if (event->attr.exclude_idle)
-		return ERR_PTR(-ENOTSUPP);
+		return -ENOTSUPP;
 
 	event->hw.last_period = event->hw.sample_period;
 	local64_set(&event->hw.period_left, event->hw.last_period);
@@ -523,11 +548,20 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 	}
 	event->destroy = hw_perf_event_destroy;
 
-	if (err)
+	return err;
-		return ERR_PTR(err);
-	return &fsl_emb_pmu;
 }
 
+static struct pmu fsl_emb_pmu = {
+	.pmu_enable	= fsl_emb_pmu_enable,
+	.pmu_disable	= fsl_emb_pmu_disable,
+	.event_init	= fsl_emb_pmu_event_init,
+	.add		= fsl_emb_pmu_add,
+	.del		= fsl_emb_pmu_del,
+	.start		= fsl_emb_pmu_start,
+	.stop		= fsl_emb_pmu_stop,
+	.read		= fsl_emb_pmu_read,
+};
+
 /*
  * A counter has overflowed; update its count and record
  * things if requested.  Note that interrupts are hard-disabled
@@ -540,6 +574,11 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 	s64 prev, delta, left;
 	int record = 0;
 
+	if (event->hw.state & PERF_HES_STOPPED) {
+		write_pmc(event->hw.idx, 0);
+		return;
+	}
+
 	/* we don't have to worry about interrupts here */
 	prev = local64_read(&event->hw.prev_count);
 	delta = (val - prev) & 0xfffffffful;
@@ -562,6 +601,11 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 			val = 0x80000000LL - left;
 	}
 
+	write_pmc(event->hw.idx, val);
+	local64_set(&event->hw.prev_count, val);
+	local64_set(&event->hw.period_left, left);
+	perf_event_update_userpage(event);
+
 	/*
 	 * Finally record data if requested.
 	 */
@@ -571,23 +615,9 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 		perf_sample_data_init(&data, 0);
 		data.period = event->hw.last_period;
 
-		if (perf_event_overflow(event, nmi, &data, regs)) {
+		if (perf_event_overflow(event, nmi, &data, regs))
-			/*
+			fsl_emb_pmu_stop(event, 0);
-			 * Interrupts are coming too fast - throttle them
-			 * by setting the event to 0, so it will be
-			 * at least 2^30 cycles until the next interrupt
-			 * (assuming each event counts at most 2 counts
-			 * per cycle).
-			 */
-			val = 0;
-			left = ~0ULL >> 1;
-		}
 	}
-
-	write_pmc(event->hw.idx, val);
-	local64_set(&event->hw.prev_count, val);
-	local64_set(&event->hw.period_left, left);
-	perf_event_update_userpage(event);
 }
 
 static void perf_event_interrupt(struct pt_regs *regs)
@@ -651,5 +681,7 @@ int register_fsl_emb_pmu(struct fsl_emb_pmu *pmu)
 	pr_info("%s performance monitor hardware support registered\n",
 		pmu->name);
 
+	perf_pmu_register(&fsl_emb_pmu);
+
 	return 0;
 }

arch/powerpc/kernel/time.c

@@ -53,7 +53,7 @@
 #include <linux/posix-timers.h>
 #include <linux/irq.h>
 #include <linux/delay.h>
-#include <linux/perf_event.h>
+#include <linux/irq_work.h>
 #include <asm/trace.h>
 
 #include <asm/io.h>
@@ -493,60 +493,60 @@ void __init iSeries_time_init_early(void)
 }
 #endif /* CONFIG_PPC_ISERIES */
 
-#ifdef CONFIG_PERF_EVENTS
+#ifdef CONFIG_IRQ_WORK
 
 /*
  * 64-bit uses a byte in the PACA, 32-bit uses a per-cpu variable...
  */
 #ifdef CONFIG_PPC64
-static inline unsigned long test_perf_event_pending(void)
+static inline unsigned long test_irq_work_pending(void)
 {
 	unsigned long x;
 
 	asm volatile("lbz %0,%1(13)"
 		: "=r" (x)
-		: "i" (offsetof(struct paca_struct, perf_event_pending)));
+		: "i" (offsetof(struct paca_struct, irq_work_pending)));
 	return x;
 }
 
-static inline void set_perf_event_pending_flag(void)
+static inline void set_irq_work_pending_flag(void)
 {
 	asm volatile("stb %0,%1(13)" : :
 		"r" (1),
-		"i" (offsetof(struct paca_struct, perf_event_pending)));
+		"i" (offsetof(struct paca_struct, irq_work_pending)));
 }
 
-static inline void clear_perf_event_pending(void)
+static inline void clear_irq_work_pending(void)
 {
 	asm volatile("stb %0,%1(13)" : :
 		"r" (0),
-		"i" (offsetof(struct paca_struct, perf_event_pending)));
+		"i" (offsetof(struct paca_struct, irq_work_pending)));
 }
 
 #else /* 32-bit */
 
-DEFINE_PER_CPU(u8, perf_event_pending);
+DEFINE_PER_CPU(u8, irq_work_pending);
 
-#define set_perf_event_pending_flag()	__get_cpu_var(perf_event_pending) = 1
+#define set_irq_work_pending_flag()	__get_cpu_var(irq_work_pending) = 1
-#define test_perf_event_pending()	__get_cpu_var(perf_event_pending)
+#define test_irq_work_pending()		__get_cpu_var(irq_work_pending)
-#define clear_perf_event_pending()	__get_cpu_var(perf_event_pending) = 0
+#define clear_irq_work_pending()	__get_cpu_var(irq_work_pending) = 0
 
 #endif /* 32 vs 64 bit */
 
-void set_perf_event_pending(void)
+void set_irq_work_pending(void)
 {
 	preempt_disable();
-	set_perf_event_pending_flag();
+	set_irq_work_pending_flag();
 	set_dec(1);
 	preempt_enable();
 }
 
-#else  /* CONFIG_PERF_EVENTS */
+#else  /* CONFIG_IRQ_WORK */
 
-#define test_perf_event_pending()	0
+#define test_irq_work_pending()	0
-#define clear_perf_event_pending()
+#define clear_irq_work_pending()
 
-#endif /* CONFIG_PERF_EVENTS */
+#endif /* CONFIG_IRQ_WORK */
 
 /*
  * For iSeries shared processors, we have to let the hypervisor
@@ -587,9 +587,9 @@ void timer_interrupt(struct pt_regs * regs)
 
 	calculate_steal_time();
 
-	if (test_perf_event_pending()) {
+	if (test_irq_work_pending()) {
-		clear_perf_event_pending();
+		clear_irq_work_pending();
-		perf_event_do_pending();
+		irq_work_run();
 	}
 
 #ifdef CONFIG_PPC_ISERIES

arch/s390/Kconfig

@@ -95,6 +95,7 @@ config S390
 	select HAVE_KVM if 64BIT
 	select HAVE_ARCH_TRACEHOOK
 	select INIT_ALL_POSSIBLE
+	select HAVE_IRQ_WORK
 	select HAVE_PERF_EVENTS
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_BZIP2

arch/s390/include/asm/hardirq.h

@@ -12,10 +12,6 @@
 #ifndef __ASM_HARDIRQ_H
 #define __ASM_HARDIRQ_H
 
-#include <linux/threads.h>
-#include <linux/sched.h>
-#include <linux/cache.h>
-#include <linux/interrupt.h>
 #include <asm/lowcore.h>
 
 #define local_softirq_pending() (S390_lowcore.softirq_pending)

arch/s390/include/asm/perf_event.h

@@ -4,7 +4,6 @@
  * Copyright 2009 Martin Schwidefsky, IBM Corporation.
  */
 
-static inline void set_perf_event_pending(void) {}
+/* Empty, just to avoid compiling error */
-static inline void clear_perf_event_pending(void) {}
 
 #define PERF_EVENT_INDEX_OFFSET 0

arch/sh/Kconfig

@@ -16,6 +16,7 @@ config SUPERH
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_DMA_API_DEBUG
 	select HAVE_DMA_ATTRS
+	select HAVE_IRQ_WORK
 	select HAVE_PERF_EVENTS
 	select PERF_USE_VMALLOC
 	select HAVE_KERNEL_GZIP
@@ -249,6 +250,11 @@ config ARCH_SHMOBILE
 	select PM
 	select PM_RUNTIME
 
+config CPU_HAS_PMU
+       depends on CPU_SH4 || CPU_SH4A
+       default y
+       bool
+
 if SUPERH32
 
 choice
@@ -738,6 +744,14 @@ config GUSA_RB
 	  LLSC, this should be more efficient than the other alternative of
 	  disabling interrupts around the atomic sequence.
 
+config HW_PERF_EVENTS
+	bool "Enable hardware performance counter support for perf events"
+	depends on PERF_EVENTS && CPU_HAS_PMU
+	default y
+	help
+	  Enable hardware performance counter support for perf events. If
+	  disabled, perf events will use software events only.
+
 source "drivers/sh/Kconfig"
 
 endmenu

arch/sh/include/asm/perf_event.h

@@ -26,11 +26,4 @@ extern int register_sh_pmu(struct sh_pmu *);
 extern int reserve_pmc_hardware(void);
 extern void release_pmc_hardware(void);
 
-static inline void set_perf_event_pending(void)
-{
-	/* Nothing to see here, move along. */
-}
-
-#define PERF_EVENT_INDEX_OFFSET	0
-
 #endif /* __ASM_SH_PERF_EVENT_H */

arch/sh/kernel/perf_callchain.c

@@ -14,11 +14,6 @@
 #include <asm/unwinder.h>
 #include <asm/ptrace.h>
 
-static inline void callchain_store(struct perf_callchain_entry *entry, u64 ip)
-{
-	if (entry->nr < PERF_MAX_STACK_DEPTH)
-		entry->ip[entry->nr++] = ip;
-}
 
 static void callchain_warning(void *data, char *msg)
 {
@@ -39,7 +34,7 @@ static void callchain_address(void *data, unsigned long addr, int reliable)
 	struct perf_callchain_entry *entry = data;
 
 	if (reliable)
-		callchain_store(entry, addr);
+		perf_callchain_store(entry, addr);
 }
 
 static const struct stacktrace_ops callchain_ops = {
@@ -49,47 +44,10 @@ static const struct stacktrace_ops callchain_ops = {
 	.address	= callchain_address,
 };
 
-static void
+void
-perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry)
+perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
-	callchain_store(entry, PERF_CONTEXT_KERNEL);
+	perf_callchain_store(entry, regs->pc);
-	callchain_store(entry, regs->pc);
 
 	unwind_stack(NULL, regs, NULL, &callchain_ops, entry);
 }
-
-static void
-perf_do_callchain(struct pt_regs *regs, struct perf_callchain_entry *entry)
-{
-	int is_user;
-
-	if (!regs)
-		return;
-
-	is_user = user_mode(regs);
-
-	if (is_user && current->state != TASK_RUNNING)
-		return;
-
-	/*
-	 * Only the kernel side is implemented for now.
-	 */
-	if (!is_user)
-		perf_callchain_kernel(regs, entry);
-}
-
-/*
- * No need for separate IRQ and NMI entries.
- */
-static DEFINE_PER_CPU(struct perf_callchain_entry, callchain);
-
-struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
-{
-	struct perf_callchain_entry *entry = &__get_cpu_var(callchain);
-
-	entry->nr = 0;
-
-	perf_do_callchain(regs, entry);
-
-	return entry;
-}

arch/sh/kernel/perf_event.c

@@ -59,6 +59,24 @@ static inline int sh_pmu_initialized(void)
 	return !!sh_pmu;
 }
 
+const char *perf_pmu_name(void)
+{
+	if (!sh_pmu)
+		return NULL;
+
+	return sh_pmu->name;
+}
+EXPORT_SYMBOL_GPL(perf_pmu_name);
+
+int perf_num_counters(void)
+{
+	if (!sh_pmu)
+		return 0;
+
+	return sh_pmu->num_events;
+}
+EXPORT_SYMBOL_GPL(perf_num_counters);
+
 /*
  * Release the PMU if this is the last perf_event.
  */
@@ -206,50 +224,80 @@ again:
 	local64_add(delta, &event->count);
 }
 
-static void sh_pmu_disable(struct perf_event *event)
+static void sh_pmu_stop(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
-	clear_bit(idx, cpuc->active_mask);
+	if (!(event->hw.state & PERF_HES_STOPPED)) {
-	sh_pmu->disable(hwc, idx);
+		sh_pmu->disable(hwc, idx);
+		cpuc->events[idx] = NULL;
+		event->hw.state |= PERF_HES_STOPPED;
+	}
 
-	barrier();
+	if ((flags & PERF_EF_UPDATE) && !(event->hw.state & PERF_HES_UPTODATE)) {
+		sh_perf_event_update(event, &event->hw, idx);
+		event->hw.state |= PERF_HES_UPTODATE;
+	}
+}
 
-	sh_perf_event_update(event, &event->hw, idx);
+static void sh_pmu_start(struct perf_event *event, int flags)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
 
-	cpuc->events[idx] = NULL;
+	if (WARN_ON_ONCE(idx == -1))
-	clear_bit(idx, cpuc->used_mask);
+		return;
+
+	if (flags & PERF_EF_RELOAD)
+		WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));
+
+	cpuc->events[idx] = event;
+	event->hw.state = 0;
+	sh_pmu->enable(hwc, idx);
+}
+
+static void sh_pmu_del(struct perf_event *event, int flags)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	sh_pmu_stop(event, PERF_EF_UPDATE);
+	__clear_bit(event->hw.idx, cpuc->used_mask);
 
 	perf_event_update_userpage(event);
 }
 
-static int sh_pmu_enable(struct perf_event *event)
+static int sh_pmu_add(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
+	int ret = -EAGAIN;
 
-	if (test_and_set_bit(idx, cpuc->used_mask)) {
+	perf_pmu_disable(event->pmu);
+
+	if (__test_and_set_bit(idx, cpuc->used_mask)) {
 		idx = find_first_zero_bit(cpuc->used_mask, sh_pmu->num_events);
 		if (idx == sh_pmu->num_events)
-			return -EAGAIN;
+			goto out;
 
-		set_bit(idx, cpuc->used_mask);
+		__set_bit(idx, cpuc->used_mask);
 		hwc->idx = idx;
 	}
 
 	sh_pmu->disable(hwc, idx);
 
-	cpuc->events[idx] = event;
+	event->hw.state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
-	set_bit(idx, cpuc->active_mask);
+	if (flags & PERF_EF_START)
-
+		sh_pmu_start(event, PERF_EF_RELOAD);
-	sh_pmu->enable(hwc, idx);
 
 	perf_event_update_userpage(event);
-
+	ret = 0;
-	return 0;
+out:
+	perf_pmu_enable(event->pmu);
+	return ret;
 }
 
 static void sh_pmu_read(struct perf_event *event)
@@ -257,24 +305,56 @@ static void sh_pmu_read(struct perf_event *event)
 	sh_perf_event_update(event, &event->hw, event->hw.idx);
 }
 
-static const struct pmu pmu = {
+static int sh_pmu_event_init(struct perf_event *event)
-	.enable		= sh_pmu_enable,
-	.disable	= sh_pmu_disable,
-	.read		= sh_pmu_read,
-};
-
-const struct pmu *hw_perf_event_init(struct perf_event *event)
 {
-	int err = __hw_perf_event_init(event);
+	int err;
+
+	switch (event->attr.type) {
+	case PERF_TYPE_RAW:
+	case PERF_TYPE_HW_CACHE:
+	case PERF_TYPE_HARDWARE:
+		err = __hw_perf_event_init(event);
+		break;
+
+	default:
+		return -ENOENT;
+	}
+
 	if (unlikely(err)) {
 		if (event->destroy)
 			event->destroy(event);
-		return ERR_PTR(err);
 	}
 
-	return &pmu;
+	return err;
 }
 
+static void sh_pmu_enable(struct pmu *pmu)
+{
+	if (!sh_pmu_initialized())
+		return;
+
+	sh_pmu->enable_all();
+}
+
+static void sh_pmu_disable(struct pmu *pmu)
+{
+	if (!sh_pmu_initialized())
+		return;
+
+	sh_pmu->disable_all();
+}
+
+static struct pmu pmu = {
+	.pmu_enable	= sh_pmu_enable,
+	.pmu_disable	= sh_pmu_disable,
+	.event_init	= sh_pmu_event_init,
+	.add		= sh_pmu_add,
+	.del		= sh_pmu_del,
+	.start		= sh_pmu_start,
+	.stop		= sh_pmu_stop,
+	.read		= sh_pmu_read,
+};
+
 static void sh_pmu_setup(int cpu)
 {
 	struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu);
@@ -299,32 +379,17 @@ sh_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
 	return NOTIFY_OK;
 }
 
-void hw_perf_enable(void)
+int __cpuinit register_sh_pmu(struct sh_pmu *_pmu)
-{
-	if (!sh_pmu_initialized())
-		return;
-
-	sh_pmu->enable_all();
-}
-
-void hw_perf_disable(void)
-{
-	if (!sh_pmu_initialized())
-		return;
-
-	sh_pmu->disable_all();
-}
-
-int __cpuinit register_sh_pmu(struct sh_pmu *pmu)
 {
 	if (sh_pmu)
 		return -EBUSY;
-	sh_pmu = pmu;
+	sh_pmu = _pmu;
 
-	pr_info("Performance Events: %s support registered\n", pmu->name);
+	pr_info("Performance Events: %s support registered\n", _pmu->name);
 
-	WARN_ON(pmu->num_events > MAX_HWEVENTS);
+	WARN_ON(_pmu->num_events > MAX_HWEVENTS);
 
+	perf_pmu_register(&pmu);
 	perf_cpu_notifier(sh_pmu_notifier);
 	return 0;
 }

arch/sh/oprofile/Makefile

@@ -6,4 +6,8 @@ DRIVER_OBJS = $(addprefix ../../../drivers/oprofile/, \
 		oprofilefs.o oprofile_stats.o \
 		timer_int.o )
 
+ifeq ($(CONFIG_HW_PERF_EVENTS),y)
+DRIVER_OBJS += $(addprefix ../../../drivers/oprofile/, oprofile_perf.o)
+endif
+
 oprofile-y	:= $(DRIVER_OBJS) common.o backtrace.o

arch/sh/oprofile/common.c

@@ -17,114 +17,45 @@
 #include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/smp.h>
+#include <linux/perf_event.h>
 #include <asm/processor.h>
-#include "op_impl.h"
-
-static struct op_sh_model *model;
-
-static struct op_counter_config ctr[20];
 
+#ifdef CONFIG_HW_PERF_EVENTS
 extern void sh_backtrace(struct pt_regs * const regs, unsigned int depth);
 
-static int op_sh_setup(void)
+char *op_name_from_perf_id(void)
 {
-	/* Pre-compute the values to stuff in the hardware registers.  */
+	const char *pmu;
-	model->reg_setup(ctr);
+	char buf[20];
+	int size;
 
-	/* Configure the registers on all cpus.  */
+	pmu = perf_pmu_name();
-	on_each_cpu(model->cpu_setup, NULL, 1);
+	if (!pmu)
+		return NULL;
 
-        return 0;
+	size = snprintf(buf, sizeof(buf), "sh/%s", pmu);
-}
+	if (size > -1 && size < sizeof(buf))
+		return buf;
 
-static int op_sh_create_files(struct super_block *sb, struct dentry *root)
+	return NULL;
-{
-	int i, ret = 0;
-
-	for (i = 0; i < model->num_counters; i++) {
-		struct dentry *dir;
-		char buf[4];
-
-		snprintf(buf, sizeof(buf), "%d", i);
-		dir = oprofilefs_mkdir(sb, root, buf);
-
-		ret |= oprofilefs_create_ulong(sb, dir, "enabled", &ctr[i].enabled);
-		ret |= oprofilefs_create_ulong(sb, dir, "event", &ctr[i].event);
-		ret |= oprofilefs_create_ulong(sb, dir, "kernel", &ctr[i].kernel);
-		ret |= oprofilefs_create_ulong(sb, dir, "user", &ctr[i].user);
-
-		if (model->create_files)
-			ret |= model->create_files(sb, dir);
-		else
-			ret |= oprofilefs_create_ulong(sb, dir, "count", &ctr[i].count);
-
-		/* Dummy entries */
-		ret |= oprofilefs_create_ulong(sb, dir, "unit_mask", &ctr[i].unit_mask);
-	}
-
-	return ret;
-}
-
-static int op_sh_start(void)
-{
-	/* Enable performance monitoring for all counters.  */
-	on_each_cpu(model->cpu_start, NULL, 1);
-
-	return 0;
-}
-
-static void op_sh_stop(void)
-{
-	/* Disable performance monitoring for all counters.  */
-	on_each_cpu(model->cpu_stop, NULL, 1);
 }
 
 int __init oprofile_arch_init(struct oprofile_operations *ops)
 {
-	struct op_sh_model *lmodel = NULL;
-	int ret;
-
-	/*
-	 * Always assign the backtrace op. If the counter initialization
-	 * fails, we fall back to the timer which will still make use of
-	 * this.
-	 */
 	ops->backtrace = sh_backtrace;
 
-	/*
+	return oprofile_perf_init(ops);
-	 * XXX
-	 *
-	 * All of the SH7750/SH-4A counters have been converted to perf,
-	 * this infrastructure hook is left for other users until they've
-	 * had a chance to convert over, at which point all of this
-	 * will be deleted.
-	 */
-
-	if (!lmodel)
-		return -ENODEV;
-	if (!(current_cpu_data.flags & CPU_HAS_PERF_COUNTER))
-		return -ENODEV;
-
-	ret = lmodel->init();
-	if (unlikely(ret != 0))
-		return ret;
-
-	model = lmodel;
-
-	ops->setup		= op_sh_setup;
-	ops->create_files	= op_sh_create_files;
-	ops->start		= op_sh_start;
-	ops->stop		= op_sh_stop;
-	ops->cpu_type		= lmodel->cpu_type;
-
-	printk(KERN_INFO "oprofile: using %s performance monitoring.\n",
-	       lmodel->cpu_type);
-
-	return 0;
 }
 
-void oprofile_arch_exit(void)
+void __exit oprofile_arch_exit(void)
 {
-	if (model && model->exit)
+	oprofile_perf_exit();
-		model->exit();
 }
+#else
+int __init oprofile_arch_init(struct oprofile_operations *ops)
+{
+	pr_info("oprofile: hardware counters not available\n");
+	return -ENODEV;
+}
+void __exit oprofile_arch_exit(void) {}
+#endif /* CONFIG_HW_PERF_EVENTS */

arch/sh/oprofile/op_impl.h

@@ -1,33 +0,0 @@
-#ifndef __OP_IMPL_H
-#define __OP_IMPL_H
-
-/* Per-counter configuration as set via oprofilefs.  */
-struct op_counter_config {
-	unsigned long enabled;
-	unsigned long event;
-
-	unsigned long count;
-
-	/* Dummy values for userspace tool compliance */
-	unsigned long kernel;
-	unsigned long user;
-	unsigned long unit_mask;
-};
-
-/* Per-architecture configury and hooks.  */
-struct op_sh_model {
-	void (*reg_setup)(struct op_counter_config *);
-	int (*create_files)(struct super_block *sb, struct dentry *dir);
-	void (*cpu_setup)(void *dummy);
-	int (*init)(void);
-	void (*exit)(void);
-	void (*cpu_start)(void *args);
-	void (*cpu_stop)(void *args);
-	char *cpu_type;
-	unsigned char num_counters;
-};
-
-/* arch/sh/oprofile/common.c */
-extern void sh_backtrace(struct pt_regs * const regs, unsigned int depth);
-
-#endif /* __OP_IMPL_H */

arch/sparc/Kconfig

@@ -26,10 +26,12 @@ config SPARC
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select RTC_CLASS
 	select RTC_DRV_M48T59
+	select HAVE_IRQ_WORK
 	select HAVE_PERF_EVENTS
 	select PERF_USE_VMALLOC
 	select HAVE_DMA_ATTRS
 	select HAVE_DMA_API_DEBUG
+	select HAVE_ARCH_JUMP_LABEL
 
 config SPARC32
 	def_bool !64BIT
@@ -53,6 +55,7 @@ config SPARC64
 	select RTC_DRV_BQ4802
 	select RTC_DRV_SUN4V
 	select RTC_DRV_STARFIRE
+	select HAVE_IRQ_WORK
 	select HAVE_PERF_EVENTS
 	select PERF_USE_VMALLOC
 

arch/sparc/include/asm/jump_label.h

@@ -0,0 +1,32 @@
+#ifndef _ASM_SPARC_JUMP_LABEL_H
+#define _ASM_SPARC_JUMP_LABEL_H
+
+#ifdef __KERNEL__
+
+#include <linux/types.h>
+#include <asm/system.h>
+
+#define JUMP_LABEL_NOP_SIZE 4
+
+#define JUMP_LABEL(key, label)					\
+	do {							\
+		asm goto("1:\n\t"				\
+			 "nop\n\t"				\
+			 "nop\n\t"				\
+			 ".pushsection __jump_table,  \"a\"\n\t"\
+			 ".word 1b, %l[" #label "], %c0\n\t"	\
+			 ".popsection \n\t"			\
+			 : :  "i" (key) :  : label);\
+	} while (0)
+
+#endif /* __KERNEL__ */
+
+typedef u32 jump_label_t;
+
+struct jump_entry {
+	jump_label_t code;
+	jump_label_t target;
+	jump_label_t key;
+};
+
+#endif

arch/sparc/include/asm/perf_event.h

@@ -1,10 +1,6 @@
 #ifndef __ASM_SPARC_PERF_EVENT_H
 #define __ASM_SPARC_PERF_EVENT_H
 
-extern void set_perf_event_pending(void);
-
-#define	PERF_EVENT_INDEX_OFFSET	0
-
 #ifdef CONFIG_PERF_EVENTS
 #include <asm/ptrace.h>
 

arch/sparc/kernel/Makefile

@@ -119,3 +119,5 @@ obj-$(CONFIG_COMPAT)    += $(audit--y)
 
 pc--$(CONFIG_PERF_EVENTS) := perf_event.o
 obj-$(CONFIG_SPARC64)	+= $(pc--y)
+
+obj-$(CONFIG_SPARC64)	+= jump_label.o

arch/sparc/kernel/jump_label.c

@@ -0,0 +1,47 @@
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/mutex.h>
+#include <linux/cpu.h>
+
+#include <linux/jump_label.h>
+#include <linux/memory.h>
+
+#ifdef HAVE_JUMP_LABEL
+
+void arch_jump_label_transform(struct jump_entry *entry,
+			       enum jump_label_type type)
+{
+	u32 val;
+	u32 *insn = (u32 *) (unsigned long) entry->code;
+
+	if (type == JUMP_LABEL_ENABLE) {
+		s32 off = (s32)entry->target - (s32)entry->code;
+
+#ifdef CONFIG_SPARC64
+		/* ba,pt %xcc, . + (off << 2) */
+		val = 0x10680000 | ((u32) off >> 2);
+#else
+		/* ba . + (off << 2) */
+		val = 0x10800000 | ((u32) off >> 2);
+#endif
+	} else {
+		val = 0x01000000;
+	}
+
+	get_online_cpus();
+	mutex_lock(&text_mutex);
+	*insn = val;
+	flushi(insn);
+	mutex_unlock(&text_mutex);
+	put_online_cpus();
+}
+
+void arch_jump_label_text_poke_early(jump_label_t addr)
+{
+	u32 *insn_p = (u32 *) (unsigned long) addr;
+
+	*insn_p = 0x01000000;
+	flushi(insn_p);
+}
+
+#endif

arch/sparc/kernel/module.c

@@ -18,6 +18,9 @@
 #include <asm/spitfire.h>
 
 #ifdef CONFIG_SPARC64
+
+#include <linux/jump_label.h>
+
 static void *module_map(unsigned long size)
 {
 	struct vm_struct *area;
@@ -227,6 +230,9 @@ int module_finalize(const Elf_Ehdr *hdr,
 		    const Elf_Shdr *sechdrs,
 		    struct module *me)
 {
+	/* make jump label nops */
+	jump_label_apply_nops(me);
+
 	/* Cheetah's I-cache is fully coherent.  */
 	if (tlb_type == spitfire) {
 		unsigned long va;

arch/sparc/kernel/pcr.c

@@ -7,7 +7,7 @@
 #include <linux/init.h>
 #include <linux/irq.h>
 
-#include <linux/perf_event.h>
+#include <linux/irq_work.h>
 #include <linux/ftrace.h>
 
 #include <asm/pil.h>
@@ -43,14 +43,14 @@ void __irq_entry deferred_pcr_work_irq(int irq, struct pt_regs *regs)
 
 	old_regs = set_irq_regs(regs);
 	irq_enter();
-#ifdef CONFIG_PERF_EVENTS
+#ifdef CONFIG_IRQ_WORK
-	perf_event_do_pending();
+	irq_work_run();
 #endif
 	irq_exit();
 	set_irq_regs(old_regs);
 }
 
-void set_perf_event_pending(void)
+void arch_irq_work_raise(void)
 {
 	set_softint(1 << PIL_DEFERRED_PCR_WORK);
 }

arch/sparc/kernel/perf_event.c

@@ -658,13 +658,16 @@ static u64 maybe_change_configuration(struct cpu_hw_events *cpuc, u64 pcr)
 
 		enc = perf_event_get_enc(cpuc->events[i]);
 		pcr &= ~mask_for_index(idx);
-		pcr |= event_encoding(enc, idx);
+		if (hwc->state & PERF_HES_STOPPED)
+			pcr |= nop_for_index(idx);
+		else
+			pcr |= event_encoding(enc, idx);
 	}
 out:
 	return pcr;
 }
 
-void hw_perf_enable(void)
+static void sparc_pmu_enable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	u64 pcr;
@@ -691,7 +694,7 @@ void hw_perf_enable(void)
 	pcr_ops->write(cpuc->pcr);
 }
 
-void hw_perf_disable(void)
+static void sparc_pmu_disable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	u64 val;
@@ -710,48 +713,6 @@ void hw_perf_disable(void)
 	pcr_ops->write(cpuc->pcr);
 }
 
-static void sparc_pmu_disable(struct perf_event *event)
-{
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-	struct hw_perf_event *hwc = &event->hw;
-	unsigned long flags;
-	int i;
-
-	local_irq_save(flags);
-	perf_disable();
-
-	for (i = 0; i < cpuc->n_events; i++) {
-		if (event == cpuc->event[i]) {
-			int idx = cpuc->current_idx[i];
-
-			/* Shift remaining entries down into
-			 * the existing slot.
-			 */
-			while (++i < cpuc->n_events) {
-				cpuc->event[i - 1] = cpuc->event[i];
-				cpuc->events[i - 1] = cpuc->events[i];
-				cpuc->current_idx[i - 1] =
-					cpuc->current_idx[i];
-			}
-
-			/* Absorb the final count and turn off the
-			 * event.
-			 */
-			sparc_pmu_disable_event(cpuc, hwc, idx);
-			barrier();
-			sparc_perf_event_update(event, hwc, idx);
-
-			perf_event_update_userpage(event);
-
-			cpuc->n_events--;
-			break;
-		}
-	}
-
-	perf_enable();
-	local_irq_restore(flags);
-}
-
 static int active_event_index(struct cpu_hw_events *cpuc,
 			      struct perf_event *event)
 {
@@ -765,6 +726,74 @@ static int active_event_index(struct cpu_hw_events *cpuc,
 	return cpuc->current_idx[i];
 }
 
+static void sparc_pmu_start(struct perf_event *event, int flags)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	int idx = active_event_index(cpuc, event);
+
+	if (flags & PERF_EF_RELOAD) {
+		WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));
+		sparc_perf_event_set_period(event, &event->hw, idx);
+	}
+
+	event->hw.state = 0;
+
+	sparc_pmu_enable_event(cpuc, &event->hw, idx);
+}
+
+static void sparc_pmu_stop(struct perf_event *event, int flags)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	int idx = active_event_index(cpuc, event);
+
+	if (!(event->hw.state & PERF_HES_STOPPED)) {
+		sparc_pmu_disable_event(cpuc, &event->hw, idx);
+		event->hw.state |= PERF_HES_STOPPED;
+	}
+
+	if (!(event->hw.state & PERF_HES_UPTODATE) && (flags & PERF_EF_UPDATE)) {
+		sparc_perf_event_update(event, &event->hw, idx);
+		event->hw.state |= PERF_HES_UPTODATE;
+	}
+}
+
+static void sparc_pmu_del(struct perf_event *event, int _flags)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	unsigned long flags;
+	int i;
+
+	local_irq_save(flags);
+	perf_pmu_disable(event->pmu);
+
+	for (i = 0; i < cpuc->n_events; i++) {
+		if (event == cpuc->event[i]) {
+			/* Absorb the final count and turn off the
+			 * event.
+			 */
+			sparc_pmu_stop(event, PERF_EF_UPDATE);
+
+			/* Shift remaining entries down into
+			 * the existing slot.
+			 */
+			while (++i < cpuc->n_events) {
+				cpuc->event[i - 1] = cpuc->event[i];
+				cpuc->events[i - 1] = cpuc->events[i];
+				cpuc->current_idx[i - 1] =
+					cpuc->current_idx[i];
+			}
+
+			perf_event_update_userpage(event);
+
+			cpuc->n_events--;
+			break;
+		}
+	}
+
+	perf_pmu_enable(event->pmu);
+	local_irq_restore(flags);
+}
+
 static void sparc_pmu_read(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
@@ -774,15 +803,6 @@ static void sparc_pmu_read(struct perf_event *event)
 	sparc_perf_event_update(event, hwc, idx);
 }
 
-static void sparc_pmu_unthrottle(struct perf_event *event)
-{
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-	int idx = active_event_index(cpuc, event);
-	struct hw_perf_event *hwc = &event->hw;
-
-	sparc_pmu_enable_event(cpuc, hwc, idx);
-}
-
 static atomic_t active_events = ATOMIC_INIT(0);
 static DEFINE_MUTEX(pmc_grab_mutex);
 
@@ -877,7 +897,7 @@ static int sparc_check_constraints(struct perf_event **evts,
 	if (!n_ev)
 		return 0;
 
-	if (n_ev > perf_max_events)
+	if (n_ev > MAX_HWEVENTS)
 		return -1;
 
 	msk0 = perf_event_get_msk(events[0]);
@@ -984,23 +1004,27 @@ static int collect_events(struct perf_event *group, int max_count,
 	return n;
 }
 
-static int sparc_pmu_enable(struct perf_event *event)
+static int sparc_pmu_add(struct perf_event *event, int ef_flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	int n0, ret = -EAGAIN;
 	unsigned long flags;
 
 	local_irq_save(flags);
-	perf_disable();
+	perf_pmu_disable(event->pmu);
 
 	n0 = cpuc->n_events;
-	if (n0 >= perf_max_events)
+	if (n0 >= MAX_HWEVENTS)
 		goto out;
 
 	cpuc->event[n0] = event;
 	cpuc->events[n0] = event->hw.event_base;
 	cpuc->current_idx[n0] = PIC_NO_INDEX;
 
+	event->hw.state = PERF_HES_UPTODATE;
+	if (!(ef_flags & PERF_EF_START))
+		event->hw.state |= PERF_HES_STOPPED;
+
 	/*
 	 * If group events scheduling transaction was started,
 	 * skip the schedulability test here, it will be peformed
@@ -1020,12 +1044,12 @@ nocheck:
 
 	ret = 0;
 out:
-	perf_enable();
+	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 	return ret;
 }
 
-static int __hw_perf_event_init(struct perf_event *event)
+static int sparc_pmu_event_init(struct perf_event *event)
 {
 	struct perf_event_attr *attr = &event->attr;
 	struct perf_event *evts[MAX_HWEVENTS];
@@ -1038,22 +1062,33 @@ static int __hw_perf_event_init(struct perf_event *event)
 	if (atomic_read(&nmi_active) < 0)
 		return -ENODEV;
 
-	pmap = NULL;
+	switch (attr->type) {
-	if (attr->type == PERF_TYPE_HARDWARE) {
+	case PERF_TYPE_HARDWARE:
 		if (attr->config >= sparc_pmu->max_events)
 			return -EINVAL;
 		pmap = sparc_pmu->event_map(attr->config);
-	} else if (attr->type == PERF_TYPE_HW_CACHE) {
+		break;
+
+	case PERF_TYPE_HW_CACHE:
 		pmap = sparc_map_cache_event(attr->config);
 		if (IS_ERR(pmap))
 			return PTR_ERR(pmap);
-	} else if (attr->type != PERF_TYPE_RAW)
+		break;
-		return -EOPNOTSUPP;
+
+	case PERF_TYPE_RAW:
+		pmap = NULL;
+		break;
+
+	default:
+		return -ENOENT;
+
+	}
 
 	if (pmap) {
 		hwc->event_base = perf_event_encode(pmap);
 	} else {
-		/* User gives us "(encoding << 16) | pic_mask" for
+		/*
+		 * User gives us "(encoding << 16) | pic_mask" for
 		 * PERF_TYPE_RAW events.
 		 */
 		hwc->event_base = attr->config;
@@ -1071,7 +1106,7 @@ static int __hw_perf_event_init(struct perf_event *event)
 	n = 0;
 	if (event->group_leader != event) {
 		n = collect_events(event->group_leader,
-				   perf_max_events - 1,
+				   MAX_HWEVENTS - 1,
 				   evts, events, current_idx_dmy);
 		if (n < 0)
 			return -EINVAL;
@@ -1107,10 +1142,11 @@ static int __hw_perf_event_init(struct perf_event *event)
  * Set the flag to make pmu::enable() not perform the
  * schedulability test, it will be performed at commit time
  */
-static void sparc_pmu_start_txn(const struct pmu *pmu)
+static void sparc_pmu_start_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
+	perf_pmu_disable(pmu);
 	cpuhw->group_flag |= PERF_EVENT_TXN;
 }
 
@@ -1119,11 +1155,12 @@ static void sparc_pmu_start_txn(const struct pmu *pmu)
  * Clear the flag and pmu::enable() will perform the
  * schedulability test.
  */
-static void sparc_pmu_cancel_txn(const struct pmu *pmu)
+static void sparc_pmu_cancel_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
 	cpuhw->group_flag &= ~PERF_EVENT_TXN;
+	perf_pmu_enable(pmu);
 }
 
 /*
@@ -1131,7 +1168,7 @@ static void sparc_pmu_cancel_txn(const struct pmu *pmu)
  * Perform the group schedulability test as a whole
  * Return 0 if success
  */
-static int sparc_pmu_commit_txn(const struct pmu *pmu)
+static int sparc_pmu_commit_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	int n;
@@ -1147,28 +1184,24 @@ static int sparc_pmu_commit_txn(const struct pmu *pmu)
 		return -EAGAIN;
 
 	cpuc->group_flag &= ~PERF_EVENT_TXN;
+	perf_pmu_enable(pmu);
 	return 0;
 }
 
-static const struct pmu pmu = {
+static struct pmu pmu = {
-	.enable		= sparc_pmu_enable,
+	.pmu_enable	= sparc_pmu_enable,
-	.disable	= sparc_pmu_disable,
+	.pmu_disable	= sparc_pmu_disable,
+	.event_init	= sparc_pmu_event_init,
+	.add		= sparc_pmu_add,
+	.del		= sparc_pmu_del,
+	.start		= sparc_pmu_start,
+	.stop		= sparc_pmu_stop,
 	.read		= sparc_pmu_read,
-	.unthrottle	= sparc_pmu_unthrottle,
 	.start_txn	= sparc_pmu_start_txn,
 	.cancel_txn	= sparc_pmu_cancel_txn,
 	.commit_txn	= sparc_pmu_commit_txn,
 };
 
-const struct pmu *hw_perf_event_init(struct perf_event *event)
-{
-	int err = __hw_perf_event_init(event);
-
-	if (err)
-		return ERR_PTR(err);
-	return &pmu;
-}
-
 void perf_event_print_debug(void)
 {
 	unsigned long flags;
@@ -1244,7 +1277,7 @@ static int __kprobes perf_event_nmi_handler(struct notifier_block *self,
 			continue;
 
 		if (perf_event_overflow(event, 1, &data, regs))
-			sparc_pmu_disable_event(cpuc, hwc, idx);
+			sparc_pmu_stop(event, 0);
 	}
 
 	return NOTIFY_STOP;
@@ -1285,28 +1318,21 @@ void __init init_hw_perf_events(void)
 
 	pr_cont("Supported PMU type is '%s'\n", sparc_pmu_type);
 
-	/* All sparc64 PMUs currently have 2 events.  */
+	perf_pmu_register(&pmu);
-	perf_max_events = 2;
-
 	register_die_notifier(&perf_event_nmi_notifier);
 }
 
-static inline void callchain_store(struct perf_callchain_entry *entry, u64 ip)
+void perf_callchain_kernel(struct perf_callchain_entry *entry,
-{
+			   struct pt_regs *regs)
-	if (entry->nr < PERF_MAX_STACK_DEPTH)
-		entry->ip[entry->nr++] = ip;
-}
-
-static void perf_callchain_kernel(struct pt_regs *regs,
-				  struct perf_callchain_entry *entry)
 {
 	unsigned long ksp, fp;
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	int graph = 0;
 #endif
 
-	callchain_store(entry, PERF_CONTEXT_KERNEL);
+	stack_trace_flush();
-	callchain_store(entry, regs->tpc);
+
+	perf_callchain_store(entry, regs->tpc);
 
 	ksp = regs->u_regs[UREG_I6];
 	fp = ksp + STACK_BIAS;
@@ -1330,13 +1356,13 @@ static void perf_callchain_kernel(struct pt_regs *regs,
 			pc = sf->callers_pc;
 			fp = (unsigned long)sf->fp + STACK_BIAS;
 		}
-		callchain_store(entry, pc);
+		perf_callchain_store(entry, pc);
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 		if ((pc + 8UL) == (unsigned long) &return_to_handler) {
 			int index = current->curr_ret_stack;
 			if (current->ret_stack && index >= graph) {
 				pc = current->ret_stack[index - graph].ret;
-				callchain_store(entry, pc);
+				perf_callchain_store(entry, pc);
 				graph++;
 			}
 		}
@@ -1344,13 +1370,12 @@ static void perf_callchain_kernel(struct pt_regs *regs,
 	} while (entry->nr < PERF_MAX_STACK_DEPTH);
 }
 
-static void perf_callchain_user_64(struct pt_regs *regs,
+static void perf_callchain_user_64(struct perf_callchain_entry *entry,
-				   struct perf_callchain_entry *entry)
+				   struct pt_regs *regs)
 {
 	unsigned long ufp;
 
-	callchain_store(entry, PERF_CONTEXT_USER);
+	perf_callchain_store(entry, regs->tpc);
-	callchain_store(entry, regs->tpc);
 
 	ufp = regs->u_regs[UREG_I6] + STACK_BIAS;
 	do {
@@ -1363,17 +1388,16 @@ static void perf_callchain_user_64(struct pt_regs *regs,
 
 		pc = sf.callers_pc;
 		ufp = (unsigned long)sf.fp + STACK_BIAS;
-		callchain_store(entry, pc);
+		perf_callchain_store(entry, pc);
 	} while (entry->nr < PERF_MAX_STACK_DEPTH);
 }
 
-static void perf_callchain_user_32(struct pt_regs *regs,
+static void perf_callchain_user_32(struct perf_callchain_entry *entry,
-				   struct perf_callchain_entry *entry)
+				   struct pt_regs *regs)
 {
 	unsigned long ufp;
 
-	callchain_store(entry, PERF_CONTEXT_USER);
+	perf_callchain_store(entry, regs->tpc);
-	callchain_store(entry, regs->tpc);
 
 	ufp = regs->u_regs[UREG_I6] & 0xffffffffUL;
 	do {
@@ -1386,34 +1410,16 @@ static void perf_callchain_user_32(struct pt_regs *regs,
 
 		pc = sf.callers_pc;
 		ufp = (unsigned long)sf.fp;
-		callchain_store(entry, pc);
+		perf_callchain_store(entry, pc);
 	} while (entry->nr < PERF_MAX_STACK_DEPTH);
 }
 
-/* Like powerpc we can't get PMU interrupts within the PMU handler,
+void
- * so no need for separate NMI and IRQ chains as on x86.
+perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
- */
-static DEFINE_PER_CPU(struct perf_callchain_entry, callchain);
-
-struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
 {
-	struct perf_callchain_entry *entry = &__get_cpu_var(callchain);
+	flushw_user();
-
+	if (test_thread_flag(TIF_32BIT))
-	entry->nr = 0;
+		perf_callchain_user_32(entry, regs);
-	if (!user_mode(regs)) {
+	else
-		stack_trace_flush();
+		perf_callchain_user_64(entry, regs);
-		perf_callchain_kernel(regs, entry);
-		if (current->mm)
-			regs = task_pt_regs(current);
-		else
-			regs = NULL;
-	}
-	if (regs) {
-		flushw_user();
-		if (test_thread_flag(TIF_32BIT))
-			perf_callchain_user_32(regs, entry);
-		else
-			perf_callchain_user_64(regs, entry);
-	}
-	return entry;
 }

arch/x86/Kconfig

@@ -25,6 +25,7 @@ config X86
 	select HAVE_IDE
 	select HAVE_OPROFILE
 	select HAVE_PERF_EVENTS if (!M386 && !M486)
+	select HAVE_IRQ_WORK
 	select HAVE_IOREMAP_PROT
 	select HAVE_KPROBES
 	select ARCH_WANT_OPTIONAL_GPIOLIB
@@ -33,6 +34,7 @@ config X86
 	select HAVE_KRETPROBES
 	select HAVE_OPTPROBES
 	select HAVE_FTRACE_MCOUNT_RECORD
+	select HAVE_C_RECORDMCOUNT
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_GRAPH_TRACER
@@ -59,6 +61,8 @@ config X86
 	select ANON_INODES
 	select HAVE_ARCH_KMEMCHECK
 	select HAVE_USER_RETURN_NOTIFIER
+	select HAVE_ARCH_JUMP_LABEL
+	select HAVE_TEXT_POKE_SMP
 
 config INSTRUCTION_DECODER
 	def_bool (KPROBES || PERF_EVENTS)
@@ -2125,6 +2129,10 @@ config HAVE_ATOMIC_IOMAP
 	def_bool y
 	depends on X86_32
 
+config HAVE_TEXT_POKE_SMP
+	bool
+	select STOP_MACHINE if SMP
+
 source "net/Kconfig"
 
 source "drivers/Kconfig"

arch/x86/include/asm/alternative.h

@@ -4,6 +4,7 @@
 #include <linux/types.h>
 #include <linux/stddef.h>
 #include <linux/stringify.h>
+#include <linux/jump_label.h>
 #include <asm/asm.h>
 
 /*
@@ -160,6 +161,8 @@ static inline void apply_paravirt(struct paravirt_patch_site *start,
 #define __parainstructions_end	NULL
 #endif
 
+extern void *text_poke_early(void *addr, const void *opcode, size_t len);
+
 /*
  * Clear and restore the kernel write-protection flag on the local CPU.
  * Allows the kernel to edit read-only pages.
@@ -180,4 +183,12 @@ static inline void apply_paravirt(struct paravirt_patch_site *start,
 extern void *text_poke(void *addr, const void *opcode, size_t len);
 extern void *text_poke_smp(void *addr, const void *opcode, size_t len);
 
+#if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL)
+#define IDEAL_NOP_SIZE_5 5
+extern unsigned char ideal_nop5[IDEAL_NOP_SIZE_5];
+extern void arch_init_ideal_nop5(void);
+#else
+static inline void arch_init_ideal_nop5(void) {}
+#endif
+
 #endif /* _ASM_X86_ALTERNATIVE_H */

arch/x86/include/asm/entry_arch.h

@@ -49,8 +49,8 @@ BUILD_INTERRUPT(apic_timer_interrupt,LOCAL_TIMER_VECTOR)
 BUILD_INTERRUPT(error_interrupt,ERROR_APIC_VECTOR)
 BUILD_INTERRUPT(spurious_interrupt,SPURIOUS_APIC_VECTOR)
 
-#ifdef CONFIG_PERF_EVENTS
+#ifdef CONFIG_IRQ_WORK
-BUILD_INTERRUPT(perf_pending_interrupt, LOCAL_PENDING_VECTOR)
+BUILD_INTERRUPT(irq_work_interrupt, IRQ_WORK_VECTOR)
 #endif
 
 #ifdef CONFIG_X86_THERMAL_VECTOR

arch/x86/include/asm/hardirq.h

@@ -14,7 +14,7 @@ typedef struct {
 #endif
 	unsigned int x86_platform_ipis;	/* arch dependent */
 	unsigned int apic_perf_irqs;
-	unsigned int apic_pending_irqs;
+	unsigned int apic_irq_work_irqs;
 #ifdef CONFIG_SMP
 	unsigned int irq_resched_count;
 	unsigned int irq_call_count;

arch/x86/include/asm/hw_irq.h

@@ -29,7 +29,7 @@
 extern void apic_timer_interrupt(void);
 extern void x86_platform_ipi(void);
 extern void error_interrupt(void);
-extern void perf_pending_interrupt(void);
+extern void irq_work_interrupt(void);
 
 extern void spurious_interrupt(void);
 extern void thermal_interrupt(void);

arch/x86/include/asm/irq_vectors.h

@@ -114,9 +114,9 @@
 #define X86_PLATFORM_IPI_VECTOR		0xed
 
 /*
- * Performance monitoring pending work vector:
+ * IRQ work vector:
  */
-#define LOCAL_PENDING_VECTOR		0xec
+#define IRQ_WORK_VECTOR			0xec
 
 #define UV_BAU_MESSAGE			0xea
 

arch/x86/include/asm/jump_label.h

@@ -0,0 +1,37 @@
+#ifndef _ASM_X86_JUMP_LABEL_H
+#define _ASM_X86_JUMP_LABEL_H
+
+#ifdef __KERNEL__
+
+#include <linux/types.h>
+#include <asm/nops.h>
+
+#define JUMP_LABEL_NOP_SIZE 5
+
+# define JUMP_LABEL_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t"
+
+# define JUMP_LABEL(key, label)					\
+	do {							\
+		asm goto("1:"					\
+			JUMP_LABEL_INITIAL_NOP			\
+			".pushsection __jump_table,  \"a\" \n\t"\
+			_ASM_PTR "1b, %l[" #label "], %c0 \n\t" \
+			".popsection \n\t"			\
+			: :  "i" (key) :  : label);		\
+	} while (0)
+
+#endif /* __KERNEL__ */
+
+#ifdef CONFIG_X86_64
+typedef u64 jump_label_t;
+#else
+typedef u32 jump_label_t;
+#endif
+
+struct jump_entry {
+	jump_label_t code;
+	jump_label_t target;
+	jump_label_t key;
+};
+
+#endif

arch/x86/include/asm/perf_event_p4.h

@@ -36,19 +36,6 @@
 #define P4_ESCR_EMASK(v)	((v) << P4_ESCR_EVENTMASK_SHIFT)
 #define P4_ESCR_TAG(v)		((v) << P4_ESCR_TAG_SHIFT)
 
-/* Non HT mask */
-#define P4_ESCR_MASK			\
-	(P4_ESCR_EVENT_MASK	|	\
-	P4_ESCR_EVENTMASK_MASK	|	\
-	P4_ESCR_TAG_MASK	|	\
-	P4_ESCR_TAG_ENABLE	|	\
-	P4_ESCR_T0_OS		|	\
-	P4_ESCR_T0_USR)
-
-/* HT mask */
-#define P4_ESCR_MASK_HT			\
-	(P4_ESCR_MASK |	P4_ESCR_T1_OS | P4_ESCR_T1_USR)
-
 #define P4_CCCR_OVF			0x80000000U
 #define P4_CCCR_CASCADE			0x40000000U
 #define P4_CCCR_OVF_PMI_T0		0x04000000U
@@ -70,23 +57,6 @@
 #define P4_CCCR_THRESHOLD(v)		((v) << P4_CCCR_THRESHOLD_SHIFT)
 #define P4_CCCR_ESEL(v)			((v) << P4_CCCR_ESCR_SELECT_SHIFT)
 
-/* Non HT mask */
-#define P4_CCCR_MASK				\
-	(P4_CCCR_OVF			|	\
-	P4_CCCR_CASCADE			|	\
-	P4_CCCR_OVF_PMI_T0		|	\
-	P4_CCCR_FORCE_OVF		|	\
-	P4_CCCR_EDGE			|	\
-	P4_CCCR_THRESHOLD_MASK		|	\
-	P4_CCCR_COMPLEMENT		|	\
-	P4_CCCR_COMPARE			|	\
-	P4_CCCR_ESCR_SELECT_MASK	|	\
-	P4_CCCR_ENABLE)
-
-/* HT mask */
-#define P4_CCCR_MASK_HT				\
-	(P4_CCCR_MASK | P4_CCCR_OVF_PMI_T1 | P4_CCCR_THREAD_ANY)
-
 #define P4_GEN_ESCR_EMASK(class, name, bit)	\
 	class##__##name = ((1 << bit) << P4_ESCR_EVENTMASK_SHIFT)
 #define P4_ESCR_EMASK_BIT(class, name)		class##__##name
@@ -127,6 +97,28 @@
 #define P4_CONFIG_HT_SHIFT		63
 #define P4_CONFIG_HT			(1ULL << P4_CONFIG_HT_SHIFT)
 
+/*
+ * The bits we allow to pass for RAW events
+ */
+#define P4_CONFIG_MASK_ESCR		\
+	P4_ESCR_EVENT_MASK	|	\
+	P4_ESCR_EVENTMASK_MASK	|	\
+	P4_ESCR_TAG_MASK	|	\
+	P4_ESCR_TAG_ENABLE
+
+#define P4_CONFIG_MASK_CCCR		\
+	P4_CCCR_EDGE		|	\
+	P4_CCCR_THRESHOLD_MASK	|	\
+	P4_CCCR_COMPLEMENT	|	\
+	P4_CCCR_COMPARE		|	\
+	P4_CCCR_THREAD_ANY	|	\
+	P4_CCCR_RESERVED
+
+/* some dangerous bits are reserved for kernel internals */
+#define P4_CONFIG_MASK				  	  \
+	(p4_config_pack_escr(P4_CONFIG_MASK_ESCR))	| \
+	(p4_config_pack_cccr(P4_CONFIG_MASK_CCCR))
+
 static inline bool p4_is_event_cascaded(u64 config)
 {
 	u32 cccr = p4_config_unpack_cccr(config);

arch/x86/kernel/Makefile

@@ -34,7 +34,8 @@ GCOV_PROFILE_paravirt.o		:= n
 obj-y			:= process_$(BITS).o signal.o entry_$(BITS).o
 obj-y			+= traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
 obj-y			+= time.o ioport.o ldt.o dumpstack.o
-obj-y			+= setup.o x86_init.o i8259.o irqinit.o
+obj-y			+= setup.o x86_init.o i8259.o irqinit.o jump_label.o
+obj-$(CONFIG_IRQ_WORK)  += irq_work.o
 obj-$(CONFIG_X86_VISWS)	+= visws_quirks.o
 obj-$(CONFIG_X86_32)	+= probe_roms_32.o
 obj-$(CONFIG_X86_32)	+= sys_i386_32.o i386_ksyms_32.o

arch/x86/kernel/alternative.c

@@ -195,7 +195,7 @@ static void __init_or_module add_nops(void *insns, unsigned int len)
 
 extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
 extern s32 __smp_locks[], __smp_locks_end[];
-static void *text_poke_early(void *addr, const void *opcode, size_t len);
+void *text_poke_early(void *addr, const void *opcode, size_t len);
 
 /* Replace instructions with better alternatives for this CPU type.
    This runs before SMP is initialized to avoid SMP problems with
@@ -522,7 +522,7 @@ void __init alternative_instructions(void)
  * instructions. And on the local CPU you need to be protected again NMI or MCE
  * handlers seeing an inconsistent instruction while you patch.
  */
-static void *__init_or_module text_poke_early(void *addr, const void *opcode,
+void *__init_or_module text_poke_early(void *addr, const void *opcode,
 					      size_t len)
 {
 	unsigned long flags;
@@ -637,7 +637,72 @@ void *__kprobes text_poke_smp(void *addr, const void *opcode, size_t len)
 	tpp.len = len;
 	atomic_set(&stop_machine_first, 1);
 	wrote_text = 0;
-	stop_machine(stop_machine_text_poke, (void *)&tpp, NULL);
+	/* Use __stop_machine() because the caller already got online_cpus. */
+	__stop_machine(stop_machine_text_poke, (void *)&tpp, NULL);
 	return addr;
 }
 
+#if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL)
+
+unsigned char ideal_nop5[IDEAL_NOP_SIZE_5];
+
+void __init arch_init_ideal_nop5(void)
+{
+	extern const unsigned char ftrace_test_p6nop[];
+	extern const unsigned char ftrace_test_nop5[];
+	extern const unsigned char ftrace_test_jmp[];
+	int faulted = 0;
+
+	/*
+	 * There is no good nop for all x86 archs.
+	 * We will default to using the P6_NOP5, but first we
+	 * will test to make sure that the nop will actually
+	 * work on this CPU. If it faults, we will then
+	 * go to a lesser efficient 5 byte nop. If that fails
+	 * we then just use a jmp as our nop. This isn't the most
+	 * efficient nop, but we can not use a multi part nop
+	 * since we would then risk being preempted in the middle
+	 * of that nop, and if we enabled tracing then, it might
+	 * cause a system crash.
+	 *
+	 * TODO: check the cpuid to determine the best nop.
+	 */
+	asm volatile (
+		"ftrace_test_jmp:"
+		"jmp ftrace_test_p6nop\n"
+		"nop\n"
+		"nop\n"
+		"nop\n"  /* 2 byte jmp + 3 bytes */
+		"ftrace_test_p6nop:"
+		P6_NOP5
+		"jmp 1f\n"
+		"ftrace_test_nop5:"
+		".byte 0x66,0x66,0x66,0x66,0x90\n"
+		"1:"
+		".section .fixup, \"ax\"\n"
+		"2:	movl $1, %0\n"
+		"	jmp ftrace_test_nop5\n"
+		"3:	movl $2, %0\n"
+		"	jmp 1b\n"
+		".previous\n"
+		_ASM_EXTABLE(ftrace_test_p6nop, 2b)
+		_ASM_EXTABLE(ftrace_test_nop5, 3b)
+		: "=r"(faulted) : "0" (faulted));
+
+	switch (faulted) {
+	case 0:
+		pr_info("converting mcount calls to 0f 1f 44 00 00\n");
+		memcpy(ideal_nop5, ftrace_test_p6nop, IDEAL_NOP_SIZE_5);
+		break;
+	case 1:
+		pr_info("converting mcount calls to 66 66 66 66 90\n");
+		memcpy(ideal_nop5, ftrace_test_nop5, IDEAL_NOP_SIZE_5);
+		break;
+	case 2:
+		pr_info("converting mcount calls to jmp . + 5\n");
+		memcpy(ideal_nop5, ftrace_test_jmp, IDEAL_NOP_SIZE_5);
+		break;
+	}
+
+}
+#endif

arch/x86/kernel/cpu/perf_event.c

@@ -531,7 +531,7 @@ static int x86_pmu_hw_config(struct perf_event *event)
 /*
  * Setup the hardware configuration for a given attr_type
  */
-static int __hw_perf_event_init(struct perf_event *event)
+static int __x86_pmu_event_init(struct perf_event *event)
 {
 	int err;
 
@@ -584,7 +584,7 @@ static void x86_pmu_disable_all(void)
 	}
 }
 
-void hw_perf_disable(void)
+static void x86_pmu_disable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
@@ -619,7 +619,7 @@ static void x86_pmu_enable_all(int added)
 	}
 }
 
-static const struct pmu pmu;
+static struct pmu pmu;
 
 static inline int is_x86_event(struct perf_event *event)
 {
@@ -801,10 +801,10 @@ static inline int match_prev_assignment(struct hw_perf_event *hwc,
 		hwc->last_tag == cpuc->tags[i];
 }
 
-static int x86_pmu_start(struct perf_event *event);
+static void x86_pmu_start(struct perf_event *event, int flags);
-static void x86_pmu_stop(struct perf_event *event);
+static void x86_pmu_stop(struct perf_event *event, int flags);
 
-void hw_perf_enable(void)
+static void x86_pmu_enable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct perf_event *event;
@@ -840,7 +840,14 @@ void hw_perf_enable(void)
 			    match_prev_assignment(hwc, cpuc, i))
 				continue;
 
-			x86_pmu_stop(event);
+			/*
+			 * Ensure we don't accidentally enable a stopped
+			 * counter simply because we rescheduled.
+			 */
+			if (hwc->state & PERF_HES_STOPPED)
+				hwc->state |= PERF_HES_ARCH;
+
+			x86_pmu_stop(event, PERF_EF_UPDATE);
 		}
 
 		for (i = 0; i < cpuc->n_events; i++) {
@@ -852,7 +859,10 @@ void hw_perf_enable(void)
 			else if (i < n_running)
 				continue;
 
-			x86_pmu_start(event);
+			if (hwc->state & PERF_HES_ARCH)
+				continue;
+
+			x86_pmu_start(event, PERF_EF_RELOAD);
 		}
 		cpuc->n_added = 0;
 		perf_events_lapic_init();
@@ -953,15 +963,12 @@ static void x86_pmu_enable_event(struct perf_event *event)
 }
 
 /*
- * activate a single event
+ * Add a single event to the PMU.
  *
  * The event is added to the group of enabled events
  * but only if it can be scehduled with existing events.
- *
- * Called with PMU disabled. If successful and return value 1,
- * then guaranteed to call perf_enable() and hw_perf_enable()
  */
-static int x86_pmu_enable(struct perf_event *event)
+static int x86_pmu_add(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc;
@@ -970,58 +977,67 @@ static int x86_pmu_enable(struct perf_event *event)
 
 	hwc = &event->hw;
 
+	perf_pmu_disable(event->pmu);
 	n0 = cpuc->n_events;
-	n = collect_events(cpuc, event, false);
+	ret = n = collect_events(cpuc, event, false);
-	if (n < 0)
+	if (ret < 0)
-		return n;
+		goto out;
+
+	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+	if (!(flags & PERF_EF_START))
+		hwc->state |= PERF_HES_ARCH;
 
 	/*
 	 * If group events scheduling transaction was started,
 	 * skip the schedulability test here, it will be peformed
-	 * at commit time(->commit_txn) as a whole
+	 * at commit time (->commit_txn) as a whole
 	 */
 	if (cpuc->group_flag & PERF_EVENT_TXN)
-		goto out;
+		goto done_collect;
 
 	ret = x86_pmu.schedule_events(cpuc, n, assign);
 	if (ret)
-		return ret;
+		goto out;
 	/*
 	 * copy new assignment, now we know it is possible
 	 * will be used by hw_perf_enable()
 	 */
 	memcpy(cpuc->assign, assign, n*sizeof(int));
 
-out:
+done_collect:
 	cpuc->n_events = n;
 	cpuc->n_added += n - n0;
 	cpuc->n_txn += n - n0;
 
-	return 0;
+	ret = 0;
+out:
+	perf_pmu_enable(event->pmu);
+	return ret;
 }
 
-static int x86_pmu_start(struct perf_event *event)
+static void x86_pmu_start(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	int idx = event->hw.idx;
 
-	if (idx == -1)
+	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
-		return -EAGAIN;
+		return;
+
+	if (WARN_ON_ONCE(idx == -1))
+		return;
+
+	if (flags & PERF_EF_RELOAD) {
+		WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));
+		x86_perf_event_set_period(event);
+	}
+
+	event->hw.state = 0;
 
-	x86_perf_event_set_period(event);
 	cpuc->events[idx] = event;
 	__set_bit(idx, cpuc->active_mask);
 	__set_bit(idx, cpuc->running);
 	x86_pmu.enable(event);
 	perf_event_update_userpage(event);
-
-	return 0;
-}
-
-static void x86_pmu_unthrottle(struct perf_event *event)
-{
-	int ret = x86_pmu_start(event);
-	WARN_ON_ONCE(ret);
 }
 
 void perf_event_print_debug(void)
@@ -1078,27 +1094,29 @@ void perf_event_print_debug(void)
 	local_irq_restore(flags);
 }
 
-static void x86_pmu_stop(struct perf_event *event)
+static void x86_pmu_stop(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
-	int idx = hwc->idx;
 
-	if (!__test_and_clear_bit(idx, cpuc->active_mask))
+	if (__test_and_clear_bit(hwc->idx, cpuc->active_mask)) {
-		return;
+		x86_pmu.disable(event);
+		cpuc->events[hwc->idx] = NULL;
+		WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
+		hwc->state |= PERF_HES_STOPPED;
+	}
 
-	x86_pmu.disable(event);
+	if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
-
+		/*
-	/*
+		 * Drain the remaining delta count out of a event
-	 * Drain the remaining delta count out of a event
+		 * that we are disabling:
-	 * that we are disabling:
+		 */
-	 */
+		x86_perf_event_update(event);
-	x86_perf_event_update(event);
+		hwc->state |= PERF_HES_UPTODATE;
-
+	}
-	cpuc->events[idx] = NULL;
 }
 
-static void x86_pmu_disable(struct perf_event *event)
+static void x86_pmu_del(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	int i;
@@ -1111,7 +1129,7 @@ static void x86_pmu_disable(struct perf_event *event)
 	if (cpuc->group_flag & PERF_EVENT_TXN)
 		return;
 
-	x86_pmu_stop(event);
+	x86_pmu_stop(event, PERF_EF_UPDATE);
 
 	for (i = 0; i < cpuc->n_events; i++) {
 		if (event == cpuc->event_list[i]) {
@@ -1134,7 +1152,6 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
 	struct perf_sample_data data;
 	struct cpu_hw_events *cpuc;
 	struct perf_event *event;
-	struct hw_perf_event *hwc;
 	int idx, handled = 0;
 	u64 val;
 
@@ -1155,7 +1172,6 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
 		}
 
 		event = cpuc->events[idx];
-		hwc = &event->hw;
 
 		val = x86_perf_event_update(event);
 		if (val & (1ULL << (x86_pmu.cntval_bits - 1)))
@@ -1171,7 +1187,7 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
 			continue;
 
 		if (perf_event_overflow(event, 1, &data, regs))
-			x86_pmu_stop(event);
+			x86_pmu_stop(event, 0);
 	}
 
 	if (handled)
@@ -1180,25 +1196,6 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
 	return handled;
 }
 
-void smp_perf_pending_interrupt(struct pt_regs *regs)
-{
-	irq_enter();
-	ack_APIC_irq();
-	inc_irq_stat(apic_pending_irqs);
-	perf_event_do_pending();
-	irq_exit();
-}
-
-void set_perf_event_pending(void)
-{
-#ifdef CONFIG_X86_LOCAL_APIC
-	if (!x86_pmu.apic || !x86_pmu_initialized())
-		return;
-
-	apic->send_IPI_self(LOCAL_PENDING_VECTOR);
-#endif
-}
-
 void perf_events_lapic_init(void)
 {
 	if (!x86_pmu.apic || !x86_pmu_initialized())
@@ -1388,7 +1385,6 @@ void __init init_hw_perf_events(void)
 		x86_pmu.num_counters = X86_PMC_MAX_GENERIC;
 	}
 	x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1;
-	perf_max_events = x86_pmu.num_counters;
 
 	if (x86_pmu.num_counters_fixed > X86_PMC_MAX_FIXED) {
 		WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!",
@@ -1424,6 +1420,7 @@ void __init init_hw_perf_events(void)
 	pr_info("... fixed-purpose events:   %d\n",     x86_pmu.num_counters_fixed);
 	pr_info("... event mask:             %016Lx\n", x86_pmu.intel_ctrl);
 
+	perf_pmu_register(&pmu);
 	perf_cpu_notifier(x86_pmu_notifier);
 }
 
@@ -1437,10 +1434,11 @@ static inline void x86_pmu_read(struct perf_event *event)
  * Set the flag to make pmu::enable() not perform the
  * schedulability test, it will be performed at commit time
  */
-static void x86_pmu_start_txn(const struct pmu *pmu)
+static void x86_pmu_start_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
+	perf_pmu_disable(pmu);
 	cpuc->group_flag |= PERF_EVENT_TXN;
 	cpuc->n_txn = 0;
 }
@@ -1450,7 +1448,7 @@ static void x86_pmu_start_txn(const struct pmu *pmu)
  * Clear the flag and pmu::enable() will perform the
  * schedulability test.
  */
-static void x86_pmu_cancel_txn(const struct pmu *pmu)
+static void x86_pmu_cancel_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
@@ -1460,6 +1458,7 @@ static void x86_pmu_cancel_txn(const struct pmu *pmu)
 	 */
 	cpuc->n_added -= cpuc->n_txn;
 	cpuc->n_events -= cpuc->n_txn;
+	perf_pmu_enable(pmu);
 }
 
 /*
@@ -1467,7 +1466,7 @@ static void x86_pmu_cancel_txn(const struct pmu *pmu)
  * Perform the group schedulability test as a whole
  * Return 0 if success
  */
-static int x86_pmu_commit_txn(const struct pmu *pmu)
+static int x86_pmu_commit_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	int assign[X86_PMC_IDX_MAX];
@@ -1489,22 +1488,10 @@ static int x86_pmu_commit_txn(const struct pmu *pmu)
 	memcpy(cpuc->assign, assign, n*sizeof(int));
 
 	cpuc->group_flag &= ~PERF_EVENT_TXN;
-
+	perf_pmu_enable(pmu);
 	return 0;
 }
 
-static const struct pmu pmu = {
-	.enable		= x86_pmu_enable,
-	.disable	= x86_pmu_disable,
-	.start		= x86_pmu_start,
-	.stop		= x86_pmu_stop,
-	.read		= x86_pmu_read,
-	.unthrottle	= x86_pmu_unthrottle,
-	.start_txn	= x86_pmu_start_txn,
-	.cancel_txn	= x86_pmu_cancel_txn,
-	.commit_txn	= x86_pmu_commit_txn,
-};
-
 /*
  * validate that we can schedule this event
  */
@@ -1579,12 +1566,22 @@ out:
 	return ret;
 }
 
-const struct pmu *hw_perf_event_init(struct perf_event *event)
+int x86_pmu_event_init(struct perf_event *event)
 {
-	const struct pmu *tmp;
+	struct pmu *tmp;
 	int err;
 
-	err = __hw_perf_event_init(event);
+	switch (event->attr.type) {
+	case PERF_TYPE_RAW:
+	case PERF_TYPE_HARDWARE:
+	case PERF_TYPE_HW_CACHE:
+		break;
+
+	default:
+		return -ENOENT;
+	}
+
+	err = __x86_pmu_event_init(event);
 	if (!err) {
 		/*
 		 * we temporarily connect event to its pmu
@@ -1604,27 +1601,32 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 	if (err) {
 		if (event->destroy)
 			event->destroy(event);
-		return ERR_PTR(err);
 	}
 
-	return &pmu;
+	return err;
 }
 
+static struct pmu pmu = {
+	.pmu_enable	= x86_pmu_enable,
+	.pmu_disable	= x86_pmu_disable,
+
+	.event_init	= x86_pmu_event_init,
+
+	.add		= x86_pmu_add,
+	.del		= x86_pmu_del,
+	.start		= x86_pmu_start,
+	.stop		= x86_pmu_stop,
+	.read		= x86_pmu_read,
+
+	.start_txn	= x86_pmu_start_txn,
+	.cancel_txn	= x86_pmu_cancel_txn,
+	.commit_txn	= x86_pmu_commit_txn,
+};
+
 /*
  * callchain support
  */
 
-static inline
-void callchain_store(struct perf_callchain_entry *entry, u64 ip)
-{
-	if (entry->nr < PERF_MAX_STACK_DEPTH)
-		entry->ip[entry->nr++] = ip;
-}
-
-static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_irq_entry);
-static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_nmi_entry);
-
-
 static void
 backtrace_warning_symbol(void *data, char *msg, unsigned long symbol)
 {
@@ -1645,7 +1647,7 @@ static void backtrace_address(void *data, unsigned long addr, int reliable)
 {
 	struct perf_callchain_entry *entry = data;
 
-	callchain_store(entry, addr);
+	perf_callchain_store(entry, addr);
 }
 
 static const struct stacktrace_ops backtrace_ops = {
@@ -1656,11 +1658,15 @@ static const struct stacktrace_ops backtrace_ops = {
 	.walk_stack		= print_context_stack_bp,
 };
 
-static void
+void
-perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry)
+perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
-	callchain_store(entry, PERF_CONTEXT_KERNEL);
+	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
-	callchain_store(entry, regs->ip);
+		/* TODO: We don't support guest os callchain now */
+		return;
+	}
+
+	perf_callchain_store(entry, regs->ip);
 
 	dump_trace(NULL, regs, NULL, regs->bp, &backtrace_ops, entry);
 }
@@ -1689,7 +1695,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
 		if (fp < compat_ptr(regs->sp))
 			break;
 
-		callchain_store(entry, frame.return_address);
+		perf_callchain_store(entry, frame.return_address);
 		fp = compat_ptr(frame.next_frame);
 	}
 	return 1;
@@ -1702,19 +1708,20 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
 }
 #endif
 
-static void
+void
-perf_callchain_user(struct pt_regs *regs, struct perf_callchain_entry *entry)
+perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
 	struct stack_frame frame;
 	const void __user *fp;
 
-	if (!user_mode(regs))
+	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
-		regs = task_pt_regs(current);
+		/* TODO: We don't support guest os callchain now */
+		return;
+	}
 
 	fp = (void __user *)regs->bp;
 
-	callchain_store(entry, PERF_CONTEXT_USER);
+	perf_callchain_store(entry, regs->ip);
-	callchain_store(entry, regs->ip);
 
 	if (perf_callchain_user32(regs, entry))
 		return;
@@ -1731,52 +1738,11 @@ perf_callchain_user(struct pt_regs *regs, struct perf_callchain_entry *entry)
 		if ((unsigned long)fp < regs->sp)
 			break;
 
-		callchain_store(entry, frame.return_address);
+		perf_callchain_store(entry, frame.return_address);
 		fp = frame.next_frame;
 	}
 }
 
-static void
-perf_do_callchain(struct pt_regs *regs, struct perf_callchain_entry *entry)
-{
-	int is_user;
-
-	if (!regs)
-		return;
-
-	is_user = user_mode(regs);
-
-	if (is_user && current->state != TASK_RUNNING)
-		return;
-
-	if (!is_user)
-		perf_callchain_kernel(regs, entry);
-
-	if (current->mm)
-		perf_callchain_user(regs, entry);
-}
-
-struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
-{
-	struct perf_callchain_entry *entry;
-
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
-		/* TODO: We don't support guest os callchain now */
-		return NULL;
-	}
-
-	if (in_nmi())
-		entry = &__get_cpu_var(pmc_nmi_entry);
-	else
-		entry = &__get_cpu_var(pmc_irq_entry);
-
-	entry->nr = 0;
-
-	perf_do_callchain(regs, entry);
-
-	return entry;
-}
-
 unsigned long perf_instruction_pointer(struct pt_regs *regs)
 {
 	unsigned long ip;

arch/x86/kernel/cpu/perf_event_amd.c

@@ -52,7 +52,7 @@ static __initconst const u64 amd_hw_cache_event_ids
  [ C(DTLB) ] = {
 	[ C(OP_READ) ] = {
 		[ C(RESULT_ACCESS) ] = 0x0040, /* Data Cache Accesses        */
-		[ C(RESULT_MISS)   ] = 0x0046, /* L1 DTLB and L2 DLTB Miss   */
+		[ C(RESULT_MISS)   ] = 0x0746, /* L1_DTLB_AND_L2_DLTB_MISS.ALL */
 	},
 	[ C(OP_WRITE) ] = {
 		[ C(RESULT_ACCESS) ] = 0,
@@ -66,7 +66,7 @@ static __initconst const u64 amd_hw_cache_event_ids
  [ C(ITLB) ] = {
 	[ C(OP_READ) ] = {
 		[ C(RESULT_ACCESS) ] = 0x0080, /* Instruction fecthes        */
-		[ C(RESULT_MISS)   ] = 0x0085, /* Instr. fetch ITLB misses   */
+		[ C(RESULT_MISS)   ] = 0x0385, /* L1_ITLB_AND_L2_ITLB_MISS.ALL */
 	},
 	[ C(OP_WRITE) ] = {
 		[ C(RESULT_ACCESS) ] = -1,

arch/x86/kernel/cpu/perf_event_intel.c

@@ -713,18 +713,18 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 	struct cpu_hw_events *cpuc;
 	int bit, loops;
 	u64 status;
-	int handled = 0;
+	int handled;
 
 	perf_sample_data_init(&data, 0);
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
 
 	intel_pmu_disable_all();
-	intel_pmu_drain_bts_buffer();
+	handled = intel_pmu_drain_bts_buffer();
 	status = intel_pmu_get_status();
 	if (!status) {
 		intel_pmu_enable_all(0);
-		return 0;
+		return handled;
 	}
 
 	loops = 0;
@@ -763,7 +763,7 @@ again:
 		data.period = event->hw.last_period;
 
 		if (perf_event_overflow(event, 1, &data, regs))
-			x86_pmu_stop(event);
+			x86_pmu_stop(event, 0);
 	}
 
 	/*

arch/x86/kernel/cpu/perf_event_intel_ds.c

@@ -214,7 +214,7 @@ static void intel_pmu_disable_bts(void)
 	update_debugctlmsr(debugctlmsr);
 }
 
-static void intel_pmu_drain_bts_buffer(void)
+static int intel_pmu_drain_bts_buffer(void)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct debug_store *ds = cpuc->ds;
@@ -231,16 +231,16 @@ static void intel_pmu_drain_bts_buffer(void)
 	struct pt_regs regs;
 
 	if (!event)
-		return;
+		return 0;
 
 	if (!ds)
-		return;
+		return 0;
 
 	at  = (struct bts_record *)(unsigned long)ds->bts_buffer_base;
 	top = (struct bts_record *)(unsigned long)ds->bts_index;
 
 	if (top <= at)
-		return;
+		return 0;
 
 	ds->bts_index = ds->bts_buffer_base;
 
@@ -256,7 +256,7 @@ static void intel_pmu_drain_bts_buffer(void)
 	perf_prepare_sample(&header, &data, event, &regs);
 
 	if (perf_output_begin(&handle, event, header.size * (top - at), 1, 1))
-		return;
+		return 1;
 
 	for (; at < top; at++) {
 		data.ip		= at->from;
@@ -270,6 +270,7 @@ static void intel_pmu_drain_bts_buffer(void)
 	/* There's new data available. */
 	event->hw.interrupts++;
 	event->pending_kill = POLL_IN;
+	return 1;
 }
 
 /*
@@ -491,7 +492,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 		regs.flags &= ~PERF_EFLAGS_EXACT;
 
 	if (perf_event_overflow(event, 1, &data, &regs))
-		x86_pmu_stop(event);
+		x86_pmu_stop(event, 0);
 }
 
 static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)

arch/x86/kernel/cpu/perf_event_p4.c

@@ -18,6 +18,8 @@
 struct p4_event_bind {
 	unsigned int opcode;			/* Event code and ESCR selector */
 	unsigned int escr_msr[2];		/* ESCR MSR for this event */
+	unsigned int escr_emask;		/* valid ESCR EventMask bits */
+	unsigned int shared;			/* event is shared across threads */
 	char cntr[2][P4_CNTR_LIMIT];		/* counter index (offset), -1 on abscence */
 };
 
@@ -66,231 +68,435 @@ static struct p4_event_bind p4_event_bind_map[] = {
 	[P4_EVENT_TC_DELIVER_MODE] = {
 		.opcode		= P4_OPCODE(P4_EVENT_TC_DELIVER_MODE),
 		.escr_msr	= { MSR_P4_TC_ESCR0, MSR_P4_TC_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, DD)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, DB)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, DI)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, BD)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, BB)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, BI)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, ID),
+		.shared		= 1,
 		.cntr		= { {4, 5, -1}, {6, 7, -1} },
 	},
 	[P4_EVENT_BPU_FETCH_REQUEST] = {
 		.opcode		= P4_OPCODE(P4_EVENT_BPU_FETCH_REQUEST),
 		.escr_msr	= { MSR_P4_BPU_ESCR0, MSR_P4_BPU_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_BPU_FETCH_REQUEST, TCMISS),
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_ITLB_REFERENCE] = {
 		.opcode		= P4_OPCODE(P4_EVENT_ITLB_REFERENCE),
 		.escr_msr	= { MSR_P4_ITLB_ESCR0, MSR_P4_ITLB_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_ITLB_REFERENCE, HIT)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_ITLB_REFERENCE, MISS)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_ITLB_REFERENCE, HIT_UK),
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_MEMORY_CANCEL] = {
 		.opcode		= P4_OPCODE(P4_EVENT_MEMORY_CANCEL),
 		.escr_msr	= { MSR_P4_DAC_ESCR0, MSR_P4_DAC_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_MEMORY_CANCEL, ST_RB_FULL)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_MEMORY_CANCEL, 64K_CONF),
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_MEMORY_COMPLETE] = {
 		.opcode		= P4_OPCODE(P4_EVENT_MEMORY_COMPLETE),
 		.escr_msr	= { MSR_P4_SAAT_ESCR0 , MSR_P4_SAAT_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_MEMORY_COMPLETE, LSC)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_MEMORY_COMPLETE, SSC),
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_LOAD_PORT_REPLAY] = {
 		.opcode		= P4_OPCODE(P4_EVENT_LOAD_PORT_REPLAY),
 		.escr_msr	= { MSR_P4_SAAT_ESCR0, MSR_P4_SAAT_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_LOAD_PORT_REPLAY, SPLIT_LD),
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_STORE_PORT_REPLAY] = {
 		.opcode		= P4_OPCODE(P4_EVENT_STORE_PORT_REPLAY),
 		.escr_msr	= { MSR_P4_SAAT_ESCR0 ,  MSR_P4_SAAT_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_STORE_PORT_REPLAY, SPLIT_ST),
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_MOB_LOAD_REPLAY] = {
 		.opcode		= P4_OPCODE(P4_EVENT_MOB_LOAD_REPLAY),
 		.escr_msr	= { MSR_P4_MOB_ESCR0, MSR_P4_MOB_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_MOB_LOAD_REPLAY, NO_STA)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_MOB_LOAD_REPLAY, NO_STD)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_MOB_LOAD_REPLAY, PARTIAL_DATA)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_MOB_LOAD_REPLAY, UNALGN_ADDR),
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_PAGE_WALK_TYPE] = {
 		.opcode		= P4_OPCODE(P4_EVENT_PAGE_WALK_TYPE),
 		.escr_msr	= { MSR_P4_PMH_ESCR0, MSR_P4_PMH_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_PAGE_WALK_TYPE, DTMISS)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_PAGE_WALK_TYPE, ITMISS),
+		.shared		= 1,
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_BSQ_CACHE_REFERENCE] = {
 		.opcode		= P4_OPCODE(P4_EVENT_BSQ_CACHE_REFERENCE),
 		.escr_msr	= { MSR_P4_BSU_ESCR0, MSR_P4_BSU_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITS)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITM)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITS)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITM)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_MISS)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_MISS)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, WR_2ndL_MISS),
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_IOQ_ALLOCATION] = {
 		.opcode		= P4_OPCODE(P4_EVENT_IOQ_ALLOCATION),
 		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, DEFAULT)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, ALL_READ)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, ALL_WRITE)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, MEM_UC)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, MEM_WC)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, MEM_WT)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, MEM_WP)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, MEM_WB)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, OWN)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, OTHER)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, PREFETCH),
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_IOQ_ACTIVE_ENTRIES] = {	/* shared ESCR */
 		.opcode		= P4_OPCODE(P4_EVENT_IOQ_ACTIVE_ENTRIES),
 		.escr_msr	= { MSR_P4_FSB_ESCR1,  MSR_P4_FSB_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, DEFAULT)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, ALL_READ)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, ALL_WRITE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_UC)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WC)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WT)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WP)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WB)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, OWN)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, OTHER)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, PREFETCH),
 		.cntr		= { {2, -1, -1}, {3, -1, -1} },
 	},
 	[P4_EVENT_FSB_DATA_ACTIVITY] = {
 		.opcode		= P4_OPCODE(P4_EVENT_FSB_DATA_ACTIVITY),
 		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_DRV)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_OWN)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_OTHER)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DBSY_DRV)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DBSY_OWN)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DBSY_OTHER),
+		.shared		= 1,
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_BSQ_ALLOCATION] = {		/* shared ESCR, broken CCCR1 */
 		.opcode		= P4_OPCODE(P4_EVENT_BSQ_ALLOCATION),
 		.escr_msr	= { MSR_P4_BSU_ESCR0, MSR_P4_BSU_ESCR0 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_TYPE0)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_TYPE1)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_LEN0)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_LEN1)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_IO_TYPE)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_LOCK_TYPE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_CACHE_TYPE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_SPLIT_TYPE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_DEM_TYPE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_ORD_TYPE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, MEM_TYPE0)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, MEM_TYPE1)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, MEM_TYPE2),
 		.cntr		= { {0, -1, -1}, {1, -1, -1} },
 	},
 	[P4_EVENT_BSQ_ACTIVE_ENTRIES] = {	/* shared ESCR */
 		.opcode		= P4_OPCODE(P4_EVENT_BSQ_ACTIVE_ENTRIES),
 		.escr_msr	= { MSR_P4_BSU_ESCR1 , MSR_P4_BSU_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_TYPE0)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_TYPE1)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_LEN0)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_LEN1)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_IO_TYPE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_LOCK_TYPE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_CACHE_TYPE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_SPLIT_TYPE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_DEM_TYPE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_ORD_TYPE)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, MEM_TYPE0)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, MEM_TYPE1)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, MEM_TYPE2),
 		.cntr		= { {2, -1, -1}, {3, -1, -1} },
 	},
 	[P4_EVENT_SSE_INPUT_ASSIST] = {
 		.opcode		= P4_OPCODE(P4_EVENT_SSE_INPUT_ASSIST),
 		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_SSE_INPUT_ASSIST, ALL),
+		.shared		= 1,
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_PACKED_SP_UOP] = {
 		.opcode		= P4_OPCODE(P4_EVENT_PACKED_SP_UOP),
 		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_PACKED_SP_UOP, ALL),
+		.shared		= 1,
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_PACKED_DP_UOP] = {
 		.opcode		= P4_OPCODE(P4_EVENT_PACKED_DP_UOP),
 		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_PACKED_DP_UOP, ALL),
+		.shared		= 1,
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_SCALAR_SP_UOP] = {
 		.opcode		= P4_OPCODE(P4_EVENT_SCALAR_SP_UOP),
 		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_SCALAR_SP_UOP, ALL),
+		.shared		= 1,
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_SCALAR_DP_UOP] = {
 		.opcode		= P4_OPCODE(P4_EVENT_SCALAR_DP_UOP),
 		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_SCALAR_DP_UOP, ALL),
+		.shared		= 1,
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_64BIT_MMX_UOP] = {
 		.opcode		= P4_OPCODE(P4_EVENT_64BIT_MMX_UOP),
 		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_64BIT_MMX_UOP, ALL),
+		.shared		= 1,
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_128BIT_MMX_UOP] = {
 		.opcode		= P4_OPCODE(P4_EVENT_128BIT_MMX_UOP),
 		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_128BIT_MMX_UOP, ALL),
+		.shared		= 1,
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_X87_FP_UOP] = {
 		.opcode		= P4_OPCODE(P4_EVENT_X87_FP_UOP),
 		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_X87_FP_UOP, ALL),
+		.shared		= 1,
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_TC_MISC] = {
 		.opcode		= P4_OPCODE(P4_EVENT_TC_MISC),
 		.escr_msr	= { MSR_P4_TC_ESCR0, MSR_P4_TC_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_TC_MISC, FLUSH),
 		.cntr		= { {4, 5, -1}, {6, 7, -1} },
 	},
 	[P4_EVENT_GLOBAL_POWER_EVENTS] = {
 		.opcode		= P4_OPCODE(P4_EVENT_GLOBAL_POWER_EVENTS),
 		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_GLOBAL_POWER_EVENTS, RUNNING),
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_TC_MS_XFER] = {
 		.opcode		= P4_OPCODE(P4_EVENT_TC_MS_XFER),
 		.escr_msr	= { MSR_P4_MS_ESCR0, MSR_P4_MS_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_TC_MS_XFER, CISC),
 		.cntr		= { {4, 5, -1}, {6, 7, -1} },
 	},
 	[P4_EVENT_UOP_QUEUE_WRITES] = {
 		.opcode		= P4_OPCODE(P4_EVENT_UOP_QUEUE_WRITES),
 		.escr_msr	= { MSR_P4_MS_ESCR0, MSR_P4_MS_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_UOP_QUEUE_WRITES, FROM_TC_BUILD)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_UOP_QUEUE_WRITES, FROM_TC_DELIVER)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_UOP_QUEUE_WRITES, FROM_ROM),
 		.cntr		= { {4, 5, -1}, {6, 7, -1} },
 	},
 	[P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE] = {
 		.opcode		= P4_OPCODE(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE),
 		.escr_msr	= { MSR_P4_TBPU_ESCR0 , MSR_P4_TBPU_ESCR0 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, CONDITIONAL)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, CALL)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, RETURN)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, INDIRECT),
 		.cntr		= { {4, 5, -1}, {6, 7, -1} },
 	},
 	[P4_EVENT_RETIRED_BRANCH_TYPE] = {
 		.opcode		= P4_OPCODE(P4_EVENT_RETIRED_BRANCH_TYPE),
 		.escr_msr	= { MSR_P4_TBPU_ESCR0 , MSR_P4_TBPU_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, CONDITIONAL)	|
+			P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, CALL)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, RETURN)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, INDIRECT),
 		.cntr		= { {4, 5, -1}, {6, 7, -1} },
 	},
 	[P4_EVENT_RESOURCE_STALL] = {
 		.opcode		= P4_OPCODE(P4_EVENT_RESOURCE_STALL),
 		.escr_msr	= { MSR_P4_ALF_ESCR0, MSR_P4_ALF_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_RESOURCE_STALL, SBFULL),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_WC_BUFFER] = {
 		.opcode		= P4_OPCODE(P4_EVENT_WC_BUFFER),
 		.escr_msr	= { MSR_P4_DAC_ESCR0, MSR_P4_DAC_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_WC_BUFFER, WCB_EVICTS)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_WC_BUFFER, WCB_FULL_EVICTS),
+		.shared		= 1,
 		.cntr		= { {8, 9, -1}, {10, 11, -1} },
 	},
 	[P4_EVENT_B2B_CYCLES] = {
 		.opcode		= P4_OPCODE(P4_EVENT_B2B_CYCLES),
 		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.escr_emask	= 0,
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_BNR] = {
 		.opcode		= P4_OPCODE(P4_EVENT_BNR),
 		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.escr_emask	= 0,
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_SNOOP] = {
 		.opcode		= P4_OPCODE(P4_EVENT_SNOOP),
 		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.escr_emask	= 0,
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_RESPONSE] = {
 		.opcode		= P4_OPCODE(P4_EVENT_RESPONSE),
 		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.escr_emask	= 0,
 		.cntr		= { {0, -1, -1}, {2, -1, -1} },
 	},
 	[P4_EVENT_FRONT_END_EVENT] = {
 		.opcode		= P4_OPCODE(P4_EVENT_FRONT_END_EVENT),
 		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_FRONT_END_EVENT, NBOGUS)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_FRONT_END_EVENT, BOGUS),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_EXECUTION_EVENT] = {
 		.opcode		= P4_OPCODE(P4_EVENT_EXECUTION_EVENT),
 		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS0)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS1)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS2)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS3)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS0)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS1)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS2)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS3),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_REPLAY_EVENT] = {
 		.opcode		= P4_OPCODE(P4_EVENT_REPLAY_EVENT),
 		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_REPLAY_EVENT, NBOGUS)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_REPLAY_EVENT, BOGUS),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_INSTR_RETIRED] = {
 		.opcode		= P4_OPCODE(P4_EVENT_INSTR_RETIRED),
 		.escr_msr	= { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_RETIRED, NBOGUSNTAG)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_RETIRED, NBOGUSTAG)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_RETIRED, BOGUSNTAG)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_RETIRED, BOGUSTAG),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_UOPS_RETIRED] = {
 		.opcode		= P4_OPCODE(P4_EVENT_UOPS_RETIRED),
 		.escr_msr	= { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_UOPS_RETIRED, NBOGUS)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_UOPS_RETIRED, BOGUS),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_UOP_TYPE] = {
 		.opcode		= P4_OPCODE(P4_EVENT_UOP_TYPE),
 		.escr_msr	= { MSR_P4_RAT_ESCR0, MSR_P4_RAT_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_UOP_TYPE, TAGLOADS)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_UOP_TYPE, TAGSTORES),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_BRANCH_RETIRED] = {
 		.opcode		= P4_OPCODE(P4_EVENT_BRANCH_RETIRED),
 		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_BRANCH_RETIRED, MMNP)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BRANCH_RETIRED, MMNM)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BRANCH_RETIRED, MMTP)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_BRANCH_RETIRED, MMTM),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_MISPRED_BRANCH_RETIRED] = {
 		.opcode		= P4_OPCODE(P4_EVENT_MISPRED_BRANCH_RETIRED),
 		.escr_msr	= { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 },
+		.escr_emask	=
+		P4_ESCR_EMASK_BIT(P4_EVENT_MISPRED_BRANCH_RETIRED, NBOGUS),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_X87_ASSIST] = {
 		.opcode		= P4_OPCODE(P4_EVENT_X87_ASSIST),
 		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_X87_ASSIST, FPSU)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_X87_ASSIST, FPSO)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_X87_ASSIST, POAO)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_X87_ASSIST, POAU)			|
+			P4_ESCR_EMASK_BIT(P4_EVENT_X87_ASSIST, PREA),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_MACHINE_CLEAR] = {
 		.opcode		= P4_OPCODE(P4_EVENT_MACHINE_CLEAR),
 		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_MACHINE_CLEAR, CLEAR)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_MACHINE_CLEAR, MOCLEAR)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_MACHINE_CLEAR, SMCLEAR),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 	[P4_EVENT_INSTR_COMPLETED] = {
 		.opcode		= P4_OPCODE(P4_EVENT_INSTR_COMPLETED),
 		.escr_msr	= { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 },
+		.escr_emask	=
+			P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_COMPLETED, NBOGUS)		|
+			P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_COMPLETED, BOGUS),
 		.cntr		= { {12, 13, 16}, {14, 15, 17} },
 	},
 };
@@ -428,29 +634,73 @@ static u64 p4_pmu_event_map(int hw_event)
 	return config;
 }
 
-static int p4_validate_raw_event(struct perf_event *event)
+/* check cpu model specifics */
+static bool p4_event_match_cpu_model(unsigned int event_idx)
 {
-	unsigned int v;
+	/* INSTR_COMPLETED event only exist for model 3, 4, 6 (Prescott) */
-
+	if (event_idx == P4_EVENT_INSTR_COMPLETED) {
-	/* user data may have out-of-bound event index */
+		if (boot_cpu_data.x86_model != 3 &&
-	v = p4_config_unpack_event(event->attr.config);
+			boot_cpu_data.x86_model != 4 &&
-	if (v >= ARRAY_SIZE(p4_event_bind_map)) {
+			boot_cpu_data.x86_model != 6)
-		pr_warning("P4 PMU: Unknown event code: %d\n", v);
+			return false;
-		return -EINVAL;
 	}
 
 	/*
-	 * it may have some screwed PEBS bits
+	 * For info
+	 * - IQ_ESCR0, IQ_ESCR1 only for models 1 and 2
 	 */
-	if (p4_config_pebs_has(event->attr.config, P4_PEBS_CONFIG_ENABLE)) {
+
-		pr_warning("P4 PMU: PEBS are not supported yet\n");
+	return true;
+}
+
+static int p4_validate_raw_event(struct perf_event *event)
+{
+	unsigned int v, emask;
+
+	/* User data may have out-of-bound event index */
+	v = p4_config_unpack_event(event->attr.config);
+	if (v >= ARRAY_SIZE(p4_event_bind_map))
 		return -EINVAL;
+
+	/* It may be unsupported: */
+	if (!p4_event_match_cpu_model(v))
+		return -EINVAL;
+
+	/*
+	 * NOTE: P4_CCCR_THREAD_ANY has not the same meaning as
+	 * in Architectural Performance Monitoring, it means not
+	 * on _which_ logical cpu to count but rather _when_, ie it
+	 * depends on logical cpu state -- count event if one cpu active,
+	 * none, both or any, so we just allow user to pass any value
+	 * desired.
+	 *
+	 * In turn we always set Tx_OS/Tx_USR bits bound to logical
+	 * cpu without their propagation to another cpu
+	 */
+
+	/*
+	 * if an event is shared accross the logical threads
+	 * the user needs special permissions to be able to use it
+	 */
+	if (p4_event_bind_map[v].shared) {
+		if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
+			return -EACCES;
 	}
+
+	/* ESCR EventMask bits may be invalid */
+	emask = p4_config_unpack_escr(event->attr.config) & P4_ESCR_EVENTMASK_MASK;
+	if (emask & ~p4_event_bind_map[v].escr_emask)
+		return -EINVAL;
+
+	/*
+	 * it may have some invalid PEBS bits
+	 */
+	if (p4_config_pebs_has(event->attr.config, P4_PEBS_CONFIG_ENABLE))
+		return -EINVAL;
+
 	v = p4_config_unpack_metric(event->attr.config);
-	if (v >= ARRAY_SIZE(p4_pebs_bind_map)) {
+	if (v >= ARRAY_SIZE(p4_pebs_bind_map))
-		pr_warning("P4 PMU: Unknown metric code: %d\n", v);
 		return -EINVAL;
-	}
 
 	return 0;
 }
@@ -478,27 +728,21 @@ static int p4_hw_config(struct perf_event *event)
 
 	if (event->attr.type == PERF_TYPE_RAW) {
 
+		/*
+		 * Clear bits we reserve to be managed by kernel itself
+		 * and never allowed from a user space
+		 */
+		 event->attr.config &= P4_CONFIG_MASK;
+
 		rc = p4_validate_raw_event(event);
 		if (rc)
 			goto out;
 
 		/*
-		 * We don't control raw events so it's up to the caller
-		 * to pass sane values (and we don't count the thread number
-		 * on HT machine but allow HT-compatible specifics to be
-		 * passed on)
-		 *
 		 * Note that for RAW events we allow user to use P4_CCCR_RESERVED
 		 * bits since we keep additional info here (for cache events and etc)
-		 *
-		 * XXX: HT wide things should check perf_paranoid_cpu() &&
-		 *      CAP_SYS_ADMIN
 		 */
-		event->hw.config |= event->attr.config &
+		event->hw.config |= event->attr.config;
-			(p4_config_pack_escr(P4_ESCR_MASK_HT) |
-			 p4_config_pack_cccr(P4_CCCR_MASK_HT | P4_CCCR_RESERVED));
-
-		event->hw.config &= ~P4_CCCR_FORCE_OVF;
 	}
 
 	rc = x86_setup_perfctr(event);

arch/x86/kernel/entry_64.S

@@ -1023,9 +1023,9 @@ apicinterrupt ERROR_APIC_VECTOR \
 apicinterrupt SPURIOUS_APIC_VECTOR \
 	spurious_interrupt smp_spurious_interrupt
 
-#ifdef CONFIG_PERF_EVENTS
+#ifdef CONFIG_IRQ_WORK
-apicinterrupt LOCAL_PENDING_VECTOR \
+apicinterrupt IRQ_WORK_VECTOR \
-	perf_pending_interrupt smp_perf_pending_interrupt
+	irq_work_interrupt smp_irq_work_interrupt
 #endif
 
 /*

arch/x86/kernel/ftrace.c

@@ -257,14 +257,9 @@ do_ftrace_mod_code(unsigned long ip, void *new_code)
 	return mod_code_status;
 }
 
-
-
-
-static unsigned char ftrace_nop[MCOUNT_INSN_SIZE];
-
 static unsigned char *ftrace_nop_replace(void)
 {
-	return ftrace_nop;
+	return ideal_nop5;
 }
 
 static int
@@ -338,62 +333,6 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 
 int __init ftrace_dyn_arch_init(void *data)
 {
-	extern const unsigned char ftrace_test_p6nop[];
-	extern const unsigned char ftrace_test_nop5[];
-	extern const unsigned char ftrace_test_jmp[];
-	int faulted = 0;
-
-	/*
-	 * There is no good nop for all x86 archs.
-	 * We will default to using the P6_NOP5, but first we
-	 * will test to make sure that the nop will actually
-	 * work on this CPU. If it faults, we will then
-	 * go to a lesser efficient 5 byte nop. If that fails
-	 * we then just use a jmp as our nop. This isn't the most
-	 * efficient nop, but we can not use a multi part nop
-	 * since we would then risk being preempted in the middle
-	 * of that nop, and if we enabled tracing then, it might
-	 * cause a system crash.
-	 *
-	 * TODO: check the cpuid to determine the best nop.
-	 */
-	asm volatile (
-		"ftrace_test_jmp:"
-		"jmp ftrace_test_p6nop\n"
-		"nop\n"
-		"nop\n"
-		"nop\n"  /* 2 byte jmp + 3 bytes */
-		"ftrace_test_p6nop:"
-		P6_NOP5
-		"jmp 1f\n"
-		"ftrace_test_nop5:"
-		".byte 0x66,0x66,0x66,0x66,0x90\n"
-		"1:"
-		".section .fixup, \"ax\"\n"
-		"2:	movl $1, %0\n"
-		"	jmp ftrace_test_nop5\n"
-		"3:	movl $2, %0\n"
-		"	jmp 1b\n"
-		".previous\n"
-		_ASM_EXTABLE(ftrace_test_p6nop, 2b)
-		_ASM_EXTABLE(ftrace_test_nop5, 3b)
-		: "=r"(faulted) : "0" (faulted));
-
-	switch (faulted) {
-	case 0:
-		pr_info("converting mcount calls to 0f 1f 44 00 00\n");
-		memcpy(ftrace_nop, ftrace_test_p6nop, MCOUNT_INSN_SIZE);
-		break;
-	case 1:
-		pr_info("converting mcount calls to 66 66 66 66 90\n");
-		memcpy(ftrace_nop, ftrace_test_nop5, MCOUNT_INSN_SIZE);
-		break;
-	case 2:
-		pr_info("converting mcount calls to jmp . + 5\n");
-		memcpy(ftrace_nop, ftrace_test_jmp, MCOUNT_INSN_SIZE);
-		break;
-	}
-
 	/* The return code is retured via data */
 	*(unsigned long *)data = 0;
 

arch/x86/kernel/irq.c

@@ -67,10 +67,10 @@ static int show_other_interrupts(struct seq_file *p, int prec)
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", irq_stats(j)->apic_perf_irqs);
 	seq_printf(p, "  Performance monitoring interrupts\n");
-	seq_printf(p, "%*s: ", prec, "PND");
+	seq_printf(p, "%*s: ", prec, "IWI");
 	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", irq_stats(j)->apic_pending_irqs);
+		seq_printf(p, "%10u ", irq_stats(j)->apic_irq_work_irqs);
-	seq_printf(p, "  Performance pending work\n");
+	seq_printf(p, "  IRQ work interrupts\n");
 #endif
 	if (x86_platform_ipi_callback) {
 		seq_printf(p, "%*s: ", prec, "PLT");
@@ -185,7 +185,7 @@ u64 arch_irq_stat_cpu(unsigned int cpu)
 	sum += irq_stats(cpu)->apic_timer_irqs;
 	sum += irq_stats(cpu)->irq_spurious_count;
 	sum += irq_stats(cpu)->apic_perf_irqs;
-	sum += irq_stats(cpu)->apic_pending_irqs;
+	sum += irq_stats(cpu)->apic_irq_work_irqs;
 #endif
 	if (x86_platform_ipi_callback)
 		sum += irq_stats(cpu)->x86_platform_ipis;

arch/x86/kernel/irq_work.c

@@ -0,0 +1,30 @@
+/*
+ * x86 specific code for irq_work
+ *
+ * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/irq_work.h>
+#include <linux/hardirq.h>
+#include <asm/apic.h>
+
+void smp_irq_work_interrupt(struct pt_regs *regs)
+{
+	irq_enter();
+	ack_APIC_irq();
+	inc_irq_stat(apic_irq_work_irqs);
+	irq_work_run();
+	irq_exit();
+}
+
+void arch_irq_work_raise(void)
+{
+#ifdef CONFIG_X86_LOCAL_APIC
+	if (!cpu_has_apic)
+		return;
+
+	apic->send_IPI_self(IRQ_WORK_VECTOR);
+	apic_wait_icr_idle();
+#endif
+}

arch/x86/kernel/irqinit.c

@@ -224,9 +224,9 @@ static void __init apic_intr_init(void)
 	alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
 	alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
 
-	/* Performance monitoring interrupts: */
+	/* IRQ work interrupts: */
-# ifdef CONFIG_PERF_EVENTS
+# ifdef CONFIG_IRQ_WORK
-	alloc_intr_gate(LOCAL_PENDING_VECTOR, perf_pending_interrupt);
+	alloc_intr_gate(IRQ_WORK_VECTOR, irq_work_interrupt);
 # endif
 
 #endif

arch/x86/kernel/jump_label.c

@@ -0,0 +1,50 @@
+/*
+ * jump label x86 support
+ *
+ * Copyright (C) 2009 Jason Baron <jbaron@redhat.com>
+ *
+ */
+#include <linux/jump_label.h>
+#include <linux/memory.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/jhash.h>
+#include <linux/cpu.h>
+#include <asm/kprobes.h>
+#include <asm/alternative.h>
+
+#ifdef HAVE_JUMP_LABEL
+
+union jump_code_union {
+	char code[JUMP_LABEL_NOP_SIZE];
+	struct {
+		char jump;
+		int offset;
+	} __attribute__((packed));
+};
+
+void arch_jump_label_transform(struct jump_entry *entry,
+			       enum jump_label_type type)
+{
+	union jump_code_union code;
+
+	if (type == JUMP_LABEL_ENABLE) {
+		code.jump = 0xe9;
+		code.offset = entry->target -
+				(entry->code + JUMP_LABEL_NOP_SIZE);
+	} else
+		memcpy(&code, ideal_nop5, JUMP_LABEL_NOP_SIZE);
+	get_online_cpus();
+	mutex_lock(&text_mutex);
+	text_poke_smp((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE);
+	mutex_unlock(&text_mutex);
+	put_online_cpus();
+}
+
+void arch_jump_label_text_poke_early(jump_label_t addr)
+{
+	text_poke_early((void *)addr, ideal_nop5, JUMP_LABEL_NOP_SIZE);
+}
+
+#endif

arch/x86/kernel/kprobes.c

@@ -230,9 +230,6 @@ static int recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr)
 	return 0;
 }
 
-/* Dummy buffers for kallsyms_lookup */
-static char __dummy_buf[KSYM_NAME_LEN];
-
 /* Check if paddr is at an instruction boundary */
 static int __kprobes can_probe(unsigned long paddr)
 {
@@ -241,7 +238,7 @@ static int __kprobes can_probe(unsigned long paddr)
 	struct insn insn;
 	kprobe_opcode_t buf[MAX_INSN_SIZE];
 
-	if (!kallsyms_lookup(paddr, NULL, &offset, NULL, __dummy_buf))
+	if (!kallsyms_lookup_size_offset(paddr, NULL, &offset))
 		return 0;
 
 	/* Decode instructions */
@@ -1129,7 +1126,7 @@ static void __kprobes synthesize_set_arg1(kprobe_opcode_t *addr,
 	*(unsigned long *)addr = val;
 }
 
-void __kprobes kprobes_optinsn_template_holder(void)
+static void __used __kprobes kprobes_optinsn_template_holder(void)
 {
 	asm volatile (
 			".global optprobe_template_entry\n"
@@ -1221,7 +1218,8 @@ static int __kprobes copy_optimized_instructions(u8 *dest, u8 *src)
 	}
 	/* Check whether the address range is reserved */
 	if (ftrace_text_reserved(src, src + len - 1) ||
-	    alternatives_text_reserved(src, src + len - 1))
+	    alternatives_text_reserved(src, src + len - 1) ||
+	    jump_label_text_reserved(src, src + len - 1))
 		return -EBUSY;
 
 	return len;
@@ -1269,11 +1267,9 @@ static int __kprobes can_optimize(unsigned long paddr)
 	unsigned long addr, size = 0, offset = 0;
 	struct insn insn;
 	kprobe_opcode_t buf[MAX_INSN_SIZE];
-	/* Dummy buffers for lookup_symbol_attrs */
-	static char __dummy_buf[KSYM_NAME_LEN];
 
 	/* Lookup symbol including addr */
-	if (!kallsyms_lookup(paddr, &size, &offset, NULL, __dummy_buf))
+	if (!kallsyms_lookup_size_offset(paddr, &size, &offset))
 		return 0;
 
 	/* Check there is enough space for a relative jump. */

arch/x86/kernel/module.c

@@ -239,6 +239,9 @@ int module_finalize(const Elf_Ehdr *hdr,
 		apply_paravirt(pseg, pseg + para->sh_size);
 	}
 
+	/* make jump label nops */
+	jump_label_apply_nops(me);
+
 	return 0;
 }
 

arch/x86/kernel/setup.c

@@ -112,6 +112,7 @@
 #include <asm/numa_64.h>
 #endif
 #include <asm/mce.h>
+#include <asm/alternative.h>
 
 /*
  * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
@@ -726,6 +727,7 @@ void __init setup_arch(char **cmdline_p)
 {
 	int acpi = 0;
 	int k8 = 0;
+	unsigned long flags;
 
 #ifdef CONFIG_X86_32
 	memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data));
@@ -1071,6 +1073,10 @@ void __init setup_arch(char **cmdline_p)
 	x86_init.oem.banner();
 
 	mcheck_init();
+
+	local_irq_save(flags);
+	arch_init_ideal_nop5();
+	local_irq_restore(flags);
 }
 
 #ifdef CONFIG_X86_32

arch/x86/mm/fault.c

@@ -251,6 +251,8 @@ static noinline __kprobes int vmalloc_fault(unsigned long address)
 	if (!(address >= VMALLOC_START && address < VMALLOC_END))
 		return -1;
 
+	WARN_ON_ONCE(in_nmi());
+
 	/*
 	 * Synchronize this task's top level page-table
 	 * with the 'reference' page table.
@@ -369,6 +371,8 @@ static noinline __kprobes int vmalloc_fault(unsigned long address)
 	if (!(address >= VMALLOC_START && address < VMALLOC_END))
 		return -1;
 
+	WARN_ON_ONCE(in_nmi());
+
 	/*
 	 * Copy kernel mappings over when needed. This can also
 	 * happen within a race in page table update. In the later

arch/x86/mm/kmemcheck/kmemcheck.c

@@ -631,6 +631,8 @@ bool kmemcheck_fault(struct pt_regs *regs, unsigned long address,
 	if (!pte)
 		return false;
 
+	WARN_ON_ONCE(in_nmi());
+
 	if (error_code & 2)
 		kmemcheck_access(regs, address, KMEMCHECK_WRITE);
 	else

arch/x86/oprofile/backtrace.c

@@ -14,6 +14,7 @@
 #include <asm/ptrace.h>
 #include <asm/uaccess.h>
 #include <asm/stacktrace.h>
+#include <linux/compat.h>
 
 static void backtrace_warning_symbol(void *data, char *msg,
 				     unsigned long symbol)
@@ -48,14 +49,12 @@ static struct stacktrace_ops backtrace_ops = {
 	.walk_stack	= print_context_stack,
 };
 
-struct frame_head {
+#ifdef CONFIG_COMPAT
-	struct frame_head *bp;
+static struct stack_frame_ia32 *
-	unsigned long ret;
+dump_user_backtrace_32(struct stack_frame_ia32 *head)
-} __attribute__((packed));
-
-static struct frame_head *dump_user_backtrace(struct frame_head *head)
 {
-	struct frame_head bufhead[2];
+	struct stack_frame_ia32 bufhead[2];
+	struct stack_frame_ia32 *fp;
 
 	/* Also check accessibility of one struct frame_head beyond */
 	if (!access_ok(VERIFY_READ, head, sizeof(bufhead)))
@@ -63,20 +62,66 @@ static struct frame_head *dump_user_backtrace(struct frame_head *head)
 	if (__copy_from_user_inatomic(bufhead, head, sizeof(bufhead)))
 		return NULL;
 
-	oprofile_add_trace(bufhead[0].ret);
+	fp = (struct stack_frame_ia32 *) compat_ptr(bufhead[0].next_frame);
+
+	oprofile_add_trace(bufhead[0].return_address);
+
+	/* frame pointers should strictly progress back up the stack
+	* (towards higher addresses) */
+	if (head >= fp)
+		return NULL;
+
+	return fp;
+}
+
+static inline int
+x86_backtrace_32(struct pt_regs * const regs, unsigned int depth)
+{
+	struct stack_frame_ia32 *head;
+
+	/* User process is 32-bit */
+	if (!current || !test_thread_flag(TIF_IA32))
+		return 0;
+
+	head = (struct stack_frame_ia32 *) regs->bp;
+	while (depth-- && head)
+		head = dump_user_backtrace_32(head);
+
+	return 1;
+}
+
+#else
+static inline int
+x86_backtrace_32(struct pt_regs * const regs, unsigned int depth)
+{
+	return 0;
+}
+#endif /* CONFIG_COMPAT */
+
+static struct stack_frame *dump_user_backtrace(struct stack_frame *head)
+{
+	struct stack_frame bufhead[2];
+
+	/* Also check accessibility of one struct stack_frame beyond */
+	if (!access_ok(VERIFY_READ, head, sizeof(bufhead)))
+		return NULL;
+	if (__copy_from_user_inatomic(bufhead, head, sizeof(bufhead)))
+		return NULL;
+
+	oprofile_add_trace(bufhead[0].return_address);
 
 	/* frame pointers should strictly progress back up the stack
 	 * (towards higher addresses) */
-	if (head >= bufhead[0].bp)
+	if (head >= bufhead[0].next_frame)
 		return NULL;
 
-	return bufhead[0].bp;
+	return bufhead[0].next_frame;
 }
 
 void
 x86_backtrace(struct pt_regs * const regs, unsigned int depth)
 {
-	struct frame_head *head = (struct frame_head *)frame_pointer(regs);
+	struct stack_frame *head = (struct stack_frame *)frame_pointer(regs);
 
 	if (!user_mode_vm(regs)) {
 		unsigned long stack = kernel_stack_pointer(regs);
@@ -86,6 +131,9 @@ x86_backtrace(struct pt_regs * const regs, unsigned int depth)
 		return;
 	}
 
+	if (x86_backtrace_32(regs, depth))
+		return;
+
 	while (depth-- && head)
 		head = dump_user_backtrace(head);
 }

arch/x86/oprofile/nmi_int.c

@@ -695,9 +695,6 @@ static int __init ppro_init(char **cpu_type)
 	return 1;
 }
 
-/* in order to get sysfs right */
-static int using_nmi;
-
 int __init op_nmi_init(struct oprofile_operations *ops)
 {
 	__u8 vendor = boot_cpu_data.x86_vendor;
@@ -705,8 +702,6 @@ int __init op_nmi_init(struct oprofile_operations *ops)
 	char *cpu_type = NULL;
 	int ret = 0;
 
-	using_nmi = 0;
-
 	if (!cpu_has_apic)
 		return -ENODEV;
 
@@ -790,13 +785,11 @@ int __init op_nmi_init(struct oprofile_operations *ops)
 	if (ret)
 		return ret;
 
-	using_nmi = 1;
 	printk(KERN_INFO "oprofile: using NMI interrupt.\n");
 	return 0;
 }
 
 void op_nmi_exit(void)
 {
-	if (using_nmi)
+	exit_sysfs();
-		exit_sysfs();
 }

drivers/oprofile/oprof.c

@@ -225,26 +225,17 @@ post_sync:
 	mutex_unlock(&start_mutex);
 }
 
-int oprofile_set_backtrace(unsigned long val)
+int oprofile_set_ulong(unsigned long *addr, unsigned long val)
 {
-	int err = 0;
+	int err = -EBUSY;
 
 	mutex_lock(&start_mutex);
-
+	if (!oprofile_started) {
-	if (oprofile_started) {
+		*addr = val;
-		err = -EBUSY;
+		err = 0;
-		goto out;
 	}
-
-	if (!oprofile_ops.backtrace) {
-		err = -EINVAL;
-		goto out;
-	}
-
-	oprofile_backtrace_depth = val;
-
-out:
 	mutex_unlock(&start_mutex);
+
 	return err;
 }
 
@@ -257,16 +248,9 @@ static int __init oprofile_init(void)
 		printk(KERN_INFO "oprofile: using timer interrupt.\n");
 		err = oprofile_timer_init(&oprofile_ops);
 		if (err)
-			goto out_arch;
+			return err;
 	}
-	err = oprofilefs_register();
+	return oprofilefs_register();
-	if (err)
-		goto out_arch;
-	return 0;
-
-out_arch:
-	oprofile_arch_exit();
-	return err;
 }
 
 

drivers/oprofile/oprof.h

@@ -37,7 +37,7 @@ void oprofile_create_files(struct super_block *sb, struct dentry *root);
 int oprofile_timer_init(struct oprofile_operations *ops);
 void oprofile_timer_exit(void);
 
-int oprofile_set_backtrace(unsigned long depth);
+int oprofile_set_ulong(unsigned long *addr, unsigned long val);
 int oprofile_set_timeout(unsigned long time);
 
 #endif /* OPROF_H */

drivers/oprofile/oprofile_files.c

@@ -79,14 +79,17 @@ static ssize_t depth_write(struct file *file, char const __user *buf, size_t cou
 	if (*offset)
 		return -EINVAL;
 
+	if (!oprofile_ops.backtrace)
+		return -EINVAL;
+
 	retval = oprofilefs_ulong_from_user(&val, buf, count);
 	if (retval)
 		return retval;
 
-	retval = oprofile_set_backtrace(val);
+	retval = oprofile_set_ulong(&oprofile_backtrace_depth, val);
-
 	if (retval)
 		return retval;
+
 	return count;
 }
 

drivers/oprofile/oprofile_perf.c

@@ -0,0 +1,328 @@
+/*
+ * Copyright 2010 ARM Ltd.
+ *
+ * Perf-events backend for OProfile.
+ */
+#include <linux/perf_event.h>
+#include <linux/platform_device.h>
+#include <linux/oprofile.h>
+#include <linux/slab.h>
+
+/*
+ * Per performance monitor configuration as set via oprofilefs.
+ */
+struct op_counter_config {
+	unsigned long count;
+	unsigned long enabled;
+	unsigned long event;
+	unsigned long unit_mask;
+	unsigned long kernel;
+	unsigned long user;
+	struct perf_event_attr attr;
+};
+
+static int oprofile_perf_enabled;
+static DEFINE_MUTEX(oprofile_perf_mutex);
+
+static struct op_counter_config *counter_config;
+static struct perf_event **perf_events[nr_cpumask_bits];
+static int num_counters;
+
+/*
+ * Overflow callback for oprofile.
+ */
+static void op_overflow_handler(struct perf_event *event, int unused,
+			struct perf_sample_data *data, struct pt_regs *regs)
+{
+	int id;
+	u32 cpu = smp_processor_id();
+
+	for (id = 0; id < num_counters; ++id)
+		if (perf_events[cpu][id] == event)
+			break;
+
+	if (id != num_counters)
+		oprofile_add_sample(regs, id);
+	else
+		pr_warning("oprofile: ignoring spurious overflow "
+				"on cpu %u\n", cpu);
+}
+
+/*
+ * Called by oprofile_perf_setup to create perf attributes to mirror the oprofile
+ * settings in counter_config. Attributes are created as `pinned' events and
+ * so are permanently scheduled on the PMU.
+ */
+static void op_perf_setup(void)
+{
+	int i;
+	u32 size = sizeof(struct perf_event_attr);
+	struct perf_event_attr *attr;
+
+	for (i = 0; i < num_counters; ++i) {
+		attr = &counter_config[i].attr;
+		memset(attr, 0, size);
+		attr->type		= PERF_TYPE_RAW;
+		attr->size		= size;
+		attr->config		= counter_config[i].event;
+		attr->sample_period	= counter_config[i].count;
+		attr->pinned		= 1;
+	}
+}
+
+static int op_create_counter(int cpu, int event)
+{
+	struct perf_event *pevent;
+
+	if (!counter_config[event].enabled || perf_events[cpu][event])
+		return 0;
+
+	pevent = perf_event_create_kernel_counter(&counter_config[event].attr,
+						  cpu, NULL,
+						  op_overflow_handler);
+
+	if (IS_ERR(pevent))
+		return PTR_ERR(pevent);
+
+	if (pevent->state != PERF_EVENT_STATE_ACTIVE) {
+		perf_event_release_kernel(pevent);
+		pr_warning("oprofile: failed to enable event %d "
+				"on CPU %d\n", event, cpu);
+		return -EBUSY;
+	}
+
+	perf_events[cpu][event] = pevent;
+
+	return 0;
+}
+
+static void op_destroy_counter(int cpu, int event)
+{
+	struct perf_event *pevent = perf_events[cpu][event];
+
+	if (pevent) {
+		perf_event_release_kernel(pevent);
+		perf_events[cpu][event] = NULL;
+	}
+}
+
+/*
+ * Called by oprofile_perf_start to create active perf events based on the
+ * perviously configured attributes.
+ */
+static int op_perf_start(void)
+{
+	int cpu, event, ret = 0;
+
+	for_each_online_cpu(cpu) {
+		for (event = 0; event < num_counters; ++event) {
+			ret = op_create_counter(cpu, event);
+			if (ret)
+				return ret;
+		}
+	}
+
+	return ret;
+}
+
+/*
+ * Called by oprofile_perf_stop at the end of a profiling run.
+ */
+static void op_perf_stop(void)
+{
+	int cpu, event;
+
+	for_each_online_cpu(cpu)
+		for (event = 0; event < num_counters; ++event)
+			op_destroy_counter(cpu, event);
+}
+
+static int oprofile_perf_create_files(struct super_block *sb, struct dentry *root)
+{
+	unsigned int i;
+
+	for (i = 0; i < num_counters; i++) {
+		struct dentry *dir;
+		char buf[4];
+
+		snprintf(buf, sizeof buf, "%d", i);
+		dir = oprofilefs_mkdir(sb, root, buf);
+		oprofilefs_create_ulong(sb, dir, "enabled", &counter_config[i].enabled);
+		oprofilefs_create_ulong(sb, dir, "event", &counter_config[i].event);
+		oprofilefs_create_ulong(sb, dir, "count", &counter_config[i].count);
+		oprofilefs_create_ulong(sb, dir, "unit_mask", &counter_config[i].unit_mask);
+		oprofilefs_create_ulong(sb, dir, "kernel", &counter_config[i].kernel);
+		oprofilefs_create_ulong(sb, dir, "user", &counter_config[i].user);
+	}
+
+	return 0;
+}
+
+static int oprofile_perf_setup(void)
+{
+	spin_lock(&oprofilefs_lock);
+	op_perf_setup();
+	spin_unlock(&oprofilefs_lock);
+	return 0;
+}
+
+static int oprofile_perf_start(void)
+{
+	int ret = -EBUSY;
+
+	mutex_lock(&oprofile_perf_mutex);
+	if (!oprofile_perf_enabled) {
+		ret = 0;
+		op_perf_start();
+		oprofile_perf_enabled = 1;
+	}
+	mutex_unlock(&oprofile_perf_mutex);
+	return ret;
+}
+
+static void oprofile_perf_stop(void)
+{
+	mutex_lock(&oprofile_perf_mutex);
+	if (oprofile_perf_enabled)
+		op_perf_stop();
+	oprofile_perf_enabled = 0;
+	mutex_unlock(&oprofile_perf_mutex);
+}
+
+#ifdef CONFIG_PM
+
+static int oprofile_perf_suspend(struct platform_device *dev, pm_message_t state)
+{
+	mutex_lock(&oprofile_perf_mutex);
+	if (oprofile_perf_enabled)
+		op_perf_stop();
+	mutex_unlock(&oprofile_perf_mutex);
+	return 0;
+}
+
+static int oprofile_perf_resume(struct platform_device *dev)
+{
+	mutex_lock(&oprofile_perf_mutex);
+	if (oprofile_perf_enabled && op_perf_start())
+		oprofile_perf_enabled = 0;
+	mutex_unlock(&oprofile_perf_mutex);
+	return 0;
+}
+
+static struct platform_driver oprofile_driver = {
+	.driver		= {
+		.name		= "oprofile-perf",
+	},
+	.resume		= oprofile_perf_resume,
+	.suspend	= oprofile_perf_suspend,
+};
+
+static struct platform_device *oprofile_pdev;
+
+static int __init init_driverfs(void)
+{
+	int ret;
+
+	ret = platform_driver_register(&oprofile_driver);
+	if (ret)
+		return ret;
+
+	oprofile_pdev =	platform_device_register_simple(
+				oprofile_driver.driver.name, 0, NULL, 0);
+	if (IS_ERR(oprofile_pdev)) {
+		ret = PTR_ERR(oprofile_pdev);
+		platform_driver_unregister(&oprofile_driver);
+	}
+
+	return ret;
+}
+
+static void exit_driverfs(void)
+{
+	platform_device_unregister(oprofile_pdev);
+	platform_driver_unregister(&oprofile_driver);
+}
+
+#else
+
+static inline int  init_driverfs(void) { return 0; }
+static inline void exit_driverfs(void) { }
+
+#endif /* CONFIG_PM */
+
+void oprofile_perf_exit(void)
+{
+	int cpu, id;
+	struct perf_event *event;
+
+	for_each_possible_cpu(cpu) {
+		for (id = 0; id < num_counters; ++id) {
+			event = perf_events[cpu][id];
+			if (event)
+				perf_event_release_kernel(event);
+		}
+
+		kfree(perf_events[cpu]);
+	}
+
+	kfree(counter_config);
+	exit_driverfs();
+}
+
+int __init oprofile_perf_init(struct oprofile_operations *ops)
+{
+	int cpu, ret = 0;
+
+	ret = init_driverfs();
+	if (ret)
+		return ret;
+
+	memset(&perf_events, 0, sizeof(perf_events));
+
+	num_counters = perf_num_counters();
+	if (num_counters <= 0) {
+		pr_info("oprofile: no performance counters\n");
+		ret = -ENODEV;
+		goto out;
+	}
+
+	counter_config = kcalloc(num_counters,
+			sizeof(struct op_counter_config), GFP_KERNEL);
+
+	if (!counter_config) {
+		pr_info("oprofile: failed to allocate %d "
+				"counters\n", num_counters);
+		ret = -ENOMEM;
+		num_counters = 0;
+		goto out;
+	}
+
+	for_each_possible_cpu(cpu) {
+		perf_events[cpu] = kcalloc(num_counters,
+				sizeof(struct perf_event *), GFP_KERNEL);
+		if (!perf_events[cpu]) {
+			pr_info("oprofile: failed to allocate %d perf events "
+					"for cpu %d\n", num_counters, cpu);
+			ret = -ENOMEM;
+			goto out;
+		}
+	}
+
+	ops->create_files	= oprofile_perf_create_files;
+	ops->setup		= oprofile_perf_setup;
+	ops->start		= oprofile_perf_start;
+	ops->stop		= oprofile_perf_stop;
+	ops->shutdown		= oprofile_perf_stop;
+	ops->cpu_type		= op_name_from_perf_id();
+
+	if (!ops->cpu_type)
+		ret = -ENODEV;
+	else
+		pr_info("oprofile: using %s\n", ops->cpu_type);
+
+out:
+	if (ret)
+		oprofile_perf_exit();
+
+	return ret;
+}

drivers/oprofile/oprofilefs.c

@@ -91,16 +91,20 @@ static ssize_t ulong_read_file(struct file *file, char __user *buf, size_t count
 
 static ssize_t ulong_write_file(struct file *file, char const __user *buf, size_t count, loff_t *offset)
 {
-	unsigned long *value = file->private_data;
+	unsigned long value;
 	int retval;
 
 	if (*offset)
 		return -EINVAL;
 
-	retval = oprofilefs_ulong_from_user(value, buf, count);
+	retval = oprofilefs_ulong_from_user(&value, buf, count);
-
 	if (retval)
 		return retval;
+
+	retval = oprofile_set_ulong(file->private_data, value);
+	if (retval)
+		return retval;
+
 	return count;
 }
 
@@ -126,50 +130,41 @@ static const struct file_operations ulong_ro_fops = {
 };
 
 
-static struct dentry *__oprofilefs_create_file(struct super_block *sb,
+static int __oprofilefs_create_file(struct super_block *sb,
 	struct dentry *root, char const *name, const struct file_operations *fops,
-	int perm)
+	int perm, void *priv)
 {
 	struct dentry *dentry;
 	struct inode *inode;
 
 	dentry = d_alloc_name(root, name);
 	if (!dentry)
-		return NULL;
+		return -ENOMEM;
 	inode = oprofilefs_get_inode(sb, S_IFREG | perm);
 	if (!inode) {
 		dput(dentry);
-		return NULL;
+		return -ENOMEM;
 	}
 	inode->i_fop = fops;
 	d_add(dentry, inode);
-	return dentry;
+	dentry->d_inode->i_private = priv;
+	return 0;
 }
 
 
 int oprofilefs_create_ulong(struct super_block *sb, struct dentry *root,
 	char const *name, unsigned long *val)
 {
-	struct dentry *d = __oprofilefs_create_file(sb, root, name,
+	return __oprofilefs_create_file(sb, root, name,
-						     &ulong_fops, 0644);
+					&ulong_fops, 0644, val);
-	if (!d)
-		return -EFAULT;
-
-	d->d_inode->i_private = val;
-	return 0;
 }
 
 
 int oprofilefs_create_ro_ulong(struct super_block *sb, struct dentry *root,
 	char const *name, unsigned long *val)
 {
-	struct dentry *d = __oprofilefs_create_file(sb, root, name,
+	return __oprofilefs_create_file(sb, root, name,
-						     &ulong_ro_fops, 0444);
+					&ulong_ro_fops, 0444, val);
-	if (!d)
-		return -EFAULT;
-
-	d->d_inode->i_private = val;
-	return 0;
 }
 
 
@@ -189,31 +184,22 @@ static const struct file_operations atomic_ro_fops = {
 int oprofilefs_create_ro_atomic(struct super_block *sb, struct dentry *root,
 	char const *name, atomic_t *val)
 {
-	struct dentry *d = __oprofilefs_create_file(sb, root, name,
+	return __oprofilefs_create_file(sb, root, name,
-						     &atomic_ro_fops, 0444);
+					&atomic_ro_fops, 0444, val);
-	if (!d)
-		return -EFAULT;
-
-	d->d_inode->i_private = val;
-	return 0;
 }
 
 
 int oprofilefs_create_file(struct super_block *sb, struct dentry *root,
 	char const *name, const struct file_operations *fops)
 {
-	if (!__oprofilefs_create_file(sb, root, name, fops, 0644))
+	return __oprofilefs_create_file(sb, root, name, fops, 0644, NULL);
-		return -EFAULT;
-	return 0;
 }
 
 
 int oprofilefs_create_file_perm(struct super_block *sb, struct dentry *root,
 	char const *name, const struct file_operations *fops, int perm)
 {
-	if (!__oprofilefs_create_file(sb, root, name, fops, perm))
+	return __oprofilefs_create_file(sb, root, name, fops, perm, NULL);
-		return -EFAULT;
-	return 0;
 }
 
 

include/asm-generic/hardirq.h

@@ -3,13 +3,13 @@
 
 #include <linux/cache.h>
 #include <linux/threads.h>
-#include <linux/irq.h>
 
 typedef struct {
 	unsigned int __softirq_pending;
 } ____cacheline_aligned irq_cpustat_t;
 
 #include <linux/irq_cpustat.h>	/* Standard mappings for irq_cpustat_t above */
+#include <linux/irq.h>
 
 #ifndef ack_bad_irq
 static inline void ack_bad_irq(unsigned int irq)

include/asm-generic/vmlinux.lds.h

@@ -220,6 +220,8 @@
 									\
 	BUG_TABLE							\
 									\
+	JUMP_TABLE							\
+									\
 	/* PCI quirks */						\
 	.pci_fixup        : AT(ADDR(.pci_fixup) - LOAD_OFFSET) {	\
 		VMLINUX_SYMBOL(__start_pci_fixups_early) = .;		\
@@ -563,6 +565,14 @@
 #define BUG_TABLE
 #endif
 
+#define JUMP_TABLE							\
+	. = ALIGN(8);							\
+	__jump_table : AT(ADDR(__jump_table) - LOAD_OFFSET) {		\
+		VMLINUX_SYMBOL(__start___jump_table) = .;		\
+		*(__jump_table)						\
+		VMLINUX_SYMBOL(__stop___jump_table) = .;		\
+	}
+
 #ifdef CONFIG_PM_TRACE
 #define TRACEDATA							\
 	. = ALIGN(4);							\

include/linux/dynamic_debug.h

@@ -1,6 +1,8 @@
 #ifndef _DYNAMIC_DEBUG_H
 #define _DYNAMIC_DEBUG_H
 
+#include <linux/jump_label.h>
+
 /* dynamic_printk_enabled, and dynamic_printk_enabled2 are bitmasks in which
  * bit n is set to 1 if any modname hashes into the bucket n, 0 otherwise. They
  * use independent hash functions, to reduce the chance of false positives.
@@ -22,8 +24,6 @@ struct _ddebug {
 	const char *function;
 	const char *filename;
 	const char *format;
-	char primary_hash;
-	char secondary_hash;
 	unsigned int lineno:24;
 	/*
  	 * The flags field controls the behaviour at the callsite.
@@ -33,6 +33,7 @@ struct _ddebug {
 #define _DPRINTK_FLAGS_PRINT   (1<<0)  /* printk() a message using the format */
 #define _DPRINTK_FLAGS_DEFAULT 0
 	unsigned int flags:8;
+	char enabled;
 } __attribute__((aligned(8)));
 
 
@@ -42,33 +43,35 @@ int ddebug_add_module(struct _ddebug *tab, unsigned int n,
 #if defined(CONFIG_DYNAMIC_DEBUG)
 extern int ddebug_remove_module(const char *mod_name);
 
-#define __dynamic_dbg_enabled(dd)  ({	     \
-	int __ret = 0;							     \
-	if (unlikely((dynamic_debug_enabled & (1LL << DEBUG_HASH)) &&	     \
-			(dynamic_debug_enabled2 & (1LL << DEBUG_HASH2))))   \
-				if (unlikely(dd.flags))			     \
-					__ret = 1;			     \
-	__ret; })
-
 #define dynamic_pr_debug(fmt, ...) do {					\
+	__label__ do_printk;						\
+	__label__ out;							\
 	static struct _ddebug descriptor				\
 	__used								\
 	__attribute__((section("__verbose"), aligned(8))) =		\
-	{ KBUILD_MODNAME, __func__, __FILE__, fmt, DEBUG_HASH,	\
+	{ KBUILD_MODNAME, __func__, __FILE__, fmt, __LINE__,		\
-		DEBUG_HASH2, __LINE__, _DPRINTK_FLAGS_DEFAULT };	\
+		_DPRINTK_FLAGS_DEFAULT };				\
-	if (__dynamic_dbg_enabled(descriptor))				\
+	JUMP_LABEL(&descriptor.enabled, do_printk);			\
-		printk(KERN_DEBUG pr_fmt(fmt),	##__VA_ARGS__);		\
+	goto out;							\
+do_printk:								\
+	printk(KERN_DEBUG pr_fmt(fmt),	##__VA_ARGS__);			\
+out:	;								\
 	} while (0)
 
 
 #define dynamic_dev_dbg(dev, fmt, ...) do {				\
+	__label__ do_printk;						\
+	__label__ out;							\
 	static struct _ddebug descriptor				\
 	__used								\
 	__attribute__((section("__verbose"), aligned(8))) =		\
-	{ KBUILD_MODNAME, __func__, __FILE__, fmt, DEBUG_HASH,	\
+	{ KBUILD_MODNAME, __func__, __FILE__, fmt, __LINE__,		\
-		DEBUG_HASH2, __LINE__, _DPRINTK_FLAGS_DEFAULT };	\
+		_DPRINTK_FLAGS_DEFAULT };				\
-	if (__dynamic_dbg_enabled(descriptor))				\
+	JUMP_LABEL(&descriptor.enabled, do_printk);			\
-		dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__);	\
+	goto out;							\
+do_printk:								\
+	dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__);		\
+out:	;								\
 	} while (0)
 
 #else

include/linux/ftrace_event.h

@@ -191,8 +191,8 @@ struct ftrace_event_call {
 	unsigned int		flags;
 
 #ifdef CONFIG_PERF_EVENTS
-	int			perf_refcount;
+	int				perf_refcount;
-	struct hlist_head	*perf_events;
+	struct hlist_head __percpu	*perf_events;
 #endif
 };
 
@@ -252,8 +252,8 @@ DECLARE_PER_CPU(struct pt_regs, perf_trace_regs);
 
 extern int  perf_trace_init(struct perf_event *event);
 extern void perf_trace_destroy(struct perf_event *event);
-extern int  perf_trace_enable(struct perf_event *event);
+extern int  perf_trace_add(struct perf_event *event, int flags);
-extern void perf_trace_disable(struct perf_event *event);
+extern void perf_trace_del(struct perf_event *event, int flags);
 extern int  ftrace_profile_set_filter(struct perf_event *event, int event_id,
 				     char *filter_str);
 extern void ftrace_profile_free_filter(struct perf_event *event);

include/linux/interrupt.h

@@ -18,6 +18,7 @@
 #include <asm/atomic.h>
 #include <asm/ptrace.h>
 #include <asm/system.h>
+#include <trace/events/irq.h>
 
 /*
  * These correspond to the IORESOURCE_IRQ_* defines in
@@ -407,7 +408,12 @@ asmlinkage void do_softirq(void);
 asmlinkage void __do_softirq(void);
 extern void open_softirq(int nr, void (*action)(struct softirq_action *));
 extern void softirq_init(void);
-#define __raise_softirq_irqoff(nr) do { or_softirq_pending(1UL << (nr)); } while (0)
+static inline void __raise_softirq_irqoff(unsigned int nr)
+{
+	trace_softirq_raise((struct softirq_action *)(unsigned long)nr, NULL);
+	or_softirq_pending(1UL << nr);
+}
+
 extern void raise_softirq_irqoff(unsigned int nr);
 extern void raise_softirq(unsigned int nr);
 extern void wakeup_softirqd(void);

include/linux/irq_work.h

@@ -0,0 +1,20 @@
+#ifndef _LINUX_IRQ_WORK_H
+#define _LINUX_IRQ_WORK_H
+
+struct irq_work {
+	struct irq_work *next;
+	void (*func)(struct irq_work *);
+};
+
+static inline
+void init_irq_work(struct irq_work *entry, void (*func)(struct irq_work *))
+{
+	entry->next = NULL;
+	entry->func = func;
+}
+
+bool irq_work_queue(struct irq_work *entry);
+void irq_work_run(void);
+void irq_work_sync(struct irq_work *entry);
+
+#endif /* _LINUX_IRQ_WORK_H */

include/linux/jump_label.h

@@ -0,0 +1,74 @@
+#ifndef _LINUX_JUMP_LABEL_H
+#define _LINUX_JUMP_LABEL_H
+
+#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_HAVE_ARCH_JUMP_LABEL)
+# include <asm/jump_label.h>
+# define HAVE_JUMP_LABEL
+#endif
+
+enum jump_label_type {
+	JUMP_LABEL_ENABLE,
+	JUMP_LABEL_DISABLE
+};
+
+struct module;
+
+#ifdef HAVE_JUMP_LABEL
+
+extern struct jump_entry __start___jump_table[];
+extern struct jump_entry __stop___jump_table[];
+
+extern void arch_jump_label_transform(struct jump_entry *entry,
+				 enum jump_label_type type);
+extern void arch_jump_label_text_poke_early(jump_label_t addr);
+extern void jump_label_update(unsigned long key, enum jump_label_type type);
+extern void jump_label_apply_nops(struct module *mod);
+extern int jump_label_text_reserved(void *start, void *end);
+
+#define jump_label_enable(key) \
+	jump_label_update((unsigned long)key, JUMP_LABEL_ENABLE);
+
+#define jump_label_disable(key) \
+	jump_label_update((unsigned long)key, JUMP_LABEL_DISABLE);
+
+#else
+
+#define JUMP_LABEL(key, label)			\
+do {						\
+	if (unlikely(*key))			\
+		goto label;			\
+} while (0)
+
+#define jump_label_enable(cond_var)	\
+do {					\
+       *(cond_var) = 1;			\
+} while (0)
+
+#define jump_label_disable(cond_var)	\
+do {					\
+       *(cond_var) = 0;			\
+} while (0)
+
+static inline int jump_label_apply_nops(struct module *mod)
+{
+	return 0;
+}
+
+static inline int jump_label_text_reserved(void *start, void *end)
+{
+	return 0;
+}
+
+#endif
+
+#define COND_STMT(key, stmt)					\
+do {								\
+	__label__ jl_enabled;					\
+	JUMP_LABEL(key, jl_enabled);				\
+	if (0) {						\
+jl_enabled:							\
+		stmt;						\
+	}							\
+} while (0)
+
+#endif

include/linux/jump_label_ref.h

@@ -0,0 +1,44 @@
+#ifndef _LINUX_JUMP_LABEL_REF_H
+#define _LINUX_JUMP_LABEL_REF_H
+
+#include <linux/jump_label.h>
+#include <asm/atomic.h>
+
+#ifdef HAVE_JUMP_LABEL
+
+static inline void jump_label_inc(atomic_t *key)
+{
+	if (atomic_add_return(1, key) == 1)
+		jump_label_enable(key);
+}
+
+static inline void jump_label_dec(atomic_t *key)
+{
+	if (atomic_dec_and_test(key))
+		jump_label_disable(key);
+}
+
+#else /* !HAVE_JUMP_LABEL */
+
+static inline void jump_label_inc(atomic_t *key)
+{
+	atomic_inc(key);
+}
+
+static inline void jump_label_dec(atomic_t *key)
+{
+	atomic_dec(key);
+}
+
+#undef JUMP_LABEL
+#define JUMP_LABEL(key, label)						\
+do {									\
+	if (unlikely(__builtin_choose_expr(				\
+	      __builtin_types_compatible_p(typeof(key), atomic_t *),	\
+	      atomic_read((atomic_t *)(key)), *(key))))			\
+		goto label;						\
+} while (0)
+
+#endif /* HAVE_JUMP_LABEL */
+
+#endif /* _LINUX_JUMP_LABEL_REF_H */

include/linux/module.h

@@ -350,7 +350,10 @@ struct module
 	struct tracepoint *tracepoints;
 	unsigned int num_tracepoints;
 #endif
-
+#ifdef HAVE_JUMP_LABEL
+	struct jump_entry *jump_entries;
+	unsigned int num_jump_entries;
+#endif
 #ifdef CONFIG_TRACING
 	const char **trace_bprintk_fmt_start;
 	unsigned int num_trace_bprintk_fmt;

include/linux/oprofile.h

@@ -15,6 +15,7 @@
 
 #include <linux/types.h>
 #include <linux/spinlock.h>
+#include <linux/init.h>
 #include <asm/atomic.h>
  
 /* Each escaped entry is prefixed by ESCAPE_CODE
@@ -185,4 +186,10 @@ int oprofile_add_data(struct op_entry *entry, unsigned long val);
 int oprofile_add_data64(struct op_entry *entry, u64 val);
 int oprofile_write_commit(struct op_entry *entry);
 
+#ifdef CONFIG_PERF_EVENTS
+int __init oprofile_perf_init(struct oprofile_operations *ops);
+void oprofile_perf_exit(void);
+char *op_name_from_perf_id(void);
+#endif /* CONFIG_PERF_EVENTS */
+
 #endif /* OPROFILE_H */

include/linux/percpu.h

@@ -39,6 +39,15 @@
 	preempt_enable();				\
 } while (0)
 
+#define get_cpu_ptr(var) ({				\
+	preempt_disable();				\
+	this_cpu_ptr(var); })
+
+#define put_cpu_ptr(var) do {				\
+	(void)(var);					\
+	preempt_enable();				\
+} while (0)
+
 #ifdef CONFIG_SMP
 
 /* minimum unit size, also is the maximum supported allocation size */

include/linux/perf_event.h

@@ -486,6 +486,8 @@ struct perf_guest_info_callbacks {
 #include <linux/workqueue.h>
 #include <linux/ftrace.h>
 #include <linux/cpu.h>
+#include <linux/irq_work.h>
+#include <linux/jump_label_ref.h>
 #include <asm/atomic.h>
 #include <asm/local.h>
 
@@ -529,16 +531,22 @@ struct hw_perf_event {
 			int		last_cpu;
 		};
 		struct { /* software */
-			s64		remaining;
 			struct hrtimer	hrtimer;
 		};
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 		struct { /* breakpoint */
 			struct arch_hw_breakpoint	info;
 			struct list_head		bp_list;
+			/*
+			 * Crufty hack to avoid the chicken and egg
+			 * problem hw_breakpoint has with context
+			 * creation and event initalization.
+			 */
+			struct task_struct		*bp_target;
 		};
 #endif
 	};
+	int				state;
 	local64_t			prev_count;
 	u64				sample_period;
 	u64				last_period;
@@ -550,6 +558,13 @@ struct hw_perf_event {
 #endif
 };
 
+/*
+ * hw_perf_event::state flags
+ */
+#define PERF_HES_STOPPED	0x01 /* the counter is stopped */
+#define PERF_HES_UPTODATE	0x02 /* event->count up-to-date */
+#define PERF_HES_ARCH		0x04
+
 struct perf_event;
 
 /*
@@ -561,36 +576,70 @@ struct perf_event;
  * struct pmu - generic performance monitoring unit
  */
 struct pmu {
-	int (*enable)			(struct perf_event *event);
+	struct list_head		entry;
-	void (*disable)			(struct perf_event *event);
+
-	int (*start)			(struct perf_event *event);
+	int * __percpu			pmu_disable_count;
-	void (*stop)			(struct perf_event *event);
+	struct perf_cpu_context * __percpu pmu_cpu_context;
+	int				task_ctx_nr;
+
+	/*
+	 * Fully disable/enable this PMU, can be used to protect from the PMI
+	 * as well as for lazy/batch writing of the MSRs.
+	 */
+	void (*pmu_enable)		(struct pmu *pmu); /* optional */
+	void (*pmu_disable)		(struct pmu *pmu); /* optional */
+
+	/*
+	 * Try and initialize the event for this PMU.
+	 * Should return -ENOENT when the @event doesn't match this PMU.
+	 */
+	int (*event_init)		(struct perf_event *event);
+
+#define PERF_EF_START	0x01		/* start the counter when adding    */
+#define PERF_EF_RELOAD	0x02		/* reload the counter when starting */
+#define PERF_EF_UPDATE	0x04		/* update the counter when stopping */
+
+	/*
+	 * Adds/Removes a counter to/from the PMU, can be done inside
+	 * a transaction, see the ->*_txn() methods.
+	 */
+	int  (*add)			(struct perf_event *event, int flags);
+	void (*del)			(struct perf_event *event, int flags);
+
+	/*
+	 * Starts/Stops a counter present on the PMU. The PMI handler
+	 * should stop the counter when perf_event_overflow() returns
+	 * !0. ->start() will be used to continue.
+	 */
+	void (*start)			(struct perf_event *event, int flags);
+	void (*stop)			(struct perf_event *event, int flags);
+
+	/*
+	 * Updates the counter value of the event.
+	 */
 	void (*read)			(struct perf_event *event);
-	void (*unthrottle)		(struct perf_event *event);
 
 	/*
-	 * Group events scheduling is treated as a transaction, add group
+	 * Group events scheduling is treated as a transaction, add
-	 * events as a whole and perform one schedulability test. If the test
+	 * group events as a whole and perform one schedulability test.
-	 * fails, roll back the whole group
+	 * If the test fails, roll back the whole group
+	 *
+	 * Start the transaction, after this ->add() doesn't need to
+	 * do schedulability tests.
 	 */
-
+	void (*start_txn)	(struct pmu *pmu); /* optional */
 	/*
-	 * Start the transaction, after this ->enable() doesn't need
+	 * If ->start_txn() disabled the ->add() schedulability test
-	 * to do schedulability tests.
-	 */
-	void (*start_txn)	(const struct pmu *pmu);
-	/*
-	 * If ->start_txn() disabled the ->enable() schedulability test
 	 * then ->commit_txn() is required to perform one. On success
 	 * the transaction is closed. On error the transaction is kept
 	 * open until ->cancel_txn() is called.
 	 */
-	int  (*commit_txn)	(const struct pmu *pmu);
+	int  (*commit_txn)	(struct pmu *pmu); /* optional */
 	/*
-	 * Will cancel the transaction, assumes ->disable() is called for
+	 * Will cancel the transaction, assumes ->del() is called
-	 * each successfull ->enable() during the transaction.
+	 * for each successfull ->add() during the transaction.
 	 */
-	void (*cancel_txn)	(const struct pmu *pmu);
+	void (*cancel_txn)	(struct pmu *pmu); /* optional */
 };
 
 /**
@@ -631,11 +680,6 @@ struct perf_buffer {
 	void				*data_pages[0];
 };
 
-struct perf_pending_entry {
-	struct perf_pending_entry *next;
-	void (*func)(struct perf_pending_entry *);
-};
-
 struct perf_sample_data;
 
 typedef void (*perf_overflow_handler_t)(struct perf_event *, int,
@@ -656,6 +700,7 @@ struct swevent_hlist {
 
 #define PERF_ATTACH_CONTEXT	0x01
 #define PERF_ATTACH_GROUP	0x02
+#define PERF_ATTACH_TASK	0x04
 
 /**
  * struct perf_event - performance event kernel representation:
@@ -669,7 +714,7 @@ struct perf_event {
 	int				nr_siblings;
 	int				group_flags;
 	struct perf_event		*group_leader;
-	const struct pmu		*pmu;
+	struct pmu			*pmu;
 
 	enum perf_event_active_state	state;
 	unsigned int			attach_state;
@@ -743,7 +788,7 @@ struct perf_event {
 	int				pending_wakeup;
 	int				pending_kill;
 	int				pending_disable;
-	struct perf_pending_entry	pending;
+	struct irq_work			pending;
 
 	atomic_t			event_limit;
 
@@ -763,12 +808,19 @@ struct perf_event {
 #endif /* CONFIG_PERF_EVENTS */
 };
 
+enum perf_event_context_type {
+	task_context,
+	cpu_context,
+};
+
 /**
  * struct perf_event_context - event context structure
  *
  * Used as a container for task events and CPU events as well:
  */
 struct perf_event_context {
+	enum perf_event_context_type	type;
+	struct pmu			*pmu;
 	/*
 	 * Protect the states of the events in the list,
 	 * nr_active, and the list:
@@ -808,6 +860,12 @@ struct perf_event_context {
 	struct rcu_head			rcu_head;
 };
 
+/*
+ * Number of contexts where an event can trigger:
+ * 	task, softirq, hardirq, nmi.
+ */
+#define PERF_NR_CONTEXTS	4
+
 /**
  * struct perf_event_cpu_context - per cpu event context structure
  */
@@ -815,18 +873,9 @@ struct perf_cpu_context {
 	struct perf_event_context	ctx;
 	struct perf_event_context	*task_ctx;
 	int				active_oncpu;
-	int				max_pertask;
 	int				exclusive;
-	struct swevent_hlist		*swevent_hlist;
+	struct list_head		rotation_list;
-	struct mutex			hlist_mutex;
+	int				jiffies_interval;
-	int				hlist_refcount;
-
-	/*
-	 * Recursion avoidance:
-	 *
-	 * task, softirq, irq, nmi context
-	 */
-	int				recursion[4];
 };
 
 struct perf_output_handle {
@@ -842,26 +891,34 @@ struct perf_output_handle {
 
 #ifdef CONFIG_PERF_EVENTS
 
-/*
+extern int perf_pmu_register(struct pmu *pmu);
- * Set by architecture code:
+extern void perf_pmu_unregister(struct pmu *pmu);
- */
-extern int perf_max_events;
 
-extern const struct pmu *hw_perf_event_init(struct perf_event *event);
+extern int perf_num_counters(void);
+extern const char *perf_pmu_name(void);
+extern void __perf_event_task_sched_in(struct task_struct *task);
+extern void __perf_event_task_sched_out(struct task_struct *task, struct task_struct *next);
+
+extern atomic_t perf_task_events;
+
+static inline void perf_event_task_sched_in(struct task_struct *task)
+{
+	COND_STMT(&perf_task_events, __perf_event_task_sched_in(task));
+}
+
+static inline
+void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next)
+{
+	COND_STMT(&perf_task_events, __perf_event_task_sched_out(task, next));
+}
 
-extern void perf_event_task_sched_in(struct task_struct *task);
-extern void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next);
-extern void perf_event_task_tick(struct task_struct *task);
 extern int perf_event_init_task(struct task_struct *child);
 extern void perf_event_exit_task(struct task_struct *child);
 extern void perf_event_free_task(struct task_struct *task);
-extern void set_perf_event_pending(void);
+extern void perf_event_delayed_put(struct task_struct *task);
-extern void perf_event_do_pending(void);
 extern void perf_event_print_debug(void);
-extern void __perf_disable(void);
+extern void perf_pmu_disable(struct pmu *pmu);
-extern bool __perf_enable(void);
+extern void perf_pmu_enable(struct pmu *pmu);
-extern void perf_disable(void);
-extern void perf_enable(void);
 extern int perf_event_task_disable(void);
 extern int perf_event_task_enable(void);
 extern void perf_event_update_userpage(struct perf_event *event);
@@ -869,7 +926,7 @@ extern int perf_event_release_kernel(struct perf_event *event);
 extern struct perf_event *
 perf_event_create_kernel_counter(struct perf_event_attr *attr,
 				int cpu,
-				pid_t pid,
+				struct task_struct *task,
 				perf_overflow_handler_t callback);
 extern u64 perf_event_read_value(struct perf_event *event,
 				 u64 *enabled, u64 *running);
@@ -920,14 +977,7 @@ extern int perf_event_overflow(struct perf_event *event, int nmi,
  */
 static inline int is_software_event(struct perf_event *event)
 {
-	switch (event->attr.type) {
+	return event->pmu->task_ctx_nr == perf_sw_context;
-	case PERF_TYPE_SOFTWARE:
-	case PERF_TYPE_TRACEPOINT:
-	/* for now the breakpoint stuff also works as software event */
-	case PERF_TYPE_BREAKPOINT:
-		return 1;
-	}
-	return 0;
 }
 
 extern atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX];
@@ -954,18 +1004,20 @@ static inline void perf_fetch_caller_regs(struct pt_regs *regs)
 	perf_arch_fetch_caller_regs(regs, CALLER_ADDR0);
 }
 
-static inline void
+static __always_inline void
 perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
 {
-	if (atomic_read(&perf_swevent_enabled[event_id])) {
+	struct pt_regs hot_regs;
-		struct pt_regs hot_regs;
 
-		if (!regs) {
+	JUMP_LABEL(&perf_swevent_enabled[event_id], have_event);
-			perf_fetch_caller_regs(&hot_regs);
+	return;
-			regs = &hot_regs;
+
-		}
+have_event:
-		__perf_sw_event(event_id, nr, nmi, regs, addr);
+	if (!regs) {
+		perf_fetch_caller_regs(&hot_regs);
+		regs = &hot_regs;
 	}
+	__perf_sw_event(event_id, nr, nmi, regs, addr);
 }
 
 extern void perf_event_mmap(struct vm_area_struct *vma);
@@ -976,7 +1028,21 @@ extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks
 extern void perf_event_comm(struct task_struct *tsk);
 extern void perf_event_fork(struct task_struct *tsk);
 
-extern struct perf_callchain_entry *perf_callchain(struct pt_regs *regs);
+/* Callchains */
+DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry);
+
+extern void perf_callchain_user(struct perf_callchain_entry *entry,
+				struct pt_regs *regs);
+extern void perf_callchain_kernel(struct perf_callchain_entry *entry,
+				  struct pt_regs *regs);
+
+
+static inline void
+perf_callchain_store(struct perf_callchain_entry *entry, u64 ip)
+{
+	if (entry->nr < PERF_MAX_STACK_DEPTH)
+		entry->ip[entry->nr++] = ip;
+}
 
 extern int sysctl_perf_event_paranoid;
 extern int sysctl_perf_event_mlock;
@@ -1019,21 +1085,18 @@ extern int perf_swevent_get_recursion_context(void);
 extern void perf_swevent_put_recursion_context(int rctx);
 extern void perf_event_enable(struct perf_event *event);
 extern void perf_event_disable(struct perf_event *event);
+extern void perf_event_task_tick(void);
 #else
 static inline void
 perf_event_task_sched_in(struct task_struct *task)			{ }
 static inline void
 perf_event_task_sched_out(struct task_struct *task,
 			    struct task_struct *next)			{ }
-static inline void
-perf_event_task_tick(struct task_struct *task)				{ }
 static inline int perf_event_init_task(struct task_struct *child)	{ return 0; }
 static inline void perf_event_exit_task(struct task_struct *child)	{ }
 static inline void perf_event_free_task(struct task_struct *task)	{ }
-static inline void perf_event_do_pending(void)				{ }
+static inline void perf_event_delayed_put(struct task_struct *task)	{ }
 static inline void perf_event_print_debug(void)				{ }
-static inline void perf_disable(void)					{ }
-static inline void perf_enable(void)					{ }
 static inline int perf_event_task_disable(void)				{ return -EINVAL; }
 static inline int perf_event_task_enable(void)				{ return -EINVAL; }
 
@@ -1056,6 +1119,7 @@ static inline int  perf_swevent_get_recursion_context(void)		{ return -1; }
 static inline void perf_swevent_put_recursion_context(int rctx)		{ }
 static inline void perf_event_enable(struct perf_event *event)		{ }
 static inline void perf_event_disable(struct perf_event *event)		{ }
+static inline void perf_event_task_tick(void)				{ }
 #endif
 
 #define perf_output_put(handle, x) \

include/linux/sched.h

@@ -1160,6 +1160,13 @@ struct sched_rt_entity {
 
 struct rcu_node;
 
+enum perf_event_task_context {
+	perf_invalid_context = -1,
+	perf_hw_context = 0,
+	perf_sw_context,
+	perf_nr_task_contexts,
+};
+
 struct task_struct {
 	volatile long state;	/* -1 unrunnable, 0 runnable, >0 stopped */
 	void *stack;
@@ -1433,7 +1440,7 @@ struct task_struct {
 	struct futex_pi_state *pi_state_cache;
 #endif
 #ifdef CONFIG_PERF_EVENTS
-	struct perf_event_context *perf_event_ctxp;
+	struct perf_event_context *perf_event_ctxp[perf_nr_task_contexts];
 	struct mutex perf_event_mutex;
 	struct list_head perf_event_list;
 #endif

include/linux/stop_machine.h

@@ -126,8 +126,8 @@ int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus);
 
 #else	 /* CONFIG_STOP_MACHINE && CONFIG_SMP */
 
-static inline int stop_machine(int (*fn)(void *), void *data,
+static inline int __stop_machine(int (*fn)(void *), void *data,
-			       const struct cpumask *cpus)
+				 const struct cpumask *cpus)
 {
 	int ret;
 	local_irq_disable();
@@ -136,5 +136,11 @@ static inline int stop_machine(int (*fn)(void *), void *data,
 	return ret;
 }
 
+static inline int stop_machine(int (*fn)(void *), void *data,
+			       const struct cpumask *cpus)
+{
+	return __stop_machine(fn, data, cpus);
+}
+
 #endif	/* CONFIG_STOP_MACHINE && CONFIG_SMP */
 #endif	/* _LINUX_STOP_MACHINE */

include/linux/tracepoint.h

@@ -17,6 +17,7 @@
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/rcupdate.h>
+#include <linux/jump_label.h>
 
 struct module;
 struct tracepoint;
@@ -145,7 +146,9 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin,
 	extern struct tracepoint __tracepoint_##name;			\
 	static inline void trace_##name(proto)				\
 	{								\
-		if (unlikely(__tracepoint_##name.state))		\
+		JUMP_LABEL(&__tracepoint_##name.state, do_trace);	\
+		return;							\
+do_trace:								\
 			__DO_TRACE(&__tracepoint_##name,		\
 				TP_PROTO(data_proto),			\
 				TP_ARGS(data_args));			\

include/trace/events/irq.h

@@ -5,7 +5,9 @@
 #define _TRACE_IRQ_H
 
 #include <linux/tracepoint.h>
-#include <linux/interrupt.h>
+
+struct irqaction;
+struct softirq_action;
 
 #define softirq_name(sirq) { sirq##_SOFTIRQ, #sirq }
 #define show_softirq_name(val)				\
@@ -93,7 +95,10 @@ DECLARE_EVENT_CLASS(softirq,
 	),
 
 	TP_fast_assign(
-		__entry->vec = (int)(h - vec);
+		if (vec)
+			__entry->vec = (int)(h - vec);
+		else
+			__entry->vec = (int)(long)h;
 	),
 
 	TP_printk("vec=%d [action=%s]", __entry->vec,
@@ -136,6 +141,23 @@ DEFINE_EVENT(softirq, softirq_exit,
 	TP_ARGS(h, vec)
 );
 
+/**
+ * softirq_raise - called immediately when a softirq is raised
+ * @h: pointer to struct softirq_action
+ * @vec: pointer to first struct softirq_action in softirq_vec array
+ *
+ * The @h parameter contains a pointer to the softirq vector number which is
+ * raised. @vec is NULL and it means @h includes vector number not
+ * softirq_action. When used in combination with the softirq_entry tracepoint
+ * we can determine the softirq raise latency.
+ */
+DEFINE_EVENT(softirq, softirq_raise,
+
+	TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
+
+	TP_ARGS(h, vec)
+);
+
 #endif /*  _TRACE_IRQ_H */
 
 /* This part must be outside protection */

include/trace/events/napi.h

@@ -6,10 +6,31 @@
 
 #include <linux/netdevice.h>
 #include <linux/tracepoint.h>
+#include <linux/ftrace.h>
+
+#define NO_DEV "(no_device)"
+
+TRACE_EVENT(napi_poll,
 
-DECLARE_TRACE(napi_poll,
 	TP_PROTO(struct napi_struct *napi),
-	TP_ARGS(napi));
+
+	TP_ARGS(napi),
+
+	TP_STRUCT__entry(
+		__field(	struct napi_struct *,	napi)
+		__string(	dev_name, napi->dev ? napi->dev->name : NO_DEV)
+	),
+
+	TP_fast_assign(
+		__entry->napi = napi;
+		__assign_str(dev_name, napi->dev ? napi->dev->name : NO_DEV);
+	),
+
+	TP_printk("napi poll on napi struct %p for device %s",
+		__entry->napi, __get_str(dev_name))
+);
+
+#undef NO_DEV
 
 #endif /* _TRACE_NAPI_H_ */
 

include/trace/events/net.h

@@ -0,0 +1,82 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM net
+
+#if !defined(_TRACE_NET_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_NET_H
+
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/ip.h>
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(net_dev_xmit,
+
+	TP_PROTO(struct sk_buff *skb,
+		 int rc),
+
+	TP_ARGS(skb, rc),
+
+	TP_STRUCT__entry(
+		__field(	void *,		skbaddr		)
+		__field(	unsigned int,	len		)
+		__field(	int,		rc		)
+		__string(	name,		skb->dev->name	)
+	),
+
+	TP_fast_assign(
+		__entry->skbaddr = skb;
+		__entry->len = skb->len;
+		__entry->rc = rc;
+		__assign_str(name, skb->dev->name);
+	),
+
+	TP_printk("dev=%s skbaddr=%p len=%u rc=%d",
+		__get_str(name), __entry->skbaddr, __entry->len, __entry->rc)
+);
+
+DECLARE_EVENT_CLASS(net_dev_template,
+
+	TP_PROTO(struct sk_buff *skb),
+
+	TP_ARGS(skb),
+
+	TP_STRUCT__entry(
+		__field(	void *,		skbaddr		)
+		__field(	unsigned int,	len		)
+		__string(	name,		skb->dev->name	)
+	),
+
+	TP_fast_assign(
+		__entry->skbaddr = skb;
+		__entry->len = skb->len;
+		__assign_str(name, skb->dev->name);
+	),
+
+	TP_printk("dev=%s skbaddr=%p len=%u",
+		__get_str(name), __entry->skbaddr, __entry->len)
+)
+
+DEFINE_EVENT(net_dev_template, net_dev_queue,
+
+	TP_PROTO(struct sk_buff *skb),
+
+	TP_ARGS(skb)
+);
+
+DEFINE_EVENT(net_dev_template, netif_receive_skb,
+
+	TP_PROTO(struct sk_buff *skb),
+
+	TP_ARGS(skb)
+);
+
+DEFINE_EVENT(net_dev_template, netif_rx,
+
+	TP_PROTO(struct sk_buff *skb),
+
+	TP_ARGS(skb)
+);
+#endif /* _TRACE_NET_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>

include/trace/events/power.h

@@ -10,12 +10,17 @@
 #ifndef _TRACE_POWER_ENUM_
 #define _TRACE_POWER_ENUM_
 enum {
-	POWER_NONE = 0,
+	POWER_NONE	= 0,
-	POWER_CSTATE = 1,
+	POWER_CSTATE	= 1,	/* C-State */
-	POWER_PSTATE = 2,
+	POWER_PSTATE	= 2,	/* Fequency change or DVFS */
+	POWER_SSTATE	= 3,	/* Suspend */
 };
 #endif
 
+/*
+ * The power events are used for cpuidle & suspend (power_start, power_end)
+ *  and for cpufreq (power_frequency)
+ */
 DECLARE_EVENT_CLASS(power,
 
 	TP_PROTO(unsigned int type, unsigned int state, unsigned int cpu_id),
@@ -70,6 +75,85 @@ TRACE_EVENT(power_end,
 
 );
 
+/*
+ * The clock events are used for clock enable/disable and for
+ *  clock rate change
+ */
+DECLARE_EVENT_CLASS(clock,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id),
+
+	TP_STRUCT__entry(
+		__string(       name,           name            )
+		__field(        u64,            state           )
+		__field(        u64,            cpu_id          )
+	),
+
+	TP_fast_assign(
+		__assign_str(name, name);
+		__entry->state = state;
+		__entry->cpu_id = cpu_id;
+	),
+
+	TP_printk("%s state=%lu cpu_id=%lu", __get_str(name),
+		(unsigned long)__entry->state, (unsigned long)__entry->cpu_id)
+);
+
+DEFINE_EVENT(clock, clock_enable,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id)
+);
+
+DEFINE_EVENT(clock, clock_disable,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id)
+);
+
+DEFINE_EVENT(clock, clock_set_rate,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id)
+);
+
+/*
+ * The power domain events are used for power domains transitions
+ */
+DECLARE_EVENT_CLASS(power_domain,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id),
+
+	TP_STRUCT__entry(
+		__string(       name,           name            )
+		__field(        u64,            state           )
+		__field(        u64,            cpu_id          )
+	),
+
+	TP_fast_assign(
+		__assign_str(name, name);
+		__entry->state = state;
+		__entry->cpu_id = cpu_id;
+),
+
+	TP_printk("%s state=%lu cpu_id=%lu", __get_str(name),
+		(unsigned long)__entry->state, (unsigned long)__entry->cpu_id)
+);
+
+DEFINE_EVENT(power_domain, power_domain_target,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id)
+);
+
 #endif /* _TRACE_POWER_H */
 
 /* This part must be outside protection */

include/trace/events/skb.h

@@ -35,6 +35,23 @@ TRACE_EVENT(kfree_skb,
 		__entry->skbaddr, __entry->protocol, __entry->location)
 );
 
+TRACE_EVENT(consume_skb,
+
+	TP_PROTO(struct sk_buff *skb),
+
+	TP_ARGS(skb),
+
+	TP_STRUCT__entry(
+		__field(	void *,	skbaddr	)
+	),
+
+	TP_fast_assign(
+		__entry->skbaddr = skb;
+	),
+
+	TP_printk("skbaddr=%p", __entry->skbaddr)
+);
+
 TRACE_EVENT(skb_copy_datagram_iovec,
 
 	TP_PROTO(const struct sk_buff *skb, int len),

init/Kconfig

@@ -21,6 +21,13 @@ config CONSTRUCTORS
 	depends on !UML
 	default y
 
+config HAVE_IRQ_WORK
+	bool
+
+config IRQ_WORK
+	bool
+	depends on HAVE_IRQ_WORK
+
 menu "General setup"
 
 config EXPERIMENTAL
@@ -1005,6 +1012,7 @@ config PERF_EVENTS
 	default y if (PROFILING || PERF_COUNTERS)
 	depends on HAVE_PERF_EVENTS
 	select ANON_INODES
+	select IRQ_WORK
 	help
 	  Enable kernel support for various performance events provided
 	  by software and hardware.

kernel/Makefile

@@ -10,7 +10,7 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o \
 	    kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
 	    hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
 	    notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \
-	    async.o range.o
+	    async.o range.o jump_label.o
 obj-$(CONFIG_HAVE_EARLY_RES) += early_res.o
 obj-y += groups.o
 
@@ -23,6 +23,7 @@ CFLAGS_REMOVE_rtmutex-debug.o = -pg
 CFLAGS_REMOVE_cgroup-debug.o = -pg
 CFLAGS_REMOVE_sched_clock.o = -pg
 CFLAGS_REMOVE_perf_event.o = -pg
+CFLAGS_REMOVE_irq_work.o = -pg
 endif
 
 obj-$(CONFIG_FREEZER) += freezer.o
@@ -101,6 +102,7 @@ obj-$(CONFIG_TRACING) += trace/
 obj-$(CONFIG_X86_DS) += trace/
 obj-$(CONFIG_RING_BUFFER) += trace/
 obj-$(CONFIG_SMP) += sched_cpupri.o
+obj-$(CONFIG_IRQ_WORK) += irq_work.o
 obj-$(CONFIG_PERF_EVENTS) += perf_event.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
 obj-$(CONFIG_USER_RETURN_NOTIFIER) += user-return-notifier.o

kernel/exit.c

@@ -149,9 +149,7 @@ static void delayed_put_task_struct(struct rcu_head *rhp)
 {
 	struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
 
-#ifdef CONFIG_PERF_EVENTS
+	perf_event_delayed_put(tsk);
-	WARN_ON_ONCE(tsk->perf_event_ctxp);
-#endif
 	trace_sched_process_free(tsk);
 	put_task_struct(tsk);
 }

kernel/hw_breakpoint.c

@@ -113,12 +113,12 @@ static unsigned int max_task_bp_pinned(int cpu, enum bp_type_idx type)
  */
 static int task_bp_pinned(struct perf_event *bp, enum bp_type_idx type)
 {
-	struct perf_event_context *ctx = bp->ctx;
+	struct task_struct *tsk = bp->hw.bp_target;
 	struct perf_event *iter;
 	int count = 0;
 
 	list_for_each_entry(iter, &bp_task_head, hw.bp_list) {
-		if (iter->ctx == ctx && find_slot_idx(iter) == type)
+		if (iter->hw.bp_target == tsk && find_slot_idx(iter) == type)
 			count += hw_breakpoint_weight(iter);
 	}
 
@@ -134,7 +134,7 @@ fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp,
 		    enum bp_type_idx type)
 {
 	int cpu = bp->cpu;
-	struct task_struct *tsk = bp->ctx->task;
+	struct task_struct *tsk = bp->hw.bp_target;
 
 	if (cpu >= 0) {
 		slots->pinned = per_cpu(nr_cpu_bp_pinned[type], cpu);
@@ -213,7 +213,7 @@ toggle_bp_slot(struct perf_event *bp, bool enable, enum bp_type_idx type,
 	       int weight)
 {
 	int cpu = bp->cpu;
-	struct task_struct *tsk = bp->ctx->task;
+	struct task_struct *tsk = bp->hw.bp_target;
 
 	/* Pinned counter cpu profiling */
 	if (!tsk) {
@@ -433,8 +433,7 @@ register_user_hw_breakpoint(struct perf_event_attr *attr,
 			    perf_overflow_handler_t triggered,
 			    struct task_struct *tsk)
 {
-	return perf_event_create_kernel_counter(attr, -1, task_pid_vnr(tsk),
+	return perf_event_create_kernel_counter(attr, -1, tsk, triggered);
-						triggered);
 }
 EXPORT_SYMBOL_GPL(register_user_hw_breakpoint);
 
@@ -516,7 +515,7 @@ register_wide_hw_breakpoint(struct perf_event_attr *attr,
 	get_online_cpus();
 	for_each_online_cpu(cpu) {
 		pevent = per_cpu_ptr(cpu_events, cpu);
-		bp = perf_event_create_kernel_counter(attr, cpu, -1, triggered);
+		bp = perf_event_create_kernel_counter(attr, cpu, NULL, triggered);
 
 		*pevent = bp;
 
@@ -566,6 +565,61 @@ static struct notifier_block hw_breakpoint_exceptions_nb = {
 	.priority = 0x7fffffff
 };
 
+static void bp_perf_event_destroy(struct perf_event *event)
+{
+	release_bp_slot(event);
+}
+
+static int hw_breakpoint_event_init(struct perf_event *bp)
+{
+	int err;
+
+	if (bp->attr.type != PERF_TYPE_BREAKPOINT)
+		return -ENOENT;
+
+	err = register_perf_hw_breakpoint(bp);
+	if (err)
+		return err;
+
+	bp->destroy = bp_perf_event_destroy;
+
+	return 0;
+}
+
+static int hw_breakpoint_add(struct perf_event *bp, int flags)
+{
+	if (!(flags & PERF_EF_START))
+		bp->hw.state = PERF_HES_STOPPED;
+
+	return arch_install_hw_breakpoint(bp);
+}
+
+static void hw_breakpoint_del(struct perf_event *bp, int flags)
+{
+	arch_uninstall_hw_breakpoint(bp);
+}
+
+static void hw_breakpoint_start(struct perf_event *bp, int flags)
+{
+	bp->hw.state = 0;
+}
+
+static void hw_breakpoint_stop(struct perf_event *bp, int flags)
+{
+	bp->hw.state = PERF_HES_STOPPED;
+}
+
+static struct pmu perf_breakpoint = {
+	.task_ctx_nr	= perf_sw_context, /* could eventually get its own */
+
+	.event_init	= hw_breakpoint_event_init,
+	.add		= hw_breakpoint_add,
+	.del		= hw_breakpoint_del,
+	.start		= hw_breakpoint_start,
+	.stop		= hw_breakpoint_stop,
+	.read		= hw_breakpoint_pmu_read,
+};
+
 static int __init init_hw_breakpoint(void)
 {
 	unsigned int **task_bp_pinned;
@@ -587,6 +641,8 @@ static int __init init_hw_breakpoint(void)
 
 	constraints_initialized = 1;
 
+	perf_pmu_register(&perf_breakpoint);
+
 	return register_die_notifier(&hw_breakpoint_exceptions_nb);
 
  err_alloc:
@@ -602,8 +658,3 @@ static int __init init_hw_breakpoint(void)
 core_initcall(init_hw_breakpoint);
 
 
-struct pmu perf_ops_bp = {
-	.enable		= arch_install_hw_breakpoint,
-	.disable	= arch_uninstall_hw_breakpoint,
-	.read		= hw_breakpoint_pmu_read,
-};

kernel/irq_work.c

@@ -0,0 +1,164 @@
+/*
+ * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *
+ * Provides a framework for enqueueing and running callbacks from hardirq
+ * context. The enqueueing is NMI-safe.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/irq_work.h>
+#include <linux/hardirq.h>
+
+/*
+ * An entry can be in one of four states:
+ *
+ * free	     NULL, 0 -> {claimed}       : free to be used
+ * claimed   NULL, 3 -> {pending}       : claimed to be enqueued
+ * pending   next, 3 -> {busy}          : queued, pending callback
+ * busy      NULL, 2 -> {free, claimed} : callback in progress, can be claimed
+ *
+ * We use the lower two bits of the next pointer to keep PENDING and BUSY
+ * flags.
+ */
+
+#define IRQ_WORK_PENDING	1UL
+#define IRQ_WORK_BUSY		2UL
+#define IRQ_WORK_FLAGS		3UL
+
+static inline bool irq_work_is_set(struct irq_work *entry, int flags)
+{
+	return (unsigned long)entry->next & flags;
+}
+
+static inline struct irq_work *irq_work_next(struct irq_work *entry)
+{
+	unsigned long next = (unsigned long)entry->next;
+	next &= ~IRQ_WORK_FLAGS;
+	return (struct irq_work *)next;
+}
+
+static inline struct irq_work *next_flags(struct irq_work *entry, int flags)
+{
+	unsigned long next = (unsigned long)entry;
+	next |= flags;
+	return (struct irq_work *)next;
+}
+
+static DEFINE_PER_CPU(struct irq_work *, irq_work_list);
+
+/*
+ * Claim the entry so that no one else will poke at it.
+ */
+static bool irq_work_claim(struct irq_work *entry)
+{
+	struct irq_work *next, *nflags;
+
+	do {
+		next = entry->next;
+		if ((unsigned long)next & IRQ_WORK_PENDING)
+			return false;
+		nflags = next_flags(next, IRQ_WORK_FLAGS);
+	} while (cmpxchg(&entry->next, next, nflags) != next);
+
+	return true;
+}
+
+
+void __weak arch_irq_work_raise(void)
+{
+	/*
+	 * Lame architectures will get the timer tick callback
+	 */
+}
+
+/*
+ * Queue the entry and raise the IPI if needed.
+ */
+static void __irq_work_queue(struct irq_work *entry)
+{
+	struct irq_work **head, *next;
+
+	head = &get_cpu_var(irq_work_list);
+
+	do {
+		next = *head;
+		/* Can assign non-atomic because we keep the flags set. */
+		entry->next = next_flags(next, IRQ_WORK_FLAGS);
+	} while (cmpxchg(head, next, entry) != next);
+
+	/* The list was empty, raise self-interrupt to start processing. */
+	if (!irq_work_next(entry))
+		arch_irq_work_raise();
+
+	put_cpu_var(irq_work_list);
+}
+
+/*
+ * Enqueue the irq_work @entry, returns true on success, failure when the
+ * @entry was already enqueued by someone else.
+ *
+ * Can be re-enqueued while the callback is still in progress.
+ */
+bool irq_work_queue(struct irq_work *entry)
+{
+	if (!irq_work_claim(entry)) {
+		/*
+		 * Already enqueued, can't do!
+		 */
+		return false;
+	}
+
+	__irq_work_queue(entry);
+	return true;
+}
+EXPORT_SYMBOL_GPL(irq_work_queue);
+
+/*
+ * Run the irq_work entries on this cpu. Requires to be ran from hardirq
+ * context with local IRQs disabled.
+ */
+void irq_work_run(void)
+{
+	struct irq_work *list, **head;
+
+	head = &__get_cpu_var(irq_work_list);
+	if (*head == NULL)
+		return;
+
+	BUG_ON(!in_irq());
+	BUG_ON(!irqs_disabled());
+
+	list = xchg(head, NULL);
+	while (list != NULL) {
+		struct irq_work *entry = list;
+
+		list = irq_work_next(list);
+
+		/*
+		 * Clear the PENDING bit, after this point the @entry
+		 * can be re-used.
+		 */
+		entry->next = next_flags(NULL, IRQ_WORK_BUSY);
+		entry->func(entry);
+		/*
+		 * Clear the BUSY bit and return to the free state if
+		 * no-one else claimed it meanwhile.
+		 */
+		cmpxchg(&entry->next, next_flags(NULL, IRQ_WORK_BUSY), NULL);
+	}
+}
+EXPORT_SYMBOL_GPL(irq_work_run);
+
+/*
+ * Synchronize against the irq_work @entry, ensures the entry is not
+ * currently in use.
+ */
+void irq_work_sync(struct irq_work *entry)
+{
+	WARN_ON_ONCE(irqs_disabled());
+
+	while (irq_work_is_set(entry, IRQ_WORK_BUSY))
+		cpu_relax();
+}
+EXPORT_SYMBOL_GPL(irq_work_sync);