performance counters: x86 support

Implement performance counters for x86 Intel CPUs.

It's simplified right now: the PERFMON CPU feature is assumed,
which is available in Core2 and later Intel CPUs.

The design is flexible to be extended to more CPU types as well.
Signed-off-by: NIngo Molnar <mingo@elte.hu>

arch/x86/Kconfig

@@ -643,6 +643,7 @@ config X86_UP_IOAPIC
 config X86_LOCAL_APIC
 	def_bool y
 	depends on X86_64 || (X86_32 && (X86_UP_APIC || (SMP && !X86_VOYAGER) || X86_GENERICARCH))
+	select HAVE_PERF_COUNTERS
 
 config X86_IO_APIC
 	def_bool y

arch/x86/ia32/ia32entry.S

@@ -823,7 +823,8 @@ ia32_sys_call_table:
 	.quad compat_sys_signalfd4
 	.quad sys_eventfd2
 	.quad sys_epoll_create1
-	.quad sys_dup3			/* 330 */
+	.quad sys_dup3				/* 330 */
 	.quad sys_pipe2
 	.quad sys_inotify_init1
+	.quad sys_perf_counter_open
 ia32_syscall_end:

arch/x86/include/asm/hardirq_32.h

@@ -9,6 +9,7 @@ typedef struct {
 	unsigned long idle_timestamp;
 	unsigned int __nmi_count;	/* arch dependent */
 	unsigned int apic_timer_irqs;	/* arch dependent */
+	unsigned int apic_perf_irqs;	/* arch dependent */
 	unsigned int irq0_irqs;
 	unsigned int irq_resched_count;
 	unsigned int irq_call_count;

arch/x86/include/asm/hw_irq.h

@@ -30,6 +30,8 @@
 /* Interrupt handlers registered during init_IRQ */
 extern void apic_timer_interrupt(void);
 extern void error_interrupt(void);
+extern void perf_counter_interrupt(void);
+
 extern void spurious_interrupt(void);
 extern void thermal_interrupt(void);
 extern void reschedule_interrupt(void);

arch/x86/include/asm/intel_arch_perfmon.h

 #ifndef _ASM_X86_INTEL_ARCH_PERFMON_H
 #define _ASM_X86_INTEL_ARCH_PERFMON_H
 
-#define MSR_ARCH_PERFMON_PERFCTR0		0xc1
-#define MSR_ARCH_PERFMON_PERFCTR1		0xc2
+#define MSR_ARCH_PERFMON_PERFCTR0			      0xc1
+#define MSR_ARCH_PERFMON_PERFCTR1			      0xc2
 
-#define MSR_ARCH_PERFMON_EVENTSEL0		0x186
-#define MSR_ARCH_PERFMON_EVENTSEL1		0x187
+#define MSR_ARCH_PERFMON_EVENTSEL0			     0x186
+#define MSR_ARCH_PERFMON_EVENTSEL1			     0x187
 
-#define ARCH_PERFMON_EVENTSEL0_ENABLE	(1 << 22)
-#define ARCH_PERFMON_EVENTSEL_INT	(1 << 20)
-#define ARCH_PERFMON_EVENTSEL_OS	(1 << 17)
-#define ARCH_PERFMON_EVENTSEL_USR	(1 << 16)
+#define ARCH_PERFMON_EVENTSEL0_ENABLE			  (1 << 22)
+#define ARCH_PERFMON_EVENTSEL_INT			  (1 << 20)
+#define ARCH_PERFMON_EVENTSEL_OS			  (1 << 17)
+#define ARCH_PERFMON_EVENTSEL_USR			  (1 << 16)
 
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL	(0x3c)
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK	(0x00 << 8)
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX (0)
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL		      0x3c
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK		(0x00 << 8)
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX 		 0
 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT \
-	(1 << (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX))
+		(1 << (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX))
+
+#define ARCH_PERFMON_BRANCH_MISSES_RETIRED			 6
 
 union cpuid10_eax {
 	struct {
@@ -28,4 +30,12 @@ union cpuid10_eax {
 	unsigned int full;
 };
 
+#ifdef CONFIG_PERF_COUNTERS
+extern void init_hw_perf_counters(void);
+extern void perf_counters_lapic_init(int nmi);
+#else
+static inline void init_hw_perf_counters(void)		{ }
+static inline void perf_counters_lapic_init(int nmi)	{ }
+#endif
+
 #endif /* _ASM_X86_INTEL_ARCH_PERFMON_H */

arch/x86/include/asm/irq_vectors.h

@@ -86,6 +86,11 @@
  */
 #define LOCAL_TIMER_VECTOR	0xef
 
+/*
+ * Performance monitoring interrupt vector:
+ */
+#define LOCAL_PERF_VECTOR	0xee
+
 /*
  * First APIC vector available to drivers: (vectors 0x30-0xee) we
  * start at 0x31(0x41) to spread out vectors evenly between priority

arch/x86/include/asm/mach-default/entry_arch.h

@@ -25,10 +25,15 @@ BUILD_INTERRUPT(irq_move_cleanup_interrupt,IRQ_MOVE_CLEANUP_VECTOR)
  * a much simpler SMP time architecture:
  */
 #ifdef CONFIG_X86_LOCAL_APIC
+
 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_COUNTERS
+BUILD_INTERRUPT(perf_counter_interrupt, LOCAL_PERF_VECTOR)
+#endif
+
 #ifdef CONFIG_X86_MCE_P4THERMAL
 BUILD_INTERRUPT(thermal_interrupt,THERMAL_APIC_VECTOR)
 #endif

arch/x86/include/asm/pda.h

@@ -30,6 +30,7 @@ struct x8664_pda {
 	short isidle;
 	struct mm_struct *active_mm;
 	unsigned apic_timer_irqs;
+	unsigned apic_perf_irqs;
 	unsigned irq0_irqs;
 	unsigned irq_resched_count;
 	unsigned irq_call_count;

arch/x86/include/asm/thread_info.h

@@ -80,6 +80,7 @@ struct thread_info {
 #define TIF_SYSCALL_AUDIT	7	/* syscall auditing active */
 #define TIF_SECCOMP		8	/* secure computing */
 #define TIF_MCE_NOTIFY		10	/* notify userspace of an MCE */
+#define TIF_PERF_COUNTERS	11	/* notify perf counter work */
 #define TIF_NOTSC		16	/* TSC is not accessible in userland */
 #define TIF_IA32		17	/* 32bit process */
 #define TIF_FORK		18	/* ret_from_fork */
@@ -103,6 +104,7 @@ struct thread_info {
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
 #define _TIF_SECCOMP		(1 << TIF_SECCOMP)
 #define _TIF_MCE_NOTIFY		(1 << TIF_MCE_NOTIFY)
+#define _TIF_PERF_COUNTERS	(1 << TIF_PERF_COUNTERS)
 #define _TIF_NOTSC		(1 << TIF_NOTSC)
 #define _TIF_IA32		(1 << TIF_IA32)
 #define _TIF_FORK		(1 << TIF_FORK)
@@ -135,7 +137,7 @@ struct thread_info {
 
 /* Only used for 64 bit */
 #define _TIF_DO_NOTIFY_MASK						\
-	(_TIF_SIGPENDING|_TIF_MCE_NOTIFY|_TIF_NOTIFY_RESUME)
+	(_TIF_SIGPENDING|_TIF_MCE_NOTIFY|_TIF_PERF_COUNTERS|_TIF_NOTIFY_RESUME)
 
 /* flags to check in __switch_to() */
 #define _TIF_WORK_CTXSW							\

arch/x86/include/asm/unistd_32.h

@@ -338,6 +338,7 @@
 #define __NR_dup3		330
 #define __NR_pipe2		331
 #define __NR_inotify_init1	332
+#define __NR_perf_counter_open	333
 
 #ifdef __KERNEL__
 

arch/x86/include/asm/unistd_64.h

@@ -653,7 +653,8 @@ __SYSCALL(__NR_dup3, sys_dup3)
 __SYSCALL(__NR_pipe2, sys_pipe2)
 #define __NR_inotify_init1			294
 __SYSCALL(__NR_inotify_init1, sys_inotify_init1)
-
+#define __NR_perf_counter_open		295
+__SYSCALL(__NR_perf_counter_open, sys_perf_counter_open)
 
 #ifndef __NO_STUBS
 #define __ARCH_WANT_OLD_READDIR

arch/x86/kernel/apic.c

@@ -31,6 +31,7 @@
 #include <linux/dmi.h>
 #include <linux/dmar.h>
 
+#include <asm/intel_arch_perfmon.h>
 #include <asm/atomic.h>
 #include <asm/smp.h>
 #include <asm/mtrr.h>
@@ -1147,6 +1148,7 @@ void __cpuinit setup_local_APIC(void)
 		apic_write(APIC_ESR, 0);
 	}
 #endif
+	perf_counters_lapic_init(0);
 
 	preempt_disable();
 

arch/x86/kernel/cpu/Makefile

 #
-# Makefile for x86-compatible CPU details and quirks
+# Makefile for x86-compatible CPU details, features and quirks
 #
 
 obj-y			:= intel_cacheinfo.o addon_cpuid_features.o
@@ -16,11 +16,13 @@ obj-$(CONFIG_CPU_SUP_CENTAUR_64)	+= centaur_64.o
 obj-$(CONFIG_CPU_SUP_TRANSMETA_32)	+= transmeta.o
 obj-$(CONFIG_CPU_SUP_UMC_32)		+= umc.o
 
-obj-$(CONFIG_X86_MCE)	+= mcheck/
-obj-$(CONFIG_MTRR)	+= mtrr/
-obj-$(CONFIG_CPU_FREQ)	+= cpufreq/
+obj-$(CONFIG_PERF_COUNTERS)		+= perf_counter.o
 
-obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o
+obj-$(CONFIG_X86_MCE)			+= mcheck/
+obj-$(CONFIG_MTRR)			+= mtrr/
+obj-$(CONFIG_CPU_FREQ)			+= cpufreq/
+
+obj-$(CONFIG_X86_LOCAL_APIC)		+= perfctr-watchdog.o
 
 quiet_cmd_mkcapflags = MKCAP   $@
       cmd_mkcapflags = $(PERL) $(srctree)/$(src)/mkcapflags.pl $< $@

arch/x86/kernel/cpu/common.c

@@ -17,6 +17,7 @@
 #include <asm/mmu_context.h>
 #include <asm/mtrr.h>
 #include <asm/mce.h>
+#include <asm/intel_arch_perfmon.h>
 #include <asm/pat.h>
 #include <asm/asm.h>
 #include <asm/numa.h>
@@ -750,6 +751,7 @@ void __init identify_boot_cpu(void)
 #else
 	vgetcpu_set_mode();
 #endif
+	init_hw_perf_counters();
 }
 
 void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c)

arch/x86/kernel/cpu/perf_counter.c

+/*
+ * Performance counter x86 architecture code
+ *
+ *  Copyright(C) 2008 Thomas Gleixner <tglx@linutronix.de>
+ *  Copyright(C) 2008 Red Hat, Inc., Ingo Molnar
+ *
+ *  For licencing details see kernel-base/COPYING
+ */
+
+#include <linux/perf_counter.h>
+#include <linux/capability.h>
+#include <linux/notifier.h>
+#include <linux/hardirq.h>
+#include <linux/kprobes.h>
+#include <linux/kdebug.h>
+#include <linux/sched.h>
+
+#include <asm/intel_arch_perfmon.h>
+#include <asm/apic.h>
+
+static bool perf_counters_initialized __read_mostly;
+
+/*
+ * Number of (generic) HW counters:
+ */
+static int nr_hw_counters __read_mostly;
+static u32 perf_counter_mask __read_mostly;
+
+/* No support for fixed function counters yet */
+
+#define MAX_HW_COUNTERS		8
+
+struct cpu_hw_counters {
+	struct perf_counter	*counters[MAX_HW_COUNTERS];
+	unsigned long		used[BITS_TO_LONGS(MAX_HW_COUNTERS)];
+	int			enable_all;
+};
+
+/*
+ * Intel PerfMon v3. Used on Core2 and later.
+ */
+static DEFINE_PER_CPU(struct cpu_hw_counters, cpu_hw_counters);
+
+const int intel_perfmon_event_map[] =
+{
+  [PERF_COUNT_CYCLES]			= 0x003c,
+  [PERF_COUNT_INSTRUCTIONS]		= 0x00c0,
+  [PERF_COUNT_CACHE_REFERENCES]		= 0x4f2e,
+  [PERF_COUNT_CACHE_MISSES]		= 0x412e,
+  [PERF_COUNT_BRANCH_INSTRUCTIONS]	= 0x00c4,
+  [PERF_COUNT_BRANCH_MISSES]		= 0x00c5,
+};
+
+const int max_intel_perfmon_events = ARRAY_SIZE(intel_perfmon_event_map);
+
+/*
+ * Setup the hardware configuration for a given hw_event_type
+ */
+int hw_perf_counter_init(struct perf_counter *counter, s32 hw_event_type)
+{
+	struct hw_perf_counter *hwc = &counter->hw;
+
+	if (unlikely(!perf_counters_initialized))
+		return -EINVAL;
+
+	/*
+	 * Count user events, and generate PMC IRQs:
+	 * (keep 'enabled' bit clear for now)
+	 */
+	hwc->config = ARCH_PERFMON_EVENTSEL_USR | ARCH_PERFMON_EVENTSEL_INT;
+
+	/*
+	 * If privileged enough, count OS events too, and allow
+	 * NMI events as well:
+	 */
+	hwc->nmi = 0;
+	if (capable(CAP_SYS_ADMIN)) {
+		hwc->config |= ARCH_PERFMON_EVENTSEL_OS;
+		if (hw_event_type & PERF_COUNT_NMI)
+			hwc->nmi = 1;
+	}
+
+	hwc->config_base = MSR_ARCH_PERFMON_EVENTSEL0;
+	hwc->counter_base = MSR_ARCH_PERFMON_PERFCTR0;
+
+	hwc->irq_period = counter->__irq_period;
+	/*
+	 * Intel PMCs cannot be accessed sanely above 32 bit width,
+	 * so we install an artificial 1<<31 period regardless of
+	 * the generic counter period:
+	 */
+	if (!hwc->irq_period)
+		hwc->irq_period = 0x7FFFFFFF;
+
+	hwc->next_count = -((s32) hwc->irq_period);
+
+	/*
+	 * Negative event types mean raw encoded event+umask values:
+	 */
+	if (hw_event_type < 0) {
+		counter->hw_event_type = -hw_event_type;
+		counter->hw_event_type &= ~PERF_COUNT_NMI;
+	} else {
+		hw_event_type &= ~PERF_COUNT_NMI;
+		if (hw_event_type >= max_intel_perfmon_events)
+			return -EINVAL;
+		/*
+		 * The generic map:
+		 */
+		counter->hw_event_type = intel_perfmon_event_map[hw_event_type];
+	}
+	hwc->config |= counter->hw_event_type;
+	counter->wakeup_pending = 0;
+
+	return 0;
+}
+
+static void __hw_perf_enable_all(void)
+{
+	wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, perf_counter_mask, 0);
+}
+
+void hw_perf_enable_all(void)
+{
+	struct cpu_hw_counters *cpuc = &__get_cpu_var(cpu_hw_counters);
+
+	cpuc->enable_all = 1;
+	__hw_perf_enable_all();
+}
+
+void hw_perf_disable_all(void)
+{
+	struct cpu_hw_counters *cpuc = &__get_cpu_var(cpu_hw_counters);
+
+	cpuc->enable_all = 0;
+	wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0, 0);
+}
+
+static DEFINE_PER_CPU(u64, prev_next_count[MAX_HW_COUNTERS]);
+
+static void __hw_perf_counter_enable(struct hw_perf_counter *hwc, int idx)
+{
+	per_cpu(prev_next_count[idx], smp_processor_id()) = hwc->next_count;
+
+	wrmsr(hwc->counter_base + idx, hwc->next_count, 0);
+	wrmsr(hwc->config_base + idx, hwc->config, 0);
+}
+
+void hw_perf_counter_enable(struct perf_counter *counter)
+{
+	struct cpu_hw_counters *cpuc = &__get_cpu_var(cpu_hw_counters);
+	struct hw_perf_counter *hwc = &counter->hw;
+	int idx = hwc->idx;
+
+	/* Try to get the previous counter again */
+	if (test_and_set_bit(idx, cpuc->used)) {
+		idx = find_first_zero_bit(cpuc->used, nr_hw_counters);
+		set_bit(idx, cpuc->used);
+		hwc->idx = idx;
+	}
+
+	perf_counters_lapic_init(hwc->nmi);
+
+	wrmsr(hwc->config_base + idx,
+	      hwc->config & ~ARCH_PERFMON_EVENTSEL0_ENABLE, 0);
+
+	cpuc->counters[idx] = counter;
+	counter->hw.config |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+	__hw_perf_counter_enable(hwc, idx);
+}
+
+#ifdef CONFIG_X86_64
+static inline void atomic64_counter_set(struct perf_counter *counter, u64 val)
+{
+	atomic64_set(&counter->count, val);
+}
+
+static inline u64 atomic64_counter_read(struct perf_counter *counter)
+{
+	return atomic64_read(&counter->count);
+}
+#else
+/*
+ * Todo: add proper atomic64_t support to 32-bit x86:
+ */
+static inline void atomic64_counter_set(struct perf_counter *counter, u64 val64)
+{
+	u32 *val32 = (void *)&val64;
+
+	atomic_set(counter->count32 + 0, *(val32 + 0));
+	atomic_set(counter->count32 + 1, *(val32 + 1));
+}
+
+static inline u64 atomic64_counter_read(struct perf_counter *counter)
+{
+	return atomic_read(counter->count32 + 0) |
+		(u64) atomic_read(counter->count32 + 1) << 32;
+}
+#endif
+
+static void __hw_perf_save_counter(struct perf_counter *counter,
+				   struct hw_perf_counter *hwc, int idx)
+{
+	s64 raw = -1;
+	s64 delta;
+	int err;
+
+	/*
+	 * Get the raw hw counter value:
+	 */
+	err = rdmsrl_safe(hwc->counter_base + idx, &raw);
+	WARN_ON_ONCE(err);
+
+	/*
+	 * Rebase it to zero (it started counting at -irq_period),
+	 * to see the delta since ->prev_count:
+	 */
+	delta = (s64)hwc->irq_period + (s64)(s32)raw;
+
+	atomic64_counter_set(counter, hwc->prev_count + delta);
+
+	/*
+	 * Adjust the ->prev_count offset - if we went beyond
+	 * irq_period of units, then we got an IRQ and the counter
+	 * was set back to -irq_period:
+	 */
+	while (delta >= (s64)hwc->irq_period) {
+		hwc->prev_count += hwc->irq_period;
+		delta -= (s64)hwc->irq_period;
+	}
+
+	/*
+	 * Calculate the next raw counter value we'll write into
+	 * the counter at the next sched-in time:
+	 */
+	delta -= (s64)hwc->irq_period;
+
+	hwc->next_count = (s32)delta;
+}
+
+void perf_counter_print_debug(void)
+{
+	u64 ctrl, status, overflow, pmc_ctrl, pmc_count, next_count;
+	int cpu, err, idx;
+
+	local_irq_disable();
+
+	cpu = smp_processor_id();
+
+	err = rdmsrl_safe(MSR_CORE_PERF_GLOBAL_CTRL, &ctrl);
+	WARN_ON_ONCE(err);
+
+	err = rdmsrl_safe(MSR_CORE_PERF_GLOBAL_STATUS, &status);
+	WARN_ON_ONCE(err);
+
+	err = rdmsrl_safe(MSR_CORE_PERF_GLOBAL_OVF_CTRL, &overflow);
+	WARN_ON_ONCE(err);
+
+	printk(KERN_INFO "\n");
+	printk(KERN_INFO "CPU#%d: ctrl:       %016llx\n", cpu, ctrl);
+	printk(KERN_INFO "CPU#%d: status:     %016llx\n", cpu, status);
+	printk(KERN_INFO "CPU#%d: overflow:   %016llx\n", cpu, overflow);
+
+	for (idx = 0; idx < nr_hw_counters; idx++) {
+		err = rdmsrl_safe(MSR_ARCH_PERFMON_EVENTSEL0 + idx, &pmc_ctrl);
+		WARN_ON_ONCE(err);
+
+		err = rdmsrl_safe(MSR_ARCH_PERFMON_PERFCTR0 + idx, &pmc_count);
+		WARN_ON_ONCE(err);
+
+		next_count = per_cpu(prev_next_count[idx], cpu);
+
+		printk(KERN_INFO "CPU#%d: PMC%d ctrl:  %016llx\n",
+			cpu, idx, pmc_ctrl);
+		printk(KERN_INFO "CPU#%d: PMC%d count: %016llx\n",
+			cpu, idx, pmc_count);
+		printk(KERN_INFO "CPU#%d: PMC%d next:  %016llx\n",
+			cpu, idx, next_count);
+	}
+	local_irq_enable();
+}
+
+void hw_perf_counter_disable(struct perf_counter *counter)
+{
+	struct cpu_hw_counters *cpuc = &__get_cpu_var(cpu_hw_counters);
+	struct hw_perf_counter *hwc = &counter->hw;
+	unsigned int idx = hwc->idx;
+
+	counter->hw.config &= ~ARCH_PERFMON_EVENTSEL0_ENABLE;
+	wrmsr(hwc->config_base + idx, hwc->config, 0);
+
+	clear_bit(idx, cpuc->used);
+	cpuc->counters[idx] = NULL;
+	__hw_perf_save_counter(counter, hwc, idx);
+}
+
+void hw_perf_counter_read(struct perf_counter *counter)
+{
+	struct hw_perf_counter *hwc = &counter->hw;
+	unsigned long addr = hwc->counter_base + hwc->idx;
+	s64 offs, val = -1LL;
+	s32 val32;
+	int err;
+
+	/* Careful: NMI might modify the counter offset */
+	do {
+		offs = hwc->prev_count;
+		err = rdmsrl_safe(addr, &val);
+		WARN_ON_ONCE(err);
+	} while (offs != hwc->prev_count);
+
+	val32 = (s32) val;
+	val =  (s64)hwc->irq_period + (s64)val32;
+	atomic64_counter_set(counter, hwc->prev_count + val);
+}
+
+static void perf_store_irq_data(struct perf_counter *counter, u64 data)
+{
+	struct perf_data *irqdata = counter->irqdata;
+
+	if (irqdata->len > PERF_DATA_BUFLEN - sizeof(u64)) {
+		irqdata->overrun++;
+	} else {
+		u64 *p = (u64 *) &irqdata->data[irqdata->len];
+
+		*p = data;
+		irqdata->len += sizeof(u64);
+	}
+}
+
+static void perf_save_and_restart(struct perf_counter *counter)
+{
+	struct hw_perf_counter *hwc = &counter->hw;
+	int idx = hwc->idx;
+
+	wrmsr(hwc->config_base + idx,
+	      hwc->config & ~ARCH_PERFMON_EVENTSEL0_ENABLE, 0);
+
+	if (hwc->config & ARCH_PERFMON_EVENTSEL0_ENABLE) {
+		__hw_perf_save_counter(counter, hwc, idx);
+		__hw_perf_counter_enable(hwc, idx);
+	}
+}
+
+static void
+perf_handle_group(struct perf_counter *leader, u64 *status, u64 *overflown)
+{
+	struct perf_counter_context *ctx = leader->ctx;
+	struct perf_counter *counter;
+	int bit;
+
+	list_for_each_entry(counter, &ctx->counters, list) {
+		if (counter->record_type != PERF_RECORD_SIMPLE ||
+		    counter == leader)
+			continue;
+
+		if (counter->active) {
+			/*
+			 * When counter was not in the overflow mask, we have to
+			 * read it from hardware. We read it as well, when it
+			 * has not been read yet and clear the bit in the
+			 * status mask.
+			 */
+			bit = counter->hw.idx;
+			if (!test_bit(bit, (unsigned long *) overflown) ||
+			    test_bit(bit, (unsigned long *) status)) {
+				clear_bit(bit, (unsigned long *) status);
+				perf_save_and_restart(counter);
+			}
+		}
+		perf_store_irq_data(leader, counter->hw_event_type);
+		perf_store_irq_data(leader, atomic64_counter_read(counter));
+	}
+}
+
+/*
+ * This handler is triggered by the local APIC, so the APIC IRQ handling
+ * rules apply:
+ */
+static void __smp_perf_counter_interrupt(struct pt_regs *regs, int nmi)
+{
+	int bit, cpu = smp_processor_id();
+	struct cpu_hw_counters *cpuc;
+	u64 ack, status;
+
+	rdmsrl(MSR_CORE_PERF_GLOBAL_STATUS, status);
+	if (!status) {
+		ack_APIC_irq();
+		return;
+	}
+
+	/* Disable counters globally */
+	wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0, 0);
+	ack_APIC_irq();
+
+	cpuc = &per_cpu(cpu_hw_counters, cpu);
+
+again:
+	ack = status;
+	for_each_bit(bit, (unsigned long *) &status, nr_hw_counters) {
+		struct perf_counter *counter = cpuc->counters[bit];
+
+		clear_bit(bit, (unsigned long *) &status);
+		if (!counter)
+			continue;
+
+		perf_save_and_restart(counter);
+
+		switch (counter->record_type) {
+		case PERF_RECORD_SIMPLE:
+			continue;
+		case PERF_RECORD_IRQ:
+			perf_store_irq_data(counter, instruction_pointer(regs));
+			break;
+		case PERF_RECORD_GROUP:
+			perf_store_irq_data(counter, counter->hw_event_type);
+			perf_store_irq_data(counter,
+					    atomic64_counter_read(counter));
+			perf_handle_group(counter, &status, &ack);
+			break;
+		}
+		/*
+		 * From NMI context we cannot call into the scheduler to
+		 * do a task wakeup - but we mark these counters as
+		 * wakeup_pending and initate a wakeup callback:
+		 */
+		if (nmi) {
+			counter->wakeup_pending = 1;
+			set_tsk_thread_flag(current, TIF_PERF_COUNTERS);
+		} else {
+			wake_up(&counter->waitq);
+		}
+	}
+
+	wrmsr(MSR_CORE_PERF_GLOBAL_OVF_CTRL, ack, 0);
+
+	/*
+	 * Repeat if there is more work to be done:
+	 */
+	rdmsrl(MSR_CORE_PERF_GLOBAL_STATUS, status);
+	if (status)
+		goto again;
+
+	/*
+	 * Do not reenable when global enable is off:
+	 */
+	if (cpuc->enable_all)
+		__hw_perf_enable_all();
+}
+
+void smp_perf_counter_interrupt(struct pt_regs *regs)
+{
+	irq_enter();
+#ifdef CONFIG_X86_64
+	add_pda(apic_perf_irqs, 1);
+#else
+	per_cpu(irq_stat, smp_processor_id()).apic_perf_irqs++;
+#endif
+	apic_write(APIC_LVTPC, LOCAL_PERF_VECTOR);
+	__smp_perf_counter_interrupt(regs, 0);
+
+	irq_exit();
+}
+
+/*
+ * This handler is triggered by NMI contexts:
+ */
+void perf_counter_notify(struct pt_regs *regs)
+{
+	struct cpu_hw_counters *cpuc;
+	unsigned long flags;
+	int bit, cpu;
+
+	local_irq_save(flags);
+	cpu = smp_processor_id();
+	cpuc = &per_cpu(cpu_hw_counters, cpu);
+
+	for_each_bit(bit, cpuc->used, nr_hw_counters) {
+		struct perf_counter *counter = cpuc->counters[bit];
+
+		if (!counter)
+			continue;
+
+		if (counter->wakeup_pending) {
+			counter->wakeup_pending = 0;
+			wake_up(&counter->waitq);
+		}
+	}
+
+	local_irq_restore(flags);
+}
+
+void __cpuinit perf_counters_lapic_init(int nmi)
+{
+	u32 apic_val;
+
+	if (!perf_counters_initialized)
+		return;
+	/*
+	 * Enable the performance counter vector in the APIC LVT:
+	 */
+	apic_val = apic_read(APIC_LVTERR);
+
+	apic_write(APIC_LVTERR, apic_val | APIC_LVT_MASKED);
+	if (nmi)
+		apic_write(APIC_LVTPC, APIC_DM_NMI);
+	else
+		apic_write(APIC_LVTPC, LOCAL_PERF_VECTOR);
+	apic_write(APIC_LVTERR, apic_val);
+}
+
+static int __kprobes
+perf_counter_nmi_handler(struct notifier_block *self,
+			 unsigned long cmd, void *__args)
+{
+	struct die_args *args = __args;
+	struct pt_regs *regs;
+
+	if (likely(cmd != DIE_NMI_IPI))
+		return NOTIFY_DONE;
+
+	regs = args->regs;
+
+	apic_write(APIC_LVTPC, APIC_DM_NMI);
+	__smp_perf_counter_interrupt(regs, 1);
+
+	return NOTIFY_STOP;
+}
+
+static __read_mostly struct notifier_block perf_counter_nmi_notifier = {
+	.notifier_call		= perf_counter_nmi_handler
+};
+
+void __init init_hw_perf_counters(void)
+{
+	union cpuid10_eax eax;
+	unsigned int unused;
+	unsigned int ebx;
+
+	if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON))
+		return;
+
+	/*
+	 * Check whether the Architectural PerfMon supports
+	 * Branch Misses Retired Event or not.
+	 */
+	cpuid(10, &(eax.full), &ebx, &unused, &unused);
+	if (eax.split.mask_length <= ARCH_PERFMON_BRANCH_MISSES_RETIRED)
+		return;
+
+	printk(KERN_INFO "Intel Performance Monitoring support detected.\n");
+
+	printk(KERN_INFO "... version:      %d\n", eax.split.version_id);
+	printk(KERN_INFO "... num_counters: %d\n", eax.split.num_counters);
+	nr_hw_counters = eax.split.num_counters;
+	if (nr_hw_counters > MAX_HW_COUNTERS) {
+		nr_hw_counters = MAX_HW_COUNTERS;
+		WARN(1, KERN_ERR "hw perf counters %d > max(%d), clipping!",
+			nr_hw_counters, MAX_HW_COUNTERS);
+	}
+	perf_counter_mask = (1 << nr_hw_counters) - 1;
+	perf_max_counters = nr_hw_counters;
+
+	printk(KERN_INFO "... bit_width:    %d\n", eax.split.bit_width);
+	printk(KERN_INFO "... mask_length:  %d\n", eax.split.mask_length);
+
+	perf_counters_lapic_init(0);
+	register_die_notifier(&perf_counter_nmi_notifier);
+
+	perf_counters_initialized = true;
+}

arch/x86/kernel/entry_64.S

@@ -984,6 +984,11 @@ apicinterrupt ERROR_APIC_VECTOR \
 apicinterrupt SPURIOUS_APIC_VECTOR \
 	spurious_interrupt smp_spurious_interrupt
 
+#ifdef CONFIG_PERF_COUNTERS
+apicinterrupt LOCAL_PERF_VECTOR \
+	perf_counter_interrupt smp_perf_counter_interrupt
+#endif
+
 /*
  * Exception entry points.
  */

arch/x86/kernel/irq.c

@@ -56,6 +56,10 @@ static int show_other_interrupts(struct seq_file *p)
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", irq_stats(j)->apic_timer_irqs);
 	seq_printf(p, "  Local timer interrupts\n");
+	seq_printf(p, "CNT: ");
+	for_each_online_cpu(j)
+		seq_printf(p, "%10u ", irq_stats(j)->apic_perf_irqs);
+	seq_printf(p, "  Performance counter interrupts\n");
 #endif
 #ifdef CONFIG_SMP
 	seq_printf(p, "RES: ");
@@ -160,6 +164,7 @@ u64 arch_irq_stat_cpu(unsigned int cpu)
 
 #ifdef CONFIG_X86_LOCAL_APIC
 	sum += irq_stats(cpu)->apic_timer_irqs;
+	sum += irq_stats(cpu)->apic_perf_irqs;
 #endif
 #ifdef CONFIG_SMP
 	sum += irq_stats(cpu)->irq_resched_count;

arch/x86/kernel/irqinit_32.c

@@ -160,6 +160,9 @@ void __init native_init_IRQ(void)
 	/* IPI vectors for APIC spurious and error interrupts */
 	alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
 	alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
+# ifdef CONFIG_PERF_COUNTERS
+	alloc_intr_gate(LOCAL_PERF_VECTOR, perf_counter_interrupt);
+# endif
 #endif
 
 #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_MCE_P4THERMAL)

arch/x86/kernel/irqinit_64.c

@@ -138,6 +138,11 @@ static void __init apic_intr_init(void)
 	/* IPI vectors for APIC spurious and error interrupts */
 	alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
 	alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
+
+	/* Performance monitoring interrupt: */
+#ifdef CONFIG_PERF_COUNTERS
+	alloc_intr_gate(LOCAL_PERF_VECTOR, perf_counter_interrupt);
+#endif
 }
 
 void __init native_init_IRQ(void)

arch/x86/kernel/signal.c

@@ -6,7 +6,7 @@
  *  2000-06-20  Pentium III FXSR, SSE support by Gareth Hughes
  *  2000-2002   x86-64 support by Andi Kleen
  */
-
+#include <linux/perf_counter.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
@@ -891,6 +891,11 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
 		tracehook_notify_resume(regs);
 	}
 
+	if (thread_info_flags & _TIF_PERF_COUNTERS) {
+		clear_thread_flag(TIF_PERF_COUNTERS);
+		perf_counter_notify(regs);
+	}
+
 #ifdef CONFIG_X86_32
 	clear_thread_flag(TIF_IRET);
 #endif /* CONFIG_X86_32 */

arch/x86/kernel/syscall_table_32.S

@@ -332,3 +332,4 @@ ENTRY(sys_call_table)
 	.long sys_dup3			/* 330 */
 	.long sys_pipe2
 	.long sys_inotify_init1
+	.long sys_perf_counter_open