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: Ingo 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/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