From cdd6c482c9ff9c55475ee7392ec8f672eddb7be6 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 21 Sep 2009 12:02:48 +0200 Subject: perf: Do the big rename: Performance Counters -> Performance Events Bye-bye Performance Counters, welcome Performance Events! In the past few months the perfcounters subsystem has grown out its initial role of counting hardware events, and has become (and is becoming) a much broader generic event enumeration, reporting, logging, monitoring, analysis facility. Naming its core object 'perf_counter' and naming the subsystem 'perfcounters' has become more and more of a misnomer. With pending code like hw-breakpoints support the 'counter' name is less and less appropriate. All in one, we've decided to rename the subsystem to 'performance events' and to propagate this rename through all fields, variables and API names. (in an ABI compatible fashion) The word 'event' is also a bit shorter than 'counter' - which makes it slightly more convenient to write/handle as well. Thanks goes to Stephane Eranian who first observed this misnomer and suggested a rename. User-space tooling and ABI compatibility is not affected - this patch should be function-invariant. (Also, defconfigs were not touched to keep the size down.) This patch has been generated via the following script: FILES=$(find * -type f | grep -vE 'oprofile|[^K]config') sed -i \ -e 's/PERF_EVENT_/PERF_RECORD_/g' \ -e 's/PERF_COUNTER/PERF_EVENT/g' \ -e 's/perf_counter/perf_event/g' \ -e 's/nb_counters/nb_events/g' \ -e 's/swcounter/swevent/g' \ -e 's/tpcounter_event/tp_event/g' \ $FILES for N in $(find . -name perf_counter.[ch]); do M=$(echo $N | sed 's/perf_counter/perf_event/g') mv $N $M done FILES=$(find . -name perf_event.*) sed -i \ -e 's/COUNTER_MASK/REG_MASK/g' \ -e 's/COUNTER/EVENT/g' \ -e 's/\/event_id/g' \ -e 's/counter/event/g' \ -e 's/Counter/Event/g' \ $FILES ... to keep it as correct as possible. This script can also be used by anyone who has pending perfcounters patches - it converts a Linux kernel tree over to the new naming. We tried to time this change to the point in time where the amount of pending patches is the smallest: the end of the merge window. Namespace clashes were fixed up in a preparatory patch - and some stylistic fallout will be fixed up in a subsequent patch. ( NOTE: 'counters' are still the proper terminology when we deal with hardware registers - and these sed scripts are a bit over-eager in renaming them. I've undone some of that, but in case there's something left where 'counter' would be better than 'event' we can undo that on an individual basis instead of touching an otherwise nicely automated patch. ) Suggested-by: Stephane Eranian Acked-by: Peter Zijlstra Acked-by: Paul Mackerras Reviewed-by: Arjan van de Ven Cc: Mike Galbraith Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Steven Rostedt Cc: Benjamin Herrenschmidt Cc: David Howells Cc: Kyle McMartin Cc: Martin Schwidefsky Cc: "David S. Miller" Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: LKML-Reference: Signed-off-by: Ingo Molnar --- init/Kconfig | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'init') diff --git a/init/Kconfig b/init/Kconfig index 8e8b76d8a272..cfdf5c322806 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -915,17 +915,17 @@ config AIO by some high performance threaded applications. Disabling this option saves about 7k. -config HAVE_PERF_COUNTERS +config HAVE_PERF_EVENTS bool help See tools/perf/design.txt for details. menu "Performance Counters" -config PERF_COUNTERS +config PERF_EVENTS bool "Kernel Performance Counters" default y if PROFILING - depends on HAVE_PERF_COUNTERS + depends on HAVE_PERF_EVENTS select ANON_INODES help Enable kernel support for performance counter hardware. @@ -947,7 +947,7 @@ config PERF_COUNTERS config EVENT_PROFILE bool "Tracepoint profiling sources" - depends on PERF_COUNTERS && EVENT_TRACING + depends on PERF_EVENTS && EVENT_TRACING default y help Allow the use of tracepoints as software performance counters. -- cgit v1.2.3 From 57c0c15b5244320065374ad2c54f4fbec77a6428 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 21 Sep 2009 12:20:38 +0200 Subject: perf: Tidy up after the big rename - provide compatibility Kconfig entry for existing PERF_COUNTERS .config's - provide courtesy copy of old perf_counter.h, for user-space projects - small indentation fixups - fix up MAINTAINERS - fix small x86 printout fallout - fix up small PowerPC comment fallout (use 'counter' as in register) Reviewed-by: Arjan van de Ven Acked-by: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Benjamin Herrenschmidt Cc: Frederic Weisbecker LKML-Reference: Signed-off-by: Ingo Molnar --- MAINTAINERS | 2 +- arch/powerpc/include/asm/paca.h | 2 +- arch/powerpc/kernel/perf_event.c | 12 +- arch/x86/kernel/cpu/perf_event.c | 14 +- include/linux/perf_counter.h | 441 +++++++++++++++++++++++++++++++++++++++ include/linux/perf_event.h | 98 ++++----- init/Kconfig | 37 +++- kernel/perf_event.c | 4 +- 8 files changed, 534 insertions(+), 76 deletions(-) create mode 100644 include/linux/perf_counter.h (limited to 'init') diff --git a/MAINTAINERS b/MAINTAINERS index 43761a00e3f1..751a307dc44e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4000,7 +4000,7 @@ S: Maintained F: include/linux/delayacct.h F: kernel/delayacct.c -PERFORMANCE COUNTER SUBSYSTEM +PERFORMANCE EVENTS SUBSYSTEM M: Peter Zijlstra M: Paul Mackerras M: Ingo Molnar diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 154f405b642f..7d8514ceceae 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -122,7 +122,7 @@ 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 perf_event_pending; /* PM interrupt while soft-disabled */ /* Stuff for accurate time accounting */ u64 user_time; /* accumulated usermode TB ticks */ diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c index c98321fcb459..197b7d958796 100644 --- a/arch/powerpc/kernel/perf_event.c +++ b/arch/powerpc/kernel/perf_event.c @@ -41,7 +41,7 @@ DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events); struct power_pmu *ppmu; /* - * Normally, to ignore kernel events we set the FCS (freeze events + * Normally, to ignore kernel events we set the FCS (freeze counters * in supervisor mode) bit in MMCR0, but if the kernel runs with the * hypervisor bit set in the MSR, or if we are running on a processor * where the hypervisor bit is forced to 1 (as on Apple G5 processors), @@ -159,7 +159,7 @@ void perf_event_print_debug(void) } /* - * Read one performance monitor event (PMC). + * Read one performance monitor counter (PMC). */ static unsigned long read_pmc(int idx) { @@ -409,7 +409,7 @@ static void power_pmu_read(struct perf_event *event) val = read_pmc(event->hw.idx); } while (atomic64_cmpxchg(&event->hw.prev_count, prev, val) != prev); - /* The events are only 32 bits wide */ + /* The counters are only 32 bits wide */ delta = (val - prev) & 0xfffffffful; atomic64_add(delta, &event->count); atomic64_sub(delta, &event->hw.period_left); @@ -543,7 +543,7 @@ void hw_perf_disable(void) } /* - * Set the 'freeze events' bit. + * Set the 'freeze counters' bit. * The barrier is to make sure the mtspr has been * executed and the PMU has frozen the events * before we return. @@ -1124,7 +1124,7 @@ const struct pmu *hw_perf_event_init(struct perf_event *event) } /* - * A event has overflowed; update its count and record + * A counter has overflowed; update its count and record * things if requested. Note that interrupts are hard-disabled * here so there is no possibility of being interrupted. */ @@ -1271,7 +1271,7 @@ static void perf_event_interrupt(struct pt_regs *regs) /* * Reset MMCR0 to its normal value. This will set PMXE and - * clear FC (freeze events) and PMAO (perf mon alert occurred) + * clear FC (freeze counters) and PMAO (perf mon alert occurred) * and thus allow interrupts to occur again. * XXX might want to use MSR.PM to keep the events frozen until * we get back out of this interrupt. diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 0d03629fb1a5..a3c7adb06b78 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -2081,13 +2081,13 @@ void __init init_hw_perf_events(void) perf_events_lapic_init(); register_die_notifier(&perf_event_nmi_notifier); - pr_info("... version: %d\n", x86_pmu.version); - pr_info("... bit width: %d\n", x86_pmu.event_bits); - pr_info("... generic events: %d\n", x86_pmu.num_events); - pr_info("... value mask: %016Lx\n", x86_pmu.event_mask); - pr_info("... max period: %016Lx\n", x86_pmu.max_period); - pr_info("... fixed-purpose events: %d\n", x86_pmu.num_events_fixed); - pr_info("... event mask: %016Lx\n", perf_event_mask); + pr_info("... version: %d\n", x86_pmu.version); + pr_info("... bit width: %d\n", x86_pmu.event_bits); + pr_info("... generic registers: %d\n", x86_pmu.num_events); + pr_info("... value mask: %016Lx\n", x86_pmu.event_mask); + pr_info("... max period: %016Lx\n", x86_pmu.max_period); + pr_info("... fixed-purpose events: %d\n", x86_pmu.num_events_fixed); + pr_info("... event mask: %016Lx\n", perf_event_mask); } static inline void x86_pmu_read(struct perf_event *event) diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h new file mode 100644 index 000000000000..368bd70f1d2d --- /dev/null +++ b/include/linux/perf_counter.h @@ -0,0 +1,441 @@ +/* + * NOTE: this file will be removed in a future kernel release, it is + * provided as a courtesy copy of user-space code that relies on the + * old (pre-rename) symbols and constants. + * + * Performance events: + * + * Copyright (C) 2008-2009, Thomas Gleixner + * Copyright (C) 2008-2009, Red Hat, Inc., Ingo Molnar + * Copyright (C) 2008-2009, Red Hat, Inc., Peter Zijlstra + * + * Data type definitions, declarations, prototypes. + * + * Started by: Thomas Gleixner and Ingo Molnar + * + * For licencing details see kernel-base/COPYING + */ +#ifndef _LINUX_PERF_COUNTER_H +#define _LINUX_PERF_COUNTER_H + +#include +#include +#include + +/* + * User-space ABI bits: + */ + +/* + * attr.type + */ +enum perf_type_id { + PERF_TYPE_HARDWARE = 0, + PERF_TYPE_SOFTWARE = 1, + PERF_TYPE_TRACEPOINT = 2, + PERF_TYPE_HW_CACHE = 3, + PERF_TYPE_RAW = 4, + + PERF_TYPE_MAX, /* non-ABI */ +}; + +/* + * Generalized performance counter event types, used by the + * attr.event_id parameter of the sys_perf_counter_open() + * syscall: + */ +enum perf_hw_id { + /* + * Common hardware events, generalized by the kernel: + */ + PERF_COUNT_HW_CPU_CYCLES = 0, + PERF_COUNT_HW_INSTRUCTIONS = 1, + PERF_COUNT_HW_CACHE_REFERENCES = 2, + PERF_COUNT_HW_CACHE_MISSES = 3, + PERF_COUNT_HW_BRANCH_INSTRUCTIONS = 4, + PERF_COUNT_HW_BRANCH_MISSES = 5, + PERF_COUNT_HW_BUS_CYCLES = 6, + + PERF_COUNT_HW_MAX, /* non-ABI */ +}; + +/* + * Generalized hardware cache counters: + * + * { L1-D, L1-I, LLC, ITLB, DTLB, BPU } x + * { read, write, prefetch } x + * { accesses, misses } + */ +enum perf_hw_cache_id { + PERF_COUNT_HW_CACHE_L1D = 0, + PERF_COUNT_HW_CACHE_L1I = 1, + PERF_COUNT_HW_CACHE_LL = 2, + PERF_COUNT_HW_CACHE_DTLB = 3, + PERF_COUNT_HW_CACHE_ITLB = 4, + PERF_COUNT_HW_CACHE_BPU = 5, + + PERF_COUNT_HW_CACHE_MAX, /* non-ABI */ +}; + +enum perf_hw_cache_op_id { + PERF_COUNT_HW_CACHE_OP_READ = 0, + PERF_COUNT_HW_CACHE_OP_WRITE = 1, + PERF_COUNT_HW_CACHE_OP_PREFETCH = 2, + + PERF_COUNT_HW_CACHE_OP_MAX, /* non-ABI */ +}; + +enum perf_hw_cache_op_result_id { + PERF_COUNT_HW_CACHE_RESULT_ACCESS = 0, + PERF_COUNT_HW_CACHE_RESULT_MISS = 1, + + PERF_COUNT_HW_CACHE_RESULT_MAX, /* non-ABI */ +}; + +/* + * Special "software" counters provided by the kernel, even if the hardware + * does not support performance counters. These counters measure various + * physical and sw events of the kernel (and allow the profiling of them as + * well): + */ +enum perf_sw_ids { + PERF_COUNT_SW_CPU_CLOCK = 0, + PERF_COUNT_SW_TASK_CLOCK = 1, + PERF_COUNT_SW_PAGE_FAULTS = 2, + PERF_COUNT_SW_CONTEXT_SWITCHES = 3, + PERF_COUNT_SW_CPU_MIGRATIONS = 4, + PERF_COUNT_SW_PAGE_FAULTS_MIN = 5, + PERF_COUNT_SW_PAGE_FAULTS_MAJ = 6, + + PERF_COUNT_SW_MAX, /* non-ABI */ +}; + +/* + * Bits that can be set in attr.sample_type to request information + * in the overflow packets. + */ +enum perf_counter_sample_format { + PERF_SAMPLE_IP = 1U << 0, + PERF_SAMPLE_TID = 1U << 1, + PERF_SAMPLE_TIME = 1U << 2, + PERF_SAMPLE_ADDR = 1U << 3, + PERF_SAMPLE_READ = 1U << 4, + PERF_SAMPLE_CALLCHAIN = 1U << 5, + PERF_SAMPLE_ID = 1U << 6, + PERF_SAMPLE_CPU = 1U << 7, + PERF_SAMPLE_PERIOD = 1U << 8, + PERF_SAMPLE_STREAM_ID = 1U << 9, + PERF_SAMPLE_RAW = 1U << 10, + + PERF_SAMPLE_MAX = 1U << 11, /* non-ABI */ +}; + +/* + * The format of the data returned by read() on a perf counter fd, + * as specified by attr.read_format: + * + * struct read_format { + * { u64 value; + * { u64 time_enabled; } && PERF_FORMAT_ENABLED + * { u64 time_running; } && PERF_FORMAT_RUNNING + * { u64 id; } && PERF_FORMAT_ID + * } && !PERF_FORMAT_GROUP + * + * { u64 nr; + * { u64 time_enabled; } && PERF_FORMAT_ENABLED + * { u64 time_running; } && PERF_FORMAT_RUNNING + * { u64 value; + * { u64 id; } && PERF_FORMAT_ID + * } cntr[nr]; + * } && PERF_FORMAT_GROUP + * }; + */ +enum perf_counter_read_format { + PERF_FORMAT_TOTAL_TIME_ENABLED = 1U << 0, + PERF_FORMAT_TOTAL_TIME_RUNNING = 1U << 1, + PERF_FORMAT_ID = 1U << 2, + PERF_FORMAT_GROUP = 1U << 3, + + PERF_FORMAT_MAX = 1U << 4, /* non-ABI */ +}; + +#define PERF_ATTR_SIZE_VER0 64 /* sizeof first published struct */ + +/* + * Hardware event to monitor via a performance monitoring counter: + */ +struct perf_counter_attr { + + /* + * Major type: hardware/software/tracepoint/etc. + */ + __u32 type; + + /* + * Size of the attr structure, for fwd/bwd compat. + */ + __u32 size; + + /* + * Type specific configuration information. + */ + __u64 config; + + union { + __u64 sample_period; + __u64 sample_freq; + }; + + __u64 sample_type; + __u64 read_format; + + __u64 disabled : 1, /* off by default */ + inherit : 1, /* children inherit it */ + pinned : 1, /* must always be on PMU */ + exclusive : 1, /* only group on PMU */ + exclude_user : 1, /* don't count user */ + exclude_kernel : 1, /* ditto kernel */ + exclude_hv : 1, /* ditto hypervisor */ + exclude_idle : 1, /* don't count when idle */ + mmap : 1, /* include mmap data */ + comm : 1, /* include comm data */ + freq : 1, /* use freq, not period */ + inherit_stat : 1, /* per task counts */ + enable_on_exec : 1, /* next exec enables */ + task : 1, /* trace fork/exit */ + watermark : 1, /* wakeup_watermark */ + + __reserved_1 : 49; + + union { + __u32 wakeup_events; /* wakeup every n events */ + __u32 wakeup_watermark; /* bytes before wakeup */ + }; + __u32 __reserved_2; + + __u64 __reserved_3; +}; + +/* + * Ioctls that can be done on a perf counter fd: + */ +#define PERF_COUNTER_IOC_ENABLE _IO ('$', 0) +#define PERF_COUNTER_IOC_DISABLE _IO ('$', 1) +#define PERF_COUNTER_IOC_REFRESH _IO ('$', 2) +#define PERF_COUNTER_IOC_RESET _IO ('$', 3) +#define PERF_COUNTER_IOC_PERIOD _IOW('$', 4, u64) +#define PERF_COUNTER_IOC_SET_OUTPUT _IO ('$', 5) + +enum perf_counter_ioc_flags { + PERF_IOC_FLAG_GROUP = 1U << 0, +}; + +/* + * Structure of the page that can be mapped via mmap + */ +struct perf_counter_mmap_page { + __u32 version; /* version number of this structure */ + __u32 compat_version; /* lowest version this is compat with */ + + /* + * Bits needed to read the hw counters in user-space. + * + * u32 seq; + * s64 count; + * + * do { + * seq = pc->lock; + * + * barrier() + * if (pc->index) { + * count = pmc_read(pc->index - 1); + * count += pc->offset; + * } else + * goto regular_read; + * + * barrier(); + * } while (pc->lock != seq); + * + * NOTE: for obvious reason this only works on self-monitoring + * processes. + */ + __u32 lock; /* seqlock for synchronization */ + __u32 index; /* hardware counter identifier */ + __s64 offset; /* add to hardware counter value */ + __u64 time_enabled; /* time counter active */ + __u64 time_running; /* time counter on cpu */ + + /* + * Hole for extension of the self monitor capabilities + */ + + __u64 __reserved[123]; /* align to 1k */ + + /* + * Control data for the mmap() data buffer. + * + * User-space reading the @data_head value should issue an rmb(), on + * SMP capable platforms, after reading this value -- see + * perf_counter_wakeup(). + * + * When the mapping is PROT_WRITE the @data_tail value should be + * written by userspace to reflect the last read data. In this case + * the kernel will not over-write unread data. + */ + __u64 data_head; /* head in the data section */ + __u64 data_tail; /* user-space written tail */ +}; + +#define PERF_EVENT_MISC_CPUMODE_MASK (3 << 0) +#define PERF_EVENT_MISC_CPUMODE_UNKNOWN (0 << 0) +#define PERF_EVENT_MISC_KERNEL (1 << 0) +#define PERF_EVENT_MISC_USER (2 << 0) +#define PERF_EVENT_MISC_HYPERVISOR (3 << 0) + +struct perf_event_header { + __u32 type; + __u16 misc; + __u16 size; +}; + +enum perf_event_type { + + /* + * The MMAP events record the PROT_EXEC mappings so that we can + * correlate userspace IPs to code. They have the following structure: + * + * struct { + * struct perf_event_header header; + * + * u32 pid, tid; + * u64 addr; + * u64 len; + * u64 pgoff; + * char filename[]; + * }; + */ + PERF_EVENT_MMAP = 1, + + /* + * struct { + * struct perf_event_header header; + * u64 id; + * u64 lost; + * }; + */ + PERF_EVENT_LOST = 2, + + /* + * struct { + * struct perf_event_header header; + * + * u32 pid, tid; + * char comm[]; + * }; + */ + PERF_EVENT_COMM = 3, + + /* + * struct { + * struct perf_event_header header; + * u32 pid, ppid; + * u32 tid, ptid; + * u64 time; + * }; + */ + PERF_EVENT_EXIT = 4, + + /* + * struct { + * struct perf_event_header header; + * u64 time; + * u64 id; + * u64 stream_id; + * }; + */ + PERF_EVENT_THROTTLE = 5, + PERF_EVENT_UNTHROTTLE = 6, + + /* + * struct { + * struct perf_event_header header; + * u32 pid, ppid; + * u32 tid, ptid; + * { u64 time; } && PERF_SAMPLE_TIME + * }; + */ + PERF_EVENT_FORK = 7, + + /* + * struct { + * struct perf_event_header header; + * u32 pid, tid; + * + * struct read_format values; + * }; + */ + PERF_EVENT_READ = 8, + + /* + * struct { + * struct perf_event_header header; + * + * { u64 ip; } && PERF_SAMPLE_IP + * { u32 pid, tid; } && PERF_SAMPLE_TID + * { u64 time; } && PERF_SAMPLE_TIME + * { u64 addr; } && PERF_SAMPLE_ADDR + * { u64 id; } && PERF_SAMPLE_ID + * { u64 stream_id;} && PERF_SAMPLE_STREAM_ID + * { u32 cpu, res; } && PERF_SAMPLE_CPU + * { u64 period; } && PERF_SAMPLE_PERIOD + * + * { struct read_format values; } && PERF_SAMPLE_READ + * + * { u64 nr, + * u64 ips[nr]; } && PERF_SAMPLE_CALLCHAIN + * + * # + * # The RAW record below is opaque data wrt the ABI + * # + * # That is, the ABI doesn't make any promises wrt to + * # the stability of its content, it may vary depending + * # on event, hardware, kernel version and phase of + * # the moon. + * # + * # In other words, PERF_SAMPLE_RAW contents are not an ABI. + * # + * + * { u32 size; + * char data[size];}&& PERF_SAMPLE_RAW + * }; + */ + PERF_EVENT_SAMPLE = 9, + + PERF_EVENT_MAX, /* non-ABI */ +}; + +enum perf_callchain_context { + PERF_CONTEXT_HV = (__u64)-32, + PERF_CONTEXT_KERNEL = (__u64)-128, + PERF_CONTEXT_USER = (__u64)-512, + + PERF_CONTEXT_GUEST = (__u64)-2048, + PERF_CONTEXT_GUEST_KERNEL = (__u64)-2176, + PERF_CONTEXT_GUEST_USER = (__u64)-2560, + + PERF_CONTEXT_MAX = (__u64)-4095, +}; + +#define PERF_FLAG_FD_NO_GROUP (1U << 0) +#define PERF_FLAG_FD_OUTPUT (1U << 1) + +/* + * In case some app still references the old symbols: + */ + +#define __NR_perf_counter_open __NR_perf_event_open + +#define PR_TASK_PERF_COUNTERS_DISABLE PR_TASK_PERF_EVENTS_DISABLE +#define PR_TASK_PERF_COUNTERS_ENABLE PR_TASK_PERF_EVENTS_ENABLE + +#endif /* _LINUX_PERF_COUNTER_H */ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index ae9d9ed6df2a..acefaf71e6dd 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1,15 +1,15 @@ /* - * Performance events: + * Performance events: * * Copyright (C) 2008-2009, Thomas Gleixner * Copyright (C) 2008-2009, Red Hat, Inc., Ingo Molnar * Copyright (C) 2008-2009, Red Hat, Inc., Peter Zijlstra * - * Data type definitions, declarations, prototypes. + * Data type definitions, declarations, prototypes. * * Started by: Thomas Gleixner and Ingo Molnar * - * For licencing details see kernel-base/COPYING + * For licencing details see kernel-base/COPYING */ #ifndef _LINUX_PERF_EVENT_H #define _LINUX_PERF_EVENT_H @@ -131,19 +131,19 @@ enum perf_event_sample_format { * as specified by attr.read_format: * * struct read_format { - * { u64 value; - * { u64 time_enabled; } && PERF_FORMAT_ENABLED - * { u64 time_running; } && PERF_FORMAT_RUNNING - * { u64 id; } && PERF_FORMAT_ID - * } && !PERF_FORMAT_GROUP + * { u64 value; + * { u64 time_enabled; } && PERF_FORMAT_ENABLED + * { u64 time_running; } && PERF_FORMAT_RUNNING + * { u64 id; } && PERF_FORMAT_ID + * } && !PERF_FORMAT_GROUP * - * { u64 nr; - * { u64 time_enabled; } && PERF_FORMAT_ENABLED - * { u64 time_running; } && PERF_FORMAT_RUNNING - * { u64 value; - * { u64 id; } && PERF_FORMAT_ID - * } cntr[nr]; - * } && PERF_FORMAT_GROUP + * { u64 nr; + * { u64 time_enabled; } && PERF_FORMAT_ENABLED + * { u64 time_running; } && PERF_FORMAT_RUNNING + * { u64 value; + * { u64 id; } && PERF_FORMAT_ID + * } cntr[nr]; + * } && PERF_FORMAT_GROUP * }; */ enum perf_event_read_format { @@ -152,7 +152,7 @@ enum perf_event_read_format { PERF_FORMAT_ID = 1U << 2, PERF_FORMAT_GROUP = 1U << 3, - PERF_FORMAT_MAX = 1U << 4, /* non-ABI */ + PERF_FORMAT_MAX = 1U << 4, /* non-ABI */ }; #define PERF_ATTR_SIZE_VER0 64 /* sizeof first published struct */ @@ -216,8 +216,8 @@ struct perf_event_attr { * Ioctls that can be done on a perf event fd: */ #define PERF_EVENT_IOC_ENABLE _IO ('$', 0) -#define PERF_EVENT_IOC_DISABLE _IO ('$', 1) -#define PERF_EVENT_IOC_REFRESH _IO ('$', 2) +#define PERF_EVENT_IOC_DISABLE _IO ('$', 1) +#define PERF_EVENT_IOC_REFRESH _IO ('$', 2) #define PERF_EVENT_IOC_RESET _IO ('$', 3) #define PERF_EVENT_IOC_PERIOD _IOW('$', 4, u64) #define PERF_EVENT_IOC_SET_OUTPUT _IO ('$', 5) @@ -314,9 +314,9 @@ enum perf_event_type { /* * struct { - * struct perf_event_header header; - * u64 id; - * u64 lost; + * struct perf_event_header header; + * u64 id; + * u64 lost; * }; */ PERF_RECORD_LOST = 2, @@ -383,23 +383,23 @@ enum perf_event_type { * { u64 id; } && PERF_SAMPLE_ID * { u64 stream_id;} && PERF_SAMPLE_STREAM_ID * { u32 cpu, res; } && PERF_SAMPLE_CPU - * { u64 period; } && PERF_SAMPLE_PERIOD + * { u64 period; } && PERF_SAMPLE_PERIOD * * { struct read_format values; } && PERF_SAMPLE_READ * * { u64 nr, * u64 ips[nr]; } && PERF_SAMPLE_CALLCHAIN * - * # - * # The RAW record below is opaque data wrt the ABI - * # - * # That is, the ABI doesn't make any promises wrt to - * # the stability of its content, it may vary depending - * # on event_id, hardware, kernel version and phase of - * # the moon. - * # - * # In other words, PERF_SAMPLE_RAW contents are not an ABI. - * # + * # + * # The RAW record below is opaque data wrt the ABI + * # + * # That is, the ABI doesn't make any promises wrt to + * # the stability of its content, it may vary depending + * # on event, hardware, kernel version and phase of + * # the moon. + * # + * # In other words, PERF_SAMPLE_RAW contents are not an ABI. + * # * * { u32 size; * char data[size];}&& PERF_SAMPLE_RAW @@ -503,10 +503,10 @@ struct pmu { * enum perf_event_active_state - the states of a event */ enum perf_event_active_state { - PERF_EVENT_STATE_ERROR = -2, + PERF_EVENT_STATE_ERROR = -2, PERF_EVENT_STATE_OFF = -1, PERF_EVENT_STATE_INACTIVE = 0, - PERF_EVENT_STATE_ACTIVE = 1, + PERF_EVENT_STATE_ACTIVE = 1, }; struct file; @@ -529,7 +529,7 @@ struct perf_mmap_data { long watermark; /* wakeup watermark */ - struct perf_event_mmap_page *user_page; + struct perf_event_mmap_page *user_page; void *data_pages[0]; }; @@ -694,14 +694,14 @@ struct perf_cpu_context { }; struct perf_output_handle { - struct perf_event *event; - struct perf_mmap_data *data; - unsigned long head; - unsigned long offset; - int nmi; - int sample; - int locked; - unsigned long flags; + struct perf_event *event; + struct perf_mmap_data *data; + unsigned long head; + unsigned long offset; + int nmi; + int sample; + int locked; + unsigned long flags; }; #ifdef CONFIG_PERF_EVENTS @@ -829,22 +829,22 @@ static inline void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next, int cpu) { } static inline void -perf_event_task_tick(struct task_struct *task, int cpu) { } +perf_event_task_tick(struct task_struct *task, int cpu) { } 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_print_debug(void) { } +static inline void perf_event_do_pending(void) { } +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; } +static inline int perf_event_task_disable(void) { return -EINVAL; } +static inline int perf_event_task_enable(void) { return -EINVAL; } static inline void perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr) { } -static inline void perf_event_mmap(struct vm_area_struct *vma) { } +static inline void perf_event_mmap(struct vm_area_struct *vma) { } static inline void perf_event_comm(struct task_struct *tsk) { } static inline void perf_event_fork(struct task_struct *tsk) { } static inline void perf_event_init(void) { } diff --git a/init/Kconfig b/init/Kconfig index cfdf5c322806..706728be312f 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -920,26 +920,31 @@ config HAVE_PERF_EVENTS help See tools/perf/design.txt for details. -menu "Performance Counters" +menu "Kernel Performance Events And Counters" config PERF_EVENTS - bool "Kernel Performance Counters" - default y if PROFILING + bool "Kernel performance events and counters" + default y if (PROFILING || PERF_COUNTERS) depends on HAVE_PERF_EVENTS select ANON_INODES help - Enable kernel support for performance counter hardware. + Enable kernel support for various performance events provided + by software and hardware. - Performance counters are special hardware registers available - on most modern CPUs. These registers count the number of certain + Software events are supported either build-in or via the + use of generic tracepoints. + + Most modern CPUs support performance events via performance + counter registers. These registers count the number of certain types of hw events: such as instructions executed, cachemisses suffered, or branches mis-predicted - without slowing down the kernel or applications. These registers can also trigger interrupts when a threshold number of events have passed - and can thus be used to profile the code that runs on that CPU. - The Linux Performance Counter subsystem provides an abstraction of - these hardware capabilities, available via a system call. It + The Linux Performance Event subsystem provides an abstraction of + these software and hardware cevent apabilities, available via a + system call and used by the "perf" utility in tools/perf/. It provides per task and per CPU counters, and it provides event capabilities on top of those. @@ -950,14 +955,26 @@ config EVENT_PROFILE depends on PERF_EVENTS && EVENT_TRACING default y help - Allow the use of tracepoints as software performance counters. + Allow the use of tracepoints as software performance events. - When this is enabled, you can create perf counters based on + When this is enabled, you can create perf events based on tracepoints using PERF_TYPE_TRACEPOINT and the tracepoint ID found in debugfs://tracing/events/*/*/id. (The -e/--events option to the perf tool can parse and interpret symbolic tracepoints, in the subsystem:tracepoint_name format.) +config PERF_COUNTERS + bool "Kernel performance counters (old config option)" + depends on HAVE_PERF_EVENTS + help + This config has been obsoleted by the PERF_EVENTS + config option - please see that one for details. + + It has no effect on the kernel whether you enable + it or not, it is a compatibility placeholder. + + Say N if unsure. + endmenu config VM_EVENT_COUNTERS diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 6e8b99a04e1e..76ac4db405e9 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -1,12 +1,12 @@ /* - * Performance event core code + * Performance events core code: * * Copyright (C) 2008 Thomas Gleixner * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra * Copyright © 2009 Paul Mackerras, IBM Corp. * - * For licensing details see kernel-base/COPYING + * For licensing details see kernel-base/COPYING */ #include -- cgit v1.2.3