From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755196Ab2BBKAr (ORCPT ); Thu, 2 Feb 2012 05:00:47 -0500 Received: from mx3.mail.elte.hu ([157.181.1.138]:53421 "EHLO mx3.mail.elte.hu" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751778Ab2BBKAn (ORCPT ); Thu, 2 Feb 2012 05:00:43 -0500 Date: Thu, 2 Feb 2012 11:00:24 +0100 From: Ingo Molnar To: Linus Torvalds Cc: linux-kernel@vger.kernel.org, Peter Zijlstra , Arnaldo Carvalho de Melo , Thomas Gleixner , Andrew Morton Subject: [GIT PULL] perf fixes Message-ID: <20120202100024.GA4160@elte.hu> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.5.21 (2010-09-15) X-ELTE-SpamScore: -2.0 X-ELTE-SpamLevel: X-ELTE-SpamCheck: no X-ELTE-SpamVersion: ELTE 2.0 X-ELTE-SpamCheck-Details: score=-2.0 required=5.9 tests=AWL,BAYES_00 autolearn=no SpamAssassin version=3.3.1 -2.0 BAYES_00 BODY: Bayes spam probability is 0 to 1% [score: 0.0000] 0.0 AWL AWL: From: address is in the auto white-list Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Linus, Please pull the latest perf-urgent-for-linus git tree from: git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus HEAD: 45179fec946dd554f74e950d2278dabd5ad23fd3 Merge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent Thanks, Ingo ------------------> Dan Carpenter (1): x86/dumpstack: Remove unneeded check in dump_trace() David Daney (1): perf tools: Fix broken build by defining _GNU_SOURCE in Makefile Stephane Eranian (3): perf: Fix broken interrupt rate throttling perf tools: Fix strlen() bug in perf_event__synthesize_event_type() perf top: Fix number of samples displayed arch/x86/kernel/dumpstack_64.c | 2 +- include/linux/perf_event.h | 1 + kernel/events/core.c | 104 ++++++++++++++++++++++------------- tools/perf/Makefile | 7 +-- tools/perf/builtin-probe.c | 2 - tools/perf/builtin-top.c | 13 +++- tools/perf/util/header.c | 2 +- tools/perf/util/probe-event.c | 2 - tools/perf/util/symbol.c | 1 - tools/perf/util/trace-event-parse.c | 3 +- tools/perf/util/ui/browsers/hists.c | 2 - tools/perf/util/ui/helpline.c | 1 - tools/perf/util/util.h | 1 - 13 files changed, 82 insertions(+), 59 deletions(-) diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 6d728d9..af7785f 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -129,7 +129,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, if (!stack) { if (regs) stack = (unsigned long *)regs->sp; - else if (task && task != current) + else if (task != current) stack = (unsigned long *)task->thread.sp; else stack = &dummy; diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 0885561..abb2776 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -587,6 +587,7 @@ struct hw_perf_event { u64 sample_period; u64 last_period; local64_t period_left; + u64 interrupts_seq; u64 interrupts; u64 freq_time_stamp; diff --git a/kernel/events/core.c b/kernel/events/core.c index 32b48c8..ba36013 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2300,6 +2300,9 @@ do { \ return div64_u64(dividend, divisor); } +static DEFINE_PER_CPU(int, perf_throttled_count); +static DEFINE_PER_CPU(u64, perf_throttled_seq); + static void perf_adjust_period(struct perf_event *event, u64 nsec, u64 count) { struct hw_perf_event *hwc = &event->hw; @@ -2325,16 +2328,29 @@ static void perf_adjust_period(struct perf_event *event, u64 nsec, u64 count) } } -static void perf_ctx_adjust_freq(struct perf_event_context *ctx, u64 period) +/* + * combine freq adjustment with unthrottling to avoid two passes over the + * events. At the same time, make sure, having freq events does not change + * the rate of unthrottling as that would introduce bias. + */ +static void perf_adjust_freq_unthr_context(struct perf_event_context *ctx, + int needs_unthr) { struct perf_event *event; struct hw_perf_event *hwc; - u64 interrupts, now; + u64 now, period = TICK_NSEC; s64 delta; - if (!ctx->nr_freq) + /* + * only need to iterate over all events iff: + * - context have events in frequency mode (needs freq adjust) + * - there are events to unthrottle on this cpu + */ + if (!(ctx->nr_freq || needs_unthr)) return; + raw_spin_lock(&ctx->lock); + list_for_each_entry_rcu(event, &ctx->event_list, event_entry) { if (event->state != PERF_EVENT_STATE_ACTIVE) continue; @@ -2344,13 +2360,8 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx, u64 period) hwc = &event->hw; - interrupts = hwc->interrupts; - hwc->interrupts = 0; - - /* - * unthrottle events on the tick - */ - if (interrupts == MAX_INTERRUPTS) { + if (needs_unthr && hwc->interrupts == MAX_INTERRUPTS) { + hwc->interrupts = 0; perf_log_throttle(event, 1); event->pmu->start(event, 0); } @@ -2358,14 +2369,26 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx, u64 period) if (!event->attr.freq || !event->attr.sample_freq) continue; - event->pmu->read(event); + /* + * stop the event and update event->count + */ + event->pmu->stop(event, PERF_EF_UPDATE); + now = local64_read(&event->count); delta = now - hwc->freq_count_stamp; hwc->freq_count_stamp = now; + /* + * restart the event + * reload only if value has changed + */ if (delta > 0) perf_adjust_period(event, period, delta); + + event->pmu->start(event, delta > 0 ? PERF_EF_RELOAD : 0); } + + raw_spin_unlock(&ctx->lock); } /* @@ -2388,16 +2411,13 @@ static void rotate_ctx(struct perf_event_context *ctx) */ static void perf_rotate_context(struct perf_cpu_context *cpuctx) { - u64 interval = (u64)cpuctx->jiffies_interval * TICK_NSEC; struct perf_event_context *ctx = NULL; - int rotate = 0, remove = 1, freq = 0; + int rotate = 0, remove = 1; if (cpuctx->ctx.nr_events) { remove = 0; if (cpuctx->ctx.nr_events != cpuctx->ctx.nr_active) rotate = 1; - if (cpuctx->ctx.nr_freq) - freq = 1; } ctx = cpuctx->task_ctx; @@ -2405,37 +2425,26 @@ static void perf_rotate_context(struct perf_cpu_context *cpuctx) remove = 0; if (ctx->nr_events != ctx->nr_active) rotate = 1; - if (ctx->nr_freq) - freq = 1; } - if (!rotate && !freq) + if (!rotate) goto done; perf_ctx_lock(cpuctx, cpuctx->task_ctx); perf_pmu_disable(cpuctx->ctx.pmu); - if (freq) { - perf_ctx_adjust_freq(&cpuctx->ctx, interval); - if (ctx) - perf_ctx_adjust_freq(ctx, interval); - } - - if (rotate) { - cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE); - if (ctx) - ctx_sched_out(ctx, cpuctx, EVENT_FLEXIBLE); + cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE); + if (ctx) + ctx_sched_out(ctx, cpuctx, EVENT_FLEXIBLE); - rotate_ctx(&cpuctx->ctx); - if (ctx) - rotate_ctx(ctx); + rotate_ctx(&cpuctx->ctx); + if (ctx) + rotate_ctx(ctx); - perf_event_sched_in(cpuctx, ctx, current); - } + perf_event_sched_in(cpuctx, ctx, current); perf_pmu_enable(cpuctx->ctx.pmu); perf_ctx_unlock(cpuctx, cpuctx->task_ctx); - done: if (remove) list_del_init(&cpuctx->rotation_list); @@ -2445,10 +2454,22 @@ void perf_event_task_tick(void) { struct list_head *head = &__get_cpu_var(rotation_list); struct perf_cpu_context *cpuctx, *tmp; + struct perf_event_context *ctx; + int throttled; WARN_ON(!irqs_disabled()); + __this_cpu_inc(perf_throttled_seq); + throttled = __this_cpu_xchg(perf_throttled_count, 0); + list_for_each_entry_safe(cpuctx, tmp, head, rotation_list) { + ctx = &cpuctx->ctx; + perf_adjust_freq_unthr_context(ctx, throttled); + + ctx = cpuctx->task_ctx; + if (ctx) + perf_adjust_freq_unthr_context(ctx, throttled); + if (cpuctx->jiffies_interval == 1 || !(jiffies % cpuctx->jiffies_interval)) perf_rotate_context(cpuctx); @@ -4509,6 +4530,7 @@ static int __perf_event_overflow(struct perf_event *event, { int events = atomic_read(&event->event_limit); struct hw_perf_event *hwc = &event->hw; + u64 seq; int ret = 0; /* @@ -4518,14 +4540,20 @@ static int __perf_event_overflow(struct perf_event *event, if (unlikely(!is_sampling_event(event))) return 0; - if (unlikely(hwc->interrupts >= max_samples_per_tick)) { - if (throttle) { + seq = __this_cpu_read(perf_throttled_seq); + if (seq != hwc->interrupts_seq) { + hwc->interrupts_seq = seq; + hwc->interrupts = 1; + } else { + hwc->interrupts++; + if (unlikely(throttle + && hwc->interrupts >= max_samples_per_tick)) { + __this_cpu_inc(perf_throttled_count); hwc->interrupts = MAX_INTERRUPTS; perf_log_throttle(event, 0); ret = 1; } - } else - hwc->interrupts++; + } if (event->attr.freq) { u64 now = perf_clock(); diff --git a/tools/perf/Makefile b/tools/perf/Makefile index ac86d67..7c12650 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -104,7 +104,7 @@ endif CFLAGS = -fno-omit-frame-pointer -ggdb3 -Wall -Wextra -std=gnu99 $(CFLAGS_WERROR) $(CFLAGS_OPTIMIZE) -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) EXTLIBS = -lpthread -lrt -lelf -lm -ALL_CFLAGS = $(CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 +ALL_CFLAGS = $(CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE ALL_LDFLAGS = $(LDFLAGS) STRIP ?= strip @@ -168,10 +168,7 @@ endif ### --- END CONFIGURATION SECTION --- -# Those must not be GNU-specific; they are shared with perl/ which may -# be built by a different compiler. (Note that this is an artifact now -# but it still might be nice to keep that distinction.) -BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include +BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE BASIC_LDFLAGS = # Guard against environment variables diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index 59d43ab..fb85661 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -20,7 +20,6 @@ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. * */ -#define _GNU_SOURCE #include #include #include @@ -31,7 +30,6 @@ #include #include -#undef _GNU_SOURCE #include "perf.h" #include "builtin.h" #include "util/util.h" diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 8f80df8..dd162aa 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -89,8 +89,6 @@ void get_term_dimensions(struct winsize *ws) static void perf_top__update_print_entries(struct perf_top *top) { - top->print_entries = top->winsize.ws_row; - if (top->print_entries > 9) top->print_entries -= 9; } @@ -100,6 +98,13 @@ static void perf_top__sig_winch(int sig __used, siginfo_t *info __used, void *ar struct perf_top *top = arg; get_term_dimensions(&top->winsize); + if (!top->print_entries + || (top->print_entries+4) > top->winsize.ws_row) { + top->print_entries = top->winsize.ws_row; + } else { + top->print_entries += 4; + top->winsize.ws_row = top->print_entries; + } perf_top__update_print_entries(top); } @@ -453,8 +458,10 @@ static void perf_top__handle_keypress(struct perf_top *top, int c) }; perf_top__sig_winch(SIGWINCH, NULL, top); sigaction(SIGWINCH, &act, NULL); - } else + } else { + perf_top__sig_winch(SIGWINCH, NULL, top); signal(SIGWINCH, SIG_DFL); + } break; case 'E': if (top->evlist->nr_entries > 1) { diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 3e7e0b0..ecd7f4d 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -2105,7 +2105,7 @@ int perf_event__synthesize_event_type(struct perf_tool *tool, strncpy(ev.event_type.event_type.name, name, MAX_EVENT_NAME - 1); ev.event_type.header.type = PERF_RECORD_HEADER_EVENT_TYPE; - size = strlen(name); + size = strlen(ev.event_type.event_type.name); size = ALIGN(size, sizeof(u64)); ev.event_type.header.size = sizeof(ev.event_type) - (sizeof(ev.event_type.event_type.name) - size); diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index eb25900..29cb654 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -19,7 +19,6 @@ * */ -#define _GNU_SOURCE #include #include #include @@ -33,7 +32,6 @@ #include #include -#undef _GNU_SOURCE #include "util.h" #include "event.h" #include "string.h" diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 215d50f..0975438 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -1,4 +1,3 @@ -#define _GNU_SOURCE #include #include #include diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index 6c164dc..1a8d4dc 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -21,14 +21,13 @@ * The parts for function graph printing was taken and modified from the * Linux Kernel that were written by Frederic Weisbecker. */ -#define _GNU_SOURCE + #include #include #include #include #include -#undef _GNU_SOURCE #include "../perf.h" #include "util.h" #include "trace-event.h" diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c index 1212a38..e81aef1 100644 --- a/tools/perf/util/ui/browsers/hists.c +++ b/tools/perf/util/ui/browsers/hists.c @@ -1,6 +1,4 @@ -#define _GNU_SOURCE #include -#undef _GNU_SOURCE #include "../libslang.h" #include #include diff --git a/tools/perf/util/ui/helpline.c b/tools/perf/util/ui/helpline.c index 6ef3c56..4f48f59 100644 --- a/tools/perf/util/ui/helpline.c +++ b/tools/perf/util/ui/helpline.c @@ -1,4 +1,3 @@ -#define _GNU_SOURCE #include #include #include diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index b9c530c..ecf9898 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -40,7 +40,6 @@ #define decimal_length(x) ((int)(sizeof(x) * 2.56 + 0.5) + 1) #define _ALL_SOURCE 1 -#define _GNU_SOURCE 1 #define _BSD_SOURCE 1 #define HAS_BOOL