diff options
-rw-r--r-- | arch/x86/kernel/cpu/perf_event.c | 8 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event_amd.c | 2 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event_intel.c | 2 | ||||
-rw-r--r-- | kernel/events/core.c | 101 | ||||
-rw-r--r-- | kernel/watchdog.c | 7 | ||||
-rw-r--r-- | tools/perf/Documentation/perf-annotate.txt | 11 | ||||
-rw-r--r-- | tools/perf/Documentation/perf-stat.txt | 7 | ||||
-rw-r--r-- | tools/perf/builtin-annotate.c | 6 | ||||
-rw-r--r-- | tools/perf/builtin-stat.c | 155 | ||||
-rw-r--r-- | tools/perf/util/annotate.c | 5 | ||||
-rw-r--r-- | tools/perf/util/color.c | 2 | ||||
-rw-r--r-- | tools/perf/util/symbol.c | 2 | ||||
-rw-r--r-- | tools/perf/util/symbol.h | 4 |
13 files changed, 237 insertions, 75 deletions
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index cfa62ec..05df6e3 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -129,6 +129,8 @@ struct cpu_hw_events { * AMD specific bits */ struct amd_nb *amd_nb; + + void *kfree_on_online; }; #define __EVENT_CONSTRAINT(c, n, m, w) {\ @@ -1466,10 +1468,12 @@ static int __cpuinit x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) { unsigned int cpu = (long)hcpu; + struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); int ret = NOTIFY_OK; switch (action & ~CPU_TASKS_FROZEN) { case CPU_UP_PREPARE: + cpuc->kfree_on_online = NULL; if (x86_pmu.cpu_prepare) ret = x86_pmu.cpu_prepare(cpu); break; @@ -1479,6 +1483,10 @@ x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) x86_pmu.cpu_starting(cpu); break; + case CPU_ONLINE: + kfree(cpuc->kfree_on_online); + break; + case CPU_DYING: if (x86_pmu.cpu_dying) x86_pmu.cpu_dying(cpu); diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index 941caa2..ee9436c 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -350,7 +350,7 @@ static void amd_pmu_cpu_starting(int cpu) continue; if (nb->nb_id == nb_id) { - kfree(cpuc->amd_nb); + cpuc->kfree_on_online = cpuc->amd_nb; cpuc->amd_nb = nb; break; } diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index f88af2c..3751494 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1362,7 +1362,7 @@ static void intel_pmu_cpu_starting(int cpu) pc = per_cpu(cpu_hw_events, i).shared_regs; if (pc && pc->core_id == core_id) { - kfree(cpuc->shared_regs); + cpuc->kfree_on_online = cpuc->shared_regs; cpuc->shared_regs = pc; break; } diff --git a/kernel/events/core.c b/kernel/events/core.c index 0f85778..d1a1bee 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -29,6 +29,7 @@ #include <linux/hardirq.h> #include <linux/rculist.h> #include <linux/uaccess.h> +#include <linux/suspend.h> #include <linux/syscalls.h> #include <linux/anon_inodes.h> #include <linux/kernel_stat.h> @@ -5758,6 +5759,7 @@ struct pmu *perf_init_event(struct perf_event *event) pmu = idr_find(&pmu_idr, event->attr.type); rcu_read_unlock(); if (pmu) { + event->pmu = pmu; ret = pmu->event_init(event); if (ret) pmu = ERR_PTR(ret); @@ -5765,6 +5767,7 @@ struct pmu *perf_init_event(struct perf_event *event) } list_for_each_entry_rcu(pmu, &pmus, entry) { + event->pmu = pmu; ret = pmu->event_init(event); if (!ret) goto unlock; @@ -5891,8 +5894,6 @@ done: return ERR_PTR(err); } - event->pmu = pmu; - if (!event->parent) { if (event->attach_state & PERF_ATTACH_TASK) jump_label_inc(&perf_sched_events); @@ -6852,7 +6853,7 @@ static void __cpuinit perf_event_init_cpu(int cpu) struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu); mutex_lock(&swhash->hlist_mutex); - if (swhash->hlist_refcount > 0) { + if (swhash->hlist_refcount > 0 && !swhash->swevent_hlist) { struct swevent_hlist *hlist; hlist = kzalloc_node(sizeof(*hlist), GFP_KERNEL, cpu_to_node(cpu)); @@ -6941,7 +6942,14 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { unsigned int cpu = (long)hcpu; - switch (action & ~CPU_TASKS_FROZEN) { + /* + * Ignore suspend/resume action, the perf_pm_notifier will + * take care of that. + */ + if (action & CPU_TASKS_FROZEN) + return NOTIFY_OK; + + switch (action) { case CPU_UP_PREPARE: case CPU_DOWN_FAILED: @@ -6960,6 +6968,90 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) return NOTIFY_OK; } +static void perf_pm_resume_cpu(void *unused) +{ + struct perf_cpu_context *cpuctx; + struct perf_event_context *ctx; + struct pmu *pmu; + int idx; + + idx = srcu_read_lock(&pmus_srcu); + list_for_each_entry_rcu(pmu, &pmus, entry) { + cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); + ctx = cpuctx->task_ctx; + + perf_ctx_lock(cpuctx, ctx); + perf_pmu_disable(cpuctx->ctx.pmu); + + cpu_ctx_sched_out(cpuctx, EVENT_ALL); + if (ctx) + ctx_sched_out(ctx, cpuctx, EVENT_ALL); + + perf_pmu_enable(cpuctx->ctx.pmu); + perf_ctx_unlock(cpuctx, ctx); + } + srcu_read_unlock(&pmus_srcu, idx); +} + +static void perf_pm_suspend_cpu(void *unused) +{ + struct perf_cpu_context *cpuctx; + struct perf_event_context *ctx; + struct pmu *pmu; + int idx; + + idx = srcu_read_lock(&pmus_srcu); + list_for_each_entry_rcu(pmu, &pmus, entry) { + cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); + ctx = cpuctx->task_ctx; + + perf_ctx_lock(cpuctx, ctx); + perf_pmu_disable(cpuctx->ctx.pmu); + + perf_event_sched_in(cpuctx, ctx, current); + + perf_pmu_enable(cpuctx->ctx.pmu); + perf_ctx_unlock(cpuctx, ctx); + } + srcu_read_unlock(&pmus_srcu, idx); +} + +static int perf_resume(void) +{ + get_online_cpus(); + smp_call_function(perf_pm_resume_cpu, NULL, 1); + put_online_cpus(); + + return NOTIFY_OK; +} + +static int perf_suspend(void) +{ + get_online_cpus(); + smp_call_function(perf_pm_suspend_cpu, NULL, 1); + put_online_cpus(); + + return NOTIFY_OK; +} + +static int perf_pm(struct notifier_block *self, unsigned long action, void *ptr) +{ + switch (action) { + case PM_POST_HIBERNATION: + case PM_POST_SUSPEND: + return perf_resume(); + case PM_HIBERNATION_PREPARE: + case PM_SUSPEND_PREPARE: + return perf_suspend(); + default: + return NOTIFY_DONE; + } +} + +static struct notifier_block perf_pm_notifier = { + .notifier_call = perf_pm, +}; + void __init perf_event_init(void) { int ret; @@ -6974,6 +7066,7 @@ void __init perf_event_init(void) perf_tp_register(); perf_cpu_notifier(perf_cpu_notify); register_reboot_notifier(&perf_reboot_notifier); + register_pm_notifier(&perf_pm_notifier); ret = init_hw_breakpoint(); WARN(ret, "hw_breakpoint initialization failed with: %d", ret); diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 36491cd..d680381 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -321,7 +321,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) */ static int watchdog(void *unused) { - static struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; + struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer); sched_setscheduler(current, SCHED_FIFO, ¶m); @@ -350,7 +350,8 @@ static int watchdog(void *unused) set_current_state(TASK_INTERRUPTIBLE); } __set_current_state(TASK_RUNNING); - + param.sched_priority = 0; + sched_setscheduler(current, SCHED_NORMAL, ¶m); return 0; } @@ -438,7 +439,7 @@ static int watchdog_enable(int cpu) /* create the watchdog thread */ if (!p) { - p = kthread_create(watchdog, (void *)(unsigned long)cpu, "watchdog/%d", cpu); + p = kthread_create_on_node(watchdog, NULL, cpu_to_node(cpu), "watchdog/%d", cpu); if (IS_ERR(p)) { printk(KERN_ERR "softlockup watchdog for %i failed\n", cpu); if (!err) { diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt index 85c5f02..98a31e3 100644 --- a/tools/perf/Documentation/perf-annotate.txt +++ b/tools/perf/Documentation/perf-annotate.txt @@ -72,6 +72,17 @@ OPTIONS CPUs are specified with -: 0-2. Default is to report samples on all CPUs. +--asm-raw:: + Show raw instruction encoding of assembly instructions. They + are displayed by default, disable with --no-asm-raw. + +--source:: + Interleave source code with assembly code. Enabled by default, + disable with --no-source. + +--symfs=<directory>:: + Look for files with symbols relative to this directory. + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-report[1] diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 918cc38..08394c4 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -94,6 +94,13 @@ an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must ha corresponding events, i.e., they always refer to events defined earlier on the command line. +-o file:: +-output file:: +Print the output into the designated file. + +--append:: +Append to the output file designated with the -o option. Ignored if -o is not specified. + EXAMPLES -------- diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 555aefd..c5be288 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -267,6 +267,12 @@ static const struct option options[] = { OPT_BOOLEAN('P', "full-paths", &full_paths, "Don't shorten the displayed pathnames"), OPT_STRING('c', "cpu", &cpu_list, "cpu", "list of cpus to profile"), + OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory", + "Look for files with symbols relative to this directory"), + OPT_BOOLEAN('0', "source", &symbol_conf.annotate_src, + "Interleave source code with assembly code (default)"), + OPT_BOOLEAN('0', "asm-raw", &symbol_conf.annotate_asm_raw, + "Display raw encoding of assembly instructions (default)"), OPT_END() }; diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 5deb17d..bec64a9 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -194,6 +194,8 @@ static const char *cpu_list; static const char *csv_sep = NULL; static bool csv_output = false; static bool group = false; +static const char *output_name = NULL; +static FILE *output = NULL; static volatile int done = 0; @@ -352,7 +354,7 @@ static int read_counter_aggr(struct perf_evsel *counter) update_stats(&ps->res_stats[i], count[i]); if (verbose) { - fprintf(stderr, "%s: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n", + fprintf(output, "%s: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n", event_name(counter), count[0], count[1], count[2]); } @@ -519,9 +521,9 @@ static void print_noise_pct(double total, double avg) pct = 100.0*total/avg; if (csv_output) - fprintf(stderr, "%s%.2f%%", csv_sep, pct); + fprintf(output, "%s%.2f%%", csv_sep, pct); else - fprintf(stderr, " ( +-%6.2f%% )", pct); + fprintf(output, " ( +-%6.2f%% )", pct); } static void print_noise(struct perf_evsel *evsel, double avg) @@ -546,16 +548,17 @@ static void nsec_printout(int cpu, struct perf_evsel *evsel, double avg) csv_output ? 0 : -4, evsel_list->cpus->map[cpu], csv_sep); - fprintf(stderr, fmt, cpustr, msecs, csv_sep, event_name(evsel)); + fprintf(output, fmt, cpustr, msecs, csv_sep, event_name(evsel)); if (evsel->cgrp) - fprintf(stderr, "%s%s", csv_sep, evsel->cgrp->name); + fprintf(output, "%s%s", csv_sep, evsel->cgrp->name); if (csv_output) return; if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK)) - fprintf(stderr, " # %8.3f CPUs utilized ", avg / avg_stats(&walltime_nsecs_stats)); + fprintf(output, " # %8.3f CPUs utilized ", + avg / avg_stats(&walltime_nsecs_stats)); } static void print_stalled_cycles_frontend(int cpu, struct perf_evsel *evsel __used, double avg) @@ -576,9 +579,9 @@ static void print_stalled_cycles_frontend(int cpu, struct perf_evsel *evsel __us else if (ratio > 10.0) color = PERF_COLOR_YELLOW; - fprintf(stderr, " # "); - color_fprintf(stderr, color, "%6.2f%%", ratio); - fprintf(stderr, " frontend cycles idle "); + fprintf(output, " # "); + color_fprintf(output, color, "%6.2f%%", ratio); + fprintf(output, " frontend cycles idle "); } static void print_stalled_cycles_backend(int cpu, struct perf_evsel *evsel __used, double avg) @@ -599,9 +602,9 @@ static void print_stalled_cycles_backend(int cpu, struct perf_evsel *evsel __use else if (ratio > 20.0) color = PERF_COLOR_YELLOW; - fprintf(stderr, " # "); - color_fprintf(stderr, color, "%6.2f%%", ratio); - fprintf(stderr, " backend cycles idle "); + fprintf(output, " # "); + color_fprintf(output, color, "%6.2f%%", ratio); + fprintf(output, " backend cycles idle "); } static void print_branch_misses(int cpu, struct perf_evsel *evsel __used, double avg) @@ -622,9 +625,9 @@ static void print_branch_misses(int cpu, struct perf_evsel *evsel __used, double else if (ratio > 5.0) color = PERF_COLOR_YELLOW; - fprintf(stderr, " # "); - color_fprintf(stderr, color, "%6.2f%%", ratio); - fprintf(stderr, " of all branches "); + fprintf(output, " # "); + color_fprintf(output, color, "%6.2f%%", ratio); + fprintf(output, " of all branches "); } static void print_l1_dcache_misses(int cpu, struct perf_evsel *evsel __used, double avg) @@ -645,9 +648,9 @@ static void print_l1_dcache_misses(int cpu, struct perf_evsel *evsel __used, dou else if (ratio > 5.0) color = PERF_COLOR_YELLOW; - fprintf(stderr, " # "); - color_fprintf(stderr, color, "%6.2f%%", ratio); - fprintf(stderr, " of all L1-dcache hits "); + fprintf(output, " # "); + color_fprintf(output, color, "%6.2f%%", ratio); + fprintf(output, " of all L1-dcache hits "); } static void print_l1_icache_misses(int cpu, struct perf_evsel *evsel __used, double avg) @@ -668,9 +671,9 @@ static void print_l1_icache_misses(int cpu, struct perf_evsel *evsel __used, dou else if (ratio > 5.0) color = PERF_COLOR_YELLOW; - fprintf(stderr, " # "); - color_fprintf(stderr, color, "%6.2f%%", ratio); - fprintf(stderr, " of all L1-icache hits "); + fprintf(output, " # "); + color_fprintf(output, color, "%6.2f%%", ratio); + fprintf(output, " of all L1-icache hits "); } static void print_dtlb_cache_misses(int cpu, struct perf_evsel *evsel __used, double avg) @@ -691,9 +694,9 @@ static void print_dtlb_cache_misses(int cpu, struct perf_evsel *evsel __used, do else if (ratio > 5.0) color = PERF_COLOR_YELLOW; - fprintf(stderr, " # "); - color_fprintf(stderr, color, "%6.2f%%", ratio); - fprintf(stderr, " of all dTLB cache hits "); + fprintf(output, " # "); + color_fprintf(output, color, "%6.2f%%", ratio); + fprintf(output, " of all dTLB cache hits "); } static void print_itlb_cache_misses(int cpu, struct perf_evsel *evsel __used, double avg) @@ -714,9 +717,9 @@ static void print_itlb_cache_misses(int cpu, struct perf_evsel *evsel __used, do else if (ratio > 5.0) color = PERF_COLOR_YELLOW; - fprintf(stderr, " # "); - color_fprintf(stderr, color, "%6.2f%%", ratio); - fprintf(stderr, " of all iTLB cache hits "); + fprintf(output, " # "); + color_fprintf(output, color, "%6.2f%%", ratio); + fprintf(output, " of all iTLB cache hits "); } static void print_ll_cache_misses(int cpu, struct perf_evsel *evsel __used, double avg) @@ -737,9 +740,9 @@ static void print_ll_cache_misses(int cpu, struct perf_evsel *evsel __used, doub else if (ratio > 5.0) color = PERF_COLOR_YELLOW; - fprintf(stderr, " # "); - color_fprintf(stderr, color, "%6.2f%%", ratio); - fprintf(stderr, " of all LL-cache hits "); + fprintf(output, " # "); + color_fprintf(output, color, "%6.2f%%", ratio); + fprintf(output, " of all LL-cache hits "); } static void abs_printout(int cpu, struct perf_evsel *evsel, double avg) @@ -762,10 +765,10 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg) else cpu = 0; - fprintf(stderr, fmt, cpustr, avg, csv_sep, event_name(evsel)); + fprintf(output, fmt, cpustr, avg, csv_sep, event_name(evsel)); if (evsel->cgrp) - fprintf(stderr, "%s%s", csv_sep, evsel->cgrp->name); + fprintf(output, "%s%s", csv_sep, evsel->cgrp->name); if (csv_output) return; @@ -776,14 +779,14 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg) if (total) ratio = avg / total; - fprintf(stderr, " # %5.2f insns per cycle ", ratio); + fprintf(output, " # %5.2f insns per cycle ", ratio); total = avg_stats(&runtime_stalled_cycles_front_stats[cpu]); total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[cpu])); if (total && avg) { ratio = total / avg; - fprintf(stderr, "\n # %5.2f stalled cycles per insn", ratio); + fprintf(output, "\n # %5.2f stalled cycles per insn", ratio); } } else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) && @@ -831,7 +834,7 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg) if (total) ratio = avg * 100 / total; - fprintf(stderr, " # %8.3f %% of all cache refs ", ratio); + fprintf(output, " # %8.3f %% of all cache refs ", ratio); } else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) { print_stalled_cycles_frontend(cpu, evsel, avg); @@ -843,16 +846,16 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg) if (total) ratio = 1.0 * avg / total; - fprintf(stderr, " # %8.3f GHz ", ratio); + fprintf(output, " # %8.3f GHz ", ratio); } else if (runtime_nsecs_stats[cpu].n != 0) { total = avg_stats(&runtime_nsecs_stats[cpu]); if (total) ratio = 1000.0 * avg / total; - fprintf(stderr, " # %8.3f M/sec ", ratio); + fprintf(output, " # %8.3f M/sec ", ratio); } else { - fprintf(stderr, " "); + fprintf(output, " "); } } @@ -867,7 +870,7 @@ static void print_counter_aggr(struct perf_evsel *counter) int scaled = counter->counts->scaled; if (scaled == -1) { - fprintf(stderr, "%*s%s%*s", + fprintf(output, "%*s%s%*s", csv_output ? 0 : 18, counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED, csv_sep, @@ -875,9 +878,9 @@ static void print_counter_aggr(struct perf_evsel *counter) event_name(counter)); if (counter->cgrp) - fprintf(stderr, "%s%s", csv_sep, counter->cgrp->name); + fprintf(output, "%s%s", csv_sep, counter->cgrp->name); - fputc('\n', stderr); + fputc('\n', output); return; } @@ -889,7 +892,7 @@ static void print_counter_aggr(struct perf_evsel *counter) print_noise(counter, avg); if (csv_output) { - fputc('\n', stderr); + fputc('\n', output); return; } @@ -899,9 +902,9 @@ static void print_counter_aggr(struct perf_evsel *counter) avg_enabled = avg_stats(&ps->res_stats[1]); avg_running = avg_stats(&ps->res_stats[2]); - fprintf(stderr, " [%5.2f%%]", 100 * avg_running / avg_enabled); + fprintf(output, " [%5.2f%%]", 100 * avg_running / avg_enabled); } - fprintf(stderr, "\n"); + fprintf(output, "\n"); } /* @@ -918,7 +921,7 @@ static void print_counter(struct perf_evsel *counter) ena = counter->counts->cpu[cpu].ena; run = counter->counts->cpu[cpu].run; if (run == 0 || ena == 0) { - fprintf(stderr, "CPU%*d%s%*s%s%*s", + fprintf(output, "CPU%*d%s%*s%s%*s", csv_output ? 0 : -4, evsel_list->cpus->map[cpu], csv_sep, csv_output ? 0 : 18, @@ -928,9 +931,10 @@ static void print_counter(struct perf_evsel *counter) event_name(counter)); if (counter->cgrp) - fprintf(stderr, "%s%s", csv_sep, counter->cgrp->name); + fprintf(output, "%s%s", + csv_sep, counter->cgrp->name); - fputc('\n', stderr); + fputc('\n', output); continue; } @@ -943,9 +947,10 @@ static void print_counter(struct perf_evsel *counter) print_noise(counter, 1.0); if (run != ena) - fprintf(stderr, " (%.2f%%)", 100.0 * run / ena); + fprintf(output, " (%.2f%%)", + 100.0 * run / ena); } - fputc('\n', stderr); + fputc('\n', output); } } @@ -957,21 +962,21 @@ static void print_stat(int argc, const char **argv) fflush(stdout); if (!csv_output) { - fprintf(stderr, "\n"); - fprintf(stderr, " Performance counter stats for "); + fprintf(output, "\n"); + fprintf(output, " Performance counter stats for "); if(target_pid == -1 && target_tid == -1) { - fprintf(stderr, "\'%s", argv[0]); + fprintf(output, "\'%s", argv[0]); for (i = 1; i < argc; i++) - fprintf(stderr, " %s", argv[i]); + fprintf(output, " %s", argv[i]); } else if (target_pid != -1) - fprintf(stderr, "process id \'%d", target_pid); + fprintf(output, "process id \'%d", target_pid); else - fprintf(stderr, "thread id \'%d", target_tid); + fprintf(output, "thread id \'%d", target_tid); - fprintf(stderr, "\'"); + fprintf(output, "\'"); if (run_count > 1) - fprintf(stderr, " (%d runs)", run_count); - fprintf(stderr, ":\n\n"); + fprintf(output, " (%d runs)", run_count); + fprintf(output, ":\n\n"); } if (no_aggr) { @@ -984,15 +989,15 @@ static void print_stat(int argc, const char **argv) if (!csv_output) { if (!null_run) - fprintf(stderr, "\n"); - fprintf(stderr, " %17.9f seconds time elapsed", + fprintf(output, "\n"); + fprintf(output, " %17.9f seconds time elapsed", avg_stats(&walltime_nsecs_stats)/1e9); if (run_count > 1) { - fprintf(stderr, " "); + fprintf(output, " "); print_noise_pct(stddev_stats(&walltime_nsecs_stats), avg_stats(&walltime_nsecs_stats)); } - fprintf(stderr, "\n\n"); + fprintf(output, "\n\n"); } } @@ -1030,6 +1035,8 @@ static int stat__set_big_num(const struct option *opt __used, return 0; } +static bool append_file; + static const struct option options[] = { OPT_CALLBACK('e', "event", &evsel_list, "event", "event selector. use 'perf list' to list available events", @@ -1070,6 +1077,9 @@ static const struct option options[] = { OPT_CALLBACK('G', "cgroup", &evsel_list, "name", "monitor event in cgroup name only", parse_cgroups), + OPT_STRING('o', "output", &output_name, "file", + "output file name"), + OPT_BOOLEAN(0, "append", &append_file, "append to the output file"), OPT_END() }; @@ -1141,6 +1151,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used) { struct perf_evsel *pos; int status = -ENOMEM; + const char *mode; setlocale(LC_ALL, ""); @@ -1151,6 +1162,23 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used) argc = parse_options(argc, argv, options, stat_usage, PARSE_OPT_STOP_AT_NON_OPTION); + output = stderr; + if (output_name && strcmp(output_name, "-")) + output = NULL; + + if (!output) { + struct timespec tm; + mode = append_file ? "a" : "w"; + + output = fopen(output_name, mode); + if (!output) { + perror("failed to create output file"); + exit(-1); + } + clock_gettime(CLOCK_REALTIME, &tm); + fprintf(output, "# started on %s\n", ctime(&tm.tv_sec)); + } + if (csv_sep) csv_output = true; else @@ -1226,7 +1254,8 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used) status = 0; for (run_idx = 0; run_idx < run_count; run_idx++) { if (run_count != 1 && verbose) - fprintf(stderr, "[ perf stat: executing run #%d ... ]\n", run_idx + 1); + fprintf(output, "[ perf stat: executing run #%d ... ]\n", + run_idx + 1); if (sync_run) sync(); diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index e01af2b..01d36ba 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -324,9 +324,12 @@ fallback: snprintf(command, sizeof(command), "objdump --start-address=0x%016" PRIx64 - " --stop-address=0x%016" PRIx64 " -dS -C %s|grep -v %s|expand", + " --stop-address=0x%016" PRIx64 + " -d %s %s -C %s|grep -v %s|expand", map__rip_2objdump(map, sym->start), map__rip_2objdump(map, sym->end), + symbol_conf.annotate_asm_raw ? "" : "--no-show-raw", + symbol_conf.annotate_src ? "-S" : "", symfs_filename, filename); pr_debug("Executing: %s\n", command); diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c index e191eb9..521c38a7 100644 --- a/tools/perf/util/color.c +++ b/tools/perf/util/color.c @@ -200,7 +200,7 @@ static int __color_vfprintf(FILE *fp, const char *color, const char *fmt, * Auto-detect: */ if (perf_use_color_default < 0) { - if (isatty(1) || pager_in_use()) + if (isatty(fileno(fp)) || pager_in_use()) perf_use_color_default = 1; else perf_use_color_default = 0; diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 469c026..245e60d 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -46,6 +46,8 @@ struct symbol_conf symbol_conf = { .exclude_other = true, .use_modules = true, .try_vmlinux_path = true, + .annotate_asm_raw = true, + .annotate_src = true, .symfs = "", }; diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 4f377d9..7733f0b 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -76,7 +76,9 @@ struct symbol_conf { exclude_other, show_cpu_utilization, initialized, - kptr_restrict; + kptr_restrict, + annotate_asm_raw, + annotate_src; const char *vmlinux_name, *kallsyms_name, *source_prefix, |