From 339ce1a4dc2ca26444c4f65c31b71a5056f3bb0b Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Mon, 18 Jan 2010 16:47:07 +1100 Subject: perf: Fix inconsistency between IP and callchain sampling When running perf across all cpus with backtracing (-a -g), sometimes we get samples without associated backtraces: 23.44% init [kernel] [k] restore 11.46% init eeba0c [k] 0x00000000eeba0c 6.77% swapper [kernel] [k] .perf_ctx_adjust_freq 5.73% init [kernel] [k] .__trace_hcall_entry 4.69% perf libc-2.9.so [.] 0x0000000006bb8c | |--11.11%-- 0xfffa941bbbc It turns out the backtrace code has a check for the idle task and the IP sampling does not. This creates problems when profiling an interrupt heavy workload (in my case 10Gbit ethernet) since we get no backtraces for interrupts received while idle (ie most of the workload). Right now x86 and sh check that current is not NULL, which should never happen so remove that too. Idle task's exclusion must be performed from the core code, on top of perf_event_attr:exclude_idle. Signed-off-by: Anton Blanchard Cc: Peter Zijlstra Cc: Paul Mackerras Cc: Ingo Molnar Cc: Benjamin Herrenschmidt Cc: Paul Mundt LKML-Reference: <20100118054707.GT12666@kryten> Signed-off-by: Frederic Weisbecker --- arch/powerpc/kernel/perf_callchain.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/kernel/perf_callchain.c b/arch/powerpc/kernel/perf_callchain.c index a3c11cac3d7..95ad9dad298 100644 --- a/arch/powerpc/kernel/perf_callchain.c +++ b/arch/powerpc/kernel/perf_callchain.c @@ -495,9 +495,6 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs) entry->nr = 0; - if (current->pid == 0) /* idle task? */ - return entry; - if (!user_mode(regs)) { perf_callchain_kernel(regs, entry); if (current->mm) -- cgit v1.2.3-70-g09d2 From 6e37738a2fac964583debe91099bc3248554f6e5 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 11 Feb 2010 13:21:58 +0100 Subject: perf_events: Simplify code by removing cpu argument to hw_perf_group_sched_in() Since the cpu argument to hw_perf_group_sched_in() is always smp_processor_id(), simplify the code a little by removing this argument and using the current cpu where needed. Signed-off-by: Peter Zijlstra Cc: David Miller Cc: Paul Mackerras Cc: Benjamin Herrenschmidt Cc: Frederic Weisbecker LKML-Reference: <1265890918.5396.3.camel@laptop> Signed-off-by: Ingo Molnar --- arch/powerpc/kernel/perf_event.c | 10 ++++----- arch/sparc/kernel/perf_event.c | 10 ++++----- arch/x86/kernel/cpu/perf_event.c | 18 ++++++++-------- include/linux/perf_event.h | 2 +- kernel/perf_event.c | 45 ++++++++++++++++------------------------ 5 files changed, 38 insertions(+), 47 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c index 1eb85fbf53a..b6cf8f1f4d3 100644 --- a/arch/powerpc/kernel/perf_event.c +++ b/arch/powerpc/kernel/perf_event.c @@ -718,10 +718,10 @@ static int collect_events(struct perf_event *group, int max_count, return n; } -static void event_sched_in(struct perf_event *event, int cpu) +static void event_sched_in(struct perf_event *event) { event->state = PERF_EVENT_STATE_ACTIVE; - event->oncpu = cpu; + event->oncpu = smp_processor_id(); event->tstamp_running += event->ctx->time - event->tstamp_stopped; if (is_software_event(event)) event->pmu->enable(event); @@ -735,7 +735,7 @@ static void event_sched_in(struct perf_event *event, int cpu) */ int hw_perf_group_sched_in(struct perf_event *group_leader, struct perf_cpu_context *cpuctx, - struct perf_event_context *ctx, int cpu) + struct perf_event_context *ctx) { struct cpu_hw_events *cpuhw; long i, n, n0; @@ -766,10 +766,10 @@ int hw_perf_group_sched_in(struct perf_event *group_leader, cpuhw->event[i]->hw.config = cpuhw->events[i]; cpuctx->active_oncpu += n; n = 1; - event_sched_in(group_leader, cpu); + event_sched_in(group_leader); list_for_each_entry(sub, &group_leader->sibling_list, group_entry) { if (sub->state != PERF_EVENT_STATE_OFF) { - event_sched_in(sub, cpu); + event_sched_in(sub); ++n; } } diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c index e856456ec02..9f2b2bac8b2 100644 --- a/arch/sparc/kernel/perf_event.c +++ b/arch/sparc/kernel/perf_event.c @@ -980,10 +980,10 @@ static int collect_events(struct perf_event *group, int max_count, return n; } -static void event_sched_in(struct perf_event *event, int cpu) +static void event_sched_in(struct perf_event *event) { event->state = PERF_EVENT_STATE_ACTIVE; - event->oncpu = cpu; + event->oncpu = smp_processor_id(); event->tstamp_running += event->ctx->time - event->tstamp_stopped; if (is_software_event(event)) event->pmu->enable(event); @@ -991,7 +991,7 @@ static void event_sched_in(struct perf_event *event, int cpu) int hw_perf_group_sched_in(struct perf_event *group_leader, struct perf_cpu_context *cpuctx, - struct perf_event_context *ctx, int cpu) + struct perf_event_context *ctx) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct perf_event *sub; @@ -1015,10 +1015,10 @@ int hw_perf_group_sched_in(struct perf_event *group_leader, cpuctx->active_oncpu += n; n = 1; - event_sched_in(group_leader, cpu); + event_sched_in(group_leader); list_for_each_entry(sub, &group_leader->sibling_list, group_entry) { if (sub->state != PERF_EVENT_STATE_OFF) { - event_sched_in(sub, cpu); + event_sched_in(sub); n++; } } diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index aa12f36e471..ad096562d69 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -2403,12 +2403,12 @@ done: } static int x86_event_sched_in(struct perf_event *event, - struct perf_cpu_context *cpuctx, int cpu) + struct perf_cpu_context *cpuctx) { int ret = 0; event->state = PERF_EVENT_STATE_ACTIVE; - event->oncpu = cpu; + event->oncpu = smp_processor_id(); event->tstamp_running += event->ctx->time - event->tstamp_stopped; if (!is_x86_event(event)) @@ -2424,7 +2424,7 @@ static int x86_event_sched_in(struct perf_event *event, } static void x86_event_sched_out(struct perf_event *event, - struct perf_cpu_context *cpuctx, int cpu) + struct perf_cpu_context *cpuctx) { event->state = PERF_EVENT_STATE_INACTIVE; event->oncpu = -1; @@ -2452,9 +2452,9 @@ static void x86_event_sched_out(struct perf_event *event, */ int hw_perf_group_sched_in(struct perf_event *leader, struct perf_cpu_context *cpuctx, - struct perf_event_context *ctx, int cpu) + struct perf_event_context *ctx) { - struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct perf_event *sub; int assign[X86_PMC_IDX_MAX]; int n0, n1, ret; @@ -2468,14 +2468,14 @@ int hw_perf_group_sched_in(struct perf_event *leader, if (ret) return ret; - ret = x86_event_sched_in(leader, cpuctx, cpu); + ret = x86_event_sched_in(leader, cpuctx); if (ret) return ret; n1 = 1; list_for_each_entry(sub, &leader->sibling_list, group_entry) { if (sub->state > PERF_EVENT_STATE_OFF) { - ret = x86_event_sched_in(sub, cpuctx, cpu); + ret = x86_event_sched_in(sub, cpuctx); if (ret) goto undo; ++n1; @@ -2500,11 +2500,11 @@ int hw_perf_group_sched_in(struct perf_event *leader, */ return 1; undo: - x86_event_sched_out(leader, cpuctx, cpu); + x86_event_sched_out(leader, cpuctx); n0 = 1; list_for_each_entry(sub, &leader->sibling_list, group_entry) { if (sub->state == PERF_EVENT_STATE_ACTIVE) { - x86_event_sched_out(sub, cpuctx, cpu); + x86_event_sched_out(sub, cpuctx); if (++n0 == n1) break; } diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index b08dfdad08c..d0e072c5b58 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -772,7 +772,7 @@ extern int perf_event_task_disable(void); extern int perf_event_task_enable(void); extern int hw_perf_group_sched_in(struct perf_event *group_leader, struct perf_cpu_context *cpuctx, - struct perf_event_context *ctx, int cpu); + struct perf_event_context *ctx); extern void perf_event_update_userpage(struct perf_event *event); extern int perf_event_release_kernel(struct perf_event *event); extern struct perf_event * diff --git a/kernel/perf_event.c b/kernel/perf_event.c index fb4e56eb58f..05b6c6b825e 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -103,7 +103,7 @@ void __weak hw_perf_event_setup_offline(int cpu) { barrier(); } int __weak hw_perf_group_sched_in(struct perf_event *group_leader, struct perf_cpu_context *cpuctx, - struct perf_event_context *ctx, int cpu) + struct perf_event_context *ctx) { return 0; } @@ -633,14 +633,13 @@ void perf_event_disable(struct perf_event *event) static int event_sched_in(struct perf_event *event, struct perf_cpu_context *cpuctx, - struct perf_event_context *ctx, - int cpu) + struct perf_event_context *ctx) { if (event->state <= PERF_EVENT_STATE_OFF) return 0; event->state = PERF_EVENT_STATE_ACTIVE; - event->oncpu = cpu; /* TODO: put 'cpu' into cpuctx->cpu */ + event->oncpu = smp_processor_id(); /* * The new state must be visible before we turn it on in the hardware: */ @@ -667,8 +666,7 @@ event_sched_in(struct perf_event *event, static int group_sched_in(struct perf_event *group_event, struct perf_cpu_context *cpuctx, - struct perf_event_context *ctx, - int cpu) + struct perf_event_context *ctx) { struct perf_event *event, *partial_group; int ret; @@ -676,18 +674,18 @@ group_sched_in(struct perf_event *group_event, if (group_event->state == PERF_EVENT_STATE_OFF) return 0; - ret = hw_perf_group_sched_in(group_event, cpuctx, ctx, cpu); + ret = hw_perf_group_sched_in(group_event, cpuctx, ctx); if (ret) return ret < 0 ? ret : 0; - if (event_sched_in(group_event, cpuctx, ctx, cpu)) + if (event_sched_in(group_event, cpuctx, ctx)) return -EAGAIN; /* * Schedule in siblings as one group (if any): */ list_for_each_entry(event, &group_event->sibling_list, group_entry) { - if (event_sched_in(event, cpuctx, ctx, cpu)) { + if (event_sched_in(event, cpuctx, ctx)) { partial_group = event; goto group_error; } @@ -761,7 +759,6 @@ static void __perf_install_in_context(void *info) struct perf_event *event = info; struct perf_event_context *ctx = event->ctx; struct perf_event *leader = event->group_leader; - int cpu = smp_processor_id(); int err; /* @@ -808,7 +805,7 @@ static void __perf_install_in_context(void *info) if (!group_can_go_on(event, cpuctx, 1)) err = -EEXIST; else - err = event_sched_in(event, cpuctx, ctx, cpu); + err = event_sched_in(event, cpuctx, ctx); if (err) { /* @@ -950,11 +947,9 @@ static void __perf_event_enable(void *info) } else { perf_disable(); if (event == leader) - err = group_sched_in(event, cpuctx, ctx, - smp_processor_id()); + err = group_sched_in(event, cpuctx, ctx); else - err = event_sched_in(event, cpuctx, ctx, - smp_processor_id()); + err = event_sched_in(event, cpuctx, ctx); perf_enable(); } @@ -1281,19 +1276,18 @@ static void cpu_ctx_sched_out(struct perf_cpu_context *cpuctx, static void ctx_pinned_sched_in(struct perf_event_context *ctx, - struct perf_cpu_context *cpuctx, - int cpu) + struct perf_cpu_context *cpuctx) { struct perf_event *event; list_for_each_entry(event, &ctx->pinned_groups, group_entry) { if (event->state <= PERF_EVENT_STATE_OFF) continue; - if (event->cpu != -1 && event->cpu != cpu) + if (event->cpu != -1 && event->cpu != smp_processor_id()) continue; if (group_can_go_on(event, cpuctx, 1)) - group_sched_in(event, cpuctx, ctx, cpu); + group_sched_in(event, cpuctx, ctx); /* * If this pinned group hasn't been scheduled, @@ -1308,8 +1302,7 @@ ctx_pinned_sched_in(struct perf_event_context *ctx, static void ctx_flexible_sched_in(struct perf_event_context *ctx, - struct perf_cpu_context *cpuctx, - int cpu) + struct perf_cpu_context *cpuctx) { struct perf_event *event; int can_add_hw = 1; @@ -1322,11 +1315,11 @@ ctx_flexible_sched_in(struct perf_event_context *ctx, * Listen to the 'cpu' scheduling filter constraint * of events: */ - if (event->cpu != -1 && event->cpu != cpu) + if (event->cpu != -1 && event->cpu != smp_processor_id()) continue; if (group_can_go_on(event, cpuctx, can_add_hw)) - if (group_sched_in(event, cpuctx, ctx, cpu)) + if (group_sched_in(event, cpuctx, ctx)) can_add_hw = 0; } } @@ -1336,8 +1329,6 @@ ctx_sched_in(struct perf_event_context *ctx, struct perf_cpu_context *cpuctx, enum event_type_t event_type) { - int cpu = smp_processor_id(); - raw_spin_lock(&ctx->lock); ctx->is_active = 1; if (likely(!ctx->nr_events)) @@ -1352,11 +1343,11 @@ ctx_sched_in(struct perf_event_context *ctx, * in order to give them the best chance of going on. */ if (event_type & EVENT_PINNED) - ctx_pinned_sched_in(ctx, cpuctx, cpu); + ctx_pinned_sched_in(ctx, cpuctx); /* Then walk through the lower prio flexible groups */ if (event_type & EVENT_FLEXIBLE) - ctx_flexible_sched_in(ctx, cpuctx, cpu); + ctx_flexible_sched_in(ctx, cpuctx); perf_enable(); out: -- cgit v1.2.3-70-g09d2