diff options
author | Ingo Molnar <mingo@kernel.org> | 2015-07-27 15:56:18 (GMT) |
---|---|---|
committer | Ingo Molnar <mingo@kernel.org> | 2015-07-27 15:56:18 (GMT) |
commit | 4b0c53e9e1a2a785746b2d379a32cb70b4dbb2fd (patch) | |
tree | ebac2c2525d9747d6220ae1319e37a7d2af13b6f /kernel/events | |
parent | a11c51acc52822754d66a11c15f6f6edd4d23c55 (diff) | |
parent | 7c14898ba9386ee5c939bb418643ac6baff52840 (diff) | |
download | linux-4b0c53e9e1a2a785746b2d379a32cb70b4dbb2fd.tar.xz |
Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core
Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:
New features:
- Introduce PERF_RECORD_SWITCH(_CPU_WIDE) and use it in 'record' to
ask for context switches, allowing non priviledged tasks to know
when they are switched in and out, which wasn't possible with
the other context switch tracepoint and software events, see the
patch description for a comprehensive justification (Adrian Hunter)
- Stop collecting /proc/kallsyms in perf.data files, saving about
4.5MB on a typical x86-64 system, use the the symbol resolution
routines used in all the other tools (report, top, etc) now that
we can ask libtraceevent to use perf's symbol resolution code.
(Arnaldo Carvalho de Melo)
User visible fixes:
- Expose perf's symbol resolver to libtraceevent, so that its plugins can
resolve tracepoint fields to kernel functions, like the 'function' field
in the "timer:hrtimer_start tracepoint" (Arnaldo Carvalho de Melo)
Infrastructure changes:
- Map propagation of thread and cpu maps improvements, prep work for
'perf stat' new features (Jiri Olsa)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'kernel/events')
-rw-r--r-- | kernel/events/core.c | 103 |
1 files changed, 103 insertions, 0 deletions
diff --git a/kernel/events/core.c b/kernel/events/core.c index d3dae34..ce21143 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -163,6 +163,7 @@ static atomic_t nr_mmap_events __read_mostly; static atomic_t nr_comm_events __read_mostly; static atomic_t nr_task_events __read_mostly; static atomic_t nr_freq_events __read_mostly; +static atomic_t nr_switch_events __read_mostly; static LIST_HEAD(pmus); static DEFINE_MUTEX(pmus_lock); @@ -2619,6 +2620,9 @@ static void perf_pmu_sched_task(struct task_struct *prev, local_irq_restore(flags); } +static void perf_event_switch(struct task_struct *task, + struct task_struct *next_prev, bool sched_in); + #define for_each_task_context_nr(ctxn) \ for ((ctxn) = 0; (ctxn) < perf_nr_task_contexts; (ctxn)++) @@ -2641,6 +2645,9 @@ void __perf_event_task_sched_out(struct task_struct *task, if (__this_cpu_read(perf_sched_cb_usages)) perf_pmu_sched_task(task, next, false); + if (atomic_read(&nr_switch_events)) + perf_event_switch(task, next, false); + for_each_task_context_nr(ctxn) perf_event_context_sched_out(task, ctxn, next); @@ -2831,6 +2838,9 @@ void __perf_event_task_sched_in(struct task_struct *prev, if (atomic_read(this_cpu_ptr(&perf_cgroup_events))) perf_cgroup_sched_in(prev, task); + if (atomic_read(&nr_switch_events)) + perf_event_switch(task, prev, true); + if (__this_cpu_read(perf_sched_cb_usages)) perf_pmu_sched_task(prev, task, true); } @@ -3454,6 +3464,10 @@ static void unaccount_event(struct perf_event *event) atomic_dec(&nr_task_events); if (event->attr.freq) atomic_dec(&nr_freq_events); + if (event->attr.context_switch) { + static_key_slow_dec_deferred(&perf_sched_events); + atomic_dec(&nr_switch_events); + } if (is_cgroup_event(event)) static_key_slow_dec_deferred(&perf_sched_events); if (has_branch_stack(event)) @@ -5982,6 +5996,91 @@ void perf_log_lost_samples(struct perf_event *event, u64 lost) } /* + * context_switch tracking + */ + +struct perf_switch_event { + struct task_struct *task; + struct task_struct *next_prev; + + struct { + struct perf_event_header header; + u32 next_prev_pid; + u32 next_prev_tid; + } event_id; +}; + +static int perf_event_switch_match(struct perf_event *event) +{ + return event->attr.context_switch; +} + +static void perf_event_switch_output(struct perf_event *event, void *data) +{ + struct perf_switch_event *se = data; + struct perf_output_handle handle; + struct perf_sample_data sample; + int ret; + + if (!perf_event_switch_match(event)) + return; + + /* Only CPU-wide events are allowed to see next/prev pid/tid */ + if (event->ctx->task) { + se->event_id.header.type = PERF_RECORD_SWITCH; + se->event_id.header.size = sizeof(se->event_id.header); + } else { + se->event_id.header.type = PERF_RECORD_SWITCH_CPU_WIDE; + se->event_id.header.size = sizeof(se->event_id); + se->event_id.next_prev_pid = + perf_event_pid(event, se->next_prev); + se->event_id.next_prev_tid = + perf_event_tid(event, se->next_prev); + } + + perf_event_header__init_id(&se->event_id.header, &sample, event); + + ret = perf_output_begin(&handle, event, se->event_id.header.size); + if (ret) + return; + + if (event->ctx->task) + perf_output_put(&handle, se->event_id.header); + else + perf_output_put(&handle, se->event_id); + + perf_event__output_id_sample(event, &handle, &sample); + + perf_output_end(&handle); +} + +static void perf_event_switch(struct task_struct *task, + struct task_struct *next_prev, bool sched_in) +{ + struct perf_switch_event switch_event; + + /* N.B. caller checks nr_switch_events != 0 */ + + switch_event = (struct perf_switch_event){ + .task = task, + .next_prev = next_prev, + .event_id = { + .header = { + /* .type */ + .misc = sched_in ? 0 : PERF_RECORD_MISC_SWITCH_OUT, + /* .size */ + }, + /* .next_prev_pid */ + /* .next_prev_tid */ + }, + }; + + perf_event_aux(perf_event_switch_output, + &switch_event, + NULL); +} + +/* * IRQ throttle logging */ @@ -7479,6 +7578,10 @@ static void account_event(struct perf_event *event) if (atomic_inc_return(&nr_freq_events) == 1) tick_nohz_full_kick_all(); } + if (event->attr.context_switch) { + atomic_inc(&nr_switch_events); + static_key_slow_inc(&perf_sched_events.key); + } if (has_branch_stack(event)) static_key_slow_inc(&perf_sched_events.key); if (is_cgroup_event(event)) |