Currently any ctx_sched_in() call will re-start the ctx time tracking, this means that calls like: ctx_sched_in(.event_type = EVENT_PINNED); ctx_sched_in(.event_type = EVENT_FLEXIBLE); will have a hole in their ctx time tracking. This is likely harmless but can confuse things a little. By adding EVENT_TIME, we can have the first ctx_sched_in() (is_active: 0 -> !0) start the time and any further ctx_sched_in() will leave the timestamps alone. Secondly, this allows for an early disable like: ctx_sched_out(.event_type = EVENT_TIME); which would update the ctx time (if the ctx is active) and any further calls to ctx_sched_out() would not further modify the ctx time. For ctx_sched_in() any 0 -> !0 transition will automatically include EVENT_TIME. For ctx_sched_out(), any transition that clears EVENT_ALL will automatically clear EVENT_TIME. These two rules ensure that under normal circumstances we need not bother with EVENT_TIME and get natural ctx time behaviour. Signed-off-by: Peter Zijlstra (Intel) --- kernel/events/core.c | 42 ++++++++++++++++++++++++++++++------------ 1 file changed, 30 insertions(+), 12 deletions(-) --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -314,6 +314,7 @@ static void event_function_call(struct p enum event_type_t { EVENT_FLEXIBLE = 0x1, EVENT_PINNED = 0x2, + EVENT_TIME = 0x4, EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED, }; @@ -1294,16 +1295,18 @@ static u64 perf_event_time(struct perf_e /* * Update the total_time_enabled and total_time_running fields for a event. - * The caller of this function needs to hold the ctx->lock. */ static void update_event_times(struct perf_event *event) { struct perf_event_context *ctx = event->ctx; u64 run_end; + lockdep_assert_held(&ctx->lock); + if (event->state < PERF_EVENT_STATE_INACTIVE || event->group_leader->state < PERF_EVENT_STATE_INACTIVE) return; + /* * in cgroup mode, time_enabled represents * the time the event was enabled AND active @@ -2349,24 +2352,33 @@ static void ctx_sched_out(struct perf_ev } ctx->is_active &= ~event_type; + if (!(ctx->is_active & EVENT_ALL)) + ctx->is_active = 0; + if (ctx->task) { WARN_ON_ONCE(cpuctx->task_ctx != ctx); if (!ctx->is_active) cpuctx->task_ctx = NULL; } - update_context_time(ctx); - update_cgrp_time_from_cpuctx(cpuctx); - if (!ctx->nr_active) + is_active ^= ctx->is_active; /* changed bits */ + + if (is_active & EVENT_TIME) { + /* update (and stop) ctx time */ + update_context_time(ctx); + update_cgrp_time_from_cpuctx(cpuctx); + } + + if (!ctx->nr_active || !(is_active & EVENT_ALL)) return; perf_pmu_disable(ctx->pmu); - if ((is_active & EVENT_PINNED) && (event_type & EVENT_PINNED)) { + if (is_active & EVENT_PINNED) { list_for_each_entry(event, &ctx->pinned_groups, group_entry) group_sched_out(event, cpuctx, ctx); } - if ((is_active & EVENT_FLEXIBLE) && (event_type & EVENT_FLEXIBLE)) { + if (is_active & EVENT_FLEXIBLE) { list_for_each_entry(event, &ctx->flexible_groups, group_entry) group_sched_out(event, cpuctx, ctx); } @@ -2740,7 +2752,7 @@ ctx_sched_in(struct perf_event_context * if (likely(!ctx->nr_events)) return; - ctx->is_active |= event_type; + ctx->is_active |= (event_type | EVENT_TIME); if (ctx->task) { if (!is_active) cpuctx->task_ctx = ctx; @@ -2748,18 +2760,24 @@ ctx_sched_in(struct perf_event_context * WARN_ON_ONCE(cpuctx->task_ctx != ctx); } - now = perf_clock(); - ctx->timestamp = now; - perf_cgroup_set_timestamp(task, ctx); + is_active ^= ctx->is_active; /* changed bits */ + + if (is_active & EVENT_TIME) { + /* start ctx time */ + now = perf_clock(); + ctx->timestamp = now; + perf_cgroup_set_timestamp(task, ctx); + } + /* * First go through the list and put on any pinned groups * in order to give them the best chance of going on. */ - if (!(is_active & EVENT_PINNED) && (event_type & EVENT_PINNED)) + if (is_active & EVENT_PINNED) ctx_pinned_sched_in(ctx, cpuctx); /* Then walk through the lower prio flexible groups */ - if (!(is_active & EVENT_FLEXIBLE) && (event_type & EVENT_FLEXIBLE)) + if (is_active & EVENT_FLEXIBLE) ctx_flexible_sched_in(ctx, cpuctx); }