From 101592b4904ecf6b8ed2a4784d41d180319d95a1 Mon Sep 17 00:00:00 2001 From: Alexey Budankov Date: Mon, 9 Apr 2018 10:25:32 +0300 Subject: [PATCH] perf/core: Store context switch out type in PERF_RECORD_SWITCH[_CPU_WIDE] Store preempting context switch out event into Perf trace as a part of PERF_RECORD_SWITCH[_CPU_WIDE] record. Percentage of preempting and non-preempting context switches help understanding the nature of workloads (CPU or IO bound) that are running on a machine; The event is treated as preemption one when task->state value of the thread being switched out is TASK_RUNNING. Event type encoding is implemented using PERF_RECORD_MISC_SWITCH_OUT_PREEMPT bit; Signed-off-by: Alexey Budankov Acked-by: Peter Zijlstra Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/9ff84e83-a0ca-dd82-a6d0-cb951689be74@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- include/uapi/linux/perf_event.h | 18 +++++++++++++++--- kernel/events/core.c | 4 ++++ tools/include/uapi/linux/perf_event.h | 18 +++++++++++++++--- 3 files changed, 34 insertions(+), 6 deletions(-) diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 912b85b52344..b8e288a1f740 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -650,11 +650,23 @@ struct perf_event_mmap_page { #define PERF_RECORD_MISC_COMM_EXEC (1 << 13) #define PERF_RECORD_MISC_SWITCH_OUT (1 << 13) /* - * Indicates that the content of PERF_SAMPLE_IP points to - * the actual instruction that triggered the event. See also - * perf_event_attr::precise_ip. + * These PERF_RECORD_MISC_* flags below are safely reused + * for the following events: + * + * PERF_RECORD_MISC_EXACT_IP - PERF_RECORD_SAMPLE of precise events + * PERF_RECORD_MISC_SWITCH_OUT_PREEMPT - PERF_RECORD_SWITCH* events + * + * + * PERF_RECORD_MISC_EXACT_IP: + * Indicates that the content of PERF_SAMPLE_IP points to + * the actual instruction that triggered the event. See also + * perf_event_attr::precise_ip. + * + * PERF_RECORD_MISC_SWITCH_OUT_PREEMPT: + * Indicates that thread was preempted in TASK_RUNNING state. */ #define PERF_RECORD_MISC_EXACT_IP (1 << 14) +#define PERF_RECORD_MISC_SWITCH_OUT_PREEMPT (1 << 14) /* * Reserve the last bit to indicate some extended misc field */ diff --git a/kernel/events/core.c b/kernel/events/core.c index 2d5fe26551f8..1bae80aaabfb 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -7587,6 +7587,10 @@ static void perf_event_switch(struct task_struct *task, }, }; + if (!sched_in && task->state == TASK_RUNNING) + switch_event.event_id.header.misc |= + PERF_RECORD_MISC_SWITCH_OUT_PREEMPT; + perf_iterate_sb(perf_event_switch_output, &switch_event, NULL); diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 912b85b52344..b8e288a1f740 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -650,11 +650,23 @@ struct perf_event_mmap_page { #define PERF_RECORD_MISC_COMM_EXEC (1 << 13) #define PERF_RECORD_MISC_SWITCH_OUT (1 << 13) /* - * Indicates that the content of PERF_SAMPLE_IP points to - * the actual instruction that triggered the event. See also - * perf_event_attr::precise_ip. + * These PERF_RECORD_MISC_* flags below are safely reused + * for the following events: + * + * PERF_RECORD_MISC_EXACT_IP - PERF_RECORD_SAMPLE of precise events + * PERF_RECORD_MISC_SWITCH_OUT_PREEMPT - PERF_RECORD_SWITCH* events + * + * + * PERF_RECORD_MISC_EXACT_IP: + * Indicates that the content of PERF_SAMPLE_IP points to + * the actual instruction that triggered the event. See also + * perf_event_attr::precise_ip. + * + * PERF_RECORD_MISC_SWITCH_OUT_PREEMPT: + * Indicates that thread was preempted in TASK_RUNNING state. */ #define PERF_RECORD_MISC_EXACT_IP (1 << 14) +#define PERF_RECORD_MISC_SWITCH_OUT_PREEMPT (1 << 14) /* * Reserve the last bit to indicate some extended misc field */ -- 2.30.2