From 45ac1403f564f411c6a383a2448688ba8dd705a4 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 21 Jul 2015 12:44:02 +0300 Subject: perf: Add PERF_RECORD_SWITCH to indicate context switches There are already two events for context switches, namely the tracepoint sched:sched_switch and the software event context_switches. Unfortunately neither are suitable for use by non-privileged users for the purpose of synchronizing hardware trace data (e.g. Intel PT) to the context switch. Tracepoints are no good at all for non-privileged users because they need either CAP_SYS_ADMIN or /proc/sys/kernel/perf_event_paranoid <= -1. On the other hand, kernel software events need either CAP_SYS_ADMIN or /proc/sys/kernel/perf_event_paranoid <= 1. Now many distributions do default perf_event_paranoid to 1 making context_switches a contender, except it has another problem (which is also shared with sched:sched_switch) which is that it happens before perf schedules events out instead of after perf schedules events in. Whereas a privileged user can see all the events anyway, a non-privileged user only sees events for their own processes, in other words they see when their process was scheduled out not when it was scheduled in. That presents two problems to use the event: 1. the information comes too late, so tools have to look ahead in the event stream to find out what the current state is 2. if they are unlucky tracing might have stopped before the context-switches event is recorded. This new PERF_RECORD_SWITCH event does not have those problems and it also has a couple of other small advantages. It is easier to use because it is an auxiliary event (like mmap, comm and task events) which can be enabled by setting a single bit. It is smaller than sched:sched_switch and easier to parse. To make the event useful for privileged users also, if the context is cpu-wide then the event record will be PERF_RECORD_SWITCH_CPU_WIDE which is the same as PERF_RECORD_SWITCH except it also provides the next or previous pid/tid. Signed-off-by: Adrian Hunter Acked-by: Peter Zijlstra (Intel) Tested-by: Jiri Olsa Cc: Andi Kleen Cc: Mathieu Poirier Cc: Pawel Moll Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1437471846-26995-2-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- include/uapi/linux/perf_event.h | 31 ++++++++++++++++++++++++++++++- 1 file changed, 30 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index d97f84c080da..022d0acf7df0 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -330,7 +330,8 @@ struct perf_event_attr { mmap2 : 1, /* include mmap with inode data */ comm_exec : 1, /* flag comm events that are due to an exec */ use_clockid : 1, /* use @clockid for time fields */ - __reserved_1 : 38; + context_switch : 1, /* context switch data */ + __reserved_1 : 37; union { __u32 wakeup_events; /* wakeup every n events */ @@ -572,9 +573,11 @@ struct perf_event_mmap_page { /* * PERF_RECORD_MISC_MMAP_DATA and PERF_RECORD_MISC_COMM_EXEC are used on * different events so can reuse the same bit position. + * Ditto PERF_RECORD_MISC_SWITCH_OUT. */ #define PERF_RECORD_MISC_MMAP_DATA (1 << 13) #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 @@ -818,6 +821,32 @@ enum perf_event_type { */ PERF_RECORD_LOST_SAMPLES = 13, + /* + * Records a context switch in or out (flagged by + * PERF_RECORD_MISC_SWITCH_OUT). See also + * PERF_RECORD_SWITCH_CPU_WIDE. + * + * struct { + * struct perf_event_header header; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_SWITCH = 14, + + /* + * CPU-wide version of PERF_RECORD_SWITCH with next_prev_pid and + * next_prev_tid that are the next (switching out) or previous + * (switching in) pid/tid. + * + * struct { + * struct perf_event_header header; + * u32 next_prev_pid; + * u32 next_prev_tid; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_SWITCH_CPU_WIDE = 15, + PERF_RECORD_MAX, /* non-ABI */ }; -- cgit v1.2.3 From 71ef3c6b9d4665ee7afbbe4c208a98917dcfc32f Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Sun, 10 May 2015 12:22:42 -0700 Subject: perf: Add cycles to branch_info Intel Skylake supports reporting the time in cycles a branch in the LBR took, to give a rough indication of the basic block performance. Export the cycle information in the branch_info structure. This can be done by just reusing some currently zero padding. This is just the generic header change. The architecture still needs to fill it in. There's no attempt to convert to real time, as we really want cycles here. Signed-off-by: Andi Kleen Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: eranian@google.com Link: http://lkml.kernel.org/r/1431285767-27027-5-git-send-email-andi@firstfloor.org Signed-off-by: Ingo Molnar --- include/uapi/linux/perf_event.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 022d0acf7df0..2881145cda86 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -951,6 +951,7 @@ union perf_mem_data_src { * * in_tx: running in a hardware transaction * abort: aborting a hardware transaction + * cycles: cycles from last branch (or 0 if not supported) */ struct perf_branch_entry { __u64 from; @@ -959,7 +960,8 @@ struct perf_branch_entry { predicted:1,/* target predicted */ in_tx:1, /* in transaction */ abort:1, /* transaction abort */ - reserved:60; + cycles:16, /* cycle count to last branch */ + reserved:44; }; #endif /* _UAPI_LINUX_PERF_EVENT_H */ -- cgit v1.2.3