perf: Add ITRACE_START record to indicate that tracing has started

For counters that generate AUX data that is bound to the context of a
running task, such as instruction tracing, the decoder needs to know
exactly which task is running when the event is first scheduled in,
before the first sched_switch. The decoder's need to know this stems
from the fact that instruction flow trace decoding will almost always
require program's object code in order to reconstruct said flow and
for that we need at least its pid/tid in the perf stream.

To single out such instruction tracing pmus, this patch introduces
ITRACE PMU capability. The reason this is not part of RECORD_AUX
record is that not all pmus capable of generating AUX data need this,
and the opposite is *probably* also true.

While sched_switch covers for most cases, there are two problems with it:
the consumer will need to process events out of order (that is, having
found RECORD_AUX, it will have to skip forward to the nearest sched_switch
to figure out which task it was, then go back to the actual trace to
decode it) and it completely misses the case when the tracing is enabled
and disabled before sched_switch, for example, via PERF_EVENT_IOC_DISABLE.

Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Kaixu Xia <kaixu.xia@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Robert Richter <rric@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: acme@infradead.org
Cc: adrian.hunter@intel.com
Cc: kan.liang@intel.com
Cc: markus.t.metzger@intel.com
Cc: mathieu.poirier@linaro.org
Link: http://lkml.kernel.org/r/1421237903-181015-15-git-send-email-alexander.shishkin@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 45c5873ad9b3ddfcd2f1ea270ea2e9cf34b0b52b..61992cf2e9771699ee06595c8fbb1bd39633018a 100644 (file)
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -129,6 +129,9 @@ struct hw_perf_event {
                        struct list_head        cqm_groups_entry;
                        struct list_head        cqm_group_entry;
                };
+               struct { /* itrace */
+                       int                     itrace_started;
+               };
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
                struct { /* breakpoint */
                        /*
@@ -177,6 +180,7 @@ struct perf_event;
 #define PERF_PMU_CAP_AUX_NO_SG                 0x04
 #define PERF_PMU_CAP_AUX_SW_DOUBLEBUF          0x08
 #define PERF_PMU_CAP_EXCLUSIVE                 0x10
+#define PERF_PMU_CAP_ITRACE                    0x20
 
 /**
  * struct pmu - generic performance monitoring unit

diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 84819546c8cea361f858daed99411ed2c5baf4c8..309211b3eb672f9449a0fc266ed643ac881196d3 100644 (file)
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -789,6 +789,17 @@ enum perf_event_type {
         */
        PERF_RECORD_AUX                         = 11,
 
+       /*
+        * Indicates that instruction trace has started
+        *
+        * struct {
+        *      struct perf_event_header        header;
+        *      u32                             pid;
+        *      u32                             tid;
+        * };
+        */
+       PERF_RECORD_ITRACE_START                = 12,
+
        PERF_RECORD_MAX,                        /* non-ABI */
 };
 

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 31f6b504ad624a395e38dcf2ba6e770060504d9a..06917d537302b6de0dca1254d5ef6dabb9c6228d 100644 (file)
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1831,6 +1831,7 @@ static void perf_set_shadow_time(struct perf_event *event,
 #define MAX_INTERRUPTS (~0ULL)
 
 static void perf_log_throttle(struct perf_event *event, int enable);
+static void perf_log_itrace_start(struct perf_event *event);
 
 static int
 event_sched_in(struct perf_event *event,
@@ -1869,6 +1870,8 @@ event_sched_in(struct perf_event *event,
 
        perf_set_shadow_time(event, ctx, tstamp);
 
+       perf_log_itrace_start(event);
+
        if (event->pmu->add(event, PERF_EF_START)) {
                event->state = PERF_EVENT_STATE_INACTIVE;
                event->oncpu = -1;
@@ -5991,6 +5994,44 @@ static void perf_log_throttle(struct perf_event *event, int enable)
        perf_output_end(&handle);
 }
 
+static void perf_log_itrace_start(struct perf_event *event)
+{
+       struct perf_output_handle handle;
+       struct perf_sample_data sample;
+       struct perf_aux_event {
+               struct perf_event_header        header;
+               u32                             pid;
+               u32                             tid;
+       } rec;
+       int ret;
+
+       if (event->parent)
+               event = event->parent;
+
+       if (!(event->pmu->capabilities & PERF_PMU_CAP_ITRACE) ||
+           event->hw.itrace_started)
+               return;
+
+       event->hw.itrace_started = 1;
+
+       rec.header.type = PERF_RECORD_ITRACE_START;
+       rec.header.misc = 0;
+       rec.header.size = sizeof(rec);
+       rec.pid = perf_event_pid(event, current);
+       rec.tid = perf_event_tid(event, current);
+
+       perf_event_header__init_id(&rec.header, &sample, event);
+       ret = perf_output_begin(&handle, event, rec.header.size);
+
+       if (ret)
+               return;
+
+       perf_output_put(&handle, rec);
+       perf_event__output_id_sample(event, &handle, &sample);
+
+       perf_output_end(&handle);
+}
+
 /*
  * Generic event overflow handling, sampling.
  */