perf/x86/intel: Introduce PERF_RECORD_LOST_SAMPLES

After enlarging the PEBS interrupt threshold, there may be some mixed up
PEBS samples which are discarded by the kernel.

This patch makes the kernel emit a PERF_RECORD_LOST_SAMPLES record with
the number of possible discarded records when it is impossible to demux
the samples.

It makes sure the user is not left in the dark about such discards.

Signed-off-by: Kan Liang <kan.liang@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: acme@infradead.org
Cc: eranian@google.com
Link: http://lkml.kernel.org/r/1431285195-14269-8-git-send-email-kan.liang@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

4 files changed, 65 insertions, 3 deletions

diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 266079a3a646..34d0c4816141 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -1126,6 +1126,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
         void *base, *at, *top;
         int bit;
         short counts[MAX_PEBS_EVENTS] = {};
+        short error[MAX_PEBS_EVENTS] = {};
 
         if (!x86_pmu.pebs_active)
                 return;
@@ -1169,20 +1170,33 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
                         /* slow path */
                         pebs_status = p->status & cpuc->pebs_enabled;
                         pebs_status &= (1ULL << MAX_PEBS_EVENTS) - 1;
-                        if (pebs_status != (1 << bit))
+                        if (pebs_status != (1 << bit)) {
+                                u8 i;
+
+                                for_each_set_bit(i, (unsigned long *)&pebs_status,
+                                                 MAX_PEBS_EVENTS)
+                                        error[i]++;
                                 continue;
+                        }
                 }
                 counts[bit]++;
         }
 
         for (bit = 0; bit < x86_pmu.max_pebs_events; bit++) {
-                if (counts[bit] == 0)
+                if ((counts[bit] == 0) && (error[bit] == 0))
                         continue;
                 event = cpuc->events[bit];
                 WARN_ON_ONCE(!event);
                 WARN_ON_ONCE(!event->attr.precise_ip);
 
-                __intel_pmu_pebs_event(event, iregs, base, top, bit, counts[bit]);
+                /* log dropped samples number */
+                if (error[bit])
+                        perf_log_lost_samples(event, error[bit]);
+
+                if (counts[bit]) {
+                        __intel_pmu_pebs_event(event, iregs, base,
+                                               top, bit, counts[bit]);
+                }
         }
 }
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 5f192e1bc98e..a204d5266f5f 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -743,6 +743,9 @@ perf_event__output_id_sample(struct perf_event *event,
                              struct perf_output_handle *handle,
                              struct perf_sample_data *sample);
 
+extern void
+perf_log_lost_samples(struct perf_event *event, u64 lost);
+
 static inline bool is_sampling_event(struct perf_event *event)
 {
         return event->attr.sample_period != 0;
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index c4622f1ce046..613ed9ad588f 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -802,6 +802,18 @@ enum perf_event_type {
          */
         PERF_RECORD_ITRACE_START                = 12,
 
+        /*
+         * Records the dropped/lost sample number.
+         *
+         * struct {
+         *      struct perf_event_header        header;
+         *
+         *      u64                             lost;
+         *      struct sample_id                sample_id;
+         * };
+         */
+        PERF_RECORD_LOST_SAMPLES                = 13,
+
         PERF_RECORD_MAX,                        /* non-ABI */
 };
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e499b4e43aff..9e0773d5d110 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5975,6 +5975,39 @@ void perf_event_aux_event(struct perf_event *event, unsigned long head,
 }
 
 /*
+ * Lost/dropped samples logging
+ */
+void perf_log_lost_samples(struct perf_event *event, u64 lost)
+{
+        struct perf_output_handle handle;
+        struct perf_sample_data sample;
+        int ret;
+
+        struct {
+                struct perf_event_header        header;
+                u64                             lost;
+        } lost_samples_event = {
+                .header = {
+                        .type = PERF_RECORD_LOST_SAMPLES,
+                        .misc = 0,
+                        .size = sizeof(lost_samples_event),
+                },
+                .lost           = lost,
+        };
+
+        perf_event_header__init_id(&lost_samples_event.header, &sample, event);
+
+        ret = perf_output_begin(&handle, event,
+                                lost_samples_event.header.size);
+        if (ret)
+                return;
+
+        perf_output_put(&handle, lost_samples_event);
+        perf_event__output_id_sample(event, &handle, &sample);
+        perf_output_end(&handle);
+}
+
+/*
  * IRQ throttle logging
  */