perf/x86/intel: Drain the PEBS buffer during context switches

Flush the PEBS buffer during context switches if PEBS interrupt threshold
is larger than one. This allows perf to supply TID for sample outputs.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
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/1430940834-8964-6-git-send-email-kan.liang@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

4 files changed, 47 insertions, 5 deletions

diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index a73dfc97226b..74089bcb6d74 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -92,9 +92,11 @@ struct amd_nb {
 /*
  * Flags PEBS can handle without an PMI.
  *
+ * TID can only be handled by flushing at context switch.
+ *
  */
 #define PEBS_FREERUNNING_FLAGS \
-        (PERF_SAMPLE_IP | PERF_SAMPLE_ADDR | \
+        (PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \
         PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \
         PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \
         PERF_SAMPLE_TRANSACTION)
@@ -877,6 +879,8 @@ void intel_pmu_pebs_enable_all(void);
 
 void intel_pmu_pebs_disable_all(void);
 
+void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in);
+
 void intel_ds_init(void);
 
 void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in);
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 6985f43c5eb9..d455e2a61287 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2642,6 +2642,15 @@ static void intel_pmu_cpu_dying(int cpu)
         fini_debug_store_on_cpu(cpu);
 }
 
+static void intel_pmu_sched_task(struct perf_event_context *ctx,
+                                 bool sched_in)
+{
+        if (x86_pmu.pebs_active)
+                intel_pmu_pebs_sched_task(ctx, sched_in);
+        if (x86_pmu.lbr_nr)
+                intel_pmu_lbr_sched_task(ctx, sched_in);
+}
+
 PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");
 
 PMU_FORMAT_ATTR(ldlat, "config1:0-15");
@@ -2731,7 +2740,7 @@ static __initconst const struct x86_pmu intel_pmu = {
         .cpu_starting           = intel_pmu_cpu_starting,
         .cpu_dying              = intel_pmu_cpu_dying,
         .guest_get_msrs         = intel_guest_get_msrs,
-        .sched_task             = intel_pmu_lbr_sched_task,
+        .sched_task             = intel_pmu_sched_task,
 };
 
 static __init void intel_clovertown_quirk(void)
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 0ce455d958b8..62852470ccbb 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -546,6 +546,19 @@ int intel_pmu_drain_bts_buffer(void)
         return 1;
 }
 
+static inline void intel_pmu_drain_pebs_buffer(void)
+{
+        struct pt_regs regs;
+
+        x86_pmu.drain_pebs(&regs);
+}
+
+void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in)
+{
+        if (!sched_in)
+                intel_pmu_drain_pebs_buffer();
+}
+
 /*
  * PEBS
  */
@@ -711,8 +724,19 @@ void intel_pmu_pebs_enable(struct perf_event *event)
         if (hwc->flags & PERF_X86_EVENT_FREERUNNING) {
                 threshold = ds->pebs_absolute_maximum -
                         x86_pmu.max_pebs_events * x86_pmu.pebs_record_size;
+
+                if (first_pebs)
+                        perf_sched_cb_inc(event->ctx->pmu);
         } else {
                 threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size;
+
+                /*
+                 * If not all events can use larger buffer,
+                 * roll back to threshold = 1
+                 */
+                if (!first_pebs &&
+                    (ds->pebs_interrupt_threshold > threshold))
+                        perf_sched_cb_dec(event->ctx->pmu);
         }
 
         /* Use auto-reload if possible to save a MSR write in the PMI */
@@ -729,6 +753,7 @@ void intel_pmu_pebs_disable(struct perf_event *event)
 {
         struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
         struct hw_perf_event *hwc = &event->hw;
+        struct debug_store *ds = cpuc->ds;
 
         cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
 
@@ -737,6 +762,13 @@ void intel_pmu_pebs_disable(struct perf_event *event)
         else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
                 cpuc->pebs_enabled &= ~(1ULL << 63);
 
+        if (ds->pebs_interrupt_threshold >
+            ds->pebs_buffer_base + x86_pmu.pebs_record_size) {
+                intel_pmu_drain_pebs_buffer();
+                if (!pebs_is_enabled(cpuc))
+                        perf_sched_cb_dec(event->ctx->pmu);
+        }
+
         if (cpuc->enabled)
                 wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 201e16f6655a..452a7bd2dedb 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -264,9 +264,6 @@ void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
         struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
         struct x86_perf_task_context *task_ctx;
 
-        if (!x86_pmu.lbr_nr)
-                return;
-
         /*
          * If LBR callstack feature is enabled and the stack was saved when
          * the task was scheduled out, restore the stack. Otherwise flush