lkml.org 
[lkml]   [2014]   [Jul]   [22]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH v3 7/9] perf, x86: drain PEBS buffer during context switch
Date
Flush the PEBS buffer during context switch 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>
---
arch/x86/kernel/cpu/perf_event.h | 3 +++
arch/x86/kernel/cpu/perf_event_intel.c | 11 +++++++++-
arch/x86/kernel/cpu/perf_event_intel_ds.c | 32 ++++++++++++++++++++++++++++--
arch/x86/kernel/cpu/perf_event_intel_lbr.c | 2 --
4 files changed, 43 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index fa8dfd4..c4a746c 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -148,6 +148,7 @@ struct cpu_hw_events {
*/
struct debug_store *ds;
u64 pebs_enabled;
+ bool pebs_sched_cb_enabled;

/*
* Intel LBR bits
@@ -683,6 +684,8 @@ 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 ef926ee..cb5a838 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2035,6 +2035,15 @@ 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");
@@ -2086,7 +2095,7 @@ 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 1e3b8cf..99b07de0 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -705,6 +705,18 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)
return &emptyconstraint;
}

+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();
+}
+
/*
* Flags PEBS can handle without an PMI.
*
@@ -745,13 +757,20 @@ void intel_pmu_pebs_enable(struct perf_event *event)
* When the event is constrained enough we can use a larger
* threshold and run the event with less frequent PMI.
*/
- if (0 && /* disable this temporarily */
- (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) &&
+ if ((hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) &&
!(event->attr.sample_type & ~PEBS_FREERUNNING_FLAGS)) {
threshold = ds->pebs_absolute_maximum -
x86_pmu.max_pebs_events * x86_pmu.pebs_record_size;
+ if (first_pebs) {
+ perf_sched_cb_user_inc(event->ctx->pmu);
+ cpuc->pebs_sched_cb_enabled = true;
+ }
} else {
threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size;
+ if (cpuc->pebs_sched_cb_enabled) {
+ perf_sched_cb_user_dec(event->ctx->pmu);
+ cpuc->pebs_sched_cb_enabled = false;
+ }
}
if (first_pebs || ds->pebs_interrupt_threshold > threshold)
ds->pebs_interrupt_threshold = threshold;
@@ -767,8 +786,17 @@ void intel_pmu_pebs_disable(struct perf_event *event)
{
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
struct hw_perf_event *hwc = &event->hw;
+ struct debug_store *ds = cpuc->ds;
+
+ if (ds->pebs_interrupt_threshold >
+ ds->pebs_buffer_base + x86_pmu.pebs_record_size)
+ intel_pmu_drain_pebs_buffer();

cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
+ if (cpuc->pebs_sched_cb_enabled && !pebs_is_enabled(cpuc)) {
+ perf_sched_cb_user_dec(event->ctx->pmu);
+ cpuc->pebs_sched_cb_enabled = false;
+ }

if (event->hw.constraint->flags & PERF_X86_EVENT_PEBS_LDLAT)
cpuc->pebs_enabled &= ~(1ULL << (hwc->idx + 32));
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index a30bfab..e4f3a09 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -185,8 +185,6 @@ void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
{
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);

- if (!x86_pmu.lbr_nr)
- return;
/*
* When sampling the branck stack in system-wide, it may be
* necessary to flush the stack on context switch. This happens
--
1.9.3


\
 
 \ /
  Last update: 2014-07-22 11:02    [W:0.357 / U:0.212 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site