Re: [RFC 2/2] perf/core: Invoke pmu::sched_task callback for per-cpu events
From: Liang, Kan
Date: Thu Nov 05 2020 - 14:39:56 EST
On 11/5/2020 10:54 AM, Namhyung Kim wrote:
-void perf_sched_cb_inc(struct pmu *pmu)
+void perf_sched_cb_inc(struct pmu *pmu, bool systemwide)
{
struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
- if (!cpuctx->sched_cb_usage++)
- list_add(&cpuctx->sched_cb_entry, this_cpu_ptr(&sched_cb_list));
+ cpuctx->sched_cb_usage++;
- this_cpu_inc(perf_sched_cb_usages);
+ if (systemwide) {
+ this_cpu_inc(perf_sched_cb_usages);
+ list_add(&cpuctx->sched_cb_entry, this_cpu_ptr(&sched_cb_list));
You need to check the value and make sure it's added only once.
Right, maybe we have to add a new variable for that.
diff --git a/arch/powerpc/perf/core-book3s.c
b/arch/powerpc/perf/core-book3s.c
index 6586f7e71cfb..63c9b87cab5e 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -380,7 +380,7 @@ static void power_pmu_bhrb_enable(struct perf_event
*event)
cpuhw->bhrb_context = event->ctx;
}
cpuhw->bhrb_users++;
- perf_sched_cb_inc(event->ctx->pmu);
+ perf_sched_cb_inc(event->ctx->pmu, !(event->attach_state &
PERF_ATTACH_TASK));
}
static void power_pmu_bhrb_disable(struct perf_event *event)
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 444e5f061d04..a34b90c7fa6d 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1022,9 +1022,9 @@ pebs_update_state(bool needed_cb, struct
cpu_hw_events *cpuc,
if (needed_cb != pebs_needs_sched_cb(cpuc)) {
if (!needed_cb)
- perf_sched_cb_inc(pmu);
+ perf_sched_cb_inc(pmu, !(event->attach_state & PERF_ATTACH_TASK));
else
- perf_sched_cb_dec(pmu);
+ perf_sched_cb_dec(pmu, !(event->attach_state & PERF_ATTACH_TASK));
update = true;
}
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 8961653c5dd2..8d4d02cde3d4 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -693,7 +693,7 @@ void intel_pmu_lbr_add(struct perf_event *event)
*/
if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0)
cpuc->lbr_pebs_users++;
- perf_sched_cb_inc(event->ctx->pmu);
+ perf_sched_cb_inc(event->ctx->pmu, !(event->attach_state &
PERF_ATTACH_TASK));
if (!cpuc->lbr_users++ && !event->total_time_running)
intel_pmu_lbr_reset();
@@ -740,7 +740,7 @@ void intel_pmu_lbr_del(struct perf_event *event)
cpuc->lbr_users--;
WARN_ON_ONCE(cpuc->lbr_users < 0);
WARN_ON_ONCE(cpuc->lbr_pebs_users < 0);
- perf_sched_cb_dec(event->ctx->pmu);
+ perf_sched_cb_dec(event->ctx->pmu, !(event->attach_state &
PERF_ATTACH_TASK));
}
static inline bool vlbr_exclude_host(void)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index a1b91f2de264..14f936385cc8 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -875,6 +875,7 @@ struct perf_cpu_context {
struct list_head sched_cb_entry;
int sched_cb_usage;
+ int sched_cb_sw_usage;
int online;
/*
@@ -967,8 +968,8 @@ extern const struct perf_event_attr
*perf_event_attrs(struct perf_event *event);
extern void perf_event_print_debug(void);
extern void perf_pmu_disable(struct pmu *pmu);
extern void perf_pmu_enable(struct pmu *pmu);
-extern void perf_sched_cb_dec(struct pmu *pmu);
-extern void perf_sched_cb_inc(struct pmu *pmu);
+extern void perf_sched_cb_dec(struct pmu *pmu, bool systemwide);
+extern void perf_sched_cb_inc(struct pmu *pmu, bool systemwide);
extern int perf_event_task_disable(void);
extern int perf_event_task_enable(void);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 66a9bd71f3da..af75859c9138 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3484,22 +3484,32 @@ static void perf_event_context_sched_out(struct
task_struct *task, int ctxn,
static DEFINE_PER_CPU(struct list_head, sched_cb_list);
-void perf_sched_cb_dec(struct pmu *pmu)
+void perf_sched_cb_dec(struct pmu *pmu, bool systemwide)
{
struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+ --cpuctx->sched_cb_usage;
+
+ if (!systemwide)
+ return;
+
this_cpu_dec(perf_sched_cb_usages);
- if (!--cpuctx->sched_cb_usage)
+ if (!--cpuctx->sched_cb_sw_usage)
list_del(&cpuctx->sched_cb_entry);
}
-void perf_sched_cb_inc(struct pmu *pmu)
+void perf_sched_cb_inc(struct pmu *pmu, bool systemwide)
{
struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
- if (!cpuctx->sched_cb_usage++)
+ cpuctx->sched_cb_usage++;
+
+ if (!systemwide)
+ return;
+
+ if (!cpuctx->sched_cb_sw_usage++)
list_add(&cpuctx->sched_cb_entry, this_cpu_ptr(&sched_cb_list));
this_cpu_inc(perf_sched_cb_usages);
Thanks,
Kan