perf/core: Flush PMU internal buffers for per-CPU events

Sometimes the PMU internal buffers have to be flushed for per-CPU events
during a context switch, e.g., large PEBS. Otherwise, the perf tool may
report samples in locations that do not belong to the process where the
samples are processed in, because PEBS does not tag samples with PID/TID.

The current code only flush the buffers for a per-task event. It doesn't
check a per-CPU event.

Add a new event state flag, PERF_ATTACH_SCHED_CB, to indicate that the
PMU internal buffers have to be flushed for this event during a context
switch.

Add sched_cb_entry and perf_sched_cb_usages back to track the PMU/cpuctx
which is required to be flushed.

Only need to invoke the sched_task() for per-CPU events in this patch.
The per-task events have been handled in perf_event_context_sched_in/out
already.

Fixes: 9c964ef ("perf/x86/intel: Drain the PEBS buffer during context switches")
Reported-by: Gabriel Marin <[email protected]>
Originally-by: Namhyung Kim <[email protected]>
Signed-off-by: Kan Liang <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]

Author: Kan Liang

include/linux/perf_event.h

@@ -606,6 +606,7 @@ struct swevent_hlist {
 #define PERF_ATTACH_TASK	0x04
 #define PERF_ATTACH_TASK_DATA	0x08
 #define PERF_ATTACH_ITRACE	0x10
+#define PERF_ATTACH_SCHED_CB	0x20
 
 struct perf_cgroup;
 struct perf_buffer;
@@ -872,6 +873,7 @@ struct perf_cpu_context {
 	struct list_head		cgrp_cpuctx_entry;
 #endif
 
+	struct list_head		sched_cb_entry;
 	int				sched_cb_usage;
 
 	int				online;

kernel/events/core.c

@@ -386,6 +386,7 @@ static DEFINE_MUTEX(perf_sched_mutex);
 static atomic_t perf_sched_count;
 
 static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
+static DEFINE_PER_CPU(int, perf_sched_cb_usages);
 static DEFINE_PER_CPU(struct pmu_event_list, pmu_sb_events);
 
 static atomic_t nr_mmap_events __read_mostly;
@@ -3461,19 +3462,27 @@ 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)
 {
 	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
 
-	--cpuctx->sched_cb_usage;
+	this_cpu_dec(perf_sched_cb_usages);
+
+	if (!--cpuctx->sched_cb_usage)
+		list_del(&cpuctx->sched_cb_entry);
 }
 
 
 void perf_sched_cb_inc(struct pmu *pmu)
 {
 	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
 
-	cpuctx->sched_cb_usage++;
+	if (!cpuctx->sched_cb_usage++)
+		list_add(&cpuctx->sched_cb_entry, this_cpu_ptr(&sched_cb_list));
+
+	this_cpu_inc(perf_sched_cb_usages);
 }
 
 /*
@@ -3502,6 +3511,24 @@ static void __perf_pmu_sched_task(struct perf_cpu_context *cpuctx, bool sched_in
 	perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
 }
 
+static void perf_pmu_sched_task(struct task_struct *prev,
+				struct task_struct *next,
+				bool sched_in)
+{
+	struct perf_cpu_context *cpuctx;
+
+	if (prev == next)
+		return;
+
+	list_for_each_entry(cpuctx, this_cpu_ptr(&sched_cb_list), sched_cb_entry) {
+		/* will be handled in perf_event_context_sched_in/out */
+		if (cpuctx->task_ctx)
+			continue;
+
+		__perf_pmu_sched_task(cpuctx, sched_in);
+	}
+}
+
 static void perf_event_switch(struct task_struct *task,
 			      struct task_struct *next_prev, bool sched_in);
 
@@ -3524,6 +3551,9 @@ void __perf_event_task_sched_out(struct task_struct *task,
 {
 	int ctxn;
 
+	if (__this_cpu_read(perf_sched_cb_usages))
+		perf_pmu_sched_task(task, next, false);
+
 	if (atomic_read(&nr_switch_events))
 		perf_event_switch(task, next, false);
 
@@ -3832,6 +3862,9 @@ void __perf_event_task_sched_in(struct task_struct *prev,
 
 	if (atomic_read(&nr_switch_events))
 		perf_event_switch(task, prev, true);
+
+	if (__this_cpu_read(perf_sched_cb_usages))
+		perf_pmu_sched_task(prev, task, true);
 }
 
 static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
@@ -4656,7 +4689,7 @@ static void unaccount_event(struct perf_event *event)
 	if (event->parent)
 		return;
 
-	if (event->attach_state & PERF_ATTACH_TASK)
+	if (event->attach_state & (PERF_ATTACH_TASK | PERF_ATTACH_SCHED_CB))
 		dec = true;
 	if (event->attr.mmap || event->attr.mmap_data)
 		atomic_dec(&nr_mmap_events);
@@ -11175,7 +11208,7 @@ static void account_event(struct perf_event *event)
 	if (event->parent)
 		return;
 
-	if (event->attach_state & PERF_ATTACH_TASK)
+	if (event->attach_state & (PERF_ATTACH_TASK | PERF_ATTACH_SCHED_CB))
 		inc = true;
 	if (event->attr.mmap || event->attr.mmap_data)
 		atomic_inc(&nr_mmap_events);
@@ -12972,6 +13005,7 @@ static void __init perf_event_init_all_cpus(void)
 #ifdef CONFIG_CGROUP_PERF
 		INIT_LIST_HEAD(&per_cpu(cgrp_cpuctx_list, cpu));
 #endif
+		INIT_LIST_HEAD(&per_cpu(sched_cb_list, cpu));
 	}
 }