[PATCH v8 2/5] perf: Track per-PMU sched_task() callback users

[Rob Herring]

From: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>

Current perf only tracks the per-CPU sched_task() callback users, which
doesn't work if a callback user is a task. For example, the dirty
counters have to be cleared to prevent data leakage when a new userspace
access task is scheduled in. The task may be created on one CPU but
running on another CPU. It cannot be tracked by the per-CPU variable. A
global variable is not going to work either because of the hybrid PMUs.
Add a per-PMU variable to track the callback users.

Suggested-by: Rob Herring <robh@xxxxxxxxxx>
Signed-off-by: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>
[robh: Also call sched_task() got sched out cases]
Signed-off-by: Rob Herring <robh@xxxxxxxxxx>
---
 include/linux/perf_event.h | 3 +++
 kernel/events/core.c       | 8 +++++---
 2 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 4cf081e22b76..a88d52e80864 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -300,6 +300,9 @@ struct pmu {
 	/* number of address filters this PMU can do */
 	unsigned int			nr_addr_filters;
 
+	/* Track the per PMU sched_task() callback users */
+	atomic_t			sched_cb_usage;
+
 	/*
 	 * Fully disable/enable this PMU, can be used to protect from the PMI
 	 * as well as for lazy/batch writing of the MSRs.
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 2e947a485898..6d0507c23240 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3448,7 +3448,8 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
 
 			perf_pmu_disable(pmu);
 
-			if (cpuctx->sched_cb_usage && pmu->sched_task)
+			if (pmu->sched_task &&
+			    (cpuctx->sched_cb_usage || atomic_read(&pmu->sched_cb_usage)))
 				pmu->sched_task(ctx, false);
 
 			/*
@@ -3488,7 +3489,8 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
 		raw_spin_lock(&ctx->lock);
 		perf_pmu_disable(pmu);
 
-		if (cpuctx->sched_cb_usage && pmu->sched_task)
+		if (pmu->sched_task &&
+		    (cpuctx->sched_cb_usage || atomic_read(&pmu->sched_cb_usage)))
 			pmu->sched_task(ctx, false);
 		task_ctx_sched_out(cpuctx, ctx, EVENT_ALL);
 
@@ -3851,7 +3853,7 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx,
 		cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
 	perf_event_sched_in(cpuctx, ctx, task);
 
-	if (cpuctx->sched_cb_usage && pmu->sched_task)
+	if (pmu->sched_task && (cpuctx->sched_cb_usage || atomic_read(&pmu->sched_cb_usage)))
 		pmu->sched_task(cpuctx->task_ctx, true);
 
 	perf_pmu_enable(pmu);
-- 
2.27.0