perf/core: Pull pmu::sched_task() into perf_event_context_sched_out()

The pmu::sched_task() is a context switch callback. It passes the
cpuctx->task_ctx as a parameter to the lower code. To find the
cpuctx->task_ctx, the current code iterates a cpuctx list.
The same context will iterated in perf_event_context_sched_out() soon.
Share the cpuctx->task_ctx can avoid the unnecessary iteration of the
cpuctx list.

The pmu::sched_task() is also required for the optimization case for
equivalent contexts.

The task_ctx_sched_out() will eventually disable and reenable the PMU
when schedule out events. Add perf_pmu_disable() and perf_pmu_enable()
around task_ctx_sched_out() don't break anything.

Drop the cpuctx->ctx.lock for the pmu::sched_task(). The lock is for
per-CPU context, which is not necessary for the per-task context
schedule.

No one uses sched_cb_entry, perf_sched_cb_usages, sched_cb_list, and
perf_pmu_sched_task() any more.
Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200821195754.20159-2-kan.liang@linux.intel.com

include/linux/perf_event.h

@@ -872,7 +872,6 @@ 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

@@ -382,7 +382,6 @@ 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;
@@ -3384,10 +3383,12 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
 	struct perf_event_context *parent, *next_parent;
 	struct perf_cpu_context *cpuctx;
 	int do_switch = 1;
+	struct pmu *pmu;
 
 	if (likely(!ctx))
 		return;
 
+	pmu = ctx->pmu;
 	cpuctx = __get_cpu_context(ctx);
 	if (!cpuctx->task_ctx)
 		return;
@@ -3417,11 +3418,15 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
 		raw_spin_lock(&ctx->lock);
 		raw_spin_lock_nested(&next_ctx->lock, SINGLE_DEPTH_NESTING);
 		if (context_equiv(ctx, next_ctx)) {
-			struct pmu *pmu = ctx->pmu;
 
 			WRITE_ONCE(ctx->task, next);
 			WRITE_ONCE(next_ctx->task, task);
 
+			perf_pmu_disable(pmu);
+
+			if (cpuctx->sched_cb_usage && pmu->sched_task)
+				pmu->sched_task(ctx, false);
+
 			/*
 			 * PMU specific parts of task perf context can require
 			 * additional synchronization. As an example of such
@@ -3433,6 +3438,8 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
 			else
 				swap(ctx->task_ctx_data, next_ctx->task_ctx_data);
 
+			perf_pmu_enable(pmu);
+
 			/*
 			 * RCU_INIT_POINTER here is safe because we've not
 			 * modified the ctx and the above modification of
@@ -3455,21 +3462,22 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
 
 	if (do_switch) {
 		raw_spin_lock(&ctx->lock);
+		perf_pmu_disable(pmu);
+
+		if (cpuctx->sched_cb_usage && pmu->sched_task)
+			pmu->sched_task(ctx, false);
 		task_ctx_sched_out(cpuctx, ctx, EVENT_ALL);
+
+		perf_pmu_enable(pmu);
 		raw_spin_unlock(&ctx->lock);
 	}
 }
 
-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);
 
-	this_cpu_dec(perf_sched_cb_usages);
-
-	if (!--cpuctx->sched_cb_usage)
-		list_del(&cpuctx->sched_cb_entry);
+	--cpuctx->sched_cb_usage;
 }
 
 
@@ -3477,10 +3485,7 @@ void perf_sched_cb_inc(struct pmu *pmu)
 {
 	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));
-
-	this_cpu_inc(perf_sched_cb_usages);
+	cpuctx->sched_cb_usage++;
 }
 
 /*
@@ -3509,20 +3514,6 @@ 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)
-		__perf_pmu_sched_task(cpuctx, sched_in);
-
-}
-
 static void perf_event_switch(struct task_struct *task,
 			      struct task_struct *next_prev, bool sched_in);
 
@@ -3545,9 +3536,6 @@ 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);
 
@@ -12867,7 +12855,6 @@ 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));
 	}
 }