perf/core: Optimize perf_init_event()

Andi reported that he was hitting the linear search in
perf_init_event() a lot. Make more agressive use of the IDR lookup to
avoid hitting the linear search.

With exception of PERF_TYPE_SOFTWARE (which relies on a hideous hack),
we can put everything in the IDR. On top of that, we can alias
TYPE_HARDWARE and TYPE_HW_CACHE to TYPE_RAW on the lookup side.

This greatly reduces the chances of hitting the linear search.

Reported-by: Andi Kleen <andi@firstfloor.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kan <kan.liang@linux.intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 30 insertions, 11 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index ea70ca614987..4d67c5d35c13 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -10080,7 +10080,7 @@ static struct lock_class_key cpuctx_lock;
 
 int perf_pmu_register(struct pmu *pmu, const char *name, int type)
 {
-	int cpu, ret;
+	int cpu, ret, max = PERF_TYPE_MAX;
 
 	mutex_lock(&pmus_lock);
 	ret = -ENOMEM;
@@ -10093,12 +10093,17 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type)
 		goto skip_type;
 	pmu->name = name;
 
-	if (type < 0) {
-		type = idr_alloc(&pmu_idr, pmu, PERF_TYPE_MAX, 0, GFP_KERNEL);
-		if (type < 0) {
-			ret = type;
+	if (type != PERF_TYPE_SOFTWARE) {
+		if (type >= 0)
+			max = type;
+
+		ret = idr_alloc(&pmu_idr, pmu, max, 0, GFP_KERNEL);
+		if (ret < 0)
 			goto free_pdc;
-		}
+
+		WARN_ON(type >= 0 && ret != type);
+
+		type = ret;
 	}
 	pmu->type = type;
 
@@ -10188,7 +10193,7 @@ free_dev:
 	put_device(pmu->dev);
 
 free_idr:
-	if (pmu->type >= PERF_TYPE_MAX)
+	if (pmu->type != PERF_TYPE_SOFTWARE)
 		idr_remove(&pmu_idr, pmu->type);
 
 free_pdc:
@@ -10210,7 +10215,7 @@ void perf_pmu_unregister(struct pmu *pmu)
 	synchronize_rcu();
 
 	free_percpu(pmu->pmu_disable_count);
-	if (pmu->type >= PERF_TYPE_MAX)
+	if (pmu->type != PERF_TYPE_SOFTWARE)
 		idr_remove(&pmu_idr, pmu->type);
 	if (pmu_bus_running) {
 		if (pmu->nr_addr_filters)
@@ -10280,9 +10285,8 @@ static int perf_try_init_event(struct pmu *pmu, struct perf_event *event)
 
 static struct pmu *perf_init_event(struct perf_event *event)
 {
+	int idx, type, ret;
 	struct pmu *pmu;
-	int idx;
-	int ret;
 
 	idx = srcu_read_lock(&pmus_srcu);
 
@@ -10295,12 +10299,27 @@ static struct pmu *perf_init_event(struct perf_event *event)
 	}
 
 	rcu_read_lock();
-	pmu = idr_find(&pmu_idr, event->attr.type);
+	/*
+	 * PERF_TYPE_HARDWARE and PERF_TYPE_HW_CACHE
+	 * are often aliases for PERF_TYPE_RAW.
+	 */
+	type = event->attr.type;
+	if (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_HW_CACHE)
+		type = PERF_TYPE_RAW;
+
+again:
+	pmu = idr_find(&pmu_idr, type);
 	rcu_read_unlock();
 	if (pmu) {
 		ret = perf_try_init_event(pmu, event);
+		if (ret == -ENOENT && event->attr.type != type) {
+			type = event->attr.type;
+			goto again;
+		}
+
 		if (ret)
 			pmu = ERR_PTR(ret);
+
 		goto unlock;
 	}