perf pmu: Use file system cache to optimize sysfs access

pmu.c does a lot of redundant /sys accesses while parsing aliases
and probing for PMUs. On large systems with a lot of PMUs this
can get expensive (>2s):

% time seconds usecs/call calls errors syscall
------ ----------- ----------- --------- --------- ----------------
27.25 1.227847 8 160888 16976 openat
26.42 1.190481 7 164224 164077 stat

Add a cache to remember if specific file names exist or don't
exist, which eliminates most of this overhead.

Also optimize some stat() calls to be slightly cheaper access()

Resulting in:

0.18 0.004166 2 1851 305 open
0.08 0.001970 2 829 622 access

Signed-off-by: Andi Kleen <[e-mail]>
Acked-by: Jiri Olsa <[e-mail]>
Link: http://lore.kernel.org/lkml/[e-mail]
Signed-off-by: Arnaldo Carvalho de Melo <[e-mail]>

tools/perf/util/Build

···
 perf-y += callchain.o
 perf-y += values.o
 perf-y += debug.o
+perf-y += fncache.o
 perf-y += machine.o
 perf-y += map.o
 perf-y += pstack.o

tools/perf/util/fncache.c

···
+// SPDX-License-Identifier: GPL-2.0-only
+/* Manage a cache of file names' existence */
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include <linux/list.h>
+#include "fncache.h"
+
+struct fncache {
+	struct hlist_node nd;
+	bool res;
+	char name[];
+};
+
+#define FNHSIZE 61
+
+static struct hlist_head fncache_hash[FNHSIZE];
+
+unsigned shash(const unsigned char *s)
+{
+	unsigned h = 0;
+	while (*s)
+		h = 65599 * h + *s++;
+	return h ^ (h >> 16);
+}
+
+static bool lookup_fncache(const char *name, bool *res)
+{
+	int h = shash((const unsigned char *)name) % FNHSIZE;
+	struct fncache *n;
+
+	hlist_for_each_entry(n, &fncache_hash[h], nd) {
+		if (!strcmp(n->name, name)) {
+			*res = n->res;
+			return true;
+		}
+	}
+	return false;
+}
+
+static void update_fncache(const char *name, bool res)
+{
+	struct fncache *n = malloc(sizeof(struct fncache) + strlen(name) + 1);
+	int h = shash((const unsigned char *)name) % FNHSIZE;
+
+	if (!n)
+		return;
+	strcpy(n->name, name);
+	n->res = res;
+	hlist_add_head(&n->nd, &fncache_hash[h]);
+}
+
+/* No LRU, only use when bounded in some other way. */
+bool file_available(const char *name)
+{
+	bool res;
+
+	if (lookup_fncache(name, &res))
+		return res;
+	res = access(name, R_OK) == 0;
+	update_fncache(name, res);
+	return res;
+}

tools/perf/util/fncache.h

···
+#ifndef _FCACHE_H
+#define _FCACHE_H 1
+
+unsigned shash(const unsigned char *s);
+bool file_available(const char *name);
+
+#endif

tools/perf/util/pmu.c

···
 #include "pmu-events/pmu-events.h"
 #include "string2.h"
 #include "strbuf.h"
+#include "fncache.h"
 
 struct perf_pmu_format {
 	char *name;
···
  */
 static int pmu_format(const char *name, struct list_head *format)
 {
-	struct stat st;
 	char path[PATH_MAX];
 	const char *sysfs = sysfs__mountpoint();
 
···
 	snprintf(path, PATH_MAX,
 		 "%s" EVENT_SOURCE_DEVICE_PATH "%s/format", sysfs, name);
 
-	if (stat(path, &st) < 0)
-		return 0;	/* no error if format does not exist */
+	if (!file_available(path))
+		return 0;
 
 	if (perf_pmu__format_parse(path, format))
 		return -1;
···
  */
 static int pmu_aliases(const char *name, struct list_head *head)
 {
-	struct stat st;
 	char path[PATH_MAX];
 	const char *sysfs = sysfs__mountpoint();
 
···
 	snprintf(path, PATH_MAX,
 		 "%s/bus/event_source/devices/%s/events", sysfs, name);
 
-	if (stat(path, &st) < 0)
-		return 0;	 /* no error if 'events' does not exist */
+	if (!file_available(path))
+		return 0;
 
 	if (pmu_aliases_parse(path, head))
 		return -1;
···
  */
 static int pmu_type(const char *name, __u32 *type)
 {
-	struct stat st;
 	char path[PATH_MAX];
 	FILE *file;
 	int ret = 0;
···
 	snprintf(path, PATH_MAX,
 		 "%s" EVENT_SOURCE_DEVICE_PATH "%s/type", sysfs, name);
 
-	if (stat(path, &st) < 0)
+	if (access(path, R_OK) < 0)
 		return -1;
 
 	file = fopen(path, "r");
···
 static bool pmu_is_uncore(const char *name)
 {
 	char path[PATH_MAX];
-	struct perf_cpu_map *cpus;
-	const char *sysfs = sysfs__mountpoint();
+	const char *sysfs;
 
+	sysfs = sysfs__mountpoint();
 	snprintf(path, PATH_MAX, CPUS_TEMPLATE_UNCORE, sysfs, name);
-	cpus = __pmu_cpumask(path);
-	perf_cpu_map__put(cpus);
-
-	return !!cpus;
+	return file_available(path);
 }
 
 /*
···
  */
 static int is_arm_pmu_core(const char *name)
 {
-	struct stat st;
 	char path[PATH_MAX];
 	const char *sysfs = sysfs__mountpoint();
 
···
 	/* Look for cpu sysfs (specific to arm) */
 	scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s/cpus",
 				sysfs, name);
-	if (stat(path, &st) == 0)
-		return 1;
-
-	return 0;
+	return file_available(path);
 }
 
 static char *perf_pmu__getcpuid(struct perf_pmu *pmu)
···
 
 static FILE *perf_pmu__open_file(struct perf_pmu *pmu, const char *name)
 {
-	struct stat st;
 	char path[PATH_MAX];
 	const char *sysfs;
 
···
 
 	snprintf(path, PATH_MAX,
 		 "%s" EVENT_SOURCE_DEVICE_PATH "%s/%s", sysfs, pmu->name, name);
-
-	if (stat(path, &st) < 0)
+	if (!file_available(path))
 		return NULL;
-
 	return fopen(path, "r");
 }
 

tools/perf/util/srccode.c

···
 #include "srccode.h"
 #include "debug.h"
 #include <internal/lib.h> // page_size
+#include "fncache.h"
 
 #define MAXSRCCACHE (32*1024*1024)
 #define MAXSRCFILES     64
···
 static LIST_HEAD(srcfile_list);
 static long map_total_sz;
 static int num_srcfiles;
-
-static unsigned shash(unsigned char *s)
-{
-	unsigned h = 0;
-	while (*s)
-		h = 65599 * h + *s++;
-	return h ^ (h >> 16);
-}
 
 static int countlines(char *map, int maplen)
 {