[PATCH v5 3/5] perf tools: fall back to eventfs for unprivileged event discovery

[Anubhav Shelat <ashelat@redhat.com>]

When tracefs events are not readable by unprivileged users, fall back
to /sys/kernel/events (the read-only eventfs mount) for tracepoint
format and id file discovery. This allows perf trace to work for
unprivileged users on kernels that expose the eventfs filesystem.

The fallback is transparent: get_events_file() tries the tracefs path
first and only switches to eventfs when access() fails. On kernels
without eventfs, the existing error path is preserved.

Assisted-by: CLAUDE:claude-opus-4 Apogee
Signed-off-by: Anubhav Shelat <ashelat@redhat.com>
---
 tools/lib/api/fs/fs.c              | 10 ++++++
 tools/lib/api/fs/fs.h              |  1 +
 tools/lib/api/fs/tracing_path.c    | 52 ++++++++++++++++++++++++++----
 tools/lib/api/fs/tracing_path.h    |  1 +
 tools/perf/util/tp_pmu.c           |  5 +--
 tools/perf/util/trace-event-info.c | 19 ++++++-----
 6 files changed, 71 insertions(+), 17 deletions(-)

diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c
index cbd8eab0d1df..abc3581a9703 100644
--- a/tools/lib/api/fs/fs.c
+++ b/tools/lib/api/fs/fs.c
@@ -46,6 +46,10 @@
 #define BPF_FS_MAGIC           0xcafe4a11
 #endif
 
+#ifndef EVENTFS_SUPER_MAGIC
+#define EVENTFS_SUPER_MAGIC    0x65766673
+#endif
+
 static const char * const sysfs__known_mountpoints[] = {
 	"/sys",
 	0,
@@ -88,6 +92,11 @@ static const char * const bpf_fs__known_mountpoints[] = {
 	0,
 };
 
+static const char * const eventfs__known_mountpoints[] = {
+	"/sys/kernel/events",
+	0,
+};
+
 struct fs {
 	const char *		 const name;
 	const char * const *	 const mounts;
@@ -150,6 +159,7 @@ FS(debugfs, debugfs, DEBUGFS);
 FS(tracefs, tracefs, TRACEFS);
 FS(hugetlbfs, hugetlbfs, HUGETLBFS);
 FS(bpf_fs, bpf, BPF_FS);
+FS(eventfs, eventfs, EVENTFS_SUPER);
 
 static bool fs__read_mounts(struct fs *fs)
 {
diff --git a/tools/lib/api/fs/fs.h b/tools/lib/api/fs/fs.h
index aa222ca30311..57790c93f80e 100644
--- a/tools/lib/api/fs/fs.h
+++ b/tools/lib/api/fs/fs.h
@@ -36,6 +36,7 @@ FS(debugfs)
 FS(tracefs)
 FS(hugetlbfs)
 FS(bpf_fs)
+FS(eventfs)
 
 #undef FS
 
diff --git a/tools/lib/api/fs/tracing_path.c b/tools/lib/api/fs/tracing_path.c
index 834fd64c7130..de4ed7c61415 100644
--- a/tools/lib/api/fs/tracing_path.c
+++ b/tools/lib/api/fs/tracing_path.c
@@ -3,6 +3,8 @@
 # define _GNU_SOURCE
 #endif
 
+#include <dirent.h>
+#include <fcntl.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -80,13 +82,46 @@ void put_tracing_file(char *file)
 	free(file);
 }
 
+char *get_events_dir(void)
+{
+	const char *eventfs;
+	char *path;
+	int saved_errno;
+
+	path = get_tracing_file("events");
+	if (path && faccessat(AT_FDCWD, path, R_OK, AT_EACCESS) == 0)
+		return path;
+
+	saved_errno = errno;
+	put_tracing_file(path);
+
+	eventfs = eventfs__mount();
+	if (eventfs && faccessat(AT_FDCWD, eventfs, R_OK, AT_EACCESS) == 0 &&
+	    eventfs__configured())
+		return strdup(eventfs);
+
+	/*
+	 * Prefer EACCES over other errors: it tells the user that events
+	 * exist but are not accessible, which is more actionable than
+	 * ENOENT from a missing filesystem.
+	 */
+	if (errno != EACCES)
+		errno = saved_errno;
+	return NULL;
+}
+
 char *get_events_file(const char *name)
 {
-	char *file;
+	char *dir, *file;
 
-	if (asprintf(&file, "%s/events/%s", tracing_path_mount(), name) < 0)
+	dir = get_events_dir();
+	if (!dir)
 		return NULL;
 
+	if (asprintf(&file, "%s/%s", dir, name) < 0)
+		file = NULL;
+
+	free(dir);
 	return file;
 }
 
@@ -97,8 +132,8 @@ void put_events_file(char *file)
 
 DIR *tracing_events__opendir(void)
 {
+	char *path = get_events_dir();
 	DIR *dir = NULL;
-	char *path = get_tracing_file("events");
 
 	if (path) {
 		dir = opendir(path);
@@ -110,7 +145,7 @@ DIR *tracing_events__opendir(void)
 
 int tracing_events__scandir_alphasort(struct dirent ***namelist)
 {
-	char *path = get_tracing_file("events");
+	char *path = get_events_dir();
 	int ret;
 
 	if (!path) {
@@ -121,6 +156,9 @@ int tracing_events__scandir_alphasort(struct dirent ***namelist)
 	ret = scandir(path, namelist, NULL, alphasort);
 	put_events_file(path);
 
+	if (ret < 0)
+		*namelist = NULL;
+
 	return ret;
 }
 
@@ -162,12 +200,12 @@ int tracing_path__strerror_open_tp(int err, char *buf, size_t size,
 			 "Hint:\tIs the debugfs/tracefs filesystem mounted?\n"
 			 "Hint:\tTry 'sudo mount -t debugfs nodev /sys/kernel/debug'");
 		break;
-	case EACCES: {
+	case EACCES:
 		snprintf(buf, size,
 			 "Error:\tNo permissions to read %s/events/%s\n"
-			 "Hint:\tTry 'sudo mount -o remount,mode=755 %s'\n",
+			 "Hint:\tTry 'sudo mount -o remount,mode=755 %s'\n"
+			 "Hint:\tOr check if /sys/kernel/events is available\n",
 			 tracing_path, filename, tracing_path_mount());
-	}
 		break;
 	default:
 		snprintf(buf, size, "%s", str_error_r(err, sbuf, sizeof(sbuf)));
diff --git a/tools/lib/api/fs/tracing_path.h b/tools/lib/api/fs/tracing_path.h
index fc6347c11deb..a93befb38f80 100644
--- a/tools/lib/api/fs/tracing_path.h
+++ b/tools/lib/api/fs/tracing_path.h
@@ -14,6 +14,7 @@ const char *tracing_path_mount(void);
 char *get_tracing_file(const char *name);
 void put_tracing_file(char *file);
 
+char *get_events_dir(void);
 char *get_events_file(const char *name);
 void put_events_file(char *file);
 
diff --git a/tools/perf/util/tp_pmu.c b/tools/perf/util/tp_pmu.c
index c2be8c9f9084..4f45bd816945 100644
--- a/tools/perf/util/tp_pmu.c
+++ b/tools/perf/util/tp_pmu.c
@@ -6,6 +6,7 @@
 #include <api/io_dir.h>
 #include <linux/kernel.h>
 #include <errno.h>
+#include <stdlib.h>
 #include <string.h>
 
 int tp_pmu__id(const char *sys, const char *name)
@@ -15,7 +16,7 @@ int tp_pmu__id(const char *sys, const char *name)
 	int id, err;
 
 	if (!tp_dir)
-		return -1;
+		return -errno;
 
 	scnprintf(path, PATH_MAX, "%s/%s/id", tp_dir, name);
 	put_events_file(tp_dir);
@@ -66,7 +67,7 @@ int tp_pmu__for_each_tp_sys(void *state, tp_sys_callback cb)
 	struct io_dirent64 *events_ent;
 	struct io_dir events_dir;
 	int ret = 0;
-	char *events_dir_path = get_tracing_file("events");
+	char *events_dir_path = get_events_dir();
 
 	if (!events_dir_path)
 		return -errno;
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index 45774722f249..643451d2c08d 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -92,8 +92,9 @@ static int record_header_files(void)
 	int err = -EIO;
 
 	if (!path) {
+		err = -errno;
 		pr_debug("can't get tracing/events/header_page");
-		return -ENOMEM;
+		return err;
 	}
 
 	if (stat(path, &st) < 0) {
@@ -115,8 +116,8 @@ static int record_header_files(void)
 
 	path = get_events_file("header_event");
 	if (!path) {
+		err = -errno;
 		pr_debug("can't get tracing/events/header_event");
-		err = -ENOMEM;
 		goto out;
 	}
 
@@ -228,13 +229,14 @@ static int record_ftrace_files(struct tracepoint_path *tps)
 
 	path = get_events_file("ftrace");
 	if (!path) {
+		ret = -errno;
 		pr_debug("can't get tracing/events/ftrace");
-		return -ENOMEM;
+		return ret;
 	}
 
 	ret = copy_event_system(path, tps);
 
-	put_tracing_file(path);
+	put_events_file(path);
 
 	return ret;
 }
@@ -256,15 +258,16 @@ static int record_event_files(struct tracepoint_path *tps)
 	struct stat st;
 	char *path;
 	char *sys;
-	DIR *dir;
+	DIR *dir = NULL;
 	int count = 0;
 	int ret;
 	int err;
 
-	path = get_tracing_file("events");
+	path = get_events_dir();
 	if (!path) {
+		err = -errno;
 		pr_debug("can't get tracing/events");
-		return -ENOMEM;
+		goto out;
 	}
 
 	dir = opendir(path);
@@ -315,7 +318,7 @@ static int record_event_files(struct tracepoint_path *tps)
 out:
 	if (dir)
 		closedir(dir);
-	put_tracing_file(path);
+	put_events_file(path);
 
 	return err;
 }
-- 
2.54.0