perf record: Support synthesizing cgroup events

Synthesize cgroup events by iterating cgroup filesystem directories.
The cgroup event only saves the portion of cgroup path after the mount
point and the cgroup id (which actually is a file handle).

Signed-off-by: Namhyung Kim <[email protected]>
Tested-by: Arnaldo Carvalho de Melo <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
Link: http://lore.kernel.org/lkml/[email protected]
[ Extracted the HAVE_FILE_HANDLE from the followup patch, added missing __maybe_unused ]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>

Author: namhyung

tools/perf/builtin-record.c

@@ -1397,6 +1397,11 @@ static int record__synthesize(struct record *rec, bool tail)
 	if (err < 0)
 		pr_warning("Couldn't synthesize bpf events.\n");
 
+	err = perf_event__synthesize_cgroups(tool, process_synthesized_event,
+					     machine);
+	if (err < 0)
+		pr_warning("Couldn't synthesize cgroup events.\n");
+
 	err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->core.threads,
 					    process_synthesized_event, opts->sample_address,
 					    1);

tools/perf/util/synthetic-events.c

@@ -16,6 +16,7 @@
 #include "util/synthetic-events.h"
 #include "util/target.h"
 #include "util/time-utils.h"
+#include "util/cgroup.h"
 #include <linux/bitops.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
@@ -414,6 +415,127 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 	return rc;
 }
 
+#ifdef HAVE_FILE_HANDLE
+static int perf_event__synthesize_cgroup(struct perf_tool *tool,
+					 union perf_event *event,
+					 char *path, size_t mount_len,
+					 perf_event__handler_t process,
+					 struct machine *machine)
+{
+	size_t event_size = sizeof(event->cgroup) - sizeof(event->cgroup.path);
+	size_t path_len = strlen(path) - mount_len + 1;
+	struct {
+		struct file_handle fh;
+		uint64_t cgroup_id;
+	} handle;
+	int mount_id;
+
+	while (path_len % sizeof(u64))
+		path[mount_len + path_len++] = '\0';
+
+	memset(&event->cgroup, 0, event_size);
+
+	event->cgroup.header.type = PERF_RECORD_CGROUP;
+	event->cgroup.header.size = event_size + path_len + machine->id_hdr_size;
+
+	handle.fh.handle_bytes = sizeof(handle.cgroup_id);
+	if (name_to_handle_at(AT_FDCWD, path, &handle.fh, &mount_id, 0) < 0) {
+		pr_debug("stat failed: %s\n", path);
+		return -1;
+	}
+
+	event->cgroup.id = handle.cgroup_id;
+	strncpy(event->cgroup.path, path + mount_len, path_len);
+	memset(event->cgroup.path + path_len, 0, machine->id_hdr_size);
+
+	if (perf_tool__process_synth_event(tool, event, machine, process) < 0) {
+		pr_debug("process synth event failed\n");
+		return -1;
+	}
+
+	return 0;
+}
+
+static int perf_event__walk_cgroup_tree(struct perf_tool *tool,
+					union perf_event *event,
+					char *path, size_t mount_len,
+					perf_event__handler_t process,
+					struct machine *machine)
+{
+	size_t pos = strlen(path);
+	DIR *d;
+	struct dirent *dent;
+	int ret = 0;
+
+	if (perf_event__synthesize_cgroup(tool, event, path, mount_len,
+					  process, machine) < 0)
+		return -1;
+
+	d = opendir(path);
+	if (d == NULL) {
+		pr_debug("failed to open directory: %s\n", path);
+		return -1;
+	}
+
+	while ((dent = readdir(d)) != NULL) {
+		if (dent->d_type != DT_DIR)
+			continue;
+		if (!strcmp(dent->d_name, ".") ||
+		    !strcmp(dent->d_name, ".."))
+			continue;
+
+		/* any sane path should be less than PATH_MAX */
+		if (strlen(path) + strlen(dent->d_name) + 1 >= PATH_MAX)
+			continue;
+
+		if (path[pos - 1] != '/')
+			strcat(path, "/");
+		strcat(path, dent->d_name);
+
+		ret = perf_event__walk_cgroup_tree(tool, event, path,
+						   mount_len, process, machine);
+		if (ret < 0)
+			break;
+
+		path[pos] = '\0';
+	}
+
+	closedir(d);
+	return ret;
+}
+
+int perf_event__synthesize_cgroups(struct perf_tool *tool,
+				   perf_event__handler_t process,
+				   struct machine *machine)
+{
+	union perf_event event;
+	char cgrp_root[PATH_MAX];
+	size_t mount_len;  /* length of mount point in the path */
+
+	if (cgroupfs_find_mountpoint(cgrp_root, PATH_MAX, "perf_event") < 0) {
+		pr_debug("cannot find cgroup mount point\n");
+		return -1;
+	}
+
+	mount_len = strlen(cgrp_root);
+	/* make sure the path starts with a slash (after mount point) */
+	strcat(cgrp_root, "/");
+
+	if (perf_event__walk_cgroup_tree(tool, &event, cgrp_root, mount_len,
+					 process, machine) < 0)
+		return -1;
+
+	return 0;
+}
+#else
+int perf_event__synthesize_cgroups(struct perf_tool *tool __maybe_unused,
+				   perf_event__handler_t process __maybe_unused,
+				   struct machine *machine __maybe_unused)
+{
+	return -1;
+}
+#endif
+
 int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t process,
 				   struct machine *machine)
 {

tools/perf/util/synthetic-events.h

@@ -45,6 +45,7 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, perf_event__handl
 int perf_event__synthesize_mmap_events(struct perf_tool *tool, union perf_event *event, pid_t pid, pid_t tgid, perf_event__handler_t process, struct machine *machine, bool mmap_data);
 int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine);
 int perf_event__synthesize_namespaces(struct perf_tool *tool, union perf_event *event, pid_t pid, pid_t tgid, perf_event__handler_t process, struct machine *machine);
+int perf_event__synthesize_cgroups(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine);
 int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_format, const struct perf_sample *sample);
 int perf_event__synthesize_stat_config(struct perf_tool *tool, struct perf_stat_config *config, perf_event__handler_t process, struct machine *machine);
 int perf_event__synthesize_stat_events(struct perf_stat_config *config, struct perf_tool *tool, struct evlist *evlist, perf_event__handler_t process, bool attrs);

tools/perf/util/tool.h

@@ -79,6 +79,7 @@ struct perf_tool {
 	bool		ordered_events;
 	bool		ordering_requires_timestamps;
 	bool		namespace_events;
+	bool		cgroup_events;
 	bool		no_warn;
 	enum show_feature_header show_feat_hdr;
 };