perf tools: Use /proc/<PID>/task/<TID>/status for PERF_RECORD_ event synthesis

To save memory usage, it needs to reduce the number of entries in the
proc filesystem.  It's using /proc/<PID>/task directory to traverse
threads in the process and then kernel creates /proc/<PID>/task/<TID>
entries.

After that it checks the thread info using the /proc/<TID>/status file
rather than /proc/<PID>/task/<TID>/status.  As far as I can see, they
are the same and contain all the info we need.

Using the latter eliminates the unnecessary /proc/<TID> entry.  This can
be useful especially a large number of threads are used in the system.
In my experiment around 1KB of memory on average was saved for each
thread (which is not a thread group leader).

To do this, pass both pid and tid to perf_event_prepare_comm() if it
knows them.  In case it doesn't know, passing 0 as pid will do the old
way.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20210202090118.2008551-2-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index 3a89852..0cc9986 100644 (file)
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -69,7 +69,7 @@ int perf_tool__process_synth_event(struct perf_tool *tool,
  * Assumes that the first 4095 bytes of /proc/pid/stat contains
  * the comm, tgid and ppid.
  */
-static int perf_event__get_comm_ids(pid_t pid, char *comm, size_t len,
+static int perf_event__get_comm_ids(pid_t pid, pid_t tid, char *comm, size_t len,
                                    pid_t *tgid, pid_t *ppid)
 {
        char bf[4096];
@@ -81,7 +81,10 @@ static int perf_event__get_comm_ids(pid_t pid, char *comm, size_t len,
        *tgid = -1;
        *ppid = -1;
 
-       snprintf(bf, sizeof(bf), "/proc/%d/status", pid);
+       if (pid)
+               snprintf(bf, sizeof(bf), "/proc/%d/task/%d/status", pid, tid);
+       else
+               snprintf(bf, sizeof(bf), "/proc/%d/status", tid);
 
        fd = open(bf, O_RDONLY);
        if (fd < 0) {
@@ -93,7 +96,7 @@ static int perf_event__get_comm_ids(pid_t pid, char *comm, size_t len,
        close(fd);
        if (n <= 0) {
                pr_warning("Couldn't get COMM, tigd and ppid for pid %d\n",
-                          pid);
+                          tid);
                return -1;
        }
        bf[n] = '\0';
@@ -116,27 +119,27 @@ static int perf_event__get_comm_ids(pid_t pid, char *comm, size_t len,
                memcpy(comm, name, size);
                comm[size] = '\0';
        } else {
-               pr_debug("Name: string not found for pid %d\n", pid);
+               pr_debug("Name: string not found for pid %d\n", tid);
        }
 
        if (tgids) {
                tgids += 5;  /* strlen("Tgid:") */
                *tgid = atoi(tgids);
        } else {
-               pr_debug("Tgid: string not found for pid %d\n", pid);
+               pr_debug("Tgid: string not found for pid %d\n", tid);
        }
 
        if (ppids) {
                ppids += 5;  /* strlen("PPid:") */
                *ppid = atoi(ppids);
        } else {
-               pr_debug("PPid: string not found for pid %d\n", pid);
+               pr_debug("PPid: string not found for pid %d\n", tid);
        }
 
        return 0;
 }
 
-static int perf_event__prepare_comm(union perf_event *event, pid_t pid,
+static int perf_event__prepare_comm(union perf_event *event, pid_t pid, pid_t tid,
                                    struct machine *machine,
                                    pid_t *tgid, pid_t *ppid)
 {
@@ -147,7 +150,7 @@ static int perf_event__prepare_comm(union perf_event *event, pid_t pid,
        memset(&event->comm, 0, sizeof(event->comm));
 
        if (machine__is_host(machine)) {
-               if (perf_event__get_comm_ids(pid, event->comm.comm,
+               if (perf_event__get_comm_ids(pid, tid, event->comm.comm,
                                             sizeof(event->comm.comm),
                                             tgid, ppid) != 0) {
                        return -1;
@@ -168,7 +171,7 @@ static int perf_event__prepare_comm(union perf_event *event, pid_t pid,
        event->comm.header.size = (sizeof(event->comm) -
                                (sizeof(event->comm.comm) - size) +
                                machine->id_hdr_size);
-       event->comm.tid = pid;
+       event->comm.tid = tid;
 
        return 0;
 }
@@ -180,7 +183,7 @@ pid_t perf_event__synthesize_comm(struct perf_tool *tool,
 {
        pid_t tgid, ppid;
 
-       if (perf_event__prepare_comm(event, pid, machine, &tgid, &ppid) != 0)
+       if (perf_event__prepare_comm(event, 0, pid, machine, &tgid, &ppid) != 0)
                return -1;
 
        if (perf_tool__process_synth_event(tool, event, machine, process) != 0)
@@ -746,7 +749,7 @@ static int __event__synthesize_thread(union perf_event *comm_event,
                        continue;
 
                rc = -1;
-               if (perf_event__prepare_comm(comm_event, _pid, machine,
+               if (perf_event__prepare_comm(comm_event, pid, _pid, machine,
                                             &tgid, &ppid) != 0)
                        break;