Commit 6562c9ac authored by Adrian Hunter's avatar Adrian Hunter Committed by Arnaldo Carvalho de Melo
Browse files

perf record: Fix way of handling non-perf-event pollfds 



perf record __cmd_record() does not poll evlist pollfds. Instead it polls
thread_data[0].pollfd. That happens whether or not threads are being used.

perf record duplicates evlist mmap pollfds as needed for separate threads.
The non-perf-event represented by evlist->ctl_fd has to handled separately,
which is done explicitly, duplicating it into the thread_data[0] pollfds.
That approach neglects any other non-perf-event file descriptors. Currently
there is also done_fd which needs the same handling.

Add a new generalized approach.

Add fdarray_flag__non_perf_event to identify the file descriptors that
need the special handling. For those cases, also keep a mapping of the
evlist pollfd index and thread pollfd index, so that the evlist revents
can be updated.

Although this patch adds the new handling, it does not take it into use.
There is no functional change, but it is the precursor to a fix, so is
marked as a fix.

Fixes: 415ccb58 ("perf record: Introduce thread specific data array")
Signed-off-by: default avatarAdrian Hunter <adrian.hunter@intel.com>
Acked-by: default avatarIan Rogers <irogers@google.com>
Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20220824072814.16422-2-adrian.hunter@intel.com


Signed-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
parent bdf45725

tools/lib/api/fd/array.h

+3 −2
Original line number Diff line number Diff line
@@ -32,7 +32,8 @@ struct fdarray { 


enum fdarray_flags {

	fdarray_flag__default		= 0x00000000,

	fdarray_flag__nonfilterable = 0x00000001

	fdarray_flag__nonfilterable	= 0x00000001,

	fdarray_flag__non_perf_event	= 0x00000002,

};



void fdarray__init(struct fdarray *fda, int nr_autogrow);

tools/perf/builtin-record.c

+80 −0
Original line number Diff line number Diff line
@@ -143,6 +143,11 @@ static const char *thread_spec_tags[THREAD_SPEC__MAX] = { 
	"undefined", "cpu", "core", "package", "numa", "user"

};



struct pollfd_index_map {

	int evlist_pollfd_index;

	int thread_pollfd_index;

};



struct record {

	struct perf_tool	tool;

	struct record_opts	opts;
@@ -171,6 +176,9 @@ struct record { 
	int			nr_threads;

	struct thread_mask	*thread_masks;

	struct record_thread	*thread_data;

	struct pollfd_index_map	*index_map;

	size_t			index_map_sz;

	size_t			index_map_cnt;

};



static volatile int done;
@@ -1074,6 +1082,70 @@ static void record__free_thread_data(struct record *rec) 
	zfree(&rec->thread_data);

}



static int record__map_thread_evlist_pollfd_indexes(struct record *rec,

						    int evlist_pollfd_index,

						    int thread_pollfd_index)

{

	size_t x = rec->index_map_cnt;



	if (realloc_array_as_needed(rec->index_map, rec->index_map_sz, x, NULL))

		return -ENOMEM;

	rec->index_map[x].evlist_pollfd_index = evlist_pollfd_index;

	rec->index_map[x].thread_pollfd_index = thread_pollfd_index;

	rec->index_map_cnt += 1;

	return 0;

}



static int record__update_evlist_pollfd_from_thread(struct record *rec,

						    struct evlist *evlist,

						    struct record_thread *thread_data)

{

	struct pollfd *e_entries = evlist->core.pollfd.entries;

	struct pollfd *t_entries = thread_data->pollfd.entries;

	int err = 0;

	size_t i;



	for (i = 0; i < rec->index_map_cnt; i++) {

		int e_pos = rec->index_map[i].evlist_pollfd_index;

		int t_pos = rec->index_map[i].thread_pollfd_index;



		if (e_entries[e_pos].fd != t_entries[t_pos].fd ||

		    e_entries[e_pos].events != t_entries[t_pos].events) {

			pr_err("Thread and evlist pollfd index mismatch\n");

			err = -EINVAL;

			continue;

		}

		e_entries[e_pos].revents = t_entries[t_pos].revents;

	}

	return err;

}



static int record__dup_non_perf_events(struct record *rec,

				       struct evlist *evlist,

				       struct record_thread *thread_data)

{

	struct fdarray *fda = &evlist->core.pollfd;

	int i, ret;



	for (i = 0; i < fda->nr; i++) {

		if (!(fda->priv[i].flags & fdarray_flag__non_perf_event))

			continue;

		ret = fdarray__dup_entry_from(&thread_data->pollfd, i, fda);

		if (ret < 0) {

			pr_err("Failed to duplicate descriptor in main thread pollfd\n");

			return ret;

		}

		pr_debug2("thread_data[%p]: pollfd[%d] <- non_perf_event fd=%d\n",

			  thread_data, ret, fda->entries[i].fd);

		ret = record__map_thread_evlist_pollfd_indexes(rec, i, ret);

		if (ret < 0) {

			pr_err("Failed to map thread and evlist pollfd indexes\n");

			return ret;

		}

	}

	return 0;

}



static int record__alloc_thread_data(struct record *rec, struct evlist *evlist)

{

	int t, ret;
@@ -1121,6 +1193,11 @@ static int record__alloc_thread_data(struct record *rec, struct evlist *evlist) 
				 thread_data[t].pipes.msg[0]);

		} else {

			thread_data[t].tid = gettid();



			ret = record__dup_non_perf_events(rec, evlist, &thread_data[t]);

			if (ret < 0)

				goto out_free;



			if (evlist->ctl_fd.pos == -1)

				continue;

			ret = fdarray__dup_entry_from(&thread_data[t].pollfd, evlist->ctl_fd.pos,
@@ -2534,6 +2611,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) 
					    record__thread_munmap_filtered, NULL) == 0)

				draining = true;



			err = record__update_evlist_pollfd_from_thread(rec, rec->evlist, thread);

			if (err)

				goto out_child;

			evlist__ctlfd_update(rec->evlist,

				&thread->pollfd.entries[thread->ctlfd_pos]);

		}