1 files changed, 93 insertions, 12 deletions

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index a3e28b49128a..3cebc9a8d52e 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -25,6 +25,9 @@
 #include <linux/bitops.h>
 #include <linux/hash.h>
 
+static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx);
+static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx);
+
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 #define SID(e, x, y) xyarray__entry(e->sample_id, x, y)
 
@@ -37,6 +40,7 @@ void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
 		INIT_HLIST_HEAD(&evlist->heads[i]);
 	INIT_LIST_HEAD(&evlist->entries);
 	perf_evlist__set_maps(evlist, cpus, threads);
+	fdarray__init(&evlist->pollfd, 64);
 	evlist->workload.pid = -1;
 }
 
@@ -102,7 +106,7 @@ static void perf_evlist__purge(struct perf_evlist *evlist)
 void perf_evlist__exit(struct perf_evlist *evlist)
 {
 	zfree(&evlist->mmap);
-	zfree(&evlist->pollfd);
+	fdarray__exit(&evlist->pollfd);
 }
 
 void perf_evlist__delete(struct perf_evlist *evlist)
@@ -402,7 +406,7 @@ int perf_evlist__enable_event_idx(struct perf_evlist *evlist,
 		return perf_evlist__enable_event_thread(evlist, evsel, idx);
 }
 
-static int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
+int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
 {
 	int nr_cpus = cpu_map__nr(evlist->cpus);
 	int nr_threads = thread_map__nr(evlist->threads);
@@ -416,16 +420,50 @@ static int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
 			nfds += nr_cpus * nr_threads;
 	}
 
-	evlist->pollfd = malloc(sizeof(struct pollfd) * nfds);
-	return evlist->pollfd != NULL ? 0 : -ENOMEM;
+	if (fdarray__available_entries(&evlist->pollfd) < nfds &&
+	    fdarray__grow(&evlist->pollfd, nfds) < 0)
+		return -ENOMEM;
+
+	return 0;
 }
 
-void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd)
+static int __perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd, int idx)
 {
-	fcntl(fd, F_SETFL, O_NONBLOCK);
-	evlist->pollfd[evlist->nr_fds].fd = fd;
-	evlist->pollfd[evlist->nr_fds].events = POLLIN;
-	evlist->nr_fds++;
+	int pos = fdarray__add(&evlist->pollfd, fd, POLLIN | POLLERR | POLLHUP);
+	/*
+	 * Save the idx so that when we filter out fds POLLHUP'ed we can
+	 * close the associated evlist->mmap[] entry.
+	 */
+	if (pos >= 0) {
+		evlist->pollfd.priv[pos].idx = idx;
+
+		fcntl(fd, F_SETFL, O_NONBLOCK);
+	}
+
+	return pos;
+}
+
+int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd)
+{
+	return __perf_evlist__add_pollfd(evlist, fd, -1);
+}
+
+static void perf_evlist__munmap_filtered(struct fdarray *fda, int fd)
+{
+	struct perf_evlist *evlist = container_of(fda, struct perf_evlist, pollfd);
+
+	perf_evlist__mmap_put(evlist, fda->priv[fd].idx);
+}
+
+int perf_evlist__filter_pollfd(struct perf_evlist *evlist, short revents_and_mask)
+{
+	return fdarray__filter(&evlist->pollfd, revents_and_mask,
+			       perf_evlist__munmap_filtered);
+}
+
+int perf_evlist__poll(struct perf_evlist *evlist, int timeout)
+{
+	return fdarray__poll(&evlist->pollfd, timeout);
 }
 
 static void perf_evlist__id_hash(struct perf_evlist *evlist,
@@ -638,14 +676,36 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 	return event;
 }
 
+static bool perf_mmap__empty(struct perf_mmap *md)
+{
+	return perf_mmap__read_head(md) != md->prev;
+}
+
+static void perf_evlist__mmap_get(struct perf_evlist *evlist, int idx)
+{
+	++evlist->mmap[idx].refcnt;
+}
+
+static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx)
+{
+	BUG_ON(evlist->mmap[idx].refcnt == 0);
+
+	if (--evlist->mmap[idx].refcnt == 0)
+		__perf_evlist__munmap(evlist, idx);
+}
+
 void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
 {
+	struct perf_mmap *md = &evlist->mmap[idx];
+
 	if (!evlist->overwrite) {
-		struct perf_mmap *md = &evlist->mmap[idx];
 		unsigned int old = md->prev;
 
 		perf_mmap__write_tail(md, old);
 	}
+
+	if (md->refcnt == 1 && perf_mmap__empty(md))
+		perf_evlist__mmap_put(evlist, idx);
 }
 
 static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
@@ -653,6 +713,7 @@ static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
 	if (evlist->mmap[idx].base != NULL) {
 		munmap(evlist->mmap[idx].base, evlist->mmap_len);
 		evlist->mmap[idx].base = NULL;
+		evlist->mmap[idx].refcnt = 0;
 	}
 }
 
@@ -686,6 +747,20 @@ struct mmap_params {
 static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
 			       struct mmap_params *mp, int fd)
 {
+	/*
+	 * The last one will be done at perf_evlist__mmap_consume(), so that we
+	 * make sure we don't prevent tools from consuming every last event in
+	 * the ring buffer.
+	 *
+	 * I.e. we can get the POLLHUP meaning that the fd doesn't exist
+	 * anymore, but the last events for it are still in the ring buffer,
+	 * waiting to be consumed.
+	 *
+	 * Tools can chose to ignore this at their own discretion, but the
+	 * evlist layer can't just drop it when filtering events in
+	 * perf_evlist__filter_pollfd().
+	 */
+	evlist->mmap[idx].refcnt = 2;
 	evlist->mmap[idx].prev = 0;
 	evlist->mmap[idx].mask = mp->mask;
 	evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, mp->prot,
@@ -697,7 +772,6 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
 		return -1;
 	}
 
-	perf_evlist__add_pollfd(evlist, fd);
 	return 0;
 }
 
@@ -722,6 +796,13 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 		} else {
 			if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0)
 				return -1;
+
+			perf_evlist__mmap_get(evlist, idx);
+		}
+
+		if (__perf_evlist__add_pollfd(evlist, fd, idx) < 0) {
+			perf_evlist__mmap_put(evlist, idx);
+			return -1;
 		}
 
 		if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
@@ -881,7 +962,7 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
 	if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0)
 		return -ENOMEM;
 
-	if (evlist->pollfd == NULL && perf_evlist__alloc_pollfd(evlist) < 0)
+	if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) < 0)
 		return -ENOMEM;
 
 	evlist->overwrite = overwrite;