1 files changed, 192 insertions, 77 deletions

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 862e69c2690d..2a40b8e1def7 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -15,6 +15,7 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "debug.h"
+#include "asm/bug.h"
 #include <unistd.h>
 
 #include "parse-events.h"
@@ -27,8 +28,8 @@
 #include <linux/log2.h>
 #include <linux/err.h>
 
-static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx);
-static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx);
+static void perf_mmap__munmap(struct perf_mmap *map);
+static void perf_mmap__put(struct perf_mmap *map);
 
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 #define SID(e, x, y) xyarray__entry(e->sample_id, x, y)
@@ -44,7 +45,7 @@ void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
 	perf_evlist__set_maps(evlist, cpus, threads);
 	fdarray__init(&evlist->pollfd, 64);
 	evlist->workload.pid = -1;
-	evlist->backward = false;
+	evlist->bkw_mmap_state = BKW_MMAP_NOTREADY;
 }
 
 struct perf_evlist *perf_evlist__new(void)
@@ -122,6 +123,7 @@ static void perf_evlist__purge(struct perf_evlist *evlist)
 void perf_evlist__exit(struct perf_evlist *evlist)
 {
 	zfree(&evlist->mmap);
+	zfree(&evlist->backward_mmap);
 	fdarray__exit(&evlist->pollfd);
 }
 
@@ -465,7 +467,8 @@ int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
 	return 0;
 }
 
-static int __perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd, int idx, short revent)
+static int __perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd,
+				     struct perf_mmap *map, short revent)
 {
 	int pos = fdarray__add(&evlist->pollfd, fd, revent | POLLERR | POLLHUP);
 	/*
@@ -473,7 +476,7 @@ static int __perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd, int idx
 	 * close the associated evlist->mmap[] entry.
 	 */
 	if (pos >= 0) {
-		evlist->pollfd.priv[pos].idx = idx;
+		evlist->pollfd.priv[pos].ptr = map;
 
 		fcntl(fd, F_SETFL, O_NONBLOCK);
 	}
@@ -483,15 +486,16 @@ static int __perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd, int idx
 
 int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd)
 {
-	return __perf_evlist__add_pollfd(evlist, fd, -1, POLLIN);
+	return __perf_evlist__add_pollfd(evlist, fd, NULL, POLLIN);
 }
 
 static void perf_evlist__munmap_filtered(struct fdarray *fda, int fd,
 					 void *arg __maybe_unused)
 {
-	struct perf_evlist *evlist = container_of(fda, struct perf_evlist, pollfd);
+	struct perf_mmap *map = fda->priv[fd].ptr;
 
-	perf_evlist__mmap_put(evlist, fda->priv[fd].idx);
+	if (map)
+		perf_mmap__put(map);
 }
 
 int perf_evlist__filter_pollfd(struct perf_evlist *evlist, short revents_and_mask)
@@ -688,8 +692,11 @@ static int perf_evlist__set_paused(struct perf_evlist *evlist, bool value)
 {
 	int i;
 
+	if (!evlist->backward_mmap)
+		return 0;
+
 	for (i = 0; i < evlist->nr_mmaps; i++) {
-		int fd = evlist->mmap[i].fd;
+		int fd = evlist->backward_mmap[i].fd;
 		int err;
 
 		if (fd < 0)
@@ -701,12 +708,12 @@ static int perf_evlist__set_paused(struct perf_evlist *evlist, bool value)
 	return 0;
 }
 
-int perf_evlist__pause(struct perf_evlist *evlist)
+static int perf_evlist__pause(struct perf_evlist *evlist)
 {
 	return perf_evlist__set_paused(evlist, true);
 }
 
-int perf_evlist__resume(struct perf_evlist *evlist)
+static int perf_evlist__resume(struct perf_evlist *evlist)
 {
 	return perf_evlist__set_paused(evlist, false);
 }
@@ -781,9 +788,8 @@ broken_event:
 	return event;
 }
 
-union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist, int idx)
+union perf_event *perf_mmap__read_forward(struct perf_mmap *md, bool check_messup)
 {
-	struct perf_mmap *md = &evlist->mmap[idx];
 	u64 head;
 	u64 old = md->prev;
 
@@ -795,13 +801,12 @@ union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist, int
 
 	head = perf_mmap__read_head(md);
 
-	return perf_mmap__read(md, evlist->overwrite, old, head, &md->prev);
+	return perf_mmap__read(md, check_messup, old, head, &md->prev);
 }
 
 union perf_event *
-perf_evlist__mmap_read_backward(struct perf_evlist *evlist, int idx)
+perf_mmap__read_backward(struct perf_mmap *md)
 {
-	struct perf_mmap *md = &evlist->mmap[idx];
 	u64 head, end;
 	u64 start = md->prev;
 
@@ -836,16 +841,38 @@ perf_evlist__mmap_read_backward(struct perf_evlist *evlist, int idx)
 	return perf_mmap__read(md, false, start, end, &md->prev);
 }
 
-union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
+union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist, int idx)
 {
-	if (!evlist->backward)
-		return perf_evlist__mmap_read_forward(evlist, idx);
-	return perf_evlist__mmap_read_backward(evlist, idx);
+	struct perf_mmap *md = &evlist->mmap[idx];
+
+	/*
+	 * Check messup is required for forward overwritable ring buffer:
+	 * memory pointed by md->prev can be overwritten in this case.
+	 * No need for read-write ring buffer: kernel stop outputting when
+	 * it hit md->prev (perf_mmap__consume()).
+	 */
+	return perf_mmap__read_forward(md, evlist->overwrite);
 }
 
-void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx)
+union perf_event *perf_evlist__mmap_read_backward(struct perf_evlist *evlist, int idx)
 {
 	struct perf_mmap *md = &evlist->mmap[idx];
+
+	/*
+	 * No need to check messup for backward ring buffer:
+	 * We can always read arbitrary long data from a backward
+	 * ring buffer unless we forget to pause it before reading.
+	 */
+	return perf_mmap__read_backward(md);
+}
+
+union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
+{
+	return perf_evlist__mmap_read_forward(evlist, idx);
+}
+
+void perf_mmap__read_catchup(struct perf_mmap *md)
+{
 	u64 head;
 
 	if (!atomic_read(&md->refcnt))
@@ -855,38 +882,44 @@ void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx)
 	md->prev = head;
 }
 
+void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx)
+{
+	perf_mmap__read_catchup(&evlist->mmap[idx]);
+}
+
 static bool perf_mmap__empty(struct perf_mmap *md)
 {
 	return perf_mmap__read_head(md) == md->prev && !md->auxtrace_mmap.base;
 }
 
-static void perf_evlist__mmap_get(struct perf_evlist *evlist, int idx)
+static void perf_mmap__get(struct perf_mmap *map)
 {
-	atomic_inc(&evlist->mmap[idx].refcnt);
+	atomic_inc(&map->refcnt);
 }
 
-static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx)
+static void perf_mmap__put(struct perf_mmap *md)
 {
-	struct perf_mmap *md = &evlist->mmap[idx];
-
 	BUG_ON(md->base && atomic_read(&md->refcnt) == 0);
 
 	if (atomic_dec_and_test(&md->refcnt))
-		__perf_evlist__munmap(evlist, idx);
+		perf_mmap__munmap(md);
 }
 
-void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
+void perf_mmap__consume(struct perf_mmap *md, bool overwrite)
 {
-	struct perf_mmap *md = &evlist->mmap[idx];
-
-	if (!evlist->overwrite) {
+	if (!overwrite) {
 		u64 old = md->prev;
 
 		perf_mmap__write_tail(md, old);
 	}
 
 	if (atomic_read(&md->refcnt) == 1 && perf_mmap__empty(md))
-		perf_evlist__mmap_put(evlist, idx);
+		perf_mmap__put(md);
+}
+
+void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
+{
+	perf_mmap__consume(&evlist->mmap[idx], evlist->overwrite);
 }
 
 int __weak auxtrace_mmap__mmap(struct auxtrace_mmap *mm __maybe_unused,
@@ -917,44 +950,52 @@ void __weak auxtrace_mmap_params__set_idx(
 {
 }
 
-static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
+static void perf_mmap__munmap(struct perf_mmap *map)
 {
-	if (evlist->mmap[idx].base != NULL) {
-		munmap(evlist->mmap[idx].base, evlist->mmap_len);
-		evlist->mmap[idx].base = NULL;
-		evlist->mmap[idx].fd = -1;
-		atomic_set(&evlist->mmap[idx].refcnt, 0);
+	if (map->base != NULL) {
+		munmap(map->base, perf_mmap__mmap_len(map));
+		map->base = NULL;
+		map->fd = -1;
+		atomic_set(&map->refcnt, 0);
 	}
-	auxtrace_mmap__munmap(&evlist->mmap[idx].auxtrace_mmap);
+	auxtrace_mmap__munmap(&map->auxtrace_mmap);
 }
 
-void perf_evlist__munmap(struct perf_evlist *evlist)
+static void perf_evlist__munmap_nofree(struct perf_evlist *evlist)
 {
 	int i;
 
-	if (evlist->mmap == NULL)
-		return;
+	if (evlist->mmap)
+		for (i = 0; i < evlist->nr_mmaps; i++)
+			perf_mmap__munmap(&evlist->mmap[i]);
 
-	for (i = 0; i < evlist->nr_mmaps; i++)
-		__perf_evlist__munmap(evlist, i);
+	if (evlist->backward_mmap)
+		for (i = 0; i < evlist->nr_mmaps; i++)
+			perf_mmap__munmap(&evlist->backward_mmap[i]);
+}
 
+void perf_evlist__munmap(struct perf_evlist *evlist)
+{
+	perf_evlist__munmap_nofree(evlist);
 	zfree(&evlist->mmap);
+	zfree(&evlist->backward_mmap);
 }
 
-static int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
+static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist)
 {
 	int i;
+	struct perf_mmap *map;
 
 	evlist->nr_mmaps = cpu_map__nr(evlist->cpus);
 	if (cpu_map__empty(evlist->cpus))
 		evlist->nr_mmaps = thread_map__nr(evlist->threads);
-	evlist->mmap = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap));
-	if (!evlist->mmap)
-		return -ENOMEM;
+	map = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap));
+	if (!map)
+		return NULL;
 
 	for (i = 0; i < evlist->nr_mmaps; i++)
-		evlist->mmap[i].fd = -1;
-	return 0;
+		map[i].fd = -1;
+	return map;
 }
 
 struct mmap_params {
@@ -963,8 +1004,8 @@ struct mmap_params {
 	struct auxtrace_mmap_params auxtrace_mp;
 };
 
-static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
-			       struct mmap_params *mp, int fd)
+static int perf_mmap__mmap(struct perf_mmap *map,
+			   struct mmap_params *mp, int fd)
 {
 	/*
 	 * The last one will be done at perf_evlist__mmap_consume(), so that we
@@ -979,21 +1020,21 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
 	 * evlist layer can't just drop it when filtering events in
 	 * perf_evlist__filter_pollfd().
 	 */
-	atomic_set(&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,
-				      MAP_SHARED, fd, 0);
-	if (evlist->mmap[idx].base == MAP_FAILED) {
+	atomic_set(&map->refcnt, 2);
+	map->prev = 0;
+	map->mask = mp->mask;
+	map->base = mmap(NULL, perf_mmap__mmap_len(map), mp->prot,
+			 MAP_SHARED, fd, 0);
+	if (map->base == MAP_FAILED) {
 		pr_debug2("failed to mmap perf event ring buffer, error %d\n",
 			  errno);
-		evlist->mmap[idx].base = NULL;
+		map->base = NULL;
 		return -1;
 	}
-	evlist->mmap[idx].fd = fd;
+	map->fd = fd;
 
-	if (auxtrace_mmap__mmap(&evlist->mmap[idx].auxtrace_mmap,
-				&mp->auxtrace_mp, evlist->mmap[idx].base, fd))
+	if (auxtrace_mmap__mmap(&map->auxtrace_mmap,
+				&mp->auxtrace_mp, map->base, fd))
 		return -1;
 
 	return 0;
@@ -1003,23 +1044,36 @@ static bool
 perf_evlist__should_poll(struct perf_evlist *evlist __maybe_unused,
 			 struct perf_evsel *evsel)
 {
-	if (evsel->overwrite)
+	if (evsel->attr.write_backward)
 		return false;
 	return true;
 }
 
 static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 				       struct mmap_params *mp, int cpu,
-				       int thread, int *output)
+				       int thread, int *_output, int *_output_backward)
 {
 	struct perf_evsel *evsel;
 	int revent;
 
 	evlist__for_each_entry(evlist, evsel) {
+		struct perf_mmap *maps = evlist->mmap;
+		int *output = _output;
 		int fd;
 
-		if (evsel->overwrite != (evlist->overwrite && evlist->backward))
-			continue;
+		if (evsel->attr.write_backward) {
+			output = _output_backward;
+			maps = evlist->backward_mmap;
+
+			if (!maps) {
+				maps = perf_evlist__alloc_mmap(evlist);
+				if (!maps)
+					return -1;
+				evlist->backward_mmap = maps;
+				if (evlist->bkw_mmap_state == BKW_MMAP_NOTREADY)
+					perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING);
+			}
+		}
 
 		if (evsel->system_wide && thread)
 			continue;
@@ -1028,13 +1082,14 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 
 		if (*output == -1) {
 			*output = fd;
-			if (__perf_evlist__mmap(evlist, idx, mp, *output) < 0)
+
+			if (perf_mmap__mmap(&maps[idx], mp, *output)  < 0)
 				return -1;
 		} else {
 			if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0)
 				return -1;
 
-			perf_evlist__mmap_get(evlist, idx);
+			perf_mmap__get(&maps[idx]);
 		}
 
 		revent = perf_evlist__should_poll(evlist, evsel) ? POLLIN : 0;
@@ -1047,8 +1102,8 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 		 * Therefore don't add it for polling.
 		 */
 		if (!evsel->system_wide &&
-		    __perf_evlist__add_pollfd(evlist, fd, idx, revent) < 0) {
-			perf_evlist__mmap_put(evlist, idx);
+		    __perf_evlist__add_pollfd(evlist, fd, &maps[idx], revent) < 0) {
+			perf_mmap__put(&maps[idx]);
 			return -1;
 		}
 
@@ -1074,13 +1129,14 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist,
 	pr_debug2("perf event ring buffer mmapped per cpu\n");
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		int output = -1;
+		int output_backward = -1;
 
 		auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, cpu,
 					      true);
 
 		for (thread = 0; thread < nr_threads; thread++) {
 			if (perf_evlist__mmap_per_evsel(evlist, cpu, mp, cpu,
-							thread, &output))
+							thread, &output, &output_backward))
 				goto out_unmap;
 		}
 	}
@@ -1088,8 +1144,7 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist,
 	return 0;
 
 out_unmap:
-	for (cpu = 0; cpu < nr_cpus; cpu++)
-		__perf_evlist__munmap(evlist, cpu);
+	perf_evlist__munmap_nofree(evlist);
 	return -1;
 }
 
@@ -1102,20 +1157,20 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist,
 	pr_debug2("perf event ring buffer mmapped per thread\n");
 	for (thread = 0; thread < nr_threads; thread++) {
 		int output = -1;
+		int output_backward = -1;
 
 		auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, thread,
 					      false);
 
 		if (perf_evlist__mmap_per_evsel(evlist, thread, mp, 0, thread,
-						&output))
+						&output, &output_backward))
 			goto out_unmap;
 	}
 
 	return 0;
 
 out_unmap:
-	for (thread = 0; thread < nr_threads; thread++)
-		__perf_evlist__munmap(evlist, thread);
+	perf_evlist__munmap_nofree(evlist);
 	return -1;
 }
 
@@ -1248,7 +1303,9 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
 		.prot = PROT_READ | (overwrite ? 0 : PROT_WRITE),
 	};
 
-	if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0)
+	if (!evlist->mmap)
+		evlist->mmap = perf_evlist__alloc_mmap(evlist);
+	if (!evlist->mmap)
 		return -ENOMEM;
 
 	if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) < 0)
@@ -1919,3 +1976,61 @@ perf_evlist__find_evsel_by_str(struct perf_evlist *evlist,
 
 	return NULL;
 }
+
+void perf_evlist__toggle_bkw_mmap(struct perf_evlist *evlist,
+				  enum bkw_mmap_state state)
+{
+	enum bkw_mmap_state old_state = evlist->bkw_mmap_state;
+	enum action {
+		NONE,
+		PAUSE,
+		RESUME,
+	} action = NONE;
+
+	if (!evlist->backward_mmap)
+		return;
+
+	switch (old_state) {
+	case BKW_MMAP_NOTREADY: {
+		if (state != BKW_MMAP_RUNNING)
+			goto state_err;;
+		break;
+	}
+	case BKW_MMAP_RUNNING: {
+		if (state != BKW_MMAP_DATA_PENDING)
+			goto state_err;
+		action = PAUSE;
+		break;
+	}
+	case BKW_MMAP_DATA_PENDING: {
+		if (state != BKW_MMAP_EMPTY)
+			goto state_err;
+		break;
+	}
+	case BKW_MMAP_EMPTY: {
+		if (state != BKW_MMAP_RUNNING)
+			goto state_err;
+		action = RESUME;
+		break;
+	}
+	default:
+		WARN_ONCE(1, "Shouldn't get there\n");
+	}
+
+	evlist->bkw_mmap_state = state;
+
+	switch (action) {
+	case PAUSE:
+		perf_evlist__pause(evlist);
+		break;
+	case RESUME:
+		perf_evlist__resume(evlist);
+		break;
+	case NONE:
+	default:
+		break;
+	}
+
+state_err:
+	return;
+}