1 files changed, 89 insertions, 44 deletions

diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index e37dfad31383..61b637f29b82 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -23,6 +23,7 @@
 #include <perf/cpumap.h>
 #include <perf/threadmap.h>
 #include <api/fd/array.h>
+#include "internal.h"
 
 void perf_evlist__init(struct perf_evlist *evlist)
 {
@@ -39,19 +40,26 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
 	 * We already have cpus for evsel (via PMU sysfs) so
 	 * keep it, if there's no target cpu list defined.
 	 */
-	if (!evsel->own_cpus || evlist->has_user_cpus) {
+	if (evsel->system_wide) {
 		perf_cpu_map__put(evsel->cpus);
-		evsel->cpus = perf_cpu_map__get(evlist->cpus);
-	} else if (!evsel->system_wide && perf_cpu_map__empty(evlist->cpus)) {
+		evsel->cpus = perf_cpu_map__new(NULL);
+	} else if (!evsel->own_cpus || evlist->has_user_cpus ||
+		   (!evsel->requires_cpu && perf_cpu_map__empty(evlist->user_requested_cpus))) {
 		perf_cpu_map__put(evsel->cpus);
-		evsel->cpus = perf_cpu_map__get(evlist->cpus);
+		evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus);
 	} else if (evsel->cpus != evsel->own_cpus) {
 		perf_cpu_map__put(evsel->cpus);
 		evsel->cpus = perf_cpu_map__get(evsel->own_cpus);
 	}
 
-	perf_thread_map__put(evsel->threads);
-	evsel->threads = perf_thread_map__get(evlist->threads);
+	if (evsel->system_wide) {
+		perf_thread_map__put(evsel->threads);
+		evsel->threads = perf_thread_map__new_dummy();
+	} else {
+		perf_thread_map__put(evsel->threads);
+		evsel->threads = perf_thread_map__get(evlist->threads);
+	}
+
 	evlist->all_cpus = perf_cpu_map__merge(evlist->all_cpus, evsel->cpus);
 }
 
@@ -59,6 +67,8 @@ static void perf_evlist__propagate_maps(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
 
+	evlist->needs_map_propagation = true;
+
 	perf_evlist__for_each_evsel(evlist, evsel)
 		__perf_evlist__propagate_maps(evlist, evsel);
 }
@@ -69,7 +79,9 @@ void perf_evlist__add(struct perf_evlist *evlist,
 	evsel->idx = evlist->nr_entries;
 	list_add_tail(&evsel->node, &evlist->entries);
 	evlist->nr_entries += 1;
-	__perf_evlist__propagate_maps(evlist, evsel);
+
+	if (evlist->needs_map_propagation)
+		__perf_evlist__propagate_maps(evlist, evsel);
 }
 
 void perf_evlist__remove(struct perf_evlist *evlist,
@@ -123,10 +135,10 @@ static void perf_evlist__purge(struct perf_evlist *evlist)
 
 void perf_evlist__exit(struct perf_evlist *evlist)
 {
-	perf_cpu_map__put(evlist->cpus);
+	perf_cpu_map__put(evlist->user_requested_cpus);
 	perf_cpu_map__put(evlist->all_cpus);
 	perf_thread_map__put(evlist->threads);
-	evlist->cpus = NULL;
+	evlist->user_requested_cpus = NULL;
 	evlist->all_cpus = NULL;
 	evlist->threads = NULL;
 	fdarray__exit(&evlist->pollfd);
@@ -155,9 +167,9 @@ void perf_evlist__set_maps(struct perf_evlist *evlist,
 	 * original reference count of 1.  If that is not the case it is up to
 	 * the caller to increase the reference count.
 	 */
-	if (cpus != evlist->cpus) {
-		perf_cpu_map__put(evlist->cpus);
-		evlist->cpus = perf_cpu_map__get(cpus);
+	if (cpus != evlist->user_requested_cpus) {
+		perf_cpu_map__put(evlist->user_requested_cpus);
+		evlist->user_requested_cpus = perf_cpu_map__get(cpus);
 	}
 
 	if (threads != evlist->threads) {
@@ -165,9 +177,6 @@ void perf_evlist__set_maps(struct perf_evlist *evlist,
 		evlist->threads = perf_thread_map__get(threads);
 	}
 
-	if (!evlist->all_cpus && cpus)
-		evlist->all_cpus = perf_cpu_map__get(cpus);
-
 	perf_evlist__propagate_maps(evlist);
 }
 
@@ -294,7 +303,7 @@ add:
 
 int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
 {
-	int nr_cpus = perf_cpu_map__nr(evlist->cpus);
+	int nr_cpus = perf_cpu_map__nr(evlist->all_cpus);
 	int nr_threads = perf_thread_map__nr(evlist->threads);
 	int nfds = 0;
 	struct perf_evsel *evsel;
@@ -407,7 +416,7 @@ perf_evlist__mmap_cb_get(struct perf_evlist *evlist, bool overwrite, int idx)
 
 static int
 perf_evlist__mmap_cb_mmap(struct perf_mmap *map, struct perf_mmap_param *mp,
-			  int output, int cpu)
+			  int output, struct perf_cpu cpu)
 {
 	return perf_mmap__mmap(map, mp, output, cpu);
 }
@@ -424,14 +433,15 @@ static void perf_evlist__set_mmap_first(struct perf_evlist *evlist, struct perf_
 static int
 mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 	       int idx, struct perf_mmap_param *mp, int cpu_idx,
-	       int thread, int *_output, int *_output_overwrite)
+	       int thread, int *_output, int *_output_overwrite, int *nr_mmaps)
 {
-	int evlist_cpu = perf_cpu_map__cpu(evlist->cpus, cpu_idx);
+	struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->all_cpus, cpu_idx);
 	struct perf_evsel *evsel;
 	int revent;
 
 	perf_evlist__for_each_entry(evlist, evsel) {
 		bool overwrite = evsel->attr.write_backward;
+		enum fdarray_flags flgs;
 		struct perf_mmap *map;
 		int *output, fd, cpu;
 
@@ -474,12 +484,21 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 			 */
 			refcount_set(&map->refcnt, 2);
 
+			if (ops->idx)
+				ops->idx(evlist, evsel, mp, idx);
+
+			/* Debug message used by test scripts */
+			pr_debug("idx %d: mmapping fd %d\n", idx, *output);
 			if (ops->mmap(map, mp, *output, evlist_cpu) < 0)
 				return -1;
 
+			*nr_mmaps += 1;
+
 			if (!idx)
 				perf_evlist__set_mmap_first(evlist, map, overwrite);
 		} else {
+			/* Debug message used by test scripts */
+			pr_debug("idx %d: set output fd %d -> %d\n", idx, fd, *output);
 			if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0)
 				return -1;
 
@@ -488,8 +507,8 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 
 		revent = !overwrite ? POLLIN : 0;
 
-		if (!evsel->system_wide &&
-		    perf_evlist__add_pollfd(evlist, fd, map, revent, fdarray_flag__default) < 0) {
+		flgs = evsel->system_wide ? fdarray_flag__nonfilterable : fdarray_flag__default;
+		if (perf_evlist__add_pollfd(evlist, fd, map, revent, flgs) < 0) {
 			perf_mmap__put(map);
 			return -1;
 		}
@@ -509,21 +528,37 @@ static int
 mmap_per_thread(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 		struct perf_mmap_param *mp)
 {
-	int thread;
 	int nr_threads = perf_thread_map__nr(evlist->threads);
+	int nr_cpus    = perf_cpu_map__nr(evlist->all_cpus);
+	int cpu, thread, idx = 0;
+	int nr_mmaps = 0;
 
-	for (thread = 0; thread < nr_threads; thread++) {
+	pr_debug("%s: nr cpu values (may include -1) %d nr threads %d\n",
+		 __func__, nr_cpus, nr_threads);
+
+	/* per-thread mmaps */
+	for (thread = 0; thread < nr_threads; thread++, idx++) {
 		int output = -1;
 		int output_overwrite = -1;
 
-		if (ops->idx)
-			ops->idx(evlist, mp, thread, false);
+		if (mmap_per_evsel(evlist, ops, idx, mp, 0, thread, &output,
+				   &output_overwrite, &nr_mmaps))
+			goto out_unmap;
+	}
 
-		if (mmap_per_evsel(evlist, ops, thread, mp, 0, thread,
-				   &output, &output_overwrite))
+	/* system-wide mmaps i.e. per-cpu */
+	for (cpu = 1; cpu < nr_cpus; cpu++, idx++) {
+		int output = -1;
+		int output_overwrite = -1;
+
+		if (mmap_per_evsel(evlist, ops, idx, mp, cpu, 0, &output,
+				   &output_overwrite, &nr_mmaps))
 			goto out_unmap;
 	}
 
+	if (nr_mmaps != evlist->nr_mmaps)
+		pr_err("Miscounted nr_mmaps %d vs %d\n", nr_mmaps, evlist->nr_mmaps);
+
 	return 0;
 
 out_unmap:
@@ -536,23 +571,26 @@ mmap_per_cpu(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 	     struct perf_mmap_param *mp)
 {
 	int nr_threads = perf_thread_map__nr(evlist->threads);
-	int nr_cpus    = perf_cpu_map__nr(evlist->cpus);
+	int nr_cpus    = perf_cpu_map__nr(evlist->all_cpus);
+	int nr_mmaps = 0;
 	int cpu, thread;
 
+	pr_debug("%s: nr cpu values %d nr threads %d\n", __func__, nr_cpus, nr_threads);
+
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		int output = -1;
 		int output_overwrite = -1;
 
-		if (ops->idx)
-			ops->idx(evlist, mp, cpu, true);
-
 		for (thread = 0; thread < nr_threads; thread++) {
 			if (mmap_per_evsel(evlist, ops, cpu, mp, cpu,
-					   thread, &output, &output_overwrite))
+					   thread, &output, &output_overwrite, &nr_mmaps))
 				goto out_unmap;
 		}
 	}
 
+	if (nr_mmaps != evlist->nr_mmaps)
+		pr_err("Miscounted nr_mmaps %d vs %d\n", nr_mmaps, evlist->nr_mmaps);
+
 	return 0;
 
 out_unmap:
@@ -564,9 +602,14 @@ static int perf_evlist__nr_mmaps(struct perf_evlist *evlist)
 {
 	int nr_mmaps;
 
-	nr_mmaps = perf_cpu_map__nr(evlist->cpus);
-	if (perf_cpu_map__empty(evlist->cpus))
-		nr_mmaps = perf_thread_map__nr(evlist->threads);
+	/* One for each CPU */
+	nr_mmaps = perf_cpu_map__nr(evlist->all_cpus);
+	if (perf_cpu_map__empty(evlist->all_cpus)) {
+		/* Plus one for each thread */
+		nr_mmaps += perf_thread_map__nr(evlist->threads);
+		/* Minus the per-thread CPU (-1) */
+		nr_mmaps -= 1;
+	}
 
 	return nr_mmaps;
 }
@@ -575,9 +618,8 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,
 			  struct perf_evlist_mmap_ops *ops,
 			  struct perf_mmap_param *mp)
 {
+	const struct perf_cpu_map *cpus = evlist->all_cpus;
 	struct perf_evsel *evsel;
-	const struct perf_cpu_map *cpus = evlist->cpus;
-	const struct perf_thread_map *threads = evlist->threads;
 
 	if (!ops || !ops->get || !ops->mmap)
 		return -EINVAL;
@@ -589,7 +631,7 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,
 	perf_evlist__for_each_entry(evlist, evsel) {
 		if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
 		    evsel->sample_id == NULL &&
-		    perf_evsel__alloc_id(evsel, perf_cpu_map__nr(cpus), threads->nr) < 0)
+		    perf_evsel__alloc_id(evsel, evsel->fd->max_x, evsel->fd->max_y) < 0)
 			return -ENOMEM;
 	}
 
@@ -643,14 +685,14 @@ perf_evlist__next_mmap(struct perf_evlist *evlist, struct perf_mmap *map,
 	return overwrite ? evlist->mmap_ovw_first : evlist->mmap_first;
 }
 
-void __perf_evlist__set_leader(struct list_head *list)
+void __perf_evlist__set_leader(struct list_head *list, struct perf_evsel *leader)
 {
-	struct perf_evsel *evsel, *leader;
+	struct perf_evsel *first, *last, *evsel;
 
-	leader = list_entry(list->next, struct perf_evsel, node);
-	evsel = list_entry(list->prev, struct perf_evsel, node);
+	first = list_first_entry(list, struct perf_evsel, node);
+	last = list_last_entry(list, struct perf_evsel, node);
 
-	leader->nr_members = evsel->idx - leader->idx + 1;
+	leader->nr_members = last->idx - first->idx + 1;
 
 	__perf_evlist__for_each_entry(list, evsel)
 		evsel->leader = leader;
@@ -659,7 +701,10 @@ void __perf_evlist__set_leader(struct list_head *list)
 void perf_evlist__set_leader(struct perf_evlist *evlist)
 {
 	if (evlist->nr_entries) {
+		struct perf_evsel *first = list_entry(evlist->entries.next,
+						struct perf_evsel, node);
+
 		evlist->nr_groups = evlist->nr_entries > 1 ? 1 : 0;
-		__perf_evlist__set_leader(&evlist->entries);
+		__perf_evlist__set_leader(&evlist->entries, first);
 	}
 }