1 files changed, 50 insertions, 0 deletions

diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index e6c98a6e3908..6b1bafe267a4 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -486,6 +486,7 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 			if (ops->idx)
 				ops->idx(evlist, evsel, mp, idx);
 
+			pr_debug("idx %d: mmapping fd %d\n", idx, *output);
 			if (ops->mmap(map, mp, *output, evlist_cpu) < 0)
 				return -1;
 
@@ -494,6 +495,7 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 			if (!idx)
 				perf_evlist__set_mmap_first(evlist, map, overwrite);
 		} else {
+			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;
 
@@ -520,6 +522,48 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 }
 
 static int
+mmap_per_thread(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->all_cpus);
+	int cpu, thread, idx = 0;
+	int nr_mmaps = 0;
+
+	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 (mmap_per_evsel(evlist, ops, idx, mp, 0, thread, &output,
+				   &output_overwrite, &nr_mmaps))
+			goto out_unmap;
+	}
+
+	/* 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:
+	perf_evlist__munmap(evlist);
+	return -1;
+}
+
+static int
 mmap_per_cpu(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 	     struct perf_mmap_param *mp)
 {
@@ -528,6 +572,8 @@ mmap_per_cpu(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 	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;
@@ -569,6 +615,7 @@ 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;
 
 	if (!ops || !ops->get || !ops->mmap)
@@ -588,6 +635,9 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,
 	if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) < 0)
 		return -ENOMEM;
 
+	if (perf_cpu_map__empty(cpus))
+		return mmap_per_thread(evlist, ops, mp);
+
 	return mmap_per_cpu(evlist, ops, mp);
 }