Merge tag 'perf-tools-for-v5.18-2022-04-02' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull more perf tools updates from Arnaldo Carvalho de Melo:

 - Avoid SEGV if core.cpus isn't set in 'perf stat'.

 - Stop depending on .git files for building PERF-VERSION-FILE, used in
   'perf --version', fixing some perf tools build scenarios.

 - Convert tracepoint.py example to python3.

 - Update UAPI header copies from the kernel sources: socket,
   mman-common, msr-index, KVM, i915 and cpufeatures.

 - Update copy of libbpf's hashmap.c.

 - Directly return instead of using local ret variable in
   evlist__create_syswide_maps(), found by coccinelle.

* tag 'perf-tools-for-v5.18-2022-04-02' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux:
  perf python: Convert tracepoint.py example to python3
  perf evlist: Directly return instead of using local ret variable
  perf cpumap: More cpu map reuse by merge.
  perf cpumap: Add is_subset function
  perf evlist: Rename cpus to user_requested_cpus
  perf tools: Stop depending on .git files for building PERF-VERSION-FILE
  tools headers cpufeatures: Sync with the kernel sources
  tools headers UAPI: Sync drm/i915_drm.h with the kernel sources
  tools headers UAPI: Sync linux/kvm.h with the kernel sources
  tools kvm headers arm64: Update KVM headers from the kernel sources
  tools arch x86: Sync the msr-index.h copy with the kernel sources
  tools headers UAPI: Sync asm-generic/mman-common.h with the kernel
  perf beauty: Update copy of linux/socket.h with the kernel sources
  perf tools: Update copy of libbpf's hashmap.c
  perf stat: Avoid SEGV if core.cpus isn't set

4 files changed, 46 insertions, 25 deletions

diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c
index ee66760f1e63..384d5e076ee4 100644
--- a/tools/lib/perf/cpumap.c
+++ b/tools/lib/perf/cpumap.c
@@ -319,6 +319,26 @@ struct perf_cpu perf_cpu_map__max(struct perf_cpu_map *map)
 	return map->nr > 0 ? map->map[map->nr - 1] : result;
 }
 
+/** Is 'b' a subset of 'a'. */
+bool perf_cpu_map__is_subset(const struct perf_cpu_map *a, const struct perf_cpu_map *b)
+{
+	if (a == b || !b)
+		return true;
+	if (!a || b->nr > a->nr)
+		return false;
+
+	for (int i = 0, j = 0; i < a->nr; i++) {
+		if (a->map[i].cpu > b->map[j].cpu)
+			return false;
+		if (a->map[i].cpu == b->map[j].cpu) {
+			j++;
+			if (j == b->nr)
+				return true;
+		}
+	}
+	return false;
+}
+
 /*
  * Merge two cpumaps
  *
@@ -335,17 +355,12 @@ struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
 	int i, j, k;
 	struct perf_cpu_map *merged;
 
-	if (!orig && !other)
-		return NULL;
-	if (!orig) {
-		perf_cpu_map__get(other);
-		return other;
-	}
-	if (!other)
-		return orig;
-	if (orig->nr == other->nr &&
-	    !memcmp(orig->map, other->map, orig->nr * sizeof(struct perf_cpu)))
+	if (perf_cpu_map__is_subset(orig, other))
 		return orig;
+	if (perf_cpu_map__is_subset(other, orig)) {
+		perf_cpu_map__put(orig);
+		return perf_cpu_map__get(other);
+	}
 
 	tmp_len = orig->nr + other->nr;
 	tmp_cpus = malloc(tmp_len * sizeof(struct perf_cpu));
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index 9a770bfdc804..1b15ba13c477 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -41,10 +41,10 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
 	 */
 	if (!evsel->own_cpus || evlist->has_user_cpus) {
 		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__get(evlist->user_requested_cpus);
+	} else if (!evsel->system_wide && 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);
@@ -123,10 +123,10 @@ 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 +155,9 @@ 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) {
@@ -294,7 +294,7 @@ 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->user_requested_cpus);
 	int nr_threads = perf_thread_map__nr(evlist->threads);
 	int nfds = 0;
 	struct perf_evsel *evsel;
@@ -426,7 +426,7 @@ 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)
 {
-	struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->cpus, cpu_idx);
+	struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->user_requested_cpus, cpu_idx);
 	struct perf_evsel *evsel;
 	int revent;
 
@@ -536,7 +536,7 @@ 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->user_requested_cpus);
 	int cpu, thread;
 
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
@@ -564,8 +564,8 @@ 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_cpu_map__nr(evlist->user_requested_cpus);
+	if (perf_cpu_map__empty(evlist->user_requested_cpus))
 		nr_mmaps = perf_thread_map__nr(evlist->threads);
 
 	return nr_mmaps;
@@ -576,7 +576,7 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,
 			  struct perf_mmap_param *mp)
 {
 	struct perf_evsel *evsel;
-	const struct perf_cpu_map *cpus = evlist->cpus;
+	const struct perf_cpu_map *cpus = evlist->user_requested_cpus;
 	const struct perf_thread_map *threads = evlist->threads;
 
 	if (!ops || !ops->get || !ops->mmap)
diff --git a/tools/lib/perf/include/internal/cpumap.h b/tools/lib/perf/include/internal/cpumap.h
index 1973a18c096b..35dd29642296 100644
--- a/tools/lib/perf/include/internal/cpumap.h
+++ b/tools/lib/perf/include/internal/cpumap.h
@@ -25,5 +25,6 @@ struct perf_cpu_map {
 #endif
 
 int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu);
+bool perf_cpu_map__is_subset(const struct perf_cpu_map *a, const struct perf_cpu_map *b);
 
 #endif /* __LIBPERF_INTERNAL_CPUMAP_H */
diff --git a/tools/lib/perf/include/internal/evlist.h b/tools/lib/perf/include/internal/evlist.h
index 4cefade540bd..e3e64f37db7b 100644
--- a/tools/lib/perf/include/internal/evlist.h
+++ b/tools/lib/perf/include/internal/evlist.h
@@ -19,7 +19,12 @@ struct perf_evlist {
 	int			 nr_entries;
 	int			 nr_groups;
 	bool			 has_user_cpus;
-	struct perf_cpu_map	*cpus;
+	/**
+	 * The cpus passed from the command line or all online CPUs by
+	 * default.
+	 */
+	struct perf_cpu_map	*user_requested_cpus;
+	/** The union of all evsel cpu maps. */
 	struct perf_cpu_map	*all_cpus;
 	struct perf_thread_map	*threads;
 	int			 nr_mmaps;