This is a note to let you know that I've just added the patch titled
perf env: Add perf_env__numa_node()
to the 5.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
perf-env-add-perf_env__numa_node.patch
and it can be found in the queue-5.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit 55251e81f3bf963c59f5e1792b8a9b8f8e911070
Author: Jiri Olsa <jolsa@xxxxxxxxxx>
Date: Thu Aug 29 13:31:48 2019 +0200
perf env: Add perf_env__numa_node()
[ Upstream commit 389799a7a1e86c55f38897e679762efadcc9dedd ]
To speed up cpu to node lookup, add perf_env__numa_node(), that creates
cpu array on the first lookup, that holds numa nodes for each stored
cpu.
Signed-off-by: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Alexander Shishkin <alexander.shishkin@xxxxxxxxxxxxxxx>
Cc: Alexey Budankov <alexey.budankov@xxxxxxxxxxxxxxx>
Cc: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Cc: Joe Mario <jmario@xxxxxxxxxx>
Cc: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>
Cc: Michael Petlan <mpetlan@xxxxxxxxxx>
Cc: Namhyung Kim <namhyung@xxxxxxxxxx>
Cc: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Link: http://lkml.kernel.org/r/20190904073415.723-3-jolsa@xxxxxxxxxx
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Stable-dep-of: 9c51f8788b5d ("perf env: Avoid recursively taking env->bpf_progs.lock")
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index ef64e197bc8d..2d517f377053 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -183,6 +183,7 @@ void perf_env__exit(struct perf_env *env)
zfree(&env->sibling_threads);
zfree(&env->pmu_mappings);
zfree(&env->cpu);
+ zfree(&env->numa_map);
for (i = 0; i < env->nr_numa_nodes; i++)
perf_cpu_map__put(env->numa_nodes[i].map);
@@ -342,3 +343,42 @@ const char *perf_env__arch(struct perf_env *env)
return normalize_arch(arch_name);
}
+
+
+int perf_env__numa_node(struct perf_env *env, int cpu)
+{
+ if (!env->nr_numa_map) {
+ struct numa_node *nn;
+ int i, nr = 0;
+
+ for (i = 0; i < env->nr_numa_nodes; i++) {
+ nn = &env->numa_nodes[i];
+ nr = max(nr, perf_cpu_map__max(nn->map));
+ }
+
+ nr++;
+
+ /*
+ * We initialize the numa_map array to prepare
+ * it for missing cpus, which return node -1
+ */
+ env->numa_map = malloc(nr * sizeof(int));
+ if (!env->numa_map)
+ return -1;
+
+ for (i = 0; i < nr; i++)
+ env->numa_map[i] = -1;
+
+ env->nr_numa_map = nr;
+
+ for (i = 0; i < env->nr_numa_nodes; i++) {
+ int tmp, j;
+
+ nn = &env->numa_nodes[i];
+ perf_cpu_map__for_each_cpu(j, tmp, nn->map)
+ env->numa_map[j] = i;
+ }
+ }
+
+ return cpu >= 0 && cpu < env->nr_numa_map ? env->numa_map[cpu] : -1;
+}
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index 37028215d4a5..ceddddace5cc 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -87,6 +87,10 @@ struct perf_env {
struct rb_root btfs;
u32 btfs_cnt;
} bpf_progs;
+
+ /* For fast cpu to numa node lookup via perf_env__numa_node */
+ int *numa_map;
+ int nr_numa_map;
};
enum perf_compress_type {
@@ -119,4 +123,6 @@ struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env,
__u32 prog_id);
bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node);
struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id);
+
+int perf_env__numa_node(struct perf_env *env, int cpu);
#endif /* __PERF_ENV_H */
