[PATCH 2/8] perf stat: Bounds-check CPU index in topology aggregation callbacks

[Arnaldo Carvalho de Melo]

From: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>

Six perf_env__get_*_aggr_by_cpu() functions access env->cpu[cpu.cpu]
after only checking cpu.cpu != -1.  env->cpu[] is allocated with
env->nr_cpus_avail entries, so a CPU index from an untrusted perf.data
file that exceeds that count causes an out-of-bounds heap read.

Replace the != -1 guard with >= 0 && < env->nr_cpus_avail in all six
functions.  The >= 0 check also catches -1 and any other negative values
that could bypass the old check.

Affected functions:
  - perf_env__get_socket_aggr_by_cpu()
  - perf_env__get_die_aggr_by_cpu()
  - perf_env__get_cache_aggr_by_cpu()
  - perf_env__get_cluster_aggr_by_cpu()
  - perf_env__get_core_aggr_by_cpu()
  - perf_env__get_cpu_aggr_by_cpu()

Fixes: 68d702f7a120 ("perf stat report: Add support to initialize aggr_map from file")
Reported-by: sashiko-bot <sashiko-bot@xxxxxxxxxx>
Cc: Ian Rogers <irogers@xxxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Namhyung Kim <namhyung@xxxxxxxxxx>
Assisted-by: Claude Opus 4.6 <noreply@xxxxxxxxxxxxx>
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
---
 tools/perf/builtin-stat.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 99d7db372b480800..9a045811c4197ccd 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1638,7 +1638,8 @@ static struct aggr_cpu_id perf_env__get_socket_aggr_by_cpu(struct perf_cpu cpu,
 	struct perf_env *env = data;
 	struct aggr_cpu_id id = aggr_cpu_id__empty();
 
-	if (cpu.cpu != -1)
+	/* env->cpu[] has env->nr_cpus_avail entries; reject untrusted indices */
+	if (cpu.cpu >= 0 && cpu.cpu < env->nr_cpus_avail)
 		id.socket = env->cpu[cpu.cpu].socket_id;
 
 	return id;
@@ -1649,7 +1650,7 @@ static struct aggr_cpu_id perf_env__get_die_aggr_by_cpu(struct perf_cpu cpu, voi
 	struct perf_env *env = data;
 	struct aggr_cpu_id id = aggr_cpu_id__empty();
 
-	if (cpu.cpu != -1) {
+	if (cpu.cpu >= 0 && cpu.cpu < env->nr_cpus_avail) {
 		/*
 		 * die_id is relative to socket, so start
 		 * with the socket ID and then add die to
@@ -1705,7 +1706,7 @@ static struct aggr_cpu_id perf_env__get_cache_aggr_by_cpu(struct perf_cpu cpu,
 	struct perf_env *env = data;
 	struct aggr_cpu_id id = aggr_cpu_id__empty();
 
-	if (cpu.cpu != -1) {
+	if (cpu.cpu >= 0 && cpu.cpu < env->nr_cpus_avail) {
 		u32 cache_level = (perf_stat.aggr_level) ?: stat_config.aggr_level;
 
 		id.socket = env->cpu[cpu.cpu].socket_id;
@@ -1722,7 +1723,7 @@ static struct aggr_cpu_id perf_env__get_cluster_aggr_by_cpu(struct perf_cpu cpu,
 	struct perf_env *env = data;
 	struct aggr_cpu_id id = aggr_cpu_id__empty();
 
-	if (cpu.cpu != -1) {
+	if (cpu.cpu >= 0 && cpu.cpu < env->nr_cpus_avail) {
 		id.socket = env->cpu[cpu.cpu].socket_id;
 		id.die = env->cpu[cpu.cpu].die_id;
 		id.cluster = env->cpu[cpu.cpu].cluster_id;
@@ -1736,7 +1737,7 @@ static struct aggr_cpu_id perf_env__get_core_aggr_by_cpu(struct perf_cpu cpu, vo
 	struct perf_env *env = data;
 	struct aggr_cpu_id id = aggr_cpu_id__empty();
 
-	if (cpu.cpu != -1) {
+	if (cpu.cpu >= 0 && cpu.cpu < env->nr_cpus_avail) {
 		/*
 		 * core_id is relative to socket, die and cluster, we need a
 		 * global id. So we set socket, die id, cluster id and core id.
@@ -1755,7 +1756,7 @@ static struct aggr_cpu_id perf_env__get_cpu_aggr_by_cpu(struct perf_cpu cpu, voi
 	struct perf_env *env = data;
 	struct aggr_cpu_id id = aggr_cpu_id__empty();
 
-	if (cpu.cpu != -1) {
+	if (cpu.cpu >= 0 && cpu.cpu < env->nr_cpus_avail) {
 		/*
 		 * core_id is relative to socket and die,
 		 * we need a global id. So we set
-- 
2.54.0