linux-kernel - [PATCH v8 2/6] perf stat-shadow: In prepare_metric fix guard on reading NULL perf_stat

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20260206222509.982489-3-irogers@google.com>
Date: Fri,  6 Feb 2026 14:25:05 -0800
From: Ian Rogers <irogers@...gle.com>
To: acme@...nel.org
Cc: adrian.hunter@...el.com, ak@...ux.intel.com, 
	alexander.shishkin@...ux.intel.com, andres@...razel.de, 
	dapeng1.mi@...ux.intel.com, irogers@...gle.com, james.clark@...aro.org, 
	jolsa@...nel.org, linux-kernel@...r.kernel.org, 
	linux-perf-users@...r.kernel.org, linux@...blig.org, mingo@...hat.com, 
	namhyung@...nel.org, peterz@...radead.org, thomas.falcon@...el.com, 
	tmricht@...ux.ibm.com, yang.lee@...ux.alibaba.com
Subject: [PATCH v8 2/6] perf stat-shadow: In prepare_metric fix guard on
 reading NULL perf_stat_evsel

The aggr value is setup to always be non-null creating a redundant
guard for reading from it. Switch to using the perf_stat_evsel (ps)
and narrow the scope of aggr so that it is known valid when used.

Reported-by: Andres Freund <andres@...razel.de>
Closes: https://lore.kernel.org/linux-perf-users/cgja46br2smmznxs7kbeabs6zgv3b4olfqgh2fdp5mxk2yom4v@w6jjgov6hdi6/
Fixes: 3d65f6445fd9 ("perf stat-shadow: Read tool events directly")
Signed-off-by: Ian Rogers <irogers@...gle.com>
---
 tools/perf/util/stat-shadow.c | 24 ++++++++++++++++--------
 1 file changed, 16 insertions(+), 8 deletions(-)

diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 5d8d09e0e6ae..59d2cd4f2188 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -57,7 +57,6 @@ static int prepare_metric(struct perf_stat_config *config,
 		bool is_tool_time =
 			tool_pmu__is_time_event(config, metric_events[i], &tool_aggr_idx);
 		struct perf_stat_evsel *ps = metric_events[i]->stats;
-		struct perf_stat_aggr *aggr;
 		char *n;
 		double val;
 
@@ -82,8 +81,7 @@ static int prepare_metric(struct perf_stat_config *config,
 			}
 		}
 		/* Time events are always on CPU0, the first aggregation index. */
-		aggr = &ps->aggr[is_tool_time ? tool_aggr_idx : aggr_idx];
-		if (!aggr || !metric_events[i]->supported || aggr->counts.run == 0) {
+		if (!ps || !metric_events[i]->supported) {
 			/*
 			 * Not supported events will have a count of 0, which
 			 * can be confusing in a metric. Explicitly set the
@@ -93,11 +91,21 @@ static int prepare_metric(struct perf_stat_config *config,
 			val = NAN;
 			source_count = 0;
 		} else {
-			val = aggr->counts.val;
-			if (is_tool_time)
-				val *= 1e-9; /* Convert time event nanoseconds to seconds. */
-			if (!source_count)
-				source_count = evsel__source_count(metric_events[i]);
+			struct perf_stat_aggr *aggr =
+				&ps->aggr[is_tool_time ? tool_aggr_idx : aggr_idx];
+
+			if (aggr->counts.run == 0) {
+				val = NAN;
+				source_count = 0;
+			} else {
+				val = aggr->counts.val;
+				if (is_tool_time) {
+					/* Convert time event nanoseconds to seconds. */
+					val *= 1e-9;
+				}
+				if (!source_count)
+					source_count = evsel__source_count(metric_events[i]);
+			}
 		}
 		n = strdup(evsel__metric_id(metric_events[i]));
 		if (!n)
-- 
2.53.0.rc2.204.g2597b5adb4-goog