Linux Perf Users
 help / color / mirror / Atom feed
From: Arnaldo Carvalho de Melo <acme@kernel.org>
To: Namhyung Kim <namhyung@kernel.org>
Cc: Ingo Molnar <mingo@kernel.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	James Clark <james.clark@linaro.org>,
	Jiri Olsa <jolsa@kernel.org>, Ian Rogers <irogers@google.com>,
	Adrian Hunter <adrian.hunter@intel.com>,
	Clark Williams <williams@redhat.com>,
	linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
	Arnaldo Carvalho de Melo <acme@redhat.com>,
	sashiko-bot@kernel.org, "Claude Opus 4.6" <noreply@anthropic.com>
Subject: [PATCH 6/8] perf timechart: Fix cat_backtrace() use-after-free on corrupted callchain
Date: Tue,  2 Jun 2026 20:57:05 -0300	[thread overview]
Message-ID: <20260602235709.1541603-7-acme@kernel.org> (raw)
In-Reply-To: <20260602235709.1541603-1-acme@kernel.org>

From: Arnaldo Carvalho de Melo <acme@redhat.com>

cat_backtrace() uses open_memstream() to build a backtrace string.
When an invalid callchain context is encountered, zfree(&p) frees
the memstream buffer, then the exit path calls fclose(f), which
flushes to the already-freed buffer — a use-after-free.  The function
then returns a dangling pointer that the caller passes to a handler
and subsequently double-frees.

Fix by replacing the zfree(&p) with a 'corrupted' flag.  At the exit
label, always fclose(f) first (which finalizes the buffer), then
conditionally free it when corrupted.  This ensures the memstream
contract is honored: the buffer remains valid until fclose().

While here, update the machine__resolve failure message to include
file_offset and the event type name, matching the pattern from the
preceding series.  Also update the three legacy power event handlers
under SUPPORT_OLD_POWER_EVENTS to include file_offset in their
out-of-bounds CPU messages for consistency.

Reported-by: sashiko-bot@kernel.org # Running on a local machine
Assisted-by: Claude Opus 4.6 <noreply@anthropic.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-timechart.c | 36 ++++++++++++++++++++++------------
 1 file changed, 23 insertions(+), 13 deletions(-)

diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 071987241a528ba4..85a9ad0455aecccd 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -489,6 +489,10 @@ static void sched_switch(struct timechart *tchart, int cpu, u64 timestamp,
 	}
 }
 
+/*
+ * Returns a malloc'd backtrace string built via open_memstream, or NULL
+ * on error.  Caller must free() the returned pointer.
+ */
 static char *cat_backtrace(union perf_event *event,
 			   struct perf_sample *sample,
 			   struct machine *machine)
@@ -500,6 +504,7 @@ static char *cat_backtrace(union perf_event *event,
 	u8 cpumode = PERF_RECORD_MISC_USER;
 	struct ip_callchain *chain = sample->callchain;
 	FILE *f = open_memstream(&p, &p_len);
+	bool corrupted = false;
 
 	if (!f) {
 		perror("open_memstream error");
@@ -511,8 +516,9 @@ static char *cat_backtrace(union perf_event *event,
 		goto exit;
 
 	if (machine__resolve(machine, &al, sample) < 0) {
-		fprintf(stderr, "problem processing %d event, skipping it.\n",
-			event->header.type);
+		pr_err("problem processing %s (%u) event at offset %#" PRIx64 ", skipping it.\n",
+		       perf_event__name(event->header.type), event->header.type,
+		       sample->file_offset);
 		goto exit;
 	}
 
@@ -537,14 +543,8 @@ static char *cat_backtrace(union perf_event *event,
 				cpumode = PERF_RECORD_MISC_USER;
 				break;
 			default:
-				pr_debug("invalid callchain context: "
-					 "%"PRId64"\n", (s64) ip);
-
-				/*
-				 * It seems the callchain is corrupted.
-				 * Discard all.
-				 */
-				zfree(&p);
+				pr_debug("invalid callchain context: %" PRId64 "\n", (s64) ip);
+				corrupted = true;
 				goto exit;
 			}
 			continue;
@@ -561,7 +561,14 @@ static char *cat_backtrace(union perf_event *event,
 	}
 exit:
 	addr_location__exit(&al);
+	/*
+	 * fclose() on an open_memstream always sets p to a valid buffer,
+	 * even if nothing was written — see open_memstream(3).  So p is
+	 * never NULL after fclose and we need the flag to discard it.
+	 */
 	fclose(f);
+	if (corrupted)
+		zfree(&p);
 
 	return p;
 }
@@ -686,7 +693,8 @@ process_sample_power_start(struct timechart *tchart __maybe_unused,
 
 	/* perf.data is untrusted input — cpu_id may be corrupted */
 	if (cpu_id >= MAX_CPUS) {
-		pr_debug("Out-of-bounds cpu_id %llu\n", (unsigned long long)cpu_id);
+		pr_debug("at offset %#" PRIx64 ": out-of-bounds cpu_id %llu\n",
+			 sample->file_offset, (unsigned long long)cpu_id);
 		return -1;
 	}
 	c_state_start(cpu_id, sample->time, value);
@@ -700,7 +708,8 @@ process_sample_power_end(struct timechart *tchart,
 {
 	/* perf.data is untrusted input — CPU may be absent or corrupted */
 	if (sample->cpu >= MAX_CPUS) {
-		pr_debug("Out-of-bounds cpu %u\n", sample->cpu);
+		pr_debug("at offset %#" PRIx64 ": out-of-bounds cpu %u\n",
+			 sample->file_offset, sample->cpu);
 		return -1;
 	}
 	c_state_end(tchart, sample->cpu, sample->time);
@@ -717,7 +726,8 @@ process_sample_power_frequency(struct timechart *tchart,
 
 	/* perf.data is untrusted input — cpu_id may be corrupted */
 	if (cpu_id >= MAX_CPUS) {
-		pr_debug("Out-of-bounds cpu_id %llu\n", (unsigned long long)cpu_id);
+		pr_debug("at offset %#" PRIx64 ": out-of-bounds cpu_id %llu\n",
+			 sample->file_offset, (unsigned long long)cpu_id);
 		return -1;
 	}
 	p_state_change(tchart, cpu_id, sample->time, value);
-- 
2.54.0


  parent reply	other threads:[~2026-06-02 23:57 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-06-02 23:56 [PATCHES 0/8] perf tools: Diagnostic offsets in skip messages + two hardening fixes Arnaldo Carvalho de Melo
2026-06-02 23:57 ` [PATCH 1/8] perf sample: Add file_offset field to struct perf_sample Arnaldo Carvalho de Melo
2026-06-02 23:57 ` [PATCH 2/8] perf session: Include file offset in event skip/stop messages Arnaldo Carvalho de Melo
2026-06-02 23:57 ` [PATCH 3/8] perf sched: Include file offset in event skip messages Arnaldo Carvalho de Melo
2026-06-02 23:57 ` [PATCH 4/8] perf timechart: Include file offset in CPU bounds check messages Arnaldo Carvalho de Melo
2026-06-03  0:36   ` sashiko-bot
2026-06-02 23:57 ` [PATCH 5/8] perf tools: Include file offset and event type name in skip messages Arnaldo Carvalho de Melo
2026-06-02 23:57 ` Arnaldo Carvalho de Melo [this message]
2026-06-02 23:57 ` [PATCH 7/8] perf sched: Replace BUG_ON on invalid CPU with graceful skip Arnaldo Carvalho de Melo
2026-06-03  1:16   ` sashiko-bot
2026-06-02 23:57 ` [PATCH 8/8] perf test: Add file offset diagnostic test for corrupted perf.data Arnaldo Carvalho de Melo
2026-06-03  1:32   ` sashiko-bot

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260602235709.1541603-7-acme@kernel.org \
    --to=acme@kernel.org \
    --cc=acme@redhat.com \
    --cc=adrian.hunter@intel.com \
    --cc=irogers@google.com \
    --cc=james.clark@linaro.org \
    --cc=jolsa@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=namhyung@kernel.org \
    --cc=noreply@anthropic.com \
    --cc=sashiko-bot@kernel.org \
    --cc=tglx@linutronix.de \
    --cc=williams@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox