From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752226AbbFLGAy (ORCPT ); Fri, 12 Jun 2015 02:00:54 -0400 Received: from e18.ny.us.ibm.com ([129.33.205.208]:47015 "EHLO e18.ny.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750773AbbFLGAx (ORCPT ); Fri, 12 Jun 2015 02:00:53 -0400 Date: Thu, 11 Jun 2015 23:00:04 -0700 From: Sukadev Bhattiprolu To: Arnaldo Carvalho de Melo Cc: Jiri Olsa , Ingo Molnar , Li Zhang , linux-kernel@vger.kernel.org Subject: [PATCH] perf, tools: Fix crash in 'perf trace' Message-ID: <20150612060003.GA19913@us.ibm.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline X-Operating-System: Linux 2.0.32 on an i486 User-Agent: Mutt/1.5.21 (2010-09-15) X-TM-AS-MML: disable X-Content-Scanned: Fidelis XPS MAILER x-cbid: 15061206-0045-0000-0000-0000006E5C77 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org >>From 6669ed960a3ee4f9a02790f60b6a73ffc82fd6de Mon Sep 17 00:00:00 2001 From: Sukadev Bhattiprolu Date: Fri, 12 Jun 2015 01:28:36 -0400 Subject: [PATCH] perf, tools: Fix crash in perf trace I get following crash on multiple systems and across several releases (at least since v3.18). Core was generated by `/tmp/perf trace sleep 0.2 '. Program terminated with signal SIGSEGV, Segmentation fault. #0 perf_mmap__read_head (mm=0x3fff9bf30070) at util/evlist.h:195 195 u64 head = ACCESS_ONCE(pc->data_head); (gdb) bt #0 perf_mmap__read_head (mm=0x3fff9bf30070) at util/evlist.h:195 #1 perf_evlist__mmap_read (evlist=0x10027f11910, idx=) at util/evlist.c:637 #2 0x000000001003ce4c in trace__run (argv=, argc=, trace=0x3fffd7b28288) at builtin-trace.c:2259 #3 cmd_trace (argc=, argv=, prefix=) at builtin-trace.c:2799 #4 0x00000000100657b8 in run_builtin (p=0x10176798 , argc=3, argv=0x3fffd7b2b550) at perf.c:370 #5 0x00000000100063e8 in handle_internal_command (argv=0x3fffd7b2b550, argc=3) at perf.c:429 #6 run_argv (argv=0x3fffd7b2af70, argcp=0x3fffd7b2af7c) at perf.c:473 #7 main (argc=3, argv=0x3fffd7b2b550) at perf.c:588 The problem seems to be a race condition, when the application has just exited. Some/all fds associated with the perf-events (tracepoints) go into a POLLHUP/ POLLERR state and the mmap region associated with those events are unmapped (in perf_evlist__filter_pollfd()). But we go back and do a perf_evlist__mmap_read() which assumes that the mmaps are still valid and we hit the crash. If the mapping for an event is released, its refcnt is 0 (and ->base is NULL), so ensure we have non-zero refcount before accessing the map. Note that perf-record has a similar logic but unlike perf-trace, the record__mmap_read_all() checks the evlist->mmap[i].base before accessing the map. Signed-off-by: Sukadev Bhattiprolu --- tools/perf/util/evlist.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 080be93..084535b 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -634,11 +634,18 @@ static struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist, union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) { struct perf_mmap *md = &evlist->mmap[idx]; - u64 head = perf_mmap__read_head(md); + u64 head; u64 old = md->prev; unsigned char *data = md->base + page_size; union perf_event *event = NULL; + /* + * Check if event was unmapped due to a POLLHUP/POLLERR. + */ + if (!md->refcnt) + return NULL; + + head = perf_mmap__read_head(md); if (evlist->overwrite) { /* * If we're further behind than half the buffer, there's a chance -- 2.1.4