summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorPeter Zijlstra <peterz@infradead.org>2018-01-09 21:23:02 +0100
committerIngo Molnar <mingo@kernel.org>2018-01-25 14:48:30 +0100
commit0c7296cad651a3a40286d70ff37e73bd6fa4e4da (patch)
tree8e22faa9d84a0b7e339f966bdbb58b324fc29ebf
parentperf/core: Fix another perf,trace,cpuhp lock inversion (diff)
downloadlinux-0c7296cad651a3a40286d70ff37e73bd6fa4e4da.tar.xz
linux-0c7296cad651a3a40286d70ff37e73bd6fa4e4da.zip
perf/core: Fix ctx::mutex deadlock
Lockdep noticed the following 3-way lockup scenario: sys_perf_event_open() perf_event_alloc() perf_try_init_event() #0 ctx = perf_event_ctx_lock_nested(1) perf_swevent_init() swevent_hlist_get() #1 mutex_lock(&pmus_lock) perf_event_init_cpu() #1 mutex_lock(&pmus_lock) #2 mutex_lock(&ctx->mutex) sys_perf_event_open() mutex_lock_double() #2 mutex_lock() #0 mutex_lock_nested() And while we need that perf_event_ctx_lock_nested() for HW PMUs such that they can iterate the sibling list, trying to match it to the available counters, the software PMUs need do no such thing. Exclude them. In particular the swevent triggers the above invertion, while the tpevent PMU triggers a more elaborate one through their event_mutex. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vince Weaver <vincent.weaver@maine.edu> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
-rw-r--r--kernel/events/core.c8
1 files changed, 7 insertions, 1 deletions
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 816f83d70fc6..5d8f4031f8d5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -9199,7 +9199,13 @@ static int perf_try_init_event(struct pmu *pmu, struct perf_event *event)
if (!try_module_get(pmu->module))
return -ENODEV;
- if (event->group_leader != event) {
+ /*
+ * A number of pmu->event_init() methods iterate the sibling_list to,
+ * for example, validate if the group fits on the PMU. Therefore,
+ * if this is a sibling event, acquire the ctx->mutex to protect
+ * the sibling_list.
+ */
+ if (event->group_leader != event && pmu->task_ctx_nr != perf_sw_context) {
/*
* This ctx->mutex can nest when we're called through
* inheritance. See the perf_event_ctx_lock_nested() comment.