Patch "perf: Fix race in swevent hash" has been added to the 3.18-stable tree
Subsystems (2)
This is a note to let you know that I've just added the patch titled
perf: Fix race in swevent hash
to the 3.18-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
perf-fix-race-in-swevent-hash.patch
and it can be found in the queue-3.18 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree, please let <[email protected]> know about it.
Quoted 1 line
From
12ca6ad2e3a896256f086497a7c7406a547ee373Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <[email protected]>
Date: Tue, 15 Dec 2015 13:49:05 +0100
Subject: perf: Fix race in swevent hash
From: Peter Zijlstra <[email protected]>
commit 12ca6ad2e3a896256f086497a7c7406a547ee373 upstream.
There's a race on CPU unplug where we free the swevent hash array while it can still have events on. This will result in a use-after-free which is BAD.
Simply do not free the hash array on unplug. This leaves the thing around and no use-after-free takes place.
When the last swevent dies, we do a for_each_possible_cpu() iteration anyway to clean these up, at which time we'll free it, so no leakage will occur.
--- kernel/events/core.c | 20 +------------------- 1 file changed, 1 insertion(+), 19 deletions(-)
kernel/events/core.c +1 -19
@@ -5851,9 +5851,6 @@ struct swevent_htable {/* Recursion avoidance in each contexts */ int recursion[PERF_NR_CONTEXTS ]; - -/* Keeps track of cpu being initialized/exited */ -bool online; }; static DEFINE_PER_CPU(struct swevent_htable, swevent_htable);
@@ -6111,14 +6108,8 @@ static int perf_swevent_add(struct perf_ hwc->state = !(flags &PERF_EF_START ); head =find_swevent_head (swhash, event); -if (!head) { -/* -* We can race with cpu hotplug code. Do not -* WARN if the cpu just got unplugged. -*/ -WARN_ON_ONCE (swhash->online); +if (WARN_ON_ONCE (!head))return -EINVAL ; - }hlist_add_head_rcu (&event->hlist_entry, head);
@@ -6185,7 +6176,6 @@ static int swevent_hlist_get_cpu(structint err =0 ;mutex_lock (&swhash->hlist_mutex); -if (!swevent_hlist_deref (swhash) &&cpu_online (cpu)) {struct swevent_hlist *hlist;
@@ -8342,7 +8332,6 @@ static void perf_event_init_cpu(int cpu)struct swevent_htable *swhash = &per_cpu (swevent_htable, cpu);mutex_lock (&swhash->hlist_mutex); - swhash->online = true;if (swhash->hlist_refcount >0 ) {struct swevent_hlist *hlist;
@@ -8395,14 +8384,7 @@ static void perf_event_exit_cpu_context(static void perf_event_exit_cpu (int cpu) { -struct swevent_htable *swhash = &per_cpu (swevent_htable, cpu); -perf_event_exit_cpu_context (cpu); - -mutex_lock (&swhash->hlist_mutex); - swhash->online = false; -swevent_hlist_release (swhash); -mutex_unlock (&swhash->hlist_mutex); }#else static inline void perf_event_exit_cpu (int cpu) { }
Patches currently in stable-queue which might be from [email protected] are
queue-3.18/arm64-perf-reject-groups-spanning-multiple-hw-pmus.patch queue-3.18/x86-boot-fix-bss-corruption-overwrite-bug-in-early-x86-kernel-startup.patch queue-3.18/perf-fix-race-in-swevent-hash.patch queue-3.18/perf-fix-event-ctx-locking.patch