From 3cffdb884f17dd6012cbf0497b2bdfb9da19c84c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 11 Jan 2017 21:09:50 +0100 Subject: [PATCH] perf/core: Fix concurrent sys_perf_event_open() vs. 'move_group' race commit 321027c1fe77f892f4ea07846aeae08cefbbb290 upstream. commit fe525a280e8b5f04c7666fe22d1a4ef592f7b953 in 3.16.40 bug: 37901413 Di Shen reported a race between two concurrent sys_perf_event_open() calls where both try and move the same pre-existing software group into a hardware context. The problem is exactly that described in commit: f63a8daa5812 ("perf: Fix event->ctx locking") ... where, while we wait for a ctx->mutex acquisition, the event->ctx relation can have changed under us. That very same commit failed to recognise sys_perf_event_context() as an external access vector to the events and thereby didn't apply the established locking rules correctly. So while one sys_perf_event_open() call is stuck waiting on mutex_lock_double(), the other (which owns said locks) moves the group about. So by the time the former sys_perf_event_open() acquires the locks, the context we've acquired is stale (and possibly dead). Apply the established locking rules as per perf_event_ctx_lock_nested() to the mutex_lock_double() for the 'move_group' case. This obviously means we need to validate state after we acquire the locks. Change-Id: I816a317dff3ce999c94d22b7e51152ad1dcc30a2 Reported-by: Di Shen (Keen Lab) Tested-by: John Dias Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Kees Cook Cc: Linus Torvalds Cc: Min Chong Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Fixes: f63a8daa5812 ("perf: Fix event->ctx locking") Link: http://lkml.kernel.org/r/20170106131444.GZ3174@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar [bwh: Backported to 3.16: - Use ACCESS_ONCE() instead of READ_ONCE() - Test perf_event::group_flags instead of group_caps - Add the err_locked cleanup block, which we didn't need before - Adjust context] Signed-off-by: Ben Hutchings Signed-off-by: Suren Baghdasaryan --- kernel/events/core.c | 61 +++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 57 insertions(+), 4 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index 5fe4fc397bba..0a121cb5e5df 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6535,6 +6535,37 @@ static void mutex_lock_double(struct mutex *a, struct mutex *b) mutex_lock_nested(b, SINGLE_DEPTH_NESTING); } +/* + * Variation on perf_event_ctx_lock_nested(), except we take two context + * mutexes. + */ +static struct perf_event_context * +__perf_event_ctx_lock_double(struct perf_event *group_leader, + struct perf_event_context *ctx) +{ + struct perf_event_context *gctx; + +again: + rcu_read_lock(); + gctx = ACCESS_ONCE(group_leader->ctx); + if (!atomic_inc_not_zero(&gctx->refcount)) { + rcu_read_unlock(); + goto again; + } + rcu_read_unlock(); + + mutex_lock_double(&gctx->mutex, &ctx->mutex); + + if (group_leader->ctx != gctx) { + mutex_unlock(&ctx->mutex); + mutex_unlock(&gctx->mutex); + put_ctx(gctx); + goto again; + } + + return gctx; +} + /** * sys_perf_event_open - open a performance event, associate it to a task/cpu * @@ -6740,14 +6771,31 @@ SYSCALL_DEFINE5(perf_event_open, } if (move_group) { - gctx = group_leader->ctx; + gctx = __perf_event_ctx_lock_double(group_leader, ctx); + + /* + * Check if we raced against another sys_perf_event_open() call + * moving the software group underneath us. + */ + if (!(group_leader->group_flags & PERF_GROUP_SOFTWARE)) { + /* + * If someone moved the group out from under us, check + * if this new event wound up on the same ctx, if so + * its the regular !move_group case, otherwise fail. + */ + if (gctx != ctx) { + err = -EINVAL; + goto err_locked; + } else { + perf_event_ctx_unlock(group_leader, gctx); + move_group = 0; + } + } /* * See perf_event_ctx_lock() for comments on the details * of swizzling perf_event::ctx. */ - mutex_lock_double(&gctx->mutex, &ctx->mutex); - perf_remove_from_context(group_leader, false); /* @@ -6789,7 +6837,7 @@ SYSCALL_DEFINE5(perf_event_open, perf_unpin_context(ctx); if (move_group) { - mutex_unlock(&gctx->mutex); + perf_event_ctx_unlock(group_leader, gctx); put_ctx(gctx); } mutex_unlock(&ctx->mutex); @@ -6816,6 +6864,11 @@ SYSCALL_DEFINE5(perf_event_open, fd_install(event_fd, event_file); return event_fd; +err_locked: + if (move_group) + perf_event_ctx_unlock(group_leader, gctx); + mutex_unlock(&ctx->mutex); + fput(event_file); err_context: perf_unpin_context(ctx); put_ctx(ctx);