From c5ed5145591774bd9a2960ba4ca45a02fc70aad1 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 17 Jan 2011 13:45:37 +0100 Subject: perf: Fix contexted inheritance Linus reported that the RCU lockdep annotation bits triggered for this rcu_dereference() because we're not holding rcu_read_lock(). Going over the code I cannot convince myself its correct: - holding a ref on the parent_ctx, doesn't avoid it being uncloned concurrently (as the comment says), so we can race with a free. - holding parent_ctx->mutex doesn't avoid the above free from taking place either, it would at best avoid parent_ctx from being freed. I.e. the warning is correct. To fix the bug, serialize against the unclone_ctx() call by extending the reach of the parent_ctx->lock. Reported-by: Linus Torvalds Signed-off-by: Peter Zijlstra Cc: Paul Mackerras Cc: Paul E. McKenney LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/perf_event.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/kernel/perf_event.c b/kernel/perf_event.c index b782b7a79f00..76be4c7bf08e 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -6494,7 +6494,6 @@ int perf_event_init_context(struct task_struct *child, int ctxn) raw_spin_lock_irqsave(&parent_ctx->lock, flags); parent_ctx->rotate_disable = 0; - raw_spin_unlock_irqrestore(&parent_ctx->lock, flags); child_ctx = child->perf_event_ctxp[ctxn]; @@ -6502,12 +6501,11 @@ int perf_event_init_context(struct task_struct *child, int ctxn) /* * Mark the child context as a clone of the parent * context, or of whatever the parent is a clone of. - * Note that if the parent is a clone, it could get - * uncloned at any point, but that doesn't matter - * because the list of events and the generation - * count can't have changed since we took the mutex. + * + * Note that if the parent is a clone, the holding of + * parent_ctx->lock avoids it from being uncloned. */ - cloned_ctx = rcu_dereference(parent_ctx->parent_ctx); + cloned_ctx = parent_ctx->parent_ctx; if (cloned_ctx) { child_ctx->parent_ctx = cloned_ctx; child_ctx->parent_gen = parent_ctx->parent_gen; @@ -6518,6 +6516,7 @@ int perf_event_init_context(struct task_struct *child, int ctxn) get_ctx(child_ctx->parent_ctx); } + raw_spin_unlock_irqrestore(&parent_ctx->lock, flags); mutex_unlock(&parent_ctx->mutex); perf_unpin_context(parent_ctx); -- cgit v1.2.3