From b5e683d5cab8cd433b06ae178621f083cabd4f63 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 2 Feb 2020 08:23:03 -0700 Subject: eventfd: track eventfd_signal() recursion depth eventfd use cases from aio and io_uring can deadlock due to circular or resursive calling, when eventfd_signal() tries to grab the waitqueue lock. On top of that, it's also possible to construct notification chains that are deep enough that we could blow the stack. Add a percpu counter that tracks the percpu recursion depth, warn if we exceed it. The counter is also exposed so that users of eventfd_signal() can do the right thing if it's non-zero in the context where it is called. Cc: stable@vger.kernel.org # 4.19+ Signed-off-by: Jens Axboe --- fs/eventfd.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'fs/eventfd.c') diff --git a/fs/eventfd.c b/fs/eventfd.c index 8aa0ea8c55e8..78e41c7c3d05 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -24,6 +24,8 @@ #include #include +DEFINE_PER_CPU(int, eventfd_wake_count); + static DEFINE_IDA(eventfd_ida); struct eventfd_ctx { @@ -60,12 +62,25 @@ __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n) { unsigned long flags; + /* + * Deadlock or stack overflow issues can happen if we recurse here + * through waitqueue wakeup handlers. If the caller users potentially + * nested waitqueues with custom wakeup handlers, then it should + * check eventfd_signal_count() before calling this function. If + * it returns true, the eventfd_signal() call should be deferred to a + * safe context. + */ + if (WARN_ON_ONCE(this_cpu_read(eventfd_wake_count))) + return 0; + spin_lock_irqsave(&ctx->wqh.lock, flags); + this_cpu_inc(eventfd_wake_count); if (ULLONG_MAX - ctx->count < n) n = ULLONG_MAX - ctx->count; ctx->count += n; if (waitqueue_active(&ctx->wqh)) wake_up_locked_poll(&ctx->wqh, EPOLLIN); + this_cpu_dec(eventfd_wake_count); spin_unlock_irqrestore(&ctx->wqh.lock, flags); return n; -- cgit v1.2.3