From 5b90fbe875a9eb1449e96cfe09c40bebc94cc937 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 3 Feb 2020 10:33:42 -0700 Subject: [PATCH 2271/2944] aio: prevent potential eventfd recursion on poll to #31501361 commit 01d7a356872eec22ef34a33a5f9cfa917d145468 upstream. If we have nested or circular eventfd wakeups, then we can deadlock if we run them inline from our poll waitqueue wakeup handler. It's also possible to have very long chains of notifications, to the extent where we could risk blowing the stack. Check the eventfd recursion count before calling eventfd_signal(). If it's non-zero, then punt the signaling to async context. This is always safe, as it takes us out-of-line in terms of stack and locking context. Cc: stable@vger.kernel.org # 4.19+ Reviewed-by: Jeff Moyer Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman Signed-off-by: Jeffle Xu Acked-by: Joseph Qi --- fs/aio.c | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) diff --git a/fs/aio.c b/fs/aio.c index 2a5ea34..a762df3 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -1601,6 +1601,14 @@ static int aio_fsync(struct fsync_iocb *req, const struct iocb *iocb, return 0; } +static void aio_poll_put_work(struct work_struct *work) +{ + struct poll_iocb *req = container_of(work, struct poll_iocb, work); + struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll); + + iocb_put(iocb); +} + static void aio_poll_complete_work(struct work_struct *work) { struct poll_iocb *req = container_of(work, struct poll_iocb, work); @@ -1665,6 +1673,8 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, list_del_init(&req->wait.entry); if (mask && spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) { + struct kioctx *ctx = iocb->ki_ctx; + /* * Try to complete the iocb inline if we can. Use * irqsave/irqrestore because not all filesystems (e.g. fuse) @@ -1674,8 +1684,14 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, list_del(&iocb->ki_list); iocb->ki_res.res = mangle_poll(mask); req->done = true; - spin_unlock_irqrestore(&iocb->ki_ctx->ctx_lock, flags); - iocb_put(iocb); + if (iocb->ki_eventfd && eventfd_signal_count()) { + iocb = NULL; + INIT_WORK(&req->work, aio_poll_put_work); + schedule_work(&req->work); + } + spin_unlock_irqrestore(&ctx->ctx_lock, flags); + if (iocb) + iocb_put(iocb); } else { schedule_work(&req->work); } -- 1.8.3.1