Drain requests all go through io_drain_req, which has a quick exit in case there is nothing pending (ie the drain is not useful). In that case it can run the issue the request immediately.
However for safety it queues it through task work. The problem is that in this case the request is run asynchronously, but the async work has not been prepared through io_req_prep_async.
This has not been a problem up to now, as the task work always would run before returning to userspace, and so the user would not have a chance to race with it.
However - with IORING_SETUP_DEFER_TASKRUN - this is no longer the case and the work might be defered, giving userspace a chance to change data being referred to in the request.
Instead _always_ prep_async for drain requests, which is simpler anyway and removes this issue.
Cc: stable@vger.kernel.org Fixes: c0e0d6ba25f1 ("io_uring: add IORING_SETUP_DEFER_TASKRUN") Signed-off-by: Dylan Yudaken dylany@meta.com ---
Hi,
Worth pointing out in discussion with Pavel that we considered just removing the fast path in io_drain_req. That felt like more of an invasive change as it can add an extra kmalloc + io_prep_async_link(), but perhaps you feel that is a better approach.
I'll send out a liburing test shortly.
Dylan
io_uring/io_uring.c | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-)
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 0a4efada9b3c..db623b3185c8 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -1765,17 +1765,12 @@ static __cold void io_drain_req(struct io_kiocb *req) } spin_unlock(&ctx->completion_lock);
- ret = io_req_prep_async(req); - if (ret) { -fail: - io_req_defer_failed(req, ret); - return; - } io_prep_async_link(req); de = kmalloc(sizeof(*de), GFP_KERNEL); if (!de) { ret = -ENOMEM; - goto fail; + io_req_defer_failed(req, ret); + return; }
spin_lock(&ctx->completion_lock); @@ -2048,13 +2043,16 @@ static void io_queue_sqe_fallback(struct io_kiocb *req) req->flags &= ~REQ_F_HARDLINK; req->flags |= REQ_F_LINK; io_req_defer_failed(req, req->cqe.res); - } else if (unlikely(req->ctx->drain_active)) { - io_drain_req(req); } else { int ret = io_req_prep_async(req);
- if (unlikely(ret)) + if (unlikely(ret)) { io_req_defer_failed(req, ret); + return; + } + + if (unlikely(req->ctx->drain_active)) + io_drain_req(req); else io_queue_iowq(req, NULL); }
base-commit: b00c51ef8f72ced0965d021a291b98ff822c5337