6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jens Axboe axboe@kernel.dk
Commit 9ce6c9875f3e995be5fd720b65835291f8a609b1 upstream.
Currently NVMe uring_cmd completions will complete locally, if they are polled. This is done because those completions are always invoked from task context. And while that is true, there's no guarantee that it's invoked under the right ring context, or even task. If someone does NVMe passthrough via multiple threads and with a limited number of poll queues, then ringA may find completions from ringB. For that case, completing the request may not be sound.
Always just punt the passthrough completions via task_work, which will redirect the completion, if needed.
Cc: stable@vger.kernel.org Fixes: 585079b6e425 ("nvme: wire up async polling for io passthrough commands") Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/nvme/host/ioctl.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-)
--- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -526,16 +526,14 @@ static enum rq_end_io_ret nvme_uring_cmd pdu->u.result = le64_to_cpu(nvme_req(req)->result.u64);
/* - * For iopoll, complete it directly. - * Otherwise, move the completion to task work. + * IOPOLL could potentially complete this request directly, but + * if multiple rings are polling on the same queue, then it's possible + * for one ring to find completions for another ring. Punting the + * completion via task_work will always direct it to the right + * location, rather than potentially complete requests for ringA + * under iopoll invocations from ringB. */ - if (blk_rq_is_poll(req)) { - WRITE_ONCE(ioucmd->cookie, NULL); - nvme_uring_task_cb(ioucmd, IO_URING_F_UNLOCKED); - } else { - io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb); - } - + io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb); return RQ_END_IO_FREE; }