Commit 849c6e77 authored Dec 12, 2014 by Jens Axboe

NVMe: fix race condition in nvme_submit_sync_cmd()



If we have a race between the schedule timing out and the command
completing, we could have the task issuing the command exit
nvme_submit_sync_cmd() while the irq is running sync_completion().
If that happens, we could be corrupting memory, since the stack
that held 'cmdinfo' is no longer valid.

Fix this by always calling nvme_abort_cmd_info(). Once that call
completes, we know that we have either run sync_completion() if
the completion came in, or that we will never run it since we now
have special_completion() as the command callback handler.

Acked-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

parent fe54303e

drivers/block/nvme-core.c

+11 −4

Original line number	Diff line number	Diff line
		@@ -804,12 +804,19 @@ static int nvme_submit_sync_cmd(struct request req, struct nvme_command cmd,
		nvme_finish_cmd(nvmeq, req->tag, NULL);
		set_current_state(TASK_RUNNING);
		}
		schedule_timeout(timeout);
		ret = schedule_timeout(timeout);

		if (cmdinfo.status == -EINTR) {
		/*
		* Ensure that sync_completion has either run, or that it will
		* never run.
		*/
		nvme_abort_cmd_info(nvmeq, blk_mq_rq_to_pdu(req));

		/*
		* We never got the completion
		*/
		if (cmdinfo.status == -EINTR)
		return -EINTR;
		}

		if (result)
		*result = cmdinfo.result;