On Thu, Nov 29, 2018 at 08:13:04PM +0100, Christoph Hellwig wrote:
> This is the last place outside of nvme_irq that handles CQEs from
> interrupt context, and thus is in the way of removing the cq_lock for
> normal queues, and avoiding lockdep warnings on the poll queues, for
> which we already take it without IRQ disabling.
>
> Signed-off-by: Christoph Hellwig <hch@xxxxxx>
> ---
> drivers/nvme/host/pci.c | 14 ++++++++++++--
> 1 file changed, 12 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
> index 9ceba9900ca3..fb8db7d8170a 100644
> --- a/drivers/nvme/host/pci.c
> +++ b/drivers/nvme/host/pci.c
> @@ -203,6 +203,7 @@ struct nvme_queue {
> unsigned long flags;
> #define NVMEQ_ENABLED 0
> #define NVMEQ_SQ_CMB 1
> +#define NVMEQ_DELETE_ERROR 2
> u32 *dbbuf_sq_db;
> u32 *dbbuf_cq_db;
> u32 *dbbuf_sq_ei;
> @@ -2216,7 +2217,7 @@ static void nvme_del_cq_end(struct request *req, blk_status_t error)
> struct nvme_queue *nvmeq = req->end_io_data;
>
> if (!error)
> - nvme_poll_irqdisable(nvmeq, -1);
> + set_bit(NVMEQ_DELETE_ERROR, &nvmeq->flags);
>
> nvme_del_queue_end(req, error);
> }
> @@ -2258,11 +2259,20 @@ static bool nvme_disable_io_queues(struct nvme_dev *dev, u8 opcode)
> nr_queues--;
> sent++;
> }
> - while (sent--) {
> + while (sent) {
> + struct nvme_queue *nvmeq = &dev->queues[nr_queues + sent];
> +
> timeout = wait_for_completion_io_timeout(&dev->ioq_wait,
> timeout);
> if (timeout == 0)
> return false;
> +
> + /* handle any remaining CQEs */
> + if (opcode == nvme_admin_delete_cq &&
> + !test_bit(NVMEQ_DELETE_ERROR, &nvmeq->flags))
> + nvme_poll_irqdisable(nvmeq, -1);
We're dispatchig lots of queue deletions in parallel, and they may
complete in any order. I don't see how you can guarantee that the
wait_for_completion() will return for the nvmeq that you're polling.
You also need to clear NVMEQ_DELETE_ERROR somewhere later, maybe in
nvme_init_queue().
