[PATCH 5/5] nvme: Add two-pass shutdown support.
Sagi Grimberg
sagi at grimberg.me
Tue Jan 30 03:15:43 PST 2024
> This works with the two-pass shutdown mechanism setup for the PCI
> drivers and participates to provide the shutdown_wait
> method at the pci_driver structure level.
>
> This patch changes the nvme shutdown() method to pass
> down the NVME_PCI_DISABLE_SHUTDOWN_TWOPASS enum value instead
> of NVME_PCI_DISABLE_SHUTDOWN. nvme_dev_disable() is changed
> to call nvme_request_shutdown() instead of nvme_disable_ctrl()
> in this case.
>
> nvme_request_shutdown() sets the shutdown bit,
> but does not wait for completion.
>
> The nvme_shutdown_wait() callback is added to synchronously
> wait for the NVME_CSTS_SHST_CMPLT bit meaning the nvme
> device has shutdown.
>
> This change speeds up the shutdown in a system which hosts
> many controllers.
>
> Based on work by Tanjore Suresh <tansuresh at google.com>
>
> Signed-off-by: Jeremy Allison <jallison at ciq.com>
> ---
> drivers/nvme/host/pci.c | 39 ++++++++++++++++++++++++++++++++++++---
> 1 file changed, 36 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
> index 8ee77f755d9d..bbd89eecf05a 100644
> --- a/drivers/nvme/host/pci.c
> +++ b/drivers/nvme/host/pci.c
> @@ -2607,7 +2607,14 @@ static void nvme_dev_disable(struct nvme_dev *dev,
>
> if (!dead && dev->ctrl.queue_count > 0) {
> nvme_delete_io_queues(dev);
> - nvme_disable_ctrl(&dev->ctrl, shutdown);
> + /*
> + * NVME_PCI_DISABLE_SHUTDOWN_TWOPASS requests shutdown
> + * but doesn't wait for completion.
> + */
> + if (shutdown_type == NVME_PCI_DISABLE_SHUTDOWN_TWOPASS)
> + nvme_request_shutdown(&dev->ctrl);
> + else
> + nvme_disable_ctrl(&dev->ctrl, shutdown);
> nvme_poll_irqdisable(&dev->queues[0]);
> }
> nvme_suspend_io_queues(dev);
> @@ -2625,7 +2632,7 @@ static void nvme_dev_disable(struct nvme_dev *dev,
> * must flush all entered requests to their failed completion to avoid
> * deadlocking blk-mq hot-cpu notifier.
> */
> - if (shutdown) {
> + if (shutdown_type == NVME_PCI_DISABLE_SHUTDOWN) {
> nvme_unquiesce_io_queues(&dev->ctrl);
> if (dev->ctrl.admin_q && !blk_queue_dying(dev->ctrl.admin_q))
> nvme_unquiesce_admin_queue(&dev->ctrl);
> @@ -3128,7 +3135,32 @@ static void nvme_shutdown(struct pci_dev *pdev)
> {
> struct nvme_dev *dev = pci_get_drvdata(pdev);
>
> - nvme_disable_prepare_reset(dev, NVME_PCI_DISABLE_SHUTDOWN);
> + nvme_disable_prepare_reset(dev, NVME_PCI_DISABLE_SHUTDOWN_TWOPASS);
> +}
> +
> +static void nvme_shutdown_wait(struct pci_dev *pdev)
> +{
> + struct nvme_dev *dev = pci_get_drvdata(pdev);
> +
> + mutex_lock(&dev->shutdown_lock);
General question that just came up, is there any risk here that the
shutdown_lock is released and re-taken later while the shutdown is still
in progress? I don't spot anything immediate, but perhaps Keith can
comment?
If this change does expose us to potential issues, you can simply
release the shutdown_lock here (while taking it in ?
> + /*
> + * Finish waiting for the shutdown request
> + * initiated in nvme_shutdown() above using
> + * NVME_PCI_DISABLE_SHUTDOWN_TWOPASS.
> + */
> + nvme_wait_ready(&dev->ctrl, NVME_CSTS_SHST_MASK,
> + NVME_CSTS_SHST_CMPLT,
> + dev->ctrl.shutdown_timeout, "shutdown");
> + /*
> + * The driver will not be starting up queues again if shutting down so
> + * must flush all entered requests to their failed completion to avoid
> + * deadlocking blk-mq hot-cpu notifier.
> + */
> + nvme_unquiesce_io_queues(&dev->ctrl);
> + if (dev->ctrl.admin_q && !blk_queue_dying(dev->ctrl.admin_q))
> + nvme_unquiesce_admin_queue(&dev->ctrl);
> +
> + mutex_unlock(&dev->shutdown_lock);
> }
>
> /*
> @@ -3522,6 +3554,7 @@ static struct pci_driver nvme_driver = {
> .probe = nvme_probe,
> .remove = nvme_remove,
> .shutdown = nvme_shutdown,
> + .shutdown_wait = nvme_shutdown_wait,
> .driver = {
> .probe_type = PROBE_PREFER_ASYNCHRONOUS,
> #ifdef CONFIG_PM_SLEEP
More information about the Linux-nvme
mailing list