summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorKeith Busch <keith.busch@intel.com>2015-12-11 13:14:28 -0700
committerJens Axboe <axboe@fb.com>2015-12-22 10:12:04 -0700
commitb5875222de2fb91339db79a753677ba4f68120d0 (patch)
tree458e729691435b753d23e860f7e76d6e0fbdf922
parentaf096e2235c5de76af7e8749f59a90de07f5e943 (diff)
NVMe: IO ending fixes on surprise removal
This patch fixes a lost request discovered during IO + hot removal. The driver's pci removal deletes gendisks prior to shutting down the controller to allow dirty data to sync. Dirty data can not be synced on a surprise removal, though, and would potentially block indefinitely. The driver previously had marked the queue as dying in this scenario to prevent new requests from attempting, however it will still block for requests that already entered the queue. This patch fixes this by quiescing IO first, then aborting the requeued requests before deleting disks. Reported-by: Sujith Pandel <sujith_pandel@dell.com> Signed-off-by: Keith Busch <keith.busch@intel.com> Tested-by: Sujith Pandel <sujith_pandel@dell.com> Signed-off-by: Jens Axboe <axboe@fb.com>
-rw-r--r--drivers/nvme/host/pci.c20
1 files changed, 19 insertions, 1 deletions
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 9e294ff4e652..0c67b57be83c 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2540,8 +2540,17 @@ static void nvme_ns_remove(struct nvme_ns *ns)
{
bool kill = nvme_io_incapable(ns->dev) && !blk_queue_dying(ns->queue);
- if (kill)
+ if (kill) {
blk_set_queue_dying(ns->queue);
+
+ /*
+ * The controller was shutdown first if we got here through
+ * device removal. The shutdown may requeue outstanding
+ * requests. These need to be aborted immediately so
+ * del_gendisk doesn't block indefinitely for their completion.
+ */
+ blk_mq_abort_requeue_list(ns->queue);
+ }
if (ns->disk->flags & GENHD_FL_UP)
del_gendisk(ns->disk);
if (kill || !blk_queue_dying(ns->queue)) {
@@ -2977,6 +2986,15 @@ static void nvme_dev_remove(struct nvme_dev *dev)
{
struct nvme_ns *ns, *next;
+ if (nvme_io_incapable(dev)) {
+ /*
+ * If the device is not capable of IO (surprise hot-removal,
+ * for example), we need to quiesce prior to deleting the
+ * namespaces. This will end outstanding requests and prevent
+ * attempts to sync dirty data.
+ */
+ nvme_dev_shutdown(dev);
+ }
list_for_each_entry_safe(ns, next, &dev->namespaces, list)
nvme_ns_remove(ns);
}