[PATCH for-4.5 11/13] NVMe: Dead namespace handling

[Keith Busch]

This adds a "dead" state to a namespace and revalidates such a namespace
to 0 capacity. This will force buffered writers to stop writing pages
that can't be synced, and ends requests in failure if any is submitted
to such a namespace.

Signed-off-by: Keith Busch <keith.busch at intel.com>
---
 drivers/nvme/host/core.c |  4 ++++
 drivers/nvme/host/nvme.h |  1 +
 drivers/nvme/host/pci.c  | 12 +++++++++++-
 3 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 41b595c..84e9f41 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -560,6 +560,10 @@ static int nvme_revalidate_disk(struct gendisk *disk)
 	u16 old_ms;
 	unsigned short bs;
 
+	if (test_bit(NVME_NS_DEAD, &ns->flags)) {
+		set_capacity(disk, 0);
+		return -ENODEV;
+	}
 	if (nvme_identify_ns(ns->ctrl, ns->ns_id, &id)) {
 		dev_warn(ns->ctrl->dev, "%s: Identify failure nvme%dn%d\n",
 				__func__, ns->ctrl->instance, ns->ns_id);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 19a64b2..e4b4110 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -117,6 +117,7 @@ struct nvme_ns {
 	unsigned long flags;
 
 #define NVME_NS_REMOVING 0
+#define NVME_NS_DEAD     1
 
 	u64 mode_select_num_blocks;
 	u32 mode_select_block_len;
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index a18e4ab..7fd8a54 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -678,7 +678,9 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 	spin_lock_irq(&nvmeq->q_lock);
 	if (unlikely(nvmeq->cq_vector < 0)) {
-		ret = BLK_MQ_RQ_QUEUE_BUSY;
+		ret = test_bit(NVME_NS_DEAD, &ns->flags) ?
+					BLK_MQ_RQ_QUEUE_ERROR :
+					BLK_MQ_RQ_QUEUE_BUSY;
 		spin_unlock_irq(&nvmeq->q_lock);
 		goto out;
 	}
@@ -1910,6 +1912,14 @@ static void nvme_kill_ns_queues(struct nvme_dev *dev)
 		if (!kref_get_unless_zero(&ns->kref))
 			continue;
 
+		/*
+		 * Revalidating a dead namespace sets capacity to 0. This will
+		 * end buffered writers dirtying more pages that can't be
+		 * synced.
+		 */
+		if (!test_and_set_bit(NVME_NS_DEAD, &ns->flags))
+			revalidate_disk(ns->disk);
+
 		blk_set_queue_dying(ns->queue);
 		blk_mq_abort_requeue_list(ns->queue);
 		blk_mq_start_stopped_hw_queues(ns->queue, true);
-- 
2.6.2.307.g37023ba