nvme: implement multipath access to nvme subsystems

This patch adds native multipath support to the nvme driver.  For each
namespace we create only single block device node, which can be used
to access that namespace through any of the controllers that refer to it.
The gendisk for each controllers path to the name space still exists
inside the kernel, but is hidden from userspace.  The character device
nodes are still available on a per-controller basis.  A new link from
the sysfs directory for the subsystem allows to find all controllers
for a given subsystem.

Currently we will always send I/O to the first available path, this will
be changed once the NVMe Asynchronous Namespace Access (ANA) TP is
ratified and implemented, at which point we will look at the ANA state
for each namespace.  Another possibility that was prototyped is to
use the path that is closes to the submitting NUMA code, which will be
mostly interesting for PCI, but might also be useful for RDMA or FC
transports in the future.  There is not plan to implement round robin
or I/O service time path selectors, as those are not scalable with
the performance rates provided by NVMe.

The multipath device will go away once all paths to it disappear,
any delay to keep it alive needs to be implemented at the controller
level.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 57 insertions, 0 deletions

diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 6e5004b00975..dd6ced664b45 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -95,6 +95,11 @@ struct nvme_request {
 	u16			status;
 };
 
+/*
+ * Mark a bio as coming in through the mpath node.
+ */
+#define REQ_NVME_MPATH		REQ_DRV
+
 enum {
 	NVME_REQ_CANCELLED		= (1 << 0),
 };
@@ -235,6 +240,13 @@ struct nvme_ns_ids {
  * only ever has a single entry for private namespaces.
  */
 struct nvme_ns_head {
+#ifdef CONFIG_NVME_MULTIPATH
+	struct gendisk		*disk;
+	struct nvme_ns __rcu	*current_path;
+	struct bio_list		requeue_list;
+	spinlock_t		requeue_lock;
+	struct work_struct	requeue_work;
+#endif
 	struct list_head	list;
 	struct srcu_struct      srcu;
 	struct nvme_subsystem	*subsys;
@@ -384,6 +396,51 @@ int nvme_reset_ctrl(struct nvme_ctrl *ctrl);
 int nvme_delete_ctrl(struct nvme_ctrl *ctrl);
 int nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl);
 
+extern const struct block_device_operations nvme_ns_head_ops;
+
+#ifdef CONFIG_NVME_MULTIPATH
+void nvme_failover_req(struct request *req);
+bool nvme_req_needs_failover(struct request *req);
+void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl);
+int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,struct nvme_ns_head *head);
+void nvme_mpath_add_disk(struct nvme_ns_head *head);
+void nvme_mpath_remove_disk(struct nvme_ns_head *head);
+
+static inline void nvme_mpath_clear_current_path(struct nvme_ns *ns)
+{
+	struct nvme_ns_head *head = ns->head;
+
+	if (head && ns == srcu_dereference(head->current_path, &head->srcu))
+		rcu_assign_pointer(head->current_path, NULL);
+}
+struct nvme_ns *nvme_find_path(struct nvme_ns_head *head);
+#else
+static inline void nvme_failover_req(struct request *req)
+{
+}
+static inline bool nvme_req_needs_failover(struct request *req)
+{
+	return false;
+}
+static inline void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
+{
+}
+static inline int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,
+		struct nvme_ns_head *head)
+{
+	return 0;
+}
+static inline void nvme_mpath_add_disk(struct nvme_ns_head *head)
+{
+}
+static inline void nvme_mpath_remove_disk(struct nvme_ns_head *head)
+{
+}
+static inline void nvme_mpath_clear_current_path(struct nvme_ns *ns)
+{
+}
+#endif /* CONFIG_NVME_MULTIPATH */
+
 #ifdef CONFIG_NVM
 int nvme_nvm_register(struct nvme_ns *ns, char *disk_name, int node);
 void nvme_nvm_unregister(struct nvme_ns *ns);