Merge tag 'nvme-5.16-2021-12-10' of git://git.infradead.org/nvme into block-5.16

Pull NVMe fixes from Christoph:

"nvme fixes for Linux 5.16

 - set ana_log_size to 0 after freeing ana_log_buf (Hou Tao)
 - show subsys nqn for duplicate cntlids (Keith Busch)
 - disable namespace access for unsupported metadata (Keith Busch)
 - report write pointer for a full zone as zone start + zone len
   (Niklas Cassel)
 - fix use after free when disconnecting a reconnecting ctrl
   (Ruozhu Li)
 - fix a list corruption in nvmet-tcp (Sagi Grimberg)"

* tag 'nvme-5.16-2021-12-10' of git://git.infradead.org/nvme:
  nvmet-tcp: fix possible list corruption for unexpected command failure
  nvme: fix use after free when disconnecting a reconnecting ctrl
  nvme-multipath: set ana_log_size to 0 after free ana_log_buf
  nvme: report write pointer for a full zone as zone start + zone len
  nvme: disable namespace access for unsupported metadata
  nvme: show subsys nqn for duplicate cntlids

5 files changed, 33 insertions, 9 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 4c63564adeaa..1af8a4513708 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -666,6 +666,7 @@ blk_status_t nvme_fail_nonready_command(struct nvme_ctrl *ctrl,
 		struct request *rq)
 {
 	if (ctrl->state != NVME_CTRL_DELETING_NOIO &&
+	    ctrl->state != NVME_CTRL_DELETING &&
 	    ctrl->state != NVME_CTRL_DEAD &&
 	    !test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags) &&
 	    !blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
@@ -1749,9 +1750,20 @@ static int nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id)
 		 */
 		if (WARN_ON_ONCE(!(id->flbas & NVME_NS_FLBAS_META_EXT)))
 			return -EINVAL;
-		if (ctrl->max_integrity_segments)
-			ns->features |=
-				(NVME_NS_METADATA_SUPPORTED | NVME_NS_EXT_LBAS);
+
+		ns->features |= NVME_NS_EXT_LBAS;
+
+		/*
+		 * The current fabrics transport drivers support namespace
+		 * metadata formats only if nvme_ns_has_pi() returns true.
+		 * Suppress support for all other formats so the namespace will
+		 * have a 0 capacity and not be usable through the block stack.
+		 *
+		 * Note, this check will need to be modified if any drivers
+		 * gain the ability to use other metadata formats.
+		 */
+		if (ctrl->max_integrity_segments && nvme_ns_has_pi(ns))
+			ns->features |= NVME_NS_METADATA_SUPPORTED;
 	} else {
 		/*
 		 * For PCIe controllers, we can't easily remap the separate
@@ -2696,8 +2708,9 @@ static bool nvme_validate_cntlid(struct nvme_subsystem *subsys,
 
 		if (tmp->cntlid == ctrl->cntlid) {
 			dev_err(ctrl->device,
-				"Duplicate cntlid %u with %s, rejecting\n",
-				ctrl->cntlid, dev_name(tmp->device));
+				"Duplicate cntlid %u with %s, subsys %s, rejecting\n",
+				ctrl->cntlid, dev_name(tmp->device),
+				subsys->subnqn);
 			return false;
 		}
 
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 7f2071f2460c..13e5d503ed07 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -866,7 +866,7 @@ int nvme_mpath_init_identify(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 	}
 	if (ana_log_size > ctrl->ana_log_size) {
 		nvme_mpath_stop(ctrl);
-		kfree(ctrl->ana_log_buf);
+		nvme_mpath_uninit(ctrl);
 		ctrl->ana_log_buf = kmalloc(ana_log_size, GFP_KERNEL);
 		if (!ctrl->ana_log_buf)
 			return -ENOMEM;
@@ -886,4 +886,5 @@ void nvme_mpath_uninit(struct nvme_ctrl *ctrl)
 {
 	kfree(ctrl->ana_log_buf);
 	ctrl->ana_log_buf = NULL;
+	ctrl->ana_log_size = 0;
 }
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index b334af8aa264..9b095ee01364 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -709,7 +709,7 @@ static inline bool nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
 		return true;
 	if (ctrl->ops->flags & NVME_F_FABRICS &&
 	    ctrl->state == NVME_CTRL_DELETING)
-		return true;
+		return queue_live;
 	return __nvme_check_ready(ctrl, rq, queue_live);
 }
 int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c
index bfc259e0d7b8..9f81beb4df4e 100644
--- a/drivers/nvme/host/zns.c
+++ b/drivers/nvme/host/zns.c
@@ -166,7 +166,10 @@ static int nvme_zone_parse_entry(struct nvme_ns *ns,
 	zone.len = ns->zsze;
 	zone.capacity = nvme_lba_to_sect(ns, le64_to_cpu(entry->zcap));
 	zone.start = nvme_lba_to_sect(ns, le64_to_cpu(entry->zslba));
-	zone.wp = nvme_lba_to_sect(ns, le64_to_cpu(entry->wp));
+	if (zone.cond == BLK_ZONE_COND_FULL)
+		zone.wp = zone.start + zone.len;
+	else
+		zone.wp = nvme_lba_to_sect(ns, le64_to_cpu(entry->wp));
 
 	return cb(&zone, idx, data);
 }
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index cb6a473c3eaf..7c1c43ce466b 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -922,7 +922,14 @@ static void nvmet_tcp_handle_req_failure(struct nvmet_tcp_queue *queue,
 	size_t data_len = le32_to_cpu(req->cmd->common.dptr.sgl.length);
 	int ret;
 
-	if (!nvme_is_write(cmd->req.cmd) ||
+	/*
+	 * This command has not been processed yet, hence we are trying to
+	 * figure out if there is still pending data left to receive. If
+	 * we don't, we can simply prepare for the next pdu and bail out,
+	 * otherwise we will need to prepare a buffer and receive the
+	 * stale data before continuing forward.
+	 */
+	if (!nvme_is_write(cmd->req.cmd) || !data_len ||
 	    data_len > cmd->req.port->inline_data_size) {
 		nvmet_prepare_receive_pdu(queue);
 		return;