Merge tag 'block-5.14-2021-07-24' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:

 - NVMe pull request (Christoph):
    - tracing fix (Keith Busch)
    - fix multipath head refcounting (Hannes Reinecke)
    - Write Zeroes vs PI fix (me)
    - drop a bogus WARN_ON (Zhihao Cheng)

 - Increase max blk-cgroup policy size, now that mq-deadline
   uses it too (Oleksandr)

* tag 'block-5.14-2021-07-24' of git://git.kernel.dk/linux-block:
  nvme: set the PRACT bit when using Write Zeroes with T10 PI
  nvme: fix nvme_setup_command metadata trace event
  nvme: fix refcounting imbalance when all paths are down
  nvme-pci: don't WARN_ON in nvme_reset_work if ctrl.state is not RESETTING
  block: increase BLKCG_MAX_POLS

drivers/nvme/host/core.c

@@ -900,6 +900,9 @@ static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns,
 		cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req)));
 	cmnd->write_zeroes.length =
 		cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
+	if (nvme_ns_has_pi(ns))
+		cmnd->write_zeroes.control = cpu_to_le16(NVME_RW_PRINFO_PRACT);
+	else
 		cmnd->write_zeroes.control = 0;
 	return BLK_STS_OK;
 }
@@ -3807,6 +3810,8 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid,
 
 static void nvme_ns_remove(struct nvme_ns *ns)
 {
+	bool last_path = false;
+
 	if (test_and_set_bit(NVME_NS_REMOVING, &ns->flags))
 		return;
 
@@ -3815,8 +3820,6 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 
 	mutex_lock(&ns->ctrl->subsys->lock);
 	list_del_rcu(&ns->siblings);
-	if (list_empty(&ns->head->list))
-		list_del_init(&ns->head->entry);
 	mutex_unlock(&ns->ctrl->subsys->lock);
 
 	synchronize_rcu(); /* guarantee not available in head->list */
@@ -3836,7 +3839,15 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 	list_del_init(&ns->list);
 	up_write(&ns->ctrl->namespaces_rwsem);
 
-	nvme_mpath_check_last_path(ns);
+	/* Synchronize with nvme_init_ns_head() */
+	mutex_lock(&ns->head->subsys->lock);
+	if (list_empty(&ns->head->list)) {
+		list_del_init(&ns->head->entry);
+		last_path = true;
+	}
+	mutex_unlock(&ns->head->subsys->lock);
+	if (last_path)
+		nvme_mpath_shutdown_disk(ns->head);
 	nvme_put_ns(ns);
 }
 

drivers/nvme/host/multipath.c

@@ -760,14 +760,21 @@ void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id)
 #endif
 }
 
-void nvme_mpath_remove_disk(struct nvme_ns_head *head)
+void nvme_mpath_shutdown_disk(struct nvme_ns_head *head)
 {
 	if (!head->disk)
 		return;
+	kblockd_schedule_work(&head->requeue_work);
 	if (head->disk->flags & GENHD_FL_UP) {
 		nvme_cdev_del(&head->cdev, &head->cdev_device);
 		del_gendisk(head->disk);
 	}
+}
+
+void nvme_mpath_remove_disk(struct nvme_ns_head *head)
+{
+	if (!head->disk)
+		return;
 	blk_set_queue_dying(head->disk->queue);
 	/* make sure all pending bios are cleaned up */
 	kblockd_schedule_work(&head->requeue_work);

drivers/nvme/host/nvme.h

@@ -716,14 +716,7 @@ void nvme_mpath_uninit(struct nvme_ctrl *ctrl);
 void nvme_mpath_stop(struct nvme_ctrl *ctrl);
 bool nvme_mpath_clear_current_path(struct nvme_ns *ns);
 void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl);
-
-static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
-{
-	struct nvme_ns_head *head = ns->head;
-
-	if (head->disk && list_empty(&head->list))
-		kblockd_schedule_work(&head->requeue_work);
-}
+void nvme_mpath_shutdown_disk(struct nvme_ns_head *head);
 
 static inline void nvme_trace_bio_complete(struct request *req)
 {
@@ -772,7 +765,7 @@ static inline bool nvme_mpath_clear_current_path(struct nvme_ns *ns)
 static inline void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl)
 {
 }
-static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
+static inline void nvme_mpath_shutdown_disk(struct nvme_ns_head *head)
 {
 }
 static inline void nvme_trace_bio_complete(struct request *req)

drivers/nvme/host/pci.c

@@ -2631,7 +2631,9 @@ static void nvme_reset_work(struct work_struct *work)
 	bool was_suspend = !!(dev->ctrl.ctrl_config & NVME_CC_SHN_NORMAL);
 	int result;
 
-	if (WARN_ON(dev->ctrl.state != NVME_CTRL_RESETTING)) {
+	if (dev->ctrl.state != NVME_CTRL_RESETTING) {
+		dev_warn(dev->ctrl.device, "ctrl state %d is not RESETTING\n",
+			 dev->ctrl.state);
 		result = -ENODEV;
 		goto out;
 	}

drivers/nvme/host/trace.h

@@ -56,7 +56,7 @@ TRACE_EVENT(nvme_setup_cmd,
 		__field(u8, fctype)
 		__field(u16, cid)
 		__field(u32, nsid)
-		__field(u64, metadata)
+		__field(bool, metadata)
 		__array(u8, cdw10, 24)
 	    ),
 	    TP_fast_assign(
@@ -66,13 +66,13 @@ TRACE_EVENT(nvme_setup_cmd,
 		__entry->flags = cmd->common.flags;
 		__entry->cid = cmd->common.command_id;
 		__entry->nsid = le32_to_cpu(cmd->common.nsid);
-		__entry->metadata = le64_to_cpu(cmd->common.metadata);
+		__entry->metadata = !!blk_integrity_rq(req);
 		__entry->fctype = cmd->fabrics.fctype;
 		__assign_disk_name(__entry->disk, req->rq_disk);
 		memcpy(__entry->cdw10, &cmd->common.cdw10,
 			sizeof(__entry->cdw10));
 	    ),
-	    TP_printk("nvme%d: %sqid=%d, cmdid=%u, nsid=%u, flags=0x%x, meta=0x%llx, cmd=(%s %s)",
+	    TP_printk("nvme%d: %sqid=%d, cmdid=%u, nsid=%u, flags=0x%x, meta=0x%x, cmd=(%s %s)",
 		      __entry->ctrl_id, __print_disk_name(__entry->disk),
 		      __entry->qid, __entry->cid, __entry->nsid,
 		      __entry->flags, __entry->metadata,

include/linux/blkdev.h

@@ -57,7 +57,7 @@ struct blk_keyslot_manager;
  * Maximum number of blkcg policies allowed to be registered concurrently.
  * Defined here to simplify include dependency.
  */
-#define BLKCG_MAX_POLS		5
+#define BLKCG_MAX_POLS		6
 
 typedef void (rq_end_io_fn)(struct request *, blk_status_t);