Merge tag 'block-6.13-20241207' of git://git.kernel.dk/linux

Pull block fixes from Jens Axboe:

 - NVMe pull request via Keith:
      - Target fix using incorrect zero buffer (Nilay)
      - Device specifc deallocate quirk fixes (Christoph, Keith)
      - Fabrics fix for handling max command target bugs (Maurizio)
      - Cocci fix usage for kzalloc (Yu-Chen)
      - DMA size fix for host memory buffer feature (Christoph)
      - Fabrics queue cleanup fixes (Chunguang)

 - CPU hotplug ordering fixes

 - Add missing MODULE_DESCRIPTION for rnull

 - bcache error value fix

 - virtio-blk queue freeze fix

* tag 'block-6.13-20241207' of git://git.kernel.dk/linux:
  blk-mq: move cpuhp callback registering out of q->sysfs_lock
  blk-mq: register cpuhp callback after hctx is added to xarray table
  virtio-blk: don't keep queue frozen during system suspend
  nvme-tcp: simplify nvme_tcp_teardown_io_queues()
  nvme-tcp: no need to quiesce admin_q in nvme_tcp_teardown_io_queues()
  nvme-rdma: unquiesce admin_q before destroy it
  nvme-tcp: fix the memleak while create new ctrl failed
  nvme-pci: don't use dma_alloc_noncontiguous with 0 merge boundary
  nvmet: replace kmalloc + memset with kzalloc for data allocation
  nvme-fabrics: handle zero MAXCMD without closing the connection
  bcache: revert replacing IS_ERR_OR_NULL with IS_ERR again
  nvme-pci: remove two deallocate zeroes quirks
  block: rnull: add missing MODULE_DESCRIPTION
  nvme: don't apply NVME_QUIRK_DEALLOCATE_ZEROES when DSM is not supported
  nvmet: use kzalloc instead of ZERO_PAGE in nvme_execute_identify_ns_nvm()

Author: torvalds

block/blk-mq.c

@@ -43,6 +43,7 @@
 
 static DEFINE_PER_CPU(struct llist_head, blk_cpu_done);
 static DEFINE_PER_CPU(call_single_data_t, blk_cpu_csd);
+static DEFINE_MUTEX(blk_mq_cpuhp_lock);
 
 static void blk_mq_insert_request(struct request *rq, blk_insert_t flags);
 static void blk_mq_request_bypass_insert(struct request *rq,
@@ -3739,13 +3740,91 @@ static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node)
 	return 0;
 }
 
-static void blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx)
+static void __blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx)
 {
-	if (!(hctx->flags & BLK_MQ_F_STACKING))
+	lockdep_assert_held(&blk_mq_cpuhp_lock);
+
+	if (!(hctx->flags & BLK_MQ_F_STACKING) &&
+	    !hlist_unhashed(&hctx->cpuhp_online)) {
 		cpuhp_state_remove_instance_nocalls(CPUHP_AP_BLK_MQ_ONLINE,
 						    &hctx->cpuhp_online);
-	cpuhp_state_remove_instance_nocalls(CPUHP_BLK_MQ_DEAD,
-					    &hctx->cpuhp_dead);
+		INIT_HLIST_NODE(&hctx->cpuhp_online);
+	}
+
+	if (!hlist_unhashed(&hctx->cpuhp_dead)) {
+		cpuhp_state_remove_instance_nocalls(CPUHP_BLK_MQ_DEAD,
+						    &hctx->cpuhp_dead);
+		INIT_HLIST_NODE(&hctx->cpuhp_dead);
+	}
+}
+
+static void blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx)
+{
+	mutex_lock(&blk_mq_cpuhp_lock);
+	__blk_mq_remove_cpuhp(hctx);
+	mutex_unlock(&blk_mq_cpuhp_lock);
+}
+
+static void __blk_mq_add_cpuhp(struct blk_mq_hw_ctx *hctx)
+{
+	lockdep_assert_held(&blk_mq_cpuhp_lock);
+
+	if (!(hctx->flags & BLK_MQ_F_STACKING) &&
+	    hlist_unhashed(&hctx->cpuhp_online))
+		cpuhp_state_add_instance_nocalls(CPUHP_AP_BLK_MQ_ONLINE,
+				&hctx->cpuhp_online);
+
+	if (hlist_unhashed(&hctx->cpuhp_dead))
+		cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD,
+				&hctx->cpuhp_dead);
+}
+
+static void __blk_mq_remove_cpuhp_list(struct list_head *head)
+{
+	struct blk_mq_hw_ctx *hctx;
+
+	lockdep_assert_held(&blk_mq_cpuhp_lock);
+
+	list_for_each_entry(hctx, head, hctx_list)
+		__blk_mq_remove_cpuhp(hctx);
+}
+
+/*
+ * Unregister cpuhp callbacks from exited hw queues
+ *
+ * Safe to call if this `request_queue` is live
+ */
+static void blk_mq_remove_hw_queues_cpuhp(struct request_queue *q)
+{
+	LIST_HEAD(hctx_list);
+
+	spin_lock(&q->unused_hctx_lock);
+	list_splice_init(&q->unused_hctx_list, &hctx_list);
+	spin_unlock(&q->unused_hctx_lock);
+
+	mutex_lock(&blk_mq_cpuhp_lock);
+	__blk_mq_remove_cpuhp_list(&hctx_list);
+	mutex_unlock(&blk_mq_cpuhp_lock);
+
+	spin_lock(&q->unused_hctx_lock);
+	list_splice(&hctx_list, &q->unused_hctx_list);
+	spin_unlock(&q->unused_hctx_lock);
+}
+
+/*
+ * Register cpuhp callbacks from all hw queues
+ *
+ * Safe to call if this `request_queue` is live
+ */
+static void blk_mq_add_hw_queues_cpuhp(struct request_queue *q)
+{
+	struct blk_mq_hw_ctx *hctx;
+	unsigned long i;
+
+	mutex_lock(&blk_mq_cpuhp_lock);
+	queue_for_each_hw_ctx(q, hctx, i)
+		__blk_mq_add_cpuhp(hctx);
+	mutex_unlock(&blk_mq_cpuhp_lock);
 }
 
 /*
@@ -3796,8 +3875,6 @@ static void blk_mq_exit_hctx(struct request_queue *q,
 	if (set->ops->exit_hctx)
 		set->ops->exit_hctx(hctx, hctx_idx);
 
-	blk_mq_remove_cpuhp(hctx);
-
 	xa_erase(&q->hctx_table, hctx_idx);
 
 	spin_lock(&q->unused_hctx_lock);
@@ -3814,6 +3891,7 @@ static void blk_mq_exit_hw_queues(struct request_queue *q,
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (i == nr_queue)
 			break;
+		blk_mq_remove_cpuhp(hctx);
 		blk_mq_exit_hctx(q, set, hctx, i);
 	}
 }
@@ -3824,16 +3902,11 @@ static int blk_mq_init_hctx(struct request_queue *q,
 {
 	hctx->queue_num = hctx_idx;
 
-	if (!(hctx->flags & BLK_MQ_F_STACKING))
-		cpuhp_state_add_instance_nocalls(CPUHP_AP_BLK_MQ_ONLINE,
-				&hctx->cpuhp_online);
-	cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead);
-
 	hctx->tags = set->tags[hctx_idx];
 
 	if (set->ops->init_hctx &&
 	    set->ops->init_hctx(hctx, set->driver_data, hctx_idx))
-		goto unregister_cpu_notifier;
+		goto fail;
 
 	if (blk_mq_init_request(set, hctx->fq->flush_rq, hctx_idx,
 				hctx->numa_node))
@@ -3850,8 +3923,7 @@ static int blk_mq_init_hctx(struct request_queue *q,
  exit_hctx:
 	if (set->ops->exit_hctx)
 		set->ops->exit_hctx(hctx, hctx_idx);
- unregister_cpu_notifier:
-	blk_mq_remove_cpuhp(hctx);
+ fail:
 	return -1;
 }
 
@@ -3877,6 +3949,8 @@ blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set,
 	INIT_DELAYED_WORK(&hctx->run_work, blk_mq_run_work_fn);
 	spin_lock_init(&hctx->lock);
 	INIT_LIST_HEAD(&hctx->dispatch);
+	INIT_HLIST_NODE(&hctx->cpuhp_dead);
+	INIT_HLIST_NODE(&hctx->cpuhp_online);
 	hctx->queue = q;
 	hctx->flags = set->flags & ~BLK_MQ_F_TAG_QUEUE_SHARED;
 
@@ -4415,6 +4489,12 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 	xa_for_each_start(&q->hctx_table, j, hctx, j)
 		blk_mq_exit_hctx(q, set, hctx, j);
 	mutex_unlock(&q->sysfs_lock);
+
+	/* unregister cpuhp callbacks for exited hctxs */
+	blk_mq_remove_hw_queues_cpuhp(q);
+
+	/* register cpuhp for new initialized hctxs */
+	blk_mq_add_hw_queues_cpuhp(q);
 }
 
 int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,

drivers/block/rnull.rs

@@ -28,6 +28,7 @@ module! {
     type: NullBlkModule,
     name: "rnull_mod",
     author: "Andreas Hindborg",
+    description: "Rust implementation of the C null block driver",
     license: "GPL v2",
 }
 

drivers/block/virtio_blk.c

@@ -1586,9 +1586,12 @@ static void virtblk_remove(struct virtio_device *vdev)
 static int virtblk_freeze(struct virtio_device *vdev)
 {
 	struct virtio_blk *vblk = vdev->priv;
+	struct request_queue *q = vblk->disk->queue;
 
 	/* Ensure no requests in virtqueues before deleting vqs. */
-	blk_mq_freeze_queue(vblk->disk->queue);
+	blk_mq_freeze_queue(q);
+	blk_mq_quiesce_queue_nowait(q);
+	blk_mq_unfreeze_queue(q);
 
 	/* Ensure we don't receive any more interrupts */
 	virtio_reset_device(vdev);
@@ -1612,8 +1615,8 @@ static int virtblk_restore(struct virtio_device *vdev)
 		return ret;
 
 	virtio_device_ready(vdev);
+	blk_mq_unquiesce_queue(vblk->disk->queue);
 
-	blk_mq_unfreeze_queue(vblk->disk->queue);
 	return 0;
 }
 #endif

drivers/md/bcache/super.c

@@ -1718,7 +1718,7 @@ static CLOSURE_CALLBACK(cache_set_flush)
 	if (!IS_ERR_OR_NULL(c->gc_thread))
 		kthread_stop(c->gc_thread);
 
-	if (!IS_ERR(c->root))
+	if (!IS_ERR_OR_NULL(c->root))
 		list_add(&c->root->list, &c->btree_cache);
 
 	/*

drivers/nvme/host/core.c

@@ -2071,7 +2071,8 @@ static bool nvme_update_disk_info(struct nvme_ns *ns, struct nvme_id_ns *id,
 	lim->physical_block_size = min(phys_bs, atomic_bs);
 	lim->io_min = phys_bs;
 	lim->io_opt = io_opt;
-	if (ns->ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES)
+	if ((ns->ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES) &&
+	    (ns->ctrl->oncs & NVME_CTRL_ONCS_DSM))
 		lim->max_write_zeroes_sectors = UINT_MAX;
 	else
 		lim->max_write_zeroes_sectors = ns->ctrl->max_zeroes_sectors;
@@ -3260,8 +3261,9 @@ static int nvme_check_ctrl_fabric_info(struct nvme_ctrl *ctrl, struct nvme_id_ct
 	}
 
 	if (!ctrl->maxcmd) {
-		dev_err(ctrl->device, "Maximum outstanding commands is 0\n");
-		return -EINVAL;
+		dev_warn(ctrl->device,
+			"Firmware bug: maximum outstanding commands is 0\n");
+		ctrl->maxcmd = ctrl->sqsize + 1;
 	}
 
 	return 0;

drivers/nvme/host/pci.c

@@ -2172,6 +2172,7 @@ static int nvme_alloc_host_mem_multi(struct nvme_dev *dev, u64 preferred,
 
 static int nvme_alloc_host_mem(struct nvme_dev *dev, u64 min, u64 preferred)
 {
+	unsigned long dma_merge_boundary = dma_get_merge_boundary(dev->dev);
 	u64 min_chunk = min_t(u64, preferred, PAGE_SIZE * MAX_ORDER_NR_PAGES);
 	u64 hmminds = max_t(u32, dev->ctrl.hmminds * 4096, PAGE_SIZE * 2);
 	u64 chunk_size;
@@ -2180,7 +2181,7 @@ static int nvme_alloc_host_mem(struct nvme_dev *dev, u64 min, u64 preferred)
 	 * If there is an IOMMU that can merge pages, try a virtually
 	 * non-contiguous allocation for a single segment first.
 	 */
-	if (!(PAGE_SIZE & dma_get_merge_boundary(dev->dev))) {
+	if (dma_merge_boundary && (PAGE_SIZE & dma_merge_boundary) == 0) {
 		if (!nvme_alloc_host_mem_single(dev, preferred))
 			return 0;
 	}
@@ -3588,12 +3589,10 @@ static const struct pci_device_id nvme_id_table[] = {
 				NVME_QUIRK_DEALLOCATE_ZEROES, },
 	{ PCI_VDEVICE(INTEL, 0x0a54),	/* Intel P4500/P4600 */
 		.driver_data = NVME_QUIRK_STRIPE_SIZE |
-				NVME_QUIRK_DEALLOCATE_ZEROES |
 				NVME_QUIRK_IGNORE_DEV_SUBNQN |
 				NVME_QUIRK_BOGUS_NID, },
 	{ PCI_VDEVICE(INTEL, 0x0a55),	/* Dell Express Flash P4600 */
-		.driver_data = NVME_QUIRK_STRIPE_SIZE |
-				NVME_QUIRK_DEALLOCATE_ZEROES, },
+		.driver_data = NVME_QUIRK_STRIPE_SIZE, },
 	{ PCI_VDEVICE(INTEL, 0xf1a5),	/* Intel 600P/P3100 */
 		.driver_data = NVME_QUIRK_NO_DEEPEST_PS |
 				NVME_QUIRK_MEDIUM_PRIO_SQ |

drivers/nvme/host/rdma.c

@@ -1091,13 +1091,7 @@ static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new)
 	}
 destroy_admin:
 	nvme_stop_keep_alive(&ctrl->ctrl);
-	nvme_quiesce_admin_queue(&ctrl->ctrl);
-	blk_sync_queue(ctrl->ctrl.admin_q);
-	nvme_rdma_stop_queue(&ctrl->queues[0]);
-	nvme_cancel_admin_tagset(&ctrl->ctrl);
-	if (new)
-		nvme_remove_admin_tag_set(&ctrl->ctrl);
-	nvme_rdma_destroy_admin_queue(ctrl);
+	nvme_rdma_teardown_admin_queue(ctrl, new);
 	return ret;
 }
 

drivers/nvme/host/tcp.c

@@ -2101,14 +2101,6 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
 	return ret;
 }
 
-static void nvme_tcp_destroy_admin_queue(struct nvme_ctrl *ctrl, bool remove)
-{
-	nvme_tcp_stop_queue(ctrl, 0);
-	if (remove)
-		nvme_remove_admin_tag_set(ctrl);
-	nvme_tcp_free_admin_queue(ctrl);
-}
-
 static int nvme_tcp_configure_admin_queue(struct nvme_ctrl *ctrl, bool new)
 {
 	int error;
@@ -2163,9 +2155,11 @@ static void nvme_tcp_teardown_admin_queue(struct nvme_ctrl *ctrl,
 	blk_sync_queue(ctrl->admin_q);
 	nvme_tcp_stop_queue(ctrl, 0);
 	nvme_cancel_admin_tagset(ctrl);
-	if (remove)
+	if (remove) {
 		nvme_unquiesce_admin_queue(ctrl);
-	nvme_tcp_destroy_admin_queue(ctrl, remove);
+		nvme_remove_admin_tag_set(ctrl);
+	}
+	nvme_tcp_free_admin_queue(ctrl);
 	if (ctrl->tls_pskid) {
 		dev_dbg(ctrl->device, "Wipe negotiated TLS_PSK %08x\n",
 			ctrl->tls_pskid);
@@ -2178,7 +2172,6 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
 {
 	if (ctrl->queue_count <= 1)
 		return;
-	nvme_quiesce_admin_queue(ctrl);
 	nvme_quiesce_io_queues(ctrl);
 	nvme_sync_io_queues(ctrl);
 	nvme_tcp_stop_io_queues(ctrl);
@@ -2278,7 +2271,7 @@ static int nvme_tcp_setup_ctrl(struct nvme_ctrl *ctrl, bool new)
 	}
 destroy_admin:
 	nvme_stop_keep_alive(ctrl);
-	nvme_tcp_teardown_admin_queue(ctrl, false);
+	nvme_tcp_teardown_admin_queue(ctrl, new);
 	return ret;
 }
 

drivers/nvme/target/admin-cmd.c

@@ -902,13 +902,18 @@ static void nvmet_execute_identify_ctrl_nvm(struct nvmet_req *req)
 static void nvme_execute_identify_ns_nvm(struct nvmet_req *req)
 {
 	u16 status;
+	struct nvme_id_ns_nvm *id;
 
 	status = nvmet_req_find_ns(req);
 	if (status)
 		goto out;
 
-	status = nvmet_copy_to_sgl(req, 0, ZERO_PAGE(0),
-				   NVME_IDENTIFY_DATA_SIZE);
+	id = kzalloc(sizeof(*id), GFP_KERNEL);
+	if (!id) {
+		status = NVME_SC_INTERNAL;
+		goto out;
+	}
+	status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id));
 out:
 	nvmet_req_complete(req, status);
 }

drivers/nvme/target/pr.c

@@ -828,12 +828,11 @@ static void nvmet_execute_pr_report(struct nvmet_req *req)
 		goto out;
 	}
 
-	data = kmalloc(num_bytes, GFP_KERNEL);
+	data = kzalloc(num_bytes, GFP_KERNEL);
 	if (!data) {
 		status = NVME_SC_INTERNAL;
 		goto out;
 	}
-	memset(data, 0, num_bytes);
 	data->gen = cpu_to_le32(atomic_read(&pr->generation));
 	data->ptpls = 0;
 	ctrl_eds = data->regctl_eds;