Merge tag 'block-6.10-20240523' of git://git.kernel.dk/linux

Pull more block updates from Jens Axboe:
 "Followup block updates, mostly due to NVMe being a bit late to the
  party. But nothing major in there, so not a big deal.

  In detail, this contains:

   - NVMe pull request via Keith:
       - Fabrics connection retries (Daniel, Hannes)
       - Fabrics logging enhancements (Tokunori)
       - RDMA delete optimization (Sagi)

   - ublk DMA alignment fix (me)

   - null_blk sparse warning fixes (Bart)

   - Discard support for brd (Keith)

   - blk-cgroup list corruption fixes (Ming)

   - blk-cgroup stat propagation fix (Waiman)

   - Regression fix for plugging stall with md (Yu)

   - Misc fixes or cleanups (David, Jeff, Justin)"

* tag 'block-6.10-20240523' of git://git.kernel.dk/linux: (24 commits)
  null_blk: fix null-ptr-dereference while configuring 'power' and 'submit_queues'
  blk-throttle: remove unused struct 'avg_latency_bucket'
  block: fix lost bio for plug enabled bio based device
  block: t10-pi: add MODULE_DESCRIPTION()
  blk-mq: add helper for checking if one CPU is mapped to specified hctx
  blk-cgroup: Properly propagate the iostat update up the hierarchy
  blk-cgroup: fix list corruption from reorder of WRITE ->lqueued
  blk-cgroup: fix list corruption from resetting io stat
  cdrom: rearrange last_media_change check to avoid unintentional overflow
  nbd: Fix signal handling
  nbd: Remove a local variable from nbd_send_cmd()
  nbd: Improve the documentation of the locking assumptions
  nbd: Remove superfluous casts
  nbd: Use NULL to represent a pointer
  brd: implement discard support
  null_blk: Fix two sparse warnings
  ublk_drv: set DMA alignment mask to 3
  nvme-rdma, nvme-tcp: include max reconnects for reconnect logging
  nvmet-rdma: Avoid o(n^2) loop in delete_ctrl
  nvme: do not retry authentication failures
  ...

5 files changed, 82 insertions, 35 deletions

diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index b900fe9e0030..558d8e670566 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -222,6 +222,23 @@ out:
 	return err;
 }
 
+static void brd_do_discard(struct brd_device *brd, sector_t sector, u32 size)
+{
+	sector_t aligned_sector = (sector + PAGE_SECTORS) & ~PAGE_SECTORS;
+	struct page *page;
+
+	size -= (aligned_sector - sector) * SECTOR_SIZE;
+	xa_lock(&brd->brd_pages);
+	while (size >= PAGE_SIZE && aligned_sector < rd_size * 2) {
+		page = __xa_erase(&brd->brd_pages, aligned_sector >> PAGE_SECTORS_SHIFT);
+		if (page)
+			__free_page(page);
+		aligned_sector += PAGE_SECTORS;
+		size -= PAGE_SIZE;
+	}
+	xa_unlock(&brd->brd_pages);
+}
+
 static void brd_submit_bio(struct bio *bio)
 {
 	struct brd_device *brd = bio->bi_bdev->bd_disk->private_data;
@@ -229,6 +246,12 @@ static void brd_submit_bio(struct bio *bio)
 	struct bio_vec bvec;
 	struct bvec_iter iter;
 
+	if (unlikely(op_is_discard(bio->bi_opf))) {
+		brd_do_discard(brd, sector, bio->bi_iter.bi_size);
+		bio_endio(bio);
+		return;
+	}
+
 	bio_for_each_segment(bvec, bio, iter) {
 		unsigned int len = bvec.bv_len;
 		int err;
@@ -309,6 +332,9 @@ static int brd_alloc(int i)
 		 *  is harmless)
 		 */
 		.physical_block_size	= PAGE_SIZE,
+		.max_hw_discard_sectors	= UINT_MAX,
+		.max_discard_segments	= 1,
+		.discard_granularity	= PAGE_SIZE,
 	};
 
 	list_for_each_entry(brd, &brd_devices, brd_list)
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 9d4ec9273bf9..22a79a62cc4e 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -222,7 +222,7 @@ static ssize_t pid_show(struct device *dev,
 			struct device_attribute *attr, char *buf)
 {
 	struct gendisk *disk = dev_to_disk(dev);
-	struct nbd_device *nbd = (struct nbd_device *)disk->private_data;
+	struct nbd_device *nbd = disk->private_data;
 
 	return sprintf(buf, "%d\n", nbd->pid);
 }
@@ -236,7 +236,7 @@ static ssize_t backend_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
 	struct gendisk *disk = dev_to_disk(dev);
-	struct nbd_device *nbd = (struct nbd_device *)disk->private_data;
+	struct nbd_device *nbd = disk->private_data;
 
 	return sprintf(buf, "%s\n", nbd->backend ?: "");
 }
@@ -588,7 +588,10 @@ static inline int was_interrupted(int result)
 	return result == -ERESTARTSYS || result == -EINTR;
 }
 
-/* always call with the tx_lock held */
+/*
+ * Returns BLK_STS_RESOURCE if the caller should retry after a delay. Returns
+ * -EAGAIN if the caller should requeue @cmd. Returns -EIO if sending failed.
+ */
 static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 {
 	struct request *req = blk_mq_rq_from_pdu(cmd);
@@ -598,13 +601,15 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 	struct nbd_request request = {.magic = htonl(NBD_REQUEST_MAGIC)};
 	struct kvec iov = {.iov_base = &request, .iov_len = sizeof(request)};
 	struct iov_iter from;
-	unsigned long size = blk_rq_bytes(req);
 	struct bio *bio;
 	u64 handle;
 	u32 type;
 	u32 nbd_cmd_flags = 0;
 	int sent = nsock->sent, skip = 0;
 
+	lockdep_assert_held(&cmd->lock);
+	lockdep_assert_held(&nsock->tx_lock);
+
 	iov_iter_kvec(&from, ITER_SOURCE, &iov, 1, sizeof(request));
 
 	type = req_to_nbd_cmd_type(req);
@@ -644,7 +649,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 	request.type = htonl(type | nbd_cmd_flags);
 	if (type != NBD_CMD_FLUSH) {
 		request.from = cpu_to_be64((u64)blk_rq_pos(req) << 9);
-		request.len = htonl(size);
+		request.len = htonl(blk_rq_bytes(req));
 	}
 	handle = nbd_cmd_handle(cmd);
 	request.cookie = cpu_to_be64(handle);
@@ -669,7 +674,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 				nsock->sent = sent;
 			}
 			set_bit(NBD_CMD_REQUEUED, &cmd->flags);
-			return BLK_STS_RESOURCE;
+			return (__force int)BLK_STS_RESOURCE;
 		}
 		dev_err_ratelimited(disk_to_dev(nbd->disk),
 			"Send control failed (result %d)\n", result);
@@ -710,7 +715,7 @@ send_pages:
 					nsock->pending = req;
 					nsock->sent = sent;
 					set_bit(NBD_CMD_REQUEUED, &cmd->flags);
-					return BLK_STS_RESOURCE;
+					return (__force int)BLK_STS_RESOURCE;
 				}
 				dev_err(disk_to_dev(nbd->disk),
 					"Send data failed (result %d)\n",
@@ -1007,7 +1012,7 @@ static int wait_for_reconnect(struct nbd_device *nbd)
 	return !test_bit(NBD_RT_DISCONNECTED, &config->runtime_flags);
 }
 
-static int nbd_handle_cmd(struct nbd_cmd *cmd, int index)
+static blk_status_t nbd_handle_cmd(struct nbd_cmd *cmd, int index)
 {
 	struct request *req = blk_mq_rq_from_pdu(cmd);
 	struct nbd_device *nbd = cmd->nbd;
@@ -1015,18 +1020,20 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index)
 	struct nbd_sock *nsock;
 	int ret;
 
+	lockdep_assert_held(&cmd->lock);
+
 	config = nbd_get_config_unlocked(nbd);
 	if (!config) {
 		dev_err_ratelimited(disk_to_dev(nbd->disk),
 				    "Socks array is empty\n");
-		return -EINVAL;
+		return BLK_STS_IOERR;
 	}
 
 	if (index >= config->num_connections) {
 		dev_err_ratelimited(disk_to_dev(nbd->disk),
 				    "Attempted send on invalid socket\n");
 		nbd_config_put(nbd);
-		return -EINVAL;
+		return BLK_STS_IOERR;
 	}
 	cmd->status = BLK_STS_OK;
 again:
@@ -1049,7 +1056,7 @@ again:
 			 */
 			sock_shutdown(nbd);
 			nbd_config_put(nbd);
-			return -EIO;
+			return BLK_STS_IOERR;
 		}
 		goto again;
 	}
@@ -1062,7 +1069,7 @@ again:
 	blk_mq_start_request(req);
 	if (unlikely(nsock->pending && nsock->pending != req)) {
 		nbd_requeue_cmd(cmd);
-		ret = 0;
+		ret = BLK_STS_OK;
 		goto out;
 	}
 	/*
@@ -1081,19 +1088,19 @@ again:
 				    "Request send failed, requeueing\n");
 		nbd_mark_nsock_dead(nbd, nsock, 1);
 		nbd_requeue_cmd(cmd);
-		ret = 0;
+		ret = BLK_STS_OK;
 	}
 out:
 	mutex_unlock(&nsock->tx_lock);
 	nbd_config_put(nbd);
-	return ret;
+	return ret < 0 ? BLK_STS_IOERR : (__force blk_status_t)ret;
 }
 
 static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx,
 			const struct blk_mq_queue_data *bd)
 {
 	struct nbd_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);
-	int ret;
+	blk_status_t ret;
 
 	/*
 	 * Since we look at the bio's to send the request over the network we
@@ -1113,10 +1120,6 @@ static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx,
 	 * appropriate.
 	 */
 	ret = nbd_handle_cmd(cmd, hctx->queue_num);
-	if (ret < 0)
-		ret = BLK_STS_IOERR;
-	else if (!ret)
-		ret = BLK_STS_OK;
 	mutex_unlock(&cmd->lock);
 
 	return ret;
diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index 4005a8b685e8..eb023d267369 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -413,13 +413,25 @@ static int nullb_update_nr_hw_queues(struct nullb_device *dev,
 static int nullb_apply_submit_queues(struct nullb_device *dev,
 				     unsigned int submit_queues)
 {
-	return nullb_update_nr_hw_queues(dev, submit_queues, dev->poll_queues);
+	int ret;
+
+	mutex_lock(&lock);
+	ret = nullb_update_nr_hw_queues(dev, submit_queues, dev->poll_queues);
+	mutex_unlock(&lock);
+
+	return ret;
 }
 
 static int nullb_apply_poll_queues(struct nullb_device *dev,
 				   unsigned int poll_queues)
 {
-	return nullb_update_nr_hw_queues(dev, dev->submit_queues, poll_queues);
+	int ret;
+
+	mutex_lock(&lock);
+	ret = nullb_update_nr_hw_queues(dev, dev->submit_queues, poll_queues);
+	mutex_unlock(&lock);
+
+	return ret;
 }
 
 NULLB_DEVICE_ATTR(size, ulong, NULL);
@@ -468,28 +480,31 @@ static ssize_t nullb_device_power_store(struct config_item *item,
 	if (ret < 0)
 		return ret;
 
+	ret = count;
+	mutex_lock(&lock);
 	if (!dev->power && newp) {
 		if (test_and_set_bit(NULLB_DEV_FL_UP, &dev->flags))
-			return count;
+			goto out;
+
 		ret = null_add_dev(dev);
 		if (ret) {
 			clear_bit(NULLB_DEV_FL_UP, &dev->flags);
-			return ret;
+			goto out;
 		}
 
 		set_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags);
 		dev->power = newp;
 	} else if (dev->power && !newp) {
 		if (test_and_clear_bit(NULLB_DEV_FL_UP, &dev->flags)) {
-			mutex_lock(&lock);
 			dev->power = newp;
 			null_del_dev(dev->nullb);
-			mutex_unlock(&lock);
 		}
 		clear_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags);
 	}
 
-	return count;
+out:
+	mutex_unlock(&lock);
+	return ret;
 }
 
 CONFIGFS_ATTR(nullb_device_, power);
@@ -1218,7 +1233,7 @@ static int null_transfer(struct nullb *nullb, struct page *page,
 	return err;
 }
 
-static int null_handle_rq(struct nullb_cmd *cmd)
+static blk_status_t null_handle_rq(struct nullb_cmd *cmd)
 {
 	struct request *rq = blk_mq_rq_from_pdu(cmd);
 	struct nullb *nullb = cmd->nq->dev->nullb;
@@ -1932,15 +1947,12 @@ static int null_add_dev(struct nullb_device *dev)
 	nullb->q->queuedata = nullb;
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, nullb->q);
 
-	mutex_lock(&lock);
 	rv = ida_alloc(&nullb_indexes, GFP_KERNEL);
-	if (rv < 0) {
-		mutex_unlock(&lock);
+	if (rv < 0)
 		goto out_cleanup_disk;
-	}
+
 	nullb->index = rv;
 	dev->index = rv;
-	mutex_unlock(&lock);
 
 	if (config_item_name(&dev->group.cg_item)) {
 		/* Use configfs dir name as the device name */
@@ -1969,9 +1981,7 @@ static int null_add_dev(struct nullb_device *dev)
 	if (rv)
 		goto out_ida_free;
 
-	mutex_lock(&lock);
 	list_add_tail(&nullb->list, &nullb_list);
-	mutex_unlock(&lock);
 
 	pr_info("disk %s created\n", nullb->disk_name);
 
@@ -2020,7 +2030,9 @@ static int null_create_dev(void)
 	if (!dev)
 		return -ENOMEM;
 
+	mutex_lock(&lock);
 	ret = null_add_dev(dev);
+	mutex_unlock(&lock);
 	if (ret) {
 		null_free_dev(dev);
 		return ret;
diff --git a/drivers/block/null_blk/trace.h b/drivers/block/null_blk/trace.h
index ef2d05d5f0df..82b8f6a5e5f0 100644
--- a/drivers/block/null_blk/trace.h
+++ b/drivers/block/null_blk/trace.h
@@ -36,7 +36,12 @@ TRACE_EVENT(nullb_zone_op,
 	    TP_ARGS(cmd, zone_no, zone_cond),
 	    TP_STRUCT__entry(
 		__array(char, disk, DISK_NAME_LEN)
-		__field(enum req_op, op)
+		/*
+		 * __field() uses is_signed_type(). is_signed_type() does not
+		 * support bitwise types. Use __field_struct() instead because
+		 * it does not use is_signed_type().
+		 */
+		__field_struct(enum req_op, op)
 		__field(unsigned int, zone_no)
 		__field(unsigned int, zone_cond)
 	    ),
diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 176657dce3e3..4e159948c912 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -2178,6 +2178,7 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd)
 		.virt_boundary_mask	= p->virt_boundary_mask,
 		.max_segments		= USHRT_MAX,
 		.max_segment_size	= UINT_MAX,
+		.dma_alignment		= 3,
 	};
 	struct gendisk *disk;
 	int ret = -EINVAL;