Merge tag 'block-7.2-20260710' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux

Pull block fixes from Jens Axboe:

 - Limit blk_hctx_poll() to one jiffy. Prevents buggy drivers from
   spinning for too long, hence triggering a stalled RCU read section
   warning

 - Avoid a potential deadlock on zone revalidation failure, which could
   otherwise trigger a lockdep circular locking splat during a SCSI disk
   rescan

 - Remove a redundant GD_NEED_PART_SCAN set in add_disk_final()

 - Make writes to queue/wbt_lat_usec honor the WBT enable state

 - ublk fix to snapshot the batch commands before preparing IO, so that
   userspace can't change an already processed tag and trip the
   WARN_ON_ONCE() in the rollback path

 - xen-blkfront fix for a double completion of split requests on resume

 - drbd fix to reject data replies with an out-of-range payload size

* tag 'block-7.2-20260710' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux:
  block: remove redundant GD_NEED_PART_SCAN in add_disk_final()
  drbd: reject data replies with an out-of-range payload size
  xen-blkfront: fix double completion of split requests on resume
  ublk: snapshot batch commands before preparing I/O
  block: Make WBT latency writes honor enable state
  block: avoid potential deadlock on zone revalidation failure
  blk-mq: bound blk_hctx_poll() to one jiffy

8 files changed, 79 insertions, 24 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 88cb5acc4f39..2c850330a32b 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -5218,6 +5218,7 @@ static int blk_hctx_poll(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
 			 struct io_comp_batch *iob, unsigned int flags)
 {
 	int ret;
+	unsigned long timeout = jiffies + 2;
 
 	do {
 		ret = q->mq_ops->poll(hctx, iob);
@@ -5228,7 +5229,7 @@ static int blk_hctx_poll(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
 		if (ret < 0 || (flags & BLK_POLL_ONESHOT))
 			break;
 		cpu_relax();
-	} while (!need_resched());
+	} while (!need_resched() && time_before(jiffies, timeout));
 
 	return 0;
 }
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index dcc2438ca16d..953d400fd013 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -813,6 +813,21 @@ static void wbt_queue_depth_changed(struct rq_qos *rqos)
 	wbt_update_limits(RQWB(rqos));
 }
 
+static bool wbt_set_lat_changed(struct request_queue *q, u64 val)
+{
+	struct rq_qos *rqos = wbt_rq_qos(q);
+	struct rq_wb *rwb;
+
+	if (!rqos)
+		return true;
+
+	rwb = RQWB(rqos);
+	if (rwb->min_lat_nsec != val)
+		return true;
+
+	return rwb_enabled(rwb) != !!val;
+}
+
 static void wbt_exit(struct rq_qos *rqos)
 {
 	struct rq_wb *rwb = RQWB(rqos);
@@ -1005,8 +1020,12 @@ int wbt_set_lat(struct gendisk *disk, s64 val)
 	else if (val >= 0)
 		val *= 1000ULL;
 
-	if (wbt_get_min_lat(q) == val)
+	mutex_lock(&disk->rqos_state_mutex);
+	if (!wbt_set_lat_changed(q, val)) {
+		mutex_unlock(&disk->rqos_state_mutex);
 		goto out;
+	}
+	mutex_unlock(&disk->rqos_state_mutex);
 
 	blk_mq_quiesce_queue(q);
 
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index bea817f3de56..ca30caec838e 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -1923,11 +1923,20 @@ static int disk_alloc_zone_resources(struct gendisk *disk,
 	if (!disk->zone_wplugs_pool)
 		goto free_hash;
 
-	disk->zone_wplugs_wq =
-		alloc_workqueue("%s_zwplugs", WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_PERCPU,
-				pool_size, disk->disk_name);
-	if (!disk->zone_wplugs_wq)
-		goto destroy_pool;
+	/*
+	 * We may already have a zone write plug workqueue as this function may
+	 * be called after disk_free_zone_resources(), which does not destroy
+	 * the workqueue (the zone write plugs workqueue is destroyed at
+	 * disk_release() time).
+	 */
+	if (!disk->zone_wplugs_wq) {
+		disk->zone_wplugs_wq =
+			alloc_workqueue("%s_zwplugs",
+					WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_PERCPU,
+					pool_size, disk->disk_name);
+		if (!disk->zone_wplugs_wq)
+			goto destroy_pool;
+	}
 
 	disk->zone_wplugs_worker =
 		kthread_create(disk_zone_wplugs_worker, disk,
@@ -1935,15 +1944,12 @@ static int disk_alloc_zone_resources(struct gendisk *disk,
 	if (IS_ERR(disk->zone_wplugs_worker)) {
 		ret = PTR_ERR(disk->zone_wplugs_worker);
 		disk->zone_wplugs_worker = NULL;
-		goto destroy_wq;
+		goto destroy_pool;
 	}
 	wake_up_process(disk->zone_wplugs_worker);
 
 	return 0;
 
-destroy_wq:
-	destroy_workqueue(disk->zone_wplugs_wq);
-	disk->zone_wplugs_wq = NULL;
 destroy_pool:
 	mempool_destroy(disk->zone_wplugs_pool);
 	disk->zone_wplugs_pool = NULL;
@@ -1999,7 +2005,7 @@ static void disk_set_zones_cond_array(struct gendisk *disk, u8 *zones_cond)
 	kfree_rcu_mightsleep(zones_cond);
 }
 
-void disk_free_zone_resources(struct gendisk *disk)
+static void disk_free_zone_resources(struct gendisk *disk)
 {
 	if (disk->zone_wplugs_worker) {
 		kthread_stop(disk->zone_wplugs_worker);
@@ -2007,10 +2013,8 @@ void disk_free_zone_resources(struct gendisk *disk)
 	}
 	WARN_ON_ONCE(!list_empty(&disk->zone_wplugs_list));
 
-	if (disk->zone_wplugs_wq) {
-		destroy_workqueue(disk->zone_wplugs_wq);
-		disk->zone_wplugs_wq = NULL;
-	}
+	if (disk->zone_wplugs_wq)
+		drain_workqueue(disk->zone_wplugs_wq);
 
 	disk_destroy_zone_wplugs_hash_table(disk);
 
@@ -2020,6 +2024,16 @@ void disk_free_zone_resources(struct gendisk *disk)
 	disk->nr_zones = 0;
 }
 
+void disk_release_zone_resources(struct gendisk *disk)
+{
+	if (disk->zone_wplugs_wq) {
+		destroy_workqueue(disk->zone_wplugs_wq);
+		disk->zone_wplugs_wq = NULL;
+	}
+
+	disk_free_zone_resources(disk);
+}
+
 struct blk_revalidate_zone_args {
 	struct gendisk	*disk;
 	u8		*zones_cond;
diff --git a/block/blk.h b/block/blk.h
index 25af8ac5ef0f..fb95d3c58950 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -528,7 +528,7 @@ static inline void ioc_clear_queue(struct request_queue *q)
 
 #ifdef CONFIG_BLK_DEV_ZONED
 void disk_init_zone_resources(struct gendisk *disk);
-void disk_free_zone_resources(struct gendisk *disk);
+void disk_release_zone_resources(struct gendisk *disk);
 static inline bool bio_zone_write_plugging(struct bio *bio)
 {
 	return bio_flagged(bio, BIO_ZONE_WRITE_PLUGGING);
@@ -581,7 +581,7 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode,
 static inline void disk_init_zone_resources(struct gendisk *disk)
 {
 }
-static inline void disk_free_zone_resources(struct gendisk *disk)
+static inline void disk_release_zone_resources(struct gendisk *disk)
 {
 }
 static inline bool bio_zone_write_plugging(struct bio *bio)
diff --git a/block/genhd.c b/block/genhd.c
index f84b6a355b57..df2c3c69b467 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -407,10 +407,6 @@ static void add_disk_final(struct gendisk *disk)
 	struct device *ddev = disk_to_dev(disk);
 
 	if (!(disk->flags & GENHD_FL_HIDDEN)) {
-		/* Make sure the first partition scan will be proceed */
-		if (get_capacity(disk) && disk_has_partscan(disk))
-			set_bit(GD_NEED_PART_SCAN, &disk->state);
-
 		bdev_add(disk->part0, ddev->devt);
 		if (get_capacity(disk))
 			disk_scan_partitions(disk, BLK_OPEN_READ);
@@ -1300,7 +1296,7 @@ static void disk_release(struct device *dev)
 
 	disk_release_events(disk);
 	kfree(disk->random);
-	disk_free_zone_resources(disk);
+	disk_release_zone_resources(disk);
 	xa_destroy(&disk->part_tbl);
 
 	kobject_put(&disk->queue_kobj);
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 58b95bf4bdca..2135c14354a8 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -1810,6 +1810,11 @@ static int recv_dless_read(struct drbd_peer_device *peer_device, struct drbd_req
 		data_size -= digest_size;
 	}
 
+	if (data_size < 0) {
+		drbd_err(peer_device, "Invalid data reply size\n");
+		return -EIO;
+	}
+
 	/* optimistically update recv_cnt.  if receiving fails below,
 	 * we disconnect anyways, and counters will be reset. */
 	peer_device->device->recv_cnt += data_size>>9;
diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 4f6d9e652187..c2c11f2a01e7 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -3584,6 +3584,7 @@ ublk_batch_auto_buf_reg(const struct ublk_batch_io *uc,
 #define UBLK_CMD_BATCH_TMP_BUF_SZ  (48 * 10)
 struct ublk_batch_io_iter {
 	void __user *uaddr;
+	const u8 *kaddr;
 	unsigned done, total;
 	unsigned char elem_bytes;
 	/* copy to this buffer from user space */
@@ -3632,7 +3633,10 @@ static int ublk_walk_cmd_buf(struct ublk_batch_io_iter *iter,
 	while (iter->done < iter->total) {
 		unsigned int len = min(sizeof(iter->buf), iter->total - iter->done);
 
-		if (copy_from_user(iter->buf, iter->uaddr + iter->done, len)) {
+		if (iter->kaddr) {
+			memcpy(iter->buf, iter->kaddr + iter->done, len);
+		} else if (copy_from_user(iter->buf, iter->uaddr + iter->done,
+				  len)) {
 			pr_warn("ublk%d: read batch cmd buffer failed\n",
 					data->ub->dev_info.dev_id);
 			return -EFAULT;
@@ -3723,14 +3727,21 @@ static int ublk_handle_batch_prep_cmd(const struct ublk_batch_io_data *data)
 		.total = uc->nr_elem * uc->elem_bytes,
 		.elem_bytes = uc->elem_bytes,
 	};
+	void *cmd_buf;
 	int ret;
 
+	cmd_buf = vmemdup_user(iter.uaddr, iter.total);
+	if (IS_ERR(cmd_buf))
+		return PTR_ERR(cmd_buf);
+	iter.kaddr = cmd_buf;
+
 	mutex_lock(&data->ub->mutex);
 	ret = ublk_walk_cmd_buf(&iter, data, ublk_batch_prep_io);
 
 	if (ret && iter.done)
 		ublk_batch_revert_prep_cmd(&iter, data);
 	mutex_unlock(&data->ub->mutex);
+	kvfree(cmd_buf);
 	return ret;
 }
 
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index f765970578f9..8dad7bf5f664 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -2080,6 +2080,15 @@ static int blkfront_resume(struct xenbus_device *dev)
 				continue;
 
 			/*
+			 * For requests split across multiple slots, process the
+			 * underlying request only once: skip the linked, sg-less
+			 * secondary slot.
+			 */
+			if (shadow[j].associated_id != NO_ASSOCIATED_ID &&
+			    shadow[j].num_sg == 0)
+				continue;
+
+			/*
 			 * Get the bios in the request so we can re-queue them.
 			 */
 			if (req_op(shadow[j].request) == REQ_OP_FLUSH ||