Merge branch 'block-6.19' into for-7.0/block

Merge in fixes that went to 6.19 after for-7.0/block was branched.
Pending ublk changes depend on particularly the async scan work.

* block-6.19:
  block: zero non-PI portion of auto integrity buffer
  ublk: fix use-after-free in ublk_partition_scan_work
  blk-mq: avoid stall during boot due to synchronize_rcu_expedited
  loop: add missing bd_abort_claiming in loop_set_status
  block: don't merge bios with different app_tags
  blk-rq-qos: Remove unlikely() hints from QoS checks
  loop: don't change loop device under exclusive opener in loop_set_status
  block, bfq: update outdated comment
  blk-mq: skip CPU offline notify on unmapped hctx
  selftests/ublk: fix Makefile to rebuild on header changes
  selftests/ublk: add test for async partition scan
  ublk: scan partition in async way
  block,bfq: fix aux stat accumulation destination
  md: Fix forward incompatibility from configurable logical block size
  md: Fix logical_block_size configuration being overwritten
  md: suspend array while updating raid_disks via sysfs
  md/raid5: fix possible null-pointer dereferences in raid5_store_group_thread_cnt()
  md: Fix static checker warning in analyze_sbs

2 files changed, 72 insertions, 15 deletions

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 32a3a5b13802..bd59c0e9508b 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1225,16 +1225,28 @@ static int loop_clr_fd(struct loop_device *lo)
 }
 
 static int
-loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
+loop_set_status(struct loop_device *lo, blk_mode_t mode,
+		struct block_device *bdev, const struct loop_info64 *info)
 {
 	int err;
 	bool partscan = false;
 	bool size_changed = false;
 	unsigned int memflags;
 
+	/*
+	 * If we don't hold exclusive handle for the device, upgrade to it
+	 * here to avoid changing device under exclusive owner.
+	 */
+	if (!(mode & BLK_OPEN_EXCL)) {
+		err = bd_prepare_to_claim(bdev, loop_set_status, NULL);
+		if (err)
+			goto out_reread_partitions;
+	}
+
 	err = mutex_lock_killable(&lo->lo_mutex);
 	if (err)
-		return err;
+		goto out_abort_claiming;
+
 	if (lo->lo_state != Lo_bound) {
 		err = -ENXIO;
 		goto out_unlock;
@@ -1273,6 +1285,10 @@ out_unfreeze:
 	}
 out_unlock:
 	mutex_unlock(&lo->lo_mutex);
+out_abort_claiming:
+	if (!(mode & BLK_OPEN_EXCL))
+		bd_abort_claiming(bdev, loop_set_status);
+out_reread_partitions:
 	if (partscan)
 		loop_reread_partitions(lo);
 
@@ -1352,7 +1368,9 @@ loop_info64_to_old(const struct loop_info64 *info64, struct loop_info *info)
 }
 
 static int
-loop_set_status_old(struct loop_device *lo, const struct loop_info __user *arg)
+loop_set_status_old(struct loop_device *lo, blk_mode_t mode,
+		    struct block_device *bdev,
+		    const struct loop_info __user *arg)
 {
 	struct loop_info info;
 	struct loop_info64 info64;
@@ -1360,17 +1378,19 @@ loop_set_status_old(struct loop_device *lo, const struct loop_info __user *arg)
 	if (copy_from_user(&info, arg, sizeof (struct loop_info)))
 		return -EFAULT;
 	loop_info64_from_old(&info, &info64);
-	return loop_set_status(lo, &info64);
+	return loop_set_status(lo, mode, bdev, &info64);
 }
 
 static int
-loop_set_status64(struct loop_device *lo, const struct loop_info64 __user *arg)
+loop_set_status64(struct loop_device *lo, blk_mode_t mode,
+		  struct block_device *bdev,
+		  const struct loop_info64 __user *arg)
 {
 	struct loop_info64 info64;
 
 	if (copy_from_user(&info64, arg, sizeof (struct loop_info64)))
 		return -EFAULT;
-	return loop_set_status(lo, &info64);
+	return loop_set_status(lo, mode, bdev, &info64);
 }
 
 static int
@@ -1549,14 +1569,14 @@ static int lo_ioctl(struct block_device *bdev, blk_mode_t mode,
 	case LOOP_SET_STATUS:
 		err = -EPERM;
 		if ((mode & BLK_OPEN_WRITE) || capable(CAP_SYS_ADMIN))
-			err = loop_set_status_old(lo, argp);
+			err = loop_set_status_old(lo, mode, bdev, argp);
 		break;
 	case LOOP_GET_STATUS:
 		return loop_get_status_old(lo, argp);
 	case LOOP_SET_STATUS64:
 		err = -EPERM;
 		if ((mode & BLK_OPEN_WRITE) || capable(CAP_SYS_ADMIN))
-			err = loop_set_status64(lo, argp);
+			err = loop_set_status64(lo, mode, bdev, argp);
 		break;
 	case LOOP_GET_STATUS64:
 		return loop_get_status64(lo, argp);
@@ -1650,8 +1670,9 @@ loop_info64_to_compat(const struct loop_info64 *info64,
 }
 
 static int
-loop_set_status_compat(struct loop_device *lo,
-		       const struct compat_loop_info __user *arg)
+loop_set_status_compat(struct loop_device *lo, blk_mode_t mode,
+		    struct block_device *bdev,
+		    const struct compat_loop_info __user *arg)
 {
 	struct loop_info64 info64;
 	int ret;
@@ -1659,7 +1680,7 @@ loop_set_status_compat(struct loop_device *lo,
 	ret = loop_info64_from_compat(arg, &info64);
 	if (ret < 0)
 		return ret;
-	return loop_set_status(lo, &info64);
+	return loop_set_status(lo, mode, bdev, &info64);
 }
 
 static int
@@ -1685,7 +1706,7 @@ static int lo_compat_ioctl(struct block_device *bdev, blk_mode_t mode,
 
 	switch(cmd) {
 	case LOOP_SET_STATUS:
-		err = loop_set_status_compat(lo,
+		err = loop_set_status_compat(lo, mode, bdev,
 			     (const struct compat_loop_info __user *)arg);
 		break;
 	case LOOP_GET_STATUS:
diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 49c208457198..f6e5a0766721 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -237,6 +237,7 @@ struct ublk_device {
 	bool canceling;
 	pid_t 	ublksrv_tgid;
 	struct delayed_work	exit_work;
+	struct work_struct	partition_scan_work;
 
 	struct ublk_queue       *queues[];
 };
@@ -1582,6 +1583,27 @@ static void ublk_put_disk(struct gendisk *disk)
 		put_device(disk_to_dev(disk));
 }
 
+static void ublk_partition_scan_work(struct work_struct *work)
+{
+	struct ublk_device *ub =
+		container_of(work, struct ublk_device, partition_scan_work);
+	/* Hold disk reference to prevent UAF during concurrent teardown */
+	struct gendisk *disk = ublk_get_disk(ub);
+
+	if (!disk)
+		return;
+
+	if (WARN_ON_ONCE(!test_and_clear_bit(GD_SUPPRESS_PART_SCAN,
+					     &disk->state)))
+		goto out;
+
+	mutex_lock(&disk->open_mutex);
+	bdev_disk_changed(disk, false);
+	mutex_unlock(&disk->open_mutex);
+out:
+	ublk_put_disk(disk);
+}
+
 /*
  * Use this function to ensure that ->canceling is consistently set for
  * the device and all queues. Do not set these flags directly.
@@ -2026,6 +2048,7 @@ static void ublk_stop_dev(struct ublk_device *ub)
 	mutex_lock(&ub->mutex);
 	ublk_stop_dev_unlocked(ub);
 	mutex_unlock(&ub->mutex);
+	cancel_work_sync(&ub->partition_scan_work);
 	ublk_cancel_dev(ub);
 }
 
@@ -2954,9 +2977,17 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub,
 
 	ublk_apply_params(ub);
 
-	/* don't probe partitions if any daemon task is un-trusted */
-	if (ub->unprivileged_daemons)
-		set_bit(GD_SUPPRESS_PART_SCAN, &disk->state);
+	/*
+	 * Suppress partition scan to avoid potential IO hang.
+	 *
+	 * If ublk server error occurs during partition scan, the IO may
+	 * wait while holding ub->mutex, which can deadlock with other
+	 * operations that need the mutex. Defer partition scan to async
+	 * work.
+	 * For unprivileged daemons, keep GD_SUPPRESS_PART_SCAN set
+	 * permanently.
+	 */
+	set_bit(GD_SUPPRESS_PART_SCAN, &disk->state);
 
 	ublk_get_device(ub);
 	ub->dev_info.state = UBLK_S_DEV_LIVE;
@@ -2973,6 +3004,10 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub,
 
 	set_bit(UB_STATE_USED, &ub->state);
 
+	/* Schedule async partition scan for trusted daemons */
+	if (!ub->unprivileged_daemons)
+		schedule_work(&ub->partition_scan_work);
+
 out_put_cdev:
 	if (ret) {
 		ublk_detach_disk(ub);
@@ -3138,6 +3173,7 @@ static int ublk_ctrl_add_dev(const struct ublksrv_ctrl_cmd *header)
 	mutex_init(&ub->mutex);
 	spin_lock_init(&ub->lock);
 	mutex_init(&ub->cancel_mutex);
+	INIT_WORK(&ub->partition_scan_work, ublk_partition_scan_work);
 
 	ret = ublk_alloc_dev_number(ub, header->dev_id);
 	if (ret < 0)