From 00f6c1b4d15d35fadb7f34768a1831c81aaa8936 Mon Sep 17 00:00:00 2001 From: Li Nan Date: Mon, 15 Dec 2025 20:44:12 +0800 Subject: md: Fix static checker warning in analyze_sbs The following warn is reported: drivers/md/md.c:3912 analyze_sbs() warn: iterator 'i' not incremented Fixes: d8730f0cf4ef ("md: Remove deprecated CONFIG_MD_MULTIPATH") Reported-by: Dan Carpenter Closes: https://lore.kernel.org/linux-raid/7e2e95ce-3740-09d8-a561-af6bfb767f18@huaweicloud.com/T/#t Signed-off-by: Li Nan Link: https://lore.kernel.org/linux-raid/20251215124412.4015572-1-linan666@huaweicloud.com Signed-off-by: Yu Kuai --- drivers/md/md.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'drivers') diff --git a/drivers/md/md.c b/drivers/md/md.c index e5922a682953..03433c88fb54 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -3882,7 +3882,6 @@ out_free_rdev: static int analyze_sbs(struct mddev *mddev) { - int i; struct md_rdev *rdev, *freshest, *tmp; freshest = NULL; @@ -3909,11 +3908,9 @@ static int analyze_sbs(struct mddev *mddev) super_types[mddev->major_version]. validate_super(mddev, NULL/*freshest*/, freshest); - i = 0; rdev_for_each_safe(rdev, tmp, mddev) { if (mddev->max_disks && - (rdev->desc_nr >= mddev->max_disks || - i > mddev->max_disks)) { + rdev->desc_nr >= mddev->max_disks) { pr_warn("md: %s: %pg: only %d devices permitted\n", mdname(mddev), rdev->bdev, mddev->max_disks); -- cgit v1.2.3 From 7ad6ef91d8745d04aff9cce7bdbc6320d8e05fe9 Mon Sep 17 00:00:00 2001 From: Tuo Li Date: Thu, 25 Dec 2025 21:03:26 +0800 Subject: md/raid5: fix possible null-pointer dereferences in raid5_store_group_thread_cnt() The variable mddev->private is first assigned to conf and then checked: conf = mddev->private; if (!conf) ... If conf is NULL, then mddev->private is also NULL. In this case, null-pointer dereferences can occur when calling raid5_quiesce(): raid5_quiesce(mddev, true); raid5_quiesce(mddev, false); since mddev->private is assigned to conf again in raid5_quiesce(), and conf is dereferenced in several places, for example: conf->quiesce = 0; wake_up(&conf->wait_for_quiescent); To fix this issue, the function should unlock mddev and return before invoking raid5_quiesce() when conf is NULL, following the existing pattern in raid5_change_consistency_policy(). Fixes: fa1944bbe622 ("md/raid5: Wait sync io to finish before changing group cnt") Signed-off-by: Tuo Li Reviewed-by: Xiao Ni Reviewed-by: Paul Menzel Link: https://lore.kernel.org/linux-raid/20251225130326.67780-1-islituo@gmail.com Signed-off-by: Yu Kuai --- drivers/md/raid5.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'drivers') diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index e57ce3295292..8dc98f545969 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -7187,12 +7187,14 @@ raid5_store_group_thread_cnt(struct mddev *mddev, const char *page, size_t len) err = mddev_suspend_and_lock(mddev); if (err) return err; + conf = mddev->private; + if (!conf) { + mddev_unlock_and_resume(mddev); + return -ENODEV; + } raid5_quiesce(mddev, true); - conf = mddev->private; - if (!conf) - err = -ENODEV; - else if (new != conf->worker_cnt_per_group) { + if (new != conf->worker_cnt_per_group) { old_groups = conf->worker_groups; if (old_groups) flush_workqueue(raid5_wq); -- cgit v1.2.3 From 2cc583653bbe050bacd1cadcc9776d39bf449740 Mon Sep 17 00:00:00 2001 From: FengWei Shih Date: Fri, 26 Dec 2025 18:18:16 +0800 Subject: md: suspend array while updating raid_disks via sysfs In raid1_reshape(), freeze_array() is called before modifying the r1bio memory pool (conf->r1bio_pool) and conf->raid_disks, and unfreeze_array() is called after the update is completed. However, freeze_array() only waits until nr_sync_pending and (nr_pending - nr_queued) of all buckets reaches zero. When an I/O error occurs, nr_queued is increased and the corresponding r1bio is queued to either retry_list or bio_end_io_list. As a result, freeze_array() may unblock before these r1bios are released. This can lead to a situation where conf->raid_disks and the mempool have already been updated while queued r1bios, allocated with the old raid_disks value, are later released. Consequently, free_r1bio() may access memory out of bounds in put_all_bios() and release r1bios of the wrong size to the new mempool, potentially causing issues with the mempool as well. Since only normal I/O might increase nr_queued while an I/O error occurs, suspending the array avoids this issue. Note: Updating raid_disks via ioctl SET_ARRAY_INFO already suspends the array. Therefore, we suspend the array when updating raid_disks via sysfs to avoid this issue too. Signed-off-by: FengWei Shih Link: https://lore.kernel.org/linux-raid/20251226101816.4506-1-dannyshih@synology.com Signed-off-by: Yu Kuai --- drivers/md/md.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers') diff --git a/drivers/md/md.c b/drivers/md/md.c index 03433c88fb54..dda272e87a1b 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -4404,7 +4404,7 @@ raid_disks_store(struct mddev *mddev, const char *buf, size_t len) if (err < 0) return err; - err = mddev_lock(mddev); + err = mddev_suspend_and_lock(mddev); if (err) return err; if (mddev->pers) @@ -4429,7 +4429,7 @@ raid_disks_store(struct mddev *mddev, const char *buf, size_t len) } else mddev->raid_disks = n; out_unlock: - mddev_unlock(mddev); + mddev_unlock_and_resume(mddev); return err ? err : len; } static struct md_sysfs_entry md_raid_disks = -- cgit v1.2.3 From 864466c38c4a0446088a8e866538c83c3f2018cb Mon Sep 17 00:00:00 2001 From: Li Nan Date: Fri, 26 Dec 2025 10:42:20 +0800 Subject: md: Fix logical_block_size configuration being overwritten In super_1_validate(), mddev->logical_block_size is directly overwritten with the value from metadata. This causes the previously configured lbs to be lost, making the configuration ineffective. Fix it. Fixes: 62ed1b582246 ("md: allow configuring logical block size") Signed-off-by: Li Nan Reviewed-by: Yu Kuai Reviewed-by: Xiao Ni Link: https://lore.kernel.org/linux-raid/20251226024221.724201-1-linan666@huaweicloud.com Signed-off-by: Yu Kuai --- drivers/md/md.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/md/md.c b/drivers/md/md.c index dda272e87a1b..a13f92a64df6 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -1999,7 +1999,6 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *freshest, struc mddev->layout = le32_to_cpu(sb->layout); mddev->raid_disks = le32_to_cpu(sb->raid_disks); mddev->dev_sectors = le64_to_cpu(sb->size); - mddev->logical_block_size = le32_to_cpu(sb->logical_block_size); mddev->events = ev1; mddev->bitmap_info.offset = 0; mddev->bitmap_info.space = 0; @@ -2015,6 +2014,9 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *freshest, struc mddev->max_disks = (4096-256)/2; + if (!mddev->logical_block_size) + mddev->logical_block_size = le32_to_cpu(sb->logical_block_size); + if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_BITMAP_OFFSET) && mddev->bitmap_info.file == NULL) { mddev->bitmap_info.offset = -- cgit v1.2.3 From a4166f1c4893a9a620507255b9d1ccab44fab189 Mon Sep 17 00:00:00 2001 From: Li Nan Date: Fri, 26 Dec 2025 10:42:21 +0800 Subject: md: Fix forward incompatibility from configurable logical block size Commit 62ed1b582246 ("md: allow configuring logical block size") used reserved pad to add 'logical_block_size' to metadata. RAID rejects non-zero reserved pad, so arrays fail when rolling back to old kernels after booting new ones. Set 'logical_block_size' only for newly created arrays to support rollback to old kernels. Importantly new arrays still won't work on old kernels to prevent data loss issue from LBS changes. For arrays created on old kernels which confirmed not to rollback, configure LBS by echo current LBS (queue/logical_block_size) to md/logical_block_size. Fixes: 62ed1b582246 ("md: allow configuring logical block size") Reported-by: BugReports Closes: https://lore.kernel.org/linux-raid/825e532d-d1e1-44bb-5581-692b7c091796@huaweicloud.com/T/#t Signed-off-by: Li Nan Link: https://lore.kernel.org/linux-raid/20251226024221.724201-2-linan666@huaweicloud.com Signed-off-by: Yu Kuai --- drivers/md/md.c | 48 ++++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 44 insertions(+), 4 deletions(-) (limited to 'drivers') diff --git a/drivers/md/md.c b/drivers/md/md.c index a13f92a64df6..6d73f6e196a9 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5980,13 +5980,33 @@ lbs_store(struct mddev *mddev, const char *buf, size_t len) if (mddev->major_version == 0) return -EINVAL; - if (mddev->pers) - return -EBUSY; - err = kstrtouint(buf, 10, &lbs); if (err < 0) return -EINVAL; + if (mddev->pers) { + unsigned int curr_lbs; + + if (mddev->logical_block_size) + return -EBUSY; + /* + * To fix forward compatibility issues, LBS is not + * configured for arrays from old kernels (<=6.18) by default. + * If the user confirms no rollback to old kernels, + * enable LBS by writing current LBS — to prevent data + * loss from LBS changes. + */ + curr_lbs = queue_logical_block_size(mddev->gendisk->queue); + if (lbs != curr_lbs) + return -EINVAL; + + mddev->logical_block_size = curr_lbs; + set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags); + pr_info("%s: logical block size configured successfully, array will not be assembled in old kernels (<= 6.18)\n", + mdname(mddev)); + return len; + } + err = mddev_lock(mddev); if (err) goto unlock; @@ -6162,7 +6182,27 @@ int mddev_stack_rdev_limits(struct mddev *mddev, struct queue_limits *lim, mdname(mddev)); return -EINVAL; } - mddev->logical_block_size = lim->logical_block_size; + + /* Only 1.x meta needs to set logical block size */ + if (mddev->major_version == 0) + return 0; + + /* + * Fix forward compatibility issue. Only set LBS by default for + * new arrays, mddev->events == 0 indicates the array was just + * created. When assembling an array, read LBS from the superblock + * instead — LBS is 0 in superblocks created by old kernels. + */ + if (!mddev->events) { + pr_info("%s: array will not be assembled in old kernels that lack configurable LBS support (<= 6.18)\n", + mdname(mddev)); + mddev->logical_block_size = lim->logical_block_size; + } + + if (!mddev->logical_block_size) + pr_warn("%s: echo current LBS to md/logical_block_size to prevent data loss issues from LBS changes.\n" + "\tNote: After setting, array will not be assembled in old kernels (<= 6.18)\n", + mdname(mddev)); return 0; } -- cgit v1.2.3 From 7fc4da6a304bdcd3de14fc946dc2c19437a9cc5a Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Tue, 23 Dec 2025 11:27:40 +0800 Subject: ublk: scan partition in async way Implement async partition scan to avoid IO hang when reading partition tables. Similar to nvme_partition_scan_work(), partition scanning is deferred to a work queue to prevent deadlocks. When partition scan happens synchronously during add_disk(), IO errors can cause the partition scan to wait while holding ub->mutex, which can deadlock with other operations that need the mutex. Changes: - Add partition_scan_work to ublk_device structure - Implement ublk_partition_scan_work() to perform async scan - Always suppress sync partition scan during add_disk() - Schedule async work after add_disk() for trusted daemons - Add flush_work() in ublk_stop_dev() before grabbing ub->mutex Reviewed-by: Caleb Sander Mateos Reported-by: Yoav Cohen Closes: https://lore.kernel.org/linux-block/DM4PR12MB63280C5637917C071C2F0D65A9A8A@DM4PR12MB6328.namprd12.prod.outlook.com/ Fixes: 71f28f3136af ("ublk_drv: add io_uring based userspace block driver") Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 35 ++++++++++++++++++++++++++++++++--- 1 file changed, 32 insertions(+), 3 deletions(-) (limited to 'drivers') diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 49c208457198..837fedb02e0d 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[]; }; @@ -254,6 +255,20 @@ static inline struct request *__ublk_check_and_get_req(struct ublk_device *ub, u16 q_id, u16 tag, struct ublk_io *io, size_t offset); static inline unsigned int ublk_req_build_flags(struct request *req); +static void ublk_partition_scan_work(struct work_struct *work) +{ + struct ublk_device *ub = + container_of(work, struct ublk_device, partition_scan_work); + + if (WARN_ON_ONCE(!test_and_clear_bit(GD_SUPPRESS_PART_SCAN, + &ub->ub_disk->state))) + return; + + mutex_lock(&ub->ub_disk->open_mutex); + bdev_disk_changed(ub->ub_disk, false); + mutex_unlock(&ub->ub_disk->open_mutex); +} + static inline struct ublksrv_io_desc * ublk_get_iod(const struct ublk_queue *ubq, unsigned tag) { @@ -2026,6 +2041,7 @@ static void ublk_stop_dev(struct ublk_device *ub) mutex_lock(&ub->mutex); ublk_stop_dev_unlocked(ub); mutex_unlock(&ub->mutex); + flush_work(&ub->partition_scan_work); ublk_cancel_dev(ub); } @@ -2954,9 +2970,17 @@ 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 +2997,10 @@ 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 +3166,7 @@ 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) -- cgit v1.2.3