kernel/git/stable/linux-stable.git/block/genhd.c, branch linux-6.15.y

block: introduce a dedicated lock for protecting queue elevator updates

2025-03-10T13:30:18+00:00

A queue's elevator can be updated either when modifying nr_hw_queues or through the sysfs scheduler attribute. Currently, elevator switching/ updating is protected using q->sysfs_lock, but this has led to lockdep splats[1] due to inconsistent lock ordering between q->sysfs_lock and the freeze-lock in multiple block layer call sites. As the scope of q->sysfs_lock is not well-defined, its (mis)use has resulted in numerous lockdep warnings. To address this, introduce a new q->elevator_lock, dedicated specifically for protecting elevator switches/updates. And we'd now use this new q->elevator_lock instead of q->sysfs_lock for protecting elevator switches/updates. While at it, make elv_iosched_load_module() a static function, as it is only called from elv_iosched_store(). Also, remove redundant parameters from elv_iosched_load_module() function signature. [1] https://lore.kernel.org/all/67637e70.050a0220.3157ee.000c.GAE@google.com/ Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Ming Lei Signed-off-by: Nilay Shroff Link: https://lore.kernel.org/r/20250304102551.2533767-5-nilay@linux.ibm.com Signed-off-by: Jens Axboe

block: limit disk max sectors to (LLONG_MAX >> 9)

2025-01-15T22:46:56+00:00

Kernel `loff_t` is defined as `long long int`, so we can't support disk which size is > LLONG_MAX. There are many virtual block drivers, and hardware may report bad capacity too, so limit max sectors to (LLONG_MAX >> 9) for avoiding potential trouble. Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20250115092648.1104452-1-ming.lei@redhat.com Signed-off-by: Jens Axboe

block: better split mq vs non-mq code in add_disk_fwnode

2025-01-06T14:37:41+00:00

Add a big conditional for blk-mq vs not mq at the beginning of add_disk_fwnode so that elevator_init_mq is only called for blk-mq disks, and add checks that the right methods or set or not set based on the queue type. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20250106083531.799976-2-hch@lst.de Signed-off-by: Jens Axboe

block: retry call probe after request_module in blk_request_module

2025-01-03T18:43:50+00:00

Set kernel config: CONFIG_BLK_DEV_LOOP=m CONFIG_BLK_DEV_LOOP_MIN_COUNT=0 Do latter: mknod loop0 b 7 0 exec 4<> loop0 Before commit e418de3abcda ("block: switch gendisk lookup to a simple xarray"), lookup_gendisk will first use base_probe to load module loop, and then the retry will call loop_probe to prepare the loop disk. Finally open for this disk will success. However, after this commit, we lose the retry logic, and open will fail with ENXIO. Block device autoloading is deprecated and will be removed soon, but maybe we should keep open success until we really remove it. So, give a retry to fix it. Fixes: e418de3abcda ("block: switch gendisk lookup to a simple xarray") Suggested-by: Christoph Hellwig Signed-off-by: Yang Erkun Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20241209110435.3670985-1-yangerkun@huaweicloud.com Signed-off-by: Jens Axboe

block: track queue dying state automatically for modeling queue freeze lockdep

2024-12-23T15:17:22+00:00

Now we only verify the outmost freeze & unfreeze in current context in case that !q->mq_freeze_depth, so it is reliable to save queue lying state when we want to lock the freeze queue since the state is one per-task variable now. Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20241127135133.3952153-5-ming.lei@redhat.com Signed-off-by: Jens Axboe

block: track disk DEAD state automatically for modeling queue freeze lockdep

2024-12-23T15:17:22+00:00

Now we only verify the outmost freeze & unfreeze in current context in case that !q->mq_freeze_depth, so it is reliable to save disk DEAD state when we want to lock the freeze queue since the state is one per-task variable now. Doing this way can kill lots of false positive when freeze queue is called before adding disk[1]. [1] https://lore.kernel.org/linux-block/6741f6b2.050a0220.1cc393.0017.GAE@google.com/ Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20241127135133.3952153-3-ming.lei@redhat.com Signed-off-by: Jens Axboe

block: fix uaf for flush rq while iterating tags

2024-11-19T01:31:57+00:00

blk_mq_clear_flush_rq_mapping() is not called during scsi probe, by checking blk_queue_init_done(). However, QUEUE_FLAG_INIT_DONE is cleared in del_gendisk by commit aec89dc5d421 ("block: keep q_usage_counter in atomic mode after del_gendisk"), hence for disk like scsi, following blk_mq_destroy_queue() will not clear flush rq from tags->rqs[] as well, cause following uaf that is found by our syzkaller for v6.6: ================================================================== BUG: KASAN: slab-use-after-free in blk_mq_find_and_get_req+0x16e/0x1a0 block/blk-mq-tag.c:261 Read of size 4 at addr ffff88811c969c20 by task kworker/1:2H/224909 CPU: 1 PID: 224909 Comm: kworker/1:2H Not tainted 6.6.0-ga836a5060850 #32 Workqueue: kblockd blk_mq_timeout_work Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x91/0xf0 lib/dump_stack.c:106 print_address_description.constprop.0+0x66/0x300 mm/kasan/report.c:364 print_report+0x3e/0x70 mm/kasan/report.c:475 kasan_report+0xb8/0xf0 mm/kasan/report.c:588 blk_mq_find_and_get_req+0x16e/0x1a0 block/blk-mq-tag.c:261 bt_iter block/blk-mq-tag.c:288 [inline] __sbitmap_for_each_set include/linux/sbitmap.h:295 [inline] sbitmap_for_each_set include/linux/sbitmap.h:316 [inline] bt_for_each+0x455/0x790 block/blk-mq-tag.c:325 blk_mq_queue_tag_busy_iter+0x320/0x740 block/blk-mq-tag.c:534 blk_mq_timeout_work+0x1a3/0x7b0 block/blk-mq.c:1673 process_one_work+0x7c4/0x1450 kernel/workqueue.c:2631 process_scheduled_works kernel/workqueue.c:2704 [inline] worker_thread+0x804/0xe40 kernel/workqueue.c:2785 kthread+0x346/0x450 kernel/kthread.c:388 ret_from_fork+0x4d/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1b/0x30 arch/x86/entry/entry_64.S:293 Allocated by task 942: kasan_save_stack+0x22/0x50 mm/kasan/common.c:45 kasan_set_track+0x25/0x30 mm/kasan/common.c:52 ____kasan_kmalloc mm/kasan/common.c:374 [inline] __kasan_kmalloc mm/kasan/common.c:383 [inline] __kasan_kmalloc+0xaa/0xb0 mm/kasan/common.c:380 kasan_kmalloc include/linux/kasan.h:198 [inline] __do_kmalloc_node mm/slab_common.c:1007 [inline] __kmalloc_node+0x69/0x170 mm/slab_common.c:1014 kmalloc_node include/linux/slab.h:620 [inline] kzalloc_node include/linux/slab.h:732 [inline] blk_alloc_flush_queue+0x144/0x2f0 block/blk-flush.c:499 blk_mq_alloc_hctx+0x601/0x940 block/blk-mq.c:3788 blk_mq_alloc_and_init_hctx+0x27f/0x330 block/blk-mq.c:4261 blk_mq_realloc_hw_ctxs+0x488/0x5e0 block/blk-mq.c:4294 blk_mq_init_allocated_queue+0x188/0x860 block/blk-mq.c:4350 blk_mq_init_queue_data block/blk-mq.c:4166 [inline] blk_mq_init_queue+0x8d/0x100 block/blk-mq.c:4176 scsi_alloc_sdev+0x843/0xd50 drivers/scsi/scsi_scan.c:335 scsi_probe_and_add_lun+0x77c/0xde0 drivers/scsi/scsi_scan.c:1189 __scsi_scan_target+0x1fc/0x5a0 drivers/scsi/scsi_scan.c:1727 scsi_scan_channel drivers/scsi/scsi_scan.c:1815 [inline] scsi_scan_channel+0x14b/0x1e0 drivers/scsi/scsi_scan.c:1791 scsi_scan_host_selected+0x2fe/0x400 drivers/scsi/scsi_scan.c:1844 scsi_scan+0x3a0/0x3f0 drivers/scsi/scsi_sysfs.c:151 store_scan+0x2a/0x60 drivers/scsi/scsi_sysfs.c:191 dev_attr_store+0x5c/0x90 drivers/base/core.c:2388 sysfs_kf_write+0x11c/0x170 fs/sysfs/file.c:136 kernfs_fop_write_iter+0x3fc/0x610 fs/kernfs/file.c:338 call_write_iter include/linux/fs.h:2083 [inline] new_sync_write+0x1b4/0x2d0 fs/read_write.c:493 vfs_write+0x76c/0xb00 fs/read_write.c:586 ksys_write+0x127/0x250 fs/read_write.c:639 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x70/0x120 arch/x86/entry/common.c:81 entry_SYSCALL_64_after_hwframe+0x78/0xe2 Freed by task 244687: kasan_save_stack+0x22/0x50 mm/kasan/common.c:45 kasan_set_track+0x25/0x30 mm/kasan/common.c:52 kasan_save_free_info+0x2b/0x50 mm/kasan/generic.c:522 ____kasan_slab_free mm/kasan/common.c:236 [inline] __kasan_slab_free+0x12a/0x1b0 mm/kasan/common.c:244 kasan_slab_free include/linux/kasan.h:164 [inline] slab_free_hook mm/slub.c:1815 [inline] slab_free_freelist_hook mm/slub.c:1841 [inline] slab_free mm/slub.c:3807 [inline] __kmem_cache_free+0xe4/0x520 mm/slub.c:3820 blk_free_flush_queue+0x40/0x60 block/blk-flush.c:520 blk_mq_hw_sysfs_release+0x4a/0x170 block/blk-mq-sysfs.c:37 kobject_cleanup+0x136/0x410 lib/kobject.c:689 kobject_release lib/kobject.c:720 [inline] kref_put include/linux/kref.h:65 [inline] kobject_put+0x119/0x140 lib/kobject.c:737 blk_mq_release+0x24f/0x3f0 block/blk-mq.c:4144 blk_free_queue block/blk-core.c:298 [inline] blk_put_queue+0xe2/0x180 block/blk-core.c:314 blkg_free_workfn+0x376/0x6e0 block/blk-cgroup.c:144 process_one_work+0x7c4/0x1450 kernel/workqueue.c:2631 process_scheduled_works kernel/workqueue.c:2704 [inline] worker_thread+0x804/0xe40 kernel/workqueue.c:2785 kthread+0x346/0x450 kernel/kthread.c:388 ret_from_fork+0x4d/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1b/0x30 arch/x86/entry/entry_64.S:293 Other than blk_mq_clear_flush_rq_mapping(), the flag is only used in blk_register_queue() from initialization path, hence it's safe not to clear the flag in del_gendisk. And since QUEUE_FLAG_REGISTERED already make sure that queue should only be registered once, there is no need to test the flag as well. Fixes: 6cfeadbff3f8 ("blk-mq: don't clear flush_rq from tags->rqs[]") Depends-on: commit aec89dc5d421 ("block: keep q_usage_counter in atomic mode after del_gendisk") Signed-off-by: Yu Kuai Reviewed-by: Ming Lei Link: https://lore.kernel.org/r/20241104110005.1412161-1-yukuai1@huaweicloud.com Signed-off-by: Jens Axboe

block/genhd: use seq_put_decimal_ull for diskstats decimal values

2024-11-13T21:02:19+00:00

seq_printf is costly. For each block device, 19 decimal values are yielded in /proc/diskstats via seq_printf. On a system with 16 logical block devices, profiling for open/read/close sequences shows seq_printf took ~75% samples of diskstats_show: diskstats_show(92.626% 2269372/2450040) seq_printf(76.026% 1725313/2269372) vsnprintf(99.163% 1710866/1725313) format_decode(26.597% 455040/1710866) number(19.554% 334542/1710866) memcpy_orig(4.183% 71570/1710866) ... srso_return_thunk(0.009% 148/1725313) part_stat_read_all(8.030% 182236/2269372) One million rounds of open/read/close /proc/diskstats takes: real 0m37.687s user 0m0.264s sys 0m32.911s On average, each sequence tooks ~0.032ms With this patch, most decimal values are yield via seq_put_decimal_ull, performance is significantly improved: real 0m20.792s user 0m0.316s sys 0m20.463s On average, each sequence tooks ~0.020ms, a ~37.5% improvement. Signed-off-by: David Wang <00107082@163.com> Link: https://lore.kernel.org/r/20241108054500.4251-1-00107082@163.com Signed-off-by: Jens Axboe

block: Replace sprintf() with sysfs_emit()

2024-11-07T22:30:30+00:00

Per Documentation/filesystems/sysfs.rst, show() should only use sysfs_emit() or sysfs_emit_at() when formatting the value to be returned to user space. No functional change intended. Signed-off-by: zhangguopeng Suggested-by: Christoph Hellwig Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20241107104258.29742-1-zhangguopeng@kylinos.cn Signed-off-by: Jens Axboe

block: model freeze & enter queue as lock for supporting lockdep

2024-10-26T13:14:53+00:00

Recently we got several deadlock report[1][2][3] caused by blk_mq_freeze_queue and blk_enter_queue(). Turns out the two are just like acquiring read/write lock, so model them as read/write lock for supporting lockdep: 1) model q->q_usage_counter as two locks(io and queue lock) - queue lock covers sync with blk_enter_queue() - io lock covers sync with bio_enter_queue() 2) make the lockdep class/key as per-queue: - different subsystem has very different lock use pattern, shared lock class causes false positive easily - freeze_queue degrades to no lock in case that disk state becomes DEAD because bio_enter_queue() won't be blocked any more - freeze_queue degrades to no lock in case that request queue becomes dying because blk_enter_queue() won't be blocked any more 3) model blk_mq_freeze_queue() as acquire_exclusive & try_lock - it is exclusive lock, so dependency with blk_enter_queue() is covered - it is trylock because blk_mq_freeze_queue() are allowed to run concurrently 4) model blk_enter_queue() & bio_enter_queue() as acquire_read() - nested blk_enter_queue() are allowed - dependency with blk_mq_freeze_queue() is covered - blk_queue_exit() is often called from other contexts(such as irq), and it can't be annotated as lock_release(), so simply do it in blk_enter_queue(), this way still covered cases as many as possible With lockdep support, such kind of reports may be reported asap and needn't wait until the real deadlock is triggered. For example, lockdep report can be triggered in the report[3] with this patch applied. [1] occasional block layer hang when setting 'echo noop > /sys/block/sda/queue/scheduler' https://bugzilla.kernel.org/show_bug.cgi?id=219166 [2] del_gendisk() vs blk_queue_enter() race condition https://lore.kernel.org/linux-block/20241003085610.GK11458@google.com/ [3] queue_freeze & queue_enter deadlock in scsi https://lore.kernel.org/linux-block/ZxG38G9BuFdBpBHZ@fedora/T/#u Reviewed-by: Christoph Hellwig Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20241025003722.3630252-4-ming.lei@redhat.com Signed-off-by: Jens Axboe