linux-stable.git/drivers/block, branch v6.16.2

ublk: check for unprivileged daemon on each I/O fetch

2025-08-20T16:41:33+00:00

[ Upstream commit 5058a62875e1916e5133a1639f0207ea2148c0bc ]

Commit ab03a61c6614 ("ublk: have a per-io daemon instead of a per-queue
daemon") allowed each ublk I/O to have an independent daemon task.
However, nr_privileged_daemon is only computed based on whether the last
I/O fetched in each ublk queue has an unprivileged daemon task.
Fix this by checking whether every fetched I/O's daemon is privileged.
Change nr_privileged_daemon from a count of queues to a boolean
indicating whether any I/Os have an unprivileged daemon.

Signed-off-by: Caleb Sander Mateos 
Fixes: ab03a61c6614 ("ublk: have a per-io daemon instead of a per-queue daemon")
Reviewed-by: Ming Lei 
Link: https://lore.kernel.org/r/20250808155216.296170-1-csander@purestorage.com
Signed-off-by: Jens Axboe 
Signed-off-by: Sasha Levin

drbd: add missing kref_get in handle_write_conflicts

2025-08-20T16:40:55+00:00

[ Upstream commit 00c9c9628b49e368d140cfa61d7df9b8922ec2a8 ]

With `two-primaries` enabled, DRBD tries to detect "concurrent" writes
and handle write conflicts, so that even if you write to the same sector
simultaneously on both nodes, they end up with the identical data once
the writes are completed.

In handling "superseeded" writes, we forgot a kref_get,
resulting in a premature drbd_destroy_device and use after free,
and further to kernel crashes with symptoms.

Relevance: No one should use DRBD as a random data generator, and apparently
all users of "two-primaries" handle concurrent writes correctly on layer up.
That is cluster file systems use some distributed lock manager,
and live migration in virtualization environments stops writes on one node
before starting writes on the other node.

Which means that other than for "test cases",
this code path is never taken in real life.

FYI, in DRBD 9, things are handled differently nowadays.  We still detect
"write conflicts", but no longer try to be smart about them.
We decided to disconnect hard instead: upper layers must not submit concurrent
writes. If they do, that's their fault.

Signed-off-by: Sarah Newman 
Signed-off-by: Lars Ellenberg 
Signed-off-by: Christoph Böhmwalder 
Link: https://lore.kernel.org/r/20250627095728.800688-1-christoph.boehmwalder@linbit.com
Signed-off-by: Jens Axboe 
Signed-off-by: Sasha Levin

loop: Avoid updating block size under exclusive owner

2025-08-20T16:40:54+00:00

[ Upstream commit 7e49538288e523427beedd26993d446afef1a6fb ]

Syzbot came up with a reproducer where a loop device block size is
changed underneath a mounted filesystem. This causes a mismatch between
the block device block size and the block size stored in the superblock
causing confusion in various places such as fs/buffer.c. The particular
issue triggered by syzbot was a warning in __getblk_slow() due to
requested buffer size not matching block device block size.

Fix the problem by getting exclusive hold of the loop device to change
its block size. This fails if somebody (such as filesystem) has already
an exclusive ownership of the block device and thus prevents modifying
the loop device under some exclusive owner which doesn't expect it.

Reported-by: syzbot+01ef7a8da81a975e1ccd@syzkaller.appspotmail.com
Signed-off-by: Jan Kara 
Tested-by: syzbot+01ef7a8da81a975e1ccd@syzkaller.appspotmail.com
Link: https://lore.kernel.org/r/20250711163202.19623-2-jack@suse.cz
Signed-off-by: Jens Axboe 
Signed-off-by: Sasha Levin

sunvdc: Balance device refcount in vdc_port_mpgroup_check

2025-08-20T16:40:47+00:00

commit 63ce53724637e2e7ba51fe3a4f78351715049905 upstream.

Using device_find_child() to locate a probed virtual-device-port node
causes a device refcount imbalance, as device_find_child() internally
calls get_device() to increment the device’s reference count before
returning its pointer. vdc_port_mpgroup_check() directly returns true
upon finding a matching device without releasing the reference via
put_device(). We should call put_device() to decrement refcount.

As comment of device_find_child() says, 'NOTE: you will need to drop
the reference with put_device() after use'.

Found by code review.

Cc: stable@vger.kernel.org
Fixes: 3ee70591d6c4 ("sunvdc: prevent sunvdc panic when mpgroup disk added to guest domain")
Signed-off-by: Ma Ke 
Link: https://lore.kernel.org/r/20250719075856.3447953-1-make24@iscas.ac.cn
Signed-off-by: Jens Axboe 
Signed-off-by: Greg Kroah-Hartman

zloop: fix KASAN use-after-free of tag set

2025-08-15T14:39:34+00:00

commit 765761851d89c772f482494d452e266795460278 upstream.

When a zoned loop device, or zloop device, is removed, KASAN enabled
kernel reports "BUG KASAN use-after-free" in blk_mq_free_tag_set(). The
BUG happens because zloop_ctl_remove() calls put_disk(), which invokes
zloop_free_disk(). The zloop_free_disk() frees the memory allocated for
the zlo pointer. However, after the memory is freed, zloop_ctl_remove()
calls blk_mq_free_tag_set(&zlo->tag_set), which accesses the freed zlo.
Hence the KASAN use-after-free.

 zloop_ctl_remove()
  put_disk(zlo->disk)
   put_device()
    kobject_put()
     ...
      zloop_free_disk()
        kvfree(zlo)
  blk_mq_free_tag_set(&zlo->tag_set)

To avoid the BUG, move the call to blk_mq_free_tag_set(&zlo->tag_set)
from zloop_ctl_remove() into zloop_free_disk(). This ensures that
the tag_set is freed before the call to kvfree(zlo).

Fixes: eb0570c7df23 ("block: new zoned loop block device driver")
CC: stable@vger.kernel.org
Signed-off-by: Shin'ichiro Kawasaki 
Reviewed-by: Christoph Hellwig 
Link: https://lore.kernel.org/r/20250731110745.165751-1-shinichiro.kawasaki@wdc.com
Signed-off-by: Jens Axboe 
Signed-off-by: Greg Kroah-Hartman

ublk: validate ublk server pid

2025-08-15T14:38:23+00:00

[ Upstream commit c2c8089f325ed703fd5123b39e2dece1dd605904 ]

ublk server pid(the `tgid` of the process opening the ublk device) is stored
in `ublk_device->ublksrv_tgid`. This `tgid` is then checked against the
`ublksrv_pid` in `ublk_ctrl_start_dev` and `ublk_ctrl_end_recovery`.

This ensures that correct ublk server pid is stored in device info.

Fixes: 71f28f3136af ("ublk_drv: add io_uring based userspace block driver")
Signed-off-by: Ming Lei 
Link: https://lore.kernel.org/r/20250713143415.2857561-2-ming.lei@redhat.com
Signed-off-by: Jens Axboe 
Signed-off-by: Sasha Levin

ublk: speed up ublk server exit handling

2025-08-15T14:38:22+00:00

[ Upstream commit 2fa9c93035e17380cafa897ee1a4d503881a3770 ]

Recently, we've observed a few cases where a ublk server is able to
complete restart more quickly than the driver can process the exit of
the previous ublk server. The new ublk server comes up, attempts
recovery of the preexisting ublk devices, and observes them still in
state UBLK_S_DEV_LIVE. While this is possible due to the asynchronous
nature of io_uring cleanup and should therefore be handled properly in
the ublk server, it is still preferable to make ublk server exit
handling faster if possible, as we should strive for it to not be a
limiting factor in how fast a ublk server can restart and provide
service again.

Analysis of the issue showed that the vast majority of the time spent in
handling the ublk server exit was in calls to blk_mq_quiesce_queue,
which is essentially just a (relatively expensive) call to
synchronize_rcu. The ublk server exit path currently issues an
unnecessarily large number of calls to blk_mq_quiesce_queue, for two
reasons:

1. It tries to call blk_mq_quiesce_queue once per ublk_queue. However,
blk_mq_quiesce_queue targets the request_queue of the underlying ublk
device, of which there is only one. So the number of calls is larger
than necessary by a factor of nr_hw_queues.
2. In practice, it calls blk_mq_quiesce_queue _more_ than once per
ublk_queue. This is because of a data race where we read
ubq->canceling without any locking when deciding if we should call
ublk_start_cancel. It is thus possible for two calls to
ublk_uring_cmd_cancel_fn against the same ublk_queue to both call
ublk_start_cancel against the same ublk_queue.

Fix this by making the "canceling" flag a per-device state. This
actually matches the existing code better, as there are several places
where the flag is set or cleared for all queues simultaneously, and
there is the general expectation that cancellation corresponds with ublk
server exit. This per-device canceling flag is then checked under a
(new) lock (addressing the data race (2) above), and the queue is only
quiesced if it is cleared (addressing (1) above). The result is just one
call to blk_mq_quiesce_queue per ublk device.

To minimize the number of cache lines that are accessed in the hot path,
the per-queue canceling flag is kept. The values of the per-device
canceling flag and all per-queue canceling flags should always match.

In our setup, where one ublk server handles I/O for 128 ublk devices,
each having 24 hardware queues of depth 4096, here are the results
before and after this patch, where teardown time is measured from the
first call to io_ring_ctx_wait_and_kill to the return from the last
ublk_ch_release:

before after
number of calls to blk_mq_quiesce_queue: 6469 256
teardown time: 11.14s 2.44s

There are still some potential optimizations here, but this takes care
of a big chunk of the ublk server exit handling delay.

Signed-off-by: Uday Shankar
Reviewed-by: Caleb Sander Mateos
Reviewed-by: Ming Lei
Link: https://lore.kernel.org/r/20250703-ublk_too_many_quiesce-v2-1-3527b5339eeb@purestorage.com
Signed-off-by: Jens Axboe
Stable-dep-of: c2c8089f325e ("ublk: validate ublk server pid")
Signed-off-by: Sasha Levin

nbd: fix lockdep deadlock warning

2025-08-15T14:38:22+00:00

[ Upstream commit 8b428f42f3edfd62422aa7ad87049ab232a2eaa9 ]

nbd grabs device lock nbd->config_lock for updating nr_hw_queues, this
ways cause the following lock dependency:

-> #2 (&disk->open_mutex){+.+.}-{4:4}:
       lock_acquire kernel/locking/lockdep.c:5871 [inline]
       lock_acquire+0x1ac/0x448 kernel/locking/lockdep.c:5828
       __mutex_lock_common kernel/locking/mutex.c:602 [inline]
       __mutex_lock+0x166/0x1292 kernel/locking/mutex.c:747
       mutex_lock_nested+0x14/0x1c kernel/locking/mutex.c:799
       __del_gendisk+0x132/0xac6 block/genhd.c:706
       del_gendisk+0xf6/0x19a block/genhd.c:819
       nbd_dev_remove+0x3c/0xf2 drivers/block/nbd.c:268
       nbd_dev_remove_work+0x1c/0x26 drivers/block/nbd.c:284
       process_one_work+0x96a/0x1f32 kernel/workqueue.c:3238
       process_scheduled_works kernel/workqueue.c:3321 [inline]
       worker_thread+0x5ce/0xde8 kernel/workqueue.c:3402
       kthread+0x39c/0x7d4 kernel/kthread.c:464
       ret_from_fork_kernel+0x2a/0xbb2 arch/riscv/kernel/process.c:214
       ret_from_fork_kernel_asm+0x16/0x18 arch/riscv/kernel/entry.S:327

-> #1 (&set->update_nr_hwq_lock){++++}-{4:4}:
       lock_acquire kernel/locking/lockdep.c:5871 [inline]
       lock_acquire+0x1ac/0x448 kernel/locking/lockdep.c:5828
       down_write+0x9c/0x19a kernel/locking/rwsem.c:1577
       blk_mq_update_nr_hw_queues+0x3e/0xb86 block/blk-mq.c:5041
       nbd_start_device+0x140/0xb2c drivers/block/nbd.c:1476
       nbd_genl_connect+0xae0/0x1b24 drivers/block/nbd.c:2201
       genl_family_rcv_msg_doit+0x206/0x2e6 net/netlink/genetlink.c:1115
       genl_family_rcv_msg net/netlink/genetlink.c:1195 [inline]
       genl_rcv_msg+0x514/0x78e net/netlink/genetlink.c:1210
       netlink_rcv_skb+0x206/0x3be net/netlink/af_netlink.c:2534
       genl_rcv+0x36/0x4c net/netlink/genetlink.c:1219
       netlink_unicast_kernel net/netlink/af_netlink.c:1313 [inline]
       netlink_unicast+0x4f0/0x82c net/netlink/af_netlink.c:1339
       netlink_sendmsg+0x85e/0xdd6 net/netlink/af_netlink.c:1883
       sock_sendmsg_nosec net/socket.c:712 [inline]
       __sock_sendmsg+0xcc/0x160 net/socket.c:727
       ____sys_sendmsg+0x63e/0x79c net/socket.c:2566
       ___sys_sendmsg+0x144/0x1e6 net/socket.c:2620
       __sys_sendmsg+0x188/0x246 net/socket.c:2652
       __do_sys_sendmsg net/socket.c:2657 [inline]
       __se_sys_sendmsg net/socket.c:2655 [inline]
       __riscv_sys_sendmsg+0x70/0xa2 net/socket.c:2655
       syscall_handler+0x94/0x118 arch/riscv/include/asm/syscall.h:112
       do_trap_ecall_u+0x396/0x530 arch/riscv/kernel/traps.c:341
       handle_exception+0x146/0x152 arch/riscv/kernel/entry.S:197

-> #0 (&nbd->config_lock){+.+.}-{4:4}:
       check_noncircular+0x132/0x146 kernel/locking/lockdep.c:2178
       check_prev_add kernel/locking/lockdep.c:3168 [inline]
       check_prevs_add kernel/locking/lockdep.c:3287 [inline]
       validate_chain kernel/locking/lockdep.c:3911 [inline]
       __lock_acquire+0x12b2/0x24ea kernel/locking/lockdep.c:5240
       lock_acquire kernel/locking/lockdep.c:5871 [inline]
       lock_acquire+0x1ac/0x448 kernel/locking/lockdep.c:5828
       __mutex_lock_common kernel/locking/mutex.c:602 [inline]
       __mutex_lock+0x166/0x1292 kernel/locking/mutex.c:747
       mutex_lock_nested+0x14/0x1c kernel/locking/mutex.c:799
       refcount_dec_and_mutex_lock+0x60/0xd8 lib/refcount.c:118
       nbd_config_put+0x3a/0x610 drivers/block/nbd.c:1423
       nbd_release+0x94/0x15c drivers/block/nbd.c:1735
       blkdev_put_whole+0xac/0xee block/bdev.c:721
       bdev_release+0x3fe/0x600 block/bdev.c:1144
       blkdev_release+0x1a/0x26 block/fops.c:684
       __fput+0x382/0xa8c fs/file_table.c:465
       ____fput+0x1c/0x26 fs/file_table.c:493
       task_work_run+0x16a/0x25e kernel/task_work.c:227
       resume_user_mode_work include/linux/resume_user_mode.h:50 [inline]
       exit_to_user_mode_loop+0x118/0x134 kernel/entry/common.c:114
       exit_to_user_mode_prepare include/linux/entry-common.h:330 [inline]
       syscall_exit_to_user_mode_work include/linux/entry-common.h:414 [inline]
       syscall_exit_to_user_mode include/linux/entry-common.h:449 [inline]
       do_trap_ecall_u+0x3f0/0x530 arch/riscv/kernel/traps.c:355
       handle_exception+0x146/0x152 arch/riscv/kernel/entry.S:197

Also it isn't necessary to require nbd->config_lock, because
blk_mq_update_nr_hw_queues() does grab tagset lock for sync everything.

Fixes the issue by releasing ->config_lock & retry in case of concurrent
updating nr_hw_queues.

Fixes: 98e68f67020c ("block: prevent adding/deleting disk during updating nr_hw_queues")
Reported-by: syzbot+2bcecf3c38cb3e8fdc8d@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/6855034f.a00a0220.137b3.0031.GAE@google.com
Reviewed-by: Yu Kuai 
Cc: Nilay Shroff 
Signed-off-by: Ming Lei 
Reviewed-by: Nilay Shroff 
Link: https://lore.kernel.org/r/20250709111744.2353050-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe 
Signed-off-by: Sasha Levin

block: mtip32xx: Fix usage of dma_map_sg()

2025-08-15T14:38:22+00:00

[ Upstream commit 8e1fab9cccc7b806b0cffdceabb09b310b83b553 ]

The dma_map_sg() can fail and, in case of failure, returns 0.  If it
fails, mtip_hw_submit_io() returns an error.

The dma_unmap_sg() requires the nents parameter to be the same as the
one passed to dma_map_sg(). This patch saves the nents in
command->scatter_ents.

Fixes: 88523a61558a ("block: Add driver for Micron RealSSD pcie flash cards")
Signed-off-by: Thomas Fourier 
Reviewed-by: Andy Shevchenko 
Link: https://lore.kernel.org/r/20250627121123.203731-2-fourier.thomas@gmail.com
Signed-off-by: Jens Axboe 
Signed-off-by: Sasha Levin

ublk: use vmalloc for ublk_device's __queues

2025-08-15T14:38:21+00:00

[ Upstream commit c2f48453b7806d41f5a3270f206a5cd5640ed207 ]

struct ublk_device's __queues points to an allocation with up to
UBLK_MAX_NR_QUEUES (4096) queues, each of which have:
- struct ublk_queue (48 bytes)
- Tail array of up to UBLK_MAX_QUEUE_DEPTH (4096) struct ublk_io's,
  32 bytes each
This means the full allocation can exceed 512 MB, which may well be
impossible to service with contiguous physical pages. Switch to
kvcalloc() and kvfree(), since there is no need for physically
contiguous memory.

Signed-off-by: Caleb Sander Mateos 
Fixes: 71f28f3136af ("ublk_drv: add io_uring based userspace block driver")
Reviewed-by: Ming Lei 
Link: https://lore.kernel.org/r/20250620151008.3976463-2-csander@purestorage.com
Signed-off-by: Jens Axboe 
Signed-off-by: Sasha Levin