Pull block driver updates from Jens Axboe:
"Sitting on top of the core block changes, here are the driver changes
for the 5.15 merge window:
- NVMe updates via Christoph:
- suspend improvements for devices with an HMB (Keith Busch)
- handle double completions more gacefull (Sagi Grimberg)
- cleanup the selects for the nvme core code a bit (Sagi Grimberg)
- don't update queue count when failing to set io queues (Ruozhu Li)
- various nvmet connect fixes (Amit Engel)
- cleanup lightnvm leftovers (Keith Busch, me)
- small cleanups (Colin Ian King, Hou Pu)
- add tracing for the Set Features command (Hou Pu)
- CMB sysfs cleanups (Keith Busch)
- add a mutex_destroy call (Keith Busch)
- remove lightnvm subsystem. It's served its purpose and ultimately
led to zoned nvme support, we no longer need it (Christoph)
- revert floppy O_NDELAY fix (Denis)
- nbd fixes (Hou, Pavel, Baokun)
- nbd locking fixes (Tetsuo)
- nbd device removal fixes (Christoph)
- raid10 rcu warning fix (Xiao)
- raid1 write behind fix (Guoqing)
- rnbd fixes (Gioh, Md Haris)
- misc fixes (Colin)"
* tag 'for-5.15/drivers-2021-08-30' of git://git.kernel.dk/linux-block: (42 commits)
Revert "floppy: reintroduce O_NDELAY fix"
raid1: ensure write behind bio has less than BIO_MAX_VECS sectors
md/raid10: Remove unnecessary rcu_dereference in raid10_handle_discard
nbd: remove nbd->destroy_complete
nbd: only return usable devices from nbd_find_unused
nbd: set nbd->index before releasing nbd_index_mutex
nbd: prevent IDR lookups from finding partially initialized devices
nbd: reset NBD to NULL when restarting in nbd_genl_connect
nbd: add missing locking to the nbd_dev_add error path
nvme: remove the unused NVME_NS_* enum
nvme: remove nvm_ndev from ns
nvme: Have NVME_FABRICS select NVME_CORE instead of transport drivers
block: nbd: add sanity check for first_minor
nvmet: check that host sqsize does not exceed ctrl MQES
nvmet: avoid duplicate qid in connect cmd
nvmet: pass back cntlid on successful completion
nvme-rdma: don't update queue count when failing to set io queues
nvme-tcp: don't update queue count when failing to set io queues
nvme-tcp: pair send_mutex init with destroy
nvme: allow user toggling hmb usage
...
Pull block fixes from Jens Axboe:
- Revert the mq-deadline priority handling, it's causing serious
performance regressions. While experimental patches exists to fix
this up, it's too late to do so now. Revert it and re-do it properly
for 5.15 instead.
- Fix a NULL vs IS_ERR() regression in this release (Dan)
- Fix a mq-deadline accounting regression in this release (Bart)
- Mark cryptoloop as deprecated. It's broken and dm-crypt fully
supports it, and it's actively intefering with loop. Plan on removal
for 5.16 (Christoph)
* tag 'block-5.14-2021-08-27' of git://git.kernel.dk/linux-block:
cryptoloop: add a deprecation warning
pd: fix a NULL vs IS_ERR() check
Revert "block/mq-deadline: Prioritize high-priority requests"
mq-deadline: Fix request accounting
Support for cryptoloop has been officially marked broken and deprecated
in favor of dm-crypt (which supports the same broken algorithms if
needed) in Linux 2.6.4 (released in March 2004), and support for it has
been entirely removed from losetup in util-linux 2.23 (released in April
2013). Add a warning and a deprecation schedule.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20210827163250.255325-1-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The nbd->destroy_complete pointer is not really needed. For creating
a device without a specific index we now simplify skip devices marked
NBD_DESTROY_ON_DISCONNECT as there is not much point to reuse them.
For device creation with a specific index there is no real need to
treat the case of a requested but not finished disconnect different
than any other device that is being shutdown, i.e. we can just return
an error, as a slightly different race window would anyway.
Fixes: 6e4df4c648 ("nbd: reduce the nbd_index_mutex scope")
Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Reported-by: syzbot+2c98885bcd769f56b6d6@syzkaller.appspotmail.com
Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20210825163108.50713-7-hch@lst.de
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Device marked as NBD_DESTROY_ON_DISCONNECT can and should be skipped
given that they won't survive the disconnect. So skip them and try
to grab a reference directly and just continue if the the devices
is being torn down or created and thus has a zero refcount.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20210825163108.50713-6-hch@lst.de
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Previously nbd_index_mutex was held during whole add/remove/lookup
operations in order to guarantee that partially initialized devices are
not reachable via idr_find() or idr_for_each(). But now that partially
initialized devices become reachable as soon as idr_alloc() succeeds,
we need to skip partially initialized devices. Since it seems that
all functions use refcount_inc_not_zero(&nbd->refs) in order to skip
destroying devices, update nbd->refs from zero to non-zero as the last
step of device initialization in order to also skip partially initialized
devices.
Fixes: 6e4df4c648 ("nbd: reduce the nbd_index_mutex scope")
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
[hch: split from a larger patch, added comments]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20210825163108.50713-4-hch@lst.de
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We never checked for errors on add_disk() as this function
returned void. Now that this is fixed, use the shiny new
error handling. The actual cleanup in case of error is
already handled by the caller of null_gendisk_register().
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Link: https://lore.kernel.org/r/20210818144542.19305-12-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Syzbot hit WARNING in internal_create_group(). The problem was in
too big disk->first_minor.
disk->first_minor is initialized by value, which comes from userspace
and there wasn't any sanity checks about value correctness. It can cause
duplicate creation of sysfs files/links, because disk->first_minor will
be passed to MKDEV() which causes truncation to byte. Since maximum
minor value is 0xff, let's check if first_minor is correct minor number.
NOTE: the root case of the reported warning was in wrong error handling
in register_disk(), but we can avoid passing knowingly wrong values to
sysfs API, because sysfs error messages can confuse users. For example:
user passed 1048576 as index, but sysfs complains about duplicate
creation of /dev/block/43:0. It's not obvious how 1048576 becomes 0.
Log and reproducer for above example can be found on syzkaller bug
report page.
Link: https://syzkaller.appspot.com/bug?id=03c2ae9146416edf811958d5fd7acfab75b143d1
Fixes: b0d9111a2d ("nbd: use an idr to keep track of nbd devices")
Reported-by: syzbot+9937dc42271cd87d4b98@syzkaller.appspotmail.com
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Pavel Skripkin <paskripkin@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pull virtio fixes from Michael Tsirkin:
"Fixes in virtio, vhost, and vdpa drivers"
* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
vdpa/mlx5: Fix queue type selection logic
vdpa/mlx5: Avoid destroying MR on empty iotlb
tools/virtio: fix build
virtio_ring: pull in spinlock header
vringh: pull in spinlock header
virtio-blk: Add validation for block size in config space
vringh: Use wiov->used to check for read/write desc order
virtio_vdpa: reject invalid vq indices
vdpa: Add documentation for vdpa_alloc_device() macro
vDPA/ifcvf: Fix return value check for vdpa_alloc_device()
vp_vdpa: Fix return value check for vdpa_alloc_device()
vdpa_sim: Fix return value check for vdpa_alloc_device()
vhost: Fix the calculation in vhost_overflow()
vhost-vdpa: Fix integer overflow in vhost_vdpa_process_iotlb_update()
virtio_pci: Support surprise removal of virtio pci device
virtio: Protect vqs list access
virtio: Keep vring_del_virtqueue() mirror of VQ create
virtio: Improve vq->broken access to avoid any compiler optimization
Pull block fixes from Jens Axboe:
"A few fixes for block that should go into 5.14:
- Revert the mq-deadline cgroup addition. More work is needed on this
front, let's revert it for now and get it right before having it in
a released kernel (Tejun)
- blk-iocost lockdep fix (Ming)
- nbd double completion fix (Xie)
- Fix for non-idling when clearing the shared tag flag (Yu)"
* tag 'block-5.14-2021-08-13' of git://git.kernel.dk/linux-block:
nbd: Aovid double completion of a request
blk-mq: clear active_queues before clearing BLK_MQ_F_TAG_QUEUE_SHARED
Revert "block/mq-deadline: Add cgroup support"
blk-iocost: fix lockdep warning on blkcg->lock
nbd_index_mutex is currently held over add_disk and inside ->open, which
leads to lock order reversals. Refactor the device creation code path
so that nbd_dev_add is called without nbd_index_mutex lock held and
only takes it for the IDR insertation.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20210811124428.2368491-7-hch@lst.de
[axboe: fix whitespace]
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Now open_mutex is used to synchronize partition operations (e.g,
blk_drop_partitions() and blkdev_reread_part()), however it makes
nbd driver broken, because nbd may call del_gendisk() in nbd_release()
or nbd_genl_disconnect() if NBD_CFLAG_DESTROY_ON_DISCONNECT is enabled,
and deadlock occurs, as shown below:
// AB-BA dead-lock
nbd_genl_disconnect blkdev_open
nbd_disconnect_and_put
lock bd_mutex
// last ref
nbd_put
lock nbd_index_mutex
del_gendisk
nbd_open
try lock nbd_index_mutex
try lock bd_mutex
or
// AA dead-lock
nbd_release
lock bd_mutex
nbd_put
try lock bd_mutex
Instead of fixing block layer (e.g, introduce another lock), fixing
the nbd driver to call del_gendisk() in a kworker when
NBD_DESTROY_ON_DISCONNECT is enabled. When NBD_DESTROY_ON_DISCONNECT
is disabled, nbd device will always be destroy through module removal,
and there is no risky of deadlock.
To ensure the reuse of nbd index succeeds, moving the calling of
idr_remove() after del_gendisk(), so if the reused index is not found
in nbd_index_idr, the old disk must have been deleted. And reusing
the existing destroy_complete mechanism to ensure nbd_genl_connect()
will wait for the completion of del_gendisk().
Also adding a new workqueue for nbd removal, so nbd_cleanup()
can ensure all removals complete before exits.
Reported-by: syzbot+0fe7752e52337864d29b@syzkaller.appspotmail.com
Fixes: c76f48eb5c ("block: take bd_mutex around delete_partitions in del_gendisk")
Signed-off-by: Hou Tao <houtao1@huawei.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20210811124428.2368491-2-hch@lst.de
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If user specify a large enough value of NBD blocks option, it may trigger
signed integer overflow which may lead to nbd->config->bytesize becomes a
large or small value, zero in particular.
UBSAN: Undefined behaviour in drivers/block/nbd.c:325:31
signed integer overflow:
1024 * 4611686155866341414 cannot be represented in type 'long long int'
[...]
Call trace:
[...]
handle_overflow+0x188/0x1dc lib/ubsan.c:192
__ubsan_handle_mul_overflow+0x34/0x44 lib/ubsan.c:213
nbd_size_set drivers/block/nbd.c:325 [inline]
__nbd_ioctl drivers/block/nbd.c:1342 [inline]
nbd_ioctl+0x998/0xa10 drivers/block/nbd.c:1395
__blkdev_driver_ioctl block/ioctl.c:311 [inline]
[...]
Although it is not a big deal, still silence the UBSAN by limit
the input value.
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Baokun Li <libaokun1@huawei.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Link: https://lore.kernel.org/r/20210804021212.990223-1-libaokun1@huawei.com
[axboe: dropped unlikely()]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
An untrusted device might presents an invalid block size
in configuration space. This tries to add validation for it
in the validate callback and clear the VIRTIO_BLK_F_BLK_SIZE
feature bit if the value is out of the supported range.
And we also double check the value in virtblk_probe() in
case that it's changed after the validation.
Signed-off-by: Xie Yongji <xieyongji@bytedance.com>
Link: https://lore.kernel.org/r/20210809101609.148-1-xieyongji@bytedance.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Pull block fixes from Jens Axboe:
"A few minor fixes:
- Fix ldm kernel-doc warning (Bart)
- Fix adding offset twice for DMA address in n64cart (Christoph)
- Fix use-after-free in dasd path handling (Stefan)
- Order kyber insert trace correctly (Vincent)
- raid1 errored write handling fix (Wei)
- Fix blk-iolatency queue get failure handling (Yu)"
* tag 'block-5.14-2021-08-07' of git://git.kernel.dk/linux-block:
kyber: make trace_block_rq call consistent with documentation
block/partitions/ldm.c: Fix a kernel-doc warning
blk-iolatency: error out if blk_get_queue() failed in iolatency_set_limit()
n64cart: fix the dma address in n64cart_do_bvec
s390/dasd: fix use after free in dasd path handling
md/raid10: properly indicate failure when ending a failed write request
We noticed that the user interface of Android devices becomes very slow
under memory pressure. This is because Android uses the zram driver on top
of the loop driver for swapping, because under memory pressure the swap
code alternates reads and writes quickly, because mq-deadline is the
default scheduler for loop devices and because mq-deadline delays writes by
five seconds for such a workload with default settings. Fix this by making
the kernel select I/O scheduler 'none' from inside add_disk() for loop
devices. This default can be overridden at any time from user space,
e.g. via a udev rule. This approach has an advantage compared to changing
the I/O scheduler from userspace from 'mq-deadline' into 'none', namely
that synchronize_rcu() does not get called.
This patch changes the default I/O scheduler for loop devices from
'mq-deadline' into 'none'.
Additionally, this patch reduces the Android boot time on my test setup
with 0.5 seconds compared to configuring the loop I/O scheduler from user
space.
Cc: Christoph Hellwig <hch@lst.de>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Martijn Coenen <maco@android.com>
Cc: Jaegeuk Kim <jaegeuk@kernel.org>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20210805174200.3250718-3-bvanassche@acm.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pull block fixes from Jens Axboe:
- gendisk freeing fix (Christoph)
- blk-iocost wake ordering fix (Tejun)
- tag allocation error handling fix (John)
- loop locking fix. While this isn't the prettiest fix in the world,
nobody has any good alternatives for 5.14. Something to likely
revisit for 5.15. (Tetsuo)
* tag 'block-5.14-2021-07-30' of git://git.kernel.dk/linux-block:
block: delay freeing the gendisk
blk-iocost: fix operation ordering in iocg_wake_fn()
blk-mq-sched: Fix blk_mq_sched_alloc_tags() error handling
loop: reintroduce global lock for safe loop_validate_file() traversal
Commit 6cc8e74308 ("loop: scale loop device by introducing per
device lock") re-opened a race window for NULL pointer dereference at
loop_validate_file() where commit 310ca162d7 ("block/loop: Use
global lock for ioctl() operation.") has closed.
Although we need to guarantee that other loop devices will not change
during traversal, we can't take remote "struct loop_device"->lo_mutex
inside loop_validate_file() in order to avoid AB-BA deadlock. Therefore,
introduce a global lock dedicated for loop_validate_file() which is
conditionally taken before local "struct loop_device"->lo_mutex is taken.
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Fixes: 6cc8e74308 ("loop: scale loop device by introducing per device lock")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
rbd_open() and rbd_release() expect that disk->private_data is set to
rbd_dev. Otherwise we hit a NULL pointer dereference when mapping the
image.
URL: https://tracker.ceph.com/issues/51759
Fixes: 195b1956b8 ("rbd: use blk_mq_alloc_disk and blk_cleanup_disk")
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Currently rbd_quiesce_lock() holds lock_rwsem for read while blocking
on releasing_wait completion. On the I/O completion side, each image
request also needs to take lock_rwsem for read. Because rw_semaphore
implementation doesn't allow new readers after a writer has indicated
interest in the lock, this can result in a deadlock if something that
needs to take lock_rwsem for write gets involved. For example:
1. watch error occurs
2. rbd_watch_errcb() takes lock_rwsem for write, clears owner_cid and
releases lock_rwsem
3. after reestablishing the watch, rbd_reregister_watch() takes
lock_rwsem for write and calls rbd_reacquire_lock()
4. rbd_quiesce_lock() downgrades lock_rwsem to for read and blocks on
releasing_wait until running_list becomes empty
5. another watch error occurs
6. rbd_watch_errcb() blocks trying to take lock_rwsem for write
7. no in-flight image request can complete and delete itself from
running_list because lock_rwsem won't be granted anymore
A similar scenario can occur with "lock has been acquired" and "lock
has been released" notification handers which also take lock_rwsem for
write to update owner_cid.
We don't actually get anything useful from sitting on lock_rwsem in
rbd_quiesce_lock() -- owner_cid updates certainly don't need to be
synchronized with. In fact the whole owner_cid tracking logic could
probably be removed from the kernel client because we don't support
proxied maintenance operations.
Cc: stable@vger.kernel.org # 5.3+
URL: https://tracker.ceph.com/issues/42757
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Tested-by: Robin Geuze <robin.geuze@nl.team.blue>
Skipping the "lock has been released" notification if the lock owner
is not what we expect based on owner_cid can lead to I/O hangs.
One example is our own notifications: because owner_cid is cleared
in rbd_unlock(), when we get our own notification it is processed as
unexpected/duplicate and maybe_kick_acquire() isn't called. If a peer
that requested the lock then doesn't go through with acquiring it,
I/O requests that came in while the lock was being quiesced would
be stalled until another I/O request is submitted and kicks acquire
from rbd_img_exclusive_lock().
This makes the comment in rbd_release_lock() actually true: prior to
this change the canceled work was being requeued in response to the
"lock has been acquired" notification from rbd_handle_acquired_lock().
Cc: stable@vger.kernel.org # 5.3+
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Tested-by: Robin Geuze <robin.geuze@nl.team.blue>
Pull block fixes from Jens Axboe:
- NVMe fixes via Christoph:
- fix various races in nvme-pci when shutting down just after
probing (Casey Chen)
- fix a net_device leak in nvme-tcp (Prabhakar Kushwaha)
- Fix regression in xen-blkfront by cleaning up the removal state
machine (Christoph)
- Fix tag_set and queue cleanup ordering regression in nbd (Wang)
- Fix tag_set and queue cleanup ordering regression in pd (Guoqing)
* tag 'block-5.14-2021-07-16' of git://git.kernel.dk/linux-block:
xen-blkfront: sanitize the removal state machine
nbd: fix order of cleaning up the queue and freeing the tagset
pd: fix order of cleaning up the queue and freeing the tagset
nvme-pci: do not call nvme_dev_remove_admin from nvme_remove
nvme-pci: fix multiple races in nvme_setup_io_queues
nvme-tcp: use __dev_get_by_name instead dev_get_by_name for OPT_HOST_IFACE
xen-blkfront has a weird protocol where close message from the remote
side can be delayed, and where hot removals are treated somewhat
differently from regular removals, all leading to potential NULL
pointer removals, and a del_gendisk from the block device release
method, which will deadlock. Fix this by just performing normal hot
removals even when the device is opened like all other Linux block
drivers.
Fixes: c76f48eb5c ("block: take bd_mutex around delete_partitions in del_gendisk")
Reported-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Link: https://lore.kernel.org/r/20210715141711.1257293-1-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
