DMDEBUG will already add a newline to the logging messages, so we
shouldn't be adding it to the message itself.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
The current codebase makes use of the zero-length array language
extension to the C90 standard, but the preferred mechanism to declare
variable-length types such as these ones is a flexible array member[1][2],
introduced in C99:
struct foo {
int stuff;
struct boo array[];
};
By making use of the mechanism above, we will get a compiler warning
in case the flexible array does not occur last in the structure, which
will help us prevent some kind of undefined behavior bugs from being
inadvertently introduced[3] to the codebase from now on.
Also, notice that, dynamic memory allocations won't be affected by
this change:
"Flexible array members have incomplete type, and so the sizeof operator
may not be applied. As a quirk of the original implementation of
zero-length arrays, sizeof evaluates to zero."[1]
sizeof(flexible-array-member) triggers a warning because flexible array
members have incomplete type[1]. There are some instances of code in
which the sizeof operator is being incorrectly/erroneously applied to
zero-length arrays and the result is zero. Such instances may be hiding
some bugs. So, this work (flexible-array member conversions) will also
help to get completely rid of those sorts of issues.
This issue was found with the help of Coccinelle.
[1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html
[2] https://github.com/KSPP/linux/issues/21
[3] commit 7649773293 ("cxgb3/l2t: Fix undefined behaviour")
Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Implement handling for metadata version 2. The new metadata adds a
label and UUID for the device mapper device, and additional UUID for
the underlying block devices.
It also allows for an additional regular drive to be used for
emulating random access zones. The emulated zones will be placed
logically in front of the zones from the zoned block device, causing
the superblocks and metadata to be stored on that device.
The first zone of the original zoned device will be used to hold
another, tertiary copy of the metadata; this copy carries a generation
number of 0 and is never updated; it's just used for identification.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Bob Liu <bob.liu@oracle.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
When looking up zones in dmz_alloc_zone() we need to ignore
metadata zones so as not to accidentally overwrite metadata.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Bob Liu <bob.liu@oracle.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
dm-zoned is becoming quite chatty during startup; reduce the noise
by moving some information to 'debug' level.
Suggested-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Use the metadata label for logging and not the underlying
device.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Bob Liu <bob.liu@oracle.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Use accessors to retrieve the device pointer in preparation
for adding an additional block device.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Bob Liu <bob.liu@oracle.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Replace the 'target' pointer in the bio context with the
device pointer as this is what's actually used.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Bob Liu <bob.liu@oracle.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Use the dmz_zone_to_dev() mapping function to remove the
'dev' argument from reclaim.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Bob Liu <bob.liu@oracle.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
blk_mq_make_request currently needs to grab an q_usage_counter
reference when allocating a request. This is because the block layer
grabs one before calling blk_mq_make_request, but also releases it as
soon as blk_mq_make_request returns. Remove the blk_queue_exit call
after blk_mq_make_request returns, and instead let it consume the
reference. This works perfectly fine for the block layer caller, just
device mapper needs an extra reference as the old problem still
persists there. Open code blk_queue_enter_live in device mapper,
as there should be no other callers and this allows better documenting
why we do a non-try get.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Introduce accessors dmz_dev_is_dying() and dmz_check_dev() to
avoid having to reference the devices directly.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Bob Liu <bob.liu@oracle.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Introduce dmz_metadata_label() to format the device-mapper device
name and use it instead of the device name of the underlying device.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Bob Liu <bob.liu@oracle.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Move fields from the device structure into the metadata structure
and provide accessor functions.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Bob Liu <bob.liu@oracle.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Store the device together with the superblock so that
we don't have to recur to the metadata to find it.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Bob Liu <bob.liu@oracle.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Instead of storing just the first superblock zone and calculate
the secondary relative to that we should be using an array for
holding the superblock zones.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Bob Liu <bob.liu@oracle.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Instead of calculating the zone index by the offset within the
zone array store the index within the structure itself. With that
the helper dmz_id() is pointless and can be replaced with accessing
the ->id value directly.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Bob Liu <bob.liu@oracle.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Add callback for 'dmsetup message' to allow the reclaim process
to be triggered manually.
Eg.
dmsetup message /dev/dm-X 0 message
will start the reclaim process even if the default threshold
of 50 percent of free random zones is not reached.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Bob Liu <bob.liu@oracle.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Add callback to supply information for 'dmsetup status'
and 'dmsetup table'. The output for 'dmsetup status' is
0 <size> zoned <nr_zones> zones <nr_unmap_rnd>/<nr_rnd> random <nr_unmap_seq>/<nr_seq> sequential
where <nr_unmap_rnd> is the number of unmapped (ie free) random zones,
<nr_rnd> the total number of random zones, <nr_unmap_seq> the number
of unmapped sequential zones, and <nr_seq> the total number of
sequential zones.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Bob Liu <bob.liu@oracle.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
This new selector keeps an exponential moving average of the service
time for each path (losely defined as delta between start_io and
end_io), and uses this along with the number of inflight requests to
estimate future service time for a path. Since we don't have a prober
to account for temporally slow paths, re-try "slow" paths every once in
a while (num_paths * historical_service_time). To account for fast paths
transitioning to slow, if a path has not completed any request within
(num_paths * historical_service_time), limit the number of outstanding
requests. To account for low volume situations where number of
inflight IOs would be zero, the last finish time of each path is
factored in.
Signed-off-by: Khazhismel Kumykov <khazhy@google.com>
Co-developed-by: Gabriel Krisman Bertazi <krisman@collabora.com>
Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
The HST path selector needs this information to perform path
prediction. For request-based mpath, struct request's io_start_time_ns
is used, while for bio-based, use the start_time stored in dm_io.
Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
When testing the dm-writecache target on a real DDR persistent memory
(Intel Optane), it turned out that explicit cache flushing using the
clflushopt instruction performs better than non-temporal stores for
block sizes 1k, 2k and 4k.
The dm-writecache target is singlethreaded (all the copying is done
while holding the writecache lock), so it benefits from clwb, see:
http://lore.kernel.org/r/alpine.LRH.2.02.2004160411460.7833@file01.intranet.prod.int.rdu2.redhat.com
Add a new function memcpy_flushcache_optimized() that tests if
clflushopt is present - and if it is, we use it instead of
memcpy_flushcache.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Remove superfluous test if dax_dev is NULL - dax_direct_access already
does this test.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
In commit 4c7da06f5a ("dm persistent data: eliminate unnecessary
return values"), r value in exit_ro_spine will not change, so
exit_ro_spine doesn't need a return value.
Signed-off-by: Zhiqiang Liu <liuzhiqiang26@huawei.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Fixes gcc '-Wunused-but-set-variable' warning:
drivers/md/dm-integrity.c: In function 'integrity_metadata':
drivers/md/dm-integrity.c:1557:12: warning:
variable 'save_metadata_offset' set but not used [-Wunused-but-set-variable]
drivers/md/dm-integrity.c:1556:12: warning:
variable 'save_metadata_block' set but not used [-Wunused-but-set-variable]
They are never used, so remove it.
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Make use of dm_bufio_issue_discard() to pass discards down to the
underlying device.
Signed-off-by: Heinz Mauelshagen <heinzm@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Add functions dm_bufio_issue_discard and dm_bufio_discard_buffers.
dm_bufio_issue_discard sends discard request to the underlying device.
dm_bufio_discard_buffers frees buffers in the range and then calls
dm_bufio_issue_discard.
Also, factor out block_to_sector for reuse in dm_bufio_issue_discard.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
This new target is similar to the linear target except that it emulates
a smaller logical block size on a device with a larger logical block
size. Its main purpose is to emulate 512 byte sectors on 4K native
disks (i.e. 512e).
See Documentation/admin-guide/device-mapper/dm-ebs.rst for details.
Reviewed-by: Damien Le Moal <DamienLeMoal@wdc.com>
Signed-off-by: Heinz Mauelshagen <heinzm@redhat.com>
Signed-off-by: Randy Dunlap <rdunlap@infradead.org> [Kconfig fixes]
Signed-off-by: Zheng Bin <zhengbin13@huawei.com> [static fixes]
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
SCSI LUN passthrough code such as qemu's "scsi-block" device model
pass every IO to the host via SG_IO ioctls. Currently, dm-multipath
calls choose_pgpath() only in the block IO code path, not in the ioctl
code path (unless current_pgpath is NULL). This has the effect that no
path switching and thus no load balancing is done for SCSI-passthrough
IO, unless the active path fails.
Fix this by using the same logic in multipath_prepare_ioctl() as in
multipath_clone_and_map().
Note: The allegedly best path selection algorithm, service-time,
still wouldn't work perfectly, because the io size of the current
request is always set to 0. Changing that for the IO passthrough
case would require the ioctl cmd and arg to be passed to dm's
prepare_ioctl() method.
Signed-off-by: Martin Wilck <mwilck@suse.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Allow one to use "encrypted" in addition to "user" and "logon" key
types for device encryption.
Signed-off-by: Dmitry Baryshkov <dmitry_baryshkov@mentor.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
We must have some way of letting a storage device driver know what
encryption context it should use for en/decrypting a request. However,
it's the upper layers (like the filesystem/fscrypt) that know about and
manages encryption contexts. As such, when the upper layer submits a bio
to the block layer, and this bio eventually reaches a device driver with
support for inline encryption, the device driver will need to have been
told the encryption context for that bio.
We want to communicate the encryption context from the upper layer to the
storage device along with the bio, when the bio is submitted to the block
layer. To do this, we add a struct bio_crypt_ctx to struct bio, which can
represent an encryption context (note that we can't use the bi_private
field in struct bio to do this because that field does not function to pass
information across layers in the storage stack). We also introduce various
functions to manipulate the bio_crypt_ctx and make the bio/request merging
logic aware of the bio_crypt_ctx.
We also make changes to blk-mq to make it handle bios with encryption
contexts. blk-mq can merge many bios into the same request. These bios need
to have contiguous data unit numbers (the necessary changes to blk-merge
are also made to ensure this) - as such, it suffices to keep the data unit
number of just the first bio, since that's all a storage driver needs to
infer the data unit number to use for each data block in each bio in a
request. blk-mq keeps track of the encryption context to be used for all
the bios in a request with the request's rq_crypt_ctx. When the first bio
is added to an empty request, blk-mq will program the encryption context
of that bio into the request_queue's keyslot manager, and store the
returned keyslot in the request's rq_crypt_ctx. All the functions to
operate on encryption contexts are in blk-crypto.c.
Upper layers only need to call bio_crypt_set_ctx with the encryption key,
algorithm and data_unit_num; they don't have to worry about getting a
keyslot for each encryption context, as blk-mq/blk-crypto handles that.
Blk-crypto also makes it possible for request-based layered devices like
dm-rq to make use of inline encryption hardware by cloning the
rq_crypt_ctx and programming a keyslot in the new request_queue when
necessary.
Note that any user of the block layer can submit bios with an
encryption context, such as filesystems, device-mapper targets, etc.
Signed-off-by: Satya Tangirala <satyat@google.com>
Reviewed-by: Eric Biggers <ebiggers@google.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The current codebase makes use of the zero-length array language
extension to the C90 standard, but the preferred mechanism to declare
variable-length types such as these ones is a flexible array member[1][2],
introduced in C99:
struct foo {
int stuff;
struct boo array[];
};
By making use of the mechanism above, we will get a compiler warning
in case the flexible array does not occur last in the structure, which
will help us prevent some kind of undefined behavior bugs from being
inadvertently introduced[3] to the codebase from now on.
Also, notice that, dynamic memory allocations won't be affected by
this change:
"Flexible array members have incomplete type, and so the sizeof operator
may not be applied. As a quirk of the original implementation of
zero-length arrays, sizeof evaluates to zero."[1]
sizeof(flexible-array-member) triggers a warning because flexible array
members have incomplete type[1]. There are some instances of code in
which the sizeof operator is being incorrectly/erroneously applied to
zero-length arrays and the result is zero. Such instances may be hiding
some bugs. So, this work (flexible-array member conversions) will also
help to get completely rid of those sorts of issues.
This issue was found with the help of Coccinelle.
[1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html
[2] https://github.com/KSPP/linux/issues/21
[3] commit 7649773293 ("cxgb3/l2t: Fix undefined behaviour")
Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: Song Liu <songliubraving@fb.com>
Add a missing newline when printing module parameter 'start_ro' by
sysfs.
Signed-off-by: Xiongfeng Wang <wangxiongfeng2@huawei.com>
Signed-off-by: Song Liu <songliubraving@fb.com>
When using RAID1 and write-behind, md can deadlock when errors occur. With
write-behind, r1bio structs can be accounted by raid1 as queued but not
counted as pending. The pending count is dropped when the original bio is
returned complete but write-behind for the r1bio may still be active.
This breaks the accounting used in some conditions to know when the raid1
md device has reached an idle state. It can result in calls to
freeze_array deadlocking. freeze_array will never complete from a negative
"unqueued" value being calculated due to a queued count larger than the
pending count.
To properly account for write-behind, move the call to allow_barrier from
call_bio_endio to raid_end_bio_io. When using write-behind, md can call
call_bio_endio before all write-behind I/O is complete. Using
raid_end_bio_io for the point to call allow_barrier will release the
pending count at a point where all I/O for an r1bio, even write-behind, is
done.
Signed-off-by: David Jeffery <djeffery@redhat.com>
Signed-off-by: Song Liu <songliubraving@fb.com>
In mddev_create_serial_pool(), memalloc scope APIs memalloc_noio_save()
and memalloc_noio_restore() are used when allocating memory by calling
mempool_create_kmalloc_pool(). After adding the memalloc scope APIs in
raid array suspend context, it is unncessary to explicitly call them
around mempool_create_kmalloc_pool() any longer.
This patch removes the redundant memalloc scope APIs in
mddev_create_serial_pool().
Signed-off-by: Coly Li <colyli@suse.de>
Cc: Guoqing Jiang <guoqing.jiang@cloud.ionos.com>
Signed-off-by: Song Liu <songliubraving@fb.com>
Code comments of scribble_alloc() is outdated for a while. This patch
update the comments in function header for the new parameter list.
Suggested-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Coly Li <colyli@suse.de>
Signed-off-by: Song Liu <songliubraving@fb.com>
Using GFP_NOIO flag to call scribble_alloc() from resize_chunk() does
not have the expected behavior. kvmalloc_array() inside scribble_alloc()
which receives the GFP_NOIO flag will eventually call kmalloc_node() to
allocate physically continuous pages.
Now we have memalloc scope APIs in mddev_suspend()/mddev_resume() to
prevent memory reclaim I/Os during raid array suspend context, calling
to kvmalloc_array() with GFP_KERNEL flag may avoid deadlock of recursive
I/O as expected.
This patch removes the useless gfp flags from parameters list of
scribble_alloc(), and call kvmalloc_array() with GFP_KERNEL flag. The
incorrect GFP_NOIO flag does not exist anymore.
Fixes: b330e6a49d ("md: convert to kvmalloc")
Suggested-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Coly Li <colyli@suse.de>
Signed-off-by: Song Liu <songliubraving@fb.com>
In raid5.c:resize_chunk(), scribble_alloc() is called with GFP_NOIO
flag, then it is sent into kvmalloc_array() inside scribble_alloc().
The problem is kvmalloc_array() eventually calls kvmalloc_node() which
does not accept non GFP_KERNEL compatible flag like GFP_NOIO, then
kmalloc_node() is called indeed to allocate physically continuous
pages. When system memory is under heavy pressure, and the requesting
size is large, there is high probability that allocating continueous
pages will fail.
But simply using GFP_KERNEL flag to call kvmalloc_array() is also
progblematic. In the code path where scribble_alloc() is called, the
raid array is suspended, if kvmalloc_node() triggers memory reclaim I/Os
and such I/Os go back to the suspend raid array, deadlock will happen.
What is desired here is to allocate non-physically (a.k.a virtually)
continuous pages and avoid memory reclaim I/Os. Michal Hocko suggests
to use the mmealloc sceope APIs to restrict memory reclaim I/O in
allocating context, specifically to call memalloc_noio_save() when
suspend the raid array and to call memalloc_noio_restore() when
resume the raid array.
This patch adds the memalloc scope APIs in mddev_suspend() and
mddev_resume(), to restrict memory reclaim I/Os during the raid array
is suspended. The benifit of adding the memalloc scope API in the
unified entry point mddev_suspend()/mddev_resume() is, no matter which
md raid array type (personality), we are sure the deadlock by recursive
memory reclaim I/O won't happen on the suspending context.
Please notice that the memalloc scope APIs only take effect on the raid
array suspending context, if the memory allocation is from another new
created kthread after raid array suspended, the recursive memory reclaim
I/Os won't be restricted. The mddev_suspend()/mddev_resume() entries are
used for the critical section where the raid metadata is modifying,
creating a kthread to allocate memory inside the critical section is
queer and very probably being buggy.
Fixes: b330e6a49d ("md: convert to kvmalloc")
Suggested-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Coly Li <colyli@suse.de>
Signed-off-by: Song Liu <songliubraving@fb.com>
It is not not necessary to add a newline for them since they don't exceed
80 characters, and it is not intutive to distinguish ->hot_add_disk() from
hot_add_disk() too.
Signed-off-by: Guoqing Jiang <guoqing.jiang@cloud.ionos.com>
Signed-off-by: Song Liu <songliubraving@fb.com>
Since rdev->kobj is removed asynchronously, it is possible that the
rdev->kobj still exists when try to add the rdev again after rdev
is removed. But this path md_ioctl (HOT_ADD_DISK) -> hot_add_disk
-> bind_rdev_to_array missed it.
Signed-off-by: Guoqing Jiang <guoqing.jiang@cloud.ionos.com>
Signed-off-by: Song Liu <songliubraving@fb.com>
Since the purpose of call flush_workqueue in new_dev_store is to ensure
md_delayed_delete() has completed, so we should check rdev->del_work is
pending or not.
To suppress lockdep warning, we have to check mddev->del_work while
md_delayed_delete is attached to rdev->del_work, so it is not aligned
to the purpose of flush workquee. So a new workqueue is needed to avoid
the awkward situation, and introduce a new func flush_rdev_wq to flush
the new workqueue after check if there was pending work.
Also like new_dev_store, ADD_NEW_DISK ioctl has the same purpose to flush
workqueue while it holds bdev->bd_mutex, so make the same change applies
to the ioctl to avoid similar lock issue.
And md_delayed_delete actually wants to delete rdev, so rename the function
to rdev_delayed_delete.
Signed-off-by: Guoqing Jiang <guoqing.jiang@cloud.ionos.com>
Signed-off-by: Song Liu <songliubraving@fb.com>
Coly reported possible circular locking dependencyi with LOCKDEP enabled,
quote the below info from the detailed report [1].
[ 1607.673903] Chain exists of:
[ 1607.673903] kn->count#256 --> (wq_completion)md_misc -->
(work_completion)(&rdev->del_work)
[ 1607.673903]
[ 1607.827946] Possible unsafe locking scenario:
[ 1607.827946]
[ 1607.898780] CPU0 CPU1
[ 1607.952980] ---- ----
[ 1608.007173] lock((work_completion)(&rdev->del_work));
[ 1608.069690] lock((wq_completion)md_misc);
[ 1608.149887] lock((work_completion)(&rdev->del_work));
[ 1608.242563] lock(kn->count#256);
[ 1608.283238]
[ 1608.283238] *** DEADLOCK ***
[ 1608.283238]
[ 1608.354078] 2 locks held by kworker/5:0/843:
[ 1608.405152] #0: ffff8889eecc9948 ((wq_completion)md_misc){+.+.}, at:
process_one_work+0x42b/0xb30
[ 1608.512399] #1: ffff888a1d3b7e10
((work_completion)(&rdev->del_work)){+.+.}, at: process_one_work+0x42b/0xb30
[ 1608.632130]
Since works (rdev->del_work and mddev->del_work) are queued in md_misc_wq,
then lockdep_map lock is held if either of them are running, then both of
them try to hold kernfs lock by call kobject_del. Then if new_dev_store
or array_state_store are triggered by write to the related sysfs node, so
the write operation gets kernfs lock, but need the lockdep_map because all
of them would trigger flush_workqueue(md_misc_wq) finally, then the same
lockdep_map lock is needed.
To suppress the lockdep warnning, we should flush the workqueue in case the
related work is pending. And several works are attached to md_misc_wq, so
we need to check which work should be checked:
1. for __md_stop_writes, the purpose of call flush workqueue is ensure sync
thread is started if it was starting, so check mddev->del_work is pending
or not since md_start_sync is attached to mddev->del_work.
2. __md_stop flushes md_misc_wq to ensure event_work is done, check the
event_work is enough. Assume raid_{ctr,dtr} -> md_stop -> __md_stop doesn't
need the kernfs lock.
3. both new_dev_store (holds kernfs lock) and ADD_NEW_DISK ioctl (holds the
bdev->bd_mutex) call flush_workqueue to ensure md_delayed_delete has
completed, this case will be handled in next patch.
4. md_open flushes workqueue to ensure the previous md is disappeared, but
it holds bdev->bd_mutex then try to flush workqueue, so it is better to
check mddev->del_work as well to avoid potential lock issue, this will be
done in another patch.
[1]: https://marc.info/?l=linux-raid&m=158518958031584&w=2
Cc: Coly Li <colyli@suse.de>
Reported-by: Coly Li <colyli@suse.de>
Signed-off-by: Guoqing Jiang <guoqing.jiang@cloud.ionos.com>
Signed-off-by: Song Liu <songliubraving@fb.com>
5.7 merge window.
- Fix potential for DM writecache data corruption during DM table
reloads.
- Fix DM verity's FEC support's hash block number calculation in
verity_fec_decode().
- Fix bio-based DM multipath crash due to use of stale copy of
MPATHF_QUEUE_IO flag state in __map_bio().
-----BEGIN PGP SIGNATURE-----
iQFHBAABCAAxFiEEJfWUX4UqZ4x1O2wixSPxCi2dA1oFAl6rSn4THHNuaXR6ZXJA
cmVkaGF0LmNvbQAKCRDFI/EKLZ0DWjmFB/9kwi4L5SQTg81ak0jmiO4lNSxqvc8s
ZJUyT8m/Iheh6FWo6kZYyfN+YVPPwXRFDWk4TGSrKyoqElTbpxkkmVxE7nhp9Z+O
1f7cfD8vCsTexHxYjxx3DxW529YVjvccifhaJFQgCA3II8+0to9PFzc7v6JpFBGS
1CWd169OUDHe2XGNmah0lbgwEgb7ZQRn9MNrkdYu3L9HihNLs8h4uin390FlfhSj
+/rS89jkA9X5MhFnspKrX0wGl3qoQBzFFvvn4KKPcH8EPt5zsUPVo+/rTOBL8Tr8
VXDYKco4CDfuqzB5LdHeTi3mKwGq+fpPmwzRTk+/gosDZHA49m7mLKGB
=cr8K
-----END PGP SIGNATURE-----
Merge tag 'for-5.7/dm-fixes-2' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm
Pull device mapper fixes from Mike Snitzer:
- Document DM integrity allow_discard feature that was added during 5.7
merge window.
- Fix potential for DM writecache data corruption during DM table
reloads.
- Fix DM verity's FEC support's hash block number calculation in
verity_fec_decode().
- Fix bio-based DM multipath crash due to use of stale copy of
MPATHF_QUEUE_IO flag state in __map_bio().
* tag 'for-5.7/dm-fixes-2' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
dm multipath: use updated MPATHF_QUEUE_IO on mapping for bio-based mpath
dm verity fec: fix hash block number in verity_fec_decode
dm writecache: fix data corruption when reloading the target
dm integrity: document allow_discard option
Call blk_mq_make_request when no ->make_request_fn is set. This is
safe now that blk_alloc_queue always sets up the pointer for make_request
based drivers. This avoids an indirect call in the blk-mq driver I/O
fast path, which is rather expensive due to spectre mitigations.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The make_request_fn pointer should only be assigned by blk_alloc_queue.
Fix a left over manual initialization.
Fixes: ff27668ce8 ("bcache: pass the make_request methods to blk_queue_make_request")
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The error correction data is computed as if data and hash blocks
were concatenated. But hash block number starts from v->hash_start.
So, we have to calculate hash block number based on that.
Fixes: a739ff3f54 ("dm verity: add support for forward error correction")
Cc: stable@vger.kernel.org
Signed-off-by: Sunwook Eom <speed.eom@samsung.com>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
The dm-writecache reads metadata in the target constructor. However, when
we reload the target, there could be another active instance running on
the same device. This is the sequence of operations when doing a reload:
1. construct new target
2. suspend old target
3. resume new target
4. destroy old target
Metadata that were written by the old target between steps 1 and 2 would
not be visible by the new target.
Fix the data corruption by loading the metadata in the resume handler.
Also, validate block_size is at least as large as both the devices'
logical block size and only read 1 block from the metadata during
target constructor -- no need to read entirety of metadata now that it
is done during resume.
Fixes: 48debafe4f ("dm: add writecache target")
Cc: stable@vger.kernel.org # v4.18+
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
- Add support for region alignment configuration and enforcement to
fix compatibility across architectures and PowerPC page size
configurations.
- Introduce 'zero_page_range' as a dax operation. This facilitates
filesystem-dax operation without a block-device.
- Introduce phys_to_target_node() to facilitate drivers that want to
know resulting numa node if a given reserved address range was
onlined.
- Advertise a persistence-domain for of_pmem and papr_scm. The
persistence domain indicates where cpu-store cycles need to reach in
the platform-memory subsystem before the platform will consider them
power-fail protected.
- Promote numa_map_to_online_node() to a cross-kernel generic facility.
- Save x86 numa information to allow for node-id lookups for reserved
memory ranges, deploy that capability for the e820-pmem driver.
- Pick up some miscellaneous minor fixes, that missed v5.6-final,
including a some smatch reports in the ioctl path and some unit test
compilation fixups.
- Fixup some flexible-array declarations.
-----BEGIN PGP SIGNATURE-----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=sY4N
-----END PGP SIGNATURE-----
Merge tag 'libnvdimm-for-5.7' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm
Pull libnvdimm and dax updates from Dan Williams:
"There were multiple touches outside of drivers/nvdimm/ this round to
add cross arch compatibility to the devm_memremap_pages() interface,
enhance numa information for persistent memory ranges, and add a
zero_page_range() dax operation.
This cycle I switched from the patchwork api to Konstantin's b4 script
for collecting tags (from x86, PowerPC, filesystem, and device-mapper
folks), and everything looks to have gone ok there. This has all
appeared in -next with no reported issues.
Summary:
- Add support for region alignment configuration and enforcement to
fix compatibility across architectures and PowerPC page size
configurations.
- Introduce 'zero_page_range' as a dax operation. This facilitates
filesystem-dax operation without a block-device.
- Introduce phys_to_target_node() to facilitate drivers that want to
know resulting numa node if a given reserved address range was
onlined.
- Advertise a persistence-domain for of_pmem and papr_scm. The
persistence domain indicates where cpu-store cycles need to reach
in the platform-memory subsystem before the platform will consider
them power-fail protected.
- Promote numa_map_to_online_node() to a cross-kernel generic
facility.
- Save x86 numa information to allow for node-id lookups for reserved
memory ranges, deploy that capability for the e820-pmem driver.
- Pick up some miscellaneous minor fixes, that missed v5.6-final,
including a some smatch reports in the ioctl path and some unit
test compilation fixups.
- Fixup some flexible-array declarations"
* tag 'libnvdimm-for-5.7' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (29 commits)
dax: Move mandatory ->zero_page_range() check in alloc_dax()
dax,iomap: Add helper dax_iomap_zero() to zero a range
dax: Use new dax zero page method for zeroing a page
dm,dax: Add dax zero_page_range operation
s390,dcssblk,dax: Add dax zero_page_range operation to dcssblk driver
dax, pmem: Add a dax operation zero_page_range
pmem: Add functions for reading/writing page to/from pmem
libnvdimm: Update persistence domain value for of_pmem and papr_scm device
tools/test/nvdimm: Fix out of tree build
libnvdimm/region: Fix build error
libnvdimm/region: Replace zero-length array with flexible-array member
libnvdimm/label: Replace zero-length array with flexible-array member
ACPI: NFIT: Replace zero-length array with flexible-array member
libnvdimm/region: Introduce an 'align' attribute
libnvdimm/region: Introduce NDD_LABELING
libnvdimm/namespace: Enforce memremap_compat_align()
libnvdimm/pfn: Prevent raw mode fallback if pfn-infoblock valid
libnvdimm: Out of bounds read in __nd_ioctl()
acpi/nfit: improve bounds checking for 'func'
mm/memremap_pages: Introduce memremap_compat_align()
...
If all the bytes are equal to DISCARD_FILLER, we want to accept the
buffer. If any of the bytes are different, we must do thorough
tag-by-tag checking.
The condition was inverted.
Fixes: 84597a44a9 ("dm integrity: add optional discard support")
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
This reverts commit effd58c95f.
blk_queue_split() is causing excessive IO splitting -- because
blk_max_size_offset() depends on 'chunk_sectors' limit being set and
if it isn't (as is the case for DM targets!) it falls back to
splitting on a 'max_sectors' boundary regardless of offset.
"Fix" this by reverting back to _not_ using blk_queue_split() in
dm_process_bio() for normal IO (reads and writes). Long-term fix is
still TBD but it should focus on training blk_max_size_offset() to
call into a DM provided hook (to call DM's max_io_len()).
Test results from simple misaligned IO test on 4-way dm-striped device
with chunksize of 128K and stripesize of 512K:
xfs_io -d -c 'pread -b 2m 224s 4072s' /dev/mapper/stripe_dev
before this revert:
253,0 21 1 0.000000000 2206 Q R 224 + 4072 [xfs_io]
253,0 21 2 0.000008267 2206 X R 224 / 480 [xfs_io]
253,0 21 3 0.000010530 2206 X R 224 / 256 [xfs_io]
253,0 21 4 0.000027022 2206 X R 480 / 736 [xfs_io]
253,0 21 5 0.000028751 2206 X R 480 / 512 [xfs_io]
253,0 21 6 0.000033323 2206 X R 736 / 992 [xfs_io]
253,0 21 7 0.000035130 2206 X R 736 / 768 [xfs_io]
253,0 21 8 0.000039146 2206 X R 992 / 1248 [xfs_io]
253,0 21 9 0.000040734 2206 X R 992 / 1024 [xfs_io]
253,0 21 10 0.000044694 2206 X R 1248 / 1504 [xfs_io]
253,0 21 11 0.000046422 2206 X R 1248 / 1280 [xfs_io]
253,0 21 12 0.000050376 2206 X R 1504 / 1760 [xfs_io]
253,0 21 13 0.000051974 2206 X R 1504 / 1536 [xfs_io]
253,0 21 14 0.000055881 2206 X R 1760 / 2016 [xfs_io]
253,0 21 15 0.000057462 2206 X R 1760 / 1792 [xfs_io]
253,0 21 16 0.000060999 2206 X R 2016 / 2272 [xfs_io]
253,0 21 17 0.000062489 2206 X R 2016 / 2048 [xfs_io]
253,0 21 18 0.000066133 2206 X R 2272 / 2528 [xfs_io]
253,0 21 19 0.000067507 2206 X R 2272 / 2304 [xfs_io]
253,0 21 20 0.000071136 2206 X R 2528 / 2784 [xfs_io]
253,0 21 21 0.000072764 2206 X R 2528 / 2560 [xfs_io]
253,0 21 22 0.000076185 2206 X R 2784 / 3040 [xfs_io]
253,0 21 23 0.000077486 2206 X R 2784 / 2816 [xfs_io]
253,0 21 24 0.000080885 2206 X R 3040 / 3296 [xfs_io]
253,0 21 25 0.000082316 2206 X R 3040 / 3072 [xfs_io]
253,0 21 26 0.000085788 2206 X R 3296 / 3552 [xfs_io]
253,0 21 27 0.000087096 2206 X R 3296 / 3328 [xfs_io]
253,0 21 28 0.000093469 2206 X R 3552 / 3808 [xfs_io]
253,0 21 29 0.000095186 2206 X R 3552 / 3584 [xfs_io]
253,0 21 30 0.000099228 2206 X R 3808 / 4064 [xfs_io]
253,0 21 31 0.000101062 2206 X R 3808 / 3840 [xfs_io]
253,0 21 32 0.000104956 2206 X R 4064 / 4096 [xfs_io]
253,0 21 33 0.001138823 0 C R 4096 + 200 [0]
after this revert:
253,0 18 1 0.000000000 4430 Q R 224 + 3896 [xfs_io]
253,0 18 2 0.000018359 4430 X R 224 / 256 [xfs_io]
253,0 18 3 0.000028898 4430 X R 256 / 512 [xfs_io]
253,0 18 4 0.000033535 4430 X R 512 / 768 [xfs_io]
253,0 18 5 0.000065684 4430 X R 768 / 1024 [xfs_io]
253,0 18 6 0.000091695 4430 X R 1024 / 1280 [xfs_io]
253,0 18 7 0.000098494 4430 X R 1280 / 1536 [xfs_io]
253,0 18 8 0.000114069 4430 X R 1536 / 1792 [xfs_io]
253,0 18 9 0.000129483 4430 X R 1792 / 2048 [xfs_io]
253,0 18 10 0.000136759 4430 X R 2048 / 2304 [xfs_io]
253,0 18 11 0.000152412 4430 X R 2304 / 2560 [xfs_io]
253,0 18 12 0.000160758 4430 X R 2560 / 2816 [xfs_io]
253,0 18 13 0.000183385 4430 X R 2816 / 3072 [xfs_io]
253,0 18 14 0.000190797 4430 X R 3072 / 3328 [xfs_io]
253,0 18 15 0.000197667 4430 X R 3328 / 3584 [xfs_io]
253,0 18 16 0.000218751 4430 X R 3584 / 3840 [xfs_io]
253,0 18 17 0.000226005 4430 X R 3840 / 4096 [xfs_io]
253,0 18 18 0.000250404 4430 Q R 4120 + 176 [xfs_io]
253,0 18 19 0.000847708 0 C R 4096 + 24 [0]
253,0 18 20 0.000855783 0 C R 4120 + 176 [0]
Fixes: effd58c95f ("dm: always call blk_queue_split() in dm_process_bio()")
Cc: stable@vger.kernel.org
Reported-by: Andreas Gruenbacher <agruenba@redhat.com>
Tested-by: Barry Marson <bmarson@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Otherwise:
In file included from drivers/md/dm-integrity.c:13:
drivers/md/dm-integrity.c: In function 'dm_integrity_status':
drivers/md/dm-integrity.c:3061:10: error: format '%llu' expects
argument of type 'long long unsigned int', but argument 4 has type
'long int' [-Werror=format=]
DMEMIT("%llu %llu",
^~~~~~~~~~~
atomic64_read(&ic->number_of_mismatches),
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
./include/linux/device-mapper.h:550:46: note: in definition of macro 'DMEMIT'
0 : scnprintf(result + sz, maxlen - sz, x))
^
cc1: all warnings being treated as errors
Fixes: 7649194a16 ("dm integrity: remove sector type casts")
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
zero_page_range() dax operation is mandatory for dax devices. Right now
that check happens in dax_zero_page_range() function. Dan thinks that's
too late and its better to do the check earlier in alloc_dax().
I also modified alloc_dax() to return pointer with error code in it in
case of failure. Right now it returns NULL and caller assumes failure
happened due to -ENOMEM. But with this ->zero_page_range() check, I
need to return -EINVAL instead.
Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
Link: https://lore.kernel.org/r/20200401161125.GB9398@redhat.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
This patch adds support for dax zero_page_range operation to dm targets.
Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
Acked-by: Mike Snitzer <snitzer@redhat.com>
Link: https://lore.kernel.org/r/20200228163456.1587-5-vgoyal@redhat.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
flushed while userspace monitors for completion to then discommision
use of caching.
- Optimize DM writecache superblock writing and also yield CPU while
initializing writecache on large PMEM devices to avoid CPU stalls.
- Various fixes to DM integrity target while preparing for the
ability to resize a DM integrity device. In addition to resize
support, add optional discard support with the "allow_discards"
feature.
- Fix DM clone target's discard handling and overflow bugs which could
cause data corruption.
- Fix memory leak in destructor for DM verity FEC support.
- Fix DM zoned target's redundant increment of nr_rnd_zones.
- Small cleanup in DM crypt to use crypt_integrity_aead() helper.
-----BEGIN PGP SIGNATURE-----
iQFHBAABCAAxFiEEJfWUX4UqZ4x1O2wixSPxCi2dA1oFAl6ExcsTHHNuaXR6ZXJA
cmVkaGF0LmNvbQAKCRDFI/EKLZ0DWj6OB/4n/EmXRI3x9uFTyaFFEjaALTUx7gye
hIlOLtRTFmU6yit/uqAARLDBMDElhL/ze8RKs/TSmi/FH37u8d6DscG5dPatCsF1
dZ7z77uxhc0RQ+WkyMBtYqxO1OGzULt8434Pos0x1aoPrK+wUEpJOcZAJompAVfj
nD3AbJ92zcv7DEdJGiCbViIrgrkAXkUWByXmn/l0AIJEjyxeCLhJdx76I+9PesOJ
JKbbjLu1w19Yyo807CRBQLhC9fXhDUJO19jIlKRfGZ9Xa6V2xVuB45VVYiM/jGqI
L9z6SsXBquX+8x9HgARuw82EkBp5DeazjrHQ2jHMHjMBhz+NFSK0MMnD
=27Eq
-----END PGP SIGNATURE-----
Merge tag 'for-5.7/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm
Pull device mapper updates from Mike Snitzer:
- Add DM writecache "cleaner" policy feature that allows cache to be
flushed while userspace monitors for completion to then discommision
use of caching.
- Optimize DM writecache superblock writing and also yield CPU while
initializing writecache on large PMEM devices to avoid CPU stalls.
- Various fixes to DM integrity target while preparing for the ability
to resize a DM integrity device. In addition to resize support, add
optional discard support with the "allow_discards" feature.
- Fix DM clone target's discard handling and overflow bugs which could
cause data corruption.
- Fix memory leak in destructor for DM verity FEC support.
- Fix DM zoned target's redundant increment of nr_rnd_zones.
- Small cleanup in DM crypt to use crypt_integrity_aead() helper.
* tag 'for-5.7/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
dm clone metadata: Fix return type of dm_clone_nr_of_hydrated_regions()
dm clone: Add missing casts to prevent overflows and data corruption
dm clone: Add overflow check for number of regions
dm clone: Fix handling of partial region discards
dm writecache: add cond_resched to avoid CPU hangs
dm integrity: improve discard in journal mode
dm integrity: add optional discard support
dm integrity: allow resize of the integrity device
dm integrity: factor out get_provided_data_sectors()
dm integrity: don't replay journal data past the end of the device
dm integrity: remove sector type casts
dm integrity: fix a crash with unusually large tag size
dm zoned: remove duplicate nr_rnd_zones increase in dmz_init_zone()
dm verity fec: fix memory leak in verity_fec_dtr
dm writecache: optimize superblock write
dm writecache: implement gradual cleanup
dm writecache: implement the "cleaner" policy
dm writecache: do direct write if the cache is full
dm integrity: print device name in integrity_metadata() error message
dm crypt: use crypt_integrity_aead() helper
dm_clone_nr_of_hydrated_regions() returns the number of regions that
have been hydrated so far. In order to do so it employs bitmap_weight().
Until now, the return type of dm_clone_nr_of_hydrated_regions() was
unsigned long.
Because bitmap_weight() returns an int, in case BITS_PER_LONG == 64 and
the return value of bitmap_weight() is 2^31 (the maximum allowed number
of regions for a device), the result is sign extended from 32 bits to 64
bits and an incorrect value is displayed, in the status output of
dm-clone, as the number of hydrated regions.
Fix this by having dm_clone_nr_of_hydrated_regions() return an unsigned
int.
Fixes: 7431b7835f ("dm: add clone target")
Cc: stable@vger.kernel.org # v5.4+
Signed-off-by: Nikos Tsironis <ntsironis@arrikto.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Add missing casts when converting from regions to sectors.
In case BITS_PER_LONG == 32, the lack of the appropriate casts can lead
to overflows and miscalculation of the device sector.
As a result, we could end up discarding and/or copying the wrong parts
of the device, thus corrupting the device's data.
Fixes: 7431b7835f ("dm: add clone target")
Cc: stable@vger.kernel.org # v5.4+
Signed-off-by: Nikos Tsironis <ntsironis@arrikto.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Add overflow check for clone->nr_regions variable, which holds the
number of regions of the target.
The overflow can occur with sufficiently large devices, if BITS_PER_LONG
== 32. E.g., if the region size is 8 sectors (4K), the overflow would
occur for device sizes > 34359738360 sectors (~16TB).
This could result in multiple device sectors wrongly mapping to the same
region number, due to the truncation from 64 bits to 32 bits, which
would lead to data corruption.
Fixes: 7431b7835f ("dm: add clone target")
Cc: stable@vger.kernel.org # v5.4+
Signed-off-by: Nikos Tsironis <ntsironis@arrikto.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
There is a bug in the way dm-clone handles discards, which can lead to
discarding the wrong blocks or trying to discard blocks beyond the end
of the device.
This could lead to data corruption, if the destination device indeed
discards the underlying blocks, i.e., if the discard operation results
in the original contents of a block to be lost.
The root of the problem is the code that calculates the range of regions
covered by a discard request and decides which regions to discard.
Since dm-clone handles the device in units of regions, we don't discard
parts of a region, only whole regions.
The range is calculated as:
rs = dm_sector_div_up(bio->bi_iter.bi_sector, clone->region_size);
re = bio_end_sector(bio) >> clone->region_shift;
, where 'rs' is the first region to discard and (re - rs) is the number
of regions to discard.
The bug manifests when we try to discard part of a single region, i.e.,
when we try to discard a block with size < region_size, and the discard
request both starts at an offset with respect to the beginning of that
region and ends before the end of the region.
The root cause is the following comparison:
if (rs == re)
// skip discard and complete original bio immediately
, which doesn't take into account that 'rs' might be greater than 're'.
Thus, we then issue a discard request for the wrong blocks, instead of
skipping the discard all together.
Fix the check to also take into account the above case, so we don't end
up discarding the wrong blocks.
Also, add some range checks to dm_clone_set_region_hydrated() and
dm_clone_cond_set_range(), which update dm-clone's region bitmap.
Note that the aforementioned bug doesn't cause invalid memory accesses,
because dm_clone_is_range_hydrated() returns True for this case, so the
checks are just precautionary.
Fixes: 7431b7835f ("dm: add clone target")
Cc: stable@vger.kernel.org # v5.4+
Signed-off-by: Nikos Tsironis <ntsironis@arrikto.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Initializing a dm-writecache device can take a long time when the
persistent memory device is large. Add cond_resched() to a few loops
to avoid warnings that the CPU is stuck.
Cc: stable@vger.kernel.org # v4.18+
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Current make_request based drivers use either blk_alloc_queue_node or
blk_alloc_queue to allocate a queue, and then set up the make_request_fn
function pointer and a few parameters using the blk_queue_make_request
helper. Simplify this by passing the make_request pointer to
blk_alloc_queue, and while at it merge the _node variant into the main
helper by always passing a node_id, and remove the superfluous gfp_mask
parameter. A lower-level __blk_alloc_queue is kept for the blk-mq case.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
bcache is the only driver not actually passing its make_request
methods to blk_queue_make_request, but instead just sets them up
manually a little later. Make bcache follow the common way of
setting up make_request based queues.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
These macros are just used by a few files. Move them out of genhd.h,
which is included everywhere into a new standalone header.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Commit 253a99d95d ("bcache: move macro btree() and btree_root()
into btree.h") makes two duplicated declaration into btree.h,
typedef int (btree_map_keys_fn)();
int bch_btree_map_keys();
The kbuild test robot <lkp@intel.com> detects and reports this
problem and this patch fixes it by removing the duplicated ones.
Fixes: 253a99d95d ("bcache: move macro btree() and btree_root() into btree.h")
Reported-by: kbuild test robot <lkp@intel.com>
Signed-off-by: Coly Li <colyli@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
When we discard something that is present in the journal, we flush the
journal first, so that discarded blocks are not overwritten by the journal
content.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Add an argument "allow_discards" that enables discard processing on
dm-integrity device. Discards are only allowed to devices using
internal hash.
When a block is discarded the integrity tag is filled with
DISCARD_FILLER (0xf6) bytes.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
If the size of the underlying device changes, change the size of the
integrity device too.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Move code to a new function get_provided_data_sectors().
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Following commits will make it possible to shrink or extend the device. If
the device was shrunk, we don't want to replay journal data pointing past
the end of the device.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Since the commit 72deb455b5 ("block:
remove CONFIG_LBDAF") sector_t is always defined as unsigned long
long.
Delete the needless type casts in printk and avoids some warnings if
DEBUG_PRINT is defined.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
If the user specifies tag size larger than HASH_MAX_DIGESTSIZE,
there's a crash in integrity_metadata().
Cc: stable@vger.kernel.org
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
zmd->nr_rnd_zones was increased twice by mistake. The other place it
is increased in dmz_init_zone() is the only one needed:
1131 zmd->nr_useable_zones++;
1132 if (dmz_is_rnd(zone)) {
1133 zmd->nr_rnd_zones++;
^^^
Fixes: 3b1a94c88b ("dm zoned: drive-managed zoned block device target")
Cc: stable@vger.kernel.org
Signed-off-by: Bob Liu <bob.liu@oracle.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
If we write a superblock in writecache_flush, we don't need to set bit and
scan the bitmap for it - we can just write the superblock directly. Also,
we can set the flag REQ_FUA on the write bio, so that we don't need to
submit a flush bio afterwards.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
If a block is stored in the cache for too long, it will now be
written to the underlying device and cleaned up.
Add a new option "max_age" that specifies the maximum age of a block
in milliseconds.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
The "flush" or "flush_on_suspend" messages flush the whole cache. However,
these flushing methods can take some time and the process is left in
an interruptible state during the flush.
Implement a "cleaner" option that offers an alternate flushing method.
When this option is activated (either by a message or in the constructor
arguments), the cache will not promote new writes (however, writes to
already cached blocks are promoted, to avoid data corruption due to
misordered writes) and it will gradually writeback any cached data. The
userspace can then monitor the cleaning process with "dmsetup status".
When the number of cached bloks drops to zero, the userspace can unload
the dm-writecache target and replace it with dm-linear or other targets.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
If the cache device is full, we do a direct write to the origin device.
Note that we must not do it if the written block is already in the cache.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Similar to f710126cfc ("dm crypt: print
device name in integrity error message"), this message should also
better identify the device with the integrity failure.
Signed-off-by: Erich Eckner <git@eckner.net>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Replace test_bit(CRYPT_MODE_INTEGRITY_AEAD, XXX) with
crypt_integrity_aead().
Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Add a new include/linux/raid/detect.h header to declare the
md_autodetect_dev prototype which can be shared between md and
the partition code. Then use IS_BUILTIN to call it instead of the
ifdef magic.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
There is no good reason for __bdevname to exist. Just open code
printing the string in the callers. For three of them the format
string can be trivially merged into existing printk statements,
and in init/do_mounts.c we can at least do the scnprintf once at
the start of the function, and unconditional of CONFIG_BLOCK to
make the output for tiny configfs a little more helpful.
Acked-by: Theodore Ts'o <tytso@mit.edu> # for ext4
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The idea of this patch is from Davidlohr Bueso, he posts a patch
for bcache to optimize barrier usage for read-modify-write atomic
bitops. Indeed such optimization can also apply on other locations
where smp_mb() is used before or after an atomic operation.
This patch replaces smp_mb() with smp_mb__before_atomic() or
smp_mb__after_atomic() in btree.c and writeback.c, where it is used
to synchronize memory cache just earlier on other cores. Although
the locations are not on hot code path, it is always not bad to mkae
things a little better.
Signed-off-by: Coly Li <colyli@suse.de>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We can avoid the unnecessary barrier on non LL/SC architectures,
such as x86. Instead, use the smp_mb__after_atomic().
Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Signed-off-by: Coly Li <colyli@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Since snprintf() returns the would-be-output size instead of the
actual output size, the succeeding calls may go beyond the given
buffer limit. Fix it by replacing with scnprintf().
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Coly Li <colyli@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
When attaching a cached device (a.k.a backing device) to a cache
device, bch_sectors_dirty_init() is called to count dirty sectors
and stripes (see what bcache_dev_sectors_dirty_add() does) on the
cache device.
The counting is done by a single thread recursive function
bch_btree_map_keys() to iterate all the bcache btree nodes.
If the btree has huge number of nodes, bch_sectors_dirty_init() will
take quite long time. In my testing, if the registering cache set has
a existed UUID which matches a already registered cached device, the
automatical attachment during the registration may take more than
55 minutes. This is too long for waiting the bcache to work in real
deployment.
Fortunately when bch_sectors_dirty_init() is called, no other thread
will access the btree yet, it is safe to do a read-only parallelized
dirty sectors counting by multiple threads.
This patch tries to create multiple threads, and each thread tries to
one-by-one count dirty sectors from the sub-tree indexed by a root
node key which the thread fetched. After the sub-tree is counted, the
counting thread will continue to fetch another root node key, until
the fetched key is NULL. How many threads in parallel depends on
the number of keys from the btree root node, and the number of online
CPU core. The thread number will be the less number but no more than
BCH_DIRTY_INIT_THRD_MAX. If there are only 2 keys in root node, it
can only be 2x times faster by this patch. But if there are 10 keys
in the root node, with this patch it can be 10x times faster.
Signed-off-by: Coly Li <colyli@suse.de>
Cc: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
When registering a cache device, bch_btree_check() is called to check
all btree nodes, to make sure the btree is consistent and not
corrupted.
bch_btree_check() is recursively executed in a single thread, when there
are a lot of data cached and the btree is huge, it may take very long
time to check all the btree nodes. In my testing, I observed it took
around 50 minutes to finish bch_btree_check().
When checking the bcache btree nodes, the cache set is not running yet,
and indeed the whole tree is in read-only state, it is safe to create
multiple threads to check the btree in parallel.
This patch tries to create multiple threads, and each thread tries to
one-by-one check the sub-tree indexed by a key from the btree root node.
The parallel thread number depends on how many keys in the btree root
node. At most BCH_BTR_CHKTHREAD_MAX (64) threads can be created, but in
practice is should be min(cpu-number/2, root-node-keys-number).
Signed-off-by: Coly Li <colyli@suse.de>
Cc: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This patch changes macro btree_root() and btree() to bcache_btree_root()
and bcache_btree(), to avoid potential generic name clash in future.
NOTE: for product kernel maintainers, this patch can be skipped if
you feel the rename stuffs introduce inconvenince to patch backport.
Suggested-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Coly Li <colyli@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
In order to accelerate bcache registration speed, the macro btree()
and btree_root() will be referenced out of btree.c. This patch moves
them from btree.c into btree.h with other relative function declaration
in btree.h, for the following changes.
Signed-off-by: Coly Li <colyli@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Don't call quiesce(1) and quiesce(0) if array is already suspended,
otherwise in level_store, the array is writable after mddev_detach
in below part though the intention is to make array writable after
resume.
mddev_suspend(mddev);
mddev_detach(mddev);
...
mddev_resume(mddev);
And it also causes calltrace as follows in [1].
[48005.653834] WARNING: CPU: 1 PID: 45380 at kernel/kthread.c:510 kthread_park+0x77/0x90
[...]
[48005.653976] CPU: 1 PID: 45380 Comm: mdadm Tainted: G OE 5.4.10-arch1-1 #1
[48005.653979] Hardware name: To Be Filled By O.E.M. To Be Filled By O.E.M./J4105-ITX, BIOS P1.40 08/06/2018
[48005.653984] RIP: 0010:kthread_park+0x77/0x90
[48005.654015] Call Trace:
[48005.654039] r5l_quiesce+0x3c/0x70 [raid456]
[48005.654052] raid5_quiesce+0x228/0x2e0 [raid456]
[48005.654073] mddev_detach+0x30/0x70 [md_mod]
[48005.654090] level_store+0x202/0x670 [md_mod]
[48005.654099] ? security_capable+0x40/0x60
[48005.654114] md_attr_store+0x7b/0xc0 [md_mod]
[48005.654123] kernfs_fop_write+0xce/0x1b0
[48005.654132] vfs_write+0xb6/0x1a0
[48005.654138] ksys_write+0x67/0xe0
[48005.654146] do_syscall_64+0x4e/0x140
[48005.654155] entry_SYSCALL_64_after_hwframe+0x44/0xa9
[48005.654161] RIP: 0033:0x7fa0c8737497
[1]: https://bugzilla.kernel.org/show_bug.cgi?id=206161
Signed-off-by: Guoqing Jiang <guoqing.jiang@cloud.ionos.com>
Signed-off-by: Song Liu <songliubraving@fb.com>
-----BEGIN PGP SIGNATURE-----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=xwKl
-----END PGP SIGNATURE-----
Merge tag 'block-5.6-2020-03-07' of git://git.kernel.dk/linux-block
Pull block fixes from Jens Axboe:
"Here are a few fixes that should go into this release. This contains:
- Revert of a bad bcache patch from this merge window
- Removed unused function (Daniel)
- Fixup for the blktrace fix from Jan from this release (Cengiz)
- Fix of deeper level bfqq overwrite in BFQ (Carlo)"
* tag 'block-5.6-2020-03-07' of git://git.kernel.dk/linux-block:
block, bfq: fix overwrite of bfq_group pointer in bfq_find_set_group()
blktrace: fix dereference after null check
Revert "bcache: ignore pending signals when creating gc and allocator thread"
block: Remove used kblockd_schedule_work_on()
bdi.
- Extend dm-bio-record to track additional struct bio members needed
by DM integrity target.
- Fix DM core to properly advertise that a device is suspended during
unload (between the presuspend and postsuspend hooks). This change
is a prereq for related DM integrity and DM writecache fixes. It
elevates DM integrity's 'suspending' state tracking to DM core.
- Four stable fixes for DM integrity target.
- Fix crash in DM cache target due to incorrect work item cancelling.
- Fix DM thin metadata lockdep warning that was introduced during 5.6
merge window.
- Fix DM zoned target's chunk work refcounting that regressed during
recent conversion to refcount_t.
- Bump the minor version for DM core and all target versions that have
seen interface changes or important fixes during the 5.6 cycle.
-----BEGIN PGP SIGNATURE-----
iQFHBAABCAAxFiEEJfWUX4UqZ4x1O2wixSPxCi2dA1oFAl5fwPgTHHNuaXR6ZXJA
cmVkaGF0LmNvbQAKCRDFI/EKLZ0DWnUJB/9+36J0Y3HYdUIKM8P5CBH0tdkMqSo4
BFm3Og4Xo1GA5xodNptgD+QoLXy3VWkekUsLvaLgOlPq7haPvHkME20vUMuO1l46
QMNR2VXciYGgV0+CFlpXL2oMr0ZEc1hkt7ZpzYaw1OIk6Mo0tEEDrSo0rvmXafPf
W4veTWRL4HfN8fy3NpQNJ4xBQs4Iw4VC20FPFIOvzA1EGk7VGGaP1mGKmOnjxo/O
o3lEH8NpQgwxwST7d4T6DPdeu3aTifnjdY8/h8mFGpQnxOiZ/wZkheKWwTCNE8r9
oeVY07qVxNAHyC8G/SmAL5KnC6En1hq5jA2M4xh9guUI2k8YbON571n+
=iAS0
-----END PGP SIGNATURE-----
Merge tag 'for-5.6/dm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm
Pull device mapper fixes from Mike Snitzer:
- Fix request-based DM's congestion_fn and actually wire it up to the
bdi.
- Extend dm-bio-record to track additional struct bio members needed by
DM integrity target.
- Fix DM core to properly advertise that a device is suspended during
unload (between the presuspend and postsuspend hooks). This change is
a prereq for related DM integrity and DM writecache fixes. It
elevates DM integrity's 'suspending' state tracking to DM core.
- Four stable fixes for DM integrity target.
- Fix crash in DM cache target due to incorrect work item cancelling.
- Fix DM thin metadata lockdep warning that was introduced during 5.6
merge window.
- Fix DM zoned target's chunk work refcounting that regressed during
recent conversion to refcount_t.
- Bump the minor version for DM core and all target versions that have
seen interface changes or important fixes during the 5.6 cycle.
* tag 'for-5.6/dm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
dm: bump version of core and various targets
dm: fix congested_fn for request-based device
dm integrity: use dm_bio_record and dm_bio_restore
dm bio record: save/restore bi_end_io and bi_integrity
dm zoned: Fix reference counter initial value of chunk works
dm writecache: verify watermark during resume
dm: report suspended device during destroy
dm thin metadata: fix lockdep complaint
dm cache: fix a crash due to incorrect work item cancelling
dm integrity: fix invalid table returned due to argument count mismatch
dm integrity: fix a deadlock due to offloading to an incorrect workqueue
dm integrity: fix recalculation when moving from journal mode to bitmap mode
Changes made during the 5.6 cycle warrant bumping the version number
for DM core and the targets modified by this commit.
It should be noted that dm-thin, dm-crypt and dm-raid already had
their target version bumped during the 5.6 merge window.
Signed-off-by; Mike Snitzer <snitzer@redhat.com>
We neither assign congested_fn for requested-based blk-mq device nor
implement it correctly. So fix both.
Also, remove incorrect comment from dm_init_normal_md_queue and rename
it to dm_init_congested_fn.
Fixes: 4aa9c692e0 ("bdi: separate out congested state into a separate struct")
Cc: stable@vger.kernel.org
Signed-off-by: Hou Tao <houtao1@huawei.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
In cases where dec_in_flight() has to requeue the integrity_bio_wait
work to transfer the rest of the data, the bio's __bi_remaining might
already have been decremented to 0, e.g.: if bio passed to underlying
data device was split via blk_queue_split().
Use dm_bio_{record,restore} rather than effectively open-coding them in
dm-integrity -- these methods now manage __bi_remaining too.
Depends-on: f7f0b057a9c1 ("dm bio record: save/restore bi_end_io and bi_integrity")
Reported-by: Daniel Glöckner <dg@emlix.com>
Suggested-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Also, save/restore __bi_remaining in case the bio was used in a
BIO_CHAIN (e.g. due to blk_queue_split).
Suggested-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
This reverts commit 0b96da639a.
We can't just go flushing random signals, under the assumption that the
OOM killer will just do something else. It's not safe from the OOM
perspective, and it could also cause other signals to get randomly lost.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
