When a resync is initiated, RESYNCING message is sent to all active
nodes with the range (lo,hi). When the resync is over, a RESYNCING
message is sent with (0,0). A high sector value of zero indicates
that the resync is over.
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Re-reads the devices by invalidating the cache.
Since we don't write to faulty devices, this is detected using
events recorded in the devices. If it is old as compared to the mddev
mark it is faulty.
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
- request to send a message
- make changes to superblock
- send messages telling everyone that the superblock has changed
- other nodes all read the superblock
- other nodes all ack the messages
- updating node release the "I'm sending a message" resource.
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
The sending part is split in two functions to make sure
atomicity of the operations, such as the MD superblock update.
Signed-off-by: Lidong Zhong <lzhong@suse.com>
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
1. receive status
sender receiver receiver
ACK:CR ACK:CR ACK:CR
2. sender get EX of TOKEN
sender get EX of MESSAGE
sender receiver receiver
TOKEN:EX ACK:CR ACK:CR
MESSAGE:EX
ACK:CR
3. sender write LVB.
sender down-convert MESSAGE from EX to CR
sender try to get EX of ACK
[ wait until all receiver has *processed* the MESSAGE ]
[ triggered by bast of ACK ]
receiver get CR of MESSAGE
receiver read LVB
receiver processes the message
[ wait finish ]
receiver release ACK
sender receiver receiver
TOKEN:EX MESSAGE:CR MESSAGE:CR
MESSAGE:CR
ACK:EX
4. sender down-convert ACK from EX to CR
sender release MESSAGE
sender release TOKEN
receiver upconvert to EX of MESSAGE
receiver get CR of ACK
receiver release MESSAGE
sender receiver receiver
ACK:CR ACK:CR ACK:CR
Signed-off-by: Lidong Zhong <lzhong@suse.com>
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
The DLM informs us in case of node failure with the DLM slot number.
cluster_info->recovery_map sets the bit corresponding to the slot number
and wakes up the recovery thread.
The recovery thread:
1. Derives the slot number from the recovery_map
2. Locks the bitmap corresponding to the slot
3. Copies the set bits to the node-local bitmap
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
bitmap_copy_from_slot reads the bitmap from the slot mentioned.
It then copies the set bits to the node local bitmap.
This is helper function for the resync operation on node failure.
bitmap_set_memory_bits() currently assumes it is only run at startup and that
they bitmap is currently empty. So if it finds that a region is already
marked as dirty, it won't mark it dirty again. Change bitmap_set_memory_bits()
to always set the NEEDED_MASK bit if 'needed' is set.
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
When a node joins, it does not know of other nodes performing resync.
So, each node keeps the resync information in it's LVB. When a new
node joins, it reads the LVB of each "online" bitmap.
[TODO] The new node attempts to get the PW lock on other bitmap, if
it is successful, it reads the bitmap and performs the resync (if
required) on it's behalf.
If the node does not get the PW, it requests CR and reads the LVB
for the resync information.
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
On-disk format:
0 4k 8k 12k
-------------------------------------------------------------------
| idle | md super | bm super [0] + bits |
| bm bits[0, contd] | bm super[1] + bits | bm bits[1, contd] |
| bm super[2] + bits | bm bits [2, contd] | bm super[3] + bits |
| bm bits [3, contd] | | |
Bitmap super has a field nodes, which defines the maximum number
of nodes the device can use. While reading the bitmap super, if
the cluster finds out that the number of nodes is > 0:
1. Requests the md-cluster module.
2. Calls md_cluster_ops->join(), which sets up clustering such as
joining DLM lockspace.
Since the first time, the first bitmap is read. After the call
to the cluster_setup, the bitmap offset is adjusted and the
superblock is re-read. This also ensures the bitmap is read
the bitmap lock (when bitmap lock is introduced in later patches)
Questions:
1. cluster name is repeated in all bitmap supers. Is that okay?
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
DLM offers callbacks when a node fails and the lock remastery
is performed:
1. recover_prep: called when DLM discovers a node is down
2. recover_slot: called when DLM identifies the node and recovery
can start
3. recover_done: called when all nodes have completed recover_slot
recover_slot() and recover_done() are also called when the node joins
initially in order to inform the node with its slot number. These slot
numbers start from one, so we deduct one to make it start with zero
which the cluster-md code uses.
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
md_cluster_info stores the cluster information in the MD device.
The join() is called when mddev detects it is a clustered device.
The main responsibilities are:
1. Setup a DLM lockspace
2. Setup all initial locks such as super block locks and bitmap lock (will come later)
The leave() clears up the lockspace and all the locks held.
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
A dlm_lock_resource is a structure which contains all information
required for locking using DLM. The init function allocates the
lock and acquires the lock in NL mode. The unlock function
converts the lock resource to NL mode. This is done to preserve
LVB and for faster processing of locks. The lock resource is
DLM unlocked only in the lockres_free function, which is the end
of life of the lock resource.
Signed-off-by: Lidong Zhong <lzhong@suse.com>
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
to changes that enable effective use of an unbound workqueue across
all available CPUs. A large battery of tests were performed to
validate these changes, summary of results is available here:
https://www.redhat.com/archives/dm-devel/2015-February/msg00106.html
- A few additional stable fixes (to DM core, dm-snapshot and dm-mirror)
and a small fix to the dm-space-map-disk.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iQEcBAABAgAGBQJU51MsAAoJEMUj8QotnQNan8wH/3Oa2/ofbX8zNYtdDxFBK7W0
pHwVA2CH9yzDDi90X9GsQODmXerMrYf+SHo/RsQTpSnt5WI/4ZVP/1EoNGu6T2Yr
XiaKc/Jwo+ScxdhoHSNtyGL5vKeipX6clgz1wcd/4/UBcBAr0Vxj25s8Ta7naK2V
hZyWnt3MCGEDQ45NVBmLOU78Cl68LGf8JOUY0l3cd8ehQjGyR9a12GXwRktepslp
hw9xu8uYmE93fD+MIe/fUs7W/WvIVgFSskhswlvD3kAFpEAsMczjLGVSRQlBE90L
OK7v1HKxiIUJa17g3LmiCFa59ZjrnSHGpOOv9IPAFU/LzFIU47lcFwRFjgfB8po=
=8vFi
-----END PGP SIGNATURE-----
Merge tag 'dm-3.20-changes-2' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm
Pull more device mapper changes from Mike Snitzer:
- Significant dm-crypt CPU scalability performance improvements thanks
to changes that enable effective use of an unbound workqueue across
all available CPUs. A large battery of tests were performed to
validate these changes, summary of results is available here:
https://www.redhat.com/archives/dm-devel/2015-February/msg00106.html
- A few additional stable fixes (to DM core, dm-snapshot and dm-mirror)
and a small fix to the dm-space-map-disk.
* tag 'dm-3.20-changes-2' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
dm snapshot: fix a possible invalid memory access on unload
dm: fix a race condition in dm_get_md
dm crypt: sort writes
dm crypt: add 'submit_from_crypt_cpus' option
dm crypt: offload writes to thread
dm crypt: remove unused io_pool and _crypt_io_pool
dm crypt: avoid deadlock in mempools
dm crypt: don't allocate pages for a partial request
dm crypt: use unbound workqueue for request processing
dm io: reject unsupported DISCARD requests with EOPNOTSUPP
dm mirror: do not degrade the mirror on discard error
dm space map disk: fix sm_disk_count_is_more_than_one()
Pull kconfig updates from Michal Marek:
"Yann E Morin was supposed to take over kconfig maintainership, but
this hasn't happened. So I'm sending a few kconfig patches that I
collected:
- Fix for missing va_end in kconfig
- merge_config.sh displays used if given too few arguments
- s/boolean/bool/ in Kconfig files for consistency, with the plan to
only support bool in the future"
* 'kconfig' of git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild:
kconfig: use va_end to match corresponding va_start
merge_config.sh: Display usage if given too few arguments
kconfig: use bool instead of boolean for type definition attributes
When the snapshot target is unloaded, snapshot_dtr() waits until
pending_exceptions_count drops to zero. Then, it destroys the snapshot.
Therefore, the function that decrements pending_exceptions_count
should not touch the snapshot structure after the decrement.
pending_complete() calls free_pending_exception(), which decrements
pending_exceptions_count, and then it performs up_write(&s->lock) and it
calls retry_origin_bios() which dereferences s->origin. These two
memory accesses to the fields of the snapshot may touch the dm_snapshot
struture after it is freed.
This patch moves the call to free_pending_exception() to the end of
pending_complete(), so that the snapshot will not be destroyed while
pending_complete() is in progress.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org
The function dm_get_md finds a device mapper device with a given dev_t,
increases the reference count and returns the pointer.
dm_get_md calls dm_find_md, dm_find_md takes _minor_lock, finds the
device, tests that the device doesn't have DMF_DELETING or DMF_FREEING
flag, drops _minor_lock and returns pointer to the device. dm_get_md then
calls dm_get. dm_get calls BUG if the device has the DMF_FREEING flag,
otherwise it increments the reference count.
There is a possible race condition - after dm_find_md exits and before
dm_get is called, there are no locks held, so the device may disappear or
DMF_FREEING flag may be set, which results in BUG.
To fix this bug, we need to call dm_get while we hold _minor_lock. This
patch renames dm_find_md to dm_get_md and changes it so that it calls
dm_get while holding the lock.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org
yet-another-livelock in raid5, and a problem with write errors
to 4K-block devices.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2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=1BWV
-----END PGP SIGNATURE-----
Merge tag 'md/3.20-fixes' of git://neil.brown.name/md
Pull md bugfixes from Neil Brown:
"Three bug md fixes for 3.20
yet-another-livelock in raid5, and a problem with write errors to
4K-block devices"
* tag 'md/3.20-fixes' of git://neil.brown.name/md:
md/raid5: Fix livelock when array is both resyncing and degraded.
md/raid10: round up to bdev_logical_block_size in narrow_write_error.
md/raid1: round up to bdev_logical_block_size in narrow_write_error
Commit a7854487cd7128a30a7f4f5259de9f67d5efb95f:
md: When RAID5 is dirty, force reconstruct-write instead of read-modify-write.
Causes an RCW cycle to be forced even when the array is degraded.
A degraded array cannot support RCW as that requires reading all data
blocks, and one may be missing.
Forcing an RCW when it is not possible causes a live-lock and the code
spins, repeatedly deciding to do something that cannot succeed.
So change the condition to only force RCW on non-degraded arrays.
Reported-by: Manibalan P <pmanibalan@amiindia.co.in>
Bisected-by: Jes Sorensen <Jes.Sorensen@redhat.com>
Tested-by: Jes Sorensen <Jes.Sorensen@redhat.com>
Signed-off-by: NeilBrown <neilb@suse.de>
Fixes: a7854487cd
Cc: stable@vger.kernel.org (v3.7+)
Write requests are sorted in a red-black tree structure and are
submitted in the sorted order.
In theory the sorting should be performed by the underlying disk
scheduler, however, in practice the disk scheduler only accepts and
sorts a finite number of requests. To allow the sorting of all
requests, dm-crypt needs to implement its own sorting.
The overhead associated with rbtree-based sorting is considered
negligible so it is not used conditionally. Even on SSD sorting can be
beneficial since in-order request dispatch promotes lower latency IO
completion to the upper layers.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Make it possible to disable offloading writes by setting the optional
'submit_from_crypt_cpus' table argument.
There are some situations where offloading write bios from the
encryption threads to a single thread degrades performance
significantly.
The default is to offload write bios to the same thread because it
benefits CFQ to have writes submitted using the same IO context.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Submitting write bios directly in the encryption thread caused serious
performance degradation. On a multiprocessor machine, encryption requests
finish in a different order than they were submitted. Consequently, write
requests would be submitted in a different order and it could cause severe
performance degradation.
Move the submission of write requests to a separate thread so that the
requests can be sorted before submitting. But this commit improves
dm-crypt performance even without having dm-crypt perform request
sorting (in particular it enables IO schedulers like CFQ to sort more
effectively).
Note: it is required that a previous commit ("dm crypt: don't allocate
pages for a partial request") be applied before applying this patch.
Otherwise, this commit could introduce a crash.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
The previous commit ("dm crypt: don't allocate pages for a partial
request") stopped using the io_pool slab mempool and backing
_crypt_io_pool kmem cache.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Fix a theoretical deadlock introduced in the previous commit ("dm crypt:
don't allocate pages for a partial request").
The function crypt_alloc_buffer may be called concurrently. If we allocate
from the mempool concurrently, there is a possibility of deadlock. For
example, if we have mempool of 256 pages, two processes, each wanting
256, pages allocate from the mempool concurrently, it may deadlock in a
situation where both processes have allocated 128 pages and the mempool
is exhausted.
To avoid such a scenario we allocate the pages under a mutex. In order
to not degrade performance with excessive locking, we try non-blocking
allocations without a mutex first and if that fails, we fallback to a
blocking allocations with a mutex.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Change crypt_alloc_buffer so that it only ever allocates pages for a
full request. This is a prerequisite for the commit "dm crypt: offload
writes to thread".
This change simplifies the dm-crypt code at the expense of reduced
throughput in low memory conditions (where allocation for a partial
request is most useful).
Note: the next commit ("dm crypt: avoid deadlock in mempools") is needed
to fix a theoretical deadlock.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Use unbound workqueue by default so that work is automatically balanced
between available CPUs. The original behavior of encrypting using the
same cpu that IO was submitted on can still be enabled by setting the
optional 'same_cpu_crypt' table argument.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
This modifies raid1's narrow_write_error to round up block_sectors to the
device's logical block size.
This prevents sd complaining about "Bad block number requested" for non-512-byte
sector disks.
Signed-off-by: Nate Dailey <nate.dailey@stratus.com>
Signed-off-by: NeilBrown <neilb@suse.de>
I created a dm-raid1 device backed by a device that supports DISCARD
and another device that does NOT support DISCARD with the following
dm configuration:
# echo '0 2048 mirror core 1 512 2 /dev/sda 0 /dev/sdb 0' | dmsetup create moo
# lsblk -D
NAME DISC-ALN DISC-GRAN DISC-MAX DISC-ZERO
sda 0 4K 1G 0
`-moo (dm-0) 0 4K 1G 0
sdb 0 0B 0B 0
`-moo (dm-0) 0 4K 1G 0
Notice that the mirror device /dev/mapper/moo advertises DISCARD
support even though one of the mirror halves doesn't.
If I issue a DISCARD request (via fstrim, mount -o discard, or ioctl
BLKDISCARD) through the mirror, kmirrord gets stuck in an infinite
loop in do_region() when it tries to issue a DISCARD request to sdb.
The problem is that when we call do_region() against sdb, num_sectors
is set to zero because q->limits.max_discard_sectors is zero.
Therefore, "remaining" never decreases and the loop never terminates.
To fix this: before entering the loop, check for the combination of
REQ_DISCARD and no discard and return -EOPNOTSUPP to avoid hanging up
the mirror device.
This bug was found by the unfortunate coincidence of pvmove and a
discard operation in the RHEL 6.5 kernel; upstream is also affected.
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Acked-by: "Martin K. Petersen" <martin.petersen@oracle.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org
It may be possible that a device claims discard support but it rejects
discards with -EOPNOTSUPP. It happens when using loopback on ext2/ext3
filesystem driven by the ext4 driver. It may also happen if the
underlying devices are moved from one disk on another.
If discard error happens, we reject the bio with -EOPNOTSUPP, but we do
not degrade the array.
This patch fixes failed test shell/lvconvert-repair-transient.sh in the
lvm2 testsuite if the testsuite is extracted on an ext2 or ext3
filesystem and it is being driven by the ext4 driver.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org
dm_tm_shadow_block() is the only caller of
dm_sm_count_is_more_than_one() which only ever operates on a metadata
space-map. So in practice, sm_disk_count_is_more_than_one() isn't
actually used (which explains why this bug never amounted to anything).
But fix sm_disk_count_is_more_than_one() to properly set *result and
return 0.
Reported-by: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
stacking ontop of blk-mq devices. This blk-mq support changes the
model request-based DM uses for cloning a request to relying on
calling blk_get_request() directly from the underlying blk-mq device.
Early consumer of this code is Intel's emerging NVMe hardware; thanks
to Keith Busch for working on, and pushing for, these changes.
- A few other small fixes and cleanups across other DM targets.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iQEcBAABAgAGBQJU3NRnAAoJEMUj8QotnQNavG0H/3yogMcHvKg9H+w0WmUQdwhN
w99Wj3nkquAw2sm9yahKlAMBNY53iu/LHmC6/PaTpJetgdH7y1foTrRa0qjyeB2D
DgNr8mOzxSxzX6CX9V8JMwqzky9XoG2IOt/7FeQQOpMqp4T1M2zgvbZtpl0lK/f3
lNaNBFpl+47NbGssD/WbtfI4Yy3hX0u406yGmQN5DxRyGTWD2AFqpA76g2mp8vrp
wmw259gPr4oLhj3pDc0GkuiVn59ZR2Zp+2gs0jD5uKlDL84VP/nE+WNB+ny1Mnmt
cOg8Q+W6/OosL66MKBHNsF0QS6DXNo5UvsN9fHGa5IUJw7Tsa11ZEPKHZGEbQw4=
=RiN2
-----END PGP SIGNATURE-----
Merge tag 'dm-3.20-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm
Pull device mapper changes from Mike Snitzer:
- The most significant change this cycle is request-based DM now
supports stacking ontop of blk-mq devices. This blk-mq support
changes the model request-based DM uses for cloning a request to
relying on calling blk_get_request() directly from the underlying
blk-mq device.
An early consumer of this code is Intel's emerging NVMe hardware;
thanks to Keith Busch for working on, and pushing for, these changes.
- A few other small fixes and cleanups across other DM targets.
* tag 'dm-3.20-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
dm: inherit QUEUE_FLAG_SG_GAPS flags from underlying queues
dm snapshot: remove unnecessary NULL checks before vfree() calls
dm mpath: simplify failure path of dm_multipath_init()
dm thin metadata: remove unused dm_pool_get_data_block_size()
dm ioctl: fix stale comment above dm_get_inactive_table()
dm crypt: update url in CONFIG_DM_CRYPT help text
dm bufio: fix time comparison to use time_after_eq()
dm: use time_in_range() and time_after()
dm raid: fix a couple integer overflows
dm table: train hybrid target type detection to select blk-mq if appropriate
dm: allocate requests in target when stacking on blk-mq devices
dm: prepare for allocating blk-mq clone requests in target
dm: submit stacked requests in irq enabled context
dm: split request structure out from dm_rq_target_io structure
dm: remove exports for request-based interfaces without external callers
Pull core block IO changes from Jens Axboe:
"This contains:
- A series from Christoph that cleans up and refactors various parts
of the REQ_BLOCK_PC handling. Contributions in that series from
Dongsu Park and Kent Overstreet as well.
- CFQ:
- A bug fix for cfq for realtime IO scheduling from Jeff Moyer.
- A stable patch fixing a potential crash in CFQ in OOM
situations. From Konstantin Khlebnikov.
- blk-mq:
- Add support for tag allocation policies, from Shaohua. This is
a prep patch enabling libata (and other SCSI parts) to use the
blk-mq tagging, instead of rolling their own.
- Various little tweaks from Keith and Mike, in preparation for
DM blk-mq support.
- Minor little fixes or tweaks from me.
- A double free error fix from Tony Battersby.
- The partition 4k issue fixes from Matthew and Boaz.
- Add support for zero+unprovision for blkdev_issue_zeroout() from
Martin"
* 'for-3.20/core' of git://git.kernel.dk/linux-block: (27 commits)
block: remove unused function blk_bio_map_sg
block: handle the null_mapped flag correctly in blk_rq_map_user_iov
blk-mq: fix double-free in error path
block: prevent request-to-request merging with gaps if not allowed
blk-mq: make blk_mq_run_queues() static
dm: fix multipath regression due to initializing wrong request
cfq-iosched: handle failure of cfq group allocation
block: Quiesce zeroout wrapper
block: rewrite and split __bio_copy_iov()
block: merge __bio_map_user_iov into bio_map_user_iov
block: merge __bio_map_kern into bio_map_kern
block: pass iov_iter to the BLOCK_PC mapping functions
block: add a helper to free bio bounce buffer pages
block: use blk_rq_map_user_iov to implement blk_rq_map_user
block: simplify bio_map_kern
block: mark blk-mq devices as stackable
block: keep established cmd_flags when cloning into a blk-mq request
block: add blk-mq support to blk_insert_cloned_request()
block: require blk_rq_prep_clone() be given an initialized clone request
blk-mq: add tag allocation policy
...
- assorted locking changes so that access to /proc/mdstat
and much of /sys/block/mdXX/md/* is protected by a spinlock
rather than a mutex and will never block indefinitely.
- Make an 'if' condition in RAID5 - which has been implicated
in recent bugs - more readable.
- misc minor fixes
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2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=/FmP
-----END PGP SIGNATURE-----
Merge tag 'md/3.20' of git://neil.brown.name/md
Pull md updates from Neil Brown:
- assorted locking changes so that access to /proc/mdstat
and much of /sys/block/mdXX/md/* is protected by a spinlock
rather than a mutex and will never block indefinitely.
- Make an 'if' condition in RAID5 - which has been implicated
in recent bugs - more readable.
- misc minor fixes
* tag 'md/3.20' of git://neil.brown.name/md: (28 commits)
md/raid10: fix conversion from RAID0 to RAID10
md: wakeup thread upon rdev_dec_pending()
md: make reconfig_mutex optional for writes to md sysfs files.
md: move mddev_lock and related to md.h
md: use mddev->lock to protect updates to resync_{min,max}.
md: minor cleanup in safe_delay_store.
md: move GET_BITMAP_FILE ioctl out from mddev_lock.
md: tidy up set_bitmap_file
md: remove unnecessary 'buf' from get_bitmap_file.
md: remove mddev_lock from rdev_attr_show()
md: remove mddev_lock() from md_attr_show()
md/raid5: use ->lock to protect accessing raid5 sysfs attributes.
md: remove need for mddev_lock() in md_seq_show()
md/bitmap: protect clearing of ->bitmap by mddev->lock
md: protect ->pers changes with mddev->lock
md: level_store: group all important changes into one place.
md: rename ->stop to ->free
md: split detach operation out from ->stop.
md/linear: remove rcu protections in favour of suspend/resume
md: make merge_bvec_fn more robust in face of personality changes.
...
A RAID0 array (like a LINEAR array) does not have a concept
of 'size' being the amount of each device that is in use.
Rather, as much of each device as is available is used.
So the 'size' is set to 0 and ignored.
RAID10 does have this concept and needs it to be set correctly.
So when we convert RAID0 to RAID10 we must determine the
'size' (that being the size of the first 'strip_zone' in the
RAID0), and set it correctly.
Reported-and-tested-by: Xiao Ni <xni@redhat.com>
Signed-off-by: NeilBrown <neilb@suse.de>
A DM device must inherit the QUEUE_FLAG_SG_GAPS flags from its
underlying block devices' request queues.
This fixes problems when submitting cloned requests to multipathed
devices requiring virtually contiguous buffers.
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Pull RCU updates from Ingo Molnar:
"The main RCU changes in this cycle are:
- Documentation updates.
- Miscellaneous fixes.
- Preemptible-RCU fixes, including fixing an old bug in the
interaction of RCU priority boosting and CPU hotplug.
- SRCU updates.
- RCU CPU stall-warning updates.
- RCU torture-test updates"
* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (54 commits)
rcu: Initialize tiny RCU stall-warning timeouts at boot
rcu: Fix RCU CPU stall detection in tiny implementation
rcu: Add GP-kthread-starvation checks to CPU stall warnings
rcu: Make cond_resched_rcu_qs() apply to normal RCU flavors
rcu: Optionally run grace-period kthreads at real-time priority
ksoftirqd: Use new cond_resched_rcu_qs() function
ksoftirqd: Enable IRQs and call cond_resched() before poking RCU
rcutorture: Add more diagnostics in rcu_barrier() test failure case
torture: Flag console.log file to prevent holdovers from earlier runs
torture: Add "-enable-kvm -soundhw pcspk" to qemu command line
rcutorture: Handle different mpstat versions
rcutorture: Check from beginning to end of grace period
rcu: Remove redundant rcu_batches_completed() declaration
rcutorture: Drop rcu_torture_completed() and friends
rcu: Provide rcu_batches_completed_sched() for TINY_RCU
rcutorture: Use unsigned for Reader Batch computations
rcutorture: Make build-output parsing correctly flag RCU's warnings
rcu: Make _batches_completed() functions return unsigned long
rcutorture: Issue warnings on close calls due to Reader Batch blows
documentation: Fix smp typo in memory-barriers.txt
...
The vfree() function performs input parameter validation.
Thus the NULL pointer test around vfree() calls is not needed.
This issue was detected by using the Coccinelle software.
Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Currently the cleanup of all error cases are open-coded. Introduce a
common exit path and labels.
Signed-off-by: Johannes Thumshirn <morbidrsa@gmail.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
The thin-pool target doesn't display the data block size as part of
its table status, unlike the dm-cache target, so there is no need for
dm_pool_get_data_block_size().
This was found using cppcheck.
Signed-off-by: Rickard Strandqvist <rickard_strandqvist@spectrumdigital.se>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Update the obsolete url in the CONFIG_DM_CRYPT help text.
Signed-off-by: Loic Pefferkorn <loic@loicp.eu>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
To be future-proof and for better readability the time comparison
is modified to use time_after_eq() instead of plain, error-prone math.
Signed-off-by: Asaf Vertz <asaf.vertz@tandemg.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
To be future-proof and for better readability the time comparisons are modified
to use time_in_range() and time_after() instead of plain, error-prone math.
Signed-off-by: Manuel Schölling <manuel.schoelling@gmx.de>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
My static checker complains that if "num_raid_params" is UINT_MAX then
the "if (num_raid_params + 1 > argc) {" check doesn't work as intended.
The other change is that I moved the "if (argc != (num_raid_devs * 2))"
condition forward a few lines so it was before the call to
context_alloc(). If we had an integer overflow inside that function
then it would lead to an immediate crash.
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Otherwise replacing the multipath target with the error target fails:
device-mapper: ioctl: can't change device type after initial table load.
The error target was mistakenly considered to be target type
DM_TYPE_REQUEST_BASED rather than DM_TYPE_MQ_REQUEST_BASED even if the
target it was to replace was of type DM_TYPE_MQ_REQUEST_BASED.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
For blk-mq request-based DM the responsibility of allocating a cloned
request is transfered from DM core to the target type. Doing so
enables the cloned request to be allocated from the appropriate
blk-mq request_queue's pool (only the DM target, e.g. multipath, can
know which block device to send a given cloned request to).
Care was taken to preserve compatibility with old-style block request
completion that requires request-based DM _not_ acquire the clone
request's queue lock in the completion path. As such, there are now 2
different request-based DM target_type interfaces:
1) the original .map_rq() interface will continue to be used for
non-blk-mq devices -- the preallocated clone request is passed in
from DM core.
2) a new .clone_and_map_rq() and .release_clone_rq() will be used for
blk-mq devices -- blk_get_request() and blk_put_request() are used
respectively from these hooks.
dm_table_set_type() was updated to detect if the request-based target is
being stacked on blk-mq devices, if so DM_TYPE_MQ_REQUEST_BASED is set.
DM core disallows switching the DM table's type after it is set. This
means that there is no mixing of non-blk-mq and blk-mq devices within
the same request-based DM table.
[This patch was started by Keith and later heavily modified by Mike]
Tested-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
For blk-mq request-based DM the responsibility of allocating a cloned
request will be transfered from DM core to the target type.
To prepare for conditionally using this new model the original
request's 'special' now points to the dm_rq_target_io because the
clone is allocated later in the block layer rather than in DM core.
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Switch to having request-based DM enqueue all prep'ed requests into work
processed by another thread. This allows request-based DM to invoke
block APIs that assume interrupt enabled context (e.g. blk_get_request)
and is a prerequisite for adding blk-mq support to request-based DM.
The new kernel thread is only initialized for request-based DM devices.
multipath_map() is now always in irq enabled context so change multipath
spinlock (m->lock) locking to always disable interrupts.
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Request-based DM support for blk-mq devices requires that
dm_rq_target_io structures not be allocated with an embedded request
structure. The request-based DM target (e.g. dm-multipath) must
allocate the request from the blk-mq devices' request_queue using
blk_get_request().
The unfortunate side-effect of this change is old-style request-based DM
support will no longer use contiguous memory for the dm_rq_target_io and
request structures for each clone.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Commit febf715 ("block: require blk_rq_prep_clone() be given an
initialized clone request") introduced a regression by calling
blk_rq_init() on the original request rather than the clone
request that is passed to setup_clone().
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Fixes: febf71588c ("block: require blk_rq_prep_clone() be given an initialized clone request")
Signed-off-by: Jens Axboe <axboe@fb.com>
After each call to rdev_dec_pending() we should wakeup the
md thread if the device is found to be faulty.
Otherwise we'll incur heavy delays on failing devices.
Signed-off-by: Neil Brown <nfbrown@suse.de>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Rather than using mddev_lock() to take the reconfig_mutex
when writing to any md sysfs file, we only take mddev_lock()
in the particular _store() functions that require it.
Admittedly this is most, but it isn't all.
This also allows us to remove special-case handling for new_dev_store
(in md_attr_store).
Signed-off-by: NeilBrown <neilb@suse.de>
The one which is not inline (mddev_unlock) gets EXPORTed.
This makes the locking available to personality modules so that it
doesn't have to be imposed upon them.
Signed-off-by: NeilBrown <neilb@suse.de>
There are interdependencies between these two sysfs attributes
and whether a resync is currently running.
Rather than depending on reconfig_mutex to ensure no races when
testing these interdependencies are met, use the spinlock.
This will allow the mutex to be remove from protecting this
code in a subsequent patch.
Signed-off-by: NeilBrown <neilb@suse.de>
There isn't really much room for races with ->safemode_delay.
But as I am trying to clean up any racy code and will soon
be removing reconfig_mutex protection from most _store()
functions:
- only set mddev->safemode_delay once, to ensure no code
can see an intermediate value
- use safemode_timer to call md_safemode_timeout() rather than
calling it directly, to ensure it never races with itself.
Signed-off-by: NeilBrown <neilb@suse.de>
It makes more sense to report bitmap_info->file, rather than
bitmap->file (the later is only available once the array is
active).
With that change, use mddev->lock to protect bitmap_info being
set to NULL, and we can call get_bitmap_file() without taking
the mutex.
Signed-off-by: NeilBrown <neilb@suse.de>
1/ delay setting mddev->bitmap_info.file until 'f' looks
usable, so we don't have to unset it.
2/ Don't allow bitmap file to be set if bitmap_info.file
is already set.
Signed-off-by: NeilBrown <neilb@suse.de>
'buf' is only used because d_path fills from the end of the
buffer instead of from the start.
We don't need a separate buf to handle that, we just need to use
memmove() to move the string to the start.
Signed-off-by: NeilBrown <neilb@suse.de>
No rdev attributes need locking for 'show', though
state_show() might benefit from ensuring it sees a
consistent set of flags.
None even use rdev->mddev, so testing for it isn't really
needed and it certainly doesn't need to be held constant.
So improve state_show() and remove the locking.
Signed-off-by: NeilBrown <neilb@suse.de>
Most attributes can be read safely without any locking.
A race might lead to a slightly out-dated value, but nothing wrong.
We already have locking in some places where needed.
All that remains is can_clear_show(), behind_writes_used_show()
and action_show() which are easily fixed.
Signed-off-by: NeilBrown <neilb@suse.de>
It is important that mddev->private isn't freed while
a sysfs attribute function is accessing it.
So use mddev->lock to protect the setting of ->private to NULL, and
take that lock when checking ->private for NULL and de-referencing it
in the sysfs access functions.
This only applies to the read ('show') side of access. Write
access will be handled separately.
Signed-off-by: NeilBrown <neilb@suse.de>
The only access in md_seq_show that could suffer from races
not protected by ->lock is walking the rdev list.
This can receive sufficient protection from 'rcu'.
So use rdev_for_each_rcu() and get rid of mddev_lock().
Now reading /proc/mdstat will never block in md_seq_show.
Signed-off-by: NeilBrown <neilb@suse.de>
1/ Another live lock, needs backporting
2/ work-around false positive with new warnings.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2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=qYoP
-----END PGP SIGNATURE-----
Merge tag 'md/3.19-fixes' of git://neil.brown.name/md
Pull two fixes for md from Neil Brown:
- Another live lock, needs backporting
- work-around false positive with new warnings.
* tag 'md/3.19-fixes' of git://neil.brown.name/md:
md/bitmap: fix a might_sleep() warning.
md/raid5: fix another livelock caused by non-aligned writes.
->pers is already protected by ->reconfig_mutex, and
cannot possibly change when there are threads running or
outstanding IO.
However there are some places where we access ->pers
not in a thread or IO context, and where ->reconfig_mutex
is unnecessarily heavy-weight: level_show and md_seq_show().
So protect all changes, and those accesses, with ->lock.
This is a step toward taking those accesses out from under
reconfig_mutex.
[Fixed missing "mddev->pers" -> "pers" conversion, thanks to
Dan Carpenter <dan.carpenter@oracle.com>]
Signed-off-by: NeilBrown <neilb@suse.de>
Gather all the changes that can happen atomically and might
be relevant to other code into one place. This will
make it easier to refine the locking.
Note that this puts quite a few things between mddev_detach()
and ->free(). Enabling this was the point of some recent patches.
Signed-off-by: NeilBrown <neilb@suse.de>
Now that the ->stop function only frees the private data,
rename is accordingly.
Also pass in the private pointer as an arg rather than using
mddev->private. This flexibility will be useful in level_store().
Finally, don't clear ->private. It doesn't make sense to clear
it seeing that isn't what we free, and it is no longer necessary
to clear ->private (it was some time ago before ->to_remove was
introduced).
Setting ->to_remove in ->free() is a bit of a wart, but not a
big problem at the moment.
Signed-off-by: NeilBrown <neilb@suse.de>
Each md personality has a 'stop' operation which does two
things:
1/ it finalizes some aspects of the array to ensure nothing
is accessing the ->private data
2/ it frees the ->private data.
All the steps in '1' can apply to all arrays and so can be
performed in common code.
This is useful as in the case where we change the personality which
manages an array (in level_store()), it would be helpful to do
step 1 early, and step 2 later.
So split the 'step 1' functionality out into a new mddev_detach().
Signed-off-by: NeilBrown <neilb@suse.de>
The use of 'rcu' to protect accesses to ->private_data so that
the ->private_data could be updated predates the introduction
of mddev_suspend/mddev_resume.
These are a cleaner mechanism for providing stability while
swapping in a new ->private data - it is used by level_store()
to support changing of raid levels.
So get rid of the RCU stuff and just use mddev_suspend, mddev_resume.
As these function call ->quiesce(), we add an empty function for
linear just like for raid0.
Signed-off-by: NeilBrown <neilb@suse.de>
There is no locking around calls to merge_bvec_fn(), so
it is possible that calls which coincide with a level (or personality)
change could go wrong.
So create a central dispatch point for these functions and use
rcu_read_lock().
If the array is suspended, reject any merge that can be rejected.
If not, we know it is safe to call the function.
Signed-off-by: NeilBrown <neilb@suse.de>
There is currently no locking around calls to the 'congested'
bdi function. If called at an awkward time while an array is
being converted from one level (or personality) to another, there
is a tiny chance of running code in an unreferenced module etc.
So add a 'congested' function to the md_personality operations
structure, and call it with appropriate locking from a central
'mddev_congested'.
When the array personality is changing the array will be 'suspended'
so no IO is processed.
If mddev_congested detects this, it simply reports that the
array is congested, which is a safe guess.
As mddev_suspend calls synchronize_rcu(), mddev_congested can
avoid races by included the whole call inside an rcu_read_lock()
region.
This require that the congested functions for all subordinate devices
can be run under rcu_lock. Fortunately this is the case.
Signed-off-by: NeilBrown <neilb@suse.de>
This lock is used for (slightly) more than helping with writing
superblocks, and it will soon be extended further. So the
name is inappropriate.
Also, the _irq variant hasn't been needed since 2.6.37 as it is
never taking from interrupt or bh context.
So:
-rename write_lock to lock
-document what it protects
-remove _irq ... except in md_flush_request() as there
is no wait_event_lock() (with no _irq). This can be
cleaned up after appropriate changes to wait.h.
Signed-off-by: NeilBrown <neilb@suse.de>
That last condition is unclear and over cautious.
There are two related issues here.
If a partial write is destined for a missing device, then
either RMW or RCW can work. We must read all the available
block. Only then can the missing blocks be calculated, and
then the parity update performed.
If RMW is not an option, then there is a complication even
without partial writes. If we would need to read a missing
device to perform the reconstruction, then we must first read every
block so the missing device data can be computed.
This is the case for RAID6 (Which currently does not support
RMW) and for times when we don't trust the parity (after a crash)
and so are in the process of resyncing it.
So make these two cases more clear and separate, and perform
the relevant tests more thoroughly.
Signed-off-by: NeilBrown <neilb@suse.de>
Both the last two cases are only relevant if something has failed and
something needs to be written (but not over-written), and if it is OK
to pre-read blocks at this point. So factor out those tests and
explain them.
Signed-off-by: NeilBrown <neilb@suse.de>
Some of the conditions in need_this_block have very straight
forward motivation. Separate those out and document them.
Signed-off-by: NeilBrown <neilb@suse.de>
fetch_block() has a very large and hard to read 'if' condition.
Separate it into its own function so that it can be
made more readable.
Signed-off-by: NeilBrown <neilb@suse.de>
67f455486d introduced a call to
md_wakeup_thread() when adding to the delayed_list. However the md
thread is woken up unconditionally just below.
Remove the unnecessary wakeup call.
Signed-off-by: Jes Sorensen <Jes.Sorensen@redhat.com>
Signed-off-by: NeilBrown <neilb@suse.de>
commit 8eb23b9f35
sched: Debug nested sleeps
causes false-positive warnings in RAID5 code.
This annotation removes them and adds a comment
explaining why there is no real problem.
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: NeilBrown <neilb@suse.de>
If a non-page-aligned write is destined for a device which
is missing/faulty, we can deadlock.
As the target device is missing, a read-modify-write cycle
is not possible.
As the write is not for a full-page, a recontruct-write cycle
is not possible.
This should be handled by logic in fetch_block() which notices
there is a non-R5_OVERWRITE write to a missing device, and so
loads all blocks.
However since commit 67f455486d, that code requires
STRIPE_PREREAD_ACTIVE before it will active, and those circumstances
never set STRIPE_PREREAD_ACTIVE.
So: in handle_stripe_dirtying, if neither rmw or rcw was possible,
set STRIPE_DELAYED, which will cause STRIPE_PREREAD_ACTIVE be set
after a suitable delay.
Fixes: 67f455486d
Cc: stable@vger.kernel.org (v3.16+)
Reported-by: Mikulas Patocka <mpatocka@redhat.com>
Tested-by: Heinz Mauelshagen <heinzm@redhat.com>
Signed-off-by: NeilBrown <neilb@suse.de>
Prepare to allow blk_rq_prep_clone() to accept clone requests that were
allocated from blk-mq request queues. As such the blk_rq_prep_clone()
caller must first initialize the clone request.
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
You can't modify the metadata in these modes. It's better to fail these
messages immediately than let the block-manager deny write locks on
metadata blocks. Otherwise these failed metadata changes will trigger
'needs_check' to get set in the metadata superblock -- requiring repair
using the thin_check utility.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org
Commit 9b1cc9f251 ("dm cache: share cache-metadata object across
inactive and active DM tables") mistakenly ignored the use of ERR_PTR
returns. Restore missing IS_ERR checks and ERR_PTR returns where
appropriate.
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org
Commit ffcc393641 ("dm: enhance internal suspend and resume interface")
attempted to handle multiple internal suspends on the same device, but
it did that incorrectly. When these functions are called in this order
on the same device the device is no longer suspended, but it should be:
dm_internal_suspend_noflush
dm_internal_suspend_noflush
dm_internal_resume
Fix this bug by maintaining an 'internal_suspend_count' and resuming
the device when this count drops to zero.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Introduce a new variable to count the number of allocated migration
structures. The existing variable cache->nr_migrations became
overloaded. It was used to:
i) track of the number of migrations in flight for the purposes of
quiescing during suspend.
ii) to estimate the amount of background IO occuring.
Recent discard changes meant that REQ_DISCARD bios are processed with
a migration. Discards are not background IO so nr_migrations was not
incremented. However this could cause quiescing to complete early.
(i) is now handled with a new variable cache->nr_allocated_migrations.
cache->nr_migrations has been renamed cache->nr_io_migrations.
cleanup_migration() is now called free_io_migration(), since it
decrements that variable.
Also, remove the unused cache->next_migration variable that got replaced
with with prealloc_structs a while ago.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org
If a DM table is reloaded with an inactive table when the device is not
suspended (normal procedure for LVM2), then there will be two dm-bufio
objects that can diverge. This can lead to a situation where the
inactive table uses bufio to read metadata at the same time the active
table writes metadata -- resulting in the inactive table having stale
metadata buffers once it is promoted to the active table slot.
Fix this by using reference counting and a global list of cache metadata
objects to ensure there is only one metadata object per metadata device.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org
Pull RCU updates from Paul E. McKenney:
- Documentation updates.
- Miscellaneous fixes.
- Preemptible-RCU fixes, including fixing an old bug in the
interaction of RCU priority boosting and CPU hotplug.
- SRCU updates.
- RCU CPU stall-warning updates.
- RCU torture-test updates.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Support for keyword 'boolean' will be dropped later on.
No functional change.
Reference: http://lkml.kernel.org/r/cover.1418003065.git.cj@linux.com
Signed-off-by: Christoph Jaeger <cj@linux.com>
Signed-off-by: Michal Marek <mmarek@suse.cz>
SRCU is not necessary to be compiled by default in all cases. For tinification
efforts not compiling SRCU unless necessary is desirable.
The current patch tries to make compiling SRCU optional by introducing a new
Kconfig option CONFIG_SRCU which is selected when any of the components making
use of SRCU are selected.
If we do not select CONFIG_SRCU, srcu.o will not be compiled at all.
text data bss dec hex filename
2007 0 0 2007 7d7 kernel/rcu/srcu.o
Size of arch/powerpc/boot/zImage changes from
text data bss dec hex filename
831552 64180 23944 919676 e087c arch/powerpc/boot/zImage : before
829504 64180 23952 917636 e0084 arch/powerpc/boot/zImage : after
so the savings are about ~2000 bytes.
Signed-off-by: Pranith Kumar <bobby.prani@gmail.com>
CC: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
CC: Josh Triplett <josh@joshtriplett.org>
CC: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
[ paulmck: resolve conflict due to removal of arch/ia64/kvm/Kconfig. ]
In bio-based DM's clone_endio(), when target_type doesn't implement
.end_io (e.g. linear) r will be always be initialized 0. So if a
WRITE SAME bio fails WRITE SAME will not be disabled as intended.
Fix this by initializing r to error, rather than 0, in clone_endio().
Signed-off-by: Alex Chen <alex.chen@huawei.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Fixes: 7eee4ae2db ("dm: disable WRITE SAME if it fails")
Cc: stable@vger.kernel.org
Commit 80e96c5484 ("dm thin: do not allow thin device activation
while pool is suspended") delayed the initialization of a new thin
device's refcount and completion until after this new thin was added
to the pool's active_thins list and the pool lock is released. This
opens a race with a worker thread that walks the list and calls
thin_get/put, noticing that the refcount goes to 0 and calling
complete, freezing up the system and giving the oops below:
kernel: BUG: unable to handle kernel NULL pointer dereference at (null)
kernel: IP: [<ffffffff810d360b>] __wake_up_common+0x2b/0x90
kernel: Call Trace:
kernel: [<ffffffff810d3683>] __wake_up_locked+0x13/0x20
kernel: [<ffffffff810d3dc7>] complete+0x37/0x50
kernel: [<ffffffffa0595c50>] thin_put+0x20/0x30 [dm_thin_pool]
kernel: [<ffffffffa059aab7>] do_worker+0x667/0x870 [dm_thin_pool]
kernel: [<ffffffff816a8a4c>] ? __schedule+0x3ac/0x9a0
kernel: [<ffffffff810b1aef>] process_one_work+0x14f/0x400
kernel: [<ffffffff810b206b>] worker_thread+0x6b/0x490
kernel: [<ffffffff810b2000>] ? rescuer_thread+0x260/0x260
kernel: [<ffffffff810b6a7b>] kthread+0xdb/0x100
kernel: [<ffffffff810b69a0>] ? kthread_create_on_node+0x170/0x170
kernel: [<ffffffff816ad7ec>] ret_from_fork+0x7c/0xb0
kernel: [<ffffffff810b69a0>] ? kthread_create_on_node+0x170/0x170
Set the thin device's initial refcount and initialize the completion
before adding it to the pool's active_thins list in thin_ctr().
Signed-off-by: Marc Dionne <marc.dionne@your-file-system.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Discard bios and thin device deletion have the potential to release data
blocks. If the thin-pool is in out-of-data-space mode, and blocks were
released, transition the thin-pool back to full write mode.
The correct time to do this is just after the thin-pool metadata commit.
It cannot be done before the commit because the space maps will not
allow immediate reuse of the data blocks in case there's a rollback
following power failure.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org
When the pool was in PM_OUT_OF_SPACE mode its process_prepared_discard
function pointer was incorrectly being set to
process_prepared_discard_passdown rather than process_prepared_discard.
This incorrect function pointer meant the discard was being passed down,
but not effecting the mapping. As such any discard that was issued, in
an attempt to reclaim blocks, would not successfully free data space.
Reported-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2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=Ar2y
-----END PGP SIGNATURE-----
Merge tag 'md/3.19' of git://neil.brown.name/md
Pull md updates from Neil Brown:
"Three fixes for md.
I did have a largish set of locking changes queued, but late testing
showed they weren't quite as stable as I thought and while I fixed
what I found, I decided it safer to delay them a release ...
particularly as I'll be AFK for a few weeks. So expect a larger batch
next time :-)"
* tag 'md/3.19' of git://neil.brown.name/md:
md: Check MD_RECOVERY_RUNNING as well as ->sync_thread.
md: fix semicolon.cocci warnings
md/raid5: fetch_block must fetch all the blocks handle_stripe_dirtying wants.
Pull block layer driver updates from Jens Axboe:
- NVMe updates:
- The blk-mq conversion from Matias (and others)
- A stack of NVMe bug fixes from the nvme tree, mostly from Keith.
- Various bug fixes from me, fixing issues in both the blk-mq
conversion and generic bugs.
- Abort and CPU online fix from Sam.
- Hot add/remove fix from Indraneel.
- A couple of drbd fixes from the drbd team (Andreas, Lars, Philipp)
- With the generic IO stat accounting from 3.19/core, converting md,
bcache, and rsxx to use those. From Gu Zheng.
- Boundary check for queue/irq mode for null_blk from Matias. Fixes
cases where invalid values could be given, causing the device to hang.
- The xen blkfront pull request, with two bug fixes from Vitaly.
* 'for-3.19/drivers' of git://git.kernel.dk/linux-block: (56 commits)
NVMe: fix race condition in nvme_submit_sync_cmd()
NVMe: fix retry/error logic in nvme_queue_rq()
NVMe: Fix FS mount issue (hot-remove followed by hot-add)
NVMe: fix error return checking from blk_mq_alloc_request()
NVMe: fix freeing of wrong request in abort path
xen/blkfront: remove redundant flush_op
xen/blkfront: improve protection against issuing unsupported REQ_FUA
NVMe: Fix command setup on IO retry
null_blk: boundary check queue_mode and irqmode
block/rsxx: use generic io stats accounting functions to simplify io stat accounting
md: use generic io stats accounting functions to simplify io stat accounting
drbd: use generic io stats accounting functions to simplify io stat accounting
md/bcache: use generic io stats accounting functions to simplify io stat accounting
NVMe: Update module version major number
NVMe: fail pci initialization if the device doesn't have any BARs
NVMe: add ->exit_hctx() hook
NVMe: make setup work for devices that don't do INTx
NVMe: enable IO stats by default
NVMe: nvme_submit_async_admin_req() must use atomic rq allocation
NVMe: replace blk_put_request() with blk_mq_free_request()
...
A recent change to md started the ->sync_thread from a asynchronously
from a work_queue rather than synchronously. This means that there
can be a small window between the time when MD_RECOVERY_RUNNING is set
and when ->sync_thread is set.
So code that checks ->sync_thread might now conclude that the thread
has not been started and (because a lock is held) will not be started.
That is no longer the case.
Most of those places are best fixed by testing MD_RECOVERY_RUNNING
as well. To make this completely reliable, we wake_up(&resync_wait)
after clearing that flag as well as after clearing ->sync_thread.
Other places are better served by flushing the relevant workqueue
to ensure that that if the sync thread was starting, it has now
started. This is particularly best if we are about to stop the
sync thread.
Fixes: ac05f25669
Signed-off-by: NeilBrown <neilb@suse.de>
performance requirements that were requested by the Gluster
distributed filesystem. Specifically, dm-thinp now takes care to
aggregate IO that will be issued to the same thinp block before
issuing IO to the underlying devices. This really helps improve
performance on HW RAID6 devices that have a writeback cache because it
avoids RMW in the HW RAID controller.
- Some stable fixes: fix leak in DM bufio if integrity profiles were
enabled, use memzero_explicit in DM crypt to avoid any potential for
information leak, and a DM cache fix to properly mark a cache block
dirty if it was promoted to the cache via the overwrite optimization.
- A few simple DM persistent data library fixes
- DM cache multiqueue policy block promotion improvements.
- DM cache discard improvements that take advantage of range
(multiblock) discard support in the DM bio-prison. This allows for
much more efficient bulk discard processing (e.g. when mkfs.xfs
discards the entire device).
- Some small optimizations in DM core and RCU deference cleanups
- DM core changes to suspend/resume code to introduce the new internal
suspend/resume interface that the DM thin-pool target now uses to
suspend/resume active thin devices when the thin-pool must
suspend/resume. This avoids forcing userspace to track all active
thin volumes in a thin-pool when the thin-pool is suspended for the
purposes of metadata or data space resize.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iQEcBAABAgAGBQJUhcvVAAoJEMUj8QotnQNaB78H+wSA6sDJGOhc6e1KlWoFh4Hx
hTmwm/O8Fxrp9StO3NPlcv9l+l9FX9pGzN/lo3OsxgWMTs/vLTKZ5SAe3/YT3/b9
6SFC7pC70+glakgMhhXWRvoeSEQC1OWb5BuvOF8irl2n+7B9NAn/zHd9pgpmyWHp
nBXK2GJBMzVSiI47NMjo2n6007LgQq0xxSJ9luwdrpwjDqD1d406DrhzbHou5H2Y
b8XJGQzUy0GZCX8ycwPVXo9svp2Bc+XajVcgOj5Qg7s2uV5car8NN7TxhSOKSXn2
VpiSyEa2MLHAbFuWtGs8XO98z/m5JlGf1eIgRO4s7w59URgpzdxOHXLlAoyqIGw=
=opXi
-----END PGP SIGNATURE-----
Merge tag 'dm-3.19-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm
Pull device mapper updates from Mike Snitzer:
- Significant DM thin-provisioning performance improvements to meet
performance requirements that were requested by the Gluster
distributed filesystem.
Specifically, dm-thinp now takes care to aggregate IO that will be
issued to the same thinp block before issuing IO to the underlying
devices. This really helps improve performance on HW RAID6 devices
that have a writeback cache because it avoids RMW in the HW RAID
controller.
- Some stable fixes: fix leak in DM bufio if integrity profiles were
enabled, use memzero_explicit in DM crypt to avoid any potential for
information leak, and a DM cache fix to properly mark a cache block
dirty if it was promoted to the cache via the overwrite optimization.
- A few simple DM persistent data library fixes
- DM cache multiqueue policy block promotion improvements.
- DM cache discard improvements that take advantage of range
(multiblock) discard support in the DM bio-prison. This allows for
much more efficient bulk discard processing (e.g. when mkfs.xfs
discards the entire device).
- Some small optimizations in DM core and RCU deference cleanups
- DM core changes to suspend/resume code to introduce the new internal
suspend/resume interface that the DM thin-pool target now uses to
suspend/resume active thin devices when the thin-pool must
suspend/resume.
This avoids forcing userspace to track all active thin volumes in a
thin-pool when the thin-pool is suspended for the purposes of
metadata or data space resize.
* tag 'dm-3.19-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm: (49 commits)
dm crypt: use memzero_explicit for on-stack buffer
dm space map metadata: fix sm_bootstrap_get_count()
dm space map metadata: fix sm_bootstrap_get_nr_blocks()
dm bufio: fix memleak when using a dm_buffer's inline bio
dm cache: fix spurious cell_defer when dealing with partial block at end of device
dm cache: dirty flag was mistakenly being cleared when promoting via overwrite
dm cache: only use overwrite optimisation for promotion when in writeback mode
dm cache: discard block size must be a multiple of cache block size
dm cache: fix a harmless race when working out if a block is discarded
dm cache: when reloading a discard bitset allow for a different discard block size
dm cache: fix some issues with the new discard range support
dm array: if resizing the array is a noop set the new root to the old one
dm: use rcu_dereference_protected instead of rcu_dereference
dm thin: fix pool_io_hints to avoid looking at max_hw_sectors
dm thin: suspend/resume active thin devices when reloading thin-pool
dm: enhance internal suspend and resume interface
dm thin: do not allow thin device activation while pool is suspended
dm: add presuspend_undo hook to target_type
dm: return earlier from dm_blk_ioctl if target doesn't implement .ioctl
dm thin: remove stale 'trim' message in block comment above pool_message
...
It is critical that fetch_block() and handle_stripe_dirtying()
are consistent in their analysis of what needs to be loaded.
Otherwise raid5 can wait forever for a block that won't be loaded.
Currently when writing to a RAID5 that is resyncing, to a location
beyond the resync offset, handle_stripe_dirtying chooses a
reconstruct-write cycle, but fetch_block() assumes a
read-modify-write, and a lockup can happen.
So treat that case just like RAID6, just as we do in
handle_stripe_dirtying. RAID6 always does reconstruct-write.
This bug was introduced when the behaviour of handle_stripe_dirtying
was changed in 3.7, so the patch is suitable for any kernel since,
though it will need careful merging for some versions.
Cc: stable@vger.kernel.org (v3.7+)
Fixes: a7854487cd
Reported-by: Henry Cai <henryplusplus@gmail.com>
Signed-off-by: NeilBrown <neilb@suse.de>
Use memzero_explicit to cleanup sensitive data allocated on stack
to prevent the compiler from optimizing and removing memset() calls.
Signed-off-by: Milan Broz <gmazyland@gmail.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org
This function isn't right and it causes a static checker warning:
drivers/md/dm-thin.c:3016 maybe_resize_data_dev()
error: potentially using uninitialized 'sb_data_size'.
It should set "*count" and return zero on success the same as the
sm_metadata_get_nr_blocks() function does earlier.
Fixes: 3241b1d3e0 ('dm: add persistent data library')
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
When dm-bufio sets out to use the bio built into a struct dm_buffer to
issue an IO, it needs to call bio_reset after it's done with the bio
so that we can free things attached to the bio such as the integrity
payload. Therefore, inject our own endio callback to take care of
the bio_reset after calling submit_io's end_io callback.
Test case:
1. modprobe scsi_debug delay=0 dif=1 dix=199 ato=1 dev_size_mb=300
2. Set up a dm-bufio client, e.g. dm-verity, on the scsi_debug device
3. Repeatedly read metadata and watch kmalloc-192 leak!
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org
We never bother caching a partial block that is at the back end of the
origin device. No cell ever gets locked, but the calling code was
assuming it was and trying to release it.
Now the code only releases if the cell has been set to a non NULL
value.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org
If the incoming bio is a WRITE and completely covers a block then we
don't bother to do any copying for a promotion operation. Once this is
done the cache block and origin block will be different, so we need to
set it to 'dirty'.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org
Overwrite causes the cache block and origin blocks to diverge, which
is only allowed in writeback mode.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org
Otherwise the cache blocks may span two discard blocks, which we don't
handle when doing the discard lookup.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
It is more correct to hold the cell before checking the discard state.
These flags are only used as hints to the policy so this change will
have negligable effect.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
The discard block size can change if the origin changes size or if an
old DM cache is upgraded from using a discard block size that was equal
to cache block size.
To fix this an extent of discarded blocks is established for the purpose
of translating the old discard block size to the new in-core discard
block size and set bits. The old (potentially huge) discard bitset is
left ondisk until it is re-written using the new in-core information on
the next successful DM cache shutdown.
Fixes: 7ae34e7778 ("dm cache: improve discard support")
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Commit 7ae34e777 ("dm cache: improve discard support") needed to also:
- discontinue having DM core split the discard bios on cache block
boundaries
- calculate the cache's discard_nr_blocks relative to the determined
discard_block_size rather than using oblock_to_dblock()
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
This could've been quite bad (to return success but not update the new
root to point at the old) but in practice the only known consumer of the
dm array code is the DM cache target. And the DM cache target passes in
the same old root to array_resize() anyway.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Use generic io stats accounting help functions (generic_{start,end}_io_acct)
to simplify io stat accounting.
Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com>
Acked-by: Kent Overstreet <kmo@datera.io>
Signed-off-by: Jens Axboe <axboe@fb.com>
rcu_dereference() should be used in sections protected by rcu_read_lock.
For writers, holding some kind of mutex or lock,
rcu_dereference_protected() is the way to go, adding explicit lockdep
bits.
In __unbind(), we are the last user of this mapped device, so can use
the constant '1' instead of a lockdep_is_held(), not consistent with
other uses of rcu_dereference_protected() which use md->suspend_lock
mutex.
Reported-by: Kirill A. Shutemov <kirill@shutemov.name>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Fixes: 33423974bf ("dm: Use rcu_dereference() for accessing rcu pointer")
Cc: Pranith Kumar <bobby.prani@gmail.com>
[snitzer: allow lines longer than 80 columns, refine subject]
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Simplify the pool_io_hints code that works to establish a max_sectors
value that is a power-of-2 factor of the thin-pool's blocksize. The
biggest associated improvement is that the DM thin-pool is no longer
concerning itself with the data device's max_hw_sectors when adjusting
max_sectors.
This fixes the relative fragility of the original "dm thin: adjust
max_sectors_kb based on thinp blocksize" commit that only became
apparent when testing was performed using a DM thin-pool ontop of a
virtio_blk device. One proposed upstream patch detailed the problems
inherent in virtio_blk: https://lkml.org/lkml/2014/11/20/611
So even though virtio_blk incorrectly set its max_hw_sectors it actually
helped make it clear that we need DM thinp to be tolerant of any future
Linux driver that incorrectly sets max_hw_sectors.
We only need to be concerned with modifying the thin-pool device's
max_sectors limit if it is smaller than the thin-pool's blocksize. In
this case the value of max_sectors does become a limiting factor when
upper layers (e.g. filesystems) construct their bios. But if the
hardware can support IOs larger than the thin-pool's blocksize the user
is encouraged to adjust the thin-pool's data device's max_sectors
accordingly -- doing so will enable the thin-pool to inherit the
established user-defined max_sectors.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Before this change it was expected that userspace would first suspend
all active thin devices, reload/resize the thin-pool target, then resume
all active thin devices. Now the thin-pool suspend/resume will trigger
the suspend/resume of all active thins via appropriate calls to
dm_internal_suspend and dm_internal_resume.
Store the mapped_device for each thin device in struct thin_c to make
these calls possible.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Acked-by: Joe Thornber <ejt@redhat.com>
Rename dm_internal_{suspend,resume} to dm_internal_{suspend,resume}_fast
-- dm-stats will continue using these methods to avoid all the extra
suspend/resume logic that is not needed in order to quickly flush IO.
Introduce dm_internal_suspend_noflush() variant that actually calls the
mapped_device's target callbacks -- otherwise target-specific hooks are
avoided (e.g. dm-thin's thin_presuspend and thin_postsuspend). Common
code between dm_internal_{suspend_noflush,resume} and
dm_{suspend,resume} was factored out as __dm_{suspend,resume}.
Update dm_internal_{suspend_noflush,resume} to always take and release
the mapped_device's suspend_lock. Also update dm_{suspend,resume} to be
aware of potential for DM_INTERNAL_SUSPEND_FLAG to be set and respond
accordingly by interruptibly waiting for the DM_INTERNAL_SUSPEND_FLAG to
be cleared. Add lockdep annotation to dm_suspend() and dm_resume().
The existing DM_SUSPEND_FLAG remains unchanged.
DM_INTERNAL_SUSPEND_FLAG is set by dm_internal_suspend_noflush() and
cleared by dm_internal_resume().
Both DM_SUSPEND_FLAG and DM_INTERNAL_SUSPEND_FLAG may be set if a device
was already suspended when dm_internal_suspend_noflush() was called --
this can be thought of as a "nested suspend". A "nested suspend" can
occur with legacy userspace dm-thin code that might suspend all active
thin volumes before suspending the pool for resize.
But otherwise, in the normal dm-thin-pool suspend case moving forward:
the thin-pool will have DM_SUSPEND_FLAG set and all active thins from
that thin-pool will have DM_INTERNAL_SUSPEND_FLAG set.
Also add DM_INTERNAL_SUSPEND_FLAG to status report. This new
DM_INTERNAL_SUSPEND_FLAG state is being reported to assist with
debugging (e.g. 'dmsetup info' will report an internally suspended
device accordingly).
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Acked-by: Joe Thornber <ejt@redhat.com>
Otherwise IO could be issued to the pool while it is suspended.
Care was taken to properly interlock between the thin and thin-pool
targets when accessing the pool's 'suspended' flag. The thin_ctr will
not add a new thin device to the pool's active_thins list if the pool is
susepended.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Acked-by: Joe Thornber <ejt@redhat.com>
The DM thin-pool target now must undo the changes performed during
pool_presuspend() so introduce presuspend_undo hook in target_type.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Acked-by: Joe Thornber <ejt@redhat.com>
This fixes a regression introduced in 3.13.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2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=Fs49
-----END PGP SIGNATURE-----
Merge tag 'md/3.18-fix' of git://neil.brown.name/md
Pull md bugfix from Neil Brown:
"One fix for md for 3.18.
This fixes a regression introduced in 3.13"
* tag 'md/3.18-fix' of git://neil.brown.name/md:
md: Always set RECOVERY_NEEDED when clearing RECOVERY_FROZEN
md_check_recovery will skip any recovery and also clear
MD_RECOVERY_NEEDED if MD_RECOVERY_FROZEN is set.
So when we clear _FROZEN, we must set _NEEDED and ensure that
md_check_recovery gets run.
Otherwise we could miss out on something that is needed.
In particular, this can make it impossible to remove a
failed device from an array is the 'recovery-needed' processing
didn't happen.
Suitable for stable kernels since 3.13.
Cc: stable@vger.kernel.org (3.13+)
Reported-and-tested-by: Joe Lawrence <joe.lawrence@stratus.com>
Fixes: 30b8feb730
Signed-off-by: NeilBrown <neilb@suse.de>
. stable fix for a dm-cache related bug in dm-btree walking code that
results from using very large fast device (e.g. 4T) with a very small
cache blocksize (e.g. 32K) -- this is a very uncommon configuration
. a couple fixes for dm-raid (one for stable and the other addresses a
crash in 3.18-rc1 code)
. stable fix for dm-thinp that addresses a very rare dm-bufio bug having
to do with memory reclaimation (via shrinker) when using dm-thinp
ontop of loopback devices
. fix a leak in dm-stripe target constructor's error path
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iQEcBAABAgAGBQJUY/p7AAoJEMUj8QotnQNaxPEIAJsmJC5ujQAIdm5yUxsOWruU
Y/36HbPvlmV8fgWqGyjaubBrzqgWry/yW/u/Sv9+9rE3Zh6JSVLVrCA6uZZ3Yr+j
HKYEPjm/O0zVJepfEDKtjG6dxeaql47+luwU1iP1bAYeZE3zmKn1oFT2GW5gTbxO
2n3MiN/dyX8v0cTw6r0O69luIAu93CSY0XDk+1ynfKlKKVmgcAUPvKuobF+yHXoF
Rd7KTqFoK6HgRhdUHvUQnCGDandZ9MHjt3oW9p3dv3ezvW1cNUARoVHMRGG6Awfu
WZkQ/VORDeaJT+bhjGfPIla1HbgxEKJrgzTUlpj+P6K2uPK2f6ECEyBpDLWKy9g=
=lkSu
-----END PGP SIGNATURE-----
Merge tag 'dm-3.18-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm
Pull device mapper fixes from Mike Snitzer:
- stable fix for dm-thin that avoids normal IO racing with discard
- stable fix for a dm-cache related bug in dm-btree walking code that
results from using very large fast device (eg 4T) with a very small
cache blocksize (eg 32K) -- this is a very uncommon configuration
- a couple fixes for dm-raid (one for stable and the other addresses a
crash in 3.18-rc1 code)
- stable fix for dm-thinp that addresses a very rare dm-bufio bug
having to do with memory reclaimation (via shrinker) when using
dm-thinp ontop of loopback devices
- fix a leak in dm-stripe target constructor's error path
* tag 'dm-3.18-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
dm btree: fix a recursion depth bug in btree walking code
dm thin: grab a virtual cell before looking up the mapping
dm raid: fix inaccessible superblocks causing oops in configure_discard_support
dm raid: ensure superblock's size matches device's logical block size
dm bufio: change __GFP_IO to __GFP_FS in shrinker callbacks
dm stripe: fix potential for leak in stripe_ctr error path
As long as struct thin_c is in the list, anyone can grab a reference of
it. Consequently, we must wait for the reference count to drop to zero
*after* we remove the structure from the list, not before.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Loading and saving millions of block mappings takes time. We may as
well explain what's going on, and encourage people to use a larger
cache block size.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Safely allow the discard blocksize to be larger than the cache blocksize
by using the bio prison's range locking support. This also improves
discard performance considerly because larger discards are issued to the
dm-cache device. The discard blocksize was always intended to be
greater than the cache blocksize. But until now it wasn't implemented
safely.
Also, by safely restoring the ability to have discard blocksize larger
than cache blocksize we're able to significantly reduce the memory used
for the cache's discard bitset. Before, with a small discard blocksize,
the discard bitset could get quite large because its size is a function
of the discard blocksize and the origin device's size. For example,
previously, using a 32KB cache blocksize with a 40TB origin resulted in
1280MB of incore memory use for the discard bitset! Now, the discard
blocksize is scaled up accordingly to ensure the discard bitset is
capped at 2**14 bits, or 16KB.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
This reverts commit d132cc6d9e because we
actually do want to allow the discard blocksize to be larger than the
cache blocksize. Further dm-cache discard changes will make this
possible.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
This reverts commit 64ab346a36 because we
actually do want to allow the discard blocksize to be larger than the
cache blocksize. Further dm-cache discard changes will make this
possible.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Ranges will be placed in the same cell if they overlap.
Range locking is a prerequisite for more efficient multi-block discard
support in both the cache and thin-provisioning targets.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Before, if the user wanted sequential IO to be promoted to the cache
they'd have to set sequential_threshold to some nebulous large value.
Now, the user may easily disable sequential IO detection (and sequential
IO's implicit bypass of the cache) by setting sequential_threshold to 0.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Rather than maintaining a separate promote_threshold variable that we
periodically update we now use the hit count of the oldest clean
block. Also add a fudge factor to discourage demoting dirty blocks.
With some tests this has a sizeable difference, because the old code
was too eager to demote blocks. For example, device-mapper-test-suite's
git_extract_cache_quick test goes from taking 190 seconds, to 142
(linear on spindle takes 250).
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
When creating new devices dm_sync_table() calls
synchronize_rcu_expedited(), causing _all_ pending RCU pointers to be
flushed. This causes a latency overhead that is especially noticeable
when creating lots of devices.
And all of this is pointless as there are no old maps to be
disconnected, and hence no stale pointers which would need to be
cleared up.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Annotate the map field with __rcu since this is a rcu pointer which is checked
by sparse.
Signed-off-by: Pranith Kumar <bobby.prani@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
The map field in 'struct mapped_device' is an rcu pointer. Use rcu_dereference()
while accessing it.
Signed-off-by: Pranith Kumar <bobby.prani@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Sort the cells in logical block order before processing each cell in
process_thin_deferred_cells(). This significantly improves the ondisk
layout on rotational storage, whereby improving read performance.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
This use of direct submission in process_shared_bio() reduces latency
for submitting bios in the shared cell by avoiding adding those bios to
the deferred list and waiting for the next iteration of the worker.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
This use of direct submission in process_prepared_mapping() reduces
latency for submitting bios in a cell by avoiding adding those bios to
the deferred list and waiting for the next iteration of the worker.
But this direct submission exposes the potential for a race between
releasing a cell and incrementing deferred set. Fix this by introducing
dm_cell_visit_release() and refactoring inc_remap_and_issue_cell()
accordingly.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
This avoids dropping the cell, so increases the probability that other
bios will collect within the cell, rather than being passed individually
to the worker.
Also add required process_cell and process_discard_cell error handling
wrappers and set associated pool-mode function pointers accordingly.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
When processing a discard bio, if the block is already quiesced do the
discard immediately rather than adding the mapping to a list for the
next iteration of the worker thread.
Discarding a fully provisioned 100G thin volume with 64k block size goes
from 860s to 95s with this change.
Clearly there's something wrong with the worker architecture, more
investigation needed.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Introduce thin_merge so that any additional constraints from the data
volume may be taken into account when determing the maximum number of
sectors that can be issued relative to the specified logical offset.
This is particularly important if/when the data volume is layered ontop
of a more sophisticated device (e.g. dm-raid or some other DM target).
Reviewed-by: Heinz Mauelshagen <heinzm@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
These code changes do not introduce a functional change.
But bio_add_page() will never attempt to build up a bio larger than
queue_max_sectors(). Similarly, bio_get_nr_vecs() is also bound by
queue_max_sectors(). Therefore, there is no point in allowing
dm_merge_bvec() to answer "how many sectors can a bio have at this
offset?" with anything larger than queue_max_sectors(). Using
queue_max_sectors() rather than BIO_MAX_SECTORS serves to more
accurately convey the limits that are being imposed.
Also, use unlikely() to clarify the fact that the defensive code in
dm_merge_bvec() relative to max_size going negative shouldn't ever
happen -- if it does happen there is a bug in the block layer for
requesting larger than dm_merge_bvec()'s initial response for a given
offset. Also, update a comment in dm_merge_bvec() relative to
max_hw_sectors_kb. And fix empty newline whitespace.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Allows for filesystems to submit bios that are a factor of the thinp
blocksize, improving dm-thinp efficiency (particularly when the data
volume is RAID).
Also set io_min to max_sectors_kb if it is a factor of the thinp
blocksize.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Throttle IO based on the time it's taking the worker to do one loop.
There were reports of hung task timeouts occuring and it was observed
that the excessively long avgqu-sz (as reported by iostat) was
contributing to these hung tasks.
Throttling definitely helps dm-thinp perform better under heavy IO load
(without being detremental by being overzealous). It reduces avgqu-sz
drastically, e.g.: from 60K to ~6K, and even as low as 150 once metadata
is cached by bufio, when dirty_ratio=5, dirty_background_ratio=2. And
avgqu-sz stays at or below 30K even with dirty_ratio=20,
dirty_background_ratio=10.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Prefetch metadata at the start of the worker thread and then again every
128th bio processed from the deferred list.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Introduce the dm_tm_issue_prefetches interface. If you're using a
non-blocking clone the tm will build up a list of requested blocks that
weren't in core. dm_tm_issue_prefetches will request those blocks to be
prefetched.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
This change is a prerequisite for allowing metadata to be prefetched.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Previously it was using a fixed sized hash table. There are times
when very many concurrent cells are held (such as when processing a very
large discard). When this happens the hash table performance becomes
very poor.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
These changes help keep metadata backed by dm-bufio in-core longer which
fixes reports of metadata churn in the face of heavy random IO workloads.
Before, bufio evicted all buffers older than DM_BUFIO_DEFAULT_AGE_SECS.
Having a device (e.g. dm-thinp or dm-cache) lose all metadata just
because associated buffers had been idle for some time is unfriendly.
Now, the user may now configure the number of bytes that bufio retains
using the 'retain_bytes' module parameter. The default is 256K.
Also, the DM_BUFIO_WORK_TIMER_SECS and DM_BUFIO_DEFAULT_AGE_SECS
defaults were quite low so increase them (to 30 and 300 respectively).
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Converting over to using an rbtree eliminates a fixed 8MB allocation
from vmalloc space for the hash table.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
The walk code was using a 'ro_spine' to hold it's locked btree nodes.
But this data structure is designed for the rolling lock scheme, and
as such automatically unlocks blocks that are two steps up the call
chain. This is not suitable for the simple recursive walk algorithm,
which retraces its steps.
This code is only used by the persistent array code, which in turn is
only used by dm-cache. In order to trigger it you need to have a
mapping tree that is more than 2 levels deep; which equates to 8-16
million cache blocks. For instance a 4T ssd with a very small block
size of 32k only just triggers this bug.
The fix just places the locked blocks on the stack, and stops using
the ro_spine altogether.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org
Avoids normal IO racing with discard.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org
Commit 48cf06bc5f ("dm raid: add discard support for RAID levels 4, 5
and 6") did not properly handle missing metadata device(s). A failing
read of the superblock causes the metadata and data devices to be
removed from the dev array in struct raid_set, setting references to
both devices to NULL. configure_discard_support() nonetheless tries to
access the data dev unconditionally causing an oops.
Signed-off-by: Heinz Mauelshagen <heinzm@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
The dm-raid superblock (struct dm_raid_superblock) is padded to 512
bytes and that size is being used to read it in from the metadata
device into one preallocated page.
Reading or writing this on a 512-byte sector device works fine but on
a 4096-byte sector device this fails.
Set the dm-raid superblock's size to the logical block size of the
metadata device, because IO at that size is guaranteed too work. Also
add a size check to avoid silent partial metadata loss in case the
superblock should ever grow past the logical block size or PAGE_SIZE.
[includes pointer math fix from Dan Carpenter]
Reported-by: "Liuhua Wang" <lwang@suse.com>
Signed-off-by: Heinz Mauelshagen <heinzm@redhat.com>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org
bioset_create_nobvec() interface when creating the DM's bioset
. fix a few bugs in dm-bufio and dm-log-userspace
. add DM core support for a DM multipath use-case that requires loading
DM tables that contain devices that have failed (by allowing active
and inactive DM tables to share dm_devs)
. add discard support to the DM raid target; like MD raid456 the user
must opt-in to raid456 discard support be specifying the
devices_handle_discard_safely=Y module param.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iQEcBAABAgAGBQJUQWcdAAoJEMUj8QotnQNaHaQH/RD0xf54AnaQ0tEGuNQXFwtx
Gc/3s+VEcKlmTvk9nm2FWNvVagPn8uBQ0O2eid4UJk9AyfPJnPwGUoVqxbKhKK9i
G5/O5s8opLlItk14h/btw/zB8RNC1bg8NGnBrGYDudiwHm+Gv4jlnHErp2JMHv9F
nonb+QoG23wlEJkBafzBNYhthkNDq1ZFrDjhqG7dNySkXh8VZAW8VcZ/ZfskkhOa
C8CDl3TKL1BBJHQKesvqHQbCSqh8Ujzs63bLA3heaSMExkhmUgdfpnbHK4hzPNJP
rtmVEW57mVI+O5Cfva1p9RClT5EjiO+5VufHkpRJSIsfsH5PMaQ7vW8gKmwd5JA=
=z+Yz
-----END PGP SIGNATURE-----
Merge tag 'dm-3.18' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm
Pull device-mapper updates from Mike Snitzer:
"I rebased the DM tree ontop of linux-block.git's 'for-3.18/core' at
the beginning of October because DM core now depends on the newly
introduced bioset_create_nobvec() interface.
Summary:
- fix DM's long-standing excessive use of memory by leveraging the
new bioset_create_nobvec() interface when creating the DM's bioset
- fix a few bugs in dm-bufio and dm-log-userspace
- add DM core support for a DM multipath use-case that requires
loading DM tables that contain devices that have failed (by
allowing active and inactive DM tables to share dm_devs)
- add discard support to the DM raid target; like MD raid456 the user
must opt-in to raid456 discard support be specifying the
devices_handle_discard_safely=Y module param"
* tag 'dm-3.18' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
dm log userspace: fix memory leak in dm_ulog_tfr_init failure path
dm bufio: when done scanning return from __scan immediately
dm bufio: update last_accessed when relinking a buffer
dm raid: add discard support for RAID levels 4, 5 and 6
dm raid: add discard support for RAID levels 1 and 10
dm: allow active and inactive tables to share dm_devs
dm mpath: stop queueing IO when no valid paths exist
dm: use bioset_create_nobvec()
dm: remove nr_iovecs parameter from alloc_tio()
Pull block layer driver update from Jens Axboe:
"This is the block driver pull request for 3.18. Not a lot in there
this round, and nothing earth shattering.
- A round of drbd fixes from the linbit team, and an improvement in
asender performance.
- Removal of deprecated (and unused) IRQF_DISABLED flag in rsxx and
hd from Michael Opdenacker.
- Disable entropy collection from flash devices by default, from Mike
Snitzer.
- A small collection of xen blkfront/back fixes from Roger Pau Monné
and Vitaly Kuznetsov"
* 'for-3.18/drivers' of git://git.kernel.dk/linux-block:
block: disable entropy contributions for nonrot devices
xen, blkfront: factor out flush-related checks from do_blkif_request()
xen-blkback: fix leak on grant map error path
xen/blkback: unmap all persistent grants when frontend gets disconnected
rsxx: Remove deprecated IRQF_DISABLED
block: hd: remove deprecated IRQF_DISABLED
drbd: use RB_DECLARE_CALLBACKS() to define augment callbacks
drbd: compute the end before rb_insert_augmented()
drbd: Add missing newline in resync progress display in /proc/drbd
drbd: reduce lock contention in drbd_worker
drbd: Improve asender performance
drbd: Get rid of the WORK_PENDING macro
drbd: Get rid of the __no_warn and __cond_lock macros
drbd: Avoid inconsistent locking warning
drbd: Remove superfluous newline from "resync_extents" debugfs entry.
drbd: Use consistent names for all the bi_end_io callbacks
drbd: Use better variable names
- a few minor bug fixes
- quite a lot of code tidy-up and simplification
- remove PRINT_RAID_DEBUG ioctl. I'm fairly sure
it is unused, and it isn't particularly useful.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.22 (GNU/Linux)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=2QEJ
-----END PGP SIGNATURE-----
Merge tag 'md/3.18' of git://neil.brown.name/md
Pull md updates from Neil Brown:
- a few minor bug fixes
- quite a lot of code tidy-up and simplification
- remove PRINT_RAID_DEBUG ioctl. I'm fairly sure it is unused, and it
isn't particularly useful.
* tag 'md/3.18' of git://neil.brown.name/md: (21 commits)
lib/raid6: Add log level to printks
md: move EXPORT_SYMBOL to after function in md.c
md: discard PRINT_RAID_DEBUG ioctl
md: remove MD_BUG()
md: clean up 'exit' labels in md_ioctl().
md: remove unnecessary test for MD_MAJOR in md_ioctl()
md: don't allow "-sync" to be set for device in an active array.
md: remove unwanted white space from md.c
md: don't start resync thread directly from md thread.
md: Just use RCU when checking for overlap between arrays.
md: avoid potential long delay under pers_lock
md: simplify export_array()
md: discard find_rdev_nr in favour of find_rdev_nr_rcu
md: use wait_event() to simplify md_super_wait()
md: be more relaxed about stopping an array which isn't started.
md/raid1: process_checks doesn't use its return value.
md/raid5: fix init_stripe() inconsistencies
md/raid10: another memory leak due to reshape.
md: use set_bit/clear_bit instead of shift/mask for bi_flags changes.
md/raid1: minor typos and reformatting.
...
The shrinker uses gfp flags to indicate what kind of operation can the
driver wait for. If __GFP_IO flag is present, the driver can wait for
block I/O operations, if __GFP_FS flag is present, the driver can wait on
operations involving the filesystem.
dm-bufio tested for __GFP_IO. However, dm-bufio can run on a loop block
device that makes calls into the filesystem. If __GFP_IO is present and
__GFP_FS isn't, dm-bufio could still block on filesystem operations if it
runs on a loop block device.
The change from __GFP_IO to __GFP_FS supposedly fixes one observed (though
unreproducible) deadlock involving dm-bufio and loop device.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org
Pull percpu consistent-ops changes from Tejun Heo:
"Way back, before the current percpu allocator was implemented, static
and dynamic percpu memory areas were allocated and handled separately
and had their own accessors. The distinction has been gone for many
years now; however, the now duplicate two sets of accessors remained
with the pointer based ones - this_cpu_*() - evolving various other
operations over time. During the process, we also accumulated other
inconsistent operations.
This pull request contains Christoph's patches to clean up the
duplicate accessor situation. __get_cpu_var() uses are replaced with
with this_cpu_ptr() and __this_cpu_ptr() with raw_cpu_ptr().
Unfortunately, the former sometimes is tricky thanks to C being a bit
messy with the distinction between lvalues and pointers, which led to
a rather ugly solution for cpumask_var_t involving the introduction of
this_cpu_cpumask_var_ptr().
This converts most of the uses but not all. Christoph will follow up
with the remaining conversions in this merge window and hopefully
remove the obsolete accessors"
* 'for-3.18-consistent-ops' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu: (38 commits)
irqchip: Properly fetch the per cpu offset
percpu: Resolve ambiguities in __get_cpu_var/cpumask_var_t -fix
ia64: sn_nodepda cannot be assigned to after this_cpu conversion. Use __this_cpu_write.
percpu: Resolve ambiguities in __get_cpu_var/cpumask_var_t
Revert "powerpc: Replace __get_cpu_var uses"
percpu: Remove __this_cpu_ptr
clocksource: Replace __this_cpu_ptr with raw_cpu_ptr
sparc: Replace __get_cpu_var uses
avr32: Replace __get_cpu_var with __this_cpu_write
blackfin: Replace __get_cpu_var uses
tile: Use this_cpu_ptr() for hardware counters
tile: Replace __get_cpu_var uses
powerpc: Replace __get_cpu_var uses
alpha: Replace __get_cpu_var
ia64: Replace __get_cpu_var uses
s390: cio driver &__get_cpu_var replacements
s390: Replace __get_cpu_var uses
mips: Replace __get_cpu_var uses
MIPS: Replace __get_cpu_var uses in FPU emulator.
arm: Replace __this_cpu_ptr with raw_cpu_ptr
...
Replaced the use of a Variable Length Array In Struct (VLAIS) with a C99
compliant equivalent. This patch allocates the appropriate amount of memory
using a char array using the SHASH_DESC_ON_STACK macro.
The new code can be compiled with both gcc and clang.
Signed-off-by: Jan-Simon Möller <dl9pf@gmx.de>
Signed-off-by: Behan Webster <behanw@converseincode.com>
Reviewed-by: Mark Charlebois <charlebm@gmail.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Cc: pageexec@freemail.hu
Cc: gmazyland@gmail.com
Cc: "David S. Miller" <davem@davemloft.net>
All the interesting information printed by this ioctl
is provided in /proc/mdstat and/or sysfs.
So it isn't needed and isn't used and would be best if it didn't
exist.
Signed-off-by: NeilBrown <neilb@suse.de>
Most of the places that call this are doing so pointlessly.
A couple of the others a best replaced with WARN_ON().
Signed-off-by: NeilBrown <neilb@suse.de>
unknown ioctls no longer get this deep into md_ioctl since
md_ioctl_valid() was introduced in 3.14.
So remove the test and the misleading comment.
Signed-off-by: NeilBrown <neilb@suse.de>
If an array is active, devices can be marked 'faulty', but simply
removing the 'sync' flag is wrong. That only makes sense
for an array which is not active (and is probably only useful
for testing anyway).
Signed-off-by: NeilBrown <neilb@suse.de>
The main 'md' thread is needed for processing writes, so if it blocks
write requests could be delayed.
Starting a new thread requires some GFP_KERNEL allocations and so can
wait for writes to complete. This can deadlock.
So instead, ask a workqueue to start the sync thread.
There is no particular rush for this to happen, so any work queue
will do.
MD_RECOVERY_RUNNING is used to ensure only one thread is started.
Reported-by: BillStuff <billstuff2001@sbcglobal.net>
Signed-off-by: NeilBrown <neilb@suse.de>
We don't really need the full mddev_lock here, and having to
drop it is messy.
RCU is enough to protect these lists.
Signed-off-by: NeilBrown <neilb@suse.de>
printk may cause long time lapse if value of printk_delay in sysctl is
configured large by user. If register_md_personality takes long time to print in
spinlock pers_lock, we may encounter high CPU usage rate when there are other
pers_lock competitors who may be blocked to spin.
We can avoid this condition by moving printk out of coverage of pers_lock
spinlock.
Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: NeilBrown <neilb@suse.de>
In general we don't allow an array to be stopped if it is in use.
However if the array hasn't really been started yet, then any
apparent use is an anomily, probably due to 'udev' or similar
having a look to see what is there.
This means that if something goes wrong while assembling an array
it cannot reliably be un-assembled - STOP_ARRAY could fail.
There is no value here, so change do_md_stop() to succeed
despite concurrent opens if the array has not yet been
activated. i.e. if ->pers is NULL.
Reported-by: "Baldysiak, Pawel" <pawel.baldysiak@intel.com>
Signed-off-by: NeilBrown <neilb@suse.de>
raid5: fix init_stripe() inconsistencies
1) remove_hash() is not necessary. We will only be called right after
get_free_stripe(). There we have already a call to remove_hash().
2) Tracing prints out the sector of the freed stripe and not the sector
that we want to initialize.
Signed-off-by: NeilBrown <neilb@suse.de>
Pull scheduler updates from Ingo Molnar:
"The main changes in this cycle were:
- Optimized support for Intel "Cluster-on-Die" (CoD) topologies (Dave
Hansen)
- Various sched/idle refinements for better idle handling (Nicolas
Pitre, Daniel Lezcano, Chuansheng Liu, Vincent Guittot)
- sched/numa updates and optimizations (Rik van Riel)
- sysbench speedup (Vincent Guittot)
- capacity calculation cleanups/refactoring (Vincent Guittot)
- Various cleanups to thread group iteration (Oleg Nesterov)
- Double-rq-lock removal optimization and various refactorings
(Kirill Tkhai)
- various sched/deadline fixes
... and lots of other changes"
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (72 commits)
sched/dl: Use dl_bw_of() under rcu_read_lock_sched()
sched/fair: Delete resched_cpu() from idle_balance()
sched, time: Fix build error with 64 bit cputime_t on 32 bit systems
sched: Improve sysbench performance by fixing spurious active migration
sched/x86: Fix up typo in topology detection
x86, sched: Add new topology for multi-NUMA-node CPUs
sched/rt: Use resched_curr() in task_tick_rt()
sched: Use rq->rd in sched_setaffinity() under RCU read lock
sched: cleanup: Rename 'out_unlock' to 'out_free_new_mask'
sched: Use dl_bw_of() under RCU read lock
sched/fair: Remove duplicate code from can_migrate_task()
sched, mips, ia64: Remove __ARCH_WANT_UNLOCKED_CTXSW
sched: print_rq(): Don't use tasklist_lock
sched: normalize_rt_tasks(): Don't use _irqsave for tasklist_lock, use task_rq_lock()
sched: Fix the task-group check in tg_has_rt_tasks()
sched/fair: Leverage the idle state info when choosing the "idlest" cpu
sched: Let the scheduler see CPU idle states
sched/deadline: Fix inter- exclusive cpusets migrations
sched/deadline: Clear dl_entity params when setscheduling to different class
sched/numa: Kill the wrong/dead TASK_DEAD check in task_numa_fault()
...
Fix a potential struct stripe_c leak that would occur if the
chunk_size exceeded the maximum allowed by dm_set_target_max_io_len
(UINT_MAX). However, in practice there is no possibility of this
occuring given that chunk_size is of type uint32_t. But it is good to
fix this to future-proof in case dm_set_target_max_io_len's
implementation were to change.
Signed-off-by: Pavitra Kumar <pavitrak@nvidia.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
If two threads call bitmap_unplug at the same time, then
one might schedule all the writes, and the other might
decide that it doesn't need to wait. But really it does.
It rarely hurts to wait when it isn't absolutely necessary,
and the current code doesn't really focus on 'absolutely necessary'
anyway. So just wait always.
This can potentially lead to data corruption if a crash happens
at an awkward time and data was written before the bitmap was
updated. It is very unlikely, but this should go to -stable
just to be safe. Appropriate for any -stable.
Signed-off-by: NeilBrown <neilb@suse.de>
Cc: stable@vger.kernel.org (please delay until 3.18 is released)
If cn_add_callback() fails in dm_ulog_tfr_init(), it does not
deallocate prealloced memory but calls cn_del_callback().
Found by Linux Driver Verification project (linuxtesting.org).
Signed-off-by: Alexey Khoroshilov <khoroshilov@ispras.ru>
Reviewed-by: Jonathan Brassow <jbrassow@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org
When __scan frees the required number of buffer entries that the
shrinker requested (nr_to_scan becomes zero) it must return. Before
this fix the __scan code exited only the inner loop and continued in the
outer loop -- which could result in reduced performance due to extra
buffers being freed (e.g. unnecessarily evicted thinp metadata needing
to be synchronously re-read into bufio's cache).
Also, move dm_bufio_cond_resched to __scan's inner loop, so that
iterating the bufio client's lru lists doesn't result in scheduling
latency.
Reported-by: Joe Thornber <thornber@redhat.com>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org # 3.2+
The 'last_accessed' member of the dm_buffer structure was only set when
the the buffer was created. This led to each buffer being discarded
after dm_bufio_max_age time even if it was used recently. In practice
this resulted in all thinp metadata being evicted soon after being read
-- this is particularly problematic for metadata intensive workloads
like multithreaded small random IO.
'last_accessed' is now updated each time the buffer is moved to the head
of the LRU list, so the buffer is now properly discarded if it was not
used in dm_bufio_max_age time.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org # v3.2+
In case of RAID levels 4, 5 and 6 we have to verify each RAID members'
ability to zero data on discards to avoid stripe data corruption -- if
discard_zeroes_data is not set for each RAID member discard support must
be disabled. But given the uncertainty of whether or not a RAID member
properly supports zeroing data on discard we require the user to
explicitly allow discard support on RAID levels 4, 5, and 6 by setting
a dm-raid module paramter, e.g.: dm-raid.devices_handle_discard_safely=Y
Otherwise, discards could cause data corruption on RAID4/5/6.
Signed-off-by: Heinz Mauelshagen <heinzm@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Discard support is not enabled for RAID levels 4, 5, and 6 at this time
due to concerns about unreliable discard_zeroes_data support on some
hardware. Otherwise, discards could cause stripe data corruption
(classic example of bad apples spoiling the bunch).
Signed-off-by: Heinz Mauelshagen <heinzm@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Until this change, when loading a new DM table, DM core would re-open
all of the devices in the DM table. Now, DM core will avoid redundant
device opens (and closes when destroying the old table) if the old
table already has a device open using the same mode. This is achieved
by managing reference counts on the table_devices that DM core now
stores in the mapped_device structure (rather than in the dm_table
structure). So a mapped_device's active and inactive dm_tables' dm_dev
lists now just point to the dm_devs stored in the mapped_device's
table_devices list.
This improvement in DM core's device reference counting has the
side-effect of fixing a long-standing limitation of the multipath
target: a DM multipath table couldn't include any paths that were unusable
(failed). For example: if all paths have failed and you add a new,
working, path to the table; you can't use it since the table load would
fail due to it still containing failed paths. Now a re-load of a
multipath table can include failed devices and when those devices become
active again they can be used instantly.
The device list code in dm.c isn't a straight copy/paste from the code in
dm-table.c, but it's very close (aside from some variable renames). One
subtle difference is that find_table_device for the tables_devices list
will only match devices with the same name and mode. This is because we
don't want to upgrade a device's mode in the active table when an
inactive table is loaded.
Access to the mapped_device structure's tables_devices list requires a
mutex (tables_devices_lock), so that tables cannot be created and
destroyed concurrently.
Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
'queue_io' is set so that IO is queued while paths are being
initialized. Clear queue_io in __choose_pgpath if there are no valid
paths, since there are obviously no paths that can be initialized.
Otherwise IOs to the device will back up.
Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Since DM core uses bio_clone_fast() for both bio-based and request-based
DM devices there is no need for DM's bioset to have a bvec mempool.
With this patch, on arch with 4KB page for example, memory usage will be
reduced by 64KB for each bio-based DM device and 1MB for each
request-based DM device.
For example, when you create 10,000 bio-based DM devices and 1,000
request-based DM devices, memory usage of biovec under no load is:
# grep biovec /proc/slabinfo
biovec-256 418068 418068 4096 ...
biovec-128 0 0 2048 ...
biovec-64 0 0 1024 ...
biovec-16 0 0 256 ...
With this patch series applied, the usage becomes:
# grep biovec /proc/slabinfo
biovec-256 116 116 4096 ...
biovec-128 0 0 2048 ...
biovec-64 0 0 1024 ...
biovec-16 0 0 256 ...
So 4096 * (418068 - 116) = 1.6GB of memory is saved in this example.
Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
alloc_tio() uses bio_alloc_bioset() to allocate a clone-bio for a bio.
alloc_tio() takes the number of bvecs to allocate for the clone-bio.
However, with v3.14's immutable biovec changes DM now uses
__bio_clone_fast() and no longer needs to allocate bvecs.
In practice, the 'nr_iovecs' passed to alloc_tio() is always effectively
0. __clone_and_map_simple_bio() looked like it was passing non-zero
nr_iovecs, but its value was always within the range of inline bvecs and
no allocation actually happened. If allocation happened, the BUG_ON() in
__bio_clone_fast() would've triggered.
Remove the nr_iovecs parameter from alloc_tio() to prevent possible
future bio_alloc_bioset() mis-use of a new bioset interface that will no
longer allow bvecs to be allocated.
Also fix extra whitespace before the __bio_clone_fast() call in
__clone_and_map_simple_bio().
Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Clear QUEUE_FLAG_ADD_RANDOM in all block drivers that set
QUEUE_FLAG_NONROT.
Historically, all block devices have automatically made entropy
contributions. But as previously stated in commit e2e1a148 ("block: add
sysfs knob for turning off disk entropy contributions"):
- On SSD disks, the completion times aren't as random as they
are for rotational drives. So it's questionable whether they
should contribute to the random pool in the first place.
- Calling add_disk_randomness() has a lot of overhead.
There are more reliable sources for randomness than non-rotational block
devices. From a security perspective it is better to err on the side of
caution than to allow entropy contributions from unreliable "random"
sources.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
It has come to my attention (thanks Martin) that 'discard_zeroes_data'
is only a hint. Some devices in some cases don't do what it
says on the label.
The use of DISCARD in RAID5 depends on reads from discarded regions
being predictably zero. If a write to a previously discarded region
performs a read-modify-write cycle it assumes that the parity block
was consistent with the data blocks. If all were zero, this would
be the case. If some are and some aren't this would not be the case.
This could lead to data corruption after a device failure when
data needs to be reconstructed from the parity.
As we cannot trust 'discard_zeroes_data', ignore it by default
and so disallow DISCARD on all raid4/5/6 arrays.
As many devices are trustworthy, and as there are benefits to using
DISCARD, add a module parameter to over-ride this caution and cause
DISCARD to work if discard_zeroes_data is set.
If a site want to enable DISCARD on some arrays but not on others they
should select DISCARD support at the filesystem level, and set the
raid456 module parameter.
raid456.devices_handle_discard_safely=Y
As this is a data-safety issue, I believe this patch is suitable for
-stable.
DISCARD support for RAID456 was added in 3.7
Cc: Shaohua Li <shli@kernel.org>
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>
Cc: Mike Snitzer <snitzer@redhat.com>
Cc: Heinz Mauelshagen <heinzm@redhat.com>
Cc: stable@vger.kernel.org (3.7+)
Acked-by: Martin K. Petersen <martin.petersen@oracle.com>
Acked-by: Mike Snitzer <snitzer@redhat.com>
Fixes: 620125f2bf
Signed-off-by: NeilBrown <neilb@suse.de>
particularly, but not only, fixing new "resync" code.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.22 (GNU/Linux)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=gMsu
-----END PGP SIGNATURE-----
Merge tag 'md/3.17-more-fixes' of git://git.neil.brown.name/md
Pull bugfixes for md/raid1 from Neil Brown:
"It is amazing how much easier it is to find bugs when you know one is
there. Two bug reports resulted in finding 7 bugs!
All are tagged for -stable. Those that can't cause (rare) data
corruption, cause lockups.
Particularly, but not only, fixing new "resync" code"
* tag 'md/3.17-more-fixes' of git://git.neil.brown.name/md:
md/raid1: fix_read_error should act on all non-faulty devices.
md/raid1: count resync requests in nr_pending.
md/raid1: update next_resync under resync_lock.
md/raid1: Don't use next_resync to determine how far resync has progressed
md/raid1: make sure resync waits for conflicting writes to complete.
md/raid1: clean up request counts properly in close_sync()
md/raid1: be more cautious where we read-balance during resync.
md/raid1: intialise start_next_window for READ case to avoid hang
If a devices is being recovered it is not InSync and is not Faulty.
If a read error is experienced on that device, fix_read_error()
will be called, but it ignores non-InSync devices. So it will
neither fix the error nor fail the device.
It is incorrect that fix_read_error() ignores non-InSync devices.
It should only ignore Faulty devices. So fix it.
This became a bug when we allowed reading from a device that was being
recovered. It is suitable for any subsequent -stable kernel.
Fixes: da8840a747
Cc: stable@vger.kernel.org (v3.5+)
Reported-by: Alexander Lyakas <alex.bolshoy@gmail.com>
Tested-by: Alexander Lyakas <alex.bolshoy@gmail.com>
Signed-off-by: NeilBrown <neilb@suse.de>
Both normal IO and resync IO can be retried with reschedule_retry()
and so be counted into ->nr_queued, but only normal IO gets counted in
->nr_pending.
Before the recent improvement to RAID1 resync there could only
possibly have been one or the other on the queue. When handling a
read failure it could only be normal IO. So when handle_read_error()
called freeze_array() the fact that freeze_array only compares
->nr_queued against ->nr_pending was safe.
But now that these two types can interleave, we can have both normal
and resync IO requests queued, so we need to count them both in
nr_pending.
This error can lead to freeze_array() hanging if there is a read
error, so it is suitable for -stable.
Fixes: 79ef3a8aa1
cc: stable@vger.kernel.org (v3.13+)
Reported-by: Brassow Jonathan <jbrassow@redhat.com>
Signed-off-by: NeilBrown <neilb@suse.de>
raise_barrier() uses next_resync as part of its calculations, so it
really should be updated first, instead of afterwards.
next_resync is always used under resync_lock so update it under
resync lock to, just before it is used. That is safest.
This could cause normal IO and resync IO to interact badly so
it suitable for -stable.
Fixes: 79ef3a8aa1
cc: stable@vger.kernel.org (v3.13+)
Signed-off-by: NeilBrown <neilb@suse.de>
next_resync is (approximately) the location for the next resync request.
However it does *not* reliably determine the earliest location
at which resync might be happening.
This is because resync requests can complete out of order, and
we only limit the number of current requests, not the distance
from the earliest pending request to the latest.
mddev->curr_resync_completed is a reliable indicator of the earliest
position at which resync could be happening. It is updated less
frequently, but is actually reliable which is more important.
So use it to determine if a write request is before the region
being resynced and so safe from conflict.
This error can allow resync IO to interfere with normal IO which
could lead to data corruption. Hence: stable.
Fixes: 79ef3a8aa1
cc: stable@vger.kernel.org (v3.13+)
Signed-off-by: NeilBrown <neilb@suse.de>
The resync/recovery process for raid1 was recently changed
so that writes could happen in parallel with resync providing
they were in different regions of the device.
There is a problem though: While a write request will always
wait for conflicting resync to complete, a resync request
will *not* always wait for conflicting writes to complete.
Two changes are needed to fix this:
1/ raise_barrier (which waits until it is safe to do resync)
must wait until current_window_requests is zero
2/ wait_battier (which waits at the start of a new write request)
must update current_window_requests if the request could
possible conflict with a concurrent resync.
As concurrent writes and resync can lead to data loss,
this patch is suitable for -stable.
Fixes: 79ef3a8aa1
Cc: stable@vger.kernel.org (v3.13+)
Cc: majianpeng <majianpeng@gmail.com>
Signed-off-by: NeilBrown <neilb@suse.de>
If there are outstanding writes when close_sync is called,
the change to ->start_next_window might cause them to
decrement the wrong counter when they complete. Fix this
by merging the two counters into the one that will be decremented.
Having an incorrect value in a counter can cause raise_barrier()
to hangs, so this is suitable for -stable.
Fixes: 79ef3a8aa1
cc: stable@vger.kernel.org (v3.13+)
Signed-off-by: NeilBrown <neilb@suse.de>
commit 79ef3a8aa1 made
it possible for reads to happen concurrently with resync.
This means that we need to be more careful where read_balancing
is allowed during resync - we can no longer be sure that any
resync that has already started will definitely finish.
So keep read_balancing to before recovery_cp, which is conservative
but safe.
This bug makes it possible to read from a device that doesn't
have up-to-date data, so it can cause data corruption.
So it is suitable for any kernel since 3.11.
Fixes: 79ef3a8aa1
cc: stable@vger.kernel.org (v3.13+)
Signed-off-by: NeilBrown <neilb@suse.de>
r1_bio->start_next_window is not initialised in the READ
case, so allow_barrier may incorrectly decrement
conf->current_window_requests
which can cause raise_barrier() to block forever.
Fixes: 79ef3a8aa1
cc: stable@vger.kernel.org (v3.13+)
Reported-by: Brassow Jonathan <jbrassow@redhat.com>
Signed-off-by: NeilBrown <neilb@suse.de>
When a writeback or a promotion of a block is completed, the cell of
that block is removed from the prison, the block is marked as clean, and
the clear_dirty() callback of the cache policy is called.
Unfortunately, performing those actions in this order allows an incoming
new write bio for that block to come in before clearing the dirty status
is completed and therefore possibly causing one of these two scenarios:
Scenario A:
Thread 1 Thread 2
cell_defer() .
- cell removed from prison .
- detained bios queued .
. incoming write bio
. remapped to cache
. set_dirty() called,
. but block already dirty
. => it does nothing
clear_dirty() .
- block marked clean .
- policy clear_dirty() called .
Result: Block is marked clean even though it is actually dirty. No
writeback will occur.
Scenario B:
Thread 1 Thread 2
cell_defer() .
- cell removed from prison .
- detained bios queued .
clear_dirty() .
- block marked clean .
. incoming write bio
. remapped to cache
. set_dirty() called
. - block marked dirty
. - policy set_dirty() called
- policy clear_dirty() called .
Result: Block is properly marked as dirty, but policy thinks it is clean
and therefore never asks us to writeback it.
This case is visible in "dmsetup status" dirty block count (which
normally decreases to 0 on a quiet device).
Fix these issues by calling clear_dirty() before calling cell_defer().
Incoming bios for that block will then be detained in the cell and
released only after clear_dirty() has completed, so the race will not
occur.
Found by inspecting the code after noticing spurious dirty counts
(scenario B).
Signed-off-by: Anssi Hannula <anssi.hannula@iki.fi>
Acked-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org
The DM crypt target accesses memory beyond allocated space resulting in
a crash on 32 bit x86 systems.
This bug is very old (it dates back to 2.6.25 commit 3a7f6c990a "dm
crypt: use async crypto"). However, this bug was masked by the fact
that kmalloc rounds the size up to the next power of two. This bug
wasn't exposed until 3.17-rc1 commit 298a9fa08a ("dm crypt: use per-bio
data"). By switching to using per-bio data there was no longer any
padding beyond the end of a dm-crypt allocated memory block.
To minimize allocation overhead dm-crypt puts several structures into one
block allocated with kmalloc. The block holds struct ablkcipher_request,
cipher-specific scratch pad (crypto_ablkcipher_reqsize(any_tfm(cc))),
struct dm_crypt_request and an initialization vector.
The variable dmreq_start is set to offset of struct dm_crypt_request
within this memory block. dm-crypt allocates the block with this size:
cc->dmreq_start + sizeof(struct dm_crypt_request) + cc->iv_size.
When accessing the initialization vector, dm-crypt uses the function
iv_of_dmreq, which performs this calculation: ALIGN((unsigned long)(dmreq
+ 1), crypto_ablkcipher_alignmask(any_tfm(cc)) + 1).
dm-crypt allocated "cc->iv_size" bytes beyond the end of dm_crypt_request
structure. However, when dm-crypt accesses the initialization vector, it
takes a pointer to the end of dm_crypt_request, aligns it, and then uses
it as the initialization vector. If the end of dm_crypt_request is not
aligned on a crypto_ablkcipher_alignmask(any_tfm(cc)) boundary the
alignment causes the initialization vector to point beyond the allocated
space.
Fix this bug by calculating the variable iv_size_padding and adding it
to the allocated size.
Also correct the alignment of dm_crypt_request. struct dm_crypt_request
is specific to dm-crypt (it isn't used by the crypto subsystem at all),
so it is aligned on __alignof__(struct dm_crypt_request).
Also align per_bio_data_size on ARCH_KMALLOC_MINALIGN, so that it is
aligned as if the block was allocated with kmalloc.
Reported-by: Krzysztof Kolasa <kkolasa@winsoft.pl>
Tested-by: Milan Broz <gmazyland@gmail.com>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Most places which allocate an r10_bio zero the ->state, some don't.
As the r10_bio comes from a mempool, and the allocation function uses
kzalloc it is often zero anyway. But sometimes it isn't and it is
best to be safe.
I only noticed this because of the bug fixed by an earlier patch
where the r10_bios allocated for a reshape were left around to
be used by a subsequent resync. In that case the R10BIO_IsReshape
flag caused problems.
Signed-off-by: NeilBrown <neilb@suse.de>
When a raid10 commences a resync/recovery/reshape it allocates
some buffer space.
When a resync/recovery completes the buffer space is freed. But not
when the reshape completes.
This can result in a small memory leak.
There is a subtle side-effect of this bug. When a RAID10 is reshaped
to a larger array (more devices), the reshape is immediately followed
by a "resync" of the new space. This "resync" will use the buffer
space which was allocated for "reshape". This can cause problems
including a "BUG" in the SCSI layer. So this is suitable for -stable.
Cc: stable@vger.kernel.org (v3.5+)
Fixes: 3ea7daa5d7
Signed-off-by: NeilBrown <neilb@suse.de>
raid10 reshape clears unwanted bits from a bio->bi_flags using
a method which, while clumsy, worked until 3.10 when BIO_OWNS_VEC
was added.
Since then it clears that bit but shouldn't. This results in a
memory leak.
So change to used the approved method of clearing unwanted bits.
As this causes a memory leak which can consume all of memory
the fix is suitable for -stable.
Fixes: a38352e0ac
Cc: stable@vger.kernel.org (v3.10+)
Reported-by: mdraid.pkoch@dfgh.net (Peter Koch)
Signed-off-by: NeilBrown <neilb@suse.de>
During recovery of a double-degraded RAID6 it is possible for
some blocks not to be recovered properly, leading to corruption.
If a write happens to one block in a stripe that would be written to a
missing device, and at the same time that stripe is recovering data
to the other missing device, then that recovered data may not be written.
This patch skips, in the double-degraded case, an optimisation that is
only safe for single-degraded arrays.
Bug was introduced in 2.6.32 and fix is suitable for any kernel since
then. In an older kernel with separate handle_stripe5() and
handle_stripe6() functions the patch must change handle_stripe6().
Cc: stable@vger.kernel.org (2.6.32+)
Fixes: 6c0069c0ae
Cc: Yuri Tikhonov <yur@emcraft.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Reported-by: "Manibalan P" <pmanibalan@amiindia.co.in>
Tested-by: "Manibalan P" <pmanibalan@amiindia.co.in>
Resolves: https://bugzilla.redhat.com/show_bug.cgi?id=1090423
Signed-off-by: NeilBrown <neilb@suse.de>
Acked-by: Dan Williams <dan.j.williams@intel.com>
If a stripe in a raid6 array received a write to each data block while
the array is degraded, and if any of these writes to a missing device
are not page-aligned, then a live-lock happens.
In this case the P and Q blocks need to be read so that the part of
the missing block which is *not* being updated by the write can be
constructed. Due to a logic error, these blocks are not loaded, so
the update cannot proceed and the stripe is 'handled' repeatedly in an
infinite loop.
This bug is unlikely as most writes are page aligned. However as it
can lead to a livelock it is suitable for -stable. It was introduced
in 3.16.
Cc: stable@vger.kernel.org (v3.16)
Fixed: 67f455486d
Signed-off-by: NeilBrown <neilb@suse.de>
allow thin snapshots to be larger than the external origin.
. Add support for quickly loading a repetitive pattern into the
dm-switch target.
. Use per-bio data in the dm-crypt target instead of always using a
mempool for each allocation. Required switching to kmalloc alignment
for the bio slab.
. Fix DM core to properly stack the QUEUE_FLAG_NO_SG_MERGE flag
. Fix the dm-cache and dm-thin targets' export of the minimum_io_size to
match the data block size -- this fixes an issue where mkfs.xfs would
improperly infer raid striping was in place on the underlying storage.
. Small cleanups in dm-io, dm-mpath and dm-cache
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iQEcBAABAgAGBQJT64yEAAoJEMUj8QotnQNatjQH/2mqm8EtPuZas70zHVDzjMlE
ZyV8xgHpU0MBmiBi+JhUBv9iKX4sVa+C25559WkKtxRVMnZmI1WDry4TagiqrhnK
9o/uvdWigJMR+uwahwe4UErEtKscOQJD30a8taN/suJ6Z2C7XJJRUZPsyL4a3Vov
w+UIi7aYDEGp/2VQ8mvTTxjdF5x5km4wKsjBTs03uTrrkEJ+bIUndl2I1X+X4bsw
kiWYOQwmcnD8GwYkSrthJYLsS3Hjur/J/My7KZwXc00ANLOexqHdKfRDwH8b36+m
olKXv3swCd8vi+jJYEYzuW9213ACsSEGP7h8NFVZ/+2FeDsSzB/C7zjW9okIUIw=
=y/3r
-----END PGP SIGNATURE-----
Merge tag 'dm-3.17-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm
Pull device mapper changes from Mike Snitzer:
- Allow the thin target to paired with any size external origin; also
allow thin snapshots to be larger than the external origin.
- Add support for quickly loading a repetitive pattern into the
dm-switch target.
- Use per-bio data in the dm-crypt target instead of always using a
mempool for each allocation. Required switching to kmalloc alignment
for the bio slab.
- Fix DM core to properly stack the QUEUE_FLAG_NO_SG_MERGE flag
- Fix the dm-cache and dm-thin targets' export of the minimum_io_size
to match the data block size -- this fixes an issue where mkfs.xfs
would improperly infer raid striping was in place on the underlying
storage.
- Small cleanups in dm-io, dm-mpath and dm-cache
* tag 'dm-3.17-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
dm table: propagate QUEUE_FLAG_NO_SG_MERGE
dm switch: efficiently support repetitive patterns
dm switch: factor out switch_region_table_read
dm cache: set minimum_io_size to cache's data block size
dm thin: set minimum_io_size to pool's data block size
dm crypt: use per-bio data
block: use kmalloc alignment for bio slab
dm table: make dm_table_supports_discards static
dm cache metadata: use dm-space-map-metadata.h defined size limits
dm cache: fail migrations in the do_worker error path
dm cache: simplify deferred set reference count increments
dm thin: relax external origin size constraints
dm thin: switch to an atomic_t for tracking pending new block preparations
dm mpath: eliminate pg_ready() wrapper
dm io: simplify dec_count and sync_io
Pull block driver changes from Jens Axboe:
"Nothing out of the ordinary here, this pull request contains:
- A big round of fixes for bcache from Kent Overstreet, Slava Pestov,
and Surbhi Palande. No new features, just a lot of fixes.
- The usual round of drbd updates from Andreas Gruenbacher, Lars
Ellenberg, and Philipp Reisner.
- virtio_blk was converted to blk-mq back in 3.13, but now Ming Lei
has taken it one step further and added support for actually using
more than one queue.
- Addition of an explicit SG_FLAG_Q_AT_HEAD for block/bsg, to
compliment the the default behavior of adding to the tail of the
queue. From Douglas Gilbert"
* 'for-3.17/drivers' of git://git.kernel.dk/linux-block: (86 commits)
bcache: Drop unneeded blk_sync_queue() calls
bcache: add mutex lock for bch_is_open
bcache: Correct printing of btree_gc_max_duration_ms
bcache: try to set b->parent properly
bcache: fix memory corruption in init error path
bcache: fix crash with incomplete cache set
bcache: Fix more early shutdown bugs
bcache: fix use-after-free in btree_gc_coalesce()
bcache: Fix an infinite loop in journal replay
bcache: fix crash in bcache_btree_node_alloc_fail tracepoint
bcache: bcache_write tracepoint was crashing
bcache: fix typo in bch_bkey_equal_header
bcache: Allocate bounce buffers with GFP_NOWAIT
bcache: Make sure to pass GFP_WAIT to mempool_alloc()
bcache: fix uninterruptible sleep in writeback thread
bcache: wait for buckets when allocating new btree root
bcache: fix crash on shutdown in passthrough mode
bcache: fix lockdep warnings on shutdown
bcache allocator: send discards with correct size
bcache: Fix to remove the rcu_sched stalls.
...
Most interesting is that md devices (major == 9) with
minor numbers of 512 or more will no longer be created
simply by opening a block device file. They can only
be created by writing to
/sys/module/md_mod/parameters/new_array
The 'auto-create-on-open' semantic is cumbersome and we
need to start moving away from it.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.22 (GNU/Linux)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=v8Er
-----END PGP SIGNATURE-----
Merge tag 'md/3.17' of git://neil.brown.name/md
Pull md updates from Neil Brown:
"Most interesting is that md devices (major == 9) with minor numbers of
512 or more will no longer be created simply by opening a block device
file. They can only be created by writing to
/sys/module/md_mod/parameters/new_array
The 'auto-create-on-open' semantic is cumbersome and we need to start
moving away from it"
* tag 'md/3.17' of git://neil.brown.name/md:
md: don't allow bitmap file to be added to raid0/linear.
md/raid0: check for bitmap compatability when changing raid levels.
md: Recovery speed is wrong
md: disable probing for md devices 512 and over.
md/raid1,raid10: always abort recover on write error.
Commit 05f1dd5 ("block: add queue flag for disabling SG merging")
introduced a new queue flag: QUEUE_FLAG_NO_SG_MERGE. This gets set by
default in blk_mq_init_queue for mq-enabled devices. The effect of
the flag is to bypass the SG segment merging. Instead, the
bio->bi_vcnt is used as the number of hardware segments.
With a device mapper target on top of a device with
QUEUE_FLAG_NO_SG_MERGE set, we can end up sending down more segments
than a driver is prepared to handle. I ran into this when backporting
the virtio_blk mq support. It triggerred this BUG_ON, in
virtio_queue_rq:
BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems);
The queue's max is set here:
blk_queue_max_segments(q, vblk->sg_elems-2);
Basically, what happens is that a bio is built up for the dm device
(which does not have the QUEUE_FLAG_NO_SG_MERGE flag set) using
bio_add_page. That path will call into __blk_recalc_rq_segments, so
what you end up with is bi_phys_segments being much smaller than bi_vcnt
(and bi_vcnt grows beyond the maximum sg elements). Then, when the bio
is submitted, it gets cloned. When the cloned bio is submitted, it will
end up in blk_recount_segments, here:
if (test_bit(QUEUE_FLAG_NO_SG_MERGE, &q->queue_flags))
bio->bi_phys_segments = bio->bi_vcnt;
and now we've set bio->bi_phys_segments to a number that is beyond what
was registered as queue_max_segments by the driver.
The right way to fix this is to propagate the queue flag up the stack.
The rules for propagating the flag are simple:
- if the flag is set for any underlying device, it must be set for the
upper device
- consequently, if the flag is not set for any underlying device, it
should not be set for the upper device.
Signed-off-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org # 3.16+
An array can only accept a bitmap if it will call bitmap_daemon_work
periodically, which means it needs a thread running.
If there is no thread, don't allow a bitmap to be added.
Signed-off-by: NeilBrown <neilb@suse.de>
When we calculate the speed of recovery, the numerator that contains
the recovery done sectors. It's need to subtract the sectors which
don't finish recovery.
Signed-off-by: Xiao Ni <xni@redhat.com>
Signed-off-by: NeilBrown <neilb@suse.de>
Pull scheduler updates from Ingo Molnar:
- Move the nohz kick code out of the scheduler tick to a dedicated IPI,
from Frederic Weisbecker.
This necessiated quite some background infrastructure rework,
including:
* Clean up some irq-work internals
* Implement remote irq-work
* Implement nohz kick on top of remote irq-work
* Move full dynticks timer enqueue notification to new kick
* Move multi-task notification to new kick
* Remove unecessary barriers on multi-task notification
- Remove proliferation of wait_on_bit() action functions and allow
wait_on_bit_action() functions to support a timeout. (Neil Brown)
- Another round of sched/numa improvements, cleanups and fixes. (Rik
van Riel)
- Implement fast idling of CPUs when the system is partially loaded,
for better scalability. (Tim Chen)
- Restructure and fix the CPU hotplug handling code that may leave
cfs_rq and rt_rq's throttled when tasks are migrated away from a dead
cpu. (Kirill Tkhai)
- Robustify the sched topology setup code. (Peterz Zijlstra)
- Improve sched_feat() handling wrt. static_keys (Jason Baron)
- Misc fixes.
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (37 commits)
sched/fair: Fix 'make xmldocs' warning caused by missing description
sched: Use macro for magic number of -1 for setparam
sched: Robustify topology setup
sched: Fix sched_setparam() policy == -1 logic
sched: Allow wait_on_bit_action() functions to support a timeout
sched: Remove proliferation of wait_on_bit() action functions
sched/numa: Revert "Use effective_load() to balance NUMA loads"
sched: Fix static_key race with sched_feat()
sched: Remove extra static_key*() function indirection
sched/rt: Fix replenish_dl_entity() comments to match the current upstream code
sched: Transform resched_task() into resched_curr()
sched/deadline: Kill task_struct->pi_top_task
sched: Rework check_for_tasks()
sched/rt: Enqueue just unthrottled rt_rq back on the stack in __disable_runtime()
sched/fair: Disable runtime_enabled on dying rq
sched/numa: Change scan period code to match intent
sched/numa: Rework best node setting in task_numa_migrate()
sched/numa: Examine a task move when examining a task swap
sched/numa: Simplify task_numa_compare()
sched/numa: Use effective_load() to balance NUMA loads
...
this is needed for the queue/block device we created (it's done by
blk_cleanup_queue() which we do call) - but calling it for the block devices we
only opened is pointless.
Change-Id: I53dfded14ed15b9581d10ca8399d5e1b3abbf9f2
Since bch_is_open will iterate linked list bch_cache_sets and
uncached_devices, it needs bch_register_lock.
Signed-off-by: Jianjian Huo <samuel.huo@gmail.com>
time_stats::btree_gc_max_duration_mc is not bit shifted by 8
Fixes BUG #138
Change-Id: I44fc6e1d0579674016acc533f1a546b080e5371a
Signed-off-by: Surbhi Palande <sap@daterainc.com>
If register_cache_set() failed, we would touch ca->set after
it had already been freed. Also, fix an assertion to catch
this.
Change-Id: I748e5f5b223e2d9b2602075dec2f997cced2394d
If we goto out_nocoalesce after we free new_nodes[0], we end up freeing
new_nodes[0] again. This was generating a lockdep warning. The fix is
to set new_nodes[0] to NULL, since the out_nocoalesce path safely
ignores NULL entries in the new_nodes array.
This regression was introduced in 2d7f9531.
Change-Id: I76564d7257800583214376b4bacf236cda90c89c
When running with multiple cache devices, if one of the devices has a completely
empty journal but we'd already found some journal entries on a previosu device
we'd go into an infinite loop.
Change-Id: I1dcdc0d738192746de28f40e8b08825b0dea5e2b
Signed-off-by: Kent Overstreet <kmo@daterainc.com>
There's no point in blocking on these allocations, since our fallback paths will
probably go faster than blocking.
Change-Id: I733ca202c25cb36bde02607a0a60552229a4241c
this was very wrong - mempool_alloc() only guarantees success with GFP_WAIT.
bcache uses GFP_NOWAIT in various other places where we have a fallback,
circuits must've gotten crossed when writing this code or something.
Signed-off-by: Kent Overstreet <kmo@daterainc.com>
There were two issues here:
- writeback thread did not start until the device first became dirty
- writeback thread used uninterruptible sleep once running
Without this patch I see kernel warnings printed and a load average of
1.52 after booting my test VM. With this patch the warnings are gone and
the load average is near 0.00 as expected.
Signed-off-by: Kent Overstreet <kmo@daterainc.com>
Tested:
- sometimes bcache_tier test would hang on startup with a failure
to allocate the btree root -- no longer seeing this
Signed-off-by: Kent Overstreet <kmo@daterainc.com>
while loop was executing infinitely.
This fix ends the while loop gracefully.
Signed-off-by: Surbhi Palande <sap@daterainc.com>
Signed-off-by: Kent Overstreet <kmo@daterainc.com>
After detaching a backing device from a cache set, a bit wasn't getting
reset meaning the second detach wouldn't work correctly.
Signed-off-by: Kent Overstreet <kmo@daterainc.com>
Add support for quickly loading a repetitive pattern into the
dm-switch target.
In the "set_regions_mappings" message, the user may now use "Rn,m" as
one of the arguments. "n" and "m" are hexadecimal numbers. The "Rn,m"
argument repeats the last "n" arguments in the following "m" slots.
For example:
dmsetup message switch 0 set_region_mappings 1000:1 :2 R2,10
is equivalent to
dmsetup message switch 0 set_region_mappings 1000:1 :2 :1 :2 :1 :2 :1 :2 \
:1 :2 :1 :2 :1 :2 :1 :2 :1 :2
Requested-by: Jay Wang <jwang@nimblestorage.com>
Tested-by: Jay Wang <jwang@nimblestorage.com>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Move code that reads the table to a switch_region_table_read.
It will be needed for the next commit. No functional change.
Tested-by: Jay Wang <jwang@nimblestorage.com>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Before, if the block layer's limit stacking didn't establish an
optimal_io_size that was compatible with the cache's data block size
we'd set optimal_io_size to the data block size and minimum_io_size to 0
(which the block layer adjusts to be physical_block_size).
Update cache_io_hints() to set both minimum_io_size and optimal_io_size
to the cache's data block size. This fixes an issue where mkfs.xfs
would create more XFS Allocation Groups on cache volumes than on a
normal linear LV of comparable size.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Before, if the block layer's limit stacking didn't establish an
optimal_io_size that was compatible with the thin-pool's data block size
we'd set optimal_io_size to the data block size and minimum_io_size to 0
(which the block layer adjusts to be physical_block_size).
Update pool_io_hints() to set both minimum_io_size and optimal_io_size
to the thin-pool's data block size. This fixes an issue reported where
mkfs.xfs would create more XFS Allocation Groups on thinp volumes than
on a normal linear LV of comparable size, see:
https://bugzilla.redhat.com/show_bug.cgi?id=1003227
Reported-by: Chris Murphy <lists@colorremedies.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Change dm-crypt so that it uses auxiliary data allocated with the bio.
Dm-crypt requires two allocations per request - struct dm_crypt_io and
struct ablkcipher_request (with other data appended to it). It
previously only used mempool allocations.
Some requests may require more dm_crypt_ios and ablkcipher_requests,
however most requests need just one of each of these two structures to
complete.
This patch changes it so that the first dm_crypt_io and ablkcipher_request
are allocated with the bio (using target per_bio_data_size option). If
the request needs additional values, they are allocated from the mempool.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
The function dm_table_supports_discards is only called from
dm-table.c:dm_table_set_restrictions(). So move it above
dm_table_set_restrictions and make it static.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Commit 7d48935e cleaned up the persistent-data's space-map-metadata
limits by elevating them to dm-space-map-metadata.h. Update
dm-cache-metadata to use these same limits.
The calculation for DM_CACHE_METADATA_MAX_SECTORS didn't account for the
sizeof the disk_bitmap_header. So the supported maximum metadata size
is a bit smaller (reduced from 33423360 to 33292800 sectors).
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Acked-by: Joe Thornber <ejt@redhat.com>
Factor out inc_and_issue and inc_ds helpers to simplify deferred set
reference count increments. Also cleanup cache_map to consistently call
cell_defer and inc_ds when the bio is DM_MAPIO_REMAPPED.
No functional change.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Track the size of any external origin. Previously the external origin's
size had to be a multiple of the thin-pool's block size, that is no
longer a requirement. In addition, snapshots that are larger than the
external origin are now supported.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Previously we used separate boolean values to track quiescing and
copying actions. By switching to an atomic_t we can support blocks that
need a partial copy and partial zero.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
pg_ready() is not comprehensive in its logic and only serves to
obfuscate code. Replace pg_ready() with the appropriate logic in
multipath_map().
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Remove the io struct off the stack in sync_io() and allocate it from
the mempool like is done in async_io().
dec_count() now always calls a callback function and always frees the io
struct back to the mempool (so sync_io and async_io share this pattern).
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
nr_dirty is updated without locking, causing it to drift so that it is
non-zero (either a small positive integer, or a very large one when an
underflow occurs) even when there are no actual dirty blocks. This was
due to a race between the workqueue and map function accessing nr_dirty
in parallel without proper protection.
People were seeing under runs due to a race on increment/decrement of
nr_dirty, see: https://lkml.org/lkml/2014/6/3/648
Fix this by using an atomic_t for nr_dirty.
Reported-by: roma1390@gmail.com
Signed-off-by: Anssi Hannula <anssi.hannula@iki.fi>
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org
1d3d4437ea ("vmscan: per-node deferred work") added a flags field to
struct shrinker assuming that all shrinkers were zero filled. The dm
bufio shrinker is not zero filled, which leaves arbitrary kmalloc() data
in flags. So far the only defined flags bit is SHRINKER_NUMA_AWARE.
But there are proposed patches which add other bits to shrinker.flags
(e.g. memcg awareness).
Rather than simply initializing the shrinker, this patch uses kzalloc()
when allocating the dm_bufio_client to ensure that the embedded shrinker
and any other similar structures are zeroed.
This fixes theoretical over aggressive shrinking of dm bufio objects.
If the uninitialized dm_bufio_client.shrinker.flags contains
SHRINKER_NUMA_AWARE then shrink_slab() would call the dm shrinker for
each numa node rather than just once. This has been broken since 3.12.
Signed-off-by: Greg Thelen <gthelen@google.com>
Acked-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org # v3.12+
The way md devices are traditionally created in the kernel
is simply to open the device with the desired major/minor number.
This can be problematic as some support tools, notably udev and
programs run by udev, can open a device just to see what is there, and
find that it has created something. It is easy for a race to cause
udev to open an md device just after it was destroy, causing it to
suddenly re-appear.
For some time we have had an alternate way to create md devices
echo md_somename > /sys/modules/md_mod/paramaters/new_array
This will always use a minor number of 512 or higher, which mdadm
normally avoids.
Using this makes the creation-by-opening unnecessary, but does
not disable it, so it is still there to cause problems.
This patch disable probing for devices with a major of 9 (MD_MAJOR)
and a minor of 512 and up. This devices created by writing to
new_array cannot be re-created by opening the node in /dev.
Signed-off-by: NeilBrown <neilb@suse.de>
Currently we don't abort recovery on a write error if the write error
to the recovering device was triggerd by normal IO (as opposed to
recovery IO).
This means that for one bitmap region, the recovery might write to the
recovering device for a few sectors, then not bother for subsequent
sectors (as it never writes to failed devices). In this case
the bitmap bit will be cleared, but it really shouldn't.
The result is that if the recovering device fails and is then re-added
(after fixing whatever hardware problem triggerred the failure),
the second recovery won't redo the region it was in the middle of,
so some of the device will not be recovered properly.
If we abort the recovery, the region being processes will be cancelled
(bit not cleared) and the whole region will be retried.
As the bug can result in data corruption the patch is suitable for
-stable. For kernels prior to 3.11 there is a conflict in raid10.c
which will require care.
Original-from: jiao hui <jiaohui@bwstor.com.cn>
Reported-and-tested-by: jiao hui <jiaohui@bwstor.com.cn>
Signed-off-by: NeilBrown <neilb@suse.de>
Cc: stable@vger.kernel.org
device's block size.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iQEcBAABAgAGBQJTyIuDAAoJEMUj8QotnQNaKOcH/iC5X88HYBke3myjj8fkQelw
05b1slxnKDINTE+L2eBzuyqzcNm8jLq02ltf9x8VuTxdzioR353PVWHfEmVkUYhJ
DSnPPtLrfF+FsoABWEcjYcHyguUusgpZ9su94yctDErJcscgs9+7hJJhNKSCf+cW
VmthtG4vXOdGP2Fl9IGQIzbGgwVWfT1QZN7yhFX2WGwgpBP4u4a9b4kY+sVQjfuz
lcqy0/MTrsI63TATaGeiILbWh86BNxaoeCe+gBXMk6uvPBaJkGCo9o4OZjbe0d0f
8wnedBiew8OlEZJAVEjxm+eNMukjeAcRE4gz/qTyaYlxwOqXQJCbsGyraWxpnXM=
=ZDsD
-----END PGP SIGNATURE-----
Merge tag 'dm-3.16-fixes-2' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm
Pull device mapper fixes from Mike Snitzer:
"Fix the dm-thinp and dm-cache targets to disallow changing the data
device's block size"
* tag 'dm-3.16-fixes-2' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
dm cache metadata: do not allow the data block size to change
dm thin metadata: do not allow the data block size to change
The current "wait_on_bit" interface requires an 'action'
function to be provided which does the actual waiting.
There are over 20 such functions, many of them identical.
Most cases can be satisfied by one of just two functions, one
which uses io_schedule() and one which just uses schedule().
So:
Rename wait_on_bit and wait_on_bit_lock to
wait_on_bit_action and wait_on_bit_lock_action
to make it explicit that they need an action function.
Introduce new wait_on_bit{,_lock} and wait_on_bit{,_lock}_io
which are *not* given an action function but implicitly use
a standard one.
The decision to error-out if a signal is pending is now made
based on the 'mode' argument rather than being encoded in the action
function.
All instances of the old wait_on_bit and wait_on_bit_lock which
can use the new version have been changed accordingly and their
action functions have been discarded.
wait_on_bit{_lock} does not return any specific error code in the
event of a signal so the caller must check for non-zero and
interpolate their own error code as appropriate.
The wait_on_bit() call in __fscache_wait_on_invalidate() was
ambiguous as it specified TASK_UNINTERRUPTIBLE but used
fscache_wait_bit_interruptible as an action function.
David Howells confirms this should be uniformly
"uninterruptible"
The main remaining user of wait_on_bit{,_lock}_action is NFS
which needs to use a freezer-aware schedule() call.
A comment in fs/gfs2/glock.c notes that having multiple 'action'
functions is useful as they display differently in the 'wchan'
field of 'ps'. (and /proc/$PID/wchan).
As the new bit_wait{,_io} functions are tagged "__sched", they
will not show up at all, but something higher in the stack. So
the distinction will still be visible, only with different
function names (gds2_glock_wait versus gfs2_glock_dq_wait in the
gfs2/glock.c case).
Since first version of this patch (against 3.15) two new action
functions appeared, on in NFS and one in CIFS. CIFS also now
uses an action function that makes the same freezer aware
schedule call as NFS.
Signed-off-by: NeilBrown <neilb@suse.de>
Acked-by: David Howells <dhowells@redhat.com> (fscache, keys)
Acked-by: Steven Whitehouse <swhiteho@redhat.com> (gfs2)
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Steve French <sfrench@samba.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20140707051603.28027.72349.stgit@notabene.brown
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The block size for the dm-cache's data device must remained fixed for
the life of the cache. Disallow any attempt to change the cache's data
block size.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Acked-by: Joe Thornber <ejt@redhat.com>
Cc: stable@vger.kernel.org
The block size for the thin-pool's data device must remained fixed for
the life of the thin-pool. Disallow any attempt to change the
thin-pool's data block size.
It should be noted that attempting to change the data block size via
thin-pool table reload will be ignored as a side-effect of the thin-pool
handover that the thin-pool target does during thin-pool table reload.
Here is an example outcome of attempting to load a thin-pool table that
reduced the thin-pool's data block size from 1024K to 512K.
Before:
kernel: device-mapper: thin: 253:4: growing the data device from 204800 to 409600 blocks
After:
kernel: device-mapper: thin metadata: changing the data block size (from 2048 to 1024) is not supported
kernel: device-mapper: table: 253:4: thin-pool: Error creating metadata object
kernel: device-mapper: ioctl: error adding target to table
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Acked-by: Joe Thornber <ejt@redhat.com>
Cc: stable@vger.kernel.org
multipath_busy. This impacted cable-pull testing and also the ability
to boot with IPR SCSI on a POWER8 box.
. Fix possible deadlock with deferred device removal by using a new
dedicated workqueue rather than using the system workqueue.
. Fix NULL pointer crash due to race condition in dm-io's wake up code
for sync_io by using a completion.
. Update dm-crypt and dm-zero author name following legal name change;
this is important to Jana so I didn't see any reason to hold it back.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iQEcBAABAgAGBQJTv+hvAAoJEMUj8QotnQNawwMH/2yQ7AE3dh44jGr1fp0UEP8e
Vd7HWtUJAm4+lYkPH7AjLCw3YBwWh/ajLXAwMpPBI878o5sgoWTfnq0hbecqoWkt
5EugETiZ20C3K/llNFpw9xdtlObFwI21WUGqmu8ygYvfSvdbg6THPT5o8BdtEvnb
MDBrrrpBpUwMCGw3v7jIoYrKZbWmp46iy5KwVqBbXnD3shpOU8KpasyIOrqlrqjJ
z7BzfprN6ut1zaVs83N4iPMPnSPrIloUisGpPn1r74qRYUv/AXQgiv09WPA3keTN
erRGFU9Mr0I4MGOLTuqHyCVO0t4tze1pL8jwEk29GUkXXcr9Is4p9I307Cm7WvE=
=pBlO
-----END PGP SIGNATURE-----
Merge tag 'dm-3.16-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm
Pull device mapper fixes from Mike Snitzer:
- Fix DM multipath IO hang regression from 3.15 due to logic bug in
multipath_busy. This impacted cable-pull testing and also the
ability to boot with IPR SCSI on a POWER8 box.
- Fix possible deadlock with deferred device removal by using a new
dedicated workqueue rather than using the system workqueue.
- Fix NULL pointer crash due to race condition in dm-io's wake up code
for sync_io by using a completion.
- Update dm-crypt and dm-zero author name following legal name change;
this is important to Jana so I didn't see any reason to hold it back.
* tag 'dm-3.16-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
dm mpath: fix IO hang due to logic bug in multipath_busy
dm io: fix a race condition in the wake up code for sync_io
dm crypt, dm zero: update author name following legal name change
dm: allocate a special workqueue for deferred device removal
Commit e80991773 ("dm mpath: push back requests instead of queueing")
modified multipath_busy() to return true if !pg_ready(). pg_ready()
checks the current state of the multipath device and may return false
even if a new IO is needed to change the state.
Bart Van Assche reported that he had multipath IO lockup when he was
performing cable pull tests. Analysis showed that the multipath
device had a single path group with both paths active, but that the
path group itself was not active. During the multipath device state
transitions 'queue_io' got set but nothing could clear it. Clearing
'queue_io' only happens in __choose_pgpath(), but it won't be called
if multipath_busy() returns true due to pg_ready() returning false
when 'queue_io' is set.
As such the !pg_ready() check in multipath_busy() is wrong because new
IO will not be sent to multipath target and the multipath state change
won't happen. That results in multipath IO lockup.
The intent of multipath_busy() is to avoid unnecessary cycles of
dequeue + request_fn + requeue if it is known that the multipath
device will requeue.
Such "busy" situations would be:
- path group is being activated
- there is no path and the multipath is setup to requeue if no path
Fix multipath_busy() to return "busy" early only for these specific
situations.
Reported-by: Bart Van Assche <bvanassche@acm.org>
Tested-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org # v3.15
There's a race condition between the atomic_dec_and_test(&io->count)
in dec_count() and the waking of the sync_io() thread. If the thread
is spuriously woken immediately after the decrement it may exit,
making the on stack io struct invalid, yet the dec_count could still
be using it.
Fix this race by using a completion in sync_io() and dec_count().
Reported-by: Minfei Huang <huangminfei@ucloud.cn>
Signed-off-by: Joe Thornber <thornber@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Acked-by: Mikulas Patocka <mpatocka@redhat.com>
Cc: stable@vger.kernel.org
The commit 2c140a246d ("dm: allow remove to be deferred") introduced a
deferred removal feature for the device mapper. When this feature is
used (by passing a flag DM_DEFERRED_REMOVE to DM_DEV_REMOVE_CMD ioctl)
and the user tries to remove a device that is currently in use, the
device will be removed automatically in the future when the last user
closes it.
Device mapper used the system workqueue to perform deferred removals.
However, some targets (dm-raid1, dm-mpath, dm-stripe) flush work items
scheduled for the system workqueue from their destructor. If the
destructor itself is called from the system workqueue during deferred
removal, it introduces a possible deadlock - the workqueue tries to flush
itself.
Fix this possible deadlock by introducing a new workqueue for deferred
removals. We allocate just one workqueue for all dm targets. The
ability of dm targets to process IOs isn't dependent on deferred removal
of unused targets, so a deadlock due to shared workqueue isn't possible.
Also, cleanup local_init() to eliminate potential for returning success
on failure.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org # 3.13+
When we write to a degraded array which has a bitmap, we
make sure the relevant bit in the bitmap remains set when
the write completes (so a 're-add' can quickly rebuilt a
temporarily-missing device).
If, immediately after such a write starts, we incorporate a spare,
commence recovery, and skip over the region where the write is
happening (because the 'needs recovery' flag isn't set yet),
then that write will not get to the new device.
Once the recovery finishes the new device will be trusted, but will
have incorrect data, leading to possible corruption.
We cannot set the 'needs recovery' flag when we start the write as we
do not know easily if the write will be "degraded" or not. That
depends on details of the particular raid level and particular write
request.
This patch fixes a corruption issue of long standing and so it
suitable for any -stable kernel. It applied correctly to 3.0 at
least and will minor editing to earlier kernels.
Reported-by: Bill <billstuff2001@sbcglobal.net>
Tested-by: Bill <billstuff2001@sbcglobal.net>
Cc: stable@vger.kernel.org
Link: http://lkml.kernel.org/r/53A518BB.60709@sbcglobal.net
Signed-off-by: NeilBrown <neilb@suse.de>
If an array has a bitmap, the when we set the "has bitmap" flag we
incorrectly clear the "is clean" flag.
"is clean" isn't really important when a bitmap is present, but it is
best to get it right anyway.
Reported-by: George Duffield <forumscollective@gmail.com>
Link: http://lkml.kernel.org/CAG__1a4MRV6gJL38XLAurtoSiD3rLBTmWpcS5HYvPpSfPR88UQ@mail.gmail.com
Fixes: 36fa30636f (v2.6.14)
Signed-off-by: NeilBrown <neilb@suse.de>
to only process a portion of a bio, the remainder being sent in the
next bio. This enables the old dm snapshot-origin target to only
split write bios on chunk boundaries, read bios are now sent to the
origin device unchanged.
. Add DM core support for disabling WRITE SAME if the underlying SCSI
layer disables it due to command failure.
. Reduce lock contention in DM's bio-prison.
. A few small cleanups and fixes to dm-thin and dm-era.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iQEcBAABAgAGBQJTmavIAAoJEMUj8QotnQNay/EIAJI6lEFlQK3gG830+Yaw1m2U
7mnnX/Rd/N6RnccyhmFqk7Xu0REM7gJEgWicTQjR58La2DKFi072N0mwgHgHfB8f
1oOvUKN5Nb/a1CmRcVzSO0sbYcJn9I1r+k0buqfFHivU68wuedG+MrVya3YzOjvC
63MQiu4+3icDprcToxn+etz75FhrFps5QAsS0cH6t1VZqFCGIzxqgUKgY8zGo1CH
P9hkYpJhhJe2aDh4vlFvpFYVFXt9zPoR+MkqXFW6Dn9GbR36gGaldTwnyhapla4N
XYHDEdETcTqm2srOM5wW+jD0p+Id9/Lmd5Ld5J2zyARCYn/EG/SDCbiaVqOxEnc=
=tv1B
-----END PGP SIGNATURE-----
Merge tag 'dm-3.16-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm
Pull device mapper updates from Mike Snitzer:
"This pull request is later than I'd have liked because I was waiting
for some performance data to help finally justify sending the
long-standing dm-crypt cpu scalability improvements upstream.
Unfortunately we came up short, so those dm-crypt changes will
continue to wait, but it seems we're not far off.
. Add dm_accept_partial_bio interface to DM core to allow DM targets
to only process a portion of a bio, the remainder being sent in the
next bio. This enables the old dm snapshot-origin target to only
split write bios on chunk boundaries, read bios are now sent to the
origin device unchanged.
. Add DM core support for disabling WRITE SAME if the underlying SCSI
layer disables it due to command failure.
. Reduce lock contention in DM's bio-prison.
. A few small cleanups and fixes to dm-thin and dm-era"
* tag 'dm-3.16-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
dm thin: update discard_granularity to reflect the thin-pool blocksize
dm bio prison: implement per bucket locking in the dm_bio_prison hash table
dm: remove symbol export for dm_set_device_limits
dm: disable WRITE SAME if it fails
dm era: check for a non-NULL metadata object before closing it
dm thin: return ENOSPC instead of EIO when error_if_no_space enabled
dm thin: cleanup noflush_work to use a proper completion
dm snapshot: do not split read bios sent to snapshot-origin target
dm snapshot: allocate a per-target structure for snapshot-origin target
dm: introduce dm_accept_partial_bio
dm: change sector_count member in clone_info from sector_t to unsigned
DM thinp already checks whether the discard_granularity of the data
device is a factor of the thin-pool block size. But when using the
dm-thin-pool's discard passdown support, DM thinp was not selecting the
max of the underlying data device's discard_granularity and the
thin-pool's block size.
Update set_discard_limits() to set discard_granularity to the max of
these values. This enables blkdev_issue_discard() to properly align the
discards that are sent to the DM thin device on a full block boundary.
As such each discard will now cover an entire DM thin-pool block and the
block will be reclaimed.
Reported-by: Zdenek Kabelac <zkabelac@redhat.com>
Signed-off-by: Lukas Czerner <lczerner@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org
Split the single per bio-prison lock by using per bucket locking. Per
bucket locking benefits both dm-thin and dm-cache targets by reducing
bio-prison lock contention.
Signed-off-by: Heinz Mauelshagen <heinzm@redhat.com>
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Mostly performance improvements with a few corner-case bug fixes.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.22 (GNU/Linux)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=MaM/
-----END PGP SIGNATURE-----
Merge tag 'md/3.16' of git://neil.brown.name/md
Pull md updates from Neil Brown:
"Assorted md fixes for 3.16
Mostly performance improvements with a few corner-case bug fixes"
* tag 'md/3.16' of git://neil.brown.name/md:
raid5: speedup sync_request processing
md/raid5: deadlock between retry_aligned_read with barrier io
raid5: add an option to avoid copy data from bio to stripe cache
md/bitmap: remove confusing code from filemap_get_page.
raid5: avoid release list until last reference of the stripe
md: md_clear_badblocks should return an error code on failure.
md/raid56: Don't perform reads to support writes until stripe is ready.
md: refuse to change shape of array if it is active but read-only
The raid5 sync_request() processing calls handle_stripe() within the context of
the resync-thread. The resync-thread issues the first set of read requests
and this adds execution latency and slows down the scheduling of the next
sync_request().
The current rebuild/resync speed of raid5 is not much faster than what
rotational HDDs can sustain.
Testing the following patch on a 6-drive array, I can increase the rebuild
speed from 100 MB/s to 175 MB/s.
The sync_request() now just sets STRIPE_HANDLE and releases the stripe. This
creates some more parallelism between the resync-thread and raid5 kernel daemon.
Signed-off-by: Eivind Sarto <esarto@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>
Now that 3.15 is released, this merges the 'next' branch into 'master',
bringing us to the normal situation where my 'master' branch is the
merge window.
* accumulated work in next: (6809 commits)
ufs: sb mutex merge + mutex_destroy
powerpc: update comments for generic idle conversion
cris: update comments for generic idle conversion
idle: remove cpu_idle() forward declarations
nbd: zero from and len fields in NBD_CMD_DISCONNECT.
mm: convert some level-less printks to pr_*
MAINTAINERS: adi-buildroot-devel is moderated
MAINTAINERS: add linux-api for review of API/ABI changes
mm/kmemleak-test.c: use pr_fmt for logging
fs/dlm/debug_fs.c: replace seq_printf by seq_puts
fs/dlm/lockspace.c: convert simple_str to kstr
fs/dlm/config.c: convert simple_str to kstr
mm: mark remap_file_pages() syscall as deprecated
mm: memcontrol: remove unnecessary memcg argument from soft limit functions
mm: memcontrol: clean up memcg zoneinfo lookup
mm/memblock.c: call kmemleak directly from memblock_(alloc|free)
mm/mempool.c: update the kmemleak stack trace for mempool allocations
lib/radix-tree.c: update the kmemleak stack trace for radix tree allocations
mm: introduce kmemleak_update_trace()
mm/kmemleak.c: use %u to print ->checksum
...
A chunk aligned read increases counter active_aligned_reads and
decreases it after sub-device handle it successfully. But when a read
error occurs, the read redispatched by raid5d, and the
active_aligned_reads will not be decreased until we can grab a stripe
head in retry_aligned_read. Now suppose, a barrier io comes, set
conf->quiesce to 2, and wait until both active_stripes and
active_aligned_reads are zero. The retried chunk aligned read gets
stuck at get_active_stripe waiting until conf->quiesce becomes 0.
Retry_aligned_read and barrier io are waiting each other now.
One possible solution is that we ignore conf->quiesce, let the retried
aligned read finish. I reproduced this deadlock and test this patch on
centos6.0
Signed-off-by: NeilBrown <neilb@suse.de>
There is no need for code other than DM core to use dm_set_device_limits
so remove its EXPORT_SYMBOL_GPL. Also, cleanup a couple whitespace nits.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Add DM core support for disabling WRITE SAME on first failure to both
request-based and bio-based targets. The need to disable WRITE SAME
stems from SCSI enabling it by default but then disabling it when it
fails. When SCSI does this it returns "permanent target failure, do
not retry" using -EREMOTEIO. Update DM core to only disable WRITE SAME
on failure if the returned error is -EREMOTEIO.
Commit f84cb8a4 ("dm mpath: disable WRITE SAME if it fails")
implemented multipath specific disabling of WRITE SAME if it fails.
However, as that commit detailed, the multipath-only solution doesn't go
far enough if bio-based DM targets are stacked ontop of the
request-based dm-multipath target (as is commonly done using dm-linear
to support partitions on multipath devices, via kpartx).
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Acked-by: Martin K. Petersen <martin.petersen@oracle.com>
Tested-by: Alex Chen <alex.chen@huawei.com>
era_ctr() may call era_destroy() before era->md is initialized so
era_destory() must only close the metadata object if it is not NULL.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Naohiro Aota <naota@elisp.net>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org # 3.15+
Update the DM thin provisioning target's allocation failure error to be
consistent with commit a9d6ceb8 ("[SCSI] return ENOSPC on thin
provisioning failure").
The DM thin target now returns -ENOSPC rather than -EIO when
block allocation fails due to the pool being out of data space (and
the 'error_if_no_space' thin-pool feature is enabled).
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Acked-By: Joe Thornber <ejt@redhat.com>
Factor out a pool_work interface that noflush_work makes use of to wait
for and complete work items (in terms of a proper completion struct).
Allows discontinuing the use of a custom completion in terms of atomic_t
and wait_event.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Change the snapshot-origin target so that only write bios are split on
chunk boundary. Read bios are passed unchanged to the underlying
device, so they don't have to be split.
Later, we could change the target so that it accepts a larger write bio
if it spans an area that is completely covered by snapshot exceptions.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Allocate a per-target dm_origin structure. This is a prerequisite for
the next commit ("dm snapshot: do not split read bios sent to
snapshot-origin target") which adds a new member to this structure.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
The function dm_accept_partial_bio allows the target to specify how many
sectors of the current bio it will process. If the target only wants to
accept part of the bio, it calls dm_accept_partial_bio and the DM core
sends the rest of the data in next bio.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
It is impossible to create bios with 2^23 or more sectors (the size is
stored as a 32-bit byte count in the bio). So we convert some sector_t
values to unsigned integers.
This is needed for the next commit ("dm: introduce
dm_accept_partial_bio") that replaces integer value arguments with
pointers, so the size of the integer must match.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
If a raid5/6 reshape is restarted (After stopping and re-assembling
the array) and the array is marked read-only (or read-auto), then
the reshape will appear to complete immediately, without actually
moving anything around. This can result in corruption.
There are two patches which do much the same thing in different places.
They are separate because one is an older bug and so can be applied to
more -stable kernels.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.22 (GNU/Linux)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=cTEe
-----END PGP SIGNATURE-----
Merge tag 'md/3.15-fixes' of git://neil.brown.name/md
Pull two md bugfixes from Neil Brown:
"Two md bugfixes for possible corruption when restarting reshape
If a raid5/6 reshape is restarted (After stopping and re-assembling
the array) and the array is marked read-only (or read-auto), then the
reshape will appear to complete immediately, without actually moving
anything around. This can result in corruption.
There are two patches which do much the same thing in different
places. They are separate because one is an older bug and so can be
applied to more -stable kernels"
* tag 'md/3.15-fixes' of git://neil.brown.name/md:
md: always set MD_RECOVERY_INTR when interrupting a reshape thread.
md: always set MD_RECOVERY_INTR when aborting a reshape or other "resync".
Pull block core updates from Jens Axboe:
"It's a big(ish) round this time, lots of development effort has gone
into blk-mq in the last 3 months. Generally we're heading to where
3.16 will be a feature complete and performant blk-mq. scsi-mq is
progressing nicely and will hopefully be in 3.17. A nvme port is in
progress, and the Micron pci-e flash driver, mtip32xx, is converted
and will be sent in with the driver pull request for 3.16.
This pull request contains:
- Lots of prep and support patches for scsi-mq have been integrated.
All from Christoph.
- API and code cleanups for blk-mq from Christoph.
- Lots of good corner case and error handling cleanup fixes for
blk-mq from Ming Lei.
- A flew of blk-mq updates from me:
* Provide strict mappings so that the driver can rely on the CPU
to queue mapping. This enables optimizations in the driver.
* Provided a bitmap tagging instead of percpu_ida, which never
really worked well for blk-mq. percpu_ida relies on the fact
that we have a lot more tags available than we really need, it
fails miserably for cases where we exhaust (or are close to
exhausting) the tag space.
* Provide sane support for shared tag maps, as utilized by scsi-mq
* Various fixes for IO timeouts.
* API cleanups, and lots of perf tweaks and optimizations.
- Remove 'buffer' from struct request. This is ancient code, from
when requests were always virtually mapped. Kill it, to reclaim
some space in struct request. From me.
- Remove 'magic' from blk_plug. Since we store these on the stack
and since we've never caught any actual bugs with this, lets just
get rid of it. From me.
- Only call part_in_flight() once for IO completion, as includes two
atomic reads. Hopefully we'll get a better implementation soon, as
the part IO stats are now one of the more expensive parts of doing
IO on blk-mq. From me.
- File migration of block code from {mm,fs}/ to block/. This
includes bio.c, bio-integrity.c, bounce.c, and ioprio.c. From me,
from a discussion on lkml.
That should describe the meat of the pull request. Also has various
little fixes and cleanups from Dave Jones, Shaohua Li, Duan Jiong,
Fengguang Wu, Fabian Frederick, Randy Dunlap, Robert Elliott, and Sam
Bradshaw"
* 'for-3.16/core' of git://git.kernel.dk/linux-block: (100 commits)
blk-mq: push IPI or local end_io decision to __blk_mq_complete_request()
blk-mq: remember to start timeout handler for direct queue
block: ensure that the timer is always added
blk-mq: blk_mq_unregister_hctx() can be static
blk-mq: make the sysfs mq/ layout reflect current mappings
blk-mq: blk_mq_tag_to_rq should handle flush request
block: remove dead code in scsi_ioctl:blk_verify_command
blk-mq: request initialization optimizations
block: add queue flag for disabling SG merging
block: remove 'magic' from struct blk_plug
blk-mq: remove alloc_hctx and free_hctx methods
blk-mq: add file comments and update copyright notices
blk-mq: remove blk_mq_alloc_request_pinned
blk-mq: do not use blk_mq_alloc_request_pinned in blk_mq_map_request
blk-mq: remove blk_mq_wait_for_tags
blk-mq: initialize request in __blk_mq_alloc_request
blk-mq: merge blk_mq_alloc_reserved_request into blk_mq_alloc_request
blk-mq: add helper to insert requests from irq context
blk-mq: remove stale comment for blk_mq_complete_request()
blk-mq: allow non-softirq completions
...
because dm-cache cannot yet handle discards that span cache blocks.
Really fix a dm-mpath LOCKDEP warning that was introduced in -rc1.
Add a 'no_space_timeout' control to dm-thinp to restore the ability to
queue IO indefinitely when no data space is available. This fixes a
change in behavior that was introduced in -rc6 where the timeout
couldn't be disabled.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iQEcBAABAgAGBQJTh9QAAAoJEMUj8QotnQNaNpYH/j07FeH8YlxXRcFzDi7xRVtx
luK5b9fLLlmPwW2eKSrvpI8Le4jwDvLwBmpEvN9/wyPiRDSUnYIyYdoV7RJXX2LT
wqXatObb84fwQBJ6/q8o2YMzU5ODa5XT6KGEZyD4cHdAZ9FZSwfgqhslyrBJDkSN
JBFfkXu066qw8cuYA6KFv4DwBf5eHAt5AjV/QPGd5zGXwETHLZ4ypgpwYHAGbdXa
MgfHetwtEnJYvVQex/e+9xC5IDc4/BEAhZq4n3YmEJjNq8EbX15udHmCX7S2M5pT
+9tNjUMz4j9BhoC9F8ntRz0pxWZtJK9hGojO4xoXqOCOHgp1xLQd/tHrFZS0v8E=
=u5Xd
-----END PGP SIGNATURE-----
Merge tag 'dm-3.15-fixes-3' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm
Pull device-mapper fixes from Mike Snitzer:
"A dm-cache stable fix to split discards on cache block boundaries
because dm-cache cannot yet handle discards that span cache blocks.
Really fix a dm-mpath LOCKDEP warning that was introduced in -rc1.
Add a 'no_space_timeout' control to dm-thinp to restore the ability to
queue IO indefinitely when no data space is available. This fixes a
change in behavior that was introduced in -rc6 where the timeout
couldn't be disabled"
* tag 'dm-3.15-fixes-3' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
dm mpath: really fix lockdep warning
dm cache: always split discards on cache block boundaries
dm thin: add 'no_space_timeout' dm-thin-pool module param
The stripe cache has two goals:
1. cache data, so next time if data can be found in stripe cache, disk access
can be avoided.
2. stable data. data is copied from bio to stripe cache and calculated parity.
data written to disk is from stripe cache, so if upper layer changes bio data,
data written to disk isn't impacted.
In my environment, I can guarantee 2 will not happen. And BDI_CAP_STABLE_WRITES
can guarantee 2 too. For 1, it's not common too. block plug mechanism will
dispatch a bunch of sequentail small requests together. And since I'm using
SSD, I'm using small chunk size. It's rare case stripe cache is really useful.
So I'd like to avoid the copy from bio to stripe cache and it's very helpful
for performance. In my 1M randwrite tests, avoid the copy can increase the
performance more than 30%.
Of course, this shouldn't be enabled by default. It's reported enabling
BDI_CAP_STABLE_WRITES can harm some workloads before, so I added an option to
control it.
Neilb:
changed BUG_ON to WARN_ON
Removed some assignments from raid5_build_block which are now not needed.
Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>
file_page_index(store, 0) is *always* 0.
This is because the bitmap sb, at 256 bytes, is *always* less than
one page.
So subtracting it has no effect and the code should be removed.
Reported-by: Goldwyn Rodrigues <rgoldwyn@suse.de>
Signed-off-by: NeilBrown <neilb@suse.de>
The (lockless) release_list reduces lock contention, but there is excessive
queueing and dequeuing of stripes on this list. A stripe will currently be
queued on the release_list with a stripe reference count > 1. This can cause
the raid5 kernel thread(s) to dequeue the stripe and decrement the refcount
without doing any other useful processing of the stripe. The are two cases
when the stripe can be put on the release_list multiple times before it is
actually handled by the kernel thread(s).
1) make_request() activates the stripe processing in 4k increments. When a
write request is large enough to span multiple chunks of a stripe_head, the
first 4k chunk adds the stripe to the plug list. The next 4k chunk that is
processed for the same stripe puts the stripe on the release_list with a
refcount=2. This can cause the kernel thread to process and decrement the
stripe before the stripe us unplugged, which again will put it back on the
release_list.
2) Whenever IO is scheduled on a stripe (pre-read and/or write), the stripe
refcount is set to the number of active IO (for each chunk). The stripe is
released as each IO complete, and can be queued and dequeued multiple times
on the release_list, until its refcount finally reached zero.
This simple patch will ensure a stripe is only queued on the release_list when
its refcount=1 and is ready to be handled by the kernel thread(s). I added some
instrumentation to raid5 and counted the number of times striped were queued on
the release_list for a variety of write IO sizes. Without this patch the number
of times stripes got queued on the release_list was 100-500% higher than with
the patch. The excess queuing will increase with the IO size. The patch also
improved throughput by 5-10%.
Signed-off-by: Eivind Sarto <esarto@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>
Julia Lawall and coccinelle report that md_clear_badblocks always
returns 0, despite appearing to have an error path.
The error path really should return an error code. ENOSPC is
reasonably appropriate.
Reported-by: Julia Lawall <Julia.Lawall@lip6.fr>
Signed-off-by: NeilBrown <neilb@suse.de>
If it is found that we need to pre-read some blocks before a write
can succeed, we normally set STRIPE_DELAYED and don't actually perform
the read until STRIPE_PREREAD_ACTIVE subsequently gets set.
However for a degraded RAID6 we currently perform the reads as soon
as we see that a write is pending. This significantly hurts
throughput.
So:
- when handle_stripe_dirtying find a block that it wants on a device
that is failed, set STRIPE_DELAY, instead of doing nothing, and
- when fetch_block detects that a read might be required to satisfy a
write, only perform the read if STRIPE_PREREAD_ACTIVE is set,
and if we would actually need to read something to complete the write.
This also helps RAID5, though less often as RAID5 supports a
read-modify-write cycle. For RAID5 the read is performed too early
only if the write is not a full 4K aligned write (i.e. no an
R5_OVERWRITE).
Also clean up a couple of horrible bits of formatting.
Reported-by: Patrik Horník <patrik@dsl.sk>
Signed-off-by: NeilBrown <neilb@suse.de>
read-only arrays should not be changed. This includes changing
the level, layout, size, or number of devices.
So reject those changes for readonly arrays.
Signed-off-by: NeilBrown <neilb@suse.de>
Commit 8313b8e57f
md: fix problem when adding device to read-only array with bitmap.
added a called to md_reap_sync_thread() which cause a reshape thread
to be interrupted (in particular, it could cause md_thread() to never even
call md_do_sync()).
However it didn't set MD_RECOVERY_INTR so ->finish_reshape() would not
know that the reshape didn't complete.
This only happens when mddev->ro is set and normally reshape threads
don't run in that situation. But raid5 and raid10 can start a reshape
thread during "run" is the array is in the middle of a reshape.
They do this even if ->ro is set.
So it is best to set MD_RECOVERY_INTR before abortingg the
sync thread, just in case.
Though it rare for this to trigger a problem it can cause data corruption
because the reshape isn't finished properly.
So it is suitable for any stable which the offending commit was applied to.
(3.2 or later)
Fixes: 8313b8e57f
Cc: stable@vger.kernel.org (3.2+)
Signed-off-by: NeilBrown <neilb@suse.de>
If mddev->ro is set, md_to_sync will (correctly) abort.
However in that case MD_RECOVERY_INTR isn't set.
If a RESHAPE had been requested, then ->finish_reshape() will be
called and it will think the reshape was successful even though
nothing happened.
Normally a resync will not be requested if ->ro is set, but if an
array is stopped while a reshape is on-going, then when the array is
started, the reshape will be restarted. If the array is also set
read-only at this point, the reshape will instantly appear to success,
resulting in data corruption.
Consequently, this patch is suitable for any -stable kernel.
Cc: stable@vger.kernel.org (any)
Signed-off-by: NeilBrown <neilb@suse.de>
lockdep complains about a circular locking. And indeed, we need to
release the lock before calling dm_table_run_md_queue_async().
As such, commit 4cdd2ad ("dm mpath: fix lock order inconsistency in
multipath_ioctl") must also be reverted in addition to fixing the
lock order in the other dm_table_run_md_queue_async() callers.
Reported-by: Bart van Assche <bvanassche@acm.org>
Tested-by: Bart van Assche <bvanassche@acm.org>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
The DM cache target cannot cope with discards that span multiple cache
blocks, so each discard bio that spans more than one cache block must
get split by the DM core.
Signed-off-by: Heinz Mauelshagen <heinzm@redhat.com>
Acked-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org # v3.9+
data to a mempool allocation (which offers allocation with cpu locality,
and there is no inter-cpu communication on slab allocation).
A couple dm-thinp stable fixes to address "out-of-data-space" issues.
A dm-multipath fix for a LOCKDEP warning introduced in 3.15-rc1.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iQEcBAABAgAGBQJTdiI7AAoJEMUj8QotnQNa1fMIAOSGppH4U/VuT1+UMDyabUba
eXsK8xBUTIDSBuTJ+ljkE5fyvXpn/wvA+b1hTKLhzVkUZ1pCY4pIw1pwpVcw89Bb
BhktFWRYvcv/MAARDHiMGW5yc6xP319Qm04XN3xbMHx71gxGRwpzb191LSO5S2VR
0rjXvZZt7WPJe/QPOFUrqyoP7t59LH9hu2/OH/Ic9o5/D0WxbqPEP6X8iJyIs32u
lNvIQ5r5f3xNzt0VDvEq3sxR3qYhQvLPDMdp0YR67c87fKfsKQj4pkvXltXhY5bM
wBHFE+NBl6MPzTXNCT9i+p360GXE7B/lY9boochAyE/UEztRq1+oqJOa/dDaBCo=
=0vk2
-----END PGP SIGNATURE-----
Merge tag 'dm-3.15-fixes-2' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm
Pull device mapper fixes from Mike Snitzer:
"A dm-crypt fix for a cpu hotplug crash that switches from using
per-cpu data to a mempool allocation (which offers allocation with cpu
locality, and there is no inter-cpu communication on slab allocation).
A couple dm-thinp stable fixes to address "out-of-data-space" issues.
A dm-multipath fix for a LOCKDEP warning introduced in 3.15-rc1"
* tag 'dm-3.15-fixes-2' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
dm mpath: fix lock order inconsistency in multipath_ioctl
dm thin: add timeout to stop out-of-data-space mode holding IO forever
dm thin: allow metadata commit if pool is in PM_OUT_OF_DATA_SPACE mode
dm crypt: fix cpu hotplug crash by removing per-cpu structure
Commit 85ad643b ("dm thin: add timeout to stop out-of-data-space mode
holding IO forever") introduced a fixed 60 second timeout. Users may
want to either disable or modify this timeout.
Allow the out-of-data-space timeout to be configured using the
'no_space_timeout' dm-thin-pool module param. Setting it to 0 will
disable the timeout, resulting in IO being queued until more data space
is added to the thin-pool.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org # 3.14+
Commit 3e9f1be1b4 ("dm mpath: remove process_queued_ios()") did not
consistently take the multipath device's spinlock (m->lock) before
calling dm_table_run_md_queue_async() -- which takes the q->queue_lock.
Found with code inspection using hint from reported lockdep warning.
Reported-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
If the pool runs out of data space, dm-thin can be configured to
either error IOs that would trigger provisioning, or hold those IOs
until the pool is resized. Unfortunately, holding IOs until the pool is
resized can result in a cascade of tasks hitting the hung_task_timeout,
which may render the system unavailable.
Add a fixed timeout so IOs can only be held for a maximum of 60 seconds.
If LVM is going to resize a thin-pool that is out of data space it needs
to be prompt about it.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org # 3.14+
Commit 3e1a0699 ("dm thin: fix out of data space handling") introduced
a regression in the metadata commit() method by returning an error if
the pool is in PM_OUT_OF_DATA_SPACE mode. This oversight caused a thin
device to return errors even if the default queue_if_no_space ENOSPC
handling mode is used.
Fix commit() to only fail if pool is in PM_READ_ONLY or PM_FAIL mode.
Reported-by: qindehua@163.com
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org # 3.14+
The DM crypt target used per-cpu structures to hold pointers to a
ablkcipher_request structure. The code assumed that the work item keeps
executing on a single CPU, so it didn't use synchronization when
accessing this structure.
If a CPU is disabled by writing 0 to /sys/devices/system/cpu/cpu*/online,
the work item could be moved to another CPU. This causes dm-crypt
crashes, like the following, because the code starts using an incorrect
ablkcipher_request:
smpboot: CPU 7 is now offline
BUG: unable to handle kernel NULL pointer dereference at 0000000000000130
IP: [<ffffffffa1862b3d>] crypt_convert+0x12d/0x3c0 [dm_crypt]
...
Call Trace:
[<ffffffffa1864415>] ? kcryptd_crypt+0x305/0x470 [dm_crypt]
[<ffffffff81062060>] ? finish_task_switch+0x40/0xc0
[<ffffffff81052a28>] ? process_one_work+0x168/0x470
[<ffffffff8105366b>] ? worker_thread+0x10b/0x390
[<ffffffff81053560>] ? manage_workers.isra.26+0x290/0x290
[<ffffffff81058d9f>] ? kthread+0xaf/0xc0
[<ffffffff81058cf0>] ? kthread_create_on_node+0x120/0x120
[<ffffffff813464ac>] ? ret_from_fork+0x7c/0xb0
[<ffffffff81058cf0>] ? kthread_create_on_node+0x120/0x120
Fix this bug by removing the per-cpu definition. The structure
ablkcipher_request is accessed via a pointer from convert_context.
Consequently, if the work item is rescheduled to a different CPU, the
thread still uses the same ablkcipher_request.
This change may undermine performance improvements intended by commit
c0297721 ("dm crypt: scale to multiple cpus") on select hardware. In
practice no performance difference was observed on recent hardware. But
regardless, correctness is more important than performance.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org
Both tagged for -stable.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.22 (GNU/Linux)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=9QhO
-----END PGP SIGNATURE-----
Merge tag 'md/3.15-fixes' of git://neil.brown.name/md
Pull md bugfixes from Neil Brown:
"Two bugfixes for md in 3.15
Both tagged for -stable"
* tag 'md/3.15-fixes' of git://neil.brown.name/md:
md: avoid possible spinning md thread at shutdown.
md/raid10: call wait_barrier() for each request submitted.
If an md array with externally managed metadata (e.g. DDF or IMSM)
is in use, then we should not set safemode==2 at shutdown because:
1/ this is ineffective: user-space need to be involved in any 'safemode' handling,
2/ The safemode management code doesn't cope with safemode==2 on external metadata
and md_check_recover enters an infinite loop.
Even at shutdown, an infinite-looping process can be problematic, so this
could cause shutdown to hang.
Cc: stable@vger.kernel.org (any kernel)
Signed-off-by: NeilBrown <neilb@suse.de>
wait_barrier() includes a counter, so we must call it precisely once
(unless balanced by allow_barrier()) for each request submitted.
Since
commit 20d0189b10
block: Introduce new bio_split()
in 3.14-rc1, we don't call it for the extra requests generated when
we need to split a bio.
When this happens the counter goes negative, any resync/recovery will
never start, and "mdadm --stop" will hang.
Reported-by: Chris Murphy <lists@colorremedies.com>
Fixes: 20d0189b10
Cc: stable@vger.kernel.org (3.14+)
Cc: Kent Overstreet <kmo@daterainc.com>
Signed-off-by: NeilBrown <neilb@suse.de>
A dm-verity fix for an immutable biovec regression that affects 3.14+.
A dm-cache fix to properly quiesce when using writethrough mode (3.14+).
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iQEcBAABAgAGBQJTY+6+AAoJEMUj8QotnQNaeC4H/35S9GZL8SVPEDS5nbQ9YdZ9
co7wAYIGswOInX9u8nq0TqcNtBMhxwwdRX9ScPxHVUTT+/lM/c7axHiMqVjZrMme
SVmmAXMp2uUMAnK4BGIQs8jjeyxBCHUF/gyfC3OC+RF72Z1bDkG/xXyKsljBSzMe
RP0iFvvvA1Sm7XzBJRuhZLIdJGkXFAy0ooEBICQOoudg6iDvDKCtiU+owB/x4bBh
xi9b1MY2VjkobWES6fyW/atolCEpgwU4xhsLl3w534P9oFvCkLEp4GTxdFWBhepl
K3usGr0t1QhmHy1hKw++WGsAkMRHocf8nIBqxxdDNWpZvOif2z+weLYbOn+TXTM=
=1Yvj
-----END PGP SIGNATURE-----
Merge tag 'dm-3.15-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm
Pull device mapper fixes from Mike Snitzer:
"A few dm-thinp fixes for changes merged in 3.15-rc1.
A dm-verity fix for an immutable biovec regression that affects 3.14+.
A dm-cache fix to properly quiesce when using writethrough mode (3.14+)"
* tag 'dm-3.15-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
dm cache: fix writethrough mode quiescing in cache_map
dm thin: use INIT_WORK_ONSTACK in noflush_work to avoid ODEBUG warning
dm verity: fix biovecs hash calculation regression
dm thin: fix rcu_read_lock being held in code that can sleep
dm thin: irqsave must always be used with the pool->lock spinlock
Commit 2ee57d5873 ("dm cache: add passthrough mode") inadvertently
removed the deferred set reference that was taken in cache_map()'s
writethrough mode support. Restore taking this reference.
This issue was found with code inspection.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Acked-by: Joe Thornber <ejt@redhat.com>
Cc: stable@vger.kernel.org # 3.13+
Use INIT_WORK_ONSTACK to silence "ODEBUG: object is on stack, but not
annotated".
Reported-by: Zdeněk Kabeláč <zkabelac@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Acked-by: Joe Thornber <ejt@redhat.com>
I hit another BUG_ON with e240c1839d. In __get_priority_stripe(),
stripe count equals to 0 initially. Between atomic_inc and BUG_ON,
get_active_stripe() finds the stripe. So the stripe count isn't 1 any more.
V2: keeps the BUG_ON suggested by Neil.
Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>
This was used in the olden days, back when onions were proper
yellow. Basically it mapped to the current buffer to be
transferred. With highmem being added more than a decade ago,
most drivers map pages out of a bio, and rq->buffer isn't
pointing at anything valid.
Convert old style drivers to just use bio_data().
For the discard payload use case, just reference the page
in the bio.
Signed-off-by: Jens Axboe <axboe@fb.com>
Commit 003b5c5719 ("block: Convert drivers
to immutable biovecs") incorrectly converted biovec iteration in
dm-verity to always calculate the hash from a full biovec, but the
function only needs to calculate the hash from part of the biovec (up to
the calculated "todo" value).
Fix this issue by limiting hash input to only the requested data size.
This problem was identified using the cryptsetup regression test for
veritysetup (verity-compat-test).
Signed-off-by: Milan Broz <gmazyland@gmail.com>
Acked-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org # 3.14+
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.22 (GNU/Linux)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=kHl3
-----END PGP SIGNATURE-----
Merge tag 'md/3.15' of git://neil.brown.name/md
Pull md updates from Neil Brown:
"Just a few md patches for the 3.15 merge window.
Not much happening in md/raid at the moment. Just a few bug fixes
(one for -stable) and a couple of performance tweaks"
* tag 'md/3.15' of git://neil.brown.name/md:
raid5: get_active_stripe avoids device_lock
raid5: make_request does less prepare wait
md: avoid oops on unload if some process is in poll or select.
md/raid1: r1buf_pool_alloc: free allocate pages when subsequent allocation fails.
md/bitmap: don't abuse i_writecount for bitmap files.
For sequential workload (or request size big workload), get_active_stripe can
find cached stripe. In this case, we always hold device_lock, which exposes a
lot of lock contention for such workload. If stripe count isn't 0, we don't
need hold the lock actually, since we just increase its count. And this is the
hot code path for such workload. Unfortunately we must delete the BUG_ON.
Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>
In NUMA machine, prepare_to_wait/finish_wait in make_request exposes a
lot of contention for sequential workload (or big request size
workload). For such workload, each bio includes several stripes. So we
can just do prepare_to_wait/finish_wait once for the whold bio instead
of every stripe. This reduces the lock contention completely for such
workload. Random workload might have the similar lock contention too,
but I didn't see it yet, maybe because my stroage is still not fast
enough.
Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>
If md-mod is unloaded while some process is in poll() or select(),
then that process maintains a pointer to md_event_waiters, and when
the try to unlink from that list, they will oops.
The procfs infrastructure ensures that ->poll won't be called after
remove_proc_entry, but doesn't provide a wait_queue_head for us to
use, and the waitqueue code doesn't provide a way to remove all
listeners from a waitqueue.
So we need to:
1/ make sure no further references to md_event_waiters are taken (by
setting md_unloading)
2/ wake up all processes currently waiting, and
3/ wait until all those processes have disconnected from our
wait_queue_head.
Reported-by: "majianpeng" <majianpeng@gmail.com>
Signed-off-by: NeilBrown <neilb@suse.de>
When performing a user-request check/repair (MD_RECOVERY_REQUEST is set)
on a raid1, we allocate multiple bios each with their own set of pages.
If the page allocations for one bio fails, we currently do *not* free
the pages allocated for the previous bios, nor do we free the bio itself.
This patch frees all the already-allocate pages, and makes sure that
all the bios are freed as well.
This bug can cause a memory leak which can ultimately OOM a machine.
It was introduced in 3.10-rc1.
Fixes: a07876064a
Cc: Kent Overstreet <koverstreet@google.com>
Cc: stable@vger.kernel.org (3.10+)
Reported-by: Russell King - ARM Linux <linux@arm.linux.org.uk>
Signed-off-by: NeilBrown <neilb@suse.de>
md bitmap code currently tries to use i_writecount to stop any other
process from writing to out bitmap file. But that is really an abuse
and has bit-rotted so locking is all wrong.
So discard that - root should be allowed to shoot self in foot.
Still use it in a much less intrusive way to stop the same file being
used as bitmap on two different array, and apply other checks to
ensure the file is at least vaguely usable for bitmap storage
(is regular, is open for write. Support for ->bmap is already checked
elsewhere).
Reported-by: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: NeilBrown <neilb@suse.de>
Commit c140e1c4e2 ("dm thin: use per thin device deferred bio lists")
introduced the use of an rculist for all active thin devices. The use
of rcu_read_lock() in process_deferred_bios() can result in a BUG if a
dm_bio_prison_cell must be allocated as a side-effect of bio_detain():
BUG: sleeping function called from invalid context at mm/mempool.c:203
in_atomic(): 1, irqs_disabled(): 0, pid: 6, name: kworker/u8:0
3 locks held by kworker/u8:0/6:
#0: ("dm-" "thin"){.+.+..}, at: [<ffffffff8106be42>] process_one_work+0x192/0x550
#1: ((&pool->worker)){+.+...}, at: [<ffffffff8106be42>] process_one_work+0x192/0x550
#2: (rcu_read_lock){.+.+..}, at: [<ffffffff816360b5>] do_worker+0x5/0x4d0
We can't process deferred bios with the rcu lock held, since
dm_bio_prison_cell allocation may block if the bio-prison's cell mempool
is exhausted.
To fix:
- Introduce a refcount and completion field to each thin_c
- Add thin_get/put methods for adjusting the refcount. If the refcount
hits zero then the completion is triggered.
- Initialise refcount to 1 when creating thin_c
- When iterating the active_thins list we thin_get() whilst the rcu
lock is held.
- After the rcu lock is dropped we process the deferred bios for that
thin.
- When destroying a thin_c we thin_put() and then wait for the
completion -- to avoid a race between the worker thread iterating
from that thin_c and destroying the thin_c.
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Commit c140e1c4e2 ("dm thin: use per thin device deferred bio lists")
incorrectly stopped disabling irqs when taking the pool's spinlock.
Irqs must be disabled when taking the pool's spinlock otherwise a thread
could spin_lock(), then get interrupted to service thin_endio() in
interrupt context, which would then deadlock in spin_lock_irqsave().
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
cache_block_size
. Fix a lock-inversion detected by LOCKDEP in dm-cache
. Fix a dangling bio bug in the dm-thinp target's process_deferred_bios
error path
. Fix corruption due to non-atomic transaction commit which allowed a
metadata superblock to be written before all other metadata was
successfully written -- this is common to all targets that use the
persistent-data library's transaction manager (dm-thinp, dm-cache and
dm-era).
. Various small cleanups in the DM core
. Add the dm-era target which is useful for keeping track of which
blocks were written within a user defined period of time called an
'era'. Use cases include tracking changed blocks for backup software,
and partially invalidating the contents of a cache to restore cache
coherency after rolling back a vendor snapshot.
. Improve the on-disk layout of multithreaded writes to the dm-thin-pool
by splitting the pool's deferred bio list to be a per-thin device list
and then sorting that list using an rb_tree. The subsequent read
throughput of the data written via multiple threads improved by ~70%.
. Simplify the multipath target's handling of queuing IO by pushing
requests back to the request queue rather than queueing the IO
internally.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iQEcBAABAgAGBQJTPv/6AAoJEMUj8QotnQNagQYH/3EkB2f66TRfjRQpVAZuchw/
U0IbVWcMJKMdhj3uaSNzIkAbTgF+QsZUOLHP/7Q6zLq0M2J3WGrJn2ELqq53MenF
E0+rJ8duKnJ5oLhhVT62ukBDh3XHWT0JyijXPWNa2gUoYwJqM9BAlXbC/OTfUNaZ
mBCxvUWGME8k3ht310GhwvzBQjYuxIXhw8XlbGvakb9S83SZwNpCh231iumOEzPe
Vzfx/xTto0fH3R5/knNV/H9xt0Dv4vt4Aqbqqys9UbQvPzj9qN/mxUZIFg+LZh/w
WuvHHw6HcAiNNrQGFcm6i1AK2jJ+F61K3afMlYsiamTxMNM+0q/B9HemkX/0ieU=
=lY8m
-----END PGP SIGNATURE-----
Merge tag 'dm-3.15-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm
Pull device mapper changes from Mike Snitzer:
- Fix dm-cache corruption caused by discard_block_size > cache_block_size
- Fix a lock-inversion detected by LOCKDEP in dm-cache
- Fix a dangling bio bug in the dm-thinp target's process_deferred_bios
error path
- Fix corruption due to non-atomic transaction commit which allowed a
metadata superblock to be written before all other metadata was
successfully written -- this is common to all targets that use the
persistent-data library's transaction manager (dm-thinp, dm-cache and
dm-era).
- Various small cleanups in the DM core
- Add the dm-era target which is useful for keeping track of which
blocks were written within a user defined period of time called an
'era'. Use cases include tracking changed blocks for backup
software, and partially invalidating the contents of a cache to
restore cache coherency after rolling back a vendor snapshot.
- Improve the on-disk layout of multithreaded writes to the
dm-thin-pool by splitting the pool's deferred bio list to be a
per-thin device list and then sorting that list using an rb_tree.
The subsequent read throughput of the data written via multiple
threads improved by ~70%.
- Simplify the multipath target's handling of queuing IO by pushing
requests back to the request queue rather than queueing the IO
internally.
* tag 'dm-3.15-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm: (24 commits)
dm cache: fix a lock-inversion
dm thin: sort the per thin deferred bios using an rb_tree
dm thin: use per thin device deferred bio lists
dm thin: simplify pool_is_congested
dm thin: fix dangling bio in process_deferred_bios error path
dm mpath: print more useful warnings in multipath_message()
dm-mpath: do not activate failed paths
dm mpath: remove extra nesting in map function
dm mpath: remove map_io()
dm mpath: reduce memory pressure when requeuing
dm mpath: remove process_queued_ios()
dm mpath: push back requests instead of queueing
dm table: add dm_table_run_md_queue_async
dm mpath: do not call pg_init when it is already running
dm: use RCU_INIT_POINTER instead of rcu_assign_pointer in __unbind
dm: stop using bi_private
dm: remove dm_get_mapinfo
dm: make dm_table_alloc_md_mempools static
dm: take care to copy the space map roots before locking the superblock
dm transaction manager: fix corruption due to non-atomic transaction commit
...
When suspending a cache the policy is walked and the individual policy
hints written to the metadata via sync_metadata(). This led to this
lock order:
policy->lock
cache_metadata->root_lock
When loading the cache target the policy is populated while the metadata
lock is held:
cache_metadata->root_lock
policy->lock
Fix this potential lock-inversion (ABBA) deadlock in sync_metadata() by
ensuring the cache_metadata root_lock is held whilst all the hints are
written, rather than being repeatedly locked while policy->lock is held
(as was the case with each callout that policy_walk_mappings() made to
the old save_hint() method).
Found by turning on the CONFIG_PROVE_LOCKING ("Lock debugging: prove
locking correctness") build option. However, it is not clear how the
LOCKDEP reported paths can lead to a deadlock since the two paths,
suspending a target and loading a target, never occur at the same time.
But that doesn't mean the same lock-inversion couldn't have occurred
elsewhere.
Reported-by: Marian Csontos <mcsontos@redhat.com>
Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org
A thin-pool will allocate blocks using FIFO order for all thin devices
which share the thin-pool. Because of this simplistic allocation the
thin-pool's space can become fragmented quite easily; especially when
multiple threads are requesting blocks in parallel.
Sort each thin device's deferred_bio_list based on logical sector to
help reduce fragmentation of the thin-pool's ondisk layout.
The following tables illustrate the realized gains/potential offered by
sorting each thin device's deferred_bio_list. An "io size"-sized random
read of the device would result in "seeks/io" fragments being read, with
an average "distance/seek" between each fragment.
Data was written to a single thin device using multiple threads via
iozone (8 threads, 64K for both the block_size and io_size).
unsorted:
io size seeks/io distance/seek
--------------------------------------
4k 0.000 0b
16k 0.013 11m
64k 0.065 11m
256k 0.274 10m
1m 1.109 10m
4m 4.411 10m
16m 17.097 11m
64m 60.055 13m
256m 148.798 25m
1g 809.929 21m
sorted:
io size seeks/io distance/seek
--------------------------------------
4k 0.000 0b
16k 0.000 1g
64k 0.001 1g
256k 0.003 1g
1m 0.011 1g
4m 0.045 1g
16m 0.181 1g
64m 0.747 1011m
256m 3.299 1g
1g 14.373 1g
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Acked-by: Joe Thornber <ejt@redhat.com>
Pull block driver update from Jens Axboe:
"On top of the core pull request, here's the pull request for the
driver related changes for 3.15. It contains:
- Improvements for msi-x registration for block drivers (mtip32xx,
skd, cciss, nvme) from Alexander Gordeev.
- A round of cleanups and improvements for drbd from Andreas
Gruenbacher and Rashika Kheria.
- A round of clanups and improvements for bcache from Kent.
- Removal of sleep_on() and friends in DAC960, ataflop, swim3 from
Arnd Bergmann.
- Bug fix for a bug in the mtip32xx async completion code from Sam
Bradshaw.
- Bug fix for accidentally bouncing IO on 32-bit platforms with
mtip32xx from Felipe Franciosi"
* 'for-3.15/drivers' of git://git.kernel.dk/linux-block: (103 commits)
bcache: remove nested function usage
bcache: Kill bucket->gc_gen
bcache: Kill unused freelist
bcache: Rework btree cache reserve handling
bcache: Kill btree_io_wq
bcache: btree locking rework
bcache: Fix a race when freeing btree nodes
bcache: Add a real GC_MARK_RECLAIMABLE
bcache: Add bch_keylist_init_single()
bcache: Improve priority_stats
bcache: Better alloc tracepoints
bcache: Kill dead cgroup code
bcache: stop moving_gc marking buckets that can't be moved.
bcache: Fix moving_pred()
bcache: Fix moving_gc deadlocking with a foreground write
bcache: Fix discard granularity
bcache: Fix another bug recovering from unclean shutdown
bcache: Fix a bug recovering from unclean shutdown
bcache: Fix a journalling reclaim after recovery bug
bcache: Fix a null ptr deref in journal replay
...
Here's the big char/misc driver updates for 3.15-rc1.
Lots of various things here, including the new mcb driver subsystem.
All of these have been in linux-next for a while.
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.22 (GNU/Linux)
iEYEABECAAYFAlM7ArIACgkQMUfUDdst+ylS+gCfcJr0Zo2v5aWnqD7rFtFETmFI
LhcAoNTQ4cvlVdxnI0driWCWFYxLj6at
=aj+L
-----END PGP SIGNATURE-----
Merge tag 'char-misc-3.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc
Pull char/misc driver patches from Greg KH:
"Here's the big char/misc driver updates for 3.15-rc1.
Lots of various things here, including the new mcb driver subsystem.
All of these have been in linux-next for a while"
* tag 'char-misc-3.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc: (118 commits)
extcon: Move OF helper function to extcon core and change function name
extcon: of: Remove unnecessary function call by using the name of device_node
extcon: gpio: Use SIMPLE_DEV_PM_OPS macro
extcon: palmas: Use SIMPLE_DEV_PM_OPS macro
mei: don't use deprecated DEFINE_PCI_DEVICE_TABLE macro
mei: amthif: fix checkpatch error
mei: client.h fix checkpatch errors
mei: use cl_dbg where appropriate
mei: fix Unnecessary space after function pointer name
mei: report consistently copy_from/to_user failures
mei: drop pr_fmt macros
mei: make me hw headers private to me hw.
mei: fix memory leak of pending write cb objects
mei: me: do not reset when less than expected data is received
drivers: mcb: Fix build error discovered by 0-day bot
cs5535-mfgpt: Simplify dependencies
spmi: pm: drop bus-level PM suspend/resume routines
spmi: pmic_arb: make selectable on ARCH_QCOM
Drivers: hv: vmbus: Increase the limit on the number of pfns we can handle
pch_phub: Report error writing MAC back to user
...
The thin-pool previously only had a single deferred_bios list that would
collect bios for all thin devices in the pool. Split this per-pool
deferred_bios list out to per-thin deferred_bios_list -- doing so
enables increased parallelism when processing deferred bios. And now
that each thin device has it's own deferred_bios_list we can sort all
bios in the list using logical sector. The requeue code in error
handling path is also cleaner as a side-effect.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Acked-by: Joe Thornber <ejt@redhat.com>
The pool is congested if the pool is in PM_OUT_OF_DATA_SPACE mode. This
is more explicit/clear/efficient than inferring whether or not the pool
is congested by checking if retry_on_resume_list is empty.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Acked-by: Joe Thornber <ejt@redhat.com>
If unable to ensure_next_mapping() we must add the current bio, which
was removed from the @bios list via bio_list_pop, back to the
deferred_bios list before all the remaining @bios.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Acked-by: Joe Thornber <ejt@redhat.com>
Cc: stable@vger.kernel.org
The warning message "Unrecognised multipath message received" is
displayed in two different situations in multipath_message(): when the
number of arguments passed is invalid and when the string passed in
argv[0] is not recognized.
Make it easier to identify where the problem is by making these warnings
more specific with additional context for each case.
Signed-off-by: Jose Castillo <jcastillo@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
activate_path() is run without a lock, so the path might be
set to failed before activate_path() had a chance to run.
This patch add a check for ->active in activate_path() to
avoid unnecessary overhead by calling functions which are known
to be failing.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Return early for case when no path exists, and when the
pathgroup isn't ready. This eliminates the need for
extra nesting for the the common case.
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Hannes Reinecke <hare@suse.de>
multipath_map() is now just a wrapper around map_io(), so we
can rename map_io() to multipath_map().
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Reviewed-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com>
When multipath needs to requeue I/O in the block layer the per-request
context shouldn't be allocated, as it will be freed immediately
afterwards anyway. Avoiding this memory allocation will reduce memory
pressure during requeuing.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Reviewed-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com>
process_queued_ios() has served 3 functions:
1) select pg and pgpath if none is selected
2) start pg_init if requested
3) dispatch queued IOs when pg is ready
Basically, a call to queue_work(process_queued_ios) can be replaced by
dm_table_run_md_queue_async(), which runs request queue and ends up
calling map_io(), which does 1), 2) and 3).
Exception is when !pg_ready() (which means either pg_init is running or
requested), then multipath_busy() prevents map_io() being called from
request_fn.
If pg_init is running, it should be ok as long as pg_init_done() does
the right thing when pg_init is completed, I.e.: restart pg_init if
!pg_ready() or call dm_table_run_md_queue_async() to kick map_io().
If pg_init is requested, we have to make sure the request is detected
and pg_init will be started. pg_init is requested in 3 places:
a) __choose_pgpath() in map_io()
b) __choose_pgpath() in multipath_ioctl()
c) pg_init retry in pg_init_done()
a) is ok because map_io() calls __pg_init_all_paths(), which does 2).
b) needs a call to __pg_init_all_paths(), which does 2).
c) needs a call to __pg_init_all_paths(), which does 2).
So this patch removes process_queued_ios() and ensures that
__pg_init_all_paths() is called at the appropriate locations.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Reviewed-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com>
Goldwyn Rodrigues