summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* Merge tag 'for-4.16/dm-changes' of ↵Linus Torvalds2018-01-3131-671/+1409
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm Pull device mapper updates from Mike Snitzer: - DM core fixes to ensure that bio submission follows a depth-first tree walk; this is critical to allow forward progress without the need to use the bioset's BIOSET_NEED_RESCUER. - Remove DM core's BIOSET_NEED_RESCUER based dm_offload infrastructure. - DM core cleanups and improvements to make bio-based DM more efficient (e.g. reduced memory footprint as well leveraging per-bio-data more). - Introduce new bio-based mode (DM_TYPE_NVME_BIO_BASED) that leverages the more direct IO submission path in the block layer; this mode is used by DM multipath and also optimizes targets like DM thin-pool that stack directly on NVMe data device. - DM multipath improvements to factor out legacy SCSI-only (e.g. scsi_dh) code paths to allow for more optimized support for NVMe multipath. - A fix for DM multipath path selectors (service-time and queue-length) to select paths in a more balanced way; largely academic but doesn't hurt. - Numerous DM raid target fixes and improvements. - Add a new DM "unstriped" target that enables Intel to workaround firmware limitations in some NVMe drives that are striped internally (this target also works when stacked above the DM "striped" target). - Various Documentation fixes and improvements. - Misc cleanups and fixes across various DM infrastructure and targets (e.g. bufio, flakey, log-writes, snapshot). * tag 'for-4.16/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm: (69 commits) dm cache: Documentation: update default migration_throttling value dm mpath selector: more evenly distribute ties dm unstripe: fix target length versus number of stripes size check dm thin: fix trailing semicolon in __remap_and_issue_shared_cell dm table: fix NVMe bio-based dm_table_determine_type() validation dm: various cleanups to md->queue initialization code dm mpath: delay the retry of a request if the target responded as busy dm mpath: return DM_MAPIO_DELAY_REQUEUE if QUEUE_IO or PG_INIT_REQUIRED dm mpath: return DM_MAPIO_REQUEUE on blk-mq rq allocation failure dm log writes: fix max length used for kstrndup dm: backfill missing calls to mutex_destroy() dm snapshot: use mutex instead of rw_semaphore dm flakey: check for null arg_name in parse_features() dm thin: extend thinpool status format string with omitted fields dm thin: fixes in thin-provisioning.txt dm thin: document representation of <highest mapped sector> when there is none dm thin: fix documentation relative to low water mark threshold dm cache: be consistent in specifying sectors and SI units in cache.txt dm cache: delete obsoleted paragraph in cache.txt dm cache: fix grammar in cache-policies.txt ...
| * dm cache: Documentation: update default migration_throttling valueJohn Pittman2018-01-301-1/+1
| | | | | | | | | | | | | | | | | | | | In commit f8350daf7af0 ("dm cache: tune migration throttling") the value for DEFAULT_MIGRATION_THRESHOLD was decreased from 204800 to 2048. Edit device-mapper/cache.txt to reflect the correct default value for migration_threshold. Signed-off-by: John Pittman <jpittman@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm mpath selector: more evenly distribute tiesKhazhismel Kumykov2018-01-292-6/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Move the last used path to the end of the list (least preferred) so that ties are more evenly distributed. For example, in case with three paths with one that is slower than others, the remaining two would be unevenly used if they tie. This is due to the rotation not being a truely fair distribution. Illustrated: paths a, b, c, 'c' has 1 outstanding IO, a and b are 'tied' Three possible rotations: (a, b, c) -> best path 'a' (b, c, a) -> best path 'b' (c, a, b) -> best path 'a' (a, b, c) -> best path 'a' (b, c, a) -> best path 'b' (c, a, b) -> best path 'a' ... So 'a' is used 2x more than 'b', although they should be used evenly. With this change, the most recently used path is always the least preferred, removing this bias resulting in even distribution. (a, b, c) -> best path 'a' (b, c, a) -> best path 'b' (c, a, b) -> best path 'a' (c, b, a) -> best path 'b' ... Signed-off-by: Khazhismel Kumykov <khazhy@google.com> Reviewed-by: Martin Wilck <mwilck@suse.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm unstripe: fix target length versus number of stripes size checkScott Bauer2018-01-291-8/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Since the unstripe target takes a target length which is the size of *one* striped member we're trying to expose, not the total size of *all* the striped members, the check does not make sense and fails for some striped setups. For example, say we have a 4TB striped device: or 3907018496 sectors per underlying device: if (sector_div(width, uc->stripes)) : 3907018496 / 2(num stripes) == 1953509248 tmp_len = width; if (sector_div(tmp_len, uc->chunk_size)) : 1953509248 / 256(chunk size) == 7630895.5 (fails) Fix this by removing the first check which isn't valid for unstriping. Signed-off-by: Scott Bauer <scott.bauer@intel.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm thin: fix trailing semicolon in __remap_and_issue_shared_cellLuis de Bethencourt2018-01-291-1/+1
| | | | | | | | | | | | | | | | The trailing semicolon is an empty statement that does no operation. Removing it since it doesn't do anything. Signed-off-by: Luis de Bethencourt <luisbg@kernel.org> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm table: fix NVMe bio-based dm_table_determine_type() validationMike Snitzer2018-01-291-22/+35
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The 'verify_rq_based:' code in dm_table_determine_type() was checking all devices in the DM table rather than only checking the data devices. Fix this by using the immutable target's iterate_devices method. Also, tweak the block of dm_table_determine_type() code that decides whether to upgrade from DM_TYPE_BIO_BASED to DM_TYPE_NVME_BIO_BASED so that it makes sure the immutable_target doesn't support require splitting IOs. These changes have been verified to allow a "thin-pool" target whose data device is an NVMe device to be upgraded to DM_TYPE_NVME_BIO_BASED. Using the thin-pool in NVMe bio-based mode was verified to pass all the device-mapper-test-suite's "thin-provisioning" tests. Also verified that request-based DM multipath (with queue_mode "rq" and "mq") works as expected using the 'mptest' harness. Fixes: 22c11858e ("dm: introduce DM_TYPE_NVME_BIO_BASED") Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm: various cleanups to md->queue initialization codeMike Snitzer2018-01-293-22/+12
| | | | | | | | | | | | Also, add dm_sysfs_init() error handling to dm_create(). Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm mpath: delay the retry of a request if the target responded as busyMike Snitzer2018-01-293-2/+10
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Add DM_ENDIO_DELAY_REQUEUE to allow request-based multipath's multipath_end_io() to instruct dm-rq.c:dm_done() to delay a requeue. This is beneficial to do if BLK_STS_RESOURCE is returned from the target (because target is busy). Relative to blk-mq: kick the hw queues via blk_mq_requeue_work(), indirectly from dm-rq.c:__dm_mq_kick_requeue_list(), after a delay. For old .request_fn: use blk_delay_queue(). bio-based multipath doesn't have feature parity with request-based for retryable error requeues; that is something that'll need fixing in the future. Suggested-by: Bart Van Assche <bart.vanassche@wdc.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com> Acked-by: Bart Van Assche <bart.vanassche@wdc.com> [as interpreted from Bart's "... patch looks fine to me."]
| * dm mpath: return DM_MAPIO_DELAY_REQUEUE if QUEUE_IO or PG_INIT_REQUIREDMing Lei2018-01-171-3/+2
| | | | | | | | | | | | | | | | | | | | | | | | Avoid using DM_MAPIO_REQUEUE unless absolutely necessary because it results in dm-rq.c:dm_mq_queue_rq() returning BLK_STS_RESOURCE to blk-mq -- doing so should only ever be done if the underlying queue is out of resources. So switch to returning DM_MAPIO_DELAY_REQUEUE from multipath_clone_and_map() if either MPATHF_QUEUE_IO or MPATHF_PG_INIT_REQUIRED are set. Signed-off-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm mpath: return DM_MAPIO_REQUEUE on blk-mq rq allocation failureMing Lei2018-01-171-1/+13
| | | | | | | | | | | | | | | | | | | | | | | | | | blk-mq will rerun queue via RESTART or dispatch wake after one request is completed, so not necessary to wait random time for requeuing, we should trust blk-mq to do it. More importantly, we need to return BLK_STS_RESOURCE to blk-mq so that dequeuing from the I/O scheduler can be stopped, this results in improved I/O merging. Signed-off-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm log writes: fix max length used for kstrndupMa Shimiao2018-01-171-1/+1
| | | | | | | | | | | | | | | | If source string is longer than max, kstrndup will allocate max+1 space. So make sure the result will not exceed max. Signed-off-by: Ma Shimiao <mashimiao.fnst@cn.fujitsu.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm: backfill missing calls to mutex_destroy()Mike Snitzer2018-01-179-2/+27
| | | | | | | | Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm snapshot: use mutex instead of rw_semaphoreMikulas Patocka2018-01-171-41/+43
| | | | | | | | | | | | | | | | | | The rw_semaphore is acquired for read only in two places, neither is performance-critical. So replace it with a mutex -- which is more efficient. Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm flakey: check for null arg_name in parse_features()Goldwyn Rodrigues2018-01-171-0/+5
| | | | | | | | | | | | | | | | | | | | | | One can crash dm-flakey by specifying more feature arguments than the number of features supplied. Checking for null in arg_name avoids this. dmsetup create flakey-test --table "0 66076080 flakey /dev/sdb9 0 0 180 2 drop_writes" Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm thin: extend thinpool status format string with omitted fieldsmulhern2018-01-171-1/+2
| | | | | | | | | | Signed-off-by: mulhern <amulhern@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm thin: fixes in thin-provisioning.txtmulhern2018-01-171-1/+1
| | | | | | | | | | | | | | | | | | Make the format string for thinpool status more correct. Swap the order of two items to correspond with reality. Signed-off-by: mulhern <amulhern@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm thin: document representation of <highest mapped sector> when there is nonemulhern2018-01-171-0/+3
| | | | | | | | | | Signed-off-by: mulhern <amulhern@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm thin: fix documentation relative to low water mark thresholdmulhern2018-01-171-3/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Fixes: 1. The use of "exceeds" when the opposite of exceeds, falls below, was meant. 2. Properly speaking, a table can not exceed a threshold. It emphasizes the important point, which is that it is the userspace daemon's responsibility to check for low free space when a device is resumed, since it won't get a special event indicating low free space in that situation. Signed-off-by: mulhern <amulhern@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm cache: be consistent in specifying sectors and SI units in cache.txtmulhern2018-01-171-2/+2
| | | | | | | | | | Signed-off-by: mulhern <amulhern@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm cache: delete obsoleted paragraph in cache.txtmulhern2018-01-171-5/+0
| | | | | | | | | | | | | | | | The 'mq' policy is no longer the default policy, and the default policy, 'smq', does not store hit counts. Signed-off-by: mulhern <amulhern@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm cache: fix grammar in cache-policies.txtmulhern2018-01-171-2/+2
| | | | | | | | | | | | | | Use possessive pronoun where appropriate, instead of contraction. Signed-off-by: mulhern <amulhern@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm snapshot: improve documentation relative to origin suspend requirementsMikulas Patocka2018-01-171-0/+4
| | | | | | | | | | | | | | | | Add a note to snapshot.txt that the origin target must be suspended when loading or unloading the snapshot target. Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm: move dm_table_destroy() to same header as dm_table_create()Brian Norris2018-01-172-1/+5
| | | | | | | | | | | | | | | | | | If anyone is going to use dm_table_create(), they probably should be able to use dm_table_destroy() too. Move the dm_table_destroy() definition outside the private header, near dm_table_create() Signed-off-by: Brian Norris <briannorris@chromium.org> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm raid: make raid_sets symbol staticWei Yongjun2018-01-171-1/+1
| | | | | | | | | | | | | | | | | | | | Fixes the following sparse warning: drivers/md/dm-raid.c:33:1: warning: symbol 'raid_sets' was not declared. Should it be static? Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm bufio: eliminate unnecessary labels in dm_bufio_client_create()Mike Snitzer2018-01-171-7/+5
| | | | | | | | Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm bufio: check result of register_shrinker()Aliaksei Karaliou2018-01-171-6/+9
| | | | | | | | | | | | | | | | dm_bufio_client_create() does not check result of register_shrinker() which was tagged as __must_check recently, reported by sparse. Signed-off-by: Aliaksei Karaliou <akaraliou.dev@gmail.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm bufio: add missed destroys of client mutexAliaksei Karaliou2018-01-171-0/+2
| | | | | | | | | | | | | | | | The client's mutex needs to be destroyed in dm_bufio_client_destroy() as well as the dm_bufio_client_create() error path. Signed-off-by: Aliaksei Karaliou <akaraliou.dev@gmail.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm bufio: use REQ_OP_READ and REQ_OP_WRITEMikulas Patocka2018-01-171-6/+6
| | | | | | | | | | | | | | | | | | Use REQ_OP_READ and REQ_OP_WRITE macros instead of READ and WRITE. They have the same value, but the block layer uses REQ_OP so bufio should too. Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm: add unstriped targetScott Bauer2018-01-174-0/+357
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This device mapper "unstriped" target remaps and unstripes I/O so it is issued solely on a single drive in a HW RAID0 or dm-striped target. In a 4 drive HW RAID0 the striped target exposes 1/4th of the LBA range as a virtual drive. Each I/O to that virtual drive will only be issued to the 1 drive that was selected of the 4 drives in the HW RAID0. This unstriped target is most useful for Intel NVMe drives that have multiple cores but that do not have firmware control to pin separate LBA ranges to each discrete cpu core. Signed-off-by: Scott Bauer <scott.bauer@intel.com> Signed-off-by: Heinz Mauelshagen <heinzm@redhat.com> Acked-by: Keith Busch <keith.busch@intel.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm mpath: factor out SCSI vs NVMe path selectionMike Snitzer2018-01-061-13/+55
| | | | | | | | | | | | | | | | | | | | Trying to do both SCSI and NVMe bio-based handling with branching in the same common code has proven too tedious on a code maintenance level. In addition it slightly hurts IO performance. Fix this by factoring out __map_bio() and __map_bio_nvme(). Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm mpath: optimize NVMe bio-based supportMike Snitzer2018-01-061-76/+95
| | | | | | | | | | | | | | | | | | | | All code that deals with pg_init is not used with bio-based NVMe mode. This includes skipping initialization of pg_init related variables. Also, pg_init related members on 'struct multipath' have been grouped together. Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm mpath: implement NVMe bio-based supportMike Snitzer2018-01-051-9/+21
| | | | | | | | | | | | | | | | | | | | | | | | | | | | This DM multipath NVMe bio-based support requires CONFIG_NVME_MULTIPATH to not be set. In the future hopefully NVMe multipath and DM multipath can co-exist more seemlessly. But as is, if CONFIG_NVME_MULTIPATH=Y then all the individal NVMe paths will remain hidden to upper layers and as such DM multipath will not be able to manage them. Though NVMe's native multipathing doesn't multipath namespaces across subsystems; so technically a user _could_ use CONFIG_NVME_MULTIPATH=Y and also use DM multipath to multipath across subsystems. Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm mpath: move dm_bio_restore out of endio methodMike Snitzer2018-01-031-4/+3
| | | | | | | | | | | | | | Moving the dm_bio_restore() to process_queued_bios() avoids doing that work in multipath_end_io_bio(). Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm mpath: optimize retrieval of bio_details from per-bio-dataMike Snitzer2017-12-201-5/+3
| | | | | | | | Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm mpath: remove unnecessary memset() calls for per-io-dataMike Snitzer2017-12-201-10/+6
| | | | | | | | | | | | | | | | All underlying members are initialized directly so the memset() calls are not needed. Also, initialize mpio->nr_bytes from the start since it never changes. Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm mpath: remove unused param from multipath_init_per_bio_data()Mike Snitzer2017-12-201-6/+2
| | | | | | | | | | | | 'struct dm_bio_details *' isn't ever needed. Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm: optimize bio-based NVMe IO submissionMike Snitzer2017-12-201-34/+120
| | | | | | | | | | | | | | | | | | | | | | Upper level bio-based drivers that stack immediately ontop of NVMe can leverage direct_make_request(). In addition DM's NVMe bio-based will initially only ever have one NVMe device that it submits IO to at a time. There is no splitting needed. Enhance DM core so that DM_TYPE_NVME_BIO_BASED's IO submission takes advantage of both of these characteristics. Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm: introduce DM_TYPE_NVME_BIO_BASEDMike Snitzer2017-12-203-6/+51
| | | | | | | | | | | | | | | | | | | | | | If dm_table_determine_type() establishes DM_TYPE_NVME_BIO_BASED then all devices in the DM table do not support partial completions. Also, the table has a single immutable target that doesn't require DM core to split bios. This will enable adding NVMe optimizations to bio-based DM. Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm: simplify start of block stats accounting for bio-basedMike Snitzer2017-12-171-8/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | No apparent need to generic_start_io_acct() until before the IO is ready for submission. start_io_acct() is the proper place to do this accounting -- it is also where DM accounts for pending IO and, if enabled, starts dm-stats accounting. Replace start_io_acct()'s part_round_stats() with generic_start_io_acct(). This eliminates needing to take part_stat_lock() multiple times when starting an IO on bio-based devices. Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm: remove redundant mapped_device member from clone_info structureMike Snitzer2017-12-171-6/+4
| | | | | | | | | | | | | | 'struct dm_io' already has the same pointer. So update all accesses from ci->md to ci->io->md. Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm: remove now unused bio-based io_pool and _io_cacheMike Snitzer2017-12-172-30/+2
| | | | | | | | Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm: improve performance by moving dm_io structure to per-bio-dataMike Snitzer2017-12-173-69/+133
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Eliminates need for a separate mempool to allocate 'struct dm_io' objects from. As such, it saves an extra mempool allocation for each original bio that DM core is issued. This complicates the per-bio-data accessor functions by needing to conditonally add extra padding to get to a target's per-bio-data. But in the end this provides a decent performance improvement for all bio-based DM devices. On an NVMe-loop based testbed to a ramdisk (~3100 MB/s): bio-based DM linear performance improved by 2% (went from 2665 to 2777 MB/s). Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm: rename 'bio' member of dm_io structure to 'orig_bio'Mike Snitzer2017-12-171-14/+14
| | | | | | | | Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm: remove stale comment blocksMike Snitzer2017-12-171-12/+0
| | | | | | | | | | | | | | | | These CRUD comments have worn out their welcome. The code is what it is, over time it'll hopefully get better. But these comments serve no purpose whatsoever. Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm: set QUEUE_FLAG_DAX accordingly in dm_table_set_restrictions()Mike Snitzer2017-12-132-3/+2
| | | | | | | | | | | | | | Rather than having DAX support be unique by setting it based on table type in dm_setup_md_queue(). Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm: fix __send_changing_extent_only() to send first bio and chain remainderMike Snitzer2017-12-131-36/+30
| | | | | | | | | | | | | | | | | | | | __send_changing_extent_only() must follow the same pattern that was established with commit "dm: ensure bio submission follows a depth-first tree walk". That is: submit first bio up to split boundary and then split the remainder to further submissions. Suggested-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm: ensure bio-based DM's bioset and io_pool support targets' maximum IOsMike Snitzer2017-12-133-15/+27
| | | | | | | | | | | | | | | | | | alloc_multiple_bios() assumes it can allocate the requested number of bios but until now there was no gaurantee that the mempools would be accomodating. Suggested-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm: remove BIOSET_NEED_RESCUER based dm_offload infrastructureMike Snitzer2017-12-131-59/+1
| | | | | | | | | | | | | | | | Now that all of DM has been revised and/or verified to no longer require the use of BIOSET_NEED_RESCUER the dm_offload code may be removed. Suggested-by: NeilBrown <neilb@suse.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm: safely allocate multiple bioset biosMike Snitzer2017-12-131-12/+57
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | DM targets can request multiple bios be sent to them by DM core (see: num_{flush,discard,write_same,write_zeroes}_bios). But until now these bios were allocated in an unsafe manner than could potentially exhaust the DM device's bioset -- in the face of multiple threads each trying to do multiple allocations from the same DM device's bioset. Fix __send_duplicate_bios() by using the new alloc_multiple_bios(). The allocation strategy used by alloc_multiple_bios() models that used by dm-crypt.c:crypt_alloc_buffer(). Neil Brown initially proposed this fix but the implementation has been revised enough that it inappropriate to attribute the entirety of it to him. Suggested-by: NeilBrown <neilb@suse.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
| * dm: remove unused 'num_write_bios' target interfaceNeilBrown2017-12-132-35/+10
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | No DM target provides num_write_bios and none has since dm-cache's brief use in 2013. Having the possibility of num_write_bios > 1 complicates bio allocation. So remove the interface and assume there is only one bio needed. If a target ever needs more, it must provide a suitable bioset and allocate itself based on its particular needs. Signed-off-by: NeilBrown <neilb@suse.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
generated by cgit v1.2.3 (git 2.39.1) at 2025-01-14 04:24:18 +0100