- dm-raid: use DM_ENDIO_INCOMPLETE
- dm-raid1: remove unused condition
- PROBLEM: read starvation during writeback
- 3.7 device-mapper changes
- read starvation during writeback
- Remove _tio_cache
- can we use wget in a kickstart file from livemedia-creator?
- default path for iSCSI
- linux-next oops
- aio: Refactor aio_read_evt, use cmxchg(), fix bug
- aio: vmap ringbuffer
- aio: Rewrite refcounting
- aio: kiocb_cancel()
- aio: Kill return value of aio_complete()
- percpu-rw-semapho lock splice methods
- hba qlogic installation
- block: Convert integrity to bvec_alloc_bs()
- dm thin: check kmalloc in dm_deferred_set_create()
- dm thin: check kmalloc in dm_deferred_set_create()
- block: Fix a buffer overrun in bio_integrity_split()
- block: Fix a buffer overrun in bio_integrity_split()
- shutting down logical volumes once an underlying device fails?
- 3.6 device-mapper fixes
- shutting down logical volumes once an underlying device fails?
- pvmove error hanging LVM layer?
- shutting down logical volumes once an underlying device fails?
- dm persistent data: convert to use le32_add_cpu()
- dm bio prison: add "dm_" prefix to bio prison and deferred set interfaces
- dm thin: remove old bio prison code that now lives in dm-bio-prison.c
- dm bio prison: factor bio prison code out to standalone library
- dm-switch target
- bufio & write completion indication
- Fix a crash when block device is read and block size is changed at the same time
- Fix a crash when block device is read and block size is changed at the same time
- dm-integrity: integrity protection device-mapper target
- dm-integrity: integrity protection device-mapper target
- block: Add bio_end_sector()
- block: Add submit_bio_wait(), remove from md
- block: Change bio_split() to respect the current value of bi_idx
- block: Add bio_end_sector()
- block: Convert integrity to bvec_alloc_bs()
- block: Fix a buffer overrun in bio_integrity_split()
- dm-integrity: integrity protection device-mapper target
- dm-integrity: integrity protection device-mapper target
- dm: gracefully fail any request beyond the end of the device
- dm: re-use live table's limits if next table has no data devices
- block: Convert some code to bio_for_each_segment_all()
- block: Add bio_for_each_segment_all()
- bounce: Refactor __blk_queue_bounce to not use bi_io_vec
- bounce: Refactor __blk_queue_bounce to not use bi_io_vec
- block: Remove some unnecessary bi_vcnt usage
- block: Don't use bi_idx in bio_split() or require it to be 0
- dm: gracefully fail any request beyond the end of the device
- bio-integrity: Add explicit field for owner of bip_buf
- dm table: do not allow queue limits that will exceed hardware limits
- dm: Use bioset's front_pad for dm_target_io
- dm: Use bioset's front_pad for dm_rq_clone_bio_info
- bio-integrity: Add explicit field for owner of bip_buf
- dm table: do not allow queue limits that will exceed hardware limits
- dm mpath: only retry ioctl if queue_if_no_path was configured
- dm mpath: only retry ioctl if queue_if_no_path was configured
- block: Convert integrity to bvec_alloc_bs(), and a bugfix
- btrfs: Kill some bi_idx references
- block: Convert integrity to bvec_alloc_bs(), and a bugfix
- block: Add BIO_SUBMITTED flag, kill BIO_CLONED
- bio-integrity: Add explicit field for owner of bip_buf
- raid1: use bio_alloc_pages()
- block: Add bio_alloc_pages()
- block: Convert some code to bio_for_each_segment_all()
- block: Add bio_for_each_segment_all()
- bounce: Refactor __blk_queue_bounce to not use bi_io_vec
- raid1: use bio_copy_data()
- pktcdvd: Use bio_reset() in disabled code to kill bi_idx usage
- pktcdvd: use bio_copy_data()
- block: Add bio_copy_data()
- raid1: Refactor narrow_write_error() to not use bi_idx
- raid5: use bio_reset()
- raid1: use bio_reset()
- raid10: Use bio_reset()
- block: Add submit_bio_wait(), remove from md
- block: Remove some unnecessary bi_vcnt usage
- block: Don't use bi_idx in bio_split() or require it to be 0
- block: Use bio_sectors() more consistently
- block: Convert integrity to bvec_alloc_bs(), and a bugfix
- block: Remove some unnecessary bi_vcnt usage
- block: Remove bi_idx references
- block: Don't use bi_idx in bio_split() or require it to be 0
- block: Use bio_sectors() more consistently
- block: Add bio_end()
- md: Convert md_trim_bio() to use bio_advance()
- block: Refactor blk_update_request()
- block: Add bio_advance()
- block: Convert integrity to bvec_alloc_bs(), and a bugfix
- Prep work for immutable bio vecs
- block: Avoid deadlocks with bio allocation by stacking drivers
- Avoid deadlocks with bio allocation
- dm mpath: move the dereference below the NULL test
- dm-bufio: use list_move instead of list_del/list_add
- block: Ues bi_pool for bio_integrity_alloc()
- RFC: use TRIM data from filesystems to speed up array rebuild?
- dm: Use bioset's front_pad for dm_target_io
- dm: Use bioset's front_pad for dm_target_io
- Linux DMMP and IBM DS4500
- Multipath issue
- scsi_dh_rdac : Consolidate rdac strings together
- scsi_dh_rdac : Add a new netapp vendor/product string
- scsi_dh_rdac : minor return fix for rdac
- multipath queues build invalid requests when all paths are lost
- Dm-cache in the Cloud (Call for beta testing, Free Linux cloud VM available)
- dm thin: fix discard support
- Fix a crash when block device is read and block size is changed at the same time
- New percpu lock implementation
- blockdev: fix a crash when block size is changed and I/O is issued simultaneously
- Add a lock that will be needed by the next patch
- Fix a crash when block device is read and block size is changed at the same time
- multipath queues build invalid requests when all paths are lost
- block: Avoid deadlocks with bio allocation by stacking drivers
- block: Avoid deadlocks with bio allocation by stacking drivers
- Immutable bio vecs
- block: Reorder struct bio_set
- Block cleanups, deadlock fix
- - Example userland code
- block: Add bio_clone_bioset(), bio_clone_kmalloc()
- block: Avoid deadlocks with bio allocation by stacking drivers
- block: Consolidate bio_alloc_bioset(), bio_kmalloc()
- hashtable: introduce a small and naive hashtable
- dm table: clear add_random unless all devices have it set
- block: Add bio_clone_bioset(), bio_clone_kmalloc()
- block: Avoid deadlocks with bio allocation by stacking drivers
- block: Consolidate bio_alloc_bioset(), bio_kmalloc()
- lockd: use new hashtable implementation
- SUNRPC: use new hashtable implementation in auth
- multipath: and wwids_file multipath.conf option
- New git URLs in old repo are wrong
- dm-crypt: parallel processing
- dm-crypt: sort writes
- dm-crypt: retain write ordering
- dm-crypt: offload writes to thread
- dm-crypt: move temporary values to stack
- dm-crypt: small changes
- dm-crypt: remove io_pending field
- dm-crypt: move error handling to crypt_convert.
- dm-crypt merge convert_context and dm_crypt_io
- dm-crypt: simplify cc_pending
- dm-crypt: avoid deadlock in mempools
- dm-crypt: don't allocate pages for a partial request.
- dm-crypt: unify io_queue and crypt_queue
- dm-crypt: simplify io queue
- dm-crypt: don't use write queue
- dm-crypt: Introduce an option that sets the number of threads.
- dm-crypt: Unify spinlock
- dm-crypt: use encryption threads
- dm-crypt: remove completion restart
- dm-crypt: use unbound workqueue for request processing
- dm-crypt: remove per-cpu structure
- dm-crypt: parallel processing
- multipath: fix setting sysfs fc timeout parameters
- multipath: and wwids_file multipath.conf option
- multipath: check if a device belongs to multipath
- md: modify dm_io() so it could return bios instead of submitting it
- md: add new interface 'mk_rq' in target_type
- hashtable: introduce a small and naive hashtable
- hashtable: introduce a small and naive hashtable
- net, rds: use new hashtable implementation
- net, l2tp: use new hashtable implementation
- net, 9p: use new hashtable implementation
- workqueue: use new hashtable implementation
- mm, ksm: use new hashtable implementation
- userns: use new hashtable implementation
- multipath: check if a device belongs to multipath
- multipath: add followover failback mode
- multipath-tools: prevent unexpected swapping of underlying LUNs
- Writing to a DM snapshot blocks for a long time
- dm-bufio & dm-verity: use ACCESS_ONCE instead of volatile
- reworked dm-switch target
- user_ns: use new hashtable implementation
- tracing output: use new hashtable implementation
- openvswitch: use new hashtable implementation
- net, rds: use new hashtable implementation
- lockd: use new hashtable implementation
- dm: use new hashtable implementation
- net, l2tp: use new hashtable implementation
- dlm: use new hashtable implementation
- SUNRPC/cache: use new hashtable implementation
- block, elevator: use new hashtable implementation
- net,9p: use new hashtable implementation
- tracepoint: use new hashtable implementation
- mm/huge_memory: use new hashtable implementation
- workqueue: use new hashtable implementation
- mm,ksm: use new hashtable implementation
- user_ns: use new hashtable implementation
- hashtable: introduce a small and naive hashtable
- generic hashtable implementation
- util-linux: resizepart: Utility to resize a partition
- dm: verity support data device offset (Linux 3.4.7)
- Consolidate bio_clone_bioset(), bio_kmalloc()
- dm: verity support data device offset (Linux 3.4.7)
- dm-verity: fix overflow checking
- scsi_dh_rdac: Add empty set_params function to scsi_dh_rdac
- dm: verity support data device offset (Linux 3.4.7)
- dm: verity support data device offset (Linux 3.4.7)
- scsi_dh_rdac: Add empty set_params function to scsi_dh_rdac
- dm-loop and kernel 3.x
- block: Only clone bio vecs that are in use
- dm: all kstrto* consumers should include kernel.h
- linux-next: Tree for Aug 2 (dm-raid)
- multipath bug
- SCSI disk IO problem with JBOD/multipath
- block: do not artificially constrain max_sectors for stacking drivers
- device-mapper updates for 3.6
- Introduce percpu rw semaphores
- blockdev: turn a rw semaphore into a percpu rw semaphore
- Introduce percpu rw semaphores
- Fix Crash when IO is being submitted and block size is changed
- multipath: fix cciss device names
- multipath: add followover failback mode
- multipath: check if a device belongs to multipath
- multipath: remove callout code
- Question about end_clone_bio()
- block: Introduce new bio_split())
- kpartx: work correctly with empty GPT table
- Dm-mirror Issue
- block: Rework bio_pair_split()
- block: Introduce new bio_split()
- bcache: Writeback, copying garbage collection
- Export __lockdep_no_validate__
- Revert "rw_semapho remove up/down_read_non_owner"
- Further device-mapper fixes for 3.5
- dm-thin: Random block placement strategy?
- fix compiler error
- multipath-tools: Preventing silent swapping of underlying LUNs
- Load balancing reads on dmraid1 (and 01) arrays
- block: split discard into aligned requests
- dm-mirror: set discard_zeroes_data_unsupported
- dm-thin: don't send discards to shared blocks
- dm-thin: fix discard_granularity
- dm-thin: fix discard support
- dm: introduce split_discard_requests
- Fix discards on dm-thin
- questions about dm-thin and discard
- questions about dm-thin and discard
- EPRD and TIER vs bcache
- Linux RAID subsystem future
- Linux RAID subsystem future
- multipath-tools/libmultipath structs.h
- How to control the device mapper 's memory use?(or the IO queue limits?)
- DM RAID: Add support for MD RAID10
- dm mpath: add 'retain_attached_hw_handler' feature
- dm mpath: add 'retain_loaded_hw_handler' feature
- dm mpath: add ability to disable partition creation