summaryrefslogtreecommitdiffstats
path: root/drivers/md/raid5.c
Commit message (Expand)AuthorAgeFilesLines
* md/raid5: Fix livelock when array is both resyncing and degraded.NeilBrown2015-02-181-1/+2
* md: make reconfig_mutex optional for writes to md sysfs files.NeilBrown2015-02-061-58/+76
* md/raid5: use ->lock to protect accessing raid5 sysfs attributes.NeilBrown2015-02-061-16/+28
* md: rename ->stop to ->freeNeilBrown2015-02-041-7/+5
* md: split detach operation out from ->stop.NeilBrown2015-02-041-1/+0
* md: make merge_bvec_fn more robust in face of personality changes.NeilBrown2015-02-041-4/+4
* md: make ->congested robust against personality changes.NeilBrown2015-02-041-15/+4
* md/raid5: need_this_block: tidy/fix last condition.NeilBrown2015-02-041-10/+32
* md/raid5: need_this_block: start simplifying the last two conditions.NeilBrown2015-02-041-5/+23
* md/raid5: separate out the easy conditions in need_this_block.NeilBrown2015-02-041-9/+29
* md/raid5: separate large if clause out of fetch_block().NeilBrown2015-02-041-4/+15
* md: do_release_stripe(): No need to call md_wakeup_thread() twiceJes Sorensen2015-02-041-5/+2
* md/raid5: fix another livelock caused by non-aligned writes.NeilBrown2015-02-021-0/+5
* md/raid5: fetch_block must fetch all the blocks handle_stripe_dirtying wants.NeilBrown2014-12-031-2/+5
* md: remove unwanted white space from md.cNeilBrown2014-10-141-22/+1
* md/raid5: fix init_stripe() inconsistenciesMarkus Stockhausen2014-10-141-3/+1
* md: use set_bit/clear_bit instead of shift/mask for bi_flags changes.NeilBrown2014-10-091-1/+1
* md/raid5: disable 'DISCARD' by default due to safety concerns.NeilBrown2014-10-021-1/+17
* md/raid6: avoid data corruption during recovery of double-degraded RAID6NeilBrown2014-08-181-0/+2
* md/raid5: avoid livelock caused by non-aligned writes.NeilBrown2014-08-181-1/+1
* Merge tag 'md/3.16' of git://neil.brown.name/mdLinus Torvalds2014-06-111-35/+123
|\
| * raid5: speedup sync_request processingEivind Sarto2014-06-101-1/+1
| * md/raid5: deadlock between retry_aligned_read with barrier iohui jiao2014-06-051-1/+1
| * raid5: add an option to avoid copy data from bio to stripe cacheShaohua Li2014-05-291-21/+98
| * raid5: avoid release list until last reference of the stripeEivind Sarto2014-05-291-0/+5
| * md/raid56: Don't perform reads to support writes until stripe is ready.NeilBrown2014-05-291-12/+18
* | arch: Mass conversion of smp_mb__*()Peter Zijlstra2014-04-181-1/+1
|/
* raid5: fix a race of stripe count checkShaohua Li2014-04-171-2/+1
* raid5: get_active_stripe avoids device_lockShaohua Li2014-04-091-7/+2
* raid5: make_request does less prepare waitShaohua Li2014-04-091-5/+14
* md/raid5: Fix CPU hotplug callback registrationOleg Nesterov2014-02-131-46/+44
* Merge branch 'for-3.14/drivers' of git://git.kernel.dk/linux-blockLinus Torvalds2014-01-301-0/+1
|\
| * bcache/md: Use raid stripe sizeKent Overstreet2014-01-081-0/+1
* | Merge branch 'for-3.14/core' of git://git.kernel.dk/linux-blockLinus Torvalds2014-01-301-41/+43
|\ \ | |/
| * Merge tag 'v3.13-rc6' into for-3.14/coreJens Axboe2013-12-311-8/+5
| |\
| * | block: Convert bio_for_each_segment() to bvec_iterKent Overstreet2013-11-231-6/+6
| * | block: Abstract out bvec iteratorKent Overstreet2013-11-231-35/+37
* | | md/raid5: close recently introduced race in stripe_head management.NeilBrown2014-01-221-4/+4
* | | md/raid5: fix long-standing problem with bitmap handling on write failure.NeilBrown2014-01-161-0/+1
* | | md/raid5: fix a recently broken BUG_ON().NeilBrown2014-01-141-1/+2
* | | md/raid5: Fix possible confusion when multiple write errors occur.NeilBrown2014-01-141-2/+2
| |/ |/|
* | md/raid5: fix newly-broken locking in get_active_stripe.NeilBrown2013-11-281-7/+4
* | md/raid5: fix new memory-reference bug in alloc_thread_groups.NeilBrown2013-11-281-1/+1
|/
* Merge tag 'md/3.13' of git://neil.brown.name/mdLinus Torvalds2013-11-201-101/+319
|\
| * md/raid5: Use conf->device_lock protect changing of multi-thread resources.majianpeng2013-11-191-24/+39
| * md/raid5: Before freeing old multi-thread worker, it should flush them.majianpeng2013-11-191-0/+3
| * md/raid5: For stripe with R5_ReadNoMerge, we replace REQ_FLUSH with REQ_NOMERGE.majianpeng2013-11-191-1/+1
| * md: use MD_RECOVERY_INTR instead of kthread_should_stop in resync thread.NeilBrown2013-11-191-4/+15
| * raid5: Retry R5_ReadNoMerge flag when hit a read error.Bian Yu2013-11-191-0/+3
| * raid5: relieve lock contention in get_active_stripe()Shaohua Li2013-11-191-1/+7
OpenPOWER on IntegriCloud