Tang Junhui 9baf30972b bcache: fix for gc and write-back race ... gc and write-back get raced (see the email "bcache get stucked" I sended before): gc thread write-back thread | |bch_writeback_thread() |bch_gc_thread() | | |==>read_dirty() |==>bch_btree_gc() | |==>btree_root() //get btree root | | //node write locker | |==>bch_btree_gc_root() | | |==>read_dirty_submit() | |==>write_dirty() | |==>continue_at(cl, | | write_dirty_finish, | | system_wq); | |==>write_dirty_finish()//excute | | //in system_wq | |==>bch_btree_insert() | |==>bch_btree_map_leaf_nodes() | |==>__bch_btree_map_nodes() | |==>btree_root //try to get btree | | //root node read | | //lock | |-----stuck here |==>bch_btree_set_root() |==>bch_journal_meta() |==>bch_journal() |==>journal_try_write() |==>journal_write_unlocked() //journal_full(&c->journal) | //condition satisfied |==>continue_at(cl, journal_write, system_wq); //try to excute | //journal_write in system_wq | //but work queue is excuting | //write_dirty_finish() |==>closure_sync(); //wait journal_write execute | //over and wake up gc, |-------------stuck here |==>release root node write locker This patch alloc a separate work-queue for write-back thread to avoid such race. (Commit log re-organized by Coly Li to pass checkpatch.pl checking) Signed-off-by: Tang Junhui <tang.junhui@zte.com.cn> Acked-by: Coly Li <colyli@suse.de> Cc: stable@vger.kernel.org Signed-off-by: Jens Axboe <axboe@kernel.dk>		2017-09-06 08:17:33 -06:00
..
alloc.c	bcache: increase the number of open buckets	2017-09-06 08:17:33 -06:00
bcache.h	bcache: fix for gc and write-back race	2017-09-06 08:17:33 -06:00
bset.c	sched/headers: Prepare for new header dependencies before moving code to <linux/sched/clock.h>	2017-03-02 08:42:27 +01:00
bset.h	bcache: fix typo in bch_bkey_equal_header	2014-08-04 15:23:03 -07:00
btree.c	block: switch bios to blk_status_t	2017-06-09 09:27:32 -06:00
btree.h	sched/wait: Rename wait_queue_t => wait_queue_entry_t	2017-06-20 12:18:27 +02:00
closure.c	bcache: Don't reinvent the wheel but use existing llist API	2017-09-06 08:17:33 -06:00
closure.h	sched/headers: Prepare for new header dependencies before moving code to <linux/sched/task_stack.h>	2017-03-02 08:42:36 +01:00
debug.c	block: replace bi_bdev with a gendisk pointer and partitions index	2017-08-23 12:49:55 -06:00
debug.h	bcache: Convert debug code to btree_keys	2014-01-08 13:05:13 -08:00
extents.c	bcache: Fix a journal replay bug	2014-08-04 15:23:02 -07:00
extents.h	bcache: Fix a journal replay bug	2014-08-04 15:23:02 -07:00
io.c	block: replace bi_bdev with a gendisk pointer and partitions index	2017-08-23 12:49:55 -06:00
journal.c	block: replace bi_bdev with a gendisk pointer and partitions index	2017-08-23 12:49:55 -06:00
journal.h	bcache: Fix a shutdown bug	2014-02-25 18:42:49 -08:00
Kconfig	bcache: Kill dead cgroup code	2014-03-18 12:22:35 -07:00
Makefile	bcache: Abstract out stuff needed for sorting	2014-01-08 13:05:12 -08:00
movinggc.c	block: switch bios to blk_status_t	2017-06-09 09:27:32 -06:00
request.c	bcache: do not subtract sectors_to_gc for bypassed IO	2017-09-06 08:17:33 -06:00
request.h	block: switch bios to blk_status_t	2017-06-09 09:27:32 -06:00
stats.c	bcache: Kill dead cgroup code	2014-03-18 12:22:35 -07:00
stats.h	bcache: Break up struct search	2013-11-10 21:56:32 -08:00
super.c	bcache: fix for gc and write-back race	2017-09-06 08:17:33 -06:00
sysfs.c	bcache: Correct return value for sysfs attach errors	2017-09-06 08:17:33 -06:00
sysfs.h	bcache: Don't export utility code, prefix with bch_	2013-03-28 12:50:55 -06:00
trace.c	bcache: Better alloc tracepoints	2014-03-18 12:22:35 -07:00
util.c	sched/headers: Prepare for new header dependencies before moving code to <linux/sched/clock.h>	2017-03-02 08:42:27 +01:00
util.h	treewide: use kv[mz]alloc* rather than opencoded variants	2017-05-08 17:15:13 -07:00
writeback.c	bcache: fix for gc and write-back race	2017-09-06 08:17:33 -06:00
writeback.h	bcache: correct cache_dirty_target in __update_writeback_rate()	2017-09-06 08:17:33 -06:00