kernel_optimize_test/block
Tomoki Sekiyama eb1c160b22 elevator: Fix a race in elevator switching and md device initialization
The soft lockup below happens at the boot time of the system using dm
multipath and the udev rules to switch scheduler.

[  356.127001] BUG: soft lockup - CPU#3 stuck for 22s! [sh:483]
[  356.127001] RIP: 0010:[<ffffffff81072a7d>]  [<ffffffff81072a7d>] lock_timer_base.isra.35+0x1d/0x50
...
[  356.127001] Call Trace:
[  356.127001]  [<ffffffff81073810>] try_to_del_timer_sync+0x20/0x70
[  356.127001]  [<ffffffff8118b08a>] ? kmem_cache_alloc_node_trace+0x20a/0x230
[  356.127001]  [<ffffffff810738b2>] del_timer_sync+0x52/0x60
[  356.127001]  [<ffffffff812ece22>] cfq_exit_queue+0x32/0xf0
[  356.127001]  [<ffffffff812c98df>] elevator_exit+0x2f/0x50
[  356.127001]  [<ffffffff812c9f21>] elevator_change+0xf1/0x1c0
[  356.127001]  [<ffffffff812caa50>] elv_iosched_store+0x20/0x50
[  356.127001]  [<ffffffff812d1d09>] queue_attr_store+0x59/0xb0
[  356.127001]  [<ffffffff812143f6>] sysfs_write_file+0xc6/0x140
[  356.127001]  [<ffffffff811a326d>] vfs_write+0xbd/0x1e0
[  356.127001]  [<ffffffff811a3ca9>] SyS_write+0x49/0xa0
[  356.127001]  [<ffffffff8164e899>] system_call_fastpath+0x16/0x1b

This is caused by a race between md device initialization by multipathd and
shell script to switch the scheduler using sysfs.

 - multipathd:
   SyS_ioctl -> do_vfs_ioctl -> dm_ctl_ioctl -> ctl_ioctl -> table_load
   -> dm_setup_md_queue -> blk_init_allocated_queue -> elevator_init
    q->elevator = elevator_alloc(q, e); // not yet initialized

 - sh -c 'echo deadline > /sys/$DEVPATH/queue/scheduler':
   elevator_switch (in the call trace above)
    struct elevator_queue *old = q->elevator;
    q->elevator = elevator_alloc(q, new_e);
    elevator_exit(old);                 // lockup! (*)

 - multipathd: (cont.)
    err = e->ops.elevator_init_fn(q);   // init fails; q->elevator is modified

(*) When del_timer_sync() is called, lock_timer_base() will loop infinitely
while timer->base == NULL. In this case, as timer will never initialized,
it results in lockup.

This patch introduces acquisition of q->sysfs_lock around elevator_init()
into blk_init_allocated_queue(), to provide mutual exclusion between
initialization of the q->scheduler and switching of the scheduler.

This should fix this bugzilla:
https://bugzilla.redhat.com/show_bug.cgi?id=902012

Signed-off-by: Tomoki Sekiyama <tomoki.sekiyama@hds.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2013-11-08 09:00:08 -07:00
..
partitions block/partitions/efi.c: treat size mismatch as a warning, not an error 2013-10-16 21:35:53 -07:00
blk-cgroup.c Merge branch 'for-3.12/core' of git://git.kernel.dk/linux-block 2013-09-22 15:00:11 -07:00
blk-cgroup.h cgroup: make css_for_each_descendant() and friends include the origin css in the iteration 2013-08-08 20:11:27 -04:00
blk-core.c elevator: Fix a race in elevator switching and md device initialization 2013-11-08 09:00:08 -07:00
blk-exec.c If the queue is dying then we only call the rq->end_io callout. 2013-09-18 08:33:55 -06:00
blk-flush.c Block: blk-flush: Fixed indent code style 2013-03-22 12:22:51 -06:00
blk-integrity.c scatterlist: introduce sg_unmark_end 2013-03-20 15:43:04 +10:30
blk-ioc.c lib/radix-tree.c: make radix_tree_node_alloc() work correctly within interrupt 2013-09-11 15:59:36 -07:00
blk-iopoll.c block: Replace __get_cpu_var uses 2013-11-08 08:59:58 -07:00
blk-lib.c block: account iowait time when waiting for completion of IO request 2013-02-15 16:45:07 +01:00
blk-map.c block: re-use existing 'reading' variable instead of checking direction again 2011-12-21 15:27:24 +01:00
blk-merge.c scatterlist: introduce sg_unmark_end 2013-03-20 15:43:04 +10:30
blk-settings.c block: discard granularity might not be power of 2 2012-12-14 20:46:04 +01:00
blk-softirq.c block: Replace __get_cpu_var uses 2013-11-08 08:59:58 -07:00
blk-sysfs.c block/blk-sysfs.c: replace strict_strtoul() with kstrtoul() 2013-09-11 15:56:56 -07:00
blk-tag.c block: Reserve only one queue tag for sync IO if only 3 tags are available 2013-06-28 21:32:27 +02:00
blk-throttle.c cgroup: make css_for_each_descendant() and friends include the origin css in the iteration 2013-08-08 20:11:27 -04:00
blk-timeout.c block: fix race between request completion and timeout handling 2013-11-08 08:59:04 -07:00
blk.h block,elevator: use new hashtable implementation 2013-01-11 14:43:13 +01:00
bsg-lib.c bsg: Remove unused function bsg_goose_queue() 2012-12-06 14:33:02 +01:00
bsg.c hlist: drop the node parameter from iterators 2013-02-27 19:10:24 -08:00
cfq-iosched.c Merge branch 'for-3.12/core' of git://git.kernel.dk/linux-block 2013-09-22 15:00:11 -07:00
cmdline-parser.c block: support embedded device command line partition 2013-09-11 15:56:57 -07:00
compat_ioctl.c kernel-wide: fix missing validations on __get/__put/__copy_to/__copy_from_user() 2013-09-11 15:58:18 -07:00
deadline-iosched.c block: Convert kmalloc_node(...GFP_ZERO...) to kzalloc_node(...) 2013-09-11 13:22:03 -06:00
elevator.c elevator: Fix a race in elevator switching and md device initialization 2013-11-08 09:00:08 -07:00
genhd.c block: Convert kmalloc_node(...GFP_ZERO...) to kzalloc_node(...) 2013-09-11 13:22:03 -06:00
ioctl.c Merge branch 'for-3.7/core' of git://git.kernel.dk/linux-block 2012-10-11 09:04:23 +09:00
Kconfig block: change config option name for cmdline partition parsing 2013-09-30 14:31:02 -07:00
Kconfig.iosched blkcg: make CONFIG_BLK_CGROUP bool 2012-03-06 21:27:21 +01:00
Makefile block: change config option name for cmdline partition parsing 2013-09-30 14:31:02 -07:00
noop-iosched.c elevator: Fix a race in elevator switching 2013-07-03 13:25:24 +02:00
partition-generic.c Revert "loop: cleanup partitions when detaching loop device" 2013-04-08 10:12:11 +02:00
scsi_ioctl.c aio: don't include aio.h in sched.h 2013-05-07 20:16:25 -07:00