blk-mq: fix calling unplug callbacks with preempt disabled

Liu reported that running certain parts of xfstests threw the
following error:

BUG: sleeping function called from invalid context at mm/page_alloc.c:3190
in_atomic(): 1, irqs_disabled(): 0, pid: 6, name: kworker/u16:0
3 locks held by kworker/u16:0/6:
 #0:  ("writeback"){++++.+}, at: [<ffffffff8107f083>] process_one_work+0x173/0x730
 #1:  ((&(&wb->dwork)->work)){+.+.+.}, at: [<ffffffff8107f083>] process_one_work+0x173/0x730
 #2:  (&type->s_umount_key#44){+++++.}, at: [<ffffffff811e6805>] trylock_super+0x25/0x60
CPU: 5 PID: 6 Comm: kworker/u16:0 Tainted: G           OE   4.3.0+ #3
Hardware name: Red Hat KVM, BIOS Bochs 01/01/2011
Workqueue: writeback wb_workfn (flush-btrfs-108)
 ffffffff81a3abab ffff88042e282ba8 ffffffff8130191b ffffffff81a3abab
 0000000000000c76 ffff88042e282ba8 ffff88042e27c180 ffff88042e282bd8
 ffffffff8108ed95 ffff880400000004 0000000000000000 0000000000000c76
Call Trace:
 [<ffffffff8130191b>] dump_stack+0x4f/0x74
 [<ffffffff8108ed95>] ___might_sleep+0x185/0x240
 [<ffffffff8108eea2>] __might_sleep+0x52/0x90
 [<ffffffff811817e8>] __alloc_pages_nodemask+0x268/0x410
 [<ffffffff8109a43c>] ? sched_clock_local+0x1c/0x90
 [<ffffffff8109a6d1>] ? local_clock+0x21/0x40
 [<ffffffff810b9eb0>] ? __lock_release+0x420/0x510
 [<ffffffff810b534c>] ? __lock_acquired+0x16c/0x3c0
 [<ffffffff811ca265>] alloc_pages_current+0xc5/0x210
 [<ffffffffa0577105>] ? rbio_is_full+0x55/0x70 [btrfs]
 [<ffffffff810b7ed8>] ? mark_held_locks+0x78/0xa0
 [<ffffffff81666d50>] ? _raw_spin_unlock_irqrestore+0x40/0x60
 [<ffffffffa0578c0a>] full_stripe_write+0x5a/0xc0 [btrfs]
 [<ffffffffa0578ca9>] __raid56_parity_write+0x39/0x60 [btrfs]
 [<ffffffffa0578deb>] run_plug+0x11b/0x140 [btrfs]
 [<ffffffffa0578e33>] btrfs_raid_unplug+0x23/0x70 [btrfs]
 [<ffffffff812d36c2>] blk_flush_plug_list+0x82/0x1f0
 [<ffffffff812e0349>] blk_sq_make_request+0x1f9/0x740
 [<ffffffff812ceba2>] ? generic_make_request_checks+0x222/0x7c0
 [<ffffffff812cf264>] ? blk_queue_enter+0x124/0x310
 [<ffffffff812cf1d2>] ? blk_queue_enter+0x92/0x310
 [<ffffffff812d0ae2>] generic_make_request+0x172/0x2c0
 [<ffffffff812d0ad4>] ? generic_make_request+0x164/0x2c0
 [<ffffffff812d0ca0>] submit_bio+0x70/0x140
 [<ffffffffa0577b29>] ? rbio_add_io_page+0x99/0x150 [btrfs]
 [<ffffffffa0578a89>] finish_rmw+0x4d9/0x600 [btrfs]
 [<ffffffffa0578c4c>] full_stripe_write+0x9c/0xc0 [btrfs]
 [<ffffffffa057ab7f>] raid56_parity_write+0xef/0x160 [btrfs]
 [<ffffffffa052bd83>] btrfs_map_bio+0xe3/0x2d0 [btrfs]
 [<ffffffffa04fbd6d>] btrfs_submit_bio_hook+0x8d/0x1d0 [btrfs]
 [<ffffffffa05173c4>] submit_one_bio+0x74/0xb0 [btrfs]
 [<ffffffffa0517f55>] submit_extent_page+0xe5/0x1c0 [btrfs]
 [<ffffffffa0519b18>] __extent_writepage_io+0x408/0x4c0 [btrfs]
 [<ffffffffa05179c0>] ? alloc_dummy_extent_buffer+0x140/0x140 [btrfs]
 [<ffffffffa051dc88>] __extent_writepage+0x218/0x3a0 [btrfs]
 [<ffffffff810b7ed8>] ? mark_held_locks+0x78/0xa0
 [<ffffffffa051e2c9>] extent_write_cache_pages.clone.0+0x2f9/0x400 [btrfs]
 [<ffffffffa051e422>] extent_writepages+0x52/0x70 [btrfs]
 [<ffffffffa05001f0>] ? btrfs_set_inode_index+0x70/0x70 [btrfs]
 [<ffffffffa04fcc17>] btrfs_writepages+0x27/0x30 [btrfs]
 [<ffffffff81184df3>] do_writepages+0x23/0x40
 [<ffffffff81212229>] __writeback_single_inode+0x89/0x4d0
 [<ffffffff81212a60>] ? writeback_sb_inodes+0x260/0x480
 [<ffffffff81212a60>] ? writeback_sb_inodes+0x260/0x480
 [<ffffffff8121295f>] ? writeback_sb_inodes+0x15f/0x480
 [<ffffffff81212ad2>] writeback_sb_inodes+0x2d2/0x480
 [<ffffffff810b1397>] ? down_read_trylock+0x57/0x60
 [<ffffffff811e6805>] ? trylock_super+0x25/0x60
 [<ffffffff810d629f>] ? rcu_read_lock_sched_held+0x4f/0x90
 [<ffffffff81212d0c>] __writeback_inodes_wb+0x8c/0xc0
 [<ffffffff812130b5>] wb_writeback+0x2b5/0x500
 [<ffffffff810b7ed8>] ? mark_held_locks+0x78/0xa0
 [<ffffffff810660a8>] ? __local_bh_enable_ip+0x68/0xc0
 [<ffffffff81213362>] ? wb_do_writeback+0x62/0x310
 [<ffffffff812133c1>] wb_do_writeback+0xc1/0x310
 [<ffffffff8107c3d9>] ? set_worker_desc+0x79/0x90
 [<ffffffff81213842>] wb_workfn+0x92/0x330
 [<ffffffff8107f133>] process_one_work+0x223/0x730
 [<ffffffff8107f083>] ? process_one_work+0x173/0x730
 [<ffffffff8108035f>] ? worker_thread+0x18f/0x430
 [<ffffffff810802ed>] worker_thread+0x11d/0x430
 [<ffffffff810801d0>] ? maybe_create_worker+0xf0/0xf0
 [<ffffffff810801d0>] ? maybe_create_worker+0xf0/0xf0
 [<ffffffff810858df>] kthread+0xef/0x110
 [<ffffffff8108f74e>] ? schedule_tail+0x1e/0xd0
 [<ffffffff810857f0>] ? __init_kthread_worker+0x70/0x70
 [<ffffffff816673bf>] ret_from_fork+0x3f/0x70
 [<ffffffff810857f0>] ? __init_kthread_worker+0x70/0x70

The issue is that we've got the software context pinned while
calling blk_flush_plug_list(), which flushes callbacks that
are allowed to sleep. btrfs and raid has such callbacks.

Flip the checks around a bit, so we can enable preempt a bit
earlier and flush plugs without having preempt disabled.

This only affects blk-mq driven devices, and only those that
register a single queue.

Reported-by: Liu Bo <bo.li.liu@oracle.com>
Tested-by: Liu Bo <bo.li.liu@oracle.com>
Cc: stable@kernel.org
Signed-off-by: Jens Axboe <axboe@fb.com>

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 3ae09de62f19ce2ca230a89ae6137a511fc9ae16..6d6f8feb48c08ab875e67c496193a743709b0621 100644 (file)
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1291,15 +1291,16 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
                blk_mq_bio_to_request(rq, bio);
 
                /*
-                * we do limited pluging. If bio can be merged, do merge.
+                * We do limited pluging. If the bio can be merged, do that.
                 * Otherwise the existing request in the plug list will be
                 * issued. So the plug list will have one request at most
                 */
                if (plug) {
                        /*
                         * The plug list might get flushed before this. If that
-                        * happens, same_queue_rq is invalid and plug list is empty
-                        **/
+                        * happens, same_queue_rq is invalid and plug list is
+                        * empty
+                        */
                        if (same_queue_rq && !list_empty(&plug->mq_list)) {
                                old_rq = same_queue_rq;
                                list_del_init(&old_rq->queuelist);
@@ -1380,12 +1381,15 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
                blk_mq_bio_to_request(rq, bio);
                if (!request_count)
                        trace_block_plug(q);
-               else if (request_count >= BLK_MAX_REQUEST_COUNT) {
+
+               blk_mq_put_ctx(data.ctx);
+
+               if (request_count >= BLK_MAX_REQUEST_COUNT) {
                        blk_flush_plug_list(plug, false);
                        trace_block_plug(q);
                }
+
                list_add_tail(&rq->queuelist, &plug->mq_list);
-               blk_mq_put_ctx(data.ctx);
                return cookie;
        }