From 9500d5e9a7ccd1f4397f927ffdc8d378955d477c Mon Sep 17 00:00:00 2001 From: Jack Wang Date: Wed, 14 Dec 2016 16:55:52 +0100 Subject: [PATCH] block: fix deadlock between freeze_array() and wait_barrier() When we call wait_barrier, we might have some bios waiting in current->bio_list, which prevents the array_freeze call to complete. Those can only be internal READs, which have already passed the wait_barrier call (thus incrementing nr_pending), but still were not submitted to the lower level, due to generic_make_request logic to avoid recursive calls. In such case, we have a deadlock: - array_frozen is already set to 1, so wait_barrier unconditionally waits, so - internal READ bios will not be submitted, thus freeze_array will never completes. To fix this, modify generic_make_request to always sort bio_list_on_stack first with lowest level, then higher, until same level. Suggested-by: Neil Brown Signed-off-by: Jack Wang --- block/blk-core.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/block/blk-core.c b/block/blk-core.c index e8d15d8..5a6390a 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2064,10 +2064,30 @@ blk_qc_t generic_make_request(struct bio *bio) struct request_queue *q = bdev_get_queue(bio->bi_bdev); if (likely(blk_queue_enter(q, __GFP_DIRECT_RECLAIM) == 0)) { + struct bio_list lower, same, hold; + + /* Create a fresh bio_list for all subordinate requests */ + bio_list_init(&hold); + bio_list_merge(&hold, &bio_list_on_stack); + bio_list_init(&bio_list_on_stack); ret = q->make_request_fn(q, bio); blk_queue_exit(q); + /* sort new bios into those for a lower level + * and those for the same level + */ + bio_list_init(&lower); + bio_list_init(&same); + while ((bio = bio_list_pop(&bio_list_on_stack)) != NULL) + if (q == bdev_get_queue(bio->bi_bdev)) + bio_list_add(&same, bio); + else + bio_list_add(&lower, bio); + /* now assemble so we handle the lowest level first */ + bio_list_merge(&bio_list_on_stack, &lower); + bio_list_merge(&bio_list_on_stack, &same); + bio_list_merge(&bio_list_on_stack, &hold); bio = bio_list_pop(current->bio_list); } else { -- 2.7.4