There were reports about heavy stack use by recursive calling .bi_end_io().[1][2][3]
Also these patches[1] [2] [3] were posted for addressing the issue. And the idea is basically similar, all serializes the recursive calling of .bi_end_io() by percpu list. This patch still takes the same idea, but uses bio_list to implement it, which turns out more simple and the code becomes more readable meantime. xfstests(-g auto) is run with this patch and no regression is found on ext4, but when testing btrfs, generic/224 and generic/323 causes kernel oops. [1] http://marc.info/?t=121428502000004&r=1&w=2 [2] http://marc.info/?l=dm-devel&m=139595190620008&w=2 [3] http://marc.info/?t=145974644100001&r=1&w=2 Cc: Shaun Tancheff <shaun.tanch...@seagate.com> Cc: Christoph Hellwig <h...@infradead.org> Cc: Mikulas Patocka <mpato...@redhat.com> Signed-off-by: Ming Lei <ming....@canonical.com> --- V1: - change to RFC - fix when unwind_bio_endio() is called recursively - run xfstest again: no regression found on ext4, but generic/323 and generic/224 cause kernel oops block/bio.c | 44 ++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 42 insertions(+), 2 deletions(-) diff --git a/block/bio.c b/block/bio.c index f124a0a..e2d0970 100644 --- a/block/bio.c +++ b/block/bio.c @@ -68,6 +68,8 @@ static DEFINE_MUTEX(bio_slab_lock); static struct bio_slab *bio_slabs; static unsigned int bio_slab_nr, bio_slab_max; +static DEFINE_PER_CPU(struct bio_list *, bio_end_list) = { NULL }; + static struct kmem_cache *bio_find_or_create_slab(unsigned int extra_size) { unsigned int sz = sizeof(struct bio) + extra_size; @@ -1737,6 +1739,45 @@ static inline bool bio_remaining_done(struct bio *bio) return false; } +/* disable local irq when manipulating the percpu bio_list */ +static void unwind_bio_endio(struct bio *bio) +{ + struct bio_list *bl; + unsigned long flags; + bool clear_list = false; + + preempt_disable(); + local_irq_save(flags); + + bl = this_cpu_read(bio_end_list); + if (!bl) { + struct bio_list bl_in_stack; + + bl = &bl_in_stack; + bio_list_init(bl); + this_cpu_write(bio_end_list, bl); + clear_list = true; + } else { + bio_list_add(bl, bio); + goto out; + } + + while (bio) { + local_irq_restore(flags); + + if (bio->bi_end_io) + bio->bi_end_io(bio); + + local_irq_save(flags); + bio = bio_list_pop(bl); + } + if (clear_list) + this_cpu_write(bio_end_list, NULL); + out: + local_irq_restore(flags); + preempt_enable(); +} + /** * bio_endio - end I/O on a bio * @bio: bio @@ -1765,8 +1806,7 @@ again: goto again; } - if (bio->bi_end_io) - bio->bi_end_io(bio); + unwind_bio_endio(bio); } EXPORT_SYMBOL(bio_endio); -- 1.9.1
