The block layer uses per-process bio list to avoid recursion in
generic_make_request. When generic_make_request is called recursively,
the bio is added to current->bio_list and generic_make_request returns
immediately. The top-level instance of generic_make_request takes bios
from current->bio_list and processes them.
Commit df2cb6daa4 ("block: Avoid deadlocks with bio allocation by
stacking drivers") created a workqueue for every bio set and code
in bio_alloc_bioset() that tries to resolve some low-memory deadlocks by
redirecting bios queued on current->bio_list to the workqueue if the
system is low on memory. However another deadlock (see below **) may
happen, without any low memory condition, because generic_make_request
is queuing bios to current->bio_list (rather than submitting them).
Fix this deadlock by redirecting any bios on current->bio_list to the
bio_set's rescue workqueue on every schedule call. Consequently, when
the process blocks on a mutex, the bios queued on current->bio_list are
dispatched to independent workqueus and they can complete without
waiting for the mutex to be available.
Also, now we can remove punt_bios_to_rescuer() and bio_alloc_bioset()'s
calls to it because bio_alloc_bioset() will implicitly punt all bios on
current->bio_list if it performs a blocking allocation.
** Here is the dm-snapshot deadlock that was observed:
1) Process A sends one-page read bio to the dm-snapshot target. The bio
spans snapshot chunk boundary and so it is split to two bios by device
mapper.
2) Device mapper creates the first sub-bio and sends it to the snapshot
driver.
3) The function snapshot_map calls track_chunk (that allocates a structure
dm_snap_tracked_chunk and adds it to tracked_chunk_hash) and then remaps
the bio to the underlying device and exits with DM_MAPIO_REMAPPED.
4) The remapped bio is submitted with generic_make_request, but it isn't
issued - it is added to current->bio_list instead.
5) Meanwhile, process B (dm's kcopyd) executes pending_complete for the
chunk affected be the first remapped bio, it takes down_write(&s->lock)
and then loops in __check_for_conflicting_io, waiting for
dm_snap_tracked_chunk created in step 3) to be released.
6) Process A continues, it creates a second sub-bio for the rest of the
original bio.
7) snapshot_map is called for this new bio, it waits on
down_write(&s->lock) that is held by Process B (in step 5).
Fixes: https://bugzilla.redhat.com/show_bug.cgi?id=1267650
Signed-off-by: Mikulas Patocka <mpatocka@xxxxxxxxxx>
Signed-off-by: Mike Snitzer <snitzer@xxxxxxxxxx>
Depends-on: df2cb6daa4 ("block: Avoid deadlocks with bio allocation by stacking drivers")
Cc: stable@xxxxxxxxxxxxxxx
---
block/bio.c | 77 +++++++++++++++++++------------------------------
include/linux/blkdev.h | 24 ++++++++++-----
kernel/sched/core.c | 7 +---
3 files changed, 50 insertions(+), 58 deletions(-)
Index: linux-4.7-rc6/block/bio.c
===================================================================
--- linux-4.7-rc6.orig/block/bio.c 2016-07-04 23:00:17.000000000 +0200
+++ linux-4.7-rc6/block/bio.c 2016-07-05 00:02:01.000000000 +0200
@@ -349,35 +349,37 @@ static void bio_alloc_rescue(struct work
}
}
-static void punt_bios_to_rescuer(struct bio_set *bs)
+/**
+ * blk_flush_bio_list
+ * @tsk: task_struct whose bio_list must be flushed
+ *
+ * Pop bios queued on @tsk->bio_list and submit each of them to
+ * their rescue workqueue.
+ *
+ * If the bio doesn't have a bio_set, we leave it on @tsk->bio_list.
+ * If the bio is allocated from fs_bio_set, we must leave it to avoid
+ * deadlock on loopback block device.
+ * Stacking bio drivers should use bio_set, so this shouldn't be
+ * an issue.
+ */
+void blk_flush_bio_list(struct task_struct *tsk)
{
- struct bio_list punt, nopunt;
struct bio *bio;
+ struct bio_list list = *tsk->bio_list;
+ bio_list_init(tsk->bio_list);
- /*
- * In order to guarantee forward progress we must punt only bios that
- * were allocated from this bio_set; otherwise, if there was a bio on
- * there for a stacking driver higher up in the stack, processing it
- * could require allocating bios from this bio_set, and doing that from
- * our own rescuer would be bad.
- *
- * Since bio lists are singly linked, pop them all instead of trying to
- * remove from the middle of the list:
- */
-
- bio_list_init(&punt);
- bio_list_init(&nopunt);
-
- while ((bio = bio_list_pop(current->bio_list)))
- bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio);
-
- *current->bio_list = nopunt;
-
- spin_lock(&bs->rescue_lock);
- bio_list_merge(&bs->rescue_list, &punt);
- spin_unlock(&bs->rescue_lock);
+ while ((bio = bio_list_pop(&list))) {
+ struct bio_set *bs = bio->bi_pool;
+ if (unlikely(!bs) || bs == fs_bio_set) {
+ bio_list_add(tsk->bio_list, bio);
+ continue;
+ }
- queue_work(bs->rescue_workqueue, &bs->rescue_work);
+ spin_lock(&bs->rescue_lock);
+ bio_list_add(&bs->rescue_list, bio);
+ queue_work(bs->rescue_workqueue, &bs->rescue_work);
+ spin_unlock(&bs->rescue_lock);
+ }
}
/**
@@ -417,7 +419,6 @@ static void punt_bios_to_rescuer(struct
*/
struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
{
- gfp_t saved_gfp = gfp_mask;
unsigned front_pad;
unsigned inline_vecs;
unsigned long idx = BIO_POOL_NONE;
@@ -452,23 +453,11 @@ struct bio *bio_alloc_bioset(gfp_t gfp_m
* reserve.
*
* We solve this, and guarantee forward progress, with a rescuer
- * workqueue per bio_set. If we go to allocate and there are
- * bios on current->bio_list, we first try the allocation
- * without __GFP_DIRECT_RECLAIM; if that fails, we punt those
- * bios we would be blocking to the rescuer workqueue before
- * we retry with the original gfp_flags.
+ * workqueue per bio_set. If an allocation would block (due to
+ * __GFP_DIRECT_RECLAIM) the scheduler will first punt all bios
+ * on current->bio_list to the rescuer workqueue.
*/
-
- if (current->bio_list && !bio_list_empty(current->bio_list))
- gfp_mask &= ~__GFP_DIRECT_RECLAIM;
-
p = mempool_alloc(bs->bio_pool, gfp_mask);
- if (!p && gfp_mask != saved_gfp) {
- punt_bios_to_rescuer(bs);
- gfp_mask = saved_gfp;
- p = mempool_alloc(bs->bio_pool, gfp_mask);
- }
-
front_pad = bs->front_pad;
inline_vecs = BIO_INLINE_VECS;
}
@@ -481,12 +470,6 @@ struct bio *bio_alloc_bioset(gfp_t gfp_m
if (nr_iovecs > inline_vecs) {
bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, bs->bvec_pool);
- if (!bvl && gfp_mask != saved_gfp) {
- punt_bios_to_rescuer(bs);
- gfp_mask = saved_gfp;
- bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, bs->bvec_pool);
- }
-
if (unlikely(!bvl))
goto err_free;
Index: linux-4.7-rc6/include/linux/blkdev.h
===================================================================
--- linux-4.7-rc6.orig/include/linux/blkdev.h 2016-07-04 23:00:17.000000000 +0200
+++ linux-4.7-rc6/include/linux/blkdev.h 2016-07-04 23:58:02.000000000 +0200
@@ -1114,6 +1114,22 @@ static inline bool blk_needs_flush_plug(
!list_empty(&plug->cb_list));
}
+extern void blk_flush_bio_list(struct task_struct *tsk);
+
+static inline void blk_flush_queued_io(struct task_struct *tsk)
+{
+ /*
+ * Flush any queued bios to corresponding rescue threads.
+ */
+ if (tsk->bio_list && !bio_list_empty(tsk->bio_list))
+ blk_flush_bio_list(tsk);
+ /*
+ * Flush any plugged IO that is queued.
+ */
+ if (blk_needs_flush_plug(tsk))
+ blk_schedule_flush_plug(tsk);
+}
+
/*
* tag stuff
*/
@@ -1722,16 +1738,10 @@ static inline void blk_flush_plug(struct
{
}
-static inline void blk_schedule_flush_plug(struct task_struct *task)
+static inline void blk_flush_queued_io(struct task_struct *tsk)
{
}
-
-static inline bool blk_needs_flush_plug(struct task_struct *tsk)
-{
- return false;
-}
-
static inline int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask,
sector_t *error_sector)
{
Index: linux-4.7-rc6/kernel/sched/core.c
===================================================================
--- linux-4.7-rc6.orig/kernel/sched/core.c 2016-07-04 23:00:17.000000000 +0200
+++ linux-4.7-rc6/kernel/sched/core.c 2016-07-04 23:01:29.000000000 +0200
@@ -3359,11 +3359,10 @@ static inline void sched_submit_work(str
if (!tsk->state || tsk_is_pi_blocked(tsk))
return;
/*
- * If we are going to sleep and we have plugged IO queued,
+ * If we are going to sleep and we have queued IO,
* make sure to submit it to avoid deadlocks.
*/
- if (blk_needs_flush_plug(tsk))
- blk_schedule_flush_plug(tsk);
+ blk_flush_queued_io(tsk);
}
asmlinkage __visible void __sched schedule(void)
@@ -4977,7 +4976,7 @@ long __sched io_schedule_timeout(long ti
long ret;
current->in_iowait = 1;
- blk_schedule_flush_plug(current);
+ blk_flush_queued_io(current);
delayacct_blkio_start();
rq = raw_rq();
--
dm-devel mailing list
dm-devel@xxxxxxxxxx
https://www.redhat.com/mailman/listinfo/dm-devel
