[PATCH 1/5] blk: Ensure users for current->bio_list can see the full list.

From: NeilBrown
Date: Fri Mar 10 2017 - 01:02:19 EST


Commit 79bd99596b73 ("blk: improve order of bio handling in generic_make_request()")
changed current->bio_list so that it did not contain *all* of the
queued bios, but only those submitted by the currently running
make_request_fn.

There are two places which walk the list and requeue selected bios,
and others that check if the list is empty. These are no longer
correct.

So redefine current->bio_list to point to an array of two lists, which
contain all queued bios, and adjust various code to test or walk both
lists.

Signed-off-by: NeilBrown <neilb@xxxxxxxx>
---
block/bio.c | 12 +++++++++---
block/blk-core.c | 30 ++++++++++++++++++------------
drivers/md/dm.c | 29 ++++++++++++++++-------------
drivers/md/raid10.c | 3 ++-
4 files changed, 45 insertions(+), 29 deletions(-)

diff --git a/block/bio.c b/block/bio.c
index 5eec5e08417f..e75878f8b14a 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -376,10 +376,14 @@ static void punt_bios_to_rescuer(struct bio_set *bs)
bio_list_init(&punt);
bio_list_init(&nopunt);

- while ((bio = bio_list_pop(current->bio_list)))
+ while ((bio = bio_list_pop(&current->bio_list[0])))
bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio);
+ current->bio_list[0] = nopunt;

- *current->bio_list = nopunt;
+ bio_list_init(&nopunt);
+ while ((bio = bio_list_pop(&current->bio_list[1])))
+ bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio);
+ current->bio_list[1] = nopunt;

spin_lock(&bs->rescue_lock);
bio_list_merge(&bs->rescue_list, &punt);
@@ -466,7 +470,9 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
* we retry with the original gfp_flags.
*/

- if (current->bio_list && !bio_list_empty(current->bio_list))
+ if (current->bio_list &&
+ (!bio_list_empty(&current->bio_list[0]) ||
+ !bio_list_empty(&current->bio_list[1])))
gfp_mask &= ~__GFP_DIRECT_RECLAIM;

p = mempool_alloc(bs->bio_pool, gfp_mask);
diff --git a/block/blk-core.c b/block/blk-core.c
index 0eeb99ef654f..d772c221cc17 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1973,7 +1973,14 @@ generic_make_request_checks(struct bio *bio)
*/
blk_qc_t generic_make_request(struct bio *bio)
{
- struct bio_list bio_list_on_stack;
+ /*
+ * bio_list_on_stack[0] contains bios submitted by the current
+ * make_request_fn.
+ * bio_list_on_stack[1] contains bios that were submitted before
+ * the current make_request_fn, but that haven't been processed
+ * yet.
+ */
+ struct bio_list bio_list_on_stack[2];
blk_qc_t ret = BLK_QC_T_NONE;

if (!generic_make_request_checks(bio))
@@ -1990,7 +1997,7 @@ blk_qc_t generic_make_request(struct bio *bio)
* should be added at the tail
*/
if (current->bio_list) {
- bio_list_add(current->bio_list, bio);
+ bio_list_add(&current->bio_list[0], bio);
goto out;
}

@@ -2009,18 +2016,17 @@ blk_qc_t generic_make_request(struct bio *bio)
* bio_list, and call into ->make_request() again.
*/
BUG_ON(bio->bi_next);
- bio_list_init(&bio_list_on_stack);
- current->bio_list = &bio_list_on_stack;
+ bio_list_init(&bio_list_on_stack[0]);
+ current->bio_list = bio_list_on_stack;
do {
struct request_queue *q = bdev_get_queue(bio->bi_bdev);

if (likely(blk_queue_enter(q, false) == 0)) {
- struct bio_list hold;
struct bio_list lower, same;

/* Create a fresh bio_list for all subordinate requests */
- hold = bio_list_on_stack;
- bio_list_init(&bio_list_on_stack);
+ bio_list_on_stack[1] = bio_list_on_stack[0];
+ bio_list_init(&bio_list_on_stack[0]);
ret = q->make_request_fn(q, bio);

blk_queue_exit(q);
@@ -2030,19 +2036,19 @@ blk_qc_t generic_make_request(struct bio *bio)
*/
bio_list_init(&lower);
bio_list_init(&same);
- while ((bio = bio_list_pop(&bio_list_on_stack)) != NULL)
+ while ((bio = bio_list_pop(&bio_list_on_stack[0])) != 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_list_merge(&bio_list_on_stack[0], &lower);
+ bio_list_merge(&bio_list_on_stack[0], &same);
+ bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]);
} else {
bio_io_error(bio);
}
- bio = bio_list_pop(current->bio_list);
+ bio = bio_list_pop(&bio_list_on_stack[0]);
} while (bio);
current->bio_list = NULL; /* deactivate */

diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index f4ffd1eb8f44..dfb75979e455 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -989,26 +989,29 @@ static void flush_current_bio_list(struct blk_plug_cb *cb, bool from_schedule)
struct dm_offload *o = container_of(cb, struct dm_offload, cb);
struct bio_list list;
struct bio *bio;
+ int i;

INIT_LIST_HEAD(&o->cb.list);

if (unlikely(!current->bio_list))
return;

- list = *current->bio_list;
- bio_list_init(current->bio_list);
-
- while ((bio = bio_list_pop(&list))) {
- struct bio_set *bs = bio->bi_pool;
- if (unlikely(!bs) || bs == fs_bio_set) {
- bio_list_add(current->bio_list, bio);
- continue;
+ for (i = 0; i < 2; i++) {
+ list = current->bio_list[i];
+ bio_list_init(&current->bio_list[i]);
+
+ while ((bio = bio_list_pop(&list))) {
+ struct bio_set *bs = bio->bi_pool;
+ if (unlikely(!bs) || bs == fs_bio_set) {
+ bio_list_add(&current->bio_list[i], bio);
+ continue;
+ }
+
+ 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);
}
-
- 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);
}
}

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 063c43d83b72..0536658c9d40 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -974,7 +974,8 @@ static void wait_barrier(struct r10conf *conf)
!conf->barrier ||
(atomic_read(&conf->nr_pending) &&
current->bio_list &&
- !bio_list_empty(current->bio_list)),
+ (!bio_list_empty(&current->bio_list[0]) ||
+ !bio_list_empty(&current->bio_list[1]))),
conf->resync_lock);
conf->nr_waiting--;
if (!conf->nr_waiting)