===================================================================
@@ -357,35 +357,37 @@ 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);
+ }
}
/**
@@ -425,7 +427,6 @@ 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;
struct bio_vec *bvl = NULL;
@@ -459,23 +460,11 @@ 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;
}
@@ -490,12 +479,6 @@ struct bio *bio_alloc_bioset(gfp_t gfp_m
unsigned long idx = 0;
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;
===================================================================
@@ -1267,6 +1267,22 @@ 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
*/
@@ -1921,16 +1937,10 @@ 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)
{
===================================================================
@@ -3441,11 +3441,10 @@ 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)
@@ -5068,7 +5067,7 @@ 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();