dm: add two stage requeue mechanism

Commit 61b6e2e5321d ("dm: fix BLK_STS_DM_REQUEUE handling when dm_io
represents split bio") reverted DM core's bio splitting back to using
bio_split()+bio_chain() because it was found that otherwise DM's
BLK_STS_DM_REQUEUE would trigger a live-lock waiting for bio
completion that would never occur.

Restore using bio_trim()+bio_inc_remaining(), like was done in commit
7dd76d1feec7 ("dm: improve bio splitting and associated IO
accounting"), but this time with proper handling for the above
scenario that is covered in more detail in the commit header for
61b6e2e5321d.

Solve this issue by adding a two staged dm_io requeue mechanism that
uses the new dm_bio_rewind() via dm_io_rewind():

1) requeue the dm_io into the requeue_list added to struct
   mapped_device, and schedule it via new added requeue work. This
   workqueue just clones the dm_io->orig_bio (which DM saves and
   ensures its end sector isn't modified). dm_io_rewind() uses the
   sectors and sectors_offset members of the dm_io that are recorded
   relative to the end of orig_bio: dm_bio_rewind()+bio_trim() are
   then used to make that cloned bio reflect the subset of the
   original bio that is represented by the dm_io that is being
   requeued.

2) the 2nd stage requeue is same with original requeue, but
   io->orig_bio points to new cloned bio (which matches the requeued
   dm_io as described above).

This allows DM core to shift the need for bio cloning from bio-split
time (during IO submission) to the less likely BLK_STS_DM_REQUEUE
handling (after IO completes with that error).

Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>

1 files changed, 12 insertions, 3 deletions

diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h
index 688aeba248d7..8ef780a6baae 100644
--- a/drivers/md/dm-core.h
+++ b/drivers/md/dm-core.h
@@ -22,6 +22,8 @@
 
 #define DM_RESERVED_MAX_IOS		1024
 
+struct dm_io;
+
 struct dm_kobject_holder {
 	struct kobject kobj;
 	struct completion completion;
@@ -91,6 +93,14 @@ struct mapped_device {
 	spinlock_t deferred_lock;
 	struct bio_list deferred;
 
+	/*
+	 * requeue work context is needed for cloning one new bio
+	 * to represent the dm_io to be requeued, since each
+	 * dm_io may point to the original bio from FS.
+	 */
+	struct work_struct requeue_work;
+	struct dm_io *requeue_list;
+
 	void *interface_ptr;
 
 	/*
@@ -275,7 +285,6 @@ struct dm_io {
 	atomic_t io_count;
 	struct mapped_device *md;
 
-	struct bio *split_bio;
 	/* The three fields represent mapped part of original bio */
 	struct bio *orig_bio;
 	unsigned int sector_offset; /* offset to end of orig_bio */
@@ -303,6 +312,8 @@ static inline void dm_io_set_flag(struct dm_io *io, unsigned int bit)
 	io->flags |= (1U << bit);
 }
 
+void dm_io_rewind(struct dm_io *io, struct bio_set *bs);
+
 static inline struct completion *dm_get_completion_from_kobject(struct kobject *kobj)
 {
 	return &container_of(kobj, struct dm_kobject_holder, kobj)->completion;
@@ -319,6 +330,4 @@ extern atomic_t dm_global_event_nr;
 extern wait_queue_head_t dm_global_eventq;
 void dm_issue_global_event(void);
 
-void dm_bio_rewind(struct bio *bio, unsigned bytes);
-
 #endif