Merge tag 'for-5.6/dm-fixes' of git://git.kernel.org/pub/scm/linux/ke…

…rnel/git/device-mapper/linux-dm

Pull device mapper fixes from Mike Snitzer:

 - Fix request-based DM's congestion_fn and actually wire it up to the
   bdi.

 - Extend dm-bio-record to track additional struct bio members needed by
   DM integrity target.

 - Fix DM core to properly advertise that a device is suspended during
   unload (between the presuspend and postsuspend hooks). This change is
   a prereq for related DM integrity and DM writecache fixes. It
   elevates DM integrity's 'suspending' state tracking to DM core.

 - Four stable fixes for DM integrity target.

 - Fix crash in DM cache target due to incorrect work item cancelling.

 - Fix DM thin metadata lockdep warning that was introduced during 5.6
   merge window.

 - Fix DM zoned target's chunk work refcounting that regressed during
   recent conversion to refcount_t.

 - Bump the minor version for DM core and all target versions that have
   seen interface changes or important fixes during the 5.6 cycle.

* tag 'for-5.6/dm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
  dm: bump version of core and various targets
  dm: fix congested_fn for request-based device
  dm integrity: use dm_bio_record and dm_bio_restore
  dm bio record: save/restore bi_end_io and bi_integrity
  dm zoned: Fix reference counter initial value of chunk works
  dm writecache: verify watermark during resume
  dm: report suspended device during destroy
  dm thin metadata: fix lockdep complaint
  dm cache: fix a crash due to incorrect work item cancelling
  dm integrity: fix invalid table returned due to argument count mismatch
  dm integrity: fix a deadlock due to offloading to an incorrect workqueue
  dm integrity: fix recalculation when moving from journal mode to bitmap mode

drivers/md/dm-bio-record.h

@@ -20,8 +20,13 @@
 struct dm_bio_details {
 	struct gendisk *bi_disk;
 	u8 bi_partno;
+	int __bi_remaining;
 	unsigned long bi_flags;
 	struct bvec_iter bi_iter;
+	bio_end_io_t *bi_end_io;
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+	struct bio_integrity_payload *bi_integrity;
+#endif
 };
 
 static inline void dm_bio_record(struct dm_bio_details *bd, struct bio *bio)
@@ -30,6 +35,11 @@ static inline void dm_bio_record(struct dm_bio_details *bd, struct bio *bio)
 	bd->bi_partno = bio->bi_partno;
 	bd->bi_flags = bio->bi_flags;
 	bd->bi_iter = bio->bi_iter;
+	bd->__bi_remaining = atomic_read(&bio->__bi_remaining);
+	bd->bi_end_io = bio->bi_end_io;
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+	bd->bi_integrity = bio_integrity(bio);
+#endif
 }
 
 static inline void dm_bio_restore(struct dm_bio_details *bd, struct bio *bio)
@@ -38,6 +48,11 @@ static inline void dm_bio_restore(struct dm_bio_details *bd, struct bio *bio)
 	bio->bi_partno = bd->bi_partno;
 	bio->bi_flags = bd->bi_flags;
 	bio->bi_iter = bd->bi_iter;
+	atomic_set(&bio->__bi_remaining, bd->__bi_remaining);
+	bio->bi_end_io = bd->bi_end_io;
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+	bio->bi_integrity = bd->bi_integrity;
+#endif
 }
 
 #endif

drivers/md/dm-cache-target.c

@@ -2846,8 +2846,8 @@ static void cache_postsuspend(struct dm_target *ti)
 	prevent_background_work(cache);
 	BUG_ON(atomic_read(&cache->nr_io_migrations));
 
-	cancel_delayed_work(&cache->waker);
-	flush_workqueue(cache->wq);
+	cancel_delayed_work_sync(&cache->waker);
+	drain_workqueue(cache->wq);
 	WARN_ON(cache->tracker.in_flight);
 
 	/*
@@ -3492,7 +3492,7 @@ static void cache_io_hints(struct dm_target *ti, struct queue_limits *limits)
 
 static struct target_type cache_target = {
 	.name = "cache",
-	.version = {2, 1, 0},
+	.version = {2, 2, 0},
 	.module = THIS_MODULE,
 	.ctr = cache_ctr,
 	.dtr = cache_dtr,

drivers/md/dm-integrity.c

@@ -6,6 +6,8 @@
  * This file is released under the GPL.
  */
 
+#include "dm-bio-record.h"
+
 #include <linux/compiler.h>
 #include <linux/module.h>
 #include <linux/device-mapper.h>
@@ -201,17 +203,19 @@ struct dm_integrity_c {
 	__u8 log2_blocks_per_bitmap_bit;
 
 	unsigned char mode;
-	int suspending;
 
 	int failed;
 
 	struct crypto_shash *internal_hash;
 
+	struct dm_target *ti;
+
 	/* these variables are locked with endio_wait.lock */
 	struct rb_root in_progress;
 	struct list_head wait_list;
 	wait_queue_head_t endio_wait;
 	struct workqueue_struct *wait_wq;
+	struct workqueue_struct *offload_wq;
 
 	unsigned char commit_seq;
 	commit_id_t commit_ids[N_COMMIT_IDS];
@@ -293,11 +297,7 @@ struct dm_integrity_io {
 
 	struct completion *completion;
 
-	struct gendisk *orig_bi_disk;
-	u8 orig_bi_partno;
-	bio_end_io_t *orig_bi_end_io;
-	struct bio_integrity_payload *orig_bi_integrity;
-	struct bvec_iter orig_bi_iter;
+	struct dm_bio_details bio_details;
 };
 
 struct journal_completion {
@@ -1439,7 +1439,7 @@ static void dec_in_flight(struct dm_integrity_io *dio)
 			dio->range.logical_sector += dio->range.n_sectors;
 			bio_advance(bio, dio->range.n_sectors << SECTOR_SHIFT);
 			INIT_WORK(&dio->work, integrity_bio_wait);
-			queue_work(ic->wait_wq, &dio->work);
+			queue_work(ic->offload_wq, &dio->work);
 			return;
 		}
 		do_endio_flush(ic, dio);
@@ -1450,14 +1450,9 @@ static void integrity_end_io(struct bio *bio)
 {
 	struct dm_integrity_io *dio = dm_per_bio_data(bio, sizeof(struct dm_integrity_io));
 
-	bio->bi_iter = dio->orig_bi_iter;
-	bio->bi_disk = dio->orig_bi_disk;
-	bio->bi_partno = dio->orig_bi_partno;
-	if (dio->orig_bi_integrity) {
-		bio->bi_integrity = dio->orig_bi_integrity;
+	dm_bio_restore(&dio->bio_details, bio);
+	if (bio->bi_integrity)
 		bio->bi_opf |= REQ_INTEGRITY;
-	}
-	bio->bi_end_io = dio->orig_bi_end_io;
 
 	if (dio->completion)
 		complete(dio->completion);
@@ -1542,7 +1537,7 @@ static void integrity_metadata(struct work_struct *w)
 			}
 		}
 
-		__bio_for_each_segment(bv, bio, iter, dio->orig_bi_iter) {
+		__bio_for_each_segment(bv, bio, iter, dio->bio_details.bi_iter) {
 			unsigned pos;
 			char *mem, *checksums_ptr;
 
@@ -1586,7 +1581,7 @@ static void integrity_metadata(struct work_struct *w)
 		if (likely(checksums != checksums_onstack))
 			kfree(checksums);
 	} else {
-		struct bio_integrity_payload *bip = dio->orig_bi_integrity;
+		struct bio_integrity_payload *bip = dio->bio_details.bi_integrity;
 
 		if (bip) {
 			struct bio_vec biv;
@@ -1865,7 +1860,7 @@ static void dm_integrity_map_continue(struct dm_integrity_io *dio, bool from_map
 
 	if (need_sync_io && from_map) {
 		INIT_WORK(&dio->work, integrity_bio_wait);
-		queue_work(ic->metadata_wq, &dio->work);
+		queue_work(ic->offload_wq, &dio->work);
 		return;
 	}
 
@@ -2005,20 +2000,13 @@ static void dm_integrity_map_continue(struct dm_integrity_io *dio, bool from_map
 	} else
 		dio->completion = NULL;
 
-	dio->orig_bi_iter = bio->bi_iter;
-
-	dio->orig_bi_disk = bio->bi_disk;
-	dio->orig_bi_partno = bio->bi_partno;
+	dm_bio_record(&dio->bio_details, bio);
 	bio_set_dev(bio, ic->dev->bdev);
-
-	dio->orig_bi_integrity = bio_integrity(bio);
 	bio->bi_integrity = NULL;
 	bio->bi_opf &= ~REQ_INTEGRITY;
-
-	dio->orig_bi_end_io = bio->bi_end_io;
 	bio->bi_end_io = integrity_end_io;
-
 	bio->bi_iter.bi_size = dio->range.n_sectors << SECTOR_SHIFT;
+
 	generic_make_request(bio);
 
 	if (need_sync_io) {
@@ -2315,7 +2303,7 @@ static void integrity_writer(struct work_struct *w)
 	unsigned prev_free_sectors;
 
 	/* the following test is not needed, but it tests the replay code */
-	if (READ_ONCE(ic->suspending) && !ic->meta_dev)
+	if (unlikely(dm_suspended(ic->ti)) && !ic->meta_dev)
 		return;
 
 	spin_lock_irq(&ic->endio_wait.lock);
@@ -2376,7 +2364,7 @@ static void integrity_recalc(struct work_struct *w)
 
 next_chunk:
 
-	if (unlikely(READ_ONCE(ic->suspending)))
+	if (unlikely(dm_suspended(ic->ti)))
 		goto unlock_ret;
 
 	range.logical_sector = le64_to_cpu(ic->sb->recalc_sector);
@@ -2501,7 +2489,7 @@ static void bitmap_block_work(struct work_struct *w)
 				    dio->range.n_sectors, BITMAP_OP_TEST_ALL_SET)) {
 			remove_range(ic, &dio->range);
 			INIT_WORK(&dio->work, integrity_bio_wait);
-			queue_work(ic->wait_wq, &dio->work);
+			queue_work(ic->offload_wq, &dio->work);
 		} else {
 			block_bitmap_op(ic, ic->journal, dio->range.logical_sector,
 					dio->range.n_sectors, BITMAP_OP_SET);
@@ -2524,7 +2512,7 @@ static void bitmap_block_work(struct work_struct *w)
 
 		remove_range(ic, &dio->range);
 		INIT_WORK(&dio->work, integrity_bio_wait);
-		queue_work(ic->wait_wq, &dio->work);
+		queue_work(ic->offload_wq, &dio->work);
 	}
 
 	queue_delayed_work(ic->commit_wq, &ic->bitmap_flush_work, ic->bitmap_flush_interval);
@@ -2804,8 +2792,6 @@ static void dm_integrity_postsuspend(struct dm_target *ti)
 
 	del_timer_sync(&ic->autocommit_timer);
 
-	WRITE_ONCE(ic->suspending, 1);
-
 	if (ic->recalc_wq)
 		drain_workqueue(ic->recalc_wq);
 
@@ -2834,8 +2820,6 @@ static void dm_integrity_postsuspend(struct dm_target *ti)
 #endif
 	}
 
-	WRITE_ONCE(ic->suspending, 0);
-
 	BUG_ON(!RB_EMPTY_ROOT(&ic->in_progress));
 
 	ic->journal_uptodate = true;
@@ -2888,17 +2872,24 @@ static void dm_integrity_resume(struct dm_target *ti)
 	} else {
 		replay_journal(ic);
 		if (ic->mode == 'B') {
-			int mode;
 			ic->sb->flags |= cpu_to_le32(SB_FLAG_DIRTY_BITMAP);
 			ic->sb->log2_blocks_per_bitmap_bit = ic->log2_blocks_per_bitmap_bit;
 			r = sync_rw_sb(ic, REQ_OP_WRITE, REQ_FUA);
 			if (unlikely(r))
 				dm_integrity_io_error(ic, "writing superblock", r);
 
-			mode = ic->recalculate_flag ? BITMAP_OP_SET : BITMAP_OP_CLEAR;
-			block_bitmap_op(ic, ic->journal, 0, ic->provided_data_sectors, mode);
-			block_bitmap_op(ic, ic->recalc_bitmap, 0, ic->provided_data_sectors, mode);
-			block_bitmap_op(ic, ic->may_write_bitmap, 0, ic->provided_data_sectors, mode);
+			block_bitmap_op(ic, ic->journal, 0, ic->provided_data_sectors, BITMAP_OP_CLEAR);
+			block_bitmap_op(ic, ic->recalc_bitmap, 0, ic->provided_data_sectors, BITMAP_OP_CLEAR);
+			block_bitmap_op(ic, ic->may_write_bitmap, 0, ic->provided_data_sectors, BITMAP_OP_CLEAR);
+			if (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING) &&
+			    le64_to_cpu(ic->sb->recalc_sector) < ic->provided_data_sectors) {
+				block_bitmap_op(ic, ic->journal, le64_to_cpu(ic->sb->recalc_sector),
+						ic->provided_data_sectors - le64_to_cpu(ic->sb->recalc_sector), BITMAP_OP_SET);
+				block_bitmap_op(ic, ic->recalc_bitmap, le64_to_cpu(ic->sb->recalc_sector),
+						ic->provided_data_sectors - le64_to_cpu(ic->sb->recalc_sector), BITMAP_OP_SET);
+				block_bitmap_op(ic, ic->may_write_bitmap, le64_to_cpu(ic->sb->recalc_sector),
+						ic->provided_data_sectors - le64_to_cpu(ic->sb->recalc_sector), BITMAP_OP_SET);
+			}
 			rw_journal_sectors(ic, REQ_OP_WRITE, REQ_FUA | REQ_SYNC, 0,
 					   ic->n_bitmap_blocks * (BITMAP_BLOCK_SIZE >> SECTOR_SHIFT), NULL);
 		}
@@ -2967,7 +2958,7 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type,
 			DMEMIT(" meta_device:%s", ic->meta_dev->name);
 		if (ic->sectors_per_block != 1)
 			DMEMIT(" block_size:%u", ic->sectors_per_block << SECTOR_SHIFT);
-		if (ic->recalculate_flag)
+		if (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING))
 			DMEMIT(" recalculate");
 		DMEMIT(" journal_sectors:%u", ic->initial_sectors - SB_SECTORS);
 		DMEMIT(" interleave_sectors:%u", 1U << ic->sb->log2_interleave_sectors);
@@ -3623,6 +3614,7 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	}
 	ti->private = ic;
 	ti->per_io_data_size = sizeof(struct dm_integrity_io);
+	ic->ti = ti;
 
 	ic->in_progress = RB_ROOT;
 	INIT_LIST_HEAD(&ic->wait_list);
@@ -3836,6 +3828,14 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv)
 		goto bad;
 	}
 
+	ic->offload_wq = alloc_workqueue("dm-integrity-offload", WQ_MEM_RECLAIM,
+					  METADATA_WORKQUEUE_MAX_ACTIVE);
+	if (!ic->offload_wq) {
+		ti->error = "Cannot allocate workqueue";
+		r = -ENOMEM;
+		goto bad;
+	}
+
 	ic->commit_wq = alloc_workqueue("dm-integrity-commit", WQ_MEM_RECLAIM, 1);
 	if (!ic->commit_wq) {
 		ti->error = "Cannot allocate workqueue";
@@ -4140,6 +4140,8 @@ static void dm_integrity_dtr(struct dm_target *ti)
 		destroy_workqueue(ic->metadata_wq);
 	if (ic->wait_wq)
 		destroy_workqueue(ic->wait_wq);
+	if (ic->offload_wq)
+		destroy_workqueue(ic->offload_wq);
 	if (ic->commit_wq)
 		destroy_workqueue(ic->commit_wq);
 	if (ic->writer_wq)
@@ -4200,7 +4202,7 @@ static void dm_integrity_dtr(struct dm_target *ti)
 
 static struct target_type integrity_target = {
 	.name			= "integrity",
-	.version		= {1, 4, 0},
+	.version		= {1, 5, 0},
 	.module			= THIS_MODULE,
 	.features		= DM_TARGET_SINGLETON | DM_TARGET_INTEGRITY,
 	.ctr			= dm_integrity_ctr,

drivers/md/dm-mpath.c

@@ -2053,7 +2053,7 @@ static int multipath_busy(struct dm_target *ti)
  *---------------------------------------------------------------*/
 static struct target_type multipath_target = {
 	.name = "multipath",
-	.version = {1, 13, 0},
+	.version = {1, 14, 0},
 	.features = DM_TARGET_SINGLETON | DM_TARGET_IMMUTABLE |
 		    DM_TARGET_PASSES_INTEGRITY,
 	.module = THIS_MODULE,

drivers/md/dm-thin-metadata.c

@@ -960,9 +960,9 @@ int dm_pool_metadata_close(struct dm_pool_metadata *pmd)
 			DMWARN("%s: __commit_transaction() failed, error = %d",
 			       __func__, r);
 	}
+	pmd_write_unlock(pmd);
 	if (!pmd->fail_io)
 		__destroy_persistent_data_objects(pmd);
-	pmd_write_unlock(pmd);
 
 	kfree(pmd);
 	return 0;

drivers/md/dm-verity-target.c

@@ -1221,7 +1221,7 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv)
 
 static struct target_type verity_target = {
 	.name		= "verity",
-	.version	= {1, 5, 0},
+	.version	= {1, 6, 0},
 	.module		= THIS_MODULE,
 	.ctr		= verity_ctr,
 	.dtr		= verity_dtr,

drivers/md/dm-writecache.c

@@ -625,6 +625,12 @@ static void writecache_add_to_freelist(struct dm_writecache *wc, struct wc_entry
 	wc->freelist_size++;
 }
 
+static inline void writecache_verify_watermark(struct dm_writecache *wc)
+{
+	if (unlikely(wc->freelist_size + wc->writeback_size <= wc->freelist_high_watermark))
+		queue_work(wc->writeback_wq, &wc->writeback_work);
+}
+
 static struct wc_entry *writecache_pop_from_freelist(struct dm_writecache *wc, sector_t expected_sector)
 {
 	struct wc_entry *e;
@@ -650,8 +656,8 @@ static struct wc_entry *writecache_pop_from_freelist(struct dm_writecache *wc, s
 		list_del(&e->lru);
 	}
 	wc->freelist_size--;
-	if (unlikely(wc->freelist_size + wc->writeback_size <= wc->freelist_high_watermark))
-		queue_work(wc->writeback_wq, &wc->writeback_work);
+
+	writecache_verify_watermark(wc);
 
 	return e;
 }
@@ -842,7 +848,7 @@ static void writecache_suspend(struct dm_target *ti)
 	}
 	wc_unlock(wc);
 
-	flush_workqueue(wc->writeback_wq);
+	drain_workqueue(wc->writeback_wq);
 
 	wc_lock(wc);
 	if (flush_on_suspend)
@@ -965,6 +971,8 @@ static void writecache_resume(struct dm_target *ti)
 		writecache_commit_flushed(wc, false);
 	}
 
+	writecache_verify_watermark(wc);
+
 	wc_unlock(wc);
 }
 
@@ -2312,7 +2320,7 @@ static void writecache_status(struct dm_target *ti, status_type_t type,
 
 static struct target_type writecache_target = {
 	.name			= "writecache",
-	.version		= {1, 1, 1},
+	.version		= {1, 2, 0},
 	.module			= THIS_MODULE,
 	.ctr			= writecache_ctr,
 	.dtr			= writecache_dtr,