1 files changed, 44 insertions, 42 deletions

diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 29a5e5b4c63c..382b8694be50 100644
--- a/drivers/md/dm-integrity.c
+++ b/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>
@@ -199,17 +201,19 @@ 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];
@@ -290,11 +294,7 @@ 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 {
@@ -1421,7 +1421,7 @@ 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);
@@ -1432,14 +1432,9 @@ 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);
@@ -1506,7 +1501,7 @@ static void integrity_metadata(struct work_struct *w)
 		struct bio *bio = dm_bio_from_per_bio_data(dio, sizeof(struct dm_integrity_io));
 		char *checksums;
 		unsigned extra_space = unlikely(digest_size > ic->tag_size) ? digest_size - ic->tag_size : 0;
-		char checksums_onstack[HASH_MAX_DIGESTSIZE];
+		char checksums_onstack[max((size_t)HASH_MAX_DIGESTSIZE, MAX_TAG_SIZE)];
 		unsigned sectors_to_process = dio->range.n_sectors;
 		sector_t sector = dio->range.logical_sector;
 
@@ -1524,7 +1519,7 @@ 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;
 
@@ -1568,7 +1563,7 @@ again:
 		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;
@@ -1735,7 +1730,7 @@ retry_kmap:
 				} while (++s < ic->sectors_per_block);
 #ifdef INTERNAL_VERIFY
 				if (ic->internal_hash) {
-					char checksums_onstack[max(HASH_MAX_DIGESTSIZE, MAX_TAG_SIZE)];
+					char checksums_onstack[max((size_t)HASH_MAX_DIGESTSIZE, MAX_TAG_SIZE)];
 
 					integrity_sector_checksum(ic, logical_sector, mem + bv.bv_offset, checksums_onstack);
 					if (unlikely(memcmp(checksums_onstack, journal_entry_tag(ic, je), ic->tag_size))) {
@@ -1847,7 +1842,7 @@ 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;
 	}
 
@@ -1987,20 +1982,13 @@ offload_to_thread:
 	} 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) {
@@ -2297,7 +2285,7 @@ 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_post_suspending(ic->ti)) && !ic->meta_dev)
 		return;
 
 	spin_lock_irq(&ic->endio_wait.lock);
@@ -2359,7 +2347,7 @@ static void integrity_recalc(struct work_struct *w)
 
 next_chunk:
 
-	if (unlikely(READ_ONCE(ic->suspending)))
+	if (unlikely(dm_post_suspending(ic->ti)))
 		goto unlock_ret;
 
 	range.logical_sector = le64_to_cpu(ic->sb->recalc_sector);
@@ -2484,7 +2472,7 @@ 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);
@@ -2507,7 +2495,7 @@ 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);
@@ -2787,8 +2775,6 @@ 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);
 
@@ -2817,8 +2803,6 @@ 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;
@@ -2871,17 +2855,24 @@ 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);
 		}
@@ -2949,7 +2940,7 @@ 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);
@@ -3596,6 +3587,7 @@ 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);
@@ -3807,6 +3799,14 @@ 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";
@@ -4111,6 +4111,8 @@ 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)