cleanup btrfs bio handling, part 1 v2

cleanup btrfs bio handling, part 1 v2

[Christoph Hellwig]

Hi all,

this series  moves btrfs to use the new as of 5.18 bio interface and
cleans up a few close by areas.  Larger cleanups focussed around
the btrfs_bio will follow as a next step.

Changes since v1:
 - rebased to btrfs/misc-next
 - improve a commit log

Diffstat:
 check-integrity.c |  165 +++++++++++++++++++++++++-----------------------------
 check-integrity.h |    8 +-
 disk-io.c         |    6 +
 extent_io.c       |   55 ++++++++----------
 extent_io.h       |    2 
 raid56.c          |   46 ++++++---------
 scrub.c           |   92 ++++++++++++------------------
 volumes.c         |   12 ++-
 8 files changed, 179 insertions(+), 207 deletions(-)

[PATCH 01/12] btrfs: refactor __btrfsic_submit_bio

[Christoph Hellwig]

Split out two helpers to mak __btrfsic_submit_bio more readable.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/btrfs/check-integrity.c | 150 +++++++++++++++++++------------------
 1 file changed, 78 insertions(+), 72 deletions(-)

diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index b8f9dfa326207..ec8a73ff82717 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -2633,6 +2633,74 @@ static struct btrfsic_dev_state *btrfsic_dev_state_lookup(dev_t dev)
 						  &btrfsic_dev_state_hashtable);
 }
 
+static void btrfsic_check_write_bio(struct bio *bio,
+		struct btrfsic_dev_state *dev_state)
+{
+	unsigned int segs = bio_segments(bio);
+	u64 dev_bytenr = 512 * bio->bi_iter.bi_sector;
+	u64 cur_bytenr = dev_bytenr;
+	struct bvec_iter iter;
+	struct bio_vec bvec;
+	char **mapped_datav;
+	int bio_is_patched = 0;
+	int i = 0;
+
+	if (dev_state->state->print_mask & BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH)
+		pr_info("submit_bio(rw=%d,0x%x, bi_vcnt=%u, bi_sector=%llu (bytenr %llu), bi_bdev=%p)\n",
+		       bio_op(bio), bio->bi_opf, segs,
+		       bio->bi_iter.bi_sector, dev_bytenr, bio->bi_bdev);
+
+	mapped_datav = kmalloc_array(segs, sizeof(*mapped_datav), GFP_NOFS);
+	if (!mapped_datav)
+		return;
+
+	bio_for_each_segment(bvec, bio, iter) {
+		BUG_ON(bvec.bv_len != PAGE_SIZE);
+		mapped_datav[i] = page_address(bvec.bv_page);
+		i++;
+
+		if (dev_state->state->print_mask &
+		    BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH_VERBOSE)
+			pr_info("#%u: bytenr=%llu, len=%u, offset=%u\n",
+			       i, cur_bytenr, bvec.bv_len, bvec.bv_offset);
+		cur_bytenr += bvec.bv_len;
+	}
+
+	btrfsic_process_written_block(dev_state, dev_bytenr, mapped_datav, segs,
+				      bio, &bio_is_patched, bio->bi_opf);
+	kfree(mapped_datav);
+}
+
+static void btrfsic_check_flush_bio(struct bio *bio,
+		struct btrfsic_dev_state *dev_state)
+{
+	if (dev_state->state->print_mask & BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH)
+		pr_info("submit_bio(rw=%d,0x%x FLUSH, bdev=%p)\n",
+		       bio_op(bio), bio->bi_opf, bio->bi_bdev);
+
+	if (dev_state->dummy_block_for_bio_bh_flush.is_iodone) {
+		struct btrfsic_block *const block =
+			&dev_state->dummy_block_for_bio_bh_flush;
+
+		block->is_iodone = 0;
+		block->never_written = 0;
+		block->iodone_w_error = 0;
+		block->flush_gen = dev_state->last_flush_gen + 1;
+		block->submit_bio_bh_rw = bio->bi_opf;
+		block->orig_bio_private = bio->bi_private;
+		block->orig_bio_end_io = bio->bi_end_io;
+		block->next_in_same_bio = NULL;
+		bio->bi_private = block;
+		bio->bi_end_io = btrfsic_bio_end_io;
+	} else if ((dev_state->state->print_mask &
+		   (BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH |
+		    BTRFSIC_PRINT_MASK_VERBOSE))) {
+		pr_info(
+"btrfsic_submit_bio(%pg) with FLUSH but dummy block already in use (ignored)!\n",
+		       dev_state->bdev);
+	}
+}
+
 static void __btrfsic_submit_bio(struct bio *bio)
 {
 	struct btrfsic_dev_state *dev_state;
@@ -2640,80 +2708,18 @@ static void __btrfsic_submit_bio(struct bio *bio)
 	if (!btrfsic_is_initialized)
 		return;
 
-	mutex_lock(&btrfsic_mutex);
-	/* since btrfsic_submit_bio() is also called before
-	 * btrfsic_mount(), this might return NULL */
+	/*
+	 * We can be called before btrfsic_mount, so there might not be a
+	 * dev_state.
+	 */
 	dev_state = btrfsic_dev_state_lookup(bio->bi_bdev->bd_dev);
-	if (NULL != dev_state &&
-	    (bio_op(bio) == REQ_OP_WRITE) && bio_has_data(bio)) {
-		int i = 0;
-		u64 dev_bytenr;
-		u64 cur_bytenr;
-		struct bio_vec bvec;
-		struct bvec_iter iter;
-		int bio_is_patched;
-		char **mapped_datav;
-		unsigned int segs = bio_segments(bio);
-
-		dev_bytenr = 512 * bio->bi_iter.bi_sector;
-		bio_is_patched = 0;
-		if (dev_state->state->print_mask &
-		    BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH)
-			pr_info("submit_bio(rw=%d,0x%x, bi_vcnt=%u, bi_sector=%llu (bytenr %llu), bi_bdev=%p)\n",
-			       bio_op(bio), bio->bi_opf, segs,
-			       bio->bi_iter.bi_sector, dev_bytenr, bio->bi_bdev);
-
-		mapped_datav = kmalloc_array(segs,
-					     sizeof(*mapped_datav), GFP_NOFS);
-		if (!mapped_datav)
-			goto leave;
-		cur_bytenr = dev_bytenr;
-
-		bio_for_each_segment(bvec, bio, iter) {
-			BUG_ON(bvec.bv_len != PAGE_SIZE);
-			mapped_datav[i] = page_address(bvec.bv_page);
-			i++;
-
-			if (dev_state->state->print_mask &
-			    BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH_VERBOSE)
-				pr_info("#%u: bytenr=%llu, len=%u, offset=%u\n",
-				       i, cur_bytenr, bvec.bv_len, bvec.bv_offset);
-			cur_bytenr += bvec.bv_len;
-		}
-		btrfsic_process_written_block(dev_state, dev_bytenr,
-					      mapped_datav, segs,
-					      bio, &bio_is_patched,
-					      bio->bi_opf);
-		kfree(mapped_datav);
-	} else if (NULL != dev_state && (bio->bi_opf & REQ_PREFLUSH)) {
-		if (dev_state->state->print_mask &
-		    BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH)
-			pr_info("submit_bio(rw=%d,0x%x FLUSH, bdev=%p)\n",
-			       bio_op(bio), bio->bi_opf, bio->bi_bdev);
-		if (!dev_state->dummy_block_for_bio_bh_flush.is_iodone) {
-			if ((dev_state->state->print_mask &
-			     (BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH |
-			      BTRFSIC_PRINT_MASK_VERBOSE)))
-				pr_info(
-"btrfsic_submit_bio(%pg) with FLUSH but dummy block already in use (ignored)!\n",
-				       dev_state->bdev);
-		} else {
-			struct btrfsic_block *const block =
-				&dev_state->dummy_block_for_bio_bh_flush;
-
-			block->is_iodone = 0;
-			block->never_written = 0;
-			block->iodone_w_error = 0;
-			block->flush_gen = dev_state->last_flush_gen + 1;
-			block->submit_bio_bh_rw = bio->bi_opf;
-			block->orig_bio_private = bio->bi_private;
-			block->orig_bio_end_io = bio->bi_end_io;
-			block->next_in_same_bio = NULL;
-			bio->bi_private = block;
-			bio->bi_end_io = btrfsic_bio_end_io;
-		}
+	mutex_lock(&btrfsic_mutex);
+	if (dev_state) {
+		if (bio_op(bio) == REQ_OP_WRITE && bio_has_data(bio))
+			btrfsic_check_write_bio(bio, dev_state);
+		else if (bio->bi_opf & REQ_PREFLUSH)
+			btrfsic_check_flush_bio(bio, dev_state);
 	}
-leave:
 	mutex_unlock(&btrfsic_mutex);
 }
 
-- 
2.30.2

[PATCH 02/12] btrfs: split submit_bio from btrfsic checking

[Christoph Hellwig]

Require a separate call to the integrity checking helpers from the
actual bio submission.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Qu Wenruo <wqu@suse.com>
---
 fs/btrfs/check-integrity.c | 14 +-------------
 fs/btrfs/check-integrity.h |  8 ++++----
 fs/btrfs/disk-io.c         |  6 ++++--
 fs/btrfs/extent_io.c       |  3 ++-
 fs/btrfs/scrub.c           | 12 ++++++++----
 fs/btrfs/volumes.c         |  3 ++-
 6 files changed, 21 insertions(+), 25 deletions(-)

diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index ec8a73ff82717..9efd33b4e24d7 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -2701,7 +2701,7 @@ static void btrfsic_check_flush_bio(struct bio *bio,
 	}
 }
 
-static void __btrfsic_submit_bio(struct bio *bio)
+void btrfsic_check_bio(struct bio *bio)
 {
 	struct btrfsic_dev_state *dev_state;
 
@@ -2723,18 +2723,6 @@ static void __btrfsic_submit_bio(struct bio *bio)
 	mutex_unlock(&btrfsic_mutex);
 }
 
-void btrfsic_submit_bio(struct bio *bio)
-{
-	__btrfsic_submit_bio(bio);
-	submit_bio(bio);
-}
-
-int btrfsic_submit_bio_wait(struct bio *bio)
-{
-	__btrfsic_submit_bio(bio);
-	return submit_bio_wait(bio);
-}
-
 int btrfsic_mount(struct btrfs_fs_info *fs_info,
 		  struct btrfs_fs_devices *fs_devices,
 		  int including_extent_data, u32 print_mask)
diff --git a/fs/btrfs/check-integrity.h b/fs/btrfs/check-integrity.h
index bcc730a06cb58..ed115e0f2ebbd 100644
--- a/fs/btrfs/check-integrity.h
+++ b/fs/btrfs/check-integrity.h
@@ -7,11 +7,11 @@
 #define BTRFS_CHECK_INTEGRITY_H
 
 #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
-void btrfsic_submit_bio(struct bio *bio);
-int btrfsic_submit_bio_wait(struct bio *bio);
+void btrfsic_check_bio(struct bio *bio);
 #else
-#define btrfsic_submit_bio submit_bio
-#define btrfsic_submit_bio_wait submit_bio_wait
+static inline void btrfsic_check_bio(struct bio *bio)
+{
+}
 #endif
 
 int btrfsic_mount(struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index dfec67e8a78c7..2bc867d353087 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -4167,7 +4167,8 @@ static int write_dev_supers(struct btrfs_device *device,
 		if (i == 0 && !btrfs_test_opt(device->fs_info, NOBARRIER))
 			bio->bi_opf |= REQ_FUA;
 
-		btrfsic_submit_bio(bio);
+		btrfsic_check_bio(bio);
+		submit_bio(bio);
 
 		if (btrfs_advance_sb_log(device, i))
 			errors++;
@@ -4280,7 +4281,8 @@ static void write_dev_flush(struct btrfs_device *device)
 	init_completion(&device->flush_wait);
 	bio->bi_private = &device->flush_wait;
 
-	btrfsic_submit_bio(bio);
+	btrfsic_check_bio(bio);
+	submit_bio(bio);
 	set_bit(BTRFS_DEV_STATE_FLUSH_SENT, &device->dev_state);
 }
 
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 4bcc182744e48..9d5bc6598489b 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2368,7 +2368,8 @@ static int repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
 	bio->bi_opf = REQ_OP_WRITE | REQ_SYNC;
 	bio_add_page(bio, page, length, pg_offset);
 
-	if (btrfsic_submit_bio_wait(bio)) {
+	btrfsic_check_bio(bio);
+	if (submit_bio_wait(bio)) {
 		/* try to remap that extent elsewhere? */
 		btrfs_bio_counter_dec(fs_info);
 		bio_put(bio);
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 5c979f7411937..a4f9cfdec8b60 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1475,7 +1475,8 @@ static void scrub_recheck_block(struct btrfs_fs_info *fs_info,
 		bio->bi_iter.bi_sector = sector->physical >> 9;
 		bio->bi_opf = REQ_OP_READ;
 
-		if (btrfsic_submit_bio_wait(bio)) {
+		btrfsic_check_bio(bio);
+		if (submit_bio_wait(bio)) {
 			sector->io_error = 1;
 			sblock->no_io_error_seen = 0;
 		}
@@ -1559,7 +1560,8 @@ static int scrub_repair_sector_from_good_copy(struct scrub_block *sblock_bad,
 			return -EIO;
 		}
 
-		if (btrfsic_submit_bio_wait(bio)) {
+		btrfsic_check_bio(bio);
+		if (submit_bio_wait(bio)) {
 			btrfs_dev_stat_inc_and_print(sector_bad->dev,
 				BTRFS_DEV_STAT_WRITE_ERRS);
 			atomic64_inc(&fs_info->dev_replace.num_write_errors);
@@ -1715,7 +1717,8 @@ static void scrub_wr_submit(struct scrub_ctx *sctx)
 	 * orders the requests before sending them to the driver which
 	 * doubled the write performance on spinning disks when measured
 	 * with Linux 3.5 */
-	btrfsic_submit_bio(sbio->bio);
+	btrfsic_check_bio(sbio->bio);
+	submit_bio(sbio->bio);
 
 	if (btrfs_is_zoned(sctx->fs_info))
 		sctx->write_pointer = sbio->physical + sbio->sector_count *
@@ -2049,7 +2052,8 @@ static void scrub_submit(struct scrub_ctx *sctx)
 	sbio = sctx->bios[sctx->curr];
 	sctx->curr = -1;
 	scrub_pending_bio_inc(sctx);
-	btrfsic_submit_bio(sbio->bio);
+	btrfsic_check_bio(sbio->bio);
+	submit_bio(sbio->bio);
 }
 
 static int scrub_add_sector_to_rd_bio(struct scrub_ctx *sctx,
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 26ada24890a5a..6b49d78d15029 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -6742,7 +6742,8 @@ static void submit_stripe_bio(struct btrfs_io_context *bioc, struct bio *bio,
 
 	btrfs_bio_counter_inc_noblocked(fs_info);
 
-	btrfsic_submit_bio(bio);
+	btrfsic_check_bio(bio);
+	submit_bio(bio);
 }
 
 static void bioc_error(struct btrfs_io_context *bioc, struct bio *bio, u64 logical)
-- 
2.30.2

[PATCH 03/12] btrfs: simplify btrfsic_read_block

[Christoph Hellwig]

btrfsic_read_block does not need the btrfs_bio structure, so switch to
plain bio_alloc.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/btrfs/check-integrity.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index 9efd33b4e24d7..864a90e825050 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -1561,10 +1561,9 @@ static int btrfsic_read_block(struct btrfsic_state *state,
 		struct bio *bio;
 		unsigned int j;
 
-		bio = btrfs_bio_alloc(num_pages - i);
-		bio_set_dev(bio, block_ctx->dev->bdev);
+		bio = bio_alloc(block_ctx->dev->bdev, num_pages - i,
+				REQ_OP_READ, GFP_NOFS);
 		bio->bi_iter.bi_sector = dev_bytenr >> 9;
-		bio->bi_opf = REQ_OP_READ;
 
 		for (j = i; j < num_pages; j++) {
 			ret = bio_add_page(bio, block_ctx->pagev[j],
-- 
2.30.2

[PATCH 04/12] btrfs: simplify repair_io_failure

[Christoph Hellwig]

The I/O in repair_io_failue is synchronous and doesn't need a btrfs_bio,
so just use an on-stack bio.  Also cleanup the error handling to use goto
labels and not discard the actual return values.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Qu Wenruo <wqu@suse.com>
---
 fs/btrfs/extent_io.c | 52 ++++++++++++++++++++------------------------
 1 file changed, 24 insertions(+), 28 deletions(-)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 9d5bc6598489b..ede7a72fe840c 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2305,12 +2305,13 @@ static int repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
 			     u64 length, u64 logical, struct page *page,
 			     unsigned int pg_offset, int mirror_num)
 {
-	struct bio *bio;
 	struct btrfs_device *dev;
+	struct bio_vec bvec;
+	struct bio bio;
 	u64 map_length = 0;
 	u64 sector;
 	struct btrfs_io_context *bioc = NULL;
-	int ret;
+	int ret = 0;
 
 	ASSERT(!(fs_info->sb->s_flags & SB_RDONLY));
 	BUG_ON(!mirror_num);
@@ -2318,8 +2319,6 @@ static int repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
 	if (btrfs_repair_one_zone(fs_info, logical))
 		return 0;
 
-	bio = btrfs_bio_alloc(1);
-	bio->bi_iter.bi_size = 0;
 	map_length = length;
 
 	/*
@@ -2337,53 +2336,50 @@ static int repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
 		 */
 		ret = btrfs_map_block(fs_info, BTRFS_MAP_READ, logical,
 				      &map_length, &bioc, 0);
-		if (ret) {
-			btrfs_bio_counter_dec(fs_info);
-			bio_put(bio);
-			return -EIO;
-		}
+		if (ret)
+			goto out_counter_dec;
 		ASSERT(bioc->mirror_num == 1);
 	} else {
 		ret = btrfs_map_block(fs_info, BTRFS_MAP_WRITE, logical,
 				      &map_length, &bioc, mirror_num);
-		if (ret) {
-			btrfs_bio_counter_dec(fs_info);
-			bio_put(bio);
-			return -EIO;
-		}
+		if (ret)
+			goto out_counter_dec;
 		BUG_ON(mirror_num != bioc->mirror_num);
 	}
 
 	sector = bioc->stripes[bioc->mirror_num - 1].physical >> 9;
-	bio->bi_iter.bi_sector = sector;
 	dev = bioc->stripes[bioc->mirror_num - 1].dev;
 	btrfs_put_bioc(bioc);
+
 	if (!dev || !dev->bdev ||
 	    !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) {
-		btrfs_bio_counter_dec(fs_info);
-		bio_put(bio);
-		return -EIO;
+		ret = -EIO;
+		goto out_counter_dec;
 	}
-	bio_set_dev(bio, dev->bdev);
-	bio->bi_opf = REQ_OP_WRITE | REQ_SYNC;
-	bio_add_page(bio, page, length, pg_offset);
 
-	btrfsic_check_bio(bio);
-	if (submit_bio_wait(bio)) {
+	bio_init(&bio, dev->bdev, &bvec, 1, REQ_OP_WRITE | REQ_SYNC);
+	bio.bi_iter.bi_sector = sector;
+	__bio_add_page(&bio, page, length, pg_offset);
+
+	btrfsic_check_bio(&bio);
+	ret = submit_bio_wait(&bio);
+	if (ret) {
 		/* try to remap that extent elsewhere? */
-		btrfs_bio_counter_dec(fs_info);
-		bio_put(bio);
 		btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS);
-		return -EIO;
+		goto out_bio_uninit;
 	}
 
 	btrfs_info_rl_in_rcu(fs_info,
 		"read error corrected: ino %llu off %llu (dev %s sector %llu)",
 				  ino, start,
 				  rcu_str_deref(dev->name), sector);
+	ret = 0;
+
+out_bio_uninit:
+	bio_uninit(&bio);
+out_counter_dec:
 	btrfs_bio_counter_dec(fs_info);
-	bio_put(bio);
-	return 0;
+	return ret;
 }
 
 int btrfs_repair_eb_io_failure(const struct extent_buffer *eb, int mirror_num)
-- 
2.30.2

[PATCH 05/12] btrfs: simplify scrub_recheck_block

[Christoph Hellwig]

The I/O in repair_io_failue is synchronous and doesn't need a btrfs_bio,
so just use an on-stack bio.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Qu Wenruo <wqu@suse.com>
---
 fs/btrfs/scrub.c | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index a4f9cfdec8b60..3790747c449b0 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1458,8 +1458,9 @@ static void scrub_recheck_block(struct btrfs_fs_info *fs_info,
 		return scrub_recheck_block_on_raid56(fs_info, sblock);
 
 	for (i = 0; i < sblock->sector_count; i++) {
-		struct bio *bio;
 		struct scrub_sector *sector = sblock->sectors[i];
+		struct bio_vec bvec;
+		struct bio bio;
 
 		if (sector->dev->bdev == NULL) {
 			sector->io_error = 1;
@@ -1468,20 +1469,17 @@ static void scrub_recheck_block(struct btrfs_fs_info *fs_info,
 		}
 
 		WARN_ON(!sector->page);
-		bio = btrfs_bio_alloc(1);
-		bio_set_dev(bio, sector->dev->bdev);
-
-		bio_add_page(bio, sector->page, fs_info->sectorsize, 0);
-		bio->bi_iter.bi_sector = sector->physical >> 9;
-		bio->bi_opf = REQ_OP_READ;
+		bio_init(&bio, sector->dev->bdev, &bvec, 1, REQ_OP_READ);
+		bio_add_page(&bio, sector->page, fs_info->sectorsize, 0);
+		bio.bi_iter.bi_sector = sector->physical >> 9;
 
-		btrfsic_check_bio(bio);
-		if (submit_bio_wait(bio)) {
+		btrfsic_check_bio(&bio);
+		if (submit_bio_wait(&bio)) {
 			sector->io_error = 1;
 			sblock->no_io_error_seen = 0;
 		}
 
-		bio_put(bio);
+		bio_uninit(&bio);
 	}
 
 	if (sblock->no_io_error_seen)
-- 
2.30.2

[PATCH 06/12] btrfs: simplify scrub_repair_page_from_good_copy

[Christoph Hellwig]

The I/O in repair_io_failue is synchronous and doesn't need a btrfs_bio,
so just use an on-stack bio.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Qu Wenruo <wqu@suse.com>
---
 fs/btrfs/scrub.c | 23 +++++++++--------------
 1 file changed, 9 insertions(+), 14 deletions(-)

diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 3790747c449b0..fe25a0d3d7c2d 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1538,7 +1538,8 @@ static int scrub_repair_sector_from_good_copy(struct scrub_block *sblock_bad,
 	BUG_ON(sector_good->page == NULL);
 	if (force_write || sblock_bad->header_error ||
 	    sblock_bad->checksum_error || sector_bad->io_error) {
-		struct bio *bio;
+		struct bio_vec bvec;
+		struct bio bio;
 		int ret;
 
 		if (!sector_bad->dev->bdev) {
@@ -1547,26 +1548,20 @@ static int scrub_repair_sector_from_good_copy(struct scrub_block *sblock_bad,
 			return -EIO;
 		}
 
-		bio = btrfs_bio_alloc(1);
-		bio_set_dev(bio, sector_bad->dev->bdev);
-		bio->bi_iter.bi_sector = sector_bad->physical >> 9;
-		bio->bi_opf = REQ_OP_WRITE;
+		bio_init(&bio, sector_bad->dev->bdev, &bvec, 1, REQ_OP_WRITE);
+		bio.bi_iter.bi_sector = sector_bad->physical >> 9;
+		__bio_add_page(&bio, sector_good->page, sectorsize, 0);
 
-		ret = bio_add_page(bio, sector_good->page, sectorsize, 0);
-		if (ret != sectorsize) {
-			bio_put(bio);
-			return -EIO;
-		}
+		btrfsic_check_bio(&bio);
+		ret = submit_bio_wait(&bio);
+		bio_uninit(&bio);
 
-		btrfsic_check_bio(bio);
-		if (submit_bio_wait(bio)) {
+		if (ret) {
 			btrfs_dev_stat_inc_and_print(sector_bad->dev,
 				BTRFS_DEV_STAT_WRITE_ERRS);
 			atomic64_inc(&fs_info->dev_replace.num_write_errors);
-			bio_put(bio);
 			return -EIO;
 		}
-		bio_put(bio);
 	}
 
 	return 0;
-- 
2.30.2

[PATCH 07/12] btrfs: move the call to bio_set_dev out of submit_stripe_bio

[Christoph Hellwig]

Prepare for additional refactoring.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/btrfs/volumes.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 6b49d78d15029..8e066b9ebfbde 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -6738,7 +6738,6 @@ static void submit_stripe_bio(struct btrfs_io_context *bioc, struct bio *bio,
 		bio_op(bio), bio->bi_opf, bio->bi_iter.bi_sector,
 		(unsigned long)dev->bdev->bd_dev, rcu_str_deref(dev->name),
 		dev->devid, bio->bi_iter.bi_size);
-	bio_set_dev(bio, dev->bdev);
 
 	btrfs_bio_counter_inc_noblocked(fs_info);
 
@@ -6830,6 +6829,7 @@ blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 		else
 			bio = first_bio;
 
+		bio_set_dev(bio, dev->bdev);
 		submit_stripe_bio(bioc, bio, bioc->stripes[dev_nr].physical, dev);
 	}
 	btrfs_bio_counter_dec(fs_info);
-- 
2.30.2

[PATCH 08/12] btrfs: pass a block_device to btrfs_bio_clone

[Christoph Hellwig]

Pass the block_device to btrfs_bio_clone so that it can be paased on to
bio_alloc_clone instead of setting it later.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/btrfs/extent_io.c | 4 ++--
 fs/btrfs/extent_io.h | 2 +-
 fs/btrfs/volumes.c   | 9 +++++----
 3 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index ede7a72fe840c..1a5a7ded31758 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3188,13 +3188,13 @@ struct bio *btrfs_bio_alloc(unsigned int nr_iovecs)
 	return bio;
 }
 
-struct bio *btrfs_bio_clone(struct bio *bio)
+struct bio *btrfs_bio_clone(struct block_device *bdev, struct bio *bio)
 {
 	struct btrfs_bio *bbio;
 	struct bio *new;
 
 	/* Bio allocation backed by a bioset does not fail */
-	new = bio_alloc_clone(bio->bi_bdev, bio, GFP_NOFS, &btrfs_bioset);
+	new = bio_alloc_clone(bdev, bio, GFP_NOFS, &btrfs_bioset);
 	bbio = btrfs_bio(new);
 	btrfs_bio_init(bbio);
 	bbio->iter = bio->bi_iter;
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 1331902c75815..05253612ce7bb 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -280,7 +280,7 @@ void extent_clear_unlock_delalloc(struct btrfs_inode *inode, u64 start, u64 end,
 
 int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array);
 struct bio *btrfs_bio_alloc(unsigned int nr_iovecs);
-struct bio *btrfs_bio_clone(struct bio *bio);
+struct bio *btrfs_bio_clone(struct block_device *bdev, struct bio *bio);
 struct bio *btrfs_bio_clone_partial(struct bio *orig, u64 offset, u64 size);
 
 void end_extent_writepage(struct page *page, int err, u64 start, u64 end);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 8e066b9ebfbde..2368a2ffbee75 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -6824,12 +6824,13 @@ blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 			continue;
 		}
 
-		if (dev_nr < total_devs - 1)
-			bio = btrfs_bio_clone(first_bio);
-		else
+		if (dev_nr < total_devs - 1) {
+			bio = btrfs_bio_clone(dev->bdev, first_bio);
+		} else {
 			bio = first_bio;
+			bio_set_dev(bio, dev->bdev);
+		}
 
-		bio_set_dev(bio, dev->bdev);
 		submit_stripe_bio(bioc, bio, bioc->stripes[dev_nr].physical, dev);
 	}
 	btrfs_bio_counter_dec(fs_info);
-- 
2.30.2

[PATCH 09/12] btrfs: initialize ->bi_opf and ->bi_private in rbio_add_io_page

[Christoph Hellwig]

Prepare for further refactoring by moving this initialization to a single
place.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/btrfs/raid56.c | 38 ++++++++++++++++++--------------------
 1 file changed, 18 insertions(+), 20 deletions(-)

diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index ba6f6be771213..13a998628b90b 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -1048,7 +1048,8 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio,
 			    struct page *page,
 			    int stripe_nr,
 			    unsigned long page_index,
-			    unsigned long bio_max_len)
+			    unsigned long bio_max_len,
+			    unsigned int opf)
 {
 	struct bio *last = bio_list->tail;
 	int ret;
@@ -1085,7 +1086,9 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio,
 	btrfs_bio(bio)->device = stripe->dev;
 	bio->bi_iter.bi_size = 0;
 	bio_set_dev(bio, stripe->dev->bdev);
+	bio->bi_opf = opf;
 	bio->bi_iter.bi_sector = disk_start >> 9;
+	bio->bi_private = rbio;
 
 	bio_add_page(bio, page, PAGE_SIZE, 0);
 	bio_list_add(bio_list, bio);
@@ -1254,7 +1257,8 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
 			}
 
 			ret = rbio_add_io_page(rbio, &bio_list,
-				       page, stripe, pagenr, rbio->stripe_len);
+				       page, stripe, pagenr, rbio->stripe_len,
+				       REQ_OP_WRITE);
 			if (ret)
 				goto cleanup;
 		}
@@ -1279,7 +1283,8 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
 
 			ret = rbio_add_io_page(rbio, &bio_list, page,
 					       rbio->bioc->tgtdev_map[stripe],
-					       pagenr, rbio->stripe_len);
+					       pagenr, rbio->stripe_len,
+					       REQ_OP_WRITE);
 			if (ret)
 				goto cleanup;
 		}
@@ -1290,9 +1295,7 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
 	BUG_ON(atomic_read(&rbio->stripes_pending) == 0);
 
 	while ((bio = bio_list_pop(&bio_list))) {
-		bio->bi_private = rbio;
 		bio->bi_end_io = raid_write_end_io;
-		bio->bi_opf = REQ_OP_WRITE;
 
 		submit_bio(bio);
 	}
@@ -1496,7 +1499,8 @@ static int raid56_rmw_stripe(struct btrfs_raid_bio *rbio)
 				continue;
 
 			ret = rbio_add_io_page(rbio, &bio_list, page,
-				       stripe, pagenr, rbio->stripe_len);
+				       stripe, pagenr, rbio->stripe_len,
+				       REQ_OP_READ);
 			if (ret)
 				goto cleanup;
 		}
@@ -1519,9 +1523,7 @@ static int raid56_rmw_stripe(struct btrfs_raid_bio *rbio)
 	 */
 	atomic_set(&rbio->stripes_pending, bios_to_read);
 	while ((bio = bio_list_pop(&bio_list))) {
-		bio->bi_private = rbio;
 		bio->bi_end_io = raid_rmw_end_io;
-		bio->bi_opf = REQ_OP_READ;
 
 		btrfs_bio_wq_end_io(rbio->bioc->fs_info, bio, BTRFS_WQ_ENDIO_RAID56);
 
@@ -2038,7 +2040,8 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio)
 
 			ret = rbio_add_io_page(rbio, &bio_list,
 				       rbio_stripe_page(rbio, stripe, pagenr),
-				       stripe, pagenr, rbio->stripe_len);
+				       stripe, pagenr, rbio->stripe_len,
+				       REQ_OP_READ);
 			if (ret < 0)
 				goto cleanup;
 		}
@@ -2065,9 +2068,7 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio)
 	 */
 	atomic_set(&rbio->stripes_pending, bios_to_read);
 	while ((bio = bio_list_pop(&bio_list))) {
-		bio->bi_private = rbio;
 		bio->bi_end_io = raid_recover_end_io;
-		bio->bi_opf = REQ_OP_READ;
 
 		btrfs_bio_wq_end_io(rbio->bioc->fs_info, bio, BTRFS_WQ_ENDIO_RAID56);
 
@@ -2398,8 +2399,8 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
 		struct page *page;
 
 		page = rbio_stripe_page(rbio, rbio->scrubp, pagenr);
-		ret = rbio_add_io_page(rbio, &bio_list,
-			       page, rbio->scrubp, pagenr, rbio->stripe_len);
+		ret = rbio_add_io_page(rbio, &bio_list, page, rbio->scrubp,
+				       pagenr, rbio->stripe_len, REQ_OP_WRITE);
 		if (ret)
 			goto cleanup;
 	}
@@ -2413,7 +2414,7 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
 		page = rbio_stripe_page(rbio, rbio->scrubp, pagenr);
 		ret = rbio_add_io_page(rbio, &bio_list, page,
 				       bioc->tgtdev_map[rbio->scrubp],
-				       pagenr, rbio->stripe_len);
+				       pagenr, rbio->stripe_len, REQ_OP_WRITE);
 		if (ret)
 			goto cleanup;
 	}
@@ -2429,9 +2430,7 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
 	atomic_set(&rbio->stripes_pending, nr_data);
 
 	while ((bio = bio_list_pop(&bio_list))) {
-		bio->bi_private = rbio;
 		bio->bi_end_io = raid_write_end_io;
-		bio->bi_opf = REQ_OP_WRITE;
 
 		submit_bio(bio);
 	}
@@ -2583,8 +2582,9 @@ static void raid56_parity_scrub_stripe(struct btrfs_raid_bio *rbio)
 			if (PageUptodate(page))
 				continue;
 
-			ret = rbio_add_io_page(rbio, &bio_list, page,
-				       stripe, pagenr, rbio->stripe_len);
+			ret = rbio_add_io_page(rbio, &bio_list, page, stripe,
+					       pagenr, rbio->stripe_len,
+					       REQ_OP_READ);
 			if (ret)
 				goto cleanup;
 		}
@@ -2607,9 +2607,7 @@ static void raid56_parity_scrub_stripe(struct btrfs_raid_bio *rbio)
 	 */
 	atomic_set(&rbio->stripes_pending, bios_to_read);
 	while ((bio = bio_list_pop(&bio_list))) {
-		bio->bi_private = rbio;
 		bio->bi_end_io = raid56_parity_scrub_end_io;
-		bio->bi_opf = REQ_OP_READ;
 
 		btrfs_bio_wq_end_io(rbio->bioc->fs_info, bio, BTRFS_WQ_ENDIO_RAID56);
 
-- 
2.30.2

[PATCH 10/12] btrfs: don't allocate a btrfs_bio for raid56 per-stripe bios

[Christoph Hellwig]

Except for the spurious initialization of ->device just after allocation
nothing uses the btrfs_bio, so just allocate a normal bio without extra
data.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Qu Wenruo <wqu@suse.com>
---
 fs/btrfs/raid56.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 13a998628b90b..1ab77d658bf15 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -1082,11 +1082,8 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio,
 	}
 
 	/* put a new bio on the list */
-	bio = btrfs_bio_alloc(bio_max_len >> PAGE_SHIFT ?: 1);
-	btrfs_bio(bio)->device = stripe->dev;
-	bio->bi_iter.bi_size = 0;
-	bio_set_dev(bio, stripe->dev->bdev);
-	bio->bi_opf = opf;
+	bio = bio_alloc(stripe->dev->bdev, max(bio_max_len >> PAGE_SHIFT, 1UL),
+			opf, GFP_NOFS);
 	bio->bi_iter.bi_sector = disk_start >> 9;
 	bio->bi_private = rbio;
 
-- 
2.30.2

[PATCH 11/12] btrfs: don't allocate a btrfs_bio for scrub bios

[Christoph Hellwig]

All the scrub bios go straight to the block device or the raid56 code,
none of which looks at the btrfs_bio.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Qu Wenruo <wqu@suse.com>
---
 fs/btrfs/scrub.c | 47 ++++++++++++++++++-----------------------------
 1 file changed, 18 insertions(+), 29 deletions(-)

diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index fe25a0d3d7c2d..7de6479020a1b 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1411,8 +1411,8 @@ static void scrub_recheck_block_on_raid56(struct btrfs_fs_info *fs_info,
 	if (!first_sector->dev->bdev)
 		goto out;
 
-	bio = btrfs_bio_alloc(BIO_MAX_VECS);
-	bio_set_dev(bio, first_sector->dev->bdev);
+	bio = bio_alloc(first_sector->dev->bdev, BIO_MAX_VECS, REQ_OP_READ,
+			GFP_NOFS);
 
 	for (i = 0; i < sblock->sector_count; i++) {
 		struct scrub_sector *sector = sblock->sectors[i];
@@ -1642,8 +1642,6 @@ static int scrub_add_sector_to_wr_bio(struct scrub_ctx *sctx,
 	}
 	sbio = sctx->wr_curr_bio;
 	if (sbio->sector_count == 0) {
-		struct bio *bio;
-
 		ret = fill_writer_pointer_gap(sctx, sector->physical_for_dev_replace);
 		if (ret) {
 			mutex_unlock(&sctx->wr_lock);
@@ -1653,17 +1651,14 @@ static int scrub_add_sector_to_wr_bio(struct scrub_ctx *sctx,
 		sbio->physical = sector->physical_for_dev_replace;
 		sbio->logical = sector->logical;
 		sbio->dev = sctx->wr_tgtdev;
-		bio = sbio->bio;
-		if (!bio) {
-			bio = btrfs_bio_alloc(sctx->sectors_per_bio);
-			sbio->bio = bio;
+		if (!sbio->bio) {
+			sbio->bio = bio_alloc(sbio->dev->bdev,
+					      sctx->sectors_per_bio,
+					      REQ_OP_WRITE, GFP_NOFS);
 		}
-
-		bio->bi_private = sbio;
-		bio->bi_end_io = scrub_wr_bio_end_io;
-		bio_set_dev(bio, sbio->dev->bdev);
-		bio->bi_iter.bi_sector = sbio->physical >> 9;
-		bio->bi_opf = REQ_OP_WRITE;
+		sbio->bio->bi_private = sbio;
+		sbio->bio->bi_end_io = scrub_wr_bio_end_io;
+		sbio->bio->bi_iter.bi_sector = sbio->physical >> 9;
 		sbio->status = 0;
 	} else if (sbio->physical + sbio->sector_count * sectorsize !=
 		   sector->physical_for_dev_replace ||
@@ -1704,7 +1699,6 @@ static void scrub_wr_submit(struct scrub_ctx *sctx)
 
 	sbio = sctx->wr_curr_bio;
 	sctx->wr_curr_bio = NULL;
-	WARN_ON(!sbio->bio->bi_bdev);
 	scrub_pending_bio_inc(sctx);
 	/* process all writes in a single worker thread. Then the block layer
 	 * orders the requests before sending them to the driver which
@@ -2076,22 +2070,17 @@ static int scrub_add_sector_to_rd_bio(struct scrub_ctx *sctx,
 	}
 	sbio = sctx->bios[sctx->curr];
 	if (sbio->sector_count == 0) {
-		struct bio *bio;
-
 		sbio->physical = sector->physical;
 		sbio->logical = sector->logical;
 		sbio->dev = sector->dev;
-		bio = sbio->bio;
-		if (!bio) {
-			bio = btrfs_bio_alloc(sctx->sectors_per_bio);
-			sbio->bio = bio;
+		if (!sbio->bio) {
+			sbio->bio = bio_alloc(sbio->dev->bdev,
+					      sctx->sectors_per_bio,
+					      REQ_OP_READ, GFP_NOFS);
 		}
-
-		bio->bi_private = sbio;
-		bio->bi_end_io = scrub_bio_end_io;
-		bio_set_dev(bio, sbio->dev->bdev);
-		bio->bi_iter.bi_sector = sbio->physical >> 9;
-		bio->bi_opf = REQ_OP_READ;
+		sbio->bio->bi_private = sbio;
+		sbio->bio->bi_end_io = scrub_bio_end_io;
+		sbio->bio->bi_iter.bi_sector = sbio->physical >> 9;
 		sbio->status = 0;
 	} else if (sbio->physical + sbio->sector_count * sectorsize !=
 		   sector->physical ||
@@ -2207,7 +2196,7 @@ static void scrub_missing_raid56_pages(struct scrub_block *sblock)
 		goto bioc_out;
 	}
 
-	bio = btrfs_bio_alloc(BIO_MAX_VECS);
+	bio = bio_alloc(NULL, BIO_MAX_VECS, REQ_OP_READ, GFP_NOFS);
 	bio->bi_iter.bi_sector = logical >> 9;
 	bio->bi_private = sblock;
 	bio->bi_end_io = scrub_missing_raid56_end_io;
@@ -2823,7 +2812,7 @@ static void scrub_parity_check_and_repair(struct scrub_parity *sparity)
 	if (ret || !bioc || !bioc->raid_map)
 		goto bioc_out;
 
-	bio = btrfs_bio_alloc(BIO_MAX_VECS);
+	bio = bio_alloc(NULL, BIO_MAX_VECS, REQ_OP_READ, GFP_NOFS);
 	bio->bi_iter.bi_sector = sparity->logic_start >> 9;
 	bio->bi_private = sparity;
 	bio->bi_end_io = scrub_parity_bio_endio;
-- 
2.30.2

[PATCH 12/12] btrfs: stop using the btrfs_bio saved iter in index_rbio_pages

[Christoph Hellwig]

The bios added to ->bio_list are the original bios fed into
btrfs_map_bio, which are never advanced.  Just use the iter in the
bio itself.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/btrfs/raid56.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 1ab77d658bf15..adc62a7352b82 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -1134,9 +1134,6 @@ static void index_rbio_pages(struct btrfs_raid_bio *rbio)
 		stripe_offset = start - rbio->bioc->raid_map[0];
 		page_index = stripe_offset >> PAGE_SHIFT;
 
-		if (bio_flagged(bio, BIO_CLONED))
-			bio->bi_iter = btrfs_bio(bio)->iter;
-
 		bio_for_each_segment(bvec, bio, iter) {
 			rbio->bio_pages[page_index + i] = bvec.bv_page;
 			i++;
-- 
2.30.2

Re: [PATCH 01/12] btrfs: refactor __btrfsic_submit_bio

[Qu Wenruo]

On 2022/4/8 13:08, Christoph Hellwig wrote:
> Split out two helpers to mak __btrfsic_submit_bio more readable.
>
> Signed-off-by: Christoph Hellwig <hch@lst.de>

The refactor itself is already pretty good.

Reviewed-by: Qu Wenruo <wqu@suse.com>

Thanks,
Qu
> ---
>   fs/btrfs/check-integrity.c | 150 +++++++++++++++++++------------------
>   1 file changed, 78 insertions(+), 72 deletions(-)
>
> diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
> index b8f9dfa326207..ec8a73ff82717 100644
> --- a/fs/btrfs/check-integrity.c
> +++ b/fs/btrfs/check-integrity.c
> @@ -2633,6 +2633,74 @@ static struct btrfsic_dev_state *btrfsic_dev_state_lookup(dev_t dev)
>   						  &btrfsic_dev_state_hashtable);
>   }
>
> +static void btrfsic_check_write_bio(struct bio *bio,
> +		struct btrfsic_dev_state *dev_state)
> +{
> +	unsigned int segs = bio_segments(bio);
> +	u64 dev_bytenr = 512 * bio->bi_iter.bi_sector;
> +	u64 cur_bytenr = dev_bytenr;
> +	struct bvec_iter iter;
> +	struct bio_vec bvec;
> +	char **mapped_datav;
> +	int bio_is_patched = 0;
> +	int i = 0;
> +
> +	if (dev_state->state->print_mask & BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH)
> +		pr_info("submit_bio(rw=%d,0x%x, bi_vcnt=%u, bi_sector=%llu (bytenr %llu), bi_bdev=%p)\n",
> +		       bio_op(bio), bio->bi_opf, segs,
> +		       bio->bi_iter.bi_sector, dev_bytenr, bio->bi_bdev);
> +
> +	mapped_datav = kmalloc_array(segs, sizeof(*mapped_datav), GFP_NOFS);
> +	if (!mapped_datav)
> +		return;
> +
> +	bio_for_each_segment(bvec, bio, iter) {
> +		BUG_ON(bvec.bv_len != PAGE_SIZE);
> +		mapped_datav[i] = page_address(bvec.bv_page);
> +		i++;
> +
> +		if (dev_state->state->print_mask &
> +		    BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH_VERBOSE)
> +			pr_info("#%u: bytenr=%llu, len=%u, offset=%u\n",
> +			       i, cur_bytenr, bvec.bv_len, bvec.bv_offset);
> +		cur_bytenr += bvec.bv_len;
> +	}
> +
> +	btrfsic_process_written_block(dev_state, dev_bytenr, mapped_datav, segs,
> +				      bio, &bio_is_patched, bio->bi_opf);
> +	kfree(mapped_datav);
> +}
> +
> +static void btrfsic_check_flush_bio(struct bio *bio,
> +		struct btrfsic_dev_state *dev_state)
> +{
> +	if (dev_state->state->print_mask & BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH)
> +		pr_info("submit_bio(rw=%d,0x%x FLUSH, bdev=%p)\n",
> +		       bio_op(bio), bio->bi_opf, bio->bi_bdev);
> +
> +	if (dev_state->dummy_block_for_bio_bh_flush.is_iodone) {
> +		struct btrfsic_block *const block =
> +			&dev_state->dummy_block_for_bio_bh_flush;
> +
> +		block->is_iodone = 0;
> +		block->never_written = 0;
> +		block->iodone_w_error = 0;
> +		block->flush_gen = dev_state->last_flush_gen + 1;
> +		block->submit_bio_bh_rw = bio->bi_opf;
> +		block->orig_bio_private = bio->bi_private;
> +		block->orig_bio_end_io = bio->bi_end_io;
> +		block->next_in_same_bio = NULL;
> +		bio->bi_private = block;
> +		bio->bi_end_io = btrfsic_bio_end_io;
> +	} else if ((dev_state->state->print_mask &
> +		   (BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH |
> +		    BTRFSIC_PRINT_MASK_VERBOSE))) {
> +		pr_info(
> +"btrfsic_submit_bio(%pg) with FLUSH but dummy block already in use (ignored)!\n",
> +		       dev_state->bdev);
> +	}
> +}
> +
>   static void __btrfsic_submit_bio(struct bio *bio)
>   {
>   	struct btrfsic_dev_state *dev_state;
> @@ -2640,80 +2708,18 @@ static void __btrfsic_submit_bio(struct bio *bio)
>   	if (!btrfsic_is_initialized)
>   		return;
>
> -	mutex_lock(&btrfsic_mutex);
> -	/* since btrfsic_submit_bio() is also called before
> -	 * btrfsic_mount(), this might return NULL */
> +	/*
> +	 * We can be called before btrfsic_mount, so there might not be a
> +	 * dev_state.
> +	 */
>   	dev_state = btrfsic_dev_state_lookup(bio->bi_bdev->bd_dev);
> -	if (NULL != dev_state &&
> -	    (bio_op(bio) == REQ_OP_WRITE) && bio_has_data(bio)) {
> -		int i = 0;
> -		u64 dev_bytenr;
> -		u64 cur_bytenr;
> -		struct bio_vec bvec;
> -		struct bvec_iter iter;
> -		int bio_is_patched;
> -		char **mapped_datav;
> -		unsigned int segs = bio_segments(bio);
> -
> -		dev_bytenr = 512 * bio->bi_iter.bi_sector;
> -		bio_is_patched = 0;
> -		if (dev_state->state->print_mask &
> -		    BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH)
> -			pr_info("submit_bio(rw=%d,0x%x, bi_vcnt=%u, bi_sector=%llu (bytenr %llu), bi_bdev=%p)\n",
> -			       bio_op(bio), bio->bi_opf, segs,
> -			       bio->bi_iter.bi_sector, dev_bytenr, bio->bi_bdev);
> -
> -		mapped_datav = kmalloc_array(segs,
> -					     sizeof(*mapped_datav), GFP_NOFS);
> -		if (!mapped_datav)
> -			goto leave;
> -		cur_bytenr = dev_bytenr;
> -
> -		bio_for_each_segment(bvec, bio, iter) {
> -			BUG_ON(bvec.bv_len != PAGE_SIZE);
> -			mapped_datav[i] = page_address(bvec.bv_page);
> -			i++;
> -
> -			if (dev_state->state->print_mask &
> -			    BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH_VERBOSE)
> -				pr_info("#%u: bytenr=%llu, len=%u, offset=%u\n",
> -				       i, cur_bytenr, bvec.bv_len, bvec.bv_offset);
> -			cur_bytenr += bvec.bv_len;
> -		}
> -		btrfsic_process_written_block(dev_state, dev_bytenr,
> -					      mapped_datav, segs,
> -					      bio, &bio_is_patched,
> -					      bio->bi_opf);
> -		kfree(mapped_datav);
> -	} else if (NULL != dev_state && (bio->bi_opf & REQ_PREFLUSH)) {
> -		if (dev_state->state->print_mask &
> -		    BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH)
> -			pr_info("submit_bio(rw=%d,0x%x FLUSH, bdev=%p)\n",
> -			       bio_op(bio), bio->bi_opf, bio->bi_bdev);
> -		if (!dev_state->dummy_block_for_bio_bh_flush.is_iodone) {
> -			if ((dev_state->state->print_mask &
> -			     (BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH |
> -			      BTRFSIC_PRINT_MASK_VERBOSE)))
> -				pr_info(
> -"btrfsic_submit_bio(%pg) with FLUSH but dummy block already in use (ignored)!\n",
> -				       dev_state->bdev);
> -		} else {
> -			struct btrfsic_block *const block =
> -				&dev_state->dummy_block_for_bio_bh_flush;
> -
> -			block->is_iodone = 0;
> -			block->never_written = 0;
> -			block->iodone_w_error = 0;
> -			block->flush_gen = dev_state->last_flush_gen + 1;
> -			block->submit_bio_bh_rw = bio->bi_opf;
> -			block->orig_bio_private = bio->bi_private;
> -			block->orig_bio_end_io = bio->bi_end_io;
> -			block->next_in_same_bio = NULL;
> -			bio->bi_private = block;
> -			bio->bi_end_io = btrfsic_bio_end_io;
> -		}
> +	mutex_lock(&btrfsic_mutex);
> +	if (dev_state) {
> +		if (bio_op(bio) == REQ_OP_WRITE && bio_has_data(bio))
> +			btrfsic_check_write_bio(bio, dev_state);
> +		else if (bio->bi_opf & REQ_PREFLUSH)
> +			btrfsic_check_flush_bio(bio, dev_state);
>   	}
> -leave:
>   	mutex_unlock(&btrfsic_mutex);
>   }
>

Re: [PATCH 03/12] btrfs: simplify btrfsic_read_block

[Qu Wenruo]

On 2022/4/8 13:08, Christoph Hellwig wrote:
> btrfsic_read_block does not need the btrfs_bio structure, so switch to
> plain bio_alloc.
>
> Signed-off-by: Christoph Hellwig <hch@lst.de>

Reviewed-by: Qu Wenruo <wqu@suse.com>

Thanks,
Qu
> ---
>   fs/btrfs/check-integrity.c | 5 ++---
>   1 file changed, 2 insertions(+), 3 deletions(-)
>
> diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
> index 9efd33b4e24d7..864a90e825050 100644
> --- a/fs/btrfs/check-integrity.c
> +++ b/fs/btrfs/check-integrity.c
> @@ -1561,10 +1561,9 @@ static int btrfsic_read_block(struct btrfsic_state *state,
>   		struct bio *bio;
>   		unsigned int j;
>
> -		bio = btrfs_bio_alloc(num_pages - i);
> -		bio_set_dev(bio, block_ctx->dev->bdev);
> +		bio = bio_alloc(block_ctx->dev->bdev, num_pages - i,
> +				REQ_OP_READ, GFP_NOFS);
>   		bio->bi_iter.bi_sector = dev_bytenr >> 9;
> -		bio->bi_opf = REQ_OP_READ;
>
>   		for (j = i; j < num_pages; j++) {
>   			ret = bio_add_page(bio, block_ctx->pagev[j],

Re: [PATCH 07/12] btrfs: move the call to bio_set_dev out of submit_stripe_bio

[Qu Wenruo]

On 2022/4/8 13:08, Christoph Hellwig wrote:
> Prepare for additional refactoring.
>
> Signed-off-by: Christoph Hellwig <hch@lst.de>

The change is small enough and doesn't make much sense by itself.

Mind to fold it into the patch which needs this change?

Thanks,
Qu
> ---
>   fs/btrfs/volumes.c | 2 +-
>   1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
> index 6b49d78d15029..8e066b9ebfbde 100644
> --- a/fs/btrfs/volumes.c
> +++ b/fs/btrfs/volumes.c
> @@ -6738,7 +6738,6 @@ static void submit_stripe_bio(struct btrfs_io_context *bioc, struct bio *bio,
>   		bio_op(bio), bio->bi_opf, bio->bi_iter.bi_sector,
>   		(unsigned long)dev->bdev->bd_dev, rcu_str_deref(dev->name),
>   		dev->devid, bio->bi_iter.bi_size);
> -	bio_set_dev(bio, dev->bdev);
>
>   	btrfs_bio_counter_inc_noblocked(fs_info);
>
> @@ -6830,6 +6829,7 @@ blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
>   		else
>   			bio = first_bio;
>
> +		bio_set_dev(bio, dev->bdev);
>   		submit_stripe_bio(bioc, bio, bioc->stripes[dev_nr].physical, dev);
>   	}
>   	btrfs_bio_counter_dec(fs_info);

Re: [PATCH 12/12] btrfs: stop using the btrfs_bio saved iter in index_rbio_pages

[Qu Wenruo]

On 2022/4/8 13:08, Christoph Hellwig wrote:
> The bios added to ->bio_list are the original bios fed into
> btrfs_map_bio, which are never advanced.  Just use the iter in the
> bio itself.
>
> Signed-off-by: Christoph Hellwig <hch@lst.de>

Reviewed-by: Qu Wenruo <wqu@suse.com>

In fact, the bio split at btrfs_map_bio() time will make all endio
functions to only utilize btrfs_bio::iter.
Thus bi_iter will be even less utilized.

Thanks,
Qu

> ---
>   fs/btrfs/raid56.c | 3 ---
>   1 file changed, 3 deletions(-)
>
> diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
> index 1ab77d658bf15..adc62a7352b82 100644
> --- a/fs/btrfs/raid56.c
> +++ b/fs/btrfs/raid56.c
> @@ -1134,9 +1134,6 @@ static void index_rbio_pages(struct btrfs_raid_bio *rbio)
>   		stripe_offset = start - rbio->bioc->raid_map[0];
>   		page_index = stripe_offset >> PAGE_SHIFT;
>
> -		if (bio_flagged(bio, BIO_CLONED))
> -			bio->bi_iter = btrfs_bio(bio)->iter;
> -
>   		bio_for_each_segment(bvec, bio, iter) {
>   			rbio->bio_pages[page_index + i] = bvec.bv_page;
>   			i++;

Re: [PATCH 07/12] btrfs: move the call to bio_set_dev out of submit_stripe_bio

[David Sterba]

On Fri, Apr 08, 2022 at 03:27:21PM +0800, Qu Wenruo wrote:
> 
> 
> On 2022/4/8 13:08, Christoph Hellwig wrote:
> > Prepare for additional refactoring.
> >
> > Signed-off-by: Christoph Hellwig <hch@lst.de>
> 
> The change is small enough and doesn't make much sense by itself.
> 
> Mind to fold it into the patch which needs this change?

Not necessary and I think it's better to make moving the call stand out,
it's the one that's hidden but very important.

Re: cleanup btrfs bio handling, part 1 v2

[David Sterba]

On Fri, Apr 08, 2022 at 07:08:27AM +0200, Christoph Hellwig wrote:
> Hi all,
> 
> this series  moves btrfs to use the new as of 5.18 bio interface and
> cleans up a few close by areas.  Larger cleanups focussed around
> the btrfs_bio will follow as a next step.
> 
> Changes since v1:
>  - rebased to btrfs/misc-next
>  - improve a commit log

Series added to misc-next, thanks. I compared the version I had locally
with the v2, there were only 2 lines swapped, besides the minor style
fixups and reworded subjects when they were too generic.

[PATCH 10/12] btrfs: don't allocate a btrfs_bio for raid56 per-stripe bios

[Christoph Hellwig]

Except for the spurious initialization of ->device just after allocation
nothing uses the btrfs_bio, so just allocate a normal bio without extra
data.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Qu Wenruo <wqu@suse.com>
---
 fs/btrfs/raid56.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 2f1f7ca27acd5..a0d65f4b2b258 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -1103,11 +1103,8 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio,
 	}
 
 	/* put a new bio on the list */
-	bio = btrfs_bio_alloc(bio_max_len >> PAGE_SHIFT ?: 1);
-	btrfs_bio(bio)->device = stripe->dev;
-	bio->bi_iter.bi_size = 0;
-	bio_set_dev(bio, stripe->dev->bdev);
-	bio->bi_opf = opf;
+	bio = bio_alloc(stripe->dev->bdev, max(bio_max_len >> PAGE_SHIFT, 1UL),
+			opf, GFP_NOFS);
 	bio->bi_iter.bi_sector = disk_start >> 9;
 	bio->bi_private = rbio;
 
-- 
2.30.2