move the low-level btrfs_bio code into a separate file v2

move the low-level btrfs_bio code into a separate file v2

[Christoph Hellwig]

Hi all,

this small series creates a new bio.c file (and a bio.h header for it)
to contain all the "storage" layer code below btrfs_submit_bio.  The
amount of code sitting below btrfs_submit_bio will grow a lot with
the "consolidate btrfs checksumming, repair and bio splitting" series,
so this pure code move series triest to prepare for that by making
sure we have a neat file to add it to.

Changes since v1:
 - rebased to the latest misc-next branch
 - added a new patch to move struct btrfs_tree_parent_check into a new
   header to invoide include hell

[PATCH 1/3] btrfs: move struct btrfs_tree_parent_check out of disk-io.h

[Christoph Hellwig]

Move struct btrfs_tree_parent_check out of disk-io.h so that volumes.h
an various .c files don't have to include disk-io.h just for it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/btrfs/backref.c      |  1 +
 fs/btrfs/disk-io.h      | 30 +-----------------------------
 fs/btrfs/parent-check.h | 36 ++++++++++++++++++++++++++++++++++++
 fs/btrfs/print-tree.c   |  1 +
 fs/btrfs/qgroup.c       |  1 +
 fs/btrfs/tree-mod-log.c |  1 +
 fs/btrfs/volumes.h      |  2 +-
 7 files changed, 42 insertions(+), 30 deletions(-)
 create mode 100644 fs/btrfs/parent-check.h

diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 55c072ba67471..9496aa93a8dcc 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -19,6 +19,7 @@
 #include "accessors.h"
 #include "extent-tree.h"
 #include "relocation.h"
+#include "parent-check.h"
 
 /* Just arbitrary numbers so we can be sure one of these happened. */
 #define BACKREF_FOUND_SHARED     6
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index 03fe4154ffb83..363935cfc0844 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -25,37 +25,9 @@ static inline u64 btrfs_sb_offset(int mirror)
 	return BTRFS_SUPER_INFO_OFFSET;
 }
 
-/* All the extra info needed to verify the parentness of a tree block. */
-struct btrfs_tree_parent_check {
-	/*
-	 * The owner check against the tree block.
-	 *
-	 * Can be 0 to skip the owner check.
-	 */
-	u64 owner_root;
-
-	/*
-	 * Expected transid, can be 0 to skip the check, but such skip
-	 * should only be utlized for backref walk related code.
-	 */
-	u64 transid;
-
-	/*
-	 * The expected first key.
-	 *
-	 * This check can be skipped if @has_first_key is false, such skip
-	 * can happen for case where we don't have the parent node key,
-	 * e.g. reading the tree root, doing backref walk.
-	 */
-	struct btrfs_key first_key;
-	bool has_first_key;
-
-	/* The expected level. Should always be set. */
-	u8 level;
-};
-
 struct btrfs_device;
 struct btrfs_fs_devices;
+struct btrfs_tree_parent_check;
 
 void btrfs_check_leaked_roots(struct btrfs_fs_info *fs_info);
 void btrfs_init_fs_info(struct btrfs_fs_info *fs_info);
diff --git a/fs/btrfs/parent-check.h b/fs/btrfs/parent-check.h
new file mode 100644
index 0000000000000..333f23ea28e25
--- /dev/null
+++ b/fs/btrfs/parent-check.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef BTRFS_PARENT_CHECK_H
+#define BTRFS_PARENT_CHECK_H
+
+#include <uapi/linux/btrfs_tree.h>
+
+/* All the extra info needed to verify the parentness of a tree block. */
+struct btrfs_tree_parent_check {
+	/*
+	 * The owner check against the tree block.
+	 *
+	 * Can be 0 to skip the owner check.
+	 */
+	u64 owner_root;
+
+	/*
+	 * Expected transid, can be 0 to skip the check, but such skip
+	 * should only be utlized for backref walk related code.
+	 */
+	u64 transid;
+
+	/*
+	 * The expected first key.
+	 *
+	 * This check can be skipped if @has_first_key is false, such skip
+	 * can happen for case where we don't have the parent node key,
+	 * e.g. reading the tree root, doing backref walk.
+	 */
+	struct btrfs_key first_key;
+	bool has_first_key;
+
+	/* The expected level. Should always be set. */
+	u8 level;
+};
+
+#endif /* BTRFS_PARENT_CHECK_H */
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index 1469aa55ad482..00d5da5f3c333 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -8,6 +8,7 @@
 #include "disk-io.h"
 #include "print-tree.h"
 #include "accessors.h"
+#include "parent-check.h"
 
 struct root_name_map {
 	u64 id;
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 05e79f7b4433a..365482ad0421b 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -28,6 +28,7 @@
 #include "accessors.h"
 #include "extent-tree.h"
 #include "root-tree.h"
+#include "parent-check.h"
 
 /*
  * Helpers to access qgroup reservation
diff --git a/fs/btrfs/tree-mod-log.c b/fs/btrfs/tree-mod-log.c
index 779ad44d285f8..5b91a2a88a398 100644
--- a/fs/btrfs/tree-mod-log.c
+++ b/fs/btrfs/tree-mod-log.c
@@ -5,6 +5,7 @@
 #include "disk-io.h"
 #include "fs.h"
 #include "accessors.h"
+#include "parent-check.h"
 
 struct tree_mod_root {
 	u64 logical;
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index efa6a3d48cd8d..bcf544849b6d5 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -11,7 +11,7 @@
 #include <linux/btrfs.h>
 #include "async-thread.h"
 #include "messages.h"
-#include "disk-io.h"
+#include "parent-check.h"
 
 #define BTRFS_MAX_DATA_CHUNK_SIZE	(10ULL * SZ_1G)
 
-- 
2.30.2

[PATCH 2/3] btrfs: split the bio submission path into a separate file

[Christoph Hellwig]

The code used by btrfs_submit_bio only interacts with the rest of
volumes.c through __btrfs_map_block (which itself is a more generic
version of two exported helpers) and does not really have anything
to do with volumes.c.  Create a new bio.c file and a bio.h header
going along with it for the btrfs_bio-based storage layer, which
will grow even more going forward.

Also update the file with my copyright notice given that a large
part of the moved code was written or rewritten by me.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
---
 fs/btrfs/Makefile      |   2 +-
 fs/btrfs/bio.c         | 291 ++++++++++++++++++++++++++++++++++++++++
 fs/btrfs/bio.h         | 126 ++++++++++++++++++
 fs/btrfs/compression.c |   2 +-
 fs/btrfs/ctree.c       |   1 +
 fs/btrfs/disk-io.c     |   2 +-
 fs/btrfs/extent-tree.c |   1 +
 fs/btrfs/extent_io.c   |   2 +-
 fs/btrfs/file-item.c   |   2 +-
 fs/btrfs/inode.c       |   2 +-
 fs/btrfs/relocation.c  |   1 +
 fs/btrfs/super.c       |   2 +-
 fs/btrfs/tree-log.c    |   1 +
 fs/btrfs/volumes.c     | 296 +----------------------------------------
 fs/btrfs/volumes.h     | 111 +---------------
 15 files changed, 438 insertions(+), 404 deletions(-)
 create mode 100644 fs/btrfs/bio.c
 create mode 100644 fs/btrfs/bio.h

diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile
index 84fb3b4c35b07..555c962fdad66 100644
--- a/fs/btrfs/Makefile
+++ b/fs/btrfs/Makefile
@@ -31,7 +31,7 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \
 	   backref.o ulist.o qgroup.o send.o dev-replace.o raid56.o \
 	   uuid-tree.o props.o free-space-tree.o tree-checker.o space-info.o \
 	   block-rsv.o delalloc-space.o block-group.o discard.o reflink.o \
-	   subpage.o tree-mod-log.o extent-io-tree.o fs.o messages.o
+	   subpage.o tree-mod-log.o extent-io-tree.o fs.o messages.o bio.o
 
 btrfs-$(CONFIG_BTRFS_FS_POSIX_ACL) += acl.o
 btrfs-$(CONFIG_BTRFS_FS_CHECK_INTEGRITY) += check-integrity.o
diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c
new file mode 100644
index 0000000000000..0887ea3b7cc20
--- /dev/null
+++ b/fs/btrfs/bio.c
@@ -0,0 +1,291 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2007 Oracle.  All rights reserved.
+ * Copyright (C) 2022 Christoph Hellwig.
+ */
+#include <linux/bio.h>
+#include "bio.h"
+#include "ctree.h"
+#include "volumes.h"
+#include "raid56.h"
+#include "async-thread.h"
+#include "check-integrity.h"
+#include "dev-replace.h"
+#include "rcu-string.h"
+#include "zoned.h"
+
+static struct bio_set btrfs_bioset;
+
+/*
+ * Initialize a btrfs_bio structure.  This skips the embedded bio itself as it
+ * is already initialized by the block layer.
+ */
+static inline void btrfs_bio_init(struct btrfs_bio *bbio,
+				  btrfs_bio_end_io_t end_io, void *private)
+{
+	memset(bbio, 0, offsetof(struct btrfs_bio, bio));
+	bbio->end_io = end_io;
+	bbio->private = private;
+}
+
+/*
+ * Allocate a btrfs_bio structure.  The btrfs_bio is the main I/O container for
+ * btrfs, and is used for all I/O submitted through btrfs_submit_bio.
+ *
+ * Just like the underlying bio_alloc_bioset it will not fail as it is backed by
+ * a mempool.
+ */
+struct bio *btrfs_bio_alloc(unsigned int nr_vecs, blk_opf_t opf,
+			    btrfs_bio_end_io_t end_io, void *private)
+{
+	struct bio *bio;
+
+	bio = bio_alloc_bioset(NULL, nr_vecs, opf, GFP_NOFS, &btrfs_bioset);
+	btrfs_bio_init(btrfs_bio(bio), end_io, private);
+	return bio;
+}
+
+struct bio *btrfs_bio_clone_partial(struct bio *orig, u64 offset, u64 size,
+				    btrfs_bio_end_io_t end_io, void *private)
+{
+	struct bio *bio;
+	struct btrfs_bio *bbio;
+
+	ASSERT(offset <= UINT_MAX && size <= UINT_MAX);
+
+	bio = bio_alloc_clone(orig->bi_bdev, orig, GFP_NOFS, &btrfs_bioset);
+	bbio = btrfs_bio(bio);
+	btrfs_bio_init(bbio, end_io, private);
+
+	bio_trim(bio, offset >> 9, size >> 9);
+	bbio->iter = bio->bi_iter;
+	return bio;
+}
+
+static void btrfs_log_dev_io_error(struct bio *bio, struct btrfs_device *dev)
+{
+	if (!dev || !dev->bdev)
+		return;
+	if (bio->bi_status != BLK_STS_IOERR && bio->bi_status != BLK_STS_TARGET)
+		return;
+
+	if (btrfs_op(bio) == BTRFS_MAP_WRITE)
+		btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS);
+	if (!(bio->bi_opf & REQ_RAHEAD))
+		btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_READ_ERRS);
+	if (bio->bi_opf & REQ_PREFLUSH)
+		btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_FLUSH_ERRS);
+}
+
+static struct workqueue_struct *btrfs_end_io_wq(struct btrfs_fs_info *fs_info,
+						struct bio *bio)
+{
+	if (bio->bi_opf & REQ_META)
+		return fs_info->endio_meta_workers;
+	return fs_info->endio_workers;
+}
+
+static void btrfs_end_bio_work(struct work_struct *work)
+{
+	struct btrfs_bio *bbio =
+		container_of(work, struct btrfs_bio, end_io_work);
+
+	bbio->end_io(bbio);
+}
+
+static void btrfs_simple_end_io(struct bio *bio)
+{
+	struct btrfs_fs_info *fs_info = bio->bi_private;
+	struct btrfs_bio *bbio = btrfs_bio(bio);
+
+	btrfs_bio_counter_dec(fs_info);
+
+	if (bio->bi_status)
+		btrfs_log_dev_io_error(bio, bbio->device);
+
+	if (bio_op(bio) == REQ_OP_READ) {
+		INIT_WORK(&bbio->end_io_work, btrfs_end_bio_work);
+		queue_work(btrfs_end_io_wq(fs_info, bio), &bbio->end_io_work);
+	} else {
+		bbio->end_io(bbio);
+	}
+}
+
+static void btrfs_raid56_end_io(struct bio *bio)
+{
+	struct btrfs_io_context *bioc = bio->bi_private;
+	struct btrfs_bio *bbio = btrfs_bio(bio);
+
+	btrfs_bio_counter_dec(bioc->fs_info);
+	bbio->mirror_num = bioc->mirror_num;
+	bbio->end_io(bbio);
+
+	btrfs_put_bioc(bioc);
+}
+
+static void btrfs_orig_write_end_io(struct bio *bio)
+{
+	struct btrfs_io_stripe *stripe = bio->bi_private;
+	struct btrfs_io_context *bioc = stripe->bioc;
+	struct btrfs_bio *bbio = btrfs_bio(bio);
+
+	btrfs_bio_counter_dec(bioc->fs_info);
+
+	if (bio->bi_status) {
+		atomic_inc(&bioc->error);
+		btrfs_log_dev_io_error(bio, stripe->dev);
+	}
+
+	/*
+	 * Only send an error to the higher layers if it is beyond the tolerance
+	 * threshold.
+	 */
+	if (atomic_read(&bioc->error) > bioc->max_errors)
+		bio->bi_status = BLK_STS_IOERR;
+	else
+		bio->bi_status = BLK_STS_OK;
+
+	bbio->end_io(bbio);
+	btrfs_put_bioc(bioc);
+}
+
+static void btrfs_clone_write_end_io(struct bio *bio)
+{
+	struct btrfs_io_stripe *stripe = bio->bi_private;
+
+	if (bio->bi_status) {
+		atomic_inc(&stripe->bioc->error);
+		btrfs_log_dev_io_error(bio, stripe->dev);
+	}
+
+	/* Pass on control to the original bio this one was cloned from */
+	bio_endio(stripe->bioc->orig_bio);
+	bio_put(bio);
+}
+
+static void btrfs_submit_dev_bio(struct btrfs_device *dev, struct bio *bio)
+{
+	if (!dev || !dev->bdev ||
+	    test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state) ||
+	    (btrfs_op(bio) == BTRFS_MAP_WRITE &&
+	     !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state))) {
+		bio_io_error(bio);
+		return;
+	}
+
+	bio_set_dev(bio, dev->bdev);
+
+	/*
+	 * For zone append writing, bi_sector must point the beginning of the
+	 * zone
+	 */
+	if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
+		u64 physical = bio->bi_iter.bi_sector << SECTOR_SHIFT;
+
+		if (btrfs_dev_is_sequential(dev, physical)) {
+			u64 zone_start = round_down(physical,
+						    dev->fs_info->zone_size);
+
+			bio->bi_iter.bi_sector = zone_start >> SECTOR_SHIFT;
+		} else {
+			bio->bi_opf &= ~REQ_OP_ZONE_APPEND;
+			bio->bi_opf |= REQ_OP_WRITE;
+		}
+	}
+	btrfs_debug_in_rcu(dev->fs_info,
+	"%s: rw %d 0x%x, sector=%llu, dev=%lu (%s id %llu), size=%u",
+		__func__, 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);
+
+	btrfsic_check_bio(bio);
+	submit_bio(bio);
+}
+
+static void btrfs_submit_mirrored_bio(struct btrfs_io_context *bioc, int dev_nr)
+{
+	struct bio *orig_bio = bioc->orig_bio, *bio;
+
+	ASSERT(bio_op(orig_bio) != REQ_OP_READ);
+
+	/* Reuse the bio embedded into the btrfs_bio for the last mirror */
+	if (dev_nr == bioc->num_stripes - 1) {
+		bio = orig_bio;
+		bio->bi_end_io = btrfs_orig_write_end_io;
+	} else {
+		bio = bio_alloc_clone(NULL, orig_bio, GFP_NOFS, &fs_bio_set);
+		bio_inc_remaining(orig_bio);
+		bio->bi_end_io = btrfs_clone_write_end_io;
+	}
+
+	bio->bi_private = &bioc->stripes[dev_nr];
+	bio->bi_iter.bi_sector = bioc->stripes[dev_nr].physical >> SECTOR_SHIFT;
+	bioc->stripes[dev_nr].bioc = bioc;
+	btrfs_submit_dev_bio(bioc->stripes[dev_nr].dev, bio);
+}
+
+void btrfs_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio, int mirror_num)
+{
+	u64 logical = bio->bi_iter.bi_sector << 9;
+	u64 length = bio->bi_iter.bi_size;
+	u64 map_length = length;
+	struct btrfs_io_context *bioc = NULL;
+	struct btrfs_io_stripe smap;
+	int ret;
+
+	btrfs_bio_counter_inc_blocked(fs_info);
+	ret = __btrfs_map_block(fs_info, btrfs_op(bio), logical, &map_length,
+				&bioc, &smap, &mirror_num, 1);
+	if (ret) {
+		btrfs_bio_counter_dec(fs_info);
+		btrfs_bio_end_io(btrfs_bio(bio), errno_to_blk_status(ret));
+		return;
+	}
+
+	if (map_length < length) {
+		btrfs_crit(fs_info,
+			   "mapping failed logical %llu bio len %llu len %llu",
+			   logical, length, map_length);
+		BUG();
+	}
+
+	if (!bioc) {
+		/* Single mirror read/write fast path */
+		btrfs_bio(bio)->mirror_num = mirror_num;
+		btrfs_bio(bio)->device = smap.dev;
+		bio->bi_iter.bi_sector = smap.physical >> SECTOR_SHIFT;
+		bio->bi_private = fs_info;
+		bio->bi_end_io = btrfs_simple_end_io;
+		btrfs_submit_dev_bio(smap.dev, bio);
+	} else if (bioc->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
+		/* Parity RAID write or read recovery */
+		bio->bi_private = bioc;
+		bio->bi_end_io = btrfs_raid56_end_io;
+		if (bio_op(bio) == REQ_OP_READ)
+			raid56_parity_recover(bio, bioc, mirror_num);
+		else
+			raid56_parity_write(bio, bioc);
+	} else {
+		/* Write to multiple mirrors */
+		int total_devs = bioc->num_stripes;
+		int dev_nr;
+
+		bioc->orig_bio = bio;
+		for (dev_nr = 0; dev_nr < total_devs; dev_nr++)
+			btrfs_submit_mirrored_bio(bioc, dev_nr);
+	}
+}
+
+int __init btrfs_bioset_init(void)
+{
+	if (bioset_init(&btrfs_bioset, BIO_POOL_SIZE,
+			offsetof(struct btrfs_bio, bio),
+			BIOSET_NEED_BVECS))
+		return -ENOMEM;
+	return 0;
+}
+
+void __cold btrfs_bioset_exit(void)
+{
+	bioset_exit(&btrfs_bioset);
+}
diff --git a/fs/btrfs/bio.h b/fs/btrfs/bio.h
new file mode 100644
index 0000000000000..4aa3bfc753911
--- /dev/null
+++ b/fs/btrfs/bio.h
@@ -0,0 +1,126 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2007 Oracle.  All rights reserved.
+ * Copyright (C) 2022 Christoph Hellwig.
+ */
+#ifndef BTRFS_BIO_H
+#define BTRFS_BIO_H
+
+#include <linux/bio.h>
+#include <linux/workqueue.h>
+#include "parent-check.h"
+
+struct btrfs_bio;
+struct btrfs_fs_info;
+
+#define BTRFS_BIO_INLINE_CSUM_SIZE	64
+
+/*
+ * Maximum number of sectors for a single bio to limit the size of the
+ * checksum array.  This matches the number of bio_vecs per bio and thus the
+ * I/O size for buffered I/O.
+ */
+#define BTRFS_MAX_BIO_SECTORS		(256)
+
+typedef void (*btrfs_bio_end_io_t)(struct btrfs_bio *bbio);
+
+/*
+ * Additional info to pass along bio.
+ *
+ * Mostly for btrfs specific features like csum and mirror_num.
+ */
+struct btrfs_bio {
+	unsigned int mirror_num:7;
+
+	/*
+	 * Extra indicator for metadata bios.
+	 * For some btrfs bios they use pages without a mapping, thus
+	 * we can not rely on page->mapping->host to determine if
+	 * it's a metadata bio.
+	 */
+	unsigned int is_metadata:1;
+	struct bvec_iter iter;
+
+	/* for direct I/O */
+	u64 file_offset;
+
+	/* @device is for stripe IO submission. */
+	struct btrfs_device *device;
+	union {
+		/* For data checksum verification. */
+		struct {
+			u8 *csum;
+			u8 csum_inline[BTRFS_BIO_INLINE_CSUM_SIZE];
+		};
+
+		/* For metadata parentness verification. */
+		struct btrfs_tree_parent_check parent_check;
+	};
+
+	/* End I/O information supplied to btrfs_bio_alloc */
+	btrfs_bio_end_io_t end_io;
+	void *private;
+
+	/* For read end I/O handling */
+	struct work_struct end_io_work;
+
+	/*
+	 * This member must come last, bio_alloc_bioset will allocate enough
+	 * bytes for entire btrfs_bio but relies on bio being last.
+	 */
+	struct bio bio;
+};
+
+static inline struct btrfs_bio *btrfs_bio(struct bio *bio)
+{
+	return container_of(bio, struct btrfs_bio, bio);
+}
+
+int __init btrfs_bioset_init(void);
+void __cold btrfs_bioset_exit(void);
+
+struct bio *btrfs_bio_alloc(unsigned int nr_vecs, blk_opf_t opf,
+			    btrfs_bio_end_io_t end_io, void *private);
+struct bio *btrfs_bio_clone_partial(struct bio *orig, u64 offset, u64 size,
+				    btrfs_bio_end_io_t end_io, void *private);
+
+
+static inline void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status)
+{
+	bbio->bio.bi_status = status;
+	bbio->end_io(bbio);
+}
+
+static inline void btrfs_bio_free_csum(struct btrfs_bio *bbio)
+{
+	if (bbio->is_metadata)
+		return;
+	if (bbio->csum != bbio->csum_inline) {
+		kfree(bbio->csum);
+		bbio->csum = NULL;
+	}
+}
+
+/*
+ * Iterate through a btrfs_bio (@bbio) on a per-sector basis.
+ *
+ * bvl        - struct bio_vec
+ * bbio       - struct btrfs_bio
+ * iters      - struct bvec_iter
+ * bio_offset - unsigned int
+ */
+#define btrfs_bio_for_each_sector(fs_info, bvl, bbio, iter, bio_offset)	\
+	for ((iter) = (bbio)->iter, (bio_offset) = 0;			\
+	     (iter).bi_size &&					\
+	     (((bvl) = bio_iter_iovec((&(bbio)->bio), (iter))), 1);	\
+	     (bio_offset) += fs_info->sectorsize,			\
+	     bio_advance_iter_single(&(bbio)->bio, &(iter),		\
+	     (fs_info)->sectorsize))
+
+void btrfs_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
+		      int mirror_num);
+int btrfs_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);
+
+#endif /* BTRFS_BIO_H */
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index ef07aeab2e853..68cd7a2c92978 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -27,7 +27,7 @@
 #include "disk-io.h"
 #include "transaction.h"
 #include "btrfs_inode.h"
-#include "volumes.h"
+#include "bio.h"
 #include "ordered-data.h"
 #include "compression.h"
 #include "extent_io.h"
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index f75e398d7b712..23b1443988ee3 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -22,6 +22,7 @@
 #include "accessors.h"
 #include "extent-tree.h"
 #include "relocation.h"
+#include "parent-check.h"
 
 static struct kmem_cache *btrfs_path_cachep;
 
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 559e7f3d727e1..352fc117992de 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -23,7 +23,7 @@
 #include "disk-io.h"
 #include "transaction.h"
 #include "btrfs_inode.h"
-#include "volumes.h"
+#include "bio.h"
 #include "print-tree.h"
 #include "locking.h"
 #include "tree-log.h"
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 10cc757a602b0..c243156caba59 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -42,6 +42,7 @@
 #include "root-tree.h"
 #include "file-item.h"
 #include "orphan.h"
+#include "parent-check.h"
 
 #undef SCRAMBLE_DELAYED_REFS
 
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 704ae7c088679..d4289370c0864 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -20,7 +20,7 @@
 #include "extent_map.h"
 #include "ctree.h"
 #include "btrfs_inode.h"
-#include "volumes.h"
+#include "bio.h"
 #include "check-integrity.h"
 #include "locking.h"
 #include "rcu-string.h"
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 456f71b42a9c8..493dfd691fe3f 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -14,7 +14,7 @@
 #include "ctree.h"
 #include "disk-io.h"
 #include "transaction.h"
-#include "volumes.h"
+#include "bio.h"
 #include "print-tree.h"
 #include "compression.h"
 #include "fs.h"
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 83898bca39d5c..324fc52797fca 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -43,7 +43,7 @@
 #include "ordered-data.h"
 #include "xattr.h"
 #include "tree-log.h"
-#include "volumes.h"
+#include "bio.h"
 #include "compression.h"
 #include "locking.h"
 #include "free-space-cache.h"
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 56c8afa6f6d2b..9f509606250e1 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -35,6 +35,7 @@
 #include "file-item.h"
 #include "relocation.h"
 #include "super.h"
+#include "parent-check.h"
 
 /*
  * Relocation overview
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index d54bfec8e5064..af5edd43ea936 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -35,7 +35,7 @@
 #include "print-tree.h"
 #include "props.h"
 #include "xattr.h"
-#include "volumes.h"
+#include "bio.h"
 #include "export.h"
 #include "compression.h"
 #include "rcu-string.h"
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index b2528d5694fb5..781457dcfd519 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -29,6 +29,7 @@
 #include "file-item.h"
 #include "file.h"
 #include "orphan.h"
+#include "parent-check.h"
 
 #define MAX_CONFLICT_INODES 10
 
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 49d6e79d4343b..5d25b9fa88c66 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -5,12 +5,9 @@
 
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
-#include <linux/bio.h>
 #include <linux/slab.h>
-#include <linux/blkdev.h>
 #include <linux/ratelimit.h>
 #include <linux/kthread.h>
-#include <linux/raid/pq.h>
 #include <linux/semaphore.h>
 #include <linux/uuid.h>
 #include <linux/list_sort.h>
@@ -23,8 +20,6 @@
 #include "print-tree.h"
 #include "volumes.h"
 #include "raid56.h"
-#include "async-thread.h"
-#include "check-integrity.h"
 #include "rcu-string.h"
 #include "dev-replace.h"
 #include "sysfs.h"
@@ -41,8 +36,6 @@
 #include "scrub.h"
 #include "super.h"
 
-static struct bio_set btrfs_bioset;
-
 #define BTRFS_BLOCK_GROUP_STRIPE_MASK	(BTRFS_BLOCK_GROUP_RAID0 | \
 					 BTRFS_BLOCK_GROUP_RAID10 | \
 					 BTRFS_BLOCK_GROUP_RAID56_MASK)
@@ -255,11 +248,6 @@ out_overflow:;
 static int init_first_rw_device(struct btrfs_trans_handle *trans);
 static int btrfs_relocate_sys_chunks(struct btrfs_fs_info *fs_info);
 static void btrfs_dev_stat_print_on_load(struct btrfs_device *device);
-static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
-			     enum btrfs_map_op op, u64 logical, u64 *length,
-			     struct btrfs_io_context **bioc_ret,
-			     struct btrfs_io_stripe *smap,
-			     int *mirror_num_ret, int need_raid_map);
 
 /*
  * Device locking
@@ -6361,11 +6349,11 @@ static void set_io_stripe(struct btrfs_io_stripe *dst, const struct map_lookup *
 			stripe_offset + stripe_nr * map->stripe_len;
 }
 
-static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
-			     enum btrfs_map_op op, u64 logical, u64 *length,
-			     struct btrfs_io_context **bioc_ret,
-			     struct btrfs_io_stripe *smap,
-			     int *mirror_num_ret, int need_raid_map)
+int __btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
+		      u64 logical, u64 *length,
+		      struct btrfs_io_context **bioc_ret,
+		      struct btrfs_io_stripe *smap, int *mirror_num_ret,
+		      int need_raid_map)
 {
 	struct extent_map *em;
 	struct map_lookup *map;
@@ -6648,266 +6636,6 @@ int btrfs_map_sblock(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 				 NULL, NULL, 1);
 }
 
-/*
- * Initialize a btrfs_bio structure.  This skips the embedded bio itself as it
- * is already initialized by the block layer.
- */
-static inline void btrfs_bio_init(struct btrfs_bio *bbio,
-				  btrfs_bio_end_io_t end_io, void *private)
-{
-	memset(bbio, 0, offsetof(struct btrfs_bio, bio));
-	bbio->end_io = end_io;
-	bbio->private = private;
-}
-
-/*
- * Allocate a btrfs_bio structure.  The btrfs_bio is the main I/O container for
- * btrfs, and is used for all I/O submitted through btrfs_submit_bio.
- *
- * Just like the underlying bio_alloc_bioset it will not fail as it is backed by
- * a mempool.
- */
-struct bio *btrfs_bio_alloc(unsigned int nr_vecs, blk_opf_t opf,
-			    btrfs_bio_end_io_t end_io, void *private)
-{
-	struct bio *bio;
-
-	bio = bio_alloc_bioset(NULL, nr_vecs, opf, GFP_NOFS, &btrfs_bioset);
-	btrfs_bio_init(btrfs_bio(bio), end_io, private);
-	return bio;
-}
-
-struct bio *btrfs_bio_clone_partial(struct bio *orig, u64 offset, u64 size,
-				    btrfs_bio_end_io_t end_io, void *private)
-{
-	struct bio *bio;
-	struct btrfs_bio *bbio;
-
-	ASSERT(offset <= UINT_MAX && size <= UINT_MAX);
-
-	bio = bio_alloc_clone(orig->bi_bdev, orig, GFP_NOFS, &btrfs_bioset);
-	bbio = btrfs_bio(bio);
-	btrfs_bio_init(bbio, end_io, private);
-
-	bio_trim(bio, offset >> 9, size >> 9);
-	bbio->iter = bio->bi_iter;
-	return bio;
-}
-
-static void btrfs_log_dev_io_error(struct bio *bio, struct btrfs_device *dev)
-{
-	if (!dev || !dev->bdev)
-		return;
-	if (bio->bi_status != BLK_STS_IOERR && bio->bi_status != BLK_STS_TARGET)
-		return;
-
-	if (btrfs_op(bio) == BTRFS_MAP_WRITE)
-		btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS);
-	if (!(bio->bi_opf & REQ_RAHEAD))
-		btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_READ_ERRS);
-	if (bio->bi_opf & REQ_PREFLUSH)
-		btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_FLUSH_ERRS);
-}
-
-static struct workqueue_struct *btrfs_end_io_wq(struct btrfs_fs_info *fs_info,
-						struct bio *bio)
-{
-	if (bio->bi_opf & REQ_META)
-		return fs_info->endio_meta_workers;
-	return fs_info->endio_workers;
-}
-
-static void btrfs_end_bio_work(struct work_struct *work)
-{
-	struct btrfs_bio *bbio =
-		container_of(work, struct btrfs_bio, end_io_work);
-
-	bbio->end_io(bbio);
-}
-
-static void btrfs_simple_end_io(struct bio *bio)
-{
-	struct btrfs_fs_info *fs_info = bio->bi_private;
-	struct btrfs_bio *bbio = btrfs_bio(bio);
-
-	btrfs_bio_counter_dec(fs_info);
-
-	if (bio->bi_status)
-		btrfs_log_dev_io_error(bio, bbio->device);
-
-	if (bio_op(bio) == REQ_OP_READ) {
-		INIT_WORK(&bbio->end_io_work, btrfs_end_bio_work);
-		queue_work(btrfs_end_io_wq(fs_info, bio), &bbio->end_io_work);
-	} else {
-		bbio->end_io(bbio);
-	}
-}
-
-static void btrfs_raid56_end_io(struct bio *bio)
-{
-	struct btrfs_io_context *bioc = bio->bi_private;
-	struct btrfs_bio *bbio = btrfs_bio(bio);
-
-	btrfs_bio_counter_dec(bioc->fs_info);
-	bbio->mirror_num = bioc->mirror_num;
-	bbio->end_io(bbio);
-
-	btrfs_put_bioc(bioc);
-}
-
-static void btrfs_orig_write_end_io(struct bio *bio)
-{
-	struct btrfs_io_stripe *stripe = bio->bi_private;
-	struct btrfs_io_context *bioc = stripe->bioc;
-	struct btrfs_bio *bbio = btrfs_bio(bio);
-
-	btrfs_bio_counter_dec(bioc->fs_info);
-
-	if (bio->bi_status) {
-		atomic_inc(&bioc->error);
-		btrfs_log_dev_io_error(bio, stripe->dev);
-	}
-
-	/*
-	 * Only send an error to the higher layers if it is beyond the tolerance
-	 * threshold.
-	 */
-	if (atomic_read(&bioc->error) > bioc->max_errors)
-		bio->bi_status = BLK_STS_IOERR;
-	else
-		bio->bi_status = BLK_STS_OK;
-
-	bbio->end_io(bbio);
-	btrfs_put_bioc(bioc);
-}
-
-static void btrfs_clone_write_end_io(struct bio *bio)
-{
-	struct btrfs_io_stripe *stripe = bio->bi_private;
-
-	if (bio->bi_status) {
-		atomic_inc(&stripe->bioc->error);
-		btrfs_log_dev_io_error(bio, stripe->dev);
-	}
-
-	/* Pass on control to the original bio this one was cloned from */
-	bio_endio(stripe->bioc->orig_bio);
-	bio_put(bio);
-}
-
-static void btrfs_submit_dev_bio(struct btrfs_device *dev, struct bio *bio)
-{
-	if (!dev || !dev->bdev ||
-	    test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state) ||
-	    (btrfs_op(bio) == BTRFS_MAP_WRITE &&
-	     !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state))) {
-		bio_io_error(bio);
-		return;
-	}
-
-	bio_set_dev(bio, dev->bdev);
-
-	/*
-	 * For zone append writing, bi_sector must point the beginning of the
-	 * zone
-	 */
-	if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
-		u64 physical = bio->bi_iter.bi_sector << SECTOR_SHIFT;
-
-		if (btrfs_dev_is_sequential(dev, physical)) {
-			u64 zone_start = round_down(physical,
-						    dev->fs_info->zone_size);
-
-			bio->bi_iter.bi_sector = zone_start >> SECTOR_SHIFT;
-		} else {
-			bio->bi_opf &= ~REQ_OP_ZONE_APPEND;
-			bio->bi_opf |= REQ_OP_WRITE;
-		}
-	}
-	btrfs_debug_in_rcu(dev->fs_info,
-	"%s: rw %d 0x%x, sector=%llu, dev=%lu (%s id %llu), size=%u",
-		__func__, 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);
-
-	btrfsic_check_bio(bio);
-	submit_bio(bio);
-}
-
-static void btrfs_submit_mirrored_bio(struct btrfs_io_context *bioc, int dev_nr)
-{
-	struct bio *orig_bio = bioc->orig_bio, *bio;
-
-	ASSERT(bio_op(orig_bio) != REQ_OP_READ);
-
-	/* Reuse the bio embedded into the btrfs_bio for the last mirror */
-	if (dev_nr == bioc->num_stripes - 1) {
-		bio = orig_bio;
-		bio->bi_end_io = btrfs_orig_write_end_io;
-	} else {
-		bio = bio_alloc_clone(NULL, orig_bio, GFP_NOFS, &fs_bio_set);
-		bio_inc_remaining(orig_bio);
-		bio->bi_end_io = btrfs_clone_write_end_io;
-	}
-
-	bio->bi_private = &bioc->stripes[dev_nr];
-	bio->bi_iter.bi_sector = bioc->stripes[dev_nr].physical >> SECTOR_SHIFT;
-	bioc->stripes[dev_nr].bioc = bioc;
-	btrfs_submit_dev_bio(bioc->stripes[dev_nr].dev, bio);
-}
-
-void btrfs_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio, int mirror_num)
-{
-	u64 logical = bio->bi_iter.bi_sector << 9;
-	u64 length = bio->bi_iter.bi_size;
-	u64 map_length = length;
-	struct btrfs_io_context *bioc = NULL;
-	struct btrfs_io_stripe smap;
-	int ret;
-
-	btrfs_bio_counter_inc_blocked(fs_info);
-	ret = __btrfs_map_block(fs_info, btrfs_op(bio), logical, &map_length,
-				&bioc, &smap, &mirror_num, 1);
-	if (ret) {
-		btrfs_bio_counter_dec(fs_info);
-		btrfs_bio_end_io(btrfs_bio(bio), errno_to_blk_status(ret));
-		return;
-	}
-
-	if (map_length < length) {
-		btrfs_crit(fs_info,
-			   "mapping failed logical %llu bio len %llu len %llu",
-			   logical, length, map_length);
-		BUG();
-	}
-
-	if (!bioc) {
-		/* Single mirror read/write fast path */
-		btrfs_bio(bio)->mirror_num = mirror_num;
-		btrfs_bio(bio)->device = smap.dev;
-		bio->bi_iter.bi_sector = smap.physical >> SECTOR_SHIFT;
-		bio->bi_private = fs_info;
-		bio->bi_end_io = btrfs_simple_end_io;
-		btrfs_submit_dev_bio(smap.dev, bio);
-	} else if (bioc->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
-		/* Parity RAID write or read recovery */
-		bio->bi_private = bioc;
-		bio->bi_end_io = btrfs_raid56_end_io;
-		if (bio_op(bio) == REQ_OP_READ)
-			raid56_parity_recover(bio, bioc, mirror_num);
-		else
-			raid56_parity_write(bio, bioc);
-	} else {
-		/* Write to multiple mirrors */
-		int total_devs = bioc->num_stripes;
-		int dev_nr;
-
-		bioc->orig_bio = bio;
-		for (dev_nr = 0; dev_nr < total_devs; dev_nr++)
-			btrfs_submit_mirrored_bio(bioc, dev_nr);
-	}
-}
-
 static bool dev_args_match_fs_devices(const struct btrfs_dev_lookup_args *args,
 				      const struct btrfs_fs_devices *fs_devices)
 {
@@ -8437,17 +8165,3 @@ bool btrfs_repair_one_zone(struct btrfs_fs_info *fs_info, u64 logical)
 
 	return true;
 }
-
-int __init btrfs_bioset_init(void)
-{
-	if (bioset_init(&btrfs_bioset, BIO_POOL_SIZE,
-			offsetof(struct btrfs_bio, bio),
-			BIOSET_NEED_BVECS))
-		return -ENOMEM;
-	return 0;
-}
-
-void __cold btrfs_bioset_exit(void)
-{
-	bioset_exit(&btrfs_bioset);
-}
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index bcf544849b6d5..55657d7593a7f 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -6,12 +6,10 @@
 #ifndef BTRFS_VOLUMES_H
 #define BTRFS_VOLUMES_H
 
-#include <linux/bio.h>
 #include <linux/sort.h>
 #include <linux/btrfs.h>
 #include "async-thread.h"
 #include "messages.h"
-#include "parent-check.h"
 
 #define BTRFS_MAX_DATA_CHUNK_SIZE	(10ULL * SZ_1G)
 
@@ -372,8 +370,6 @@ struct btrfs_fs_devices {
 	enum btrfs_read_policy read_policy;
 };
 
-#define BTRFS_BIO_INLINE_CSUM_SIZE	64
-
 #define BTRFS_MAX_DEVS(info) ((BTRFS_MAX_ITEM_SIZE(info)	\
 			- sizeof(struct btrfs_chunk))		\
 			/ sizeof(struct btrfs_stripe) + 1)
@@ -383,107 +379,6 @@ struct btrfs_fs_devices {
 				- 2 * sizeof(struct btrfs_chunk))	\
 				/ sizeof(struct btrfs_stripe) + 1)
 
-/*
- * Maximum number of sectors for a single bio to limit the size of the
- * checksum array.  This matches the number of bio_vecs per bio and thus the
- * I/O size for buffered I/O.
- */
-#define BTRFS_MAX_BIO_SECTORS				(256)
-
-typedef void (*btrfs_bio_end_io_t)(struct btrfs_bio *bbio);
-
-/*
- * Additional info to pass along bio.
- *
- * Mostly for btrfs specific features like csum and mirror_num.
- */
-struct btrfs_bio {
-	unsigned int mirror_num:7;
-
-	/*
-	 * Extra indicator for metadata bios.
-	 * For some btrfs bios they use pages without a mapping, thus
-	 * we can not rely on page->mapping->host to determine if
-	 * it's a metadata bio.
-	 */
-	unsigned int is_metadata:1;
-	struct bvec_iter iter;
-
-	/* for direct I/O */
-	u64 file_offset;
-
-	/* @device is for stripe IO submission. */
-	struct btrfs_device *device;
-	union {
-		/* For data checksum verification. */
-		struct {
-			u8 *csum;
-			u8 csum_inline[BTRFS_BIO_INLINE_CSUM_SIZE];
-		};
-
-		/* For metadata parentness verification. */
-		struct btrfs_tree_parent_check parent_check;
-	};
-
-	/* End I/O information supplied to btrfs_bio_alloc */
-	btrfs_bio_end_io_t end_io;
-	void *private;
-
-	/* For read end I/O handling */
-	struct work_struct end_io_work;
-
-	/*
-	 * This member must come last, bio_alloc_bioset will allocate enough
-	 * bytes for entire btrfs_bio but relies on bio being last.
-	 */
-	struct bio bio;
-};
-
-static inline struct btrfs_bio *btrfs_bio(struct bio *bio)
-{
-	return container_of(bio, struct btrfs_bio, bio);
-}
-
-int __init btrfs_bioset_init(void);
-void __cold btrfs_bioset_exit(void);
-
-struct bio *btrfs_bio_alloc(unsigned int nr_vecs, blk_opf_t opf,
-			    btrfs_bio_end_io_t end_io, void *private);
-struct bio *btrfs_bio_clone_partial(struct bio *orig, u64 offset, u64 size,
-				    btrfs_bio_end_io_t end_io, void *private);
-
-static inline void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status)
-{
-	bbio->bio.bi_status = status;
-	bbio->end_io(bbio);
-}
-
-static inline void btrfs_bio_free_csum(struct btrfs_bio *bbio)
-{
-	if (bbio->is_metadata)
-		return;
-	if (bbio->csum != bbio->csum_inline) {
-		kfree(bbio->csum);
-		bbio->csum = NULL;
-	}
-}
-
-/*
- * Iterate through a btrfs_bio (@bbio) on a per-sector basis.
- *
- * bvl        - struct bio_vec
- * bbio       - struct btrfs_bio
- * iters      - struct bvec_iter
- * bio_offset - unsigned int
- */
-#define btrfs_bio_for_each_sector(fs_info, bvl, bbio, iter, bio_offset)	\
-	for ((iter) = (bbio)->iter, (bio_offset) = 0;			\
-	     (iter).bi_size &&					\
-	     (((bvl) = bio_iter_iovec((&(bbio)->bio), (iter))), 1);	\
-	     (bio_offset) += fs_info->sectorsize,			\
-	     bio_advance_iter_single(&(bbio)->bio, &(iter),		\
-	     (fs_info)->sectorsize))
-
 struct btrfs_io_stripe {
 	struct btrfs_device *dev;
 	union {
@@ -640,6 +535,11 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 int btrfs_map_sblock(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 		     u64 logical, u64 *length,
 		     struct btrfs_io_context **bioc_ret);
+int __btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
+		      u64 logical, u64 *length,
+		      struct btrfs_io_context **bioc_ret,
+		      struct btrfs_io_stripe *smap, int *mirror_num_ret,
+		      int need_raid_map);
 struct btrfs_discard_stripe *btrfs_map_discard(struct btrfs_fs_info *fs_info,
 					       u64 logical, u64 *length_ret,
 					       u32 *num_stripes);
@@ -651,7 +551,6 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info);
 struct btrfs_block_group *btrfs_create_chunk(struct btrfs_trans_handle *trans,
 					    u64 type);
 void btrfs_mapping_tree_free(struct extent_map_tree *tree);
-void btrfs_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio, int mirror_num);
 int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 		       fmode_t flags, void *holder);
 struct btrfs_device *btrfs_scan_one_device(const char *path,
-- 
2.30.2

[PATCH 3/3] btrfs: move repair_io_failure to bio.c

[Christoph Hellwig]

repair_io_failure ties directly into all the glory low-level details of
mapping a bio with a logic address to the actual physical location.
Move it right below btrfs_submit_bio to keep all the related logic
together.

Also move btrfs_repair_eb_io_failure to its caller in disk-io.c now that
repair_io_failure is available in a header.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
---
 fs/btrfs/bio.c       |  91 +++++++++++++++++++++++++++++++++
 fs/btrfs/disk-io.c   |  24 +++++++++
 fs/btrfs/extent_io.c | 118 +------------------------------------------
 fs/btrfs/extent_io.h |   1 -
 4 files changed, 117 insertions(+), 117 deletions(-)

diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c
index 0887ea3b7cc20..fc704d350647a 100644
--- a/fs/btrfs/bio.c
+++ b/fs/btrfs/bio.c
@@ -276,6 +276,97 @@ void btrfs_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio, int mirror
 	}
 }
 
+/*
+ * Submit a repair write.
+ *
+ * This bypasses btrfs_submit_bio deliberately, as that writes all copies in a
+ * RAID setup.  Here we only want to write the one bad copy, so we do the
+ * mapping ourselves and submit the bio directly.
+ *
+ * The I/O is issued sychronously to block the repair read completion from
+ * freeing the bio.
+ */
+int btrfs_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 btrfs_device *dev;
+	struct bio_vec bvec;
+	struct bio bio;
+	u64 map_length = 0;
+	u64 sector;
+	struct btrfs_io_context *bioc = NULL;
+	int ret = 0;
+
+	ASSERT(!(fs_info->sb->s_flags & SB_RDONLY));
+	BUG_ON(!mirror_num);
+
+	if (btrfs_repair_one_zone(fs_info, logical))
+		return 0;
+
+	map_length = length;
+
+	/*
+	 * Avoid races with device replace and make sure our bioc has devices
+	 * associated to its stripes that don't go away while we are doing the
+	 * read repair operation.
+	 */
+	btrfs_bio_counter_inc_blocked(fs_info);
+	if (btrfs_is_parity_mirror(fs_info, logical, length)) {
+		/*
+		 * Note that we don't use BTRFS_MAP_WRITE because it's supposed
+		 * to update all raid stripes, but here we just want to correct
+		 * bad stripe, thus BTRFS_MAP_READ is abused to only get the bad
+		 * stripe's dev and sector.
+		 */
+		ret = btrfs_map_block(fs_info, BTRFS_MAP_READ, logical,
+				      &map_length, &bioc, 0);
+		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)
+			goto out_counter_dec;
+		BUG_ON(mirror_num != bioc->mirror_num);
+	}
+
+	sector = bioc->stripes[bioc->mirror_num - 1].physical >> 9;
+	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)) {
+		ret = -EIO;
+		goto out_counter_dec;
+	}
+
+	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_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS);
+		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);
+	return ret;
+}
+
 int __init btrfs_bioset_init(void)
 {
 	if (bioset_init(&btrfs_bioset, BIO_POOL_SIZE,
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 352fc117992de..6f43985940b41 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -255,6 +255,30 @@ int btrfs_verify_level_key(struct extent_buffer *eb, int level,
 	return ret;
 }
 
+static int btrfs_repair_eb_io_failure(const struct extent_buffer *eb,
+				      int mirror_num)
+{
+	struct btrfs_fs_info *fs_info = eb->fs_info;
+	u64 start = eb->start;
+	int i, num_pages = num_extent_pages(eb);
+	int ret = 0;
+
+	if (sb_rdonly(fs_info->sb))
+		return -EROFS;
+
+	for (i = 0; i < num_pages; i++) {
+		struct page *p = eb->pages[i];
+
+		ret = btrfs_repair_io_failure(fs_info, 0, start, PAGE_SIZE,
+				start, p, start - page_offset(p), mirror_num);
+		if (ret)
+			break;
+		start += PAGE_SIZE;
+	}
+
+	return ret;
+}
+
 /*
  * helper to read a given tree block, doing retries as required when
  * the checksums don't match and we have alternate mirrors to try.
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index d4289370c0864..8528e7d3f38fe 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -531,120 +531,6 @@ static void free_io_failure(struct btrfs_inode *inode,
 	kfree(rec);
 }
 
-/*
- * this bypasses the standard btrfs submit functions deliberately, as
- * the standard behavior is to write all copies in a raid setup. here we only
- * want to write the one bad copy. so we do the mapping for ourselves and issue
- * submit_bio directly.
- * to avoid any synchronization issues, wait for the data after writing, which
- * actually prevents the read that triggered the error from finishing.
- * currently, there can be no more than two copies of every data bit. thus,
- * exactly one rewrite is required.
- */
-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 btrfs_device *dev;
-	struct bio_vec bvec;
-	struct bio bio;
-	u64 map_length = 0;
-	u64 sector;
-	struct btrfs_io_context *bioc = NULL;
-	int ret = 0;
-
-	ASSERT(!(fs_info->sb->s_flags & SB_RDONLY));
-	BUG_ON(!mirror_num);
-
-	if (btrfs_repair_one_zone(fs_info, logical))
-		return 0;
-
-	map_length = length;
-
-	/*
-	 * Avoid races with device replace and make sure our bioc has devices
-	 * associated to its stripes that don't go away while we are doing the
-	 * read repair operation.
-	 */
-	btrfs_bio_counter_inc_blocked(fs_info);
-	if (btrfs_is_parity_mirror(fs_info, logical, length)) {
-		/*
-		 * Note that we don't use BTRFS_MAP_WRITE because it's supposed
-		 * to update all raid stripes, but here we just want to correct
-		 * bad stripe, thus BTRFS_MAP_READ is abused to only get the bad
-		 * stripe's dev and sector.
-		 */
-		ret = btrfs_map_block(fs_info, BTRFS_MAP_READ, logical,
-				      &map_length, &bioc, 0);
-		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)
-			goto out_counter_dec;
-		BUG_ON(mirror_num != bioc->mirror_num);
-	}
-
-	sector = bioc->stripes[bioc->mirror_num - 1].physical >> 9;
-	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)) {
-		ret = -EIO;
-		goto out_counter_dec;
-	}
-
-	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_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS);
-		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);
-	return ret;
-}
-
-int btrfs_repair_eb_io_failure(const struct extent_buffer *eb, int mirror_num)
-{
-	struct btrfs_fs_info *fs_info = eb->fs_info;
-	u64 start = eb->start;
-	int i, num_pages = num_extent_pages(eb);
-	int ret = 0;
-
-	if (sb_rdonly(fs_info->sb))
-		return -EROFS;
-
-	for (i = 0; i < num_pages; i++) {
-		struct page *p = eb->pages[i];
-
-		ret = repair_io_failure(fs_info, 0, start, PAGE_SIZE, start, p,
-					start - page_offset(p), mirror_num);
-		if (ret)
-			break;
-		start += PAGE_SIZE;
-	}
-
-	return ret;
-}
-
 static int next_mirror(const struct io_failure_record *failrec, int cur_mirror)
 {
 	if (cur_mirror == failrec->num_copies)
@@ -692,7 +578,7 @@ int btrfs_clean_io_failure(struct btrfs_inode *inode, u64 start,
 	mirror = failrec->this_mirror;
 	do {
 		mirror = prev_mirror(failrec, mirror);
-		repair_io_failure(fs_info, ino, start, failrec->len,
+		btrfs_repair_io_failure(fs_info, ino, start, failrec->len,
 				  failrec->logical, page, pg_offset, mirror);
 	} while (mirror != failrec->failed_mirror);
 
@@ -823,7 +709,7 @@ int btrfs_repair_one_sector(struct btrfs_inode *inode, struct btrfs_bio *failed_
 	 *
 	 * Since we're only doing repair for one sector, we only need to get
 	 * a good copy of the failed sector and if we succeed, we have setup
-	 * everything for repair_io_failure to do the rest for us.
+	 * everything for btrfs_repair_io_failure to do the rest for us.
 	 */
 	failrec->this_mirror = next_mirror(failrec, failrec->this_mirror);
 	if (failrec->this_mirror == failrec->failed_mirror) {
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index a0bafc7f6c075..9b486419854eb 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -245,7 +245,6 @@ int extent_invalidate_folio(struct extent_io_tree *tree,
 int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array);
 
 void end_extent_writepage(struct page *page, int err, u64 start, u64 end);
-int btrfs_repair_eb_io_failure(const struct extent_buffer *eb, int mirror_num);
 
 /*
  * When IO fails, either with EIO or csum verification fails, we
-- 
2.30.2

Re: [PATCH 1/3] btrfs: move struct btrfs_tree_parent_check out of disk-io.h

[Qu Wenruo]

On 2022/11/14 00:24, Christoph Hellwig wrote:
> Move struct btrfs_tree_parent_check out of disk-io.h so that volumes.h
> an various .c files don't have to include disk-io.h just for it.
> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>

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

Thanks,
Qu
> ---
>   fs/btrfs/backref.c      |  1 +
>   fs/btrfs/disk-io.h      | 30 +-----------------------------
>   fs/btrfs/parent-check.h | 36 ++++++++++++++++++++++++++++++++++++
>   fs/btrfs/print-tree.c   |  1 +
>   fs/btrfs/qgroup.c       |  1 +
>   fs/btrfs/tree-mod-log.c |  1 +
>   fs/btrfs/volumes.h      |  2 +-
>   7 files changed, 42 insertions(+), 30 deletions(-)
>   create mode 100644 fs/btrfs/parent-check.h
> 
> diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
> index 55c072ba67471..9496aa93a8dcc 100644
> --- a/fs/btrfs/backref.c
> +++ b/fs/btrfs/backref.c
> @@ -19,6 +19,7 @@
>   #include "accessors.h"
>   #include "extent-tree.h"
>   #include "relocation.h"
> +#include "parent-check.h"
>   
>   /* Just arbitrary numbers so we can be sure one of these happened. */
>   #define BACKREF_FOUND_SHARED     6
> diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
> index 03fe4154ffb83..363935cfc0844 100644
> --- a/fs/btrfs/disk-io.h
> +++ b/fs/btrfs/disk-io.h
> @@ -25,37 +25,9 @@ static inline u64 btrfs_sb_offset(int mirror)
>   	return BTRFS_SUPER_INFO_OFFSET;
>   }
>   
> -/* All the extra info needed to verify the parentness of a tree block. */
> -struct btrfs_tree_parent_check {
> -	/*
> -	 * The owner check against the tree block.
> -	 *
> -	 * Can be 0 to skip the owner check.
> -	 */
> -	u64 owner_root;
> -
> -	/*
> -	 * Expected transid, can be 0 to skip the check, but such skip
> -	 * should only be utlized for backref walk related code.
> -	 */
> -	u64 transid;
> -
> -	/*
> -	 * The expected first key.
> -	 *
> -	 * This check can be skipped if @has_first_key is false, such skip
> -	 * can happen for case where we don't have the parent node key,
> -	 * e.g. reading the tree root, doing backref walk.
> -	 */
> -	struct btrfs_key first_key;
> -	bool has_first_key;
> -
> -	/* The expected level. Should always be set. */
> -	u8 level;
> -};
> -
>   struct btrfs_device;
>   struct btrfs_fs_devices;
> +struct btrfs_tree_parent_check;
>   
>   void btrfs_check_leaked_roots(struct btrfs_fs_info *fs_info);
>   void btrfs_init_fs_info(struct btrfs_fs_info *fs_info);
> diff --git a/fs/btrfs/parent-check.h b/fs/btrfs/parent-check.h
> new file mode 100644
> index 0000000000000..333f23ea28e25
> --- /dev/null
> +++ b/fs/btrfs/parent-check.h
> @@ -0,0 +1,36 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +#ifndef BTRFS_PARENT_CHECK_H
> +#define BTRFS_PARENT_CHECK_H
> +
> +#include <uapi/linux/btrfs_tree.h>
> +
> +/* All the extra info needed to verify the parentness of a tree block. */
> +struct btrfs_tree_parent_check {
> +	/*
> +	 * The owner check against the tree block.
> +	 *
> +	 * Can be 0 to skip the owner check.
> +	 */
> +	u64 owner_root;
> +
> +	/*
> +	 * Expected transid, can be 0 to skip the check, but such skip
> +	 * should only be utlized for backref walk related code.
> +	 */
> +	u64 transid;
> +
> +	/*
> +	 * The expected first key.
> +	 *
> +	 * This check can be skipped if @has_first_key is false, such skip
> +	 * can happen for case where we don't have the parent node key,
> +	 * e.g. reading the tree root, doing backref walk.
> +	 */
> +	struct btrfs_key first_key;
> +	bool has_first_key;
> +
> +	/* The expected level. Should always be set. */
> +	u8 level;
> +};
> +
> +#endif /* BTRFS_PARENT_CHECK_H */
> diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
> index 1469aa55ad482..00d5da5f3c333 100644
> --- a/fs/btrfs/print-tree.c
> +++ b/fs/btrfs/print-tree.c
> @@ -8,6 +8,7 @@
>   #include "disk-io.h"
>   #include "print-tree.h"
>   #include "accessors.h"
> +#include "parent-check.h"
>   
>   struct root_name_map {
>   	u64 id;
> diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
> index 05e79f7b4433a..365482ad0421b 100644
> --- a/fs/btrfs/qgroup.c
> +++ b/fs/btrfs/qgroup.c
> @@ -28,6 +28,7 @@
>   #include "accessors.h"
>   #include "extent-tree.h"
>   #include "root-tree.h"
> +#include "parent-check.h"
>   
>   /*
>    * Helpers to access qgroup reservation
> diff --git a/fs/btrfs/tree-mod-log.c b/fs/btrfs/tree-mod-log.c
> index 779ad44d285f8..5b91a2a88a398 100644
> --- a/fs/btrfs/tree-mod-log.c
> +++ b/fs/btrfs/tree-mod-log.c
> @@ -5,6 +5,7 @@
>   #include "disk-io.h"
>   #include "fs.h"
>   #include "accessors.h"
> +#include "parent-check.h"
>   
>   struct tree_mod_root {
>   	u64 logical;
> diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
> index efa6a3d48cd8d..bcf544849b6d5 100644
> --- a/fs/btrfs/volumes.h
> +++ b/fs/btrfs/volumes.h
> @@ -11,7 +11,7 @@
>   #include <linux/btrfs.h>
>   #include "async-thread.h"
>   #include "messages.h"
> -#include "disk-io.h"
> +#include "parent-check.h"
>   
>   #define BTRFS_MAX_DATA_CHUNK_SIZE	(10ULL * SZ_1G)
>   

Re: [PATCH 1/3] btrfs: move struct btrfs_tree_parent_check out of disk-io.h

[Johannes Thumshirn]

Looks good,
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>

Re: move the low-level btrfs_bio code into a separate file v2

[Christoph Hellwig]

FYI, I just sent a v3 as the rcu_string changes from last night caused
conflicts:

https://lore.kernel.org/linux-btrfs/20221115094407.1626250-1-hch@lst.de/T/