diff options
author | Christoph Hellwig <hch@lst.de> | 2022-11-15 12:44:05 +0300 |
---|---|---|
committer | David Sterba <dsterba@suse.com> | 2022-12-05 20:00:57 +0300 |
commit | 103c19723c80bf74e4e70cd6cde3b8783a27aceb (patch) | |
tree | 2a78636927002cbb72c58a4ef811dca8a362f7c3 | |
parent | 27137fac4c0628fc8320bb7f1ce3bb9f84b76a9b (diff) | |
download | linux-103c19723c80bf74e4e70cd6cde3b8783a27aceb.tar.xz |
btrfs: split the bio submission path into a separate file
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.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
-rw-r--r-- | fs/btrfs/Makefile | 2 | ||||
-rw-r--r-- | fs/btrfs/bio.c | 291 | ||||
-rw-r--r-- | fs/btrfs/bio.h | 127 | ||||
-rw-r--r-- | fs/btrfs/compression.c | 2 | ||||
-rw-r--r-- | fs/btrfs/disk-io.c | 2 | ||||
-rw-r--r-- | fs/btrfs/extent-tree.c | 1 | ||||
-rw-r--r-- | fs/btrfs/extent_io.c | 2 | ||||
-rw-r--r-- | fs/btrfs/file-item.c | 2 | ||||
-rw-r--r-- | fs/btrfs/inode.c | 2 | ||||
-rw-r--r-- | fs/btrfs/relocation.c | 1 | ||||
-rw-r--r-- | fs/btrfs/super.c | 2 | ||||
-rw-r--r-- | fs/btrfs/tree-log.c | 1 | ||||
-rw-r--r-- | fs/btrfs/volumes.c | 296 | ||||
-rw-r--r-- | fs/btrfs/volumes.h | 110 |
14 files changed, 438 insertions, 403 deletions
diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile index 84fb3b4c35b0..555c962fdad6 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 000000000000..9e881dc91bae --- /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, btrfs_dev_name(dev), + 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 000000000000..b12f84b3b341 --- /dev/null +++ b/fs/btrfs/bio.h @@ -0,0 +1,127 @@ +/* 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 "tree-checker.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 diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index 30adf430241e..5122ca79f7ea 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/disk-io.c b/fs/btrfs/disk-io.c index 91a088210e5a..d5be259845d1 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 17f599027c3d..892d78c1853c 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 "tree-checker.h" #undef SCRAMBLE_DELAYED_REFS diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 65ba5c3658cf..95d54b5834c0 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 352bbb33b76f..5de73466b2ca 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 4248e6cabbdc..905ea19df125 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 aa80e51bc8ca..31ec4a7658ce 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 "tree-checker.h" /* * Relocation overview diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index ea83dd9f735a..93f52ee85f6f 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 8f8d7e7dc3a8..4387cd2ade97 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 "tree-checker.h" #define MAX_CONFLICT_INODES 10 diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index e51fd5f1042a..acab20f2863d 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 @@ -6364,11 +6352,11 @@ 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; @@ -6651,266 +6639,6 @@ 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, btrfs_dev_name(dev), - 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) { @@ -8440,17 +8168,3 @@ 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 ab551471c1f8..6b7a05f6cf82 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -6,7 +6,6 @@ #ifndef BTRFS_VOLUMES_H #define BTRFS_VOLUMES_H -#include <linux/bio.h> #include <linux/sort.h> #include <linux/btrfs.h> #include "async-thread.h" @@ -373,8 +372,6 @@ 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) @@ -384,107 +381,6 @@ 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 { @@ -641,6 +537,11 @@ 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); @@ -652,7 +553,6 @@ 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, |