diff options
Diffstat (limited to 'fs/btrfs')
65 files changed, 1633 insertions, 1622 deletions
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index a2de5c05f97c..e2f478ecd7fd 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -219,8 +219,8 @@ static void free_pref(struct prelim_ref *ref) * A -1 return indicates ref1 is a 'lower' block than ref2, while 1 * indicates a 'higher' block. */ -static int prelim_ref_compare(struct prelim_ref *ref1, - struct prelim_ref *ref2) +static int prelim_ref_compare(const struct prelim_ref *ref1, + const struct prelim_ref *ref2) { if (ref1->level < ref2->level) return -1; @@ -251,7 +251,7 @@ static int prelim_ref_compare(struct prelim_ref *ref1, } static void update_share_count(struct share_check *sc, int oldcount, - int newcount, struct prelim_ref *newref) + int newcount, const struct prelim_ref *newref) { if ((!sc) || (oldcount == 0 && newcount < 1)) return; diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c index b4e31ae17cd9..fec5c6cde0a7 100644 --- a/fs/btrfs/bio.c +++ b/fs/btrfs/bio.c @@ -53,7 +53,7 @@ void btrfs_bio_init(struct btrfs_bio *bbio, struct btrfs_fs_info *fs_info, /* * 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. + * btrfs, and is used for all I/O submitted through btrfs_submit_bbio(). * * Just like the underlying bio_alloc_bioset it will not fail as it is backed by * a mempool. @@ -73,20 +73,13 @@ struct btrfs_bio *btrfs_bio_alloc(unsigned int nr_vecs, blk_opf_t opf, static struct btrfs_bio *btrfs_split_bio(struct btrfs_fs_info *fs_info, struct btrfs_bio *orig_bbio, - u64 map_length, bool use_append) + u64 map_length) { struct btrfs_bio *bbio; struct bio *bio; - if (use_append) { - unsigned int nr_segs; - - bio = bio_split_rw(&orig_bbio->bio, &fs_info->limits, &nr_segs, - &btrfs_clone_bioset, map_length); - } else { - bio = bio_split(&orig_bbio->bio, map_length >> SECTOR_SHIFT, - GFP_NOFS, &btrfs_clone_bioset); - } + bio = bio_split(&orig_bbio->bio, map_length >> SECTOR_SHIFT, GFP_NOFS, + &btrfs_clone_bioset); bbio = btrfs_bio(bio); btrfs_bio_init(bbio, fs_info, NULL, orig_bbio); bbio->inode = orig_bbio->inode; @@ -120,12 +113,6 @@ static void __btrfs_bio_end_io(struct btrfs_bio *bbio) } } -void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status) -{ - bbio->bio.bi_status = status; - __btrfs_bio_end_io(bbio); -} - static void btrfs_orig_write_end_io(struct bio *bio); static void btrfs_bbio_propagate_error(struct btrfs_bio *bbio, @@ -147,8 +134,9 @@ static void btrfs_bbio_propagate_error(struct btrfs_bio *bbio, } } -static void btrfs_orig_bbio_end_io(struct btrfs_bio *bbio) +void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status) { + bbio->bio.bi_status = status; if (bbio->bio.bi_pool == &btrfs_clone_bioset) { struct btrfs_bio *orig_bbio = bbio->private; @@ -179,7 +167,7 @@ static int prev_repair_mirror(struct btrfs_failed_bio *fbio, int cur_mirror) static void btrfs_repair_done(struct btrfs_failed_bio *fbio) { if (atomic_dec_and_test(&fbio->repair_count)) { - btrfs_orig_bbio_end_io(fbio->bbio); + btrfs_bio_end_io(fbio->bbio, fbio->bbio->bio.bi_status); mempool_free(fbio, &btrfs_failed_bio_pool); } } @@ -211,7 +199,7 @@ static void btrfs_end_repair_bio(struct btrfs_bio *repair_bbio, goto done; } - btrfs_submit_bio(repair_bbio, mirror); + btrfs_submit_bbio(repair_bbio, mirror); return; } @@ -280,7 +268,7 @@ static struct btrfs_failed_bio *repair_one_sector(struct btrfs_bio *failed_bbio, mirror = next_repair_mirror(fbio, failed_bbio->mirror_num); btrfs_debug(fs_info, "submitting repair read to mirror %d", mirror); - btrfs_submit_bio(repair_bbio, mirror); + btrfs_submit_bbio(repair_bbio, mirror); return fbio; } @@ -326,7 +314,7 @@ static void btrfs_check_read_bio(struct btrfs_bio *bbio, struct btrfs_device *de if (fbio) btrfs_repair_done(fbio); else - btrfs_orig_bbio_end_io(bbio); + btrfs_bio_end_io(bbio, bbio->bio.bi_status); } static void btrfs_log_dev_io_error(struct bio *bio, struct btrfs_device *dev) @@ -360,7 +348,7 @@ static void btrfs_end_bio_work(struct work_struct *work) if (is_data_bbio(bbio)) btrfs_check_read_bio(bbio, bbio->bio.bi_private); else - btrfs_orig_bbio_end_io(bbio); + btrfs_bio_end_io(bbio, bbio->bio.bi_status); } static void btrfs_simple_end_io(struct bio *bio) @@ -380,7 +368,7 @@ static void btrfs_simple_end_io(struct bio *bio) } else { if (bio_op(bio) == REQ_OP_ZONE_APPEND && !bio->bi_status) btrfs_record_physical_zoned(bbio); - btrfs_orig_bbio_end_io(bbio); + btrfs_bio_end_io(bbio, bbio->bio.bi_status); } } @@ -394,7 +382,7 @@ static void btrfs_raid56_end_io(struct bio *bio) if (bio_op(bio) == REQ_OP_READ && is_data_bbio(bbio)) btrfs_check_read_bio(bbio, NULL); else - btrfs_orig_bbio_end_io(bbio); + btrfs_bio_end_io(bbio, bbio->bio.bi_status); btrfs_put_bioc(bioc); } @@ -424,7 +412,7 @@ static void btrfs_orig_write_end_io(struct bio *bio) if (bio_op(bio) == REQ_OP_ZONE_APPEND && !bio->bi_status) stripe->physical = bio->bi_iter.bi_sector << SECTOR_SHIFT; - btrfs_orig_bbio_end_io(bbio); + btrfs_bio_end_io(bbio, bbio->bio.bi_status); btrfs_put_bioc(bioc); } @@ -502,8 +490,8 @@ static void btrfs_submit_mirrored_bio(struct btrfs_io_context *bioc, int dev_nr) btrfs_submit_dev_bio(bioc->stripes[dev_nr].dev, bio); } -static void __btrfs_submit_bio(struct bio *bio, struct btrfs_io_context *bioc, - struct btrfs_io_stripe *smap, int mirror_num) +static void btrfs_submit_bio(struct bio *bio, struct btrfs_io_context *bioc, + struct btrfs_io_stripe *smap, int mirror_num) { if (!bioc) { /* Single mirror read/write fast path. */ @@ -593,7 +581,7 @@ static void run_one_async_done(struct btrfs_work *work, bool do_free) /* If an error occurred we just want to clean up the bio and move on. */ if (bio->bi_status) { - btrfs_orig_bbio_end_io(async->bbio); + btrfs_bio_end_io(async->bbio, async->bbio->bio.bi_status); return; } @@ -603,7 +591,7 @@ static void run_one_async_done(struct btrfs_work *work, bool do_free) * context. This changes nothing when cgroups aren't in use. */ bio->bi_opf |= REQ_BTRFS_CGROUP_PUNT; - __btrfs_submit_bio(bio, async->bioc, &async->smap, async->mirror_num); + btrfs_submit_bio(bio, async->bioc, &async->smap, async->mirror_num); } static bool should_async_write(struct btrfs_bio *bbio) @@ -664,6 +652,19 @@ static bool btrfs_wq_submit_bio(struct btrfs_bio *bbio, return true; } +static u64 btrfs_append_map_length(struct btrfs_bio *bbio, u64 map_length) +{ + unsigned int nr_segs; + int sector_offset; + + map_length = min(map_length, bbio->fs_info->max_zone_append_size); + sector_offset = bio_split_rw_at(&bbio->bio, &bbio->fs_info->limits, + &nr_segs, map_length); + if (sector_offset) + return sector_offset << SECTOR_SHIFT; + return map_length; +} + static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num) { struct btrfs_inode *inode = bbio->inode; @@ -678,7 +679,10 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num) blk_status_t ret; int error; - smap.is_scrub = !bbio->inode; + if (!bbio->inode || btrfs_is_data_reloc_root(inode->root)) + smap.rst_search_commit_root = true; + else + smap.rst_search_commit_root = false; btrfs_bio_counter_inc_blocked(fs_info); error = btrfs_map_block(fs_info, btrfs_op(bio), logical, &map_length, @@ -690,10 +694,10 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num) map_length = min(map_length, length); if (use_append) - map_length = min(map_length, fs_info->max_zone_append_size); + map_length = btrfs_append_map_length(bbio, map_length); if (map_length < length) { - bbio = btrfs_split_bio(fs_info, bbio, map_length, use_append); + bbio = btrfs_split_bio(fs_info, bbio, map_length); bio = &bbio->bio; } @@ -749,7 +753,7 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num) } } - __btrfs_submit_bio(bio, bioc, &smap, mirror_num); + btrfs_submit_bio(bio, bioc, &smap, mirror_num); done: return map_length == length; @@ -765,16 +769,14 @@ fail: ASSERT(bbio->bio.bi_pool == &btrfs_clone_bioset); ASSERT(remaining); - remaining->bio.bi_status = ret; - btrfs_orig_bbio_end_io(remaining); + btrfs_bio_end_io(remaining, ret); } - bbio->bio.bi_status = ret; - btrfs_orig_bbio_end_io(bbio); + btrfs_bio_end_io(bbio, ret); /* Do not submit another chunk */ return true; } -void btrfs_submit_bio(struct btrfs_bio *bbio, int mirror_num) +void btrfs_submit_bbio(struct btrfs_bio *bbio, int mirror_num) { /* If bbio->inode is not populated, its file_offset must be 0. */ ASSERT(bbio->inode || bbio->file_offset == 0); @@ -786,7 +788,7 @@ void btrfs_submit_bio(struct btrfs_bio *bbio, int mirror_num) /* * Submit a repair write. * - * This bypasses btrfs_submit_bio deliberately, as that writes all copies in a + * This bypasses btrfs_submit_bbio() 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. * @@ -875,7 +877,7 @@ void btrfs_submit_repair_write(struct btrfs_bio *bbio, int mirror_num, bool dev_ ASSERT(smap.dev == fs_info->dev_replace.srcdev); smap.dev = fs_info->dev_replace.tgtdev; } - __btrfs_submit_bio(&bbio->bio, NULL, &smap, mirror_num); + btrfs_submit_bio(&bbio->bio, NULL, &smap, mirror_num); return; fail: diff --git a/fs/btrfs/bio.h b/fs/btrfs/bio.h index d9dd5276093d..e48612340745 100644 --- a/fs/btrfs/bio.h +++ b/fs/btrfs/bio.h @@ -29,7 +29,7 @@ typedef void (*btrfs_bio_end_io_t)(struct btrfs_bio *bbio); /* * Highlevel btrfs I/O structure. It is allocated by btrfs_bio_alloc and - * passed to btrfs_submit_bio for mapping to the physical devices. + * passed to btrfs_submit_bbio() for mapping to the physical devices. */ struct btrfs_bio { /* @@ -42,7 +42,7 @@ struct btrfs_bio { union { /* * For data reads: checksumming and original I/O information. - * (for internal use in the btrfs_submit_bio machinery only) + * (for internal use in the btrfs_submit_bbio() machinery only) */ struct { u8 *csum; @@ -104,7 +104,7 @@ void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status); /* Submit using blkcg_punt_bio_submit. */ #define REQ_BTRFS_CGROUP_PUNT REQ_FS_PRIVATE -void btrfs_submit_bio(struct btrfs_bio *bbio, int mirror_num); +void btrfs_submit_bbio(struct btrfs_bio *bbio, int mirror_num); void btrfs_submit_repair_write(struct btrfs_bio *bbio, int mirror_num, bool dev_replace); int btrfs_repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start, u64 length, u64 logical, struct folio *folio, diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 2e49d978f504..7980b2e33a92 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -23,7 +23,7 @@ #include "extent-tree.h" #ifdef CONFIG_BTRFS_DEBUG -int btrfs_should_fragment_free_space(struct btrfs_block_group *block_group) +int btrfs_should_fragment_free_space(const struct btrfs_block_group *block_group) { struct btrfs_fs_info *fs_info = block_group->fs_info; @@ -40,9 +40,9 @@ int btrfs_should_fragment_free_space(struct btrfs_block_group *block_group) * * Should be called with balance_lock held */ -static u64 get_restripe_target(struct btrfs_fs_info *fs_info, u64 flags) +static u64 get_restripe_target(const struct btrfs_fs_info *fs_info, u64 flags) { - struct btrfs_balance_control *bctl = fs_info->balance_ctl; + const struct btrfs_balance_control *bctl = fs_info->balance_ctl; u64 target = 0; if (!bctl) @@ -1415,9 +1415,9 @@ out: } static bool clean_pinned_extents(struct btrfs_trans_handle *trans, - struct btrfs_block_group *bg) + const struct btrfs_block_group *bg) { - struct btrfs_fs_info *fs_info = bg->fs_info; + struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_transaction *prev_trans = NULL; const u64 start = bg->start; const u64 end = start + bg->length - 1; @@ -1756,14 +1756,14 @@ static int reclaim_bgs_cmp(void *unused, const struct list_head *a, return bg1->used > bg2->used; } -static inline bool btrfs_should_reclaim(struct btrfs_fs_info *fs_info) +static inline bool btrfs_should_reclaim(const struct btrfs_fs_info *fs_info) { if (btrfs_is_zoned(fs_info)) return btrfs_zoned_should_reclaim(fs_info); return true; } -static bool should_reclaim_block_group(struct btrfs_block_group *bg, u64 bytes_freed) +static bool should_reclaim_block_group(const struct btrfs_block_group *bg, u64 bytes_freed) { const int thresh_pct = btrfs_calc_reclaim_threshold(bg->space_info); u64 thresh_bytes = mult_perc(bg->length, thresh_pct); @@ -2006,8 +2006,8 @@ void btrfs_mark_bg_to_reclaim(struct btrfs_block_group *bg) spin_unlock(&fs_info->unused_bgs_lock); } -static int read_bg_from_eb(struct btrfs_fs_info *fs_info, struct btrfs_key *key, - struct btrfs_path *path) +static int read_bg_from_eb(struct btrfs_fs_info *fs_info, const struct btrfs_key *key, + const struct btrfs_path *path) { struct btrfs_chunk_map *map; struct btrfs_block_group_item bg; @@ -2055,7 +2055,7 @@ out_free_map: static int find_first_block_group(struct btrfs_fs_info *fs_info, struct btrfs_path *path, - struct btrfs_key *key) + const struct btrfs_key *key) { struct btrfs_root *root = btrfs_block_group_root(fs_info); int ret; @@ -2640,8 +2640,8 @@ static int insert_block_group_item(struct btrfs_trans_handle *trans, } static int insert_dev_extent(struct btrfs_trans_handle *trans, - struct btrfs_device *device, u64 chunk_offset, - u64 start, u64 num_bytes) + const struct btrfs_device *device, u64 chunk_offset, + u64 start, u64 num_bytes) { struct btrfs_fs_info *fs_info = device->fs_info; struct btrfs_root *root = fs_info->dev_root; @@ -2817,7 +2817,7 @@ next: * For extent tree v2 we use the block_group_item->chunk_offset to point at our * global root id. For v1 it's always set to BTRFS_FIRST_CHUNK_TREE_OBJECTID. */ -static u64 calculate_global_root_id(struct btrfs_fs_info *fs_info, u64 offset) +static u64 calculate_global_root_id(const struct btrfs_fs_info *fs_info, u64 offset) { u64 div = SZ_1G; u64 index; @@ -3842,8 +3842,8 @@ static void force_metadata_allocation(struct btrfs_fs_info *info) } } -static int should_alloc_chunk(struct btrfs_fs_info *fs_info, - struct btrfs_space_info *sinfo, int force) +static int should_alloc_chunk(const struct btrfs_fs_info *fs_info, + const struct btrfs_space_info *sinfo, int force) { u64 bytes_used = btrfs_space_info_used(sinfo, false); u64 thresh; @@ -4218,7 +4218,7 @@ out: return ret; } -static u64 get_profile_num_devs(struct btrfs_fs_info *fs_info, u64 type) +static u64 get_profile_num_devs(const struct btrfs_fs_info *fs_info, u64 type) { u64 num_dev; @@ -4622,7 +4622,7 @@ int btrfs_use_block_group_size_class(struct btrfs_block_group *bg, return 0; } -bool btrfs_block_group_should_use_size_class(struct btrfs_block_group *bg) +bool btrfs_block_group_should_use_size_class(const struct btrfs_block_group *bg) { if (btrfs_is_zoned(bg->fs_info)) return false; diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index 915111338fc0..36937eeab9b8 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -266,7 +266,7 @@ struct btrfs_block_group { u64 reclaim_mark; }; -static inline u64 btrfs_block_group_end(struct btrfs_block_group *block_group) +static inline u64 btrfs_block_group_end(const struct btrfs_block_group *block_group) { return (block_group->start + block_group->length); } @@ -278,8 +278,7 @@ static inline bool btrfs_is_block_group_used(const struct btrfs_block_group *bg) return (bg->used > 0 || bg->reserved > 0 || bg->pinned > 0); } -static inline bool btrfs_is_block_group_data_only( - struct btrfs_block_group *block_group) +static inline bool btrfs_is_block_group_data_only(const struct btrfs_block_group *block_group) { /* * In mixed mode the fragmentation is expected to be high, lowering the @@ -290,7 +289,7 @@ static inline bool btrfs_is_block_group_data_only( } #ifdef CONFIG_BTRFS_DEBUG -int btrfs_should_fragment_free_space(struct btrfs_block_group *block_group); +int btrfs_should_fragment_free_space(const struct btrfs_block_group *block_group); #endif struct btrfs_block_group *btrfs_lookup_first_block_group( @@ -370,7 +369,7 @@ static inline u64 btrfs_system_alloc_profile(struct btrfs_fs_info *fs_info) return btrfs_get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_SYSTEM); } -static inline int btrfs_block_group_done(struct btrfs_block_group *cache) +static inline int btrfs_block_group_done(const struct btrfs_block_group *cache) { smp_mb(); return cache->cached == BTRFS_CACHE_FINISHED || @@ -387,6 +386,6 @@ enum btrfs_block_group_size_class btrfs_calc_block_group_size_class(u64 size); int btrfs_use_block_group_size_class(struct btrfs_block_group *bg, enum btrfs_block_group_size_class size_class, bool force_wrong_size_class); -bool btrfs_block_group_should_use_size_class(struct btrfs_block_group *bg); +bool btrfs_block_group_should_use_size_class(const struct btrfs_block_group *bg); #endif /* BTRFS_BLOCK_GROUP_H */ diff --git a/fs/btrfs/block-rsv.c b/fs/btrfs/block-rsv.c index b299b82d676e..a07b9594dc70 100644 --- a/fs/btrfs/block-rsv.c +++ b/fs/btrfs/block-rsv.c @@ -553,7 +553,7 @@ try_reserve: return ERR_PTR(ret); } -int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info, +int btrfs_check_trunc_cache_free_space(const struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *rsv) { u64 needed_bytes; diff --git a/fs/btrfs/block-rsv.h b/fs/btrfs/block-rsv.h index 1f53b967d069..d12b1fac5c74 100644 --- a/fs/btrfs/block-rsv.h +++ b/fs/btrfs/block-rsv.h @@ -89,7 +89,7 @@ void btrfs_release_global_block_rsv(struct btrfs_fs_info *fs_info); struct btrfs_block_rsv *btrfs_use_block_rsv(struct btrfs_trans_handle *trans, struct btrfs_root *root, u32 blocksize); -int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info, +int btrfs_check_trunc_cache_free_space(const struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *rsv); static inline void btrfs_unuse_block_rsv(struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *block_rsv, diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index 3056c8aed8ef..9a4b7c119318 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -350,10 +350,12 @@ static inline void btrfs_set_first_dir_index_to_log(struct btrfs_inode *inode, WRITE_ONCE(inode->first_dir_index_to_log, index); } -static inline struct btrfs_inode *BTRFS_I(const struct inode *inode) -{ - return container_of(inode, struct btrfs_inode, vfs_inode); -} +/* Type checked and const-preserving VFS inode -> btrfs inode. */ +#define BTRFS_I(_inode) \ + _Generic(_inode, \ + struct inode *: container_of(_inode, struct btrfs_inode, vfs_inode), \ + const struct inode *: (const struct btrfs_inode *)container_of( \ + _inode, const struct btrfs_inode, vfs_inode)) static inline unsigned long btrfs_inode_hash(u64 objectid, const struct btrfs_root *root) @@ -505,6 +507,14 @@ static inline bool btrfs_inode_can_compress(const struct btrfs_inode *inode) return true; } +static inline void btrfs_assert_inode_locked(struct btrfs_inode *inode) +{ + /* Immediately trigger a crash if the inode is not locked. */ + ASSERT(inode_is_locked(&inode->vfs_inode)); + /* Trigger a splat in dmesg if this task is not holding the lock. */ + lockdep_assert_held(&inode->vfs_inode.i_rwsem); +} + /* Array of bytes with variable length, hexadecimal format 0x1234 */ #define CSUM_FMT "0x%*phN" #define CSUM_FMT_VALUE(size, bytes) size, bytes @@ -578,7 +588,7 @@ struct inode *btrfs_iget_path(u64 ino, struct btrfs_root *root, struct btrfs_path *path); struct inode *btrfs_iget(u64 ino, struct btrfs_root *root); struct extent_map *btrfs_get_extent(struct btrfs_inode *inode, - struct page *page, u64 start, u64 len); + struct folio *folio, u64 start, u64 len); int btrfs_update_inode(struct btrfs_trans_handle *trans, struct btrfs_inode *inode); int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans, @@ -596,9 +606,9 @@ int btrfs_prealloc_file_range_trans(struct inode *inode, struct btrfs_trans_handle *trans, int mode, u64 start, u64 num_bytes, u64 min_size, loff_t actual_len, u64 *alloc_hint); -int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page, +int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct folio *locked_folio, u64 start, u64 end, struct writeback_control *wbc); -int btrfs_writepage_cow_fixup(struct page *page); +int btrfs_writepage_cow_fixup(struct folio *folio); int btrfs_encoded_io_compression_from_extent(struct btrfs_fs_info *fs_info, int compress_type); int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode, diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index a8e2c461aff7..90aef2627ca2 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -138,15 +138,15 @@ static int compression_decompress_bio(struct list_head *ws, } static int compression_decompress(int type, struct list_head *ws, - const u8 *data_in, struct page *dest_page, + const u8 *data_in, struct folio *dest_folio, unsigned long dest_pgoff, size_t srclen, size_t destlen) { switch (type) { - case BTRFS_COMPRESS_ZLIB: return zlib_decompress(ws, data_in, dest_page, + case BTRFS_COMPRESS_ZLIB: return zlib_decompress(ws, data_in, dest_folio, dest_pgoff, srclen, destlen); - case BTRFS_COMPRESS_LZO: return lzo_decompress(ws, data_in, dest_page, + case BTRFS_COMPRESS_LZO: return lzo_decompress(ws, data_in, dest_folio, dest_pgoff, srclen, destlen); - case BTRFS_COMPRESS_ZSTD: return zstd_decompress(ws, data_in, dest_page, + case BTRFS_COMPRESS_ZSTD: return zstd_decompress(ws, data_in, dest_folio, dest_pgoff, srclen, destlen); case BTRFS_COMPRESS_NONE: default: @@ -395,7 +395,7 @@ void btrfs_submit_compressed_write(struct btrfs_ordered_extent *ordered, cb->bbio.ordered = ordered; btrfs_add_compressed_bio_folios(cb); - btrfs_submit_bio(&cb->bbio, 0); + btrfs_submit_bbio(&cb->bbio, 0); } /* @@ -420,7 +420,7 @@ static noinline int add_ra_bio_pages(struct inode *inode, u64 cur = cb->orig_bbio->file_offset + orig_bio->bi_iter.bi_size; u64 isize = i_size_read(inode); int ret; - struct page *page; + struct folio *folio; struct extent_map *em; struct address_space *mapping = inode->i_mapping; struct extent_map_tree *em_tree; @@ -453,9 +453,13 @@ static noinline int add_ra_bio_pages(struct inode *inode, if (pg_index > end_index) break; - page = xa_load(&mapping->i_pages, pg_index); - if (page && !xa_is_value(page)) { - sectors_missed += (PAGE_SIZE - offset_in_page(cur)) >> + folio = __filemap_get_folio(mapping, pg_index, 0, 0); + if (!IS_ERR(folio)) { + u64 folio_sz = folio_size(folio); + u64 offset = offset_in_folio(folio, cur); + + folio_put(folio); + sectors_missed += (folio_sz - offset) >> fs_info->sectorsize_bits; /* Beyond threshold, no need to continue */ @@ -466,35 +470,35 @@ static noinline int add_ra_bio_pages(struct inode *inode, * Jump to next page start as we already have page for * current offset. */ - cur = (pg_index << PAGE_SHIFT) + PAGE_SIZE; + cur += (folio_sz - offset); continue; } - page = __page_cache_alloc(mapping_gfp_constraint(mapping, - ~__GFP_FS)); - if (!page) + folio = filemap_alloc_folio(mapping_gfp_constraint(mapping, + ~__GFP_FS), 0); + if (!folio) break; - if (add_to_page_cache_lru(page, mapping, pg_index, GFP_NOFS)) { - put_page(page); + if (filemap_add_folio(mapping, folio, pg_index, GFP_NOFS)) { /* There is already a page, skip to page end */ - cur = (pg_index << PAGE_SHIFT) + PAGE_SIZE; + cur += folio_size(folio); + folio_put(folio); continue; } - if (!*memstall && PageWorkingset(page)) { + if (!*memstall && folio_test_workingset(folio)) { psi_memstall_enter(pflags); *memstall = 1; } - ret = set_page_extent_mapped(page); + ret = set_folio_extent_mapped(folio); if (ret < 0) { - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); break; } - page_end = (pg_index << PAGE_SHIFT) + PAGE_SIZE - 1; + page_end = (pg_index << PAGE_SHIFT) + folio_size(folio) - 1; lock_extent(tree, cur, page_end, NULL); read_lock(&em_tree->lock); em = lookup_extent_mapping(em_tree, cur, page_end + 1 - cur); @@ -511,28 +515,28 @@ static noinline int add_ra_bio_pages(struct inode *inode, orig_bio->bi_iter.bi_sector) { free_extent_map(em); unlock_extent(tree, cur, page_end, NULL); - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); break; } add_size = min(em->start + em->len, page_end + 1) - cur; free_extent_map(em); + unlock_extent(tree, cur, page_end, NULL); - if (page->index == end_index) { - size_t zero_offset = offset_in_page(isize); + if (folio->index == end_index) { + size_t zero_offset = offset_in_folio(folio, isize); if (zero_offset) { int zeros; - zeros = PAGE_SIZE - zero_offset; - memzero_page(page, zero_offset, zeros); + zeros = folio_size(folio) - zero_offset; + folio_zero_range(folio, zero_offset, zeros); } } - ret = bio_add_page(orig_bio, page, add_size, offset_in_page(cur)); - if (ret != add_size) { - unlock_extent(tree, cur, page_end, NULL); - unlock_page(page); - put_page(page); + if (!bio_add_folio(orig_bio, folio, add_size, + offset_in_folio(folio, cur))) { + folio_unlock(folio); + folio_put(folio); break; } /* @@ -541,9 +545,9 @@ static noinline int add_ra_bio_pages(struct inode *inode, * subpage::readers and to unlock the page. */ if (fs_info->sectorsize < PAGE_SIZE) - btrfs_subpage_start_reader(fs_info, page_folio(page), - cur, add_size); - put_page(page); + btrfs_subpage_start_reader(fs_info, folio, cur, + add_size); + folio_put(folio); cur += add_size; } return 0; @@ -626,7 +630,7 @@ void btrfs_submit_compressed_read(struct btrfs_bio *bbio) if (memstall) psi_memstall_leave(&pflags); - btrfs_submit_bio(&cb->bbio, 0); + btrfs_submit_bbio(&cb->bbio, 0); return; out_free_compressed_pages: @@ -1057,10 +1061,10 @@ static int btrfs_decompress_bio(struct compressed_bio *cb) * single page, and we want to read a single page out of it. * start_byte tells us the offset into the compressed data we're interested in */ -int btrfs_decompress(int type, const u8 *data_in, struct page *dest_page, +int btrfs_decompress(int type, const u8 *data_in, struct folio *dest_folio, unsigned long dest_pgoff, size_t srclen, size_t destlen) { - struct btrfs_fs_info *fs_info = page_to_fs_info(dest_page); + struct btrfs_fs_info *fs_info = folio_to_fs_info(dest_folio); struct list_head *workspace; const u32 sectorsize = fs_info->sectorsize; int ret; @@ -1073,7 +1077,7 @@ int btrfs_decompress(int type, const u8 *data_in, struct page *dest_page, ASSERT(dest_pgoff + destlen <= PAGE_SIZE && destlen <= sectorsize); workspace = get_workspace(type, 0); - ret = compression_decompress(type, workspace, data_in, dest_page, + ret = compression_decompress(type, workspace, data_in, dest_folio, dest_pgoff, srclen, destlen); put_workspace(type, workspace); diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h index cfdc64319186..b6563b6a333e 100644 --- a/fs/btrfs/compression.h +++ b/fs/btrfs/compression.h @@ -82,13 +82,21 @@ static inline unsigned int btrfs_compress_level(unsigned int type_level) return ((type_level & 0xF0) >> 4); } +/* @range_end must be exclusive. */ +static inline u32 btrfs_calc_input_length(u64 range_end, u64 cur) +{ + u64 page_end = round_down(cur, PAGE_SIZE) + PAGE_SIZE; + + return min(range_end, page_end) - cur; +} + int __init btrfs_init_compress(void); void __cold btrfs_exit_compress(void); int btrfs_compress_folios(unsigned int type_level, struct address_space *mapping, u64 start, struct folio **folios, unsigned long *out_folios, unsigned long *total_in, unsigned long *total_out); -int btrfs_decompress(int type, const u8 *data_in, struct page *dest_page, +int btrfs_decompress(int type, const u8 *data_in, struct folio *dest_folio, unsigned long start_byte, size_t srclen, size_t destlen); int btrfs_decompress_buf2page(const char *buf, u32 buf_len, struct compressed_bio *cb, u32 decompressed); @@ -154,7 +162,7 @@ int zlib_compress_folios(struct list_head *ws, struct address_space *mapping, unsigned long *total_in, unsigned long *total_out); int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb); int zlib_decompress(struct list_head *ws, const u8 *data_in, - struct page *dest_page, unsigned long dest_pgoff, size_t srclen, + struct folio *dest_folio, unsigned long dest_pgoff, size_t srclen, size_t destlen); struct list_head *zlib_alloc_workspace(unsigned int level); void zlib_free_workspace(struct list_head *ws); @@ -165,7 +173,7 @@ int lzo_compress_folios(struct list_head *ws, struct address_space *mapping, unsigned long *total_in, unsigned long *total_out); int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb); int lzo_decompress(struct list_head *ws, const u8 *data_in, - struct page *dest_page, unsigned long dest_pgoff, size_t srclen, + struct folio *dest_folio, unsigned long dest_pgoff, size_t srclen, size_t destlen); struct list_head *lzo_alloc_workspace(unsigned int level); void lzo_free_workspace(struct list_head *ws); @@ -175,7 +183,7 @@ int zstd_compress_folios(struct list_head *ws, struct address_space *mapping, unsigned long *total_in, unsigned long *total_out); int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb); int zstd_decompress(struct list_head *ws, const u8 *data_in, - struct page *dest_page, unsigned long dest_pgoff, size_t srclen, + struct folio *dest_folio, unsigned long dest_pgoff, size_t srclen, size_t destlen); void zstd_init_workspace_manager(void); void zstd_cleanup_workspace_manager(void); diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 451203055bbf..0cc919d15b14 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -2564,8 +2564,8 @@ int btrfs_get_next_valid_item(struct btrfs_root *root, struct btrfs_key *key, * */ static void fixup_low_keys(struct btrfs_trans_handle *trans, - struct btrfs_path *path, - struct btrfs_disk_key *key, int level) + const struct btrfs_path *path, + const struct btrfs_disk_key *key, int level) { int i; struct extent_buffer *t; @@ -2594,7 +2594,7 @@ static void fixup_low_keys(struct btrfs_trans_handle *trans, * that the new key won't break the order */ void btrfs_set_item_key_safe(struct btrfs_trans_handle *trans, - struct btrfs_path *path, + const struct btrfs_path *path, const struct btrfs_key *new_key) { struct btrfs_fs_info *fs_info = trans->fs_info; @@ -2660,8 +2660,8 @@ void btrfs_set_item_key_safe(struct btrfs_trans_handle *trans, * is correct, we only need to bother the last key of @left and the first * key of @right. */ -static bool check_sibling_keys(struct extent_buffer *left, - struct extent_buffer *right) +static bool check_sibling_keys(const struct extent_buffer *left, + const struct extent_buffer *right) { struct btrfs_key left_last; struct btrfs_key right_first; @@ -2928,8 +2928,8 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans, * blocknr is the block the key points to. */ static int insert_ptr(struct btrfs_trans_handle *trans, - struct btrfs_path *path, - struct btrfs_disk_key *key, u64 bytenr, + const struct btrfs_path *path, + const struct btrfs_disk_key *key, u64 bytenr, int slot, int level) { struct extent_buffer *lower; @@ -4019,7 +4019,7 @@ int btrfs_split_item(struct btrfs_trans_handle *trans, * the front. */ void btrfs_truncate_item(struct btrfs_trans_handle *trans, - struct btrfs_path *path, u32 new_size, int from_end) + const struct btrfs_path *path, u32 new_size, int from_end) { int slot; struct extent_buffer *leaf; @@ -4111,7 +4111,7 @@ void btrfs_truncate_item(struct btrfs_trans_handle *trans, * make the item pointed to by the path bigger, data_size is the added size. */ void btrfs_extend_item(struct btrfs_trans_handle *trans, - struct btrfs_path *path, u32 data_size) + const struct btrfs_path *path, u32 data_size) { int slot; struct extent_buffer *leaf; diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 75fa563e4cac..1a44fb9845e3 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -6,6 +6,7 @@ #ifndef BTRFS_CTREE_H #define BTRFS_CTREE_H +#include "linux/cleanup.h" #include <linux/pagemap.h> #include <linux/spinlock.h> #include <linux/rbtree.h> @@ -84,6 +85,9 @@ struct btrfs_path { unsigned int nowait:1; }; +#define BTRFS_PATH_AUTO_FREE(path_name) \ + struct btrfs_path *path_name __free(btrfs_free_path) = NULL + /* * The state of btrfs root */ @@ -459,7 +463,6 @@ struct btrfs_file_private { void *filldir_buf; u64 last_index; struct extent_state *llseek_cached_state; - bool fsync_skip_inode_lock; }; static inline u32 BTRFS_LEAF_DATA_SIZE(const struct btrfs_fs_info *info) @@ -539,7 +542,7 @@ int btrfs_previous_item(struct btrfs_root *root, int btrfs_previous_extent_item(struct btrfs_root *root, struct btrfs_path *path, u64 min_objectid); void btrfs_set_item_key_safe(struct btrfs_trans_handle *trans, - struct btrfs_path *path, + const struct btrfs_path *path, const struct btrfs_key *new_key); struct extent_buffer *btrfs_root_node(struct btrfs_root *root); int btrfs_find_next_key(struct btrfs_root *root, struct btrfs_path *path, @@ -573,9 +576,9 @@ bool btrfs_block_can_be_shared(struct btrfs_trans_handle *trans, int btrfs_del_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int level, int slot); void btrfs_extend_item(struct btrfs_trans_handle *trans, - struct btrfs_path *path, u32 data_size); + const struct btrfs_path *path, u32 data_size); void btrfs_truncate_item(struct btrfs_trans_handle *trans, - struct btrfs_path *path, u32 new_size, int from_end); + const struct btrfs_path *path, u32 new_size, int from_end); int btrfs_split_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, @@ -599,6 +602,7 @@ int btrfs_search_slot_for_read(struct btrfs_root *root, void btrfs_release_path(struct btrfs_path *p); struct btrfs_path *btrfs_alloc_path(void); void btrfs_free_path(struct btrfs_path *p); +DEFINE_FREE(btrfs_free_path, struct btrfs_path *, btrfs_free_path(_T)) int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int slot, int nr); diff --git a/fs/btrfs/defrag.c b/fs/btrfs/defrag.c index f6dbda37a361..acf1f39e45d0 100644 --- a/fs/btrfs/defrag.c +++ b/fs/btrfs/defrag.c @@ -45,8 +45,8 @@ struct inode_defrag { u32 extent_thresh; }; -static int __compare_inode_defrag(struct inode_defrag *defrag1, - struct inode_defrag *defrag2) +static int compare_inode_defrag(const struct inode_defrag *defrag1, + const struct inode_defrag *defrag2) { if (defrag1->root > defrag2->root) return 1; @@ -61,16 +61,14 @@ static int __compare_inode_defrag(struct inode_defrag *defrag1, } /* - * Pop a record for an inode into the defrag tree. The lock must be held + * Insert a record for an inode into the defrag tree. The lock must be held * already. * * If you're inserting a record for an older transid than an existing record, * the transid already in the tree is lowered. - * - * If an existing record is found the defrag item you pass in is freed. */ -static int __btrfs_add_inode_defrag(struct btrfs_inode *inode, - struct inode_defrag *defrag) +static int btrfs_insert_inode_defrag(struct btrfs_inode *inode, + struct inode_defrag *defrag) { struct btrfs_fs_info *fs_info = inode->root->fs_info; struct inode_defrag *entry; @@ -83,7 +81,7 @@ static int __btrfs_add_inode_defrag(struct btrfs_inode *inode, parent = *p; entry = rb_entry(parent, struct inode_defrag, rb_node); - ret = __compare_inode_defrag(defrag, entry); + ret = compare_inode_defrag(defrag, entry); if (ret < 0) p = &parent->rb_left; else if (ret > 0) @@ -107,7 +105,7 @@ static int __btrfs_add_inode_defrag(struct btrfs_inode *inode, return 0; } -static inline int __need_auto_defrag(struct btrfs_fs_info *fs_info) +static inline int need_auto_defrag(struct btrfs_fs_info *fs_info) { if (!btrfs_test_opt(fs_info, AUTO_DEFRAG)) return 0; @@ -119,34 +117,28 @@ static inline int __need_auto_defrag(struct btrfs_fs_info *fs_info) } /* - * Insert a defrag record for this inode if auto defrag is enabled. + * Insert a defrag record for this inode if auto defrag is enabled. No errors + * returned as they're not considered fatal. */ -int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans, - struct btrfs_inode *inode, u32 extent_thresh) +void btrfs_add_inode_defrag(struct btrfs_inode *inode, u32 extent_thresh) { struct btrfs_root *root = inode->root; struct btrfs_fs_info *fs_info = root->fs_info; struct inode_defrag *defrag; - u64 transid; int ret; - if (!__need_auto_defrag(fs_info)) - return 0; + if (!need_auto_defrag(fs_info)) + return; if (test_bit(BTRFS_INODE_IN_DEFRAG, &inode->runtime_flags)) - return 0; - - if (trans) - transid = trans->transid; - else - transid = btrfs_get_root_last_trans(root); + return; defrag = kmem_cache_zalloc(btrfs_inode_defrag_cachep, GFP_NOFS); if (!defrag) - return -ENOMEM; + return; defrag->ino = btrfs_ino(inode); - defrag->transid = transid; + defrag->transid = btrfs_get_root_last_trans(root); defrag->root = btrfs_root_id(root); defrag->extent_thresh = extent_thresh; @@ -157,14 +149,13 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans, * and then re-read this inode, this new inode doesn't have * IN_DEFRAG flag. At the case, we may find the existed defrag. */ - ret = __btrfs_add_inode_defrag(inode, defrag); + ret = btrfs_insert_inode_defrag(inode, defrag); if (ret) kmem_cache_free(btrfs_inode_defrag_cachep, defrag); } else { kmem_cache_free(btrfs_inode_defrag_cachep, defrag); } spin_unlock(&fs_info->defrag_inodes_lock); - return 0; } /* @@ -189,7 +180,7 @@ static struct inode_defrag *btrfs_pick_defrag_inode( parent = p; entry = rb_entry(parent, struct inode_defrag, rb_node); - ret = __compare_inode_defrag(&tmp, entry); + ret = compare_inode_defrag(&tmp, entry); if (ret < 0) p = parent->rb_left; else if (ret > 0) @@ -198,7 +189,7 @@ static struct inode_defrag *btrfs_pick_defrag_inode( goto out; } - if (parent && __compare_inode_defrag(&tmp, entry) > 0) { + if (parent && compare_inode_defrag(&tmp, entry) > 0) { parent = rb_next(parent); if (parent) entry = rb_entry(parent, struct inode_defrag, rb_node); @@ -214,27 +205,22 @@ out: void btrfs_cleanup_defrag_inodes(struct btrfs_fs_info *fs_info) { - struct inode_defrag *defrag; - struct rb_node *node; + struct inode_defrag *defrag, *next; spin_lock(&fs_info->defrag_inodes_lock); - node = rb_first(&fs_info->defrag_inodes); - while (node) { - rb_erase(node, &fs_info->defrag_inodes); - defrag = rb_entry(node, struct inode_defrag, rb_node); - kmem_cache_free(btrfs_inode_defrag_cachep, defrag); - cond_resched_lock(&fs_info->defrag_inodes_lock); + rbtree_postorder_for_each_entry_safe(defrag, next, + &fs_info->defrag_inodes, rb_node) + kmem_cache_free(btrfs_inode_defrag_cachep, defrag); - node = rb_first(&fs_info->defrag_inodes); - } spin_unlock(&fs_info->defrag_inodes_lock); } #define BTRFS_DEFRAG_BATCH 1024 -static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info, - struct inode_defrag *defrag) +static int btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info, + struct inode_defrag *defrag, + struct file_ra_state *ra) { struct btrfs_root *inode_root; struct inode *inode; @@ -245,7 +231,7 @@ static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info, again: if (test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state)) goto cleanup; - if (!__need_auto_defrag(fs_info)) + if (!need_auto_defrag(fs_info)) goto cleanup; /* Get the inode */ @@ -273,9 +259,10 @@ again: range.len = (u64)-1; range.start = cur; range.extent_thresh = defrag->extent_thresh; + file_ra_state_init(ra, inode->i_mapping); sb_start_write(fs_info->sb); - ret = btrfs_defrag_file(inode, NULL, &range, defrag->transid, + ret = btrfs_defrag_file(inode, ra, &range, defrag->transid, BTRFS_DEFRAG_BATCH); sb_end_write(fs_info->sb); iput(inode); @@ -302,11 +289,13 @@ int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info) atomic_inc(&fs_info->defrag_running); while (1) { + struct file_ra_state ra = { 0 }; + /* Pause the auto defragger. */ if (test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state)) break; - if (!__need_auto_defrag(fs_info)) + if (!need_auto_defrag(fs_info)) break; /* find an inode to defrag */ @@ -324,7 +313,7 @@ int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info) first_ino = defrag->ino + 1; root_objectid = defrag->root; - __btrfs_run_defrag_inode(fs_info, defrag); + btrfs_run_defrag_inode(fs_info, defrag, &ra); } atomic_dec(&fs_info->defrag_running); @@ -1317,8 +1306,7 @@ static int defrag_one_cluster(struct btrfs_inode *inode, if (entry->start + range_len <= *last_scanned_ret) continue; - if (ra) - page_cache_sync_readahead(inode->vfs_inode.i_mapping, + page_cache_sync_readahead(inode->vfs_inode.i_mapping, ra, NULL, entry->start >> PAGE_SHIFT, ((entry->start + range_len - 1) >> PAGE_SHIFT) - (entry->start >> PAGE_SHIFT) + 1); @@ -1350,7 +1338,7 @@ out: * Entry point to file defragmentation. * * @inode: inode to be defragged - * @ra: readahead state (can be NUL) + * @ra: readahead state * @range: defrag options including range and flags * @newer_than: minimum transid to defrag * @max_to_defrag: max number of sectors to be defragged, if 0, the whole inode @@ -1372,12 +1360,13 @@ int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra, u64 cur; u64 last_byte; bool do_compress = (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS); - bool ra_allocated = false; int compress_type = BTRFS_COMPRESS_ZLIB; int ret = 0; u32 extent_thresh = range->extent_thresh; pgoff_t start_index; + ASSERT(ra); + if (isize == 0) return 0; @@ -1407,18 +1396,6 @@ int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra, last_byte = round_up(last_byte, fs_info->sectorsize) - 1; /* - * If we were not given a ra, allocate a readahead context. As - * readahead is just an optimization, defrag will work without it so - * we don't error out. - */ - if (!ra) { - ra_allocated = true; - ra = kzalloc(sizeof(*ra), GFP_KERNEL); - if (ra) - file_ra_state_init(ra, inode->i_mapping); - } - - /* * Make writeback start from the beginning of the range, so that the * defrag range can be written sequentially. */ @@ -1472,8 +1449,6 @@ int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra, cond_resched(); } - if (ra_allocated) - kfree(ra); /* * Update range.start for autodefrag, this will indicate where to start * in next run. diff --git a/fs/btrfs/defrag.h b/fs/btrfs/defrag.h index 878528e086fb..6b7596c4f0dc 100644 --- a/fs/btrfs/defrag.h +++ b/fs/btrfs/defrag.h @@ -18,8 +18,7 @@ int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra, u64 newer_than, unsigned long max_to_defrag); int __init btrfs_auto_defrag_init(void); void __cold btrfs_auto_defrag_exit(void); -int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans, - struct btrfs_inode *inode, u32 extent_thresh); +void btrfs_add_inode_defrag(struct btrfs_inode *inode, u32 extent_thresh); int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info); void btrfs_cleanup_defrag_inodes(struct btrfs_fs_info *fs_info); int btrfs_defrag_root(struct btrfs_root *root); diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index 06a9e0542d70..ad9ef8312e41 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -855,11 +855,17 @@ add_delayed_ref_head(struct btrfs_trans_handle *trans, /* Record qgroup extent info if provided */ if (qrecord) { - if (btrfs_qgroup_trace_extent_nolock(trans->fs_info, - delayed_refs, qrecord)) + int ret; + + ret = btrfs_qgroup_trace_extent_nolock(trans->fs_info, + delayed_refs, qrecord); + if (ret) { + /* Clean up if insertion fails or item exists. */ + xa_release(&delayed_refs->dirty_extents, qrecord->bytenr); kfree(qrecord); - else + } else { qrecord_inserted = true; + } } trace_add_delayed_ref_head(trans->fs_info, head_ref, action); @@ -1005,18 +1011,16 @@ static int add_delayed_ref(struct btrfs_trans_handle *trans, return -ENOMEM; head_ref = kmem_cache_alloc(btrfs_delayed_ref_head_cachep, GFP_NOFS); - if (!head_ref) { - kmem_cache_free(btrfs_delayed_ref_node_cachep, node); - return -ENOMEM; - } + if (!head_ref) + goto free_node; if (btrfs_qgroup_full_accounting(fs_info) && !generic_ref->skip_qgroup) { record = kzalloc(sizeof(*record), GFP_NOFS); - if (!record) { - kmem_cache_free(btrfs_delayed_ref_node_cachep, node); - kmem_cache_free(btrfs_delayed_ref_head_cachep, head_ref); - return -ENOMEM; - } + if (!record) + goto free_head_ref; + if (xa_reserve(&trans->transaction->delayed_refs.dirty_extents, + generic_ref->bytenr, GFP_NOFS)) + goto free_record; } init_delayed_ref_common(fs_info, node, generic_ref); @@ -1052,6 +1056,14 @@ static int add_delayed_ref(struct btrfs_trans_handle *trans, if (qrecord_inserted) return btrfs_qgroup_trace_extent_post(trans, record); return 0; + +free_record: + kfree(record); +free_head_ref: + kmem_cache_free(btrfs_delayed_ref_head_cachep, head_ref); +free_node: + kmem_cache_free(btrfs_delayed_ref_node_cachep, node); + return -ENOMEM; } /* diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h index 05f634eb472d..085f30968aba 100644 --- a/fs/btrfs/delayed-ref.h +++ b/fs/btrfs/delayed-ref.h @@ -202,8 +202,8 @@ struct btrfs_delayed_ref_root { /* head ref rbtree */ struct rb_root_cached href_root; - /* dirty extent records */ - struct rb_root dirty_extent_root; + /* Track dirty extent records. */ + struct xarray dirty_extents; /* this spin lock protects the rbtree and the entries inside */ spinlock_t lock; diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index f638c458d285..83d5cdd77f29 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -824,22 +824,45 @@ static void btrfs_dev_replace_update_device_in_mapping_tree( struct btrfs_device *srcdev, struct btrfs_device *tgtdev) { - u64 start = 0; - int i; + struct rb_node *node; + + /* + * The chunk mutex must be held so that no new chunks can be created + * while we are updating existing chunks. This guarantees we don't miss + * any new chunk that gets created for a range that falls before the + * range of the last chunk we processed. + */ + lockdep_assert_held(&fs_info->chunk_mutex); write_lock(&fs_info->mapping_tree_lock); - do { + node = rb_first_cached(&fs_info->mapping_tree); + while (node) { + struct rb_node *next = rb_next(node); struct btrfs_chunk_map *map; + u64 next_start; - map = btrfs_find_chunk_map_nolock(fs_info, start, U64_MAX); - if (!map) - break; - for (i = 0; i < map->num_stripes; i++) + map = rb_entry(node, struct btrfs_chunk_map, rb_node); + next_start = map->start + map->chunk_len; + + for (int i = 0; i < map->num_stripes; i++) if (srcdev == map->stripes[i].dev) map->stripes[i].dev = tgtdev; - start = map->start + map->chunk_len; - btrfs_free_chunk_map(map); - } while (start); + + if (cond_resched_rwlock_write(&fs_info->mapping_tree_lock)) { + map = btrfs_find_chunk_map_nolock(fs_info, next_start, U64_MAX); + if (!map) + break; + node = &map->rb_node; + /* + * Drop the lookup reference since we are holding the + * lock in write mode and no one can remove the chunk + * map from the tree and drop its tree reference. + */ + btrfs_free_chunk_map(map); + } else { + node = next; + } + } write_unlock(&fs_info->mapping_tree_lock); } diff --git a/fs/btrfs/direct-io.c b/fs/btrfs/direct-io.c index 67adbe9d294a..bd38df5647e3 100644 --- a/fs/btrfs/direct-io.c +++ b/fs/btrfs/direct-io.c @@ -40,11 +40,21 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend, struct btrfs_ordered_extent *ordered; int ret = 0; + /* Direct lock must be taken before the extent lock. */ + if (nowait) { + if (!try_lock_dio_extent(io_tree, lockstart, lockend, cached_state)) + return -EAGAIN; + } else { + lock_dio_extent(io_tree, lockstart, lockend, cached_state); + } + while (1) { if (nowait) { if (!try_lock_extent(io_tree, lockstart, lockend, - cached_state)) - return -EAGAIN; + cached_state)) { + ret = -EAGAIN; + break; + } } else { lock_extent(io_tree, lockstart, lockend, cached_state); } @@ -120,6 +130,8 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend, cond_resched(); } + if (ret) + unlock_dio_extent(io_tree, lockstart, lockend, cached_state); return ret; } @@ -353,7 +365,7 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start, int ret = 0; u64 len = length; const u64 data_alloc_len = length; - bool unlock_extents = false; + u32 unlock_bits = EXTENT_LOCKED; /* * We could potentially fault if we have a buffer > PAGE_SIZE, and if @@ -514,7 +526,6 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start, start, &len, flags); if (ret < 0) goto unlock_err; - unlock_extents = true; /* Recalc len in case the new em is smaller than requested */ len = min(len, em->len - (start - em->start)); if (dio_data->data_space_reserved) { @@ -535,22 +546,8 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start, release_offset, release_len); } - } else { - /* - * We need to unlock only the end area that we aren't using. - * The rest is going to be unlocked by the endio routine. - */ - lockstart = start + len; - if (lockstart < lockend) - unlock_extents = true; } - if (unlock_extents) - unlock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend, - &cached_state); - else - free_extent_state(cached_state); - /* * Translate extent map information to iomap. * We trim the extents (and move the addr) even though iomap code does @@ -569,11 +566,33 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start, iomap->length = len; free_extent_map(em); + /* + * Reads will hold the EXTENT_DIO_LOCKED bit until the io is completed, + * writes only hold it for this part. We hold the extent lock until + * we're completely done with the extent map to make sure it remains + * valid. + */ + if (write) + unlock_bits |= EXTENT_DIO_LOCKED; + + clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend, + unlock_bits, &cached_state); + + /* We didn't use everything, unlock the dio extent for the remainder. */ + if (!write && (start + len) < lockend) + unlock_dio_extent(&BTRFS_I(inode)->io_tree, start + len, + lockend, NULL); + return 0; unlock_err: - unlock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend, - &cached_state); + /* + * Don't use EXTENT_LOCK_BITS here in case we extend it later and forget + * to update this, be explicit that we expect EXTENT_LOCKED and + * EXTENT_DIO_LOCKED to be set here, and so that's what we're clearing. + */ + clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend, + EXTENT_LOCKED | EXTENT_DIO_LOCKED, &cached_state); err: if (dio_data->data_space_reserved) { btrfs_free_reserved_data_space(BTRFS_I(inode), @@ -596,8 +615,8 @@ static int btrfs_dio_iomap_end(struct inode *inode, loff_t pos, loff_t length, if (!write && (iomap->type == IOMAP_HOLE)) { /* If reading from a hole, unlock and return */ - unlock_extent(&BTRFS_I(inode)->io_tree, pos, pos + length - 1, - NULL); + unlock_dio_extent(&BTRFS_I(inode)->io_tree, pos, + pos + length - 1, NULL); return 0; } @@ -608,8 +627,8 @@ static int btrfs_dio_iomap_end(struct inode *inode, loff_t pos, loff_t length, btrfs_finish_ordered_extent(dio_data->ordered, NULL, pos, length, false); else - unlock_extent(&BTRFS_I(inode)->io_tree, pos, - pos + length - 1, NULL); + unlock_dio_extent(&BTRFS_I(inode)->io_tree, pos, + pos + length - 1, NULL); ret = -ENOTBLK; } if (write) { @@ -641,8 +660,8 @@ static void btrfs_dio_end_io(struct btrfs_bio *bbio) dip->file_offset, dip->bytes, !bio->bi_status); } else { - unlock_extent(&inode->io_tree, dip->file_offset, - dip->file_offset + dip->bytes - 1, NULL); + unlock_dio_extent(&inode->io_tree, dip->file_offset, + dip->file_offset + dip->bytes - 1, NULL); } bbio->bio.bi_private = bbio->private; @@ -726,7 +745,7 @@ static void btrfs_dio_submit_io(const struct iomap_iter *iter, struct bio *bio, } } - btrfs_submit_bio(bbio, 0); + btrfs_submit_bbio(bbio, 0); } static const struct iomap_ops btrfs_dio_iomap_ops = { @@ -864,13 +883,6 @@ again: if (IS_ERR_OR_NULL(dio)) { ret = PTR_ERR_OR_ZERO(dio); } else { - struct btrfs_file_private stack_private = { 0 }; - struct btrfs_file_private *private; - const bool have_private = (file->private_data != NULL); - - if (!have_private) - file->private_data = &stack_private; - /* * If we have a synchronous write, we must make sure the fsync * triggered by the iomap_dio_complete() call below doesn't @@ -879,13 +891,10 @@ again: * partial writes due to the input buffer (or parts of it) not * being already faulted in. */ - private = file->private_data; - private->fsync_skip_inode_lock = true; + ASSERT(current->journal_info == NULL); + current->journal_info = BTRFS_TRANS_DIO_WRITE_STUB; ret = iomap_dio_complete(dio); - private->fsync_skip_inode_lock = false; - - if (!have_private) - file->private_data = NULL; + current->journal_info = NULL; } /* No increment (+=) because iomap returns a cumulative value. */ diff --git a/fs/btrfs/discard.c b/fs/btrfs/discard.c index 944a7340f6a4..e815d165cccc 100644 --- a/fs/btrfs/discard.c +++ b/fs/btrfs/discard.c @@ -68,7 +68,7 @@ static int discard_minlen[BTRFS_NR_DISCARD_LISTS] = { }; static struct list_head *get_discard_list(struct btrfs_discard_ctl *discard_ctl, - struct btrfs_block_group *block_group) + const struct btrfs_block_group *block_group) { return &discard_ctl->discard_list[block_group->discard_index]; } @@ -80,7 +80,7 @@ static struct list_head *get_discard_list(struct btrfs_discard_ctl *discard_ctl, * * Check if the file system is writeable and BTRFS_FS_DISCARD_RUNNING is set. */ -static bool btrfs_run_discard_work(struct btrfs_discard_ctl *discard_ctl) +static bool btrfs_run_discard_work(const struct btrfs_discard_ctl *discard_ctl) { struct btrfs_fs_info *fs_info = container_of(discard_ctl, struct btrfs_fs_info, diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index a6f5441e62d1..25d768e67e37 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -525,7 +525,7 @@ static bool btree_release_folio(struct folio *folio, gfp_t gfp_flags) if (folio_test_writeback(folio) || folio_test_dirty(folio)) return false; - return try_release_extent_buffer(&folio->page); + return try_release_extent_buffer(folio); } static void btree_invalidate_folio(struct folio *folio, size_t offset, @@ -1285,7 +1285,6 @@ void btrfs_free_fs_info(struct btrfs_fs_info *fs_info) btrfs_extent_buffer_leak_debug_check(fs_info); kfree(fs_info->super_copy); kfree(fs_info->super_for_commit); - kfree(fs_info->subpage_info); kvfree(fs_info); } @@ -3322,6 +3321,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device fs_info->nodesize = nodesize; fs_info->sectorsize = sectorsize; fs_info->sectorsize_bits = ilog2(sectorsize); + fs_info->sectors_per_page = (PAGE_SIZE >> fs_info->sectorsize_bits); fs_info->csums_per_leaf = BTRFS_MAX_ITEM_SIZE(fs_info) / fs_info->csum_size; fs_info->stripesize = stripesize; @@ -3346,20 +3346,10 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device */ fs_info->max_inline = min_t(u64, fs_info->max_inline, fs_info->sectorsize); - if (sectorsize < PAGE_SIZE) { - struct btrfs_subpage_info *subpage_info; - + if (sectorsize < PAGE_SIZE) btrfs_warn(fs_info, "read-write for sector size %u with page size %lu is experimental", sectorsize, PAGE_SIZE); - subpage_info = kzalloc(sizeof(*subpage_info), GFP_KERNEL); - if (!subpage_info) { - ret = -ENOMEM; - goto fail_alloc; - } - btrfs_init_subpage_info(subpage_info, sectorsize); - fs_info->subpage_info = subpage_info; - } ret = btrfs_init_workqueues(fs_info); if (ret) diff --git a/fs/btrfs/extent-io-tree.c b/fs/btrfs/extent-io-tree.c index c54c5d7a5cd5..6d08c100b01d 100644 --- a/fs/btrfs/extent-io-tree.c +++ b/fs/btrfs/extent-io-tree.c @@ -126,7 +126,7 @@ void extent_io_tree_init(struct btrfs_fs_info *fs_info, * Empty an io tree, removing and freeing every extent state record from the * tree. This should be called once we are sure no other task can access the * tree anymore, so no tree updates happen after we empty the tree and there - * aren't any waiters on any extent state record (EXTENT_LOCKED bit is never + * aren't any waiters on any extent state record (EXTENT_LOCK_BITS are never * set on any extent state when calling this function). */ void extent_io_tree_release(struct extent_io_tree *tree) @@ -141,7 +141,7 @@ void extent_io_tree_release(struct extent_io_tree *tree) rbtree_postorder_for_each_entry_safe(state, tmp, &root, rb_node) { /* Clear node to keep free_extent_state() happy. */ RB_CLEAR_NODE(&state->rb_node); - ASSERT(!(state->state & EXTENT_LOCKED)); + ASSERT(!(state->state & EXTENT_LOCK_BITS)); /* * No need for a memory barrier here, as we are holding the tree * lock and we only change the waitqueue while holding that lock @@ -399,7 +399,7 @@ static void merge_next_state(struct extent_io_tree *tree, struct extent_state *s */ static void merge_state(struct extent_io_tree *tree, struct extent_state *state) { - if (state->state & (EXTENT_LOCKED | EXTENT_BOUNDARY)) + if (state->state & (EXTENT_LOCK_BITS | EXTENT_BOUNDARY)) return; merge_prev_state(tree, state); @@ -445,7 +445,7 @@ static struct extent_state *insert_state(struct extent_io_tree *tree, struct rb_node *parent = NULL; const u64 start = state->start - 1; const u64 end = state->end + 1; - const bool try_merge = !(bits & (EXTENT_LOCKED | EXTENT_BOUNDARY)); + const bool try_merge = !(bits & (EXTENT_LOCK_BITS | EXTENT_BOUNDARY)); set_state_bits(tree, state, bits, changeset); @@ -616,9 +616,6 @@ static void set_gfp_mask_from_bits(u32 *bits, gfp_t *mask) * inserting elements in the tree, so the gfp mask is used to indicate which * allocations or sleeping are allowed. * - * Pass 'wake' == 1 to kick any sleepers, and 'delete' == 1 to remove the given - * range from the tree regardless of state (ie for truncate). - * * The range [start, end] is inclusive. * * This takes the tree lock, and returns 0 on success and < 0 on error. @@ -647,8 +644,8 @@ int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, if (bits & EXTENT_DELALLOC) bits |= EXTENT_NORESERVE; - wake = (bits & EXTENT_LOCKED) ? 1 : 0; - if (bits & (EXTENT_LOCKED | EXTENT_BOUNDARY)) + wake = ((bits & EXTENT_LOCK_BITS) ? 1 : 0); + if (bits & (EXTENT_LOCK_BITS | EXTENT_BOUNDARY)) clear = 1; again: if (!prealloc) { @@ -861,8 +858,7 @@ static void cache_state_if_flags(struct extent_state *state, static void cache_state(struct extent_state *state, struct extent_state **cached_ptr) { - return cache_state_if_flags(state, cached_ptr, - EXTENT_LOCKED | EXTENT_BOUNDARY); + return cache_state_if_flags(state, cached_ptr, EXTENT_LOCK_BITS | EXTENT_BOUNDARY); } /* @@ -1063,7 +1059,7 @@ static int __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, int ret = 0; u64 last_start; u64 last_end; - u32 exclusive_bits = (bits & EXTENT_LOCKED); + u32 exclusive_bits = (bits & EXTENT_LOCK_BITS); gfp_t mask; set_gfp_mask_from_bits(&bits, &mask); @@ -1812,12 +1808,11 @@ int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, u32 bits, struct extent_changeset *changeset) { /* - * We don't support EXTENT_LOCKED yet, as current changeset will - * record any bits changed, so for EXTENT_LOCKED case, it will - * either fail with -EEXIST or changeset will record the whole - * range. + * We don't support EXTENT_LOCK_BITS yet, as current changeset will + * record any bits changed, so for EXTENT_LOCK_BITS case, it will either + * fail with -EEXIST or changeset will record the whole range. */ - ASSERT(!(bits & EXTENT_LOCKED)); + ASSERT(!(bits & EXTENT_LOCK_BITS)); return __set_extent_bit(tree, start, end, bits, NULL, NULL, NULL, changeset); } @@ -1826,26 +1821,25 @@ int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, u32 bits, struct extent_changeset *changeset) { /* - * Don't support EXTENT_LOCKED case, same reason as + * Don't support EXTENT_LOCK_BITS case, same reason as * set_record_extent_bits(). */ - ASSERT(!(bits & EXTENT_LOCKED)); + ASSERT(!(bits & EXTENT_LOCK_BITS)); return __clear_extent_bit(tree, start, end, bits, NULL, changeset); } -int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end, - struct extent_state **cached) +bool __try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end, u32 bits, + struct extent_state **cached) { int err; u64 failed_start; - err = __set_extent_bit(tree, start, end, EXTENT_LOCKED, &failed_start, + err = __set_extent_bit(tree, start, end, bits, &failed_start, NULL, cached, NULL); if (err == -EEXIST) { if (failed_start > start) - clear_extent_bit(tree, start, failed_start - 1, - EXTENT_LOCKED, cached); + clear_extent_bit(tree, start, failed_start - 1, bits, cached); return 0; } return 1; @@ -1855,23 +1849,22 @@ int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end, * Either insert or lock state struct between start and end use mask to tell * us if waiting is desired. */ -int lock_extent(struct extent_io_tree *tree, u64 start, u64 end, - struct extent_state **cached_state) +int __lock_extent(struct extent_io_tree *tree, u64 start, u64 end, u32 bits, + struct extent_state **cached_state) { struct extent_state *failed_state = NULL; int err; u64 failed_start; - err = __set_extent_bit(tree, start, end, EXTENT_LOCKED, &failed_start, + err = __set_extent_bit(tree, start, end, bits, &failed_start, &failed_state, cached_state, NULL); while (err == -EEXIST) { if (failed_start != start) clear_extent_bit(tree, start, failed_start - 1, - EXTENT_LOCKED, cached_state); + bits, cached_state); - wait_extent_bit(tree, failed_start, end, EXTENT_LOCKED, - &failed_state); - err = __set_extent_bit(tree, start, end, EXTENT_LOCKED, + wait_extent_bit(tree, failed_start, end, bits, &failed_state); + err = __set_extent_bit(tree, start, end, bits, &failed_start, &failed_state, cached_state, NULL); } diff --git a/fs/btrfs/extent-io-tree.h b/fs/btrfs/extent-io-tree.h index 9d3a52d8f59a..6ffef1cd37c1 100644 --- a/fs/btrfs/extent-io-tree.h +++ b/fs/btrfs/extent-io-tree.h @@ -19,6 +19,7 @@ enum { ENUM_BIT(EXTENT_DIRTY), ENUM_BIT(EXTENT_UPTODATE), ENUM_BIT(EXTENT_LOCKED), + ENUM_BIT(EXTENT_DIO_LOCKED), ENUM_BIT(EXTENT_NEW), ENUM_BIT(EXTENT_DELALLOC), ENUM_BIT(EXTENT_DEFRAG), @@ -67,6 +68,8 @@ enum { EXTENT_ADD_INODE_BYTES | \ EXTENT_CLEAR_ALL_BITS) +#define EXTENT_LOCK_BITS (EXTENT_LOCKED | EXTENT_DIO_LOCKED) + /* * Redefined bits above which are used only in the device allocation tree, * shouldn't be using EXTENT_LOCKED / EXTENT_BOUNDARY / EXTENT_CLEAR_META_RESV @@ -134,12 +137,22 @@ const struct btrfs_fs_info *extent_io_tree_to_fs_info(const struct extent_io_tre void extent_io_tree_init(struct btrfs_fs_info *fs_info, struct extent_io_tree *tree, unsigned int owner); void extent_io_tree_release(struct extent_io_tree *tree); +int __lock_extent(struct extent_io_tree *tree, u64 start, u64 end, u32 bits, + struct extent_state **cached); +bool __try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end, u32 bits, + struct extent_state **cached); -int lock_extent(struct extent_io_tree *tree, u64 start, u64 end, - struct extent_state **cached); +static inline int lock_extent(struct extent_io_tree *tree, u64 start, u64 end, + struct extent_state **cached) +{ + return __lock_extent(tree, start, end, EXTENT_LOCKED, cached); +} -int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end, - struct extent_state **cached); +static inline bool try_lock_extent(struct extent_io_tree *tree, u64 start, + u64 end, struct extent_state **cached) +{ + return __try_lock_extent(tree, start, end, EXTENT_LOCKED, cached); +} int __init extent_state_init_cachep(void); void __cold extent_state_free_cachep(void); @@ -212,5 +225,22 @@ int find_contiguous_extent_bit(struct extent_io_tree *tree, u64 start, bool btrfs_find_delalloc_range(struct extent_io_tree *tree, u64 *start, u64 *end, u64 max_bytes, struct extent_state **cached_state); +static inline int lock_dio_extent(struct extent_io_tree *tree, u64 start, + u64 end, struct extent_state **cached) +{ + return __lock_extent(tree, start, end, EXTENT_DIO_LOCKED, cached); +} + +static inline bool try_lock_dio_extent(struct extent_io_tree *tree, u64 start, + u64 end, struct extent_state **cached) +{ + return __try_lock_extent(tree, start, end, EXTENT_DIO_LOCKED, cached); +} + +static inline int unlock_dio_extent(struct extent_io_tree *tree, u64 start, + u64 end, struct extent_state **cached) +{ + return __clear_extent_bit(tree, start, end, EXTENT_DIO_LOCKED, cached, NULL); +} #endif /* BTRFS_EXTENT_IO_TREE_H */ diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index feec49e6f9c8..a5966324607d 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -6551,13 +6551,13 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range) continue; ret = btrfs_trim_free_extents(device, &group_trimmed); + + trimmed += group_trimmed; if (ret) { dev_failed++; dev_ret = ret; break; } - - trimmed += group_trimmed; } mutex_unlock(&fs_devices->device_list_mutex); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index c73cd4f89015..39c9677c47d5 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -101,6 +101,13 @@ struct btrfs_bio_ctrl { blk_opf_t opf; btrfs_bio_end_io_t end_io_func; struct writeback_control *wbc; + + /* + * The sectors of the page which are going to be submitted by + * extent_writepage_io(). + * This is to avoid touching ranges covered by compression/inline. + */ + unsigned long submit_bitmap; }; static void submit_one_bio(struct btrfs_bio_ctrl *bio_ctrl) @@ -117,7 +124,7 @@ static void submit_one_bio(struct btrfs_bio_ctrl *bio_ctrl) bio_ctrl->compress_type != BTRFS_COMPRESS_NONE) btrfs_submit_compressed_read(bbio); else - btrfs_submit_bio(bbio, 0); + btrfs_submit_bbio(bbio, 0); /* The bbio is owned by the end_io handler now */ bio_ctrl->bbio = NULL; @@ -164,11 +171,10 @@ void __cold extent_buffer_free_cachep(void) kmem_cache_destroy(extent_buffer_cache); } -static void process_one_page(struct btrfs_fs_info *fs_info, - struct page *page, const struct page *locked_page, - unsigned long page_ops, u64 start, u64 end) +static void process_one_folio(struct btrfs_fs_info *fs_info, + struct folio *folio, const struct folio *locked_folio, + unsigned long page_ops, u64 start, u64 end) { - struct folio *folio = page_folio(page); u32 len; ASSERT(end + 1 - start != 0 && end + 1 - start < U32_MAX); @@ -183,13 +189,13 @@ static void process_one_page(struct btrfs_fs_info *fs_info, if (page_ops & PAGE_END_WRITEBACK) btrfs_folio_clamp_clear_writeback(fs_info, folio, start, len); - if (page != locked_page && (page_ops & PAGE_UNLOCK)) + if (folio != locked_folio && (page_ops & PAGE_UNLOCK)) btrfs_folio_end_writer_lock(fs_info, folio, start, len); } -static void __process_pages_contig(struct address_space *mapping, - const struct page *locked_page, u64 start, u64 end, - unsigned long page_ops) +static void __process_folios_contig(struct address_space *mapping, + const struct folio *locked_folio, u64 start, + u64 end, unsigned long page_ops) { struct btrfs_fs_info *fs_info = inode_to_fs_info(mapping->host); pgoff_t start_index = start >> PAGE_SHIFT; @@ -207,8 +213,8 @@ static void __process_pages_contig(struct address_space *mapping, for (i = 0; i < found_folios; i++) { struct folio *folio = fbatch.folios[i]; - process_one_page(fs_info, &folio->page, locked_page, - page_ops, start, end); + process_one_folio(fs_info, folio, locked_folio, + page_ops, start, end); } folio_batch_release(&fbatch); cond_resched(); @@ -216,24 +222,23 @@ static void __process_pages_contig(struct address_space *mapping, } static noinline void __unlock_for_delalloc(const struct inode *inode, - const struct page *locked_page, + const struct folio *locked_folio, u64 start, u64 end) { unsigned long index = start >> PAGE_SHIFT; unsigned long end_index = end >> PAGE_SHIFT; - ASSERT(locked_page); - if (index == locked_page->index && end_index == index) + ASSERT(locked_folio); + if (index == locked_folio->index && end_index == index) return; - __process_pages_contig(inode->i_mapping, locked_page, start, end, - PAGE_UNLOCK); + __process_folios_contig(inode->i_mapping, locked_folio, start, end, + PAGE_UNLOCK); } -static noinline int lock_delalloc_pages(struct inode *inode, - const struct page *locked_page, - u64 start, - u64 end) +static noinline int lock_delalloc_folios(struct inode *inode, + const struct folio *locked_folio, + u64 start, u64 end) { struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct address_space *mapping = inode->i_mapping; @@ -243,7 +248,7 @@ static noinline int lock_delalloc_pages(struct inode *inode, u64 processed_end = start; struct folio_batch fbatch; - if (index == locked_page->index && index == end_index) + if (index == locked_folio->index && index == end_index) return 0; folio_batch_init(&fbatch); @@ -257,23 +262,22 @@ static noinline int lock_delalloc_pages(struct inode *inode, for (i = 0; i < found_folios; i++) { struct folio *folio = fbatch.folios[i]; - struct page *page = folio_page(folio, 0); u32 len = end + 1 - start; - if (page == locked_page) + if (folio == locked_folio) continue; if (btrfs_folio_start_writer_lock(fs_info, folio, start, len)) goto out; - if (!PageDirty(page) || page->mapping != mapping) { + if (!folio_test_dirty(folio) || folio->mapping != mapping) { btrfs_folio_end_writer_lock(fs_info, folio, start, len); goto out; } - processed_end = page_offset(page) + PAGE_SIZE - 1; + processed_end = folio_pos(folio) + folio_size(folio) - 1; } folio_batch_release(&fbatch); cond_resched(); @@ -283,7 +287,8 @@ static noinline int lock_delalloc_pages(struct inode *inode, out: folio_batch_release(&fbatch); if (processed_end > start) - __unlock_for_delalloc(inode, locked_page, start, processed_end); + __unlock_for_delalloc(inode, locked_folio, start, + processed_end); return -EAGAIN; } @@ -304,8 +309,8 @@ out: */ EXPORT_FOR_TESTS noinline_for_stack bool find_lock_delalloc_range(struct inode *inode, - struct page *locked_page, u64 *start, - u64 *end) + struct folio *locked_folio, + u64 *start, u64 *end) { struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree; @@ -323,9 +328,9 @@ noinline_for_stack bool find_lock_delalloc_range(struct inode *inode, /* Caller should pass a valid @end to indicate the search range end */ ASSERT(orig_end > orig_start); - /* The range should at least cover part of the page */ - ASSERT(!(orig_start >= page_offset(locked_page) + PAGE_SIZE || - orig_end <= page_offset(locked_page))); + /* The range should at least cover part of the folio */ + ASSERT(!(orig_start >= folio_pos(locked_folio) + folio_size(locked_folio) || + orig_end <= folio_pos(locked_folio))); again: /* step one, find a bunch of delalloc bytes starting at start */ delalloc_start = *start; @@ -342,25 +347,25 @@ again: } /* - * start comes from the offset of locked_page. We have to lock - * pages in order, so we can't process delalloc bytes before - * locked_page + * start comes from the offset of locked_folio. We have to lock + * folios in order, so we can't process delalloc bytes before + * locked_folio */ if (delalloc_start < *start) delalloc_start = *start; /* - * make sure to limit the number of pages we try to lock down + * make sure to limit the number of folios we try to lock down */ if (delalloc_end + 1 - delalloc_start > max_bytes) delalloc_end = delalloc_start + max_bytes - 1; - /* step two, lock all the pages after the page that has start */ - ret = lock_delalloc_pages(inode, locked_page, - delalloc_start, delalloc_end); + /* step two, lock all the folioss after the folios that has start */ + ret = lock_delalloc_folios(inode, locked_folio, delalloc_start, + delalloc_end); ASSERT(!ret || ret == -EAGAIN); if (ret == -EAGAIN) { - /* some of the pages are gone, lets avoid looping by + /* some of the folios are gone, lets avoid looping by * shortening the size of the delalloc range we're searching */ free_extent_state(cached_state); @@ -384,8 +389,8 @@ again: unlock_extent(tree, delalloc_start, delalloc_end, &cached_state); if (!ret) { - __unlock_for_delalloc(inode, locked_page, - delalloc_start, delalloc_end); + __unlock_for_delalloc(inode, locked_folio, delalloc_start, + delalloc_end); cond_resched(); goto again; } @@ -396,40 +401,41 @@ out_failed: } void extent_clear_unlock_delalloc(struct btrfs_inode *inode, u64 start, u64 end, - const struct page *locked_page, + const struct folio *locked_folio, struct extent_state **cached, u32 clear_bits, unsigned long page_ops) { clear_extent_bit(&inode->io_tree, start, end, clear_bits, cached); - __process_pages_contig(inode->vfs_inode.i_mapping, locked_page, - start, end, page_ops); + __process_folios_contig(inode->vfs_inode.i_mapping, locked_folio, start, + end, page_ops); } -static bool btrfs_verify_page(struct page *page, u64 start) +static bool btrfs_verify_folio(struct folio *folio, u64 start, u32 len) { - if (!fsverity_active(page->mapping->host) || - PageUptodate(page) || - start >= i_size_read(page->mapping->host)) + struct btrfs_fs_info *fs_info = folio_to_fs_info(folio); + + if (!fsverity_active(folio->mapping->host) || + btrfs_folio_test_uptodate(fs_info, folio, start, len) || + start >= i_size_read(folio->mapping->host)) return true; - return fsverity_verify_page(page); + return fsverity_verify_folio(folio); } -static void end_page_read(struct page *page, bool uptodate, u64 start, u32 len) +static void end_folio_read(struct folio *folio, bool uptodate, u64 start, u32 len) { - struct btrfs_fs_info *fs_info = page_to_fs_info(page); - struct folio *folio = page_folio(page); + struct btrfs_fs_info *fs_info = folio_to_fs_info(folio); - ASSERT(page_offset(page) <= start && - start + len <= page_offset(page) + PAGE_SIZE); + ASSERT(folio_pos(folio) <= start && + start + len <= folio_pos(folio) + PAGE_SIZE); - if (uptodate && btrfs_verify_page(page, start)) + if (uptodate && btrfs_verify_folio(folio, start, len)) btrfs_folio_set_uptodate(fs_info, folio, start, len); else btrfs_folio_clear_uptodate(fs_info, folio, start, len); - if (!btrfs_is_subpage(fs_info, page->mapping)) - unlock_page(page); + if (!btrfs_is_subpage(fs_info, folio->mapping)) + folio_unlock(folio); else btrfs_subpage_end_reader(fs_info, folio, start, len); } @@ -471,8 +477,8 @@ static void end_bbio_data_write(struct btrfs_bio *bbio) "incomplete page write with offset %zu and length %zu", fi.offset, fi.length); - btrfs_finish_ordered_extent(bbio->ordered, - folio_page(folio, 0), start, len, !error); + btrfs_finish_ordered_extent(bbio->ordered, folio, start, len, + !error); if (error) mapping_set_error(folio->mapping, error); btrfs_folio_clear_writeback(fs_info, folio, start, len); @@ -481,85 +487,14 @@ static void end_bbio_data_write(struct btrfs_bio *bbio) bio_put(bio); } -/* - * Record previously processed extent range - * - * For endio_readpage_release_extent() to handle a full extent range, reducing - * the extent io operations. - */ -struct processed_extent { - struct btrfs_inode *inode; - /* Start of the range in @inode */ - u64 start; - /* End of the range in @inode */ - u64 end; - bool uptodate; -}; - -/* - * Try to release processed extent range - * - * May not release the extent range right now if the current range is - * contiguous to processed extent. - * - * Will release processed extent when any of @inode, @uptodate, the range is - * no longer contiguous to the processed range. - * - * Passing @inode == NULL will force processed extent to be released. - */ -static void endio_readpage_release_extent(struct processed_extent *processed, - struct btrfs_inode *inode, u64 start, u64 end, - bool uptodate) -{ - struct extent_state *cached = NULL; - struct extent_io_tree *tree; - - /* The first extent, initialize @processed */ - if (!processed->inode) - goto update; - - /* - * Contiguous to processed extent, just uptodate the end. - * - * Several things to notice: - * - * - bio can be merged as long as on-disk bytenr is contiguous - * This means we can have page belonging to other inodes, thus need to - * check if the inode still matches. - * - bvec can contain range beyond current page for multi-page bvec - * Thus we need to do processed->end + 1 >= start check - */ - if (processed->inode == inode && processed->uptodate == uptodate && - processed->end + 1 >= start && end >= processed->end) { - processed->end = end; - return; - } - - tree = &processed->inode->io_tree; - /* - * Now we don't have range contiguous to the processed range, release - * the processed range now. - */ - unlock_extent(tree, processed->start, processed->end, &cached); - -update: - /* Update processed to current range */ - processed->inode = inode; - processed->start = start; - processed->end = end; - processed->uptodate = uptodate; -} - -static void begin_page_read(struct btrfs_fs_info *fs_info, struct page *page) +static void begin_folio_read(struct btrfs_fs_info *fs_info, struct folio *folio) { - struct folio *folio = page_folio(page); - ASSERT(folio_test_locked(folio)); if (!btrfs_is_subpage(fs_info, folio->mapping)) return; ASSERT(folio_test_private(folio)); - btrfs_subpage_start_reader(fs_info, folio, page_offset(page), PAGE_SIZE); + btrfs_subpage_start_reader(fs_info, folio, folio_pos(folio), PAGE_SIZE); } /* @@ -578,7 +513,6 @@ static void end_bbio_data_read(struct btrfs_bio *bbio) { struct btrfs_fs_info *fs_info = bbio->fs_info; struct bio *bio = &bbio->bio; - struct processed_extent processed = { 0 }; struct folio_iter fi; const u32 sectorsize = fs_info->sectorsize; @@ -642,12 +576,8 @@ static void end_bbio_data_read(struct btrfs_bio *bbio) } /* Update page status and unlock. */ - end_page_read(folio_page(folio, 0), uptodate, start, len); - endio_readpage_release_extent(&processed, BTRFS_I(inode), - start, end, uptodate); + end_folio_read(folio, uptodate, start, len); } - /* Release the last extent */ - endio_readpage_release_extent(&processed, NULL, 0, 0, false); bio_put(bio); } @@ -737,12 +667,13 @@ static int alloc_eb_folio_array(struct extent_buffer *eb, bool nofail) } static bool btrfs_bio_is_contig(struct btrfs_bio_ctrl *bio_ctrl, - struct page *page, u64 disk_bytenr, + struct folio *folio, u64 disk_bytenr, unsigned int pg_offset) { struct bio *bio = &bio_ctrl->bbio->bio; struct bio_vec *bvec = bio_last_bvec_all(bio); const sector_t sector = disk_bytenr >> SECTOR_SHIFT; + struct folio *bv_folio = page_folio(bvec->bv_page); if (bio_ctrl->compress_type != BTRFS_COMPRESS_NONE) { /* @@ -755,7 +686,7 @@ static bool btrfs_bio_is_contig(struct btrfs_bio_ctrl *bio_ctrl, /* * The contig check requires the following conditions to be met: * - * 1) The pages are belonging to the same inode + * 1) The folios are belonging to the same inode * This is implied by the call chain. * * 2) The range has adjacent logical bytenr @@ -764,8 +695,8 @@ static bool btrfs_bio_is_contig(struct btrfs_bio_ctrl *bio_ctrl, * This is required for the usage of btrfs_bio->file_offset. */ return bio_end_sector(bio) == sector && - page_offset(bvec->bv_page) + bvec->bv_offset + bvec->bv_len == - page_offset(page) + pg_offset; + folio_pos(bv_folio) + bvec->bv_offset + bvec->bv_len == + folio_pos(folio) + pg_offset; } static void alloc_new_bio(struct btrfs_inode *inode, @@ -818,17 +749,17 @@ static void alloc_new_bio(struct btrfs_inode *inode, * The mirror number for this IO should already be initizlied in * @bio_ctrl->mirror_num. */ -static void submit_extent_page(struct btrfs_bio_ctrl *bio_ctrl, - u64 disk_bytenr, struct page *page, +static void submit_extent_folio(struct btrfs_bio_ctrl *bio_ctrl, + u64 disk_bytenr, struct folio *folio, size_t size, unsigned long pg_offset) { - struct btrfs_inode *inode = page_to_inode(page); + struct btrfs_inode *inode = folio_to_inode(folio); ASSERT(pg_offset + size <= PAGE_SIZE); ASSERT(bio_ctrl->end_io_func); if (bio_ctrl->bbio && - !btrfs_bio_is_contig(bio_ctrl, page, disk_bytenr, pg_offset)) + !btrfs_bio_is_contig(bio_ctrl, folio, disk_bytenr, pg_offset)) submit_one_bio(bio_ctrl); do { @@ -837,7 +768,7 @@ static void submit_extent_page(struct btrfs_bio_ctrl *bio_ctrl, /* Allocate new bio if needed */ if (!bio_ctrl->bbio) { alloc_new_bio(inode, bio_ctrl, disk_bytenr, - page_offset(page) + pg_offset); + folio_pos(folio) + pg_offset); } /* Cap to the current ordered extent boundary if there is one. */ @@ -847,21 +778,22 @@ static void submit_extent_page(struct btrfs_bio_ctrl *bio_ctrl, len = bio_ctrl->len_to_oe_boundary; } - if (bio_add_page(&bio_ctrl->bbio->bio, page, len, pg_offset) != len) { + if (!bio_add_folio(&bio_ctrl->bbio->bio, folio, len, pg_offset)) { /* bio full: move on to a new one */ submit_one_bio(bio_ctrl); continue; } if (bio_ctrl->wbc) - wbc_account_cgroup_owner(bio_ctrl->wbc, page, len); + wbc_account_cgroup_owner(bio_ctrl->wbc, &folio->page, + len); size -= len; pg_offset += len; disk_bytenr += len; /* - * len_to_oe_boundary defaults to U32_MAX, which isn't page or + * len_to_oe_boundary defaults to U32_MAX, which isn't folio or * sector aligned. alloc_new_bio() then sets it to the end of * our ordered extent for writes into zoned devices. * @@ -871,15 +803,15 @@ static void submit_extent_page(struct btrfs_bio_ctrl *bio_ctrl, * boundary is correct. * * When len_to_oe_boundary is U32_MAX, the cap above would - * result in a 4095 byte IO for the last page right before - * we hit the bio limit of UINT_MAX. bio_add_page() has all + * result in a 4095 byte IO for the last folio right before + * we hit the bio limit of UINT_MAX. bio_add_folio() has all * the checks required to make sure we don't overflow the bio, * and we should just ignore len_to_oe_boundary completely * unless we're using it to track an ordered extent. * * It's pretty hard to make a bio sized U32_MAX, but it can * happen when the page cache is able to feed us contiguous - * pages for large extents. + * folios for large extents. */ if (bio_ctrl->len_to_oe_boundary != U32_MAX) bio_ctrl->len_to_oe_boundary -= len; @@ -952,27 +884,28 @@ int set_folio_extent_mapped(struct folio *folio) return 0; } -void clear_page_extent_mapped(struct page *page) +void clear_folio_extent_mapped(struct folio *folio) { - struct folio *folio = page_folio(page); struct btrfs_fs_info *fs_info; - ASSERT(page->mapping); + ASSERT(folio->mapping); if (!folio_test_private(folio)) return; - fs_info = page_to_fs_info(page); - if (btrfs_is_subpage(fs_info, page->mapping)) + fs_info = folio_to_fs_info(folio); + if (btrfs_is_subpage(fs_info, folio->mapping)) return btrfs_detach_subpage(fs_info, folio); folio_detach_private(folio); } -static struct extent_map *__get_extent_map(struct inode *inode, struct page *page, - u64 start, u64 len, struct extent_map **em_cached) +static struct extent_map *__get_extent_map(struct inode *inode, + struct folio *folio, u64 start, + u64 len, struct extent_map **em_cached) { struct extent_map *em; + struct extent_state *cached_state = NULL; ASSERT(em_cached); @@ -988,12 +921,15 @@ static struct extent_map *__get_extent_map(struct inode *inode, struct page *pag *em_cached = NULL; } - em = btrfs_get_extent(BTRFS_I(inode), page, start, len); + btrfs_lock_and_flush_ordered_range(BTRFS_I(inode), start, start + len - 1, &cached_state); + em = btrfs_get_extent(BTRFS_I(inode), folio, start, len); if (!IS_ERR(em)) { BUG_ON(*em_cached); refcount_inc(&em->refs); *em_cached = em; } + unlock_extent(&BTRFS_I(inode)->io_tree, start, start + len - 1, &cached_state); + return em; } /* @@ -1003,12 +939,12 @@ static struct extent_map *__get_extent_map(struct inode *inode, struct page *pag * XXX JDM: This needs looking at to ensure proper page locking * return 0 on success, otherwise return error */ -static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, +static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached, struct btrfs_bio_ctrl *bio_ctrl, u64 *prev_em_start) { - struct inode *inode = page->mapping->host; + struct inode *inode = folio->mapping->host; struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); - u64 start = page_offset(page); + u64 start = folio_pos(folio); const u64 end = start + PAGE_SIZE - 1; u64 cur = start; u64 extent_offset; @@ -1019,25 +955,23 @@ static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, size_t pg_offset = 0; size_t iosize; size_t blocksize = fs_info->sectorsize; - struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree; - ret = set_page_extent_mapped(page); + ret = set_folio_extent_mapped(folio); if (ret < 0) { - unlock_extent(tree, start, end, NULL); - unlock_page(page); + folio_unlock(folio); return ret; } - if (page->index == last_byte >> PAGE_SHIFT) { - size_t zero_offset = offset_in_page(last_byte); + if (folio->index == last_byte >> folio_shift(folio)) { + size_t zero_offset = offset_in_folio(folio, last_byte); if (zero_offset) { - iosize = PAGE_SIZE - zero_offset; - memzero_page(page, zero_offset, iosize); + iosize = folio_size(folio) - zero_offset; + folio_zero_range(folio, zero_offset, iosize); } } bio_ctrl->end_io_func = end_bbio_data_read; - begin_page_read(fs_info, page); + begin_folio_read(fs_info, folio); while (cur <= end) { enum btrfs_compression_type compress_type = BTRFS_COMPRESS_NONE; bool force_bio_submit = false; @@ -1045,16 +979,15 @@ static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, ASSERT(IS_ALIGNED(cur, fs_info->sectorsize)); if (cur >= last_byte) { - iosize = PAGE_SIZE - pg_offset; - memzero_page(page, pg_offset, iosize); - unlock_extent(tree, cur, cur + iosize - 1, NULL); - end_page_read(page, true, cur, iosize); + iosize = folio_size(folio) - pg_offset; + folio_zero_range(folio, pg_offset, iosize); + end_folio_read(folio, true, cur, iosize); break; } - em = __get_extent_map(inode, page, cur, end - cur + 1, em_cached); + em = __get_extent_map(inode, folio, cur, end - cur + 1, + em_cached); if (IS_ERR(em)) { - unlock_extent(tree, cur, end, NULL); - end_page_read(page, false, cur, end + 1 - cur); + end_folio_read(folio, false, cur, end + 1 - cur); return PTR_ERR(em); } extent_offset = cur - em->start; @@ -1079,8 +1012,8 @@ static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, * to the same compressed extent (possibly with a different * offset and/or length, so it either points to the whole extent * or only part of it), we must make sure we do not submit a - * single bio to populate the pages for the 2 ranges because - * this makes the compressed extent read zero out the pages + * single bio to populate the folios for the 2 ranges because + * this makes the compressed extent read zero out the folios * belonging to the 2nd range. Imagine the following scenario: * * File layout @@ -1093,13 +1026,13 @@ static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, * [extent X, compressed length = 4K uncompressed length = 16K] * * If the bio to read the compressed extent covers both ranges, - * it will decompress extent X into the pages belonging to the + * it will decompress extent X into the folios belonging to the * first range and then it will stop, zeroing out the remaining - * pages that belong to the other range that points to extent X. + * folios that belong to the other range that points to extent X. * So here we make sure we submit 2 bios, one for the first * range and another one for the third range. Both will target * the same physical extent from disk, but we can't currently - * make the compressed bio endio callback populate the pages + * make the compressed bio endio callback populate the folios * for both ranges because each compressed bio is tightly * coupled with a single extent map, and each range can have * an extent map with a different offset value relative to the @@ -1120,18 +1053,16 @@ static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, /* we've found a hole, just zero and go on */ if (block_start == EXTENT_MAP_HOLE) { - memzero_page(page, pg_offset, iosize); + folio_zero_range(folio, pg_offset, iosize); - unlock_extent(tree, cur, cur + iosize - 1, NULL); - end_page_read(page, true, cur, iosize); + end_folio_read(folio, true, cur, iosize); cur = cur + iosize; pg_offset += iosize; continue; } - /* the get_extent function already copied into the page */ + /* the get_extent function already copied into the folio */ if (block_start == EXTENT_MAP_INLINE) { - unlock_extent(tree, cur, cur + iosize - 1, NULL); - end_page_read(page, true, cur, iosize); + end_folio_read(folio, true, cur, iosize); cur = cur + iosize; pg_offset += iosize; continue; @@ -1144,8 +1075,8 @@ static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, if (force_bio_submit) submit_one_bio(bio_ctrl); - submit_extent_page(bio_ctrl, disk_bytenr, page, iosize, - pg_offset); + submit_extent_folio(bio_ctrl, disk_bytenr, folio, iosize, + pg_offset); cur = cur + iosize; pg_offset += iosize; } @@ -1155,17 +1086,11 @@ static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, int btrfs_read_folio(struct file *file, struct folio *folio) { - struct page *page = &folio->page; - struct btrfs_inode *inode = page_to_inode(page); - u64 start = page_offset(page); - u64 end = start + PAGE_SIZE - 1; struct btrfs_bio_ctrl bio_ctrl = { .opf = REQ_OP_READ }; struct extent_map *em_cached = NULL; int ret; - btrfs_lock_and_flush_ordered_range(inode, start, end, NULL); - - ret = btrfs_do_readpage(page, &em_cached, &bio_ctrl, NULL); + ret = btrfs_do_readpage(folio, &em_cached, &bio_ctrl, NULL); free_extent_map(em_cached); /* @@ -1176,28 +1101,8 @@ int btrfs_read_folio(struct file *file, struct folio *folio) return ret; } -static inline void contiguous_readpages(struct page *pages[], int nr_pages, - u64 start, u64 end, - struct extent_map **em_cached, - struct btrfs_bio_ctrl *bio_ctrl, - u64 *prev_em_start) -{ - struct btrfs_inode *inode = page_to_inode(pages[0]); - int index; - - ASSERT(em_cached); - - btrfs_lock_and_flush_ordered_range(inode, start, end, NULL); - - for (index = 0; index < nr_pages; index++) { - btrfs_do_readpage(pages[index], em_cached, bio_ctrl, - prev_em_start); - put_page(pages[index]); - } -} - /* - * helper for __extent_writepage, doing all of the delayed allocation setup. + * helper for extent_writepage(), doing all of the delayed allocation setup. * * This returns 1 if btrfs_run_delalloc_range function did all the work required * to write the page (copy into inline extent). In this case the IO has @@ -1207,13 +1112,14 @@ static inline void contiguous_readpages(struct page *pages[], int nr_pages, * This returns < 0 if there were errors (page still locked) */ static noinline_for_stack int writepage_delalloc(struct btrfs_inode *inode, - struct page *page, struct writeback_control *wbc) + struct folio *folio, + struct btrfs_bio_ctrl *bio_ctrl) { struct btrfs_fs_info *fs_info = inode_to_fs_info(&inode->vfs_inode); - struct folio *folio = page_folio(page); - const bool is_subpage = btrfs_is_subpage(fs_info, page->mapping); - const u64 page_start = page_offset(page); - const u64 page_end = page_start + PAGE_SIZE - 1; + struct writeback_control *wbc = bio_ctrl->wbc; + const bool is_subpage = btrfs_is_subpage(fs_info, folio->mapping); + const u64 page_start = folio_pos(folio); + const u64 page_end = page_start + folio_size(folio) - 1; /* * Save the last found delalloc end. As the delalloc end can go beyond * page boundary, thus we cannot rely on subpage bitmap to locate the @@ -1225,10 +1131,18 @@ static noinline_for_stack int writepage_delalloc(struct btrfs_inode *inode, u64 delalloc_to_write = 0; int ret = 0; - /* Lock all (subpage) delalloc ranges inside the page first. */ + /* Save the dirty bitmap as our submission bitmap will be a subset of it. */ + if (btrfs_is_subpage(fs_info, inode->vfs_inode.i_mapping)) { + ASSERT(fs_info->sectors_per_page > 1); + btrfs_get_subpage_dirty_bitmap(fs_info, folio, &bio_ctrl->submit_bitmap); + } else { + bio_ctrl->submit_bitmap = 1; + } + + /* Lock all (subpage) delalloc ranges inside the folio first. */ while (delalloc_start < page_end) { delalloc_end = page_end; - if (!find_lock_delalloc_range(&inode->vfs_inode, page, + if (!find_lock_delalloc_range(&inode->vfs_inode, folio, &delalloc_start, &delalloc_end)) { delalloc_start = delalloc_end + 1; continue; @@ -1253,7 +1167,7 @@ static noinline_for_stack int writepage_delalloc(struct btrfs_inode *inode, if (!is_subpage) { /* * For non-subpage case, the found delalloc range must - * cover this page and there must be only one locked + * cover this folio and there must be only one locked * delalloc range. */ found_start = page_start; @@ -1267,7 +1181,7 @@ static noinline_for_stack int writepage_delalloc(struct btrfs_inode *inode, break; /* * The subpage range covers the last sector, the delalloc range may - * end beyond the page boundary, use the saved delalloc_end + * end beyond the folio boundary, use the saved delalloc_end * instead. */ if (found_start + found_len >= page_end) @@ -1275,7 +1189,8 @@ static noinline_for_stack int writepage_delalloc(struct btrfs_inode *inode, if (ret >= 0) { /* No errors hit so far, run the current delalloc range. */ - ret = btrfs_run_delalloc_range(inode, page, found_start, + ret = btrfs_run_delalloc_range(inode, folio, + found_start, found_start + found_len - 1, wbc); } else { @@ -1285,30 +1200,27 @@ static noinline_for_stack int writepage_delalloc(struct btrfs_inode *inode, */ unlock_extent(&inode->io_tree, found_start, found_start + found_len - 1, NULL); - __unlock_for_delalloc(&inode->vfs_inode, page, found_start, + __unlock_for_delalloc(&inode->vfs_inode, folio, + found_start, found_start + found_len - 1); } /* - * We can hit btrfs_run_delalloc_range() with >0 return value. - * - * This happens when either the IO is already done and page - * unlocked (inline) or the IO submission and page unlock would - * be handled as async (compression). - * - * Inline is only possible for regular sectorsize for now. - * - * Compression is possible for both subpage and regular cases, - * but even for subpage compression only happens for page aligned - * range, thus the found delalloc range must go beyond current - * page. + * We have some ranges that's going to be submitted asynchronously + * (compression or inline). These range have their own control + * on when to unlock the pages. We should not touch them + * anymore, so clear the range from the submission bitmap. */ - if (ret > 0) - ASSERT(!is_subpage || found_start + found_len >= page_end); - + if (ret > 0) { + unsigned int start_bit = (found_start - page_start) >> + fs_info->sectorsize_bits; + unsigned int end_bit = (min(page_end + 1, found_start + found_len) - + page_start) >> fs_info->sectorsize_bits; + bitmap_clear(&bio_ctrl->submit_bitmap, start_bit, end_bit - start_bit); + } /* - * Above btrfs_run_delalloc_range() may have unlocked the page, - * thus for the last range, we cannot touch the page anymore. + * Above btrfs_run_delalloc_range() may have unlocked the folio, + * thus for the last range, we cannot touch the folio anymore. */ if (found_start + found_len >= last_delalloc_end + 1) break; @@ -1330,10 +1242,10 @@ out: DIV_ROUND_UP(delalloc_end + 1 - page_start, PAGE_SIZE); /* - * If btrfs_run_dealloc_range() already started I/O and unlocked - * the pages, we just need to account for them here. + * If all ranges are submitted asynchronously, we just need to account + * for them here. */ - if (ret == 1) { + if (bitmap_empty(&bio_ctrl->submit_bitmap, fs_info->sectors_per_page)) { wbc->nr_to_write -= delalloc_to_write; return 1; } @@ -1351,182 +1263,148 @@ out: } /* - * Find the first byte we need to write. + * Return 0 if we have submitted or queued the sector for submission. + * Return <0 for critical errors. * - * For subpage, one page can contain several sectors, and - * __extent_writepage_io() will just grab all extent maps in the page - * range and try to submit all non-inline/non-compressed extents. - * - * This is a big problem for subpage, we shouldn't re-submit already written - * data at all. - * This function will lookup subpage dirty bit to find which range we really - * need to submit. - * - * Return the next dirty range in [@start, @end). - * If no dirty range is found, @start will be page_offset(page) + PAGE_SIZE. + * Caller should make sure filepos < i_size and handle filepos >= i_size case. */ -static void find_next_dirty_byte(const struct btrfs_fs_info *fs_info, - struct page *page, u64 *start, u64 *end) +static int submit_one_sector(struct btrfs_inode *inode, + struct folio *folio, + u64 filepos, struct btrfs_bio_ctrl *bio_ctrl, + loff_t i_size) { - struct folio *folio = page_folio(page); - struct btrfs_subpage *subpage = folio_get_private(folio); - struct btrfs_subpage_info *spi = fs_info->subpage_info; - u64 orig_start = *start; - /* Declare as unsigned long so we can use bitmap ops */ - unsigned long flags; - int range_start_bit; - int range_end_bit; + struct btrfs_fs_info *fs_info = inode->root->fs_info; + struct extent_map *em; + u64 block_start; + u64 disk_bytenr; + u64 extent_offset; + u64 em_end; + const u32 sectorsize = fs_info->sectorsize; - /* - * For regular sector size == page size case, since one page only - * contains one sector, we return the page offset directly. - */ - if (!btrfs_is_subpage(fs_info, page->mapping)) { - *start = page_offset(page); - *end = page_offset(page) + PAGE_SIZE; - return; - } + ASSERT(IS_ALIGNED(filepos, sectorsize)); + + /* @filepos >= i_size case should be handled by the caller. */ + ASSERT(filepos < i_size); - range_start_bit = spi->dirty_offset + - (offset_in_page(orig_start) >> fs_info->sectorsize_bits); + em = btrfs_get_extent(inode, NULL, filepos, sectorsize); + if (IS_ERR(em)) + return PTR_ERR_OR_ZERO(em); - /* We should have the page locked, but just in case */ - spin_lock_irqsave(&subpage->lock, flags); - bitmap_next_set_region(subpage->bitmaps, &range_start_bit, &range_end_bit, - spi->dirty_offset + spi->bitmap_nr_bits); - spin_unlock_irqrestore(&subpage->lock, flags); + extent_offset = filepos - em->start; + em_end = extent_map_end(em); + ASSERT(filepos <= em_end); + ASSERT(IS_ALIGNED(em->start, sectorsize)); + ASSERT(IS_ALIGNED(em->len, sectorsize)); - range_start_bit -= spi->dirty_offset; - range_end_bit -= spi->dirty_offset; + block_start = extent_map_block_start(em); + disk_bytenr = extent_map_block_start(em) + extent_offset; - *start = page_offset(page) + range_start_bit * fs_info->sectorsize; - *end = page_offset(page) + range_end_bit * fs_info->sectorsize; + ASSERT(!extent_map_is_compressed(em)); + ASSERT(block_start != EXTENT_MAP_HOLE); + ASSERT(block_start != EXTENT_MAP_INLINE); + + free_extent_map(em); + em = NULL; + + btrfs_set_range_writeback(inode, filepos, filepos + sectorsize - 1); + /* + * Above call should set the whole folio with writeback flag, even + * just for a single subpage sector. + * As long as the folio is properly locked and the range is correct, + * we should always get the folio with writeback flag. + */ + ASSERT(folio_test_writeback(folio)); + + /* + * Although the PageDirty bit is cleared before entering this + * function, subpage dirty bit is not cleared. + * So clear subpage dirty bit here so next time we won't submit + * folio for range already written to disk. + */ + btrfs_folio_clear_dirty(fs_info, folio, filepos, sectorsize); + submit_extent_folio(bio_ctrl, disk_bytenr, folio, + sectorsize, filepos - folio_pos(folio)); + return 0; } /* - * helper for __extent_writepage. This calls the writepage start hooks, + * Helper for extent_writepage(). This calls the writepage start hooks, * and does the loop to map the page into extents and bios. * * We return 1 if the IO is started and the page is unlocked, * 0 if all went well (page still locked) * < 0 if there were errors (page still locked) */ -static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, - struct page *page, u64 start, u32 len, - struct btrfs_bio_ctrl *bio_ctrl, - loff_t i_size, - int *nr_ret) +static noinline_for_stack int extent_writepage_io(struct btrfs_inode *inode, + struct folio *folio, + u64 start, u32 len, + struct btrfs_bio_ctrl *bio_ctrl, + loff_t i_size) { struct btrfs_fs_info *fs_info = inode->root->fs_info; - u64 cur = start; - u64 end = start + len - 1; - u64 extent_offset; - u64 block_start; - struct extent_map *em; + unsigned long range_bitmap = 0; + bool submitted_io = false; + const u64 folio_start = folio_pos(folio); + u64 cur; + int bit; int ret = 0; - int nr = 0; - ASSERT(start >= page_offset(page) && - start + len <= page_offset(page) + PAGE_SIZE); + ASSERT(start >= folio_start && + start + len <= folio_start + folio_size(folio)); - ret = btrfs_writepage_cow_fixup(page); + ret = btrfs_writepage_cow_fixup(folio); if (ret) { /* Fixup worker will requeue */ - redirty_page_for_writepage(bio_ctrl->wbc, page); - unlock_page(page); + folio_redirty_for_writepage(bio_ctrl->wbc, folio); + folio_unlock(folio); return 1; } + for (cur = start; cur < start + len; cur += fs_info->sectorsize) + set_bit((cur - folio_start) >> fs_info->sectorsize_bits, &range_bitmap); + bitmap_and(&bio_ctrl->submit_bitmap, &bio_ctrl->submit_bitmap, &range_bitmap, + fs_info->sectors_per_page); + bio_ctrl->end_io_func = end_bbio_data_write; - while (cur <= end) { - u32 len = end - cur + 1; - u64 disk_bytenr; - u64 em_end; - u64 dirty_range_start = cur; - u64 dirty_range_end; - u32 iosize; + + for_each_set_bit(bit, &bio_ctrl->submit_bitmap, fs_info->sectors_per_page) { + cur = folio_pos(folio) + (bit << fs_info->sectorsize_bits); if (cur >= i_size) { - btrfs_mark_ordered_io_finished(inode, page, cur, len, - true); + btrfs_mark_ordered_io_finished(inode, folio, cur, + start + len - cur, true); /* * This range is beyond i_size, thus we don't need to * bother writing back. * But we still need to clear the dirty subpage bit, or - * the next time the page gets dirtied, we will try to + * the next time the folio gets dirtied, we will try to * writeback the sectors with subpage dirty bits, * causing writeback without ordered extent. */ - btrfs_folio_clear_dirty(fs_info, page_folio(page), cur, len); + btrfs_folio_clear_dirty(fs_info, folio, cur, + start + len - cur); break; } - - find_next_dirty_byte(fs_info, page, &dirty_range_start, - &dirty_range_end); - if (cur < dirty_range_start) { - cur = dirty_range_start; - continue; - } - - em = btrfs_get_extent(inode, NULL, cur, len); - if (IS_ERR(em)) { - ret = PTR_ERR_OR_ZERO(em); - goto out_error; - } - - extent_offset = cur - em->start; - em_end = extent_map_end(em); - ASSERT(cur <= em_end); - ASSERT(cur < end); - ASSERT(IS_ALIGNED(em->start, fs_info->sectorsize)); - ASSERT(IS_ALIGNED(em->len, fs_info->sectorsize)); - - block_start = extent_map_block_start(em); - disk_bytenr = extent_map_block_start(em) + extent_offset; - - ASSERT(!extent_map_is_compressed(em)); - ASSERT(block_start != EXTENT_MAP_HOLE); - ASSERT(block_start != EXTENT_MAP_INLINE); - - /* - * Note that em_end from extent_map_end() and dirty_range_end from - * find_next_dirty_byte() are all exclusive - */ - iosize = min(min(em_end, end + 1), dirty_range_end) - cur; - free_extent_map(em); - em = NULL; - - /* - * Although the PageDirty bit might be cleared before entering - * this function, subpage dirty bit is not cleared. - * So clear subpage dirty bit here so next time we won't submit - * page for range already written to disk. - */ - btrfs_folio_clear_dirty(fs_info, page_folio(page), cur, iosize); - btrfs_set_range_writeback(inode, cur, cur + iosize - 1); - if (!PageWriteback(page)) { - btrfs_err(inode->root->fs_info, - "page %lu not writeback, cur %llu end %llu", - page->index, cur, end); - } - - - submit_extent_page(bio_ctrl, disk_bytenr, page, iosize, - cur - page_offset(page)); - cur += iosize; - nr++; + ret = submit_one_sector(inode, folio, cur, bio_ctrl, i_size); + if (ret < 0) + goto out; + submitted_io = true; } - btrfs_folio_assert_not_dirty(fs_info, page_folio(page), start, len); - *nr_ret = nr; - return 0; - -out_error: + btrfs_folio_assert_not_dirty(fs_info, folio, start, len); +out: /* - * If we finish without problem, we should not only clear page dirty, - * but also empty subpage dirty bits + * If we didn't submitted any sector (>= i_size), folio dirty get + * cleared but PAGECACHE_TAG_DIRTY is not cleared (only cleared + * by folio_start_writeback() if the folio is not dirty). + * + * Here we set writeback and clear for the range. If the full folio + * is no longer dirty then we clear the PAGECACHE_TAG_DIRTY tag. */ - *nr_ret = nr; + if (!submitted_io) { + btrfs_folio_set_writeback(fs_info, folio, start, len); + btrfs_folio_clear_writeback(fs_info, folio, start, len); + } return ret; } @@ -1539,62 +1417,65 @@ out_error: * Return 0 if everything goes well. * Return <0 for error. */ -static int __extent_writepage(struct page *page, struct btrfs_bio_ctrl *bio_ctrl) +static int extent_writepage(struct folio *folio, struct btrfs_bio_ctrl *bio_ctrl) { - struct folio *folio = page_folio(page); - struct inode *inode = page->mapping->host; - const u64 page_start = page_offset(page); + struct inode *inode = folio->mapping->host; + struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); + const u64 page_start = folio_pos(folio); int ret; - int nr = 0; size_t pg_offset; loff_t i_size = i_size_read(inode); unsigned long end_index = i_size >> PAGE_SHIFT; - trace___extent_writepage(page, inode, bio_ctrl->wbc); + trace_extent_writepage(folio, inode, bio_ctrl->wbc); - WARN_ON(!PageLocked(page)); + WARN_ON(!folio_test_locked(folio)); - pg_offset = offset_in_page(i_size); - if (page->index > end_index || - (page->index == end_index && !pg_offset)) { + pg_offset = offset_in_folio(folio, i_size); + if (folio->index > end_index || + (folio->index == end_index && !pg_offset)) { folio_invalidate(folio, 0, folio_size(folio)); folio_unlock(folio); return 0; } - if (page->index == end_index) - memzero_page(page, pg_offset, PAGE_SIZE - pg_offset); + if (folio->index == end_index) + folio_zero_range(folio, pg_offset, folio_size(folio) - pg_offset); - ret = set_page_extent_mapped(page); + /* + * Default to unlock the whole folio. + * The proper bitmap can only be initialized until writepage_delalloc(). + */ + bio_ctrl->submit_bitmap = (unsigned long)-1; + ret = set_folio_extent_mapped(folio); if (ret < 0) goto done; - ret = writepage_delalloc(BTRFS_I(inode), page, bio_ctrl->wbc); + ret = writepage_delalloc(BTRFS_I(inode), folio, bio_ctrl); if (ret == 1) return 0; if (ret) goto done; - ret = __extent_writepage_io(BTRFS_I(inode), page, page_offset(page), - PAGE_SIZE, bio_ctrl, i_size, &nr); + ret = extent_writepage_io(BTRFS_I(inode), folio, folio_pos(folio), + PAGE_SIZE, bio_ctrl, i_size); if (ret == 1) return 0; bio_ctrl->wbc->nr_to_write--; done: - if (nr == 0) { - /* make sure the mapping tag for page dirty gets cleared */ - set_page_writeback(page); - end_page_writeback(page); - } if (ret) { - btrfs_mark_ordered_io_finished(BTRFS_I(inode), page, page_start, - PAGE_SIZE, !ret); - mapping_set_error(page->mapping, ret); + btrfs_mark_ordered_io_finished(BTRFS_I(inode), folio, + page_start, PAGE_SIZE, !ret); + mapping_set_error(folio->mapping, ret); } - btrfs_folio_end_all_writers(inode_to_fs_info(inode), folio); + /* + * Only unlock ranges that are submitted. As there can be some async + * submitted ranges inside the folio. + */ + btrfs_folio_end_writer_lock_bitmap(fs_info, folio, bio_ctrl->submit_bitmap); ASSERT(ret <= 0); return ret; } @@ -1846,7 +1727,7 @@ static noinline_for_stack void write_one_eb(struct extent_buffer *eb, folio_unlock(folio); } } - btrfs_submit_bio(bbio, 0); + btrfs_submit_bbio(bbio, 0); } /* @@ -1863,17 +1744,16 @@ static noinline_for_stack void write_one_eb(struct extent_buffer *eb, * Return >=0 for the number of submitted extent buffers. * Return <0 for fatal error. */ -static int submit_eb_subpage(struct page *page, struct writeback_control *wbc) +static int submit_eb_subpage(struct folio *folio, struct writeback_control *wbc) { - struct btrfs_fs_info *fs_info = page_to_fs_info(page); - struct folio *folio = page_folio(page); + struct btrfs_fs_info *fs_info = folio_to_fs_info(folio); int submitted = 0; - u64 page_start = page_offset(page); + u64 folio_start = folio_pos(folio); int bit_start = 0; int sectors_per_node = fs_info->nodesize >> fs_info->sectorsize_bits; /* Lock and write each dirty extent buffers in the range */ - while (bit_start < fs_info->subpage_info->bitmap_nr_bits) { + while (bit_start < fs_info->sectors_per_page) { struct btrfs_subpage *subpage = folio_get_private(folio); struct extent_buffer *eb; unsigned long flags; @@ -1883,21 +1763,21 @@ static int submit_eb_subpage(struct page *page, struct writeback_control *wbc) * Take private lock to ensure the subpage won't be detached * in the meantime. */ - spin_lock(&page->mapping->i_private_lock); + spin_lock(&folio->mapping->i_private_lock); if (!folio_test_private(folio)) { - spin_unlock(&page->mapping->i_private_lock); + spin_unlock(&folio->mapping->i_private_lock); break; } spin_lock_irqsave(&subpage->lock, flags); - if (!test_bit(bit_start + fs_info->subpage_info->dirty_offset, + if (!test_bit(bit_start + btrfs_bitmap_nr_dirty * fs_info->sectors_per_page, subpage->bitmaps)) { spin_unlock_irqrestore(&subpage->lock, flags); - spin_unlock(&page->mapping->i_private_lock); + spin_unlock(&folio->mapping->i_private_lock); bit_start++; continue; } - start = page_start + bit_start * fs_info->sectorsize; + start = folio_start + bit_start * fs_info->sectorsize; bit_start += sectors_per_node; /* @@ -1906,7 +1786,7 @@ static int submit_eb_subpage(struct page *page, struct writeback_control *wbc) */ eb = find_extent_buffer_nolock(fs_info, start); spin_unlock_irqrestore(&subpage->lock, flags); - spin_unlock(&page->mapping->i_private_lock); + spin_unlock(&folio->mapping->i_private_lock); /* * The eb has already reached 0 refs thus find_extent_buffer() @@ -1945,19 +1825,18 @@ static int submit_eb_subpage(struct page *page, struct writeback_control *wbc) * previous call. * Return <0 for fatal error. */ -static int submit_eb_page(struct page *page, struct btrfs_eb_write_context *ctx) +static int submit_eb_page(struct folio *folio, struct btrfs_eb_write_context *ctx) { struct writeback_control *wbc = ctx->wbc; - struct address_space *mapping = page->mapping; - struct folio *folio = page_folio(page); + struct address_space *mapping = folio->mapping; struct extent_buffer *eb; int ret; if (!folio_test_private(folio)) return 0; - if (page_to_fs_info(page)->nodesize < PAGE_SIZE) - return submit_eb_subpage(page, wbc); + if (folio_to_fs_info(folio)->nodesize < PAGE_SIZE) + return submit_eb_subpage(folio, wbc); spin_lock(&mapping->i_private_lock); if (!folio_test_private(folio)) { @@ -2055,7 +1934,7 @@ retry: for (i = 0; i < nr_folios; i++) { struct folio *folio = fbatch.folios[i]; - ret = submit_eb_page(&folio->page, &ctx); + ret = submit_eb_page(folio, &ctx); if (ret == 0) continue; if (ret < 0) { @@ -2109,7 +1988,7 @@ retry: * extent io tree. Thus we don't want to submit such wild eb * if the fs already has error. * - * We can get ret > 0 from submit_extent_page() indicating how many ebs + * We can get ret > 0 from submit_extent_folio() indicating how many ebs * were submitted. Reset it to 0 to avoid false alerts for the caller. */ if (ret > 0) @@ -2248,7 +2127,7 @@ retry: continue; } - ret = __extent_writepage(&folio->page, bio_ctrl); + ret = extent_writepage(folio, bio_ctrl); if (ret < 0) { done = 1; break; @@ -2295,7 +2174,7 @@ retry: * already been ran (aka, ordered extent inserted) and all pages are still * locked. */ -void extent_write_locked_range(struct inode *inode, const struct page *locked_page, +void extent_write_locked_range(struct inode *inode, const struct folio *locked_folio, u64 start, u64 end, struct writeback_control *wbc, bool pages_dirty) { @@ -2319,37 +2198,46 @@ void extent_write_locked_range(struct inode *inode, const struct page *locked_pa while (cur <= end) { u64 cur_end = min(round_down(cur, PAGE_SIZE) + PAGE_SIZE - 1, end); u32 cur_len = cur_end + 1 - cur; - struct page *page; - int nr = 0; + struct folio *folio; - page = find_get_page(mapping, cur >> PAGE_SHIFT); - ASSERT(PageLocked(page)); - if (pages_dirty && page != locked_page) - ASSERT(PageDirty(page)); + folio = __filemap_get_folio(mapping, cur >> PAGE_SHIFT, 0, 0); - ret = __extent_writepage_io(BTRFS_I(inode), page, cur, cur_len, - &bio_ctrl, i_size, &nr); + /* + * This shouldn't happen, the pages are pinned and locked, this + * code is just in case, but shouldn't actually be run. + */ + if (IS_ERR(folio)) { + btrfs_mark_ordered_io_finished(BTRFS_I(inode), NULL, + cur, cur_len, false); + mapping_set_error(mapping, PTR_ERR(folio)); + cur = cur_end + 1; + continue; + } + + ASSERT(folio_test_locked(folio)); + if (pages_dirty && folio != locked_folio) + ASSERT(folio_test_dirty(folio)); + + /* + * Set the submission bitmap to submit all sectors. + * extent_writepage_io() will do the truncation correctly. + */ + bio_ctrl.submit_bitmap = (unsigned long)-1; + ret = extent_writepage_io(BTRFS_I(inode), folio, cur, cur_len, + &bio_ctrl, i_size); if (ret == 1) goto next_page; - /* Make sure the mapping tag for page dirty gets cleared. */ - if (nr == 0) { - struct folio *folio; - - folio = page_folio(page); - btrfs_folio_set_writeback(fs_info, folio, cur, cur_len); - btrfs_folio_clear_writeback(fs_info, folio, cur, cur_len); - } if (ret) { - btrfs_mark_ordered_io_finished(BTRFS_I(inode), page, + btrfs_mark_ordered_io_finished(BTRFS_I(inode), folio, cur, cur_len, !ret); - mapping_set_error(page->mapping, ret); + mapping_set_error(mapping, ret); } - btrfs_folio_unlock_writer(fs_info, page_folio(page), cur, cur_len); + btrfs_folio_end_writer_lock(fs_info, folio, cur, cur_len); if (ret < 0) found_error = true; next_page: - put_page(page); + folio_put(folio); cur = cur_end + 1; } @@ -2379,18 +2267,12 @@ int btrfs_writepages(struct address_space *mapping, struct writeback_control *wb void btrfs_readahead(struct readahead_control *rac) { struct btrfs_bio_ctrl bio_ctrl = { .opf = REQ_OP_READ | REQ_RAHEAD }; - struct page *pagepool[16]; + struct folio *folio; struct extent_map *em_cached = NULL; u64 prev_em_start = (u64)-1; - int nr; - - while ((nr = readahead_page_batch(rac, pagepool))) { - u64 contig_start = readahead_pos(rac); - u64 contig_end = contig_start + readahead_batch_length(rac) - 1; - contiguous_readpages(pagepool, nr, contig_start, contig_end, - &em_cached, &bio_ctrl, &prev_em_start); - } + while ((folio = readahead_folio(rac)) != NULL) + btrfs_do_readpage(folio, &em_cached, &bio_ctrl, &prev_em_start); if (em_cached) free_extent_map(em_cached); @@ -2435,9 +2317,9 @@ int extent_invalidate_folio(struct extent_io_tree *tree, * to drop the page. */ static bool try_release_extent_state(struct extent_io_tree *tree, - struct page *page, gfp_t mask) + struct folio *folio, gfp_t mask) { - u64 start = page_offset(page); + u64 start = folio_pos(folio); u64 end = start + PAGE_SIZE - 1; bool ret; @@ -2473,11 +2355,11 @@ static bool try_release_extent_state(struct extent_io_tree *tree, * in the range corresponding to the page, both state records and extent * map records are removed */ -bool try_release_extent_mapping(struct page *page, gfp_t mask) +bool try_release_extent_mapping(struct folio *folio, gfp_t mask) { - u64 start = page_offset(page); + u64 start = folio_pos(folio); u64 end = start + PAGE_SIZE - 1; - struct btrfs_inode *inode = page_to_inode(page); + struct btrfs_inode *inode = folio_to_inode(folio); struct extent_io_tree *io_tree = &inode->io_tree; while (start <= end) { @@ -2546,7 +2428,7 @@ next: cond_resched(); } } - return try_release_extent_state(io_tree, page, mask); + return try_release_extent_state(io_tree, folio, mask); } static void __free_extent_buffer(struct extent_buffer *eb) @@ -2572,7 +2454,7 @@ static bool folio_range_has_eb(struct btrfs_fs_info *fs_info, struct folio *foli return true; /* * Even there is no eb refs here, we may still have - * end_page_read() call relying on page::private. + * end_folio_read() call relying on page::private. */ if (atomic_read(&subpage->readers)) return true; @@ -3615,7 +3497,7 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num, ASSERT(ret); } } - btrfs_submit_bio(bbio, mirror_num); + btrfs_submit_bbio(bbio, mirror_num); done: if (wait == WAIT_COMPLETE) { @@ -4171,17 +4053,17 @@ void memmove_extent_buffer(const struct extent_buffer *dst, #define GANG_LOOKUP_SIZE 16 static struct extent_buffer *get_next_extent_buffer( - const struct btrfs_fs_info *fs_info, struct page *page, u64 bytenr) + const struct btrfs_fs_info *fs_info, struct folio *folio, u64 bytenr) { struct extent_buffer *gang[GANG_LOOKUP_SIZE]; struct extent_buffer *found = NULL; - u64 page_start = page_offset(page); - u64 cur = page_start; + u64 folio_start = folio_pos(folio); + u64 cur = folio_start; - ASSERT(in_range(bytenr, page_start, PAGE_SIZE)); + ASSERT(in_range(bytenr, folio_start, PAGE_SIZE)); lockdep_assert_held(&fs_info->buffer_lock); - while (cur < page_start + PAGE_SIZE) { + while (cur < folio_start + PAGE_SIZE) { int ret; int i; @@ -4193,7 +4075,7 @@ static struct extent_buffer *get_next_extent_buffer( goto out; for (i = 0; i < ret; i++) { /* Already beyond page end */ - if (gang[i]->start >= page_start + PAGE_SIZE) + if (gang[i]->start >= folio_start + PAGE_SIZE) goto out; /* Found one */ if (gang[i]->start >= bytenr) { @@ -4207,11 +4089,11 @@ out: return found; } -static int try_release_subpage_extent_buffer(struct page *page) +static int try_release_subpage_extent_buffer(struct folio *folio) { - struct btrfs_fs_info *fs_info = page_to_fs_info(page); - u64 cur = page_offset(page); - const u64 end = page_offset(page) + PAGE_SIZE; + struct btrfs_fs_info *fs_info = folio_to_fs_info(folio); + u64 cur = folio_pos(folio); + const u64 end = cur + PAGE_SIZE; int ret; while (cur < end) { @@ -4226,7 +4108,7 @@ static int try_release_subpage_extent_buffer(struct page *page) * with spinlock rather than RCU. */ spin_lock(&fs_info->buffer_lock); - eb = get_next_extent_buffer(fs_info, page, cur); + eb = get_next_extent_buffer(fs_info, folio, cur); if (!eb) { /* No more eb in the page range after or at cur */ spin_unlock(&fs_info->buffer_lock); @@ -4267,31 +4149,30 @@ static int try_release_subpage_extent_buffer(struct page *page) * Finally to check if we have cleared folio private, as if we have * released all ebs in the page, the folio private should be cleared now. */ - spin_lock(&page->mapping->i_private_lock); - if (!folio_test_private(page_folio(page))) + spin_lock(&folio->mapping->i_private_lock); + if (!folio_test_private(folio)) ret = 1; else ret = 0; - spin_unlock(&page->mapping->i_private_lock); + spin_unlock(&folio->mapping->i_private_lock); return ret; } -int try_release_extent_buffer(struct page *page) +int try_release_extent_buffer(struct folio *folio) { - struct folio *folio = page_folio(page); struct extent_buffer *eb; - if (page_to_fs_info(page)->nodesize < PAGE_SIZE) - return try_release_subpage_extent_buffer(page); + if (folio_to_fs_info(folio)->nodesize < PAGE_SIZE) + return try_release_subpage_extent_buffer(folio); /* * We need to make sure nobody is changing folio private, as we rely on * folio private as the pointer to extent buffer. */ - spin_lock(&page->mapping->i_private_lock); + spin_lock(&folio->mapping->i_private_lock); if (!folio_test_private(folio)) { - spin_unlock(&page->mapping->i_private_lock); + spin_unlock(&folio->mapping->i_private_lock); return 1; } @@ -4306,10 +4187,10 @@ int try_release_extent_buffer(struct page *page) spin_lock(&eb->refs_lock); if (atomic_read(&eb->refs) != 1 || extent_buffer_under_io(eb)) { spin_unlock(&eb->refs_lock); - spin_unlock(&page->mapping->i_private_lock); + spin_unlock(&folio->mapping->i_private_lock); return 0; } - spin_unlock(&page->mapping->i_private_lock); + spin_unlock(&folio->mapping->i_private_lock); /* * If tree ref isn't set then we know the ref on this eb is a real ref, diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index dceebd76c7d1..8a36117ed453 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -236,11 +236,11 @@ static inline void extent_changeset_free(struct extent_changeset *changeset) kfree(changeset); } -bool try_release_extent_mapping(struct page *page, gfp_t mask); -int try_release_extent_buffer(struct page *page); +bool try_release_extent_mapping(struct folio *folio, gfp_t mask); +int try_release_extent_buffer(struct folio *folio); int btrfs_read_folio(struct file *file, struct folio *folio); -void extent_write_locked_range(struct inode *inode, const struct page *locked_page, +void extent_write_locked_range(struct inode *inode, const struct folio *locked_folio, u64 start, u64 end, struct writeback_control *wbc, bool pages_dirty); int btrfs_writepages(struct address_space *mapping, struct writeback_control *wbc); @@ -249,7 +249,7 @@ int btree_write_cache_pages(struct address_space *mapping, void btrfs_readahead(struct readahead_control *rac); int set_folio_extent_mapped(struct folio *folio); int set_page_extent_mapped(struct page *page); -void clear_page_extent_mapped(struct page *page); +void clear_folio_extent_mapped(struct folio *folio); struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start, u64 owner_root, int level); @@ -354,7 +354,7 @@ void set_extent_buffer_dirty(struct extent_buffer *eb); void set_extent_buffer_uptodate(struct extent_buffer *eb); void clear_extent_buffer_uptodate(struct extent_buffer *eb); void extent_clear_unlock_delalloc(struct btrfs_inode *inode, u64 start, u64 end, - const struct page *locked_page, + const struct folio *locked_folio, struct extent_state **cached, u32 bits_to_clear, unsigned long page_ops); int extent_invalidate_folio(struct extent_io_tree *tree, @@ -368,7 +368,7 @@ int btrfs_alloc_folio_array(unsigned int nr_folios, struct folio **folio_array); #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS bool find_lock_delalloc_range(struct inode *inode, - struct page *locked_page, u64 *start, + struct folio *locked_folio, u64 *start, u64 *end); #endif struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info, diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 10ac5f657e38..25d191f1ac10 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -192,10 +192,13 @@ static inline u64 extent_map_block_len(const struct extent_map *em) static inline u64 extent_map_block_end(const struct extent_map *em) { - if (extent_map_block_start(em) + extent_map_block_len(em) < - extent_map_block_start(em)) + const u64 block_start = extent_map_block_start(em); + const u64 block_end = block_start + extent_map_block_len(em); + + if (block_end < block_start) return (u64)-1; - return extent_map_block_start(em) + extent_map_block_len(em); + + return block_end; } static bool can_merge_extent_map(const struct extent_map *em) diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 5c342fe1af61..886749b39672 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -151,7 +151,7 @@ static inline u32 max_ordered_sum_bytes(const struct btrfs_fs_info *fs_info) * Calculate the total size needed to allocate for an ordered sum structure * spanning @bytes in the file. */ -static int btrfs_ordered_sum_size(struct btrfs_fs_info *fs_info, unsigned long bytes) +static int btrfs_ordered_sum_size(const struct btrfs_fs_info *fs_info, unsigned long bytes) { return sizeof(struct btrfs_ordered_sum) + bytes_to_csum_size(fs_info, bytes); } @@ -1272,7 +1272,7 @@ out: void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode, const struct btrfs_path *path, - struct btrfs_file_extent_item *fi, + const struct btrfs_file_extent_item *fi, struct extent_map *em) { struct btrfs_fs_info *fs_info = inode->root->fs_info; diff --git a/fs/btrfs/file-item.h b/fs/btrfs/file-item.h index 557dc43d7142..0e13661a71f3 100644 --- a/fs/btrfs/file-item.h +++ b/fs/btrfs/file-item.h @@ -74,7 +74,7 @@ int btrfs_lookup_csums_bitmap(struct btrfs_root *root, struct btrfs_path *path, unsigned long *csum_bitmap); void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode, const struct btrfs_path *path, - struct btrfs_file_extent_item *fi, + const struct btrfs_file_extent_item *fi, struct extent_map *em); int btrfs_inode_clear_file_extent_range(struct btrfs_inode *inode, u64 start, u64 len); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 9914419f3b7d..c5e36f58eb07 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1603,7 +1603,6 @@ static inline bool skip_inode_logging(const struct btrfs_log_ctx *ctx) */ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) { - struct btrfs_file_private *private = file->private_data; struct dentry *dentry = file_dentry(file); struct btrfs_inode *inode = BTRFS_I(d_inode(dentry)); struct btrfs_root *root = inode->root; @@ -1613,7 +1612,13 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) int ret = 0, err; u64 len; bool full_sync; - const bool skip_ilock = (private ? private->fsync_skip_inode_lock : false); + bool skip_ilock = false; + + if (current->journal_info == BTRFS_TRANS_DIO_WRITE_STUB) { + skip_ilock = true; + current->journal_info = NULL; + btrfs_assert_inode_locked(inode); + } trace_btrfs_sync_file(file, datasync); @@ -1915,8 +1920,8 @@ static vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf) reserved_space = PAGE_SIZE; sb_start_pagefault(inode->i_sb); - page_start = page_offset(page); - page_end = page_start + PAGE_SIZE - 1; + page_start = folio_pos(folio); + page_end = page_start + folio_size(folio) - 1; end = page_end; /* @@ -1944,18 +1949,18 @@ static vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf) ret = VM_FAULT_NOPAGE; again: down_read(&BTRFS_I(inode)->i_mmap_lock); - lock_page(page); + folio_lock(folio); size = i_size_read(inode); - if ((page->mapping != inode->i_mapping) || + if ((folio->mapping != inode->i_mapping) || (page_start >= size)) { /* Page got truncated out from underneath us. */ goto out_unlock; } - wait_on_page_writeback(page); + folio_wait_writeback(folio); lock_extent(io_tree, page_start, page_end, &cached_state); - ret2 = set_page_extent_mapped(page); + ret2 = set_folio_extent_mapped(folio); if (ret2 < 0) { ret = vmf_error(ret2); unlock_extent(io_tree, page_start, page_end, &cached_state); @@ -1969,14 +1974,14 @@ again: ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), page_start, PAGE_SIZE); if (ordered) { unlock_extent(io_tree, page_start, page_end, &cached_state); - unlock_page(page); + folio_unlock(folio); up_read(&BTRFS_I(inode)->i_mmap_lock); btrfs_start_ordered_extent(ordered); btrfs_put_ordered_extent(ordered); goto again; } - if (page->index == ((size - 1) >> PAGE_SHIFT)) { + if (folio->index == ((size - 1) >> PAGE_SHIFT)) { reserved_space = round_up(size - page_start, fs_info->sectorsize); if (reserved_space < PAGE_SIZE) { end = page_start + reserved_space - 1; @@ -2006,13 +2011,13 @@ again: } /* Page is wholly or partially inside EOF. */ - if (page_start + PAGE_SIZE > size) - zero_start = offset_in_page(size); + if (page_start + folio_size(folio) > size) + zero_start = offset_in_folio(folio, size); else zero_start = PAGE_SIZE; if (zero_start != PAGE_SIZE) - memzero_page(page, zero_start, PAGE_SIZE - zero_start); + folio_zero_range(folio, zero_start, folio_size(folio) - zero_start); btrfs_folio_clear_checked(fs_info, folio, page_start, PAGE_SIZE); btrfs_folio_set_dirty(fs_info, folio, page_start, end + 1 - page_start); @@ -2029,7 +2034,7 @@ again: return VM_FAULT_LOCKED; out_unlock: - unlock_page(page); + folio_unlock(folio); up_read(&BTRFS_I(inode)->i_mmap_lock); out: btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE); diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h index 3d6d4b503220..79f64e383edd 100644 --- a/fs/btrfs/fs.h +++ b/fs/btrfs/fs.h @@ -703,8 +703,8 @@ struct btrfs_fs_info { * running. */ refcount_t scrub_workers_refcnt; + u32 sectors_per_page; struct workqueue_struct *scrub_workers; - struct btrfs_subpage_info *subpage_info; struct btrfs_discard_ctl discard_ctl; diff --git a/fs/btrfs/inode-item.c b/fs/btrfs/inode-item.c index 316756ff08ac..29572dfaf878 100644 --- a/fs/btrfs/inode-item.c +++ b/fs/btrfs/inode-item.c @@ -14,7 +14,7 @@ #include "extent-tree.h" #include "file-item.h" -struct btrfs_inode_ref *btrfs_find_name_in_backref(struct extent_buffer *leaf, +struct btrfs_inode_ref *btrfs_find_name_in_backref(const struct extent_buffer *leaf, int slot, const struct fscrypt_str *name) { @@ -42,7 +42,7 @@ struct btrfs_inode_ref *btrfs_find_name_in_backref(struct extent_buffer *leaf, } struct btrfs_inode_extref *btrfs_find_name_in_ext_backref( - struct extent_buffer *leaf, int slot, u64 ref_objectid, + const struct extent_buffer *leaf, int slot, u64 ref_objectid, const struct fscrypt_str *name) { struct btrfs_inode_extref *extref; @@ -423,9 +423,9 @@ int btrfs_lookup_inode(struct btrfs_trans_handle *trans, struct btrfs_root return ret; } -static inline void btrfs_trace_truncate(struct btrfs_inode *inode, - struct extent_buffer *leaf, - struct btrfs_file_extent_item *fi, +static inline void btrfs_trace_truncate(const struct btrfs_inode *inode, + const struct extent_buffer *leaf, + const struct btrfs_file_extent_item *fi, u64 offset, int extent_type, int slot) { if (!inode) diff --git a/fs/btrfs/inode-item.h b/fs/btrfs/inode-item.h index c4aded82709b..c11b97fdccc4 100644 --- a/fs/btrfs/inode-item.h +++ b/fs/btrfs/inode-item.h @@ -109,11 +109,11 @@ struct btrfs_inode_extref *btrfs_lookup_inode_extref( u64 inode_objectid, u64 ref_objectid, int ins_len, int cow); -struct btrfs_inode_ref *btrfs_find_name_in_backref(struct extent_buffer *leaf, +struct btrfs_inode_ref *btrfs_find_name_in_backref(const struct extent_buffer *leaf, int slot, const struct fscrypt_str *name); struct btrfs_inode_extref *btrfs_find_name_in_ext_backref( - struct extent_buffer *leaf, int slot, u64 ref_objectid, + const struct extent_buffer *leaf, int slot, u64 ref_objectid, const struct fscrypt_str *name); #endif diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index b1b6564ab68f..edac499fd83d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -116,7 +116,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr); static int btrfs_truncate(struct btrfs_inode *inode, bool skip_writeback); static noinline int run_delalloc_cow(struct btrfs_inode *inode, - struct page *locked_page, u64 start, + struct folio *locked_folio, u64 start, u64 end, struct writeback_control *wbc, bool pages_dirty); @@ -393,17 +393,17 @@ void btrfs_inode_unlock(struct btrfs_inode *inode, unsigned int ilock_flags) * extent (btrfs_finish_ordered_io()). */ static inline void btrfs_cleanup_ordered_extents(struct btrfs_inode *inode, - struct page *locked_page, + struct folio *locked_folio, u64 offset, u64 bytes) { unsigned long index = offset >> PAGE_SHIFT; unsigned long end_index = (offset + bytes - 1) >> PAGE_SHIFT; u64 page_start = 0, page_end = 0; - struct page *page; + struct folio *folio; - if (locked_page) { - page_start = page_offset(locked_page); - page_end = page_start + PAGE_SIZE - 1; + if (locked_folio) { + page_start = folio_pos(locked_folio); + page_end = page_start + folio_size(locked_folio) - 1; } while (index <= end_index) { @@ -417,13 +417,13 @@ static inline void btrfs_cleanup_ordered_extents(struct btrfs_inode *inode, * btrfs_mark_ordered_io_finished() would skip the accounting * for the page range, and the ordered extent will never finish. */ - if (locked_page && index == (page_start >> PAGE_SHIFT)) { + if (locked_folio && index == (page_start >> PAGE_SHIFT)) { index++; continue; } - page = find_get_page(inode->vfs_inode.i_mapping, index); + folio = __filemap_get_folio(inode->vfs_inode.i_mapping, index, 0, 0); index++; - if (!page) + if (IS_ERR(folio)) continue; /* @@ -431,14 +431,14 @@ static inline void btrfs_cleanup_ordered_extents(struct btrfs_inode *inode, * range, then btrfs_mark_ordered_io_finished() will handle * the ordered extent accounting for the range. */ - btrfs_folio_clamp_clear_ordered(inode->root->fs_info, - page_folio(page), offset, bytes); - put_page(page); + btrfs_folio_clamp_clear_ordered(inode->root->fs_info, folio, + offset, bytes); + folio_put(folio); } - if (locked_page) { + if (locked_folio) { /* The locked page covers the full range, nothing needs to be done */ - if (bytes + offset <= page_start + PAGE_SIZE) + if (bytes + offset <= page_start + folio_size(locked_folio)) return; /* * In case this page belongs to the delalloc range being @@ -447,8 +447,9 @@ static inline void btrfs_cleanup_ordered_extents(struct btrfs_inode *inode, * run_delalloc_range */ if (page_start >= offset && page_end <= (offset + bytes - 1)) { - bytes = offset + bytes - page_offset(locked_page) - PAGE_SIZE; - offset = page_offset(locked_page) + PAGE_SIZE; + bytes = offset + bytes - folio_pos(locked_folio) - + folio_size(locked_folio); + offset = folio_pos(locked_folio) + folio_size(locked_folio); } } @@ -494,7 +495,6 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans, { struct btrfs_root *root = inode->root; struct extent_buffer *leaf; - struct page *page = NULL; const u32 sectorsize = trans->fs_info->sectorsize; char *kaddr; unsigned long ptr; @@ -554,12 +554,16 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans, btrfs_set_file_extent_compression(leaf, ei, compress_type); } else { - page = find_get_page(inode->vfs_inode.i_mapping, 0); + struct folio *folio; + + folio = __filemap_get_folio(inode->vfs_inode.i_mapping, + 0, 0, 0); + ASSERT(!IS_ERR(folio)); btrfs_set_file_extent_compression(leaf, ei, 0); - kaddr = kmap_local_page(page); + kaddr = kmap_local_folio(folio, 0); write_extent_buffer(leaf, kaddr, ptr, size); kunmap_local(kaddr); - put_page(page); + folio_put(folio); } btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); @@ -715,7 +719,7 @@ out: } static noinline int cow_file_range_inline(struct btrfs_inode *inode, - struct page *locked_page, + struct folio *locked_folio, u64 offset, u64 end, size_t compressed_size, int compress_type, @@ -740,13 +744,26 @@ static noinline int cow_file_range_inline(struct btrfs_inode *inode, return ret; } + /* + * In the successful case (ret == 0 here), cow_file_range will return 1. + * + * Quite a bit further up the callstack in extent_writepage(), ret == 1 + * is treated as a short circuited success and does not unlock the folio, + * so we must do it here. + * + * In the failure case, the locked_folio does get unlocked by + * btrfs_folio_end_all_writers, which asserts that it is still locked + * at that point, so we must *not* unlock it here. + * + * The other two callsites in compress_file_range do not have a + * locked_folio, so they are not relevant to this logic. + */ if (ret == 0) - locked_page = NULL; + locked_folio = NULL; - extent_clear_unlock_delalloc(inode, offset, end, locked_page, &cached, - clear_flags, - PAGE_UNLOCK | PAGE_START_WRITEBACK | - PAGE_END_WRITEBACK); + extent_clear_unlock_delalloc(inode, offset, end, locked_folio, &cached, + clear_flags, PAGE_UNLOCK | + PAGE_START_WRITEBACK | PAGE_END_WRITEBACK); return ret; } @@ -762,7 +779,7 @@ struct async_extent { struct async_chunk { struct btrfs_inode *inode; - struct page *locked_page; + struct folio *locked_folio; u64 start; u64 end; blk_opf_t write_flags; @@ -868,25 +885,25 @@ static inline void inode_should_defrag(struct btrfs_inode *inode, /* If this is a small write inside eof, kick off a defrag */ if (num_bytes < small_write && (start > 0 || end + 1 < inode->disk_i_size)) - btrfs_add_inode_defrag(NULL, inode, small_write); + btrfs_add_inode_defrag(inode, small_write); } static int extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end) { unsigned long end_index = end >> PAGE_SHIFT; - struct page *page; + struct folio *folio; int ret = 0; for (unsigned long index = start >> PAGE_SHIFT; index <= end_index; index++) { - page = find_get_page(inode->i_mapping, index); - if (unlikely(!page)) { + folio = __filemap_get_folio(inode->i_mapping, index, 0, 0); + if (IS_ERR(folio)) { if (!ret) - ret = -ENOENT; + ret = PTR_ERR(folio); continue; } - clear_page_dirty_for_io(page); - put_page(page); + folio_clear_dirty_for_io(folio); + folio_put(folio); } return ret; } @@ -1122,7 +1139,7 @@ static void free_async_extent_pages(struct async_extent *async_extent) static void submit_uncompressed_range(struct btrfs_inode *inode, struct async_extent *async_extent, - struct page *locked_page) + struct folio *locked_folio) { u64 start = async_extent->start; u64 end = async_extent->start + async_extent->ram_size - 1; @@ -1135,20 +1152,22 @@ static void submit_uncompressed_range(struct btrfs_inode *inode, }; wbc_attach_fdatawrite_inode(&wbc, &inode->vfs_inode); - ret = run_delalloc_cow(inode, locked_page, start, end, &wbc, false); + ret = run_delalloc_cow(inode, locked_folio, start, end, + &wbc, false); wbc_detach_inode(&wbc); if (ret < 0) { - btrfs_cleanup_ordered_extents(inode, locked_page, start, end - start + 1); - if (locked_page) { - const u64 page_start = page_offset(locked_page); - - set_page_writeback(locked_page); - end_page_writeback(locked_page); - btrfs_mark_ordered_io_finished(inode, locked_page, + btrfs_cleanup_ordered_extents(inode, locked_folio, + start, end - start + 1); + if (locked_folio) { + const u64 page_start = folio_pos(locked_folio); + + folio_start_writeback(locked_folio); + folio_end_writeback(locked_folio); + btrfs_mark_ordered_io_finished(inode, locked_folio, page_start, PAGE_SIZE, !ret); - mapping_set_error(locked_page->mapping, ret); - unlock_page(locked_page); + mapping_set_error(locked_folio->mapping, ret); + folio_unlock(locked_folio); } } } @@ -1164,7 +1183,7 @@ static void submit_one_async_extent(struct async_chunk *async_chunk, struct btrfs_ordered_extent *ordered; struct btrfs_file_extent file_extent; struct btrfs_key ins; - struct page *locked_page = NULL; + struct folio *locked_folio = NULL; struct extent_state *cached = NULL; struct extent_map *em; int ret = 0; @@ -1175,19 +1194,20 @@ static void submit_one_async_extent(struct async_chunk *async_chunk, kthread_associate_blkcg(async_chunk->blkcg_css); /* - * If async_chunk->locked_page is in the async_extent range, we need to + * If async_chunk->locked_folio is in the async_extent range, we need to * handle it. */ - if (async_chunk->locked_page) { - u64 locked_page_start = page_offset(async_chunk->locked_page); - u64 locked_page_end = locked_page_start + PAGE_SIZE - 1; + if (async_chunk->locked_folio) { + u64 locked_folio_start = folio_pos(async_chunk->locked_folio); + u64 locked_folio_end = locked_folio_start + + folio_size(async_chunk->locked_folio) - 1; - if (!(start >= locked_page_end || end <= locked_page_start)) - locked_page = async_chunk->locked_page; + if (!(start >= locked_folio_end || end <= locked_folio_start)) + locked_folio = async_chunk->locked_folio; } if (async_extent->compress_type == BTRFS_COMPRESS_NONE) { - submit_uncompressed_range(inode, async_extent, locked_page); + submit_uncompressed_range(inode, async_extent, locked_folio); goto done; } @@ -1202,7 +1222,7 @@ static void submit_one_async_extent(struct async_chunk *async_chunk, * non-contiguous space for the uncompressed size instead. So * fall back to uncompressed. */ - submit_uncompressed_range(inode, async_extent, locked_page); + submit_uncompressed_range(inode, async_extent, locked_folio); goto done; } @@ -1306,21 +1326,21 @@ u64 btrfs_get_extent_allocation_hint(struct btrfs_inode *inode, u64 start, * allocate extents on disk for the range, and create ordered data structs * in ram to track those extents. * - * locked_page is the page that writepage had locked already. We use + * locked_folio is the folio that writepage had locked already. We use * it to make sure we don't do extra locks or unlocks. * - * When this function fails, it unlocks all pages except @locked_page. + * When this function fails, it unlocks all pages except @locked_folio. * * When this function successfully creates an inline extent, it returns 1 and - * unlocks all pages including locked_page and starts I/O on them. - * (In reality inline extents are limited to a single page, so locked_page is + * unlocks all pages including locked_folio and starts I/O on them. + * (In reality inline extents are limited to a single page, so locked_folio is * the only page handled anyway). * * When this function succeed and creates a normal extent, the page locking * status depends on the passed in flags: * * - If @keep_locked is set, all pages are kept locked. - * - Else all pages except for @locked_page are unlocked. + * - Else all pages except for @locked_folio are unlocked. * * When a failure happens in the second or later iteration of the * while-loop, the ordered extents created in previous iterations are kept @@ -1329,8 +1349,8 @@ u64 btrfs_get_extent_allocation_hint(struct btrfs_inode *inode, u64 start, * example. */ static noinline int cow_file_range(struct btrfs_inode *inode, - struct page *locked_page, u64 start, u64 end, - u64 *done_offset, + struct folio *locked_folio, u64 start, + u64 end, u64 *done_offset, bool keep_locked, bool no_inline) { struct btrfs_root *root = inode->root; @@ -1363,7 +1383,7 @@ static noinline int cow_file_range(struct btrfs_inode *inode, if (!no_inline) { /* lets try to make an inline extent */ - ret = cow_file_range_inline(inode, locked_page, start, end, 0, + ret = cow_file_range_inline(inode, locked_folio, start, end, 0, BTRFS_COMPRESS_NONE, NULL, false); if (ret <= 0) { /* @@ -1500,7 +1520,7 @@ static noinline int cow_file_range(struct btrfs_inode *inode, page_ops |= PAGE_SET_ORDERED; extent_clear_unlock_delalloc(inode, start, start + ram_size - 1, - locked_page, &cached, + locked_folio, &cached, EXTENT_LOCKED | EXTENT_DELALLOC, page_ops); if (num_bytes < cur_alloc_size) @@ -1553,13 +1573,13 @@ out_unlock: * function. * * However, in case of @keep_locked, we still need to unlock the pages - * (except @locked_page) to ensure all the pages are unlocked. + * (except @locked_folio) to ensure all the pages are unlocked. */ if (keep_locked && orig_start < start) { - if (!locked_page) + if (!locked_folio) mapping_set_error(inode->vfs_inode.i_mapping, ret); extent_clear_unlock_delalloc(inode, orig_start, start - 1, - locked_page, NULL, 0, page_ops); + locked_folio, NULL, 0, page_ops); } /* @@ -1582,8 +1602,7 @@ out_unlock: if (extent_reserved) { extent_clear_unlock_delalloc(inode, start, start + cur_alloc_size - 1, - locked_page, &cached, - clear_bits, + locked_folio, &cached, clear_bits, page_ops); btrfs_qgroup_free_data(inode, NULL, start, cur_alloc_size, NULL); start += cur_alloc_size; @@ -1597,7 +1616,7 @@ out_unlock: */ if (start < end) { clear_bits |= EXTENT_CLEAR_DATA_RESV; - extent_clear_unlock_delalloc(inode, start, end, locked_page, + extent_clear_unlock_delalloc(inode, start, end, locked_folio, &cached, clear_bits, page_ops); btrfs_qgroup_free_data(inode, NULL, start, cur_alloc_size, NULL); } @@ -1651,7 +1670,7 @@ static noinline void submit_compressed_extents(struct btrfs_work *work, bool do_ } static bool run_delalloc_compressed(struct btrfs_inode *inode, - struct page *locked_page, u64 start, + struct folio *locked_folio, u64 start, u64 end, struct writeback_control *wbc) { struct btrfs_fs_info *fs_info = inode->root->fs_info; @@ -1691,15 +1710,16 @@ static bool run_delalloc_compressed(struct btrfs_inode *inode, INIT_LIST_HEAD(&async_chunk[i].extents); /* - * The locked_page comes all the way from writepage and its - * the original page we were actually given. As we spread + * The locked_folio comes all the way from writepage and its + * the original folio we were actually given. As we spread * this large delalloc region across multiple async_chunk - * structs, only the first struct needs a pointer to locked_page + * structs, only the first struct needs a pointer to + * locked_folio. * * This way we don't need racey decisions about who is supposed * to unlock it. */ - if (locked_page) { + if (locked_folio) { /* * Depending on the compressibility, the pages might or * might not go through async. We want all of them to @@ -1709,12 +1729,12 @@ static bool run_delalloc_compressed(struct btrfs_inode *inode, * need full accuracy. Just account the whole thing * against the first page. */ - wbc_account_cgroup_owner(wbc, locked_page, + wbc_account_cgroup_owner(wbc, &locked_folio->page, cur_end - start); - async_chunk[i].locked_page = locked_page; - locked_page = NULL; + async_chunk[i].locked_folio = locked_folio; + locked_folio = NULL; } else { - async_chunk[i].locked_page = NULL; + async_chunk[i].locked_folio = NULL; } if (blkcg_css != blkcg_root_css) { @@ -1743,7 +1763,7 @@ static bool run_delalloc_compressed(struct btrfs_inode *inode, * covered by the range. */ static noinline int run_delalloc_cow(struct btrfs_inode *inode, - struct page *locked_page, u64 start, + struct folio *locked_folio, u64 start, u64 end, struct writeback_control *wbc, bool pages_dirty) { @@ -1751,20 +1771,21 @@ static noinline int run_delalloc_cow(struct btrfs_inode *inode, int ret; while (start <= end) { - ret = cow_file_range(inode, locked_page, start, end, &done_offset, - true, false); + ret = cow_file_range(inode, locked_folio, start, end, + &done_offset, true, false); if (ret) return ret; - extent_write_locked_range(&inode->vfs_inode, locked_page, start, - done_offset, wbc, pages_dirty); + extent_write_locked_range(&inode->vfs_inode, locked_folio, + start, done_offset, wbc, pages_dirty); start = done_offset + 1; } return 1; } -static int fallback_to_cow(struct btrfs_inode *inode, struct page *locked_page, - const u64 start, const u64 end) +static int fallback_to_cow(struct btrfs_inode *inode, + struct folio *locked_folio, const u64 start, + const u64 end) { const bool is_space_ino = btrfs_is_free_space_inode(inode); const bool is_reloc_ino = btrfs_is_data_reloc_root(inode->root); @@ -1833,7 +1854,8 @@ static int fallback_to_cow(struct btrfs_inode *inode, struct page *locked_page, * is written out and unlocked directly and a normal NOCOW extent * doesn't work. */ - ret = cow_file_range(inode, locked_page, start, end, NULL, false, true); + ret = cow_file_range(inode, locked_folio, start, end, NULL, false, + true); ASSERT(ret != 1); return ret; } @@ -1987,7 +2009,7 @@ static int can_nocow_file_extent(struct btrfs_path *path, * blocks on disk */ static noinline int run_delalloc_nocow(struct btrfs_inode *inode, - struct page *locked_page, + struct folio *locked_folio, const u64 start, const u64 end) { struct btrfs_fs_info *fs_info = inode->root->fs_info; @@ -2150,8 +2172,8 @@ must_cow: * NOCOW, following one which needs to be COW'ed */ if (cow_start != (u64)-1) { - ret = fallback_to_cow(inode, locked_page, - cow_start, found_key.offset - 1); + ret = fallback_to_cow(inode, locked_folio, cow_start, + found_key.offset - 1); cow_start = (u64)-1; if (ret) { btrfs_dec_nocow_writers(nocow_bg); @@ -2206,7 +2228,7 @@ must_cow: btrfs_put_ordered_extent(ordered); extent_clear_unlock_delalloc(inode, cur_offset, nocow_end, - locked_page, &cached_state, + locked_folio, &cached_state, EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_CLEAR_DATA_RESV, PAGE_UNLOCK | PAGE_SET_ORDERED); @@ -2228,7 +2250,7 @@ must_cow: if (cow_start != (u64)-1) { cur_offset = end; - ret = fallback_to_cow(inode, locked_page, cow_start, end); + ret = fallback_to_cow(inode, locked_folio, cow_start, end); cow_start = (u64)-1; if (ret) goto error; @@ -2255,7 +2277,7 @@ error: lock_extent(&inode->io_tree, cur_offset, end, &cached); extent_clear_unlock_delalloc(inode, cur_offset, end, - locked_page, &cached, + locked_folio, &cached, EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING, PAGE_UNLOCK | @@ -2282,39 +2304,39 @@ static bool should_nocow(struct btrfs_inode *inode, u64 start, u64 end) * Function to process delayed allocation (create CoW) for ranges which are * being touched for the first time. */ -int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page, +int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct folio *locked_folio, u64 start, u64 end, struct writeback_control *wbc) { const bool zoned = btrfs_is_zoned(inode->root->fs_info); int ret; /* - * The range must cover part of the @locked_page, or a return of 1 + * The range must cover part of the @locked_folio, or a return of 1 * can confuse the caller. */ - ASSERT(!(end <= page_offset(locked_page) || - start >= page_offset(locked_page) + PAGE_SIZE)); + ASSERT(!(end <= folio_pos(locked_folio) || + start >= folio_pos(locked_folio) + folio_size(locked_folio))); if (should_nocow(inode, start, end)) { - ret = run_delalloc_nocow(inode, locked_page, start, end); + ret = run_delalloc_nocow(inode, locked_folio, start, end); goto out; } if (btrfs_inode_can_compress(inode) && inode_need_compress(inode, start, end) && - run_delalloc_compressed(inode, locked_page, start, end, wbc)) + run_delalloc_compressed(inode, locked_folio, start, end, wbc)) return 1; if (zoned) - ret = run_delalloc_cow(inode, locked_page, start, end, wbc, + ret = run_delalloc_cow(inode, locked_folio, start, end, wbc, true); else - ret = cow_file_range(inode, locked_page, start, end, NULL, + ret = cow_file_range(inode, locked_folio, start, end, NULL, false, false); out: if (ret < 0) - btrfs_cleanup_ordered_extents(inode, locked_page, start, + btrfs_cleanup_ordered_extents(inode, locked_folio, start, end - start + 1); return ret; } @@ -2690,7 +2712,7 @@ int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end, /* see btrfs_writepage_start_hook for details on why this is required */ struct btrfs_writepage_fixup { - struct page *page; + struct folio *folio; struct btrfs_inode *inode; struct btrfs_work work; }; @@ -2702,50 +2724,51 @@ static void btrfs_writepage_fixup_worker(struct btrfs_work *work) struct btrfs_ordered_extent *ordered; struct extent_state *cached_state = NULL; struct extent_changeset *data_reserved = NULL; - struct page *page = fixup->page; + struct folio *folio = fixup->folio; struct btrfs_inode *inode = fixup->inode; struct btrfs_fs_info *fs_info = inode->root->fs_info; - u64 page_start = page_offset(page); - u64 page_end = page_offset(page) + PAGE_SIZE - 1; + u64 page_start = folio_pos(folio); + u64 page_end = folio_pos(folio) + folio_size(folio) - 1; int ret = 0; bool free_delalloc_space = true; /* * This is similar to page_mkwrite, we need to reserve the space before - * we take the page lock. + * we take the folio lock. */ ret = btrfs_delalloc_reserve_space(inode, &data_reserved, page_start, - PAGE_SIZE); + folio_size(folio)); again: - lock_page(page); + folio_lock(folio); /* - * Before we queued this fixup, we took a reference on the page. - * page->mapping may go NULL, but it shouldn't be moved to a different + * Before we queued this fixup, we took a reference on the folio. + * folio->mapping may go NULL, but it shouldn't be moved to a different * address space. */ - if (!page->mapping || !PageDirty(page) || !PageChecked(page)) { + if (!folio->mapping || !folio_test_dirty(folio) || + !folio_test_checked(folio)) { /* * Unfortunately this is a little tricky, either * - * 1) We got here and our page had already been dealt with and + * 1) We got here and our folio had already been dealt with and * we reserved our space, thus ret == 0, so we need to just * drop our space reservation and bail. This can happen the * first time we come into the fixup worker, or could happen * while waiting for the ordered extent. - * 2) Our page was already dealt with, but we happened to get an + * 2) Our folio was already dealt with, but we happened to get an * ENOSPC above from the btrfs_delalloc_reserve_space. In * this case we obviously don't have anything to release, but - * because the page was already dealt with we don't want to - * mark the page with an error, so make sure we're resetting + * because the folio was already dealt with we don't want to + * mark the folio with an error, so make sure we're resetting * ret to 0. This is why we have this check _before_ the ret * check, because we do not want to have a surprise ENOSPC - * when the page was already properly dealt with. + * when the folio was already properly dealt with. */ if (!ret) { - btrfs_delalloc_release_extents(inode, PAGE_SIZE); + btrfs_delalloc_release_extents(inode, folio_size(folio)); btrfs_delalloc_release_space(inode, data_reserved, - page_start, PAGE_SIZE, + page_start, folio_size(folio), true); } ret = 0; @@ -2753,7 +2776,7 @@ again: } /* - * We can't mess with the page state unless it is locked, so now that + * We can't mess with the folio state unless it is locked, so now that * it is locked bail if we failed to make our space reservation. */ if (ret) @@ -2762,14 +2785,14 @@ again: lock_extent(&inode->io_tree, page_start, page_end, &cached_state); /* already ordered? We're done */ - if (PageOrdered(page)) + if (folio_test_ordered(folio)) goto out_reserved; ordered = btrfs_lookup_ordered_range(inode, page_start, PAGE_SIZE); if (ordered) { unlock_extent(&inode->io_tree, page_start, page_end, &cached_state); - unlock_page(page); + folio_unlock(folio); btrfs_start_ordered_extent(ordered); btrfs_put_ordered_extent(ordered); goto again; @@ -2787,7 +2810,7 @@ again: * * The page was dirty when we started, nothing should have cleaned it. */ - BUG_ON(!PageDirty(page)); + BUG_ON(!folio_test_dirty(folio)); free_delalloc_space = false; out_reserved: btrfs_delalloc_release_extents(inode, PAGE_SIZE); @@ -2801,14 +2824,14 @@ out_page: * We hit ENOSPC or other errors. Update the mapping and page * to reflect the errors and clean the page. */ - mapping_set_error(page->mapping, ret); - btrfs_mark_ordered_io_finished(inode, page, page_start, - PAGE_SIZE, !ret); - clear_page_dirty_for_io(page); - } - btrfs_folio_clear_checked(fs_info, page_folio(page), page_start, PAGE_SIZE); - unlock_page(page); - put_page(page); + mapping_set_error(folio->mapping, ret); + btrfs_mark_ordered_io_finished(inode, folio, page_start, + folio_size(folio), !ret); + folio_clear_dirty_for_io(folio); + } + btrfs_folio_clear_checked(fs_info, folio, page_start, PAGE_SIZE); + folio_unlock(folio); + folio_put(folio); kfree(fixup); extent_changeset_free(data_reserved); /* @@ -2821,33 +2844,34 @@ out_page: /* * There are a few paths in the higher layers of the kernel that directly - * set the page dirty bit without asking the filesystem if it is a + * set the folio dirty bit without asking the filesystem if it is a * good idea. This causes problems because we want to make sure COW * properly happens and the data=ordered rules are followed. * * In our case any range that doesn't have the ORDERED bit set * hasn't been properly setup for IO. We kick off an async process * to fix it up. The async helper will wait for ordered extents, set - * the delalloc bit and make it safe to write the page. + * the delalloc bit and make it safe to write the folio. */ -int btrfs_writepage_cow_fixup(struct page *page) +int btrfs_writepage_cow_fixup(struct folio *folio) { - struct inode *inode = page->mapping->host; + struct inode *inode = folio->mapping->host; struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_writepage_fixup *fixup; - /* This page has ordered extent covering it already */ - if (PageOrdered(page)) + /* This folio has ordered extent covering it already */ + if (folio_test_ordered(folio)) return 0; /* - * PageChecked is set below when we create a fixup worker for this page, - * don't try to create another one if we're already PageChecked() + * folio_checked is set below when we create a fixup worker for this + * folio, don't try to create another one if we're already + * folio_test_checked. * - * The extent_io writepage code will redirty the page if we send back + * The extent_io writepage code will redirty the foio if we send back * EAGAIN. */ - if (PageChecked(page)) + if (folio_test_checked(folio)) return -EAGAIN; fixup = kzalloc(sizeof(*fixup), GFP_NOFS); @@ -2857,14 +2881,14 @@ int btrfs_writepage_cow_fixup(struct page *page) /* * We are already holding a reference to this inode from * write_cache_pages. We need to hold it because the space reservation - * takes place outside of the page lock, and we can't trust - * page->mapping outside of the page lock. + * takes place outside of the folio lock, and we can't trust + * page->mapping outside of the folio lock. */ ihold(inode); - btrfs_folio_set_checked(fs_info, page_folio(page), page_offset(page), PAGE_SIZE); - get_page(page); + btrfs_folio_set_checked(fs_info, folio, folio_pos(folio), folio_size(folio)); + folio_get(folio); btrfs_init_work(&fixup->work, btrfs_writepage_fixup_worker, NULL); - fixup->page = page; + fixup->folio = folio; fixup->inode = BTRFS_I(inode); btrfs_queue_work(fs_info->fixup_workers, &fixup->work); @@ -6700,7 +6724,7 @@ static int btrfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, } static noinline int uncompress_inline(struct btrfs_path *path, - struct page *page, + struct folio *folio, struct btrfs_file_extent_item *item) { int ret; @@ -6722,7 +6746,8 @@ static noinline int uncompress_inline(struct btrfs_path *path, read_extent_buffer(leaf, tmp, ptr, inline_size); max_size = min_t(unsigned long, PAGE_SIZE, max_size); - ret = btrfs_decompress(compress_type, tmp, page, 0, inline_size, max_size); + ret = btrfs_decompress(compress_type, tmp, folio, 0, inline_size, + max_size); /* * decompression code contains a memset to fill in any space between the end @@ -6733,36 +6758,36 @@ static noinline int uncompress_inline(struct btrfs_path *path, */ if (max_size < PAGE_SIZE) - memzero_page(page, max_size, PAGE_SIZE - max_size); + folio_zero_range(folio, max_size, PAGE_SIZE - max_size); kfree(tmp); return ret; } static int read_inline_extent(struct btrfs_inode *inode, struct btrfs_path *path, - struct page *page) + struct folio *folio) { struct btrfs_file_extent_item *fi; void *kaddr; size_t copy_size; - if (!page || PageUptodate(page)) + if (!folio || folio_test_uptodate(folio)) return 0; - ASSERT(page_offset(page) == 0); + ASSERT(folio_pos(folio) == 0); fi = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_file_extent_item); if (btrfs_file_extent_compression(path->nodes[0], fi) != BTRFS_COMPRESS_NONE) - return uncompress_inline(path, page, fi); + return uncompress_inline(path, folio, fi); copy_size = min_t(u64, PAGE_SIZE, btrfs_file_extent_ram_bytes(path->nodes[0], fi)); - kaddr = kmap_local_page(page); + kaddr = kmap_local_folio(folio, 0); read_extent_buffer(path->nodes[0], kaddr, btrfs_file_extent_inline_start(fi), copy_size); kunmap_local(kaddr); if (copy_size < PAGE_SIZE) - memzero_page(page, copy_size, PAGE_SIZE - copy_size); + folio_zero_range(folio, copy_size, PAGE_SIZE - copy_size); return 0; } @@ -6784,7 +6809,7 @@ static int read_inline_extent(struct btrfs_inode *inode, struct btrfs_path *path * Return: ERR_PTR on error, non-NULL extent_map on success. */ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode, - struct page *page, u64 start, u64 len) + struct folio *folio, u64 start, u64 len) { struct btrfs_fs_info *fs_info = inode->root->fs_info; int ret = 0; @@ -6807,7 +6832,7 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode, if (em) { if (em->start > start || em->start + em->len <= start) free_extent_map(em); - else if (em->disk_bytenr == EXTENT_MAP_INLINE && page) + else if (em->disk_bytenr == EXTENT_MAP_INLINE && folio) free_extent_map(em); else goto out; @@ -6937,7 +6962,7 @@ next: ASSERT(em->disk_bytenr == EXTENT_MAP_INLINE); ASSERT(em->len == fs_info->sectorsize); - ret = read_inline_extent(inode, path, page); + ret = read_inline_extent(inode, path, folio); if (ret < 0) goto out; goto insert; @@ -7179,13 +7204,12 @@ struct extent_map *btrfs_create_io_em(struct btrfs_inode *inode, u64 start, * for subpage spinlock. So this function is to spin and wait for subpage * spinlock. */ -static void wait_subpage_spinlock(struct page *page) +static void wait_subpage_spinlock(struct folio *folio) { - struct btrfs_fs_info *fs_info = page_to_fs_info(page); - struct folio *folio = page_folio(page); + struct btrfs_fs_info *fs_info = folio_to_fs_info(folio); struct btrfs_subpage *subpage; - if (!btrfs_is_subpage(fs_info, page->mapping)) + if (!btrfs_is_subpage(fs_info, folio->mapping)) return; ASSERT(folio_test_private(folio) && folio_get_private(folio)); @@ -7214,9 +7238,9 @@ static int btrfs_launder_folio(struct folio *folio) static bool __btrfs_release_folio(struct folio *folio, gfp_t gfp_flags) { - if (try_release_extent_mapping(&folio->page, gfp_flags)) { - wait_subpage_spinlock(&folio->page); - clear_page_extent_mapped(&folio->page); + if (try_release_extent_mapping(folio, gfp_flags)) { + wait_subpage_spinlock(folio); + clear_folio_extent_mapped(folio); return true; } return false; @@ -7276,7 +7300,7 @@ static void btrfs_invalidate_folio(struct folio *folio, size_t offset, * do double ordered extent accounting on the same folio. */ folio_wait_writeback(folio); - wait_subpage_spinlock(&folio->page); + wait_subpage_spinlock(folio); /* * For subpage case, we have call sites like @@ -7414,7 +7438,7 @@ next: btrfs_folio_clear_checked(fs_info, folio, folio_pos(folio), folio_size(folio)); if (!inode_evicting) __btrfs_release_folio(folio, GFP_NOFS); - clear_page_extent_mapped(&folio->page); + clear_folio_extent_mapped(folio); } static int btrfs_truncate(struct btrfs_inode *inode, bool skip_writeback) @@ -8951,19 +8975,19 @@ void btrfs_set_range_writeback(struct btrfs_inode *inode, u64 start, u64 end) struct btrfs_fs_info *fs_info = inode->root->fs_info; unsigned long index = start >> PAGE_SHIFT; unsigned long end_index = end >> PAGE_SHIFT; - struct page *page; + struct folio *folio; u32 len; ASSERT(end + 1 - start <= U32_MAX); len = end + 1 - start; while (index <= end_index) { - page = find_get_page(inode->vfs_inode.i_mapping, index); - ASSERT(page); /* Pages should be in the extent_io_tree */ + folio = __filemap_get_folio(inode->vfs_inode.i_mapping, index, 0, 0); + ASSERT(!IS_ERR(folio)); /* folios should be in the extent_io_tree */ /* This is for data, which doesn't yet support larger folio. */ - ASSERT(folio_order(page_folio(page)) == 0); - btrfs_folio_set_writeback(fs_info, page_folio(page), start, len); - put_page(page); + ASSERT(folio_order(folio) == 0); + btrfs_folio_set_writeback(fs_info, folio, start, len); + folio_put(folio); index++; } } @@ -9128,7 +9152,7 @@ int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode, if (bio_add_page(&bbio->bio, pages[i], bytes, 0) < bytes) { atomic_inc(&priv.pending); - btrfs_submit_bio(bbio, 0); + btrfs_submit_bbio(bbio, 0); bbio = btrfs_bio_alloc(BIO_MAX_VECS, REQ_OP_READ, fs_info, btrfs_encoded_read_endio, &priv); @@ -9143,7 +9167,7 @@ int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode, } while (disk_io_size); atomic_inc(&priv.pending); - btrfs_submit_bio(bbio, 0); + btrfs_submit_bbio(bbio, 0); if (atomic_dec_return(&priv.pending)) io_wait_event(priv.wait, !atomic_read(&priv.pending)); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index e0a664b8a46a..8537eb9b5531 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -543,13 +543,11 @@ static noinline int btrfs_ioctl_fitrim(struct btrfs_fs_info *fs_info, range.minlen = max(range.minlen, minlen); ret = btrfs_trim_fs(fs_info, &range); - if (ret < 0) - return ret; if (copy_to_user(arg, &range, sizeof(range))) return -EFAULT; - return 0; + return ret; } int __pure btrfs_is_empty_uuid(const u8 *uuid) @@ -4765,11 +4763,10 @@ long btrfs_ioctl(struct file *file, unsigned int return ret; ret = btrfs_sync_fs(inode->i_sb, 1); /* - * The transaction thread may want to do more work, - * namely it pokes the cleaner kthread that will start - * processing uncleaned subvols. + * There may be work for the cleaner kthread to do (subvolume + * deletion, delayed iputs, defrag inodes, etc), so wake it up. */ - wake_up_process(fs_info->transaction_kthread); + wake_up_process(fs_info->cleaner_kthread); return ret; } case BTRFS_IOC_START_SYNC: diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c index 1e2a68b8f62d..72856f6775f7 100644 --- a/fs/btrfs/lzo.c +++ b/fs/btrfs/lzo.c @@ -438,11 +438,11 @@ int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb) } int lzo_decompress(struct list_head *ws, const u8 *data_in, - struct page *dest_page, unsigned long dest_pgoff, size_t srclen, + struct folio *dest_folio, unsigned long dest_pgoff, size_t srclen, size_t destlen) { struct workspace *workspace = list_entry(ws, struct workspace, list); - struct btrfs_fs_info *fs_info = page_to_fs_info(dest_page); + struct btrfs_fs_info *fs_info = folio_to_fs_info(dest_folio); const u32 sectorsize = fs_info->sectorsize; size_t in_len; size_t out_len; @@ -467,22 +467,22 @@ int lzo_decompress(struct list_head *ws, const u8 *data_in, out_len = sectorsize; ret = lzo1x_decompress_safe(data_in, in_len, workspace->buf, &out_len); if (unlikely(ret != LZO_E_OK)) { - struct btrfs_inode *inode = BTRFS_I(dest_page->mapping->host); + struct btrfs_inode *inode = folio_to_inode(dest_folio); btrfs_err(fs_info, "lzo decompression failed, error %d root %llu inode %llu offset %llu", ret, btrfs_root_id(inode->root), btrfs_ino(inode), - page_offset(dest_page)); + folio_pos(dest_folio)); ret = -EIO; goto out; } ASSERT(out_len <= sectorsize); - memcpy_to_page(dest_page, dest_pgoff, workspace->buf, out_len); + memcpy_to_folio(dest_folio, dest_pgoff, workspace->buf, out_len); /* Early end, considered as an error. */ if (unlikely(out_len < destlen)) { ret = -EIO; - memzero_page(dest_page, dest_pgoff + out_len, destlen - out_len); + folio_zero_range(dest_folio, dest_pgoff + out_len, destlen - out_len); } out: return ret; diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 82a68394a89c..2104d60c2161 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -332,7 +332,7 @@ static void finish_ordered_fn(struct btrfs_work *work) } static bool can_finish_ordered_extent(struct btrfs_ordered_extent *ordered, - struct page *page, u64 file_offset, + struct folio *folio, u64 file_offset, u64 len, bool uptodate) { struct btrfs_inode *inode = ordered->inode; @@ -340,10 +340,10 @@ static bool can_finish_ordered_extent(struct btrfs_ordered_extent *ordered, lockdep_assert_held(&inode->ordered_tree_lock); - if (page) { - ASSERT(page->mapping); - ASSERT(page_offset(page) <= file_offset); - ASSERT(file_offset + len <= page_offset(page) + PAGE_SIZE); + if (folio) { + ASSERT(folio->mapping); + ASSERT(folio_pos(folio) <= file_offset); + ASSERT(file_offset + len <= folio_pos(folio) + folio_size(folio)); /* * Ordered (Private2) bit indicates whether we still have @@ -351,10 +351,9 @@ static bool can_finish_ordered_extent(struct btrfs_ordered_extent *ordered, * * If there's no such bit, we need to skip to next range. */ - if (!btrfs_folio_test_ordered(fs_info, page_folio(page), - file_offset, len)) + if (!btrfs_folio_test_ordered(fs_info, folio, file_offset, len)) return false; - btrfs_folio_clear_ordered(fs_info, page_folio(page), file_offset, len); + btrfs_folio_clear_ordered(fs_info, folio, file_offset, len); } /* Now we're fine to update the accounting. */ @@ -398,7 +397,7 @@ static void btrfs_queue_ordered_fn(struct btrfs_ordered_extent *ordered) } void btrfs_finish_ordered_extent(struct btrfs_ordered_extent *ordered, - struct page *page, u64 file_offset, u64 len, + struct folio *folio, u64 file_offset, u64 len, bool uptodate) { struct btrfs_inode *inode = ordered->inode; @@ -408,7 +407,8 @@ void btrfs_finish_ordered_extent(struct btrfs_ordered_extent *ordered, trace_btrfs_finish_ordered_extent(inode, file_offset, len, uptodate); spin_lock_irqsave(&inode->ordered_tree_lock, flags); - ret = can_finish_ordered_extent(ordered, page, file_offset, len, uptodate); + ret = can_finish_ordered_extent(ordered, folio, file_offset, len, + uptodate); spin_unlock_irqrestore(&inode->ordered_tree_lock, flags); /* @@ -449,8 +449,8 @@ void btrfs_finish_ordered_extent(struct btrfs_ordered_extent *ordered, /* * Mark all ordered extents io inside the specified range finished. * - * @page: The involved page for the operation. - * For uncompressed buffered IO, the page status also needs to be + * @folio: The involved folio for the operation. + * For uncompressed buffered IO, the folio status also needs to be * updated to indicate whether the pending ordered io is finished. * Can be NULL for direct IO and compressed write. * For these cases, callers are ensured they won't execute the @@ -460,7 +460,7 @@ void btrfs_finish_ordered_extent(struct btrfs_ordered_extent *ordered, * extent(s) covering it. */ void btrfs_mark_ordered_io_finished(struct btrfs_inode *inode, - struct page *page, u64 file_offset, + struct folio *folio, u64 file_offset, u64 num_bytes, bool uptodate) { struct rb_node *node; @@ -524,7 +524,7 @@ void btrfs_mark_ordered_io_finished(struct btrfs_inode *inode, ASSERT(end + 1 - cur < U32_MAX); len = end + 1 - cur; - if (can_finish_ordered_extent(entry, page, cur, len, uptodate)) { + if (can_finish_ordered_extent(entry, folio, cur, len, uptodate)) { spin_unlock_irqrestore(&inode->ordered_tree_lock, flags); btrfs_queue_ordered_fn(entry); spin_lock_irqsave(&inode->ordered_tree_lock, flags); @@ -1015,7 +1015,7 @@ void btrfs_get_ordered_extents_for_logging(struct btrfs_inode *inode, { struct rb_node *n; - ASSERT(inode_is_locked(&inode->vfs_inode)); + btrfs_assert_inode_locked(inode); spin_lock_irq(&inode->ordered_tree_lock); for (n = rb_first(&inode->ordered_tree); n; n = rb_next(n)) { diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h index 51b9e81726e2..4e152736d06c 100644 --- a/fs/btrfs/ordered-data.h +++ b/fs/btrfs/ordered-data.h @@ -163,11 +163,11 @@ void btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry); void btrfs_remove_ordered_extent(struct btrfs_inode *btrfs_inode, struct btrfs_ordered_extent *entry); void btrfs_finish_ordered_extent(struct btrfs_ordered_extent *ordered, - struct page *page, u64 file_offset, u64 len, + struct folio *folio, u64 file_offset, u64 len, bool uptodate); void btrfs_mark_ordered_io_finished(struct btrfs_inode *inode, - struct page *page, u64 file_offset, - u64 num_bytes, bool uptodate); + struct folio *folio, u64 file_offset, + u64 num_bytes, bool uptodate); bool btrfs_dec_test_ordered_pending(struct btrfs_inode *inode, struct btrfs_ordered_extent **cached, u64 file_offset, u64 io_size); diff --git a/fs/btrfs/orphan.c b/fs/btrfs/orphan.c index 6195a2215b8f..9f3ad124104f 100644 --- a/fs/btrfs/orphan.c +++ b/fs/btrfs/orphan.c @@ -9,9 +9,8 @@ int btrfs_insert_orphan_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 offset) { - struct btrfs_path *path; + BTRFS_PATH_AUTO_FREE(path); struct btrfs_key key; - int ret = 0; key.objectid = BTRFS_ORPHAN_OBJECTID; key.type = BTRFS_ORPHAN_ITEM_KEY; @@ -21,16 +20,13 @@ int btrfs_insert_orphan_item(struct btrfs_trans_handle *trans, if (!path) return -ENOMEM; - ret = btrfs_insert_empty_item(trans, root, path, &key, 0); - - btrfs_free_path(path); - return ret; + return btrfs_insert_empty_item(trans, root, path, &key, 0); } int btrfs_del_orphan_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 offset) { - struct btrfs_path *path; + BTRFS_PATH_AUTO_FREE(path); struct btrfs_key key; int ret = 0; @@ -44,15 +40,9 @@ int btrfs_del_orphan_item(struct btrfs_trans_handle *trans, ret = btrfs_search_slot(trans, root, &key, path, -1, 1); if (ret < 0) - goto out; - if (ret) { /* JDM: Really? */ - ret = -ENOENT; - goto out; - } - - ret = btrfs_del_item(trans, root, path); + return ret; + if (ret) + return -ENOENT; -out: - btrfs_free_path(path); - return ret; + return btrfs_del_item(trans, root, path); } diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 7d6f5d9420ec..c297909f1506 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1998,16 +1998,14 @@ out: * * Return 0 for success insert * Return >0 for existing record, caller can free @record safely. - * Error is not possible + * Return <0 for insertion failure, caller can free @record safely. */ int btrfs_qgroup_trace_extent_nolock(struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_root *delayed_refs, struct btrfs_qgroup_extent_record *record) { - struct rb_node **p = &delayed_refs->dirty_extent_root.rb_node; - struct rb_node *parent_node = NULL; - struct btrfs_qgroup_extent_record *entry; - u64 bytenr = record->bytenr; + struct btrfs_qgroup_extent_record *existing, *ret; + unsigned long bytenr = record->bytenr; if (!btrfs_qgroup_full_accounting(fs_info)) return 1; @@ -2015,26 +2013,24 @@ int btrfs_qgroup_trace_extent_nolock(struct btrfs_fs_info *fs_info, lockdep_assert_held(&delayed_refs->lock); trace_btrfs_qgroup_trace_extent(fs_info, record); - while (*p) { - parent_node = *p; - entry = rb_entry(parent_node, struct btrfs_qgroup_extent_record, - node); - if (bytenr < entry->bytenr) { - p = &(*p)->rb_left; - } else if (bytenr > entry->bytenr) { - p = &(*p)->rb_right; - } else { - if (record->data_rsv && !entry->data_rsv) { - entry->data_rsv = record->data_rsv; - entry->data_rsv_refroot = - record->data_rsv_refroot; - } - return 1; + xa_lock(&delayed_refs->dirty_extents); + existing = xa_load(&delayed_refs->dirty_extents, bytenr); + if (existing) { + if (record->data_rsv && !existing->data_rsv) { + existing->data_rsv = record->data_rsv; + existing->data_rsv_refroot = record->data_rsv_refroot; } + xa_unlock(&delayed_refs->dirty_extents); + return 1; + } + + ret = __xa_store(&delayed_refs->dirty_extents, record->bytenr, record, GFP_ATOMIC); + xa_unlock(&delayed_refs->dirty_extents); + if (xa_is_err(ret)) { + qgroup_mark_inconsistent(fs_info); + return xa_err(ret); } - rb_link_node(&record->node, parent_node, p); - rb_insert_color(&record->node, &delayed_refs->dirty_extent_root); return 0; } @@ -2141,6 +2137,11 @@ int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans, u64 bytenr, if (!record) return -ENOMEM; + if (xa_reserve(&trans->transaction->delayed_refs.dirty_extents, bytenr, GFP_NOFS)) { + kfree(record); + return -ENOMEM; + } + delayed_refs = &trans->transaction->delayed_refs; record->bytenr = bytenr; record->num_bytes = num_bytes; @@ -2149,7 +2150,9 @@ int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans, u64 bytenr, spin_lock(&delayed_refs->lock); ret = btrfs_qgroup_trace_extent_nolock(fs_info, delayed_refs, record); spin_unlock(&delayed_refs->lock); - if (ret > 0) { + if (ret) { + /* Clean up if insertion fails or item exists. */ + xa_release(&delayed_refs->dirty_extents, record->bytenr); kfree(record); return 0; } @@ -3018,7 +3021,7 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans) struct btrfs_qgroup_extent_record *record; struct btrfs_delayed_ref_root *delayed_refs; struct ulist *new_roots = NULL; - struct rb_node *node; + unsigned long index; u64 num_dirty_extents = 0; u64 qgroup_to_skip; int ret = 0; @@ -3028,10 +3031,7 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans) delayed_refs = &trans->transaction->delayed_refs; qgroup_to_skip = delayed_refs->qgroup_to_skip; - while ((node = rb_first(&delayed_refs->dirty_extent_root))) { - record = rb_entry(node, struct btrfs_qgroup_extent_record, - node); - + xa_for_each(&delayed_refs->dirty_extents, index, record) { num_dirty_extents++; trace_btrfs_qgroup_account_extents(fs_info, record); @@ -3097,7 +3097,7 @@ cleanup: ulist_free(record->old_roots); ulist_free(new_roots); new_roots = NULL; - rb_erase(node, &delayed_refs->dirty_extent_root); + xa_erase(&delayed_refs->dirty_extents, index); kfree(record); } @@ -4346,10 +4346,9 @@ static int __btrfs_qgroup_release_data(struct btrfs_inode *inode, int ret; if (btrfs_qgroup_mode(inode->root->fs_info) == BTRFS_QGROUP_MODE_DISABLED) { - extent_changeset_init(&changeset); return clear_record_extent_bits(&inode->io_tree, start, start + len - 1, - EXTENT_QGROUP_RESERVED, &changeset); + EXTENT_QGROUP_RESERVED, NULL); } /* In release case, we shouldn't have @reserved */ @@ -4875,15 +4874,13 @@ out: void btrfs_qgroup_destroy_extent_records(struct btrfs_transaction *trans) { struct btrfs_qgroup_extent_record *entry; - struct btrfs_qgroup_extent_record *next; - struct rb_root *root; + unsigned long index; - root = &trans->delayed_refs.dirty_extent_root; - rbtree_postorder_for_each_entry_safe(entry, next, root, node) { + xa_for_each(&trans->delayed_refs.dirty_extents, index, entry) { ulist_free(entry->old_roots); kfree(entry); } - *root = RB_ROOT; + xa_destroy(&trans->delayed_refs.dirty_extents); } void btrfs_free_squota_rsv(struct btrfs_fs_info *fs_info, u64 root, u64 rsv_bytes) diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index deb479d176a9..98adf4ec7b01 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -125,7 +125,6 @@ struct btrfs_inode; * Record a dirty extent, and info qgroup to update quota on it */ struct btrfs_qgroup_extent_record { - struct rb_node node; u64 bytenr; u64 num_bytes; diff --git a/fs/btrfs/raid-stripe-tree.c b/fs/btrfs/raid-stripe-tree.c index e6f7a234b8f6..4c859b550f6c 100644 --- a/fs/btrfs/raid-stripe-tree.c +++ b/fs/btrfs/raid-stripe-tree.c @@ -66,6 +66,11 @@ int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 le if (ret) break; + start += key.offset; + length -= key.offset; + if (length == 0) + break; + btrfs_release_path(path); } @@ -73,6 +78,36 @@ int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 le return ret; } +static int update_raid_extent_item(struct btrfs_trans_handle *trans, + struct btrfs_key *key, + struct btrfs_stripe_extent *stripe_extent, + const size_t item_size) +{ + struct btrfs_path *path; + struct extent_buffer *leaf; + int ret; + int slot; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + + ret = btrfs_search_slot(trans, trans->fs_info->stripe_root, key, path, + 0, 1); + if (ret) + return (ret == 1 ? ret : -EINVAL); + + leaf = path->nodes[0]; + slot = path->slots[0]; + + write_extent_buffer(leaf, stripe_extent, btrfs_item_ptr_offset(leaf, slot), + item_size); + btrfs_mark_buffer_dirty(trans, leaf); + btrfs_free_path(path); + + return ret; +} + static int btrfs_insert_one_raid_extent(struct btrfs_trans_handle *trans, struct btrfs_io_context *bioc) { @@ -112,6 +147,9 @@ static int btrfs_insert_one_raid_extent(struct btrfs_trans_handle *trans, ret = btrfs_insert_item(trans, stripe_root, &stripe_key, stripe_extent, item_size); + if (ret == -EEXIST) + ret = update_raid_extent_item(trans, &stripe_key, stripe_extent, + item_size); if (ret) btrfs_abort_transaction(trans, ret); @@ -172,7 +210,7 @@ int btrfs_get_raid_extent_offset(struct btrfs_fs_info *fs_info, if (!path) return -ENOMEM; - if (stripe->is_scrub) { + if (stripe->rst_search_commit_root) { path->skip_locking = 1; path->search_commit_root = 1; } @@ -245,10 +283,8 @@ int btrfs_get_raid_extent_offset(struct btrfs_fs_info *fs_info, out: if (ret > 0) ret = -ENOENT; - if (ret && ret != -EIO && !stripe->is_scrub) { - if (IS_ENABLED(CONFIG_BTRFS_DEBUG)) - btrfs_print_tree(leaf, 1); - btrfs_err(fs_info, + if (ret && ret != -EIO && !stripe->rst_search_commit_root) { + btrfs_debug(fs_info, "cannot find raid-stripe for logical [%llu, %llu] devid %llu, profile %s", logical, logical + *length, stripe->dev->devid, btrfs_bg_type_to_raid_name(map_type)); diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c index df6b93b927cd..f0824c948cb7 100644 --- a/fs/btrfs/reflink.c +++ b/fs/btrfs/reflink.c @@ -66,7 +66,7 @@ static int copy_inline_to_page(struct btrfs_inode *inode, const size_t inline_size = size - btrfs_file_extent_calc_inline_size(0); char *data_start = inline_data + btrfs_file_extent_calc_inline_size(0); struct extent_changeset *data_reserved = NULL; - struct page *page = NULL; + struct folio *folio = NULL; struct address_space *mapping = inode->vfs_inode.i_mapping; int ret; @@ -83,14 +83,15 @@ static int copy_inline_to_page(struct btrfs_inode *inode, if (ret) goto out; - page = find_or_create_page(mapping, file_offset >> PAGE_SHIFT, - btrfs_alloc_write_mask(mapping)); - if (!page) { + folio = __filemap_get_folio(mapping, file_offset >> PAGE_SHIFT, + FGP_LOCK | FGP_ACCESSED | FGP_CREAT, + btrfs_alloc_write_mask(mapping)); + if (IS_ERR(folio)) { ret = -ENOMEM; goto out_unlock; } - ret = set_page_extent_mapped(page); + ret = set_folio_extent_mapped(folio); if (ret < 0) goto out_unlock; @@ -115,15 +116,15 @@ static int copy_inline_to_page(struct btrfs_inode *inode, set_bit(BTRFS_INODE_NO_DELALLOC_FLUSH, &inode->runtime_flags); if (comp_type == BTRFS_COMPRESS_NONE) { - memcpy_to_page(page, offset_in_page(file_offset), data_start, - datal); + memcpy_to_folio(folio, offset_in_folio(folio, file_offset), data_start, + datal); } else { - ret = btrfs_decompress(comp_type, data_start, page, - offset_in_page(file_offset), + ret = btrfs_decompress(comp_type, data_start, folio, + offset_in_folio(folio, file_offset), inline_size, datal); if (ret) goto out_unlock; - flush_dcache_page(page); + flush_dcache_folio(folio); } /* @@ -139,15 +140,15 @@ static int copy_inline_to_page(struct btrfs_inode *inode, * So what's in the range [500, 4095] corresponds to zeroes. */ if (datal < block_size) - memzero_page(page, datal, block_size - datal); + folio_zero_range(folio, datal, block_size - datal); - btrfs_folio_set_uptodate(fs_info, page_folio(page), file_offset, block_size); - btrfs_folio_clear_checked(fs_info, page_folio(page), file_offset, block_size); - btrfs_folio_set_dirty(fs_info, page_folio(page), file_offset, block_size); + btrfs_folio_set_uptodate(fs_info, folio, file_offset, block_size); + btrfs_folio_clear_checked(fs_info, folio, file_offset, block_size); + btrfs_folio_set_dirty(fs_info, folio, file_offset, block_size); out_unlock: - if (page) { - unlock_page(page); - put_page(page); + if (!IS_ERR(folio)) { + folio_unlock(folio); + folio_put(folio); } if (ret) btrfs_delalloc_release_space(inode, data_reserved, file_offset, diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 0533d0f82dc9..ea4ed85919ec 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -36,6 +36,7 @@ #include "relocation.h" #include "super.h" #include "tree-checker.h" +#include "raid-stripe-tree.h" /* * Relocation overview @@ -2965,21 +2966,34 @@ static int relocate_one_folio(struct reloc_control *rc, u64 folio_end; u64 cur; int ret; + const bool use_rst = btrfs_need_stripe_tree_update(fs_info, rc->block_group->flags); ASSERT(index <= last_index); folio = filemap_lock_folio(inode->i_mapping, index); if (IS_ERR(folio)) { - page_cache_sync_readahead(inode->i_mapping, ra, NULL, - index, last_index + 1 - index); + + /* + * On relocation we're doing readahead on the relocation inode, + * but if the filesystem is backed by a RAID stripe tree we can + * get ENOENT (e.g. due to preallocated extents not being + * mapped in the RST) from the lookup. + * + * But readahead doesn't handle the error and submits invalid + * reads to the device, causing a assertion failures. + */ + if (!use_rst) + page_cache_sync_readahead(inode->i_mapping, ra, NULL, + index, last_index + 1 - index); folio = __filemap_get_folio(inode->i_mapping, index, - FGP_LOCK | FGP_ACCESSED | FGP_CREAT, mask); + FGP_LOCK | FGP_ACCESSED | FGP_CREAT, + mask); if (IS_ERR(folio)) return PTR_ERR(folio); } WARN_ON(folio_order(folio)); - if (folio_test_readahead(folio)) + if (folio_test_readahead(folio) && !use_rst) page_cache_async_readahead(inode->i_mapping, ra, NULL, folio, last_index + 1 - index); diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 0de9162ff481..3a3427428074 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -838,7 +838,7 @@ static void scrub_stripe_submit_repair_read(struct scrub_stripe *stripe, bbio->bio.bi_iter.bi_size >= blocksize)) { ASSERT(bbio->bio.bi_iter.bi_size); atomic_inc(&stripe->pending_io); - btrfs_submit_bio(bbio, mirror); + btrfs_submit_bbio(bbio, mirror); if (wait) wait_scrub_stripe_io(stripe); bbio = NULL; @@ -857,7 +857,7 @@ static void scrub_stripe_submit_repair_read(struct scrub_stripe *stripe, if (bbio) { ASSERT(bbio->bio.bi_iter.bi_size); atomic_inc(&stripe->pending_io); - btrfs_submit_bio(bbio, mirror); + btrfs_submit_bbio(bbio, mirror); if (wait) wait_scrub_stripe_io(stripe); } @@ -1683,7 +1683,7 @@ static void scrub_submit_extent_sector_read(struct scrub_ctx *sctx, bbio->bio.bi_iter.bi_size >= stripe_len)) { ASSERT(bbio->bio.bi_iter.bi_size); atomic_inc(&stripe->pending_io); - btrfs_submit_bio(bbio, mirror); + btrfs_submit_bbio(bbio, mirror); bbio = NULL; } @@ -1694,7 +1694,7 @@ static void scrub_submit_extent_sector_read(struct scrub_ctx *sctx, (i << fs_info->sectorsize_bits); int err; - io_stripe.is_scrub = true; + io_stripe.rst_search_commit_root = true; stripe_len = (nr_sectors - i) << fs_info->sectorsize_bits; /* * For RST cases, we need to manually split the bbio to @@ -1720,7 +1720,7 @@ static void scrub_submit_extent_sector_read(struct scrub_ctx *sctx, if (bbio) { ASSERT(bbio->bio.bi_iter.bi_size); atomic_inc(&stripe->pending_io); - btrfs_submit_bio(bbio, mirror); + btrfs_submit_bbio(bbio, mirror); } if (atomic_dec_and_test(&stripe->pending_io)) { @@ -1776,7 +1776,7 @@ static void scrub_submit_initial_read(struct scrub_ctx *sctx, mirror = calc_next_mirror(mirror, num_copies); } - btrfs_submit_bio(bbio, mirror); + btrfs_submit_bbio(bbio, mirror); } static bool stripe_has_metadata_error(struct scrub_stripe *stripe) diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 619fa0b8b3f6..7f48ba6c1c77 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -62,7 +62,7 @@ struct fs_path { /* * Average path length does not exceed 200 bytes, we'll have * better packing in the slab and higher chance to satisfy - * a allocation later during send. + * an allocation later during send. */ char pad[256]; }; @@ -1136,7 +1136,7 @@ static int iterate_dir_item(struct btrfs_root *root, struct btrfs_path *path, /* * Start with a small buffer (1 page). If later we end up needing more * space, which can happen for xattrs on a fs with a leaf size greater - * then the page size, attempt to increase the buffer. Typically xattr + * than the page size, attempt to increase the buffer. Typically xattr * values are small. */ buf_len = PATH_MAX; diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index c691784b4660..d5a9cd8a4fd8 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -163,7 +163,7 @@ * thing with or without extra unallocated space. */ -u64 __pure btrfs_space_info_used(struct btrfs_space_info *s_info, +u64 __pure btrfs_space_info_used(const struct btrfs_space_info *s_info, bool may_use_included) { ASSERT(s_info); @@ -368,7 +368,7 @@ static u64 calc_effective_data_chunk_size(struct btrfs_fs_info *fs_info) } static u64 calc_available_free_space(struct btrfs_fs_info *fs_info, - struct btrfs_space_info *space_info, + const struct btrfs_space_info *space_info, enum btrfs_reserve_flush_enum flush) { u64 profile; @@ -437,7 +437,7 @@ static u64 calc_available_free_space(struct btrfs_fs_info *fs_info, } int btrfs_can_overcommit(struct btrfs_fs_info *fs_info, - struct btrfs_space_info *space_info, u64 bytes, + const struct btrfs_space_info *space_info, u64 bytes, enum btrfs_reserve_flush_enum flush) { u64 avail; @@ -542,8 +542,8 @@ static void dump_global_block_rsv(struct btrfs_fs_info *fs_info) DUMP_BLOCK_RSV(fs_info, delayed_refs_rsv); } -static void __btrfs_dump_space_info(struct btrfs_fs_info *fs_info, - struct btrfs_space_info *info) +static void __btrfs_dump_space_info(const struct btrfs_fs_info *fs_info, + const struct btrfs_space_info *info) { const char *flag_str = space_info_flag_to_str(info); lockdep_assert_held(&info->lock); @@ -844,9 +844,8 @@ static void flush_space(struct btrfs_fs_info *fs_info, return; } -static inline u64 -btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info, - struct btrfs_space_info *space_info) +static u64 btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info, + const struct btrfs_space_info *space_info) { u64 used; u64 avail; @@ -871,7 +870,7 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info, } static bool need_preemptive_reclaim(struct btrfs_fs_info *fs_info, - struct btrfs_space_info *space_info) + const struct btrfs_space_info *space_info) { const u64 global_rsv_size = btrfs_block_rsv_reserved(&fs_info->global_block_rsv); u64 ordered, delalloc; @@ -1943,7 +1942,7 @@ static u64 calc_unalloc_target(struct btrfs_fs_info *fs_info) * Typically with 10 block groups as the target, the discrete values this comes * out to are 0, 10, 20, ... , 80, 90, and 99. */ -static int calc_dynamic_reclaim_threshold(struct btrfs_space_info *space_info) +static int calc_dynamic_reclaim_threshold(const struct btrfs_space_info *space_info) { struct btrfs_fs_info *fs_info = space_info->fs_info; u64 unalloc = atomic64_read(&fs_info->free_chunk_space); @@ -1962,7 +1961,7 @@ static int calc_dynamic_reclaim_threshold(struct btrfs_space_info *space_info) return calc_pct_ratio(want, target); } -int btrfs_calc_reclaim_threshold(struct btrfs_space_info *space_info) +int btrfs_calc_reclaim_threshold(const struct btrfs_space_info *space_info) { lockdep_assert_held(&space_info->lock); @@ -1985,7 +1984,7 @@ static bool is_reclaim_urgent(struct btrfs_space_info *space_info) return unalloc < data_chunk_size; } -static void do_reclaim_sweep(struct btrfs_fs_info *fs_info, +static void do_reclaim_sweep(const struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, int raid) { struct btrfs_block_group *bg; @@ -2073,7 +2072,7 @@ bool btrfs_should_periodic_reclaim(struct btrfs_space_info *space_info) return ret; } -void btrfs_reclaim_sweep(struct btrfs_fs_info *fs_info) +void btrfs_reclaim_sweep(const struct btrfs_fs_info *fs_info) { int raid; struct btrfs_space_info *space_info; diff --git a/fs/btrfs/space-info.h b/fs/btrfs/space-info.h index 5602026c5e14..efbecc0c5258 100644 --- a/fs/btrfs/space-info.h +++ b/fs/btrfs/space-info.h @@ -217,7 +217,7 @@ struct reserve_ticket { wait_queue_head_t wait; }; -static inline bool btrfs_mixed_space_info(struct btrfs_space_info *space_info) +static inline bool btrfs_mixed_space_info(const struct btrfs_space_info *space_info) { return ((space_info->flags & BTRFS_BLOCK_GROUP_METADATA) && (space_info->flags & BTRFS_BLOCK_GROUP_DATA)); @@ -258,7 +258,7 @@ void btrfs_update_space_info_chunk_size(struct btrfs_space_info *space_info, u64 chunk_size); struct btrfs_space_info *btrfs_find_space_info(struct btrfs_fs_info *info, u64 flags); -u64 __pure btrfs_space_info_used(struct btrfs_space_info *s_info, +u64 __pure btrfs_space_info_used(const struct btrfs_space_info *s_info, bool may_use_included); void btrfs_clear_space_info_full(struct btrfs_fs_info *info); void btrfs_dump_space_info(struct btrfs_fs_info *fs_info, @@ -271,7 +271,7 @@ int btrfs_reserve_metadata_bytes(struct btrfs_fs_info *fs_info, void btrfs_try_granting_tickets(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info); int btrfs_can_overcommit(struct btrfs_fs_info *fs_info, - struct btrfs_space_info *space_info, u64 bytes, + const struct btrfs_space_info *space_info, u64 bytes, enum btrfs_reserve_flush_enum flush); static inline void btrfs_space_info_free_bytes_may_use( @@ -293,7 +293,7 @@ u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo); void btrfs_space_info_update_reclaimable(struct btrfs_space_info *space_info, s64 bytes); void btrfs_set_periodic_reclaim_ready(struct btrfs_space_info *space_info, bool ready); bool btrfs_should_periodic_reclaim(struct btrfs_space_info *space_info); -int btrfs_calc_reclaim_threshold(struct btrfs_space_info *space_info); -void btrfs_reclaim_sweep(struct btrfs_fs_info *fs_info); +int btrfs_calc_reclaim_threshold(const struct btrfs_space_info *space_info); +void btrfs_reclaim_sweep(const struct btrfs_fs_info *fs_info); #endif /* BTRFS_SPACE_INFO_H */ diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c index 8ddd5fcbeb93..fe4d719d506b 100644 --- a/fs/btrfs/subpage.c +++ b/fs/btrfs/subpage.c @@ -64,6 +64,7 @@ * This means a slightly higher tree locking latency. */ +#if PAGE_SIZE > SZ_4K bool btrfs_is_subpage(const struct btrfs_fs_info *fs_info, struct address_space *mapping) { if (fs_info->sectorsize >= PAGE_SIZE) @@ -85,37 +86,7 @@ bool btrfs_is_subpage(const struct btrfs_fs_info *fs_info, struct address_space return true; return false; } - -void btrfs_init_subpage_info(struct btrfs_subpage_info *subpage_info, u32 sectorsize) -{ - unsigned int cur = 0; - unsigned int nr_bits; - - ASSERT(IS_ALIGNED(PAGE_SIZE, sectorsize)); - - nr_bits = PAGE_SIZE / sectorsize; - subpage_info->bitmap_nr_bits = nr_bits; - - subpage_info->uptodate_offset = cur; - cur += nr_bits; - - subpage_info->dirty_offset = cur; - cur += nr_bits; - - subpage_info->writeback_offset = cur; - cur += nr_bits; - - subpage_info->ordered_offset = cur; - cur += nr_bits; - - subpage_info->checked_offset = cur; - cur += nr_bits; - - subpage_info->locked_offset = cur; - cur += nr_bits; - - subpage_info->total_nr_bits = cur; -} +#endif int btrfs_attach_subpage(const struct btrfs_fs_info *fs_info, struct folio *folio, enum btrfs_subpage_type type) @@ -163,7 +134,7 @@ struct btrfs_subpage *btrfs_alloc_subpage(const struct btrfs_fs_info *fs_info, ASSERT(fs_info->sectorsize < PAGE_SIZE); real_size = struct_size(ret, bitmaps, - BITS_TO_LONGS(fs_info->subpage_info->total_nr_bits)); + BITS_TO_LONGS(btrfs_bitmap_nr_max * fs_info->sectors_per_page)); ret = kzalloc(real_size, GFP_NOFS); if (!ret) return ERR_PTR(-ENOMEM); @@ -246,7 +217,7 @@ static void btrfs_subpage_assert(const struct btrfs_fs_info *fs_info, \ btrfs_subpage_assert(fs_info, folio, start, len); \ __start_bit = offset_in_page(start) >> fs_info->sectorsize_bits; \ - __start_bit += fs_info->subpage_info->name##_offset; \ + __start_bit += fs_info->sectors_per_page * btrfs_bitmap_nr_##name; \ __start_bit; \ }) @@ -351,6 +322,8 @@ static bool btrfs_subpage_end_and_test_writer(const struct btrfs_fs_info *fs_inf const int start_bit = subpage_calc_start_bit(fs_info, folio, locked, start, len); const int nbits = (len >> fs_info->sectorsize_bits); unsigned long flags; + unsigned int cleared = 0; + int bit = start_bit; bool last; btrfs_subpage_assert(fs_info, folio, start, len); @@ -368,11 +341,12 @@ static bool btrfs_subpage_end_and_test_writer(const struct btrfs_fs_info *fs_inf return true; } - ASSERT(atomic_read(&subpage->writers) >= nbits); - /* The target range should have been locked. */ - ASSERT(bitmap_test_range_all_set(subpage->bitmaps, start_bit, nbits)); - bitmap_clear(subpage->bitmaps, start_bit, nbits); - last = atomic_sub_and_test(nbits, &subpage->writers); + for_each_set_bit_from(bit, subpage->bitmaps, start_bit + nbits) { + clear_bit(bit, subpage->bitmaps); + cleared++; + } + ASSERT(atomic_read(&subpage->writers) >= cleared); + last = atomic_sub_and_test(cleared, &subpage->writers); spin_unlock_irqrestore(&subpage->lock, flags); return last; } @@ -404,27 +378,94 @@ int btrfs_folio_start_writer_lock(const struct btrfs_fs_info *fs_info, return 0; } +/* + * Handle different locked folios: + * + * - Non-subpage folio + * Just unlock it. + * + * - folio locked but without any subpage locked + * This happens either before writepage_delalloc() or the delalloc range is + * already handled by previous folio. + * We can simple unlock it. + * + * - folio locked with subpage range locked. + * We go through the locked sectors inside the range and clear their locked + * bitmap, reduce the writer lock number, and unlock the page if that's + * the last locked range. + */ void btrfs_folio_end_writer_lock(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 start, u32 len) { + struct btrfs_subpage *subpage = folio_get_private(folio); + + ASSERT(folio_test_locked(folio)); + if (unlikely(!fs_info) || !btrfs_is_subpage(fs_info, folio->mapping)) { folio_unlock(folio); return; } + + /* + * For subpage case, there are two types of locked page. With or + * without writers number. + * + * Since we own the page lock, no one else could touch subpage::writers + * and we are safe to do several atomic operations without spinlock. + */ + if (atomic_read(&subpage->writers) == 0) { + /* No writers, locked by plain lock_page(). */ + folio_unlock(folio); + return; + } + btrfs_subpage_clamp_range(folio, &start, &len); if (btrfs_subpage_end_and_test_writer(fs_info, folio, start, len)) folio_unlock(folio); } +void btrfs_folio_end_writer_lock_bitmap(const struct btrfs_fs_info *fs_info, + struct folio *folio, unsigned long bitmap) +{ + struct btrfs_subpage *subpage = folio_get_private(folio); + const int start_bit = fs_info->sectors_per_page * btrfs_bitmap_nr_locked; + unsigned long flags; + bool last = false; + int cleared = 0; + int bit; + + if (unlikely(!fs_info) || !btrfs_is_subpage(fs_info, folio->mapping)) { + folio_unlock(folio); + return; + } + + if (atomic_read(&subpage->writers) == 0) { + /* No writers, locked by plain lock_page(). */ + folio_unlock(folio); + return; + } + + spin_lock_irqsave(&subpage->lock, flags); + for_each_set_bit(bit, &bitmap, fs_info->sectors_per_page) { + if (test_and_clear_bit(bit + start_bit, subpage->bitmaps)) + cleared++; + } + ASSERT(atomic_read(&subpage->writers) >= cleared); + last = atomic_sub_and_test(cleared, &subpage->writers); + spin_unlock_irqrestore(&subpage->lock, flags); + if (last) + folio_unlock(folio); +} + #define subpage_test_bitmap_all_set(fs_info, subpage, name) \ bitmap_test_range_all_set(subpage->bitmaps, \ - fs_info->subpage_info->name##_offset, \ - fs_info->subpage_info->bitmap_nr_bits) + fs_info->sectors_per_page * btrfs_bitmap_nr_##name, \ + fs_info->sectors_per_page) #define subpage_test_bitmap_all_zero(fs_info, subpage, name) \ bitmap_test_range_all_zero(subpage->bitmaps, \ - fs_info->subpage_info->name##_offset, \ - fs_info->subpage_info->bitmap_nr_bits) + fs_info->sectors_per_page * btrfs_bitmap_nr_##name, \ + fs_info->sectors_per_page) void btrfs_subpage_set_uptodate(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 start, u32 len) @@ -729,53 +770,6 @@ void btrfs_folio_assert_not_dirty(const struct btrfs_fs_info *fs_info, } /* - * Handle different locked pages with different page sizes: - * - * - Page locked by plain lock_page() - * It should not have any subpage::writers count. - * Can be unlocked by unlock_page(). - * This is the most common locked page for __extent_writepage() called - * inside extent_write_cache_pages(). - * Rarer cases include the @locked_page from extent_write_locked_range(). - * - * - Page locked by lock_delalloc_pages() - * There is only one caller, all pages except @locked_page for - * extent_write_locked_range(). - * In this case, we have to call subpage helper to handle the case. - */ -void btrfs_folio_unlock_writer(struct btrfs_fs_info *fs_info, - struct folio *folio, u64 start, u32 len) -{ - struct btrfs_subpage *subpage; - - ASSERT(folio_test_locked(folio)); - /* For non-subpage case, we just unlock the page */ - if (!btrfs_is_subpage(fs_info, folio->mapping)) { - folio_unlock(folio); - return; - } - - ASSERT(folio_test_private(folio) && folio_get_private(folio)); - subpage = folio_get_private(folio); - - /* - * For subpage case, there are two types of locked page. With or - * without writers number. - * - * Since we own the page lock, no one else could touch subpage::writers - * and we are safe to do several atomic operations without spinlock. - */ - if (atomic_read(&subpage->writers) == 0) { - /* No writers, locked by plain lock_page() */ - folio_unlock(folio); - return; - } - - /* Have writers, use proper subpage helper to end it */ - btrfs_folio_end_writer_lock(fs_info, folio, start, len); -} - -/* * This is for folio already locked by plain lock_page()/folio_lock(), which * doesn't have any subpage awareness. * @@ -803,7 +797,7 @@ void btrfs_folio_set_writer_lock(const struct btrfs_fs_info *fs_info, ASSERT(bitmap_test_range_all_zero(subpage->bitmaps, start_bit, nbits)); bitmap_set(subpage->bitmaps, start_bit, nbits); ret = atomic_add_return(nbits, &subpage->writers); - ASSERT(ret <= fs_info->subpage_info->bitmap_nr_bits); + ASSERT(ret <= fs_info->sectors_per_page); spin_unlock_irqrestore(&subpage->lock, flags); } @@ -819,14 +813,13 @@ bool btrfs_subpage_find_writer_locked(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 search_start, u64 *found_start_ret, u32 *found_len_ret) { - struct btrfs_subpage_info *subpage_info = fs_info->subpage_info; struct btrfs_subpage *subpage = folio_get_private(folio); + const u32 sectors_per_page = fs_info->sectors_per_page; const unsigned int len = PAGE_SIZE - offset_in_page(search_start); const unsigned int start_bit = subpage_calc_start_bit(fs_info, folio, locked, search_start, len); - const unsigned int locked_bitmap_start = subpage_info->locked_offset; - const unsigned int locked_bitmap_end = locked_bitmap_start + - subpage_info->bitmap_nr_bits; + const unsigned int locked_bitmap_start = sectors_per_page * btrfs_bitmap_nr_locked; + const unsigned int locked_bitmap_end = locked_bitmap_start + sectors_per_page; unsigned long flags; int first_zero; int first_set; @@ -855,59 +848,21 @@ out: return found; } -/* - * Unlike btrfs_folio_end_writer_lock() which unlocks a specified subpage range, - * this ends all writer locked ranges of a page. - * - * This is for the locked page of __extent_writepage(), as the locked page - * can contain several locked subpage ranges. - */ -void btrfs_folio_end_all_writers(const struct btrfs_fs_info *fs_info, struct folio *folio) -{ - struct btrfs_subpage *subpage = folio_get_private(folio); - u64 folio_start = folio_pos(folio); - u64 cur = folio_start; - - ASSERT(folio_test_locked(folio)); - if (!btrfs_is_subpage(fs_info, folio->mapping)) { - folio_unlock(folio); - return; - } - - /* The page has no new delalloc range locked on it. Just plain unlock. */ - if (atomic_read(&subpage->writers) == 0) { - folio_unlock(folio); - return; - } - while (cur < folio_start + PAGE_SIZE) { - u64 found_start; - u32 found_len; - bool found; - bool last; - - found = btrfs_subpage_find_writer_locked(fs_info, folio, cur, - &found_start, &found_len); - if (!found) - break; - last = btrfs_subpage_end_and_test_writer(fs_info, folio, - found_start, found_len); - if (last) { - folio_unlock(folio); - break; - } - cur = found_start + found_len; - } +#define GET_SUBPAGE_BITMAP(subpage, fs_info, name, dst) \ +{ \ + const int sectors_per_page = fs_info->sectors_per_page; \ + \ + ASSERT(sectors_per_page < BITS_PER_LONG); \ + *dst = bitmap_read(subpage->bitmaps, \ + sectors_per_page * btrfs_bitmap_nr_##name, \ + sectors_per_page); \ } -#define GET_SUBPAGE_BITMAP(subpage, subpage_info, name, dst) \ - bitmap_cut(dst, subpage->bitmaps, 0, \ - subpage_info->name##_offset, subpage_info->bitmap_nr_bits) - void __cold btrfs_subpage_dump_bitmap(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 start, u32 len) { - struct btrfs_subpage_info *subpage_info = fs_info->subpage_info; struct btrfs_subpage *subpage; + const u32 sectors_per_page = fs_info->sectors_per_page; unsigned long uptodate_bitmap; unsigned long dirty_bitmap; unsigned long writeback_bitmap; @@ -916,25 +871,41 @@ void __cold btrfs_subpage_dump_bitmap(const struct btrfs_fs_info *fs_info, unsigned long flags; ASSERT(folio_test_private(folio) && folio_get_private(folio)); - ASSERT(subpage_info); + ASSERT(sectors_per_page > 1); subpage = folio_get_private(folio); spin_lock_irqsave(&subpage->lock, flags); - GET_SUBPAGE_BITMAP(subpage, subpage_info, uptodate, &uptodate_bitmap); - GET_SUBPAGE_BITMAP(subpage, subpage_info, dirty, &dirty_bitmap); - GET_SUBPAGE_BITMAP(subpage, subpage_info, writeback, &writeback_bitmap); - GET_SUBPAGE_BITMAP(subpage, subpage_info, ordered, &ordered_bitmap); - GET_SUBPAGE_BITMAP(subpage, subpage_info, checked, &checked_bitmap); - GET_SUBPAGE_BITMAP(subpage, subpage_info, locked, &checked_bitmap); + GET_SUBPAGE_BITMAP(subpage, fs_info, uptodate, &uptodate_bitmap); + GET_SUBPAGE_BITMAP(subpage, fs_info, dirty, &dirty_bitmap); + GET_SUBPAGE_BITMAP(subpage, fs_info, writeback, &writeback_bitmap); + GET_SUBPAGE_BITMAP(subpage, fs_info, ordered, &ordered_bitmap); + GET_SUBPAGE_BITMAP(subpage, fs_info, checked, &checked_bitmap); + GET_SUBPAGE_BITMAP(subpage, fs_info, locked, &checked_bitmap); spin_unlock_irqrestore(&subpage->lock, flags); dump_page(folio_page(folio, 0), "btrfs subpage dump"); btrfs_warn(fs_info, "start=%llu len=%u page=%llu, bitmaps uptodate=%*pbl dirty=%*pbl writeback=%*pbl ordered=%*pbl checked=%*pbl", start, len, folio_pos(folio), - subpage_info->bitmap_nr_bits, &uptodate_bitmap, - subpage_info->bitmap_nr_bits, &dirty_bitmap, - subpage_info->bitmap_nr_bits, &writeback_bitmap, - subpage_info->bitmap_nr_bits, &ordered_bitmap, - subpage_info->bitmap_nr_bits, &checked_bitmap); + sectors_per_page, &uptodate_bitmap, + sectors_per_page, &dirty_bitmap, + sectors_per_page, &writeback_bitmap, + sectors_per_page, &ordered_bitmap, + sectors_per_page, &checked_bitmap); +} + +void btrfs_get_subpage_dirty_bitmap(struct btrfs_fs_info *fs_info, + struct folio *folio, + unsigned long *ret_bitmap) +{ + struct btrfs_subpage *subpage; + unsigned long flags; + + ASSERT(folio_test_private(folio) && folio_get_private(folio)); + ASSERT(fs_info->sectors_per_page > 1); + subpage = folio_get_private(folio); + + spin_lock_irqsave(&subpage->lock, flags); + GET_SUBPAGE_BITMAP(subpage, fs_info, dirty, ret_bitmap); + spin_unlock_irqrestore(&subpage->lock, flags); } diff --git a/fs/btrfs/subpage.h b/fs/btrfs/subpage.h index 249396e118d0..4b85d91d0e18 100644 --- a/fs/btrfs/subpage.h +++ b/fs/btrfs/subpage.h @@ -5,6 +5,7 @@ #include <linux/spinlock.h> #include <linux/atomic.h> +#include <linux/sizes.h> struct address_space; struct folio; @@ -18,39 +19,23 @@ struct btrfs_fs_info; * * This structure records how they are organized in the bitmap: * - * /- uptodate_offset /- dirty_offset /- ordered_offset + * /- uptodate /- dirty /- ordered * | | | * v v v * |u|u|u|u|........|u|u|d|d|.......|d|d|o|o|.......|o|o| - * |<- bitmap_nr_bits ->| - * |<----------------- total_nr_bits ------------------>| + * |< sectors_per_page >| + * + * Unlike regular macro-like enums, here we do not go upper-case names, as + * these names will be utilized in various macros to define function names. */ -struct btrfs_subpage_info { - /* Number of bits for each bitmap */ - unsigned int bitmap_nr_bits; - - /* Total number of bits for the whole bitmap */ - unsigned int total_nr_bits; - - /* - * *_offset indicates where the bitmap starts, the length is always - * @bitmap_size, which is calculated from PAGE_SIZE / sectorsize. - */ - unsigned int uptodate_offset; - unsigned int dirty_offset; - unsigned int writeback_offset; - unsigned int ordered_offset; - unsigned int checked_offset; - - /* - * For locked bitmaps, normally it's subpage representation for folio - * Locked flag, but metadata is different: - * - * - Metadata doesn't really lock the folio - * It's just to prevent page::private get cleared before the last - * end_page_read(). - */ - unsigned int locked_offset; +enum { + btrfs_bitmap_nr_uptodate = 0, + btrfs_bitmap_nr_dirty, + btrfs_bitmap_nr_writeback, + btrfs_bitmap_nr_ordered, + btrfs_bitmap_nr_checked, + btrfs_bitmap_nr_locked, + btrfs_bitmap_nr_max }; /* @@ -88,9 +73,16 @@ enum btrfs_subpage_type { BTRFS_SUBPAGE_DATA, }; +#if PAGE_SIZE > SZ_4K bool btrfs_is_subpage(const struct btrfs_fs_info *fs_info, struct address_space *mapping); +#else +static inline bool btrfs_is_subpage(const struct btrfs_fs_info *fs_info, + struct address_space *mapping) +{ + return false; +} +#endif -void btrfs_init_subpage_info(struct btrfs_subpage_info *subpage_info, u32 sectorsize); int btrfs_attach_subpage(const struct btrfs_fs_info *fs_info, struct folio *folio, enum btrfs_subpage_type type); void btrfs_detach_subpage(const struct btrfs_fs_info *fs_info, struct folio *folio); @@ -114,10 +106,11 @@ void btrfs_folio_end_writer_lock(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 start, u32 len); void btrfs_folio_set_writer_lock(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 start, u32 len); +void btrfs_folio_end_writer_lock_bitmap(const struct btrfs_fs_info *fs_info, + struct folio *folio, unsigned long bitmap); bool btrfs_subpage_find_writer_locked(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 search_start, u64 *found_start_ret, u32 *found_len_ret); -void btrfs_folio_end_all_writers(const struct btrfs_fs_info *fs_info, struct folio *folio); /* * Template for subpage related operations. @@ -164,8 +157,9 @@ bool btrfs_subpage_clear_and_test_dirty(const struct btrfs_fs_info *fs_info, void btrfs_folio_assert_not_dirty(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 start, u32 len); -void btrfs_folio_unlock_writer(struct btrfs_fs_info *fs_info, - struct folio *folio, u64 start, u32 len); +void btrfs_get_subpage_dirty_bitmap(struct btrfs_fs_info *fs_info, + struct folio *folio, + unsigned long *ret_bitmap); void __cold btrfs_subpage_dump_bitmap(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 start, u32 len); diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c index 865d4af4b303..0a2dbfaaf49e 100644 --- a/fs/btrfs/tests/extent-io-tests.c +++ b/fs/btrfs/tests/extent-io-tests.c @@ -180,7 +180,7 @@ static int test_find_delalloc(u32 sectorsize, u32 nodesize) set_extent_bit(tmp, 0, sectorsize - 1, EXTENT_DELALLOC, NULL); start = 0; end = start + PAGE_SIZE - 1; - found = find_lock_delalloc_range(inode, locked_page, &start, + found = find_lock_delalloc_range(inode, page_folio(locked_page), &start, &end); if (!found) { test_err("should have found at least one delalloc"); @@ -211,7 +211,7 @@ static int test_find_delalloc(u32 sectorsize, u32 nodesize) set_extent_bit(tmp, sectorsize, max_bytes - 1, EXTENT_DELALLOC, NULL); start = test_start; end = start + PAGE_SIZE - 1; - found = find_lock_delalloc_range(inode, locked_page, &start, + found = find_lock_delalloc_range(inode, page_folio(locked_page), &start, &end); if (!found) { test_err("couldn't find delalloc in our range"); @@ -245,7 +245,7 @@ static int test_find_delalloc(u32 sectorsize, u32 nodesize) } start = test_start; end = start + PAGE_SIZE - 1; - found = find_lock_delalloc_range(inode, locked_page, &start, + found = find_lock_delalloc_range(inode, page_folio(locked_page), &start, &end); if (found) { test_err("found range when we shouldn't have"); @@ -266,7 +266,7 @@ static int test_find_delalloc(u32 sectorsize, u32 nodesize) set_extent_bit(tmp, max_bytes, total_dirty - 1, EXTENT_DELALLOC, NULL); start = test_start; end = start + PAGE_SIZE - 1; - found = find_lock_delalloc_range(inode, locked_page, &start, + found = find_lock_delalloc_range(inode, page_folio(locked_page), &start, &end); if (!found) { test_err("didn't find our range"); @@ -307,7 +307,7 @@ static int test_find_delalloc(u32 sectorsize, u32 nodesize) * this changes at any point in the future we will need to fix this * tests expected behavior. */ - found = find_lock_delalloc_range(inode, locked_page, &start, + found = find_lock_delalloc_range(inode, page_folio(locked_page), &start, &end); if (!found) { test_err("didn't find our range"); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 5e6fff8e1003..0fc873af891f 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -143,8 +143,7 @@ void btrfs_put_transaction(struct btrfs_transaction *transaction) BUG_ON(!list_empty(&transaction->list)); WARN_ON(!RB_EMPTY_ROOT( &transaction->delayed_refs.href_root.rb_root)); - WARN_ON(!RB_EMPTY_ROOT( - &transaction->delayed_refs.dirty_extent_root)); + WARN_ON(!xa_empty(&transaction->delayed_refs.dirty_extents)); if (transaction->delayed_refs.pending_csums) btrfs_err(transaction->fs_info, "pending csums is %llu", @@ -351,7 +350,7 @@ loop: memset(&cur_trans->delayed_refs, 0, sizeof(cur_trans->delayed_refs)); cur_trans->delayed_refs.href_root = RB_ROOT_CACHED; - cur_trans->delayed_refs.dirty_extent_root = RB_ROOT; + xa_init(&cur_trans->delayed_refs.dirty_extents); atomic_set(&cur_trans->delayed_refs.num_entries, 0); /* diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 98c03ddc760b..dd9ce9b9f69e 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -27,6 +27,12 @@ struct btrfs_root_item; struct btrfs_root; struct btrfs_path; +/* + * Signal that a direct IO write is in progress, to avoid deadlock for sync + * direct IO writes when fsync is called during the direct IO write path. + */ +#define BTRFS_TRANS_DIO_WRITE_STUB ((void *) 1) + /* Radix-tree tag for roots that are part of the trasaction. */ #define BTRFS_ROOT_TRANS_TAG 0 diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index f0cf8ce26f01..e2ed2a791f8f 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -2877,7 +2877,7 @@ void btrfs_release_log_ctx_extents(struct btrfs_log_ctx *ctx) struct btrfs_ordered_extent *ordered; struct btrfs_ordered_extent *tmp; - ASSERT(inode_is_locked(&ctx->inode->vfs_inode)); + btrfs_assert_inode_locked(ctx->inode); list_for_each_entry_safe(ordered, tmp, &ctx->ordered_extents, log_list) { list_del_init(&ordered->log_list); diff --git a/fs/btrfs/tree-mod-log.c b/fs/btrfs/tree-mod-log.c index fa45b5fb9683..b382a4c443d4 100644 --- a/fs/btrfs/tree-mod-log.c +++ b/fs/btrfs/tree-mod-log.c @@ -170,7 +170,7 @@ static noinline int tree_mod_log_insert(struct btrfs_fs_info *fs_info, * this until all tree mod log insertions are recorded in the rb tree and then * write unlock fs_info::tree_mod_log_lock. */ -static bool tree_mod_dont_log(struct btrfs_fs_info *fs_info, struct extent_buffer *eb) +static bool tree_mod_dont_log(struct btrfs_fs_info *fs_info, const struct extent_buffer *eb) { if (!test_bit(BTRFS_FS_TREE_MOD_LOG_USERS, &fs_info->flags)) return true; @@ -188,7 +188,7 @@ static bool tree_mod_dont_log(struct btrfs_fs_info *fs_info, struct extent_buffe /* Similar to tree_mod_dont_log, but doesn't acquire any locks. */ static bool tree_mod_need_log(const struct btrfs_fs_info *fs_info, - struct extent_buffer *eb) + const struct extent_buffer *eb) { if (!test_bit(BTRFS_FS_TREE_MOD_LOG_USERS, &fs_info->flags)) return false; @@ -198,7 +198,7 @@ static bool tree_mod_need_log(const struct btrfs_fs_info *fs_info, return true; } -static struct tree_mod_elem *alloc_tree_mod_elem(struct extent_buffer *eb, +static struct tree_mod_elem *alloc_tree_mod_elem(const struct extent_buffer *eb, int slot, enum btrfs_mod_log_op op) { @@ -221,7 +221,7 @@ static struct tree_mod_elem *alloc_tree_mod_elem(struct extent_buffer *eb, return tm; } -int btrfs_tree_mod_log_insert_key(struct extent_buffer *eb, int slot, +int btrfs_tree_mod_log_insert_key(const struct extent_buffer *eb, int slot, enum btrfs_mod_log_op op) { struct tree_mod_elem *tm; @@ -258,7 +258,7 @@ out_unlock: return ret; } -static struct tree_mod_elem *tree_mod_log_alloc_move(struct extent_buffer *eb, +static struct tree_mod_elem *tree_mod_log_alloc_move(const struct extent_buffer *eb, int dst_slot, int src_slot, int nr_items) { @@ -278,7 +278,7 @@ static struct tree_mod_elem *tree_mod_log_alloc_move(struct extent_buffer *eb, return tm; } -int btrfs_tree_mod_log_insert_move(struct extent_buffer *eb, +int btrfs_tree_mod_log_insert_move(const struct extent_buffer *eb, int dst_slot, int src_slot, int nr_items) { @@ -535,7 +535,7 @@ static struct tree_mod_elem *tree_mod_log_search(struct btrfs_fs_info *fs_info, } int btrfs_tree_mod_log_eb_copy(struct extent_buffer *dst, - struct extent_buffer *src, + const struct extent_buffer *src, unsigned long dst_offset, unsigned long src_offset, int nr_items) diff --git a/fs/btrfs/tree-mod-log.h b/fs/btrfs/tree-mod-log.h index ff00c8e8a393..6308c577a4a4 100644 --- a/fs/btrfs/tree-mod-log.h +++ b/fs/btrfs/tree-mod-log.h @@ -37,7 +37,7 @@ void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info, int btrfs_tree_mod_log_insert_root(struct extent_buffer *old_root, struct extent_buffer *new_root, bool log_removal); -int btrfs_tree_mod_log_insert_key(struct extent_buffer *eb, int slot, +int btrfs_tree_mod_log_insert_key(const struct extent_buffer *eb, int slot, enum btrfs_mod_log_op op); int btrfs_tree_mod_log_free_eb(struct extent_buffer *eb); struct extent_buffer *btrfs_tree_mod_log_rewind(struct btrfs_fs_info *fs_info, @@ -47,11 +47,11 @@ struct extent_buffer *btrfs_tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *btrfs_get_old_root(struct btrfs_root *root, u64 time_seq); int btrfs_old_root_level(struct btrfs_root *root, u64 time_seq); int btrfs_tree_mod_log_eb_copy(struct extent_buffer *dst, - struct extent_buffer *src, + const struct extent_buffer *src, unsigned long dst_offset, unsigned long src_offset, int nr_items); -int btrfs_tree_mod_log_insert_move(struct extent_buffer *eb, +int btrfs_tree_mod_log_insert_move(const struct extent_buffer *eb, int dst_slot, int src_slot, int nr_items); u64 btrfs_tree_mod_log_lowest_seq(struct btrfs_fs_info *fs_info); diff --git a/fs/btrfs/uuid-tree.c b/fs/btrfs/uuid-tree.c index eae75bb572b9..c6399513c66f 100644 --- a/fs/btrfs/uuid-tree.c +++ b/fs/btrfs/uuid-tree.c @@ -3,6 +3,7 @@ * Copyright (C) STRATO AG 2013. All rights reserved. */ +#include <linux/kthread.h> #include <linux/uuid.h> #include <asm/unaligned.h> #include "messages.h" @@ -12,6 +13,7 @@ #include "fs.h" #include "accessors.h" #include "uuid-tree.h" +#include "ioctl.h" static void btrfs_uuid_to_key(const u8 *uuid, u8 type, struct btrfs_key *key) { @@ -390,3 +392,180 @@ out: btrfs_free_path(path); return ret; } + +int btrfs_uuid_scan_kthread(void *data) +{ + struct btrfs_fs_info *fs_info = data; + struct btrfs_root *root = fs_info->tree_root; + struct btrfs_key key; + struct btrfs_path *path = NULL; + int ret = 0; + struct extent_buffer *eb; + int slot; + struct btrfs_root_item root_item; + u32 item_size; + struct btrfs_trans_handle *trans = NULL; + bool closing = false; + + path = btrfs_alloc_path(); + if (!path) { + ret = -ENOMEM; + goto out; + } + + key.objectid = 0; + key.type = BTRFS_ROOT_ITEM_KEY; + key.offset = 0; + + while (1) { + if (btrfs_fs_closing(fs_info)) { + closing = true; + break; + } + ret = btrfs_search_forward(root, &key, path, + BTRFS_OLDEST_GENERATION); + if (ret) { + if (ret > 0) + ret = 0; + break; + } + + if (key.type != BTRFS_ROOT_ITEM_KEY || + (key.objectid < BTRFS_FIRST_FREE_OBJECTID && + key.objectid != BTRFS_FS_TREE_OBJECTID) || + key.objectid > BTRFS_LAST_FREE_OBJECTID) + goto skip; + + eb = path->nodes[0]; + slot = path->slots[0]; + item_size = btrfs_item_size(eb, slot); + if (item_size < sizeof(root_item)) + goto skip; + + read_extent_buffer(eb, &root_item, + btrfs_item_ptr_offset(eb, slot), + (int)sizeof(root_item)); + if (btrfs_root_refs(&root_item) == 0) + goto skip; + + if (!btrfs_is_empty_uuid(root_item.uuid) || + !btrfs_is_empty_uuid(root_item.received_uuid)) { + if (trans) + goto update_tree; + + btrfs_release_path(path); + /* + * 1 - subvol uuid item + * 1 - received_subvol uuid item + */ + trans = btrfs_start_transaction(fs_info->uuid_root, 2); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); + break; + } + continue; + } else { + goto skip; + } +update_tree: + btrfs_release_path(path); + if (!btrfs_is_empty_uuid(root_item.uuid)) { + ret = btrfs_uuid_tree_add(trans, root_item.uuid, + BTRFS_UUID_KEY_SUBVOL, + key.objectid); + if (ret < 0) { + btrfs_warn(fs_info, "uuid_tree_add failed %d", + ret); + break; + } + } + + if (!btrfs_is_empty_uuid(root_item.received_uuid)) { + ret = btrfs_uuid_tree_add(trans, + root_item.received_uuid, + BTRFS_UUID_KEY_RECEIVED_SUBVOL, + key.objectid); + if (ret < 0) { + btrfs_warn(fs_info, "uuid_tree_add failed %d", + ret); + break; + } + } + +skip: + btrfs_release_path(path); + if (trans) { + ret = btrfs_end_transaction(trans); + trans = NULL; + if (ret) + break; + } + + if (key.offset < (u64)-1) { + key.offset++; + } else if (key.type < BTRFS_ROOT_ITEM_KEY) { + key.offset = 0; + key.type = BTRFS_ROOT_ITEM_KEY; + } else if (key.objectid < (u64)-1) { + key.offset = 0; + key.type = BTRFS_ROOT_ITEM_KEY; + key.objectid++; + } else { + break; + } + cond_resched(); + } + +out: + btrfs_free_path(path); + if (trans && !IS_ERR(trans)) + btrfs_end_transaction(trans); + if (ret) + btrfs_warn(fs_info, "btrfs_uuid_scan_kthread failed %d", ret); + else if (!closing) + set_bit(BTRFS_FS_UPDATE_UUID_TREE_GEN, &fs_info->flags); + up(&fs_info->uuid_tree_rescan_sem); + return 0; +} + +int btrfs_create_uuid_tree(struct btrfs_fs_info *fs_info) +{ + struct btrfs_trans_handle *trans; + struct btrfs_root *tree_root = fs_info->tree_root; + struct btrfs_root *uuid_root; + struct task_struct *task; + int ret; + + /* + * 1 - root node + * 1 - root item + */ + trans = btrfs_start_transaction(tree_root, 2); + if (IS_ERR(trans)) + return PTR_ERR(trans); + + uuid_root = btrfs_create_tree(trans, BTRFS_UUID_TREE_OBJECTID); + if (IS_ERR(uuid_root)) { + ret = PTR_ERR(uuid_root); + btrfs_abort_transaction(trans, ret); + btrfs_end_transaction(trans); + return ret; + } + + fs_info->uuid_root = uuid_root; + + ret = btrfs_commit_transaction(trans); + if (ret) + return ret; + + down(&fs_info->uuid_tree_rescan_sem); + task = kthread_run(btrfs_uuid_scan_kthread, fs_info, "btrfs-uuid"); + if (IS_ERR(task)) { + /* fs_info->update_uuid_tree_gen remains 0 in all error case */ + btrfs_warn(fs_info, "failed to start uuid_scan task"); + up(&fs_info->uuid_tree_rescan_sem); + return PTR_ERR(task); + } + + return 0; +} diff --git a/fs/btrfs/uuid-tree.h b/fs/btrfs/uuid-tree.h index a3f5757cc7cf..c60ad20325cc 100644 --- a/fs/btrfs/uuid-tree.h +++ b/fs/btrfs/uuid-tree.h @@ -13,5 +13,7 @@ int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans, const u8 *uuid, u8 typ int btrfs_uuid_tree_remove(struct btrfs_trans_handle *trans, const u8 *uuid, u8 type, u64 subid); int btrfs_uuid_tree_iterate(struct btrfs_fs_info *fs_info); +int btrfs_create_uuid_tree(struct btrfs_fs_info *fs_info); +int btrfs_uuid_scan_kthread(void *data); #endif diff --git a/fs/btrfs/verity.c b/fs/btrfs/verity.c index 4042dd6437ae..e97ad824ae16 100644 --- a/fs/btrfs/verity.c +++ b/fs/btrfs/verity.c @@ -284,7 +284,7 @@ static int write_key_bytes(struct btrfs_inode *inode, u8 key_type, u64 offset, * page and ignore dest, but it must still be non-NULL to avoid the * counting-only behavior. * @len: length in bytes to read - * @dest_page: copy into this page instead of the dest buffer + * @dest_folio: copy into this folio instead of the dest buffer * * Helper function to read items from the btree. This returns the number of * bytes read or < 0 for errors. We can return short reads if the items don't @@ -294,7 +294,7 @@ static int write_key_bytes(struct btrfs_inode *inode, u8 key_type, u64 offset, * Returns number of bytes read or a negative error code on failure. */ static int read_key_bytes(struct btrfs_inode *inode, u8 key_type, u64 offset, - char *dest, u64 len, struct page *dest_page) + char *dest, u64 len, struct folio *dest_folio) { struct btrfs_path *path; struct btrfs_root *root = inode->root; @@ -314,7 +314,7 @@ static int read_key_bytes(struct btrfs_inode *inode, u8 key_type, u64 offset, if (!path) return -ENOMEM; - if (dest_page) + if (dest_folio) path->reada = READA_FORWARD; key.objectid = btrfs_ino(inode); @@ -371,15 +371,15 @@ static int read_key_bytes(struct btrfs_inode *inode, u8 key_type, u64 offset, copy_offset = offset - key.offset; if (dest) { - if (dest_page) - kaddr = kmap_local_page(dest_page); + if (dest_folio) + kaddr = kmap_local_folio(dest_folio, 0); data = btrfs_item_ptr(leaf, path->slots[0], void); read_extent_buffer(leaf, kaddr + dest_offset, (unsigned long)data + copy_offset, copy_bytes); - if (dest_page) + if (dest_folio) kunmap_local(kaddr); } @@ -460,7 +460,7 @@ static int rollback_verity(struct btrfs_inode *inode) struct btrfs_root *root = inode->root; int ret; - ASSERT(inode_is_locked(&inode->vfs_inode)); + btrfs_assert_inode_locked(inode); truncate_inode_pages(inode->vfs_inode.i_mapping, inode->vfs_inode.i_size); clear_bit(BTRFS_INODE_VERITY_IN_PROGRESS, &inode->runtime_flags); ret = btrfs_drop_verity_items(inode); @@ -585,7 +585,7 @@ static int btrfs_begin_enable_verity(struct file *filp) struct btrfs_trans_handle *trans; int ret; - ASSERT(inode_is_locked(file_inode(filp))); + btrfs_assert_inode_locked(inode); if (test_bit(BTRFS_INODE_VERITY_IN_PROGRESS, &inode->runtime_flags)) return -EBUSY; @@ -633,7 +633,7 @@ static int btrfs_end_enable_verity(struct file *filp, const void *desc, int ret = 0; int rollback_ret; - ASSERT(inode_is_locked(file_inode(filp))); + btrfs_assert_inode_locked(inode); if (desc == NULL) goto rollback; @@ -762,7 +762,7 @@ again: * [ inode objectid, BTRFS_MERKLE_ITEM_KEY, offset in bytes ] */ ret = read_key_bytes(BTRFS_I(inode), BTRFS_VERITY_MERKLE_ITEM_KEY, off, - folio_address(folio), PAGE_SIZE, &folio->page); + folio_address(folio), PAGE_SIZE, folio); if (ret < 0) { folio_put(folio); return ERR_PTR(ret); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index fcedc43ef291..8f340ad1d938 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -476,6 +476,8 @@ btrfs_get_bdev_and_sb(const char *device_path, blk_mode_t flags, void *holder, if (IS_ERR(*bdev_file)) { ret = PTR_ERR(*bdev_file); + btrfs_err(NULL, "failed to open device for path %s with flags 0x%x: %d", + device_path, flags, ret); goto error; } bdev = file_bdev(*bdev_file); @@ -4784,183 +4786,6 @@ int btrfs_cancel_balance(struct btrfs_fs_info *fs_info) return 0; } -int btrfs_uuid_scan_kthread(void *data) -{ - struct btrfs_fs_info *fs_info = data; - struct btrfs_root *root = fs_info->tree_root; - struct btrfs_key key; - struct btrfs_path *path = NULL; - int ret = 0; - struct extent_buffer *eb; - int slot; - struct btrfs_root_item root_item; - u32 item_size; - struct btrfs_trans_handle *trans = NULL; - bool closing = false; - - path = btrfs_alloc_path(); - if (!path) { - ret = -ENOMEM; - goto out; - } - - key.objectid = 0; - key.type = BTRFS_ROOT_ITEM_KEY; - key.offset = 0; - - while (1) { - if (btrfs_fs_closing(fs_info)) { - closing = true; - break; - } - ret = btrfs_search_forward(root, &key, path, - BTRFS_OLDEST_GENERATION); - if (ret) { - if (ret > 0) - ret = 0; - break; - } - - if (key.type != BTRFS_ROOT_ITEM_KEY || - (key.objectid < BTRFS_FIRST_FREE_OBJECTID && - key.objectid != BTRFS_FS_TREE_OBJECTID) || - key.objectid > BTRFS_LAST_FREE_OBJECTID) - goto skip; - - eb = path->nodes[0]; - slot = path->slots[0]; - item_size = btrfs_item_size(eb, slot); - if (item_size < sizeof(root_item)) - goto skip; - - read_extent_buffer(eb, &root_item, - btrfs_item_ptr_offset(eb, slot), - (int)sizeof(root_item)); - if (btrfs_root_refs(&root_item) == 0) - goto skip; - - if (!btrfs_is_empty_uuid(root_item.uuid) || - !btrfs_is_empty_uuid(root_item.received_uuid)) { - if (trans) - goto update_tree; - - btrfs_release_path(path); - /* - * 1 - subvol uuid item - * 1 - received_subvol uuid item - */ - trans = btrfs_start_transaction(fs_info->uuid_root, 2); - if (IS_ERR(trans)) { - ret = PTR_ERR(trans); - break; - } - continue; - } else { - goto skip; - } -update_tree: - btrfs_release_path(path); - if (!btrfs_is_empty_uuid(root_item.uuid)) { - ret = btrfs_uuid_tree_add(trans, root_item.uuid, - BTRFS_UUID_KEY_SUBVOL, - key.objectid); - if (ret < 0) { - btrfs_warn(fs_info, "uuid_tree_add failed %d", - ret); - break; - } - } - - if (!btrfs_is_empty_uuid(root_item.received_uuid)) { - ret = btrfs_uuid_tree_add(trans, - root_item.received_uuid, - BTRFS_UUID_KEY_RECEIVED_SUBVOL, - key.objectid); - if (ret < 0) { - btrfs_warn(fs_info, "uuid_tree_add failed %d", - ret); - break; - } - } - -skip: - btrfs_release_path(path); - if (trans) { - ret = btrfs_end_transaction(trans); - trans = NULL; - if (ret) - break; - } - - if (key.offset < (u64)-1) { - key.offset++; - } else if (key.type < BTRFS_ROOT_ITEM_KEY) { - key.offset = 0; - key.type = BTRFS_ROOT_ITEM_KEY; - } else if (key.objectid < (u64)-1) { - key.offset = 0; - key.type = BTRFS_ROOT_ITEM_KEY; - key.objectid++; - } else { - break; - } - cond_resched(); - } - -out: - btrfs_free_path(path); - if (trans && !IS_ERR(trans)) - btrfs_end_transaction(trans); - if (ret) - btrfs_warn(fs_info, "btrfs_uuid_scan_kthread failed %d", ret); - else if (!closing) - set_bit(BTRFS_FS_UPDATE_UUID_TREE_GEN, &fs_info->flags); - up(&fs_info->uuid_tree_rescan_sem); - return 0; -} - -int btrfs_create_uuid_tree(struct btrfs_fs_info *fs_info) -{ - struct btrfs_trans_handle *trans; - struct btrfs_root *tree_root = fs_info->tree_root; - struct btrfs_root *uuid_root; - struct task_struct *task; - int ret; - - /* - * 1 - root node - * 1 - root item - */ - trans = btrfs_start_transaction(tree_root, 2); - if (IS_ERR(trans)) - return PTR_ERR(trans); - - uuid_root = btrfs_create_tree(trans, BTRFS_UUID_TREE_OBJECTID); - if (IS_ERR(uuid_root)) { - ret = PTR_ERR(uuid_root); - btrfs_abort_transaction(trans, ret); - btrfs_end_transaction(trans); - return ret; - } - - fs_info->uuid_root = uuid_root; - - ret = btrfs_commit_transaction(trans); - if (ret) - return ret; - - down(&fs_info->uuid_tree_rescan_sem); - task = kthread_run(btrfs_uuid_scan_kthread, fs_info, "btrfs-uuid"); - if (IS_ERR(task)) { - /* fs_info->update_uuid_tree_gen remains 0 in all error case */ - btrfs_warn(fs_info, "failed to start uuid_scan task"); - up(&fs_info->uuid_tree_rescan_sem); - return PTR_ERR(task); - } - - return 0; -} - /* * shrinking a device means finding all of the device extents past * the new size, and then following the back refs to the chunks. @@ -5956,11 +5781,31 @@ void btrfs_mapping_tree_free(struct btrfs_fs_info *fs_info) write_unlock(&fs_info->mapping_tree_lock); } +static int btrfs_chunk_map_num_copies(const struct btrfs_chunk_map *map) +{ + enum btrfs_raid_types index = btrfs_bg_flags_to_raid_index(map->type); + + if (map->type & BTRFS_BLOCK_GROUP_RAID5) + return 2; + + /* + * There could be two corrupted data stripes, we need to loop retry in + * order to rebuild the correct data. + * + * Fail a stripe at a time on every retry except the stripe under + * reconstruction. + */ + if (map->type & BTRFS_BLOCK_GROUP_RAID6) + return map->num_stripes; + + /* Non-RAID56, use their ncopies from btrfs_raid_array. */ + return btrfs_raid_array[index].ncopies; +} + int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len) { struct btrfs_chunk_map *map; - enum btrfs_raid_types index; - int ret = 1; + int ret; map = btrfs_get_chunk_map(fs_info, logical, len); if (IS_ERR(map)) @@ -5972,22 +5817,7 @@ int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len) */ return 1; - index = btrfs_bg_flags_to_raid_index(map->type); - - /* Non-RAID56, use their ncopies from btrfs_raid_array. */ - if (!(map->type & BTRFS_BLOCK_GROUP_RAID56_MASK)) - ret = btrfs_raid_array[index].ncopies; - else if (map->type & BTRFS_BLOCK_GROUP_RAID5) - ret = 2; - else if (map->type & BTRFS_BLOCK_GROUP_RAID6) - /* - * There could be two corrupted data stripes, we need - * to loop retry in order to rebuild the correct data. - * - * Fail a stripe at a time on every retry except the - * stripe under reconstruction. - */ - ret = map->num_stripes; + ret = btrfs_chunk_map_num_copies(map); btrfs_free_chunk_map(map); return ret; } @@ -6637,14 +6467,14 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, io_geom.stripe_index = 0; io_geom.op = op; - num_copies = btrfs_num_copies(fs_info, logical, fs_info->sectorsize); - if (io_geom.mirror_num > num_copies) - return -EINVAL; - map = btrfs_get_chunk_map(fs_info, logical, *length); if (IS_ERR(map)) return PTR_ERR(map); + num_copies = btrfs_chunk_map_num_copies(map); + if (io_geom.mirror_num > num_copies) + return -EINVAL; + map_offset = logical - map->start; io_geom.raid56_full_stripe_start = (u64)-1; max_len = btrfs_max_io_len(map, map_offset, &io_geom); diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 37a09ebb34dd..03d2d60afe0c 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -444,7 +444,7 @@ struct btrfs_io_stripe { /* Block mapping. */ u64 physical; u64 length; - bool is_scrub; + bool rst_search_commit_root; /* For the endio handler. */ struct btrfs_io_context *bioc; }; @@ -725,8 +725,6 @@ int btrfs_recover_balance(struct btrfs_fs_info *fs_info); int btrfs_pause_balance(struct btrfs_fs_info *fs_info); int btrfs_relocate_chunk(struct btrfs_fs_info *fs_info, u64 chunk_offset); int btrfs_cancel_balance(struct btrfs_fs_info *fs_info); -int btrfs_create_uuid_tree(struct btrfs_fs_info *fs_info); -int btrfs_uuid_scan_kthread(void *data); bool btrfs_chunk_writeable(struct btrfs_fs_info *fs_info, u64 chunk_offset); void btrfs_dev_stat_inc_and_print(struct btrfs_device *dev, int index); int btrfs_get_dev_stats(struct btrfs_fs_info *fs_info, diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index 738c7bb8ea7c..ce464cd8e0ac 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -120,7 +120,7 @@ int btrfs_setxattr(struct btrfs_trans_handle *trans, struct inode *inode, * locks the inode's i_mutex before calling setxattr or removexattr. */ if (flags & XATTR_REPLACE) { - ASSERT(inode_is_locked(inode)); + btrfs_assert_inode_locked(BTRFS_I(inode)); di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(BTRFS_I(inode)), name, name_len, 0); if (!di) diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c index 30971dd741e2..100abc00b794 100644 --- a/fs/btrfs/zlib.c +++ b/fs/btrfs/zlib.c @@ -20,6 +20,8 @@ #include <linux/refcount.h> #include "btrfs_inode.h" #include "compression.h" +#include "fs.h" +#include "subpage.h" /* workspace buffer size for s390 zlib hardware support */ #define ZLIB_DFLTCC_BUF_SIZE (4 * PAGE_SIZE) @@ -108,6 +110,7 @@ int zlib_compress_folios(struct list_head *ws, struct address_space *mapping, unsigned long len = *total_out; unsigned long nr_dest_folios = *out_folios; const unsigned long max_out = nr_dest_folios * PAGE_SIZE; + const u64 orig_end = start + len; *out_folios = 0; *total_out = 0; @@ -153,6 +156,10 @@ int zlib_compress_folios(struct list_head *ws, struct address_space *mapping, if (in_buf_folios > 1) { int i; + /* S390 hardware acceleration path, not subpage. */ + ASSERT(!btrfs_is_subpage( + inode_to_fs_info(mapping->host), + mapping)); for (i = 0; i < in_buf_folios; i++) { if (data_in) { kunmap_local(data_in); @@ -167,9 +174,14 @@ int zlib_compress_folios(struct list_head *ws, struct address_space *mapping, copy_page(workspace->buf + i * PAGE_SIZE, data_in); start += PAGE_SIZE; + workspace->strm.avail_in = + (in_buf_folios << PAGE_SHIFT); } workspace->strm.next_in = workspace->buf; } else { + unsigned int pg_off; + unsigned int cur_len; + if (data_in) { kunmap_local(data_in); folio_put(in_folio); @@ -179,12 +191,13 @@ int zlib_compress_folios(struct list_head *ws, struct address_space *mapping, start, &in_folio); if (ret < 0) goto out; - data_in = kmap_local_folio(in_folio, 0); + pg_off = offset_in_page(start); + cur_len = btrfs_calc_input_length(orig_end, start); + data_in = kmap_local_folio(in_folio, pg_off); start += PAGE_SIZE; workspace->strm.next_in = data_in; + workspace->strm.avail_in = cur_len; } - workspace->strm.avail_in = min(bytes_left, - (unsigned long) workspace->buf_size); } ret = zlib_deflate(&workspace->strm, Z_SYNC_FLUSH); @@ -380,7 +393,7 @@ done: } int zlib_decompress(struct list_head *ws, const u8 *data_in, - struct page *dest_page, unsigned long dest_pgoff, size_t srclen, + struct folio *dest_folio, unsigned long dest_pgoff, size_t srclen, size_t destlen) { struct workspace *workspace = list_entry(ws, struct workspace, list); @@ -408,12 +421,12 @@ int zlib_decompress(struct list_head *ws, const u8 *data_in, ret = zlib_inflateInit2(&workspace->strm, wbits); if (unlikely(ret != Z_OK)) { - struct btrfs_inode *inode = BTRFS_I(dest_page->mapping->host); + struct btrfs_inode *inode = folio_to_inode(dest_folio); btrfs_err(inode->root->fs_info, "zlib decompression init failed, error %d root %llu inode %llu offset %llu", ret, btrfs_root_id(inode->root), btrfs_ino(inode), - page_offset(dest_page)); + folio_pos(dest_folio)); return -EIO; } @@ -426,16 +439,16 @@ int zlib_decompress(struct list_head *ws, const u8 *data_in, if (ret != Z_STREAM_END) goto out; - memcpy_to_page(dest_page, dest_pgoff, workspace->buf, to_copy); + memcpy_to_folio(dest_folio, dest_pgoff, workspace->buf, to_copy); out: if (unlikely(to_copy != destlen)) { - struct btrfs_inode *inode = BTRFS_I(dest_page->mapping->host); + struct btrfs_inode *inode = folio_to_inode(dest_folio); btrfs_err(inode->root->fs_info, "zlib decompression failed, error %d root %llu inode %llu offset %llu decompressed %lu expected %zu", ret, btrfs_root_id(inode->root), btrfs_ino(inode), - page_offset(dest_page), to_copy, destlen); + folio_pos(dest_folio), to_copy, destlen); ret = -EIO; } else { ret = 0; @@ -444,7 +457,7 @@ out: zlib_inflateEnd(&workspace->strm); if (unlikely(to_copy < destlen)) - memzero_page(dest_page, dest_pgoff + to_copy, destlen - to_copy); + folio_zero_range(dest_folio, dest_pgoff + to_copy, destlen - to_copy); return ret; } diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 66f63e82af79..7fa2920632ba 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -287,7 +287,7 @@ static int btrfs_get_dev_zones(struct btrfs_device *device, u64 pos, /* The emulated zone size is determined from the size of device extent */ static int calculate_emulated_zone_size(struct btrfs_fs_info *fs_info) { - struct btrfs_path *path; + BTRFS_PATH_AUTO_FREE(path); struct btrfs_root *root = fs_info->dev_root; struct btrfs_key key; struct extent_buffer *leaf; @@ -304,28 +304,21 @@ static int calculate_emulated_zone_size(struct btrfs_fs_info *fs_info) ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) - goto out; + return ret; if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) { ret = btrfs_next_leaf(root, path); if (ret < 0) - goto out; + return ret; /* No dev extents at all? Not good */ - if (ret > 0) { - ret = -EUCLEAN; - goto out; - } + if (ret > 0) + return -EUCLEAN; } leaf = path->nodes[0]; dext = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dev_extent); fs_info->zone_size = btrfs_dev_extent_length(leaf, dext); - ret = 0; - -out: - btrfs_free_path(path); - - return ret; + return 0; } int btrfs_get_dev_zone_info_all_devices(struct btrfs_fs_info *fs_info) @@ -1211,7 +1204,7 @@ static int calculate_alloc_pointer(struct btrfs_block_group *cache, { struct btrfs_fs_info *fs_info = cache->fs_info; struct btrfs_root *root; - struct btrfs_path *path; + BTRFS_PATH_AUTO_FREE(path); struct btrfs_key key; struct btrfs_key found_key; int ret; @@ -1246,7 +1239,7 @@ static int calculate_alloc_pointer(struct btrfs_block_group *cache, if (!ret) ret = -EUCLEAN; if (ret < 0) - goto out; + return ret; ret = btrfs_previous_extent_item(root, path, cache->start); if (ret) { @@ -1254,7 +1247,7 @@ static int calculate_alloc_pointer(struct btrfs_block_group *cache, ret = 0; *offset_ret = 0; } - goto out; + return ret; } btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]); @@ -1266,15 +1259,10 @@ static int calculate_alloc_pointer(struct btrfs_block_group *cache, if (!(found_key.objectid >= cache->start && found_key.objectid + length <= cache->start + cache->length)) { - ret = -EUCLEAN; - goto out; + return -EUCLEAN; } *offset_ret = found_key.objectid + length - cache->start; - ret = 0; - -out: - btrfs_free_path(path); - return ret; + return 0; } struct zone_info { @@ -1406,6 +1394,8 @@ static int btrfs_load_block_group_dup(struct btrfs_block_group *bg, return -EINVAL; } + bg->zone_capacity = min_not_zero(zone_info[0].capacity, zone_info[1].capacity); + if (zone_info[0].alloc_offset == WP_MISSING_DEV) { btrfs_err(bg->fs_info, "zoned: cannot recover write pointer for zone %llu", @@ -1432,7 +1422,6 @@ static int btrfs_load_block_group_dup(struct btrfs_block_group *bg, } bg->alloc_offset = zone_info[0].alloc_offset; - bg->zone_capacity = min(zone_info[0].capacity, zone_info[1].capacity); return 0; } @@ -1450,6 +1439,9 @@ static int btrfs_load_block_group_raid1(struct btrfs_block_group *bg, return -EINVAL; } + /* In case a device is missing we have a cap of 0, so don't use it. */ + bg->zone_capacity = min_not_zero(zone_info[0].capacity, zone_info[1].capacity); + for (i = 0; i < map->num_stripes; i++) { if (zone_info[i].alloc_offset == WP_MISSING_DEV || zone_info[i].alloc_offset == WP_CONVENTIONAL) @@ -1471,9 +1463,6 @@ static int btrfs_load_block_group_raid1(struct btrfs_block_group *bg, if (test_bit(0, active)) set_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &bg->runtime_flags); } - /* In case a device is missing we have a cap of 0, so don't use it. */ - bg->zone_capacity = min_not_zero(zone_info[0].capacity, - zone_info[1].capacity); } if (zone_info[0].alloc_offset != WP_MISSING_DEV) @@ -1563,6 +1552,7 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) unsigned long *active = NULL; u64 last_alloc = 0; u32 num_sequential = 0, num_conventional = 0; + u64 profile; if (!btrfs_is_zoned(fs_info)) return 0; @@ -1623,7 +1613,8 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) } } - switch (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) { + profile = map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK; + switch (profile) { case 0: /* single */ ret = btrfs_load_block_group_single(cache, &zone_info[0], active); break; @@ -1650,6 +1641,23 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) goto out; } + if (ret == -EIO && profile != 0 && profile != BTRFS_BLOCK_GROUP_RAID0 && + profile != BTRFS_BLOCK_GROUP_RAID10) { + /* + * Detected broken write pointer. Make this block group + * unallocatable by setting the allocation pointer at the end of + * allocatable region. Relocating this block group will fix the + * mismatch. + * + * Currently, we cannot handle RAID0 or RAID10 case like this + * because we don't have a proper zone_capacity value. But, + * reading from this block group won't work anyway by a missing + * stripe. + */ + cache->alloc_offset = cache->zone_capacity; + ret = 0; + } + out: /* Reject non SINGLE data profiles without RST */ if ((map->type & BTRFS_BLOCK_GROUP_DATA) && @@ -2439,7 +2447,7 @@ void btrfs_free_zone_cache(struct btrfs_fs_info *fs_info) mutex_unlock(&fs_devices->device_list_mutex); } -bool btrfs_zoned_should_reclaim(struct btrfs_fs_info *fs_info) +bool btrfs_zoned_should_reclaim(const struct btrfs_fs_info *fs_info) { struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; struct btrfs_device *device; diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h index 30b2e48a1cec..7612e6572605 100644 --- a/fs/btrfs/zoned.h +++ b/fs/btrfs/zoned.h @@ -89,7 +89,7 @@ void btrfs_schedule_zone_finish_bg(struct btrfs_block_group *bg, struct extent_buffer *eb); void btrfs_clear_data_reloc_bg(struct btrfs_block_group *bg); void btrfs_free_zone_cache(struct btrfs_fs_info *fs_info); -bool btrfs_zoned_should_reclaim(struct btrfs_fs_info *fs_info); +bool btrfs_zoned_should_reclaim(const struct btrfs_fs_info *fs_info); void btrfs_zoned_release_data_reloc_bg(struct btrfs_fs_info *fs_info, u64 logical, u64 length); int btrfs_zone_finish_one_bg(struct btrfs_fs_info *fs_info); @@ -242,7 +242,7 @@ static inline void btrfs_clear_data_reloc_bg(struct btrfs_block_group *bg) { } static inline void btrfs_free_zone_cache(struct btrfs_fs_info *fs_info) { } -static inline bool btrfs_zoned_should_reclaim(struct btrfs_fs_info *fs_info) +static inline bool btrfs_zoned_should_reclaim(const struct btrfs_fs_info *fs_info) { return false; } diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c index 2a079561b2b1..866607fd3e58 100644 --- a/fs/btrfs/zstd.c +++ b/fs/btrfs/zstd.c @@ -389,7 +389,10 @@ int zstd_compress_folios(struct list_head *ws, struct address_space *mapping, unsigned long tot_out = 0; unsigned long len = *total_out; const unsigned long nr_dest_folios = *out_folios; + const u64 orig_end = start + len; unsigned long max_out = nr_dest_folios * PAGE_SIZE; + unsigned int pg_off; + unsigned int cur_len; zstd_parameters params = zstd_get_btrfs_parameters(workspace->req_level, len); @@ -415,9 +418,11 @@ int zstd_compress_folios(struct list_head *ws, struct address_space *mapping, ret = btrfs_compress_filemap_get_folio(mapping, start, &in_folio); if (ret < 0) goto out; - workspace->in_buf.src = kmap_local_folio(in_folio, 0); + pg_off = offset_in_page(start); + cur_len = btrfs_calc_input_length(orig_end, start); + workspace->in_buf.src = kmap_local_folio(in_folio, pg_off); workspace->in_buf.pos = 0; - workspace->in_buf.size = min_t(size_t, len, PAGE_SIZE); + workspace->in_buf.size = cur_len; /* Allocate and map in the output buffer */ out_folio = btrfs_alloc_compr_folio(); @@ -494,14 +499,16 @@ int zstd_compress_folios(struct list_head *ws, struct address_space *mapping, kunmap_local(workspace->in_buf.src); workspace->in_buf.src = NULL; folio_put(in_folio); - start += PAGE_SIZE; - len -= PAGE_SIZE; + start += cur_len; + len -= cur_len; ret = btrfs_compress_filemap_get_folio(mapping, start, &in_folio); if (ret < 0) goto out; - workspace->in_buf.src = kmap_local_folio(in_folio, 0); + pg_off = offset_in_page(start); + cur_len = btrfs_calc_input_length(orig_end, start); + workspace->in_buf.src = kmap_local_folio(in_folio, pg_off); workspace->in_buf.pos = 0; - workspace->in_buf.size = min_t(size_t, len, PAGE_SIZE); + workspace->in_buf.size = cur_len; } } while (1) { @@ -649,11 +656,11 @@ done: } int zstd_decompress(struct list_head *ws, const u8 *data_in, - struct page *dest_page, unsigned long dest_pgoff, size_t srclen, + struct folio *dest_folio, unsigned long dest_pgoff, size_t srclen, size_t destlen) { struct workspace *workspace = list_entry(ws, struct workspace, list); - struct btrfs_fs_info *fs_info = btrfs_sb(dest_page->mapping->host->i_sb); + struct btrfs_fs_info *fs_info = btrfs_sb(folio_inode(dest_folio)->i_sb); const u32 sectorsize = fs_info->sectorsize; zstd_dstream *stream; int ret = 0; @@ -662,12 +669,12 @@ int zstd_decompress(struct list_head *ws, const u8 *data_in, stream = zstd_init_dstream( ZSTD_BTRFS_MAX_INPUT, workspace->mem, workspace->size); if (unlikely(!stream)) { - struct btrfs_inode *inode = BTRFS_I(dest_page->mapping->host); + struct btrfs_inode *inode = folio_to_inode(dest_folio); btrfs_err(inode->root->fs_info, "zstd decompression init failed, root %llu inode %llu offset %llu", btrfs_root_id(inode->root), btrfs_ino(inode), - page_offset(dest_page)); + folio_pos(dest_folio)); ret = -EIO; goto finish; } @@ -686,21 +693,21 @@ int zstd_decompress(struct list_head *ws, const u8 *data_in, */ ret = zstd_decompress_stream(stream, &workspace->out_buf, &workspace->in_buf); if (unlikely(zstd_is_error(ret))) { - struct btrfs_inode *inode = BTRFS_I(dest_page->mapping->host); + struct btrfs_inode *inode = folio_to_inode(dest_folio); btrfs_err(inode->root->fs_info, "zstd decompression failed, error %d root %llu inode %llu offset %llu", zstd_get_error_code(ret), btrfs_root_id(inode->root), - btrfs_ino(inode), page_offset(dest_page)); + btrfs_ino(inode), folio_pos(dest_folio)); goto finish; } to_copy = workspace->out_buf.pos; - memcpy_to_page(dest_page, dest_pgoff, workspace->out_buf.dst, to_copy); + memcpy_to_folio(dest_folio, dest_pgoff, workspace->out_buf.dst, to_copy); finish: /* Error or early end. */ if (unlikely(to_copy < destlen)) { ret = -EIO; - memzero_page(dest_page, dest_pgoff + to_copy, destlen - to_copy); + folio_zero_range(dest_folio, dest_pgoff + to_copy, destlen - to_copy); } return ret; } |