diff options
Diffstat (limited to 'fs/btrfs')
-rw-r--r-- | fs/btrfs/block-group.c | 40 | ||||
-rw-r--r-- | fs/btrfs/block-group.h | 4 | ||||
-rw-r--r-- | fs/btrfs/btrfs_inode.h | 11 | ||||
-rw-r--r-- | fs/btrfs/compression.c | 8 | ||||
-rw-r--r-- | fs/btrfs/ctree.h | 1 | ||||
-rw-r--r-- | fs/btrfs/dev-replace.c | 7 | ||||
-rw-r--r-- | fs/btrfs/disk-io.c | 17 | ||||
-rw-r--r-- | fs/btrfs/extent-tree.c | 2 | ||||
-rw-r--r-- | fs/btrfs/extent_io.c | 44 | ||||
-rw-r--r-- | fs/btrfs/inode.c | 42 | ||||
-rw-r--r-- | fs/btrfs/ioctl.c | 2 | ||||
-rw-r--r-- | fs/btrfs/props.c | 59 | ||||
-rw-r--r-- | fs/btrfs/props.h | 4 | ||||
-rw-r--r-- | fs/btrfs/scrub.c | 26 | ||||
-rw-r--r-- | fs/btrfs/sysfs.c | 3 | ||||
-rw-r--r-- | fs/btrfs/tree-log.c | 54 | ||||
-rw-r--r-- | fs/btrfs/volumes.c | 2 | ||||
-rw-r--r-- | fs/btrfs/volumes.h | 3 | ||||
-rw-r--r-- | fs/btrfs/xattr.c | 11 | ||||
-rw-r--r-- | fs/btrfs/zoned.c | 34 | ||||
-rw-r--r-- | fs/btrfs/zoned.h | 4 |
21 files changed, 269 insertions, 109 deletions
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index c22d287e020b..0dd6de994199 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -2503,12 +2503,6 @@ struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *tran return ERR_PTR(ret); } - /* - * New block group is likely to be used soon. Try to activate it now. - * Failure is OK for now. - */ - btrfs_zone_activate(cache); - ret = exclude_super_stripes(cache); if (ret) { /* We may have excluded something, so call this just in case */ @@ -2946,7 +2940,6 @@ int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans) struct btrfs_path *path = NULL; LIST_HEAD(dirty); struct list_head *io = &cur_trans->io_bgs; - int num_started = 0; int loops = 0; spin_lock(&cur_trans->dirty_bgs_lock); @@ -3012,7 +3005,6 @@ again: cache->io_ctl.inode = NULL; ret = btrfs_write_out_cache(trans, cache, path); if (ret == 0 && cache->io_ctl.inode) { - num_started++; should_put = 0; /* @@ -3113,7 +3105,6 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans) int should_put; struct btrfs_path *path; struct list_head *io = &cur_trans->io_bgs; - int num_started = 0; path = btrfs_alloc_path(); if (!path) @@ -3171,7 +3162,6 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans) cache->io_ctl.inode = NULL; ret = btrfs_write_out_cache(trans, cache, path); if (ret == 0 && cache->io_ctl.inode) { - num_started++; should_put = 0; list_add_tail(&cache->io_list, io); } else { @@ -3455,7 +3445,7 @@ int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans, u64 type) return btrfs_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE); } -static int do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags) +static struct btrfs_block_group *do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags) { struct btrfs_block_group *bg; int ret; @@ -3542,7 +3532,11 @@ static int do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags) out: btrfs_trans_release_chunk_metadata(trans); - return ret; + if (ret) + return ERR_PTR(ret); + + btrfs_get_block_group(bg); + return bg; } /* @@ -3657,10 +3651,17 @@ int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags, { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_space_info *space_info; + struct btrfs_block_group *ret_bg; bool wait_for_alloc = false; bool should_alloc = false; + bool from_extent_allocation = false; int ret = 0; + if (force == CHUNK_ALLOC_FORCE_FOR_EXTENT) { + from_extent_allocation = true; + force = CHUNK_ALLOC_FORCE; + } + /* Don't re-enter if we're already allocating a chunk */ if (trans->allocating_chunk) return -ENOSPC; @@ -3750,9 +3751,22 @@ int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags, force_metadata_allocation(fs_info); } - ret = do_chunk_alloc(trans, flags); + ret_bg = do_chunk_alloc(trans, flags); trans->allocating_chunk = false; + if (IS_ERR(ret_bg)) { + ret = PTR_ERR(ret_bg); + } else if (from_extent_allocation) { + /* + * New block group is likely to be used soon. Try to activate + * it now. Failure is OK for now. + */ + btrfs_zone_activate(ret_bg); + } + + if (!ret) + btrfs_put_block_group(ret_bg); + spin_lock(&space_info->lock); if (ret < 0) { if (ret == -ENOSPC) diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index 93aabc68bb6a..e8308f2ad07d 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -35,11 +35,15 @@ enum btrfs_discard_state { * the FS with empty chunks * * CHUNK_ALLOC_FORCE means it must try to allocate one + * + * CHUNK_ALLOC_FORCE_FOR_EXTENT like CHUNK_ALLOC_FORCE but called from + * find_free_extent() that also activaes the zone */ enum btrfs_chunk_alloc_enum { CHUNK_ALLOC_NO_FORCE, CHUNK_ALLOC_LIMITED, CHUNK_ALLOC_FORCE, + CHUNK_ALLOC_FORCE_FOR_EXTENT, }; struct btrfs_caching_control { diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index 47e72d72f7d0..32131a5d321b 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -384,6 +384,17 @@ static inline bool btrfs_inode_in_log(struct btrfs_inode *inode, u64 generation) return ret; } +/* + * Check if the inode has flags compatible with compression + */ +static inline bool btrfs_inode_can_compress(const struct btrfs_inode *inode) +{ + if (inode->flags & BTRFS_INODE_NODATACOW || + inode->flags & BTRFS_INODE_NODATASUM) + return false; + return true; +} + struct btrfs_dio_private { struct inode *inode; diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index be476f094300..19bf36d8ffea 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -537,6 +537,9 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start, cb->orig_bio = NULL; cb->nr_pages = nr_pages; + if (blkcg_css) + kthread_associate_blkcg(blkcg_css); + while (cur_disk_bytenr < disk_start + compressed_len) { u64 offset = cur_disk_bytenr - disk_start; unsigned int index = offset >> PAGE_SHIFT; @@ -555,6 +558,8 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start, bio = NULL; goto finish_cb; } + if (blkcg_css) + bio->bi_opf |= REQ_CGROUP_PUNT; } /* * We should never reach next_stripe_start start as we will @@ -612,6 +617,9 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start, return 0; finish_cb: + if (blkcg_css) + kthread_associate_blkcg(NULL); + if (bio) { bio->bi_status = ret; bio_endio(bio); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index b7631b88426e..077c95e9baa5 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1060,6 +1060,7 @@ struct btrfs_fs_info { */ spinlock_t relocation_bg_lock; u64 data_reloc_bg; + struct mutex zoned_data_reloc_io_lock; u64 nr_global_roots; diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 71fd99b48283..f26202621989 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -734,7 +734,12 @@ static int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info, btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1); - /* Commit dev_replace state and reserve 1 item for it. */ + /* + * Commit dev_replace state and reserve 1 item for it. + * This is crucial to ensure we won't miss copying extents for new block + * groups that are allocated after we started the device replace, and + * must be done after setting up the device replace state. + */ trans = btrfs_start_transaction(root, 1); if (IS_ERR(trans)) { ret = PTR_ERR(trans); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index b30309f187cf..31c3f592e587 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1850,9 +1850,10 @@ again: ret = btrfs_insert_fs_root(fs_info, root); if (ret) { - btrfs_put_root(root); - if (ret == -EEXIST) + if (ret == -EEXIST) { + btrfs_put_root(root); goto again; + } goto fail; } return root; @@ -3156,6 +3157,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info) mutex_init(&fs_info->reloc_mutex); mutex_init(&fs_info->delalloc_root_mutex); mutex_init(&fs_info->zoned_meta_io_lock); + mutex_init(&fs_info->zoned_data_reloc_io_lock); seqlock_init(&fs_info->profiles_lock); INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots); @@ -3656,6 +3658,17 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device if (sectorsize < PAGE_SIZE) { struct btrfs_subpage_info *subpage_info; + /* + * V1 space cache has some hardcoded PAGE_SIZE usage, and is + * going to be deprecated. + * + * Force to use v2 cache for subpage case. + */ + btrfs_clear_opt(fs_info->mount_opt, SPACE_CACHE); + btrfs_set_and_info(fs_info, FREE_SPACE_TREE, + "forcing free space tree for sector size %u with page size %lu", + sectorsize, PAGE_SIZE); + btrfs_warn(fs_info, "read-write for sector size %u with page size %lu is experimental", sectorsize, PAGE_SIZE); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index f477035a2ac2..6aa92f84f465 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4082,7 +4082,7 @@ static int find_free_extent_update_loop(struct btrfs_fs_info *fs_info, } ret = btrfs_chunk_alloc(trans, ffe_ctl->flags, - CHUNK_ALLOC_FORCE); + CHUNK_ALLOC_FORCE_FOR_EXTENT); /* Do not bail out on ENOSPC since we can do more. */ if (ret == -ENOSPC) diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 724e8fe06aa0..33c19f51d79b 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2658,6 +2658,7 @@ int btrfs_repair_one_sector(struct inode *inode, repair_bio = btrfs_bio_alloc(1); repair_bbio = btrfs_bio(repair_bio); + repair_bbio->file_offset = start; repair_bio->bi_opf = REQ_OP_READ; repair_bio->bi_end_io = failed_bio->bi_end_io; repair_bio->bi_iter.bi_sector = failrec->logical >> 9; @@ -3333,24 +3334,37 @@ static int alloc_new_bio(struct btrfs_inode *inode, ret = calc_bio_boundaries(bio_ctrl, inode, file_offset); if (ret < 0) goto error; - if (wbc) { - struct block_device *bdev; - bdev = fs_info->fs_devices->latest_dev->bdev; - bio_set_dev(bio, bdev); - wbc_init_bio(wbc, bio); - } - if (bio_op(bio) == REQ_OP_ZONE_APPEND) { - struct btrfs_device *device; + if (wbc) { + /* + * For Zone append we need the correct block_device that we are + * going to write to set in the bio to be able to respect the + * hardware limitation. Look it up here: + */ + if (bio_op(bio) == REQ_OP_ZONE_APPEND) { + struct btrfs_device *dev; + + dev = btrfs_zoned_get_device(fs_info, disk_bytenr, + fs_info->sectorsize); + if (IS_ERR(dev)) { + ret = PTR_ERR(dev); + goto error; + } - device = btrfs_zoned_get_device(fs_info, disk_bytenr, - fs_info->sectorsize); - if (IS_ERR(device)) { - ret = PTR_ERR(device); - goto error; + bio_set_dev(bio, dev->bdev); + } else { + /* + * Otherwise pick the last added device to support + * cgroup writeback. For multi-device file systems this + * means blk-cgroup policies have to always be set on the + * last added/replaced device. This is a bit odd but has + * been like that for a long time. + */ + bio_set_dev(bio, fs_info->fs_devices->latest_dev->bdev); } - - btrfs_bio(bio)->device = device; + wbc_init_bio(wbc, bio); + } else { + ASSERT(bio_op(bio) != REQ_OP_ZONE_APPEND); } return 0; error: diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 17d5557f98ec..95c499b8424e 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -481,17 +481,6 @@ static noinline int add_async_extent(struct async_chunk *cow, } /* - * Check if the inode has flags compatible with compression - */ -static inline bool inode_can_compress(struct btrfs_inode *inode) -{ - if (inode->flags & BTRFS_INODE_NODATACOW || - inode->flags & BTRFS_INODE_NODATASUM) - return false; - return true; -} - -/* * Check if the inode needs to be submitted to compression, based on mount * options, defragmentation, properties or heuristics. */ @@ -500,7 +489,7 @@ static inline int inode_need_compress(struct btrfs_inode *inode, u64 start, { struct btrfs_fs_info *fs_info = inode->root->fs_info; - if (!inode_can_compress(inode)) { + if (!btrfs_inode_can_compress(inode)) { WARN(IS_ENABLED(CONFIG_BTRFS_DEBUG), KERN_ERR "BTRFS: unexpected compression for ino %llu\n", btrfs_ino(inode)); @@ -2016,11 +2005,10 @@ int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page * to use run_delalloc_nocow() here, like for regular * preallocated inodes. */ - ASSERT(!zoned || - (zoned && btrfs_is_data_reloc_root(inode->root))); + ASSERT(!zoned || btrfs_is_data_reloc_root(inode->root)); ret = run_delalloc_nocow(inode, locked_page, start, end, page_started, nr_written); - } else if (!inode_can_compress(inode) || + } else if (!btrfs_inode_can_compress(inode) || !inode_need_compress(inode, start, end)) { if (zoned) ret = run_delalloc_zoned(inode, locked_page, start, end, @@ -7444,6 +7432,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, u64 block_start, orig_start, orig_block_len, ram_bytes; bool can_nocow = false; bool space_reserved = false; + u64 prev_len; int ret = 0; /* @@ -7471,6 +7460,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, can_nocow = true; } + prev_len = len; if (can_nocow) { struct extent_map *em2; @@ -7500,8 +7490,6 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, goto out; } } else { - const u64 prev_len = len; - /* Our caller expects us to free the input extent map. */ free_extent_map(em); *map = NULL; @@ -7532,7 +7520,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, * We have created our ordered extent, so we can now release our reservation * for an outstanding extent. */ - btrfs_delalloc_release_extents(BTRFS_I(inode), len); + btrfs_delalloc_release_extents(BTRFS_I(inode), prev_len); /* * Need to update the i_size under the extent lock so buffered @@ -7811,8 +7799,6 @@ static blk_status_t btrfs_check_read_dio_bio(struct btrfs_dio_private *dip, const bool csum = !(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM); struct bio_vec bvec; struct bvec_iter iter; - const u64 orig_file_offset = dip->file_offset; - u64 start = orig_file_offset; u32 bio_offset = 0; blk_status_t err = BLK_STS_OK; @@ -7822,6 +7808,8 @@ static blk_status_t btrfs_check_read_dio_bio(struct btrfs_dio_private *dip, nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec.bv_len); pgoff = bvec.bv_offset; for (i = 0; i < nr_sectors; i++) { + u64 start = bbio->file_offset + bio_offset; + ASSERT(pgoff < PAGE_SIZE); if (uptodate && (!csum || !check_data_csum(inode, bbio, @@ -7834,17 +7822,13 @@ static blk_status_t btrfs_check_read_dio_bio(struct btrfs_dio_private *dip, } else { int ret; - ASSERT((start - orig_file_offset) < UINT_MAX); - ret = btrfs_repair_one_sector(inode, - &bbio->bio, - start - orig_file_offset, - bvec.bv_page, pgoff, + ret = btrfs_repair_one_sector(inode, &bbio->bio, + bio_offset, bvec.bv_page, pgoff, start, bbio->mirror_num, submit_dio_repair_bio); if (ret) err = errno_to_blk_status(ret); } - start += sectorsize; ASSERT(bio_offset + sectorsize > bio_offset); bio_offset += sectorsize; pgoff += sectorsize; @@ -7871,6 +7855,7 @@ static blk_status_t btrfs_submit_bio_start_direct_io(struct inode *inode, static void btrfs_end_dio_bio(struct bio *bio) { struct btrfs_dio_private *dip = bio->bi_private; + struct btrfs_bio *bbio = btrfs_bio(bio); blk_status_t err = bio->bi_status; if (err) @@ -7881,12 +7866,12 @@ static void btrfs_end_dio_bio(struct bio *bio) bio->bi_iter.bi_size, err); if (bio_op(bio) == REQ_OP_READ) - err = btrfs_check_read_dio_bio(dip, btrfs_bio(bio), !err); + err = btrfs_check_read_dio_bio(dip, bbio, !err); if (err) dip->dio_bio->bi_status = err; - btrfs_record_physical_zoned(dip->inode, dip->file_offset, bio); + btrfs_record_physical_zoned(dip->inode, bbio->file_offset, bio); bio_put(bio); btrfs_dio_private_put(dip); @@ -8047,6 +8032,7 @@ static void btrfs_submit_direct(const struct iomap_iter *iter, bio = btrfs_bio_clone_partial(dio_bio, clone_offset, clone_len); bio->bi_private = dip; bio->bi_end_io = btrfs_end_dio_bio; + btrfs_bio(bio)->file_offset = file_offset; if (bio_op(bio) == REQ_OP_ZONE_APPEND) { status = extract_ordered_extent(BTRFS_I(inode), bio, diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index f46e71061942..be6c24577dbe 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -5456,8 +5456,6 @@ long btrfs_ioctl(struct file *file, unsigned int return btrfs_ioctl_fs_info(fs_info, argp); case BTRFS_IOC_DEV_INFO: return btrfs_ioctl_dev_info(fs_info, argp); - case BTRFS_IOC_BALANCE: - return btrfs_ioctl_balance(file, NULL); case BTRFS_IOC_TREE_SEARCH: return btrfs_ioctl_tree_search(inode, argp); case BTRFS_IOC_TREE_SEARCH_V2: diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c index 1a6d2d5b4b33..1b31481f9e72 100644 --- a/fs/btrfs/props.c +++ b/fs/btrfs/props.c @@ -17,9 +17,11 @@ static DEFINE_HASHTABLE(prop_handlers_ht, BTRFS_PROP_HANDLERS_HT_BITS); struct prop_handler { struct hlist_node node; const char *xattr_name; - int (*validate)(const char *value, size_t len); + int (*validate)(const struct btrfs_inode *inode, const char *value, + size_t len); int (*apply)(struct inode *inode, const char *value, size_t len); const char *(*extract)(struct inode *inode); + bool (*ignore)(const struct btrfs_inode *inode); int inheritable; }; @@ -55,7 +57,8 @@ find_prop_handler(const char *name, return NULL; } -int btrfs_validate_prop(const char *name, const char *value, size_t value_len) +int btrfs_validate_prop(const struct btrfs_inode *inode, const char *name, + const char *value, size_t value_len) { const struct prop_handler *handler; @@ -69,7 +72,29 @@ int btrfs_validate_prop(const char *name, const char *value, size_t value_len) if (value_len == 0) return 0; - return handler->validate(value, value_len); + return handler->validate(inode, value, value_len); +} + +/* + * Check if a property should be ignored (not set) for an inode. + * + * @inode: The target inode. + * @name: The property's name. + * + * The caller must be sure the given property name is valid, for example by + * having previously called btrfs_validate_prop(). + * + * Returns: true if the property should be ignored for the given inode + * false if the property must not be ignored for the given inode + */ +bool btrfs_ignore_prop(const struct btrfs_inode *inode, const char *name) +{ + const struct prop_handler *handler; + + handler = find_prop_handler(name, NULL); + ASSERT(handler != NULL); + + return handler->ignore(inode); } int btrfs_set_prop(struct btrfs_trans_handle *trans, struct inode *inode, @@ -252,8 +277,12 @@ int btrfs_load_inode_props(struct inode *inode, struct btrfs_path *path) return ret; } -static int prop_compression_validate(const char *value, size_t len) +static int prop_compression_validate(const struct btrfs_inode *inode, + const char *value, size_t len) { + if (!btrfs_inode_can_compress(inode)) + return -EINVAL; + if (!value) return 0; @@ -310,6 +339,22 @@ static int prop_compression_apply(struct inode *inode, const char *value, return 0; } +static bool prop_compression_ignore(const struct btrfs_inode *inode) +{ + /* + * Compression only has effect for regular files, and for directories + * we set it just to propagate it to new files created inside them. + * Everything else (symlinks, devices, sockets, fifos) is pointless as + * it will do nothing, so don't waste metadata space on a compression + * xattr for anything that is neither a file nor a directory. + */ + if (!S_ISREG(inode->vfs_inode.i_mode) && + !S_ISDIR(inode->vfs_inode.i_mode)) + return true; + + return false; +} + static const char *prop_compression_extract(struct inode *inode) { switch (BTRFS_I(inode)->prop_compress) { @@ -330,6 +375,7 @@ static struct prop_handler prop_handlers[] = { .validate = prop_compression_validate, .apply = prop_compression_apply, .extract = prop_compression_extract, + .ignore = prop_compression_ignore, .inheritable = 1 }, }; @@ -356,6 +402,9 @@ static int inherit_props(struct btrfs_trans_handle *trans, if (!h->inheritable) continue; + if (h->ignore(BTRFS_I(inode))) + continue; + value = h->extract(parent); if (!value) continue; @@ -364,7 +413,7 @@ static int inherit_props(struct btrfs_trans_handle *trans, * This is not strictly necessary as the property should be * valid, but in case it isn't, don't propagate it further. */ - ret = h->validate(value, strlen(value)); + ret = h->validate(BTRFS_I(inode), value, strlen(value)); if (ret) continue; diff --git a/fs/btrfs/props.h b/fs/btrfs/props.h index 40b2c65b518c..59bea741cfcf 100644 --- a/fs/btrfs/props.h +++ b/fs/btrfs/props.h @@ -13,7 +13,9 @@ void __init btrfs_props_init(void); int btrfs_set_prop(struct btrfs_trans_handle *trans, struct inode *inode, const char *name, const char *value, size_t value_len, int flags); -int btrfs_validate_prop(const char *name, const char *value, size_t value_len); +int btrfs_validate_prop(const struct btrfs_inode *inode, const char *name, + const char *value, size_t value_len); +bool btrfs_ignore_prop(const struct btrfs_inode *inode, const char *name); int btrfs_load_inode_props(struct inode *inode, struct btrfs_path *path); diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 11089568b287..8cd713d37ad2 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -3699,6 +3699,31 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, if (!cache) goto skip; + ASSERT(cache->start <= chunk_offset); + /* + * We are using the commit root to search for device extents, so + * that means we could have found a device extent item from a + * block group that was deleted in the current transaction. The + * logical start offset of the deleted block group, stored at + * @chunk_offset, might be part of the logical address range of + * a new block group (which uses different physical extents). + * In this case btrfs_lookup_block_group() has returned the new + * block group, and its start address is less than @chunk_offset. + * + * We skip such new block groups, because it's pointless to + * process them, as we won't find their extents because we search + * for them using the commit root of the extent tree. For a device + * replace it's also fine to skip it, we won't miss copying them + * to the target device because we have the write duplication + * setup through the regular write path (by btrfs_map_block()), + * and we have committed a transaction when we started the device + * replace, right after setting up the device replace state. + */ + if (cache->start < chunk_offset) { + btrfs_put_block_group(cache); + goto skip; + } + if (sctx->is_dev_replace && btrfs_is_zoned(fs_info)) { spin_lock(&cache->lock); if (!cache->to_copy) { @@ -3822,7 +3847,6 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, dev_replace->item_needs_writeback = 1; up_write(&dev_replace->rwsem); - ASSERT(cache->start == chunk_offset); ret = scrub_chunk(sctx, cache, scrub_dev, found_key.offset, dev_extent_len); diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 17389a42a3ab..ba78ca5aabbb 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -922,6 +922,9 @@ static ssize_t btrfs_exclusive_operation_show(struct kobject *kobj, case BTRFS_EXCLOP_BALANCE: str = "balance\n"; break; + case BTRFS_EXCLOP_BALANCE_PAUSED: + str = "balance paused\n"; + break; case BTRFS_EXCLOP_DEV_ADD: str = "device add\n"; break; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 571dae8ad65e..e65633686378 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3188,6 +3188,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, ret = btrfs_alloc_log_tree_node(trans, log_root_tree); if (ret) { mutex_unlock(&fs_info->tree_root->log_mutex); + blk_finish_plug(&plug); goto out; } } @@ -3720,11 +3721,29 @@ static noinline int insert_dir_log_key(struct btrfs_trans_handle *trans, key.offset = first_offset; key.type = BTRFS_DIR_LOG_INDEX_KEY; ret = btrfs_insert_empty_item(trans, log, path, &key, sizeof(*item)); - if (ret) + /* + * -EEXIST is fine and can happen sporadically when we are logging a + * directory and have concurrent insertions in the subvolume's tree for + * items from other inodes and that result in pushing off some dir items + * from one leaf to another in order to accommodate for the new items. + * This results in logging the same dir index range key. + */ + if (ret && ret != -EEXIST) return ret; item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_dir_log_item); + if (ret == -EEXIST) { + const u64 curr_end = btrfs_dir_log_end(path->nodes[0], item); + + /* + * btrfs_del_dir_entries_in_log() might have been called during + * an unlink between the initial insertion of this key and the + * current update, or we might be logging a single entry deletion + * during a rename, so set the new last_offset to the max value. + */ + last_offset = max(last_offset, curr_end); + } btrfs_set_dir_log_end(path->nodes[0], item, last_offset); btrfs_mark_buffer_dirty(path->nodes[0]); btrfs_release_path(path); @@ -3848,13 +3867,6 @@ static int process_dir_items_leaf(struct btrfs_trans_handle *trans, ret = insert_dir_log_key(trans, log, dst_path, ino, *last_old_dentry_offset + 1, key.offset - 1); - /* - * -EEXIST should never happen because when we - * log a directory in full mode (LOG_INODE_ALL) - * we drop all BTRFS_DIR_LOG_INDEX_KEY keys from - * the log tree. - */ - ASSERT(ret != -EEXIST); if (ret < 0) return ret; } @@ -5804,6 +5816,18 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, } /* + * For symlinks, we must always log their content, which is stored in an + * inline extent, otherwise we could end up with an empty symlink after + * log replay, which is invalid on linux (symlink(2) returns -ENOENT if + * one attempts to create an empty symlink). + * We don't need to worry about flushing delalloc, because when we create + * the inline extent when the symlink is created (we never have delalloc + * for symlinks). + */ + if (S_ISLNK(inode->vfs_inode.i_mode)) + inode_only = LOG_INODE_ALL; + + /* * Before logging the inode item, cache the value returned by * inode_logged(), because after that we have the need to figure out if * the inode was previously logged in this transaction. @@ -6181,7 +6205,7 @@ again: } ctx->log_new_dentries = false; - if (type == BTRFS_FT_DIR || type == BTRFS_FT_SYMLINK) + if (type == BTRFS_FT_DIR) log_mode = LOG_INODE_ALL; ret = btrfs_log_inode(trans, BTRFS_I(di_inode), log_mode, ctx); @@ -7018,12 +7042,12 @@ void btrfs_log_new_name(struct btrfs_trans_handle *trans, /* * Other concurrent task might be logging the old directory, * as it can be triggered when logging other inode that had or - * still has a dentry in the old directory. So take the old - * directory's log_mutex to prevent getting an -EEXIST when - * logging a key to record the deletion, or having that other - * task logging the old directory get an -EEXIST if it attempts - * to log the same key after we just did it. In both cases that - * would result in falling back to a transaction commit. + * still has a dentry in the old directory. We lock the old + * directory's log_mutex to ensure the deletion of the old + * name is persisted, because during directory logging we + * delete all BTRFS_DIR_LOG_INDEX_KEY keys and the deletion of + * the old name's dir index item is in the delayed items, so + * it could be missed by an in progress directory logging. */ mutex_lock(&old_dir->log_mutex); ret = del_logged_dentry(trans, log, path, btrfs_ino(old_dir), diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 2cfbc74a3b4e..a8cc736731fd 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -4430,10 +4430,12 @@ static int balance_kthread(void *data) struct btrfs_fs_info *fs_info = data; int ret = 0; + sb_start_write(fs_info->sb); mutex_lock(&fs_info->balance_mutex); if (fs_info->balance_ctl) ret = btrfs_balance(fs_info, fs_info->balance_ctl, NULL); mutex_unlock(&fs_info->balance_mutex); + sb_end_write(fs_info->sb); return ret; } diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index bd297f23d19e..f3e28f11cfb6 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -328,6 +328,9 @@ struct btrfs_fs_devices { struct btrfs_bio { unsigned int mirror_num; + /* for direct I/O */ + u64 file_offset; + /* @device is for stripe IO submission. */ struct btrfs_device *device; u8 *csum; diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index 99abf41b89b9..85691dc2232f 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -262,7 +262,8 @@ int btrfs_setxattr_trans(struct inode *inode, const char *name, inode_inc_iversion(inode); inode->i_ctime = current_time(inode); ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); - BUG_ON(ret); + if (ret) + btrfs_abort_transaction(trans, ret); out: if (start_trans) btrfs_end_transaction(trans); @@ -403,10 +404,13 @@ static int btrfs_xattr_handler_set_prop(const struct xattr_handler *handler, struct btrfs_root *root = BTRFS_I(inode)->root; name = xattr_full_name(handler, name); - ret = btrfs_validate_prop(name, value, size); + ret = btrfs_validate_prop(BTRFS_I(inode), name, value, size); if (ret) return ret; + if (btrfs_ignore_prop(BTRFS_I(inode), name)) + return 0; + trans = btrfs_start_transaction(root, 2); if (IS_ERR(trans)) return PTR_ERR(trans); @@ -416,7 +420,8 @@ static int btrfs_xattr_handler_set_prop(const struct xattr_handler *handler, inode_inc_iversion(inode); inode->i_ctime = current_time(inode); ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); - BUG_ON(ret); + if (ret) + btrfs_abort_transaction(trans, ret); } btrfs_end_transaction(trans); diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 1b1b310c3c51..d31b0eda210f 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1835,6 +1835,12 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group) goto out_unlock; } + /* No space left */ + if (block_group->alloc_offset == block_group->zone_capacity) { + ret = false; + goto out_unlock; + } + for (i = 0; i < map->num_stripes; i++) { device = map->stripes[i].dev; physical = map->stripes[i].physical; @@ -1842,35 +1848,23 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group) if (device->zone_info->max_active_zones == 0) continue; - /* No space left */ - if (block_group->alloc_offset == block_group->zone_capacity) { - ret = false; - goto out_unlock; - } - if (!btrfs_dev_set_active_zone(device, physical)) { /* Cannot activate the zone */ ret = false; goto out_unlock; } - - /* Successfully activated all the zones */ - if (i == map->num_stripes - 1) - block_group->zone_is_active = 1; - - } + + /* Successfully activated all the zones */ + block_group->zone_is_active = 1; spin_unlock(&block_group->lock); - if (block_group->zone_is_active) { - /* For the active block group list */ - btrfs_get_block_group(block_group); + /* For the active block group list */ + btrfs_get_block_group(block_group); - spin_lock(&fs_info->zone_active_bgs_lock); - list_add_tail(&block_group->active_bg_list, - &fs_info->zone_active_bgs); - spin_unlock(&fs_info->zone_active_bgs_lock); - } + spin_lock(&fs_info->zone_active_bgs_lock); + list_add_tail(&block_group->active_bg_list, &fs_info->zone_active_bgs); + spin_unlock(&fs_info->zone_active_bgs_lock); return true; diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h index cbf016a7bb5d..6dee76248cb4 100644 --- a/fs/btrfs/zoned.h +++ b/fs/btrfs/zoned.h @@ -359,7 +359,7 @@ static inline void btrfs_zoned_data_reloc_lock(struct btrfs_inode *inode) struct btrfs_root *root = inode->root; if (btrfs_is_data_reloc_root(root) && btrfs_is_zoned(root->fs_info)) - btrfs_inode_lock(&inode->vfs_inode, 0); + mutex_lock(&root->fs_info->zoned_data_reloc_io_lock); } static inline void btrfs_zoned_data_reloc_unlock(struct btrfs_inode *inode) @@ -367,7 +367,7 @@ static inline void btrfs_zoned_data_reloc_unlock(struct btrfs_inode *inode) struct btrfs_root *root = inode->root; if (btrfs_is_data_reloc_root(root) && btrfs_is_zoned(root->fs_info)) - btrfs_inode_unlock(&inode->vfs_inode, 0); + mutex_unlock(&root->fs_info->zoned_data_reloc_io_lock); } #endif |