diff options
Diffstat (limited to 'fs/btrfs')
77 files changed, 9898 insertions, 5670 deletions
diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile index e738f6206ea5..b634c42115ea 100644 --- a/fs/btrfs/Makefile +++ b/fs/btrfs/Makefile @@ -1,9 +1,25 @@ # SPDX-License-Identifier: GPL-2.0 +# Subset of W=1 warnings +subdir-ccflags-y += -Wextra -Wunused -Wno-unused-parameter +subdir-ccflags-y += -Wmissing-declarations +subdir-ccflags-y += -Wmissing-format-attribute +subdir-ccflags-y += -Wmissing-prototypes +subdir-ccflags-y += -Wold-style-definition +subdir-ccflags-y += -Wmissing-include-dirs +subdir-ccflags-y += $(call cc-option, -Wunused-but-set-variable) +subdir-ccflags-y += $(call cc-option, -Wunused-const-variable) +subdir-ccflags-y += $(call cc-option, -Wpacked-not-aligned) +subdir-ccflags-y += $(call cc-option, -Wstringop-truncation) +# The following turn off the warnings enabled by -Wextra +subdir-ccflags-y += -Wno-missing-field-initializers +subdir-ccflags-y += -Wno-sign-compare +subdir-ccflags-y += -Wno-type-limits + obj-$(CONFIG_BTRFS_FS) := btrfs.o btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \ - file-item.o inode-item.o inode-map.o disk-io.o \ + file-item.o inode-item.o disk-io.o \ transaction.o inode.o file.o tree-defrag.o \ extent_map.o sysfs.o struct-funcs.o xattr.o ordered-data.o \ extent_io.o volumes.o async-thread.o ioctl.o locking.o orphan.o \ @@ -11,11 +27,13 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \ compression.o delayed-ref.o relocation.o delayed-inode.o scrub.o \ reada.o backref.o ulist.o qgroup.o send.o dev-replace.o raid56.o \ uuid-tree.o props.o free-space-tree.o tree-checker.o space-info.o \ - block-rsv.o delalloc-space.o block-group.o discard.o reflink.o + block-rsv.o delalloc-space.o block-group.o discard.o reflink.o \ + subpage.o btrfs-$(CONFIG_BTRFS_FS_POSIX_ACL) += acl.o btrfs-$(CONFIG_BTRFS_FS_CHECK_INTEGRITY) += check-integrity.o btrfs-$(CONFIG_BTRFS_FS_REF_VERIFY) += ref-verify.o +btrfs-$(CONFIG_BLK_DEV_ZONED) += zoned.o btrfs-$(CONFIG_BTRFS_FS_RUN_SANITY_TESTS) += tests/free-space-tests.o \ tests/extent-buffer-tests.o tests/btrfs-tests.o \ diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index b3268f4ea5f3..f47c1528eb9a 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -544,7 +544,18 @@ static int resolve_indirect_ref(struct btrfs_fs_info *fs_info, int level = ref->level; struct btrfs_key search_key = ref->key_for_search; - root = btrfs_get_fs_root(fs_info, ref->root_id, false); + /* + * If we're search_commit_root we could possibly be holding locks on + * other tree nodes. This happens when qgroups does backref walks when + * adding new delayed refs. To deal with this we need to look in cache + * for the root, and if we don't find it then we need to search the + * tree_root's commit root, thus the btrfs_get_fs_root_commit_root usage + * here. + */ + if (path->search_commit_root) + root = btrfs_get_fs_root_commit_root(fs_info, path, ref->root_id); + else + root = btrfs_get_fs_root(fs_info, ref->root_id, false); if (IS_ERR(root)) { ret = PTR_ERR(root); goto out_free; @@ -772,8 +783,8 @@ static int add_missing_keys(struct btrfs_fs_info *fs_info, BUG_ON(ref->key_for_search.type); BUG_ON(!ref->wanted_disk_byte); - eb = read_tree_block(fs_info, ref->wanted_disk_byte, 0, - ref->level - 1, NULL); + eb = read_tree_block(fs_info, ref->wanted_disk_byte, + ref->root_id, 0, ref->level - 1, NULL); if (IS_ERR(eb)) { free_pref(ref); return PTR_ERR(eb); @@ -1320,7 +1331,7 @@ again: struct extent_buffer *eb; eb = read_tree_block(fs_info, ref->parent, 0, - ref->level, NULL); + 0, ref->level, NULL); if (IS_ERR(eb)) { ret = PTR_ERR(eb); goto out; @@ -1330,14 +1341,12 @@ again: goto out; } - if (!path->skip_locking) { + if (!path->skip_locking) btrfs_tree_read_lock(eb); - btrfs_set_lock_blocking_read(eb); - } ret = find_extent_in_eb(eb, bytenr, *extent_item_pos, &eie, ignore_offset); if (!path->skip_locking) - btrfs_tree_read_unlock_blocking(eb); + btrfs_tree_read_unlock(eb); free_extent_buffer(eb); if (ret < 0) goto out; @@ -1492,7 +1501,13 @@ int btrfs_find_all_roots(struct btrfs_trans_handle *trans, } /** - * btrfs_check_shared - tell us whether an extent is shared + * Check if an extent is shared or not + * + * @root: root inode belongs to + * @inum: inode number of the inode whose extent we are checking + * @bytenr: logical bytenr of the extent we are checking + * @roots: list of roots this extent is shared among + * @tmp: temporary list used for iteration * * btrfs_check_shared uses the backref walking code but will short * circuit as soon as it finds a root or inode that doesn't match the @@ -1660,13 +1675,11 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path, s64 bytes_left = ((s64)size) - 1; struct extent_buffer *eb = eb_in; struct btrfs_key found_key; - int leave_spinning = path->leave_spinning; struct btrfs_inode_ref *iref; if (bytes_left >= 0) dest[bytes_left] = '\0'; - path->leave_spinning = 1; while (1) { bytes_left -= name_len; if (bytes_left >= 0) @@ -1674,7 +1687,7 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path, name_off, name_len); if (eb != eb_in) { if (!path->skip_locking) - btrfs_tree_read_unlock_blocking(eb); + btrfs_tree_read_unlock(eb); free_extent_buffer(eb); } ret = btrfs_find_item(fs_root, path, parent, 0, @@ -1694,8 +1707,6 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path, eb = path->nodes[0]; /* make sure we can use eb after releasing the path */ if (eb != eb_in) { - if (!path->skip_locking) - btrfs_set_lock_blocking_read(eb); path->nodes[0] = NULL; path->locks[0] = 0; } @@ -1712,7 +1723,6 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path, } btrfs_release_path(path); - path->leave_spinning = leave_spinning; if (ret) return ERR_PTR(ret); @@ -2537,13 +2547,6 @@ void btrfs_backref_cleanup_node(struct btrfs_backref_cache *cache, list_del(&edge->list[UPPER]); btrfs_backref_free_edge(cache, edge); - if (RB_EMPTY_NODE(&upper->rb_node)) { - BUG_ON(!list_empty(&node->upper)); - btrfs_backref_drop_node(cache, node); - node = upper; - node->lowest = 1; - continue; - } /* * Add the node to leaf node list if no other child block * cached. @@ -2620,7 +2623,7 @@ static int handle_direct_tree_backref(struct btrfs_backref_cache *cache, /* Only reloc backref cache cares about a specific root */ if (cache->is_reloc) { root = find_reloc_root(cache->fs_info, cur->bytenr); - if (WARN_ON(!root)) + if (!root) return -ENOENT; cur->root = root; } else { @@ -3113,7 +3116,7 @@ void btrfs_backref_error_cleanup(struct btrfs_backref_cache *cache, list_del_init(&lower->list); if (lower == node) node = NULL; - btrfs_backref_free_node(cache, lower); + btrfs_backref_drop_node(cache, lower); } btrfs_backref_cleanup_node(cache, node); diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h index ff705cc564a9..17abde7f794c 100644 --- a/fs/btrfs/backref.h +++ b/fs/btrfs/backref.h @@ -296,6 +296,9 @@ static inline void btrfs_backref_free_node(struct btrfs_backref_cache *cache, struct btrfs_backref_node *node) { if (node) { + ASSERT(list_empty(&node->list)); + ASSERT(list_empty(&node->lower)); + ASSERT(node->eb == NULL); cache->nr_nodes--; btrfs_put_root(node->root); kfree(node); @@ -340,11 +343,11 @@ static inline void btrfs_backref_drop_node_buffer( static inline void btrfs_backref_drop_node(struct btrfs_backref_cache *tree, struct btrfs_backref_node *node) { - BUG_ON(!list_empty(&node->upper)); + ASSERT(list_empty(&node->upper)); btrfs_backref_drop_node_buffer(node); - list_del(&node->list); - list_del(&node->lower); + list_del_init(&node->list); + list_del_init(&node->lower); if (!RB_EMPTY_NODE(&node->rb_node)) rb_erase(&node->rb_node, &tree->rb_root); btrfs_backref_free_node(tree, node); diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index c0f1d6818df7..5064be59dac5 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -15,6 +15,7 @@ #include "delalloc-space.h" #include "discard.h" #include "raid56.h" +#include "zoned.h" /* * Return target flags in extended format or 0 if restripe for this chunk_type @@ -424,6 +425,23 @@ int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache) return ret; } +static bool space_cache_v1_done(struct btrfs_block_group *cache) +{ + bool ret; + + spin_lock(&cache->lock); + ret = cache->cached != BTRFS_CACHE_FAST; + spin_unlock(&cache->lock); + + return ret; +} + +void btrfs_wait_space_cache_v1_finished(struct btrfs_block_group *cache, + struct btrfs_caching_control *caching_ctl) +{ + wait_event(caching_ctl->wait, space_cache_v1_done(cache)); +} + #ifdef CONFIG_BTRFS_DEBUG static void fragment_free_space(struct btrfs_block_group *block_group) { @@ -639,11 +657,36 @@ static noinline void caching_thread(struct btrfs_work *work) mutex_lock(&caching_ctl->mutex); down_read(&fs_info->commit_root_sem); - if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) + if (btrfs_test_opt(fs_info, SPACE_CACHE)) { + ret = load_free_space_cache(block_group); + if (ret == 1) { + ret = 0; + goto done; + } + + /* + * We failed to load the space cache, set ourselves to + * CACHE_STARTED and carry on. + */ + spin_lock(&block_group->lock); + block_group->cached = BTRFS_CACHE_STARTED; + spin_unlock(&block_group->lock); + wake_up(&caching_ctl->wait); + } + + /* + * If we are in the transaction that populated the free space tree we + * can't actually cache from the free space tree as our commit root and + * real root are the same, so we could change the contents of the blocks + * while caching. Instead do the slow caching in this case, and after + * the transaction has committed we will be safe. + */ + if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) && + !(test_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags))) ret = load_free_space_tree(caching_ctl); else ret = load_extent_tree_free(caching_ctl); - +done: spin_lock(&block_group->lock); block_group->caching_ctl = NULL; block_group->cached = ret ? BTRFS_CACHE_ERROR : BTRFS_CACHE_FINISHED; @@ -679,9 +722,13 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only { DEFINE_WAIT(wait); struct btrfs_fs_info *fs_info = cache->fs_info; - struct btrfs_caching_control *caching_ctl; + struct btrfs_caching_control *caching_ctl = NULL; int ret = 0; + /* Allocator for zoned filesystems does not use the cache at all */ + if (btrfs_is_zoned(fs_info)) + return 0; + caching_ctl = kzalloc(sizeof(*caching_ctl), GFP_NOFS); if (!caching_ctl) return -ENOMEM; @@ -691,119 +738,41 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only init_waitqueue_head(&caching_ctl->wait); caching_ctl->block_group = cache; caching_ctl->progress = cache->start; - refcount_set(&caching_ctl->count, 1); + refcount_set(&caching_ctl->count, 2); btrfs_init_work(&caching_ctl->work, caching_thread, NULL, NULL); spin_lock(&cache->lock); - /* - * This should be a rare occasion, but this could happen I think in the - * case where one thread starts to load the space cache info, and then - * some other thread starts a transaction commit which tries to do an - * allocation while the other thread is still loading the space cache - * info. The previous loop should have kept us from choosing this block - * group, but if we've moved to the state where we will wait on caching - * block groups we need to first check if we're doing a fast load here, - * so we can wait for it to finish, otherwise we could end up allocating - * from a block group who's cache gets evicted for one reason or - * another. - */ - while (cache->cached == BTRFS_CACHE_FAST) { - struct btrfs_caching_control *ctl; - - ctl = cache->caching_ctl; - refcount_inc(&ctl->count); - prepare_to_wait(&ctl->wait, &wait, TASK_UNINTERRUPTIBLE); - spin_unlock(&cache->lock); - - schedule(); - - finish_wait(&ctl->wait, &wait); - btrfs_put_caching_control(ctl); - spin_lock(&cache->lock); - } - if (cache->cached != BTRFS_CACHE_NO) { - spin_unlock(&cache->lock); kfree(caching_ctl); - return 0; + + caching_ctl = cache->caching_ctl; + if (caching_ctl) + refcount_inc(&caching_ctl->count); + spin_unlock(&cache->lock); + goto out; } WARN_ON(cache->caching_ctl); cache->caching_ctl = caching_ctl; - cache->cached = BTRFS_CACHE_FAST; + if (btrfs_test_opt(fs_info, SPACE_CACHE)) + cache->cached = BTRFS_CACHE_FAST; + else + cache->cached = BTRFS_CACHE_STARTED; + cache->has_caching_ctl = 1; spin_unlock(&cache->lock); - if (btrfs_test_opt(fs_info, SPACE_CACHE)) { - mutex_lock(&caching_ctl->mutex); - ret = load_free_space_cache(cache); - - spin_lock(&cache->lock); - if (ret == 1) { - cache->caching_ctl = NULL; - cache->cached = BTRFS_CACHE_FINISHED; - cache->last_byte_to_unpin = (u64)-1; - caching_ctl->progress = (u64)-1; - } else { - if (load_cache_only) { - cache->caching_ctl = NULL; - cache->cached = BTRFS_CACHE_NO; - } else { - cache->cached = BTRFS_CACHE_STARTED; - cache->has_caching_ctl = 1; - } - } - spin_unlock(&cache->lock); -#ifdef CONFIG_BTRFS_DEBUG - if (ret == 1 && - btrfs_should_fragment_free_space(cache)) { - u64 bytes_used; - - spin_lock(&cache->space_info->lock); - spin_lock(&cache->lock); - bytes_used = cache->length - cache->used; - cache->space_info->bytes_used += bytes_used >> 1; - spin_unlock(&cache->lock); - spin_unlock(&cache->space_info->lock); - fragment_free_space(cache); - } -#endif - mutex_unlock(&caching_ctl->mutex); - - wake_up(&caching_ctl->wait); - if (ret == 1) { - btrfs_put_caching_control(caching_ctl); - btrfs_free_excluded_extents(cache); - return 0; - } - } else { - /* - * We're either using the free space tree or no caching at all. - * Set cached to the appropriate value and wakeup any waiters. - */ - spin_lock(&cache->lock); - if (load_cache_only) { - cache->caching_ctl = NULL; - cache->cached = BTRFS_CACHE_NO; - } else { - cache->cached = BTRFS_CACHE_STARTED; - cache->has_caching_ctl = 1; - } - spin_unlock(&cache->lock); - wake_up(&caching_ctl->wait); - } - - if (load_cache_only) { - btrfs_put_caching_control(caching_ctl); - return 0; - } - - down_write(&fs_info->commit_root_sem); + spin_lock(&fs_info->block_group_cache_lock); refcount_inc(&caching_ctl->count); list_add_tail(&caching_ctl->list, &fs_info->caching_block_groups); - up_write(&fs_info->commit_root_sem); + spin_unlock(&fs_info->block_group_cache_lock); btrfs_get_block_group(cache); btrfs_queue_work(fs_info->caching_workers, &caching_ctl->work); +out: + if (load_cache_only && caching_ctl) + btrfs_wait_space_cache_v1_finished(cache, caching_ctl); + if (caching_ctl) + btrfs_put_caching_control(caching_ctl); return ret; } @@ -892,8 +861,6 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, struct btrfs_path *path; struct btrfs_block_group *block_group; struct btrfs_free_cluster *cluster; - struct btrfs_root *tree_root = fs_info->tree_root; - struct btrfs_key key; struct inode *inode; struct kobject *kobj = NULL; int ret; @@ -934,6 +901,8 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, btrfs_return_cluster_to_free_space(block_group, cluster); spin_unlock(&cluster->refill_lock); + btrfs_clear_treelog_bg(block_group); + path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; @@ -971,42 +940,9 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, spin_unlock(&trans->transaction->dirty_bgs_lock); mutex_unlock(&trans->transaction->cache_write_mutex); - if (!IS_ERR(inode)) { - ret = btrfs_orphan_add(trans, BTRFS_I(inode)); - if (ret) { - btrfs_add_delayed_iput(inode); - goto out; - } - clear_nlink(inode); - /* One for the block groups ref */ - spin_lock(&block_group->lock); - if (block_group->iref) { - block_group->iref = 0; - block_group->inode = NULL; - spin_unlock(&block_group->lock); - iput(inode); - } else { - spin_unlock(&block_group->lock); - } - /* One for our lookup ref */ - btrfs_add_delayed_iput(inode); - } - - key.objectid = BTRFS_FREE_SPACE_OBJECTID; - key.type = 0; - key.offset = block_group->start; - - ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1); - if (ret < 0) + ret = btrfs_remove_free_space_inode(trans, inode, block_group); + if (ret) goto out; - if (ret > 0) - btrfs_release_path(path); - if (ret == 0) { - ret = btrfs_del_item(trans, tree_root, path); - if (ret) - goto out; - btrfs_release_path(path); - } spin_lock(&fs_info->block_group_cache_lock); rb_erase(&block_group->cache_node, @@ -1043,7 +979,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, if (block_group->cached == BTRFS_CACHE_STARTED) btrfs_wait_block_group_cache_done(block_group); if (block_group->has_caching_ctl) { - down_write(&fs_info->commit_root_sem); + spin_lock(&fs_info->block_group_cache_lock); if (!caching_ctl) { struct btrfs_caching_control *ctl; @@ -1057,7 +993,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, } if (caching_ctl) list_del_init(&caching_ctl->list); - up_write(&fs_info->commit_root_sem); + spin_unlock(&fs_info->block_group_cache_lock); if (caching_ctl) { /* Once for the caching bgs list and once for us. */ btrfs_put_caching_control(caching_ctl); @@ -1079,12 +1015,17 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, WARN_ON(block_group->space_info->total_bytes < block_group->length); WARN_ON(block_group->space_info->bytes_readonly - < block_group->length); + < block_group->length - block_group->zone_unusable); + WARN_ON(block_group->space_info->bytes_zone_unusable + < block_group->zone_unusable); WARN_ON(block_group->space_info->disk_total < block_group->length * factor); } block_group->space_info->total_bytes -= block_group->length; - block_group->space_info->bytes_readonly -= block_group->length; + block_group->space_info->bytes_readonly -= + (block_group->length - block_group->zone_unusable); + block_group->space_info->bytes_zone_unusable -= + block_group->zone_unusable; block_group->space_info->disk_total -= block_group->length * factor; spin_unlock(&block_group->space_info->lock); @@ -1228,7 +1169,7 @@ static int inc_block_group_ro(struct btrfs_block_group *cache, int force) } num_bytes = cache->length - cache->reserved - cache->pinned - - cache->bytes_super - cache->used; + cache->bytes_super - cache->zone_unusable - cache->used; /* * Data never overcommits, even in mixed mode, so do just the straight @@ -1259,6 +1200,12 @@ static int inc_block_group_ro(struct btrfs_block_group *cache, int force) if (!ret) { sinfo->bytes_readonly += num_bytes; + if (btrfs_is_zoned(cache->fs_info)) { + /* Migrate zone_unusable bytes to readonly */ + sinfo->bytes_readonly += cache->zone_unusable; + sinfo->bytes_zone_unusable -= cache->zone_unusable; + cache->zone_unusable = 0; + } cache->ro++; list_add_tail(&cache->ro_list, &sinfo->ro_bgs); } @@ -1333,6 +1280,13 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) if (!test_bit(BTRFS_FS_OPEN, &fs_info->flags)) return; + /* + * Long running balances can keep us blocked here for eternity, so + * simply skip deletion if we're unable to get the mutex. + */ + if (!mutex_trylock(&fs_info->delete_unused_bgs_mutex)) + return; + spin_lock(&fs_info->unused_bgs_lock); while (!list_empty(&fs_info->unused_bgs)) { int trimming; @@ -1352,8 +1306,6 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) btrfs_discard_cancel_work(&fs_info->discard_ctl, block_group); - mutex_lock(&fs_info->delete_unused_bgs_mutex); - /* Don't want to race with allocators so take the groups_sem */ down_write(&space_info->groups_sem); @@ -1442,9 +1394,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) btrfs_space_info_update_bytes_pinned(fs_info, space_info, -block_group->pinned); space_info->bytes_readonly += block_group->pinned; - percpu_counter_add_batch(&space_info->total_bytes_pinned, - -block_group->pinned, - BTRFS_TOTAL_BYTES_PINNED_BATCH); + __btrfs_mod_total_bytes_pinned(space_info, -block_group->pinned); block_group->pinned = 0; spin_unlock(&block_group->lock); @@ -1460,8 +1410,12 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) if (!async_trim_enabled && btrfs_test_opt(fs_info, DISCARD_ASYNC)) goto flip_async; - /* DISCARD can flip during remount */ - trimming = btrfs_test_opt(fs_info, DISCARD_SYNC); + /* + * DISCARD can flip during remount. On zoned filesystems, we + * need to reset sequential-required zones. + */ + trimming = btrfs_test_opt(fs_info, DISCARD_SYNC) || + btrfs_is_zoned(fs_info); /* Implicit trim during transaction commit. */ if (trimming) @@ -1499,11 +1453,11 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) end_trans: btrfs_end_transaction(trans); next: - mutex_unlock(&fs_info->delete_unused_bgs_mutex); btrfs_put_block_group(block_group); spin_lock(&fs_info->unused_bgs_lock); } spin_unlock(&fs_info->unused_bgs_lock); + mutex_unlock(&fs_info->delete_unused_bgs_mutex); return; flip_async: @@ -1632,8 +1586,11 @@ static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags) } /** - * btrfs_rmap_block - Map a physical disk address to a list of logical addresses + * Map a physical disk address to a list of logical addresses + * + * @fs_info: the filesystem * @chunk_start: logical address of block group + * @bdev: physical device to resolve, can be NULL to indicate any device * @physical: physical address to map to logical addresses * @logical: return array of logical addresses which map to @physical * @naddrs: length of @logical @@ -1643,9 +1600,9 @@ static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags) * Used primarily to exclude those portions of a block group that contain super * block copies. */ -EXPORT_FOR_TESTS int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start, - u64 physical, u64 **logical, int *naddrs, int *stripe_len) + struct block_device *bdev, u64 physical, u64 **logical, + int *naddrs, int *stripe_len) { struct extent_map *em; struct map_lookup *map; @@ -1663,6 +1620,7 @@ int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start, map = em->map_lookup; data_stripe_length = em->orig_block_len; io_stripe_size = map->stripe_len; + chunk_start = em->start; /* For RAID5/6 adjust to a full IO stripe length */ if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) @@ -1677,14 +1635,18 @@ int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start, for (i = 0; i < map->num_stripes; i++) { bool already_inserted = false; u64 stripe_nr; + u64 offset; int j; if (!in_range(physical, map->stripes[i].physical, data_stripe_length)) continue; + if (bdev && map->stripes[i].dev->bdev != bdev) + continue; + stripe_nr = physical - map->stripes[i].physical; - stripe_nr = div64_u64(stripe_nr, map->stripe_len); + stripe_nr = div64_u64_rem(stripe_nr, map->stripe_len, &offset); if (map->type & BTRFS_BLOCK_GROUP_RAID10) { stripe_nr = stripe_nr * map->num_stripes + i; @@ -1698,7 +1660,7 @@ int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start, * instead of map->stripe_len */ - bytenr = chunk_start + stripe_nr * io_stripe_size; + bytenr = chunk_start + stripe_nr * io_stripe_size + offset; /* Ensure we don't add duplicate addresses */ for (j = 0; j < nr; j++) { @@ -1723,6 +1685,7 @@ out: static int exclude_super_stripes(struct btrfs_block_group *cache) { struct btrfs_fs_info *fs_info = cache->fs_info; + const bool zoned = btrfs_is_zoned(fs_info); u64 bytenr; u64 *logical; int stripe_len; @@ -1739,11 +1702,19 @@ static int exclude_super_stripes(struct btrfs_block_group *cache) for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) { bytenr = btrfs_sb_offset(i); - ret = btrfs_rmap_block(fs_info, cache->start, + ret = btrfs_rmap_block(fs_info, cache->start, NULL, bytenr, &logical, &nr, &stripe_len); if (ret) return ret; + /* Shouldn't have super stripes in sequential zones */ + if (zoned && nr) { + btrfs_err(fs_info, + "zoned: block group %llu must not contain super block", + cache->start); + return -EUCLEAN; + } + while (nr--) { u64 len = min_t(u64, stripe_len, cache->start + cache->length - logical[nr]); @@ -1805,7 +1776,7 @@ static struct btrfs_block_group *btrfs_create_block_group_cache( INIT_LIST_HEAD(&cache->discard_list); INIT_LIST_HEAD(&cache->dirty_list); INIT_LIST_HEAD(&cache->io_list); - btrfs_init_free_space_ctl(cache); + btrfs_init_free_space_ctl(cache, cache->free_space_ctl); atomic_set(&cache->frozen, 0); mutex_init(&cache->free_space_lock); btrfs_init_full_stripe_locks_tree(&cache->full_stripe_locks_root); @@ -1867,24 +1838,8 @@ static int check_chunk_block_group_mappings(struct btrfs_fs_info *fs_info) return ret; } -static void read_block_group_item(struct btrfs_block_group *cache, - struct btrfs_path *path, - const struct btrfs_key *key) -{ - struct extent_buffer *leaf = path->nodes[0]; - struct btrfs_block_group_item bgi; - int slot = path->slots[0]; - - cache->length = key->offset; - - read_extent_buffer(leaf, &bgi, btrfs_item_ptr_offset(leaf, slot), - sizeof(bgi)); - cache->used = btrfs_stack_block_group_used(&bgi); - cache->flags = btrfs_stack_block_group_flags(&bgi); -} - static int read_one_block_group(struct btrfs_fs_info *info, - struct btrfs_path *path, + struct btrfs_block_group_item *bgi, const struct btrfs_key *key, int need_clear) { @@ -1899,7 +1854,9 @@ static int read_one_block_group(struct btrfs_fs_info *info, if (!cache) return -ENOMEM; - read_block_group_item(cache, path, key); + cache->length = key->offset; + cache->used = btrfs_stack_block_group_used(bgi); + cache->flags = btrfs_stack_block_group_flags(bgi); set_free_space_tree_thresholds(cache); @@ -1926,6 +1883,13 @@ static int read_one_block_group(struct btrfs_fs_info *info, goto error; } + ret = btrfs_load_block_group_zone_info(cache, false); + if (ret) { + btrfs_err(info, "zoned: failed to load zone info of bg %llu", + cache->start); + goto error; + } + /* * We need to exclude the super stripes now so that the space info has * super bytes accounted for, otherwise we'll think we have more space @@ -1939,12 +1903,20 @@ static int read_one_block_group(struct btrfs_fs_info *info, } /* - * Check for two cases, either we are full, and therefore don't need - * to bother with the caching work since we won't find any space, or we - * are empty, and we can just add all the space in and be done with it. - * This saves us _a_lot_ of time, particularly in the full case. + * For zoned filesystem, space after the allocation offset is the only + * free space for a block group. So, we don't need any caching work. + * btrfs_calc_zone_unusable() will set the amount of free space and + * zone_unusable space. + * + * For regular filesystem, check for two cases, either we are full, and + * therefore don't need to bother with the caching work since we won't + * find any space, or we are empty, and we can just add all the space + * in and be done with it. This saves us _a_lot_ of time, particularly + * in the full case. */ - if (cache->length == cache->used) { + if (btrfs_is_zoned(info)) { + btrfs_calc_zone_unusable(cache); + } else if (cache->length == cache->used) { cache->last_byte_to_unpin = (u64)-1; cache->cached = BTRFS_CACHE_FINISHED; btrfs_free_excluded_extents(cache); @@ -1963,7 +1935,8 @@ static int read_one_block_group(struct btrfs_fs_info *info, } trace_btrfs_add_block_group(info, cache, 0); btrfs_update_space_info(info, cache->flags, cache->length, - cache->used, cache->bytes_super, &space_info); + cache->used, cache->bytes_super, + cache->zone_unusable, &space_info); cache->space_info = space_info; @@ -1985,6 +1958,51 @@ error: return ret; } +static int fill_dummy_bgs(struct btrfs_fs_info *fs_info) +{ + struct extent_map_tree *em_tree = &fs_info->mapping_tree; + struct btrfs_space_info *space_info; + struct rb_node *node; + int ret = 0; + + for (node = rb_first_cached(&em_tree->map); node; node = rb_next(node)) { + struct extent_map *em; + struct map_lookup *map; + struct btrfs_block_group *bg; + + em = rb_entry(node, struct extent_map, rb_node); + map = em->map_lookup; + bg = btrfs_create_block_group_cache(fs_info, em->start); + if (!bg) { + ret = -ENOMEM; + break; + } + + /* Fill dummy cache as FULL */ + bg->length = em->len; + bg->flags = map->type; + bg->last_byte_to_unpin = (u64)-1; + bg->cached = BTRFS_CACHE_FINISHED; + bg->used = em->len; + bg->flags = map->type; + ret = btrfs_add_block_group_cache(fs_info, bg); + if (ret) { + btrfs_remove_free_space_cache(bg); + btrfs_put_block_group(bg); + break; + } + btrfs_update_space_info(fs_info, bg->flags, em->len, em->len, + 0, 0, &space_info); + bg->space_info = space_info; + link_block_group(bg); + + set_avail_alloc_bits(fs_info, bg->flags); + } + if (!ret) + btrfs_init_global_block_rsv(fs_info); + return ret; +} + int btrfs_read_block_groups(struct btrfs_fs_info *info) { struct btrfs_path *path; @@ -1995,6 +2013,9 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info) int need_clear = 0; u64 cache_gen; + if (!info->extent_root) + return fill_dummy_bgs(info); + key.objectid = 0; key.offset = 0; key.type = BTRFS_BLOCK_GROUP_ITEM_KEY; @@ -2010,20 +2031,31 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info) need_clear = 1; while (1) { + struct btrfs_block_group_item bgi; + struct extent_buffer *leaf; + int slot; + ret = find_first_block_group(info, path, &key); if (ret > 0) break; if (ret != 0) goto error; - btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); - ret = read_one_block_group(info, path, &key, need_clear); + leaf = path->nodes[0]; + slot = path->slots[0]; + + read_extent_buffer(leaf, &bgi, btrfs_item_ptr_offset(leaf, slot), + sizeof(bgi)); + + btrfs_item_key_to_cpu(leaf, &key, slot); + btrfs_release_path(path); + ret = read_one_block_group(info, &bgi, &key, need_clear); if (ret < 0) goto error; key.objectid += key.offset; key.offset = 0; - btrfs_release_path(path); } + btrfs_release_path(path); list_for_each_entry(space_info, &info->space_info, list) { int i; @@ -2151,7 +2183,15 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used, cache->flags = type; cache->last_byte_to_unpin = (u64)-1; cache->cached = BTRFS_CACHE_FINISHED; - cache->needs_free_space = 1; + if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) + cache->needs_free_space = 1; + + ret = btrfs_load_block_group_zone_info(cache, true); + if (ret) { + btrfs_put_block_group(cache); + return ret; + } + ret = exclude_super_stripes(cache); if (ret) { /* We may have excluded something, so call this just in case */ @@ -2193,7 +2233,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used, */ trace_btrfs_add_block_group(fs_info, cache, 1); btrfs_update_space_info(fs_info, cache->flags, size, bytes_used, - cache->bytes_super, &cache->space_info); + cache->bytes_super, 0, &cache->space_info); btrfs_update_global_block_rsv(fs_info); link_block_group(cache); @@ -2301,8 +2341,15 @@ void btrfs_dec_block_group_ro(struct btrfs_block_group *cache) spin_lock(&cache->lock); if (!--cache->ro) { num_bytes = cache->length - cache->reserved - - cache->pinned - cache->bytes_super - cache->used; + cache->pinned - cache->bytes_super - + cache->zone_unusable - cache->used; sinfo->bytes_readonly -= num_bytes; + if (btrfs_is_zoned(cache->fs_info)) { + /* Migrate zone_unusable bytes back */ + cache->zone_unusable = cache->alloc_offset - cache->used; + sinfo->bytes_zone_unusable += cache->zone_unusable; + sinfo->bytes_readonly -= cache->zone_unusable; + } list_del_init(&cache->ro_list); } spin_unlock(&cache->lock); @@ -2360,6 +2407,9 @@ static int cache_save_setup(struct btrfs_block_group *block_group, int retries = 0; int ret = 0; + if (!btrfs_test_opt(fs_info, SPACE_CACHE)) + return 0; + /* * If this block group is smaller than 100 megs don't bother caching the * block group. @@ -2400,7 +2450,7 @@ again: * time. */ BTRFS_I(inode)->generation = 0; - ret = btrfs_update_inode(trans, root, inode); + ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); if (ret) { /* * So theoretically we could recover from this, simply set the @@ -2573,8 +2623,10 @@ again: if (!path) { path = btrfs_alloc_path(); - if (!path) - return -ENOMEM; + if (!path) { + ret = -ENOMEM; + goto out; + } } /* @@ -2668,16 +2720,14 @@ again: btrfs_put_block_group(cache); if (drop_reserve) btrfs_delayed_refs_rsv_release(fs_info, 1); - - if (ret) - break; - /* * Avoid blocking other tasks for too long. It might even save * us from writing caches for block groups that are going to be * removed. */ mutex_unlock(&trans->transaction->cache_write_mutex); + if (ret) + goto out; mutex_lock(&trans->transaction->cache_write_mutex); } mutex_unlock(&trans->transaction->cache_write_mutex); @@ -2686,7 +2736,8 @@ again: * Go through delayed refs for all the stuff we've just kicked off * and then loop back (just once) */ - ret = btrfs_run_delayed_refs(trans, 0); + if (!ret) + ret = btrfs_run_delayed_refs(trans, 0); if (!ret && loops == 0) { loops++; spin_lock(&cur_trans->dirty_bgs_lock); @@ -2700,7 +2751,12 @@ again: goto again; } spin_unlock(&cur_trans->dirty_bgs_lock); - } else if (ret < 0) { + } +out: + if (ret < 0) { + spin_lock(&cur_trans->dirty_bgs_lock); + list_splice_init(&dirty, &cur_trans->dirty_bgs); + spin_unlock(&cur_trans->dirty_bgs_lock); btrfs_cleanup_dirty_bgs(cur_trans, fs_info); } @@ -2904,10 +2960,8 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans, spin_unlock(&cache->lock); spin_unlock(&cache->space_info->lock); - percpu_counter_add_batch( - &cache->space_info->total_bytes_pinned, - num_bytes, - BTRFS_TOTAL_BYTES_PINNED_BATCH); + __btrfs_mod_total_bytes_pinned(cache->space_info, + num_bytes); set_extent_dirty(&trans->transaction->pinned_extents, bytenr, bytenr + num_bytes - 1, GFP_NOFS | __GFP_NOFAIL); @@ -3306,14 +3360,14 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info) struct btrfs_caching_control *caching_ctl; struct rb_node *n; - down_write(&info->commit_root_sem); + spin_lock(&info->block_group_cache_lock); while (!list_empty(&info->caching_block_groups)) { caching_ctl = list_entry(info->caching_block_groups.next, struct btrfs_caching_control, list); list_del(&caching_ctl->list); btrfs_put_caching_control(caching_ctl); } - up_write(&info->commit_root_sem); + spin_unlock(&info->block_group_cache_lock); spin_lock(&info->unused_bgs_lock); while (!list_empty(&info->unused_bgs)) { diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index adfd7583a17b..29678426247d 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -95,6 +95,8 @@ struct btrfs_block_group { unsigned int iref:1; unsigned int has_caching_ctl:1; unsigned int removed:1; + unsigned int to_copy:1; + unsigned int relocating_repair:1; int disk_cache_state; @@ -181,8 +183,19 @@ struct btrfs_block_group { */ int needs_free_space; + /* Flag indicating this block group is placed on a sequential zone */ + bool seq_zone; + /* Record locked full stripes for RAID5/6 block group */ struct btrfs_full_stripe_locks_tree full_stripe_locks_root; + + /* + * Allocation offset for the block group to implement sequential + * allocation. This is used only on a zoned filesystem. + */ + u64 alloc_offset; + u64 zone_unusable; + u64 meta_write_pointer; }; static inline u64 btrfs_block_group_end(struct btrfs_block_group *block_group) @@ -268,6 +281,11 @@ void check_system_chunk(struct btrfs_trans_handle *trans, const u64 type); u64 btrfs_get_alloc_profile(struct btrfs_fs_info *fs_info, u64 orig_flags); void btrfs_put_block_group_cache(struct btrfs_fs_info *info); int btrfs_free_block_groups(struct btrfs_fs_info *info); +void btrfs_wait_space_cache_v1_finished(struct btrfs_block_group *cache, + struct btrfs_caching_control *caching_ctl); +int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start, + struct block_device *bdev, u64 physical, u64 **logical, + int *naddrs, int *stripe_len); static inline u64 btrfs_data_alloc_profile(struct btrfs_fs_info *fs_info) { @@ -294,9 +312,4 @@ static inline int btrfs_block_group_done(struct btrfs_block_group *cache) void btrfs_freeze_block_group(struct btrfs_block_group *cache); void btrfs_unfreeze_block_group(struct btrfs_block_group *cache); -#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS -int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start, - u64 physical, u64 **logical, int *naddrs, int *stripe_len); -#endif - #endif /* BTRFS_BLOCK_GROUP_H */ diff --git a/fs/btrfs/block-rsv.c b/fs/btrfs/block-rsv.c index 7e1549a84fcc..04a6226e0388 100644 --- a/fs/btrfs/block-rsv.c +++ b/fs/btrfs/block-rsv.c @@ -426,6 +426,14 @@ void btrfs_init_global_block_rsv(struct btrfs_fs_info *fs_info) fs_info->delayed_block_rsv.space_info = space_info; fs_info->delayed_refs_rsv.space_info = space_info; + /* + * Our various recovery options can leave us with NULL roots, so check + * here and just bail before we go dereferencing NULLs everywhere. + */ + if (!fs_info->extent_root || !fs_info->csum_root || + !fs_info->dev_root || !fs_info->chunk_root || !fs_info->tree_root) + return; + fs_info->extent_root->block_rsv = &fs_info->delayed_refs_rsv; fs_info->csum_root->block_rsv = &fs_info->delayed_refs_rsv; fs_info->dev_root->block_rsv = &fs_info->global_block_rsv; @@ -511,7 +519,8 @@ again: /*DEFAULT_RATELIMIT_BURST*/ 1); if (__ratelimit(&_rs)) WARN(1, KERN_DEBUG - "BTRFS: block rsv returned %d\n", ret); + "BTRFS: block rsv %d returned %d\n", + block_rsv->type, ret); } try_reserve: ret = btrfs_reserve_metadata_bytes(root, block_rsv, blocksize, diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index 92dd86bceae3..28e202e89660 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -35,6 +35,22 @@ enum { BTRFS_INODE_IN_DELALLOC_LIST, BTRFS_INODE_HAS_PROPS, BTRFS_INODE_SNAPSHOT_FLUSH, + /* + * Set and used when logging an inode and it serves to signal that an + * inode does not have xattrs, so subsequent fsyncs can avoid searching + * for xattrs to log. This bit must be cleared whenever a xattr is added + * to an inode. + */ + BTRFS_INODE_NO_XATTRS, + /* + * Set when we are in a context where we need to start a transaction and + * have dirty pages with the respective file range locked. This is to + * ensure that when reserving space for the transaction, if we are low + * on available space and need to flush delalloc, we will not flush + * delalloc for this inode, because that could result in a deadlock (on + * the file range, inode's io_tree). + */ + BTRFS_INODE_NO_DELALLOC_FLUSH, }; /* in memory btrfs inode */ @@ -50,7 +66,8 @@ struct btrfs_inode { /* * Lock for counters and all fields used to determine if the inode is in * the log or not (last_trans, last_sub_trans, last_log_commit, - * logged_trans). + * logged_trans), to access/update new_delalloc_bytes and to update the + * VFS' inode number of bytes used. */ spinlock_t lock; @@ -203,16 +220,6 @@ struct btrfs_inode { /* Hook into fs_info->delayed_iputs */ struct list_head delayed_iput; - /* - * To avoid races between lockless (i_mutex not held) direct IO writes - * and concurrent fsync requests. Direct IO writes must acquire read - * access on this semaphore for creating an extent map and its - * corresponding ordered extent. The fast fsync path must acquire write - * access on this semaphore before it collects ordered extents and - * extent maps. - */ - struct rw_semaphore dio_sem; - struct inode vfs_inode; }; @@ -318,7 +325,8 @@ struct btrfs_dio_private { struct inode *inode; u64 logical_offset; u64 disk_bytenr; - u64 bytes; + /* Used for bio::bi_size */ + u32 bytes; /* * References to this structure. There is one reference per in-flight @@ -341,8 +349,7 @@ static inline void btrfs_print_data_csum_error(struct btrfs_inode *inode, u64 logical_start, u8 *csum, u8 *csum_expected, int mirror_num) { struct btrfs_root *root = inode->root; - struct btrfs_super_block *sb = root->fs_info->super_copy; - const u16 csum_size = btrfs_super_csum_size(sb); + const u32 csum_size = root->fs_info->csum_size; /* Output minus objectid, which is more meaningful */ if (root->root_key.objectid >= BTRFS_LAST_FREE_OBJECTID) diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c index 81a8c87a5afb..113cb85c1fd4 100644 --- a/fs/btrfs/check-integrity.c +++ b/fs/btrfs/check-integrity.c @@ -233,7 +233,6 @@ struct btrfsic_stack_frame { struct btrfsic_state { u32 print_mask; int include_extent_data; - int csum_size; struct list_head all_blocks_list; struct btrfsic_block_hashtable block_hashtable; struct btrfsic_block_link_hashtable block_link_hashtable; @@ -660,8 +659,6 @@ static int btrfsic_process_superblock(struct btrfsic_state *state, return -1; } - state->csum_size = btrfs_super_csum_size(selected_super); - for (pass = 0; pass < 3; pass++) { int num_copies; int mirror_num; @@ -954,7 +951,7 @@ static noinline_for_stack int btrfsic_process_metablock( sf->prev = NULL; continue_with_new_stack_frame: - sf->block->generation = le64_to_cpu(sf->hdr->generation); + sf->block->generation = btrfs_stack_header_generation(sf->hdr); if (0 == sf->hdr->level) { struct btrfs_leaf *const leafhdr = (struct btrfs_leaf *)sf->hdr; @@ -1723,7 +1720,7 @@ static noinline_for_stack int btrfsic_test_for_metadata( crypto_shash_update(shash, data, sublen); } crypto_shash_final(shash, csum); - if (memcmp(csum, h->csum, state->csum_size)) + if (memcmp(csum, h->csum, fs_info->csum_size)) return 1; return 0; /* is metadata */ @@ -2677,7 +2674,7 @@ static void __btrfsic_submit_bio(struct bio *bio) mutex_lock(&btrfsic_mutex); /* since btrfsic_submit_bio() is also called before * btrfsic_mount(), this might return NULL */ - dev_state = btrfsic_dev_state_lookup(bio_dev(bio) + bio->bi_partno); + dev_state = btrfsic_dev_state_lookup(bio->bi_bdev->bd_dev); if (NULL != dev_state && (bio_op(bio) == REQ_OP_WRITE) && bio_has_data(bio)) { unsigned int i = 0; @@ -2693,10 +2690,9 @@ static void __btrfsic_submit_bio(struct bio *bio) bio_is_patched = 0; if (dev_state->state->print_mask & BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH) - pr_info("submit_bio(rw=%d,0x%x, bi_vcnt=%u, bi_sector=%llu (bytenr %llu), bi_disk=%p)\n", + pr_info("submit_bio(rw=%d,0x%x, bi_vcnt=%u, bi_sector=%llu (bytenr %llu), bi_bdev=%p)\n", bio_op(bio), bio->bi_opf, segs, - (unsigned long long)bio->bi_iter.bi_sector, - dev_bytenr, bio->bi_disk); + bio->bi_iter.bi_sector, dev_bytenr, bio->bi_bdev); mapped_datav = kmalloc_array(segs, sizeof(*mapped_datav), GFP_NOFS); @@ -2725,8 +2721,8 @@ static void __btrfsic_submit_bio(struct bio *bio) } else if (NULL != dev_state && (bio->bi_opf & REQ_PREFLUSH)) { if (dev_state->state->print_mask & BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH) - pr_info("submit_bio(rw=%d,0x%x FLUSH, disk=%p)\n", - bio_op(bio), bio->bi_opf, bio->bi_disk); + pr_info("submit_bio(rw=%d,0x%x FLUSH, bdev=%p)\n", + bio_op(bio), bio->bi_opf, bio->bi_bdev); if (!dev_state->dummy_block_for_bio_bh_flush.is_iodone) { if ((dev_state->state->print_mask & (BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH | @@ -2797,7 +2793,6 @@ int btrfsic_mount(struct btrfs_fs_info *fs_info, state->fs_info = fs_info; state->print_mask = print_mask; state->include_extent_data = including_extent_data; - state->csum_size = 0; state->metablock_size = fs_info->nodesize; state->datablock_size = fs_info->sectorsize; INIT_LIST_HEAD(&state->all_blocks_list); diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index eeface30facd..6d203acfdeb3 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -131,10 +131,8 @@ static int btrfs_decompress_bio(struct compressed_bio *cb); static inline int compressed_bio_size(struct btrfs_fs_info *fs_info, unsigned long disk_size) { - u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); - return sizeof(struct compressed_bio) + - (DIV_ROUND_UP(disk_size, fs_info->sectorsize)) * csum_size; + (DIV_ROUND_UP(disk_size, fs_info->sectorsize)) * fs_info->csum_size; } static int check_compressed_csum(struct btrfs_inode *inode, struct bio *bio, @@ -142,7 +140,7 @@ static int check_compressed_csum(struct btrfs_inode *inode, struct bio *bio, { struct btrfs_fs_info *fs_info = inode->root->fs_info; SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); - const u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); + const u32 csum_size = fs_info->csum_size; struct page *page; unsigned long i; char *kaddr; @@ -150,7 +148,7 @@ static int check_compressed_csum(struct btrfs_inode *inode, struct bio *bio, struct compressed_bio *cb = bio->bi_private; u8 *cb_sum = cb->sums; - if (inode->flags & BTRFS_INODE_NODATASUM) + if (!fs_info->csum_root || (inode->flags & BTRFS_INODE_NODATASUM)) return 0; shash->tfm = fs_info->csum_shash; @@ -220,7 +218,7 @@ static void end_compressed_bio_read(struct bio *bio) inode = cb->inode; ret = check_compressed_csum(BTRFS_I(inode), bio, - (u64)bio->bi_iter.bi_sector << 9); + bio->bi_iter.bi_sector << 9); if (ret) goto csum_failed; @@ -544,13 +542,19 @@ static noinline int add_ra_bio_pages(struct inode *inode, goto next; } - end = last_offset + PAGE_SIZE - 1; /* * at this point, we have a locked page in the page cache * for these bytes in the file. But, we have to make * sure they map to this compressed extent on disk. */ - set_page_extent_mapped(page); + ret = set_page_extent_mapped(page); + if (ret < 0) { + unlock_page(page); + put_page(page); + break; + } + + end = last_offset + PAGE_SIZE - 1; lock_extent(tree, last_offset, end); read_lock(&em_tree->lock); em = lookup_extent_mapping(em_tree, last_offset, @@ -622,13 +626,12 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, unsigned long pg_index; struct page *page; struct bio *comp_bio; - u64 cur_disk_byte = (u64)bio->bi_iter.bi_sector << 9; + u64 cur_disk_byte = bio->bi_iter.bi_sector << 9; u64 em_len; u64 em_start; struct extent_map *em; blk_status_t ret = BLK_STS_RESOURCE; int faili = 0; - const u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); u8 *sums; em_tree = &BTRFS_I(inode)->extent_tree; @@ -722,15 +725,12 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, */ refcount_inc(&cb->pending_bios); - if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) { - ret = btrfs_lookup_bio_sums(inode, comp_bio, - (u64)-1, sums); - BUG_ON(ret); /* -ENOMEM */ - } + ret = btrfs_lookup_bio_sums(inode, comp_bio, sums); + BUG_ON(ret); /* -ENOMEM */ nr_sectors = DIV_ROUND_UP(comp_bio->bi_iter.bi_size, fs_info->sectorsize); - sums += csum_size * nr_sectors; + sums += fs_info->csum_size * nr_sectors; ret = btrfs_map_bio(fs_info, comp_bio, mirror_num); if (ret) { @@ -751,10 +751,8 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, ret = btrfs_bio_wq_end_io(fs_info, comp_bio, BTRFS_WQ_ENDIO_DATA); BUG_ON(ret); /* -ENOMEM */ - if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) { - ret = btrfs_lookup_bio_sums(inode, comp_bio, (u64)-1, sums); - BUG_ON(ret); /* -ENOMEM */ - } + ret = btrfs_lookup_bio_sums(inode, comp_bio, sums); + BUG_ON(ret); /* -ENOMEM */ ret = btrfs_map_bio(fs_info, comp_bio, mirror_num); if (ret) { diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 113da62dc17f..d56730a67885 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -221,9 +221,12 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans, ret = btrfs_inc_ref(trans, root, cow, 1); else ret = btrfs_inc_ref(trans, root, cow, 0); - - if (ret) + if (ret) { + btrfs_tree_unlock(cow); + free_extent_buffer(cow); + btrfs_abort_transaction(trans, ret); return ret; + } btrfs_mark_buffer_dirty(cow); *cow_ret = cow; @@ -1278,14 +1281,11 @@ tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct btrfs_path *path, if (!tm) return eb; - btrfs_set_path_blocking(path); - btrfs_set_lock_blocking_read(eb); - if (tm->op == MOD_LOG_KEY_REMOVE_WHILE_FREEING) { BUG_ON(tm->slot != 0); eb_rewin = alloc_dummy_extent_buffer(fs_info, eb->start); if (!eb_rewin) { - btrfs_tree_read_unlock_blocking(eb); + btrfs_tree_read_unlock(eb); free_extent_buffer(eb); return NULL; } @@ -1297,13 +1297,13 @@ tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct btrfs_path *path, } else { eb_rewin = btrfs_clone_extent_buffer(eb); if (!eb_rewin) { - btrfs_tree_read_unlock_blocking(eb); + btrfs_tree_read_unlock(eb); free_extent_buffer(eb); return NULL; } } - btrfs_tree_read_unlock_blocking(eb); + btrfs_tree_read_unlock(eb); free_extent_buffer(eb); btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb_rewin), @@ -1356,7 +1356,8 @@ get_old_root(struct btrfs_root *root, u64 time_seq) if (old_root && tm && tm->op != MOD_LOG_KEY_REMOVE_WHILE_FREEING) { btrfs_tree_read_unlock(eb_root); free_extent_buffer(eb_root); - old = read_tree_block(fs_info, logical, 0, level, NULL); + old = read_tree_block(fs_info, logical, root->root_key.objectid, + 0, level, NULL); if (WARN_ON(IS_ERR(old) || !extent_buffer_uptodate(old))) { if (!IS_ERR(old)) free_extent_buffer(old); @@ -1373,9 +1374,8 @@ get_old_root(struct btrfs_root *root, u64 time_seq) free_extent_buffer(eb_root); eb = alloc_dummy_extent_buffer(fs_info, logical); } else { - btrfs_set_lock_blocking_read(eb_root); eb = btrfs_clone_extent_buffer(eb_root); - btrfs_tree_read_unlock_blocking(eb_root); + btrfs_tree_read_unlock(eb_root); free_extent_buffer(eb_root); } @@ -1483,10 +1483,6 @@ noinline int btrfs_cow_block(struct btrfs_trans_handle *trans, search_start = buf->start & ~((u64)SZ_1G - 1); - if (parent) - btrfs_set_lock_blocking_write(parent); - btrfs_set_lock_blocking_write(buf); - /* * Before CoWing this block for later modification, check if it's * the subtree root and do the delayed subtree trace if needed. @@ -1501,6 +1497,7 @@ noinline int btrfs_cow_block(struct btrfs_trans_handle *trans, return ret; } +ALLOW_ERROR_INJECTION(btrfs_cow_block, ERRNO); /* * helper function for defrag to decide if two blocks pointed to by a @@ -1578,7 +1575,6 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info = root->fs_info; struct extent_buffer *cur; u64 blocknr; - u64 gen; u64 search_start = *last_ret; u64 last_block = 0; u64 other; @@ -1586,14 +1582,10 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans, int end_slot; int i; int err = 0; - int parent_level; - int uptodate; u32 blocksize; int progress_passed = 0; struct btrfs_disk_key disk_key; - parent_level = btrfs_header_level(parent); - WARN_ON(trans->transaction != fs_info->running_transaction); WARN_ON(trans->transid != fs_info->generation); @@ -1604,10 +1596,7 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans, if (parent_nritems <= 1) return 0; - btrfs_set_lock_blocking_write(parent); - for (i = start_slot; i <= end_slot; i++) { - struct btrfs_key first_key; int close = 1; btrfs_node_key(parent, &disk_key, i); @@ -1616,8 +1605,6 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans, progress_passed = 1; blocknr = btrfs_node_blockptr(parent, i); - gen = btrfs_node_ptr_generation(parent, i); - btrfs_node_key_to_cpu(parent, &first_key, i); if (last_block == 0) last_block = blocknr; @@ -1634,36 +1621,13 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans, continue; } - cur = find_extent_buffer(fs_info, blocknr); - if (cur) - uptodate = btrfs_buffer_uptodate(cur, gen, 0); - else - uptodate = 0; - if (!cur || !uptodate) { - if (!cur) { - cur = read_tree_block(fs_info, blocknr, gen, - parent_level - 1, - &first_key); - if (IS_ERR(cur)) { - return PTR_ERR(cur); - } else if (!extent_buffer_uptodate(cur)) { - free_extent_buffer(cur); - return -EIO; - } - } else if (!uptodate) { - err = btrfs_read_buffer(cur, gen, - parent_level - 1,&first_key); - if (err) { - free_extent_buffer(cur); - return err; - } - } - } + cur = btrfs_read_node_slot(parent, i); + if (IS_ERR(cur)) + return PTR_ERR(cur); if (search_start == 0) search_start = last_block; btrfs_tree_lock(cur); - btrfs_set_lock_blocking_write(cur); err = __btrfs_cow_block(trans, root, cur, parent, i, &cur, search_start, min(16 * blocksize, @@ -1723,9 +1687,10 @@ static noinline int generic_bin_search(struct extent_buffer *eb, oip = offset_in_page(offset); if (oip + key_size <= PAGE_SIZE) { - const unsigned long idx = offset >> PAGE_SHIFT; + const unsigned long idx = get_eb_page_index(offset); char *kaddr = page_address(eb->pages[idx]); + oip = get_eb_offset_in_page(eb, offset); tmp = (struct btrfs_disk_key *)(kaddr + oip); } else { read_extent_buffer(eb, &unaligned, offset, key_size); @@ -1801,6 +1766,7 @@ struct extent_buffer *btrfs_read_node_slot(struct extent_buffer *parent, btrfs_node_key_to_cpu(parent, &first_key, slot); eb = read_tree_block(parent->fs_info, btrfs_node_blockptr(parent, slot), + btrfs_header_owner(parent), btrfs_node_ptr_generation(parent, slot), level - 1, &first_key); if (!IS_ERR(eb) && !extent_buffer_uptodate(eb)) { @@ -1835,8 +1801,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, mid = path->nodes[level]; - WARN_ON(path->locks[level] != BTRFS_WRITE_LOCK && - path->locks[level] != BTRFS_WRITE_LOCK_BLOCKING); + WARN_ON(path->locks[level] != BTRFS_WRITE_LOCK); WARN_ON(btrfs_header_generation(mid) != trans->transid); orig_ptr = btrfs_node_blockptr(mid, orig_slot); @@ -1865,7 +1830,6 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, } btrfs_tree_lock(child); - btrfs_set_lock_blocking_write(child); ret = btrfs_cow_block(trans, root, child, mid, 0, &child, BTRFS_NESTING_COW); if (ret) { @@ -1904,7 +1868,6 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, if (left) { __btrfs_tree_lock(left, BTRFS_NESTING_LEFT); - btrfs_set_lock_blocking_write(left); wret = btrfs_cow_block(trans, root, left, parent, pslot - 1, &left, BTRFS_NESTING_LEFT_COW); @@ -1920,7 +1883,6 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, if (right) { __btrfs_tree_lock(right, BTRFS_NESTING_RIGHT); - btrfs_set_lock_blocking_write(right); wret = btrfs_cow_block(trans, root, right, parent, pslot + 1, &right, BTRFS_NESTING_RIGHT_COW); @@ -2084,7 +2046,6 @@ static noinline int push_nodes_for_insert(struct btrfs_trans_handle *trans, u32 left_nr; __btrfs_tree_lock(left, BTRFS_NESTING_LEFT); - btrfs_set_lock_blocking_write(left); left_nr = btrfs_header_nritems(left); if (left_nr >= BTRFS_NODEPTRS_PER_BLOCK(fs_info) - 1) { @@ -2139,7 +2100,6 @@ static noinline int push_nodes_for_insert(struct btrfs_trans_handle *trans, u32 right_nr; __btrfs_tree_lock(right, BTRFS_NESTING_RIGHT); - btrfs_set_lock_blocking_write(right); right_nr = btrfs_header_nritems(right); if (right_nr >= BTRFS_NODEPTRS_PER_BLOCK(fs_info) - 1) { @@ -2243,7 +2203,7 @@ static void reada_for_search(struct btrfs_fs_info *fs_info, search = btrfs_node_blockptr(node, nr); if ((search <= target && target - search <= 65536) || (search > target && search - target <= 65536)) { - readahead_tree_block(fs_info, search); + btrfs_readahead_node_child(node, nr); nread += blocksize; } nscan++; @@ -2252,16 +2212,11 @@ static void reada_for_search(struct btrfs_fs_info *fs_info, } } -static noinline void reada_for_balance(struct btrfs_fs_info *fs_info, - struct btrfs_path *path, int level) +static noinline void reada_for_balance(struct btrfs_path *path, int level) { + struct extent_buffer *parent; int slot; int nritems; - struct extent_buffer *parent; - struct extent_buffer *eb; - u64 gen; - u64 block1 = 0; - u64 block2 = 0; parent = path->nodes[level + 1]; if (!parent) @@ -2270,32 +2225,10 @@ static noinline void reada_for_balance(struct btrfs_fs_info *fs_info, nritems = btrfs_header_nritems(parent); slot = path->slots[level + 1]; - if (slot > 0) { - block1 = btrfs_node_blockptr(parent, slot - 1); - gen = btrfs_node_ptr_generation(parent, slot - 1); - eb = find_extent_buffer(fs_info, block1); - /* - * if we get -eagain from btrfs_buffer_uptodate, we - * don't want to return eagain here. That will loop - * forever - */ - if (eb && btrfs_buffer_uptodate(eb, gen, 1) != 0) - block1 = 0; - free_extent_buffer(eb); - } - if (slot + 1 < nritems) { - block2 = btrfs_node_blockptr(parent, slot + 1); - gen = btrfs_node_ptr_generation(parent, slot + 1); - eb = find_extent_buffer(fs_info, block2); - if (eb && btrfs_buffer_uptodate(eb, gen, 1) != 0) - block2 = 0; - free_extent_buffer(eb); - } - - if (block1) - readahead_tree_block(fs_info, block1); - if (block2) - readahead_tree_block(fs_info, block2); + if (slot > 0) + btrfs_readahead_node_child(parent, slot - 1); + if (slot + 1 < nritems) + btrfs_readahead_node_child(parent, slot + 1); } @@ -2399,14 +2332,6 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p, return 0; } - /* the pages were up to date, but we failed - * the generation number check. Do a full - * read for the generation number that is correct. - * We must do this without dropping locks so - * we can trust our generation number - */ - btrfs_set_path_blocking(p); - /* now we're allowed to do a blocking uptodate check */ ret = btrfs_read_buffer(tmp, gen, parent_level - 1, &first_key); if (!ret) { @@ -2426,14 +2351,13 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p, * out which blocks to read. */ btrfs_unlock_up_safe(p, level + 1); - btrfs_set_path_blocking(p); if (p->reada != READA_NONE) reada_for_search(fs_info, p, level, slot, key->objectid); ret = -EAGAIN; - tmp = read_tree_block(fs_info, blocknr, gen, parent_level - 1, - &first_key); + tmp = read_tree_block(fs_info, blocknr, root->root_key.objectid, + gen, parent_level - 1, &first_key); if (!IS_ERR(tmp)) { /* * If the read above didn't mark this buffer up to date, @@ -2468,58 +2392,42 @@ setup_nodes_for_search(struct btrfs_trans_handle *trans, int *write_lock_level) { struct btrfs_fs_info *fs_info = root->fs_info; - int ret; + int ret = 0; if ((p->search_for_split || ins_len > 0) && btrfs_header_nritems(b) >= BTRFS_NODEPTRS_PER_BLOCK(fs_info) - 3) { - int sret; if (*write_lock_level < level + 1) { *write_lock_level = level + 1; btrfs_release_path(p); - goto again; + return -EAGAIN; } - btrfs_set_path_blocking(p); - reada_for_balance(fs_info, p, level); - sret = split_node(trans, root, p, level); + reada_for_balance(p, level); + ret = split_node(trans, root, p, level); - BUG_ON(sret > 0); - if (sret) { - ret = sret; - goto done; - } b = p->nodes[level]; } else if (ins_len < 0 && btrfs_header_nritems(b) < BTRFS_NODEPTRS_PER_BLOCK(fs_info) / 2) { - int sret; if (*write_lock_level < level + 1) { *write_lock_level = level + 1; btrfs_release_path(p); - goto again; + return -EAGAIN; } - btrfs_set_path_blocking(p); - reada_for_balance(fs_info, p, level); - sret = balance_level(trans, root, p, level); + reada_for_balance(p, level); + ret = balance_level(trans, root, p, level); + if (ret) + return ret; - if (sret) { - ret = sret; - goto done; - } b = p->nodes[level]; if (!b) { btrfs_release_path(p); - goto again; + return -EAGAIN; } BUG_ON(btrfs_header_nritems(b) == 1); } - return 0; - -again: - ret = -EAGAIN; -done: return ret; } @@ -2616,7 +2524,7 @@ static struct extent_buffer *btrfs_search_slot_get_root(struct btrfs_root *root, * We don't know the level of the root node until we actually * have it read locked */ - b = __btrfs_read_lock_root_node(root, p->recurse); + b = btrfs_read_lock_root_node(root); level = btrfs_header_level(b); if (level > write_lock_level) goto out; @@ -2651,8 +2559,14 @@ out: * @p: Holds all btree nodes along the search path * @root: The root node of the tree * @key: The key we are looking for - * @ins_len: Indicates purpose of search, for inserts it is 1, for - * deletions it's -1. 0 for plain searches + * @ins_len: Indicates purpose of search: + * >0 for inserts it's size of item inserted (*) + * <0 for deletions + * 0 for plain searches, not modifying the tree + * + * (*) If size of item inserted doesn't include + * sizeof(struct btrfs_item), then p->search_for_extension must + * be set. * @cow: boolean should CoW operations be performed. Must always be 1 * when modifying the tree. * @@ -2752,7 +2666,6 @@ again: goto again; } - btrfs_set_path_blocking(p); if (last_level) err = btrfs_cow_block(trans, root, b, NULL, 0, &b, @@ -2814,6 +2727,20 @@ cow_done: if (level == 0) { p->slots[level] = slot; + /* + * Item key already exists. In this case, if we are + * allowed to insert the item (for example, in dir_item + * case, item key collision is allowed), it will be + * merged with the original item. Only the item size + * grows, no new btrfs item will be added. If + * search_for_extension is not set, ins_len already + * accounts the size btrfs_item, deduct it here so leaf + * space check will be correct. + */ + if (ret == 0 && ins_len > 0 && !p->search_for_extension) { + ASSERT(ins_len >= sizeof(struct btrfs_item)); + ins_len -= sizeof(struct btrfs_item); + } if (ins_len > 0 && btrfs_leaf_free_space(b) < ins_len) { if (write_lock_level < 1) { @@ -2822,7 +2749,6 @@ cow_done: goto again; } - btrfs_set_path_blocking(p); err = split_leaf(trans, root, key, p, ins_len, ret == 0); @@ -2884,17 +2810,10 @@ cow_done: if (!p->skip_locking) { level = btrfs_header_level(b); if (level <= write_lock_level) { - if (!btrfs_try_tree_write_lock(b)) { - btrfs_set_path_blocking(p); - btrfs_tree_lock(b); - } + btrfs_tree_lock(b); p->locks[level] = BTRFS_WRITE_LOCK; } else { - if (!btrfs_tree_read_lock_atomic(b)) { - btrfs_set_path_blocking(p); - __btrfs_tree_read_lock(b, BTRFS_NESTING_NORMAL, - p->recurse); - } + btrfs_tree_read_lock(b); p->locks[level] = BTRFS_READ_LOCK; } p->nodes[level] = b; @@ -2902,16 +2821,11 @@ cow_done: } ret = 1; done: - /* - * we don't really know what they plan on doing with the path - * from here on, so for now just mark it as blocking - */ - if (!p->leave_spinning) - btrfs_set_path_blocking(p); if (ret < 0 && !p->skip_release_on_error) btrfs_release_path(p); return ret; } +ALLOW_ERROR_INJECTION(btrfs_search_slot, ERRNO); /* * Like btrfs_search_slot, this looks for a key in the given tree. It uses the @@ -2999,10 +2913,7 @@ again: } level = btrfs_header_level(b); - if (!btrfs_tree_read_lock_atomic(b)) { - btrfs_set_path_blocking(p); - btrfs_tree_read_lock(b); - } + btrfs_tree_read_lock(b); b = tree_mod_log_rewind(fs_info, p, b, time_seq); if (!b) { ret = -ENOMEM; @@ -3013,8 +2924,6 @@ again: } ret = 1; done: - if (!p->leave_spinning) - btrfs_set_path_blocking(p); if (ret < 0) btrfs_release_path(p); @@ -3441,7 +3350,7 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans, add_root_to_dirty_list(root); atomic_inc(&c->refs); path->nodes[level] = c; - path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING; + path->locks[level] = BTRFS_WRITE_LOCK; path->slots[level] = 0; return 0; } @@ -3562,7 +3471,6 @@ static noinline int split_node(struct btrfs_trans_handle *trans, (c_nritems - mid) * sizeof(struct btrfs_key_ptr)); btrfs_set_header_nritems(split, c_nritems - mid); btrfs_set_header_nritems(c, mid); - ret = 0; btrfs_mark_buffer_dirty(c); btrfs_mark_buffer_dirty(split); @@ -3580,7 +3488,7 @@ static noinline int split_node(struct btrfs_trans_handle *trans, btrfs_tree_unlock(split); free_extent_buffer(split); } - return ret; + return 0; } /* @@ -3814,7 +3722,6 @@ static int push_leaf_right(struct btrfs_trans_handle *trans, struct btrfs_root return 1; __btrfs_tree_lock(right, BTRFS_NESTING_RIGHT); - btrfs_set_lock_blocking_write(right); free_space = btrfs_leaf_free_space(right); if (free_space < data_size) @@ -4053,7 +3960,6 @@ static int push_leaf_left(struct btrfs_trans_handle *trans, struct btrfs_root return 1; __btrfs_tree_lock(left, BTRFS_NESTING_LEFT); - btrfs_set_lock_blocking_write(left); free_space = btrfs_leaf_free_space(left); if (free_space < data_size) { @@ -4448,7 +4354,6 @@ static noinline int setup_leaf_for_split(struct btrfs_trans_handle *trans, goto err; } - btrfs_set_path_blocking(path); ret = split_leaf(trans, root, &key, path, ins_len, 1); if (ret) goto err; @@ -4478,8 +4383,6 @@ static noinline int split_item(struct btrfs_path *path, leaf = path->nodes[0]; BUG_ON(btrfs_leaf_free_space(leaf) < sizeof(struct btrfs_item)); - btrfs_set_path_blocking(path); - item = btrfs_item_nr(path->slots[0]); orig_offset = btrfs_item_offset(leaf, item); item_size = btrfs_item_size(leaf, item); @@ -5055,7 +4958,6 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, if (leaf == root->node) { btrfs_set_header_level(leaf, 0); } else { - btrfs_set_path_blocking(path); btrfs_clean_tree_block(leaf); btrfs_del_leaf(trans, root, path, leaf); } @@ -5077,7 +4979,6 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, slot = path->slots[1]; atomic_inc(&leaf->refs); - btrfs_set_path_blocking(path); wret = push_leaf_left(trans, root, path, 1, 1, 1, (u32)-1); if (wret < 0 && wret != -ENOSPC) @@ -5248,7 +5149,6 @@ find_next_key: */ if (slot >= nritems) { path->slots[level] = slot; - btrfs_set_path_blocking(path); sret = btrfs_find_next_key(root, path, min_key, level, min_trans); if (sret == 0) { @@ -5265,7 +5165,6 @@ find_next_key: ret = 0; goto out; } - btrfs_set_path_blocking(path); cur = btrfs_read_node_slot(cur, slot); if (IS_ERR(cur)) { ret = PTR_ERR(cur); @@ -5282,7 +5181,6 @@ out: path->keep_locks = keep_locks; if (ret == 0) { btrfs_unlock_up_safe(path, path->lowest_level + 1); - btrfs_set_path_blocking(path); memcpy(min_key, &found_key, sizeof(found_key)); } return ret; @@ -5384,8 +5282,7 @@ int btrfs_next_old_leaf(struct btrfs_root *root, struct btrfs_path *path, struct btrfs_key key; u32 nritems; int ret; - int old_spinning = path->leave_spinning; - int next_rw_lock = 0; + int i; nritems = btrfs_header_nritems(path->nodes[0]); if (nritems == 0) @@ -5395,11 +5292,9 @@ int btrfs_next_old_leaf(struct btrfs_root *root, struct btrfs_path *path, again: level = 1; next = NULL; - next_rw_lock = 0; btrfs_release_path(path); path->keep_locks = 1; - path->leave_spinning = 1; if (time_seq) ret = btrfs_search_old_slot(root, &key, path, time_seq); @@ -5459,13 +5354,22 @@ again: continue; } - if (next) { - btrfs_tree_unlock_rw(next, next_rw_lock); - free_extent_buffer(next); + + /* + * Our current level is where we're going to start from, and to + * make sure lockdep doesn't complain we need to drop our locks + * and nodes from 0 to our current level. + */ + for (i = 0; i < level; i++) { + if (path->locks[level]) { + btrfs_tree_read_unlock(path->nodes[i]); + path->locks[i] = 0; + } + free_extent_buffer(path->nodes[i]); + path->nodes[i] = NULL; } next = c; - next_rw_lock = path->locks[level]; ret = read_block_for_search(root, path, &next, level, slot, &key); if (ret == -EAGAIN) @@ -5491,28 +5395,18 @@ again: cond_resched(); goto again; } - if (!ret) { - btrfs_set_path_blocking(path); - __btrfs_tree_read_lock(next, - BTRFS_NESTING_RIGHT, - path->recurse); - } - next_rw_lock = BTRFS_READ_LOCK; + if (!ret) + btrfs_tree_read_lock(next); } break; } path->slots[level] = slot; while (1) { level--; - c = path->nodes[level]; - if (path->locks[level]) - btrfs_tree_unlock_rw(c, path->locks[level]); - - free_extent_buffer(c); path->nodes[level] = next; path->slots[level] = 0; if (!path->skip_locking) - path->locks[level] = next_rw_lock; + path->locks[level] = BTRFS_READ_LOCK; if (!level) break; @@ -5526,23 +5420,12 @@ again: goto done; } - if (!path->skip_locking) { - ret = btrfs_try_tree_read_lock(next); - if (!ret) { - btrfs_set_path_blocking(path); - __btrfs_tree_read_lock(next, - BTRFS_NESTING_RIGHT, - path->recurse); - } - next_rw_lock = BTRFS_READ_LOCK; - } + if (!path->skip_locking) + btrfs_tree_read_lock(next); } ret = 0; done: unlock_up(path, 0, 1, 0, NULL); - path->leave_spinning = old_spinning; - if (!old_spinning) - btrfs_set_path_blocking(path); return ret; } @@ -5564,7 +5447,6 @@ int btrfs_previous_item(struct btrfs_root *root, while (1) { if (path->slots[0] == 0) { - btrfs_set_path_blocking(path); ret = btrfs_prev_leaf(root, path); if (ret != 0) return ret; @@ -5606,7 +5488,6 @@ int btrfs_previous_extent_item(struct btrfs_root *root, while (1) { if (path->slots[0] == 0) { - btrfs_set_path_blocking(path); ret = btrfs_prev_leaf(root, path); if (ret != 0) return ret; diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index aac3d6f4e35b..3bc00aed13b2 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -17,7 +17,6 @@ #include <linux/wait.h> #include <linux/slab.h> #include <trace/events/btrfs.h> -#include <asm/kmap_types.h> #include <asm/unaligned.h> #include <linux/pagemap.h> #include <linux/btrfs.h> @@ -28,6 +27,7 @@ #include <linux/dynamic_debug.h> #include <linux/refcount.h> #include <linux/crc32c.h> +#include <linux/iomap.h> #include "extent-io-tree.h" #include "extent_io.h" #include "extent_map.h" @@ -67,12 +67,6 @@ struct btrfs_ref; #define BTRFS_OLDEST_GENERATION 0ULL /* - * the max metadata block size. This limit is somewhat artificial, - * but the memmove costs go through the roof for larger blocks. - */ -#define BTRFS_MAX_METADATA_BLOCKSIZE 65536 - -/* * we can actually store much bigger names, but lets not confuse the rest * of linux */ @@ -137,6 +131,8 @@ enum { * defrag */ BTRFS_FS_STATE_REMOUNTING, + /* Filesystem in RO mode */ + BTRFS_FS_STATE_RO, /* Track if a transaction abort has been reported on this filesystem */ BTRFS_FS_STATE_TRANS_ABORTED, /* @@ -302,7 +298,8 @@ struct btrfs_super_block { BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA | \ BTRFS_FEATURE_INCOMPAT_NO_HOLES | \ BTRFS_FEATURE_INCOMPAT_METADATA_UUID | \ - BTRFS_FEATURE_INCOMPAT_RAID1C34) + BTRFS_FEATURE_INCOMPAT_RAID1C34 | \ + BTRFS_FEATURE_INCOMPAT_ZONED) #define BTRFS_FEATURE_INCOMPAT_SAFE_SET \ (BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF) @@ -370,11 +367,15 @@ struct btrfs_path { unsigned int search_for_split:1; unsigned int keep_locks:1; unsigned int skip_locking:1; - unsigned int leave_spinning:1; unsigned int search_commit_root:1; unsigned int need_commit_sem:1; unsigned int skip_release_on_error:1; - unsigned int recurse:1; + /* + * Indicate that new item (btrfs_search_slot) is extending already + * existing item and ins_len contains only the data size and not item + * header (ie. sizeof(struct btrfs_item) is not included). + */ + unsigned int search_for_extension:1; }; #define BTRFS_MAX_EXTENT_ITEM_SIZE(r) ((BTRFS_LEAF_DATA_SIZE(r->fs_info) >> 4) - \ sizeof(struct btrfs_item)) @@ -469,10 +470,11 @@ struct btrfs_discard_ctl { struct btrfs_block_group *block_group; struct list_head discard_list[BTRFS_NR_DISCARD_LISTS]; u64 prev_discard; + u64 prev_discard_time; atomic_t discardable_extents; atomic64_t discardable_bytes; u64 max_discard_size; - unsigned long delay; + u64 delay_ms; u32 iops_limit; u32 kbps_limit; u64 discard_extent_bytes; @@ -559,6 +561,12 @@ enum { /* Indicate that the discard workqueue can service discards. */ BTRFS_FS_DISCARD_RUNNING, + + /* Indicate that we need to cleanup space cache v1 */ + BTRFS_FS_CLEANUP_SPACE_CACHE_V1, + + /* Indicate that we can't trust the free space tree for caching yet */ + BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, }; /* @@ -790,7 +798,7 @@ struct btrfs_fs_info { /* used to keep from writing metadata until there is a nice batch */ struct percpu_counter dirty_metadata_bytes; struct percpu_counter delalloc_bytes; - struct percpu_counter dio_bytes; + struct percpu_counter ordered_bytes; s32 dirty_metadata_batch; s32 delalloc_batch; @@ -878,7 +886,10 @@ struct btrfs_fs_info { */ struct ulist *qgroup_ulist; - /* protect user change for quota operations */ + /* + * Protect user change for quota operations. If a transaction is needed, + * it must be started before locking this lock. + */ struct mutex qgroup_ioctl_lock; /* list of dirty qgroups to be written at next commit */ @@ -909,6 +920,7 @@ struct btrfs_fs_info { /* Extent buffer radix tree */ spinlock_t buffer_lock; + /* Entries are eb->start / sectorsize */ struct radix_tree_root buffer_radix; /* next backup root to be overwritten */ @@ -922,6 +934,7 @@ struct btrfs_fs_info { /* Used to reclaim the metadata space in the background. */ struct work_struct async_reclaim_work; struct work_struct async_data_reclaim_work; + struct work_struct preempt_reclaim_work; spinlock_t unused_bgs_lock; struct list_head unused_bgs; @@ -931,6 +944,10 @@ struct btrfs_fs_info { /* Cached block sizes */ u32 nodesize; u32 sectorsize; + /* ilog2 of sectorsize, use to avoid 64bit division */ + u32 sectorsize_bits; + u32 csum_size; + u32 csums_per_leaf; u32 stripesize; /* Block groups and devices containing active swapfiles. */ @@ -948,6 +965,21 @@ struct btrfs_fs_info { /* Type of exclusive operation running */ unsigned long exclusive_operation; + /* + * Zone size > 0 when in ZONED mode, otherwise it's used for a check + * if the mode is enabled + */ + union { + u64 zone_size; + u64 zoned; + }; + + /* Max size to emit ZONE_APPEND write command */ + u64 max_zone_append_size; + struct mutex zoned_meta_io_lock; + spinlock_t treelog_bg_lock; + u64 treelog_bg; + #ifdef CONFIG_BTRFS_FS_REF_VERIFY spinlock_t ref_verify_lock; struct rb_root block_tree; @@ -1018,7 +1050,7 @@ enum { BTRFS_ROOT_DEAD_RELOC_TREE, /* Mark dead root stored on device whose cleanup needs to be resumed */ BTRFS_ROOT_DEAD_TREE, - /* The root has a log tree. Used only for subvolume roots. */ + /* The root has a log tree. Used for subvolume roots and the tree root. */ BTRFS_ROOT_HAS_LOG_TREE, /* Qgroup flushing is in progress */ BTRFS_ROOT_QGROUP_FLUSHING, @@ -1057,15 +1089,6 @@ struct btrfs_root { spinlock_t accounting_lock; struct btrfs_block_rsv *block_rsv; - /* free ino cache stuff */ - struct btrfs_free_space_ctl *free_ino_ctl; - enum btrfs_caching_type ino_cache_state; - spinlock_t ino_cache_lock; - wait_queue_head_t ino_cache_wait; - struct btrfs_free_space_ctl *free_ino_pinned; - u64 ino_cache_progress; - struct inode *ino_cache_inode; - struct mutex log_mutex; wait_queue_head_t log_writer_wait; wait_queue_head_t log_commit_wait[2]; @@ -1086,7 +1109,7 @@ struct btrfs_root { u32 type; - u64 highest_objectid; + u64 free_objectid; struct btrfs_key defrag_progress; struct btrfs_key defrag_max; @@ -1224,6 +1247,63 @@ struct btrfs_replace_extent_info { int insertions; }; +/* Arguments for btrfs_drop_extents() */ +struct btrfs_drop_extents_args { + /* Input parameters */ + + /* + * If NULL, btrfs_drop_extents() will allocate and free its own path. + * If 'replace_extent' is true, this must not be NULL. Also the path + * is always released except if 'replace_extent' is true and + * btrfs_drop_extents() sets 'extent_inserted' to true, in which case + * the path is kept locked. + */ + struct btrfs_path *path; + /* Start offset of the range to drop extents from */ + u64 start; + /* End (exclusive, last byte + 1) of the range to drop extents from */ + u64 end; + /* If true drop all the extent maps in the range */ + bool drop_cache; + /* + * If true it means we want to insert a new extent after dropping all + * the extents in the range. If this is true, the 'extent_item_size' + * parameter must be set as well and the 'extent_inserted' field will + * be set to true by btrfs_drop_extents() if it could insert the new + * extent. + * Note: when this is set to true the path must not be NULL. + */ + bool replace_extent; + /* + * Used if 'replace_extent' is true. Size of the file extent item to + * insert after dropping all existing extents in the range + */ + u32 extent_item_size; + + /* Output parameters */ + + /* + * Set to the minimum between the input parameter 'end' and the end + * (exclusive, last byte + 1) of the last dropped extent. This is always + * set even if btrfs_drop_extents() returns an error. + */ + u64 drop_end; + /* + * The number of allocated bytes found in the range. This can be smaller + * than the range's length when there are holes in the range. + */ + u64 bytes_found; + /* + * Only set if 'replace_extent' is true. Set to true if we were able + * to insert a replacement extent after dropping all extents in the + * range, otherwise set to false by btrfs_drop_extents(). + * Also, if btrfs_drop_extents() has set this to true it means it + * returned with the path locked, otherwise if it has set this to + * false it has returned with the path released. + */ + bool extent_inserted; +}; + struct btrfs_file_private { void *filldir_buf; }; @@ -1282,7 +1362,7 @@ static inline u32 BTRFS_MAX_XATTR_SIZE(const struct btrfs_fs_info *info) #define BTRFS_MOUNT_USER_SUBVOL_RM_ALLOWED (1 << 14) #define BTRFS_MOUNT_ENOSPC_DEBUG (1 << 15) #define BTRFS_MOUNT_AUTO_DEFRAG (1 << 16) -#define BTRFS_MOUNT_INODE_MAP_CACHE (1 << 17) +/* bit 17 is free */ #define BTRFS_MOUNT_USEBACKUPROOT (1 << 18) #define BTRFS_MOUNT_SKIP_BALANCE (1 << 19) #define BTRFS_MOUNT_CHECK_INTEGRITY (1 << 20) @@ -1295,6 +1375,8 @@ static inline u32 BTRFS_MAX_XATTR_SIZE(const struct btrfs_fs_info *info) #define BTRFS_MOUNT_NOLOGREPLAY (1 << 27) #define BTRFS_MOUNT_REF_VERIFY (1 << 28) #define BTRFS_MOUNT_DISCARD_ASYNC (1 << 29) +#define BTRFS_MOUNT_IGNOREBADROOTS (1 << 30) +#define BTRFS_MOUNT_IGNOREDATACSUMS (1 << 31) #define BTRFS_DEFAULT_COMMIT_INTERVAL (30) #define BTRFS_DEFAULT_MAX_INLINE (2048) @@ -1327,9 +1409,7 @@ do { \ * transaction commit) */ -#define BTRFS_PENDING_SET_INODE_MAP_CACHE (0) -#define BTRFS_PENDING_CLEAR_INODE_MAP_CACHE (1) -#define BTRFS_PENDING_COMMIT (2) +#define BTRFS_PENDING_COMMIT (0) #define btrfs_test_pending(info, opt) \ test_bit(BTRFS_PENDING_##opt, &(info)->pending_changes) @@ -1402,7 +1482,7 @@ struct btrfs_map_token { }; #define BTRFS_BYTES_TO_BLKS(fs_info, bytes) \ - ((bytes) >> (fs_info)->sb->s_blocksize_bits) + ((bytes) >> (fs_info)->sectorsize_bits) static inline void btrfs_init_map_token(struct btrfs_map_token *token, struct extent_buffer *eb) @@ -1487,13 +1567,14 @@ static inline void btrfs_set_token_##name(struct btrfs_map_token *token,\ #define BTRFS_SETGET_HEADER_FUNCS(name, type, member, bits) \ static inline u##bits btrfs_##name(const struct extent_buffer *eb) \ { \ - const type *p = page_address(eb->pages[0]); \ + const type *p = page_address(eb->pages[0]) + \ + offset_in_page(eb->start); \ return get_unaligned_le##bits(&p->member); \ } \ static inline void btrfs_set_##name(const struct extent_buffer *eb, \ u##bits val) \ { \ - type *p = page_address(eb->pages[0]); \ + type *p = page_address(eb->pages[0]) + offset_in_page(eb->start); \ put_unaligned_le##bits(val, &p->member); \ } @@ -2083,6 +2164,7 @@ BTRFS_SETGET_FUNCS(disk_root_level, struct btrfs_root_item, level, 8); BTRFS_SETGET_STACK_FUNCS(root_generation, struct btrfs_root_item, generation, 64); BTRFS_SETGET_STACK_FUNCS(root_bytenr, struct btrfs_root_item, bytenr, 64); +BTRFS_SETGET_STACK_FUNCS(root_drop_level, struct btrfs_root_item, drop_level, 8); BTRFS_SETGET_STACK_FUNCS(root_level, struct btrfs_root_item, level, 8); BTRFS_SETGET_STACK_FUNCS(root_dirid, struct btrfs_root_item, root_dirid, 64); BTRFS_SETGET_STACK_FUNCS(root_refs, struct btrfs_root_item, refs, 32); @@ -2515,7 +2597,17 @@ int btrfs_get_extent_inline_ref_type(const struct extent_buffer *eb, enum btrfs_inline_ref_type is_data); u64 hash_extent_data_ref(u64 root_objectid, u64 owner, u64 offset); -u64 btrfs_csum_bytes_to_leaves(struct btrfs_fs_info *fs_info, u64 csum_bytes); +/* + * Take the number of bytes to be checksummmed and figure out how many leaves + * it would require to store the csums for that many bytes. + */ +static inline u64 btrfs_csum_bytes_to_leaves( + const struct btrfs_fs_info *fs_info, u64 csum_bytes) +{ + const u64 num_csums = csum_bytes >> fs_info->sectorsize_bits; + + return DIV_ROUND_UP_ULL(num_csums, fs_info->csums_per_leaf); +} /* * Use this if we would be adding new items, as we could split nodes as we cow @@ -2590,7 +2682,6 @@ int btrfs_free_reserved_extent(struct btrfs_fs_info *fs_info, u64 start, u64 len, int delalloc); int btrfs_pin_reserved_extent(struct btrfs_trans_handle *trans, u64 start, u64 len); -void btrfs_prepare_extent_commit(struct btrfs_fs_info *fs_info); int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans); int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, struct btrfs_ref *generic_ref); @@ -2654,6 +2745,7 @@ enum btrfs_flush_state { ALLOC_CHUNK_FORCE = 8, RUN_DELAYED_IPUTS = 9, COMMIT_TRANS = 10, + FORCE_COMMIT_TRANS = 11, }; int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, @@ -2810,10 +2902,26 @@ static inline int btrfs_fs_closing(struct btrfs_fs_info *fs_info) * If we remount the fs to be R/O or umount the fs, the cleaner needn't do * anything except sleeping. This function is used to check the status of * the fs. + * We check for BTRFS_FS_STATE_RO to avoid races with a concurrent remount, + * since setting and checking for SB_RDONLY in the superblock's flags is not + * atomic. */ static inline int btrfs_need_cleaner_sleep(struct btrfs_fs_info *fs_info) { - return fs_info->sb->s_flags & SB_RDONLY || btrfs_fs_closing(fs_info); + return test_bit(BTRFS_FS_STATE_RO, &fs_info->fs_state) || + btrfs_fs_closing(fs_info); +} + +static inline void btrfs_set_sb_rdonly(struct super_block *sb) +{ + sb->s_flags |= SB_RDONLY; + set_bit(BTRFS_FS_STATE_RO, &btrfs_sb(sb)->fs_state); +} + +static inline void btrfs_clear_sb_rdonly(struct super_block *sb) +{ + sb->s_flags &= ~SB_RDONLY; + clear_bit(BTRFS_FS_STATE_RO, &btrfs_sb(sb)->fs_state); } /* tree mod log functions from ctree.c */ @@ -2937,8 +3045,7 @@ struct btrfs_inode_extref *btrfs_find_name_in_ext_backref( struct btrfs_dio_private; int btrfs_del_csums(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 len); -blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, - u64 offset, u8 *dst); +blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u8 *dst); int btrfs_insert_file_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 objectid, u64 pos, @@ -2965,13 +3072,13 @@ int btrfs_inode_clear_file_extent_range(struct btrfs_inode *inode, u64 start, u64 len); int btrfs_inode_set_file_extent_range(struct btrfs_inode *inode, u64 start, u64 len); -void btrfs_inode_safe_disk_i_size_write(struct inode *inode, u64 new_i_size); +void btrfs_inode_safe_disk_i_size_write(struct btrfs_inode *inode, u64 new_i_size); u64 btrfs_file_extent_end(const struct btrfs_path *path); /* inode.c */ blk_status_t btrfs_submit_data_bio(struct inode *inode, struct bio *bio, int mirror_num, unsigned long bio_flags); -int btrfs_verify_data_csum(struct btrfs_io_bio *io_bio, u64 phy_offset, +int btrfs_verify_data_csum(struct btrfs_io_bio *io_bio, u32 bio_offset, struct page *page, u64 start, u64 end, int mirror); struct extent_map *btrfs_get_extent_fiemap(struct btrfs_inode *inode, u64 start, u64 len); @@ -2991,22 +3098,22 @@ int btrfs_add_link(struct btrfs_trans_handle *trans, struct btrfs_inode *parent_inode, struct btrfs_inode *inode, const char *name, int name_len, int add_backref, u64 index); int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry); -int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len, - int front); +int btrfs_truncate_block(struct btrfs_inode *inode, loff_t from, loff_t len, + int front); int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, - struct inode *inode, u64 new_size, + struct btrfs_inode *inode, u64 new_size, u32 min_type); int btrfs_start_delalloc_snapshot(struct btrfs_root *root); -int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr); +int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, long nr, + bool in_reclaim_context); int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end, unsigned int extra_bits, struct extent_state **cached_state); int btrfs_create_subvol_root(struct btrfs_trans_handle *trans, struct btrfs_root *new_root, - struct btrfs_root *parent_root, - u64 new_dirid); + struct btrfs_root *parent_root); void btrfs_set_delalloc_extent(struct inode *inode, struct extent_state *state, unsigned *bits); void btrfs_clear_delalloc_extent(struct inode *inode, @@ -3017,6 +3124,8 @@ void btrfs_split_delalloc_extent(struct inode *inode, struct extent_state *orig, u64 split); int btrfs_bio_fits_in_stripe(struct page *page, size_t size, struct bio *bio, unsigned long bio_flags); +bool btrfs_bio_fits_in_ordered_extent(struct page *page, struct bio *bio, + unsigned int size); void btrfs_set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end); vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf); int btrfs_readpage(struct file *file, struct page *page); @@ -3035,14 +3144,13 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode, struct page *page, size_t pg_offset, u64 start, u64 end); int btrfs_update_inode(struct btrfs_trans_handle *trans, - struct btrfs_root *root, - struct inode *inode); + struct btrfs_root *root, struct btrfs_inode *inode); int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans, - struct btrfs_root *root, struct inode *inode); + struct btrfs_root *root, struct btrfs_inode *inode); int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct btrfs_inode *inode); int btrfs_orphan_cleanup(struct btrfs_root *root); -int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size); +int btrfs_cont_expand(struct btrfs_inode *inode, loff_t oldsize, loff_t size); void btrfs_add_delayed_iput(struct inode *inode); void btrfs_run_delayed_iputs(struct btrfs_fs_info *fs_info); int btrfs_wait_on_delayed_iputs(struct btrfs_fs_info *fs_info); @@ -3060,7 +3168,18 @@ int btrfs_writepage_cow_fixup(struct page *page, u64 start, u64 end); void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start, u64 end, int uptodate); extern const struct dentry_operations btrfs_dentry_operations; -ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter); +extern const struct iomap_ops btrfs_dio_iomap_ops; +extern const struct iomap_dio_ops btrfs_dio_ops; + +/* Inode locking type flags, by default the exclusive lock is taken */ +#define BTRFS_ILOCK_SHARED (1U << 0) +#define BTRFS_ILOCK_TRY (1U << 1) + +int btrfs_inode_lock(struct inode *inode, unsigned int ilock_flags); +void btrfs_inode_unlock(struct inode *inode, unsigned int ilock_flags); +void btrfs_update_inode_bytes(struct btrfs_inode *inode, + const u64 add_bytes, + const u64 del_bytes); /* ioctl.c */ long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); @@ -3090,16 +3209,9 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync); void btrfs_drop_extent_cache(struct btrfs_inode *inode, u64 start, u64 end, int skip_pinned); extern const struct file_operations btrfs_file_operations; -int __btrfs_drop_extents(struct btrfs_trans_handle *trans, - struct btrfs_root *root, struct btrfs_inode *inode, - struct btrfs_path *path, u64 start, u64 end, - u64 *drop_end, int drop_cache, - int replace_extent, - u32 extent_item_size, - int *key_inserted); int btrfs_drop_extents(struct btrfs_trans_handle *trans, - struct btrfs_root *root, struct inode *inode, u64 start, - u64 end, int drop_cache); + struct btrfs_root *root, struct btrfs_inode *inode, + struct btrfs_drop_extents_args *args); int btrfs_replace_file_extents(struct inode *inode, struct btrfs_path *path, const u64 start, const u64 end, struct btrfs_replace_extent_info *extent_info, @@ -3109,7 +3221,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans, int btrfs_release_file(struct inode *inode, struct file *file); int btrfs_dirty_pages(struct btrfs_inode *inode, struct page **pages, size_t num_pages, loff_t pos, size_t write_bytes, - struct extent_state **cached); + struct extent_state **cached, bool noreserve); int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end); int btrfs_check_nocow_lock(struct btrfs_inode *inode, loff_t pos, size_t *write_bytes); @@ -3289,6 +3401,39 @@ static inline void assertfail(const char *expr, const char* file, int line) { } #endif /* + * Get the correct offset inside the page of extent buffer. + * + * @eb: target extent buffer + * @start: offset inside the extent buffer + * + * Will handle both sectorsize == PAGE_SIZE and sectorsize < PAGE_SIZE cases. + */ +static inline size_t get_eb_offset_in_page(const struct extent_buffer *eb, + unsigned long offset) +{ + /* + * For sectorsize == PAGE_SIZE case, eb->start will always be aligned + * to PAGE_SIZE, thus adding it won't cause any difference. + * + * For sectorsize < PAGE_SIZE, we must only read the data that belongs + * to the eb, thus we have to take the eb->start into consideration. + */ + return offset_in_page(offset + eb->start); +} + +static inline unsigned long get_eb_page_index(unsigned long offset) +{ + /* + * For sectorsize == PAGE_SIZE case, plain >> PAGE_SHIFT is enough. + * + * For sectorsize < PAGE_SIZE case, we only support 64K PAGE_SIZE, + * and have ensured that all tree blocks are contained in one page, + * thus we always get index == 0. + */ + return offset >> PAGE_SHIFT; +} + +/* * Use that for functions that are conditionally exported for sanity tests but * otherwise static */ @@ -3564,6 +3709,8 @@ struct reada_control *btrfs_reada_add(struct btrfs_root *root, int btrfs_reada_wait(void *handle); void btrfs_reada_detach(void *handle); int btree_readahead_hook(struct extent_buffer *eb, int err); +void btrfs_reada_remove_dev(struct btrfs_device *dev); +void btrfs_reada_undo_remove_dev(struct btrfs_device *dev); static inline int is_fstree(u64 rootid) { @@ -3595,4 +3742,9 @@ static inline int btrfs_is_testing(struct btrfs_fs_info *fs_info) } #endif +static inline bool btrfs_is_zoned(const struct btrfs_fs_info *fs_info) +{ + return fs_info->zoned != 0; +} + #endif diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c index bacee09b7bfd..56642ca7af10 100644 --- a/fs/btrfs/delalloc-space.c +++ b/fs/btrfs/delalloc-space.c @@ -191,12 +191,14 @@ void btrfs_free_reserved_data_space(struct btrfs_inode *inode, } /** - * btrfs_inode_rsv_release - release any excessive reservation. - * @inode - the inode we need to release from. - * @qgroup_free - free or convert qgroup meta. - * Unlike normal operation, qgroup meta reservation needs to know if we are - * freeing qgroup reservation or just converting it into per-trans. Normally - * @qgroup_free is true for error handling, and false for normal release. + * Release any excessive reservation + * + * @inode: the inode we need to release from + * @qgroup_free: free or convert qgroup meta. Unlike normal operation, qgroup + * meta reservation needs to know if we are freeing qgroup + * reservation or just converting it into per-trans. Normally + * @qgroup_free is true for error handling, and false for normal + * release. * * This is the same as btrfs_block_rsv_release, except that it handles the * tracepoint for the reservation. @@ -361,7 +363,8 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes) } /** - * btrfs_delalloc_release_metadata - release a metadata reservation for an inode + * Release a metadata reservation for an inode + * * @inode: the inode to release the reservation for. * @num_bytes: the number of bytes we are releasing. * @qgroup_free: free qgroup reservation or convert it to per-trans reservation @@ -455,11 +458,13 @@ int btrfs_delalloc_reserve_space(struct btrfs_inode *inode, } /** - * btrfs_delalloc_release_space - release data and metadata space for delalloc - * @inode: inode we're releasing space for - * @start: start position of the space already reserved - * @len: the len of the space already reserved - * @release_bytes: the len of the space we consumed or didn't use + * Release data and metadata space for delalloc + * + * @inode: inode we're releasing space for + * @reserved: list of changed/reserved ranges + * @start: start position of the space already reserved + * @len: length of the space already reserved + * @qgroup_free: should qgroup reserved-space also be freed * * This function will release the metadata space that was not used and will * decrement ->delalloc_bytes and remove it from the fs_info delalloc_inodes diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 5aba81e16113..ec0b50b8c5d6 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -740,13 +740,6 @@ static int btrfs_batch_insert_items(struct btrfs_root *root, goto out; } - /* - * we need allocate some memory space, but it might cause the task - * to sleep, so we set all locked nodes in the path to blocking locks - * first. - */ - btrfs_set_path_blocking(path); - keys = kmalloc_array(nitems, sizeof(struct btrfs_key), GFP_NOFS); if (!keys) { ret = -ENOMEM; @@ -1154,7 +1147,6 @@ static int __btrfs_run_delayed_items(struct btrfs_trans_handle *trans, int nr) path = btrfs_alloc_path(); if (!path) return -ENOMEM; - path->leave_spinning = 1; block_rsv = trans->block_rsv; trans->block_rsv = &fs_info->delayed_block_rsv; @@ -1162,7 +1154,7 @@ static int __btrfs_run_delayed_items(struct btrfs_trans_handle *trans, int nr) delayed_root = fs_info->delayed_root; curr_node = btrfs_first_delayed_node(delayed_root); - while (curr_node && (!count || (count && nr--))) { + while (curr_node && (!count || nr--)) { ret = __btrfs_commit_inode_delayed_items(trans, path, curr_node); if (ret) { @@ -1219,7 +1211,6 @@ int btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans, btrfs_release_delayed_node(delayed_node); return -ENOMEM; } - path->leave_spinning = 1; block_rsv = trans->block_rsv; trans->block_rsv = &delayed_node->root->fs_info->delayed_block_rsv; @@ -1264,7 +1255,6 @@ int btrfs_commit_inode_delayed_inode(struct btrfs_inode *inode) ret = -ENOMEM; goto trans_out; } - path->leave_spinning = 1; block_rsv = trans->block_rsv; trans->block_rsv = &fs_info->delayed_block_rsv; @@ -1333,7 +1323,6 @@ static void btrfs_async_run_delayed_root(struct btrfs_work *work) if (!delayed_node) break; - path->leave_spinning = 1; root = delayed_node->root; trans = btrfs_join_transaction(root); @@ -1826,27 +1815,29 @@ int btrfs_fill_inode(struct inode *inode, u32 *rdev) } int btrfs_delayed_update_inode(struct btrfs_trans_handle *trans, - struct btrfs_root *root, struct inode *inode) + struct btrfs_root *root, + struct btrfs_inode *inode) { struct btrfs_delayed_node *delayed_node; int ret = 0; - delayed_node = btrfs_get_or_create_delayed_node(BTRFS_I(inode)); + delayed_node = btrfs_get_or_create_delayed_node(inode); if (IS_ERR(delayed_node)) return PTR_ERR(delayed_node); mutex_lock(&delayed_node->mutex); if (test_bit(BTRFS_DELAYED_NODE_INODE_DIRTY, &delayed_node->flags)) { - fill_stack_inode_item(trans, &delayed_node->inode_item, inode); + fill_stack_inode_item(trans, &delayed_node->inode_item, + &inode->vfs_inode); goto release_node; } - ret = btrfs_delayed_inode_reserve_metadata(trans, root, BTRFS_I(inode), + ret = btrfs_delayed_inode_reserve_metadata(trans, root, inode, delayed_node); if (ret) goto release_node; - fill_stack_inode_item(trans, &delayed_node->inode_item, inode); + fill_stack_inode_item(trans, &delayed_node->inode_item, &inode->vfs_inode); set_bit(BTRFS_DELAYED_NODE_INODE_DIRTY, &delayed_node->flags); delayed_node->count++; atomic_inc(&root->fs_info->delayed_root->items); diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h index ca96ef007d8f..b2412160c5bc 100644 --- a/fs/btrfs/delayed-inode.h +++ b/fs/btrfs/delayed-inode.h @@ -110,7 +110,8 @@ int btrfs_commit_inode_delayed_inode(struct btrfs_inode *inode); int btrfs_delayed_update_inode(struct btrfs_trans_handle *trans, - struct btrfs_root *root, struct inode *inode); + struct btrfs_root *root, + struct btrfs_inode *inode); int btrfs_fill_inode(struct inode *inode, u32 *rdev); int btrfs_delayed_delete_inode_ref(struct btrfs_inode *inode); diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index 353cc2994d10..63be7d01a9a3 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -69,9 +69,10 @@ int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans) } /** - * btrfs_delayed_refs_rsv_release - release a ref head's reservation. - * @fs_info - the fs_info for our fs. - * @nr - the number of items to drop. + * Release a ref head's reservation + * + * @fs_info: the filesystem + * @nr: number of items to drop * * This drops the delayed ref head's count from the delayed refs rsv and frees * any excess reservation we had. @@ -114,10 +115,11 @@ void btrfs_update_delayed_refs_rsv(struct btrfs_trans_handle *trans) } /** - * btrfs_migrate_to_delayed_refs_rsv - transfer bytes to our delayed refs rsv. - * @fs_info - the fs info for our fs. - * @src - the source block rsv to transfer from. - * @num_bytes - the number of bytes to transfer. + * Transfer bytes to our delayed refs rsv + * + * @fs_info: the filesystem + * @src: source block rsv to transfer from + * @num_bytes: number of bytes to transfer * * This transfers up to the num_bytes amount from the src rsv to the * delayed_refs_rsv. Any extra bytes are returned to the space info. @@ -162,9 +164,10 @@ void btrfs_migrate_to_delayed_refs_rsv(struct btrfs_fs_info *fs_info, } /** - * btrfs_delayed_refs_rsv_refill - refill based on our delayed refs usage. - * @fs_info - the fs_info for our fs. - * @flush - control how we can flush for this reservation. + * Refill based on our delayed refs usage + * + * @fs_info: the filesystem + * @flush: control how we can flush for this reservation. * * This will refill the delayed block_rsv up to 1 items size worth of space and * will return -ENOSPC if we can't make the reservation. @@ -648,12 +651,12 @@ inserted: */ static noinline void update_existing_head_ref(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_head *existing, - struct btrfs_delayed_ref_head *update, - int *old_ref_mod_ret) + struct btrfs_delayed_ref_head *update) { struct btrfs_delayed_ref_root *delayed_refs = &trans->transaction->delayed_refs; struct btrfs_fs_info *fs_info = trans->fs_info; + u64 flags = btrfs_ref_head_to_space_flags(existing); int old_ref_mod; BUG_ON(existing->is_data != update->is_data); @@ -701,8 +704,6 @@ static noinline void update_existing_head_ref(struct btrfs_trans_handle *trans, * currently, for refs we just added we know we're a-ok. */ old_ref_mod = existing->total_ref_mod; - if (old_ref_mod_ret) - *old_ref_mod_ret = old_ref_mod; existing->ref_mod += update->ref_mod; existing->total_ref_mod += update->ref_mod; @@ -724,6 +725,27 @@ static noinline void update_existing_head_ref(struct btrfs_trans_handle *trans, trans->delayed_ref_updates += csum_leaves; } } + + /* + * This handles the following conditions: + * + * 1. We had a ref mod of 0 or more and went negative, indicating that + * we may be freeing space, so add our space to the + * total_bytes_pinned counter. + * 2. We were negative and went to 0 or positive, so no longer can say + * that the space would be pinned, decrement our counter from the + * total_bytes_pinned counter. + * 3. We are now at 0 and have ->must_insert_reserved set, which means + * this was a new allocation and then we dropped it, and thus must + * add our space to the total_bytes_pinned counter. + */ + if (existing->total_ref_mod < 0 && old_ref_mod >= 0) + btrfs_mod_total_bytes_pinned(fs_info, flags, existing->num_bytes); + else if (existing->total_ref_mod >= 0 && old_ref_mod < 0) + btrfs_mod_total_bytes_pinned(fs_info, flags, -existing->num_bytes); + else if (existing->total_ref_mod == 0 && existing->must_insert_reserved) + btrfs_mod_total_bytes_pinned(fs_info, flags, existing->num_bytes); + spin_unlock(&existing->lock); } @@ -798,8 +820,7 @@ static noinline struct btrfs_delayed_ref_head * add_delayed_ref_head(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_head *head_ref, struct btrfs_qgroup_extent_record *qrecord, - int action, int *qrecord_inserted_ret, - int *old_ref_mod, int *new_ref_mod) + int action, int *qrecord_inserted_ret) { struct btrfs_delayed_ref_head *existing; struct btrfs_delayed_ref_root *delayed_refs; @@ -821,8 +842,7 @@ add_delayed_ref_head(struct btrfs_trans_handle *trans, existing = htree_insert(&delayed_refs->href_root, &head_ref->href_node); if (existing) { - update_existing_head_ref(trans, existing, head_ref, - old_ref_mod); + update_existing_head_ref(trans, existing, head_ref); /* * we've updated the existing ref, free the newly * allocated ref @@ -830,14 +850,17 @@ add_delayed_ref_head(struct btrfs_trans_handle *trans, kmem_cache_free(btrfs_delayed_ref_head_cachep, head_ref); head_ref = existing; } else { - if (old_ref_mod) - *old_ref_mod = 0; + u64 flags = btrfs_ref_head_to_space_flags(head_ref); + if (head_ref->is_data && head_ref->ref_mod < 0) { delayed_refs->pending_csums += head_ref->num_bytes; trans->delayed_ref_updates += btrfs_csum_bytes_to_leaves(trans->fs_info, head_ref->num_bytes); } + if (head_ref->ref_mod < 0) + btrfs_mod_total_bytes_pinned(trans->fs_info, flags, + head_ref->num_bytes); delayed_refs->num_heads++; delayed_refs->num_heads_ready++; atomic_inc(&delayed_refs->num_entries); @@ -845,8 +868,6 @@ add_delayed_ref_head(struct btrfs_trans_handle *trans, } if (qrecord_inserted_ret) *qrecord_inserted_ret = qrecord_inserted; - if (new_ref_mod) - *new_ref_mod = head_ref->total_ref_mod; return head_ref; } @@ -909,8 +930,7 @@ static void init_delayed_ref_common(struct btrfs_fs_info *fs_info, */ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, struct btrfs_ref *generic_ref, - struct btrfs_delayed_extent_op *extent_op, - int *old_ref_mod, int *new_ref_mod) + struct btrfs_delayed_extent_op *extent_op) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_delayed_tree_ref *ref; @@ -977,8 +997,7 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, * the spin lock */ head_ref = add_delayed_ref_head(trans, head_ref, record, - action, &qrecord_inserted, - old_ref_mod, new_ref_mod); + action, &qrecord_inserted); ret = insert_delayed_ref(trans, delayed_refs, head_ref, &ref->node); spin_unlock(&delayed_refs->lock); @@ -1006,8 +1025,7 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, */ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans, struct btrfs_ref *generic_ref, - u64 reserved, int *old_ref_mod, - int *new_ref_mod) + u64 reserved) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_delayed_data_ref *ref; @@ -1073,8 +1091,7 @@ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans, * the spin lock */ head_ref = add_delayed_ref_head(trans, head_ref, record, - action, &qrecord_inserted, - old_ref_mod, new_ref_mod); + action, &qrecord_inserted); ret = insert_delayed_ref(trans, delayed_refs, head_ref, &ref->node); spin_unlock(&delayed_refs->lock); @@ -1117,7 +1134,7 @@ int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans, spin_lock(&delayed_refs->lock); add_delayed_ref_head(trans, head_ref, NULL, BTRFS_UPDATE_DELAYED_HEAD, - NULL, NULL, NULL); + NULL); spin_unlock(&delayed_refs->lock); diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h index 1c977e6d45dc..e22fba272e4f 100644 --- a/fs/btrfs/delayed-ref.h +++ b/fs/btrfs/delayed-ref.h @@ -135,6 +135,11 @@ struct btrfs_delayed_data_ref { u64 offset; }; +enum btrfs_delayed_ref_flags { + /* Indicate that we are flushing delayed refs for the commit */ + BTRFS_DELAYED_REFS_FLUSHING, +}; + struct btrfs_delayed_ref_root { /* head ref rbtree */ struct rb_root_cached href_root; @@ -158,12 +163,7 @@ struct btrfs_delayed_ref_root { u64 pending_csums; - /* - * set when the tree is flushing before a transaction commit, - * used by the throttling code to decide if new updates need - * to be run right away - */ - int flushing; + unsigned long flags; u64 run_delayed_start; @@ -326,6 +326,16 @@ static inline void btrfs_put_delayed_ref(struct btrfs_delayed_ref_node *ref) } } +static inline u64 btrfs_ref_head_to_space_flags( + struct btrfs_delayed_ref_head *head_ref) +{ + if (head_ref->is_data) + return BTRFS_BLOCK_GROUP_DATA; + else if (head_ref->is_system) + return BTRFS_BLOCK_GROUP_SYSTEM; + return BTRFS_BLOCK_GROUP_METADATA; +} + static inline void btrfs_put_delayed_ref_head(struct btrfs_delayed_ref_head *head) { if (refcount_dec_and_test(&head->refs)) @@ -334,12 +344,10 @@ static inline void btrfs_put_delayed_ref_head(struct btrfs_delayed_ref_head *hea int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, struct btrfs_ref *generic_ref, - struct btrfs_delayed_extent_op *extent_op, - int *old_ref_mod, int *new_ref_mod); + struct btrfs_delayed_extent_op *extent_op); int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans, struct btrfs_ref *generic_ref, - u64 reserved, int *old_ref_mod, - int *new_ref_mod); + u64 reserved); int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, struct btrfs_delayed_extent_op *extent_op); diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 4a0243cb9d97..3a9c1e046ebe 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -21,6 +21,8 @@ #include "rcu-string.h" #include "dev-replace.h" #include "sysfs.h" +#include "zoned.h" +#include "block-group.h" /* * Device replace overview @@ -91,6 +93,17 @@ int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info) ret = btrfs_search_slot(NULL, dev_root, &key, path, 0, 0); if (ret) { no_valid_dev_replace_entry_found: + /* + * We don't have a replace item or it's corrupted. If there is + * a replace target, fail the mount. + */ + if (btrfs_find_device(fs_info->fs_devices, + BTRFS_DEV_REPLACE_DEVID, NULL, NULL)) { + btrfs_err(fs_info, + "found replace target device without a valid replace item"); + ret = -EUCLEAN; + goto out; + } ret = 0; dev_replace->replace_state = BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED; @@ -143,16 +156,27 @@ no_valid_dev_replace_entry_found: case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED: case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED: case BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED: - dev_replace->srcdev = NULL; - dev_replace->tgtdev = NULL; + /* + * We don't have an active replace item but if there is a + * replace target, fail the mount. + */ + if (btrfs_find_device(fs_info->fs_devices, + BTRFS_DEV_REPLACE_DEVID, NULL, NULL)) { + btrfs_err(fs_info, + "replace devid present without an active replace item"); + ret = -EUCLEAN; + } else { + dev_replace->srcdev = NULL; + dev_replace->tgtdev = NULL; + } break; case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED: case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED: dev_replace->srcdev = btrfs_find_device(fs_info->fs_devices, - src_devid, NULL, NULL, true); + src_devid, NULL, NULL); dev_replace->tgtdev = btrfs_find_device(fs_info->fs_devices, BTRFS_DEV_REPLACE_DEVID, - NULL, NULL, true); + NULL, NULL); /* * allow 'btrfs dev replace_cancel' if src/tgt device is * missing @@ -237,6 +261,13 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, return PTR_ERR(bdev); } + if (!btrfs_check_device_zone_type(fs_info, bdev)) { + btrfs_err(fs_info, + "dev-replace: zoned type of target device mismatch with filesystem"); + ret = -EINVAL; + goto error; + } + sync_blockdev(bdev); list_for_each_entry(device, &fs_info->fs_devices->devices, dev_list) { @@ -291,6 +322,10 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE); device->fs_devices = fs_info->fs_devices; + ret = btrfs_get_dev_zone_info(device); + if (ret) + goto error; + mutex_lock(&fs_info->fs_devices->device_list_mutex); list_add(&device->dev_list, &fs_info->fs_devices->devices); fs_info->fs_devices->num_devices++; @@ -425,6 +460,185 @@ static char* btrfs_dev_name(struct btrfs_device *device) return rcu_str_deref(device->name); } +static int mark_block_group_to_copy(struct btrfs_fs_info *fs_info, + struct btrfs_device *src_dev) +{ + struct btrfs_path *path; + struct btrfs_key key; + struct btrfs_key found_key; + struct btrfs_root *root = fs_info->dev_root; + struct btrfs_dev_extent *dev_extent = NULL; + struct btrfs_block_group *cache; + struct btrfs_trans_handle *trans; + int ret = 0; + u64 chunk_offset; + + /* Do not use "to_copy" on non zoned filesystem for now */ + if (!btrfs_is_zoned(fs_info)) + return 0; + + mutex_lock(&fs_info->chunk_mutex); + + /* Ensure we don't have pending new block group */ + spin_lock(&fs_info->trans_lock); + while (fs_info->running_transaction && + !list_empty(&fs_info->running_transaction->dev_update_list)) { + spin_unlock(&fs_info->trans_lock); + mutex_unlock(&fs_info->chunk_mutex); + trans = btrfs_attach_transaction(root); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); + mutex_lock(&fs_info->chunk_mutex); + if (ret == -ENOENT) { + spin_lock(&fs_info->trans_lock); + continue; + } else { + goto unlock; + } + } + + ret = btrfs_commit_transaction(trans); + mutex_lock(&fs_info->chunk_mutex); + if (ret) + goto unlock; + + spin_lock(&fs_info->trans_lock); + } + spin_unlock(&fs_info->trans_lock); + + path = btrfs_alloc_path(); + if (!path) { + ret = -ENOMEM; + goto unlock; + } + + path->reada = READA_FORWARD; + path->search_commit_root = 1; + path->skip_locking = 1; + + key.objectid = src_dev->devid; + key.type = BTRFS_DEV_EXTENT_KEY; + key.offset = 0; + + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) + goto free_path; + if (ret > 0) { + if (path->slots[0] >= + btrfs_header_nritems(path->nodes[0])) { + ret = btrfs_next_leaf(root, path); + if (ret < 0) + goto free_path; + if (ret > 0) { + ret = 0; + goto free_path; + } + } else { + ret = 0; + } + } + + while (1) { + struct extent_buffer *leaf = path->nodes[0]; + int slot = path->slots[0]; + + btrfs_item_key_to_cpu(leaf, &found_key, slot); + + if (found_key.objectid != src_dev->devid) + break; + + if (found_key.type != BTRFS_DEV_EXTENT_KEY) + break; + + if (found_key.offset < key.offset) + break; + + dev_extent = btrfs_item_ptr(leaf, slot, struct btrfs_dev_extent); + + chunk_offset = btrfs_dev_extent_chunk_offset(leaf, dev_extent); + + cache = btrfs_lookup_block_group(fs_info, chunk_offset); + if (!cache) + goto skip; + + spin_lock(&cache->lock); + cache->to_copy = 1; + spin_unlock(&cache->lock); + + btrfs_put_block_group(cache); + +skip: + ret = btrfs_next_item(root, path); + if (ret != 0) { + if (ret > 0) + ret = 0; + break; + } + } + +free_path: + btrfs_free_path(path); +unlock: + mutex_unlock(&fs_info->chunk_mutex); + + return ret; +} + +bool btrfs_finish_block_group_to_copy(struct btrfs_device *srcdev, + struct btrfs_block_group *cache, + u64 physical) +{ + struct btrfs_fs_info *fs_info = cache->fs_info; + struct extent_map *em; + struct map_lookup *map; + u64 chunk_offset = cache->start; + int num_extents, cur_extent; + int i; + + /* Do not use "to_copy" on non zoned filesystem for now */ + if (!btrfs_is_zoned(fs_info)) + return true; + + spin_lock(&cache->lock); + if (cache->removed) { + spin_unlock(&cache->lock); + return true; + } + spin_unlock(&cache->lock); + + em = btrfs_get_chunk_map(fs_info, chunk_offset, 1); + ASSERT(!IS_ERR(em)); + map = em->map_lookup; + + num_extents = cur_extent = 0; + for (i = 0; i < map->num_stripes; i++) { + /* We have more device extent to copy */ + if (srcdev != map->stripes[i].dev) + continue; + + num_extents++; + if (physical == map->stripes[i].physical) + cur_extent = i; + } + + free_extent_map(em); + + if (num_extents > 1 && cur_extent < num_extents - 1) { + /* + * Has more stripes on this device. Keep this block group + * readonly until we finish all the stripes. + */ + return false; + } + + /* Last stripe on this device */ + spin_lock(&cache->lock); + cache->to_copy = 0; + spin_unlock(&cache->lock); + + return true; +} + static int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info, const char *tgtdev_name, u64 srcdevid, const char *srcdev_name, int read_src) @@ -466,6 +680,10 @@ static int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info, if (ret) return ret; + ret = mark_block_group_to_copy(fs_info, src_device); + if (ret) + return ret; + down_write(&dev_replace->rwsem); switch (dev_replace->replace_state) { case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED: @@ -681,13 +899,16 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, * flush all outstanding I/O and inode extent mappings before the * copy operation is declared as being finished */ - ret = btrfs_start_delalloc_roots(fs_info, U64_MAX); + ret = btrfs_start_delalloc_roots(fs_info, LONG_MAX, false); if (ret) { mutex_unlock(&dev_replace->lock_finishing_cancel_unmount); return ret; } btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1); + if (!scrub_ret) + btrfs_reada_remove_dev(src_device); + /* * We have to use this loop approach because at this point src_device * has to be available for transaction commit to complete, yet new @@ -696,6 +917,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, while (1) { trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { + btrfs_reada_undo_remove_dev(src_device); mutex_unlock(&dev_replace->lock_finishing_cancel_unmount); return PTR_ERR(trans); } @@ -746,6 +968,7 @@ error: up_write(&dev_replace->rwsem); mutex_unlock(&fs_info->chunk_mutex); mutex_unlock(&fs_info->fs_devices->device_list_mutex); + btrfs_reada_undo_remove_dev(src_device); btrfs_rm_dev_replace_blocked(fs_info); if (tgt_device) btrfs_destroy_dev_replace_tgtdev(tgt_device); diff --git a/fs/btrfs/dev-replace.h b/fs/btrfs/dev-replace.h index 60b70dacc299..3911049a5f23 100644 --- a/fs/btrfs/dev-replace.h +++ b/fs/btrfs/dev-replace.h @@ -18,5 +18,8 @@ int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info); void btrfs_dev_replace_suspend_for_unmount(struct btrfs_fs_info *fs_info); int btrfs_resume_dev_replace_async(struct btrfs_fs_info *fs_info); int __pure btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace); +bool btrfs_finish_block_group_to_copy(struct btrfs_device *srcdev, + struct btrfs_block_group *cache, + u64 physical); #endif diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c index 863367c2c620..98b63ebed539 100644 --- a/fs/btrfs/dir-item.c +++ b/fs/btrfs/dir-item.c @@ -127,7 +127,6 @@ int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, const char *name, path = btrfs_alloc_path(); if (!path) return -ENOMEM; - path->leave_spinning = 1; btrfs_cpu_key_to_disk(&disk_key, location); diff --git a/fs/btrfs/discard.c b/fs/btrfs/discard.c index 741c7e19c32f..306ff20af70f 100644 --- a/fs/btrfs/discard.c +++ b/fs/btrfs/discard.c @@ -185,10 +185,12 @@ static struct btrfs_block_group *find_next_block_group( } /** - * peek_discard_list - wrap find_next_block_group() - * @discard_ctl: discard control + * Wrap find_next_block_group() + * + * @discard_ctl: discard control * @discard_state: the discard_state of the block_group after state management * @discard_index: the discard_index of the block_group after state management + * @now: time when discard was invoked, in ns * * This wraps find_next_block_group() and sets the block_group to be in use. * discard_state's control flow is managed here. Variables related to @@ -199,16 +201,15 @@ static struct btrfs_block_group *find_next_block_group( static struct btrfs_block_group *peek_discard_list( struct btrfs_discard_ctl *discard_ctl, enum btrfs_discard_state *discard_state, - int *discard_index) + int *discard_index, u64 now) { struct btrfs_block_group *block_group; - const u64 now = ktime_get_ns(); spin_lock(&discard_ctl->lock); again: block_group = find_next_block_group(discard_ctl, now); - if (block_group && now > block_group->discard_eligible_time) { + if (block_group && now >= block_group->discard_eligible_time) { if (block_group->discard_index == BTRFS_DISCARD_INDEX_UNUSED && block_group->used != 0) { if (btrfs_is_block_group_data_only(block_group)) @@ -222,12 +223,11 @@ again: block_group->discard_state = BTRFS_DISCARD_EXTENTS; } discard_ctl->block_group = block_group; + } + if (block_group) { *discard_state = block_group->discard_state; *discard_index = block_group->discard_index; - } else { - block_group = NULL; } - spin_unlock(&discard_ctl->lock); return block_group; @@ -330,32 +330,19 @@ void btrfs_discard_queue_work(struct btrfs_discard_ctl *discard_ctl, btrfs_discard_schedule_work(discard_ctl, false); } -/** - * btrfs_discard_schedule_work - responsible for scheduling the discard work - * @discard_ctl: discard control - * @override: override the current timer - * - * Discards are issued by a delayed workqueue item. @override is used to - * update the current delay as the baseline delay interval is reevaluated on - * transaction commit. This is also maxed with any other rate limit. - */ -void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl, - bool override) +static void __btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl, + u64 now, bool override) { struct btrfs_block_group *block_group; - const u64 now = ktime_get_ns(); - - spin_lock(&discard_ctl->lock); if (!btrfs_run_discard_work(discard_ctl)) - goto out; - + return; if (!override && delayed_work_pending(&discard_ctl->work)) - goto out; + return; block_group = find_next_block_group(discard_ctl, now); if (block_group) { - unsigned long delay = discard_ctl->delay; + u64 delay = discard_ctl->delay_ms * NSEC_PER_MSEC; u32 kbps_limit = READ_ONCE(discard_ctl->kbps_limit); /* @@ -366,9 +353,9 @@ void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl, if (kbps_limit && discard_ctl->prev_discard) { u64 bps_limit = ((u64)kbps_limit) * SZ_1K; u64 bps_delay = div64_u64(discard_ctl->prev_discard * - MSEC_PER_SEC, bps_limit); + NSEC_PER_SEC, bps_limit); - delay = max(delay, msecs_to_jiffies(bps_delay)); + delay = max(delay, bps_delay); } /* @@ -378,13 +365,39 @@ void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl, if (now < block_group->discard_eligible_time) { u64 bg_timeout = block_group->discard_eligible_time - now; - delay = max(delay, nsecs_to_jiffies(bg_timeout)); + delay = max(delay, bg_timeout); + } + + if (override && discard_ctl->prev_discard) { + u64 elapsed = now - discard_ctl->prev_discard_time; + + if (delay > elapsed) + delay -= elapsed; + else + delay = 0; } mod_delayed_work(discard_ctl->discard_workers, - &discard_ctl->work, delay); + &discard_ctl->work, nsecs_to_jiffies(delay)); } -out: +} + +/* + * btrfs_discard_schedule_work - responsible for scheduling the discard work + * @discard_ctl: discard control + * @override: override the current timer + * + * Discards are issued by a delayed workqueue item. @override is used to + * update the current delay as the baseline delay interval is reevaluated on + * transaction commit. This is also maxed with any other rate limit. + */ +void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl, + bool override) +{ + const u64 now = ktime_get_ns(); + + spin_lock(&discard_ctl->lock); + __btrfs_discard_schedule_work(discard_ctl, now, override); spin_unlock(&discard_ctl->lock); } @@ -429,13 +442,18 @@ static void btrfs_discard_workfn(struct work_struct *work) int discard_index = 0; u64 trimmed = 0; u64 minlen = 0; + u64 now = ktime_get_ns(); discard_ctl = container_of(work, struct btrfs_discard_ctl, work.work); block_group = peek_discard_list(discard_ctl, &discard_state, - &discard_index); + &discard_index, now); if (!block_group || !btrfs_run_discard_work(discard_ctl)) return; + if (now < block_group->discard_eligible_time) { + btrfs_discard_schedule_work(discard_ctl, false); + return; + } /* Perform discarding */ minlen = discard_minlen[discard_index]; @@ -465,8 +483,6 @@ static void btrfs_discard_workfn(struct work_struct *work) discard_ctl->discard_extent_bytes += trimmed; } - discard_ctl->prev_discard = trimmed; - /* Determine next steps for a block_group */ if (block_group->discard_cursor >= btrfs_block_group_end(block_group)) { if (discard_state == BTRFS_DISCARD_BITMAPS) { @@ -482,11 +498,13 @@ static void btrfs_discard_workfn(struct work_struct *work) } } + now = ktime_get_ns(); spin_lock(&discard_ctl->lock); + discard_ctl->prev_discard = trimmed; + discard_ctl->prev_discard_time = now; discard_ctl->block_group = NULL; + __btrfs_discard_schedule_work(discard_ctl, now, false); spin_unlock(&discard_ctl->lock); - - btrfs_discard_schedule_work(discard_ctl, false); } /** @@ -519,7 +537,6 @@ void btrfs_discard_calc_delay(struct btrfs_discard_ctl *discard_ctl) s64 discardable_bytes; u32 iops_limit; unsigned long delay; - unsigned long lower_limit = BTRFS_DISCARD_MIN_DELAY_MSEC; discardable_extents = atomic_read(&discard_ctl->discardable_extents); if (!discardable_extents) @@ -550,12 +567,13 @@ void btrfs_discard_calc_delay(struct btrfs_discard_ctl *discard_ctl) iops_limit = READ_ONCE(discard_ctl->iops_limit); if (iops_limit) - lower_limit = max_t(unsigned long, lower_limit, - MSEC_PER_SEC / iops_limit); + delay = MSEC_PER_SEC / iops_limit; + else + delay = BTRFS_DISCARD_TARGET_MSEC / discardable_extents; - delay = BTRFS_DISCARD_TARGET_MSEC / discardable_extents; - delay = clamp(delay, lower_limit, BTRFS_DISCARD_MAX_DELAY_MSEC); - discard_ctl->delay = msecs_to_jiffies(delay); + delay = clamp(delay, BTRFS_DISCARD_MIN_DELAY_MSEC, + BTRFS_DISCARD_MAX_DELAY_MSEC); + discard_ctl->delay_ms = delay; spin_unlock(&discard_ctl->lock); } @@ -563,15 +581,14 @@ void btrfs_discard_calc_delay(struct btrfs_discard_ctl *discard_ctl) /** * btrfs_discard_update_discardable - propagate discard counters * @block_group: block_group of interest - * @ctl: free_space_ctl of @block_group * * This propagates deltas of counters up to the discard_ctl. It maintains a * current counter and a previous counter passing the delta up to the global * stat. Then the current counter value becomes the previous counter value. */ -void btrfs_discard_update_discardable(struct btrfs_block_group *block_group, - struct btrfs_free_space_ctl *ctl) +void btrfs_discard_update_discardable(struct btrfs_block_group *block_group) { + struct btrfs_free_space_ctl *ctl; struct btrfs_discard_ctl *discard_ctl; s32 extents_delta; s64 bytes_delta; @@ -581,8 +598,10 @@ void btrfs_discard_update_discardable(struct btrfs_block_group *block_group, !btrfs_is_block_group_data_only(block_group)) return; + ctl = block_group->free_space_ctl; discard_ctl = &block_group->fs_info->discard_ctl; + lockdep_assert_held(&ctl->tree_lock); extents_delta = ctl->discardable_extents[BTRFS_STAT_CURR] - ctl->discardable_extents[BTRFS_STAT_PREV]; if (extents_delta) { @@ -684,10 +703,11 @@ void btrfs_discard_init(struct btrfs_fs_info *fs_info) INIT_LIST_HEAD(&discard_ctl->discard_list[i]); discard_ctl->prev_discard = 0; + discard_ctl->prev_discard_time = 0; atomic_set(&discard_ctl->discardable_extents, 0); atomic64_set(&discard_ctl->discardable_bytes, 0); discard_ctl->max_discard_size = BTRFS_ASYNC_DISCARD_DEFAULT_MAX_SIZE; - discard_ctl->delay = BTRFS_DISCARD_MAX_DELAY_MSEC; + discard_ctl->delay_ms = BTRFS_DISCARD_MAX_DELAY_MSEC; discard_ctl->iops_limit = BTRFS_DISCARD_MAX_IOPS; discard_ctl->kbps_limit = 0; discard_ctl->discard_extent_bytes = 0; diff --git a/fs/btrfs/discard.h b/fs/btrfs/discard.h index 353228d62f5a..57b9202f427f 100644 --- a/fs/btrfs/discard.h +++ b/fs/btrfs/discard.h @@ -28,8 +28,7 @@ bool btrfs_run_discard_work(struct btrfs_discard_ctl *discard_ctl); /* Update operations */ void btrfs_discard_calc_delay(struct btrfs_discard_ctl *discard_ctl); -void btrfs_discard_update_discardable(struct btrfs_block_group *block_group, - struct btrfs_free_space_ctl *ctl); +void btrfs_discard_update_discardable(struct btrfs_block_group *block_group); /* Setup/cleanup operations */ void btrfs_discard_punt_unused_bgs_list(struct btrfs_fs_info *fs_info); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 8e3438672a82..41b718cfea40 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -29,7 +29,6 @@ #include "tree-log.h" #include "free-space-cache.h" #include "free-space-tree.h" -#include "inode-map.h" #include "check-integrity.h" #include "rcu-string.h" #include "dev-replace.h" @@ -42,6 +41,7 @@ #include "block-group.h" #include "discard.h" #include "space-info.h" +#include "zoned.h" #define BTRFS_SUPER_FLAG_SUPP (BTRFS_HEADER_FLAG_WRITTEN |\ BTRFS_HEADER_FLAG_RELOC |\ @@ -109,15 +109,13 @@ static void btrfs_free_csum_hash(struct btrfs_fs_info *fs_info) * just before they are sent down the IO stack. */ struct async_submit_bio { - void *private_data; + struct inode *inode; struct bio *bio; extent_submit_bio_start_t *submit_bio_start; int mirror_num; - /* - * bio_offset is optional, can be used if the pages in the bio - * can't tell us where in the file the bio should go - */ - u64 bio_offset; + + /* Optional parameter for submit_bio_start used by direct io */ + u64 dio_file_offset; struct btrfs_work work; blk_status_t status; }; @@ -150,40 +148,41 @@ struct async_submit_bio { # error # endif +#define DEFINE_LEVEL(stem, level) \ + .names[level] = "btrfs-" stem "-0" #level, + +#define DEFINE_NAME(stem) \ + DEFINE_LEVEL(stem, 0) \ + DEFINE_LEVEL(stem, 1) \ + DEFINE_LEVEL(stem, 2) \ + DEFINE_LEVEL(stem, 3) \ + DEFINE_LEVEL(stem, 4) \ + DEFINE_LEVEL(stem, 5) \ + DEFINE_LEVEL(stem, 6) \ + DEFINE_LEVEL(stem, 7) + static struct btrfs_lockdep_keyset { u64 id; /* root objectid */ - const char *name_stem; /* lock name stem */ - char names[BTRFS_MAX_LEVEL + 1][20]; - struct lock_class_key keys[BTRFS_MAX_LEVEL + 1]; + /* Longest entry: btrfs-free-space-00 */ + char names[BTRFS_MAX_LEVEL][20]; + struct lock_class_key keys[BTRFS_MAX_LEVEL]; } btrfs_lockdep_keysets[] = { - { .id = BTRFS_ROOT_TREE_OBJECTID, .name_stem = "root" }, - { .id = BTRFS_EXTENT_TREE_OBJECTID, .name_stem = "extent" }, - { .id = BTRFS_CHUNK_TREE_OBJECTID, .name_stem = "chunk" }, - { .id = BTRFS_DEV_TREE_OBJECTID, .name_stem = "dev" }, - { .id = BTRFS_FS_TREE_OBJECTID, .name_stem = "fs" }, - { .id = BTRFS_CSUM_TREE_OBJECTID, .name_stem = "csum" }, - { .id = BTRFS_QUOTA_TREE_OBJECTID, .name_stem = "quota" }, - { .id = BTRFS_TREE_LOG_OBJECTID, .name_stem = "log" }, - { .id = BTRFS_TREE_RELOC_OBJECTID, .name_stem = "treloc" }, - { .id = BTRFS_DATA_RELOC_TREE_OBJECTID, .name_stem = "dreloc" }, - { .id = BTRFS_UUID_TREE_OBJECTID, .name_stem = "uuid" }, - { .id = BTRFS_FREE_SPACE_TREE_OBJECTID, .name_stem = "free-space" }, - { .id = 0, .name_stem = "tree" }, + { .id = BTRFS_ROOT_TREE_OBJECTID, DEFINE_NAME("root") }, + { .id = BTRFS_EXTENT_TREE_OBJECTID, DEFINE_NAME("extent") }, + { .id = BTRFS_CHUNK_TREE_OBJECTID, DEFINE_NAME("chunk") }, + { .id = BTRFS_DEV_TREE_OBJECTID, DEFINE_NAME("dev") }, + { .id = BTRFS_CSUM_TREE_OBJECTID, DEFINE_NAME("csum") }, + { .id = BTRFS_QUOTA_TREE_OBJECTID, DEFINE_NAME("quota") }, + { .id = BTRFS_TREE_LOG_OBJECTID, DEFINE_NAME("log") }, + { .id = BTRFS_TREE_RELOC_OBJECTID, DEFINE_NAME("treloc") }, + { .id = BTRFS_DATA_RELOC_TREE_OBJECTID, DEFINE_NAME("dreloc") }, + { .id = BTRFS_UUID_TREE_OBJECTID, DEFINE_NAME("uuid") }, + { .id = BTRFS_FREE_SPACE_TREE_OBJECTID, DEFINE_NAME("free-space") }, + { .id = 0, DEFINE_NAME("tree") }, }; -void __init btrfs_init_lockdep(void) -{ - int i, j; - - /* initialize lockdep class names */ - for (i = 0; i < ARRAY_SIZE(btrfs_lockdep_keysets); i++) { - struct btrfs_lockdep_keyset *ks = &btrfs_lockdep_keysets[i]; - - for (j = 0; j < ARRAY_SIZE(ks->names); j++) - snprintf(ks->names[j], sizeof(ks->names[j]), - "btrfs-%s-%02d", ks->name_stem, j); - } -} +#undef DEFINE_LEVEL +#undef DEFINE_NAME void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb, int level) @@ -210,15 +209,16 @@ static void csum_tree_block(struct extent_buffer *buf, u8 *result) { struct btrfs_fs_info *fs_info = buf->fs_info; const int num_pages = fs_info->nodesize >> PAGE_SHIFT; + const int first_page_part = min_t(u32, PAGE_SIZE, fs_info->nodesize); SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); char *kaddr; int i; shash->tfm = fs_info->csum_shash; crypto_shash_init(shash); - kaddr = page_address(buf->pages[0]); + kaddr = page_address(buf->pages[0]) + offset_in_page(buf->start); crypto_shash_update(shash, kaddr + BTRFS_CSUM_SIZE, - PAGE_SIZE - BTRFS_CSUM_SIZE); + first_page_part - BTRFS_CSUM_SIZE); for (i = 1; i < num_pages; i++) { kaddr = page_address(buf->pages[i]); @@ -248,10 +248,8 @@ static int verify_parent_transid(struct extent_io_tree *io_tree, if (atomic) return -EAGAIN; - if (need_lock) { + if (need_lock) btrfs_tree_read_lock(eb); - btrfs_set_lock_blocking_read(eb); - } lock_extent_bits(io_tree, eb->start, eb->start + eb->len - 1, &cached_state); @@ -280,7 +278,7 @@ out: unlock_extent_cached(io_tree, eb->start, eb->start + eb->len - 1, &cached_state); if (need_lock) - btrfs_tree_read_unlock_blocking(eb); + btrfs_tree_read_unlock(eb); return ret; } @@ -319,7 +317,7 @@ static int btrfs_check_super_csum(struct btrfs_fs_info *fs_info, crypto_shash_digest(shash, raw_disk_sb + BTRFS_CSUM_SIZE, BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE, result); - if (memcmp(disk_sb->csum, result, btrfs_super_csum_size(disk_sb))) + if (memcmp(disk_sb->csum, result, fs_info->csum_size)) return 1; return 0; @@ -443,16 +441,16 @@ static int btree_read_extent_buffer_pages(struct extent_buffer *eb, } /* - * checksum a dirty tree block before IO. This has extra checks to make sure - * we only fill in the checksum field in the first page of a multi-page block + * Checksum a dirty tree block before IO. This has extra checks to make sure + * we only fill in the checksum field in the first page of a multi-page block. + * For subpage extent buffers we need bvec to also read the offset in the page. */ - -static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct page *page) +static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct bio_vec *bvec) { + struct page *page = bvec->bv_page; u64 start = page_offset(page); u64 found_start; u8 result[BTRFS_CSUM_SIZE]; - u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); struct extent_buffer *eb; int ret; @@ -461,6 +459,12 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct page *page) return 0; found_start = btrfs_header_bytenr(eb); + + if (test_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags)) { + WARN_ON(found_start != 0); + return 0; + } + /* * Please do not consolidate these warnings into a single if. * It is useful to know what went wrong. @@ -489,7 +493,7 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct page *page) WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG)); return ret; } - write_extent_buffer(eb, result, 0, csum_size); + write_extent_buffer(eb, result, 0, fs_info->csum_size); return 0; } @@ -523,65 +527,37 @@ static int check_tree_block_fsid(struct extent_buffer *eb) return 1; } -int btrfs_validate_metadata_buffer(struct btrfs_io_bio *io_bio, u64 phy_offset, - struct page *page, u64 start, u64 end, - int mirror) +/* Do basic extent buffer checks at read time */ +static int validate_extent_buffer(struct extent_buffer *eb) { + struct btrfs_fs_info *fs_info = eb->fs_info; u64 found_start; - int found_level; - struct extent_buffer *eb; - struct btrfs_fs_info *fs_info; - u16 csum_size; - int ret = 0; + const u32 csum_size = fs_info->csum_size; + u8 found_level; u8 result[BTRFS_CSUM_SIZE]; - int reads_done; - - if (!page->private) - goto out; - - eb = (struct extent_buffer *)page->private; - fs_info = eb->fs_info; - csum_size = btrfs_super_csum_size(fs_info->super_copy); - - /* the pending IO might have been the only thing that kept this buffer - * in memory. Make sure we have a ref for all this other checks - */ - atomic_inc(&eb->refs); - - reads_done = atomic_dec_and_test(&eb->io_pages); - if (!reads_done) - goto err; - - eb->read_mirror = mirror; - if (test_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags)) { - ret = -EIO; - goto err; - } + int ret = 0; found_start = btrfs_header_bytenr(eb); if (found_start != eb->start) { btrfs_err_rl(fs_info, "bad tree block start, want %llu have %llu", eb->start, found_start); ret = -EIO; - goto err; + goto out; } if (check_tree_block_fsid(eb)) { btrfs_err_rl(fs_info, "bad fsid on block %llu", eb->start); ret = -EIO; - goto err; + goto out; } found_level = btrfs_header_level(eb); if (found_level >= BTRFS_MAX_LEVEL) { btrfs_err(fs_info, "bad tree block level %d on %llu", (int)btrfs_header_level(eb), eb->start); ret = -EIO; - goto err; + goto out; } - btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb), - eb, found_level); - csum_tree_block(eb, result); if (memcmp_extent_buffer(eb, result, 0, csum_size)) { @@ -595,7 +571,7 @@ int btrfs_validate_metadata_buffer(struct btrfs_io_bio *io_bio, u64 phy_offset, CSUM_FMT_VALUE(csum_size, result), btrfs_header_level(eb)); ret = -EUCLEAN; - goto err; + goto out; } /* @@ -617,6 +593,94 @@ int btrfs_validate_metadata_buffer(struct btrfs_io_bio *io_bio, u64 phy_offset, btrfs_err(fs_info, "block=%llu read time tree block corruption detected", eb->start); +out: + return ret; +} + +static int validate_subpage_buffer(struct page *page, u64 start, u64 end, + int mirror) +{ + struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb); + struct extent_buffer *eb; + bool reads_done; + int ret = 0; + + /* + * We don't allow bio merge for subpage metadata read, so we should + * only get one eb for each endio hook. + */ + ASSERT(end == start + fs_info->nodesize - 1); + ASSERT(PagePrivate(page)); + + eb = find_extent_buffer(fs_info, start); + /* + * When we are reading one tree block, eb must have been inserted into + * the radix tree. If not, something is wrong. + */ + ASSERT(eb); + + reads_done = atomic_dec_and_test(&eb->io_pages); + /* Subpage read must finish in page read */ + ASSERT(reads_done); + + eb->read_mirror = mirror; + if (test_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags)) { + ret = -EIO; + goto err; + } + ret = validate_extent_buffer(eb); + if (ret < 0) + goto err; + + if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags)) + btree_readahead_hook(eb, ret); + + set_extent_buffer_uptodate(eb); + + free_extent_buffer(eb); + return ret; +err: + /* + * end_bio_extent_readpage decrements io_pages in case of error, + * make sure it has something to decrement. + */ + atomic_inc(&eb->io_pages); + clear_extent_buffer_uptodate(eb); + free_extent_buffer(eb); + return ret; +} + +int btrfs_validate_metadata_buffer(struct btrfs_io_bio *io_bio, + struct page *page, u64 start, u64 end, + int mirror) +{ + struct extent_buffer *eb; + int ret = 0; + int reads_done; + + ASSERT(page->private); + + if (btrfs_sb(page->mapping->host->i_sb)->sectorsize < PAGE_SIZE) + return validate_subpage_buffer(page, start, end, mirror); + + eb = (struct extent_buffer *)page->private; + + /* + * The pending IO might have been the only thing that kept this buffer + * in memory. Make sure we have a ref for all this other checks + */ + atomic_inc(&eb->refs); + + reads_done = atomic_dec_and_test(&eb->io_pages); + if (!reads_done) + goto err; + + eb->read_mirror = mirror; + if (test_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags)) { + ret = -EIO; + goto err; + } + ret = validate_extent_buffer(eb); err: if (reads_done && test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags)) @@ -632,7 +696,7 @@ err: clear_extent_buffer_uptodate(eb); } free_extent_buffer(eb); -out: + return ret; } @@ -645,7 +709,7 @@ static void end_workqueue_bio(struct bio *bio) fs_info = end_io_wq->info; end_io_wq->status = bio->bi_status; - if (bio_op(bio) == REQ_OP_WRITE) { + if (btrfs_op(bio) == BTRFS_MAP_WRITE) { if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA) wq = fs_info->endio_meta_write_workers; else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE) @@ -694,8 +758,8 @@ static void run_one_async_start(struct btrfs_work *work) blk_status_t ret; async = container_of(work, struct async_submit_bio, work); - ret = async->submit_bio_start(async->private_data, async->bio, - async->bio_offset); + ret = async->submit_bio_start(async->inode, async->bio, + async->dio_file_offset); if (ret) async->status = ret; } @@ -715,7 +779,7 @@ static void run_one_async_done(struct btrfs_work *work) blk_status_t ret; async = container_of(work, struct async_submit_bio, work); - inode = async->private_data; + inode = async->inode; /* If an error occurred we just want to clean up the bio and move on */ if (async->status) { @@ -745,18 +809,19 @@ static void run_one_async_free(struct btrfs_work *work) kfree(async); } -blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio, +blk_status_t btrfs_wq_submit_bio(struct inode *inode, struct bio *bio, int mirror_num, unsigned long bio_flags, - u64 bio_offset, void *private_data, + u64 dio_file_offset, extent_submit_bio_start_t *submit_bio_start) { + struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info; struct async_submit_bio *async; async = kmalloc(sizeof(*async), GFP_NOFS); if (!async) return BLK_STS_RESOURCE; - async->private_data = private_data; + async->inode = inode; async->bio = bio; async->mirror_num = mirror_num; async->submit_bio_start = submit_bio_start; @@ -764,7 +829,7 @@ blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio, btrfs_init_work(&async->work, run_one_async_start, run_one_async_done, run_one_async_free); - async->bio_offset = bio_offset; + async->dio_file_offset = dio_file_offset; async->status = 0; @@ -785,7 +850,7 @@ static blk_status_t btree_csum_one_bio(struct bio *bio) ASSERT(!bio_flagged(bio, BIO_CLONED)); bio_for_each_segment_all(bvec, bio, iter_all) { root = BTRFS_I(bvec->bv_page->mapping->host)->root; - ret = csum_dirty_buffer(root->fs_info, bvec->bv_page); + ret = csum_dirty_buffer(root->fs_info, bvec); if (ret) break; } @@ -793,8 +858,8 @@ static blk_status_t btree_csum_one_bio(struct bio *bio) return errno_to_blk_status(ret); } -static blk_status_t btree_submit_bio_start(void *private_data, struct bio *bio, - u64 bio_offset) +static blk_status_t btree_submit_bio_start(struct inode *inode, struct bio *bio, + u64 dio_file_offset) { /* * when we're called for a write, we're already in the async @@ -806,6 +871,8 @@ static blk_status_t btree_submit_bio_start(void *private_data, struct bio *bio, static int check_async_write(struct btrfs_fs_info *fs_info, struct btrfs_inode *bi) { + if (btrfs_is_zoned(fs_info)) + return 0; if (atomic_read(&bi->sync_writers)) return 0; if (test_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags)) @@ -820,7 +887,7 @@ blk_status_t btrfs_submit_metadata_bio(struct inode *inode, struct bio *bio, int async = check_async_write(fs_info, BTRFS_I(inode)); blk_status_t ret; - if (bio_op(bio) != REQ_OP_WRITE) { + if (btrfs_op(bio) != BTRFS_MAP_WRITE) { /* * called for a read, do the setup so that checksum validation * can happen in the async kernel threads @@ -840,8 +907,8 @@ blk_status_t btrfs_submit_metadata_bio(struct inode *inode, struct bio *bio, * kthread helpers are used to submit writes so that * checksumming can happen in parallel across all CPUs */ - ret = btrfs_wq_submit_bio(fs_info, bio, mirror_num, 0, - 0, inode, btree_submit_bio_start); + ret = btrfs_wq_submit_bio(inode, bio, mirror_num, 0, + 0, btree_submit_bio_start); } if (ret) @@ -947,47 +1014,33 @@ static const struct address_space_operations btree_aops = { .set_page_dirty = btree_set_page_dirty, }; -void readahead_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr) -{ - struct extent_buffer *buf = NULL; - int ret; - - buf = btrfs_find_create_tree_block(fs_info, bytenr); - if (IS_ERR(buf)) - return; - - ret = read_extent_buffer_pages(buf, WAIT_NONE, 0); - if (ret < 0) - free_extent_buffer_stale(buf); - else - free_extent_buffer(buf); -} - struct extent_buffer *btrfs_find_create_tree_block( struct btrfs_fs_info *fs_info, - u64 bytenr) + u64 bytenr, u64 owner_root, + int level) { if (btrfs_is_testing(fs_info)) return alloc_test_extent_buffer(fs_info, bytenr); - return alloc_extent_buffer(fs_info, bytenr); + return alloc_extent_buffer(fs_info, bytenr, owner_root, level); } /* * Read tree block at logical address @bytenr and do variant basic but critical * verification. * + * @owner_root: the objectid of the root owner for this block. * @parent_transid: expected transid of this tree block, skip check if 0 * @level: expected level, mandatory check * @first_key: expected key in slot 0, skip check if NULL */ struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr, - u64 parent_transid, int level, - struct btrfs_key *first_key) + u64 owner_root, u64 parent_transid, + int level, struct btrfs_key *first_key) { struct extent_buffer *buf = NULL; int ret; - buf = btrfs_find_create_tree_block(fs_info, bytenr); + buf = btrfs_find_create_tree_block(fs_info, bytenr, owner_root, level); if (IS_ERR(buf)) return buf; @@ -1012,8 +1065,6 @@ void btrfs_clean_tree_block(struct extent_buffer *buf) percpu_counter_add_batch(&fs_info->dirty_metadata_bytes, -buf->len, fs_info->dirty_metadata_batch); - /* ugh, clear_extent_buffer_dirty needs to lock the page */ - btrfs_set_lock_blocking_write(buf); clear_extent_buffer_dirty(buf); } } @@ -1030,7 +1081,7 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, root->orphan_cleanup_state = 0; root->last_trans = 0; - root->highest_objectid = 0; + root->free_objectid = 0; root->nr_delalloc_inodes = 0; root->nr_ordered_extents = 0; root->inode_tree = RB_ROOT; @@ -1155,7 +1206,7 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans, if (IS_ERR(leaf)) { ret = PTR_ERR(leaf); leaf = NULL; - goto fail; + goto fail_unlock; } root->node = leaf; @@ -1164,8 +1215,8 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans, root->commit_root = btrfs_root_node(root); set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); - root->root_item.flags = 0; - root->root_item.byte_limit = 0; + btrfs_set_root_flags(&root->root_item, 0); + btrfs_set_root_limit(&root->root_item, 0); btrfs_set_root_bytenr(&root->root_item, leaf->start); btrfs_set_root_generation(&root->root_item, trans->transid); btrfs_set_root_level(&root->root_item, 0); @@ -1177,7 +1228,9 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans, generate_random_guid(root->root_item.uuid); else export_guid(root->root_item.uuid, &guid_null); - root->root_item.drop_level = 0; + btrfs_set_root_drop_level(&root->root_item, 0); + + btrfs_tree_unlock(leaf); key.objectid = objectid; key.type = BTRFS_ROOT_ITEM_KEY; @@ -1186,13 +1239,12 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans, if (ret) goto fail; - btrfs_tree_unlock(leaf); - return root; -fail: +fail_unlock: if (leaf) btrfs_tree_unlock(leaf); +fail: btrfs_put_root(root); return ERR_PTR(ret); @@ -1202,7 +1254,6 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info) { struct btrfs_root *root; - struct extent_buffer *leaf; root = btrfs_alloc_root(fs_info, BTRFS_TREE_LOG_OBJECTID, GFP_NOFS); if (!root) @@ -1212,6 +1263,14 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans, root->root_key.type = BTRFS_ROOT_ITEM_KEY; root->root_key.offset = BTRFS_TREE_LOG_OBJECTID; + return root; +} + +int btrfs_alloc_log_tree_node(struct btrfs_trans_handle *trans, + struct btrfs_root *root) +{ + struct extent_buffer *leaf; + /* * DON'T set SHAREABLE bit for log trees. * @@ -1224,16 +1283,15 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans, leaf = btrfs_alloc_tree_block(trans, root, 0, BTRFS_TREE_LOG_OBJECTID, NULL, 0, 0, 0, BTRFS_NESTING_NORMAL); - if (IS_ERR(leaf)) { - btrfs_put_root(root); - return ERR_CAST(leaf); - } + if (IS_ERR(leaf)) + return PTR_ERR(leaf); root->node = leaf; btrfs_mark_buffer_dirty(root->node); btrfs_tree_unlock(root->node); - return root; + + return 0; } int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans, @@ -1244,6 +1302,16 @@ int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans, log_root = alloc_log_tree(trans, fs_info); if (IS_ERR(log_root)) return PTR_ERR(log_root); + + if (!btrfs_is_zoned(fs_info)) { + int ret = btrfs_alloc_log_tree_node(trans, log_root); + + if (ret) { + btrfs_put_root(log_root); + return ret; + } + } + WARN_ON(fs_info->log_root_tree); fs_info->log_root_tree = log_root; return 0; @@ -1255,11 +1323,18 @@ int btrfs_add_log_tree(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_root *log_root; struct btrfs_inode_item *inode_item; + int ret; log_root = alloc_log_tree(trans, fs_info); if (IS_ERR(log_root)) return PTR_ERR(log_root); + ret = btrfs_alloc_log_tree_node(trans, log_root); + if (ret) { + btrfs_put_root(log_root); + return ret; + } + log_root->last_trans = trans->transid; log_root->root_key.offset = root->root_key.objectid; @@ -1281,57 +1356,61 @@ int btrfs_add_log_tree(struct btrfs_trans_handle *trans, return 0; } -struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root, - struct btrfs_key *key) +static struct btrfs_root *read_tree_root_path(struct btrfs_root *tree_root, + struct btrfs_path *path, + struct btrfs_key *key) { struct btrfs_root *root; struct btrfs_fs_info *fs_info = tree_root->fs_info; - struct btrfs_path *path; u64 generation; int ret; int level; - path = btrfs_alloc_path(); - if (!path) - return ERR_PTR(-ENOMEM); - root = btrfs_alloc_root(fs_info, key->objectid, GFP_NOFS); - if (!root) { - ret = -ENOMEM; - goto alloc_fail; - } + if (!root) + return ERR_PTR(-ENOMEM); ret = btrfs_find_root(tree_root, key, path, &root->root_item, &root->root_key); if (ret) { if (ret > 0) ret = -ENOENT; - goto find_fail; + goto fail; } generation = btrfs_root_generation(&root->root_item); level = btrfs_root_level(&root->root_item); root->node = read_tree_block(fs_info, btrfs_root_bytenr(&root->root_item), - generation, level, NULL); + key->objectid, generation, level, NULL); if (IS_ERR(root->node)) { ret = PTR_ERR(root->node); root->node = NULL; - goto find_fail; + goto fail; } else if (!btrfs_buffer_uptodate(root->node, generation, 0)) { ret = -EIO; - goto find_fail; + goto fail; } root->commit_root = btrfs_root_node(root); -out: - btrfs_free_path(path); return root; - -find_fail: +fail: btrfs_put_root(root); -alloc_fail: - root = ERR_PTR(ret); - goto out; + return ERR_PTR(ret); +} + +struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root, + struct btrfs_key *key) +{ + struct btrfs_root *root; + struct btrfs_path *path; + + path = btrfs_alloc_path(); + if (!path) + return ERR_PTR(-ENOMEM); + root = read_tree_root_path(tree_root, path, key); + btrfs_free_path(path); + + return root; } /* @@ -1344,14 +1423,6 @@ static int btrfs_init_fs_root(struct btrfs_root *root, dev_t anon_dev) int ret; unsigned int nofs_flag; - root->free_ino_ctl = kzalloc(sizeof(*root->free_ino_ctl), GFP_NOFS); - root->free_ino_pinned = kzalloc(sizeof(*root->free_ino_pinned), - GFP_NOFS); - if (!root->free_ino_pinned || !root->free_ino_ctl) { - ret = -ENOMEM; - goto fail; - } - /* * We might be called under a transaction (e.g. indirect backref * resolution) which could deadlock if it triggers memory reclaim @@ -1368,10 +1439,6 @@ static int btrfs_init_fs_root(struct btrfs_root *root, dev_t anon_dev) btrfs_check_and_init_root_item(&root->root_item); } - btrfs_init_free_ino_ctl(root); - spin_lock_init(&root->ino_cache_lock); - init_waitqueue_head(&root->ino_cache_wait); - /* * Don't assign anonymous block device to roots that are not exposed to * userspace, the id pool is limited to 1M @@ -1388,14 +1455,13 @@ static int btrfs_init_fs_root(struct btrfs_root *root, dev_t anon_dev) } mutex_lock(&root->objectid_mutex); - ret = btrfs_find_highest_objectid(root, - &root->highest_objectid); + ret = btrfs_init_root_free_objectid(root); if (ret) { mutex_unlock(&root->objectid_mutex); goto fail; } - ASSERT(root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID); + ASSERT(root->free_objectid <= BTRFS_LAST_FREE_OBJECTID); mutex_unlock(&root->objectid_mutex); @@ -1419,6 +1485,31 @@ static struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info, return root; } +static struct btrfs_root *btrfs_get_global_root(struct btrfs_fs_info *fs_info, + u64 objectid) +{ + if (objectid == BTRFS_ROOT_TREE_OBJECTID) + return btrfs_grab_root(fs_info->tree_root); + if (objectid == BTRFS_EXTENT_TREE_OBJECTID) + return btrfs_grab_root(fs_info->extent_root); + if (objectid == BTRFS_CHUNK_TREE_OBJECTID) + return btrfs_grab_root(fs_info->chunk_root); + if (objectid == BTRFS_DEV_TREE_OBJECTID) + return btrfs_grab_root(fs_info->dev_root); + if (objectid == BTRFS_CSUM_TREE_OBJECTID) + return btrfs_grab_root(fs_info->csum_root); + if (objectid == BTRFS_QUOTA_TREE_OBJECTID) + return btrfs_grab_root(fs_info->quota_root) ? + fs_info->quota_root : ERR_PTR(-ENOENT); + if (objectid == BTRFS_UUID_TREE_OBJECTID) + return btrfs_grab_root(fs_info->uuid_root) ? + fs_info->uuid_root : ERR_PTR(-ENOENT); + if (objectid == BTRFS_FREE_SPACE_TREE_OBJECTID) + return btrfs_grab_root(fs_info->free_space_root) ? + fs_info->free_space_root : ERR_PTR(-ENOENT); + return NULL; +} + int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root) { @@ -1453,7 +1544,7 @@ void btrfs_check_leaked_roots(struct btrfs_fs_info *fs_info) root = list_first_entry(&fs_info->allocated_roots, struct btrfs_root, leak_list); btrfs_err(fs_info, "leaked root %s refcount %d", - btrfs_root_name(root->root_key.objectid, buf), + btrfs_root_name(&root->root_key, buf), refcount_read(&root->refs)); while (refcount_read(&root->refs) > 1) btrfs_put_root(root); @@ -1466,7 +1557,7 @@ void btrfs_free_fs_info(struct btrfs_fs_info *fs_info) { percpu_counter_destroy(&fs_info->dirty_metadata_bytes); percpu_counter_destroy(&fs_info->delalloc_bytes); - percpu_counter_destroy(&fs_info->dio_bytes); + percpu_counter_destroy(&fs_info->ordered_bytes); percpu_counter_destroy(&fs_info->dev_replace.bio_counter); btrfs_free_csum_hash(fs_info); btrfs_free_stripe_hash_table(fs_info); @@ -1518,25 +1609,9 @@ static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info, struct btrfs_key key; int ret; - if (objectid == BTRFS_ROOT_TREE_OBJECTID) - return btrfs_grab_root(fs_info->tree_root); - if (objectid == BTRFS_EXTENT_TREE_OBJECTID) - return btrfs_grab_root(fs_info->extent_root); - if (objectid == BTRFS_CHUNK_TREE_OBJECTID) - return btrfs_grab_root(fs_info->chunk_root); - if (objectid == BTRFS_DEV_TREE_OBJECTID) - return btrfs_grab_root(fs_info->dev_root); - if (objectid == BTRFS_CSUM_TREE_OBJECTID) - return btrfs_grab_root(fs_info->csum_root); - if (objectid == BTRFS_QUOTA_TREE_OBJECTID) - return btrfs_grab_root(fs_info->quota_root) ? - fs_info->quota_root : ERR_PTR(-ENOENT); - if (objectid == BTRFS_UUID_TREE_OBJECTID) - return btrfs_grab_root(fs_info->uuid_root) ? - fs_info->uuid_root : ERR_PTR(-ENOENT); - if (objectid == BTRFS_FREE_SPACE_TREE_OBJECTID) - return btrfs_grab_root(fs_info->free_space_root) ? - fs_info->free_space_root : ERR_PTR(-ENOENT); + root = btrfs_get_global_root(fs_info, objectid); + if (root) + return root; again: root = btrfs_lookup_fs_root(fs_info, objectid); if (root) { @@ -1622,6 +1697,52 @@ struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info, } /* + * btrfs_get_fs_root_commit_root - return a root for the given objectid + * @fs_info: the fs_info + * @objectid: the objectid we need to lookup + * + * This is exclusively used for backref walking, and exists specifically because + * of how qgroups does lookups. Qgroups will do a backref lookup at delayed ref + * creation time, which means we may have to read the tree_root in order to look + * up a fs root that is not in memory. If the root is not in memory we will + * read the tree root commit root and look up the fs root from there. This is a + * temporary root, it will not be inserted into the radix tree as it doesn't + * have the most uptodate information, it'll simply be discarded once the + * backref code is finished using the root. + */ +struct btrfs_root *btrfs_get_fs_root_commit_root(struct btrfs_fs_info *fs_info, + struct btrfs_path *path, + u64 objectid) +{ + struct btrfs_root *root; + struct btrfs_key key; + + ASSERT(path->search_commit_root && path->skip_locking); + + /* + * This can return -ENOENT if we ask for a root that doesn't exist, but + * since this is called via the backref walking code we won't be looking + * up a root that doesn't exist, unless there's corruption. So if root + * != NULL just return it. + */ + root = btrfs_get_global_root(fs_info, objectid); + if (root) + return root; + + root = btrfs_lookup_fs_root(fs_info, objectid); + if (root) + return root; + + key.objectid = objectid; + key.type = BTRFS_ROOT_ITEM_KEY; + key.offset = (u64)-1; + root = read_tree_root_path(fs_info->tree_root, path, &key); + btrfs_release_path(path); + + return root; +} + +/* * called by the kthread helper functions to finally call the bio end_io * functions. This is where read checksum verification actually happens */ @@ -1695,7 +1816,7 @@ static int cleaner_kthread(void *arg) */ btrfs_delete_unused_bgs(fs_info); sleep: - clear_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags); + clear_and_wake_up_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags); if (kthread_should_park()) kthread_parkme(); if (kthread_should_stop()) @@ -1715,13 +1836,13 @@ static int transaction_kthread(void *arg) struct btrfs_trans_handle *trans; struct btrfs_transaction *cur; u64 transid; - time64_t now; + time64_t delta; unsigned long delay; bool cannot_commit; do { cannot_commit = false; - delay = HZ * fs_info->commit_interval; + delay = msecs_to_jiffies(fs_info->commit_interval * 1000); mutex_lock(&fs_info->transaction_kthread_mutex); spin_lock(&fs_info->trans_lock); @@ -1731,12 +1852,13 @@ static int transaction_kthread(void *arg) goto sleep; } - now = ktime_get_seconds(); + delta = ktime_get_seconds() - cur->start_time; if (cur->state < TRANS_STATE_COMMIT_START && - (now < cur->start_time || - now - cur->start_time < fs_info->commit_interval)) { + delta < fs_info->commit_interval) { spin_unlock(&fs_info->trans_lock); - delay = HZ * 5; + delay -= msecs_to_jiffies((delta - 1) * 1000); + delay = min(delay, + msecs_to_jiffies(fs_info->commit_interval * 1000)); goto sleep; } transid = cur->transid; @@ -1985,8 +2107,6 @@ void btrfs_put_root(struct btrfs_root *root) free_anon_bdev(root->anon_dev); btrfs_drew_lock_destroy(&root->snapshot_lock); free_root_extent_buffers(root); - kfree(root->free_ino_ctl); - kfree(root->free_ino_pinned); #ifdef CONFIG_BTRFS_DEBUG spin_lock(&root->fs_info->fs_roots_radix_lock); list_del_init(&root->leak_list); @@ -2201,8 +2321,9 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info, return -ENOMEM; log_tree_root->node = read_tree_block(fs_info, bytenr, - fs_info->generation + 1, - level, NULL); + BTRFS_TREE_LOG_OBJECTID, + fs_info->generation + 1, level, + NULL); if (IS_ERR(log_tree_root->node)) { btrfs_warn(fs_info, "failed to read log tree"); ret = PTR_ERR(log_tree_root->node); @@ -2247,30 +2368,42 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info) root = btrfs_read_tree_root(tree_root, &location); if (IS_ERR(root)) { - ret = PTR_ERR(root); - goto out; + if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) { + ret = PTR_ERR(root); + goto out; + } + } else { + set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); + fs_info->extent_root = root; } - set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); - fs_info->extent_root = root; location.objectid = BTRFS_DEV_TREE_OBJECTID; root = btrfs_read_tree_root(tree_root, &location); if (IS_ERR(root)) { - ret = PTR_ERR(root); - goto out; + if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) { + ret = PTR_ERR(root); + goto out; + } + } else { + set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); + fs_info->dev_root = root; + btrfs_init_devices_late(fs_info); } - set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); - fs_info->dev_root = root; - btrfs_init_devices_late(fs_info); - location.objectid = BTRFS_CSUM_TREE_OBJECTID; - root = btrfs_read_tree_root(tree_root, &location); - if (IS_ERR(root)) { - ret = PTR_ERR(root); - goto out; + /* If IGNOREDATACSUMS is set don't bother reading the csum root. */ + if (!btrfs_test_opt(fs_info, IGNOREDATACSUMS)) { + location.objectid = BTRFS_CSUM_TREE_OBJECTID; + root = btrfs_read_tree_root(tree_root, &location); + if (IS_ERR(root)) { + if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) { + ret = PTR_ERR(root); + goto out; + } + } else { + set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); + fs_info->csum_root = root; + } } - set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); - fs_info->csum_root = root; /* * This tree can share blocks with some other fs tree during relocation @@ -2279,11 +2412,14 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info) root = btrfs_get_fs_root(tree_root->fs_info, BTRFS_DATA_RELOC_TREE_OBJECTID, true); if (IS_ERR(root)) { - ret = PTR_ERR(root); - goto out; + if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) { + ret = PTR_ERR(root); + goto out; + } + } else { + set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); + fs_info->data_reloc_root = root; } - set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); - fs_info->data_reloc_root = root; location.objectid = BTRFS_QUOTA_TREE_OBJECTID; root = btrfs_read_tree_root(tree_root, &location); @@ -2296,9 +2432,11 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info) location.objectid = BTRFS_UUID_TREE_OBJECTID; root = btrfs_read_tree_root(tree_root, &location); if (IS_ERR(root)) { - ret = PTR_ERR(root); - if (ret != -ENOENT) - goto out; + if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) { + ret = PTR_ERR(root); + if (ret != -ENOENT) + goto out; + } } else { set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); fs_info->uuid_root = root; @@ -2308,11 +2446,14 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info) location.objectid = BTRFS_FREE_SPACE_TREE_OBJECTID; root = btrfs_read_tree_root(tree_root, &location); if (IS_ERR(root)) { - ret = PTR_ERR(root); - goto out; + if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) { + ret = PTR_ERR(root); + goto out; + } + } else { + set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); + fs_info->free_space_root = root; } - set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); - fs_info->free_space_root = root; } return 0; @@ -2373,13 +2514,21 @@ static int validate_super(struct btrfs_fs_info *fs_info, btrfs_err(fs_info, "invalid sectorsize %llu", sectorsize); ret = -EINVAL; } - /* Only PAGE SIZE is supported yet */ - if (sectorsize != PAGE_SIZE) { + + /* + * For 4K page size, we only support 4K sector size. + * For 64K page size, we support read-write for 64K sector size, and + * read-only for 4K sector size. + */ + if ((PAGE_SIZE == SZ_4K && sectorsize != PAGE_SIZE) || + (PAGE_SIZE == SZ_64K && (sectorsize != SZ_4K && + sectorsize != SZ_64K))) { btrfs_err(fs_info, - "sectorsize %llu not supported yet, only support %lu", + "sectorsize %llu not yet supported for page size %lu", sectorsize, PAGE_SIZE); ret = -EINVAL; } + if (!is_power_of_2(nodesize) || nodesize < sectorsize || nodesize > BTRFS_MAX_METADATA_BLOCKSIZE) { btrfs_err(fs_info, "invalid nodesize %llu", nodesize); @@ -2568,6 +2717,7 @@ static int __cold init_tree_roots(struct btrfs_fs_info *fs_info) generation = btrfs_super_generation(sb); level = btrfs_super_root_level(sb); tree_root->node = read_tree_block(fs_info, btrfs_super_root(sb), + BTRFS_ROOT_TREE_OBJECTID, generation, level, NULL); if (IS_ERR(tree_root->node)) { handle_error = true; @@ -2591,14 +2741,13 @@ static int __cold init_tree_roots(struct btrfs_fs_info *fs_info) * No need to hold btrfs_root::objectid_mutex since the fs * hasn't been fully initialised and we are the only user */ - ret = btrfs_find_highest_objectid(tree_root, - &tree_root->highest_objectid); + ret = btrfs_init_root_free_objectid(tree_root); if (ret < 0) { handle_error = true; continue; } - ASSERT(tree_root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID); + ASSERT(tree_root->free_objectid <= BTRFS_LAST_FREE_OBJECTID); ret = btrfs_read_roots(fs_info); if (ret < 0) { @@ -2640,11 +2789,13 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info) spin_lock_init(&fs_info->super_lock); spin_lock_init(&fs_info->buffer_lock); spin_lock_init(&fs_info->unused_bgs_lock); + spin_lock_init(&fs_info->treelog_bg_lock); rwlock_init(&fs_info->tree_mod_log_lock); mutex_init(&fs_info->unused_bg_unpin_mutex); mutex_init(&fs_info->delete_unused_bgs_mutex); mutex_init(&fs_info->reloc_mutex); mutex_init(&fs_info->delalloc_root_mutex); + mutex_init(&fs_info->zoned_meta_io_lock); seqlock_init(&fs_info->profiles_lock); INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots); @@ -2732,6 +2883,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info) /* Usable values until the real ones are cached from the superblock */ fs_info->nodesize = 4096; fs_info->sectorsize = 4096; + fs_info->sectorsize_bits = ilog2(4096); fs_info->stripesize = 4096; spin_lock_init(&fs_info->swapfile_pins_lock); @@ -2748,7 +2900,7 @@ static int init_mount_fs_info(struct btrfs_fs_info *fs_info, struct super_block sb->s_blocksize = BTRFS_BDEV_BLOCKSIZE; sb->s_blocksize_bits = blksize_bits(BTRFS_BDEV_BLOCKSIZE); - ret = percpu_counter_init(&fs_info->dio_bytes, 0, GFP_KERNEL); + ret = percpu_counter_init(&fs_info->ordered_bytes, 0, GFP_KERNEL); if (ret) return ret; @@ -2774,6 +2926,9 @@ static int init_mount_fs_info(struct btrfs_fs_info *fs_info, struct super_block return -ENOMEM; btrfs_init_delayed_root(fs_info->delayed_root); + if (sb_rdonly(sb)) + set_bit(BTRFS_FS_STATE_RO, &fs_info->fs_state); + return btrfs_alloc_stripe_hash_table(fs_info); } @@ -2814,6 +2969,110 @@ static int btrfs_check_uuid_tree(struct btrfs_fs_info *fs_info) return 0; } +/* + * Some options only have meaning at mount time and shouldn't persist across + * remounts, or be displayed. Clear these at the end of mount and remount + * code paths. + */ +void btrfs_clear_oneshot_options(struct btrfs_fs_info *fs_info) +{ + btrfs_clear_opt(fs_info->mount_opt, USEBACKUPROOT); + btrfs_clear_opt(fs_info->mount_opt, CLEAR_CACHE); +} + +/* + * Mounting logic specific to read-write file systems. Shared by open_ctree + * and btrfs_remount when remounting from read-only to read-write. + */ +int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info) +{ + int ret; + const bool cache_opt = btrfs_test_opt(fs_info, SPACE_CACHE); + bool clear_free_space_tree = false; + + if (btrfs_test_opt(fs_info, CLEAR_CACHE) && + btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) { + clear_free_space_tree = true; + } else if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) && + !btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID)) { + btrfs_warn(fs_info, "free space tree is invalid"); + clear_free_space_tree = true; + } + + if (clear_free_space_tree) { + btrfs_info(fs_info, "clearing free space tree"); + ret = btrfs_clear_free_space_tree(fs_info); + if (ret) { + btrfs_warn(fs_info, + "failed to clear free space tree: %d", ret); + goto out; + } + } + + ret = btrfs_cleanup_fs_roots(fs_info); + if (ret) + goto out; + + down_read(&fs_info->cleanup_work_sem); + if ((ret = btrfs_orphan_cleanup(fs_info->fs_root)) || + (ret = btrfs_orphan_cleanup(fs_info->tree_root))) { + up_read(&fs_info->cleanup_work_sem); + goto out; + } + up_read(&fs_info->cleanup_work_sem); + + mutex_lock(&fs_info->cleaner_mutex); + ret = btrfs_recover_relocation(fs_info->tree_root); + mutex_unlock(&fs_info->cleaner_mutex); + if (ret < 0) { + btrfs_warn(fs_info, "failed to recover relocation: %d", ret); + goto out; + } + + if (btrfs_test_opt(fs_info, FREE_SPACE_TREE) && + !btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) { + btrfs_info(fs_info, "creating free space tree"); + ret = btrfs_create_free_space_tree(fs_info); + if (ret) { + btrfs_warn(fs_info, + "failed to create free space tree: %d", ret); + goto out; + } + } + + if (cache_opt != btrfs_free_space_cache_v1_active(fs_info)) { + ret = btrfs_set_free_space_cache_v1_active(fs_info, cache_opt); + if (ret) + goto out; + } + + ret = btrfs_resume_balance_async(fs_info); + if (ret) + goto out; + + ret = btrfs_resume_dev_replace_async(fs_info); + if (ret) { + btrfs_warn(fs_info, "failed to resume dev_replace"); + goto out; + } + + btrfs_qgroup_rescan_resume(fs_info); + + if (!fs_info->uuid_root) { + btrfs_info(fs_info, "creating UUID tree"); + ret = btrfs_create_uuid_tree(fs_info); + if (ret) { + btrfs_warn(fs_info, + "failed to create the UUID tree %d", ret); + goto out; + } + } + + ret = btrfs_find_orphan_roots(fs_info); +out: + return ret; +} + int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_devices, char *options) { @@ -2829,7 +3088,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device struct btrfs_root *chunk_root; int ret; int err = -EINVAL; - int clear_free_space_tree = 0; int level; ret = init_mount_fs_info(fs_info, sb); @@ -2882,6 +3140,8 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device goto fail_alloc; } + fs_info->csum_size = btrfs_super_csum_size(disk_super); + ret = btrfs_init_csum_hash(fs_info, csum_type); if (ret) { err = ret; @@ -2996,6 +3256,8 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device /* Cache block sizes */ fs_info->nodesize = nodesize; fs_info->sectorsize = sectorsize; + fs_info->sectorsize_bits = ilog2(sectorsize); + fs_info->csums_per_leaf = BTRFS_MAX_ITEM_SIZE(fs_info) / fs_info->csum_size; fs_info->stripesize = stripesize; /* @@ -3026,6 +3288,17 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device goto fail_alloc; } + /* For 4K sector size support, it's only read-only */ + if (PAGE_SIZE == SZ_64K && sectorsize == SZ_4K) { + if (!sb_rdonly(sb) || btrfs_super_log_root(disk_super)) { + btrfs_err(fs_info, + "subpage sectorsize %u only supported read-only for page size %lu", + sectorsize, PAGE_SIZE); + err = -EINVAL; + goto fail_alloc; + } + } + ret = btrfs_init_workqueues(fs_info, fs_devices); if (ret) { err = ret; @@ -3052,6 +3325,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device chunk_root->node = read_tree_block(fs_info, btrfs_super_chunk_root(disk_super), + BTRFS_CHUNK_TREE_OBJECTID, generation, level, NULL); if (IS_ERR(chunk_root->node) || !extent_buffer_uptodate(chunk_root->node)) { @@ -3075,11 +3349,13 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device } /* - * Keep the devid that is marked to be the target device for the - * device replace procedure + * At this point we know all the devices that make this filesystem, + * including the seed devices but we don't know yet if the replace + * target is required. So free devices that are not part of this + * filesystem but skip the replace traget device which is checked + * below in btrfs_init_dev_replace(). */ - btrfs_free_extra_devids(fs_devices, 0); - + btrfs_free_extra_devids(fs_devices); if (!fs_devices->latest_bdev) { btrfs_err(fs_info, "failed to read devices"); goto fail_tree_roots; @@ -3090,6 +3366,19 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device goto fail_tree_roots; /* + * Get zone type information of zoned block devices. This will also + * handle emulation of a zoned filesystem if a regular device has the + * zoned incompat feature flag set. + */ + ret = btrfs_get_dev_zone_info_all_devices(fs_info); + if (ret) { + btrfs_err(fs_info, + "zoned: failed to read device zone info: %d", + ret); + goto fail_block_groups; + } + + /* * If we have a uuid root and we're not being told to rescan we need to * check the generation here so we can set the * BTRFS_FS_UPDATE_UUID_TREE_GEN bit. Otherwise we could commit the @@ -3126,7 +3415,12 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device goto fail_block_groups; } - btrfs_free_extra_devids(fs_devices, 1); + ret = btrfs_check_zoned_mode(fs_info); + if (ret) { + btrfs_err(fs_info, "failed to initialize zoned mode: %d", + ret); + goto fail_block_groups; + } ret = btrfs_sysfs_add_fsid(fs_devices); if (ret) { @@ -3212,26 +3506,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device } } - ret = btrfs_find_orphan_roots(fs_info); - if (ret) - goto fail_qgroup; - - if (!sb_rdonly(sb)) { - ret = btrfs_cleanup_fs_roots(fs_info); - if (ret) - goto fail_qgroup; - - mutex_lock(&fs_info->cleaner_mutex); - ret = btrfs_recover_relocation(tree_root); - mutex_unlock(&fs_info->cleaner_mutex); - if (ret < 0) { - btrfs_warn(fs_info, "failed to recover relocation: %d", - ret); - err = -EINVAL; - goto fail_qgroup; - } - } - fs_info->fs_root = btrfs_get_fs_root(fs_info, BTRFS_FS_TREE_OBJECTID, true); if (IS_ERR(fs_info->fs_root)) { err = PTR_ERR(fs_info->fs_root); @@ -3241,78 +3515,18 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device } if (sb_rdonly(sb)) - return 0; - - if (btrfs_test_opt(fs_info, CLEAR_CACHE) && - btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) { - clear_free_space_tree = 1; - } else if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) && - !btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID)) { - btrfs_warn(fs_info, "free space tree is invalid"); - clear_free_space_tree = 1; - } - - if (clear_free_space_tree) { - btrfs_info(fs_info, "clearing free space tree"); - ret = btrfs_clear_free_space_tree(fs_info); - if (ret) { - btrfs_warn(fs_info, - "failed to clear free space tree: %d", ret); - close_ctree(fs_info); - return ret; - } - } - - if (btrfs_test_opt(fs_info, FREE_SPACE_TREE) && - !btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) { - btrfs_info(fs_info, "creating free space tree"); - ret = btrfs_create_free_space_tree(fs_info); - if (ret) { - btrfs_warn(fs_info, - "failed to create free space tree: %d", ret); - close_ctree(fs_info); - return ret; - } - } + goto clear_oneshot; - down_read(&fs_info->cleanup_work_sem); - if ((ret = btrfs_orphan_cleanup(fs_info->fs_root)) || - (ret = btrfs_orphan_cleanup(fs_info->tree_root))) { - up_read(&fs_info->cleanup_work_sem); - close_ctree(fs_info); - return ret; - } - up_read(&fs_info->cleanup_work_sem); - - ret = btrfs_resume_balance_async(fs_info); - if (ret) { - btrfs_warn(fs_info, "failed to resume balance: %d", ret); - close_ctree(fs_info); - return ret; - } - - ret = btrfs_resume_dev_replace_async(fs_info); + ret = btrfs_start_pre_rw_mount(fs_info); if (ret) { - btrfs_warn(fs_info, "failed to resume device replace: %d", ret); close_ctree(fs_info); return ret; } - - btrfs_qgroup_rescan_resume(fs_info); btrfs_discard_resume(fs_info); - if (!fs_info->uuid_root) { - btrfs_info(fs_info, "creating UUID tree"); - ret = btrfs_create_uuid_tree(fs_info); - if (ret) { - btrfs_warn(fs_info, - "failed to create the UUID tree: %d", ret); - close_ctree(fs_info); - return ret; - } - } else if (btrfs_test_opt(fs_info, RESCAN_UUID_TREE) || - fs_info->generation != - btrfs_super_uuid_tree_generation(disk_super)) { + if (fs_info->uuid_root && + (btrfs_test_opt(fs_info, RESCAN_UUID_TREE) || + fs_info->generation != btrfs_super_uuid_tree_generation(disk_super))) { btrfs_info(fs_info, "checking UUID tree"); ret = btrfs_check_uuid_tree(fs_info); if (ret) { @@ -3322,14 +3536,11 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device return ret; } } - set_bit(BTRFS_FS_OPEN, &fs_info->flags); - /* - * backuproot only affect mount behavior, and if open_ctree succeeded, - * no need to keep the flag - */ - btrfs_clear_opt(fs_info->mount_opt, USEBACKUPROOT); + set_bit(BTRFS_FS_OPEN, &fs_info->flags); +clear_oneshot: + btrfs_clear_oneshot_options(fs_info); return 0; fail_qgroup: @@ -3410,10 +3621,17 @@ struct btrfs_super_block *btrfs_read_dev_one_super(struct block_device *bdev, { struct btrfs_super_block *super; struct page *page; - u64 bytenr; + u64 bytenr, bytenr_orig; struct address_space *mapping = bdev->bd_inode->i_mapping; + int ret; + + bytenr_orig = btrfs_sb_offset(copy_num); + ret = btrfs_sb_log_location_bdev(bdev, copy_num, READ, &bytenr); + if (ret == -ENOENT) + return ERR_PTR(-EINVAL); + else if (ret) + return ERR_PTR(ret); - bytenr = btrfs_sb_offset(copy_num); if (bytenr + BTRFS_SUPER_INFO_SIZE >= i_size_read(bdev->bd_inode)) return ERR_PTR(-EINVAL); @@ -3427,7 +3645,7 @@ struct btrfs_super_block *btrfs_read_dev_one_super(struct block_device *bdev, return ERR_PTR(-ENODATA); } - if (btrfs_super_bytenr(super) != bytenr) { + if (btrfs_super_bytenr(super) != bytenr_orig) { btrfs_release_disk_super(super); return ERR_PTR(-EINVAL); } @@ -3482,7 +3700,8 @@ static int write_dev_supers(struct btrfs_device *device, SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); int i; int errors = 0; - u64 bytenr; + int ret; + u64 bytenr, bytenr_orig; if (max_mirrors == 0) max_mirrors = BTRFS_SUPER_MIRROR_MAX; @@ -3494,12 +3713,22 @@ static int write_dev_supers(struct btrfs_device *device, struct bio *bio; struct btrfs_super_block *disk_super; - bytenr = btrfs_sb_offset(i); + bytenr_orig = btrfs_sb_offset(i); + ret = btrfs_sb_log_location(device, i, WRITE, &bytenr); + if (ret == -ENOENT) { + continue; + } else if (ret < 0) { + btrfs_err(device->fs_info, + "couldn't get super block location for mirror %d", + i); + errors++; + continue; + } if (bytenr + BTRFS_SUPER_INFO_SIZE >= device->commit_total_bytes) break; - btrfs_set_super_bytenr(sb, bytenr); + btrfs_set_super_bytenr(sb, bytenr_orig); crypto_shash_digest(shash, (const char *)sb + BTRFS_CSUM_SIZE, BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE, @@ -3544,6 +3773,7 @@ static int write_dev_supers(struct btrfs_device *device, bio->bi_opf |= REQ_FUA; btrfsic_submit_bio(bio); + btrfs_advance_sb_log(device, i); } return errors < i ? 0 : -1; } @@ -3560,6 +3790,7 @@ static int wait_dev_supers(struct btrfs_device *device, int max_mirrors) int i; int errors = 0; bool primary_failed = false; + int ret; u64 bytenr; if (max_mirrors == 0) @@ -3568,7 +3799,15 @@ static int wait_dev_supers(struct btrfs_device *device, int max_mirrors) for (i = 0; i < max_mirrors; i++) { struct page *page; - bytenr = btrfs_sb_offset(i); + ret = btrfs_sb_log_location(device, i, READ, &bytenr); + if (ret == -ENOENT) { + break; + } else if (ret < 0) { + errors++; + if (i == 0) + primary_failed = true; + continue; + } if (bytenr + BTRFS_SUPER_INFO_SIZE >= device->commit_total_bytes) break; @@ -3882,14 +4121,6 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info, } } - if (root->free_ino_pinned) - __btrfs_remove_free_space_cache(root->free_ino_pinned); - if (root->free_ino_ctl) - __btrfs_remove_free_space_cache(root->free_ino_ctl); - if (root->ino_cache_inode) { - iput(root->ino_cache_inode); - root->ino_cache_inode = NULL; - } if (drop_ref) btrfs_put_root(root); } @@ -4001,6 +4232,7 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) cancel_work_sync(&fs_info->async_reclaim_work); cancel_work_sync(&fs_info->async_data_reclaim_work); + cancel_work_sync(&fs_info->preempt_reclaim_work); /* Cancel or finish ongoing discard work */ btrfs_discard_cleanup(fs_info); @@ -4053,9 +4285,9 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) percpu_counter_sum(&fs_info->delalloc_bytes)); } - if (percpu_counter_sum(&fs_info->dio_bytes)) + if (percpu_counter_sum(&fs_info->ordered_bytes)) btrfs_info(fs_info, "at unmount dio bytes count %lld", - percpu_counter_sum(&fs_info->dio_bytes)); + percpu_counter_sum(&fs_info->ordered_bytes)); btrfs_sysfs_remove_mounted(fs_info); btrfs_sysfs_remove_fsid(fs_info->fs_devices); @@ -4069,6 +4301,9 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) invalidate_inode_pages2(fs_info->btree_inode->i_mapping); btrfs_stop_all_workers(fs_info); + /* We shouldn't have any transaction open at this point */ + ASSERT(list_empty(&fs_info->trans_list)); + clear_bit(BTRFS_FS_OPEN, &fs_info->flags); free_root_pointers(fs_info, true); btrfs_free_fs_roots(fs_info); @@ -4112,8 +4347,7 @@ int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid, void btrfs_mark_buffer_dirty(struct extent_buffer *buf) { - struct btrfs_fs_info *fs_info; - struct btrfs_root *root; + struct btrfs_fs_info *fs_info = buf->fs_info; u64 transid = btrfs_header_generation(buf); int was_dirty; @@ -4126,8 +4360,6 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf) if (unlikely(test_bit(EXTENT_BUFFER_UNMAPPED, &buf->bflags))) return; #endif - root = BTRFS_I(buf->pages[0]->mapping->host)->root; - fs_info = root->fs_info; btrfs_assert_tree_locked(buf); if (transid != fs_info->generation) WARN(1, KERN_CRIT "btrfs transid mismatch buffer %llu, found %llu running %llu\n", @@ -4576,6 +4808,8 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, EXTENT_DIRTY); btrfs_destroy_pinned_extent(fs_info, &cur_trans->pinned_extents); + btrfs_free_redirty_list(cur_trans); + cur_trans->state =TRANS_STATE_COMPLETED; wake_up(&cur_trans->commit_wait); } @@ -4632,3 +4866,58 @@ static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info) return 0; } + +int btrfs_init_root_free_objectid(struct btrfs_root *root) +{ + struct btrfs_path *path; + int ret; + struct extent_buffer *l; + struct btrfs_key search_key; + struct btrfs_key found_key; + int slot; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + + search_key.objectid = BTRFS_LAST_FREE_OBJECTID; + search_key.type = -1; + search_key.offset = (u64)-1; + ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0); + if (ret < 0) + goto error; + BUG_ON(ret == 0); /* Corruption */ + if (path->slots[0] > 0) { + slot = path->slots[0] - 1; + l = path->nodes[0]; + btrfs_item_key_to_cpu(l, &found_key, slot); + root->free_objectid = max_t(u64, found_key.objectid + 1, + BTRFS_FIRST_FREE_OBJECTID); + } else { + root->free_objectid = BTRFS_FIRST_FREE_OBJECTID; + } + ret = 0; +error: + btrfs_free_path(path); + return ret; +} + +int btrfs_get_free_objectid(struct btrfs_root *root, u64 *objectid) +{ + int ret; + mutex_lock(&root->objectid_mutex); + + if (unlikely(root->free_objectid >= BTRFS_LAST_FREE_OBJECTID)) { + btrfs_warn(root->fs_info, + "the objectid of root %llu reaches its highest value", + root->root_key.objectid); + ret = -ENOSPC; + goto out; + } + + *objectid = root->free_objectid++; + ret = 0; +out: + mutex_unlock(&root->objectid_mutex); + return ret; +} diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index fee69ced58b4..0e7e9526b6a8 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -43,13 +43,15 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info); int btrfs_verify_level_key(struct extent_buffer *eb, int level, struct btrfs_key *first_key, u64 parent_transid); struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr, - u64 parent_transid, int level, - struct btrfs_key *first_key); -void readahead_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr); + u64 owner_root, u64 parent_transid, + int level, struct btrfs_key *first_key); struct extent_buffer *btrfs_find_create_tree_block( struct btrfs_fs_info *fs_info, - u64 bytenr); + u64 bytenr, u64 owner_root, + int level); void btrfs_clean_tree_block(struct extent_buffer *buf); +void btrfs_clear_oneshot_options(struct btrfs_fs_info *fs_info); +int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info); int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_devices, char *options); @@ -69,6 +71,9 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, u64 objectid, bool check_ref); struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info, u64 objectid, dev_t anon_dev); +struct btrfs_root *btrfs_get_fs_root_commit_root(struct btrfs_fs_info *fs_info, + struct btrfs_path *path, + u64 objectid); void btrfs_free_fs_info(struct btrfs_fs_info *fs_info); int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info); @@ -76,7 +81,7 @@ void btrfs_btree_balance_dirty(struct btrfs_fs_info *fs_info); void btrfs_btree_balance_dirty_nodelay(struct btrfs_fs_info *fs_info); void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root); -int btrfs_validate_metadata_buffer(struct btrfs_io_bio *io_bio, u64 phy_offset, +int btrfs_validate_metadata_buffer(struct btrfs_io_bio *io_bio, struct page *page, u64 start, u64 end, int mirror); blk_status_t btrfs_submit_metadata_bio(struct inode *inode, struct bio *bio, @@ -109,12 +114,14 @@ int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid, int level, struct btrfs_key *first_key); blk_status_t btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio, enum btrfs_wq_endio_type metadata); -blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio, - int mirror_num, unsigned long bio_flags, - u64 bio_offset, void *private_data, - extent_submit_bio_start_t *submit_bio_start); +blk_status_t btrfs_wq_submit_bio(struct inode *inode, struct bio *bio, + int mirror_num, unsigned long bio_flags, + u64 dio_file_offset, + extent_submit_bio_start_t *submit_bio_start); blk_status_t btrfs_submit_bio_done(void *private_data, struct bio *bio, int mirror_num); +int btrfs_alloc_log_tree_node(struct btrfs_trans_handle *trans, + struct btrfs_root *root); int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); int btrfs_add_log_tree(struct btrfs_trans_handle *trans, @@ -128,16 +135,15 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans, int btree_lock_page_hook(struct page *page, void *data, void (*flush_fn)(void *)); int btrfs_get_num_tolerated_disk_barrier_failures(u64 flags); +int btrfs_get_free_objectid(struct btrfs_root *root, u64 *objectid); +int btrfs_init_root_free_objectid(struct btrfs_root *root); int __init btrfs_end_io_wq_init(void); void __cold btrfs_end_io_wq_exit(void); #ifdef CONFIG_DEBUG_LOCK_ALLOC -void btrfs_init_lockdep(void); void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb, int level); #else -static inline void btrfs_init_lockdep(void) -{ } static inline void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb, int level) { diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c index 1a8d419d9e1f..1d4c2397d0d6 100644 --- a/fs/btrfs/export.c +++ b/fs/btrfs/export.c @@ -222,7 +222,6 @@ static int btrfs_get_name(struct dentry *parent, char *name, path = btrfs_alloc_path(); if (!path) return -ENOMEM; - path->leave_spinning = 1; if (ino == BTRFS_FIRST_FREE_OBJECTID) { key.objectid = BTRFS_I(inode)->root->root_key.objectid; diff --git a/fs/btrfs/extent-io-tree.h b/fs/btrfs/extent-io-tree.h index 9800a8306368..04083ee5ae6e 100644 --- a/fs/btrfs/extent-io-tree.h +++ b/fs/btrfs/extent-io-tree.h @@ -21,10 +21,24 @@ struct io_failure_record; #define EXTENT_NORESERVE (1U << 11) #define EXTENT_QGROUP_RESERVED (1U << 12) #define EXTENT_CLEAR_DATA_RESV (1U << 13) +/* + * Must be cleared only during ordered extent completion or on error paths if we + * did not manage to submit bios and create the ordered extents for the range. + * Should not be cleared during page release and page invalidation (if there is + * an ordered extent in flight), that is left for the ordered extent completion. + */ #define EXTENT_DELALLOC_NEW (1U << 14) +/* + * When an ordered extent successfully completes for a region marked as a new + * delalloc range, use this flag when clearing a new delalloc range to indicate + * that the VFS' inode number of bytes should be incremented and the inode's new + * delalloc bytes decremented, in an atomic way to prevent races with stat(2). + */ +#define EXTENT_ADD_INODE_BYTES (1U << 15) #define EXTENT_DO_ACCOUNTING (EXTENT_CLEAR_META_RESV | \ EXTENT_CLEAR_DATA_RESV) -#define EXTENT_CTLBITS (EXTENT_DO_ACCOUNTING) +#define EXTENT_CTLBITS (EXTENT_DO_ACCOUNTING | \ + EXTENT_ADD_INODE_BYTES) /* * Redefined bits above which are used only in the device allocation tree, @@ -73,7 +87,7 @@ struct extent_state { /* ADD NEW ELEMENTS AFTER THIS */ wait_queue_head_t wq; refcount_t refs; - unsigned state; + u32 state; struct io_failure_record *failrec; @@ -105,19 +119,18 @@ void __cold extent_io_exit(void); u64 count_range_bits(struct extent_io_tree *tree, u64 *start, u64 search_end, - u64 max_bytes, unsigned bits, int contig); + u64 max_bytes, u32 bits, int contig); void free_extent_state(struct extent_state *state); int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end, - unsigned bits, int filled, - struct extent_state *cached_state); + u32 bits, int filled, struct extent_state *cached_state); int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, - unsigned bits, struct extent_changeset *changeset); + u32 bits, struct extent_changeset *changeset); int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, - unsigned bits, int wake, int delete, + u32 bits, int wake, int delete, struct extent_state **cached); int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, - unsigned bits, int wake, int delete, + u32 bits, int wake, int delete, struct extent_state **cached, gfp_t mask, struct extent_changeset *changeset); @@ -141,7 +154,7 @@ static inline int unlock_extent_cached_atomic(struct extent_io_tree *tree, } static inline int clear_extent_bits(struct extent_io_tree *tree, u64 start, - u64 end, unsigned bits) + u64 end, u32 bits) { int wake = 0; @@ -152,17 +165,19 @@ static inline int clear_extent_bits(struct extent_io_tree *tree, u64 start, } int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, - unsigned bits, struct extent_changeset *changeset); + u32 bits, struct extent_changeset *changeset); int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, - unsigned bits, u64 *failed_start, - struct extent_state **cached_state, gfp_t mask); + u32 bits, unsigned exclusive_bits, u64 *failed_start, + struct extent_state **cached_state, gfp_t mask, + struct extent_changeset *changeset); int set_extent_bits_nowait(struct extent_io_tree *tree, u64 start, u64 end, - unsigned bits); + u32 bits); static inline int set_extent_bits(struct extent_io_tree *tree, u64 start, - u64 end, unsigned bits) + u64 end, u32 bits) { - return set_extent_bit(tree, start, end, bits, NULL, NULL, GFP_NOFS); + return set_extent_bit(tree, start, end, bits, 0, NULL, NULL, GFP_NOFS, + NULL); } static inline int clear_extent_uptodate(struct extent_io_tree *tree, u64 start, @@ -175,8 +190,8 @@ static inline int clear_extent_uptodate(struct extent_io_tree *tree, u64 start, static inline int set_extent_dirty(struct extent_io_tree *tree, u64 start, u64 end, gfp_t mask) { - return set_extent_bit(tree, start, end, EXTENT_DIRTY, NULL, - NULL, mask); + return set_extent_bit(tree, start, end, EXTENT_DIRTY, 0, NULL, NULL, + mask, NULL); } static inline int clear_extent_dirty(struct extent_io_tree *tree, u64 start, @@ -188,16 +203,16 @@ static inline int clear_extent_dirty(struct extent_io_tree *tree, u64 start, } int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, - unsigned bits, unsigned clear_bits, + u32 bits, u32 clear_bits, struct extent_state **cached_state); static inline int set_extent_delalloc(struct extent_io_tree *tree, u64 start, - u64 end, unsigned int extra_bits, + u64 end, u32 extra_bits, struct extent_state **cached_state) { return set_extent_bit(tree, start, end, EXTENT_DELALLOC | EXTENT_UPTODATE | extra_bits, - NULL, cached_state, GFP_NOFS); + 0, NULL, cached_state, GFP_NOFS, NULL); } static inline int set_extent_defrag(struct extent_io_tree *tree, u64 start, @@ -205,30 +220,30 @@ static inline int set_extent_defrag(struct extent_io_tree *tree, u64 start, { return set_extent_bit(tree, start, end, EXTENT_DELALLOC | EXTENT_UPTODATE | EXTENT_DEFRAG, - NULL, cached_state, GFP_NOFS); + 0, NULL, cached_state, GFP_NOFS, NULL); } static inline int set_extent_new(struct extent_io_tree *tree, u64 start, u64 end) { - return set_extent_bit(tree, start, end, EXTENT_NEW, NULL, NULL, - GFP_NOFS); + return set_extent_bit(tree, start, end, EXTENT_NEW, 0, NULL, NULL, + GFP_NOFS, NULL); } static inline int set_extent_uptodate(struct extent_io_tree *tree, u64 start, u64 end, struct extent_state **cached_state, gfp_t mask) { - return set_extent_bit(tree, start, end, EXTENT_UPTODATE, NULL, - cached_state, mask); + return set_extent_bit(tree, start, end, EXTENT_UPTODATE, 0, NULL, + cached_state, mask, NULL); } int find_first_extent_bit(struct extent_io_tree *tree, u64 start, - u64 *start_ret, u64 *end_ret, unsigned bits, + u64 *start_ret, u64 *end_ret, u32 bits, struct extent_state **cached_state); void find_first_clear_extent_bit(struct extent_io_tree *tree, u64 start, - u64 *start_ret, u64 *end_ret, unsigned bits); + u64 *start_ret, u64 *end_ret, u32 bits); int find_contiguous_extent_bit(struct extent_io_tree *tree, u64 start, - u64 *start_ret, u64 *end_ret, unsigned bits); + u64 *start_ret, u64 *end_ret, u32 bits); int extent_invalidatepage(struct extent_io_tree *tree, struct page *page, unsigned long offset); bool btrfs_find_delalloc_range(struct extent_io_tree *tree, u64 *start, diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 3b21fee13e77..78ad31a59e59 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -34,6 +34,8 @@ #include "block-group.h" #include "discard.h" #include "rcu-string.h" +#include "zoned.h" +#include "dev-replace.h" #undef SCRAMBLE_DELAYED_REFS @@ -82,41 +84,6 @@ void btrfs_free_excluded_extents(struct btrfs_block_group *cache) EXTENT_UPTODATE); } -static u64 generic_ref_to_space_flags(struct btrfs_ref *ref) -{ - if (ref->type == BTRFS_REF_METADATA) { - if (ref->tree_ref.root == BTRFS_CHUNK_TREE_OBJECTID) - return BTRFS_BLOCK_GROUP_SYSTEM; - else - return BTRFS_BLOCK_GROUP_METADATA; - } - return BTRFS_BLOCK_GROUP_DATA; -} - -static void add_pinned_bytes(struct btrfs_fs_info *fs_info, - struct btrfs_ref *ref) -{ - struct btrfs_space_info *space_info; - u64 flags = generic_ref_to_space_flags(ref); - - space_info = btrfs_find_space_info(fs_info, flags); - ASSERT(space_info); - percpu_counter_add_batch(&space_info->total_bytes_pinned, ref->len, - BTRFS_TOTAL_BYTES_PINNED_BATCH); -} - -static void sub_pinned_bytes(struct btrfs_fs_info *fs_info, - struct btrfs_ref *ref) -{ - struct btrfs_space_info *space_info; - u64 flags = generic_ref_to_space_flags(ref); - - space_info = btrfs_find_space_info(fs_info, flags); - ASSERT(space_info); - percpu_counter_add_batch(&space_info->total_bytes_pinned, -ref->len, - BTRFS_TOTAL_BYTES_PINNED_BATCH); -} - /* simple helper to search for an existing data extent at a given offset */ int btrfs_lookup_data_extent(struct btrfs_fs_info *fs_info, u64 start, u64 len) { @@ -844,6 +811,7 @@ int lookup_inline_extent_backref(struct btrfs_trans_handle *trans, want = extent_ref_type(parent, owner); if (insert) { extra_size = btrfs_extent_inline_ref_size(want); + path->search_for_extension = 1; path->keep_locks = 1; } else extra_size = -1; @@ -996,6 +964,7 @@ again: out: if (insert) { path->keep_locks = 0; + path->search_for_extension = 0; btrfs_unlock_up_safe(path, 1); } return err; @@ -1297,6 +1266,46 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len, return ret; } +static int do_discard_extent(struct btrfs_bio_stripe *stripe, u64 *bytes) +{ + struct btrfs_device *dev = stripe->dev; + struct btrfs_fs_info *fs_info = dev->fs_info; + struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace; + u64 phys = stripe->physical; + u64 len = stripe->length; + u64 discarded = 0; + int ret = 0; + + /* Zone reset on a zoned filesystem */ + if (btrfs_can_zone_reset(dev, phys, len)) { + u64 src_disc; + + ret = btrfs_reset_device_zone(dev, phys, len, &discarded); + if (ret) + goto out; + + if (!btrfs_dev_replace_is_ongoing(dev_replace) || + dev != dev_replace->srcdev) + goto out; + + src_disc = discarded; + + /* Send to replace target as well */ + ret = btrfs_reset_device_zone(dev_replace->tgtdev, phys, len, + &discarded); + discarded += src_disc; + } else if (blk_queue_discard(bdev_get_queue(stripe->dev->bdev))) { + ret = btrfs_issue_discard(dev->bdev, phys, len, &discarded); + } else { + ret = 0; + *bytes = 0; + } + +out: + *bytes = discarded; + return ret; +} + int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes, u64 *actual_bytes) { @@ -1331,20 +1340,13 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr, stripe = bbio->stripes; for (i = 0; i < bbio->num_stripes; i++, stripe++) { u64 bytes; - struct request_queue *req_q; if (!stripe->dev->bdev) { ASSERT(btrfs_test_opt(fs_info, DEGRADED)); continue; } - req_q = bdev_get_queue(stripe->dev->bdev); - if (!blk_queue_discard(req_q)) - continue; - ret = btrfs_issue_discard(stripe->dev->bdev, - stripe->physical, - stripe->length, - &bytes); + ret = do_discard_extent(stripe, &bytes); if (!ret) { discarded_bytes += bytes; } else if (ret != -EOPNOTSUPP) { @@ -1386,7 +1388,6 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, struct btrfs_ref *generic_ref) { struct btrfs_fs_info *fs_info = trans->fs_info; - int old_ref_mod, new_ref_mod; int ret; ASSERT(generic_ref->type != BTRFS_REF_NOT_SET && @@ -1395,17 +1396,12 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, generic_ref->tree_ref.root == BTRFS_TREE_LOG_OBJECTID); if (generic_ref->type == BTRFS_REF_METADATA) - ret = btrfs_add_delayed_tree_ref(trans, generic_ref, - NULL, &old_ref_mod, &new_ref_mod); + ret = btrfs_add_delayed_tree_ref(trans, generic_ref, NULL); else - ret = btrfs_add_delayed_data_ref(trans, generic_ref, 0, - &old_ref_mod, &new_ref_mod); + ret = btrfs_add_delayed_data_ref(trans, generic_ref, 0); btrfs_ref_tree_mod(fs_info, generic_ref); - if (ret == 0 && old_ref_mod < 0 && new_ref_mod >= 0) - sub_pinned_bytes(fs_info, generic_ref); - return ret; } @@ -1465,7 +1461,6 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, if (!path) return -ENOMEM; - path->leave_spinning = 1; /* this will setup the path even if it fails to insert the back ref */ ret = insert_inline_extent_backref(trans, path, bytenr, num_bytes, parent, root_objectid, owner, @@ -1489,7 +1484,6 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, btrfs_mark_buffer_dirty(leaf); btrfs_release_path(path); - path->leave_spinning = 1; /* now insert the actual backref */ if (owner < BTRFS_FIRST_FREE_OBJECTID) { BUG_ON(refs_to_add != 1); @@ -1605,7 +1599,6 @@ static int run_delayed_extent_op(struct btrfs_trans_handle *trans, } again: - path->leave_spinning = 1; ret = btrfs_search_slot(trans, fs_info->extent_root, &key, path, 0, 1); if (ret < 0) { err = ret; @@ -1796,34 +1789,28 @@ void btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info, { int nr_items = 1; /* Dropping this ref head update. */ - if (head->total_ref_mod < 0) { - struct btrfs_space_info *space_info; - u64 flags; + /* + * We had csum deletions accounted for in our delayed refs rsv, we need + * to drop the csum leaves for this update from our delayed_refs_rsv. + */ + if (head->total_ref_mod < 0 && head->is_data) { + spin_lock(&delayed_refs->lock); + delayed_refs->pending_csums -= head->num_bytes; + spin_unlock(&delayed_refs->lock); + nr_items += btrfs_csum_bytes_to_leaves(fs_info, head->num_bytes); + } - if (head->is_data) - flags = BTRFS_BLOCK_GROUP_DATA; - else if (head->is_system) - flags = BTRFS_BLOCK_GROUP_SYSTEM; - else - flags = BTRFS_BLOCK_GROUP_METADATA; - space_info = btrfs_find_space_info(fs_info, flags); - ASSERT(space_info); - percpu_counter_add_batch(&space_info->total_bytes_pinned, - -head->num_bytes, - BTRFS_TOTAL_BYTES_PINNED_BATCH); + /* + * We were dropping refs, or had a new ref and dropped it, and thus must + * adjust down our total_bytes_pinned, the space may or may not have + * been pinned and so is accounted for properly in the pinned space by + * now. + */ + if (head->total_ref_mod < 0 || + (head->total_ref_mod == 0 && head->must_insert_reserved)) { + u64 flags = btrfs_ref_head_to_space_flags(head); - /* - * We had csum deletions accounted for in our delayed refs rsv, - * we need to drop the csum leaves for this update from our - * delayed_refs_rsv. - */ - if (head->is_data) { - spin_lock(&delayed_refs->lock); - delayed_refs->pending_csums -= head->num_bytes; - spin_unlock(&delayed_refs->lock); - nr_items += btrfs_csum_bytes_to_leaves(fs_info, - head->num_bytes); - } + btrfs_mod_total_bytes_pinned(fs_info, flags, -head->num_bytes); } btrfs_delayed_refs_rsv_release(fs_info, nr_items); @@ -2133,25 +2120,6 @@ static u64 find_middle(struct rb_root *root) #endif /* - * Takes the number of bytes to be csumm'ed and figures out how many leaves it - * would require to store the csums for that many bytes. - */ -u64 btrfs_csum_bytes_to_leaves(struct btrfs_fs_info *fs_info, u64 csum_bytes) -{ - u64 csum_size; - u64 num_csums_per_leaf; - u64 num_csums; - - csum_size = BTRFS_MAX_ITEM_SIZE(fs_info); - num_csums_per_leaf = div64_u64(csum_size, - (u64)btrfs_super_csum_size(fs_info->super_copy)); - num_csums = div64_u64(csum_bytes, fs_info->sectorsize); - num_csums += num_csums_per_leaf - 1; - num_csums = div64_u64(num_csums, num_csums_per_leaf); - return num_csums; -} - -/* * this starts processing the delayed reference count updates and * extent insertions we have queued up so far. count can be * 0, which means to process everything in the tree at the start @@ -2180,7 +2148,7 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, delayed_refs = &trans->transaction->delayed_refs; if (count == 0) - count = atomic_read(&delayed_refs->num_entries) * 2; + count = delayed_refs->num_heads_ready; again: #ifdef SCRAMBLE_DELAYED_REFS @@ -2592,8 +2560,7 @@ static int pin_down_extent(struct btrfs_trans_handle *trans, spin_unlock(&cache->lock); spin_unlock(&cache->space_info->lock); - percpu_counter_add_batch(&cache->space_info->total_bytes_pinned, - num_bytes, BTRFS_TOTAL_BYTES_PINNED_BATCH); + __btrfs_mod_total_bytes_pinned(cache->space_info, num_bytes); set_extent_dirty(&trans->transaction->pinned_extents, bytenr, bytenr + num_bytes - 1, GFP_NOFS | __GFP_NOFAIL); return 0; @@ -2622,8 +2589,6 @@ int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans, struct btrfs_block_group *cache; int ret; - btrfs_add_excluded_extent(trans->fs_info, bytenr, num_bytes); - cache = btrfs_lookup_block_group(trans->fs_info, bytenr); if (!cache) return -EINVAL; @@ -2635,11 +2600,19 @@ int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans, * the pinned extents. */ btrfs_cache_block_group(cache, 1); + /* + * Make sure we wait until the cache is completely built in case it is + * missing or is invalid and therefore needs to be rebuilt. + */ + ret = btrfs_wait_block_group_cache_done(cache); + if (ret) + goto out; pin_down_extent(trans, cache, bytenr, num_bytes, 0); /* remove us from the free space cache (if we're there at all) */ ret = btrfs_remove_free_space(cache, bytenr, num_bytes); +out: btrfs_put_block_group(cache); return ret; } @@ -2649,45 +2622,22 @@ static int __exclude_logged_extent(struct btrfs_fs_info *fs_info, { int ret; struct btrfs_block_group *block_group; - struct btrfs_caching_control *caching_ctl; block_group = btrfs_lookup_block_group(fs_info, start); if (!block_group) return -EINVAL; - btrfs_cache_block_group(block_group, 0); - caching_ctl = btrfs_get_caching_control(block_group); - - if (!caching_ctl) { - /* Logic error */ - BUG_ON(!btrfs_block_group_done(block_group)); - ret = btrfs_remove_free_space(block_group, start, num_bytes); - } else { - mutex_lock(&caching_ctl->mutex); - - if (start >= caching_ctl->progress) { - ret = btrfs_add_excluded_extent(fs_info, start, - num_bytes); - } else if (start + num_bytes <= caching_ctl->progress) { - ret = btrfs_remove_free_space(block_group, - start, num_bytes); - } else { - num_bytes = caching_ctl->progress - start; - ret = btrfs_remove_free_space(block_group, - start, num_bytes); - if (ret) - goto out_lock; + btrfs_cache_block_group(block_group, 1); + /* + * Make sure we wait until the cache is completely built in case it is + * missing or is invalid and therefore needs to be rebuilt. + */ + ret = btrfs_wait_block_group_cache_done(block_group); + if (ret) + goto out; - num_bytes = (start + num_bytes) - - caching_ctl->progress; - start = caching_ctl->progress; - ret = btrfs_add_excluded_extent(fs_info, start, - num_bytes); - } -out_lock: - mutex_unlock(&caching_ctl->mutex); - btrfs_put_caching_control(caching_ctl); - } + ret = btrfs_remove_free_space(block_group, start, num_bytes); +out: btrfs_put_block_group(block_group); return ret; } @@ -2730,31 +2680,6 @@ btrfs_inc_block_group_reservations(struct btrfs_block_group *bg) atomic_inc(&bg->reservations); } -void btrfs_prepare_extent_commit(struct btrfs_fs_info *fs_info) -{ - struct btrfs_caching_control *next; - struct btrfs_caching_control *caching_ctl; - struct btrfs_block_group *cache; - - down_write(&fs_info->commit_root_sem); - - list_for_each_entry_safe(caching_ctl, next, - &fs_info->caching_block_groups, list) { - cache = caching_ctl->block_group; - if (btrfs_block_group_done(cache)) { - cache->last_byte_to_unpin = (u64)-1; - list_del_init(&caching_ctl->list); - btrfs_put_caching_control(caching_ctl); - } else { - cache->last_byte_to_unpin = caching_ctl->progress; - } - } - - up_write(&fs_info->commit_root_sem); - - btrfs_update_global_block_rsv(fs_info); -} - /* * Returns the free cluster for the given space info and sets empty_cluster to * what it should be based on the mount options. @@ -2816,11 +2741,13 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info, len = cache->start + cache->length - start; len = min(len, end + 1 - start); - if (start < cache->last_byte_to_unpin) { - len = min(len, cache->last_byte_to_unpin - start); - if (return_free_space) - btrfs_add_free_space(cache, start, len); + down_read(&fs_info->commit_root_sem); + if (start < cache->last_byte_to_unpin && return_free_space) { + u64 add_len = min(len, cache->last_byte_to_unpin - start); + + btrfs_add_free_space(cache, start, add_len); } + up_read(&fs_info->commit_root_sem); start += len; total_unpinned += len; @@ -2844,11 +2771,14 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info, cache->pinned -= len; btrfs_space_info_update_bytes_pinned(fs_info, space_info, -len); space_info->max_extent_size = 0; - percpu_counter_add_batch(&space_info->total_bytes_pinned, - -len, BTRFS_TOTAL_BYTES_PINNED_BATCH); + __btrfs_mod_total_bytes_pinned(space_info, -len); if (cache->ro) { space_info->bytes_readonly += len; readonly = true; + } else if (btrfs_is_zoned(fs_info)) { + /* Need reset before reusing in a zoned block group */ + space_info->bytes_zone_unusable += len; + readonly = true; } spin_unlock(&cache->lock); if (!readonly && return_free_space && @@ -2901,9 +2831,6 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans) mutex_unlock(&fs_info->unused_bg_unpin_mutex); break; } - if (test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags)) - clear_extent_bits(&fs_info->excluded_extents, start, - end, EXTENT_UPTODATE); if (btrfs_test_opt(fs_info, DISCARD_SYNC)) ret = btrfs_discard_extent(fs_info, start, @@ -3040,8 +2967,6 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, if (!path) return -ENOMEM; - path->leave_spinning = 1; - is_data = owner_objectid >= BTRFS_FIRST_FREE_OBJECTID; if (!is_data && refs_to_drop != 1) { @@ -3106,7 +3031,6 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, goto out; } btrfs_release_path(path); - path->leave_spinning = 1; /* Slow path to locate EXTENT/METADATA_ITEM */ key.objectid = bytenr; @@ -3185,7 +3109,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_tree_block_info *bi; if (item_size < sizeof(*ei) + sizeof(*bi)) { btrfs_crit(info, -"invalid extent item size for key (%llu, %u, %llu) owner %llu, has %u expect >= %lu", +"invalid extent item size for key (%llu, %u, %llu) owner %llu, has %u expect >= %zu", key.objectid, key.type, key.offset, owner_objectid, item_size, sizeof(*ei) + sizeof(*bi)); @@ -3384,7 +3308,6 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, { struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_ref generic_ref = { 0 }; - int pin = 1; int ret; btrfs_init_generic_ref(&generic_ref, BTRFS_DROP_DELAYED_REF, @@ -3393,13 +3316,9 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, root->root_key.objectid); if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) { - int old_ref_mod, new_ref_mod; - btrfs_ref_tree_mod(fs_info, &generic_ref); - ret = btrfs_add_delayed_tree_ref(trans, &generic_ref, NULL, - &old_ref_mod, &new_ref_mod); + ret = btrfs_add_delayed_tree_ref(trans, &generic_ref, NULL); BUG_ON(ret); /* -ENOMEM */ - pin = old_ref_mod >= 0 && new_ref_mod < 0; } if (last_ref && btrfs_header_generation(buf) == trans->transid) { @@ -3407,11 +3326,12 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) { ret = check_ref_cleanup(trans, buf->start); - if (!ret) + if (!ret) { + btrfs_redirty_list_add(trans->transaction, buf); goto out; + } } - pin = 0; cache = btrfs_lookup_block_group(fs_info, buf->start); if (btrfs_header_flag(buf, BTRFS_HEADER_FLAG_WRITTEN)) { @@ -3420,6 +3340,13 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, goto out; } + if (btrfs_is_zoned(fs_info)) { + btrfs_redirty_list_add(trans->transaction, buf); + pin_down_extent(trans, cache, buf->start, buf->len, 1); + btrfs_put_block_group(cache); + goto out; + } + WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->bflags)); btrfs_add_free_space(cache, buf->start, buf->len); @@ -3428,9 +3355,6 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, trace_btrfs_reserved_extent_free(fs_info, buf->start, buf->len); } out: - if (pin) - add_pinned_bytes(fs_info, &generic_ref); - if (last_ref) { /* * Deleting the buffer, clear the corrupt flag since it doesn't @@ -3444,7 +3368,6 @@ out: int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_ref *ref) { struct btrfs_fs_info *fs_info = trans->fs_info; - int old_ref_mod, new_ref_mod; int ret; if (btrfs_is_testing(fs_info)) @@ -3460,14 +3383,11 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_ref *ref) ref->data_ref.ref_root == BTRFS_TREE_LOG_OBJECTID)) { /* unlocks the pinned mutex */ btrfs_pin_extent(trans, ref->bytenr, ref->len, 1); - old_ref_mod = new_ref_mod = 0; ret = 0; } else if (ref->type == BTRFS_REF_METADATA) { - ret = btrfs_add_delayed_tree_ref(trans, ref, NULL, - &old_ref_mod, &new_ref_mod); + ret = btrfs_add_delayed_tree_ref(trans, ref, NULL); } else { - ret = btrfs_add_delayed_data_ref(trans, ref, 0, - &old_ref_mod, &new_ref_mod); + ret = btrfs_add_delayed_data_ref(trans, ref, 0); } if (!((ref->type == BTRFS_REF_METADATA && @@ -3476,9 +3396,6 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_ref *ref) ref->data_ref.ref_root == BTRFS_TREE_LOG_OBJECTID))) btrfs_ref_tree_mod(fs_info, ref); - if (ret == 0 && old_ref_mod >= 0 && new_ref_mod < 0) - add_pinned_bytes(fs_info, ref); - return ret; } @@ -3555,6 +3472,7 @@ btrfs_release_block_group(struct btrfs_block_group *cache, enum btrfs_extent_allocation_policy { BTRFS_EXTENT_ALLOC_CLUSTERED, + BTRFS_EXTENT_ALLOC_ZONED, }; /* @@ -3579,6 +3497,9 @@ struct find_free_extent_ctl { bool have_caching_bg; bool orig_have_caching_bg; + /* Allocation is called for tree-log */ + bool for_treelog; + /* RAID index, converted from flags */ int index; @@ -3807,6 +3728,118 @@ static int do_allocation_clustered(struct btrfs_block_group *block_group, return find_free_extent_unclustered(block_group, ffe_ctl); } +/* + * Tree-log block group locking + * ============================ + * + * fs_info::treelog_bg_lock protects the fs_info::treelog_bg which + * indicates the starting address of a block group, which is reserved only + * for tree-log metadata. + * + * Lock nesting + * ============ + * + * space_info::lock + * block_group::lock + * fs_info::treelog_bg_lock + */ + +/* + * Simple allocator for sequential-only block group. It only allows sequential + * allocation. No need to play with trees. This function also reserves the + * bytes as in btrfs_add_reserved_bytes. + */ +static int do_allocation_zoned(struct btrfs_block_group *block_group, + struct find_free_extent_ctl *ffe_ctl, + struct btrfs_block_group **bg_ret) +{ + struct btrfs_fs_info *fs_info = block_group->fs_info; + struct btrfs_space_info *space_info = block_group->space_info; + struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; + u64 start = block_group->start; + u64 num_bytes = ffe_ctl->num_bytes; + u64 avail; + u64 bytenr = block_group->start; + u64 log_bytenr; + int ret = 0; + bool skip; + + ASSERT(btrfs_is_zoned(block_group->fs_info)); + + /* + * Do not allow non-tree-log blocks in the dedicated tree-log block + * group, and vice versa. + */ + spin_lock(&fs_info->treelog_bg_lock); + log_bytenr = fs_info->treelog_bg; + skip = log_bytenr && ((ffe_ctl->for_treelog && bytenr != log_bytenr) || + (!ffe_ctl->for_treelog && bytenr == log_bytenr)); + spin_unlock(&fs_info->treelog_bg_lock); + if (skip) + return 1; + + spin_lock(&space_info->lock); + spin_lock(&block_group->lock); + spin_lock(&fs_info->treelog_bg_lock); + + ASSERT(!ffe_ctl->for_treelog || + block_group->start == fs_info->treelog_bg || + fs_info->treelog_bg == 0); + + if (block_group->ro) { + ret = 1; + goto out; + } + + /* + * Do not allow currently using block group to be tree-log dedicated + * block group. + */ + if (ffe_ctl->for_treelog && !fs_info->treelog_bg && + (block_group->used || block_group->reserved)) { + ret = 1; + goto out; + } + + avail = block_group->length - block_group->alloc_offset; + if (avail < num_bytes) { + if (ffe_ctl->max_extent_size < avail) { + /* + * With sequential allocator, free space is always + * contiguous + */ + ffe_ctl->max_extent_size = avail; + ffe_ctl->total_free_space = avail; + } + ret = 1; + goto out; + } + + if (ffe_ctl->for_treelog && !fs_info->treelog_bg) + fs_info->treelog_bg = block_group->start; + + ffe_ctl->found_offset = start + block_group->alloc_offset; + block_group->alloc_offset += num_bytes; + spin_lock(&ctl->tree_lock); + ctl->free_space -= num_bytes; + spin_unlock(&ctl->tree_lock); + + /* + * We do not check if found_offset is aligned to stripesize. The + * address is anyway rewritten when using zone append writing. + */ + + ffe_ctl->search_start = ffe_ctl->found_offset; + +out: + if (ret && ffe_ctl->for_treelog) + fs_info->treelog_bg = 0; + spin_unlock(&fs_info->treelog_bg_lock); + spin_unlock(&block_group->lock); + spin_unlock(&space_info->lock); + return ret; +} + static int do_allocation(struct btrfs_block_group *block_group, struct find_free_extent_ctl *ffe_ctl, struct btrfs_block_group **bg_ret) @@ -3814,6 +3847,8 @@ static int do_allocation(struct btrfs_block_group *block_group, switch (ffe_ctl->policy) { case BTRFS_EXTENT_ALLOC_CLUSTERED: return do_allocation_clustered(block_group, ffe_ctl, bg_ret); + case BTRFS_EXTENT_ALLOC_ZONED: + return do_allocation_zoned(block_group, ffe_ctl, bg_ret); default: BUG(); } @@ -3828,6 +3863,9 @@ static void release_block_group(struct btrfs_block_group *block_group, ffe_ctl->retry_clustered = false; ffe_ctl->retry_unclustered = false; break; + case BTRFS_EXTENT_ALLOC_ZONED: + /* Nothing to do */ + break; default: BUG(); } @@ -3856,6 +3894,9 @@ static void found_extent(struct find_free_extent_ctl *ffe_ctl, case BTRFS_EXTENT_ALLOC_CLUSTERED: found_extent_clustered(ffe_ctl, ins); break; + case BTRFS_EXTENT_ALLOC_ZONED: + /* Nothing to do */ + break; default: BUG(); } @@ -3871,6 +3912,9 @@ static int chunk_allocation_failed(struct find_free_extent_ctl *ffe_ctl) */ ffe_ctl->loop = LOOP_NO_EMPTY_SIZE; return 0; + case BTRFS_EXTENT_ALLOC_ZONED: + /* Give up here */ + return -ENOSPC; default: BUG(); } @@ -4039,6 +4083,14 @@ static int prepare_allocation(struct btrfs_fs_info *fs_info, case BTRFS_EXTENT_ALLOC_CLUSTERED: return prepare_allocation_clustered(fs_info, ffe_ctl, space_info, ins); + case BTRFS_EXTENT_ALLOC_ZONED: + if (ffe_ctl->for_treelog) { + spin_lock(&fs_info->treelog_bg_lock); + if (fs_info->treelog_bg) + ffe_ctl->hint_byte = fs_info->treelog_bg; + spin_unlock(&fs_info->treelog_bg_lock); + } + return 0; default: BUG(); } @@ -4081,6 +4133,7 @@ static noinline int find_free_extent(struct btrfs_root *root, struct find_free_extent_ctl ffe_ctl = {0}; struct btrfs_space_info *space_info; bool full_search = false; + bool for_treelog = (root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID); WARN_ON(num_bytes < fs_info->sectorsize); @@ -4094,6 +4147,7 @@ static noinline int find_free_extent(struct btrfs_root *root, ffe_ctl.orig_have_caching_bg = false; ffe_ctl.found_offset = 0; ffe_ctl.hint_byte = hint_byte_orig; + ffe_ctl.for_treelog = for_treelog; ffe_ctl.policy = BTRFS_EXTENT_ALLOC_CLUSTERED; /* For clustered allocation */ @@ -4102,6 +4156,9 @@ static noinline int find_free_extent(struct btrfs_root *root, ffe_ctl.last_ptr = NULL; ffe_ctl.use_cluster = true; + if (btrfs_is_zoned(fs_info)) + ffe_ctl.policy = BTRFS_EXTENT_ALLOC_ZONED; + ins->type = BTRFS_EXTENT_ITEM_KEY; ins->objectid = 0; ins->offset = 0; @@ -4165,8 +4222,11 @@ search: struct btrfs_block_group *bg_ret; /* If the block group is read-only, we can skip it entirely. */ - if (unlikely(block_group->ro)) + if (unlikely(block_group->ro)) { + if (for_treelog) + btrfs_clear_treelog_bg(block_group); continue; + } btrfs_grab_block_group(block_group, delalloc); ffe_ctl.search_start = block_group->start; @@ -4244,20 +4304,21 @@ have_block_group: /* move on to the next group */ if (ffe_ctl.search_start + num_bytes > block_group->start + block_group->length) { - btrfs_add_free_space(block_group, ffe_ctl.found_offset, - num_bytes); + btrfs_add_free_space_unused(block_group, + ffe_ctl.found_offset, num_bytes); goto loop; } if (ffe_ctl.found_offset < ffe_ctl.search_start) - btrfs_add_free_space(block_group, ffe_ctl.found_offset, - ffe_ctl.search_start - ffe_ctl.found_offset); + btrfs_add_free_space_unused(block_group, + ffe_ctl.found_offset, + ffe_ctl.search_start - ffe_ctl.found_offset); ret = btrfs_add_reserved_bytes(block_group, ram_bytes, num_bytes, delalloc); if (ret == -EAGAIN) { - btrfs_add_free_space(block_group, ffe_ctl.found_offset, - num_bytes); + btrfs_add_free_space_unused(block_group, + ffe_ctl.found_offset, num_bytes); goto loop; } btrfs_inc_block_group_reservations(block_group); @@ -4351,6 +4412,7 @@ int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes, bool final_tried = num_bytes == min_alloc_size; u64 flags; int ret; + bool for_treelog = (root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID); flags = get_alloc_profile_by_root(root, is_data); again: @@ -4374,8 +4436,8 @@ again: sinfo = btrfs_find_space_info(fs_info, flags); btrfs_err(fs_info, - "allocation failed flags %llu, wanted %llu", - flags, num_bytes); + "allocation failed flags %llu, wanted %llu tree-log %d", + flags, num_bytes, for_treelog); if (sinfo) btrfs_dump_space_info(fs_info, sinfo, num_bytes, 1); @@ -4448,7 +4510,6 @@ static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans, if (!path) return -ENOMEM; - path->leave_spinning = 1; ret = btrfs_insert_empty_item(trans, fs_info->extent_root, path, ins, size); if (ret) { @@ -4533,7 +4594,6 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans, if (!path) return -ENOMEM; - path->leave_spinning = 1; ret = btrfs_insert_empty_item(trans, fs_info->extent_root, path, &extent_key, size); if (ret) { @@ -4559,7 +4619,6 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans, } if (node->type == BTRFS_SHARED_BLOCK_REF_KEY) { - BUG_ON(!(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF)); btrfs_set_extent_inline_ref_type(leaf, iref, BTRFS_SHARED_BLOCK_REF_KEY); btrfs_set_extent_inline_ref_offset(leaf, iref, ref->parent); @@ -4596,7 +4655,6 @@ int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans, struct btrfs_key *ins) { struct btrfs_ref generic_ref = { 0 }; - int ret; BUG_ON(root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID); @@ -4604,9 +4662,8 @@ int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans, ins->objectid, ins->offset, 0); btrfs_init_data_ref(&generic_ref, root->root_key.objectid, owner, offset); btrfs_ref_tree_mod(root->fs_info, &generic_ref); - ret = btrfs_add_delayed_data_ref(trans, &generic_ref, - ram_bytes, NULL, NULL); - return ret; + + return btrfs_add_delayed_data_ref(trans, &generic_ref, ram_bytes); } /* @@ -4662,7 +4719,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_fs_info *fs_info = root->fs_info; struct extent_buffer *buf; - buf = btrfs_find_create_tree_block(fs_info, bytenr); + buf = btrfs_find_create_tree_block(fs_info, bytenr, owner, level); if (IS_ERR(buf)) return buf; @@ -4679,12 +4736,17 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root, return ERR_PTR(-EUCLEAN); } + /* + * This needs to stay, because we could allocate a freed block from an + * old tree into a new tree, so we need to make sure this new block is + * set to the appropriate level and owner. + */ btrfs_set_buffer_lockdep_class(owner, buf, level); __btrfs_tree_lock(buf, nest); btrfs_clean_tree_block(buf); clear_bit(EXTENT_BUFFER_STALE, &buf->bflags); + clear_bit(EXTENT_BUFFER_NO_CHECK, &buf->bflags); - btrfs_set_lock_blocking_write(buf); set_extent_buffer_uptodate(buf); memzero_extent_buffer(buf, 0, sizeof(struct btrfs_header)); @@ -4794,8 +4856,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, generic_ref.real_root = root->root_key.objectid; btrfs_init_tree_ref(&generic_ref, level, root_objectid); btrfs_ref_tree_mod(fs_info, &generic_ref); - ret = btrfs_add_delayed_tree_ref(trans, &generic_ref, - extent_op, NULL, NULL); + ret = btrfs_add_delayed_tree_ref(trans, &generic_ref, extent_op); if (ret) goto out_free_delayed; } @@ -4905,7 +4966,7 @@ static noinline void reada_walk_down(struct btrfs_trans_handle *trans, continue; } reada: - readahead_tree_block(fs_info, bytenr); + btrfs_readahead_node_child(eb, slot); nread++; } wc->reada_slot = slot; @@ -5064,16 +5125,13 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans, next = find_extent_buffer(fs_info, bytenr); if (!next) { - next = btrfs_find_create_tree_block(fs_info, bytenr); + next = btrfs_find_create_tree_block(fs_info, bytenr, + root->root_key.objectid, level - 1); if (IS_ERR(next)) return PTR_ERR(next); - - btrfs_set_buffer_lockdep_class(root->root_key.objectid, next, - level - 1); reada = 1; } btrfs_tree_lock(next); - btrfs_set_lock_blocking_write(next); ret = btrfs_lookup_extent_info(trans, fs_info, bytenr, level - 1, 1, &wc->refs[level - 1], @@ -5124,8 +5182,8 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans, if (!next) { if (reada && level == 1) reada_walk_down(trans, root, wc, path); - next = read_tree_block(fs_info, bytenr, generation, level - 1, - &first_key); + next = read_tree_block(fs_info, bytenr, root->root_key.objectid, + generation, level - 1, &first_key); if (IS_ERR(next)) { return PTR_ERR(next); } else if (!extent_buffer_uptodate(next)) { @@ -5133,7 +5191,6 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans, return -EIO; } btrfs_tree_lock(next); - btrfs_set_lock_blocking_write(next); } level--; @@ -5145,7 +5202,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans, } path->nodes[level] = next; path->slots[level] = 0; - path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING; + path->locks[level] = BTRFS_WRITE_LOCK; wc->level = level; if (wc->level == 1) wc->reada_slot = 0; @@ -5273,8 +5330,7 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans, if (!path->locks[level]) { BUG_ON(level == 0); btrfs_tree_lock(eb); - btrfs_set_lock_blocking_write(eb); - path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING; + path->locks[level] = BTRFS_WRITE_LOCK; ret = btrfs_lookup_extent_info(trans, fs_info, eb->start, level, 1, @@ -5317,8 +5373,7 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans, if (!path->locks[level] && btrfs_header_generation(eb) == trans->transid) { btrfs_tree_lock(eb); - btrfs_set_lock_blocking_write(eb); - path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING; + path->locks[level] = BTRFS_WRITE_LOCK; } btrfs_clean_tree_block(eb); } @@ -5486,9 +5541,8 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc) if (btrfs_disk_key_objectid(&root_item->drop_progress) == 0) { level = btrfs_header_level(root->node); path->nodes[level] = btrfs_lock_root_node(root); - btrfs_set_lock_blocking_write(path->nodes[level]); path->slots[level] = 0; - path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING; + path->locks[level] = BTRFS_WRITE_LOCK; memset(&wc->update_progress, 0, sizeof(wc->update_progress)); } else { @@ -5496,7 +5550,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc) memcpy(&wc->update_progress, &key, sizeof(wc->update_progress)); - level = root_item->drop_level; + level = btrfs_root_drop_level(root_item); BUG_ON(level == 0); path->lowest_level = level; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); @@ -5516,8 +5570,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc) level = btrfs_header_level(root->node); while (1) { btrfs_tree_lock(path->nodes[level]); - btrfs_set_lock_blocking_write(path->nodes[level]); - path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING; + path->locks[level] = BTRFS_WRITE_LOCK; ret = btrfs_lookup_extent_info(trans, fs_info, path->nodes[level]->start, @@ -5529,7 +5582,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc) } BUG_ON(wc->refs[level] == 0); - if (level == root_item->drop_level) + if (level == btrfs_root_drop_level(root_item)) break; btrfs_tree_unlock(path->nodes[level]); @@ -5574,7 +5627,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc) } btrfs_cpu_key_to_disk(&root_item->drop_progress, &wc->drop_progress); - root_item->drop_level = wc->drop_level; + btrfs_set_root_drop_level(root_item, wc->drop_level); BUG_ON(wc->level == 0); if (btrfs_should_end_transaction(trans) || @@ -5596,7 +5649,15 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc) goto out_free; } - trans = btrfs_start_transaction(tree_root, 0); + /* + * Use join to avoid potential EINTR from transaction + * start. See wait_reserve_ticket and the whole + * reservation callchain. + */ + if (for_reloc) + trans = btrfs_join_transaction(tree_root); + else + trans = btrfs_start_transaction(tree_root, 0); if (IS_ERR(trans)) { err = PTR_ERR(trans); goto out_free; @@ -5704,7 +5765,7 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans, level = btrfs_header_level(node); path->nodes[level] = node; path->slots[level] = 0; - path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING; + path->locks[level] = BTRFS_WRITE_LOCK; wc->refs[parent_level] = 1; wc->flags[parent_level] = BTRFS_BLOCK_FLAG_FULL_BACKREF; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 60f5f68d892d..4dfb3ead1175 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -24,6 +24,9 @@ #include "rcu-string.h" #include "backref.h" #include "disk-io.h" +#include "subpage.h" +#include "zoned.h" +#include "block-group.h" static struct kmem_cache *extent_state_cache; static struct kmem_cache *extent_buffer_cache; @@ -142,7 +145,7 @@ struct extent_page_data { unsigned int sync_io:1; }; -static int add_extent_changeset(struct extent_state *state, unsigned bits, +static int add_extent_changeset(struct extent_state *state, u32 bits, struct extent_changeset *changeset, int set) { @@ -389,16 +392,16 @@ do_insert: } /** - * __etree_search - searche @tree for an entry that contains @offset. Such - * entry would have entry->start <= offset && entry->end >= offset. + * Search @tree for an entry that contains @offset. Such entry would have + * entry->start <= offset && entry->end >= offset. * - * @tree - the tree to search - * @offset - offset that should fall within an entry in @tree - * @next_ret - pointer to the first entry whose range ends after @offset - * @prev - pointer to the first entry whose range begins before @offset - * @p_ret - pointer where new node should be anchored (used when inserting an - * entry in the tree) - * @parent_ret - points to entry which would have been the parent of the entry, + * @tree: the tree to search + * @offset: offset that should fall within an entry in @tree + * @next_ret: pointer to the first entry whose range ends after @offset + * @prev_ret: pointer to the first entry whose range begins before @offset + * @p_ret: pointer where new node should be anchored (used when inserting an + * entry in the tree) + * @parent_ret: points to entry which would have been the parent of the entry, * containing @offset * * This function returns a pointer to the entry that contains @offset byte @@ -530,7 +533,7 @@ static void merge_state(struct extent_io_tree *tree, } static void set_state_bits(struct extent_io_tree *tree, - struct extent_state *state, unsigned *bits, + struct extent_state *state, u32 *bits, struct extent_changeset *changeset); /* @@ -547,7 +550,7 @@ static int insert_state(struct extent_io_tree *tree, struct extent_state *state, u64 start, u64 end, struct rb_node ***p, struct rb_node **parent, - unsigned *bits, struct extent_changeset *changeset) + u32 *bits, struct extent_changeset *changeset) { struct rb_node *node; @@ -628,11 +631,11 @@ static struct extent_state *next_state(struct extent_state *state) */ static struct extent_state *clear_state_bit(struct extent_io_tree *tree, struct extent_state *state, - unsigned *bits, int wake, + u32 *bits, int wake, struct extent_changeset *changeset) { struct extent_state *next; - unsigned bits_to_clear = *bits & ~EXTENT_CTLBITS; + u32 bits_to_clear = *bits & ~EXTENT_CTLBITS; int ret; if ((bits_to_clear & EXTENT_DIRTY) && (state->state & EXTENT_DIRTY)) { @@ -676,9 +679,7 @@ alloc_extent_state_atomic(struct extent_state *prealloc) static void extent_io_tree_panic(struct extent_io_tree *tree, int err) { - struct inode *inode = tree->private_data; - - btrfs_panic(btrfs_sb(inode->i_sb), err, + btrfs_panic(tree->fs_info, err, "locking error: extent tree was modified by another thread while locked"); } @@ -695,9 +696,9 @@ static void extent_io_tree_panic(struct extent_io_tree *tree, int err) * This takes the tree lock, and returns 0 on success and < 0 on error. */ int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, - unsigned bits, int wake, int delete, - struct extent_state **cached_state, - gfp_t mask, struct extent_changeset *changeset) + u32 bits, int wake, int delete, + struct extent_state **cached_state, + gfp_t mask, struct extent_changeset *changeset) { struct extent_state *state; struct extent_state *cached; @@ -868,7 +869,7 @@ static void wait_on_state(struct extent_io_tree *tree, * The tree lock is taken by this function */ static void wait_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, - unsigned long bits) + u32 bits) { struct extent_state *state; struct rb_node *node; @@ -915,9 +916,9 @@ out: static void set_state_bits(struct extent_io_tree *tree, struct extent_state *state, - unsigned *bits, struct extent_changeset *changeset) + u32 *bits, struct extent_changeset *changeset) { - unsigned bits_to_set = *bits & ~EXTENT_CTLBITS; + u32 bits_to_set = *bits & ~EXTENT_CTLBITS; int ret; if (tree->private_data && is_data_inode(tree->private_data)) @@ -961,12 +962,10 @@ static void cache_state(struct extent_state *state, * * [start, end] is inclusive This takes the tree lock. */ - -static int __must_check -__set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, - unsigned bits, unsigned exclusive_bits, - u64 *failed_start, struct extent_state **cached_state, - gfp_t mask, struct extent_changeset *changeset) +int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, u32 bits, + u32 exclusive_bits, u64 *failed_start, + struct extent_state **cached_state, gfp_t mask, + struct extent_changeset *changeset) { struct extent_state *state; struct extent_state *prealloc = NULL; @@ -980,6 +979,10 @@ __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, btrfs_debug_check_extent_io_range(tree, start, end); trace_btrfs_set_extent_bit(tree, start, end - start + 1, bits); + if (exclusive_bits) + ASSERT(failed_start); + else + ASSERT(failed_start == NULL); again: if (!prealloc && gfpflags_allow_blocking(mask)) { /* @@ -1179,15 +1182,6 @@ out: } -int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, - unsigned bits, u64 * failed_start, - struct extent_state **cached_state, gfp_t mask) -{ - return __set_extent_bit(tree, start, end, bits, 0, failed_start, - cached_state, mask, NULL); -} - - /** * convert_extent_bit - convert all bits in a given range from one bit to * another @@ -1207,7 +1201,7 @@ int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, * All allocations are done with GFP_NOFS. */ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, - unsigned bits, unsigned clear_bits, + u32 bits, u32 clear_bits, struct extent_state **cached_state) { struct extent_state *state; @@ -1408,7 +1402,7 @@ out: /* wrappers around set/clear extent bit */ int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, - unsigned bits, struct extent_changeset *changeset) + u32 bits, struct extent_changeset *changeset) { /* * We don't support EXTENT_LOCKED yet, as current changeset will @@ -1418,19 +1412,19 @@ int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, */ BUG_ON(bits & EXTENT_LOCKED); - return __set_extent_bit(tree, start, end, bits, 0, NULL, NULL, GFP_NOFS, - changeset); + return set_extent_bit(tree, start, end, bits, 0, NULL, NULL, GFP_NOFS, + changeset); } int set_extent_bits_nowait(struct extent_io_tree *tree, u64 start, u64 end, - unsigned bits) + u32 bits) { - return __set_extent_bit(tree, start, end, bits, 0, NULL, NULL, - GFP_NOWAIT, NULL); + return set_extent_bit(tree, start, end, bits, 0, NULL, NULL, + GFP_NOWAIT, NULL); } int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, - unsigned bits, int wake, int delete, + u32 bits, int wake, int delete, struct extent_state **cached) { return __clear_extent_bit(tree, start, end, bits, wake, delete, @@ -1438,7 +1432,7 @@ int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, } int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, - unsigned bits, struct extent_changeset *changeset) + u32 bits, struct extent_changeset *changeset) { /* * Don't support EXTENT_LOCKED case, same reason as @@ -1461,9 +1455,9 @@ int lock_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, u64 failed_start; while (1) { - err = __set_extent_bit(tree, start, end, EXTENT_LOCKED, - EXTENT_LOCKED, &failed_start, - cached_state, GFP_NOFS, NULL); + err = set_extent_bit(tree, start, end, EXTENT_LOCKED, + EXTENT_LOCKED, &failed_start, + cached_state, GFP_NOFS, NULL); if (err == -EEXIST) { wait_extent_bit(tree, failed_start, end, EXTENT_LOCKED); start = failed_start; @@ -1479,8 +1473,8 @@ int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end) int err; u64 failed_start; - err = __set_extent_bit(tree, start, end, EXTENT_LOCKED, EXTENT_LOCKED, - &failed_start, NULL, GFP_NOFS, NULL); + err = set_extent_bit(tree, start, end, EXTENT_LOCKED, EXTENT_LOCKED, + &failed_start, NULL, GFP_NOFS, NULL); if (err == -EEXIST) { if (failed_start > start) clear_extent_bit(tree, start, failed_start - 1, @@ -1526,8 +1520,7 @@ void extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end) * nothing was found after 'start' */ static struct extent_state * -find_first_extent_bit_state(struct extent_io_tree *tree, - u64 start, unsigned bits) +find_first_extent_bit_state(struct extent_io_tree *tree, u64 start, u32 bits) { struct rb_node *node; struct extent_state *state; @@ -1554,14 +1547,15 @@ out: } /* - * find the first offset in the io tree with 'bits' set. zero is - * returned if we find something, and *start_ret and *end_ret are - * set to reflect the state struct that was found. + * Find the first offset in the io tree with one or more @bits set. * - * If nothing was found, 1 is returned. If found something, return 0. + * Note: If there are multiple bits set in @bits, any of them will match. + * + * Return 0 if we find something, and update @start_ret and @end_ret. + * Return 1 if we found nothing. */ int find_first_extent_bit(struct extent_io_tree *tree, u64 start, - u64 *start_ret, u64 *end_ret, unsigned bits, + u64 *start_ret, u64 *end_ret, u32 bits, struct extent_state **cached_state) { struct extent_state *state; @@ -1597,12 +1591,13 @@ out: } /** - * find_contiguous_extent_bit: find a contiguous area of bits - * @tree - io tree to check - * @start - offset to start the search from - * @start_ret - the first offset we found with the bits set - * @end_ret - the final contiguous range of the bits that were set - * @bits - bits to look for + * Find a contiguous area of bits + * + * @tree: io tree to check + * @start: offset to start the search from + * @start_ret: the first offset we found with the bits set + * @end_ret: the final contiguous range of the bits that were set + * @bits: bits to look for * * set_extent_bit and clear_extent_bit can temporarily split contiguous ranges * to set bits appropriately, and then merge them again. During this time it @@ -1612,7 +1607,7 @@ out: * returned will be the full contiguous area with the bits set. */ int find_contiguous_extent_bit(struct extent_io_tree *tree, u64 start, - u64 *start_ret, u64 *end_ret, unsigned bits) + u64 *start_ret, u64 *end_ret, u32 bits) { struct extent_state *state; int ret = 1; @@ -1634,14 +1629,14 @@ int find_contiguous_extent_bit(struct extent_io_tree *tree, u64 start, } /** - * find_first_clear_extent_bit - find the first range that has @bits not set. - * This range could start before @start. + * Find the first range that has @bits not set. This range could start before + * @start. * - * @tree - the tree to search - * @start - the offset at/after which the found extent should start - * @start_ret - records the beginning of the range - * @end_ret - records the end of the range (inclusive) - * @bits - the set of bits which must be unset + * @tree: the tree to search + * @start: offset at/after which the found extent should start + * @start_ret: records the beginning of the range + * @end_ret: records the end of the range (inclusive) + * @bits: the set of bits which must be unset * * Since unallocated range is also considered one which doesn't have the bits * set it's possible that @end_ret contains -1, this happens in case the range @@ -1649,7 +1644,7 @@ int find_contiguous_extent_bit(struct extent_io_tree *tree, u64 start, * trim @end_ret to the appropriate size. */ void find_first_clear_extent_bit(struct extent_io_tree *tree, u64 start, - u64 *start_ret, u64 *end_ret, unsigned bits) + u64 *start_ret, u64 *end_ret, u32 bits) { struct extent_state *state; struct rb_node *node, *prev = NULL, *next; @@ -1946,7 +1941,7 @@ static int __process_pages_contig(struct address_space *mapping, unsigned long page_ops, pgoff_t *index_ret) { unsigned long nr_pages = end_index - start_index + 1; - unsigned long pages_locked = 0; + unsigned long pages_processed = 0; pgoff_t index = start_index; struct page *pages[16]; unsigned ret; @@ -1981,13 +1976,13 @@ static int __process_pages_contig(struct address_space *mapping, if (locked_page && pages[i] == locked_page) { put_page(pages[i]); - pages_locked++; + pages_processed++; continue; } - if (page_ops & PAGE_CLEAR_DIRTY) + if (page_ops & PAGE_START_WRITEBACK) { clear_page_dirty_for_io(pages[i]); - if (page_ops & PAGE_SET_WRITEBACK) set_page_writeback(pages[i]); + } if (page_ops & PAGE_SET_ERROR) SetPageError(pages[i]); if (page_ops & PAGE_END_WRITEBACK) @@ -2006,7 +2001,7 @@ static int __process_pages_contig(struct address_space *mapping, } } put_page(pages[i]); - pages_locked++; + pages_processed++; } nr_pages -= ret; index += ret; @@ -2014,14 +2009,13 @@ static int __process_pages_contig(struct address_space *mapping, } out: if (err && index_ret) - *index_ret = start_index + pages_locked - 1; + *index_ret = start_index + pages_processed - 1; return err; } void extent_clear_unlock_delalloc(struct btrfs_inode *inode, u64 start, u64 end, struct page *locked_page, - unsigned clear_bits, - unsigned long page_ops) + u32 clear_bits, unsigned long page_ops) { clear_extent_bit(&inode->io_tree, start, end, clear_bits, 1, 0, NULL); @@ -2037,7 +2031,7 @@ void extent_clear_unlock_delalloc(struct btrfs_inode *inode, u64 start, u64 end, */ u64 count_range_bits(struct extent_io_tree *tree, u64 *start, u64 search_end, u64 max_bytes, - unsigned bits, int contig) + u32 bits, int contig) { struct rb_node *node; struct extent_state *state; @@ -2157,7 +2151,7 @@ out: * range is found set. */ int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end, - unsigned bits, int filled, struct extent_state *cached) + u32 bits, int filled, struct extent_state *cached) { struct extent_state *state = NULL; struct rb_node *node; @@ -2266,6 +2260,9 @@ int repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start, ASSERT(!(fs_info->sb->s_flags & SB_RDONLY)); BUG_ON(!mirror_num); + if (btrfs_is_zoned(fs_info)) + return btrfs_repair_one_zone(fs_info, logical); + bio = btrfs_io_bio_alloc(1); bio->bi_iter.bi_size = 0; map_length = length; @@ -2642,7 +2639,7 @@ static bool btrfs_io_needs_validation(struct inode *inode, struct bio *bio) } blk_status_t btrfs_submit_read_repair(struct inode *inode, - struct bio *failed_bio, u64 phy_offset, + struct bio *failed_bio, u32 bio_offset, struct page *page, unsigned int pgoff, u64 start, u64 end, int failed_mirror, submit_bio_hook_t *submit_bio_hook) @@ -2652,7 +2649,7 @@ blk_status_t btrfs_submit_read_repair(struct inode *inode, struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree; struct extent_io_tree *failure_tree = &BTRFS_I(inode)->io_failure_tree; struct btrfs_io_bio *failed_io_bio = btrfs_io_bio(failed_bio); - const int icsum = phy_offset >> inode->i_sb->s_blocksize_bits; + const int icsum = bio_offset >> fs_info->sectorsize_bits; bool need_validation; struct bio *repair_bio; struct btrfs_io_bio *repair_io_bio; @@ -2685,7 +2682,7 @@ blk_status_t btrfs_submit_read_repair(struct inode *inode, repair_bio->bi_private = failed_bio->bi_private; if (failed_io_bio->csum) { - const u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); + const u32 csum_size = fs_info->csum_size; repair_io_bio->csum = repair_io_bio->csum_inline; memcpy(repair_io_bio->csum, @@ -2742,6 +2739,7 @@ static void end_bio_extent_writepage(struct bio *bio) u64 start; u64 end; struct bvec_iter_all iter_all; + bool first_bvec = true; ASSERT(!bio_flagged(bio, BIO_CLONED)); bio_for_each_segment_all(bvec, bio, iter_all) { @@ -2768,6 +2766,11 @@ static void end_bio_extent_writepage(struct bio *bio) start = page_offset(page); end = start + bvec->bv_offset + bvec->bv_len - 1; + if (first_bvec) { + btrfs_record_physical_zoned(inode, start, bio); + first_bvec = false; + } + end_extent_writepage(page, error, start, end); end_page_writeback(page); } @@ -2775,16 +2778,111 @@ static void end_bio_extent_writepage(struct bio *bio) bio_put(bio); } -static void -endio_readpage_release_extent(struct extent_io_tree *tree, u64 start, u64 len, - int uptodate) +/* + * 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; - u64 end = start + len - 1; + struct extent_io_tree *tree; - if (uptodate && tree->track_uptodate) - set_extent_uptodate(tree, start, end, &cached, GFP_ATOMIC); - unlock_extent_cached_atomic(tree, start, end, &cached); + /* 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. + */ + if (processed->uptodate && tree->track_uptodate) + set_extent_uptodate(tree, processed->start, processed->end, + &cached, GFP_ATOMIC); + unlock_extent_cached_atomic(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) +{ + ASSERT(PageLocked(page)); + if (fs_info->sectorsize == PAGE_SIZE) + return; + + ASSERT(PagePrivate(page)); + btrfs_subpage_start_reader(fs_info, page, page_offset(page), PAGE_SIZE); +} + +static void end_page_read(struct page *page, bool uptodate, u64 start, u32 len) +{ + struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb); + + ASSERT(page_offset(page) <= start && + start + len <= page_offset(page) + PAGE_SIZE); + + if (uptodate) { + btrfs_page_set_uptodate(fs_info, page, start, len); + } else { + btrfs_page_clear_uptodate(fs_info, page, start, len); + btrfs_page_set_error(fs_info, page, start, len); + } + + if (fs_info->sectorsize == PAGE_SIZE) + unlock_page(page); + else if (is_data_inode(page->mapping->host)) + /* + * For subpage data, unlock the page if we're the last reader. + * For subpage metadata, page lock is not utilized for read. + */ + btrfs_subpage_end_reader(fs_info, page, start, len); } /* @@ -2804,12 +2902,12 @@ static void end_bio_extent_readpage(struct bio *bio) int uptodate = !bio->bi_status; struct btrfs_io_bio *io_bio = btrfs_io_bio(bio); struct extent_io_tree *tree, *failure_tree; - u64 offset = 0; - u64 start; - u64 end; - u64 len; - u64 extent_start = 0; - u64 extent_len = 0; + struct processed_extent processed = { 0 }; + /* + * The offset to the beginning of a bio, since one bio can never be + * larger than UINT_MAX, u32 here is enough. + */ + u32 bio_offset = 0; int mirror; int ret; struct bvec_iter_all iter_all; @@ -2819,42 +2917,48 @@ static void end_bio_extent_readpage(struct bio *bio) struct page *page = bvec->bv_page; struct inode *inode = page->mapping->host; struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + const u32 sectorsize = fs_info->sectorsize; + u64 start; + u64 end; + u32 len; btrfs_debug(fs_info, "end_bio_extent_readpage: bi_sector=%llu, err=%d, mirror=%u", - (u64)bio->bi_iter.bi_sector, bio->bi_status, + bio->bi_iter.bi_sector, bio->bi_status, io_bio->mirror_num); tree = &BTRFS_I(inode)->io_tree; failure_tree = &BTRFS_I(inode)->io_failure_tree; - /* We always issue full-page reads, but if some block - * in a page fails to read, blk_update_request() will - * advance bv_offset and adjust bv_len to compensate. - * Print a warning for nonzero offsets, and an error - * if they don't add up to a full page. */ - if (bvec->bv_offset || bvec->bv_len != PAGE_SIZE) { - if (bvec->bv_offset + bvec->bv_len != PAGE_SIZE) - btrfs_err(fs_info, - "partial page read in btrfs with offset %u and length %u", - bvec->bv_offset, bvec->bv_len); - else - btrfs_info(fs_info, - "incomplete page read in btrfs with offset %u and length %u", - bvec->bv_offset, bvec->bv_len); - } - - start = page_offset(page); - end = start + bvec->bv_offset + bvec->bv_len - 1; + /* + * We always issue full-sector reads, but if some block in a + * page fails to read, blk_update_request() will advance + * bv_offset and adjust bv_len to compensate. Print a warning + * for unaligned offsets, and an error if they don't add up to + * a full sector. + */ + if (!IS_ALIGNED(bvec->bv_offset, sectorsize)) + btrfs_err(fs_info, + "partial page read in btrfs with offset %u and length %u", + bvec->bv_offset, bvec->bv_len); + else if (!IS_ALIGNED(bvec->bv_offset + bvec->bv_len, + sectorsize)) + btrfs_info(fs_info, + "incomplete page read with offset %u and length %u", + bvec->bv_offset, bvec->bv_len); + + start = page_offset(page) + bvec->bv_offset; + end = start + bvec->bv_len - 1; len = bvec->bv_len; mirror = io_bio->mirror_num; if (likely(uptodate)) { if (is_data_inode(inode)) - ret = btrfs_verify_data_csum(io_bio, offset, page, - start, end, mirror); + ret = btrfs_verify_data_csum(io_bio, + bio_offset, page, start, end, + mirror); else ret = btrfs_validate_metadata_buffer(io_bio, - offset, page, start, end, mirror); + page, start, end, mirror); if (ret) uptodate = 0; else @@ -2879,12 +2983,14 @@ static void end_bio_extent_readpage(struct bio *bio) * If it can't handle the error it will return -EIO and * we remain responsible for that page. */ - if (!btrfs_submit_read_repair(inode, bio, offset, page, + if (!btrfs_submit_read_repair(inode, bio, bio_offset, + page, start - page_offset(page), start, end, mirror, btrfs_submit_data_bio)) { uptodate = !bio->bi_status; - offset += len; + ASSERT(bio_offset + len > bio_offset); + bio_offset += len; continue; } } else { @@ -2908,40 +3014,17 @@ readpage_ok: off = offset_in_page(i_size); if (page->index == end_index && off) zero_user_segment(page, off, PAGE_SIZE); - SetPageUptodate(page); - } else { - ClearPageUptodate(page); - SetPageError(page); } - unlock_page(page); - offset += len; - - if (unlikely(!uptodate)) { - if (extent_len) { - endio_readpage_release_extent(tree, - extent_start, - extent_len, 1); - extent_start = 0; - extent_len = 0; - } - endio_readpage_release_extent(tree, start, - end - start + 1, 0); - } else if (!extent_len) { - extent_start = start; - extent_len = end + 1 - start; - } else if (extent_start + extent_len == start) { - extent_len += end + 1 - start; - } else { - endio_readpage_release_extent(tree, extent_start, - extent_len, uptodate); - extent_start = start; - extent_len = end + 1 - start; - } - } + ASSERT(bio_offset + len > bio_offset); + bio_offset += len; - if (extent_len) - endio_readpage_release_extent(tree, extent_start, extent_len, - uptodate); + /* Update page status and unlock */ + end_page_read(page, uptodate, start, len); + endio_readpage_release_extent(&processed, BTRFS_I(inode), + start, end, uptodate); + } + /* Release the last extent */ + endio_readpage_release_extent(&processed, NULL, 0, 0, false); btrfs_io_bio_free_csum(io_bio); bio_put(bio); } @@ -3011,14 +3094,67 @@ struct bio *btrfs_bio_clone_partial(struct bio *orig, int offset, int size) return bio; } +/** + * Attempt to add a page to bio + * + * @bio: destination bio + * @page: page to add to the bio + * @disk_bytenr: offset of the new bio or to check whether we are adding + * a contiguous page to the previous one + * @pg_offset: starting offset in the page + * @size: portion of page that we want to write + * @prev_bio_flags: flags of previous bio to see if we can merge the current one + * @bio_flags: flags of the current bio to see if we can merge them + * @return: true if page was added, false otherwise + * + * Attempt to add a page to bio considering stripe alignment etc. + * + * Return true if successfully page added. Otherwise, return false. + */ +static bool btrfs_bio_add_page(struct bio *bio, struct page *page, + u64 disk_bytenr, unsigned int size, + unsigned int pg_offset, + unsigned long prev_bio_flags, + unsigned long bio_flags) +{ + const sector_t sector = disk_bytenr >> SECTOR_SHIFT; + bool contig; + int ret; + + if (prev_bio_flags != bio_flags) + return false; + + if (prev_bio_flags & EXTENT_BIO_COMPRESSED) + contig = bio->bi_iter.bi_sector == sector; + else + contig = bio_end_sector(bio) == sector; + if (!contig) + return false; + + if (btrfs_bio_fits_in_stripe(page, size, bio, bio_flags)) + return false; + + if (bio_op(bio) == REQ_OP_ZONE_APPEND) { + struct page *first_page = bio_first_bvec_all(bio)->bv_page; + + if (!btrfs_bio_fits_in_ordered_extent(first_page, bio, size)) + return false; + ret = bio_add_zone_append_page(bio, page, size, pg_offset); + } else { + ret = bio_add_page(bio, page, size, pg_offset); + } + + return ret == size; +} + /* * @opf: bio REQ_OP_* and REQ_* flags as one value * @wbc: optional writeback control for io accounting * @page: page to add to the bio + * @disk_bytenr: logical bytenr where the write will be + * @size: portion of page that we want to write to * @pg_offset: offset of the new bio or to check whether we are adding * a contiguous page to the previous one - * @size: portion of page that we want to write - * @offset: starting offset in the page * @bio_ret: must be valid pointer, newly allocated bio will be stored there * @end_io_func: end_io callback for new bio * @mirror_num: desired mirror to read/write @@ -3027,7 +3163,7 @@ struct bio *btrfs_bio_clone_partial(struct bio *orig, int offset, int size) */ static int submit_extent_page(unsigned int opf, struct writeback_control *wbc, - struct page *page, u64 offset, + struct page *page, u64 disk_bytenr, size_t size, unsigned long pg_offset, struct bio **bio_ret, bio_end_io_t end_io_func, @@ -3038,28 +3174,18 @@ static int submit_extent_page(unsigned int opf, { int ret = 0; struct bio *bio; - size_t page_size = min_t(size_t, size, PAGE_SIZE); - sector_t sector = offset >> 9; - struct extent_io_tree *tree = &BTRFS_I(page->mapping->host)->io_tree; + size_t io_size = min_t(size_t, size, PAGE_SIZE); + struct btrfs_inode *inode = BTRFS_I(page->mapping->host); + struct extent_io_tree *tree = &inode->io_tree; + struct btrfs_fs_info *fs_info = inode->root->fs_info; ASSERT(bio_ret); if (*bio_ret) { - bool contig; - bool can_merge = true; - bio = *bio_ret; - if (prev_bio_flags & EXTENT_BIO_COMPRESSED) - contig = bio->bi_iter.bi_sector == sector; - else - contig = bio_end_sector(bio) == sector; - - if (btrfs_bio_fits_in_stripe(page, page_size, bio, bio_flags)) - can_merge = false; - - if (prev_bio_flags != bio_flags || !contig || !can_merge || - force_bio_submit || - bio_add_page(bio, page, page_size, pg_offset) < page_size) { + if (force_bio_submit || + !btrfs_bio_add_page(bio, page, disk_bytenr, io_size, + pg_offset, prev_bio_flags, bio_flags)) { ret = submit_one_bio(bio, mirror_num, prev_bio_flags); if (ret < 0) { *bio_ret = NULL; @@ -3068,13 +3194,13 @@ static int submit_extent_page(unsigned int opf, bio = NULL; } else { if (wbc) - wbc_account_cgroup_owner(wbc, page, page_size); + wbc_account_cgroup_owner(wbc, page, io_size); return 0; } } - bio = btrfs_bio_alloc(offset); - bio_add_page(bio, page, page_size, pg_offset); + bio = btrfs_bio_alloc(disk_bytenr); + bio_add_page(bio, page, io_size, pg_offset); bio->bi_end_io = end_io_func; bio->bi_private = tree; bio->bi_write_hint = page->mapping->host->i_write_hint; @@ -3082,10 +3208,25 @@ static int submit_extent_page(unsigned int opf, if (wbc) { struct block_device *bdev; - bdev = BTRFS_I(page->mapping->host)->root->fs_info->fs_devices->latest_bdev; + bdev = fs_info->fs_devices->latest_bdev; bio_set_dev(bio, bdev); wbc_init_bio(wbc, bio); - wbc_account_cgroup_owner(wbc, page, page_size); + wbc_account_cgroup_owner(wbc, page, io_size); + } + if (btrfs_is_zoned(fs_info) && bio_op(bio) == REQ_OP_ZONE_APPEND) { + struct extent_map *em; + struct map_lookup *map; + + em = btrfs_get_chunk_map(fs_info, disk_bytenr, io_size); + if (IS_ERR(em)) + return PTR_ERR(em); + + map = em->map_lookup; + /* We only support single profile for now */ + ASSERT(map->num_stripes == 1); + btrfs_io_bio(bio)->device = map->stripes[0].dev; + + free_extent_map(em); } *bio_ret = bio; @@ -3093,19 +3234,78 @@ static int submit_extent_page(unsigned int opf, return ret; } -static void attach_extent_buffer_page(struct extent_buffer *eb, - struct page *page) +static int attach_extent_buffer_page(struct extent_buffer *eb, + struct page *page, + struct btrfs_subpage *prealloc) { - if (!PagePrivate(page)) - attach_page_private(page, eb); + struct btrfs_fs_info *fs_info = eb->fs_info; + int ret = 0; + + /* + * If the page is mapped to btree inode, we should hold the private + * lock to prevent race. + * For cloned or dummy extent buffers, their pages are not mapped and + * will not race with any other ebs. + */ + if (page->mapping) + lockdep_assert_held(&page->mapping->private_lock); + + if (fs_info->sectorsize == PAGE_SIZE) { + if (!PagePrivate(page)) + attach_page_private(page, eb); + else + WARN_ON(page->private != (unsigned long)eb); + return 0; + } + + /* Already mapped, just free prealloc */ + if (PagePrivate(page)) { + btrfs_free_subpage(prealloc); + return 0; + } + + if (prealloc) + /* Has preallocated memory for subpage */ + attach_page_private(page, prealloc); else - WARN_ON(page->private != (unsigned long)eb); + /* Do new allocation to attach subpage */ + ret = btrfs_attach_subpage(fs_info, page, + BTRFS_SUBPAGE_METADATA); + return ret; +} + +int set_page_extent_mapped(struct page *page) +{ + struct btrfs_fs_info *fs_info; + + ASSERT(page->mapping); + + if (PagePrivate(page)) + return 0; + + fs_info = btrfs_sb(page->mapping->host->i_sb); + + if (fs_info->sectorsize < PAGE_SIZE) + return btrfs_attach_subpage(fs_info, page, BTRFS_SUBPAGE_DATA); + + attach_page_private(page, (void *)EXTENT_PAGE_PRIVATE); + return 0; } -void set_page_extent_mapped(struct page *page) +void clear_page_extent_mapped(struct page *page) { + struct btrfs_fs_info *fs_info; + + ASSERT(page->mapping); + if (!PagePrivate(page)) - attach_page_private(page, (void *)EXTENT_PAGE_PRIVATE); + return; + + fs_info = btrfs_sb(page->mapping->host->i_sb); + if (fs_info->sectorsize < PAGE_SIZE) + return btrfs_detach_subpage(fs_info, page); + + detach_page_private(page); } static struct extent_map * @@ -3146,6 +3346,7 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, unsigned int read_flags, u64 *prev_em_start) { struct inode *inode = page->mapping->host; + struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); u64 start = page_offset(page); const u64 end = start + PAGE_SIZE - 1; u64 cur = start; @@ -3158,17 +3359,23 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, int nr = 0; size_t pg_offset = 0; size_t iosize; - size_t disk_io_size; size_t blocksize = inode->i_sb->s_blocksize; unsigned long this_bio_flag = 0; struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree; - set_page_extent_mapped(page); + ret = set_page_extent_mapped(page); + if (ret < 0) { + unlock_extent(tree, start, end); + btrfs_page_set_error(fs_info, page, start, PAGE_SIZE); + unlock_page(page); + goto out; + } if (!PageUptodate(page)) { if (cleancache_get_page(page) == 0) { BUG_ON(blocksize != PAGE_SIZE); unlock_extent(tree, start, end); + unlock_page(page); goto out; } } @@ -3185,9 +3392,10 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, kunmap_atomic(userpage); } } + begin_page_read(fs_info, page); while (cur <= end) { bool force_bio_submit = false; - u64 offset; + u64 disk_bytenr; if (cur >= last_byte) { char *userpage; @@ -3202,13 +3410,14 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, &cached, GFP_NOFS); unlock_extent_cached(tree, cur, cur + iosize - 1, &cached); + end_page_read(page, true, cur, iosize); break; } em = __get_extent_map(inode, page, pg_offset, cur, end - cur + 1, em_cached); if (IS_ERR_OR_NULL(em)) { - SetPageError(page); unlock_extent(tree, cur, end); + end_page_read(page, false, cur, end + 1 - cur); break; } extent_offset = cur - em->start; @@ -3224,13 +3433,10 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, iosize = min(extent_map_end(em) - cur, end - cur + 1); cur_end = min(extent_map_end(em) - 1, end); iosize = ALIGN(iosize, blocksize); - if (this_bio_flag & EXTENT_BIO_COMPRESSED) { - disk_io_size = em->block_len; - offset = em->block_start; - } else { - offset = em->block_start + extent_offset; - disk_io_size = iosize; - } + if (this_bio_flag & EXTENT_BIO_COMPRESSED) + disk_bytenr = em->block_start; + else + disk_bytenr = em->block_start + extent_offset; block_start = em->block_start; if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) block_start = EXTENT_MAP_HOLE; @@ -3294,6 +3500,7 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, &cached, GFP_NOFS); unlock_extent_cached(tree, cur, cur + iosize - 1, &cached); + end_page_read(page, true, cur, iosize); cur = cur + iosize; pg_offset += iosize; continue; @@ -3303,6 +3510,7 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, EXTENT_UPTODATE, 1, NULL)) { check_page_uptodate(tree, page); unlock_extent(tree, cur, cur + iosize - 1); + end_page_read(page, true, cur, iosize); cur = cur + iosize; pg_offset += iosize; continue; @@ -3311,15 +3519,15 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, * to date. Error out */ if (block_start == EXTENT_MAP_INLINE) { - SetPageError(page); unlock_extent(tree, cur, cur + iosize - 1); + end_page_read(page, false, cur, iosize); cur = cur + iosize; pg_offset += iosize; continue; } ret = submit_extent_page(REQ_OP_READ | read_flags, NULL, - page, offset, disk_io_size, + page, disk_bytenr, iosize, pg_offset, bio, end_bio_extent_readpage, 0, *bio_flags, @@ -3329,19 +3537,14 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, nr++; *bio_flags = this_bio_flag; } else { - SetPageError(page); unlock_extent(tree, cur, cur + iosize - 1); + end_page_read(page, false, cur, iosize); goto out; } cur = cur + iosize; pg_offset += iosize; } out: - if (!nr) { - if (!PageError(page)) - SetPageUptodate(page); - unlock_page(page); - } return ret; } @@ -3461,23 +3664,21 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, unsigned long nr_written, int *nr_ret) { + struct btrfs_fs_info *fs_info = inode->root->fs_info; struct extent_io_tree *tree = &inode->io_tree; u64 start = page_offset(page); - u64 page_end = start + PAGE_SIZE - 1; - u64 end; + u64 end = start + PAGE_SIZE - 1; u64 cur = start; u64 extent_offset; u64 block_start; - u64 iosize; struct extent_map *em; - size_t pg_offset = 0; - size_t blocksize; int ret = 0; int nr = 0; + u32 opf = REQ_OP_WRITE; const unsigned int write_flags = wbc_to_write_flags(wbc); bool compressed; - ret = btrfs_writepage_cow_fixup(page, start, page_end); + ret = btrfs_writepage_cow_fixup(page, start, end); if (ret) { /* Fixup worker will requeue */ redirty_page_for_writepage(wbc, page); @@ -3492,16 +3693,13 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, */ update_nr_written(wbc, nr_written + 1); - end = page_end; - blocksize = inode->vfs_inode.i_sb->s_blocksize; - while (cur <= end) { + u64 disk_bytenr; u64 em_end; - u64 offset; + u32 iosize; if (cur >= i_size) { - btrfs_writepage_endio_finish_ordered(page, cur, - page_end, 1); + btrfs_writepage_endio_finish_ordered(page, cur, end, 1); break; } em = btrfs_get_extent(inode, NULL, 0, cur, end - cur + 1); @@ -3513,13 +3711,20 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, extent_offset = cur - em->start; em_end = extent_map_end(em); - BUG_ON(em_end <= cur); - BUG_ON(end < cur); - iosize = min(em_end - cur, end - cur + 1); - iosize = ALIGN(iosize, blocksize); - offset = em->block_start + extent_offset; + 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 = em->block_start; compressed = test_bit(EXTENT_FLAG_COMPRESSED, &em->flags); + disk_bytenr = em->block_start + extent_offset; + + /* Note that em_end from extent_map_end() is exclusive */ + iosize = min(em_end, end + 1) - cur; + + if (btrfs_use_zone_append(inode, em)) + opf = REQ_OP_ZONE_APPEND; + free_extent_map(em); em = NULL; @@ -3535,7 +3740,6 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, btrfs_writepage_endio_finish_ordered(page, cur, cur + iosize - 1, 1); cur += iosize; - pg_offset += iosize; continue; } @@ -3546,9 +3750,9 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, page->index, cur, end); } - ret = submit_extent_page(REQ_OP_WRITE | write_flags, wbc, - page, offset, iosize, pg_offset, - &epd->bio, + ret = submit_extent_page(opf | write_flags, wbc, page, + disk_bytenr, iosize, + cur - page_offset(page), &epd->bio, end_bio_extent_writepage, 0, 0, 0, false); if (ret) { @@ -3557,8 +3761,7 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, end_page_writeback(page); } - cur = cur + iosize; - pg_offset += iosize; + cur += iosize; nr++; } *nr_ret = nr; @@ -3611,7 +3814,11 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc, flush_dcache_page(page); } - set_page_extent_mapped(page); + ret = set_page_extent_mapped(page); + if (ret < 0) { + SetPageError(page); + goto done; + } if (!epd->extent_locked) { ret = writepage_delalloc(BTRFS_I(inode), page, wbc, start, @@ -3656,11 +3863,14 @@ static void end_extent_buffer_writeback(struct extent_buffer *eb) } /* - * Lock eb pages and flush the bio if we can't the locks + * Lock extent buffer status and pages for writeback. + * + * May try to flush write bio if we can't get the lock. * - * Return 0 if nothing went wrong - * Return >0 is same as 0, except bio is not submitted - * Return <0 if something went wrong, no page is locked + * Return 0 if the extent buffer doesn't need to be submitted. + * (E.g. the extent buffer is not dirty) + * Return >0 is the extent buffer is submitted to bio. + * Return <0 if something went wrong, no page is locked. */ static noinline_for_stack int lock_extent_buffer_for_io(struct extent_buffer *eb, struct extent_page_data *epd) @@ -3868,7 +4078,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb, struct writeback_control *wbc, struct extent_page_data *epd) { - u64 offset = eb->start; + u64 disk_bytenr = eb->start; u32 nritems; int i, num_pages; unsigned long start, end; @@ -3901,7 +4111,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb, clear_page_dirty_for_io(p); set_page_writeback(p); ret = submit_extent_page(REQ_OP_WRITE | write_flags, wbc, - p, offset, PAGE_SIZE, 0, + p, disk_bytenr, PAGE_SIZE, 0, &epd->bio, end_bio_extent_buffer_writepage, 0, 0, 0, false); @@ -3914,7 +4124,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb, ret = -EIO; break; } - offset += PAGE_SIZE; + disk_bytenr += PAGE_SIZE; update_nr_written(wbc, 1); unlock_page(p); } @@ -3930,10 +4140,100 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb, return ret; } +/* + * Submit all page(s) of one extent buffer. + * + * @page: the page of one extent buffer + * @eb_context: to determine if we need to submit this page, if current page + * belongs to this eb, we don't need to submit + * + * The caller should pass each page in their bytenr order, and here we use + * @eb_context to determine if we have submitted pages of one extent buffer. + * + * If we have, we just skip until we hit a new page that doesn't belong to + * current @eb_context. + * + * If not, we submit all the page(s) of the extent buffer. + * + * Return >0 if we have submitted the extent buffer successfully. + * Return 0 if we don't need to submit the page, as it's already submitted by + * previous call. + * Return <0 for fatal error. + */ +static int submit_eb_page(struct page *page, struct writeback_control *wbc, + struct extent_page_data *epd, + struct extent_buffer **eb_context) +{ + struct address_space *mapping = page->mapping; + struct btrfs_block_group *cache = NULL; + struct extent_buffer *eb; + int ret; + + if (!PagePrivate(page)) + return 0; + + spin_lock(&mapping->private_lock); + if (!PagePrivate(page)) { + spin_unlock(&mapping->private_lock); + return 0; + } + + eb = (struct extent_buffer *)page->private; + + /* + * Shouldn't happen and normally this would be a BUG_ON but no point + * crashing the machine for something we can survive anyway. + */ + if (WARN_ON(!eb)) { + spin_unlock(&mapping->private_lock); + return 0; + } + + if (eb == *eb_context) { + spin_unlock(&mapping->private_lock); + return 0; + } + ret = atomic_inc_not_zero(&eb->refs); + spin_unlock(&mapping->private_lock); + if (!ret) + return 0; + + if (!btrfs_check_meta_write_pointer(eb->fs_info, eb, &cache)) { + /* + * If for_sync, this hole will be filled with + * trasnsaction commit. + */ + if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync) + ret = -EAGAIN; + else + ret = 0; + free_extent_buffer(eb); + return ret; + } + + *eb_context = eb; + + ret = lock_extent_buffer_for_io(eb, epd); + if (ret <= 0) { + btrfs_revert_meta_write_pointer(cache, eb); + if (cache) + btrfs_put_block_group(cache); + free_extent_buffer(eb); + return ret; + } + if (cache) + btrfs_put_block_group(cache); + ret = write_one_eb(eb, wbc, epd); + free_extent_buffer(eb); + if (ret < 0) + return ret; + return 1; +} + int btree_write_cache_pages(struct address_space *mapping, struct writeback_control *wbc) { - struct extent_buffer *eb, *prev_eb = NULL; + struct extent_buffer *eb_context = NULL; struct extent_page_data epd = { .bio = NULL, .extent_locked = 0, @@ -3968,6 +4268,7 @@ int btree_write_cache_pages(struct address_space *mapping, tag = PAGECACHE_TAG_TOWRITE; else tag = PAGECACHE_TAG_DIRTY; + btrfs_zoned_meta_io_lock(fs_info); retry: if (wbc->sync_mode == WB_SYNC_ALL) tag_pages_for_writeback(mapping, index, end); @@ -3979,55 +4280,13 @@ retry: for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; - if (!PagePrivate(page)) + ret = submit_eb_page(page, wbc, &epd, &eb_context); + if (ret == 0) continue; - - spin_lock(&mapping->private_lock); - if (!PagePrivate(page)) { - spin_unlock(&mapping->private_lock); - continue; - } - - eb = (struct extent_buffer *)page->private; - - /* - * Shouldn't happen and normally this would be a BUG_ON - * but no sense in crashing the users box for something - * we can survive anyway. - */ - if (WARN_ON(!eb)) { - spin_unlock(&mapping->private_lock); - continue; - } - - if (eb == prev_eb) { - spin_unlock(&mapping->private_lock); - continue; - } - - ret = atomic_inc_not_zero(&eb->refs); - spin_unlock(&mapping->private_lock); - if (!ret) - continue; - - prev_eb = eb; - ret = lock_extent_buffer_for_io(eb, &epd); - if (!ret) { - free_extent_buffer(eb); - continue; - } else if (ret < 0) { - done = 1; - free_extent_buffer(eb); - break; - } - - ret = write_one_eb(eb, wbc, &epd); - if (ret) { + if (ret < 0) { done = 1; - free_extent_buffer(eb); break; } - free_extent_buffer(eb); /* * the filesystem may choose to bump up nr_to_write. @@ -4048,10 +4307,9 @@ retry: index = 0; goto retry; } - ASSERT(ret <= 0); if (ret < 0) { end_write_bio(&epd, ret); - return ret; + goto out; } /* * If something went wrong, don't allow any metadata write bio to be @@ -4086,14 +4344,17 @@ retry: ret = -EROFS; end_write_bio(&epd, ret); } +out: + btrfs_zoned_meta_io_unlock(fs_info); return ret; } /** - * write_cache_pages - walk the list of dirty pages of the given address space and write all of them. + * Walk the list of dirty pages of the given address space and write all of them. + * * @mapping: address space structure to write - * @wbc: subtract the number of written pages from *@wbc->nr_to_write - * @data: data passed to __extent_writepage function + * @wbc: subtract the number of written pages from *@wbc->nr_to_write + * @epd: holds context for the write, namely the bio * * If a page is already under I/O, write_cache_pages() skips it, even * if it's dirty. This is desirable behaviour for memory-cleaning writeback, @@ -4382,14 +4643,22 @@ int extent_invalidatepage(struct extent_io_tree *tree, u64 end = start + PAGE_SIZE - 1; size_t blocksize = page->mapping->host->i_sb->s_blocksize; + /* This function is only called for the btree inode */ + ASSERT(tree->owner == IO_TREE_BTREE_INODE_IO); + start += ALIGN(offset, blocksize); if (start > end) return 0; lock_extent_bits(tree, start, end, &cached_state); wait_on_page_writeback(page); - clear_extent_bit(tree, start, end, EXTENT_LOCKED | EXTENT_DELALLOC | - EXTENT_DO_ACCOUNTING, 1, 1, &cached_state); + + /* + * Currently for btree io tree, only EXTENT_LOCKED is utilized, + * so here we only need to unlock the extent range to free any + * existing extent state. + */ + unlock_extent_cached(tree, start, end, &cached_state); return 0; } @@ -4409,12 +4678,14 @@ static int try_release_extent_state(struct extent_io_tree *tree, ret = 0; } else { /* - * at this point we can safely clear everything except the - * locked bit and the nodatasum bit + * At this point we can safely clear everything except the + * locked bit, the nodatasum bit and the delalloc new bit. + * The delalloc new bit will be cleared by ordered extent + * completion. */ ret = __clear_extent_bit(tree, start, end, - ~(EXTENT_LOCKED | EXTENT_NODATASUM), - 0, 0, NULL, mask, NULL); + ~(EXTENT_LOCKED | EXTENT_NODATASUM | EXTENT_DELALLOC_NEW), + 0, 0, NULL, mask, NULL); /* if clear_extent_bit failed for enomem reasons, * we can't allow the release to continue. @@ -4691,7 +4962,6 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, path = btrfs_alloc_path(); if (!path) return -ENOMEM; - path->leave_spinning = 1; roots = ulist_alloc(GFP_KERNEL); tmp_ulist = ulist_alloc(GFP_KERNEL); @@ -4883,25 +5153,39 @@ int extent_buffer_under_io(const struct extent_buffer *eb) test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)); } -/* - * Release all pages attached to the extent buffer. - */ -static void btrfs_release_extent_buffer_pages(struct extent_buffer *eb) +static bool page_range_has_eb(struct btrfs_fs_info *fs_info, struct page *page) { - int i; - int num_pages; - int mapped = !test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags); + struct btrfs_subpage *subpage; - BUG_ON(extent_buffer_under_io(eb)); + lockdep_assert_held(&page->mapping->private_lock); - num_pages = num_extent_pages(eb); - for (i = 0; i < num_pages; i++) { - struct page *page = eb->pages[i]; + if (PagePrivate(page)) { + subpage = (struct btrfs_subpage *)page->private; + if (atomic_read(&subpage->eb_refs)) + return true; + } + return false; +} - if (!page) - continue; +static void detach_extent_buffer_page(struct extent_buffer *eb, struct page *page) +{ + struct btrfs_fs_info *fs_info = eb->fs_info; + const bool mapped = !test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags); + + /* + * For mapped eb, we're going to change the page private, which should + * be done under the private_lock. + */ + if (mapped) + spin_lock(&page->mapping->private_lock); + + if (!PagePrivate(page)) { if (mapped) - spin_lock(&page->mapping->private_lock); + spin_unlock(&page->mapping->private_lock); + return; + } + + if (fs_info->sectorsize == PAGE_SIZE) { /* * We do this since we'll remove the pages after we've * removed the eb from the radix tree, so we could race @@ -4920,9 +5204,49 @@ static void btrfs_release_extent_buffer_pages(struct extent_buffer *eb) */ detach_page_private(page); } - if (mapped) spin_unlock(&page->mapping->private_lock); + return; + } + + /* + * For subpage, we can have dummy eb with page private. In this case, + * we can directly detach the private as such page is only attached to + * one dummy eb, no sharing. + */ + if (!mapped) { + btrfs_detach_subpage(fs_info, page); + return; + } + + btrfs_page_dec_eb_refs(fs_info, page); + + /* + * We can only detach the page private if there are no other ebs in the + * page range. + */ + if (!page_range_has_eb(fs_info, page)) + btrfs_detach_subpage(fs_info, page); + + spin_unlock(&page->mapping->private_lock); +} + +/* Release all pages attached to the extent buffer */ +static void btrfs_release_extent_buffer_pages(struct extent_buffer *eb) +{ + int i; + int num_pages; + + ASSERT(!extent_buffer_under_io(eb)); + + num_pages = num_extent_pages(eb); + for (i = 0; i < num_pages; i++) { + struct page *page = eb->pages[i]; + + if (!page) + continue; + + detach_extent_buffer_page(eb, page); /* One for when we allocated the page */ put_page(page); @@ -4950,33 +5274,17 @@ __alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start, eb->len = len; eb->fs_info = fs_info; eb->bflags = 0; - rwlock_init(&eb->lock); - atomic_set(&eb->blocking_readers, 0); - eb->blocking_writers = 0; - eb->lock_recursed = false; - init_waitqueue_head(&eb->write_lock_wq); - init_waitqueue_head(&eb->read_lock_wq); + init_rwsem(&eb->lock); btrfs_leak_debug_add(&fs_info->eb_leak_lock, &eb->leak_list, &fs_info->allocated_ebs); + INIT_LIST_HEAD(&eb->release_list); spin_lock_init(&eb->refs_lock); atomic_set(&eb->refs, 1); atomic_set(&eb->io_pages, 0); - /* - * Sanity checks, currently the maximum is 64k covered by 16x 4k pages - */ - BUILD_BUG_ON(BTRFS_MAX_METADATA_BLOCKSIZE - > MAX_INLINE_EXTENT_BUFFER_SIZE); - BUG_ON(len > MAX_INLINE_EXTENT_BUFFER_SIZE); - -#ifdef CONFIG_BTRFS_DEBUG - eb->spinning_writers = 0; - atomic_set(&eb->spinning_readers, 0); - atomic_set(&eb->read_locks, 0); - eb->write_locks = 0; -#endif + ASSERT(len <= BTRFS_MAX_METADATA_BLOCKSIZE); return eb; } @@ -4992,21 +5300,32 @@ struct extent_buffer *btrfs_clone_extent_buffer(const struct extent_buffer *src) if (new == NULL) return NULL; + /* + * Set UNMAPPED before calling btrfs_release_extent_buffer(), as + * btrfs_release_extent_buffer() have different behavior for + * UNMAPPED subpage extent buffer. + */ + set_bit(EXTENT_BUFFER_UNMAPPED, &new->bflags); + for (i = 0; i < num_pages; i++) { + int ret; + p = alloc_page(GFP_NOFS); if (!p) { btrfs_release_extent_buffer(new); return NULL; } - attach_extent_buffer_page(new, p); + ret = attach_extent_buffer_page(new, p, NULL); + if (ret < 0) { + put_page(p); + btrfs_release_extent_buffer(new); + return NULL; + } WARN_ON(PageDirty(p)); - SetPageUptodate(p); new->pages[i] = p; copy_page(page_address(p), page_address(src->pages[i])); } - - set_bit(EXTENT_BUFFER_UPTODATE, &new->bflags); - set_bit(EXTENT_BUFFER_UNMAPPED, &new->bflags); + set_extent_buffer_uptodate(new); return new; } @@ -5024,9 +5343,14 @@ struct extent_buffer *__alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info, num_pages = num_extent_pages(eb); for (i = 0; i < num_pages; i++) { + int ret; + eb->pages[i] = alloc_page(GFP_NOFS); if (!eb->pages[i]) goto err; + ret = attach_extent_buffer_page(eb, eb->pages[i], NULL); + if (ret < 0) + goto err; } set_extent_buffer_uptodate(eb); btrfs_set_header_nritems(eb, 0); @@ -5034,8 +5358,10 @@ struct extent_buffer *__alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info, return eb; err: - for (; i > 0; i--) + for (; i > 0; i--) { + detach_extent_buffer_page(eb, eb->pages[i - 1]); __free_page(eb->pages[i - 1]); + } __free_extent_buffer(eb); return NULL; } @@ -5105,7 +5431,7 @@ struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info, rcu_read_lock(); eb = radix_tree_lookup(&fs_info->buffer_radix, - start >> PAGE_SHIFT); + start >> fs_info->sectorsize_bits); if (eb && atomic_inc_not_zero(&eb->refs)) { rcu_read_unlock(); /* @@ -5157,7 +5483,7 @@ again: } spin_lock(&fs_info->buffer_lock); ret = radix_tree_insert(&fs_info->buffer_radix, - start >> PAGE_SHIFT, eb); + start >> fs_info->sectorsize_bits, eb); spin_unlock(&fs_info->buffer_lock); radix_tree_preload_end(); if (ret == -EEXIST) { @@ -5177,8 +5503,40 @@ free_eb: } #endif +static struct extent_buffer *grab_extent_buffer( + struct btrfs_fs_info *fs_info, struct page *page) +{ + struct extent_buffer *exists; + + /* + * For subpage case, we completely rely on radix tree to ensure we + * don't try to insert two ebs for the same bytenr. So here we always + * return NULL and just continue. + */ + if (fs_info->sectorsize < PAGE_SIZE) + return NULL; + + /* Page not yet attached to an extent buffer */ + if (!PagePrivate(page)) + return NULL; + + /* + * We could have already allocated an eb for this page and attached one + * so lets see if we can get a ref on the existing eb, and if we can we + * know it's good and we can just return that one, else we know we can + * just overwrite page->private. + */ + exists = (struct extent_buffer *)page->private; + if (atomic_inc_not_zero(&exists->refs)) + return exists; + + WARN_ON(PageDirty(page)); + detach_page_private(page); + return NULL; +} + struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, - u64 start) + u64 start, u64 owner_root, int level) { unsigned long len = fs_info->nodesize; int num_pages; @@ -5196,6 +5554,14 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, return ERR_PTR(-EINVAL); } + if (fs_info->sectorsize < PAGE_SIZE && + offset_in_page(start) + len > PAGE_SIZE) { + btrfs_err(fs_info, + "tree block crosses page boundary, start %llu nodesize %lu", + start, len); + return ERR_PTR(-EINVAL); + } + eb = find_extent_buffer(fs_info, start); if (eb) return eb; @@ -5203,44 +5569,62 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, eb = __alloc_extent_buffer(fs_info, start, len); if (!eb) return ERR_PTR(-ENOMEM); + btrfs_set_buffer_lockdep_class(owner_root, eb, level); num_pages = num_extent_pages(eb); for (i = 0; i < num_pages; i++, index++) { + struct btrfs_subpage *prealloc = NULL; + p = find_or_create_page(mapping, index, GFP_NOFS|__GFP_NOFAIL); if (!p) { exists = ERR_PTR(-ENOMEM); goto free_eb; } - spin_lock(&mapping->private_lock); - if (PagePrivate(p)) { - /* - * We could have already allocated an eb for this page - * and attached one so lets see if we can get a ref on - * the existing eb, and if we can we know it's good and - * we can just return that one, else we know we can just - * overwrite page->private. - */ - exists = (struct extent_buffer *)p->private; - if (atomic_inc_not_zero(&exists->refs)) { - spin_unlock(&mapping->private_lock); - unlock_page(p); - put_page(p); - mark_extent_buffer_accessed(exists, p); - goto free_eb; - } - exists = NULL; + /* + * Preallocate page->private for subpage case, so that we won't + * allocate memory with private_lock hold. The memory will be + * freed by attach_extent_buffer_page() or freed manually if + * we exit earlier. + * + * Although we have ensured one subpage eb can only have one + * page, but it may change in the future for 16K page size + * support, so we still preallocate the memory in the loop. + */ + ret = btrfs_alloc_subpage(fs_info, &prealloc, + BTRFS_SUBPAGE_METADATA); + if (ret < 0) { + unlock_page(p); + put_page(p); + exists = ERR_PTR(ret); + goto free_eb; + } - /* - * Do this so attach doesn't complain and we need to - * drop the ref the old guy had. - */ - ClearPagePrivate(p); - WARN_ON(PageDirty(p)); + spin_lock(&mapping->private_lock); + exists = grab_extent_buffer(fs_info, p); + if (exists) { + spin_unlock(&mapping->private_lock); + unlock_page(p); put_page(p); + mark_extent_buffer_accessed(exists, p); + btrfs_free_subpage(prealloc); + goto free_eb; } - attach_extent_buffer_page(eb, p); + /* Should not fail, as we have preallocated the memory */ + ret = attach_extent_buffer_page(eb, p, prealloc); + ASSERT(!ret); + /* + * To inform we have extra eb under allocation, so that + * detach_extent_buffer_page() won't release the page private + * when the eb hasn't yet been inserted into radix tree. + * + * The ref will be decreased when the eb released the page, in + * detach_extent_buffer_page(). + * Thus needs no special handling in error path. + */ + btrfs_page_inc_eb_refs(fs_info, p); spin_unlock(&mapping->private_lock); + WARN_ON(PageDirty(p)); eb->pages[i] = p; if (!PageUptodate(p)) @@ -5265,7 +5649,7 @@ again: spin_lock(&fs_info->buffer_lock); ret = radix_tree_insert(&fs_info->buffer_radix, - start >> PAGE_SHIFT, eb); + start >> fs_info->sectorsize_bits, eb); spin_unlock(&fs_info->buffer_lock); radix_tree_preload_end(); if (ret == -EEXIST) { @@ -5321,7 +5705,7 @@ static int release_extent_buffer(struct extent_buffer *eb) spin_lock(&fs_info->buffer_lock); radix_tree_delete(&fs_info->buffer_radix, - eb->start >> PAGE_SHIFT); + eb->start >> fs_info->sectorsize_bits); spin_unlock(&fs_info->buffer_lock); } else { spin_unlock(&eb->refs_lock); @@ -5446,33 +5830,103 @@ bool set_extent_buffer_dirty(struct extent_buffer *eb) void clear_extent_buffer_uptodate(struct extent_buffer *eb) { - int i; + struct btrfs_fs_info *fs_info = eb->fs_info; struct page *page; int num_pages; + int i; clear_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); num_pages = num_extent_pages(eb); for (i = 0; i < num_pages; i++) { page = eb->pages[i]; if (page) - ClearPageUptodate(page); + btrfs_page_clear_uptodate(fs_info, page, + eb->start, eb->len); } } void set_extent_buffer_uptodate(struct extent_buffer *eb) { - int i; + struct btrfs_fs_info *fs_info = eb->fs_info; struct page *page; int num_pages; + int i; set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); num_pages = num_extent_pages(eb); for (i = 0; i < num_pages; i++) { page = eb->pages[i]; - SetPageUptodate(page); + btrfs_page_set_uptodate(fs_info, page, eb->start, eb->len); } } +static int read_extent_buffer_subpage(struct extent_buffer *eb, int wait, + int mirror_num) +{ + struct btrfs_fs_info *fs_info = eb->fs_info; + struct extent_io_tree *io_tree; + struct page *page = eb->pages[0]; + struct bio *bio = NULL; + int ret = 0; + + ASSERT(!test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags)); + ASSERT(PagePrivate(page)); + io_tree = &BTRFS_I(fs_info->btree_inode)->io_tree; + + if (wait == WAIT_NONE) { + ret = try_lock_extent(io_tree, eb->start, + eb->start + eb->len - 1); + if (ret <= 0) + return ret; + } else { + ret = lock_extent(io_tree, eb->start, eb->start + eb->len - 1); + if (ret < 0) + return ret; + } + + ret = 0; + if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags) || + PageUptodate(page) || + btrfs_subpage_test_uptodate(fs_info, page, eb->start, eb->len)) { + set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); + unlock_extent(io_tree, eb->start, eb->start + eb->len - 1); + return ret; + } + + clear_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags); + eb->read_mirror = 0; + atomic_set(&eb->io_pages, 1); + check_buffer_tree_ref(eb); + btrfs_subpage_clear_error(fs_info, page, eb->start, eb->len); + + ret = submit_extent_page(REQ_OP_READ | REQ_META, NULL, page, eb->start, + eb->len, eb->start - page_offset(page), &bio, + end_bio_extent_readpage, mirror_num, 0, 0, + true); + if (ret) { + /* + * In the endio function, if we hit something wrong we will + * increase the io_pages, so here we need to decrease it for + * error path. + */ + atomic_dec(&eb->io_pages); + } + if (bio) { + int tmp; + + tmp = submit_one_bio(bio, mirror_num, 0); + if (tmp < 0) + return tmp; + } + if (ret || wait != WAIT_COMPLETE) + return ret; + + wait_extent_bit(io_tree, eb->start, eb->start + eb->len - 1, EXTENT_LOCKED); + if (!test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags)) + ret = -EIO; + return ret; +} + int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num) { int i; @@ -5489,10 +5943,20 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num) if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags)) return 0; + if (eb->fs_info->sectorsize < PAGE_SIZE) + return read_extent_buffer_subpage(eb, wait, mirror_num); + num_pages = num_extent_pages(eb); for (i = 0; i < num_pages; i++) { page = eb->pages[i]; if (wait == WAIT_NONE) { + /* + * WAIT_NONE is only utilized by readahead. If we can't + * acquire the lock atomically it means either the eb + * is being read out or under modification. + * Either way the eb will be or has been cached, + * readahead can exit safely. + */ if (!trylock_page(page)) goto unlock_exit; } else { @@ -5622,12 +6086,12 @@ void read_extent_buffer(const struct extent_buffer *eb, void *dstv, struct page *page; char *kaddr; char *dst = (char *)dstv; - unsigned long i = start >> PAGE_SHIFT; + unsigned long i = get_eb_page_index(start); if (check_eb_range(eb, start, len)) return; - offset = offset_in_page(start); + offset = get_eb_offset_in_page(eb, start); while (len > 0) { page = eb->pages[i]; @@ -5652,13 +6116,13 @@ int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb, struct page *page; char *kaddr; char __user *dst = (char __user *)dstv; - unsigned long i = start >> PAGE_SHIFT; + unsigned long i = get_eb_page_index(start); int ret = 0; WARN_ON(start > eb->len); WARN_ON(start + len > eb->start + eb->len); - offset = offset_in_page(start); + offset = get_eb_offset_in_page(eb, start); while (len > 0) { page = eb->pages[i]; @@ -5687,13 +6151,13 @@ int memcmp_extent_buffer(const struct extent_buffer *eb, const void *ptrv, struct page *page; char *kaddr; char *ptr = (char *)ptrv; - unsigned long i = start >> PAGE_SHIFT; + unsigned long i = get_eb_page_index(start); int ret = 0; if (check_eb_range(eb, start, len)) return -EINVAL; - offset = offset_in_page(start); + offset = get_eb_offset_in_page(eb, start); while (len > 0) { page = eb->pages[i]; @@ -5719,7 +6183,7 @@ void write_extent_buffer_chunk_tree_uuid(const struct extent_buffer *eb, char *kaddr; WARN_ON(!PageUptodate(eb->pages[0])); - kaddr = page_address(eb->pages[0]); + kaddr = page_address(eb->pages[0]) + get_eb_offset_in_page(eb, 0); memcpy(kaddr + offsetof(struct btrfs_header, chunk_tree_uuid), srcv, BTRFS_FSID_SIZE); } @@ -5729,7 +6193,7 @@ void write_extent_buffer_fsid(const struct extent_buffer *eb, const void *srcv) char *kaddr; WARN_ON(!PageUptodate(eb->pages[0])); - kaddr = page_address(eb->pages[0]); + kaddr = page_address(eb->pages[0]) + get_eb_offset_in_page(eb, 0); memcpy(kaddr + offsetof(struct btrfs_header, fsid), srcv, BTRFS_FSID_SIZE); } @@ -5742,12 +6206,14 @@ void write_extent_buffer(const struct extent_buffer *eb, const void *srcv, struct page *page; char *kaddr; char *src = (char *)srcv; - unsigned long i = start >> PAGE_SHIFT; + unsigned long i = get_eb_page_index(start); + + WARN_ON(test_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags)); if (check_eb_range(eb, start, len)) return; - offset = offset_in_page(start); + offset = get_eb_offset_in_page(eb, start); while (len > 0) { page = eb->pages[i]; @@ -5771,12 +6237,12 @@ void memzero_extent_buffer(const struct extent_buffer *eb, unsigned long start, size_t offset; struct page *page; char *kaddr; - unsigned long i = start >> PAGE_SHIFT; + unsigned long i = get_eb_page_index(start); if (check_eb_range(eb, start, len)) return; - offset = offset_in_page(start); + offset = get_eb_offset_in_page(eb, start); while (len > 0) { page = eb->pages[i]; @@ -5800,10 +6266,20 @@ void copy_extent_buffer_full(const struct extent_buffer *dst, ASSERT(dst->len == src->len); - num_pages = num_extent_pages(dst); - for (i = 0; i < num_pages; i++) - copy_page(page_address(dst->pages[i]), - page_address(src->pages[i])); + if (dst->fs_info->sectorsize == PAGE_SIZE) { + num_pages = num_extent_pages(dst); + for (i = 0; i < num_pages; i++) + copy_page(page_address(dst->pages[i]), + page_address(src->pages[i])); + } else { + size_t src_offset = get_eb_offset_in_page(src, 0); + size_t dst_offset = get_eb_offset_in_page(dst, 0); + + ASSERT(src->fs_info->sectorsize < PAGE_SIZE); + memcpy(page_address(dst->pages[0]) + dst_offset, + page_address(src->pages[0]) + src_offset, + src->len); + } } void copy_extent_buffer(const struct extent_buffer *dst, @@ -5816,7 +6292,7 @@ void copy_extent_buffer(const struct extent_buffer *dst, size_t offset; struct page *page; char *kaddr; - unsigned long i = dst_offset >> PAGE_SHIFT; + unsigned long i = get_eb_page_index(dst_offset); if (check_eb_range(dst, dst_offset, len) || check_eb_range(src, src_offset, len)) @@ -5824,7 +6300,7 @@ void copy_extent_buffer(const struct extent_buffer *dst, WARN_ON(src->len != dst_len); - offset = offset_in_page(dst_offset); + offset = get_eb_offset_in_page(dst, dst_offset); while (len > 0) { page = dst->pages[i]; @@ -5868,7 +6344,7 @@ static inline void eb_bitmap_offset(const struct extent_buffer *eb, * the bitmap item in the extent buffer + the offset of the byte in the * bitmap item. */ - offset = start + byte_offset; + offset = start + offset_in_page(eb->start) + byte_offset; *page_index = offset >> PAGE_SHIFT; *page_offset = offset_in_page(offset); @@ -6022,11 +6498,11 @@ void memcpy_extent_buffer(const struct extent_buffer *dst, return; while (len > 0) { - dst_off_in_page = offset_in_page(dst_offset); - src_off_in_page = offset_in_page(src_offset); + dst_off_in_page = get_eb_offset_in_page(dst, dst_offset); + src_off_in_page = get_eb_offset_in_page(dst, src_offset); - dst_i = dst_offset >> PAGE_SHIFT; - src_i = src_offset >> PAGE_SHIFT; + dst_i = get_eb_page_index(dst_offset); + src_i = get_eb_page_index(src_offset); cur = min(len, (unsigned long)(PAGE_SIZE - src_off_in_page)); @@ -6062,11 +6538,11 @@ void memmove_extent_buffer(const struct extent_buffer *dst, return; } while (len > 0) { - dst_i = dst_end >> PAGE_SHIFT; - src_i = src_end >> PAGE_SHIFT; + dst_i = get_eb_page_index(dst_end); + src_i = get_eb_page_index(src_end); - dst_off_in_page = offset_in_page(dst_end); - src_off_in_page = offset_in_page(src_end); + dst_off_in_page = get_eb_offset_in_page(dst, dst_end); + src_off_in_page = get_eb_offset_in_page(dst, src_end); cur = min_t(unsigned long, len, src_off_in_page + 1); cur = min(cur, dst_off_in_page + 1); @@ -6080,13 +6556,115 @@ void memmove_extent_buffer(const struct extent_buffer *dst, } } +static struct extent_buffer *get_next_extent_buffer( + struct btrfs_fs_info *fs_info, struct page *page, u64 bytenr) +{ + struct extent_buffer *gang[BTRFS_SUBPAGE_BITMAP_SIZE]; + struct extent_buffer *found = NULL; + u64 page_start = page_offset(page); + int ret; + int i; + + ASSERT(in_range(bytenr, page_start, PAGE_SIZE)); + ASSERT(PAGE_SIZE / fs_info->nodesize <= BTRFS_SUBPAGE_BITMAP_SIZE); + lockdep_assert_held(&fs_info->buffer_lock); + + ret = radix_tree_gang_lookup(&fs_info->buffer_radix, (void **)gang, + bytenr >> fs_info->sectorsize_bits, + PAGE_SIZE / fs_info->nodesize); + for (i = 0; i < ret; i++) { + /* Already beyond page end */ + if (gang[i]->start >= page_start + PAGE_SIZE) + break; + /* Found one */ + if (gang[i]->start >= bytenr) { + found = gang[i]; + break; + } + } + return found; +} + +static int try_release_subpage_extent_buffer(struct page *page) +{ + struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb); + u64 cur = page_offset(page); + const u64 end = page_offset(page) + PAGE_SIZE; + int ret; + + while (cur < end) { + struct extent_buffer *eb = NULL; + + /* + * Unlike try_release_extent_buffer() which uses page->private + * to grab buffer, for subpage case we rely on radix tree, thus + * we need to ensure radix tree consistency. + * + * We also want an atomic snapshot of the radix tree, thus go + * with spinlock rather than RCU. + */ + spin_lock(&fs_info->buffer_lock); + eb = get_next_extent_buffer(fs_info, page, cur); + if (!eb) { + /* No more eb in the page range after or at cur */ + spin_unlock(&fs_info->buffer_lock); + break; + } + cur = eb->start + eb->len; + + /* + * The same as try_release_extent_buffer(), to ensure the eb + * won't disappear out from under us. + */ + spin_lock(&eb->refs_lock); + if (atomic_read(&eb->refs) != 1 || extent_buffer_under_io(eb)) { + spin_unlock(&eb->refs_lock); + spin_unlock(&fs_info->buffer_lock); + break; + } + spin_unlock(&fs_info->buffer_lock); + + /* + * If tree ref isn't set then we know the ref on this eb is a + * real ref, so just return, this eb will likely be freed soon + * anyway. + */ + if (!test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) { + spin_unlock(&eb->refs_lock); + break; + } + + /* + * Here we don't care about the return value, we will always + * check the page private at the end. And + * release_extent_buffer() will release the refs_lock. + */ + release_extent_buffer(eb); + } + /* + * Finally to check if we have cleared page private, as if we have + * released all ebs in the page, the page private should be cleared now. + */ + spin_lock(&page->mapping->private_lock); + if (!PagePrivate(page)) + ret = 1; + else + ret = 0; + spin_unlock(&page->mapping->private_lock); + return ret; + +} + int try_release_extent_buffer(struct page *page) { struct extent_buffer *eb; + if (btrfs_sb(page->mapping->host->i_sb)->sectorsize < PAGE_SIZE) + return try_release_subpage_extent_buffer(page); + /* - * We need to make sure nobody is attaching this page to an eb right - * now. + * We need to make sure nobody is changing page->private, as we rely on + * page->private as the pointer to extent buffer. */ spin_lock(&page->mapping->private_lock); if (!PagePrivate(page)) { @@ -6121,3 +6699,54 @@ int try_release_extent_buffer(struct page *page) return release_extent_buffer(eb); } + +/* + * btrfs_readahead_tree_block - attempt to readahead a child block + * @fs_info: the fs_info + * @bytenr: bytenr to read + * @owner_root: objectid of the root that owns this eb + * @gen: generation for the uptodate check, can be 0 + * @level: level for the eb + * + * Attempt to readahead a tree block at @bytenr. If @gen is 0 then we do a + * normal uptodate check of the eb, without checking the generation. If we have + * to read the block we will not block on anything. + */ +void btrfs_readahead_tree_block(struct btrfs_fs_info *fs_info, + u64 bytenr, u64 owner_root, u64 gen, int level) +{ + struct extent_buffer *eb; + int ret; + + eb = btrfs_find_create_tree_block(fs_info, bytenr, owner_root, level); + if (IS_ERR(eb)) + return; + + if (btrfs_buffer_uptodate(eb, gen, 1)) { + free_extent_buffer(eb); + return; + } + + ret = read_extent_buffer_pages(eb, WAIT_NONE, 0); + if (ret < 0) + free_extent_buffer_stale(eb); + else + free_extent_buffer(eb); +} + +/* + * btrfs_readahead_node_child - readahead a node's child block + * @node: parent node we're reading from + * @slot: slot in the parent node for the child we want to read + * + * A helper for btrfs_readahead_tree_block, we simply read the bytenr pointed at + * the slot in the node provided. + */ +void btrfs_readahead_node_child(struct extent_buffer *node, int slot) +{ + btrfs_readahead_tree_block(node->fs_info, + btrfs_node_blockptr(node, slot), + btrfs_header_owner(node), + btrfs_node_ptr_generation(node, slot), + btrfs_header_level(node) - 1); +} diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index f39d02e7f7ef..824640cb0ace 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -6,6 +6,7 @@ #include <linux/rbtree.h> #include <linux/refcount.h> #include <linux/fiemap.h> +#include <linux/btrfs_tree.h> #include "ulist.h" /* @@ -30,16 +31,17 @@ enum { EXTENT_BUFFER_IN_TREE, /* write IO error */ EXTENT_BUFFER_WRITE_ERR, + EXTENT_BUFFER_NO_CHECK, }; /* these are flags for __process_pages_contig */ #define PAGE_UNLOCK (1 << 0) -#define PAGE_CLEAR_DIRTY (1 << 1) -#define PAGE_SET_WRITEBACK (1 << 2) -#define PAGE_END_WRITEBACK (1 << 3) -#define PAGE_SET_PRIVATE2 (1 << 4) -#define PAGE_SET_ERROR (1 << 5) -#define PAGE_LOCK (1 << 6) +/* Page starts writeback, clear dirty bit and set writeback bit */ +#define PAGE_START_WRITEBACK (1 << 1) +#define PAGE_END_WRITEBACK (1 << 2) +#define PAGE_SET_PRIVATE2 (1 << 3) +#define PAGE_SET_ERROR (1 << 4) +#define PAGE_LOCK (1 << 5) /* * page->private values. Every page that is controlled by the extent @@ -71,11 +73,10 @@ typedef blk_status_t (submit_bio_hook_t)(struct inode *inode, struct bio *bio, int mirror_num, unsigned long bio_flags); -typedef blk_status_t (extent_submit_bio_start_t)(void *private_data, - struct bio *bio, u64 bio_offset); +typedef blk_status_t (extent_submit_bio_start_t)(struct inode *inode, + struct bio *bio, u64 dio_file_offset); -#define INLINE_EXTENT_BUFFER_PAGES 16 -#define MAX_INLINE_EXTENT_BUFFER_SIZE (INLINE_EXTENT_BUFFER_PAGES * PAGE_SIZE) +#define INLINE_EXTENT_BUFFER_PAGES (BTRFS_MAX_METADATA_BLOCKSIZE / PAGE_SIZE) struct extent_buffer { u64 start; unsigned long len; @@ -87,31 +88,14 @@ struct extent_buffer { int read_mirror; struct rcu_head rcu_head; pid_t lock_owner; - - int blocking_writers; - atomic_t blocking_readers; - bool lock_recursed; /* >= 0 if eb belongs to a log tree, -1 otherwise */ - short log_index; - - /* protects write locks */ - rwlock_t lock; + s8 log_index; - /* readers use lock_wq while they wait for the write - * lock holders to unlock - */ - wait_queue_head_t write_lock_wq; + struct rw_semaphore lock; - /* writers use read_lock_wq while they wait for readers - * to unlock - */ - wait_queue_head_t read_lock_wq; struct page *pages[INLINE_EXTENT_BUFFER_PAGES]; + struct list_head release_list; #ifdef CONFIG_BTRFS_DEBUG - int spinning_writers; - atomic_t spinning_readers; - atomic_t read_locks; - int write_locks; struct list_head leak_list; #endif }; @@ -196,10 +180,11 @@ int btree_write_cache_pages(struct address_space *mapping, void extent_readahead(struct readahead_control *rac); int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len); -void set_page_extent_mapped(struct page *page); +int set_page_extent_mapped(struct page *page); +void clear_page_extent_mapped(struct page *page); struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, - u64 start); + u64 start, u64 owner_root, int level); struct extent_buffer *__alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info, u64 start, unsigned long len); struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info, @@ -215,11 +200,20 @@ void free_extent_buffer_stale(struct extent_buffer *eb); int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num); void wait_on_extent_buffer_writeback(struct extent_buffer *eb); +void btrfs_readahead_tree_block(struct btrfs_fs_info *fs_info, + u64 bytenr, u64 owner_root, u64 gen, int level); +void btrfs_readahead_node_child(struct extent_buffer *node, int slot); static inline int num_extent_pages(const struct extent_buffer *eb) { - return (round_up(eb->start + eb->len, PAGE_SIZE) >> PAGE_SHIFT) - - (eb->start >> PAGE_SHIFT); + /* + * For sectorsize == PAGE_SIZE case, since nodesize is always aligned to + * sectorsize, it's just eb->len >> PAGE_SHIFT. + * + * For sectorsize < PAGE_SIZE case, we could have nodesize < PAGE_SIZE, + * thus have to ensure we get at least one page. + */ + return (eb->len >> PAGE_SHIFT) ?: 1; } static inline int extent_buffer_uptodate(const struct extent_buffer *eb) @@ -270,8 +264,7 @@ void extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end); void extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end); void extent_clear_unlock_delalloc(struct btrfs_inode *inode, u64 start, u64 end, struct page *locked_page, - unsigned bits_to_clear, - unsigned long page_ops); + u32 bits_to_clear, unsigned long page_ops); struct bio *btrfs_bio_alloc(u64 first_byte); struct bio *btrfs_io_bio_alloc(unsigned int nr_iovecs); struct bio *btrfs_bio_clone(struct bio *bio); @@ -307,7 +300,7 @@ struct io_failure_record { blk_status_t btrfs_submit_read_repair(struct inode *inode, - struct bio *failed_bio, u64 phy_offset, + struct bio *failed_bio, u32 bio_offset, struct page *page, unsigned int pgoff, u64 start, u64 end, int failed_mirror, submit_bio_hook_t *submit_bio_hook); diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index bd6229fb2b6f..4a8e02f7b6c7 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -385,9 +385,12 @@ static void extent_map_device_clear_bits(struct extent_map *em, unsigned bits) } /** - * add_extent_mapping - add new extent map to the extent tree + * Add new extent map to the extent tree + * * @tree: tree to insert new map in * @em: map to insert + * @modified: indicate whether the given @em should be added to the + * modified list, which indicates the extent needs to be logged * * Insert @em into @tree or perform a simple forward/backward merge with * existing mappings. The extent_map struct passed in will be inserted @@ -574,12 +577,13 @@ static noinline int merge_extent_mapping(struct extent_map_tree *em_tree, } /** - * btrfs_add_extent_mapping - add extent mapping into em_tree - * @fs_info - used for tracepoint - * @em_tree - the extent tree into which we want to insert the extent mapping - * @em_in - extent we are inserting - * @start - start of the logical range btrfs_get_extent() is requesting - * @len - length of the logical range btrfs_get_extent() is requesting + * Add extent mapping into em_tree + * + * @fs_info: the filesystem + * @em_tree: extent tree into which we want to insert the extent mapping + * @em_in: extent we are inserting + * @start: start of the logical range btrfs_get_extent() is requesting + * @len: length of the logical range btrfs_get_extent() is requesting * * Note that @em_in's range may be different from [start, start+len), * but they must be overlapped. diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 8f4f2bd6d9b9..47cd3a6dc635 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -24,8 +24,10 @@ PAGE_SIZE)) /** - * @inode - the inode we want to update the disk_i_size for - * @new_i_size - the i_size we want to set to, 0 if we use i_size + * Set inode's size according to filesystem options + * + * @inode: inode we want to update the disk_i_size for + * @new_i_size: i_size we want to set to, 0 if we use i_size * * With NO_HOLES set this simply sets the disk_is_size to whatever i_size_read() * returns as it is perfectly fine with a file that has holes without hole file @@ -38,33 +40,35 @@ * Finally new_i_size should only be set in the case of truncate where we're not * ready to use i_size_read() as the limiter yet. */ -void btrfs_inode_safe_disk_i_size_write(struct inode *inode, u64 new_i_size) +void btrfs_inode_safe_disk_i_size_write(struct btrfs_inode *inode, u64 new_i_size) { - struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info; + struct btrfs_fs_info *fs_info = inode->root->fs_info; u64 start, end, i_size; int ret; - i_size = new_i_size ?: i_size_read(inode); + i_size = new_i_size ?: i_size_read(&inode->vfs_inode); if (btrfs_fs_incompat(fs_info, NO_HOLES)) { - BTRFS_I(inode)->disk_i_size = i_size; + inode->disk_i_size = i_size; return; } - spin_lock(&BTRFS_I(inode)->lock); - ret = find_contiguous_extent_bit(&BTRFS_I(inode)->file_extent_tree, 0, - &start, &end, EXTENT_DIRTY); + spin_lock(&inode->lock); + ret = find_contiguous_extent_bit(&inode->file_extent_tree, 0, &start, + &end, EXTENT_DIRTY); if (!ret && start == 0) i_size = min(i_size, end + 1); else i_size = 0; - BTRFS_I(inode)->disk_i_size = i_size; - spin_unlock(&BTRFS_I(inode)->lock); + inode->disk_i_size = i_size; + spin_unlock(&inode->lock); } /** - * @inode - the inode we're modifying - * @start - the start file offset of the file extent we've inserted - * @len - the logical length of the file extent item + * Mark range within a file as having a new extent inserted + * + * @inode: inode being modified + * @start: start file offset of the file extent we've inserted + * @len: logical length of the file extent item * * Call when we are inserting a new file extent where there was none before. * Does not need to call this in the case where we're replacing an existing file @@ -88,9 +92,11 @@ int btrfs_inode_set_file_extent_range(struct btrfs_inode *inode, u64 start, } /** - * @inode - the inode we're modifying - * @start - the start file offset of the file extent we've inserted - * @len - the logical length of the file extent item + * Marks an inode range as not having a backing extent + * + * @inode: inode being modified + * @start: start file offset of the file extent we've inserted + * @len: logical length of the file extent item * * Called when we drop a file extent, for example when we truncate. Doesn't * need to be called for cases where we're replacing a file extent, like when @@ -142,7 +148,6 @@ int btrfs_insert_file_extent(struct btrfs_trans_handle *trans, file_key.offset = pos; file_key.type = BTRFS_EXTENT_DATA_KEY; - path->leave_spinning = 1; ret = btrfs_insert_empty_item(trans, root, path, &file_key, sizeof(*item)); if (ret < 0) @@ -181,7 +186,7 @@ btrfs_lookup_csum(struct btrfs_trans_handle *trans, struct btrfs_csum_item *item; struct extent_buffer *leaf; u64 csum_offset = 0; - u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); + const u32 csum_size = fs_info->csum_size; int csums_in_item; file_key.objectid = BTRFS_EXTENT_CSUM_OBJECTID; @@ -201,7 +206,7 @@ btrfs_lookup_csum(struct btrfs_trans_handle *trans, goto fail; csum_offset = (bytenr - found_key.offset) >> - fs_info->sb->s_blocksize_bits; + fs_info->sectorsize_bits; csums_in_item = btrfs_item_size_nr(leaf, path->slots[0]); csums_in_item /= csum_size; @@ -239,12 +244,117 @@ int btrfs_lookup_file_extent(struct btrfs_trans_handle *trans, return ret; } +/* + * Find checksums for logical bytenr range [disk_bytenr, disk_bytenr + len) and + * estore the result to @dst. + * + * Return >0 for the number of sectors we found. + * Return 0 for the range [disk_bytenr, disk_bytenr + sectorsize) has no csum + * for it. Caller may want to try next sector until one range is hit. + * Return <0 for fatal error. + */ +static int search_csum_tree(struct btrfs_fs_info *fs_info, + struct btrfs_path *path, u64 disk_bytenr, + u64 len, u8 *dst) +{ + struct btrfs_csum_item *item = NULL; + struct btrfs_key key; + const u32 sectorsize = fs_info->sectorsize; + const u32 csum_size = fs_info->csum_size; + u32 itemsize; + int ret; + u64 csum_start; + u64 csum_len; + + ASSERT(IS_ALIGNED(disk_bytenr, sectorsize) && + IS_ALIGNED(len, sectorsize)); + + /* Check if the current csum item covers disk_bytenr */ + if (path->nodes[0]) { + item = btrfs_item_ptr(path->nodes[0], path->slots[0], + struct btrfs_csum_item); + btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); + itemsize = btrfs_item_size_nr(path->nodes[0], path->slots[0]); + + csum_start = key.offset; + csum_len = (itemsize / csum_size) * sectorsize; + + if (in_range(disk_bytenr, csum_start, csum_len)) + goto found; + } + + /* Current item doesn't contain the desired range, search again */ + btrfs_release_path(path); + item = btrfs_lookup_csum(NULL, fs_info->csum_root, path, disk_bytenr, 0); + if (IS_ERR(item)) { + ret = PTR_ERR(item); + goto out; + } + btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); + itemsize = btrfs_item_size_nr(path->nodes[0], path->slots[0]); + + csum_start = key.offset; + csum_len = (itemsize / csum_size) * sectorsize; + ASSERT(in_range(disk_bytenr, csum_start, csum_len)); + +found: + ret = (min(csum_start + csum_len, disk_bytenr + len) - + disk_bytenr) >> fs_info->sectorsize_bits; + read_extent_buffer(path->nodes[0], dst, (unsigned long)item, + ret * csum_size); +out: + if (ret == -ENOENT) + ret = 0; + return ret; +} + +/* + * Locate the file_offset of @cur_disk_bytenr of a @bio. + * + * Bio of btrfs represents read range of + * [bi_sector << 9, bi_sector << 9 + bi_size). + * Knowing this, we can iterate through each bvec to locate the page belong to + * @cur_disk_bytenr and get the file offset. + * + * @inode is used to determine if the bvec page really belongs to @inode. + * + * Return 0 if we can't find the file offset + * Return >0 if we find the file offset and restore it to @file_offset_ret + */ +static int search_file_offset_in_bio(struct bio *bio, struct inode *inode, + u64 disk_bytenr, u64 *file_offset_ret) +{ + struct bvec_iter iter; + struct bio_vec bvec; + u64 cur = bio->bi_iter.bi_sector << SECTOR_SHIFT; + int ret = 0; + + bio_for_each_segment(bvec, bio, iter) { + struct page *page = bvec.bv_page; + + if (cur > disk_bytenr) + break; + if (cur + bvec.bv_len <= disk_bytenr) { + cur += bvec.bv_len; + continue; + } + ASSERT(in_range(disk_bytenr, cur, bvec.bv_len)); + if (page->mapping && page->mapping->host && + page->mapping->host == inode) { + ret = 1; + *file_offset_ret = page_offset(page) + bvec.bv_offset + + disk_bytenr - cur; + break; + } + } + return ret; +} + /** - * btrfs_lookup_bio_sums - Look up checksums for a bio. + * Lookup the checksum for the read bio in csum tree. + * * @inode: inode that the bio is for. * @bio: bio to look up. - * @offset: Unless (u64)-1, look up checksums for this offset in the file. - * If (u64)-1, use the page offsets from the bio instead. * @dst: Buffer of size nblocks * btrfs_super_csum_size() used to return * checksum (nblocks = bio->bi_iter.bi_size / fs_info->sectorsize). If * NULL, the checksum buffer is allocated and returned in @@ -252,31 +362,40 @@ int btrfs_lookup_file_extent(struct btrfs_trans_handle *trans, * * Return: BLK_STS_RESOURCE if allocating memory fails, BLK_STS_OK otherwise. */ -blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, - u64 offset, u8 *dst) +blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u8 *dst) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct bio_vec bvec; - struct bvec_iter iter; - struct btrfs_csum_item *item = NULL; struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; struct btrfs_path *path; - const bool page_offsets = (offset == (u64)-1); + const u32 sectorsize = fs_info->sectorsize; + const u32 csum_size = fs_info->csum_size; + u32 orig_len = bio->bi_iter.bi_size; + u64 orig_disk_bytenr = bio->bi_iter.bi_sector << SECTOR_SHIFT; + u64 cur_disk_bytenr; u8 *csum; - u64 item_start_offset = 0; - u64 item_last_offset = 0; - u64 disk_bytenr; - u64 page_bytes_left; - u32 diff; - int nblocks; + const unsigned int nblocks = orig_len >> fs_info->sectorsize_bits; int count = 0; - u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); + if (!fs_info->csum_root || (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) + return BLK_STS_OK; + + /* + * This function is only called for read bio. + * + * This means two things: + * - All our csums should only be in csum tree + * No ordered extents csums, as ordered extents are only for write + * path. + * - No need to bother any other info from bvec + * Since we're looking up csums, the only important info is the + * disk_bytenr and the length, which can be extracted from bi_iter + * directly. + */ + ASSERT(bio_op(bio) == REQ_OP_READ); path = btrfs_alloc_path(); if (!path) return BLK_STS_RESOURCE; - nblocks = bio->bi_iter.bi_size >> inode->i_sb->s_blocksize_bits; if (!dst) { struct btrfs_io_bio *btrfs_bio = btrfs_io_bio(bio); @@ -295,7 +414,11 @@ blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, csum = dst; } - if (bio->bi_iter.bi_size > PAGE_SIZE * 8) + /* + * If requested number of sectors is larger than one leaf can contain, + * kick the readahead for csum tree. + */ + if (nblocks > fs_info->csums_per_leaf) path->reada = READA_FORWARD; /* @@ -309,85 +432,62 @@ blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, path->skip_locking = 1; } - disk_bytenr = (u64)bio->bi_iter.bi_sector << 9; - - bio_for_each_segment(bvec, bio, iter) { - page_bytes_left = bvec.bv_len; - if (count) - goto next; + for (cur_disk_bytenr = orig_disk_bytenr; + cur_disk_bytenr < orig_disk_bytenr + orig_len; + cur_disk_bytenr += (count * sectorsize)) { + u64 search_len = orig_disk_bytenr + orig_len - cur_disk_bytenr; + unsigned int sector_offset; + u8 *csum_dst; - if (page_offsets) - offset = page_offset(bvec.bv_page) + bvec.bv_offset; - count = btrfs_find_ordered_sum(BTRFS_I(inode), offset, - disk_bytenr, csum, nblocks); - if (count) - goto found; + /* + * Although both cur_disk_bytenr and orig_disk_bytenr is u64, + * we're calculating the offset to the bio start. + * + * Bio size is limited to UINT_MAX, thus unsigned int is large + * enough to contain the raw result, not to mention the right + * shifted result. + */ + ASSERT(cur_disk_bytenr - orig_disk_bytenr < UINT_MAX); + sector_offset = (cur_disk_bytenr - orig_disk_bytenr) >> + fs_info->sectorsize_bits; + csum_dst = csum + sector_offset * csum_size; + + count = search_csum_tree(fs_info, path, cur_disk_bytenr, + search_len, csum_dst); + if (count <= 0) { + /* + * Either we hit a critical error or we didn't find + * the csum. + * Either way, we put zero into the csums dst, and skip + * to the next sector. + */ + memset(csum_dst, 0, csum_size); + count = 1; - if (!item || disk_bytenr < item_start_offset || - disk_bytenr >= item_last_offset) { - struct btrfs_key found_key; - u32 item_size; - - if (item) - btrfs_release_path(path); - item = btrfs_lookup_csum(NULL, fs_info->csum_root, - path, disk_bytenr, 0); - if (IS_ERR(item)) { - count = 1; - memset(csum, 0, csum_size); - if (BTRFS_I(inode)->root->root_key.objectid == - BTRFS_DATA_RELOC_TREE_OBJECTID) { - set_extent_bits(io_tree, offset, - offset + fs_info->sectorsize - 1, + /* + * For data reloc inode, we need to mark the range + * NODATASUM so that balance won't report false csum + * error. + */ + if (BTRFS_I(inode)->root->root_key.objectid == + BTRFS_DATA_RELOC_TREE_OBJECTID) { + u64 file_offset; + int ret; + + ret = search_file_offset_in_bio(bio, inode, + cur_disk_bytenr, &file_offset); + if (ret) + set_extent_bits(io_tree, file_offset, + file_offset + sectorsize - 1, EXTENT_NODATASUM); - } else { - btrfs_info_rl(fs_info, - "no csum found for inode %llu start %llu", - btrfs_ino(BTRFS_I(inode)), offset); - } - item = NULL; - btrfs_release_path(path); - goto found; + } else { + btrfs_warn_rl(fs_info, + "csum hole found for disk bytenr range [%llu, %llu)", + cur_disk_bytenr, cur_disk_bytenr + sectorsize); } - btrfs_item_key_to_cpu(path->nodes[0], &found_key, - path->slots[0]); - - item_start_offset = found_key.offset; - item_size = btrfs_item_size_nr(path->nodes[0], - path->slots[0]); - item_last_offset = item_start_offset + - (item_size / csum_size) * - fs_info->sectorsize; - item = btrfs_item_ptr(path->nodes[0], path->slots[0], - struct btrfs_csum_item); - } - /* - * this byte range must be able to fit inside - * a single leaf so it will also fit inside a u32 - */ - diff = disk_bytenr - item_start_offset; - diff = diff / fs_info->sectorsize; - diff = diff * csum_size; - count = min_t(int, nblocks, (item_last_offset - disk_bytenr) >> - inode->i_sb->s_blocksize_bits); - read_extent_buffer(path->nodes[0], csum, - ((unsigned long)item) + diff, - csum_size * count); -found: - csum += count * csum_size; - nblocks -= count; -next: - while (count > 0) { - count--; - disk_bytenr += fs_info->sectorsize; - offset += fs_info->sectorsize; - page_bytes_left -= fs_info->sectorsize; - if (!page_bytes_left) - break; /* move to next bio */ } } - WARN_ON_ONCE(count); btrfs_free_path(path); return BLK_STS_OK; } @@ -406,7 +506,7 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end, int ret; size_t size; u64 csum_end; - u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); + const u32 csum_size = fs_info->csum_size; ASSERT(IS_ALIGNED(start, fs_info->sectorsize) && IS_ALIGNED(end + 1, fs_info->sectorsize)); @@ -433,8 +533,7 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end, btrfs_item_key_to_cpu(leaf, &key, path->slots[0] - 1); if (key.objectid == BTRFS_EXTENT_CSUM_OBJECTID && key.type == BTRFS_EXTENT_CSUM_KEY) { - offset = (start - key.offset) >> - fs_info->sb->s_blocksize_bits; + offset = (start - key.offset) >> fs_info->sectorsize_bits; if (offset * csum_size < btrfs_item_size_nr(leaf, path->slots[0] - 1)) path->slots[0]--; @@ -484,10 +583,9 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end, sums->bytenr = start; sums->len = (int)size; - offset = (start - key.offset) >> - fs_info->sb->s_blocksize_bits; + offset = (start - key.offset) >> fs_info->sectorsize_bits; offset *= csum_size; - size >>= fs_info->sb->s_blocksize_bits; + size >>= fs_info->sectorsize_bits; read_extent_buffer(path->nodes[0], sums->sums, @@ -539,7 +637,6 @@ blk_status_t btrfs_csum_one_bio(struct btrfs_inode *inode, struct bio *bio, int i; u64 offset; unsigned nofs_flag; - const u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); nofs_flag = memalloc_nofs_save(); sums = kvzalloc(btrfs_ordered_sum_size(fs_info, bio->bi_iter.bi_size), @@ -557,7 +654,7 @@ blk_status_t btrfs_csum_one_bio(struct btrfs_inode *inode, struct bio *bio, else offset = 0; /* shut up gcc */ - sums->bytenr = (u64)bio->bi_iter.bi_sector << 9; + sums->bytenr = bio->bi_iter.bi_sector << 9; index = 0; shash->tfm = fs_info->csum_shash; @@ -596,7 +693,7 @@ blk_status_t btrfs_csum_one_bio(struct btrfs_inode *inode, struct bio *bio, ordered = btrfs_lookup_ordered_extent(inode, offset); ASSERT(ordered); /* Logic error */ - sums->bytenr = ((u64)bio->bi_iter.bi_sector << 9) + sums->bytenr = (bio->bi_iter.bi_sector << 9) + total_bytes; index = 0; } @@ -607,7 +704,7 @@ blk_status_t btrfs_csum_one_bio(struct btrfs_inode *inode, struct bio *bio, fs_info->sectorsize, sums->sums + index); kunmap_atomic(data); - index += csum_size; + index += fs_info->csum_size; offset += fs_info->sectorsize; this_sum_bytes += fs_info->sectorsize; total_bytes += fs_info->sectorsize; @@ -637,14 +734,14 @@ static noinline void truncate_one_csum(struct btrfs_fs_info *fs_info, u64 bytenr, u64 len) { struct extent_buffer *leaf; - u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); + const u32 csum_size = fs_info->csum_size; u64 csum_end; u64 end_byte = bytenr + len; - u32 blocksize_bits = fs_info->sb->s_blocksize_bits; + u32 blocksize_bits = fs_info->sectorsize_bits; leaf = path->nodes[0]; csum_end = btrfs_item_size_nr(leaf, path->slots[0]) / csum_size; - csum_end <<= fs_info->sb->s_blocksize_bits; + csum_end <<= blocksize_bits; csum_end += key->offset; if (key->offset < bytenr && csum_end <= end_byte) { @@ -691,8 +788,8 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans, u64 csum_end; struct extent_buffer *leaf; int ret; - u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); - int blocksize_bits = fs_info->sb->s_blocksize_bits; + const u32 csum_size = fs_info->csum_size; + u32 blocksize_bits = fs_info->sectorsize_bits; ASSERT(root == fs_info->csum_root || root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID); @@ -706,7 +803,6 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans, key.offset = end_byte - 1; key.type = BTRFS_EXTENT_CSUM_KEY; - path->leave_spinning = 1; ret = btrfs_search_slot(trans, root, &key, path, -1, 1); if (ret > 0) { if (path->slots[0] == 0) @@ -846,7 +942,7 @@ int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans, int index = 0; int found_next; int ret; - u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); + const u32 csum_size = fs_info->csum_size; path = btrfs_alloc_path(); if (!path) @@ -921,13 +1017,15 @@ again: if (btrfs_leaf_free_space(leaf) >= csum_size) { btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]); csum_offset = (bytenr - found_key.offset) >> - fs_info->sb->s_blocksize_bits; + fs_info->sectorsize_bits; goto extend_csum; } btrfs_release_path(path); + path->search_for_extension = 1; ret = btrfs_search_slot(trans, root, &file_key, path, csum_size, 1); + path->search_for_extension = 0; if (ret < 0) goto out; @@ -939,8 +1037,7 @@ again: leaf = path->nodes[0]; btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]); - csum_offset = (bytenr - found_key.offset) >> - fs_info->sb->s_blocksize_bits; + csum_offset = (bytenr - found_key.offset) >> fs_info->sectorsize_bits; if (found_key.type != BTRFS_EXTENT_CSUM_KEY || found_key.objectid != BTRFS_EXTENT_CSUM_OBJECTID || @@ -956,7 +1053,7 @@ extend_csum: u32 diff; tmp = sums->len - total_bytes; - tmp >>= fs_info->sb->s_blocksize_bits; + tmp >>= fs_info->sectorsize_bits; WARN_ON(tmp < 1); extend_nr = max_t(int, 1, (int)tmp); @@ -981,9 +1078,9 @@ insert: u64 tmp; tmp = sums->len - total_bytes; - tmp >>= fs_info->sb->s_blocksize_bits; + tmp >>= fs_info->sectorsize_bits; tmp = min(tmp, (next_offset - file_key.offset) >> - fs_info->sb->s_blocksize_bits); + fs_info->sectorsize_bits); tmp = max_t(u64, 1, tmp); tmp = min_t(u64, tmp, MAX_CSUM_ITEMS(fs_info, csum_size)); @@ -991,10 +1088,8 @@ insert: } else { ins_size = csum_size; } - path->leave_spinning = 1; ret = btrfs_insert_empty_item(trans, root, path, &file_key, ins_size); - path->leave_spinning = 0; if (ret < 0) goto out; if (WARN_ON(ret != 0)) @@ -1007,8 +1102,7 @@ csum: item = (struct btrfs_csum_item *)((unsigned char *)item + csum_offset * csum_size); found: - ins_size = (u32)(sums->len - total_bytes) >> - fs_info->sb->s_blocksize_bits; + ins_size = (u32)(sums->len - total_bytes) >> fs_info->sectorsize_bits; ins_size *= csum_size; ins_size = min_t(u32, (unsigned long)item_end - (unsigned long)item, ins_size); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 0ff659455b1e..be9e3900cce8 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -452,57 +452,16 @@ static void btrfs_drop_pages(struct page **pages, size_t num_pages) } } -static int btrfs_find_new_delalloc_bytes(struct btrfs_inode *inode, - const u64 start, - const u64 len, - struct extent_state **cached_state) -{ - u64 search_start = start; - const u64 end = start + len - 1; - - while (search_start < end) { - const u64 search_len = end - search_start + 1; - struct extent_map *em; - u64 em_len; - int ret = 0; - - em = btrfs_get_extent(inode, NULL, 0, search_start, search_len); - if (IS_ERR(em)) - return PTR_ERR(em); - - if (em->block_start != EXTENT_MAP_HOLE) - goto next; - - em_len = em->len; - if (em->start < search_start) - em_len -= search_start - em->start; - if (em_len > search_len) - em_len = search_len; - - ret = set_extent_bit(&inode->io_tree, search_start, - search_start + em_len - 1, - EXTENT_DELALLOC_NEW, - NULL, cached_state, GFP_NOFS); -next: - search_start = extent_map_end(em); - free_extent_map(em); - if (ret) - return ret; - } - return 0; -} - /* - * after copy_from_user, pages need to be dirtied and we need to make - * sure holes are created between the current EOF and the start of - * any next extents (if required). - * - * this also makes the decision about creating an inline extent vs - * doing real data extents, marking pages dirty and delalloc as required. + * After btrfs_copy_from_user(), update the following things for delalloc: + * - Mark newly dirtied pages as DELALLOC in the io tree. + * Used to advise which range is to be written back. + * - Mark modified pages as Uptodate/Dirty and not needing COW fixup + * - Update inode size for past EOF write */ int btrfs_dirty_pages(struct btrfs_inode *inode, struct page **pages, size_t num_pages, loff_t pos, size_t write_bytes, - struct extent_state **cached) + struct extent_state **cached, bool noreserve) { struct btrfs_fs_info *fs_info = inode->root->fs_info; int err = 0; @@ -514,7 +473,13 @@ int btrfs_dirty_pages(struct btrfs_inode *inode, struct page **pages, loff_t isize = i_size_read(&inode->vfs_inode); unsigned int extra_bits = 0; - start_pos = pos & ~((u64) fs_info->sectorsize - 1); + if (write_bytes == 0) + return 0; + + if (noreserve) + extra_bits |= EXTENT_NORESERVE; + + start_pos = round_down(pos, fs_info->sectorsize); num_bytes = round_up(write_bytes + pos - start_pos, fs_info->sectorsize); @@ -528,23 +493,6 @@ int btrfs_dirty_pages(struct btrfs_inode *inode, struct page **pages, EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0, cached); - if (!btrfs_is_free_space_inode(inode)) { - if (start_pos >= isize && - !(inode->flags & BTRFS_INODE_PREALLOC)) { - /* - * There can't be any extents following eof in this case - * so just set the delalloc new bit for the range - * directly. - */ - extra_bits |= EXTENT_DELALLOC_NEW; - } else { - err = btrfs_find_new_delalloc_bytes(inode, start_pos, - num_bytes, cached); - if (err) - return err; - } - } - err = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block, extra_bits, cached); if (err) @@ -728,14 +676,16 @@ next: * If an extent intersects the range but is not entirely inside the range * it is either truncated or split. Anything entirely inside the range * is deleted from the tree. + * + * Note: the VFS' inode number of bytes is not updated, it's up to the caller + * to deal with that. We set the field 'bytes_found' of the arguments structure + * with the number of allocated bytes found in the target range, so that the + * caller can update the inode's number of bytes in an atomic way when + * replacing extents in a range to avoid races with stat(2). */ -int __btrfs_drop_extents(struct btrfs_trans_handle *trans, - struct btrfs_root *root, struct btrfs_inode *inode, - struct btrfs_path *path, u64 start, u64 end, - u64 *drop_end, int drop_cache, - int replace_extent, - u32 extent_item_size, - int *key_inserted) +int btrfs_drop_extents(struct btrfs_trans_handle *trans, + struct btrfs_root *root, struct btrfs_inode *inode, + struct btrfs_drop_extents_args *args) { struct btrfs_fs_info *fs_info = root->fs_info; struct extent_buffer *leaf; @@ -743,14 +693,13 @@ int __btrfs_drop_extents(struct btrfs_trans_handle *trans, struct btrfs_ref ref = { 0 }; struct btrfs_key key; struct btrfs_key new_key; - struct inode *vfs_inode = &inode->vfs_inode; u64 ino = btrfs_ino(inode); - u64 search_start = start; + u64 search_start = args->start; u64 disk_bytenr = 0; u64 num_bytes = 0; u64 extent_offset = 0; u64 extent_end = 0; - u64 last_end = start; + u64 last_end = args->start; int del_nr = 0; int del_slot = 0; int extent_type; @@ -760,11 +709,26 @@ int __btrfs_drop_extents(struct btrfs_trans_handle *trans, int update_refs; int found = 0; int leafs_visited = 0; + struct btrfs_path *path = args->path; + + args->bytes_found = 0; + args->extent_inserted = false; - if (drop_cache) - btrfs_drop_extent_cache(inode, start, end - 1, 0); + /* Must always have a path if ->replace_extent is true */ + ASSERT(!(args->replace_extent && !args->path)); - if (start >= inode->disk_i_size && !replace_extent) + if (!path) { + path = btrfs_alloc_path(); + if (!path) { + ret = -ENOMEM; + goto out; + } + } + + if (args->drop_cache) + btrfs_drop_extent_cache(inode, args->start, args->end - 1, 0); + + if (args->start >= inode->disk_i_size && !args->replace_extent) modify_tree = 0; update_refs = (test_bit(BTRFS_ROOT_SHAREABLE, &root->state) || @@ -775,7 +739,7 @@ int __btrfs_drop_extents(struct btrfs_trans_handle *trans, search_start, modify_tree); if (ret < 0) break; - if (ret > 0 && path->slots[0] > 0 && search_start == start) { + if (ret > 0 && path->slots[0] > 0 && search_start == args->start) { leaf = path->nodes[0]; btrfs_item_key_to_cpu(leaf, &key, path->slots[0] - 1); if (key.objectid == ino && @@ -810,7 +774,7 @@ next_slot: path->slots[0]++; goto next_slot; } - if (key.type > BTRFS_EXTENT_DATA_KEY || key.offset >= end) + if (key.type > BTRFS_EXTENT_DATA_KEY || key.offset >= args->end) break; fi = btrfs_item_ptr(leaf, path->slots[0], @@ -852,7 +816,7 @@ next_slot: } found = 1; - search_start = max(key.offset, start); + search_start = max(key.offset, args->start); if (recow || !modify_tree) { modify_tree = -1; btrfs_release_path(path); @@ -863,7 +827,7 @@ next_slot: * | - range to drop - | * | -------- extent -------- | */ - if (start > key.offset && end < extent_end) { + if (args->start > key.offset && args->end < extent_end) { BUG_ON(del_nr > 0); if (extent_type == BTRFS_FILE_EXTENT_INLINE) { ret = -EOPNOTSUPP; @@ -871,7 +835,7 @@ next_slot: } memcpy(&new_key, &key, sizeof(new_key)); - new_key.offset = start; + new_key.offset = args->start; ret = btrfs_duplicate_item(trans, root, path, &new_key); if (ret == -EAGAIN) { @@ -885,15 +849,15 @@ next_slot: fi = btrfs_item_ptr(leaf, path->slots[0] - 1, struct btrfs_file_extent_item); btrfs_set_file_extent_num_bytes(leaf, fi, - start - key.offset); + args->start - key.offset); fi = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); - extent_offset += start - key.offset; + extent_offset += args->start - key.offset; btrfs_set_file_extent_offset(leaf, fi, extent_offset); btrfs_set_file_extent_num_bytes(leaf, fi, - extent_end - start); + extent_end - args->start); btrfs_mark_buffer_dirty(leaf); if (update_refs && disk_bytenr > 0) { @@ -903,11 +867,11 @@ next_slot: btrfs_init_data_ref(&ref, root->root_key.objectid, new_key.objectid, - start - extent_offset); + args->start - extent_offset); ret = btrfs_inc_extent_ref(trans, &ref); BUG_ON(ret); /* -ENOMEM */ } - key.offset = start; + key.offset = args->start; } /* * From here on out we will have actually dropped something, so @@ -919,23 +883,23 @@ next_slot: * | ---- range to drop ----- | * | -------- extent -------- | */ - if (start <= key.offset && end < extent_end) { + if (args->start <= key.offset && args->end < extent_end) { if (extent_type == BTRFS_FILE_EXTENT_INLINE) { ret = -EOPNOTSUPP; break; } memcpy(&new_key, &key, sizeof(new_key)); - new_key.offset = end; + new_key.offset = args->end; btrfs_set_item_key_safe(fs_info, path, &new_key); - extent_offset += end - key.offset; + extent_offset += args->end - key.offset; btrfs_set_file_extent_offset(leaf, fi, extent_offset); btrfs_set_file_extent_num_bytes(leaf, fi, - extent_end - end); + extent_end - args->end); btrfs_mark_buffer_dirty(leaf); if (update_refs && disk_bytenr > 0) - inode_sub_bytes(vfs_inode, end - key.offset); + args->bytes_found += args->end - key.offset; break; } @@ -944,7 +908,7 @@ next_slot: * | ---- range to drop ----- | * | -------- extent -------- | */ - if (start > key.offset && end >= extent_end) { + if (args->start > key.offset && args->end >= extent_end) { BUG_ON(del_nr > 0); if (extent_type == BTRFS_FILE_EXTENT_INLINE) { ret = -EOPNOTSUPP; @@ -952,11 +916,11 @@ next_slot: } btrfs_set_file_extent_num_bytes(leaf, fi, - start - key.offset); + args->start - key.offset); btrfs_mark_buffer_dirty(leaf); if (update_refs && disk_bytenr > 0) - inode_sub_bytes(vfs_inode, extent_end - start); - if (end == extent_end) + args->bytes_found += extent_end - args->start; + if (args->end == extent_end) break; path->slots[0]++; @@ -967,7 +931,7 @@ next_slot: * | ---- range to drop ----- | * | ------ extent ------ | */ - if (start <= key.offset && end >= extent_end) { + if (args->start <= key.offset && args->end >= extent_end) { delete_extent_item: if (del_nr == 0) { del_slot = path->slots[0]; @@ -979,8 +943,7 @@ delete_extent_item: if (update_refs && extent_type == BTRFS_FILE_EXTENT_INLINE) { - inode_sub_bytes(vfs_inode, - extent_end - key.offset); + args->bytes_found += extent_end - key.offset; extent_end = ALIGN(extent_end, fs_info->sectorsize); } else if (update_refs && disk_bytenr > 0) { @@ -993,11 +956,10 @@ delete_extent_item: key.offset - extent_offset); ret = btrfs_free_extent(trans, &ref); BUG_ON(ret); /* -ENOMEM */ - inode_sub_bytes(vfs_inode, - extent_end - key.offset); + args->bytes_found += extent_end - key.offset; } - if (end == extent_end) + if (args->end == extent_end) break; if (path->slots[0] + 1 < btrfs_header_nritems(leaf)) { @@ -1027,7 +989,7 @@ delete_extent_item: * Set path->slots[0] to first slot, so that after the delete * if items are move off from our leaf to its immediate left or * right neighbor leafs, we end up with a correct and adjusted - * path->slots[0] for our insertion (if replace_extent != 0). + * path->slots[0] for our insertion (if args->replace_extent). */ path->slots[0] = del_slot; ret = btrfs_del_items(trans, root, path, del_slot, del_nr); @@ -1041,15 +1003,14 @@ delete_extent_item: * which case it unlocked our path, so check path->locks[0] matches a * write lock. */ - if (!ret && replace_extent && leafs_visited == 1 && - (path->locks[0] == BTRFS_WRITE_LOCK_BLOCKING || - path->locks[0] == BTRFS_WRITE_LOCK) && + if (!ret && args->replace_extent && leafs_visited == 1 && + path->locks[0] == BTRFS_WRITE_LOCK && btrfs_leaf_free_space(leaf) >= - sizeof(struct btrfs_item) + extent_item_size) { + sizeof(struct btrfs_item) + args->extent_item_size) { key.objectid = ino; key.type = BTRFS_EXTENT_DATA_KEY; - key.offset = start; + key.offset = args->start; if (!del_nr && path->slots[0] < btrfs_header_nritems(leaf)) { struct btrfs_key slot_key; @@ -1057,30 +1018,18 @@ delete_extent_item: if (btrfs_comp_cpu_keys(&key, &slot_key) > 0) path->slots[0]++; } - setup_items_for_insert(root, path, &key, &extent_item_size, 1); - *key_inserted = 1; + setup_items_for_insert(root, path, &key, + &args->extent_item_size, 1); + args->extent_inserted = true; } - if (!replace_extent || !(*key_inserted)) + if (!args->path) + btrfs_free_path(path); + else if (!args->extent_inserted) btrfs_release_path(path); - if (drop_end) - *drop_end = found ? min(end, last_end) : end; - return ret; -} - -int btrfs_drop_extents(struct btrfs_trans_handle *trans, - struct btrfs_root *root, struct inode *inode, u64 start, - u64 end, int drop_cache) -{ - struct btrfs_path *path; - int ret; +out: + args->drop_end = found ? min(args->end, last_end) : args->end; - path = btrfs_alloc_path(); - if (!path) - return -ENOMEM; - ret = __btrfs_drop_extents(trans, root, BTRFS_I(inode), path, start, - end, NULL, drop_cache, 0, 0, NULL); - btrfs_free_path(path); return ret; } @@ -1420,6 +1369,12 @@ again: goto fail; } + err = set_page_extent_mapped(pages[i]); + if (err < 0) { + faili = i; + goto fail; + } + if (i == 0) err = prepare_uptodate_page(inode, pages[i], pos, force_uptodate); @@ -1504,23 +1459,11 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages, } /* - * It's possible the pages are dirty right now, but we don't want - * to clean them yet because copy_from_user may catch a page fault - * and we might have to fall back to one page at a time. If that - * happens, we'll unlock these pages and we'd have a window where - * reclaim could sneak in and drop the once-dirty page on the floor - * without writing it. - * - * We have the pages locked and the extent range locked, so there's - * no way someone can start IO on any dirty pages in this range. - * - * We'll call btrfs_dirty_pages() later on, and that will flip around - * delalloc bits and dirty the pages as required. + * We should be called after prepare_pages() which should have locked + * all pages in the range. */ - for (i = 0; i < num_pages; i++) { - set_page_extent_mapped(pages[i]); + for (i = 0; i < num_pages; i++) WARN_ON(!PageLocked(pages[i])); - } return ret; } @@ -1615,11 +1558,84 @@ void btrfs_check_nocow_unlock(struct btrfs_inode *inode) btrfs_drew_write_unlock(&inode->root->snapshot_lock); } +static void update_time_for_write(struct inode *inode) +{ + struct timespec64 now; + + if (IS_NOCMTIME(inode)) + return; + + now = current_time(inode); + if (!timespec64_equal(&inode->i_mtime, &now)) + inode->i_mtime = now; + + if (!timespec64_equal(&inode->i_ctime, &now)) + inode->i_ctime = now; + + if (IS_I_VERSION(inode)) + inode_inc_iversion(inode); +} + +static int btrfs_write_check(struct kiocb *iocb, struct iov_iter *from, + size_t count) +{ + struct file *file = iocb->ki_filp; + struct inode *inode = file_inode(file); + struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + loff_t pos = iocb->ki_pos; + int ret; + loff_t oldsize; + loff_t start_pos; + + if (iocb->ki_flags & IOCB_NOWAIT) { + size_t nocow_bytes = count; + + /* We will allocate space in case nodatacow is not set, so bail */ + if (check_nocow_nolock(BTRFS_I(inode), pos, &nocow_bytes) <= 0) + return -EAGAIN; + /* + * There are holes in the range or parts of the range that must + * be COWed (shared extents, RO block groups, etc), so just bail + * out. + */ + if (nocow_bytes < count) + return -EAGAIN; + } + + current->backing_dev_info = inode_to_bdi(inode); + ret = file_remove_privs(file); + if (ret) + return ret; + + /* + * We reserve space for updating the inode when we reserve space for the + * extent we are going to write, so we will enospc out there. We don't + * need to start yet another transaction to update the inode as we will + * update the inode when we finish writing whatever data we write. + */ + update_time_for_write(inode); + + start_pos = round_down(pos, fs_info->sectorsize); + oldsize = i_size_read(inode); + if (start_pos > oldsize) { + /* Expand hole size to cover write data, preventing empty gap */ + loff_t end_pos = round_up(pos + count, fs_info->sectorsize); + + ret = btrfs_cont_expand(BTRFS_I(inode), oldsize, end_pos); + if (ret) { + current->backing_dev_info = NULL; + return ret; + } + } + + return 0; +} + static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb, struct iov_iter *i) { struct file *file = iocb->ki_filp; - loff_t pos = iocb->ki_pos; + loff_t pos; struct inode *inode = file_inode(file); struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct page **pages = NULL; @@ -1629,17 +1645,37 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb, u64 lockend; size_t num_written = 0; int nrptrs; - int ret = 0; + ssize_t ret; bool only_release_metadata = false; bool force_page_uptodate = false; + loff_t old_isize = i_size_read(inode); + unsigned int ilock_flags = 0; + + if (iocb->ki_flags & IOCB_NOWAIT) + ilock_flags |= BTRFS_ILOCK_TRY; + + ret = btrfs_inode_lock(inode, ilock_flags); + if (ret < 0) + return ret; + + ret = generic_write_checks(iocb, i); + if (ret <= 0) + goto out; + + ret = btrfs_write_check(iocb, i, ret); + if (ret < 0) + goto out; + pos = iocb->ki_pos; nrptrs = min(DIV_ROUND_UP(iov_iter_count(i), PAGE_SIZE), PAGE_SIZE / (sizeof(struct page *))); nrptrs = min(nrptrs, current->nr_dirtied_pause - current->nr_dirtied); nrptrs = max(nrptrs, 8); pages = kmalloc_array(nrptrs, sizeof(struct page *), GFP_KERNEL); - if (!pages) - return -ENOMEM; + if (!pages) { + ret = -ENOMEM; + goto out; + } while (iov_iter_count(i) > 0) { struct extent_state *cached_state = NULL; @@ -1648,8 +1684,7 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb, size_t write_bytes = min(iov_iter_count(i), nrptrs * (size_t)PAGE_SIZE - offset); - size_t num_pages = DIV_ROUND_UP(write_bytes + offset, - PAGE_SIZE); + size_t num_pages; size_t reserve_bytes; size_t dirty_pages; size_t copied; @@ -1657,8 +1692,6 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb, size_t num_sectors; int extents_locked; - WARN_ON(num_pages > nrptrs); - /* * Fault pages before locking them in prepare_pages * to avoid recursive lock @@ -1670,35 +1703,28 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb, only_release_metadata = false; sector_offset = pos & (fs_info->sectorsize - 1); - reserve_bytes = round_up(write_bytes + sector_offset, - fs_info->sectorsize); extent_changeset_release(data_reserved); ret = btrfs_check_data_free_space(BTRFS_I(inode), &data_reserved, pos, write_bytes); if (ret < 0) { + /* + * If we don't have to COW at the offset, reserve + * metadata only. write_bytes may get smaller than + * requested here. + */ if (btrfs_check_nocow_lock(BTRFS_I(inode), pos, - &write_bytes) > 0) { - /* - * For nodata cow case, no need to reserve - * data space. - */ + &write_bytes) > 0) only_release_metadata = true; - /* - * our prealloc extent may be smaller than - * write_bytes, so scale down. - */ - num_pages = DIV_ROUND_UP(write_bytes + offset, - PAGE_SIZE); - reserve_bytes = round_up(write_bytes + - sector_offset, - fs_info->sectorsize); - } else { + else break; - } } + num_pages = DIV_ROUND_UP(write_bytes + offset, PAGE_SIZE); + WARN_ON(num_pages > nrptrs); + reserve_bytes = round_up(write_bytes + sector_offset, + fs_info->sectorsize); WARN_ON(reserve_bytes == 0); ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), reserve_bytes); @@ -1767,8 +1793,7 @@ again: if (num_sectors > dirty_sectors) { /* release everything except the sectors we dirtied */ - release_bytes -= dirty_sectors << - fs_info->sb->s_blocksize_bits; + release_bytes -= dirty_sectors << fs_info->sectorsize_bits; if (only_release_metadata) { btrfs_delalloc_release_metadata(BTRFS_I(inode), release_bytes, true); @@ -1787,10 +1812,9 @@ again: release_bytes = round_up(copied + sector_offset, fs_info->sectorsize); - if (copied > 0) - ret = btrfs_dirty_pages(BTRFS_I(inode), pages, - dirty_pages, pos, copied, - &cached_state); + ret = btrfs_dirty_pages(BTRFS_I(inode), pages, + dirty_pages, pos, copied, + &cached_state, only_release_metadata); /* * If we have not locked the extent range, because the range's @@ -1815,17 +1839,6 @@ again: if (only_release_metadata) btrfs_check_nocow_unlock(BTRFS_I(inode)); - if (only_release_metadata && copied > 0) { - lockstart = round_down(pos, - fs_info->sectorsize); - lockend = round_up(pos + copied, - fs_info->sectorsize) - 1; - - set_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, - lockend, EXTENT_NORESERVE, NULL, - NULL, GFP_NOFS); - } - btrfs_drop_pages(pages, num_pages); cond_resched(); @@ -1852,24 +1865,102 @@ again: } extent_changeset_free(data_reserved); + if (num_written > 0) { + pagecache_isize_extended(inode, old_isize, iocb->ki_pos); + iocb->ki_pos += num_written; + } +out: + btrfs_inode_unlock(inode, ilock_flags); return num_written ? num_written : ret; } -static ssize_t __btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from) +static ssize_t check_direct_IO(struct btrfs_fs_info *fs_info, + const struct iov_iter *iter, loff_t offset) +{ + const u32 blocksize_mask = fs_info->sectorsize - 1; + + if (offset & blocksize_mask) + return -EINVAL; + + if (iov_iter_alignment(iter) & blocksize_mask) + return -EINVAL; + + return 0; +} + +static ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); + struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); loff_t pos; - ssize_t written; + ssize_t written = 0; ssize_t written_buffered; loff_t endbyte; - int err; + ssize_t err; + unsigned int ilock_flags = 0; + struct iomap_dio *dio = NULL; + + if (iocb->ki_flags & IOCB_NOWAIT) + ilock_flags |= BTRFS_ILOCK_TRY; + + /* If the write DIO is within EOF, use a shared lock */ + if (iocb->ki_pos + iov_iter_count(from) <= i_size_read(inode)) + ilock_flags |= BTRFS_ILOCK_SHARED; + +relock: + err = btrfs_inode_lock(inode, ilock_flags); + if (err < 0) + return err; + + err = generic_write_checks(iocb, from); + if (err <= 0) { + btrfs_inode_unlock(inode, ilock_flags); + return err; + } + + err = btrfs_write_check(iocb, from, err); + if (err < 0) { + btrfs_inode_unlock(inode, ilock_flags); + goto out; + } + + pos = iocb->ki_pos; + /* + * Re-check since file size may have changed just before taking the + * lock or pos may have changed because of O_APPEND in generic_write_check() + */ + if ((ilock_flags & BTRFS_ILOCK_SHARED) && + pos + iov_iter_count(from) > i_size_read(inode)) { + btrfs_inode_unlock(inode, ilock_flags); + ilock_flags &= ~BTRFS_ILOCK_SHARED; + goto relock; + } - written = btrfs_direct_IO(iocb, from); + if (check_direct_IO(fs_info, from, pos)) { + btrfs_inode_unlock(inode, ilock_flags); + goto buffered; + } + + dio = __iomap_dio_rw(iocb, from, &btrfs_dio_iomap_ops, &btrfs_dio_ops, + 0); + + btrfs_inode_unlock(inode, ilock_flags); - if (written < 0 || !iov_iter_count(from)) - return written; + if (IS_ERR_OR_NULL(dio)) { + err = PTR_ERR_OR_ZERO(dio); + if (err < 0 && err != -ENOTBLK) + goto out; + } else { + written = iomap_dio_complete(dio); + } + if (written < 0 || !iov_iter_count(from)) { + err = written; + goto out; + } + +buffered: pos = iocb->ki_pos; written_buffered = btrfs_buffered_write(iocb, from); if (written_buffered < 0) { @@ -1895,190 +1986,50 @@ out: return written ? written : err; } -static void update_time_for_write(struct inode *inode) -{ - struct timespec64 now; - - if (IS_NOCMTIME(inode)) - return; - - now = current_time(inode); - if (!timespec64_equal(&inode->i_mtime, &now)) - inode->i_mtime = now; - - if (!timespec64_equal(&inode->i_ctime, &now)) - inode->i_ctime = now; - - if (IS_I_VERSION(inode)) - inode_inc_iversion(inode); -} - static ssize_t btrfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; - struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_root *root = BTRFS_I(inode)->root; - u64 start_pos; - u64 end_pos; + struct btrfs_inode *inode = BTRFS_I(file_inode(file)); ssize_t num_written = 0; const bool sync = iocb->ki_flags & IOCB_DSYNC; - ssize_t err; - loff_t pos; - size_t count; - loff_t oldsize; - int clean_page = 0; - - if (!(iocb->ki_flags & IOCB_DIRECT) && - (iocb->ki_flags & IOCB_NOWAIT)) - return -EOPNOTSUPP; - - if (iocb->ki_flags & IOCB_NOWAIT) { - if (!inode_trylock(inode)) - return -EAGAIN; - } else { - inode_lock(inode); - } - - err = generic_write_checks(iocb, from); - if (err <= 0) { - inode_unlock(inode); - return err; - } - - pos = iocb->ki_pos; - count = iov_iter_count(from); - if (iocb->ki_flags & IOCB_NOWAIT) { - size_t nocow_bytes = count; - - /* - * We will allocate space in case nodatacow is not set, - * so bail - */ - if (check_nocow_nolock(BTRFS_I(inode), pos, &nocow_bytes) - <= 0) { - inode_unlock(inode); - return -EAGAIN; - } - /* - * There are holes in the range or parts of the range that must - * be COWed (shared extents, RO block groups, etc), so just bail - * out. - */ - if (nocow_bytes < count) { - inode_unlock(inode); - return -EAGAIN; - } - } - - current->backing_dev_info = inode_to_bdi(inode); - err = file_remove_privs(file); - if (err) { - inode_unlock(inode); - goto out; - } /* - * If BTRFS flips readonly due to some impossible error - * (fs_info->fs_state now has BTRFS_SUPER_FLAG_ERROR), - * although we have opened a file as writable, we have - * to stop this write operation to ensure FS consistency. + * If the fs flips readonly due to some impossible error, although we + * have opened a file as writable, we have to stop this write operation + * to ensure consistency. */ - if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) { - inode_unlock(inode); - err = -EROFS; - goto out; - } - - /* - * We reserve space for updating the inode when we reserve space for the - * extent we are going to write, so we will enospc out there. We don't - * need to start yet another transaction to update the inode as we will - * update the inode when we finish writing whatever data we write. - */ - update_time_for_write(inode); + if (test_bit(BTRFS_FS_STATE_ERROR, &inode->root->fs_info->fs_state)) + return -EROFS; - start_pos = round_down(pos, fs_info->sectorsize); - oldsize = i_size_read(inode); - if (start_pos > oldsize) { - /* Expand hole size to cover write data, preventing empty gap */ - end_pos = round_up(pos + count, - fs_info->sectorsize); - err = btrfs_cont_expand(inode, oldsize, end_pos); - if (err) { - inode_unlock(inode); - goto out; - } - if (start_pos > round_up(oldsize, fs_info->sectorsize)) - clean_page = 1; - } + if (!(iocb->ki_flags & IOCB_DIRECT) && + (iocb->ki_flags & IOCB_NOWAIT)) + return -EOPNOTSUPP; if (sync) - atomic_inc(&BTRFS_I(inode)->sync_writers); - - if (iocb->ki_flags & IOCB_DIRECT) { - /* - * 1. We must always clear IOCB_DSYNC in order to not deadlock - * in iomap, as it calls generic_write_sync() in this case. - * 2. If we are async, we can call iomap_dio_complete() either - * in - * - * 2.1. A worker thread from the last bio completed. In this - * case we need to mark the btrfs_dio_data that it is - * async in order to call generic_write_sync() properly. - * This is handled by setting BTRFS_DIO_SYNC_STUB in the - * current->journal_info. - * 2.2 The submitter context, because all IO completed - * before we exited iomap_dio_rw(). In this case we can - * just re-set the IOCB_DSYNC on the iocb and we'll do - * the sync below. If our ->end_io() gets called and - * current->journal_info is set, then we know we're in - * our current context and we will clear - * current->journal_info to indicate that we need to - * sync below. - */ - if (sync) { - ASSERT(current->journal_info == NULL); - iocb->ki_flags &= ~IOCB_DSYNC; - current->journal_info = BTRFS_DIO_SYNC_STUB; - } - num_written = __btrfs_direct_write(iocb, from); + atomic_inc(&inode->sync_writers); - /* - * As stated above, we cleared journal_info, so we need to do - * the sync ourselves. - */ - if (sync && current->journal_info == NULL) - iocb->ki_flags |= IOCB_DSYNC; - current->journal_info = NULL; - } else { + if (iocb->ki_flags & IOCB_DIRECT) + num_written = btrfs_direct_write(iocb, from); + else num_written = btrfs_buffered_write(iocb, from); - if (num_written > 0) - iocb->ki_pos = pos + num_written; - if (clean_page) - pagecache_isize_extended(inode, oldsize, - i_size_read(inode)); - } - - inode_unlock(inode); /* * We also have to set last_sub_trans to the current log transid, * otherwise subsequent syncs to a file that's been synced in this * transaction will appear to have already occurred. */ - spin_lock(&BTRFS_I(inode)->lock); - BTRFS_I(inode)->last_sub_trans = root->log_transid; - spin_unlock(&BTRFS_I(inode)->lock); + spin_lock(&inode->lock); + inode->last_sub_trans = inode->root->log_transid; + spin_unlock(&inode->lock); if (num_written > 0) num_written = generic_write_sync(iocb, num_written); if (sync) - atomic_dec(&BTRFS_I(inode)->sync_writers); -out: + atomic_dec(&inode->sync_writers); + current->backing_dev_info = NULL; - return num_written ? num_written : err; + return num_written; } int btrfs_release_file(struct inode *inode, struct file *filp) @@ -2173,13 +2124,6 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) inode_lock(inode); - /* - * We take the dio_sem here because the tree log stuff can race with - * lockless dio writes and get an extent map logged for an extent we - * never waited on. We need it this high up for lockdep reasons. - */ - down_write(&BTRFS_I(inode)->dio_sem); - atomic_inc(&root->log_batch); /* @@ -2210,7 +2154,6 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) */ ret = start_ordered_ops(inode, start, end); if (ret) { - up_write(&BTRFS_I(inode)->dio_sem); inode_unlock(inode); goto out; } @@ -2225,8 +2168,12 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) * commit waits for their completion, to avoid data loss if we fsync, * the current transaction commits before the ordered extents complete * and a power failure happens right after that. + * + * For zoned filesystem, if a write IO uses a ZONE_APPEND command, the + * logical address recorded in the ordered extent may change. We need + * to wait for the IO to stabilize the logical address. */ - if (full_sync) { + if (full_sync || btrfs_is_zoned(fs_info)) { ret = btrfs_wait_ordered_range(inode, start, len); } else { /* @@ -2289,6 +2236,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) ret = PTR_ERR(trans); goto out_release_extents; } + trans->in_fsync = true; ret = btrfs_log_dentry_safe(trans, dentry, &ctx); btrfs_release_log_ctx_extents(&ctx); @@ -2307,7 +2255,6 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) * file again, but that will end up using the synchronization * inside btrfs_sync_log to keep things safe. */ - up_write(&BTRFS_I(inode)->dio_sem); inode_unlock(inode); if (ret != BTRFS_NO_LOG_SYNC) { @@ -2338,7 +2285,6 @@ out: out_release_extents: btrfs_release_log_ctx_extents(&ctx); - up_write(&BTRFS_I(inode)->dio_sem); inode_unlock(inode); goto out; } @@ -2500,13 +2446,13 @@ out: * em->start + em->len > start) * When a hole extent is found, return 1 and modify start/len. */ -static int find_first_non_hole(struct inode *inode, u64 *start, u64 *len) +static int find_first_non_hole(struct btrfs_inode *inode, u64 *start, u64 *len) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = inode->root->fs_info; struct extent_map *em; int ret = 0; - em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, + em = btrfs_get_extent(inode, NULL, 0, round_down(*start, fs_info->sectorsize), round_up(*len, fs_info->sectorsize)); if (IS_ERR(em)) @@ -2566,13 +2512,14 @@ static int btrfs_punch_hole_lock_range(struct inode *inode, } static int btrfs_insert_replace_extent(struct btrfs_trans_handle *trans, - struct inode *inode, + struct btrfs_inode *inode, struct btrfs_path *path, struct btrfs_replace_extent_info *extent_info, - const u64 replace_len) + const u64 replace_len, + const u64 bytes_to_drop) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_fs_info *fs_info = trans->fs_info; + struct btrfs_root *root = inode->root; struct btrfs_file_extent_item *extent; struct extent_buffer *leaf; struct btrfs_key key; @@ -2584,10 +2531,12 @@ static int btrfs_insert_replace_extent(struct btrfs_trans_handle *trans, return 0; if (extent_info->disk_offset == 0 && - btrfs_fs_incompat(fs_info, NO_HOLES)) + btrfs_fs_incompat(fs_info, NO_HOLES)) { + btrfs_update_inode_bytes(inode, 0, bytes_to_drop); return 0; + } - key.objectid = btrfs_ino(BTRFS_I(inode)); + key.objectid = btrfs_ino(inode); key.type = BTRFS_EXTENT_DATA_KEY; key.offset = extent_info->file_offset; ret = btrfs_insert_empty_item(trans, root, path, &key, @@ -2608,23 +2557,25 @@ static int btrfs_insert_replace_extent(struct btrfs_trans_handle *trans, btrfs_mark_buffer_dirty(leaf); btrfs_release_path(path); - ret = btrfs_inode_set_file_extent_range(BTRFS_I(inode), - extent_info->file_offset, replace_len); + ret = btrfs_inode_set_file_extent_range(inode, extent_info->file_offset, + replace_len); if (ret) return ret; /* If it's a hole, nothing more needs to be done. */ - if (extent_info->disk_offset == 0) + if (extent_info->disk_offset == 0) { + btrfs_update_inode_bytes(inode, 0, bytes_to_drop); return 0; + } - inode_add_bytes(inode, replace_len); + btrfs_update_inode_bytes(inode, replace_len, bytes_to_drop); if (extent_info->is_new_extent && extent_info->insertions == 0) { key.objectid = extent_info->disk_offset; key.type = BTRFS_EXTENT_ITEM_KEY; key.offset = extent_info->disk_len; ret = btrfs_alloc_reserved_file_extent(trans, root, - btrfs_ino(BTRFS_I(inode)), + btrfs_ino(inode), extent_info->file_offset, extent_info->qgroup_reserved, &key); @@ -2636,7 +2587,7 @@ static int btrfs_insert_replace_extent(struct btrfs_trans_handle *trans, extent_info->disk_len, 0); ref_offset = extent_info->file_offset - extent_info->data_offset; btrfs_init_data_ref(&ref, root->root_key.objectid, - btrfs_ino(BTRFS_I(inode)), ref_offset); + btrfs_ino(inode), ref_offset); ret = btrfs_inc_extent_ref(trans, &ref); } @@ -2659,6 +2610,7 @@ int btrfs_replace_file_extents(struct inode *inode, struct btrfs_path *path, struct btrfs_replace_extent_info *extent_info, struct btrfs_trans_handle **trans_out) { + struct btrfs_drop_extents_args drop_args = { 0 }; struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); u64 min_size = btrfs_calc_insert_metadata_size(fs_info, 1); u64 ino_size = round_up(inode->i_size, fs_info->sectorsize); @@ -2667,7 +2619,6 @@ int btrfs_replace_file_extents(struct inode *inode, struct btrfs_path *path, struct btrfs_block_rsv *rsv; unsigned int rsv_count; u64 cur_offset; - u64 drop_end; u64 len = end - start; int ret = 0; @@ -2706,10 +2657,16 @@ int btrfs_replace_file_extents(struct inode *inode, struct btrfs_path *path, trans->block_rsv = rsv; cur_offset = start; + drop_args.path = path; + drop_args.end = end + 1; + drop_args.drop_cache = true; while (cur_offset < end) { - ret = __btrfs_drop_extents(trans, root, BTRFS_I(inode), path, - cur_offset, end + 1, &drop_end, - 1, 0, 0, NULL); + drop_args.start = cur_offset; + ret = btrfs_drop_extents(trans, root, BTRFS_I(inode), &drop_args); + /* If we are punching a hole decrement the inode's byte count */ + if (!extent_info) + btrfs_update_inode_bytes(BTRFS_I(inode), 0, + drop_args.bytes_found); if (ret != -ENOSPC) { /* * When cloning we want to avoid transaction aborts when @@ -2726,10 +2683,10 @@ int btrfs_replace_file_extents(struct inode *inode, struct btrfs_path *path, trans->block_rsv = &fs_info->trans_block_rsv; - if (!extent_info && cur_offset < drop_end && + if (!extent_info && cur_offset < drop_args.drop_end && cur_offset < ino_size) { ret = fill_holes(trans, BTRFS_I(inode), path, - cur_offset, drop_end); + cur_offset, drop_args.drop_end); if (ret) { /* * If we failed then we didn't insert our hole @@ -2740,7 +2697,7 @@ int btrfs_replace_file_extents(struct inode *inode, struct btrfs_path *path, btrfs_abort_transaction(trans, ret); break; } - } else if (!extent_info && cur_offset < drop_end) { + } else if (!extent_info && cur_offset < drop_args.drop_end) { /* * We are past the i_size here, but since we didn't * insert holes we need to clear the mapped area so we @@ -2748,7 +2705,8 @@ int btrfs_replace_file_extents(struct inode *inode, struct btrfs_path *path, * file extent is inserted here. */ ret = btrfs_inode_clear_file_extent_range(BTRFS_I(inode), - cur_offset, drop_end - cur_offset); + cur_offset, + drop_args.drop_end - cur_offset); if (ret) { /* * We couldn't clear our area, so we could @@ -2760,11 +2718,14 @@ int btrfs_replace_file_extents(struct inode *inode, struct btrfs_path *path, } } - if (extent_info && drop_end > extent_info->file_offset) { - u64 replace_len = drop_end - extent_info->file_offset; + if (extent_info && + drop_args.drop_end > extent_info->file_offset) { + u64 replace_len = drop_args.drop_end - + extent_info->file_offset; - ret = btrfs_insert_replace_extent(trans, inode, path, - extent_info, replace_len); + ret = btrfs_insert_replace_extent(trans, BTRFS_I(inode), + path, extent_info, replace_len, + drop_args.bytes_found); if (ret) { btrfs_abort_transaction(trans, ret); break; @@ -2774,9 +2735,9 @@ int btrfs_replace_file_extents(struct inode *inode, struct btrfs_path *path, extent_info->file_offset += replace_len; } - cur_offset = drop_end; + cur_offset = drop_args.drop_end; - ret = btrfs_update_inode(trans, root, inode); + ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); if (ret) break; @@ -2796,7 +2757,8 @@ int btrfs_replace_file_extents(struct inode *inode, struct btrfs_path *path, trans->block_rsv = rsv; if (!extent_info) { - ret = find_first_non_hole(inode, &cur_offset, &len); + ret = find_first_non_hole(BTRFS_I(inode), &cur_offset, + &len); if (unlikely(ret < 0)) break; if (ret && !len) { @@ -2833,25 +2795,26 @@ int btrfs_replace_file_extents(struct inode *inode, struct btrfs_path *path, * will not record the existence of the hole region * [existing_hole_start, lockend]. */ - if (drop_end <= end) - drop_end = end + 1; + if (drop_args.drop_end <= end) + drop_args.drop_end = end + 1; /* * Don't insert file hole extent item if it's for a range beyond eof * (because it's useless) or if it represents a 0 bytes range (when * cur_offset == drop_end). */ - if (!extent_info && cur_offset < ino_size && cur_offset < drop_end) { + if (!extent_info && cur_offset < ino_size && + cur_offset < drop_args.drop_end) { ret = fill_holes(trans, BTRFS_I(inode), path, - cur_offset, drop_end); + cur_offset, drop_args.drop_end); if (ret) { /* Same comment as above. */ btrfs_abort_transaction(trans, ret); goto out_trans; } - } else if (!extent_info && cur_offset < drop_end) { + } else if (!extent_info && cur_offset < drop_args.drop_end) { /* See the comment in the loop above for the reasoning here. */ ret = btrfs_inode_clear_file_extent_range(BTRFS_I(inode), - cur_offset, drop_end - cur_offset); + cur_offset, drop_args.drop_end - cur_offset); if (ret) { btrfs_abort_transaction(trans, ret); goto out_trans; @@ -2859,8 +2822,9 @@ int btrfs_replace_file_extents(struct inode *inode, struct btrfs_path *path, } if (extent_info) { - ret = btrfs_insert_replace_extent(trans, inode, path, extent_info, - extent_info->data_len); + ret = btrfs_insert_replace_extent(trans, BTRFS_I(inode), path, + extent_info, extent_info->data_len, + drop_args.bytes_found); if (ret) { btrfs_abort_transaction(trans, ret); goto out_trans; @@ -2906,7 +2870,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) inode_lock(inode); ino_size = round_up(inode->i_size, fs_info->sectorsize); - ret = find_first_non_hole(inode, &offset, &len); + ret = find_first_non_hole(BTRFS_I(inode), &offset, &len); if (ret < 0) goto out_only_mutex; if (ret && !len) { @@ -2931,7 +2895,8 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) if (same_block && len < fs_info->sectorsize) { if (offset < ino_size) { truncated_block = true; - ret = btrfs_truncate_block(inode, offset, len, 0); + ret = btrfs_truncate_block(BTRFS_I(inode), offset, len, + 0); } else { ret = 0; } @@ -2941,7 +2906,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) /* zero back part of the first block */ if (offset < ino_size) { truncated_block = true; - ret = btrfs_truncate_block(inode, offset, 0, 0); + ret = btrfs_truncate_block(BTRFS_I(inode), offset, 0, 0); if (ret) { inode_unlock(inode); return ret; @@ -2956,7 +2921,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) /* after truncate page, check hole again */ len = offset + len - lockstart; offset = lockstart; - ret = find_first_non_hole(inode, &offset, &len); + ret = find_first_non_hole(BTRFS_I(inode), &offset, &len); if (ret < 0) goto out_only_mutex; if (ret && !len) { @@ -2970,14 +2935,14 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) tail_start = lockend + 1; tail_len = offset + len - tail_start; if (tail_len) { - ret = find_first_non_hole(inode, &tail_start, &tail_len); + ret = find_first_non_hole(BTRFS_I(inode), &tail_start, &tail_len); if (unlikely(ret < 0)) goto out_only_mutex; if (!ret) { /* zero the front end of the last page */ if (tail_start + tail_len < ino_size) { truncated_block = true; - ret = btrfs_truncate_block(inode, + ret = btrfs_truncate_block(BTRFS_I(inode), tail_start + tail_len, 0, 1); if (ret) @@ -3011,7 +2976,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) ASSERT(trans != NULL); inode_inc_iversion(inode); inode->i_mtime = inode->i_ctime = current_time(inode); - ret = btrfs_update_inode(trans, root, inode); + ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); updated_inode = true; btrfs_end_transaction(trans); btrfs_btree_balance_dirty(fs_info); @@ -3038,7 +3003,7 @@ out_only_mutex: } else { int ret2; - ret = btrfs_update_inode(trans, root, inode); + ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); ret2 = btrfs_end_transaction(trans); if (!ret) ret = ret2; @@ -3106,8 +3071,8 @@ static int btrfs_fallocate_update_isize(struct inode *inode, inode->i_ctime = current_time(inode); i_size_write(inode, end); - btrfs_inode_safe_disk_i_size_write(inode, 0); - ret = btrfs_update_inode(trans, root, inode); + btrfs_inode_safe_disk_i_size_write(BTRFS_I(inode), 0); + ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); ret2 = btrfs_end_transaction(trans); return ret ? ret : ret2; @@ -3219,7 +3184,8 @@ static int btrfs_zero_range(struct inode *inode, } if (len < sectorsize && em->block_start != EXTENT_MAP_HOLE) { free_extent_map(em); - ret = btrfs_truncate_block(inode, offset, len, 0); + ret = btrfs_truncate_block(BTRFS_I(inode), offset, len, + 0); if (!ret) ret = btrfs_fallocate_update_isize(inode, offset + len, @@ -3250,7 +3216,7 @@ static int btrfs_zero_range(struct inode *inode, alloc_start = round_down(offset, sectorsize); ret = 0; } else if (ret == RANGE_BOUNDARY_WRITTEN_EXTENT) { - ret = btrfs_truncate_block(inode, offset, 0, 0); + ret = btrfs_truncate_block(BTRFS_I(inode), offset, 0, 0); if (ret) goto out; } else { @@ -3267,7 +3233,8 @@ static int btrfs_zero_range(struct inode *inode, alloc_end = round_up(offset + len, sectorsize); ret = 0; } else if (ret == RANGE_BOUNDARY_WRITTEN_EXTENT) { - ret = btrfs_truncate_block(inode, offset + len, 0, 1); + ret = btrfs_truncate_block(BTRFS_I(inode), offset + len, + 0, 1); if (ret) goto out; } else { @@ -3337,6 +3304,10 @@ static long btrfs_fallocate(struct file *file, int mode, int blocksize = btrfs_inode_sectorsize(BTRFS_I(inode)); int ret; + /* Do not allow fallocate in ZONED mode */ + if (btrfs_is_zoned(btrfs_sb(inode->i_sb))) + return -EOPNOTSUPP; + alloc_start = round_down(offset, blocksize); alloc_end = round_up(offset + len, blocksize); cur_offset = alloc_start; @@ -3361,7 +3332,7 @@ static long btrfs_fallocate(struct file *file, int mode, return ret; } - inode_lock(inode); + btrfs_inode_lock(inode, 0); if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size) { ret = inode_newsize_ok(inode, offset + len); @@ -3377,7 +3348,7 @@ static long btrfs_fallocate(struct file *file, int mode, * But that's a minor problem and won't do much harm BTW. */ if (alloc_start > inode->i_size) { - ret = btrfs_cont_expand(inode, i_size_read(inode), + ret = btrfs_cont_expand(BTRFS_I(inode), i_size_read(inode), alloc_start); if (ret) goto out; @@ -3387,7 +3358,7 @@ static long btrfs_fallocate(struct file *file, int mode, * need to zero out the end of the block if i_size lands in the * middle of a block. */ - ret = btrfs_truncate_block(inode, inode->i_size, 0, 0); + ret = btrfs_truncate_block(BTRFS_I(inode), inode->i_size, 0, 0); if (ret) goto out; } @@ -3600,9 +3571,9 @@ static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int whence) return generic_file_llseek(file, offset, whence); case SEEK_DATA: case SEEK_HOLE: - inode_lock_shared(inode); + btrfs_inode_lock(inode, BTRFS_ILOCK_SHARED); offset = find_desired_extent(inode, offset, whence); - inode_unlock_shared(inode); + btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED); break; } @@ -3618,17 +3589,48 @@ static int btrfs_file_open(struct inode *inode, struct file *filp) return generic_file_open(inode, filp); } +static int check_direct_read(struct btrfs_fs_info *fs_info, + const struct iov_iter *iter, loff_t offset) +{ + int ret; + int i, seg; + + ret = check_direct_IO(fs_info, iter, offset); + if (ret < 0) + return ret; + + if (!iter_is_iovec(iter)) + return 0; + + for (seg = 0; seg < iter->nr_segs; seg++) + for (i = seg + 1; i < iter->nr_segs; i++) + if (iter->iov[seg].iov_base == iter->iov[i].iov_base) + return -EINVAL; + return 0; +} + +static ssize_t btrfs_direct_read(struct kiocb *iocb, struct iov_iter *to) +{ + struct inode *inode = file_inode(iocb->ki_filp); + ssize_t ret; + + if (check_direct_read(btrfs_sb(inode->i_sb), to, iocb->ki_pos)) + return 0; + + btrfs_inode_lock(inode, BTRFS_ILOCK_SHARED); + ret = iomap_dio_rw(iocb, to, &btrfs_dio_iomap_ops, &btrfs_dio_ops, 0); + btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED); + return ret; +} + static ssize_t btrfs_file_read_iter(struct kiocb *iocb, struct iov_iter *to) { ssize_t ret = 0; if (iocb->ki_flags & IOCB_DIRECT) { - struct inode *inode = file_inode(iocb->ki_filp); - - inode_lock_shared(inode); - ret = btrfs_direct_IO(iocb, to); - inode_unlock_shared(inode); - if (ret < 0) + ret = btrfs_direct_read(iocb, to); + if (ret < 0 || !iov_iter_count(to) || + iocb->ki_pos >= i_size_read(file_inode(iocb->ki_filp))) return ret; } diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index af0013d3df63..5400294bd271 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -16,7 +16,6 @@ #include "transaction.h" #include "disk-io.h" #include "extent_io.h" -#include "inode-map.h" #include "volumes.h" #include "space-info.h" #include "delalloc-space.h" @@ -33,16 +32,18 @@ struct btrfs_trim_range { struct list_head list; }; -static int count_bitmap_extents(struct btrfs_free_space_ctl *ctl, - struct btrfs_free_space *bitmap_info); static int link_free_space(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *info); static void unlink_free_space(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *info); -static int btrfs_wait_cache_io_root(struct btrfs_root *root, - struct btrfs_trans_handle *trans, - struct btrfs_io_ctl *io_ctl, - struct btrfs_path *path); +static int search_bitmap(struct btrfs_free_space_ctl *ctl, + struct btrfs_free_space *bitmap_info, u64 *offset, + u64 *bytes, bool for_alloc); +static void free_bitmap(struct btrfs_free_space_ctl *ctl, + struct btrfs_free_space *bitmap_info); +static void bitmap_clear_bits(struct btrfs_free_space_ctl *ctl, + struct btrfs_free_space *info, u64 offset, + u64 bytes); static struct inode *__lookup_free_space_inode(struct btrfs_root *root, struct btrfs_path *path, @@ -141,17 +142,15 @@ static int __create_free_space_inode(struct btrfs_root *root, struct btrfs_free_space_header *header; struct btrfs_inode_item *inode_item; struct extent_buffer *leaf; - u64 flags = BTRFS_INODE_NOCOMPRESS | BTRFS_INODE_PREALLOC; + /* We inline CRCs for the free disk space cache */ + const u64 flags = BTRFS_INODE_NOCOMPRESS | BTRFS_INODE_PREALLOC | + BTRFS_INODE_NODATASUM | BTRFS_INODE_NODATACOW; int ret; ret = btrfs_insert_empty_inode(trans, root, path, ino); if (ret) return ret; - /* We inline crc's for the free disk space cache */ - if (ino != BTRFS_FREE_INO_OBJECTID) - flags |= BTRFS_INODE_NODATASUM | BTRFS_INODE_NODATACOW; - leaf = path->nodes[0]; inode_item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_inode_item); @@ -199,7 +198,7 @@ int create_free_space_inode(struct btrfs_trans_handle *trans, int ret; u64 ino; - ret = btrfs_find_free_objectid(trans->fs_info->tree_root, &ino); + ret = btrfs_get_free_objectid(trans->fs_info->tree_root, &ino); if (ret < 0) return ret; @@ -207,6 +206,65 @@ int create_free_space_inode(struct btrfs_trans_handle *trans, ino, block_group->start); } +/* + * inode is an optional sink: if it is NULL, btrfs_remove_free_space_inode + * handles lookup, otherwise it takes ownership and iputs the inode. + * Don't reuse an inode pointer after passing it into this function. + */ +int btrfs_remove_free_space_inode(struct btrfs_trans_handle *trans, + struct inode *inode, + struct btrfs_block_group *block_group) +{ + struct btrfs_path *path; + struct btrfs_key key; + int ret = 0; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + + if (!inode) + inode = lookup_free_space_inode(block_group, path); + if (IS_ERR(inode)) { + if (PTR_ERR(inode) != -ENOENT) + ret = PTR_ERR(inode); + goto out; + } + ret = btrfs_orphan_add(trans, BTRFS_I(inode)); + if (ret) { + btrfs_add_delayed_iput(inode); + goto out; + } + clear_nlink(inode); + /* One for the block groups ref */ + spin_lock(&block_group->lock); + if (block_group->iref) { + block_group->iref = 0; + block_group->inode = NULL; + spin_unlock(&block_group->lock); + iput(inode); + } else { + spin_unlock(&block_group->lock); + } + /* One for the lookup ref */ + btrfs_add_delayed_iput(inode); + + key.objectid = BTRFS_FREE_SPACE_OBJECTID; + key.type = 0; + key.offset = block_group->start; + ret = btrfs_search_slot(trans, trans->fs_info->tree_root, &key, path, + -1, 1); + if (ret) { + if (ret > 0) + ret = 0; + goto out; + } + ret = btrfs_del_item(trans, trans->fs_info->tree_root, path); +out: + btrfs_free_path(path); + return ret; +} + int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *rsv) { @@ -267,12 +325,12 @@ int btrfs_truncate_free_space_cache(struct btrfs_trans_handle *trans, * We skip the throttling logic for free space cache inodes, so we don't * need to check for -EAGAIN. */ - ret = btrfs_truncate_inode_items(trans, root, inode, + ret = btrfs_truncate_inode_items(trans, root, BTRFS_I(inode), 0, BTRFS_EXTENT_DATA_KEY); if (ret) goto fail; - ret = btrfs_update_inode(trans, root, inode); + ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); fail: if (locked) @@ -304,16 +362,11 @@ static int io_ctl_init(struct btrfs_io_ctl *io_ctl, struct inode *inode, int write) { int num_pages; - int check_crcs = 0; num_pages = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); - if (btrfs_ino(BTRFS_I(inode)) != BTRFS_FREE_INO_OBJECTID) - check_crcs = 1; - /* Make sure we can fit our crcs and generation into the first page */ - if (write && check_crcs && - (num_pages * sizeof(u32) + sizeof(u64)) > PAGE_SIZE) + if (write && (num_pages * sizeof(u32) + sizeof(u64)) > PAGE_SIZE) return -ENOSPC; memset(io_ctl, 0, sizeof(struct btrfs_io_ctl)); @@ -324,7 +377,6 @@ static int io_ctl_init(struct btrfs_io_ctl *io_ctl, struct inode *inode, io_ctl->num_pages = num_pages; io_ctl->fs_info = btrfs_sb(inode->i_sb); - io_ctl->check_crcs = check_crcs; io_ctl->inode = inode; return 0; @@ -379,11 +431,22 @@ static int io_ctl_prepare_pages(struct btrfs_io_ctl *io_ctl, bool uptodate) int i; for (i = 0; i < io_ctl->num_pages; i++) { + int ret; + page = find_or_create_page(inode->i_mapping, i, mask); if (!page) { io_ctl_drop_pages(io_ctl); return -ENOMEM; } + + ret = set_page_extent_mapped(page); + if (ret < 0) { + unlock_page(page); + put_page(page); + io_ctl_drop_pages(io_ctl); + return ret; + } + io_ctl->pages[i] = page; if (uptodate && !PageUptodate(page)) { btrfs_readpage(NULL, page); @@ -403,10 +466,8 @@ static int io_ctl_prepare_pages(struct btrfs_io_ctl *io_ctl, bool uptodate) } } - for (i = 0; i < io_ctl->num_pages; i++) { + for (i = 0; i < io_ctl->num_pages; i++) clear_page_dirty_for_io(io_ctl->pages[i]); - set_page_extent_mapped(io_ctl->pages[i]); - } return 0; } @@ -419,13 +480,8 @@ static void io_ctl_set_generation(struct btrfs_io_ctl *io_ctl, u64 generation) * Skip the csum areas. If we don't check crcs then we just have a * 64bit chunk at the front of the first page. */ - if (io_ctl->check_crcs) { - io_ctl->cur += (sizeof(u32) * io_ctl->num_pages); - io_ctl->size -= sizeof(u64) + (sizeof(u32) * io_ctl->num_pages); - } else { - io_ctl->cur += sizeof(u64); - io_ctl->size -= sizeof(u64) * 2; - } + io_ctl->cur += (sizeof(u32) * io_ctl->num_pages); + io_ctl->size -= sizeof(u64) + (sizeof(u32) * io_ctl->num_pages); put_unaligned_le64(generation, io_ctl->cur); io_ctl->cur += sizeof(u64); @@ -439,14 +495,8 @@ static int io_ctl_check_generation(struct btrfs_io_ctl *io_ctl, u64 generation) * Skip the crc area. If we don't check crcs then we just have a 64bit * chunk at the front of the first page. */ - if (io_ctl->check_crcs) { - io_ctl->cur += sizeof(u32) * io_ctl->num_pages; - io_ctl->size -= sizeof(u64) + - (sizeof(u32) * io_ctl->num_pages); - } else { - io_ctl->cur += sizeof(u64); - io_ctl->size -= sizeof(u64) * 2; - } + io_ctl->cur += sizeof(u32) * io_ctl->num_pages; + io_ctl->size -= sizeof(u64) + (sizeof(u32) * io_ctl->num_pages); cache_gen = get_unaligned_le64(io_ctl->cur); if (cache_gen != generation) { @@ -466,11 +516,6 @@ static void io_ctl_set_crc(struct btrfs_io_ctl *io_ctl, int index) u32 crc = ~(u32)0; unsigned offset = 0; - if (!io_ctl->check_crcs) { - io_ctl_unmap_page(io_ctl); - return; - } - if (index == 0) offset = sizeof(u32) * io_ctl->num_pages; @@ -488,11 +533,6 @@ static int io_ctl_check_crc(struct btrfs_io_ctl *io_ctl, int index) u32 crc = ~(u32)0; unsigned offset = 0; - if (!io_ctl->check_crcs) { - io_ctl_map_page(io_ctl, 0); - return 0; - } - if (index == 0) offset = sizeof(u32) * io_ctl->num_pages; @@ -625,42 +665,42 @@ static int io_ctl_read_bitmap(struct btrfs_io_ctl *io_ctl, return 0; } -/* - * Since we attach pinned extents after the fact we can have contiguous sections - * of free space that are split up in entries. This poses a problem with the - * tree logging stuff since it could have allocated across what appears to be 2 - * entries since we would have merged the entries when adding the pinned extents - * back to the free space cache. So run through the space cache that we just - * loaded and merge contiguous entries. This will make the log replay stuff not - * blow up and it will make for nicer allocator behavior. - */ -static void merge_space_tree(struct btrfs_free_space_ctl *ctl) +static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl) { - struct btrfs_free_space *e, *prev = NULL; - struct rb_node *n; + struct btrfs_block_group *block_group = ctl->private; + u64 max_bytes; + u64 bitmap_bytes; + u64 extent_bytes; + u64 size = block_group->length; + u64 bytes_per_bg = BITS_PER_BITMAP * ctl->unit; + u64 max_bitmaps = div64_u64(size + bytes_per_bg - 1, bytes_per_bg); -again: - spin_lock(&ctl->tree_lock); - for (n = rb_first(&ctl->free_space_offset); n; n = rb_next(n)) { - e = rb_entry(n, struct btrfs_free_space, offset_index); - if (!prev) - goto next; - if (e->bitmap || prev->bitmap) - goto next; - if (prev->offset + prev->bytes == e->offset) { - unlink_free_space(ctl, prev); - unlink_free_space(ctl, e); - prev->bytes += e->bytes; - kmem_cache_free(btrfs_free_space_cachep, e); - link_free_space(ctl, prev); - prev = NULL; - spin_unlock(&ctl->tree_lock); - goto again; - } -next: - prev = e; - } - spin_unlock(&ctl->tree_lock); + max_bitmaps = max_t(u64, max_bitmaps, 1); + + ASSERT(ctl->total_bitmaps <= max_bitmaps); + + /* + * We are trying to keep the total amount of memory used per 1GiB of + * space to be MAX_CACHE_BYTES_PER_GIG. However, with a reclamation + * mechanism of pulling extents >= FORCE_EXTENT_THRESHOLD out of + * bitmaps, we may end up using more memory than this. + */ + if (size < SZ_1G) + max_bytes = MAX_CACHE_BYTES_PER_GIG; + else + max_bytes = MAX_CACHE_BYTES_PER_GIG * div_u64(size, SZ_1G); + + bitmap_bytes = ctl->total_bitmaps * ctl->unit; + + /* + * we want the extent entry threshold to always be at most 1/2 the max + * bytes we can have, or whatever is less than that. + */ + extent_bytes = max_bytes - bitmap_bytes; + extent_bytes = min_t(u64, extent_bytes, max_bytes >> 1); + + ctl->extents_thresh = + div_u64(extent_bytes, sizeof(struct btrfs_free_space)); } static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode, @@ -744,8 +784,10 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode, while (num_entries) { e = kmem_cache_zalloc(btrfs_free_space_cachep, GFP_NOFS); - if (!e) + if (!e) { + ret = -ENOMEM; goto free_cache; + } ret = io_ctl_read_entry(&io_ctl, e, &type); if (ret) { @@ -753,17 +795,8 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode, goto free_cache; } - /* - * Sync discard ensures that the free space cache is always - * trimmed. So when reading this in, the state should reflect - * that. We also do this for async as a stop gap for lack of - * persistence. - */ - if (btrfs_test_opt(fs_info, DISCARD_SYNC) || - btrfs_test_opt(fs_info, DISCARD_ASYNC)) - e->trim_state = BTRFS_TRIM_STATE_TRIMMED; - if (!e->bytes) { + ret = -1; kmem_cache_free(btrfs_free_space_cachep, e); goto free_cache; } @@ -784,6 +817,7 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode, e->bitmap = kmem_cache_zalloc( btrfs_free_space_bitmap_cachep, GFP_NOFS); if (!e->bitmap) { + ret = -ENOMEM; kmem_cache_free( btrfs_free_space_cachep, e); goto free_cache; @@ -791,7 +825,7 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode, spin_lock(&ctl->tree_lock); ret = link_free_space(ctl, e); ctl->total_bitmaps++; - ctl->op->recalc_thresholds(ctl); + recalculate_thresholds(ctl); spin_unlock(&ctl->tree_lock); if (ret) { btrfs_err(fs_info, @@ -816,19 +850,11 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode, ret = io_ctl_read_bitmap(&io_ctl, e); if (ret) goto free_cache; - e->bitmap_extents = count_bitmap_extents(ctl, e); - if (!btrfs_free_space_trimmed(e)) { - ctl->discardable_extents[BTRFS_STAT_CURR] += - e->bitmap_extents; - ctl->discardable_bytes[BTRFS_STAT_CURR] += e->bytes; - } } io_ctl_drop_pages(&io_ctl); - merge_space_tree(ctl); ret = 1; out: - btrfs_discard_update_discardable(ctl->private, ctl); io_ctl_free(&io_ctl); return ret; free_cache: @@ -837,10 +863,46 @@ free_cache: goto out; } +static int copy_free_space_cache(struct btrfs_block_group *block_group, + struct btrfs_free_space_ctl *ctl) +{ + struct btrfs_free_space *info; + struct rb_node *n; + int ret = 0; + + while (!ret && (n = rb_first(&ctl->free_space_offset)) != NULL) { + info = rb_entry(n, struct btrfs_free_space, offset_index); + if (!info->bitmap) { + unlink_free_space(ctl, info); + ret = btrfs_add_free_space(block_group, info->offset, + info->bytes); + kmem_cache_free(btrfs_free_space_cachep, info); + } else { + u64 offset = info->offset; + u64 bytes = ctl->unit; + + while (search_bitmap(ctl, info, &offset, &bytes, + false) == 0) { + ret = btrfs_add_free_space(block_group, offset, + bytes); + if (ret) + break; + bitmap_clear_bits(ctl, info, offset, bytes); + offset = info->offset; + bytes = ctl->unit; + } + free_bitmap(ctl, info); + } + cond_resched(); + } + return ret; +} + int load_free_space_cache(struct btrfs_block_group *block_group) { struct btrfs_fs_info *fs_info = block_group->fs_info; struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; + struct btrfs_free_space_ctl tmp_ctl = {}; struct inode *inode; struct btrfs_path *path; int ret = 0; @@ -848,6 +910,13 @@ int load_free_space_cache(struct btrfs_block_group *block_group) u64 used = block_group->used; /* + * Because we could potentially discard our loaded free space, we want + * to load everything into a temporary structure first, and then if it's + * valid copy it all into the actual free space ctl. + */ + btrfs_init_free_space_ctl(block_group, &tmp_ctl); + + /* * If this block group has been marked to be cleared for one reason or * another then we can't trust the on disk cache, so just return. */ @@ -898,19 +967,25 @@ int load_free_space_cache(struct btrfs_block_group *block_group) } spin_unlock(&block_group->lock); - ret = __load_free_space_cache(fs_info->tree_root, inode, ctl, + ret = __load_free_space_cache(fs_info->tree_root, inode, &tmp_ctl, path, block_group->start); btrfs_free_path(path); if (ret <= 0) goto out; - spin_lock(&ctl->tree_lock); - matched = (ctl->free_space == (block_group->length - used - - block_group->bytes_super)); - spin_unlock(&ctl->tree_lock); + matched = (tmp_ctl.free_space == (block_group->length - used - + block_group->bytes_super)); - if (!matched) { - __btrfs_remove_free_space_cache(ctl); + if (matched) { + ret = copy_free_space_cache(block_group, &tmp_ctl); + /* + * ret == 1 means we successfully loaded the free space cache, + * so we need to re-set it here. + */ + if (ret == 0) + ret = 1; + } else { + __btrfs_remove_free_space_cache(&tmp_ctl); btrfs_warn(fs_info, "block group %llu has wrong amount of free space", block_group->start); @@ -929,6 +1004,9 @@ out: block_group->start); } + spin_lock(&ctl->tree_lock); + btrfs_discard_update_discardable(block_group); + spin_unlock(&ctl->tree_lock); iput(inode); return ret; } @@ -1191,7 +1269,7 @@ out: "failed to write free space cache for block group %llu error %d", block_group->start, ret); } - btrfs_update_inode(trans, root, inode); + btrfs_update_inode(trans, root, BTRFS_I(inode)); if (block_group) { /* the dirty list is protected by the dirty_bgs_lock */ @@ -1220,14 +1298,6 @@ out: } -static int btrfs_wait_cache_io_root(struct btrfs_root *root, - struct btrfs_trans_handle *trans, - struct btrfs_io_ctl *io_ctl, - struct btrfs_path *path) -{ - return __btrfs_wait_cache_io(root, trans, NULL, io_ctl, path, 0); -} - int btrfs_wait_cache_io(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path) @@ -1238,11 +1308,14 @@ int btrfs_wait_cache_io(struct btrfs_trans_handle *trans, } /** - * __btrfs_write_out_cache - write out cached info to an inode - * @root - the root the inode belongs to - * @ctl - the free space cache we are going to write out - * @block_group - the block_group for this cache if it belongs to a block_group - * @trans - the trans handle + * Write out cached info to an inode + * + * @root: root the inode belongs to + * @inode: freespace inode we are writing out + * @ctl: free space cache we are going to write out + * @block_group: block_group for this cache if it belongs to a block_group + * @io_ctl: holds context for the io + * @trans: the trans handle * * This function writes out a free space cache struct to disk for quick recovery * on mount. This will return 0 if it was successful in writing the cache out, @@ -1332,7 +1405,7 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode, /* Everything is written out, now we dirty the pages in the file. */ ret = btrfs_dirty_pages(BTRFS_I(inode), io_ctl->pages, io_ctl->num_pages, 0, i_size_read(inode), - &cached_state); + &cached_state, false); if (ret) goto out_nospc; @@ -1381,7 +1454,7 @@ out: invalidate_inode_pages2(inode->i_mapping); BTRFS_I(inode)->generation = 0; } - btrfs_update_inode(trans, root, inode); + btrfs_update_inode(trans, root, BTRFS_I(inode)); if (must_iput) iput(inode); return ret; @@ -1672,44 +1745,6 @@ static int link_free_space(struct btrfs_free_space_ctl *ctl, return ret; } -static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl) -{ - struct btrfs_block_group *block_group = ctl->private; - u64 max_bytes; - u64 bitmap_bytes; - u64 extent_bytes; - u64 size = block_group->length; - u64 bytes_per_bg = BITS_PER_BITMAP * ctl->unit; - u64 max_bitmaps = div64_u64(size + bytes_per_bg - 1, bytes_per_bg); - - max_bitmaps = max_t(u64, max_bitmaps, 1); - - ASSERT(ctl->total_bitmaps <= max_bitmaps); - - /* - * We are trying to keep the total amount of memory used per 1GiB of - * space to be MAX_CACHE_BYTES_PER_GIG. However, with a reclamation - * mechanism of pulling extents >= FORCE_EXTENT_THRESHOLD out of - * bitmaps, we may end up using more memory than this. - */ - if (size < SZ_1G) - max_bytes = MAX_CACHE_BYTES_PER_GIG; - else - max_bytes = MAX_CACHE_BYTES_PER_GIG * div_u64(size, SZ_1G); - - bitmap_bytes = ctl->total_bitmaps * ctl->unit; - - /* - * we want the extent entry threshold to always be at most 1/2 the max - * bytes we can have, or whatever is less than that. - */ - extent_bytes = max_bytes - bitmap_bytes; - extent_bytes = min_t(u64, extent_bytes, max_bytes >> 1); - - ctl->extents_thresh = - div_u64(extent_bytes, sizeof(struct btrfs_free_space)); -} - static inline void __bitmap_clear_bits(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *info, u64 offset, u64 bytes) @@ -1912,29 +1947,6 @@ out: return NULL; } -static int count_bitmap_extents(struct btrfs_free_space_ctl *ctl, - struct btrfs_free_space *bitmap_info) -{ - struct btrfs_block_group *block_group = ctl->private; - u64 bytes = bitmap_info->bytes; - unsigned int rs, re; - int count = 0; - - if (!block_group || !bytes) - return count; - - bitmap_for_each_set_region(bitmap_info->bitmap, rs, re, 0, - BITS_PER_BITMAP) { - bytes -= (rs - re) * ctl->unit; - count++; - - if (!bytes) - break; - } - - return count; -} - static void add_new_bitmap(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *info, u64 offset) { @@ -1944,8 +1956,7 @@ static void add_new_bitmap(struct btrfs_free_space_ctl *ctl, INIT_LIST_HEAD(&info->list); link_free_space(ctl, info); ctl->total_bitmaps++; - - ctl->op->recalc_thresholds(ctl); + recalculate_thresholds(ctl); } static void free_bitmap(struct btrfs_free_space_ctl *ctl, @@ -1967,7 +1978,7 @@ static void free_bitmap(struct btrfs_free_space_ctl *ctl, kmem_cache_free(btrfs_free_space_bitmap_cachep, bitmap_info->bitmap); kmem_cache_free(btrfs_free_space_cachep, bitmap_info); ctl->total_bitmaps--; - ctl->op->recalc_thresholds(ctl); + recalculate_thresholds(ctl); } static noinline int remove_from_bitmap(struct btrfs_free_space_ctl *ctl, @@ -2134,7 +2145,6 @@ static bool use_bitmap(struct btrfs_free_space_ctl *ctl, } static const struct btrfs_free_space_op free_space_op = { - .recalc_thresholds = recalculate_thresholds, .use_bitmap = use_bitmap, }; @@ -2467,6 +2477,8 @@ int __btrfs_add_free_space(struct btrfs_fs_info *fs_info, int ret = 0; u64 filter_bytes = bytes; + ASSERT(!btrfs_is_zoned(fs_info)); + info = kmem_cache_zalloc(btrfs_free_space_cachep, GFP_NOFS); if (!info) return -ENOMEM; @@ -2508,7 +2520,7 @@ link: if (ret) kmem_cache_free(btrfs_free_space_cachep, info); out: - btrfs_discard_update_discardable(block_group, ctl); + btrfs_discard_update_discardable(block_group); spin_unlock(&ctl->tree_lock); if (ret) { @@ -2524,11 +2536,49 @@ out: return ret; } +static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group, + u64 bytenr, u64 size, bool used) +{ + struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; + u64 offset = bytenr - block_group->start; + u64 to_free, to_unusable; + + spin_lock(&ctl->tree_lock); + if (!used) + to_free = size; + else if (offset >= block_group->alloc_offset) + to_free = size; + else if (offset + size <= block_group->alloc_offset) + to_free = 0; + else + to_free = offset + size - block_group->alloc_offset; + to_unusable = size - to_free; + + ctl->free_space += to_free; + block_group->zone_unusable += to_unusable; + spin_unlock(&ctl->tree_lock); + if (!used) { + spin_lock(&block_group->lock); + block_group->alloc_offset -= size; + spin_unlock(&block_group->lock); + } + + /* All the region is now unusable. Mark it as unused and reclaim */ + if (block_group->zone_unusable == block_group->length) + btrfs_mark_bg_unused(block_group); + + return 0; +} + int btrfs_add_free_space(struct btrfs_block_group *block_group, u64 bytenr, u64 size) { enum btrfs_trim_state trim_state = BTRFS_TRIM_STATE_UNTRIMMED; + if (btrfs_is_zoned(block_group->fs_info)) + return __btrfs_add_free_space_zoned(block_group, bytenr, size, + true); + if (btrfs_test_opt(block_group->fs_info, DISCARD_SYNC)) trim_state = BTRFS_TRIM_STATE_TRIMMED; @@ -2537,6 +2587,16 @@ int btrfs_add_free_space(struct btrfs_block_group *block_group, bytenr, size, trim_state); } +int btrfs_add_free_space_unused(struct btrfs_block_group *block_group, + u64 bytenr, u64 size) +{ + if (btrfs_is_zoned(block_group->fs_info)) + return __btrfs_add_free_space_zoned(block_group, bytenr, size, + false); + + return btrfs_add_free_space(block_group, bytenr, size); +} + /* * This is a subtle distinction because when adding free space back in general, * we want it to be added as untrimmed for async. But in the case where we add @@ -2547,6 +2607,10 @@ int btrfs_add_free_space_async_trimmed(struct btrfs_block_group *block_group, { enum btrfs_trim_state trim_state = BTRFS_TRIM_STATE_UNTRIMMED; + if (btrfs_is_zoned(block_group->fs_info)) + return __btrfs_add_free_space_zoned(block_group, bytenr, size, + true); + if (btrfs_test_opt(block_group->fs_info, DISCARD_SYNC) || btrfs_test_opt(block_group->fs_info, DISCARD_ASYNC)) trim_state = BTRFS_TRIM_STATE_TRIMMED; @@ -2564,6 +2628,23 @@ int btrfs_remove_free_space(struct btrfs_block_group *block_group, int ret; bool re_search = false; + if (btrfs_is_zoned(block_group->fs_info)) { + /* + * This can happen with conventional zones when replaying log. + * Since the allocation info of tree-log nodes are not recorded + * to the extent-tree, calculate_alloc_pointer() failed to + * advance the allocation pointer after last allocated tree log + * node blocks. + * + * This function is called from + * btrfs_pin_extent_for_log_replay() when replaying the log. + * Advance the pointer not to overwrite the tree-log nodes. + */ + if (block_group->alloc_offset < offset + bytes) + block_group->alloc_offset = offset + bytes; + return 0; + } + spin_lock(&ctl->tree_lock); again: @@ -2643,7 +2724,7 @@ again: goto again; } out_lock: - btrfs_discard_update_discardable(block_group, ctl); + btrfs_discard_update_discardable(block_group); spin_unlock(&ctl->tree_lock); out: return ret; @@ -2658,6 +2739,16 @@ void btrfs_dump_free_space(struct btrfs_block_group *block_group, struct rb_node *n; int count = 0; + /* + * Zoned btrfs does not use free space tree and cluster. Just print + * out the free space after the allocation offset. + */ + if (btrfs_is_zoned(fs_info)) { + btrfs_info(fs_info, "free space %llu", + block_group->length - block_group->alloc_offset); + return; + } + spin_lock(&ctl->tree_lock); for (n = rb_first(&ctl->free_space_offset); n; n = rb_next(n)) { info = rb_entry(n, struct btrfs_free_space, offset_index); @@ -2674,10 +2765,10 @@ void btrfs_dump_free_space(struct btrfs_block_group *block_group, "%d blocks of free space at or bigger than bytes is", count); } -void btrfs_init_free_space_ctl(struct btrfs_block_group *block_group) +void btrfs_init_free_space_ctl(struct btrfs_block_group *block_group, + struct btrfs_free_space_ctl *ctl) { struct btrfs_fs_info *fs_info = block_group->fs_info; - struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; spin_lock_init(&ctl->tree_lock); ctl->unit = fs_info->sectorsize; @@ -2779,7 +2870,7 @@ void __btrfs_remove_free_space_cache(struct btrfs_free_space_ctl *ctl) spin_lock(&ctl->tree_lock); __btrfs_remove_free_space_cache_locked(ctl); if (ctl->private) - btrfs_discard_update_discardable(ctl->private, ctl); + btrfs_discard_update_discardable(ctl->private); spin_unlock(&ctl->tree_lock); } @@ -2801,7 +2892,7 @@ void btrfs_remove_free_space_cache(struct btrfs_block_group *block_group) cond_resched_lock(&ctl->tree_lock); } __btrfs_remove_free_space_cache_locked(ctl); - btrfs_discard_update_discardable(block_group, ctl); + btrfs_discard_update_discardable(block_group); spin_unlock(&ctl->tree_lock); } @@ -2851,6 +2942,8 @@ u64 btrfs_find_space_for_alloc(struct btrfs_block_group *block_group, u64 align_gap_len = 0; enum btrfs_trim_state align_gap_trim_state = BTRFS_TRIM_STATE_UNTRIMMED; + ASSERT(!btrfs_is_zoned(block_group->fs_info)); + spin_lock(&ctl->tree_lock); entry = find_free_space(ctl, &offset, &bytes_search, block_group->full_stripe_len, max_extent_size); @@ -2885,7 +2978,7 @@ u64 btrfs_find_space_for_alloc(struct btrfs_block_group *block_group, link_free_space(ctl, entry); } out: - btrfs_discard_update_discardable(block_group, ctl); + btrfs_discard_update_discardable(block_group); spin_unlock(&ctl->tree_lock); if (align_gap_len) @@ -2982,6 +3075,8 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group *block_group, struct rb_node *node; u64 ret = 0; + ASSERT(!btrfs_is_zoned(block_group->fs_info)); + spin_lock(&cluster->lock); if (bytes > cluster->max_size) goto out; @@ -3054,7 +3149,7 @@ out: kmem_cache_free(btrfs_free_space_bitmap_cachep, entry->bitmap); ctl->total_bitmaps--; - ctl->op->recalc_thresholds(ctl); + recalculate_thresholds(ctl); } else if (!btrfs_free_space_trimmed(entry)) { ctl->discardable_extents[BTRFS_STAT_CURR]--; } @@ -3758,6 +3853,8 @@ int btrfs_trim_block_group(struct btrfs_block_group *block_group, int ret; u64 rem = 0; + ASSERT(!btrfs_is_zoned(block_group->fs_info)); + *trimmed = 0; spin_lock(&block_group->lock); @@ -3828,166 +3925,62 @@ int btrfs_trim_block_group_bitmaps(struct btrfs_block_group *block_group, return ret; } -/* - * Find the left-most item in the cache tree, and then return the - * smallest inode number in the item. - * - * Note: the returned inode number may not be the smallest one in - * the tree, if the left-most item is a bitmap. - */ -u64 btrfs_find_ino_for_alloc(struct btrfs_root *fs_root) +bool btrfs_free_space_cache_v1_active(struct btrfs_fs_info *fs_info) { - struct btrfs_free_space_ctl *ctl = fs_root->free_ino_ctl; - struct btrfs_free_space *entry = NULL; - u64 ino = 0; - - spin_lock(&ctl->tree_lock); - - if (RB_EMPTY_ROOT(&ctl->free_space_offset)) - goto out; - - entry = rb_entry(rb_first(&ctl->free_space_offset), - struct btrfs_free_space, offset_index); - - if (!entry->bitmap) { - ino = entry->offset; - - unlink_free_space(ctl, entry); - entry->offset++; - entry->bytes--; - if (!entry->bytes) - kmem_cache_free(btrfs_free_space_cachep, entry); - else - link_free_space(ctl, entry); - } else { - u64 offset = 0; - u64 count = 1; - int ret; - - ret = search_bitmap(ctl, entry, &offset, &count, true); - /* Logic error; Should be empty if it can't find anything */ - ASSERT(!ret); - - ino = offset; - bitmap_clear_bits(ctl, entry, offset, 1); - if (entry->bytes == 0) - free_bitmap(ctl, entry); - } -out: - spin_unlock(&ctl->tree_lock); - - return ino; + return btrfs_super_cache_generation(fs_info->super_copy); } -struct inode *lookup_free_ino_inode(struct btrfs_root *root, - struct btrfs_path *path) +static int cleanup_free_space_cache_v1(struct btrfs_fs_info *fs_info, + struct btrfs_trans_handle *trans) { - struct inode *inode = NULL; - - spin_lock(&root->ino_cache_lock); - if (root->ino_cache_inode) - inode = igrab(root->ino_cache_inode); - spin_unlock(&root->ino_cache_lock); - if (inode) - return inode; - - inode = __lookup_free_space_inode(root, path, 0); - if (IS_ERR(inode)) - return inode; - - spin_lock(&root->ino_cache_lock); - if (!btrfs_fs_closing(root->fs_info)) - root->ino_cache_inode = igrab(inode); - spin_unlock(&root->ino_cache_lock); - - return inode; -} - -int create_free_ino_inode(struct btrfs_root *root, - struct btrfs_trans_handle *trans, - struct btrfs_path *path) -{ - return __create_free_space_inode(root, trans, path, - BTRFS_FREE_INO_OBJECTID, 0); -} - -int load_free_ino_cache(struct btrfs_fs_info *fs_info, struct btrfs_root *root) -{ - struct btrfs_free_space_ctl *ctl = root->free_ino_ctl; - struct btrfs_path *path; - struct inode *inode; - int ret = 0; - u64 root_gen = btrfs_root_generation(&root->root_item); - - if (!btrfs_test_opt(fs_info, INODE_MAP_CACHE)) - return 0; - - /* - * If we're unmounting then just return, since this does a search on the - * normal root and not the commit root and we could deadlock. - */ - if (btrfs_fs_closing(fs_info)) - return 0; - - path = btrfs_alloc_path(); - if (!path) - return 0; - - inode = lookup_free_ino_inode(root, path); - if (IS_ERR(inode)) - goto out; - - if (root_gen != BTRFS_I(inode)->generation) - goto out_put; + struct btrfs_block_group *block_group; + struct rb_node *node; + int ret; - ret = __load_free_space_cache(root, inode, ctl, path, 0); + btrfs_info(fs_info, "cleaning free space cache v1"); - if (ret < 0) - btrfs_err(fs_info, - "failed to load free ino cache for root %llu", - root->root_key.objectid); -out_put: - iput(inode); + node = rb_first(&fs_info->block_group_cache_tree); + while (node) { + block_group = rb_entry(node, struct btrfs_block_group, cache_node); + ret = btrfs_remove_free_space_inode(trans, NULL, block_group); + if (ret) + goto out; + node = rb_next(node); + } out: - btrfs_free_path(path); return ret; } -int btrfs_write_out_ino_cache(struct btrfs_root *root, - struct btrfs_trans_handle *trans, - struct btrfs_path *path, - struct inode *inode) +int btrfs_set_free_space_cache_v1_active(struct btrfs_fs_info *fs_info, bool active) { - struct btrfs_fs_info *fs_info = root->fs_info; - struct btrfs_free_space_ctl *ctl = root->free_ino_ctl; + struct btrfs_trans_handle *trans; int ret; - struct btrfs_io_ctl io_ctl; - bool release_metadata = true; - if (!btrfs_test_opt(fs_info, INODE_MAP_CACHE)) - return 0; + /* + * update_super_roots will appropriately set or unset + * super_copy->cache_generation based on SPACE_CACHE and + * BTRFS_FS_CLEANUP_SPACE_CACHE_V1. For this reason, we need a + * transaction commit whether we are enabling space cache v1 and don't + * have any other work to do, or are disabling it and removing free + * space inodes. + */ + trans = btrfs_start_transaction(fs_info->tree_root, 0); + if (IS_ERR(trans)) + return PTR_ERR(trans); - memset(&io_ctl, 0, sizeof(io_ctl)); - ret = __btrfs_write_out_cache(root, inode, ctl, NULL, &io_ctl, trans); - if (!ret) { - /* - * At this point writepages() didn't error out, so our metadata - * reservation is released when the writeback finishes, at - * inode.c:btrfs_finish_ordered_io(), regardless of it finishing - * with or without an error. - */ - release_metadata = false; - ret = btrfs_wait_cache_io_root(root, trans, &io_ctl, path); + if (!active) { + set_bit(BTRFS_FS_CLEANUP_SPACE_CACHE_V1, &fs_info->flags); + ret = cleanup_free_space_cache_v1(fs_info, trans); + if (ret) { + btrfs_abort_transaction(trans, ret); + btrfs_end_transaction(trans); + goto out; + } } - if (ret) { - if (release_metadata) - btrfs_delalloc_release_metadata(BTRFS_I(inode), - inode->i_size, true); - btrfs_debug(fs_info, - "failed to write free ino cache for root %llu error %d", - root->root_key.objectid, ret); - } + ret = btrfs_commit_transaction(trans); +out: + clear_bit(BTRFS_FS_CLEANUP_SPACE_CACHE_V1, &fs_info->flags); return ret; } diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h index e3d5e0ad8f8e..1f23088d43f9 100644 --- a/fs/btrfs/free-space-cache.h +++ b/fs/btrfs/free-space-cache.h @@ -60,7 +60,6 @@ struct btrfs_free_space_ctl { }; struct btrfs_free_space_op { - void (*recalc_thresholds)(struct btrfs_free_space_ctl *ctl); bool (*use_bitmap)(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *info); }; @@ -76,7 +75,6 @@ struct btrfs_io_ctl { int num_pages; int entries; int bitmaps; - unsigned check_crcs:1; }; struct inode *lookup_free_space_inode(struct btrfs_block_group *block_group, @@ -84,6 +82,9 @@ struct inode *lookup_free_space_inode(struct btrfs_block_group *block_group, int create_free_space_inode(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path); +int btrfs_remove_free_space_inode(struct btrfs_trans_handle *trans, + struct inode *inode, + struct btrfs_block_group *block_group); int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *rsv); @@ -97,25 +98,17 @@ int btrfs_wait_cache_io(struct btrfs_trans_handle *trans, int btrfs_write_out_cache(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path); -struct inode *lookup_free_ino_inode(struct btrfs_root *root, - struct btrfs_path *path); -int create_free_ino_inode(struct btrfs_root *root, - struct btrfs_trans_handle *trans, - struct btrfs_path *path); -int load_free_ino_cache(struct btrfs_fs_info *fs_info, - struct btrfs_root *root); -int btrfs_write_out_ino_cache(struct btrfs_root *root, - struct btrfs_trans_handle *trans, - struct btrfs_path *path, - struct inode *inode); -void btrfs_init_free_space_ctl(struct btrfs_block_group *block_group); +void btrfs_init_free_space_ctl(struct btrfs_block_group *block_group, + struct btrfs_free_space_ctl *ctl); int __btrfs_add_free_space(struct btrfs_fs_info *fs_info, struct btrfs_free_space_ctl *ctl, u64 bytenr, u64 size, enum btrfs_trim_state trim_state); int btrfs_add_free_space(struct btrfs_block_group *block_group, u64 bytenr, u64 size); +int btrfs_add_free_space_unused(struct btrfs_block_group *block_group, + u64 bytenr, u64 size); int btrfs_add_free_space_async_trimmed(struct btrfs_block_group *block_group, u64 bytenr, u64 size); int btrfs_remove_free_space(struct btrfs_block_group *block_group, @@ -126,7 +119,6 @@ bool btrfs_is_free_space_trimmed(struct btrfs_block_group *block_group); u64 btrfs_find_space_for_alloc(struct btrfs_block_group *block_group, u64 offset, u64 bytes, u64 empty_size, u64 *max_extent_size); -u64 btrfs_find_ino_for_alloc(struct btrfs_root *fs_root); void btrfs_dump_free_space(struct btrfs_block_group *block_group, u64 bytes); int btrfs_find_space_cluster(struct btrfs_block_group *block_group, @@ -148,6 +140,8 @@ int btrfs_trim_block_group_bitmaps(struct btrfs_block_group *block_group, u64 *trimmed, u64 start, u64 end, u64 minlen, u64 maxlen, bool async); +bool btrfs_free_space_cache_v1_active(struct btrfs_fs_info *fs_info); +int btrfs_set_free_space_cache_v1_active(struct btrfs_fs_info *fs_info, bool active); /* Support functions for running our sanity tests */ #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS int test_add_free_space_entry(struct btrfs_block_group *cache, diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index 6b9faf3b0e96..a33bca94d133 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -136,9 +136,10 @@ static int btrfs_search_prev_slot(struct btrfs_trans_handle *trans, return 0; } -static inline u32 free_space_bitmap_size(u64 size, u32 sectorsize) +static inline u32 free_space_bitmap_size(const struct btrfs_fs_info *fs_info, + u64 size) { - return DIV_ROUND_UP((u32)div_u64(size, sectorsize), BITS_PER_BYTE); + return DIV_ROUND_UP(size >> fs_info->sectorsize_bits, BITS_PER_BYTE); } static unsigned long *alloc_bitmap(u32 bitmap_size) @@ -200,8 +201,7 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans, int done = 0, nr; int ret; - bitmap_size = free_space_bitmap_size(block_group->length, - fs_info->sectorsize); + bitmap_size = free_space_bitmap_size(fs_info, block_group->length); bitmap = alloc_bitmap(bitmap_size); if (!bitmap) { ret = -ENOMEM; @@ -290,8 +290,7 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans, u32 data_size; extent_size = min(end - i, bitmap_range); - data_size = free_space_bitmap_size(extent_size, - fs_info->sectorsize); + data_size = free_space_bitmap_size(fs_info, extent_size); key.objectid = i; key.type = BTRFS_FREE_SPACE_BITMAP_KEY; @@ -339,8 +338,7 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans, int done = 0, nr; int ret; - bitmap_size = free_space_bitmap_size(block_group->length, - fs_info->sectorsize); + bitmap_size = free_space_bitmap_size(fs_info, block_group->length); bitmap = alloc_bitmap(bitmap_size); if (!bitmap) { ret = -ENOMEM; @@ -383,8 +381,8 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans, fs_info->sectorsize * BITS_PER_BYTE); bitmap_cursor = ((char *)bitmap) + bitmap_pos; - data_size = free_space_bitmap_size(found_key.offset, - fs_info->sectorsize); + data_size = free_space_bitmap_size(fs_info, + found_key.offset); ptr = btrfs_item_ptr_offset(leaf, path->slots[0] - 1); read_extent_buffer(leaf, bitmap_cursor, ptr, @@ -416,7 +414,7 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans, btrfs_mark_buffer_dirty(leaf); btrfs_release_path(path); - nrbits = div_u64(block_group->length, block_group->fs_info->sectorsize); + nrbits = block_group->length >> block_group->fs_info->sectorsize_bits; start_bit = find_next_bit_le(bitmap, nrbits, 0); while (start_bit < nrbits) { @@ -540,8 +538,8 @@ static void free_space_set_bits(struct btrfs_block_group *block_group, end = found_end; ptr = btrfs_item_ptr_offset(leaf, path->slots[0]); - first = div_u64(*start - found_start, fs_info->sectorsize); - last = div_u64(end - found_start, fs_info->sectorsize); + first = (*start - found_start) >> fs_info->sectorsize_bits; + last = (end - found_start) >> fs_info->sectorsize_bits; if (bit) extent_buffer_bitmap_set(leaf, ptr, first, last - first); else @@ -1152,6 +1150,7 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info) return PTR_ERR(trans); set_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); + set_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags); free_space_root = btrfs_create_tree(trans, BTRFS_FREE_SPACE_TREE_OBJECTID); if (IS_ERR(free_space_root)) { @@ -1173,11 +1172,18 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info) btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE); btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID); clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); + ret = btrfs_commit_transaction(trans); - return btrfs_commit_transaction(trans); + /* + * Now that we've committed the transaction any reading of our commit + * root will be safe, so we can cache from the free space tree now. + */ + clear_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags); + return ret; abort: clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); + clear_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags); btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); return ret; @@ -1195,8 +1201,6 @@ static int clear_free_space_tree(struct btrfs_trans_handle *trans, if (!path) return -ENOMEM; - path->leave_spinning = 1; - key.objectid = 0; key.type = 0; key.offset = 0; diff --git a/fs/btrfs/inode-item.c b/fs/btrfs/inode-item.c index 668701832845..37f36ffdaf6b 100644 --- a/fs/btrfs/inode-item.c +++ b/fs/btrfs/inode-item.c @@ -119,8 +119,6 @@ static int btrfs_del_inode_extref(struct btrfs_trans_handle *trans, if (!path) return -ENOMEM; - path->leave_spinning = 1; - ret = btrfs_search_slot(trans, root, &key, path, -1, 1); if (ret > 0) ret = -ENOENT; @@ -193,8 +191,6 @@ int btrfs_del_inode_ref(struct btrfs_trans_handle *trans, if (!path) return -ENOMEM; - path->leave_spinning = 1; - ret = btrfs_search_slot(trans, root, &key, path, -1, 1); if (ret > 0) { ret = -ENOENT; @@ -270,7 +266,6 @@ static int btrfs_insert_inode_extref(struct btrfs_trans_handle *trans, if (!path) return -ENOMEM; - path->leave_spinning = 1; ret = btrfs_insert_empty_item(trans, root, path, &key, ins_len); if (ret == -EEXIST) { @@ -327,7 +322,6 @@ int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans, if (!path) return -ENOMEM; - path->leave_spinning = 1; path->skip_release_on_error = 1; ret = btrfs_insert_empty_item(trans, root, path, &key, ins_len); diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c deleted file mode 100644 index 76d2e43817ea..000000000000 --- a/fs/btrfs/inode-map.c +++ /dev/null @@ -1,582 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (C) 2007 Oracle. All rights reserved. - */ - -#include <linux/kthread.h> -#include <linux/pagemap.h> - -#include "ctree.h" -#include "disk-io.h" -#include "free-space-cache.h" -#include "inode-map.h" -#include "transaction.h" -#include "delalloc-space.h" - -static void fail_caching_thread(struct btrfs_root *root) -{ - struct btrfs_fs_info *fs_info = root->fs_info; - - btrfs_warn(fs_info, "failed to start inode caching task"); - btrfs_clear_pending_and_info(fs_info, INODE_MAP_CACHE, - "disabling inode map caching"); - spin_lock(&root->ino_cache_lock); - root->ino_cache_state = BTRFS_CACHE_ERROR; - spin_unlock(&root->ino_cache_lock); - wake_up(&root->ino_cache_wait); -} - -static int caching_kthread(void *data) -{ - struct btrfs_root *root = data; - struct btrfs_fs_info *fs_info = root->fs_info; - struct btrfs_free_space_ctl *ctl = root->free_ino_ctl; - struct btrfs_key key; - struct btrfs_path *path; - struct extent_buffer *leaf; - u64 last = (u64)-1; - int slot; - int ret; - - if (!btrfs_test_opt(fs_info, INODE_MAP_CACHE)) - return 0; - - path = btrfs_alloc_path(); - if (!path) { - fail_caching_thread(root); - return -ENOMEM; - } - - /* Since the commit root is read-only, we can safely skip locking. */ - path->skip_locking = 1; - path->search_commit_root = 1; - path->reada = READA_FORWARD; - - key.objectid = BTRFS_FIRST_FREE_OBJECTID; - key.offset = 0; - key.type = BTRFS_INODE_ITEM_KEY; -again: - /* need to make sure the commit_root doesn't disappear */ - down_read(&fs_info->commit_root_sem); - - ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); - if (ret < 0) - goto out; - - while (1) { - if (btrfs_fs_closing(fs_info)) - goto out; - - leaf = path->nodes[0]; - slot = path->slots[0]; - if (slot >= btrfs_header_nritems(leaf)) { - ret = btrfs_next_leaf(root, path); - if (ret < 0) - goto out; - else if (ret > 0) - break; - - if (need_resched() || - btrfs_transaction_in_commit(fs_info)) { - leaf = path->nodes[0]; - - if (WARN_ON(btrfs_header_nritems(leaf) == 0)) - break; - - /* - * Save the key so we can advances forward - * in the next search. - */ - btrfs_item_key_to_cpu(leaf, &key, 0); - btrfs_release_path(path); - root->ino_cache_progress = last; - up_read(&fs_info->commit_root_sem); - schedule_timeout(1); - goto again; - } else - continue; - } - - btrfs_item_key_to_cpu(leaf, &key, slot); - - if (key.type != BTRFS_INODE_ITEM_KEY) - goto next; - - if (key.objectid >= root->highest_objectid) - break; - - if (last != (u64)-1 && last + 1 != key.objectid) { - __btrfs_add_free_space(fs_info, ctl, last + 1, - key.objectid - last - 1, 0); - wake_up(&root->ino_cache_wait); - } - - last = key.objectid; -next: - path->slots[0]++; - } - - if (last < root->highest_objectid - 1) { - __btrfs_add_free_space(fs_info, ctl, last + 1, - root->highest_objectid - last - 1, 0); - } - - spin_lock(&root->ino_cache_lock); - root->ino_cache_state = BTRFS_CACHE_FINISHED; - spin_unlock(&root->ino_cache_lock); - - root->ino_cache_progress = (u64)-1; - btrfs_unpin_free_ino(root); -out: - wake_up(&root->ino_cache_wait); - up_read(&fs_info->commit_root_sem); - - btrfs_free_path(path); - - return ret; -} - -static void start_caching(struct btrfs_root *root) -{ - struct btrfs_fs_info *fs_info = root->fs_info; - struct btrfs_free_space_ctl *ctl = root->free_ino_ctl; - struct task_struct *tsk; - int ret; - u64 objectid; - - if (!btrfs_test_opt(fs_info, INODE_MAP_CACHE)) - return; - - spin_lock(&root->ino_cache_lock); - if (root->ino_cache_state != BTRFS_CACHE_NO) { - spin_unlock(&root->ino_cache_lock); - return; - } - - root->ino_cache_state = BTRFS_CACHE_STARTED; - spin_unlock(&root->ino_cache_lock); - - ret = load_free_ino_cache(fs_info, root); - if (ret == 1) { - spin_lock(&root->ino_cache_lock); - root->ino_cache_state = BTRFS_CACHE_FINISHED; - spin_unlock(&root->ino_cache_lock); - wake_up(&root->ino_cache_wait); - return; - } - - /* - * It can be quite time-consuming to fill the cache by searching - * through the extent tree, and this can keep ino allocation path - * waiting. Therefore at start we quickly find out the highest - * inode number and we know we can use inode numbers which fall in - * [highest_ino + 1, BTRFS_LAST_FREE_OBJECTID]. - */ - ret = btrfs_find_free_objectid(root, &objectid); - if (!ret && objectid <= BTRFS_LAST_FREE_OBJECTID) { - __btrfs_add_free_space(fs_info, ctl, objectid, - BTRFS_LAST_FREE_OBJECTID - objectid + 1, - 0); - wake_up(&root->ino_cache_wait); - } - - tsk = kthread_run(caching_kthread, root, "btrfs-ino-cache-%llu", - root->root_key.objectid); - if (IS_ERR(tsk)) - fail_caching_thread(root); -} - -int btrfs_find_free_ino(struct btrfs_root *root, u64 *objectid) -{ - if (!btrfs_test_opt(root->fs_info, INODE_MAP_CACHE)) - return btrfs_find_free_objectid(root, objectid); - -again: - *objectid = btrfs_find_ino_for_alloc(root); - - if (*objectid != 0) - return 0; - - start_caching(root); - - wait_event(root->ino_cache_wait, - root->ino_cache_state == BTRFS_CACHE_FINISHED || - root->ino_cache_state == BTRFS_CACHE_ERROR || - root->free_ino_ctl->free_space > 0); - - if (root->ino_cache_state == BTRFS_CACHE_FINISHED && - root->free_ino_ctl->free_space == 0) - return -ENOSPC; - else if (root->ino_cache_state == BTRFS_CACHE_ERROR) - return btrfs_find_free_objectid(root, objectid); - else - goto again; -} - -void btrfs_return_ino(struct btrfs_root *root, u64 objectid) -{ - struct btrfs_fs_info *fs_info = root->fs_info; - struct btrfs_free_space_ctl *pinned = root->free_ino_pinned; - - if (!btrfs_test_opt(fs_info, INODE_MAP_CACHE)) - return; -again: - if (root->ino_cache_state == BTRFS_CACHE_FINISHED) { - __btrfs_add_free_space(fs_info, pinned, objectid, 1, 0); - } else { - down_write(&fs_info->commit_root_sem); - spin_lock(&root->ino_cache_lock); - if (root->ino_cache_state == BTRFS_CACHE_FINISHED) { - spin_unlock(&root->ino_cache_lock); - up_write(&fs_info->commit_root_sem); - goto again; - } - spin_unlock(&root->ino_cache_lock); - - start_caching(root); - - __btrfs_add_free_space(fs_info, pinned, objectid, 1, 0); - - up_write(&fs_info->commit_root_sem); - } -} - -/* - * When a transaction is committed, we'll move those inode numbers which are - * smaller than root->ino_cache_progress from pinned tree to free_ino tree, and - * others will just be dropped, because the commit root we were searching has - * changed. - * - * Must be called with root->fs_info->commit_root_sem held - */ -void btrfs_unpin_free_ino(struct btrfs_root *root) -{ - struct btrfs_free_space_ctl *ctl = root->free_ino_ctl; - struct rb_root *rbroot = &root->free_ino_pinned->free_space_offset; - spinlock_t *rbroot_lock = &root->free_ino_pinned->tree_lock; - struct btrfs_free_space *info; - struct rb_node *n; - u64 count; - - if (!btrfs_test_opt(root->fs_info, INODE_MAP_CACHE)) - return; - - while (1) { - spin_lock(rbroot_lock); - n = rb_first(rbroot); - if (!n) { - spin_unlock(rbroot_lock); - break; - } - - info = rb_entry(n, struct btrfs_free_space, offset_index); - BUG_ON(info->bitmap); /* Logic error */ - - if (info->offset > root->ino_cache_progress) - count = 0; - else - count = min(root->ino_cache_progress - info->offset + 1, - info->bytes); - - rb_erase(&info->offset_index, rbroot); - spin_unlock(rbroot_lock); - if (count) - __btrfs_add_free_space(root->fs_info, ctl, - info->offset, count, 0); - kmem_cache_free(btrfs_free_space_cachep, info); - } -} - -#define INIT_THRESHOLD ((SZ_32K / 2) / sizeof(struct btrfs_free_space)) -#define INODES_PER_BITMAP (PAGE_SIZE * 8) - -/* - * The goal is to keep the memory used by the free_ino tree won't - * exceed the memory if we use bitmaps only. - */ -static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl) -{ - struct btrfs_free_space *info; - struct rb_node *n; - int max_ino; - int max_bitmaps; - - n = rb_last(&ctl->free_space_offset); - if (!n) { - ctl->extents_thresh = INIT_THRESHOLD; - return; - } - info = rb_entry(n, struct btrfs_free_space, offset_index); - - /* - * Find the maximum inode number in the filesystem. Note we - * ignore the fact that this can be a bitmap, because we are - * not doing precise calculation. - */ - max_ino = info->bytes - 1; - - max_bitmaps = ALIGN(max_ino, INODES_PER_BITMAP) / INODES_PER_BITMAP; - if (max_bitmaps <= ctl->total_bitmaps) { - ctl->extents_thresh = 0; - return; - } - - ctl->extents_thresh = (max_bitmaps - ctl->total_bitmaps) * - PAGE_SIZE / sizeof(*info); -} - -/* - * We don't fall back to bitmap, if we are below the extents threshold - * or this chunk of inode numbers is a big one. - */ -static bool use_bitmap(struct btrfs_free_space_ctl *ctl, - struct btrfs_free_space *info) -{ - if (ctl->free_extents < ctl->extents_thresh || - info->bytes > INODES_PER_BITMAP / 10) - return false; - - return true; -} - -static const struct btrfs_free_space_op free_ino_op = { - .recalc_thresholds = recalculate_thresholds, - .use_bitmap = use_bitmap, -}; - -static void pinned_recalc_thresholds(struct btrfs_free_space_ctl *ctl) -{ -} - -static bool pinned_use_bitmap(struct btrfs_free_space_ctl *ctl, - struct btrfs_free_space *info) -{ - /* - * We always use extents for two reasons: - * - * - The pinned tree is only used during the process of caching - * work. - * - Make code simpler. See btrfs_unpin_free_ino(). - */ - return false; -} - -static const struct btrfs_free_space_op pinned_free_ino_op = { - .recalc_thresholds = pinned_recalc_thresholds, - .use_bitmap = pinned_use_bitmap, -}; - -void btrfs_init_free_ino_ctl(struct btrfs_root *root) -{ - struct btrfs_free_space_ctl *ctl = root->free_ino_ctl; - struct btrfs_free_space_ctl *pinned = root->free_ino_pinned; - - spin_lock_init(&ctl->tree_lock); - ctl->unit = 1; - ctl->start = 0; - ctl->private = NULL; - ctl->op = &free_ino_op; - INIT_LIST_HEAD(&ctl->trimming_ranges); - mutex_init(&ctl->cache_writeout_mutex); - - /* - * Initially we allow to use 16K of ram to cache chunks of - * inode numbers before we resort to bitmaps. This is somewhat - * arbitrary, but it will be adjusted in runtime. - */ - ctl->extents_thresh = INIT_THRESHOLD; - - spin_lock_init(&pinned->tree_lock); - pinned->unit = 1; - pinned->start = 0; - pinned->private = NULL; - pinned->extents_thresh = 0; - pinned->op = &pinned_free_ino_op; -} - -int btrfs_save_ino_cache(struct btrfs_root *root, - struct btrfs_trans_handle *trans) -{ - struct btrfs_fs_info *fs_info = root->fs_info; - struct btrfs_free_space_ctl *ctl = root->free_ino_ctl; - struct btrfs_path *path; - struct inode *inode; - struct btrfs_block_rsv *rsv; - struct extent_changeset *data_reserved = NULL; - u64 num_bytes; - u64 alloc_hint = 0; - int ret; - int prealloc; - bool retry = false; - - /* only fs tree and subvol/snap needs ino cache */ - if (root->root_key.objectid != BTRFS_FS_TREE_OBJECTID && - (root->root_key.objectid < BTRFS_FIRST_FREE_OBJECTID || - root->root_key.objectid > BTRFS_LAST_FREE_OBJECTID)) - return 0; - - /* Don't save inode cache if we are deleting this root */ - if (btrfs_root_refs(&root->root_item) == 0) - return 0; - - if (!btrfs_test_opt(fs_info, INODE_MAP_CACHE)) - return 0; - - path = btrfs_alloc_path(); - if (!path) - return -ENOMEM; - - rsv = trans->block_rsv; - trans->block_rsv = &fs_info->trans_block_rsv; - - num_bytes = trans->bytes_reserved; - /* - * 1 item for inode item insertion if need - * 4 items for inode item update (in the worst case) - * 1 items for slack space if we need do truncation - * 1 item for free space object - * 3 items for pre-allocation - */ - trans->bytes_reserved = btrfs_calc_insert_metadata_size(fs_info, 10); - ret = btrfs_block_rsv_add(root, trans->block_rsv, - trans->bytes_reserved, - BTRFS_RESERVE_NO_FLUSH); - if (ret) - goto out; - trace_btrfs_space_reservation(fs_info, "ino_cache", trans->transid, - trans->bytes_reserved, 1); -again: - inode = lookup_free_ino_inode(root, path); - if (IS_ERR(inode) && (PTR_ERR(inode) != -ENOENT || retry)) { - ret = PTR_ERR(inode); - goto out_release; - } - - if (IS_ERR(inode)) { - BUG_ON(retry); /* Logic error */ - retry = true; - - ret = create_free_ino_inode(root, trans, path); - if (ret) - goto out_release; - goto again; - } - - BTRFS_I(inode)->generation = 0; - ret = btrfs_update_inode(trans, root, inode); - if (ret) { - btrfs_abort_transaction(trans, ret); - goto out_put; - } - - if (i_size_read(inode) > 0) { - ret = btrfs_truncate_free_space_cache(trans, NULL, inode); - if (ret) { - if (ret != -ENOSPC) - btrfs_abort_transaction(trans, ret); - goto out_put; - } - } - - spin_lock(&root->ino_cache_lock); - if (root->ino_cache_state != BTRFS_CACHE_FINISHED) { - ret = -1; - spin_unlock(&root->ino_cache_lock); - goto out_put; - } - spin_unlock(&root->ino_cache_lock); - - spin_lock(&ctl->tree_lock); - prealloc = sizeof(struct btrfs_free_space) * ctl->free_extents; - prealloc = ALIGN(prealloc, PAGE_SIZE); - prealloc += ctl->total_bitmaps * PAGE_SIZE; - spin_unlock(&ctl->tree_lock); - - /* Just to make sure we have enough space */ - prealloc += 8 * PAGE_SIZE; - - ret = btrfs_delalloc_reserve_space(BTRFS_I(inode), &data_reserved, 0, - prealloc); - if (ret) - goto out_put; - - ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, prealloc, - prealloc, prealloc, &alloc_hint); - if (ret) { - btrfs_delalloc_release_extents(BTRFS_I(inode), prealloc); - btrfs_delalloc_release_metadata(BTRFS_I(inode), prealloc, true); - goto out_put; - } - - ret = btrfs_write_out_ino_cache(root, trans, path, inode); - btrfs_delalloc_release_extents(BTRFS_I(inode), prealloc); -out_put: - iput(inode); -out_release: - trace_btrfs_space_reservation(fs_info, "ino_cache", trans->transid, - trans->bytes_reserved, 0); - btrfs_block_rsv_release(fs_info, trans->block_rsv, - trans->bytes_reserved, NULL); -out: - trans->block_rsv = rsv; - trans->bytes_reserved = num_bytes; - - btrfs_free_path(path); - extent_changeset_free(data_reserved); - return ret; -} - -int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid) -{ - struct btrfs_path *path; - int ret; - struct extent_buffer *l; - struct btrfs_key search_key; - struct btrfs_key found_key; - int slot; - - path = btrfs_alloc_path(); - if (!path) - return -ENOMEM; - - search_key.objectid = BTRFS_LAST_FREE_OBJECTID; - search_key.type = -1; - search_key.offset = (u64)-1; - ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0); - if (ret < 0) - goto error; - BUG_ON(ret == 0); /* Corruption */ - if (path->slots[0] > 0) { - slot = path->slots[0] - 1; - l = path->nodes[0]; - btrfs_item_key_to_cpu(l, &found_key, slot); - *objectid = max_t(u64, found_key.objectid, - BTRFS_FIRST_FREE_OBJECTID - 1); - } else { - *objectid = BTRFS_FIRST_FREE_OBJECTID - 1; - } - ret = 0; -error: - btrfs_free_path(path); - return ret; -} - -int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid) -{ - int ret; - mutex_lock(&root->objectid_mutex); - - if (unlikely(root->highest_objectid >= BTRFS_LAST_FREE_OBJECTID)) { - btrfs_warn(root->fs_info, - "the objectid of root %llu reaches its highest value", - root->root_key.objectid); - ret = -ENOSPC; - goto out; - } - - *objectid = ++root->highest_objectid; - ret = 0; -out: - mutex_unlock(&root->objectid_mutex); - return ret; -} diff --git a/fs/btrfs/inode-map.h b/fs/btrfs/inode-map.h deleted file mode 100644 index 7a962811dffe..000000000000 --- a/fs/btrfs/inode-map.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -#ifndef BTRFS_INODE_MAP_H -#define BTRFS_INODE_MAP_H - -void btrfs_init_free_ino_ctl(struct btrfs_root *root); -void btrfs_unpin_free_ino(struct btrfs_root *root); -void btrfs_return_ino(struct btrfs_root *root, u64 objectid); -int btrfs_find_free_ino(struct btrfs_root *root, u64 *objectid); -int btrfs_save_ino_cache(struct btrfs_root *root, - struct btrfs_trans_handle *trans); - -int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid); -int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid); - -#endif diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 936c3137c646..535abf898225 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -45,12 +45,12 @@ #include "compression.h" #include "locking.h" #include "free-space-cache.h" -#include "inode-map.h" #include "props.h" #include "qgroup.h" #include "delalloc-space.h" #include "block-group.h" #include "space-info.h" +#include "zoned.h" struct btrfs_iget_args { u64 ino; @@ -62,7 +62,6 @@ struct btrfs_dio_data { loff_t length; ssize_t submitted; struct extent_changeset *data_reserved; - bool sync; }; static const struct inode_operations btrfs_dir_inode_operations; @@ -96,6 +95,51 @@ static void __endio_write_update_ordered(struct btrfs_inode *inode, const bool uptodate); /* + * btrfs_inode_lock - lock inode i_rwsem based on arguments passed + * + * ilock_flags can have the following bit set: + * + * BTRFS_ILOCK_SHARED - acquire a shared lock on the inode + * BTRFS_ILOCK_TRY - try to acquire the lock, if fails on first attempt + * return -EAGAIN + */ +int btrfs_inode_lock(struct inode *inode, unsigned int ilock_flags) +{ + if (ilock_flags & BTRFS_ILOCK_SHARED) { + if (ilock_flags & BTRFS_ILOCK_TRY) { + if (!inode_trylock_shared(inode)) + return -EAGAIN; + else + return 0; + } + inode_lock_shared(inode); + } else { + if (ilock_flags & BTRFS_ILOCK_TRY) { + if (!inode_trylock(inode)) + return -EAGAIN; + else + return 0; + } + inode_lock(inode); + } + return 0; +} + +/* + * btrfs_inode_unlock - unock inode i_rwsem + * + * ilock_flags should contain the same bits set as passed to btrfs_inode_lock() + * to decide whether the lock acquired is shared or exclusive. + */ +void btrfs_inode_unlock(struct inode *inode, unsigned int ilock_flags) +{ + if (ilock_flags & BTRFS_ILOCK_SHARED) + inode_unlock_shared(inode); + else + inode_unlock(inode); +} + +/* * Cleanup all submitted ordered extents in specified range to handle errors * from the btrfs_run_delalloc_range() callback. * @@ -158,7 +202,7 @@ static int btrfs_init_inode_security(struct btrfs_trans_handle *trans, * no overlapping inline items exist in the btree */ static int insert_inline_extent(struct btrfs_trans_handle *trans, - struct btrfs_path *path, int extent_inserted, + struct btrfs_path *path, bool extent_inserted, struct btrfs_root *root, struct inode *inode, u64 start, size_t size, size_t compressed_size, int compress_type, @@ -179,8 +223,6 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans, if (compressed_size && compressed_pages) cur_size = compressed_size; - inode_add_bytes(inode, size); - if (!extent_inserted) { struct btrfs_key key; size_t datasize; @@ -190,7 +232,6 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans, key.type = BTRFS_EXTENT_DATA_KEY; datasize = btrfs_file_extent_calc_inline_size(cur_size); - path->leave_spinning = 1; ret = btrfs_insert_empty_item(trans, root, path, &key, datasize); if (ret) @@ -256,8 +297,6 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans, * could end up racing with unlink. */ BTRFS_I(inode)->disk_i_size = inode->i_size; - ret = btrfs_update_inode(trans, root, inode); - fail: return ret; } @@ -273,6 +312,7 @@ static noinline int cow_file_range_inline(struct btrfs_inode *inode, u64 start, int compress_type, struct page **compressed_pages) { + struct btrfs_drop_extents_args drop_args = { 0 }; struct btrfs_root *root = inode->root; struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_trans_handle *trans; @@ -283,8 +323,6 @@ static noinline int cow_file_range_inline(struct btrfs_inode *inode, u64 start, u64 data_len = inline_len; int ret; struct btrfs_path *path; - int extent_inserted = 0; - u32 extent_item_size; if (compressed_size) data_len = compressed_size; @@ -310,16 +348,20 @@ static noinline int cow_file_range_inline(struct btrfs_inode *inode, u64 start, } trans->block_rsv = &inode->block_rsv; + drop_args.path = path; + drop_args.start = start; + drop_args.end = aligned_end; + drop_args.drop_cache = true; + drop_args.replace_extent = true; + if (compressed_size && compressed_pages) - extent_item_size = btrfs_file_extent_calc_inline_size( + drop_args.extent_item_size = btrfs_file_extent_calc_inline_size( compressed_size); else - extent_item_size = btrfs_file_extent_calc_inline_size( + drop_args.extent_item_size = btrfs_file_extent_calc_inline_size( inline_len); - ret = __btrfs_drop_extents(trans, root, inode, path, start, aligned_end, - NULL, 1, 1, extent_item_size, - &extent_inserted); + ret = btrfs_drop_extents(trans, root, inode, &drop_args); if (ret) { btrfs_abort_transaction(trans, ret); goto out; @@ -327,7 +369,7 @@ static noinline int cow_file_range_inline(struct btrfs_inode *inode, u64 start, if (isize > actual_end) inline_len = min_t(u64, isize, actual_end); - ret = insert_inline_extent(trans, path, extent_inserted, + ret = insert_inline_extent(trans, path, drop_args.extent_inserted, root, &inode->vfs_inode, start, inline_len, compressed_size, compress_type, compressed_pages); @@ -339,8 +381,17 @@ static noinline int cow_file_range_inline(struct btrfs_inode *inode, u64 start, goto out; } + btrfs_update_inode_bytes(inode, inline_len, drop_args.bytes_found); + ret = btrfs_update_inode(trans, root, inode); + if (ret && ret != -ENOSPC) { + btrfs_abort_transaction(trans, ret); + goto out; + } else if (ret == -ENOSPC) { + ret = 1; + goto out; + } + set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags); - btrfs_drop_extent_cache(inode, start, aligned_end - 1, 0); out: /* * Don't forget to free the reserved space, as for inlined extent @@ -642,8 +693,7 @@ cont: NULL, clear_flags, PAGE_UNLOCK | - PAGE_CLEAR_DIRTY | - PAGE_SET_WRITEBACK | + PAGE_START_WRITEBACK | page_error_op | PAGE_END_WRITEBACK); @@ -867,7 +917,6 @@ retry: ins.objectid, async_extent->ram_size, ins.offset, - BTRFS_ORDERED_COMPRESSED, async_extent->compress_type); if (ret) { btrfs_drop_extent_cache(inode, async_extent->start, @@ -884,8 +933,7 @@ retry: async_extent->start + async_extent->ram_size - 1, NULL, EXTENT_LOCKED | EXTENT_DELALLOC, - PAGE_UNLOCK | PAGE_CLEAR_DIRTY | - PAGE_SET_WRITEBACK); + PAGE_UNLOCK | PAGE_START_WRITEBACK); if (btrfs_submit_compressed_write(inode, async_extent->start, async_extent->ram_size, ins.objectid, @@ -921,9 +969,8 @@ out_free: NULL, EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING, - PAGE_UNLOCK | PAGE_CLEAR_DIRTY | - PAGE_SET_WRITEBACK | PAGE_END_WRITEBACK | - PAGE_SET_ERROR); + PAGE_UNLOCK | PAGE_START_WRITEBACK | + PAGE_END_WRITEBACK | PAGE_SET_ERROR); free_async_extent_pages(async_extent); kfree(async_extent); goto again; @@ -1021,8 +1068,7 @@ static noinline int cow_file_range(struct btrfs_inode *inode, EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING, PAGE_UNLOCK | - PAGE_CLEAR_DIRTY | PAGE_SET_WRITEBACK | - PAGE_END_WRITEBACK); + PAGE_START_WRITEBACK | PAGE_END_WRITEBACK); *nr_written = *nr_written + (end - start + PAGE_SIZE) / PAGE_SIZE; *page_started = 1; @@ -1077,7 +1123,8 @@ static noinline int cow_file_range(struct btrfs_inode *inode, free_extent_map(em); ret = btrfs_add_ordered_extent(inode, start, ins.objectid, - ram_size, cur_alloc_size, 0); + ram_size, cur_alloc_size, + BTRFS_ORDERED_REGULAR); if (ret) goto out_drop_extent_cache; @@ -1144,8 +1191,7 @@ out_reserve: out_unlock: clear_bits = EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV; - page_ops = PAGE_UNLOCK | PAGE_CLEAR_DIRTY | PAGE_SET_WRITEBACK | - PAGE_END_WRITEBACK; + page_ops = PAGE_UNLOCK | PAGE_START_WRITEBACK | PAGE_END_WRITEBACK; /* * If we reserved an extent for our delalloc range (or a subrange) and * failed to create the respective ordered extent, then it means that @@ -1270,9 +1316,8 @@ static int cow_file_range_async(struct btrfs_inode *inode, unsigned clear_bits = EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING; - unsigned long page_ops = PAGE_UNLOCK | PAGE_CLEAR_DIRTY | - PAGE_SET_WRITEBACK | PAGE_END_WRITEBACK | - PAGE_SET_ERROR; + unsigned long page_ops = PAGE_UNLOCK | PAGE_START_WRITEBACK | + PAGE_END_WRITEBACK | PAGE_SET_ERROR; extent_clear_unlock_delalloc(inode, start, end, locked_page, clear_bits, page_ops); @@ -1349,6 +1394,29 @@ static int cow_file_range_async(struct btrfs_inode *inode, return 0; } +static noinline int run_delalloc_zoned(struct btrfs_inode *inode, + struct page *locked_page, u64 start, + u64 end, int *page_started, + unsigned long *nr_written) +{ + int ret; + + ret = cow_file_range(inode, locked_page, start, end, page_started, + nr_written, 0); + if (ret) + return ret; + + if (*page_started) + return 0; + + __set_page_dirty_nobuffers(locked_page); + account_page_redirty(locked_page); + extent_write_locked_range(&inode->vfs_inode, start, end, WB_SYNC_ALL); + *page_started = 1; + + return 0; +} + static noinline int csum_exist_in_range(struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes) { @@ -1469,8 +1537,7 @@ static noinline int run_delalloc_nocow(struct btrfs_inode *inode, EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, PAGE_UNLOCK | - PAGE_CLEAR_DIRTY | - PAGE_SET_WRITEBACK | + PAGE_START_WRITEBACK | PAGE_END_WRITEBACK); return -ENOMEM; } @@ -1598,6 +1665,15 @@ next_slot: goto out_check; if (extent_type == BTRFS_FILE_EXTENT_REG && !force) goto out_check; + + /* + * The following checks can be expensive, as they need to + * take other locks and do btree or rbtree searches, so + * release the path to avoid blocking other tasks for too + * long. + */ + btrfs_release_path(path); + /* If extent is RO, we must COW it */ if (btrfs_extent_readonly(fs_info, disk_bytenr)) goto out_check; @@ -1673,12 +1749,12 @@ out_check: cur_offset = extent_end; if (cur_offset > end) break; + if (!path->nodes[0]) + continue; path->slots[0]++; goto next_slot; } - btrfs_release_path(path); - /* * COW range from cow_start to found_key.offset - 1. As the key * will contain the beginning of the first extent that can be @@ -1783,8 +1859,7 @@ error: locked_page, EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING, PAGE_UNLOCK | - PAGE_CLEAR_DIRTY | - PAGE_SET_WRITEBACK | + PAGE_START_WRITEBACK | PAGE_END_WRITEBACK); btrfs_free_path(path); return ret; @@ -1819,17 +1894,24 @@ int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page { int ret; int force_cow = need_force_cow(inode, start, end); + const bool zoned = btrfs_is_zoned(inode->root->fs_info); if (inode->flags & BTRFS_INODE_NODATACOW && !force_cow) { + ASSERT(!zoned); ret = run_delalloc_nocow(inode, locked_page, start, end, page_started, 1, nr_written); } else if (inode->flags & BTRFS_INODE_PREALLOC && !force_cow) { + ASSERT(!zoned); ret = run_delalloc_nocow(inode, locked_page, start, end, page_started, 0, nr_written); } else if (!inode_can_compress(inode) || !inode_need_compress(inode, start, end)) { - ret = cow_file_range(inode, locked_page, start, end, - page_started, nr_written, 1); + if (zoned) + ret = run_delalloc_zoned(inode, locked_page, start, end, + page_started, nr_written); + else + ret = cow_file_range(inode, locked_page, start, end, + page_started, nr_written, 1); } else { set_bit(BTRFS_INODE_HAS_ASYNC_EXTENT, &inode->runtime_flags); ret = cow_file_range_async(inode, wbc, locked_page, start, end, @@ -2098,6 +2180,8 @@ void btrfs_clear_delalloc_extent(struct inode *vfs_inode, spin_lock(&inode->lock); ASSERT(inode->new_delalloc_bytes >= len); inode->new_delalloc_bytes -= len; + if (*bits & EXTENT_ADD_INODE_BYTES) + inode_add_bytes(&inode->vfs_inode, len); spin_unlock(&inode->lock); } } @@ -2121,10 +2205,11 @@ int btrfs_bio_fits_in_stripe(struct page *page, size_t size, struct bio *bio, { struct inode *inode = page->mapping->host; struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - u64 logical = (u64)bio->bi_iter.bi_sector << 9; + u64 logical = bio->bi_iter.bi_sector << 9; + struct extent_map *em; u64 length = 0; u64 map_length; - int ret; + int ret = 0; struct btrfs_io_geometry geom; if (bio_flags & EXTENT_BIO_COMPRESSED) @@ -2132,14 +2217,19 @@ int btrfs_bio_fits_in_stripe(struct page *page, size_t size, struct bio *bio, length = bio->bi_iter.bi_size; map_length = length; - ret = btrfs_get_io_geometry(fs_info, btrfs_op(bio), logical, map_length, - &geom); + em = btrfs_get_chunk_map(fs_info, logical, map_length); + if (IS_ERR(em)) + return PTR_ERR(em); + ret = btrfs_get_io_geometry(fs_info, em, btrfs_op(bio), logical, + map_length, &geom); if (ret < 0) - return ret; + goto out; if (geom.len < length + size) - return 1; - return 0; + ret = 1; +out: + free_extent_map(em); + return ret; } /* @@ -2150,14 +2240,125 @@ int btrfs_bio_fits_in_stripe(struct page *page, size_t size, struct bio *bio, * At IO completion time the cums attached on the ordered extent record * are inserted into the btree */ -static blk_status_t btrfs_submit_bio_start(void *private_data, struct bio *bio, - u64 bio_offset) +static blk_status_t btrfs_submit_bio_start(struct inode *inode, struct bio *bio, + u64 dio_file_offset) { - struct inode *inode = private_data; - return btrfs_csum_one_bio(BTRFS_I(inode), bio, 0, 0); } +bool btrfs_bio_fits_in_ordered_extent(struct page *page, struct bio *bio, + unsigned int size) +{ + struct btrfs_inode *inode = BTRFS_I(page->mapping->host); + struct btrfs_fs_info *fs_info = inode->root->fs_info; + struct btrfs_ordered_extent *ordered; + u64 len = bio->bi_iter.bi_size + size; + bool ret = true; + + ASSERT(btrfs_is_zoned(fs_info)); + ASSERT(fs_info->max_zone_append_size > 0); + ASSERT(bio_op(bio) == REQ_OP_ZONE_APPEND); + + /* Ordered extent not yet created, so we're good */ + ordered = btrfs_lookup_ordered_extent(inode, page_offset(page)); + if (!ordered) + return ret; + + if ((bio->bi_iter.bi_sector << SECTOR_SHIFT) + len > + ordered->disk_bytenr + ordered->disk_num_bytes) + ret = false; + + btrfs_put_ordered_extent(ordered); + + return ret; +} + +static blk_status_t extract_ordered_extent(struct btrfs_inode *inode, + struct bio *bio, loff_t file_offset) +{ + struct btrfs_ordered_extent *ordered; + struct extent_map *em = NULL, *em_new = NULL; + struct extent_map_tree *em_tree = &inode->extent_tree; + u64 start = (u64)bio->bi_iter.bi_sector << SECTOR_SHIFT; + u64 len = bio->bi_iter.bi_size; + u64 end = start + len; + u64 ordered_end; + u64 pre, post; + int ret = 0; + + ordered = btrfs_lookup_ordered_extent(inode, file_offset); + if (WARN_ON_ONCE(!ordered)) + return BLK_STS_IOERR; + + /* No need to split */ + if (ordered->disk_num_bytes == len) + goto out; + + /* We cannot split once end_bio'd ordered extent */ + if (WARN_ON_ONCE(ordered->bytes_left != ordered->disk_num_bytes)) { + ret = -EINVAL; + goto out; + } + + /* We cannot split a compressed ordered extent */ + if (WARN_ON_ONCE(ordered->disk_num_bytes != ordered->num_bytes)) { + ret = -EINVAL; + goto out; + } + + ordered_end = ordered->disk_bytenr + ordered->disk_num_bytes; + /* bio must be in one ordered extent */ + if (WARN_ON_ONCE(start < ordered->disk_bytenr || end > ordered_end)) { + ret = -EINVAL; + goto out; + } + + /* Checksum list should be empty */ + if (WARN_ON_ONCE(!list_empty(&ordered->list))) { + ret = -EINVAL; + goto out; + } + + pre = start - ordered->disk_bytenr; + post = ordered_end - end; + + ret = btrfs_split_ordered_extent(ordered, pre, post); + if (ret) + goto out; + + read_lock(&em_tree->lock); + em = lookup_extent_mapping(em_tree, ordered->file_offset, len); + if (!em) { + read_unlock(&em_tree->lock); + ret = -EIO; + goto out; + } + read_unlock(&em_tree->lock); + + ASSERT(!test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)); + /* + * We cannot reuse em_new here but have to create a new one, as + * unpin_extent_cache() expects the start of the extent map to be the + * logical offset of the file, which does not hold true anymore after + * splitting. + */ + em_new = create_io_em(inode, em->start + pre, len, + em->start + pre, em->block_start + pre, len, + len, len, BTRFS_COMPRESS_NONE, + BTRFS_ORDERED_REGULAR); + if (IS_ERR(em_new)) { + ret = PTR_ERR(em_new); + goto out; + } + free_extent_map(em_new); + +out: + free_extent_map(em); + btrfs_put_ordered_extent(ordered); + + return errno_to_blk_status(ret); +} + /* * extent_io.c submission hook. This does the right thing for csum calculation * on write, or reading the csums from the tree before a read. @@ -2187,12 +2388,22 @@ blk_status_t btrfs_submit_data_bio(struct inode *inode, struct bio *bio, int skip_sum; int async = !atomic_read(&BTRFS_I(inode)->sync_writers); - skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM; + skip_sum = (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM) || + !fs_info->csum_root; if (btrfs_is_free_space_inode(BTRFS_I(inode))) metadata = BTRFS_WQ_ENDIO_FREE_SPACE; - if (bio_op(bio) != REQ_OP_WRITE) { + if (bio_op(bio) == REQ_OP_ZONE_APPEND) { + struct page *page = bio_first_bvec_all(bio)->bv_page; + loff_t file_offset = page_offset(page); + + ret = extract_ordered_extent(BTRFS_I(inode), bio, file_offset); + if (ret) + goto out; + } + + if (btrfs_op(bio) != BTRFS_MAP_WRITE) { ret = btrfs_bio_wq_end_io(fs_info, bio, metadata); if (ret) goto out; @@ -2202,8 +2413,13 @@ blk_status_t btrfs_submit_data_bio(struct inode *inode, struct bio *bio, mirror_num, bio_flags); goto out; - } else if (!skip_sum) { - ret = btrfs_lookup_bio_sums(inode, bio, (u64)-1, NULL); + } else { + /* + * Lookup bio sums does extra checks around whether we + * need to csum or not, which is why we ignore skip_sum + * here. + */ + ret = btrfs_lookup_bio_sums(inode, bio, NULL); if (ret) goto out; } @@ -2213,8 +2429,8 @@ blk_status_t btrfs_submit_data_bio(struct inode *inode, struct bio *bio, if (root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID) goto mapit; /* we're doing a write, do the async checksumming */ - ret = btrfs_wq_submit_bio(fs_info, bio, mirror_num, bio_flags, - 0, inode, btrfs_submit_bio_start); + ret = btrfs_wq_submit_bio(inode, bio, mirror_num, bio_flags, + 0, btrfs_submit_bio_start); goto out; } else if (!skip_sum) { ret = btrfs_csum_one_bio(BTRFS_I(inode), bio, 0, 0); @@ -2253,11 +2469,69 @@ static int add_pending_csums(struct btrfs_trans_handle *trans, return 0; } +static int btrfs_find_new_delalloc_bytes(struct btrfs_inode *inode, + const u64 start, + const u64 len, + struct extent_state **cached_state) +{ + u64 search_start = start; + const u64 end = start + len - 1; + + while (search_start < end) { + const u64 search_len = end - search_start + 1; + struct extent_map *em; + u64 em_len; + int ret = 0; + + em = btrfs_get_extent(inode, NULL, 0, search_start, search_len); + if (IS_ERR(em)) + return PTR_ERR(em); + + if (em->block_start != EXTENT_MAP_HOLE) + goto next; + + em_len = em->len; + if (em->start < search_start) + em_len -= search_start - em->start; + if (em_len > search_len) + em_len = search_len; + + ret = set_extent_bit(&inode->io_tree, search_start, + search_start + em_len - 1, + EXTENT_DELALLOC_NEW, 0, NULL, cached_state, + GFP_NOFS, NULL); +next: + search_start = extent_map_end(em); + free_extent_map(em); + if (ret) + return ret; + } + return 0; +} + int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end, unsigned int extra_bits, struct extent_state **cached_state) { WARN_ON(PAGE_ALIGNED(end)); + + if (start >= i_size_read(&inode->vfs_inode) && + !(inode->flags & BTRFS_INODE_PREALLOC)) { + /* + * There can't be any extents following eof in this case so just + * set the delalloc new bit for the range directly. + */ + extra_bits |= EXTENT_DELALLOC_NEW; + } else { + int ret; + + ret = btrfs_find_new_delalloc_bytes(inode, start, + end + 1 - start, + cached_state); + if (ret) + return ret; + } + return set_extent_delalloc(&inode->io_tree, start, end, extra_bits, cached_state); } @@ -2453,9 +2727,11 @@ int btrfs_writepage_cow_fixup(struct page *page, u64 start, u64 end) static int insert_reserved_file_extent(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, u64 file_pos, struct btrfs_file_extent_item *stack_fi, + const bool update_inode_bytes, u64 qgroup_reserved) { struct btrfs_root *root = inode->root; + const u64 sectorsize = root->fs_info->sectorsize; struct btrfs_path *path; struct extent_buffer *leaf; struct btrfs_key ins; @@ -2463,7 +2739,7 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans, u64 disk_bytenr = btrfs_stack_file_extent_disk_bytenr(stack_fi); u64 num_bytes = btrfs_stack_file_extent_num_bytes(stack_fi); u64 ram_bytes = btrfs_stack_file_extent_ram_bytes(stack_fi); - int extent_inserted = 0; + struct btrfs_drop_extents_args drop_args = { 0 }; int ret; path = btrfs_alloc_path(); @@ -2479,18 +2755,20 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans, * the caller is expected to unpin it and allow it to be merged * with the others. */ - ret = __btrfs_drop_extents(trans, root, inode, path, file_pos, - file_pos + num_bytes, NULL, 0, - 1, sizeof(*stack_fi), &extent_inserted); + drop_args.path = path; + drop_args.start = file_pos; + drop_args.end = file_pos + num_bytes; + drop_args.replace_extent = true; + drop_args.extent_item_size = sizeof(*stack_fi); + ret = btrfs_drop_extents(trans, root, inode, &drop_args); if (ret) goto out; - if (!extent_inserted) { + if (!drop_args.extent_inserted) { ins.objectid = btrfs_ino(inode); ins.offset = file_pos; ins.type = BTRFS_EXTENT_DATA_KEY; - path->leave_spinning = 1; ret = btrfs_insert_empty_item(trans, root, path, &ins, sizeof(*stack_fi)); if (ret) @@ -2505,7 +2783,24 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans, btrfs_mark_buffer_dirty(leaf); btrfs_release_path(path); - inode_add_bytes(&inode->vfs_inode, num_bytes); + /* + * If we dropped an inline extent here, we know the range where it is + * was not marked with the EXTENT_DELALLOC_NEW bit, so we update the + * number of bytes only for that range contaning the inline extent. + * The remaining of the range will be processed when clearning the + * EXTENT_DELALLOC_BIT bit through the ordered extent completion. + */ + if (file_pos == 0 && !IS_ALIGNED(drop_args.bytes_found, sectorsize)) { + u64 inline_size = round_down(drop_args.bytes_found, sectorsize); + + inline_size = drop_args.bytes_found - inline_size; + btrfs_update_inode_bytes(inode, sectorsize, inline_size); + drop_args.bytes_found -= inline_size; + num_bytes -= sectorsize; + } + + if (update_inode_bytes) + btrfs_update_inode_bytes(inode, num_bytes, drop_args.bytes_found); ins.objectid = disk_bytenr; ins.offset = disk_num_bytes; @@ -2543,6 +2838,7 @@ static int insert_ordered_extent_file_extent(struct btrfs_trans_handle *trans, { struct btrfs_file_extent_item stack_fi; u64 logical_len; + bool update_inode_bytes; memset(&stack_fi, 0, sizeof(stack_fi)); btrfs_set_stack_file_extent_type(&stack_fi, BTRFS_FILE_EXTENT_REG); @@ -2558,9 +2854,18 @@ static int insert_ordered_extent_file_extent(struct btrfs_trans_handle *trans, btrfs_set_stack_file_extent_compression(&stack_fi, oe->compress_type); /* Encryption and other encoding is reserved and all 0 */ + /* + * For delalloc, when completing an ordered extent we update the inode's + * bytes when clearing the range in the inode's io tree, so pass false + * as the argument 'update_inode_bytes' to insert_reserved_file_extent(), + * except if the ordered extent was truncated. + */ + update_inode_bytes = test_bit(BTRFS_ORDERED_DIRECT, &oe->flags) || + test_bit(BTRFS_ORDERED_TRUNCATED, &oe->flags); + return insert_reserved_file_extent(trans, BTRFS_I(oe->inode), oe->file_offset, &stack_fi, - oe->qgroup_rsv); + update_inode_bytes, oe->qgroup_rsv); } /* @@ -2570,11 +2875,11 @@ static int insert_ordered_extent_file_extent(struct btrfs_trans_handle *trans, */ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) { - struct inode *inode = ordered_extent->inode; - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_inode *inode = BTRFS_I(ordered_extent->inode); + struct btrfs_root *root = inode->root; + struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_trans_handle *trans = NULL; - struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; + struct extent_io_tree *io_tree = &inode->io_tree; struct extent_state *cached_state = NULL; u64 start, end; int compress_type = 0; @@ -2582,10 +2887,8 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) u64 logical_len = ordered_extent->num_bytes; bool freespace_inode; bool truncated = false; - bool range_locked = false; - bool clear_new_delalloc_bytes = false; bool clear_reserved_extent = true; - unsigned int clear_bits; + unsigned int clear_bits = EXTENT_DEFRAG; start = ordered_extent->file_offset; end = start + ordered_extent->num_bytes - 1; @@ -2593,16 +2896,19 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) if (!test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags) && !test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags) && !test_bit(BTRFS_ORDERED_DIRECT, &ordered_extent->flags)) - clear_new_delalloc_bytes = true; + clear_bits |= EXTENT_DELALLOC_NEW; - freespace_inode = btrfs_is_free_space_inode(BTRFS_I(inode)); + freespace_inode = btrfs_is_free_space_inode(inode); if (test_bit(BTRFS_ORDERED_IOERR, &ordered_extent->flags)) { ret = -EIO; goto out; } - btrfs_free_io_failure_record(BTRFS_I(inode), start, end); + if (ordered_extent->disk) + btrfs_rewrite_logical_zoned(ordered_extent); + + btrfs_free_io_failure_record(inode, start, end); if (test_bit(BTRFS_ORDERED_TRUNCATED, &ordered_extent->flags)) { truncated = true; @@ -2625,14 +2931,14 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) trans = NULL; goto out; } - trans->block_rsv = &BTRFS_I(inode)->block_rsv; + trans->block_rsv = &inode->block_rsv; ret = btrfs_update_inode_fallback(trans, root, inode); if (ret) /* -ENOMEM or corruption */ btrfs_abort_transaction(trans, ret); goto out; } - range_locked = true; + clear_bits |= EXTENT_LOCKED; lock_extent_bits(io_tree, start, end, &cached_state); if (freespace_inode) @@ -2645,13 +2951,13 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) goto out; } - trans->block_rsv = &BTRFS_I(inode)->block_rsv; + trans->block_rsv = &inode->block_rsv; if (test_bit(BTRFS_ORDERED_COMPRESSED, &ordered_extent->flags)) compress_type = ordered_extent->compress_type; if (test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags)) { BUG_ON(compress_type); - ret = btrfs_mark_extent_written(trans, BTRFS_I(inode), + ret = btrfs_mark_extent_written(trans, inode, ordered_extent->file_offset, ordered_extent->file_offset + logical_len); @@ -2665,8 +2971,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) ordered_extent->disk_num_bytes); } } - unpin_extent_cache(&BTRFS_I(inode)->extent_tree, - ordered_extent->file_offset, + unpin_extent_cache(&inode->extent_tree, ordered_extent->file_offset, ordered_extent->num_bytes, trans->transid); if (ret < 0) { btrfs_abort_transaction(trans, ret); @@ -2679,6 +2984,17 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) goto out; } + /* + * If this is a new delalloc range, clear its new delalloc flag to + * update the inode's number of bytes. This needs to be done first + * before updating the inode item. + */ + if ((clear_bits & EXTENT_DELALLOC_NEW) && + !test_bit(BTRFS_ORDERED_TRUNCATED, &ordered_extent->flags)) + clear_extent_bit(&inode->io_tree, start, end, + EXTENT_DELALLOC_NEW | EXTENT_ADD_INODE_BYTES, + 0, 0, &cached_state); + btrfs_inode_safe_disk_i_size_write(inode, 0); ret = btrfs_update_inode_fallback(trans, root, inode); if (ret) { /* -ENOMEM or corruption */ @@ -2687,12 +3003,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) } ret = 0; out: - clear_bits = EXTENT_DEFRAG; - if (range_locked) - clear_bits |= EXTENT_LOCKED; - if (clear_new_delalloc_bytes) - clear_bits |= EXTENT_DELALLOC_NEW; - clear_extent_bit(&BTRFS_I(inode)->io_tree, start, end, clear_bits, + clear_extent_bit(&inode->io_tree, start, end, clear_bits, (clear_bits & EXTENT_LOCKED) ? 1 : 0, 0, &cached_state); @@ -2707,7 +3018,7 @@ out: clear_extent_uptodate(io_tree, unwritten_start, end, NULL); /* Drop the cache for the part of the extent we didn't write. */ - btrfs_drop_extent_cache(BTRFS_I(inode), unwritten_start, end, 0); + btrfs_drop_extent_cache(inode, unwritten_start, end, 0); /* * If the ordered extent had an IOERR or something else went @@ -2742,7 +3053,7 @@ out: * This needs to be done to make sure anybody waiting knows we are done * updating everything for this ordered extent. */ - btrfs_remove_ordered_extent(BTRFS_I(inode), ordered_extent); + btrfs_remove_ordered_extent(inode, ordered_extent); /* once for us */ btrfs_put_ordered_extent(ordered_extent); @@ -2783,18 +3094,32 @@ void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start, btrfs_queue_work(wq, &ordered_extent->work); } +/* + * check_data_csum - verify checksum of one sector of uncompressed data + * @inode: inode + * @io_bio: btrfs_io_bio which contains the csum + * @bio_offset: offset to the beginning of the bio (in bytes) + * @page: page where is the data to be verified + * @pgoff: offset inside the page + * + * The length of such check is always one sector size. + */ static int check_data_csum(struct inode *inode, struct btrfs_io_bio *io_bio, - int icsum, struct page *page, int pgoff, u64 start, - size_t len) + u32 bio_offset, struct page *page, u32 pgoff) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); char *kaddr; - u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); + u32 len = fs_info->sectorsize; + const u32 csum_size = fs_info->csum_size; + unsigned int offset_sectors; u8 *csum_expected; u8 csum[BTRFS_CSUM_SIZE]; - csum_expected = ((u8 *)io_bio->csum) + icsum * csum_size; + ASSERT(pgoff + len <= PAGE_SIZE); + + offset_sectors = bio_offset >> fs_info->sectorsize_bits; + csum_expected = ((u8 *)io_bio->csum) + offset_sectors * csum_size; kaddr = kmap_atomic(page); shash->tfm = fs_info->csum_shash; @@ -2807,8 +3132,8 @@ static int check_data_csum(struct inode *inode, struct btrfs_io_bio *io_bio, kunmap_atomic(kaddr); return 0; zeroit: - btrfs_print_data_csum_error(BTRFS_I(inode), start, csum, csum_expected, - io_bio->mirror_num); + btrfs_print_data_csum_error(BTRFS_I(inode), page_offset(page) + pgoff, + csum, csum_expected, io_bio->mirror_num); if (io_bio->device) btrfs_dev_stat_inc_and_print(io_bio->device, BTRFS_DEV_STAT_CORRUPTION_ERRS); @@ -2819,17 +3144,23 @@ zeroit: } /* - * when reads are done, we need to check csums to verify the data is correct + * When reads are done, we need to check csums to verify the data is correct. * if there's a match, we allow the bio to finish. If not, the code in * extent_io.c will try to find good copies for us. + * + * @bio_offset: offset to the beginning of the bio (in bytes) + * @start: file offset of the range start + * @end: file offset of the range end (inclusive) + * @mirror: mirror number */ -int btrfs_verify_data_csum(struct btrfs_io_bio *io_bio, u64 phy_offset, +int btrfs_verify_data_csum(struct btrfs_io_bio *io_bio, u32 bio_offset, struct page *page, u64 start, u64 end, int mirror) { - size_t offset = start - page_offset(page); struct inode *inode = page->mapping->host; struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; struct btrfs_root *root = BTRFS_I(inode)->root; + const u32 sectorsize = root->fs_info->sectorsize; + u32 pg_off; if (PageChecked(page)) { ClearPageChecked(page); @@ -2839,15 +3170,27 @@ int btrfs_verify_data_csum(struct btrfs_io_bio *io_bio, u64 phy_offset, if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM) return 0; + if (!root->fs_info->csum_root) + return 0; + if (root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID && test_range_bit(io_tree, start, end, EXTENT_NODATASUM, 1, NULL)) { clear_extent_bits(io_tree, start, end, EXTENT_NODATASUM); return 0; } - phy_offset >>= inode->i_sb->s_blocksize_bits; - return check_data_csum(inode, io_bio, phy_offset, page, offset, start, - (size_t)(end - start + 1)); + ASSERT(page_offset(page) <= start && + end <= page_offset(page) + PAGE_SIZE - 1); + for (pg_off = offset_in_page(start); + pg_off < offset_in_page(end); + pg_off += sectorsize, bio_offset += sectorsize) { + int ret; + + ret = check_data_csum(inode, io_bio, bio_offset, page, pg_off); + if (ret < 0) + return -EIO; + } + return 0; } /* @@ -2914,14 +3257,16 @@ void btrfs_run_delayed_iputs(struct btrfs_fs_info *fs_info) } /** - * btrfs_wait_on_delayed_iputs - wait on the delayed iputs to be done running - * @fs_info - the fs_info for this fs - * @return - EINTR if we were killed, 0 if nothing's pending + * Wait for flushing all delayed iputs + * + * @fs_info: the filesystem * * This will wait on any delayed iputs that are currently running with KILLABLE * set. Once they are all done running we will return, unless we are killed in * which case we return EINTR. This helps in user operations like fallocate etc * that might get blocked on the iputs. + * + * Return EINTR if we were killed, 0 if nothing's pending */ int btrfs_wait_on_delayed_iputs(struct btrfs_fs_info *fs_info) { @@ -3457,7 +3802,8 @@ static void fill_inode_item(struct btrfs_trans_handle *trans, * copy everything in the in-memory inode into the btree. */ static noinline int btrfs_update_inode_item(struct btrfs_trans_handle *trans, - struct btrfs_root *root, struct inode *inode) + struct btrfs_root *root, + struct btrfs_inode *inode) { struct btrfs_inode_item *inode_item; struct btrfs_path *path; @@ -3468,9 +3814,7 @@ static noinline int btrfs_update_inode_item(struct btrfs_trans_handle *trans, if (!path) return -ENOMEM; - path->leave_spinning = 1; - ret = btrfs_lookup_inode(trans, root, path, &BTRFS_I(inode)->location, - 1); + ret = btrfs_lookup_inode(trans, root, path, &inode->location, 1); if (ret) { if (ret > 0) ret = -ENOENT; @@ -3481,9 +3825,9 @@ static noinline int btrfs_update_inode_item(struct btrfs_trans_handle *trans, inode_item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_inode_item); - fill_inode_item(trans, leaf, inode_item, inode); + fill_inode_item(trans, leaf, inode_item, &inode->vfs_inode); btrfs_mark_buffer_dirty(leaf); - btrfs_set_inode_last_trans(trans, BTRFS_I(inode)); + btrfs_set_inode_last_trans(trans, inode); ret = 0; failed: btrfs_free_path(path); @@ -3494,7 +3838,8 @@ failed: * copy everything in the in-memory inode into the btree. */ noinline int btrfs_update_inode(struct btrfs_trans_handle *trans, - struct btrfs_root *root, struct inode *inode) + struct btrfs_root *root, + struct btrfs_inode *inode) { struct btrfs_fs_info *fs_info = root->fs_info; int ret; @@ -3506,23 +3851,22 @@ noinline int btrfs_update_inode(struct btrfs_trans_handle *trans, * The data relocation inode should also be directly updated * without delay */ - if (!btrfs_is_free_space_inode(BTRFS_I(inode)) + if (!btrfs_is_free_space_inode(inode) && root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID && !test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags)) { btrfs_update_root_times(trans, root); ret = btrfs_delayed_update_inode(trans, root, inode); if (!ret) - btrfs_set_inode_last_trans(trans, BTRFS_I(inode)); + btrfs_set_inode_last_trans(trans, inode); return ret; } return btrfs_update_inode_item(trans, root, inode); } -noinline int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans, - struct btrfs_root *root, - struct inode *inode) +int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans, + struct btrfs_root *root, struct btrfs_inode *inode) { int ret; @@ -3557,7 +3901,6 @@ static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans, goto out; } - path->leave_spinning = 1; di = btrfs_lookup_dir_item(trans, root, path, dir_ino, name, name_len, -1); if (IS_ERR_OR_NULL(di)) { @@ -3637,7 +3980,7 @@ err: inode_inc_iversion(&dir->vfs_inode); inode->vfs_inode.i_ctime = dir->vfs_inode.i_mtime = dir->vfs_inode.i_ctime = current_time(&inode->vfs_inode); - ret = btrfs_update_inode(trans, root, &dir->vfs_inode); + ret = btrfs_update_inode(trans, root, dir); out: return ret; } @@ -3651,7 +3994,7 @@ int btrfs_unlink_inode(struct btrfs_trans_handle *trans, ret = __btrfs_unlink_inode(trans, root, dir, inode, name, name_len); if (!ret) { drop_nlink(&inode->vfs_inode); - ret = btrfs_update_inode(trans, root, &inode->vfs_inode); + ret = btrfs_update_inode(trans, root, inode); } return ret; } @@ -3800,7 +4143,7 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, btrfs_i_size_write(BTRFS_I(dir), dir->i_size - name_len * 2); inode_inc_iversion(dir); dir->i_mtime = dir->i_ctime = current_time(dir); - ret = btrfs_update_inode_fallback(trans, root, dir); + ret = btrfs_update_inode_fallback(trans, root, BTRFS_I(dir)); if (ret) btrfs_abort_transaction(trans, ret); out: @@ -3937,7 +4280,6 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) struct btrfs_block_rsv block_rsv; u64 root_flags; int ret; - int err; /* * Don't allow to delete a subvolume with send in progress. This is @@ -3959,8 +4301,8 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) down_write(&fs_info->subvol_sem); - err = may_destroy_subvol(dest); - if (err) + ret = may_destroy_subvol(dest); + if (ret) goto out_up_write; btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP); @@ -3969,13 +4311,13 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) * two for dir entries, * two for root ref/backref. */ - err = btrfs_subvolume_reserve_metadata(root, &block_rsv, 5, true); - if (err) + ret = btrfs_subvolume_reserve_metadata(root, &block_rsv, 5, true); + if (ret) goto out_up_write; trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { - err = PTR_ERR(trans); + ret = PTR_ERR(trans); goto out_release; } trans->block_rsv = &block_rsv; @@ -3985,7 +4327,6 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) ret = btrfs_unlink_subvol(trans, dir, dentry); if (ret) { - err = ret; btrfs_abort_transaction(trans, ret); goto out_end_trans; } @@ -3994,7 +4335,7 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) memset(&dest->root_item.drop_progress, 0, sizeof(dest->root_item.drop_progress)); - dest->root_item.drop_level = 0; + btrfs_set_root_drop_level(&dest->root_item, 0); btrfs_set_root_refs(&dest->root_item, 0); if (!test_and_set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &dest->state)) { @@ -4003,7 +4344,6 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) dest->root_key.objectid); if (ret) { btrfs_abort_transaction(trans, ret); - err = ret; goto out_end_trans; } } @@ -4013,7 +4353,6 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) dest->root_key.objectid); if (ret && ret != -ENOENT) { btrfs_abort_transaction(trans, ret); - err = ret; goto out_end_trans; } if (!btrfs_is_empty_uuid(dest->root_item.received_uuid)) { @@ -4023,7 +4362,6 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) dest->root_key.objectid); if (ret && ret != -ENOENT) { btrfs_abort_transaction(trans, ret); - err = ret; goto out_end_trans; } } @@ -4034,14 +4372,12 @@ out_end_trans: trans->block_rsv = NULL; trans->bytes_reserved = 0; ret = btrfs_end_transaction(trans); - if (ret && !err) - err = ret; inode->i_flags |= S_DEAD; out_release: btrfs_subvolume_release_metadata(root, &block_rsv); out_up_write: up_write(&fs_info->subvol_sem); - if (err) { + if (ret) { spin_lock(&dest->root_item_lock); root_flags = btrfs_root_flags(&dest->root_item); btrfs_set_root_flags(&dest->root_item, @@ -4051,15 +4387,9 @@ out_up_write: d_invalidate(dentry); btrfs_prune_dentries(dest); ASSERT(dest->send_in_progress == 0); - - /* the last ref */ - if (dest->ino_cache_inode) { - iput(dest->ino_cache_inode); - dest->ino_cache_inode = NULL; - } } - return err; + return ret; } static int btrfs_rmdir(struct inode *dir, struct dentry *dentry) @@ -4136,7 +4466,7 @@ out: */ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, - struct inode *inode, + struct btrfs_inode *inode, u64 new_size, u32 min_type) { struct btrfs_fs_info *fs_info = root->fs_info; @@ -4157,7 +4487,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, int pending_del_slot = 0; int extent_type = -1; int ret; - u64 ino = btrfs_ino(BTRFS_I(inode)); + u64 ino = btrfs_ino(inode); u64 bytes_deleted = 0; bool be_nice = false; bool should_throttle = false; @@ -4171,7 +4501,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, * off from time to time. This means all inodes in subvolume roots, * reloc roots, and data reloc roots. */ - if (!btrfs_is_free_space_inode(BTRFS_I(inode)) && + if (!btrfs_is_free_space_inode(inode) && test_bit(BTRFS_ROOT_SHAREABLE, &root->state)) be_nice = true; @@ -4181,7 +4511,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, path->reada = READA_BACK; if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) { - lock_extent_bits(&BTRFS_I(inode)->io_tree, lock_start, (u64)-1, + lock_extent_bits(&inode->io_tree, lock_start, (u64)-1, &cached_state); /* @@ -4189,7 +4519,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, * new size is not block aligned since we will be keeping the * last block of the extent just the way it is. */ - btrfs_drop_extent_cache(BTRFS_I(inode), ALIGN(new_size, + btrfs_drop_extent_cache(inode, ALIGN(new_size, fs_info->sectorsize), (u64)-1, 0); } @@ -4200,8 +4530,8 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, * it is used to drop the logged items. So we shouldn't kill the delayed * items. */ - if (min_type == 0 && root == BTRFS_I(inode)->root) - btrfs_kill_delayed_inode_items(BTRFS_I(inode)); + if (min_type == 0 && root == inode->root) + btrfs_kill_delayed_inode_items(inode); key.objectid = ino; key.offset = (u64)-1; @@ -4257,14 +4587,13 @@ search_again: btrfs_file_extent_num_bytes(leaf, fi); trace_btrfs_truncate_show_fi_regular( - BTRFS_I(inode), leaf, fi, - found_key.offset); + inode, leaf, fi, found_key.offset); } else if (extent_type == BTRFS_FILE_EXTENT_INLINE) { item_end += btrfs_file_extent_ram_bytes(leaf, fi); trace_btrfs_truncate_show_fi_inline( - BTRFS_I(inode), leaf, fi, path->slots[0], + inode, leaf, fi, path->slots[0], found_key.offset); } item_end--; @@ -4303,7 +4632,8 @@ search_again: if (test_bit(BTRFS_ROOT_SHAREABLE, &root->state) && extent_start != 0) - inode_sub_bytes(inode, num_dec); + inode_sub_bytes(&inode->vfs_inode, + num_dec); btrfs_mark_buffer_dirty(leaf); } else { extent_num_bytes = @@ -4318,7 +4648,8 @@ search_again: found_extent = 1; if (test_bit(BTRFS_ROOT_SHAREABLE, &root->state)) - inode_sub_bytes(inode, num_dec); + inode_sub_bytes(&inode->vfs_inode, + num_dec); } } clear_len = num_dec; @@ -4353,7 +4684,8 @@ search_again: } if (test_bit(BTRFS_ROOT_SHAREABLE, &root->state)) - inode_sub_bytes(inode, item_end + 1 - new_size); + inode_sub_bytes(&inode->vfs_inode, + item_end + 1 - new_size); } delete: /* @@ -4361,8 +4693,8 @@ delete: * multiple fsyncs, and in this case we don't want to clear the * file extent range because it's just the log. */ - if (root == BTRFS_I(inode)->root) { - ret = btrfs_inode_clear_file_extent_range(BTRFS_I(inode), + if (root == inode->root) { + ret = btrfs_inode_clear_file_extent_range(inode, clear_start, clear_len); if (ret) { btrfs_abort_transaction(trans, ret); @@ -4471,8 +4803,8 @@ out: if (!ret && last_size > new_size) last_size = new_size; btrfs_inode_safe_disk_i_size_write(inode, last_size); - unlock_extent_cached(&BTRFS_I(inode)->io_tree, lock_start, - (u64)-1, &cached_state); + unlock_extent_cached(&inode->io_tree, lock_start, (u64)-1, + &cached_state); } btrfs_free_path(path); @@ -4490,12 +4822,12 @@ out: * This will find the block for the "from" offset and cow the block and zero the * part we want to zero. This is used with truncate and hole punching. */ -int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len, - int front) +int btrfs_truncate_block(struct btrfs_inode *inode, loff_t from, loff_t len, + int front) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct address_space *mapping = inode->i_mapping; - struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; + struct btrfs_fs_info *fs_info = inode->root->fs_info; + struct address_space *mapping = inode->vfs_inode.i_mapping; + struct extent_io_tree *io_tree = &inode->io_tree; struct btrfs_ordered_extent *ordered; struct extent_state *cached_state = NULL; struct extent_changeset *data_reserved = NULL; @@ -4518,33 +4850,35 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len, block_start = round_down(from, blocksize); block_end = block_start + blocksize - 1; - ret = btrfs_check_data_free_space(BTRFS_I(inode), &data_reserved, - block_start, blocksize); + ret = btrfs_check_data_free_space(inode, &data_reserved, block_start, + blocksize); if (ret < 0) { - if (btrfs_check_nocow_lock(BTRFS_I(inode), block_start, - &write_bytes) > 0) { + if (btrfs_check_nocow_lock(inode, block_start, &write_bytes) > 0) { /* For nocow case, no need to reserve data space */ only_release_metadata = true; } else { goto out; } } - ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), blocksize); + ret = btrfs_delalloc_reserve_metadata(inode, blocksize); if (ret < 0) { if (!only_release_metadata) - btrfs_free_reserved_data_space(BTRFS_I(inode), - data_reserved, block_start, blocksize); + btrfs_free_reserved_data_space(inode, data_reserved, + block_start, blocksize); goto out; } again: page = find_or_create_page(mapping, index, mask); if (!page) { - btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved, - block_start, blocksize, true); - btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize); + btrfs_delalloc_release_space(inode, data_reserved, block_start, + blocksize, true); + btrfs_delalloc_release_extents(inode, blocksize); ret = -ENOMEM; goto out; } + ret = set_page_extent_mapped(page); + if (ret < 0) + goto out_unlock; if (!PageUptodate(page)) { ret = btrfs_readpage(NULL, page); @@ -4562,9 +4896,8 @@ again: wait_on_page_writeback(page); lock_extent_bits(io_tree, block_start, block_end, &cached_state); - set_page_extent_mapped(page); - ordered = btrfs_lookup_ordered_extent(BTRFS_I(inode), block_start); + ordered = btrfs_lookup_ordered_extent(inode, block_start); if (ordered) { unlock_extent_cached(io_tree, block_start, block_end, &cached_state); @@ -4575,11 +4908,11 @@ again: goto again; } - clear_extent_bit(&BTRFS_I(inode)->io_tree, block_start, block_end, + clear_extent_bit(&inode->io_tree, block_start, block_end, EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0, &cached_state); - ret = btrfs_set_extent_delalloc(BTRFS_I(inode), block_start, block_end, 0, + ret = btrfs_set_extent_delalloc(inode, block_start, block_end, 0, &cached_state); if (ret) { unlock_extent_cached(io_tree, block_start, block_end, @@ -4605,34 +4938,33 @@ again: unlock_extent_cached(io_tree, block_start, block_end, &cached_state); if (only_release_metadata) - set_extent_bit(&BTRFS_I(inode)->io_tree, block_start, - block_end, EXTENT_NORESERVE, NULL, NULL, - GFP_NOFS); + set_extent_bit(&inode->io_tree, block_start, block_end, + EXTENT_NORESERVE, 0, NULL, NULL, GFP_NOFS, NULL); out_unlock: if (ret) { if (only_release_metadata) - btrfs_delalloc_release_metadata(BTRFS_I(inode), - blocksize, true); + btrfs_delalloc_release_metadata(inode, blocksize, true); else - btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved, + btrfs_delalloc_release_space(inode, data_reserved, block_start, blocksize, true); } - btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize); + btrfs_delalloc_release_extents(inode, blocksize); unlock_page(page); put_page(page); out: if (only_release_metadata) - btrfs_check_nocow_unlock(BTRFS_I(inode)); + btrfs_check_nocow_unlock(inode); extent_changeset_free(data_reserved); return ret; } -static int maybe_insert_hole(struct btrfs_root *root, struct inode *inode, +static int maybe_insert_hole(struct btrfs_root *root, struct btrfs_inode *inode, u64 offset, u64 len) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_trans_handle *trans; + struct btrfs_drop_extents_args drop_args = { 0 }; int ret; /* @@ -4640,9 +4972,9 @@ static int maybe_insert_hole(struct btrfs_root *root, struct inode *inode, * that any holes get logged if we fsync. */ if (btrfs_fs_incompat(fs_info, NO_HOLES)) { - BTRFS_I(inode)->last_trans = fs_info->generation; - BTRFS_I(inode)->last_sub_trans = root->log_transid; - BTRFS_I(inode)->last_log_commit = root->last_log_commit; + inode->last_trans = fs_info->generation; + inode->last_sub_trans = root->log_transid; + inode->last_log_commit = root->last_log_commit; return 0; } @@ -4655,19 +4987,25 @@ static int maybe_insert_hole(struct btrfs_root *root, struct inode *inode, if (IS_ERR(trans)) return PTR_ERR(trans); - ret = btrfs_drop_extents(trans, root, inode, offset, offset + len, 1); + drop_args.start = offset; + drop_args.end = offset + len; + drop_args.drop_cache = true; + + ret = btrfs_drop_extents(trans, root, inode, &drop_args); if (ret) { btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); return ret; } - ret = btrfs_insert_file_extent(trans, root, btrfs_ino(BTRFS_I(inode)), + ret = btrfs_insert_file_extent(trans, root, btrfs_ino(inode), offset, 0, 0, len, 0, len, 0, 0, 0); - if (ret) + if (ret) { btrfs_abort_transaction(trans, ret); - else + } else { + btrfs_update_inode_bytes(inode, 0, drop_args.bytes_found); btrfs_update_inode(trans, root, inode); + } btrfs_end_transaction(trans); return ret; } @@ -4678,14 +5016,14 @@ static int maybe_insert_hole(struct btrfs_root *root, struct inode *inode, * these file extents so that btrfs_get_extent will return a EXTENT_MAP_HOLE for * the range between oldsize and size */ -int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size) +int btrfs_cont_expand(struct btrfs_inode *inode, loff_t oldsize, loff_t size) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_root *root = BTRFS_I(inode)->root; - struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; + struct btrfs_root *root = inode->root; + struct btrfs_fs_info *fs_info = root->fs_info; + struct extent_io_tree *io_tree = &inode->io_tree; struct extent_map *em = NULL; struct extent_state *cached_state = NULL; - struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree; + struct extent_map_tree *em_tree = &inode->extent_tree; u64 hole_start = ALIGN(oldsize, fs_info->sectorsize); u64 block_end = ALIGN(size, fs_info->sectorsize); u64 last_byte; @@ -4705,11 +5043,11 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size) if (size <= hole_start) return 0; - btrfs_lock_and_flush_ordered_range(BTRFS_I(inode), hole_start, - block_end - 1, &cached_state); + btrfs_lock_and_flush_ordered_range(inode, hole_start, block_end - 1, + &cached_state); cur_offset = hole_start; while (1) { - em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, cur_offset, + em = btrfs_get_extent(inode, NULL, 0, cur_offset, block_end - cur_offset); if (IS_ERR(em)) { err = PTR_ERR(em); @@ -4728,17 +5066,17 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size) if (err) break; - err = btrfs_inode_set_file_extent_range(BTRFS_I(inode), + err = btrfs_inode_set_file_extent_range(inode, cur_offset, hole_size); if (err) break; - btrfs_drop_extent_cache(BTRFS_I(inode), cur_offset, + btrfs_drop_extent_cache(inode, cur_offset, cur_offset + hole_size - 1, 0); hole_em = alloc_extent_map(); if (!hole_em) { set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, - &BTRFS_I(inode)->runtime_flags); + &inode->runtime_flags); goto next; } hole_em->start = cur_offset; @@ -4758,14 +5096,13 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size) write_unlock(&em_tree->lock); if (err != -EEXIST) break; - btrfs_drop_extent_cache(BTRFS_I(inode), - cur_offset, + btrfs_drop_extent_cache(inode, cur_offset, cur_offset + hole_size - 1, 0); } free_extent_map(hole_em); } else { - err = btrfs_inode_set_file_extent_range(BTRFS_I(inode), + err = btrfs_inode_set_file_extent_range(inode, cur_offset, hole_size); if (err) break; @@ -4813,7 +5150,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr) * this truncation. */ btrfs_drew_write_lock(&root->snapshot_lock); - ret = btrfs_cont_expand(inode, oldsize, newsize); + ret = btrfs_cont_expand(BTRFS_I(inode), oldsize, newsize); if (ret) { btrfs_drew_write_unlock(&root->snapshot_lock); return ret; @@ -4826,12 +5163,21 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr) } i_size_write(inode, newsize); - btrfs_inode_safe_disk_i_size_write(inode, 0); + btrfs_inode_safe_disk_i_size_write(BTRFS_I(inode), 0); pagecache_isize_extended(inode, oldsize, newsize); - ret = btrfs_update_inode(trans, root, inode); + ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); btrfs_drew_write_unlock(&root->snapshot_lock); btrfs_end_transaction(trans); } else { + struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + + if (btrfs_is_zoned(fs_info)) { + ret = btrfs_wait_ordered_range(inode, + ALIGN(newsize, fs_info->sectorsize), + (u64)-1); + if (ret) + return ret; + } /* * We're truncating a file that used to have good data down to @@ -5099,7 +5445,8 @@ void btrfs_evict_inode(struct inode *inode) trans->block_rsv = rsv; - ret = btrfs_truncate_inode_items(trans, root, inode, 0, 0); + ret = btrfs_truncate_inode_items(trans, root, BTRFS_I(inode), + 0, 0); trans->block_rsv = &fs_info->trans_block_rsv; btrfs_end_transaction(trans); btrfs_btree_balance_dirty(fs_info); @@ -5126,10 +5473,6 @@ void btrfs_evict_inode(struct inode *inode) btrfs_end_transaction(trans); } - if (!(root == fs_info->tree_root || - root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID)) - btrfs_return_ino(root, btrfs_ino(BTRFS_I(inode))); - free_rsv: btrfs_free_block_rsv(fs_info, rsv); no_delete: @@ -5739,7 +6082,7 @@ static int btrfs_dirty_inode(struct inode *inode) if (IS_ERR(trans)) return PTR_ERR(trans); - ret = btrfs_update_inode(trans, root, inode); + ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); if (ret && ret == -ENOSPC) { /* whoops, lets try again with the full transaction */ btrfs_end_transaction(trans); @@ -5747,7 +6090,7 @@ static int btrfs_dirty_inode(struct inode *inode) if (IS_ERR(trans)) return PTR_ERR(trans); - ret = btrfs_update_inode(trans, root, inode); + ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); } btrfs_end_transaction(trans); if (BTRFS_I(inode)->delayed_node) @@ -6010,7 +6353,6 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans, goto fail; } - path->leave_spinning = 1; ret = btrfs_insert_empty_items(trans, root, path, key, sizes, nitems); if (ret != 0) goto fail_unlock; @@ -6136,7 +6478,7 @@ int btrfs_add_link(struct btrfs_trans_handle *trans, parent_inode->vfs_inode.i_mtime = now; parent_inode->vfs_inode.i_ctime = now; } - ret = btrfs_update_inode(trans, root, &parent_inode->vfs_inode); + ret = btrfs_update_inode(trans, root, parent_inode); if (ret) btrfs_abort_transaction(trans, ret); return ret; @@ -6196,7 +6538,7 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry, if (IS_ERR(trans)) return PTR_ERR(trans); - err = btrfs_find_free_ino(root, &objectid); + err = btrfs_get_free_objectid(root, &objectid); if (err) goto out_unlock; @@ -6227,7 +6569,7 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry, if (err) goto out_unlock; - btrfs_update_inode(trans, root, inode); + btrfs_update_inode(trans, root, BTRFS_I(inode)); d_instantiate_new(dentry, inode); out_unlock: @@ -6260,7 +6602,7 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry, if (IS_ERR(trans)) return PTR_ERR(trans); - err = btrfs_find_free_ino(root, &objectid); + err = btrfs_get_free_objectid(root, &objectid); if (err) goto out_unlock; @@ -6286,7 +6628,7 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry, if (err) goto out_unlock; - err = btrfs_update_inode(trans, root, inode); + err = btrfs_update_inode(trans, root, BTRFS_I(inode)); if (err) goto out_unlock; @@ -6358,7 +6700,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, } else { struct dentry *parent = dentry->d_parent; - err = btrfs_update_inode(trans, root, inode); + err = btrfs_update_inode(trans, root, BTRFS_I(inode)); if (err) goto fail; if (inode->i_nlink == 1) { @@ -6404,7 +6746,7 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) if (IS_ERR(trans)) return PTR_ERR(trans); - err = btrfs_find_free_ino(root, &objectid); + err = btrfs_get_free_objectid(root, &objectid); if (err) goto out_fail; @@ -6426,7 +6768,7 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) goto out_fail; btrfs_i_size_write(BTRFS_I(inode), 0); - err = btrfs_update_inode(trans, root, inode); + err = btrfs_update_inode(trans, root, BTRFS_I(inode)); if (err) goto out_fail; @@ -6563,12 +6905,14 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode, path->reada = READA_FORWARD; /* - * Unless we're going to uncompress the inline extent, no sleep would - * happen. + * The same explanation in load_free_space_cache applies here as well, + * we only read when we're loading the free space cache, and at that + * point the commit_root has everything we need. */ - path->leave_spinning = 1; - - path->recurse = btrfs_is_free_space_inode(inode); + if (btrfs_is_free_space_inode(inode)) { + path->search_commit_root = 1; + path->skip_locking = 1; + } ret = btrfs_lookup_file_extent(NULL, root, path, objectid, start, 0); if (ret < 0) { @@ -6670,7 +7014,6 @@ next: em->orig_start = em->start; ptr = btrfs_file_extent_inline_start(item) + extent_offset; - btrfs_set_path_blocking(path); if (!PageUptodate(page)) { if (btrfs_file_extent_compression(leaf, item) != BTRFS_COMPRESS_NONE) { @@ -6927,9 +7270,6 @@ static struct extent_map *btrfs_new_extent_direct(struct btrfs_inode *inode, * @strict: if true, omit optimizations that might force us into unnecessary * cow. e.g., don't trust generation number. * - * This function will flush ordered extents in the range to ensure proper - * nocow checks for (nowait == false) case. - * * Return: * >0 and update @len if we can do nocow write * 0 if we can't do nocow write @@ -7319,17 +7659,6 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start, int ret = 0; u64 len = length; bool unlock_extents = false; - bool sync = (current->journal_info == BTRFS_DIO_SYNC_STUB); - - /* - * We used current->journal_info here to see if we were sync, but - * there's a lot of tests in the enospc machinery to not do flushing if - * we have a journal_info set, so we need to clear this out and re-set - * it in iomap_end. - */ - ASSERT(current->journal_info == NULL || - current->journal_info == BTRFS_DIO_SYNC_STUB); - current->journal_info = NULL; if (!write) len = min_t(u64, len, fs_info->sectorsize); @@ -7355,7 +7684,6 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start, if (!dio_data) return -ENOMEM; - dio_data->sync = sync; dio_data->length = length; if (write) { dio_data->reserve = round_up(length, fs_info->sectorsize); @@ -7449,6 +7777,9 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start, iomap->bdev = fs_info->fs_devices->latest_bdev; iomap->length = len; + if (write && btrfs_use_zone_append(BTRFS_I(inode), em)) + iomap->flags |= IOMAP_F_ZONE_APPEND; + free_extent_map(em); return 0; @@ -7503,14 +7834,6 @@ static int btrfs_dio_iomap_end(struct inode *inode, loff_t pos, loff_t length, extent_changeset_free(dio_data->data_reserved); } out: - /* - * We're all done, we can re-set the current->journal_info now safely - * for our endio. - */ - if (dio_data->sync) { - ASSERT(current->journal_info == NULL); - current->journal_info = BTRFS_DIO_SYNC_STUB; - } kfree(dio_data); iomap->private = NULL; @@ -7526,7 +7849,7 @@ static void btrfs_dio_private_put(struct btrfs_dio_private *dip) if (!refcount_dec_and_test(&dip->refs)) return; - if (bio_op(dip->dio_bio) == REQ_OP_WRITE) { + if (btrfs_op(dip->dio_bio) == BTRFS_MAP_WRITE) { __endio_write_update_ordered(BTRFS_I(dip->inode), dip->logical_offset, dip->bytes, @@ -7574,7 +7897,7 @@ static blk_status_t btrfs_check_read_dio_bio(struct inode *inode, struct bio_vec bvec; struct bvec_iter iter; u64 start = io_bio->logical; - int icsum = 0; + u32 bio_offset = 0; blk_status_t err = BLK_STS_OK; __bio_for_each_segment(bvec, &io_bio->bio, iter, io_bio->iter) { @@ -7585,9 +7908,8 @@ static blk_status_t btrfs_check_read_dio_bio(struct inode *inode, for (i = 0; i < nr_sectors; i++) { ASSERT(pgoff < PAGE_SIZE); if (uptodate && - (!csum || !check_data_csum(inode, io_bio, icsum, - bvec.bv_page, pgoff, - start, sectorsize))) { + (!csum || !check_data_csum(inode, io_bio, + bio_offset, bvec.bv_page, pgoff))) { clean_io_failure(fs_info, failure_tree, io_tree, start, bvec.bv_page, btrfs_ino(BTRFS_I(inode)), @@ -7595,6 +7917,7 @@ static blk_status_t btrfs_check_read_dio_bio(struct inode *inode, } else { blk_status_t status; + ASSERT((start - io_bio->logical) < UINT_MAX); status = btrfs_submit_read_repair(inode, &io_bio->bio, start - io_bio->logical, @@ -7607,7 +7930,8 @@ static blk_status_t btrfs_check_read_dio_bio(struct inode *inode, err = status; } start += sectorsize; - icsum++; + ASSERT(bio_offset + sectorsize > bio_offset); + bio_offset += sectorsize; pgoff += sectorsize; } } @@ -7640,10 +7964,8 @@ static void __endio_write_update_ordered(struct btrfs_inode *inode, NULL); btrfs_queue_work(wq, &ordered->work); } - /* - * If btrfs_dec_test_ordered_pending does not find any ordered - * extent in the range, we can exit. - */ + + /* No ordered extent found in the range, exit */ if (ordered_offset == last_offset) return; /* @@ -7657,12 +7979,11 @@ static void __endio_write_update_ordered(struct btrfs_inode *inode, } } -static blk_status_t btrfs_submit_bio_start_direct_io(void *private_data, - struct bio *bio, u64 offset) +static blk_status_t btrfs_submit_bio_start_direct_io(struct inode *inode, + struct bio *bio, + u64 dio_file_offset) { - struct inode *inode = private_data; - - return btrfs_csum_one_bio(BTRFS_I(inode), bio, offset, 1); + return btrfs_csum_one_bio(BTRFS_I(inode), bio, dio_file_offset, 1); } static void btrfs_end_dio_bio(struct bio *bio) @@ -7674,8 +7995,7 @@ static void btrfs_end_dio_bio(struct bio *bio) btrfs_warn(BTRFS_I(dip->inode)->root->fs_info, "direct IO failed ino %llu rw %d,%u sector %#Lx len %u err no %d", btrfs_ino(BTRFS_I(dip->inode)), bio_op(bio), - bio->bi_opf, - (unsigned long long)bio->bi_iter.bi_sector, + bio->bi_opf, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, err); if (bio_op(bio) == REQ_OP_READ) { @@ -7686,6 +8006,8 @@ static void btrfs_end_dio_bio(struct bio *bio) if (err) dip->dio_bio->bi_status = err; + btrfs_record_physical_zoned(dip->inode, dip->logical_offset, bio); + bio_put(bio); btrfs_dio_private_put(dip); } @@ -7695,7 +8017,7 @@ static inline blk_status_t btrfs_submit_dio_bio(struct bio *bio, { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_dio_private *dip = bio->bi_private; - bool write = bio_op(bio) == REQ_OP_WRITE; + bool write = btrfs_op(bio) == BTRFS_MAP_WRITE; blk_status_t ret; /* Check btrfs_submit_bio_hook() for rules about async submit. */ @@ -7712,8 +8034,7 @@ static inline blk_status_t btrfs_submit_dio_bio(struct bio *bio, goto map; if (write && async_submit) { - ret = btrfs_wq_submit_bio(fs_info, bio, 0, 0, - file_offset, inode, + ret = btrfs_wq_submit_bio(inode, bio, 0, 0, file_offset, btrfs_submit_bio_start_direct_io); goto err; } else if (write) { @@ -7728,8 +8049,8 @@ static inline blk_status_t btrfs_submit_dio_bio(struct bio *bio, u64 csum_offset; csum_offset = file_offset - dip->logical_offset; - csum_offset >>= inode->i_sb->s_blocksize_bits; - csum_offset *= btrfs_super_csum_size(fs_info->super_copy); + csum_offset >>= fs_info->sectorsize_bits; + csum_offset *= fs_info->csum_size; btrfs_io_bio(bio)->csum = dip->csums + csum_offset; } map: @@ -7746,7 +8067,7 @@ static struct btrfs_dio_private *btrfs_create_dio_private(struct bio *dio_bio, struct inode *inode, loff_t file_offset) { - const bool write = (bio_op(dio_bio) == REQ_OP_WRITE); + const bool write = (btrfs_op(dio_bio) == BTRFS_MAP_WRITE); const bool csum = !(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM); size_t dip_size; struct btrfs_dio_private *dip; @@ -7754,11 +8075,10 @@ static struct btrfs_dio_private *btrfs_create_dio_private(struct bio *dio_bio, dip_size = sizeof(*dip); if (!write && csum) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - const u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); size_t nblocks; - nblocks = dio_bio->bi_iter.bi_size >> inode->i_sb->s_blocksize_bits; - dip_size += csum_size * nblocks; + nblocks = dio_bio->bi_iter.bi_size >> fs_info->sectorsize_bits; + dip_size += fs_info->csum_size * nblocks; } dip = kzalloc(dip_size, GFP_NOFS); @@ -7768,7 +8088,7 @@ static struct btrfs_dio_private *btrfs_create_dio_private(struct bio *dio_bio, dip->inode = inode; dip->logical_offset = file_offset; dip->bytes = dio_bio->bi_iter.bi_size; - dip->disk_bytenr = (u64)dio_bio->bi_iter.bi_sector << 9; + dip->disk_bytenr = dio_bio->bi_iter.bi_sector << 9; dip->dio_bio = dio_bio; refcount_set(&dip->refs, 1); return dip; @@ -7777,8 +8097,7 @@ static struct btrfs_dio_private *btrfs_create_dio_private(struct bio *dio_bio, static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap, struct bio *dio_bio, loff_t file_offset) { - const bool write = (bio_op(dio_bio) == REQ_OP_WRITE); - const bool csum = !(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM); + const bool write = (btrfs_op(dio_bio) == BTRFS_MAP_WRITE); struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); const bool raid56 = (btrfs_data_alloc_profile(fs_info) & BTRFS_BLOCK_GROUP_RAID56_MASK); @@ -7789,10 +8108,12 @@ static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap, u64 submit_len; int clone_offset = 0; int clone_len; + u64 logical; int ret; blk_status_t status; struct btrfs_io_geometry geom; struct btrfs_dio_data *dio_data = iomap->private; + struct extent_map *em = NULL; dip = btrfs_create_dio_private(dio_bio, inode, file_offset); if (!dip) { @@ -7805,13 +8126,14 @@ static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap, return BLK_QC_T_NONE; } - if (!write && csum) { + if (!write) { /* * Load the csums up front to reduce csum tree searches and * contention when submitting bios. + * + * If we have csums disabled this will do nothing. */ - status = btrfs_lookup_bio_sums(inode, dio_bio, file_offset, - dip->csums); + status = btrfs_lookup_bio_sums(inode, dio_bio, dip->csums); if (status != BLK_STS_OK) goto out_err; } @@ -7820,12 +8142,18 @@ static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap, submit_len = dio_bio->bi_iter.bi_size; do { - ret = btrfs_get_io_geometry(fs_info, btrfs_op(dio_bio), - start_sector << 9, submit_len, - &geom); + logical = start_sector << 9; + em = btrfs_get_chunk_map(fs_info, logical, submit_len); + if (IS_ERR(em)) { + status = errno_to_blk_status(PTR_ERR(em)); + em = NULL; + goto out_err_em; + } + ret = btrfs_get_io_geometry(fs_info, em, btrfs_op(dio_bio), + logical, submit_len, &geom); if (ret) { status = errno_to_blk_status(ret); - goto out_err; + goto out_err_em; } ASSERT(geom.len <= INT_MAX); @@ -7840,6 +8168,19 @@ static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap, bio->bi_end_io = btrfs_end_dio_bio; btrfs_io_bio(bio)->logical = file_offset; + WARN_ON_ONCE(write && btrfs_is_zoned(fs_info) && + fs_info->max_zone_append_size && + bio_op(bio) != REQ_OP_ZONE_APPEND); + + if (bio_op(bio) == REQ_OP_ZONE_APPEND) { + status = extract_ordered_extent(BTRFS_I(inode), bio, + file_offset); + if (status) { + bio_put(bio); + goto out_err; + } + } + ASSERT(submit_len >= clone_len); submit_len -= clone_len; @@ -7870,145 +8211,36 @@ static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap, bio_put(bio); if (submit_len > 0) refcount_dec(&dip->refs); - goto out_err; + goto out_err_em; } dio_data->submitted += clone_len; clone_offset += clone_len; start_sector += clone_len >> 9; file_offset += clone_len; + + free_extent_map(em); } while (submit_len > 0); return BLK_QC_T_NONE; +out_err_em: + free_extent_map(em); out_err: dip->dio_bio->bi_status = status; btrfs_dio_private_put(dip); - return BLK_QC_T_NONE; -} - -static ssize_t check_direct_IO(struct btrfs_fs_info *fs_info, - const struct iov_iter *iter, loff_t offset) -{ - int seg; - int i; - unsigned int blocksize_mask = fs_info->sectorsize - 1; - ssize_t retval = -EINVAL; - - if (offset & blocksize_mask) - goto out; - if (iov_iter_alignment(iter) & blocksize_mask) - goto out; - - /* If this is a write we don't need to check anymore */ - if (iov_iter_rw(iter) != READ || !iter_is_iovec(iter)) - return 0; - /* - * Check to make sure we don't have duplicate iov_base's in this - * iovec, if so return EINVAL, otherwise we'll get csum errors - * when reading back. - */ - for (seg = 0; seg < iter->nr_segs; seg++) { - for (i = seg + 1; i < iter->nr_segs; i++) { - if (iter->iov[seg].iov_base == iter->iov[i].iov_base) - goto out; - } - } - retval = 0; -out: - return retval; -} - -static inline int btrfs_maybe_fsync_end_io(struct kiocb *iocb, ssize_t size, - int error, unsigned flags) -{ - /* - * Now if we're still in the context of our submitter we know we can't - * safely run generic_write_sync(), so clear our flag here so that the - * caller knows to follow up with a sync. - */ - if (current->journal_info == BTRFS_DIO_SYNC_STUB) { - current->journal_info = NULL; - return error; - } - - if (error) - return error; - - if (size) { - iocb->ki_flags |= IOCB_DSYNC; - return generic_write_sync(iocb, size); - } - - return 0; + return BLK_QC_T_NONE; } -static const struct iomap_ops btrfs_dio_iomap_ops = { +const struct iomap_ops btrfs_dio_iomap_ops = { .iomap_begin = btrfs_dio_iomap_begin, .iomap_end = btrfs_dio_iomap_end, }; -static const struct iomap_dio_ops btrfs_dio_ops = { - .submit_io = btrfs_submit_direct, -}; - -static const struct iomap_dio_ops btrfs_sync_dops = { +const struct iomap_dio_ops btrfs_dio_ops = { .submit_io = btrfs_submit_direct, - .end_io = btrfs_maybe_fsync_end_io, }; -ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) -{ - struct file *file = iocb->ki_filp; - struct inode *inode = file->f_mapping->host; - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct extent_changeset *data_reserved = NULL; - loff_t offset = iocb->ki_pos; - size_t count = 0; - bool relock = false; - ssize_t ret; - - if (check_direct_IO(fs_info, iter, offset)) - return 0; - - count = iov_iter_count(iter); - if (iov_iter_rw(iter) == WRITE) { - /* - * If the write DIO is beyond the EOF, we need update - * the isize, but it is protected by i_mutex. So we can - * not unlock the i_mutex at this case. - */ - if (offset + count <= inode->i_size) { - inode_unlock(inode); - relock = true; - } - down_read(&BTRFS_I(inode)->dio_sem); - } - - /* - * We have are actually a sync iocb, so we need our fancy endio to know - * if we need to sync. - */ - if (current->journal_info) - ret = iomap_dio_rw(iocb, iter, &btrfs_dio_iomap_ops, - &btrfs_sync_dops, is_sync_kiocb(iocb)); - else - ret = iomap_dio_rw(iocb, iter, &btrfs_dio_iomap_ops, - &btrfs_dio_ops, is_sync_kiocb(iocb)); - - if (ret == -ENOTBLK) - ret = 0; - - if (iov_iter_rw(iter) == WRITE) - up_read(&BTRFS_I(inode)->dio_sem); - - if (relock) - inode_lock(inode); - - extent_changeset_free(data_reserved); - return ret; -} - static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len) { @@ -8078,7 +8310,7 @@ static int __btrfs_releasepage(struct page *page, gfp_t gfp_flags) { int ret = try_release_extent_mapping(page, gfp_flags); if (ret == 1) - detach_page_private(page); + clear_page_extent_mapped(page); return ret; } @@ -8128,6 +8360,8 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset, u64 start; u64 end; int inode_evicting = inode->vfs_inode.i_state & I_FREEING; + bool found_ordered = false; + bool completed_ordered = false; /* * we have the page locked, so new writeback can't start, @@ -8145,19 +8379,22 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset, if (!inode_evicting) lock_extent_bits(tree, page_start, page_end, &cached_state); -again: + start = page_start; +again: ordered = btrfs_lookup_ordered_range(inode, start, page_end - start + 1); if (ordered) { + found_ordered = true; end = min(page_end, ordered->file_offset + ordered->num_bytes - 1); /* - * IO on this page will never be started, so we need - * to account for any ordered extents now + * IO on this page will never be started, so we need to account + * for any ordered extents now. Don't clear EXTENT_DELALLOC_NEW + * here, must leave that up for the ordered extent completion. */ if (!inode_evicting) clear_extent_bit(tree, start, end, - EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | + EXTENT_DELALLOC | EXTENT_LOCKED | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 1, 0, &cached_state); /* @@ -8179,8 +8416,10 @@ again: if (btrfs_dec_test_ordered_pending(inode, &ordered, start, - end - start + 1, 1)) + end - start + 1, 1)) { btrfs_finish_ordered_io(ordered); + completed_ordered = true; + } } btrfs_put_ordered_extent(ordered); if (!inode_evicting) { @@ -8209,16 +8448,29 @@ again: */ btrfs_qgroup_free_data(inode, NULL, page_start, PAGE_SIZE); if (!inode_evicting) { + bool delete = true; + + /* + * If there's an ordered extent for this range and we have not + * finished it ourselves, we must leave EXTENT_DELALLOC_NEW set + * in the range for the ordered extent completion. We must also + * not delete the range, otherwise we would lose that bit (and + * any other bits set in the range). Make sure EXTENT_UPTODATE + * is cleared if we don't delete, otherwise it can lead to + * corruptions if the i_size is extented later. + */ + if (found_ordered && !completed_ordered) + delete = false; clear_extent_bit(tree, page_start, page_end, EXTENT_LOCKED | - EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | - EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 1, 1, - &cached_state); + EXTENT_DELALLOC | EXTENT_UPTODATE | + EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 1, + delete, &cached_state); __btrfs_releasepage(page, GFP_NOFS); } ClearPageChecked(page); - detach_page_private(page); + clear_page_extent_mapped(page); } /* @@ -8297,7 +8549,12 @@ again: wait_on_page_writeback(page); lock_extent_bits(io_tree, page_start, page_end, &cached_state); - set_page_extent_mapped(page); + ret2 = set_page_extent_mapped(page); + if (ret2 < 0) { + ret = vmf_error(ret2); + unlock_extent_cached(io_tree, page_start, page_end, &cached_state); + goto out_unlock; + } /* * we can't set the delalloc bits if there are pending ordered @@ -8461,14 +8718,14 @@ static int btrfs_truncate(struct inode *inode, bool skip_writeback) trans->block_rsv = rsv; while (1) { - ret = btrfs_truncate_inode_items(trans, root, inode, + ret = btrfs_truncate_inode_items(trans, root, BTRFS_I(inode), inode->i_size, BTRFS_EXTENT_DATA_KEY); trans->block_rsv = &fs_info->trans_block_rsv; if (ret != -ENOSPC && ret != -EAGAIN) break; - ret = btrfs_update_inode(trans, root, inode); + ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); if (ret) break; @@ -8499,7 +8756,7 @@ static int btrfs_truncate(struct inode *inode, bool skip_writeback) btrfs_end_transaction(trans); btrfs_btree_balance_dirty(fs_info); - ret = btrfs_truncate_block(inode, inode->i_size, 0, 0); + ret = btrfs_truncate_block(BTRFS_I(inode), inode->i_size, 0, 0); if (ret) goto out; trans = btrfs_start_transaction(root, 1); @@ -8507,14 +8764,14 @@ static int btrfs_truncate(struct inode *inode, bool skip_writeback) ret = PTR_ERR(trans); goto out; } - btrfs_inode_safe_disk_i_size_write(inode, 0); + btrfs_inode_safe_disk_i_size_write(BTRFS_I(inode), 0); } if (trans) { int ret2; trans->block_rsv = &fs_info->trans_block_rsv; - ret2 = btrfs_update_inode(trans, root, inode); + ret2 = btrfs_update_inode(trans, root, BTRFS_I(inode)); if (ret2 && !ret) ret = ret2; @@ -8534,15 +8791,18 @@ out: */ int btrfs_create_subvol_root(struct btrfs_trans_handle *trans, struct btrfs_root *new_root, - struct btrfs_root *parent_root, - u64 new_dirid) + struct btrfs_root *parent_root) { struct inode *inode; int err; u64 index = 0; + u64 ino; - inode = btrfs_new_inode(trans, new_root, NULL, "..", 2, - new_dirid, new_dirid, + err = btrfs_get_free_objectid(new_root, &ino); + if (err < 0) + return err; + + inode = btrfs_new_inode(trans, new_root, NULL, "..", 2, ino, ino, S_IFDIR | (~current_umask() & S_IRWXUGO), &index); if (IS_ERR(inode)) @@ -8560,7 +8820,7 @@ int btrfs_create_subvol_root(struct btrfs_trans_handle *trans, "error inheriting subvolume %llu properties: %d", new_root->root_key.objectid, err); - err = btrfs_update_inode(trans, new_root, inode); + err = btrfs_update_inode(trans, new_root, BTRFS_I(inode)); iput(inode); return err; @@ -8622,7 +8882,6 @@ struct inode *btrfs_alloc_inode(struct super_block *sb) INIT_LIST_HEAD(&ei->delalloc_inodes); INIT_LIST_HEAD(&ei->delayed_iput); RB_CLEAR_NODE(&ei->rb_node); - init_rwsem(&ei->dio_sem); return inode; } @@ -8762,6 +9021,7 @@ static int btrfs_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { u64 delalloc_bytes; + u64 inode_bytes; struct inode *inode = d_inode(path->dentry); u32 blocksize = inode->i_sb->s_blocksize; u32 bi_flags = BTRFS_I(inode)->flags; @@ -8788,8 +9048,9 @@ static int btrfs_getattr(const struct path *path, struct kstat *stat, spin_lock(&BTRFS_I(inode)->lock); delalloc_bytes = BTRFS_I(inode)->new_delalloc_bytes; + inode_bytes = inode_get_bytes(inode); spin_unlock(&BTRFS_I(inode)->lock); - stat->blocks = (ALIGN(inode_get_bytes(inode), blocksize) + + stat->blocks = (ALIGN(inode_bytes, blocksize) + ALIGN(delalloc_bytes, blocksize)) >> 9; return 0; } @@ -8915,7 +9176,7 @@ static int btrfs_rename_exchange(struct inode *old_dir, old_dentry->d_name.name, old_dentry->d_name.len); if (!ret) - ret = btrfs_update_inode(trans, root, old_inode); + ret = btrfs_update_inode(trans, root, BTRFS_I(old_inode)); } if (ret) { btrfs_abort_transaction(trans, ret); @@ -8931,7 +9192,7 @@ static int btrfs_rename_exchange(struct inode *old_dir, new_dentry->d_name.name, new_dentry->d_name.len); if (!ret) - ret = btrfs_update_inode(trans, dest, new_inode); + ret = btrfs_update_inode(trans, dest, BTRFS_I(new_inode)); } if (ret) { btrfs_abort_transaction(trans, ret); @@ -9020,7 +9281,7 @@ static int btrfs_whiteout_for_rename(struct btrfs_trans_handle *trans, u64 objectid; u64 index; - ret = btrfs_find_free_ino(root, &objectid); + ret = btrfs_get_free_objectid(root, &objectid); if (ret) return ret; @@ -9051,7 +9312,7 @@ static int btrfs_whiteout_for_rename(struct btrfs_trans_handle *trans, if (ret) goto out; - ret = btrfs_update_inode(trans, root, inode); + ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); out: unlock_new_inode(inode); if (ret) @@ -9185,7 +9446,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, old_dentry->d_name.name, old_dentry->d_name.len); if (!ret) - ret = btrfs_update_inode(trans, root, old_inode); + ret = btrfs_update_inode(trans, root, BTRFS_I(old_inode)); } if (ret) { btrfs_abort_transaction(trans, ret); @@ -9331,7 +9592,9 @@ static struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode * some fairly slow code that needs optimization. This walks the list * of all the inodes with pending delalloc and forces them to disk. */ -static int start_delalloc_inodes(struct btrfs_root *root, u64 *nr, bool snapshot) +static int start_delalloc_inodes(struct btrfs_root *root, + struct writeback_control *wbc, bool snapshot, + bool in_reclaim_context) { struct btrfs_inode *binode; struct inode *inode; @@ -9339,6 +9602,7 @@ static int start_delalloc_inodes(struct btrfs_root *root, u64 *nr, bool snapshot struct list_head works; struct list_head splice; int ret = 0; + bool full_flush = wbc->nr_to_write == LONG_MAX; INIT_LIST_HEAD(&works); INIT_LIST_HEAD(&splice); @@ -9352,6 +9616,11 @@ static int start_delalloc_inodes(struct btrfs_root *root, u64 *nr, bool snapshot list_move_tail(&binode->delalloc_inodes, &root->delalloc_inodes); + + if (in_reclaim_context && + test_bit(BTRFS_INODE_NO_DELALLOC_FLUSH, &binode->runtime_flags)) + continue; + inode = igrab(&binode->vfs_inode); if (!inode) { cond_resched_lock(&root->delalloc_lock); @@ -9362,18 +9631,24 @@ static int start_delalloc_inodes(struct btrfs_root *root, u64 *nr, bool snapshot if (snapshot) set_bit(BTRFS_INODE_SNAPSHOT_FLUSH, &binode->runtime_flags); - work = btrfs_alloc_delalloc_work(inode); - if (!work) { - iput(inode); - ret = -ENOMEM; - goto out; - } - list_add_tail(&work->list, &works); - btrfs_queue_work(root->fs_info->flush_workers, - &work->work); - if (*nr != U64_MAX) { - (*nr)--; - if (*nr == 0) + if (full_flush) { + work = btrfs_alloc_delalloc_work(inode); + if (!work) { + iput(inode); + ret = -ENOMEM; + goto out; + } + list_add_tail(&work->list, &works); + btrfs_queue_work(root->fs_info->flush_workers, + &work->work); + } else { + ret = sync_inode(inode, wbc); + if (!ret && + test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT, + &BTRFS_I(inode)->runtime_flags)) + ret = sync_inode(inode, wbc); + btrfs_add_delayed_iput(inode); + if (ret || wbc->nr_to_write <= 0) goto out; } cond_resched(); @@ -9399,17 +9674,29 @@ out: int btrfs_start_delalloc_snapshot(struct btrfs_root *root) { + struct writeback_control wbc = { + .nr_to_write = LONG_MAX, + .sync_mode = WB_SYNC_NONE, + .range_start = 0, + .range_end = LLONG_MAX, + }; struct btrfs_fs_info *fs_info = root->fs_info; - u64 nr = U64_MAX; if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) return -EROFS; - return start_delalloc_inodes(root, &nr, true); + return start_delalloc_inodes(root, &wbc, true, false); } -int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr) +int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, long nr, + bool in_reclaim_context) { + struct writeback_control wbc = { + .nr_to_write = nr, + .sync_mode = WB_SYNC_NONE, + .range_start = 0, + .range_end = LLONG_MAX, + }; struct btrfs_root *root; struct list_head splice; int ret; @@ -9422,7 +9709,14 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr) mutex_lock(&fs_info->delalloc_root_mutex); spin_lock(&fs_info->delalloc_root_lock); list_splice_init(&fs_info->delalloc_roots, &splice); - while (!list_empty(&splice) && nr) { + while (!list_empty(&splice)) { + /* + * Reset nr_to_write here so we know that we're doing a full + * flush. + */ + if (nr == LONG_MAX) + wbc.nr_to_write = LONG_MAX; + root = list_first_entry(&splice, struct btrfs_root, delalloc_root); root = btrfs_grab_root(root); @@ -9431,9 +9725,9 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr) &fs_info->delalloc_roots); spin_unlock(&fs_info->delalloc_root_lock); - ret = start_delalloc_inodes(root, &nr, false); + ret = start_delalloc_inodes(root, &wbc, false, in_reclaim_context); btrfs_put_root(root); - if (ret < 0) + if (ret < 0 || wbc.nr_to_write <= 0) goto out; spin_lock(&fs_info->delalloc_root_lock); } @@ -9483,7 +9777,7 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry, if (IS_ERR(trans)) return PTR_ERR(trans); - err = btrfs_find_free_ino(root, &objectid); + err = btrfs_get_free_objectid(root, &objectid); if (err) goto out_unlock; @@ -9545,7 +9839,7 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry, inode_nohighmem(inode); inode_set_bytes(inode, name_len); btrfs_i_size_write(BTRFS_I(inode), name_len); - err = btrfs_update_inode(trans, root, inode); + err = btrfs_update_inode(trans, root, BTRFS_I(inode)); /* * Last step, add directory indexes for our symlink inode. This is the * last step to avoid extra cleanup of these indexes if an error happens @@ -9571,7 +9865,8 @@ out_unlock: static struct btrfs_trans_handle *insert_prealloc_file_extent( struct btrfs_trans_handle *trans_in, - struct inode *inode, struct btrfs_key *ins, + struct btrfs_inode *inode, + struct btrfs_key *ins, u64 file_offset) { struct btrfs_file_extent_item stack_fi; @@ -9592,13 +9887,14 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent( btrfs_set_stack_file_extent_compression(&stack_fi, BTRFS_COMPRESS_NONE); /* Encryption and other encoding is reserved and all 0 */ - ret = btrfs_qgroup_release_data(BTRFS_I(inode), file_offset, len); + ret = btrfs_qgroup_release_data(inode, file_offset, len); if (ret < 0) return ERR_PTR(ret); if (trans) { - ret = insert_reserved_file_extent(trans, BTRFS_I(inode), - file_offset, &stack_fi, ret); + ret = insert_reserved_file_extent(trans, inode, + file_offset, &stack_fi, + true, ret); if (ret) return ERR_PTR(ret); return trans; @@ -9618,7 +9914,7 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent( if (!path) return ERR_PTR(-ENOMEM); - ret = btrfs_replace_file_extents(inode, path, file_offset, + ret = btrfs_replace_file_extents(&inode->vfs_inode, path, file_offset, file_offset + len - 1, &extent_info, &trans); btrfs_free_path(path); @@ -9672,10 +9968,17 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode, * clear_offset by our extent size. */ clear_offset += ins.offset; - btrfs_dec_block_group_reservations(fs_info, ins.objectid); last_alloc = ins.offset; - trans = insert_prealloc_file_extent(trans, inode, &ins, cur_offset); + trans = insert_prealloc_file_extent(trans, BTRFS_I(inode), + &ins, cur_offset); + /* + * Now that we inserted the prealloc extent we can finally + * decrement the number of reservations in the block group. + * If we did it before, we could race with relocation and have + * relocation miss the reserved extent, making it fail later. + */ + btrfs_dec_block_group_reservations(fs_info, ins.objectid); if (IS_ERR(trans)) { ret = PTR_ERR(trans); btrfs_free_reserved_extent(fs_info, ins.objectid, @@ -9730,10 +10033,10 @@ next: else i_size = cur_offset; i_size_write(inode, i_size); - btrfs_inode_safe_disk_i_size_write(inode, 0); + btrfs_inode_safe_disk_i_size_write(BTRFS_I(inode), 0); } - ret = btrfs_update_inode(trans, root, inode); + ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); if (ret) { btrfs_abort_transaction(trans, ret); @@ -9808,7 +10111,7 @@ static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) if (IS_ERR(trans)) return PTR_ERR(trans); - ret = btrfs_find_free_ino(root, &objectid); + ret = btrfs_get_free_objectid(root, &objectid); if (ret) goto out; @@ -9829,7 +10132,7 @@ static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) if (ret) goto out; - ret = btrfs_update_inode(trans, root, inode); + ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); if (ret) goto out; ret = btrfs_orphan_add(trans, BTRFS_I(inode)); @@ -10208,6 +10511,27 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, } #endif +/* + * Update the number of bytes used in the VFS' inode. When we replace extents in + * a range (clone, dedupe, fallocate's zero range), we must update the number of + * bytes used by the inode in an atomic manner, so that concurrent stat(2) calls + * always get a correct value. + */ +void btrfs_update_inode_bytes(struct btrfs_inode *inode, + const u64 add_bytes, + const u64 del_bytes) +{ + if (add_bytes == del_bytes) + return; + + spin_lock(&inode->lock); + if (del_bytes > 0) + inode_sub_bytes(&inode->vfs_inode, del_bytes); + if (add_bytes > 0) + inode_add_bytes(&inode->vfs_inode, add_bytes); + spin_unlock(&inode->lock); +} + static const struct inode_operations btrfs_dir_inode_operations = { .getattr = btrfs_getattr, .lookup = btrfs_lookup, diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index ab408a23ba32..a8c60d46d19c 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -34,7 +34,6 @@ #include "print-tree.h" #include "volumes.h" #include "locking.h" -#include "inode-map.h" #include "backref.h" #include "rcu-string.h" #include "send.h" @@ -193,6 +192,15 @@ static int check_fsflags(unsigned int old_flags, unsigned int flags) return 0; } +static int check_fsflags_compatible(struct btrfs_fs_info *fs_info, + unsigned int flags) +{ + if (btrfs_is_zoned(fs_info) && (flags & FS_NOCOW_FL)) + return -EPERM; + + return 0; +} + static int btrfs_ioctl_setflags(struct file *file, void __user *arg) { struct inode *inode = file_inode(file); @@ -230,6 +238,10 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) if (ret) goto out_unlock; + ret = check_fsflags_compatible(fs_info, fsflags); + if (ret) + goto out_unlock; + binode_flags = binode->flags; if (fsflags & FS_SYNC_FL) binode_flags |= BTRFS_INODE_SYNC; @@ -336,7 +348,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) btrfs_sync_inode_flags_to_i_flags(inode); inode_inc_iversion(inode); inode->i_ctime = current_time(inode); - ret = btrfs_update_inode(trans, root, inode); + ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); out_end_trans: btrfs_end_transaction(trans); @@ -479,7 +491,7 @@ static int btrfs_ioctl_fssetxattr(struct file *file, void __user *arg) btrfs_sync_inode_flags_to_i_flags(inode); inode_inc_iversion(inode); inode->i_ctime = current_time(inode); - ret = btrfs_update_inode(trans, root, inode); + ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); btrfs_end_transaction(trans); @@ -516,6 +528,14 @@ static noinline int btrfs_ioctl_fitrim(struct btrfs_fs_info *fs_info, return -EPERM; /* + * btrfs_trim_block_group() depends on space cache, which is not + * available in zoned filesystem. So, disallow fitrim on a zoned + * filesystem for now. + */ + if (btrfs_is_zoned(fs_info)) + return -EOPNOTSUPP; + + /* * If the fs is mounted with nologreplay, which requires it to be * mounted in RO mode as well, we can not allow discard on free space * inside block groups, because log trees refer to extents that are not @@ -594,14 +614,13 @@ static noinline int create_subvol(struct inode *dir, int err; dev_t anon_dev = 0; u64 objectid; - u64 new_dirid = BTRFS_FIRST_FREE_OBJECTID; u64 index = 0; root_item = kzalloc(sizeof(*root_item), GFP_KERNEL); if (!root_item) return -ENOMEM; - ret = btrfs_find_free_objectid(fs_info->tree_root, &objectid); + ret = btrfs_get_free_objectid(fs_info->tree_root, &objectid); if (ret) goto fail_free; @@ -681,7 +700,7 @@ static noinline int create_subvol(struct inode *dir, free_extent_buffer(leaf); leaf = NULL; - btrfs_set_root_dirid(root_item, new_dirid); + btrfs_set_root_dirid(root_item, BTRFS_FIRST_FREE_OBJECTID); key.objectid = objectid; key.offset = 0; @@ -704,7 +723,7 @@ static noinline int create_subvol(struct inode *dir, btrfs_record_root_in_trans(trans, new_root); - ret = btrfs_create_subvol_root(trans, new_root, root, new_dirid); + ret = btrfs_create_subvol_root(trans, new_root, root); btrfs_put_root(new_root); if (ret) { /* We potentially lose an unused inode item here */ @@ -712,10 +731,6 @@ static noinline int create_subvol(struct inode *dir, goto fail; } - mutex_lock(&new_root->objectid_mutex); - new_root->highest_objectid = new_dirid; - mutex_unlock(&new_root->objectid_mutex); - /* * insert the directory item */ @@ -733,7 +748,7 @@ static noinline int create_subvol(struct inode *dir, } btrfs_i_size_write(BTRFS_I(dir), dir->i_size + namelen * 2); - ret = btrfs_update_inode(trans, root, dir); + ret = btrfs_update_inode(trans, root, BTRFS_I(dir)); if (ret) { btrfs_abort_transaction(trans, ret); goto fail; @@ -1274,6 +1289,8 @@ static int cluster_pages_for_defrag(struct inode *inode, u64 page_start; u64 page_end; u64 page_cnt; + u64 start = (u64)start_index << PAGE_SHIFT; + u64 search_start; int ret; int i; int i_done; @@ -1290,8 +1307,7 @@ static int cluster_pages_for_defrag(struct inode *inode, page_cnt = min_t(u64, (u64)num_pages, (u64)file_end - start_index + 1); ret = btrfs_delalloc_reserve_space(BTRFS_I(inode), &data_reserved, - start_index << PAGE_SHIFT, - page_cnt << PAGE_SHIFT); + start, page_cnt << PAGE_SHIFT); if (ret) return ret; i_done = 0; @@ -1306,6 +1322,13 @@ again: if (!page) break; + ret = set_page_extent_mapped(page); + if (ret < 0) { + unlock_page(page); + put_page(page); + break; + } + page_start = page_offset(page); page_end = page_start + PAGE_SIZE - 1; while (1) { @@ -1371,6 +1394,40 @@ again: lock_extent_bits(&BTRFS_I(inode)->io_tree, page_start, page_end - 1, &cached_state); + + /* + * When defragmenting we skip ranges that have holes or inline extents, + * (check should_defrag_range()), to avoid unnecessary IO and wasting + * space. At btrfs_defrag_file(), we check if a range should be defragged + * before locking the inode and then, if it should, we trigger a sync + * page cache readahead - we lock the inode only after that to avoid + * blocking for too long other tasks that possibly want to operate on + * other file ranges. But before we were able to get the inode lock, + * some other task may have punched a hole in the range, or we may have + * now an inline extent, in which case we should not defrag. So check + * for that here, where we have the inode and the range locked, and bail + * out if that happened. + */ + search_start = page_start; + while (search_start < page_end) { + struct extent_map *em; + + em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, search_start, + page_end - search_start); + if (IS_ERR(em)) { + ret = PTR_ERR(em); + goto out_unlock_range; + } + if (em->block_start >= EXTENT_MAP_LAST_BYTE) { + free_extent_map(em); + /* Ok, 0 means we did not defrag anything */ + ret = 0; + goto out_unlock_range; + } + search_start = extent_map_end(em); + free_extent_map(em); + } + clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start, page_end - 1, EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0, &cached_state); @@ -1380,8 +1437,7 @@ again: btrfs_mod_outstanding_extents(BTRFS_I(inode), 1); spin_unlock(&BTRFS_I(inode)->lock); btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved, - start_index << PAGE_SHIFT, - (page_cnt - i_done) << PAGE_SHIFT, true); + start, (page_cnt - i_done) << PAGE_SHIFT, true); } @@ -1394,7 +1450,6 @@ again: for (i = 0; i < i_done; i++) { clear_page_dirty_for_io(pages[i]); ClearPageChecked(pages[i]); - set_page_extent_mapped(pages[i]); set_page_dirty(pages[i]); unlock_page(pages[i]); put_page(pages[i]); @@ -1402,14 +1457,17 @@ again: btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT); extent_changeset_free(data_reserved); return i_done; + +out_unlock_range: + unlock_extent_cached(&BTRFS_I(inode)->io_tree, + page_start, page_end - 1, &cached_state); out: for (i = 0; i < i_done; i++) { unlock_page(pages[i]); put_page(pages[i]); } btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved, - start_index << PAGE_SHIFT, - page_cnt << PAGE_SHIFT, true); + start, page_cnt << PAGE_SHIFT, true); btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT); extent_changeset_free(data_reserved); return ret; @@ -1680,7 +1738,7 @@ static noinline int btrfs_ioctl_resize(struct file *file, btrfs_info(fs_info, "resizing devid %llu", devid); } - device = btrfs_find_device(fs_info->fs_devices, devid, NULL, NULL, true); + device = btrfs_find_device(fs_info->fs_devices, devid, NULL, NULL); if (!device) { btrfs_info(fs_info, "resizer unable to find device %llu", devid); @@ -3323,7 +3381,7 @@ static long btrfs_ioctl_dev_info(struct btrfs_fs_info *fs_info, rcu_read_lock(); dev = btrfs_find_device(fs_info->fs_devices, di_args->devid, s_uuid, - NULL, true); + NULL); if (!dev) { ret = -ENODEV; @@ -3395,7 +3453,6 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp) ret = -ENOMEM; goto out_free; } - path->leave_spinning = 1; trans = btrfs_start_transaction(root, 1); if (IS_ERR(trans)) { @@ -4903,7 +4960,7 @@ long btrfs_ioctl(struct file *file, unsigned int case BTRFS_IOC_SYNC: { int ret; - ret = btrfs_start_delalloc_roots(fs_info, U64_MAX); + ret = btrfs_start_delalloc_roots(fs_info, LONG_MAX, false); if (ret) return ret; ret = btrfs_sync_fs(inode->i_sb, 1); diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c index 66e02ebdd340..5fafc5e89bb7 100644 --- a/fs/btrfs/locking.c +++ b/fs/btrfs/locking.c @@ -17,404 +17,89 @@ * Extent buffer locking * ===================== * - * The locks use a custom scheme that allows to do more operations than are - * available fromt current locking primitives. The building blocks are still - * rwlock and wait queues. - * - * Required semantics: + * We use a rw_semaphore for tree locking, and the semantics are exactly the + * same: * * - reader/writer exclusion * - writer/writer exclusion * - reader/reader sharing - * - spinning lock semantics - * - blocking lock semantics * - try-lock semantics for readers and writers - * - one level nesting, allowing read lock to be taken by the same thread that - * already has write lock - * - * The extent buffer locks (also called tree locks) manage access to eb data - * related to the storage in the b-tree (keys, items, but not the individual - * members of eb). - * We want concurrency of many readers and safe updates. The underlying locking - * is done by read-write spinlock and the blocking part is implemented using - * counters and wait queues. - * - * spinning semantics - the low-level rwlock is held so all other threads that - * want to take it are spinning on it. - * - * blocking semantics - the low-level rwlock is not held but the counter - * denotes how many times the blocking lock was held; - * sleeping is possible - * - * Write lock always allows only one thread to access the data. - * - * - * Debugging - * --------- - * - * There are additional state counters that are asserted in various contexts, - * removed from non-debug build to reduce extent_buffer size and for - * performance reasons. - * - * - * Lock recursion - * -------------- - * - * A write operation on a tree might indirectly start a look up on the same - * tree. This can happen when btrfs_cow_block locks the tree and needs to - * lookup free extents. - * - * btrfs_cow_block - * .. - * alloc_tree_block_no_bg_flush - * btrfs_alloc_tree_block - * btrfs_reserve_extent - * .. - * load_free_space_cache - * .. - * btrfs_lookup_file_extent - * btrfs_search_slot - * - * - * Locking pattern - spinning - * -------------------------- - * - * The simple locking scenario, the +--+ denotes the spinning section. - * - * +- btrfs_tree_lock - * | - extent_buffer::rwlock is held - * | - no heavy operations should happen, eg. IO, memory allocations, large - * | structure traversals - * +- btrfs_tree_unock -* -* - * Locking pattern - blocking - * -------------------------- - * - * The blocking write uses the following scheme. The +--+ denotes the spinning - * section. - * - * +- btrfs_tree_lock - * | - * +- btrfs_set_lock_blocking_write - * - * - allowed: IO, memory allocations, etc. - * - * -- btrfs_tree_unlock - note, no explicit unblocking necessary - * - * - * Blocking read is similar. - * - * +- btrfs_tree_read_lock - * | - * +- btrfs_set_lock_blocking_read - * - * - heavy operations allowed - * - * +- btrfs_tree_read_unlock_blocking - * | - * +- btrfs_tree_read_unlock - * - */ - -#ifdef CONFIG_BTRFS_DEBUG -static inline void btrfs_assert_spinning_writers_get(struct extent_buffer *eb) -{ - WARN_ON(eb->spinning_writers); - eb->spinning_writers++; -} - -static inline void btrfs_assert_spinning_writers_put(struct extent_buffer *eb) -{ - WARN_ON(eb->spinning_writers != 1); - eb->spinning_writers--; -} - -static inline void btrfs_assert_no_spinning_writers(struct extent_buffer *eb) -{ - WARN_ON(eb->spinning_writers); -} - -static inline void btrfs_assert_spinning_readers_get(struct extent_buffer *eb) -{ - atomic_inc(&eb->spinning_readers); -} - -static inline void btrfs_assert_spinning_readers_put(struct extent_buffer *eb) -{ - WARN_ON(atomic_read(&eb->spinning_readers) == 0); - atomic_dec(&eb->spinning_readers); -} - -static inline void btrfs_assert_tree_read_locks_get(struct extent_buffer *eb) -{ - atomic_inc(&eb->read_locks); -} - -static inline void btrfs_assert_tree_read_locks_put(struct extent_buffer *eb) -{ - atomic_dec(&eb->read_locks); -} - -static inline void btrfs_assert_tree_read_locked(struct extent_buffer *eb) -{ - BUG_ON(!atomic_read(&eb->read_locks)); -} - -static inline void btrfs_assert_tree_write_locks_get(struct extent_buffer *eb) -{ - eb->write_locks++; -} - -static inline void btrfs_assert_tree_write_locks_put(struct extent_buffer *eb) -{ - eb->write_locks--; -} - -#else -static void btrfs_assert_spinning_writers_get(struct extent_buffer *eb) { } -static void btrfs_assert_spinning_writers_put(struct extent_buffer *eb) { } -static void btrfs_assert_no_spinning_writers(struct extent_buffer *eb) { } -static void btrfs_assert_spinning_readers_put(struct extent_buffer *eb) { } -static void btrfs_assert_spinning_readers_get(struct extent_buffer *eb) { } -static void btrfs_assert_tree_read_locked(struct extent_buffer *eb) { } -static void btrfs_assert_tree_read_locks_get(struct extent_buffer *eb) { } -static void btrfs_assert_tree_read_locks_put(struct extent_buffer *eb) { } -static void btrfs_assert_tree_write_locks_get(struct extent_buffer *eb) { } -static void btrfs_assert_tree_write_locks_put(struct extent_buffer *eb) { } -#endif - -/* - * Mark already held read lock as blocking. Can be nested in write lock by the - * same thread. - * - * Use when there are potentially long operations ahead so other thread waiting - * on the lock will not actively spin but sleep instead. - * - * The rwlock is released and blocking reader counter is increased. - */ -void btrfs_set_lock_blocking_read(struct extent_buffer *eb) -{ - trace_btrfs_set_lock_blocking_read(eb); - /* - * No lock is required. The lock owner may change if we have a read - * lock, but it won't change to or away from us. If we have the write - * lock, we are the owner and it'll never change. - */ - if (eb->lock_recursed && current->pid == eb->lock_owner) - return; - btrfs_assert_tree_read_locked(eb); - atomic_inc(&eb->blocking_readers); - btrfs_assert_spinning_readers_put(eb); - read_unlock(&eb->lock); -} - -/* - * Mark already held write lock as blocking. - * - * Use when there are potentially long operations ahead so other threads - * waiting on the lock will not actively spin but sleep instead. * - * The rwlock is released and blocking writers is set. + * The rwsem implementation does opportunistic spinning which reduces number of + * times the locking task needs to sleep. */ -void btrfs_set_lock_blocking_write(struct extent_buffer *eb) -{ - trace_btrfs_set_lock_blocking_write(eb); - /* - * No lock is required. The lock owner may change if we have a read - * lock, but it won't change to or away from us. If we have the write - * lock, we are the owner and it'll never change. - */ - if (eb->lock_recursed && current->pid == eb->lock_owner) - return; - if (eb->blocking_writers == 0) { - btrfs_assert_spinning_writers_put(eb); - btrfs_assert_tree_locked(eb); - WRITE_ONCE(eb->blocking_writers, 1); - write_unlock(&eb->lock); - } -} /* - * Lock the extent buffer for read. Wait for any writers (spinning or blocking). - * Can be nested in write lock by the same thread. + * __btrfs_tree_read_lock - lock extent buffer for read + * @eb: the eb to be locked + * @nest: the nesting level to be used for lockdep * - * Use when the locked section does only lightweight actions and busy waiting - * would be cheaper than making other threads do the wait/wake loop. - * - * The rwlock is held upon exit. + * This takes the read lock on the extent buffer, using the specified nesting + * level for lockdep purposes. */ -void __btrfs_tree_read_lock(struct extent_buffer *eb, enum btrfs_lock_nesting nest, - bool recurse) +void __btrfs_tree_read_lock(struct extent_buffer *eb, enum btrfs_lock_nesting nest) { u64 start_ns = 0; if (trace_btrfs_tree_read_lock_enabled()) start_ns = ktime_get_ns(); -again: - read_lock(&eb->lock); - BUG_ON(eb->blocking_writers == 0 && - current->pid == eb->lock_owner); - if (eb->blocking_writers) { - if (current->pid == eb->lock_owner) { - /* - * This extent is already write-locked by our thread. - * We allow an additional read lock to be added because - * it's for the same thread. btrfs_find_all_roots() - * depends on this as it may be called on a partly - * (write-)locked tree. - */ - WARN_ON(!recurse); - BUG_ON(eb->lock_recursed); - eb->lock_recursed = true; - read_unlock(&eb->lock); - trace_btrfs_tree_read_lock(eb, start_ns); - return; - } - read_unlock(&eb->lock); - wait_event(eb->write_lock_wq, - READ_ONCE(eb->blocking_writers) == 0); - goto again; - } - btrfs_assert_tree_read_locks_get(eb); - btrfs_assert_spinning_readers_get(eb); + + down_read_nested(&eb->lock, nest); + eb->lock_owner = current->pid; trace_btrfs_tree_read_lock(eb, start_ns); } void btrfs_tree_read_lock(struct extent_buffer *eb) { - __btrfs_tree_read_lock(eb, BTRFS_NESTING_NORMAL, false); -} - -/* - * Lock extent buffer for read, optimistically expecting that there are no - * contending blocking writers. If there are, don't wait. - * - * Return 1 if the rwlock has been taken, 0 otherwise - */ -int btrfs_tree_read_lock_atomic(struct extent_buffer *eb) -{ - if (READ_ONCE(eb->blocking_writers)) - return 0; - - read_lock(&eb->lock); - /* Refetch value after lock */ - if (READ_ONCE(eb->blocking_writers)) { - read_unlock(&eb->lock); - return 0; - } - btrfs_assert_tree_read_locks_get(eb); - btrfs_assert_spinning_readers_get(eb); - trace_btrfs_tree_read_lock_atomic(eb); - return 1; + __btrfs_tree_read_lock(eb, BTRFS_NESTING_NORMAL); } /* - * Try-lock for read. Don't block or wait for contending writers. + * Try-lock for read. * * Retrun 1 if the rwlock has been taken, 0 otherwise */ int btrfs_try_tree_read_lock(struct extent_buffer *eb) { - if (READ_ONCE(eb->blocking_writers)) - return 0; - - if (!read_trylock(&eb->lock)) - return 0; - - /* Refetch value after lock */ - if (READ_ONCE(eb->blocking_writers)) { - read_unlock(&eb->lock); - return 0; + if (down_read_trylock(&eb->lock)) { + eb->lock_owner = current->pid; + trace_btrfs_try_tree_read_lock(eb); + return 1; } - btrfs_assert_tree_read_locks_get(eb); - btrfs_assert_spinning_readers_get(eb); - trace_btrfs_try_tree_read_lock(eb); - return 1; + return 0; } /* - * Try-lock for write. May block until the lock is uncontended, but does not - * wait until it is free. + * Try-lock for write. * * Retrun 1 if the rwlock has been taken, 0 otherwise */ int btrfs_try_tree_write_lock(struct extent_buffer *eb) { - if (READ_ONCE(eb->blocking_writers) || atomic_read(&eb->blocking_readers)) - return 0; - - write_lock(&eb->lock); - /* Refetch value after lock */ - if (READ_ONCE(eb->blocking_writers) || atomic_read(&eb->blocking_readers)) { - write_unlock(&eb->lock); - return 0; + if (down_write_trylock(&eb->lock)) { + eb->lock_owner = current->pid; + trace_btrfs_try_tree_write_lock(eb); + return 1; } - btrfs_assert_tree_write_locks_get(eb); - btrfs_assert_spinning_writers_get(eb); - eb->lock_owner = current->pid; - trace_btrfs_try_tree_write_lock(eb); - return 1; + return 0; } /* - * Release read lock. Must be used only if the lock is in spinning mode. If - * the read lock is nested, must pair with read lock before the write unlock. - * - * The rwlock is not held upon exit. + * Release read lock. */ void btrfs_tree_read_unlock(struct extent_buffer *eb) { trace_btrfs_tree_read_unlock(eb); - /* - * if we're nested, we have the write lock. No new locking - * is needed as long as we are the lock owner. - * The write unlock will do a barrier for us, and the lock_recursed - * field only matters to the lock owner. - */ - if (eb->lock_recursed && current->pid == eb->lock_owner) { - eb->lock_recursed = false; - return; - } - btrfs_assert_tree_read_locked(eb); - btrfs_assert_spinning_readers_put(eb); - btrfs_assert_tree_read_locks_put(eb); - read_unlock(&eb->lock); -} - -/* - * Release read lock, previously set to blocking by a pairing call to - * btrfs_set_lock_blocking_read(). Can be nested in write lock by the same - * thread. - * - * State of rwlock is unchanged, last reader wakes waiting threads. - */ -void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb) -{ - trace_btrfs_tree_read_unlock_blocking(eb); - /* - * if we're nested, we have the write lock. No new locking - * is needed as long as we are the lock owner. - * The write unlock will do a barrier for us, and the lock_recursed - * field only matters to the lock owner. - */ - if (eb->lock_recursed && current->pid == eb->lock_owner) { - eb->lock_recursed = false; - return; - } - btrfs_assert_tree_read_locked(eb); - WARN_ON(atomic_read(&eb->blocking_readers) == 0); - /* atomic_dec_and_test implies a barrier */ - if (atomic_dec_and_test(&eb->blocking_readers)) - cond_wake_up_nomb(&eb->read_lock_wq); - btrfs_assert_tree_read_locks_put(eb); + eb->lock_owner = 0; + up_read(&eb->lock); } /* - * Lock for write. Wait for all blocking and spinning readers and writers. This - * starts context where reader lock could be nested by the same thread. + * __btrfs_tree_lock - lock eb for write + * @eb: the eb to lock + * @nest: the nesting to use for the lock * - * The rwlock is held for write upon exit. + * Returns with the eb->lock write locked. */ void __btrfs_tree_lock(struct extent_buffer *eb, enum btrfs_lock_nesting nest) __acquires(&eb->lock) @@ -424,19 +109,7 @@ void __btrfs_tree_lock(struct extent_buffer *eb, enum btrfs_lock_nesting nest) if (trace_btrfs_tree_lock_enabled()) start_ns = ktime_get_ns(); - WARN_ON(eb->lock_owner == current->pid); -again: - wait_event(eb->read_lock_wq, atomic_read(&eb->blocking_readers) == 0); - wait_event(eb->write_lock_wq, READ_ONCE(eb->blocking_writers) == 0); - write_lock(&eb->lock); - /* Refetch value after lock */ - if (atomic_read(&eb->blocking_readers) || - READ_ONCE(eb->blocking_writers)) { - write_unlock(&eb->lock); - goto again; - } - btrfs_assert_spinning_writers_get(eb); - btrfs_assert_tree_write_locks_get(eb); + down_write_nested(&eb->lock, nest); eb->lock_owner = current->pid; trace_btrfs_tree_lock(eb, start_ns); } @@ -447,68 +120,13 @@ void btrfs_tree_lock(struct extent_buffer *eb) } /* - * Release the write lock, either blocking or spinning (ie. there's no need - * for an explicit blocking unlock, like btrfs_tree_read_unlock_blocking). - * This also ends the context for nesting, the read lock must have been - * released already. - * - * Tasks blocked and waiting are woken, rwlock is not held upon exit. + * Release the write lock. */ void btrfs_tree_unlock(struct extent_buffer *eb) { - /* - * This is read both locked and unlocked but always by the same thread - * that already owns the lock so we don't need to use READ_ONCE - */ - int blockers = eb->blocking_writers; - - BUG_ON(blockers > 1); - - btrfs_assert_tree_locked(eb); trace_btrfs_tree_unlock(eb); eb->lock_owner = 0; - btrfs_assert_tree_write_locks_put(eb); - - if (blockers) { - btrfs_assert_no_spinning_writers(eb); - /* Unlocked write */ - WRITE_ONCE(eb->blocking_writers, 0); - /* - * We need to order modifying blocking_writers above with - * actually waking up the sleepers to ensure they see the - * updated value of blocking_writers - */ - cond_wake_up(&eb->write_lock_wq); - } else { - btrfs_assert_spinning_writers_put(eb); - write_unlock(&eb->lock); - } -} - -/* - * Set all locked nodes in the path to blocking locks. This should be done - * before scheduling - */ -void btrfs_set_path_blocking(struct btrfs_path *p) -{ - int i; - - for (i = 0; i < BTRFS_MAX_LEVEL; i++) { - if (!p->nodes[i] || !p->locks[i]) - continue; - /* - * If we currently have a spinning reader or writer lock this - * will bump the count of blocking holders and drop the - * spinlock. - */ - if (p->locks[i] == BTRFS_READ_LOCK) { - btrfs_set_lock_blocking_read(p->nodes[i]); - p->locks[i] = BTRFS_READ_LOCK_BLOCKING; - } else if (p->locks[i] == BTRFS_WRITE_LOCK) { - btrfs_set_lock_blocking_write(p->nodes[i]); - p->locks[i] = BTRFS_WRITE_LOCK_BLOCKING; - } - } + up_write(&eb->lock); } /* @@ -564,14 +182,13 @@ struct extent_buffer *btrfs_lock_root_node(struct btrfs_root *root) * * Return: root extent buffer with read lock held */ -struct extent_buffer *__btrfs_read_lock_root_node(struct btrfs_root *root, - bool recurse) +struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root) { struct extent_buffer *eb; while (1) { eb = btrfs_root_node(root); - __btrfs_tree_read_lock(eb, BTRFS_NESTING_NORMAL, recurse); + btrfs_tree_read_lock(eb); if (eb == root->node) break; btrfs_tree_read_unlock(eb); diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h index 3ea81ed3320b..a2e1f1f5c6e3 100644 --- a/fs/btrfs/locking.h +++ b/fs/btrfs/locking.h @@ -13,8 +13,6 @@ #define BTRFS_WRITE_LOCK 1 #define BTRFS_READ_LOCK 2 -#define BTRFS_WRITE_LOCK_BLOCKING 3 -#define BTRFS_READ_LOCK_BLOCKING 4 /* * We are limited in number of subclasses by MAX_LOCKDEP_SUBCLASSES, which at @@ -89,42 +87,28 @@ void __btrfs_tree_lock(struct extent_buffer *eb, enum btrfs_lock_nesting nest); void btrfs_tree_lock(struct extent_buffer *eb); void btrfs_tree_unlock(struct extent_buffer *eb); -void __btrfs_tree_read_lock(struct extent_buffer *eb, enum btrfs_lock_nesting nest, - bool recurse); +void __btrfs_tree_read_lock(struct extent_buffer *eb, enum btrfs_lock_nesting nest); void btrfs_tree_read_lock(struct extent_buffer *eb); void btrfs_tree_read_unlock(struct extent_buffer *eb); -void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb); -void btrfs_set_lock_blocking_read(struct extent_buffer *eb); -void btrfs_set_lock_blocking_write(struct extent_buffer *eb); int btrfs_try_tree_read_lock(struct extent_buffer *eb); int btrfs_try_tree_write_lock(struct extent_buffer *eb); -int btrfs_tree_read_lock_atomic(struct extent_buffer *eb); struct extent_buffer *btrfs_lock_root_node(struct btrfs_root *root); -struct extent_buffer *__btrfs_read_lock_root_node(struct btrfs_root *root, - bool recurse); - -static inline struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root) -{ - return __btrfs_read_lock_root_node(root, false); -} +struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root); #ifdef CONFIG_BTRFS_DEBUG static inline void btrfs_assert_tree_locked(struct extent_buffer *eb) { - BUG_ON(!eb->write_locks); + lockdep_assert_held(&eb->lock); } #else static inline void btrfs_assert_tree_locked(struct extent_buffer *eb) { } #endif -void btrfs_set_path_blocking(struct btrfs_path *p); void btrfs_unlock_up_safe(struct btrfs_path *path, int level); static inline void btrfs_tree_unlock_rw(struct extent_buffer *eb, int rw) { - if (rw == BTRFS_WRITE_LOCK || rw == BTRFS_WRITE_LOCK_BLOCKING) + if (rw == BTRFS_WRITE_LOCK) btrfs_tree_unlock(eb); - else if (rw == BTRFS_READ_LOCK_BLOCKING) - btrfs_tree_read_unlock_blocking(eb); else if (rw == BTRFS_READ_LOCK) btrfs_tree_read_unlock(eb); else diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 87bac9ecdf4c..985a21558437 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -199,14 +199,21 @@ static int __btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset entry->compress_type = compress_type; entry->truncated_len = (u64)-1; entry->qgroup_rsv = ret; - if (type != BTRFS_ORDERED_IO_DONE && type != BTRFS_ORDERED_COMPLETE) - set_bit(type, &entry->flags); + entry->physical = (u64)-1; + entry->disk = NULL; + entry->partno = (u8)-1; - if (dio) { - percpu_counter_add_batch(&fs_info->dio_bytes, num_bytes, - fs_info->delalloc_batch); + ASSERT(type == BTRFS_ORDERED_REGULAR || + type == BTRFS_ORDERED_NOCOW || + type == BTRFS_ORDERED_PREALLOC || + type == BTRFS_ORDERED_COMPRESSED); + set_bit(type, &entry->flags); + + percpu_counter_add_batch(&fs_info->ordered_bytes, num_bytes, + fs_info->delalloc_batch); + + if (dio) set_bit(BTRFS_ORDERED_DIRECT, &entry->flags); - } /* one ref for the tree */ refcount_set(&entry->refs, 1); @@ -256,6 +263,9 @@ int btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset, u64 disk_bytenr, u64 num_bytes, u64 disk_num_bytes, int type) { + ASSERT(type == BTRFS_ORDERED_REGULAR || + type == BTRFS_ORDERED_NOCOW || + type == BTRFS_ORDERED_PREALLOC); return __btrfs_add_ordered_extent(inode, file_offset, disk_bytenr, num_bytes, disk_num_bytes, type, 0, BTRFS_COMPRESS_NONE); @@ -265,6 +275,9 @@ int btrfs_add_ordered_extent_dio(struct btrfs_inode *inode, u64 file_offset, u64 disk_bytenr, u64 num_bytes, u64 disk_num_bytes, int type) { + ASSERT(type == BTRFS_ORDERED_REGULAR || + type == BTRFS_ORDERED_NOCOW || + type == BTRFS_ORDERED_PREALLOC); return __btrfs_add_ordered_extent(inode, file_offset, disk_bytenr, num_bytes, disk_num_bytes, type, 1, BTRFS_COMPRESS_NONE); @@ -272,11 +285,12 @@ int btrfs_add_ordered_extent_dio(struct btrfs_inode *inode, u64 file_offset, int btrfs_add_ordered_extent_compress(struct btrfs_inode *inode, u64 file_offset, u64 disk_bytenr, u64 num_bytes, - u64 disk_num_bytes, int type, - int compress_type) + u64 disk_num_bytes, int compress_type) { + ASSERT(compress_type != BTRFS_COMPRESS_NONE); return __btrfs_add_ordered_extent(inode, file_offset, disk_bytenr, - num_bytes, disk_num_bytes, type, 0, + num_bytes, disk_num_bytes, + BTRFS_ORDERED_COMPRESSED, 0, compress_type); } @@ -297,26 +311,33 @@ void btrfs_add_ordered_sum(struct btrfs_ordered_extent *entry, } /* - * this is used to account for finished IO across a given range - * of the file. The IO may span ordered extents. If - * a given ordered_extent is completely done, 1 is returned, otherwise - * 0. + * Finish IO for one ordered extent across a given range. The range can + * contain several ordered extents. * - * test_and_set_bit on a flag in the struct btrfs_ordered_extent is used - * to make sure this function only returns 1 once for a given ordered extent. + * @found_ret: Return the finished ordered extent + * @file_offset: File offset for the finished IO + * Will also be updated to one byte past the range that is + * recordered as finished. This allows caller to walk forward. + * @io_size: Length of the finish IO range + * @uptodate: If the IO finished without problem * - * file_offset is updated to one byte past the range that is recorded as - * complete. This allows you to walk forward in the file. + * Return true if any ordered extent is finished in the range, and update + * @found_ret and @file_offset. + * Return false otherwise. + * + * NOTE: Although The range can cross multiple ordered extents, only one + * ordered extent will be updated during one call. The caller is responsible to + * iterate all ordered extents in the range. */ -int btrfs_dec_test_first_ordered_pending(struct btrfs_inode *inode, - struct btrfs_ordered_extent **cached, +bool btrfs_dec_test_first_ordered_pending(struct btrfs_inode *inode, + struct btrfs_ordered_extent **finished_ret, u64 *file_offset, u64 io_size, int uptodate) { struct btrfs_fs_info *fs_info = inode->root->fs_info; struct btrfs_ordered_inode_tree *tree = &inode->ordered_tree; struct rb_node *node; struct btrfs_ordered_extent *entry = NULL; - int ret; + bool finished = false; unsigned long flags; u64 dec_end; u64 dec_start; @@ -324,16 +345,12 @@ int btrfs_dec_test_first_ordered_pending(struct btrfs_inode *inode, spin_lock_irqsave(&tree->lock, flags); node = tree_search(tree, *file_offset); - if (!node) { - ret = 1; + if (!node) goto out; - } entry = rb_entry(node, struct btrfs_ordered_extent, rb_node); - if (!offset_in_entry(entry, *file_offset)) { - ret = 1; + if (!offset_in_entry(entry, *file_offset)) goto out; - } dec_start = max(*file_offset, entry->file_offset); dec_end = min(*file_offset + io_size, @@ -354,39 +371,50 @@ int btrfs_dec_test_first_ordered_pending(struct btrfs_inode *inode, set_bit(BTRFS_ORDERED_IOERR, &entry->flags); if (entry->bytes_left == 0) { - ret = test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags); + /* + * Ensure only one caller can set the flag and finished_ret + * accordingly + */ + finished = !test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags); /* test_and_set_bit implies a barrier */ cond_wake_up_nomb(&entry->wait); - } else { - ret = 1; } out: - if (!ret && cached && entry) { - *cached = entry; + if (finished && finished_ret && entry) { + *finished_ret = entry; refcount_inc(&entry->refs); } spin_unlock_irqrestore(&tree->lock, flags); - return ret == 0; + return finished; } /* - * this is used to account for finished IO across a given range - * of the file. The IO should not span ordered extents. If - * a given ordered_extent is completely done, 1 is returned, otherwise - * 0. + * Finish IO for one ordered extent across a given range. The range can only + * contain one ordered extent. * - * test_and_set_bit on a flag in the struct btrfs_ordered_extent is used - * to make sure this function only returns 1 once for a given ordered extent. + * @cached: The cached ordered extent. If not NULL, we can skip the tree + * search and use the ordered extent directly. + * Will be also used to store the finished ordered extent. + * @file_offset: File offset for the finished IO + * @io_size: Length of the finish IO range + * @uptodate: If the IO finishes without problem + * + * Return true if the ordered extent is finished in the range, and update + * @cached. + * Return false otherwise. + * + * NOTE: The range can NOT cross multiple ordered extents. + * Thus caller should ensure the range doesn't cross ordered extents. */ -int btrfs_dec_test_ordered_pending(struct btrfs_inode *inode, - struct btrfs_ordered_extent **cached, - u64 file_offset, u64 io_size, int uptodate) +bool btrfs_dec_test_ordered_pending(struct btrfs_inode *inode, + struct btrfs_ordered_extent **cached, + u64 file_offset, u64 io_size, int uptodate) { struct btrfs_ordered_inode_tree *tree = &inode->ordered_tree; struct rb_node *node; struct btrfs_ordered_extent *entry = NULL; unsigned long flags; - int ret; + bool finished = false; spin_lock_irqsave(&tree->lock, flags); if (cached && *cached) { @@ -395,41 +423,39 @@ int btrfs_dec_test_ordered_pending(struct btrfs_inode *inode, } node = tree_search(tree, file_offset); - if (!node) { - ret = 1; + if (!node) goto out; - } entry = rb_entry(node, struct btrfs_ordered_extent, rb_node); have_entry: - if (!offset_in_entry(entry, file_offset)) { - ret = 1; + if (!offset_in_entry(entry, file_offset)) goto out; - } - if (io_size > entry->bytes_left) { + if (io_size > entry->bytes_left) btrfs_crit(inode->root->fs_info, "bad ordered accounting left %llu size %llu", entry->bytes_left, io_size); - } + entry->bytes_left -= io_size; if (!uptodate) set_bit(BTRFS_ORDERED_IOERR, &entry->flags); if (entry->bytes_left == 0) { - ret = test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags); + /* + * Ensure only one caller can set the flag and finished_ret + * accordingly + */ + finished = !test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags); /* test_and_set_bit implies a barrier */ cond_wake_up_nomb(&entry->wait); - } else { - ret = 1; } out: - if (!ret && cached && entry) { + if (finished && cached && entry) { *cached = entry; refcount_inc(&entry->refs); } spin_unlock_irqrestore(&tree->lock, flags); - return ret == 0; + return finished; } /* @@ -480,9 +506,8 @@ void btrfs_remove_ordered_extent(struct btrfs_inode *btrfs_inode, btrfs_delalloc_release_metadata(btrfs_inode, entry->num_bytes, false); - if (test_bit(BTRFS_ORDERED_DIRECT, &entry->flags)) - percpu_counter_add_batch(&fs_info->dio_bytes, -entry->num_bytes, - fs_info->delalloc_batch); + percpu_counter_add_batch(&fs_info->ordered_bytes, -entry->num_bytes, + fs_info->delalloc_batch); tree = &btrfs_inode->ordered_tree; spin_lock_irq(&tree->lock); @@ -745,9 +770,10 @@ struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct btrfs_inode *ino struct btrfs_ordered_inode_tree *tree; struct rb_node *node; struct btrfs_ordered_extent *entry = NULL; + unsigned long flags; tree = &inode->ordered_tree; - spin_lock_irq(&tree->lock); + spin_lock_irqsave(&tree->lock, flags); node = tree_search(tree, file_offset); if (!node) goto out; @@ -758,7 +784,7 @@ struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct btrfs_inode *ino if (entry) refcount_inc(&entry->refs); out: - spin_unlock_irq(&tree->lock); + spin_unlock_irqrestore(&tree->lock, flags); return entry; } @@ -855,51 +881,6 @@ out: } /* - * search the ordered extents for one corresponding to 'offset' and - * try to find a checksum. This is used because we allow pages to - * be reclaimed before their checksum is actually put into the btree - */ -int btrfs_find_ordered_sum(struct btrfs_inode *inode, u64 offset, - u64 disk_bytenr, u8 *sum, int len) -{ - struct btrfs_fs_info *fs_info = inode->root->fs_info; - struct btrfs_ordered_sum *ordered_sum; - struct btrfs_ordered_extent *ordered; - struct btrfs_ordered_inode_tree *tree = &inode->ordered_tree; - unsigned long num_sectors; - unsigned long i; - u32 sectorsize = btrfs_inode_sectorsize(inode); - const u8 blocksize_bits = inode->vfs_inode.i_sb->s_blocksize_bits; - const u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); - int index = 0; - - ordered = btrfs_lookup_ordered_extent(inode, offset); - if (!ordered) - return 0; - - spin_lock_irq(&tree->lock); - list_for_each_entry_reverse(ordered_sum, &ordered->list, list) { - if (disk_bytenr >= ordered_sum->bytenr && - disk_bytenr < ordered_sum->bytenr + ordered_sum->len) { - i = (disk_bytenr - ordered_sum->bytenr) >> blocksize_bits; - num_sectors = ordered_sum->len >> blocksize_bits; - num_sectors = min_t(int, len - index, num_sectors - i); - memcpy(sum + index, ordered_sum->sums + i * csum_size, - num_sectors * csum_size); - - index += (int)num_sectors * csum_size; - if (index == len) - goto out; - disk_bytenr += num_sectors * sectorsize; - } - } -out: - spin_unlock_irq(&tree->lock); - btrfs_put_ordered_extent(ordered); - return index; -} - -/* * btrfs_flush_ordered_range - Lock the passed range and ensures all pending * ordered extents in it are run to completion. * @@ -943,6 +924,84 @@ void btrfs_lock_and_flush_ordered_range(struct btrfs_inode *inode, u64 start, } } +static int clone_ordered_extent(struct btrfs_ordered_extent *ordered, u64 pos, + u64 len) +{ + struct inode *inode = ordered->inode; + u64 file_offset = ordered->file_offset + pos; + u64 disk_bytenr = ordered->disk_bytenr + pos; + u64 num_bytes = len; + u64 disk_num_bytes = len; + int type; + unsigned long flags_masked = ordered->flags & ~(1 << BTRFS_ORDERED_DIRECT); + int compress_type = ordered->compress_type; + unsigned long weight; + int ret; + + weight = hweight_long(flags_masked); + WARN_ON_ONCE(weight > 1); + if (!weight) + type = 0; + else + type = __ffs(flags_masked); + + if (test_bit(BTRFS_ORDERED_COMPRESSED, &ordered->flags)) { + WARN_ON_ONCE(1); + ret = btrfs_add_ordered_extent_compress(BTRFS_I(inode), + file_offset, disk_bytenr, num_bytes, + disk_num_bytes, compress_type); + } else if (test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags)) { + ret = btrfs_add_ordered_extent_dio(BTRFS_I(inode), file_offset, + disk_bytenr, num_bytes, disk_num_bytes, type); + } else { + ret = btrfs_add_ordered_extent(BTRFS_I(inode), file_offset, + disk_bytenr, num_bytes, disk_num_bytes, type); + } + + return ret; +} + +int btrfs_split_ordered_extent(struct btrfs_ordered_extent *ordered, u64 pre, + u64 post) +{ + struct inode *inode = ordered->inode; + struct btrfs_ordered_inode_tree *tree = &BTRFS_I(inode)->ordered_tree; + struct rb_node *node; + struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + int ret = 0; + + spin_lock_irq(&tree->lock); + /* Remove from tree once */ + node = &ordered->rb_node; + rb_erase(node, &tree->tree); + RB_CLEAR_NODE(node); + if (tree->last == node) + tree->last = NULL; + + ordered->file_offset += pre; + ordered->disk_bytenr += pre; + ordered->num_bytes -= (pre + post); + ordered->disk_num_bytes -= (pre + post); + ordered->bytes_left -= (pre + post); + + /* Re-insert the node */ + node = tree_insert(&tree->tree, ordered->file_offset, &ordered->rb_node); + if (node) + btrfs_panic(fs_info, -EEXIST, + "zoned: inconsistency in ordered tree at offset %llu", + ordered->file_offset); + + spin_unlock_irq(&tree->lock); + + if (pre) + ret = clone_ordered_extent(ordered, 0, pre); + if (post) + ret = clone_ordered_extent(ordered, pre + ordered->disk_num_bytes, + post); + + return ret; +} + int __init ordered_data_init(void) { btrfs_ordered_extent_cache = kmem_cache_create("btrfs_ordered_extent", diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h index c3a2325e64a4..99e0853e4d3b 100644 --- a/fs/btrfs/ordered-data.h +++ b/fs/btrfs/ordered-data.h @@ -27,7 +27,7 @@ struct btrfs_ordered_sum { }; /* - * bits for the flags field: + * Bits for btrfs_ordered_extent::flags. * * BTRFS_ORDERED_IO_DONE is set when all of the blocks are written. * It is used to make sure metadata is inserted into the tree only once @@ -38,24 +38,36 @@ struct btrfs_ordered_sum { * IO is done and any metadata is inserted into the tree. */ enum { + /* + * Different types for direct io, one and only one of the 4 type can + * be set when creating ordered extent. + * + * REGULAR: For regular non-compressed COW write + * NOCOW: For NOCOW write into existing non-hole extent + * PREALLOC: For NOCOW write into preallocated extent + * COMPRESSED: For compressed COW write + */ + BTRFS_ORDERED_REGULAR, + BTRFS_ORDERED_NOCOW, + BTRFS_ORDERED_PREALLOC, + BTRFS_ORDERED_COMPRESSED, + + /* + * Extra bit for direct io, can only be set for + * REGULAR/NOCOW/PREALLOC. No direct io for compressed extent. + */ + BTRFS_ORDERED_DIRECT, + + /* Extra status bits for ordered extents */ + /* set when all the pages are written */ BTRFS_ORDERED_IO_DONE, /* set when removed from the tree */ BTRFS_ORDERED_COMPLETE, - /* set when we want to write in place */ - BTRFS_ORDERED_NOCOW, - /* writing a zlib compressed extent */ - BTRFS_ORDERED_COMPRESSED, - /* set when writing to preallocated extent */ - BTRFS_ORDERED_PREALLOC, - /* set when we're doing DIO with this extent */ - BTRFS_ORDERED_DIRECT, /* We had an io error when writing this out */ BTRFS_ORDERED_IOERR, /* Set when we have to truncate an extent */ BTRFS_ORDERED_TRUNCATED, - /* Regular IO for COW */ - BTRFS_ORDERED_REGULAR, /* Used during fsync to track already logged extents */ BTRFS_ORDERED_LOGGED, /* We have already logged all the csums of the ordered extent */ @@ -127,6 +139,14 @@ struct btrfs_ordered_extent { struct completion completion; struct btrfs_work flush_work; struct list_head work_list; + + /* + * Used to reverse-map physical address returned from ZONE_APPEND write + * command in a workqueue context + */ + u64 physical; + struct gendisk *disk; + u8 partno; }; /* @@ -137,9 +157,8 @@ static inline int btrfs_ordered_sum_size(struct btrfs_fs_info *fs_info, unsigned long bytes) { int num_sectors = (int)DIV_ROUND_UP(bytes, fs_info->sectorsize); - int csum_size = btrfs_super_csum_size(fs_info->super_copy); - return sizeof(struct btrfs_ordered_sum) + num_sectors * csum_size; + return sizeof(struct btrfs_ordered_sum) + num_sectors * fs_info->csum_size; } static inline void @@ -153,11 +172,11 @@ btrfs_ordered_inode_tree_init(struct btrfs_ordered_inode_tree *t) 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); -int btrfs_dec_test_ordered_pending(struct btrfs_inode *inode, - struct btrfs_ordered_extent **cached, - u64 file_offset, u64 io_size, int uptodate); -int btrfs_dec_test_first_ordered_pending(struct btrfs_inode *inode, - struct btrfs_ordered_extent **cached, +bool btrfs_dec_test_ordered_pending(struct btrfs_inode *inode, + struct btrfs_ordered_extent **cached, + u64 file_offset, u64 io_size, int uptodate); +bool btrfs_dec_test_first_ordered_pending(struct btrfs_inode *inode, + struct btrfs_ordered_extent **finished_ret, u64 *file_offset, u64 io_size, int uptodate); int btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset, @@ -168,8 +187,7 @@ int btrfs_add_ordered_extent_dio(struct btrfs_inode *inode, u64 file_offset, u64 disk_num_bytes, int type); int btrfs_add_ordered_extent_compress(struct btrfs_inode *inode, u64 file_offset, u64 disk_bytenr, u64 num_bytes, - u64 disk_num_bytes, int type, - int compress_type); + u64 disk_num_bytes, int compress_type); void btrfs_add_ordered_sum(struct btrfs_ordered_extent *entry, struct btrfs_ordered_sum *sum); struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct btrfs_inode *inode, @@ -184,8 +202,6 @@ struct btrfs_ordered_extent *btrfs_lookup_ordered_range( u64 len); void btrfs_get_ordered_extents_for_logging(struct btrfs_inode *inode, struct list_head *list); -int btrfs_find_ordered_sum(struct btrfs_inode *inode, u64 offset, - u64 disk_bytenr, u8 *sum, int len); u64 btrfs_wait_ordered_extents(struct btrfs_root *root, u64 nr, const u64 range_start, const u64 range_len); void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr, @@ -193,6 +209,8 @@ void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr, void btrfs_lock_and_flush_ordered_range(struct btrfs_inode *inode, u64 start, u64 end, struct extent_state **cached_state); +int btrfs_split_ordered_extent(struct btrfs_ordered_extent *ordered, u64 pre, + u64 post); int __init ordered_data_init(void); void __cold ordered_data_exit(void); diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c index 7695c4783d33..aae1027bd76a 100644 --- a/fs/btrfs/print-tree.c +++ b/fs/btrfs/print-tree.c @@ -26,22 +26,22 @@ static const struct root_name_map root_map[] = { { BTRFS_DATA_RELOC_TREE_OBJECTID, "DATA_RELOC_TREE" }, }; -const char *btrfs_root_name(u64 objectid, char *buf) +const char *btrfs_root_name(const struct btrfs_key *key, char *buf) { int i; - if (objectid == BTRFS_TREE_RELOC_OBJECTID) { + if (key->objectid == BTRFS_TREE_RELOC_OBJECTID) { snprintf(buf, BTRFS_ROOT_NAME_BUF_LEN, - "TREE_RELOC offset=%llu", objectid); + "TREE_RELOC offset=%llu", key->offset); return buf; } for (i = 0; i < ARRAY_SIZE(root_map); i++) { - if (root_map[i].id == objectid) + if (root_map[i].id == key->objectid) return root_map[i].name; } - snprintf(buf, BTRFS_ROOT_NAME_BUF_LEN, "%llu", objectid); + snprintf(buf, BTRFS_ROOT_NAME_BUF_LEN, "%llu", key->objectid); return buf; } @@ -177,8 +177,7 @@ static void print_uuid_item(struct extent_buffer *l, unsigned long offset, __le64 subvol_id; read_extent_buffer(l, &subvol_id, offset, sizeof(subvol_id)); - pr_info("\t\tsubvol_id %llu\n", - (unsigned long long)le64_to_cpu(subvol_id)); + pr_info("\t\tsubvol_id %llu\n", le64_to_cpu(subvol_id)); item_size -= sizeof(u64); offset += sizeof(u64); } @@ -191,15 +190,8 @@ static void print_uuid_item(struct extent_buffer *l, unsigned long offset, static void print_eb_refs_lock(struct extent_buffer *eb) { #ifdef CONFIG_BTRFS_DEBUG - btrfs_info(eb->fs_info, -"refs %u lock (w:%d r:%d bw:%d br:%d sw:%d sr:%d) lock_owner %u current %u", - atomic_read(&eb->refs), eb->write_locks, - atomic_read(&eb->read_locks), - eb->blocking_writers, - atomic_read(&eb->blocking_readers), - eb->spinning_writers, - atomic_read(&eb->spinning_readers), - eb->lock_owner, current->pid); + btrfs_info(eb->fs_info, "refs %u lock_owner %u current %u", + atomic_read(&eb->refs), eb->lock_owner, current->pid); #endif } @@ -398,6 +390,7 @@ void btrfs_print_tree(struct extent_buffer *c, bool follow) btrfs_node_key_to_cpu(c, &first_key, i); next = read_tree_block(fs_info, btrfs_node_blockptr(c, i), + btrfs_header_owner(c), btrfs_node_ptr_generation(c, i), level - 1, &first_key); if (IS_ERR(next)) { diff --git a/fs/btrfs/print-tree.h b/fs/btrfs/print-tree.h index 78b99385a503..8c3e9319ec4e 100644 --- a/fs/btrfs/print-tree.h +++ b/fs/btrfs/print-tree.h @@ -11,6 +11,6 @@ void btrfs_print_leaf(struct extent_buffer *l); void btrfs_print_tree(struct extent_buffer *c, bool follow); -const char *btrfs_root_name(u64 objectid, char *buf); +const char *btrfs_root_name(const struct btrfs_key *key, char *buf); #endif diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 580899bdb991..808370ada888 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -11,6 +11,7 @@ #include <linux/slab.h> #include <linux/workqueue.h> #include <linux/btrfs.h> +#include <linux/sched/mm.h> #include "ctree.h" #include "transaction.h" @@ -497,13 +498,13 @@ next2: break; } out: + btrfs_free_path(path); fs_info->qgroup_flags |= flags; if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON)) clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); else if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN && ret >= 0) ret = qgroup_rescan_init(fs_info, rescan_progress, 0); - btrfs_free_path(path); if (ret < 0) { ulist_free(fs_info->qgroup_ulist); @@ -893,8 +894,6 @@ static int btrfs_clean_quota_tree(struct btrfs_trans_handle *trans, if (!path) return -ENOMEM; - path->leave_spinning = 1; - key.objectid = 0; key.offset = 0; key.type = 0; @@ -936,6 +935,7 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info) struct btrfs_key found_key; struct btrfs_qgroup *qgroup = NULL; struct btrfs_trans_handle *trans = NULL; + struct ulist *ulist = NULL; int ret = 0; int slot; @@ -943,8 +943,8 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info) if (fs_info->quota_root) goto out; - fs_info->qgroup_ulist = ulist_alloc(GFP_KERNEL); - if (!fs_info->qgroup_ulist) { + ulist = ulist_alloc(GFP_KERNEL); + if (!ulist) { ret = -ENOMEM; goto out; } @@ -952,6 +952,22 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info) ret = btrfs_sysfs_add_qgroups(fs_info); if (ret < 0) goto out; + + /* + * Unlock qgroup_ioctl_lock before starting the transaction. This is to + * avoid lock acquisition inversion problems (reported by lockdep) between + * qgroup_ioctl_lock and the vfs freeze semaphores, acquired when we + * start a transaction. + * After we started the transaction lock qgroup_ioctl_lock again and + * check if someone else created the quota root in the meanwhile. If so, + * just return success and release the transaction handle. + * + * Also we don't need to worry about someone else calling + * btrfs_sysfs_add_qgroups() after we unlock and getting an error because + * that function returns 0 (success) when the sysfs entries already exist. + */ + mutex_unlock(&fs_info->qgroup_ioctl_lock); + /* * 1 for quota root item * 1 for BTRFS_QGROUP_STATUS item @@ -961,12 +977,20 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info) * would be a lot of overkill. */ trans = btrfs_start_transaction(tree_root, 2); + + mutex_lock(&fs_info->qgroup_ioctl_lock); if (IS_ERR(trans)) { ret = PTR_ERR(trans); trans = NULL; goto out; } + if (fs_info->quota_root) + goto out; + + fs_info->qgroup_ulist = ulist; + ulist = NULL; + /* * initially create the quota tree */ @@ -1026,6 +1050,10 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info) btrfs_item_key_to_cpu(leaf, &found_key, slot); if (found_key.type == BTRFS_ROOT_REF_KEY) { + + /* Release locks on tree_root before we access quota_root */ + btrfs_release_path(path); + ret = add_qgroup_item(trans, quota_root, found_key.offset); if (ret) { @@ -1044,6 +1072,20 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info) btrfs_abort_transaction(trans, ret); goto out_free_path; } + ret = btrfs_search_slot_for_read(tree_root, &found_key, + path, 1, 0); + if (ret < 0) { + btrfs_abort_transaction(trans, ret); + goto out_free_path; + } + if (ret > 0) { + /* + * Shouldn't happen, but in case it does we + * don't need to do the btrfs_next_item, just + * continue. + */ + continue; + } } ret = btrfs_next_item(tree_root, path); if (ret < 0) { @@ -1106,11 +1148,14 @@ out: if (ret) { ulist_free(fs_info->qgroup_ulist); fs_info->qgroup_ulist = NULL; - if (trans) - btrfs_end_transaction(trans); btrfs_sysfs_del_qgroups(fs_info); } mutex_unlock(&fs_info->qgroup_ioctl_lock); + if (ret && trans) + btrfs_end_transaction(trans); + else if (trans) + ret = btrfs_end_transaction(trans); + ulist_free(ulist); return ret; } @@ -1123,19 +1168,29 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) mutex_lock(&fs_info->qgroup_ioctl_lock); if (!fs_info->quota_root) goto out; + mutex_unlock(&fs_info->qgroup_ioctl_lock); /* * 1 For the root item * * We should also reserve enough items for the quota tree deletion in * btrfs_clean_quota_tree but this is not done. + * + * Also, we must always start a transaction without holding the mutex + * qgroup_ioctl_lock, see btrfs_quota_enable(). */ trans = btrfs_start_transaction(fs_info->tree_root, 1); + + mutex_lock(&fs_info->qgroup_ioctl_lock); if (IS_ERR(trans)) { ret = PTR_ERR(trans); + trans = NULL; goto out; } + if (!fs_info->quota_root) + goto out; + clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); btrfs_qgroup_wait_for_completion(fs_info, false); spin_lock(&fs_info->qgroup_lock); @@ -1149,13 +1204,13 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) ret = btrfs_clean_quota_tree(trans, quota_root); if (ret) { btrfs_abort_transaction(trans, ret); - goto end_trans; + goto out; } ret = btrfs_del_root(trans, "a_root->root_key); if (ret) { btrfs_abort_transaction(trans, ret); - goto end_trans; + goto out; } list_del("a_root->dirty_list); @@ -1167,10 +1222,13 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) btrfs_put_root(quota_root); -end_trans: - ret = btrfs_end_transaction(trans); out: mutex_unlock(&fs_info->qgroup_ioctl_lock); + if (ret && trans) + btrfs_end_transaction(trans); + else if (trans) + ret = btrfs_end_transaction(trans); + return ret; } @@ -1306,13 +1364,17 @@ int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src, struct btrfs_qgroup *member; struct btrfs_qgroup_list *list; struct ulist *tmp; + unsigned int nofs_flag; int ret = 0; /* Check the level of src and dst first */ if (btrfs_qgroup_level(src) >= btrfs_qgroup_level(dst)) return -EINVAL; + /* We hold a transaction handle open, must do a NOFS allocation. */ + nofs_flag = memalloc_nofs_save(); tmp = ulist_alloc(GFP_KERNEL); + memalloc_nofs_restore(nofs_flag); if (!tmp) return -ENOMEM; @@ -1369,10 +1431,14 @@ static int __del_qgroup_relation(struct btrfs_trans_handle *trans, u64 src, struct btrfs_qgroup_list *list; struct ulist *tmp; bool found = false; + unsigned int nofs_flag; int ret = 0; int ret2; + /* We hold a transaction handle open, must do a NOFS allocation. */ + nofs_flag = memalloc_nofs_save(); tmp = ulist_alloc(GFP_KERNEL); + memalloc_nofs_restore(nofs_flag); if (!tmp) return -ENOMEM; @@ -1876,34 +1942,22 @@ static int qgroup_trace_extent_swap(struct btrfs_trans_handle* trans, struct btrfs_key dst_key; if (src_path->nodes[cur_level] == NULL) { - struct btrfs_key first_key; struct extent_buffer *eb; int parent_slot; - u64 child_gen; - u64 child_bytenr; eb = src_path->nodes[cur_level + 1]; parent_slot = src_path->slots[cur_level + 1]; - child_bytenr = btrfs_node_blockptr(eb, parent_slot); - child_gen = btrfs_node_ptr_generation(eb, parent_slot); - btrfs_node_key_to_cpu(eb, &first_key, parent_slot); - eb = read_tree_block(fs_info, child_bytenr, child_gen, - cur_level, &first_key); + eb = btrfs_read_node_slot(eb, parent_slot); if (IS_ERR(eb)) { ret = PTR_ERR(eb); goto out; - } else if (!extent_buffer_uptodate(eb)) { - free_extent_buffer(eb); - ret = -EIO; - goto out; } src_path->nodes[cur_level] = eb; btrfs_tree_read_lock(eb); - btrfs_set_lock_blocking_read(eb); - src_path->locks[cur_level] = BTRFS_READ_LOCK_BLOCKING; + src_path->locks[cur_level] = BTRFS_READ_LOCK; } src_path->slots[cur_level] = dst_path->slots[cur_level]; @@ -1998,10 +2052,8 @@ static int qgroup_trace_new_subtree_blocks(struct btrfs_trans_handle* trans, /* Read the tree block if needed */ if (dst_path->nodes[cur_level] == NULL) { - struct btrfs_key first_key; int parent_slot; u64 child_gen; - u64 child_bytenr; /* * dst_path->nodes[root_level] must be initialized before @@ -2020,31 +2072,23 @@ static int qgroup_trace_new_subtree_blocks(struct btrfs_trans_handle* trans, */ eb = dst_path->nodes[cur_level + 1]; parent_slot = dst_path->slots[cur_level + 1]; - child_bytenr = btrfs_node_blockptr(eb, parent_slot); child_gen = btrfs_node_ptr_generation(eb, parent_slot); - btrfs_node_key_to_cpu(eb, &first_key, parent_slot); /* This node is old, no need to trace */ if (child_gen < last_snapshot) goto out; - eb = read_tree_block(fs_info, child_bytenr, child_gen, - cur_level, &first_key); + eb = btrfs_read_node_slot(eb, parent_slot); if (IS_ERR(eb)) { ret = PTR_ERR(eb); goto out; - } else if (!extent_buffer_uptodate(eb)) { - free_extent_buffer(eb); - ret = -EIO; - goto out; } dst_path->nodes[cur_level] = eb; dst_path->slots[cur_level] = 0; btrfs_tree_read_lock(eb); - btrfs_set_lock_blocking_read(eb); - dst_path->locks[cur_level] = BTRFS_READ_LOCK_BLOCKING; + dst_path->locks[cur_level] = BTRFS_READ_LOCK; need_cleanup = true; } @@ -2188,38 +2232,28 @@ walk_down: level = root_level; while (level >= 0) { if (path->nodes[level] == NULL) { - struct btrfs_key first_key; int parent_slot; - u64 child_gen; u64 child_bytenr; /* - * We need to get child blockptr/gen from parent before - * we can read it. + * We need to get child blockptr from parent before we + * can read it. */ eb = path->nodes[level + 1]; parent_slot = path->slots[level + 1]; child_bytenr = btrfs_node_blockptr(eb, parent_slot); - child_gen = btrfs_node_ptr_generation(eb, parent_slot); - btrfs_node_key_to_cpu(eb, &first_key, parent_slot); - eb = read_tree_block(fs_info, child_bytenr, child_gen, - level, &first_key); + eb = btrfs_read_node_slot(eb, parent_slot); if (IS_ERR(eb)) { ret = PTR_ERR(eb); goto out; - } else if (!extent_buffer_uptodate(eb)) { - free_extent_buffer(eb); - ret = -EIO; - goto out; } path->nodes[level] = eb; path->slots[level] = 0; btrfs_tree_read_lock(eb); - btrfs_set_lock_blocking_read(eb); - path->locks[level] = BTRFS_READ_LOCK_BLOCKING; + path->locks[level] = BTRFS_READ_LOCK; ret = btrfs_qgroup_trace_extent(trans, child_bytenr, fs_info->nodesize, @@ -3156,6 +3190,12 @@ out: return ret; } +static bool rescan_should_stop(struct btrfs_fs_info *fs_info) +{ + return btrfs_fs_closing(fs_info) || + test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state); +} + static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) { struct btrfs_fs_info *fs_info = container_of(work, struct btrfs_fs_info, @@ -3164,6 +3204,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) struct btrfs_trans_handle *trans = NULL; int err = -ENOMEM; int ret = 0; + bool stopped = false; path = btrfs_alloc_path(); if (!path) @@ -3176,7 +3217,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) path->skip_locking = 1; err = 0; - while (!err && !btrfs_fs_closing(fs_info)) { + while (!err && !(stopped = rescan_should_stop(fs_info))) { trans = btrfs_start_transaction(fs_info->fs_root, 0); if (IS_ERR(trans)) { err = PTR_ERR(trans); @@ -3219,7 +3260,7 @@ out: } mutex_lock(&fs_info->qgroup_rescan_lock); - if (!btrfs_fs_closing(fs_info)) + if (!stopped) fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN; if (trans) { ret = update_qgroup_status_item(trans); @@ -3238,7 +3279,7 @@ out: btrfs_end_transaction(trans); - if (btrfs_fs_closing(fs_info)) { + if (stopped) { btrfs_info(fs_info, "qgroup scan paused"); } else if (err >= 0) { btrfs_info(fs_info, "qgroup scan completed%s", @@ -3417,24 +3458,20 @@ static int qgroup_unreserve_range(struct btrfs_inode *inode, { struct rb_node *node; struct rb_node *next; - struct ulist_node *entry = NULL; + struct ulist_node *entry; int ret = 0; node = reserved->range_changed.root.rb_node; + if (!node) + return 0; while (node) { entry = rb_entry(node, struct ulist_node, rb_node); if (entry->val < start) node = node->rb_right; - else if (entry) - node = node->rb_left; else - break; + node = node->rb_left; } - /* Empty changeset */ - if (!entry) - return 0; - if (entry->val > start && rb_prev(&entry->rb_node)) entry = rb_entry(rb_prev(&entry->rb_node), struct ulist_node, rb_node); @@ -3498,12 +3535,37 @@ static int try_flush_qgroup(struct btrfs_root *root) { struct btrfs_trans_handle *trans; int ret; + bool can_commit = true; + + /* + * If current process holds a transaction, we shouldn't flush, as we + * assume all space reservation happens before a transaction handle is + * held. + * + * But there are cases like btrfs_delayed_item_reserve_metadata() where + * we try to reserve space with one transction handle already held. + * In that case we can't commit transaction, but at least try to end it + * and hope the started data writes can free some space. + */ + if (current->journal_info && + current->journal_info != BTRFS_SEND_TRANS_STUB) + can_commit = false; /* * We don't want to run flush again and again, so if there is a running * one, we won't try to start a new flush, but exit directly. */ if (test_and_set_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state)) { + /* + * We are already holding a transaction, thus we can block other + * threads from flushing. So exit right now. This increases + * the chance of EDQUOT for heavy load and near limit cases. + * But we can argue that if we're already near limit, EDQUOT is + * unavoidable anyway. + */ + if (!can_commit) + return 0; + wait_event(root->qgroup_flush_wait, !test_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state)); return 0; @@ -3520,7 +3582,10 @@ static int try_flush_qgroup(struct btrfs_root *root) goto out; } - ret = btrfs_commit_transaction(trans); + if (can_commit) + ret = btrfs_commit_transaction(trans); + else + ret = btrfs_end_transaction(trans); out: clear_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state); wake_up(&root->qgroup_flush_wait); @@ -4160,7 +4225,7 @@ int btrfs_qgroup_trace_subtree_after_cow(struct btrfs_trans_handle *trans, spin_unlock(&blocks->lock); /* Read out reloc subtree root */ - reloc_eb = read_tree_block(fs_info, block->reloc_bytenr, + reloc_eb = read_tree_block(fs_info, block->reloc_bytenr, 0, block->reloc_generation, block->level, &block->first_key); if (IS_ERR(reloc_eb)) { diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 255490f42b5d..8ec34ecb6d68 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -233,8 +233,7 @@ int btrfs_alloc_stripe_hash_table(struct btrfs_fs_info *info) } x = cmpxchg(&info->stripe_hash_table, NULL, table); - if (x) - kvfree(x); + kvfree(x); return 0; } @@ -1097,7 +1096,7 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio, /* see if we can add this page onto our existing bio */ if (last) { - u64 last_end = (u64)last->bi_iter.bi_sector << 9; + u64 last_end = last->bi_iter.bi_sector << 9; last_end += last->bi_iter.bi_size; /* @@ -1105,8 +1104,7 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio, * devices or if they are not contiguous */ if (last_end == disk_start && !last->bi_status && - last->bi_disk == stripe->dev->bdev->bd_disk && - last->bi_partno == stripe->dev->bdev->bd_partno) { + last->bi_bdev == stripe->dev->bdev) { ret = bio_add_page(last, page, PAGE_SIZE, 0); if (ret == PAGE_SIZE) return 0; @@ -1163,7 +1161,7 @@ static void index_rbio_pages(struct btrfs_raid_bio *rbio) struct bvec_iter iter; int i = 0; - start = (u64)bio->bi_iter.bi_sector << 9; + start = bio->bi_iter.bi_sector << 9; stripe_offset = start - rbio->bbio->raid_map[0]; page_index = stripe_offset >> PAGE_SHIFT; @@ -1357,9 +1355,7 @@ static int find_bio_stripe(struct btrfs_raid_bio *rbio, for (i = 0; i < rbio->bbio->num_stripes; i++) { stripe = &rbio->bbio->stripes[i]; if (in_range(physical, stripe->physical, rbio->stripe_len) && - stripe->dev->bdev && - bio->bi_disk == stripe->dev->bdev->bd_disk && - bio->bi_partno == stripe->dev->bdev->bd_partno) { + stripe->dev->bdev && bio->bi_bdev == stripe->dev->bdev) { return i; } } @@ -1374,7 +1370,7 @@ static int find_bio_stripe(struct btrfs_raid_bio *rbio, static int find_logical_bio_stripe(struct btrfs_raid_bio *rbio, struct bio *bio) { - u64 logical = (u64)bio->bi_iter.bi_sector << 9; + u64 logical = bio->bi_iter.bi_sector << 9; int i; for (i = 0; i < rbio->nr_data; i++) { @@ -2150,7 +2146,7 @@ int raid56_parity_recover(struct btrfs_fs_info *fs_info, struct bio *bio, if (rbio->faila == -1) { btrfs_warn(fs_info, "%s could not find the bad stripe in raid56 so that we cannot recover any more (bio has logical %llu len %llu, bbio has map_type %llu)", - __func__, (u64)bio->bi_iter.bi_sector << 9, + __func__, bio->bi_iter.bi_sector << 9, (u64)bio->bi_iter.bi_size, bbio->map_type); if (generic_io) btrfs_put_bbio(bbio); diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c index 9d4f5316a7e8..20fd4aa48a8c 100644 --- a/fs/btrfs/reada.c +++ b/fs/btrfs/reada.c @@ -52,6 +52,7 @@ struct reada_extctl { struct reada_extent { u64 logical; + u64 owner_root; struct btrfs_key top; struct list_head extctl; int refcnt; @@ -59,6 +60,7 @@ struct reada_extent { struct reada_zone *zones[BTRFS_MAX_MIRRORS]; int nzones; int scheduled; + int level; }; struct reada_zone { @@ -87,7 +89,8 @@ static void reada_start_machine(struct btrfs_fs_info *fs_info); static void __reada_start_machine(struct btrfs_fs_info *fs_info); static int reada_add_block(struct reada_control *rc, u64 logical, - struct btrfs_key *top, u64 generation); + struct btrfs_key *top, u64 owner_root, + u64 generation, int level); /* recurses */ /* in case of err, eb might be NULL */ @@ -165,7 +168,9 @@ static void __readahead_hook(struct btrfs_fs_info *fs_info, if (rec->generation == generation && btrfs_comp_cpu_keys(&key, &rc->key_end) < 0 && btrfs_comp_cpu_keys(&next_key, &rc->key_start) > 0) - reada_add_block(rc, bytenr, &next_key, n_gen); + reada_add_block(rc, bytenr, &next_key, + btrfs_header_owner(eb), n_gen, + btrfs_header_level(eb) - 1); } } @@ -298,7 +303,8 @@ static struct reada_zone *reada_find_zone(struct btrfs_device *dev, u64 logical, static struct reada_extent *reada_find_extent(struct btrfs_fs_info *fs_info, u64 logical, - struct btrfs_key *top) + struct btrfs_key *top, + u64 owner_root, int level) { int ret; struct reada_extent *re = NULL; @@ -331,6 +337,8 @@ static struct reada_extent *reada_find_extent(struct btrfs_fs_info *fs_info, INIT_LIST_HEAD(&re->extctl); spin_lock_init(&re->lock); re->refcnt = 1; + re->owner_root = owner_root; + re->level = level; /* * map block @@ -421,6 +429,9 @@ static struct reada_extent *reada_find_extent(struct btrfs_fs_info *fs_info, if (!dev->bdev) continue; + if (test_bit(BTRFS_DEV_STATE_NO_READA, &dev->dev_state)) + continue; + if (dev_replace_is_ongoing && dev == fs_info->dev_replace.tgtdev) { /* @@ -445,6 +456,8 @@ static struct reada_extent *reada_find_extent(struct btrfs_fs_info *fs_info, } have_zone = 1; } + if (!have_zone) + radix_tree_delete(&fs_info->reada_tree, index); spin_unlock(&fs_info->reada_lock); up_read(&fs_info->dev_replace.rwsem); @@ -526,6 +539,8 @@ static void reada_zone_release(struct kref *kref) { struct reada_zone *zone = container_of(kref, struct reada_zone, refcnt); + lockdep_assert_held(&zone->device->fs_info->reada_lock); + radix_tree_delete(&zone->device->reada_zones, zone->end >> PAGE_SHIFT); @@ -541,14 +556,15 @@ static void reada_control_release(struct kref *kref) } static int reada_add_block(struct reada_control *rc, u64 logical, - struct btrfs_key *top, u64 generation) + struct btrfs_key *top, u64 owner_root, + u64 generation, int level) { struct btrfs_fs_info *fs_info = rc->fs_info; struct reada_extent *re; struct reada_extctl *rec; /* takes one ref */ - re = reada_find_extent(fs_info, logical, top); + re = reada_find_extent(fs_info, logical, top, owner_root, level); if (!re) return -1; @@ -640,12 +656,13 @@ static int reada_pick_zone(struct btrfs_device *dev) } static int reada_tree_block_flagged(struct btrfs_fs_info *fs_info, u64 bytenr, - int mirror_num, struct extent_buffer **eb) + u64 owner_root, int level, int mirror_num, + struct extent_buffer **eb) { struct extent_buffer *buf = NULL; int ret; - buf = btrfs_find_create_tree_block(fs_info, bytenr); + buf = btrfs_find_create_tree_block(fs_info, bytenr, owner_root, level); if (IS_ERR(buf)) return 0; @@ -733,7 +750,8 @@ static int reada_start_machine_dev(struct btrfs_device *dev) logical = re->logical; atomic_inc(&dev->reada_in_flight); - ret = reada_tree_block_flagged(fs_info, logical, mirror_num, &eb); + ret = reada_tree_block_flagged(fs_info, logical, re->owner_root, + re->level, mirror_num, &eb); if (ret) __readahead_hook(fs_info, re, NULL, ret); else if (eb) @@ -940,6 +958,7 @@ struct reada_control *btrfs_reada_add(struct btrfs_root *root, u64 start; u64 generation; int ret; + int level; struct extent_buffer *node; static struct btrfs_key max_key = { .objectid = (u64)-1, @@ -962,9 +981,11 @@ struct reada_control *btrfs_reada_add(struct btrfs_root *root, node = btrfs_root_node(root); start = node->start; generation = btrfs_header_generation(node); + level = btrfs_header_level(node); free_extent_buffer(node); - ret = reada_add_block(rc, start, &max_key, generation); + ret = reada_add_block(rc, start, &max_key, root->root_key.objectid, + generation, level); if (ret) { kfree(rc); return ERR_PTR(ret); @@ -1020,3 +1041,45 @@ void btrfs_reada_detach(void *handle) kref_put(&rc->refcnt, reada_control_release); } + +/* + * Before removing a device (device replace or device remove ioctls), call this + * function to wait for all existing readahead requests on the device and to + * make sure no one queues more readahead requests for the device. + * + * Must be called without holding neither the device list mutex nor the device + * replace semaphore, otherwise it will deadlock. + */ +void btrfs_reada_remove_dev(struct btrfs_device *dev) +{ + struct btrfs_fs_info *fs_info = dev->fs_info; + + /* Serialize with readahead extent creation at reada_find_extent(). */ + spin_lock(&fs_info->reada_lock); + set_bit(BTRFS_DEV_STATE_NO_READA, &dev->dev_state); + spin_unlock(&fs_info->reada_lock); + + /* + * There might be readahead requests added to the radix trees which + * were not yet added to the readahead work queue. We need to start + * them and wait for their completion, otherwise we can end up with + * use-after-free problems when dropping the last reference on the + * readahead extents and their zones, as they need to access the + * device structure. + */ + reada_start_machine(fs_info); + btrfs_flush_workqueue(fs_info->readahead_workers); +} + +/* + * If when removing a device (device replace or device remove ioctls) an error + * happens after calling btrfs_reada_remove_dev(), call this to undo what that + * function did. This is safe to call even if btrfs_reada_remove_dev() was not + * called before. + */ +void btrfs_reada_undo_remove_dev(struct btrfs_device *dev) +{ + spin_lock(&dev->fs_info->reada_lock); + clear_bit(BTRFS_DEV_STATE_NO_READA, &dev->dev_state); + spin_unlock(&dev->fs_info->reada_lock); +} diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c index 7f03dbe5b609..2b490becbe67 100644 --- a/fs/btrfs/ref-verify.c +++ b/fs/btrfs/ref-verify.c @@ -495,14 +495,15 @@ static int process_extent_item(struct btrfs_fs_info *fs_info, } static int process_leaf(struct btrfs_root *root, - struct btrfs_path *path, u64 *bytenr, u64 *num_bytes) + struct btrfs_path *path, u64 *bytenr, u64 *num_bytes, + int *tree_block_level) { struct btrfs_fs_info *fs_info = root->fs_info; struct extent_buffer *leaf = path->nodes[0]; struct btrfs_extent_data_ref *dref; struct btrfs_shared_data_ref *sref; u32 count; - int i = 0, tree_block_level = 0, ret = 0; + int i = 0, ret = 0; struct btrfs_key key; int nritems = btrfs_header_nritems(leaf); @@ -515,15 +516,15 @@ static int process_leaf(struct btrfs_root *root, case BTRFS_METADATA_ITEM_KEY: *bytenr = key.objectid; ret = process_extent_item(fs_info, path, &key, i, - &tree_block_level); + tree_block_level); break; case BTRFS_TREE_BLOCK_REF_KEY: ret = add_tree_block(fs_info, key.offset, 0, - key.objectid, tree_block_level); + key.objectid, *tree_block_level); break; case BTRFS_SHARED_BLOCK_REF_KEY: ret = add_tree_block(fs_info, 0, key.offset, - key.objectid, tree_block_level); + key.objectid, *tree_block_level); break; case BTRFS_EXTENT_DATA_REF_KEY: dref = btrfs_item_ptr(leaf, i, @@ -549,38 +550,25 @@ static int process_leaf(struct btrfs_root *root, /* Walk down to the leaf from the given level */ static int walk_down_tree(struct btrfs_root *root, struct btrfs_path *path, - int level, u64 *bytenr, u64 *num_bytes) + int level, u64 *bytenr, u64 *num_bytes, + int *tree_block_level) { - struct btrfs_fs_info *fs_info = root->fs_info; struct extent_buffer *eb; - u64 block_bytenr, gen; int ret = 0; while (level >= 0) { if (level) { - struct btrfs_key first_key; - - block_bytenr = btrfs_node_blockptr(path->nodes[level], - path->slots[level]); - gen = btrfs_node_ptr_generation(path->nodes[level], - path->slots[level]); - btrfs_node_key_to_cpu(path->nodes[level], &first_key, - path->slots[level]); - eb = read_tree_block(fs_info, block_bytenr, gen, - level - 1, &first_key); + eb = btrfs_read_node_slot(path->nodes[level], + path->slots[level]); if (IS_ERR(eb)) return PTR_ERR(eb); - if (!extent_buffer_uptodate(eb)) { - free_extent_buffer(eb); - return -EIO; - } btrfs_tree_read_lock(eb); - btrfs_set_lock_blocking_read(eb); path->nodes[level-1] = eb; path->slots[level-1] = 0; - path->locks[level-1] = BTRFS_READ_LOCK_BLOCKING; + path->locks[level-1] = BTRFS_READ_LOCK; } else { - ret = process_leaf(root, path, bytenr, num_bytes); + ret = process_leaf(root, path, bytenr, num_bytes, + tree_block_level); if (ret) break; } @@ -681,18 +669,18 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info, u64 bytenr = generic_ref->bytenr; u64 num_bytes = generic_ref->len; u64 parent = generic_ref->parent; - u64 ref_root; - u64 owner; - u64 offset; + u64 ref_root = 0; + u64 owner = 0; + u64 offset = 0; if (!btrfs_test_opt(fs_info, REF_VERIFY)) return 0; if (generic_ref->type == BTRFS_REF_METADATA) { - ref_root = generic_ref->tree_ref.root; + if (!parent) + ref_root = generic_ref->tree_ref.root; owner = generic_ref->tree_ref.level; - offset = 0; - } else { + } else if (!parent) { ref_root = generic_ref->data_ref.ref_root; owner = generic_ref->data_ref.ino; offset = generic_ref->data_ref.offset; @@ -708,13 +696,10 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info, goto out; } - if (parent) { - ref->parent = parent; - } else { - ref->root_objectid = ref_root; - ref->owner = owner; - ref->offset = offset; - } + ref->parent = parent; + ref->owner = owner; + ref->root_objectid = ref_root; + ref->offset = offset; ref->num_refs = (action == BTRFS_DROP_DELAYED_REF) ? -1 : 1; memcpy(&ra->ref, ref, sizeof(struct ref_entry)); @@ -799,8 +784,7 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info, if (!be) { btrfs_err(fs_info, "trying to do action %d to bytenr %llu num_bytes %llu but there is no existing entry!", - action, (unsigned long long)bytenr, - (unsigned long long)num_bytes); + action, bytenr, num_bytes); dump_ref_action(fs_info, ra); kfree(ref); kfree(ra); @@ -860,6 +844,7 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info, "dropping a ref for a root that doesn't have a ref on the block"); dump_block_entry(fs_info, be); dump_ref_action(fs_info, ra); + kfree(ref); kfree(ra); goto out_unlock; } @@ -989,6 +974,7 @@ int btrfs_build_ref_tree(struct btrfs_fs_info *fs_info) { struct btrfs_path *path; struct extent_buffer *eb; + int tree_block_level = 0; u64 bytenr = 0, num_bytes = 0; int ret, level; @@ -1000,11 +986,10 @@ int btrfs_build_ref_tree(struct btrfs_fs_info *fs_info) return -ENOMEM; eb = btrfs_read_lock_root_node(fs_info->extent_root); - btrfs_set_lock_blocking_read(eb); level = btrfs_header_level(eb); path->nodes[level] = eb; path->slots[level] = 0; - path->locks[level] = BTRFS_READ_LOCK_BLOCKING; + path->locks[level] = BTRFS_READ_LOCK; while (1) { /* @@ -1014,7 +999,7 @@ int btrfs_build_ref_tree(struct btrfs_fs_info *fs_info) * different leaf from the original extent item. */ ret = walk_down_tree(fs_info->extent_root, path, level, - &bytenr, &num_bytes); + &bytenr, &num_bytes, &tree_block_level); if (ret) break; ret = walk_up_tree(path, &level); diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c index 99aa87c08912..b24396cf2f99 100644 --- a/fs/btrfs/reflink.c +++ b/fs/btrfs/reflink.c @@ -31,10 +31,10 @@ static int clone_finish_inode_update(struct btrfs_trans_handle *trans, endoff = destoff + olen; if (endoff > inode->i_size) { i_size_write(inode, endoff); - btrfs_inode_safe_disk_i_size_write(inode, 0); + btrfs_inode_safe_disk_i_size_write(BTRFS_I(inode), 0); } - ret = btrfs_update_inode(trans, root, inode); + ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); if (ret) { btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); @@ -81,7 +81,10 @@ static int copy_inline_to_page(struct btrfs_inode *inode, goto out_unlock; } - set_page_extent_mapped(page); + ret = set_page_extent_mapped(page); + if (ret < 0) + goto out_unlock; + clear_extent_bit(&inode->io_tree, file_offset, range_end, EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0, NULL); @@ -89,6 +92,19 @@ static int copy_inline_to_page(struct btrfs_inode *inode, if (ret) goto out_unlock; + /* + * After dirtying the page our caller will need to start a transaction, + * and if we are low on metadata free space, that can cause flushing of + * delalloc for all inodes in order to get metadata space released. + * However we are holding the range locked for the whole duration of + * the clone/dedupe operation, so we may deadlock if that happens and no + * other task releases enough space. So mark this inode as not being + * possible to flush to avoid such deadlock. We will clear that flag + * when we finish cloning all extents, since a transaction is started + * after finding each extent to clone. + */ + set_bit(BTRFS_INODE_NO_DELALLOC_FLUSH, &inode->runtime_flags); + if (comp_type == BTRFS_COMPRESS_NONE) { char *map; @@ -163,6 +179,7 @@ static int clone_copy_inline_extent(struct inode *dst, const u64 aligned_end = ALIGN(new_key->offset + datal, fs_info->sectorsize); struct btrfs_trans_handle *trans = NULL; + struct btrfs_drop_extents_args drop_args = { 0 }; int ret; struct btrfs_key key; @@ -252,7 +269,11 @@ copy_inline_extent: trans = NULL; goto out; } - ret = btrfs_drop_extents(trans, root, dst, drop_start, aligned_end, 1); + drop_args.path = path; + drop_args.start = drop_start; + drop_args.end = aligned_end; + drop_args.drop_cache = true; + ret = btrfs_drop_extents(trans, root, BTRFS_I(dst), &drop_args); if (ret) goto out; ret = btrfs_insert_empty_item(trans, root, path, new_key, size); @@ -263,7 +284,7 @@ copy_inline_extent: btrfs_item_ptr_offset(path->nodes[0], path->slots[0]), size); - inode_add_bytes(dst, datal); + btrfs_update_inode_bytes(BTRFS_I(dst), datal, drop_args.bytes_found); set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &BTRFS_I(dst)->runtime_flags); ret = btrfs_inode_set_file_extent_range(BTRFS_I(dst), 0, aligned_end); out: @@ -347,7 +368,6 @@ static int btrfs_clone(struct inode *src, struct inode *inode, u64 drop_start; /* Note the key will change type as we walk through the tree */ - path->leave_spinning = 1; ret = btrfs_search_slot(NULL, BTRFS_I(src)->root, &key, path, 0, 0); if (ret < 0) @@ -417,7 +437,6 @@ process_slot: size); btrfs_release_path(path); - path->leave_spinning = 0; memcpy(&new_key, &key, sizeof(new_key)); new_key.objectid = btrfs_ino(BTRFS_I(inode)); @@ -533,7 +552,6 @@ process_slot: * mixing buffered and direct IO writes against this file. */ btrfs_release_path(path); - path->leave_spinning = 0; ret = btrfs_replace_file_extents(inode, path, last_dest_end, destoff + len - 1, NULL, &trans); @@ -547,6 +565,8 @@ process_slot: out: btrfs_free_path(path); kvfree(buf); + clear_bit(BTRFS_INODE_NO_DELALLOC_FLUSH, &BTRFS_I(inode)->runtime_flags); + return ret; } @@ -652,7 +672,7 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src, if (destoff > inode->i_size) { const u64 wb_start = ALIGN_DOWN(inode->i_size, bs); - ret = btrfs_cont_expand(inode, inode->i_size, destoff); + ret = btrfs_cont_expand(BTRFS_I(inode), inode->i_size, destoff); if (ret) return ret; /* diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 3602806d71bd..232d5da7b7be 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -18,7 +18,6 @@ #include "btrfs_inode.h" #include "async-thread.h" #include "free-space-cache.h" -#include "inode-map.h" #include "qgroup.h" #include "print-tree.h" #include "delalloc-space.h" @@ -98,6 +97,7 @@ struct tree_block { struct rb_node rb_node; u64 bytenr; }; /* Use rb_simple_node for search/insert */ + u64 owner; struct btrfs_key key; unsigned int level:8; unsigned int key_ready:1; @@ -669,9 +669,7 @@ static void __del_reloc_root(struct btrfs_root *root) RB_CLEAR_NODE(&node->rb_node); } spin_unlock(&rc->reloc_root_tree.lock); - if (!node) - return; - BUG_ON((struct btrfs_root *)node->data != root); + ASSERT(!node || (struct btrfs_root *)node->data == root); } /* @@ -783,7 +781,7 @@ static struct btrfs_root *create_reloc_root(struct btrfs_trans_handle *trans, btrfs_set_root_refs(root_item, 0); memset(&root_item->drop_progress, 0, sizeof(struct btrfs_disk_key)); - root_item->drop_level = 0; + btrfs_set_root_drop_level(root_item, 0); } btrfs_tree_unlock(eb); @@ -1196,7 +1194,6 @@ again: btrfs_node_key_to_cpu(path->nodes[lowest_level], &key, slot); eb = btrfs_lock_root_node(dest); - btrfs_set_lock_blocking_write(eb); level = btrfs_header_level(eb); if (level < lowest_level) { @@ -1210,7 +1207,6 @@ again: BTRFS_NESTING_COW); BUG_ON(ret); } - btrfs_set_lock_blocking_write(eb); if (next_key) { next_key->objectid = (u64)-1; @@ -1220,8 +1216,6 @@ again: parent = eb; while (1) { - struct btrfs_key first_key; - level = btrfs_header_level(parent); BUG_ON(level < lowest_level); @@ -1237,7 +1231,6 @@ again: old_bytenr = btrfs_node_blockptr(parent, slot); blocksize = fs_info->nodesize; old_ptr_gen = btrfs_node_ptr_generation(parent, slot); - btrfs_node_key_to_cpu(parent, &first_key, slot); if (level <= max_level) { eb = path->nodes[level]; @@ -1262,15 +1255,10 @@ again: break; } - eb = read_tree_block(fs_info, old_bytenr, old_ptr_gen, - level - 1, &first_key); + eb = btrfs_read_node_slot(parent, slot); if (IS_ERR(eb)) { ret = PTR_ERR(eb); break; - } else if (!extent_buffer_uptodate(eb)) { - ret = -EIO; - free_extent_buffer(eb); - break; } btrfs_tree_lock(eb); if (cow) { @@ -1279,7 +1267,6 @@ again: BTRFS_NESTING_COW); BUG_ON(ret); } - btrfs_set_lock_blocking_write(eb); btrfs_tree_unlock(parent); free_extent_buffer(parent); @@ -1418,10 +1405,8 @@ static noinline_for_stack int walk_down_reloc_tree(struct btrfs_root *root, struct btrfs_path *path, int *level) { - struct btrfs_fs_info *fs_info = root->fs_info; struct extent_buffer *eb = NULL; int i; - u64 bytenr; u64 ptr_gen = 0; u64 last_snapshot; u32 nritems; @@ -1429,8 +1414,6 @@ int walk_down_reloc_tree(struct btrfs_root *root, struct btrfs_path *path, last_snapshot = btrfs_root_last_snapshot(&root->root_item); for (i = *level; i > 0; i--) { - struct btrfs_key first_key; - eb = path->nodes[i]; nritems = btrfs_header_nritems(eb); while (path->slots[i] < nritems) { @@ -1450,16 +1433,9 @@ int walk_down_reloc_tree(struct btrfs_root *root, struct btrfs_path *path, return 0; } - bytenr = btrfs_node_blockptr(eb, path->slots[i]); - btrfs_node_key_to_cpu(eb, &first_key, path->slots[i]); - eb = read_tree_block(fs_info, bytenr, ptr_gen, i - 1, - &first_key); - if (IS_ERR(eb)) { + eb = btrfs_read_node_slot(eb, path->slots[i]); + if (IS_ERR(eb)) return PTR_ERR(eb); - } else if (!extent_buffer_uptodate(eb)) { - free_extent_buffer(eb); - return -EIO; - } BUG_ON(btrfs_header_level(eb) != i - 1); path->nodes[i - 1] = eb; path->slots[i - 1] = 0; @@ -1575,7 +1551,7 @@ static void insert_dirty_subvol(struct btrfs_trans_handle *trans, reloc_root_item = &reloc_root->root_item; memset(&reloc_root_item->drop_progress, 0, sizeof(reloc_root_item->drop_progress)); - reloc_root_item->drop_level = 0; + btrfs_set_root_drop_level(reloc_root_item, 0); btrfs_set_root_refs(reloc_root_item, 0); btrfs_update_reloc_root(trans, root); @@ -1648,11 +1624,11 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc, struct btrfs_root_item *root_item; struct btrfs_path *path; struct extent_buffer *leaf; + int reserve_level; int level; int max_level; int replaced = 0; - int ret; - int err = 0; + int ret = 0; u32 min_reserved; path = btrfs_alloc_path(); @@ -1671,7 +1647,7 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc, } else { btrfs_disk_key_to_cpu(&key, &root_item->drop_progress); - level = root_item->drop_level; + level = btrfs_root_drop_level(root_item); BUG_ON(level == 0); path->lowest_level = level; ret = btrfs_search_slot(NULL, reloc_root, &key, path, 0, 0); @@ -1696,19 +1672,18 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc, * Thus the needed metadata size is at most root_level * nodesize, * and * 2 since we have two trees to COW. */ - min_reserved = fs_info->nodesize * btrfs_root_level(root_item) * 2; + reserve_level = max_t(int, 1, btrfs_root_level(root_item)); + min_reserved = fs_info->nodesize * reserve_level * 2; memset(&next_key, 0, sizeof(next_key)); while (1) { ret = btrfs_block_rsv_refill(root, rc->block_rsv, min_reserved, BTRFS_RESERVE_FLUSH_LIMIT); - if (ret) { - err = ret; + if (ret) goto out; - } trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { - err = PTR_ERR(trans); + ret = PTR_ERR(trans); trans = NULL; goto out; } @@ -1730,10 +1705,8 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc, max_level = level; ret = walk_down_reloc_tree(reloc_root, path, &level); - if (ret < 0) { - err = ret; + if (ret < 0) goto out; - } if (ret > 0) break; @@ -1744,11 +1717,8 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc, ret = replace_path(trans, rc, root, reloc_root, path, &next_key, level, max_level); } - if (ret < 0) { - err = ret; + if (ret < 0) goto out; - } - if (ret > 0) { level = ret; btrfs_node_key_to_cpu(path->nodes[level], &key, @@ -1767,7 +1737,7 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc, */ btrfs_node_key(path->nodes[level], &root_item->drop_progress, path->slots[level]); - root_item->drop_level = level; + btrfs_set_root_drop_level(root_item, level); btrfs_end_transaction_throttle(trans); trans = NULL; @@ -1787,12 +1757,10 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc, BTRFS_NESTING_COW); btrfs_tree_unlock(leaf); free_extent_buffer(leaf); - if (ret < 0) - err = ret; out: btrfs_free_path(path); - if (err == 0) + if (ret == 0) insert_dirty_subvol(trans, rc, root); if (trans) @@ -1803,7 +1771,7 @@ out: if (replaced && rc->stage == UPDATE_DATA_PTRS) invalidate_extent_cache(root, &key, &next_key); - return err; + return ret; } static noinline_for_stack @@ -2203,7 +2171,6 @@ static int do_relocation(struct btrfs_trans_handle *trans, struct btrfs_key *key, struct btrfs_path *path, int lowest) { - struct btrfs_fs_info *fs_info = rc->extent_root->fs_info; struct btrfs_backref_node *upper; struct btrfs_backref_edge *edge; struct btrfs_backref_edge *edges[BTRFS_MAX_LEVEL - 1]; @@ -2211,17 +2178,14 @@ static int do_relocation(struct btrfs_trans_handle *trans, struct extent_buffer *eb; u32 blocksize; u64 bytenr; - u64 generation; int slot; - int ret; - int err = 0; + int ret = 0; BUG_ON(lowest && node->eb); path->lowest_level = node->level + 1; rc->backref_cache.path[node->level] = node; list_for_each_entry(edge, &node->upper, list[LOWER]) { - struct btrfs_key first_key; struct btrfs_ref ref = { 0 }; cond_resched(); @@ -2233,10 +2197,8 @@ static int do_relocation(struct btrfs_trans_handle *trans, if (upper->eb && !upper->locked) { if (!lowest) { ret = btrfs_bin_search(upper->eb, key, &slot); - if (ret < 0) { - err = ret; + if (ret < 0) goto next; - } BUG_ON(ret); bytenr = btrfs_node_blockptr(upper->eb, slot); if (node->eb->start == bytenr) @@ -2248,10 +2210,8 @@ static int do_relocation(struct btrfs_trans_handle *trans, if (!upper->eb) { ret = btrfs_search_slot(trans, root, key, path, 0, 1); if (ret) { - if (ret < 0) - err = ret; - else - err = -ENOENT; + if (ret > 0) + ret = -ENOENT; btrfs_release_path(path); break; @@ -2271,10 +2231,8 @@ static int do_relocation(struct btrfs_trans_handle *trans, btrfs_release_path(path); } else { ret = btrfs_bin_search(upper->eb, key, &slot); - if (ret < 0) { - err = ret; + if (ret < 0) goto next; - } BUG_ON(ret); } @@ -2285,7 +2243,7 @@ static int do_relocation(struct btrfs_trans_handle *trans, "lowest leaf/node mismatch: bytenr %llu node->bytenr %llu slot %d upper %llu", bytenr, node->bytenr, slot, upper->eb->start); - err = -EIO; + ret = -EIO; goto next; } } else { @@ -2294,30 +2252,20 @@ static int do_relocation(struct btrfs_trans_handle *trans, } blocksize = root->fs_info->nodesize; - generation = btrfs_node_ptr_generation(upper->eb, slot); - btrfs_node_key_to_cpu(upper->eb, &first_key, slot); - eb = read_tree_block(fs_info, bytenr, generation, - upper->level - 1, &first_key); + eb = btrfs_read_node_slot(upper->eb, slot); if (IS_ERR(eb)) { - err = PTR_ERR(eb); - goto next; - } else if (!extent_buffer_uptodate(eb)) { - free_extent_buffer(eb); - err = -EIO; + ret = PTR_ERR(eb); goto next; } btrfs_tree_lock(eb); - btrfs_set_lock_blocking_write(eb); if (!node->eb) { ret = btrfs_cow_block(trans, root, eb, upper->eb, slot, &eb, BTRFS_NESTING_COW); btrfs_tree_unlock(eb); free_extent_buffer(eb); - if (ret < 0) { - err = ret; + if (ret < 0) goto next; - } BUG_ON(node->eb != eb); } else { btrfs_set_node_blockptr(upper->eb, slot, @@ -2343,19 +2291,19 @@ next: btrfs_backref_drop_node_buffer(upper); else btrfs_backref_unlock_node_buffer(upper); - if (err) + if (ret) break; } - if (!err && node->pending) { + if (!ret && node->pending) { btrfs_backref_drop_node_buffer(node); list_move_tail(&node->list, &rc->backref_cache.changed); node->pending = 0; } path->lowest_level = 0; - BUG_ON(err == -ENOSPC); - return err; + BUG_ON(ret == -ENOSPC); + return ret; } static int link_to_upper(struct btrfs_trans_handle *trans, @@ -2444,8 +2392,8 @@ static int get_tree_block_key(struct btrfs_fs_info *fs_info, { struct extent_buffer *eb; - eb = read_tree_block(fs_info, block->bytenr, block->key.offset, - block->level, NULL); + eb = read_tree_block(fs_info, block->bytenr, block->owner, + block->key.offset, block->level, NULL); if (IS_ERR(eb)) { return PTR_ERR(eb); } else if (!extent_buffer_uptodate(eb)) { @@ -2544,7 +2492,9 @@ int relocate_tree_blocks(struct btrfs_trans_handle *trans, /* Kick in readahead for tree blocks with missing keys */ rbtree_postorder_for_each_entry_safe(block, next, blocks, rb_node) { if (!block->key_ready) - readahead_tree_block(fs_info, block->bytenr); + btrfs_readahead_tree_block(fs_info, block->bytenr, + block->owner, 0, + block->level); } /* Get first keys */ @@ -2603,6 +2553,31 @@ static noinline_for_stack int prealloc_file_extent_cluster( if (ret) return ret; + /* + * On a zoned filesystem, we cannot preallocate the file region. + * Instead, we dirty and fiemap_write the region. + */ + if (btrfs_is_zoned(inode->root->fs_info)) { + struct btrfs_root *root = inode->root; + struct btrfs_trans_handle *trans; + + end = cluster->end - offset + 1; + trans = btrfs_start_transaction(root, 1); + if (IS_ERR(trans)) + return PTR_ERR(trans); + + inode->vfs_inode.i_ctime = current_time(&inode->vfs_inode); + i_size_write(&inode->vfs_inode, end); + ret = btrfs_update_inode(trans, root, inode); + if (ret) { + btrfs_abort_transaction(trans, ret); + btrfs_end_transaction(trans); + return ret; + } + + return btrfs_end_transaction(trans); + } + inode_lock(&inode->vfs_inode); for (nr = 0; nr < cluster->nr; nr++) { start = cluster->boundary[nr] - offset; @@ -2665,7 +2640,7 @@ int setup_extent_mapping(struct inode *inode, u64 start, u64 end, /* * Allow error injection to test balance cancellation */ -int btrfs_should_cancel_balance(struct btrfs_fs_info *fs_info) +noinline int btrfs_should_cancel_balance(struct btrfs_fs_info *fs_info) { return atomic_read(&fs_info->balance_cancel_req) || fatal_signal_pending(current); @@ -2729,6 +2704,15 @@ static int relocate_file_extent_cluster(struct inode *inode, goto out; } } + ret = set_page_extent_mapped(page); + if (ret < 0) { + btrfs_delalloc_release_metadata(BTRFS_I(inode), + PAGE_SIZE, true); + btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE); + unlock_page(page); + put_page(page); + goto out; + } if (PageReadahead(page)) { page_cache_async_readahead(inode->i_mapping, @@ -2756,8 +2740,6 @@ static int relocate_file_extent_cluster(struct inode *inode, lock_extent(&BTRFS_I(inode)->io_tree, page_start, page_end); - set_page_extent_mapped(page); - if (nr < cluster->nr && page_start + offset == cluster->boundary[nr]) { set_extent_bits(&BTRFS_I(inode)->io_tree, @@ -2799,6 +2781,8 @@ static int relocate_file_extent_cluster(struct inode *inode, } } WARN_ON(nr != cluster->nr); + if (btrfs_is_zoned(fs_info) && !ret) + ret = btrfs_wait_ordered_range(inode, 0, (u64)-1); out: kfree(ra); return ret; @@ -2851,21 +2835,58 @@ static int add_tree_block(struct reloc_control *rc, u32 item_size; int level = -1; u64 generation; + u64 owner = 0; eb = path->nodes[0]; item_size = btrfs_item_size_nr(eb, path->slots[0]); if (extent_key->type == BTRFS_METADATA_ITEM_KEY || item_size >= sizeof(*ei) + sizeof(*bi)) { + unsigned long ptr = 0, end; + ei = btrfs_item_ptr(eb, path->slots[0], struct btrfs_extent_item); + end = (unsigned long)ei + item_size; if (extent_key->type == BTRFS_EXTENT_ITEM_KEY) { bi = (struct btrfs_tree_block_info *)(ei + 1); level = btrfs_tree_block_level(eb, bi); + ptr = (unsigned long)(bi + 1); } else { level = (int)extent_key->offset; + ptr = (unsigned long)(ei + 1); } generation = btrfs_extent_generation(eb, ei); + + /* + * We're reading random blocks without knowing their owner ahead + * of time. This is ok most of the time, as all reloc roots and + * fs roots have the same lock type. However normal trees do + * not, and the only way to know ahead of time is to read the + * inline ref offset. We know it's an fs root if + * + * 1. There's more than one ref. + * 2. There's a SHARED_DATA_REF_KEY set. + * 3. FULL_BACKREF is set on the flags. + * + * Otherwise it's safe to assume that the ref offset == the + * owner of this block, so we can use that when calling + * read_tree_block. + */ + if (btrfs_extent_refs(eb, ei) == 1 && + !(btrfs_extent_flags(eb, ei) & + BTRFS_BLOCK_FLAG_FULL_BACKREF) && + ptr < end) { + struct btrfs_extent_inline_ref *iref; + int type; + + iref = (struct btrfs_extent_inline_ref *)ptr; + type = btrfs_get_extent_inline_ref_type(eb, iref, + BTRFS_REF_TYPE_BLOCK); + if (type == BTRFS_REF_TYPE_INVALID) + return -EINVAL; + if (type == BTRFS_TREE_BLOCK_REF_KEY) + owner = btrfs_extent_inline_ref_offset(eb, iref); + } } else if (unlikely(item_size == sizeof(struct btrfs_extent_item_v0))) { btrfs_print_v0_err(eb->fs_info); btrfs_handle_fs_error(eb->fs_info, -EINVAL, NULL); @@ -2887,6 +2908,7 @@ static int add_tree_block(struct reloc_control *rc, block->key.offset = generation; block->level = level; block->key_ready = 0; + block->owner = owner; rb_node = rb_simple_insert(blocks, block->bytenr, &block->rb_node); if (rb_node) @@ -3025,11 +3047,16 @@ static int delete_v1_space_cache(struct extent_buffer *leaf, return 0; for (i = 0; i < btrfs_header_nritems(leaf); i++) { + u8 type; + btrfs_item_key_to_cpu(leaf, &key, i); if (key.type != BTRFS_EXTENT_DATA_KEY) continue; ei = btrfs_item_ptr(leaf, i, struct btrfs_file_extent_item); - if (btrfs_file_extent_type(leaf, ei) == BTRFS_FILE_EXTENT_REG && + type = btrfs_file_extent_type(leaf, ei); + + if ((type == BTRFS_FILE_EXTENT_REG || + type == BTRFS_FILE_EXTENT_PREALLOC) && btrfs_file_extent_disk_bytenr(leaf, ei) == data_bytenr) { found = true; space_cache_ino = key.objectid; @@ -3069,7 +3096,7 @@ int add_data_references(struct reloc_control *rc, while ((ref_node = ulist_next(leaves, &leaf_uiter))) { struct extent_buffer *eb; - eb = read_tree_block(fs_info, ref_node->val, 0, 0, NULL); + eb = read_tree_block(fs_info, ref_node->val, 0, 0, 0, NULL); if (IS_ERR(eb)) { ret = PTR_ERR(eb); break; @@ -3434,8 +3461,12 @@ static int __insert_orphan_inode(struct btrfs_trans_handle *trans, struct btrfs_path *path; struct btrfs_inode_item *item; struct extent_buffer *leaf; + u64 flags = BTRFS_INODE_NOCOMPRESS | BTRFS_INODE_PREALLOC; int ret; + if (btrfs_is_zoned(trans->fs_info)) + flags &= ~BTRFS_INODE_PREALLOC; + path = btrfs_alloc_path(); if (!path) return -ENOMEM; @@ -3450,8 +3481,7 @@ static int __insert_orphan_inode(struct btrfs_trans_handle *trans, btrfs_set_inode_generation(leaf, item, 1); btrfs_set_inode_size(leaf, item, 0); btrfs_set_inode_mode(leaf, item, S_IFREG | 0600); - btrfs_set_inode_flags(leaf, item, BTRFS_INODE_NOCOMPRESS | - BTRFS_INODE_PREALLOC); + btrfs_set_inode_flags(leaf, item, flags); btrfs_mark_buffer_dirty(leaf); out: btrfs_free_path(path); @@ -3479,7 +3509,7 @@ struct inode *create_reloc_inode(struct btrfs_fs_info *fs_info, return ERR_CAST(trans); } - err = btrfs_find_free_objectid(root, &objectid); + err = btrfs_get_free_objectid(root, &objectid); if (err) goto out; @@ -3692,7 +3722,7 @@ static noinline_for_stack int mark_garbage_root(struct btrfs_root *root) memset(&root->root_item.drop_progress, 0, sizeof(root->root_item.drop_progress)); - root->root_item.drop_level = 0; + btrfs_set_root_drop_level(&root->root_item, 0); btrfs_set_root_refs(&root->root_item, 0); ret = btrfs_update_root(trans, fs_info->tree_root, &root->root_key, &root->root_item); diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index cf63f1e27a27..582df11d298a 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -20,6 +20,7 @@ #include "rcu-string.h" #include "raid56.h" #include "block-group.h" +#include "zoned.h" /* * This is only the first step towards a full-features scrub. It reads all @@ -71,11 +72,9 @@ struct scrub_page { u64 physical; u64 physical_for_dev_replace; atomic_t refs; - struct { - unsigned int mirror_num:8; - unsigned int have_csum:1; - unsigned int io_error:1; - }; + u8 mirror_num; + int have_csum:1; + int io_error:1; u8 csum[BTRFS_CSUM_SIZE]; struct scrub_recover *recover; @@ -131,7 +130,7 @@ struct scrub_parity { int nsectors; - u64 stripe_len; + u32 stripe_len; refcount_t refs; @@ -161,13 +160,13 @@ struct scrub_ctx { atomic_t workers_pending; spinlock_t list_lock; wait_queue_head_t list_wait; - u16 csum_size; struct list_head csum_list; atomic_t cancel_req; int readonly; int pages_per_rd_bio; int is_dev_replace; + u64 write_pointer; struct scrub_bio *wr_curr_bio; struct mutex wr_lock; @@ -235,15 +234,15 @@ static void scrub_parity_get(struct scrub_parity *sparity); static void scrub_parity_put(struct scrub_parity *sparity); static int scrub_add_page_to_rd_bio(struct scrub_ctx *sctx, struct scrub_page *spage); -static int scrub_pages(struct scrub_ctx *sctx, u64 logical, u64 len, +static int scrub_pages(struct scrub_ctx *sctx, u64 logical, u32 len, u64 physical, struct btrfs_device *dev, u64 flags, - u64 gen, int mirror_num, u8 *csum, int force, + u64 gen, int mirror_num, u8 *csum, u64 physical_for_dev_replace); static void scrub_bio_end_io(struct bio *bio); static void scrub_bio_end_io_worker(struct btrfs_work *work); static void scrub_block_complete(struct scrub_block *sblock); static void scrub_remap_extent(struct btrfs_fs_info *fs_info, - u64 extent_logical, u64 extent_len, + u64 extent_logical, u32 extent_len, u64 *extent_physical, struct btrfs_device **extent_dev, int *extent_mirror_num); @@ -256,10 +255,10 @@ static void __scrub_blocked_if_needed(struct btrfs_fs_info *fs_info); static void scrub_blocked_if_needed(struct btrfs_fs_info *fs_info); static void scrub_put_ctx(struct scrub_ctx *sctx); -static inline int scrub_is_page_on_raid56(struct scrub_page *page) +static inline int scrub_is_page_on_raid56(struct scrub_page *spage) { - return page->recover && - (page->recover->bbio->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK); + return spage->recover && + (spage->recover->bbio->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK); } static void scrub_pending_bio_inc(struct scrub_ctx *sctx) @@ -610,7 +609,6 @@ static noinline_for_stack struct scrub_ctx *scrub_setup_ctx( atomic_set(&sctx->bios_in_flight, 0); atomic_set(&sctx->workers_pending, 0); atomic_set(&sctx->cancel_req, 0); - sctx->csum_size = btrfs_super_csum_size(fs_info->super_copy); spin_lock_init(&sctx->list_lock); spin_lock_init(&sctx->stat_lock); @@ -859,6 +857,9 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) have_csum = sblock_to_check->pagev[0]->have_csum; dev = sblock_to_check->pagev[0]->dev; + if (btrfs_is_zoned(fs_info) && !sctx->is_dev_replace) + return btrfs_repair_one_zone(fs_info, logical); + /* * We must use GFP_NOFS because the scrub task might be waiting for a * worker task executing this function and in turn a transaction commit @@ -1092,11 +1093,11 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) success = 1; for (page_num = 0; page_num < sblock_bad->page_count; page_num++) { - struct scrub_page *page_bad = sblock_bad->pagev[page_num]; + struct scrub_page *spage_bad = sblock_bad->pagev[page_num]; struct scrub_block *sblock_other = NULL; /* skip no-io-error page in scrub */ - if (!page_bad->io_error && !sctx->is_dev_replace) + if (!spage_bad->io_error && !sctx->is_dev_replace) continue; if (scrub_is_page_on_raid56(sblock_bad->pagev[0])) { @@ -1108,7 +1109,7 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) * sblock_for_recheck array to target device. */ sblock_other = NULL; - } else if (page_bad->io_error) { + } else if (spage_bad->io_error) { /* try to find no-io-error page in mirrors */ for (mirror_index = 0; mirror_index < BTRFS_MAX_MIRRORS && @@ -1147,7 +1148,7 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) sblock_other, page_num, 0); if (0 == ret) - page_bad->io_error = 0; + spage_bad->io_error = 0; else success = 0; } @@ -1325,13 +1326,13 @@ static int scrub_setup_recheck_block(struct scrub_block *original_sblock, for (mirror_index = 0; mirror_index < nmirrors; mirror_index++) { struct scrub_block *sblock; - struct scrub_page *page; + struct scrub_page *spage; sblock = sblocks_for_recheck + mirror_index; sblock->sctx = sctx; - page = kzalloc(sizeof(*page), GFP_NOFS); - if (!page) { + spage = kzalloc(sizeof(*spage), GFP_NOFS); + if (!spage) { leave_nomem: spin_lock(&sctx->stat_lock); sctx->stat.malloc_errors++; @@ -1339,17 +1340,17 @@ leave_nomem: scrub_put_recover(fs_info, recover); return -ENOMEM; } - scrub_page_get(page); - sblock->pagev[page_index] = page; - page->sblock = sblock; - page->flags = flags; - page->generation = generation; - page->logical = logical; - page->have_csum = have_csum; + scrub_page_get(spage); + sblock->pagev[page_index] = spage; + spage->sblock = sblock; + spage->flags = flags; + spage->generation = generation; + spage->logical = logical; + spage->have_csum = have_csum; if (have_csum) - memcpy(page->csum, + memcpy(spage->csum, original_sblock->pagev[0]->csum, - sctx->csum_size); + sctx->fs_info->csum_size); scrub_stripe_index_and_offset(logical, bbio->map_type, @@ -1360,23 +1361,23 @@ leave_nomem: mirror_index, &stripe_index, &stripe_offset); - page->physical = bbio->stripes[stripe_index].physical + + spage->physical = bbio->stripes[stripe_index].physical + stripe_offset; - page->dev = bbio->stripes[stripe_index].dev; + spage->dev = bbio->stripes[stripe_index].dev; BUG_ON(page_index >= original_sblock->page_count); - page->physical_for_dev_replace = + spage->physical_for_dev_replace = original_sblock->pagev[page_index]-> physical_for_dev_replace; /* for missing devices, dev->bdev is NULL */ - page->mirror_num = mirror_index + 1; + spage->mirror_num = mirror_index + 1; sblock->page_count++; - page->page = alloc_page(GFP_NOFS); - if (!page->page) + spage->page = alloc_page(GFP_NOFS); + if (!spage->page) goto leave_nomem; scrub_get_recover(recover); - page->recover = recover; + spage->recover = recover; } scrub_put_recover(fs_info, recover); length -= sublen; @@ -1394,19 +1395,19 @@ static void scrub_bio_wait_endio(struct bio *bio) static int scrub_submit_raid56_bio_wait(struct btrfs_fs_info *fs_info, struct bio *bio, - struct scrub_page *page) + struct scrub_page *spage) { DECLARE_COMPLETION_ONSTACK(done); int ret; int mirror_num; - bio->bi_iter.bi_sector = page->logical >> 9; + bio->bi_iter.bi_sector = spage->logical >> 9; bio->bi_private = &done; bio->bi_end_io = scrub_bio_wait_endio; - mirror_num = page->sblock->pagev[0]->mirror_num; - ret = raid56_parity_recover(fs_info, bio, page->recover->bbio, - page->recover->map_length, + mirror_num = spage->sblock->pagev[0]->mirror_num; + ret = raid56_parity_recover(fs_info, bio, spage->recover->bbio, + spage->recover->map_length, mirror_num, 0); if (ret) return ret; @@ -1431,10 +1432,10 @@ static void scrub_recheck_block_on_raid56(struct btrfs_fs_info *fs_info, bio_set_dev(bio, first_page->dev->bdev); for (page_num = 0; page_num < sblock->page_count; page_num++) { - struct scrub_page *page = sblock->pagev[page_num]; + struct scrub_page *spage = sblock->pagev[page_num]; - WARN_ON(!page->page); - bio_add_page(bio, page->page, PAGE_SIZE, 0); + WARN_ON(!spage->page); + bio_add_page(bio, spage->page, PAGE_SIZE, 0); } if (scrub_submit_raid56_bio_wait(fs_info, bio, first_page)) { @@ -1475,24 +1476,24 @@ static void scrub_recheck_block(struct btrfs_fs_info *fs_info, for (page_num = 0; page_num < sblock->page_count; page_num++) { struct bio *bio; - struct scrub_page *page = sblock->pagev[page_num]; + struct scrub_page *spage = sblock->pagev[page_num]; - if (page->dev->bdev == NULL) { - page->io_error = 1; + if (spage->dev->bdev == NULL) { + spage->io_error = 1; sblock->no_io_error_seen = 0; continue; } - WARN_ON(!page->page); + WARN_ON(!spage->page); bio = btrfs_io_bio_alloc(1); - bio_set_dev(bio, page->dev->bdev); + bio_set_dev(bio, spage->dev->bdev); - bio_add_page(bio, page->page, PAGE_SIZE, 0); - bio->bi_iter.bi_sector = page->physical >> 9; + bio_add_page(bio, spage->page, PAGE_SIZE, 0); + bio->bi_iter.bi_sector = spage->physical >> 9; bio->bi_opf = REQ_OP_READ; if (btrfsic_submit_bio_wait(bio)) { - page->io_error = 1; + spage->io_error = 1; sblock->no_io_error_seen = 0; } @@ -1548,36 +1549,36 @@ static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad, struct scrub_block *sblock_good, int page_num, int force_write) { - struct scrub_page *page_bad = sblock_bad->pagev[page_num]; - struct scrub_page *page_good = sblock_good->pagev[page_num]; + struct scrub_page *spage_bad = sblock_bad->pagev[page_num]; + struct scrub_page *spage_good = sblock_good->pagev[page_num]; struct btrfs_fs_info *fs_info = sblock_bad->sctx->fs_info; - BUG_ON(page_bad->page == NULL); - BUG_ON(page_good->page == NULL); + BUG_ON(spage_bad->page == NULL); + BUG_ON(spage_good->page == NULL); if (force_write || sblock_bad->header_error || - sblock_bad->checksum_error || page_bad->io_error) { + sblock_bad->checksum_error || spage_bad->io_error) { struct bio *bio; int ret; - if (!page_bad->dev->bdev) { + if (!spage_bad->dev->bdev) { btrfs_warn_rl(fs_info, "scrub_repair_page_from_good_copy(bdev == NULL) is unexpected"); return -EIO; } bio = btrfs_io_bio_alloc(1); - bio_set_dev(bio, page_bad->dev->bdev); - bio->bi_iter.bi_sector = page_bad->physical >> 9; + bio_set_dev(bio, spage_bad->dev->bdev); + bio->bi_iter.bi_sector = spage_bad->physical >> 9; bio->bi_opf = REQ_OP_WRITE; - ret = bio_add_page(bio, page_good->page, PAGE_SIZE, 0); + ret = bio_add_page(bio, spage_good->page, PAGE_SIZE, 0); if (PAGE_SIZE != ret) { bio_put(bio); return -EIO; } if (btrfsic_submit_bio_wait(bio)) { - btrfs_dev_stat_inc_and_print(page_bad->dev, + btrfs_dev_stat_inc_and_print(spage_bad->dev, BTRFS_DEV_STAT_WRITE_ERRS); atomic64_inc(&fs_info->dev_replace.num_write_errors); bio_put(bio); @@ -1622,6 +1623,28 @@ static int scrub_write_page_to_dev_replace(struct scrub_block *sblock, return scrub_add_page_to_wr_bio(sblock->sctx, spage); } +static int fill_writer_pointer_gap(struct scrub_ctx *sctx, u64 physical) +{ + int ret = 0; + u64 length; + + if (!btrfs_is_zoned(sctx->fs_info)) + return 0; + + if (!btrfs_dev_is_sequential(sctx->wr_tgtdev, physical)) + return 0; + + if (sctx->write_pointer < physical) { + length = physical - sctx->write_pointer; + + ret = btrfs_zoned_issue_zeroout(sctx->wr_tgtdev, + sctx->write_pointer, length); + if (!ret) + sctx->write_pointer = physical; + } + return ret; +} + static int scrub_add_page_to_wr_bio(struct scrub_ctx *sctx, struct scrub_page *spage) { @@ -1644,6 +1667,13 @@ again: if (sbio->page_count == 0) { struct bio *bio; + ret = fill_writer_pointer_gap(sctx, + spage->physical_for_dev_replace); + if (ret) { + mutex_unlock(&sctx->wr_lock); + return ret; + } + sbio->physical = spage->physical_for_dev_replace; sbio->logical = spage->logical; sbio->dev = sctx->wr_tgtdev; @@ -1698,13 +1728,16 @@ static void scrub_wr_submit(struct scrub_ctx *sctx) sbio = sctx->wr_curr_bio; sctx->wr_curr_bio = NULL; - WARN_ON(!sbio->bio->bi_disk); + WARN_ON(!sbio->bio->bi_bdev); scrub_pending_bio_inc(sctx); /* process all writes in a single worker thread. Then the block layer * orders the requests before sending them to the driver which * doubled the write performance on spinning disks when measured * with Linux 3.5 */ btrfsic_submit_bio(sbio->bio); + + if (btrfs_is_zoned(sctx->fs_info)) + sctx->write_pointer = sbio->physical + sbio->page_count * PAGE_SIZE; } static void scrub_wr_bio_end_io(struct bio *bio) @@ -1798,11 +1831,15 @@ static int scrub_checksum_data(struct scrub_block *sblock) shash->tfm = fs_info->csum_shash; crypto_shash_init(shash); - crypto_shash_digest(shash, kaddr, PAGE_SIZE, csum); - if (memcmp(csum, spage->csum, sctx->csum_size)) - sblock->checksum_error = 1; + /* + * In scrub_pages() and scrub_pages_for_parity() we ensure each spage + * only contains one sector of data. + */ + crypto_shash_digest(shash, kaddr, fs_info->sectorsize, csum); + if (memcmp(csum, spage->csum, fs_info->csum_size)) + sblock->checksum_error = 1; return sblock->checksum_error; } @@ -1814,16 +1851,26 @@ static int scrub_checksum_tree_block(struct scrub_block *sblock) SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); u8 calculated_csum[BTRFS_CSUM_SIZE]; u8 on_disk_csum[BTRFS_CSUM_SIZE]; - const int num_pages = sctx->fs_info->nodesize >> PAGE_SHIFT; + /* + * This is done in sectorsize steps even for metadata as there's a + * constraint for nodesize to be aligned to sectorsize. This will need + * to change so we don't misuse data and metadata units like that. + */ + const u32 sectorsize = sctx->fs_info->sectorsize; + const int num_sectors = fs_info->nodesize >> fs_info->sectorsize_bits; int i; struct scrub_page *spage; char *kaddr; BUG_ON(sblock->page_count < 1); + + /* Each member in pagev is just one block, not a full page */ + ASSERT(sblock->page_count == num_sectors); + spage = sblock->pagev[0]; kaddr = page_address(spage->page); h = (struct btrfs_header *)kaddr; - memcpy(on_disk_csum, h->csum, sctx->csum_size); + memcpy(on_disk_csum, h->csum, sctx->fs_info->csum_size); /* * we don't use the getter functions here, as we @@ -1848,15 +1895,15 @@ static int scrub_checksum_tree_block(struct scrub_block *sblock) shash->tfm = fs_info->csum_shash; crypto_shash_init(shash); crypto_shash_update(shash, kaddr + BTRFS_CSUM_SIZE, - PAGE_SIZE - BTRFS_CSUM_SIZE); + sectorsize - BTRFS_CSUM_SIZE); - for (i = 1; i < num_pages; i++) { + for (i = 1; i < num_sectors; i++) { kaddr = page_address(sblock->pagev[i]->page); - crypto_shash_update(shash, kaddr, PAGE_SIZE); + crypto_shash_update(shash, kaddr, sectorsize); } crypto_shash_final(shash, calculated_csum); - if (memcmp(calculated_csum, on_disk_csum, sctx->csum_size)) + if (memcmp(calculated_csum, on_disk_csum, sctx->fs_info->csum_size)) sblock->checksum_error = 1; return sblock->header_error || sblock->checksum_error; @@ -1893,7 +1940,7 @@ static int scrub_checksum_super(struct scrub_block *sblock) crypto_shash_digest(shash, kaddr + BTRFS_CSUM_SIZE, BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE, calculated_csum); - if (memcmp(calculated_csum, s->csum, sctx->csum_size)) + if (memcmp(calculated_csum, s->csum, sctx->fs_info->csum_size)) ++fail_cor; if (fail_cor + fail_gen) { @@ -2150,12 +2197,13 @@ bbio_out: spin_unlock(&sctx->stat_lock); } -static int scrub_pages(struct scrub_ctx *sctx, u64 logical, u64 len, +static int scrub_pages(struct scrub_ctx *sctx, u64 logical, u32 len, u64 physical, struct btrfs_device *dev, u64 flags, - u64 gen, int mirror_num, u8 *csum, int force, + u64 gen, int mirror_num, u8 *csum, u64 physical_for_dev_replace) { struct scrub_block *sblock; + const u32 sectorsize = sctx->fs_info->sectorsize; int index; sblock = kzalloc(sizeof(*sblock), GFP_KERNEL); @@ -2174,7 +2222,12 @@ static int scrub_pages(struct scrub_ctx *sctx, u64 logical, u64 len, for (index = 0; len > 0; index++) { struct scrub_page *spage; - u64 l = min_t(u64, len, PAGE_SIZE); + /* + * Here we will allocate one page for one sector to scrub. + * This is fine if PAGE_SIZE == sectorsize, but will cost + * more memory for PAGE_SIZE > sectorsize case. + */ + u32 l = min(sectorsize, len); spage = kzalloc(sizeof(*spage), GFP_KERNEL); if (!spage) { @@ -2198,7 +2251,7 @@ leave_nomem: spage->mirror_num = mirror_num; if (csum) { spage->have_csum = 1; - memcpy(spage->csum, csum, sctx->csum_size); + memcpy(spage->csum, csum, sctx->fs_info->csum_size); } else { spage->have_csum = 0; } @@ -2231,7 +2284,7 @@ leave_nomem: } } - if (force) + if (flags & BTRFS_EXTENT_FLAG_SUPER) scrub_submit(sctx); } @@ -2295,12 +2348,11 @@ static void scrub_bio_end_io_worker(struct btrfs_work *work) static inline void __scrub_mark_bitmap(struct scrub_parity *sparity, unsigned long *bitmap, - u64 start, u64 len) + u64 start, u32 len) { u64 offset; - u64 nsectors64; u32 nsectors; - int sectorsize = sparity->sctx->fs_info->sectorsize; + u32 sectorsize_bits = sparity->sctx->fs_info->sectorsize_bits; if (len >= sparity->stripe_len) { bitmap_set(bitmap, 0, sparity->nsectors); @@ -2309,11 +2361,8 @@ static inline void __scrub_mark_bitmap(struct scrub_parity *sparity, start -= sparity->logic_start; start = div64_u64_rem(start, sparity->stripe_len, &offset); - offset = div_u64(offset, sectorsize); - nsectors64 = div_u64(len, sectorsize); - - ASSERT(nsectors64 < UINT_MAX); - nsectors = (u32)nsectors64; + offset = offset >> sectorsize_bits; + nsectors = len >> sectorsize_bits; if (offset + nsectors <= sparity->nsectors) { bitmap_set(bitmap, offset, nsectors); @@ -2325,13 +2374,13 @@ static inline void __scrub_mark_bitmap(struct scrub_parity *sparity, } static inline void scrub_parity_mark_sectors_error(struct scrub_parity *sparity, - u64 start, u64 len) + u64 start, u32 len) { __scrub_mark_bitmap(sparity, sparity->ebitmap, start, len); } static inline void scrub_parity_mark_sectors_data(struct scrub_parity *sparity, - u64 start, u64 len) + u64 start, u32 len) { __scrub_mark_bitmap(sparity, sparity->dbitmap, start, len); } @@ -2359,48 +2408,77 @@ static void scrub_block_complete(struct scrub_block *sblock) u64 end = sblock->pagev[sblock->page_count - 1]->logical + PAGE_SIZE; + ASSERT(end - start <= U32_MAX); scrub_parity_mark_sectors_error(sblock->sparity, start, end - start); } } +static void drop_csum_range(struct scrub_ctx *sctx, struct btrfs_ordered_sum *sum) +{ + sctx->stat.csum_discards += sum->len >> sctx->fs_info->sectorsize_bits; + list_del(&sum->list); + kfree(sum); +} + +/* + * Find the desired csum for range [logical, logical + sectorsize), and store + * the csum into @csum. + * + * The search source is sctx->csum_list, which is a pre-populated list + * storing bytenr ordered csum ranges. We're reponsible to cleanup any range + * that is before @logical. + * + * Return 0 if there is no csum for the range. + * Return 1 if there is csum for the range and copied to @csum. + */ static int scrub_find_csum(struct scrub_ctx *sctx, u64 logical, u8 *csum) { - struct btrfs_ordered_sum *sum = NULL; - unsigned long index; - unsigned long num_sectors; + bool found = false; while (!list_empty(&sctx->csum_list)) { + struct btrfs_ordered_sum *sum = NULL; + unsigned long index; + unsigned long num_sectors; + sum = list_first_entry(&sctx->csum_list, struct btrfs_ordered_sum, list); + /* The current csum range is beyond our range, no csum found */ if (sum->bytenr > logical) - return 0; - if (sum->bytenr + sum->len > logical) break; - ++sctx->stat.csum_discards; - list_del(&sum->list); - kfree(sum); - sum = NULL; - } - if (!sum) - return 0; + /* + * The current sum is before our bytenr, since scrub is always + * done in bytenr order, the csum will never be used anymore, + * clean it up so that later calls won't bother with the range, + * and continue search the next range. + */ + if (sum->bytenr + sum->len <= logical) { + drop_csum_range(sctx, sum); + continue; + } - index = div_u64(logical - sum->bytenr, sctx->fs_info->sectorsize); - ASSERT(index < UINT_MAX); + /* Now the csum range covers our bytenr, copy the csum */ + found = true; + index = (logical - sum->bytenr) >> sctx->fs_info->sectorsize_bits; + num_sectors = sum->len >> sctx->fs_info->sectorsize_bits; - num_sectors = sum->len / sctx->fs_info->sectorsize; - memcpy(csum, sum->sums + index * sctx->csum_size, sctx->csum_size); - if (index == num_sectors - 1) { - list_del(&sum->list); - kfree(sum); + memcpy(csum, sum->sums + index * sctx->fs_info->csum_size, + sctx->fs_info->csum_size); + + /* Cleanup the range if we're at the end of the csum range */ + if (index == num_sectors - 1) + drop_csum_range(sctx, sum); + break; } + if (!found) + return 0; return 1; } /* scrub extent tries to collect up to 64 kB for each bio */ static int scrub_extent(struct scrub_ctx *sctx, struct map_lookup *map, - u64 logical, u64 len, + u64 logical, u32 len, u64 physical, struct btrfs_device *dev, u64 flags, u64 gen, int mirror_num, u64 physical_for_dev_replace) { @@ -2432,7 +2510,7 @@ static int scrub_extent(struct scrub_ctx *sctx, struct map_lookup *map, } while (len) { - u64 l = min_t(u64, len, blocksize); + u32 l = min(len, blocksize); int have_csum = 0; if (flags & BTRFS_EXTENT_FLAG_DATA) { @@ -2442,7 +2520,7 @@ static int scrub_extent(struct scrub_ctx *sctx, struct map_lookup *map, ++sctx->stat.no_csum; } ret = scrub_pages(sctx, logical, l, physical, dev, flags, gen, - mirror_num, have_csum ? csum : NULL, 0, + mirror_num, have_csum ? csum : NULL, physical_for_dev_replace); if (ret) return ret; @@ -2455,14 +2533,17 @@ static int scrub_extent(struct scrub_ctx *sctx, struct map_lookup *map, } static int scrub_pages_for_parity(struct scrub_parity *sparity, - u64 logical, u64 len, + u64 logical, u32 len, u64 physical, struct btrfs_device *dev, u64 flags, u64 gen, int mirror_num, u8 *csum) { struct scrub_ctx *sctx = sparity->sctx; struct scrub_block *sblock; + const u32 sectorsize = sctx->fs_info->sectorsize; int index; + ASSERT(IS_ALIGNED(len, sectorsize)); + sblock = kzalloc(sizeof(*sblock), GFP_KERNEL); if (!sblock) { spin_lock(&sctx->stat_lock); @@ -2481,7 +2562,6 @@ static int scrub_pages_for_parity(struct scrub_parity *sparity, for (index = 0; len > 0; index++) { struct scrub_page *spage; - u64 l = min_t(u64, len, PAGE_SIZE); spage = kzalloc(sizeof(*spage), GFP_KERNEL); if (!spage) { @@ -2508,7 +2588,7 @@ leave_nomem: spage->mirror_num = mirror_num; if (csum) { spage->have_csum = 1; - memcpy(spage->csum, csum, sctx->csum_size); + memcpy(spage->csum, csum, sctx->fs_info->csum_size); } else { spage->have_csum = 0; } @@ -2516,9 +2596,12 @@ leave_nomem: spage->page = alloc_page(GFP_KERNEL); if (!spage->page) goto leave_nomem; - len -= l; - logical += l; - physical += l; + + + /* Iterate over the stripe range in sectorsize steps */ + len -= sectorsize; + logical += sectorsize; + physical += sectorsize; } WARN_ON(sblock->page_count == 0); @@ -2539,7 +2622,7 @@ leave_nomem: } static int scrub_extent_for_parity(struct scrub_parity *sparity, - u64 logical, u64 len, + u64 logical, u32 len, u64 physical, struct btrfs_device *dev, u64 flags, u64 gen, int mirror_num) { @@ -2563,7 +2646,7 @@ static int scrub_extent_for_parity(struct scrub_parity *sparity, } while (len) { - u64 l = min_t(u64, len, blocksize); + u32 l = min(len, blocksize); int have_csum = 0; if (flags & BTRFS_EXTENT_FLAG_DATA) { @@ -2767,7 +2850,8 @@ static noinline_for_stack int scrub_raid56_parity(struct scrub_ctx *sctx, u64 generation; u64 extent_logical; u64 extent_physical; - u64 extent_len; + /* Check the comment in scrub_stripe() for why u32 is enough here */ + u32 extent_len; u64 mapped_length; struct btrfs_device *extent_dev; struct scrub_parity *sparity; @@ -2776,7 +2860,8 @@ static noinline_for_stack int scrub_raid56_parity(struct scrub_ctx *sctx, int extent_mirror_num; int stop_loop = 0; - nsectors = div_u64(map->stripe_len, fs_info->sectorsize); + ASSERT(map->stripe_len <= U32_MAX); + nsectors = map->stripe_len >> fs_info->sectorsize_bits; bitmap_len = scrub_calc_parity_bitmap_len(nsectors); sparity = kzalloc(sizeof(struct scrub_parity) + 2 * bitmap_len, GFP_NOFS); @@ -2787,6 +2872,7 @@ static noinline_for_stack int scrub_raid56_parity(struct scrub_ctx *sctx, return -ENOMEM; } + ASSERT(map->stripe_len <= U32_MAX); sparity->stripe_len = map->stripe_len; sparity->nsectors = nsectors; sparity->sctx = sctx; @@ -2881,6 +2967,7 @@ static noinline_for_stack int scrub_raid56_parity(struct scrub_ctx *sctx, } again: extent_logical = key.objectid; + ASSERT(bytes <= U32_MAX); extent_len = bytes; if (extent_logical < logic_start) { @@ -2959,9 +3046,11 @@ next: logic_start += map->stripe_len; } out: - if (ret < 0) + if (ret < 0) { + ASSERT(logic_end - logic_start <= U32_MAX); scrub_parity_mark_sectors_error(sparity, logic_start, logic_end - logic_start); + } scrub_parity_put(sparity); scrub_submit(sctx); mutex_lock(&sctx->wr_lock); @@ -2972,6 +3061,46 @@ out: return ret < 0 ? ret : 0; } +static void sync_replace_for_zoned(struct scrub_ctx *sctx) +{ + if (!btrfs_is_zoned(sctx->fs_info)) + return; + + sctx->flush_all_writes = true; + scrub_submit(sctx); + mutex_lock(&sctx->wr_lock); + scrub_wr_submit(sctx); + mutex_unlock(&sctx->wr_lock); + + wait_event(sctx->list_wait, atomic_read(&sctx->bios_in_flight) == 0); +} + +static int sync_write_pointer_for_zoned(struct scrub_ctx *sctx, u64 logical, + u64 physical, u64 physical_end) +{ + struct btrfs_fs_info *fs_info = sctx->fs_info; + int ret = 0; + + if (!btrfs_is_zoned(fs_info)) + return 0; + + wait_event(sctx->list_wait, atomic_read(&sctx->bios_in_flight) == 0); + + mutex_lock(&sctx->wr_lock); + if (sctx->write_pointer < physical_end) { + ret = btrfs_sync_zone_write_pointer(sctx->wr_tgtdev, logical, + physical, + sctx->write_pointer); + if (ret) + btrfs_err(fs_info, + "zoned: failed to recover write pointer"); + } + mutex_unlock(&sctx->wr_lock); + btrfs_dev_clear_zone_empty(sctx->wr_tgtdev, physical); + + return ret; +} + static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, struct map_lookup *map, struct btrfs_device *scrub_dev, @@ -3003,7 +3132,11 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, u64 offset; u64 extent_logical; u64 extent_physical; - u64 extent_len; + /* + * Unlike chunk length, extent length should never go beyond + * BTRFS_MAX_EXTENT_SIZE, thus u32 is enough here. + */ + u32 extent_len; u64 stripe_logical; u64 stripe_end; struct btrfs_device *extent_dev; @@ -3084,17 +3217,21 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, key_end.offset = (u64)-1; reada1 = btrfs_reada_add(root, &key, &key_end); - key.objectid = BTRFS_EXTENT_CSUM_OBJECTID; - key.type = BTRFS_EXTENT_CSUM_KEY; - key.offset = logical; - key_end.objectid = BTRFS_EXTENT_CSUM_OBJECTID; - key_end.type = BTRFS_EXTENT_CSUM_KEY; - key_end.offset = logic_end; - reada2 = btrfs_reada_add(csum_root, &key, &key_end); + if (cache->flags & BTRFS_BLOCK_GROUP_DATA) { + key.objectid = BTRFS_EXTENT_CSUM_OBJECTID; + key.type = BTRFS_EXTENT_CSUM_KEY; + key.offset = logical; + key_end.objectid = BTRFS_EXTENT_CSUM_OBJECTID; + key_end.type = BTRFS_EXTENT_CSUM_KEY; + key_end.offset = logic_end; + reada2 = btrfs_reada_add(csum_root, &key, &key_end); + } else { + reada2 = NULL; + } if (!IS_ERR(reada1)) btrfs_reada_wait(reada1); - if (!IS_ERR(reada2)) + if (!IS_ERR_OR_NULL(reada2)) btrfs_reada_wait(reada2); @@ -3104,6 +3241,14 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, */ blk_start_plug(&plug); + if (sctx->is_dev_replace && + btrfs_dev_is_sequential(sctx->wr_tgtdev, physical)) { + mutex_lock(&sctx->wr_lock); + sctx->write_pointer = physical; + mutex_unlock(&sctx->wr_lock); + sctx->flush_all_writes = true; + } + /* * now find all extents for each stripe and scrub them */ @@ -3248,6 +3393,7 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, again: extent_logical = key.objectid; + ASSERT(bytes <= U32_MAX); extent_len = bytes; /* @@ -3291,6 +3437,9 @@ again: if (ret) goto out; + if (sctx->is_dev_replace) + sync_replace_for_zoned(sctx); + if (extent_logical + extent_len < key.objectid + bytes) { if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) { @@ -3358,6 +3507,17 @@ out: blk_finish_plug(&plug); btrfs_free_path(path); btrfs_free_path(ppath); + + if (sctx->is_dev_replace && ret >= 0) { + int ret2; + + ret2 = sync_write_pointer_for_zoned(sctx, base + offset, + map->stripes[num].physical, + physical_end); + if (ret2) + ret = ret2; + } + return ret < 0 ? ret : 0; } @@ -3413,6 +3573,25 @@ out: return ret; } +static int finish_extent_writes_for_zoned(struct btrfs_root *root, + struct btrfs_block_group *cache) +{ + struct btrfs_fs_info *fs_info = cache->fs_info; + struct btrfs_trans_handle *trans; + + if (!btrfs_is_zoned(fs_info)) + return 0; + + btrfs_wait_block_group_reservations(cache); + btrfs_wait_nocow_writers(cache); + btrfs_wait_ordered_roots(fs_info, U64_MAX, cache->start, cache->length); + + trans = btrfs_join_transaction(root); + if (IS_ERR(trans)) + return PTR_ERR(trans); + return btrfs_commit_transaction(trans); +} + static noinline_for_stack int scrub_enumerate_chunks(struct scrub_ctx *sctx, struct btrfs_device *scrub_dev, u64 start, u64 end) @@ -3499,6 +3678,16 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, if (!cache) goto skip; + if (sctx->is_dev_replace && btrfs_is_zoned(fs_info)) { + spin_lock(&cache->lock); + if (!cache->to_copy) { + spin_unlock(&cache->lock); + ro_set = 0; + goto done; + } + spin_unlock(&cache->lock); + } + /* * Make sure that while we are scrubbing the corresponding block * group doesn't get its logical address and its device extents @@ -3557,6 +3746,16 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, * group is not RO. */ ret = btrfs_inc_block_group_ro(cache, sctx->is_dev_replace); + if (!ret && sctx->is_dev_replace) { + ret = finish_extent_writes_for_zoned(root, cache); + if (ret) { + btrfs_dec_block_group_ro(cache); + scrub_pause_off(fs_info); + btrfs_put_block_group(cache); + break; + } + } + if (ret == 0) { ro_set = 1; } else if (ret == -ENOSPC && !sctx->is_dev_replace) { @@ -3630,6 +3829,12 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, scrub_pause_off(fs_info); + if (sctx->is_dev_replace && + !btrfs_finish_block_group_to_copy(dev_replace->srcdev, + cache, found_key.offset)) + ro_set = 0; + +done: down_write(&dev_replace->rwsem); dev_replace->cursor_left = dev_replace->cursor_right; dev_replace->item_needs_writeback = 1; @@ -3704,10 +3909,12 @@ static noinline_for_stack int scrub_supers(struct scrub_ctx *sctx, if (bytenr + BTRFS_SUPER_INFO_SIZE > scrub_dev->commit_total_bytes) break; + if (!btrfs_check_super_location(scrub_dev, bytenr)) + continue; ret = scrub_pages(sctx, bytenr, BTRFS_SUPER_INFO_SIZE, bytenr, scrub_dev, BTRFS_EXTENT_FLAG_SUPER, gen, i, - NULL, 1, bytenr); + NULL, bytenr); if (ret) return ret; } @@ -3821,14 +4028,6 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, return -EINVAL; } - if (fs_info->sectorsize != PAGE_SIZE) { - /* not supported for data w/o checksums */ - btrfs_err_rl(fs_info, - "scrub: size assumption sectorsize != PAGE_SIZE (%d != %lu) fails", - fs_info->sectorsize, PAGE_SIZE); - return -EINVAL; - } - if (fs_info->nodesize > PAGE_SIZE * SCRUB_MAX_PAGES_PER_BLOCK || fs_info->sectorsize > PAGE_SIZE * SCRUB_MAX_PAGES_PER_BLOCK) { @@ -3855,7 +4054,7 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, goto out_free_ctx; mutex_lock(&fs_info->fs_devices->device_list_mutex); - dev = btrfs_find_device(fs_info->fs_devices, devid, NULL, NULL, true); + dev = btrfs_find_device(fs_info->fs_devices, devid, NULL, NULL); if (!dev || (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state) && !is_dev_replace)) { mutex_unlock(&fs_info->fs_devices->device_list_mutex); @@ -3866,8 +4065,9 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, if (!is_dev_replace && !readonly && !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) { mutex_unlock(&fs_info->fs_devices->device_list_mutex); - btrfs_err_in_rcu(fs_info, "scrub: device %s is not writable", - rcu_str_deref(dev->name)); + btrfs_err_in_rcu(fs_info, + "scrub on devid %llu: filesystem on %s is not writable", + devid, rcu_str_deref(dev->name)); ret = -EROFS; goto out; } @@ -4031,7 +4231,7 @@ int btrfs_scrub_progress(struct btrfs_fs_info *fs_info, u64 devid, struct scrub_ctx *sctx = NULL; mutex_lock(&fs_info->fs_devices->device_list_mutex); - dev = btrfs_find_device(fs_info->fs_devices, devid, NULL, NULL, true); + dev = btrfs_find_device(fs_info->fs_devices, devid, NULL, NULL); if (dev) sctx = dev->scrub_ctx; if (sctx) @@ -4042,7 +4242,7 @@ int btrfs_scrub_progress(struct btrfs_fs_info *fs_info, u64 devid, } static void scrub_remap_extent(struct btrfs_fs_info *fs_info, - u64 extent_logical, u64 extent_len, + u64 extent_logical, u32 extent_len, u64 *extent_physical, struct btrfs_device **extent_dev, int *extent_mirror_num) diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 340c76a12ce1..f87878274e9f 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -236,6 +236,7 @@ struct waiting_dir_move { * after this directory is moved, we can try to rmdir the ino rmdir_ino. */ u64 rmdir_ino; + u64 rmdir_gen; bool orphanized; }; @@ -316,7 +317,7 @@ static int is_waiting_for_move(struct send_ctx *sctx, u64 ino); static struct waiting_dir_move * get_waiting_dir_move(struct send_ctx *sctx, u64 ino); -static int is_waiting_for_rm(struct send_ctx *sctx, u64 dir_ino); +static int is_waiting_for_rm(struct send_ctx *sctx, u64 dir_ino, u64 gen); static int need_send_hole(struct send_ctx *sctx) { @@ -1190,9 +1191,6 @@ struct backref_ctx { /* may be truncated in case it's the last extent in a file */ u64 extent_len; - /* data offset in the file extent item */ - u64 data_offset; - /* Just to check for bugs in backref resolving */ int found_itself; }; @@ -1400,19 +1398,6 @@ static int find_extent_clone(struct send_ctx *sctx, backref_ctx->cur_offset = data_offset; backref_ctx->found_itself = 0; backref_ctx->extent_len = num_bytes; - /* - * For non-compressed extents iterate_extent_inodes() gives us extent - * offsets that already take into account the data offset, but not for - * compressed extents, since the offset is logical and not relative to - * the physical extent locations. We must take this into account to - * avoid sending clone offsets that go beyond the source file's size, - * which would result in the clone ioctl failing with -EINVAL on the - * receiving end. - */ - if (compressed == BTRFS_COMPRESS_NONE) - backref_ctx->data_offset = 0; - else - backref_ctx->data_offset = btrfs_file_extent_offset(eb, fi); /* * The last extent of a file may be too large due to page alignment. @@ -2299,7 +2284,7 @@ static int get_cur_path(struct send_ctx *sctx, u64 ino, u64 gen, fs_path_reset(name); - if (is_waiting_for_rm(sctx, ino)) { + if (is_waiting_for_rm(sctx, ino, gen)) { ret = gen_unique_name(sctx, ino, gen, name); if (ret < 0) goto out; @@ -2410,7 +2395,7 @@ static int send_subvol_begin(struct send_ctx *sctx) sctx->send_root->root_item.uuid); TLV_PUT_U64(sctx, BTRFS_SEND_A_CTRANSID, - le64_to_cpu(sctx->send_root->root_item.ctransid)); + btrfs_root_ctransid(&sctx->send_root->root_item)); if (parent_root) { if (!btrfs_is_empty_uuid(parent_root->root_item.received_uuid)) TLV_PUT_UUID(sctx, BTRFS_SEND_A_CLONE_UUID, @@ -2419,7 +2404,7 @@ static int send_subvol_begin(struct send_ctx *sctx) TLV_PUT_UUID(sctx, BTRFS_SEND_A_CLONE_UUID, parent_root->root_item.uuid); TLV_PUT_U64(sctx, BTRFS_SEND_A_CLONE_CTRANSID, - le64_to_cpu(sctx->parent_root->root_item.ctransid)); + btrfs_root_ctransid(&sctx->parent_root->root_item)); } ret = send_cmd(sctx); @@ -2858,8 +2843,8 @@ out: return ret; } -static struct orphan_dir_info * -add_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino) +static struct orphan_dir_info *add_orphan_dir_info(struct send_ctx *sctx, + u64 dir_ino, u64 dir_gen) { struct rb_node **p = &sctx->orphan_dirs.rb_node; struct rb_node *parent = NULL; @@ -2868,20 +2853,23 @@ add_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino) while (*p) { parent = *p; entry = rb_entry(parent, struct orphan_dir_info, node); - if (dir_ino < entry->ino) { + if (dir_ino < entry->ino) p = &(*p)->rb_left; - } else if (dir_ino > entry->ino) { + else if (dir_ino > entry->ino) p = &(*p)->rb_right; - } else { + else if (dir_gen < entry->gen) + p = &(*p)->rb_left; + else if (dir_gen > entry->gen) + p = &(*p)->rb_right; + else return entry; - } } odi = kmalloc(sizeof(*odi), GFP_KERNEL); if (!odi) return ERR_PTR(-ENOMEM); odi->ino = dir_ino; - odi->gen = 0; + odi->gen = dir_gen; odi->last_dir_index_offset = 0; rb_link_node(&odi->node, parent, p); @@ -2889,8 +2877,8 @@ add_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino) return odi; } -static struct orphan_dir_info * -get_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino) +static struct orphan_dir_info *get_orphan_dir_info(struct send_ctx *sctx, + u64 dir_ino, u64 gen) { struct rb_node *n = sctx->orphan_dirs.rb_node; struct orphan_dir_info *entry; @@ -2901,15 +2889,19 @@ get_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino) n = n->rb_left; else if (dir_ino > entry->ino) n = n->rb_right; + else if (gen < entry->gen) + n = n->rb_left; + else if (gen > entry->gen) + n = n->rb_right; else return entry; } return NULL; } -static int is_waiting_for_rm(struct send_ctx *sctx, u64 dir_ino) +static int is_waiting_for_rm(struct send_ctx *sctx, u64 dir_ino, u64 gen) { - struct orphan_dir_info *odi = get_orphan_dir_info(sctx, dir_ino); + struct orphan_dir_info *odi = get_orphan_dir_info(sctx, dir_ino, gen); return odi != NULL; } @@ -2954,7 +2946,7 @@ static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen, key.type = BTRFS_DIR_INDEX_KEY; key.offset = 0; - odi = get_orphan_dir_info(sctx, dir); + odi = get_orphan_dir_info(sctx, dir, dir_gen); if (odi) key.offset = odi->last_dir_index_offset; @@ -2985,7 +2977,7 @@ static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen, dm = get_waiting_dir_move(sctx, loc.objectid); if (dm) { - odi = add_orphan_dir_info(sctx, dir); + odi = add_orphan_dir_info(sctx, dir, dir_gen); if (IS_ERR(odi)) { ret = PTR_ERR(odi); goto out; @@ -2993,12 +2985,13 @@ static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen, odi->gen = dir_gen; odi->last_dir_index_offset = found_key.offset; dm->rmdir_ino = dir; + dm->rmdir_gen = dir_gen; ret = 0; goto out; } if (loc.objectid > send_progress) { - odi = add_orphan_dir_info(sctx, dir); + odi = add_orphan_dir_info(sctx, dir, dir_gen); if (IS_ERR(odi)) { ret = PTR_ERR(odi); goto out; @@ -3038,6 +3031,7 @@ static int add_waiting_dir_move(struct send_ctx *sctx, u64 ino, bool orphanized) return -ENOMEM; dm->ino = ino; dm->rmdir_ino = 0; + dm->rmdir_gen = 0; dm->orphanized = orphanized; while (*p) { @@ -3183,7 +3177,7 @@ static int path_loop(struct send_ctx *sctx, struct fs_path *name, while (ino != BTRFS_FIRST_FREE_OBJECTID) { fs_path_reset(name); - if (is_waiting_for_rm(sctx, ino)) + if (is_waiting_for_rm(sctx, ino, gen)) break; if (is_waiting_for_move(sctx, ino)) { if (*ancestor_ino == 0) @@ -3223,6 +3217,7 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm) u64 parent_ino, parent_gen; struct waiting_dir_move *dm = NULL; u64 rmdir_ino = 0; + u64 rmdir_gen; u64 ancestor; bool is_orphan; int ret; @@ -3237,6 +3232,7 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm) dm = get_waiting_dir_move(sctx, pm->ino); ASSERT(dm); rmdir_ino = dm->rmdir_ino; + rmdir_gen = dm->rmdir_gen; is_orphan = dm->orphanized; free_waiting_dir_move(sctx, dm); @@ -3273,6 +3269,7 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm) dm = get_waiting_dir_move(sctx, pm->ino); ASSERT(dm); dm->rmdir_ino = rmdir_ino; + dm->rmdir_gen = rmdir_gen; } goto out; } @@ -3291,7 +3288,7 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm) struct orphan_dir_info *odi; u64 gen; - odi = get_orphan_dir_info(sctx, rmdir_ino); + odi = get_orphan_dir_info(sctx, rmdir_ino, rmdir_gen); if (!odi) { /* already deleted */ goto finish; @@ -5101,7 +5098,7 @@ static int send_clone(struct send_ctx *sctx, TLV_PUT_UUID(sctx, BTRFS_SEND_A_CLONE_UUID, clone_root->root->root_item.uuid); TLV_PUT_U64(sctx, BTRFS_SEND_A_CLONE_CTRANSID, - le64_to_cpu(clone_root->root->root_item.ctransid)); + btrfs_root_ctransid(&clone_root->root->root_item)); TLV_PUT_PATH(sctx, BTRFS_SEND_A_CLONE_PATH, p); TLV_PUT_U64(sctx, BTRFS_SEND_A_CLONE_OFFSET, clone_root->offset); @@ -5499,6 +5496,21 @@ static int clone_range(struct send_ctx *sctx, break; offset += clone_len; clone_root->offset += clone_len; + + /* + * If we are cloning from the file we are currently processing, + * and using the send root as the clone root, we must stop once + * the current clone offset reaches the current eof of the file + * at the receiver, otherwise we would issue an invalid clone + * operation (source range going beyond eof) and cause the + * receiver to fail. So if we reach the current eof, bail out + * and fallback to a regular write. + */ + if (clone_root->root == sctx->send_root && + clone_root->ino == sctx->cur_ino && + clone_root->offset >= sctx->cur_inode_next_write_offset) + break; + data_offset += clone_len; next: path->slots[0]++; @@ -6579,10 +6591,9 @@ static int changed_cb(struct btrfs_path *left_path, struct btrfs_path *right_path, struct btrfs_key *key, enum btrfs_compare_tree_result result, - void *ctx) + struct send_ctx *sctx) { int ret = 0; - struct send_ctx *sctx = ctx; if (result == BTRFS_COMPARE_TREE_SAME) { if (key->type == BTRFS_INODE_REF_KEY || @@ -6787,7 +6798,7 @@ static int tree_compare_item(struct btrfs_path *left_path, * If it detects a change, it aborts immediately. */ static int btrfs_compare_trees(struct btrfs_root *left_root, - struct btrfs_root *right_root, void *ctx) + struct btrfs_root *right_root, struct send_ctx *sctx) { struct btrfs_fs_info *fs_info = left_root->fs_info; int ret; @@ -6939,7 +6950,7 @@ static int btrfs_compare_trees(struct btrfs_root *left_root, ret = changed_cb(left_path, right_path, &right_key, BTRFS_COMPARE_TREE_DELETED, - ctx); + sctx); if (ret < 0) goto out; } @@ -6950,7 +6961,7 @@ static int btrfs_compare_trees(struct btrfs_root *left_root, ret = changed_cb(left_path, right_path, &left_key, BTRFS_COMPARE_TREE_NEW, - ctx); + sctx); if (ret < 0) goto out; } @@ -6964,7 +6975,7 @@ static int btrfs_compare_trees(struct btrfs_root *left_root, ret = changed_cb(left_path, right_path, &left_key, BTRFS_COMPARE_TREE_NEW, - ctx); + sctx); if (ret < 0) goto out; advance_left = ADVANCE; @@ -6972,7 +6983,7 @@ static int btrfs_compare_trees(struct btrfs_root *left_root, ret = changed_cb(left_path, right_path, &right_key, BTRFS_COMPARE_TREE_DELETED, - ctx); + sctx); if (ret < 0) goto out; advance_right = ADVANCE; @@ -6987,7 +6998,7 @@ static int btrfs_compare_trees(struct btrfs_root *left_root, else result = BTRFS_COMPARE_TREE_SAME; ret = changed_cb(left_path, right_path, - &left_key, result, ctx); + &left_key, result, sctx); if (ret < 0) goto out; advance_left = ADVANCE; diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index 64099565ab8f..2da6177f4b0b 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -140,6 +140,12 @@ * be freed, plus any delayed work we may not have gotten rid of in the case * of metadata. * + * FORCE_COMMIT_TRANS + * For use by the preemptive flusher. We use this to bypass the ticketing + * checks in may_commit_transaction, as we have more information about the + * overall state of the system and may want to commit the transaction ahead + * of actual ENOSPC conditions. + * * OVERCOMMIT * * Because we hold so many reservations for metadata we will allow you to @@ -163,6 +169,7 @@ u64 __pure btrfs_space_info_used(struct btrfs_space_info *s_info, ASSERT(s_info); return s_info->bytes_used + s_info->bytes_reserved + s_info->bytes_pinned + s_info->bytes_readonly + + s_info->bytes_zone_unusable + (may_use_included ? s_info->bytes_may_use : 0); } @@ -206,6 +213,7 @@ static int create_space_info(struct btrfs_fs_info *info, u64 flags) INIT_LIST_HEAD(&space_info->ro_bgs); INIT_LIST_HEAD(&space_info->tickets); INIT_LIST_HEAD(&space_info->priority_tickets); + space_info->clamp = 1; ret = btrfs_sysfs_add_space_info_type(info, space_info); if (ret) @@ -257,7 +265,7 @@ out: void btrfs_update_space_info(struct btrfs_fs_info *info, u64 flags, u64 total_bytes, u64 bytes_used, - u64 bytes_readonly, + u64 bytes_readonly, u64 bytes_zone_unusable, struct btrfs_space_info **space_info) { struct btrfs_space_info *found; @@ -273,6 +281,7 @@ void btrfs_update_space_info(struct btrfs_fs_info *info, u64 flags, found->bytes_used += bytes_used; found->disk_used += bytes_used * factor; found->bytes_readonly += bytes_readonly; + found->bytes_zone_unusable += bytes_zone_unusable; if (total_bytes > 0) found->full = 0; btrfs_try_granting_tickets(info, found); @@ -422,10 +431,10 @@ static void __btrfs_dump_space_info(struct btrfs_fs_info *fs_info, info->total_bytes - btrfs_space_info_used(info, true), info->full ? "" : "not "); btrfs_info(fs_info, - "space_info total=%llu, used=%llu, pinned=%llu, reserved=%llu, may_use=%llu, readonly=%llu", + "space_info total=%llu, used=%llu, pinned=%llu, reserved=%llu, may_use=%llu, readonly=%llu zone_unusable=%llu", info->total_bytes, info->bytes_used, info->bytes_pinned, info->bytes_reserved, info->bytes_may_use, - info->bytes_readonly); + info->bytes_readonly, info->bytes_zone_unusable); DUMP_BLOCK_RSV(fs_info, global_block_rsv); DUMP_BLOCK_RSV(fs_info, trans_block_rsv); @@ -454,9 +463,10 @@ again: list_for_each_entry(cache, &info->block_groups[index], list) { spin_lock(&cache->lock); btrfs_info(fs_info, - "block group %llu has %llu bytes, %llu used %llu pinned %llu reserved %s", + "block group %llu has %llu bytes, %llu used %llu pinned %llu reserved %llu zone_unusable %s", cache->start, cache->length, cache->used, cache->pinned, - cache->reserved, cache->ro ? "[readonly]" : ""); + cache->reserved, cache->zone_unusable, + cache->ro ? "[readonly]" : ""); spin_unlock(&cache->lock); btrfs_dump_free_space(cache, bytes); } @@ -489,7 +499,7 @@ static void shrink_delalloc(struct btrfs_fs_info *fs_info, { struct btrfs_trans_handle *trans; u64 delalloc_bytes; - u64 dio_bytes; + u64 ordered_bytes; u64 items; long time_left; int loops; @@ -513,26 +523,24 @@ static void shrink_delalloc(struct btrfs_fs_info *fs_info, delalloc_bytes = percpu_counter_sum_positive( &fs_info->delalloc_bytes); - dio_bytes = percpu_counter_sum_positive(&fs_info->dio_bytes); - if (delalloc_bytes == 0 && dio_bytes == 0) { - if (trans) - return; - if (wait_ordered) - btrfs_wait_ordered_roots(fs_info, items, 0, (u64)-1); + ordered_bytes = percpu_counter_sum_positive(&fs_info->ordered_bytes); + if (delalloc_bytes == 0 && ordered_bytes == 0) return; - } /* * If we are doing more ordered than delalloc we need to just wait on * ordered extents, otherwise we'll waste time trying to flush delalloc * that likely won't give us the space back we need. */ - if (dio_bytes > delalloc_bytes) + if (ordered_bytes > delalloc_bytes) wait_ordered = true; loops = 0; - while ((delalloc_bytes || dio_bytes) && loops < 3) { - btrfs_start_delalloc_roots(fs_info, items); + while ((delalloc_bytes || ordered_bytes) && loops < 3) { + u64 temp = min(delalloc_bytes, to_reclaim) >> PAGE_SHIFT; + long nr_pages = min_t(u64, temp, LONG_MAX); + + btrfs_start_delalloc_roots(fs_info, nr_pages, true); loops++; if (wait_ordered && !trans) { @@ -553,15 +561,16 @@ static void shrink_delalloc(struct btrfs_fs_info *fs_info, delalloc_bytes = percpu_counter_sum_positive( &fs_info->delalloc_bytes); - dio_bytes = percpu_counter_sum_positive(&fs_info->dio_bytes); + ordered_bytes = percpu_counter_sum_positive( + &fs_info->ordered_bytes); } } /** - * maybe_commit_transaction - possibly commit the transaction if its ok to - * @root - the root we're allocating for - * @bytes - the number of bytes we want to reserve - * @force - force the commit + * Possibly commit the transaction if its ok to + * + * @fs_info: the filesystem + * @space_info: space_info we are checking for commit, either data or metadata * * This will check to make sure that committing the transaction will actually * get us somewhere and then commit the transaction if it does. Otherwise it @@ -667,7 +676,7 @@ enospc: */ static void flush_space(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, u64 num_bytes, - int state) + enum btrfs_flush_state state, bool for_preempt) { struct btrfs_root *root = fs_info->extent_root; struct btrfs_trans_handle *trans; @@ -736,13 +745,21 @@ static void flush_space(struct btrfs_fs_info *fs_info, case COMMIT_TRANS: ret = may_commit_transaction(fs_info, space_info); break; + case FORCE_COMMIT_TRANS: + trans = btrfs_join_transaction(root); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); + break; + } + ret = btrfs_commit_transaction(trans); + break; default: ret = -ENOSPC; break; } trace_btrfs_flush_space(fs_info, space_info->flags, num_bytes, state, - ret); + ret, for_preempt); return; } @@ -752,7 +769,6 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info, { u64 used; u64 avail; - u64 expected; u64 to_reclaim = space_info->reclaim_size; lockdep_assert_held(&space_info->lock); @@ -770,43 +786,88 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info, if (space_info->total_bytes + avail < used) to_reclaim += used - (space_info->total_bytes + avail); - if (to_reclaim) - return to_reclaim; - - to_reclaim = min_t(u64, num_online_cpus() * SZ_1M, SZ_16M); - if (btrfs_can_overcommit(fs_info, space_info, to_reclaim, - BTRFS_RESERVE_FLUSH_ALL)) - return 0; - - used = btrfs_space_info_used(space_info, true); - - if (btrfs_can_overcommit(fs_info, space_info, SZ_1M, - BTRFS_RESERVE_FLUSH_ALL)) - expected = div_factor_fine(space_info->total_bytes, 95); - else - expected = div_factor_fine(space_info->total_bytes, 90); - - if (used > expected) - to_reclaim = used - expected; - else - to_reclaim = 0; - to_reclaim = min(to_reclaim, space_info->bytes_may_use + - space_info->bytes_reserved); return to_reclaim; } -static inline int need_do_async_reclaim(struct btrfs_fs_info *fs_info, - struct btrfs_space_info *space_info, - u64 used) +static bool need_preemptive_reclaim(struct btrfs_fs_info *fs_info, + struct btrfs_space_info *space_info) { + u64 ordered, delalloc; u64 thresh = div_factor_fine(space_info->total_bytes, 98); + u64 used; /* If we're just plain full then async reclaim just slows us down. */ if ((space_info->bytes_used + space_info->bytes_reserved) >= thresh) - return 0; + return false; - if (!btrfs_calc_reclaim_metadata_size(fs_info, space_info)) - return 0; + /* + * We have tickets queued, bail so we don't compete with the async + * flushers. + */ + if (space_info->reclaim_size) + return false; + + /* + * If we have over half of the free space occupied by reservations or + * pinned then we want to start flushing. + * + * We do not do the traditional thing here, which is to say + * + * if (used >= ((total_bytes + avail) / 2)) + * return 1; + * + * because this doesn't quite work how we want. If we had more than 50% + * of the space_info used by bytes_used and we had 0 available we'd just + * constantly run the background flusher. Instead we want it to kick in + * if our reclaimable space exceeds our clamped free space. + * + * Our clamping range is 2^1 -> 2^8. Practically speaking that means + * the following: + * + * Amount of RAM Minimum threshold Maximum threshold + * + * 256GiB 1GiB 128GiB + * 128GiB 512MiB 64GiB + * 64GiB 256MiB 32GiB + * 32GiB 128MiB 16GiB + * 16GiB 64MiB 8GiB + * + * These are the range our thresholds will fall in, corresponding to how + * much delalloc we need for the background flusher to kick in. + */ + + thresh = calc_available_free_space(fs_info, space_info, + BTRFS_RESERVE_FLUSH_ALL); + thresh += (space_info->total_bytes - space_info->bytes_used - + space_info->bytes_reserved - space_info->bytes_readonly); + thresh >>= space_info->clamp; + + used = space_info->bytes_pinned; + + /* + * If we have more ordered bytes than delalloc bytes then we're either + * doing a lot of DIO, or we simply don't have a lot of delalloc waiting + * around. Preemptive flushing is only useful in that it can free up + * space before tickets need to wait for things to finish. In the case + * of ordered extents, preemptively waiting on ordered extents gets us + * nothing, if our reservations are tied up in ordered extents we'll + * simply have to slow down writers by forcing them to wait on ordered + * extents. + * + * In the case that ordered is larger than delalloc, only include the + * block reserves that we would actually be able to directly reclaim + * from. In this case if we're heavy on metadata operations this will + * clearly be heavy enough to warrant preemptive flushing. In the case + * of heavy DIO or ordered reservations, preemptive flushing will just + * waste time and cause us to slow down. + */ + ordered = percpu_counter_sum_positive(&fs_info->ordered_bytes); + delalloc = percpu_counter_sum_positive(&fs_info->delalloc_bytes); + if (ordered >= delalloc) + used += fs_info->delayed_refs_rsv.reserved + + fs_info->delayed_block_rsv.reserved; + else + used += space_info->bytes_may_use; return (used >= thresh && !btrfs_fs_closing(fs_info) && !test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state)); @@ -920,7 +981,7 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work) struct btrfs_fs_info *fs_info; struct btrfs_space_info *space_info; u64 to_reclaim; - int flush_state; + enum btrfs_flush_state flush_state; int commit_cycles = 0; u64 last_tickets_id; @@ -939,7 +1000,7 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work) flush_state = FLUSH_DELAYED_ITEMS_NR; do { - flush_space(fs_info, space_info, to_reclaim, flush_state); + flush_space(fs_info, space_info, to_reclaim, flush_state, false); spin_lock(&space_info->lock); if (list_empty(&space_info->tickets)) { space_info->flush = 0; @@ -988,6 +1049,105 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work) } /* + * This handles pre-flushing of metadata space before we get to the point that + * we need to start blocking threads on tickets. The logic here is different + * from the other flush paths because it doesn't rely on tickets to tell us how + * much we need to flush, instead it attempts to keep us below the 80% full + * watermark of space by flushing whichever reservation pool is currently the + * largest. + */ +static void btrfs_preempt_reclaim_metadata_space(struct work_struct *work) +{ + struct btrfs_fs_info *fs_info; + struct btrfs_space_info *space_info; + struct btrfs_block_rsv *delayed_block_rsv; + struct btrfs_block_rsv *delayed_refs_rsv; + struct btrfs_block_rsv *global_rsv; + struct btrfs_block_rsv *trans_rsv; + int loops = 0; + + fs_info = container_of(work, struct btrfs_fs_info, + preempt_reclaim_work); + space_info = btrfs_find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA); + delayed_block_rsv = &fs_info->delayed_block_rsv; + delayed_refs_rsv = &fs_info->delayed_refs_rsv; + global_rsv = &fs_info->global_block_rsv; + trans_rsv = &fs_info->trans_block_rsv; + + spin_lock(&space_info->lock); + while (need_preemptive_reclaim(fs_info, space_info)) { + enum btrfs_flush_state flush; + u64 delalloc_size = 0; + u64 to_reclaim, block_rsv_size; + u64 global_rsv_size = global_rsv->reserved; + + loops++; + + /* + * We don't have a precise counter for the metadata being + * reserved for delalloc, so we'll approximate it by subtracting + * out the block rsv's space from the bytes_may_use. If that + * amount is higher than the individual reserves, then we can + * assume it's tied up in delalloc reservations. + */ + block_rsv_size = global_rsv_size + + delayed_block_rsv->reserved + + delayed_refs_rsv->reserved + + trans_rsv->reserved; + if (block_rsv_size < space_info->bytes_may_use) + delalloc_size = space_info->bytes_may_use - block_rsv_size; + spin_unlock(&space_info->lock); + + /* + * We don't want to include the global_rsv in our calculation, + * because that's space we can't touch. Subtract it from the + * block_rsv_size for the next checks. + */ + block_rsv_size -= global_rsv_size; + + /* + * We really want to avoid flushing delalloc too much, as it + * could result in poor allocation patterns, so only flush it if + * it's larger than the rest of the pools combined. + */ + if (delalloc_size > block_rsv_size) { + to_reclaim = delalloc_size; + flush = FLUSH_DELALLOC; + } else if (space_info->bytes_pinned > + (delayed_block_rsv->reserved + + delayed_refs_rsv->reserved)) { + to_reclaim = space_info->bytes_pinned; + flush = FORCE_COMMIT_TRANS; + } else if (delayed_block_rsv->reserved > + delayed_refs_rsv->reserved) { + to_reclaim = delayed_block_rsv->reserved; + flush = FLUSH_DELAYED_ITEMS_NR; + } else { + to_reclaim = delayed_refs_rsv->reserved; + flush = FLUSH_DELAYED_REFS_NR; + } + + /* + * We don't want to reclaim everything, just a portion, so scale + * down the to_reclaim by 1/4. If it takes us down to 0, + * reclaim 1 items worth. + */ + to_reclaim >>= 2; + if (!to_reclaim) + to_reclaim = btrfs_calc_insert_metadata_size(fs_info, 1); + flush_space(fs_info, space_info, to_reclaim, flush, true); + cond_resched(); + spin_lock(&space_info->lock); + } + + /* We only went through once, back off our clamping. */ + if (loops == 1 && !space_info->reclaim_size) + space_info->clamp = max(1, space_info->clamp - 1); + trace_btrfs_done_preemptive_reclaim(fs_info, space_info); + spin_unlock(&space_info->lock); +} + +/* * FLUSH_DELALLOC_WAIT: * Space is freed from flushing delalloc in one of two ways. * @@ -1052,7 +1212,7 @@ static void btrfs_async_reclaim_data_space(struct work_struct *work) struct btrfs_fs_info *fs_info; struct btrfs_space_info *space_info; u64 last_tickets_id; - int flush_state = 0; + enum btrfs_flush_state flush_state = 0; fs_info = container_of(work, struct btrfs_fs_info, async_data_reclaim_work); space_info = fs_info->data_sinfo; @@ -1067,7 +1227,7 @@ static void btrfs_async_reclaim_data_space(struct work_struct *work) spin_unlock(&space_info->lock); while (!space_info->full) { - flush_space(fs_info, space_info, U64_MAX, ALLOC_CHUNK_FORCE); + flush_space(fs_info, space_info, U64_MAX, ALLOC_CHUNK_FORCE, false); spin_lock(&space_info->lock); if (list_empty(&space_info->tickets)) { space_info->flush = 0; @@ -1080,7 +1240,7 @@ static void btrfs_async_reclaim_data_space(struct work_struct *work) while (flush_state < ARRAY_SIZE(data_flush_states)) { flush_space(fs_info, space_info, U64_MAX, - data_flush_states[flush_state]); + data_flush_states[flush_state], false); spin_lock(&space_info->lock); if (list_empty(&space_info->tickets)) { space_info->flush = 0; @@ -1113,6 +1273,8 @@ void btrfs_init_async_reclaim_work(struct btrfs_fs_info *fs_info) { INIT_WORK(&fs_info->async_reclaim_work, btrfs_async_reclaim_metadata_space); INIT_WORK(&fs_info->async_data_reclaim_work, btrfs_async_reclaim_data_space); + INIT_WORK(&fs_info->preempt_reclaim_work, + btrfs_preempt_reclaim_metadata_space); } static const enum btrfs_flush_state priority_flush_states[] = { @@ -1151,7 +1313,8 @@ static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info, flush_state = 0; do { - flush_space(fs_info, space_info, to_reclaim, states[flush_state]); + flush_space(fs_info, space_info, to_reclaim, states[flush_state], + false); flush_state++; spin_lock(&space_info->lock); if (ticket->bytes == 0) { @@ -1167,7 +1330,7 @@ static void priority_reclaim_data_space(struct btrfs_fs_info *fs_info, struct reserve_ticket *ticket) { while (!space_info->full) { - flush_space(fs_info, space_info, U64_MAX, ALLOC_CHUNK_FORCE); + flush_space(fs_info, space_info, U64_MAX, ALLOC_CHUNK_FORCE, false); spin_lock(&space_info->lock); if (ticket->bytes == 0) { spin_unlock(&space_info->lock); @@ -1212,11 +1375,14 @@ static void wait_reserve_ticket(struct btrfs_fs_info *fs_info, } /** - * handle_reserve_ticket - do the appropriate flushing and waiting for a ticket - * @fs_info - the fs - * @space_info - the space_info for the reservation - * @ticket - the ticket for the reservation - * @flush - how much we can flush + * Do the appropriate flushing and waiting for a ticket + * + * @fs_info: the filesystem + * @space_info: space info for the reservation + * @ticket: ticket for the reservation + * @start_ns: timestamp when the reservation started + * @orig_bytes: amount of bytes originally reserved + * @flush: how much we can flush * * This does the work of figuring out how to flush for the ticket, waiting for * the reservation, and returning the appropriate error if there is one. @@ -1224,6 +1390,7 @@ static void wait_reserve_ticket(struct btrfs_fs_info *fs_info, static int handle_reserve_ticket(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, struct reserve_ticket *ticket, + u64 start_ns, u64 orig_bytes, enum btrfs_reserve_flush_enum flush) { int ret; @@ -1279,6 +1446,8 @@ static int handle_reserve_ticket(struct btrfs_fs_info *fs_info, * space wasn't reserved at all). */ ASSERT(!(ticket->bytes == 0 && ticket->error)); + trace_btrfs_reserve_ticket(fs_info, space_info->flags, orig_bytes, + start_ns, flush, ticket->error); return ret; } @@ -1292,12 +1461,31 @@ static inline bool is_normal_flushing(enum btrfs_reserve_flush_enum flush) (flush == BTRFS_RESERVE_FLUSH_ALL_STEAL); } +static inline void maybe_clamp_preempt(struct btrfs_fs_info *fs_info, + struct btrfs_space_info *space_info) +{ + u64 ordered = percpu_counter_sum_positive(&fs_info->ordered_bytes); + u64 delalloc = percpu_counter_sum_positive(&fs_info->delalloc_bytes); + + /* + * If we're heavy on ordered operations then clamping won't help us. We + * need to clamp specifically to keep up with dirty'ing buffered + * writers, because there's not a 1:1 correlation of writing delalloc + * and freeing space, like there is with flushing delayed refs or + * delayed nodes. If we're already more ordered than delalloc then + * we're keeping up, otherwise we aren't and should probably clamp. + */ + if (ordered < delalloc) + space_info->clamp = min(space_info->clamp + 1, 8); +} + /** - * reserve_metadata_bytes - try to reserve bytes from the block_rsv's space - * @root - the root we're allocating for - * @space_info - the space info we want to allocate from - * @orig_bytes - the number of bytes we want - * @flush - whether or not we can flush to make our reservation + * Try to reserve bytes from the block_rsv's space + * + * @fs_info: the filesystem + * @space_info: space info we want to allocate from + * @orig_bytes: number of bytes we want + * @flush: whether or not we can flush to make our reservation * * This will reserve orig_bytes number of bytes from the space info associated * with the block_rsv. If there is not enough space it will make an attempt to @@ -1312,6 +1500,7 @@ static int __reserve_bytes(struct btrfs_fs_info *fs_info, { struct work_struct *async_work; struct reserve_ticket ticket; + u64 start_ns = 0; u64 used; int ret = 0; bool pending_tickets; @@ -1364,6 +1553,9 @@ static int __reserve_bytes(struct btrfs_fs_info *fs_info, space_info->reclaim_size += ticket.bytes; init_waitqueue_head(&ticket.wait); ticket.steal = (flush == BTRFS_RESERVE_FLUSH_ALL_STEAL); + if (trace_btrfs_reserve_ticket_enabled()) + start_ns = ktime_get_ns(); + if (flush == BTRFS_RESERVE_FLUSH_ALL || flush == BTRFS_RESERVE_FLUSH_ALL_STEAL || flush == BTRFS_RESERVE_FLUSH_DATA) { @@ -1380,6 +1572,14 @@ static int __reserve_bytes(struct btrfs_fs_info *fs_info, list_add_tail(&ticket.list, &space_info->priority_tickets); } + + /* + * We were forced to add a reserve ticket, so our preemptive + * flushing is unable to keep up. Clamp down on the threshold + * for the preemptive flushing in order to keep up with the + * workload. + */ + maybe_clamp_preempt(fs_info, space_info); } else if (!ret && space_info->flags & BTRFS_BLOCK_GROUP_METADATA) { used += orig_bytes; /* @@ -1388,27 +1588,29 @@ static int __reserve_bytes(struct btrfs_fs_info *fs_info, * the async reclaim as we will panic. */ if (!test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags) && - need_do_async_reclaim(fs_info, space_info, used) && - !work_busy(&fs_info->async_reclaim_work)) { + need_preemptive_reclaim(fs_info, space_info) && + !work_busy(&fs_info->preempt_reclaim_work)) { trace_btrfs_trigger_flush(fs_info, space_info->flags, orig_bytes, flush, "preempt"); queue_work(system_unbound_wq, - &fs_info->async_reclaim_work); + &fs_info->preempt_reclaim_work); } } spin_unlock(&space_info->lock); if (!ret || flush == BTRFS_RESERVE_NO_FLUSH) return ret; - return handle_reserve_ticket(fs_info, space_info, &ticket, flush); + return handle_reserve_ticket(fs_info, space_info, &ticket, start_ns, + orig_bytes, flush); } /** - * reserve_metadata_bytes - try to reserve bytes from the block_rsv's space - * @root - the root we're allocating for - * @block_rsv - the block_rsv we're allocating for - * @orig_bytes - the number of bytes we want - * @flush - whether or not we can flush to make our reservation + * Trye to reserve metadata bytes from the block_rsv's space + * + * @root: the root we're allocating for + * @block_rsv: block_rsv we're allocating for + * @orig_bytes: number of bytes we want + * @flush: whether or not we can flush to make our reservation * * This will reserve orig_bytes number of bytes from the space info associated * with the block_rsv. If there is not enough space it will make an attempt to @@ -1446,10 +1648,11 @@ int btrfs_reserve_metadata_bytes(struct btrfs_root *root, } /** - * btrfs_reserve_data_bytes - try to reserve data bytes for an allocation - * @fs_info - the filesystem - * @bytes - the number of bytes we need - * @flush - how we are allowed to flush + * Try to reserve data bytes for an allocation + * + * @fs_info: the filesystem + * @bytes: number of bytes we need + * @flush: how we are allowed to flush * * This will reserve bytes from the data space info. If there is not enough * space then we will attempt to flush space as specified by flush. diff --git a/fs/btrfs/space-info.h b/fs/btrfs/space-info.h index 5646393b928c..b1a8ffb03b3e 100644 --- a/fs/btrfs/space-info.h +++ b/fs/btrfs/space-info.h @@ -17,11 +17,17 @@ struct btrfs_space_info { u64 bytes_may_use; /* number of bytes that may be used for delalloc/allocations */ u64 bytes_readonly; /* total bytes that are read only */ + u64 bytes_zone_unusable; /* total bytes that are unusable until + resetting the device zone */ u64 max_extent_size; /* This will hold the maximum extent size of the space info if we had an ENOSPC in the allocator. */ + int clamp; /* Used to scale our threshold for preemptive + flushing. The value is >> clamp, so turns + out to be a 2^clamp divisor. */ + unsigned int full:1; /* indicates that we cannot allocate any more chunks for this space */ unsigned int chunk_alloc:1; /* set if we are allocating a chunk */ @@ -119,7 +125,7 @@ DECLARE_SPACE_INFO_UPDATE(bytes_pinned, "pinned"); int btrfs_init_space_info(struct btrfs_fs_info *fs_info); void btrfs_update_space_info(struct btrfs_fs_info *info, u64 flags, u64 total_bytes, u64 bytes_used, - u64 bytes_readonly, + u64 bytes_readonly, u64 bytes_zone_unusable, struct btrfs_space_info **space_info); struct btrfs_space_info *btrfs_find_space_info(struct btrfs_fs_info *info, u64 flags); @@ -152,4 +158,21 @@ static inline void btrfs_space_info_free_bytes_may_use( int btrfs_reserve_data_bytes(struct btrfs_fs_info *fs_info, u64 bytes, enum btrfs_reserve_flush_enum flush); +static inline void __btrfs_mod_total_bytes_pinned( + struct btrfs_space_info *space_info, + s64 mod) +{ + percpu_counter_add_batch(&space_info->total_bytes_pinned, mod, + BTRFS_TOTAL_BYTES_PINNED_BATCH); +} + +static inline void btrfs_mod_total_bytes_pinned(struct btrfs_fs_info *fs_info, + u64 flags, s64 mod) +{ + struct btrfs_space_info *space_info = btrfs_find_space_info(fs_info, flags); + + ASSERT(space_info); + __btrfs_mod_total_bytes_pinned(space_info, mod); +} + #endif /* BTRFS_SPACE_INFO_H */ diff --git a/fs/btrfs/struct-funcs.c b/fs/btrfs/struct-funcs.c index c46be27be700..8260f8bb3ff0 100644 --- a/fs/btrfs/struct-funcs.c +++ b/fs/btrfs/struct-funcs.c @@ -57,8 +57,9 @@ u##bits btrfs_get_token_##bits(struct btrfs_map_token *token, \ const void *ptr, unsigned long off) \ { \ const unsigned long member_offset = (unsigned long)ptr + off; \ - const unsigned long idx = member_offset >> PAGE_SHIFT; \ - const unsigned long oip = offset_in_page(member_offset); \ + const unsigned long idx = get_eb_page_index(member_offset); \ + const unsigned long oip = get_eb_offset_in_page(token->eb, \ + member_offset); \ const int size = sizeof(u##bits); \ u8 lebytes[sizeof(u##bits)]; \ const int part = PAGE_SIZE - oip; \ @@ -85,8 +86,8 @@ u##bits btrfs_get_##bits(const struct extent_buffer *eb, \ const void *ptr, unsigned long off) \ { \ const unsigned long member_offset = (unsigned long)ptr + off; \ - const unsigned long oip = offset_in_page(member_offset); \ - const unsigned long idx = member_offset >> PAGE_SHIFT; \ + const unsigned long oip = get_eb_offset_in_page(eb, member_offset); \ + const unsigned long idx = get_eb_page_index(member_offset); \ char *kaddr = page_address(eb->pages[idx]); \ const int size = sizeof(u##bits); \ const int part = PAGE_SIZE - oip; \ @@ -106,8 +107,9 @@ void btrfs_set_token_##bits(struct btrfs_map_token *token, \ u##bits val) \ { \ const unsigned long member_offset = (unsigned long)ptr + off; \ - const unsigned long idx = member_offset >> PAGE_SHIFT; \ - const unsigned long oip = offset_in_page(member_offset); \ + const unsigned long idx = get_eb_page_index(member_offset); \ + const unsigned long oip = get_eb_offset_in_page(token->eb, \ + member_offset); \ const int size = sizeof(u##bits); \ u8 lebytes[sizeof(u##bits)]; \ const int part = PAGE_SIZE - oip; \ @@ -136,8 +138,8 @@ void btrfs_set_##bits(const struct extent_buffer *eb, void *ptr, \ unsigned long off, u##bits val) \ { \ const unsigned long member_offset = (unsigned long)ptr + off; \ - const unsigned long oip = offset_in_page(member_offset); \ - const unsigned long idx = member_offset >> PAGE_SHIFT; \ + const unsigned long oip = get_eb_offset_in_page(eb, member_offset); \ + const unsigned long idx = get_eb_page_index(member_offset); \ char *kaddr = page_address(eb->pages[idx]); \ const int size = sizeof(u##bits); \ const int part = PAGE_SIZE - oip; \ diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c new file mode 100644 index 000000000000..c69049e7daa9 --- /dev/null +++ b/fs/btrfs/subpage.c @@ -0,0 +1,278 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/slab.h> +#include "ctree.h" +#include "subpage.h" + +int btrfs_attach_subpage(const struct btrfs_fs_info *fs_info, + struct page *page, enum btrfs_subpage_type type) +{ + struct btrfs_subpage *subpage = NULL; + int ret; + + /* + * We have cases like a dummy extent buffer page, which is not mappped + * and doesn't need to be locked. + */ + if (page->mapping) + ASSERT(PageLocked(page)); + /* Either not subpage, or the page already has private attached */ + if (fs_info->sectorsize == PAGE_SIZE || PagePrivate(page)) + return 0; + + ret = btrfs_alloc_subpage(fs_info, &subpage, type); + if (ret < 0) + return ret; + attach_page_private(page, subpage); + return 0; +} + +void btrfs_detach_subpage(const struct btrfs_fs_info *fs_info, + struct page *page) +{ + struct btrfs_subpage *subpage; + + /* Either not subpage, or already detached */ + if (fs_info->sectorsize == PAGE_SIZE || !PagePrivate(page)) + return; + + subpage = (struct btrfs_subpage *)detach_page_private(page); + ASSERT(subpage); + btrfs_free_subpage(subpage); +} + +int btrfs_alloc_subpage(const struct btrfs_fs_info *fs_info, + struct btrfs_subpage **ret, + enum btrfs_subpage_type type) +{ + if (fs_info->sectorsize == PAGE_SIZE) + return 0; + + *ret = kzalloc(sizeof(struct btrfs_subpage), GFP_NOFS); + if (!*ret) + return -ENOMEM; + spin_lock_init(&(*ret)->lock); + if (type == BTRFS_SUBPAGE_METADATA) + atomic_set(&(*ret)->eb_refs, 0); + else + atomic_set(&(*ret)->readers, 0); + return 0; +} + +void btrfs_free_subpage(struct btrfs_subpage *subpage) +{ + kfree(subpage); +} + +/* + * Increase the eb_refs of current subpage. + * + * This is important for eb allocation, to prevent race with last eb freeing + * of the same page. + * With the eb_refs increased before the eb inserted into radix tree, + * detach_extent_buffer_page() won't detach the page private while we're still + * allocating the extent buffer. + */ +void btrfs_page_inc_eb_refs(const struct btrfs_fs_info *fs_info, + struct page *page) +{ + struct btrfs_subpage *subpage; + + if (fs_info->sectorsize == PAGE_SIZE) + return; + + ASSERT(PagePrivate(page) && page->mapping); + lockdep_assert_held(&page->mapping->private_lock); + + subpage = (struct btrfs_subpage *)page->private; + atomic_inc(&subpage->eb_refs); +} + +void btrfs_page_dec_eb_refs(const struct btrfs_fs_info *fs_info, + struct page *page) +{ + struct btrfs_subpage *subpage; + + if (fs_info->sectorsize == PAGE_SIZE) + return; + + ASSERT(PagePrivate(page) && page->mapping); + lockdep_assert_held(&page->mapping->private_lock); + + subpage = (struct btrfs_subpage *)page->private; + ASSERT(atomic_read(&subpage->eb_refs)); + atomic_dec(&subpage->eb_refs); +} + +static void btrfs_subpage_assert(const struct btrfs_fs_info *fs_info, + struct page *page, u64 start, u32 len) +{ + /* Basic checks */ + ASSERT(PagePrivate(page) && page->private); + ASSERT(IS_ALIGNED(start, fs_info->sectorsize) && + IS_ALIGNED(len, fs_info->sectorsize)); + /* + * The range check only works for mapped page, we can still have + * unmapped page like dummy extent buffer pages. + */ + if (page->mapping) + ASSERT(page_offset(page) <= start && + start + len <= page_offset(page) + PAGE_SIZE); +} + +void btrfs_subpage_start_reader(const struct btrfs_fs_info *fs_info, + struct page *page, u64 start, u32 len) +{ + struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private; + const int nbits = len >> fs_info->sectorsize_bits; + int ret; + + btrfs_subpage_assert(fs_info, page, start, len); + + ret = atomic_add_return(nbits, &subpage->readers); + ASSERT(ret == nbits); +} + +void btrfs_subpage_end_reader(const struct btrfs_fs_info *fs_info, + struct page *page, u64 start, u32 len) +{ + struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private; + const int nbits = len >> fs_info->sectorsize_bits; + + btrfs_subpage_assert(fs_info, page, start, len); + ASSERT(atomic_read(&subpage->readers) >= nbits); + if (atomic_sub_and_test(nbits, &subpage->readers)) + unlock_page(page); +} + +/* + * Convert the [start, start + len) range into a u16 bitmap + * + * For example: if start == page_offset() + 16K, len = 16K, we get 0x00f0. + */ +static u16 btrfs_subpage_calc_bitmap(const struct btrfs_fs_info *fs_info, + struct page *page, u64 start, u32 len) +{ + const int bit_start = offset_in_page(start) >> fs_info->sectorsize_bits; + const int nbits = len >> fs_info->sectorsize_bits; + + btrfs_subpage_assert(fs_info, page, start, len); + + /* + * Here nbits can be 16, thus can go beyond u16 range. We make the + * first left shift to be calculate in unsigned long (at least u32), + * then truncate the result to u16. + */ + return (u16)(((1UL << nbits) - 1) << bit_start); +} + +void btrfs_subpage_set_uptodate(const struct btrfs_fs_info *fs_info, + struct page *page, u64 start, u32 len) +{ + struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private; + const u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len); + unsigned long flags; + + spin_lock_irqsave(&subpage->lock, flags); + subpage->uptodate_bitmap |= tmp; + if (subpage->uptodate_bitmap == U16_MAX) + SetPageUptodate(page); + spin_unlock_irqrestore(&subpage->lock, flags); +} + +void btrfs_subpage_clear_uptodate(const struct btrfs_fs_info *fs_info, + struct page *page, u64 start, u32 len) +{ + struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private; + const u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len); + unsigned long flags; + + spin_lock_irqsave(&subpage->lock, flags); + subpage->uptodate_bitmap &= ~tmp; + ClearPageUptodate(page); + spin_unlock_irqrestore(&subpage->lock, flags); +} + +void btrfs_subpage_set_error(const struct btrfs_fs_info *fs_info, + struct page *page, u64 start, u32 len) +{ + struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private; + const u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len); + unsigned long flags; + + spin_lock_irqsave(&subpage->lock, flags); + subpage->error_bitmap |= tmp; + SetPageError(page); + spin_unlock_irqrestore(&subpage->lock, flags); +} + +void btrfs_subpage_clear_error(const struct btrfs_fs_info *fs_info, + struct page *page, u64 start, u32 len) +{ + struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private; + const u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len); + unsigned long flags; + + spin_lock_irqsave(&subpage->lock, flags); + subpage->error_bitmap &= ~tmp; + if (subpage->error_bitmap == 0) + ClearPageError(page); + spin_unlock_irqrestore(&subpage->lock, flags); +} + +/* + * Unlike set/clear which is dependent on each page status, for test all bits + * are tested in the same way. + */ +#define IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(name) \ +bool btrfs_subpage_test_##name(const struct btrfs_fs_info *fs_info, \ + struct page *page, u64 start, u32 len) \ +{ \ + struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private; \ + const u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len); \ + unsigned long flags; \ + bool ret; \ + \ + spin_lock_irqsave(&subpage->lock, flags); \ + ret = ((subpage->name##_bitmap & tmp) == tmp); \ + spin_unlock_irqrestore(&subpage->lock, flags); \ + return ret; \ +} +IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(uptodate); +IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(error); + +/* + * Note that, in selftests (extent-io-tests), we can have empty fs_info passed + * in. We only test sectorsize == PAGE_SIZE cases so far, thus we can fall + * back to regular sectorsize branch. + */ +#define IMPLEMENT_BTRFS_PAGE_OPS(name, set_page_func, clear_page_func, \ + test_page_func) \ +void btrfs_page_set_##name(const struct btrfs_fs_info *fs_info, \ + struct page *page, u64 start, u32 len) \ +{ \ + if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE) { \ + set_page_func(page); \ + return; \ + } \ + btrfs_subpage_set_##name(fs_info, page, start, len); \ +} \ +void btrfs_page_clear_##name(const struct btrfs_fs_info *fs_info, \ + struct page *page, u64 start, u32 len) \ +{ \ + if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE) { \ + clear_page_func(page); \ + return; \ + } \ + btrfs_subpage_clear_##name(fs_info, page, start, len); \ +} \ +bool btrfs_page_test_##name(const struct btrfs_fs_info *fs_info, \ + struct page *page, u64 start, u32 len) \ +{ \ + if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE) \ + return test_page_func(page); \ + return btrfs_subpage_test_##name(fs_info, page, start, len); \ +} +IMPLEMENT_BTRFS_PAGE_OPS(uptodate, SetPageUptodate, ClearPageUptodate, + PageUptodate); +IMPLEMENT_BTRFS_PAGE_OPS(error, SetPageError, ClearPageError, PageError); diff --git a/fs/btrfs/subpage.h b/fs/btrfs/subpage.h new file mode 100644 index 000000000000..b86a4881475d --- /dev/null +++ b/fs/btrfs/subpage.h @@ -0,0 +1,91 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef BTRFS_SUBPAGE_H +#define BTRFS_SUBPAGE_H + +#include <linux/spinlock.h> + +/* + * Maximum page size we support is 64K, minimum sector size is 4K, u16 bitmap + * is sufficient. Regular bitmap_* is not used due to size reasons. + */ +#define BTRFS_SUBPAGE_BITMAP_SIZE 16 + +/* + * Structure to trace status of each sector inside a page, attached to + * page::private for both data and metadata inodes. + */ +struct btrfs_subpage { + /* Common members for both data and metadata pages */ + spinlock_t lock; + u16 uptodate_bitmap; + u16 error_bitmap; + union { + /* + * Structures only used by metadata + * + * @eb_refs should only be operated under private_lock, as it + * manages whether the subpage can be detached. + */ + atomic_t eb_refs; + /* Structures only used by data */ + struct { + atomic_t readers; + }; + }; +}; + +enum btrfs_subpage_type { + BTRFS_SUBPAGE_METADATA, + BTRFS_SUBPAGE_DATA, +}; + +int btrfs_attach_subpage(const struct btrfs_fs_info *fs_info, + struct page *page, enum btrfs_subpage_type type); +void btrfs_detach_subpage(const struct btrfs_fs_info *fs_info, + struct page *page); + +/* Allocate additional data where page represents more than one sector */ +int btrfs_alloc_subpage(const struct btrfs_fs_info *fs_info, + struct btrfs_subpage **ret, + enum btrfs_subpage_type type); +void btrfs_free_subpage(struct btrfs_subpage *subpage); + +void btrfs_page_inc_eb_refs(const struct btrfs_fs_info *fs_info, + struct page *page); +void btrfs_page_dec_eb_refs(const struct btrfs_fs_info *fs_info, + struct page *page); + +void btrfs_subpage_start_reader(const struct btrfs_fs_info *fs_info, + struct page *page, u64 start, u32 len); +void btrfs_subpage_end_reader(const struct btrfs_fs_info *fs_info, + struct page *page, u64 start, u32 len); + +/* + * Template for subpage related operations. + * + * btrfs_subpage_*() are for call sites where the page has subpage attached and + * the range is ensured to be inside the page. + * + * btrfs_page_*() are for call sites where the page can either be subpage + * specific or regular page. The function will handle both cases. + * But the range still needs to be inside the page. + */ +#define DECLARE_BTRFS_SUBPAGE_OPS(name) \ +void btrfs_subpage_set_##name(const struct btrfs_fs_info *fs_info, \ + struct page *page, u64 start, u32 len); \ +void btrfs_subpage_clear_##name(const struct btrfs_fs_info *fs_info, \ + struct page *page, u64 start, u32 len); \ +bool btrfs_subpage_test_##name(const struct btrfs_fs_info *fs_info, \ + struct page *page, u64 start, u32 len); \ +void btrfs_page_set_##name(const struct btrfs_fs_info *fs_info, \ + struct page *page, u64 start, u32 len); \ +void btrfs_page_clear_##name(const struct btrfs_fs_info *fs_info, \ + struct page *page, u64 start, u32 len); \ +bool btrfs_page_test_##name(const struct btrfs_fs_info *fs_info, \ + struct page *page, u64 start, u32 len); + +DECLARE_BTRFS_SUBPAGE_OPS(uptodate); +DECLARE_BTRFS_SUBPAGE_OPS(error); + +#endif diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 8840a4fa81eb..f8435641b912 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -44,10 +44,10 @@ #include "backref.h" #include "space-info.h" #include "sysfs.h" +#include "zoned.h" #include "tests/btrfs-tests.h" #include "block-group.h" #include "discard.h" - #include "qgroup.h" #define CREATE_TRACE_POINTS #include <trace/events/btrfs.h> @@ -174,7 +174,7 @@ void __btrfs_handle_fs_error(struct btrfs_fs_info *fs_info, const char *function btrfs_discard_stop(fs_info); /* btrfs handle error by forcing the filesystem readonly */ - sb->s_flags |= SB_RDONLY; + btrfs_set_sb_rdonly(sb); btrfs_info(fs_info, "forced readonly"); /* * Note that a running device replace operation is not canceled here @@ -240,9 +240,13 @@ void __cold btrfs_printk(const struct btrfs_fs_info *fs_info, const char *fmt, . vaf.fmt = fmt; vaf.va = &args; - if (__ratelimit(ratelimit)) - printk("%sBTRFS %s (device %s): %pV\n", lvl, type, - fs_info ? fs_info->sb->s_id : "<unknown>", &vaf); + if (__ratelimit(ratelimit)) { + if (fs_info) + printk("%sBTRFS %s (device %s): %pV\n", lvl, type, + fs_info->sb->s_id, &vaf); + else + printk("%sBTRFS %s: %pV\n", lvl, type, &vaf); + } va_end(args); } @@ -333,7 +337,6 @@ enum { Opt_device, Opt_fatal_errors, Opt_flushoncommit, Opt_noflushoncommit, - Opt_inode_cache, Opt_noinode_cache, Opt_max_inline, Opt_barrier, Opt_nobarrier, Opt_datacow, Opt_nodatacow, @@ -360,9 +363,13 @@ enum { Opt_rescue, Opt_usebackuproot, Opt_nologreplay, + Opt_ignorebadroots, + Opt_ignoredatacsums, + Opt_rescue_all, /* Deprecated options */ Opt_recovery, + Opt_inode_cache, Opt_noinode_cache, /* Debugging options */ Opt_check_integrity, @@ -455,9 +462,25 @@ static const match_table_t tokens = { static const match_table_t rescue_tokens = { {Opt_usebackuproot, "usebackuproot"}, {Opt_nologreplay, "nologreplay"}, + {Opt_ignorebadroots, "ignorebadroots"}, + {Opt_ignorebadroots, "ibadroots"}, + {Opt_ignoredatacsums, "ignoredatacsums"}, + {Opt_ignoredatacsums, "idatacsums"}, + {Opt_rescue_all, "all"}, {Opt_err, NULL}, }; +static bool check_ro_option(struct btrfs_fs_info *fs_info, unsigned long opt, + const char *opt_name) +{ + if (fs_info->mount_opt & opt) { + btrfs_err(fs_info, "%s must be used with ro mount option", + opt_name); + return true; + } + return false; +} + static int parse_rescue_options(struct btrfs_fs_info *info, const char *options) { char *opts; @@ -487,6 +510,23 @@ static int parse_rescue_options(struct btrfs_fs_info *info, const char *options) btrfs_set_and_info(info, NOLOGREPLAY, "disabling log replay at mount time"); break; + case Opt_ignorebadroots: + btrfs_set_and_info(info, IGNOREBADROOTS, + "ignoring bad roots"); + break; + case Opt_ignoredatacsums: + btrfs_set_and_info(info, IGNOREDATACSUMS, + "ignoring data csums"); + break; + case Opt_rescue_all: + btrfs_info(info, "enabling all of the rescue options"); + btrfs_set_and_info(info, IGNOREDATACSUMS, + "ignoring data csums"); + btrfs_set_and_info(info, IGNOREBADROOTS, + "ignoring bad roots"); + btrfs_set_and_info(info, NOLOGREPLAY, + "disabling log replay at mount time"); + break; case Opt_err: btrfs_info(info, "unrecognized rescue option '%s'", p); ret = -EINVAL; @@ -511,7 +551,6 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, { substring_t args[MAX_OPT_ARGS]; char *p, *num; - u64 cache_gen; int intarg; int ret = 0; char *compress_type; @@ -521,11 +560,17 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, bool saved_compress_force; int no_compress = 0; - cache_gen = btrfs_super_cache_generation(info->super_copy); if (btrfs_fs_compat_ro(info, FREE_SPACE_TREE)) btrfs_set_opt(info->mount_opt, FREE_SPACE_TREE); - else if (cache_gen) - btrfs_set_opt(info->mount_opt, SPACE_CACHE); + else if (btrfs_free_space_cache_v1_active(info)) { + if (btrfs_is_zoned(info)) { + btrfs_info(info, + "zoned: clearing existing space cache"); + btrfs_set_super_cache_generation(info->super_copy, 0); + } else { + btrfs_set_opt(info->mount_opt, SPACE_CACHE); + } + } /* * Even the options are empty, we still need to do extra check @@ -832,14 +877,9 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, } break; case Opt_inode_cache: - btrfs_warn(info, - "the 'inode_cache' option is deprecated and will have no effect from 5.11"); - btrfs_set_pending_and_info(info, INODE_MAP_CACHE, - "enabling inode map caching"); - break; case Opt_noinode_cache: - btrfs_clear_pending_and_info(info, INODE_MAP_CACHE, - "disabling inode map caching"); + btrfs_warn(info, + "the 'inode_cache' option is deprecated and has no effect since 5.11"); break; case Opt_clear_cache: btrfs_set_and_info(info, CLEAR_CACHE, @@ -968,14 +1008,14 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, } } check: - /* - * Extra check for current option against current flag - */ - if (btrfs_test_opt(info, NOLOGREPLAY) && !(new_flags & SB_RDONLY)) { - btrfs_err(info, - "nologreplay must be used with ro mount option"); + /* We're read-only, don't have to check. */ + if (new_flags & SB_RDONLY) + goto out; + + if (check_ro_option(info, BTRFS_MOUNT_NOLOGREPLAY, "nologreplay") || + check_ro_option(info, BTRFS_MOUNT_IGNOREBADROOTS, "ignorebadroots") || + check_ro_option(info, BTRFS_MOUNT_IGNOREDATACSUMS, "ignoredatacsums")) ret = -EINVAL; - } out: if (btrfs_fs_compat_ro(info, FREE_SPACE_TREE) && !btrfs_test_opt(info, FREE_SPACE_TREE) && @@ -984,6 +1024,8 @@ out: ret = -EINVAL; } + if (!ret) + ret = btrfs_check_mountopts_zoned(info); if (!ret && btrfs_test_opt(info, SPACE_CACHE)) btrfs_info(info, "disk space caching is enabled"); if (!ret && btrfs_test_opt(info, FREE_SPACE_TREE)) @@ -1127,7 +1169,6 @@ char *btrfs_get_subvol_name_from_objectid(struct btrfs_fs_info *fs_info, ret = -ENOMEM; goto err; } - path->leave_spinning = 1; name = kmalloc(PATH_MAX, GFP_KERNEL); if (!name) { @@ -1256,7 +1297,6 @@ static int get_default_subvol_objectid(struct btrfs_fs_info *fs_info, u64 *objec path = btrfs_alloc_path(); if (!path) return -ENOMEM; - path->leave_spinning = 1; /* * Find the "default" dir item which points to the root item that we @@ -1383,11 +1423,18 @@ int btrfs_sync_fs(struct super_block *sb, int wait) return btrfs_commit_transaction(trans); } +static void print_rescue_option(struct seq_file *seq, const char *s, bool *printed) +{ + seq_printf(seq, "%s%s", (*printed) ? ":" : ",rescue=", s); + *printed = true; +} + static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry) { struct btrfs_fs_info *info = btrfs_sb(dentry->d_sb); const char *compress_type; const char *subvol_name; + bool printed = false; if (btrfs_test_opt(info, DEGRADED)) seq_puts(seq, ",degraded"); @@ -1420,7 +1467,13 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry) if (btrfs_test_opt(info, NOTREELOG)) seq_puts(seq, ",notreelog"); if (btrfs_test_opt(info, NOLOGREPLAY)) - seq_puts(seq, ",rescue=nologreplay"); + print_rescue_option(seq, "nologreplay", &printed); + if (btrfs_test_opt(info, USEBACKUPROOT)) + print_rescue_option(seq, "usebackuproot", &printed); + if (btrfs_test_opt(info, IGNOREBADROOTS)) + print_rescue_option(seq, "ignorebadroots", &printed); + if (btrfs_test_opt(info, IGNOREDATACSUMS)) + print_rescue_option(seq, "ignoredatacsums", &printed); if (btrfs_test_opt(info, FLUSHONCOMMIT)) seq_puts(seq, ",flushoncommit"); if (btrfs_test_opt(info, DISCARD_SYNC)) @@ -1429,9 +1482,9 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry) seq_puts(seq, ",discard=async"); if (!(info->sb->s_flags & SB_POSIXACL)) seq_puts(seq, ",noacl"); - if (btrfs_test_opt(info, SPACE_CACHE)) + if (btrfs_free_space_cache_v1_active(info)) seq_puts(seq, ",space_cache"); - else if (btrfs_test_opt(info, FREE_SPACE_TREE)) + else if (btrfs_fs_compat_ro(info, FREE_SPACE_TREE)) seq_puts(seq, ",space_cache=v2"); else seq_puts(seq, ",nospace_cache"); @@ -1445,8 +1498,6 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry) seq_puts(seq, ",enospc_debug"); if (btrfs_test_opt(info, AUTO_DEFRAG)) seq_puts(seq, ",autodefrag"); - if (btrfs_test_opt(info, INODE_MAP_CACHE)) - seq_puts(seq, ",inode_cache"); if (btrfs_test_opt(info, SKIP_BALANCE)) seq_puts(seq, ",skip_balance"); #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY @@ -1810,6 +1861,8 @@ static inline void btrfs_remount_begin(struct btrfs_fs_info *fs_info, static inline void btrfs_remount_cleanup(struct btrfs_fs_info *fs_info, unsigned long old_opts) { + const bool cache_opt = btrfs_test_opt(fs_info, SPACE_CACHE); + /* * We need to cleanup all defragable inodes if the autodefragment is * close or the filesystem is read only. @@ -1826,12 +1879,15 @@ static inline void btrfs_remount_cleanup(struct btrfs_fs_info *fs_info, else if (btrfs_raw_test_opt(old_opts, DISCARD_ASYNC) && !btrfs_test_opt(fs_info, DISCARD_ASYNC)) btrfs_discard_cleanup(fs_info); + + /* If we toggled space cache */ + if (cache_opt != btrfs_free_space_cache_v1_active(fs_info)) + btrfs_set_free_space_cache_v1_active(fs_info, cache_opt); } static int btrfs_remount(struct super_block *sb, int *flags, char *data) { struct btrfs_fs_info *fs_info = btrfs_sb(sb); - struct btrfs_root *root = fs_info->tree_root; unsigned old_flags = sb->s_flags; unsigned long old_opts = fs_info->mount_opt; unsigned long old_compress_type = fs_info->compress_type; @@ -1862,6 +1918,22 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) btrfs_resize_thread_pool(fs_info, fs_info->thread_pool_size, old_thread_pool_size); + if (btrfs_test_opt(fs_info, FREE_SPACE_TREE) != + btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) && + (!sb_rdonly(sb) || (*flags & SB_RDONLY))) { + btrfs_warn(fs_info, + "remount supports changing free space tree only from ro to rw"); + /* Make sure free space cache options match the state on disk */ + if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) { + btrfs_set_opt(fs_info->mount_opt, FREE_SPACE_TREE); + btrfs_clear_opt(fs_info->mount_opt, SPACE_CACHE); + } + if (btrfs_free_space_cache_v1_active(fs_info)) { + btrfs_clear_opt(fs_info->mount_opt, FREE_SPACE_TREE); + btrfs_set_opt(fs_info->mount_opt, SPACE_CACHE); + } + } + if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb)) goto out; @@ -1880,7 +1952,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) /* avoid complains from lockdep et al. */ up(&fs_info->uuid_tree_rescan_sem); - sb->s_flags |= SB_RDONLY; + btrfs_set_sb_rdonly(sb); /* * Setting SB_RDONLY will put the cleaner thread to @@ -1891,10 +1963,42 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) */ btrfs_delete_unused_bgs(fs_info); + /* + * The cleaner task could be already running before we set the + * flag BTRFS_FS_STATE_RO (and SB_RDONLY in the superblock). + * We must make sure that after we finish the remount, i.e. after + * we call btrfs_commit_super(), the cleaner can no longer start + * a transaction - either because it was dropping a dead root, + * running delayed iputs or deleting an unused block group (the + * cleaner picked a block group from the list of unused block + * groups before we were able to in the previous call to + * btrfs_delete_unused_bgs()). + */ + wait_on_bit(&fs_info->flags, BTRFS_FS_CLEANER_RUNNING, + TASK_UNINTERRUPTIBLE); + + /* + * We've set the superblock to RO mode, so we might have made + * the cleaner task sleep without running all pending delayed + * iputs. Go through all the delayed iputs here, so that if an + * unmount happens without remounting RW we don't end up at + * finishing close_ctree() with a non-empty list of delayed + * iputs. + */ + btrfs_run_delayed_iputs(fs_info); + btrfs_dev_replace_suspend_for_unmount(fs_info); btrfs_scrub_cancel(fs_info); btrfs_pause_balance(fs_info); + /* + * Pause the qgroup rescan worker if it is running. We don't want + * it to be still running after we are in RO mode, as after that, + * by the time we unmount, it might have left a transaction open, + * so we would leak the transaction and/or crash. + */ + btrfs_qgroup_wait_for_completion(fs_info, false); + ret = btrfs_commit_super(fs_info); if (ret) goto restore; @@ -1923,41 +2027,24 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) ret = -EINVAL; goto restore; } - - ret = btrfs_cleanup_fs_roots(fs_info); - if (ret) - goto restore; - - /* recover relocation */ - mutex_lock(&fs_info->cleaner_mutex); - ret = btrfs_recover_relocation(root); - mutex_unlock(&fs_info->cleaner_mutex); - if (ret) + if (fs_info->sectorsize < PAGE_SIZE) { + btrfs_warn(fs_info, + "read-write mount is not yet allowed for sectorsize %u page size %lu", + fs_info->sectorsize, PAGE_SIZE); + ret = -EINVAL; goto restore; + } - ret = btrfs_resume_balance_async(fs_info); + /* + * NOTE: when remounting with a change that does writes, don't + * put it anywhere above this point, as we are not sure to be + * safe to write until we pass the above checks. + */ + ret = btrfs_start_pre_rw_mount(fs_info); if (ret) goto restore; - ret = btrfs_resume_dev_replace_async(fs_info); - if (ret) { - btrfs_warn(fs_info, "failed to resume dev_replace"); - goto restore; - } - - btrfs_qgroup_rescan_resume(fs_info); - - if (!fs_info->uuid_root) { - btrfs_info(fs_info, "creating UUID tree"); - ret = btrfs_create_uuid_tree(fs_info); - if (ret) { - btrfs_warn(fs_info, - "failed to create the UUID tree %d", - ret); - goto restore; - } - } - sb->s_flags &= ~SB_RDONLY; + btrfs_clear_sb_rdonly(sb); set_bit(BTRFS_FS_OPEN, &fs_info->flags); } @@ -1970,6 +2057,7 @@ out: wake_up_process(fs_info->transaction_kthread); btrfs_remount_cleanup(fs_info, old_opts); + btrfs_clear_oneshot_options(fs_info); clear_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state); return 0; @@ -1978,6 +2066,8 @@ restore: /* We've hit an error - don't reset SB_RDONLY */ if (sb_rdonly(sb)) old_flags |= SB_RDONLY; + if (!(old_flags & SB_RDONLY)) + clear_bit(BTRFS_FS_STATE_RO, &fs_info->fs_state); sb->s_flags = old_flags; fs_info->mount_opt = old_opts; fs_info->compress_type = old_compress_type; @@ -2156,7 +2246,7 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) u64 total_used = 0; u64 total_free_data = 0; u64 total_free_meta = 0; - int bits = dentry->d_sb->s_blocksize_bits; + u32 bits = fs_info->sectorsize_bits; __be32 *fsid = (__be32 *)fs_info->fs_devices->fsid; unsigned factor = 1; struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv; @@ -2463,6 +2553,11 @@ static void __init btrfs_print_mod_info(void) #ifdef CONFIG_BTRFS_FS_REF_VERIFY ", ref-verify=on" #endif +#ifdef CONFIG_BLK_DEV_ZONED + ", zoned=yes" +#else + ", zoned=no" +#endif ; pr_info("Btrfs loaded, crc32c=%s%s\n", crc32c_impl(), options); } @@ -2523,8 +2618,6 @@ static int __init init_btrfs_fs(void) if (err) goto free_end_io_wq; - btrfs_init_lockdep(); - btrfs_print_mod_info(); err = btrfs_run_sanity_tests(); diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 279d9262b676..6eb1c50fa98c 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -263,6 +263,10 @@ BTRFS_FEAT_ATTR_INCOMPAT(no_holes, NO_HOLES); BTRFS_FEAT_ATTR_INCOMPAT(metadata_uuid, METADATA_UUID); BTRFS_FEAT_ATTR_COMPAT_RO(free_space_tree, FREE_SPACE_TREE); BTRFS_FEAT_ATTR_INCOMPAT(raid1c34, RAID1C34); +/* Remove once support for zoned allocation is feature complete */ +#ifdef CONFIG_BTRFS_DEBUG +BTRFS_FEAT_ATTR_INCOMPAT(zoned, ZONED); +#endif static struct attribute *btrfs_supported_feature_attrs[] = { BTRFS_FEAT_ATTR_PTR(mixed_backref), @@ -278,6 +282,9 @@ static struct attribute *btrfs_supported_feature_attrs[] = { BTRFS_FEAT_ATTR_PTR(metadata_uuid), BTRFS_FEAT_ATTR_PTR(free_space_tree), BTRFS_FEAT_ATTR_PTR(raid1c34), +#ifdef CONFIG_BTRFS_DEBUG + BTRFS_FEAT_ATTR_PTR(zoned), +#endif NULL }; @@ -329,10 +336,35 @@ static ssize_t send_stream_version_show(struct kobject *kobj, } BTRFS_ATTR(static_feature, send_stream_version, send_stream_version_show); +static const char *rescue_opts[] = { + "usebackuproot", + "nologreplay", + "ignorebadroots", + "ignoredatacsums", + "all", +}; + +static ssize_t supported_rescue_options_show(struct kobject *kobj, + struct kobj_attribute *a, + char *buf) +{ + ssize_t ret = 0; + int i; + + for (i = 0; i < ARRAY_SIZE(rescue_opts); i++) + ret += scnprintf(buf + ret, PAGE_SIZE - ret, "%s%s", + (i ? " " : ""), rescue_opts[i]); + ret += scnprintf(buf + ret, PAGE_SIZE - ret, "\n"); + return ret; +} +BTRFS_ATTR(static_feature, supported_rescue_options, + supported_rescue_options_show); + static struct attribute *btrfs_supported_static_feature_attrs[] = { BTRFS_ATTR_PTR(static_feature, rmdir_subvol), BTRFS_ATTR_PTR(static_feature, supported_checksums), BTRFS_ATTR_PTR(static_feature, send_stream_version), + BTRFS_ATTR_PTR(static_feature, supported_rescue_options), NULL }; @@ -433,7 +465,8 @@ static ssize_t btrfs_discard_iops_limit_store(struct kobject *kobj, return -EINVAL; WRITE_ONCE(discard_ctl->iops_limit, iops_limit); - + btrfs_discard_calc_delay(discard_ctl); + btrfs_discard_schedule_work(discard_ctl, true); return len; } BTRFS_ATTR_RW(discard, iops_limit, btrfs_discard_iops_limit_show, @@ -463,7 +496,7 @@ static ssize_t btrfs_discard_kbps_limit_store(struct kobject *kobj, return -EINVAL; WRITE_ONCE(discard_ctl->kbps_limit, kbps_limit); - + btrfs_discard_schedule_work(discard_ctl, true); return len; } BTRFS_ATTR_RW(discard, kbps_limit, btrfs_discard_kbps_limit_show, @@ -633,6 +666,7 @@ SPACE_INFO_ATTR(bytes_pinned); SPACE_INFO_ATTR(bytes_reserved); SPACE_INFO_ATTR(bytes_may_use); SPACE_INFO_ATTR(bytes_readonly); +SPACE_INFO_ATTR(bytes_zone_unusable); SPACE_INFO_ATTR(disk_used); SPACE_INFO_ATTR(disk_total); BTRFS_ATTR(space_info, total_bytes_pinned, @@ -646,6 +680,7 @@ static struct attribute *space_info_attrs[] = { BTRFS_ATTR_PTR(space_info, bytes_reserved), BTRFS_ATTR_PTR(space_info, bytes_may_use), BTRFS_ATTR_PTR(space_info, bytes_readonly), + BTRFS_ATTR_PTR(space_info, bytes_zone_unusable), BTRFS_ATTR_PTR(space_info, disk_used), BTRFS_ATTR_PTR(space_info, disk_total), BTRFS_ATTR_PTR(space_info, total_bytes_pinned), @@ -854,6 +889,82 @@ static ssize_t btrfs_exclusive_operation_show(struct kobject *kobj, } BTRFS_ATTR(, exclusive_operation, btrfs_exclusive_operation_show); +static ssize_t btrfs_generation_show(struct kobject *kobj, + struct kobj_attribute *a, char *buf) +{ + struct btrfs_fs_info *fs_info = to_fs_info(kobj); + + return scnprintf(buf, PAGE_SIZE, "%llu\n", fs_info->generation); +} +BTRFS_ATTR(, generation, btrfs_generation_show); + +/* + * Look for an exact string @string in @buffer with possible leading or + * trailing whitespace + */ +static bool strmatch(const char *buffer, const char *string) +{ + const size_t len = strlen(string); + + /* Skip leading whitespace */ + buffer = skip_spaces(buffer); + + /* Match entire string, check if the rest is whitespace or empty */ + if (strncmp(string, buffer, len) == 0 && + strlen(skip_spaces(buffer + len)) == 0) + return true; + + return false; +} + +static const char * const btrfs_read_policy_name[] = { "pid" }; + +static ssize_t btrfs_read_policy_show(struct kobject *kobj, + struct kobj_attribute *a, char *buf) +{ + struct btrfs_fs_devices *fs_devices = to_fs_devs(kobj); + ssize_t ret = 0; + int i; + + for (i = 0; i < BTRFS_NR_READ_POLICY; i++) { + if (fs_devices->read_policy == i) + ret += scnprintf(buf + ret, PAGE_SIZE - ret, "%s[%s]", + (ret == 0 ? "" : " "), + btrfs_read_policy_name[i]); + else + ret += scnprintf(buf + ret, PAGE_SIZE - ret, "%s%s", + (ret == 0 ? "" : " "), + btrfs_read_policy_name[i]); + } + + ret += scnprintf(buf + ret, PAGE_SIZE - ret, "\n"); + + return ret; +} + +static ssize_t btrfs_read_policy_store(struct kobject *kobj, + struct kobj_attribute *a, + const char *buf, size_t len) +{ + struct btrfs_fs_devices *fs_devices = to_fs_devs(kobj); + int i; + + for (i = 0; i < BTRFS_NR_READ_POLICY; i++) { + if (strmatch(buf, btrfs_read_policy_name[i])) { + if (i != fs_devices->read_policy) { + fs_devices->read_policy = i; + btrfs_info(fs_devices->fs_info, + "read policy set to '%s'", + btrfs_read_policy_name[i]); + } + return len; + } + } + + return -EINVAL; +} +BTRFS_ATTR_RW(, read_policy, btrfs_read_policy_show, btrfs_read_policy_store); + static const struct attribute *btrfs_attrs[] = { BTRFS_ATTR_PTR(, label), BTRFS_ATTR_PTR(, nodesize), @@ -863,6 +974,8 @@ static const struct attribute *btrfs_attrs[] = { BTRFS_ATTR_PTR(, metadata_uuid), BTRFS_ATTR_PTR(, checksum), BTRFS_ATTR_PTR(, exclusive_operation), + BTRFS_ATTR_PTR(, generation), + BTRFS_ATTR_PTR(, read_policy), NULL, }; @@ -1207,7 +1320,7 @@ static const char *alloc_name(u64 flags) default: WARN_ON(1); return "invalid-combination"; - }; + } } /* @@ -1232,8 +1345,6 @@ int btrfs_sysfs_add_space_info_type(struct btrfs_fs_info *fs_info, void btrfs_sysfs_remove_device(struct btrfs_device *device) { - struct hd_struct *disk; - struct kobject *disk_kobj; struct kobject *devices_kobj; /* @@ -1243,11 +1354,8 @@ void btrfs_sysfs_remove_device(struct btrfs_device *device) devices_kobj = device->fs_info->fs_devices->devices_kobj; ASSERT(devices_kobj); - if (device->bdev) { - disk = device->bdev->bd_part; - disk_kobj = &part_to_dev(disk)->kobj; - sysfs_remove_link(devices_kobj, disk_kobj->name); - } + if (device->bdev) + sysfs_remove_link(devices_kobj, bdev_kobj(device->bdev)->name); if (device->devid_kobj.state_initialized) { kobject_del(&device->devid_kobj); @@ -1353,11 +1461,7 @@ int btrfs_sysfs_add_device(struct btrfs_device *device) nofs_flag = memalloc_nofs_save(); if (device->bdev) { - struct hd_struct *disk; - struct kobject *disk_kobj; - - disk = device->bdev->bd_part; - disk_kobj = &part_to_dev(disk)->kobj; + struct kobject *disk_kobj = bdev_kobj(device->bdev); ret = sysfs_create_link(devices_kobj, disk_kobj, disk_kobj->name); if (ret) { diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c index 999c14e5d0bd..6bd97bd4cb37 100644 --- a/fs/btrfs/tests/btrfs-tests.c +++ b/fs/btrfs/tests/btrfs-tests.c @@ -55,8 +55,14 @@ struct inode *btrfs_new_test_inode(void) struct inode *inode; inode = new_inode(test_mnt->mnt_sb); - if (inode) - inode_init_owner(inode, NULL, S_IFREG); + if (!inode) + return NULL; + + inode->i_mode = S_IFREG; + BTRFS_I(inode)->location.type = BTRFS_INODE_ITEM_KEY; + BTRFS_I(inode)->location.objectid = BTRFS_FIRST_FREE_OBJECTID; + BTRFS_I(inode)->location.offset = 0; + inode_init_owner(inode, NULL, S_IFREG); return inode; } @@ -134,6 +140,7 @@ struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(u32 nodesize, u32 sectorsize) fs_info->nodesize = nodesize; fs_info->sectorsize = sectorsize; + fs_info->sectorsize_bits = ilog2(sectorsize); set_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state); test_mnt->mnt_sb->s_fs_info = fs_info; @@ -224,7 +231,7 @@ btrfs_alloc_dummy_block_group(struct btrfs_fs_info *fs_info, INIT_LIST_HEAD(&cache->list); INIT_LIST_HEAD(&cache->cluster_list); INIT_LIST_HEAD(&cache->bg_list); - btrfs_init_free_space_ctl(cache); + btrfs_init_free_space_ctl(cache, cache->free_space_ctl); mutex_init(&cache->free_space_lock); return cache; diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c index df7ce874a74b..73e96d505f4f 100644 --- a/fs/btrfs/tests/extent-io-tests.c +++ b/fs/btrfs/tests/extent-io-tests.c @@ -379,54 +379,50 @@ static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb, static int test_eb_bitmaps(u32 sectorsize, u32 nodesize) { struct btrfs_fs_info *fs_info; - unsigned long len; unsigned long *bitmap = NULL; struct extent_buffer *eb = NULL; int ret; test_msg("running extent buffer bitmap tests"); - /* - * In ppc64, sectorsize can be 64K, thus 4 * 64K will be larger than - * BTRFS_MAX_METADATA_BLOCKSIZE. - */ - len = (sectorsize < BTRFS_MAX_METADATA_BLOCKSIZE) - ? sectorsize * 4 : sectorsize; - - fs_info = btrfs_alloc_dummy_fs_info(len, len); + fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize); if (!fs_info) { test_std_err(TEST_ALLOC_FS_INFO); return -ENOMEM; } - bitmap = kmalloc(len, GFP_KERNEL); + bitmap = kmalloc(nodesize, GFP_KERNEL); if (!bitmap) { test_err("couldn't allocate test bitmap"); ret = -ENOMEM; goto out; } - eb = __alloc_dummy_extent_buffer(fs_info, 0, len); + eb = __alloc_dummy_extent_buffer(fs_info, 0, nodesize); if (!eb) { test_std_err(TEST_ALLOC_ROOT); ret = -ENOMEM; goto out; } - ret = __test_eb_bitmaps(bitmap, eb, len); + ret = __test_eb_bitmaps(bitmap, eb, nodesize); if (ret) goto out; - /* Do it over again with an extent buffer which isn't page-aligned. */ free_extent_buffer(eb); - eb = __alloc_dummy_extent_buffer(fs_info, nodesize / 2, len); + + /* + * Test again for case where the tree block is sectorsize aligned but + * not nodesize aligned. + */ + eb = __alloc_dummy_extent_buffer(fs_info, sectorsize, nodesize); if (!eb) { test_std_err(TEST_ALLOC_ROOT); ret = -ENOMEM; goto out; } - ret = __test_eb_bitmaps(bitmap, eb, len); + ret = __test_eb_bitmaps(bitmap, eb, nodesize); out: free_extent_buffer(eb); kfree(bitmap); diff --git a/fs/btrfs/tests/extent-map-tests.c b/fs/btrfs/tests/extent-map-tests.c index 57379e96ccc9..c0aefe6dee0b 100644 --- a/fs/btrfs/tests/extent-map-tests.c +++ b/fs/btrfs/tests/extent-map-tests.c @@ -507,7 +507,7 @@ static int test_rmap_block(struct btrfs_fs_info *fs_info, goto out_free; } - ret = btrfs_rmap_block(fs_info, em->start, btrfs_sb_offset(1), + ret = btrfs_rmap_block(fs_info, em->start, NULL, btrfs_sb_offset(1), &logical, &out_ndaddrs, &out_stripe_len); if (ret || (out_ndaddrs == 0 && test->expected_mapped_addr)) { test_err("didn't rmap anything but expected %d", diff --git a/fs/btrfs/tests/free-space-tests.c b/fs/btrfs/tests/free-space-tests.c index aebdf23f0cdd..8f05c1eb833f 100644 --- a/fs/btrfs/tests/free-space-tests.c +++ b/fs/btrfs/tests/free-space-tests.c @@ -399,7 +399,6 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group *cache, u64 offset; u64 max_extent_size; const struct btrfs_free_space_op test_free_space_ops = { - .recalc_thresholds = cache->free_space_ctl->op->recalc_thresholds, .use_bitmap = test_use_bitmap, }; const struct btrfs_free_space_op *orig_free_space_ops; diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c index e6719f7db386..c9874b12d337 100644 --- a/fs/btrfs/tests/inode-tests.c +++ b/fs/btrfs/tests/inode-tests.c @@ -232,11 +232,6 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize) return ret; } - inode->i_mode = S_IFREG; - BTRFS_I(inode)->location.type = BTRFS_INODE_ITEM_KEY; - BTRFS_I(inode)->location.objectid = BTRFS_FIRST_FREE_OBJECTID; - BTRFS_I(inode)->location.offset = 0; - fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize); if (!fs_info) { test_std_err(TEST_ALLOC_FS_INFO); @@ -835,10 +830,6 @@ static int test_hole_first(u32 sectorsize, u32 nodesize) return ret; } - BTRFS_I(inode)->location.type = BTRFS_INODE_ITEM_KEY; - BTRFS_I(inode)->location.objectid = BTRFS_FIRST_FREE_OBJECTID; - BTRFS_I(inode)->location.offset = 0; - fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize); if (!fs_info) { test_std_err(TEST_ALLOC_FS_INFO); @@ -983,7 +974,8 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) ret = clear_extent_bit(&BTRFS_I(inode)->io_tree, BTRFS_MAX_EXTENT_SIZE >> 1, (BTRFS_MAX_EXTENT_SIZE >> 1) + sectorsize - 1, - EXTENT_DELALLOC | EXTENT_UPTODATE, 0, 0, NULL); + EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | + EXTENT_UPTODATE, 0, 0, NULL); if (ret) { test_err("clear_extent_bit returned %d", ret); goto out; @@ -1050,7 +1042,8 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) ret = clear_extent_bit(&BTRFS_I(inode)->io_tree, BTRFS_MAX_EXTENT_SIZE + sectorsize, BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, - EXTENT_DELALLOC | EXTENT_UPTODATE, 0, 0, NULL); + EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | + EXTENT_UPTODATE, 0, 0, NULL); if (ret) { test_err("clear_extent_bit returned %d", ret); goto out; @@ -1082,7 +1075,8 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) /* Empty */ ret = clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1, - EXTENT_DELALLOC | EXTENT_UPTODATE, 0, 0, NULL); + EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | + EXTENT_UPTODATE, 0, 0, NULL); if (ret) { test_err("clear_extent_bit returned %d", ret); goto out; @@ -1097,7 +1091,8 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) out: if (ret) clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1, - EXTENT_DELALLOC | EXTENT_UPTODATE, 0, 0, NULL); + EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | + EXTENT_UPTODATE, 0, 0, NULL); iput(inode); btrfs_free_dummy_root(root); btrfs_free_dummy_fs_info(fs_info); diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c index ce1ca8e73c2d..f3137285a9e2 100644 --- a/fs/btrfs/tests/qgroup-tests.c +++ b/fs/btrfs/tests/qgroup-tests.c @@ -36,7 +36,6 @@ static int insert_normal_tree_ref(struct btrfs_root *root, u64 bytenr, return -ENOMEM; } - path->leave_spinning = 1; ret = btrfs_insert_empty_item(&trans, root, path, &ins, size); if (ret) { test_err("couldn't insert ref %d", ret); @@ -86,7 +85,6 @@ static int add_tree_ref(struct btrfs_root *root, u64 bytenr, u64 num_bytes, return -ENOMEM; } - path->leave_spinning = 1; ret = btrfs_search_slot(&trans, root, &key, path, 0, 1); if (ret) { test_err("couldn't find extent ref"); @@ -135,7 +133,6 @@ static int remove_extent_item(struct btrfs_root *root, u64 bytenr, test_std_err(TEST_ALLOC_ROOT); return -ENOMEM; } - path->leave_spinning = 1; ret = btrfs_search_slot(&trans, root, &key, path, -1, 1); if (ret) { @@ -170,7 +167,6 @@ static int remove_extent_ref(struct btrfs_root *root, u64 bytenr, return -ENOMEM; } - path->leave_spinning = 1; ret = btrfs_search_slot(&trans, root, &key, path, 0, 1); if (ret) { test_err("couldn't find extent ref"); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 52ada47aff50..acff6bb49a97 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -16,12 +16,12 @@ #include "transaction.h" #include "locking.h" #include "tree-log.h" -#include "inode-map.h" #include "volumes.h" #include "dev-replace.h" #include "qgroup.h" #include "block-group.h" #include "space-info.h" +#include "zoned.h" #define BTRFS_ROOT_TRANS_TAG 0 @@ -108,6 +108,11 @@ static const unsigned int btrfs_blocked_trans_types[TRANS_STATE_MAX] = { __TRANS_JOIN | __TRANS_JOIN_NOLOCK | __TRANS_JOIN_NOSTART), + [TRANS_STATE_SUPER_COMMITTED] = (__TRANS_START | + __TRANS_ATTACH | + __TRANS_JOIN | + __TRANS_JOIN_NOLOCK | + __TRANS_JOIN_NOSTART), [TRANS_STATE_COMPLETED] = (__TRANS_START | __TRANS_ATTACH | __TRANS_JOIN | @@ -155,6 +160,7 @@ static noinline void switch_commit_roots(struct btrfs_trans_handle *trans) struct btrfs_transaction *cur_trans = trans->transaction; struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_root *root, *tmp; + struct btrfs_caching_control *caching_ctl, *next; down_write(&fs_info->commit_root_sem); list_for_each_entry_safe(root, tmp, &cur_trans->switch_commits, @@ -162,8 +168,6 @@ static noinline void switch_commit_roots(struct btrfs_trans_handle *trans) list_del_init(&root->dirty_list); free_extent_buffer(root->commit_root); root->commit_root = btrfs_root_node(root); - if (is_fstree(root->root_key.objectid)) - btrfs_unpin_free_ino(root); extent_io_tree_release(&root->dirty_log_pages); btrfs_qgroup_clean_swapped_blocks(root); } @@ -180,6 +184,47 @@ static noinline void switch_commit_roots(struct btrfs_trans_handle *trans) spin_lock(&cur_trans->dropped_roots_lock); } spin_unlock(&cur_trans->dropped_roots_lock); + + /* + * We have to update the last_byte_to_unpin under the commit_root_sem, + * at the same time we swap out the commit roots. + * + * This is because we must have a real view of the last spot the caching + * kthreads were while caching. Consider the following views of the + * extent tree for a block group + * + * commit root + * +----+----+----+----+----+----+----+ + * |\\\\| |\\\\|\\\\| |\\\\|\\\\| + * +----+----+----+----+----+----+----+ + * 0 1 2 3 4 5 6 7 + * + * new commit root + * +----+----+----+----+----+----+----+ + * | | | |\\\\| | |\\\\| + * +----+----+----+----+----+----+----+ + * 0 1 2 3 4 5 6 7 + * + * If the cache_ctl->progress was at 3, then we are only allowed to + * unpin [0,1) and [2,3], because the caching thread has already + * processed those extents. We are not allowed to unpin [5,6), because + * the caching thread will re-start it's search from 3, and thus find + * the hole from [4,6) to add to the free space cache. + */ + spin_lock(&fs_info->block_group_cache_lock); + list_for_each_entry_safe(caching_ctl, next, + &fs_info->caching_block_groups, list) { + struct btrfs_block_group *cache = caching_ctl->block_group; + + if (btrfs_block_group_done(cache)) { + cache->last_byte_to_unpin = (u64)-1; + list_del_init(&caching_ctl->list); + btrfs_put_caching_control(caching_ctl); + } else { + cache->last_byte_to_unpin = caching_ctl->progress; + } + } + spin_unlock(&fs_info->block_group_cache_lock); up_write(&fs_info->commit_root_sem); } @@ -336,6 +381,8 @@ loop: spin_lock_init(&cur_trans->dirty_bgs_lock); INIT_LIST_HEAD(&cur_trans->deleted_bgs); spin_lock_init(&cur_trans->dropped_roots_lock); + INIT_LIST_HEAD(&cur_trans->releasing_ebs); + spin_lock_init(&cur_trans->releasing_ebs_lock); list_add_tail(&cur_trans->list, &fs_info->trans_list); extent_io_tree_init(fs_info, &cur_trans->dirty_pages, IO_TREE_TRANS_DIRTY_PAGES, fs_info->btree_inode); @@ -787,10 +834,11 @@ btrfs_attach_transaction_barrier(struct btrfs_root *root) return trans; } -/* wait for a transaction commit to be fully complete */ -static noinline void wait_for_commit(struct btrfs_transaction *commit) +/* Wait for a transaction commit to reach at least the given state. */ +static noinline void wait_for_commit(struct btrfs_transaction *commit, + const enum btrfs_trans_state min_state) { - wait_event(commit->commit_wait, commit->state == TRANS_STATE_COMPLETED); + wait_event(commit->commit_wait, commit->state >= min_state); } int btrfs_wait_for_commit(struct btrfs_fs_info *fs_info, u64 transid) @@ -845,7 +893,7 @@ int btrfs_wait_for_commit(struct btrfs_fs_info *fs_info, u64 transid) goto out; /* nothing committing|committed */ } - wait_for_commit(cur_trans); + wait_for_commit(cur_trans, TRANS_STATE_COMPLETED); btrfs_put_transaction(cur_trans); out: return ret; @@ -856,24 +904,23 @@ void btrfs_throttle(struct btrfs_fs_info *fs_info) wait_current_trans(fs_info); } -static int should_end_transaction(struct btrfs_trans_handle *trans) +static bool should_end_transaction(struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; if (btrfs_check_space_for_delayed_refs(fs_info)) - return 1; + return true; return !!btrfs_block_rsv_check(&fs_info->global_block_rsv, 5); } -int btrfs_should_end_transaction(struct btrfs_trans_handle *trans) +bool btrfs_should_end_transaction(struct btrfs_trans_handle *trans) { struct btrfs_transaction *cur_trans = trans->transaction; - smp_mb(); if (cur_trans->state >= TRANS_STATE_COMMIT_START || - cur_trans->delayed_refs.flushing) - return 1; + test_bit(BTRFS_DELAYED_REFS_FLUSHING, &cur_trans->delayed_refs.flags)) + return true; return should_end_transaction(trans); } @@ -1191,10 +1238,6 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans) if (ret) return ret; - ret = btrfs_run_delayed_refs(trans, (unsigned long)-1); - if (ret) - return ret; - ret = btrfs_run_dev_stats(trans); if (ret) return ret; @@ -1209,10 +1252,6 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans) if (ret) return ret; - /* run_qgroups might have added some more refs */ - ret = btrfs_run_delayed_refs(trans, (unsigned long)-1); - if (ret) - return ret; again: while (!list_empty(&fs_info->dirty_cowonly_roots)) { struct btrfs_root *root; @@ -1227,15 +1266,24 @@ again: ret = update_cowonly_root(trans, root); if (ret) return ret; - ret = btrfs_run_delayed_refs(trans, (unsigned long)-1); - if (ret) - return ret; } + /* Now flush any delayed refs generated by updating all of the roots */ + ret = btrfs_run_delayed_refs(trans, (unsigned long)-1); + if (ret) + return ret; + while (!list_empty(dirty_bgs) || !list_empty(io_bgs)) { ret = btrfs_write_dirty_block_groups(trans); if (ret) return ret; + + /* + * We're writing the dirty block groups, which could generate + * delayed refs, which could generate more dirty block groups, + * so we want to keep this flushing in this loop to make sure + * everything gets run. + */ ret = btrfs_run_delayed_refs(trans, (unsigned long)-1); if (ret) return ret; @@ -1280,7 +1328,6 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans) struct btrfs_root *gang[8]; int i; int ret; - int err = 0; spin_lock(&fs_info->fs_roots_radix_lock); while (1) { @@ -1292,6 +1339,8 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans) break; for (i = 0; i < ret; i++) { struct btrfs_root *root = gang[i]; + int ret2; + radix_tree_tag_clear(&fs_info->fs_roots_radix, (unsigned long)root->root_key.objectid, BTRFS_ROOT_TRANS_TAG); @@ -1300,8 +1349,6 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans) btrfs_free_log(trans, root); btrfs_update_reloc_root(trans, root); - btrfs_save_ino_cache(root, trans); - /* see comments in should_cow_block() */ clear_bit(BTRFS_ROOT_FORCE_COW, &root->state); smp_mb__after_atomic(); @@ -1313,17 +1360,17 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans) root->node); } - err = btrfs_update_root(trans, fs_info->tree_root, + ret2 = btrfs_update_root(trans, fs_info->tree_root, &root->root_key, &root->root_item); + if (ret2) + return ret2; spin_lock(&fs_info->fs_roots_radix_lock); - if (err) - break; btrfs_qgroup_free_meta_all_pertrans(root); } } spin_unlock(&fs_info->fs_roots_radix_lock); - return err; + return 0; } /* @@ -1396,6 +1443,23 @@ static int qgroup_account_snapshot(struct btrfs_trans_handle *trans, record_root_in_trans(trans, src, 1); /* + * btrfs_qgroup_inherit relies on a consistent view of the usage for the + * src root, so we must run the delayed refs here. + * + * However this isn't particularly fool proof, because there's no + * synchronization keeping us from changing the tree after this point + * before we do the qgroup_inherit, or even from making changes while + * we're doing the qgroup_inherit. But that's a problem for the future, + * for now flush the delayed refs to narrow the race window where the + * qgroup counters could end up wrong. + */ + ret = btrfs_run_delayed_refs(trans, (unsigned long)-1); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out; + } + + /* * We are going to commit transaction, see btrfs_commit_transaction() * comment for reason locking tree_log_mutex */ @@ -1488,7 +1552,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, ASSERT(pending->root_item); new_root_item = pending->root_item; - pending->error = btrfs_find_free_objectid(tree_root, &objectid); + pending->error = btrfs_get_free_objectid(tree_root, &objectid); if (pending->error) goto no_free_objectid; @@ -1598,8 +1662,6 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, goto fail; } - btrfs_set_lock_blocking_write(old); - ret = btrfs_copy_root(trans, root, old, &tmp, objectid); /* clean up in any case */ btrfs_tree_unlock(old); @@ -1650,12 +1712,6 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, goto fail; } - ret = btrfs_run_delayed_refs(trans, (unsigned long)-1); - if (ret) { - btrfs_abort_transaction(trans, ret); - goto fail; - } - /* * Do special qgroup accounting for snapshot, as we do some qgroup * snapshot hack to do fast snapshot. @@ -1681,7 +1737,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, dentry->d_name.len * 2); parent_inode->i_mtime = parent_inode->i_ctime = current_time(parent_inode); - ret = btrfs_update_inode_fallback(trans, parent_root, parent_inode); + ret = btrfs_update_inode_fallback(trans, parent_root, BTRFS_I(parent_inode)); if (ret) { btrfs_abort_transaction(trans, ret); goto fail; @@ -1703,12 +1759,6 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, } } - ret = btrfs_run_delayed_refs(trans, (unsigned long)-1); - if (ret) { - btrfs_abort_transaction(trans, ret); - goto fail; - } - fail: pending->error = ret; dir_item_existed: @@ -1761,6 +1811,8 @@ static void update_super_roots(struct btrfs_fs_info *fs_info) super->root_level = root_item->level; if (btrfs_test_opt(fs_info, SPACE_CACHE)) super->cache_generation = root_item->generation; + else if (test_bit(BTRFS_FS_CLEANUP_SPACE_CACHE_V1, &fs_info->flags)) + super->cache_generation = 0; if (test_bit(BTRFS_FS_UPDATE_UUID_TREE_GEN, &fs_info->flags)) super->uuid_tree_generation = root_item->generation; } @@ -1956,10 +2008,8 @@ static void btrfs_cleanup_pending_block_groups(struct btrfs_trans_handle *trans) } } -static inline int btrfs_start_delalloc_flush(struct btrfs_trans_handle *trans) +static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info) { - struct btrfs_fs_info *fs_info = trans->fs_info; - /* * We use writeback_inodes_sb here because if we used * btrfs_start_delalloc_roots we would deadlock with fs freeze. @@ -1969,50 +2019,15 @@ static inline int btrfs_start_delalloc_flush(struct btrfs_trans_handle *trans) * from already being in a transaction and our join_transaction doesn't * have to re-take the fs freeze lock. */ - if (btrfs_test_opt(fs_info, FLUSHONCOMMIT)) { + if (btrfs_test_opt(fs_info, FLUSHONCOMMIT)) writeback_inodes_sb(fs_info->sb, WB_REASON_SYNC); - } else { - struct btrfs_pending_snapshot *pending; - struct list_head *head = &trans->transaction->pending_snapshots; - - /* - * Flush dellaloc for any root that is going to be snapshotted. - * This is done to avoid a corrupted version of files, in the - * snapshots, that had both buffered and direct IO writes (even - * if they were done sequentially) due to an unordered update of - * the inode's size on disk. - */ - list_for_each_entry(pending, head, list) { - int ret; - - ret = btrfs_start_delalloc_snapshot(pending->root); - if (ret) - return ret; - } - } return 0; } -static inline void btrfs_wait_delalloc_flush(struct btrfs_trans_handle *trans) +static inline void btrfs_wait_delalloc_flush(struct btrfs_fs_info *fs_info) { - struct btrfs_fs_info *fs_info = trans->fs_info; - - if (btrfs_test_opt(fs_info, FLUSHONCOMMIT)) { + if (btrfs_test_opt(fs_info, FLUSHONCOMMIT)) btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1); - } else { - struct btrfs_pending_snapshot *pending; - struct list_head *head = &trans->transaction->pending_snapshots; - - /* - * Wait for any dellaloc that we started previously for the roots - * that are going to be snapshotted. This is to avoid a corrupted - * version of files in the snapshots that had both buffered and - * direct IO writes (even if they were done sequentially). - */ - list_for_each_entry(pending, head, list) - btrfs_wait_ordered_extents(pending->root, - U64_MAX, 0, U64_MAX); - } } int btrfs_commit_transaction(struct btrfs_trans_handle *trans) @@ -2042,32 +2057,25 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) btrfs_trans_release_metadata(trans); trans->block_rsv = NULL; - /* make a pass through all the delayed refs we have so far - * any runnings procs may add more while we are here - */ - ret = btrfs_run_delayed_refs(trans, 0); - if (ret) { - btrfs_end_transaction(trans); - return ret; - } - - cur_trans = trans->transaction; - /* - * set the flushing flag so procs in this transaction have to - * start sending their work down. + * We only want one transaction commit doing the flushing so we do not + * waste a bunch of time on lock contention on the extent root node. */ - cur_trans->delayed_refs.flushing = 1; - smp_wmb(); + if (!test_and_set_bit(BTRFS_DELAYED_REFS_FLUSHING, + &cur_trans->delayed_refs.flags)) { + /* + * Make a pass through all the delayed refs we have so far. + * Any running threads may add more while we are here. + */ + ret = btrfs_run_delayed_refs(trans, 0); + if (ret) { + btrfs_end_transaction(trans); + return ret; + } + } btrfs_create_pending_block_groups(trans); - ret = btrfs_run_delayed_refs(trans, 0); - if (ret) { - btrfs_end_transaction(trans); - return ret; - } - if (!test_bit(BTRFS_TRANS_DIRTY_BG_RUN, &cur_trans->flags)) { int run_it = 0; @@ -2101,11 +2109,15 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) spin_lock(&fs_info->trans_lock); if (cur_trans->state >= TRANS_STATE_COMMIT_START) { + enum btrfs_trans_state want_state = TRANS_STATE_COMPLETED; + spin_unlock(&fs_info->trans_lock); refcount_inc(&cur_trans->use_count); - ret = btrfs_end_transaction(trans); - wait_for_commit(cur_trans); + if (trans->in_fsync) + want_state = TRANS_STATE_SUPER_COMMITTED; + ret = btrfs_end_transaction(trans); + wait_for_commit(cur_trans, want_state); if (TRANS_ABORTED(cur_trans)) ret = cur_trans->aborted; @@ -2119,13 +2131,19 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) wake_up(&fs_info->transaction_blocked_wait); if (cur_trans->list.prev != &fs_info->trans_list) { + enum btrfs_trans_state want_state = TRANS_STATE_COMPLETED; + + if (trans->in_fsync) + want_state = TRANS_STATE_SUPER_COMMITTED; + prev_trans = list_entry(cur_trans->list.prev, struct btrfs_transaction, list); - if (prev_trans->state != TRANS_STATE_COMPLETED) { + if (prev_trans->state < want_state) { refcount_inc(&prev_trans->use_count); spin_unlock(&fs_info->trans_lock); - wait_for_commit(prev_trans); + wait_for_commit(prev_trans, want_state); + ret = READ_ONCE(prev_trans->aborted); btrfs_put_transaction(prev_trans); @@ -2150,7 +2168,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) extwriter_counter_dec(cur_trans, trans->type); - ret = btrfs_start_delalloc_flush(trans); + ret = btrfs_start_delalloc_flush(fs_info); if (ret) goto cleanup_transaction; @@ -2166,7 +2184,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) if (ret) goto cleanup_transaction; - btrfs_wait_delalloc_flush(trans); + btrfs_wait_delalloc_flush(fs_info); /* * Wait for all ordered extents started by a fast fsync that joined this @@ -2265,14 +2283,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) btrfs_free_log_root_tree(trans, fs_info); /* - * commit_fs_roots() can call btrfs_save_ino_cache(), which generates - * new delayed refs. Must handle them or qgroup can be wrong. - */ - ret = btrfs_run_delayed_refs(trans, (unsigned long)-1); - if (ret) - goto unlock_tree_log; - - /* * Since fs roots are all committed, we can get a quite accurate * new_roots. So let's do quota accounting. */ @@ -2293,8 +2303,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) goto unlock_tree_log; } - btrfs_prepare_extent_commit(fs_info); - cur_trans = fs_info->running_transaction; btrfs_set_root_node(&fs_info->tree_root->root_item, @@ -2345,6 +2353,13 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) goto scrub_continue; } + /* + * At this point, we should have written all the tree blocks allocated + * in this transaction. So it's now safe to free the redirtyied extent + * buffers. + */ + btrfs_free_redirty_list(cur_trans); + ret = write_all_supers(fs_info, 0); /* * the super is written, we can safely allow the tree-loggers @@ -2354,6 +2369,13 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) if (ret) goto scrub_continue; + /* + * We needn't acquire the lock here because there is no other task + * which can change it. + */ + cur_trans->state = TRANS_STATE_SUPER_COMMITTED; + wake_up(&cur_trans->commit_wait); + btrfs_finish_extent_commit(trans); if (test_bit(BTRFS_TRANS_HAVE_FREE_BGS, &cur_trans->flags)) @@ -2435,10 +2457,6 @@ int btrfs_clean_one_deleted_snapshot(struct btrfs_root *root) btrfs_debug(fs_info, "cleaner removing %llu", root->root_key.objectid); btrfs_kill_all_delayed_nodes(root); - if (root->ino_cache_inode) { - iput(root->ino_cache_inode); - root->ino_cache_inode = NULL; - } if (btrfs_header_backref_rev(root->node) < BTRFS_MIXED_BACKREF_REV) @@ -2459,16 +2477,6 @@ void btrfs_apply_pending_changes(struct btrfs_fs_info *fs_info) if (!prev) return; - bit = 1 << BTRFS_PENDING_SET_INODE_MAP_CACHE; - if (prev & bit) - btrfs_set_opt(fs_info->mount_opt, INODE_MAP_CACHE); - prev &= ~bit; - - bit = 1 << BTRFS_PENDING_CLEAR_INODE_MAP_CACHE; - if (prev & bit) - btrfs_clear_opt(fs_info->mount_opt, INODE_MAP_CACHE); - prev &= ~bit; - bit = 1 << BTRFS_PENDING_COMMIT; if (prev & bit) btrfs_debug(fs_info, "pending commit done"); diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 858d9153a1cd..6335716e513f 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -16,6 +16,7 @@ enum btrfs_trans_state { TRANS_STATE_COMMIT_START, TRANS_STATE_COMMIT_DOING, TRANS_STATE_UNBLOCKED, + TRANS_STATE_SUPER_COMMITTED, TRANS_STATE_COMPLETED, TRANS_STATE_MAX, }; @@ -92,6 +93,9 @@ struct btrfs_transaction { */ atomic_t pending_ordered; wait_queue_head_t pending_wait; + + spinlock_t releasing_ebs_lock; + struct list_head releasing_ebs; }; #define __TRANS_FREEZABLE (1U << 0) @@ -112,7 +116,6 @@ struct btrfs_transaction { #define TRANS_EXTWRITERS (__TRANS_START | __TRANS_ATTACH) #define BTRFS_SEND_TRANS_STUB ((void *)1) -#define BTRFS_DIO_SYNC_STUB ((void *)2) struct btrfs_trans_handle { u64 transid; @@ -134,6 +137,7 @@ struct btrfs_trans_handle { bool can_flush_pending_bgs; bool reloc_reserved; bool dirty; + bool in_fsync; struct btrfs_root *root; struct btrfs_fs_info *fs_info; struct list_head new_bgs; @@ -219,7 +223,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans); int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans, int wait_for_unblock); int btrfs_end_transaction_throttle(struct btrfs_trans_handle *trans); -int btrfs_should_end_transaction(struct btrfs_trans_handle *trans); +bool btrfs_should_end_transaction(struct btrfs_trans_handle *trans); void btrfs_throttle(struct btrfs_fs_info *fs_info); int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans, struct btrfs_root *root); diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index f0ffd5ee77bd..582061c7b547 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -100,7 +100,8 @@ static void file_extent_err(const struct extent_buffer *eb, int slot, */ #define CHECK_FE_ALIGNED(leaf, slot, fi, name, alignment) \ ({ \ - if (!IS_ALIGNED(btrfs_file_extent_##name((leaf), (fi)), (alignment))) \ + if (unlikely(!IS_ALIGNED(btrfs_file_extent_##name((leaf), (fi)), \ + (alignment)))) \ file_extent_err((leaf), (slot), \ "invalid %s for file extent, have %llu, should be aligned to %u", \ (#name), btrfs_file_extent_##name((leaf), (fi)), \ @@ -203,7 +204,7 @@ static int check_extent_data_item(struct extent_buffer *leaf, u32 item_size = btrfs_item_size_nr(leaf, slot); u64 extent_end; - if (!IS_ALIGNED(key->offset, sectorsize)) { + if (unlikely(!IS_ALIGNED(key->offset, sectorsize))) { file_extent_err(leaf, slot, "unaligned file_offset for file extent, have %llu should be aligned to %u", key->offset, sectorsize); @@ -216,7 +217,7 @@ static int check_extent_data_item(struct extent_buffer *leaf, * But if objectids mismatch, it means we have a missing * INODE_ITEM. */ - if (!check_prev_ino(leaf, key, slot, prev_key)) + if (unlikely(!check_prev_ino(leaf, key, slot, prev_key))) return -EUCLEAN; fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item); @@ -225,14 +226,15 @@ static int check_extent_data_item(struct extent_buffer *leaf, * Make sure the item contains at least inline header, so the file * extent type is not some garbage. */ - if (item_size < BTRFS_FILE_EXTENT_INLINE_DATA_START) { + if (unlikely(item_size < BTRFS_FILE_EXTENT_INLINE_DATA_START)) { file_extent_err(leaf, slot, "invalid item size, have %u expect [%zu, %u)", item_size, BTRFS_FILE_EXTENT_INLINE_DATA_START, SZ_4K); return -EUCLEAN; } - if (btrfs_file_extent_type(leaf, fi) >= BTRFS_NR_FILE_EXTENT_TYPES) { + if (unlikely(btrfs_file_extent_type(leaf, fi) >= + BTRFS_NR_FILE_EXTENT_TYPES)) { file_extent_err(leaf, slot, "invalid type for file extent, have %u expect range [0, %u]", btrfs_file_extent_type(leaf, fi), @@ -244,14 +246,15 @@ static int check_extent_data_item(struct extent_buffer *leaf, * Support for new compression/encryption must introduce incompat flag, * and must be caught in open_ctree(). */ - if (btrfs_file_extent_compression(leaf, fi) >= BTRFS_NR_COMPRESS_TYPES) { + if (unlikely(btrfs_file_extent_compression(leaf, fi) >= + BTRFS_NR_COMPRESS_TYPES)) { file_extent_err(leaf, slot, "invalid compression for file extent, have %u expect range [0, %u]", btrfs_file_extent_compression(leaf, fi), BTRFS_NR_COMPRESS_TYPES - 1); return -EUCLEAN; } - if (btrfs_file_extent_encryption(leaf, fi)) { + if (unlikely(btrfs_file_extent_encryption(leaf, fi))) { file_extent_err(leaf, slot, "invalid encryption for file extent, have %u expect 0", btrfs_file_extent_encryption(leaf, fi)); @@ -259,7 +262,7 @@ static int check_extent_data_item(struct extent_buffer *leaf, } if (btrfs_file_extent_type(leaf, fi) == BTRFS_FILE_EXTENT_INLINE) { /* Inline extent must have 0 as key offset */ - if (key->offset) { + if (unlikely(key->offset)) { file_extent_err(leaf, slot, "invalid file_offset for inline file extent, have %llu expect 0", key->offset); @@ -272,8 +275,8 @@ static int check_extent_data_item(struct extent_buffer *leaf, return 0; /* Uncompressed inline extent size must match item size */ - if (item_size != BTRFS_FILE_EXTENT_INLINE_DATA_START + - btrfs_file_extent_ram_bytes(leaf, fi)) { + if (unlikely(item_size != BTRFS_FILE_EXTENT_INLINE_DATA_START + + btrfs_file_extent_ram_bytes(leaf, fi))) { file_extent_err(leaf, slot, "invalid ram_bytes for uncompressed inline extent, have %u expect %llu", item_size, BTRFS_FILE_EXTENT_INLINE_DATA_START + @@ -284,22 +287,22 @@ static int check_extent_data_item(struct extent_buffer *leaf, } /* Regular or preallocated extent has fixed item size */ - if (item_size != sizeof(*fi)) { + if (unlikely(item_size != sizeof(*fi))) { file_extent_err(leaf, slot, "invalid item size for reg/prealloc file extent, have %u expect %zu", item_size, sizeof(*fi)); return -EUCLEAN; } - if (CHECK_FE_ALIGNED(leaf, slot, fi, ram_bytes, sectorsize) || - CHECK_FE_ALIGNED(leaf, slot, fi, disk_bytenr, sectorsize) || - CHECK_FE_ALIGNED(leaf, slot, fi, disk_num_bytes, sectorsize) || - CHECK_FE_ALIGNED(leaf, slot, fi, offset, sectorsize) || - CHECK_FE_ALIGNED(leaf, slot, fi, num_bytes, sectorsize)) + if (unlikely(CHECK_FE_ALIGNED(leaf, slot, fi, ram_bytes, sectorsize) || + CHECK_FE_ALIGNED(leaf, slot, fi, disk_bytenr, sectorsize) || + CHECK_FE_ALIGNED(leaf, slot, fi, disk_num_bytes, sectorsize) || + CHECK_FE_ALIGNED(leaf, slot, fi, offset, sectorsize) || + CHECK_FE_ALIGNED(leaf, slot, fi, num_bytes, sectorsize))) return -EUCLEAN; /* Catch extent end overflow */ - if (check_add_overflow(btrfs_file_extent_num_bytes(leaf, fi), - key->offset, &extent_end)) { + if (unlikely(check_add_overflow(btrfs_file_extent_num_bytes(leaf, fi), + key->offset, &extent_end))) { file_extent_err(leaf, slot, "extent end overflow, have file offset %llu extent num bytes %llu", key->offset, @@ -320,7 +323,7 @@ static int check_extent_data_item(struct extent_buffer *leaf, prev_fi = btrfs_item_ptr(leaf, slot - 1, struct btrfs_file_extent_item); prev_end = file_extent_end(leaf, prev_key, prev_fi); - if (prev_end > key->offset) { + if (unlikely(prev_end > key->offset)) { file_extent_err(leaf, slot - 1, "file extent end range (%llu) goes beyond start offset (%llu) of the next file extent", prev_end, key->offset); @@ -336,21 +339,21 @@ static int check_csum_item(struct extent_buffer *leaf, struct btrfs_key *key, { struct btrfs_fs_info *fs_info = leaf->fs_info; u32 sectorsize = fs_info->sectorsize; - u32 csumsize = btrfs_super_csum_size(fs_info->super_copy); + const u32 csumsize = fs_info->csum_size; - if (key->objectid != BTRFS_EXTENT_CSUM_OBJECTID) { + if (unlikely(key->objectid != BTRFS_EXTENT_CSUM_OBJECTID)) { generic_err(leaf, slot, "invalid key objectid for csum item, have %llu expect %llu", key->objectid, BTRFS_EXTENT_CSUM_OBJECTID); return -EUCLEAN; } - if (!IS_ALIGNED(key->offset, sectorsize)) { + if (unlikely(!IS_ALIGNED(key->offset, sectorsize))) { generic_err(leaf, slot, "unaligned key offset for csum item, have %llu should be aligned to %u", key->offset, sectorsize); return -EUCLEAN; } - if (!IS_ALIGNED(btrfs_item_size_nr(leaf, slot), csumsize)) { + if (unlikely(!IS_ALIGNED(btrfs_item_size_nr(leaf, slot), csumsize))) { generic_err(leaf, slot, "unaligned item size for csum item, have %u should be aligned to %u", btrfs_item_size_nr(leaf, slot), csumsize); @@ -363,7 +366,7 @@ static int check_csum_item(struct extent_buffer *leaf, struct btrfs_key *key, prev_item_size = btrfs_item_size_nr(leaf, slot - 1); prev_csum_end = (prev_item_size / csumsize) * sectorsize; prev_csum_end += prev_key->offset; - if (prev_csum_end > key->offset) { + if (unlikely(prev_csum_end > key->offset)) { generic_err(leaf, slot - 1, "csum end range (%llu) goes beyond the start range (%llu) of the next csum item", prev_csum_end, key->offset); @@ -388,15 +391,16 @@ static int check_inode_key(struct extent_buffer *leaf, struct btrfs_key *key, /* For XATTR_ITEM, location key should be all 0 */ if (item_key.type == BTRFS_XATTR_ITEM_KEY) { - if (key->type != 0 || key->objectid != 0 || key->offset != 0) + if (unlikely(key->objectid != 0 || key->type != 0 || + key->offset != 0)) return -EUCLEAN; return 0; } - if ((key->objectid < BTRFS_FIRST_FREE_OBJECTID || - key->objectid > BTRFS_LAST_FREE_OBJECTID) && - key->objectid != BTRFS_ROOT_TREE_DIR_OBJECTID && - key->objectid != BTRFS_FREE_INO_OBJECTID) { + if (unlikely((key->objectid < BTRFS_FIRST_FREE_OBJECTID || + key->objectid > BTRFS_LAST_FREE_OBJECTID) && + key->objectid != BTRFS_ROOT_TREE_DIR_OBJECTID && + key->objectid != BTRFS_FREE_INO_OBJECTID)) { if (is_inode_item) { generic_err(leaf, slot, "invalid key objectid: has %llu expect %llu or [%llu, %llu] or %llu", @@ -414,7 +418,7 @@ static int check_inode_key(struct extent_buffer *leaf, struct btrfs_key *key, } return -EUCLEAN; } - if (key->offset != 0) { + if (unlikely(key->offset != 0)) { if (is_inode_item) inode_item_err(leaf, slot, "invalid key offset: has %llu expect 0", @@ -438,7 +442,7 @@ static int check_root_key(struct extent_buffer *leaf, struct btrfs_key *key, is_root_item = (item_key.type == BTRFS_ROOT_ITEM_KEY); /* No such tree id */ - if (key->objectid == 0) { + if (unlikely(key->objectid == 0)) { if (is_root_item) generic_err(leaf, slot, "invalid root id 0"); else @@ -448,7 +452,7 @@ static int check_root_key(struct extent_buffer *leaf, struct btrfs_key *key, } /* DIR_ITEM/INDEX/INODE_REF is not allowed to point to non-fs trees */ - if (!is_fstree(key->objectid) && !is_root_item) { + if (unlikely(!is_fstree(key->objectid) && !is_root_item)) { dir_item_err(leaf, slot, "invalid location key objectid, have %llu expect [%llu, %llu]", key->objectid, BTRFS_FIRST_FREE_OBJECTID, @@ -464,7 +468,8 @@ static int check_root_key(struct extent_buffer *leaf, struct btrfs_key *key, * So here we only check offset for reloc tree whose key->offset must * be a valid tree. */ - if (key->objectid == BTRFS_TREE_RELOC_OBJECTID && key->offset == 0) { + if (unlikely(key->objectid == BTRFS_TREE_RELOC_OBJECTID && + key->offset == 0)) { generic_err(leaf, slot, "invalid root id 0 for reloc tree"); return -EUCLEAN; } @@ -480,8 +485,9 @@ static int check_dir_item(struct extent_buffer *leaf, u32 item_size = btrfs_item_size_nr(leaf, slot); u32 cur = 0; - if (!check_prev_ino(leaf, key, slot, prev_key)) + if (unlikely(!check_prev_ino(leaf, key, slot, prev_key))) return -EUCLEAN; + di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item); while (cur < item_size) { struct btrfs_key location_key; @@ -494,7 +500,7 @@ static int check_dir_item(struct extent_buffer *leaf, int ret; /* header itself should not cross item boundary */ - if (cur + sizeof(*di) > item_size) { + if (unlikely(cur + sizeof(*di) > item_size)) { dir_item_err(leaf, slot, "dir item header crosses item boundary, have %zu boundary %u", cur + sizeof(*di), item_size); @@ -505,12 +511,12 @@ static int check_dir_item(struct extent_buffer *leaf, btrfs_dir_item_key_to_cpu(leaf, di, &location_key); if (location_key.type == BTRFS_ROOT_ITEM_KEY) { ret = check_root_key(leaf, &location_key, slot); - if (ret < 0) + if (unlikely(ret < 0)) return ret; } else if (location_key.type == BTRFS_INODE_ITEM_KEY || location_key.type == 0) { ret = check_inode_key(leaf, &location_key, slot); - if (ret < 0) + if (unlikely(ret < 0)) return ret; } else { dir_item_err(leaf, slot, @@ -522,22 +528,22 @@ static int check_dir_item(struct extent_buffer *leaf, /* dir type check */ dir_type = btrfs_dir_type(leaf, di); - if (dir_type >= BTRFS_FT_MAX) { + if (unlikely(dir_type >= BTRFS_FT_MAX)) { dir_item_err(leaf, slot, "invalid dir item type, have %u expect [0, %u)", dir_type, BTRFS_FT_MAX); return -EUCLEAN; } - if (key->type == BTRFS_XATTR_ITEM_KEY && - dir_type != BTRFS_FT_XATTR) { + if (unlikely(key->type == BTRFS_XATTR_ITEM_KEY && + dir_type != BTRFS_FT_XATTR)) { dir_item_err(leaf, slot, "invalid dir item type for XATTR key, have %u expect %u", dir_type, BTRFS_FT_XATTR); return -EUCLEAN; } - if (dir_type == BTRFS_FT_XATTR && - key->type != BTRFS_XATTR_ITEM_KEY) { + if (unlikely(dir_type == BTRFS_FT_XATTR && + key->type != BTRFS_XATTR_ITEM_KEY)) { dir_item_err(leaf, slot, "xattr dir type found for non-XATTR key"); return -EUCLEAN; @@ -550,13 +556,13 @@ static int check_dir_item(struct extent_buffer *leaf, /* Name/data length check */ name_len = btrfs_dir_name_len(leaf, di); data_len = btrfs_dir_data_len(leaf, di); - if (name_len > max_name_len) { + if (unlikely(name_len > max_name_len)) { dir_item_err(leaf, slot, "dir item name len too long, have %u max %u", name_len, max_name_len); return -EUCLEAN; } - if (name_len + data_len > BTRFS_MAX_XATTR_SIZE(fs_info)) { + if (unlikely(name_len + data_len > BTRFS_MAX_XATTR_SIZE(fs_info))) { dir_item_err(leaf, slot, "dir item name and data len too long, have %u max %u", name_len + data_len, @@ -564,7 +570,7 @@ static int check_dir_item(struct extent_buffer *leaf, return -EUCLEAN; } - if (data_len && dir_type != BTRFS_FT_XATTR) { + if (unlikely(data_len && dir_type != BTRFS_FT_XATTR)) { dir_item_err(leaf, slot, "dir item with invalid data len, have %u expect 0", data_len); @@ -574,7 +580,7 @@ static int check_dir_item(struct extent_buffer *leaf, total_size = sizeof(*di) + name_len + data_len; /* header and name/data should not cross item boundary */ - if (cur + total_size > item_size) { + if (unlikely(cur + total_size > item_size)) { dir_item_err(leaf, slot, "dir item data crosses item boundary, have %u boundary %u", cur + total_size, item_size); @@ -592,7 +598,7 @@ static int check_dir_item(struct extent_buffer *leaf, read_extent_buffer(leaf, namebuf, (unsigned long)(di + 1), name_len); name_hash = btrfs_name_hash(namebuf, name_len); - if (key->offset != name_hash) { + if (unlikely(key->offset != name_hash)) { dir_item_err(leaf, slot, "name hash mismatch with key, have 0x%016x expect 0x%016llx", name_hash, key->offset); @@ -641,13 +647,13 @@ static int check_block_group_item(struct extent_buffer *leaf, * Here we don't really care about alignment since extent allocator can * handle it. We care more about the size. */ - if (key->offset == 0) { + if (unlikely(key->offset == 0)) { block_group_err(leaf, slot, "invalid block group size 0"); return -EUCLEAN; } - if (item_size != sizeof(bgi)) { + if (unlikely(item_size != sizeof(bgi))) { block_group_err(leaf, slot, "invalid item size, have %u expect %zu", item_size, sizeof(bgi)); @@ -656,8 +662,8 @@ static int check_block_group_item(struct extent_buffer *leaf, read_extent_buffer(leaf, &bgi, btrfs_item_ptr_offset(leaf, slot), sizeof(bgi)); - if (btrfs_stack_block_group_chunk_objectid(&bgi) != - BTRFS_FIRST_CHUNK_TREE_OBJECTID) { + if (unlikely(btrfs_stack_block_group_chunk_objectid(&bgi) != + BTRFS_FIRST_CHUNK_TREE_OBJECTID)) { block_group_err(leaf, slot, "invalid block group chunk objectid, have %llu expect %llu", btrfs_stack_block_group_chunk_objectid(&bgi), @@ -665,7 +671,7 @@ static int check_block_group_item(struct extent_buffer *leaf, return -EUCLEAN; } - if (btrfs_stack_block_group_used(&bgi) > key->offset) { + if (unlikely(btrfs_stack_block_group_used(&bgi) > key->offset)) { block_group_err(leaf, slot, "invalid block group used, have %llu expect [0, %llu)", btrfs_stack_block_group_used(&bgi), key->offset); @@ -673,7 +679,7 @@ static int check_block_group_item(struct extent_buffer *leaf, } flags = btrfs_stack_block_group_flags(&bgi); - if (hweight64(flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) > 1) { + if (unlikely(hweight64(flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) > 1)) { block_group_err(leaf, slot, "invalid profile flags, have 0x%llx (%lu bits set) expect no more than 1 bit set", flags & BTRFS_BLOCK_GROUP_PROFILE_MASK, @@ -682,11 +688,11 @@ static int check_block_group_item(struct extent_buffer *leaf, } type = flags & BTRFS_BLOCK_GROUP_TYPE_MASK; - if (type != BTRFS_BLOCK_GROUP_DATA && - type != BTRFS_BLOCK_GROUP_METADATA && - type != BTRFS_BLOCK_GROUP_SYSTEM && - type != (BTRFS_BLOCK_GROUP_METADATA | - BTRFS_BLOCK_GROUP_DATA)) { + if (unlikely(type != BTRFS_BLOCK_GROUP_DATA && + type != BTRFS_BLOCK_GROUP_METADATA && + type != BTRFS_BLOCK_GROUP_SYSTEM && + type != (BTRFS_BLOCK_GROUP_METADATA | + BTRFS_BLOCK_GROUP_DATA))) { block_group_err(leaf, slot, "invalid type, have 0x%llx (%lu bits set) expect either 0x%llx, 0x%llx, 0x%llx or 0x%llx", type, hweight64(type), @@ -754,50 +760,75 @@ int btrfs_check_chunk_valid(struct extent_buffer *leaf, { struct btrfs_fs_info *fs_info = leaf->fs_info; u64 length; + u64 chunk_end; u64 stripe_len; u16 num_stripes; u16 sub_stripes; u64 type; u64 features; bool mixed = false; + int raid_index; + int nparity; + int ncopies; length = btrfs_chunk_length(leaf, chunk); stripe_len = btrfs_chunk_stripe_len(leaf, chunk); num_stripes = btrfs_chunk_num_stripes(leaf, chunk); sub_stripes = btrfs_chunk_sub_stripes(leaf, chunk); type = btrfs_chunk_type(leaf, chunk); + raid_index = btrfs_bg_flags_to_raid_index(type); + ncopies = btrfs_raid_array[raid_index].ncopies; + nparity = btrfs_raid_array[raid_index].nparity; - if (!num_stripes) { + if (unlikely(!num_stripes)) { chunk_err(leaf, chunk, logical, "invalid chunk num_stripes, have %u", num_stripes); return -EUCLEAN; } - if (!IS_ALIGNED(logical, fs_info->sectorsize)) { + if (unlikely(num_stripes < ncopies)) { + chunk_err(leaf, chunk, logical, + "invalid chunk num_stripes < ncopies, have %u < %d", + num_stripes, ncopies); + return -EUCLEAN; + } + if (unlikely(nparity && num_stripes == nparity)) { + chunk_err(leaf, chunk, logical, + "invalid chunk num_stripes == nparity, have %u == %d", + num_stripes, nparity); + return -EUCLEAN; + } + if (unlikely(!IS_ALIGNED(logical, fs_info->sectorsize))) { chunk_err(leaf, chunk, logical, "invalid chunk logical, have %llu should aligned to %u", logical, fs_info->sectorsize); return -EUCLEAN; } - if (btrfs_chunk_sector_size(leaf, chunk) != fs_info->sectorsize) { + if (unlikely(btrfs_chunk_sector_size(leaf, chunk) != fs_info->sectorsize)) { chunk_err(leaf, chunk, logical, "invalid chunk sectorsize, have %u expect %u", btrfs_chunk_sector_size(leaf, chunk), fs_info->sectorsize); return -EUCLEAN; } - if (!length || !IS_ALIGNED(length, fs_info->sectorsize)) { + if (unlikely(!length || !IS_ALIGNED(length, fs_info->sectorsize))) { chunk_err(leaf, chunk, logical, "invalid chunk length, have %llu", length); return -EUCLEAN; } - if (!is_power_of_2(stripe_len) || stripe_len != BTRFS_STRIPE_LEN) { + if (unlikely(check_add_overflow(logical, length, &chunk_end))) { + chunk_err(leaf, chunk, logical, +"invalid chunk logical start and length, have logical start %llu length %llu", + logical, length); + return -EUCLEAN; + } + if (unlikely(!is_power_of_2(stripe_len) || stripe_len != BTRFS_STRIPE_LEN)) { chunk_err(leaf, chunk, logical, "invalid chunk stripe length: %llu", stripe_len); return -EUCLEAN; } - if (~(BTRFS_BLOCK_GROUP_TYPE_MASK | BTRFS_BLOCK_GROUP_PROFILE_MASK) & - type) { + if (unlikely(type & ~(BTRFS_BLOCK_GROUP_TYPE_MASK | + BTRFS_BLOCK_GROUP_PROFILE_MASK))) { chunk_err(leaf, chunk, logical, "unrecognized chunk type: 0x%llx", ~(BTRFS_BLOCK_GROUP_TYPE_MASK | @@ -806,22 +837,23 @@ int btrfs_check_chunk_valid(struct extent_buffer *leaf, return -EUCLEAN; } - if (!has_single_bit_set(type & BTRFS_BLOCK_GROUP_PROFILE_MASK) && - (type & BTRFS_BLOCK_GROUP_PROFILE_MASK) != 0) { + if (unlikely(!has_single_bit_set(type & BTRFS_BLOCK_GROUP_PROFILE_MASK) && + (type & BTRFS_BLOCK_GROUP_PROFILE_MASK) != 0)) { chunk_err(leaf, chunk, logical, "invalid chunk profile flag: 0x%llx, expect 0 or 1 bit set", type & BTRFS_BLOCK_GROUP_PROFILE_MASK); return -EUCLEAN; } - if ((type & BTRFS_BLOCK_GROUP_TYPE_MASK) == 0) { + if (unlikely((type & BTRFS_BLOCK_GROUP_TYPE_MASK) == 0)) { chunk_err(leaf, chunk, logical, "missing chunk type flag, have 0x%llx one bit must be set in 0x%llx", type, BTRFS_BLOCK_GROUP_TYPE_MASK); return -EUCLEAN; } - if ((type & BTRFS_BLOCK_GROUP_SYSTEM) && - (type & (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA))) { + if (unlikely((type & BTRFS_BLOCK_GROUP_SYSTEM) && + (type & (BTRFS_BLOCK_GROUP_METADATA | + BTRFS_BLOCK_GROUP_DATA)))) { chunk_err(leaf, chunk, logical, "system chunk with data or metadata type: 0x%llx", type); @@ -833,20 +865,21 @@ int btrfs_check_chunk_valid(struct extent_buffer *leaf, mixed = true; if (!mixed) { - if ((type & BTRFS_BLOCK_GROUP_METADATA) && - (type & BTRFS_BLOCK_GROUP_DATA)) { + if (unlikely((type & BTRFS_BLOCK_GROUP_METADATA) && + (type & BTRFS_BLOCK_GROUP_DATA))) { chunk_err(leaf, chunk, logical, "mixed chunk type in non-mixed mode: 0x%llx", type); return -EUCLEAN; } } - if ((type & BTRFS_BLOCK_GROUP_RAID10 && sub_stripes != 2) || - (type & BTRFS_BLOCK_GROUP_RAID1 && num_stripes != 2) || - (type & BTRFS_BLOCK_GROUP_RAID5 && num_stripes < 2) || - (type & BTRFS_BLOCK_GROUP_RAID6 && num_stripes < 3) || - (type & BTRFS_BLOCK_GROUP_DUP && num_stripes != 2) || - ((type & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0 && num_stripes != 1)) { + if (unlikely((type & BTRFS_BLOCK_GROUP_RAID10 && sub_stripes != 2) || + (type & BTRFS_BLOCK_GROUP_RAID1 && num_stripes != 2) || + (type & BTRFS_BLOCK_GROUP_RAID5 && num_stripes < 2) || + (type & BTRFS_BLOCK_GROUP_RAID6 && num_stripes < 3) || + (type & BTRFS_BLOCK_GROUP_DUP && num_stripes != 2) || + ((type & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0 && + num_stripes != 1))) { chunk_err(leaf, chunk, logical, "invalid num_stripes:sub_stripes %u:%u for profile %llu", num_stripes, sub_stripes, @@ -869,7 +902,7 @@ static int check_leaf_chunk_item(struct extent_buffer *leaf, { int num_stripes; - if (btrfs_item_size_nr(leaf, slot) < sizeof(struct btrfs_chunk)) { + if (unlikely(btrfs_item_size_nr(leaf, slot) < sizeof(struct btrfs_chunk))) { chunk_err(leaf, chunk, key->offset, "invalid chunk item size: have %u expect [%zu, %u)", btrfs_item_size_nr(leaf, slot), @@ -883,8 +916,8 @@ static int check_leaf_chunk_item(struct extent_buffer *leaf, if (num_stripes == 0) goto out; - if (btrfs_chunk_item_size(num_stripes) != - btrfs_item_size_nr(leaf, slot)) { + if (unlikely(btrfs_chunk_item_size(num_stripes) != + btrfs_item_size_nr(leaf, slot))) { chunk_err(leaf, chunk, key->offset, "invalid chunk item size: have %u expect %lu", btrfs_item_size_nr(leaf, slot), @@ -923,14 +956,14 @@ static int check_dev_item(struct extent_buffer *leaf, { struct btrfs_dev_item *ditem; - if (key->objectid != BTRFS_DEV_ITEMS_OBJECTID) { + if (unlikely(key->objectid != BTRFS_DEV_ITEMS_OBJECTID)) { dev_item_err(leaf, slot, "invalid objectid: has=%llu expect=%llu", key->objectid, BTRFS_DEV_ITEMS_OBJECTID); return -EUCLEAN; } ditem = btrfs_item_ptr(leaf, slot, struct btrfs_dev_item); - if (btrfs_device_id(leaf, ditem) != key->offset) { + if (unlikely(btrfs_device_id(leaf, ditem) != key->offset)) { dev_item_err(leaf, slot, "devid mismatch: key has=%llu item has=%llu", key->offset, btrfs_device_id(leaf, ditem)); @@ -942,8 +975,8 @@ static int check_dev_item(struct extent_buffer *leaf, * it can be 0 for device removal. Device size check can only be done * by dev extents check. */ - if (btrfs_device_bytes_used(leaf, ditem) > - btrfs_device_total_bytes(leaf, ditem)) { + if (unlikely(btrfs_device_bytes_used(leaf, ditem) > + btrfs_device_total_bytes(leaf, ditem))) { dev_item_err(leaf, slot, "invalid bytes used: have %llu expect [0, %llu]", btrfs_device_bytes_used(leaf, ditem), @@ -968,13 +1001,13 @@ static int check_inode_item(struct extent_buffer *leaf, int ret; ret = check_inode_key(leaf, key, slot); - if (ret < 0) + if (unlikely(ret < 0)) return ret; iitem = btrfs_item_ptr(leaf, slot, struct btrfs_inode_item); /* Here we use super block generation + 1 to handle log tree */ - if (btrfs_inode_generation(leaf, iitem) > super_gen + 1) { + if (unlikely(btrfs_inode_generation(leaf, iitem) > super_gen + 1)) { inode_item_err(leaf, slot, "invalid inode generation: has %llu expect (0, %llu]", btrfs_inode_generation(leaf, iitem), @@ -982,7 +1015,7 @@ static int check_inode_item(struct extent_buffer *leaf, return -EUCLEAN; } /* Note for ROOT_TREE_DIR_ITEM, mkfs could set its transid 0 */ - if (btrfs_inode_transid(leaf, iitem) > super_gen + 1) { + if (unlikely(btrfs_inode_transid(leaf, iitem) > super_gen + 1)) { inode_item_err(leaf, slot, "invalid inode transid: has %llu expect [0, %llu]", btrfs_inode_transid(leaf, iitem), super_gen + 1); @@ -995,7 +1028,7 @@ static int check_inode_item(struct extent_buffer *leaf, * anything in the fs. So here we skip the check. */ mode = btrfs_inode_mode(leaf, iitem); - if (mode & ~valid_mask) { + if (unlikely(mode & ~valid_mask)) { inode_item_err(leaf, slot, "unknown mode bit detected: 0x%x", mode & ~valid_mask); @@ -1008,20 +1041,20 @@ static int check_inode_item(struct extent_buffer *leaf, * FIFO/CHR/DIR/REG. Only needs to check BLK, LNK and SOCKS */ if (!has_single_bit_set(mode & S_IFMT)) { - if (!S_ISLNK(mode) && !S_ISBLK(mode) && !S_ISSOCK(mode)) { + if (unlikely(!S_ISLNK(mode) && !S_ISBLK(mode) && !S_ISSOCK(mode))) { inode_item_err(leaf, slot, "invalid mode: has 0%o expect valid S_IF* bit(s)", mode & S_IFMT); return -EUCLEAN; } } - if (S_ISDIR(mode) && btrfs_inode_nlink(leaf, iitem) > 1) { + if (unlikely(S_ISDIR(mode) && btrfs_inode_nlink(leaf, iitem) > 1)) { inode_item_err(leaf, slot, "invalid nlink: has %u expect no more than 1 for dir", btrfs_inode_nlink(leaf, iitem)); return -EUCLEAN; } - if (btrfs_inode_flags(leaf, iitem) & ~BTRFS_INODE_FLAG_MASK) { + if (unlikely(btrfs_inode_flags(leaf, iitem) & ~BTRFS_INODE_FLAG_MASK)) { inode_item_err(leaf, slot, "unknown flags detected: 0x%llx", btrfs_inode_flags(leaf, iitem) & @@ -1041,15 +1074,17 @@ static int check_root_item(struct extent_buffer *leaf, struct btrfs_key *key, int ret; ret = check_root_key(leaf, key, slot); - if (ret < 0) + if (unlikely(ret < 0)) return ret; - if (btrfs_item_size_nr(leaf, slot) != sizeof(ri) && - btrfs_item_size_nr(leaf, slot) != btrfs_legacy_root_item_size()) { + if (unlikely(btrfs_item_size_nr(leaf, slot) != sizeof(ri) && + btrfs_item_size_nr(leaf, slot) != + btrfs_legacy_root_item_size())) { generic_err(leaf, slot, "invalid root item size, have %u expect %zu or %u", btrfs_item_size_nr(leaf, slot), sizeof(ri), btrfs_legacy_root_item_size()); + return -EUCLEAN; } /* @@ -1061,24 +1096,24 @@ static int check_root_item(struct extent_buffer *leaf, struct btrfs_key *key, btrfs_item_size_nr(leaf, slot)); /* Generation related */ - if (btrfs_root_generation(&ri) > - btrfs_super_generation(fs_info->super_copy) + 1) { + if (unlikely(btrfs_root_generation(&ri) > + btrfs_super_generation(fs_info->super_copy) + 1)) { generic_err(leaf, slot, "invalid root generation, have %llu expect (0, %llu]", btrfs_root_generation(&ri), btrfs_super_generation(fs_info->super_copy) + 1); return -EUCLEAN; } - if (btrfs_root_generation_v2(&ri) > - btrfs_super_generation(fs_info->super_copy) + 1) { + if (unlikely(btrfs_root_generation_v2(&ri) > + btrfs_super_generation(fs_info->super_copy) + 1)) { generic_err(leaf, slot, "invalid root v2 generation, have %llu expect (0, %llu]", btrfs_root_generation_v2(&ri), btrfs_super_generation(fs_info->super_copy) + 1); return -EUCLEAN; } - if (btrfs_root_last_snapshot(&ri) > - btrfs_super_generation(fs_info->super_copy) + 1) { + if (unlikely(btrfs_root_last_snapshot(&ri) > + btrfs_super_generation(fs_info->super_copy) + 1)) { generic_err(leaf, slot, "invalid root last_snapshot, have %llu expect (0, %llu]", btrfs_root_last_snapshot(&ri), @@ -1087,27 +1122,27 @@ static int check_root_item(struct extent_buffer *leaf, struct btrfs_key *key, } /* Alignment and level check */ - if (!IS_ALIGNED(btrfs_root_bytenr(&ri), fs_info->sectorsize)) { + if (unlikely(!IS_ALIGNED(btrfs_root_bytenr(&ri), fs_info->sectorsize))) { generic_err(leaf, slot, "invalid root bytenr, have %llu expect to be aligned to %u", btrfs_root_bytenr(&ri), fs_info->sectorsize); return -EUCLEAN; } - if (btrfs_root_level(&ri) >= BTRFS_MAX_LEVEL) { + if (unlikely(btrfs_root_level(&ri) >= BTRFS_MAX_LEVEL)) { generic_err(leaf, slot, "invalid root level, have %u expect [0, %u]", btrfs_root_level(&ri), BTRFS_MAX_LEVEL - 1); return -EUCLEAN; } - if (ri.drop_level >= BTRFS_MAX_LEVEL) { + if (unlikely(btrfs_root_drop_level(&ri) >= BTRFS_MAX_LEVEL)) { generic_err(leaf, slot, "invalid root level, have %u expect [0, %u]", - ri.drop_level, BTRFS_MAX_LEVEL - 1); + btrfs_root_drop_level(&ri), BTRFS_MAX_LEVEL - 1); return -EUCLEAN; } /* Flags check */ - if (btrfs_root_flags(&ri) & ~valid_root_flags) { + if (unlikely(btrfs_root_flags(&ri) & ~valid_root_flags)) { generic_err(leaf, slot, "invalid root flags, have 0x%llx expect mask 0x%llx", btrfs_root_flags(&ri), valid_root_flags); @@ -1161,14 +1196,14 @@ static int check_extent_item(struct extent_buffer *leaf, u64 total_refs; /* Total refs in btrfs_extent_item */ u64 inline_refs = 0; /* found total inline refs */ - if (key->type == BTRFS_METADATA_ITEM_KEY && - !btrfs_fs_incompat(fs_info, SKINNY_METADATA)) { + if (unlikely(key->type == BTRFS_METADATA_ITEM_KEY && + !btrfs_fs_incompat(fs_info, SKINNY_METADATA))) { generic_err(leaf, slot, "invalid key type, METADATA_ITEM type invalid when SKINNY_METADATA feature disabled"); return -EUCLEAN; } /* key->objectid is the bytenr for both key types */ - if (!IS_ALIGNED(key->objectid, fs_info->sectorsize)) { + if (unlikely(!IS_ALIGNED(key->objectid, fs_info->sectorsize))) { generic_err(leaf, slot, "invalid key objectid, have %llu expect to be aligned to %u", key->objectid, fs_info->sectorsize); @@ -1176,8 +1211,8 @@ static int check_extent_item(struct extent_buffer *leaf, } /* key->offset is tree level for METADATA_ITEM_KEY */ - if (key->type == BTRFS_METADATA_ITEM_KEY && - key->offset >= BTRFS_MAX_LEVEL) { + if (unlikely(key->type == BTRFS_METADATA_ITEM_KEY && + key->offset >= BTRFS_MAX_LEVEL)) { extent_err(leaf, slot, "invalid tree level, have %llu expect [0, %u]", key->offset, BTRFS_MAX_LEVEL - 1); @@ -1203,7 +1238,7 @@ static int check_extent_item(struct extent_buffer *leaf, * Either using btrfs_extent_inline_ref::offset, or specific * data structure. */ - if (item_size < sizeof(*ei)) { + if (unlikely(item_size < sizeof(*ei))) { extent_err(leaf, slot, "invalid item size, have %u expect [%zu, %u)", item_size, sizeof(*ei), @@ -1217,15 +1252,16 @@ static int check_extent_item(struct extent_buffer *leaf, flags = btrfs_extent_flags(leaf, ei); total_refs = btrfs_extent_refs(leaf, ei); generation = btrfs_extent_generation(leaf, ei); - if (generation > btrfs_super_generation(fs_info->super_copy) + 1) { + if (unlikely(generation > + btrfs_super_generation(fs_info->super_copy) + 1)) { extent_err(leaf, slot, "invalid generation, have %llu expect (0, %llu]", generation, btrfs_super_generation(fs_info->super_copy) + 1); return -EUCLEAN; } - if (!has_single_bit_set(flags & (BTRFS_EXTENT_FLAG_DATA | - BTRFS_EXTENT_FLAG_TREE_BLOCK))) { + if (unlikely(!has_single_bit_set(flags & (BTRFS_EXTENT_FLAG_DATA | + BTRFS_EXTENT_FLAG_TREE_BLOCK)))) { extent_err(leaf, slot, "invalid extent flag, have 0x%llx expect 1 bit set in 0x%llx", flags, BTRFS_EXTENT_FLAG_DATA | @@ -1234,21 +1270,21 @@ static int check_extent_item(struct extent_buffer *leaf, } is_tree_block = !!(flags & BTRFS_EXTENT_FLAG_TREE_BLOCK); if (is_tree_block) { - if (key->type == BTRFS_EXTENT_ITEM_KEY && - key->offset != fs_info->nodesize) { + if (unlikely(key->type == BTRFS_EXTENT_ITEM_KEY && + key->offset != fs_info->nodesize)) { extent_err(leaf, slot, "invalid extent length, have %llu expect %u", key->offset, fs_info->nodesize); return -EUCLEAN; } } else { - if (key->type != BTRFS_EXTENT_ITEM_KEY) { + if (unlikely(key->type != BTRFS_EXTENT_ITEM_KEY)) { extent_err(leaf, slot, "invalid key type, have %u expect %u for data backref", key->type, BTRFS_EXTENT_ITEM_KEY); return -EUCLEAN; } - if (!IS_ALIGNED(key->offset, fs_info->sectorsize)) { + if (unlikely(!IS_ALIGNED(key->offset, fs_info->sectorsize))) { extent_err(leaf, slot, "invalid extent length, have %llu expect aligned to %u", key->offset, fs_info->sectorsize); @@ -1262,7 +1298,7 @@ static int check_extent_item(struct extent_buffer *leaf, struct btrfs_tree_block_info *info; info = (struct btrfs_tree_block_info *)ptr; - if (btrfs_tree_block_level(leaf, info) >= BTRFS_MAX_LEVEL) { + if (unlikely(btrfs_tree_block_level(leaf, info) >= BTRFS_MAX_LEVEL)) { extent_err(leaf, slot, "invalid tree block info level, have %u expect [0, %u]", btrfs_tree_block_level(leaf, info), @@ -1281,7 +1317,7 @@ static int check_extent_item(struct extent_buffer *leaf, u64 inline_offset; u8 inline_type; - if (ptr + sizeof(*iref) > end) { + if (unlikely(ptr + sizeof(*iref) > end)) { extent_err(leaf, slot, "inline ref item overflows extent item, ptr %lu iref size %zu end %lu", ptr, sizeof(*iref), end); @@ -1290,7 +1326,7 @@ static int check_extent_item(struct extent_buffer *leaf, iref = (struct btrfs_extent_inline_ref *)ptr; inline_type = btrfs_extent_inline_ref_type(leaf, iref); inline_offset = btrfs_extent_inline_ref_offset(leaf, iref); - if (ptr + btrfs_extent_inline_ref_size(inline_type) > end) { + if (unlikely(ptr + btrfs_extent_inline_ref_size(inline_type) > end)) { extent_err(leaf, slot, "inline ref item overflows extent item, ptr %lu iref size %u end %lu", ptr, inline_type, end); @@ -1304,7 +1340,8 @@ static int check_extent_item(struct extent_buffer *leaf, break; /* Contains parent bytenr */ case BTRFS_SHARED_BLOCK_REF_KEY: - if (!IS_ALIGNED(inline_offset, fs_info->sectorsize)) { + if (unlikely(!IS_ALIGNED(inline_offset, + fs_info->sectorsize))) { extent_err(leaf, slot, "invalid tree parent bytenr, have %llu expect aligned to %u", inline_offset, fs_info->sectorsize); @@ -1319,7 +1356,8 @@ static int check_extent_item(struct extent_buffer *leaf, case BTRFS_EXTENT_DATA_REF_KEY: dref = (struct btrfs_extent_data_ref *)(&iref->offset); dref_offset = btrfs_extent_data_ref_offset(leaf, dref); - if (!IS_ALIGNED(dref_offset, fs_info->sectorsize)) { + if (unlikely(!IS_ALIGNED(dref_offset, + fs_info->sectorsize))) { extent_err(leaf, slot, "invalid data ref offset, have %llu expect aligned to %u", dref_offset, fs_info->sectorsize); @@ -1330,7 +1368,8 @@ static int check_extent_item(struct extent_buffer *leaf, /* Contains parent bytenr and ref count */ case BTRFS_SHARED_DATA_REF_KEY: sref = (struct btrfs_shared_data_ref *)(iref + 1); - if (!IS_ALIGNED(inline_offset, fs_info->sectorsize)) { + if (unlikely(!IS_ALIGNED(inline_offset, + fs_info->sectorsize))) { extent_err(leaf, slot, "invalid data parent bytenr, have %llu expect aligned to %u", inline_offset, fs_info->sectorsize); @@ -1346,14 +1385,14 @@ static int check_extent_item(struct extent_buffer *leaf, ptr += btrfs_extent_inline_ref_size(inline_type); } /* No padding is allowed */ - if (ptr != end) { + if (unlikely(ptr != end)) { extent_err(leaf, slot, "invalid extent item size, padding bytes found"); return -EUCLEAN; } /* Finally, check the inline refs against total refs */ - if (inline_refs > total_refs) { + if (unlikely(inline_refs > total_refs)) { extent_err(leaf, slot, "invalid extent refs, have %llu expect >= inline %llu", total_refs, inline_refs); @@ -1370,21 +1409,21 @@ static int check_simple_keyed_refs(struct extent_buffer *leaf, if (key->type == BTRFS_SHARED_DATA_REF_KEY) expect_item_size = sizeof(struct btrfs_shared_data_ref); - if (btrfs_item_size_nr(leaf, slot) != expect_item_size) { + if (unlikely(btrfs_item_size_nr(leaf, slot) != expect_item_size)) { generic_err(leaf, slot, "invalid item size, have %u expect %u for key type %u", btrfs_item_size_nr(leaf, slot), expect_item_size, key->type); return -EUCLEAN; } - if (!IS_ALIGNED(key->objectid, leaf->fs_info->sectorsize)) { + if (unlikely(!IS_ALIGNED(key->objectid, leaf->fs_info->sectorsize))) { generic_err(leaf, slot, "invalid key objectid for shared block ref, have %llu expect aligned to %u", key->objectid, leaf->fs_info->sectorsize); return -EUCLEAN; } - if (key->type != BTRFS_TREE_BLOCK_REF_KEY && - !IS_ALIGNED(key->offset, leaf->fs_info->sectorsize)) { + if (unlikely(key->type != BTRFS_TREE_BLOCK_REF_KEY && + !IS_ALIGNED(key->offset, leaf->fs_info->sectorsize))) { extent_err(leaf, slot, "invalid tree parent bytenr, have %llu expect aligned to %u", key->offset, leaf->fs_info->sectorsize); @@ -1400,13 +1439,14 @@ static int check_extent_data_ref(struct extent_buffer *leaf, unsigned long ptr = btrfs_item_ptr_offset(leaf, slot); const unsigned long end = ptr + btrfs_item_size_nr(leaf, slot); - if (btrfs_item_size_nr(leaf, slot) % sizeof(*dref) != 0) { + if (unlikely(btrfs_item_size_nr(leaf, slot) % sizeof(*dref) != 0)) { generic_err(leaf, slot, "invalid item size, have %u expect aligned to %zu for key type %u", btrfs_item_size_nr(leaf, slot), sizeof(*dref), key->type); + return -EUCLEAN; } - if (!IS_ALIGNED(key->objectid, leaf->fs_info->sectorsize)) { + if (unlikely(!IS_ALIGNED(key->objectid, leaf->fs_info->sectorsize))) { generic_err(leaf, slot, "invalid key objectid for shared block ref, have %llu expect aligned to %u", key->objectid, leaf->fs_info->sectorsize); @@ -1423,16 +1463,17 @@ static int check_extent_data_ref(struct extent_buffer *leaf, owner = btrfs_extent_data_ref_objectid(leaf, dref); offset = btrfs_extent_data_ref_offset(leaf, dref); hash = hash_extent_data_ref(root_objectid, owner, offset); - if (hash != key->offset) { + if (unlikely(hash != key->offset)) { extent_err(leaf, slot, "invalid extent data ref hash, item has 0x%016llx key has 0x%016llx", hash, key->offset); return -EUCLEAN; } - if (!IS_ALIGNED(offset, leaf->fs_info->sectorsize)) { + if (unlikely(!IS_ALIGNED(offset, leaf->fs_info->sectorsize))) { extent_err(leaf, slot, "invalid extent data backref offset, have %llu expect aligned to %u", offset, leaf->fs_info->sectorsize); + return -EUCLEAN; } } return 0; @@ -1448,10 +1489,10 @@ static int check_inode_ref(struct extent_buffer *leaf, unsigned long ptr; unsigned long end; - if (!check_prev_ino(leaf, key, slot, prev_key)) + if (unlikely(!check_prev_ino(leaf, key, slot, prev_key))) return -EUCLEAN; /* namelen can't be 0, so item_size == sizeof() is also invalid */ - if (btrfs_item_size_nr(leaf, slot) <= sizeof(*iref)) { + if (unlikely(btrfs_item_size_nr(leaf, slot) <= sizeof(*iref))) { inode_ref_err(leaf, slot, "invalid item size, have %u expect (%zu, %u)", btrfs_item_size_nr(leaf, slot), @@ -1464,7 +1505,7 @@ static int check_inode_ref(struct extent_buffer *leaf, while (ptr < end) { u16 namelen; - if (ptr + sizeof(iref) > end) { + if (unlikely(ptr + sizeof(iref) > end)) { inode_ref_err(leaf, slot, "inode ref overflow, ptr %lu end %lu inode_ref_size %zu", ptr, end, sizeof(iref)); @@ -1473,7 +1514,7 @@ static int check_inode_ref(struct extent_buffer *leaf, iref = (struct btrfs_inode_ref *)ptr; namelen = btrfs_inode_ref_name_len(leaf, iref); - if (ptr + sizeof(*iref) + namelen > end) { + if (unlikely(ptr + sizeof(*iref) + namelen > end)) { inode_ref_err(leaf, slot, "inode ref overflow, ptr %lu end %lu namelen %u", ptr, end, namelen); @@ -1556,7 +1597,7 @@ static int check_leaf(struct extent_buffer *leaf, bool check_item_data) u32 nritems = btrfs_header_nritems(leaf); int slot; - if (btrfs_header_level(leaf) != 0) { + if (unlikely(btrfs_header_level(leaf) != 0)) { generic_err(leaf, 0, "invalid level for leaf, have %d expect 0", btrfs_header_level(leaf)); @@ -1575,19 +1616,19 @@ static int check_leaf(struct extent_buffer *leaf, bool check_item_data) u64 owner = btrfs_header_owner(leaf); /* These trees must never be empty */ - if (owner == BTRFS_ROOT_TREE_OBJECTID || - owner == BTRFS_CHUNK_TREE_OBJECTID || - owner == BTRFS_EXTENT_TREE_OBJECTID || - owner == BTRFS_DEV_TREE_OBJECTID || - owner == BTRFS_FS_TREE_OBJECTID || - owner == BTRFS_DATA_RELOC_TREE_OBJECTID) { + if (unlikely(owner == BTRFS_ROOT_TREE_OBJECTID || + owner == BTRFS_CHUNK_TREE_OBJECTID || + owner == BTRFS_EXTENT_TREE_OBJECTID || + owner == BTRFS_DEV_TREE_OBJECTID || + owner == BTRFS_FS_TREE_OBJECTID || + owner == BTRFS_DATA_RELOC_TREE_OBJECTID)) { generic_err(leaf, 0, "invalid root, root %llu must never be empty", owner); return -EUCLEAN; } /* Unknown tree */ - if (owner == 0) { + if (unlikely(owner == 0)) { generic_err(leaf, 0, "invalid owner, root 0 is not defined"); return -EUCLEAN; @@ -1595,7 +1636,7 @@ static int check_leaf(struct extent_buffer *leaf, bool check_item_data) return 0; } - if (nritems == 0) + if (unlikely(nritems == 0)) return 0; /* @@ -1616,7 +1657,7 @@ static int check_leaf(struct extent_buffer *leaf, bool check_item_data) btrfs_item_key_to_cpu(leaf, &key, slot); /* Make sure the keys are in the right order */ - if (btrfs_comp_cpu_keys(&prev_key, &key) >= 0) { + if (unlikely(btrfs_comp_cpu_keys(&prev_key, &key) >= 0)) { generic_err(leaf, slot, "bad key order, prev (%llu %u %llu) current (%llu %u %llu)", prev_key.objectid, prev_key.type, @@ -1635,7 +1676,7 @@ static int check_leaf(struct extent_buffer *leaf, bool check_item_data) else item_end_expected = btrfs_item_offset_nr(leaf, slot - 1); - if (btrfs_item_end_nr(leaf, slot) != item_end_expected) { + if (unlikely(btrfs_item_end_nr(leaf, slot) != item_end_expected)) { generic_err(leaf, slot, "unexpected item end, have %u expect %u", btrfs_item_end_nr(leaf, slot), @@ -1648,8 +1689,8 @@ static int check_leaf(struct extent_buffer *leaf, bool check_item_data) * just in case all the items are consistent to each other, but * all point outside of the leaf. */ - if (btrfs_item_end_nr(leaf, slot) > - BTRFS_LEAF_DATA_SIZE(fs_info)) { + if (unlikely(btrfs_item_end_nr(leaf, slot) > + BTRFS_LEAF_DATA_SIZE(fs_info))) { generic_err(leaf, slot, "slot end outside of leaf, have %u expect range [0, %u]", btrfs_item_end_nr(leaf, slot), @@ -1658,8 +1699,8 @@ static int check_leaf(struct extent_buffer *leaf, bool check_item_data) } /* Also check if the item pointer overlaps with btrfs item. */ - if (btrfs_item_nr_offset(slot) + sizeof(struct btrfs_item) > - btrfs_item_ptr_offset(leaf, slot)) { + if (unlikely(btrfs_item_ptr_offset(leaf, slot) < + btrfs_item_nr_offset(slot) + sizeof(struct btrfs_item))) { generic_err(leaf, slot, "slot overlaps with its data, item end %lu data start %lu", btrfs_item_nr_offset(slot) + @@ -1674,7 +1715,7 @@ static int check_leaf(struct extent_buffer *leaf, bool check_item_data) * criteria */ ret = check_leaf_item(leaf, &key, slot, &prev_key); - if (ret < 0) + if (unlikely(ret < 0)) return ret; } @@ -1707,13 +1748,13 @@ int btrfs_check_node(struct extent_buffer *node) u64 bytenr; int ret = 0; - if (level <= 0 || level >= BTRFS_MAX_LEVEL) { + if (unlikely(level <= 0 || level >= BTRFS_MAX_LEVEL)) { generic_err(node, 0, "invalid level for node, have %d expect [1, %d]", level, BTRFS_MAX_LEVEL - 1); return -EUCLEAN; } - if (nr == 0 || nr > BTRFS_NODEPTRS_PER_BLOCK(fs_info)) { + if (unlikely(nr == 0 || nr > BTRFS_NODEPTRS_PER_BLOCK(fs_info))) { btrfs_crit(fs_info, "corrupt node: root=%llu block=%llu, nritems too %s, have %lu expect range [1,%u]", btrfs_header_owner(node), node->start, @@ -1727,13 +1768,13 @@ int btrfs_check_node(struct extent_buffer *node) btrfs_node_key_to_cpu(node, &key, slot); btrfs_node_key_to_cpu(node, &next_key, slot + 1); - if (!bytenr) { + if (unlikely(!bytenr)) { generic_err(node, slot, "invalid NULL node pointer"); ret = -EUCLEAN; goto out; } - if (!IS_ALIGNED(bytenr, fs_info->sectorsize)) { + if (unlikely(!IS_ALIGNED(bytenr, fs_info->sectorsize))) { generic_err(node, slot, "unaligned pointer, have %llu should be aligned to %u", bytenr, fs_info->sectorsize); @@ -1741,7 +1782,7 @@ int btrfs_check_node(struct extent_buffer *node) goto out; } - if (btrfs_comp_cpu_keys(&key, &next_key) >= 0) { + if (unlikely(btrfs_comp_cpu_keys(&key, &next_key) >= 0)) { generic_err(node, slot, "bad key order, current (%llu %u %llu) next (%llu %u %llu)", key.objectid, key.type, key.offset, diff --git a/fs/btrfs/tree-defrag.c b/fs/btrfs/tree-defrag.c index d3f28b8f4ff9..7c45d960b53c 100644 --- a/fs/btrfs/tree-defrag.c +++ b/fs/btrfs/tree-defrag.c @@ -52,7 +52,6 @@ int btrfs_defrag_leaves(struct btrfs_trans_handle *trans, u32 nritems; root_node = btrfs_lock_root_node(root); - btrfs_set_lock_blocking_write(root_node); nritems = btrfs_header_nritems(root_node); root->defrag_max.objectid = 0; /* from above we know this is not a leaf */ diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 56cbc1706b6f..d90695c1ab6c 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -17,9 +17,9 @@ #include "backref.h" #include "compression.h" #include "qgroup.h" -#include "inode-map.h" #include "block-group.h" #include "space-info.h" +#include "zoned.h" /* magic values for the inode_only field in btrfs_log_inode: * @@ -105,6 +105,7 @@ static noinline int replay_dir_deletes(struct btrfs_trans_handle *trans, struct btrfs_root *log, struct btrfs_path *path, u64 dirid, int del_all); +static void wait_log_commit(struct btrfs_root *root, int transid); /* * tree logging is a special write ahead log used to make sure that @@ -139,16 +140,45 @@ static int start_log_trans(struct btrfs_trans_handle *trans, struct btrfs_log_ctx *ctx) { struct btrfs_fs_info *fs_info = root->fs_info; + struct btrfs_root *tree_root = fs_info->tree_root; + const bool zoned = btrfs_is_zoned(fs_info); int ret = 0; + bool created = false; + + /* + * First check if the log root tree was already created. If not, create + * it before locking the root's log_mutex, just to keep lockdep happy. + */ + if (!test_bit(BTRFS_ROOT_HAS_LOG_TREE, &tree_root->state)) { + mutex_lock(&tree_root->log_mutex); + if (!fs_info->log_root_tree) { + ret = btrfs_init_log_root_tree(trans, fs_info); + if (!ret) { + set_bit(BTRFS_ROOT_HAS_LOG_TREE, &tree_root->state); + created = true; + } + } + mutex_unlock(&tree_root->log_mutex); + if (ret) + return ret; + } mutex_lock(&root->log_mutex); +again: if (root->log_root) { + int index = (root->log_transid + 1) % 2; + if (btrfs_need_log_full_commit(trans)) { ret = -EAGAIN; goto out; } + if (zoned && atomic_read(&root->log_commit[index])) { + wait_log_commit(root, root->log_transid - 1); + goto again; + } + if (!root->log_start_pid) { clear_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state); root->log_start_pid = current->pid; @@ -156,12 +186,16 @@ static int start_log_trans(struct btrfs_trans_handle *trans, set_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state); } } else { - mutex_lock(&fs_info->tree_log_mutex); - if (!fs_info->log_root_tree) - ret = btrfs_init_log_root_tree(trans, fs_info); - mutex_unlock(&fs_info->tree_log_mutex); - if (ret) + /* + * This means fs_info->log_root_tree was already created + * for some other FS trees. Do the full commit not to mix + * nodes from multiple log transactions to do sequential + * writing. + */ + if (zoned && !created) { + ret = -EAGAIN; goto out; + } ret = btrfs_add_log_tree(trans, root); if (ret) @@ -172,7 +206,6 @@ static int start_log_trans(struct btrfs_trans_handle *trans, root->log_start_pid = current->pid; } - atomic_inc(&root->log_batch); atomic_inc(&root->log_writers); if (ctx && !ctx->logging_new_name) { int index = root->log_transid % 2; @@ -192,14 +225,22 @@ out: */ static int join_running_log_trans(struct btrfs_root *root) { + const bool zoned = btrfs_is_zoned(root->fs_info); int ret = -ENOENT; if (!test_bit(BTRFS_ROOT_HAS_LOG_TREE, &root->state)) return ret; mutex_lock(&root->log_mutex); +again: if (root->log_root) { + int index = (root->log_transid + 1) % 2; + ret = 0; + if (zoned && atomic_read(&root->log_commit[index])) { + wait_log_commit(root, root->log_transid - 1); + goto again; + } atomic_inc(&root->log_writers); } mutex_unlock(&root->log_mutex); @@ -576,6 +617,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, struct extent_buffer *eb, int slot, struct btrfs_key *key) { + struct btrfs_drop_extents_args drop_args = { 0 }; struct btrfs_fs_info *fs_info = root->fs_info; int found_type; u64 extent_end; @@ -653,7 +695,10 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, btrfs_release_path(path); /* drop any overlapping extents */ - ret = btrfs_drop_extents(trans, root, inode, start, extent_end, 1); + drop_args.start = start; + drop_args.end = extent_end; + drop_args.drop_cache = true; + ret = btrfs_drop_extents(trans, root, BTRFS_I(inode), &drop_args); if (ret) goto out; @@ -828,9 +873,9 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, if (ret) goto out; - inode_add_bytes(inode, nbytes); update_inode: - ret = btrfs_update_inode(trans, root, inode); + btrfs_update_inode_bytes(BTRFS_I(inode), nbytes, drop_args.bytes_found); + ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); out: if (inode) iput(inode); @@ -1529,7 +1574,7 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, if (ret) goto out; - btrfs_update_inode(trans, root, inode); + btrfs_update_inode(trans, root, BTRFS_I(inode)); } ref_ptr = (unsigned long)(ref_ptr + ref_struct_size) + namelen; @@ -1564,18 +1609,6 @@ out: return ret; } -static int insert_orphan_item(struct btrfs_trans_handle *trans, - struct btrfs_root *root, u64 ino) -{ - int ret; - - ret = btrfs_insert_orphan_item(trans, root, ino); - if (ret == -EEXIST) - ret = 0; - - return ret; -} - static int count_inode_extrefs(struct btrfs_root *root, struct btrfs_inode *inode, struct btrfs_path *path) { @@ -1716,7 +1749,7 @@ static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans, if (nlink != inode->i_nlink) { set_nlink(inode, nlink); - btrfs_update_inode(trans, root, inode); + btrfs_update_inode(trans, root, BTRFS_I(inode)); } BTRFS_I(inode)->index_cnt = (u64)-1; @@ -1727,7 +1760,9 @@ static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans, if (ret) goto out; } - ret = insert_orphan_item(trans, root, ino); + ret = btrfs_insert_orphan_item(trans, root, ino); + if (ret == -EEXIST) + ret = 0; } out: @@ -1820,7 +1855,7 @@ static noinline int link_to_fixup_dir(struct btrfs_trans_handle *trans, set_nlink(inode, 1); else inc_nlink(inode); - ret = btrfs_update_inode(trans, root, inode); + ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); } else if (ret == -EEXIST) { ret = 0; } else { @@ -1973,7 +2008,7 @@ out: btrfs_release_path(path); if (!ret && update_size) { btrfs_i_size_write(BTRFS_I(dir), dir->i_size + name_len * 2); - ret = btrfs_update_inode(trans, root, dir); + ret = btrfs_update_inode(trans, root, BTRFS_I(dir)); } kfree(name); iput(dir); @@ -2586,6 +2621,7 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb, * those prealloc extents just after replaying them. */ if (S_ISREG(mode)) { + struct btrfs_drop_extents_args drop_args = { 0 }; struct inode *inode; u64 from; @@ -2596,12 +2632,18 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb, } from = ALIGN(i_size_read(inode), root->fs_info->sectorsize); - ret = btrfs_drop_extents(wc->trans, root, inode, - from, (u64)-1, 1); + drop_args.start = from; + drop_args.end = (u64)-1; + drop_args.drop_cache = true; + ret = btrfs_drop_extents(wc->trans, root, + BTRFS_I(inode), + &drop_args); if (!ret) { + inode_sub_bytes(inode, + drop_args.bytes_found); /* Update the inode's nbytes. */ ret = btrfs_update_inode(wc->trans, - root, inode); + root, BTRFS_I(inode)); } iput(inode); if (ret) @@ -2709,7 +2751,9 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans, btrfs_node_key_to_cpu(cur, &first_key, path->slots[*level]); blocksize = fs_info->nodesize; - next = btrfs_find_create_tree_block(fs_info, bytenr); + next = btrfs_find_create_tree_block(fs_info, bytenr, + btrfs_header_owner(cur), + *level - 1); if (IS_ERR(next)) return PTR_ERR(next); @@ -2732,7 +2776,6 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans, if (trans) { btrfs_tree_lock(next); - btrfs_set_lock_blocking_write(next); btrfs_clean_tree_block(next); btrfs_wait_tree_block_writeback(next); btrfs_tree_unlock(next); @@ -2742,6 +2785,8 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans, free_extent_buffer(next); return ret; } + btrfs_redirty_list_add( + trans->transaction, next); } else { if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags)) clear_extent_buffer_dirty(next); @@ -2801,7 +2846,6 @@ static noinline int walk_up_log_tree(struct btrfs_trans_handle *trans, if (trans) { btrfs_tree_lock(next); - btrfs_set_lock_blocking_write(next); btrfs_clean_tree_block(next); btrfs_wait_tree_block_writeback(next); btrfs_tree_unlock(next); @@ -2883,7 +2927,6 @@ static int walk_log_tree(struct btrfs_trans_handle *trans, if (trans) { btrfs_tree_lock(next); - btrfs_set_lock_blocking_write(next); btrfs_clean_tree_block(next); btrfs_wait_tree_block_writeback(next); btrfs_tree_unlock(next); @@ -3023,6 +3066,8 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, int log_transid = 0; struct btrfs_log_ctx root_log_ctx; struct blk_plug plug; + u64 log_root_start; + u64 log_root_level; mutex_lock(&root->log_mutex); log_transid = ctx->log_transid; @@ -3075,6 +3120,17 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, */ blk_start_plug(&plug); ret = btrfs_write_marked_extents(fs_info, &log->dirty_log_pages, mark); + /* + * -EAGAIN happens when someone, e.g., a concurrent transaction + * commit, writes a dirty extent in this tree-log commit. This + * concurrent write will create a hole writing out the extents, + * and we cannot proceed on a zoned filesystem, requiring + * sequential writing. While we can bail out to a full commit + * here, but we can continue hoping the concurrent writing fills + * the hole. + */ + if (ret == -EAGAIN && btrfs_is_zoned(fs_info)) + ret = 0; if (ret) { blk_finish_plug(&plug); btrfs_abort_transaction(trans, ret); @@ -3117,6 +3173,19 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, list_add_tail(&root_log_ctx.list, &log_root_tree->log_ctxs[index2]); root_log_ctx.log_transid = log_root_tree->log_transid; + if (btrfs_is_zoned(fs_info)) { + mutex_lock(&fs_info->tree_root->log_mutex); + if (!log_root_tree->node) { + ret = btrfs_alloc_log_tree_node(trans, log_root_tree); + if (ret) { + mutex_unlock(&fs_info->tree_log_mutex); + mutex_unlock(&log_root_tree->log_mutex); + goto out; + } + } + mutex_unlock(&fs_info->tree_root->log_mutex); + } + /* * Now we are safe to update the log_root_tree because we're under the * log_mutex, and we're a current writer so we're holding the commit @@ -3184,7 +3253,17 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, &log_root_tree->dirty_log_pages, EXTENT_DIRTY | EXTENT_NEW); blk_finish_plug(&plug); - if (ret) { + /* + * As described above, -EAGAIN indicates a hole in the extents. We + * cannot wait for these write outs since the waiting cause a + * deadlock. Bail out to the full commit instead. + */ + if (ret == -EAGAIN && btrfs_is_zoned(fs_info)) { + btrfs_set_log_full_commit(trans); + btrfs_wait_tree_log_extents(log, mark); + mutex_unlock(&log_root_tree->log_mutex); + goto out_wake_log_root; + } else if (ret) { btrfs_set_log_full_commit(trans); btrfs_abort_transaction(trans, ret); mutex_unlock(&log_root_tree->log_mutex); @@ -3200,22 +3279,31 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, goto out_wake_log_root; } - btrfs_set_super_log_root(fs_info->super_for_commit, - log_root_tree->node->start); - btrfs_set_super_log_root_level(fs_info->super_for_commit, - btrfs_header_level(log_root_tree->node)); - + log_root_start = log_root_tree->node->start; + log_root_level = btrfs_header_level(log_root_tree->node); log_root_tree->log_transid++; mutex_unlock(&log_root_tree->log_mutex); /* - * Nobody else is going to jump in and write the ctree - * super here because the log_commit atomic below is protecting - * us. We must be called with a transaction handle pinning - * the running transaction open, so a full commit can't hop - * in and cause problems either. + * Here we are guaranteed that nobody is going to write the superblock + * for the current transaction before us and that neither we do write + * our superblock before the previous transaction finishes its commit + * and writes its superblock, because: + * + * 1) We are holding a handle on the current transaction, so no body + * can commit it until we release the handle; + * + * 2) Before writing our superblock we acquire the tree_log_mutex, so + * if the previous transaction is still committing, and hasn't yet + * written its superblock, we wait for it to do it, because a + * transaction commit acquires the tree_log_mutex when the commit + * begins and releases it only after writing its superblock. */ + mutex_lock(&fs_info->tree_log_mutex); + btrfs_set_super_log_root(fs_info->super_for_commit, log_root_start); + btrfs_set_super_log_root_level(fs_info->super_for_commit, log_root_level); ret = write_all_supers(fs_info, 1); + mutex_unlock(&fs_info->tree_log_mutex); if (ret) { btrfs_set_log_full_commit(trans); btrfs_abort_transaction(trans, ret); @@ -3266,17 +3354,22 @@ static void free_log_tree(struct btrfs_trans_handle *trans, .process_func = process_one_buffer }; - ret = walk_log_tree(trans, log, &wc); - if (ret) { - if (trans) - btrfs_abort_transaction(trans, ret); - else - btrfs_handle_fs_error(log->fs_info, ret, NULL); + if (log->node) { + ret = walk_log_tree(trans, log, &wc); + if (ret) { + if (trans) + btrfs_abort_transaction(trans, ret); + else + btrfs_handle_fs_error(log->fs_info, ret, NULL); + } } clear_extent_bits(&log->dirty_log_pages, 0, (u64)-1, EXTENT_DIRTY | EXTENT_NEW | EXTENT_NEED_WAIT); extent_io_tree_release(&log->log_csum_range); + + if (trans && log->node) + btrfs_redirty_list_add(trans->transaction, log->node); btrfs_put_root(log); } @@ -3300,6 +3393,7 @@ int btrfs_free_log_root_tree(struct btrfs_trans_handle *trans, if (fs_info->log_root_tree) { free_log_tree(trans, fs_info->log_root_tree); fs_info->log_root_tree = NULL; + clear_bit(BTRFS_ROOT_HAS_LOG_TREE, &fs_info->tree_root->state); } return 0; } @@ -3359,7 +3453,6 @@ int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans, struct btrfs_path *path; int ret; int err = 0; - int bytes_del = 0; u64 dir_ino = btrfs_ino(dir); if (!inode_logged(trans, dir)) @@ -3386,7 +3479,6 @@ int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans, } if (di) { ret = btrfs_delete_one_dir_name(trans, log, path, di); - bytes_del += name_len; if (ret) { err = ret; goto fail; @@ -3401,46 +3493,17 @@ int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans, } if (di) { ret = btrfs_delete_one_dir_name(trans, log, path, di); - bytes_del += name_len; if (ret) { err = ret; goto fail; } } - /* update the directory size in the log to reflect the names - * we have removed + /* + * We do not need to update the size field of the directory's inode item + * because on log replay we update the field to reflect all existing + * entries in the directory (see overwrite_item()). */ - if (bytes_del) { - struct btrfs_key key; - - key.objectid = dir_ino; - key.offset = 0; - key.type = BTRFS_INODE_ITEM_KEY; - btrfs_release_path(path); - - ret = btrfs_search_slot(trans, log, &key, path, 0, 1); - if (ret < 0) { - err = ret; - goto fail; - } - if (ret == 0) { - struct btrfs_inode_item *item; - u64 i_size; - - item = btrfs_item_ptr(path->nodes[0], path->slots[0], - struct btrfs_inode_item); - i_size = btrfs_inode_size(path->nodes[0], item); - if (i_size > bytes_del) - i_size -= bytes_del; - else - i_size = 0; - btrfs_set_inode_size(path->nodes[0], item, i_size); - btrfs_mark_buffer_dirty(path->nodes[0]); - } else - ret = 0; - btrfs_release_path(path); - } fail: btrfs_free_path(path); out_unlock: @@ -3869,7 +3932,14 @@ static void fill_inode_item(struct btrfs_trans_handle *trans, btrfs_set_token_timespec_nsec(&token, &item->ctime, inode->i_ctime.tv_nsec); - btrfs_set_token_inode_nbytes(&token, item, inode_get_bytes(inode)); + /* + * We do not need to set the nbytes field, in fact during a fast fsync + * its value may not even be correct, since a fast fsync does not wait + * for ordered extent completion, which is where we update nbytes, it + * only waits for writeback to complete. During log replay as we find + * file extent items and replay them, we adjust the nbytes field of the + * inode item in subvolume tree as needed (see overwrite_item()). + */ btrfs_set_token_inode_sequence(&token, item, inode_peek_iversion(inode)); btrfs_set_token_inode_transid(&token, item, trans->transid); @@ -4196,6 +4266,7 @@ static int log_one_extent(struct btrfs_trans_handle *trans, struct btrfs_path *path, struct btrfs_log_ctx *ctx) { + struct btrfs_drop_extents_args drop_args = { 0 }; struct btrfs_root *log = root->log_root; struct btrfs_file_extent_item *fi; struct extent_buffer *leaf; @@ -4204,19 +4275,21 @@ static int log_one_extent(struct btrfs_trans_handle *trans, u64 extent_offset = em->start - em->orig_start; u64 block_len; int ret; - int extent_inserted = 0; ret = log_extent_csums(trans, inode, log, em, ctx); if (ret) return ret; - ret = __btrfs_drop_extents(trans, log, inode, path, em->start, - em->start + em->len, NULL, 0, 1, - sizeof(*fi), &extent_inserted); + drop_args.path = path; + drop_args.start = em->start; + drop_args.end = em->start + em->len; + drop_args.replace_extent = true; + drop_args.extent_item_size = sizeof(*fi); + ret = btrfs_drop_extents(trans, log, inode, &drop_args); if (ret) return ret; - if (!extent_inserted) { + if (!drop_args.extent_inserted) { key.objectid = btrfs_ino(inode); key.type = BTRFS_EXTENT_DATA_KEY; key.offset = em->start; @@ -4375,8 +4448,7 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans, do { ret = btrfs_truncate_inode_items(trans, root->log_root, - &inode->vfs_inode, - truncate_offset, + inode, truncate_offset, BTRFS_EXTENT_DATA_KEY); } while (ret == -EAGAIN); if (ret) @@ -4415,14 +4487,12 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, struct extent_map *em, *n; struct list_head extents; struct extent_map_tree *tree = &inode->extent_tree; - u64 test_gen; int ret = 0; int num = 0; INIT_LIST_HEAD(&extents); write_lock(&tree->lock); - test_gen = root->fs_info->last_trans_committed; list_for_each_entry_safe(em, n, &tree->modified_extents, list) { list_del_init(&em->list); @@ -4438,7 +4508,7 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, goto process; } - if (em->generation <= test_gen) + if (em->generation < trans->transid) continue; /* We log prealloc extents beyond eof later. */ @@ -4571,6 +4641,10 @@ static int btrfs_log_all_xattrs(struct btrfs_trans_handle *trans, const u64 ino = btrfs_ino(inode); int ins_nr = 0; int start_slot = 0; + bool found_xattrs = false; + + if (test_bit(BTRFS_INODE_NO_XATTRS, &inode->runtime_flags)) + return 0; key.objectid = ino; key.type = BTRFS_XATTR_ITEM_KEY; @@ -4609,6 +4683,7 @@ static int btrfs_log_all_xattrs(struct btrfs_trans_handle *trans, start_slot = slot; ins_nr++; path->slots[0]++; + found_xattrs = true; cond_resched(); } if (ins_nr > 0) { @@ -4618,6 +4693,9 @@ static int btrfs_log_all_xattrs(struct btrfs_trans_handle *trans, return ret; } + if (!found_xattrs) + set_bit(BTRFS_INODE_NO_XATTRS, &inode->runtime_flags); + return 0; } @@ -5262,12 +5340,28 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, } /* + * This is for cases where logging a directory could result in losing a + * a file after replaying the log. For example, if we move a file from a + * directory A to a directory B, then fsync directory A, we have no way + * to known the file was moved from A to B, so logging just A would + * result in losing the file after a log replay. + */ + if (S_ISDIR(inode->vfs_inode.i_mode) && + inode_only == LOG_INODE_ALL && + inode->last_unlink_trans >= trans->transid) { + btrfs_set_log_full_commit(trans); + err = 1; + goto out_unlock; + } + + /* * a brute force approach to making sure we get the most uptodate * copies of everything. */ if (S_ISDIR(inode->vfs_inode.i_mode)) { int max_key_type = BTRFS_DIR_LOG_INDEX_KEY; + clear_bit(BTRFS_INODE_COPY_EVERYTHING, &inode->runtime_flags); if (inode_only == LOG_INODE_EXISTS) max_key_type = BTRFS_XATTR_ITEM_KEY; ret = drop_objectid_items(trans, log, path, ino, max_key_type); @@ -5303,7 +5397,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, &inode->runtime_flags); while(1) { ret = btrfs_truncate_inode_items(trans, - log, &inode->vfs_inode, 0, 0); + log, inode, 0, 0); if (ret != -EAGAIN) break; } @@ -5424,98 +5518,31 @@ out_unlock: } /* - * Check if we must fallback to a transaction commit when logging an inode. - * This must be called after logging the inode and is used only in the context - * when fsyncing an inode requires the need to log some other inode - in which - * case we can't lock the i_mutex of each other inode we need to log as that - * can lead to deadlocks with concurrent fsync against other inodes (as we can - * log inodes up or down in the hierarchy) or rename operations for example. So - * we take the log_mutex of the inode after we have logged it and then check for - * its last_unlink_trans value - this is safe because any task setting - * last_unlink_trans must take the log_mutex and it must do this before it does - * the actual unlink operation, so if we do this check before a concurrent task - * sets last_unlink_trans it means we've logged a consistent version/state of - * all the inode items, otherwise we are not sure and must do a transaction - * commit (the concurrent task might have only updated last_unlink_trans before - * we logged the inode or it might have also done the unlink). - */ -static bool btrfs_must_commit_transaction(struct btrfs_trans_handle *trans, - struct btrfs_inode *inode) -{ - struct btrfs_fs_info *fs_info = inode->root->fs_info; - bool ret = false; - - mutex_lock(&inode->log_mutex); - if (inode->last_unlink_trans > fs_info->last_trans_committed) { - /* - * Make sure any commits to the log are forced to be full - * commits. - */ - btrfs_set_log_full_commit(trans); - ret = true; - } - mutex_unlock(&inode->log_mutex); - - return ret; -} - -/* - * follow the dentry parent pointers up the chain and see if any - * of the directories in it require a full commit before they can - * be logged. Returns zero if nothing special needs to be done or 1 if - * a full commit is required. + * Check if we need to log an inode. This is used in contexts where while + * logging an inode we need to log another inode (either that it exists or in + * full mode). This is used instead of btrfs_inode_in_log() because the later + * requires the inode to be in the log and have the log transaction committed, + * while here we do not care if the log transaction was already committed - our + * caller will commit the log later - and we want to avoid logging an inode + * multiple times when multiple tasks have joined the same log transaction. */ -static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans, - struct btrfs_inode *inode, - struct dentry *parent, - struct super_block *sb, - u64 last_committed) +static bool need_log_inode(struct btrfs_trans_handle *trans, + struct btrfs_inode *inode) { - int ret = 0; - struct dentry *old_parent = NULL; - /* - * for regular files, if its inode is already on disk, we don't - * have to worry about the parents at all. This is because - * we can use the last_unlink_trans field to record renames - * and other fun in this file. + * If this inode does not have new/updated/deleted xattrs since the last + * time it was logged and is flagged as logged in the current transaction, + * we can skip logging it. As for new/deleted names, those are updated in + * the log by link/unlink/rename operations. + * In case the inode was logged and then evicted and reloaded, its + * logged_trans will be 0, in which case we have to fully log it since + * logged_trans is a transient field, not persisted. */ - if (S_ISREG(inode->vfs_inode.i_mode) && - inode->generation <= last_committed && - inode->last_unlink_trans <= last_committed) - goto out; - - if (!S_ISDIR(inode->vfs_inode.i_mode)) { - if (!parent || d_really_is_negative(parent) || sb != parent->d_sb) - goto out; - inode = BTRFS_I(d_inode(parent)); - } - - while (1) { - if (btrfs_must_commit_transaction(trans, inode)) { - ret = 1; - break; - } - - if (!parent || d_really_is_negative(parent) || sb != parent->d_sb) - break; - - if (IS_ROOT(parent)) { - inode = BTRFS_I(d_inode(parent)); - if (btrfs_must_commit_transaction(trans, inode)) - ret = 1; - break; - } - - parent = dget_parent(parent); - dput(old_parent); - old_parent = parent; - inode = BTRFS_I(d_inode(parent)); + if (inode->logged_trans == trans->transid && + !test_bit(BTRFS_INODE_COPY_EVERYTHING, &inode->runtime_flags)) + return false; - } - dput(old_parent); -out: - return ret; + return true; } struct btrfs_dir_list { @@ -5645,7 +5672,7 @@ process_leaf: goto next_dir_inode; } - if (btrfs_inode_in_log(BTRFS_I(di_inode), trans->transid)) { + if (!need_log_inode(trans, BTRFS_I(di_inode))) { btrfs_add_delayed_iput(di_inode); break; } @@ -5655,9 +5682,6 @@ process_leaf: log_mode = LOG_INODE_ALL; ret = btrfs_log_inode(trans, root, BTRFS_I(di_inode), log_mode, ctx); - if (!ret && - btrfs_must_commit_transaction(trans, BTRFS_I(di_inode))) - ret = 1; btrfs_add_delayed_iput(di_inode); if (ret) goto next_dir_inode; @@ -5795,13 +5819,15 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans, goto out; } + if (!need_log_inode(trans, BTRFS_I(dir_inode))) { + btrfs_add_delayed_iput(dir_inode); + continue; + } + if (ctx) ctx->log_new_dentries = false; ret = btrfs_log_inode(trans, root, BTRFS_I(dir_inode), LOG_INODE_ALL, ctx); - if (!ret && - btrfs_must_commit_transaction(trans, BTRFS_I(dir_inode))) - ret = 1; if (!ret && ctx && ctx->log_new_dentries) ret = log_new_dir_dentries(trans, root, BTRFS_I(dir_inode), ctx); @@ -5828,7 +5854,6 @@ static int log_new_ancestors(struct btrfs_trans_handle *trans, while (true) { struct btrfs_fs_info *fs_info = root->fs_info; - const u64 last_committed = fs_info->last_trans_committed; struct extent_buffer *leaf = path->nodes[0]; int slot = path->slots[0]; struct btrfs_key search_key; @@ -5847,7 +5872,8 @@ static int log_new_ancestors(struct btrfs_trans_handle *trans, if (IS_ERR(inode)) return PTR_ERR(inode); - if (BTRFS_I(inode)->generation > last_committed) + if (BTRFS_I(inode)->generation >= trans->transid && + need_log_inode(trans, BTRFS_I(inode))) ret = btrfs_log_inode(trans, root, BTRFS_I(inode), LOG_INODE_EXISTS, ctx); btrfs_add_delayed_iput(inode); @@ -5888,7 +5914,6 @@ static int log_new_ancestors_fast(struct btrfs_trans_handle *trans, struct btrfs_log_ctx *ctx) { struct btrfs_root *root = inode->root; - struct btrfs_fs_info *fs_info = root->fs_info; struct dentry *old_parent = NULL; struct super_block *sb = inode->vfs_inode.i_sb; int ret = 0; @@ -5902,7 +5927,8 @@ static int log_new_ancestors_fast(struct btrfs_trans_handle *trans, if (root != inode->root) break; - if (inode->generation > fs_info->last_trans_committed) { + if (inode->generation >= trans->transid && + need_log_inode(trans, inode)) { ret = btrfs_log_inode(trans, root, inode, LOG_INODE_EXISTS, ctx); if (ret) @@ -6017,38 +6043,19 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, { struct btrfs_root *root = inode->root; struct btrfs_fs_info *fs_info = root->fs_info; - struct super_block *sb; int ret = 0; - u64 last_committed = fs_info->last_trans_committed; bool log_dentries = false; - sb = inode->vfs_inode.i_sb; - if (btrfs_test_opt(fs_info, NOTREELOG)) { ret = 1; goto end_no_trans; } - /* - * The prev transaction commit doesn't complete, we need do - * full commit by ourselves. - */ - if (fs_info->last_trans_log_full_commit > - fs_info->last_trans_committed) { - ret = 1; - goto end_no_trans; - } - if (btrfs_root_refs(&root->root_item) == 0) { ret = 1; goto end_no_trans; } - ret = check_parent_dirs_for_sync(trans, inode, parent, sb, - last_committed); - if (ret) - goto end_no_trans; - /* * Skip already logged inodes or inodes corresponding to tmpfiles * (since logging them is pointless, a link count of 0 means they @@ -6075,8 +6082,8 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, * and other fun in this file. */ if (S_ISREG(inode->vfs_inode.i_mode) && - inode->generation <= last_committed && - inode->last_unlink_trans <= last_committed) { + inode->generation < trans->transid && + inode->last_unlink_trans < trans->transid) { ret = 0; goto end_trans; } @@ -6125,7 +6132,7 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, * but the file inode does not have a matching BTRFS_INODE_REF_KEY item * and has a link count of 2. */ - if (inode->last_unlink_trans > last_committed) { + if (inode->last_unlink_trans >= trans->transid) { ret = btrfs_log_all_parents(trans, inode, ctx); if (ret) goto end_trans; @@ -6295,8 +6302,7 @@ again: * root->objectid_mutex is not acquired as log replay * could only happen during mount. */ - ret = btrfs_find_highest_objectid(root, - &root->highest_objectid); + ret = btrfs_init_root_free_objectid(root); } wc.replay_dest->log_root = NULL; @@ -6434,7 +6440,6 @@ void btrfs_log_new_name(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_inode *old_dir, struct dentry *parent) { - struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_log_ctx ctx; /* @@ -6448,8 +6453,8 @@ void btrfs_log_new_name(struct btrfs_trans_handle *trans, * if this inode hasn't been logged and directory we're renaming it * from hasn't been logged, we don't need to log it */ - if (inode->logged_trans <= fs_info->last_trans_committed && - (!old_dir || old_dir->logged_trans <= fs_info->last_trans_committed)) + if (inode->logged_trans < trans->transid && + (!old_dir || old_dir->logged_trans < trans->transid)) return; btrfs_init_log_ctx(&ctx, &inode->vfs_inode); diff --git a/fs/btrfs/uuid-tree.c b/fs/btrfs/uuid-tree.c index 28525ad7ff8c..74023c8a783f 100644 --- a/fs/btrfs/uuid-tree.c +++ b/fs/btrfs/uuid-tree.c @@ -129,8 +129,7 @@ int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans, u8 *uuid, u8 type, } else { btrfs_warn(fs_info, "insert uuid item failed %d (0x%016llx, 0x%016llx) type %u!", - ret, (unsigned long long)key.objectid, - (unsigned long long)key.offset, type); + ret, key.objectid, key.offset, type); goto out; } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 58b9c419a2b6..bc3b33efddc5 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -31,6 +31,7 @@ #include "space-info.h" #include "block-group.h" #include "discard.h" +#include "zoned.h" const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = { [BTRFS_RAID_RAID10] = { @@ -374,6 +375,7 @@ void btrfs_free_device(struct btrfs_device *device) rcu_string_free(device->name); extent_io_tree_release(&device->alloc_state); bio_put(device->flush_bio); + btrfs_destroy_dev_zone_info(device); kfree(device); } @@ -419,7 +421,7 @@ static struct btrfs_device *__alloc_device(struct btrfs_fs_info *fs_info) * Preallocate a bio that's always going to be used for flushing device * barriers and matches the device lifespan */ - dev->flush_bio = bio_alloc_bioset(GFP_KERNEL, 0, NULL); + dev->flush_bio = bio_kmalloc(GFP_KERNEL, 0); if (!dev->flush_bio) { kfree(dev); return ERR_PTR(-ENOMEM); @@ -822,7 +824,7 @@ static noinline struct btrfs_device *device_list_add(const char *path, } else { mutex_lock(&fs_devices->device_list_mutex); device = btrfs_find_device(fs_devices, devid, - disk_super->dev_item.uuid, NULL, false); + disk_super->dev_item.uuid, NULL); /* * If this disk has been pulled into an fs devices created by @@ -929,25 +931,30 @@ static noinline struct btrfs_device *device_list_add(const char *path, * make sure it's the same device if the device is mounted */ if (device->bdev) { - struct block_device *path_bdev; + int error; + dev_t path_dev; - path_bdev = lookup_bdev(path); - if (IS_ERR(path_bdev)) { + error = lookup_bdev(path, &path_dev); + if (error) { mutex_unlock(&fs_devices->device_list_mutex); - return ERR_CAST(path_bdev); + return ERR_PTR(error); } - if (device->bdev != path_bdev) { - bdput(path_bdev); + if (device->bdev->bd_dev != path_dev) { mutex_unlock(&fs_devices->device_list_mutex); - btrfs_warn_in_rcu(device->fs_info, + /* + * device->fs_info may not be reliable here, so + * pass in a NULL instead. This avoids a + * possible use-after-free when the fs_info and + * fs_info->sb are already torn down. + */ + btrfs_warn_in_rcu(NULL, "duplicate device %s devid %llu generation %llu scanned by %s (%d)", path, devid, found_transid, current->comm, task_pid_nr(current)); return ERR_PTR(-EEXIST); } - bdput(path_bdev); btrfs_info_in_rcu(device->fs_info, "devid %llu device path %s changed to %s scanned by %s (%d)", devid, rcu_str_deref(device->name), @@ -1038,7 +1045,7 @@ error: } static void __btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices, - int step, struct btrfs_device **latest_dev) + struct btrfs_device **latest_dev) { struct btrfs_device *device, *next; @@ -1056,22 +1063,13 @@ static void __btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices, continue; } - if (device->devid == BTRFS_DEV_REPLACE_DEVID) { - /* - * In the first step, keep the device which has - * the correct fsid and the devid that is used - * for the dev_replace procedure. - * In the second step, the dev_replace state is - * read from the device tree and it is known - * whether the procedure is really active or - * not, which means whether this device is - * used or whether it should be removed. - */ - if (step == 0 || test_bit(BTRFS_DEV_STATE_REPLACE_TGT, - &device->dev_state)) { - continue; - } - } + /* + * We have already validated the presence of BTRFS_DEV_REPLACE_DEVID, + * in btrfs_init_dev_replace() so just continue. + */ + if (device->devid == BTRFS_DEV_REPLACE_DEVID) + continue; + if (device->bdev) { blkdev_put(device->bdev, device->mode); device->bdev = NULL; @@ -1080,9 +1078,6 @@ static void __btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices, if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) { list_del_init(&device->dev_alloc_list); clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state); - if (!test_bit(BTRFS_DEV_STATE_REPLACE_TGT, - &device->dev_state)) - fs_devices->rw_devices--; } list_del_init(&device->dev_list); fs_devices->num_devices--; @@ -1095,16 +1090,16 @@ static void __btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices, * After we have read the system tree and know devids belonging to this * filesystem, remove the device which does not belong there. */ -void btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices, int step) +void btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices) { struct btrfs_device *latest_dev = NULL; struct btrfs_fs_devices *seed_dev; mutex_lock(&uuid_mutex); - __btrfs_free_extra_devids(fs_devices, step, &latest_dev); + __btrfs_free_extra_devids(fs_devices, &latest_dev); list_for_each_entry(seed_dev, &fs_devices->seed_list, seed_list) - __btrfs_free_extra_devids(seed_dev, step, &latest_dev); + __btrfs_free_extra_devids(seed_dev, &latest_dev); fs_devices->latest_bdev = latest_dev->bdev; @@ -1143,6 +1138,7 @@ static void btrfs_close_one_device(struct btrfs_device *device) device->bdev = NULL; } clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state); + btrfs_destroy_dev_zone_info(device); device->fs_info = NULL; atomic_set(&device->dev_stats_ccnt, 0); @@ -1223,6 +1219,7 @@ static int open_fs_devices(struct btrfs_fs_devices *fs_devices, fs_devices->latest_bdev = latest_dev->bdev; fs_devices->total_rw_bytes = 0; fs_devices->chunk_alloc_policy = BTRFS_CHUNK_ALLOC_REGULAR; + fs_devices->read_policy = BTRFS_READ_POLICY_PID; return 0; } @@ -1274,7 +1271,7 @@ void btrfs_release_disk_super(struct btrfs_super_block *super) } static struct btrfs_super_block *btrfs_read_disk_super(struct block_device *bdev, - u64 bytenr) + u64 bytenr, u64 bytenr_orig) { struct btrfs_super_block *disk_super; struct page *page; @@ -1305,7 +1302,7 @@ static struct btrfs_super_block *btrfs_read_disk_super(struct block_device *bdev /* align our pointer to the offset of the super block */ disk_super = p + offset_in_page(bytenr); - if (btrfs_super_bytenr(disk_super) != bytenr || + if (btrfs_super_bytenr(disk_super) != bytenr_orig || btrfs_super_magic(disk_super) != BTRFS_MAGIC) { btrfs_release_disk_super(p); return ERR_PTR(-EINVAL); @@ -1340,7 +1337,8 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, fmode_t flags, bool new_device_added = false; struct btrfs_device *device = NULL; struct block_device *bdev; - u64 bytenr; + u64 bytenr, bytenr_orig; + int ret; lockdep_assert_held(&uuid_mutex); @@ -1350,14 +1348,18 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, fmode_t flags, * So, we need to add a special mount option to scan for * later supers, using BTRFS_SUPER_MIRROR_MAX instead */ - bytenr = btrfs_sb_offset(0); flags |= FMODE_EXCL; bdev = blkdev_get_by_path(path, flags, holder); if (IS_ERR(bdev)) return ERR_CAST(bdev); - disk_super = btrfs_read_disk_super(bdev, bytenr); + bytenr_orig = btrfs_sb_offset(0); + ret = btrfs_sb_log_location_bdev(bdev, 0, READ, &bytenr); + if (ret) + return ERR_PTR(ret); + + disk_super = btrfs_read_disk_super(bdev, bytenr, bytenr_orig); if (IS_ERR(disk_super)) { device = ERR_CAST(disk_super); goto error_bdev_put; @@ -1412,11 +1414,62 @@ static u64 dev_extent_search_start(struct btrfs_device *device, u64 start) * make sure to start at an offset of at least 1MB. */ return max_t(u64, start, SZ_1M); + case BTRFS_CHUNK_ALLOC_ZONED: + /* + * We don't care about the starting region like regular + * allocator, because we anyway use/reserve the first two zones + * for superblock logging. + */ + return ALIGN(start, device->zone_info->zone_size); default: BUG(); } } +static bool dev_extent_hole_check_zoned(struct btrfs_device *device, + u64 *hole_start, u64 *hole_size, + u64 num_bytes) +{ + u64 zone_size = device->zone_info->zone_size; + u64 pos; + int ret; + bool changed = false; + + ASSERT(IS_ALIGNED(*hole_start, zone_size)); + + while (*hole_size > 0) { + pos = btrfs_find_allocatable_zones(device, *hole_start, + *hole_start + *hole_size, + num_bytes); + if (pos != *hole_start) { + *hole_size = *hole_start + *hole_size - pos; + *hole_start = pos; + changed = true; + if (*hole_size < num_bytes) + break; + } + + ret = btrfs_ensure_empty_zones(device, pos, num_bytes); + + /* Range is ensured to be empty */ + if (!ret) + return changed; + + /* Given hole range was invalid (outside of device) */ + if (ret == -ERANGE) { + *hole_start += *hole_size; + *hole_size = 0; + return 1; + } + + *hole_start += zone_size; + *hole_size -= zone_size; + changed = true; + } + + return changed; +} + /** * dev_extent_hole_check - check if specified hole is suitable for allocation * @device: the device which we have the hole @@ -1424,7 +1477,7 @@ static u64 dev_extent_search_start(struct btrfs_device *device, u64 start) * @hole_size: the size of the hole * @num_bytes: the size of the free space that we need * - * This function may modify @hole_start and @hole_end to reflect the suitable + * This function may modify @hole_start and @hole_size to reflect the suitable * position for allocation. Returns 1 if hole position is updated, 0 otherwise. */ static bool dev_extent_hole_check(struct btrfs_device *device, u64 *hole_start, @@ -1433,24 +1486,39 @@ static bool dev_extent_hole_check(struct btrfs_device *device, u64 *hole_start, bool changed = false; u64 hole_end = *hole_start + *hole_size; - /* - * Check before we set max_hole_start, otherwise we could end up - * sending back this offset anyway. - */ - if (contains_pending_extent(device, hole_start, *hole_size)) { - if (hole_end >= *hole_start) - *hole_size = hole_end - *hole_start; - else - *hole_size = 0; - changed = true; - } + for (;;) { + /* + * Check before we set max_hole_start, otherwise we could end up + * sending back this offset anyway. + */ + if (contains_pending_extent(device, hole_start, *hole_size)) { + if (hole_end >= *hole_start) + *hole_size = hole_end - *hole_start; + else + *hole_size = 0; + changed = true; + } + + switch (device->fs_devices->chunk_alloc_policy) { + case BTRFS_CHUNK_ALLOC_REGULAR: + /* No extra check */ + break; + case BTRFS_CHUNK_ALLOC_ZONED: + if (dev_extent_hole_check_zoned(device, hole_start, + hole_size, num_bytes)) { + changed = true; + /* + * The changed hole can contain pending extent. + * Loop again to check that. + */ + continue; + } + break; + default: + BUG(); + } - switch (device->fs_devices->chunk_alloc_policy) { - case BTRFS_CHUNK_ALLOC_REGULAR: - /* No extra check */ break; - default: - BUG(); } return changed; @@ -1503,6 +1571,9 @@ static int find_free_dev_extent_start(struct btrfs_device *device, search_start = dev_extent_search_start(device, search_start); + WARN_ON(device->zone_info && + !IS_ALIGNED(num_bytes, device->zone_info->zone_size)); + path = btrfs_alloc_path(); if (!path) return -ENOMEM; @@ -2021,6 +2092,11 @@ void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info, if (IS_ERR(disk_super)) continue; + if (bdev_is_zoned(bdev)) { + btrfs_reset_sb_log_zones(bdev, copy_num); + continue; + } + memset(&disk_super->magic, 0, sizeof(disk_super->magic)); page = virt_to_page(disk_super); @@ -2099,6 +2175,8 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path, mutex_unlock(&uuid_mutex); ret = btrfs_shrink_device(device, 0); + if (!ret) + btrfs_reada_remove_dev(device); mutex_lock(&uuid_mutex); if (ret) goto error_undo; @@ -2179,6 +2257,7 @@ out: return ret; error_undo: + btrfs_reada_undo_remove_dev(device); if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) { mutex_lock(&fs_info->chunk_mutex); list_add(&device->dev_alloc_list, @@ -2296,10 +2375,10 @@ static struct btrfs_device *btrfs_find_device_by_path( dev_uuid = disk_super->dev_item.uuid; if (btrfs_fs_incompat(fs_info, METADATA_UUID)) device = btrfs_find_device(fs_info->fs_devices, devid, dev_uuid, - disk_super->metadata_uuid, true); + disk_super->metadata_uuid); else device = btrfs_find_device(fs_info->fs_devices, devid, dev_uuid, - disk_super->fsid, true); + disk_super->fsid); btrfs_release_disk_super(disk_super); if (!device) @@ -2319,7 +2398,7 @@ struct btrfs_device *btrfs_find_device_by_devspec( if (devid) { device = btrfs_find_device(fs_info->fs_devices, devid, NULL, - NULL, true); + NULL); if (!device) return ERR_PTR(-ENOENT); return device; @@ -2468,7 +2547,7 @@ next_slot: read_extent_buffer(leaf, fs_uuid, btrfs_device_fsid(dev_item), BTRFS_FSID_SIZE); device = btrfs_find_device(fs_info->fs_devices, devid, dev_uuid, - fs_uuid, true); + fs_uuid); BUG_ON(!device); /* Logic error */ if (device->fs_devices->seeding) { @@ -2510,6 +2589,11 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path if (IS_ERR(bdev)) return PTR_ERR(bdev); + if (!btrfs_check_device_zone_type(fs_info, bdev)) { + ret = -EINVAL; + goto error; + } + if (fs_devices->seeding) { seeding_dev = 1; down_write(&sb->s_umount); @@ -2543,10 +2627,17 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path } rcu_assign_pointer(device->name, name); + device->fs_info = fs_info; + device->bdev = bdev; + + ret = btrfs_get_dev_zone_info(device); + if (ret) + goto error_free_device; + trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { ret = PTR_ERR(trans); - goto error_free_device; + goto error_free_zone; } q = bdev_get_queue(bdev); @@ -2559,8 +2650,6 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path fs_info->sectorsize); device->disk_total_bytes = device->total_bytes; device->commit_total_bytes = device->total_bytes; - device->fs_info = fs_info; - device->bdev = bdev; set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); clear_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state); device->mode = FMODE_EXCL; @@ -2568,7 +2657,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE); if (seeding_dev) { - sb->s_flags &= ~SB_RDONLY; + btrfs_clear_sb_rdonly(sb); ret = btrfs_prepare_sprout(fs_info); if (ret) { btrfs_abort_transaction(trans, ret); @@ -2704,9 +2793,11 @@ error_sysfs: mutex_unlock(&fs_info->fs_devices->device_list_mutex); error_trans: if (seeding_dev) - sb->s_flags |= SB_RDONLY; + btrfs_set_sb_rdonly(sb); if (trans) btrfs_end_transaction(trans); +error_free_zone: + btrfs_destroy_dev_zone_info(device); error_free_device: btrfs_free_device(device); error: @@ -4291,6 +4382,8 @@ int btrfs_recover_balance(struct btrfs_fs_info *fs_info) btrfs_warn(fs_info, "balance: cannot set exclusive op status, resume manually"); + btrfs_release_path(path); + mutex_lock(&fs_info->balance_mutex); BUG_ON(fs_info->balance_ctl); spin_lock(&fs_info->balance_lock); @@ -4640,11 +4733,10 @@ again: } ret = btrfs_previous_item(root, path, 0, key.type); - if (ret) - mutex_unlock(&fs_info->delete_unused_bgs_mutex); - if (ret < 0) - goto done; if (ret) { + mutex_unlock(&fs_info->delete_unused_bgs_mutex); + if (ret < 0) + goto done; ret = 0; btrfs_release_path(path); break; @@ -4876,6 +4968,37 @@ static void init_alloc_chunk_ctl_policy_regular( ctl->dev_extent_min = BTRFS_STRIPE_LEN * ctl->dev_stripes; } +static void init_alloc_chunk_ctl_policy_zoned( + struct btrfs_fs_devices *fs_devices, + struct alloc_chunk_ctl *ctl) +{ + u64 zone_size = fs_devices->fs_info->zone_size; + u64 limit; + int min_num_stripes = ctl->devs_min * ctl->dev_stripes; + int min_data_stripes = (min_num_stripes - ctl->nparity) / ctl->ncopies; + u64 min_chunk_size = min_data_stripes * zone_size; + u64 type = ctl->type; + + ctl->max_stripe_size = zone_size; + if (type & BTRFS_BLOCK_GROUP_DATA) { + ctl->max_chunk_size = round_down(BTRFS_MAX_DATA_CHUNK_SIZE, + zone_size); + } else if (type & BTRFS_BLOCK_GROUP_METADATA) { + ctl->max_chunk_size = ctl->max_stripe_size; + } else if (type & BTRFS_BLOCK_GROUP_SYSTEM) { + ctl->max_chunk_size = 2 * ctl->max_stripe_size; + ctl->devs_max = min_t(int, ctl->devs_max, + BTRFS_MAX_DEVS_SYS_CHUNK); + } + + /* We don't want a chunk larger than 10% of writable space */ + limit = max(round_down(div_factor(fs_devices->total_rw_bytes, 1), + zone_size), + min_chunk_size); + ctl->max_chunk_size = min(limit, ctl->max_chunk_size); + ctl->dev_extent_min = zone_size * ctl->dev_stripes; +} + static void init_alloc_chunk_ctl(struct btrfs_fs_devices *fs_devices, struct alloc_chunk_ctl *ctl) { @@ -4896,6 +5019,9 @@ static void init_alloc_chunk_ctl(struct btrfs_fs_devices *fs_devices, case BTRFS_CHUNK_ALLOC_REGULAR: init_alloc_chunk_ctl_policy_regular(fs_devices, ctl); break; + case BTRFS_CHUNK_ALLOC_ZONED: + init_alloc_chunk_ctl_policy_zoned(fs_devices, ctl); + break; default: BUG(); } @@ -5022,6 +5148,38 @@ static int decide_stripe_size_regular(struct alloc_chunk_ctl *ctl, return 0; } +static int decide_stripe_size_zoned(struct alloc_chunk_ctl *ctl, + struct btrfs_device_info *devices_info) +{ + u64 zone_size = devices_info[0].dev->zone_info->zone_size; + /* Number of stripes that count for block group size */ + int data_stripes; + + /* + * It should hold because: + * dev_extent_min == dev_extent_want == zone_size * dev_stripes + */ + ASSERT(devices_info[ctl->ndevs - 1].max_avail == ctl->dev_extent_min); + + ctl->stripe_size = zone_size; + ctl->num_stripes = ctl->ndevs * ctl->dev_stripes; + data_stripes = (ctl->num_stripes - ctl->nparity) / ctl->ncopies; + + /* stripe_size is fixed in zoned filesysmte. Reduce ndevs instead. */ + if (ctl->stripe_size * data_stripes > ctl->max_chunk_size) { + ctl->ndevs = div_u64(div_u64(ctl->max_chunk_size * ctl->ncopies, + ctl->stripe_size) + ctl->nparity, + ctl->dev_stripes); + ctl->num_stripes = ctl->ndevs * ctl->dev_stripes; + data_stripes = (ctl->num_stripes - ctl->nparity) / ctl->ncopies; + ASSERT(ctl->stripe_size * data_stripes <= ctl->max_chunk_size); + } + + ctl->chunk_size = ctl->stripe_size * data_stripes; + + return 0; +} + static int decide_stripe_size(struct btrfs_fs_devices *fs_devices, struct alloc_chunk_ctl *ctl, struct btrfs_device_info *devices_info) @@ -5049,6 +5207,8 @@ static int decide_stripe_size(struct btrfs_fs_devices *fs_devices, switch (fs_devices->chunk_alloc_policy) { case BTRFS_CHUNK_ALLOC_REGULAR: return decide_stripe_size_regular(ctl, devices_info); + case BTRFS_CHUNK_ALLOC_ZONED: + return decide_stripe_size_zoned(ctl, devices_info); default: BUG(); } @@ -5482,7 +5642,18 @@ static int find_live_mirror(struct btrfs_fs_info *fs_info, else num_stripes = map->num_stripes; - preferred_mirror = first + current->pid % num_stripes; + switch (fs_info->fs_devices->read_policy) { + default: + /* Shouldn't happen, just warn and use pid instead of failing */ + btrfs_warn_rl(fs_info, + "unknown read_policy type %u, reset to pid", + fs_info->fs_devices->read_policy); + fs_info->fs_devices->read_policy = BTRFS_READ_POLICY_PID; + fallthrough; + case BTRFS_READ_POLICY_PID: + preferred_mirror = first + (current->pid % num_stripes); + break; + } if (dev_replace_is_ongoing && fs_info->dev_replace.cont_reading_from_srcdev_mode == @@ -5802,9 +5973,29 @@ static int get_extra_mirror_from_replace(struct btrfs_fs_info *fs_info, return ret; } +static bool is_block_group_to_copy(struct btrfs_fs_info *fs_info, u64 logical) +{ + struct btrfs_block_group *cache; + bool ret; + + /* Non zoned filesystem does not use "to_copy" flag */ + if (!btrfs_is_zoned(fs_info)) + return false; + + cache = btrfs_lookup_block_group(fs_info, logical); + + spin_lock(&cache->lock); + ret = cache->to_copy; + spin_unlock(&cache->lock); + + btrfs_put_block_group(cache); + return ret; +} + static void handle_ops_on_dev_replace(enum btrfs_map_op op, struct btrfs_bio **bbio_ret, struct btrfs_dev_replace *dev_replace, + u64 logical, int *num_stripes_ret, int *max_errors_ret) { struct btrfs_bio *bbio = *bbio_ret; @@ -5818,6 +6009,13 @@ static void handle_ops_on_dev_replace(enum btrfs_map_op op, int index_where_to_add; /* + * A block group which have "to_copy" set will eventually + * copied by dev-replace process. We can avoid cloning IO here. + */ + if (is_block_group_to_copy(dev_replace->srcdev->fs_info, logical)) + return; + + /* * duplicate the write operations while the dev replace * procedure is running. Since the copying of the old disk to * the new disk takes place at run time while the filesystem is @@ -5902,23 +6100,24 @@ static bool need_full_stripe(enum btrfs_map_op op) } /* - * btrfs_get_io_geometry - calculates the geomery of a particular (address, len) - * tuple. This information is used to calculate how big a - * particular bio can get before it straddles a stripe. + * Calculate the geometry of a particular (address, len) tuple. This + * information is used to calculate how big a particular bio can get before it + * straddles a stripe. * - * @fs_info - the filesystem - * @logical - address that we want to figure out the geometry of - * @len - the length of IO we are going to perform, starting at @logical - * @op - type of operation - write or read - * @io_geom - pointer used to return values + * @fs_info: the filesystem + * @em: mapping containing the logical extent + * @op: type of operation - write or read + * @logical: address that we want to figure out the geometry of + * @len: the length of IO we are going to perform, starting at @logical + * @io_geom: pointer used to return values * * Returns < 0 in case a chunk for the given logical address cannot be found, * usually shouldn't happen unless @logical is corrupted, 0 otherwise. */ -int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, - u64 logical, u64 len, struct btrfs_io_geometry *io_geom) +int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, struct extent_map *em, + enum btrfs_map_op op, u64 logical, u64 len, + struct btrfs_io_geometry *io_geom) { - struct extent_map *em; struct map_lookup *map; u64 offset; u64 stripe_offset; @@ -5926,14 +6125,9 @@ int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, u64 stripe_len; u64 raid56_full_stripe_start = (u64)-1; int data_stripes; - int ret = 0; ASSERT(op != BTRFS_MAP_DISCARD); - em = btrfs_get_chunk_map(fs_info, logical, len); - if (IS_ERR(em)) - return PTR_ERR(em); - map = em->map_lookup; /* Offset of this logical address in the chunk */ offset = logical - em->start; @@ -5947,8 +6141,7 @@ int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, btrfs_crit(fs_info, "stripe math has gone wrong, stripe_offset=%llu offset=%llu start=%llu logical=%llu stripe_len=%llu", stripe_offset, offset, em->start, logical, stripe_len); - ret = -EINVAL; - goto out; + return -EINVAL; } /* stripe_offset is the offset of this block in its stripe */ @@ -5995,10 +6188,7 @@ int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, io_geom->stripe_offset = stripe_offset; io_geom->raid56_stripe_offset = raid56_full_stripe_start; -out: - /* once for us */ - free_extent_map(em); - return ret; + return 0; } static int __btrfs_map_block(struct btrfs_fs_info *fs_info, @@ -6031,12 +6221,13 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, ASSERT(bbio_ret); ASSERT(op != BTRFS_MAP_DISCARD); - ret = btrfs_get_io_geometry(fs_info, op, logical, *length, &geom); + em = btrfs_get_chunk_map(fs_info, logical, *length); + ASSERT(!IS_ERR(em)); + + ret = btrfs_get_io_geometry(fs_info, em, op, logical, *length, &geom); if (ret < 0) return ret; - em = btrfs_get_chunk_map(fs_info, logical, *length); - ASSERT(!IS_ERR(em)); map = em->map_lookup; *length = geom.len; @@ -6212,8 +6403,8 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, if (dev_replace_is_ongoing && dev_replace->tgtdev != NULL && need_full_stripe(op)) { - handle_ops_on_dev_replace(op, &bbio, dev_replace, &num_stripes, - &max_errors); + handle_ops_on_dev_replace(op, &bbio, dev_replace, logical, + &num_stripes, &max_errors); } *bbio_ret = bbio; @@ -6284,7 +6475,7 @@ static void btrfs_end_bio(struct bio *bio) struct btrfs_device *dev = btrfs_io_bio(bio)->device; ASSERT(dev->bdev); - if (bio_op(bio) == REQ_OP_WRITE) + if (btrfs_op(bio) == BTRFS_MAP_WRITE) btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS); else if (!(bio->bi_opf & REQ_RAHEAD)) @@ -6336,9 +6527,23 @@ static void submit_stripe_bio(struct btrfs_bio *bbio, struct bio *bio, btrfs_io_bio(bio)->device = dev; bio->bi_end_io = btrfs_end_bio; bio->bi_iter.bi_sector = physical >> 9; + /* + * For zone append writing, bi_sector must point the beginning of the + * zone + */ + if (bio_op(bio) == REQ_OP_ZONE_APPEND) { + if (btrfs_dev_is_sequential(dev, physical)) { + u64 zone_start = round_down(physical, fs_info->zone_size); + + bio->bi_iter.bi_sector = zone_start >> SECTOR_SHIFT; + } else { + bio->bi_opf &= ~REQ_OP_ZONE_APPEND; + bio->bi_opf |= REQ_OP_WRITE; + } + } btrfs_debug_in_rcu(fs_info, "btrfs_map_bio: rw %d 0x%x, sector=%llu, dev=%lu (%s id %llu), size=%u", - bio_op(bio), bio->bi_opf, (u64)bio->bi_iter.bi_sector, + bio_op(bio), bio->bi_opf, bio->bi_iter.bi_sector, (unsigned long)dev->bdev->bd_dev, rcu_str_deref(dev->name), dev->devid, bio->bi_iter.bi_size); bio_set_dev(bio, dev->bdev); @@ -6370,7 +6575,7 @@ blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, { struct btrfs_device *dev; struct bio *first_bio = bio; - u64 logical = (u64)bio->bi_iter.bi_sector << 9; + u64 logical = bio->bi_iter.bi_sector << 9; u64 length = 0; u64 map_length; int ret; @@ -6397,10 +6602,10 @@ blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, atomic_set(&bbio->stripes_pending, bbio->num_stripes); if ((bbio->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) && - ((bio_op(bio) == REQ_OP_WRITE) || (mirror_num > 1))) { + ((btrfs_op(bio) == BTRFS_MAP_WRITE) || (mirror_num > 1))) { /* In this case, map_length has been set to the length of a single stripe; not the whole write */ - if (bio_op(bio) == REQ_OP_WRITE) { + if (btrfs_op(bio) == BTRFS_MAP_WRITE) { ret = raid56_parity_write(fs_info, bio, bbio, map_length); } else { @@ -6423,7 +6628,7 @@ blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, dev = bbio->stripes[dev_nr].dev; if (!dev || !dev->bdev || test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state) || - (bio_op(first_bio) == REQ_OP_WRITE && + (btrfs_op(first_bio) == BTRFS_MAP_WRITE && !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state))) { bbio_error(bbio, first_bio, logical); continue; @@ -6450,8 +6655,7 @@ blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, * If @seed is true, traverse through the seed devices. */ struct btrfs_device *btrfs_find_device(struct btrfs_fs_devices *fs_devices, - u64 devid, u8 *uuid, u8 *fsid, - bool seed) + u64 devid, u8 *uuid, u8 *fsid) { struct btrfs_device *device; struct btrfs_fs_devices *seed_devs; @@ -6658,7 +6862,7 @@ static int read_one_chunk(struct btrfs_key *key, struct extent_buffer *leaf, btrfs_stripe_dev_uuid_nr(chunk, i), BTRFS_UUID_SIZE); map->stripes[i].dev = btrfs_find_device(fs_info->fs_devices, - devid, uuid, NULL, true); + devid, uuid, NULL); if (!map->stripes[i].dev && !btrfs_test_opt(fs_info, DEGRADED)) { free_extent_map(em); @@ -6797,7 +7001,7 @@ static int read_one_dev(struct extent_buffer *leaf, } device = btrfs_find_device(fs_info->fs_devices, devid, dev_uuid, - fs_uuid, true); + fs_uuid); if (!device) { if (!btrfs_test_opt(fs_info, DEGRADED)) { btrfs_report_missing_device(fs_info, devid, @@ -6860,6 +7064,16 @@ static int read_one_dev(struct extent_buffer *leaf, } fill_device_from_item(leaf, dev_item, device); + if (device->bdev) { + u64 max_total_bytes = i_size_read(device->bdev->bd_inode); + + if (device->total_bytes > max_total_bytes) { + btrfs_err(fs_info, + "device total_bytes should be at most %llu but found %llu", + max_total_bytes, device->total_bytes); + return -EINVAL; + } + } set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state) && !test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state)) { @@ -6894,11 +7108,11 @@ int btrfs_read_sys_array(struct btrfs_fs_info *fs_info) * fixed to BTRFS_SUPER_INFO_SIZE. If nodesize > sb size, this will * overallocate but we can keep it as-is, only the first page is used. */ - sb = btrfs_find_create_tree_block(fs_info, BTRFS_SUPER_INFO_OFFSET); + sb = btrfs_find_create_tree_block(fs_info, BTRFS_SUPER_INFO_OFFSET, + root->root_key.objectid, 0); if (IS_ERR(sb)) return PTR_ERR(sb); set_extent_buffer_uptodate(sb); - btrfs_set_buffer_lockdep_class(root->root_key.objectid, sb, 0); /* * The sb extent buffer is artificial and just used to read the system array. * set_extent_buffer_uptodate() call does not properly mark all it's @@ -7062,12 +7276,8 @@ static void readahead_tree_node_children(struct extent_buffer *node) int i; const int nr_items = btrfs_header_nritems(node); - for (i = 0; i < nr_items; i++) { - u64 start; - - start = btrfs_node_blockptr(node, i); - readahead_tree_block(node->fs_info, start); - } + for (i = 0; i < nr_items; i++) + btrfs_readahead_node_child(node, i); } int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info) @@ -7454,8 +7664,7 @@ int btrfs_get_dev_stats(struct btrfs_fs_info *fs_info, int i; mutex_lock(&fs_devices->device_list_mutex); - dev = btrfs_find_device(fs_info->fs_devices, stats->devid, NULL, NULL, - true); + dev = btrfs_find_device(fs_info->fs_devices, stats->devid, NULL, NULL); mutex_unlock(&fs_devices->device_list_mutex); if (!dev) { @@ -7586,28 +7795,13 @@ static int verify_one_dev_extent(struct btrfs_fs_info *fs_info, } /* Make sure no dev extent is beyond device bondary */ - dev = btrfs_find_device(fs_info->fs_devices, devid, NULL, NULL, true); + dev = btrfs_find_device(fs_info->fs_devices, devid, NULL, NULL); if (!dev) { btrfs_err(fs_info, "failed to find devid %llu", devid); ret = -EUCLEAN; goto out; } - /* It's possible this device is a dummy for seed device */ - if (dev->disk_total_bytes == 0) { - struct btrfs_fs_devices *devs; - - devs = list_first_entry(&fs_info->fs_devices->seed_list, - struct btrfs_fs_devices, seed_list); - dev = btrfs_find_device(devs, devid, NULL, NULL, false); - if (!dev) { - btrfs_err(fs_info, "failed to find seed devid %llu", - devid); - ret = -EUCLEAN; - goto out; - } - } - if (physical_offset + physical_len > dev->disk_total_bytes) { btrfs_err(fs_info, "dev extent devid %llu physical offset %llu len %llu is beyond device boundary %llu", @@ -7616,6 +7810,20 @@ static int verify_one_dev_extent(struct btrfs_fs_info *fs_info, ret = -EUCLEAN; goto out; } + + if (dev->zone_info) { + u64 zone_size = dev->zone_info->zone_size; + + if (!IS_ALIGNED(physical_offset, zone_size) || + !IS_ALIGNED(physical_len, zone_size)) { + btrfs_err(fs_info, +"zoned: dev extent devid %llu physical offset %llu len %llu is not aligned to device zone", + devid, physical_offset, physical_len); + ret = -EUCLEAN; + goto out; + } + } + out: free_extent_map(em); return ret; @@ -7662,6 +7870,19 @@ int btrfs_verify_dev_extents(struct btrfs_fs_info *fs_info) u64 prev_dev_ext_end = 0; int ret = 0; + /* + * We don't have a dev_root because we mounted with ignorebadroots and + * failed to load the root, so we want to skip the verification in this + * case for sure. + * + * However if the dev root is fine, but the tree itself is corrupted + * we'd still fail to mount. This verification is only to make sure + * writes can happen safely, so instead just bypass this check + * completely in the case of IGNOREBADROOTS. + */ + if (btrfs_test_opt(fs_info, IGNOREBADROOTS)) + return 0; + key.objectid = 1; key.type = BTRFS_DEV_EXTENT_KEY; key.offset = 0; @@ -7759,3 +7980,75 @@ bool btrfs_pinned_by_swapfile(struct btrfs_fs_info *fs_info, void *ptr) spin_unlock(&fs_info->swapfile_pins_lock); return node != NULL; } + +static int relocating_repair_kthread(void *data) +{ + struct btrfs_block_group *cache = (struct btrfs_block_group *)data; + struct btrfs_fs_info *fs_info = cache->fs_info; + u64 target; + int ret = 0; + + target = cache->start; + btrfs_put_block_group(cache); + + if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_BALANCE)) { + btrfs_info(fs_info, + "zoned: skip relocating block group %llu to repair: EBUSY", + target); + return -EBUSY; + } + + mutex_lock(&fs_info->delete_unused_bgs_mutex); + + /* Ensure block group still exists */ + cache = btrfs_lookup_block_group(fs_info, target); + if (!cache) + goto out; + + if (!cache->relocating_repair) + goto out; + + ret = btrfs_may_alloc_data_chunk(fs_info, target); + if (ret < 0) + goto out; + + btrfs_info(fs_info, + "zoned: relocating block group %llu to repair IO failure", + target); + ret = btrfs_relocate_chunk(fs_info, target); + +out: + if (cache) + btrfs_put_block_group(cache); + mutex_unlock(&fs_info->delete_unused_bgs_mutex); + btrfs_exclop_finish(fs_info); + + return ret; +} + +int btrfs_repair_one_zone(struct btrfs_fs_info *fs_info, u64 logical) +{ + struct btrfs_block_group *cache; + + /* Do not attempt to repair in degraded state */ + if (btrfs_test_opt(fs_info, DEGRADED)) + return 0; + + cache = btrfs_lookup_block_group(fs_info, logical); + if (!cache) + return 0; + + spin_lock(&cache->lock); + if (cache->relocating_repair) { + spin_unlock(&cache->lock); + btrfs_put_block_group(cache); + return 0; + } + cache->relocating_repair = 1; + spin_unlock(&cache->lock); + + kthread_run(relocating_repair_kthread, cache, + "btrfs-relocating-repair"); + + return 0; +} diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index bf27ac07d315..d4c3e0dd32b8 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -50,6 +50,9 @@ struct btrfs_io_geometry { #define BTRFS_DEV_STATE_MISSING (2) #define BTRFS_DEV_STATE_REPLACE_TGT (3) #define BTRFS_DEV_STATE_FLUSH_SENT (4) +#define BTRFS_DEV_STATE_NO_READA (5) + +struct btrfs_zoned_device_info; struct btrfs_device { struct list_head dev_list; /* device_list_mutex */ @@ -64,6 +67,8 @@ struct btrfs_device { struct block_device *bdev; + struct btrfs_zoned_device_info *zone_info; + /* the mode sent to blkdev_get */ fmode_t mode; @@ -209,6 +214,17 @@ BTRFS_DEVICE_GETSET_FUNCS(bytes_used); enum btrfs_chunk_allocation_policy { BTRFS_CHUNK_ALLOC_REGULAR, + BTRFS_CHUNK_ALLOC_ZONED, +}; + +/* + * Read policies for mirrored block group profiles, read picks the stripe based + * on these policies. + */ +enum btrfs_read_policy { + /* Use process PID to choose the stripe */ + BTRFS_READ_POLICY_PID, + BTRFS_NR_READ_POLICY, }; struct btrfs_fs_devices { @@ -264,6 +280,9 @@ struct btrfs_fs_devices { struct completion kobj_unregister; enum btrfs_chunk_allocation_policy chunk_alloc_policy; + + /* Policy used to read the mirrored stripes */ + enum btrfs_read_policy read_policy; }; #define BTRFS_BIO_INLINE_CSUM_SIZE 64 @@ -405,6 +424,7 @@ static inline enum btrfs_map_op btrfs_op(struct bio *bio) case REQ_OP_DISCARD: return BTRFS_MAP_DISCARD; case REQ_OP_WRITE: + case REQ_OP_ZONE_APPEND: return BTRFS_MAP_WRITE; default: WARN_ON_ONCE(1); @@ -422,8 +442,9 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, int btrfs_map_sblock(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, u64 logical, u64 *length, struct btrfs_bio **bbio_ret); -int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, - u64 logical, u64 len, struct btrfs_io_geometry *io_geom); +int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, struct extent_map *map, + enum btrfs_map_op op, u64 logical, u64 len, + struct btrfs_io_geometry *io_geom); int btrfs_read_sys_array(struct btrfs_fs_info *fs_info); int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info); int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, u64 type); @@ -436,7 +457,7 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, fmode_t flags, void *holder); int btrfs_forget_devices(const char *path); void btrfs_close_devices(struct btrfs_fs_devices *fs_devices); -void btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices, int step); +void btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices); void btrfs_assign_next_active_device(struct btrfs_device *device, struct btrfs_device *this_dev); struct btrfs_device *btrfs_find_device_by_devspec(struct btrfs_fs_info *fs_info, @@ -453,7 +474,7 @@ int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len); int btrfs_grow_device(struct btrfs_trans_handle *trans, struct btrfs_device *device, u64 new_size); struct btrfs_device *btrfs_find_device(struct btrfs_fs_devices *fs_devices, - u64 devid, u8 *uuid, u8 *fsid, bool seed); + u64 devid, u8 *uuid, u8 *fsid); int btrfs_shrink_device(struct btrfs_device *device, u64 new_size); int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *path); int btrfs_balance(struct btrfs_fs_info *fs_info, @@ -578,5 +599,6 @@ void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info, int btrfs_bg_type_to_factor(u64 flags); const char *btrfs_bg_type_to_raid_name(u64 flags); int btrfs_verify_dev_extents(struct btrfs_fs_info *fs_info); +int btrfs_repair_one_zone(struct btrfs_fs_info *fs_info, u64 logical); #endif diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index 95d9aebff2c4..af6246f36a9e 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -213,9 +213,11 @@ int btrfs_setxattr(struct btrfs_trans_handle *trans, struct inode *inode, } out: btrfs_free_path(path); - if (!ret) + if (!ret) { set_bit(BTRFS_INODE_COPY_EVERYTHING, &BTRFS_I(inode)->runtime_flags); + clear_bit(BTRFS_INODE_NO_XATTRS, &BTRFS_I(inode)->runtime_flags); + } return ret; } @@ -239,7 +241,7 @@ 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, inode); + ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); BUG_ON(ret); out: btrfs_end_transaction(trans); @@ -390,7 +392,7 @@ static int btrfs_xattr_handler_set_prop(const struct xattr_handler *handler, if (!ret) { inode_inc_iversion(inode); inode->i_ctime = current_time(inode); - ret = btrfs_update_inode(trans, root, inode); + ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); BUG_ON(ret); } diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c new file mode 100644 index 000000000000..d0eb0c8d6269 --- /dev/null +++ b/fs/btrfs/zoned.c @@ -0,0 +1,1461 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bitops.h> +#include <linux/slab.h> +#include <linux/blkdev.h> +#include <linux/sched/mm.h> +#include "ctree.h" +#include "volumes.h" +#include "zoned.h" +#include "rcu-string.h" +#include "disk-io.h" +#include "block-group.h" +#include "transaction.h" +#include "dev-replace.h" +#include "space-info.h" + +/* Maximum number of zones to report per blkdev_report_zones() call */ +#define BTRFS_REPORT_NR_ZONES 4096 +/* Invalid allocation pointer value for missing devices */ +#define WP_MISSING_DEV ((u64)-1) +/* Pseudo write pointer value for conventional zone */ +#define WP_CONVENTIONAL ((u64)-2) + +/* Number of superblock log zones */ +#define BTRFS_NR_SB_LOG_ZONES 2 + +static int copy_zone_info_cb(struct blk_zone *zone, unsigned int idx, void *data) +{ + struct blk_zone *zones = data; + + memcpy(&zones[idx], zone, sizeof(*zone)); + + return 0; +} + +static int sb_write_pointer(struct block_device *bdev, struct blk_zone *zones, + u64 *wp_ret) +{ + bool empty[BTRFS_NR_SB_LOG_ZONES]; + bool full[BTRFS_NR_SB_LOG_ZONES]; + sector_t sector; + + ASSERT(zones[0].type != BLK_ZONE_TYPE_CONVENTIONAL && + zones[1].type != BLK_ZONE_TYPE_CONVENTIONAL); + + empty[0] = (zones[0].cond == BLK_ZONE_COND_EMPTY); + empty[1] = (zones[1].cond == BLK_ZONE_COND_EMPTY); + full[0] = (zones[0].cond == BLK_ZONE_COND_FULL); + full[1] = (zones[1].cond == BLK_ZONE_COND_FULL); + + /* + * Possible states of log buffer zones + * + * Empty[0] In use[0] Full[0] + * Empty[1] * x 0 + * In use[1] 0 x 0 + * Full[1] 1 1 C + * + * Log position: + * *: Special case, no superblock is written + * 0: Use write pointer of zones[0] + * 1: Use write pointer of zones[1] + * C: Compare super blcoks from zones[0] and zones[1], use the latest + * one determined by generation + * x: Invalid state + */ + + if (empty[0] && empty[1]) { + /* Special case to distinguish no superblock to read */ + *wp_ret = zones[0].start << SECTOR_SHIFT; + return -ENOENT; + } else if (full[0] && full[1]) { + /* Compare two super blocks */ + struct address_space *mapping = bdev->bd_inode->i_mapping; + struct page *page[BTRFS_NR_SB_LOG_ZONES]; + struct btrfs_super_block *super[BTRFS_NR_SB_LOG_ZONES]; + int i; + + for (i = 0; i < BTRFS_NR_SB_LOG_ZONES; i++) { + u64 bytenr; + + bytenr = ((zones[i].start + zones[i].len) + << SECTOR_SHIFT) - BTRFS_SUPER_INFO_SIZE; + + page[i] = read_cache_page_gfp(mapping, + bytenr >> PAGE_SHIFT, GFP_NOFS); + if (IS_ERR(page[i])) { + if (i == 1) + btrfs_release_disk_super(super[0]); + return PTR_ERR(page[i]); + } + super[i] = page_address(page[i]); + } + + if (super[0]->generation > super[1]->generation) + sector = zones[1].start; + else + sector = zones[0].start; + + for (i = 0; i < BTRFS_NR_SB_LOG_ZONES; i++) + btrfs_release_disk_super(super[i]); + } else if (!full[0] && (empty[1] || full[1])) { + sector = zones[0].wp; + } else if (full[0]) { + sector = zones[1].wp; + } else { + return -EUCLEAN; + } + *wp_ret = sector << SECTOR_SHIFT; + return 0; +} + +/* + * The following zones are reserved as the circular buffer on ZONED btrfs. + * - The primary superblock: zones 0 and 1 + * - The first copy: zones 16 and 17 + * - The second copy: zones 1024 or zone at 256GB which is minimum, and + * the following one + */ +static inline u32 sb_zone_number(int shift, int mirror) +{ + ASSERT(mirror < BTRFS_SUPER_MIRROR_MAX); + + switch (mirror) { + case 0: return 0; + case 1: return 16; + case 2: return min_t(u64, btrfs_sb_offset(mirror) >> shift, 1024); + } + + return 0; +} + +/* + * Emulate blkdev_report_zones() for a non-zoned device. It slices up the block + * device into static sized chunks and fake a conventional zone on each of + * them. + */ +static int emulate_report_zones(struct btrfs_device *device, u64 pos, + struct blk_zone *zones, unsigned int nr_zones) +{ + const sector_t zone_sectors = device->fs_info->zone_size >> SECTOR_SHIFT; + sector_t bdev_size = bdev_nr_sectors(device->bdev); + unsigned int i; + + pos >>= SECTOR_SHIFT; + for (i = 0; i < nr_zones; i++) { + zones[i].start = i * zone_sectors + pos; + zones[i].len = zone_sectors; + zones[i].capacity = zone_sectors; + zones[i].wp = zones[i].start + zone_sectors; + zones[i].type = BLK_ZONE_TYPE_CONVENTIONAL; + zones[i].cond = BLK_ZONE_COND_NOT_WP; + + if (zones[i].wp >= bdev_size) { + i++; + break; + } + } + + return i; +} + +static int btrfs_get_dev_zones(struct btrfs_device *device, u64 pos, + struct blk_zone *zones, unsigned int *nr_zones) +{ + int ret; + + if (!*nr_zones) + return 0; + + if (!bdev_is_zoned(device->bdev)) { + ret = emulate_report_zones(device, pos, zones, *nr_zones); + *nr_zones = ret; + return 0; + } + + ret = blkdev_report_zones(device->bdev, pos >> SECTOR_SHIFT, *nr_zones, + copy_zone_info_cb, zones); + if (ret < 0) { + btrfs_err_in_rcu(device->fs_info, + "zoned: failed to read zone %llu on %s (devid %llu)", + pos, rcu_str_deref(device->name), + device->devid); + return ret; + } + *nr_zones = ret; + if (!ret) + return -EIO; + + return 0; +} + +/* 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; + struct btrfs_root *root = fs_info->dev_root; + struct btrfs_key key; + struct extent_buffer *leaf; + struct btrfs_dev_extent *dext; + int ret = 0; + + key.objectid = 1; + key.type = BTRFS_DEV_EXTENT_KEY; + key.offset = 0; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) + goto out; + + if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) { + ret = btrfs_next_item(root, path); + if (ret < 0) + goto out; + /* No dev extents at all? Not good */ + if (ret > 0) { + ret = -EUCLEAN; + goto out; + } + } + + 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; +} + +int btrfs_get_dev_zone_info_all_devices(struct btrfs_fs_info *fs_info) +{ + struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; + struct btrfs_device *device; + int ret = 0; + + /* fs_info->zone_size might not set yet. Use the incomapt flag here. */ + if (!btrfs_fs_incompat(fs_info, ZONED)) + return 0; + + mutex_lock(&fs_devices->device_list_mutex); + list_for_each_entry(device, &fs_devices->devices, dev_list) { + /* We can skip reading of zone info for missing devices */ + if (!device->bdev) + continue; + + ret = btrfs_get_dev_zone_info(device); + if (ret) + break; + } + mutex_unlock(&fs_devices->device_list_mutex); + + return ret; +} + +int btrfs_get_dev_zone_info(struct btrfs_device *device) +{ + struct btrfs_fs_info *fs_info = device->fs_info; + struct btrfs_zoned_device_info *zone_info = NULL; + struct block_device *bdev = device->bdev; + struct request_queue *queue = bdev_get_queue(bdev); + sector_t nr_sectors; + sector_t sector = 0; + struct blk_zone *zones = NULL; + unsigned int i, nreported = 0, nr_zones; + unsigned int zone_sectors; + char *model, *emulated; + int ret; + + /* + * Cannot use btrfs_is_zoned here, since fs_info::zone_size might not + * yet be set. + */ + if (!btrfs_fs_incompat(fs_info, ZONED)) + return 0; + + if (device->zone_info) + return 0; + + zone_info = kzalloc(sizeof(*zone_info), GFP_KERNEL); + if (!zone_info) + return -ENOMEM; + + if (!bdev_is_zoned(bdev)) { + if (!fs_info->zone_size) { + ret = calculate_emulated_zone_size(fs_info); + if (ret) + goto out; + } + + ASSERT(fs_info->zone_size); + zone_sectors = fs_info->zone_size >> SECTOR_SHIFT; + } else { + zone_sectors = bdev_zone_sectors(bdev); + } + + nr_sectors = bdev_nr_sectors(bdev); + /* Check if it's power of 2 (see is_power_of_2) */ + ASSERT(zone_sectors != 0 && (zone_sectors & (zone_sectors - 1)) == 0); + zone_info->zone_size = zone_sectors << SECTOR_SHIFT; + zone_info->zone_size_shift = ilog2(zone_info->zone_size); + zone_info->max_zone_append_size = + (u64)queue_max_zone_append_sectors(queue) << SECTOR_SHIFT; + zone_info->nr_zones = nr_sectors >> ilog2(zone_sectors); + if (!IS_ALIGNED(nr_sectors, zone_sectors)) + zone_info->nr_zones++; + + zone_info->seq_zones = bitmap_zalloc(zone_info->nr_zones, GFP_KERNEL); + if (!zone_info->seq_zones) { + ret = -ENOMEM; + goto out; + } + + zone_info->empty_zones = bitmap_zalloc(zone_info->nr_zones, GFP_KERNEL); + if (!zone_info->empty_zones) { + ret = -ENOMEM; + goto out; + } + + zones = kcalloc(BTRFS_REPORT_NR_ZONES, sizeof(struct blk_zone), GFP_KERNEL); + if (!zones) { + ret = -ENOMEM; + goto out; + } + + /* Get zones type */ + while (sector < nr_sectors) { + nr_zones = BTRFS_REPORT_NR_ZONES; + ret = btrfs_get_dev_zones(device, sector << SECTOR_SHIFT, zones, + &nr_zones); + if (ret) + goto out; + + for (i = 0; i < nr_zones; i++) { + if (zones[i].type == BLK_ZONE_TYPE_SEQWRITE_REQ) + __set_bit(nreported, zone_info->seq_zones); + if (zones[i].cond == BLK_ZONE_COND_EMPTY) + __set_bit(nreported, zone_info->empty_zones); + nreported++; + } + sector = zones[nr_zones - 1].start + zones[nr_zones - 1].len; + } + + if (nreported != zone_info->nr_zones) { + btrfs_err_in_rcu(device->fs_info, + "inconsistent number of zones on %s (%u/%u)", + rcu_str_deref(device->name), nreported, + zone_info->nr_zones); + ret = -EIO; + goto out; + } + + /* Validate superblock log */ + nr_zones = BTRFS_NR_SB_LOG_ZONES; + for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) { + u32 sb_zone; + u64 sb_wp; + int sb_pos = BTRFS_NR_SB_LOG_ZONES * i; + + sb_zone = sb_zone_number(zone_info->zone_size_shift, i); + if (sb_zone + 1 >= zone_info->nr_zones) + continue; + + sector = sb_zone << (zone_info->zone_size_shift - SECTOR_SHIFT); + ret = btrfs_get_dev_zones(device, sector << SECTOR_SHIFT, + &zone_info->sb_zones[sb_pos], + &nr_zones); + if (ret) + goto out; + + if (nr_zones != BTRFS_NR_SB_LOG_ZONES) { + btrfs_err_in_rcu(device->fs_info, + "zoned: failed to read super block log zone info at devid %llu zone %u", + device->devid, sb_zone); + ret = -EUCLEAN; + goto out; + } + + /* + * If zones[0] is conventional, always use the beggining of the + * zone to record superblock. No need to validate in that case. + */ + if (zone_info->sb_zones[BTRFS_NR_SB_LOG_ZONES * i].type == + BLK_ZONE_TYPE_CONVENTIONAL) + continue; + + ret = sb_write_pointer(device->bdev, + &zone_info->sb_zones[sb_pos], &sb_wp); + if (ret != -ENOENT && ret) { + btrfs_err_in_rcu(device->fs_info, + "zoned: super block log zone corrupted devid %llu zone %u", + device->devid, sb_zone); + ret = -EUCLEAN; + goto out; + } + } + + + kfree(zones); + + device->zone_info = zone_info; + + switch (bdev_zoned_model(bdev)) { + case BLK_ZONED_HM: + model = "host-managed zoned"; + emulated = ""; + break; + case BLK_ZONED_HA: + model = "host-aware zoned"; + emulated = ""; + break; + case BLK_ZONED_NONE: + model = "regular"; + emulated = "emulated "; + break; + default: + /* Just in case */ + btrfs_err_in_rcu(fs_info, "zoned: unsupported model %d on %s", + bdev_zoned_model(bdev), + rcu_str_deref(device->name)); + ret = -EOPNOTSUPP; + goto out_free_zone_info; + } + + btrfs_info_in_rcu(fs_info, + "%s block device %s, %u %szones of %llu bytes", + model, rcu_str_deref(device->name), zone_info->nr_zones, + emulated, zone_info->zone_size); + + return 0; + +out: + kfree(zones); +out_free_zone_info: + bitmap_free(zone_info->empty_zones); + bitmap_free(zone_info->seq_zones); + kfree(zone_info); + device->zone_info = NULL; + + return ret; +} + +void btrfs_destroy_dev_zone_info(struct btrfs_device *device) +{ + struct btrfs_zoned_device_info *zone_info = device->zone_info; + + if (!zone_info) + return; + + bitmap_free(zone_info->seq_zones); + bitmap_free(zone_info->empty_zones); + kfree(zone_info); + device->zone_info = NULL; +} + +int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos, + struct blk_zone *zone) +{ + unsigned int nr_zones = 1; + int ret; + + ret = btrfs_get_dev_zones(device, pos, zone, &nr_zones); + if (ret != 0 || !nr_zones) + return ret ? ret : -EIO; + + return 0; +} + +int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info) +{ + struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; + struct btrfs_device *device; + u64 zoned_devices = 0; + u64 nr_devices = 0; + u64 zone_size = 0; + u64 max_zone_append_size = 0; + const bool incompat_zoned = btrfs_fs_incompat(fs_info, ZONED); + int ret = 0; + + /* Count zoned devices */ + list_for_each_entry(device, &fs_devices->devices, dev_list) { + enum blk_zoned_model model; + + if (!device->bdev) + continue; + + model = bdev_zoned_model(device->bdev); + /* + * A Host-Managed zoned device must be used as a zoned device. + * A Host-Aware zoned device and a non-zoned devices can be + * treated as a zoned device, if ZONED flag is enabled in the + * superblock. + */ + if (model == BLK_ZONED_HM || + (model == BLK_ZONED_HA && incompat_zoned) || + (model == BLK_ZONED_NONE && incompat_zoned)) { + struct btrfs_zoned_device_info *zone_info = + device->zone_info; + + zone_info = device->zone_info; + zoned_devices++; + if (!zone_size) { + zone_size = zone_info->zone_size; + } else if (zone_info->zone_size != zone_size) { + btrfs_err(fs_info, + "zoned: unequal block device zone sizes: have %llu found %llu", + device->zone_info->zone_size, + zone_size); + ret = -EINVAL; + goto out; + } + if (!max_zone_append_size || + (zone_info->max_zone_append_size && + zone_info->max_zone_append_size < max_zone_append_size)) + max_zone_append_size = + zone_info->max_zone_append_size; + } + nr_devices++; + } + + if (!zoned_devices && !incompat_zoned) + goto out; + + if (!zoned_devices && incompat_zoned) { + /* No zoned block device found on ZONED filesystem */ + btrfs_err(fs_info, + "zoned: no zoned devices found on a zoned filesystem"); + ret = -EINVAL; + goto out; + } + + if (zoned_devices && !incompat_zoned) { + btrfs_err(fs_info, + "zoned: mode not enabled but zoned device found"); + ret = -EINVAL; + goto out; + } + + if (zoned_devices != nr_devices) { + btrfs_err(fs_info, + "zoned: cannot mix zoned and regular devices"); + ret = -EINVAL; + goto out; + } + + /* + * stripe_size is always aligned to BTRFS_STRIPE_LEN in + * __btrfs_alloc_chunk(). Since we want stripe_len == zone_size, + * check the alignment here. + */ + if (!IS_ALIGNED(zone_size, BTRFS_STRIPE_LEN)) { + btrfs_err(fs_info, + "zoned: zone size %llu not aligned to stripe %u", + zone_size, BTRFS_STRIPE_LEN); + ret = -EINVAL; + goto out; + } + + if (btrfs_fs_incompat(fs_info, MIXED_GROUPS)) { + btrfs_err(fs_info, "zoned: mixed block groups not supported"); + ret = -EINVAL; + goto out; + } + + fs_info->zone_size = zone_size; + fs_info->max_zone_append_size = max_zone_append_size; + fs_info->fs_devices->chunk_alloc_policy = BTRFS_CHUNK_ALLOC_ZONED; + + /* + * Check mount options here, because we might change fs_info->zoned + * from fs_info->zone_size. + */ + ret = btrfs_check_mountopts_zoned(fs_info); + if (ret) + goto out; + + btrfs_info(fs_info, "zoned mode enabled with zone size %llu", zone_size); +out: + return ret; +} + +int btrfs_check_mountopts_zoned(struct btrfs_fs_info *info) +{ + if (!btrfs_is_zoned(info)) + return 0; + + /* + * Space cache writing is not COWed. Disable that to avoid write errors + * in sequential zones. + */ + if (btrfs_test_opt(info, SPACE_CACHE)) { + btrfs_err(info, "zoned: space cache v1 is not supported"); + return -EINVAL; + } + + if (btrfs_test_opt(info, NODATACOW)) { + btrfs_err(info, "zoned: NODATACOW not supported"); + return -EINVAL; + } + + return 0; +} + +static int sb_log_location(struct block_device *bdev, struct blk_zone *zones, + int rw, u64 *bytenr_ret) +{ + u64 wp; + int ret; + + if (zones[0].type == BLK_ZONE_TYPE_CONVENTIONAL) { + *bytenr_ret = zones[0].start << SECTOR_SHIFT; + return 0; + } + + ret = sb_write_pointer(bdev, zones, &wp); + if (ret != -ENOENT && ret < 0) + return ret; + + if (rw == WRITE) { + struct blk_zone *reset = NULL; + + if (wp == zones[0].start << SECTOR_SHIFT) + reset = &zones[0]; + else if (wp == zones[1].start << SECTOR_SHIFT) + reset = &zones[1]; + + if (reset && reset->cond != BLK_ZONE_COND_EMPTY) { + ASSERT(reset->cond == BLK_ZONE_COND_FULL); + + ret = blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET, + reset->start, reset->len, + GFP_NOFS); + if (ret) + return ret; + + reset->cond = BLK_ZONE_COND_EMPTY; + reset->wp = reset->start; + } + } else if (ret != -ENOENT) { + /* For READ, we want the precious one */ + if (wp == zones[0].start << SECTOR_SHIFT) + wp = (zones[1].start + zones[1].len) << SECTOR_SHIFT; + wp -= BTRFS_SUPER_INFO_SIZE; + } + + *bytenr_ret = wp; + return 0; + +} + +int btrfs_sb_log_location_bdev(struct block_device *bdev, int mirror, int rw, + u64 *bytenr_ret) +{ + struct blk_zone zones[BTRFS_NR_SB_LOG_ZONES]; + unsigned int zone_sectors; + u32 sb_zone; + int ret; + u8 zone_sectors_shift; + sector_t nr_sectors; + u32 nr_zones; + + if (!bdev_is_zoned(bdev)) { + *bytenr_ret = btrfs_sb_offset(mirror); + return 0; + } + + ASSERT(rw == READ || rw == WRITE); + + zone_sectors = bdev_zone_sectors(bdev); + if (!is_power_of_2(zone_sectors)) + return -EINVAL; + zone_sectors_shift = ilog2(zone_sectors); + nr_sectors = bdev_nr_sectors(bdev); + nr_zones = nr_sectors >> zone_sectors_shift; + + sb_zone = sb_zone_number(zone_sectors_shift + SECTOR_SHIFT, mirror); + if (sb_zone + 1 >= nr_zones) + return -ENOENT; + + ret = blkdev_report_zones(bdev, sb_zone << zone_sectors_shift, + BTRFS_NR_SB_LOG_ZONES, copy_zone_info_cb, + zones); + if (ret < 0) + return ret; + if (ret != BTRFS_NR_SB_LOG_ZONES) + return -EIO; + + return sb_log_location(bdev, zones, rw, bytenr_ret); +} + +int btrfs_sb_log_location(struct btrfs_device *device, int mirror, int rw, + u64 *bytenr_ret) +{ + struct btrfs_zoned_device_info *zinfo = device->zone_info; + u32 zone_num; + + /* + * For a zoned filesystem on a non-zoned block device, use the same + * super block locations as regular filesystem. Doing so, the super + * block can always be retrieved and the zoned flag of the volume + * detected from the super block information. + */ + if (!bdev_is_zoned(device->bdev)) { + *bytenr_ret = btrfs_sb_offset(mirror); + return 0; + } + + zone_num = sb_zone_number(zinfo->zone_size_shift, mirror); + if (zone_num + 1 >= zinfo->nr_zones) + return -ENOENT; + + return sb_log_location(device->bdev, + &zinfo->sb_zones[BTRFS_NR_SB_LOG_ZONES * mirror], + rw, bytenr_ret); +} + +static inline bool is_sb_log_zone(struct btrfs_zoned_device_info *zinfo, + int mirror) +{ + u32 zone_num; + + if (!zinfo) + return false; + + zone_num = sb_zone_number(zinfo->zone_size_shift, mirror); + if (zone_num + 1 >= zinfo->nr_zones) + return false; + + if (!test_bit(zone_num, zinfo->seq_zones)) + return false; + + return true; +} + +void btrfs_advance_sb_log(struct btrfs_device *device, int mirror) +{ + struct btrfs_zoned_device_info *zinfo = device->zone_info; + struct blk_zone *zone; + + if (!is_sb_log_zone(zinfo, mirror)) + return; + + zone = &zinfo->sb_zones[BTRFS_NR_SB_LOG_ZONES * mirror]; + if (zone->cond != BLK_ZONE_COND_FULL) { + if (zone->cond == BLK_ZONE_COND_EMPTY) + zone->cond = BLK_ZONE_COND_IMP_OPEN; + + zone->wp += (BTRFS_SUPER_INFO_SIZE >> SECTOR_SHIFT); + + if (zone->wp == zone->start + zone->len) + zone->cond = BLK_ZONE_COND_FULL; + + return; + } + + zone++; + ASSERT(zone->cond != BLK_ZONE_COND_FULL); + if (zone->cond == BLK_ZONE_COND_EMPTY) + zone->cond = BLK_ZONE_COND_IMP_OPEN; + + zone->wp += (BTRFS_SUPER_INFO_SIZE >> SECTOR_SHIFT); + + if (zone->wp == zone->start + zone->len) + zone->cond = BLK_ZONE_COND_FULL; +} + +int btrfs_reset_sb_log_zones(struct block_device *bdev, int mirror) +{ + sector_t zone_sectors; + sector_t nr_sectors; + u8 zone_sectors_shift; + u32 sb_zone; + u32 nr_zones; + + zone_sectors = bdev_zone_sectors(bdev); + zone_sectors_shift = ilog2(zone_sectors); + nr_sectors = bdev_nr_sectors(bdev); + nr_zones = nr_sectors >> zone_sectors_shift; + + sb_zone = sb_zone_number(zone_sectors_shift + SECTOR_SHIFT, mirror); + if (sb_zone + 1 >= nr_zones) + return -ENOENT; + + return blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET, + sb_zone << zone_sectors_shift, + zone_sectors * BTRFS_NR_SB_LOG_ZONES, GFP_NOFS); +} + +/** + * btrfs_find_allocatable_zones - find allocatable zones within a given region + * + * @device: the device to allocate a region on + * @hole_start: the position of the hole to allocate the region + * @num_bytes: size of wanted region + * @hole_end: the end of the hole + * @return: position of allocatable zones + * + * Allocatable region should not contain any superblock locations. + */ +u64 btrfs_find_allocatable_zones(struct btrfs_device *device, u64 hole_start, + u64 hole_end, u64 num_bytes) +{ + struct btrfs_zoned_device_info *zinfo = device->zone_info; + const u8 shift = zinfo->zone_size_shift; + u64 nzones = num_bytes >> shift; + u64 pos = hole_start; + u64 begin, end; + bool have_sb; + int i; + + ASSERT(IS_ALIGNED(hole_start, zinfo->zone_size)); + ASSERT(IS_ALIGNED(num_bytes, zinfo->zone_size)); + + while (pos < hole_end) { + begin = pos >> shift; + end = begin + nzones; + + if (end > zinfo->nr_zones) + return hole_end; + + /* Check if zones in the region are all empty */ + if (btrfs_dev_is_sequential(device, pos) && + find_next_zero_bit(zinfo->empty_zones, end, begin) != end) { + pos += zinfo->zone_size; + continue; + } + + have_sb = false; + for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) { + u32 sb_zone; + u64 sb_pos; + + sb_zone = sb_zone_number(shift, i); + if (!(end <= sb_zone || + sb_zone + BTRFS_NR_SB_LOG_ZONES <= begin)) { + have_sb = true; + pos = ((u64)sb_zone + BTRFS_NR_SB_LOG_ZONES) << shift; + break; + } + + /* We also need to exclude regular superblock positions */ + sb_pos = btrfs_sb_offset(i); + if (!(pos + num_bytes <= sb_pos || + sb_pos + BTRFS_SUPER_INFO_SIZE <= pos)) { + have_sb = true; + pos = ALIGN(sb_pos + BTRFS_SUPER_INFO_SIZE, + zinfo->zone_size); + break; + } + } + if (!have_sb) + break; + } + + return pos; +} + +int btrfs_reset_device_zone(struct btrfs_device *device, u64 physical, + u64 length, u64 *bytes) +{ + int ret; + + *bytes = 0; + ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_RESET, + physical >> SECTOR_SHIFT, length >> SECTOR_SHIFT, + GFP_NOFS); + if (ret) + return ret; + + *bytes = length; + while (length) { + btrfs_dev_set_zone_empty(device, physical); + physical += device->zone_info->zone_size; + length -= device->zone_info->zone_size; + } + + return 0; +} + +int btrfs_ensure_empty_zones(struct btrfs_device *device, u64 start, u64 size) +{ + struct btrfs_zoned_device_info *zinfo = device->zone_info; + const u8 shift = zinfo->zone_size_shift; + unsigned long begin = start >> shift; + unsigned long end = (start + size) >> shift; + u64 pos; + int ret; + + ASSERT(IS_ALIGNED(start, zinfo->zone_size)); + ASSERT(IS_ALIGNED(size, zinfo->zone_size)); + + if (end > zinfo->nr_zones) + return -ERANGE; + + /* All the zones are conventional */ + if (find_next_bit(zinfo->seq_zones, begin, end) == end) + return 0; + + /* All the zones are sequential and empty */ + if (find_next_zero_bit(zinfo->seq_zones, begin, end) == end && + find_next_zero_bit(zinfo->empty_zones, begin, end) == end) + return 0; + + for (pos = start; pos < start + size; pos += zinfo->zone_size) { + u64 reset_bytes; + + if (!btrfs_dev_is_sequential(device, pos) || + btrfs_dev_is_empty_zone(device, pos)) + continue; + + /* Free regions should be empty */ + btrfs_warn_in_rcu( + device->fs_info, + "zoned: resetting device %s (devid %llu) zone %llu for allocation", + rcu_str_deref(device->name), device->devid, pos >> shift); + WARN_ON_ONCE(1); + + ret = btrfs_reset_device_zone(device, pos, zinfo->zone_size, + &reset_bytes); + if (ret) + return ret; + } + + return 0; +} + +/* + * Calculate an allocation pointer from the extent allocation information + * for a block group consist of conventional zones. It is pointed to the + * end of the highest addressed extent in the block group as an allocation + * offset. + */ +static int calculate_alloc_pointer(struct btrfs_block_group *cache, + u64 *offset_ret) +{ + struct btrfs_fs_info *fs_info = cache->fs_info; + struct btrfs_root *root = fs_info->extent_root; + struct btrfs_path *path; + struct btrfs_key key; + struct btrfs_key found_key; + int ret; + u64 length; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + + key.objectid = cache->start + cache->length; + key.type = 0; + key.offset = 0; + + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + /* We should not find the exact match */ + if (!ret) + ret = -EUCLEAN; + if (ret < 0) + goto out; + + ret = btrfs_previous_extent_item(root, path, cache->start); + if (ret) { + if (ret == 1) { + ret = 0; + *offset_ret = 0; + } + goto out; + } + + btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]); + + if (found_key.type == BTRFS_EXTENT_ITEM_KEY) + length = found_key.offset; + else + length = fs_info->nodesize; + + if (!(found_key.objectid >= cache->start && + found_key.objectid + length <= cache->start + cache->length)) { + ret = -EUCLEAN; + goto out; + } + *offset_ret = found_key.objectid + length - cache->start; + ret = 0; + +out: + btrfs_free_path(path); + return ret; +} + +int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) +{ + struct btrfs_fs_info *fs_info = cache->fs_info; + struct extent_map_tree *em_tree = &fs_info->mapping_tree; + struct extent_map *em; + struct map_lookup *map; + struct btrfs_device *device; + u64 logical = cache->start; + u64 length = cache->length; + u64 physical = 0; + int ret; + int i; + unsigned int nofs_flag; + u64 *alloc_offsets = NULL; + u64 last_alloc = 0; + u32 num_sequential = 0, num_conventional = 0; + + if (!btrfs_is_zoned(fs_info)) + return 0; + + /* Sanity check */ + if (!IS_ALIGNED(length, fs_info->zone_size)) { + btrfs_err(fs_info, + "zoned: block group %llu len %llu unaligned to zone size %llu", + logical, length, fs_info->zone_size); + return -EIO; + } + + /* Get the chunk mapping */ + read_lock(&em_tree->lock); + em = lookup_extent_mapping(em_tree, logical, length); + read_unlock(&em_tree->lock); + + if (!em) + return -EINVAL; + + map = em->map_lookup; + + alloc_offsets = kcalloc(map->num_stripes, sizeof(*alloc_offsets), GFP_NOFS); + if (!alloc_offsets) { + free_extent_map(em); + return -ENOMEM; + } + + for (i = 0; i < map->num_stripes; i++) { + bool is_sequential; + struct blk_zone zone; + struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace; + int dev_replace_is_ongoing = 0; + + device = map->stripes[i].dev; + physical = map->stripes[i].physical; + + if (device->bdev == NULL) { + alloc_offsets[i] = WP_MISSING_DEV; + continue; + } + + is_sequential = btrfs_dev_is_sequential(device, physical); + if (is_sequential) + num_sequential++; + else + num_conventional++; + + if (!is_sequential) { + alloc_offsets[i] = WP_CONVENTIONAL; + continue; + } + + /* + * This zone will be used for allocation, so mark this zone + * non-empty. + */ + btrfs_dev_clear_zone_empty(device, physical); + + down_read(&dev_replace->rwsem); + dev_replace_is_ongoing = btrfs_dev_replace_is_ongoing(dev_replace); + if (dev_replace_is_ongoing && dev_replace->tgtdev != NULL) + btrfs_dev_clear_zone_empty(dev_replace->tgtdev, physical); + up_read(&dev_replace->rwsem); + + /* + * The group is mapped to a sequential zone. Get the zone write + * pointer to determine the allocation offset within the zone. + */ + WARN_ON(!IS_ALIGNED(physical, fs_info->zone_size)); + nofs_flag = memalloc_nofs_save(); + ret = btrfs_get_dev_zone(device, physical, &zone); + memalloc_nofs_restore(nofs_flag); + if (ret == -EIO || ret == -EOPNOTSUPP) { + ret = 0; + alloc_offsets[i] = WP_MISSING_DEV; + continue; + } else if (ret) { + goto out; + } + + switch (zone.cond) { + case BLK_ZONE_COND_OFFLINE: + case BLK_ZONE_COND_READONLY: + btrfs_err(fs_info, + "zoned: offline/readonly zone %llu on device %s (devid %llu)", + physical >> device->zone_info->zone_size_shift, + rcu_str_deref(device->name), device->devid); + alloc_offsets[i] = WP_MISSING_DEV; + break; + case BLK_ZONE_COND_EMPTY: + alloc_offsets[i] = 0; + break; + case BLK_ZONE_COND_FULL: + alloc_offsets[i] = fs_info->zone_size; + break; + default: + /* Partially used zone */ + alloc_offsets[i] = + ((zone.wp - zone.start) << SECTOR_SHIFT); + break; + } + } + + if (num_sequential > 0) + cache->seq_zone = true; + + if (num_conventional > 0) { + /* + * Avoid calling calculate_alloc_pointer() for new BG. It + * is no use for new BG. It must be always 0. + * + * Also, we have a lock chain of extent buffer lock -> + * chunk mutex. For new BG, this function is called from + * btrfs_make_block_group() which is already taking the + * chunk mutex. Thus, we cannot call + * calculate_alloc_pointer() which takes extent buffer + * locks to avoid deadlock. + */ + if (new) { + cache->alloc_offset = 0; + goto out; + } + ret = calculate_alloc_pointer(cache, &last_alloc); + if (ret || map->num_stripes == num_conventional) { + if (!ret) + cache->alloc_offset = last_alloc; + else + btrfs_err(fs_info, + "zoned: failed to determine allocation offset of bg %llu", + cache->start); + goto out; + } + } + + switch (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) { + case 0: /* single */ + cache->alloc_offset = alloc_offsets[0]; + break; + case BTRFS_BLOCK_GROUP_DUP: + case BTRFS_BLOCK_GROUP_RAID1: + case BTRFS_BLOCK_GROUP_RAID0: + case BTRFS_BLOCK_GROUP_RAID10: + case BTRFS_BLOCK_GROUP_RAID5: + case BTRFS_BLOCK_GROUP_RAID6: + /* non-single profiles are not supported yet */ + default: + btrfs_err(fs_info, "zoned: profile %s not yet supported", + btrfs_bg_type_to_raid_name(map->type)); + ret = -EINVAL; + goto out; + } + +out: + /* An extent is allocated after the write pointer */ + if (!ret && num_conventional && last_alloc > cache->alloc_offset) { + btrfs_err(fs_info, + "zoned: got wrong write pointer in BG %llu: %llu > %llu", + logical, last_alloc, cache->alloc_offset); + ret = -EIO; + } + + if (!ret) + cache->meta_write_pointer = cache->alloc_offset + cache->start; + + kfree(alloc_offsets); + free_extent_map(em); + + return ret; +} + +void btrfs_calc_zone_unusable(struct btrfs_block_group *cache) +{ + u64 unusable, free; + + if (!btrfs_is_zoned(cache->fs_info)) + return; + + WARN_ON(cache->bytes_super != 0); + unusable = cache->alloc_offset - cache->used; + free = cache->length - cache->alloc_offset; + + /* We only need ->free_space in ALLOC_SEQ block groups */ + cache->last_byte_to_unpin = (u64)-1; + cache->cached = BTRFS_CACHE_FINISHED; + cache->free_space_ctl->free_space = free; + cache->zone_unusable = unusable; + + /* Should not have any excluded extents. Just in case, though */ + btrfs_free_excluded_extents(cache); +} + +void btrfs_redirty_list_add(struct btrfs_transaction *trans, + struct extent_buffer *eb) +{ + struct btrfs_fs_info *fs_info = eb->fs_info; + + if (!btrfs_is_zoned(fs_info) || + btrfs_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN) || + !list_empty(&eb->release_list)) + return; + + set_extent_buffer_dirty(eb); + set_extent_bits_nowait(&trans->dirty_pages, eb->start, + eb->start + eb->len - 1, EXTENT_DIRTY); + memzero_extent_buffer(eb, 0, eb->len); + set_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags); + + spin_lock(&trans->releasing_ebs_lock); + list_add_tail(&eb->release_list, &trans->releasing_ebs); + spin_unlock(&trans->releasing_ebs_lock); + atomic_inc(&eb->refs); +} + +void btrfs_free_redirty_list(struct btrfs_transaction *trans) +{ + spin_lock(&trans->releasing_ebs_lock); + while (!list_empty(&trans->releasing_ebs)) { + struct extent_buffer *eb; + + eb = list_first_entry(&trans->releasing_ebs, + struct extent_buffer, release_list); + list_del_init(&eb->release_list); + free_extent_buffer(eb); + } + spin_unlock(&trans->releasing_ebs_lock); +} + +bool btrfs_use_zone_append(struct btrfs_inode *inode, struct extent_map *em) +{ + struct btrfs_fs_info *fs_info = inode->root->fs_info; + struct btrfs_block_group *cache; + bool ret = false; + + if (!btrfs_is_zoned(fs_info)) + return false; + + if (!fs_info->max_zone_append_size) + return false; + + if (!is_data_inode(&inode->vfs_inode)) + return false; + + cache = btrfs_lookup_block_group(fs_info, em->block_start); + ASSERT(cache); + if (!cache) + return false; + + ret = cache->seq_zone; + btrfs_put_block_group(cache); + + return ret; +} + +void btrfs_record_physical_zoned(struct inode *inode, u64 file_offset, + struct bio *bio) +{ + struct btrfs_ordered_extent *ordered; + const u64 physical = bio->bi_iter.bi_sector << SECTOR_SHIFT; + + if (bio_op(bio) != REQ_OP_ZONE_APPEND) + return; + + ordered = btrfs_lookup_ordered_extent(BTRFS_I(inode), file_offset); + if (WARN_ON(!ordered)) + return; + + ordered->physical = physical; + ordered->disk = bio->bi_bdev->bd_disk; + ordered->partno = bio->bi_bdev->bd_partno; + + btrfs_put_ordered_extent(ordered); +} + +void btrfs_rewrite_logical_zoned(struct btrfs_ordered_extent *ordered) +{ + struct btrfs_inode *inode = BTRFS_I(ordered->inode); + struct btrfs_fs_info *fs_info = inode->root->fs_info; + struct extent_map_tree *em_tree; + struct extent_map *em; + struct btrfs_ordered_sum *sum; + struct block_device *bdev; + u64 orig_logical = ordered->disk_bytenr; + u64 *logical = NULL; + int nr, stripe_len; + + /* Zoned devices should not have partitions. So, we can assume it is 0 */ + ASSERT(ordered->partno == 0); + bdev = bdgrab(ordered->disk->part0); + if (WARN_ON(!bdev)) + return; + + if (WARN_ON(btrfs_rmap_block(fs_info, orig_logical, bdev, + ordered->physical, &logical, &nr, + &stripe_len))) + goto out; + + WARN_ON(nr != 1); + + if (orig_logical == *logical) + goto out; + + ordered->disk_bytenr = *logical; + + em_tree = &inode->extent_tree; + write_lock(&em_tree->lock); + em = search_extent_mapping(em_tree, ordered->file_offset, + ordered->num_bytes); + em->block_start = *logical; + free_extent_map(em); + write_unlock(&em_tree->lock); + + list_for_each_entry(sum, &ordered->list, list) { + if (*logical < orig_logical) + sum->bytenr -= orig_logical - *logical; + else + sum->bytenr += *logical - orig_logical; + } + +out: + kfree(logical); + bdput(bdev); +} + +bool btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info, + struct extent_buffer *eb, + struct btrfs_block_group **cache_ret) +{ + struct btrfs_block_group *cache; + bool ret = true; + + if (!btrfs_is_zoned(fs_info)) + return true; + + cache = *cache_ret; + + if (cache && (eb->start < cache->start || + cache->start + cache->length <= eb->start)) { + btrfs_put_block_group(cache); + cache = NULL; + *cache_ret = NULL; + } + + if (!cache) + cache = btrfs_lookup_block_group(fs_info, eb->start); + + if (cache) { + if (cache->meta_write_pointer != eb->start) { + btrfs_put_block_group(cache); + cache = NULL; + ret = false; + } else { + cache->meta_write_pointer = eb->start + eb->len; + } + + *cache_ret = cache; + } + + return ret; +} + +void btrfs_revert_meta_write_pointer(struct btrfs_block_group *cache, + struct extent_buffer *eb) +{ + if (!btrfs_is_zoned(eb->fs_info) || !cache) + return; + + ASSERT(cache->meta_write_pointer == eb->start + eb->len); + cache->meta_write_pointer = eb->start; +} + +int btrfs_zoned_issue_zeroout(struct btrfs_device *device, u64 physical, u64 length) +{ + if (!btrfs_dev_is_sequential(device, physical)) + return -EOPNOTSUPP; + + return blkdev_issue_zeroout(device->bdev, physical >> SECTOR_SHIFT, + length >> SECTOR_SHIFT, GFP_NOFS, 0); +} + +static int read_zone_info(struct btrfs_fs_info *fs_info, u64 logical, + struct blk_zone *zone) +{ + struct btrfs_bio *bbio = NULL; + u64 mapped_length = PAGE_SIZE; + unsigned int nofs_flag; + int nmirrors; + int i, ret; + + ret = btrfs_map_sblock(fs_info, BTRFS_MAP_GET_READ_MIRRORS, logical, + &mapped_length, &bbio); + if (ret || !bbio || mapped_length < PAGE_SIZE) { + btrfs_put_bbio(bbio); + return -EIO; + } + + if (bbio->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) + return -EINVAL; + + nofs_flag = memalloc_nofs_save(); + nmirrors = (int)bbio->num_stripes; + for (i = 0; i < nmirrors; i++) { + u64 physical = bbio->stripes[i].physical; + struct btrfs_device *dev = bbio->stripes[i].dev; + + /* Missing device */ + if (!dev->bdev) + continue; + + ret = btrfs_get_dev_zone(dev, physical, zone); + /* Failing device */ + if (ret == -EIO || ret == -EOPNOTSUPP) + continue; + break; + } + memalloc_nofs_restore(nofs_flag); + + return ret; +} + +/* + * Synchronize write pointer in a zone at @physical_start on @tgt_dev, by + * filling zeros between @physical_pos to a write pointer of dev-replace + * source device. + */ +int btrfs_sync_zone_write_pointer(struct btrfs_device *tgt_dev, u64 logical, + u64 physical_start, u64 physical_pos) +{ + struct btrfs_fs_info *fs_info = tgt_dev->fs_info; + struct blk_zone zone; + u64 length; + u64 wp; + int ret; + + if (!btrfs_dev_is_sequential(tgt_dev, physical_pos)) + return 0; + + ret = read_zone_info(fs_info, logical, &zone); + if (ret) + return ret; + + wp = physical_start + ((zone.wp - zone.start) << SECTOR_SHIFT); + + if (physical_pos == wp) + return 0; + + if (physical_pos > wp) + return -EUCLEAN; + + length = wp - physical_pos; + return btrfs_zoned_issue_zeroout(tgt_dev, physical_pos, length); +} diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h new file mode 100644 index 000000000000..61e969652fe1 --- /dev/null +++ b/fs/btrfs/zoned.h @@ -0,0 +1,307 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef BTRFS_ZONED_H +#define BTRFS_ZONED_H + +#include <linux/types.h> +#include <linux/blkdev.h> +#include "volumes.h" +#include "disk-io.h" +#include "block-group.h" + +struct btrfs_zoned_device_info { + /* + * Number of zones, zone size and types of zones if bdev is a + * zoned block device. + */ + u64 zone_size; + u8 zone_size_shift; + u64 max_zone_append_size; + u32 nr_zones; + unsigned long *seq_zones; + unsigned long *empty_zones; + struct blk_zone sb_zones[2 * BTRFS_SUPER_MIRROR_MAX]; +}; + +#ifdef CONFIG_BLK_DEV_ZONED +int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos, + struct blk_zone *zone); +int btrfs_get_dev_zone_info_all_devices(struct btrfs_fs_info *fs_info); +int btrfs_get_dev_zone_info(struct btrfs_device *device); +void btrfs_destroy_dev_zone_info(struct btrfs_device *device); +int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info); +int btrfs_check_mountopts_zoned(struct btrfs_fs_info *info); +int btrfs_sb_log_location_bdev(struct block_device *bdev, int mirror, int rw, + u64 *bytenr_ret); +int btrfs_sb_log_location(struct btrfs_device *device, int mirror, int rw, + u64 *bytenr_ret); +void btrfs_advance_sb_log(struct btrfs_device *device, int mirror); +int btrfs_reset_sb_log_zones(struct block_device *bdev, int mirror); +u64 btrfs_find_allocatable_zones(struct btrfs_device *device, u64 hole_start, + u64 hole_end, u64 num_bytes); +int btrfs_reset_device_zone(struct btrfs_device *device, u64 physical, + u64 length, u64 *bytes); +int btrfs_ensure_empty_zones(struct btrfs_device *device, u64 start, u64 size); +int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new); +void btrfs_calc_zone_unusable(struct btrfs_block_group *cache); +void btrfs_redirty_list_add(struct btrfs_transaction *trans, + struct extent_buffer *eb); +void btrfs_free_redirty_list(struct btrfs_transaction *trans); +bool btrfs_use_zone_append(struct btrfs_inode *inode, struct extent_map *em); +void btrfs_record_physical_zoned(struct inode *inode, u64 file_offset, + struct bio *bio); +void btrfs_rewrite_logical_zoned(struct btrfs_ordered_extent *ordered); +bool btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info, + struct extent_buffer *eb, + struct btrfs_block_group **cache_ret); +void btrfs_revert_meta_write_pointer(struct btrfs_block_group *cache, + struct extent_buffer *eb); +int btrfs_zoned_issue_zeroout(struct btrfs_device *device, u64 physical, u64 length); +int btrfs_sync_zone_write_pointer(struct btrfs_device *tgt_dev, u64 logical, + u64 physical_start, u64 physical_pos); +#else /* CONFIG_BLK_DEV_ZONED */ +static inline int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos, + struct blk_zone *zone) +{ + return 0; +} + +static inline int btrfs_get_dev_zone_info_all_devices(struct btrfs_fs_info *fs_info) +{ + return 0; +} + +static inline int btrfs_get_dev_zone_info(struct btrfs_device *device) +{ + return 0; +} + +static inline void btrfs_destroy_dev_zone_info(struct btrfs_device *device) { } + +static inline int btrfs_check_zoned_mode(const struct btrfs_fs_info *fs_info) +{ + if (!btrfs_is_zoned(fs_info)) + return 0; + + btrfs_err(fs_info, "zoned block devices support is not enabled"); + return -EOPNOTSUPP; +} + +static inline int btrfs_check_mountopts_zoned(struct btrfs_fs_info *info) +{ + return 0; +} + +static inline int btrfs_sb_log_location_bdev(struct block_device *bdev, + int mirror, int rw, u64 *bytenr_ret) +{ + *bytenr_ret = btrfs_sb_offset(mirror); + return 0; +} + +static inline int btrfs_sb_log_location(struct btrfs_device *device, int mirror, + int rw, u64 *bytenr_ret) +{ + *bytenr_ret = btrfs_sb_offset(mirror); + return 0; +} + +static inline void btrfs_advance_sb_log(struct btrfs_device *device, int mirror) +{ } + +static inline int btrfs_reset_sb_log_zones(struct block_device *bdev, int mirror) +{ + return 0; +} + +static inline u64 btrfs_find_allocatable_zones(struct btrfs_device *device, + u64 hole_start, u64 hole_end, + u64 num_bytes) +{ + return hole_start; +} + +static inline int btrfs_reset_device_zone(struct btrfs_device *device, + u64 physical, u64 length, u64 *bytes) +{ + *bytes = 0; + return 0; +} + +static inline int btrfs_ensure_empty_zones(struct btrfs_device *device, + u64 start, u64 size) +{ + return 0; +} + +static inline int btrfs_load_block_group_zone_info( + struct btrfs_block_group *cache, bool new) +{ + return 0; +} + +static inline void btrfs_calc_zone_unusable(struct btrfs_block_group *cache) { } + +static inline void btrfs_redirty_list_add(struct btrfs_transaction *trans, + struct extent_buffer *eb) { } +static inline void btrfs_free_redirty_list(struct btrfs_transaction *trans) { } + +static inline bool btrfs_use_zone_append(struct btrfs_inode *inode, + struct extent_map *em) +{ + return false; +} + +static inline void btrfs_record_physical_zoned(struct inode *inode, + u64 file_offset, struct bio *bio) +{ +} + +static inline void btrfs_rewrite_logical_zoned( + struct btrfs_ordered_extent *ordered) { } + +static inline bool btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info, + struct extent_buffer *eb, + struct btrfs_block_group **cache_ret) +{ + return true; +} + +static inline void btrfs_revert_meta_write_pointer( + struct btrfs_block_group *cache, + struct extent_buffer *eb) +{ +} + +static inline int btrfs_zoned_issue_zeroout(struct btrfs_device *device, + u64 physical, u64 length) +{ + return -EOPNOTSUPP; +} + +static inline int btrfs_sync_zone_write_pointer(struct btrfs_device *tgt_dev, + u64 logical, u64 physical_start, + u64 physical_pos) +{ + return -EOPNOTSUPP; +} + +#endif + +static inline bool btrfs_dev_is_sequential(struct btrfs_device *device, u64 pos) +{ + struct btrfs_zoned_device_info *zone_info = device->zone_info; + + if (!zone_info) + return false; + + return test_bit(pos >> zone_info->zone_size_shift, zone_info->seq_zones); +} + +static inline bool btrfs_dev_is_empty_zone(struct btrfs_device *device, u64 pos) +{ + struct btrfs_zoned_device_info *zone_info = device->zone_info; + + if (!zone_info) + return true; + + return test_bit(pos >> zone_info->zone_size_shift, zone_info->empty_zones); +} + +static inline void btrfs_dev_set_empty_zone_bit(struct btrfs_device *device, + u64 pos, bool set) +{ + struct btrfs_zoned_device_info *zone_info = device->zone_info; + unsigned int zno; + + if (!zone_info) + return; + + zno = pos >> zone_info->zone_size_shift; + if (set) + set_bit(zno, zone_info->empty_zones); + else + clear_bit(zno, zone_info->empty_zones); +} + +static inline void btrfs_dev_set_zone_empty(struct btrfs_device *device, u64 pos) +{ + btrfs_dev_set_empty_zone_bit(device, pos, true); +} + +static inline void btrfs_dev_clear_zone_empty(struct btrfs_device *device, u64 pos) +{ + btrfs_dev_set_empty_zone_bit(device, pos, false); +} + +static inline bool btrfs_check_device_zone_type(const struct btrfs_fs_info *fs_info, + struct block_device *bdev) +{ + if (btrfs_is_zoned(fs_info)) { + /* + * We can allow a regular device on a zoned filesystem, because + * we will emulate the zoned capabilities. + */ + if (!bdev_is_zoned(bdev)) + return true; + + return fs_info->zone_size == + (bdev_zone_sectors(bdev) << SECTOR_SHIFT); + } + + /* Do not allow Host Manged zoned device */ + return bdev_zoned_model(bdev) != BLK_ZONED_HM; +} + +static inline bool btrfs_check_super_location(struct btrfs_device *device, u64 pos) +{ + /* + * On a non-zoned device, any address is OK. On a zoned device, + * non-SEQUENTIAL WRITE REQUIRED zones are capable. + */ + return device->zone_info == NULL || !btrfs_dev_is_sequential(device, pos); +} + +static inline bool btrfs_can_zone_reset(struct btrfs_device *device, + u64 physical, u64 length) +{ + u64 zone_size; + + if (!btrfs_dev_is_sequential(device, physical)) + return false; + + zone_size = device->zone_info->zone_size; + if (!IS_ALIGNED(physical, zone_size) || !IS_ALIGNED(length, zone_size)) + return false; + + return true; +} + +static inline void btrfs_zoned_meta_io_lock(struct btrfs_fs_info *fs_info) +{ + if (!btrfs_is_zoned(fs_info)) + return; + mutex_lock(&fs_info->zoned_meta_io_lock); +} + +static inline void btrfs_zoned_meta_io_unlock(struct btrfs_fs_info *fs_info) +{ + if (!btrfs_is_zoned(fs_info)) + return; + mutex_unlock(&fs_info->zoned_meta_io_lock); +} + +static inline void btrfs_clear_treelog_bg(struct btrfs_block_group *bg) +{ + struct btrfs_fs_info *fs_info = bg->fs_info; + + if (!btrfs_is_zoned(fs_info)) + return; + + spin_lock(&fs_info->treelog_bg_lock); + if (fs_info->treelog_bg == bg->start) + fs_info->treelog_bg = 0; + spin_unlock(&fs_info->treelog_bg_lock); +} + +#endif |