From: Chris Mason Date: Sun, 6 Nov 2011 08:05:08 +0000 (-0500) Subject: Merge branch 'for-chris' of git://github.com/sensille/linux into integration X-Git-Tag: v3.2-rc1~21^2~9 X-Git-Url: https://git.openpandora.org/cgi-bin/gitweb.cgi?p=pandora-kernel.git;a=commitdiff_plain;h=531f4b1ae5e0fc8c9b3f03838218e5ea178f80d3;hp=-c Merge branch 'for-chris' of git://github.com/sensille/linux into integration Conflicts: fs/btrfs/ctree.h Signed-off-by: Chris Mason --- 531f4b1ae5e0fc8c9b3f03838218e5ea178f80d3 diff --combined fs/btrfs/ctree.h index 6bb34fc1ff22,370af767440d..b9ba59ff9292 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@@ -30,7 -30,6 +30,7 @@@ #include #include #include +#include #include "extent_io.h" #include "extent_map.h" #include "async-thread.h" @@@ -360,47 -359,6 +360,47 @@@ struct btrfs_header #define BTRFS_SYSTEM_CHUNK_ARRAY_SIZE 2048 #define BTRFS_LABEL_SIZE 256 +/* + * just in case we somehow lose the roots and are not able to mount, + * we store an array of the roots from previous transactions + * in the super. + */ +#define BTRFS_NUM_BACKUP_ROOTS 4 +struct btrfs_root_backup { + __le64 tree_root; + __le64 tree_root_gen; + + __le64 chunk_root; + __le64 chunk_root_gen; + + __le64 extent_root; + __le64 extent_root_gen; + + __le64 fs_root; + __le64 fs_root_gen; + + __le64 dev_root; + __le64 dev_root_gen; + + __le64 csum_root; + __le64 csum_root_gen; + + __le64 total_bytes; + __le64 bytes_used; + __le64 num_devices; + /* future */ + __le64 unsed_64[4]; + + u8 tree_root_level; + u8 chunk_root_level; + u8 extent_root_level; + u8 fs_root_level; + u8 dev_root_level; + u8 csum_root_level; + /* future and to align */ + u8 unused_8[10]; +} __attribute__ ((__packed__)); + /* * the super block basically lists the main trees of the FS * it currently lacks any block count etc etc @@@ -447,7 -405,6 +447,7 @@@ struct btrfs_super_block /* future expansion */ __le64 reserved[31]; u8 sys_chunk_array[BTRFS_SYSTEM_CHUNK_ARRAY_SIZE]; + struct btrfs_root_backup super_roots[BTRFS_NUM_BACKUP_ROOTS]; } __attribute__ ((__packed__)); /* @@@ -815,8 -772,14 +815,8 @@@ struct btrfs_space_info struct btrfs_block_rsv { u64 size; u64 reserved; - u64 freed[2]; struct btrfs_space_info *space_info; - struct list_head list; spinlock_t lock; - atomic_t usage; - unsigned int priority:8; - unsigned int durable:1; - unsigned int refill_used:1; unsigned int full:1; }; @@@ -877,10 -840,10 +877,10 @@@ struct btrfs_block_group_cache spinlock_t lock; u64 pinned; u64 reserved; - u64 reserved_pinned; u64 bytes_super; u64 flags; u64 sectorsize; + u64 cache_generation; unsigned int ro:1; unsigned int dirty:1; unsigned int iref:1; @@@ -936,10 -899,6 +936,10 @@@ struct btrfs_fs_info spinlock_t block_group_cache_lock; struct rb_root block_group_cache_tree; + /* keep track of unallocated space */ + spinlock_t free_chunk_lock; + u64 free_chunk_space; + struct extent_io_tree freed_extents[2]; struct extent_io_tree *pinned_extents; @@@ -957,11 -916,14 +957,11 @@@ struct btrfs_block_rsv trans_block_rsv; /* block reservation for chunk tree */ struct btrfs_block_rsv chunk_block_rsv; + /* block reservation for delayed operations */ + struct btrfs_block_rsv delayed_block_rsv; struct btrfs_block_rsv empty_block_rsv; - /* list of block reservations that cross multiple transactions */ - struct list_head durable_block_rsv_list; - - struct mutex durable_block_rsv_mutex; - u64 generation; u64 last_trans_committed; @@@ -980,8 -942,8 +980,8 @@@ wait_queue_head_t transaction_blocked_wait; wait_queue_head_t async_submit_wait; - struct btrfs_super_block super_copy; - struct btrfs_super_block super_for_commit; + struct btrfs_super_block *super_copy; + struct btrfs_super_block *super_for_commit; struct block_device *__bdev; struct super_block *sb; struct inode *btree_inode; @@@ -1074,6 -1036,7 +1074,7 @@@ struct btrfs_workers endio_freespace_worker; struct btrfs_workers submit_workers; struct btrfs_workers caching_workers; + struct btrfs_workers readahead_workers; /* * fixup workers take dirty pages that didn't properly go through @@@ -1158,8 -1121,9 +1159,12 @@@ struct btrfs_delayed_root *delayed_root; + /* readahead tree */ + spinlock_t reada_lock; + struct radix_tree_root reada_tree; ++ + /* next backup root to be overwritten */ + int backup_root_index; }; /* @@@ -1404,7 -1368,6 +1409,7 @@@ struct btrfs_ioctl_defrag_range_args #define BTRFS_MOUNT_ENOSPC_DEBUG (1 << 15) #define BTRFS_MOUNT_AUTO_DEFRAG (1 << 16) #define BTRFS_MOUNT_INODE_MAP_CACHE (1 << 17) +#define BTRFS_MOUNT_RECOVERY (1 << 18) #define btrfs_clear_opt(o, opt) ((o) &= ~BTRFS_MOUNT_##opt) #define btrfs_set_opt(o, opt) ((o) |= BTRFS_MOUNT_##opt) @@@ -2020,55 -1983,6 +2025,55 @@@ static inline bool btrfs_root_readonly( return root->root_item.flags & BTRFS_ROOT_SUBVOL_RDONLY; } +/* struct btrfs_root_backup */ +BTRFS_SETGET_STACK_FUNCS(backup_tree_root, struct btrfs_root_backup, + tree_root, 64); +BTRFS_SETGET_STACK_FUNCS(backup_tree_root_gen, struct btrfs_root_backup, + tree_root_gen, 64); +BTRFS_SETGET_STACK_FUNCS(backup_tree_root_level, struct btrfs_root_backup, + tree_root_level, 8); + +BTRFS_SETGET_STACK_FUNCS(backup_chunk_root, struct btrfs_root_backup, + chunk_root, 64); +BTRFS_SETGET_STACK_FUNCS(backup_chunk_root_gen, struct btrfs_root_backup, + chunk_root_gen, 64); +BTRFS_SETGET_STACK_FUNCS(backup_chunk_root_level, struct btrfs_root_backup, + chunk_root_level, 8); + +BTRFS_SETGET_STACK_FUNCS(backup_extent_root, struct btrfs_root_backup, + extent_root, 64); +BTRFS_SETGET_STACK_FUNCS(backup_extent_root_gen, struct btrfs_root_backup, + extent_root_gen, 64); +BTRFS_SETGET_STACK_FUNCS(backup_extent_root_level, struct btrfs_root_backup, + extent_root_level, 8); + +BTRFS_SETGET_STACK_FUNCS(backup_fs_root, struct btrfs_root_backup, + fs_root, 64); +BTRFS_SETGET_STACK_FUNCS(backup_fs_root_gen, struct btrfs_root_backup, + fs_root_gen, 64); +BTRFS_SETGET_STACK_FUNCS(backup_fs_root_level, struct btrfs_root_backup, + fs_root_level, 8); + +BTRFS_SETGET_STACK_FUNCS(backup_dev_root, struct btrfs_root_backup, + dev_root, 64); +BTRFS_SETGET_STACK_FUNCS(backup_dev_root_gen, struct btrfs_root_backup, + dev_root_gen, 64); +BTRFS_SETGET_STACK_FUNCS(backup_dev_root_level, struct btrfs_root_backup, + dev_root_level, 8); + +BTRFS_SETGET_STACK_FUNCS(backup_csum_root, struct btrfs_root_backup, + csum_root, 64); +BTRFS_SETGET_STACK_FUNCS(backup_csum_root_gen, struct btrfs_root_backup, + csum_root_gen, 64); +BTRFS_SETGET_STACK_FUNCS(backup_csum_root_level, struct btrfs_root_backup, + csum_root_level, 8); +BTRFS_SETGET_STACK_FUNCS(backup_total_bytes, struct btrfs_root_backup, + total_bytes, 64); +BTRFS_SETGET_STACK_FUNCS(backup_bytes_used, struct btrfs_root_backup, + bytes_used, 64); +BTRFS_SETGET_STACK_FUNCS(backup_num_devices, struct btrfs_root_backup, + num_devices, 64); + /* struct btrfs_super_block */ BTRFS_SETGET_STACK_FUNCS(super_bytenr, struct btrfs_super_block, bytenr, 64); @@@ -2220,11 -2134,6 +2225,11 @@@ static inline bool btrfs_mixed_space_in (space_info->flags & BTRFS_BLOCK_GROUP_DATA)); } +static inline gfp_t btrfs_alloc_write_mask(struct address_space *mapping) +{ + return mapping_gfp_mask(mapping) & ~__GFP_FS; +} + /* extent-tree.c */ static inline u64 btrfs_calc_trans_metadata_size(struct btrfs_root *root, unsigned num_items) @@@ -2233,17 -2142,6 +2238,17 @@@ 3 * num_items; } +/* + * Doing a truncate won't result in new nodes or leaves, just what we need for + * COW. + */ +static inline u64 btrfs_calc_trunc_metadata_size(struct btrfs_root *root, + unsigned num_items) +{ + return (root->leafsize + root->nodesize * (BTRFS_MAX_LEVEL - 1)) * + num_items; +} + void btrfs_put_block_group(struct btrfs_block_group_cache *cache); int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, struct btrfs_root *root, unsigned long count); @@@ -2253,9 -2151,6 +2258,9 @@@ int btrfs_lookup_extent_info(struct btr u64 num_bytes, u64 *refs, u64 *flags); int btrfs_pin_extent(struct btrfs_root *root, u64 bytenr, u64 num, int reserved); +int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans, + struct btrfs_root *root, + u64 bytenr, u64 num_bytes); int btrfs_cross_ref_exist(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 objectid, u64 offset, u64 bytenr); @@@ -2306,8 -2201,8 +2311,8 @@@ int btrfs_free_extent(struct btrfs_tran u64 root_objectid, u64 owner, u64 offset); int btrfs_free_reserved_extent(struct btrfs_root *root, u64 start, u64 len); -int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache, - u64 num_bytes, int reserve, int sinfo); +int btrfs_free_and_pin_reserved_extent(struct btrfs_root *root, + u64 start, u64 len); int btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans, struct btrfs_root *root); int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans, @@@ -2350,23 -2245,25 +2355,23 @@@ void btrfs_init_block_rsv(struct btrfs_ struct btrfs_block_rsv *btrfs_alloc_block_rsv(struct btrfs_root *root); void btrfs_free_block_rsv(struct btrfs_root *root, struct btrfs_block_rsv *rsv); -void btrfs_add_durable_block_rsv(struct btrfs_fs_info *fs_info, - struct btrfs_block_rsv *rsv); -int btrfs_block_rsv_add(struct btrfs_trans_handle *trans, - struct btrfs_root *root, +int btrfs_block_rsv_add(struct btrfs_root *root, struct btrfs_block_rsv *block_rsv, u64 num_bytes); -int btrfs_block_rsv_check(struct btrfs_trans_handle *trans, - struct btrfs_root *root, +int btrfs_block_rsv_add_noflush(struct btrfs_root *root, + struct btrfs_block_rsv *block_rsv, + u64 num_bytes); +int btrfs_block_rsv_check(struct btrfs_root *root, + struct btrfs_block_rsv *block_rsv, int min_factor); +int btrfs_block_rsv_refill(struct btrfs_root *root, struct btrfs_block_rsv *block_rsv, - u64 min_reserved, int min_factor); + u64 min_reserved); int btrfs_block_rsv_migrate(struct btrfs_block_rsv *src_rsv, struct btrfs_block_rsv *dst_rsv, u64 num_bytes); void btrfs_block_rsv_release(struct btrfs_root *root, struct btrfs_block_rsv *block_rsv, u64 num_bytes); -int btrfs_truncate_reserve_metadata(struct btrfs_trans_handle *trans, - struct btrfs_root *root, - struct btrfs_block_rsv *rsv); int btrfs_set_block_group_ro(struct btrfs_root *root, struct btrfs_block_group_cache *cache); int btrfs_set_block_group_rw(struct btrfs_root *root, @@@ -2487,18 -2384,6 +2492,18 @@@ static inline int btrfs_fs_closing(stru smp_mb(); return fs_info->closing; } +static inline void free_fs_info(struct btrfs_fs_info *fs_info) +{ + kfree(fs_info->delayed_root); + kfree(fs_info->extent_root); + kfree(fs_info->tree_root); + kfree(fs_info->chunk_root); + kfree(fs_info->dev_root); + kfree(fs_info->csum_root); + kfree(fs_info->super_copy); + kfree(fs_info->super_for_commit); + kfree(fs_info); +} /* root-item.c */ int btrfs_find_root_ref(struct btrfs_root *tree_root, @@@ -2699,6 -2584,11 +2704,6 @@@ int btrfs_update_inode(struct btrfs_tra int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode); int btrfs_orphan_del(struct btrfs_trans_handle *trans, struct inode *inode); int btrfs_orphan_cleanup(struct btrfs_root *root); -void btrfs_orphan_pre_snapshot(struct btrfs_trans_handle *trans, - struct btrfs_pending_snapshot *pending, - u64 *bytes_to_reserve); -void btrfs_orphan_post_snapshot(struct btrfs_trans_handle *trans, - struct btrfs_pending_snapshot *pending); void btrfs_orphan_commit_root(struct btrfs_trans_handle *trans, struct btrfs_root *root); int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size); @@@ -2812,4 -2702,20 +2817,20 @@@ int btrfs_scrub_cancel_devid(struct btr int btrfs_scrub_progress(struct btrfs_root *root, u64 devid, struct btrfs_scrub_progress *progress); + /* reada.c */ + struct reada_control { + struct btrfs_root *root; /* tree to prefetch */ + struct btrfs_key key_start; + struct btrfs_key key_end; /* exclusive */ + atomic_t elems; + struct kref refcnt; + wait_queue_head_t wait; + }; + struct reada_control *btrfs_reada_add(struct btrfs_root *root, + struct btrfs_key *start, struct btrfs_key *end); + int btrfs_reada_wait(void *handle); + void btrfs_reada_detach(void *handle); + int btree_readahead_hook(struct btrfs_root *root, struct extent_buffer *eb, + u64 start, int err); + #endif diff --combined fs/btrfs/disk-io.c index 23b6776477b7,2151828aa142..cedfbfb278eb --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@@ -256,7 -256,8 +256,7 @@@ void btrfs_csum_final(u32 crc, char *re static int csum_tree_block(struct btrfs_root *root, struct extent_buffer *buf, int verify) { - u16 csum_size = - btrfs_super_csum_size(&root->fs_info->super_copy); + u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy); char *result = NULL; unsigned long len; unsigned long cur_len; @@@ -366,7 -367,8 +366,8 @@@ static int btree_read_extent_buffer_pag clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags); io_tree = &BTRFS_I(root->fs_info->btree_inode)->io_tree; while (1) { - ret = read_extent_buffer_pages(io_tree, eb, start, 1, + ret = read_extent_buffer_pages(io_tree, eb, start, + WAIT_COMPLETE, btree_get_extent, mirror_num); if (!ret && !verify_parent_transid(io_tree, eb, parent_transid)) @@@ -607,11 -609,47 +608,47 @@@ static int btree_readpage_end_io_hook(s end = min_t(u64, eb->len, PAGE_CACHE_SIZE); end = eb->start + end - 1; err: + if (test_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags)) { + clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags); + btree_readahead_hook(root, eb, eb->start, ret); + } + free_extent_buffer(eb); out: return ret; } + static int btree_io_failed_hook(struct bio *failed_bio, + struct page *page, u64 start, u64 end, + struct extent_state *state) + { + struct extent_io_tree *tree; + unsigned long len; + struct extent_buffer *eb; + struct btrfs_root *root = BTRFS_I(page->mapping->host)->root; + + tree = &BTRFS_I(page->mapping->host)->io_tree; + if (page->private == EXTENT_PAGE_PRIVATE) + goto out; + if (!page->private) + goto out; + + len = page->private >> 2; + WARN_ON(len == 0); + + eb = alloc_extent_buffer(tree, start, len, page); + if (eb == NULL) + goto out; + + if (test_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags)) { + clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags); + btree_readahead_hook(root, eb, eb->start, -EIO); + } + + out: + return -EIO; /* we fixed nothing */ + } + static void end_workqueue_bio(struct bio *bio, int err) { struct end_io_wq *end_io_wq = bio->bi_private; @@@ -973,11 -1011,43 +1010,43 @@@ int readahead_tree_block(struct btrfs_r if (!buf) return 0; read_extent_buffer_pages(&BTRFS_I(btree_inode)->io_tree, - buf, 0, 0, btree_get_extent, 0); + buf, 0, WAIT_NONE, btree_get_extent, 0); free_extent_buffer(buf); return ret; } + int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr, u32 blocksize, + int mirror_num, struct extent_buffer **eb) + { + struct extent_buffer *buf = NULL; + struct inode *btree_inode = root->fs_info->btree_inode; + struct extent_io_tree *io_tree = &BTRFS_I(btree_inode)->io_tree; + int ret; + + buf = btrfs_find_create_tree_block(root, bytenr, blocksize); + if (!buf) + return 0; + + set_bit(EXTENT_BUFFER_READAHEAD, &buf->bflags); + + ret = read_extent_buffer_pages(io_tree, buf, 0, WAIT_PAGE_LOCK, + btree_get_extent, mirror_num); + if (ret) { + free_extent_buffer(buf); + return ret; + } + + if (test_bit(EXTENT_BUFFER_CORRUPT, &buf->bflags)) { + free_extent_buffer(buf); + return -EIO; + } else if (extent_buffer_uptodate(io_tree, buf, NULL)) { + *eb = buf; + } else { + free_extent_buffer(buf); + } + return 0; + } + struct extent_buffer *btrfs_find_tree_block(struct btrfs_root *root, u64 bytenr, u32 blocksize) { @@@ -1134,12 -1204,10 +1203,12 @@@ static int find_and_setup_root(struct b generation = btrfs_root_generation(&root->root_item); blocksize = btrfs_level_size(root, btrfs_root_level(&root->root_item)); + root->commit_root = NULL; root->node = read_tree_block(root, btrfs_root_bytenr(&root->root_item), blocksize, generation); if (!root->node || !btrfs_buffer_uptodate(root->node, generation)) { free_extent_buffer(root->node); + root->node = NULL; return -EIO; } root->commit_root = btrfs_root_node(root); @@@ -1578,228 -1646,6 +1647,228 @@@ sleep return 0; } +/* + * this will find the highest generation in the array of + * root backups. The index of the highest array is returned, + * or -1 if we can't find anything. + * + * We check to make sure the array is valid by comparing the + * generation of the latest root in the array with the generation + * in the super block. If they don't match we pitch it. + */ +static int find_newest_super_backup(struct btrfs_fs_info *info, u64 newest_gen) +{ + u64 cur; + int newest_index = -1; + struct btrfs_root_backup *root_backup; + int i; + + for (i = 0; i < BTRFS_NUM_BACKUP_ROOTS; i++) { + root_backup = info->super_copy->super_roots + i; + cur = btrfs_backup_tree_root_gen(root_backup); + if (cur == newest_gen) + newest_index = i; + } + + /* check to see if we actually wrapped around */ + if (newest_index == BTRFS_NUM_BACKUP_ROOTS - 1) { + root_backup = info->super_copy->super_roots; + cur = btrfs_backup_tree_root_gen(root_backup); + if (cur == newest_gen) + newest_index = 0; + } + return newest_index; +} + + +/* + * find the oldest backup so we know where to store new entries + * in the backup array. This will set the backup_root_index + * field in the fs_info struct + */ +static void find_oldest_super_backup(struct btrfs_fs_info *info, + u64 newest_gen) +{ + int newest_index = -1; + + newest_index = find_newest_super_backup(info, newest_gen); + /* if there was garbage in there, just move along */ + if (newest_index == -1) { + info->backup_root_index = 0; + } else { + info->backup_root_index = (newest_index + 1) % BTRFS_NUM_BACKUP_ROOTS; + } +} + +/* + * copy all the root pointers into the super backup array. + * this will bump the backup pointer by one when it is + * done + */ +static void backup_super_roots(struct btrfs_fs_info *info) +{ + int next_backup; + struct btrfs_root_backup *root_backup; + int last_backup; + + next_backup = info->backup_root_index; + last_backup = (next_backup + BTRFS_NUM_BACKUP_ROOTS - 1) % + BTRFS_NUM_BACKUP_ROOTS; + + /* + * just overwrite the last backup if we're at the same generation + * this happens only at umount + */ + root_backup = info->super_for_commit->super_roots + last_backup; + if (btrfs_backup_tree_root_gen(root_backup) == + btrfs_header_generation(info->tree_root->node)) + next_backup = last_backup; + + root_backup = info->super_for_commit->super_roots + next_backup; + + /* + * make sure all of our padding and empty slots get zero filled + * regardless of which ones we use today + */ + memset(root_backup, 0, sizeof(*root_backup)); + + info->backup_root_index = (next_backup + 1) % BTRFS_NUM_BACKUP_ROOTS; + + btrfs_set_backup_tree_root(root_backup, info->tree_root->node->start); + btrfs_set_backup_tree_root_gen(root_backup, + btrfs_header_generation(info->tree_root->node)); + + btrfs_set_backup_tree_root_level(root_backup, + btrfs_header_level(info->tree_root->node)); + + btrfs_set_backup_chunk_root(root_backup, info->chunk_root->node->start); + btrfs_set_backup_chunk_root_gen(root_backup, + btrfs_header_generation(info->chunk_root->node)); + btrfs_set_backup_chunk_root_level(root_backup, + btrfs_header_level(info->chunk_root->node)); + + btrfs_set_backup_extent_root(root_backup, info->extent_root->node->start); + btrfs_set_backup_extent_root_gen(root_backup, + btrfs_header_generation(info->extent_root->node)); + btrfs_set_backup_extent_root_level(root_backup, + btrfs_header_level(info->extent_root->node)); + + btrfs_set_backup_fs_root(root_backup, info->fs_root->node->start); + btrfs_set_backup_fs_root_gen(root_backup, + btrfs_header_generation(info->fs_root->node)); + btrfs_set_backup_fs_root_level(root_backup, + btrfs_header_level(info->fs_root->node)); + + btrfs_set_backup_dev_root(root_backup, info->dev_root->node->start); + btrfs_set_backup_dev_root_gen(root_backup, + btrfs_header_generation(info->dev_root->node)); + btrfs_set_backup_dev_root_level(root_backup, + btrfs_header_level(info->dev_root->node)); + + btrfs_set_backup_csum_root(root_backup, info->csum_root->node->start); + btrfs_set_backup_csum_root_gen(root_backup, + btrfs_header_generation(info->csum_root->node)); + btrfs_set_backup_csum_root_level(root_backup, + btrfs_header_level(info->csum_root->node)); + + btrfs_set_backup_total_bytes(root_backup, + btrfs_super_total_bytes(info->super_copy)); + btrfs_set_backup_bytes_used(root_backup, + btrfs_super_bytes_used(info->super_copy)); + btrfs_set_backup_num_devices(root_backup, + btrfs_super_num_devices(info->super_copy)); + + /* + * if we don't copy this out to the super_copy, it won't get remembered + * for the next commit + */ + memcpy(&info->super_copy->super_roots, + &info->super_for_commit->super_roots, + sizeof(*root_backup) * BTRFS_NUM_BACKUP_ROOTS); +} + +/* + * this copies info out of the root backup array and back into + * the in-memory super block. It is meant to help iterate through + * the array, so you send it the number of backups you've already + * tried and the last backup index you used. + * + * this returns -1 when it has tried all the backups + */ +static noinline int next_root_backup(struct btrfs_fs_info *info, + struct btrfs_super_block *super, + int *num_backups_tried, int *backup_index) +{ + struct btrfs_root_backup *root_backup; + int newest = *backup_index; + + if (*num_backups_tried == 0) { + u64 gen = btrfs_super_generation(super); + + newest = find_newest_super_backup(info, gen); + if (newest == -1) + return -1; + + *backup_index = newest; + *num_backups_tried = 1; + } else if (*num_backups_tried == BTRFS_NUM_BACKUP_ROOTS) { + /* we've tried all the backups, all done */ + return -1; + } else { + /* jump to the next oldest backup */ + newest = (*backup_index + BTRFS_NUM_BACKUP_ROOTS - 1) % + BTRFS_NUM_BACKUP_ROOTS; + *backup_index = newest; + *num_backups_tried += 1; + } + root_backup = super->super_roots + newest; + + btrfs_set_super_generation(super, + btrfs_backup_tree_root_gen(root_backup)); + btrfs_set_super_root(super, btrfs_backup_tree_root(root_backup)); + btrfs_set_super_root_level(super, + btrfs_backup_tree_root_level(root_backup)); + btrfs_set_super_bytes_used(super, btrfs_backup_bytes_used(root_backup)); + + /* + * fixme: the total bytes and num_devices need to match or we should + * need a fsck + */ + btrfs_set_super_total_bytes(super, btrfs_backup_total_bytes(root_backup)); + btrfs_set_super_num_devices(super, btrfs_backup_num_devices(root_backup)); + return 0; +} + +/* helper to cleanup tree roots */ +static void free_root_pointers(struct btrfs_fs_info *info, int chunk_root) +{ + free_extent_buffer(info->tree_root->node); + free_extent_buffer(info->tree_root->commit_root); + free_extent_buffer(info->dev_root->node); + free_extent_buffer(info->dev_root->commit_root); + free_extent_buffer(info->extent_root->node); + free_extent_buffer(info->extent_root->commit_root); + free_extent_buffer(info->csum_root->node); + free_extent_buffer(info->csum_root->commit_root); + + info->tree_root->node = NULL; + info->tree_root->commit_root = NULL; + info->dev_root->node = NULL; + info->dev_root->commit_root = NULL; + info->extent_root->node = NULL; + info->extent_root->commit_root = NULL; + info->csum_root->node = NULL; + info->csum_root->commit_root = NULL; + + if (chunk_root) { + free_extent_buffer(info->chunk_root->node); + free_extent_buffer(info->chunk_root->commit_root); + info->chunk_root->node = NULL; + info->chunk_root->commit_root = NULL; + } +} + + struct btrfs_root *open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_devices, char *options) @@@ -1827,8 -1673,6 +1896,8 @@@ int ret; int err = -EINVAL; + int num_backups_tried = 0; + int backup_index = 0; struct btrfs_super_block *disk_super; @@@ -1873,7 -1717,6 +1942,7 @@@ spin_lock_init(&fs_info->fs_roots_radix_lock); spin_lock_init(&fs_info->delayed_iput_lock); spin_lock_init(&fs_info->defrag_inodes_lock); + spin_lock_init(&fs_info->free_chunk_lock); mutex_init(&fs_info->reloc_mutex); init_completion(&fs_info->kobj_unregister); @@@ -1891,7 -1734,8 +1960,7 @@@ btrfs_init_block_rsv(&fs_info->trans_block_rsv); btrfs_init_block_rsv(&fs_info->chunk_block_rsv); btrfs_init_block_rsv(&fs_info->empty_block_rsv); - INIT_LIST_HEAD(&fs_info->durable_block_rsv_list); - mutex_init(&fs_info->durable_block_rsv_mutex); + btrfs_init_block_rsv(&fs_info->delayed_block_rsv); atomic_set(&fs_info->nr_async_submits, 0); atomic_set(&fs_info->async_delalloc_pages, 0); atomic_set(&fs_info->async_submit_draining, 0); @@@ -1902,8 -1746,11 +1971,12 @@@ fs_info->metadata_ratio = 0; fs_info->defrag_inodes = RB_ROOT; fs_info->trans_no_join = 0; + fs_info->free_chunk_space = 0; + /* readahead state */ + INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_WAIT); + spin_lock_init(&fs_info->reada_lock); + fs_info->thread_pool_size = min_t(unsigned long, num_online_cpus() + 2, 8); @@@ -1992,14 -1839,14 +2065,14 @@@ goto fail_alloc; } - memcpy(&fs_info->super_copy, bh->b_data, sizeof(fs_info->super_copy)); - memcpy(&fs_info->super_for_commit, &fs_info->super_copy, - sizeof(fs_info->super_for_commit)); + memcpy(fs_info->super_copy, bh->b_data, sizeof(*fs_info->super_copy)); + memcpy(fs_info->super_for_commit, fs_info->super_copy, + sizeof(*fs_info->super_for_commit)); brelse(bh); - memcpy(fs_info->fsid, fs_info->super_copy.fsid, BTRFS_FSID_SIZE); + memcpy(fs_info->fsid, fs_info->super_copy->fsid, BTRFS_FSID_SIZE); - disk_super = &fs_info->super_copy; + disk_super = fs_info->super_copy; if (!btrfs_super_root(disk_super)) goto fail_alloc; @@@ -2008,13 -1855,6 +2081,13 @@@ btrfs_check_super_valid(fs_info, sb->s_flags & MS_RDONLY); + /* + * run through our array of backup supers and setup + * our ring pointer to the oldest one + */ + generation = btrfs_super_generation(disk_super); + find_oldest_super_backup(fs_info, generation); + /* * In the long term, we'll store the compression type in the super * block, and it'll be used for per file compression control. @@@ -2103,6 -1943,9 +2176,9 @@@ btrfs_init_workers(&fs_info->delayed_workers, "delayed-meta", fs_info->thread_pool_size, &fs_info->generic_worker); + btrfs_init_workers(&fs_info->readahead_workers, "readahead", + fs_info->thread_pool_size, + &fs_info->generic_worker); /* * endios are largely parallel and should have a very @@@ -2113,6 -1956,7 +2189,7 @@@ fs_info->endio_write_workers.idle_thresh = 2; fs_info->endio_meta_write_workers.idle_thresh = 2; + fs_info->readahead_workers.idle_thresh = 2; btrfs_start_workers(&fs_info->workers, 1); btrfs_start_workers(&fs_info->generic_worker, 1); @@@ -2126,6 -1970,7 +2203,7 @@@ btrfs_start_workers(&fs_info->endio_freespace_worker, 1); btrfs_start_workers(&fs_info->delayed_workers, 1); btrfs_start_workers(&fs_info->caching_workers, 1); + btrfs_start_workers(&fs_info->readahead_workers, 1); fs_info->bdi.ra_pages *= btrfs_super_num_devices(disk_super); fs_info->bdi.ra_pages = max(fs_info->bdi.ra_pages, @@@ -2172,7 -2017,7 +2250,7 @@@ if (!test_bit(EXTENT_BUFFER_UPTODATE, &chunk_root->node->bflags)) { printk(KERN_WARNING "btrfs: failed to read chunk root on %s\n", sb->s_id); - goto fail_chunk_root; + goto fail_tree_roots; } btrfs_set_root_node(&chunk_root->root_item, chunk_root->node); chunk_root->commit_root = btrfs_root_node(chunk_root); @@@ -2187,12 -2032,11 +2265,12 @@@ if (ret) { printk(KERN_WARNING "btrfs: failed to read chunk tree on %s\n", sb->s_id); - goto fail_chunk_root; + goto fail_tree_roots; } btrfs_close_extra_devices(fs_devices); +retry_root_backup: blocksize = btrfs_level_size(tree_root, btrfs_super_root_level(disk_super)); generation = btrfs_super_generation(disk_super); @@@ -2200,33 -2044,32 +2278,33 @@@ tree_root->node = read_tree_block(tree_root, btrfs_super_root(disk_super), blocksize, generation); - if (!tree_root->node) - goto fail_chunk_root; - if (!test_bit(EXTENT_BUFFER_UPTODATE, &tree_root->node->bflags)) { + if (!tree_root->node || + !test_bit(EXTENT_BUFFER_UPTODATE, &tree_root->node->bflags)) { printk(KERN_WARNING "btrfs: failed to read tree root on %s\n", sb->s_id); - goto fail_tree_root; + + goto recovery_tree_root; } + btrfs_set_root_node(&tree_root->root_item, tree_root->node); tree_root->commit_root = btrfs_root_node(tree_root); ret = find_and_setup_root(tree_root, fs_info, BTRFS_EXTENT_TREE_OBJECTID, extent_root); if (ret) - goto fail_tree_root; + goto recovery_tree_root; extent_root->track_dirty = 1; ret = find_and_setup_root(tree_root, fs_info, BTRFS_DEV_TREE_OBJECTID, dev_root); if (ret) - goto fail_extent_root; + goto recovery_tree_root; dev_root->track_dirty = 1; ret = find_and_setup_root(tree_root, fs_info, BTRFS_CSUM_TREE_OBJECTID, csum_root); if (ret) - goto fail_dev_root; + goto recovery_tree_root; csum_root->track_dirty = 1; @@@ -2359,10 -2202,20 +2437,10 @@@ fail_cleaner fail_block_groups: btrfs_free_block_groups(fs_info); - free_extent_buffer(csum_root->node); - free_extent_buffer(csum_root->commit_root); -fail_dev_root: - free_extent_buffer(dev_root->node); - free_extent_buffer(dev_root->commit_root); -fail_extent_root: - free_extent_buffer(extent_root->node); - free_extent_buffer(extent_root->commit_root); -fail_tree_root: - free_extent_buffer(tree_root->node); - free_extent_buffer(tree_root->commit_root); -fail_chunk_root: - free_extent_buffer(chunk_root->node); - free_extent_buffer(chunk_root->commit_root); + +fail_tree_roots: + free_root_pointers(fs_info, 1); + fail_sb_buffer: btrfs_stop_workers(&fs_info->generic_worker); btrfs_stop_workers(&fs_info->fixup_workers); @@@ -2377,6 -2230,7 +2455,6 @@@ btrfs_stop_workers(&fs_info->delayed_workers); btrfs_stop_workers(&fs_info->caching_workers); fail_alloc: - kfree(fs_info->delayed_root); fail_iput: invalidate_inode_pages2(fs_info->btree_inode->i_mapping); iput(fs_info->btree_inode); @@@ -2388,27 -2242,13 +2466,27 @@@ fail_bdi fail_srcu: cleanup_srcu_struct(&fs_info->subvol_srcu); fail: - kfree(extent_root); - kfree(tree_root); - kfree(fs_info); - kfree(chunk_root); - kfree(dev_root); - kfree(csum_root); + free_fs_info(fs_info); return ERR_PTR(err); + +recovery_tree_root: + + if (!btrfs_test_opt(tree_root, RECOVERY)) + goto fail_tree_roots; + + free_root_pointers(fs_info, 0); + + /* don't use the log in recovery mode, it won't be valid */ + btrfs_set_super_log_root(disk_super, 0); + + /* we can't trust the free space cache either */ + btrfs_set_opt(fs_info->mount_opt, CLEAR_CACHE); + + ret = next_root_backup(fs_info, fs_info->super_copy, + &num_backups_tried, &backup_index); + if (ret == -1) + goto fail_block_groups; + goto retry_root_backup; } static void btrfs_end_buffer_write_sync(struct buffer_head *bh, int uptodate) @@@ -2576,11 -2416,10 +2654,11 @@@ int write_all_supers(struct btrfs_root int total_errors = 0; u64 flags; - max_errors = btrfs_super_num_devices(&root->fs_info->super_copy) - 1; + max_errors = btrfs_super_num_devices(root->fs_info->super_copy) - 1; do_barriers = !btrfs_test_opt(root, NOBARRIER); + backup_super_roots(root->fs_info); - sb = &root->fs_info->super_for_commit; + sb = root->fs_info->super_for_commit; dev_item = &sb->dev_item; mutex_lock(&root->fs_info->fs_devices->device_list_mutex); @@@ -2784,6 -2623,8 +2862,6 @@@ int close_ctree(struct btrfs_root *root /* clear out the rbtree of defraggable inodes */ btrfs_run_defrag_inodes(root->fs_info); - btrfs_put_block_group_cache(fs_info); - /* * Here come 2 situations when btrfs is broken to flip readonly: * @@@ -2809,8 -2650,6 +2887,8 @@@ printk(KERN_ERR "btrfs: commit super ret %d\n", ret); } + btrfs_put_block_group_cache(fs_info); + kthread_stop(root->fs_info->transaction_kthread); kthread_stop(root->fs_info->cleaner_kthread); @@@ -2842,6 -2681,7 +2920,6 @@@ del_fs_roots(fs_info); iput(fs_info->btree_inode); - kfree(fs_info->delayed_root); btrfs_stop_workers(&fs_info->generic_worker); btrfs_stop_workers(&fs_info->fixup_workers); @@@ -2855,6 -2695,7 +2933,7 @@@ btrfs_stop_workers(&fs_info->submit_workers); btrfs_stop_workers(&fs_info->delayed_workers); btrfs_stop_workers(&fs_info->caching_workers); + btrfs_stop_workers(&fs_info->readahead_workers); btrfs_close_devices(fs_info->fs_devices); btrfs_mapping_tree_free(&fs_info->mapping_tree); @@@ -2862,7 -2703,12 +2941,7 @@@ bdi_destroy(&fs_info->bdi); cleanup_srcu_struct(&fs_info->subvol_srcu); - kfree(fs_info->extent_root); - kfree(fs_info->tree_root); - kfree(fs_info->chunk_root); - kfree(fs_info->dev_root); - kfree(fs_info->csum_root); - kfree(fs_info); + free_fs_info(fs_info); return 0; } @@@ -2968,8 -2814,7 +3047,8 @@@ int btrfs_read_buffer(struct extent_buf return ret; } -int btree_lock_page_hook(struct page *page) +static int btree_lock_page_hook(struct page *page, void *data, + void (*flush_fn)(void *)) { struct inode *inode = page->mapping->host; struct btrfs_root *root = BTRFS_I(inode)->root; @@@ -2986,10 -2831,7 +3065,10 @@@ if (!eb) goto out; - btrfs_tree_lock(eb); + if (!btrfs_try_tree_write_lock(eb)) { + flush_fn(data); + btrfs_tree_lock(eb); + } btrfs_set_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN); if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)) { @@@ -3004,10 -2846,7 +3083,10 @@@ btrfs_tree_unlock(eb); free_extent_buffer(eb); out: - lock_page(page); + if (!trylock_page(page)) { + flush_fn(data); + lock_page(page); + } return 0; } @@@ -3363,6 -3202,7 +3442,7 @@@ static int btrfs_cleanup_transaction(st static struct extent_io_ops btree_extent_io_ops = { .write_cache_pages_lock_hook = btree_lock_page_hook, .readpage_end_io_hook = btree_readpage_end_io_hook, + .readpage_io_failed_hook = btree_io_failed_hook, .submit_bio_hook = btree_submit_bio_hook, /* note we're sharing with inode.c for the merge bio hook */ .merge_bio_hook = btrfs_merge_bio_hook, diff --combined fs/btrfs/disk-io.h index e678539c8519,b3bdb5c1390f..c99d0a8f13fa --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@@ -40,6 -40,8 +40,8 @@@ struct extent_buffer *read_tree_block(s u32 blocksize, u64 parent_transid); int readahead_tree_block(struct btrfs_root *root, u64 bytenr, u32 blocksize, u64 parent_transid); + int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr, u32 blocksize, + int mirror_num, struct extent_buffer **eb); struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root, u64 bytenr, u32 blocksize); int clean_tree_block(struct btrfs_trans_handle *trans, @@@ -83,6 -85,8 +85,6 @@@ int btrfs_init_log_root_tree(struct btr struct btrfs_fs_info *fs_info); int btrfs_add_log_tree(struct btrfs_trans_handle *trans, struct btrfs_root *root); -int btree_lock_page_hook(struct page *page); - #ifdef CONFIG_DEBUG_LOCK_ALLOC void btrfs_init_lockdep(void); diff --combined fs/btrfs/extent_io.c index cc3c58970d4e,deba714236d7..c12705682c65 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@@ -894,194 -894,6 +894,194 @@@ search_again goto again; } +/** + * convert_extent - convert all bits in a given range from one bit to another + * @tree: the io tree to search + * @start: the start offset in bytes + * @end: the end offset in bytes (inclusive) + * @bits: the bits to set in this range + * @clear_bits: the bits to clear in this range + * @mask: the allocation mask + * + * This will go through and set bits for the given range. If any states exist + * already in this range they are set with the given bit and cleared of the + * clear_bits. This is only meant to be used by things that are mergeable, ie + * converting from say DELALLOC to DIRTY. This is not meant to be used with + * boundary bits like LOCK. + */ +int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, + int bits, int clear_bits, gfp_t mask) +{ + struct extent_state *state; + struct extent_state *prealloc = NULL; + struct rb_node *node; + int err = 0; + u64 last_start; + u64 last_end; + +again: + if (!prealloc && (mask & __GFP_WAIT)) { + prealloc = alloc_extent_state(mask); + if (!prealloc) + return -ENOMEM; + } + + spin_lock(&tree->lock); + /* + * this search will find all the extents that end after + * our range starts. + */ + node = tree_search(tree, start); + if (!node) { + prealloc = alloc_extent_state_atomic(prealloc); + if (!prealloc) + return -ENOMEM; + err = insert_state(tree, prealloc, start, end, &bits); + prealloc = NULL; + BUG_ON(err == -EEXIST); + goto out; + } + state = rb_entry(node, struct extent_state, rb_node); +hit_next: + last_start = state->start; + last_end = state->end; + + /* + * | ---- desired range ---- | + * | state | + * + * Just lock what we found and keep going + */ + if (state->start == start && state->end <= end) { + struct rb_node *next_node; + + set_state_bits(tree, state, &bits); + clear_state_bit(tree, state, &clear_bits, 0); + + merge_state(tree, state); + if (last_end == (u64)-1) + goto out; + + start = last_end + 1; + next_node = rb_next(&state->rb_node); + if (next_node && start < end && prealloc && !need_resched()) { + state = rb_entry(next_node, struct extent_state, + rb_node); + if (state->start == start) + goto hit_next; + } + goto search_again; + } + + /* + * | ---- desired range ---- | + * | state | + * or + * | ------------- state -------------- | + * + * We need to split the extent we found, and may flip bits on + * second half. + * + * If the extent we found extends past our + * range, we just split and search again. It'll get split + * again the next time though. + * + * If the extent we found is inside our range, we set the + * desired bit on it. + */ + if (state->start < start) { + prealloc = alloc_extent_state_atomic(prealloc); + if (!prealloc) + return -ENOMEM; + err = split_state(tree, state, prealloc, start); + BUG_ON(err == -EEXIST); + prealloc = NULL; + if (err) + goto out; + if (state->end <= end) { + set_state_bits(tree, state, &bits); + clear_state_bit(tree, state, &clear_bits, 0); + merge_state(tree, state); + if (last_end == (u64)-1) + goto out; + start = last_end + 1; + } + goto search_again; + } + /* + * | ---- desired range ---- | + * | state | or | state | + * + * There's a hole, we need to insert something in it and + * ignore the extent we found. + */ + if (state->start > start) { + u64 this_end; + if (end < last_start) + this_end = end; + else + this_end = last_start - 1; + + prealloc = alloc_extent_state_atomic(prealloc); + if (!prealloc) + return -ENOMEM; + + /* + * Avoid to free 'prealloc' if it can be merged with + * the later extent. + */ + err = insert_state(tree, prealloc, start, this_end, + &bits); + BUG_ON(err == -EEXIST); + if (err) { + free_extent_state(prealloc); + prealloc = NULL; + goto out; + } + prealloc = NULL; + start = this_end + 1; + goto search_again; + } + /* + * | ---- desired range ---- | + * | state | + * We need to split the extent, and set the bit + * on the first half + */ + if (state->start <= end && state->end > end) { + prealloc = alloc_extent_state_atomic(prealloc); + if (!prealloc) + return -ENOMEM; + + err = split_state(tree, state, prealloc, end + 1); + BUG_ON(err == -EEXIST); + + set_state_bits(tree, prealloc, &bits); + clear_state_bit(tree, prealloc, &clear_bits, 0); + + merge_state(tree, prealloc); + prealloc = NULL; + goto out; + } + + goto search_again; + +out: + spin_unlock(&tree->lock); + if (prealloc) + free_extent_state(prealloc); + + return err; + +search_again: + if (start > end) + goto out; + spin_unlock(&tree->lock); + if (mask & __GFP_WAIT) + cond_resched(); + goto again; +} + /* wrappers around set/clear extent bit */ int set_extent_dirty(struct extent_io_tree *tree, u64 start, u64 end, gfp_t mask) @@@ -1107,7 -919,7 +1107,7 @@@ int set_extent_delalloc(struct extent_i struct extent_state **cached_state, gfp_t mask) { return set_extent_bit(tree, start, end, - EXTENT_DELALLOC | EXTENT_DIRTY | EXTENT_UPTODATE, + EXTENT_DELALLOC | EXTENT_UPTODATE, 0, NULL, cached_state, mask); } @@@ -1919,7 -1731,7 +1919,7 @@@ static void end_bio_extent_readpage(str if (!uptodate && tree->ops && tree->ops->readpage_io_failed_hook) { ret = tree->ops->readpage_io_failed_hook(bio, page, - start, end, NULL); + start, end, state); if (ret == 0) { uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); @@@ -2324,7 -2136,6 +2324,7 @@@ static int __extent_writepage(struct pa int compressed; int write_flags; unsigned long nr_written = 0; + bool fill_delalloc = true; if (wbc->sync_mode == WB_SYNC_ALL) write_flags = WRITE_SYNC; @@@ -2334,9 -2145,6 +2334,9 @@@ trace___extent_writepage(page, inode, wbc); WARN_ON(!PageLocked(page)); + + ClearPageError(page); + pg_offset = i_size & (PAGE_CACHE_SIZE - 1); if (page->index > end_index || (page->index == end_index && !pg_offset)) { @@@ -2358,13 -2166,10 +2358,13 @@@ set_page_extent_mapped(page); + if (!tree->ops || !tree->ops->fill_delalloc) + fill_delalloc = false; + delalloc_start = start; delalloc_end = 0; page_started = 0; - if (!epd->extent_locked) { + if (!epd->extent_locked && fill_delalloc) { u64 delalloc_to_write = 0; /* * make sure the wbc mapping index is at least updated @@@ -2616,16 -2421,10 +2616,16 @@@ retry * swizzled back from swapper_space to tmpfs file * mapping */ - if (tree->ops && tree->ops->write_cache_pages_lock_hook) - tree->ops->write_cache_pages_lock_hook(page); - else - lock_page(page); + if (tree->ops && + tree->ops->write_cache_pages_lock_hook) { + tree->ops->write_cache_pages_lock_hook(page, + data, flush_fn); + } else { + if (!trylock_page(page)) { + flush_fn(data); + lock_page(page); + } + } if (unlikely(page->mapping != mapping)) { unlock_page(page); @@@ -3405,7 -3204,6 +3405,7 @@@ int clear_extent_buffer_dirty(struct ex PAGECACHE_TAG_DIRTY); } spin_unlock_irq(&page->mapping->tree_lock); + ClearPageError(page); unlock_page(page); } return 0; @@@ -3551,8 -3349,7 +3551,7 @@@ int extent_buffer_uptodate(struct exten } int read_extent_buffer_pages(struct extent_io_tree *tree, - struct extent_buffer *eb, - u64 start, int wait, + struct extent_buffer *eb, u64 start, int wait, get_extent_t *get_extent, int mirror_num) { unsigned long i; @@@ -3588,7 -3385,7 +3587,7 @@@ num_pages = num_extent_pages(eb->start, eb->len); for (i = start_i; i < num_pages; i++) { page = extent_buffer_page(eb, i); - if (!wait) { + if (wait == WAIT_NONE) { if (!trylock_page(page)) goto unlock_exit; } else { @@@ -3632,7 -3429,7 +3631,7 @@@ if (bio) submit_one_bio(READ, bio, mirror_num, bio_flags); - if (ret || !wait) + if (ret || wait != WAIT_COMPLETE) return ret; for (i = start_i; i < num_pages; i++) { diff --combined fs/btrfs/extent_io.h index cbd4824a7c94,fcaf49bcb880..697570eed9e8 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@@ -17,7 -17,6 +17,7 @@@ #define EXTENT_NODATASUM (1 << 10) #define EXTENT_DO_ACCOUNTING (1 << 11) #define EXTENT_FIRST_DELALLOC (1 << 12) +#define EXTENT_NEED_WAIT (1 << 13) #define EXTENT_IOBITS (EXTENT_LOCKED | EXTENT_WRITEBACK) #define EXTENT_CTLBITS (EXTENT_DO_ACCOUNTING | EXTENT_FIRST_DELALLOC) @@@ -33,6 -32,7 +33,7 @@@ #define EXTENT_BUFFER_BLOCKING 1 #define EXTENT_BUFFER_DIRTY 2 #define EXTENT_BUFFER_CORRUPT 3 + #define EXTENT_BUFFER_READAHEAD 4 /* this got triggered by readahead */ /* these are flags for extent_clear_unlock_delalloc */ #define EXTENT_CLEAR_UNLOCK_PAGE 0x1 @@@ -86,8 -86,7 +87,8 @@@ struct extent_io_ops struct extent_state *other); void (*split_extent_hook)(struct inode *inode, struct extent_state *orig, u64 split); - int (*write_cache_pages_lock_hook)(struct page *page); + int (*write_cache_pages_lock_hook)(struct page *page, void *data, + void (*flush_fn)(void *)); }; struct extent_io_tree { @@@ -216,8 -215,6 +217,8 @@@ int set_extent_dirty(struct extent_io_t gfp_t mask); int clear_extent_dirty(struct extent_io_tree *tree, u64 start, u64 end, gfp_t mask); +int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, + int bits, int clear_bits, gfp_t mask); int set_extent_delalloc(struct extent_io_tree *tree, u64 start, u64 end, struct extent_state **cached_state, gfp_t mask); int find_first_extent_bit(struct extent_io_tree *tree, u64 start, @@@ -252,6 -249,9 +253,9 @@@ struct extent_buffer *alloc_extent_buff struct extent_buffer *find_extent_buffer(struct extent_io_tree *tree, u64 start, unsigned long len); void free_extent_buffer(struct extent_buffer *eb); + #define WAIT_NONE 0 + #define WAIT_COMPLETE 1 + #define WAIT_PAGE_LOCK 2 int read_extent_buffer_pages(struct extent_io_tree *tree, struct extent_buffer *eb, u64 start, int wait, get_extent_t *get_extent, int mirror_num); diff --combined fs/btrfs/scrub.c index 69a600f07763,f930f2776589..5bc4ec827b3d --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@@ -29,15 -29,12 +29,12 @@@ * any can be found. * * Future enhancements: - * - To enhance the performance, better read-ahead strategies for the - * extent-tree can be employed. * - In case an unrepairable extent is encountered, track which files are * affected and report them * - In case of a read error on files with nodatasum, map the file and read * the extent to trigger a writeback of the good copy * - track and record media errors, throw out bad devices * - add a mode to also read unallocated space - * - make the prefetch cancellable */ struct scrub_bio; @@@ -182,7 -179,7 +179,7 @@@ struct scrub_dev *scrub_setup_dev(struc sdev->curr = -1; atomic_set(&sdev->in_flight, 0); atomic_set(&sdev->cancel_req, 0); - sdev->csum_size = btrfs_super_csum_size(&fs_info->super_copy); + sdev->csum_size = btrfs_super_csum_size(fs_info->super_copy); INIT_LIST_HEAD(&sdev->csum_list); spin_lock_init(&sdev->list_lock); @@@ -741,13 -738,16 +738,16 @@@ static noinline_for_stack int scrub_str int slot; int i; u64 nstripes; - int start_stripe; struct extent_buffer *l; struct btrfs_key key; u64 physical; u64 logical; u64 generation; u64 mirror_num; + struct reada_control *reada1; + struct reada_control *reada2; + struct btrfs_key key_start; + struct btrfs_key key_end; u64 increment = map->stripe_len; u64 offset; @@@ -779,81 -779,67 +779,67 @@@ if (!path) return -ENOMEM; - path->reada = 2; path->search_commit_root = 1; path->skip_locking = 1; /* - * find all extents for each stripe and just read them to get - * them into the page cache - * FIXME: we can do better. build a more intelligent prefetching + * trigger the readahead for extent tree csum tree and wait for + * completion. During readahead, the scrub is officially paused + * to not hold off transaction commits */ logical = base + offset; - physical = map->stripes[num].physical; - ret = 0; - for (i = 0; i < nstripes; ++i) { - key.objectid = logical; - key.type = BTRFS_EXTENT_ITEM_KEY; - key.offset = (u64)0; - ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); - if (ret < 0) - goto out_noplug; - - /* - * we might miss half an extent here, but that doesn't matter, - * as it's only the prefetch - */ - while (1) { - l = path->nodes[0]; - slot = path->slots[0]; - if (slot >= btrfs_header_nritems(l)) { - ret = btrfs_next_leaf(root, path); - if (ret == 0) - continue; - if (ret < 0) - goto out_noplug; - - break; - } - btrfs_item_key_to_cpu(l, &key, slot); - - if (key.objectid >= logical + map->stripe_len) - break; - - path->slots[0]++; - } - btrfs_release_path(path); - logical += increment; - physical += map->stripe_len; - cond_resched(); + wait_event(sdev->list_wait, + atomic_read(&sdev->in_flight) == 0); + atomic_inc(&fs_info->scrubs_paused); + wake_up(&fs_info->scrub_pause_wait); + + /* FIXME it might be better to start readahead at commit root */ + key_start.objectid = logical; + key_start.type = BTRFS_EXTENT_ITEM_KEY; + key_start.offset = (u64)0; + key_end.objectid = base + offset + nstripes * increment; + key_end.type = BTRFS_EXTENT_ITEM_KEY; + key_end.offset = (u64)0; + reada1 = btrfs_reada_add(root, &key_start, &key_end); + + key_start.objectid = BTRFS_EXTENT_CSUM_OBJECTID; + key_start.type = BTRFS_EXTENT_CSUM_KEY; + key_start.offset = logical; + key_end.objectid = BTRFS_EXTENT_CSUM_OBJECTID; + key_end.type = BTRFS_EXTENT_CSUM_KEY; + key_end.offset = base + offset + nstripes * increment; + reada2 = btrfs_reada_add(csum_root, &key_start, &key_end); + + if (!IS_ERR(reada1)) + btrfs_reada_wait(reada1); + if (!IS_ERR(reada2)) + btrfs_reada_wait(reada2); + + mutex_lock(&fs_info->scrub_lock); + while (atomic_read(&fs_info->scrub_pause_req)) { + mutex_unlock(&fs_info->scrub_lock); + wait_event(fs_info->scrub_pause_wait, + atomic_read(&fs_info->scrub_pause_req) == 0); + mutex_lock(&fs_info->scrub_lock); } + atomic_dec(&fs_info->scrubs_paused); + mutex_unlock(&fs_info->scrub_lock); + wake_up(&fs_info->scrub_pause_wait); /* * collect all data csums for the stripe to avoid seeking during * the scrub. This might currently (crc32) end up to be about 1MB */ - start_stripe = 0; blk_start_plug(&plug); - again: - logical = base + offset + start_stripe * increment; - for (i = start_stripe; i < nstripes; ++i) { - ret = btrfs_lookup_csums_range(csum_root, logical, - logical + map->stripe_len - 1, - &sdev->csum_list, 1); - if (ret) - goto out; - logical += increment; - cond_resched(); - } /* * now find all extents for each stripe and scrub them */ - logical = base + offset + start_stripe * increment; - physical = map->stripes[num].physical + start_stripe * map->stripe_len; + logical = base + offset; + physical = map->stripes[num].physical; ret = 0; - for (i = start_stripe; i < nstripes; ++i) { + for (i = 0; i < nstripes; ++i) { /* * canceled? */ @@@ -882,11 -868,14 +868,14 @@@ atomic_dec(&fs_info->scrubs_paused); mutex_unlock(&fs_info->scrub_lock); wake_up(&fs_info->scrub_pause_wait); - scrub_free_csums(sdev); - start_stripe = i; - goto again; } + ret = btrfs_lookup_csums_range(csum_root, logical, + logical + map->stripe_len - 1, + &sdev->csum_list, 1); + if (ret) + goto out; + key.objectid = logical; key.type = BTRFS_EXTENT_ITEM_KEY; key.offset = (u64)0; @@@ -982,7 -971,6 +971,6 @@@ next out: blk_finish_plug(&plug); - out_noplug: btrfs_free_path(path); return ret < 0 ? ret : 0; } diff --combined fs/btrfs/volumes.c index c3b45564048e,1dccce5bc93d..f1685a2b45c8 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@@ -366,6 -366,14 +366,14 @@@ static noinline int device_list_add(con } INIT_LIST_HEAD(&device->dev_alloc_list); + /* init readahead state */ + spin_lock_init(&device->reada_lock); + device->reada_curr_zone = NULL; + atomic_set(&device->reada_in_flight, 0); + device->reada_next = 0; + INIT_RADIX_TREE(&device->reada_zones, GFP_NOFS & ~__GFP_WAIT); + INIT_RADIX_TREE(&device->reada_extents, GFP_NOFS & ~__GFP_WAIT); + mutex_lock(&fs_devices->device_list_mutex); list_add_rcu(&device->dev_list, &fs_devices->devices); mutex_unlock(&fs_devices->device_list_mutex); @@@ -597,8 -605,10 +605,8 @@@ static int __btrfs_open_devices(struct set_blocksize(bdev, 4096); bh = btrfs_read_dev_super(bdev); - if (!bh) { - ret = -EINVAL; + if (!bh) goto error_close; - } disk_super = (struct btrfs_super_block *)bh->b_data; devid = btrfs_stack_device_id(&disk_super->dev_item); @@@ -653,7 -663,7 +661,7 @@@ error continue; } if (fs_devices->open_devices == 0) { - ret = -EIO; + ret = -EINVAL; goto out; } fs_devices->seeding = seeding; @@@ -1011,13 -1021,8 +1019,13 @@@ static int btrfs_free_dev_extent(struc } BUG_ON(ret); - if (device->bytes_used > 0) - device->bytes_used -= btrfs_dev_extent_length(leaf, extent); + if (device->bytes_used > 0) { + u64 len = btrfs_dev_extent_length(leaf, extent); + device->bytes_used -= len; + spin_lock(&root->fs_info->free_chunk_lock); + root->fs_info->free_chunk_space += len; + spin_unlock(&root->fs_info->free_chunk_lock); + } ret = btrfs_del_item(trans, root, path); out: @@@ -1359,11 -1364,6 +1367,11 @@@ int btrfs_rm_device(struct btrfs_root * if (ret) goto error_undo; + spin_lock(&root->fs_info->free_chunk_lock); + root->fs_info->free_chunk_space = device->total_bytes - + device->bytes_used; + spin_unlock(&root->fs_info->free_chunk_lock); + device->in_fs_metadata = 0; btrfs_scrub_cancel_dev(root, device); @@@ -1395,8 -1395,8 +1403,8 @@@ call_rcu(&device->rcu, free_device); mutex_unlock(&root->fs_info->fs_devices->device_list_mutex); - num_devices = btrfs_super_num_devices(&root->fs_info->super_copy) - 1; - btrfs_set_super_num_devices(&root->fs_info->super_copy, num_devices); + num_devices = btrfs_super_num_devices(root->fs_info->super_copy) - 1; + btrfs_set_super_num_devices(root->fs_info->super_copy, num_devices); if (cur_devices->open_devices == 0) { struct btrfs_fs_devices *fs_devices; @@@ -1458,7 -1458,7 +1466,7 @@@ static int btrfs_prepare_sprout(struct struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices; struct btrfs_fs_devices *old_devices; struct btrfs_fs_devices *seed_devices; - struct btrfs_super_block *disk_super = &root->fs_info->super_copy; + struct btrfs_super_block *disk_super = root->fs_info->super_copy; struct btrfs_device *device; u64 super_flags; @@@ -1699,19 -1699,15 +1707,19 @@@ int btrfs_init_new_device(struct btrfs_ root->fs_info->fs_devices->num_can_discard++; root->fs_info->fs_devices->total_rw_bytes += device->total_bytes; + spin_lock(&root->fs_info->free_chunk_lock); + root->fs_info->free_chunk_space += device->total_bytes; + spin_unlock(&root->fs_info->free_chunk_lock); + if (!blk_queue_nonrot(bdev_get_queue(bdev))) root->fs_info->fs_devices->rotating = 1; - total_bytes = btrfs_super_total_bytes(&root->fs_info->super_copy); - btrfs_set_super_total_bytes(&root->fs_info->super_copy, + total_bytes = btrfs_super_total_bytes(root->fs_info->super_copy); + btrfs_set_super_total_bytes(root->fs_info->super_copy, total_bytes + device->total_bytes); - total_bytes = btrfs_super_num_devices(&root->fs_info->super_copy); - btrfs_set_super_num_devices(&root->fs_info->super_copy, + total_bytes = btrfs_super_num_devices(root->fs_info->super_copy); + btrfs_set_super_num_devices(root->fs_info->super_copy, total_bytes + 1); mutex_unlock(&root->fs_info->fs_devices->device_list_mutex); @@@ -1802,7 -1798,7 +1810,7 @@@ static int __btrfs_grow_device(struct b struct btrfs_device *device, u64 new_size) { struct btrfs_super_block *super_copy = - &device->dev_root->fs_info->super_copy; + device->dev_root->fs_info->super_copy; u64 old_total = btrfs_super_total_bytes(super_copy); u64 diff = new_size - device->total_bytes; @@@ -1861,7 -1857,7 +1869,7 @@@ static int btrfs_free_chunk(struct btrf static int btrfs_del_sys_chunk(struct btrfs_root *root, u64 chunk_objectid, u64 chunk_offset) { - struct btrfs_super_block *super_copy = &root->fs_info->super_copy; + struct btrfs_super_block *super_copy = root->fs_info->super_copy; struct btrfs_disk_key *disk_key; struct btrfs_chunk *chunk; u8 *ptr; @@@ -2187,7 -2183,7 +2195,7 @@@ int btrfs_shrink_device(struct btrfs_de bool retried = false; struct extent_buffer *l; struct btrfs_key key; - struct btrfs_super_block *super_copy = &root->fs_info->super_copy; + struct btrfs_super_block *super_copy = root->fs_info->super_copy; u64 old_total = btrfs_super_total_bytes(super_copy); u64 old_size = device->total_bytes; u64 diff = device->total_bytes - new_size; @@@ -2204,12 -2200,8 +2212,12 @@@ lock_chunks(root); device->total_bytes = new_size; - if (device->writeable) + if (device->writeable) { device->fs_devices->total_rw_bytes -= diff; + spin_lock(&root->fs_info->free_chunk_lock); + root->fs_info->free_chunk_space -= diff; + spin_unlock(&root->fs_info->free_chunk_lock); + } unlock_chunks(root); again: @@@ -2273,9 -2265,6 +2281,9 @@@ device->total_bytes = old_size; if (device->writeable) device->fs_devices->total_rw_bytes += diff; + spin_lock(&root->fs_info->free_chunk_lock); + root->fs_info->free_chunk_space += diff; + spin_unlock(&root->fs_info->free_chunk_lock); unlock_chunks(root); goto done; } @@@ -2311,7 -2300,7 +2319,7 @@@ static int btrfs_add_system_chunk(struc struct btrfs_key *key, struct btrfs_chunk *chunk, int item_size) { - struct btrfs_super_block *super_copy = &root->fs_info->super_copy; + struct btrfs_super_block *super_copy = root->fs_info->super_copy; struct btrfs_disk_key disk_key; u32 array_size; u8 *ptr; @@@ -2634,11 -2623,6 +2642,11 @@@ static int __finish_chunk_alloc(struct index++; } + spin_lock(&extent_root->fs_info->free_chunk_lock); + extent_root->fs_info->free_chunk_space -= (stripe_size * + map->num_stripes); + spin_unlock(&extent_root->fs_info->free_chunk_lock); + index = 0; stripe = &chunk->stripe; while (index < map->num_stripes) { @@@ -3640,20 -3624,15 +3648,20 @@@ static int read_one_dev(struct btrfs_ro fill_device_from_item(leaf, dev_item, device); device->dev_root = root->fs_info->dev_root; device->in_fs_metadata = 1; - if (device->writeable) + if (device->writeable) { device->fs_devices->total_rw_bytes += device->total_bytes; + spin_lock(&root->fs_info->free_chunk_lock); + root->fs_info->free_chunk_space += device->total_bytes - + device->bytes_used; + spin_unlock(&root->fs_info->free_chunk_lock); + } ret = 0; return ret; } int btrfs_read_sys_array(struct btrfs_root *root) { - struct btrfs_super_block *super_copy = &root->fs_info->super_copy; + struct btrfs_super_block *super_copy = root->fs_info->super_copy; struct extent_buffer *sb; struct btrfs_disk_key *disk_key; struct btrfs_chunk *chunk;