From: Chris Mason Date: Mon, 16 Jan 2012 20:27:58 +0000 (-0500) Subject: Merge branch 'integrity-check-patch-v2' of git://btrfs.giantdisaster.de/git/btrfs... X-Git-Tag: v3.3-rc1~26^2~9 X-Git-Url: http://pileus.org/git/?a=commitdiff_plain;h=c126dea771be1b3c370c0ffc4a09e6a82d492a49;hp=-c;p=~andy%2Flinux Merge branch 'integrity-check-patch-v2' of git://btrfs.giantdisaster.de/git/btrfs into integration Conflicts: fs/btrfs/ctree.h fs/btrfs/super.c Signed-off-by: Chris Mason --- c126dea771be1b3c370c0ffc4a09e6a82d492a49 diff --combined fs/btrfs/Makefile index 70798407b9a,bc5b3556cee..0c4fa2befae --- a/fs/btrfs/Makefile +++ b/fs/btrfs/Makefile @@@ -8,6 -8,7 +8,7 @@@ btrfs-y += super.o ctree.o extent-tree. extent_io.o volumes.o async-thread.o ioctl.o locking.o orphan.o \ export.o tree-log.o free-space-cache.o zlib.o lzo.o \ compression.o delayed-ref.o relocation.o delayed-inode.o scrub.o \ - reada.o backref.o + reada.o backref.o ulist.o btrfs-$(CONFIG_BTRFS_FS_POSIX_ACL) += acl.o + btrfs-$(CONFIG_BTRFS_FS_CHECK_INTEGRITY) += check-integrity.o diff --combined fs/btrfs/ctree.h index b6d1020c457,39f6188688e..3c2cbf7b666 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@@ -86,9 -86,6 +86,9 @@@ struct btrfs_ordered_sum /* holds checksums of all the data extents */ #define BTRFS_CSUM_TREE_OBJECTID 7ULL +/* for storing balance parameters in the root tree */ +#define BTRFS_BALANCE_OBJECTID -4ULL + /* orhpan objectid for tracking unlinked/truncated files */ #define BTRFS_ORPHAN_OBJECTID -5ULL @@@ -695,54 -692,6 +695,54 @@@ struct btrfs_root_ref __le16 name_len; } __attribute__ ((__packed__)); +struct btrfs_disk_balance_args { + /* + * profiles to operate on, single is denoted by + * BTRFS_AVAIL_ALLOC_BIT_SINGLE + */ + __le64 profiles; + + /* usage filter */ + __le64 usage; + + /* devid filter */ + __le64 devid; + + /* devid subset filter [pstart..pend) */ + __le64 pstart; + __le64 pend; + + /* btrfs virtual address space subset filter [vstart..vend) */ + __le64 vstart; + __le64 vend; + + /* + * profile to convert to, single is denoted by + * BTRFS_AVAIL_ALLOC_BIT_SINGLE + */ + __le64 target; + + /* BTRFS_BALANCE_ARGS_* */ + __le64 flags; + + __le64 unused[8]; +} __attribute__ ((__packed__)); + +/* + * store balance parameters to disk so that balance can be properly + * resumed after crash or unmount + */ +struct btrfs_balance_item { + /* BTRFS_BALANCE_* */ + __le64 flags; + + struct btrfs_disk_balance_args data; + struct btrfs_disk_balance_args meta; + struct btrfs_disk_balance_args sys; + + __le64 unused[4]; +} __attribute__ ((__packed__)); + #define BTRFS_FILE_EXTENT_INLINE 0 #define BTRFS_FILE_EXTENT_REG 1 #define BTRFS_FILE_EXTENT_PREALLOC 2 @@@ -802,32 -751,14 +802,32 @@@ struct btrfs_csum_item } __attribute__ ((__packed__)); /* different types of block groups (and chunks) */ -#define BTRFS_BLOCK_GROUP_DATA (1 << 0) -#define BTRFS_BLOCK_GROUP_SYSTEM (1 << 1) -#define BTRFS_BLOCK_GROUP_METADATA (1 << 2) -#define BTRFS_BLOCK_GROUP_RAID0 (1 << 3) -#define BTRFS_BLOCK_GROUP_RAID1 (1 << 4) -#define BTRFS_BLOCK_GROUP_DUP (1 << 5) -#define BTRFS_BLOCK_GROUP_RAID10 (1 << 6) -#define BTRFS_NR_RAID_TYPES 5 +#define BTRFS_BLOCK_GROUP_DATA (1ULL << 0) +#define BTRFS_BLOCK_GROUP_SYSTEM (1ULL << 1) +#define BTRFS_BLOCK_GROUP_METADATA (1ULL << 2) +#define BTRFS_BLOCK_GROUP_RAID0 (1ULL << 3) +#define BTRFS_BLOCK_GROUP_RAID1 (1ULL << 4) +#define BTRFS_BLOCK_GROUP_DUP (1ULL << 5) +#define BTRFS_BLOCK_GROUP_RAID10 (1ULL << 6) +#define BTRFS_BLOCK_GROUP_RESERVED BTRFS_AVAIL_ALLOC_BIT_SINGLE +#define BTRFS_NR_RAID_TYPES 5 + +#define BTRFS_BLOCK_GROUP_TYPE_MASK (BTRFS_BLOCK_GROUP_DATA | \ + BTRFS_BLOCK_GROUP_SYSTEM | \ + BTRFS_BLOCK_GROUP_METADATA) + +#define BTRFS_BLOCK_GROUP_PROFILE_MASK (BTRFS_BLOCK_GROUP_RAID0 | \ + BTRFS_BLOCK_GROUP_RAID1 | \ + BTRFS_BLOCK_GROUP_DUP | \ + BTRFS_BLOCK_GROUP_RAID10) +/* + * We need a bit for restriper to be able to tell when chunks of type + * SINGLE are available. This "extended" profile format is used in + * fs_info->avail_*_alloc_bits (in-memory) and balance item fields + * (on-disk). The corresponding on-disk bit in chunk.type is reserved + * to avoid remappings between two formats in future. + */ +#define BTRFS_AVAIL_ALLOC_BIT_SINGLE (1ULL << 48) struct btrfs_block_group_item { __le64 used; @@@ -985,7 -916,6 +985,7 @@@ struct btrfs_block_group_cache struct reloc_control; struct btrfs_device; struct btrfs_fs_devices; +struct btrfs_balance_control; struct btrfs_delayed_root; struct btrfs_fs_info { u8 fsid[BTRFS_FSID_SIZE]; @@@ -1041,7 -971,7 +1041,7 @@@ * is required instead of the faster short fsync log commits */ u64 last_trans_log_full_commit; - unsigned long mount_opt:20; + unsigned long mount_opt:21; unsigned long compress_type:4; u64 max_inline; u64 alloc_start; @@@ -1202,23 -1132,12 +1202,23 @@@ spinlock_t ref_cache_lock; u64 total_ref_cache_size; + /* + * these three are in extended format (availability of single + * chunks is denoted by BTRFS_AVAIL_ALLOC_BIT_SINGLE bit, other + * types are denoted by corresponding BTRFS_BLOCK_GROUP_* bits) + */ u64 avail_data_alloc_bits; u64 avail_metadata_alloc_bits; u64 avail_system_alloc_bits; - u64 data_alloc_profile; - u64 metadata_alloc_profile; - u64 system_alloc_profile; + + /* restriper state */ + spinlock_t balance_lock; + struct mutex balance_mutex; + atomic_t balance_running; + atomic_t balance_pause_req; + atomic_t balance_cancel_req; + struct btrfs_balance_control *balance_ctl; + wait_queue_head_t balance_wait_q; unsigned data_chunk_allocations; unsigned metadata_ratio; @@@ -1236,6 -1155,10 +1236,10 @@@ int scrub_workers_refcnt; struct btrfs_workers scrub_workers; + #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY + u32 check_integrity_print_mask; + #endif + /* filesystem state */ u64 fs_state; @@@ -1464,8 -1387,6 +1468,8 @@@ struct btrfs_ioctl_defrag_range_args #define BTRFS_DEV_ITEM_KEY 216 #define BTRFS_CHUNK_ITEM_KEY 228 +#define BTRFS_BALANCE_ITEM_KEY 248 + /* * string items are for debugging. They just store a short string of * data in the FS @@@ -1496,7 -1417,8 +1500,9 @@@ #define BTRFS_MOUNT_AUTO_DEFRAG (1 << 16) #define BTRFS_MOUNT_INODE_MAP_CACHE (1 << 17) #define BTRFS_MOUNT_RECOVERY (1 << 18) -#define BTRFS_MOUNT_CHECK_INTEGRITY (1 << 19) -#define BTRFS_MOUNT_CHECK_INTEGRITY_INCLUDING_EXTENT_DATA (1 << 20) +#define BTRFS_MOUNT_SKIP_BALANCE (1 << 19) ++#define BTRFS_MOUNT_CHECK_INTEGRITY (1 << 20) ++#define BTRFS_MOUNT_CHECK_INTEGRITY_INCLUDING_EXTENT_DATA (1 << 21) #define btrfs_clear_opt(o, opt) ((o) &= ~BTRFS_MOUNT_##opt) #define btrfs_set_opt(o, opt) ((o) |= BTRFS_MOUNT_##opt) @@@ -2161,86 -2083,8 +2167,86 @@@ BTRFS_SETGET_STACK_FUNCS(backup_bytes_u BTRFS_SETGET_STACK_FUNCS(backup_num_devices, struct btrfs_root_backup, num_devices, 64); -/* struct btrfs_super_block */ +/* struct btrfs_balance_item */ +BTRFS_SETGET_FUNCS(balance_flags, struct btrfs_balance_item, flags, 64); + +static inline void btrfs_balance_data(struct extent_buffer *eb, + struct btrfs_balance_item *bi, + struct btrfs_disk_balance_args *ba) +{ + read_eb_member(eb, bi, struct btrfs_balance_item, data, ba); +} +static inline void btrfs_set_balance_data(struct extent_buffer *eb, + struct btrfs_balance_item *bi, + struct btrfs_disk_balance_args *ba) +{ + write_eb_member(eb, bi, struct btrfs_balance_item, data, ba); +} + +static inline void btrfs_balance_meta(struct extent_buffer *eb, + struct btrfs_balance_item *bi, + struct btrfs_disk_balance_args *ba) +{ + read_eb_member(eb, bi, struct btrfs_balance_item, meta, ba); +} + +static inline void btrfs_set_balance_meta(struct extent_buffer *eb, + struct btrfs_balance_item *bi, + struct btrfs_disk_balance_args *ba) +{ + write_eb_member(eb, bi, struct btrfs_balance_item, meta, ba); +} + +static inline void btrfs_balance_sys(struct extent_buffer *eb, + struct btrfs_balance_item *bi, + struct btrfs_disk_balance_args *ba) +{ + read_eb_member(eb, bi, struct btrfs_balance_item, sys, ba); +} + +static inline void btrfs_set_balance_sys(struct extent_buffer *eb, + struct btrfs_balance_item *bi, + struct btrfs_disk_balance_args *ba) +{ + write_eb_member(eb, bi, struct btrfs_balance_item, sys, ba); +} + +static inline void +btrfs_disk_balance_args_to_cpu(struct btrfs_balance_args *cpu, + struct btrfs_disk_balance_args *disk) +{ + memset(cpu, 0, sizeof(*cpu)); + + cpu->profiles = le64_to_cpu(disk->profiles); + cpu->usage = le64_to_cpu(disk->usage); + cpu->devid = le64_to_cpu(disk->devid); + cpu->pstart = le64_to_cpu(disk->pstart); + cpu->pend = le64_to_cpu(disk->pend); + cpu->vstart = le64_to_cpu(disk->vstart); + cpu->vend = le64_to_cpu(disk->vend); + cpu->target = le64_to_cpu(disk->target); + cpu->flags = le64_to_cpu(disk->flags); +} + +static inline void +btrfs_cpu_balance_args_to_disk(struct btrfs_disk_balance_args *disk, + struct btrfs_balance_args *cpu) +{ + memset(disk, 0, sizeof(*disk)); + + disk->profiles = cpu_to_le64(cpu->profiles); + disk->usage = cpu_to_le64(cpu->usage); + disk->devid = cpu_to_le64(cpu->devid); + disk->pstart = cpu_to_le64(cpu->pstart); + disk->pend = cpu_to_le64(cpu->pend); + disk->vstart = cpu_to_le64(cpu->vstart); + disk->vend = cpu_to_le64(cpu->vend); + disk->target = cpu_to_le64(cpu->target); + disk->flags = cpu_to_le64(cpu->flags); +} + +/* struct btrfs_super_block */ BTRFS_SETGET_STACK_FUNCS(super_bytenr, struct btrfs_super_block, bytenr, 64); BTRFS_SETGET_STACK_FUNCS(super_flags, struct btrfs_super_block, flags, 64); BTRFS_SETGET_STACK_FUNCS(super_generation, struct btrfs_super_block, @@@ -2439,11 -2283,11 +2445,11 @@@ struct extent_buffer *btrfs_alloc_free_ struct btrfs_root *root, u32 blocksize, u64 parent, u64 root_objectid, struct btrfs_disk_key *key, int level, - u64 hint, u64 empty_size); + u64 hint, u64 empty_size, int for_cow); void btrfs_free_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, - u64 parent, int last_ref); + u64 parent, int last_ref, int for_cow); struct extent_buffer *btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u32 blocksize, @@@ -2463,17 -2307,17 +2469,17 @@@ int btrfs_reserve_extent(struct btrfs_t u64 search_end, struct btrfs_key *ins, u64 data); int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, - struct extent_buffer *buf, int full_backref); + struct extent_buffer *buf, int full_backref, int for_cow); int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, - struct extent_buffer *buf, int full_backref); + struct extent_buffer *buf, int full_backref, int for_cow); int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 num_bytes, u64 flags, int is_data); int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root, - u64 bytenr, u64 num_bytes, u64 parent, - u64 root_objectid, u64 owner, u64 offset); + u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid, + u64 owner, u64 offset, int for_cow); int btrfs_free_reserved_extent(struct btrfs_root *root, u64 start, u64 len); int btrfs_free_and_pin_reserved_extent(struct btrfs_root *root, @@@ -2485,7 -2329,7 +2491,7 @@@ int btrfs_finish_extent_commit(struct b int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 num_bytes, u64 parent, - u64 root_objectid, u64 owner, u64 offset); + u64 root_objectid, u64 owner, u64 offset, int for_cow); int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans, struct btrfs_root *root); @@@ -2644,18 -2488,10 +2650,18 @@@ static inline int btrfs_insert_empty_it } int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path); +static inline int btrfs_next_item(struct btrfs_root *root, struct btrfs_path *p) +{ + ++p->slots[0]; + if (p->slots[0] >= btrfs_header_nritems(p->nodes[0])) + return btrfs_next_leaf(root, p); + return 0; +} int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path); int btrfs_leaf_free_space(struct btrfs_root *root, struct extent_buffer *leaf); void btrfs_drop_snapshot(struct btrfs_root *root, - struct btrfs_block_rsv *block_rsv, int update_ref); + struct btrfs_block_rsv *block_rsv, int update_ref, + int for_reloc); int btrfs_drop_subtree(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *node, @@@ -2670,7 -2506,6 +2676,7 @@@ static inline int btrfs_fs_closing(stru } static inline void free_fs_info(struct btrfs_fs_info *fs_info) { + kfree(fs_info->balance_ctl); kfree(fs_info->delayed_root); kfree(fs_info->extent_root); kfree(fs_info->tree_root); @@@ -2681,24 -2516,6 +2687,24 @@@ kfree(fs_info->super_for_commit); kfree(fs_info); } +/** + * profile_is_valid - tests whether a given profile is valid and reduced + * @flags: profile to validate + * @extended: if true @flags is treated as an extended profile + */ +static inline int profile_is_valid(u64 flags, int extended) +{ + u64 mask = ~BTRFS_BLOCK_GROUP_PROFILE_MASK; + + flags &= ~BTRFS_BLOCK_GROUP_TYPE_MASK; + if (extended) + mask &= ~BTRFS_AVAIL_ALLOC_BIT_SINGLE; + + if (flags & mask) + return 0; + /* true if zero or exactly one bit set */ + return (flags & (~flags + 1)) == flags; +} /* root-item.c */ int btrfs_find_root_ref(struct btrfs_root *tree_root, diff --combined fs/btrfs/disk-io.c index 9be97716c5e,f363c6d9c3d..da4457f84d7 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@@ -43,6 -43,7 +43,7 @@@ #include "tree-log.h" #include "free-space-cache.h" #include "inode-map.h" + #include "check-integrity.h" static struct extent_io_ops btree_extent_io_ops; static void end_workqueue_fn(struct btrfs_work *work); @@@ -1243,8 -1244,7 +1244,8 @@@ static struct btrfs_root *alloc_log_tre root->ref_cows = 0; leaf = btrfs_alloc_free_block(trans, root, root->leafsize, 0, - BTRFS_TREE_LOG_OBJECTID, NULL, 0, 0, 0); + BTRFS_TREE_LOG_OBJECTID, NULL, + 0, 0, 0, 0); if (IS_ERR(leaf)) { kfree(root); return ERR_CAST(leaf); @@@ -2002,21 -2002,16 +2003,24 @@@ struct btrfs_root *open_ctree(struct su init_waitqueue_head(&fs_info->scrub_pause_wait); init_rwsem(&fs_info->scrub_super_lock); fs_info->scrub_workers_refcnt = 0; + #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY + fs_info->check_integrity_print_mask = 0; + #endif + spin_lock_init(&fs_info->balance_lock); + mutex_init(&fs_info->balance_mutex); + atomic_set(&fs_info->balance_running, 0); + atomic_set(&fs_info->balance_pause_req, 0); + atomic_set(&fs_info->balance_cancel_req, 0); + fs_info->balance_ctl = NULL; + init_waitqueue_head(&fs_info->balance_wait_q); + sb->s_blocksize = 4096; sb->s_blocksize_bits = blksize_bits(4096); sb->s_bdi = &fs_info->bdi; fs_info->btree_inode->i_ino = BTRFS_BTREE_INODE_OBJECTID; - fs_info->btree_inode->i_nlink = 1; + set_nlink(fs_info->btree_inode, 1); /* * we set the i_size on the btree inode to the max possible int. * the real end of the address space is determined by all of @@@ -2279,7 -2274,9 +2283,7 @@@ (unsigned long)btrfs_header_chunk_tree_uuid(chunk_root->node), BTRFS_UUID_SIZE); - mutex_lock(&fs_info->chunk_mutex); ret = btrfs_read_chunk_tree(chunk_root); - mutex_unlock(&fs_info->chunk_mutex); if (ret) { printk(KERN_WARNING "btrfs: failed to read chunk tree on %s\n", sb->s_id); @@@ -2328,6 -2325,9 +2332,6 @@@ retry_root_backup fs_info->generation = generation; fs_info->last_trans_committed = generation; - fs_info->data_alloc_profile = (u64)-1; - fs_info->metadata_alloc_profile = (u64)-1; - fs_info->system_alloc_profile = fs_info->metadata_alloc_profile; ret = btrfs_init_space_info(fs_info); if (ret) { @@@ -2360,6 -2360,19 +2364,19 @@@ btrfs_set_opt(fs_info->mount_opt, SSD); } + #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY + if (btrfs_test_opt(tree_root, CHECK_INTEGRITY)) { + ret = btrfsic_mount(tree_root, fs_devices, + btrfs_test_opt(tree_root, + CHECK_INTEGRITY_INCLUDING_EXTENT_DATA) ? + 1 : 0, + fs_info->check_integrity_print_mask); + if (ret) + printk(KERN_WARNING "btrfs: failed to initialize" + " integrity check module %s\n", sb->s_id); + } + #endif + /* do not make disk changes in broken FS */ if (btrfs_super_log_root(disk_super) != 0 && !(fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR)) { @@@ -2430,10 -2443,6 +2447,10 @@@ if (!err) err = btrfs_orphan_cleanup(fs_info->tree_root); up_read(&fs_info->cleanup_work_sem); + + if (!err) + err = btrfs_recover_balance(fs_info->tree_root); + if (err) { close_ctree(tree_root); return ERR_PTR(err); @@@ -2642,7 -2651,7 +2659,7 @@@ static int write_dev_supers(struct btrf * we fua the first super. The others we allow * to go down lazy. */ - ret = submit_bh(WRITE_FUA, bh); + ret = btrfsic_submit_bh(WRITE_FUA, bh); if (ret) errors++; } @@@ -2719,7 -2728,7 +2736,7 @@@ static int write_dev_flush(struct btrfs device->flush_bio = bio; bio_get(bio); - submit_bio(WRITE_FLUSH, bio); + btrfsic_submit_bio(WRITE_FLUSH, bio); return 0; } @@@ -2983,9 -2992,6 +3000,9 @@@ int close_ctree(struct btrfs_root *root fs_info->closing = 1; smp_mb(); + /* pause restriper - we want to resume on mount */ + btrfs_pause_balance(root->fs_info); + btrfs_scrub_cancel(root); /* wait for any defraggers to finish */ @@@ -3068,6 -3074,11 +3085,11 @@@ btrfs_stop_workers(&fs_info->caching_workers); btrfs_stop_workers(&fs_info->readahead_workers); + #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY + if (btrfs_test_opt(root, CHECK_INTEGRITY)) + btrfsic_unmount(root, fs_info->fs_devices); + #endif + btrfs_close_devices(fs_info->fs_devices); btrfs_mapping_tree_free(&fs_info->mapping_tree); diff --combined fs/btrfs/extent_io.c index 3622cc22ff9,246669296e0..9d09a4f8187 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@@ -18,6 -18,7 +18,7 @@@ #include "ctree.h" #include "btrfs_inode.h" #include "volumes.h" + #include "check-integrity.h" static struct kmem_cache *extent_state_cache; static struct kmem_cache *extent_buffer_cache; @@@ -1895,7 -1896,7 +1896,7 @@@ int repair_io_failure(struct btrfs_mapp } bio->bi_bdev = dev->bdev; bio_add_page(bio, page, length, start-page_offset(page)); - submit_bio(WRITE_SYNC, bio); + btrfsic_submit_bio(WRITE_SYNC, bio); wait_for_completion(&compl); if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) { @@@ -2393,7 -2394,7 +2394,7 @@@ static int submit_one_bio(int rw, struc ret = tree->ops->submit_bio_hook(page->mapping->host, rw, bio, mirror_num, bio_flags, start); else - submit_bio(rw, bio); + btrfsic_submit_bio(rw, bio); if (bio_flagged(bio, BIO_EOPNOTSUPP)) ret = -EOPNOTSUPP; @@@ -3579,7 -3580,6 +3580,7 @@@ static struct extent_buffer *__alloc_ex atomic_set(&eb->blocking_writers, 0); atomic_set(&eb->spinning_readers, 0); atomic_set(&eb->spinning_writers, 0); + eb->lock_nested = 0; init_waitqueue_head(&eb->write_lock_wq); init_waitqueue_head(&eb->read_lock_wq); diff --combined fs/btrfs/scrub.c index 6a6a51a809b,567e148caca..9770cc5bfb7 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@@ -25,6 -25,7 +25,7 @@@ #include "transaction.h" #include "backref.h" #include "extent_io.h" + #include "check-integrity.h" /* * This is only the first step towards a full-features scrub. It reads all @@@ -309,7 -310,7 +310,7 @@@ static void scrub_print_warning(const c u8 ref_level; unsigned long ptr = 0; const int bufsize = 4096; - u64 extent_offset; + u64 extent_item_pos; path = btrfs_alloc_path(); @@@ -329,13 -330,12 +330,13 @@@ if (ret < 0) goto out; - extent_offset = swarn.logical - found_key.objectid; + extent_item_pos = swarn.logical - found_key.objectid; swarn.extent_item_size = found_key.offset; eb = path->nodes[0]; ei = btrfs_item_ptr(eb, path->slots[0], struct btrfs_extent_item); item_size = btrfs_item_size_nr(eb, path->slots[0]); + btrfs_release_path(path); if (ret & BTRFS_EXTENT_FLAG_TREE_BLOCK) { do { @@@ -352,7 -352,7 +353,7 @@@ } else { swarn.path = path; iterate_extent_inodes(fs_info, path, found_key.objectid, - extent_offset, + extent_item_pos, scrub_print_warning_inode, &swarn); } @@@ -733,7 -733,7 +734,7 @@@ static int scrub_fixup_io(int rw, struc bio_add_page(bio, page, PAGE_SIZE, 0); bio->bi_end_io = scrub_fixup_end_io; bio->bi_private = &complete; - submit_bio(rw, bio); + btrfsic_submit_bio(rw, bio); /* this will also unplug the queue */ wait_for_completion(&complete); @@@ -959,7 -959,7 +960,7 @@@ static int scrub_submit(struct scrub_de sdev->curr = -1; atomic_inc(&sdev->in_flight); - submit_bio(READ, sbio->bio); + btrfsic_submit_bio(READ, sbio->bio); return 0; } diff --combined fs/btrfs/super.c index 5a7227fa938,22a2015f1d7..61717a4eb14 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@@ -164,8 -164,10 +164,10 @@@ enum Opt_compress_type, Opt_compress_force, Opt_compress_force_type, Opt_notreelog, Opt_ratio, Opt_flushoncommit, Opt_discard, Opt_space_cache, Opt_clear_cache, Opt_user_subvol_rm_allowed, - Opt_enospc_debug, Opt_subvolrootid, Opt_defrag, - Opt_inode_cache, Opt_no_space_cache, Opt_recovery, + Opt_enospc_debug, Opt_subvolrootid, Opt_defrag, Opt_inode_cache, + Opt_no_space_cache, Opt_recovery, Opt_skip_balance, + Opt_check_integrity, Opt_check_integrity_including_extent_data, + Opt_check_integrity_print_mask, Opt_err, }; @@@ -201,7 -203,9 +203,10 @@@ static match_table_t tokens = {Opt_inode_cache, "inode_cache"}, {Opt_no_space_cache, "nospace_cache"}, {Opt_recovery, "recovery"}, + {Opt_skip_balance, "skip_balance"}, + {Opt_check_integrity, "check_int"}, + {Opt_check_integrity_including_extent_data, "check_int_data"}, + {Opt_check_integrity_print_mask, "check_int_print_mask=%d"}, {Opt_err, NULL}, }; @@@ -400,9 -404,37 +405,40 @@@ int btrfs_parse_options(struct btrfs_ro printk(KERN_INFO "btrfs: enabling auto recovery"); btrfs_set_opt(info->mount_opt, RECOVERY); break; + case Opt_skip_balance: + btrfs_set_opt(info->mount_opt, SKIP_BALANCE); + break; + #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY + case Opt_check_integrity_including_extent_data: + printk(KERN_INFO "btrfs: enabling check integrity" + " including extent data\n"); + btrfs_set_opt(info->mount_opt, + CHECK_INTEGRITY_INCLUDING_EXTENT_DATA); + btrfs_set_opt(info->mount_opt, CHECK_INTEGRITY); + break; + case Opt_check_integrity: + printk(KERN_INFO "btrfs: enabling check integrity\n"); + btrfs_set_opt(info->mount_opt, CHECK_INTEGRITY); + break; + case Opt_check_integrity_print_mask: + intarg = 0; + match_int(&args[0], &intarg); + if (intarg) { + info->check_integrity_print_mask = intarg; + printk(KERN_INFO "btrfs:" + " check_integrity_print_mask 0x%x\n", + info->check_integrity_print_mask); + } + break; + #else + case Opt_check_integrity_including_extent_data: + case Opt_check_integrity: + case Opt_check_integrity_print_mask: + printk(KERN_ERR "btrfs: support for check_integrity*" + " not compiled in!\n"); + ret = -EINVAL; + goto out; + #endif case Opt_err: printk(KERN_INFO "btrfs: unrecognized mount option " "'%s'\n", p); @@@ -728,8 -760,6 +764,8 @@@ static int btrfs_show_options(struct se seq_puts(seq, ",autodefrag"); if (btrfs_test_opt(root, INODE_MAP_CACHE)) seq_puts(seq, ",inode_cache"); + if (btrfs_test_opt(root, SKIP_BALANCE)) + seq_puts(seq, ",skip_balance"); return 0; } @@@ -833,9 -863,13 +869,9 @@@ static char *setup_root_args(char *args static struct dentry *mount_subvol(const char *subvol_name, int flags, const char *device_name, char *data) { - struct super_block *s; struct dentry *root; struct vfsmount *mnt; - struct mnt_namespace *ns_private; char *newargs; - struct path path; - int error; newargs = setup_root_args(data); if (!newargs) @@@ -846,17 -880,39 +882,17 @@@ if (IS_ERR(mnt)) return ERR_CAST(mnt); - ns_private = create_mnt_ns(mnt); - if (IS_ERR(ns_private)) { - mntput(mnt); - return ERR_CAST(ns_private); - } + root = mount_subtree(mnt, subvol_name); - /* - * This will trigger the automount of the subvol so we can just - * drop the mnt we have here and return the dentry that we - * found. - */ - error = vfs_path_lookup(mnt->mnt_root, mnt, subvol_name, - LOOKUP_FOLLOW, &path); - put_mnt_ns(ns_private); - if (error) - return ERR_PTR(error); - - if (!is_subvolume_inode(path.dentry->d_inode)) { - path_put(&path); - mntput(mnt); - error = -EINVAL; + if (!IS_ERR(root) && !is_subvolume_inode(root->d_inode)) { + struct super_block *s = root->d_sb; + dput(root); + root = ERR_PTR(-EINVAL); + deactivate_locked_super(s); printk(KERN_ERR "btrfs: '%s' is not a valid subvolume\n", subvol_name); - return ERR_PTR(-EINVAL); } - /* Get a ref to the sb and the dentry we found and return it */ - s = path.mnt->mnt_sb; - atomic_inc(&s->s_active); - root = dget(path.dentry); - path_put(&path); - down_write(&s->s_umount); - return root; } diff --combined fs/btrfs/volumes.c index e0b7bb92a17,821334f6e3a..59e878f9fdc --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@@ -23,7 -23,6 +23,7 @@@ #include #include #include +#include #include #include "compat.h" #include "ctree.h" @@@ -33,6 -32,7 +33,7 @@@ #include "print-tree.h" #include "volumes.h" #include "async-thread.h" + #include "check-integrity.h" static int init_first_rw_device(struct btrfs_trans_handle *trans, struct btrfs_root *root, @@@ -247,7 -247,7 +248,7 @@@ loop_lock sync_pending = 0; } - submit_bio(cur->bi_rw, cur); + btrfsic_submit_bio(cur->bi_rw, cur); num_run++; batch_run++; if (need_resched()) @@@ -830,6 -830,7 +831,6 @@@ out /* * find_free_dev_extent - find free space in the specified device - * @trans: transaction handler * @device: the device which we search the free space in * @num_bytes: the size of the free space that we need * @start: store the start of the free space. @@@ -848,7 -849,8 +849,7 @@@ * But if we don't find suitable free space, it is used to store the size of * the max free space. */ -int find_free_dev_extent(struct btrfs_trans_handle *trans, - struct btrfs_device *device, u64 num_bytes, +int find_free_dev_extent(struct btrfs_device *device, u64 num_bytes, u64 *start, u64 *len) { struct btrfs_key key; @@@ -892,7 -894,7 +893,7 @@@ key.offset = search_start; key.type = BTRFS_DEV_EXTENT_KEY; - ret = btrfs_search_slot(trans, root, &key, path, 0, 0); + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) goto out; if (ret > 0) { @@@ -1281,6 -1283,7 +1282,6 @@@ int btrfs_rm_device(struct btrfs_root * bool clear_super = false; mutex_lock(&uuid_mutex); - mutex_lock(&root->fs_info->volume_mutex); all_avail = root->fs_info->avail_data_alloc_bits | root->fs_info->avail_system_alloc_bits | @@@ -1450,6 -1453,7 +1451,6 @@@ error_close if (bdev) blkdev_put(bdev, FMODE_READ | FMODE_EXCL); out: - mutex_unlock(&root->fs_info->volume_mutex); mutex_unlock(&uuid_mutex); return ret; error_undo: @@@ -1466,7 -1470,8 +1467,7 @@@ /* * does all the dirty work required for changing file system's UUID. */ -static int btrfs_prepare_sprout(struct btrfs_trans_handle *trans, - struct btrfs_root *root) +static int btrfs_prepare_sprout(struct btrfs_root *root) { struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices; struct btrfs_fs_devices *old_devices; @@@ -1625,6 -1630,7 +1626,6 @@@ int btrfs_init_new_device(struct btrfs_ } filemap_write_and_wait(bdev->bd_inode->i_mapping); - mutex_lock(&root->fs_info->volume_mutex); devices = &root->fs_info->fs_devices->devices; /* @@@ -1690,7 -1696,7 +1691,7 @@@ if (seeding_dev) { sb->s_flags &= ~MS_RDONLY; - ret = btrfs_prepare_sprout(trans, root); + ret = btrfs_prepare_sprout(root); BUG_ON(ret); } @@@ -1752,7 -1758,8 +1753,7 @@@ ret = btrfs_relocate_sys_chunks(root); BUG_ON(ret); } -out: - mutex_unlock(&root->fs_info->volume_mutex); + return ret; error: blkdev_put(bdev, FMODE_EXCL); @@@ -1760,7 -1767,7 +1761,7 @@@ mutex_unlock(&uuid_mutex); up_write(&sb->s_umount); } - goto out; + return ret; } static noinline int btrfs_update_device(struct btrfs_trans_handle *trans, @@@ -2071,362 -2078,6 +2072,362 @@@ error return ret; } +static int insert_balance_item(struct btrfs_root *root, + struct btrfs_balance_control *bctl) +{ + struct btrfs_trans_handle *trans; + struct btrfs_balance_item *item; + struct btrfs_disk_balance_args disk_bargs; + struct btrfs_path *path; + struct extent_buffer *leaf; + struct btrfs_key key; + int ret, err; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + + trans = btrfs_start_transaction(root, 0); + if (IS_ERR(trans)) { + btrfs_free_path(path); + return PTR_ERR(trans); + } + + key.objectid = BTRFS_BALANCE_OBJECTID; + key.type = BTRFS_BALANCE_ITEM_KEY; + key.offset = 0; + + ret = btrfs_insert_empty_item(trans, root, path, &key, + sizeof(*item)); + if (ret) + goto out; + + leaf = path->nodes[0]; + item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_balance_item); + + memset_extent_buffer(leaf, 0, (unsigned long)item, sizeof(*item)); + + btrfs_cpu_balance_args_to_disk(&disk_bargs, &bctl->data); + btrfs_set_balance_data(leaf, item, &disk_bargs); + btrfs_cpu_balance_args_to_disk(&disk_bargs, &bctl->meta); + btrfs_set_balance_meta(leaf, item, &disk_bargs); + btrfs_cpu_balance_args_to_disk(&disk_bargs, &bctl->sys); + btrfs_set_balance_sys(leaf, item, &disk_bargs); + + btrfs_set_balance_flags(leaf, item, bctl->flags); + + btrfs_mark_buffer_dirty(leaf); +out: + btrfs_free_path(path); + err = btrfs_commit_transaction(trans, root); + if (err && !ret) + ret = err; + return ret; +} + +static int del_balance_item(struct btrfs_root *root) +{ + struct btrfs_trans_handle *trans; + struct btrfs_path *path; + struct btrfs_key key; + int ret, err; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + + trans = btrfs_start_transaction(root, 0); + if (IS_ERR(trans)) { + btrfs_free_path(path); + return PTR_ERR(trans); + } + + key.objectid = BTRFS_BALANCE_OBJECTID; + key.type = BTRFS_BALANCE_ITEM_KEY; + key.offset = 0; + + ret = btrfs_search_slot(trans, root, &key, path, -1, 1); + if (ret < 0) + goto out; + if (ret > 0) { + ret = -ENOENT; + goto out; + } + + ret = btrfs_del_item(trans, root, path); +out: + btrfs_free_path(path); + err = btrfs_commit_transaction(trans, root); + if (err && !ret) + ret = err; + return ret; +} + +/* + * This is a heuristic used to reduce the number of chunks balanced on + * resume after balance was interrupted. + */ +static void update_balance_args(struct btrfs_balance_control *bctl) +{ + /* + * Turn on soft mode for chunk types that were being converted. + */ + if (bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) + bctl->data.flags |= BTRFS_BALANCE_ARGS_SOFT; + if (bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) + bctl->sys.flags |= BTRFS_BALANCE_ARGS_SOFT; + if (bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) + bctl->meta.flags |= BTRFS_BALANCE_ARGS_SOFT; + + /* + * Turn on usage filter if is not already used. The idea is + * that chunks that we have already balanced should be + * reasonably full. Don't do it for chunks that are being + * converted - that will keep us from relocating unconverted + * (albeit full) chunks. + */ + if (!(bctl->data.flags & BTRFS_BALANCE_ARGS_USAGE) && + !(bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT)) { + bctl->data.flags |= BTRFS_BALANCE_ARGS_USAGE; + bctl->data.usage = 90; + } + if (!(bctl->sys.flags & BTRFS_BALANCE_ARGS_USAGE) && + !(bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT)) { + bctl->sys.flags |= BTRFS_BALANCE_ARGS_USAGE; + bctl->sys.usage = 90; + } + if (!(bctl->meta.flags & BTRFS_BALANCE_ARGS_USAGE) && + !(bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT)) { + bctl->meta.flags |= BTRFS_BALANCE_ARGS_USAGE; + bctl->meta.usage = 90; + } +} + +/* + * Should be called with both balance and volume mutexes held to + * serialize other volume operations (add_dev/rm_dev/resize) with + * restriper. Same goes for unset_balance_control. + */ +static void set_balance_control(struct btrfs_balance_control *bctl) +{ + struct btrfs_fs_info *fs_info = bctl->fs_info; + + BUG_ON(fs_info->balance_ctl); + + spin_lock(&fs_info->balance_lock); + fs_info->balance_ctl = bctl; + spin_unlock(&fs_info->balance_lock); +} + +static void unset_balance_control(struct btrfs_fs_info *fs_info) +{ + struct btrfs_balance_control *bctl = fs_info->balance_ctl; + + BUG_ON(!fs_info->balance_ctl); + + spin_lock(&fs_info->balance_lock); + fs_info->balance_ctl = NULL; + spin_unlock(&fs_info->balance_lock); + + kfree(bctl); +} + +/* + * Balance filters. Return 1 if chunk should be filtered out + * (should not be balanced). + */ +static int chunk_profiles_filter(u64 chunk_profile, + struct btrfs_balance_args *bargs) +{ + chunk_profile &= BTRFS_BLOCK_GROUP_PROFILE_MASK; + + if (chunk_profile == 0) + chunk_profile = BTRFS_AVAIL_ALLOC_BIT_SINGLE; + + if (bargs->profiles & chunk_profile) + return 0; + + return 1; +} + +static u64 div_factor_fine(u64 num, int factor) +{ + if (factor <= 0) + return 0; + if (factor >= 100) + return num; + + num *= factor; + do_div(num, 100); + return num; +} + +static int chunk_usage_filter(struct btrfs_fs_info *fs_info, u64 chunk_offset, + struct btrfs_balance_args *bargs) +{ + struct btrfs_block_group_cache *cache; + u64 chunk_used, user_thresh; + int ret = 1; + + cache = btrfs_lookup_block_group(fs_info, chunk_offset); + chunk_used = btrfs_block_group_used(&cache->item); + + user_thresh = div_factor_fine(cache->key.offset, bargs->usage); + if (chunk_used < user_thresh) + ret = 0; + + btrfs_put_block_group(cache); + return ret; +} + +static int chunk_devid_filter(struct extent_buffer *leaf, + struct btrfs_chunk *chunk, + struct btrfs_balance_args *bargs) +{ + struct btrfs_stripe *stripe; + int num_stripes = btrfs_chunk_num_stripes(leaf, chunk); + int i; + + for (i = 0; i < num_stripes; i++) { + stripe = btrfs_stripe_nr(chunk, i); + if (btrfs_stripe_devid(leaf, stripe) == bargs->devid) + return 0; + } + + return 1; +} + +/* [pstart, pend) */ +static int chunk_drange_filter(struct extent_buffer *leaf, + struct btrfs_chunk *chunk, + u64 chunk_offset, + struct btrfs_balance_args *bargs) +{ + struct btrfs_stripe *stripe; + int num_stripes = btrfs_chunk_num_stripes(leaf, chunk); + u64 stripe_offset; + u64 stripe_length; + int factor; + int i; + + if (!(bargs->flags & BTRFS_BALANCE_ARGS_DEVID)) + return 0; + + if (btrfs_chunk_type(leaf, chunk) & (BTRFS_BLOCK_GROUP_DUP | + BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID10)) + factor = 2; + else + factor = 1; + factor = num_stripes / factor; + + for (i = 0; i < num_stripes; i++) { + stripe = btrfs_stripe_nr(chunk, i); + if (btrfs_stripe_devid(leaf, stripe) != bargs->devid) + continue; + + stripe_offset = btrfs_stripe_offset(leaf, stripe); + stripe_length = btrfs_chunk_length(leaf, chunk); + do_div(stripe_length, factor); + + if (stripe_offset < bargs->pend && + stripe_offset + stripe_length > bargs->pstart) + return 0; + } + + return 1; +} + +/* [vstart, vend) */ +static int chunk_vrange_filter(struct extent_buffer *leaf, + struct btrfs_chunk *chunk, + u64 chunk_offset, + struct btrfs_balance_args *bargs) +{ + if (chunk_offset < bargs->vend && + chunk_offset + btrfs_chunk_length(leaf, chunk) > bargs->vstart) + /* at least part of the chunk is inside this vrange */ + return 0; + + return 1; +} + +static int chunk_soft_convert_filter(u64 chunk_profile, + struct btrfs_balance_args *bargs) +{ + if (!(bargs->flags & BTRFS_BALANCE_ARGS_CONVERT)) + return 0; + + chunk_profile &= BTRFS_BLOCK_GROUP_PROFILE_MASK; + + if (chunk_profile == 0) + chunk_profile = BTRFS_AVAIL_ALLOC_BIT_SINGLE; + + if (bargs->target & chunk_profile) + return 1; + + return 0; +} + +static int should_balance_chunk(struct btrfs_root *root, + struct extent_buffer *leaf, + struct btrfs_chunk *chunk, u64 chunk_offset) +{ + struct btrfs_balance_control *bctl = root->fs_info->balance_ctl; + struct btrfs_balance_args *bargs = NULL; + u64 chunk_type = btrfs_chunk_type(leaf, chunk); + + /* type filter */ + if (!((chunk_type & BTRFS_BLOCK_GROUP_TYPE_MASK) & + (bctl->flags & BTRFS_BALANCE_TYPE_MASK))) { + return 0; + } + + if (chunk_type & BTRFS_BLOCK_GROUP_DATA) + bargs = &bctl->data; + else if (chunk_type & BTRFS_BLOCK_GROUP_SYSTEM) + bargs = &bctl->sys; + else if (chunk_type & BTRFS_BLOCK_GROUP_METADATA) + bargs = &bctl->meta; + + /* profiles filter */ + if ((bargs->flags & BTRFS_BALANCE_ARGS_PROFILES) && + chunk_profiles_filter(chunk_type, bargs)) { + return 0; + } + + /* usage filter */ + if ((bargs->flags & BTRFS_BALANCE_ARGS_USAGE) && + chunk_usage_filter(bctl->fs_info, chunk_offset, bargs)) { + return 0; + } + + /* devid filter */ + if ((bargs->flags & BTRFS_BALANCE_ARGS_DEVID) && + chunk_devid_filter(leaf, chunk, bargs)) { + return 0; + } + + /* drange filter, makes sense only with devid filter */ + if ((bargs->flags & BTRFS_BALANCE_ARGS_DRANGE) && + chunk_drange_filter(leaf, chunk, chunk_offset, bargs)) { + return 0; + } + + /* vrange filter */ + if ((bargs->flags & BTRFS_BALANCE_ARGS_VRANGE) && + chunk_vrange_filter(leaf, chunk, chunk_offset, bargs)) { + return 0; + } + + /* soft profile changing mode */ + if ((bargs->flags & BTRFS_BALANCE_ARGS_SOFT) && + chunk_soft_convert_filter(chunk_type, bargs)) { + return 0; + } + + return 1; +} + static u64 div_factor(u64 num, int factor) { if (factor == 10) @@@ -2436,28 -2087,29 +2437,28 @@@ return num; } -int btrfs_balance(struct btrfs_root *dev_root) +static int __btrfs_balance(struct btrfs_fs_info *fs_info) { - int ret; - struct list_head *devices = &dev_root->fs_info->fs_devices->devices; + struct btrfs_balance_control *bctl = fs_info->balance_ctl; + struct btrfs_root *chunk_root = fs_info->chunk_root; + struct btrfs_root *dev_root = fs_info->dev_root; + struct list_head *devices; struct btrfs_device *device; u64 old_size; u64 size_to_free; + struct btrfs_chunk *chunk; struct btrfs_path *path; struct btrfs_key key; - struct btrfs_root *chunk_root = dev_root->fs_info->chunk_root; - struct btrfs_trans_handle *trans; struct btrfs_key found_key; - - if (dev_root->fs_info->sb->s_flags & MS_RDONLY) - return -EROFS; - - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - - mutex_lock(&dev_root->fs_info->volume_mutex); - dev_root = dev_root->fs_info->dev_root; + struct btrfs_trans_handle *trans; + struct extent_buffer *leaf; + int slot; + int ret; + int enospc_errors = 0; + bool counting = true; /* step one make some room on all the devices */ + devices = &fs_info->fs_devices->devices; list_for_each_entry(device, devices, dev_list) { old_size = device->total_bytes; size_to_free = div_factor(old_size, 1); @@@ -2486,23 -2138,11 +2487,23 @@@ ret = -ENOMEM; goto error; } + + /* zero out stat counters */ + spin_lock(&fs_info->balance_lock); + memset(&bctl->stat, 0, sizeof(bctl->stat)); + spin_unlock(&fs_info->balance_lock); +again: key.objectid = BTRFS_FIRST_CHUNK_TREE_OBJECTID; key.offset = (u64)-1; key.type = BTRFS_CHUNK_ITEM_KEY; while (1) { + if ((!counting && atomic_read(&fs_info->balance_pause_req)) || + atomic_read(&fs_info->balance_cancel_req)) { + ret = -ECANCELED; + goto error; + } + ret = btrfs_search_slot(NULL, chunk_root, &key, path, 0, 0); if (ret < 0) goto error; @@@ -2512,19 -2152,15 +2513,19 @@@ * failed */ if (ret == 0) - break; + BUG(); /* FIXME break ? */ ret = btrfs_previous_item(chunk_root, path, 0, BTRFS_CHUNK_ITEM_KEY); - if (ret) + if (ret) { + ret = 0; break; + } + + leaf = path->nodes[0]; + slot = path->slots[0]; + btrfs_item_key_to_cpu(leaf, &found_key, slot); - btrfs_item_key_to_cpu(path->nodes[0], &found_key, - path->slots[0]); if (found_key.objectid != key.objectid) break; @@@ -2532,375 -2168,22 +2533,375 @@@ if (found_key.offset == 0) break; + chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk); + + if (!counting) { + spin_lock(&fs_info->balance_lock); + bctl->stat.considered++; + spin_unlock(&fs_info->balance_lock); + } + + ret = should_balance_chunk(chunk_root, leaf, chunk, + found_key.offset); btrfs_release_path(path); + if (!ret) + goto loop; + + if (counting) { + spin_lock(&fs_info->balance_lock); + bctl->stat.expected++; + spin_unlock(&fs_info->balance_lock); + goto loop; + } + ret = btrfs_relocate_chunk(chunk_root, chunk_root->root_key.objectid, found_key.objectid, found_key.offset); if (ret && ret != -ENOSPC) goto error; + if (ret == -ENOSPC) { + enospc_errors++; + } else { + spin_lock(&fs_info->balance_lock); + bctl->stat.completed++; + spin_unlock(&fs_info->balance_lock); + } +loop: key.offset = found_key.offset - 1; } - ret = 0; + + if (counting) { + btrfs_release_path(path); + counting = false; + goto again; + } error: btrfs_free_path(path); - mutex_unlock(&dev_root->fs_info->volume_mutex); + if (enospc_errors) { + printk(KERN_INFO "btrfs: %d enospc errors during balance\n", + enospc_errors); + if (!ret) + ret = -ENOSPC; + } + + return ret; +} + +static inline int balance_need_close(struct btrfs_fs_info *fs_info) +{ + /* cancel requested || normal exit path */ + return atomic_read(&fs_info->balance_cancel_req) || + (atomic_read(&fs_info->balance_pause_req) == 0 && + atomic_read(&fs_info->balance_cancel_req) == 0); +} + +static void __cancel_balance(struct btrfs_fs_info *fs_info) +{ + int ret; + + unset_balance_control(fs_info); + ret = del_balance_item(fs_info->tree_root); + BUG_ON(ret); +} + +void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, int lock, + struct btrfs_ioctl_balance_args *bargs); + +/* + * Should be called with both balance and volume mutexes held + */ +int btrfs_balance(struct btrfs_balance_control *bctl, + struct btrfs_ioctl_balance_args *bargs) +{ + struct btrfs_fs_info *fs_info = bctl->fs_info; + u64 allowed; + int ret; + + if (btrfs_fs_closing(fs_info) || + atomic_read(&fs_info->balance_pause_req) || + atomic_read(&fs_info->balance_cancel_req)) { + ret = -EINVAL; + goto out; + } + + /* + * In case of mixed groups both data and meta should be picked, + * and identical options should be given for both of them. + */ + allowed = btrfs_super_incompat_flags(fs_info->super_copy); + if ((allowed & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) && + (bctl->flags & (BTRFS_BALANCE_DATA | BTRFS_BALANCE_METADATA))) { + if (!(bctl->flags & BTRFS_BALANCE_DATA) || + !(bctl->flags & BTRFS_BALANCE_METADATA) || + memcmp(&bctl->data, &bctl->meta, sizeof(bctl->data))) { + printk(KERN_ERR "btrfs: with mixed groups data and " + "metadata balance options must be the same\n"); + ret = -EINVAL; + goto out; + } + } + + /* + * Profile changing sanity checks. Skip them if a simple + * balance is requested. + */ + if (!((bctl->data.flags | bctl->sys.flags | bctl->meta.flags) & + BTRFS_BALANCE_ARGS_CONVERT)) + goto do_balance; + + allowed = BTRFS_AVAIL_ALLOC_BIT_SINGLE; + if (fs_info->fs_devices->num_devices == 1) + allowed |= BTRFS_BLOCK_GROUP_DUP; + else if (fs_info->fs_devices->num_devices < 4) + allowed |= (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID1); + else + allowed |= (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID1 | + BTRFS_BLOCK_GROUP_RAID10); + + if (!profile_is_valid(bctl->data.target, 1) || + bctl->data.target & ~allowed) { + printk(KERN_ERR "btrfs: unable to start balance with target " + "data profile %llu\n", + (unsigned long long)bctl->data.target); + ret = -EINVAL; + goto out; + } + if (!profile_is_valid(bctl->meta.target, 1) || + bctl->meta.target & ~allowed) { + printk(KERN_ERR "btrfs: unable to start balance with target " + "metadata profile %llu\n", + (unsigned long long)bctl->meta.target); + ret = -EINVAL; + goto out; + } + if (!profile_is_valid(bctl->sys.target, 1) || + bctl->sys.target & ~allowed) { + printk(KERN_ERR "btrfs: unable to start balance with target " + "system profile %llu\n", + (unsigned long long)bctl->sys.target); + ret = -EINVAL; + goto out; + } + + if (bctl->data.target & BTRFS_BLOCK_GROUP_DUP) { + printk(KERN_ERR "btrfs: dup for data is not allowed\n"); + ret = -EINVAL; + goto out; + } + + /* allow to reduce meta or sys integrity only if force set */ + allowed = BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1 | + BTRFS_BLOCK_GROUP_RAID10; + if (((bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) && + (fs_info->avail_system_alloc_bits & allowed) && + !(bctl->sys.target & allowed)) || + ((bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) && + (fs_info->avail_metadata_alloc_bits & allowed) && + !(bctl->meta.target & allowed))) { + if (bctl->flags & BTRFS_BALANCE_FORCE) { + printk(KERN_INFO "btrfs: force reducing metadata " + "integrity\n"); + } else { + printk(KERN_ERR "btrfs: balance will reduce metadata " + "integrity, use force if you want this\n"); + ret = -EINVAL; + goto out; + } + } + +do_balance: + ret = insert_balance_item(fs_info->tree_root, bctl); + if (ret && ret != -EEXIST) + goto out; + + if (!(bctl->flags & BTRFS_BALANCE_RESUME)) { + BUG_ON(ret == -EEXIST); + set_balance_control(bctl); + } else { + BUG_ON(ret != -EEXIST); + spin_lock(&fs_info->balance_lock); + update_balance_args(bctl); + spin_unlock(&fs_info->balance_lock); + } + + atomic_inc(&fs_info->balance_running); + mutex_unlock(&fs_info->balance_mutex); + + ret = __btrfs_balance(fs_info); + + mutex_lock(&fs_info->balance_mutex); + atomic_dec(&fs_info->balance_running); + + if (bargs) { + memset(bargs, 0, sizeof(*bargs)); + update_ioctl_balance_args(fs_info, 0, bargs); + } + + if ((ret && ret != -ECANCELED && ret != -ENOSPC) || + balance_need_close(fs_info)) { + __cancel_balance(fs_info); + } + + wake_up(&fs_info->balance_wait_q); + + return ret; +out: + if (bctl->flags & BTRFS_BALANCE_RESUME) + __cancel_balance(fs_info); + else + kfree(bctl); + return ret; +} + +static int balance_kthread(void *data) +{ + struct btrfs_balance_control *bctl = + (struct btrfs_balance_control *)data; + struct btrfs_fs_info *fs_info = bctl->fs_info; + int ret = 0; + + mutex_lock(&fs_info->volume_mutex); + mutex_lock(&fs_info->balance_mutex); + + set_balance_control(bctl); + + if (btrfs_test_opt(fs_info->tree_root, SKIP_BALANCE)) { + printk(KERN_INFO "btrfs: force skipping balance\n"); + } else { + printk(KERN_INFO "btrfs: continuing balance\n"); + ret = btrfs_balance(bctl, NULL); + } + + mutex_unlock(&fs_info->balance_mutex); + mutex_unlock(&fs_info->volume_mutex); + return ret; +} + +int btrfs_recover_balance(struct btrfs_root *tree_root) +{ + struct task_struct *tsk; + struct btrfs_balance_control *bctl; + struct btrfs_balance_item *item; + struct btrfs_disk_balance_args disk_bargs; + struct btrfs_path *path; + struct extent_buffer *leaf; + struct btrfs_key key; + int ret; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + + bctl = kzalloc(sizeof(*bctl), GFP_NOFS); + if (!bctl) { + ret = -ENOMEM; + goto out; + } + + key.objectid = BTRFS_BALANCE_OBJECTID; + key.type = BTRFS_BALANCE_ITEM_KEY; + key.offset = 0; + + ret = btrfs_search_slot(NULL, tree_root, &key, path, 0, 0); + if (ret < 0) + goto out_bctl; + if (ret > 0) { /* ret = -ENOENT; */ + ret = 0; + goto out_bctl; + } + + leaf = path->nodes[0]; + item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_balance_item); + + bctl->fs_info = tree_root->fs_info; + bctl->flags = btrfs_balance_flags(leaf, item) | BTRFS_BALANCE_RESUME; + + btrfs_balance_data(leaf, item, &disk_bargs); + btrfs_disk_balance_args_to_cpu(&bctl->data, &disk_bargs); + btrfs_balance_meta(leaf, item, &disk_bargs); + btrfs_disk_balance_args_to_cpu(&bctl->meta, &disk_bargs); + btrfs_balance_sys(leaf, item, &disk_bargs); + btrfs_disk_balance_args_to_cpu(&bctl->sys, &disk_bargs); + + tsk = kthread_run(balance_kthread, bctl, "btrfs-balance"); + if (IS_ERR(tsk)) + ret = PTR_ERR(tsk); + else + goto out; + +out_bctl: + kfree(bctl); +out: + btrfs_free_path(path); return ret; } +int btrfs_pause_balance(struct btrfs_fs_info *fs_info) +{ + int ret = 0; + + mutex_lock(&fs_info->balance_mutex); + if (!fs_info->balance_ctl) { + mutex_unlock(&fs_info->balance_mutex); + return -ENOTCONN; + } + + if (atomic_read(&fs_info->balance_running)) { + atomic_inc(&fs_info->balance_pause_req); + mutex_unlock(&fs_info->balance_mutex); + + wait_event(fs_info->balance_wait_q, + atomic_read(&fs_info->balance_running) == 0); + + mutex_lock(&fs_info->balance_mutex); + /* we are good with balance_ctl ripped off from under us */ + BUG_ON(atomic_read(&fs_info->balance_running)); + atomic_dec(&fs_info->balance_pause_req); + } else { + ret = -ENOTCONN; + } + + mutex_unlock(&fs_info->balance_mutex); + return ret; +} + +int btrfs_cancel_balance(struct btrfs_fs_info *fs_info) +{ + mutex_lock(&fs_info->balance_mutex); + if (!fs_info->balance_ctl) { + mutex_unlock(&fs_info->balance_mutex); + return -ENOTCONN; + } + + atomic_inc(&fs_info->balance_cancel_req); + /* + * if we are running just wait and return, balance item is + * deleted in btrfs_balance in this case + */ + if (atomic_read(&fs_info->balance_running)) { + mutex_unlock(&fs_info->balance_mutex); + wait_event(fs_info->balance_wait_q, + atomic_read(&fs_info->balance_running) == 0); + mutex_lock(&fs_info->balance_mutex); + } else { + /* __cancel_balance needs volume_mutex */ + mutex_unlock(&fs_info->balance_mutex); + mutex_lock(&fs_info->volume_mutex); + mutex_lock(&fs_info->balance_mutex); + + if (fs_info->balance_ctl) + __cancel_balance(fs_info); + + mutex_unlock(&fs_info->volume_mutex); + } + + BUG_ON(fs_info->balance_ctl || atomic_read(&fs_info->balance_running)); + atomic_dec(&fs_info->balance_cancel_req); + mutex_unlock(&fs_info->balance_mutex); + return 0; +} + /* * shrinking a device means finding all of the device extents past * the new size, and then following the back refs to the chunks. @@@ -3041,7 -2324,8 +3042,7 @@@ done return ret; } -static int btrfs_add_system_chunk(struct btrfs_trans_handle *trans, - struct btrfs_root *root, +static int btrfs_add_system_chunk(struct btrfs_root *root, struct btrfs_key *key, struct btrfs_chunk *chunk, int item_size) { @@@ -3158,11 -2442,7 +3159,11 @@@ static int __btrfs_alloc_chunk(struct b max_stripe_size = 1024 * 1024 * 1024; max_chunk_size = 10 * max_stripe_size; } else if (type & BTRFS_BLOCK_GROUP_METADATA) { - max_stripe_size = 256 * 1024 * 1024; + /* for larger filesystems, use larger metadata chunks */ + if (fs_devices->total_rw_bytes > 50ULL * 1024 * 1024 * 1024) + max_stripe_size = 1024 * 1024 * 1024; + else + max_stripe_size = 256 * 1024 * 1024; max_chunk_size = max_stripe_size; } else if (type & BTRFS_BLOCK_GROUP_SYSTEM) { max_stripe_size = 8 * 1024 * 1024; @@@ -3217,7 -2497,7 +3218,7 @@@ if (total_avail == 0) continue; - ret = find_free_dev_extent(trans, device, + ret = find_free_dev_extent(device, max_stripe_size * dev_stripes, &dev_offset, &max_avail); if (ret && ret != -ENOSPC) @@@ -3408,7 -2688,7 +3409,7 @@@ static int __finish_chunk_alloc(struct BUG_ON(ret); if (map->type & BTRFS_BLOCK_GROUP_SYSTEM) { - ret = btrfs_add_system_chunk(trans, chunk_root, &key, chunk, + ret = btrfs_add_system_chunk(chunk_root, &key, chunk, item_size); BUG_ON(ret); } @@@ -3473,7 -2753,8 +3474,7 @@@ static noinline int init_first_rw_devic return ret; alloc_profile = BTRFS_BLOCK_GROUP_METADATA | - (fs_info->metadata_alloc_profile & - fs_info->avail_metadata_alloc_bits); + fs_info->avail_metadata_alloc_bits; alloc_profile = btrfs_reduce_alloc_profile(root, alloc_profile); ret = __btrfs_alloc_chunk(trans, extent_root, &map, &chunk_size, @@@ -3483,7 -2764,8 +3484,7 @@@ sys_chunk_offset = chunk_offset + chunk_size; alloc_profile = BTRFS_BLOCK_GROUP_SYSTEM | - (fs_info->system_alloc_profile & - fs_info->avail_system_alloc_bits); + fs_info->avail_system_alloc_bits; alloc_profile = btrfs_reduce_alloc_profile(root, alloc_profile); ret = __btrfs_alloc_chunk(trans, extent_root, &sys_map, @@@ -3620,13 -2902,26 +3621,13 @@@ static int __btrfs_map_block(struct btr u64 stripe_nr; u64 stripe_nr_orig; u64 stripe_nr_end; - int stripes_allocated = 8; - int stripes_required = 1; int stripe_index; int i; + int ret = 0; int num_stripes; int max_errors = 0; struct btrfs_bio *bbio = NULL; - if (bbio_ret && !(rw & (REQ_WRITE | REQ_DISCARD))) - stripes_allocated = 1; -again: - if (bbio_ret) { - bbio = kzalloc(btrfs_bio_size(stripes_allocated), - GFP_NOFS); - if (!bbio) - return -ENOMEM; - - atomic_set(&bbio->error, 0); - } - read_lock(&em_tree->lock); em = lookup_extent_mapping(em_tree, logical, *length); read_unlock(&em_tree->lock); @@@ -3645,6 -2940,32 +3646,6 @@@ if (mirror_num > map->num_stripes) mirror_num = 0; - /* if our btrfs_bio struct is too small, back off and try again */ - if (rw & REQ_WRITE) { - if (map->type & (BTRFS_BLOCK_GROUP_RAID1 | - BTRFS_BLOCK_GROUP_DUP)) { - stripes_required = map->num_stripes; - max_errors = 1; - } else if (map->type & BTRFS_BLOCK_GROUP_RAID10) { - stripes_required = map->sub_stripes; - max_errors = 1; - } - } - if (rw & REQ_DISCARD) { - if (map->type & (BTRFS_BLOCK_GROUP_RAID0 | - BTRFS_BLOCK_GROUP_RAID1 | - BTRFS_BLOCK_GROUP_DUP | - BTRFS_BLOCK_GROUP_RAID10)) { - stripes_required = map->num_stripes; - } - } - if (bbio_ret && (rw & (REQ_WRITE | REQ_DISCARD)) && - stripes_allocated < stripes_required) { - stripes_allocated = map->num_stripes; - free_extent_map(em); - kfree(bbio); - goto again; - } stripe_nr = offset; /* * stripe_nr counts the total number of stripes we have to stride @@@ -3660,7 -2981,10 +3661,7 @@@ if (rw & REQ_DISCARD) *length = min_t(u64, em->len - offset, *length); - else if (map->type & (BTRFS_BLOCK_GROUP_RAID0 | - BTRFS_BLOCK_GROUP_RAID1 | - BTRFS_BLOCK_GROUP_RAID10 | - BTRFS_BLOCK_GROUP_DUP)) { + else if (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) { /* we limit the length of each bio to what fits in a stripe */ *length = min_t(u64, em->len - offset, map->stripe_len - stripe_offset); @@@ -3736,55 -3060,81 +3737,55 @@@ } BUG_ON(stripe_index >= map->num_stripes); + bbio = kzalloc(btrfs_bio_size(num_stripes), GFP_NOFS); + if (!bbio) { + ret = -ENOMEM; + goto out; + } + atomic_set(&bbio->error, 0); + if (rw & REQ_DISCARD) { + int factor = 0; + int sub_stripes = 0; + u64 stripes_per_dev = 0; + u32 remaining_stripes = 0; + + if (map->type & + (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID10)) { + if (map->type & BTRFS_BLOCK_GROUP_RAID0) + sub_stripes = 1; + else + sub_stripes = map->sub_stripes; + + factor = map->num_stripes / sub_stripes; + stripes_per_dev = div_u64_rem(stripe_nr_end - + stripe_nr_orig, + factor, + &remaining_stripes); + } + for (i = 0; i < num_stripes; i++) { bbio->stripes[i].physical = map->stripes[stripe_index].physical + stripe_offset + stripe_nr * map->stripe_len; bbio->stripes[i].dev = map->stripes[stripe_index].dev; - if (map->type & BTRFS_BLOCK_GROUP_RAID0) { - u64 stripes; - u32 last_stripe = 0; - int j; - - div_u64_rem(stripe_nr_end - 1, - map->num_stripes, - &last_stripe); - - for (j = 0; j < map->num_stripes; j++) { - u32 test; - - div_u64_rem(stripe_nr_end - 1 - j, - map->num_stripes, &test); - if (test == stripe_index) - break; - } - stripes = stripe_nr_end - 1 - j; - do_div(stripes, map->num_stripes); - bbio->stripes[i].length = map->stripe_len * - (stripes - stripe_nr + 1); - - if (i == 0) { - bbio->stripes[i].length -= - stripe_offset; - stripe_offset = 0; - } - if (stripe_index == last_stripe) - bbio->stripes[i].length -= - stripe_end_offset; - } else if (map->type & BTRFS_BLOCK_GROUP_RAID10) { - u64 stripes; - int j; - int factor = map->num_stripes / - map->sub_stripes; - u32 last_stripe = 0; - - div_u64_rem(stripe_nr_end - 1, - factor, &last_stripe); - last_stripe *= map->sub_stripes; - - for (j = 0; j < factor; j++) { - u32 test; - - div_u64_rem(stripe_nr_end - 1 - j, - factor, &test); - - if (test == - stripe_index / map->sub_stripes) - break; - } - stripes = stripe_nr_end - 1 - j; - do_div(stripes, factor); - bbio->stripes[i].length = map->stripe_len * - (stripes - stripe_nr + 1); - - if (i < map->sub_stripes) { + if (map->type & (BTRFS_BLOCK_GROUP_RAID0 | + BTRFS_BLOCK_GROUP_RAID10)) { + bbio->stripes[i].length = stripes_per_dev * + map->stripe_len; + if (i / sub_stripes < remaining_stripes) + bbio->stripes[i].length += + map->stripe_len; + if (i < sub_stripes) bbio->stripes[i].length -= stripe_offset; - if (i == map->sub_stripes - 1) - stripe_offset = 0; - } - if (stripe_index >= last_stripe && - stripe_index <= (last_stripe + - map->sub_stripes - 1)) { + if ((i / sub_stripes + 1) % + sub_stripes == remaining_stripes) bbio->stripes[i].length -= stripe_end_offset; - } + if (i == sub_stripes - 1) + stripe_offset = 0; } else bbio->stripes[i].length = *length; @@@ -3806,22 -3156,15 +3807,22 @@@ stripe_index++; } } - if (bbio_ret) { - *bbio_ret = bbio; - bbio->num_stripes = num_stripes; - bbio->max_errors = max_errors; - bbio->mirror_num = mirror_num; + + if (rw & REQ_WRITE) { + if (map->type & (BTRFS_BLOCK_GROUP_RAID1 | + BTRFS_BLOCK_GROUP_RAID10 | + BTRFS_BLOCK_GROUP_DUP)) { + max_errors = 1; + } } + + *bbio_ret = bbio; + bbio->num_stripes = num_stripes; + bbio->max_errors = max_errors; + bbio->mirror_num = mirror_num; out: free_extent_map(em); - return 0; + return ret; } int btrfs_map_block(struct btrfs_mapping_tree *map_tree, int rw, @@@ -3962,7 -3305,7 +3963,7 @@@ static noinline int schedule_bio(struc /* don't bother with additional async steps for reads, right now */ if (!(rw & REQ_WRITE)) { bio_get(bio); - submit_bio(rw, bio); + btrfsic_submit_bio(rw, bio); bio_put(bio); return 0; } @@@ -4057,7 -3400,7 +4058,7 @@@ int btrfs_map_bio(struct btrfs_root *ro if (async_submit) schedule_bio(root, dev, rw, bio); else - submit_bio(rw, bio); + btrfsic_submit_bio(rw, bio); } else { bio->bi_bdev = root->fs_info->fs_devices->latest_bdev; bio->bi_sector = logical >> 9; @@@ -4226,7 -3569,7 +4227,7 @@@ static int open_seed_devices(struct btr struct btrfs_fs_devices *fs_devices; int ret; - mutex_lock(&uuid_mutex); + BUG_ON(!mutex_is_locked(&uuid_mutex)); fs_devices = root->fs_info->fs_devices->seed; while (fs_devices) { @@@ -4264,6 -3607,7 +4265,6 @@@ fs_devices->seed = root->fs_info->fs_devices->seed; root->fs_info->fs_devices->seed = fs_devices; out: - mutex_unlock(&uuid_mutex); return ret; } @@@ -4406,9 -3750,6 +4407,9 @@@ int btrfs_read_chunk_tree(struct btrfs_ if (!path) return -ENOMEM; + mutex_lock(&uuid_mutex); + lock_chunks(root); + /* first we search for all of the device items, and then we * read in all of the chunk items. This way we can create chunk * mappings that reference all of the devices that are afound @@@ -4459,9 -3800,6 +4460,9 @@@ again } ret = 0; error: + unlock_chunks(root); + mutex_unlock(&uuid_mutex); + btrfs_free_path(path); return ret; }