diff options
Diffstat (limited to 'fs/btrfs/disk-io.c')
| -rw-r--r-- | fs/btrfs/disk-io.c | 3633 |
1 files changed, 2607 insertions, 1026 deletions
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index fb827d0d718..08e65e9cf2a 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -26,11 +26,15 @@ #include <linux/workqueue.h> #include <linux/kthread.h> #include <linux/freezer.h> -#include <linux/crc32c.h> #include <linux/slab.h> -#include "compat.h" +#include <linux/migrate.h> +#include <linux/ratelimit.h> +#include <linux/uuid.h> +#include <linux/semaphore.h> +#include <asm/unaligned.h> #include "ctree.h" #include "disk-io.h" +#include "hash.h" #include "transaction.h" #include "btrfs_inode.h" #include "volumes.h" @@ -39,10 +43,36 @@ #include "locking.h" #include "tree-log.h" #include "free-space-cache.h" +#include "inode-map.h" +#include "check-integrity.h" +#include "rcu-string.h" +#include "dev-replace.h" +#include "raid56.h" +#include "sysfs.h" +#include "qgroup.h" + +#ifdef CONFIG_X86 +#include <asm/cpufeature.h> +#endif static struct extent_io_ops btree_extent_io_ops; static void end_workqueue_fn(struct btrfs_work *work); static void free_fs_root(struct btrfs_root *root); +static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info, + int read_only); +static void btrfs_destroy_ordered_operations(struct btrfs_transaction *t, + struct btrfs_root *root); +static void btrfs_destroy_ordered_extents(struct btrfs_root *root); +static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, + struct btrfs_root *root); +static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root); +static int btrfs_destroy_marked_extents(struct btrfs_root *root, + struct extent_io_tree *dirty_pages, + int mark); +static int btrfs_destroy_pinned_extent(struct btrfs_root *root, + struct extent_io_tree *pinned_extents); +static int btrfs_cleanup_transaction(struct btrfs_root *root); +static void btrfs_error_commit_super(struct btrfs_root *root); /* * end_io_wq structs are used to do processing in task context when an IO is @@ -80,40 +110,87 @@ struct async_submit_bio { */ u64 bio_offset; struct btrfs_work work; + int error; }; -/* These are used to set the lockdep class on the extent buffer locks. - * The class is set by the readpage_end_io_hook after the buffer has - * passed csum validation but before the pages are unlocked. +/* + * Lockdep class keys for extent_buffer->lock's in this root. For a given + * eb, the lockdep key is determined by the btrfs_root it belongs to and + * the level the eb occupies in the tree. * - * The lockdep class is also set by btrfs_init_new_buffer on freshly - * allocated blocks. + * Different roots are used for different purposes and may nest inside each + * other and they require separate keysets. As lockdep keys should be + * static, assign keysets according to the purpose of the root as indicated + * by btrfs_root->objectid. This ensures that all special purpose roots + * have separate keysets. * - * The class is based on the level in the tree block, which allows lockdep - * to know that lower nodes nest inside the locks of higher nodes. + * Lock-nesting across peer nodes is always done with the immediate parent + * node locked thus preventing deadlock. As lockdep doesn't know this, use + * subclass to avoid triggering lockdep warning in such cases. * - * We also add a check to make sure the highest level of the tree is - * the same as our lockdep setup here. If BTRFS_MAX_LEVEL changes, this - * code needs update as well. + * The key is set by the readpage_end_io_hook after the buffer has passed + * csum validation but before the pages are unlocked. It is also set by + * btrfs_init_new_buffer on freshly allocated blocks. + * + * We also add a check to make sure the highest level of the tree is the + * same as our lockdep setup here. If BTRFS_MAX_LEVEL changes, this code + * needs update as well. */ #ifdef CONFIG_DEBUG_LOCK_ALLOC # if BTRFS_MAX_LEVEL != 8 # error # endif -static struct lock_class_key btrfs_eb_class[BTRFS_MAX_LEVEL + 1]; -static const char *btrfs_eb_name[BTRFS_MAX_LEVEL + 1] = { - /* leaf */ - "btrfs-extent-00", - "btrfs-extent-01", - "btrfs-extent-02", - "btrfs-extent-03", - "btrfs-extent-04", - "btrfs-extent-05", - "btrfs-extent-06", - "btrfs-extent-07", - /* highest possible level */ - "btrfs-extent-08", + +static struct btrfs_lockdep_keyset { + u64 id; /* root objectid */ + const char *name_stem; /* lock name stem */ + char names[BTRFS_MAX_LEVEL + 1][20]; + struct lock_class_key keys[BTRFS_MAX_LEVEL + 1]; +} btrfs_lockdep_keysets[] = { + { .id = BTRFS_ROOT_TREE_OBJECTID, .name_stem = "root" }, + { .id = BTRFS_EXTENT_TREE_OBJECTID, .name_stem = "extent" }, + { .id = BTRFS_CHUNK_TREE_OBJECTID, .name_stem = "chunk" }, + { .id = BTRFS_DEV_TREE_OBJECTID, .name_stem = "dev" }, + { .id = BTRFS_FS_TREE_OBJECTID, .name_stem = "fs" }, + { .id = BTRFS_CSUM_TREE_OBJECTID, .name_stem = "csum" }, + { .id = BTRFS_QUOTA_TREE_OBJECTID, .name_stem = "quota" }, + { .id = BTRFS_TREE_LOG_OBJECTID, .name_stem = "log" }, + { .id = BTRFS_TREE_RELOC_OBJECTID, .name_stem = "treloc" }, + { .id = BTRFS_DATA_RELOC_TREE_OBJECTID, .name_stem = "dreloc" }, + { .id = BTRFS_UUID_TREE_OBJECTID, .name_stem = "uuid" }, + { .id = 0, .name_stem = "tree" }, }; + +void __init btrfs_init_lockdep(void) +{ + int i, j; + + /* initialize lockdep class names */ + for (i = 0; i < ARRAY_SIZE(btrfs_lockdep_keysets); i++) { + struct btrfs_lockdep_keyset *ks = &btrfs_lockdep_keysets[i]; + + for (j = 0; j < ARRAY_SIZE(ks->names); j++) + snprintf(ks->names[j], sizeof(ks->names[j]), + "btrfs-%s-%02d", ks->name_stem, j); + } +} + +void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb, + int level) +{ + struct btrfs_lockdep_keyset *ks; + + BUG_ON(level >= ARRAY_SIZE(ks->keys)); + + /* find the matching keyset, id 0 is the default entry */ + for (ks = btrfs_lockdep_keysets; ks->id; ks++) + if (ks->id == objectid) + break; + + lockdep_set_class_and_name(&eb->lock, + &ks->keys[level], ks->names[level]); +} + #endif /* @@ -121,7 +198,7 @@ static const char *btrfs_eb_name[BTRFS_MAX_LEVEL + 1] = { * that covers the entire device */ static struct extent_map *btree_get_extent(struct inode *inode, - struct page *page, size_t page_offset, u64 start, u64 len, + struct page *page, size_t pg_offset, u64 start, u64 len, int create) { struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree; @@ -138,7 +215,7 @@ static struct extent_map *btree_get_extent(struct inode *inode, } read_unlock(&em_tree->lock); - em = alloc_extent_map(GFP_NOFS); + em = alloc_extent_map(); if (!em) { em = ERR_PTR(-ENOMEM); goto out; @@ -150,40 +227,30 @@ static struct extent_map *btree_get_extent(struct inode *inode, em->bdev = BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev; write_lock(&em_tree->lock); - ret = add_extent_mapping(em_tree, em); + ret = add_extent_mapping(em_tree, em, 0); if (ret == -EEXIST) { - u64 failed_start = em->start; - u64 failed_len = em->len; - free_extent_map(em); em = lookup_extent_mapping(em_tree, start, len); - if (em) { - ret = 0; - } else { - em = lookup_extent_mapping(em_tree, failed_start, - failed_len); - ret = -EIO; - } + if (!em) + em = ERR_PTR(-EIO); } else if (ret) { free_extent_map(em); - em = NULL; + em = ERR_PTR(ret); } write_unlock(&em_tree->lock); - if (ret) - em = ERR_PTR(ret); out: return em; } -u32 btrfs_csum_data(struct btrfs_root *root, char *data, u32 seed, size_t len) +u32 btrfs_csum_data(char *data, u32 seed, size_t len) { - return crc32c(seed, data, len); + return btrfs_crc32c(seed, data, len); } void btrfs_csum_final(u32 crc, char *result) { - *(__le32 *)result = ~cpu_to_le32(crc); + put_unaligned_le32(~crc, result); } /* @@ -193,13 +260,11 @@ void btrfs_csum_final(u32 crc, char *result) 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; unsigned long offset = BTRFS_CSUM_SIZE; - char *map_token = NULL; char *kaddr; unsigned long map_start; unsigned long map_len; @@ -210,16 +275,14 @@ static int csum_tree_block(struct btrfs_root *root, struct extent_buffer *buf, len = buf->len - offset; while (len > 0) { err = map_private_extent_buffer(buf, offset, 32, - &map_token, &kaddr, - &map_start, &map_len, KM_USER0); + &kaddr, &map_start, &map_len); if (err) return 1; cur_len = min(len, map_len - (offset - map_start)); - crc = btrfs_csum_data(root, kaddr + offset - map_start, + crc = btrfs_csum_data(kaddr + offset - map_start, crc, cur_len); len -= cur_len; offset += cur_len; - unmap_extent_buffer(buf, map_token, KM_USER0); } if (csum_size > sizeof(inline_result)) { result = kzalloc(csum_size * sizeof(char), GFP_NOFS); @@ -238,14 +301,11 @@ static int csum_tree_block(struct btrfs_root *root, struct extent_buffer *buf, memcpy(&found, result, csum_size); read_extent_buffer(buf, &val, 0, csum_size); - if (printk_ratelimit()) { - printk(KERN_INFO "btrfs: %s checksum verify " - "failed on %llu wanted %X found %X " - "level %d\n", - root->fs_info->sb->s_id, - (unsigned long long)buf->start, val, found, - btrfs_header_level(buf)); - } + printk_ratelimited(KERN_INFO + "BTRFS: %s checksum verify failed on %llu wanted %X found %X " + "level %d\n", + root->fs_info->sb->s_id, buf->start, + val, found, btrfs_header_level(buf)); if (result != (char *)&inline_result) kfree(result); return 1; @@ -265,33 +325,96 @@ static int csum_tree_block(struct btrfs_root *root, struct extent_buffer *buf, * in the wrong place. */ static int verify_parent_transid(struct extent_io_tree *io_tree, - struct extent_buffer *eb, u64 parent_transid) + struct extent_buffer *eb, u64 parent_transid, + int atomic) { struct extent_state *cached_state = NULL; int ret; + bool need_lock = (current->journal_info == + (void *)BTRFS_SEND_TRANS_STUB); if (!parent_transid || btrfs_header_generation(eb) == parent_transid) return 0; + if (atomic) + return -EAGAIN; + + if (need_lock) { + btrfs_tree_read_lock(eb); + btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); + } + lock_extent_bits(io_tree, eb->start, eb->start + eb->len - 1, - 0, &cached_state, GFP_NOFS); - if (extent_buffer_uptodate(io_tree, eb, cached_state) && + 0, &cached_state); + if (extent_buffer_uptodate(eb) && btrfs_header_generation(eb) == parent_transid) { ret = 0; goto out; } - if (printk_ratelimit()) { - printk("parent transid verify failed on %llu wanted %llu " + printk_ratelimited("parent transid verify failed on %llu wanted %llu " "found %llu\n", - (unsigned long long)eb->start, - (unsigned long long)parent_transid, - (unsigned long long)btrfs_header_generation(eb)); - } + eb->start, parent_transid, btrfs_header_generation(eb)); ret = 1; - clear_extent_buffer_uptodate(io_tree, eb, &cached_state); + + /* + * Things reading via commit roots that don't have normal protection, + * like send, can have a really old block in cache that may point at a + * block that has been free'd and re-allocated. So don't clear uptodate + * if we find an eb that is under IO (dirty/writeback) because we could + * end up reading in the stale data and then writing it back out and + * making everybody very sad. + */ + if (!extent_buffer_under_io(eb)) + clear_extent_buffer_uptodate(eb); out: unlock_extent_cached(io_tree, eb->start, eb->start + eb->len - 1, &cached_state, GFP_NOFS); + if (need_lock) + btrfs_tree_read_unlock_blocking(eb); + return ret; +} + +/* + * Return 0 if the superblock checksum type matches the checksum value of that + * algorithm. Pass the raw disk superblock data. + */ +static int btrfs_check_super_csum(char *raw_disk_sb) +{ + struct btrfs_super_block *disk_sb = + (struct btrfs_super_block *)raw_disk_sb; + u16 csum_type = btrfs_super_csum_type(disk_sb); + int ret = 0; + + if (csum_type == BTRFS_CSUM_TYPE_CRC32) { + u32 crc = ~(u32)0; + const int csum_size = sizeof(crc); + char result[csum_size]; + + /* + * The super_block structure does not span the whole + * BTRFS_SUPER_INFO_SIZE range, we expect that the unused space + * is filled with zeros and is included in the checkum. + */ + crc = btrfs_csum_data(raw_disk_sb + BTRFS_CSUM_SIZE, + crc, BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE); + btrfs_csum_final(crc, result); + + if (memcmp(raw_disk_sb, result, csum_size)) + ret = 1; + + if (ret && btrfs_super_generation(disk_sb) < 10) { + printk(KERN_WARNING + "BTRFS: super block crcs don't match, older mkfs detected\n"); + ret = 0; + } + } + + if (csum_type >= ARRAY_SIZE(btrfs_csum_sizes)) { + printk(KERN_ERR "BTRFS: unsupported checksum algorithm %u\n", + csum_type); + ret = 1; + } + return ret; } @@ -304,28 +427,56 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root, u64 start, u64 parent_transid) { struct extent_io_tree *io_tree; + int failed = 0; int ret; int num_copies = 0; int mirror_num = 0; + int failed_mirror = 0; + 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)) - return ret; + if (!ret) { + if (!verify_parent_transid(io_tree, eb, + parent_transid, 0)) + break; + else + ret = -EIO; + } + + /* + * This buffer's crc is fine, but its contents are corrupted, so + * there is no reason to read the other copies, they won't be + * any less wrong. + */ + if (test_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags)) + break; - num_copies = btrfs_num_copies(&root->fs_info->mapping_tree, + num_copies = btrfs_num_copies(root->fs_info, eb->start, eb->len); if (num_copies == 1) - return ret; + break; + + if (!failed_mirror) { + failed = 1; + failed_mirror = eb->read_mirror; + } mirror_num++; + if (mirror_num == failed_mirror) + mirror_num++; + if (mirror_num > num_copies) - return ret; + break; } - return -EIO; + + if (failed && !ret && failed_mirror) + repair_eb_io_failure(root, eb, failed_mirror); + + return ret; } /* @@ -335,43 +486,17 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root, static int csum_dirty_buffer(struct btrfs_root *root, struct page *page) { - struct extent_io_tree *tree; - u64 start = (u64)page->index << PAGE_CACHE_SHIFT; + u64 start = page_offset(page); u64 found_start; - unsigned long len; struct extent_buffer *eb; - int ret; - 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, GFP_NOFS); - ret = btree_read_extent_buffer_pages(root, eb, start + PAGE_CACHE_SIZE, - btrfs_header_generation(eb)); - BUG_ON(ret); + eb = (struct extent_buffer *)page->private; + if (page != eb->pages[0]) + return 0; found_start = btrfs_header_bytenr(eb); - if (found_start != start) { - WARN_ON(1); - goto err; - } - if (eb->first_page != page) { - WARN_ON(1); - goto err; - } - if (!PageUptodate(page)) { - WARN_ON(1); - goto err; - } + if (WARN_ON(found_start != start || !PageUptodate(page))) + return 0; csum_tree_block(root, eb, 0); -err: - free_extent_buffer(eb); -out: return 0; } @@ -382,8 +507,7 @@ static int check_tree_block_fsid(struct btrfs_root *root, u8 fsid[BTRFS_UUID_SIZE]; int ret = 1; - read_extent_buffer(eb, fsid, (unsigned long)btrfs_header_fsid(eb), - BTRFS_FSID_SIZE); + read_extent_buffer(eb, fsid, btrfs_header_fsid(), BTRFS_FSID_SIZE); while (fs_devices) { if (!memcmp(fsid, fs_devices->fsid, BTRFS_FSID_SIZE)) { ret = 0; @@ -394,79 +518,179 @@ static int check_tree_block_fsid(struct btrfs_root *root, return ret; } -#ifdef CONFIG_DEBUG_LOCK_ALLOC -void btrfs_set_buffer_lockdep_class(struct extent_buffer *eb, int level) +#define CORRUPT(reason, eb, root, slot) \ + btrfs_crit(root->fs_info, "corrupt leaf, %s: block=%llu," \ + "root=%llu, slot=%d", reason, \ + btrfs_header_bytenr(eb), root->objectid, slot) + +static noinline int check_leaf(struct btrfs_root *root, + struct extent_buffer *leaf) { - lockdep_set_class_and_name(&eb->lock, - &btrfs_eb_class[level], - btrfs_eb_name[level]); + struct btrfs_key key; + struct btrfs_key leaf_key; + u32 nritems = btrfs_header_nritems(leaf); + int slot; + + if (nritems == 0) + return 0; + + /* Check the 0 item */ + if (btrfs_item_offset_nr(leaf, 0) + btrfs_item_size_nr(leaf, 0) != + BTRFS_LEAF_DATA_SIZE(root)) { + CORRUPT("invalid item offset size pair", leaf, root, 0); + return -EIO; + } + + /* + * Check to make sure each items keys are in the correct order and their + * offsets make sense. We only have to loop through nritems-1 because + * we check the current slot against the next slot, which verifies the + * next slot's offset+size makes sense and that the current's slot + * offset is correct. + */ + for (slot = 0; slot < nritems - 1; slot++) { + btrfs_item_key_to_cpu(leaf, &leaf_key, slot); + btrfs_item_key_to_cpu(leaf, &key, slot + 1); + + /* Make sure the keys are in the right order */ + if (btrfs_comp_cpu_keys(&leaf_key, &key) >= 0) { + CORRUPT("bad key order", leaf, root, slot); + return -EIO; + } + + /* + * Make sure the offset and ends are right, remember that the + * item data starts at the end of the leaf and grows towards the + * front. + */ + if (btrfs_item_offset_nr(leaf, slot) != + btrfs_item_end_nr(leaf, slot + 1)) { + CORRUPT("slot offset bad", leaf, root, slot); + return -EIO; + } + + /* + * Check to make sure that we don't point outside of the leaf, + * just incase all the items are consistent to eachother, but + * all point outside of the leaf. + */ + if (btrfs_item_end_nr(leaf, slot) > + BTRFS_LEAF_DATA_SIZE(root)) { + CORRUPT("slot end outside of leaf", leaf, root, slot); + return -EIO; + } + } + + return 0; } -#endif -static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end, - struct extent_state *state) +static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio, + u64 phy_offset, struct page *page, + u64 start, u64 end, int mirror) { - struct extent_io_tree *tree; u64 found_start; int found_level; - unsigned long len; struct extent_buffer *eb; struct btrfs_root *root = BTRFS_I(page->mapping->host)->root; int ret = 0; + int reads_done; - 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 = (struct extent_buffer *)page->private; - eb = alloc_extent_buffer(tree, start, len, page, GFP_NOFS); + /* the pending IO might have been the only thing that kept this buffer + * in memory. Make sure we have a ref for all this other checks + */ + extent_buffer_get(eb); - found_start = btrfs_header_bytenr(eb); - if (found_start != start) { - if (printk_ratelimit()) { - printk(KERN_INFO "btrfs bad tree block start " - "%llu %llu\n", - (unsigned long long)found_start, - (unsigned long long)eb->start); - } + reads_done = atomic_dec_and_test(&eb->io_pages); + if (!reads_done) + goto err; + + eb->read_mirror = mirror; + if (test_bit(EXTENT_BUFFER_IOERR, &eb->bflags)) { ret = -EIO; goto err; } - if (eb->first_page != page) { - printk(KERN_INFO "btrfs bad first page %lu %lu\n", - eb->first_page->index, page->index); - WARN_ON(1); + + found_start = btrfs_header_bytenr(eb); + if (found_start != eb->start) { + printk_ratelimited(KERN_INFO "BTRFS: bad tree block start " + "%llu %llu\n", + found_start, eb->start); ret = -EIO; goto err; } if (check_tree_block_fsid(root, eb)) { - if (printk_ratelimit()) { - printk(KERN_INFO "btrfs bad fsid on block %llu\n", - (unsigned long long)eb->start); - } + printk_ratelimited(KERN_INFO "BTRFS: bad fsid on block %llu\n", + eb->start); ret = -EIO; goto err; } found_level = btrfs_header_level(eb); + if (found_level >= BTRFS_MAX_LEVEL) { + btrfs_info(root->fs_info, "bad tree block level %d", + (int)btrfs_header_level(eb)); + ret = -EIO; + goto err; + } - btrfs_set_buffer_lockdep_class(eb, found_level); + btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb), + eb, found_level); ret = csum_tree_block(root, eb, 1); - if (ret) + if (ret) { ret = -EIO; + goto err; + } - end = min_t(u64, eb->len, PAGE_CACHE_SIZE); - end = eb->start + end - 1; + /* + * If this is a leaf block and it is corrupt, set the corrupt bit so + * that we don't try and read the other copies of this block, just + * return -EIO. + */ + if (found_level == 0 && check_leaf(root, eb)) { + set_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags); + ret = -EIO; + } + + if (!ret) + set_extent_buffer_uptodate(eb); err: + if (reads_done && + test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags)) + btree_readahead_hook(root, eb, eb->start, ret); + + if (ret) { + /* + * our io error hook is going to dec the io pages + * again, we have to make sure it has something + * to decrement + */ + atomic_inc(&eb->io_pages); + clear_extent_buffer_uptodate(eb); + } free_extent_buffer(eb); out: return ret; } +static int btree_io_failed_hook(struct page *page, int failed_mirror) +{ + struct extent_buffer *eb; + struct btrfs_root *root = BTRFS_I(page->mapping->host)->root; + + eb = (struct extent_buffer *)page->private; + set_bit(EXTENT_BUFFER_IOERR, &eb->bflags); + eb->read_mirror = failed_mirror; + atomic_dec(&eb->io_pages); + if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags)) + btree_readahead_hook(root, eb, eb->start, -EIO); + 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; @@ -474,26 +698,31 @@ static void end_workqueue_bio(struct bio *bio, int err) fs_info = end_io_wq->info; end_io_wq->error = err; - end_io_wq->work.func = end_workqueue_fn; - end_io_wq->work.flags = 0; + btrfs_init_work(&end_io_wq->work, end_workqueue_fn, NULL, NULL); if (bio->bi_rw & REQ_WRITE) { - if (end_io_wq->metadata == 1) - btrfs_queue_worker(&fs_info->endio_meta_write_workers, - &end_io_wq->work); - else if (end_io_wq->metadata == 2) - btrfs_queue_worker(&fs_info->endio_freespace_worker, - &end_io_wq->work); + if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA) + btrfs_queue_work(fs_info->endio_meta_write_workers, + &end_io_wq->work); + else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE) + btrfs_queue_work(fs_info->endio_freespace_worker, + &end_io_wq->work); + else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) + btrfs_queue_work(fs_info->endio_raid56_workers, + &end_io_wq->work); else - btrfs_queue_worker(&fs_info->endio_write_workers, - &end_io_wq->work); + btrfs_queue_work(fs_info->endio_write_workers, + &end_io_wq->work); } else { - if (end_io_wq->metadata) - btrfs_queue_worker(&fs_info->endio_meta_workers, - &end_io_wq->work); + if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) + btrfs_queue_work(fs_info->endio_raid56_workers, + &end_io_wq->work); + else if (end_io_wq->metadata) + btrfs_queue_work(fs_info->endio_meta_workers, + &end_io_wq->work); else - btrfs_queue_worker(&fs_info->endio_workers, - &end_io_wq->work); + btrfs_queue_work(fs_info->endio_workers, + &end_io_wq->work); } } @@ -503,6 +732,7 @@ static void end_workqueue_bio(struct bio *bio, int err) * 0 - if data * 1 - if normal metadta * 2 - if writing to the free space cache area + * 3 - raid parity work */ int btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio, int metadata) @@ -527,25 +757,22 @@ int btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio, unsigned long btrfs_async_submit_limit(struct btrfs_fs_info *info) { unsigned long limit = min_t(unsigned long, - info->workers.max_workers, + info->thread_pool_size, info->fs_devices->open_devices); return 256 * limit; } -int btrfs_congested_async(struct btrfs_fs_info *info, int iodone) -{ - return atomic_read(&info->nr_async_bios) > - btrfs_async_submit_limit(info); -} - static void run_one_async_start(struct btrfs_work *work) { struct async_submit_bio *async; + int ret; async = container_of(work, struct async_submit_bio, work); - async->submit_bio_start(async->inode, async->rw, async->bio, - async->mirror_num, async->bio_flags, - async->bio_offset); + ret = async->submit_bio_start(async->inode, async->rw, async->bio, + async->mirror_num, async->bio_flags, + async->bio_offset); + if (ret) + async->error = ret; } static void run_one_async_done(struct btrfs_work *work) @@ -560,12 +787,16 @@ static void run_one_async_done(struct btrfs_work *work) limit = btrfs_async_submit_limit(fs_info); limit = limit * 2 / 3; - atomic_dec(&fs_info->nr_async_submits); - - if (atomic_read(&fs_info->nr_async_submits) < limit && + if (atomic_dec_return(&fs_info->nr_async_submits) < limit && waitqueue_active(&fs_info->async_submit_wait)) wake_up(&fs_info->async_submit_wait); + /* If an error occured we just want to clean up the bio and move on */ + if (async->error) { + bio_endio(async->bio, async->error); + return; + } + async->submit_bio_done(async->inode, async->rw, async->bio, async->mirror_num, async->bio_flags, async->bio_offset); @@ -599,20 +830,20 @@ int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode, async->submit_bio_start = submit_bio_start; async->submit_bio_done = submit_bio_done; - async->work.func = run_one_async_start; - async->work.ordered_func = run_one_async_done; - async->work.ordered_free = run_one_async_free; + btrfs_init_work(&async->work, run_one_async_start, + run_one_async_done, run_one_async_free); - async->work.flags = 0; async->bio_flags = bio_flags; async->bio_offset = bio_offset; + async->error = 0; + atomic_inc(&fs_info->nr_async_submits); if (rw & REQ_SYNC) - btrfs_set_work_high_prio(&async->work); + btrfs_set_work_high_priority(&async->work); - btrfs_queue_worker(&fs_info->workers, &async->work); + btrfs_queue_work(fs_info->workers, &async->work); while (atomic_read(&fs_info->async_submit_draining) && atomic_read(&fs_info->nr_async_submits)) { @@ -625,18 +856,18 @@ int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode, static int btree_csum_one_bio(struct bio *bio) { - struct bio_vec *bvec = bio->bi_io_vec; - int bio_index = 0; + struct bio_vec *bvec; struct btrfs_root *root; + int i, ret = 0; - WARN_ON(bio->bi_vcnt <= 0); - while (bio_index < bio->bi_vcnt) { + bio_for_each_segment_all(bvec, bio, i) { root = BTRFS_I(bvec->bv_page->mapping->host)->root; - csum_dirty_buffer(root, bvec->bv_page); - bio_index++; - bvec++; + ret = csum_dirty_buffer(root, bvec->bv_page); + if (ret) + break; } - return 0; + + return ret; } static int __btree_submit_bio_start(struct inode *inode, int rw, @@ -648,157 +879,179 @@ static int __btree_submit_bio_start(struct inode *inode, int rw, * when we're called for a write, we're already in the async * submission context. Just jump into btrfs_map_bio */ - btree_csum_one_bio(bio); - return 0; + return btree_csum_one_bio(bio); } static int __btree_submit_bio_done(struct inode *inode, int rw, struct bio *bio, int mirror_num, unsigned long bio_flags, u64 bio_offset) { + int ret; + /* * when we're called for a write, we're already in the async * submission context. Just jump into btrfs_map_bio */ - return btrfs_map_bio(BTRFS_I(inode)->root, rw, bio, mirror_num, 1); + ret = btrfs_map_bio(BTRFS_I(inode)->root, rw, bio, mirror_num, 1); + if (ret) + bio_endio(bio, ret); + return ret; +} + +static int check_async_write(struct inode *inode, unsigned long bio_flags) +{ + if (bio_flags & EXTENT_BIO_TREE_LOG) + return 0; +#ifdef CONFIG_X86 + if (cpu_has_xmm4_2) + return 0; +#endif + return 1; } static int btree_submit_bio_hook(struct inode *inode, int rw, struct bio *bio, int mirror_num, unsigned long bio_flags, u64 bio_offset) { + int async = check_async_write(inode, bio_flags); int ret; - ret = btrfs_bio_wq_end_io(BTRFS_I(inode)->root->fs_info, - bio, 1); - BUG_ON(ret); - if (!(rw & REQ_WRITE)) { /* * called for a read, do the setup so that checksum validation * can happen in the async kernel threads */ - return btrfs_map_bio(BTRFS_I(inode)->root, rw, bio, - mirror_num, 0); + ret = btrfs_bio_wq_end_io(BTRFS_I(inode)->root->fs_info, + bio, 1); + if (ret) + goto out_w_error; + ret = btrfs_map_bio(BTRFS_I(inode)->root, rw, bio, + mirror_num, 0); + } else if (!async) { + ret = btree_csum_one_bio(bio); + if (ret) + goto out_w_error; + ret = btrfs_map_bio(BTRFS_I(inode)->root, rw, bio, + mirror_num, 0); + } else { + /* + * kthread helpers are used to submit writes so that + * checksumming can happen in parallel across all CPUs + */ + ret = btrfs_wq_submit_bio(BTRFS_I(inode)->root->fs_info, + inode, rw, bio, mirror_num, 0, + bio_offset, + __btree_submit_bio_start, + __btree_submit_bio_done); } - /* - * kthread helpers are used to submit writes so that checksumming - * can happen in parallel across all CPUs - */ - return btrfs_wq_submit_bio(BTRFS_I(inode)->root->fs_info, - inode, rw, bio, mirror_num, 0, - bio_offset, - __btree_submit_bio_start, - __btree_submit_bio_done); + if (ret) { +out_w_error: + bio_endio(bio, ret); + } + return ret; } -static int btree_writepage(struct page *page, struct writeback_control *wbc) +#ifdef CONFIG_MIGRATION +static int btree_migratepage(struct address_space *mapping, + struct page *newpage, struct page *page, + enum migrate_mode mode) { - struct extent_io_tree *tree; - struct btrfs_root *root = BTRFS_I(page->mapping->host)->root; - struct extent_buffer *eb; - int was_dirty; - - tree = &BTRFS_I(page->mapping->host)->io_tree; - if (!(current->flags & PF_MEMALLOC)) { - return extent_write_full_page(tree, page, - btree_get_extent, wbc); - } - - redirty_page_for_writepage(wbc, page); - eb = btrfs_find_tree_block(root, page_offset(page), - PAGE_CACHE_SIZE); - WARN_ON(!eb); - - was_dirty = test_and_set_bit(EXTENT_BUFFER_DIRTY, &eb->bflags); - if (!was_dirty) { - spin_lock(&root->fs_info->delalloc_lock); - root->fs_info->dirty_metadata_bytes += PAGE_CACHE_SIZE; - spin_unlock(&root->fs_info->delalloc_lock); - } - free_extent_buffer(eb); - - unlock_page(page); - return 0; + /* + * we can't safely write a btree page from here, + * we haven't done the locking hook + */ + if (PageDirty(page)) + return -EAGAIN; + /* + * Buffers may be managed in a filesystem specific way. + * We must have no buffers or drop them. + */ + if (page_has_private(page) && + !try_to_release_page(page, GFP_KERNEL)) + return -EAGAIN; + return migrate_page(mapping, newpage, page, mode); } +#endif + static int btree_writepages(struct address_space *mapping, struct writeback_control *wbc) { - struct extent_io_tree *tree; - tree = &BTRFS_I(mapping->host)->io_tree; + struct btrfs_fs_info *fs_info; + int ret; + if (wbc->sync_mode == WB_SYNC_NONE) { - struct btrfs_root *root = BTRFS_I(mapping->host)->root; - u64 num_dirty; - unsigned long thresh = 32 * 1024 * 1024; if (wbc->for_kupdate) return 0; + fs_info = BTRFS_I(mapping->host)->root->fs_info; /* this is a bit racy, but that's ok */ - num_dirty = root->fs_info->dirty_metadata_bytes; - if (num_dirty < thresh) + ret = percpu_counter_compare(&fs_info->dirty_metadata_bytes, + BTRFS_DIRTY_METADATA_THRESH); + if (ret < 0) return 0; } - return extent_writepages(tree, mapping, btree_get_extent, wbc); + return btree_write_cache_pages(mapping, wbc); } static int btree_readpage(struct file *file, struct page *page) { struct extent_io_tree *tree; tree = &BTRFS_I(page->mapping->host)->io_tree; - return extent_read_full_page(tree, page, btree_get_extent); + return extent_read_full_page(tree, page, btree_get_extent, 0); } static int btree_releasepage(struct page *page, gfp_t gfp_flags) { - struct extent_io_tree *tree; - struct extent_map_tree *map; - int ret; - if (PageWriteback(page) || PageDirty(page)) return 0; - tree = &BTRFS_I(page->mapping->host)->io_tree; - map = &BTRFS_I(page->mapping->host)->extent_tree; - - ret = try_release_extent_state(map, tree, page, gfp_flags); - if (!ret) - return 0; - - ret = try_release_extent_buffer(tree, page); - if (ret == 1) { - ClearPagePrivate(page); - set_page_private(page, 0); - page_cache_release(page); - } - - return ret; + return try_release_extent_buffer(page); } -static void btree_invalidatepage(struct page *page, unsigned long offset) +static void btree_invalidatepage(struct page *page, unsigned int offset, + unsigned int length) { struct extent_io_tree *tree; tree = &BTRFS_I(page->mapping->host)->io_tree; extent_invalidatepage(tree, page, offset); btree_releasepage(page, GFP_NOFS); if (PagePrivate(page)) { - printk(KERN_WARNING "btrfs warning page private not zero " - "on page %llu\n", (unsigned long long)page_offset(page)); + btrfs_warn(BTRFS_I(page->mapping->host)->root->fs_info, + "page private not zero on page %llu", + (unsigned long long)page_offset(page)); ClearPagePrivate(page); set_page_private(page, 0); page_cache_release(page); } } +static int btree_set_page_dirty(struct page *page) +{ +#ifdef DEBUG + struct extent_buffer *eb; + + BUG_ON(!PagePrivate(page)); + eb = (struct extent_buffer *)page->private; + BUG_ON(!eb); + BUG_ON(!test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)); + BUG_ON(!atomic_read(&eb->refs)); + btrfs_assert_tree_locked(eb); +#endif + return __set_page_dirty_nobuffers(page); +} + static const struct address_space_operations btree_aops = { .readpage = btree_readpage, - .writepage = btree_writepage, .writepages = btree_writepages, .releasepage = btree_releasepage, .invalidatepage = btree_invalidatepage, - .sync_page = block_sync_page, +#ifdef CONFIG_MIGRATION + .migratepage = btree_migratepage, +#endif + .set_page_dirty = btree_set_page_dirty, }; int readahead_tree_block(struct btrfs_root *root, u64 bytenr, u32 blocksize, @@ -812,42 +1065,70 @@ int readahead_tree_block(struct btrfs_root *root, u64 bytenr, u32 blocksize, 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(buf)) { + *eb = buf; + } else { + free_extent_buffer(buf); + } + return 0; +} + struct extent_buffer *btrfs_find_tree_block(struct btrfs_root *root, u64 bytenr, u32 blocksize) { - struct inode *btree_inode = root->fs_info->btree_inode; - struct extent_buffer *eb; - eb = find_extent_buffer(&BTRFS_I(btree_inode)->io_tree, - bytenr, blocksize, GFP_NOFS); - return eb; + return find_extent_buffer(root->fs_info, bytenr); } struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root, u64 bytenr, u32 blocksize) { - struct inode *btree_inode = root->fs_info->btree_inode; - struct extent_buffer *eb; - - eb = alloc_extent_buffer(&BTRFS_I(btree_inode)->io_tree, - bytenr, blocksize, NULL, GFP_NOFS); - return eb; +#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS + if (unlikely(test_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state))) + return alloc_test_extent_buffer(root->fs_info, bytenr, + blocksize); +#endif + return alloc_extent_buffer(root->fs_info, bytenr, blocksize); } int btrfs_write_tree_block(struct extent_buffer *buf) { - return filemap_fdatawrite_range(buf->first_page->mapping, buf->start, + return filemap_fdatawrite_range(buf->pages[0]->mapping, buf->start, buf->start + buf->len - 1); } int btrfs_wait_tree_block_writeback(struct extent_buffer *buf) { - return filemap_fdatawait_range(buf->first_page->mapping, + return filemap_fdatawait_range(buf->pages[0]->mapping, buf->start, buf->start + buf->len - 1); } @@ -862,42 +1143,64 @@ struct extent_buffer *read_tree_block(struct btrfs_root *root, u64 bytenr, return NULL; ret = btree_read_extent_buffer_pages(root, buf, 0, parent_transid); - - if (ret == 0) - set_bit(EXTENT_BUFFER_UPTODATE, &buf->bflags); + if (ret) { + free_extent_buffer(buf); + return NULL; + } return buf; } -int clean_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, - struct extent_buffer *buf) +void clean_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, + struct extent_buffer *buf) { - struct inode *btree_inode = root->fs_info->btree_inode; + struct btrfs_fs_info *fs_info = root->fs_info; + if (btrfs_header_generation(buf) == - root->fs_info->running_transaction->transid) { + fs_info->running_transaction->transid) { btrfs_assert_tree_locked(buf); if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &buf->bflags)) { - spin_lock(&root->fs_info->delalloc_lock); - if (root->fs_info->dirty_metadata_bytes >= buf->len) - root->fs_info->dirty_metadata_bytes -= buf->len; - else - WARN_ON(1); - spin_unlock(&root->fs_info->delalloc_lock); + __percpu_counter_add(&fs_info->dirty_metadata_bytes, + -buf->len, + fs_info->dirty_metadata_batch); + /* ugh, clear_extent_buffer_dirty needs to lock the page */ + btrfs_set_lock_blocking(buf); + clear_extent_buffer_dirty(buf); } + } +} + +static struct btrfs_subvolume_writers *btrfs_alloc_subvolume_writers(void) +{ + struct btrfs_subvolume_writers *writers; + int ret; + + writers = kmalloc(sizeof(*writers), GFP_NOFS); + if (!writers) + return ERR_PTR(-ENOMEM); - /* ugh, clear_extent_buffer_dirty needs to lock the page */ - btrfs_set_lock_blocking(buf); - clear_extent_buffer_dirty(&BTRFS_I(btree_inode)->io_tree, - buf); + ret = percpu_counter_init(&writers->counter, 0); + if (ret < 0) { + kfree(writers); + return ERR_PTR(ret); } - return 0; + + init_waitqueue_head(&writers->wait); + return writers; } -static int __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize, - u32 stripesize, struct btrfs_root *root, - struct btrfs_fs_info *fs_info, - u64 objectid) +static void +btrfs_free_subvolume_writers(struct btrfs_subvolume_writers *writers) +{ + percpu_counter_destroy(&writers->counter); + kfree(writers); +} + +static void __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize, + u32 stripesize, struct btrfs_root *root, + struct btrfs_fs_info *fs_info, + u64 objectid) { root->node = NULL; root->commit_root = NULL; @@ -905,85 +1208,178 @@ static int __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize, root->nodesize = nodesize; root->leafsize = leafsize; root->stripesize = stripesize; - root->ref_cows = 0; - root->track_dirty = 0; - root->in_radix = 0; - root->orphan_item_inserted = 0; + root->state = 0; root->orphan_cleanup_state = 0; - root->fs_info = fs_info; root->objectid = objectid; root->last_trans = 0; root->highest_objectid = 0; + root->nr_delalloc_inodes = 0; + root->nr_ordered_extents = 0; root->name = NULL; - root->in_sysfs = 0; root->inode_tree = RB_ROOT; + INIT_RADIX_TREE(&root->delayed_nodes_tree, GFP_ATOMIC); root->block_rsv = NULL; root->orphan_block_rsv = NULL; INIT_LIST_HEAD(&root->dirty_list); - INIT_LIST_HEAD(&root->orphan_list); INIT_LIST_HEAD(&root->root_list); - spin_lock_init(&root->node_lock); + INIT_LIST_HEAD(&root->delalloc_inodes); + INIT_LIST_HEAD(&root->delalloc_root); + INIT_LIST_HEAD(&root->ordered_extents); + INIT_LIST_HEAD(&root->ordered_root); + INIT_LIST_HEAD(&root->logged_list[0]); + INIT_LIST_HEAD(&root->logged_list[1]); spin_lock_init(&root->orphan_lock); spin_lock_init(&root->inode_lock); + spin_lock_init(&root->delalloc_lock); + spin_lock_init(&root->ordered_extent_lock); spin_lock_init(&root->accounting_lock); + spin_lock_init(&root->log_extents_lock[0]); + spin_lock_init(&root->log_extents_lock[1]); mutex_init(&root->objectid_mutex); mutex_init(&root->log_mutex); + mutex_init(&root->ordered_extent_mutex); + mutex_init(&root->delalloc_mutex); init_waitqueue_head(&root->log_writer_wait); init_waitqueue_head(&root->log_commit_wait[0]); init_waitqueue_head(&root->log_commit_wait[1]); + INIT_LIST_HEAD(&root->log_ctxs[0]); + INIT_LIST_HEAD(&root->log_ctxs[1]); atomic_set(&root->log_commit[0], 0); atomic_set(&root->log_commit[1], 0); atomic_set(&root->log_writers, 0); - root->log_batch = 0; + atomic_set(&root->log_batch, 0); + atomic_set(&root->orphan_inodes, 0); + atomic_set(&root->refs, 1); + atomic_set(&root->will_be_snapshoted, 0); root->log_transid = 0; + root->log_transid_committed = -1; root->last_log_commit = 0; - extent_io_tree_init(&root->dirty_log_pages, - fs_info->btree_inode->i_mapping, GFP_NOFS); + if (fs_info) + extent_io_tree_init(&root->dirty_log_pages, + fs_info->btree_inode->i_mapping); memset(&root->root_key, 0, sizeof(root->root_key)); memset(&root->root_item, 0, sizeof(root->root_item)); memset(&root->defrag_progress, 0, sizeof(root->defrag_progress)); memset(&root->root_kobj, 0, sizeof(root->root_kobj)); - root->defrag_trans_start = fs_info->generation; + if (fs_info) + root->defrag_trans_start = fs_info->generation; + else + root->defrag_trans_start = 0; init_completion(&root->kobj_unregister); - root->defrag_running = 0; root->root_key.objectid = objectid; - root->anon_super.s_root = NULL; - root->anon_super.s_dev = 0; - INIT_LIST_HEAD(&root->anon_super.s_list); - INIT_LIST_HEAD(&root->anon_super.s_instances); - init_rwsem(&root->anon_super.s_umount); + root->anon_dev = 0; - return 0; + spin_lock_init(&root->root_item_lock); } -static int find_and_setup_root(struct btrfs_root *tree_root, - struct btrfs_fs_info *fs_info, - u64 objectid, - struct btrfs_root *root) +static struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info) { - int ret; - u32 blocksize; - u64 generation; + struct btrfs_root *root = kzalloc(sizeof(*root), GFP_NOFS); + if (root) + root->fs_info = fs_info; + return root; +} + +#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS +/* Should only be used by the testing infrastructure */ +struct btrfs_root *btrfs_alloc_dummy_root(void) +{ + struct btrfs_root *root; + + root = btrfs_alloc_root(NULL); + if (!root) + return ERR_PTR(-ENOMEM); + __setup_root(4096, 4096, 4096, 4096, root, NULL, 1); + set_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state); + root->alloc_bytenr = 0; + + return root; +} +#endif + +struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans, + struct btrfs_fs_info *fs_info, + u64 objectid) +{ + struct extent_buffer *leaf; + struct btrfs_root *tree_root = fs_info->tree_root; + struct btrfs_root *root; + struct btrfs_key key; + int ret = 0; + uuid_le uuid; + + root = btrfs_alloc_root(fs_info); + if (!root) + return ERR_PTR(-ENOMEM); __setup_root(tree_root->nodesize, tree_root->leafsize, tree_root->sectorsize, tree_root->stripesize, root, fs_info, objectid); - ret = btrfs_find_last_root(tree_root, objectid, - &root->root_item, &root->root_key); - if (ret > 0) - return -ENOENT; - BUG_ON(ret); + root->root_key.objectid = objectid; + root->root_key.type = BTRFS_ROOT_ITEM_KEY; + root->root_key.offset = 0; + + leaf = btrfs_alloc_free_block(trans, root, root->leafsize, + 0, objectid, NULL, 0, 0, 0); + if (IS_ERR(leaf)) { + ret = PTR_ERR(leaf); + leaf = NULL; + goto fail; + } + + memset_extent_buffer(leaf, 0, 0, sizeof(struct btrfs_header)); + btrfs_set_header_bytenr(leaf, leaf->start); + btrfs_set_header_generation(leaf, trans->transid); + btrfs_set_header_backref_rev(leaf, BTRFS_MIXED_BACKREF_REV); + btrfs_set_header_owner(leaf, objectid); + root->node = leaf; + + write_extent_buffer(leaf, fs_info->fsid, btrfs_header_fsid(), + BTRFS_FSID_SIZE); + write_extent_buffer(leaf, fs_info->chunk_tree_uuid, + btrfs_header_chunk_tree_uuid(leaf), + BTRFS_UUID_SIZE); + btrfs_mark_buffer_dirty(leaf); - generation = btrfs_root_generation(&root->root_item); - blocksize = btrfs_level_size(root, btrfs_root_level(&root->root_item)); - root->node = read_tree_block(root, btrfs_root_bytenr(&root->root_item), - blocksize, generation); - BUG_ON(!root->node); root->commit_root = btrfs_root_node(root); - return 0; + set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); + + root->root_item.flags = 0; + root->root_item.byte_limit = 0; + btrfs_set_root_bytenr(&root->root_item, leaf->start); + btrfs_set_root_generation(&root->root_item, trans->transid); + btrfs_set_root_level(&root->root_item, 0); + btrfs_set_root_refs(&root->root_item, 1); + btrfs_set_root_used(&root->root_item, leaf->len); + btrfs_set_root_last_snapshot(&root->root_item, 0); + btrfs_set_root_dirid(&root->root_item, 0); + uuid_le_gen(&uuid); + memcpy(root->root_item.uuid, uuid.b, BTRFS_UUID_SIZE); + root->root_item.drop_level = 0; + + key.objectid = objectid; + key.type = BTRFS_ROOT_ITEM_KEY; + key.offset = 0; + ret = btrfs_insert_root(trans, tree_root, &key, &root->root_item); + if (ret) + goto fail; + + btrfs_tree_unlock(leaf); + + return root; + +fail: + if (leaf) { + btrfs_tree_unlock(leaf); + free_extent_buffer(root->commit_root); + free_extent_buffer(leaf); + } + kfree(root); + + return ERR_PTR(ret); } static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans, @@ -993,7 +1389,7 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans, struct btrfs_root *tree_root = fs_info->tree_root; struct extent_buffer *leaf; - root = kzalloc(sizeof(*root), GFP_NOFS); + root = btrfs_alloc_root(fs_info); if (!root) return ERR_PTR(-ENOMEM); @@ -1004,16 +1400,19 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans, root->root_key.objectid = BTRFS_TREE_LOG_OBJECTID; root->root_key.type = BTRFS_ROOT_ITEM_KEY; root->root_key.offset = BTRFS_TREE_LOG_OBJECTID; + /* + * DON'T set REF_COWS for log trees + * * log trees do not get reference counted because they go away * before a real commit is actually done. They do store pointers * to file data extents, and those reference counts still get * updated (along with back refs to the log tree). */ - 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); if (IS_ERR(leaf)) { kfree(root); return ERR_CAST(leaf); @@ -1027,8 +1426,7 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans, root->node = leaf; write_extent_buffer(root->node, root->fs_info->fsid, - (unsigned long)btrfs_header_fsid(root->node), - BTRFS_FSID_SIZE); + btrfs_header_fsid(), BTRFS_FSID_SIZE); btrfs_mark_buffer_dirty(root->node); btrfs_tree_unlock(root->node); return root; @@ -1061,96 +1459,169 @@ int btrfs_add_log_tree(struct btrfs_trans_handle *trans, log_root->root_key.offset = root->root_key.objectid; inode_item = &log_root->root_item.inode; - inode_item->generation = cpu_to_le64(1); - inode_item->size = cpu_to_le64(3); - inode_item->nlink = cpu_to_le32(1); - inode_item->nbytes = cpu_to_le64(root->leafsize); - inode_item->mode = cpu_to_le32(S_IFDIR | 0755); + btrfs_set_stack_inode_generation(inode_item, 1); + btrfs_set_stack_inode_size(inode_item, 3); + btrfs_set_stack_inode_nlink(inode_item, 1); + btrfs_set_stack_inode_nbytes(inode_item, root->leafsize); + btrfs_set_stack_inode_mode(inode_item, S_IFDIR | 0755); btrfs_set_root_node(&log_root->root_item, log_root->node); WARN_ON(root->log_root); root->log_root = log_root; root->log_transid = 0; + root->log_transid_committed = -1; root->last_log_commit = 0; return 0; } -struct btrfs_root *btrfs_read_fs_root_no_radix(struct btrfs_root *tree_root, - struct btrfs_key *location) +static struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root, + struct btrfs_key *key) { struct btrfs_root *root; struct btrfs_fs_info *fs_info = tree_root->fs_info; struct btrfs_path *path; - struct extent_buffer *l; u64 generation; u32 blocksize; - int ret = 0; + int ret; - root = kzalloc(sizeof(*root), GFP_NOFS); - if (!root) + path = btrfs_alloc_path(); + if (!path) return ERR_PTR(-ENOMEM); - if (location->offset == (u64)-1) { - ret = find_and_setup_root(tree_root, fs_info, - location->objectid, root); - if (ret) { - kfree(root); - return ERR_PTR(ret); - } - goto out; + + root = btrfs_alloc_root(fs_info); + if (!root) { + ret = -ENOMEM; + goto alloc_fail; } __setup_root(tree_root->nodesize, tree_root->leafsize, tree_root->sectorsize, tree_root->stripesize, - root, fs_info, location->objectid); + root, fs_info, key->objectid); - path = btrfs_alloc_path(); - BUG_ON(!path); - ret = btrfs_search_slot(NULL, tree_root, location, path, 0, 0); - if (ret == 0) { - l = path->nodes[0]; - read_extent_buffer(l, &root->root_item, - btrfs_item_ptr_offset(l, path->slots[0]), - sizeof(root->root_item)); - memcpy(&root->root_key, location, sizeof(*location)); - } - btrfs_free_path(path); + ret = btrfs_find_root(tree_root, key, path, + &root->root_item, &root->root_key); if (ret) { if (ret > 0) ret = -ENOENT; - return ERR_PTR(ret); + goto find_fail; } generation = btrfs_root_generation(&root->root_item); blocksize = btrfs_level_size(root, btrfs_root_level(&root->root_item)); root->node = read_tree_block(root, btrfs_root_bytenr(&root->root_item), blocksize, generation); + if (!root->node) { + ret = -ENOMEM; + goto find_fail; + } else if (!btrfs_buffer_uptodate(root->node, generation, 0)) { + ret = -EIO; + goto read_fail; + } root->commit_root = btrfs_root_node(root); - BUG_ON(!root->node); out: - if (location->objectid != BTRFS_TREE_LOG_OBJECTID) - root->ref_cows = 1; - + btrfs_free_path(path); return root; + +read_fail: + free_extent_buffer(root->node); +find_fail: + kfree(root); +alloc_fail: + root = ERR_PTR(ret); + goto out; } -struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info, - u64 root_objectid) +struct btrfs_root *btrfs_read_fs_root(struct btrfs_root *tree_root, + struct btrfs_key *location) { struct btrfs_root *root; - if (root_objectid == BTRFS_ROOT_TREE_OBJECTID) - return fs_info->tree_root; - if (root_objectid == BTRFS_EXTENT_TREE_OBJECTID) - return fs_info->extent_root; + root = btrfs_read_tree_root(tree_root, location); + if (IS_ERR(root)) + return root; + + if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) { + set_bit(BTRFS_ROOT_REF_COWS, &root->state); + btrfs_check_and_init_root_item(&root->root_item); + } + + return root; +} + +int btrfs_init_fs_root(struct btrfs_root *root) +{ + int ret; + struct btrfs_subvolume_writers *writers; + + root->free_ino_ctl = kzalloc(sizeof(*root->free_ino_ctl), GFP_NOFS); + root->free_ino_pinned = kzalloc(sizeof(*root->free_ino_pinned), + GFP_NOFS); + if (!root->free_ino_pinned || !root->free_ino_ctl) { + ret = -ENOMEM; + goto fail; + } + + writers = btrfs_alloc_subvolume_writers(); + if (IS_ERR(writers)) { + ret = PTR_ERR(writers); + goto fail; + } + root->subv_writers = writers; + + btrfs_init_free_ino_ctl(root); + spin_lock_init(&root->cache_lock); + init_waitqueue_head(&root->cache_wait); + + ret = get_anon_bdev(&root->anon_dev); + if (ret) + goto free_writers; + return 0; + +free_writers: + btrfs_free_subvolume_writers(root->subv_writers); +fail: + kfree(root->free_ino_ctl); + kfree(root->free_ino_pinned); + return ret; +} +static struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info, + u64 root_id) +{ + struct btrfs_root *root; + + spin_lock(&fs_info->fs_roots_radix_lock); root = radix_tree_lookup(&fs_info->fs_roots_radix, - (unsigned long)root_objectid); + (unsigned long)root_id); + spin_unlock(&fs_info->fs_roots_radix_lock); return root; } -struct btrfs_root *btrfs_read_fs_root_no_name(struct btrfs_fs_info *fs_info, - struct btrfs_key *location) +int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info, + struct btrfs_root *root) +{ + int ret; + + ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM); + if (ret) + return ret; + + spin_lock(&fs_info->fs_roots_radix_lock); + ret = radix_tree_insert(&fs_info->fs_roots_radix, + (unsigned long)root->root_key.objectid, + root); + if (ret == 0) + set_bit(BTRFS_ROOT_IN_RADIX, &root->state); + spin_unlock(&fs_info->fs_roots_radix_lock); + radix_tree_preload_end(); + + return ret; +} + +struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, + struct btrfs_key *location, + bool check_ref) { struct btrfs_root *root; int ret; @@ -1165,44 +1636,41 @@ struct btrfs_root *btrfs_read_fs_root_no_name(struct btrfs_fs_info *fs_info, return fs_info->dev_root; if (location->objectid == BTRFS_CSUM_TREE_OBJECTID) return fs_info->csum_root; + if (location->objectid == BTRFS_QUOTA_TREE_OBJECTID) + return fs_info->quota_root ? fs_info->quota_root : + ERR_PTR(-ENOENT); + if (location->objectid == BTRFS_UUID_TREE_OBJECTID) + return fs_info->uuid_root ? fs_info->uuid_root : + ERR_PTR(-ENOENT); again: - spin_lock(&fs_info->fs_roots_radix_lock); - root = radix_tree_lookup(&fs_info->fs_roots_radix, - (unsigned long)location->objectid); - spin_unlock(&fs_info->fs_roots_radix_lock); - if (root) + root = btrfs_lookup_fs_root(fs_info, location->objectid); + if (root) { + if (check_ref && btrfs_root_refs(&root->root_item) == 0) + return ERR_PTR(-ENOENT); return root; + } - root = btrfs_read_fs_root_no_radix(fs_info->tree_root, location); + root = btrfs_read_fs_root(fs_info->tree_root, location); if (IS_ERR(root)) return root; - set_anon_super(&root->anon_super, NULL); - - if (btrfs_root_refs(&root->root_item) == 0) { + if (check_ref && btrfs_root_refs(&root->root_item) == 0) { ret = -ENOENT; goto fail; } - ret = btrfs_find_orphan_item(fs_info->tree_root, location->objectid); - if (ret < 0) - goto fail; - if (ret == 0) - root->orphan_item_inserted = 1; - - ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM); + ret = btrfs_init_fs_root(root); if (ret) goto fail; - spin_lock(&fs_info->fs_roots_radix_lock); - ret = radix_tree_insert(&fs_info->fs_roots_radix, - (unsigned long)root->root_key.objectid, - root); + ret = btrfs_find_item(fs_info->tree_root, NULL, BTRFS_ORPHAN_OBJECTID, + location->objectid, BTRFS_ORPHAN_ITEM_KEY, NULL); + if (ret < 0) + goto fail; if (ret == 0) - root->in_radix = 1; + set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state); - spin_unlock(&fs_info->fs_roots_radix_lock); - radix_tree_preload_end(); + ret = btrfs_insert_fs_root(fs_info, root); if (ret) { if (ret == -EEXIST) { free_fs_root(root); @@ -1210,51 +1678,12 @@ again: } goto fail; } - - ret = btrfs_find_dead_roots(fs_info->tree_root, - root->root_key.objectid); - WARN_ON(ret); return root; fail: free_fs_root(root); return ERR_PTR(ret); } -struct btrfs_root *btrfs_read_fs_root(struct btrfs_fs_info *fs_info, - struct btrfs_key *location, - const char *name, int namelen) -{ - return btrfs_read_fs_root_no_name(fs_info, location); -#if 0 - struct btrfs_root *root; - int ret; - - root = btrfs_read_fs_root_no_name(fs_info, location); - if (!root) - return NULL; - - if (root->in_sysfs) - return root; - - ret = btrfs_set_root_name(root, name, namelen); - if (ret) { - free_extent_buffer(root->node); - kfree(root); - return ERR_PTR(ret); - } - - ret = btrfs_sysfs_add_root(root); - if (ret) { - free_extent_buffer(root->node); - kfree(root->name); - kfree(root); - return ERR_PTR(ret); - } - root->in_sysfs = 1; - return root; -#endif -} - static int btrfs_congested_fn(void *congested_data, int bdi_bits) { struct btrfs_fs_info *info = (struct btrfs_fs_info *)congested_data; @@ -1262,7 +1691,8 @@ static int btrfs_congested_fn(void *congested_data, int bdi_bits) struct btrfs_device *device; struct backing_dev_info *bdi; - list_for_each_entry(device, &info->fs_devices->devices, dev_list) { + rcu_read_lock(); + list_for_each_entry_rcu(device, &info->fs_devices->devices, dev_list) { if (!device->bdev) continue; bdi = blk_get_backing_dev_info(device->bdev); @@ -1271,86 +1701,11 @@ static int btrfs_congested_fn(void *congested_data, int bdi_bits) break; } } + rcu_read_unlock(); return ret; } /* - * this unplugs every device on the box, and it is only used when page - * is null - */ -static void __unplug_io_fn(struct backing_dev_info *bdi, struct page *page) -{ - struct btrfs_device *device; - struct btrfs_fs_info *info; - - info = (struct btrfs_fs_info *)bdi->unplug_io_data; - list_for_each_entry(device, &info->fs_devices->devices, dev_list) { - if (!device->bdev) - continue; - - bdi = blk_get_backing_dev_info(device->bdev); - if (bdi->unplug_io_fn) - bdi->unplug_io_fn(bdi, page); - } -} - -static void btrfs_unplug_io_fn(struct backing_dev_info *bdi, struct page *page) -{ - struct inode *inode; - struct extent_map_tree *em_tree; - struct extent_map *em; - struct address_space *mapping; - u64 offset; - - /* the generic O_DIRECT read code does this */ - if (1 || !page) { - __unplug_io_fn(bdi, page); - return; - } - - /* - * page->mapping may change at any time. Get a consistent copy - * and use that for everything below - */ - smp_mb(); - mapping = page->mapping; - if (!mapping) - return; - - inode = mapping->host; - - /* - * don't do the expensive searching for a small number of - * devices - */ - if (BTRFS_I(inode)->root->fs_info->fs_devices->open_devices <= 2) { - __unplug_io_fn(bdi, page); - return; - } - - offset = page_offset(page); - - em_tree = &BTRFS_I(inode)->extent_tree; - read_lock(&em_tree->lock); - em = lookup_extent_mapping(em_tree, offset, PAGE_CACHE_SIZE); - read_unlock(&em_tree->lock); - if (!em) { - __unplug_io_fn(bdi, page); - return; - } - - if (em->block_start >= EXTENT_MAP_LAST_BYTE) { - free_extent_map(em); - __unplug_io_fn(bdi, page); - return; - } - offset = offset - em->start; - btrfs_unplug_page(&BTRFS_I(inode)->root->fs_info->mapping_tree, - em->block_start + offset, page); - free_extent_map(em); -} - -/* * If this fails, caller must call bdi_destroy() to get rid of the * bdi again. */ @@ -1364,48 +1719,11 @@ static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi) return err; bdi->ra_pages = default_backing_dev_info.ra_pages; - bdi->unplug_io_fn = btrfs_unplug_io_fn; - bdi->unplug_io_data = info; bdi->congested_fn = btrfs_congested_fn; bdi->congested_data = info; return 0; } -static int bio_ready_for_csum(struct bio *bio) -{ - u64 length = 0; - u64 buf_len = 0; - u64 start = 0; - struct page *page; - struct extent_io_tree *io_tree = NULL; - struct bio_vec *bvec; - int i; - int ret; - - bio_for_each_segment(bvec, bio, i) { - page = bvec->bv_page; - if (page->private == EXTENT_PAGE_PRIVATE) { - length += bvec->bv_len; - continue; - } - if (!page->private) { - length += bvec->bv_len; - continue; - } - length = bvec->bv_len; - buf_len = page->private >> 2; - start = page_offset(page) + bvec->bv_offset; - io_tree = &BTRFS_I(page->mapping->host)->io_tree; - } - /* are we fully contained in this bio? */ - if (buf_len <= length) - return 1; - - ret = extent_range_uptodate(io_tree, start + length, - start + buf_len - 1); - return ret; -} - /* * called by the kthread helper functions to finally call the bio end_io * functions. This is where read checksum verification actually happens @@ -1414,48 +1732,53 @@ static void end_workqueue_fn(struct btrfs_work *work) { struct bio *bio; struct end_io_wq *end_io_wq; - struct btrfs_fs_info *fs_info; int error; end_io_wq = container_of(work, struct end_io_wq, work); bio = end_io_wq->bio; - fs_info = end_io_wq->info; - /* metadata bio reads are special because the whole tree block must - * be checksummed at once. This makes sure the entire block is in - * ram and up to date before trying to verify things. For - * blocksize <= pagesize, it is basically a noop - */ - if (!(bio->bi_rw & REQ_WRITE) && end_io_wq->metadata && - !bio_ready_for_csum(bio)) { - btrfs_queue_worker(&fs_info->endio_meta_workers, - &end_io_wq->work); - return; - } error = end_io_wq->error; bio->bi_private = end_io_wq->private; bio->bi_end_io = end_io_wq->end_io; kfree(end_io_wq); - bio_endio(bio, error); + bio_endio_nodec(bio, error); } static int cleaner_kthread(void *arg) { struct btrfs_root *root = arg; + int again; do { - vfs_check_frozen(root->fs_info->sb, SB_FREEZE_WRITE); + again = 0; + + /* Make the cleaner go to sleep early. */ + if (btrfs_need_cleaner_sleep(root)) + goto sleep; + + if (!mutex_trylock(&root->fs_info->cleaner_mutex)) + goto sleep; - if (!(root->fs_info->sb->s_flags & MS_RDONLY) && - mutex_trylock(&root->fs_info->cleaner_mutex)) { - btrfs_run_delayed_iputs(root); - btrfs_clean_old_snapshots(root); + /* + * Avoid the problem that we change the status of the fs + * during the above check and trylock. + */ + if (btrfs_need_cleaner_sleep(root)) { mutex_unlock(&root->fs_info->cleaner_mutex); + goto sleep; } - if (freezing(current)) { - refrigerator(); - } else { + btrfs_run_delayed_iputs(root); + again = btrfs_clean_one_deleted_snapshot(root); + mutex_unlock(&root->fs_info->cleaner_mutex); + + /* + * The defragger has dealt with the R/O remount and umount, + * needn't do anything special here. + */ + btrfs_run_defrag_inodes(root->fs_info); +sleep: + if (!try_to_freeze() && !again) { set_current_state(TASK_INTERRUPTIBLE); if (!kthread_should_stop()) schedule(); @@ -1473,34 +1796,40 @@ static int transaction_kthread(void *arg) u64 transid; unsigned long now; unsigned long delay; - int ret; + bool cannot_commit; do { - delay = HZ * 30; - vfs_check_frozen(root->fs_info->sb, SB_FREEZE_WRITE); + cannot_commit = false; + delay = HZ * root->fs_info->commit_interval; mutex_lock(&root->fs_info->transaction_kthread_mutex); - spin_lock(&root->fs_info->new_trans_lock); + spin_lock(&root->fs_info->trans_lock); cur = root->fs_info->running_transaction; if (!cur) { - spin_unlock(&root->fs_info->new_trans_lock); + spin_unlock(&root->fs_info->trans_lock); goto sleep; } now = get_seconds(); - if (!cur->blocked && - (now < cur->start_time || now - cur->start_time < 30)) { - spin_unlock(&root->fs_info->new_trans_lock); + if (cur->state < TRANS_STATE_BLOCKED && + (now < cur->start_time || + now - cur->start_time < root->fs_info->commit_interval)) { + spin_unlock(&root->fs_info->trans_lock); delay = HZ * 5; goto sleep; } transid = cur->transid; - spin_unlock(&root->fs_info->new_trans_lock); + spin_unlock(&root->fs_info->trans_lock); - trans = btrfs_join_transaction(root, 1); + /* If the file system is aborted, this will always fail. */ + trans = btrfs_attach_transaction(root); + if (IS_ERR(trans)) { + if (PTR_ERR(trans) != -ENOENT) + cannot_commit = true; + goto sleep; + } if (transid == trans->transid) { - ret = btrfs_commit_transaction(trans, root); - BUG_ON(ret); + btrfs_commit_transaction(trans, root); } else { btrfs_end_transaction(trans, root); } @@ -1508,12 +1837,14 @@ sleep: wake_up_process(root->fs_info->cleaner_kthread); mutex_unlock(&root->fs_info->transaction_kthread_mutex); - if (freezing(current)) { - refrigerator(); - } else { + if (unlikely(test_bit(BTRFS_FS_STATE_ERROR, + &root->fs_info->fs_state))) + btrfs_cleanup_transaction(root); + if (!try_to_freeze()) { set_current_state(TASK_INTERRUPTIBLE); if (!kthread_should_stop() && - !btrfs_transaction_blocked(root->fs_info)) + (!btrfs_transaction_blocked(root->fs_info) || + cannot_commit)) schedule_timeout(delay); __set_current_state(TASK_RUNNING); } @@ -1521,9 +1852,291 @@ sleep: return 0; } -struct btrfs_root *open_ctree(struct super_block *sb, - struct btrfs_fs_devices *fs_devices, - char *options) +/* + * 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)); + + /* + * we might commit during log recovery, which happens before we set + * the fs_root. Make sure it is valid before we fill it in. + */ + if (info->fs_root && info->fs_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 workers */ +static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info) +{ + btrfs_destroy_workqueue(fs_info->fixup_workers); + btrfs_destroy_workqueue(fs_info->delalloc_workers); + btrfs_destroy_workqueue(fs_info->workers); + btrfs_destroy_workqueue(fs_info->endio_workers); + btrfs_destroy_workqueue(fs_info->endio_meta_workers); + btrfs_destroy_workqueue(fs_info->endio_raid56_workers); + btrfs_destroy_workqueue(fs_info->rmw_workers); + btrfs_destroy_workqueue(fs_info->endio_meta_write_workers); + btrfs_destroy_workqueue(fs_info->endio_write_workers); + btrfs_destroy_workqueue(fs_info->endio_freespace_worker); + btrfs_destroy_workqueue(fs_info->submit_workers); + btrfs_destroy_workqueue(fs_info->delayed_workers); + btrfs_destroy_workqueue(fs_info->caching_workers); + btrfs_destroy_workqueue(fs_info->readahead_workers); + btrfs_destroy_workqueue(fs_info->flush_workers); + btrfs_destroy_workqueue(fs_info->qgroup_rescan_workers); + btrfs_destroy_workqueue(fs_info->extent_workers); +} + +static void free_root_extent_buffers(struct btrfs_root *root) +{ + if (root) { + free_extent_buffer(root->node); + free_extent_buffer(root->commit_root); + root->node = NULL; + root->commit_root = NULL; + } +} + +/* helper to cleanup tree roots */ +static void free_root_pointers(struct btrfs_fs_info *info, int chunk_root) +{ + free_root_extent_buffers(info->tree_root); + + free_root_extent_buffers(info->dev_root); + free_root_extent_buffers(info->extent_root); + free_root_extent_buffers(info->csum_root); + free_root_extent_buffers(info->quota_root); + free_root_extent_buffers(info->uuid_root); + if (chunk_root) + free_root_extent_buffers(info->chunk_root); +} + +void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info) +{ + int ret; + struct btrfs_root *gang[8]; + int i; + + while (!list_empty(&fs_info->dead_roots)) { + gang[0] = list_entry(fs_info->dead_roots.next, + struct btrfs_root, root_list); + list_del(&gang[0]->root_list); + + if (test_bit(BTRFS_ROOT_IN_RADIX, &gang[0]->state)) { + btrfs_drop_and_free_fs_root(fs_info, gang[0]); + } else { + free_extent_buffer(gang[0]->node); + free_extent_buffer(gang[0]->commit_root); + btrfs_put_fs_root(gang[0]); + } + } + + while (1) { + ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix, + (void **)gang, 0, + ARRAY_SIZE(gang)); + if (!ret) + break; + for (i = 0; i < ret; i++) + btrfs_drop_and_free_fs_root(fs_info, gang[i]); + } + + if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) { + btrfs_free_log_root_tree(NULL, fs_info); + btrfs_destroy_pinned_extent(fs_info->tree_root, + fs_info->pinned_extents); + } +} + +int open_ctree(struct super_block *sb, + struct btrfs_fs_devices *fs_devices, + char *options) { u32 sectorsize; u32 nodesize; @@ -1534,27 +2147,28 @@ struct btrfs_root *open_ctree(struct super_block *sb, u64 features; struct btrfs_key location; struct buffer_head *bh; - struct btrfs_root *extent_root = kzalloc(sizeof(struct btrfs_root), - GFP_NOFS); - struct btrfs_root *csum_root = kzalloc(sizeof(struct btrfs_root), - GFP_NOFS); - struct btrfs_root *tree_root = kzalloc(sizeof(struct btrfs_root), - GFP_NOFS); - struct btrfs_fs_info *fs_info = kzalloc(sizeof(*fs_info), - GFP_NOFS); - struct btrfs_root *chunk_root = kzalloc(sizeof(struct btrfs_root), - GFP_NOFS); - struct btrfs_root *dev_root = kzalloc(sizeof(struct btrfs_root), - GFP_NOFS); + struct btrfs_super_block *disk_super; + struct btrfs_fs_info *fs_info = btrfs_sb(sb); + struct btrfs_root *tree_root; + struct btrfs_root *extent_root; + struct btrfs_root *csum_root; + struct btrfs_root *chunk_root; + struct btrfs_root *dev_root; + struct btrfs_root *quota_root; + struct btrfs_root *uuid_root; struct btrfs_root *log_tree_root; - int ret; int err = -EINVAL; - - struct btrfs_super_block *disk_super; - - if (!extent_root || !tree_root || !fs_info || - !chunk_root || !dev_root || !csum_root) { + int num_backups_tried = 0; + int backup_index = 0; + int max_active; + int flags = WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_UNBOUND; + bool create_uuid_tree; + bool check_uuid_tree; + + tree_root = fs_info->tree_root = btrfs_alloc_root(fs_info); + chunk_root = fs_info->chunk_root = btrfs_alloc_root(fs_info); + if (!tree_root || !chunk_root) { err = -ENOMEM; goto fail; } @@ -1571,63 +2185,129 @@ struct btrfs_root *open_ctree(struct super_block *sb, goto fail_srcu; } + ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0); + if (ret) { + err = ret; + goto fail_bdi; + } + fs_info->dirty_metadata_batch = PAGE_CACHE_SIZE * + (1 + ilog2(nr_cpu_ids)); + + ret = percpu_counter_init(&fs_info->delalloc_bytes, 0); + if (ret) { + err = ret; + goto fail_dirty_metadata_bytes; + } + + ret = percpu_counter_init(&fs_info->bio_counter, 0); + if (ret) { + err = ret; + goto fail_delalloc_bytes; + } + fs_info->btree_inode = new_inode(sb); if (!fs_info->btree_inode) { err = -ENOMEM; - goto fail_bdi; + goto fail_bio_counter; } + mapping_set_gfp_mask(fs_info->btree_inode->i_mapping, GFP_NOFS); + INIT_RADIX_TREE(&fs_info->fs_roots_radix, GFP_ATOMIC); + INIT_RADIX_TREE(&fs_info->buffer_radix, GFP_ATOMIC); INIT_LIST_HEAD(&fs_info->trans_list); INIT_LIST_HEAD(&fs_info->dead_roots); INIT_LIST_HEAD(&fs_info->delayed_iputs); - INIT_LIST_HEAD(&fs_info->hashers); - INIT_LIST_HEAD(&fs_info->delalloc_inodes); - INIT_LIST_HEAD(&fs_info->ordered_operations); + INIT_LIST_HEAD(&fs_info->delalloc_roots); INIT_LIST_HEAD(&fs_info->caching_block_groups); - spin_lock_init(&fs_info->delalloc_lock); - spin_lock_init(&fs_info->new_trans_lock); - spin_lock_init(&fs_info->ref_cache_lock); + spin_lock_init(&fs_info->delalloc_root_lock); + spin_lock_init(&fs_info->trans_lock); 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); + spin_lock_init(&fs_info->tree_mod_seq_lock); + spin_lock_init(&fs_info->super_lock); + spin_lock_init(&fs_info->qgroup_op_lock); + spin_lock_init(&fs_info->buffer_lock); + rwlock_init(&fs_info->tree_mod_log_lock); + mutex_init(&fs_info->reloc_mutex); + mutex_init(&fs_info->delalloc_root_mutex); + seqlock_init(&fs_info->profiles_lock); init_completion(&fs_info->kobj_unregister); - fs_info->tree_root = tree_root; - fs_info->extent_root = extent_root; - fs_info->csum_root = csum_root; - fs_info->chunk_root = chunk_root; - fs_info->dev_root = dev_root; - fs_info->fs_devices = fs_devices; INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots); INIT_LIST_HEAD(&fs_info->space_info); + INIT_LIST_HEAD(&fs_info->tree_mod_seq_list); btrfs_mapping_init(&fs_info->mapping_tree); - btrfs_init_block_rsv(&fs_info->global_block_rsv); - btrfs_init_block_rsv(&fs_info->delalloc_block_rsv); - 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->global_block_rsv, + BTRFS_BLOCK_RSV_GLOBAL); + btrfs_init_block_rsv(&fs_info->delalloc_block_rsv, + BTRFS_BLOCK_RSV_DELALLOC); + btrfs_init_block_rsv(&fs_info->trans_block_rsv, BTRFS_BLOCK_RSV_TRANS); + btrfs_init_block_rsv(&fs_info->chunk_block_rsv, BTRFS_BLOCK_RSV_CHUNK); + btrfs_init_block_rsv(&fs_info->empty_block_rsv, BTRFS_BLOCK_RSV_EMPTY); + btrfs_init_block_rsv(&fs_info->delayed_block_rsv, + BTRFS_BLOCK_RSV_DELOPS); atomic_set(&fs_info->nr_async_submits, 0); atomic_set(&fs_info->async_delalloc_pages, 0); atomic_set(&fs_info->async_submit_draining, 0); atomic_set(&fs_info->nr_async_bios, 0); + atomic_set(&fs_info->defrag_running, 0); + atomic_set(&fs_info->qgroup_op_seq, 0); + atomic64_set(&fs_info->tree_mod_seq, 0); fs_info->sb = sb; fs_info->max_inline = 8192 * 1024; fs_info->metadata_ratio = 0; + fs_info->defrag_inodes = RB_ROOT; + fs_info->free_chunk_space = 0; + fs_info->tree_mod_log = RB_ROOT; + fs_info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL; + fs_info->avg_delayed_ref_runtime = div64_u64(NSEC_PER_SEC, 64); + /* 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); - INIT_LIST_HEAD(&fs_info->ordered_extents); - spin_lock_init(&fs_info->ordered_extent_lock); + INIT_LIST_HEAD(&fs_info->ordered_roots); + spin_lock_init(&fs_info->ordered_root_lock); + fs_info->delayed_root = kmalloc(sizeof(struct btrfs_delayed_root), + GFP_NOFS); + if (!fs_info->delayed_root) { + err = -ENOMEM; + goto fail_iput; + } + btrfs_init_delayed_root(fs_info->delayed_root); + + mutex_init(&fs_info->scrub_lock); + atomic_set(&fs_info->scrubs_running, 0); + atomic_set(&fs_info->scrub_pause_req, 0); + atomic_set(&fs_info->scrubs_paused, 0); + atomic_set(&fs_info->scrub_cancel_req, 0); + init_waitqueue_head(&fs_info->replace_wait); + init_waitqueue_head(&fs_info->scrub_pause_wait); + 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); + btrfs_init_async_reclaim_work(&fs_info->async_reclaim_work); 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 @@ -1639,40 +2319,58 @@ struct btrfs_root *open_ctree(struct super_block *sb, RB_CLEAR_NODE(&BTRFS_I(fs_info->btree_inode)->rb_node); extent_io_tree_init(&BTRFS_I(fs_info->btree_inode)->io_tree, - fs_info->btree_inode->i_mapping, - GFP_NOFS); - extent_map_tree_init(&BTRFS_I(fs_info->btree_inode)->extent_tree, - GFP_NOFS); + fs_info->btree_inode->i_mapping); + BTRFS_I(fs_info->btree_inode)->io_tree.track_uptodate = 0; + extent_map_tree_init(&BTRFS_I(fs_info->btree_inode)->extent_tree); BTRFS_I(fs_info->btree_inode)->io_tree.ops = &btree_extent_io_ops; BTRFS_I(fs_info->btree_inode)->root = tree_root; memset(&BTRFS_I(fs_info->btree_inode)->location, 0, sizeof(struct btrfs_key)); - BTRFS_I(fs_info->btree_inode)->dummy_inode = 1; - insert_inode_hash(fs_info->btree_inode); + set_bit(BTRFS_INODE_DUMMY, + &BTRFS_I(fs_info->btree_inode)->runtime_flags); + btrfs_insert_inode_hash(fs_info->btree_inode); spin_lock_init(&fs_info->block_group_cache_lock); fs_info->block_group_cache_tree = RB_ROOT; + fs_info->first_logical_byte = (u64)-1; extent_io_tree_init(&fs_info->freed_extents[0], - fs_info->btree_inode->i_mapping, GFP_NOFS); + fs_info->btree_inode->i_mapping); extent_io_tree_init(&fs_info->freed_extents[1], - fs_info->btree_inode->i_mapping, GFP_NOFS); + fs_info->btree_inode->i_mapping); fs_info->pinned_extents = &fs_info->freed_extents[0]; fs_info->do_barriers = 1; - mutex_init(&fs_info->trans_mutex); mutex_init(&fs_info->ordered_operations_mutex); + mutex_init(&fs_info->ordered_extent_flush_mutex); mutex_init(&fs_info->tree_log_mutex); mutex_init(&fs_info->chunk_mutex); mutex_init(&fs_info->transaction_kthread_mutex); mutex_init(&fs_info->cleaner_mutex); mutex_init(&fs_info->volume_mutex); - init_rwsem(&fs_info->extent_commit_sem); + init_rwsem(&fs_info->commit_root_sem); init_rwsem(&fs_info->cleanup_work_sem); init_rwsem(&fs_info->subvol_sem); + sema_init(&fs_info->uuid_tree_rescan_sem, 1); + fs_info->dev_replace.lock_owner = 0; + atomic_set(&fs_info->dev_replace.nesting_level, 0); + mutex_init(&fs_info->dev_replace.lock_finishing_cancel_unmount); + mutex_init(&fs_info->dev_replace.lock_management_lock); + mutex_init(&fs_info->dev_replace.lock); + + spin_lock_init(&fs_info->qgroup_lock); + mutex_init(&fs_info->qgroup_ioctl_lock); + fs_info->qgroup_tree = RB_ROOT; + fs_info->qgroup_op_tree = RB_ROOT; + INIT_LIST_HEAD(&fs_info->dirty_qgroups); + fs_info->qgroup_seq = 1; + fs_info->quota_enabled = 0; + fs_info->pending_quota_state = 0; + fs_info->qgroup_ulist = NULL; + mutex_init(&fs_info->qgroup_rescan_lock); btrfs_init_free_cluster(&fs_info->meta_alloc_cluster); btrfs_init_free_cluster(&fs_info->data_alloc_cluster); @@ -1682,28 +2380,80 @@ struct btrfs_root *open_ctree(struct super_block *sb, init_waitqueue_head(&fs_info->transaction_blocked_wait); init_waitqueue_head(&fs_info->async_submit_wait); + ret = btrfs_alloc_stripe_hash_table(fs_info); + if (ret) { + err = ret; + goto fail_alloc; + } + __setup_root(4096, 4096, 4096, 4096, tree_root, fs_info, BTRFS_ROOT_TREE_OBJECTID); + invalidate_bdev(fs_devices->latest_bdev); + + /* + * Read super block and check the signature bytes only + */ bh = btrfs_read_dev_super(fs_devices->latest_bdev); - if (!bh) - goto fail_iput; + if (!bh) { + err = -EINVAL; + goto fail_alloc; + } + + /* + * We want to check superblock checksum, the type is stored inside. + * Pass the whole disk block of size BTRFS_SUPER_INFO_SIZE (4k). + */ + if (btrfs_check_super_csum(bh->b_data)) { + printk(KERN_ERR "BTRFS: superblock checksum mismatch\n"); + err = -EINVAL; + 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)); + /* + * super_copy is zeroed at allocation time and we never touch the + * following bytes up to INFO_SIZE, the checksum is calculated from + * the whole block of INFO_SIZE + */ + 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; + ret = btrfs_check_super_valid(fs_info, sb->s_flags & MS_RDONLY); + if (ret) { + printk(KERN_ERR "BTRFS: superblock contains fatal errors\n"); + err = -EINVAL; + goto fail_alloc; + } + + disk_super = fs_info->super_copy; if (!btrfs_super_root(disk_super)) - goto fail_iput; + goto fail_alloc; + + /* check FS state, whether FS is broken. */ + if (btrfs_super_flags(disk_super) & BTRFS_SUPER_FLAG_ERROR) + set_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state); + + /* + * 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. + */ + fs_info->compress_type = BTRFS_COMPRESS_ZLIB; ret = btrfs_parse_options(tree_root, options); if (ret) { err = ret; - goto fail_iput; + goto fail_alloc; } features = btrfs_super_incompat_flags(disk_super) & @@ -1711,101 +2461,156 @@ struct btrfs_root *open_ctree(struct super_block *sb, if (features) { printk(KERN_ERR "BTRFS: couldn't mount because of " "unsupported optional features (%Lx).\n", - (unsigned long long)features); + features); err = -EINVAL; - goto fail_iput; + goto fail_alloc; + } + + if (btrfs_super_leafsize(disk_super) != + btrfs_super_nodesize(disk_super)) { + printk(KERN_ERR "BTRFS: couldn't mount because metadata " + "blocksizes don't match. node %d leaf %d\n", + btrfs_super_nodesize(disk_super), + btrfs_super_leafsize(disk_super)); + err = -EINVAL; + goto fail_alloc; + } + if (btrfs_super_leafsize(disk_super) > BTRFS_MAX_METADATA_BLOCKSIZE) { + printk(KERN_ERR "BTRFS: couldn't mount because metadata " + "blocksize (%d) was too large\n", + btrfs_super_leafsize(disk_super)); + err = -EINVAL; + goto fail_alloc; } features = btrfs_super_incompat_flags(disk_super); - if (!(features & BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF)) { - features |= BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF; - btrfs_set_super_incompat_flags(disk_super, features); + features |= BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF; + if (tree_root->fs_info->compress_type == BTRFS_COMPRESS_LZO) + features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO; + + if (features & BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA) + printk(KERN_ERR "BTRFS: has skinny extents\n"); + + /* + * flag our filesystem as having big metadata blocks if + * they are bigger than the page size + */ + if (btrfs_super_leafsize(disk_super) > PAGE_CACHE_SIZE) { + if (!(features & BTRFS_FEATURE_INCOMPAT_BIG_METADATA)) + printk(KERN_INFO "BTRFS: flagging fs with big metadata feature\n"); + features |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA; } + nodesize = btrfs_super_nodesize(disk_super); + leafsize = btrfs_super_leafsize(disk_super); + sectorsize = btrfs_super_sectorsize(disk_super); + stripesize = btrfs_super_stripesize(disk_super); + fs_info->dirty_metadata_batch = leafsize * (1 + ilog2(nr_cpu_ids)); + fs_info->delalloc_batch = sectorsize * 512 * (1 + ilog2(nr_cpu_ids)); + + /* + * mixed block groups end up with duplicate but slightly offset + * extent buffers for the same range. It leads to corruptions + */ + if ((features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) && + (sectorsize != leafsize)) { + printk(KERN_WARNING "BTRFS: unequal leaf/node/sector sizes " + "are not allowed for mixed block groups on %s\n", + sb->s_id); + goto fail_alloc; + } + + /* + * Needn't use the lock because there is no other task which will + * update the flag. + */ + btrfs_set_super_incompat_flags(disk_super, features); + features = btrfs_super_compat_ro_flags(disk_super) & ~BTRFS_FEATURE_COMPAT_RO_SUPP; if (!(sb->s_flags & MS_RDONLY) && features) { printk(KERN_ERR "BTRFS: couldn't mount RDWR because of " "unsupported option features (%Lx).\n", - (unsigned long long)features); + features); err = -EINVAL; - goto fail_iput; + goto fail_alloc; } - btrfs_init_workers(&fs_info->generic_worker, - "genwork", 1, NULL); + max_active = fs_info->thread_pool_size; + + fs_info->workers = + btrfs_alloc_workqueue("worker", flags | WQ_HIGHPRI, + max_active, 16); - btrfs_init_workers(&fs_info->workers, "worker", - fs_info->thread_pool_size, - &fs_info->generic_worker); + fs_info->delalloc_workers = + btrfs_alloc_workqueue("delalloc", flags, max_active, 2); - btrfs_init_workers(&fs_info->delalloc_workers, "delalloc", - fs_info->thread_pool_size, - &fs_info->generic_worker); + fs_info->flush_workers = + btrfs_alloc_workqueue("flush_delalloc", flags, max_active, 0); - btrfs_init_workers(&fs_info->submit_workers, "submit", - min_t(u64, fs_devices->num_devices, - fs_info->thread_pool_size), - &fs_info->generic_worker); + fs_info->caching_workers = + btrfs_alloc_workqueue("cache", flags, max_active, 0); - /* a higher idle thresh on the submit workers makes it much more + /* + * a higher idle thresh on the submit workers makes it much more * likely that bios will be send down in a sane order to the * devices */ - fs_info->submit_workers.idle_thresh = 64; - - fs_info->workers.idle_thresh = 16; - fs_info->workers.ordered = 1; - - fs_info->delalloc_workers.idle_thresh = 2; - fs_info->delalloc_workers.ordered = 1; - - btrfs_init_workers(&fs_info->fixup_workers, "fixup", 1, - &fs_info->generic_worker); - btrfs_init_workers(&fs_info->endio_workers, "endio", - fs_info->thread_pool_size, - &fs_info->generic_worker); - btrfs_init_workers(&fs_info->endio_meta_workers, "endio-meta", - fs_info->thread_pool_size, - &fs_info->generic_worker); - btrfs_init_workers(&fs_info->endio_meta_write_workers, - "endio-meta-write", fs_info->thread_pool_size, - &fs_info->generic_worker); - btrfs_init_workers(&fs_info->endio_write_workers, "endio-write", - fs_info->thread_pool_size, - &fs_info->generic_worker); - btrfs_init_workers(&fs_info->endio_freespace_worker, "freespace-write", - 1, &fs_info->generic_worker); + fs_info->submit_workers = + btrfs_alloc_workqueue("submit", flags, + min_t(u64, fs_devices->num_devices, + max_active), 64); + + fs_info->fixup_workers = + btrfs_alloc_workqueue("fixup", flags, 1, 0); /* * endios are largely parallel and should have a very * low idle thresh */ - fs_info->endio_workers.idle_thresh = 4; - fs_info->endio_meta_workers.idle_thresh = 4; - - fs_info->endio_write_workers.idle_thresh = 2; - fs_info->endio_meta_write_workers.idle_thresh = 2; - - btrfs_start_workers(&fs_info->workers, 1); - btrfs_start_workers(&fs_info->generic_worker, 1); - btrfs_start_workers(&fs_info->submit_workers, 1); - btrfs_start_workers(&fs_info->delalloc_workers, 1); - btrfs_start_workers(&fs_info->fixup_workers, 1); - btrfs_start_workers(&fs_info->endio_workers, 1); - btrfs_start_workers(&fs_info->endio_meta_workers, 1); - btrfs_start_workers(&fs_info->endio_meta_write_workers, 1); - btrfs_start_workers(&fs_info->endio_write_workers, 1); - btrfs_start_workers(&fs_info->endio_freespace_worker, 1); + fs_info->endio_workers = + btrfs_alloc_workqueue("endio", flags, max_active, 4); + fs_info->endio_meta_workers = + btrfs_alloc_workqueue("endio-meta", flags, max_active, 4); + fs_info->endio_meta_write_workers = + btrfs_alloc_workqueue("endio-meta-write", flags, max_active, 2); + fs_info->endio_raid56_workers = + btrfs_alloc_workqueue("endio-raid56", flags, max_active, 4); + fs_info->rmw_workers = + btrfs_alloc_workqueue("rmw", flags, max_active, 2); + fs_info->endio_write_workers = + btrfs_alloc_workqueue("endio-write", flags, max_active, 2); + fs_info->endio_freespace_worker = + btrfs_alloc_workqueue("freespace-write", flags, max_active, 0); + fs_info->delayed_workers = + btrfs_alloc_workqueue("delayed-meta", flags, max_active, 0); + fs_info->readahead_workers = + btrfs_alloc_workqueue("readahead", flags, max_active, 2); + fs_info->qgroup_rescan_workers = + btrfs_alloc_workqueue("qgroup-rescan", flags, 1, 0); + fs_info->extent_workers = + btrfs_alloc_workqueue("extent-refs", flags, + min_t(u64, fs_devices->num_devices, + max_active), 8); + + if (!(fs_info->workers && fs_info->delalloc_workers && + fs_info->submit_workers && fs_info->flush_workers && + fs_info->endio_workers && fs_info->endio_meta_workers && + fs_info->endio_meta_write_workers && + fs_info->endio_write_workers && fs_info->endio_raid56_workers && + fs_info->endio_freespace_worker && fs_info->rmw_workers && + fs_info->caching_workers && fs_info->readahead_workers && + fs_info->fixup_workers && fs_info->delayed_workers && + fs_info->fixup_workers && fs_info->extent_workers && + fs_info->qgroup_rescan_workers)) { + err = -ENOMEM; + goto fail_sb_buffer; + } fs_info->bdi.ra_pages *= btrfs_super_num_devices(disk_super); fs_info->bdi.ra_pages = max(fs_info->bdi.ra_pages, 4 * 1024 * 1024 / PAGE_CACHE_SIZE); - nodesize = btrfs_super_nodesize(disk_super); - leafsize = btrfs_super_leafsize(disk_super); - sectorsize = btrfs_super_sectorsize(disk_super); - stripesize = btrfs_super_stripesize(disk_super); tree_root->nodesize = nodesize; tree_root->leafsize = leafsize; tree_root->sectorsize = sectorsize; @@ -1814,9 +2619,14 @@ struct btrfs_root *open_ctree(struct super_block *sb, sb->s_blocksize = sectorsize; sb->s_blocksize_bits = blksize_bits(sectorsize); - if (strncmp((char *)(&disk_super->magic), BTRFS_MAGIC, - sizeof(disk_super->magic))) { - printk(KERN_INFO "btrfs: valid FS not found on %s\n", sb->s_id); + if (btrfs_super_magic(disk_super) != BTRFS_MAGIC) { + printk(KERN_INFO "BTRFS: valid FS not found on %s\n", sb->s_id); + goto fail_sb_buffer; + } + + if (sectorsize != PAGE_SIZE) { + printk(KERN_WARNING "BTRFS: Incompatible sector size(%lu) " + "found on %s\n", (unsigned long)sectorsize, sb->s_id); goto fail_sb_buffer; } @@ -1824,7 +2634,7 @@ struct btrfs_root *open_ctree(struct super_block *sb, ret = btrfs_read_sys_array(tree_root); mutex_unlock(&fs_info->chunk_mutex); if (ret) { - printk(KERN_WARNING "btrfs: failed to read the system " + printk(KERN_WARNING "BTRFS: failed to read the system " "array on %s\n", sb->s_id); goto fail_sb_buffer; } @@ -1839,30 +2649,38 @@ struct btrfs_root *open_ctree(struct super_block *sb, chunk_root->node = read_tree_block(chunk_root, btrfs_super_chunk_root(disk_super), blocksize, generation); - BUG_ON(!chunk_root->node); - if (!test_bit(EXTENT_BUFFER_UPTODATE, &chunk_root->node->bflags)) { - printk(KERN_WARNING "btrfs: failed to read chunk root on %s\n", + if (!chunk_root->node || + !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); read_extent_buffer(chunk_root->node, fs_info->chunk_tree_uuid, - (unsigned long)btrfs_header_chunk_tree_uuid(chunk_root->node), - BTRFS_UUID_SIZE); + 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", + 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); + /* + * keep the device that is marked to be the target device for the + * dev_replace procedure + */ + btrfs_close_extra_devices(fs_info, fs_devices, 0); + + if (!fs_devices->latest_bdev) { + printk(KERN_CRIT "BTRFS: failed to read devices on %s\n", + sb->s_id); + goto fail_tree_roots; + } +retry_root_backup: blocksize = btrfs_level_size(tree_root, btrfs_super_root_level(disk_super)); generation = btrfs_super_generation(disk_super); @@ -1870,51 +2688,129 @@ struct btrfs_root *open_ctree(struct super_block *sb, 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)) { - printk(KERN_WARNING "btrfs: failed to read tree root on %s\n", + 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); + btrfs_set_root_refs(&tree_root->root_item, 1); - ret = find_and_setup_root(tree_root, fs_info, - BTRFS_EXTENT_TREE_OBJECTID, extent_root); - if (ret) - goto fail_tree_root; - extent_root->track_dirty = 1; + location.objectid = BTRFS_EXTENT_TREE_OBJECTID; + location.type = BTRFS_ROOT_ITEM_KEY; + location.offset = 0; - ret = find_and_setup_root(tree_root, fs_info, - BTRFS_DEV_TREE_OBJECTID, dev_root); - if (ret) - goto fail_extent_root; - dev_root->track_dirty = 1; + extent_root = btrfs_read_tree_root(tree_root, &location); + if (IS_ERR(extent_root)) { + ret = PTR_ERR(extent_root); + goto recovery_tree_root; + } + set_bit(BTRFS_ROOT_TRACK_DIRTY, &extent_root->state); + fs_info->extent_root = extent_root; - ret = find_and_setup_root(tree_root, fs_info, - BTRFS_CSUM_TREE_OBJECTID, csum_root); - if (ret) - goto fail_dev_root; + location.objectid = BTRFS_DEV_TREE_OBJECTID; + dev_root = btrfs_read_tree_root(tree_root, &location); + if (IS_ERR(dev_root)) { + ret = PTR_ERR(dev_root); + goto recovery_tree_root; + } + set_bit(BTRFS_ROOT_TRACK_DIRTY, &dev_root->state); + fs_info->dev_root = dev_root; + btrfs_init_devices_late(fs_info); + + location.objectid = BTRFS_CSUM_TREE_OBJECTID; + csum_root = btrfs_read_tree_root(tree_root, &location); + if (IS_ERR(csum_root)) { + ret = PTR_ERR(csum_root); + goto recovery_tree_root; + } + set_bit(BTRFS_ROOT_TRACK_DIRTY, &csum_root->state); + fs_info->csum_root = csum_root; - csum_root->track_dirty = 1; + location.objectid = BTRFS_QUOTA_TREE_OBJECTID; + quota_root = btrfs_read_tree_root(tree_root, &location); + if (!IS_ERR(quota_root)) { + set_bit(BTRFS_ROOT_TRACK_DIRTY, "a_root->state); + fs_info->quota_enabled = 1; + fs_info->pending_quota_state = 1; + fs_info->quota_root = quota_root; + } + + location.objectid = BTRFS_UUID_TREE_OBJECTID; + uuid_root = btrfs_read_tree_root(tree_root, &location); + if (IS_ERR(uuid_root)) { + ret = PTR_ERR(uuid_root); + if (ret != -ENOENT) + goto recovery_tree_root; + create_uuid_tree = true; + check_uuid_tree = false; + } else { + set_bit(BTRFS_ROOT_TRACK_DIRTY, &uuid_root->state); + fs_info->uuid_root = uuid_root; + create_uuid_tree = false; + check_uuid_tree = + generation != btrfs_super_uuid_tree_generation(disk_super); + } 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_read_block_groups(extent_root); + ret = btrfs_recover_balance(fs_info); + if (ret) { + printk(KERN_WARNING "BTRFS: failed to recover balance\n"); + goto fail_block_groups; + } + + ret = btrfs_init_dev_stats(fs_info); if (ret) { - printk(KERN_ERR "Failed to read block groups: %d\n", ret); + printk(KERN_ERR "BTRFS: failed to init dev_stats: %d\n", + ret); goto fail_block_groups; } + ret = btrfs_init_dev_replace(fs_info); + if (ret) { + pr_err("BTRFS: failed to init dev_replace: %d\n", ret); + goto fail_block_groups; + } + + btrfs_close_extra_devices(fs_info, fs_devices, 1); + + ret = btrfs_sysfs_add_one(fs_info); + if (ret) { + pr_err("BTRFS: failed to init sysfs interface: %d\n", ret); + goto fail_block_groups; + } + + ret = btrfs_init_space_info(fs_info); + if (ret) { + printk(KERN_ERR "BTRFS: Failed to initial space info: %d\n", ret); + goto fail_sysfs; + } + + ret = btrfs_read_block_groups(extent_root); + if (ret) { + printk(KERN_ERR "BTRFS: Failed to read block groups: %d\n", ret); + goto fail_sysfs; + } + fs_info->num_tolerated_disk_barrier_failures = + btrfs_calc_num_tolerated_disk_barrier_failures(fs_info); + if (fs_info->fs_devices->missing_devices > + fs_info->num_tolerated_disk_barrier_failures && + !(sb->s_flags & MS_RDONLY)) { + printk(KERN_WARNING "BTRFS: " + "too many missing devices, writeable mount is not allowed\n"); + goto fail_sysfs; + } + fs_info->cleaner_kthread = kthread_run(cleaner_kthread, tree_root, "btrfs-cleaner"); if (IS_ERR(fs_info->cleaner_kthread)) - goto fail_block_groups; + goto fail_sysfs; fs_info->transaction_kthread = kthread_run(transaction_kthread, tree_root, @@ -1925,28 +2821,49 @@ struct btrfs_root *open_ctree(struct super_block *sb, if (!btrfs_test_opt(tree_root, SSD) && !btrfs_test_opt(tree_root, NOSSD) && !fs_info->fs_devices->rotating) { - printk(KERN_INFO "Btrfs detected SSD devices, enabling SSD " + printk(KERN_INFO "BTRFS: detected SSD devices, enabling SSD " "mode\n"); btrfs_set_opt(fs_info->mount_opt, SSD); } + /* Set the real inode map cache flag */ + if (btrfs_test_opt(tree_root, CHANGE_INODE_CACHE)) + btrfs_set_opt(tree_root->fs_info->mount_opt, INODE_MAP_CACHE); + +#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 + ret = btrfs_read_qgroup_config(fs_info); + if (ret) + goto fail_trans_kthread; + + /* do not make disk changes in broken FS */ if (btrfs_super_log_root(disk_super) != 0) { u64 bytenr = btrfs_super_log_root(disk_super); if (fs_devices->rw_devices == 0) { - printk(KERN_WARNING "Btrfs log replay required " + printk(KERN_WARNING "BTRFS: log replay required " "on RO media\n"); err = -EIO; - goto fail_trans_kthread; + goto fail_qgroup; } blocksize = btrfs_level_size(tree_root, btrfs_super_log_root_level(disk_super)); - log_tree_root = kzalloc(sizeof(struct btrfs_root), GFP_NOFS); + log_tree_root = btrfs_alloc_root(fs_info); if (!log_tree_root) { err = -ENOMEM; - goto fail_trans_kthread; + goto fail_qgroup; } __setup_root(nodesize, leafsize, sectorsize, stripesize, @@ -1955,54 +2872,119 @@ struct btrfs_root *open_ctree(struct super_block *sb, log_tree_root->node = read_tree_block(tree_root, bytenr, blocksize, generation + 1); + if (!log_tree_root->node || + !extent_buffer_uptodate(log_tree_root->node)) { + printk(KERN_ERR "BTRFS: failed to read log tree\n"); + free_extent_buffer(log_tree_root->node); + kfree(log_tree_root); + goto fail_qgroup; + } + /* returns with log_tree_root freed on success */ ret = btrfs_recover_log_trees(log_tree_root); - BUG_ON(ret); + if (ret) { + btrfs_error(tree_root->fs_info, ret, + "Failed to recover log tree"); + free_extent_buffer(log_tree_root->node); + kfree(log_tree_root); + goto fail_qgroup; + } if (sb->s_flags & MS_RDONLY) { - ret = btrfs_commit_super(tree_root); - BUG_ON(ret); + ret = btrfs_commit_super(tree_root); + if (ret) + goto fail_qgroup; } } ret = btrfs_find_orphan_roots(tree_root); - BUG_ON(ret); + if (ret) + goto fail_qgroup; if (!(sb->s_flags & MS_RDONLY)) { ret = btrfs_cleanup_fs_roots(fs_info); - BUG_ON(ret); + if (ret) + goto fail_qgroup; + mutex_lock(&fs_info->cleaner_mutex); ret = btrfs_recover_relocation(tree_root); + mutex_unlock(&fs_info->cleaner_mutex); if (ret < 0) { printk(KERN_WARNING - "btrfs: failed to recover relocation\n"); + "BTRFS: failed to recover relocation\n"); err = -EINVAL; - goto fail_trans_kthread; + goto fail_qgroup; } } location.objectid = BTRFS_FS_TREE_OBJECTID; location.type = BTRFS_ROOT_ITEM_KEY; - location.offset = (u64)-1; + location.offset = 0; fs_info->fs_root = btrfs_read_fs_root_no_name(fs_info, &location); - if (!fs_info->fs_root) - goto fail_trans_kthread; if (IS_ERR(fs_info->fs_root)) { err = PTR_ERR(fs_info->fs_root); - goto fail_trans_kthread; + goto fail_qgroup; } - if (!(sb->s_flags & MS_RDONLY)) { - down_read(&fs_info->cleanup_work_sem); - btrfs_orphan_cleanup(fs_info->fs_root); - btrfs_orphan_cleanup(fs_info->tree_root); + if (sb->s_flags & MS_RDONLY) + return 0; + + down_read(&fs_info->cleanup_work_sem); + if ((ret = btrfs_orphan_cleanup(fs_info->fs_root)) || + (ret = btrfs_orphan_cleanup(fs_info->tree_root))) { up_read(&fs_info->cleanup_work_sem); + close_ctree(tree_root); + return ret; } + up_read(&fs_info->cleanup_work_sem); - return tree_root; + ret = btrfs_resume_balance_async(fs_info); + if (ret) { + printk(KERN_WARNING "BTRFS: failed to resume balance\n"); + close_ctree(tree_root); + return ret; + } + + ret = btrfs_resume_dev_replace_async(fs_info); + if (ret) { + pr_warn("BTRFS: failed to resume dev_replace\n"); + close_ctree(tree_root); + return ret; + } + + btrfs_qgroup_rescan_resume(fs_info); + + if (create_uuid_tree) { + pr_info("BTRFS: creating UUID tree\n"); + ret = btrfs_create_uuid_tree(fs_info); + if (ret) { + pr_warn("BTRFS: failed to create the UUID tree %d\n", + ret); + close_ctree(tree_root); + return ret; + } + } else if (check_uuid_tree || + btrfs_test_opt(tree_root, RESCAN_UUID_TREE)) { + pr_info("BTRFS: checking UUID tree\n"); + ret = btrfs_check_uuid_tree(fs_info); + if (ret) { + pr_warn("BTRFS: failed to check the UUID tree %d\n", + ret); + close_ctree(tree_root); + return ret; + } + } else { + fs_info->update_uuid_tree_gen = 1; + } + + return 0; +fail_qgroup: + btrfs_free_qgroup_config(fs_info); fail_trans_kthread: kthread_stop(fs_info->transaction_kthread); + btrfs_cleanup_transaction(fs_info->tree_root); + btrfs_free_fs_roots(fs_info); fail_cleaner: kthread_stop(fs_info->cleaner_kthread); @@ -2011,71 +2993,75 @@ fail_cleaner: * kthreads */ filemap_write_and_wait(fs_info->btree_inode->i_mapping); - invalidate_inode_pages2(fs_info->btree_inode->i_mapping); + +fail_sysfs: + btrfs_sysfs_remove_one(fs_info); fail_block_groups: + btrfs_put_block_group_cache(fs_info); 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_sb_buffer: - btrfs_stop_workers(&fs_info->generic_worker); - btrfs_stop_workers(&fs_info->fixup_workers); - btrfs_stop_workers(&fs_info->delalloc_workers); - btrfs_stop_workers(&fs_info->workers); - btrfs_stop_workers(&fs_info->endio_workers); - btrfs_stop_workers(&fs_info->endio_meta_workers); - btrfs_stop_workers(&fs_info->endio_meta_write_workers); - btrfs_stop_workers(&fs_info->endio_write_workers); - btrfs_stop_workers(&fs_info->endio_freespace_worker); - btrfs_stop_workers(&fs_info->submit_workers); -fail_iput: + +fail_tree_roots: + free_root_pointers(fs_info, 1); invalidate_inode_pages2(fs_info->btree_inode->i_mapping); - iput(fs_info->btree_inode); - btrfs_close_devices(fs_info->fs_devices); +fail_sb_buffer: + btrfs_stop_all_workers(fs_info); +fail_alloc: +fail_iput: btrfs_mapping_tree_free(&fs_info->mapping_tree); + + iput(fs_info->btree_inode); +fail_bio_counter: + percpu_counter_destroy(&fs_info->bio_counter); +fail_delalloc_bytes: + percpu_counter_destroy(&fs_info->delalloc_bytes); +fail_dirty_metadata_bytes: + percpu_counter_destroy(&fs_info->dirty_metadata_bytes); fail_bdi: bdi_destroy(&fs_info->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); - return ERR_PTR(err); + btrfs_free_stripe_hash_table(fs_info); + btrfs_close_devices(fs_info->fs_devices); + return 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) { - char b[BDEVNAME_SIZE]; - if (uptodate) { set_buffer_uptodate(bh); } else { - if (printk_ratelimit()) { - printk(KERN_WARNING "lost page write due to " - "I/O error on %s\n", - bdevname(bh->b_bdev, b)); - } + struct btrfs_device *device = (struct btrfs_device *) + bh->b_private; + + printk_ratelimited_in_rcu(KERN_WARNING "BTRFS: lost page write due to " + "I/O error on %s\n", + rcu_str_deref(device->name)); /* note, we dont' set_buffer_write_io_error because we have * our own ways of dealing with the IO errors */ clear_buffer_uptodate(bh); + btrfs_dev_stat_inc_and_print(device, BTRFS_DEV_STAT_WRITE_ERRS); } unlock_buffer(bh); put_bh(bh); @@ -2097,16 +3083,17 @@ struct buffer_head *btrfs_read_dev_super(struct block_device *bdev) */ for (i = 0; i < 1; i++) { bytenr = btrfs_sb_offset(i); - if (bytenr + 4096 >= i_size_read(bdev->bd_inode)) + if (bytenr + BTRFS_SUPER_INFO_SIZE >= + i_size_read(bdev->bd_inode)) break; - bh = __bread(bdev, bytenr / 4096, 4096); + bh = __bread(bdev, bytenr / 4096, + BTRFS_SUPER_INFO_SIZE); if (!bh) continue; super = (struct btrfs_super_block *)bh->b_data; if (btrfs_super_bytenr(super) != bytenr || - strncmp((char *)(&super->magic), BTRFS_MAGIC, - sizeof(super->magic))) { + btrfs_super_magic(super) != BTRFS_MAGIC) { brelse(bh); continue; } @@ -2143,22 +3130,10 @@ static int write_dev_supers(struct btrfs_device *device, int errors = 0; u32 crc; u64 bytenr; - int last_barrier = 0; if (max_mirrors == 0) max_mirrors = BTRFS_SUPER_MIRROR_MAX; - /* make sure only the last submit_bh does a barrier */ - if (do_barriers) { - for (i = 0; i < max_mirrors; i++) { - bytenr = btrfs_sb_offset(i); - if (bytenr + BTRFS_SUPER_INFO_SIZE >= - device->total_bytes) - break; - last_barrier = i; - } - } - for (i = 0; i < max_mirrors; i++) { bytenr = btrfs_sb_offset(i); if (bytenr + BTRFS_SUPER_INFO_SIZE >= device->total_bytes) @@ -2167,7 +3142,10 @@ static int write_dev_supers(struct btrfs_device *device, if (wait) { bh = __find_get_block(device->bdev, bytenr / 4096, BTRFS_SUPER_INFO_SIZE); - BUG_ON(!bh); + if (!bh) { + errors++; + continue; + } wait_on_buffer(bh); if (!buffer_uptodate(bh)) errors++; @@ -2182,7 +3160,7 @@ static int write_dev_supers(struct btrfs_device *device, btrfs_set_super_bytenr(sb, bytenr); crc = ~(u32)0; - crc = btrfs_csum_data(NULL, (char *)sb + + crc = btrfs_csum_data((char *)sb + BTRFS_CSUM_SIZE, crc, BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE); @@ -2194,6 +3172,13 @@ static int write_dev_supers(struct btrfs_device *device, */ bh = __getblk(device->bdev, bytenr / 4096, BTRFS_SUPER_INFO_SIZE); + if (!bh) { + printk(KERN_ERR "BTRFS: couldn't get super " + "buffer head for bytenr %Lu\n", bytenr); + errors++; + continue; + } + memcpy(bh->b_data, sb, BTRFS_SUPER_INFO_SIZE); /* one reference for submit_bh */ @@ -2202,20 +3187,228 @@ static int write_dev_supers(struct btrfs_device *device, set_buffer_uptodate(bh); lock_buffer(bh); bh->b_end_io = btrfs_end_buffer_write_sync; + bh->b_private = device; } - if (i == last_barrier && do_barriers) - ret = submit_bh(WRITE_FLUSH_FUA, bh); + /* + * we fua the first super. The others we allow + * to go down lazy. + */ + if (i == 0) + ret = btrfsic_submit_bh(WRITE_FUA, bh); else - ret = submit_bh(WRITE_SYNC, bh); - + ret = btrfsic_submit_bh(WRITE_SYNC, bh); if (ret) errors++; } return errors < i ? 0 : -1; } -int write_all_supers(struct btrfs_root *root, int max_mirrors) +/* + * endio for the write_dev_flush, this will wake anyone waiting + * for the barrier when it is done + */ +static void btrfs_end_empty_barrier(struct bio *bio, int err) +{ + if (err) { + if (err == -EOPNOTSUPP) + set_bit(BIO_EOPNOTSUPP, &bio->bi_flags); + clear_bit(BIO_UPTODATE, &bio->bi_flags); + } + if (bio->bi_private) + complete(bio->bi_private); + bio_put(bio); +} + +/* + * trigger flushes for one the devices. If you pass wait == 0, the flushes are + * sent down. With wait == 1, it waits for the previous flush. + * + * any device where the flush fails with eopnotsupp are flagged as not-barrier + * capable + */ +static int write_dev_flush(struct btrfs_device *device, int wait) +{ + struct bio *bio; + int ret = 0; + + if (device->nobarriers) + return 0; + + if (wait) { + bio = device->flush_bio; + if (!bio) + return 0; + + wait_for_completion(&device->flush_wait); + + if (bio_flagged(bio, BIO_EOPNOTSUPP)) { + printk_in_rcu("BTRFS: disabling barriers on dev %s\n", + rcu_str_deref(device->name)); + device->nobarriers = 1; + } else if (!bio_flagged(bio, BIO_UPTODATE)) { + ret = -EIO; + btrfs_dev_stat_inc_and_print(device, + BTRFS_DEV_STAT_FLUSH_ERRS); + } + + /* drop the reference from the wait == 0 run */ + bio_put(bio); + device->flush_bio = NULL; + + return ret; + } + + /* + * one reference for us, and we leave it for the + * caller + */ + device->flush_bio = NULL; + bio = btrfs_io_bio_alloc(GFP_NOFS, 0); + if (!bio) + return -ENOMEM; + + bio->bi_end_io = btrfs_end_empty_barrier; + bio->bi_bdev = device->bdev; + init_completion(&device->flush_wait); + bio->bi_private = &device->flush_wait; + device->flush_bio = bio; + + bio_get(bio); + btrfsic_submit_bio(WRITE_FLUSH, bio); + + return 0; +} + +/* + * send an empty flush down to each device in parallel, + * then wait for them + */ +static int barrier_all_devices(struct btrfs_fs_info *info) +{ + struct list_head *head; + struct btrfs_device *dev; + int errors_send = 0; + int errors_wait = 0; + int ret; + + /* send down all the barriers */ + head = &info->fs_devices->devices; + list_for_each_entry_rcu(dev, head, dev_list) { + if (dev->missing) + continue; + if (!dev->bdev) { + errors_send++; + continue; + } + if (!dev->in_fs_metadata || !dev->writeable) + continue; + + ret = write_dev_flush(dev, 0); + if (ret) + errors_send++; + } + + /* wait for all the barriers */ + list_for_each_entry_rcu(dev, head, dev_list) { + if (dev->missing) + continue; + if (!dev->bdev) { + errors_wait++; + continue; + } + if (!dev->in_fs_metadata || !dev->writeable) + continue; + + ret = write_dev_flush(dev, 1); + if (ret) + errors_wait++; + } + if (errors_send > info->num_tolerated_disk_barrier_failures || + errors_wait > info->num_tolerated_disk_barrier_failures) + return -EIO; + return 0; +} + +int btrfs_calc_num_tolerated_disk_barrier_failures( + struct btrfs_fs_info *fs_info) +{ + struct btrfs_ioctl_space_info space; + struct btrfs_space_info *sinfo; + u64 types[] = {BTRFS_BLOCK_GROUP_DATA, + BTRFS_BLOCK_GROUP_SYSTEM, + BTRFS_BLOCK_GROUP_METADATA, + BTRFS_BLOCK_GROUP_DATA | BTRFS_BLOCK_GROUP_METADATA}; + int num_types = 4; + int i; + int c; + int num_tolerated_disk_barrier_failures = + (int)fs_info->fs_devices->num_devices; + + for (i = 0; i < num_types; i++) { + struct btrfs_space_info *tmp; + + sinfo = NULL; + rcu_read_lock(); + list_for_each_entry_rcu(tmp, &fs_info->space_info, list) { + if (tmp->flags == types[i]) { + sinfo = tmp; + break; + } + } + rcu_read_unlock(); + + if (!sinfo) + continue; + + down_read(&sinfo->groups_sem); + for (c = 0; c < BTRFS_NR_RAID_TYPES; c++) { + if (!list_empty(&sinfo->block_groups[c])) { + u64 flags; + + btrfs_get_block_group_info( + &sinfo->block_groups[c], &space); + if (space.total_bytes == 0 || + space.used_bytes == 0) + continue; + flags = space.flags; + /* + * return + * 0: if dup, single or RAID0 is configured for + * any of metadata, system or data, else + * 1: if RAID5 is configured, or if RAID1 or + * RAID10 is configured and only two mirrors + * are used, else + * 2: if RAID6 is configured, else + * num_mirrors - 1: if RAID1 or RAID10 is + * configured and more than + * 2 mirrors are used. + */ + if (num_tolerated_disk_barrier_failures > 0 && + ((flags & (BTRFS_BLOCK_GROUP_DUP | + BTRFS_BLOCK_GROUP_RAID0)) || + ((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) + == 0))) + num_tolerated_disk_barrier_failures = 0; + else if (num_tolerated_disk_barrier_failures > 1) { + if (flags & (BTRFS_BLOCK_GROUP_RAID1 | + BTRFS_BLOCK_GROUP_RAID5 | + BTRFS_BLOCK_GROUP_RAID10)) { + num_tolerated_disk_barrier_failures = 1; + } else if (flags & + BTRFS_BLOCK_GROUP_RAID6) { + num_tolerated_disk_barrier_failures = 2; + } + } + } + } + up_read(&sinfo->groups_sem); + } + + return num_tolerated_disk_barrier_failures; +} + +static int write_all_supers(struct btrfs_root *root, int max_mirrors) { struct list_head *head; struct btrfs_device *dev; @@ -2227,15 +3420,28 @@ int write_all_supers(struct btrfs_root *root, int max_mirrors) int total_errors = 0; u64 flags; - 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); head = &root->fs_info->fs_devices->devices; - list_for_each_entry(dev, head, dev_list) { + max_errors = btrfs_super_num_devices(root->fs_info->super_copy) - 1; + + if (do_barriers) { + ret = barrier_all_devices(root->fs_info); + if (ret) { + mutex_unlock( + &root->fs_info->fs_devices->device_list_mutex); + btrfs_error(root->fs_info, ret, + "errors while submitting device barriers."); + return ret; + } + } + + list_for_each_entry_rcu(dev, head, dev_list) { if (!dev->bdev) { total_errors++; continue; @@ -2262,13 +3468,18 @@ int write_all_supers(struct btrfs_root *root, int max_mirrors) total_errors++; } if (total_errors > max_errors) { - printk(KERN_ERR "btrfs: %d errors while writing supers\n", + btrfs_err(root->fs_info, "%d errors while writing supers", total_errors); - BUG(); + mutex_unlock(&root->fs_info->fs_devices->device_list_mutex); + + /* FUA is masked off if unsupported and can't be the reason */ + btrfs_error(root->fs_info, -EIO, + "%d errors while writing supers", total_errors); + return -EIO; } total_errors = 0; - list_for_each_entry(dev, head, dev_list) { + list_for_each_entry_rcu(dev, head, dev_list) { if (!dev->bdev) continue; if (!dev->in_fs_metadata || !dev->writeable) @@ -2280,9 +3491,9 @@ int write_all_supers(struct btrfs_root *root, int max_mirrors) } mutex_unlock(&root->fs_info->fs_devices->device_list_mutex); if (total_errors > max_errors) { - printk(KERN_ERR "btrfs: %d errors while writing supers\n", - total_errors); - BUG(); + btrfs_error(root->fs_info, -EIO, + "%d errors while writing supers", total_errors); + return -EIO; } return 0; } @@ -2290,13 +3501,12 @@ int write_all_supers(struct btrfs_root *root, int max_mirrors) int write_ctree_super(struct btrfs_trans_handle *trans, struct btrfs_root *root, int max_mirrors) { - int ret; - - ret = write_all_supers(root, max_mirrors); - return ret; + return write_all_supers(root, max_mirrors); } -int btrfs_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root) +/* Drop a fs root from the radix tree and free it. */ +void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info, + struct btrfs_root *root) { spin_lock(&fs_info->fs_roots_radix_lock); radix_tree_delete(&fs_info->fs_roots_radix, @@ -2306,104 +3516,107 @@ int btrfs_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root) if (btrfs_root_refs(&root->root_item) == 0) synchronize_srcu(&fs_info->subvol_srcu); + if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) + btrfs_free_log(NULL, root); + + if (root->free_ino_pinned) + __btrfs_remove_free_space_cache(root->free_ino_pinned); + if (root->free_ino_ctl) + __btrfs_remove_free_space_cache(root->free_ino_ctl); free_fs_root(root); - return 0; } static void free_fs_root(struct btrfs_root *root) { + iput(root->cache_inode); WARN_ON(!RB_EMPTY_ROOT(&root->inode_tree)); - if (root->anon_super.s_dev) { - down_write(&root->anon_super.s_umount); - kill_anon_super(&root->anon_super); - } + btrfs_free_block_rsv(root, root->orphan_block_rsv); + root->orphan_block_rsv = NULL; + if (root->anon_dev) + free_anon_bdev(root->anon_dev); + if (root->subv_writers) + btrfs_free_subvolume_writers(root->subv_writers); free_extent_buffer(root->node); free_extent_buffer(root->commit_root); + kfree(root->free_ino_ctl); + kfree(root->free_ino_pinned); kfree(root->name); - kfree(root); + btrfs_put_fs_root(root); } -static int del_fs_roots(struct btrfs_fs_info *fs_info) +void btrfs_free_fs_root(struct btrfs_root *root) { - int ret; - struct btrfs_root *gang[8]; - int i; - - while (!list_empty(&fs_info->dead_roots)) { - gang[0] = list_entry(fs_info->dead_roots.next, - struct btrfs_root, root_list); - list_del(&gang[0]->root_list); - - if (gang[0]->in_radix) { - btrfs_free_fs_root(fs_info, gang[0]); - } else { - free_extent_buffer(gang[0]->node); - free_extent_buffer(gang[0]->commit_root); - kfree(gang[0]); - } - } - - while (1) { - ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix, - (void **)gang, 0, - ARRAY_SIZE(gang)); - if (!ret) - break; - for (i = 0; i < ret; i++) - btrfs_free_fs_root(fs_info, gang[i]); - } - return 0; + free_fs_root(root); } int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info) { u64 root_objectid = 0; struct btrfs_root *gang[8]; - int i; - int ret; + int i = 0; + int err = 0; + unsigned int ret = 0; + int index; while (1) { + index = srcu_read_lock(&fs_info->subvol_srcu); ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix, (void **)gang, root_objectid, ARRAY_SIZE(gang)); - if (!ret) + if (!ret) { + srcu_read_unlock(&fs_info->subvol_srcu, index); break; - + } root_objectid = gang[ret - 1]->root_key.objectid + 1; + + for (i = 0; i < ret; i++) { + /* Avoid to grab roots in dead_roots */ + if (btrfs_root_refs(&gang[i]->root_item) == 0) { + gang[i] = NULL; + continue; + } + /* grab all the search result for later use */ + gang[i] = btrfs_grab_fs_root(gang[i]); + } + srcu_read_unlock(&fs_info->subvol_srcu, index); + for (i = 0; i < ret; i++) { + if (!gang[i]) + continue; root_objectid = gang[i]->root_key.objectid; - btrfs_orphan_cleanup(gang[i]); + err = btrfs_orphan_cleanup(gang[i]); + if (err) + break; + btrfs_put_fs_root(gang[i]); } root_objectid++; } - return 0; + + /* release the uncleaned roots due to error */ + for (; i < ret; i++) { + if (gang[i]) + btrfs_put_fs_root(gang[i]); + } + return err; } int btrfs_commit_super(struct btrfs_root *root) { struct btrfs_trans_handle *trans; - int ret; mutex_lock(&root->fs_info->cleaner_mutex); btrfs_run_delayed_iputs(root); - btrfs_clean_old_snapshots(root); mutex_unlock(&root->fs_info->cleaner_mutex); + wake_up_process(root->fs_info->cleaner_kthread); /* wait until ongoing cleanup work done */ down_write(&root->fs_info->cleanup_work_sem); up_write(&root->fs_info->cleanup_work_sem); - trans = btrfs_join_transaction(root, 1); - ret = btrfs_commit_transaction(trans, root); - BUG_ON(ret); - /* run commit again to drop the original snapshot */ - trans = btrfs_join_transaction(root, 1); - btrfs_commit_transaction(trans, root); - ret = btrfs_write_and_wait_transaction(NULL, root); - BUG_ON(ret); - - ret = write_ctree_super(NULL, root, 0); - return ret; + trans = btrfs_join_transaction(root); + if (IS_ERR(trans)) + return PTR_ERR(trans); + return btrfs_commit_transaction(trans, root); } int close_ctree(struct btrfs_root *root) @@ -2414,187 +3627,555 @@ int close_ctree(struct btrfs_root *root) fs_info->closing = 1; smp_mb(); - btrfs_put_block_group_cache(fs_info); + /* wait for the uuid_scan task to finish */ + down(&fs_info->uuid_tree_rescan_sem); + /* avoid complains from lockdep et al., set sem back to initial state */ + up(&fs_info->uuid_tree_rescan_sem); + + /* pause restriper - we want to resume on mount */ + btrfs_pause_balance(fs_info); + + btrfs_dev_replace_suspend_for_unmount(fs_info); + + btrfs_scrub_cancel(fs_info); + + /* wait for any defraggers to finish */ + wait_event(fs_info->transaction_wait, + (atomic_read(&fs_info->defrag_running) == 0)); + + /* clear out the rbtree of defraggable inodes */ + btrfs_cleanup_defrag_inodes(fs_info); + + cancel_work_sync(&fs_info->async_reclaim_work); + if (!(fs_info->sb->s_flags & MS_RDONLY)) { - ret = btrfs_commit_super(root); + ret = btrfs_commit_super(root); if (ret) - printk(KERN_ERR "btrfs: commit super ret %d\n", ret); + btrfs_err(root->fs_info, "commit super ret %d", ret); } - kthread_stop(root->fs_info->transaction_kthread); - kthread_stop(root->fs_info->cleaner_kthread); + if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) + btrfs_error_commit_super(root); + + kthread_stop(fs_info->transaction_kthread); + kthread_stop(fs_info->cleaner_kthread); fs_info->closing = 2; smp_mb(); - if (fs_info->delalloc_bytes) { - printk(KERN_INFO "btrfs: at unmount delalloc count %llu\n", - (unsigned long long)fs_info->delalloc_bytes); - } - if (fs_info->total_ref_cache_size) { - printk(KERN_INFO "btrfs: at umount reference cache size %llu\n", - (unsigned long long)fs_info->total_ref_cache_size); + btrfs_free_qgroup_config(root->fs_info); + + if (percpu_counter_sum(&fs_info->delalloc_bytes)) { + btrfs_info(root->fs_info, "at unmount delalloc count %lld", + percpu_counter_sum(&fs_info->delalloc_bytes)); } - free_extent_buffer(fs_info->extent_root->node); - free_extent_buffer(fs_info->extent_root->commit_root); - free_extent_buffer(fs_info->tree_root->node); - free_extent_buffer(fs_info->tree_root->commit_root); - free_extent_buffer(root->fs_info->chunk_root->node); - free_extent_buffer(root->fs_info->chunk_root->commit_root); - free_extent_buffer(root->fs_info->dev_root->node); - free_extent_buffer(root->fs_info->dev_root->commit_root); - free_extent_buffer(root->fs_info->csum_root->node); - free_extent_buffer(root->fs_info->csum_root->commit_root); + btrfs_sysfs_remove_one(fs_info); - btrfs_free_block_groups(root->fs_info); + btrfs_free_fs_roots(fs_info); + + btrfs_put_block_group_cache(fs_info); + + btrfs_free_block_groups(fs_info); + + /* + * we must make sure there is not any read request to + * submit after we stopping all workers. + */ + invalidate_inode_pages2(fs_info->btree_inode->i_mapping); + btrfs_stop_all_workers(fs_info); - del_fs_roots(fs_info); + free_root_pointers(fs_info, 1); iput(fs_info->btree_inode); - btrfs_stop_workers(&fs_info->generic_worker); - btrfs_stop_workers(&fs_info->fixup_workers); - btrfs_stop_workers(&fs_info->delalloc_workers); - btrfs_stop_workers(&fs_info->workers); - btrfs_stop_workers(&fs_info->endio_workers); - btrfs_stop_workers(&fs_info->endio_meta_workers); - btrfs_stop_workers(&fs_info->endio_meta_write_workers); - btrfs_stop_workers(&fs_info->endio_write_workers); - btrfs_stop_workers(&fs_info->endio_freespace_worker); - btrfs_stop_workers(&fs_info->submit_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); + percpu_counter_destroy(&fs_info->dirty_metadata_bytes); + percpu_counter_destroy(&fs_info->delalloc_bytes); + percpu_counter_destroy(&fs_info->bio_counter); 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); + btrfs_free_stripe_hash_table(fs_info); + + btrfs_free_block_rsv(root, root->orphan_block_rsv); + root->orphan_block_rsv = NULL; + return 0; } -int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid) +int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid, + int atomic) { int ret; - struct inode *btree_inode = buf->first_page->mapping->host; + struct inode *btree_inode = buf->pages[0]->mapping->host; - ret = extent_buffer_uptodate(&BTRFS_I(btree_inode)->io_tree, buf, - NULL); + ret = extent_buffer_uptodate(buf); if (!ret) return ret; ret = verify_parent_transid(&BTRFS_I(btree_inode)->io_tree, buf, - parent_transid); + parent_transid, atomic); + if (ret == -EAGAIN) + return ret; return !ret; } int btrfs_set_buffer_uptodate(struct extent_buffer *buf) { - struct inode *btree_inode = buf->first_page->mapping->host; - return set_extent_buffer_uptodate(&BTRFS_I(btree_inode)->io_tree, - buf); + return set_extent_buffer_uptodate(buf); } void btrfs_mark_buffer_dirty(struct extent_buffer *buf) { - struct btrfs_root *root = BTRFS_I(buf->first_page->mapping->host)->root; + struct btrfs_root *root; u64 transid = btrfs_header_generation(buf); - struct inode *btree_inode = root->fs_info->btree_inode; int was_dirty; +#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS + /* + * This is a fast path so only do this check if we have sanity tests + * enabled. Normal people shouldn't be marking dummy buffers as dirty + * outside of the sanity tests. + */ + if (unlikely(test_bit(EXTENT_BUFFER_DUMMY, &buf->bflags))) + return; +#endif + root = BTRFS_I(buf->pages[0]->mapping->host)->root; btrfs_assert_tree_locked(buf); - if (transid != root->fs_info->generation) { - printk(KERN_CRIT "btrfs transid mismatch buffer %llu, " + if (transid != root->fs_info->generation) + WARN(1, KERN_CRIT "btrfs transid mismatch buffer %llu, " "found %llu running %llu\n", - (unsigned long long)buf->start, - (unsigned long long)transid, - (unsigned long long)root->fs_info->generation); - WARN_ON(1); - } - was_dirty = set_extent_buffer_dirty(&BTRFS_I(btree_inode)->io_tree, - buf); - if (!was_dirty) { - spin_lock(&root->fs_info->delalloc_lock); - root->fs_info->dirty_metadata_bytes += buf->len; - spin_unlock(&root->fs_info->delalloc_lock); + buf->start, transid, root->fs_info->generation); + was_dirty = set_extent_buffer_dirty(buf); + if (!was_dirty) + __percpu_counter_add(&root->fs_info->dirty_metadata_bytes, + buf->len, + root->fs_info->dirty_metadata_batch); +#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY + if (btrfs_header_level(buf) == 0 && check_leaf(root, buf)) { + btrfs_print_leaf(root, buf); + ASSERT(0); } +#endif } -void btrfs_btree_balance_dirty(struct btrfs_root *root, unsigned long nr) +static void __btrfs_btree_balance_dirty(struct btrfs_root *root, + int flush_delayed) { /* * looks as though older kernels can get into trouble with * this code, they end up stuck in balance_dirty_pages forever */ - u64 num_dirty; - unsigned long thresh = 32 * 1024 * 1024; + int ret; if (current->flags & PF_MEMALLOC) return; - num_dirty = root->fs_info->dirty_metadata_bytes; + if (flush_delayed) + btrfs_balance_delayed_items(root); - if (num_dirty > thresh) { - balance_dirty_pages_ratelimited_nr( - root->fs_info->btree_inode->i_mapping, 1); + ret = percpu_counter_compare(&root->fs_info->dirty_metadata_bytes, + BTRFS_DIRTY_METADATA_THRESH); + if (ret > 0) { + balance_dirty_pages_ratelimited( + root->fs_info->btree_inode->i_mapping); } return; } +void btrfs_btree_balance_dirty(struct btrfs_root *root) +{ + __btrfs_btree_balance_dirty(root, 1); +} + +void btrfs_btree_balance_dirty_nodelay(struct btrfs_root *root) +{ + __btrfs_btree_balance_dirty(root, 0); +} + int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid) { - struct btrfs_root *root = BTRFS_I(buf->first_page->mapping->host)->root; - int ret; - ret = btree_read_extent_buffer_pages(root, buf, 0, parent_transid); - if (ret == 0) - set_bit(EXTENT_BUFFER_UPTODATE, &buf->bflags); + struct btrfs_root *root = BTRFS_I(buf->pages[0]->mapping->host)->root; + return btree_read_extent_buffer_pages(root, buf, 0, parent_transid); +} + +static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info, + int read_only) +{ + /* + * Placeholder for checks + */ + return 0; +} + +static void btrfs_error_commit_super(struct btrfs_root *root) +{ + mutex_lock(&root->fs_info->cleaner_mutex); + btrfs_run_delayed_iputs(root); + mutex_unlock(&root->fs_info->cleaner_mutex); + + down_write(&root->fs_info->cleanup_work_sem); + up_write(&root->fs_info->cleanup_work_sem); + + /* cleanup FS via transaction */ + btrfs_cleanup_transaction(root); +} + +static void btrfs_destroy_ordered_operations(struct btrfs_transaction *t, + struct btrfs_root *root) +{ + struct btrfs_inode *btrfs_inode; + struct list_head splice; + + INIT_LIST_HEAD(&splice); + + mutex_lock(&root->fs_info->ordered_operations_mutex); + spin_lock(&root->fs_info->ordered_root_lock); + + list_splice_init(&t->ordered_operations, &splice); + while (!list_empty(&splice)) { + btrfs_inode = list_entry(splice.next, struct btrfs_inode, + ordered_operations); + + list_del_init(&btrfs_inode->ordered_operations); + spin_unlock(&root->fs_info->ordered_root_lock); + + btrfs_invalidate_inodes(btrfs_inode->root); + + spin_lock(&root->fs_info->ordered_root_lock); + } + + spin_unlock(&root->fs_info->ordered_root_lock); + mutex_unlock(&root->fs_info->ordered_operations_mutex); +} + +static void btrfs_destroy_ordered_extents(struct btrfs_root *root) +{ + struct btrfs_ordered_extent *ordered; + + spin_lock(&root->ordered_extent_lock); + /* + * This will just short circuit the ordered completion stuff which will + * make sure the ordered extent gets properly cleaned up. + */ + list_for_each_entry(ordered, &root->ordered_extents, + root_extent_list) + set_bit(BTRFS_ORDERED_IOERR, &ordered->flags); + spin_unlock(&root->ordered_extent_lock); +} + +static void btrfs_destroy_all_ordered_extents(struct btrfs_fs_info *fs_info) +{ + struct btrfs_root *root; + struct list_head splice; + + INIT_LIST_HEAD(&splice); + + spin_lock(&fs_info->ordered_root_lock); + list_splice_init(&fs_info->ordered_roots, &splice); + while (!list_empty(&splice)) { + root = list_first_entry(&splice, struct btrfs_root, + ordered_root); + list_move_tail(&root->ordered_root, + &fs_info->ordered_roots); + + spin_unlock(&fs_info->ordered_root_lock); + btrfs_destroy_ordered_extents(root); + + cond_resched(); + spin_lock(&fs_info->ordered_root_lock); + } + spin_unlock(&fs_info->ordered_root_lock); +} + +static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, + struct btrfs_root *root) +{ + struct rb_node *node; + struct btrfs_delayed_ref_root *delayed_refs; + struct btrfs_delayed_ref_node *ref; + int ret = 0; + + delayed_refs = &trans->delayed_refs; + + spin_lock(&delayed_refs->lock); + if (atomic_read(&delayed_refs->num_entries) == 0) { + spin_unlock(&delayed_refs->lock); + btrfs_info(root->fs_info, "delayed_refs has NO entry"); + return ret; + } + + while ((node = rb_first(&delayed_refs->href_root)) != NULL) { + struct btrfs_delayed_ref_head *head; + bool pin_bytes = false; + + head = rb_entry(node, struct btrfs_delayed_ref_head, + href_node); + if (!mutex_trylock(&head->mutex)) { + atomic_inc(&head->node.refs); + spin_unlock(&delayed_refs->lock); + + mutex_lock(&head->mutex); + mutex_unlock(&head->mutex); + btrfs_put_delayed_ref(&head->node); + spin_lock(&delayed_refs->lock); + continue; + } + spin_lock(&head->lock); + while ((node = rb_first(&head->ref_root)) != NULL) { + ref = rb_entry(node, struct btrfs_delayed_ref_node, + rb_node); + ref->in_tree = 0; + rb_erase(&ref->rb_node, &head->ref_root); + atomic_dec(&delayed_refs->num_entries); + btrfs_put_delayed_ref(ref); + } + if (head->must_insert_reserved) + pin_bytes = true; + btrfs_free_delayed_extent_op(head->extent_op); + delayed_refs->num_heads--; + if (head->processing == 0) + delayed_refs->num_heads_ready--; + atomic_dec(&delayed_refs->num_entries); + head->node.in_tree = 0; + rb_erase(&head->href_node, &delayed_refs->href_root); + spin_unlock(&head->lock); + spin_unlock(&delayed_refs->lock); + mutex_unlock(&head->mutex); + + if (pin_bytes) + btrfs_pin_extent(root, head->node.bytenr, + head->node.num_bytes, 1); + btrfs_put_delayed_ref(&head->node); + cond_resched(); + spin_lock(&delayed_refs->lock); + } + + spin_unlock(&delayed_refs->lock); + return ret; } -int btree_lock_page_hook(struct page *page) +static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root) +{ + struct btrfs_inode *btrfs_inode; + struct list_head splice; + + INIT_LIST_HEAD(&splice); + + spin_lock(&root->delalloc_lock); + list_splice_init(&root->delalloc_inodes, &splice); + + while (!list_empty(&splice)) { + btrfs_inode = list_first_entry(&splice, struct btrfs_inode, + delalloc_inodes); + + list_del_init(&btrfs_inode->delalloc_inodes); + clear_bit(BTRFS_INODE_IN_DELALLOC_LIST, + &btrfs_inode->runtime_flags); + spin_unlock(&root->delalloc_lock); + + btrfs_invalidate_inodes(btrfs_inode->root); + + spin_lock(&root->delalloc_lock); + } + + spin_unlock(&root->delalloc_lock); +} + +static void btrfs_destroy_all_delalloc_inodes(struct btrfs_fs_info *fs_info) +{ + struct btrfs_root *root; + struct list_head splice; + + INIT_LIST_HEAD(&splice); + + spin_lock(&fs_info->delalloc_root_lock); + list_splice_init(&fs_info->delalloc_roots, &splice); + while (!list_empty(&splice)) { + root = list_first_entry(&splice, struct btrfs_root, + delalloc_root); + list_del_init(&root->delalloc_root); + root = btrfs_grab_fs_root(root); + BUG_ON(!root); + spin_unlock(&fs_info->delalloc_root_lock); + + btrfs_destroy_delalloc_inodes(root); + btrfs_put_fs_root(root); + + spin_lock(&fs_info->delalloc_root_lock); + } + spin_unlock(&fs_info->delalloc_root_lock); +} + +static int btrfs_destroy_marked_extents(struct btrfs_root *root, + struct extent_io_tree *dirty_pages, + int mark) { - struct inode *inode = page->mapping->host; - struct btrfs_root *root = BTRFS_I(inode)->root; - struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; + int ret; struct extent_buffer *eb; - unsigned long len; - u64 bytenr = page_offset(page); + u64 start = 0; + u64 end; - if (page->private == EXTENT_PAGE_PRIVATE) - goto out; + while (1) { + ret = find_first_extent_bit(dirty_pages, start, &start, &end, + mark, NULL); + if (ret) + break; - len = page->private >> 2; - eb = find_extent_buffer(io_tree, bytenr, len, GFP_NOFS); - if (!eb) - goto out; + clear_extent_bits(dirty_pages, start, end, mark, GFP_NOFS); + while (start <= end) { + eb = btrfs_find_tree_block(root, start, + root->leafsize); + start += root->leafsize; + if (!eb) + continue; + wait_on_extent_buffer_writeback(eb); + + if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, + &eb->bflags)) + clear_extent_buffer_dirty(eb); + free_extent_buffer_stale(eb); + } + } + + return ret; +} + +static int btrfs_destroy_pinned_extent(struct btrfs_root *root, + struct extent_io_tree *pinned_extents) +{ + struct extent_io_tree *unpin; + u64 start; + u64 end; + int ret; + bool loop = true; - btrfs_tree_lock(eb); - btrfs_set_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN); + unpin = pinned_extents; +again: + while (1) { + ret = find_first_extent_bit(unpin, 0, &start, &end, + EXTENT_DIRTY, NULL); + if (ret) + break; + + /* opt_discard */ + if (btrfs_test_opt(root, DISCARD)) + ret = btrfs_error_discard_extent(root, start, + end + 1 - start, + NULL); + + clear_extent_dirty(unpin, start, end, GFP_NOFS); + btrfs_error_unpin_extent_range(root, start, end); + cond_resched(); + } - if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)) { - spin_lock(&root->fs_info->delalloc_lock); - if (root->fs_info->dirty_metadata_bytes >= eb->len) - root->fs_info->dirty_metadata_bytes -= eb->len; + if (loop) { + if (unpin == &root->fs_info->freed_extents[0]) + unpin = &root->fs_info->freed_extents[1]; else - WARN_ON(1); - spin_unlock(&root->fs_info->delalloc_lock); + unpin = &root->fs_info->freed_extents[0]; + loop = false; + goto again; } - btrfs_tree_unlock(eb); - free_extent_buffer(eb); -out: - lock_page(page); + return 0; +} + +void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, + struct btrfs_root *root) +{ + btrfs_destroy_ordered_operations(cur_trans, root); + + btrfs_destroy_delayed_refs(cur_trans, root); + + cur_trans->state = TRANS_STATE_COMMIT_START; + wake_up(&root->fs_info->transaction_blocked_wait); + + cur_trans->state = TRANS_STATE_UNBLOCKED; + wake_up(&root->fs_info->transaction_wait); + + btrfs_destroy_delayed_inodes(root); + btrfs_assert_delayed_root_empty(root); + + btrfs_destroy_marked_extents(root, &cur_trans->dirty_pages, + EXTENT_DIRTY); + btrfs_destroy_pinned_extent(root, + root->fs_info->pinned_extents); + + cur_trans->state =TRANS_STATE_COMPLETED; + wake_up(&cur_trans->commit_wait); + + /* + memset(cur_trans, 0, sizeof(*cur_trans)); + kmem_cache_free(btrfs_transaction_cachep, cur_trans); + */ +} + +static int btrfs_cleanup_transaction(struct btrfs_root *root) +{ + struct btrfs_transaction *t; + + mutex_lock(&root->fs_info->transaction_kthread_mutex); + + spin_lock(&root->fs_info->trans_lock); + while (!list_empty(&root->fs_info->trans_list)) { + t = list_first_entry(&root->fs_info->trans_list, + struct btrfs_transaction, list); + if (t->state >= TRANS_STATE_COMMIT_START) { + atomic_inc(&t->use_count); + spin_unlock(&root->fs_info->trans_lock); + btrfs_wait_for_commit(root, t->transid); + btrfs_put_transaction(t); + spin_lock(&root->fs_info->trans_lock); + continue; + } + if (t == root->fs_info->running_transaction) { + t->state = TRANS_STATE_COMMIT_DOING; + spin_unlock(&root->fs_info->trans_lock); + /* + * We wait for 0 num_writers since we don't hold a trans + * handle open currently for this transaction. + */ + wait_event(t->writer_wait, + atomic_read(&t->num_writers) == 0); + } else { + spin_unlock(&root->fs_info->trans_lock); + } + btrfs_cleanup_one_transaction(t, root); + + spin_lock(&root->fs_info->trans_lock); + if (t == root->fs_info->running_transaction) + root->fs_info->running_transaction = NULL; + list_del_init(&t->list); + spin_unlock(&root->fs_info->trans_lock); + + btrfs_put_transaction(t); + trace_btrfs_transaction_commit(root); + spin_lock(&root->fs_info->trans_lock); + } + spin_unlock(&root->fs_info->trans_lock); + btrfs_destroy_all_ordered_extents(root->fs_info); + btrfs_destroy_delayed_inodes(root); + btrfs_assert_delayed_root_empty(root); + btrfs_destroy_pinned_extent(root, root->fs_info->pinned_extents); + btrfs_destroy_all_delalloc_inodes(root->fs_info); + mutex_unlock(&root->fs_info->transaction_kthread_mutex); + return 0; } 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, |