diff options
Diffstat (limited to 'fs')
84 files changed, 1471 insertions, 2203 deletions
diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index 79000bf62491..6b801d1ddf4b 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -24,7 +24,7 @@ /** * enum p9_session_flags - option flags for each 9P session * @V9FS_PROTO_2000U: whether or not to use 9P2000.u extensions - * @V9FS_PROTO_2010L: whether or not to use 9P2010.l extensions + * @V9FS_PROTO_2000L: whether or not to use 9P2000.l extensions * @V9FS_ACCESS_SINGLE: only the mounting user can access the hierarchy * @V9FS_ACCESS_USER: a new attach will be issued for every user (default) * @V9FS_ACCESS_ANY: use a single attach for all users @@ -34,7 +34,7 @@ */ enum p9_session_flags { V9FS_PROTO_2000U = 0x01, - V9FS_PROTO_2010L = 0x02, + V9FS_PROTO_2000L = 0x02, V9FS_ACCESS_SINGLE = 0x04, V9FS_ACCESS_USER = 0x08, V9FS_ACCESS_ANY = 0x0C, @@ -130,5 +130,5 @@ static inline int v9fs_proto_dotu(struct v9fs_session_info *v9ses) static inline int v9fs_proto_dotl(struct v9fs_session_info *v9ses) { - return v9ses->flags & V9FS_PROTO_2010L; + return v9ses->flags & V9FS_PROTO_2000L; } diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c index 6580aa449541..d8a3afe4ff72 100644 --- a/fs/9p/vfs_dir.c +++ b/fs/9p/vfs_dir.c @@ -76,6 +76,15 @@ static inline int dt_type(struct p9_wstat *mistat) return rettype; } +static void p9stat_init(struct p9_wstat *stbuf) +{ + stbuf->name = NULL; + stbuf->uid = NULL; + stbuf->gid = NULL; + stbuf->muid = NULL; + stbuf->extension = NULL; +} + /** * v9fs_dir_readdir - read a directory * @filp: opened file structure @@ -131,8 +140,8 @@ static int v9fs_dir_readdir(struct file *filp, void *dirent, filldir_t filldir) rdir->head = 0; rdir->tail = err; } - while (rdir->head < rdir->tail) { + p9stat_init(&st); err = p9stat_read(rdir->buf + rdir->head, buflen - rdir->head, &st, fid->clnt->proto_version); diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 36122683fae8..df52d488d2a6 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -114,7 +114,7 @@ static int v9fs_file_lock(struct file *filp, int cmd, struct file_lock *fl) P9_DPRINTK(P9_DEBUG_VFS, "filp: %p lock: %p\n", filp, fl); /* No mandatory locks */ - if (__mandatory_lock(inode)) + if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK) return -ENOLCK; if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->fl_type != F_UNLCK) { @@ -215,7 +215,7 @@ v9fs_file_write(struct file *filp, const char __user * data, struct p9_fid *fid; struct p9_client *clnt; struct inode *inode = filp->f_path.dentry->d_inode; - int origin = *offset; + loff_t origin = *offset; unsigned long pg_start, pg_end; P9_DPRINTK(P9_DEBUG_VFS, "data %p count %d offset %x\n", data, diff --git a/fs/affs/bitmap.c b/fs/affs/bitmap.c index dc5ef14bdc1c..8306d53307ed 100644 --- a/fs/affs/bitmap.c +++ b/fs/affs/bitmap.c @@ -128,7 +128,7 @@ err_range: /* * Allocate a block in the given allocation zone. * Since we have to byte-swap the bitmap on little-endian - * machines, this is rather expensive. Therefor we will + * machines, this is rather expensive. Therefore we will * preallocate up to 16 blocks from the same word, if * possible. We are not doing preallocations in the * header zone, though. diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c index 9f0bf13291e5..2de009565d8e 100644 --- a/fs/anon_inodes.c +++ b/fs/anon_inodes.c @@ -209,6 +209,7 @@ static struct inode *anon_inode_mkinode(void) inode->i_mode = S_IRUSR | S_IWUSR; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); + inode->i_flags |= S_PRIVATE; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; return inode; } diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index 6d6a16c5e9bb..2c32d00a6690 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -1374,7 +1374,7 @@ static inline void fill_note(struct memelfnote *note, const char *name, int type /* * fill up all the fields in prstatus from the given task struct, except - * registers which need to be filled up seperately. + * registers which need to be filled up separately. */ static void fill_prstatus(struct elf_prstatus *prstatus, struct task_struct *p, long signr) @@ -264,13 +264,12 @@ EXPORT_SYMBOL(bio_init); * bio_alloc_bioset - allocate a bio for I/O * @gfp_mask: the GFP_ mask given to the slab allocator * @nr_iovecs: number of iovecs to pre-allocate - * @bs: the bio_set to allocate from. If %NULL, just use kmalloc + * @bs: the bio_set to allocate from. * * Description: - * bio_alloc_bioset will first try its own mempool to satisfy the allocation. + * bio_alloc_bioset will try its own mempool to satisfy the allocation. * If %__GFP_WAIT is set then we will block on the internal pool waiting - * for a &struct bio to become free. If a %NULL @bs is passed in, we will - * fall back to just using @kmalloc to allocate the required memory. + * for a &struct bio to become free. * * Note that the caller must set ->bi_destructor on successful return * of a bio, to do the appropriate freeing of the bio once the reference diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index 3f1f50d9d916..7a4dee199832 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -153,6 +153,11 @@ struct btrfs_inode { unsigned ordered_data_close:1; unsigned dummy_inode:1; + /* + * always compress this one file + */ + unsigned force_compress:1; + struct inode vfs_inode; }; diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index a11a32058b50..28b92a7218ab 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -478,7 +478,7 @@ static noinline int add_ra_bio_pages(struct inode *inode, goto next; } - page = alloc_page(mapping_gfp_mask(mapping) | GFP_NOFS); + page = alloc_page(mapping_gfp_mask(mapping) & ~__GFP_FS); if (!page) break; diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 8b5cfdd4bfc1..0af2e3868573 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -373,11 +373,13 @@ struct btrfs_super_block { * ones specified below then we will fail to mount */ #define BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF (1ULL << 0) +#define BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL (2ULL << 0) #define BTRFS_FEATURE_COMPAT_SUPP 0ULL #define BTRFS_FEATURE_COMPAT_RO_SUPP 0ULL #define BTRFS_FEATURE_INCOMPAT_SUPP \ - BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF + (BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF | \ + BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL) /* * A leaf is full of items. offset and size tell us where to find @@ -1182,7 +1184,6 @@ struct btrfs_root { #define BTRFS_INODE_NOATIME (1 << 9) #define BTRFS_INODE_DIRSYNC (1 << 10) - /* some macros to generate set/get funcs for the struct fields. This * assumes there is a lefoo_to_cpu for every type, so lets make a simple * one for u8: @@ -1842,7 +1843,7 @@ BTRFS_SETGET_STACK_FUNCS(super_num_devices, struct btrfs_super_block, BTRFS_SETGET_STACK_FUNCS(super_compat_flags, struct btrfs_super_block, compat_flags, 64); BTRFS_SETGET_STACK_FUNCS(super_compat_ro_flags, struct btrfs_super_block, - compat_flags, 64); + compat_ro_flags, 64); BTRFS_SETGET_STACK_FUNCS(super_incompat_flags, struct btrfs_super_block, incompat_flags, 64); BTRFS_SETGET_STACK_FUNCS(super_csum_type, struct btrfs_super_block, @@ -2310,7 +2311,8 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, u32 min_type); int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput); -int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end); +int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end, + struct extent_state **cached_state); int btrfs_writepages(struct address_space *mapping, struct writeback_control *wbc); int btrfs_create_subvol_root(struct btrfs_trans_handle *trans, @@ -2335,7 +2337,7 @@ int btrfs_init_cachep(void); void btrfs_destroy_cachep(void); long btrfs_ioctl_trans_end(struct file *file); struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, - struct btrfs_root *root); + struct btrfs_root *root, int *was_new); int btrfs_commit_write(struct file *file, struct page *page, unsigned from, unsigned to); struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page, @@ -2386,7 +2388,6 @@ void btrfs_sysfs_del_super(struct btrfs_fs_info *root); ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size); /* super.c */ -u64 btrfs_parse_size(char *str); int btrfs_parse_options(struct btrfs_root *root, char *options); int btrfs_sync_fs(struct super_block *sb, int wait); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 2b59201b955c..11d0ad30e203 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -263,13 +263,15 @@ static int csum_tree_block(struct btrfs_root *root, struct extent_buffer *buf, static int verify_parent_transid(struct extent_io_tree *io_tree, struct extent_buffer *eb, u64 parent_transid) { + struct extent_state *cached_state = NULL; int ret; if (!parent_transid || btrfs_header_generation(eb) == parent_transid) return 0; - lock_extent(io_tree, eb->start, eb->start + eb->len - 1, GFP_NOFS); - if (extent_buffer_uptodate(io_tree, eb) && + 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) && btrfs_header_generation(eb) == parent_transid) { ret = 0; goto out; @@ -282,10 +284,10 @@ static int verify_parent_transid(struct extent_io_tree *io_tree, (unsigned long long)btrfs_header_generation(eb)); } ret = 1; - clear_extent_buffer_uptodate(io_tree, eb); + clear_extent_buffer_uptodate(io_tree, eb, &cached_state); out: - unlock_extent(io_tree, eb->start, eb->start + eb->len - 1, - GFP_NOFS); + unlock_extent_cached(io_tree, eb->start, eb->start + eb->len - 1, + &cached_state, GFP_NOFS); return ret; } @@ -901,7 +903,7 @@ static int __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize, root->highest_objectid = 0; root->name = NULL; root->in_sysfs = 0; - root->inode_tree.rb_node = NULL; + root->inode_tree = RB_ROOT; INIT_LIST_HEAD(&root->dirty_list); INIT_LIST_HEAD(&root->orphan_list); @@ -1673,7 +1675,7 @@ struct btrfs_root *open_ctree(struct super_block *sb, insert_inode_hash(fs_info->btree_inode); spin_lock_init(&fs_info->block_group_cache_lock); - fs_info->block_group_cache_tree.rb_node = NULL; + fs_info->block_group_cache_tree = RB_ROOT; extent_io_tree_init(&fs_info->freed_extents[0], fs_info->btree_inode->i_mapping, GFP_NOFS); @@ -2497,7 +2499,8 @@ int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid) int ret; struct inode *btree_inode = buf->first_page->mapping->host; - ret = extent_buffer_uptodate(&BTRFS_I(btree_inode)->io_tree, buf); + ret = extent_buffer_uptodate(&BTRFS_I(btree_inode)->io_tree, buf, + NULL); if (!ret) return ret; diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c index ba5c3fd5ab8c..951ef09b82f4 100644 --- a/fs/btrfs/export.c +++ b/fs/btrfs/export.c @@ -95,7 +95,7 @@ static struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid, btrfs_set_key_type(&key, BTRFS_INODE_ITEM_KEY); key.offset = 0; - inode = btrfs_iget(sb, &key, root); + inode = btrfs_iget(sb, &key, root, NULL); if (IS_ERR(inode)) { err = PTR_ERR(inode); goto fail; @@ -223,7 +223,7 @@ static struct dentry *btrfs_get_parent(struct dentry *child) key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; - dentry = d_obtain_alias(btrfs_iget(root->fs_info->sb, &key, root)); + dentry = d_obtain_alias(btrfs_iget(root->fs_info->sb, &key, root, NULL)); if (!IS_ERR(dentry)) dentry->d_op = &btrfs_dentry_operations; return dentry; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 559f72489b3b..1727b26fb194 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -6561,6 +6561,7 @@ static noinline int invalidate_extent_cache(struct btrfs_root *root, struct btrfs_key key; struct inode *inode = NULL; struct btrfs_file_extent_item *fi; + struct extent_state *cached_state = NULL; u64 num_bytes; u64 skip_objectid = 0; u32 nritems; @@ -6589,12 +6590,14 @@ static noinline int invalidate_extent_cache(struct btrfs_root *root, } num_bytes = btrfs_file_extent_num_bytes(leaf, fi); - lock_extent(&BTRFS_I(inode)->io_tree, key.offset, - key.offset + num_bytes - 1, GFP_NOFS); + lock_extent_bits(&BTRFS_I(inode)->io_tree, key.offset, + key.offset + num_bytes - 1, 0, &cached_state, + GFP_NOFS); btrfs_drop_extent_cache(inode, key.offset, key.offset + num_bytes - 1, 1); - unlock_extent(&BTRFS_I(inode)->io_tree, key.offset, - key.offset + num_bytes - 1, GFP_NOFS); + unlock_extent_cached(&BTRFS_I(inode)->io_tree, key.offset, + key.offset + num_bytes - 1, &cached_state, + GFP_NOFS); cond_resched(); } iput(inode); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index b177ed319612..c99121ac5d6b 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -104,8 +104,8 @@ void extent_io_exit(void) void extent_io_tree_init(struct extent_io_tree *tree, struct address_space *mapping, gfp_t mask) { - tree->state.rb_node = NULL; - tree->buffer.rb_node = NULL; + tree->state = RB_ROOT; + tree->buffer = RB_ROOT; tree->ops = NULL; tree->dirty_bytes = 0; spin_lock_init(&tree->lock); @@ -513,7 +513,10 @@ int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, u64 last_end; int err; int set = 0; + int clear = 0; + if (bits & (EXTENT_IOBITS | EXTENT_BOUNDARY)) + clear = 1; again: if (!prealloc && (mask & __GFP_WAIT)) { prealloc = alloc_extent_state(mask); @@ -524,14 +527,20 @@ again: spin_lock(&tree->lock); if (cached_state) { cached = *cached_state; - *cached_state = NULL; - cached_state = NULL; + + if (clear) { + *cached_state = NULL; + cached_state = NULL; + } + if (cached && cached->tree && cached->start == start) { - atomic_dec(&cached->refs); + if (clear) + atomic_dec(&cached->refs); state = cached; goto hit_next; } - free_extent_state(cached); + if (clear) + free_extent_state(cached); } /* * this search will find the extents that end after @@ -946,11 +955,11 @@ int clear_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, } int set_extent_delalloc(struct extent_io_tree *tree, u64 start, u64 end, - gfp_t mask) + struct extent_state **cached_state, gfp_t mask) { return set_extent_bit(tree, start, end, EXTENT_DELALLOC | EXTENT_DIRTY | EXTENT_UPTODATE, - 0, NULL, NULL, mask); + 0, NULL, cached_state, mask); } int clear_extent_dirty(struct extent_io_tree *tree, u64 start, u64 end, @@ -984,10 +993,11 @@ int set_extent_uptodate(struct extent_io_tree *tree, u64 start, u64 end, } static int clear_extent_uptodate(struct extent_io_tree *tree, u64 start, - u64 end, gfp_t mask) + u64 end, struct extent_state **cached_state, + gfp_t mask) { return clear_extent_bit(tree, start, end, EXTENT_UPTODATE, 0, 0, - NULL, mask); + cached_state, mask); } int wait_on_extent_writeback(struct extent_io_tree *tree, u64 start, u64 end) @@ -1171,7 +1181,8 @@ out: * 1 is returned if we find something, 0 if nothing was in the tree */ static noinline u64 find_delalloc_range(struct extent_io_tree *tree, - u64 *start, u64 *end, u64 max_bytes) + u64 *start, u64 *end, u64 max_bytes, + struct extent_state **cached_state) { struct rb_node *node; struct extent_state *state; @@ -1203,8 +1214,11 @@ static noinline u64 find_delalloc_range(struct extent_io_tree *tree, *end = state->end; goto out; } - if (!found) + if (!found) { *start = state->start; + *cached_state = state; + atomic_inc(&state->refs); + } found++; *end = state->end; cur_start = state->end + 1; @@ -1336,10 +1350,11 @@ again: delalloc_start = *start; delalloc_end = 0; found = find_delalloc_range(tree, &delalloc_start, &delalloc_end, - max_bytes); + max_bytes, &cached_state); if (!found || delalloc_end <= *start) { *start = delalloc_start; *end = delalloc_end; + free_extent_state(cached_state); return found; } @@ -1722,7 +1737,7 @@ static void end_bio_extent_writepage(struct bio *bio, int err) } if (!uptodate) { - clear_extent_uptodate(tree, start, end, GFP_NOFS); + clear_extent_uptodate(tree, start, end, NULL, GFP_NOFS); ClearPageUptodate(page); SetPageError(page); } @@ -1750,7 +1765,8 @@ static void end_bio_extent_writepage(struct bio *bio, int err) static void end_bio_extent_readpage(struct bio *bio, int err) { int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); - struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1; + struct bio_vec *bvec_end = bio->bi_io_vec + bio->bi_vcnt - 1; + struct bio_vec *bvec = bio->bi_io_vec; struct extent_io_tree *tree; u64 start; u64 end; @@ -1773,7 +1789,7 @@ static void end_bio_extent_readpage(struct bio *bio, int err) else whole_page = 0; - if (--bvec >= bio->bi_io_vec) + if (++bvec <= bvec_end) prefetchw(&bvec->bv_page->flags); if (uptodate && tree->ops && tree->ops->readpage_end_io_hook) { @@ -1818,7 +1834,7 @@ static void end_bio_extent_readpage(struct bio *bio, int err) } check_page_locked(tree, page); } - } while (bvec >= bio->bi_io_vec); + } while (bvec <= bvec_end); bio_put(bio); } @@ -2704,6 +2720,7 @@ int extent_readpages(struct extent_io_tree *tree, int extent_invalidatepage(struct extent_io_tree *tree, struct page *page, unsigned long offset) { + struct extent_state *cached_state = NULL; u64 start = ((u64)page->index << PAGE_CACHE_SHIFT); u64 end = start + PAGE_CACHE_SIZE - 1; size_t blocksize = page->mapping->host->i_sb->s_blocksize; @@ -2712,12 +2729,12 @@ int extent_invalidatepage(struct extent_io_tree *tree, if (start > end) return 0; - lock_extent(tree, start, end, GFP_NOFS); + lock_extent_bits(tree, start, end, 0, &cached_state, GFP_NOFS); wait_on_page_writeback(page); clear_extent_bit(tree, start, end, EXTENT_LOCKED | EXTENT_DIRTY | EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING, - 1, 1, NULL, GFP_NOFS); + 1, 1, &cached_state, GFP_NOFS); return 0; } @@ -2920,16 +2937,17 @@ sector_t extent_bmap(struct address_space *mapping, sector_t iblock, get_extent_t *get_extent) { struct inode *inode = mapping->host; + struct extent_state *cached_state = NULL; u64 start = iblock << inode->i_blkbits; sector_t sector = 0; size_t blksize = (1 << inode->i_blkbits); struct extent_map *em; - lock_extent(&BTRFS_I(inode)->io_tree, start, start + blksize - 1, - GFP_NOFS); + lock_extent_bits(&BTRFS_I(inode)->io_tree, start, start + blksize - 1, + 0, &cached_state, GFP_NOFS); em = get_extent(inode, NULL, 0, start, blksize, 0); - unlock_extent(&BTRFS_I(inode)->io_tree, start, start + blksize - 1, - GFP_NOFS); + unlock_extent_cached(&BTRFS_I(inode)->io_tree, start, + start + blksize - 1, &cached_state, GFP_NOFS); if (!em || IS_ERR(em)) return 0; @@ -2951,6 +2969,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u32 flags = 0; u64 disko = 0; struct extent_map *em = NULL; + struct extent_state *cached_state = NULL; int end = 0; u64 em_start = 0, em_len = 0; unsigned long emflags; @@ -2959,8 +2978,8 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, if (len == 0) return -EINVAL; - lock_extent(&BTRFS_I(inode)->io_tree, start, start + len, - GFP_NOFS); + lock_extent_bits(&BTRFS_I(inode)->io_tree, start, start + len, 0, + &cached_state, GFP_NOFS); em = get_extent(inode, NULL, 0, off, max - off, 0); if (!em) goto out; @@ -3023,8 +3042,8 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, out_free: free_extent_map(em); out: - unlock_extent(&BTRFS_I(inode)->io_tree, start, start + len, - GFP_NOFS); + unlock_extent_cached(&BTRFS_I(inode)->io_tree, start, start + len, + &cached_state, GFP_NOFS); return ret; } @@ -3264,7 +3283,8 @@ int set_extent_buffer_dirty(struct extent_io_tree *tree, } int clear_extent_buffer_uptodate(struct extent_io_tree *tree, - struct extent_buffer *eb) + struct extent_buffer *eb, + struct extent_state **cached_state) { unsigned long i; struct page *page; @@ -3274,7 +3294,7 @@ int clear_extent_buffer_uptodate(struct extent_io_tree *tree, clear_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); clear_extent_uptodate(tree, eb->start, eb->start + eb->len - 1, - GFP_NOFS); + cached_state, GFP_NOFS); for (i = 0; i < num_pages; i++) { page = extent_buffer_page(eb, i); if (page) @@ -3334,7 +3354,8 @@ int extent_range_uptodate(struct extent_io_tree *tree, } int extent_buffer_uptodate(struct extent_io_tree *tree, - struct extent_buffer *eb) + struct extent_buffer *eb, + struct extent_state *cached_state) { int ret = 0; unsigned long num_pages; @@ -3346,7 +3367,7 @@ int extent_buffer_uptodate(struct extent_io_tree *tree, return 1; ret = test_range_bit(tree, eb->start, eb->start + eb->len - 1, - EXTENT_UPTODATE, 1, NULL); + EXTENT_UPTODATE, 1, cached_state); if (ret) return ret; diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 36de250a7b2b..bbab4813646f 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -163,6 +163,8 @@ int lock_extent(struct extent_io_tree *tree, u64 start, u64 end, gfp_t mask); int lock_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, int bits, struct extent_state **cached, gfp_t mask); int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end, gfp_t mask); +int unlock_extent_cached(struct extent_io_tree *tree, u64 start, u64 end, + struct extent_state **cached, gfp_t mask); int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end, gfp_t mask); int extent_read_full_page(struct extent_io_tree *tree, struct page *page, @@ -196,7 +198,7 @@ int clear_extent_ordered(struct extent_io_tree *tree, u64 start, u64 end, int clear_extent_ordered_metadata(struct extent_io_tree *tree, u64 start, u64 end, gfp_t mask); int set_extent_delalloc(struct extent_io_tree *tree, u64 start, u64 end, - gfp_t mask); + struct extent_state **cached_state, gfp_t mask); int set_extent_ordered(struct extent_io_tree *tree, u64 start, u64 end, gfp_t mask); int find_first_extent_bit(struct extent_io_tree *tree, u64 start, @@ -281,9 +283,11 @@ int test_extent_buffer_dirty(struct extent_io_tree *tree, int set_extent_buffer_uptodate(struct extent_io_tree *tree, struct extent_buffer *eb); int clear_extent_buffer_uptodate(struct extent_io_tree *tree, - struct extent_buffer *eb); + struct extent_buffer *eb, + struct extent_state **cached_state); int extent_buffer_uptodate(struct extent_io_tree *tree, - struct extent_buffer *eb); + struct extent_buffer *eb, + struct extent_state *cached_state); int map_extent_buffer(struct extent_buffer *eb, unsigned long offset, unsigned long min_len, char **token, char **map, unsigned long *map_start, diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 428fcac45f90..28d87ba60ce8 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -35,7 +35,7 @@ void extent_map_exit(void) */ void extent_map_tree_init(struct extent_map_tree *tree, gfp_t mask) { - tree->map.rb_node = NULL; + tree->map = RB_ROOT; rwlock_init(&tree->lock); } diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 6ed434ac037f..ee3323c7fc1c 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -123,7 +123,8 @@ static noinline int dirty_and_release_pages(struct btrfs_trans_handle *trans, root->sectorsize - 1) & ~((u64)root->sectorsize - 1); end_of_last_block = start_pos + num_bytes - 1; - err = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block); + err = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block, + NULL); if (err) return err; @@ -753,6 +754,7 @@ static noinline int prepare_pages(struct btrfs_root *root, struct file *file, loff_t pos, unsigned long first_index, unsigned long last_index, size_t write_bytes) { + struct extent_state *cached_state = NULL; int i; unsigned long index = pos >> PAGE_CACHE_SHIFT; struct inode *inode = fdentry(file)->d_inode; @@ -781,16 +783,18 @@ again: } if (start_pos < inode->i_size) { struct btrfs_ordered_extent *ordered; - lock_extent(&BTRFS_I(inode)->io_tree, - start_pos, last_pos - 1, GFP_NOFS); + lock_extent_bits(&BTRFS_I(inode)->io_tree, + start_pos, last_pos - 1, 0, &cached_state, + GFP_NOFS); ordered = btrfs_lookup_first_ordered_extent(inode, last_pos - 1); if (ordered && ordered->file_offset + ordered->len > start_pos && ordered->file_offset < last_pos) { btrfs_put_ordered_extent(ordered); - unlock_extent(&BTRFS_I(inode)->io_tree, - start_pos, last_pos - 1, GFP_NOFS); + unlock_extent_cached(&BTRFS_I(inode)->io_tree, + start_pos, last_pos - 1, + &cached_state, GFP_NOFS); for (i = 0; i < num_pages; i++) { unlock_page(pages[i]); page_cache_release(pages[i]); @@ -802,12 +806,13 @@ again: if (ordered) btrfs_put_ordered_extent(ordered); - clear_extent_bits(&BTRFS_I(inode)->io_tree, start_pos, + clear_extent_bit(&BTRFS_I(inode)->io_tree, start_pos, last_pos - 1, EXTENT_DIRTY | EXTENT_DELALLOC | - EXTENT_DO_ACCOUNTING, + EXTENT_DO_ACCOUNTING, 0, 0, &cached_state, GFP_NOFS); - unlock_extent(&BTRFS_I(inode)->io_tree, - start_pos, last_pos - 1, GFP_NOFS); + unlock_extent_cached(&BTRFS_I(inode)->io_tree, + start_pos, last_pos - 1, &cached_state, + GFP_NOFS); } for (i = 0; i < num_pages; i++) { clear_page_dirty_for_io(pages[i]); diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index cb2849f03251..dd831ed31eea 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -870,7 +870,7 @@ __btrfs_return_cluster_to_free_space( tree_insert_offset(&block_group->free_space_offset, entry->offset, &entry->offset_index, 0); } - cluster->root.rb_node = NULL; + cluster->root = RB_ROOT; out: spin_unlock(&cluster->lock); @@ -1355,7 +1355,7 @@ void btrfs_init_free_cluster(struct btrfs_free_cluster *cluster) { spin_lock_init(&cluster->lock); spin_lock_init(&cluster->refill_lock); - cluster->root.rb_node = NULL; + cluster->root = RB_ROOT; cluster->max_size = 0; cluster->points_to_bitmap = false; INIT_LIST_HEAD(&cluster->block_group_list); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index c41db6d45ab6..02bb099845fd 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -379,7 +379,8 @@ again: * change at any time if we discover bad compression ratios. */ if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NOCOMPRESS) && - btrfs_test_opt(root, COMPRESS)) { + (btrfs_test_opt(root, COMPRESS) || + (BTRFS_I(inode)->force_compress))) { WARN_ON(pages); pages = kzalloc(sizeof(struct page *) * nr_pages, GFP_NOFS); @@ -483,8 +484,10 @@ again: nr_pages_ret = 0; /* flag the file so we don't compress in the future */ - if (!btrfs_test_opt(root, FORCE_COMPRESS)) + if (!btrfs_test_opt(root, FORCE_COMPRESS) && + !(BTRFS_I(inode)->force_compress)) { BTRFS_I(inode)->flags |= BTRFS_INODE_NOCOMPRESS; + } } if (will_compress) { *num_added += 1; @@ -570,8 +573,8 @@ retry: unsigned long nr_written = 0; lock_extent(io_tree, async_extent->start, - async_extent->start + - async_extent->ram_size - 1, GFP_NOFS); + async_extent->start + + async_extent->ram_size - 1, GFP_NOFS); /* allocate blocks */ ret = cow_file_range(inode, async_cow->locked_page, @@ -1211,7 +1214,8 @@ static int run_delalloc_range(struct inode *inode, struct page *locked_page, else if (BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC) ret = run_delalloc_nocow(inode, locked_page, start, end, page_started, 0, nr_written); - else if (!btrfs_test_opt(root, COMPRESS)) + else if (!btrfs_test_opt(root, COMPRESS) && + !(BTRFS_I(inode)->force_compress)) ret = cow_file_range(inode, locked_page, start, end, page_started, nr_written, 1); else @@ -1508,12 +1512,13 @@ static noinline int add_pending_csums(struct btrfs_trans_handle *trans, return 0; } -int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end) +int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end, + struct extent_state **cached_state) { if ((end & (PAGE_CACHE_SIZE - 1)) == 0) WARN_ON(1); return set_extent_delalloc(&BTRFS_I(inode)->io_tree, start, end, - GFP_NOFS); + cached_state, GFP_NOFS); } /* see btrfs_writepage_start_hook for details on why this is required */ @@ -1526,6 +1531,7 @@ static void btrfs_writepage_fixup_worker(struct btrfs_work *work) { struct btrfs_writepage_fixup *fixup; struct btrfs_ordered_extent *ordered; + struct extent_state *cached_state = NULL; struct page *page; struct inode *inode; u64 page_start; @@ -1544,7 +1550,8 @@ again: page_start = page_offset(page); page_end = page_offset(page) + PAGE_CACHE_SIZE - 1; - lock_extent(&BTRFS_I(inode)->io_tree, page_start, page_end, GFP_NOFS); + lock_extent_bits(&BTRFS_I(inode)->io_tree, page_start, page_end, 0, + &cached_state, GFP_NOFS); /* already ordered? We're done */ if (PagePrivate2(page)) @@ -1552,17 +1559,18 @@ again: ordered = btrfs_lookup_ordered_extent(inode, page_start); if (ordered) { - unlock_extent(&BTRFS_I(inode)->io_tree, page_start, - page_end, GFP_NOFS); + unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start, + page_end, &cached_state, GFP_NOFS); unlock_page(page); btrfs_start_ordered_extent(inode, ordered, 1); goto again; } - btrfs_set_extent_delalloc(inode, page_start, page_end); + btrfs_set_extent_delalloc(inode, page_start, page_end, &cached_state); ClearPageChecked(page); out: - unlock_extent(&BTRFS_I(inode)->io_tree, page_start, page_end, GFP_NOFS); + unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start, page_end, + &cached_state, GFP_NOFS); out_page: unlock_page(page); page_cache_release(page); @@ -1691,14 +1699,14 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end) struct btrfs_trans_handle *trans; struct btrfs_ordered_extent *ordered_extent = NULL; struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; + struct extent_state *cached_state = NULL; int compressed = 0; int ret; - ret = btrfs_dec_test_ordered_pending(inode, start, end - start + 1); + ret = btrfs_dec_test_ordered_pending(inode, &ordered_extent, start, + end - start + 1); if (!ret) return 0; - - ordered_extent = btrfs_lookup_ordered_extent(inode, start); BUG_ON(!ordered_extent); if (test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags)) { @@ -1713,9 +1721,9 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end) goto out; } - lock_extent(io_tree, ordered_extent->file_offset, - ordered_extent->file_offset + ordered_extent->len - 1, - GFP_NOFS); + lock_extent_bits(io_tree, ordered_extent->file_offset, + ordered_extent->file_offset + ordered_extent->len - 1, + 0, &cached_state, GFP_NOFS); trans = btrfs_join_transaction(root, 1); @@ -1742,9 +1750,10 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end) ordered_extent->len); BUG_ON(ret); } - unlock_extent(io_tree, ordered_extent->file_offset, - ordered_extent->file_offset + ordered_extent->len - 1, - GFP_NOFS); + unlock_extent_cached(io_tree, ordered_extent->file_offset, + ordered_extent->file_offset + + ordered_extent->len - 1, &cached_state, GFP_NOFS); + add_pending_csums(trans, inode, ordered_extent->file_offset, &ordered_extent->list); @@ -2153,7 +2162,7 @@ void btrfs_orphan_cleanup(struct btrfs_root *root) found_key.objectid = found_key.offset; found_key.type = BTRFS_INODE_ITEM_KEY; found_key.offset = 0; - inode = btrfs_iget(root->fs_info->sb, &found_key, root); + inode = btrfs_iget(root->fs_info->sb, &found_key, root, NULL); if (IS_ERR(inode)) break; @@ -3081,6 +3090,7 @@ static int btrfs_truncate_page(struct address_space *mapping, loff_t from) struct btrfs_root *root = BTRFS_I(inode)->root; struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; struct btrfs_ordered_extent *ordered; + struct extent_state *cached_state = NULL; char *kaddr; u32 blocksize = root->sectorsize; pgoff_t index = from >> PAGE_CACHE_SHIFT; @@ -3127,12 +3137,14 @@ again: } wait_on_page_writeback(page); - lock_extent(io_tree, page_start, page_end, GFP_NOFS); + lock_extent_bits(io_tree, page_start, page_end, 0, &cached_state, + GFP_NOFS); set_page_extent_mapped(page); ordered = btrfs_lookup_ordered_extent(inode, page_start); if (ordered) { - unlock_extent(io_tree, page_start, page_end, GFP_NOFS); + unlock_extent_cached(io_tree, page_start, page_end, + &cached_state, GFP_NOFS); unlock_page(page); page_cache_release(page); btrfs_start_ordered_extent(inode, ordered, 1); @@ -3140,13 +3152,15 @@ again: goto again; } - clear_extent_bits(&BTRFS_I(inode)->io_tree, page_start, page_end, + clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start, page_end, EXTENT_DIRTY | EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING, - GFP_NOFS); + 0, 0, &cached_state, GFP_NOFS); - ret = btrfs_set_extent_delalloc(inode, page_start, page_end); + ret = btrfs_set_extent_delalloc(inode, page_start, page_end, + &cached_state); if (ret) { - unlock_extent(io_tree, page_start, page_end, GFP_NOFS); + unlock_extent_cached(io_tree, page_start, page_end, + &cached_state, GFP_NOFS); goto out_unlock; } @@ -3159,7 +3173,8 @@ again: } ClearPageChecked(page); set_page_dirty(page); - unlock_extent(io_tree, page_start, page_end, GFP_NOFS); + unlock_extent_cached(io_tree, page_start, page_end, &cached_state, + GFP_NOFS); out_unlock: if (ret) @@ -3177,6 +3192,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t size) struct btrfs_root *root = BTRFS_I(inode)->root; struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; struct extent_map *em; + struct extent_state *cached_state = NULL; u64 mask = root->sectorsize - 1; u64 hole_start = (inode->i_size + mask) & ~mask; u64 block_end = (size + mask) & ~mask; @@ -3192,11 +3208,13 @@ int btrfs_cont_expand(struct inode *inode, loff_t size) struct btrfs_ordered_extent *ordered; btrfs_wait_ordered_range(inode, hole_start, block_end - hole_start); - lock_extent(io_tree, hole_start, block_end - 1, GFP_NOFS); + lock_extent_bits(io_tree, hole_start, block_end - 1, 0, + &cached_state, GFP_NOFS); ordered = btrfs_lookup_ordered_extent(inode, hole_start); if (!ordered) break; - unlock_extent(io_tree, hole_start, block_end - 1, GFP_NOFS); + unlock_extent_cached(io_tree, hole_start, block_end - 1, + &cached_state, GFP_NOFS); btrfs_put_ordered_extent(ordered); } @@ -3241,7 +3259,8 @@ int btrfs_cont_expand(struct inode *inode, loff_t size) break; } - unlock_extent(io_tree, hole_start, block_end - 1, GFP_NOFS); + unlock_extent_cached(io_tree, hole_start, block_end - 1, &cached_state, + GFP_NOFS); return err; } @@ -3639,6 +3658,7 @@ static noinline void init_btrfs_i(struct inode *inode) bi->index_cnt = (u64)-1; bi->last_unlink_trans = 0; bi->ordered_data_close = 0; + bi->force_compress = 0; extent_map_tree_init(&BTRFS_I(inode)->extent_tree, GFP_NOFS); extent_io_tree_init(&BTRFS_I(inode)->io_tree, inode->i_mapping, GFP_NOFS); @@ -3687,7 +3707,7 @@ static struct inode *btrfs_iget_locked(struct super_block *s, * Returns in *is_new if the inode was read from disk */ struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, - struct btrfs_root *root) + struct btrfs_root *root, int *new) { struct inode *inode; @@ -3702,6 +3722,8 @@ struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, inode_tree_add(inode); unlock_new_inode(inode); + if (new) + *new = 1; } return inode; @@ -3754,7 +3776,7 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry) return NULL; if (location.type == BTRFS_INODE_ITEM_KEY) { - inode = btrfs_iget(dir->i_sb, &location, root); + inode = btrfs_iget(dir->i_sb, &location, root, NULL); return inode; } @@ -3769,7 +3791,7 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry) else inode = new_simple_dir(dir->i_sb, &location, sub_root); } else { - inode = btrfs_iget(dir->i_sb, &location, sub_root); + inode = btrfs_iget(dir->i_sb, &location, sub_root, NULL); } srcu_read_unlock(&root->fs_info->subvol_srcu, index); @@ -4501,7 +4523,7 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, int mode) err = btrfs_find_free_objectid(trans, root, dir->i_ino, &objectid); if (err) { err = -ENOSPC; - goto out_unlock; + goto out_fail; } inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name, @@ -4979,6 +5001,7 @@ static void btrfs_invalidatepage(struct page *page, unsigned long offset) { struct extent_io_tree *tree; struct btrfs_ordered_extent *ordered; + struct extent_state *cached_state = NULL; u64 page_start = page_offset(page); u64 page_end = page_start + PAGE_CACHE_SIZE - 1; @@ -4997,7 +5020,8 @@ static void btrfs_invalidatepage(struct page *page, unsigned long offset) btrfs_releasepage(page, GFP_NOFS); return; } - lock_extent(tree, page_start, page_end, GFP_NOFS); + lock_extent_bits(tree, page_start, page_end, 0, &cached_state, + GFP_NOFS); ordered = btrfs_lookup_ordered_extent(page->mapping->host, page_offset(page)); if (ordered) { @@ -5008,7 +5032,7 @@ static void btrfs_invalidatepage(struct page *page, unsigned long offset) clear_extent_bit(tree, page_start, page_end, EXTENT_DIRTY | EXTENT_DELALLOC | EXTENT_LOCKED | EXTENT_DO_ACCOUNTING, 1, 0, - NULL, GFP_NOFS); + &cached_state, GFP_NOFS); /* * whoever cleared the private bit is responsible * for the finish_ordered_io @@ -5018,11 +5042,13 @@ static void btrfs_invalidatepage(struct page *page, unsigned long offset) page_start, page_end); } btrfs_put_ordered_extent(ordered); - lock_extent(tree, page_start, page_end, GFP_NOFS); + cached_state = NULL; + lock_extent_bits(tree, page_start, page_end, 0, &cached_state, + GFP_NOFS); } clear_extent_bit(tree, page_start, page_end, EXTENT_LOCKED | EXTENT_DIRTY | EXTENT_DELALLOC | - EXTENT_DO_ACCOUNTING, 1, 1, NULL, GFP_NOFS); + EXTENT_DO_ACCOUNTING, 1, 1, &cached_state, GFP_NOFS); __btrfs_releasepage(page, GFP_NOFS); ClearPageChecked(page); @@ -5055,6 +5081,7 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) struct btrfs_root *root = BTRFS_I(inode)->root; struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; struct btrfs_ordered_extent *ordered; + struct extent_state *cached_state = NULL; char *kaddr; unsigned long zero_start; loff_t size; @@ -5093,7 +5120,8 @@ again: } wait_on_page_writeback(page); - lock_extent(io_tree, page_start, page_end, GFP_NOFS); + lock_extent_bits(io_tree, page_start, page_end, 0, &cached_state, + GFP_NOFS); set_page_extent_mapped(page); /* @@ -5102,7 +5130,8 @@ again: */ ordered = btrfs_lookup_ordered_extent(inode, page_start); if (ordered) { - unlock_extent(io_tree, page_start, page_end, GFP_NOFS); + unlock_extent_cached(io_tree, page_start, page_end, + &cached_state, GFP_NOFS); unlock_page(page); btrfs_start_ordered_extent(inode, ordered, 1); btrfs_put_ordered_extent(ordered); @@ -5116,13 +5145,15 @@ again: * is probably a better way to do this, but for now keep consistent with * prepare_pages in the normal write path. */ - clear_extent_bits(&BTRFS_I(inode)->io_tree, page_start, page_end, + clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start, page_end, EXTENT_DIRTY | EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING, - GFP_NOFS); + 0, 0, &cached_state, GFP_NOFS); - ret = btrfs_set_extent_delalloc(inode, page_start, page_end); + ret = btrfs_set_extent_delalloc(inode, page_start, page_end, + &cached_state); if (ret) { - unlock_extent(io_tree, page_start, page_end, GFP_NOFS); + unlock_extent_cached(io_tree, page_start, page_end, + &cached_state, GFP_NOFS); ret = VM_FAULT_SIGBUS; btrfs_free_reserved_data_space(root, inode, PAGE_CACHE_SIZE); goto out_unlock; @@ -5148,7 +5179,7 @@ again: BTRFS_I(inode)->last_trans = root->fs_info->generation; BTRFS_I(inode)->last_sub_trans = BTRFS_I(inode)->root->log_transid; - unlock_extent(io_tree, page_start, page_end, GFP_NOFS); + unlock_extent_cached(io_tree, page_start, page_end, &cached_state, GFP_NOFS); out_unlock: btrfs_unreserve_metadata_for_delalloc(root, inode, 1); @@ -5827,6 +5858,7 @@ stop_trans: static long btrfs_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len) { + struct extent_state *cached_state = NULL; u64 cur_offset; u64 last_byte; u64 alloc_start; @@ -5865,16 +5897,17 @@ static long btrfs_fallocate(struct inode *inode, int mode, /* the extent lock is ordered inside the running * transaction */ - lock_extent(&BTRFS_I(inode)->io_tree, alloc_start, locked_end, - GFP_NOFS); + lock_extent_bits(&BTRFS_I(inode)->io_tree, alloc_start, + locked_end, 0, &cached_state, GFP_NOFS); ordered = btrfs_lookup_first_ordered_extent(inode, alloc_end - 1); if (ordered && ordered->file_offset + ordered->len > alloc_start && ordered->file_offset < alloc_end) { btrfs_put_ordered_extent(ordered); - unlock_extent(&BTRFS_I(inode)->io_tree, - alloc_start, locked_end, GFP_NOFS); + unlock_extent_cached(&BTRFS_I(inode)->io_tree, + alloc_start, locked_end, + &cached_state, GFP_NOFS); /* * we can't wait on the range with the transaction * running or with the extent lock held @@ -5916,8 +5949,8 @@ static long btrfs_fallocate(struct inode *inode, int mode, break; } } - unlock_extent(&BTRFS_I(inode)->io_tree, alloc_start, locked_end, - GFP_NOFS); + unlock_extent_cached(&BTRFS_I(inode)->io_tree, alloc_start, locked_end, + &cached_state, GFP_NOFS); btrfs_free_reserved_data_space(BTRFS_I(inode)->root, inode, alloc_end - alloc_start); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 645a17927a8f..2845c6ceecd2 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -48,6 +48,7 @@ #include "print-tree.h" #include "volumes.h" #include "locking.h" +#include "ctree.h" /* Mask out flags that are inappropriate for the given type of inode. */ static inline __u32 btrfs_mask_flags(umode_t mode, __u32 flags) @@ -474,7 +475,79 @@ out_unlock: return error; } -static int btrfs_defrag_file(struct file *file) +static int should_defrag_range(struct inode *inode, u64 start, u64 len, + int thresh, u64 *last_len, u64 *skip, + u64 *defrag_end) +{ + struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; + struct extent_map *em = NULL; + struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree; + int ret = 1; + + + if (thresh == 0) + thresh = 256 * 1024; + + /* + * make sure that once we start defragging and extent, we keep on + * defragging it + */ + if (start < *defrag_end) + return 1; + + *skip = 0; + + /* + * hopefully we have this extent in the tree already, try without + * the full extent lock + */ + read_lock(&em_tree->lock); + em = lookup_extent_mapping(em_tree, start, len); + read_unlock(&em_tree->lock); + + if (!em) { + /* get the big lock and read metadata off disk */ + lock_extent(io_tree, start, start + len - 1, GFP_NOFS); + em = btrfs_get_extent(inode, NULL, 0, start, len, 0); + unlock_extent(io_tree, start, start + len - 1, GFP_NOFS); + + if (!em) + return 0; + } + + /* this will cover holes, and inline extents */ + if (em->block_start >= EXTENT_MAP_LAST_BYTE) + ret = 0; + + /* + * we hit a real extent, if it is big don't bother defragging it again + */ + if ((*last_len == 0 || *last_len >= thresh) && em->len >= thresh) + ret = 0; + + /* + * last_len ends up being a counter of how many bytes we've defragged. + * every time we choose not to defrag an extent, we reset *last_len + * so that the next tiny extent will force a defrag. + * + * The end result of this is that tiny extents before a single big + * extent will force at least part of that big extent to be defragged. + */ + if (ret) { + *last_len += len; + *defrag_end = extent_map_end(em); + } else { + *last_len = 0; + *skip = extent_map_end(em); + *defrag_end = 0; + } + + free_extent_map(em); + return ret; +} + +static int btrfs_defrag_file(struct file *file, + struct btrfs_ioctl_defrag_range_args *range) { struct inode *inode = fdentry(file)->d_inode; struct btrfs_root *root = BTRFS_I(inode)->root; @@ -486,37 +559,96 @@ static int btrfs_defrag_file(struct file *file) unsigned long total_read = 0; u64 page_start; u64 page_end; + u64 last_len = 0; + u64 skip = 0; + u64 defrag_end = 0; unsigned long i; int ret; - ret = btrfs_check_data_free_space(root, inode, inode->i_size); - if (ret) - return -ENOSPC; + if (inode->i_size == 0) + return 0; + + if (range->start + range->len > range->start) { + last_index = min_t(u64, inode->i_size - 1, + range->start + range->len - 1) >> PAGE_CACHE_SHIFT; + } else { + last_index = (inode->i_size - 1) >> PAGE_CACHE_SHIFT; + } + + i = range->start >> PAGE_CACHE_SHIFT; + while (i <= last_index) { + if (!should_defrag_range(inode, (u64)i << PAGE_CACHE_SHIFT, + PAGE_CACHE_SIZE, + range->extent_thresh, + &last_len, &skip, + &defrag_end)) { + unsigned long next; + /* + * the should_defrag function tells us how much to skip + * bump our counter by the suggested amount + */ + next = (skip + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + i = max(i + 1, next); + continue; + } - mutex_lock(&inode->i_mutex); - last_index = inode->i_size >> PAGE_CACHE_SHIFT; - for (i = 0; i <= last_index; i++) { if (total_read % ra_pages == 0) { btrfs_force_ra(inode->i_mapping, &file->f_ra, file, i, min(last_index, i + ra_pages - 1)); } total_read++; + mutex_lock(&inode->i_mutex); + if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS) + BTRFS_I(inode)->force_compress = 1; + + ret = btrfs_check_data_free_space(root, inode, PAGE_CACHE_SIZE); + if (ret) { + ret = -ENOSPC; + break; + } + + ret = btrfs_reserve_metadata_for_delalloc(root, inode, 1); + if (ret) { + btrfs_free_reserved_data_space(root, inode, + PAGE_CACHE_SIZE); + ret = -ENOSPC; + break; + } again: + if (inode->i_size == 0 || + i > ((inode->i_size - 1) >> PAGE_CACHE_SHIFT)) { + ret = 0; + goto err_reservations; + } + page = grab_cache_page(inode->i_mapping, i); if (!page) - goto out_unlock; + goto err_reservations; + if (!PageUptodate(page)) { btrfs_readpage(NULL, page); lock_page(page); if (!PageUptodate(page)) { unlock_page(page); page_cache_release(page); - goto out_unlock; + goto err_reservations; } } + if (page->mapping != inode->i_mapping) { + unlock_page(page); + page_cache_release(page); + goto again; + } + wait_on_page_writeback(page); + if (PageDirty(page)) { + btrfs_free_reserved_data_space(root, inode, + PAGE_CACHE_SIZE); + goto loop_unlock; + } + page_start = (u64)page->index << PAGE_CACHE_SHIFT; page_end = page_start + PAGE_CACHE_SIZE - 1; lock_extent(io_tree, page_start, page_end, GFP_NOFS); @@ -537,18 +669,54 @@ again: * page if it is dirtied again later */ clear_page_dirty_for_io(page); + clear_extent_bits(&BTRFS_I(inode)->io_tree, page_start, + page_end, EXTENT_DIRTY | EXTENT_DELALLOC | + EXTENT_DO_ACCOUNTING, GFP_NOFS); - btrfs_set_extent_delalloc(inode, page_start, page_end); + btrfs_set_extent_delalloc(inode, page_start, page_end, NULL); + ClearPageChecked(page); set_page_dirty(page); unlock_extent(io_tree, page_start, page_end, GFP_NOFS); + +loop_unlock: unlock_page(page); page_cache_release(page); + mutex_unlock(&inode->i_mutex); + + btrfs_unreserve_metadata_for_delalloc(root, inode, 1); balance_dirty_pages_ratelimited_nr(inode->i_mapping, 1); + i++; + } + + if ((range->flags & BTRFS_DEFRAG_RANGE_START_IO)) + filemap_flush(inode->i_mapping); + + if ((range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)) { + /* the filemap_flush will queue IO into the worker threads, but + * we have to make sure the IO is actually started and that + * ordered extents get created before we return + */ + atomic_inc(&root->fs_info->async_submit_draining); + while (atomic_read(&root->fs_info->nr_async_submits) || + atomic_read(&root->fs_info->async_delalloc_pages)) { + wait_event(root->fs_info->async_submit_wait, + (atomic_read(&root->fs_info->nr_async_submits) == 0 && + atomic_read(&root->fs_info->async_delalloc_pages) == 0)); + } + atomic_dec(&root->fs_info->async_submit_draining); + + mutex_lock(&inode->i_mutex); + BTRFS_I(inode)->force_compress = 0; + mutex_unlock(&inode->i_mutex); } -out_unlock: - mutex_unlock(&inode->i_mutex); return 0; + +err_reservations: + mutex_unlock(&inode->i_mutex); + btrfs_free_reserved_data_space(root, inode, PAGE_CACHE_SIZE); + btrfs_unreserve_metadata_for_delalloc(root, inode, 1); + return ret; } static noinline int btrfs_ioctl_resize(struct btrfs_root *root, @@ -608,7 +776,7 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root, mod = 1; sizestr++; } - new_size = btrfs_parse_size(sizestr); + new_size = memparse(sizestr, NULL); if (new_size == 0) { ret = -EINVAL; goto out_unlock; @@ -743,6 +911,327 @@ out: return ret; } +static noinline int key_in_sk(struct btrfs_key *key, + struct btrfs_ioctl_search_key *sk) +{ + struct btrfs_key test; + int ret; + + test.objectid = sk->min_objectid; + test.type = sk->min_type; + test.offset = sk->min_offset; + + ret = btrfs_comp_cpu_keys(key, &test); + if (ret < 0) + return 0; + + test.objectid = sk->max_objectid; + test.type = sk->max_type; + test.offset = sk->max_offset; + + ret = btrfs_comp_cpu_keys(key, &test); + if (ret > 0) + return 0; + return 1; +} + +static noinline int copy_to_sk(struct btrfs_root *root, + struct btrfs_path *path, + struct btrfs_key *key, + struct btrfs_ioctl_search_key *sk, + char *buf, + unsigned long *sk_offset, + int *num_found) +{ + u64 found_transid; + struct extent_buffer *leaf; + struct btrfs_ioctl_search_header sh; + unsigned long item_off; + unsigned long item_len; + int nritems; + int i; + int slot; + int found = 0; + int ret = 0; + + leaf = path->nodes[0]; + slot = path->slots[0]; + nritems = btrfs_header_nritems(leaf); + + if (btrfs_header_generation(leaf) > sk->max_transid) { + i = nritems; + goto advance_key; + } + found_transid = btrfs_header_generation(leaf); + + for (i = slot; i < nritems; i++) { + item_off = btrfs_item_ptr_offset(leaf, i); + item_len = btrfs_item_size_nr(leaf, i); + + if (item_len > BTRFS_SEARCH_ARGS_BUFSIZE) + item_len = 0; + + if (sizeof(sh) + item_len + *sk_offset > + BTRFS_SEARCH_ARGS_BUFSIZE) { + ret = 1; + goto overflow; + } + + btrfs_item_key_to_cpu(leaf, key, i); + if (!key_in_sk(key, sk)) + continue; + + sh.objectid = key->objectid; + sh.offset = key->offset; + sh.type = key->type; + sh.len = item_len; + sh.transid = found_transid; + + /* copy search result header */ + memcpy(buf + *sk_offset, &sh, sizeof(sh)); + *sk_offset += sizeof(sh); + + if (item_len) { + char *p = buf + *sk_offset; + /* copy the item */ + read_extent_buffer(leaf, p, + item_off, item_len); + *sk_offset += item_len; + } + found++; + + if (*num_found >= sk->nr_items) + break; + } +advance_key: + ret = 0; + if (key->offset < (u64)-1 && key->offset < sk->max_offset) + key->offset++; + else if (key->type < (u8)-1 && key->type < sk->max_type) { + key->offset = 0; + key->type++; + } else if (key->objectid < (u64)-1 && key->objectid < sk->max_objectid) { + key->offset = 0; + key->type = 0; + key->objectid++; + } else + ret = 1; +overflow: + *num_found += found; + return ret; +} + +static noinline int search_ioctl(struct inode *inode, + struct btrfs_ioctl_search_args *args) +{ + struct btrfs_root *root; + struct btrfs_key key; + struct btrfs_key max_key; + struct btrfs_path *path; + struct btrfs_ioctl_search_key *sk = &args->key; + struct btrfs_fs_info *info = BTRFS_I(inode)->root->fs_info; + int ret; + int num_found = 0; + unsigned long sk_offset = 0; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + + if (sk->tree_id == 0) { + /* search the root of the inode that was passed */ + root = BTRFS_I(inode)->root; + } else { + key.objectid = sk->tree_id; + key.type = BTRFS_ROOT_ITEM_KEY; + key.offset = (u64)-1; + root = btrfs_read_fs_root_no_name(info, &key); + if (IS_ERR(root)) { + printk(KERN_ERR "could not find root %llu\n", + sk->tree_id); + btrfs_free_path(path); + return -ENOENT; + } + } + + key.objectid = sk->min_objectid; + key.type = sk->min_type; + key.offset = sk->min_offset; + + max_key.objectid = sk->max_objectid; + max_key.type = sk->max_type; + max_key.offset = sk->max_offset; + + path->keep_locks = 1; + + while(1) { + ret = btrfs_search_forward(root, &key, &max_key, path, 0, + sk->min_transid); + if (ret != 0) { + if (ret > 0) + ret = 0; + goto err; + } + ret = copy_to_sk(root, path, &key, sk, args->buf, + &sk_offset, &num_found); + btrfs_release_path(root, path); + if (ret || num_found >= sk->nr_items) + break; + + } + ret = 0; +err: + sk->nr_items = num_found; + btrfs_free_path(path); + return ret; +} + +static noinline int btrfs_ioctl_tree_search(struct file *file, + void __user *argp) +{ + struct btrfs_ioctl_search_args *args; + struct inode *inode; + int ret; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + args = kmalloc(sizeof(*args), GFP_KERNEL); + if (!args) + return -ENOMEM; + + if (copy_from_user(args, argp, sizeof(*args))) { + kfree(args); + return -EFAULT; + } + inode = fdentry(file)->d_inode; + ret = search_ioctl(inode, args); + if (ret == 0 && copy_to_user(argp, args, sizeof(*args))) + ret = -EFAULT; + kfree(args); + return ret; +} + +/* + * Search INODE_REFs to identify path name of 'dirid' directory + * in a 'tree_id' tree. and sets path name to 'name'. + */ +static noinline int btrfs_search_path_in_tree(struct btrfs_fs_info *info, + u64 tree_id, u64 dirid, char *name) +{ + struct btrfs_root *root; + struct btrfs_key key; + char *ptr; + int ret = -1; + int slot; + int len; + int total_len = 0; + struct btrfs_inode_ref *iref; + struct extent_buffer *l; + struct btrfs_path *path; + + if (dirid == BTRFS_FIRST_FREE_OBJECTID) { + name[0]='\0'; + return 0; + } + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + + ptr = &name[BTRFS_INO_LOOKUP_PATH_MAX]; + + key.objectid = tree_id; + key.type = BTRFS_ROOT_ITEM_KEY; + key.offset = (u64)-1; + root = btrfs_read_fs_root_no_name(info, &key); + if (IS_ERR(root)) { + printk(KERN_ERR "could not find root %llu\n", tree_id); + ret = -ENOENT; + goto out; + } + + key.objectid = dirid; + key.type = BTRFS_INODE_REF_KEY; + key.offset = (u64)-1; + + while(1) { + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) + goto out; + + l = path->nodes[0]; + slot = path->slots[0]; + if (ret > 0 && slot > 0) + slot--; + btrfs_item_key_to_cpu(l, &key, slot); + + if (ret > 0 && (key.objectid != dirid || + key.type != BTRFS_INODE_REF_KEY)) { + ret = -ENOENT; + goto out; + } + + iref = btrfs_item_ptr(l, slot, struct btrfs_inode_ref); + len = btrfs_inode_ref_name_len(l, iref); + ptr -= len + 1; + total_len += len + 1; + if (ptr < name) + goto out; + + *(ptr + len) = '/'; + read_extent_buffer(l, ptr,(unsigned long)(iref + 1), len); + + if (key.offset == BTRFS_FIRST_FREE_OBJECTID) + break; + + btrfs_release_path(root, path); + key.objectid = key.offset; + key.offset = (u64)-1; + dirid = key.objectid; + + } + if (ptr < name) + goto out; + memcpy(name, ptr, total_len); + name[total_len]='\0'; + ret = 0; +out: + btrfs_free_path(path); + return ret; +} + +static noinline int btrfs_ioctl_ino_lookup(struct file *file, + void __user *argp) +{ + struct btrfs_ioctl_ino_lookup_args *args; + struct inode *inode; + int ret; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + args = kmalloc(sizeof(*args), GFP_KERNEL); + if (copy_from_user(args, argp, sizeof(*args))) { + kfree(args); + return -EFAULT; + } + inode = fdentry(file)->d_inode; + + if (args->treeid == 0) + args->treeid = BTRFS_I(inode)->root->root_key.objectid; + + ret = btrfs_search_path_in_tree(BTRFS_I(inode)->root->fs_info, + args->treeid, args->objectid, + args->name); + + if (ret == 0 && copy_to_user(argp, args, sizeof(*args))) + ret = -EFAULT; + + kfree(args); + return ret; +} + static noinline int btrfs_ioctl_snap_destroy(struct file *file, void __user *arg) { @@ -849,10 +1338,11 @@ out: return err; } -static int btrfs_ioctl_defrag(struct file *file) +static int btrfs_ioctl_defrag(struct file *file, void __user *argp) { struct inode *inode = fdentry(file)->d_inode; struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_ioctl_defrag_range_args *range; int ret; ret = mnt_want_write(file->f_path.mnt); @@ -873,7 +1363,30 @@ static int btrfs_ioctl_defrag(struct file *file) ret = -EINVAL; goto out; } - btrfs_defrag_file(file); + + range = kzalloc(sizeof(*range), GFP_KERNEL); + if (!range) { + ret = -ENOMEM; + goto out; + } + + if (argp) { + if (copy_from_user(range, argp, + sizeof(*range))) { + ret = -EFAULT; + kfree(range); + } + /* compression requires us to start the IO */ + if ((range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)) { + range->flags |= BTRFS_DEFRAG_RANGE_START_IO; + range->extent_thresh = (u32)-1; + } + } else { + /* the rest are all set to zero by kzalloc */ + range->len = (u64)-1; + } + btrfs_defrag_file(file, range); + kfree(range); break; } out: @@ -1274,6 +1787,157 @@ out: return ret; } +static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp) +{ + struct inode *inode = fdentry(file)->d_inode; + struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_root *new_root; + struct btrfs_dir_item *di; + struct btrfs_trans_handle *trans; + struct btrfs_path *path; + struct btrfs_key location; + struct btrfs_disk_key disk_key; + struct btrfs_super_block *disk_super; + u64 features; + u64 objectid = 0; + u64 dir_id; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (copy_from_user(&objectid, argp, sizeof(objectid))) + return -EFAULT; + + if (!objectid) + objectid = root->root_key.objectid; + + location.objectid = objectid; + location.type = BTRFS_ROOT_ITEM_KEY; + location.offset = (u64)-1; + + new_root = btrfs_read_fs_root_no_name(root->fs_info, &location); + if (IS_ERR(new_root)) + return PTR_ERR(new_root); + + if (btrfs_root_refs(&new_root->root_item) == 0) + return -ENOENT; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + path->leave_spinning = 1; + + trans = btrfs_start_transaction(root, 1); + if (!trans) { + btrfs_free_path(path); + return -ENOMEM; + } + + dir_id = btrfs_super_root_dir(&root->fs_info->super_copy); + di = btrfs_lookup_dir_item(trans, root->fs_info->tree_root, path, + dir_id, "default", 7, 1); + if (!di) { + btrfs_free_path(path); + btrfs_end_transaction(trans, root); + printk(KERN_ERR "Umm, you don't have the default dir item, " + "this isn't going to work\n"); + return -ENOENT; + } + + btrfs_cpu_key_to_disk(&disk_key, &new_root->root_key); + btrfs_set_dir_item_key(path->nodes[0], di, &disk_key); + btrfs_mark_buffer_dirty(path->nodes[0]); + btrfs_free_path(path); + + disk_super = &root->fs_info->super_copy; + features = btrfs_super_incompat_flags(disk_super); + if (!(features & BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL)) { + features |= BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL; + btrfs_set_super_incompat_flags(disk_super, features); + } + btrfs_end_transaction(trans, root); + + return 0; +} + +long btrfs_ioctl_space_info(struct btrfs_root *root, void __user *arg) +{ + struct btrfs_ioctl_space_args space_args; + struct btrfs_ioctl_space_info space; + struct btrfs_ioctl_space_info *dest; + struct btrfs_ioctl_space_info *dest_orig; + struct btrfs_ioctl_space_info *user_dest; + struct btrfs_space_info *info; + int alloc_size; + int ret = 0; + int slot_count = 0; + + if (copy_from_user(&space_args, + (struct btrfs_ioctl_space_args __user *)arg, + sizeof(space_args))) + return -EFAULT; + + /* first we count slots */ + rcu_read_lock(); + list_for_each_entry_rcu(info, &root->fs_info->space_info, list) + slot_count++; + rcu_read_unlock(); + + /* space_slots == 0 means they are asking for a count */ + if (space_args.space_slots == 0) { + space_args.total_spaces = slot_count; + goto out; + } + alloc_size = sizeof(*dest) * slot_count; + /* we generally have at most 6 or so space infos, one for each raid + * level. So, a whole page should be more than enough for everyone + */ + if (alloc_size > PAGE_CACHE_SIZE) + return -ENOMEM; + + space_args.total_spaces = 0; + dest = kmalloc(alloc_size, GFP_NOFS); + if (!dest) + return -ENOMEM; + dest_orig = dest; + + /* now we have a buffer to copy into */ + rcu_read_lock(); + list_for_each_entry_rcu(info, &root->fs_info->space_info, list) { + /* make sure we don't copy more than we allocated + * in our buffer + */ + if (slot_count == 0) + break; + slot_count--; + + /* make sure userland has enough room in their buffer */ + if (space_args.total_spaces >= space_args.space_slots) + break; + + space.flags = info->flags; + space.total_bytes = info->total_bytes; + space.used_bytes = info->bytes_used; + memcpy(dest, &space, sizeof(space)); + dest++; + space_args.total_spaces++; + } + rcu_read_unlock(); + + user_dest = (struct btrfs_ioctl_space_info *) + (arg + sizeof(struct btrfs_ioctl_space_args)); + + if (copy_to_user(user_dest, dest_orig, alloc_size)) + ret = -EFAULT; + + kfree(dest_orig); +out: + if (ret == 0 && copy_to_user(arg, &space_args, sizeof(space_args))) + ret = -EFAULT; + + return ret; +} + /* * there are many ways the trans_start and trans_end ioctls can lead * to deadlocks. They should only be used by applications that @@ -1320,8 +1984,12 @@ long btrfs_ioctl(struct file *file, unsigned int return btrfs_ioctl_snap_create(file, argp, 1); case BTRFS_IOC_SNAP_DESTROY: return btrfs_ioctl_snap_destroy(file, argp); + case BTRFS_IOC_DEFAULT_SUBVOL: + return btrfs_ioctl_default_subvol(file, argp); case BTRFS_IOC_DEFRAG: - return btrfs_ioctl_defrag(file); + return btrfs_ioctl_defrag(file, NULL); + case BTRFS_IOC_DEFRAG_RANGE: + return btrfs_ioctl_defrag(file, argp); case BTRFS_IOC_RESIZE: return btrfs_ioctl_resize(root, argp); case BTRFS_IOC_ADD_DEV: @@ -1338,6 +2006,12 @@ long btrfs_ioctl(struct file *file, unsigned int return btrfs_ioctl_trans_start(file); case BTRFS_IOC_TRANS_END: return btrfs_ioctl_trans_end(file); + case BTRFS_IOC_TREE_SEARCH: + return btrfs_ioctl_tree_search(file, argp); + case BTRFS_IOC_INO_LOOKUP: + return btrfs_ioctl_ino_lookup(file, argp); + case BTRFS_IOC_SPACE_INFO: + return btrfs_ioctl_space_info(root, argp); case BTRFS_IOC_SYNC: btrfs_sync_fs(file->f_dentry->d_sb, 1); return 0; diff --git a/fs/btrfs/ioctl.h b/fs/btrfs/ioctl.h index bc49914475eb..424694aa517f 100644 --- a/fs/btrfs/ioctl.h +++ b/fs/btrfs/ioctl.h @@ -30,12 +30,114 @@ struct btrfs_ioctl_vol_args { char name[BTRFS_PATH_NAME_MAX + 1]; }; +#define BTRFS_INO_LOOKUP_PATH_MAX 4080 +struct btrfs_ioctl_ino_lookup_args { + __u64 treeid; + __u64 objectid; + char name[BTRFS_INO_LOOKUP_PATH_MAX]; +}; + +struct btrfs_ioctl_search_key { + /* which root are we searching. 0 is the tree of tree roots */ + __u64 tree_id; + + /* keys returned will be >= min and <= max */ + __u64 min_objectid; + __u64 max_objectid; + + /* keys returned will be >= min and <= max */ + __u64 min_offset; + __u64 max_offset; + + /* max and min transids to search for */ + __u64 min_transid; + __u64 max_transid; + + /* keys returned will be >= min and <= max */ + __u32 min_type; + __u32 max_type; + + /* + * how many items did userland ask for, and how many are we + * returning + */ + __u32 nr_items; + + /* align to 64 bits */ + __u32 unused; + + /* some extra for later */ + __u64 unused1; + __u64 unused2; + __u64 unused3; + __u64 unused4; +}; + +struct btrfs_ioctl_search_header { + __u64 transid; + __u64 objectid; + __u64 offset; + __u32 type; + __u32 len; +}; + +#define BTRFS_SEARCH_ARGS_BUFSIZE (4096 - sizeof(struct btrfs_ioctl_search_key)) +/* + * the buf is an array of search headers where + * each header is followed by the actual item + * the type field is expanded to 32 bits for alignment + */ +struct btrfs_ioctl_search_args { + struct btrfs_ioctl_search_key key; + char buf[BTRFS_SEARCH_ARGS_BUFSIZE]; +}; + struct btrfs_ioctl_clone_range_args { __s64 src_fd; __u64 src_offset, src_length; __u64 dest_offset; }; +/* flags for the defrag range ioctl */ +#define BTRFS_DEFRAG_RANGE_COMPRESS 1 +#define BTRFS_DEFRAG_RANGE_START_IO 2 + +struct btrfs_ioctl_defrag_range_args { + /* start of the defrag operation */ + __u64 start; + + /* number of bytes to defrag, use (u64)-1 to say all */ + __u64 len; + + /* + * flags for the operation, which can include turning + * on compression for this one defrag + */ + __u64 flags; + + /* + * any extent bigger than this will be considered + * already defragged. Use 0 to take the kernel default + * Use 1 to say every single extent must be rewritten + */ + __u32 extent_thresh; + + /* spare for later */ + __u32 unused[5]; +}; + +struct btrfs_ioctl_space_info { + __u64 flags; + __u64 total_bytes; + __u64 used_bytes; +}; + +struct btrfs_ioctl_space_args { + __u64 space_slots; + __u64 total_spaces; + struct btrfs_ioctl_space_info spaces[0]; +}; + #define BTRFS_IOC_SNAP_CREATE _IOW(BTRFS_IOCTL_MAGIC, 1, \ struct btrfs_ioctl_vol_args) #define BTRFS_IOC_DEFRAG _IOW(BTRFS_IOCTL_MAGIC, 2, \ @@ -67,4 +169,13 @@ struct btrfs_ioctl_clone_range_args { struct btrfs_ioctl_vol_args) #define BTRFS_IOC_SNAP_DESTROY _IOW(BTRFS_IOCTL_MAGIC, 15, \ struct btrfs_ioctl_vol_args) +#define BTRFS_IOC_DEFRAG_RANGE _IOW(BTRFS_IOCTL_MAGIC, 16, \ + struct btrfs_ioctl_defrag_range_args) +#define BTRFS_IOC_TREE_SEARCH _IOWR(BTRFS_IOCTL_MAGIC, 17, \ + struct btrfs_ioctl_search_args) +#define BTRFS_IOC_INO_LOOKUP _IOWR(BTRFS_IOCTL_MAGIC, 18, \ + struct btrfs_ioctl_ino_lookup_args) +#define BTRFS_IOC_DEFAULT_SUBVOL _IOW(BTRFS_IOCTL_MAGIC, 19, u64) +#define BTRFS_IOC_SPACE_INFO _IOWR(BTRFS_IOCTL_MAGIC, 20, \ + struct btrfs_ioctl_space_args) #endif diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 5c2a9e78a949..a8ffecd0b491 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -174,7 +174,6 @@ int btrfs_add_ordered_extent(struct inode *inode, u64 file_offset, if (!entry) return -ENOMEM; - mutex_lock(&tree->mutex); entry->file_offset = file_offset; entry->start = start; entry->len = len; @@ -190,16 +189,17 @@ int btrfs_add_ordered_extent(struct inode *inode, u64 file_offset, INIT_LIST_HEAD(&entry->list); INIT_LIST_HEAD(&entry->root_extent_list); + spin_lock(&tree->lock); node = tree_insert(&tree->tree, file_offset, &entry->rb_node); BUG_ON(node); + spin_unlock(&tree->lock); spin_lock(&BTRFS_I(inode)->root->fs_info->ordered_extent_lock); list_add_tail(&entry->root_extent_list, &BTRFS_I(inode)->root->fs_info->ordered_extents); spin_unlock(&BTRFS_I(inode)->root->fs_info->ordered_extent_lock); - mutex_unlock(&tree->mutex); BUG_ON(node); return 0; } @@ -216,9 +216,9 @@ int btrfs_add_ordered_sum(struct inode *inode, struct btrfs_ordered_inode_tree *tree; tree = &BTRFS_I(inode)->ordered_tree; - mutex_lock(&tree->mutex); + spin_lock(&tree->lock); list_add_tail(&sum->list, &entry->list); - mutex_unlock(&tree->mutex); + spin_unlock(&tree->lock); return 0; } @@ -232,15 +232,16 @@ int btrfs_add_ordered_sum(struct inode *inode, * to make sure this function only returns 1 once for a given ordered extent. */ int btrfs_dec_test_ordered_pending(struct inode *inode, + struct btrfs_ordered_extent **cached, u64 file_offset, u64 io_size) { struct btrfs_ordered_inode_tree *tree; struct rb_node *node; - struct btrfs_ordered_extent *entry; + struct btrfs_ordered_extent *entry = NULL; int ret; tree = &BTRFS_I(inode)->ordered_tree; - mutex_lock(&tree->mutex); + spin_lock(&tree->lock); node = tree_search(tree, file_offset); if (!node) { ret = 1; @@ -264,7 +265,11 @@ int btrfs_dec_test_ordered_pending(struct inode *inode, else ret = 1; out: - mutex_unlock(&tree->mutex); + if (!ret && cached && entry) { + *cached = entry; + atomic_inc(&entry->refs); + } + spin_unlock(&tree->lock); return ret == 0; } @@ -291,7 +296,7 @@ int btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry) /* * remove an ordered extent from the tree. No references are dropped - * and you must wake_up entry->wait. You must hold the tree mutex + * and you must wake_up entry->wait. You must hold the tree lock * while you call this function. */ static int __btrfs_remove_ordered_extent(struct inode *inode, @@ -340,9 +345,9 @@ int btrfs_remove_ordered_extent(struct inode *inode, int ret; tree = &BTRFS_I(inode)->ordered_tree; - mutex_lock(&tree->mutex); + spin_lock(&tree->lock); ret = __btrfs_remove_ordered_extent(inode, entry); - mutex_unlock(&tree->mutex); + spin_unlock(&tree->lock); wake_up(&entry->wait); return ret; @@ -567,7 +572,7 @@ struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct inode *inode, struct btrfs_ordered_extent *entry = NULL; tree = &BTRFS_I(inode)->ordered_tree; - mutex_lock(&tree->mutex); + spin_lock(&tree->lock); node = tree_search(tree, file_offset); if (!node) goto out; @@ -578,7 +583,7 @@ struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct inode *inode, if (entry) atomic_inc(&entry->refs); out: - mutex_unlock(&tree->mutex); + spin_unlock(&tree->lock); return entry; } @@ -594,7 +599,7 @@ btrfs_lookup_first_ordered_extent(struct inode *inode, u64 file_offset) struct btrfs_ordered_extent *entry = NULL; tree = &BTRFS_I(inode)->ordered_tree; - mutex_lock(&tree->mutex); + spin_lock(&tree->lock); node = tree_search(tree, file_offset); if (!node) goto out; @@ -602,7 +607,7 @@ btrfs_lookup_first_ordered_extent(struct inode *inode, u64 file_offset) entry = rb_entry(node, struct btrfs_ordered_extent, rb_node); atomic_inc(&entry->refs); out: - mutex_unlock(&tree->mutex); + spin_unlock(&tree->lock); return entry; } @@ -629,7 +634,7 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset, else offset = ALIGN(offset, BTRFS_I(inode)->root->sectorsize); - mutex_lock(&tree->mutex); + spin_lock(&tree->lock); disk_i_size = BTRFS_I(inode)->disk_i_size; /* truncate file */ @@ -735,7 +740,7 @@ out: */ if (ordered) __btrfs_remove_ordered_extent(inode, ordered); - mutex_unlock(&tree->mutex); + spin_unlock(&tree->lock); if (ordered) wake_up(&ordered->wait); return ret; @@ -762,7 +767,7 @@ int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr, if (!ordered) return 1; - mutex_lock(&tree->mutex); + spin_lock(&tree->lock); list_for_each_entry_reverse(ordered_sum, &ordered->list, list) { if (disk_bytenr >= ordered_sum->bytenr) { num_sectors = ordered_sum->len / sectorsize; @@ -777,7 +782,7 @@ int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr, } } out: - mutex_unlock(&tree->mutex); + spin_unlock(&tree->lock); btrfs_put_ordered_extent(ordered); return ret; } diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h index 1fe1282ef47c..c82f76a9f040 100644 --- a/fs/btrfs/ordered-data.h +++ b/fs/btrfs/ordered-data.h @@ -21,7 +21,7 @@ /* one of these per inode */ struct btrfs_ordered_inode_tree { - struct mutex mutex; + spinlock_t lock; struct rb_root tree; struct rb_node *last; }; @@ -128,8 +128,8 @@ static inline int btrfs_ordered_sum_size(struct btrfs_root *root, static inline void btrfs_ordered_inode_tree_init(struct btrfs_ordered_inode_tree *t) { - mutex_init(&t->mutex); - t->tree.rb_node = NULL; + spin_lock_init(&t->lock); + t->tree = RB_ROOT; t->last = NULL; } @@ -137,7 +137,8 @@ int btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry); int btrfs_remove_ordered_extent(struct inode *inode, struct btrfs_ordered_extent *entry); int btrfs_dec_test_ordered_pending(struct inode *inode, - u64 file_offset, u64 io_size); + struct btrfs_ordered_extent **cached, + u64 file_offset, u64 io_size); int btrfs_add_ordered_extent(struct inode *inode, u64 file_offset, u64 start, u64 len, u64 disk_len, int tyep); int btrfs_add_ordered_sum(struct inode *inode, diff --git a/fs/btrfs/ref-cache.h b/fs/btrfs/ref-cache.h index bc283ad2db73..e2a55cb2072b 100644 --- a/fs/btrfs/ref-cache.h +++ b/fs/btrfs/ref-cache.h @@ -52,7 +52,7 @@ static inline size_t btrfs_leaf_ref_size(int nr_extents) static inline void btrfs_leaf_ref_tree_init(struct btrfs_leaf_ref_tree *tree) { - tree->root.rb_node = NULL; + tree->root = RB_ROOT; INIT_LIST_HEAD(&tree->list); spin_lock_init(&tree->lock); } diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index ab7ab5318745..0b23942cbc0d 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -170,14 +170,14 @@ struct async_merge { static void mapping_tree_init(struct mapping_tree *tree) { - tree->rb_root.rb_node = NULL; + tree->rb_root = RB_ROOT; spin_lock_init(&tree->lock); } static void backref_cache_init(struct backref_cache *cache) { int i; - cache->rb_root.rb_node = NULL; + cache->rb_root = RB_ROOT; for (i = 0; i < BTRFS_MAX_LEVEL; i++) INIT_LIST_HEAD(&cache->pending[i]); spin_lock_init(&cache->lock); @@ -2659,7 +2659,7 @@ static int relocate_file_extent_cluster(struct inode *inode, EXTENT_BOUNDARY, GFP_NOFS); nr++; } - btrfs_set_extent_delalloc(inode, page_start, page_end); + btrfs_set_extent_delalloc(inode, page_start, page_end, NULL); set_page_dirty(page); dirty_page++; @@ -3487,7 +3487,7 @@ static struct inode *create_reloc_inode(struct btrfs_fs_info *fs_info, key.objectid = objectid; key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; - inode = btrfs_iget(root->fs_info->sb, &key, root); + inode = btrfs_iget(root->fs_info->sb, &key, root, NULL); BUG_ON(IS_ERR(inode) || is_bad_inode(inode)); BTRFS_I(inode)->index_cnt = group->key.objectid; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 8a1ea6e64575..9ac612e6ca60 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -63,10 +63,10 @@ static void btrfs_put_super(struct super_block *sb) } enum { - Opt_degraded, Opt_subvol, Opt_device, Opt_nodatasum, Opt_nodatacow, - Opt_max_extent, Opt_max_inline, Opt_alloc_start, Opt_nobarrier, - Opt_ssd, Opt_nossd, Opt_ssd_spread, Opt_thread_pool, Opt_noacl, - Opt_compress, Opt_compress_force, Opt_notreelog, Opt_ratio, + Opt_degraded, Opt_subvol, Opt_subvolid, Opt_device, Opt_nodatasum, + Opt_nodatacow, Opt_max_extent, Opt_max_inline, Opt_alloc_start, + Opt_nobarrier, Opt_ssd, Opt_nossd, Opt_ssd_spread, Opt_thread_pool, + Opt_noacl, Opt_compress, Opt_compress_force, Opt_notreelog, Opt_ratio, Opt_flushoncommit, Opt_discard, Opt_err, }; @@ -74,6 +74,7 @@ enum { static match_table_t tokens = { {Opt_degraded, "degraded"}, {Opt_subvol, "subvol=%s"}, + {Opt_subvolid, "subvolid=%d"}, {Opt_device, "device=%s"}, {Opt_nodatasum, "nodatasum"}, {Opt_nodatacow, "nodatacow"}, @@ -95,31 +96,6 @@ static match_table_t tokens = { {Opt_err, NULL}, }; -u64 btrfs_parse_size(char *str) -{ - u64 res; - int mult = 1; - char *end; - char last; - - res = simple_strtoul(str, &end, 10); - - last = end[0]; - if (isalpha(last)) { - last = tolower(last); - switch (last) { - case 'g': - mult *= 1024; - case 'm': - mult *= 1024; - case 'k': - mult *= 1024; - } - res = res * mult; - } - return res; -} - /* * Regular mount options parser. Everything that is needed only when * reading in a new superblock is parsed here. @@ -128,7 +104,7 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) { struct btrfs_fs_info *info = root->fs_info; substring_t args[MAX_OPT_ARGS]; - char *p, *num; + char *p, *num, *orig; int intarg; int ret = 0; @@ -143,6 +119,7 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) if (!options) return -ENOMEM; + orig = options; while ((p = strsep(&options, ",")) != NULL) { int token; @@ -156,6 +133,7 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) btrfs_set_opt(info->mount_opt, DEGRADED); break; case Opt_subvol: + case Opt_subvolid: case Opt_device: /* * These are parsed by btrfs_parse_early_options @@ -213,7 +191,7 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) case Opt_max_extent: num = match_strdup(&args[0]); if (num) { - info->max_extent = btrfs_parse_size(num); + info->max_extent = memparse(num, NULL); kfree(num); info->max_extent = max_t(u64, @@ -225,7 +203,7 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) case Opt_max_inline: num = match_strdup(&args[0]); if (num) { - info->max_inline = btrfs_parse_size(num); + info->max_inline = memparse(num, NULL); kfree(num); if (info->max_inline) { @@ -240,7 +218,7 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) case Opt_alloc_start: num = match_strdup(&args[0]); if (num) { - info->alloc_start = btrfs_parse_size(num); + info->alloc_start = memparse(num, NULL); kfree(num); printk(KERN_INFO "btrfs: allocations start at %llu\n", @@ -280,7 +258,7 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) } } out: - kfree(options); + kfree(orig); return ret; } @@ -291,12 +269,13 @@ out: * only when we need to allocate a new super block. */ static int btrfs_parse_early_options(const char *options, fmode_t flags, - void *holder, char **subvol_name, + void *holder, char **subvol_name, u64 *subvol_objectid, struct btrfs_fs_devices **fs_devices) { substring_t args[MAX_OPT_ARGS]; char *opts, *p; int error = 0; + int intarg; if (!options) goto out; @@ -319,6 +298,18 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags, case Opt_subvol: *subvol_name = match_strdup(&args[0]); break; + case Opt_subvolid: + intarg = 0; + error = match_int(&args[0], &intarg); + if (!error) { + /* we want the original fs_tree */ + if (!intarg) + *subvol_objectid = + BTRFS_FS_TREE_OBJECTID; + else + *subvol_objectid = intarg; + } + break; case Opt_device: error = btrfs_scan_one_device(match_strdup(&args[0]), flags, holder, fs_devices); @@ -346,6 +337,110 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags, return error; } +static struct dentry *get_default_root(struct super_block *sb, + u64 subvol_objectid) +{ + struct btrfs_root *root = sb->s_fs_info; + struct btrfs_root *new_root; + struct btrfs_dir_item *di; + struct btrfs_path *path; + struct btrfs_key location; + struct inode *inode; + struct dentry *dentry; + u64 dir_id; + int new = 0; + + /* + * We have a specific subvol we want to mount, just setup location and + * go look up the root. + */ + if (subvol_objectid) { + location.objectid = subvol_objectid; + location.type = BTRFS_ROOT_ITEM_KEY; + location.offset = (u64)-1; + goto find_root; + } + + path = btrfs_alloc_path(); + if (!path) + return ERR_PTR(-ENOMEM); + path->leave_spinning = 1; + + /* + * Find the "default" dir item which points to the root item that we + * will mount by default if we haven't been given a specific subvolume + * to mount. + */ + dir_id = btrfs_super_root_dir(&root->fs_info->super_copy); + di = btrfs_lookup_dir_item(NULL, root, path, dir_id, "default", 7, 0); + if (!di) { + /* + * Ok the default dir item isn't there. This is weird since + * it's always been there, but don't freak out, just try and + * mount to root most subvolume. + */ + btrfs_free_path(path); + dir_id = BTRFS_FIRST_FREE_OBJECTID; + new_root = root->fs_info->fs_root; + goto setup_root; + } + + btrfs_dir_item_key_to_cpu(path->nodes[0], di, &location); + btrfs_free_path(path); + +find_root: + new_root = btrfs_read_fs_root_no_name(root->fs_info, &location); + if (IS_ERR(new_root)) + return ERR_PTR(PTR_ERR(new_root)); + + if (btrfs_root_refs(&new_root->root_item) == 0) + return ERR_PTR(-ENOENT); + + dir_id = btrfs_root_dirid(&new_root->root_item); +setup_root: + location.objectid = dir_id; + location.type = BTRFS_INODE_ITEM_KEY; + location.offset = 0; + + inode = btrfs_iget(sb, &location, new_root, &new); + if (!inode) + return ERR_PTR(-ENOMEM); + + /* + * If we're just mounting the root most subvol put the inode and return + * a reference to the dentry. We will have already gotten a reference + * to the inode in btrfs_fill_super so we're good to go. + */ + if (!new && sb->s_root->d_inode == inode) { + iput(inode); + return dget(sb->s_root); + } + + if (new) { + const struct qstr name = { .name = "/", .len = 1 }; + + /* + * New inode, we need to make the dentry a sibling of s_root so + * everything gets cleaned up properly on unmount. + */ + dentry = d_alloc(sb->s_root, &name); + if (!dentry) { + iput(inode); + return ERR_PTR(-ENOMEM); + } + d_splice_alias(inode, dentry); + } else { + /* + * We found the inode in cache, just find a dentry for it and + * put the reference to the inode we just got. + */ + dentry = d_find_alias(inode); + iput(inode); + } + + return dentry; +} + static int btrfs_fill_super(struct super_block *sb, struct btrfs_fs_devices *fs_devices, void *data, int silent) @@ -379,7 +474,7 @@ static int btrfs_fill_super(struct super_block *sb, key.objectid = BTRFS_FIRST_FREE_OBJECTID; key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; - inode = btrfs_iget(sb, &key, tree_root->fs_info->fs_root); + inode = btrfs_iget(sb, &key, tree_root->fs_info->fs_root, NULL); if (IS_ERR(inode)) { err = PTR_ERR(inode); goto fail_close; @@ -391,12 +486,6 @@ static int btrfs_fill_super(struct super_block *sb, err = -ENOMEM; goto fail_close; } -#if 0 - /* this does the super kobj at the same time */ - err = btrfs_sysfs_add_super(tree_root->fs_info); - if (err) - goto fail_close; -#endif sb->s_root = root_dentry; @@ -488,19 +577,22 @@ static int btrfs_test_super(struct super_block *s, void *data) static int btrfs_get_sb(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, struct vfsmount *mnt) { - char *subvol_name = NULL; struct block_device *bdev = NULL; struct super_block *s; struct dentry *root; struct btrfs_fs_devices *fs_devices = NULL; fmode_t mode = FMODE_READ; + char *subvol_name = NULL; + u64 subvol_objectid = 0; int error = 0; + int found = 0; if (!(flags & MS_RDONLY)) mode |= FMODE_WRITE; error = btrfs_parse_early_options(data, mode, fs_type, - &subvol_name, &fs_devices); + &subvol_name, &subvol_objectid, + &fs_devices); if (error) return error; @@ -529,6 +621,7 @@ static int btrfs_get_sb(struct file_system_type *fs_type, int flags, goto error_close_devices; } + found = 1; btrfs_close_devices(fs_devices); } else { char b[BDEVNAME_SIZE]; @@ -546,25 +639,35 @@ static int btrfs_get_sb(struct file_system_type *fs_type, int flags, s->s_flags |= MS_ACTIVE; } - if (!strcmp(subvol_name, ".")) - root = dget(s->s_root); - else { - mutex_lock(&s->s_root->d_inode->i_mutex); - root = lookup_one_len(subvol_name, s->s_root, + root = get_default_root(s, subvol_objectid); + if (IS_ERR(root)) { + error = PTR_ERR(root); + deactivate_locked_super(s); + goto error; + } + /* if they gave us a subvolume name bind mount into that */ + if (strcmp(subvol_name, ".")) { + struct dentry *new_root; + mutex_lock(&root->d_inode->i_mutex); + new_root = lookup_one_len(subvol_name, root, strlen(subvol_name)); - mutex_unlock(&s->s_root->d_inode->i_mutex); + mutex_unlock(&root->d_inode->i_mutex); - if (IS_ERR(root)) { + if (IS_ERR(new_root)) { deactivate_locked_super(s); - error = PTR_ERR(root); - goto error_free_subvol_name; + error = PTR_ERR(new_root); + dput(root); + goto error_close_devices; } - if (!root->d_inode) { + if (!new_root->d_inode) { dput(root); + dput(new_root); deactivate_locked_super(s); error = -ENXIO; - goto error_free_subvol_name; + goto error_close_devices; } + dput(root); + root = new_root; } mnt->mnt_sb = s; @@ -579,6 +682,7 @@ error_close_devices: btrfs_close_devices(fs_devices); error_free_subvol_name: kfree(subvol_name); +error: return error; } @@ -623,14 +727,37 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct btrfs_root *root = btrfs_sb(dentry->d_sb); struct btrfs_super_block *disk_super = &root->fs_info->super_copy; + struct list_head *head = &root->fs_info->space_info; + struct btrfs_space_info *found; + u64 total_used = 0; + u64 data_used = 0; int bits = dentry->d_sb->s_blocksize_bits; __be32 *fsid = (__be32 *)root->fs_info->fsid; + rcu_read_lock(); + list_for_each_entry_rcu(found, head, list) { + if (found->flags & (BTRFS_BLOCK_GROUP_DUP| + BTRFS_BLOCK_GROUP_RAID10| + BTRFS_BLOCK_GROUP_RAID1)) { + total_used += found->bytes_used; + if (found->flags & BTRFS_BLOCK_GROUP_DATA) + data_used += found->bytes_used; + else + data_used += found->total_bytes; + } + + total_used += found->bytes_used; + if (found->flags & BTRFS_BLOCK_GROUP_DATA) + data_used += found->bytes_used; + else + data_used += found->total_bytes; + } + rcu_read_unlock(); + buf->f_namelen = BTRFS_NAME_LEN; buf->f_blocks = btrfs_super_total_bytes(disk_super) >> bits; - buf->f_bfree = buf->f_blocks - - (btrfs_super_bytes_used(disk_super) >> bits); - buf->f_bavail = buf->f_bfree; + buf->f_bfree = buf->f_blocks - (total_used >> bits); + buf->f_bavail = buf->f_blocks - (data_used >> bits); buf->f_bsize = dentry->d_sb->s_blocksize; buf->f_type = BTRFS_SUPER_MAGIC; diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index b2acc79f1b34..2d654c1c794d 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -69,7 +69,7 @@ static noinline int join_transaction(struct btrfs_root *root) cur_trans->commit_done = 0; cur_trans->start_time = get_seconds(); - cur_trans->delayed_refs.root.rb_node = NULL; + cur_trans->delayed_refs.root = RB_ROOT; cur_trans->delayed_refs.num_entries = 0; cur_trans->delayed_refs.num_heads_ready = 0; cur_trans->delayed_refs.num_heads = 0; @@ -997,13 +997,10 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, mutex_unlock(&root->fs_info->trans_mutex); - if (flush_on_commit) { + if (flush_on_commit || snap_pending) { btrfs_start_delalloc_inodes(root, 1); ret = btrfs_wait_ordered_extents(root, 0, 1); BUG_ON(ret); - } else if (snap_pending) { - ret = btrfs_wait_ordered_extents(root, 0, 1); - BUG_ON(ret); } /* diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 4a9434b622ec..1255fcc8ade5 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -445,7 +445,7 @@ static noinline struct inode *read_one_inode(struct btrfs_root *root, key.objectid = objectid; key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; - inode = btrfs_iget(root->fs_info->sb, &key, root); + inode = btrfs_iget(root->fs_info->sb, &key, root, NULL); if (IS_ERR(inode)) { inode = NULL; } else if (is_bad_inode(inode)) { diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 41ecbb2347f2..9df8e3f1ccab 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -256,13 +256,13 @@ loop_lock: wake_up(&fs_info->async_submit_wait); BUG_ON(atomic_read(&cur->bi_cnt) == 0); - submit_bio(cur->bi_rw, cur); - num_run++; - batch_run++; if (bio_rw_flagged(cur, BIO_RW_SYNCIO)) num_sync_run++; + submit_bio(cur->bi_rw, cur); + num_run++; + batch_run++; if (need_resched()) { if (num_sync_run) { blk_run_backing_dev(bdi, NULL); @@ -325,16 +325,6 @@ loop_lock: num_sync_run = 0; blk_run_backing_dev(bdi, NULL); } - - cond_resched(); - if (again) - goto loop; - - spin_lock(&device->io_lock); - if (device->pending_bios.head || device->pending_sync_bios.head) - goto loop_lock; - spin_unlock(&device->io_lock); - /* * IO has already been through a long path to get here. Checksumming, * async helper threads, perhaps compression. We've done a pretty @@ -346,6 +336,16 @@ loop_lock: * cared about found its way down here. */ blk_run_backing_dev(bdi, NULL); + + cond_resched(); + if (again) + goto loop; + + spin_lock(&device->io_lock); + if (device->pending_bios.head || device->pending_sync_bios.head) + goto loop_lock; + spin_unlock(&device->io_lock); + done: return 0; } @@ -365,6 +365,7 @@ static noinline int device_list_add(const char *path, struct btrfs_device *device; struct btrfs_fs_devices *fs_devices; u64 found_transid = btrfs_super_generation(disk_super); + char *name; fs_devices = find_fsid(disk_super->fsid); if (!fs_devices) { @@ -411,6 +412,12 @@ static noinline int device_list_add(const char *path, device->fs_devices = fs_devices; fs_devices->num_devices++; + } else if (strcmp(device->name, path)) { + name = kstrdup(path, GFP_NOFS); + if (!name) + return -ENOMEM; + kfree(device->name); + device->name = name; } if (found_transid > fs_devices->latest_trans) { @@ -592,7 +599,7 @@ static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices, goto error_close; disk_super = (struct btrfs_super_block *)bh->b_data; - devid = le64_to_cpu(disk_super->dev_item.devid); + devid = btrfs_stack_device_id(&disk_super->dev_item); if (devid != device->devid) goto error_brelse; @@ -694,7 +701,7 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder, goto error_close; } disk_super = (struct btrfs_super_block *)bh->b_data; - devid = le64_to_cpu(disk_super->dev_item.devid); + devid = btrfs_stack_device_id(&disk_super->dev_item); transid = btrfs_super_generation(disk_super); if (disk_super->label[0]) printk(KERN_INFO "device label %s ", disk_super->label); @@ -1187,7 +1194,7 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path) goto error_close; } disk_super = (struct btrfs_super_block *)bh->b_data; - devid = le64_to_cpu(disk_super->dev_item.devid); + devid = btrfs_stack_device_id(&disk_super->dev_item); dev_uuid = disk_super->dev_item.uuid; device = btrfs_find_device(root, devid, dev_uuid, disk_super->fsid); diff --git a/fs/buffer.c b/fs/buffer.c index 6fa530256bfd..c9c266db0624 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2893,7 +2893,7 @@ int block_write_full_page_endio(struct page *page, get_block_t *get_block, /* * The page straddles i_size. It must be zeroed out on each and every - * writepage invokation because it may be mmapped. "A file is mapped + * writepage invocation because it may be mmapped. "A file is mapped * in multiples of the page size. For a file that is not a multiple of * the page size, the remaining memory is zeroed when mapped, and * writes to that region are not written out to the file." @@ -3265,7 +3265,7 @@ static void recalc_bh_state(void) struct buffer_head *alloc_buffer_head(gfp_t gfp_flags) { - struct buffer_head *ret = kmem_cache_alloc(bh_cachep, gfp_flags); + struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags); if (ret) { INIT_LIST_HEAD(&ret->b_assoc_buffers); get_cpu_var(bh_accounting).nr++; @@ -3352,15 +3352,6 @@ int bh_submit_read(struct buffer_head *bh) } EXPORT_SYMBOL(bh_submit_read); -static void -init_buffer_head(void *data) -{ - struct buffer_head *bh = data; - - memset(bh, 0, sizeof(*bh)); - INIT_LIST_HEAD(&bh->b_assoc_buffers); -} - void __init buffer_init(void) { int nrpages; @@ -3369,7 +3360,7 @@ void __init buffer_init(void) sizeof(struct buffer_head), 0, (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC| SLAB_MEM_SPREAD), - init_buffer_head); + NULL); /* * Limit the bh occupancy to 10% of ZONE_NORMAL diff --git a/fs/cifs/asn1.c b/fs/cifs/asn1.c index 20692fbfdb24..a20bea598933 100644 --- a/fs/cifs/asn1.c +++ b/fs/cifs/asn1.c @@ -136,7 +136,7 @@ asn1_enum_decode(struct asn1_ctx *ctx, __le32 *val) return 0; } - ch = *(ctx->pointer)++; /* ch has 0xa, ptr points to lenght octet */ + ch = *(ctx->pointer)++; /* ch has 0xa, ptr points to length octet */ if ((ch) == ASN1_ENUM) /* if ch value is ENUM, 0xa */ *val = *(++(ctx->pointer)); /* value has enum value */ else diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c index b44ce0a0711c..b1d61d0bdfc7 100644 --- a/fs/cifs/cifs_dfs_ref.c +++ b/fs/cifs/cifs_dfs_ref.c @@ -54,7 +54,7 @@ void cifs_dfs_release_automount_timer(void) * Extracts sharename form full UNC. * i.e. strips from UNC trailing path that is not part of share * name and fixup missing '\' in the begining of DFS node refferal - * if neccessary. + * if necessary. * Returns pointer to share name on success or ERR_PTR on error. * Caller is responsible for freeing returned string. */ diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 9d17df3e0768..611835899844 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -3886,7 +3886,7 @@ parse_DFS_referrals(TRANSACTION2_GET_DFS_REFER_RSP *pSMBr, goto parse_DFS_referrals_exit; } - /* collect neccessary data from referrals */ + /* collect necessary data from referrals */ for (i = 0; i < *num_of_nodes; i++) { char *temp; int max_len; diff --git a/fs/compat.c b/fs/compat.c index 00d90c2e66f0..030602d453b7 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -1795,6 +1795,24 @@ asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp, return ret; } +struct compat_sel_arg_struct { + compat_ulong_t n; + compat_uptr_t inp; + compat_uptr_t outp; + compat_uptr_t exp; + compat_uptr_t tvp; +}; + +asmlinkage long compat_sys_old_select(struct compat_sel_arg_struct __user *arg) +{ + struct compat_sel_arg_struct a; + + if (copy_from_user(&a, arg, sizeof(a))) + return -EFAULT; + return compat_sys_select(a.n, compat_ptr(a.inp), compat_ptr(a.outp), + compat_ptr(a.exp), compat_ptr(a.tvp)); +} + #ifdef HAVE_SET_RESTORE_SIGMASK static long do_compat_pselect(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, diff --git a/fs/dlm/member.c b/fs/dlm/member.c index 84f70bfb0baf..b12532e553f8 100644 --- a/fs/dlm/member.c +++ b/fs/dlm/member.c @@ -312,7 +312,7 @@ int dlm_ls_stop(struct dlm_ls *ls) /* * This in_recovery lock does two things: * 1) Keeps this function from returning until all threads are out - * of locking routines and locking is truely stopped. + * of locking routines and locking is truly stopped. * 2) Keeps any new requests from being processed until it's unlocked * when recovery is complete. */ diff --git a/fs/ext3/super.c b/fs/ext3/super.c index e844accbf55d..1bee604cc6cd 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -164,7 +164,7 @@ void ext3_msg(struct super_block *sb, const char *prefix, * write out the superblock safely. * * We'll just use the journal_abort() error code to record an error in - * the journal instead. On recovery, the journal will compain about + * the journal instead. On recovery, the journal will complain about * that error until we've noted it down and cleared it. */ diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 506713a2ebd8..54df209d2eed 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -69,7 +69,7 @@ * * pa_lstart -> the logical start block for this prealloc space * pa_pstart -> the physical start block for this prealloc space - * pa_len -> lenght for this prealloc space + * pa_len -> length for this prealloc space * pa_free -> free space available in this prealloc space * * The inode preallocation space is used looking at the _logical_ start diff --git a/fs/ext4/super.c b/fs/ext4/super.c index ce84a6ed4a48..ba191dae8730 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -302,7 +302,7 @@ void ext4_journal_abort_handle(const char *caller, const char *err_fn, * write out the superblock safely. * * We'll just use the jbd2_journal_abort() error code to record an error in - * the journal instead. On recovery, the journal will compain about + * the journal instead. On recovery, the journal will complain about * that error until we've noted it down and cleared it. */ diff --git a/fs/fat/inode.c b/fs/fat/inode.c index fbeecdc194dc..0ce143bd7d56 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -558,7 +558,7 @@ static int fat_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_bavail = sbi->free_clusters; buf->f_fsid.val[0] = (u32)id; buf->f_fsid.val[1] = (u32)(id >> 32); - buf->f_namelen = sbi->options.isvfat ? 260 : 12; + buf->f_namelen = sbi->options.isvfat ? FAT_LFN_LEN : 12; return 0; } diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c index f565f24019b5..c1ef50154868 100644 --- a/fs/fat/namei_vfat.c +++ b/fs/fat/namei_vfat.c @@ -502,14 +502,14 @@ xlate_to_uni(const unsigned char *name, int len, unsigned char *outname, *outlen = utf8s_to_utf16s(name, len, (wchar_t *)outname); if (*outlen < 0) return *outlen; - else if (*outlen > 255) + else if (*outlen > FAT_LFN_LEN) return -ENAMETOOLONG; op = &outname[*outlen * sizeof(wchar_t)]; } else { if (nls) { for (i = 0, ip = name, op = outname, *outlen = 0; - i < len && *outlen <= 255; + i < len && *outlen <= FAT_LFN_LEN; *outlen += 1) { if (escape && (*ip == ':')) { @@ -549,7 +549,7 @@ xlate_to_uni(const unsigned char *name, int len, unsigned char *outname, return -ENAMETOOLONG; } else { for (i = 0, ip = name, op = outname, *outlen = 0; - i < len && *outlen <= 255; + i < len && *outlen <= FAT_LFN_LEN; i++, *outlen += 1) { *op++ = *ip++; @@ -701,6 +701,15 @@ static int vfat_find(struct inode *dir, struct qstr *qname, return fat_search_long(dir, qname->name, len, sinfo); } +/* + * (nfsd's) anonymous disconnected dentry? + * NOTE: !IS_ROOT() is not anonymous (I.e. d_splice_alias() did the job). + */ +static int vfat_d_anon_disconn(struct dentry *dentry) +{ + return IS_ROOT(dentry) && (dentry->d_flags & DCACHE_DISCONNECTED); +} + static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) { @@ -729,11 +738,11 @@ static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry, } alias = d_find_alias(inode); - if (alias && !(alias->d_flags & DCACHE_DISCONNECTED)) { + if (alias && !vfat_d_anon_disconn(alias)) { /* - * This inode has non DCACHE_DISCONNECTED dentry. This - * means, the user did ->lookup() by an another name - * (longname vs 8.3 alias of it) in past. + * This inode has non anonymous-DCACHE_DISCONNECTED + * dentry. This means, the user did ->lookup() by an + * another name (longname vs 8.3 alias of it) in past. * * Switch to new one for reason of locality if possible. */ @@ -743,7 +752,9 @@ static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry, iput(inode); unlock_super(sb); return alias; - } + } else + dput(alias); + out: unlock_super(sb); dentry->d_op = sb->s_root->d_op; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 1a822ce2b24b..ec14d19ce501 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -850,7 +850,7 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req) req->in.args[0].size = sizeof(*arg); req->in.args[0].value = arg; req->out.numargs = 1; - /* Variable length arguement used for backward compatibility + /* Variable length argument used for backward compatibility with interface version < 7.5. Rest of init_out is zeroed by do_get_request(), so a short reply is not a problem */ req->out.argvar = 1; diff --git a/fs/gfs2/Kconfig b/fs/gfs2/Kconfig index 4dcddf83326f..a47b43107112 100644 --- a/fs/gfs2/Kconfig +++ b/fs/gfs2/Kconfig @@ -8,7 +8,6 @@ config GFS2_FS select FS_POSIX_ACL select CRC32 select SLOW_WORK - select QUOTA select QUOTACTL help A cluster filesystem. diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index a6abbae8a278..e6dd2aec6f82 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -640,7 +640,7 @@ static int gfs2_lock(struct file *file, int cmd, struct file_lock *fl) if (!(fl->fl_flags & FL_POSIX)) return -ENOLCK; - if (__mandatory_lock(&ip->i_inode)) + if (__mandatory_lock(&ip->i_inode) && fl->fl_type != F_UNLCK) return -ENOLCK; if (cmd == F_CANCELLK) { diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index b8025e51cabf..3aac46f6853e 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -616,7 +616,7 @@ struct gfs2_sbd { unsigned int sd_log_blks_reserved; unsigned int sd_log_commited_buf; unsigned int sd_log_commited_databuf; - unsigned int sd_log_commited_revoke; + int sd_log_commited_revoke; unsigned int sd_log_num_buf; unsigned int sd_log_num_revoke; diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 4511b08fc451..e5bf4b59d46e 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -417,7 +417,7 @@ static unsigned int calc_reserved(struct gfs2_sbd *sdp) databufhdrs_needed = (sdp->sd_log_commited_databuf + (dbuf_limit - 1)) / dbuf_limit; - if (sdp->sd_log_commited_revoke) + if (sdp->sd_log_commited_revoke > 0) revokes = gfs2_struct2blk(sdp, sdp->sd_log_commited_revoke, sizeof(u64)); @@ -790,7 +790,6 @@ static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr) gfs2_assert_withdraw(sdp, (((int)sdp->sd_log_commited_buf) >= 0) || (((int)sdp->sd_log_commited_databuf) >= 0)); sdp->sd_log_commited_revoke += tr->tr_num_revoke - tr->tr_num_revoke_rm; - gfs2_assert_withdraw(sdp, ((int)sdp->sd_log_commited_revoke) >= 0); reserved = calc_reserved(sdp); gfs2_assert_withdraw(sdp, sdp->sd_log_blks_reserved + tr->tr_reserved >= reserved); unused = sdp->sd_log_blks_reserved - reserved + tr->tr_reserved; diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index a054b526dc08..c1309ed1c496 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -1001,7 +1001,7 @@ static const struct lm_lockops nolock_ops = { /** * gfs2_lm_mount - mount a locking protocol * @sdp: the filesystem - * @args: mount arguements + * @args: mount arguments * @silent: if 1, don't complain if the FS isn't a GFS2 fs * * Returns: errno diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c index 99e9fea11077..5ae71e75a491 100644 --- a/fs/jbd/transaction.c +++ b/fs/jbd/transaction.c @@ -1398,7 +1398,7 @@ int journal_stop(handle_t *handle) * the case where our storage is so fast that it is more optimal to go * ahead and force a flush and wait for the transaction to be committed * than it is to wait for an arbitrary amount of time for new writers to - * join the transaction. We acheive this by measuring how long it takes + * join the transaction. We achieve this by measuring how long it takes * to commit a transaction, and compare it with how long this * transaction has been running, and if run time < commit time then we * sleep for the delta and commit. This greatly helps super fast disks diff --git a/fs/jffs2/readinode.c b/fs/jffs2/readinode.c index e22de8397b74..d32ee9412cb9 100644 --- a/fs/jffs2/readinode.c +++ b/fs/jffs2/readinode.c @@ -567,7 +567,7 @@ static void jffs2_free_tmp_dnode_info_list(struct rb_root *list) else BUG(); } } - list->rb_node = NULL; + *list = RB_ROOT; } static void jffs2_free_full_dirent_list(struct jffs2_full_dirent *fd) diff --git a/fs/locks.c b/fs/locks.c index ae9ded026b7c..ab24d49fc048 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1455,7 +1455,7 @@ EXPORT_SYMBOL(generic_setlease); * leases held by processes on this node. * * There is also no break_lease method; filesystems that - * handle their own leases shoud break leases themselves from the + * handle their own leases should break leases themselves from the * filesystem's open, create, and (on truncate) setattr methods. * * Warning: the only current setlease methods exist only to disable diff --git a/fs/mpage.c b/fs/mpage.c index 42381bd6543b..598d54e200eb 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -561,7 +561,7 @@ page_is_mapped: if (page->index >= end_index) { /* * The page straddles i_size. It must be zeroed out on each - * and every writepage invokation because it may be mmapped. + * and every writepage invocation because it may be mmapped. * "A file is mapped in multiples of the page size. For a file * that is not a multiple of the page size, the remaining memory * is zeroed when mapped, and writes to that region are not diff --git a/fs/namei.c b/fs/namei.c index 48e60a187325..1c0fca6e899e 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2544,7 +2544,7 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname * e) conversion from fhandle to dentry may come in the wrong moment - when * we are removing the target. Solution: we will have to grab ->i_mutex * in the fhandle_to_dentry code. [FIXME - current nfsfh.c relies on - * ->i_mutex on parents, which works but leads to some truely excessive + * ->i_mutex on parents, which works but leads to some truly excessive * locking]. */ static int vfs_rename_dir(struct inode *old_dir, struct dentry *old_dentry, diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index db30c0b398b5..a2b8b4df125d 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -782,6 +782,7 @@ struct svc_version nfs4_callback_version1 = { .vs_proc = nfs4_callback_procedures1, .vs_xdrsize = NFS4_CALLBACK_XDRSIZE, .vs_dispatch = NULL, + .vs_hidden = 1, }; struct svc_version nfs4_callback_version4 = { diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h index 944b627ec6e1..69e7b8140122 100644 --- a/fs/nfs/delegation.h +++ b/fs/nfs/delegation.h @@ -71,4 +71,10 @@ static inline int nfs_inode_return_delegation(struct inode *inode) } #endif +static inline int nfs_have_delegated_attributes(struct inode *inode) +{ + return nfs_have_delegation(inode, FMODE_READ) && + !(NFS_I(inode)->cache_validity & NFS_INO_REVAL_FORCED); +} + #endif diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index a1f6b4438fb1..c6f2750648f4 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1789,7 +1789,7 @@ static int nfs_access_get_cached(struct inode *inode, struct rpc_cred *cred, str cache = nfs_access_search_rbtree(inode, cred); if (cache == NULL) goto out; - if (!nfs_have_delegation(inode, FMODE_READ) && + if (!nfs_have_delegated_attributes(inode) && !time_in_range_open(jiffies, cache->jiffies, cache->jiffies + nfsi->attrtimeo)) goto out_stale; res->jiffies = cache->jiffies; diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 657201acda84..e358df75a6ad 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -729,7 +729,7 @@ int nfs_attribute_timeout(struct inode *inode) { struct nfs_inode *nfsi = NFS_I(inode); - if (nfs_have_delegation(inode, FMODE_READ)) + if (nfs_have_delegated_attributes(inode)) return 0; return !time_in_range_open(jiffies, nfsi->read_cache_jiffies, nfsi->read_cache_jiffies + nfsi->attrtimeo); } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index eda74c42d552..f9254fb0c9d0 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5107,6 +5107,7 @@ static int nfs41_proc_async_sequence(struct nfs_client *clp, res = kzalloc(sizeof(*res), GFP_KERNEL); if (!args || !res) { kfree(args); + kfree(res); nfs_put_client(clp); return -ENOMEM; } diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index a12c45b65dd4..29d9d36cd5f4 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -112,12 +112,10 @@ void nfs_unlock_request(struct nfs_page *req) */ int nfs_set_page_tag_locked(struct nfs_page *req) { - struct nfs_inode *nfsi = NFS_I(req->wb_context->path.dentry->d_inode); - if (!nfs_lock_request_dontget(req)) return 0; if (req->wb_page != NULL) - radix_tree_tag_set(&nfsi->nfs_page_tree, req->wb_index, NFS_PAGE_TAG_LOCKED); + radix_tree_tag_set(&NFS_I(req->wb_context->path.dentry->d_inode)->nfs_page_tree, req->wb_index, NFS_PAGE_TAG_LOCKED); return 1; } @@ -126,10 +124,10 @@ int nfs_set_page_tag_locked(struct nfs_page *req) */ void nfs_clear_page_tag_locked(struct nfs_page *req) { - struct inode *inode = req->wb_context->path.dentry->d_inode; - struct nfs_inode *nfsi = NFS_I(inode); - if (req->wb_page != NULL) { + struct inode *inode = req->wb_context->path.dentry->d_inode; + struct nfs_inode *nfsi = NFS_I(inode); + spin_lock(&inode->i_lock); radix_tree_tag_clear(&nfsi->nfs_page_tree, req->wb_index, NFS_PAGE_TAG_LOCKED); nfs_unlock_request(req); @@ -142,16 +140,22 @@ void nfs_clear_page_tag_locked(struct nfs_page *req) * nfs_clear_request - Free up all resources allocated to the request * @req: * - * Release page resources associated with a write request after it - * has completed. + * Release page and open context resources associated with a read/write + * request after it has completed. */ void nfs_clear_request(struct nfs_page *req) { struct page *page = req->wb_page; + struct nfs_open_context *ctx = req->wb_context; + if (page != NULL) { page_cache_release(page); req->wb_page = NULL; } + if (ctx != NULL) { + put_nfs_open_context(ctx); + req->wb_context = NULL; + } } @@ -165,9 +169,8 @@ static void nfs_free_request(struct kref *kref) { struct nfs_page *req = container_of(kref, struct nfs_page, wb_kref); - /* Release struct file or cached credential */ + /* Release struct file and open context */ nfs_clear_request(req); - put_nfs_open_context(req->wb_context); nfs_page_free(req); } diff --git a/fs/nfs/super.c b/fs/nfs/super.c index f1afee4eea77..6baf9a393466 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -2214,7 +2214,7 @@ static int nfs_get_sb(struct file_system_type *fs_type, } else { error = nfs_bdi_register(server); if (error) - goto error_splat_super; + goto error_splat_bdi; } if (!s->s_root) { @@ -2256,6 +2256,9 @@ out_err_nosb: error_splat_root: dput(mntroot); error_splat_super: + if (server && !s->s_root) + bdi_unregister(&server->backing_dev_info); +error_splat_bdi: deactivate_locked_super(s); goto out; } @@ -2326,7 +2329,7 @@ static int nfs_xdev_get_sb(struct file_system_type *fs_type, int flags, } else { error = nfs_bdi_register(server); if (error) - goto error_splat_super; + goto error_splat_bdi; } if (!s->s_root) { @@ -2363,6 +2366,9 @@ out_err_noserver: return error; error_splat_super: + if (server && !s->s_root) + bdi_unregister(&server->backing_dev_info); +error_splat_bdi: deactivate_locked_super(s); dprintk("<-- nfs_xdev_get_sb() = %d [splat]\n", error); return error; @@ -2578,7 +2584,7 @@ static int nfs4_remote_get_sb(struct file_system_type *fs_type, } else { error = nfs_bdi_register(server); if (error) - goto error_splat_super; + goto error_splat_bdi; } if (!s->s_root) { @@ -2616,6 +2622,9 @@ out_free: error_splat_root: dput(mntroot); error_splat_super: + if (server && !s->s_root) + bdi_unregister(&server->backing_dev_info); +error_splat_bdi: deactivate_locked_super(s); goto out; } @@ -2811,7 +2820,7 @@ static int nfs4_xdev_get_sb(struct file_system_type *fs_type, int flags, } else { error = nfs_bdi_register(server); if (error) - goto error_splat_super; + goto error_splat_bdi; } if (!s->s_root) { @@ -2847,6 +2856,9 @@ out_err_noserver: return error; error_splat_super: + if (server && !s->s_root) + bdi_unregister(&server->backing_dev_info); +error_splat_bdi: deactivate_locked_super(s); dprintk("<-- nfs4_xdev_get_sb() = %d [splat]\n", error); return error; @@ -2893,7 +2905,7 @@ static int nfs4_remote_referral_get_sb(struct file_system_type *fs_type, } else { error = nfs_bdi_register(server); if (error) - goto error_splat_super; + goto error_splat_bdi; } if (!s->s_root) { @@ -2929,6 +2941,9 @@ out_err_noserver: return error; error_splat_super: + if (server && !s->s_root) + bdi_unregister(&server->backing_dev_info); +error_splat_bdi: deactivate_locked_super(s); dprintk("<-- nfs4_referral_get_sb() = %d [splat]\n", error); return error; diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 78c7e24e5129..c47b4d7bafa7 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -1528,7 +1528,7 @@ static void write_cinfo(__be32 **p, struct nfsd4_change_info *c) } } while (0); /* Encode as an array of strings the string given with components - * seperated @sep. + * separated @sep. */ static __be32 nfsd4_encode_components(char sep, char *components, __be32 **pp, int *buflen) diff --git a/fs/nilfs2/alloc.h b/fs/nilfs2/alloc.h index f4543ac4f560..5cccf874d692 100644 --- a/fs/nilfs2/alloc.h +++ b/fs/nilfs2/alloc.h @@ -42,7 +42,7 @@ void *nilfs_palloc_block_get_entry(const struct inode *, __u64, const struct buffer_head *, void *); /** - * nilfs_palloc_req - persistent alloctor request and reply + * nilfs_palloc_req - persistent allocator request and reply * @pr_entry_nr: entry number (vblocknr or inode number) * @pr_desc_bh: buffer head of the buffer containing block group descriptors * @pr_bitmap_bh: buffer head of the buffer containing a block group bitmap diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c index 9d1e5de91afb..013146755683 100644 --- a/fs/nilfs2/dat.c +++ b/fs/nilfs2/dat.c @@ -288,7 +288,7 @@ int nilfs_dat_mark_dirty(struct inode *dat, __u64 vblocknr) * @vblocknrs and @nitems. * * Return Value: On success, 0 is returned. On error, one of the following - * nagative error codes is returned. + * negative error codes is returned. * * %-EIO - I/O error. * diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c index 0092840492ee..85c89dfc71f0 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -396,7 +396,7 @@ nilfs_find_entry(struct inode *dir, const struct qstr *qstr, /* next page is past the blocks we've got */ if (unlikely(n > (dir->i_blocks >> (PAGE_CACHE_SHIFT - 9)))) { nilfs_error(dir->i_sb, __func__, - "dir %lu size %lld exceeds block cout %llu", + "dir %lu size %lld exceeds block count %llu", dir->i_ino, dir->i_size, (unsigned long long)dir->i_blocks); goto out; diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c index e16a6664dfa2..8880a9e281e7 100644 --- a/fs/nilfs2/gcinode.c +++ b/fs/nilfs2/gcinode.c @@ -28,10 +28,10 @@ * gcinodes), and this file provides lookup function of the dummy * inodes and their buffer read function. * - * Since NILFS2 keeps up multiple checkpoints/snapshots accross GC, it + * Since NILFS2 keeps up multiple checkpoints/snapshots across GC, it * has to treat blocks that belong to a same file but have different * checkpoint numbers. To avoid interference among generations, dummy - * inodes are managed separatly from actual inodes, and their lookup + * inodes are managed separately from actual inodes, and their lookup * function (nilfs_gc_iget) is designed to be specified with a * checkpoint number argument as well as an inode number. * diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index a2692bbc7b50..fc246dba112a 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -292,7 +292,7 @@ void nilfs_free_private_page(struct page *page) * @src: source page * @copy_dirty: flag whether to copy dirty states on the page's buffer heads. * - * This fuction is for both data pages and btnode pages. The dirty flag + * This function is for both data pages and btnode pages. The dirty flag * should be treated by caller. The page must not be under i/o. * Both src and dst page must be locked */ @@ -388,7 +388,7 @@ repeat: } /** - * nilfs_copy_back_pages -- copy back pages to orignal cache from shadow cache + * nilfs_copy_back_pages -- copy back pages to original cache from shadow cache * @dmap: destination page cache * @smap: source page cache * diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c index ab56fe44e377..636eaafd6ea2 100644 --- a/fs/nilfs2/segbuf.c +++ b/fs/nilfs2/segbuf.c @@ -32,7 +32,7 @@ struct nilfs_write_info { struct the_nilfs *nilfs; struct bio *bio; - int start, end; /* The region to be submitted */ + int start, end; /* The region to be submitted */ int rest_blocks; int max_pages; int nr_vecs; @@ -174,7 +174,7 @@ int nilfs_segbuf_reset(struct nilfs_segment_buffer *segbuf, unsigned flags, } /* - * Setup segument summary + * Setup segment summary */ void nilfs_segbuf_fill_in_segsum(struct nilfs_segment_buffer *segbuf) { @@ -470,8 +470,8 @@ static int nilfs_segbuf_submit_bh(struct nilfs_segment_buffer *segbuf, * * %-ENOMEM - Insufficient memory available. */ -int nilfs_segbuf_write(struct nilfs_segment_buffer *segbuf, - struct the_nilfs *nilfs) +static int nilfs_segbuf_write(struct nilfs_segment_buffer *segbuf, + struct the_nilfs *nilfs) { struct nilfs_write_info wi; struct buffer_head *bh; @@ -514,7 +514,7 @@ int nilfs_segbuf_write(struct nilfs_segment_buffer *segbuf, * * %-EIO - I/O error */ -int nilfs_segbuf_wait(struct nilfs_segment_buffer *segbuf) +static int nilfs_segbuf_wait(struct nilfs_segment_buffer *segbuf) { int err = 0; diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index ada2f1b947a3..69576a95e13f 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -141,7 +141,7 @@ int nilfs_init_transaction_cache(void) } /** - * nilfs_detroy_transaction_cache - destroy the cache for transaction info + * nilfs_destroy_transaction_cache - destroy the cache for transaction info * * nilfs_destroy_transaction_cache() frees the slab cache for the struct * nilfs_transaction_info. @@ -201,7 +201,7 @@ static int nilfs_prepare_segment_lock(struct nilfs_transaction_info *ti) * This function allocates a nilfs_transaction_info struct to keep context * information on it. It is initialized and hooked onto the current task in * the outermost call. If a pre-allocated struct is given to @ti, it is used - * instead; othewise a new struct is assigned from a slab. + * instead; otherwise a new struct is assigned from a slab. * * When @vacancy_check flag is set, this function will check the amount of * free space, and will wait for the GC to reclaim disk space if low capacity. @@ -2214,7 +2214,7 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode) } /** - * nilfs_secgtor_start_timer - set timer of background write + * nilfs_segctor_start_timer - set timer of background write * @sci: nilfs_sc_info * * If the timer has already been set, it ignores the new request. @@ -2854,7 +2854,7 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci) * @sbi: nilfs_sb_info * * nilfs_attach_segment_constructor() allocates a struct nilfs_sc_info, - * initilizes it, and starts the segment constructor. + * initializes it, and starts the segment constructor. * * Return Value: On success, 0 is returned. On error, one of the following * negative error code is returned. diff --git a/fs/nilfs2/segment.h b/fs/nilfs2/segment.h index 3155e0c7f415..82dfd6a686b9 100644 --- a/fs/nilfs2/segment.h +++ b/fs/nilfs2/segment.h @@ -30,7 +30,7 @@ #include "sb.h" /** - * struct nilfs_recovery_info - Recovery infomation + * struct nilfs_recovery_info - Recovery information * @ri_need_recovery: Recovery status * @ri_super_root: Block number of the last super root * @ri_ri_cno: Number of the last checkpoint @@ -71,7 +71,7 @@ struct nilfs_recovery_info { */ struct nilfs_cstage { int scnt; - unsigned flags; + unsigned flags; struct nilfs_inode_info *dirty_file_ptr; struct nilfs_inode_info *gc_inode_ptr; }; diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c index b6c36d0cc331..3c6cc6005c2e 100644 --- a/fs/nilfs2/sufile.c +++ b/fs/nilfs2/sufile.c @@ -18,7 +18,7 @@ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA * * Written by Koji Sato <koji@osrg.net>. - * Rivised by Ryusuke Konishi <ryusuke@osrg.net>. + * Revised by Ryusuke Konishi <ryusuke@osrg.net>. */ #include <linux/kernel.h> diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 92579cc4c935..0cdbc5e7655a 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -436,7 +436,7 @@ static int nilfs_statfs(struct dentry *dentry, struct kstatfs *buf) /* * Compute the overhead * - * When distributing meta data blocks outside semgent structure, + * When distributing meta data blocks outside segment structure, * We must count them as the overhead. */ overhead = 0; @@ -866,7 +866,7 @@ static int nilfs_remount(struct super_block *sb, int *flags, char *data) if ((*flags & MS_RDONLY) && sbi->s_snapshot_cno != old_opts.snapshot_cno) { printk(KERN_WARNING "NILFS (device %s): couldn't " - "remount to a different snapshot. \n", + "remount to a different snapshot.\n", sb->s_id); err = -EINVAL; goto restore_opts; diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index 92733d5651d2..33871f7e4f01 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -386,7 +386,7 @@ static int nilfs_store_disk_layout(struct the_nilfs *nilfs, nilfs->ns_blocks_per_segment = le32_to_cpu(sbp->s_blocks_per_segment); if (nilfs->ns_blocks_per_segment < NILFS_SEG_MIN_BLOCKS) { - printk(KERN_ERR "NILFS: too short segment. \n"); + printk(KERN_ERR "NILFS: too short segment.\n"); return -EINVAL; } diff --git a/fs/ntfs/ChangeLog b/fs/ntfs/ChangeLog deleted file mode 100644 index 37c11e194372..000000000000 --- a/fs/ntfs/ChangeLog +++ /dev/null @@ -1,1702 +0,0 @@ -ToDo/Notes: - - Find and fix bugs. - - The only places in the kernel where a file is resized are - ntfs_file_write*() and ntfs_truncate() for both of which i_mutex is - held. Just have to be careful in read-/writepage and other helpers - not running under i_mutex that we play nice. Also need to be careful - with initialized_size extension in ntfs_file_write*() and writepage. - UPDATE: The only things that need to be checked are the compressed - write and the other attribute resize/write cases like index - attributes, etc. For now none of these are implemented so are safe. - - Implement filling in of holes in aops.c::ntfs_writepage() and its - helpers. - - Implement mft.c::sync_mft_mirror_umount(). We currently will just - leave the volume dirty on umount if the final iput(vol->mft_ino) - causes a write of any mirrored mft records due to the mft mirror - inode having been discarded already. Whether this can actually ever - happen is unclear however so it is worth waiting until someone hits - the problem. - -2.1.29 - Fix a deadlock at mount time. - - - During mount the VFS holds s_umount lock on the superblock. So when - we try to empty the journal $LogFile contents by calling - ntfs_attr_set() when the machine does not have much memory and the - journal is large ntfs_attr_set() results in the VM trying to balance - dirty pages which in turn tries to that the s_umount lock and thus we - get a deadlock. The solution is to not use ntfs_attr_set() and - instead do the zeroing by hand at the block level rather than page - cache level. - - Fix sparse warnings. - -2.1.28 - Fix a deadlock. - - - Fix deadlock in fs/ntfs/inode.c::ntfs_put_inode(). Thanks to Sergey - Vlasov for the report and detailed analysis of the deadlock. The fix - involved getting rid of ntfs_put_inode() altogether and hence NTFS no - longer has a ->put_inode super operation. - -2.1.27 - Various bug fixes and cleanups. - - - Fix two compiler warnings on Alpha. Thanks to Andrew Morton for - reporting them. - - Fix an (innocent) off-by-one error in the runlist code. - - Fix a buggette in an "should be impossible" case handling where we - continued the attribute lookup loop instead of aborting it. - - Use buffer_migrate_page() for the ->migratepage function of all ntfs - address space operations. - - Fix comparison of $MFT and $MFTMirr to not bail out when there are - unused, invalid mft records which are the same in both $MFT and - $MFTMirr. - - Add support for sparse files which have a compression unit of 0. - - Remove all the make_bad_inode() calls. This should only be called - from read inode and new inode code paths. - - Limit name length in fs/ntfs/unistr.c::ntfs_nlstoucs() to maximum - allowed by NTFS, i.e. 255 Unicode characters, not including the - terminating NULL (which is not stored on disk). - - Improve comments on file attribute flags in fs/ntfs/layout.h. - - Fix a bug in fs/ntfs/inode.c::ntfs_read_locked_index_inode() where we - forgot to update a temporary variable so loading index inodes which - have an index allocation attribute failed. - - Add a missing call to flush_dcache_mft_record_page() in - fs/ntfs/inode.c::ntfs_write_inode(). - - Handle the recently introduced -ENAMETOOLONG return value from - fs/ntfs/unistr.c::ntfs_nlstoucs() in fs/ntfs/namei.c::ntfs_lookup(). - - Semaphore to mutex conversion. (Ingo Molnar) - -2.1.26 - Minor bug fixes and updates. - - - Fix a potential overflow in file.c where a cast to s64 was missing in - a left shift of a page index. - - The struct inode has had its i_sem semaphore changed to a mutex named - i_mutex. - - We have struct kmem_cache now so use it instead of the typedef - kmem_cache_t. (Pekka Enberg) - - Implement support for sector sizes above 512 bytes (up to the maximum - supported by NTFS which is 4096 bytes). - - Do more detailed reporting of why we cannot mount read-write by - special casing the VOLUME_MODIFIED_BY_CHKDSK flag. - - Miscellaneous updates to layout.h. - - Cope with attribute list attribute having invalid flags. Windows - copes with this and even chkdsk does not detect or fix this so we - have to cope with it, too. Thanks to Pawel Kot for reporting the - problem. - -2.1.25 - (Almost) fully implement write(2) and truncate(2). - - - Change ntfs_map_runlist_nolock(), ntfs_attr_find_vcn_nolock() and - {__,}ntfs_cluster_free() to also take an optional attribute search - context as argument. This allows calling these functions with the - mft record mapped. Update all callers. - - Fix potential deadlock in ntfs_mft_data_extend_allocation_nolock() - error handling by passing in the active search context when calling - ntfs_cluster_free(). - - Change ntfs_cluster_alloc() to take an extra boolean parameter - specifying whether the cluster are being allocated to extend an - attribute or to fill a hole. - - Change ntfs_attr_make_non_resident() to call ntfs_cluster_alloc() - with @is_extension set to TRUE and remove the runlist terminator - fixup code as this is now done by ntfs_cluster_alloc(). - - Change ntfs_attr_make_non_resident to take the attribute value size - as an extra parameter. This is needed since we need to know the size - before we can map the mft record and our callers always know it. The - reason we cannot simply read the size from the vfs inode i_size is - that this is not necessarily uptodate. This happens when - ntfs_attr_make_non_resident() is called in the ->truncate call path. - - Fix ntfs_attr_make_non_resident() to update the vfs inode i_blocks - which is zero for a resident attribute but should no longer be zero - once the attribute is non-resident as it then has real clusters - allocated. - - Add fs/ntfs/attrib.[hc]::ntfs_attr_extend_allocation(), a function to - extend the allocation of an attributes. Optionally, the data size, - but not the initialized size can be extended, too. - - Implement fs/ntfs/inode.[hc]::ntfs_truncate(). It only supports - uncompressed and unencrypted files and it never creates sparse files - at least for the moment (making a file sparse requires us to modify - its directory entries and we do not support directory operations at - the moment). Also, support for highly fragmented files, i.e. ones - whose data attribute is split across multiple extents, is severly - limited. When such a case is encountered, EOPNOTSUPP is returned. - - Enable ATTR_SIZE attribute changes in ntfs_setattr(). This completes - the initial implementation of file truncation. Now both open(2)ing - a file with the O_TRUNC flag and the {,f}truncate(2) system calls - will resize a file appropriately. The limitations are that only - uncompressed and unencrypted files are supported. Also, there is - only very limited support for highly fragmented files (the ones whose - $DATA attribute is split into multiple attribute extents). - - In attrib.c::ntfs_attr_set() call balance_dirty_pages_ratelimited() - and cond_resched() in the main loop as we could be dirtying a lot of - pages and this ensures we play nice with the VM and the system as a - whole. - - Implement file operations ->write, ->aio_write, ->writev for regular - files. This replaces the old use of generic_file_write(), et al and - the address space operations ->prepare_write and ->commit_write. - This means that both sparse and non-sparse (unencrypted and - uncompressed) files can now be extended using the normal write(2) - code path. There are two limitations at present and these are that - we never create sparse files and that we only have limited support - for highly fragmented files, i.e. ones whose data attribute is split - across multiple extents. When such a case is encountered, - EOPNOTSUPP is returned. - - $EA attributes can be both resident and non-resident. - - Use %z for size_t to fix compilation warnings. (Andrew Morton) - - Fix compilation warnings with gcc-4.0.2 on SUSE 10.0. - - Document extended attribute ($EA) NEED_EA flag. (Based on libntfs - patch by Yura Pakhuchiy.) - -2.1.24 - Lots of bug fixes and support more clean journal states. - - - Support journals ($LogFile) which have been modified by chkdsk. This - means users can boot into Windows after we marked the volume dirty. - The Windows boot will run chkdsk and then reboot. The user can then - immediately boot into Linux rather than having to do a full Windows - boot first before rebooting into Linux and we will recognize such a - journal and empty it as it is clean by definition. Note, this only - works if chkdsk left the journal in an obviously clean state. - - Support journals ($LogFile) with only one restart page as well as - journals with two different restart pages. We sanity check both and - either use the only sane one or the more recent one of the two in the - case that both are valid. - - Add fs/ntfs/malloc.h::ntfs_malloc_nofs_nofail() which is analogous to - ntfs_malloc_nofs() but it performs allocations with __GFP_NOFAIL and - hence cannot fail. - - Use ntfs_malloc_nofs_nofail() in the two critical regions in - fs/ntfs/runlist.c::ntfs_runlists_merge(). This means we no longer - need to panic() if the allocation fails as it now cannot fail. - - Fix two nasty runlist merging bugs that had gone unnoticed so far. - Thanks to Stefano Picerno for the bug report. - - Remove two bogus BUG_ON()s from fs/ntfs/mft.c. - - Fix handling of valid but empty mapping pairs array in - fs/ntfs/runlist.c::ntfs_mapping_pairs_decompress(). - - Report unrepresentable inodes during ntfs_readdir() as KERN_WARNING - messages and include the inode number. Thanks to Yura Pakhuchiy for - pointing this out. - - Change ntfs_rl_truncate_nolock() to throw away the runlist if the new - length is zero. - - Add runlist.[hc]::ntfs_rl_punch_nolock() which punches a caller - specified hole into a runlist. - - Fix a bug in fs/ntfs/index.c::ntfs_index_lookup(). When the returned - index entry is in the index root, we forgot to set the @ir pointer in - the index context. Thanks to Yura Pakhuchiy for finding this bug. - - Remove bogus setting of PageError in ntfs_read_compressed_block(). - - Add fs/ntfs/attrib.[hc]::ntfs_resident_attr_value_resize(). - - Fix a bug in ntfs_map_runlist_nolock() where we forgot to protect - access to the allocated size in the ntfs inode with the size lock. - - Fix ntfs_attr_vcn_to_lcn_nolock() and ntfs_attr_find_vcn_nolock() to - return LCN_ENOENT when there is no runlist and the allocated size is - zero. - - Fix load_attribute_list() to handle the case of a NULL runlist. - - Fix handling of sparse attributes in ntfs_attr_make_non_resident(). - - Add BUG() checks to ntfs_attr_make_non_resident() and ntfs_attr_set() - to ensure that these functions are never called for compressed or - encrypted attributes. - - Fix cluster (de)allocators to work when the runlist is NULL and more - importantly to take a locked runlist rather than them locking it - which leads to lock reversal. - - Truncate {a,c,m}time to the ntfs supported time granularity when - updating the times in the inode in ntfs_setattr(). - - Fixup handling of sparse, compressed, and encrypted attributes in - fs/ntfs/inode.c::ntfs_read_locked_{,attr_,index_}inode(), - fs/ntfs/aops.c::ntfs_{read,write}page(). - - Make ntfs_write_block() not instantiate sparse blocks if they contain - only zeroes. - - Optimize fs/ntfs/aops.c::ntfs_write_block() by extending the page - lock protection over the buffer submission for i/o which allows the - removal of the get_bh()/put_bh() pairs for each buffer. - - Fix fs/ntfs/aops.c::ntfs_{read,write}_block() to handle the case - where a concurrent truncate has truncated the runlist under our feet. - - Fix page_has_buffers()/page_buffers() handling in fs/ntfs/aops.c. - - In fs/ntfs/aops.c::ntfs_end_buffer_async_read(), use a bit spin lock - in the first buffer head instead of a driver global spin lock to - improve scalability. - - Minor fix to error handling and error message display in - fs/ntfs/aops.c::ntfs_prepare_nonresident_write(). - - Change the mount options {u,f,d}mask to always parse the number as - an octal number to conform to how chmod(1) works, too. Thanks to - Giuseppe Bilotta and Horst von Brand for pointing out the errors of - my ways. - - Fix various bugs in the runlist merging code. (Based on libntfs - changes by Richard Russon.) - - Fix sparse warnings that have crept in over time. - - Change ntfs_cluster_free() to require a write locked runlist on entry - since we otherwise get into a lock reversal deadlock if a read locked - runlist is passed in. In the process also change it to take an ntfs - inode instead of a vfs inode as parameter. - - Fix the definition of the CHKD ntfs record magic. It had an off by - two error causing it to be CHKB instead of CHKD. - - Fix a stupid bug in __ntfs_bitmap_set_bits_in_run() which caused the - count to become negative and hence we had a wild memset() scribbling - all over the system's ram. - -2.1.23 - Implement extension of resident files and make writing safe as well as - many bug fixes, cleanups, and enhancements... - - - Add printk rate limiting for ntfs_warning() and ntfs_error() when - compiled without debug. This avoids a possible denial of service - attack. Thanks to Carl-Daniel Hailfinger from SuSE for pointing this - out. - - Fix compilation warnings on ia64. (Randy Dunlap) - - Use i_size_{read,write}() instead of reading i_size by hand and cache - the value where apropriate. - - Add size_lock to the ntfs_inode structure. This is an rw spinlock - and it locks against access to the inode sizes. Note, ->size_lock - is also accessed from irq context so you must use the _irqsave and - _irqrestore lock and unlock functions, respectively. Protect all - accesses to allocated_size, initialized_size, and compressed_size. - - Minor optimization to fs/ntfs/super.c::ntfs_statfs() and its helpers. - - Implement extension of resident files in the regular file write code - paths (fs/ntfs/aops.c::ntfs_{prepare,commit}_write()). At present - this only works until the data attribute becomes too big for the mft - record after which we abort the write returning -EOPNOTSUPP from - ntfs_prepare_write(). - - Add disable_sparse mount option together with a per volume sparse - enable bit which is set appropriately and a per inode sparse disable - bit which is preset on some system file inodes as appropriate. - - Enforce that sparse support is disabled on NTFS volumes pre 3.0. - - Fix a bug in fs/ntfs/runlist.c::ntfs_mapping_pairs_decompress() in - the creation of the unmapped runlist element for the base attribute - extent. - - Split ntfs_map_runlist() into ntfs_map_runlist() and a non-locking - helper ntfs_map_runlist_nolock() which is used by ntfs_map_runlist(). - This allows us to map runlist fragments with the runlist lock already - held without having to drop and reacquire it around the call. Adapt - all callers. - - Change ntfs_find_vcn() to ntfs_find_vcn_nolock() which takes a locked - runlist. This allows us to find runlist elements with the runlist - lock already held without having to drop and reacquire it around the - call. Adapt all callers. - - Change time to u64 in time.h::ntfs2utc() as it otherwise generates a - warning in the do_div() call on sparc32. Thanks to Meelis Roos for - the report and analysis of the warning. - - Fix a nasty runlist merge bug when merging two holes. - - Set the ntfs_inode->allocated_size to the real allocated size in the - mft record for resident attributes (fs/ntfs/inode.c). - - Small readability cleanup to use "a" instead of "ctx->attr" - everywhere (fs/ntfs/inode.c). - - Make fs/ntfs/namei.c::ntfs_get_{parent,dentry} static and move the - definition of ntfs_export_ops from fs/ntfs/super.c to namei.c. Also, - declare ntfs_export_ops in fs/ntfs/ntfs.h. - - Correct sparse file handling. The compressed values need to be - checked and set in the ntfs inode as done for compressed files and - the compressed size needs to be used for vfs inode->i_blocks instead - of the allocated size, again, as done for compressed files. - - Add AT_EA in addition to AT_DATA to whitelist for being allowed to be - non-resident in fs/ntfs/attrib.c::ntfs_attr_can_be_non_resident(). - - Add fs/ntfs/attrib.c::ntfs_attr_vcn_to_lcn_nolock() used by the new - write code. - - Fix bug in fs/ntfs/attrib.c::ntfs_find_vcn_nolock() where after - dropping the read lock and taking the write lock we were not checking - whether someone else did not already do the work we wanted to do. - - Rename fs/ntfs/attrib.c::ntfs_find_vcn_nolock() to - ntfs_attr_find_vcn_nolock() and update all callers. - - Add fs/ntfs/attrib.[hc]::ntfs_attr_make_non_resident(). - - Fix sign of various error return values to be negative in - fs/ntfs/lcnalloc.c. - - Modify ->readpage and ->writepage (fs/ntfs/aops.c) so they detect and - handle the case where an attribute is converted from resident to - non-resident by a concurrent file write. - - Remove checks for NULL before calling kfree() since kfree() does the - checking itself. (Jesper Juhl) - - Some utilities modify the boot sector but do not update the checksum. - Thus, relax the checking in fs/ntfs/super.c::is_boot_sector_ntfs() to - only emit a warning when the checksum is incorrect rather than - refusing the mount. Thanks to Bernd Casimir for pointing this - problem out. - - Update attribute definition handling. - - Add NTFS_MAX_CLUSTER_SIZE and NTFS_MAX_PAGES_PER_CLUSTER constants. - - Use NTFS_MAX_CLUSTER_SIZE in super.c instead of hard coding 0x10000. - - Use MAX_BUF_PER_PAGE instead of variable sized array allocation for - better code generation and one less sparse warning in fs/ntfs/aops.c. - - Remove spurious void pointer casts from fs/ntfs/. (Pekka Enberg) - - Use C99 style structure initialization after memory allocation where - possible (fs/ntfs/{attrib.c,index.c,super.c}). Thanks to Al Viro and - Pekka Enberg. - - Stamp the transaction log ($UsnJrnl), aka user space journal, if it - is active on the volume and we are mounting read-write or remounting - from read-only to read-write. - - Fix a bug in address space operations error recovery code paths where - if the runlist was not mapped at all and a mapping error occured we - would leave the runlist locked on exit to the function so that the - next access to the same file would try to take the lock and deadlock. - - Detect the case when Windows has been suspended to disk on the volume - to be mounted and if this is the case do not allow (re)mounting - read-write. This is done by parsing hiberfil.sys if present. - - Fix several occurences of a bug where we would perform 'var & ~const' - with a 64-bit variable and a int, i.e. 32-bit, constant. This causes - the higher order 32-bits of the 64-bit variable to be zeroed. To fix - this cast the 'const' to the same 64-bit type as 'var'. - - Change the runlist terminator of the newly allocated cluster(s) to - LCN_ENOENT in ntfs_attr_make_non_resident(). Otherwise the runlist - code gets confused. - - Add an extra parameter @last_vcn to ntfs_get_size_for_mapping_pairs() - and ntfs_mapping_pairs_build() to allow the runlist encoding to be - partial which is desirable when filling holes in sparse attributes. - Update all callers. - - Change ntfs_map_runlist_nolock() to only decompress the mapping pairs - if the requested vcn is inside it. Otherwise we get into problems - when we try to map an out of bounds vcn because we then try to map - the already mapped runlist fragment which causes - ntfs_mapping_pairs_decompress() to fail and return error. Update - ntfs_attr_find_vcn_nolock() accordingly. - - Fix a nasty deadlock that appeared in recent kernels. - The situation: VFS inode X on a mounted ntfs volume is dirty. For - same inode X, the ntfs_inode is dirty and thus corresponding on-disk - inode, i.e. mft record, which is in a dirty PAGE_CACHE_PAGE belonging - to the table of inodes, i.e. $MFT, inode 0. - What happens: - Process 1: sys_sync()/umount()/whatever... calls - __sync_single_inode() for $MFT -> do_writepages() -> write_page for - the dirty page containing the on-disk inode X, the page is now locked - -> ntfs_write_mst_block() which clears PageUptodate() on the page to - prevent anyone else getting hold of it whilst it does the write out. - This is necessary as the on-disk inode needs "fixups" applied before - the write to disk which are removed again after the write and - PageUptodate is then set again. It then analyses the page looking - for dirty on-disk inodes and when it finds one it calls - ntfs_may_write_mft_record() to see if it is safe to write this - on-disk inode. This then calls ilookup5() to check if the - corresponding VFS inode is in icache(). This in turn calls ifind() - which waits on the inode lock via wait_on_inode whilst holding the - global inode_lock. - Process 2: pdflush results in a call to __sync_single_inode for the - same VFS inode X on the ntfs volume. This locks the inode (I_LOCK) - then calls write-inode -> ntfs_write_inode -> map_mft_record() -> - read_cache_page() for the page (in page cache of table of inodes - $MFT, inode 0) containing the on-disk inode. This page has - PageUptodate() clear because of Process 1 (see above) so - read_cache_page() blocks when it tries to take the page lock for the - page so it can call ntfs_read_page(). - Thus Process 1 is holding the page lock on the page containing the - on-disk inode X and it is waiting on the inode X to be unlocked in - ifind() so it can write the page out and then unlock the page. - And Process 2 is holding the inode lock on inode X and is waiting for - the page to be unlocked so it can call ntfs_readpage() or discover - that Process 1 set PageUptodate() again and use the page. - Thus we have a deadlock due to ifind() waiting on the inode lock. - The solution: The fix is to use the newly introduced - ilookup5_nowait() which does not wait on the inode's lock and hence - avoids the deadlock. This is safe as we do not care about the VFS - inode and only use the fact that it is in the VFS inode cache and the - fact that the vfs and ntfs inodes are one struct in memory to find - the ntfs inode in memory if present. Also, the ntfs inode has its - own locking so it does not matter if the vfs inode is locked. - - Fix bug in mft record writing where we forgot to set the device in - the buffers when mapping them after the VM had discarded them. - Thanks to Martin MOKREJÅ for the bug report. - -2.1.22 - Many bug and race fixes and error handling improvements. - - - Improve error handling in fs/ntfs/inode.c::ntfs_truncate(). - - Change fs/ntfs/inode.c::ntfs_truncate() to return an error code - instead of void and provide a helper ntfs_truncate_vfs() for the - vfs ->truncate method. - - Add a new ntfs inode flag NInoTruncateFailed() and modify - fs/ntfs/inode.c::ntfs_truncate() to set and clear it appropriately. - - Fix min_size and max_size definitions in ATTR_DEF structure in - fs/ntfs/layout.h to be signed. - - Add attribute definition handling helpers to fs/ntfs/attrib.[hc]: - ntfs_attr_size_bounds_check(), ntfs_attr_can_be_non_resident(), and - ntfs_attr_can_be_resident(), which in turn use the new private helper - ntfs_attr_find_in_attrdef(). - - In fs/ntfs/aops.c::mark_ntfs_record_dirty(), take the - mapping->private_lock around the dirtying of the buffer heads - analagous to the way it is done in __set_page_dirty_buffers(). - - Ensure the mft record size does not exceed the PAGE_CACHE_SIZE at - mount time as this cannot work with the current implementation. - - Check for location of attribute name and improve error handling in - general in fs/ntfs/inode.c::ntfs_read_locked_inode() and friends. - - In fs/ntfs/aops.c::ntfs_writepage(), if the page is fully outside - i_size, i.e. race with truncate, invalidate the buffers on the page - so that they become freeable and hence the page does not leak. - - Remove unused function fs/ntfs/runlist.c::ntfs_rl_merge(). (Adrian - Bunk) - - Fix stupid bug in fs/ntfs/attrib.c::ntfs_attr_find() that resulted in - a NULL pointer dereference in the error code path when a corrupt - attribute was found. (Thanks to Domen Puncer for the bug report.) - - Add MODULE_VERSION() to fs/ntfs/super.c. - - Make several functions and variables static. (Adrian Bunk) - - Modify fs/ntfs/aops.c::mark_ntfs_record_dirty() so it allocates - buffers for the page if they are not present and then marks the - buffers belonging to the ntfs record dirty. This causes the buffers - to become busy and hence they are safe from removal until the page - has been written out. - - Fix stupid bug in fs/ntfs/attrib.c::ntfs_external_attr_find() in the - error handling code path that resulted in a BUG() due to trying to - unmap an extent mft record when the mapping of it had failed and it - thus was not mapped. (Thanks to Ken MacFerrin for the bug report.) - - Drop the runlist lock after the vcn has been read in - fs/ntfs/lcnalloc.c::__ntfs_cluster_free(). - - Rewrite handling of multi sector transfer errors. We now do not set - PageError() when such errors are detected in the async i/o handler - fs/ntfs/aops.c::ntfs_end_buffer_async_read(). All users of mst - protected attributes now check the magic of each ntfs record as they - use it and act appropriately. This has the effect of making errors - granular per ntfs record rather than per page which solves the case - where we cannot access any of the ntfs records in a page when a - single one of them had an mst error. (Thanks to Ken MacFerrin for - the bug report.) - - Fix error handling in fs/ntfs/quota.c::ntfs_mark_quotas_out_of_date() - where we failed to release i_mutex on the $Quota/$Q attribute inode. - - Fix bug in handling of bad inodes in fs/ntfs/namei.c::ntfs_lookup(). - - Add mapping of unmapped buffers to all remaining code paths, i.e. - fs/ntfs/aops.c::ntfs_write_mst_block(), mft.c::ntfs_sync_mft_mirror(), - and write_mft_record_nolock(). From now on we require that the - complete runlist for the mft mirror is always mapped into memory. - - Add creation of buffers to fs/ntfs/mft.c::ntfs_sync_mft_mirror(). - - Improve error handling in fs/ntfs/aops.c::ntfs_{read,write}_block(). - - Cleanup fs/ntfs/aops.c::ntfs_{read,write}page() since we know that a - resident attribute will be smaller than a page which makes the code - simpler. Also make the code more tolerant to concurrent ->truncate. - -2.1.21 - Fix some races and bugs, rewrite mft write code, add mft allocator. - - - Implement extent mft record deallocation - fs/ntfs/mft.c::ntfs_extent_mft_record_free(). - - Splitt runlist related functions off from attrib.[hc] to runlist.[hc]. - - Add vol->mft_data_pos and initialize it at mount time. - - Rename init_runlist() to ntfs_init_runlist(), ntfs_vcn_to_lcn() to - ntfs_rl_vcn_to_lcn(), decompress_mapping_pairs() to - ntfs_mapping_pairs_decompress(), ntfs_merge_runlists() to - ntfs_runlists_merge() and adapt all callers. - - Add fs/ntfs/runlist.[hc]::ntfs_get_nr_significant_bytes(), - ntfs_get_size_for_mapping_pairs(), ntfs_write_significant_bytes(), - and ntfs_mapping_pairs_build(), adapted from libntfs. - - Make fs/ntfs/lcnalloc.c::ntfs_cluster_free_from_rl_nolock() not - static and add a declaration for it to lcnalloc.h. - - Add fs/ntfs/lcnalloc.h::ntfs_cluster_free_from_rl() which is a static - inline wrapper for ntfs_cluster_free_from_rl_nolock() which takes the - cluster bitmap lock for the duration of the call. - - Add fs/ntfs/attrib.[hc]::ntfs_attr_record_resize(). - - Implement the equivalent of memset() for an ntfs attribute in - fs/ntfs/attrib.[hc]::ntfs_attr_set() and switch - fs/ntfs/logfile.c::ntfs_empty_logfile() to using it. - - Remove unnecessary casts from LCN_* constants. - - Implement fs/ntfs/runlist.c::ntfs_rl_truncate_nolock(). - - Add MFT_RECORD_OLD as a copy of MFT_RECORD in fs/ntfs/layout.h and - change MFT_RECORD to contain the NTFS 3.1+ specific fields. - - Add a helper function fs/ntfs/aops.c::mark_ntfs_record_dirty() which - marks all buffers belonging to an ntfs record dirty, followed by - marking the page the ntfs record is in dirty and also marking the vfs - inode containing the ntfs record dirty (I_DIRTY_PAGES). - - Switch fs/ntfs/index.h::ntfs_index_entry_mark_dirty() to using the - new helper fs/ntfs/aops.c::mark_ntfs_record_dirty() and remove the no - longer needed fs/ntfs/index.[hc]::__ntfs_index_entry_mark_dirty(). - - Move ntfs_{un,}map_page() from ntfs.h to aops.h and fix resulting - include errors. - - Move the typedefs for runlist_element and runlist from types.h to - runlist.h and fix resulting include errors. - - Remove unused {__,}format_mft_record() from fs/ntfs/mft.c. - - Modify fs/ntfs/mft.c::__mark_mft_record_dirty() to use the helper - mark_ntfs_record_dirty() which also changes the behaviour in that we - now set the buffers belonging to the mft record dirty as well as the - page itself. - - Update fs/ntfs/mft.c::write_mft_record_nolock() and sync_mft_mirror() - to cope with the fact that there now are dirty buffers in mft pages. - - Update fs/ntfs/inode.c::ntfs_write_inode() to also use the helper - mark_ntfs_record_dirty() and thus to set the buffers belonging to the - mft record dirty as well as the page itself. - - Fix compiler warnings on x86-64 in fs/ntfs/dir.c. (Randy Dunlap, - slightly modified by me) - - Add fs/ntfs/mft.c::try_map_mft_record() which fails with -EALREADY if - the mft record is already locked and otherwise behaves the same way - as fs/ntfs/mft.c::map_mft_record(). - - Modify fs/ntfs/mft.c::write_mft_record_nolock() so that it only - writes the mft record if the buffers belonging to it are dirty. - Otherwise we assume that it was written out by other means already. - - Attempting to write outside initialized size is _not_ a bug so remove - the bug check from fs/ntfs/aops.c::ntfs_write_mst_block(). It is in - fact required to write outside initialized size when preparing to - extend the initialized size. - - Map the page instead of using page_address() before writing to it in - fs/ntfs/aops.c::ntfs_mft_writepage(). - - Provide exclusion between opening an inode / mapping an mft record - and accessing the mft record in fs/ntfs/mft.c::ntfs_mft_writepage() - by setting the page not uptodate throughout ntfs_mft_writepage(). - - Clear the page uptodate flag in fs/ntfs/aops.c::ntfs_write_mst_block() - to ensure noone can see the page whilst the mst fixups are applied. - - Add the helper fs/ntfs/mft.c::ntfs_may_write_mft_record() which - checks if an mft record may be written out safely obtaining any - necessary locks in the process. This is used by - fs/ntfs/aops.c::ntfs_write_mst_block(). - - Modify fs/ntfs/aops.c::ntfs_write_mst_block() to also work for - writing mft records and improve its error handling in the process. - Now if any of the records in the page fail to be written out, all - other records will be written out instead of aborting completely. - - Remove ntfs_mft_aops and update all users to use ntfs_mst_aops. - - Modify fs/ntfs/inode.c::ntfs_read_locked_inode() to set the - ntfs_mst_aops for all inodes which are NInoMstProtected() and - ntfs_aops for all other inodes. - - Rename fs/ntfs/mft.c::sync_mft_mirror{,_umount}() to - ntfs_sync_mft_mirror{,_umount}() and change their parameters so they - no longer require an ntfs inode to be present. Update all callers. - - Cleanup the error handling in fs/ntfs/mft.c::ntfs_sync_mft_mirror(). - - Clear the page uptodate flag in fs/ntfs/mft.c::ntfs_sync_mft_mirror() - to ensure noone can see the page whilst the mst fixups are applied. - - Remove the no longer needed fs/ntfs/mft.c::ntfs_mft_writepage() and - fs/ntfs/mft.c::try_map_mft_record(). - - Fix callers of fs/ntfs/aops.c::mark_ntfs_record_dirty() to call it - with the ntfs inode which contains the page rather than the ntfs - inode the mft record of which is in the page. - - Fix race condition in fs/ntfs/inode.c::ntfs_put_inode() by moving the - index inode bitmap inode release code from there to - fs/ntfs/inode.c::ntfs_clear_big_inode(). (Thanks to Christoph - Hellwig for spotting this.) - - Fix race condition in fs/ntfs/inode.c::ntfs_put_inode() by taking the - inode semaphore around the code that sets ni->itype.index.bmp_ino to - NULL and reorganize the code to optimize it a bit. (Thanks to - Christoph Hellwig for spotting this.) - - Modify fs/ntfs/aops.c::mark_ntfs_record_dirty() to no longer take the - ntfs inode as a parameter as this is confusing and misleading and the - needed ntfs inode is available via NTFS_I(page->mapping->host). - Adapt all callers to this change. - - Modify fs/ntfs/mft.c::write_mft_record_nolock() and - fs/ntfs/aops.c::ntfs_write_mst_block() to only check the dirty state - of the first buffer in a record and to take this as the ntfs record - dirty state. We cannot look at the dirty state for subsequent - buffers because we might be racing with - fs/ntfs/aops.c::mark_ntfs_record_dirty(). - - Move the static inline ntfs_init_big_inode() from fs/ntfs/inode.c to - inode.h and make fs/ntfs/inode.c::__ntfs_init_inode() non-static and - add a declaration for it to inode.h. Fix some compilation issues - that resulted due to #includes and header file interdependencies. - - Simplify setup of i_mode in fs/ntfs/inode.c::ntfs_read_locked_inode(). - - Add helpers fs/ntfs/layout.h::MK_MREF() and MK_LE_MREF(). - - Modify fs/ntfs/mft.c::map_extent_mft_record() to only verify the mft - record sequence number if it is specified (i.e. not zero). - - Add fs/ntfs/mft.[hc]::ntfs_mft_record_alloc() and various helper - functions used by it. - - Update Documentation/filesystems/ntfs.txt with instructions on how to - use the Device-Mapper driver with NTFS ftdisk/LDM raid. This removes - the linear raid problem with the Software RAID / MD driver when one - or more of the devices has an odd number of sectors. - -2.1.20 - Fix two stupid bugs introduced in 2.1.18 release. - - - Fix stupid bug in fs/ntfs/attrib.c::ntfs_attr_reinit_search_ctx() - where we did not clear ctx->al_entry but it was still set due to - changes in ntfs_attr_lookup() and ntfs_external_attr_find() in - particular. - - Fix another stupid bug in fs/ntfs/attrib.c::ntfs_external_attr_find() - where we forgot to unmap the extent mft record when we had finished - enumerating an attribute which caused a bug check to trigger when the - VFS calls ->clear_inode. - -2.1.19 - Many cleanups, improvements, and a minor bug fix. - - - Update ->setattr (fs/ntfs/inode.c::ntfs_setattr()) to refuse to - change the uid, gid, and mode of an inode as we do not support NTFS - ACLs yet. - - Remove BKL use from ntfs_setattr() syncing up with the rest of the - kernel. - - Get rid of the ugly transparent union in fs/ntfs/dir.c::ntfs_readdir() - and ntfs_filldir() as per suggestion from Al Viro. - - Change '\0' and L'\0' to simply 0 as per advice from Linus Torvalds. - - Update ->truncate (fs/ntfs/inode.c::ntfs_truncate()) to check if the - inode size has changed and to only output an error if so. - - Rename fs/ntfs/attrib.h::attribute_value_length() to ntfs_attr_size(). - - Add le{16,32,64} as well as sle{16,32,64} data types to - fs/ntfs/types.h. - - Change ntfschar to be le16 instead of u16 in fs/ntfs/types.h. - - Add le versions of VCN, LCN, and LSN called leVCN, leLCN, and leLSN, - respectively, to fs/ntfs/types.h. - - Update endianness conversion macros in fs/ntfs/endian.h to use the - new types as appropriate. - - Do proper type casting when using sle64_to_cpup() in fs/ntfs/dir.c - and index.c. - - Add leMFT_REF data type to fs/ntfs/layout.h. - - Update all NTFS header files with the new little endian data types. - Affected files are fs/ntfs/layout.h, logfile.h, and time.h. - - Do proper type casting when using ntfs_is_*_recordp() in - fs/ntfs/logfile.c, mft.c, and super.c. - - Fix all the sparse bitwise warnings. Had to change all the typedef - enums storing little endian values to simple enums plus a typedef for - the datatype to make sparse happy. - - Fix a bug found by the new sparse bitwise warnings where the default - upcase table was defined as a pointer to wchar_t rather than ntfschar - in fs/ntfs/ntfs.h and super.c. - - Change {const_,}cpu_to_le{16,32}(0) to just 0 as suggested by Al Viro. - -2.1.18 - Fix scheduling latencies at mount time as well as an endianness bug. - - - Remove vol->nr_mft_records as it was pretty meaningless and optimize - the calculation of total/free inodes as used by statfs(). - - Fix scheduling latencies in ntfs_fill_super() by dropping the BKL - because the code itself is using the ntfs_lock semaphore which - provides safe locking. (Ingo Molnar) - - Fix a potential bug in fs/ntfs/mft.c::map_extent_mft_record() that - could occur in the future for when we start closing/freeing extent - inodes if we don't set base_ni->ext.extent_ntfs_inos to NULL after - we free it. - - Rename {find,lookup}_attr() to ntfs_attr_{find,lookup}() as well as - find_external_attr() to ntfs_external_attr_find() to cleanup the - namespace a bit and to be more consistent with libntfs. - - Rename {{re,}init,get,put}_attr_search_ctx() to - ntfs_attr_{{re,}init,get,put}_search_ctx() as well as the type - attr_search_context to ntfs_attr_search_ctx. - - Force use of ntfs_attr_find() in ntfs_attr_lookup() when searching - for the attribute list attribute itself. - - Fix endianness bug in ntfs_external_attr_find(). - - Change ntfs_{external_,}attr_find() to return 0 on success, -ENOENT - if the attribute is not found, and -EIO on real error. In the case - of -ENOENT, the search context is updated to describe the attribute - before which the attribute being searched for would need to be - inserted if such an action were to be desired and in the case of - ntfs_external_attr_find() the search context is also updated to - indicate the attribute list entry before which the attribute list - entry of the attribute being searched for would need to be inserted - if such an action were to be desired. Also make ntfs_find_attr() - static and remove its prototype from attrib.h as it is not used - anywhere other than attrib.c. Update ntfs_attr_lookup() and all - callers of ntfs_{external,}attr_{find,lookup}() for the new return - values. - - Minor cleanup of fs/ntfs/inode.c::ntfs_init_locked_inode(). - -2.1.17 - Fix bugs in mount time error code paths and other updates. - - - Implement bitmap modification code (fs/ntfs/bitmap.[hc]). This - includes functions to set/clear a single bit or a run of bits. - - Add fs/ntfs/attrib.[hc]::ntfs_find_vcn() which returns the locked - runlist element containing a particular vcn. It also takes care of - mapping any needed runlist fragments. - - Implement cluster (de-)allocation code (fs/ntfs/lcnalloc.[hc]). - - Load attribute definition table from $AttrDef at mount time. - - Fix bugs in mount time error code paths involving (de)allocation of - the default and volume upcase tables. - - Remove ntfs_nr_mounts as it is no longer used. - -2.1.16 - Implement access time updates, file sync, async io, and read/writev. - - - Add support for readv/writev and aio_read/aio_write (fs/ntfs/file.c). - This is done by setting the appropriate file operations pointers to - the generic helper functions provided by mm/filemap.c. - - Implement fsync, fdatasync, and msync both for files (fs/ntfs/file.c) - and directories (fs/ntfs/dir.c). - - Add support for {a,m,c}time updates to inode.c::ntfs_write_inode(). - Note, except for the root directory and any other system files opened - by the user, the system files will not have their access times - updated as they are only accessed at the inode level an hence the - file level functions which cause the times to be updated are never - invoked. - -2.1.15 - Invalidate quotas when (re)mounting read-write. - - - Add new element itype.index.collation_rule to the ntfs inode - structure and set it appropriately in ntfs_read_locked_inode(). - - Implement a new inode type "index" to allow efficient access to the - indices found in various system files and adapt inode handling - accordingly (fs/ntfs/inode.[hc]). An index inode is essentially an - attribute inode (NInoAttr() is true) with an attribute type of - AT_INDEX_ALLOCATION. As such, it is no longer allowed to call - ntfs_attr_iget() with an attribute type of AT_INDEX_ALLOCATION as - there would be no way to distinguish between normal attribute inodes - and index inodes. The function to obtain an index inode is - ntfs_index_iget() and it uses the helper function - ntfs_read_locked_index_inode(). Note, we do not overload - ntfs_attr_iget() as indices consist of multiple attributes so using - ntfs_attr_iget() to obtain an index inode would be confusing. - - Ensure that there is no overflow when doing page->index << - PAGE_CACHE_SHIFT by casting page->index to s64 in fs/ntfs/aops.c. - - Use atomic kmap instead of kmap() in fs/ntfs/aops.c::ntfs_read_page() - and ntfs_read_block(). - - Use case sensitive attribute lookups instead of case insensitive ones. - - Lock all page cache pages belonging to mst protected attributes while - accessing them to ensure we never see corrupt data while the page is - under writeout. - - Add framework for generic ntfs collation (fs/ntfs/collation.[hc]). - We have ntfs_is_collation_rule_supported() to check if the collation - rule you want to use is supported and ntfs_collation() which actually - collates two data items. We currently only support COLLATION_BINARY - and COLLATION_NTOFS_ULONG but support for other collation rules will - be added as the need arises. - - Add a new type, ntfs_index_context, to allow retrieval of an index - entry using the corresponding index key. To get an index context, - use ntfs_index_ctx_get() and to release it, use ntfs_index_ctx_put(). - This also adds a new slab cache for the index contexts. To lookup a - key in an index inode, use ntfs_index_lookup(). After modifying an - index entry, call ntfs_index_entry_flush_dcache_page() followed by - ntfs_index_entry_mark_dirty() to ensure the changes are written out - to disk. For details see fs/ntfs/index.[hc]. Note, at present, if - an index entry is in the index allocation attribute rather than the - index root attribute it will not be written out (you will get a - warning message about discarded changes instead). - - Load the quota file ($Quota) and check if quota tracking is enabled - and if so, mark the quotas out of date. This causes windows to - rescan the volume on boot and update all quota entries. - - Add a set_page_dirty address space operation for ntfs_m[fs]t_aops. - It is simply set to __set_page_dirty_nobuffers() to make sure that - running set_page_dirty() on a page containing mft/ntfs records will - not affect the dirty state of the page buffers. - - Add fs/ntfs/index.c::__ntfs_index_entry_mark_dirty() which sets all - buffers that are inside the ntfs record in the page dirty after which - it sets the page dirty. This allows ->writepage to only write the - dirty index records rather than having to write all the records in - the page. Modify fs/ntfs/index.h::ntfs_index_entry_mark_dirty() to - use this rather than __set_page_dirty_nobuffers(). - - Implement fs/ntfs/aops.c::ntfs_write_mst_block() which enables the - writing of page cache pages belonging to mst protected attributes - like the index allocation attribute in directory indices and other - indices like $Quota/$Q, etc. This means that the quota is now marked - out of date on all volumes rather than only on ones where the quota - defaults entry is in the index root attribute of the $Quota/$Q index. - -2.1.14 - Fix an NFSd caused deadlock reported by several users. - - - Modify fs/ntfs/ntfs_readdir() to copy the index root attribute value - to a buffer so that we can put the search context and unmap the mft - record before calling the filldir() callback. We need to do this - because of NFSd which calls ->lookup() from its filldir callback() - and this causes NTFS to deadlock as ntfs_lookup() maps the mft record - of the directory and since ntfs_readdir() has got it mapped already - ntfs_lookup() deadlocks. - -2.1.13 - Enable overwriting of resident files and housekeeping of system files. - - - Implement writing of mft records (fs/ntfs/mft.[hc]), which includes - keeping the mft mirror in sync with the mft when mirrored mft records - are written. The functions are write_mft_record{,_nolock}(). The - implementation is quite rudimentary for now with lots of things not - implemented yet but I am not sure any of them can actually occur so - I will wait for people to hit each one and only then implement it. - - Commit open system inodes at umount time. This should make it - virtually impossible for sync_mft_mirror_umount() to ever be needed. - - Implement ->write_inode (fs/ntfs/inode.c::ntfs_write_inode()) for the - ntfs super operations. This gives us inode writing via the VFS inode - dirty code paths. Note: Access time updates are not implemented yet. - - Implement fs/ntfs/mft.[hc]::{,__}mark_mft_record_dirty() and make - fs/ntfs/aops.c::ntfs_writepage() and ntfs_commit_write() use it, thus - finally enabling resident file overwrite! (-8 This also includes a - placeholder for ->writepage (ntfs_mft_writepage()), which for now - just redirties the page and returns. Also, at umount time, we for - now throw away all mft data page cache pages after the last call to - ntfs_commit_inode() in the hope that all inodes will have been - written out by then and hence no dirty (meta)data will be lost. We - also check for this case and emit an error message telling the user - to run chkdsk. - - Use set_page_writeback() and end_page_writeback() in the resident - attribute code path of fs/ntfs/aops.c::ntfs_writepage() otherwise - the radix-tree tag PAGECACHE_TAG_DIRTY remains set even though the - page is clean. - - Implement ntfs_mft_writepage() so it now checks if any of the mft - records in the page are dirty and if so redirties the page and - returns. Otherwise it just returns (after doing set_page_writeback(), - unlock_page(), end_page_writeback() or the radix-tree tag - PAGECACHE_TAG_DIRTY remains set even though the page is clean), thus - alowing the VM to do with the page as it pleases. Also, at umount - time, now only throw away dirty mft (meta)data pages if dirty inodes - are present and ask the user to email us if they see this happening. - - Add functions ntfs_{clear,set}_volume_flags(), to modify the volume - information flags (fs/ntfs/super.c). - - Mark the volume dirty when (re)mounting read-write and mark it clean - when unmounting or remounting read-only. If any volume errors are - found, the volume is left marked dirty to force chkdsk to run. - - Add code to set the NT4 compatibility flag when (re)mounting - read-write for newer NTFS versions but leave it commented out for now - since we do not make any modifications that are NTFS 1.2 specific yet - and since setting this flag breaks Captive-NTFS which is not nice. - This code must be enabled once we start writing NTFS 1.2 specific - changes otherwise Windows NTFS driver might crash / cause corruption. - -2.1.12 - Fix the second fix to the decompression engine and some cleanups. - - - Add a new address space operations struct, ntfs_mst_aops, for mst - protected attributes. This is because the default ntfs_aops do not - make sense with mst protected data and were they to write anything to - such an attribute they would cause data corruption so we provide - ntfs_mst_aops which does not have any write related operations set. - - Cleanup dirty ntfs inode handling (fs/ntfs/inode.[hc]) which also - includes an adapted ntfs_commit_inode() and an implementation of - ntfs_write_inode() which for now just cleans dirty inodes without - writing them (it does emit a warning that this is happening). - - Undo the second decompression engine fix (see 2.1.9 release ChangeLog - entry) as it was only fixing a theoretical bug but at the same time - it badly broke the handling of sparse and uncompressed compression - blocks. - -2.1.11 - Driver internal cleanups. - - - Only build logfile.o if building the driver with read-write support. - - Really final white space cleanups. - - Use generic_ffs() instead of ffs() in logfile.c which allows the - log_page_size variable to be optimized by gcc into a constant. - - Rename uchar_t to ntfschar everywhere as uchar_t is unsigned 1-byte - char as defined by POSIX and as found on some systems. - -2.1.10 - Force read-only (re)mounting of volumes with unsupported volume flags. - - - Finish off the white space cleanups (remove trailing spaces, etc). - - Clean up ntfs_fill_super() and ntfs_read_inode_mount() by removing - the kludges around the first iget(). Instead of (re)setting ->s_op - we have the $MFT inode set up by explicit new_inode() / set ->i_ino / - insert_inode_hash() / call ntfs_read_inode_mount() directly. This - kills the need for second super_operations and allows to return error - from ntfs_read_inode_mount() without resorting to ugly "poisoning" - tricks. (Al Viro) - - Force read-only (re)mounting if any of the following bits are set in - the volume information flags: - VOLUME_IS_DIRTY, VOLUME_RESIZE_LOG_FILE, - VOLUME_UPGRADE_ON_MOUNT, VOLUME_DELETE_USN_UNDERWAY, - VOLUME_REPAIR_OBJECT_ID, VOLUME_MODIFIED_BY_CHKDSK - To make this easier we define VOLUME_MUST_MOUNT_RO_MASK with all the - above bits set so the test is made easy. - -2.1.9 - Fix two bugs in decompression engine. - - - Fix a bug where we would not always detect that we have reached the - end of a compression block because we were ending at minus one byte - which is effectively the same as being at the end. The fix is to - check whether the uncompressed buffer has been fully filled and if so - we assume we have reached the end of the compression block. A big - thank you to Marcin Gibuła for the bug report, the assistance in - tracking down the bug and testing the fix. - - Fix a possible bug where when a compressed read is truncated to the - end of the file, the offset inside the last page was not truncated. - -2.1.8 - Handle $MFT mirror and $LogFile, improve time handling, and cleanups. - - - Use get_bh() instead of manual atomic_inc() in fs/ntfs/compress.c. - - Modify fs/ntfs/time.c::ntfs2utc(), get_current_ntfs_time(), and - utc2ntfs() to work with struct timespec instead of time_t on the - Linux UTC time side thus preserving the full precision of the NTFS - time and only loosing up to 99 nano-seconds in the Linux UTC time. - - Move fs/ntfs/time.c to fs/ntfs/time.h and make the time functions - static inline. - - Remove unused ntfs_dirty_inode(). - - Cleanup super operations declaration in fs/ntfs/super.c. - - Wrap flush_dcache_mft_record_page() in #ifdef NTFS_RW. - - Add NInoTestSetFoo() and NInoTestClearFoo() macro magic to - fs/ntfs/inode.h and use it to declare NInoTest{Set,Clear}Dirty. - - Move typedefs for ntfs_attr and test_t from fs/ntfs/inode.c to - fs/ntfs/inode.h so they can be used elsewhere. - - Determine the mft mirror size as the number of mirrored mft records - and store it in ntfs_volume->mftmirr_size (fs/ntfs/super.c). - - Load the mft mirror at mount time and compare the mft records stored - in it to the ones in the mft. Force a read-only mount if the two do - not match (fs/ntfs/super.c). - - Fix type casting related warnings on 64-bit architectures. Thanks - to Meelis Roos for reporting them. - - Move %L to %ll as %L is floating point and %ll is integer which is - what we want. - - Read the journal ($LogFile) and determine if the volume has been - shutdown cleanly and force a read-only mount if not (fs/ntfs/super.c - and fs/ntfs/logfile.c). This is a little bit of a crude check in - that we only look at the restart areas and not at the actual log - records so that there will be a very small number of cases where we - think that a volume is dirty when in fact it is clean. This should - only affect volumes that have not been shutdown cleanly and did not - have any pending, non-check-pointed i/o. - - If the $LogFile indicates a clean shutdown and a read-write (re)mount - is requested, empty $LogFile by overwriting it with 0xff bytes to - ensure that Windows cannot cause data corruption by replaying a stale - journal after Linux has written to the volume. - -2.1.7 - Enable NFS exporting of mounted NTFS volumes. - - - Set i_generation in the VFS inode from the seq_no of the NTFS inode. - - Make ntfs_lookup() NFS export safe, i.e. use d_splice_alias(), etc. - - Implement ->get_dentry() in fs/ntfs/namei.c::ntfs_get_dentry() as the - default doesn't allow inode number 0 which is a valid inode on NTFS - and even if it did allow that it uses iget() instead of ntfs_iget() - which makes it useless for us. - - Implement ->get_parent() in fs/ntfs/namei.c::ntfs_get_parent() as the - default just returns -EACCES which is not very useful. - - Define export operations (->s_export_op) for NTFS (ntfs_export_ops) - and set them up in the super block at mount time (super.c) this - allows mounted NTFS volumes to be exported via NFS. - - Add missing return -EOPNOTSUPP; in - fs/ntfs/aops.c::ntfs_commit_nonresident_write(). - - Enforce no atime and no dir atime updates at mount/remount time as - they are not implemented yet anyway. - - Move a few assignments in fs/ntfs/attrib.c::load_attribute_list() to - after a NULL check. Thanks to Dave Jones for pointing this out. - -2.1.6 - Fix minor bug in handling of compressed directories. - - - Fix bug in handling of compressed directories. A compressed - directory is not really compressed so when we set the ->i_blocks - field of a compressed directory inode we were setting it from the - non-existing field ni->itype.compressed.size which gave random - results... For directories we now always use ni->allocated_size. - -2.1.5 - Fix minor bug in attribute list attribute handling. - - - Fix bug in attribute list handling. Actually it is not as much a bug - as too much protection in that we were not allowing attribute lists - which waste space on disk while Windows XP clearly allows it and in - fact creates such attribute lists so our driver was failing. - - Update NTFS documentation ready for 2.6 kernel release. - -2.1.4 - Reduce compiler requirements. - - - Remove all uses of unnamed structs and unions in the driver to make - old and newer gcc versions happy. Makes it a bit uglier IMO but at - least people will stop hassling me about it. - -2.1.3 - Important bug fixes in corner cases. - - - super.c::parse_ntfs_boot_sector(): Correct the check for 64-bit - clusters. (Philipp Thomas) - - attrib.c::load_attribute_list(): Fix bug when initialized_size is a - multiple of the block_size but not the cluster size. (Szabolcs - Szakacsits) - -2.1.2 - Important bug fixes aleviating the hangs in statfs. - - - Fix buggy free cluster and free inode determination logic. - -2.1.1 - Minor updates. - - - Add handling for initialized_size != data_size in compressed files. - - Reduce function local stack usage from 0x3d4 bytes to just noise in - fs/ntfs/upcase.c. (Randy Dunlap) - - Remove compiler warnings for newer gcc. - - Pages are no longer kmapped by mm/filemap.c::generic_file_write() - around calls to ->{prepare,commit}_write. Adapt NTFS appropriately - in fs/ntfs/aops.c::ntfs_prepare_nonresident_write() by using - kmap_atomic(KM_USER0). - -2.1.0 - First steps towards write support: implement file overwrite. - - - Add configuration option for developmental write support with an - appropriately scary configuration help text. - - Initial implementation of fs/ntfs/aops.c::ntfs_writepage() and its - helper fs/ntfs/aops.c::ntfs_write_block(). This enables mmap(2) based - overwriting of existing files on ntfs. Note: Resident files are - only written into memory, and not written out to disk at present, so - avoid writing to files smaller than about 1kiB. - - Initial implementation of fs/ntfs/aops.c::ntfs_prepare_write(), its - helper fs/ntfs/aops.c::ntfs_prepare_nonresident_write() and their - counterparts, fs/ntfs/aops.c::ntfs_commit_write(), and - fs/ntfs/aops.c::ntfs_commit_nonresident_write(), respectively. Also, - add generic_file_write() to the ntfs file operations (fs/ntfs/file.c). - This enables write(2) based overwriting of existing files on ntfs. - Note: As with mmap(2) based overwriting, resident files are only - written into memory, and not written out to disk at present, so avoid - writing to files smaller than about 1kiB. - - Implement ->truncate (fs/ntfs/inode.c::ntfs_truncate()) and - ->setattr() (fs/ntfs/inode.c::ntfs_setattr()) inode operations for - files with the purpose of intercepting and aborting all i_size - changes which we do not support yet. ntfs_truncate() actually only - emits a warning message but AFAICS our interception of i_size changes - elsewhere means ntfs_truncate() never gets called for i_size changes. - It is only called from generic_file_write() when we fail in - ntfs_prepare_{,nonresident_}write() in order to discard any - instantiated buffers beyond i_size. Thus i_size is not actually - changed so our warning message is enough. Unfortunately it is not - possible to easily determine if i_size is being changed or not hence - we just emit an appropriately worded error message. - -2.0.25 - Small bug fixes and cleanups. - - - Unlock the page in an out of memory error code path in - fs/ntfs/aops.c::ntfs_read_block(). - - If fs/ntfs/aops.c::ntfs_read_page() is called on an uptodate page, - just unlock the page and return. (This can happen due to ->writepage - clearing PageUptodate() during write out of MstProtected() - attributes. - - Remove leaked write code again. - -2.0.24 - Cleanups. - - - Treat BUG_ON() as ASSERT() not VERIFY(), i.e. do not use side effects - inside BUG_ON(). (Adam J. Richter) - - Split logical OR expressions inside BUG_ON() into individual BUG_ON() - calls for improved debugging. (Adam J. Richter) - - Add errors flag to the ntfs volume state, accessed via - NVol{,Set,Clear}Errors(vol). - - Do not allow read-write remounts of read-only volumes with errors. - - Clarify comment for ntfs file operation sendfile which was added by - Christoph Hellwig a while ago (just using generic_file_sendfile()) - to say that ntfs ->sendfile is only used for the case where the - source data is on the ntfs partition and the destination is - somewhere else, i.e. nothing we need to concern ourselves with. - - Add generic_file_write() as our ntfs file write operation. - -2.0.23 - Major bug fixes (races, deadlocks, non-i386 architectures). - - - Massive internal locking changes to mft record locking. Fixes lock - recursion and replaces the mrec_lock read/write semaphore with a - mutex. Also removes the now superfluous mft_count. This fixes several - race conditions and deadlocks, especially in the future write code. - - Fix ntfs over loopback for compressed files by adding an - optimization barrier. (gcc was screwing up otherwise ?) - - Miscellaneous cleanups all over the code and a fix or two in error - handling code paths. - Thanks go to Christoph Hellwig for pointing out the following two: - - Remove now unused function fs/ntfs/malloc.h::vmalloc_nofs(). - - Fix ntfs_free() for ia64 and parisc by checking for VMALLOC_END, too. - -2.0.22 - Cleanups, mainly to ntfs_readdir(), and use C99 initializers. - - - Change fs/ntfs/dir.c::ntfs_reddir() to only read/write ->f_pos once - at entry/exit respectively. - - Use C99 initializers for structures. - - Remove unused variable blocks from fs/ntfs/aops.c::ntfs_read_block(). - -2.0.21 - Check for, and refuse to work with too large files/directories/volumes. - - - Limit volume size at mount time to 2TiB on architectures where - unsigned long is 32-bits (fs/ntfs/super.c::parse_ntfs_boot_sector()). - This is the most we can do without overflowing the 32-bit limit of - the block device size imposed on us by sb_bread() and sb_getblk() - for the time being. - - Limit file/directory size at open() time to 16TiB on architectures - where unsigned long is 32-bits (fs/ntfs/file.c::ntfs_file_open() and - fs/ntfs/dir.c::ntfs_dir_open()). This is the most we can do without - overflowing the page cache page index. - -2.0.20 - Support non-resident directory index bitmaps, fix page leak in readdir. - - - Move the directory index bitmap to use an attribute inode instead of - having special fields for it inside the ntfs inode structure. This - means that the index bitmaps now use the page cache for i/o, too, - and also as a side effect we get support for non-resident index - bitmaps for free. - - Simplify/cleanup error handling in fs/ntfs/dir.c::ntfs_readdir() and - fix a page leak that manifested itself in some cases. - - Add fs/ntfs/inode.c::ntfs_put_inode(), which we need to release the - index bitmap inode on the final iput(). - -2.0.19 - Fix race condition, improvements, and optimizations in i/o interface. - - - Apply block optimization added to fs/ntfs/aops.c::ntfs_read_block() - to fs/ntfs/compress.c::ntfs_file_read_compressed_block() as well. - - Drop the "file" from ntfs_file_read_compressed_block(). - - Rename fs/ntfs/aops.c::ntfs_enb_buffer_read_async() to - ntfs_end_buffer_async_read() (more like the fs/buffer.c counterpart). - - Update ntfs_end_buffer_async_read() with the improved logic from - its updated counterpart fs/buffer.c::end_buffer_async_read(). Apply - further logic improvements to better determine when we set PageError. - - Update submission of buffers in fs/ntfs/aops.c::ntfs_read_block() to - check for the buffers being uptodate first in line with the updated - fs/buffer.c::block_read_full_page(). This plugs a small race - condition. - -2.0.18 - Fix race condition in reading of compressed files. - - - There was a narrow window between checking a buffer head for being - uptodate and locking it in ntfs_file_read_compressed_block(). We now - lock the buffer and then check whether it is uptodate or not. - -2.0.17 - Cleanups and optimizations - shrinking the ToDo list. - - - Modify fs/ntfs/inode.c::ntfs_read_locked_inode() to return an error - code and update callers, i.e. ntfs_iget(), to pass that error code - up instead of just using -EIO. - - Modifications to super.c to ensure that both mount and remount - cannot set any write related options when the driver is compiled - read-only. - - Optimize block resolution in fs/ntfs/aops.c::ntfs_read_block() to - cache the current runlist element. This should improve performance - when reading very large and/or very fragmented data. - -2.0.16 - Convert access to $MFT/$BITMAP to attribute inode API. - - - Fix a stupid bug introduced in 2.0.15 where we were unmapping the - wrong inode in fs/ntfs/inode.c::ntfs_attr_iget(). - - Fix debugging check in fs/ntfs/aops.c::ntfs_read_block(). - - Convert $MFT/$BITMAP access to attribute inode API and remove all - remnants of the ugly mftbmp address space and operations hack. This - means we finally have only one readpage function as well as only one - async io completion handler. Yey! The mft bitmap is now just an - attribute inode and is accessed from vol->mftbmp_ino just as if it - were a normal file. Fake inodes rule. (-: - -2.0.15 - Fake inodes based attribute i/o via the pagecache, fixes and cleanups. - - - Fix silly bug in fs/ntfs/super.c::parse_options() which was causing - remounts to fail when the partition had an entry in /etc/fstab and - the entry specified the nls= option. - - Apply same macro magic used in fs/ntfs/inode.h to fs/ntfs/volume.h to - expand all the helper functions NVolFoo(), NVolSetFoo(), and - NVolClearFoo(). - - Move copyright statement from driver initialisation message to - module description (fs/super.c). This makes the initialisation - message fit on one line and fits in better with rest of kernel. - - Update fs/ntfs/attrib.c::map_run_list() to work on both real and - attribute inodes, and both for files and directories. - - Implement fake attribute inodes allowing all attribute i/o to go via - the page cache and to use all the normal vfs/mm functionality: - - Add ntfs_attr_iget() and its helper ntfs_read_locked_attr_inode() - to fs/ntfs/inode.c. - - Add needed cleanup code to ntfs_clear_big_inode(). - - Merge address space operations for files and directories (aops.c), - now just have ntfs_aops: - - Rename: - end_buffer_read_attr_async() -> ntfs_end_buffer_read_async(), - ntfs_attr_read_block() -> ntfs_read_block(), - ntfs_file_read_page() -> ntfs_readpage(). - - Rewrite fs/ntfs/aops.c::ntfs_readpage() to work on both real and - attribute inodes, and both for files and directories. - - Remove obsolete fs/ntfs/aops.c::ntfs_mst_readpage(). - -2.0.14 - Run list merging code cleanup, minor locking changes, typo fixes. - - - Change fs/ntfs/super.c::ntfs_statfs() to not rely on BKL by moving - the locking out of super.c::get_nr_free_mft_records() and taking and - dropping the mftbmp_lock rw_semaphore in ntfs_statfs() itself. - - Bring attribute runlist merging code (fs/ntfs/attrib.c) in sync with - current userspace ntfs library code. This means that if a merge - fails the original runlists are always left unmodified instead of - being silently corrupted. - - Misc typo fixes. - -2.0.13 - Use iget5_locked() in preparation for fake inodes and small cleanups. - - - Remove nr_mft_bits and the now superfluous union with nr_mft_records - from ntfs_volume structure. - - Remove nr_lcn_bits and the now superfluous union with nr_clusters - from ntfs_volume structure. - - Use iget5_locked() and friends instead of conventional iget(). Wrap - the call in fs/ntfs/inode.c::ntfs_iget() and update callers of iget() - to use ntfs_iget(). Leave only one iget() call at mount time so we - don't need an ntfs_iget_mount(). - - Change fs/ntfs/inode.c::ntfs_new_extent_inode() to take mft_no as an - additional argument. - -2.0.12 - Initial cleanup of address space operations following 2.0.11 changes. - - - Merge fs/ntfs/aops.c::end_buffer_read_mst_async() and - fs/ntfs/aops.c::end_buffer_read_file_async() into one function - fs/ntfs/aops.c::end_buffer_read_attr_async() using NInoMstProtected() - to determine whether to apply mst fixups or not. - - Above change allows merging fs/ntfs/aops.c::ntfs_file_read_block() - and fs/ntfs/aops.c::ntfs_mst_readpage() into one function - fs/ntfs/aops.c::ntfs_attr_read_block(). Also, create a tiny wrapper - fs/ntfs/aops.c::ntfs_mst_readpage() to transform the parameters from - the VFS readpage function prototype to the ntfs_attr_read_block() - function prototype. - -2.0.11 - Initial preparations for fake inode based attribute i/o. - - - Move definition of ntfs_inode_state_bits to fs/ntfs/inode.h and - do some macro magic (adapted from include/linux/buffer_head.h) to - expand all the helper functions NInoFoo(), NInoSetFoo(), and - NInoClearFoo(). - - Add new flag to ntfs_inode_state_bits: NI_Sparse. - - Add new fields to ntfs_inode structure to allow use of fake inodes - for attribute i/o: type, name, name_len. Also add new state bits: - NI_Attr, which, if set, indicates the inode is a fake inode, and - NI_MstProtected, which, if set, indicates the attribute uses multi - sector transfer protection, i.e. fixups need to be applied after - reads and before/after writes. - - Rename fs/ntfs/inode.c::ntfs_{new,clear,destroy}_inode() to - ntfs_{new,clear,destroy}_extent_inode() and update callers. - - Use ntfs_clear_extent_inode() in fs/ntfs/inode.c::__ntfs_clear_inode() - instead of ntfs_destroy_extent_inode(). - - Cleanup memory deallocations in {__,}ntfs_clear_{,big_}inode(). - - Make all operations on ntfs inode state bits use the NIno* functions. - - Set up the new ntfs inode fields and state bits in - fs/ntfs/inode.c::ntfs_read_inode() and add appropriate cleanup of - allocated memory to __ntfs_clear_inode(). - - Cleanup ntfs_inode structure a bit for better ordering of elements - w.r.t. their size to allow better packing of the structure in memory. - -2.0.10 - There can only be 2^32 - 1 inodes on an NTFS volume. - - - Add check at mount time to verify that the number of inodes on the - volume does not exceed 2^32 - 1, which is the maximum allowed for - NTFS according to Microsoft. - - Change mft_no member of ntfs_inode structure to be unsigned long. - Update all users. This makes ntfs_inode->mft_no just a copy of struct - inode->i_ino. But we can't just always use struct inode->i_ino and - remove mft_no because extent inodes do not have an attached struct - inode. - -2.0.9 - Decompression engine now uses a single buffer and other cleanups. - - - Change decompression engine to use a single buffer protected by a - spin lock instead of per-CPU buffers. (Rusty Russell) - - Do not update cb_pos when handling a partial final page during - decompression of a sparse compression block, as the value is later - reset without being read/used. (Rusty Russell) - - Switch to using the new KM_BIO_SRC_IRQ for atomic kmap()s. (Andrew - Morton) - - Change buffer size in ntfs_readdir()/ntfs_filldir() to use - NLS_MAX_CHARSET_SIZE which makes the buffers almost 1kiB each but - it also makes everything safer so it is a good thing. - - Miscellaneous minor cleanups to comments. - -2.0.8 - Major updates for handling of case sensitivity and dcache aliasing. - - Big thanks go to Al Viro and other inhabitants of #kernel for investing - their time to discuss the case sensitivity and dcache aliasing issues. - - - Remove unused source file fs/ntfs/attraops.c. - - Remove show_inodes mount option(s), thus dropping support for - displaying of short file names. - - Remove deprecated mount option posix. - - Restore show_sys_files mount option. - - Add new mount option case_sensitive, to determine if the driver - treats file names as case sensitive or not. If case sensitive, create - file names in the POSIX namespace. Otherwise create file names in the - LONG/WIN32 namespace. Note, files remain accessible via their short - file name, if it exists. - - Remove really dumb logic bug in boot sector recovery code. - - Fix dcache aliasing issues wrt short/long file names via changes - to fs/ntfs/dir.c::ntfs_lookup_inode_by_name() and - fs/ntfs/namei.c::ntfs_lookup(): - - Add additional argument to ntfs_lookup_inode_by_name() in which we - return information about the matching file name if the case is not - matching or the match is a short file name. See comments above the - function definition for details. - - Change ntfs_lookup() to only create dcache entries for the correctly - cased file name and only for the WIN32 namespace counterpart of DOS - namespace file names. This ensures we have only one dentry per - directory and also removes all dcache aliasing issues between short - and long file names once we add write support. See comments above - function for details. - - Fix potential 1 byte overflow in fs/ntfs/unistr.c::ntfs_ucstonls(). - -2.0.7 - Minor cleanups and updates for changes in core kernel code. - - - Remove much of the NULL struct element initializers. - - Various updates to make compatible with recent kernels. - - Remove defines of MAX_BUF_PER_PAGE and include linux/buffer_head.h - in fs/ntfs/ntfs.h instead. - - Remove no longer needed KERNEL_VERSION checks. We are now in the - kernel proper so they are no longer needed. - -2.0.6 - Major bugfix to make compatible with other kernel changes. - - - Initialize the mftbmp address space properly now that there are more - fields in the struct address_space. This was leading to hangs and - oopses on umount since 2.5.12 because of changes to other parts of - the kernel. We probably want a kernel generic init_address_space() - function... - - Drop BKL from ntfs_readdir() after consultation with Al Viro. The - only caller of ->readdir() is vfs_readdir() which holds i_mutex - during the call, and i_mutex is sufficient protection against changes - in the directory inode (including ->i_size). - - Use generic_file_llseek() for directories (as opposed to - default_llseek()) as this downs i_mutex instead of the BKL which is - what we now need for exclusion against ->f_pos changes considering we - no longer take the BKL in ntfs_readdir(). - -2.0.5 - Major bugfix. Buffer overflow in extent inode handling. - - - No need to set old blocksize in super.c::ntfs_fill_super() as the - VFS does so via invocation of deactivate_super() calling - fs->fill_super() calling block_kill_super() which does it. - - BKL moved from VFS into dir.c::ntfs_readdir(). (Linus Torvalds) - -> Do we really need it? I don't think so as we have exclusion on - the directory ntfs_inode rw_semaphore mrec_lock. We mmight have to - move the ->f_pos accesses under the mrec_lock though. Check this... - - Fix really, really, really stupid buffer overflow in extent inode - handling in mft.c::map_extent_mft_record(). - -2.0.4 - Cleanups and updates for kernel 2.5.11. - - - Add documentation on how to use the MD driver to be able to use NTFS - stripe and volume sets in Linux and generally cleanup documentation - a bit. - Remove all uses of kdev_t in favour of struct block_device *: - - Change compress.c::ntfs_file_read_compressed_block() to use - sb_getblk() instead of getblk(). - - Change super.c::ntfs_fill_super() to use bdev_hardsect_size() instead - of get_hardsect_size(). - - No need to get old blocksize in super.c::ntfs_fill_super() as - fs/super.c::get_sb_bdev() already does this. - - Set bh->b_bdev instead of bh->b_dev throughout aops.c. - -2.0.3 - Small bug fixes, cleanups, and performance improvements. - - - Remove some dead code from mft.c. - - Optimize readpage and read_block functions throughout aops.c so that - only initialized blocks are read. Non-initialized ones have their - buffer head mapped, zeroed, and set up to date, without scheduling - any i/o. Thanks to Al Viro for advice on how to avoid the device i/o. - Thanks go to Andrew Morton for spotting the below: - - Fix buglet in allocate_compression_buffers() error code path. - - Call flush_dcache_page() after modifying page cache page contents in - ntfs_file_readpage(). - - Check for existence of page buffers throughout aops.c before calling - create_empty_buffers(). This happens when an I/O error occurs and the - read is retried. (It also happens once writing is implemented so that - needed doing anyway but I had left it for later...) - - Don't BUG_ON() uptodate and/or mapped buffers throughout aops.c in - readpage and read_block functions. Reasoning same as above (i.e. I/O - error retries and future write code paths.) - -2.0.2 - Minor updates and cleanups. - - - Cleanup: rename mst.c::__post_read_mst_fixup to post_write_mst_fixup - and cleanup the code a bit, removing the unused size parameter. - - Change default fmask to 0177 and update documentation. - - Change attrib.c::get_attr_search_ctx() to return the search context - directly instead of taking the address of a pointer. A return value - of NULL means the allocation failed. Updated all callers - appropriately. - - Update to 2.5.9 kernel (preserving backwards compatibility) by - replacing all occurences of page->buffers with page_buffers(page). - - Fix minor bugs in runlist merging, also minor cleanup. - - Updates to bootsector layout and mft mirror contents descriptions. - - Small bug fix in error detection in unistr.c and some cleanups. - - Grow name buffer allocations in unistr.c in aligned mutlipled of 64 - bytes. - -2.0.1 - Minor updates. - - - Make default umask correspond to documentation. - - Improve documentation. - - Set default mode to include execute bit. The {u,f,d}mask can be used - to take it away if desired. This allows binaries to be executed from - a mounted ntfs partition. - -2.0.0 - New version number. Remove TNG from the name. Now in the kernel. - - - Add kill_super, just keeping up with the vfs changes in the kernel. - - Repeat some changes from tng-0.0.8 that somehow got lost on the way - from the CVS import into BitKeeper. - - Begin to implement proper handling of allocated_size vs - initialized_size vs data_size (i.e. i_size). Done are - mft.c::ntfs_mft_readpage(), aops.c::end_buffer_read_index_async(), - and attrib.c::load_attribute_list(). - - Lock the runlist in attrib.c::load_attribute_list() while using it. - - Fix memory leak in ntfs_file_read_compressed_block() and generally - clean up compress.c a little, removing some uncommented/unused debug - code. - - Tidy up dir.c a little bit. - - Don't bother getting the runlist in inode.c::ntfs_read_inode(). - - Merge mft.c::ntfs_mft_readpage() and aops.c::ntfs_index_readpage() - creating aops.c::ntfs_mst_readpage(), improving the handling of - holes and overflow in the process and implementing the correct - equivalent of ntfs_file_get_block() in ntfs_mst_readpage() itself. - I am aiming for correctness at the moment. Modularisation can come - later. - - Rename aops.c::end_buffer_read_index_async() to - end_buffer_read_mst_async() and optimize the overflow checking and - handling. - - Use the host of the mftbmp address space mapping to hold the ntfs - volume. This is needed so the async i/o completion handler can - retrieve a pointer to the volume. Hopefully this will not cause - problems elsewhere in the kernel... Otherwise will need to use a - fake inode. - - Complete implementation of proper handling of allocated_size vs - initialized_size vs data_size (i.e. i_size) in whole driver. - Basically aops.c is now completely rewritten. - - Change NTFS driver name to just NTFS and set version number to 2.0.0 - to make a clear distinction from the old driver which is still on - version 1.1.22. - -tng-0.0.8 - 08/03/2002 - Now using BitKeeper, http://linux-ntfs.bkbits.net/ - - - Replace bdevname(sb->s_dev) with sb->s_id. - - Remove now superfluous new-line characters in all callers of - ntfs_debug(). - - Apply kludge in ntfs_read_inode(), setting i_nlink to 1 for - directories. Without this the "find" utility gets very upset which is - fair enough as Linux/Unix do not support directory hard links. - - Further runlist merging work. (Richard Russon) - - Backwards compatibility for gcc-2.95. (Richard Russon) - - Update to kernel 2.5.5-pre1 and rediff the now tiny patch. - - Convert to new filesystem declaration using ->ntfs_get_sb() and - replacing ntfs_read_super() with ntfs_fill_super(). - - Set s_maxbytes to MAX_LFS_FILESIZE to avoid page cache page index - overflow on 32-bit architectures. - - Cleanup upcase loading code to use ntfs_(un)map_page(). - - Disable/reenable preemtion in critical sections of compession engine. - - Replace device size determination in ntfs_fill_super() with - sb->s_bdev->bd_inode->i_size (in bytes) and remove now superfluous - function super.c::get_nr_blocks(). - - Implement a mount time option (show_inodes) allowing choice of which - types of inode names readdir() returns and modify ntfs_filldir() - accordingly. There are several parameters to show_inodes: - system: system files - win32: long file names (including POSIX file names) [DEFAULT] - long: same as win32 - dos: short file names only (excluding POSIX file names) - short: same as dos - posix: same as both win32 and dos - all: all file names - Note that the options are additive, i.e. specifying: - -o show_inodes=system,show_inodes=win32,show_inodes=dos - is the same as specifying: - -o show_inodes=all - Note that the "posix" and "all" options will show all directory - names, BUT the link count on each directory inode entry is set to 1, - due to Linux not supporting directory hard links. This may well - confuse some userspace applications, since the directory names will - have the same inode numbers. Thus it is NOT advisable to use the - "posix" or "all" options. We provide them only for completeness sake. - - Add copies of allocated_size, initialized_size, and compressed_size to - the ntfs inode structure and set them up in - inode.c::ntfs_read_inode(). These reflect the unnamed data attribute - for files and the index allocation attribute for directories. - - Add copies of allocated_size and initialized_size to ntfs inode for - $BITMAP attribute of large directories and set them up in - inode.c::ntfs_read_inode(). - - Add copies of allocated_size and initialized_size to ntfs volume for - $BITMAP attribute of $MFT and set them up in - super.c::load_system_files(). - - Parse deprecated ntfs driver options (iocharset, show_sys_files, - posix, and utf8) and tell user what the new options to use are. Note - we still do support them but they will be removed with kernel 2.7.x. - - Change all occurences of integer long long printf formatting to hex - as printk() will not support long long integer format if/when the - div64 patch goes into the kernel. - - Make slab caches have stable names and change the names to what they - were intended to be. These changes are required/made possible by the - new slab cache name handling which removes the length limitation by - requiring the caller of kmem_cache_create() to supply a stable name - which is then referenced but not copied. - - Rename run_list structure to run_list_element and create a new - run_list structure containing a pointer to a run_list_element - structure and a read/write semaphore. Adapt all users of runlists - to new scheme and take and release the lock as needed. This fixes a - nasty race as the run_list changes even when inodes are locked for - reading and even when the inode isn't locked at all, so we really - needed the serialization. We use a semaphore rather than a spinlock - as memory allocations can sleep and doing everything GFP_ATOMIC - would be silly. - - Cleanup read_inode() removing all code checking for lowest_vcn != 0. - This can never happen due to the nature of lookup_attr() and how we - support attribute lists. If it did happen it would imply the inode - being corrupt. - - Check for lowest_vcn != 0 in ntfs_read_inode() and mark the inode as - bad if found. - - Update to 2.5.6-pre2 changes in struct address_space. - - Use parent_ino() when accessing d_parent inode number in dir.c. - - Import Sourceforge CVS repository into BitKeeper repository: - http://linux-ntfs.bkbits.net/ntfs-tng-2.5 - - Update fs/Makefile, fs/Config.help, fs/Config.in, and - Documentation/filesystems/ntfs.txt for NTFS TNG. - - Create kernel configuration option controlling whether debugging - is enabled or not. - - Add the required export of end_buffer_io_sync() from the patches - directory to the kernel code. - - Update inode.c::ntfs_show_options() with show_inodes mount option. - - Update errors mount option. - -tng-0.0.7 - 13/02/2002 - The driver is now feature complete for read-only! - - - Cleanup mft.c and it's debug/error output in particular. Fix a minor - bug in mapping of extent inodes. Update all the comments to fit all - the recent code changes. - - Modify vcn_to_lcn() to cope with entirely unmapped runlists. - - Cleanups in compress.c, mostly comments and folding help. - - Implement attrib.c::map_run_list() as a generic helper. - - Make compress.c::ntfs_file_read_compressed_block() use map_run_list() - thus making code shorter and enabling attribute list support. - - Cleanup incorrect use of [su]64 with %L printf format specifier in - all source files. Type casts to [unsigned] long long added to correct - the mismatches (important for architectures which have long long not - being 64 bits). - - Merge async io completion handlers for directory indexes and $MFT - data into one by setting the index_block_size{_bits} of the ntfs - inode for $MFT to the mft_record_size{_bits} of the ntfs_volume. - - Cleanup aops.c, update comments. - - Make ntfs_file_get_block() use map_run_list() so all files now - support attribute lists. - - Make ntfs_dir_readpage() almost verbatim copy of - block_read_full_page() by using ntfs_file_get_block() with only real - difference being the use of our own async io completion handler - rather than the default one, thus reducing the amount of code and - automatically enabling attribute list support for directory indices. - - Fix bug in load_attribute_list() - forgot to call brelse in error - code path. - - Change parameters to find_attr() and lookup_attr(). We no longer - pass in the upcase table and its length. These can be gotten from - ctx->ntfs_ino->vol->upcase{_len}. Update all callers. - - Cleanups in attrib.c. - - Implement merging of runlists, attrib.c::merge_run_lists() and its - helpers. (Richard Russon) - - Attribute lists part 2, attribute extents and multi part runlists: - enable proper support for LCN_RL_NOT_MAPPED and automatic mapping of - further runlist parts via attrib.c::map_run_list(). - - Tiny endianness bug fix in decompress_mapping_pairs(). - -tng-0.0.6 - Encrypted directories, bug fixes, cleanups, debugging enhancements. - - - Enable encrypted directories. (Their index root is marked encrypted - to indicate that new files in that directory should be created - encrypted.) - - Fix bug in NInoBmpNonResident() macro. (Cut and paste error.) - - Enable $Extend system directory. Most (if not all) extended system - files do not have unnamed data attributes so ntfs_read_inode() had to - special case them but that is ok, as the special casing recovery - happens inside an error code path so there is zero slow down in the - normal fast path. The special casing is done by introducing a new - function inode.c::ntfs_is_extended_system_file() which checks if any - of the hard links in the inode point to $Extend as being their parent - directory and if they do we assume this is an extended system file. - - Create a sysctl/proc interface to allow {dis,en}abling of debug output - when compiled with -DDEBUG. Default is debug messages to be disabled. - To enable them, one writes a non-zero value to /proc/sys/fs/ntfs-debug - (if /proc is enabled) or uses sysctl(2) to effect the same (if sysctl - interface is enabled). Inspired by old ntfs driver. - - Add debug_msgs insmod/kernel boot parameter to set whether debug - messages are {dis,en}abled. This is useful to enable debug messages - during ntfs initialization and is the only way to activate debugging - when the sysctl interface is not enabled. - - Cleanup debug output in various places. - - Remove all dollar signs ($) from the source (except comments) to - enable compilation on architectures whose gcc compiler does not - support dollar signs in the names of variables/constants. Attribute - types now start with AT_ instead of $ and $I30 is now just I30. - - Cleanup ntfs_lookup() and add consistency check of sequence numbers. - - Load complete runlist for $MFT/$BITMAP during mount and cleanup - access functions. This means we now cope with $MFT/$BITMAP being - spread accross several mft records. - - Disable modification of mft_zone_multiplier on remount. We can always - reenable this later on if we really want to, but we will need to make - sure we readjust the mft_zone size / layout accordingly. - -tng-0.0.5 - Modernize for 2.5.x and further in line-ing with Al Viro's comments. - - - Use sb_set_blocksize() instead of set_blocksize() and verify the - return value. - - Use sb_bread() instead of bread() throughout. - - Add index_vcn_size{_bits} to ntfs_inode structure to store the size - of a directory index block vcn. Apply resulting simplifications in - dir.c everywhere. - - Fix a small bug somewhere (but forgot what it was). - - Change ntfs_{debug,error,warning} to enable gcc to do type checking - on the printf-format parameter list and fix bugs reported by gcc - as a result. (Richard Russon) - - Move inode allocation strategy to Al's new stuff but maintain the - divorce of ntfs_inode from struct inode. To achieve this we have two - separate slab caches, one for big ntfs inodes containing a struct - inode and pure ntfs inodes and at the same time fix some faulty - error code paths in ntfs_read_inode(). - - Show mount options in proc (inode.c::ntfs_show_options()). - -tng-0.0.4 - Big changes, getting in line with Al Viro's comments. - - - Modified (un)map_mft_record functions to be common for read and write - case. To specify which is which, added extra parameter at front of - parameter list. Pass either READ or WRITE to this, each has the - obvious meaning. - - General cleanups to allow for easier folding in vi. - - attrib.c::decompress_mapping_pairs() now accepts the old runlist - argument, and invokes attrib.c::merge_run_lists() to merge the old - and the new runlists. - - Removed attrib.c::find_first_attr(). - - Implemented loading of attribute list and complete runlist for $MFT. - This means we now cope with $MFT being spread across several mft - records. - - Adapt to 2.5.2-pre9 and the changed create_empty_buffers() syntax. - - Adapt major/minor/kdev_t/[bk]devname stuff to new 2.5.x kernels. - - Make ntfs_volume be allocated via kmalloc() instead of using a slab - cache. There are too little ntfs_volume structures at any one time - to justify a private slab cache. - - Fix bogus kmap() use in async io completion. Now use kmap_atomic(). - Use KM_BIO_IRQ on advice from IRC/kernel... - - Use ntfs_map_page() in map_mft_record() and create ->readpage method - for reading $MFT (ntfs_mft_readpage). In the process create dedicated - address space operations (ntfs_mft_aops) for $MFT inode mapping. Also - removed the now superfluous exports from the kernel core patch. - - Fix a bug where kfree() was used instead of ntfs_free(). - - Change map_mft_record() to take ntfs_inode as argument instead of - vfs inode. Dito for unmap_mft_record(). Adapt all callers. - - Add pointer to ntfs_volume to ntfs_inode. - - Add mft record number and sequence number to ntfs_inode. Stop using - i_ino and i_generation for in-driver purposes. - - Implement attrib.c::merge_run_lists(). (Richard Russon) - - Remove use of proper inodes by extent inodes. Move i_ino and - i_generation to ntfs_inode to do this. Apply simplifications that - result and remove iget_no_wait(), etc. - - Pass ntfs_inode everywhere in the driver (used to be struct inode). - - Add reference counting in ntfs_inode for the ntfs inode itself and - for the mapped mft record. - - Extend mft record mapping so we can (un)map extent mft records (new - functions (un)map_extent_mft_record), and so mappings are reference - counted and don't have to happen twice if already mapped - just ref - count increases. - - Add -o iocharset as alias to -o nls for backwards compatibility. - - The latest core patch is now tiny. In fact just a single additional - export is necessary over the base kernel. - -tng-0.0.3 - Cleanups, enhancements, bug fixes. - - - Work on attrib.c::decompress_mapping_pairs() to detect base extents - and setup the runlist appropriately using knowledge provided by the - sizes in the base attribute record. - - Balance the get_/put_attr_search_ctx() calls so we don't leak memory - any more. - - Introduce ntfs_malloc_nofs() and ntfs_free() to allocate/free a single - page or use vmalloc depending on the amount of memory requested. - - Cleanup error output. The __FUNCTION__ "(): " is now added - automatically. Introduced a new header file debug.h to support this - and also moved ntfs_debug() function into it. - - Make reading of compressed files more intelligent and especially get - rid of the vmalloc_nofs() from readpage(). This now uses per CPU - buffers (allocated at first mount with cluster size <= 4kiB and - deallocated on last umount with cluster size <= 4kiB), and - asynchronous io for the compressed data using a list of buffer heads. - Er, we use synchronous io as async io only works on whole pages - covered by buffers and not on individual buffer heads... - - Bug fix for reading compressed files with sparse compression blocks. - -tng-0.0.2 - Now handles larger/fragmented/compressed volumes/files/dirs. - - - Fixed handling of directories when cluster size exceeds index block - size. - - Hide DOS only name space directory entries from readdir() but allow - them in lookup(). This should fix the problem that Linux doesn't - support directory hard links, while still allowing access to entries - via their short file name. This also has the benefit of mimicking - what Windows users are used to, so it is the ideal solution. - - Implemented sync_page everywhere so no more hangs in D state when - waiting for a page. - - Stop using bforget() in favour of brelse(). - - Stop locking buffers unnecessarily. - - Implemented compressed files (inode->mapping contains uncompressed - data, raw compressed data is currently bread() into a vmalloc()ed - memory buffer). - - Enable compressed directories. (Their index root is marked compressed - to indicate that new files in that directory should be created - compressed.) - - Use vsnprintf rather than vsprintf in the ntfs_error and ntfs_warning - functions. (Thanks to Will Dyson for pointing this out.) - - Moved the ntfs_inode and ntfs_volume (the former ntfs_inode_info and - ntfs_sb_info) out of the common inode and super_block structures and - started using the generic_ip and generic_sbp pointers instead. This - makes ntfs entirely private with respect to the kernel tree. - - Detect compiler version and abort with error message if gcc less than - 2.96 is used. - - Fix bug in name comparison function in unistr.c. - - Implement attribute lists part 1, the infrastructure: search contexts - and operations, find_external_attr(), lookup_attr()) and make the - code use the infrastructure. - - Fix stupid buffer overflow bug that became apparent on larger run - list containing attributes. - - Fix bugs in readdir() that became apparent on larger directories. - - The driver is now really useful and survives the test - find . -type f -exec md5sum "{}" \; - without any error messages on a over 1GiB sized partition with >16k - files on it, including compressed files and directories and many files - and directories with attribute lists. - -tng-0.0.1 - The first useful version. - - - Added ntfs_lookup(). - - Added default upcase generation and handling. - - Added compile options to be shown on module init. - - Many bug fixes that were "hidden" before. - - Update to latest kernel. - - Added ntfs_readdir(). - - Added file operations for mmap(), read(), open() and llseek(). We just - use the generic ones. The whole point of going through implementing - readpage() methods and where possible get_block() call backs is that - this allows us to make use of the generic high level methods provided - by the kernel. - - The driver is now actually useful! Yey. (-: It undoubtedly has got bugs - though and it doesn't implement accesssing compressed files yet. Also, - accessing files with attribute list attributes is not implemented yet - either. But for small or simple filesystems it should work and allow - you to list directories, use stat on directory entries and the file - system, open, read, mmap and llseek around in files. A big mile stone - has been reached! - -tng-0.0.0 - Initial version tag. - - Initial driver implementation. The driver can mount and umount simple - NTFS filesystems (i.e. ones without attribute lists in the system - files). If the mount fails there might be problems in the error handling - code paths, so be warned. Otherwise it seems to be loading the system - files nicely and the mft record read mapping/unmapping seems to be - working nicely, too. Proof of inode metadata in the page cache and non- - resident file unnamed stream data in the page cache concepts is thus - complete. diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index 1cf39dfaee7a..0de1db6cddbf 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -31,6 +31,7 @@ #include <linux/vfs.h> #include <linux/moduleparam.h> #include <linux/smp_lock.h> +#include <linux/bitmap.h> #include "sysctl.h" #include "logfile.h" @@ -2458,7 +2459,6 @@ static void ntfs_put_super(struct super_block *sb) static s64 get_nr_free_clusters(ntfs_volume *vol) { s64 nr_free = vol->nr_clusters; - u32 *kaddr; struct address_space *mapping = vol->lcnbmp_ino->i_mapping; struct page *page; pgoff_t index, max_index; @@ -2477,7 +2477,8 @@ static s64 get_nr_free_clusters(ntfs_volume *vol) ntfs_debug("Reading $Bitmap, max_index = 0x%lx, max_size = 0x%lx.", max_index, PAGE_CACHE_SIZE / 4); for (index = 0; index < max_index; index++) { - unsigned int i; + unsigned long *kaddr; + /* * Read the page from page cache, getting it from backing store * if necessary, and increment the use count. @@ -2490,16 +2491,16 @@ static s64 get_nr_free_clusters(ntfs_volume *vol) nr_free -= PAGE_CACHE_SIZE * 8; continue; } - kaddr = (u32*)kmap_atomic(page, KM_USER0); + kaddr = kmap_atomic(page, KM_USER0); /* - * For each 4 bytes, subtract the number of set bits. If this + * Subtract the number of set bits. If this * is the last page and it is partial we don't really care as * it just means we do a little extra work but it won't affect * the result as all out of range bytes are set to zero by * ntfs_readpage(). */ - for (i = 0; i < PAGE_CACHE_SIZE / 4; i++) - nr_free -= (s64)hweight32(kaddr[i]); + nr_free -= bitmap_weight(kaddr, + PAGE_CACHE_SIZE * BITS_PER_BYTE); kunmap_atomic(kaddr, KM_USER0); page_cache_release(page); } @@ -2538,7 +2539,6 @@ static s64 get_nr_free_clusters(ntfs_volume *vol) static unsigned long __get_nr_free_mft_records(ntfs_volume *vol, s64 nr_free, const pgoff_t max_index) { - u32 *kaddr; struct address_space *mapping = vol->mftbmp_ino->i_mapping; struct page *page; pgoff_t index; @@ -2548,7 +2548,8 @@ static unsigned long __get_nr_free_mft_records(ntfs_volume *vol, ntfs_debug("Reading $MFT/$BITMAP, max_index = 0x%lx, max_size = " "0x%lx.", max_index, PAGE_CACHE_SIZE / 4); for (index = 0; index < max_index; index++) { - unsigned int i; + unsigned long *kaddr; + /* * Read the page from page cache, getting it from backing store * if necessary, and increment the use count. @@ -2561,16 +2562,16 @@ static unsigned long __get_nr_free_mft_records(ntfs_volume *vol, nr_free -= PAGE_CACHE_SIZE * 8; continue; } - kaddr = (u32*)kmap_atomic(page, KM_USER0); + kaddr = kmap_atomic(page, KM_USER0); /* - * For each 4 bytes, subtract the number of set bits. If this + * Subtract the number of set bits. If this * is the last page and it is partial we don't really care as * it just means we do a little extra work but it won't affect * the result as all out of range bytes are set to zero by * ntfs_readpage(). */ - for (i = 0; i < PAGE_CACHE_SIZE / 4; i++) - nr_free -= (s64)hweight32(kaddr[i]); + nr_free -= bitmap_weight(kaddr, + PAGE_CACHE_SIZE * BITS_PER_BYTE); kunmap_atomic(kaddr, KM_USER0); page_cache_release(page); } diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index d8d0c65ac03c..73e743eea2c8 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -72,9 +72,9 @@ #include "tcp_internal.h" -#define SC_NODEF_FMT "node %s (num %u) at %u.%u.%u.%u:%u" +#define SC_NODEF_FMT "node %s (num %u) at %pI4:%u" #define SC_NODEF_ARGS(sc) sc->sc_node->nd_name, sc->sc_node->nd_num, \ - NIPQUAD(sc->sc_node->nd_ipv4_address), \ + &sc->sc_node->nd_ipv4_address, \ ntohs(sc->sc_node->nd_ipv4_port) /* diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 8298608d4165..50c4ee805da4 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -1881,7 +1881,7 @@ out: * ocfs2_file_lock() and ocfs2_file_unlock() map to a single pair of * flock() calls. The locking approach this requires is sufficiently * different from all other cluster lock types that we implement a - * seperate path to the "low-level" dlm calls. In particular: + * separate path to the "low-level" dlm calls. In particular: * * - No optimization of lock levels is done - we take at exactly * what's been requested. diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c index 5328529e7fd2..c562a7581cf9 100644 --- a/fs/ocfs2/extent_map.c +++ b/fs/ocfs2/extent_map.c @@ -453,7 +453,7 @@ static int ocfs2_get_clusters_nocache(struct inode *inode, if (i == -1) { /* * Holes can be larger than the maximum size of an - * extent, so we return their lengths in a seperate + * extent, so we return their lengths in a separate * field. */ if (hole_len) { diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c index ebf3440d28ca..277575ddc05c 100644 --- a/fs/qnx4/inode.c +++ b/fs/qnx4/inode.c @@ -201,7 +201,8 @@ static const char *qnx4_checkroot(struct super_block *sb) rootdir = (struct qnx4_inode_entry *) (bh->b_data + i * QNX4_DIR_ENTRY_SIZE); if (rootdir->di_fname != NULL) { QNX4DEBUG((KERN_INFO "rootdir entry found : [%s]\n", rootdir->di_fname)); - if (!strncmp(rootdir->di_fname, QNX4_BMNAME, sizeof QNX4_BMNAME)) { + if (!strcmp(rootdir->di_fname, + QNX4_BMNAME)) { found = 1; qnx4_sb(sb)->BitMap = kmalloc( sizeof( struct qnx4_inode_entry ), GFP_KERNEL ); if (!qnx4_sb(sb)->BitMap) { diff --git a/fs/reiserfs/bitmap.c b/fs/reiserfs/bitmap.c index dc014f7def05..483442e66ed6 100644 --- a/fs/reiserfs/bitmap.c +++ b/fs/reiserfs/bitmap.c @@ -169,7 +169,7 @@ static int scan_bitmap_block(struct reiserfs_transaction_handle *th, return 0; // No free blocks in this bitmap } - /* search for a first zero bit -- beggining of a window */ + /* search for a first zero bit -- beginning of a window */ *beg = reiserfs_find_next_zero_le_bit ((unsigned long *)(bh->b_data), boundary, *beg); diff --git a/fs/select.c b/fs/select.c index 73715e90030f..500a669f7790 100644 --- a/fs/select.c +++ b/fs/select.c @@ -691,6 +691,23 @@ SYSCALL_DEFINE6(pselect6, int, n, fd_set __user *, inp, fd_set __user *, outp, } #endif /* HAVE_SET_RESTORE_SIGMASK */ +#ifdef __ARCH_WANT_SYS_OLD_SELECT +struct sel_arg_struct { + unsigned long n; + fd_set __user *inp, *outp, *exp; + struct timeval __user *tvp; +}; + +SYSCALL_DEFINE1(old_select, struct sel_arg_struct __user *, arg) +{ + struct sel_arg_struct a; + + if (copy_from_user(&a, arg, sizeof(a))) + return -EFAULT; + return sys_select(a.n, a.inp, a.outp, a.exp, a.tvp); +} +#endif + struct poll_list { struct poll_list *next; int len; diff --git a/fs/udf/balloc.c b/fs/udf/balloc.c index ccc3ad7242d4..19626e2491c4 100644 --- a/fs/udf/balloc.c +++ b/fs/udf/balloc.c @@ -31,55 +31,8 @@ #define udf_clear_bit(nr, addr) ext2_clear_bit(nr, addr) #define udf_set_bit(nr, addr) ext2_set_bit(nr, addr) #define udf_test_bit(nr, addr) ext2_test_bit(nr, addr) -#define udf_find_first_one_bit(addr, size) find_first_one_bit(addr, size) #define udf_find_next_one_bit(addr, size, offset) \ - find_next_one_bit(addr, size, offset) - -#define leBPL_to_cpup(x) leNUM_to_cpup(BITS_PER_LONG, x) -#define leNUM_to_cpup(x, y) xleNUM_to_cpup(x, y) -#define xleNUM_to_cpup(x, y) (le ## x ## _to_cpup(y)) -#define uintBPL_t uint(BITS_PER_LONG) -#define uint(x) xuint(x) -#define xuint(x) __le ## x - -static inline int find_next_one_bit(void *addr, int size, int offset) -{ - uintBPL_t *p = ((uintBPL_t *) addr) + (offset / BITS_PER_LONG); - int result = offset & ~(BITS_PER_LONG - 1); - unsigned long tmp; - - if (offset >= size) - return size; - size -= result; - offset &= (BITS_PER_LONG - 1); - if (offset) { - tmp = leBPL_to_cpup(p++); - tmp &= ~0UL << offset; - if (size < BITS_PER_LONG) - goto found_first; - if (tmp) - goto found_middle; - size -= BITS_PER_LONG; - result += BITS_PER_LONG; - } - while (size & ~(BITS_PER_LONG - 1)) { - tmp = leBPL_to_cpup(p++); - if (tmp) - goto found_middle; - result += BITS_PER_LONG; - size -= BITS_PER_LONG; - } - if (!size) - return result; - tmp = leBPL_to_cpup(p); -found_first: - tmp &= ~0UL >> (BITS_PER_LONG - size); -found_middle: - return result + ffz(~tmp); -} - -#define find_first_one_bit(addr, size)\ - find_next_one_bit((addr), (size), 0) + ext2_find_next_bit(addr, size, offset) static int read_block_bitmap(struct super_block *sb, struct udf_bitmap *bitmap, unsigned int block, diff --git a/fs/udf/inode.c b/fs/udf/inode.c index b57ab0402d89..bb863fe579ac 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -106,7 +106,7 @@ void udf_clear_inode(struct inode *inode) if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB && inode->i_size != iinfo->i_lenExtents) { printk(KERN_WARNING "UDF-fs (%s): Inode %lu (mode %o) has " - "inode size %llu different from extent lenght %llu. " + "inode size %llu different from extent length %llu. " "Filesystem need not be standards compliant.\n", inode->i_sb->s_id, inode->i_ino, inode->i_mode, (unsigned long long)inode->i_size, @@ -1408,20 +1408,19 @@ static int udf_update_inode(struct inode *inode, int do_sync) unsigned char blocksize_bits = inode->i_sb->s_blocksize_bits; struct udf_inode_info *iinfo = UDF_I(inode); - bh = udf_tread(inode->i_sb, - udf_get_lb_pblock(inode->i_sb, - &iinfo->i_location, 0)); + bh = udf_tgetblk(inode->i_sb, + udf_get_lb_pblock(inode->i_sb, &iinfo->i_location, 0)); if (!bh) { - udf_debug("bread failure\n"); - return -EIO; + udf_debug("getblk failure\n"); + return -ENOMEM; } - memset(bh->b_data, 0x00, inode->i_sb->s_blocksize); - + lock_buffer(bh); + memset(bh->b_data, 0, inode->i_sb->s_blocksize); fe = (struct fileEntry *)bh->b_data; efe = (struct extendedFileEntry *)bh->b_data; - if (fe->descTag.tagIdent == cpu_to_le16(TAG_IDENT_USE)) { + if (iinfo->i_use) { struct unallocSpaceEntry *use = (struct unallocSpaceEntry *)bh->b_data; @@ -1429,20 +1428,18 @@ static int udf_update_inode(struct inode *inode, int do_sync) memcpy(bh->b_data + sizeof(struct unallocSpaceEntry), iinfo->i_ext.i_data, inode->i_sb->s_blocksize - sizeof(struct unallocSpaceEntry)); + use->descTag.tagIdent = cpu_to_le16(TAG_IDENT_USE); + use->descTag.tagLocation = + cpu_to_le32(iinfo->i_location.logicalBlockNum); crclen = sizeof(struct unallocSpaceEntry) + iinfo->i_lenAlloc - sizeof(struct tag); - use->descTag.tagLocation = cpu_to_le32( - iinfo->i_location. - logicalBlockNum); use->descTag.descCRCLength = cpu_to_le16(crclen); use->descTag.descCRC = cpu_to_le16(crc_itu_t(0, (char *)use + sizeof(struct tag), crclen)); use->descTag.tagChecksum = udf_tag_checksum(&use->descTag); - mark_buffer_dirty(bh); - brelse(bh); - return err; + goto out; } if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_UID_FORGET)) @@ -1597,18 +1594,21 @@ static int udf_update_inode(struct inode *inode, int do_sync) fe->descTag.tagSerialNum = cpu_to_le16(sbi->s_serial_number); fe->descTag.tagLocation = cpu_to_le32( iinfo->i_location.logicalBlockNum); - crclen += iinfo->i_lenEAttr + iinfo->i_lenAlloc - - sizeof(struct tag); + crclen += iinfo->i_lenEAttr + iinfo->i_lenAlloc - sizeof(struct tag); fe->descTag.descCRCLength = cpu_to_le16(crclen); fe->descTag.descCRC = cpu_to_le16(crc_itu_t(0, (char *)fe + sizeof(struct tag), crclen)); fe->descTag.tagChecksum = udf_tag_checksum(&fe->descTag); +out: + set_buffer_uptodate(bh); + unlock_buffer(bh); + /* write the data blocks */ mark_buffer_dirty(bh); if (do_sync) { sync_dirty_buffer(bh); - if (buffer_req(bh) && !buffer_uptodate(bh)) { + if (buffer_write_io_error(bh)) { printk(KERN_WARNING "IO error syncing udf inode " "[%s:%08lx]\n", inode->i_sb->s_id, inode->i_ino); diff --git a/fs/ufs/super.c b/fs/ufs/super.c index 66b63a751615..14743d935a93 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -1016,6 +1016,9 @@ magic_found: case UFS_FSSTABLE: UFSD("fs is stable\n"); break; + case UFS_FSLOG: + UFSD("fs is logging fs\n"); + break; case UFS_FSOSF1: UFSD("fs is DEC OSF/1\n"); break; diff --git a/fs/ufs/ufs_fs.h b/fs/ufs/ufs_fs.h index 54bde1895a80..6943ec677c0b 100644 --- a/fs/ufs/ufs_fs.h +++ b/fs/ufs/ufs_fs.h @@ -138,6 +138,7 @@ typedef __u16 __bitwise __fs16; #define UFS_USEEFT ((__u16)65535) +/* fs_clean values */ #define UFS_FSOK 0x7c269d38 #define UFS_FSACTIVE ((__s8)0x00) #define UFS_FSCLEAN ((__s8)0x01) @@ -145,6 +146,11 @@ typedef __u16 __bitwise __fs16; #define UFS_FSOSF1 ((__s8)0x03) /* is this correct for DEC OSF/1? */ #define UFS_FSBAD ((__s8)0xff) +/* Solaris-specific fs_clean values */ +#define UFS_FSSUSPEND ((__s8)0xfe) /* temporarily suspended */ +#define UFS_FSLOG ((__s8)0xfd) /* logging fs */ +#define UFS_FSFIX ((__s8)0xfc) /* being repaired while mounted */ + /* From here to next blank line, s_flags for ufs_sb_info */ /* directory entry encoding */ #define UFS_DE_MASK 0x00000010 /* mask for the following */ @@ -227,11 +233,16 @@ typedef __u16 __bitwise __fs16; */ #define ufs_cbtocylno(bno) \ ((bno) * uspi->s_nspf / uspi->s_spc) -#define ufs_cbtorpos(bno) \ +#define ufs_cbtorpos(bno) \ + ((UFS_SB(sb)->s_flags & UFS_CG_SUN) ? \ + (((((bno) * uspi->s_nspf % uspi->s_spc) % \ + uspi->s_nsect) * \ + uspi->s_nrpos) / uspi->s_nsect) \ + : \ ((((bno) * uspi->s_nspf % uspi->s_spc / uspi->s_nsect \ * uspi->s_trackskew + (bno) * uspi->s_nspf % uspi->s_spc \ % uspi->s_nsect * uspi->s_interleave) % uspi->s_nsect \ - * uspi->s_nrpos) / uspi->s_npsect) + * uspi->s_nrpos) / uspi->s_npsect)) /* * The following macros optimize certain frequently calculated diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c index 9083357f9e44..99628508cb11 100644 --- a/fs/xfs/linux-2.6/xfs_aops.c +++ b/fs/xfs/linux-2.6/xfs_aops.c @@ -932,6 +932,9 @@ xfs_aops_discard_page( if (!xfs_is_delayed_page(page, IOMAP_DELAY)) goto out_invalidate; + if (XFS_FORCED_SHUTDOWN(ip->i_mount)) + goto out_invalidate; + xfs_fs_cmn_err(CE_ALERT, ip->i_mount, "page discard on page %p, inode 0x%llx, offset %llu.", page, ip->i_ino, offset); @@ -964,8 +967,10 @@ xfs_aops_discard_page( if (error) { /* something screwed, just bail */ - xfs_fs_cmn_err(CE_ALERT, ip->i_mount, - "page discard failed delalloc mapping lookup."); + if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) { + xfs_fs_cmn_err(CE_ALERT, ip->i_mount, + "page discard failed delalloc mapping lookup."); + } break; } if (!nimaps) { @@ -991,8 +996,10 @@ xfs_aops_discard_page( ASSERT(!flist.xbf_count && !flist.xbf_first); if (error) { /* something screwed, just bail */ - xfs_fs_cmn_err(CE_ALERT, ip->i_mount, + if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) { + xfs_fs_cmn_err(CE_ALERT, ip->i_mount, "page discard unable to remove delalloc mapping."); + } break; } next_buffer: diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c index 6f76ba85f193..bd111b7e1daa 100644 --- a/fs/xfs/linux-2.6/xfs_buf.c +++ b/fs/xfs/linux-2.6/xfs_buf.c @@ -168,75 +168,6 @@ test_page_region( } /* - * Mapping of multi-page buffers into contiguous virtual space - */ - -typedef struct a_list { - void *vm_addr; - struct a_list *next; -} a_list_t; - -static a_list_t *as_free_head; -static int as_list_len; -static DEFINE_SPINLOCK(as_lock); - -/* - * Try to batch vunmaps because they are costly. - */ -STATIC void -free_address( - void *addr) -{ - a_list_t *aentry; - -#ifdef CONFIG_XEN - /* - * Xen needs to be able to make sure it can get an exclusive - * RO mapping of pages it wants to turn into a pagetable. If - * a newly allocated page is also still being vmap()ed by xfs, - * it will cause pagetable construction to fail. This is a - * quick workaround to always eagerly unmap pages so that Xen - * is happy. - */ - vunmap(addr); - return; -#endif - - aentry = kmalloc(sizeof(a_list_t), GFP_NOWAIT); - if (likely(aentry)) { - spin_lock(&as_lock); - aentry->next = as_free_head; - aentry->vm_addr = addr; - as_free_head = aentry; - as_list_len++; - spin_unlock(&as_lock); - } else { - vunmap(addr); - } -} - -STATIC void -purge_addresses(void) -{ - a_list_t *aentry, *old; - - if (as_free_head == NULL) - return; - - spin_lock(&as_lock); - aentry = as_free_head; - as_free_head = NULL; - as_list_len = 0; - spin_unlock(&as_lock); - - while ((old = aentry) != NULL) { - vunmap(aentry->vm_addr); - aentry = aentry->next; - kfree(old); - } -} - -/* * Internal xfs_buf_t object manipulation */ @@ -337,7 +268,8 @@ xfs_buf_free( uint i; if (xfs_buf_is_vmapped(bp)) - free_address(bp->b_addr - bp->b_offset); + vm_unmap_ram(bp->b_addr - bp->b_offset, + bp->b_page_count); for (i = 0; i < bp->b_page_count; i++) { struct page *page = bp->b_pages[i]; @@ -457,10 +389,8 @@ _xfs_buf_map_pages( bp->b_addr = page_address(bp->b_pages[0]) + bp->b_offset; bp->b_flags |= XBF_MAPPED; } else if (flags & XBF_MAPPED) { - if (as_list_len > 64) - purge_addresses(); - bp->b_addr = vmap(bp->b_pages, bp->b_page_count, - VM_MAP, PAGE_KERNEL); + bp->b_addr = vm_map_ram(bp->b_pages, bp->b_page_count, + -1, PAGE_KERNEL); if (unlikely(bp->b_addr == NULL)) return -ENOMEM; bp->b_addr += bp->b_offset; @@ -1955,9 +1885,6 @@ xfsbufd( xfs_buf_iostrategy(bp); count++; } - - if (as_list_len > 0) - purge_addresses(); if (count) blk_run_address_space(target->bt_mapping); |