diff options
Diffstat (limited to 'fs/reiserfs/inode.c')
| -rw-r--r-- | fs/reiserfs/inode.c | 4915 |
1 files changed, 2521 insertions, 2394 deletions
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 289d864fe73..1aaf2c7d44e 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -18,107 +18,109 @@ #include <linux/writeback.h> #include <linux/quotaops.h> -extern int reiserfs_default_io_size; /* default io size devuned in super.c */ +extern int reiserfs_default_io_size; /* default io size devuned in super.c */ static int reiserfs_commit_write(struct file *f, struct page *page, - unsigned from, unsigned to); + unsigned from, unsigned to); static int reiserfs_prepare_write(struct file *f, struct page *page, unsigned from, unsigned to); -void reiserfs_delete_inode (struct inode * inode) +void reiserfs_delete_inode(struct inode *inode) { - /* We need blocks for transaction + (user+group) quota update (possibly delete) */ - int jbegin_count = JOURNAL_PER_BALANCE_CNT * 2 + 2 * REISERFS_QUOTA_INIT_BLOCKS(inode->i_sb); - struct reiserfs_transaction_handle th ; - - reiserfs_write_lock(inode->i_sb); + /* We need blocks for transaction + (user+group) quota update (possibly delete) */ + int jbegin_count = + JOURNAL_PER_BALANCE_CNT * 2 + + 2 * REISERFS_QUOTA_INIT_BLOCKS(inode->i_sb); + struct reiserfs_transaction_handle th; - /* The = 0 happens when we abort creating a new inode for some reason like lack of space.. */ - if (!(inode->i_state & I_NEW) && INODE_PKEY(inode)->k_objectid != 0) { /* also handles bad_inode case */ - down (&inode->i_sem); + reiserfs_write_lock(inode->i_sb); - reiserfs_delete_xattrs (inode); + /* The = 0 happens when we abort creating a new inode for some reason like lack of space.. */ + if (!(inode->i_state & I_NEW) && INODE_PKEY(inode)->k_objectid != 0) { /* also handles bad_inode case */ + down(&inode->i_sem); - if (journal_begin(&th, inode->i_sb, jbegin_count)) { - up (&inode->i_sem); - goto out; - } - reiserfs_update_inode_transaction(inode) ; + reiserfs_delete_xattrs(inode); - if (reiserfs_delete_object (&th, inode)) { - up (&inode->i_sem); - goto out; - } + if (journal_begin(&th, inode->i_sb, jbegin_count)) { + up(&inode->i_sem); + goto out; + } + reiserfs_update_inode_transaction(inode); - /* Do quota update inside a transaction for journaled quotas. We must do that - * after delete_object so that quota updates go into the same transaction as - * stat data deletion */ - DQUOT_FREE_INODE(inode); + if (reiserfs_delete_object(&th, inode)) { + up(&inode->i_sem); + goto out; + } - if (journal_end(&th, inode->i_sb, jbegin_count)) { - up (&inode->i_sem); - goto out; - } + /* Do quota update inside a transaction for journaled quotas. We must do that + * after delete_object so that quota updates go into the same transaction as + * stat data deletion */ + DQUOT_FREE_INODE(inode); + + if (journal_end(&th, inode->i_sb, jbegin_count)) { + up(&inode->i_sem); + goto out; + } - up (&inode->i_sem); + up(&inode->i_sem); - /* all items of file are deleted, so we can remove "save" link */ - remove_save_link (inode, 0/* not truncate */); /* we can't do anything - * about an error here */ - } else { - /* no object items are in the tree */ - ; - } -out: - clear_inode (inode); /* note this must go after the journal_end to prevent deadlock */ - inode->i_blocks = 0; - reiserfs_write_unlock(inode->i_sb); + /* all items of file are deleted, so we can remove "save" link */ + remove_save_link(inode, 0 /* not truncate */ ); /* we can't do anything + * about an error here */ + } else { + /* no object items are in the tree */ + ; + } + out: + clear_inode(inode); /* note this must go after the journal_end to prevent deadlock */ + inode->i_blocks = 0; + reiserfs_write_unlock(inode->i_sb); } -static void _make_cpu_key (struct cpu_key * key, int version, __u32 dirid, __u32 objectid, - loff_t offset, int type, int length ) +static void _make_cpu_key(struct cpu_key *key, int version, __u32 dirid, + __u32 objectid, loff_t offset, int type, int length) { - key->version = version; + key->version = version; - key->on_disk_key.k_dir_id = dirid; - key->on_disk_key.k_objectid = objectid; - set_cpu_key_k_offset (key, offset); - set_cpu_key_k_type (key, type); - key->key_length = length; + key->on_disk_key.k_dir_id = dirid; + key->on_disk_key.k_objectid = objectid; + set_cpu_key_k_offset(key, offset); + set_cpu_key_k_type(key, type); + key->key_length = length; } - /* take base of inode_key (it comes from inode always) (dirid, objectid) and version from an inode, set offset and type of key */ -void make_cpu_key (struct cpu_key * key, struct inode * inode, loff_t offset, - int type, int length ) +void make_cpu_key(struct cpu_key *key, struct inode *inode, loff_t offset, + int type, int length) { - _make_cpu_key (key, get_inode_item_key_version (inode), le32_to_cpu (INODE_PKEY (inode)->k_dir_id), - le32_to_cpu (INODE_PKEY (inode)->k_objectid), - offset, type, length); + _make_cpu_key(key, get_inode_item_key_version(inode), + le32_to_cpu(INODE_PKEY(inode)->k_dir_id), + le32_to_cpu(INODE_PKEY(inode)->k_objectid), offset, type, + length); } - // // when key is 0, do not set version and short key // -inline void make_le_item_head (struct item_head * ih, const struct cpu_key * key, - int version, - loff_t offset, int type, int length, - int entry_count/*or ih_free_space*/) +inline void make_le_item_head(struct item_head *ih, const struct cpu_key *key, + int version, + loff_t offset, int type, int length, + int entry_count /*or ih_free_space */ ) { - if (key) { - ih->ih_key.k_dir_id = cpu_to_le32 (key->on_disk_key.k_dir_id); - ih->ih_key.k_objectid = cpu_to_le32 (key->on_disk_key.k_objectid); - } - put_ih_version( ih, version ); - set_le_ih_k_offset (ih, offset); - set_le_ih_k_type (ih, type); - put_ih_item_len( ih, length ); - /* set_ih_free_space (ih, 0);*/ - // for directory items it is entry count, for directs and stat - // datas - 0xffff, for indirects - 0 - put_ih_entry_count( ih, entry_count ); + if (key) { + ih->ih_key.k_dir_id = cpu_to_le32(key->on_disk_key.k_dir_id); + ih->ih_key.k_objectid = + cpu_to_le32(key->on_disk_key.k_objectid); + } + put_ih_version(ih, version); + set_le_ih_k_offset(ih, offset); + set_le_ih_k_type(ih, type); + put_ih_item_len(ih, length); + /* set_ih_free_space (ih, 0); */ + // for directory items it is entry count, for directs and stat + // datas - 0xffff, for indirects - 0 + put_ih_entry_count(ih, entry_count); } // @@ -153,84 +155,84 @@ inline void make_le_item_head (struct item_head * ih, const struct cpu_key * key ** to be unmapped, so that block_prepare_write will correctly call ** reiserfs_get_block to convert the tail into an unformatted node */ -static inline void fix_tail_page_for_writing(struct page *page) { - struct buffer_head *head, *next, *bh ; - - if (page && page_has_buffers(page)) { - head = page_buffers(page) ; - bh = head ; - do { - next = bh->b_this_page ; - if (buffer_mapped(bh) && bh->b_blocknr == 0) { - reiserfs_unmap_buffer(bh) ; - } - bh = next ; - } while (bh != head) ; - } +static inline void fix_tail_page_for_writing(struct page *page) +{ + struct buffer_head *head, *next, *bh; + + if (page && page_has_buffers(page)) { + head = page_buffers(page); + bh = head; + do { + next = bh->b_this_page; + if (buffer_mapped(bh) && bh->b_blocknr == 0) { + reiserfs_unmap_buffer(bh); + } + bh = next; + } while (bh != head); + } } /* reiserfs_get_block does not need to allocate a block only if it has been done already or non-hole position has been found in the indirect item */ -static inline int allocation_needed (int retval, b_blocknr_t allocated, - struct item_head * ih, - __le32 * item, int pos_in_item) +static inline int allocation_needed(int retval, b_blocknr_t allocated, + struct item_head *ih, + __le32 * item, int pos_in_item) { - if (allocated) - return 0; - if (retval == POSITION_FOUND && is_indirect_le_ih (ih) && - get_block_num(item, pos_in_item)) - return 0; - return 1; + if (allocated) + return 0; + if (retval == POSITION_FOUND && is_indirect_le_ih(ih) && + get_block_num(item, pos_in_item)) + return 0; + return 1; } -static inline int indirect_item_found (int retval, struct item_head * ih) +static inline int indirect_item_found(int retval, struct item_head *ih) { - return (retval == POSITION_FOUND) && is_indirect_le_ih (ih); + return (retval == POSITION_FOUND) && is_indirect_le_ih(ih); } - -static inline void set_block_dev_mapped (struct buffer_head * bh, - b_blocknr_t block, struct inode * inode) +static inline void set_block_dev_mapped(struct buffer_head *bh, + b_blocknr_t block, struct inode *inode) { map_bh(bh, inode->i_sb, block); } - // // files which were created in the earlier version can not be longer, // than 2 gb // -static int file_capable (struct inode * inode, long block) +static int file_capable(struct inode *inode, long block) { - if (get_inode_item_key_version (inode) != KEY_FORMAT_3_5 || // it is new file. - block < (1 << (31 - inode->i_sb->s_blocksize_bits))) // old file, but 'block' is inside of 2gb - return 1; + if (get_inode_item_key_version(inode) != KEY_FORMAT_3_5 || // it is new file. + block < (1 << (31 - inode->i_sb->s_blocksize_bits))) // old file, but 'block' is inside of 2gb + return 1; - return 0; + return 0; } /*static*/ int restart_transaction(struct reiserfs_transaction_handle *th, - struct inode *inode, struct path *path) { - struct super_block *s = th->t_super ; - int len = th->t_blocks_allocated ; - int err; - - BUG_ON (!th->t_trans_id); - BUG_ON (!th->t_refcount); - - /* we cannot restart while nested */ - if (th->t_refcount > 1) { - return 0 ; - } - pathrelse(path) ; - reiserfs_update_sd(th, inode) ; - err = journal_end(th, s, len) ; - if (!err) { - err = journal_begin(th, s, JOURNAL_PER_BALANCE_CNT * 6) ; - if (!err) - reiserfs_update_inode_transaction(inode) ; - } - return err; + struct inode *inode, struct path *path) +{ + struct super_block *s = th->t_super; + int len = th->t_blocks_allocated; + int err; + + BUG_ON(!th->t_trans_id); + BUG_ON(!th->t_refcount); + + /* we cannot restart while nested */ + if (th->t_refcount > 1) { + return 0; + } + pathrelse(path); + reiserfs_update_sd(th, inode); + err = journal_end(th, s, len); + if (!err) { + err = journal_begin(th, s, JOURNAL_PER_BALANCE_CNT * 6); + if (!err) + reiserfs_update_inode_transaction(inode); + } + return err; } // it is called by get_block when create == 0. Returns block number @@ -241,190 +243,192 @@ static int file_capable (struct inode * inode, long block) // Please improve the english/clarity in the comment above, as it is // hard to understand. -static int _get_block_create_0 (struct inode * inode, long block, - struct buffer_head * bh_result, - int args) +static int _get_block_create_0(struct inode *inode, long block, + struct buffer_head *bh_result, int args) { - INITIALIZE_PATH (path); - struct cpu_key key; - struct buffer_head * bh; - struct item_head * ih, tmp_ih; - int fs_gen ; - int blocknr; - char * p = NULL; - int chars; - int ret ; - int result ; - int done = 0 ; - unsigned long offset ; - - // prepare the key to look for the 'block'-th block of file - make_cpu_key (&key, inode, - (loff_t)block * inode->i_sb->s_blocksize + 1, TYPE_ANY, 3); - -research: - result = search_for_position_by_key (inode->i_sb, &key, &path) ; - if (result != POSITION_FOUND) { - pathrelse (&path); - if (p) - kunmap(bh_result->b_page) ; - if (result == IO_ERROR) - return -EIO; - // We do not return -ENOENT if there is a hole but page is uptodate, because it means - // That there is some MMAPED data associated with it that is yet to be written to disk. - if ((args & GET_BLOCK_NO_HOLE) && !PageUptodate(bh_result->b_page) ) { - return -ENOENT ; - } - return 0 ; - } - - // - bh = get_last_bh (&path); - ih = get_ih (&path); - if (is_indirect_le_ih (ih)) { - __le32 * ind_item = (__le32 *)B_I_PITEM (bh, ih); - - /* FIXME: here we could cache indirect item or part of it in - the inode to avoid search_by_key in case of subsequent - access to file */ - blocknr = get_block_num(ind_item, path.pos_in_item) ; - ret = 0 ; - if (blocknr) { - map_bh(bh_result, inode->i_sb, blocknr); - if (path.pos_in_item == ((ih_item_len(ih) / UNFM_P_SIZE) - 1)) { - set_buffer_boundary(bh_result); - } - } else - // We do not return -ENOENT if there is a hole but page is uptodate, because it means - // That there is some MMAPED data associated with it that is yet to be written to disk. - if ((args & GET_BLOCK_NO_HOLE) && !PageUptodate(bh_result->b_page) ) { - ret = -ENOENT ; - } - - pathrelse (&path); - if (p) - kunmap(bh_result->b_page) ; - return ret ; - } - - // requested data are in direct item(s) - if (!(args & GET_BLOCK_READ_DIRECT)) { - // we are called by bmap. FIXME: we can not map block of file - // when it is stored in direct item(s) - pathrelse (&path); - if (p) - kunmap(bh_result->b_page) ; - return -ENOENT; - } - - /* if we've got a direct item, and the buffer or page was uptodate, - ** we don't want to pull data off disk again. skip to the - ** end, where we map the buffer and return - */ - if (buffer_uptodate(bh_result)) { - goto finished ; - } else - /* - ** grab_tail_page can trigger calls to reiserfs_get_block on up to date - ** pages without any buffers. If the page is up to date, we don't want - ** read old data off disk. Set the up to date bit on the buffer instead - ** and jump to the end - */ - if (!bh_result->b_page || PageUptodate(bh_result->b_page)) { + INITIALIZE_PATH(path); + struct cpu_key key; + struct buffer_head *bh; + struct item_head *ih, tmp_ih; + int fs_gen; + int blocknr; + char *p = NULL; + int chars; + int ret; + int result; + int done = 0; + unsigned long offset; + + // prepare the key to look for the 'block'-th block of file + make_cpu_key(&key, inode, + (loff_t) block * inode->i_sb->s_blocksize + 1, TYPE_ANY, + 3); + + research: + result = search_for_position_by_key(inode->i_sb, &key, &path); + if (result != POSITION_FOUND) { + pathrelse(&path); + if (p) + kunmap(bh_result->b_page); + if (result == IO_ERROR) + return -EIO; + // We do not return -ENOENT if there is a hole but page is uptodate, because it means + // That there is some MMAPED data associated with it that is yet to be written to disk. + if ((args & GET_BLOCK_NO_HOLE) + && !PageUptodate(bh_result->b_page)) { + return -ENOENT; + } + return 0; + } + // + bh = get_last_bh(&path); + ih = get_ih(&path); + if (is_indirect_le_ih(ih)) { + __le32 *ind_item = (__le32 *) B_I_PITEM(bh, ih); + + /* FIXME: here we could cache indirect item or part of it in + the inode to avoid search_by_key in case of subsequent + access to file */ + blocknr = get_block_num(ind_item, path.pos_in_item); + ret = 0; + if (blocknr) { + map_bh(bh_result, inode->i_sb, blocknr); + if (path.pos_in_item == + ((ih_item_len(ih) / UNFM_P_SIZE) - 1)) { + set_buffer_boundary(bh_result); + } + } else + // We do not return -ENOENT if there is a hole but page is uptodate, because it means + // That there is some MMAPED data associated with it that is yet to be written to disk. + if ((args & GET_BLOCK_NO_HOLE) + && !PageUptodate(bh_result->b_page)) { + ret = -ENOENT; + } + + pathrelse(&path); + if (p) + kunmap(bh_result->b_page); + return ret; + } + // requested data are in direct item(s) + if (!(args & GET_BLOCK_READ_DIRECT)) { + // we are called by bmap. FIXME: we can not map block of file + // when it is stored in direct item(s) + pathrelse(&path); + if (p) + kunmap(bh_result->b_page); + return -ENOENT; + } + + /* if we've got a direct item, and the buffer or page was uptodate, + ** we don't want to pull data off disk again. skip to the + ** end, where we map the buffer and return + */ + if (buffer_uptodate(bh_result)) { + goto finished; + } else + /* + ** grab_tail_page can trigger calls to reiserfs_get_block on up to date + ** pages without any buffers. If the page is up to date, we don't want + ** read old data off disk. Set the up to date bit on the buffer instead + ** and jump to the end + */ + if (!bh_result->b_page || PageUptodate(bh_result->b_page)) { set_buffer_uptodate(bh_result); - goto finished ; - } - - // read file tail into part of page - offset = (cpu_key_k_offset(&key) - 1) & (PAGE_CACHE_SIZE - 1) ; - fs_gen = get_generation(inode->i_sb) ; - copy_item_head (&tmp_ih, ih); - - /* we only want to kmap if we are reading the tail into the page. - ** this is not the common case, so we don't kmap until we are - ** sure we need to. But, this means the item might move if - ** kmap schedules - */ - if (!p) { - p = (char *)kmap(bh_result->b_page) ; - if (fs_changed (fs_gen, inode->i_sb) && item_moved (&tmp_ih, &path)) { - goto research; - } - } - p += offset ; - memset (p, 0, inode->i_sb->s_blocksize); - do { - if (!is_direct_le_ih (ih)) { - BUG (); - } - /* make sure we don't read more bytes than actually exist in - ** the file. This can happen in odd cases where i_size isn't - ** correct, and when direct item padding results in a few - ** extra bytes at the end of the direct item - */ - if ((le_ih_k_offset(ih) + path.pos_in_item) > inode->i_size) - break ; - if ((le_ih_k_offset(ih) - 1 + ih_item_len(ih)) > inode->i_size) { - chars = inode->i_size - (le_ih_k_offset(ih) - 1) - path.pos_in_item; - done = 1 ; - } else { - chars = ih_item_len(ih) - path.pos_in_item; - } - memcpy (p, B_I_PITEM (bh, ih) + path.pos_in_item, chars); - - if (done) - break ; - - p += chars; - - if (PATH_LAST_POSITION (&path) != (B_NR_ITEMS (bh) - 1)) - // we done, if read direct item is not the last item of - // node FIXME: we could try to check right delimiting key - // to see whether direct item continues in the right - // neighbor or rely on i_size - break; - - // update key to look for the next piece - set_cpu_key_k_offset (&key, cpu_key_k_offset (&key) + chars); - result = search_for_position_by_key (inode->i_sb, &key, &path); - if (result != POSITION_FOUND) - // i/o error most likely - break; - bh = get_last_bh (&path); - ih = get_ih (&path); - } while (1); - - flush_dcache_page(bh_result->b_page) ; - kunmap(bh_result->b_page) ; - -finished: - pathrelse (&path); - - if (result == IO_ERROR) - return -EIO; - - /* this buffer has valid data, but isn't valid for io. mapping it to - * block #0 tells the rest of reiserfs it just has a tail in it - */ - map_bh(bh_result, inode->i_sb, 0); - set_buffer_uptodate (bh_result); - return 0; -} + goto finished; + } + // read file tail into part of page + offset = (cpu_key_k_offset(&key) - 1) & (PAGE_CACHE_SIZE - 1); + fs_gen = get_generation(inode->i_sb); + copy_item_head(&tmp_ih, ih); + + /* we only want to kmap if we are reading the tail into the page. + ** this is not the common case, so we don't kmap until we are + ** sure we need to. But, this means the item might move if + ** kmap schedules + */ + if (!p) { + p = (char *)kmap(bh_result->b_page); + if (fs_changed(fs_gen, inode->i_sb) + && item_moved(&tmp_ih, &path)) { + goto research; + } + } + p += offset; + memset(p, 0, inode->i_sb->s_blocksize); + do { + if (!is_direct_le_ih(ih)) { + BUG(); + } + /* make sure we don't read more bytes than actually exist in + ** the file. This can happen in odd cases where i_size isn't + ** correct, and when direct item padding results in a few + ** extra bytes at the end of the direct item + */ + if ((le_ih_k_offset(ih) + path.pos_in_item) > inode->i_size) + break; + if ((le_ih_k_offset(ih) - 1 + ih_item_len(ih)) > inode->i_size) { + chars = + inode->i_size - (le_ih_k_offset(ih) - 1) - + path.pos_in_item; + done = 1; + } else { + chars = ih_item_len(ih) - path.pos_in_item; + } + memcpy(p, B_I_PITEM(bh, ih) + path.pos_in_item, chars); + + if (done) + break; + + p += chars; + + if (PATH_LAST_POSITION(&path) != (B_NR_ITEMS(bh) - 1)) + // we done, if read direct item is not the last item of + // node FIXME: we could try to check right delimiting key + // to see whether direct item continues in the right + // neighbor or rely on i_size + break; + + // update key to look for the next piece + set_cpu_key_k_offset(&key, cpu_key_k_offset(&key) + chars); + result = search_for_position_by_key(inode->i_sb, &key, &path); + if (result != POSITION_FOUND) + // i/o error most likely + break; + bh = get_last_bh(&path); + ih = get_ih(&path); + } while (1); + + flush_dcache_page(bh_result->b_page); + kunmap(bh_result->b_page); + + finished: + pathrelse(&path); + + if (result == IO_ERROR) + return -EIO; + /* this buffer has valid data, but isn't valid for io. mapping it to + * block #0 tells the rest of reiserfs it just has a tail in it + */ + map_bh(bh_result, inode->i_sb, 0); + set_buffer_uptodate(bh_result); + return 0; +} // this is called to create file map. So, _get_block_create_0 will not // read direct item -static int reiserfs_bmap (struct inode * inode, sector_t block, - struct buffer_head * bh_result, int create) +static int reiserfs_bmap(struct inode *inode, sector_t block, + struct buffer_head *bh_result, int create) { - if (!file_capable (inode, block)) - return -EFBIG; - - reiserfs_write_lock(inode->i_sb); - /* do not read the direct item */ - _get_block_create_0 (inode, block, bh_result, 0) ; - reiserfs_write_unlock(inode->i_sb); - return 0; + if (!file_capable(inode, block)) + return -EFBIG; + + reiserfs_write_lock(inode->i_sb); + /* do not read the direct item */ + _get_block_create_0(inode, block, bh_result, 0); + reiserfs_write_unlock(inode->i_sb); + return 0; } /* special version of get_block that is only used by grab_tail_page right @@ -444,9 +448,11 @@ static int reiserfs_bmap (struct inode * inode, sector_t block, ** don't want to send create == GET_BLOCK_NO_HOLE to reiserfs_get_block, ** don't use this function. */ -static int reiserfs_get_block_create_0 (struct inode * inode, sector_t block, - struct buffer_head * bh_result, int create) { - return reiserfs_get_block(inode, block, bh_result, GET_BLOCK_NO_HOLE) ; +static int reiserfs_get_block_create_0(struct inode *inode, sector_t block, + struct buffer_head *bh_result, + int create) +{ + return reiserfs_get_block(inode, block, bh_result, GET_BLOCK_NO_HOLE); } /* This is special helper for reiserfs_get_block in case we are executing @@ -457,43 +463,42 @@ static int reiserfs_get_blocks_direct_io(struct inode *inode, struct buffer_head *bh_result, int create) { - int ret ; - - bh_result->b_page = NULL; - - /* We set the b_size before reiserfs_get_block call since it is - referenced in convert_tail_for_hole() that may be called from - reiserfs_get_block() */ - bh_result->b_size = (1 << inode->i_blkbits); - - ret = reiserfs_get_block(inode, iblock, bh_result, - create | GET_BLOCK_NO_DANGLE) ; - if (ret) - goto out; - - /* don't allow direct io onto tail pages */ - if (buffer_mapped(bh_result) && bh_result->b_blocknr == 0) { - /* make sure future calls to the direct io funcs for this offset - ** in the file fail by unmapping the buffer - */ - clear_buffer_mapped(bh_result); - ret = -EINVAL ; - } - /* Possible unpacked tail. Flush the data before pages have - disappeared */ - if (REISERFS_I(inode)->i_flags & i_pack_on_close_mask) { - int err; - lock_kernel(); - err = reiserfs_commit_for_inode(inode); - REISERFS_I(inode)->i_flags &= ~i_pack_on_close_mask; - unlock_kernel(); - if (err < 0) - ret = err; - } -out: - return ret ; -} + int ret; + + bh_result->b_page = NULL; + /* We set the b_size before reiserfs_get_block call since it is + referenced in convert_tail_for_hole() that may be called from + reiserfs_get_block() */ + bh_result->b_size = (1 << inode->i_blkbits); + + ret = reiserfs_get_block(inode, iblock, bh_result, + create | GET_BLOCK_NO_DANGLE); + if (ret) + goto out; + + /* don't allow direct io onto tail pages */ + if (buffer_mapped(bh_result) && bh_result->b_blocknr == 0) { + /* make sure future calls to the direct io funcs for this offset + ** in the file fail by unmapping the buffer + */ + clear_buffer_mapped(bh_result); + ret = -EINVAL; + } + /* Possible unpacked tail. Flush the data before pages have + disappeared */ + if (REISERFS_I(inode)->i_flags & i_pack_on_close_mask) { + int err; + lock_kernel(); + err = reiserfs_commit_for_inode(inode); + REISERFS_I(inode)->i_flags &= ~i_pack_on_close_mask; + unlock_kernel(); + if (err < 0) + ret = err; + } + out: + return ret; +} /* ** helper function for when reiserfs_get_block is called for a hole @@ -505,490 +510,547 @@ out: ** you should not be in a transaction, or have any paths held when you ** call this. */ -static int convert_tail_for_hole(struct inode *inode, - struct buffer_head *bh_result, - loff_t tail_offset) { - unsigned long index ; - unsigned long tail_end ; - unsigned long tail_start ; - struct page * tail_page ; - struct page * hole_page = bh_result->b_page ; - int retval = 0 ; - - if ((tail_offset & (bh_result->b_size - 1)) != 1) - return -EIO ; - - /* always try to read until the end of the block */ - tail_start = tail_offset & (PAGE_CACHE_SIZE - 1) ; - tail_end = (tail_start | (bh_result->b_size - 1)) + 1 ; - - index = tail_offset >> PAGE_CACHE_SHIFT ; - /* hole_page can be zero in case of direct_io, we are sure - that we cannot get here if we write with O_DIRECT into - tail page */ - if (!hole_page || index != hole_page->index) { - tail_page = grab_cache_page(inode->i_mapping, index) ; - retval = -ENOMEM; - if (!tail_page) { - goto out ; - } - } else { - tail_page = hole_page ; - } - - /* we don't have to make sure the conversion did not happen while - ** we were locking the page because anyone that could convert - ** must first take i_sem. - ** - ** We must fix the tail page for writing because it might have buffers - ** that are mapped, but have a block number of 0. This indicates tail - ** data that has been read directly into the page, and block_prepare_write - ** won't trigger a get_block in this case. - */ - fix_tail_page_for_writing(tail_page) ; - retval = reiserfs_prepare_write(NULL, tail_page, tail_start, tail_end); - if (retval) - goto unlock ; - - /* tail conversion might change the data in the page */ - flush_dcache_page(tail_page) ; - - retval = reiserfs_commit_write(NULL, tail_page, tail_start, tail_end) ; - -unlock: - if (tail_page != hole_page) { - unlock_page(tail_page) ; - page_cache_release(tail_page) ; - } -out: - return retval ; +static int convert_tail_for_hole(struct inode *inode, + struct buffer_head *bh_result, + loff_t tail_offset) +{ + unsigned long index; + unsigned long tail_end; + unsigned long tail_start; + struct page *tail_page; + struct page *hole_page = bh_result->b_page; + int retval = 0; + + if ((tail_offset & (bh_result->b_size - 1)) != 1) + return -EIO; + + /* always try to read until the end of the block */ + tail_start = tail_offset & (PAGE_CACHE_SIZE - 1); + tail_end = (tail_start | (bh_result->b_size - 1)) + 1; + + index = tail_offset >> PAGE_CACHE_SHIFT; + /* hole_page can be zero in case of direct_io, we are sure + that we cannot get here if we write with O_DIRECT into + tail page */ + if (!hole_page || index != hole_page->index) { + tail_page = grab_cache_page(inode->i_mapping, index); + retval = -ENOMEM; + if (!tail_page) { + goto out; + } + } else { + tail_page = hole_page; + } + + /* we don't have to make sure the conversion did not happen while + ** we were locking the page because anyone that could convert + ** must first take i_sem. + ** + ** We must fix the tail page for writing because it might have buffers + ** that are mapped, but have a block number of 0. This indicates tail + ** data that has been read directly into the page, and block_prepare_write + ** won't trigger a get_block in this case. + */ + fix_tail_page_for_writing(tail_page); + retval = reiserfs_prepare_write(NULL, tail_page, tail_start, tail_end); + if (retval) + goto unlock; + + /* tail conversion might change the data in the page */ + flush_dcache_page(tail_page); + + retval = reiserfs_commit_write(NULL, tail_page, tail_start, tail_end); + + unlock: + if (tail_page != hole_page) { + unlock_page(tail_page); + page_cache_release(tail_page); + } + out: + return retval; } static inline int _allocate_block(struct reiserfs_transaction_handle *th, - long block, - struct inode *inode, - b_blocknr_t *allocated_block_nr, - struct path * path, - int flags) { - BUG_ON (!th->t_trans_id); - + long block, + struct inode *inode, + b_blocknr_t * allocated_block_nr, + struct path *path, int flags) +{ + BUG_ON(!th->t_trans_id); + #ifdef REISERFS_PREALLOCATE - if (!(flags & GET_BLOCK_NO_ISEM)) { - return reiserfs_new_unf_blocknrs2(th, inode, allocated_block_nr, path, block); - } + if (!(flags & GET_BLOCK_NO_ISEM)) { + return reiserfs_new_unf_blocknrs2(th, inode, allocated_block_nr, + path, block); + } #endif - return reiserfs_new_unf_blocknrs (th, inode, allocated_block_nr, path, block); + return reiserfs_new_unf_blocknrs(th, inode, allocated_block_nr, path, + block); } -int reiserfs_get_block (struct inode * inode, sector_t block, - struct buffer_head * bh_result, int create) +int reiserfs_get_block(struct inode *inode, sector_t block, + struct buffer_head *bh_result, int create) { - int repeat, retval = 0; - b_blocknr_t allocated_block_nr = 0;// b_blocknr_t is (unsigned) 32 bit int - INITIALIZE_PATH(path); - int pos_in_item; - struct cpu_key key; - struct buffer_head * bh, * unbh = NULL; - struct item_head * ih, tmp_ih; - __le32 * item; - int done; - int fs_gen; - struct reiserfs_transaction_handle *th = NULL; - /* space reserved in transaction batch: - . 3 balancings in direct->indirect conversion - . 1 block involved into reiserfs_update_sd() - XXX in practically impossible worst case direct2indirect() - can incur (much) more than 3 balancings. - quota update for user, group */ - int jbegin_count = JOURNAL_PER_BALANCE_CNT * 3 + 1 + 2 * REISERFS_QUOTA_TRANS_BLOCKS(inode->i_sb); - int version; - int dangle = 1; - loff_t new_offset = (((loff_t)block) << inode->i_sb->s_blocksize_bits) + 1 ; - - /* bad.... */ - reiserfs_write_lock(inode->i_sb); - version = get_inode_item_key_version (inode); - - if (block < 0) { - reiserfs_write_unlock(inode->i_sb); - return -EIO; - } + int repeat, retval = 0; + b_blocknr_t allocated_block_nr = 0; // b_blocknr_t is (unsigned) 32 bit int + INITIALIZE_PATH(path); + int pos_in_item; + struct cpu_key key; + struct buffer_head *bh, *unbh = NULL; + struct item_head *ih, tmp_ih; + __le32 *item; + int done; + int fs_gen; + struct reiserfs_transaction_handle *th = NULL; + /* space reserved in transaction batch: + . 3 balancings in direct->indirect conversion + . 1 block involved into reiserfs_update_sd() + XXX in practically impossible worst case direct2indirect() + can incur (much) more than 3 balancings. + quota update for user, group */ + int jbegin_count = + JOURNAL_PER_BALANCE_CNT * 3 + 1 + + 2 * REISERFS_QUOTA_TRANS_BLOCKS(inode->i_sb); + int version; + int dangle = 1; + loff_t new_offset = + (((loff_t) block) << inode->i_sb->s_blocksize_bits) + 1; + + /* bad.... */ + reiserfs_write_lock(inode->i_sb); + version = get_inode_item_key_version(inode); - if (!file_capable (inode, block)) { - reiserfs_write_unlock(inode->i_sb); - return -EFBIG; - } - - /* if !create, we aren't changing the FS, so we don't need to - ** log anything, so we don't need to start a transaction - */ - if (!(create & GET_BLOCK_CREATE)) { - int ret ; - /* find number of block-th logical block of the file */ - ret = _get_block_create_0 (inode, block, bh_result, - create | GET_BLOCK_READ_DIRECT) ; - reiserfs_write_unlock(inode->i_sb); - return ret; - } - /* - * if we're already in a transaction, make sure to close - * any new transactions we start in this func - */ - if ((create & GET_BLOCK_NO_DANGLE) || - reiserfs_transaction_running(inode->i_sb)) - dangle = 0; - - /* If file is of such a size, that it might have a tail and tails are enabled - ** we should mark it as possibly needing tail packing on close - */ - if ( (have_large_tails (inode->i_sb) && inode->i_size < i_block_size (inode)*4) || - (have_small_tails (inode->i_sb) && inode->i_size < i_block_size(inode)) ) - REISERFS_I(inode)->i_flags |= i_pack_on_close_mask ; - - /* set the key of the first byte in the 'block'-th block of file */ - make_cpu_key (&key, inode, new_offset, - TYPE_ANY, 3/*key length*/); - if ((new_offset + inode->i_sb->s_blocksize - 1) > inode->i_size) { -start_trans: - th = reiserfs_persistent_transaction(inode->i_sb, jbegin_count); - if (!th) { - retval = -ENOMEM; - goto failure; - } - reiserfs_update_inode_transaction(inode) ; - } - research: - - retval = search_for_position_by_key (inode->i_sb, &key, &path); - if (retval == IO_ERROR) { - retval = -EIO; - goto failure; - } - - bh = get_last_bh (&path); - ih = get_ih (&path); - item = get_item (&path); - pos_in_item = path.pos_in_item; - - fs_gen = get_generation (inode->i_sb); - copy_item_head (&tmp_ih, ih); - - if (allocation_needed (retval, allocated_block_nr, ih, item, pos_in_item)) { - /* we have to allocate block for the unformatted node */ - if (!th) { - pathrelse(&path) ; - goto start_trans; - } - - repeat = _allocate_block(th, block, inode, &allocated_block_nr, &path, create); - - if (repeat == NO_DISK_SPACE || repeat == QUOTA_EXCEEDED) { - /* restart the transaction to give the journal a chance to free - ** some blocks. releases the path, so we have to go back to - ** research if we succeed on the second try - */ - SB_JOURNAL(inode->i_sb)->j_next_async_flush = 1; - retval = restart_transaction(th, i |