X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=fs%2Fext4%2Finode.c;h=8fab233cb05fd6bdc8538c7ee4ad6990c2fded70;hb=233607dbbc823caf685e778cabc49fb7f679900b;hp=0e9055cf700e606f1aacb5432b8744a810242e11;hpb=060195500e0347a6ba8ea89739a9898961eb6f2b;p=linux-2.6 diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 0e9055cf70..8fab233cb0 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -382,7 +382,7 @@ no_block: * @inode: owner * @ind: descriptor of indirect block. * - * This function returns the prefered place for block allocation. + * This function returns the preferred place for block allocation. * It is used when heuristic for sequential allocation fails. * Rules are: * + if there is a block to the left of our position - allocate near it. @@ -403,6 +403,7 @@ static ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind) __le32 *start = ind->bh ? (__le32*) ind->bh->b_data : ei->i_data; __le32 *p; ext4_fsblk_t bg_start; + ext4_fsblk_t last_block; ext4_grpblk_t colour; /* Try to find previous block */ @@ -420,18 +421,23 @@ static ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind) * into the same cylinder group then. */ bg_start = ext4_group_first_block_no(inode->i_sb, ei->i_block_group); - colour = (current->pid % 16) * + last_block = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es) - 1; + + if (bg_start + EXT4_BLOCKS_PER_GROUP(inode->i_sb) <= last_block) + colour = (current->pid % 16) * (EXT4_BLOCKS_PER_GROUP(inode->i_sb) / 16); + else + colour = (current->pid % 16) * ((last_block - bg_start) / 16); return bg_start + colour; } /** - * ext4_find_goal - find a prefered place for allocation. + * ext4_find_goal - find a preferred place for allocation. * @inode: owner * @block: block we want * @partial: pointer to the last triple within a chain * - * Normally this function find the prefered place for block allocation, + * Normally this function find the preferred place for block allocation, * returns it. */ static ext4_fsblk_t ext4_find_goal(struct inode *inode, ext4_lblk_t block, @@ -768,7 +774,6 @@ err_out: * * `handle' can be NULL if create == 0. * - * The BKL may not be held on entry here. Be sure to take it early. * return > 0, # of blocks mapped or allocated. * return = 0, if plain lookup failed. * return < 0, error case. @@ -892,13 +897,49 @@ out: return err; } -#define DIO_CREDITS (EXT4_RESERVE_TRANS_BLOCKS + 32) +/* Maximum number of blocks we map for direct IO at once. */ +#define DIO_MAX_BLOCKS 4096 +/* + * Number of credits we need for writing DIO_MAX_BLOCKS: + * We need sb + group descriptor + bitmap + inode -> 4 + * For B blocks with A block pointers per block we need: + * 1 (triple ind.) + (B/A/A + 2) (doubly ind.) + (B/A + 2) (indirect). + * If we plug in 4096 for B and 256 for A (for 1KB block size), we get 25. + */ +#define DIO_CREDITS 25 + +/* + * + * + * ext4_ext4 get_block() wrapper function + * It will do a look up first, and returns if the blocks already mapped. + * Otherwise it takes the write lock of the i_data_sem and allocate blocks + * and store the allocated blocks in the result buffer head and mark it + * mapped. + * + * If file type is extents based, it will call ext4_ext_get_blocks(), + * Otherwise, call with ext4_get_blocks_handle() to handle indirect mapping + * based files + * + * On success, it returns the number of blocks being mapped or allocate. + * if create==0 and the blocks are pre-allocated and uninitialized block, + * the result buffer head is unmapped. If the create ==1, it will make sure + * the buffer head is mapped. + * + * It returns 0 if plain look up failed (blocks have not been allocated), in + * that casem, buffer head is unmapped + * + * It returns the error in case of allocation failure. + */ int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, unsigned long max_blocks, struct buffer_head *bh, int create, int extend_disksize) { int retval; + + clear_buffer_mapped(bh); + /* * Try to see if we can get the block without requesting * for new file system block. @@ -912,12 +953,26 @@ int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, inode, block, max_blocks, bh, 0, 0); } up_read((&EXT4_I(inode)->i_data_sem)); - if (!create || (retval > 0)) + + /* If it is only a block(s) look up */ + if (!create) return retval; /* - * We need to allocate new blocks which will result - * in i_data update + * Returns if the blocks have already allocated + * + * Note that if blocks have been preallocated + * ext4_ext_get_block() returns th create = 0 + * with buffer head unmapped. + */ + if (retval > 0 && buffer_mapped(bh)) + return retval; + + /* + * New blocks allocate and/or writing to uninitialized extent + * will possibly result in updating i_data, so we take + * the write lock of i_data_sem, and call get_blocks() + * with create == 1 flag. */ down_write((&EXT4_I(inode)->i_data_sem)); /* @@ -939,49 +994,31 @@ static int ext4_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { handle_t *handle = ext4_journal_current_handle(); - int ret = 0; + int ret = 0, started = 0; unsigned max_blocks = bh_result->b_size >> inode->i_blkbits; - if (!create) - goto get_block; /* A read */ - - if (max_blocks == 1) - goto get_block; /* A single block get */ - - if (handle->h_transaction->t_state == T_LOCKED) { - /* - * Huge direct-io writes can hold off commits for long - * periods of time. Let this commit run. - */ - ext4_journal_stop(handle); - handle = ext4_journal_start(inode, DIO_CREDITS); - if (IS_ERR(handle)) + if (create && !handle) { + /* Direct IO write... */ + if (max_blocks > DIO_MAX_BLOCKS) + max_blocks = DIO_MAX_BLOCKS; + handle = ext4_journal_start(inode, DIO_CREDITS + + 2 * EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb)); + if (IS_ERR(handle)) { ret = PTR_ERR(handle); - goto get_block; - } - - if (handle->h_buffer_credits <= EXT4_RESERVE_TRANS_BLOCKS) { - /* - * Getting low on buffer credits... - */ - ret = ext4_journal_extend(handle, DIO_CREDITS); - if (ret > 0) { - /* - * Couldn't extend the transaction. Start a new one. - */ - ret = ext4_journal_restart(handle, DIO_CREDITS); + goto out; } + started = 1; } -get_block: - if (ret == 0) { - ret = ext4_get_blocks_wrap(handle, inode, iblock, + ret = ext4_get_blocks_wrap(handle, inode, iblock, max_blocks, bh_result, create, 0); - if (ret > 0) { - bh_result->b_size = (ret << inode->i_blkbits); - ret = 0; - } + if (ret > 0) { + bh_result->b_size = (ret << inode->i_blkbits); + ret = 0; } + if (started) + ext4_journal_stop(handle); +out: return ret; } @@ -1671,7 +1708,8 @@ static int ext4_releasepage(struct page *page, gfp_t wait) * if the machine crashes during the write. * * If the O_DIRECT write is intantiating holes inside i_size and the machine - * crashes then stale disk data _may_ be exposed inside the file. + * crashes then stale disk data _may_ be exposed inside the file. But current + * VFS code falls back into buffered path in that case so we are safe. */ static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_t offset, @@ -1680,7 +1718,7 @@ static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb, struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; struct ext4_inode_info *ei = EXT4_I(inode); - handle_t *handle = NULL; + handle_t *handle; ssize_t ret; int orphan = 0; size_t count = iov_length(iov, nr_segs); @@ -1688,17 +1726,21 @@ static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb, if (rw == WRITE) { loff_t final_size = offset + count; - handle = ext4_journal_start(inode, DIO_CREDITS); - if (IS_ERR(handle)) { - ret = PTR_ERR(handle); - goto out; - } if (final_size > inode->i_size) { + /* Credits for sb + inode write */ + handle = ext4_journal_start(inode, 2); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto out; + } ret = ext4_orphan_add(handle, inode); - if (ret) - goto out_stop; + if (ret) { + ext4_journal_stop(handle); + goto out; + } orphan = 1; ei->i_disksize = inode->i_size; + ext4_journal_stop(handle); } } @@ -1706,18 +1748,21 @@ static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb, offset, nr_segs, ext4_get_block, NULL); - /* - * Reacquire the handle: ext4_get_block() can restart the transaction - */ - handle = ext4_journal_current_handle(); - -out_stop: - if (handle) { + if (orphan) { int err; - if (orphan && inode->i_nlink) + /* Credits for sb + inode write */ + handle = ext4_journal_start(inode, 2); + if (IS_ERR(handle)) { + /* This is really bad luck. We've written the data + * but cannot extend i_size. Bail out and pretend + * the write failed... */ + ret = PTR_ERR(handle); + goto out; + } + if (inode->i_nlink) ext4_orphan_del(handle, inode); - if (orphan && ret > 0) { + if (ret > 0) { loff_t end = offset + ret; if (end > inode->i_size) { ei->i_disksize = end; @@ -2680,21 +2725,31 @@ static blkcnt_t ext4_inode_blocks(struct ext4_inode *raw_inode, } } -void ext4_read_inode(struct inode * inode) +struct inode *ext4_iget(struct super_block *sb, unsigned long ino) { struct ext4_iloc iloc; struct ext4_inode *raw_inode; - struct ext4_inode_info *ei = EXT4_I(inode); + struct ext4_inode_info *ei; struct buffer_head *bh; + struct inode *inode; + long ret; int block; + inode = iget_locked(sb, ino); + if (!inode) + return ERR_PTR(-ENOMEM); + if (!(inode->i_state & I_NEW)) + return inode; + + ei = EXT4_I(inode); #ifdef CONFIG_EXT4DEV_FS_POSIX_ACL ei->i_acl = EXT4_ACL_NOT_CACHED; ei->i_default_acl = EXT4_ACL_NOT_CACHED; #endif ei->i_block_alloc_info = NULL; - if (__ext4_get_inode_loc(inode, &iloc, 0)) + ret = __ext4_get_inode_loc(inode, &iloc, 0); + if (ret < 0) goto bad_inode; bh = iloc.bh; raw_inode = ext4_raw_inode(&iloc); @@ -2720,6 +2775,7 @@ void ext4_read_inode(struct inode * inode) !(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) { /* this inode is deleted */ brelse (bh); + ret = -ESTALE; goto bad_inode; } /* The only unlinked inodes we let through here have @@ -2747,17 +2803,12 @@ void ext4_read_inode(struct inode * inode) ei->i_data[block] = raw_inode->i_block[block]; INIT_LIST_HEAD(&ei->i_orphan); - if (inode->i_ino >= EXT4_FIRST_INO(inode->i_sb) + 1 && - EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) { - /* - * When mke2fs creates big inodes it does not zero out - * the unused bytes above EXT4_GOOD_OLD_INODE_SIZE, - * so ignore those first few inodes. - */ + if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) { ei->i_extra_isize = le16_to_cpu(raw_inode->i_extra_isize); if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize > EXT4_INODE_SIZE(inode->i_sb)) { brelse (bh); + ret = -EIO; goto bad_inode; } if (ei->i_extra_isize == 0) { @@ -2811,11 +2862,12 @@ void ext4_read_inode(struct inode * inode) } brelse (iloc.bh); ext4_set_inode_flags(inode); - return; + unlock_new_inode(inode); + return inode; bad_inode: - make_bad_inode(inode); - return; + iget_failed(inode); + return ERR_PTR(ret); } static int ext4_inode_blocks_set(handle_t *handle,