X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=fs%2Fext3%2Finode.c;h=455e6e6e5cb993912ab0ddae5dd1b6e16d60a7fa;hb=dbfc196a3cc1a2514ad0737a82f764de23bd65e6;hp=48ae0339af175a1df095f6de4fa04f21a5af2c7f;hpb=f91a2ad2ed97099fb565e3336f8df0df717f2ba9;p=safe%2Fjmp%2Flinux-2.6 diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 48ae033..455e6e6 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -13,11 +13,11 @@ * Copyright (C) 1991, 1992 Linus Torvalds * * Goal-directed block allocation by Stephen Tweedie - * (sct@redhat.com), 1993, 1998 + * (sct@redhat.com), 1993, 1998 * Big-endian to little-endian byte-swapping/bitmaps by * David S. Miller (davem@caip.rutgers.edu), 1995 * 64-bit file support on 64-bit platforms by Jakub Jelinek - * (jj@sunsite.ms.mff.cuni.cz) + * (jj@sunsite.ms.mff.cuni.cz) * * Assorted race fixes, rewrite of ext3_get_block() by Al Viro, 2000 */ @@ -27,7 +27,6 @@ #include #include #include -#include #include #include #include @@ -36,6 +35,9 @@ #include #include #include +#include +#include +#include #include "xattr.h" #include "acl.h" @@ -55,14 +57,14 @@ static int ext3_inode_is_fast_symlink(struct inode *inode) /* * The ext3 forget function must perform a revoke if we are freeing data * which has been journaled. Metadata (eg. indirect blocks) must be - * revoked in all cases. + * revoked in all cases. * * "bh" may be NULL: a metadata block may have been freed from memory * but there may still be a record of it in the journal, and that record * still needs to be revoked. */ int ext3_forget(handle_t *handle, int is_metadata, struct inode *inode, - struct buffer_head *bh, int blocknr) + struct buffer_head *bh, ext3_fsblk_t blocknr) { int err; @@ -95,7 +97,7 @@ int ext3_forget(handle_t *handle, int is_metadata, struct inode *inode, BUFFER_TRACE(bh, "call ext3_journal_revoke"); err = ext3_journal_revoke(handle, blocknr, bh); if (err) - ext3_abort(inode->i_sb, __FUNCTION__, + ext3_abort(inode->i_sb, __func__, "error %d when attempting revoke", err); BUFFER_TRACE(bh, "exit"); return err; @@ -105,7 +107,7 @@ int ext3_forget(handle_t *handle, int is_metadata, struct inode *inode, * Work out how many blocks we need to proceed with the next chunk of a * truncate transaction. */ -static unsigned long blocks_for_truncate(struct inode *inode) +static unsigned long blocks_for_truncate(struct inode *inode) { unsigned long needed; @@ -122,13 +124,13 @@ static unsigned long blocks_for_truncate(struct inode *inode) /* But we need to bound the transaction so we don't overflow the * journal. */ - if (needed > EXT3_MAX_TRANS_DATA) + if (needed > EXT3_MAX_TRANS_DATA) needed = EXT3_MAX_TRANS_DATA; return EXT3_DATA_TRANS_BLOCKS(inode->i_sb) + needed; } -/* +/* * Truncate transactions can be complex and absolutely huge. So we need to * be able to restart the transaction at a conventient checkpoint to make * sure we don't overflow the journal. @@ -136,9 +138,9 @@ static unsigned long blocks_for_truncate(struct inode *inode) * start_transaction gets us a new handle for a truncate transaction, * and extend_transaction tries to extend the existing one a bit. If * extend fails, we need to propagate the failure up and restart the - * transaction in the top-level truncate loop. --sct + * transaction in the top-level truncate loop. --sct */ -static handle_t *start_transaction(struct inode *inode) +static handle_t *start_transaction(struct inode *inode) { handle_t *result; @@ -170,10 +172,21 @@ static int try_to_extend_transaction(handle_t *handle, struct inode *inode) * so before we call here everything must be consistently dirtied against * this transaction. */ -static int ext3_journal_test_restart(handle_t *handle, struct inode *inode) +static int truncate_restart_transaction(handle_t *handle, struct inode *inode) { + int ret; + jbd_debug(2, "restarting handle %p\n", handle); - return ext3_journal_restart(handle, blocks_for_truncate(inode)); + /* + * Drop truncate_mutex to avoid deadlock with ext3_get_blocks_handle + * At this moment, get_block can be called only for blocks inside + * i_size since page cache has been already dropped and writes are + * blocked by i_mutex. So we can safely drop the truncate_mutex. + */ + mutex_unlock(&EXT3_I(inode)->truncate_mutex); + ret = ext3_journal_restart(handle, blocks_for_truncate(inode)); + mutex_lock(&EXT3_I(inode)->truncate_mutex); + return ret; } /* @@ -215,12 +228,12 @@ void ext3_delete_inode (struct inode * inode) ext3_orphan_del(handle, inode); EXT3_I(inode)->i_dtime = get_seconds(); - /* + /* * One subtle ordering requirement: if anything has gone wrong * (transaction abort, IO errors, whatever), then we can still * do these next steps (the fs will already have been marked as * having errors), but we can't free the inode if the mark_dirty - * fails. + * fails. */ if (ext3_mark_inode_dirty(handle, inode)) /* If that failed, just do the required in-core inode clear. */ @@ -392,13 +405,13 @@ 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. * + if pointer will live in indirect block - allocate near that block. * + if pointer will live in inode - allocate in the same - * cylinder group. + * cylinder group. * * In the latter case we colour the starting block by the callers PID to * prevent it from clashing with concurrent allocations for a different inode @@ -407,13 +420,13 @@ no_block: * * Caller must make sure that @ind is valid and will stay that way. */ -static unsigned long ext3_find_near(struct inode *inode, Indirect *ind) +static ext3_fsblk_t ext3_find_near(struct inode *inode, Indirect *ind) { struct ext3_inode_info *ei = EXT3_I(inode); __le32 *start = ind->bh ? (__le32*) ind->bh->b_data : ei->i_data; __le32 *p; - unsigned long bg_start; - unsigned long colour; + ext3_fsblk_t bg_start; + ext3_grpblk_t colour; /* Try to find previous block */ for (p = ind->p - 1; p >= start; p--) { @@ -429,27 +442,24 @@ static unsigned long ext3_find_near(struct inode *inode, Indirect *ind) * It is going to be referred to from the inode itself? OK, just put it * into the same cylinder group then. */ - bg_start = (ei->i_block_group * EXT3_BLOCKS_PER_GROUP(inode->i_sb)) + - le32_to_cpu(EXT3_SB(inode->i_sb)->s_es->s_first_data_block); + bg_start = ext3_group_first_block_no(inode->i_sb, ei->i_block_group); colour = (current->pid % 16) * (EXT3_BLOCKS_PER_GROUP(inode->i_sb) / 16); return bg_start + colour; } /** - * ext3_find_goal - find a prefered place for allocation. + * ext3_find_goal - find a preferred place for allocation. * @inode: owner * @block: block we want - * @chain: chain of indirect blocks * @partial: pointer to the last triple within a chain - * @goal: place to store the result. * - * Normally this function find the prefered place for block allocation, - * stores it in *@goal and returns zero. + * Normally this function find the preferred place for block allocation, + * returns it. */ -static unsigned long ext3_find_goal(struct inode *inode, long block, - Indirect chain[4], Indirect *partial) +static ext3_fsblk_t ext3_find_goal(struct inode *inode, long block, + Indirect *partial) { struct ext3_block_alloc_info *block_i; @@ -471,7 +481,7 @@ static unsigned long ext3_find_goal(struct inode *inode, long block, * ext3_blks_to_allocate: Look up the block map and count the number * of direct blocks need to be allocated for the given branch. * - * @branch: chain of indirect blocks + * @branch: chain of indirect blocks * @k: number of blocks need for indirect blocks * @blks: number of data blocks to be mapped. * @blocks_to_boundary: the offset in the indirect block @@ -516,13 +526,13 @@ static int ext3_blks_to_allocate(Indirect *branch, int k, unsigned long blks, * direct blocks */ static int ext3_alloc_blocks(handle_t *handle, struct inode *inode, - unsigned long goal, int indirect_blks, int blks, - unsigned long long new_blocks[4], int *err) + ext3_fsblk_t goal, int indirect_blks, int blks, + ext3_fsblk_t new_blocks[4], int *err) { int target, i; unsigned long count = 0; int index = 0; - unsigned long current_block = 0; + ext3_fsblk_t current_block = 0; int ret = 0; /* @@ -592,7 +602,7 @@ failed_out: * as described above and return 0. */ static int ext3_alloc_branch(handle_t *handle, struct inode *inode, - int indirect_blks, int *blks, unsigned long goal, + int indirect_blks, int *blks, ext3_fsblk_t goal, int *offsets, Indirect *branch) { int blocksize = inode->i_sb->s_blocksize; @@ -600,8 +610,8 @@ static int ext3_alloc_branch(handle_t *handle, struct inode *inode, int err = 0; struct buffer_head *bh; int num; - unsigned long long new_blocks[4]; - unsigned long long current_block; + ext3_fsblk_t new_blocks[4]; + ext3_fsblk_t current_block; num = ext3_alloc_blocks(handle, inode, goal, indirect_blks, *blks, new_blocks, &err); @@ -688,9 +698,10 @@ static int ext3_splice_branch(handle_t *handle, struct inode *inode, int i; int err = 0; struct ext3_block_alloc_info *block_i; - unsigned long current_block; + ext3_fsblk_t current_block; + struct ext3_inode_info *ei = EXT3_I(inode); - block_i = EXT3_I(inode)->i_block_alloc_info; + block_i = ei->i_block_alloc_info; /* * If we're splicing into a [td]indirect block (as opposed to the * inode) then we need to get write access to the [td]indirect block @@ -711,7 +722,7 @@ static int ext3_splice_branch(handle_t *handle, struct inode *inode, * direct blocks blocks */ if (num == 0 && blks > 1) { - current_block = le32_to_cpu(where->key + 1); + current_block = le32_to_cpu(where->key) + 1; for (i = 1; i < blks; i++) *(where->p + i ) = cpu_to_le32(current_block++); } @@ -724,13 +735,15 @@ static int ext3_splice_branch(handle_t *handle, struct inode *inode, if (block_i) { block_i->last_alloc_logical_block = block + blks - 1; block_i->last_alloc_physical_block = - le32_to_cpu(where[num].key + blks - 1); + le32_to_cpu(where[num].key) + blks - 1; } /* We are done with atomic stuff, now do the rest of housekeeping */ inode->i_ctime = CURRENT_TIME_SEC; ext3_mark_inode_dirty(handle, inode); + /* ext3_mark_inode_dirty already updated i_sync_tid */ + atomic_set(&ei->i_datasync_tid, handle->h_transaction->t_tid); /* had we spliced it onto indirect block? */ if (where->bh) { @@ -745,7 +758,7 @@ static int ext3_splice_branch(handle_t *handle, struct inode *inode, jbd_debug(5, "splicing indirect only\n"); BUFFER_TRACE(where->bh, "call ext3_journal_dirty_metadata"); err = ext3_journal_dirty_metadata(handle, where->bh); - if (err) + if (err) goto err_out; } else { /* @@ -789,19 +802,19 @@ err_out: int ext3_get_blocks_handle(handle_t *handle, struct inode *inode, sector_t iblock, unsigned long maxblocks, struct buffer_head *bh_result, - int create, int extend_disksize) + int create) { int err = -EIO; int offsets[4]; Indirect chain[4]; Indirect *partial; - unsigned long goal; + ext3_fsblk_t goal; int indirect_blks; int blocks_to_boundary = 0; int depth; struct ext3_inode_info *ei = EXT3_I(inode); int count = 0; - unsigned long first_block = 0; + ext3_fsblk_t first_block = 0; J_ASSERT(handle != NULL || create == 0); @@ -814,12 +827,14 @@ int ext3_get_blocks_handle(handle_t *handle, struct inode *inode, /* Simplest case - block found, no allocation needed */ if (!partial) { - first_block = chain[depth - 1].key; + first_block = le32_to_cpu(chain[depth - 1].key); clear_buffer_new(bh_result); count++; /*map more blocks*/ while (count < maxblocks && count <= blocks_to_boundary) { - if (!verify_chain(chain, partial)) { + ext3_fsblk_t blk; + + if (!verify_chain(chain, chain + depth - 1)) { /* * Indirect block might be removed by * truncate while we were reading it. @@ -831,8 +846,9 @@ int ext3_get_blocks_handle(handle_t *handle, struct inode *inode, count = 0; break; } - if (le32_to_cpu(*(chain[depth-1].p+count) == - (first_block + count))) + blk = le32_to_cpu(*(chain[depth-1].p + count)); + + if (blk == first_block + count) count++; else break; @@ -882,7 +898,7 @@ int ext3_get_blocks_handle(handle_t *handle, struct inode *inode, if (S_ISREG(inode->i_mode) && (!ei->i_block_alloc_info)) ext3_init_block_alloc_info(inode); - goal = ext3_find_goal(inode, iblock, chain, partial); + goal = ext3_find_goal(inode, iblock, partial); /* the number of blocks need to allocate for [d,t]indirect blocks */ indirect_blks = (chain + depth) - partial - 1; @@ -909,13 +925,6 @@ int ext3_get_blocks_handle(handle_t *handle, struct inode *inode, if (!err) err = ext3_splice_branch(handle, inode, iblock, partial, indirect_blks, count); - /* - * i_disksize growing is protected by truncate_mutex. Don't forget to - * protect it if you're about to implement concurrent - * ext3_get_block() -bzzz - */ - if (!err && extend_disksize && inode->i_size > ei->i_disksize) - ei->i_disksize = inode->i_size; mutex_unlock(&ei->truncate_mutex); if (err) goto cleanup; @@ -923,7 +932,7 @@ int ext3_get_blocks_handle(handle_t *handle, struct inode *inode, set_buffer_new(bh_result); got_it: map_bh(bh_result, inode->i_sb, le32_to_cpu(chain[depth-1].key)); - if (blocks_to_boundary == 0) + if (count > blocks_to_boundary) set_buffer_boundary(bh_result); err = count; /* Clean up and exit */ @@ -939,58 +948,55 @@ out: return err; } -#define DIO_CREDITS (EXT3_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 static int ext3_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { - handle_t *handle = journal_current_handle(); - int ret = 0; + handle_t *handle = ext3_journal_current_handle(); + 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. - */ - ext3_journal_stop(handle); - handle = ext3_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 = ext3_journal_start(inode, DIO_CREDITS + + EXT3_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb)); + if (IS_ERR(handle)) { ret = PTR_ERR(handle); - goto get_block; - } - - if (handle->h_buffer_credits <= EXT3_RESERVE_TRANS_BLOCKS) { - /* - * Getting low on buffer credits... - */ - ret = ext3_journal_extend(handle, DIO_CREDITS); - if (ret > 0) { - /* - * Couldn't extend the transaction. Start a new one. - */ - ret = ext3_journal_restart(handle, DIO_CREDITS); + goto out; } + started = 1; } -get_block: - if (ret == 0) { - ret = ext3_get_blocks_handle(handle, inode, iblock, - max_blocks, bh_result, create, 0); - if (ret > 0) { - bh_result->b_size = (ret << inode->i_blkbits); - ret = 0; - } + ret = ext3_get_blocks_handle(handle, inode, iblock, + max_blocks, bh_result, create); + if (ret > 0) { + bh_result->b_size = (ret << inode->i_blkbits); + ret = 0; } + if (started) + ext3_journal_stop(handle); +out: return ret; } +int ext3_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, + u64 start, u64 len) +{ + return generic_block_fiemap(inode, fieinfo, start, len, + ext3_get_block); +} + /* * `handle' can be NULL if create is zero */ @@ -1006,12 +1012,15 @@ struct buffer_head *ext3_getblk(handle_t *handle, struct inode *inode, dummy.b_blocknr = -1000; buffer_trace_init(&dummy.b_history); err = ext3_get_blocks_handle(handle, inode, block, 1, - &dummy, create, 1); - if (err == 1) { + &dummy, create); + /* + * ext3_get_blocks_handle() returns number of blocks + * mapped. 0 in case of a HOLE. + */ + if (err > 0) { + if (err > 1) + WARN_ON(1); err = 0; - } else if (err >= 0) { - WARN_ON(1); - err = -EIO; } *errp = err; if (!err && buffer_mapped(&dummy)) { @@ -1023,7 +1032,7 @@ struct buffer_head *ext3_getblk(handle_t *handle, struct inode *inode, } if (buffer_new(&dummy)) { J_ASSERT(create != 0); - J_ASSERT(handle != 0); + J_ASSERT(handle != NULL); /* * Now that we do not always journal data, we should @@ -1068,7 +1077,7 @@ struct buffer_head *ext3_bread(handle_t *handle, struct inode *inode, return bh; if (buffer_uptodate(bh)) return bh; - ll_rw_block(READ, 1, &bh); + ll_rw_block(READ_META, 1, &bh); wait_on_buffer(bh); if (buffer_uptodate(bh)) return bh; @@ -1093,7 +1102,7 @@ static int walk_page_buffers( handle_t *handle, for ( bh = head, block_start = 0; ret == 0 && (bh != head || !block_start); - block_start = block_end, bh = next) + block_start = block_end, bh = next) { next = bh->b_this_page; block_end = block_start + blocksize; @@ -1132,7 +1141,7 @@ static int walk_page_buffers( handle_t *handle, * So what we do is to rely on the fact that journal_stop/journal_start * will _not_ run commit under these circumstances because handle->h_ref * is elevated. We'll still have enough credits for the tiny quotafile - * write. + * write. */ static int do_journal_get_write_access(handle_t *handle, struct buffer_head *bh) @@ -1142,51 +1151,106 @@ static int do_journal_get_write_access(handle_t *handle, return ext3_journal_get_write_access(handle, bh); } -static int ext3_prepare_write(struct file *file, struct page *page, - unsigned from, unsigned to) +/* + * Truncate blocks that were not used by write. We have to truncate the + * pagecache as well so that corresponding buffers get properly unmapped. + */ +static void ext3_truncate_failed_write(struct inode *inode) +{ + truncate_inode_pages(inode->i_mapping, inode->i_size); + ext3_truncate(inode); +} + +static int ext3_write_begin(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned flags, + struct page **pagep, void **fsdata) { - struct inode *inode = page->mapping->host; - int ret, needed_blocks = ext3_writepage_trans_blocks(inode); + struct inode *inode = mapping->host; + int ret; handle_t *handle; int retries = 0; + struct page *page; + pgoff_t index; + unsigned from, to; + /* Reserve one block more for addition to orphan list in case + * we allocate blocks but write fails for some reason */ + int needed_blocks = ext3_writepage_trans_blocks(inode) + 1; + + index = pos >> PAGE_CACHE_SHIFT; + from = pos & (PAGE_CACHE_SIZE - 1); + to = from + len; retry: + page = grab_cache_page_write_begin(mapping, index, flags); + if (!page) + return -ENOMEM; + *pagep = page; + handle = ext3_journal_start(inode, needed_blocks); if (IS_ERR(handle)) { + unlock_page(page); + page_cache_release(page); ret = PTR_ERR(handle); goto out; } - if (test_opt(inode->i_sb, NOBH)) - ret = nobh_prepare_write(page, from, to, ext3_get_block); - else - ret = block_prepare_write(page, from, to, ext3_get_block); + ret = block_write_begin(file, mapping, pos, len, flags, pagep, fsdata, + ext3_get_block); if (ret) - goto prepare_write_failed; + goto write_begin_failed; if (ext3_should_journal_data(inode)) { ret = walk_page_buffers(handle, page_buffers(page), from, to, NULL, do_journal_get_write_access); } -prepare_write_failed: - if (ret) +write_begin_failed: + if (ret) { + /* + * block_write_begin may have instantiated a few blocks + * outside i_size. Trim these off again. Don't need + * i_size_read because we hold i_mutex. + * + * Add inode to orphan list in case we crash before truncate + * finishes. Do this only if ext3_can_truncate() agrees so + * that orphan processing code is happy. + */ + if (pos + len > inode->i_size && ext3_can_truncate(inode)) + ext3_orphan_add(handle, inode); ext3_journal_stop(handle); + unlock_page(page); + page_cache_release(page); + if (pos + len > inode->i_size) + ext3_truncate_failed_write(inode); + } if (ret == -ENOSPC && ext3_should_retry_alloc(inode->i_sb, &retries)) goto retry; out: return ret; } + int ext3_journal_dirty_data(handle_t *handle, struct buffer_head *bh) { int err = journal_dirty_data(handle, bh); if (err) - ext3_journal_abort_handle(__FUNCTION__, __FUNCTION__, - bh, handle,err); + ext3_journal_abort_handle(__func__, __func__, + bh, handle, err); return err; } -/* For commit_write() in data=journal mode */ -static int commit_write_fn(handle_t *handle, struct buffer_head *bh) +/* For ordered writepage and write_end functions */ +static int journal_dirty_data_fn(handle_t *handle, struct buffer_head *bh) +{ + /* + * Write could have mapped the buffer but it didn't copy the data in + * yet. So avoid filing such buffer into a transaction. + */ + if (buffer_mapped(bh) && buffer_uptodate(bh)) + return ext3_journal_dirty_data(handle, bh); + return 0; +} + +/* For write_end() in data=journal mode */ +static int write_end_fn(handle_t *handle, struct buffer_head *bh) { if (!buffer_mapped(bh) || buffer_freed(bh)) return 0; @@ -1195,98 +1259,145 @@ static int commit_write_fn(handle_t *handle, struct buffer_head *bh) } /* + * This is nasty and subtle: ext3_write_begin() could have allocated blocks + * for the whole page but later we failed to copy the data in. Update inode + * size according to what we managed to copy. The rest is going to be + * truncated in write_end function. + */ +static void update_file_sizes(struct inode *inode, loff_t pos, unsigned copied) +{ + /* What matters to us is i_disksize. We don't write i_size anywhere */ + if (pos + copied > inode->i_size) + i_size_write(inode, pos + copied); + if (pos + copied > EXT3_I(inode)->i_disksize) { + EXT3_I(inode)->i_disksize = pos + copied; + mark_inode_dirty(inode); + } +} + +/* * We need to pick up the new inode size which generic_commit_write gave us * `file' can be NULL - eg, when called from page_symlink(). * * ext3 never places buffers on inode->i_mapping->private_list. metadata * buffers are managed internally. */ -static int ext3_ordered_commit_write(struct file *file, struct page *page, - unsigned from, unsigned to) +static int ext3_ordered_write_end(struct file *file, + struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata) { handle_t *handle = ext3_journal_current_handle(); - struct inode *inode = page->mapping->host; + struct inode *inode = file->f_mapping->host; + unsigned from, to; int ret = 0, ret2; - ret = walk_page_buffers(handle, page_buffers(page), - from, to, NULL, ext3_journal_dirty_data); + copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); - if (ret == 0) { - /* - * generic_commit_write() will run mark_inode_dirty() if i_size - * changes. So let's piggyback the i_disksize mark_inode_dirty - * into that. - */ - loff_t new_i_size; + from = pos & (PAGE_CACHE_SIZE - 1); + to = from + copied; + ret = walk_page_buffers(handle, page_buffers(page), + from, to, NULL, journal_dirty_data_fn); - new_i_size = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to; - if (new_i_size > EXT3_I(inode)->i_disksize) - EXT3_I(inode)->i_disksize = new_i_size; - ret = generic_commit_write(file, page, from, to); - } + if (ret == 0) + update_file_sizes(inode, pos, copied); + /* + * There may be allocated blocks outside of i_size because + * we failed to copy some data. Prepare for truncate. + */ + if (pos + len > inode->i_size && ext3_can_truncate(inode)) + ext3_orphan_add(handle, inode); ret2 = ext3_journal_stop(handle); if (!ret) ret = ret2; - return ret; + unlock_page(page); + page_cache_release(page); + + if (pos + len > inode->i_size) + ext3_truncate_failed_write(inode); + return ret ? ret : copied; } -static int ext3_writeback_commit_write(struct file *file, struct page *page, - unsigned from, unsigned to) +static int ext3_writeback_write_end(struct file *file, + struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata) { handle_t *handle = ext3_journal_current_handle(); - struct inode *inode = page->mapping->host; - int ret = 0, ret2; - loff_t new_i_size; - - new_i_size = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to; - if (new_i_size > EXT3_I(inode)->i_disksize) - EXT3_I(inode)->i_disksize = new_i_size; + struct inode *inode = file->f_mapping->host; + int ret; - if (test_opt(inode->i_sb, NOBH)) - ret = nobh_commit_write(file, page, from, to); - else - ret = generic_commit_write(file, page, from, to); + copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); + update_file_sizes(inode, pos, copied); + /* + * There may be allocated blocks outside of i_size because + * we failed to copy some data. Prepare for truncate. + */ + if (pos + len > inode->i_size && ext3_can_truncate(inode)) + ext3_orphan_add(handle, inode); + ret = ext3_journal_stop(handle); + unlock_page(page); + page_cache_release(page); - ret2 = ext3_journal_stop(handle); - if (!ret) - ret = ret2; - return ret; + if (pos + len > inode->i_size) + ext3_truncate_failed_write(inode); + return ret ? ret : copied; } -static int ext3_journalled_commit_write(struct file *file, - struct page *page, unsigned from, unsigned to) +static int ext3_journalled_write_end(struct file *file, + struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata) { handle_t *handle = ext3_journal_current_handle(); - struct inode *inode = page->mapping->host; + struct inode *inode = mapping->host; int ret = 0, ret2; int partial = 0; - loff_t pos; + unsigned from, to; - /* - * Here we duplicate the generic_commit_write() functionality - */ - pos = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to; + from = pos & (PAGE_CACHE_SIZE - 1); + to = from + len; + + if (copied < len) { + if (!PageUptodate(page)) + copied = 0; + page_zero_new_buffers(page, from + copied, to); + to = from + copied; + } ret = walk_page_buffers(handle, page_buffers(page), from, - to, &partial, commit_write_fn); + to, &partial, write_end_fn); if (!partial) SetPageUptodate(page); - if (pos > inode->i_size) - i_size_write(inode, pos); + + if (pos + copied > inode->i_size) + i_size_write(inode, pos + copied); + /* + * There may be allocated blocks outside of i_size because + * we failed to copy some data. Prepare for truncate. + */ + if (pos + len > inode->i_size && ext3_can_truncate(inode)) + ext3_orphan_add(handle, inode); EXT3_I(inode)->i_state |= EXT3_STATE_JDATA; if (inode->i_size > EXT3_I(inode)->i_disksize) { EXT3_I(inode)->i_disksize = inode->i_size; ret2 = ext3_mark_inode_dirty(handle, inode); - if (!ret) + if (!ret) ret = ret2; } + ret2 = ext3_journal_stop(handle); if (!ret) ret = ret2; - return ret; + unlock_page(page); + page_cache_release(page); + + if (pos + len > inode->i_size) + ext3_truncate_failed_write(inode); + return ret ? ret : copied; } -/* +/* * bmap() is special. It gets used by applications such as lilo and by * the swapper to find the on-disk block of a specific piece of data. * @@ -1295,10 +1406,10 @@ static int ext3_journalled_commit_write(struct file *file, * filesystem and enables swap, then they may get a nasty shock when the * data getting swapped to that swapfile suddenly gets overwritten by * the original zero's written out previously to the journal and - * awaiting writeback in the kernel's buffer cache. + * awaiting writeback in the kernel's buffer cache. * * So, if we see any bmap calls here on a modified, data-journaled file, - * take extra steps to flush any blocks which might be in the cache. + * take extra steps to flush any blocks which might be in the cache. */ static sector_t ext3_bmap(struct address_space *mapping, sector_t block) { @@ -1307,16 +1418,16 @@ static sector_t ext3_bmap(struct address_space *mapping, sector_t block) int err; if (EXT3_I(inode)->i_state & EXT3_STATE_JDATA) { - /* + /* * This is a REALLY heavyweight approach, but the use of * bmap on dirty files is expected to be extremely rare: * only if we run lilo or swapon on a freshly made file - * do we expect this to happen. + * do we expect this to happen. * * (bmap requires CAP_SYS_RAWIO so this does not * represent an unprivileged user DOS attack --- we'd be * in trouble if mortal users could trigger this path at - * will.) + * will.) * * NB. EXT3_STATE_JDATA is not set on files other than * regular files. If somebody wants to bmap a directory @@ -1350,11 +1461,9 @@ static int bput_one(handle_t *handle, struct buffer_head *bh) return 0; } -static int journal_dirty_data_fn(handle_t *handle, struct buffer_head *bh) +static int buffer_unmapped(handle_t *handle, struct buffer_head *bh) { - if (buffer_mapped(bh)) - return ext3_journal_dirty_data(handle, bh); - return 0; + return !buffer_mapped(bh); } /* @@ -1427,6 +1536,19 @@ static int ext3_ordered_writepage(struct page *page, if (ext3_journal_current_handle()) goto out_fail; + if (!page_has_buffers(page)) { + create_empty_buffers(page, inode->i_sb->s_blocksize, + (1 << BH_Dirty)|(1 << BH_Uptodate)); + page_bufs = page_buffers(page); + } else { + page_bufs = page_buffers(page); + if (!walk_page_buffers(NULL, page_bufs, 0, PAGE_CACHE_SIZE, + NULL, buffer_unmapped)) { + /* Provide NULL get_block() to catch bugs if buffers + * weren't really mapped */ + return block_write_full_page(page, NULL, wbc); + } + } handle = ext3_journal_start(inode, ext3_writepage_trans_blocks(inode)); if (IS_ERR(handle)) { @@ -1434,11 +1556,6 @@ static int ext3_ordered_writepage(struct page *page, goto out_fail; } - if (!page_has_buffers(page)) { - create_empty_buffers(page, inode->i_sb->s_blocksize, - (1 << BH_Dirty)|(1 << BH_Uptodate)); - } - page_bufs = page_buffers(page); walk_page_buffers(handle, page_bufs, 0, PAGE_CACHE_SIZE, NULL, bget_one); @@ -1452,7 +1569,7 @@ static int ext3_ordered_writepage(struct page *page, */ /* - * And attach them to the current transaction. But only if + * And attach them to the current transaction. But only if * block_write_full_page() succeeded. Otherwise they are unmapped, * and generally junk. */ @@ -1486,13 +1603,22 @@ static int ext3_writeback_writepage(struct page *page, if (ext3_journal_current_handle()) goto out_fail; + if (page_has_buffers(page)) { + if (!walk_page_buffers(NULL, page_buffers(page), 0, + PAGE_CACHE_SIZE, NULL, buffer_unmapped)) { + /* Provide NULL get_block() to catch bugs if buffers + * weren't really mapped */ + return block_write_full_page(page, NULL, wbc); + } + } + handle = ext3_journal_start(inode, ext3_writepage_trans_blocks(inode)); if (IS_ERR(handle)) { ret = PTR_ERR(handle); goto out_fail; } - if (test_opt(inode->i_sb, NOBH)) + if (test_opt(inode->i_sb, NOBH) && ext3_should_writeback_data(inode)) ret = nobh_writepage(page, ext3_get_block, wbc); else ret = block_write_full_page(page, ext3_get_block, wbc); @@ -1541,7 +1667,7 @@ static int ext3_journalled_writepage(struct page *page, PAGE_CACHE_SIZE, NULL, do_journal_get_write_access); err = walk_page_buffers(handle, page_buffers(page), 0, - PAGE_CACHE_SIZE, NULL, commit_write_fn); + PAGE_CACHE_SIZE, NULL, write_end_fn); if (ret == 0) ret = err; EXT3_I(inode)->i_state |= EXT3_STATE_JDATA; @@ -1608,7 +1734,8 @@ static int ext3_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 ext3_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_t offset, @@ -1617,44 +1744,55 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb, struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; struct ext3_inode_info *ei = EXT3_I(inode); - handle_t *handle = NULL; + handle_t *handle; ssize_t ret; int orphan = 0; size_t count = iov_length(iov, nr_segs); + int retries = 0; if (rw == WRITE) { loff_t final_size = offset + count; - handle = ext3_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 = ext3_journal_start(inode, 2); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto out; + } ret = ext3_orphan_add(handle, inode); - if (ret) - goto out_stop; + if (ret) { + ext3_journal_stop(handle); + goto out; + } orphan = 1; ei->i_disksize = inode->i_size; + ext3_journal_stop(handle); } } - ret = blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov, +retry: + ret = blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov, offset, nr_segs, ext3_get_block, NULL); + if (ret == -ENOSPC && ext3_should_retry_alloc(inode->i_sb, &retries)) + goto retry; - /* - * Reacquire the handle: ext3_get_block() can restart the transaction - */ - handle = journal_current_handle(); - -out_stop: - if (handle) { + if (orphan) { int err; - if (orphan && inode->i_nlink) + /* Credits for sb + inode write */ + handle = ext3_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) ext3_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; @@ -1696,45 +1834,51 @@ static int ext3_journalled_set_page_dirty(struct page *page) return __set_page_dirty_nobuffers(page); } -static struct address_space_operations ext3_ordered_aops = { - .readpage = ext3_readpage, - .readpages = ext3_readpages, - .writepage = ext3_ordered_writepage, - .sync_page = block_sync_page, - .prepare_write = ext3_prepare_write, - .commit_write = ext3_ordered_commit_write, - .bmap = ext3_bmap, - .invalidatepage = ext3_invalidatepage, - .releasepage = ext3_releasepage, - .direct_IO = ext3_direct_IO, - .migratepage = buffer_migrate_page, +static const struct address_space_operations ext3_ordered_aops = { + .readpage = ext3_readpage, + .readpages = ext3_readpages, + .writepage = ext3_ordered_writepage, + .sync_page = block_sync_page, + .write_begin = ext3_write_begin, + .write_end = ext3_ordered_write_end, + .bmap = ext3_bmap, + .invalidatepage = ext3_invalidatepage, + .releasepage = ext3_releasepage, + .direct_IO = ext3_direct_IO, + .migratepage = buffer_migrate_page, + .is_partially_uptodate = block_is_partially_uptodate, + .error_remove_page = generic_error_remove_page, }; -static struct address_space_operations ext3_writeback_aops = { - .readpage = ext3_readpage, - .readpages = ext3_readpages, - .writepage = ext3_writeback_writepage, - .sync_page = block_sync_page, - .prepare_write = ext3_prepare_write, - .commit_write = ext3_writeback_commit_write, - .bmap = ext3_bmap, - .invalidatepage = ext3_invalidatepage, - .releasepage = ext3_releasepage, - .direct_IO = ext3_direct_IO, - .migratepage = buffer_migrate_page, +static const struct address_space_operations ext3_writeback_aops = { + .readpage = ext3_readpage, + .readpages = ext3_readpages, + .writepage = ext3_writeback_writepage, + .sync_page = block_sync_page, + .write_begin = ext3_write_begin, + .write_end = ext3_writeback_write_end, + .bmap = ext3_bmap, + .invalidatepage = ext3_invalidatepage, + .releasepage = ext3_releasepage, + .direct_IO = ext3_direct_IO, + .migratepage = buffer_migrate_page, + .is_partially_uptodate = block_is_partially_uptodate, + .error_remove_page = generic_error_remove_page, }; -static struct address_space_operations ext3_journalled_aops = { - .readpage = ext3_readpage, - .readpages = ext3_readpages, - .writepage = ext3_journalled_writepage, - .sync_page = block_sync_page, - .prepare_write = ext3_prepare_write, - .commit_write = ext3_journalled_commit_write, - .set_page_dirty = ext3_journalled_set_page_dirty, - .bmap = ext3_bmap, - .invalidatepage = ext3_invalidatepage, - .releasepage = ext3_releasepage, +static const struct address_space_operations ext3_journalled_aops = { + .readpage = ext3_readpage, + .readpages = ext3_readpages, + .writepage = ext3_journalled_writepage, + .sync_page = block_sync_page, + .write_begin = ext3_write_begin, + .write_end = ext3_journalled_write_end, + .set_page_dirty = ext3_journalled_set_page_dirty, + .bmap = ext3_bmap, + .invalidatepage = ext3_invalidatepage, + .releasepage = ext3_releasepage, + .is_partially_uptodate = block_is_partially_uptodate, + .error_remove_page = generic_error_remove_page, }; void ext3_set_aops(struct inode *inode) @@ -1756,13 +1900,12 @@ void ext3_set_aops(struct inode *inode) static int ext3_block_truncate_page(handle_t *handle, struct page *page, struct address_space *mapping, loff_t from) { - unsigned long index = from >> PAGE_CACHE_SHIFT; + ext3_fsblk_t index = from >> PAGE_CACHE_SHIFT; unsigned offset = from & (PAGE_CACHE_SIZE-1); unsigned blocksize, iblock, length, pos; struct inode *inode = mapping->host; struct buffer_head *bh; int err = 0; - void *kaddr; blocksize = inode->i_sb->s_blocksize; length = blocksize - (offset & (blocksize - 1)); @@ -1774,10 +1917,7 @@ static int ext3_block_truncate_page(handle_t *handle, struct page *page, */ if (!page_has_buffers(page) && test_opt(inode->i_sb, NOBH) && ext3_should_writeback_data(inode) && PageUptodate(page)) { - kaddr = kmap_atomic(page, KM_USER0); - memset(kaddr + offset, 0, length); - flush_dcache_page(page); - kunmap_atomic(kaddr, KM_USER0); + zero_user(page, offset, length); set_page_dirty(page); goto unlock; } @@ -1830,11 +1970,7 @@ static int ext3_block_truncate_page(handle_t *handle, struct page *page, goto unlock; } - kaddr = kmap_atomic(page, KM_USER0); - memset(kaddr + offset, 0, length); - flush_dcache_page(page); - kunmap_atomic(kaddr, KM_USER0); - + zero_user(page, offset, length); BUFFER_TRACE(bh, "zeroed end of block"); err = 0; @@ -1907,7 +2043,7 @@ static Indirect *ext3_find_shared(struct inode *inode, int depth, int k, err; *top = 0; - /* Make k index the deepest non-null offest + 1 */ + /* Make k index the deepest non-null offset + 1 */ for (k = depth; k > 1 && !offsets[k-1]; k--) ; partial = ext3_get_branch(inode, k, offsets, chain, &err); @@ -1957,7 +2093,7 @@ no_top: * than `count' because there can be holes in there. */ static void ext3_clear_blocks(handle_t *handle, struct inode *inode, - struct buffer_head *bh, unsigned long block_to_free, + struct buffer_head *bh, ext3_fsblk_t block_to_free, unsigned long count, __le32 *first, __le32 *last) { __le32 *p; @@ -1967,7 +2103,7 @@ static void ext3_clear_blocks(handle_t *handle, struct inode *inode, ext3_journal_dirty_metadata(handle, bh); } ext3_mark_inode_dirty(handle, inode); - ext3_journal_test_restart(handle, inode); + truncate_restart_transaction(handle, inode); if (bh) { BUFFER_TRACE(bh, "retaking write access"); ext3_journal_get_write_access(handle, bh); @@ -2019,12 +2155,12 @@ static void ext3_free_data(handle_t *handle, struct inode *inode, struct buffer_head *this_bh, __le32 *first, __le32 *last) { - unsigned long block_to_free = 0; /* Starting block # of a run */ - unsigned long count = 0; /* Number of blocks in the run */ + ext3_fsblk_t block_to_free = 0; /* Starting block # of a run */ + unsigned long count = 0; /* Number of blocks in the run */ __le32 *block_to_free_p = NULL; /* Pointer into inode/ind corresponding to block_to_free */ - unsigned long nr; /* Current block # */ + ext3_fsblk_t nr; /* Current block # */ __le32 *p; /* Pointer into inode/ind for current block */ int err; @@ -2049,7 +2185,7 @@ static void ext3_free_data(handle_t *handle, struct inode *inode, } else if (nr == block_to_free + count) { count++; } else { - ext3_clear_blocks(handle, inode, this_bh, + ext3_clear_blocks(handle, inode, this_bh, block_to_free, count, block_to_free_p, p); block_to_free = nr; @@ -2065,7 +2201,21 @@ static void ext3_free_data(handle_t *handle, struct inode *inode, if (this_bh) { BUFFER_TRACE(this_bh, "call ext3_journal_dirty_metadata"); - ext3_journal_dirty_metadata(handle, this_bh); + + /* + * The buffer head should have an attached journal head at this + * point. However, if the data is corrupted and an indirect + * block pointed to itself, it would have been detached when + * the block was cleared. Check for this instead of OOPSing. + */ + if (bh2jh(this_bh)) + ext3_journal_dirty_metadata(handle, this_bh); + else + ext3_error(inode->i_sb, "ext3_free_data", + "circular indirect block detected, " + "inode=%lu, block=%llu", + inode->i_ino, + (unsigned long long)this_bh->b_blocknr); } } @@ -2086,7 +2236,7 @@ static void ext3_free_branches(handle_t *handle, struct inode *inode, struct buffer_head *parent_bh, __le32 *first, __le32 *last, int depth) { - unsigned long nr; + ext3_fsblk_t nr; __le32 *p; if (is_handle_aborted(handle)) @@ -2110,7 +2260,7 @@ static void ext3_free_branches(handle_t *handle, struct inode *inode, */ if (!bh) { ext3_error(inode->i_sb, "ext3_free_branches", - "Read failure, inode=%ld, block=%ld", + "Read failure, inode=%lu, block="E3FSBLK, inode->i_ino, nr); continue; } @@ -2163,7 +2313,7 @@ static void ext3_free_branches(handle_t *handle, struct inode *inode, return; if (try_to_extend_transaction(handle, inode)) { ext3_mark_inode_dirty(handle, inode); - ext3_journal_test_restart(handle, inode); + truncate_restart_transaction(handle, inode); } ext3_free_blocks(handle, inode, nr, 1); @@ -2179,7 +2329,7 @@ static void ext3_free_branches(handle_t *handle, struct inode *inode, *p = 0; BUFFER_TRACE(parent_bh, "call ext3_journal_dirty_metadata"); - ext3_journal_dirty_metadata(handle, + ext3_journal_dirty_metadata(handle, parent_bh); } } @@ -2191,6 +2341,19 @@ static void ext3_free_branches(handle_t *handle, struct inode *inode, } } +int ext3_can_truncate(struct inode *inode) +{ + if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) + return 0; + if (S_ISREG(inode->i_mode)) + return 1; + if (S_ISDIR(inode->i_mode)) + return 1; + if (S_ISLNK(inode->i_mode)) + return !ext3_inode_is_fast_symlink(inode); + return 0; +} + /* * ext3_truncate() * @@ -2235,13 +2398,11 @@ void ext3_truncate(struct inode *inode) unsigned blocksize = inode->i_sb->s_blocksize; struct page *page; - if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || - S_ISLNK(inode->i_mode))) - return; - if (ext3_inode_is_fast_symlink(inode)) - return; - if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) - return; + if (!ext3_can_truncate(inode)) + goto out_notrans; + + if (inode->i_size == 0 && ext3_should_writeback_data(inode)) + ei->i_state |= EXT3_STATE_FLUSH_ON_CLOSE; /* * We have to lock the EOF page here, because lock_page() nests @@ -2254,7 +2415,7 @@ void ext3_truncate(struct inode *inode) page = grab_cache_page(mapping, inode->i_size >> PAGE_CACHE_SHIFT); if (!page) - return; + goto out_notrans; } handle = start_transaction(inode); @@ -2265,7 +2426,7 @@ void ext3_truncate(struct inode *inode) unlock_page(page); page_cache_release(page); } - return; /* AKPM: return what? */ + goto out_notrans; } last_block = (inode->i_size + blocksize-1) @@ -2389,46 +2550,43 @@ out_stop: ext3_orphan_del(handle, inode); ext3_journal_stop(handle); + return; +out_notrans: + /* + * Delete the inode from orphan list so that it doesn't stay there + * forever and trigger assertion on umount. + */ + if (inode->i_nlink) + ext3_orphan_del(NULL, inode); } -static unsigned long ext3_get_inode_block(struct super_block *sb, +static ext3_fsblk_t ext3_get_inode_block(struct super_block *sb, unsigned long ino, struct ext3_iloc *iloc) { - unsigned long desc, group_desc, block_group; - unsigned long offset, block; - struct buffer_head *bh; - struct ext3_group_desc * gdp; + unsigned long block_group; + unsigned long offset; + ext3_fsblk_t block; + struct ext3_group_desc *gdp; - - if ((ino != EXT3_ROOT_INO && ino != EXT3_JOURNAL_INO && - ino != EXT3_RESIZE_INO && ino < EXT3_FIRST_INO(sb)) || - ino > le32_to_cpu(EXT3_SB(sb)->s_es->s_inodes_count)) { - ext3_error(sb, "ext3_get_inode_block", - "bad inode number: %lu", ino); + if (!ext3_valid_inum(sb, ino)) { + /* + * This error is already checked for in namei.c unless we are + * looking at an NFS filehandle, in which case no error + * report is needed + */ return 0; } + block_group = (ino - 1) / EXT3_INODES_PER_GROUP(sb); - if (block_group >= EXT3_SB(sb)->s_groups_count) { - ext3_error(sb,"ext3_get_inode_block","group >= groups count"); - return 0; - } - smp_rmb(); - group_desc = block_group >> EXT3_DESC_PER_BLOCK_BITS(sb); - desc = block_group & (EXT3_DESC_PER_BLOCK(sb) - 1); - bh = EXT3_SB(sb)->s_group_desc[group_desc]; - if (!bh) { - ext3_error (sb, "ext3_get_inode_block", - "Descriptor not loaded"); + gdp = ext3_get_group_desc(sb, block_group, NULL); + if (!gdp) return 0; - } - - gdp = (struct ext3_group_desc *)bh->b_data; /* * Figure out the offset within the block group inode table */ offset = ((ino - 1) % EXT3_INODES_PER_GROUP(sb)) * EXT3_INODE_SIZE(sb); - block = le32_to_cpu(gdp[desc].bg_inode_table) + + block = le32_to_cpu(gdp->bg_inode_table) + (offset >> EXT3_BLOCK_SIZE_BITS(sb)); iloc->block_group = block_group; @@ -2445,7 +2603,7 @@ static unsigned long ext3_get_inode_block(struct super_block *sb, static int __ext3_get_inode_loc(struct inode *inode, struct ext3_iloc *iloc, int in_mem) { - unsigned long block; + ext3_fsblk_t block; struct buffer_head *bh; block = ext3_get_inode_block(inode->i_sb, inode->i_ino, iloc); @@ -2456,11 +2614,22 @@ static int __ext3_get_inode_loc(struct inode *inode, if (!bh) { ext3_error (inode->i_sb, "ext3_get_inode_loc", "unable to read inode block - " - "inode=%lu, block=%lu", inode->i_ino, block); + "inode=%lu, block="E3FSBLK, + inode->i_ino, block); return -EIO; } if (!buffer_uptodate(bh)) { lock_buffer(bh); + + /* + * If the buffer has the write error flag, we have failed + * to write out another inode in the same block. In this + * case, we don't have to read the block because we may + * read the old inode data successfully. + */ + if (buffer_write_io_error(bh) && !buffer_uptodate(bh)) + set_buffer_uptodate(bh); + if (buffer_uptodate(bh)) { /* someone brought it uptodate while we waited */ unlock_buffer(bh); @@ -2532,12 +2701,12 @@ make_io: */ get_bh(bh); bh->b_end_io = end_buffer_read_sync; - submit_bh(READ, bh); + submit_bh(READ_META, bh); wait_on_buffer(bh); if (!buffer_uptodate(bh)) { ext3_error(inode->i_sb, "ext3_get_inode_loc", "unable to read inode block - " - "inode=%lu, block=%lu", + "inode=%lu, block="E3FSBLK, inode->i_ino, block); brelse(bh); return -EIO; @@ -2572,21 +2741,48 @@ void ext3_set_inode_flags(struct inode *inode) inode->i_flags |= S_DIRSYNC; } -void ext3_read_inode(struct inode * inode) +/* Propagate flags from i_flags to EXT3_I(inode)->i_flags */ +void ext3_get_inode_flags(struct ext3_inode_info *ei) +{ + unsigned int flags = ei->vfs_inode.i_flags; + + ei->i_flags &= ~(EXT3_SYNC_FL|EXT3_APPEND_FL| + EXT3_IMMUTABLE_FL|EXT3_NOATIME_FL|EXT3_DIRSYNC_FL); + if (flags & S_SYNC) + ei->i_flags |= EXT3_SYNC_FL; + if (flags & S_APPEND) + ei->i_flags |= EXT3_APPEND_FL; + if (flags & S_IMMUTABLE) + ei->i_flags |= EXT3_IMMUTABLE_FL; + if (flags & S_NOATIME) + ei->i_flags |= EXT3_NOATIME_FL; + if (flags & S_DIRSYNC) + ei->i_flags |= EXT3_DIRSYNC_FL; +} + +struct inode *ext3_iget(struct super_block *sb, unsigned long ino) { struct ext3_iloc iloc; struct ext3_inode *raw_inode; - struct ext3_inode_info *ei = EXT3_I(inode); + struct ext3_inode_info *ei; struct buffer_head *bh; + struct inode *inode; + journal_t *journal = EXT3_SB(sb)->s_journal; + transaction_t *transaction; + long ret; int block; -#ifdef CONFIG_EXT3_FS_POSIX_ACL - ei->i_acl = EXT3_ACL_NOT_CACHED; - ei->i_default_acl = EXT3_ACL_NOT_CACHED; -#endif + inode = iget_locked(sb, ino); + if (!inode) + return ERR_PTR(-ENOMEM); + if (!(inode->i_state & I_NEW)) + return inode; + + ei = EXT3_I(inode); ei->i_block_alloc_info = NULL; - if (__ext3_get_inode_loc(inode, &iloc, 0)) + ret = __ext3_get_inode_loc(inode, &iloc, 0); + if (ret < 0) goto bad_inode; bh = iloc.bh; raw_inode = ext3_raw_inode(&iloc); @@ -2599,9 +2795,9 @@ void ext3_read_inode(struct inode * inode) } inode->i_nlink = le16_to_cpu(raw_inode->i_links_count); inode->i_size = le32_to_cpu(raw_inode->i_size); - inode->i_atime.tv_sec = le32_to_cpu(raw_inode->i_atime); - inode->i_ctime.tv_sec = le32_to_cpu(raw_inode->i_ctime); - inode->i_mtime.tv_sec = le32_to_cpu(raw_inode->i_mtime); + inode->i_atime.tv_sec = (signed)le32_to_cpu(raw_inode->i_atime); + inode->i_ctime.tv_sec = (signed)le32_to_cpu(raw_inode->i_ctime); + inode->i_mtime.tv_sec = (signed)le32_to_cpu(raw_inode->i_mtime); inode->i_atime.tv_nsec = inode->i_ctime.tv_nsec = inode->i_mtime.tv_nsec = 0; ei->i_state = 0; @@ -2617,6 +2813,7 @@ void ext3_read_inode(struct inode * inode) !(EXT3_SB(inode->i_sb)->s_mount_state & EXT3_ORPHAN_FS)) { /* this inode is deleted */ brelse (bh); + ret = -ESTALE; goto bad_inode; } /* The only unlinked inodes we let through here have @@ -2624,9 +2821,6 @@ void ext3_read_inode(struct inode * inode) * recovery code: that's fine, we're about to complete * the process of deleting those. */ } - inode->i_blksize = PAGE_SIZE; /* This is the optimal IO size - * (for stat), not the fs block - * size */ inode->i_blocks = le32_to_cpu(raw_inode->i_blocks); ei->i_flags = le32_to_cpu(raw_inode->i_flags); #ifdef EXT3_FRAGMENTS @@ -2652,6 +2846,30 @@ void ext3_read_inode(struct inode * inode) ei->i_data[block] = raw_inode->i_block[block]; INIT_LIST_HEAD(&ei->i_orphan); + /* + * Set transaction id's of transactions that have to be committed + * to finish f[data]sync. We set them to currently running transaction + * as we cannot be sure that the inode or some of its metadata isn't + * part of the transaction - the inode could have been reclaimed and + * now it is reread from disk. + */ + if (journal) { + tid_t tid; + + spin_lock(&journal->j_state_lock); + if (journal->j_running_transaction) + transaction = journal->j_running_transaction; + else + transaction = journal->j_committing_transaction; + if (transaction) + tid = transaction->t_tid; + else + tid = journal->j_commit_sequence; + spin_unlock(&journal->j_state_lock); + atomic_set(&ei->i_sync_tid, tid); + atomic_set(&ei->i_datasync_tid, tid); + } + if (inode->i_ino >= EXT3_FIRST_INO(inode->i_sb) + 1 && EXT3_INODE_SIZE(inode->i_sb) > EXT3_GOOD_OLD_INODE_SIZE) { /* @@ -2661,8 +2879,11 @@ void ext3_read_inode(struct inode * inode) */ ei->i_extra_isize = le16_to_cpu(raw_inode->i_extra_isize); if (EXT3_GOOD_OLD_INODE_SIZE + ei->i_extra_isize > - EXT3_INODE_SIZE(inode->i_sb)) + EXT3_INODE_SIZE(inode->i_sb)) { + brelse (bh); + ret = -EIO; goto bad_inode; + } if (ei->i_extra_isize == 0) { /* The extra space is currently unused. Use it. */ ei->i_extra_isize = sizeof(struct ext3_inode) - @@ -2685,9 +2906,11 @@ void ext3_read_inode(struct inode * inode) inode->i_op = &ext3_dir_inode_operations; inode->i_fop = &ext3_dir_operations; } else if (S_ISLNK(inode->i_mode)) { - if (ext3_inode_is_fast_symlink(inode)) + if (ext3_inode_is_fast_symlink(inode)) { inode->i_op = &ext3_fast_symlink_inode_operations; - else { + nd_terminate_link(ei->i_data, inode->i_size, + sizeof(ei->i_data) - 1); + } else { inode->i_op = &ext3_symlink_inode_operations; ext3_set_aops(inode); } @@ -2696,17 +2919,18 @@ void ext3_read_inode(struct inode * inode) if (raw_inode->i_block[0]) init_special_inode(inode, inode->i_mode, old_decode_dev(le32_to_cpu(raw_inode->i_block[0]))); - else + else init_special_inode(inode, inode->i_mode, new_decode_dev(le32_to_cpu(raw_inode->i_block[1]))); } brelse (iloc.bh); ext3_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); } /* @@ -2716,8 +2940,8 @@ bad_inode: * * The caller must have write access to iloc->bh. */ -static int ext3_do_update_inode(handle_t *handle, - struct inode *inode, +static int ext3_do_update_inode(handle_t *handle, + struct inode *inode, struct ext3_iloc *iloc) { struct ext3_inode *raw_inode = ext3_raw_inode(iloc); @@ -2725,11 +2949,16 @@ static int ext3_do_update_inode(handle_t *handle, struct buffer_head *bh = iloc->bh; int err = 0, rc, block; +again: + /* we can't allow multiple procs in here at once, its a bit racey */ + lock_buffer(bh); + /* For fields not not tracking in the in-memory inode, * initialise them to zero for new inodes. */ if (ei->i_state & EXT3_STATE_NEW) memset(raw_inode, 0, EXT3_SB(inode->i_sb)->s_inode_size); + ext3_get_inode_flags(ei); raw_inode->i_mode = cpu_to_le16(inode->i_mode); if(!(test_opt(inode->i_sb, NO_UID32))) { raw_inode->i_uid_low = cpu_to_le16(low_16_bits(inode->i_uid)); @@ -2783,17 +3012,20 @@ static int ext3_do_update_inode(handle_t *handle, /* If this is the first large file * created, add a flag to the superblock. */ + unlock_buffer(bh); err = ext3_journal_get_write_access(handle, EXT3_SB(sb)->s_sbh); if (err) goto out_brelse; + ext3_update_dynamic_rev(sb); EXT3_SET_RO_COMPAT_FEATURE(sb, EXT3_FEATURE_RO_COMPAT_LARGE_FILE); - sb->s_dirt = 1; handle->h_sync = 1; err = ext3_journal_dirty_metadata(handle, EXT3_SB(sb)->s_sbh); + /* get our lock and start over */ + goto again; } } } @@ -2816,11 +3048,13 @@ static int ext3_do_update_inode(handle_t *handle, raw_inode->i_extra_isize = cpu_to_le16(ei->i_extra_isize); BUFFER_TRACE(bh, "call ext3_journal_dirty_metadata"); + unlock_buffer(bh); rc = ext3_journal_dirty_metadata(handle, bh); if (!err) err = rc; ei->i_state &= ~EXT3_STATE_NEW; + atomic_set(&ei->i_sync_tid, handle->h_transaction->t_tid); out_brelse: brelse (bh); ext3_std_error(inode->i_sb, err); @@ -2868,7 +3102,7 @@ int ext3_write_inode(struct inode *inode, int wait) return 0; if (ext3_journal_current_handle()) { - jbd_debug(0, "called recursively, non-PF_MEMALLOC!\n"); + jbd_debug(1, "called recursively, non-PF_MEMALLOC!\n"); dump_stack(); return -EIO; } @@ -2892,7 +3126,7 @@ int ext3_write_inode(struct inode *inode, int wait) * commit will leave the blocks being flushed in an unused state on * disk. (On recovery, the inode will get truncated and the blocks will * be freed, so we have a strong guarantee that no future commit will - * leave these blocks visible to the user.) + * leave these blocks visible to the user.) * * Called with inode->sem down. */ @@ -2912,13 +3146,13 @@ int ext3_setattr(struct dentry *dentry, struct iattr *attr) /* (user+group)*(old+new) structure, inode write (sb, * inode block, ? - but truncate inode update has it) */ - handle = ext3_journal_start(inode, 2*(EXT3_QUOTA_INIT_BLOCKS(inode->i_sb)+ - EXT3_QUOTA_DEL_BLOCKS(inode->i_sb))+3); + handle = ext3_journal_start(inode, EXT3_MAXQUOTAS_INIT_BLOCKS(inode->i_sb)+ + EXT3_MAXQUOTAS_DEL_BLOCKS(inode->i_sb)+3); if (IS_ERR(handle)) { error = PTR_ERR(handle); goto err_out; } - error = DQUOT_TRANSFER(inode, attr) ? -EDQUOT : 0; + error = vfs_dq_transfer(inode, attr) ? -EDQUOT : 0; if (error) { ext3_journal_stop(handle); return error; @@ -2953,12 +3187,6 @@ int ext3_setattr(struct dentry *dentry, struct iattr *attr) rc = inode_setattr(inode, attr); - /* If inode_setattr's call to ext3_truncate failed to get a - * transaction handle at all, we need to clean up the in-core - * orphan list manually. */ - if (inode->i_nlink) - ext3_orphan_del(NULL, inode); - if (!rc && (ia_valid & ATTR_MODE)) rc = ext3_acl_chmod(inode); @@ -3009,9 +3237,9 @@ static int ext3_writepage_trans_blocks(struct inode *inode) ret = 2 * (bpp + indirects) + 2; #ifdef CONFIG_QUOTA - /* We know that structure was already allocated during DQUOT_INIT so + /* We know that structure was already allocated during vfs_dq_init so * we will be updating only the data blocks + inodes */ - ret += 2*EXT3_QUOTA_TRANS_BLOCKS(inode->i_sb); + ret += EXT3_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb); #endif return ret; @@ -3035,13 +3263,13 @@ int ext3_mark_iloc_dirty(handle_t *handle, return err; } -/* +/* * On success, We end up with an outstanding reference count against - * iloc->bh. This _must_ be cleaned up later. + * iloc->bh. This _must_ be cleaned up later. */ int -ext3_reserve_inode_write(handle_t *handle, struct inode *inode, +ext3_reserve_inode_write(handle_t *handle, struct inode *inode, struct ext3_iloc *iloc) { int err = 0; @@ -3100,7 +3328,7 @@ int ext3_mark_inode_dirty(handle_t *handle, struct inode *inode) * i_size has been changed by generic_commit_write() and we thus need * to include the updated inode in the current transaction. * - * Also, DQUOT_ALLOC_SPACE() will always dirty the inode when blocks + * Also, vfs_dq_alloc_space() will always dirty the inode when blocks * are allocated to the file. * * If the inode is marked synchronous, we don't honour that here - doing @@ -3119,7 +3347,7 @@ void ext3_dirty_inode(struct inode *inode) current_handle->h_transaction != handle->h_transaction) { /* This task has a transaction open against a different fs */ printk(KERN_EMERG "%s: transactions do not match!\n", - __FUNCTION__); + __func__); } else { jbd_debug(5, "marking dirty. outer handle=%p\n", current_handle); @@ -3131,7 +3359,7 @@ out: } #if 0 -/* +/* * Bind an inode's backing buffer_head into this transaction, to prevent * it from being flushed to disk early. Unlike * ext3_reserve_inode_write, this leaves behind no bh reference and @@ -3149,7 +3377,7 @@ static int ext3_pin_inode(handle_t *handle, struct inode *inode) BUFFER_TRACE(iloc.bh, "get_write_access"); err = journal_get_write_access(handle, iloc.bh); if (!err) - err = ext3_journal_dirty_metadata(handle, + err = ext3_journal_dirty_metadata(handle, iloc.bh); brelse(iloc.bh); } @@ -3176,7 +3404,7 @@ int ext3_change_inode_journal_flag(struct inode *inode, int val) */ journal = EXT3_JOURNAL(inode); - if (is_journal_aborted(journal) || IS_RDONLY(inode)) + if (is_journal_aborted(journal)) return -EROFS; journal_lock_updates(journal);