diff options
Diffstat (limited to 'fs/ext3/inode.c')
| -rw-r--r-- | fs/ext3/inode.c | 1127 |
1 files changed, 696 insertions, 431 deletions
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index eb95670a27e..2c6ccc49ba2 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -22,24 +22,18 @@ * Assorted race fixes, rewrite of ext3_get_block() by Al Viro, 2000 */ -#include <linux/module.h> -#include <linux/fs.h> -#include <linux/time.h> -#include <linux/ext3_jbd.h> -#include <linux/jbd.h> #include <linux/highuid.h> -#include <linux/pagemap.h> #include <linux/quotaops.h> -#include <linux/string.h> -#include <linux/buffer_head.h> #include <linux/writeback.h> #include <linux/mpage.h> -#include <linux/uio.h> -#include <linux/bio.h> +#include <linux/namei.h> +#include <linux/aio.h> +#include "ext3.h" #include "xattr.h" #include "acl.h" static int ext3_writepage_trans_blocks(struct inode *inode); +static int ext3_block_truncate_page(struct inode *inode, loff_t from); /* * Test whether an inode is a fast symlink. @@ -68,6 +62,7 @@ int ext3_forget(handle_t *handle, int is_metadata, struct inode *inode, might_sleep(); + trace_ext3_forget(inode, is_metadata, blocknr); BUFFER_TRACE(bh, "enter"); jbd_debug(4, "forgetting bh %p: is_metadata = %d, mode %o, " @@ -95,7 +90,7 @@ 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; @@ -170,22 +165,78 @@ 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; } /* - * Called at the last iput() if i_nlink is zero. + * Called at inode eviction from icache */ -void ext3_delete_inode (struct inode * inode) +void ext3_evict_inode (struct inode *inode) { + struct ext3_inode_info *ei = EXT3_I(inode); + struct ext3_block_alloc_info *rsv; handle_t *handle; + int want_delete = 0; + + trace_ext3_evict_inode(inode); + if (!inode->i_nlink && !is_bad_inode(inode)) { + dquot_initialize(inode); + want_delete = 1; + } + + /* + * When journalling data dirty buffers are tracked only in the journal. + * So although mm thinks everything is clean and ready for reaping the + * inode might still have some pages to write in the running + * transaction or waiting to be checkpointed. Thus calling + * journal_invalidatepage() (via truncate_inode_pages()) to discard + * these buffers can cause data loss. Also even if we did not discard + * these buffers, we would have no way to find them after the inode + * is reaped and thus user could see stale data if he tries to read + * them before the transaction is checkpointed. So be careful and + * force everything to disk here... We use ei->i_datasync_tid to + * store the newest transaction containing inode's data. + * + * Note that directories do not have this problem because they don't + * use page cache. + * + * The s_journal check handles the case when ext3_get_journal() fails + * and puts the journal inode. + */ + if (inode->i_nlink && ext3_should_journal_data(inode) && + EXT3_SB(inode->i_sb)->s_journal && + (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode)) && + inode->i_ino != EXT3_JOURNAL_INO) { + tid_t commit_tid = atomic_read(&ei->i_datasync_tid); + journal_t *journal = EXT3_SB(inode->i_sb)->s_journal; + + log_start_commit(journal, commit_tid); + log_wait_commit(journal, commit_tid); + filemap_write_and_wait(&inode->i_data); + } + truncate_inode_pages_final(&inode->i_data); - truncate_inode_pages(&inode->i_data, 0); + ext3_discard_reservation(inode); + rsv = ei->i_block_alloc_info; + ei->i_block_alloc_info = NULL; + if (unlikely(rsv)) + kfree(rsv); - if (is_bad_inode(inode)) + if (!want_delete) goto no_delete; handle = start_transaction(inode); @@ -205,15 +256,13 @@ void ext3_delete_inode (struct inode * inode) if (inode->i_blocks) ext3_truncate(inode); /* - * Kill off the orphan record which ext3_truncate created. - * AKPM: I think this can be inside the above `if'. - * Note that ext3_orphan_del() has to be able to cope with the - * deletion of a non-existent orphan - this is because we don't - * know if ext3_truncate() actually created an orphan record. - * (Well, we could do this if we need to, but heck - it works) + * Kill off the orphan record created when the inode lost the last + * link. Note that ext3_orphan_del() has to be able to cope with the + * deletion of a non-existent orphan - ext3_truncate() could + * have removed the record. */ ext3_orphan_del(handle, inode); - EXT3_I(inode)->i_dtime = get_seconds(); + ei->i_dtime = get_seconds(); /* * One subtle ordering requirement: if anything has gone wrong @@ -222,15 +271,22 @@ void ext3_delete_inode (struct inode * inode) * having errors), but we can't free the inode if the mark_dirty * fails. */ - if (ext3_mark_inode_dirty(handle, inode)) - /* If that failed, just do the required in-core inode clear. */ + if (ext3_mark_inode_dirty(handle, inode)) { + /* If that failed, just dquot_drop() and be done with that */ + dquot_drop(inode); + clear_inode(inode); + } else { + ext3_xattr_delete_inode(handle, inode); + dquot_free_inode(inode); + dquot_drop(inode); clear_inode(inode); - else ext3_free_inode(handle, inode); + } ext3_journal_stop(handle); return; no_delete: - clear_inode(inode); /* We must guarantee clearing of inode... */ + clear_inode(inode); + dquot_drop(inode); } typedef struct { @@ -392,7 +448,7 @@ 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. @@ -436,12 +492,12 @@ static ext3_fsblk_t ext3_find_near(struct inode *inode, Indirect *ind) } /** - * ext3_find_goal - find a prefered place for allocation. + * ext3_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. */ @@ -465,7 +521,7 @@ static ext3_fsblk_t ext3_find_goal(struct inode *inode, long block, } /** - * ext3_blks_to_allocate: Look up the block map and count the number + * 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 @@ -503,14 +559,18 @@ static int ext3_blks_to_allocate(Indirect *branch, int k, unsigned long blks, } /** - * ext3_alloc_blocks: multiple allocate blocks needed for a branch + * ext3_alloc_blocks - multiple allocate blocks needed for a branch + * @handle: handle for this transaction + * @inode: owner + * @goal: preferred place for allocation * @indirect_blks: the number of blocks need to allocate for indirect * blocks - * + * @blks: number of blocks need to allocated for direct blocks * @new_blocks: on return it will store the new block numbers for * the indirect blocks(if needed) and the first direct block, - * @blks: on return it will store the total number of allocated - * direct blocks + * @err: here we store the error value + * + * return the number of direct blocks allocated */ static int ext3_alloc_blocks(handle_t *handle, struct inode *inode, ext3_fsblk_t goal, int indirect_blks, int blks, @@ -565,9 +625,11 @@ failed_out: /** * ext3_alloc_branch - allocate and set up a chain of blocks. + * @handle: handle for this transaction * @inode: owner * @indirect_blks: number of allocated indirect blocks * @blks: number of allocated direct blocks + * @goal: preferred place for allocation * @offsets: offsets (in the blocks) to store the pointers to next. * @branch: place to store the chain in. * @@ -616,6 +678,10 @@ static int ext3_alloc_branch(handle_t *handle, struct inode *inode, * parent to disk. */ bh = sb_getblk(inode->i_sb, new_blocks[n-1]); + if (unlikely(!bh)) { + err = -ENOMEM; + goto failed; + } branch[n].bh = bh; lock_buffer(bh); BUFFER_TRACE(bh, "call get_create_access"); @@ -657,7 +723,7 @@ failed: BUFFER_TRACE(branch[i].bh, "call journal_forget"); ext3_journal_forget(handle, branch[i].bh); } - for (i = 0; i <indirect_blks; i++) + for (i = 0; i < indirect_blks; i++) ext3_free_blocks(handle, inode, new_blocks[i], 1); ext3_free_blocks(handle, inode, new_blocks[i], num); @@ -667,10 +733,9 @@ failed: /** * ext3_splice_branch - splice the allocated branch onto inode. + * @handle: handle for this transaction * @inode: owner * @block: (logical) number of block we are adding - * @chain: chain of indirect blocks (with a missing link - see - * ext3_alloc_branch) * @where: location of missing link * @num: number of indirect blocks we are adding * @blks: number of direct blocks we are adding @@ -686,8 +751,10 @@ static int ext3_splice_branch(handle_t *handle, struct inode *inode, int err = 0; struct ext3_block_alloc_info *block_i; ext3_fsblk_t current_block; + struct ext3_inode_info *ei = EXT3_I(inode); + struct timespec now; - 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 @@ -725,9 +792,13 @@ static int ext3_splice_branch(handle_t *handle, struct inode *inode, } /* We are done with atomic stuff, now do the rest of housekeeping */ - - inode->i_ctime = CURRENT_TIME_SEC; - ext3_mark_inode_dirty(handle, inode); + now = CURRENT_TIME_SEC; + if (!timespec_equal(&inode->i_ctime, &now) || !where->bh) { + inode->i_ctime = now; + 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) { @@ -786,7 +857,7 @@ 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]; @@ -801,6 +872,7 @@ int ext3_get_blocks_handle(handle_t *handle, struct inode *inode, ext3_fsblk_t first_block = 0; + trace_ext3_get_blocks_enter(inode, iblock, maxblocks, create); J_ASSERT(handle != NULL || create == 0); depth = ext3_block_to_path(inode,iblock,offsets,&blocks_to_boundary); @@ -818,7 +890,7 @@ int ext3_get_blocks_handle(handle_t *handle, struct inode *inode, while (count < maxblocks && count <= blocks_to_boundary) { ext3_fsblk_t blk; - if (!verify_chain(chain, partial)) { + if (!verify_chain(chain, chain + depth - 1)) { /* * Indirect block might be removed by * truncate while we were reading it. @@ -845,6 +917,9 @@ int ext3_get_blocks_handle(handle_t *handle, struct inode *inode, if (!create || err == -EIO) goto cleanup; + /* + * Block out ext3_truncate while we alter the tree + */ mutex_lock(&ei->truncate_mutex); /* @@ -893,9 +968,6 @@ int ext3_get_blocks_handle(handle_t *handle, struct inode *inode, */ count = ext3_blks_to_allocate(partial, indirect_blks, maxblocks, blocks_to_boundary); - /* - * Block out ext3_truncate while we alter the tree - */ err = ext3_alloc_branch(handle, inode, indirect_blks, &count, goal, offsets + (partial - chain), partial); @@ -909,13 +981,6 @@ 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; @@ -936,6 +1001,9 @@ cleanup: } BUFFER_TRACE(bh_result, "returned"); out: + trace_ext3_get_blocks_exit(inode, iblock, + depth ? le32_to_cpu(chain[depth-1].key) : 0, + count, err); return err; } @@ -961,7 +1029,7 @@ static int ext3_get_block(struct inode *inode, sector_t iblock, if (max_blocks > DIO_MAX_BLOCKS) max_blocks = DIO_MAX_BLOCKS; handle = ext3_journal_start(inode, DIO_CREDITS + - 2 * EXT3_QUOTA_TRANS_BLOCKS(inode->i_sb)); + EXT3_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb)); if (IS_ERR(handle)) { ret = PTR_ERR(handle); goto out; @@ -970,7 +1038,7 @@ static int ext3_get_block(struct inode *inode, sector_t iblock, } ret = ext3_get_blocks_handle(handle, inode, iblock, - max_blocks, bh_result, create, 0); + max_blocks, bh_result, create); if (ret > 0) { bh_result->b_size = (ret << inode->i_blkbits); ret = 0; @@ -981,6 +1049,13 @@ 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 */ @@ -996,22 +1071,21 @@ 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); + &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); + WARN_ON(err > 1); err = 0; } *errp = err; if (!err && buffer_mapped(&dummy)) { struct buffer_head *bh; bh = sb_getblk(inode->i_sb, dummy.b_blocknr); - if (!bh) { - *errp = -EIO; + if (unlikely(!bh)) { + *errp = -ENOMEM; goto err; } if (buffer_new(&dummy)) { @@ -1059,9 +1133,11 @@ struct buffer_head *ext3_bread(handle_t *handle, struct inode *inode, bh = ext3_getblk(handle, inode, block, create, err); if (!bh) return bh; - if (buffer_uptodate(bh)) + if (bh_uptodate_or_lock(bh)) return bh; - ll_rw_block(READ_META, 1, &bh); + get_bh(bh); + bh->b_end_io = end_buffer_read_sync; + submit_bh(READ | REQ_META | REQ_PRIO, bh); wait_on_buffer(bh); if (buffer_uptodate(bh)) return bh; @@ -1130,9 +1206,45 @@ static int walk_page_buffers( handle_t *handle, static int do_journal_get_write_access(handle_t *handle, struct buffer_head *bh) { + int dirty = buffer_dirty(bh); + int ret; + if (!buffer_mapped(bh) || buffer_freed(bh)) return 0; - return ext3_journal_get_write_access(handle, bh); + /* + * __block_prepare_write() could have dirtied some buffers. Clean + * the dirty bit as jbd2_journal_get_write_access() could complain + * otherwise about fs integrity issues. Setting of the dirty bit + * by __block_prepare_write() isn't a real problem here as we clear + * the bit before releasing a page lock and thus writeback cannot + * ever write the buffer. + */ + if (dirty) + clear_buffer_dirty(bh); + ret = ext3_journal_get_write_access(handle, bh); + if (!ret && dirty) + ret = ext3_journal_dirty_metadata(handle, bh); + return ret; +} + +/* + * 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); +} + +/* + * Truncate blocks that were not used by direct IO write. We have to zero out + * the last file block as well because direct IO might have written to it. + */ +static void ext3_truncate_failed_direct_write(struct inode *inode) +{ + ext3_block_truncate_page(inode, inode->i_size); + ext3_truncate(inode); } static int ext3_write_begin(struct file *file, struct address_space *mapping, @@ -1140,19 +1252,24 @@ static int ext3_write_begin(struct file *file, struct address_space *mapping, struct page **pagep, void **fsdata) { struct inode *inode = mapping->host; - int ret, needed_blocks = ext3_writepage_trans_blocks(inode); + 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; + + trace_ext3_write_begin(inode, pos, len, flags); index = pos >> PAGE_CACHE_SHIFT; from = pos & (PAGE_CACHE_SIZE - 1); to = from + len; retry: - page = __grab_cache_page(mapping, index); + page = grab_cache_page_write_begin(mapping, index, flags); if (!page) return -ENOMEM; *pagep = page; @@ -1164,8 +1281,7 @@ retry: ret = PTR_ERR(handle); goto out; } - ret = block_write_begin(file, mapping, pos, len, flags, pagep, fsdata, - ext3_get_block); + ret = __block_write_begin(page, pos, len, ext3_get_block); if (ret) goto write_begin_failed; @@ -1175,9 +1291,22 @@ retry: } 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; @@ -1190,11 +1319,23 @@ 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__, + ext3_journal_abort_handle(__func__, __func__, bh, handle, err); return err; } +/* 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) { @@ -1205,26 +1346,20 @@ static int write_end_fn(handle_t *handle, struct buffer_head *bh) } /* - * Generic write_end handler for ordered and writeback ext3 journal modes. - * We can't use generic_write_end, because that unlocks the page and we need to - * unlock the page after ext3_journal_stop, but ext3_journal_stop must run - * after block_write_end. + * 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 int ext3_generic_write_end(struct file *file, - struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) +static void update_file_sizes(struct inode *inode, loff_t pos, unsigned copied) { - struct inode *inode = file->f_mapping->host; - - copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); - - if (pos+copied > inode->i_size) { - i_size_write(inode, pos+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); } - - return copied; } /* @@ -1244,34 +1379,30 @@ static int ext3_ordered_write_end(struct file *file, unsigned from, to; int ret = 0, ret2; - from = pos & (PAGE_CACHE_SIZE - 1); - to = from + len; + trace_ext3_ordered_write_end(inode, pos, len, copied); + copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); + from = pos & (PAGE_CACHE_SIZE - 1); + to = from + copied; ret = walk_page_buffers(handle, page_buffers(page), - from, to, NULL, ext3_journal_dirty_data); - - if (ret == 0) { - /* - * generic_write_end() 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, to, NULL, journal_dirty_data_fn); - new_i_size = pos + copied; - if (new_i_size > EXT3_I(inode)->i_disksize) - EXT3_I(inode)->i_disksize = new_i_size; - copied = ext3_generic_write_end(file, mapping, pos, len, copied, - page, fsdata); - if (copied < 0) - ret = copied; - } + 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; unlock_page(page); page_cache_release(page); + if (pos + len > inode->i_size) + ext3_truncate_failed_write(inode); return ret ? ret : copied; } @@ -1282,24 +1413,23 @@ static int ext3_writeback_write_end(struct file *file, { handle_t *handle = ext3_journal_current_handle(); struct inode *inode = file->f_mapping->host; - int ret = 0, ret2; - loff_t new_i_size; - - new_i_size = pos + copied; - if (new_i_size > EXT3_I(inode)->i_disksize) - EXT3_I(inode)->i_disksize = new_i_size; - - copied = ext3_generic_write_end(file, mapping, pos, len, copied, - page, fsdata); - if (copied < 0) - ret = copied; + int ret; - ret2 = ext3_journal_stop(handle); - if (!ret) - ret = ret2; + trace_ext3_writeback_write_end(inode, pos, len, copied); + 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); + if (pos + len > inode->i_size) + ext3_truncate_failed_write(inode); return ret ? ret : copied; } @@ -1310,28 +1440,39 @@ static int ext3_journalled_write_end(struct file *file, { handle_t *handle = ext3_journal_current_handle(); struct inode *inode = mapping->host; + struct ext3_inode_info *ei = EXT3_I(inode); int ret = 0, ret2; int partial = 0; unsigned from, to; + trace_ext3_journalled_write_end(inode, pos, len, copied); 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); + page_zero_new_buffers(page, from + copied, to); + to = from + copied; } ret = walk_page_buffers(handle, page_buffers(page), from, to, &partial, write_end_fn); if (!partial) SetPageUptodate(page); - if (pos+copied > inode->i_size) - i_size_write(inode, pos+copied); - 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; + + 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_set_inode_state(inode, EXT3_STATE_JDATA); + atomic_set(&ei->i_datasync_tid, handle->h_transaction->t_tid); + if (inode->i_size > ei->i_disksize) { + ei->i_disksize = inode->i_size; ret2 = ext3_mark_inode_dirty(handle, inode); if (!ret) ret = ret2; @@ -1343,6 +1484,8 @@ static int ext3_journalled_write_end(struct file *file, unlock_page(page); page_cache_release(page); + if (pos + len > inode->i_size) + ext3_truncate_failed_write(inode); return ret ? ret : copied; } @@ -1366,7 +1509,7 @@ static sector_t ext3_bmap(struct address_space *mapping, sector_t block) journal_t *journal; int err; - if (EXT3_I(inode)->i_state & EXT3_STATE_JDATA) { + if (ext3_test_inode_state(inode, EXT3_STATE_JDATA)) { /* * This is a REALLY heavyweight approach, but the use of * bmap on dirty files is expected to be extremely rare: @@ -1385,7 +1528,7 @@ static sector_t ext3_bmap(struct address_space *mapping, sector_t block) * everything they get. */ - EXT3_I(inode)->i_state &= ~EXT3_STATE_JDATA; + ext3_clear_inode_state(inode, EXT3_STATE_JDATA); journal = EXT3_JOURNAL(inode); journal_lock_updates(journal); err = journal_flush(journal); @@ -1410,64 +1553,23 @@ 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); } /* - * Note that we always start a transaction even if we're not journalling - * data. This is to preserve ordering: any hole instantiation within - * __block_write_full_page -> ext3_get_block() should be journalled - * along with the data so we don't crash and then get metadata which + * Note that whenever we need to map blocks we start a transaction even if + * we're not journalling data. This is to preserve ordering: any hole + * instantiation within __block_write_full_page -> ext3_get_block() should be + * journalled along with the data so we don't crash and then get metadata which * refers to old data. * * In all journalling modes block_write_full_page() will start the I/O. * - * Problem: - * - * ext3_writepage() -> kmalloc() -> __alloc_pages() -> page_launder() -> - * ext3_writepage() - * - * Similar for: - * - * ext3_file_write() -> generic_file_write() -> __alloc_pages() -> ... - * - * Same applies to ext3_get_block(). We will deadlock on various things like - * lock_journal and i_truncate_mutex. - * - * Setting PF_MEMALLOC here doesn't work - too many internal memory - * allocations fail. - * - * 16May01: If we're reentered then journal_current_handle() will be - * non-zero. We simply *return*. - * - * 1 July 2001: @@@ FIXME: - * In journalled data mode, a data buffer may be metadata against the - * current transaction. But the same file is part of a shared mapping - * and someone does a writepage() on it. - * - * We will move the buffer onto the async_data list, but *after* it has - * been dirtied. So there's a small window where we have dirty data on - * BJ_Metadata. - * - * Note that this only applies to the last partial page in the file. The - * bit which block_write_full_page() uses prepare/commit for. (That's - * broken code anyway: it's wrong for msync()). - * - * It's a rare case: affects the final partial page, for journalled data - * where the file is subject to bith write() and writepage() in the same - * transction. To fix it we'll need a custom block_write_full_page(). - * We'll probably need that anyway for journalling writepage() output. - * * We don't honour synchronous mounts for writepage(). That would be * disastrous. Any write() or metadata operation will sync the fs for * us. - * - * AKPM2: if all the page's buffers are mapped to disk and !data=journal, - * we don't need to open a transaction here. */ static int ext3_ordered_writepage(struct page *page, struct writeback_control *wbc) @@ -1479,6 +1581,13 @@ static int ext3_ordered_writepage(struct page *page, int err; J_ASSERT(PageLocked(page)); + /* + * We don't want to warn for emergency remount. The condition is + * ordered to avoid dereferencing inode->i_sb in non-error case to + * avoid slow-downs. + */ + WARN_ON_ONCE(IS_RDONLY(inode) && + !(EXT3_SB(inode->i_sb)->s_mount_state & EXT3_ERROR_FS)); /* * We give up here if we're reentered, because it might be for a @@ -1487,6 +1596,20 @@ static int ext3_ordered_writepage(struct page *page, if (ext3_journal_current_handle()) goto out_fail; + trace_ext3_ordered_writepage(page); + 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)) { @@ -1494,11 +1617,6 @@ 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); @@ -1516,12 +1634,9 @@ static int ext3_ordered_writepage(struct page *page, * block_write_full_page() succeeded. Otherwise they are unmapped, * and generally junk. */ - if (ret == 0) { - err = walk_page_buffers(handle, page_bufs, 0, PAGE_CACHE_SIZE, + if (ret == 0) + ret = walk_page_buffers(handle, page_bufs, 0, PAGE_CACHE_SIZE, NULL, journal_dirty_data_fn); - if (!ret) - ret = err; - } walk_page_buffers(handle, page_bufs, 0, PAGE_CACHE_SIZE, NULL, bput_one); err = ext3_journal_stop(handle); @@ -1543,19 +1658,35 @@ static int ext3_writeback_writepage(struct page *page, int ret = 0; int err; + J_ASSERT(PageLocked(page)); + /* + * We don't want to warn for emergency remount. The condition is + * ordered to avoid dereferencing inode->i_sb in non-error case to + * avoid slow-downs. + */ + WARN_ON_ONCE(IS_RDONLY(inode) && + !(EXT3_SB(inode->i_sb)->s_mount_state & EXT3_ERROR_FS)); + if (ext3_journal_current_handle()) goto out_fail; + trace_ext3_writeback_writepage(page); + 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) && ext3_should_writeback_data(inode)) - ret = nobh_writepage(page, ext3_get_block, wbc); - else - ret = block_write_full_page(page, ext3_get_block, wbc); + ret = block_write_full_page(page, ext3_get_block, wbc); err = ext3_journal_stop(handle); if (!ret) @@ -1576,23 +1707,33 @@ static int ext3_journalled_writepage(struct page *page, int ret = 0; int err; - if (ext3_journal_current_handle()) - goto no_write; - - handle = ext3_journal_start(inode, ext3_writepage_trans_blocks(inode)); - if (IS_ERR(handle)) { - ret = PTR_ERR(handle); - goto no_write; - } + J_ASSERT(PageLocked(page)); + /* + * We don't want to warn for emergency remount. The condition is + * ordered to avoid dereferencing inode->i_sb in non-error case to + * avoid slow-downs. + */ + WARN_ON_ONCE(IS_RDONLY(inode) && + !(EXT3_SB(inode->i_sb)->s_mount_state & EXT3_ERROR_FS)); + trace_ext3_journalled_writepage(page); if (!page_has_buffers(page) || PageChecked(page)) { + if (ext3_journal_current_handle()) + goto no_write; + + handle = ext3_journal_start(inode, + ext3_writepage_trans_blocks(inode)); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto no_write; + } /* * It's mmapped pagecache. Add buffers and journal it. There * doesn't seem much point in redirtying the page here. */ ClearPageChecked(page); - ret = block_prepare_write(page, 0, PAGE_CACHE_SIZE, - ext3_get_block); + ret = __block_write_begin(page, 0, PAGE_CACHE_SIZE, + ext3_get_block); if (ret != 0) { ext3_journal_stop(handle); goto out_unlock; @@ -1604,19 +1745,22 @@ static int ext3_journalled_writepage(struct page *page, PAGE_CACHE_SIZE, NULL, write_end_fn); if (ret == 0) ret = err; - EXT3_I(inode)->i_state |= EXT3_STATE_JDATA; + ext3_set_inode_state(inode, EXT3_STATE_JDATA); + atomic_set(&EXT3_I(inode)->i_datasync_tid, + handle->h_transaction->t_tid); unlock_page(page); + err = ext3_journal_stop(handle); + if (!ret) + ret = err; } else { /* - * It may be a page full of checkpoint-mode buffers. We don't - * really know unless we go poke around in the buffer_heads. - * But block_write_full_page will do the right thing. + * It is a page full of checkpoint-mode buffers. Go and write + * them. They should have been already mapped when they went + * to the journal so provide NULL get_block function to catch + * errors. */ - ret = block_write_full_page(page, ext3_get_block, wbc); + ret = block_write_full_page(page, NULL, wbc); } - err = ext3_journal_stop(handle); - if (!ret) - ret = err; out: return ret; @@ -1629,6 +1773,7 @@ out_unlock: static int ext3_readpage(struct file *file, struct page *page) { + trace_ext3_readpage(page); return mpage_readpage(page, ext3_get_block); } @@ -1639,23 +1784,27 @@ ext3_readpages(struct file *file, struct address_space *mapping, return mpage_readpages(mapping, pages, nr_pages, ext3_get_block); } -static void ext3_invalidatepage(struct page *page, unsigned long offset) +static void ext3_invalidatepage(struct page *page, unsigned int offset, + unsigned int length) { journal_t *journal = EXT3_JOURNAL(page->mapping->host); + trace_ext3_invalidatepage(page, offset, length); + /* * If it's a full truncate we just forget about the pending dirtying */ - if (offset == 0) + if (offset == 0 && length == PAGE_CACHE_SIZE) ClearPageChecked(page); - journal_invalidatepage(journal, page, offset); + journal_invalidatepage(journal, page, offset, length); } static int ext3_releasepage(struct page *page, gfp_t wait) { journal_t *journal = EXT3_JOURNAL(page->mapping->host); + trace_ext3_releasepage(page); WARN_ON(PageChecked(page)); if (!page_has_buffers(page)) return 0; @@ -1672,8 +1821,7 @@ static int ext3_releasepage(struct page *page, gfp_t wait) * 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, - unsigned long nr_segs) + struct iov_iter *iter, loff_t offset) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; @@ -1681,7 +1829,10 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb, handle_t *handle; ssize_t ret; int orphan = 0; - size_t count = iov_length(iov, nr_segs); + size_t count = iov_iter_count(iter); + int retries = 0; + + trace_ext3_direct_IO_enter(inode, offset, count, rw); if (rw == WRITE) { loff_t final_size = offset + count; @@ -1704,9 +1855,21 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb, } } - ret = blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov, - offset, nr_segs, - ext3_get_block, NULL); +retry: + ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, ext3_get_block); + /* + * In case of error extending write may have instantiated a few + * blocks outside i_size. Trim these off again. + */ + if (unlikely((rw & WRITE) && ret < 0)) { + loff_t isize = i_size_read(inode); + loff_t end = offset + count; + + if (end > isize) + ext3_truncate_failed_direct_write(inode); + } + if (ret == -ENOSPC && ext3_should_retry_alloc(inode->i_sb, &retries)) + goto retry; if (orphan) { int err; @@ -1715,9 +1878,12 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb, 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... */ + * but cannot extend i_size. Truncate allocated blocks + * and pretend the write failed... */ + ext3_truncate_failed_direct_write(inode); ret = PTR_ERR(handle); + if (inode->i_nlink) + ext3_orphan_del(NULL, inode); goto out; } if (inode->i_nlink) @@ -1742,6 +1908,7 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb, ret = err; } out: + trace_ext3_direct_IO_exit(inode, offset, count, rw, ret); return ret; } @@ -1765,44 +1932,48 @@ static int ext3_journalled_set_page_dirty(struct page *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, + .readpage = ext3_readpage, + .readpages = ext3_readpages, + .writepage = ext3_ordered_writepage, + .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, + .is_dirty_writeback = buffer_check_dirty_writeback, + .error_remove_page = generic_error_remove_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, + .readpage = ext3_readpage, + .readpages = ext3_readpages, + .writepage = ext3_writeback_writepage, + .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 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, + .readpage = ext3_readpage, + .readpages = ext3_readpages, + .writepage = ext3_journalled_writepage, + .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) @@ -1821,31 +1992,27 @@ void ext3_set_aops(struct inode *inode) * This required during truncate. We need to physically zero the tail end * of that block so it doesn't yield old data if the file is later grown. */ -static int ext3_block_truncate_page(handle_t *handle, struct page *page, - struct address_space *mapping, loff_t from) +static int ext3_block_truncate_page(struct inode *inode, loff_t from) { ext3_fsblk_t index = from >> PAGE_CACHE_SHIFT; - unsigned offset = from & (PAGE_CACHE_SIZE-1); + unsigned offset = from & (PAGE_CACHE_SIZE - 1); unsigned blocksize, iblock, length, pos; - struct inode *inode = mapping->host; + struct page *page; + handle_t *handle = NULL; struct buffer_head *bh; int err = 0; + /* Truncated on block boundary - nothing to do */ blocksize = inode->i_sb->s_blocksize; + if ((from & (blocksize - 1)) == 0) + return 0; + + page = grab_cache_page(inode->i_mapping, index); + if (!page) + return -ENOMEM; length = blocksize - (offset & (blocksize - 1)); iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits); - /* - * For "nobh" option, we can only work if we don't need to - * read-in the page - otherwise we create buffers to do the IO. - */ - if (!page_has_buffers(page) && test_opt(inode->i_sb, NOBH) && - ext3_should_writeback_data(inode) && PageUptodate(page)) { - zero_user(page, offset, length); - set_page_dirty(page); - goto unlock; - } - if (!page_has_buffers(page)) create_empty_buffers(page, blocksize, 0); @@ -1878,20 +2045,30 @@ static int ext3_block_truncate_page(handle_t *handle, struct page *page, if (PageUptodate(page)) set_buffer_uptodate(bh); - if (!buffer_uptodate(bh)) { - err = -EIO; - ll_rw_block(READ, 1, &bh); - wait_on_buffer(bh); + if (!bh_uptodate_or_lock(bh)) { + err = bh_submit_read(bh); /* Uhhuh. Read error. Complain and punt. */ - if (!buffer_uptodate(bh)) + if (err) + goto unlock; + } + + /* data=writeback mode doesn't need transaction to zero-out data */ + if (!ext3_should_writeback_data(inode)) { + /* We journal at most one block */ + handle = ext3_journal_start(inode, 1); + if (IS_ERR(handle)) { + clear_highpage(page); + flush_dcache_page(page); + err = PTR_ERR(handle); goto unlock; + } } if (ext3_should_journal_data(inode)) { BUFFER_TRACE(bh, "get write access"); err = ext3_journal_get_write_access(handle, bh); if (err) - goto unlock; + goto stop; } zero_user(page, offset, length); @@ -1905,6 +2082,9 @@ static int ext3_block_truncate_page(handle_t *handle, struct page *page, err = ext3_journal_dirty_data(handle, bh); mark_buffer_dirty(bh); } +stop: + if (handle) + ext3_journal_stop(handle); unlock: unlock_page(page); @@ -1937,7 +2117,7 @@ static inline int all_zeroes(__le32 *p, __le32 *q) * * When we do truncate() we may have to clean the ends of several * indirect blocks but leave the blocks themselves alive. Block is - * partially truncated if some data below the new i_size is refered + * partially truncated if some data below the new i_size is referred * from it (and it is on the path to the first completely truncated * data block, indeed). We have to free the top of that path along * with everything to the right of the path. Since no allocation @@ -1967,7 +2147,7 @@ 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); @@ -2024,13 +2204,15 @@ static void ext3_clear_blocks(handle_t *handle, struct inode *inode, if (try_to_extend_transaction(handle, inode)) { if (bh) { BUFFER_TRACE(bh, "call ext3_journal_dirty_metadata"); - ext3_journal_dirty_metadata(handle, bh); + if (ext3_journal_dirty_metadata(handle, bh)) + return; } 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); + if (ext3_journal_get_write_access(handle, bh)) + return; } } @@ -2064,7 +2246,7 @@ static void ext3_clear_blocks(handle_t *handle, struct inode *inode, * @first: array of block numbers * @last: points immediately past the end of array * - * We are freeing all blocks refered from that array (numbers are stored as + * We are freeing all blocks referred from that array (numbers are stored as * little-endian 32-bit) and updating @inode->i_blocks appropriately. * * We accumulate contiguous runs of blocks to free. Conveniently, if these @@ -2125,7 +2307,21 @@ 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); } } @@ -2138,7 +2334,7 @@ static void ext3_free_data(handle_t *handle, struct inode *inode, * @last: pointer immediately past the end of array * @depth: depth of the branches to free * - * We are freeing all blocks refered from these branches (numbers are + * We are freeing all blocks referred from these branches (numbers are * stored as little-endian 32-bit) and updating @inode->i_blocks * appropriately. */ @@ -2183,27 +2379,6 @@ static void ext3_free_branches(handle_t *handle, struct inode *inode, depth); /* - * We've probably journalled the indirect block several - * times during the truncate. But it's no longer - * needed and we now drop it from the transaction via - * journal_revoke(). - * - * That's easy if it's exclusively part of this - * transaction. But if it's part of the committing - * transaction then journal_forget() will simply - * brelse() it. That means that if the underlying - * block is reallocated in ext3_get_block(), - * unmap_underlying_metadata() will find this block - * and will try to get rid of it. damn, damn. - * - * If this block has already been committed to the - * journal, a revoke record will be written. And - * revoke records must be emitted *before* clearing - * this block's bit in the bitmaps. - */ - ext3_forget(handle, 1, inode, bh, bh->b_blocknr); - - /* * Everything below this this pointer has been * released. Now let this top-of-subtree go. * @@ -2223,9 +2398,34 @@ 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); } + /* + * We've probably journalled the indirect block several + * times during the truncate. But it's no longer + * needed and we now drop it from the transaction via + * journal_revoke(). + * + * That's easy if it's exclusively part of this + * transaction. But if it's part of the committing + * transaction then journal_forget() will simply + * brelse() it. That means that if the underlying + * block is reallocated in ext3_get_block(), + * unmap_underlying_metadata() will find this block + * and will try to get rid of it. damn, damn. Thus + * we don't allow a block to be reallocated until + * a transaction freeing it has fully committed. + * + * We also have to make sure journal replay after a + * crash does not overwrite non-journaled data blocks + * with old metadata when the block got reallocated for + * data. Thus we have to store a revoke record for a + * block in the same transaction in which we free the + * block. + */ + ext3_forget(handle, 1, inode, bh, bh->b_blocknr); + ext3_free_blocks(handle, inode, nr, 1); if (parent_bh) { @@ -2251,6 +2451,17 @@ static void ext3_free_branches(handle_t *handle, struct inode *inode, } } +int ext3_can_truncate(struct inode *inode) +{ + 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() * @@ -2258,7 +2469,7 @@ static void ext3_free_branches(handle_t *handle, struct inode *inode, * transaction, and VFS/VM ensures that ext3_truncate() cannot run * simultaneously on behalf of the same inode. * - * As we work through the truncate and commmit bits of it to the journal there + * As we work through the truncate and commit bits of it to the journal there * is one core, guiding principle: the file's tree must always be consistent on * disk. We must be able to restart the truncate after a crash. * @@ -2285,7 +2496,6 @@ void ext3_truncate(struct inode *inode) struct ext3_inode_info *ei = EXT3_I(inode); __le32 *i_data = ei->i_data; int addr_per_block = EXT3_ADDR_PER_BLOCK(inode->i_sb); - struct address_space *mapping = inode->i_mapping; int offsets[4]; Indirect chain[4]; Indirect *partial; @@ -2293,47 +2503,21 @@ void ext3_truncate(struct inode *inode) int n; long last_block; 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; + trace_ext3_truncate_enter(inode); - /* - * We have to lock the EOF page here, because lock_page() nests - * outside journal_start(). - */ - if ((inode->i_size & (blocksize - 1)) == 0) { - /* Block boundary? Nothing to do */ - page = NULL; - } else { - page = grab_cache_page(mapping, - inode->i_size >> PAGE_CACHE_SHIFT); - if (!page) - return; - } + if (!ext3_can_truncate(inode)) + goto out_notrans; + + if (inode->i_size == 0 && ext3_should_writeback_data(inode)) + ext3_set_inode_state(inode, EXT3_STATE_FLUSH_ON_CLOSE); handle = start_transaction(inode); - if (IS_ERR(handle)) { - if (page) { - clear_highpage(page); - flush_dcache_page(page); - unlock_page(page); - page_cache_release(page); - } - return; /* AKPM: return what? */ - } + if (IS_ERR(handle)) + goto out_notrans; last_block = (inode->i_size + blocksize-1) >> EXT3_BLOCK_SIZE_BITS(inode->i_sb); - - if (page) - ext3_block_truncate_page(handle, page, mapping, inode->i_size); - n = ext3_block_to_path(inode, last_block, offsets, NULL); if (n == 0) goto out_stop; /* error */ @@ -2385,7 +2569,6 @@ void ext3_truncate(struct inode *inode) */ } else { /* Shared branch grows from an indirect block */ - BUFFER_TRACE(partial->bh, "get_write_access"); ext3_free_branches(handle, inode, partial->bh, partial->p, partial->p+1, (chain+n-1) - partial); @@ -2442,23 +2625,32 @@ out_stop: * If this was a simple ftruncate(), and the file will remain alive * then we need to clear up the orphan record which we created above. * However, if this was a real unlink then we were called by - * ext3_delete_inode(), and we allow that function to clean up the + * ext3_evict_inode(), and we allow that function to clean up the * orphan info for us. */ if (inode->i_nlink) ext3_orphan_del(handle, inode); ext3_journal_stop(handle); + trace_ext3_truncate_exit(inode); + 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); + trace_ext3_truncate_exit(inode); } 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 block_group; unsigned long offset; ext3_fsblk_t block; - struct buffer_head *bh; - struct ext3_group_desc * gdp; + struct ext3_group_desc *gdp; if (!ext3_valid_inum(sb, ino)) { /* @@ -2470,27 +2662,15 @@ static ext3_fsblk_t ext3_get_inode_block(struct super_block *sb, } 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; @@ -2515,15 +2695,25 @@ static int __ext3_get_inode_loc(struct inode *inode, return -EIO; bh = sb_getblk(inode->i_sb, block); - if (!bh) { + if (unlikely(!bh)) { ext3_error (inode->i_sb, "ext3_get_inode_loc", "unable to read inode block - " "inode=%lu, block="E3FSBLK, inode->i_ino, block); - return -EIO; + return -ENOMEM; } 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); @@ -2559,7 +2749,7 @@ static int __ext3_get_inode_loc(struct inode *inode, bitmap_bh = sb_getblk(inode->i_sb, le32_to_cpu(desc->bg_inode_bitmap)); - if (!bitmap_bh) + if (unlikely(!bitmap_bh)) goto make_io; /* @@ -2593,9 +2783,10 @@ make_io: * has in-inode xattrs, or we don't have this inode in memory. * Read the block from disk. */ + trace_ext3_load_inode(inode); get_bh(bh); bh->b_end_io = end_buffer_read_sync; - submit_bh(READ_META, bh); + submit_bh(READ | REQ_META | REQ_PRIO, bh); wait_on_buffer(bh); if (!buffer_uptodate(bh)) { ext3_error(inode->i_sb, "ext3_get_inode_loc", @@ -2615,7 +2806,7 @@ int ext3_get_inode_loc(struct inode *inode, struct ext3_iloc *iloc) { /* We have all inode data except xattrs in memory here. */ return __ext3_get_inode_loc(inode, iloc, - !(EXT3_I(inode)->i_state & EXT3_STATE_XATTR)); + !ext3_test_inode_state(inode, EXT3_STATE_XATTR)); } void ext3_set_inode_flags(struct inode *inode) @@ -2661,8 +2852,12 @@ struct inode *ext3_iget(struct super_block *sb, unsigned long ino) 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; + uid_t i_uid; + gid_t i_gid; inode = iget_locked(sb, ino); if (!inode) @@ -2671,10 +2866,6 @@ struct inode *ext3_iget(struct super_block *sb, unsigned long ino) return inode; ei = EXT3_I(inode); -#ifdef CONFIG_EXT3_FS_POSIX_ACL - ei->i_acl = EXT3_ACL_NOT_CACHED; - ei->i_default_acl = EXT3_ACL_NOT_CACHED; -#endif ei->i_block_alloc_info = NULL; ret = __ext3_get_inode_loc(inode, &iloc, 0); @@ -2683,20 +2874,22 @@ struct inode *ext3_iget(struct super_block *sb, unsigned long ino) bh = iloc.bh; raw_inode = ext3_raw_inode(&iloc); inode->i_mode = le16_to_cpu(raw_inode->i_mode); - inode->i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low); - inode->i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low); + i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low); + i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low); if(!(test_opt (inode->i_sb, NO_UID32))) { - inode->i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16; - inode->i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16; + i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16; + i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16; } - inode->i_nlink = le16_to_cpu(raw_inode->i_links_count); + i_uid_write(inode, i_uid); + i_gid_write(inode, i_gid); + set_nlink(inode, le16_to_cpu(raw_inode->i_links_count)); inode->i_size = le32_to_cpu(raw_inode->i_size); 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; + ei->i_state_flags = 0; ei->i_dir_start_lookup = 0; ei->i_dtime = le32_to_cpu(raw_inode->i_dtime); /* We now have enough fields to check if the inode was active or not. @@ -2742,6 +2935,30 @@ struct inode *ext3_iget(struct super_block *sb, unsigned long ino) 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) { /* @@ -2765,7 +2982,7 @@ struct inode *ext3_iget(struct super_block *sb, unsigned long ino) EXT3_GOOD_OLD_INODE_SIZE + ei->i_extra_isize; if (*magic == cpu_to_le32(EXT3_XATTR_MAGIC)) - ei->i_state |= EXT3_STATE_XATTR; + ext3_set_inode_state(inode, EXT3_STATE_XATTR); } } else ei->i_extra_isize = 0; @@ -2778,9 +2995,11 @@ struct inode *ext3_iget(struct super_block *sb, unsigned long ino) 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); } @@ -2818,40 +3037,54 @@ static int ext3_do_update_inode(handle_t *handle, struct ext3_inode_info *ei = EXT3_I(inode); struct buffer_head *bh = iloc->bh; int err = 0, rc, block; + int need_datasync = 0; + __le32 disksize; + uid_t i_uid; + gid_t i_gid; + +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) + if (ext3_test_inode_state(inode, 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); + i_uid = i_uid_read(inode); + i_gid = i_gid_read(inode); if(!(test_opt(inode->i_sb, NO_UID32))) { - raw_inode->i_uid_low = cpu_to_le16(low_16_bits(inode->i_uid)); - raw_inode->i_gid_low = cpu_to_le16(low_16_bits(inode->i_gid)); + raw_inode->i_uid_low = cpu_to_le16(low_16_bits(i_uid)); + raw_inode->i_gid_low = cpu_to_le16(low_16_bits(i_gid)); /* * Fix up interoperability with old kernels. Otherwise, old inodes get * re-used with the upper 16 bits of the uid/gid intact */ if(!ei->i_dtime) { raw_inode->i_uid_high = - cpu_to_le16(high_16_bits(inode->i_uid)); + cpu_to_le16(high_16_bits(i_uid)); raw_inode->i_gid_high = - cpu_to_le16(high_16_bits(inode->i_gid)); + cpu_to_le16(high_16_bits(i_gid)); } else { raw_inode->i_uid_high = 0; raw_inode->i_gid_high = 0; } } else { raw_inode->i_uid_low = - cpu_to_le16(fs_high2lowuid(inode->i_uid)); + cpu_to_le16(fs_high2lowuid(i_uid)); raw_inode->i_gid_low = - cpu_to_le16(fs_high2lowgid(inode->i_gid)); + cpu_to_le16(fs_high2lowgid(i_gid)); raw_inode->i_uid_high = 0; raw_inode->i_gid_high = 0; } raw_inode->i_links_count = cpu_to_le16(inode->i_nlink); - raw_inode->i_size = cpu_to_le32(ei->i_disksize); + disksize = cpu_to_le32(ei->i_disksize); + if (disksize != raw_inode->i_size) { + need_datasync = 1; + raw_inode->i_size = disksize; + } raw_inode->i_atime = cpu_to_le32(inode->i_atime.tv_sec); raw_inode->i_ctime = cpu_to_le32(inode->i_ctime.tv_sec); raw_inode->i_mtime = cpu_to_le32(inode->i_mtime.tv_sec); @@ -2867,8 +3100,11 @@ static int ext3_do_update_inode(handle_t *handle, if (!S_ISREG(inode->i_mode)) { raw_inode->i_dir_acl = cpu_to_le32(ei->i_dir_acl); } else { - raw_inode->i_size_high = - cpu_to_le32(ei->i_disksize >> 32); + disksize = cpu_to_le32(ei->i_disksize >> 32); + if (disksize != raw_inode->i_size_high) { + raw_inode->i_size_high = disksize; + need_datasync = 1; + } if (ei->i_disksize > 0x7fffffffULL) { struct super_block *sb = inode->i_sb; if (!EXT3_HAS_RO_COMPAT_FEATURE(sb, @@ -2878,17 +3114,20 @@ 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; } } } @@ -2911,11 +3150,15 @@ 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; + ext3_clear_inode_state(inode, EXT3_STATE_NEW); + atomic_set(&ei->i_sync_tid, handle->h_transaction->t_tid); + if (need_datasync) + atomic_set(&ei->i_datasync_tid, handle->h_transaction->t_tid); out_brelse: brelse (bh); ext3_std_error(inode->i_sb, err); @@ -2927,21 +3170,20 @@ out_brelse: * * We are called from a few places: * - * - Within generic_file_write() for O_SYNC files. + * - Within generic_file_aio_write() -> generic_write_sync() for O_SYNC files. * Here, there will be no transaction running. We wait for any running - * trasnaction to commit. + * transaction to commit. * - * - Within sys_sync(), kupdate and such. - * We wait on commit, if tol to. + * - Within flush work (for sys_sync(), kupdate and such). + * We wait on commit, if told to. * - * - Within prune_icache() (PF_MEMALLOC == true) - * Here we simply return. We can't afford to block kswapd on the - * journal commit. + * - Within iput_final() -> write_inode_now() + * We wait on commit, if told to. * * In all cases it is actually safe for us to return without doing anything, * because the inode has been copied into a raw inode buffer in - * ext3_mark_inode_dirty(). This is a correctness thing for O_SYNC and for - * knfsd. + * ext3_mark_inode_dirty(). This is a correctness thing for WB_SYNC_ALL + * writeback. * * Note that we are absolutely dependent upon all inode dirtiers doing the * right thing: they *must* call mark_inode_dirty() after dirtying info in @@ -2953,13 +3195,13 @@ out_brelse: * stuff(); * inode->i_size = expr; * - * is in error because a kswapd-driven write_inode() could occur while - * `stuff()' is running, and the new i_size will be lost. Plus the inode - * will no longer be on the superblock's dirty inode list. + * is in error because write_inode() could occur while `stuff()' is running, + * and the new i_size will be lost. Plus the inode will no longer be on the + * superblock's dirty inode list. */ -int ext3_write_inode(struct inode *inode, int wait) +int ext3_write_inode(struct inode *inode, struct writeback_control *wbc) { - if (current->flags & PF_MEMALLOC) + if (WARN_ON_ONCE(current->flags & PF_MEMALLOC)) return 0; if (ext3_journal_current_handle()) { @@ -2968,7 +3210,12 @@ int ext3_write_inode(struct inode *inode, int wait) return -EIO; } - if (!wait) + /* + * No need to force transaction in WB_SYNC_NONE mode. Also + * ext3_sync_fs() will force the commit after everything is + * written. + */ + if (wbc->sync_mode != WB_SYNC_ALL || wbc->for_sync) return 0; return ext3_force_commit(inode->i_sb); @@ -3001,19 +3248,21 @@ int ext3_setattr(struct dentry *dentry, struct iattr *attr) if (error) return error; - if ((ia_valid & ATTR_UID && attr->ia_uid != inode->i_uid) || - (ia_valid & ATTR_GID && attr->ia_gid != inode->i_gid)) { + if (is_quota_modification(inode, attr)) + dquot_initialize(inode); + if ((ia_valid & ATTR_UID && !uid_eq(attr->ia_uid, inode->i_uid)) || + (ia_valid & ATTR_GID && !gid_eq(attr->ia_gid, inode->i_gid))) { handle_t *handle; /* (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 = dquot_transfer(inode, attr); if (error) { ext3_journal_stop(handle); return error; @@ -3028,6 +3277,9 @@ int ext3_setattr(struct dentry *dentry, struct iattr *attr) ext3_journal_stop(handle); } + if (attr->ia_valid & ATTR_SIZE) + inode_dio_wait(inode); + if (S_ISREG(inode->i_mode) && attr->ia_valid & ATTR_SIZE && attr->ia_size < inode->i_size) { handle_t *handle; @@ -3039,23 +3291,43 @@ int ext3_setattr(struct dentry *dentry, struct iattr *attr) } error = ext3_orphan_add(handle, inode); + if (error) { + ext3_journal_stop(handle); + goto err_out; + } EXT3_I(inode)->i_disksize = attr->ia_size; - rc = ext3_mark_inode_dirty(handle, inode); - if (!error) - error = rc; + error = ext3_mark_inode_dirty(handle, inode); ext3_journal_stop(handle); + if (error) { + /* Some hard fs error must have happened. Bail out. */ + ext3_orphan_del(NULL, inode); + goto err_out; + } + rc = ext3_block_truncate_page(inode, attr->ia_size); + if (rc) { + /* Cleanup orphan list and exit */ + handle = ext3_journal_start(inode, 3); + if (IS_ERR(handle)) { + ext3_orphan_del(NULL, inode); + goto err_out; + } + ext3_orphan_del(handle, inode); + ext3_journal_stop(handle); + goto err_out; + } } - rc = inode_setattr(inode, attr); + if ((attr->ia_valid & ATTR_SIZE) && + attr->ia_size != i_size_read(inode)) { + truncate_setsize(inode, attr->ia_size); + ext3_truncate(inode); + } - /* 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); + setattr_copy(inode, attr); + mark_inode_dirty(inode); - if (!rc && (ia_valid & ATTR_MODE)) - rc = ext3_acl_chmod(inode); + if (ia_valid & ATTR_MODE) + rc = posix_acl_chmod(inode, inode->i_mode); err_out: ext3_std_error(inode->i_sb, error); @@ -3101,12 +3373,12 @@ static int ext3_writepage_trans_blocks(struct inode *inode) if (ext3_should_journal_data(inode)) ret = 3 * (bpp + indirects) + 2; else - ret = 2 * (bpp + indirects) + 2; + ret = 2 * (bpp + indirects) + indirects + 2; #ifdef CONFIG_QUOTA - /* We know that structure was already allocated during DQUOT_INIT so + /* We know that structure was already allocated during dquot_initialize 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; @@ -3167,14 +3439,6 @@ ext3_reserve_inode_write(handle_t *handle, struct inode *inode, * inode out, but prune_icache isn't a user-visible syncing function. * Whenever the user wants stuff synced (sys_sync, sys_msync, sys_fsync) * we start and wait on commits. - * - * Is this efficient/effective? Well, we're being nice to the system - * by cleaning up our inodes proactively so they can be reaped - * without I/O. But we are potentially leaving up to five seconds' - * worth of inodes floating about which prune_icache wants us to - * write out. One way to fix that would be to get prune_icache() - * to do a write_super() to free up some memory. It has the desired - * effect. */ int ext3_mark_inode_dirty(handle_t *handle, struct inode *inode) { @@ -3182,6 +3446,7 @@ int ext3_mark_inode_dirty(handle_t *handle, struct inode *inode) int err; might_sleep(); + trace_ext3_mark_inode_dirty(inode, _RET_IP_); err = ext3_reserve_inode_write(handle, inode, &iloc); if (!err) err = ext3_mark_iloc_dirty(handle, inode, &iloc); @@ -3195,14 +3460,14 @@ 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, dquot_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 * so would cause a commit on atime updates, which we don't bother doing. * We handle synchronous inodes at the highest possible level. */ -void ext3_dirty_inode(struct inode *inode) +void ext3_dirty_inode(struct inode *inode, int flags) { handle_t *current_handle = ext3_journal_current_handle(); handle_t *handle; @@ -3214,7 +3479,7 @@ 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); |