From d47992f86b307985b3215bcf141d56d1849d71df Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Tue, 21 May 2013 23:17:23 -0400 Subject: mm: change invalidatepage prototype to accept length Currently there is no way to truncate partial page where the end truncate point is not at the end of the page. This is because it was not needed and the functionality was enough for file system truncate operation to work properly. However more file systems now support punch hole feature and it can benefit from mm supporting truncating page just up to the certain point. Specifically, with this functionality truncate_inode_pages_range() can be changed so it supports truncating partial page at the end of the range (currently it will BUG_ON() if 'end' is not at the end of the page). This commit changes the invalidatepage() address space operation prototype to accept range to be invalidated and update all the instances for it. We also change the block_invalidatepage() in the same way and actually make a use of the new length argument implementing range invalidation. Actual file system implementations will follow except the file systems where the changes are really simple and should not change the behaviour in any way .Implementation for truncate_page_range() which will be able to accept page unaligned ranges will follow as well. Signed-off-by: Lukas Czerner Cc: Andrew Morton Cc: Hugh Dickins --- fs/ext3/inode.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'fs/ext3') diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 23c712825640..b6e5934f5dd6 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -1825,7 +1825,8 @@ 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); -- cgit v1.2.3 From d8c8900ac113d2b2b3d382acda198b4ae29b1b51 Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Tue, 21 May 2013 23:26:36 -0400 Subject: jbd: change journal_invalidatepage() to accept length ->invalidatepage() aop now accepts range to invalidate so we can make use of it in journal_invalidatepage() and all the users in ext3 file system. Also update ext3 trace point to print out length argument. Signed-off-by: Lukas Czerner Reviewed-by: Jan Kara --- fs/ext3/inode.c | 6 +++--- fs/jbd/transaction.c | 19 ++++++++++++++----- include/linux/jbd.h | 2 +- include/trace/events/ext3.h | 12 +++++++----- 4 files changed, 25 insertions(+), 14 deletions(-) (limited to 'fs/ext3') diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index b6e5934f5dd6..f67668f724ba 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -1830,15 +1830,15 @@ static void ext3_invalidatepage(struct page *page, unsigned int offset, { journal_t *journal = EXT3_JOURNAL(page->mapping->host); - trace_ext3_invalidatepage(page, offset); + 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) diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c index e3e255c0a509..be0c39b66fe0 100644 --- a/fs/jbd/transaction.c +++ b/fs/jbd/transaction.c @@ -2019,16 +2019,20 @@ zap_buffer_unlocked: * void journal_invalidatepage() - invalidate a journal page * @journal: journal to use for flush * @page: page to flush - * @offset: length of page to invalidate. + * @offset: offset of the range to invalidate + * @length: length of the range to invalidate * - * Reap page buffers containing data after offset in page. + * Reap page buffers containing data in specified range in page. */ void journal_invalidatepage(journal_t *journal, struct page *page, - unsigned long offset) + unsigned int offset, + unsigned int length) { struct buffer_head *head, *bh, *next; + unsigned int stop = offset + length; unsigned int curr_off = 0; + int partial_page = (offset || length < PAGE_CACHE_SIZE); int may_free = 1; if (!PageLocked(page)) @@ -2036,6 +2040,8 @@ void journal_invalidatepage(journal_t *journal, if (!page_has_buffers(page)) return; + BUG_ON(stop > PAGE_CACHE_SIZE || stop < length); + /* We will potentially be playing with lists other than just the * data lists (especially for journaled data mode), so be * cautious in our locking. */ @@ -2045,11 +2051,14 @@ void journal_invalidatepage(journal_t *journal, unsigned int next_off = curr_off + bh->b_size; next = bh->b_this_page; + if (next_off > stop) + return; + if (offset <= curr_off) { /* This block is wholly outside the truncation point */ lock_buffer(bh); may_free &= journal_unmap_buffer(journal, bh, - offset > 0); + partial_page); unlock_buffer(bh); } curr_off = next_off; @@ -2057,7 +2066,7 @@ void journal_invalidatepage(journal_t *journal, } while (bh != head); - if (!offset) { + if (!partial_page) { if (may_free && try_to_free_buffers(page)) J_ASSERT(!page_has_buffers(page)); } diff --git a/include/linux/jbd.h b/include/linux/jbd.h index 7e0b622503c4..9c505f1aa1fd 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -840,7 +840,7 @@ extern void journal_release_buffer (handle_t *, struct buffer_head *); extern int journal_forget (handle_t *, struct buffer_head *); extern void journal_sync_buffer (struct buffer_head *); extern void journal_invalidatepage(journal_t *, - struct page *, unsigned long); + struct page *, unsigned int, unsigned int); extern int journal_try_to_free_buffers(journal_t *, struct page *, gfp_t); extern int journal_stop(handle_t *); extern int journal_flush (journal_t *); diff --git a/include/trace/events/ext3.h b/include/trace/events/ext3.h index 15d11a39be47..6797b9de90ed 100644 --- a/include/trace/events/ext3.h +++ b/include/trace/events/ext3.h @@ -290,13 +290,14 @@ DEFINE_EVENT(ext3__page_op, ext3_releasepage, ); TRACE_EVENT(ext3_invalidatepage, - TP_PROTO(struct page *page, unsigned long offset), + TP_PROTO(struct page *page, unsigned int offset, unsigned int length), - TP_ARGS(page, offset), + TP_ARGS(page, offset, length), TP_STRUCT__entry( __field( pgoff_t, index ) - __field( unsigned long, offset ) + __field( unsigned int, offset ) + __field( unsigned int, length ) __field( ino_t, ino ) __field( dev_t, dev ) @@ -305,14 +306,15 @@ TRACE_EVENT(ext3_invalidatepage, TP_fast_assign( __entry->index = page->index; __entry->offset = offset; + __entry->length = length; __entry->ino = page->mapping->host->i_ino; __entry->dev = page->mapping->host->i_sb->s_dev; ), - TP_printk("dev %d,%d ino %lu page_index %lu offset %lu", + TP_printk("dev %d,%d ino %lu page_index %lu offset %u length %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, - __entry->index, __entry->offset) + __entry->index, __entry->offset, __entry->length) ); TRACE_EVENT(ext3_discard_blocks, -- cgit v1.2.3 From 64cb927371cd2ec43758d8a094a003d27bc3d0dc Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 1 Jul 2013 08:12:38 -0400 Subject: ext3,ext4: don't mess with dir_file->f_pos in htree_dirblock_to_tree() Both ext3 and ext4 htree_dirblock_to_tree() is just filling the in-core rbtree for use by call_filldir(). All updates of ->f_pos are done by the latter; bumping it here (on error) is obviously wrong - we might very well have it nowhere near the block we'd found an error in. Signed-off-by: Al Viro Signed-off-by: "Theodore Ts'o" Cc: stable@vger.kernel.org --- fs/ext3/namei.c | 7 ++----- fs/ext4/namei.c | 7 ++----- 2 files changed, 4 insertions(+), 10 deletions(-) (limited to 'fs/ext3') diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index 692de13e3596..cea8ecf3e76e 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -576,11 +576,8 @@ static int htree_dirblock_to_tree(struct file *dir_file, if (!ext3_check_dir_entry("htree_dirblock_to_tree", dir, de, bh, (block<i_sb)) +((char *)de - bh->b_data))) { - /* On error, skip the f_pos to the next block. */ - dir_file->f_pos = (dir_file->f_pos | - (dir->i_sb->s_blocksize - 1)) + 1; - brelse (bh); - return count; + /* silently ignore the rest of the block */ + break; } ext3fs_dirhash(de->name, de->name_len, hinfo); if ((hinfo->hash < start_hash) || diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 6653fc35ecb7..ab2f6dc44b3a 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -918,11 +918,8 @@ static int htree_dirblock_to_tree(struct file *dir_file, bh->b_data, bh->b_size, (block<i_sb)) + ((char *)de - bh->b_data))) { - /* On error, skip the f_pos to the next block. */ - dir_file->f_pos = (dir_file->f_pos | - (dir->i_sb->s_blocksize - 1)) + 1; - brelse(bh); - return count; + /* silently ignore the rest of the block */ + break; } ext4fs_dirhash(de->name, de->name_len, hinfo); if ((hinfo->hash < start_hash) || -- cgit v1.2.3