Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
  jbd2: fix race between write_metadata_buffer and get_write_access
  ext4: Fix ext4_mb_initialize_context() to initialize all fields
  ext4: fix null handler of ioctls in no journal mode
  ext4: Fix buffer head reference leak in no-journal mode
  ext4: Move __ext4_journalled_writepage() to avoid forward declaration
  ext4: Fix mmap/truncate race when blocksize < pagesize && !nodellaoc
  ext4: Fix mmap/truncate race when blocksize < pagesize && delayed allocation
  ext4: Don't look at buffer_heads outside i_size.
  ext4: Fix goal inum check in the inode allocator
  ext4: fix no journal corruption with locale-gen
  ext4: Calculate required journal credits for inserting an extent properly
  ext4: Fix truncation of symlinks after failed write
  jbd2: Fix a race between checkpointing code and journal_get_write_access()
  ext4: Use rcu_barrier() on module unload.
  ext4: naturally align struct ext4_allocation_request
  ext4: mark several more functions in mballoc.c as noinline
  ext4: Fix potential reclaim deadlock when truncating partial block
  jbd2: Remove GFP_ATOMIC kmalloc from inside spinlock critical region
  ext4: Fix type warning on 64-bit platforms in tracing events header

fs/ext4/ext4.h

@@ -93,20 +93,20 @@ typedef unsigned int ext4_group_t;
 struct ext4_allocation_request {
 	/* target inode for block we're allocating */
 	struct inode *inode;
+	/* how many blocks we want to allocate */
+	unsigned int len;
 	/* logical block in target inode */
 	ext4_lblk_t logical;
-	/* phys. target (a hint) */
-	ext4_fsblk_t goal;
 	/* the closest logical allocated block to the left */
 	ext4_lblk_t lleft;
-	/* phys. block for ^^^ */
-	ext4_fsblk_t pleft;
 	/* the closest logical allocated block to the right */
 	ext4_lblk_t lright;
-	/* phys. block for ^^^ */
+	/* phys. target (a hint) */
+	ext4_fsblk_t goal;
+	/* phys. block for the closest logical allocated block to the left */
+	ext4_fsblk_t pleft;
+	/* phys. block for the closest logical allocated block to the right */
 	ext4_fsblk_t pright;
-	/* how many blocks we want to allocate */
-	unsigned int len;
 	/* flags. see above EXT4_MB_HINT_* */
 	unsigned int flags;
 };

fs/ext4/ext4_jbd2.c

@@ -43,6 +43,8 @@ int __ext4_journal_forget(const char *where, handle_t *handle,
 			ext4_journal_abort_handle(where, __func__, bh,
 						  handle, err);
 	}
+	else
+		brelse(bh);
 	return err;
 }
 
@@ -57,6 +59,8 @@ int __ext4_journal_revoke(const char *where, handle_t *handle,
 			ext4_journal_abort_handle(where, __func__, bh,
 						  handle, err);
 	}
+	else
+		brelse(bh);
 	return err;
 }
 

fs/ext4/ext4_jbd2.h

@@ -131,9 +131,11 @@ int __ext4_journal_get_undo_access(const char *where, handle_t *handle,
 int __ext4_journal_get_write_access(const char *where, handle_t *handle,
 				struct buffer_head *bh);
 
+/* When called with an invalid handle, this will still do a put on the BH */
 int __ext4_journal_forget(const char *where, handle_t *handle,
 				struct buffer_head *bh);
 
+/* When called with an invalid handle, this will still do a put on the BH */
 int __ext4_journal_revoke(const char *where, handle_t *handle,
 				ext4_fsblk_t blocknr, struct buffer_head *bh);
 
@@ -281,10 +283,10 @@ static inline int ext4_should_order_data(struct inode *inode)
 
 static inline int ext4_should_writeback_data(struct inode *inode)
 {
-	if (EXT4_JOURNAL(inode) == NULL)
-		return 0;
 	if (!S_ISREG(inode->i_mode))
 		return 0;
+	if (EXT4_JOURNAL(inode) == NULL)
+		return 1;
 	if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL)
 		return 0;
 	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)

fs/ext4/extents.c

@@ -1977,6 +1977,7 @@ int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int nrblocks,
 			 */
 			/* 1 bitmap, 1 block group descriptor */
 			ret = 2 + EXT4_META_TRANS_BLOCKS(inode->i_sb);
+			return ret;
 		}
 	}
 

fs/ext4/ialloc.c

@@ -833,7 +833,7 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode,
 	if (!goal)
 		goal = sbi->s_inode_goal;
 
-	if (goal && goal < le32_to_cpu(sbi->s_es->s_inodes_count)) {
+	if (goal && goal <= le32_to_cpu(sbi->s_es->s_inodes_count)) {
 		group = (goal - 1) / EXT4_INODES_PER_GROUP(sb);
 		ino = (goal - 1) % EXT4_INODES_PER_GROUP(sb);
 		ret2 = 0;

fs/ext4/inode.c

@@ -78,16 +78,14 @@ static int ext4_inode_is_fast_symlink(struct inode *inode)
  * but there may still be a record of it in the journal, and that record
  * still needs to be revoked.
  *
- * If the handle isn't valid we're not journaling so there's nothing to do.
+ * If the handle isn't valid we're not journaling, but we still need to
+ * call into ext4_journal_revoke() to put the buffer head.
  */
 int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode,
 		struct buffer_head *bh, ext4_fsblk_t blocknr)
 {
 	int err;
 
-	if (!ext4_handle_valid(handle))
-		return 0;
-
 	might_sleep();
 
 	BUFFER_TRACE(bh, "enter");
@@ -1513,14 +1511,14 @@ retry:
 		 * Add inode to orphan list in case we crash before
 		 * truncate finishes
 		 */
-		if (pos + len > inode->i_size)
+		if (pos + len > inode->i_size && ext4_can_truncate(inode))
 			ext4_orphan_add(handle, inode);
 
 		ext4_journal_stop(handle);
 		if (pos + len > inode->i_size) {
-			vmtruncate(inode, inode->i_size);
+			ext4_truncate(inode);
 			/*
-			 * If vmtruncate failed early the inode might
+			 * If truncate failed early the inode might
 			 * still be on the orphan list; we need to
 			 * make sure the inode is removed from the
 			 * orphan list in that case.
@@ -1614,7 +1612,7 @@ static int ext4_ordered_write_end(struct file *file,
 		ret2 = ext4_generic_write_end(file, mapping, pos, len, copied,
 							page, fsdata);
 		copied = ret2;
-		if (pos + len > inode->i_size)
+		if (pos + len > inode->i_size && ext4_can_truncate(inode))
 			/* if we have allocated more blocks and copied
 			 * less. We will have blocks allocated outside
 			 * inode->i_size. So truncate them
@@ -1628,9 +1626,9 @@ static int ext4_ordered_write_end(struct file *file,
 		ret = ret2;
 
 	if (pos + len > inode->i_size) {
-		vmtruncate(inode, inode->i_size);
+		ext4_truncate(inode);
 		/*
-		 * If vmtruncate failed early the inode might still be
+		 * If truncate failed early the inode might still be
 		 * on the orphan list; we need to make sure the inode
 		 * is removed from the orphan list in that case.
 		 */
@@ -1655,7 +1653,7 @@ static int ext4_writeback_write_end(struct file *file,
 	ret2 = ext4_generic_write_end(file, mapping, pos, len, copied,
 							page, fsdata);
 	copied = ret2;
-	if (pos + len > inode->i_size)
+	if (pos + len > inode->i_size && ext4_can_truncate(inode))
 		/* if we have allocated more blocks and copied
 		 * less. We will have blocks allocated outside
 		 * inode->i_size. So truncate them
@@ -1670,9 +1668,9 @@ static int ext4_writeback_write_end(struct file *file,
 		ret = ret2;
 
 	if (pos + len > inode->i_size) {
-		vmtruncate(inode, inode->i_size);
+		ext4_truncate(inode);
 		/*
-		 * If vmtruncate failed early the inode might still be
+		 * If truncate failed early the inode might still be
 		 * on the orphan list; we need to make sure the inode
 		 * is removed from the orphan list in that case.
 		 */
@@ -1722,7 +1720,7 @@ static int ext4_journalled_write_end(struct file *file,
 
 	unlock_page(page);
 	page_cache_release(page);
-	if (pos + len > inode->i_size)
+	if (pos + len > inode->i_size && ext4_can_truncate(inode))
 		/* if we have allocated more blocks and copied
 		 * less. We will have blocks allocated outside
 		 * inode->i_size. So truncate them
@@ -1733,9 +1731,9 @@ static int ext4_journalled_write_end(struct file *file,
 	if (!ret)
 		ret = ret2;
 	if (pos + len > inode->i_size) {
-		vmtruncate(inode, inode->i_size);
+		ext4_truncate(inode);
 		/*
-		 * If vmtruncate failed early the inode might still be
+		 * If truncate failed early the inode might still be
 		 * on the orphan list; we need to make sure the inode
 		 * is removed from the orphan list in that case.
 		 */
@@ -2305,15 +2303,9 @@ flush_it:
 	return;
 }
 
-static int ext4_bh_unmapped_or_delay(handle_t *handle, struct buffer_head *bh)
+static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh)
 {
-	/*
-	 * unmapped buffer is possible for holes.
-	 * delay buffer is possible with delayed allocation.
-	 * We also need to consider unwritten buffer as unmapped.
-	 */
-	return (!buffer_mapped(bh) || buffer_delay(bh) ||
-				buffer_unwritten(bh)) && buffer_dirty(bh);
+	return (buffer_delay(bh) || buffer_unwritten(bh)) && buffer_dirty(bh);
 }
 
 /*
@@ -2398,9 +2390,9 @@ static int __mpage_da_writepage(struct page *page,
 			 * We need to try to allocate
 			 * unmapped blocks in the same page.
 			 * Otherwise we won't make progress
-			 * with the page in ext4_da_writepage
+			 * with the page in ext4_writepage
 			 */
-			if (ext4_bh_unmapped_or_delay(NULL, bh)) {
+			if (ext4_bh_delay_or_unwritten(NULL, bh)) {
 				mpage_add_bh_to_extent(mpd, logical,
 						       bh->b_size,
 						       bh->b_state);
@@ -2517,7 +2509,6 @@ static int noalloc_get_block_write(struct inode *inode, sector_t iblock,
 	 * so call get_block_wrap with create = 0
 	 */
 	ret = ext4_get_blocks(NULL, inode, iblock, max_blocks, bh_result, 0);
-	BUG_ON(create && ret == 0);
 	if (ret > 0) {
 		bh_result->b_size = (ret << inode->i_blkbits);
 		ret = 0;
@@ -2525,14 +2516,101 @@ static int noalloc_get_block_write(struct inode *inode, sector_t iblock,
 	return ret;
 }
 
+static int bget_one(handle_t *handle, struct buffer_head *bh)
+{
+	get_bh(bh);
+	return 0;
+}
+
+static int bput_one(handle_t *handle, struct buffer_head *bh)
+{
+	put_bh(bh);
+	return 0;
+}
+
+static int __ext4_journalled_writepage(struct page *page,
+				       struct writeback_control *wbc,
+				       unsigned int len)
+{
+	struct address_space *mapping = page->mapping;
+	struct inode *inode = mapping->host;
+	struct buffer_head *page_bufs;
+	handle_t *handle = NULL;
+	int ret = 0;
+	int err;
+
+	page_bufs = page_buffers(page);
+	BUG_ON(!page_bufs);
+	walk_page_buffers(handle, page_bufs, 0, len, NULL, bget_one);
+	/* As soon as we unlock the page, it can go away, but we have
+	 * references to buffers so we are safe */
+	unlock_page(page);
+
+	handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode));
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		goto out;
+	}
+
+	ret = walk_page_buffers(handle, page_bufs, 0, len, NULL,
+				do_journal_get_write_access);
+
+	err = walk_page_buffers(handle, page_bufs, 0, len, NULL,
+				write_end_fn);
+	if (ret == 0)
+		ret = err;
+	err = ext4_journal_stop(handle);
+	if (!ret)
+		ret = err;
+
+	walk_page_buffers(handle, page_bufs, 0, len, NULL, bput_one);
+	EXT4_I(inode)->i_state |= EXT4_STATE_JDATA;
+out:
+	return ret;
+}
+
 /*
+ * Note that we don't need to start a transaction unless we're journaling data
+ * because we should have holes filled from ext4_page_mkwrite(). We even don't
+ * need to file the inode to the transaction's list in ordered mode because if
+ * we are writing back data added by write(), the inode is already there and if
+ * we are writing back data modified via mmap(), noone guarantees in which
+ * transaction the data will hit the disk. In case we are journaling data, we
+ * cannot start transaction directly because transaction start ranks above page
+ * lock so we have to do some magic.
+ *
  * This function can get called via...
  *   - ext4_da_writepages after taking page lock (have journal handle)
  *   - journal_submit_inode_data_buffers (no journal handle)
  *   - shrink_page_list via pdflush (no journal handle)
  *   - grab_page_cache when doing write_begin (have journal handle)
+ *
+ * We don't do any block allocation in this function. If we have page with
+ * multiple blocks we need to write those buffer_heads that are mapped. This
+ * is important for mmaped based write. So if we do with blocksize 1K
+ * truncate(f, 1024);
+ * a = mmap(f, 0, 4096);
+ * a[0] = 'a';
+ * truncate(f, 4096);
+ * we have in the page first buffer_head mapped via page_mkwrite call back
+ * but other bufer_heads would be unmapped but dirty(dirty done via the
+ * do_wp_page). So writepage should write the first block. If we modify
+ * the mmap area beyond 1024 we will again get a page_fault and the
+ * page_mkwrite callback will do the block allocation and mark the
+ * buffer_heads mapped.
+ *
+ * We redirty the page if we have any buffer_heads that is either delay or
+ * unwritten in the page.
+ *
+ * We can get recursively called as show below.
+ *
+ *	ext4_writepage() -> kmalloc() -> __alloc_pages() -> page_launder() ->
+ *		ext4_writepage()
+ *
+ * But since we don't do any block allocation we should not deadlock.
+ * Page also have the dirty flag cleared so we don't get recurive page_lock.
  */
-static int ext4_da_writepage(struct page *page,
+static int ext4_writepage(struct page *page,
 			  struct writeback_control *wbc)
 {
 	int ret = 0;
@@ -2541,7 +2619,7 @@ static int ext4_da_writepage(struct page *page,
 	struct buffer_head *page_bufs;
 	struct inode *inode = page->mapping->host;
 
-	trace_ext4_da_writepage(inode, page);
+	trace_ext4_writepage(inode, page);
 	size = i_size_read(inode);
 	if (page->index == size >> PAGE_CACHE_SHIFT)
 		len = size & ~PAGE_CACHE_MASK;
@@ -2551,7 +2629,7 @@ static int ext4_da_writepage(struct page *page,
 	if (page_has_buffers(page)) {
 		page_bufs = page_buffers(page);
 		if (walk_page_buffers(NULL, page_bufs, 0, len, NULL,
-					ext4_bh_unmapped_or_delay)) {
+					ext4_bh_delay_or_unwritten)) {
 			/*
 			 * We don't want to do  block allocation
 			 * So redirty the page and return
@@ -2578,13 +2656,13 @@ static int ext4_da_writepage(struct page *page,
 		 * all are mapped and non delay. We don't want to
 		 * do block allocation here.
 		 */
-		ret = block_prepare_write(page, 0, PAGE_CACHE_SIZE,
+		ret = block_prepare_write(page, 0, len,
 					  noalloc_get_block_write);
 		if (!ret) {
 			page_bufs = page_buffers(page);
 			/* check whether all are mapped and non delay */
 			if (walk_page_buffers(NULL, page_bufs, 0, len, NULL,
-						ext4_bh_unmapped_or_delay)) {
+						ext4_bh_delay_or_unwritten)) {
 				redirty_page_for_writepage(wbc, page);
 				unlock_page(page);
 				return 0;
@@ -2600,7 +2678,16 @@ static int ext4_da_writepage(struct page *page,
 			return 0;
 		}
 		/* now mark the buffer_heads as dirty and uptodate */
-		block_commit_write(page, 0, PAGE_CACHE_SIZE);
+		block_commit_write(page, 0, len);
+	}
+
+	if (PageChecked(page) && ext4_should_journal_data(inode)) {
+		/*
+		 * It's mmapped pagecache.  Add buffers and journal it.  There
+		 * doesn't seem much point in redirtying the page here.
+		 */
+		ClearPageChecked(page);
+		return __ext4_journalled_writepage(page, wbc, len);
 	}
 
 	if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode))
@@ -2907,7 +2994,7 @@ retry:
 		 * i_size_read because we hold i_mutex.
 		 */
 		if (pos + len > inode->i_size)
-			vmtruncate(inode, inode->i_size);
+			ext4_truncate(inode);
 	}
 
 	if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
@@ -3130,222 +3217,6 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block)
 	return generic_block_bmap(mapping, block, ext4_get_block);
 }
 
-static int bget_one(handle_t *handle, struct buffer_head *bh)
-{
-	get_bh(bh);
-	return 0;
-}
-
-static int bput_one(handle_t *handle, struct buffer_head *bh)
-{
-	put_bh(bh);
-	return 0;
-}
-
-/*
- * Note that we don't need to start a transaction unless we're journaling data
- * because we should have holes filled from ext4_page_mkwrite(). We even don't
- * need to file the inode to the transaction's list in ordered mode because if
- * we are writing back data added by write(), the inode is already there and if
- * we are writing back data modified via mmap(), noone guarantees in which
- * transaction the data will hit the disk. In case we are journaling data, we
- * cannot start transaction directly because transaction start ranks above page
- * lock so we have to do some magic.
- *
- * In all journaling modes block_write_full_page() will start the I/O.
- *
- * Problem:
- *
- *	ext4_writepage() -> kmalloc() -> __alloc_pages() -> page_launder() ->
- *		ext4_writepage()
- *
- * Similar for:
- *
- *	ext4_file_write() -> generic_file_write() -> __alloc_pages() -> ...
- *
- * Same applies to ext4_get_block().  We will deadlock on various things like
- * lock_journal and i_data_sem
- *
- * 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.
- *
- */
-static int __ext4_normal_writepage(struct page *page,
-				   struct writeback_control *wbc)
-{
-	struct inode *inode = page->mapping->host;
-
-	if (test_opt(inode->i_sb, NOBH))
-		return nobh_writepage(page, noalloc_get_block_write, wbc);
-	else
-		return block_write_full_page(page, noalloc_get_block_write,
-					     wbc);
-}
-
-static int ext4_normal_writepage(struct page *page,
-				 struct writeback_control *wbc)
-{
-	struct inode *inode = page->mapping->host;
-	loff_t size = i_size_read(inode);
-	loff_t len;
-
-	trace_ext4_normal_writepage(inode, page);
-	J_ASSERT(PageLocked(page));
-	if (page->index == size >> PAGE_CACHE_SHIFT)
-		len = size & ~PAGE_CACHE_MASK;
-	else
-		len = PAGE_CACHE_SIZE;
-
-	if (page_has_buffers(page)) {
-		/* if page has buffers it should all be mapped
-		 * and allocated. If there are not buffers attached
-		 * to the page we know the page is dirty but it lost
-		 * buffers. That means that at some moment in time
-		 * after write_begin() / write_end() has been called
-		 * all buffers have been clean and thus they must have been
-		 * written at least once. So they are all mapped and we can
-		 * happily proceed with mapping them and writing the page.
-		 */
-		BUG_ON(walk_page_buffers(NULL, page_buffers(page), 0, len, NULL,
-					ext4_bh_unmapped_or_delay));
-	}
-
-	if (!ext4_journal_current_handle())
-		return __ext4_normal_writepage(page, wbc);
-
-	redirty_page_for_writepage(wbc, page);
-	unlock_page(page);
-	return 0;
-}
-
-static int __ext4_journalled_writepage(struct page *page,
-				       struct writeback_control *wbc)
-{
-	struct address_space *mapping = page->mapping;
-	struct inode *inode = mapping->host;
-	struct buffer_head *page_bufs;
-	handle_t *handle = NULL;
-	int ret = 0;
-	int err;
-
-	ret = block_prepare_write(page, 0, PAGE_CACHE_SIZE,
-				  noalloc_get_block_write);
-	if (ret != 0)
-		goto out_unlock;
-
-	page_bufs = page_buffers(page);
-	walk_page_buffers(handle, page_bufs, 0, PAGE_CACHE_SIZE, NULL,
-								bget_one);
-	/* As soon as we unlock the page, it can go away, but we have
-	 * references to buffers so we are safe */
-	unlock_page(page);
-
-	handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode));
-	if (IS_ERR(handle)) {
-		ret = PTR_ERR(handle);
-		goto out;
-	}
-
-	ret = walk_page_buffers(handle, page_bufs, 0,
-			PAGE_CACHE_SIZE, NULL, do_journal_get_write_access);
-
-	err = walk_page_buffers(handle, page_bufs, 0,
-				PAGE_CACHE_SIZE, NULL, write_end_fn);
-	if (ret == 0)
-		ret = err;
-	err = ext4_journal_stop(handle);
-	if (!ret)
-		ret = err;
-
-	walk_page_buffers(handle, page_bufs, 0,
-				PAGE_CACHE_SIZE, NULL, bput_one);
-	EXT4_I(inode)->i_state |= EXT4_STATE_JDATA;
-	goto out;
-
-out_unlock:
-	unlock_page(page);
-out:
-	return ret;
-}
-
-static int ext4_journalled_writepage(struct page *page,
-				     struct writeback_control *wbc)
-{
-	struct inode *inode = page->mapping->host;
-	loff_t size = i_size_read(inode);
-	loff_t len;
-
-	trace_ext4_journalled_writepage(inode, page);
-	J_ASSERT(PageLocked(page));
-	if (page->index == size >> PAGE_CACHE_SHIFT)
-		len = size & ~PAGE_CACHE_MASK;
-	else
-		len = PAGE_CACHE_SIZE;
-
-	if (page_has_buffers(page)) {
-		/* if page has buffers it should all be mapped
-		 * and allocated. If there are not buffers attached
-		 * to the page we know the page is dirty but it lost
-		 * buffers. That means that at some moment in time
-		 * after write_begin() / write_end() has been called
-		 * all buffers have been clean and thus they must have been
-		 * written at least once. So they are all mapped and we can
-		 * happily proceed with mapping them and writing the page.
-		 */
-		BUG_ON(walk_page_buffers(NULL, page_buffers(page), 0, len, NULL,
-					ext4_bh_unmapped_or_delay));
-	}
-
-	if (ext4_journal_current_handle())
-		goto no_write;
-
-	if (PageChecked(page)) {
-		/*
-		 * It's mmapped pagecache.  Add buffers and journal it.  There
-		 * doesn't seem much point in redirtying the page here.
-		 */
-		ClearPageChecked(page);
-		return __ext4_journalled_writepage(page, wbc);
-	} 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.
-		 */
-		return block_write_full_page(page, noalloc_get_block_write,
-					     wbc);
-	}
-no_write:
-	redirty_page_for_writepage(wbc, page);
-	unlock_page(page);
-	return 0;
-}
-
 static int ext4_readpage(struct file *file, struct page *page)
 {
 	return mpage_readpage(page, ext4_get_block);
@@ -3492,7 +3363,7 @@ static int ext4_journalled_set_page_dirty(struct page *page)
 static const struct address_space_operations ext4_ordered_aops = {
 	.readpage		= ext4_readpage,
 	.readpages		= ext4_readpages,
-	.writepage		= ext4_normal_writepage,
+	.writepage		= ext4_writepage,
 	.sync_page		= block_sync_page,
 	.write_begin		= ext4_write_begin,
 	.write_end		= ext4_ordered_write_end,
@@ -3507,7 +3378,7 @@ static const struct address_space_operations ext4_ordered_aops = {
 static const struct address_space_operations ext4_writeback_aops = {
 	.readpage		= ext4_readpage,
 	.readpages		= ext4_readpages,
-	.writepage		= ext4_normal_writepage,
+	.writepage		= ext4_writepage,
 	.sync_page		= block_sync_page,
 	.write_begin		= ext4_write_begin,
 	.write_end		= ext4_writeback_write_end,
@@ -3522,7 +3393,7 @@ static const struct address_space_operations ext4_writeback_aops = {
 static const struct address_space_operations ext4_journalled_aops = {
 	.readpage		= ext4_readpage,
 	.readpages		= ext4_readpages,
-	.writepage		= ext4_journalled_writepage,
+	.writepage		= ext4_writepage,
 	.sync_page		= block_sync_page,
 	.write_begin		= ext4_write_begin,
 	.write_end		= ext4_journalled_write_end,
@@ -3536,7 +3407,7 @@ static const struct address_space_operations ext4_journalled_aops = {
 static const struct address_space_operations ext4_da_aops = {
 	.readpage		= ext4_readpage,
 	.readpages		= ext4_readpages,
-	.writepage		= ext4_da_writepage,
+	.writepage		= ext4_writepage,
 	.writepages		= ext4_da_writepages,
 	.sync_page		= block_sync_page,
 	.write_begin		= ext4_da_write_begin,
@@ -3583,7 +3454,8 @@ int ext4_block_truncate_page(handle_t *handle,
 	struct page *page;
 	int err = 0;
 
-	page = grab_cache_page(mapping, from >> PAGE_CACHE_SHIFT);
+	page = find_or_create_page(mapping, from >> PAGE_CACHE_SHIFT,
+				   mapping_gfp_mask(mapping) & ~__GFP_FS);
 	if (!page)
 		return -EINVAL;
 

fs/ext4/ioctl.c

@@ -191,7 +191,7 @@ setversion_out:
 	case EXT4_IOC_GROUP_EXTEND: {
 		ext4_fsblk_t n_blocks_count;
 		struct super_block *sb = inode->i_sb;
-		int err, err2;
+		int err, err2=0;
 
 		if (!capable(CAP_SYS_RESOURCE))
 			return -EPERM;
@@ -204,9 +204,11 @@ setversion_out:
 			return err;
 
 		err = ext4_group_extend(sb, EXT4_SB(sb)->s_es, n_blocks_count);
+		if (EXT4_SB(sb)->s_journal) {
 			jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
 			err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
 			jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
+		}
 		if (err == 0)
 			err = err2;
 		mnt_drop_write(filp->f_path.mnt);
@@ -251,7 +253,7 @@ setversion_out:
 	case EXT4_IOC_GROUP_ADD: {
 		struct ext4_new_group_data input;
 		struct super_block *sb = inode->i_sb;
-		int err, err2;
+		int err, err2=0;
 
 		if (!capable(CAP_SYS_RESOURCE))
 			return -EPERM;
@@ -265,9 +267,11 @@ setversion_out:
 			return err;
 
 		err = ext4_group_add(sb, &input);
+		if (EXT4_SB(sb)->s_journal) {
 			jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
 			err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
 			jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
+		}
 		if (err == 0)
 			err = err2;
 		mnt_drop_write(filp->f_path.mnt);

fs/ext4/mballoc.c

@@ -657,7 +657,8 @@ static void ext4_mb_mark_free_simple(struct super_block *sb,
 	}
 }
 
-static void ext4_mb_generate_buddy(struct super_block *sb,
+static noinline_for_stack
+void ext4_mb_generate_buddy(struct super_block *sb,
 				void *buddy, void *bitmap, ext4_group_t group)
 {
 	struct ext4_group_info *grp = ext4_get_group_info(sb, group);
@@ -1480,7 +1481,8 @@ static void ext4_mb_measure_extent(struct ext4_allocation_context *ac,
 	ext4_mb_check_limits(ac, e4b, 0);
 }
 
-static int ext4_mb_try_best_found(struct ext4_allocation_context *ac,
+static noinline_for_stack
+int ext4_mb_try_best_found(struct ext4_allocation_context *ac,
 					struct ext4_buddy *e4b)
 {
 	struct ext4_free_extent ex = ac->ac_b_ex;
@@ -1507,7 +1509,8 @@ static int ext4_mb_try_best_found(struct ext4_allocation_context *ac,
 	return 0;
 }
 
-static int ext4_mb_find_by_goal(struct ext4_allocation_context *ac,
+static noinline_for_stack
+int ext4_mb_find_by_goal(struct ext4_allocation_context *ac,
 				struct ext4_buddy *e4b)
 {
 	ext4_group_t group = ac->ac_g_ex.fe_group;
@@ -1566,7 +1569,8 @@ static int ext4_mb_find_by_goal(struct ext4_allocation_context *ac,
  * The routine scans buddy structures (not bitmap!) from given order
  * to max order and tries to find big enough chunk to satisfy the req
  */
-static void ext4_mb_simple_scan_group(struct ext4_allocation_context *ac,
+static noinline_for_stack
+void ext4_mb_simple_scan_group(struct ext4_allocation_context *ac,
 					struct ext4_buddy *e4b)
 {
 	struct super_block *sb = ac->ac_sb;
@@ -1609,7 +1613,8 @@ static void ext4_mb_simple_scan_group(struct ext4_allocation_context *ac,
  * In order to optimize scanning, caller must pass number of
  * free blocks in the group, so the routine can know upper limit.
  */
-static void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac,
+static noinline_for_stack
+void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac,
 					struct ext4_buddy *e4b)
 {
 	struct super_block *sb = ac->ac_sb;
@@ -1668,7 +1673,8 @@ static void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac,
  * we try to find stripe-aligned chunks for stripe-size requests
  * XXX should do so at least for multiples of stripe size as well
  */
-static void ext4_mb_scan_aligned(struct ext4_allocation_context *ac,
+static noinline_for_stack
+void ext4_mb_scan_aligned(struct ext4_allocation_context *ac,
 				 struct ext4_buddy *e4b)
 {
 	struct super_block *sb = ac->ac_sb;
@@ -1831,7 +1837,8 @@ void ext4_mb_put_buddy_cache_lock(struct super_block *sb,
 
 }
 
-static int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
+static noinline_for_stack
+int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
 {
 
 	int ret;
@@ -2902,7 +2909,11 @@ int __init init_ext4_mballoc(void)
 
 void exit_ext4_mballoc(void)
 {
-	/* XXX: synchronize_rcu(); */
+	/* 
+	 * Wait for completion of call_rcu()'s on ext4_pspace_cachep
+	 * before destroying the slab cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(ext4_pspace_cachep);
 	kmem_cache_destroy(ext4_ac_cachep);
 	kmem_cache_destroy(ext4_free_ext_cachep);
@@ -3457,7 +3468,8 @@ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap,
  * used in in-core bitmap. buddy must be generated from this bitmap
  * Need to be called with ext4 group lock held
  */
-static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
+static noinline_for_stack
+void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
 					ext4_group_t group)
 {
 	struct ext4_group_info *grp = ext4_get_group_info(sb, group);
@@ -4215,14 +4227,9 @@ ext4_mb_initialize_context(struct ext4_allocation_context *ac,
 	ext4_get_group_no_and_offset(sb, goal, &group, &block);
 
 	/* set up allocation goals */
+	memset(ac, 0, sizeof(struct ext4_allocation_context));
 	ac->ac_b_ex.fe_logical = ar->logical;
-	ac->ac_b_ex.fe_group = 0;
-	ac->ac_b_ex.fe_start = 0;
-	ac->ac_b_ex.fe_len = 0;
 	ac->ac_status = AC_STATUS_CONTINUE;
-	ac->ac_groups_scanned = 0;
-	ac->ac_ex_scanned = 0;
-	ac->ac_found = 0;
 	ac->ac_sb = sb;
 	ac->ac_inode = ar->inode;
 	ac->ac_o_ex.fe_logical = ar->logical;
@@ -4233,15 +4240,7 @@ ext4_mb_initialize_context(struct ext4_allocation_context *ac,
 	ac->ac_g_ex.fe_group = group;
 	ac->ac_g_ex.fe_start = block;
 	ac->ac_g_ex.fe_len = len;
-	ac->ac_f_ex.fe_len = 0;
 	ac->ac_flags = ar->flags;
-	ac->ac_2order = 0;
-	ac->ac_criteria = 0;
-	ac->ac_pa = NULL;
-	ac->ac_bitmap_page = NULL;
-	ac->ac_buddy_page = NULL;
-	ac->alloc_semp = NULL;
-	ac->ac_lg = NULL;
 
 	/* we have to define context: we'll we work with a file or
 	 * locality group. this is a policy, actually */
@@ -4509,10 +4508,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
 	}
 
 	ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS);
-	if (ac) {
-		ac->ac_sb = sb;
-		ac->ac_inode = ar->inode;
-	} else {
+	if (!ac) {
 		ar->len = 0;
 		*errp = -ENOMEM;
 		goto out1;

fs/jbd2/journal.c

@@ -297,6 +297,7 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
 	unsigned int new_offset;
 	struct buffer_head *bh_in = jh2bh(jh_in);
 	struct jbd2_buffer_trigger_type *triggers;
+	journal_t *journal = transaction->t_journal;
 
 	/*
 	 * The buffer really shouldn't be locked: only the current committing
@@ -310,6 +311,11 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
 	J_ASSERT_BH(bh_in, buffer_jbddirty(bh_in));
 
 	new_bh = alloc_buffer_head(GFP_NOFS|__GFP_NOFAIL);
+	/* keep subsequent assertions sane */
+	new_bh->b_state = 0;
+	init_buffer(new_bh, NULL, NULL);
+	atomic_set(&new_bh->b_count, 1);
+	new_jh = jbd2_journal_add_journal_head(new_bh);	/* This sleeps */
 
 	/*
 	 * If a new transaction has already done a buffer copy-out, then
@@ -388,14 +394,6 @@ repeat:
 		kunmap_atomic(mapped_data, KM_USER0);
 	}
 
-	/* keep subsequent assertions sane */
-	new_bh->b_state = 0;
-	init_buffer(new_bh, NULL, NULL);
-	atomic_set(&new_bh->b_count, 1);
-	jbd_unlock_bh_state(bh_in);
-
-	new_jh = jbd2_journal_add_journal_head(new_bh);	/* This sleeps */
-
 	set_bh_page(new_bh, new_page, new_offset);
 	new_jh->b_transaction = NULL;
 	new_bh->b_size = jh2bh(jh_in)->b_size;
@@ -412,7 +410,11 @@ repeat:
 	 * copying is moved to the transaction's shadow queue.
 	 */
 	JBUFFER_TRACE(jh_in, "file as BJ_Shadow");
-	jbd2_journal_file_buffer(jh_in, transaction, BJ_Shadow);
+	spin_lock(&journal->j_list_lock);
+	__jbd2_journal_file_buffer(jh_in, transaction, BJ_Shadow);
+	spin_unlock(&journal->j_list_lock);
+	jbd_unlock_bh_state(bh_in);
+
 	JBUFFER_TRACE(new_jh, "file as BJ_IO");
 	jbd2_journal_file_buffer(new_jh, transaction, BJ_IO);
 
@@ -2410,6 +2412,7 @@ const char *jbd2_dev_to_name(dev_t device)
 	int	i = hash_32(device, CACHE_SIZE_BITS);
 	char	*ret;
 	struct block_device *bd;
+	static struct devname_cache *new_dev;
 
 	rcu_read_lock();
 	if (devcache[i] && devcache[i]->device == device) {
@@ -2419,20 +2422,20 @@ const char *jbd2_dev_to_name(dev_t device)
 	}
 	rcu_read_unlock();
 
+	new_dev = kmalloc(sizeof(struct devname_cache), GFP_KERNEL);
+	if (!new_dev)
+		return "NODEV-ALLOCFAILURE"; /* Something non-NULL */
 	spin_lock(&devname_cache_lock);
 	if (devcache[i]) {
 		if (devcache[i]->device == device) {
+			kfree(new_dev);
 			ret = devcache[i]->devname;
 			spin_unlock(&devname_cache_lock);
 			return ret;
 		}
 		call_rcu(&devcache[i]->rcu, free_devcache);
 	}
-	devcache[i] = kmalloc(sizeof(struct devname_cache), GFP_KERNEL);
-	if (!devcache[i]) {
-		spin_unlock(&devname_cache_lock);
-		return "NODEV-ALLOCFAILURE"; /* Something non-NULL */
-	}
+	devcache[i] = new_dev;
 	devcache[i]->device = device;
 	bd = bdget(device);
 	if (bd) {

fs/jbd2/transaction.c

@@ -499,34 +499,15 @@ void jbd2_journal_unlock_updates (journal_t *journal)
 	wake_up(&journal->j_wait_transaction_locked);
 }
 
-/*
- * Report any unexpected dirty buffers which turn up.  Normally those
- * indicate an error, but they can occur if the user is running (say)
- * tune2fs to modify the live filesystem, so we need the option of
- * continuing as gracefully as possible.  #
- *
- * The caller should already hold the journal lock and
- * j_list_lock spinlock: most callers will need those anyway
- * in order to probe the buffer's journaling state safely.
- */
-static void jbd_unexpected_dirty_buffer(struct journal_head *jh)
+static void warn_dirty_buffer(struct buffer_head *bh)
 {
-	int jlist;
-
-	/* If this buffer is one which might reasonably be dirty
-	 * --- ie. data, or not part of this journal --- then
-	 * we're OK to leave it alone, but otherwise we need to
-	 * move the dirty bit to the journal's own internal
-	 * JBDDirty bit. */
-	jlist = jh->b_jlist;
-
-	if (jlist == BJ_Metadata || jlist == BJ_Reserved ||
-	    jlist == BJ_Shadow || jlist == BJ_Forget) {
-		struct buffer_head *bh = jh2bh(jh);
+	char b[BDEVNAME_SIZE];
 
-		if (test_clear_buffer_dirty(bh))
-			set_buffer_jbddirty(bh);
-	}
+	printk(KERN_WARNING
+	       "JBD: Spotted dirty metadata buffer (dev = %s, blocknr = %llu). "
+	       "There's a risk of filesystem corruption in case of system "
+	       "crash.\n",
+	       bdevname(bh->b_bdev, b), (unsigned long long)bh->b_blocknr);
 }
 
 /*
@@ -593,14 +574,16 @@ repeat:
 			if (jh->b_next_transaction)
 				J_ASSERT_JH(jh, jh->b_next_transaction ==
 							transaction);
+			warn_dirty_buffer(bh);
 		}
 		/*
 		 * In any case we need to clean the dirty flag and we must
 		 * do it under the buffer lock to be sure we don't race
 		 * with running write-out.
 		 */
-		JBUFFER_TRACE(jh, "Unexpected dirty buffer");
-		jbd_unexpected_dirty_buffer(jh);
+		JBUFFER_TRACE(jh, "Journalling dirty buffer");
+		clear_buffer_dirty(bh);
+		set_buffer_jbddirty(bh);
 	}
 
 	unlock_buffer(bh);
@@ -843,6 +826,15 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh)
 	J_ASSERT_JH(jh, buffer_locked(jh2bh(jh)));
 
 	if (jh->b_transaction == NULL) {
+		/*
+		 * Previous jbd2_journal_forget() could have left the buffer
+		 * with jbddirty bit set because it was being committed. When
+		 * the commit finished, we've filed the buffer for
+		 * checkpointing and marked it dirty. Now we are reallocating
+		 * the buffer so the transaction freeing it must have
+		 * committed and so it's safe to clear the dirty bit.
+		 */
+		clear_buffer_dirty(jh2bh(jh));
 		jh->b_transaction = transaction;
 
 		/* first access by this transaction */
@@ -1644,8 +1636,13 @@ static int __dispose_buffer(struct journal_head *jh, transaction_t *transaction)
 
 	if (jh->b_cp_transaction) {
 		JBUFFER_TRACE(jh, "on running+cp transaction");
+		/*
+		 * We don't want to write the buffer anymore, clear the
+		 * bit so that we don't confuse checks in
+		 * __journal_file_buffer
+		 */
+		clear_buffer_dirty(bh);
 		__jbd2_journal_file_buffer(jh, transaction, BJ_Forget);
-		clear_buffer_jbddirty(bh);
 		may_free = 0;
 	} else {
 		JBUFFER_TRACE(jh, "on running transaction");
@@ -1896,12 +1893,17 @@ void __jbd2_journal_file_buffer(struct journal_head *jh,
 	if (jh->b_transaction && jh->b_jlist == jlist)
 		return;
 
-	/* The following list of buffer states needs to be consistent
-	 * with __jbd_unexpected_dirty_buffer()'s handling of dirty
-	 * state. */
-
 	if (jlist == BJ_Metadata || jlist == BJ_Reserved ||
 	    jlist == BJ_Shadow || jlist == BJ_Forget) {
+		/*
+		 * For metadata buffers, we track dirty bit in buffer_jbddirty
+		 * instead of buffer_dirty. We should not see a dirty bit set
+		 * here because we clear it in do_get_write_access but e.g.
+		 * tune2fs can modify the sb and set the dirty bit at any time
+		 * so we try to gracefully handle that.
+		 */
+		if (buffer_dirty(bh))
+			warn_dirty_buffer(bh);
 		if (test_clear_buffer_dirty(bh) ||
 		    test_clear_buffer_jbddirty(bh))
 			was_dirty = 1;

include/trace/events/ext4.h

@@ -34,7 +34,8 @@ TRACE_EVENT(ext4_free_inode,
 
 	TP_printk("dev %s ino %lu mode %d uid %u gid %u blocks %llu",
 		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->mode,
-		  __entry->uid, __entry->gid, __entry->blocks)
+		  __entry->uid, __entry->gid,
+		  (unsigned long long) __entry->blocks)
 );
 
 TRACE_EVENT(ext4_request_inode,
@@ -189,7 +190,7 @@ TRACE_EVENT(ext4_journalled_write_end,
 		  __entry->copied)
 );
 
-TRACE_EVENT(ext4_da_writepage,
+TRACE_EVENT(ext4_writepage,
 	TP_PROTO(struct inode *inode, struct page *page),
 
 	TP_ARGS(inode, page),
@@ -341,49 +342,6 @@ TRACE_EVENT(ext4_da_write_end,
 		  __entry->copied)
 );
 
-TRACE_EVENT(ext4_normal_writepage,
-	TP_PROTO(struct inode *inode, struct page *page),
-
-	TP_ARGS(inode, page),
-
-	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
-		__field(	ino_t,	ino			)
-		__field(	pgoff_t, index			)
-	),
-
-	TP_fast_assign(
-		__entry->dev	= inode->i_sb->s_dev;
-		__entry->ino	= inode->i_ino;
-		__entry->index	= page->index;
-	),
-
-	TP_printk("dev %s ino %lu page_index %lu",
-		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->index)
-);
-
-TRACE_EVENT(ext4_journalled_writepage,
-	TP_PROTO(struct inode *inode, struct page *page),
-
-	TP_ARGS(inode, page),
-
-	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
-		__field(	ino_t,	ino			)
-		__field(	pgoff_t, index			)
-
-	),
-
-	TP_fast_assign(
-		__entry->dev	= inode->i_sb->s_dev;
-		__entry->ino	= inode->i_ino;
-		__entry->index	= page->index;
-	),
-
-	TP_printk("dev %s ino %lu page_index %lu",
-		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->index)
-);
-
 TRACE_EVENT(ext4_discard_blocks,
 	TP_PROTO(struct super_block *sb, unsigned long long blk,
 			unsigned long long count),