Merge tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/lin…

…ux/kernel/git/tytso/ext4

Pull ext4 fixes from Ted Ts'o:
 "Fix various bug fixes in ext4 caused by races and memory allocation
  failures"

* tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
  ext4: fix fdatasync(2) after extent manipulation operations
  ext4: fix data corruption for mmap writes
  ext4: fix data corruption with EXT4_GET_BLOCKS_ZERO
  ext4: fix quota charging for shared xattr blocks
  ext4: remove redundant check for encrypted file on dio write path
  ext4: remove unused d_name argument from ext4_search_dir() et al.
  ext4: fix off-by-one error when writing back pages before dio read
  ext4: fix off-by-one on max nr_pages in ext4_find_unwritten_pgoff()
  ext4: keep existing extra fields when inode expands
  ext4: handle the rest of ext4_mb_load_buddy() ENOMEM errors
  ext4: fix off-by-in in loop termination in ext4_find_unwritten_pgoff()
  ext4: fix SEEK_HOLE
  jbd2: preserve original nofs flag during journal restart
  ext4: clear lockdep subtype for quota files on quota off

fs/ext4/acl.c

@@ -4,6 +4,7 @@
  * Copyright (C) 2001-2003 Andreas Gruenbacher, <[email protected]>
  */
 
+#include <linux/quotaops.h>
 #include "ext4_jbd2.h"
 #include "ext4.h"
 #include "xattr.h"
@@ -232,6 +233,9 @@ ext4_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 	handle_t *handle;
 	int error, retries = 0;
 
+	error = dquot_initialize(inode);
+	if (error)
+		return error;
 retry:
 	handle = ext4_journal_start(inode, EXT4_HT_XATTR,
 				    ext4_jbd2_credits_xattr(inode));

fs/ext4/ext4.h

@@ -2523,7 +2523,6 @@ extern int ext4_search_dir(struct buffer_head *bh,
 			   int buf_size,
 			   struct inode *dir,
 			   struct ext4_filename *fname,
-			   const struct qstr *d_name,
 			   unsigned int offset,
 			   struct ext4_dir_entry_2 **res_dir);
 extern int ext4_generic_delete_entry(handle_t *handle,
@@ -3007,7 +3006,6 @@ extern int htree_inlinedir_to_tree(struct file *dir_file,
 				   int *has_inline_data);
 extern struct buffer_head *ext4_find_inline_entry(struct inode *dir,
 					struct ext4_filename *fname,
-					const struct qstr *d_name,
 					struct ext4_dir_entry_2 **res_dir,
 					int *has_inline_data);
 extern int ext4_delete_inline_entry(handle_t *handle,

fs/ext4/extents.c

@@ -3413,13 +3413,13 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 	struct ext4_sb_info *sbi;
 	struct ext4_extent_header *eh;
 	struct ext4_map_blocks split_map;
-	struct ext4_extent zero_ex;
+	struct ext4_extent zero_ex1, zero_ex2;
 	struct ext4_extent *ex, *abut_ex;
 	ext4_lblk_t ee_block, eof_block;
 	unsigned int ee_len, depth, map_len = map->m_len;
 	int allocated = 0, max_zeroout = 0;
 	int err = 0;
-	int split_flag = 0;
+	int split_flag = EXT4_EXT_DATA_VALID2;
 
 	ext_debug("ext4_ext_convert_to_initialized: inode %lu, logical"
 		"block %llu, max_blocks %u\n", inode->i_ino,
@@ -3436,7 +3436,8 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 	ex = path[depth].p_ext;
 	ee_block = le32_to_cpu(ex->ee_block);
 	ee_len = ext4_ext_get_actual_len(ex);
-	zero_ex.ee_len = 0;
+	zero_ex1.ee_len = 0;
+	zero_ex2.ee_len = 0;
 
 	trace_ext4_ext_convert_to_initialized_enter(inode, map, ex);
 
@@ -3576,62 +3577,52 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 	if (ext4_encrypted_inode(inode))
 		max_zeroout = 0;
 
-	/* If extent is less than s_max_zeroout_kb, zeroout directly */
-	if (max_zeroout && (ee_len <= max_zeroout)) {
-		err = ext4_ext_zeroout(inode, ex);
-		if (err)
-			goto out;
-		zero_ex.ee_block = ex->ee_block;
-		zero_ex.ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex));
-		ext4_ext_store_pblock(&zero_ex, ext4_ext_pblock(ex));
-
-		err = ext4_ext_get_access(handle, inode, path + depth);
-		if (err)
-			goto out;
-		ext4_ext_mark_initialized(ex);
-		ext4_ext_try_to_merge(handle, inode, path, ex);
-		err = ext4_ext_dirty(handle, inode, path + path->p_depth);
-		goto out;
-	}
-
 	/*
-	 * four cases:
+	 * five cases:
 	 * 1. split the extent into three extents.
-	 * 2. split the extent into two extents, zeroout the first half.
-	 * 3. split the extent into two extents, zeroout the second half.
+	 * 2. split the extent into two extents, zeroout the head of the first
+	 *    extent.
+	 * 3. split the extent into two extents, zeroout the tail of the second
+	 *    extent.
 	 * 4. split the extent into two extents with out zeroout.
+	 * 5. no splitting needed, just possibly zeroout the head and / or the
+	 *    tail of the extent.
 	 */
 	split_map.m_lblk = map->m_lblk;
 	split_map.m_len = map->m_len;
 
-	if (max_zeroout && (allocated > map->m_len)) {
+	if (max_zeroout && (allocated > split_map.m_len)) {
 		if (allocated <= max_zeroout) {
-			/* case 3 */
-			zero_ex.ee_block =
-					 cpu_to_le32(map->m_lblk);
-			zero_ex.ee_len = cpu_to_le16(allocated);
-			ext4_ext_store_pblock(&zero_ex,
-				ext4_ext_pblock(ex) + map->m_lblk - ee_block);
-			err = ext4_ext_zeroout(inode, &zero_ex);
+			/* case 3 or 5 */
+			zero_ex1.ee_block =
+				 cpu_to_le32(split_map.m_lblk +
+					     split_map.m_len);
+			zero_ex1.ee_len =
+				cpu_to_le16(allocated - split_map.m_len);
+			ext4_ext_store_pblock(&zero_ex1,
+				ext4_ext_pblock(ex) + split_map.m_lblk +
+				split_map.m_len - ee_block);
+			err = ext4_ext_zeroout(inode, &zero_ex1);
 			if (err)
 				goto out;
-			split_map.m_lblk = map->m_lblk;
 			split_map.m_len = allocated;
-		} else if (map->m_lblk - ee_block + map->m_len < max_zeroout) {
-			/* case 2 */
-			if (map->m_lblk != ee_block) {
-				zero_ex.ee_block = ex->ee_block;
-				zero_ex.ee_len = cpu_to_le16(map->m_lblk -
+		}
+		if (split_map.m_lblk - ee_block + split_map.m_len <
+								max_zeroout) {
+			/* case 2 or 5 */
+			if (split_map.m_lblk != ee_block) {
+				zero_ex2.ee_block = ex->ee_block;
+				zero_ex2.ee_len = cpu_to_le16(split_map.m_lblk -
 							ee_block);
-				ext4_ext_store_pblock(&zero_ex,
+				ext4_ext_store_pblock(&zero_ex2,
 						      ext4_ext_pblock(ex));
-				err = ext4_ext_zeroout(inode, &zero_ex);
+				err = ext4_ext_zeroout(inode, &zero_ex2);
 				if (err)
 					goto out;
 			}
 
+			split_map.m_len += split_map.m_lblk - ee_block;
 			split_map.m_lblk = ee_block;
-			split_map.m_len = map->m_lblk - ee_block + map->m_len;
 			allocated = map->m_len;
 		}
 	}
@@ -3642,8 +3633,11 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 		err = 0;
 out:
 	/* If we have gotten a failure, don't zero out status tree */
-	if (!err)
-		err = ext4_zeroout_es(inode, &zero_ex);
+	if (!err) {
+		err = ext4_zeroout_es(inode, &zero_ex1);
+		if (!err)
+			err = ext4_zeroout_es(inode, &zero_ex2);
+	}
 	return err ? err : allocated;
 }
 
@@ -4883,6 +4877,8 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 
 	/* Zero out partial block at the edges of the range */
 	ret = ext4_zero_partial_blocks(handle, inode, offset, len);
+	if (ret >= 0)
+		ext4_update_inode_fsync_trans(handle, inode, 1);
 
 	if (file->f_flags & O_SYNC)
 		ext4_handle_sync(handle);
@@ -5569,6 +5565,7 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 		ext4_handle_sync(handle);
 	inode->i_mtime = inode->i_ctime = current_time(inode);
 	ext4_mark_inode_dirty(handle, inode);
+	ext4_update_inode_fsync_trans(handle, inode, 1);
 
 out_stop:
 	ext4_journal_stop(handle);
@@ -5742,6 +5739,8 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 	up_write(&EXT4_I(inode)->i_data_sem);
 	if (IS_SYNC(inode))
 		ext4_handle_sync(handle);
+	if (ret >= 0)
+		ext4_update_inode_fsync_trans(handle, inode, 1);
 
 out_stop:
 	ext4_journal_stop(handle);

fs/ext4/file.c

@@ -474,57 +474,37 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
 	endoff = (loff_t)end_blk << blkbits;
 
 	index = startoff >> PAGE_SHIFT;
-	end = endoff >> PAGE_SHIFT;
+	end = (endoff - 1) >> PAGE_SHIFT;
 
 	pagevec_init(&pvec, 0);
 	do {
 		int i, num;
 		unsigned long nr_pages;
 
-		num = min_t(pgoff_t, end - index, PAGEVEC_SIZE);
+		num = min_t(pgoff_t, end - index, PAGEVEC_SIZE - 1) + 1;
 		nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index,
 					  (pgoff_t)num);
-		if (nr_pages == 0) {
-			if (whence == SEEK_DATA)
-				break;
-
-			BUG_ON(whence != SEEK_HOLE);
-			/*
-			 * If this is the first time to go into the loop and
-			 * offset is not beyond the end offset, it will be a
-			 * hole at this offset
-			 */
-			if (lastoff == startoff || lastoff < endoff)
-				found = 1;
-			break;
-		}
-
-		/*
-		 * If this is the first time to go into the loop and
-		 * offset is smaller than the first page offset, it will be a
-		 * hole at this offset.
-		 */
-		if (lastoff == startoff && whence == SEEK_HOLE &&
-		    lastoff < page_offset(pvec.pages[0])) {
-			found = 1;
+		if (nr_pages == 0)
 			break;
-		}
 
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
 			struct buffer_head *bh, *head;
 
 			/*
-			 * If the current offset is not beyond the end of given
-			 * range, it will be a hole.
+			 * If current offset is smaller than the page offset,
+			 * there is a hole at this offset.
 			 */
-			if (lastoff < endoff && whence == SEEK_HOLE &&
-			    page->index > end) {
+			if (whence == SEEK_HOLE && lastoff < endoff &&
+			    lastoff < page_offset(pvec.pages[i])) {
 				found = 1;
 				*offset = lastoff;
 				goto out;
 			}
 
+			if (page->index > end)
+				goto out;
+
 			lock_page(page);
 
 			if (unlikely(page->mapping != inode->i_mapping)) {
@@ -564,20 +544,18 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
 			unlock_page(page);
 		}
 
-		/*
-		 * The no. of pages is less than our desired, that would be a
-		 * hole in there.
-		 */
-		if (nr_pages < num && whence == SEEK_HOLE) {
-			found = 1;
-			*offset = lastoff;
+		/* The no. of pages is less than our desired, we are done. */
+		if (nr_pages < num)
 			break;
-		}
 
 		index = pvec.pages[i - 1]->index + 1;
 		pagevec_release(&pvec);
 	} while (index <= end);
 
+	if (whence == SEEK_HOLE && lastoff < endoff) {
+		found = 1;
+		*offset = lastoff;
+	}
 out:
 	pagevec_release(&pvec);
 	return found;

fs/ext4/inline.c

@@ -1627,7 +1627,6 @@ int ext4_try_create_inline_dir(handle_t *handle, struct inode *parent,
 
 struct buffer_head *ext4_find_inline_entry(struct inode *dir,
 					struct ext4_filename *fname,
-					const struct qstr *d_name,
 					struct ext4_dir_entry_2 **res_dir,
 					int *has_inline_data)
 {
@@ -1649,7 +1648,7 @@ struct buffer_head *ext4_find_inline_entry(struct inode *dir,
 						EXT4_INLINE_DOTDOT_SIZE;
 	inline_size = EXT4_MIN_INLINE_DATA_SIZE - EXT4_INLINE_DOTDOT_SIZE;
 	ret = ext4_search_dir(iloc.bh, inline_start, inline_size,
-			      dir, fname, d_name, 0, res_dir);
+			      dir, fname, 0, res_dir);
 	if (ret == 1)
 		goto out_find;
 	if (ret < 0)
@@ -1662,7 +1661,7 @@ struct buffer_head *ext4_find_inline_entry(struct inode *dir,
 	inline_size = ext4_get_inline_size(dir) - EXT4_MIN_INLINE_DATA_SIZE;
 
 	ret = ext4_search_dir(iloc.bh, inline_start, inline_size,
-			      dir, fname, d_name, 0, res_dir);
+			      dir, fname, 0, res_dir);
 	if (ret == 1)
 		goto out_find;
 

fs/ext4/inode.c

@@ -2124,15 +2124,29 @@ static int ext4_writepage(struct page *page,
 static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page)
 {
 	int len;
-	loff_t size = i_size_read(mpd->inode);
+	loff_t size;
 	int err;
 
 	BUG_ON(page->index != mpd->first_page);
+	clear_page_dirty_for_io(page);
+	/*
+	 * We have to be very careful here!  Nothing protects writeback path
+	 * against i_size changes and the page can be writeably mapped into
+	 * page tables. So an application can be growing i_size and writing
+	 * data through mmap while writeback runs. clear_page_dirty_for_io()
+	 * write-protects our page in page tables and the page cannot get
+	 * written to again until we release page lock. So only after
+	 * clear_page_dirty_for_io() we are safe to sample i_size for
+	 * ext4_bio_write_page() to zero-out tail of the written page. We rely
+	 * on the barrier provided by TestClearPageDirty in
+	 * clear_page_dirty_for_io() to make sure i_size is really sampled only
+	 * after page tables are updated.
+	 */
+	size = i_size_read(mpd->inode);
 	if (page->index == size >> PAGE_SHIFT)
 		len = size & ~PAGE_MASK;
 	else
 		len = PAGE_SIZE;
-	clear_page_dirty_for_io(page);
 	err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc, false);
 	if (!err)
 		mpd->wbc->nr_to_write--;
@@ -3629,9 +3643,6 @@ static ssize_t ext4_direct_IO_write(struct kiocb *iocb, struct iov_iter *iter)
 		get_block_func = ext4_dio_get_block_unwritten_async;
 		dio_flags = DIO_LOCKING;
 	}
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
-	BUG_ON(ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode));
-#endif
 	ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter,
 				   get_block_func, ext4_end_io_dio, NULL,
 				   dio_flags);
@@ -3713,7 +3724,7 @@ static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter)
 	 */
 	inode_lock_shared(inode);
 	ret = filemap_write_and_wait_range(mapping, iocb->ki_pos,
-					   iocb->ki_pos + count);
+					   iocb->ki_pos + count - 1);
 	if (ret)
 		goto out_unlock;
 	ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
@@ -4207,6 +4218,8 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 
 	inode->i_mtime = inode->i_ctime = current_time(inode);
 	ext4_mark_inode_dirty(handle, inode);
+	if (ret >= 0)
+		ext4_update_inode_fsync_trans(handle, inode, 1);
 out_stop:
 	ext4_journal_stop(handle);
 out_dio:
@@ -5637,8 +5650,9 @@ static int ext4_expand_extra_isize(struct inode *inode,
 	/* No extended attributes present */
 	if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR) ||
 	    header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)) {
-		memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE, 0,
-			new_extra_isize);
+		memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE +
+		       EXT4_I(inode)->i_extra_isize, 0,
+		       new_extra_isize - EXT4_I(inode)->i_extra_isize);
 		EXT4_I(inode)->i_extra_isize = new_extra_isize;
 		return 0;
 	}