1 files changed, 297 insertions, 156 deletions

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 981a1fc30eaa..9c064727ed62 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -51,25 +51,31 @@ static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw,
 			      struct ext4_inode_info *ei)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-	__u16 csum_lo;
-	__u16 csum_hi = 0;
 	__u32 csum;
+	__u16 dummy_csum = 0;
+	int offset = offsetof(struct ext4_inode, i_checksum_lo);
+	unsigned int csum_size = sizeof(dummy_csum);
 
-	csum_lo = le16_to_cpu(raw->i_checksum_lo);
-	raw->i_checksum_lo = 0;
-	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
-	    EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) {
-		csum_hi = le16_to_cpu(raw->i_checksum_hi);
-		raw->i_checksum_hi = 0;
-	}
-
-	csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)raw,
-			   EXT4_INODE_SIZE(inode->i_sb));
+	csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)raw, offset);
+	csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum, csum_size);
+	offset += csum_size;
+	csum = ext4_chksum(sbi, csum, (__u8 *)raw + offset,
+			   EXT4_GOOD_OLD_INODE_SIZE - offset);
 
-	raw->i_checksum_lo = cpu_to_le16(csum_lo);
-	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
-	    EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi))
-		raw->i_checksum_hi = cpu_to_le16(csum_hi);
+	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
+		offset = offsetof(struct ext4_inode, i_checksum_hi);
+		csum = ext4_chksum(sbi, csum, (__u8 *)raw +
+				   EXT4_GOOD_OLD_INODE_SIZE,
+				   offset - EXT4_GOOD_OLD_INODE_SIZE);
+		if (EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) {
+			csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum,
+					   csum_size);
+			offset += csum_size;
+			csum = ext4_chksum(sbi, csum, (__u8 *)raw + offset,
+					   EXT4_INODE_SIZE(inode->i_sb) -
+					   offset);
+		}
+	}
 
 	return csum;
 }
@@ -205,9 +211,9 @@ void ext4_evict_inode(struct inode *inode)
 		 * Note that directories do not have this problem because they
 		 * don't use page cache.
 		 */
-		if (ext4_should_journal_data(inode) &&
-		    (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode)) &&
-		    inode->i_ino != EXT4_JOURNAL_INO) {
+		if (inode->i_ino != EXT4_JOURNAL_INO &&
+		    ext4_should_journal_data(inode) &&
+		    (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode))) {
 			journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
 			tid_t commit_tid = EXT4_I(inode)->i_datasync_tid;
 
@@ -386,7 +392,7 @@ int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk,
 	int ret;
 
 	if (ext4_encrypted_inode(inode))
-		return ext4_encrypted_zeroout(inode, lblk, pblk, len);
+		return fscrypt_zeroout_range(inode, lblk, pblk, len);
 
 	ret = sb_issue_zeroout(inode->i_sb, pblk, len, GFP_NOFS);
 	if (ret > 0)
@@ -641,11 +647,19 @@ found:
 		/*
 		 * We have to zeroout blocks before inserting them into extent
 		 * status tree. Otherwise someone could look them up there and
-		 * use them before they are really zeroed.
+		 * use them before they are really zeroed. We also have to
+		 * unmap metadata before zeroing as otherwise writeback can
+		 * overwrite zeros with stale data from block device.
 		 */
 		if (flags & EXT4_GET_BLOCKS_ZERO &&
 		    map->m_flags & EXT4_MAP_MAPPED &&
 		    map->m_flags & EXT4_MAP_NEW) {
+			ext4_lblk_t i;
+
+			for (i = 0; i < map->m_len; i++) {
+				unmap_underlying_metadata(inode->i_sb->s_bdev,
+							  map->m_pblk + i);
+			}
 			ret = ext4_issue_zeroout(inode, map->m_lblk,
 						 map->m_pblk, map->m_len);
 			if (ret) {
@@ -684,6 +698,24 @@ out_sem:
 		ret = check_block_validity(inode, map);
 		if (ret != 0)
 			return ret;
+
+		/*
+		 * Inodes with freshly allocated blocks where contents will be
+		 * visible after transaction commit must be on transaction's
+		 * ordered data list.
+		 */
+		if (map->m_flags & EXT4_MAP_NEW &&
+		    !(map->m_flags & EXT4_MAP_UNWRITTEN) &&
+		    !(flags & EXT4_GET_BLOCKS_ZERO) &&
+		    !IS_NOQUOTA(inode) &&
+		    ext4_should_order_data(inode)) {
+			if (flags & EXT4_GET_BLOCKS_IO_SUBMIT)
+				ret = ext4_jbd2_inode_add_wait(handle, inode);
+			else
+				ret = ext4_jbd2_inode_add_write(handle, inode);
+			if (ret)
+				return ret;
+		}
 	}
 	return retval;
 }
@@ -963,7 +995,7 @@ struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode,
 		return bh;
 	if (!bh || buffer_uptodate(bh))
 		return bh;
-	ll_rw_block(READ | REQ_META | REQ_PRIO, 1, &bh);
+	ll_rw_block(REQ_OP_READ, REQ_META | REQ_PRIO, 1, &bh);
 	wait_on_buffer(bh);
 	if (buffer_uptodate(bh))
 		return bh;
@@ -1117,7 +1149,7 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len,
 		if (!buffer_uptodate(bh) && !buffer_delay(bh) &&
 		    !buffer_unwritten(bh) &&
 		    (block_start < from || block_end > to)) {
-			ll_rw_block(READ, 1, &bh);
+			ll_rw_block(REQ_OP_READ, 0, 1, &bh);
 			*wait_bh++ = bh;
 			decrypt = ext4_encrypted_inode(inode) &&
 				S_ISREG(inode->i_mode);
@@ -1134,7 +1166,7 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len,
 	if (unlikely(err))
 		page_zero_new_buffers(page, from, to);
 	else if (decrypt)
-		err = ext4_decrypt(page);
+		err = fscrypt_decrypt_page(page);
 	return err;
 }
 #endif
@@ -1289,15 +1321,6 @@ static int ext4_write_end(struct file *file,
 	int i_size_changed = 0;
 
 	trace_ext4_write_end(inode, pos, len, copied);
-	if (ext4_test_inode_state(inode, EXT4_STATE_ORDERED_MODE)) {
-		ret = ext4_jbd2_file_inode(handle, inode);
-		if (ret) {
-			unlock_page(page);
-			put_page(page);
-			goto errout;
-		}
-	}
-
 	if (ext4_has_inline_data(inode)) {
 		ret = ext4_write_inline_data_end(inode, pos, len,
 						 copied, page);
@@ -1634,6 +1657,8 @@ static void mpage_release_unused_pages(struct mpage_da_data *mpd,
 			BUG_ON(!PageLocked(page));
 			BUG_ON(PageWriteback(page));
 			if (invalidate) {
+				if (page_mapped(page))
+					clear_page_dirty_for_io(page);
 				block_invalidatepage(page, 0, PAGE_SIZE);
 				ClearPageUptodate(page);
 			}
@@ -2313,7 +2338,8 @@ static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
 	 * the data was copied into the page cache.
 	 */
 	get_blocks_flags = EXT4_GET_BLOCKS_CREATE |
-			   EXT4_GET_BLOCKS_METADATA_NOFAIL;
+			   EXT4_GET_BLOCKS_METADATA_NOFAIL |
+			   EXT4_GET_BLOCKS_IO_SUBMIT;
 	dioread_nolock = ext4_should_dioread_nolock(inode);
 	if (dioread_nolock)
 		get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT;
@@ -2602,11 +2628,14 @@ static int ext4_writepages(struct address_space *mapping,
 	struct blk_plug plug;
 	bool give_up_on_write = false;
 
+	percpu_down_read(&sbi->s_journal_flag_rwsem);
 	trace_ext4_writepages(inode, wbc);
 
-	if (dax_mapping(mapping))
-		return dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev,
-						   wbc);
+	if (dax_mapping(mapping)) {
+		ret = dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev,
+						  wbc);
+		goto out_writepages;
+	}
 
 	/*
 	 * No pages to write? This is mainly a kludge to avoid starting
@@ -2735,13 +2764,36 @@ retry:
 				done = true;
 			}
 		}
-		ext4_journal_stop(handle);
+		/*
+		 * Caution: If the handle is synchronous,
+		 * ext4_journal_stop() can wait for transaction commit
+		 * to finish which may depend on writeback of pages to
+		 * complete or on page lock to be released.  In that
+		 * case, we have to wait until after after we have
+		 * submitted all the IO, released page locks we hold,
+		 * and dropped io_end reference (for extent conversion
+		 * to be able to complete) before stopping the handle.
+		 */
+		if (!ext4_handle_valid(handle) || handle->h_sync == 0) {
+			ext4_journal_stop(handle);
+			handle = NULL;
+		}
 		/* Submit prepared bio */
 		ext4_io_submit(&mpd.io_submit);
 		/* Unlock pages we didn't use */
 		mpage_release_unused_pages(&mpd, give_up_on_write);
-		/* Drop our io_end reference we got from init */
-		ext4_put_io_end(mpd.io_submit.io_end);
+		/*
+		 * Drop our io_end reference we got from init. We have
+		 * to be careful and use deferred io_end finishing if
+		 * we are still holding the transaction as we can
+		 * release the last reference to io_end which may end
+		 * up doing unwritten extent conversion.
+		 */
+		if (handle) {
+			ext4_put_io_end_defer(mpd.io_submit.io_end);
+			ext4_journal_stop(handle);
+		} else
+			ext4_put_io_end(mpd.io_submit.io_end);
 
 		if (ret == -ENOSPC && sbi->s_journal) {
 			/*
@@ -2776,6 +2828,7 @@ retry:
 out_writepages:
 	trace_ext4_writepages_result(inode, wbc, ret,
 				     nr_to_write - wbc->nr_to_write);
+	percpu_up_read(&sbi->s_journal_flag_rwsem);
 	return ret;
 }
 
@@ -3215,75 +3268,52 @@ static int ext4_releasepage(struct page *page, gfp_t wait)
 }
 
 #ifdef CONFIG_FS_DAX
-int ext4_dax_mmap_get_block(struct inode *inode, sector_t iblock,
-			    struct buffer_head *bh_result, int create)
+/*
+ * Get block function for DAX IO and mmap faults. It takes care of converting
+ * unwritten extents to written ones and initializes new / converted blocks
+ * to zeros.
+ */
+int ext4_dax_get_block(struct inode *inode, sector_t iblock,
+		       struct buffer_head *bh_result, int create)
 {
-	int ret, err;
-	int credits;
-	struct ext4_map_blocks map;
-	handle_t *handle = NULL;
-	int flags = 0;
-
-	ext4_debug("ext4_dax_mmap_get_block: inode %lu, create flag %d\n",
-		   inode->i_ino, create);
-	map.m_lblk = iblock;
-	map.m_len = bh_result->b_size >> inode->i_blkbits;
-	credits = ext4_chunk_trans_blocks(inode, map.m_len);
-	if (create) {
-		flags |= EXT4_GET_BLOCKS_PRE_IO | EXT4_GET_BLOCKS_CREATE_ZERO;
-		handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, credits);
-		if (IS_ERR(handle)) {
-			ret = PTR_ERR(handle);
-			return ret;
-		}
-	}
+	int ret;
 
-	ret = ext4_map_blocks(handle, inode, &map, flags);
-	if (create) {
-		err = ext4_journal_stop(handle);
-		if (ret >= 0 && err < 0)
-			ret = err;
-	}
-	if (ret <= 0)
-		goto out;
-	if (map.m_flags & EXT4_MAP_UNWRITTEN) {
-		int err2;
+	ext4_debug("inode %lu, create flag %d\n", inode->i_ino, create);
+	if (!create)
+		return _ext4_get_block(inode, iblock, bh_result, 0);
 
-		/*
-		 * We are protected by i_mmap_sem so we know block cannot go
-		 * away from under us even though we dropped i_data_sem.
-		 * Convert extent to written and write zeros there.
-		 *
-		 * Note: We may get here even when create == 0.
-		 */
-		handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, credits);
-		if (IS_ERR(handle)) {
-			ret = PTR_ERR(handle);
-			goto out;
-		}
+	ret = ext4_get_block_trans(inode, iblock, bh_result,
+				   EXT4_GET_BLOCKS_PRE_IO |
+				   EXT4_GET_BLOCKS_CREATE_ZERO);
+	if (ret < 0)
+		return ret;
 
-		err = ext4_map_blocks(handle, inode, &map,
-		      EXT4_GET_BLOCKS_CONVERT | EXT4_GET_BLOCKS_CREATE_ZERO);
-		if (err < 0)
-			ret = err;
-		err2 = ext4_journal_stop(handle);
-		if (err2 < 0 && ret > 0)
-			ret = err2;
-	}
-out:
-	WARN_ON_ONCE(ret == 0 && create);
-	if (ret > 0) {
-		map_bh(bh_result, inode->i_sb, map.m_pblk);
+	if (buffer_unwritten(bh_result)) {
 		/*
-		 * At least for now we have to clear BH_New so that DAX code
-		 * doesn't attempt to zero blocks again in a racy way.
+		 * We are protected by i_mmap_sem or i_mutex so we know block
+		 * cannot go away from under us even though we dropped
+		 * i_data_sem. Convert extent to written and write zeros there.
 		 */
-		map.m_flags &= ~EXT4_MAP_NEW;
-		ext4_update_bh_state(bh_result, map.m_flags);
-		bh_result->b_size = map.m_len << inode->i_blkbits;
-		ret = 0;
+		ret = ext4_get_block_trans(inode, iblock, bh_result,
+					   EXT4_GET_BLOCKS_CONVERT |
+					   EXT4_GET_BLOCKS_CREATE_ZERO);
+		if (ret < 0)
+			return ret;
 	}
-	return ret;
+	/*
+	 * At least for now we have to clear BH_New so that DAX code
+	 * doesn't attempt to zero blocks again in a racy way.
+	 */
+	clear_buffer_new(bh_result);
+	return 0;
+}
+#else
+/* Just define empty function, it will never get called. */
+int ext4_dax_get_block(struct inode *inode, sector_t iblock,
+		       struct buffer_head *bh_result, int create)
+{
+	BUG();
+	return 0;
 }
 #endif
 
@@ -3316,7 +3346,9 @@ static int ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
 }
 
 /*
- * For ext4 extent files, ext4 will do direct-io write to holes,
+ * Handling of direct IO writes.
+ *
+ * For ext4 extent files, ext4 will do direct-io write even to holes,
  * preallocated extents, and those write extend the file, no need to
  * fall back to buffered IO.
  *
@@ -3334,21 +3366,37 @@ static int ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
  * if the machine crashes during the write.
  *
  */
-static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
-				  loff_t offset)
+static ssize_t ext4_direct_IO_write(struct kiocb *iocb, struct iov_iter *iter)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
+	struct ext4_inode_info *ei = EXT4_I(inode);
 	ssize_t ret;
+	loff_t offset = iocb->ki_pos;
 	size_t count = iov_iter_count(iter);
 	int overwrite = 0;
 	get_block_t *get_block_func = NULL;
 	int dio_flags = 0;
 	loff_t final_size = offset + count;
+	int orphan = 0;
+	handle_t *handle;
 
-	/* Use the old path for reads and writes beyond i_size. */
-	if (iov_iter_rw(iter) != WRITE || final_size > inode->i_size)
-		return ext4_ind_direct_IO(iocb, iter, offset);
+	if (final_size > inode->i_size) {
+		/* Credits for sb + inode write */
+		handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
+		if (IS_ERR(handle)) {
+			ret = PTR_ERR(handle);
+			goto out;
+		}
+		ret = ext4_orphan_add(handle, inode);
+		if (ret) {
+			ext4_journal_stop(handle);
+			goto out;
+		}
+		orphan = 1;
+		ei->i_disksize = inode->i_size;
+		ext4_journal_stop(handle);
+	}
 
 	BUG_ON(iocb->private == NULL);
 
@@ -3357,8 +3405,7 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	 * conversion. This also disallows race between truncate() and
 	 * overwrite DIO as i_dio_count needs to be incremented under i_mutex.
 	 */
-	if (iov_iter_rw(iter) == WRITE)
-		inode_dio_begin(inode);
+	inode_dio_begin(inode);
 
 	/* If we do a overwrite dio, i_mutex locking can be released */
 	overwrite = *((int *)iocb->private);
@@ -3367,7 +3414,7 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 		inode_unlock(inode);
 
 	/*
-	 * We could direct write to holes and fallocate.
+	 * For extent mapped files we could direct write to holes and fallocate.
 	 *
 	 * Allocated blocks to fill the hole are marked as unwritten to prevent
 	 * parallel buffered read to expose the stale data before DIO complete
@@ -3389,7 +3436,23 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	iocb->private = NULL;
 	if (overwrite)
 		get_block_func = ext4_dio_get_block_overwrite;
-	else if (is_sync_kiocb(iocb)) {
+	else if (IS_DAX(inode)) {
+		/*
+		 * We can avoid zeroing for aligned DAX writes beyond EOF. Other
+		 * writes need zeroing either because they can race with page
+		 * faults or because they use partial blocks.
+		 */
+		if (round_down(offset, 1<<inode->i_blkbits) >= inode->i_size &&
+		    ext4_aligned_io(inode, offset, count))
+			get_block_func = ext4_dio_get_block;
+		else
+			get_block_func = ext4_dax_get_block;
+		dio_flags = DIO_LOCKING;
+	} else if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) ||
+		   round_down(offset, 1 << inode->i_blkbits) >= inode->i_size) {
+		get_block_func = ext4_dio_get_block;
+		dio_flags = DIO_LOCKING | DIO_SKIP_HOLES;
+	} else if (is_sync_kiocb(iocb)) {
 		get_block_func = ext4_dio_get_block_unwritten_sync;
 		dio_flags = DIO_LOCKING;
 	} else {
@@ -3399,12 +3462,12 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
 	BUG_ON(ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode));
 #endif
-	if (IS_DAX(inode))
-		ret = dax_do_io(iocb, inode, iter, offset, get_block_func,
+	if (IS_DAX(inode)) {
+		ret = dax_do_io(iocb, inode, iter, get_block_func,
 				ext4_end_io_dio, dio_flags);
-	else
+	} else
 		ret = __blockdev_direct_IO(iocb, inode,
-					   inode->i_sb->s_bdev, iter, offset,
+					   inode->i_sb->s_bdev, iter,
 					   get_block_func,
 					   ext4_end_io_dio, NULL, dio_flags);
 
@@ -3422,21 +3485,91 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 		ext4_clear_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
 	}
 
-	if (iov_iter_rw(iter) == WRITE)
-		inode_dio_end(inode);
+	inode_dio_end(inode);
 	/* take i_mutex locking again if we do a ovewrite dio */
 	if (overwrite)
 		inode_lock(inode);
 
+	if (ret < 0 && final_size > inode->i_size)
+		ext4_truncate_failed_write(inode);
+
+	/* Handle extending of i_size after direct IO write */
+	if (orphan) {
+		int err;
+
+		/* Credits for sb + inode write */
+		handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
+		if (IS_ERR(handle)) {
+			/* This is really bad luck. We've written the data
+			 * but cannot extend i_size. Bail out and pretend
+			 * the write failed... */
+			ret = PTR_ERR(handle);
+			if (inode->i_nlink)
+				ext4_orphan_del(NULL, inode);
+
+			goto out;
+		}
+		if (inode->i_nlink)
+			ext4_orphan_del(handle, inode);
+		if (ret > 0) {
+			loff_t end = offset + ret;
+			if (end > inode->i_size) {
+				ei->i_disksize = end;
+				i_size_write(inode, end);
+				/*
+				 * We're going to return a positive `ret'
+				 * here due to non-zero-length I/O, so there's
+				 * no way of reporting error returns from
+				 * ext4_mark_inode_dirty() to userspace.  So
+				 * ignore it.
+				 */
+				ext4_mark_inode_dirty(handle, inode);
+			}
+		}
+		err = ext4_journal_stop(handle);
+		if (ret == 0)
+			ret = err;
+	}
+out:
+	return ret;
+}
+
+static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct address_space *mapping = iocb->ki_filp->f_mapping;
+	struct inode *inode = mapping->host;
+	ssize_t ret;
+
+	/*
+	 * Shared inode_lock is enough for us - it protects against concurrent
+	 * writes & truncates and since we take care of writing back page cache,
+	 * we are protected against page writeback as well.
+	 */
+	inode_lock_shared(inode);
+	if (IS_DAX(inode)) {
+		ret = dax_do_io(iocb, inode, iter, ext4_dio_get_block, NULL, 0);
+	} else {
+		size_t count = iov_iter_count(iter);
+
+		ret = filemap_write_and_wait_range(mapping, iocb->ki_pos,
+						   iocb->ki_pos + count);
+		if (ret)
+			goto out_unlock;
+		ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
+					   iter, ext4_dio_get_block,
+					   NULL, NULL, 0);
+	}
+out_unlock:
+	inode_unlock_shared(inode);
 	return ret;
 }
 
-static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
-			      loff_t offset)
+static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
 	size_t count = iov_iter_count(iter);
+	loff_t offset = iocb->ki_pos;
 	ssize_t ret;
 
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
@@ -3455,10 +3588,10 @@ static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 		return 0;
 
 	trace_ext4_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
-	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
-		ret = ext4_ext_direct_IO(iocb, iter, offset);
+	if (iov_iter_rw(iter) == READ)
+		ret = ext4_direct_IO_read(iocb, iter);
 	else
-		ret = ext4_ind_direct_IO(iocb, iter, offset);
+		ret = ext4_direct_IO_write(iocb, iter);
 	trace_ext4_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), ret);
 	return ret;
 }
@@ -3534,10 +3667,7 @@ void ext4_set_aops(struct inode *inode)
 {
 	switch (ext4_inode_journal_mode(inode)) {
 	case EXT4_INODE_ORDERED_DATA_MODE:
-		ext4_set_inode_state(inode, EXT4_STATE_ORDERED_MODE);
-		break;
 	case EXT4_INODE_WRITEBACK_DATA_MODE:
-		ext4_clear_inode_state(inode, EXT4_STATE_ORDERED_MODE);
 		break;
 	case EXT4_INODE_JOURNAL_DATA_MODE:
 		inode->i_mapping->a_ops = &ext4_journalled_aops;
@@ -3603,7 +3733,7 @@ static int __ext4_block_zero_page_range(handle_t *handle,
 
 	if (!buffer_uptodate(bh)) {
 		err = -EIO;
-		ll_rw_block(READ, 1, &bh);
+		ll_rw_block(REQ_OP_READ, 0, 1, &bh);
 		wait_on_buffer(bh);
 		/* Uhhuh. Read error. Complain and punt. */
 		if (!buffer_uptodate(bh))
@@ -3611,9 +3741,9 @@ static int __ext4_block_zero_page_range(handle_t *handle,
 		if (S_ISREG(inode->i_mode) &&
 		    ext4_encrypted_inode(inode)) {
 			/* We expect the key to be set. */
-			BUG_ON(!ext4_has_encryption_key(inode));
+			BUG_ON(!fscrypt_has_encryption_key(inode));
 			BUG_ON(blocksize != PAGE_SIZE);
-			WARN_ON_ONCE(ext4_decrypt(page));
+			WARN_ON_ONCE(fscrypt_decrypt_page(page));
 		}
 	}
 	if (ext4_should_journal_data(inode)) {
@@ -3630,8 +3760,8 @@ static int __ext4_block_zero_page_range(handle_t *handle,
 	} else {
 		err = 0;
 		mark_buffer_dirty(bh);
-		if (ext4_test_inode_state(inode, EXT4_STATE_ORDERED_MODE))
-			err = ext4_jbd2_file_inode(handle, inode);
+		if (ext4_should_order_data(inode))
+			err = ext4_jbd2_inode_add_write(handle, inode);
 	}
 
 unlock:
@@ -3766,7 +3896,7 @@ int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
 }
 
 /*
- * ext4_punch_hole: punches a hole in a file by releaseing the blocks
+ * ext4_punch_hole: punches a hole in a file by releasing the blocks
  * associated with the given offset and length
  *
  * @inode:  File inode
@@ -3795,7 +3925,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 	 * Write out all dirty pages to avoid race conditions
 	 * Then release them.
 	 */
-	if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
+	if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
 		ret = filemap_write_and_wait_range(mapping, offset,
 						   offset + length - 1);
 		if (ret)
@@ -4186,7 +4316,7 @@ make_io:
 		trace_ext4_load_inode(inode);
 		get_bh(bh);
 		bh->b_end_io = end_buffer_read_sync;
-		submit_bh(READ | REQ_META | REQ_PRIO, bh);
+		submit_bh(REQ_OP_READ, REQ_META | REQ_PRIO, bh);
 		wait_on_buffer(bh);
 		if (!buffer_uptodate(bh)) {
 			EXT4_ERROR_INODE_BLOCK(inode, block,
@@ -4290,7 +4420,7 @@ static inline void ext4_iget_extra_inode(struct inode *inode,
 
 int ext4_get_projid(struct inode *inode, kprojid_t *projid)
 {
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, EXT4_FEATURE_RO_COMPAT_PROJECT))
+	if (!ext4_has_feature_project(inode->i_sb))
 		return -EOPNOTSUPP;
 	*projid = EXT4_I(inode)->i_projid;
 	return 0;
@@ -4357,7 +4487,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 	inode->i_mode = le16_to_cpu(raw_inode->i_mode);
 	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 (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_PROJECT) &&
+	if (ext4_has_feature_project(sb) &&
 	    EXT4_INODE_SIZE(sb) > EXT4_GOOD_OLD_INODE_SIZE &&
 	    EXT4_FITS_IN_INODE(raw_inode, ei, i_projid))
 		i_projid = (projid_t)le32_to_cpu(raw_inode->i_projid);
@@ -4690,14 +4820,14 @@ static int ext4_do_update_inode(handle_t *handle,
  * 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) {
+		if (ei->i_dtime && list_empty(&ei->i_orphan)) {
+			raw_inode->i_uid_high = 0;
+			raw_inode->i_gid_high = 0;
+		} else {
 			raw_inode->i_uid_high =
 				cpu_to_le16(high_16_bits(i_uid));
 			raw_inode->i_gid_high =
 				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(i_uid));
@@ -4761,8 +4891,7 @@ static int ext4_do_update_inode(handle_t *handle,
 		}
 	}
 
-	BUG_ON(!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
-			EXT4_FEATURE_RO_COMPAT_PROJECT) &&
+	BUG_ON(!ext4_has_feature_project(inode->i_sb) &&
 	       i_projid != EXT4_DEF_PROJID);
 
 	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
@@ -4949,7 +5078,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 	int orphan = 0;
 	const unsigned int ia_valid = attr->ia_valid;
 
-	error = inode_change_ok(inode, attr);
+	error = setattr_prepare(dentry, attr);
 	if (error)
 		return error;
 
@@ -5342,8 +5471,6 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
 						      sbi->s_want_extra_isize,
 						      iloc, handle);
 			if (ret) {
-				ext4_set_inode_state(inode,
-						     EXT4_STATE_NO_EXPAND);
 				if (mnt_count !=
 					le16_to_cpu(sbi->s_es->s_mnt_count)) {
 					ext4_warning(inode->i_sb,
@@ -5429,6 +5556,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 	journal_t *journal;
 	handle_t *handle;
 	int err;
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 
 	/*
 	 * We have to be very careful here: changing a data block's
@@ -5445,22 +5573,30 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 		return 0;
 	if (is_journal_aborted(journal))
 		return -EROFS;
-	/* We have to allocate physical blocks for delalloc blocks
-	 * before flushing journal. otherwise delalloc blocks can not
-	 * be allocated any more. even more truncate on delalloc blocks
-	 * could trigger BUG by flushing delalloc blocks in journal.
-	 * There is no delalloc block in non-journal data mode.
-	 */
-	if (val && test_opt(inode->i_sb, DELALLOC)) {
-		err = ext4_alloc_da_blocks(inode);
-		if (err < 0)
-			return err;
-	}
 
 	/* Wait for all existing dio workers */
 	ext4_inode_block_unlocked_dio(inode);
 	inode_dio_wait(inode);
 
+	/*
+	 * Before flushing the journal and switching inode's aops, we have
+	 * to flush all dirty data the inode has. There can be outstanding
+	 * delayed allocations, there can be unwritten extents created by
+	 * fallocate or buffered writes in dioread_nolock mode covered by
+	 * dirty data which can be converted only after flushing the dirty
+	 * data (and journalled aops don't know how to handle these cases).
+	 */
+	if (val) {
+		down_write(&EXT4_I(inode)->i_mmap_sem);
+		err = filemap_write_and_wait(inode->i_mapping);
+		if (err < 0) {
+			up_write(&EXT4_I(inode)->i_mmap_sem);
+			ext4_inode_resume_unlocked_dio(inode);
+			return err;
+		}
+	}
+
+	percpu_down_write(&sbi->s_journal_flag_rwsem);
 	jbd2_journal_lock_updates(journal);
 
 	/*
@@ -5477,6 +5613,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 		err = jbd2_journal_flush(journal);
 		if (err < 0) {
 			jbd2_journal_unlock_updates(journal);
+			percpu_up_write(&sbi->s_journal_flag_rwsem);
 			ext4_inode_resume_unlocked_dio(inode);
 			return err;
 		}
@@ -5485,6 +5622,10 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 	ext4_set_aops(inode);
 
 	jbd2_journal_unlock_updates(journal);
+	percpu_up_write(&sbi->s_journal_flag_rwsem);
+
+	if (val)
+		up_write(&EXT4_I(inode)->i_mmap_sem);
 	ext4_inode_resume_unlocked_dio(inode);
 
 	/* Finally we can mark the inode as dirty. */