1 files changed, 91 insertions, 19 deletions

diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 65c077d9a5e9..6831534924e1 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -32,6 +32,7 @@
 #include <linux/buffer_head.h>
 #include <linux/mpage.h>
 #include <linux/fiemap.h>
+#include <linux/iomap.h>
 #include <linux/namei.h>
 #include <linux/uio.h>
 #include "ext2.h"
@@ -618,7 +619,7 @@ static void ext2_splice_branch(struct inode *inode,
  */
 static int ext2_get_blocks(struct inode *inode,
 			   sector_t iblock, unsigned long maxblocks,
-			   struct buffer_head *bh_result,
+			   u32 *bno, bool *new, bool *boundary,
 			   int create)
 {
 	int err = -EIO;
@@ -644,7 +645,6 @@ static int ext2_get_blocks(struct inode *inode,
 	/* Simplest case - block found, no allocation needed */
 	if (!partial) {
 		first_block = le32_to_cpu(chain[depth - 1].key);
-		clear_buffer_new(bh_result); /* What's this do? */
 		count++;
 		/*map more blocks*/
 		while (count < maxblocks && count <= blocks_to_boundary) {
@@ -699,7 +699,6 @@ static int ext2_get_blocks(struct inode *inode,
 			mutex_unlock(&ei->truncate_mutex);
 			if (err)
 				goto cleanup;
-			clear_buffer_new(bh_result);
 			goto got_it;
 		}
 	}
@@ -733,6 +732,16 @@ static int ext2_get_blocks(struct inode *inode,
 	}
 
 	if (IS_DAX(inode)) {
+		int i;
+
+		/*
+		 * We must unmap blocks before zeroing so that writeback cannot
+		 * overwrite zeros with stale data from block device page cache.
+		 */
+		for (i = 0; i < count; i++) {
+			unmap_underlying_metadata(inode->i_sb->s_bdev,
+					le32_to_cpu(chain[depth-1].key) + i);
+		}
 		/*
 		 * block must be initialised before we put it in the tree
 		 * so that it's not found by another thread before it's
@@ -745,15 +754,16 @@ static int ext2_get_blocks(struct inode *inode,
 			mutex_unlock(&ei->truncate_mutex);
 			goto cleanup;
 		}
-	} else
-		set_buffer_new(bh_result);
+	} else {
+		*new = true;
+	}
 
 	ext2_splice_branch(inode, iblock, partial, indirect_blks, count);
 	mutex_unlock(&ei->truncate_mutex);
 got_it:
-	map_bh(bh_result, inode->i_sb, le32_to_cpu(chain[depth-1].key));
+	*bno = le32_to_cpu(chain[depth-1].key);
 	if (count > blocks_to_boundary)
-		set_buffer_boundary(bh_result);
+		*boundary = true;
 	err = count;
 	/* Clean up and exit */
 	partial = chain + depth - 1;	/* the whole chain */
@@ -765,19 +775,82 @@ cleanup:
 	return err;
 }
 
-int ext2_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create)
+int ext2_get_block(struct inode *inode, sector_t iblock,
+		struct buffer_head *bh_result, int create)
 {
 	unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
-	int ret = ext2_get_blocks(inode, iblock, max_blocks,
-			      bh_result, create);
-	if (ret > 0) {
-		bh_result->b_size = (ret << inode->i_blkbits);
-		ret = 0;
+	bool new = false, boundary = false;
+	u32 bno;
+	int ret;
+
+	ret = ext2_get_blocks(inode, iblock, max_blocks, &bno, &new, &boundary,
+			create);
+	if (ret <= 0)
+		return ret;
+
+	map_bh(bh_result, inode->i_sb, bno);
+	bh_result->b_size = (ret << inode->i_blkbits);
+	if (new)
+		set_buffer_new(bh_result);
+	if (boundary)
+		set_buffer_boundary(bh_result);
+	return 0;
+
+}
+
+#ifdef CONFIG_FS_DAX
+static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
+		unsigned flags, struct iomap *iomap)
+{
+	unsigned int blkbits = inode->i_blkbits;
+	unsigned long first_block = offset >> blkbits;
+	unsigned long max_blocks = (length + (1 << blkbits) - 1) >> blkbits;
+	bool new = false, boundary = false;
+	u32 bno;
+	int ret;
+
+	ret = ext2_get_blocks(inode, first_block, max_blocks,
+			&bno, &new, &boundary, flags & IOMAP_WRITE);
+	if (ret < 0)
+		return ret;
+
+	iomap->flags = 0;
+	iomap->bdev = inode->i_sb->s_bdev;
+	iomap->offset = (u64)first_block << blkbits;
+
+	if (ret == 0) {
+		iomap->type = IOMAP_HOLE;
+		iomap->blkno = IOMAP_NULL_BLOCK;
+		iomap->length = 1 << blkbits;
+	} else {
+		iomap->type = IOMAP_MAPPED;
+		iomap->blkno = (sector_t)bno << (blkbits - 9);
+		iomap->length = (u64)ret << blkbits;
+		iomap->flags |= IOMAP_F_MERGED;
 	}
-	return ret;
 
+	if (new)
+		iomap->flags |= IOMAP_F_NEW;
+	return 0;
 }
 
+static int
+ext2_iomap_end(struct inode *inode, loff_t offset, loff_t length,
+		ssize_t written, unsigned flags, struct iomap *iomap)
+{
+	if (iomap->type == IOMAP_MAPPED &&
+	    written < length &&
+	    (flags & IOMAP_WRITE))
+		ext2_write_failed(inode->i_mapping, offset + length);
+	return 0;
+}
+
+struct iomap_ops ext2_iomap_ops = {
+	.iomap_begin		= ext2_iomap_begin,
+	.iomap_end		= ext2_iomap_end,
+};
+#endif /* CONFIG_FS_DAX */
+
 int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		u64 start, u64 len)
 {
@@ -863,11 +936,10 @@ ext2_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	loff_t offset = iocb->ki_pos;
 	ssize_t ret;
 
-	if (IS_DAX(inode))
-		ret = dax_do_io(iocb, inode, iter, ext2_get_block, NULL,
-				DIO_LOCKING);
-	else
-		ret = blockdev_direct_IO(iocb, inode, iter, ext2_get_block);
+	if (WARN_ON_ONCE(IS_DAX(inode)))
+		return -EIO;
+
+	ret = blockdev_direct_IO(iocb, inode, iter, ext2_get_block);
 	if (ret < 0 && iov_iter_rw(iter) == WRITE)
 		ext2_write_failed(mapping, offset + count);
 	return ret;