Merge branch 'dedupe-cleanup' into overlayfs-next

Following series for stacking overlay files depends on this mini series.

6 files changed, 74 insertions, 84 deletions

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 118346aceea9..d9d924017dfb 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3247,8 +3247,9 @@ void btrfs_get_block_group_info(struct list_head *groups_list,
 				struct btrfs_ioctl_space_info *space);
 void btrfs_update_ioctl_balance_args(struct btrfs_fs_info *fs_info,
 			       struct btrfs_ioctl_balance_args *bargs);
-ssize_t btrfs_dedupe_file_range(struct file *src_file, u64 loff, u64 olen,
-			   struct file *dst_file, u64 dst_loff);
+int btrfs_dedupe_file_range(struct file *src_file, loff_t src_loff,
+			    struct file *dst_file, loff_t dst_loff,
+			    u64 olen);
 
 /* file.c */
 int __init btrfs_auto_defrag_init(void);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index c2837a32d689..755c9a306321 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3600,13 +3600,13 @@ out_free:
 	return ret;
 }
 
-ssize_t btrfs_dedupe_file_range(struct file *src_file, u64 loff, u64 olen,
-				struct file *dst_file, u64 dst_loff)
+int btrfs_dedupe_file_range(struct file *src_file, loff_t src_loff,
+			    struct file *dst_file, loff_t dst_loff,
+			    u64 olen)
 {
 	struct inode *src = file_inode(src_file);
 	struct inode *dst = file_inode(dst_file);
 	u64 bs = BTRFS_I(src)->root->fs_info->sb->s_blocksize;
-	ssize_t res;
 
 	if (WARN_ON_ONCE(bs < PAGE_SIZE)) {
 		/*
@@ -3617,10 +3617,7 @@ ssize_t btrfs_dedupe_file_range(struct file *src_file, u64 loff, u64 olen,
 		return -EINVAL;
 	}
 
-	res = btrfs_extent_same(src, loff, olen, dst, dst_loff);
-	if (res)
-		return res;
-	return olen;
+	return btrfs_extent_same(src, src_loff, olen, dst, dst_loff);
 }
 
 static int clone_finish_inode_update(struct btrfs_trans_handle *trans,
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 255f758af03a..9fa35cb6f6e0 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2537,19 +2537,14 @@ static int ocfs2_file_clone_range(struct file *file_in,
 					 len, false);
 }
 
-static ssize_t ocfs2_file_dedupe_range(struct file *src_file,
-				       u64 loff,
-				       u64 len,
-				       struct file *dst_file,
-				       u64 dst_loff)
+static int ocfs2_file_dedupe_range(struct file *file_in,
+				   loff_t pos_in,
+				   struct file *file_out,
+				   loff_t pos_out,
+				   u64 len)
 {
-	int error;
-
-	error = ocfs2_reflink_remap_range(src_file, loff, dst_file, dst_loff,
+	return ocfs2_reflink_remap_range(file_in, pos_in, file_out, pos_out,
 					  len, true);
-	if (error)
-		return error;
-	return len;
 }
 
 const struct inode_operations ocfs2_file_iops = {
diff --git a/fs/read_write.c b/fs/read_write.c
index 153f8f690490..cce4ebac34a8 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1964,6 +1964,44 @@ out_error:
 }
 EXPORT_SYMBOL(vfs_dedupe_file_range_compare);
 
+static int vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
+				     struct file *dst_file, loff_t dst_pos,
+				     u64 len)
+{
+	s64 ret;
+
+	ret = mnt_want_write_file(dst_file);
+	if (ret)
+		return ret;
+
+	ret = clone_verify_area(dst_file, dst_pos, len, true);
+	if (ret < 0)
+		goto out_drop_write;
+
+	ret = -EINVAL;
+	if (!(capable(CAP_SYS_ADMIN) || (dst_file->f_mode & FMODE_WRITE)))
+		goto out_drop_write;
+
+	ret = -EXDEV;
+	if (src_file->f_path.mnt != dst_file->f_path.mnt)
+		goto out_drop_write;
+
+	ret = -EISDIR;
+	if (S_ISDIR(file_inode(dst_file)->i_mode))
+		goto out_drop_write;
+
+	ret = -EINVAL;
+	if (!dst_file->f_op->dedupe_file_range)
+		goto out_drop_write;
+
+	ret = dst_file->f_op->dedupe_file_range(src_file, src_pos,
+						dst_file, dst_pos, len);
+out_drop_write:
+	mnt_drop_write_file(dst_file);
+
+	return ret;
+}
+
 int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same)
 {
 	struct file_dedupe_range_info *info;
@@ -1972,11 +2010,8 @@ int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same)
 	u64 len;
 	int i;
 	int ret;
-	bool is_admin = capable(CAP_SYS_ADMIN);
 	u16 count = same->dest_count;
-	struct file *dst_file;
-	loff_t dst_off;
-	ssize_t deduped;
+	int deduped;
 
 	if (!(file->f_mode & FMODE_READ))
 		return -EINVAL;
@@ -2003,6 +2038,9 @@ int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same)
 	if (off + len > i_size_read(src))
 		return -EINVAL;
 
+	/* Arbitrary 1G limit on a single dedupe request, can be raised. */
+	len = min_t(u64, len, 1 << 30);
+
 	/* pre-format output fields to sane values */
 	for (i = 0; i < count; i++) {
 		same->info[i].bytes_deduped = 0ULL;
@@ -2010,54 +2048,28 @@ int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same)
 	}
 
 	for (i = 0, info = same->info; i < count; i++, info++) {
-		struct inode *dst;
 		struct fd dst_fd = fdget(info->dest_fd);
+		struct file *dst_file = dst_fd.file;
 
-		dst_file = dst_fd.file;
 		if (!dst_file) {
 			info->status = -EBADF;
 			goto next_loop;
 		}
-		dst = file_inode(dst_file);
-
-		ret = mnt_want_write_file(dst_file);
-		if (ret) {
-			info->status = ret;
-			goto next_fdput;
-		}
-
-		dst_off = info->dest_offset;
-		ret = clone_verify_area(dst_file, dst_off, len, true);
-		if (ret < 0) {
-			info->status = ret;
-			goto next_file;
-		}
-		ret = 0;
 
 		if (info->reserved) {
 			info->status = -EINVAL;
-		} else if (!(is_admin || (dst_file->f_mode & FMODE_WRITE))) {
-			info->status = -EINVAL;
-		} else if (file->f_path.mnt != dst_file->f_path.mnt) {
-			info->status = -EXDEV;
-		} else if (S_ISDIR(dst->i_mode)) {
-			info->status = -EISDIR;
-		} else if (dst_file->f_op->dedupe_file_range == NULL) {
-			info->status = -EINVAL;
-		} else {
-			deduped = dst_file->f_op->dedupe_file_range(file, off,
-							len, dst_file,
-							info->dest_offset);
-			if (deduped == -EBADE)
-				info->status = FILE_DEDUPE_RANGE_DIFFERS;
-			else if (deduped < 0)
-				info->status = deduped;
-			else
-				info->bytes_deduped += deduped;
+			goto next_fdput;
 		}
 
-next_file:
-		mnt_drop_write_file(dst_file);
+		deduped = vfs_dedupe_file_range_one(file, off, dst_file,
+						    info->dest_offset, len);
+		if (deduped == -EBADE)
+			info->status = FILE_DEDUPE_RANGE_DIFFERS;
+		else if (deduped < 0)
+			info->status = deduped;
+		else
+			info->bytes_deduped = len;
+
 next_fdput:
 		fdput(dst_fd);
 next_loop:
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index a3e7767a5715..0f40ba54d83f 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -933,31 +933,16 @@ xfs_file_clone_range(
 				     len, false);
 }
 
-STATIC ssize_t
+STATIC int
 xfs_file_dedupe_range(
-	struct file	*src_file,
-	u64		loff,
-	u64		len,
-	struct file	*dst_file,
-	u64		dst_loff)
+	struct file	*file_in,
+	loff_t		pos_in,
+	struct file	*file_out,
+	loff_t		pos_out,
+	u64		len)
 {
-	struct inode	*srci = file_inode(src_file);
-	u64		max_dedupe;
-	int		error;
-
-	/*
-	 * Since we have to read all these pages in to compare them, cut
-	 * it off at MAX_RW_COUNT/2 rounded down to the nearest block.
-	 * That means we won't do more than MAX_RW_COUNT IO per request.
-	 */
-	max_dedupe = (MAX_RW_COUNT >> 1) & ~(i_blocksize(srci) - 1);
-	if (len > max_dedupe)
-		len = max_dedupe;
-	error = xfs_reflink_remap_range(src_file, loff, dst_file, dst_loff,
+	return xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out,
 				     len, true);
-	if (error)
-		return error;
-	return len;
 }
 
 STATIC int
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 4ff7b7012186..5ce2b413abc6 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1751,7 +1751,7 @@ struct file_operations {
 			loff_t, size_t, unsigned int);
 	int (*clone_file_range)(struct file *, loff_t, struct file *, loff_t,
 			u64);
-	ssize_t (*dedupe_file_range)(struct file *, u64, u64, struct file *,
+	int (*dedupe_file_range)(struct file *, loff_t, struct file *, loff_t,
 			u64);
 } __randomize_layout;