From 1383a7ed67490fb00d793e36c7a4d599ff88a64d Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Tue, 30 Oct 2018 10:40:31 +1100
Subject: vfs: check file ranges before cloning files

Move the file range checks from vfs_clone_file_prep into a separate
generic_remap_checks function so that all the checks are collected in a
central location.  This forms the basis for adding more checks from
generic_write_checks that will make cloning's input checking more
consistent with write input checking.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>
---
 include/linux/fs.h | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 897eae8faee1..ba93a6e7dac4 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1825,9 +1825,9 @@ extern ssize_t vfs_readv(struct file *, const struct iovec __user *,
 		unsigned long, loff_t *, rwf_t);
 extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *,
 				   loff_t, size_t, unsigned int);
-extern int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in,
-				      struct inode *inode_out, loff_t pos_out,
-				      u64 *len, bool is_dedupe);
+extern int vfs_clone_file_prep(struct file *file_in, loff_t pos_in,
+			       struct file *file_out, loff_t pos_out,
+			       u64 *count, bool is_dedupe);
 extern int do_clone_file_range(struct file *file_in, loff_t pos_in,
 			       struct file *file_out, loff_t pos_out, u64 len);
 extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in,
@@ -2967,6 +2967,9 @@ extern int sb_min_blocksize(struct super_block *, int);
 extern int generic_file_mmap(struct file *, struct vm_area_struct *);
 extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
 extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *);
+extern int generic_remap_checks(struct file *file_in, loff_t pos_in,
+				struct file *file_out, loff_t pos_out,
+				uint64_t *count, bool is_dedupe);
 extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *);
 extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *);
 extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *);
-- 
cgit v1.2.3


From a83ab01a62e61616ebb8b97f90f568c1214dc10d Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Tue, 30 Oct 2018 10:41:08 +1100
Subject: vfs: rename vfs_clone_file_prep to be more descriptive

The vfs_clone_file_prep is a generic function to be called by filesystem
implementations only.  Rename the prefix to generic_ and make it more
clear that it applies to remap operations, not just clones.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>
---
 fs/ocfs2/refcounttree.c | 2 +-
 fs/read_write.c         | 8 ++++----
 fs/xfs/xfs_reflink.c    | 2 +-
 include/linux/fs.h      | 6 +++---
 4 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index 19e03936c5e1..36c56dfbe485 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -4850,7 +4850,7 @@ int ocfs2_reflink_remap_range(struct file *file_in,
 	    (OCFS2_I(inode_out)->ip_flags & OCFS2_INODE_SYSTEM_FILE))
 		goto out_unlock;
 
-	ret = vfs_clone_file_prep(file_in, pos_in, file_out, pos_out,
+	ret = generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out,
 			&len, is_dedupe);
 	if (ret <= 0)
 		goto out_unlock;
diff --git a/fs/read_write.c b/fs/read_write.c
index f5395d8da741..aca75a97a695 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1745,9 +1745,9 @@ static int generic_remap_check_len(struct inode *inode_in,
  * Returns: 0 for "nothing to clone", 1 for "something to clone", or
  * the usual negative error code.
  */
-int vfs_clone_file_prep(struct file *file_in, loff_t pos_in,
-			struct file *file_out, loff_t pos_out,
-			u64 *len, bool is_dedupe)
+int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
+				  struct file *file_out, loff_t pos_out,
+				  u64 *len, bool is_dedupe)
 {
 	struct inode *inode_in = file_inode(file_in);
 	struct inode *inode_out = file_inode(file_out);
@@ -1822,7 +1822,7 @@ int vfs_clone_file_prep(struct file *file_in, loff_t pos_in,
 
 	return 1;
 }
-EXPORT_SYMBOL(vfs_clone_file_prep);
+EXPORT_SYMBOL(generic_remap_file_range_prep);
 
 int do_clone_file_range(struct file *file_in, loff_t pos_in,
 			struct file *file_out, loff_t pos_out, u64 len)
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 281d5f53f2ec..a7757a128a78 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1326,7 +1326,7 @@ xfs_reflink_remap_prep(
 	if (IS_DAX(inode_in) || IS_DAX(inode_out))
 		goto out_unlock;
 
-	ret = vfs_clone_file_prep(file_in, pos_in, file_out, pos_out,
+	ret = generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out,
 			len, is_dedupe);
 	if (ret <= 0)
 		goto out_unlock;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ba93a6e7dac4..55729e1c2e75 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1825,9 +1825,9 @@ extern ssize_t vfs_readv(struct file *, const struct iovec __user *,
 		unsigned long, loff_t *, rwf_t);
 extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *,
 				   loff_t, size_t, unsigned int);
-extern int vfs_clone_file_prep(struct file *file_in, loff_t pos_in,
-			       struct file *file_out, loff_t pos_out,
-			       u64 *count, bool is_dedupe);
+extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
+					 struct file *file_out, loff_t pos_out,
+					 u64 *count, bool is_dedupe);
 extern int do_clone_file_range(struct file *file_in, loff_t pos_in,
 			       struct file *file_out, loff_t pos_out, u64 len);
 extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in,
-- 
cgit v1.2.3


From 2e5dfc99f2e61c42083ba742395e7a7b353513d1 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Tue, 30 Oct 2018 10:41:21 +1100
Subject: vfs: combine the clone and dedupe into a single remap_file_range

Combine the clone_file_range and dedupe_file_range operations into a
single remap_file_range file operation dispatch since they're
fundamentally the same operation.  The differences between the two can
be made in the prep functions.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dave Chinner <david@fromorbit.com>
---
 Documentation/filesystems/porting |  5 +++++
 Documentation/filesystems/vfs.txt | 20 +++++++++++------
 fs/btrfs/ctree.h                  |  8 +++----
 fs/btrfs/file.c                   |  3 +--
 fs/btrfs/ioctl.c                  | 45 ++++++++++++++++++++-------------------
 fs/cifs/cifsfs.c                  | 22 +++++++++++--------
 fs/nfs/nfs4file.c                 | 10 ++++++---
 fs/ocfs2/file.c                   | 24 +++++++--------------
 fs/overlayfs/file.c               | 30 +++++++++++++++-----------
 fs/read_write.c                   | 18 ++++++++--------
 fs/xfs/xfs_file.c                 | 23 ++++++--------------
 include/linux/fs.h                | 25 ++++++++++++++++++----
 12 files changed, 127 insertions(+), 106 deletions(-)

(limited to 'include')

diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting
index 7b7b845c490a..e6d4466268dd 100644
--- a/Documentation/filesystems/porting
+++ b/Documentation/filesystems/porting
@@ -622,3 +622,8 @@ in your dentry operations instead.
 	alloc_file_clone(file, flags, ops) does not affect any caller's references.
 	On success you get a new struct file sharing the mount/dentry with the
 	original, on failure - ERR_PTR().
+--
+[mandatory]
+	->clone_file_range() and ->dedupe_file_range have been replaced with
+	->remap_file_range().  See Documentation/filesystems/vfs.txt for more
+	information.
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index a6c6a8af48a2..6f5babfee27b 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -883,8 +883,9 @@ struct file_operations {
 	unsigned (*mmap_capabilities)(struct file *);
 #endif
 	ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int);
-	int (*clone_file_range)(struct file *, loff_t, struct file *, loff_t, u64);
-	int (*dedupe_file_range)(struct file *, loff_t, struct file *, loff_t, u64);
+	int (*remap_file_range)(struct file *file_in, loff_t pos_in,
+				struct file *file_out, loff_t pos_out,
+				u64 len, unsigned int remap_flags);
 	int (*fadvise)(struct file *, loff_t, loff_t, int);
 };
 
@@ -960,11 +961,16 @@ otherwise noted.
 
   copy_file_range: called by the copy_file_range(2) system call.
 
-  clone_file_range: called by the ioctl(2) system call for FICLONERANGE and
-	FICLONE commands.
-
-  dedupe_file_range: called by the ioctl(2) system call for FIDEDUPERANGE
-	command.
+  remap_file_range: called by the ioctl(2) system call for FICLONERANGE and
+	FICLONE and FIDEDUPERANGE commands to remap file ranges.  An
+	implementation should remap len bytes at pos_in of the source file into
+	the dest file at pos_out.  Implementations must handle callers passing
+	in len == 0; this means "remap to the end of the source file".  The
+	return value should be zero if all bytes were remapped, or the usual
+	negative error code if the remapping did not succeed completely.
+	The remap_flags parameter accepts REMAP_FILE_* flags.  If
+	REMAP_FILE_DEDUP is set then the implementation must only remap if the
+	requested file ranges have identical contents.
 
   fadvise: possibly called by the fadvise64() system call.
 
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 2cddfe7806a4..124a05662fc2 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3218,9 +3218,6 @@ 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);
-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);
@@ -3250,8 +3247,9 @@ int btrfs_dirty_pages(struct inode *inode, struct page **pages,
 		      size_t num_pages, loff_t pos, size_t write_bytes,
 		      struct extent_state **cached);
 int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end);
-int btrfs_clone_file_range(struct file *file_in, loff_t pos_in,
-			   struct file *file_out, loff_t pos_out, u64 len);
+int btrfs_remap_file_range(struct file *file_in, loff_t pos_in,
+			   struct file *file_out, loff_t pos_out, u64 len,
+			   unsigned int remap_flags);
 
 /* tree-defrag.c */
 int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 2be00e873e92..9a963f061393 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -3269,8 +3269,7 @@ const struct file_operations btrfs_file_operations = {
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= btrfs_compat_ioctl,
 #endif
-	.clone_file_range = btrfs_clone_file_range,
-	.dedupe_file_range = btrfs_dedupe_file_range,
+	.remap_file_range = btrfs_remap_file_range,
 };
 
 void __cold btrfs_auto_defrag_exit(void)
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index d60b6caf09e8..bfd99c66723e 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3627,26 +3627,6 @@ out_unlock:
 	return ret;
 }
 
-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;
-
-	if (WARN_ON_ONCE(bs < PAGE_SIZE)) {
-		/*
-		 * Btrfs does not support blocksize < page_size. As a
-		 * result, btrfs_cmp_data() won't correctly handle
-		 * this situation without an update.
-		 */
-		return -EINVAL;
-	}
-
-	return btrfs_extent_same(src, src_loff, olen, dst, dst_loff);
-}
-
 static int clone_finish_inode_update(struct btrfs_trans_handle *trans,
 				     struct inode *inode,
 				     u64 endoff,
@@ -4348,9 +4328,30 @@ out_unlock:
 	return ret;
 }
 
-int btrfs_clone_file_range(struct file *src_file, loff_t off,
-		struct file *dst_file, loff_t destoff, u64 len)
+int btrfs_remap_file_range(struct file *src_file, loff_t off,
+		struct file *dst_file, loff_t destoff, u64 len,
+		unsigned int remap_flags)
 {
+	if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY))
+		return -EINVAL;
+
+	if (remap_flags & REMAP_FILE_DEDUP) {
+		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;
+
+		if (WARN_ON_ONCE(bs < PAGE_SIZE)) {
+			/*
+			 * Btrfs does not support blocksize < page_size. As a
+			 * result, btrfs_cmp_data() won't correctly handle
+			 * this situation without an update.
+			 */
+			return -EINVAL;
+		}
+
+		return btrfs_extent_same(src, off, len, dst, destoff);
+	}
+
 	return btrfs_clone_files(dst_file, src_file, off, len, destoff);
 }
 
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 7065426b3280..e8144d0dcde2 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -975,8 +975,9 @@ const struct inode_operations cifs_symlink_inode_ops = {
 	.listxattr = cifs_listxattr,
 };
 
-static int cifs_clone_file_range(struct file *src_file, loff_t off,
-		struct file *dst_file, loff_t destoff, u64 len)
+static int cifs_remap_file_range(struct file *src_file, loff_t off,
+		struct file *dst_file, loff_t destoff, u64 len,
+		unsigned int remap_flags)
 {
 	struct inode *src_inode = file_inode(src_file);
 	struct inode *target_inode = file_inode(dst_file);
@@ -986,6 +987,9 @@ static int cifs_clone_file_range(struct file *src_file, loff_t off,
 	unsigned int xid;
 	int rc;
 
+	if (remap_flags & ~REMAP_FILE_ADVISORY)
+		return -EINVAL;
+
 	cifs_dbg(FYI, "clone range\n");
 
 	xid = get_xid();
@@ -1134,7 +1138,7 @@ const struct file_operations cifs_file_ops = {
 	.llseek = cifs_llseek,
 	.unlocked_ioctl	= cifs_ioctl,
 	.copy_file_range = cifs_copy_file_range,
-	.clone_file_range = cifs_clone_file_range,
+	.remap_file_range = cifs_remap_file_range,
 	.setlease = cifs_setlease,
 	.fallocate = cifs_fallocate,
 };
@@ -1153,7 +1157,7 @@ const struct file_operations cifs_file_strict_ops = {
 	.llseek = cifs_llseek,
 	.unlocked_ioctl	= cifs_ioctl,
 	.copy_file_range = cifs_copy_file_range,
-	.clone_file_range = cifs_clone_file_range,
+	.remap_file_range = cifs_remap_file_range,
 	.setlease = cifs_setlease,
 	.fallocate = cifs_fallocate,
 };
@@ -1172,7 +1176,7 @@ const struct file_operations cifs_file_direct_ops = {
 	.splice_write = iter_file_splice_write,
 	.unlocked_ioctl  = cifs_ioctl,
 	.copy_file_range = cifs_copy_file_range,
-	.clone_file_range = cifs_clone_file_range,
+	.remap_file_range = cifs_remap_file_range,
 	.llseek = cifs_llseek,
 	.setlease = cifs_setlease,
 	.fallocate = cifs_fallocate,
@@ -1191,7 +1195,7 @@ const struct file_operations cifs_file_nobrl_ops = {
 	.llseek = cifs_llseek,
 	.unlocked_ioctl	= cifs_ioctl,
 	.copy_file_range = cifs_copy_file_range,
-	.clone_file_range = cifs_clone_file_range,
+	.remap_file_range = cifs_remap_file_range,
 	.setlease = cifs_setlease,
 	.fallocate = cifs_fallocate,
 };
@@ -1209,7 +1213,7 @@ const struct file_operations cifs_file_strict_nobrl_ops = {
 	.llseek = cifs_llseek,
 	.unlocked_ioctl	= cifs_ioctl,
 	.copy_file_range = cifs_copy_file_range,
-	.clone_file_range = cifs_clone_file_range,
+	.remap_file_range = cifs_remap_file_range,
 	.setlease = cifs_setlease,
 	.fallocate = cifs_fallocate,
 };
@@ -1227,7 +1231,7 @@ const struct file_operations cifs_file_direct_nobrl_ops = {
 	.splice_write = iter_file_splice_write,
 	.unlocked_ioctl  = cifs_ioctl,
 	.copy_file_range = cifs_copy_file_range,
-	.clone_file_range = cifs_clone_file_range,
+	.remap_file_range = cifs_remap_file_range,
 	.llseek = cifs_llseek,
 	.setlease = cifs_setlease,
 	.fallocate = cifs_fallocate,
@@ -1239,7 +1243,7 @@ const struct file_operations cifs_dir_ops = {
 	.read    = generic_read_dir,
 	.unlocked_ioctl  = cifs_ioctl,
 	.copy_file_range = cifs_copy_file_range,
-	.clone_file_range = cifs_clone_file_range,
+	.remap_file_range = cifs_remap_file_range,
 	.llseek = generic_file_llseek,
 	.fsync = cifs_dir_fsync,
 };
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 4288a6ecaf75..ae5780ce41dc 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -180,8 +180,9 @@ static long nfs42_fallocate(struct file *filep, int mode, loff_t offset, loff_t
 	return nfs42_proc_allocate(filep, offset, len);
 }
 
-static int nfs42_clone_file_range(struct file *src_file, loff_t src_off,
-		struct file *dst_file, loff_t dst_off, u64 count)
+static int nfs42_remap_file_range(struct file *src_file, loff_t src_off,
+		struct file *dst_file, loff_t dst_off, u64 count,
+		unsigned int remap_flags)
 {
 	struct inode *dst_inode = file_inode(dst_file);
 	struct nfs_server *server = NFS_SERVER(dst_inode);
@@ -190,6 +191,9 @@ static int nfs42_clone_file_range(struct file *src_file, loff_t src_off,
 	bool same_inode = false;
 	int ret;
 
+	if (remap_flags & ~REMAP_FILE_ADVISORY)
+		return -EINVAL;
+
 	/* check alignment w.r.t. clone_blksize */
 	ret = -EINVAL;
 	if (bs) {
@@ -262,7 +266,7 @@ const struct file_operations nfs4_file_operations = {
 	.copy_file_range = nfs4_copy_file_range,
 	.llseek		= nfs4_file_llseek,
 	.fallocate	= nfs42_fallocate,
-	.clone_file_range = nfs42_clone_file_range,
+	.remap_file_range = nfs42_remap_file_range,
 #else
 	.llseek		= nfs_file_llseek,
 #endif
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 9fa35cb6f6e0..0b757a24567c 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2527,24 +2527,18 @@ out:
 	return offset;
 }
 
-static int ocfs2_file_clone_range(struct file *file_in,
+static int ocfs2_remap_file_range(struct file *file_in,
 				  loff_t pos_in,
 				  struct file *file_out,
 				  loff_t pos_out,
-				  u64 len)
+				  u64 len,
+				  unsigned int remap_flags)
 {
-	return ocfs2_reflink_remap_range(file_in, pos_in, file_out, pos_out,
-					 len, false);
-}
+	if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY))
+		return -EINVAL;
 
-static int ocfs2_file_dedupe_range(struct file *file_in,
-				   loff_t pos_in,
-				   struct file *file_out,
-				   loff_t pos_out,
-				   u64 len)
-{
 	return ocfs2_reflink_remap_range(file_in, pos_in, file_out, pos_out,
-					  len, true);
+					 len, remap_flags & REMAP_FILE_DEDUP);
 }
 
 const struct inode_operations ocfs2_file_iops = {
@@ -2586,8 +2580,7 @@ const struct file_operations ocfs2_fops = {
 	.splice_read	= generic_file_splice_read,
 	.splice_write	= iter_file_splice_write,
 	.fallocate	= ocfs2_fallocate,
-	.clone_file_range = ocfs2_file_clone_range,
-	.dedupe_file_range = ocfs2_file_dedupe_range,
+	.remap_file_range = ocfs2_remap_file_range,
 };
 
 const struct file_operations ocfs2_dops = {
@@ -2633,8 +2626,7 @@ const struct file_operations ocfs2_fops_no_plocks = {
 	.splice_read	= generic_file_splice_read,
 	.splice_write	= iter_file_splice_write,
 	.fallocate	= ocfs2_fallocate,
-	.clone_file_range = ocfs2_file_clone_range,
-	.dedupe_file_range = ocfs2_file_dedupe_range,
+	.remap_file_range = ocfs2_remap_file_range,
 };
 
 const struct file_operations ocfs2_dops_no_plocks = {
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index 986313da0c88..fffb36fd5920 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -489,26 +489,31 @@ static ssize_t ovl_copy_file_range(struct file *file_in, loff_t pos_in,
 			    OVL_COPY);
 }
 
-static int ovl_clone_file_range(struct file *file_in, loff_t pos_in,
-				struct file *file_out, loff_t pos_out, u64 len)
+static int ovl_remap_file_range(struct file *file_in, loff_t pos_in,
+				struct file *file_out, loff_t pos_out,
+				u64 len, unsigned int remap_flags)
 {
-	return ovl_copyfile(file_in, pos_in, file_out, pos_out, len, 0,
-			    OVL_CLONE);
-}
+	enum ovl_copyop op;
+
+	if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY))
+		return -EINVAL;
+
+	if (remap_flags & REMAP_FILE_DEDUP)
+		op = OVL_DEDUPE;
+	else
+		op = OVL_CLONE;
 
-static int ovl_dedupe_file_range(struct file *file_in, loff_t pos_in,
-				 struct file *file_out, loff_t pos_out, u64 len)
-{
 	/*
 	 * Don't copy up because of a dedupe request, this wouldn't make sense
 	 * most of the time (data would be duplicated instead of deduplicated).
 	 */
-	if (!ovl_inode_upper(file_inode(file_in)) ||
-	    !ovl_inode_upper(file_inode(file_out)))
+	if (op == OVL_DEDUPE &&
+	    (!ovl_inode_upper(file_inode(file_in)) ||
+	     !ovl_inode_upper(file_inode(file_out))))
 		return -EPERM;
 
 	return ovl_copyfile(file_in, pos_in, file_out, pos_out, len, 0,
-			    OVL_DEDUPE);
+			    op);
 }
 
 const struct file_operations ovl_file_operations = {
@@ -525,6 +530,5 @@ const struct file_operations ovl_file_operations = {
 	.compat_ioctl	= ovl_compat_ioctl,
 
 	.copy_file_range	= ovl_copy_file_range,
-	.clone_file_range	= ovl_clone_file_range,
-	.dedupe_file_range	= ovl_dedupe_file_range,
+	.remap_file_range	= ovl_remap_file_range,
 };
diff --git a/fs/read_write.c b/fs/read_write.c
index 734c5661fb69..766bdcb381f3 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1588,9 +1588,9 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
 	 * Try cloning first, this is supported by more file systems, and
 	 * more efficient if both clone and copy are supported (e.g. NFS).
 	 */
-	if (file_in->f_op->clone_file_range) {
-		ret = file_in->f_op->clone_file_range(file_in, pos_in,
-				file_out, pos_out, len);
+	if (file_in->f_op->remap_file_range) {
+		ret = file_in->f_op->remap_file_range(file_in, pos_in,
+				file_out, pos_out, len, 0);
 		if (ret == 0) {
 			ret = len;
 			goto done;
@@ -1849,7 +1849,7 @@ int do_clone_file_range(struct file *file_in, loff_t pos_in,
 	    (file_out->f_flags & O_APPEND))
 		return -EBADF;
 
-	if (!file_in->f_op->clone_file_range)
+	if (!file_in->f_op->remap_file_range)
 		return -EOPNOTSUPP;
 
 	ret = remap_verify_area(file_in, pos_in, len, false);
@@ -1860,8 +1860,8 @@ int do_clone_file_range(struct file *file_in, loff_t pos_in,
 	if (ret)
 		return ret;
 
-	ret = file_in->f_op->clone_file_range(file_in, pos_in,
-			file_out, pos_out, len);
+	ret = file_in->f_op->remap_file_range(file_in, pos_in,
+			file_out, pos_out, len, 0);
 	if (!ret) {
 		fsnotify_access(file_in);
 		fsnotify_modify(file_out);
@@ -2006,7 +2006,7 @@ int vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
 		goto out_drop_write;
 
 	ret = -EINVAL;
-	if (!dst_file->f_op->dedupe_file_range)
+	if (!dst_file->f_op->remap_file_range)
 		goto out_drop_write;
 
 	if (len == 0) {
@@ -2014,8 +2014,8 @@ int vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
 		goto out_drop_write;
 	}
 
-	ret = dst_file->f_op->dedupe_file_range(src_file, src_pos,
-						dst_file, dst_pos, len);
+	ret = dst_file->f_op->remap_file_range(src_file, src_pos, dst_file,
+			dst_pos, len, REMAP_FILE_DEDUP);
 out_drop_write:
 	mnt_drop_write_file(dst_file);
 
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 61a5ad2600e8..2ad94d508f80 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -920,27 +920,19 @@ out_unlock:
 }
 
 STATIC int
-xfs_file_clone_range(
+xfs_file_remap_range(
 	struct file	*file_in,
 	loff_t		pos_in,
 	struct file	*file_out,
 	loff_t		pos_out,
-	u64		len)
+	u64		len,
+	unsigned int	remap_flags)
 {
-	return xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out,
-				     len, false);
-}
+	if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY))
+		return -EINVAL;
 
-STATIC int
-xfs_file_dedupe_range(
-	struct file	*file_in,
-	loff_t		pos_in,
-	struct file	*file_out,
-	loff_t		pos_out,
-	u64		len)
-{
 	return xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out,
-				     len, true);
+			len, remap_flags & REMAP_FILE_DEDUP);
 }
 
 STATIC int
@@ -1175,8 +1167,7 @@ const struct file_operations xfs_file_operations = {
 	.fsync		= xfs_file_fsync,
 	.get_unmapped_area = thp_get_unmapped_area,
 	.fallocate	= xfs_file_fallocate,
-	.clone_file_range = xfs_file_clone_range,
-	.dedupe_file_range = xfs_file_dedupe_range,
+	.remap_file_range = xfs_file_remap_range,
 };
 
 const struct file_operations xfs_dir_file_operations = {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 55729e1c2e75..888cef35c7d7 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1721,6 +1721,24 @@ struct block_device_operations;
 #define NOMMU_VMFLAGS \
 	(NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC)
 
+/*
+ * These flags control the behavior of the remap_file_range function pointer.
+ * If it is called with len == 0 that means "remap to end of source file".
+ * See Documentation/filesystems/vfs.txt for more details about this call.
+ *
+ * REMAP_FILE_DEDUP: only remap if contents identical (i.e. deduplicate)
+ */
+#define REMAP_FILE_DEDUP		(1 << 0)
+
+/*
+ * These flags signal that the caller is ok with altering various aspects of
+ * the behavior of the remap operation.  The changes must be made by the
+ * implementation; the vfs remap helper functions can take advantage of them.
+ * Flags in this category exist to preserve the quirky behavior of the hoisted
+ * btrfs clone/dedupe ioctls.
+ * There are no flags yet, but subsequent commits will add some.
+ */
+#define REMAP_FILE_ADVISORY		(0)
 
 struct iov_iter;
 
@@ -1759,10 +1777,9 @@ struct file_operations {
 #endif
 	ssize_t (*copy_file_range)(struct file *, loff_t, struct file *,
 			loff_t, size_t, unsigned int);
-	int (*clone_file_range)(struct file *, loff_t, struct file *, loff_t,
-			u64);
-	int (*dedupe_file_range)(struct file *, loff_t, struct file *, loff_t,
-			u64);
+	int (*remap_file_range)(struct file *file_in, loff_t pos_in,
+				struct file *file_out, loff_t pos_out,
+				u64 len, unsigned int remap_flags);
 	int (*fadvise)(struct file *, loff_t, loff_t, int);
 } __randomize_layout;
 
-- 
cgit v1.2.3


From a91ae49bbaf43910edb09e03fedf26b23875bd52 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Tue, 30 Oct 2018 10:41:28 +1100
Subject: vfs: pass remap flags to generic_remap_file_range_prep

Plumb the remap flags through the filesystem from the vfs function
dispatcher all the way to the prep function to prepare for behavior
changes in subsequent patches.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dave Chinner <david@fromorbit.com>
---
 fs/ocfs2/file.c         |  2 +-
 fs/ocfs2/refcounttree.c |  4 ++--
 fs/ocfs2/refcounttree.h |  2 +-
 fs/read_write.c         | 14 +++++++-------
 fs/xfs/xfs_file.c       |  2 +-
 fs/xfs/xfs_reflink.c    | 21 +++++++++++----------
 fs/xfs/xfs_reflink.h    |  3 ++-
 include/linux/fs.h      |  2 +-
 8 files changed, 26 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 0b757a24567c..9809b0e5746f 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2538,7 +2538,7 @@ static int ocfs2_remap_file_range(struct file *file_in,
 		return -EINVAL;
 
 	return ocfs2_reflink_remap_range(file_in, pos_in, file_out, pos_out,
-					 len, remap_flags & REMAP_FILE_DEDUP);
+					 len, remap_flags);
 }
 
 const struct inode_operations ocfs2_file_iops = {
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index 36c56dfbe485..df9781567ec0 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -4825,7 +4825,7 @@ int ocfs2_reflink_remap_range(struct file *file_in,
 			      struct file *file_out,
 			      loff_t pos_out,
 			      u64 len,
-			      bool is_dedupe)
+			      unsigned int remap_flags)
 {
 	struct inode *inode_in = file_inode(file_in);
 	struct inode *inode_out = file_inode(file_out);
@@ -4851,7 +4851,7 @@ int ocfs2_reflink_remap_range(struct file *file_in,
 		goto out_unlock;
 
 	ret = generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out,
-			&len, is_dedupe);
+			&len, remap_flags);
 	if (ret <= 0)
 		goto out_unlock;
 
diff --git a/fs/ocfs2/refcounttree.h b/fs/ocfs2/refcounttree.h
index 4af55bf4b35b..d2c5f526edff 100644
--- a/fs/ocfs2/refcounttree.h
+++ b/fs/ocfs2/refcounttree.h
@@ -120,6 +120,6 @@ int ocfs2_reflink_remap_range(struct file *file_in,
 			      struct file *file_out,
 			      loff_t pos_out,
 			      u64 len,
-			      bool is_dedupe);
+			      unsigned int remap_flags);
 
 #endif /* OCFS2_REFCOUNTTREE_H */
diff --git a/fs/read_write.c b/fs/read_write.c
index 766bdcb381f3..201381689284 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1722,14 +1722,14 @@ static int generic_remap_check_len(struct inode *inode_in,
 				   struct inode *inode_out,
 				   loff_t pos_out,
 				   u64 *len,
-				   bool is_dedupe)
+				   unsigned int remap_flags)
 {
 	u64 blkmask = i_blocksize(inode_in) - 1;
 
 	if ((*len & blkmask) == 0)
 		return 0;
 
-	if (is_dedupe)
+	if (remap_flags & REMAP_FILE_DEDUP)
 		*len &= ~blkmask;
 	else if (pos_out + *len < i_size_read(inode_out))
 		return -EINVAL;
@@ -1747,7 +1747,7 @@ static int generic_remap_check_len(struct inode *inode_in,
  */
 int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 				  struct file *file_out, loff_t pos_out,
-				  u64 *len, bool is_dedupe)
+				  u64 *len, unsigned int remap_flags)
 {
 	struct inode *inode_in = file_inode(file_in);
 	struct inode *inode_out = file_inode(file_out);
@@ -1771,7 +1771,7 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 	if (*len == 0) {
 		loff_t isize = i_size_read(inode_in);
 
-		if (is_dedupe || pos_in == isize)
+		if ((remap_flags & REMAP_FILE_DEDUP) || pos_in == isize)
 			return 0;
 		if (pos_in > isize)
 			return -EINVAL;
@@ -1782,7 +1782,7 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 
 	/* Check that we don't violate system file offset limits. */
 	ret = generic_remap_checks(file_in, pos_in, file_out, pos_out, len,
-			is_dedupe);
+			(remap_flags & REMAP_FILE_DEDUP));
 	if (ret)
 		return ret;
 
@@ -1804,7 +1804,7 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 	/*
 	 * Check that the extents are the same.
 	 */
-	if (is_dedupe) {
+	if (remap_flags & REMAP_FILE_DEDUP) {
 		bool		is_same = false;
 
 		ret = vfs_dedupe_file_range_compare(inode_in, pos_in,
@@ -1816,7 +1816,7 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 	}
 
 	ret = generic_remap_check_len(inode_in, inode_out, pos_out, len,
-			is_dedupe);
+			remap_flags);
 	if (ret)
 		return ret;
 
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 2ad94d508f80..20314eb4677a 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -932,7 +932,7 @@ xfs_file_remap_range(
 		return -EINVAL;
 
 	return xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out,
-			len, remap_flags & REMAP_FILE_DEDUP);
+			len, remap_flags);
 }
 
 STATIC int
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index a7757a128a78..29aab196ce7e 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -921,13 +921,14 @@ xfs_reflink_update_dest(
 	struct xfs_inode	*dest,
 	xfs_off_t		newlen,
 	xfs_extlen_t		cowextsize,
-	bool			is_dedupe)
+	unsigned int		remap_flags)
 {
 	struct xfs_mount	*mp = dest->i_mount;
 	struct xfs_trans	*tp;
 	int			error;
 
-	if (is_dedupe && newlen <= i_size_read(VFS_I(dest)) && cowextsize == 0)
+	if ((remap_flags & REMAP_FILE_DEDUP) &&
+	    newlen <= i_size_read(VFS_I(dest)) && cowextsize == 0)
 		return 0;
 
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp);
@@ -948,7 +949,7 @@ xfs_reflink_update_dest(
 		dest->i_d.di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
 	}
 
-	if (!is_dedupe) {
+	if (!(remap_flags & REMAP_FILE_DEDUP)) {
 		xfs_trans_ichgtime(tp, dest,
 				   XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
 	}
@@ -1296,7 +1297,7 @@ xfs_reflink_remap_prep(
 	struct file		*file_out,
 	loff_t			pos_out,
 	u64			*len,
-	bool			is_dedupe)
+	unsigned int		remap_flags)
 {
 	struct inode		*inode_in = file_inode(file_in);
 	struct xfs_inode	*src = XFS_I(inode_in);
@@ -1327,7 +1328,7 @@ xfs_reflink_remap_prep(
 		goto out_unlock;
 
 	ret = generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out,
-			len, is_dedupe);
+			len, remap_flags);
 	if (ret <= 0)
 		goto out_unlock;
 
@@ -1336,7 +1337,7 @@ xfs_reflink_remap_prep(
 	 * from the source file so we don't try to dedupe the partial
 	 * EOF block.
 	 */
-	if (is_dedupe) {
+	if (remap_flags & REMAP_FILE_DEDUP) {
 		*len &= ~blkmask;
 	} else if (*len & blkmask) {
 		/*
@@ -1372,7 +1373,7 @@ xfs_reflink_remap_prep(
 				   PAGE_ALIGN(pos_out + *len) - 1);
 
 	/* If we're altering the file contents... */
-	if (!is_dedupe) {
+	if (!(remap_flags & REMAP_FILE_DEDUP)) {
 		/*
 		 * ...update the timestamps (which will grab the ilock again
 		 * from xfs_fs_dirty_inode, so we have to call it before we
@@ -1410,7 +1411,7 @@ xfs_reflink_remap_range(
 	struct file		*file_out,
 	loff_t			pos_out,
 	u64			len,
-	bool			is_dedupe)
+	unsigned int		remap_flags)
 {
 	struct inode		*inode_in = file_inode(file_in);
 	struct xfs_inode	*src = XFS_I(inode_in);
@@ -1430,7 +1431,7 @@ xfs_reflink_remap_range(
 
 	/* Prepare and then clone file data. */
 	ret = xfs_reflink_remap_prep(file_in, pos_in, file_out, pos_out,
-			&len, is_dedupe);
+			&len, remap_flags);
 	if (ret <= 0)
 		return ret;
 
@@ -1457,7 +1458,7 @@ xfs_reflink_remap_range(
 		cowextsize = src->i_d.di_cowextsize;
 
 	ret = xfs_reflink_update_dest(dest, pos_out + len, cowextsize,
-			is_dedupe);
+			remap_flags);
 
 out_unlock:
 	xfs_reflink_remap_unlock(file_in, file_out);
diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h
index c585ad9552b2..6f82d628bf17 100644
--- a/fs/xfs/xfs_reflink.h
+++ b/fs/xfs/xfs_reflink.h
@@ -28,7 +28,8 @@ extern int xfs_reflink_end_cow(struct xfs_inode *ip, xfs_off_t offset,
 		xfs_off_t count);
 extern int xfs_reflink_recover_cow(struct xfs_mount *mp);
 extern int xfs_reflink_remap_range(struct file *file_in, loff_t pos_in,
-		struct file *file_out, loff_t pos_out, u64 len, bool is_dedupe);
+		struct file *file_out, loff_t pos_out, u64 len,
+		unsigned int remap_flags);
 extern int xfs_reflink_inode_has_shared_extents(struct xfs_trans *tp,
 		struct xfs_inode *ip, bool *has_shared);
 extern int xfs_reflink_clear_inode_flag(struct xfs_inode *ip,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 888cef35c7d7..631c28ce1436 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1844,7 +1844,7 @@ extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *,
 				   loff_t, size_t, unsigned int);
 extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 					 struct file *file_out, loff_t pos_out,
-					 u64 *count, bool is_dedupe);
+					 u64 *count, unsigned int remap_flags);
 extern int do_clone_file_range(struct file *file_in, loff_t pos_in,
 			       struct file *file_out, loff_t pos_out, u64 len);
 extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in,
-- 
cgit v1.2.3


From 3d28193e1df043764deb7abdaba5e3a6660bc393 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Tue, 30 Oct 2018 10:41:34 +1100
Subject: vfs: pass remap flags to generic_remap_checks

Pass the same remap flags to generic_remap_checks for consistency.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dave Chinner <david@fromorbit.com>
---
 fs/read_write.c    | 2 +-
 include/linux/fs.h | 2 +-
 mm/filemap.c       | 4 ++--
 3 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/fs/read_write.c b/fs/read_write.c
index 201381689284..ebcbfc4f2907 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1782,7 +1782,7 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 
 	/* Check that we don't violate system file offset limits. */
 	ret = generic_remap_checks(file_in, pos_in, file_out, pos_out, len,
-			(remap_flags & REMAP_FILE_DEDUP));
+			remap_flags);
 	if (ret)
 		return ret;
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 631c28ce1436..c5435ca81132 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2986,7 +2986,7 @@ extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
 extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *);
 extern int generic_remap_checks(struct file *file_in, loff_t pos_in,
 				struct file *file_out, loff_t pos_out,
-				uint64_t *count, bool is_dedupe);
+				uint64_t *count, unsigned int remap_flags);
 extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *);
 extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *);
 extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *);
diff --git a/mm/filemap.c b/mm/filemap.c
index 84b7301e41a0..410dc58f7b16 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2994,7 +2994,7 @@ EXPORT_SYMBOL(generic_write_checks);
  */
 int generic_remap_checks(struct file *file_in, loff_t pos_in,
 			 struct file *file_out, loff_t pos_out,
-			 uint64_t *req_count, bool is_dedupe)
+			 uint64_t *req_count, unsigned int remap_flags)
 {
 	struct inode *inode_in = file_in->f_mapping->host;
 	struct inode *inode_out = file_out->f_mapping->host;
@@ -3016,7 +3016,7 @@ int generic_remap_checks(struct file *file_in, loff_t pos_in,
 	size_out = i_size_read(inode_out);
 
 	/* Dedupe requires both ranges to be within EOF. */
-	if (is_dedupe &&
+	if ((remap_flags & REMAP_FILE_DEDUP) &&
 	    (pos_in >= size_in || pos_in + count > size_in ||
 	     pos_out >= size_out || pos_out + count > size_out))
 		return -EINVAL;
-- 
cgit v1.2.3


From 42ec3d4c02187a18e27ff94b409ec27234bf2ffd Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Tue, 30 Oct 2018 10:41:49 +1100
Subject: vfs: make remap_file_range functions take and return bytes completed

Change the remap_file_range functions to take a number of bytes to
operate upon and return the number of bytes they operated on.  This is a
requirement for allowing fs implementations to return short clone/dedupe
results to the user, which will enable us to obey resource limits in a
graceful manner.

A subsequent patch will enable copy_file_range to signal to the
->clone_file_range implementation that it can handle a short length,
which will be returned in the function's return value.  For now the
short return is not implemented anywhere so the behavior won't change --
either copy_file_range manages to clone the entire range or it tries an
alternative.

Neither clone ioctl can take advantage of this, alas.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>
---
 Documentation/filesystems/vfs.txt | 10 ++++----
 fs/btrfs/ctree.h                  |  6 ++---
 fs/btrfs/ioctl.c                  | 13 +++++++----
 fs/cifs/cifsfs.c                  |  6 ++---
 fs/ioctl.c                        | 10 +++++++-
 fs/nfs/nfs4file.c                 |  6 ++---
 fs/nfsd/vfs.c                     |  8 +++++--
 fs/ocfs2/file.c                   | 16 ++++++-------
 fs/ocfs2/refcounttree.c           |  2 +-
 fs/ocfs2/refcounttree.h           |  2 +-
 fs/overlayfs/copy_up.c            |  6 ++---
 fs/overlayfs/file.c               | 12 +++++-----
 fs/read_write.c                   | 49 +++++++++++++++++++++------------------
 fs/xfs/xfs_file.c                 |  9 ++++---
 fs/xfs/xfs_reflink.c              |  4 ++--
 fs/xfs/xfs_reflink.h              |  2 +-
 include/linux/fs.h                | 27 +++++++++++----------
 mm/filemap.c                      |  2 +-
 18 files changed, 108 insertions(+), 82 deletions(-)

(limited to 'include')

diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 6f5babfee27b..1bd2919deaca 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -883,9 +883,9 @@ struct file_operations {
 	unsigned (*mmap_capabilities)(struct file *);
 #endif
 	ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int);
-	int (*remap_file_range)(struct file *file_in, loff_t pos_in,
-				struct file *file_out, loff_t pos_out,
-				u64 len, unsigned int remap_flags);
+	loff_t (*remap_file_range)(struct file *file_in, loff_t pos_in,
+				   struct file *file_out, loff_t pos_out,
+				   loff_t len, unsigned int remap_flags);
 	int (*fadvise)(struct file *, loff_t, loff_t, int);
 };
 
@@ -966,8 +966,8 @@ otherwise noted.
 	implementation should remap len bytes at pos_in of the source file into
 	the dest file at pos_out.  Implementations must handle callers passing
 	in len == 0; this means "remap to the end of the source file".  The
-	return value should be zero if all bytes were remapped, or the usual
-	negative error code if the remapping did not succeed completely.
+	return value should the number of bytes remapped, or the usual
+	negative error code if errors occurred before any bytes were remapped.
 	The remap_flags parameter accepts REMAP_FILE_* flags.  If
 	REMAP_FILE_DEDUP is set then the implementation must only remap if the
 	requested file ranges have identical contents.
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 124a05662fc2..771a961d77ad 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3247,9 +3247,9 @@ int btrfs_dirty_pages(struct inode *inode, struct page **pages,
 		      size_t num_pages, loff_t pos, size_t write_bytes,
 		      struct extent_state **cached);
 int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end);
-int btrfs_remap_file_range(struct file *file_in, loff_t pos_in,
-			   struct file *file_out, loff_t pos_out, u64 len,
-			   unsigned int remap_flags);
+loff_t btrfs_remap_file_range(struct file *file_in, loff_t pos_in,
+			      struct file *file_out, loff_t pos_out,
+			      loff_t len, unsigned int remap_flags);
 
 /* tree-defrag.c */
 int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index bfd99c66723e..b0c513e10977 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -4328,10 +4328,12 @@ out_unlock:
 	return ret;
 }
 
-int btrfs_remap_file_range(struct file *src_file, loff_t off,
-		struct file *dst_file, loff_t destoff, u64 len,
+loff_t btrfs_remap_file_range(struct file *src_file, loff_t off,
+		struct file *dst_file, loff_t destoff, loff_t len,
 		unsigned int remap_flags)
 {
+	int ret;
+
 	if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY))
 		return -EINVAL;
 
@@ -4349,10 +4351,11 @@ int btrfs_remap_file_range(struct file *src_file, loff_t off,
 			return -EINVAL;
 		}
 
-		return btrfs_extent_same(src, off, len, dst, destoff);
+		ret = btrfs_extent_same(src, off, len, dst, destoff);
+	} else {
+		ret = btrfs_clone_files(dst_file, src_file, off, len, destoff);
 	}
-
-	return btrfs_clone_files(dst_file, src_file, off, len, destoff);
+	return ret < 0 ? ret : len;
 }
 
 static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp)
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index e8144d0dcde2..5ca71c6c8be2 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -975,8 +975,8 @@ const struct inode_operations cifs_symlink_inode_ops = {
 	.listxattr = cifs_listxattr,
 };
 
-static int cifs_remap_file_range(struct file *src_file, loff_t off,
-		struct file *dst_file, loff_t destoff, u64 len,
+static loff_t cifs_remap_file_range(struct file *src_file, loff_t off,
+		struct file *dst_file, loff_t destoff, loff_t len,
 		unsigned int remap_flags)
 {
 	struct inode *src_inode = file_inode(src_file);
@@ -1029,7 +1029,7 @@ static int cifs_remap_file_range(struct file *src_file, loff_t off,
 	unlock_two_nondirectories(src_inode, target_inode);
 out:
 	free_xid(xid);
-	return rc;
+	return rc < 0 ? rc : len;
 }
 
 ssize_t cifs_file_copychunk_range(unsigned int xid,
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 2005529af560..72537b68c272 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -223,6 +223,7 @@ static long ioctl_file_clone(struct file *dst_file, unsigned long srcfd,
 			     u64 off, u64 olen, u64 destoff)
 {
 	struct fd src_file = fdget(srcfd);
+	loff_t cloned;
 	int ret;
 
 	if (!src_file.file)
@@ -230,7 +231,14 @@ static long ioctl_file_clone(struct file *dst_file, unsigned long srcfd,
 	ret = -EXDEV;
 	if (src_file.file->f_path.mnt != dst_file->f_path.mnt)
 		goto fdput;
-	ret = vfs_clone_file_range(src_file.file, off, dst_file, destoff, olen);
+	cloned = vfs_clone_file_range(src_file.file, off, dst_file, destoff,
+				      olen);
+	if (cloned < 0)
+		ret = cloned;
+	else if (olen && cloned != olen)
+		ret = -EINVAL;
+	else
+		ret = 0;
 fdput:
 	fdput(src_file);
 	return ret;
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index ae5780ce41dc..46d691ba04bc 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -180,8 +180,8 @@ static long nfs42_fallocate(struct file *filep, int mode, loff_t offset, loff_t
 	return nfs42_proc_allocate(filep, offset, len);
 }
 
-static int nfs42_remap_file_range(struct file *src_file, loff_t src_off,
-		struct file *dst_file, loff_t dst_off, u64 count,
+static loff_t nfs42_remap_file_range(struct file *src_file, loff_t src_off,
+		struct file *dst_file, loff_t dst_off, loff_t count,
 		unsigned int remap_flags)
 {
 	struct inode *dst_inode = file_inode(dst_file);
@@ -244,7 +244,7 @@ out_unlock:
 		inode_unlock(src_inode);
 	}
 out:
-	return ret;
+	return ret < 0 ? ret : count;
 }
 #endif /* CONFIG_NFS_V4_2 */
 
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index b53e76391e52..ac6cb6101cbe 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -541,8 +541,12 @@ __be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp,
 __be32 nfsd4_clone_file_range(struct file *src, u64 src_pos, struct file *dst,
 		u64 dst_pos, u64 count)
 {
-	return nfserrno(vfs_clone_file_range(src, src_pos, dst, dst_pos,
-					     count));
+	loff_t cloned;
+
+	cloned = vfs_clone_file_range(src, src_pos, dst, dst_pos, count);
+	if (count && cloned != count)
+		cloned = -EINVAL;
+	return nfserrno(cloned < 0 ? cloned : 0);
 }
 
 ssize_t nfsd_copy_file_range(struct file *src, u64 src_pos, struct file *dst,
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 9809b0e5746f..fbaeafe44b5f 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2527,18 +2527,18 @@ out:
 	return offset;
 }
 
-static int ocfs2_remap_file_range(struct file *file_in,
-				  loff_t pos_in,
-				  struct file *file_out,
-				  loff_t pos_out,
-				  u64 len,
-				  unsigned int remap_flags)
+static loff_t ocfs2_remap_file_range(struct file *file_in, loff_t pos_in,
+				     struct file *file_out, loff_t pos_out,
+				     loff_t len, unsigned int remap_flags)
 {
+	int ret;
+
 	if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY))
 		return -EINVAL;
 
-	return ocfs2_reflink_remap_range(file_in, pos_in, file_out, pos_out,
-					 len, remap_flags);
+	ret = ocfs2_reflink_remap_range(file_in, pos_in, file_out, pos_out,
+					len, remap_flags);
+	return ret < 0 ? ret : len;
 }
 
 const struct inode_operations ocfs2_file_iops = {
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index df9781567ec0..6a42c04ac0ab 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -4824,7 +4824,7 @@ int ocfs2_reflink_remap_range(struct file *file_in,
 			      loff_t pos_in,
 			      struct file *file_out,
 			      loff_t pos_out,
-			      u64 len,
+			      loff_t len,
 			      unsigned int remap_flags)
 {
 	struct inode *inode_in = file_inode(file_in);
diff --git a/fs/ocfs2/refcounttree.h b/fs/ocfs2/refcounttree.h
index d2c5f526edff..eb65c1d0843c 100644
--- a/fs/ocfs2/refcounttree.h
+++ b/fs/ocfs2/refcounttree.h
@@ -119,7 +119,7 @@ int ocfs2_reflink_remap_range(struct file *file_in,
 			      loff_t pos_in,
 			      struct file *file_out,
 			      loff_t pos_out,
-			      u64 len,
+			      loff_t len,
 			      unsigned int remap_flags);
 
 #endif /* OCFS2_REFCOUNTTREE_H */
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 1cc797a08a5b..8750b7235516 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -125,6 +125,7 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len)
 	struct file *new_file;
 	loff_t old_pos = 0;
 	loff_t new_pos = 0;
+	loff_t cloned;
 	int error = 0;
 
 	if (len == 0)
@@ -141,11 +142,10 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len)
 	}
 
 	/* Try to use clone_file_range to clone up within the same fs */
-	error = do_clone_file_range(old_file, 0, new_file, 0, len);
-	if (!error)
+	cloned = do_clone_file_range(old_file, 0, new_file, 0, len);
+	if (cloned == len)
 		goto out;
 	/* Couldn't clone, so now we try to copy the data */
-	error = 0;
 
 	/* FIXME: copy up sparse files efficiently */
 	while (len) {
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index fffb36fd5920..6c3fec6168e9 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -434,14 +434,14 @@ enum ovl_copyop {
 	OVL_DEDUPE,
 };
 
-static ssize_t ovl_copyfile(struct file *file_in, loff_t pos_in,
+static loff_t ovl_copyfile(struct file *file_in, loff_t pos_in,
 			    struct file *file_out, loff_t pos_out,
-			    u64 len, unsigned int flags, enum ovl_copyop op)
+			    loff_t len, unsigned int flags, enum ovl_copyop op)
 {
 	struct inode *inode_out = file_inode(file_out);
 	struct fd real_in, real_out;
 	const struct cred *old_cred;
-	ssize_t ret;
+	loff_t ret;
 
 	ret = ovl_real_fdget(file_out, &real_out);
 	if (ret)
@@ -489,9 +489,9 @@ static ssize_t ovl_copy_file_range(struct file *file_in, loff_t pos_in,
 			    OVL_COPY);
 }
 
-static int ovl_remap_file_range(struct file *file_in, loff_t pos_in,
-				struct file *file_out, loff_t pos_out,
-				u64 len, unsigned int remap_flags)
+static loff_t ovl_remap_file_range(struct file *file_in, loff_t pos_in,
+				   struct file *file_out, loff_t pos_out,
+				   loff_t len, unsigned int remap_flags)
 {
 	enum ovl_copyop op;
 
diff --git a/fs/read_write.c b/fs/read_write.c
index b61bd3fc7154..356641afa487 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1589,10 +1589,13 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
 	 * more efficient if both clone and copy are supported (e.g. NFS).
 	 */
 	if (file_in->f_op->remap_file_range) {
-		ret = file_in->f_op->remap_file_range(file_in, pos_in,
-				file_out, pos_out, len, 0);
-		if (ret == 0) {
-			ret = len;
+		loff_t cloned;
+
+		cloned = file_in->f_op->remap_file_range(file_in, pos_in,
+				file_out, pos_out,
+				min_t(loff_t, MAX_RW_COUNT, len), 0);
+		if (cloned > 0) {
+			ret = cloned;
 			goto done;
 		}
 	}
@@ -1686,11 +1689,12 @@ out2:
 	return ret;
 }
 
-static int remap_verify_area(struct file *file, loff_t pos, u64 len, bool write)
+static int remap_verify_area(struct file *file, loff_t pos, loff_t len,
+			     bool write)
 {
 	struct inode *inode = file_inode(file);
 
-	if (unlikely(pos < 0))
+	if (unlikely(pos < 0 || len < 0))
 		return -EINVAL;
 
 	 if (unlikely((loff_t) (pos + len) < 0))
@@ -1721,7 +1725,7 @@ static int remap_verify_area(struct file *file, loff_t pos, u64 len, bool write)
 static int generic_remap_check_len(struct inode *inode_in,
 				   struct inode *inode_out,
 				   loff_t pos_out,
-				   u64 *len,
+				   loff_t *len,
 				   unsigned int remap_flags)
 {
 	u64 blkmask = i_blocksize(inode_in) - 1;
@@ -1747,7 +1751,7 @@ static int generic_remap_check_len(struct inode *inode_in,
  */
 int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 				  struct file *file_out, loff_t pos_out,
-				  u64 *len, unsigned int remap_flags)
+				  loff_t *len, unsigned int remap_flags)
 {
 	struct inode *inode_in = file_inode(file_in);
 	struct inode *inode_out = file_inode(file_out);
@@ -1843,12 +1847,12 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 }
 EXPORT_SYMBOL(generic_remap_file_range_prep);
 
-int do_clone_file_range(struct file *file_in, loff_t pos_in,
-			struct file *file_out, loff_t pos_out, u64 len)
+loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
+			   struct file *file_out, loff_t pos_out, loff_t len)
 {
 	struct inode *inode_in = file_inode(file_in);
 	struct inode *inode_out = file_inode(file_out);
-	int ret;
+	loff_t ret;
 
 	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
 		return -EISDIR;
@@ -1881,19 +1885,19 @@ int do_clone_file_range(struct file *file_in, loff_t pos_in,
 
 	ret = file_in->f_op->remap_file_range(file_in, pos_in,
 			file_out, pos_out, len, 0);
-	if (!ret) {
-		fsnotify_access(file_in);
-		fsnotify_modify(file_out);
-	}
+	if (ret < 0)
+		return ret;
 
+	fsnotify_access(file_in);
+	fsnotify_modify(file_out);
 	return ret;
 }
 EXPORT_SYMBOL(do_clone_file_range);
 
-int vfs_clone_file_range(struct file *file_in, loff_t pos_in,
-			 struct file *file_out, loff_t pos_out, u64 len)
+loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
+			    struct file *file_out, loff_t pos_out, loff_t len)
 {
-	int ret;
+	loff_t ret;
 
 	file_start_write(file_out);
 	ret = do_clone_file_range(file_in, pos_in, file_out, pos_out, len);
@@ -1999,10 +2003,11 @@ out_error:
 }
 EXPORT_SYMBOL(vfs_dedupe_file_range_compare);
 
-int vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
-			      struct file *dst_file, loff_t dst_pos, u64 len)
+loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
+				 struct file *dst_file, loff_t dst_pos,
+				 loff_t len)
 {
-	s64 ret;
+	loff_t ret;
 
 	ret = mnt_want_write_file(dst_file);
 	if (ret)
@@ -2051,7 +2056,7 @@ int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same)
 	int i;
 	int ret;
 	u16 count = same->dest_count;
-	int deduped;
+	loff_t deduped;
 
 	if (!(file->f_mode & FMODE_READ))
 		return -EINVAL;
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 20314eb4677a..38fde4e11714 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -919,20 +919,23 @@ out_unlock:
 	return error;
 }
 
-STATIC int
+STATIC loff_t
 xfs_file_remap_range(
 	struct file	*file_in,
 	loff_t		pos_in,
 	struct file	*file_out,
 	loff_t		pos_out,
-	u64		len,
+	loff_t		len,
 	unsigned int	remap_flags)
 {
+	int		ret;
+
 	if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY))
 		return -EINVAL;
 
-	return xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out,
+	ret = xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out,
 			len, remap_flags);
+	return ret < 0 ? ret : len;
 }
 
 STATIC int
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 2d7dd8b28d7c..3dbe5fb7e9c0 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1296,7 +1296,7 @@ xfs_reflink_remap_prep(
 	loff_t			pos_in,
 	struct file		*file_out,
 	loff_t			pos_out,
-	u64			*len,
+	loff_t			*len,
 	unsigned int		remap_flags)
 {
 	struct inode		*inode_in = file_inode(file_in);
@@ -1387,7 +1387,7 @@ xfs_reflink_remap_range(
 	loff_t			pos_in,
 	struct file		*file_out,
 	loff_t			pos_out,
-	u64			len,
+	loff_t			len,
 	unsigned int		remap_flags)
 {
 	struct inode		*inode_in = file_inode(file_in);
diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h
index 6f82d628bf17..c3c46c276fe1 100644
--- a/fs/xfs/xfs_reflink.h
+++ b/fs/xfs/xfs_reflink.h
@@ -28,7 +28,7 @@ extern int xfs_reflink_end_cow(struct xfs_inode *ip, xfs_off_t offset,
 		xfs_off_t count);
 extern int xfs_reflink_recover_cow(struct xfs_mount *mp);
 extern int xfs_reflink_remap_range(struct file *file_in, loff_t pos_in,
-		struct file *file_out, loff_t pos_out, u64 len,
+		struct file *file_out, loff_t pos_out, loff_t len,
 		unsigned int remap_flags);
 extern int xfs_reflink_inode_has_shared_extents(struct xfs_trans *tp,
 		struct xfs_inode *ip, bool *has_shared);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index c5435ca81132..c72d8c3c065a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1777,9 +1777,9 @@ struct file_operations {
 #endif
 	ssize_t (*copy_file_range)(struct file *, loff_t, struct file *,
 			loff_t, size_t, unsigned int);
-	int (*remap_file_range)(struct file *file_in, loff_t pos_in,
-				struct file *file_out, loff_t pos_out,
-				u64 len, unsigned int remap_flags);
+	loff_t (*remap_file_range)(struct file *file_in, loff_t pos_in,
+				   struct file *file_out, loff_t pos_out,
+				   loff_t len, unsigned int remap_flags);
 	int (*fadvise)(struct file *, loff_t, loff_t, int);
 } __randomize_layout;
 
@@ -1844,19 +1844,22 @@ extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *,
 				   loff_t, size_t, unsigned int);
 extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 					 struct file *file_out, loff_t pos_out,
-					 u64 *count, unsigned int remap_flags);
-extern int do_clone_file_range(struct file *file_in, loff_t pos_in,
-			       struct file *file_out, loff_t pos_out, u64 len);
-extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in,
-				struct file *file_out, loff_t pos_out, u64 len);
+					 loff_t *count,
+					 unsigned int remap_flags);
+extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
+				  struct file *file_out, loff_t pos_out,
+				  loff_t len);
+extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
+				   struct file *file_out, loff_t pos_out,
+				   loff_t len);
 extern int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
 					 struct inode *dest, loff_t destoff,
 					 loff_t len, bool *is_same);
 extern int vfs_dedupe_file_range(struct file *file,
 				 struct file_dedupe_range *same);
-extern int vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
-				     struct file *dst_file, loff_t dst_pos,
-				     u64 len);
+extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
+					struct file *dst_file, loff_t dst_pos,
+					loff_t len);
 
 
 struct super_operations {
@@ -2986,7 +2989,7 @@ extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
 extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *);
 extern int generic_remap_checks(struct file *file_in, loff_t pos_in,
 				struct file *file_out, loff_t pos_out,
-				uint64_t *count, unsigned int remap_flags);
+				loff_t *count, unsigned int remap_flags);
 extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *);
 extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *);
 extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *);
diff --git a/mm/filemap.c b/mm/filemap.c
index 410dc58f7b16..e9091d731f84 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2994,7 +2994,7 @@ EXPORT_SYMBOL(generic_write_checks);
  */
 int generic_remap_checks(struct file *file_in, loff_t pos_in,
 			 struct file *file_out, loff_t pos_out,
-			 uint64_t *req_count, unsigned int remap_flags)
+			 loff_t *req_count, unsigned int remap_flags)
 {
 	struct inode *inode_in = file_in->f_mapping->host;
 	struct inode *inode_out = file_out->f_mapping->host;
-- 
cgit v1.2.3


From 452ce65951a2f0719e4e119ecca134c06cfe22ee Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Tue, 30 Oct 2018 10:41:56 +1100
Subject: vfs: plumb remap flags through the vfs clone functions

Plumb a remap_flags argument through the {do,vfs}_clone_file_range
functions so that clone can take advantage of it.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>
---
 fs/ioctl.c             |  2 +-
 fs/nfsd/vfs.c          |  2 +-
 fs/overlayfs/copy_up.c |  2 +-
 fs/overlayfs/file.c    |  6 +++---
 fs/read_write.c        | 13 +++++++++----
 include/linux/fs.h     |  4 ++--
 6 files changed, 17 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/fs/ioctl.c b/fs/ioctl.c
index 72537b68c272..505275ec5596 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -232,7 +232,7 @@ static long ioctl_file_clone(struct file *dst_file, unsigned long srcfd,
 	if (src_file.file->f_path.mnt != dst_file->f_path.mnt)
 		goto fdput;
 	cloned = vfs_clone_file_range(src_file.file, off, dst_file, destoff,
-				      olen);
+				      olen, 0);
 	if (cloned < 0)
 		ret = cloned;
 	else if (olen && cloned != olen)
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index ac6cb6101cbe..726fc5b2b27a 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -543,7 +543,7 @@ __be32 nfsd4_clone_file_range(struct file *src, u64 src_pos, struct file *dst,
 {
 	loff_t cloned;
 
-	cloned = vfs_clone_file_range(src, src_pos, dst, dst_pos, count);
+	cloned = vfs_clone_file_range(src, src_pos, dst, dst_pos, count, 0);
 	if (count && cloned != count)
 		cloned = -EINVAL;
 	return nfserrno(cloned < 0 ? cloned : 0);
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 8750b7235516..5f82fece64a0 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -142,7 +142,7 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len)
 	}
 
 	/* Try to use clone_file_range to clone up within the same fs */
-	cloned = do_clone_file_range(old_file, 0, new_file, 0, len);
+	cloned = do_clone_file_range(old_file, 0, new_file, 0, len, 0);
 	if (cloned == len)
 		goto out;
 	/* Couldn't clone, so now we try to copy the data */
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index 6c3fec6168e9..0393815c8971 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -462,7 +462,7 @@ static loff_t ovl_copyfile(struct file *file_in, loff_t pos_in,
 
 	case OVL_CLONE:
 		ret = vfs_clone_file_range(real_in.file, pos_in,
-					   real_out.file, pos_out, len);
+					   real_out.file, pos_out, len, flags);
 		break;
 
 	case OVL_DEDUPE:
@@ -512,8 +512,8 @@ static loff_t ovl_remap_file_range(struct file *file_in, loff_t pos_in,
 	     !ovl_inode_upper(file_inode(file_out))))
 		return -EPERM;
 
-	return ovl_copyfile(file_in, pos_in, file_out, pos_out, len, 0,
-			    op);
+	return ovl_copyfile(file_in, pos_in, file_out, pos_out, len,
+			    remap_flags, op);
 }
 
 const struct file_operations ovl_file_operations = {
diff --git a/fs/read_write.c b/fs/read_write.c
index 356641afa487..0d1ac1b9bc22 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1848,12 +1848,15 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 EXPORT_SYMBOL(generic_remap_file_range_prep);
 
 loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
-			   struct file *file_out, loff_t pos_out, loff_t len)
+			   struct file *file_out, loff_t pos_out,
+			   loff_t len, unsigned int remap_flags)
 {
 	struct inode *inode_in = file_inode(file_in);
 	struct inode *inode_out = file_inode(file_out);
 	loff_t ret;
 
+	WARN_ON_ONCE(remap_flags);
+
 	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
 		return -EISDIR;
 	if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
@@ -1884,7 +1887,7 @@ loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
 		return ret;
 
 	ret = file_in->f_op->remap_file_range(file_in, pos_in,
-			file_out, pos_out, len, 0);
+			file_out, pos_out, len, remap_flags);
 	if (ret < 0)
 		return ret;
 
@@ -1895,12 +1898,14 @@ loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
 EXPORT_SYMBOL(do_clone_file_range);
 
 loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
-			    struct file *file_out, loff_t pos_out, loff_t len)
+			    struct file *file_out, loff_t pos_out,
+			    loff_t len, unsigned int remap_flags)
 {
 	loff_t ret;
 
 	file_start_write(file_out);
-	ret = do_clone_file_range(file_in, pos_in, file_out, pos_out, len);
+	ret = do_clone_file_range(file_in, pos_in, file_out, pos_out, len,
+				  remap_flags);
 	file_end_write(file_out);
 
 	return ret;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index c72d8c3c065a..1c5e55d2a67d 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1848,10 +1848,10 @@ extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 					 unsigned int remap_flags);
 extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
 				  struct file *file_out, loff_t pos_out,
-				  loff_t len);
+				  loff_t len, unsigned int remap_flags);
 extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
 				   struct file *file_out, loff_t pos_out,
-				   loff_t len);
+				   loff_t len, unsigned int remap_flags);
 extern int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
 					 struct inode *dest, loff_t destoff,
 					 loff_t len, bool *is_same);
-- 
cgit v1.2.3


From df3658361951e17364f1e1c3fa92862a990ad8bd Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Tue, 30 Oct 2018 10:42:03 +1100
Subject: vfs: plumb remap flags through the vfs dedupe functions

Plumb a remap_flags argument through the vfs_dedupe_file_range_one
functions so that dedupe can take advantage of it.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>
---
 fs/overlayfs/file.c | 3 ++-
 fs/read_write.c     | 9 ++++++---
 include/linux/fs.h  | 2 +-
 3 files changed, 9 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index 0393815c8971..84dd957efa24 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -467,7 +467,8 @@ static loff_t ovl_copyfile(struct file *file_in, loff_t pos_in,
 
 	case OVL_DEDUPE:
 		ret = vfs_dedupe_file_range_one(real_in.file, pos_in,
-						real_out.file, pos_out, len);
+						real_out.file, pos_out, len,
+						flags);
 		break;
 	}
 	revert_creds(old_cred);
diff --git a/fs/read_write.c b/fs/read_write.c
index 0d1ac1b9bc22..ea30666013b0 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -2010,10 +2010,12 @@ EXPORT_SYMBOL(vfs_dedupe_file_range_compare);
 
 loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
 				 struct file *dst_file, loff_t dst_pos,
-				 loff_t len)
+				 loff_t len, unsigned int remap_flags)
 {
 	loff_t ret;
 
+	WARN_ON_ONCE(remap_flags & ~(REMAP_FILE_DEDUP));
+
 	ret = mnt_want_write_file(dst_file);
 	if (ret)
 		return ret;
@@ -2044,7 +2046,7 @@ loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
 	}
 
 	ret = dst_file->f_op->remap_file_range(src_file, src_pos, dst_file,
-			dst_pos, len, REMAP_FILE_DEDUP);
+			dst_pos, len, remap_flags | REMAP_FILE_DEDUP);
 out_drop_write:
 	mnt_drop_write_file(dst_file);
 
@@ -2112,7 +2114,8 @@ int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same)
 		}
 
 		deduped = vfs_dedupe_file_range_one(file, off, dst_file,
-						    info->dest_offset, len);
+						    info->dest_offset, len,
+						    0);
 		if (deduped == -EBADE)
 			info->status = FILE_DEDUPE_RANGE_DIFFERS;
 		else if (deduped < 0)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 1c5e55d2a67d..544ab5083b48 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1859,7 +1859,7 @@ extern int vfs_dedupe_file_range(struct file *file,
 				 struct file_dedupe_range *same);
 extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
 					struct file *dst_file, loff_t dst_pos,
-					loff_t len);
+					loff_t len, unsigned int remap_flags);
 
 
 struct super_operations {
-- 
cgit v1.2.3


From eca3654e3cc7d93e9734d0fa96cfb15c7f356244 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Tue, 30 Oct 2018 10:42:10 +1100
Subject: vfs: enable remap callers that can handle short operations

Plumb in a remap flag that enables the filesystem remap handler to
shorten remapping requests for callers that can handle it.  Now
copy_file_range can report partial success (in case we run up against
alignment problems, resource limits, etc.).

We also enable CAN_SHORTEN for fideduperange to maintain existing
userspace-visible behavior where xfs/btrfs shorten the dedupe range to
avoid stale post-eof data exposure.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>
---
 Documentation/filesystems/vfs.txt |  4 +++-
 fs/read_write.c                   | 28 ++++++++++++++++++++--------
 include/linux/fs.h                |  5 +++--
 mm/filemap.c                      | 11 +++++++----
 4 files changed, 33 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 1bd2919deaca..5f71a252e2e0 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -970,7 +970,9 @@ otherwise noted.
 	negative error code if errors occurred before any bytes were remapped.
 	The remap_flags parameter accepts REMAP_FILE_* flags.  If
 	REMAP_FILE_DEDUP is set then the implementation must only remap if the
-	requested file ranges have identical contents.
+	requested file ranges have identical contents.  If REMAP_CAN_SHORTEN is
+	set, the caller is ok with the implementation shortening the request
+	length to satisfy alignment or EOF requirements (or any other reason).
 
   fadvise: possibly called by the fadvise64() system call.
 
diff --git a/fs/read_write.c b/fs/read_write.c
index ea30666013b0..c0bcc1a20650 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1593,7 +1593,8 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
 
 		cloned = file_in->f_op->remap_file_range(file_in, pos_in,
 				file_out, pos_out,
-				min_t(loff_t, MAX_RW_COUNT, len), 0);
+				min_t(loff_t, MAX_RW_COUNT, len),
+				REMAP_FILE_CAN_SHORTEN);
 		if (cloned > 0) {
 			ret = cloned;
 			goto done;
@@ -1721,6 +1722,8 @@ static int remap_verify_area(struct file *file, loff_t pos, loff_t len,
  * can't meaningfully compare post-EOF contents.
  *
  * For clone we only link a partial EOF block above the destination file's EOF.
+ *
+ * Shorten the request if possible.
  */
 static int generic_remap_check_len(struct inode *inode_in,
 				   struct inode *inode_out,
@@ -1729,16 +1732,24 @@ static int generic_remap_check_len(struct inode *inode_in,
 				   unsigned int remap_flags)
 {
 	u64 blkmask = i_blocksize(inode_in) - 1;
+	loff_t new_len = *len;
 
 	if ((*len & blkmask) == 0)
 		return 0;
 
-	if (remap_flags & REMAP_FILE_DEDUP)
-		*len &= ~blkmask;
-	else if (pos_out + *len < i_size_read(inode_out))
-		return -EINVAL;
+	if ((remap_flags & REMAP_FILE_DEDUP) ||
+	    pos_out + *len < i_size_read(inode_out))
+		new_len &= ~blkmask;
 
-	return 0;
+	if (new_len == *len)
+		return 0;
+
+	if (remap_flags & REMAP_FILE_CAN_SHORTEN) {
+		*len = new_len;
+		return 0;
+	}
+
+	return (remap_flags & REMAP_FILE_DEDUP) ? -EBADE : -EINVAL;
 }
 
 /*
@@ -2014,7 +2025,8 @@ loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
 {
 	loff_t ret;
 
-	WARN_ON_ONCE(remap_flags & ~(REMAP_FILE_DEDUP));
+	WARN_ON_ONCE(remap_flags & ~(REMAP_FILE_DEDUP |
+				     REMAP_FILE_CAN_SHORTEN));
 
 	ret = mnt_want_write_file(dst_file);
 	if (ret)
@@ -2115,7 +2127,7 @@ int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same)
 
 		deduped = vfs_dedupe_file_range_one(file, off, dst_file,
 						    info->dest_offset, len,
-						    0);
+						    REMAP_FILE_CAN_SHORTEN);
 		if (deduped == -EBADE)
 			info->status = FILE_DEDUPE_RANGE_DIFFERS;
 		else if (deduped < 0)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 544ab5083b48..34c22d695011 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1727,8 +1727,10 @@ struct block_device_operations;
  * See Documentation/filesystems/vfs.txt for more details about this call.
  *
  * REMAP_FILE_DEDUP: only remap if contents identical (i.e. deduplicate)
+ * REMAP_FILE_CAN_SHORTEN: caller can handle a shortened request
  */
 #define REMAP_FILE_DEDUP		(1 << 0)
+#define REMAP_FILE_CAN_SHORTEN		(1 << 1)
 
 /*
  * These flags signal that the caller is ok with altering various aspects of
@@ -1736,9 +1738,8 @@ struct block_device_operations;
  * implementation; the vfs remap helper functions can take advantage of them.
  * Flags in this category exist to preserve the quirky behavior of the hoisted
  * btrfs clone/dedupe ioctls.
- * There are no flags yet, but subsequent commits will add some.
  */
-#define REMAP_FILE_ADVISORY		(0)
+#define REMAP_FILE_ADVISORY		(REMAP_FILE_CAN_SHORTEN)
 
 struct iov_iter;
 
diff --git a/mm/filemap.c b/mm/filemap.c
index e9091d731f84..1775d4ad3317 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3045,8 +3045,7 @@ int generic_remap_checks(struct file *file_in, loff_t pos_in,
 		bcount = ALIGN(size_in, bs) - pos_in;
 	} else {
 		if (!IS_ALIGNED(count, bs))
-			return -EINVAL;
-
+			count = ALIGN_DOWN(count, bs);
 		bcount = count;
 	}
 
@@ -3056,10 +3055,14 @@ int generic_remap_checks(struct file *file_in, loff_t pos_in,
 	    pos_out < pos_in + bcount)
 		return -EINVAL;
 
-	/* For now we don't support changing the length. */
-	if (*req_count != count)
+	/*
+	 * We shortened the request but the caller can't deal with that, so
+	 * bounce the request back to userspace.
+	 */
+	if (*req_count != count && !(remap_flags & REMAP_FILE_CAN_SHORTEN))
 		return -EINVAL;
 
+	*req_count = count;
 	return 0;
 }
 
-- 
cgit v1.2.3


From c32e5f39953fa6bbff35c655bdcb7b3128f1e79f Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Tue, 30 Oct 2018 10:42:17 +1100
Subject: vfs: hide file range comparison function

There are no callers of vfs_dedupe_file_range_compare, so we might as
well make it a static helper and remove the export.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dave Chinner <david@fromorbit.com>
---
 fs/read_write.c    | 187 ++++++++++++++++++++++++++---------------------------
 include/linux/fs.h |   3 -
 2 files changed, 91 insertions(+), 99 deletions(-)

(limited to 'include')

diff --git a/fs/read_write.c b/fs/read_write.c
index c0bcc1a20650..e4d295d0d236 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1752,6 +1752,97 @@ static int generic_remap_check_len(struct inode *inode_in,
 	return (remap_flags & REMAP_FILE_DEDUP) ? -EBADE : -EINVAL;
 }
 
+/*
+ * Read a page's worth of file data into the page cache.  Return the page
+ * locked.
+ */
+static struct page *vfs_dedupe_get_page(struct inode *inode, loff_t offset)
+{
+	struct page *page;
+
+	page = read_mapping_page(inode->i_mapping, offset >> PAGE_SHIFT, NULL);
+	if (IS_ERR(page))
+		return page;
+	if (!PageUptodate(page)) {
+		put_page(page);
+		return ERR_PTR(-EIO);
+	}
+	lock_page(page);
+	return page;
+}
+
+/*
+ * Compare extents of two files to see if they are the same.
+ * Caller must have locked both inodes to prevent write races.
+ */
+static int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
+					 struct inode *dest, loff_t destoff,
+					 loff_t len, bool *is_same)
+{
+	loff_t src_poff;
+	loff_t dest_poff;
+	void *src_addr;
+	void *dest_addr;
+	struct page *src_page;
+	struct page *dest_page;
+	loff_t cmp_len;
+	bool same;
+	int error;
+
+	error = -EINVAL;
+	same = true;
+	while (len) {
+		src_poff = srcoff & (PAGE_SIZE - 1);
+		dest_poff = destoff & (PAGE_SIZE - 1);
+		cmp_len = min(PAGE_SIZE - src_poff,
+			      PAGE_SIZE - dest_poff);
+		cmp_len = min(cmp_len, len);
+		if (cmp_len <= 0)
+			goto out_error;
+
+		src_page = vfs_dedupe_get_page(src, srcoff);
+		if (IS_ERR(src_page)) {
+			error = PTR_ERR(src_page);
+			goto out_error;
+		}
+		dest_page = vfs_dedupe_get_page(dest, destoff);
+		if (IS_ERR(dest_page)) {
+			error = PTR_ERR(dest_page);
+			unlock_page(src_page);
+			put_page(src_page);
+			goto out_error;
+		}
+		src_addr = kmap_atomic(src_page);
+		dest_addr = kmap_atomic(dest_page);
+
+		flush_dcache_page(src_page);
+		flush_dcache_page(dest_page);
+
+		if (memcmp(src_addr + src_poff, dest_addr + dest_poff, cmp_len))
+			same = false;
+
+		kunmap_atomic(dest_addr);
+		kunmap_atomic(src_addr);
+		unlock_page(dest_page);
+		unlock_page(src_page);
+		put_page(dest_page);
+		put_page(src_page);
+
+		if (!same)
+			break;
+
+		srcoff += cmp_len;
+		destoff += cmp_len;
+		len -= cmp_len;
+	}
+
+	*is_same = same;
+	return 0;
+
+out_error:
+	return error;
+}
+
 /*
  * Check that the two inodes are eligible for cloning, the ranges make
  * sense, and then flush all dirty data.  Caller must ensure that the
@@ -1923,102 +2014,6 @@ loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
 }
 EXPORT_SYMBOL(vfs_clone_file_range);
 
-/*
- * Read a page's worth of file data into the page cache.  Return the page
- * locked.
- */
-static struct page *vfs_dedupe_get_page(struct inode *inode, loff_t offset)
-{
-	struct address_space *mapping;
-	struct page *page;
-	pgoff_t n;
-
-	n = offset >> PAGE_SHIFT;
-	mapping = inode->i_mapping;
-	page = read_mapping_page(mapping, n, NULL);
-	if (IS_ERR(page))
-		return page;
-	if (!PageUptodate(page)) {
-		put_page(page);
-		return ERR_PTR(-EIO);
-	}
-	lock_page(page);
-	return page;
-}
-
-/*
- * Compare extents of two files to see if they are the same.
- * Caller must have locked both inodes to prevent write races.
- */
-int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
-				  struct inode *dest, loff_t destoff,
-				  loff_t len, bool *is_same)
-{
-	loff_t src_poff;
-	loff_t dest_poff;
-	void *src_addr;
-	void *dest_addr;
-	struct page *src_page;
-	struct page *dest_page;
-	loff_t cmp_len;
-	bool same;
-	int error;
-
-	error = -EINVAL;
-	same = true;
-	while (len) {
-		src_poff = srcoff & (PAGE_SIZE - 1);
-		dest_poff = destoff & (PAGE_SIZE - 1);
-		cmp_len = min(PAGE_SIZE - src_poff,
-			      PAGE_SIZE - dest_poff);
-		cmp_len = min(cmp_len, len);
-		if (cmp_len <= 0)
-			goto out_error;
-
-		src_page = vfs_dedupe_get_page(src, srcoff);
-		if (IS_ERR(src_page)) {
-			error = PTR_ERR(src_page);
-			goto out_error;
-		}
-		dest_page = vfs_dedupe_get_page(dest, destoff);
-		if (IS_ERR(dest_page)) {
-			error = PTR_ERR(dest_page);
-			unlock_page(src_page);
-			put_page(src_page);
-			goto out_error;
-		}
-		src_addr = kmap_atomic(src_page);
-		dest_addr = kmap_atomic(dest_page);
-
-		flush_dcache_page(src_page);
-		flush_dcache_page(dest_page);
-
-		if (memcmp(src_addr + src_poff, dest_addr + dest_poff, cmp_len))
-			same = false;
-
-		kunmap_atomic(dest_addr);
-		kunmap_atomic(src_addr);
-		unlock_page(dest_page);
-		unlock_page(src_page);
-		put_page(dest_page);
-		put_page(src_page);
-
-		if (!same)
-			break;
-
-		srcoff += cmp_len;
-		destoff += cmp_len;
-		len -= cmp_len;
-	}
-
-	*is_same = same;
-	return 0;
-
-out_error:
-	return error;
-}
-EXPORT_SYMBOL(vfs_dedupe_file_range_compare);
-
 loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
 				 struct file *dst_file, loff_t dst_pos,
 				 loff_t len, unsigned int remap_flags)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 34c22d695011..346036a84f18 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1853,9 +1853,6 @@ extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
 extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
 				   struct file *file_out, loff_t pos_out,
 				   loff_t len, unsigned int remap_flags);
-extern int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
-					 struct inode *dest, loff_t destoff,
-					 loff_t len, bool *is_same);
 extern int vfs_dedupe_file_range(struct file *file,
 				 struct file_dedupe_range *same);
 extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
-- 
cgit v1.2.3