diff mbox series

[14/25] vfs: make remap_file_range functions take and return bytes completed

Message ID 153913040858.32295.9474188640729118153.stgit@magnolia (mailing list archive)
State New, archived
Headers show
Series fs: fixes for serious clone/dedupe problems | expand

Commit Message

Darrick J. Wong Oct. 10, 2018, 12:13 a.m. UTC 
From: Darrick J. Wong <darrick.wong@oracle.com>

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.  Neither clone
ioctl can take advantage of this, alas.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 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  |    5 +++--
 fs/overlayfs/file.c     |   12 ++++++------
 fs/read_write.c         |   49 ++++++++++++++++++++++++++---------------------
 fs/xfs/xfs_file.c       |   11 +++++++----
 fs/xfs/xfs_reflink.c    |    4 ++--
 fs/xfs/xfs_reflink.h    |    2 +-
 include/linux/fs.h      |   27 ++++++++++++++------------
 mm/filemap.c            |    8 ++++----
 17 files changed, 107 insertions(+), 80 deletions(-)

Comments

Amir Goldstein Oct. 10, 2018, 6:47 a.m. UTC | #1 
On Wed, Oct 10, 2018 at 3:14 AM Darrick J. Wong <darrick.wong@oracle.com> wrote:
>
> From: Darrick J. Wong <darrick.wong@oracle.com>
>
> 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.  Neither clone
> ioctl can take advantage of this, alas.
>
> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
> ---
[...]
> @@ -141,8 +142,8 @@ 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;

This error = 0 not needed anymore, but not a big deal...

> diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
> index 693bd0620a81..c8c890c22898 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 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 flags)
>  {
>         enum ovl_copyop op;
>
> diff --git a/fs/read_write.c b/fs/read_write.c
> index 917934770b08..f43b0620afd4 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;
> +               s64 cloned;

loff_t?

> +
> +               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;
>                 }
>         }

Commit message wasn't clear enough on the behavior of copy_file_range()
before and after the patch IMO. Maybe it would be better to pospone this
semantic change to the RFR_SHORTEN patch and keep if (cloned == len)
in this patch?

Thanks,
Amir.
Darrick J. Wong Oct. 10, 2018, 3:50 p.m. UTC | #2 
On Wed, Oct 10, 2018 at 09:47:00AM +0300, Amir Goldstein wrote:
> On Wed, Oct 10, 2018 at 3:14 AM Darrick J. Wong <darrick.wong@oracle.com> wrote:
> >
> > From: Darrick J. Wong <darrick.wong@oracle.com>
> >
> > 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.  Neither clone
> > ioctl can take advantage of this, alas.
> >
> > Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
> > ---
> [...]
> > @@ -141,8 +142,8 @@ 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;
> 
> This error = 0 not needed anymore, but not a big deal...

Fixed.

> > diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
> > index 693bd0620a81..c8c890c22898 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 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 flags)
> >  {
> >         enum ovl_copyop op;
> >
> > diff --git a/fs/read_write.c b/fs/read_write.c
> > index 917934770b08..f43b0620afd4 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;
> > +               s64 cloned;
> 
> loff_t?

Fixed.

> > +
> > +               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;
> >                 }
> >         }
> 
> Commit message wasn't clear enough on the behavior of copy_file_range()
> before and after the patch IMO. Maybe it would be better to pospone this
> semantic change to the RFR_SHORTEN patch and keep if (cloned == len)
> in this patch?

There shouldn't be any behavior change here -- all implementations
return a negative error code or the length that was passed in.  I'll
clarify that in the commit message.

--D

> Thanks,
> Amir.
Amir Goldstein Oct. 10, 2018, 6:28 p.m. UTC | #3 
On Wed, Oct 10, 2018 at 6:51 PM Darrick J. Wong <darrick.wong@oracle.com> wrote:
>
> On Wed, Oct 10, 2018 at 09:47:00AM +0300, Amir Goldstein wrote:
> > On Wed, Oct 10, 2018 at 3:14 AM Darrick J. Wong <darrick.wong@oracle.com> wrote:
> > >
> > > From: Darrick J. Wong <darrick.wong@oracle.com>
> > >
> > > 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.  Neither clone
> > > ioctl can take advantage of this, alas.
> > >
> > > Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
> > > ---
[...]
> > Commit message wasn't clear enough on the behavior of copy_file_range()
> > before and after the patch IMO. Maybe it would be better to pospone this
> > semantic change to the RFR_SHORTEN patch and keep if (cloned == len)
> > in this patch?
>
> There shouldn't be any behavior change here -- all implementations
> return a negative error code or the length that was passed in.  I'll
> clarify that in the commit message.
>

OK. BTW, you forgot to update Documentation/filesystems/vfs.txt.

Also since this series has a potential to break clone/dedup on
overlayfs, it would be great if you could run some of the clone/dedupe
xfstests with overlay over xfs.

For the simple case of running ./check with a local.config file that is
not multi section, this just means running ./check -overlay after the
first ./check run (-overlay doesn't mkfs the base fs).

If this is a problem, let me know once new devel branch is ready
and I'll pull it for testing. If I need to pull in extra xfstests, please
mention that as well.

Thanks,
Amir.
Darrick J. Wong Oct. 10, 2018, 6:32 p.m. UTC | #4 
On Wed, Oct 10, 2018 at 09:28:34PM +0300, Amir Goldstein wrote:
> On Wed, Oct 10, 2018 at 6:51 PM Darrick J. Wong <darrick.wong@oracle.com> wrote:
> >
> > On Wed, Oct 10, 2018 at 09:47:00AM +0300, Amir Goldstein wrote:
> > > On Wed, Oct 10, 2018 at 3:14 AM Darrick J. Wong <darrick.wong@oracle.com> wrote:
> > > >
> > > > From: Darrick J. Wong <darrick.wong@oracle.com>
> > > >
> > > > 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.  Neither clone
> > > > ioctl can take advantage of this, alas.
> > > >
> > > > Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
> > > > ---
> [...]
> > > Commit message wasn't clear enough on the behavior of copy_file_range()
> > > before and after the patch IMO. Maybe it would be better to pospone this
> > > semantic change to the RFR_SHORTEN patch and keep if (cloned == len)
> > > in this patch?
> >
> > There shouldn't be any behavior change here -- all implementations
> > return a negative error code or the length that was passed in.  I'll
> > clarify that in the commit message.
> >
> 
> OK. BTW, you forgot to update Documentation/filesystems/vfs.txt.

Yeah, I noticed that and updated it too.

> Also since this series has a potential to break clone/dedup on
> overlayfs, it would be great if you could run some of the clone/dedupe
> xfstests with overlay over xfs.
> 
> For the simple case of running ./check with a local.config file that is
> not multi section, this just means running ./check -overlay after the
> first ./check run (-overlay doesn't mkfs the base fs).

I'll give it a try, though we should probably both run '-g clone' just
to make sure everything is working...

> If this is a problem, let me know once new devel branch is ready

Yeah, Dave asked me to merge the xfs for-next branch so I'm working on
that too.

> and I'll pull it for testing. If I need to pull in extra xfstests, please
> mention that as well.

You'll probably want "generic: test creation time recovery after power
failure" that I sent to the fstests lists a few days ago.

--D

> 
> Thanks,
> Amir.
diff mbox series

Patch

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index a79783a713f0..d09af171d185 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 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 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 e22b294fa25b..3488bc90e5eb 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -4328,10 +4328,12 @@  static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
 	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 flags)
 {
+	int ret;
+
 	if (flags & RFR_IDENTICAL_DATA) {
 		struct inode *src = file_inode(src_file);
 		struct inode *dst = file_inode(dst_file);
@@ -4346,10 +4348,11 @@  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 bf971fd7cab2..c6ea368ea920 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 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 a93aa225c454..0c56d1acac18 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 flags)
 {
 	struct inode *dst_inode = file_inode(dst_file);
@@ -244,7 +244,7 @@  static int nfs42_remap_file_range(struct file *src_file, loff_t src_off,
 		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 ca41e69c8e68..c018605ac279 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2527,15 +2527,15 @@  static loff_t ocfs2_file_llseek(struct file *file, loff_t offset, int whence)
 	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 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 flags)
 {
-	return ocfs2_reflink_remap_range(file_in, pos_in, file_out, pos_out,
-					 len, flags);
+	int ret;
+
+	ret = ocfs2_reflink_remap_range(file_in, pos_in, file_out, pos_out,
+					len, 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 270a5b1919f6..a3df118bf3b9 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..c2b53509e7f1 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)
@@ -141,8 +142,8 @@  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;
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index 693bd0620a81..c8c890c22898 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 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 flags)
 {
 	enum ovl_copyop op;
 
diff --git a/fs/read_write.c b/fs/read_write.c
index 917934770b08..f43b0620afd4 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;
+		s64 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 @@  SYSCALL_DEFINE6(copy_file_range, int, fd_in, loff_t __user *, off_in,
 	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))
@@ -1720,7 +1724,7 @@  static int remap_verify_area(struct file *file, loff_t pos, u64 len, bool write)
  */
 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);
@@ -1816,12 +1820,12 @@  int generic_remap_file_range_touch(struct file *file, unsigned int remap_flags)
 }
 EXPORT_SYMBOL(generic_remap_file_range_touch);
 
-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;
@@ -1854,19 +1858,19 @@  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);
@@ -1972,10 +1976,11 @@  int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
 }
 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)
@@ -2024,7 +2029,7 @@  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;
@@ -2081,7 +2086,7 @@  int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same)
 		else if (deduped < 0)
 			info->status = deduped;
 		else
-			info->bytes_deduped = len;
+			info->bytes_deduped = deduped;
 
 next_fdput:
 		fdput(dst_fd);
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 4c0ae1efb63f..6f4205846451 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -919,17 +919,20 @@  xfs_file_fallocate(
 	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	flags)
 {
-	return xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out,
-			len, flags);
+	int		ret;
+
+	ret = xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out,
+			len, false);
+	return ret < 0 ? ret : len;
 }
 
 STATIC int
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 4f5e3923d9c2..ec09e2783afe 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1274,7 +1274,7 @@  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);
@@ -1354,7 +1354,7 @@  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 56167b10cbad..1ee09152ecd5 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1765,9 +1765,9 @@  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 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 flags);
 	int (*fadvise)(struct file *, loff_t, loff_t, int);
 } __randomize_layout;
 
@@ -1832,21 +1832,24 @@  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);
+					 loff_t *count,
+					 unsigned int remap_flags);
 extern int generic_remap_file_range_touch(struct file *file,
 					  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);
+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 {
@@ -2976,7 +2979,7 @@  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 e099c8880863..2522737483de 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2975,7 +2975,7 @@  inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
 EXPORT_SYMBOL(generic_write_checks);
 
 static int
-generic_remap_check_limits(struct file *file, loff_t pos, uint64_t *count)
+generic_remap_check_limits(struct file *file, loff_t pos, loff_t *count)
 {
 	struct inode *inode = file->f_mapping->host;
 
@@ -2984,14 +2984,14 @@  generic_remap_check_limits(struct file *file, loff_t pos, uint64_t *count)
 				!(file->f_flags & O_LARGEFILE))) {
 		if (pos >= MAX_NON_LFS)
 			return -EFBIG;
-		*count = min(*count, MAX_NON_LFS - (uint64_t)pos);
+		*count = min(*count, (loff_t)MAX_NON_LFS - pos);
 	}
 
 	/* Don't operate on ranges the page cache doesn't support. */
 	if (unlikely(pos >= inode->i_sb->s_maxbytes))
 		return -EFBIG;
 
-	*count = min(*count, inode->i_sb->s_maxbytes - (uint64_t)pos);
+	*count = min(*count, inode->i_sb->s_maxbytes - pos);
 	return 0;
 }
 
@@ -3004,7 +3004,7 @@  generic_remap_check_limits(struct file *file, loff_t pos, uint64_t *count)
  */
 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;