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>
---
 mm/filemap.c | 69 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 69 insertions(+)

(limited to 'mm/filemap.c')

diff --git a/mm/filemap.c b/mm/filemap.c
index 52517f28e6f4..47e6bfd45a91 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2974,6 +2974,75 @@ inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
 }
 EXPORT_SYMBOL(generic_write_checks);
 
+/*
+ * Performs necessary checks before doing a clone.
+ *
+ * Can adjust amount of bytes to clone.
+ * Returns appropriate error code that caller should return or
+ * zero in case the clone should be allowed.
+ */
+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)
+{
+	struct inode *inode_in = file_in->f_mapping->host;
+	struct inode *inode_out = file_out->f_mapping->host;
+	uint64_t count = *req_count;
+	uint64_t bcount;
+	loff_t size_in, size_out;
+	loff_t bs = inode_out->i_sb->s_blocksize;
+
+	/* The start of both ranges must be aligned to an fs block. */
+	if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_out, bs))
+		return -EINVAL;
+
+	/* Ensure offsets don't wrap. */
+	if (pos_in + count < pos_in || pos_out + count < pos_out)
+		return -EINVAL;
+
+	size_in = i_size_read(inode_in);
+	size_out = i_size_read(inode_out);
+
+	/* Dedupe requires both ranges to be within EOF. */
+	if (is_dedupe &&
+	    (pos_in >= size_in || pos_in + count > size_in ||
+	     pos_out >= size_out || pos_out + count > size_out))
+		return -EINVAL;
+
+	/* Ensure the infile range is within the infile. */
+	if (pos_in >= size_in)
+		return -EINVAL;
+	count = min(count, size_in - (uint64_t)pos_in);
+
+	/*
+	 * If the user wanted us to link to the infile's EOF, round up to the
+	 * next block boundary for this check.
+	 *
+	 * Otherwise, make sure the count is also block-aligned, having
+	 * already confirmed the starting offsets' block alignment.
+	 */
+	if (pos_in + count == size_in) {
+		bcount = ALIGN(size_in, bs) - pos_in;
+	} else {
+		if (!IS_ALIGNED(count, bs))
+			return -EINVAL;
+
+		bcount = count;
+	}
+
+	/* Don't allow overlapped cloning within the same file. */
+	if (inode_in == inode_out &&
+	    pos_out + bcount > pos_in &&
+	    pos_out < pos_in + bcount)
+		return -EINVAL;
+
+	/* For now we don't support changing the length. */
+	if (*req_count != count)
+		return -EINVAL;
+
+	return 0;
+}
+
 int pagecache_write_begin(struct file *file, struct address_space *mapping,
 				loff_t pos, unsigned len, unsigned flags,
 				struct page **pagep, void **fsdata)
-- 
cgit v1.2.3-58-ga151


From 9fd91a90cb9837372af24a804853e15c11aed93e Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Tue, 30 Oct 2018 10:40:46 +1100
Subject: vfs: strengthen checking of file range inputs to generic_remap_checks

File range remapping, if allowed to run past the destination file's EOF,
is an optimization on a regular file write.  Regular file writes that
extend the file length are subject to various constraints which are not
checked by range cloning.

This is a correctness problem because we're never allowed to touch
ranges that the page cache can't support (s_maxbytes); we're not
supposed to deal with large offsets (MAX_NON_LFS) if O_LARGEFILE isn't
set; and we must obey resource limits (RLIMIT_FSIZE).

Therefore, add these checks to the new generic_remap_checks function so
that we curtail unexpected behavior.

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>
---
 mm/filemap.c | 84 +++++++++++++++++++++++++++++++++++++-----------------------
 1 file changed, 52 insertions(+), 32 deletions(-)

(limited to 'mm/filemap.c')

diff --git a/mm/filemap.c b/mm/filemap.c
index 47e6bfd45a91..84b7301e41a0 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2915,6 +2915,42 @@ struct page *read_cache_page_gfp(struct address_space *mapping,
 }
 EXPORT_SYMBOL(read_cache_page_gfp);
 
+/*
+ * Don't operate on ranges the page cache doesn't support, and don't exceed the
+ * LFS limits.  If pos is under the limit it becomes a short access.  If it
+ * exceeds the limit we return -EFBIG.
+ */
+static int generic_access_check_limits(struct file *file, loff_t pos,
+				       loff_t *count)
+{
+	struct inode *inode = file->f_mapping->host;
+	loff_t max_size = inode->i_sb->s_maxbytes;
+
+	if (!(file->f_flags & O_LARGEFILE))
+		max_size = MAX_NON_LFS;
+
+	if (unlikely(pos >= max_size))
+		return -EFBIG;
+	*count = min(*count, max_size - pos);
+	return 0;
+}
+
+static int generic_write_check_limits(struct file *file, loff_t pos,
+				      loff_t *count)
+{
+	loff_t limit = rlimit(RLIMIT_FSIZE);
+
+	if (limit != RLIM_INFINITY) {
+		if (pos >= limit) {
+			send_sig(SIGXFSZ, current, 0);
+			return -EFBIG;
+		}
+		*count = min(*count, limit - pos);
+	}
+
+	return generic_access_check_limits(file, pos, count);
+}
+
 /*
  * Performs necessary checks before doing a write
  *
@@ -2926,8 +2962,8 @@ inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
-	unsigned long limit = rlimit(RLIMIT_FSIZE);
-	loff_t pos;
+	loff_t count;
+	int ret;
 
 	if (!iov_iter_count(from))
 		return 0;
@@ -2936,40 +2972,15 @@ inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
 	if (iocb->ki_flags & IOCB_APPEND)
 		iocb->ki_pos = i_size_read(inode);
 
-	pos = iocb->ki_pos;
-
 	if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT))
 		return -EINVAL;
 
-	if (limit != RLIM_INFINITY) {
-		if (iocb->ki_pos >= limit) {
-			send_sig(SIGXFSZ, current, 0);
-			return -EFBIG;
-		}
-		iov_iter_truncate(from, limit - (unsigned long)pos);
-	}
-
-	/*
-	 * LFS rule
-	 */
-	if (unlikely(pos + iov_iter_count(from) > MAX_NON_LFS &&
-				!(file->f_flags & O_LARGEFILE))) {
-		if (pos >= MAX_NON_LFS)
-			return -EFBIG;
-		iov_iter_truncate(from, MAX_NON_LFS - (unsigned long)pos);
-	}
-
-	/*
-	 * Are we about to exceed the fs block limit ?
-	 *
-	 * If we have written data it becomes a short write.  If we have
-	 * exceeded without writing data we send a signal and return EFBIG.
-	 * Linus frestrict idea will clean these up nicely..
-	 */
-	if (unlikely(pos >= inode->i_sb->s_maxbytes))
-		return -EFBIG;
+	count = iov_iter_count(from);
+	ret = generic_write_check_limits(file, iocb->ki_pos, &count);
+	if (ret)
+		return ret;
 
-	iov_iter_truncate(from, inode->i_sb->s_maxbytes - pos);
+	iov_iter_truncate(from, count);
 	return iov_iter_count(from);
 }
 EXPORT_SYMBOL(generic_write_checks);
@@ -2991,6 +3002,7 @@ int generic_remap_checks(struct file *file_in, loff_t pos_in,
 	uint64_t bcount;
 	loff_t size_in, size_out;
 	loff_t bs = inode_out->i_sb->s_blocksize;
+	int ret;
 
 	/* The start of both ranges must be aligned to an fs block. */
 	if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_out, bs))
@@ -3014,6 +3026,14 @@ int generic_remap_checks(struct file *file_in, loff_t pos_in,
 		return -EINVAL;
 	count = min(count, size_in - (uint64_t)pos_in);
 
+	ret = generic_access_check_limits(file_in, pos_in, &count);
+	if (ret)
+		return ret;
+
+	ret = generic_write_check_limits(file_out, pos_out, &count);
+	if (ret)
+		return ret;
+
 	/*
 	 * If the user wanted us to link to the infile's EOF, round up to the
 	 * next block boundary for this check.
-- 
cgit v1.2.3-58-ga151


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 'mm/filemap.c')

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 v1.2.3-58-ga151


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 'mm/filemap.c')

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 v1.2.3-58-ga151


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 'mm/filemap.c')

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 v1.2.3-58-ga151