[PATCH v4 0/9] VFS: In-kernel copy system call

@@ -16,6 +16,7 @@
 #include <linux/pagemap.h>
 #include <linux/splice.h>
 #include <linux/compat.h>
+#include <linux/mount.h>
 #include "internal.h"
 
 #include <asm/uaccess.h>

@@ -1327,3 +1328,131 @@ COMPAT_SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd,
 	return do_sendfile(out_fd, in_fd, NULL, count, 0);
 }
 #endif
+
+/*
+ * copy_file_range() differs from regular file read and write in that it
+ * specifically allows return partial success.  When it does so is up to
+ * the copy_file_range method.
+ */
+ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
+			    struct file *file_out, loff_t pos_out,
+			    size_t len, unsigned int flags)
+{
+	struct inode *inode_in;
+	struct inode *inode_out;
+	ssize_t ret;
+
+	if (flags)
+		return -EINVAL;
+
+	if (len == 0)
+		return 0;
+
+	/* copy_file_range allows full ssize_t len, ignoring MAX_RW_COUNT  */
+	ret = rw_verify_area(READ, file_in, &pos_in, len);
+	if (ret >= 0)
+		ret = rw_verify_area(WRITE, file_out, &pos_out, len);
+	if (ret < 0)
+		return ret;
+
+	if (!(file_in->f_mode & FMODE_READ) ||
+	    !(file_out->f_mode & FMODE_WRITE) ||
+	    (file_out->f_flags & O_APPEND) ||
+	    !file_in->f_op || !file_in->f_op->copy_file_range)
+		return -EBADF;
+
+	inode_in = file_inode(file_in);
+	inode_out = file_inode(file_out);
+
+	/* make sure offsets don't wrap and the input is inside i_size */
+	if (pos_in + len < pos_in || pos_out + len < pos_out ||
+	    pos_in + len > i_size_read(inode_in))
+		return -EINVAL;
+
+	/* this could be relaxed once a method supports cross-fs copies */
+	if (inode_in->i_sb != inode_out->i_sb ||
+	    file_in->f_path.mnt != file_out->f_path.mnt)
+		return -EXDEV;
+
+	/* forbid ranges in the same file */
+	if (inode_in == inode_out)
+		return -EINVAL;
+
+	ret = mnt_want_write_file(file_out);
+	if (ret)
+		return ret;
+
+	ret = file_in->f_op->copy_file_range(file_in, pos_in, file_out, pos_out,
+					     len, flags);
+	if (ret > 0) {
+		fsnotify_access(file_in);
+		add_rchar(current, ret);
+		fsnotify_modify(file_out);
+		add_wchar(current, ret);
+	}
+	inc_syscr(current);
+	inc_syscw(current);
+
+	mnt_drop_write_file(file_out);
+
+	return ret;
+}
+EXPORT_SYMBOL(vfs_copy_file_range);
+
+SYSCALL_DEFINE6(copy_file_range, int, fd_in, loff_t __user *, off_in,
+		int, fd_out, loff_t __user *, off_out,
+		size_t, len, unsigned int, flags)
+{
+	loff_t pos_in;
+	loff_t pos_out;
+	struct fd f_in;
+	struct fd f_out;
+	ssize_t ret;
+
+	f_in = fdget(fd_in);
+	f_out = fdget(fd_out);
+	if (!f_in.file || !f_out.file) {
+		ret = -EBADF;
+		goto out;
+	}
+
+	ret = -EFAULT;
+	if (off_in) {
+		if (copy_from_user(&pos_in, off_in, sizeof(loff_t)))
+			goto out;
+	} else {
+		pos_in = f_in.file->f_pos;
+	}
+
+	if (off_out) {
+		if (copy_from_user(&pos_out, off_out, sizeof(loff_t)))
+			goto out;
+	} else {
+		pos_out = f_out.file->f_pos;
+	}
+
+	ret = vfs_copy_file_range(f_in.file, pos_in, f_out.file, pos_out, len,
+				  flags);
+	if (ret > 0) {
+		pos_in += ret;
+		pos_out += ret;
+
+		if (off_in) {
+			if (copy_to_user(off_in, &pos_in, sizeof(loff_t)))
+				ret = -EFAULT;
+		} else {
+			f_in.file->f_pos = pos_in;
+		}
+
+		if (off_out) {
+			if (copy_to_user(off_out, &pos_out, sizeof(loff_t)))
+				ret = -EFAULT;
+		} else {
+			f_out.file->f_pos = pos_out;
+		}
+	}
+out:
+	fdput(f_in);
+	fdput(f_out);
+	return ret;
+}

@@ -1642,6 +1642,7 @@ struct file_operations {
 #ifndef CONFIG_MMU
 	unsigned (*mmap_capabilities)(struct file *);
 #endif
+	ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int);
 };
 
 struct inode_operations {

@@ -1695,6 +1696,8 @@ extern ssize_t vfs_readv(struct file *, const struct iovec __user *,
 		unsigned long, loff_t *);
 extern ssize_t vfs_writev(struct file *, const struct iovec __user *,
 		unsigned long, loff_t *);
+extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *,
+				   loff_t, size_t, unsigned int);
 
 struct super_operations {
    	struct inode *(*alloc_inode)(struct super_block *sb);

@@ -713,6 +713,8 @@ __SC_COMP(__NR_execveat, sys_execveat, compat_sys_execveat)
 __SYSCALL(__NR_userfaultfd, sys_userfaultfd)
 #define __NR_membarrier 283
 __SYSCALL(__NR_membarrier, sys_membarrier)
+#define __NR_copy_file_range 283
+__SYSCALL(__NR_copy_file_range, sys_copy_file_range)
 
 #undef __NR_syscalls
 #define __NR_syscalls 284

@@ -174,6 +174,7 @@ cond_syscall(sys_setfsuid);
 cond_syscall(sys_setfsgid);
 cond_syscall(sys_capget);
 cond_syscall(sys_capset);
+cond_syscall(sys_copy_file_range);
 
 /* arch-specific weak syscall entries */
 cond_syscall(sys_pciconfig_read);

@@ -1345,9 +1345,6 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
 	if (flags)
 		return -EINVAL;
 
-	if (len == 0)
-		return 0;
-
 	/* copy_file_range allows full ssize_t len, ignoring MAX_RW_COUNT  */
 	ret = rw_verify_area(READ, file_in, &pos_in, len);
 	if (ret >= 0)

@@ -1378,6 +1375,9 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
 	if (inode_in == inode_out)
 		return -EINVAL;
 
+	if (len == 0)
+		return 0;
+
 	ret = mnt_want_write_file(file_out);
 	if (ret)
 		return ret;

@@ -44,6 +44,7 @@
 #include <linux/uuid.h>
 #include <linux/btrfs.h>
 #include <linux/uaccess.h>
+#include <linux/copy.h>
 #include "ctree.h"
 #include "disk-io.h"
 #include "transaction.h"

@@ -3848,6 +3849,9 @@ ssize_t btrfs_copy_file_range(struct file *file_in, loff_t pos_in,
 {
 	ssize_t ret;
 
+	if (!(flags & COPY_FR_REFLINK))
+		return -EOPNOTSUPP;
+
 	ret = btrfs_clone_files(file_out, file_in, pos_in, len, pos_out);
 	if (ret == 0)
 		ret = len;

@@ -0,0 +1,224 @@
+.\"This manpage is Copyright (C) 2015 Anna Schumaker <Anna.Schumaker@Netapp.com>
+.\"
+.\" %%%LICENSE_START(VERBATIM)
+.\" Permission is granted to make and distribute verbatim copies of this
+.\" manual provided the copyright notice and this permission notice are
+.\" preserved on all copies.
+.\"
+.\" Permission is granted to copy and distribute modified versions of
+.\" this manual under the conditions for verbatim copying, provided that
+.\" the entire resulting derived work is distributed under the terms of
+.\" a permission notice identical to this one.
+.\"
+.\" Since the Linux kernel and libraries are constantly changing, this
+.\" manual page may be incorrect or out-of-date.  The author(s) assume.
+.\" no responsibility for errors or omissions, or for damages resulting.
+.\" from the use of the information contained herein.  The author(s) may.
+.\" not have taken the same level of care in the production of this.
+.\" manual, which is licensed free of charge, as they might when working.
+.\" professionally.
+.\"
+.\" Formatted or processed versions of this manual, if unaccompanied by
+.\" the source, must acknowledge the copyright and authors of this work.
+.\" %%%LICENSE_END
+.\"
+.TH COPY 2 2015-09-29 "Linux" "Linux Programmer's Manual"
+.SH NAME
+copy_file_range \- Copy a range of data from one file to another
+.SH SYNOPSIS
+.nf
+.B #include <linux/copy.h>
+.B #include <sys/syscall.h>
+.B #include <unistd.h>
+
+.BI "ssize_t copy_file_range(int " fd_in ", loff_t *" off_in ", int " fd_out ",
+.BI "                        loff_t *" off_out ", size_t " len \
+", unsigned int " flags );
+.fi
+.SH DESCRIPTION
+The
+.BR copy_file_range ()
+system call performs an in-kernel copy between two file descriptors
+without the additional cost of transferring data from the kernel to userspace
+and then back into the kernel.
+It copies up to
+.I len
+bytes of data from file descriptor
+.I fd_in
+to file descriptor
+.IR fd_out ,
+overwriting any data that exists within the requested range of the target file.
+
+The following semantics apply for
+.IR off_in ,
+and similar statements apply to
+.IR off_out :
+.IP * 3
+If
+.I off_in
+is NULL, then bytes are read from
+.I fd_in
+starting from the current file offset, and the offset is
+adjusted by the number of bytes copied.
+.IP *
+If
+.I off_in
+is not NULL, then
+.I off_in
+must point to a buffer that specifies the starting
+offset where bytes from
+.I fd_in
+will be read.  The current file offset of
+.I fd_in
+is not changed, but
+.I off_in
+is adjusted appropriately.
+.PP
+
+The
+.I flags
+argument can have one of the following flags set:
+.TP 1.9i
+.B COPY_FR_COPY
+Copy all the file data in the requested range.
+Some filesystems might be able to accelerate this copy
+to avoid unnecessary data transfers.
+.TP
+.B COPY_FR_REFLINK
+Create a lightweight "reflink", where data is not copied until
+one of the files is modified.
+.TP
+.B COPY_FR_DEDUP
+Create a reflink, but only if the contents of
+both files' byte ranges are identical.
+If ranges do not match,
+.B EILSEQ
+will be returned.
+.PP
+The default behavior
+.RI ( flags
+== 0) is to try creating a reflink,
+and if reflinking fails
+.BR copy_file_range ()
+will fall back to performing a full data copy.
+.SH RETURN VALUE
+Upon successful completion,
+.BR copy_file_range ()
+will return the number of bytes copied between files.
+This could be less than the length originally requested.
+
+On error,
+.BR copy_file_range ()
+returns \-1 and
+.I errno
+is set to indicate the error.
+.SH ERRORS
+.TP
+.B EBADF
+One or more file descriptors are not valid; or
+.I fd_in
+is not open for reading; or
+.I fd_out
+is not open for writing.
+.TP
+.B EILSEQ
+The contents of both files' byte ranges did not match.
+.TP
+.B EINVAL
+Requested range extends beyond the end of the source file; or the
+.I flags
+argument is set to an invalid value.
+.TP
+.B EIO
+A low level I/O error occurred while copying.
+.TP
+.B ENOMEM
+Out of memory.
+.TP
+.B ENOSPC
+There is not enough space on the target filesystem to complete the copy.
+.TP
+.B EOPNOTSUPP
+.B COPY_REFLINK
+or
+.B COPY_DEDUP
+was specified in
+.IR flags ,
+but the target filesystem does not support the given operation.
+.TP
+.B EXDEV
+Target filesystem doesn't support cross-filesystem copies.
+.SH VERSIONS
+The
+.BR copy_file_range ()
+system call first appeared in Linux 4.4.
+.SH CONFORMING TO
+The
+.BR copy_file_range ()
+system call is a nonstandard Linux extension.
+.SH EXAMPLE
+.nf
+#define _GNU_SOURCE
+#include <fcntl.h>
+#include <linux/copy.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+
+loff_t copy_file_range(int fd_in, loff_t *off_in, int fd_out,
+                       loff_t *off_out, size_t len, unsigned int flags)
+{
+    return syscall(__NR_copy_file_range, fd_in, off_in, fd_out,
+                   off_out, len, flags);
+}
+
+int main(int argc, char **argv)
+{
+    int fd_in, fd_out;
+    struct stat stat;
+    loff_t len, ret;
+    char buf[2];
+
+    if (argc != 3) {
+        fprintf(stderr, "Usage: %s <source> <destination>\\n", argv[0]);
+        exit(EXIT_FAILURE);
+    }
+
+    fd_in = open(argv[1], O_RDONLY);
+    if (fd_in == \-1) {
+        perror("open (argv[1])");
+        exit(EXIT_FAILURE);
+    }
+
+    if (fstat(fd_in, &stat) == \-1) {
+        perror("fstat");
+        exit(EXIT_FAILURE);
+    }
+    len = stat.st_size;
+
+    fd_out = open(argv[2], O_CREAT|O_WRONLY|O_TRUNC, 0644);
+    if (fd_out == \-1) {
+        perror("open (argv[2])");
+        exit(EXIT_FAILURE);
+    }
+
+    do {
+        ret = copy_file_range(fd_in, NULL, fd_out, NULL, 
+                              len, COPY_FR_COPY);
+        if (ret == \-1) {
+            perror("copy_file_range");
+            exit(EXIT_FAILURE);
+        }
+
+        len \-= ret;
+    } while (len > 0);
+
+    close(fd_in);
+    close(fd_out);
+    exit(EXIT_SUCCESS);
+}
+.fi
+.SH SEE ALSO
+.BR splice (2)

@@ -238,6 +238,7 @@ only pointers are copied, not the pages of the buffer.
 See
 .BR tee (2).
 .SH SEE ALSO
+.BR copy_file_range (2),
 .BR sendfile (2),
 .BR tee (2),
 .BR vmsplice (2)