From: Paul Eggert <eggert@cs.ucla.edu>
Date: Fri, 26 Jun 2020 00:34:23 +0000 (-0700)
Subject: cp: use copy_file_range if available
X-Git-Tag: v9.0~227
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=4b04a0c3b792d27909670a81d21f2a3b3e0ea563;p=thirdparty%2Fcoreutils.git

cp: use copy_file_range if available

* NEWS: Mention this.
* bootstrap.conf (gnulib_modules): Add copy-file-range.
* src/copy.c (sparse_copy): Try copy_file_range if not
looking for holes.
---

diff --git a/NEWS b/NEWS
index 63cb47d105..1c3f6378d6 100644
--- a/NEWS
+++ b/NEWS
@@ -17,8 +17,9 @@ GNU coreutils NEWS                                    -*- outline -*-
 
   cp and install now default to copy-on-write (COW) if available.
 
-  cp, install and mv now prefer lseek+SEEK_HOLE to ioctl+FS_IOC_FIEMAP
-  on sparse files, as lseek is simpler and more portable.
+  cp, install and mv now use the copy_file_range syscall if available.
+  Also, they prefer lseek+SEEK_HOLE to ioctl+FS_IOC_FIEMAP on sparse
+  files, as lseek is simpler and more portable.
 
   On GNU/Linux systems, ls no longer issues an error message on a
   directory merely because it was removed.  This reverts a change
diff --git a/bootstrap.conf b/bootstrap.conf
index 12e2d831a3..2506f0db47 100644
--- a/bootstrap.conf
+++ b/bootstrap.conf
@@ -54,6 +54,7 @@ gnulib_modules="
   closeout
   config-h
   configmake
+  copy-file-range
   crypto/md5
   crypto/sha1
   crypto/sha256
diff --git a/src/copy.c b/src/copy.c
index d88f8cf930..4050f69536 100644
--- a/src/copy.c
+++ b/src/copy.c
@@ -265,6 +265,46 @@ sparse_copy (int src_fd, int dest_fd, char *buf, size_t buf_size,
 {
   *last_write_made_hole = false;
   *total_n_read = 0;
+
+  /* If not looking for holes, use copy_file_range if available.  */
+  if (!hole_size)
+    while (max_n_read)
+      {
+        /* Copy at most COPY_MAX bytes at a time; this is min
+           (PTRDIFF_MAX, SIZE_MAX) truncated to a value that is
+           surely aligned well.  */
+        ssize_t ssize_max = TYPE_MAXIMUM (ssize_t);
+        ptrdiff_t copy_max = MIN (ssize_max, SIZE_MAX) >> 30 << 30;
+        ssize_t n_copied = copy_file_range (src_fd, NULL, dest_fd, NULL,
+                                            MIN (max_n_read, copy_max), 0);
+        if (n_copied == 0)
+          {
+            /* copy_file_range incorrectly returns 0 when reading from
+               the proc file system on the Linux kernel through at
+               least 5.6.19 (2020), so fall back on 'read' if the
+               input file seems empty.  */
+            if (*total_n_read == 0)
+              break;
+            return true;
+          }
+        if (n_copied < 0)
+          {
+            if (errno == ENOSYS || errno == EINVAL
+                || errno == EBADF || errno == EXDEV)
+              break;
+            if (errno == EINTR)
+              n_copied = 0;
+            else
+              {
+                error (0, errno, _("error copying %s to %s"),
+                       quoteaf_n (0, src_name), quoteaf_n (1, dst_name));
+                return false;
+              }
+          }
+        max_n_read -= n_copied;
+        *total_n_read += n_copied;
+      }
+
   bool make_hole = false;
   off_t psize = 0;