raw-posix: support discard on more filesystems

Linux 2.6.38 introduced the filesystem independent interface to
deallocate part of a file. As of Linux 3.7, btrfs, ext4, ocfs2,
tmpfs and xfs support it.

Even though the system calls here are in practice issued on Linux,
the code is structured to allow plugging in alternatives for other Unix
variants.  EOPNOTSUPP is used unconditionally in this patch, but it is
supported in both OpenBSD and Mac OS X since forever (see for example
http://lists.debian.org/debian-glibc/2006/02/msg00337.html).

Signed-off-by: Kusanagi Kouichi <slash@ac.auone-net.jp>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

diff --git a/block/raw-posix.c b/block/raw-posix.c
index c3d7fda7b7b53d24e4df2e54d661d3125b48fceb..e8d79afe5ffbf34e64772a2182bc81d2568baca2 100644 (file)
--- a/block/raw-posix.c
+++ b/block/raw-posix.c
@@ -59,6 +59,9 @@
 #ifdef CONFIG_FIEMAP
 #include <linux/fiemap.h>
 #endif
+#ifdef CONFIG_FALLOCATE_PUNCH_HOLE
+#include <linux/falloc.h>
+#endif
 #if defined (__FreeBSD__) || defined(__FreeBSD_kernel__)
 #include <sys/disk.h>
 #include <sys/cdio.h>
@@ -1074,15 +1077,34 @@ static int xfs_discard(BDRVRawState *s, int64_t sector_num, int nb_sectors)
 static coroutine_fn int raw_co_discard(BlockDriverState *bs,
     int64_t sector_num, int nb_sectors)
 {
-#ifdef CONFIG_XFS
+    int ret = -EOPNOTSUPP;
+
+#if defined(CONFIG_FALLOCATE_PUNCH_HOLE) || defined(CONFIG_XFS)
     BDRVRawState *s = bs->opaque;
 
+#ifdef CONFIG_XFS
     if (s->is_xfs) {
         return xfs_discard(s, sector_num, nb_sectors);
     }
 #endif
 
-    return 0;
+#ifdef CONFIG_FALLOCATE_PUNCH_HOLE
+    do {
+        if (fallocate(s->fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
+                      sector_num << BDRV_SECTOR_BITS,
+                      (int64_t)nb_sectors << BDRV_SECTOR_BITS) == 0) {
+            return 0;
+        }
+    } while (errno == EINTR);
+
+    ret = -errno;
+#endif
+#endif
+
+    if (ret == -EOPNOTSUPP) {
+        return 0;
+    }
+    return ret;
 }
 
 static QEMUOptionParameter raw_create_options[] = {

diff --git a/configure b/configure
index c908f66583a4303a3976a7eabf3e31c6b3cb6448..40d250ccac575c70db0f96095c999840bfbb1604 100755 (executable)
--- a/configure
+++ b/configure
@@ -2581,6 +2581,22 @@ if compile_prog "" "" ; then
   fallocate=yes
 fi
 
+# check for fallocate hole punching
+fallocate_punch_hole=no
+cat > $TMPC << EOF
+#include <fcntl.h>
+#include <linux/falloc.h>
+
+int main(void)
+{
+    fallocate(0, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, 0);
+    return 0;
+}
+EOF
+if compile_prog "" "" ; then
+  fallocate_punch_hole=yes
+fi
+
 # check for sync_file_range
 sync_file_range=no
 cat > $TMPC << EOF
@@ -3490,6 +3506,9 @@ fi
 if test "$fallocate" = "yes" ; then
   echo "CONFIG_FALLOCATE=y" >> $config_host_mak
 fi
+if test "$fallocate_punch_hole" = "yes" ; then
+  echo "CONFIG_FALLOCATE_PUNCH_HOLE=y" >> $config_host_mak
+fi
 if test "$sync_file_range" = "yes" ; then
   echo "CONFIG_SYNC_FILE_RANGE=y" >> $config_host_mak
 fi