[PATCH qemu-kvm] Enable UFO on virtio-net and tap devices

[Sridhar Samudrala <sri@xxxxxxxxxx>]

linux 2.6.32 includes UDP fragmentation offload support in software. 
So we can enable UFO on the host tap device if supported and allow setting
UFO on virtio-net in the guest.

This improves UDP stream performance significantly between guest to host
and inter-guest.

TUN_F_UFO is a new #define added to 2.6.32 kernel header file
include/linux/if_tun.h. Until this updated header file gets into distro
releases, i think we need to have this defined in qemu.

Signed-off-by: Sridhar Samudrala <sri@xxxxxxxxxx>

diff --git a/hw/virtio-net.c b/hw/virtio-net.c
index ce8e6cb..c73487d 100644
--- a/hw/virtio-net.c
+++ b/hw/virtio-net.c
@@ -150,7 +150,8 @@ static uint32_t virtio_net_get_features(VirtIODevice *vdev)
         features |= (1 << VIRTIO_NET_F_HOST_TSO6);
         features |= (1 << VIRTIO_NET_F_HOST_ECN);
         features |= (1 << VIRTIO_NET_F_MRG_RXBUF);
-        /* Kernel can't actually handle UFO in software currently. */
+        features |= (1 << VIRTIO_NET_F_GUEST_UFO);
+        features |= (1 << VIRTIO_NET_F_HOST_UFO);
     }
 #endif
 
@@ -189,7 +190,8 @@ static void virtio_net_set_features(VirtIODevice *vdev, uint32_t features)
                       (features >> VIRTIO_NET_F_GUEST_CSUM) & 1,
                       (features >> VIRTIO_NET_F_GUEST_TSO4) & 1,
                       (features >> VIRTIO_NET_F_GUEST_TSO6) & 1,
-                      (features >> VIRTIO_NET_F_GUEST_ECN)  & 1);
+                      (features >> VIRTIO_NET_F_GUEST_ECN)  & 1,
+                      (features >> VIRTIO_NET_F_GUEST_UFO)  & 1);
 #endif
 }
 
diff --git a/net.c b/net.c
index 8032ff8..1942e25 100644
--- a/net.c
+++ b/net.c
@@ -1528,8 +1528,13 @@ static int tap_probe_vnet_hdr(int fd)
 }
 
 #ifdef TUNSETOFFLOAD
+
+#ifndef TUN_F_UFO
+#define TUN_F_UFO	0x10
+#endif
+
 static void tap_set_offload(VLANClientState *vc, int csum, int tso4, int tso6,
-			    int ecn)
+			    int ecn, int ufo)
 {
     TAPState *s = vc->opaque;
     unsigned int offload = 0;
@@ -1542,11 +1547,18 @@ static void tap_set_offload(VLANClientState *vc, int csum, int tso4, int tso6,
 	    offload |= TUN_F_TSO6;
 	if ((tso4 || tso6) && ecn)
 	    offload |= TUN_F_TSO_ECN;
+	if (ufo)
+	    offload |= TUN_F_UFO;
     }
 
-    if (ioctl(s->fd, TUNSETOFFLOAD, offload) != 0)
-	fprintf(stderr, "TUNSETOFFLOAD ioctl() failed: %s\n",
-		strerror(errno));
+    if (ioctl(s->fd, TUNSETOFFLOAD, offload) != 0) {
+        /* Try without UFO */
+        offload &= ~TUN_F_UFO;
+        if (ioctl(s->fd, TUNSETOFFLOAD, offload) != 0) {
+	    fprintf(stderr, "TUNSETOFFLOAD ioctl() failed: %s\n",
+	   	strerror(errno));
+        }
+    }
 }
 #endif /* TUNSETOFFLOAD */
 
@@ -1583,7 +1595,7 @@ static TAPState *net_tap_fd_init(VLANState *vlan,
     s->vc->receive_raw = tap_receive_raw;
 #ifdef TUNSETOFFLOAD
     s->vc->set_offload = tap_set_offload;
-    tap_set_offload(s->vc, 0, 0, 0, 0);
+    tap_set_offload(s->vc, 0, 0, 0, 0, 0);
 #endif
     tap_read_poll(s, 1);
     snprintf(s->vc->info_str, sizeof(s->vc->info_str), "fd=%d", fd);
diff --git a/net.h b/net.h
index 925c67c..ac3701c 100644
--- a/net.h
+++ b/net.h
@@ -14,7 +14,7 @@ typedef ssize_t (NetReceive)(VLANClientState *, const uint8_t *, size_t);
 typedef ssize_t (NetReceiveIOV)(VLANClientState *, const struct iovec *, int);
 typedef void (NetCleanup) (VLANClientState *);
 typedef void (LinkStatusChanged)(VLANClientState *);
-typedef void (SetOffload)(VLANClientState *, int, int, int, int);
+typedef void (SetOffload)(VLANClientState *, int, int, int, int, int);
 
 struct VLANClientState {
     NetReceive *receive;



--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html