net: implement tunnel probing

Tap devices support GSO over UDP tunnel offload. Probe for such
feature in a similar manner to other offloads.

GSO over UDP tunnel needs to be enabled in addition to a "plain"
offload (TSO or USO).

No need to check separately for the outer header checksum offload:
the kernel is going to support both of them or none.

The new features are disabled by default to avoid compat issues,
and could be enabled, after that hw_compat_10_1 will be added,
together with the related compat entries.

Reviewed-by: Akihiko Odaki <odaki@rsg.ci.i.u-tokyo.ac.jp>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Tested-by: Lei Yang <leiyang@redhat.com>
Acked-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Message-ID: <a987a8a7613cbf33bb2209c7c7f5889b512638a7.1758549625.git.pabeni@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index 39f2a8c9879e24a7e98650c0497622c8c74b5bb8..f8e2b4823ea48f3b4b72b2ef7d557704e4380025 100644 (file)
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -649,6 +649,15 @@ static int peer_has_uso(VirtIONet *n)
     return qemu_has_uso(qemu_get_queue(n->nic)->peer);
 }
 
+static bool peer_has_tunnel(VirtIONet *n)
+{
+    if (!peer_has_vnet_hdr(n)) {
+        return false;
+    }
+
+    return qemu_has_tunnel(qemu_get_queue(n->nic)->peer);
+}
+
 static void virtio_net_set_mrg_rx_bufs(VirtIONet *n, int mergeable_rx_bufs,
                                        int version_1, int hash_report)
 {
@@ -3079,6 +3088,13 @@ static void virtio_net_get_features(VirtIODevice *vdev, uint64_t *features,
         virtio_clear_feature_ex(features, VIRTIO_NET_F_GUEST_USO4);
         virtio_clear_feature_ex(features, VIRTIO_NET_F_GUEST_USO6);
 
+        virtio_clear_feature_ex(features, VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO);
+        virtio_clear_feature_ex(features, VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO);
+        virtio_clear_feature_ex(features,
+                                VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_CSUM);
+        virtio_clear_feature_ex(features,
+                                VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO_CSUM);
+
         virtio_clear_feature_ex(features, VIRTIO_NET_F_HASH_REPORT);
     }
 
@@ -3092,6 +3108,15 @@ static void virtio_net_get_features(VirtIODevice *vdev, uint64_t *features,
         virtio_clear_feature_ex(features, VIRTIO_NET_F_GUEST_USO6);
     }
 
+    if (!peer_has_tunnel(n)) {
+        virtio_clear_feature_ex(features, VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO);
+        virtio_clear_feature_ex(features, VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO);
+        virtio_clear_feature_ex(features,
+                                VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_CSUM);
+        virtio_clear_feature_ex(features,
+                                VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO_CSUM);
+    }
+
     if (!get_vhost_net(nc->peer)) {
         if (!use_own_hash) {
             virtio_clear_feature_ex(features, VIRTIO_NET_F_HASH_REPORT);
@@ -4254,6 +4279,22 @@ static const Property virtio_net_properties[] = {
                                   rss_data.specified_hash_types,
                                   VIRTIO_NET_HASH_REPORT_UDPv6_EX - 1,
                                   ON_OFF_AUTO_AUTO),
+    VIRTIO_DEFINE_PROP_FEATURE("host_tunnel", VirtIONet,
+                               host_features_ex,
+                               VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO,
+                               false),
+    VIRTIO_DEFINE_PROP_FEATURE("host_tunnel_csum", VirtIONet,
+                               host_features_ex,
+                               VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO_CSUM,
+                               false),
+    VIRTIO_DEFINE_PROP_FEATURE("guest_tunnel", VirtIONet,
+                               host_features_ex,
+                               VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO,
+                               false),
+    VIRTIO_DEFINE_PROP_FEATURE("guest_tunnel_csum", VirtIONet,
+                               host_features_ex,
+                               VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_CSUM,
+                               false),
 };
 
 static void virtio_net_class_init(ObjectClass *klass, const void *data)

diff --git a/include/net/net.h b/include/net/net.h
index 48ba333d0276f8120cf77e0ffa40bc43e0470fc3..9a9084690db467d8c6302d44987adbcd640c5a53 100644 (file)
--- a/include/net/net.h
+++ b/include/net/net.h
@@ -65,6 +65,7 @@ typedef void (NetClientDestructor)(NetClientState *);
 typedef RxFilterInfo *(QueryRxFilter)(NetClientState *);
 typedef bool (HasUfo)(NetClientState *);
 typedef bool (HasUso)(NetClientState *);
+typedef bool (HasTunnel)(NetClientState *);
 typedef bool (HasVnetHdr)(NetClientState *);
 typedef bool (HasVnetHdrLen)(NetClientState *, int);
 typedef void (SetOffload)(NetClientState *, const NetOffloads *);
@@ -95,6 +96,7 @@ typedef struct NetClientInfo {
     NetPoll *poll;
     HasUfo *has_ufo;
     HasUso *has_uso;
+    HasTunnel *has_tunnel;
     HasVnetHdr *has_vnet_hdr;
     HasVnetHdrLen *has_vnet_hdr_len;
     SetOffload *set_offload;
@@ -197,6 +199,7 @@ void qemu_set_info_str(NetClientState *nc,
 void qemu_format_nic_info_str(NetClientState *nc, uint8_t macaddr[6]);
 bool qemu_has_ufo(NetClientState *nc);
 bool qemu_has_uso(NetClientState *nc);
+bool qemu_has_tunnel(NetClientState *nc);
 bool qemu_has_vnet_hdr(NetClientState *nc);
 bool qemu_has_vnet_hdr_len(NetClientState *nc, int len);
 void qemu_set_offload(NetClientState *nc, const NetOffloads *ol);

diff --git a/net/net.c b/net/net.c
index 63872b6855609965d1bbebff3c97b3abdf879163..9536184a0cf4ab64a57ace8e14cb5f939dc14753 100644 (file)
--- a/net/net.c
+++ b/net/net.c
@@ -522,6 +522,15 @@ bool qemu_has_uso(NetClientState *nc)
     return nc->info->has_uso(nc);
 }
 
+bool qemu_has_tunnel(NetClientState *nc)
+{
+    if (!nc || !nc->info->has_tunnel) {
+        return false;
+    }
+
+    return nc->info->has_tunnel(nc);
+}
+
 bool qemu_has_vnet_hdr(NetClientState *nc)
 {
     if (!nc || !nc->info->has_vnet_hdr) {

diff --git a/net/tap-bsd.c b/net/tap-bsd.c
index 38eb28cb5878cfa4afb03ef4e724367684b142a8..bbf84d1828d34bd5d85000fb5b249a9c50d3c2ff 100644 (file)
--- a/net/tap-bsd.c
+++ b/net/tap-bsd.c
@@ -225,6 +225,11 @@ int tap_probe_has_uso(int fd)
     return 0;
 }
 
+bool tap_probe_has_tunnel(int fd)
+{
+    return false;
+}
+
 void tap_fd_set_vnet_hdr_len(int fd, int len)
 {
 }

diff --git a/net/tap-linux.c b/net/tap-linux.c
index 79a9dd0da01deebf67998dc3620d665bb3390ea5..98b0ae9602d09a75a57201db5a8ecbd855baad79 100644 (file)
--- a/net/tap-linux.c
+++ b/net/tap-linux.c
@@ -201,6 +201,17 @@ int tap_probe_has_uso(int fd)
     return 1;
 }
 
+bool tap_probe_has_tunnel(int fd)
+{
+    unsigned offload;
+
+    offload = TUN_F_CSUM | TUN_F_TSO4 | TUN_F_UDP_TUNNEL_GSO;
+    if (ioctl(fd, TUNSETOFFLOAD, offload) < 0) {
+        return false;
+    }
+    return true;
+}
+
 void tap_fd_set_vnet_hdr_len(int fd, int len)
 {
     if (ioctl(fd, TUNSETVNETHDRSZ, &len) == -1) {

diff --git a/net/tap-linux.h b/net/tap-linux.h
index 9a58cecb7f47933a919d3345af0451e88c9a3f9c..8cd6b5874b988c4aab6cf16be8d526a6ba4aea1f 100644 (file)
--- a/net/tap-linux.h
+++ b/net/tap-linux.h
@@ -53,4 +53,13 @@
 #define TUN_F_USO4    0x20    /* I can handle USO for IPv4 packets */
 #define TUN_F_USO6    0x40    /* I can handle USO for IPv6 packets */
 
+/* I can handle TSO/USO for UDP tunneled packets */
+#define TUN_F_UDP_TUNNEL_GSO       0x080
+
+/*
+ * I can handle TSO/USO for UDP tunneled packets requiring csum offload for
+ * the outer header
+ */
+#define TUN_F_UDP_TUNNEL_GSO_CSUM  0x100
+
 #endif /* QEMU_TAP_LINUX_H */

diff --git a/net/tap-solaris.c b/net/tap-solaris.c
index ef8e0feeb0f71b1b20ad0f407b80e3a4cf068e5e..75397e6c5447bb36a52f1198a02fba957bd22623 100644 (file)
--- a/net/tap-solaris.c
+++ b/net/tap-solaris.c
@@ -227,6 +227,11 @@ int tap_probe_has_uso(int fd)
     return 0;
 }
 
+bool tap_probe_has_tunnel(int fd)
+{
+    return false;
+}
+
 void tap_fd_set_vnet_hdr_len(int fd, int len)
 {
 }

diff --git a/net/tap-stub.c b/net/tap-stub.c
index 67d14ad4d5ddf89d7af03f6b728ec611cbe395f9..f7a5e0c1632e41921e15f971f1d39240e5e65b9f 100644 (file)
--- a/net/tap-stub.c
+++ b/net/tap-stub.c
@@ -52,6 +52,11 @@ int tap_probe_has_uso(int fd)
     return 0;
 }
 
+bool tap_probe_has_tunnel(int fd)
+{
+    return false;
+}
+
 void tap_fd_set_vnet_hdr_len(int fd, int len)
 {
 }

diff --git a/net/tap.c b/net/tap.c
index df232837446d71100c7cf284ddeb323486c1ad92..5124372316834ceec5fd58a27177b7b0cb87bc5f 100644 (file)
--- a/net/tap.c
+++ b/net/tap.c
@@ -76,6 +76,7 @@ typedef struct TAPState {
     bool using_vnet_hdr;
     bool has_ufo;
     bool has_uso;
+    bool has_tunnel;
     bool enabled;
     VHostNetState *vhost_net;
     unsigned host_vnet_hdr_len;
@@ -246,6 +247,14 @@ static bool tap_has_uso(NetClientState *nc)
     return s->has_uso;
 }
 
+static bool tap_has_tunnel(NetClientState *nc)
+{
+    TAPState *s = DO_UPCAST(TAPState, nc, nc);
+
+    assert(nc->info->type == NET_CLIENT_DRIVER_TAP);
+    return s->has_tunnel;
+}
+
 static bool tap_has_vnet_hdr(NetClientState *nc)
 {
     TAPState *s = DO_UPCAST(TAPState, nc, nc);
@@ -374,6 +383,7 @@ static NetClientInfo net_tap_info = {
     .cleanup = tap_cleanup,
     .has_ufo = tap_has_ufo,
     .has_uso = tap_has_uso,
+    .has_tunnel = tap_has_tunnel,
     .has_vnet_hdr = tap_has_vnet_hdr,
     .has_vnet_hdr_len = tap_has_vnet_hdr_len,
     .set_offload = tap_set_offload,
@@ -403,6 +413,7 @@ static TAPState *net_tap_fd_init(NetClientState *peer,
     s->using_vnet_hdr = false;
     s->has_ufo = tap_probe_has_ufo(s->fd);
     s->has_uso = tap_probe_has_uso(s->fd);
+    s->has_tunnel = tap_probe_has_tunnel(s->fd);
     s->enabled = true;
     tap_set_offload(&s->nc, &ol);
     /*

diff --git a/net/tap_int.h b/net/tap_int.h
index f8bbe1cb0c6d3515cb5cb566678e0514c7cfc0a8..b76a05044bc5a32b0caf2a0011fdcfbafe05074a 100644 (file)
--- a/net/tap_int.h
+++ b/net/tap_int.h
@@ -38,6 +38,7 @@ void tap_set_sndbuf(int fd, const NetdevTapOptions *tap, Error **errp);
 int tap_probe_vnet_hdr(int fd, Error **errp);
 int tap_probe_has_ufo(int fd);
 int tap_probe_has_uso(int fd);
+bool tap_probe_has_tunnel(int fd);
 void tap_fd_set_offload(int fd, const NetOffloads *ol);
 void tap_fd_set_vnet_hdr_len(int fd, int len);
 int tap_fd_set_vnet_le(int fd, int vnet_is_le);