From e5fd02d8253abdc25c0eb145765734890c256b71 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Mon, 22 Sep 2025 16:18:15 +0200 Subject: net: bundle all offloads in a single struct The set_offload() argument list is already pretty long and we are going to introduce soon a bunch of additional offloads. Replace the offload arguments with a single struct and update all the relevant call-sites. No functional changes intended. Signed-off-by: Paolo Abeni Tested-by: Lei Yang Reviewed-by: Michael S. Tsirkin Message-ID: Signed-off-by: Michael S. Tsirkin --- hw/net/virtio-net.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) (limited to 'hw/net/virtio-net.c') diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c index 7848e26278..129bebd82e 100644 --- a/hw/net/virtio-net.c +++ b/hw/net/virtio-net.c @@ -773,14 +773,17 @@ static uint64_t virtio_net_bad_features(VirtIODevice *vdev) static void virtio_net_apply_guest_offloads(VirtIONet *n) { - qemu_set_offload(qemu_get_queue(n->nic)->peer, - !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_CSUM)), - !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_TSO4)), - !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_TSO6)), - !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_ECN)), - !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_UFO)), - !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_USO4)), - !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_USO6))); + NetOffloads ol = { + .csum = !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_CSUM)), + .tso4 = !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_TSO4)), + .tso6 = !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_TSO6)), + .ecn = !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_ECN)), + .ufo = !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_UFO)), + .uso4 = !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_USO4)), + .uso6 = !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_USO6)), + }; + + qemu_set_offload(qemu_get_queue(n->nic)->peer, &ol); } static uint64_t virtio_net_guest_offloads_by_features(uint64_t features) -- cgit 1.4.1 From 3a7741c3bdc3537de4159418d712debbd22e4df6 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Mon, 22 Sep 2025 16:18:26 +0200 Subject: virtio-net: implement extended features support Use the extended types and helpers to manipulate the virtio_net features. Note that offloads are still 64bits wide, as per specification, and extended offloads will be mapped into such range. Reviewed-by: Akihiko Odaki Acked-by: Jason Wang Signed-off-by: Paolo Abeni Tested-by: Lei Yang Acked-by: Stefano Garzarella Reviewed-by: Michael S. Tsirkin Message-ID: Signed-off-by: Michael S. Tsirkin --- hw/net/virtio-net.c | 140 ++++++++++++++++++++++++----------------- include/hw/virtio/virtio-net.h | 2 +- 2 files changed, 83 insertions(+), 59 deletions(-) (limited to 'hw/net/virtio-net.c') diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c index 129bebd82e..39f2a8c987 100644 --- a/hw/net/virtio-net.c +++ b/hw/net/virtio-net.c @@ -90,6 +90,19 @@ VIRTIO_NET_RSS_HASH_TYPE_TCP_EX | \ VIRTIO_NET_RSS_HASH_TYPE_UDP_EX) +/* + * Features starting from VIRTIO_NET_FEATURES_MAP_MIN bit correspond + * to guest offloads in the VIRTIO_NET_OFFLOAD_MAP range + */ +#define VIRTIO_NET_OFFLOAD_MAP_MIN 46 +#define VIRTIO_NET_OFFLOAD_MAP_LENGTH 4 +#define VIRTIO_NET_OFFLOAD_MAP MAKE_64BIT_MASK( \ + VIRTIO_NET_OFFLOAD_MAP_MIN, \ + VIRTIO_NET_OFFLOAD_MAP_LENGTH) +#define VIRTIO_NET_FEATURES_MAP_MIN 65 +#define VIRTIO_NET_F2O_SHIFT (VIRTIO_NET_OFFLOAD_MAP_MIN - \ + VIRTIO_NET_FEATURES_MAP_MIN + 64) + static const VirtIOFeature feature_sizes[] = { {.flags = 1ULL << VIRTIO_NET_F_MAC, .end = endof(struct virtio_net_config, mac)}, @@ -786,7 +799,14 @@ static void virtio_net_apply_guest_offloads(VirtIONet *n) qemu_set_offload(qemu_get_queue(n->nic)->peer, &ol); } -static uint64_t virtio_net_guest_offloads_by_features(uint64_t features) +static uint64_t virtio_net_features_to_offload(const uint64_t *features) +{ + return (features[0] & ~VIRTIO_NET_OFFLOAD_MAP) | + ((features[1] << VIRTIO_NET_F2O_SHIFT) & VIRTIO_NET_OFFLOAD_MAP); +} + +static uint64_t +virtio_net_guest_offloads_by_features(const uint64_t *features) { static const uint64_t guest_offloads_mask = (1ULL << VIRTIO_NET_F_GUEST_CSUM) | @@ -797,13 +817,13 @@ static uint64_t virtio_net_guest_offloads_by_features(uint64_t features) (1ULL << VIRTIO_NET_F_GUEST_USO4) | (1ULL << VIRTIO_NET_F_GUEST_USO6); - return guest_offloads_mask & features; + return guest_offloads_mask & virtio_net_features_to_offload(features); } uint64_t virtio_net_supported_guest_offloads(const VirtIONet *n) { VirtIODevice *vdev = VIRTIO_DEVICE(n); - return virtio_net_guest_offloads_by_features(vdev->guest_features); + return virtio_net_guest_offloads_by_features(vdev->guest_features_ex); } typedef struct { @@ -882,34 +902,39 @@ static void failover_add_primary(VirtIONet *n, Error **errp) error_propagate(errp, err); } -static void virtio_net_set_features(VirtIODevice *vdev, uint64_t features) +static void virtio_net_set_features(VirtIODevice *vdev, + const uint64_t *in_features) { + uint64_t features[VIRTIO_FEATURES_NU64S]; VirtIONet *n = VIRTIO_NET(vdev); Error *err = NULL; int i; + virtio_features_copy(features, in_features); if (n->mtu_bypass_backend && !virtio_has_feature(vdev->backend_features, VIRTIO_NET_F_MTU)) { - features &= ~(1ULL << VIRTIO_NET_F_MTU); + virtio_clear_feature_ex(features, VIRTIO_NET_F_MTU); } virtio_net_set_multiqueue(n, - virtio_has_feature(features, VIRTIO_NET_F_RSS) || - virtio_has_feature(features, VIRTIO_NET_F_MQ)); + virtio_has_feature_ex(features, + VIRTIO_NET_F_RSS) || + virtio_has_feature_ex(features, + VIRTIO_NET_F_MQ)); virtio_net_set_mrg_rx_bufs(n, - virtio_has_feature(features, + virtio_has_feature_ex(features, VIRTIO_NET_F_MRG_RXBUF), - virtio_has_feature(features, + virtio_has_feature_ex(features, VIRTIO_F_VERSION_1), - virtio_has_feature(features, + virtio_has_feature_ex(features, VIRTIO_NET_F_HASH_REPORT)); - n->rsc4_enabled = virtio_has_feature(features, VIRTIO_NET_F_RSC_EXT) && - virtio_has_feature(features, VIRTIO_NET_F_GUEST_TSO4); - n->rsc6_enabled = virtio_has_feature(features, VIRTIO_NET_F_RSC_EXT) && - virtio_has_feature(features, VIRTIO_NET_F_GUEST_TSO6); - n->rss_data.redirect = virtio_has_feature(features, VIRTIO_NET_F_RSS); + n->rsc4_enabled = virtio_has_feature_ex(features, VIRTIO_NET_F_RSC_EXT) && + virtio_has_feature_ex(features, VIRTIO_NET_F_GUEST_TSO4); + n->rsc6_enabled = virtio_has_feature_ex(features, VIRTIO_NET_F_RSC_EXT) && + virtio_has_feature_ex(features, VIRTIO_NET_F_GUEST_TSO6); + n->rss_data.redirect = virtio_has_feature_ex(features, VIRTIO_NET_F_RSS); if (n->has_vnet_hdr) { n->curr_guest_offloads = @@ -923,7 +948,7 @@ static void virtio_net_set_features(VirtIODevice *vdev, uint64_t features) if (!get_vhost_net(nc->peer)) { continue; } - vhost_net_ack_features(get_vhost_net(nc->peer), features); + vhost_net_ack_features_ex(get_vhost_net(nc->peer), features); /* * keep acked_features in NetVhostUserState up-to-date so it @@ -932,12 +957,14 @@ static void virtio_net_set_features(VirtIODevice *vdev, uint64_t features) vhost_net_save_acked_features(nc->peer); } - if (virtio_has_feature(vdev->guest_features ^ features, VIRTIO_NET_F_CTRL_VLAN)) { - bool vlan = virtio_has_feature(features, VIRTIO_NET_F_CTRL_VLAN); + if (virtio_has_feature_ex(features, VIRTIO_NET_F_CTRL_VLAN) != + virtio_has_feature_ex(vdev->guest_features_ex, + VIRTIO_NET_F_CTRL_VLAN)) { + bool vlan = virtio_has_feature_ex(features, VIRTIO_NET_F_CTRL_VLAN); memset(n->vlans, vlan ? 0 : 0xff, MAX_VLAN >> 3); } - if (virtio_has_feature(features, VIRTIO_NET_F_STANDBY)) { + if (virtio_has_feature_ex(features, VIRTIO_NET_F_STANDBY)) { qapi_event_send_failover_negotiated(n->netclient_name); qatomic_set(&n->failover_primary_hidden, false); failover_add_primary(n, &err); @@ -1908,10 +1935,10 @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf, virtio_error(vdev, "virtio-net unexpected empty queue: " "i %zd mergeable %d offset %zd, size %zd, " "guest hdr len %zd, host hdr len %zd " - "guest features 0x%" PRIx64, + "guest features 0x" VIRTIO_FEATURES_FMT, i, n->mergeable_rx_bufs, offset, size, n->guest_hdr_len, n->host_hdr_len, - vdev->guest_features); + VIRTIO_FEATURES_PR(vdev->guest_features_ex)); } err = -1; goto err; @@ -3018,8 +3045,8 @@ static int virtio_net_pre_load_queues(VirtIODevice *vdev, uint32_t n) return 0; } -static uint64_t virtio_net_get_features(VirtIODevice *vdev, uint64_t features, - Error **errp) +static void virtio_net_get_features(VirtIODevice *vdev, uint64_t *features, + Error **errp) { VirtIONet *n = VIRTIO_NET(vdev); NetClientState *nc = qemu_get_queue(n->nic); @@ -3033,68 +3060,67 @@ static uint64_t virtio_net_get_features(VirtIODevice *vdev, uint64_t features, (supported_hash_types & peer_hash_types) == supported_hash_types; /* Firstly sync all virtio-net possible supported features */ - features |= n->host_features; + virtio_features_or(features, features, n->host_features_ex); - virtio_add_feature(&features, VIRTIO_NET_F_MAC); + virtio_add_feature_ex(features, VIRTIO_NET_F_MAC); if (!peer_has_vnet_hdr(n)) { - virtio_clear_feature(&features, VIRTIO_NET_F_CSUM); - virtio_clear_feature(&features, VIRTIO_NET_F_HOST_TSO4); - virtio_clear_feature(&features, VIRTIO_NET_F_HOST_TSO6); - virtio_clear_feature(&features, VIRTIO_NET_F_HOST_ECN); + virtio_clear_feature_ex(features, VIRTIO_NET_F_CSUM); + virtio_clear_feature_ex(features, VIRTIO_NET_F_HOST_TSO4); + virtio_clear_feature_ex(features, VIRTIO_NET_F_HOST_TSO6); + virtio_clear_feature_ex(features, VIRTIO_NET_F_HOST_ECN); - virtio_clear_feature(&features, VIRTIO_NET_F_GUEST_CSUM); - virtio_clear_feature(&features, VIRTIO_NET_F_GUEST_TSO4); - virtio_clear_feature(&features, VIRTIO_NET_F_GUEST_TSO6); - virtio_clear_feature(&features, VIRTIO_NET_F_GUEST_ECN); + virtio_clear_feature_ex(features, VIRTIO_NET_F_GUEST_CSUM); + virtio_clear_feature_ex(features, VIRTIO_NET_F_GUEST_TSO4); + virtio_clear_feature_ex(features, VIRTIO_NET_F_GUEST_TSO6); + virtio_clear_feature_ex(features, VIRTIO_NET_F_GUEST_ECN); - virtio_clear_feature(&features, VIRTIO_NET_F_HOST_USO); - virtio_clear_feature(&features, VIRTIO_NET_F_GUEST_USO4); - virtio_clear_feature(&features, VIRTIO_NET_F_GUEST_USO6); + virtio_clear_feature_ex(features, VIRTIO_NET_F_HOST_USO); + virtio_clear_feature_ex(features, VIRTIO_NET_F_GUEST_USO4); + virtio_clear_feature_ex(features, VIRTIO_NET_F_GUEST_USO6); - virtio_clear_feature(&features, VIRTIO_NET_F_HASH_REPORT); + virtio_clear_feature_ex(features, VIRTIO_NET_F_HASH_REPORT); } if (!peer_has_vnet_hdr(n) || !peer_has_ufo(n)) { - virtio_clear_feature(&features, VIRTIO_NET_F_GUEST_UFO); - virtio_clear_feature(&features, VIRTIO_NET_F_HOST_UFO); + virtio_clear_feature_ex(features, VIRTIO_NET_F_GUEST_UFO); + virtio_clear_feature_ex(features, VIRTIO_NET_F_HOST_UFO); } - if (!peer_has_uso(n)) { - virtio_clear_feature(&features, VIRTIO_NET_F_HOST_USO); - virtio_clear_feature(&features, VIRTIO_NET_F_GUEST_USO4); - virtio_clear_feature(&features, VIRTIO_NET_F_GUEST_USO6); + virtio_clear_feature_ex(features, VIRTIO_NET_F_HOST_USO); + virtio_clear_feature_ex(features, VIRTIO_NET_F_GUEST_USO4); + virtio_clear_feature_ex(features, VIRTIO_NET_F_GUEST_USO6); } if (!get_vhost_net(nc->peer)) { if (!use_own_hash) { - virtio_clear_feature(&features, VIRTIO_NET_F_HASH_REPORT); - virtio_clear_feature(&features, VIRTIO_NET_F_RSS); - } else if (virtio_has_feature(features, VIRTIO_NET_F_RSS)) { + virtio_clear_feature_ex(features, VIRTIO_NET_F_HASH_REPORT); + virtio_clear_feature_ex(features, VIRTIO_NET_F_RSS); + } else if (virtio_has_feature_ex(features, VIRTIO_NET_F_RSS)) { virtio_net_load_ebpf(n, errp); } - return features; + return; } if (!use_peer_hash) { - virtio_clear_feature(&features, VIRTIO_NET_F_HASH_REPORT); + virtio_clear_feature_ex(features, VIRTIO_NET_F_HASH_REPORT); if (!use_own_hash || !virtio_net_attach_ebpf_to_backend(n->nic, -1)) { if (!virtio_net_load_ebpf(n, errp)) { - return features; + return; } - virtio_clear_feature(&features, VIRTIO_NET_F_RSS); + virtio_clear_feature_ex(features, VIRTIO_NET_F_RSS); } } - features = vhost_net_get_features(get_vhost_net(nc->peer), features); - vdev->backend_features = features; + vhost_net_get_features_ex(get_vhost_net(nc->peer), features); + virtio_features_copy(vdev->backend_features_ex, features); if (n->mtu_bypass_backend && (n->host_features & 1ULL << VIRTIO_NET_F_MTU)) { - features |= (1ULL << VIRTIO_NET_F_MTU); + virtio_add_feature_ex(features, VIRTIO_NET_F_MTU); } /* @@ -3109,10 +3135,8 @@ static uint64_t virtio_net_get_features(VirtIODevice *vdev, uint64_t features, * support it. */ if (!virtio_has_feature(vdev->backend_features, VIRTIO_NET_F_CTRL_VQ)) { - virtio_clear_feature(&features, VIRTIO_NET_F_GUEST_ANNOUNCE); + virtio_clear_feature_ex(features, VIRTIO_NET_F_GUEST_ANNOUNCE); } - - return features; } static int virtio_net_post_load_device(void *opaque, int version_id) @@ -4244,8 +4268,8 @@ static void virtio_net_class_init(ObjectClass *klass, const void *data) vdc->unrealize = virtio_net_device_unrealize; vdc->get_config = virtio_net_get_config; vdc->set_config = virtio_net_set_config; - vdc->get_features = virtio_net_get_features; - vdc->set_features = virtio_net_set_features; + vdc->get_features_ex = virtio_net_get_features; + vdc->set_features_ex = virtio_net_set_features; vdc->bad_features = virtio_net_bad_features; vdc->reset = virtio_net_reset; vdc->queue_reset = virtio_net_queue_reset; diff --git a/include/hw/virtio/virtio-net.h b/include/hw/virtio/virtio-net.h index 73fdefc0dc..5b8ab7bda7 100644 --- a/include/hw/virtio/virtio-net.h +++ b/include/hw/virtio/virtio-net.h @@ -182,7 +182,7 @@ struct VirtIONet { uint32_t has_vnet_hdr; size_t host_hdr_len; size_t guest_hdr_len; - uint64_t host_features; + VIRTIO_DECLARE_FEATURES(host_features); uint32_t rsc_timeout; uint8_t rsc4_enabled; uint8_t rsc6_enabled; -- cgit 1.4.1 From fffac046282c99801b62fa7fa1032cdc261bca6d Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Mon, 22 Sep 2025 16:18:27 +0200 Subject: 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 Acked-by: Jason Wang Signed-off-by: Paolo Abeni Tested-by: Lei Yang Acked-by: Stefano Garzarella Reviewed-by: Michael S. Tsirkin Message-ID: Signed-off-by: Michael S. Tsirkin --- hw/net/virtio-net.c | 41 +++++++++++++++++++++++++++++++++++++++++ include/net/net.h | 3 +++ net/net.c | 9 +++++++++ net/tap-bsd.c | 5 +++++ net/tap-linux.c | 11 +++++++++++ net/tap-linux.h | 9 +++++++++ net/tap-solaris.c | 5 +++++ net/tap-stub.c | 5 +++++ net/tap.c | 11 +++++++++++ net/tap_int.h | 1 + 10 files changed, 100 insertions(+) (limited to 'hw/net/virtio-net.c') diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c index 39f2a8c987..f8e2b4823e 100644 --- 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 48ba333d02..9a9084690d 100644 --- 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 63872b6855..9536184a0c 100644 --- 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 38eb28cb58..bbf84d1828 100644 --- 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 79a9dd0da0..98b0ae9602 100644 --- 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 9a58cecb7f..8cd6b5874b 100644 --- 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 ef8e0feeb0..75397e6c54 100644 --- 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 67d14ad4d5..f7a5e0c163 100644 --- 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 df23283744..5124372316 100644 --- 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 f8bbe1cb0c..b76a05044b 100644 --- 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); -- cgit 1.4.1 From a5289563ad74a2a37e8d2101d82935454c71fef4 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Mon, 22 Sep 2025 16:18:28 +0200 Subject: net: implement UDP tunnel features offloading When any host or guest GSO over UDP tunnel offload is enabled the virtio net header includes the additional tunnel-related fields, update the size accordingly. Push the GSO over UDP tunnel offloads all the way down to the tap device extending the newly introduced NetFeatures struct, and eventually enable the associated features. As per virtio specification, to convert features bit to offload bit, map the extended features into the reserved range. Finally, make the vhost backend aware of the exact header layout, to copy it correctly. The tunnel-related field are present if either the guest or the host negotiated any UDP tunnel related feature: add them to the kernel supported features list, to allow qemu transfer to the backend the needed information. Reviewed-by: Akihiko Odaki Acked-by: Jason Wang Signed-off-by: Paolo Abeni Tested-by: Lei Yang Acked-by: Stefano Garzarella Reviewed-by: Michael S. Tsirkin Message-ID: <093b4bc68368046bffbcab2202227632d6e4e83b.1758549625.git.pabeni@redhat.com> Signed-off-by: Michael S. Tsirkin --- hw/net/virtio-net.c | 34 ++++++++++++++++++++++++++-------- include/net/net.h | 2 ++ net/net.c | 3 ++- net/tap-linux.c | 6 ++++++ net/tap.c | 2 ++ 5 files changed, 38 insertions(+), 9 deletions(-) (limited to 'hw/net/virtio-net.c') diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c index f8e2b4823e..33116712eb 100644 --- a/hw/net/virtio-net.c +++ b/hw/net/virtio-net.c @@ -103,6 +103,12 @@ #define VIRTIO_NET_F2O_SHIFT (VIRTIO_NET_OFFLOAD_MAP_MIN - \ VIRTIO_NET_FEATURES_MAP_MIN + 64) +static bool virtio_has_tunnel_hdr(const uint64_t *features) +{ + return virtio_has_feature_ex(features, VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO) || + virtio_has_feature_ex(features, VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO); +} + static const VirtIOFeature feature_sizes[] = { {.flags = 1ULL << VIRTIO_NET_F_MAC, .end = endof(struct virtio_net_config, mac)}, @@ -659,7 +665,8 @@ static bool peer_has_tunnel(VirtIONet *n) } static void virtio_net_set_mrg_rx_bufs(VirtIONet *n, int mergeable_rx_bufs, - int version_1, int hash_report) + int version_1, int hash_report, + int tunnel) { int i; NetClientState *nc; @@ -667,9 +674,11 @@ static void virtio_net_set_mrg_rx_bufs(VirtIONet *n, int mergeable_rx_bufs, n->mergeable_rx_bufs = mergeable_rx_bufs; if (version_1) { - n->guest_hdr_len = hash_report ? - sizeof(struct virtio_net_hdr_v1_hash) : - sizeof(struct virtio_net_hdr_mrg_rxbuf); + n->guest_hdr_len = tunnel ? + sizeof(struct virtio_net_hdr_v1_hash_tunnel) : + (hash_report ? + sizeof(struct virtio_net_hdr_v1_hash) : + sizeof(struct virtio_net_hdr_mrg_rxbuf)); n->rss_data.populate_hash = !!hash_report; } else { n->guest_hdr_len = n->mergeable_rx_bufs ? @@ -803,6 +812,10 @@ static void virtio_net_apply_guest_offloads(VirtIONet *n) .ufo = !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_UFO)), .uso4 = !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_USO4)), .uso6 = !!(n->curr_guest_offloads & (1ULL << VIRTIO_NET_F_GUEST_USO6)), + .tnl = !!(n->curr_guest_offloads & + (1ULL << VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_MAPPED)), + .tnl_csum = !!(n->curr_guest_offloads & + (1ULL << VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_CSUM_MAPPED)), }; qemu_set_offload(qemu_get_queue(n->nic)->peer, &ol); @@ -824,7 +837,9 @@ virtio_net_guest_offloads_by_features(const uint64_t *features) (1ULL << VIRTIO_NET_F_GUEST_ECN) | (1ULL << VIRTIO_NET_F_GUEST_UFO) | (1ULL << VIRTIO_NET_F_GUEST_USO4) | - (1ULL << VIRTIO_NET_F_GUEST_USO6); + (1ULL << VIRTIO_NET_F_GUEST_USO6) | + (1ULL << VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_MAPPED) | + (1ULL << VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_CSUM_MAPPED); return guest_offloads_mask & virtio_net_features_to_offload(features); } @@ -937,7 +952,8 @@ static void virtio_net_set_features(VirtIODevice *vdev, virtio_has_feature_ex(features, VIRTIO_F_VERSION_1), virtio_has_feature_ex(features, - VIRTIO_NET_F_HASH_REPORT)); + VIRTIO_NET_F_HASH_REPORT), + virtio_has_tunnel_hdr(features)); n->rsc4_enabled = virtio_has_feature_ex(features, VIRTIO_NET_F_RSC_EXT) && virtio_has_feature_ex(features, VIRTIO_NET_F_GUEST_TSO4); @@ -3169,13 +3185,15 @@ static int virtio_net_post_load_device(void *opaque, int version_id) VirtIONet *n = opaque; VirtIODevice *vdev = VIRTIO_DEVICE(n); int i, link_down; + bool has_tunnel_hdr = virtio_has_tunnel_hdr(vdev->guest_features_ex); trace_virtio_net_post_load_device(); virtio_net_set_mrg_rx_bufs(n, n->mergeable_rx_bufs, virtio_vdev_has_feature(vdev, VIRTIO_F_VERSION_1), virtio_vdev_has_feature(vdev, - VIRTIO_NET_F_HASH_REPORT)); + VIRTIO_NET_F_HASH_REPORT), + has_tunnel_hdr); /* MAC_TABLE_ENTRIES may be different from the saved image */ if (n->mac_table.in_use > MAC_TABLE_ENTRIES) { @@ -3995,7 +4013,7 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp) n->vqs[0].tx_waiting = 0; n->tx_burst = n->net_conf.txburst; - virtio_net_set_mrg_rx_bufs(n, 0, 0, 0); + virtio_net_set_mrg_rx_bufs(n, 0, 0, 0, 0); n->promisc = 1; /* for compatibility */ n->mac_table.macs = g_malloc0(MAC_TABLE_ENTRIES * ETH_ALEN); diff --git a/include/net/net.h b/include/net/net.h index 9a9084690d..72b476ee1d 100644 --- a/include/net/net.h +++ b/include/net/net.h @@ -43,6 +43,8 @@ typedef struct NetOffloads { bool ufo; bool uso4; bool uso6; + bool tnl; + bool tnl_csum; } NetOffloads; #define DEFINE_NIC_PROPERTIES(_state, _conf) \ diff --git a/net/net.c b/net/net.c index 9536184a0c..27e0d27807 100644 --- a/net/net.c +++ b/net/net.c @@ -575,7 +575,8 @@ void qemu_set_vnet_hdr_len(NetClientState *nc, int len) assert(len == sizeof(struct virtio_net_hdr_mrg_rxbuf) || len == sizeof(struct virtio_net_hdr) || - len == sizeof(struct virtio_net_hdr_v1_hash)); + len == sizeof(struct virtio_net_hdr_v1_hash) || + len == sizeof(struct virtio_net_hdr_v1_hash_tunnel)); nc->vnet_hdr_len = len; nc->info->set_vnet_hdr_len(nc, len); diff --git a/net/tap-linux.c b/net/tap-linux.c index 98b0ae9602..2a90b58467 100644 --- a/net/tap-linux.c +++ b/net/tap-linux.c @@ -284,6 +284,12 @@ void tap_fd_set_offload(int fd, const NetOffloads *ol) if (ol->uso6) { offload |= TUN_F_USO6; } + if (ol->tnl) { + offload |= TUN_F_UDP_TUNNEL_GSO; + } + if (ol->tnl_csum) { + offload |= TUN_F_UDP_TUNNEL_GSO_CSUM; + } } if (ioctl(fd, TUNSETOFFLOAD, offload) != 0) { diff --git a/net/tap.c b/net/tap.c index 5124372316..abe3b2d036 100644 --- a/net/tap.c +++ b/net/tap.c @@ -62,6 +62,8 @@ static const int kernel_feature_bits[] = { VIRTIO_F_NOTIFICATION_DATA, VIRTIO_NET_F_RSC_EXT, VIRTIO_NET_F_HASH_REPORT, + VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO, + VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO, VHOST_INVALID_FEATURE_BIT }; -- cgit 1.4.1