From: Yuri Benditovich <yuri.benditovich@daynix.com> To: Jason Wang <jasowang@redhat.com> Cc: "David S. Miller" <davem@davemloft.net>, Jakub Kicinski <kuba@kernel.org>, "Michael S . Tsirkin" <mst@redhat.com>, Network Development <netdev@vger.kernel.org>, LKML <linux-kernel@vger.kernel.org>, virtualization@lists.linux-foundation.org, Yan Vugenfirer <yan@daynix.com> Subject: Re: [PATCH 1/4] virtio-net: add definitions for host USO feature Date: Tue, 11 May 2021 11:12:16 +0300 [thread overview] Message-ID: <CAOEp5OdgYtP+W1thGsTGnvEPWrJ02s1HemskQpnMTUyYbsX4jQ@mail.gmail.com> (raw) In-Reply-To: <40938c20-5851-089b-c3c0-074bbd636970@redhat.com> On Tue, May 11, 2021 at 9:47 AM Jason Wang <jasowang@redhat.com> wrote: > > > 在 2021/5/11 下午12:42, Yuri Benditovich 写道: > > Define feature bit and GSO type according to the VIRTIO > > specification. > > > > Signed-off-by: Yuri Benditovich <yuri.benditovich@daynix.com> > > --- > > include/uapi/linux/virtio_net.h | 2 ++ > > 1 file changed, 2 insertions(+) > > > > diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h > > index 3f55a4215f11..a556ac735d7f 100644 > > --- a/include/uapi/linux/virtio_net.h > > +++ b/include/uapi/linux/virtio_net.h > > @@ -57,6 +57,7 @@ > > * Steering */ > > #define VIRTIO_NET_F_CTRL_MAC_ADDR 23 /* Set MAC address */ > > > > +#define VIRTIO_NET_F_HOST_USO 56 /* Host can handle USO packets */ This is the virtio-net feature > > #define VIRTIO_NET_F_HASH_REPORT 57 /* Supports hash report */ > > #define VIRTIO_NET_F_RSS 60 /* Supports RSS RX steering */ > > #define VIRTIO_NET_F_RSC_EXT 61 /* extended coalescing info */ > > @@ -130,6 +131,7 @@ struct virtio_net_hdr_v1 { > > #define VIRTIO_NET_HDR_GSO_TCPV4 1 /* GSO frame, IPv4 TCP (TSO) */ > > #define VIRTIO_NET_HDR_GSO_UDP 3 /* GSO frame, IPv4 UDP (UFO) */ > > #define VIRTIO_NET_HDR_GSO_TCPV6 4 /* GSO frame, IPv6 TCP */ > > +#define VIRTIO_NET_HDR_GSO_UDP_L4 5 /* GSO frame, IPv4 UDP (USO) */ This is respective GSO type > > > This is the gso_type not the feature actually. > > I wonder what's the reason for not > > 1) introducing a dedicated virtio-net feature bit for this > (VIRTIO_NET_F_GUEST_GSO_UDP_L4. This series is not for GUEST's feature, it is only for host feature. > 2) toggle the NETIF_F_GSO_UDP_L4 feature for tuntap based on the > negotiated feature. The NETIF_F_GSO_UDP_L4 would be required for the guest RX path. The guest TX path does not require any flags to be propagated, it only allows the guest to transmit large UDP packets and have them automatically splitted. (This is similar to HOST_UFO but does packet segmentation instead of fragmentation. GUEST_UFO indeed requires a respective NETIF flag, as it is unclear whether the guest is capable of receiving such packets). > > Thanks > > > > #define VIRTIO_NET_HDR_GSO_ECN 0x80 /* TCP has ECN set */ > > __u8 gso_type; > > __virtio16 hdr_len; /* Ethernet + IP + tcp/udp hdrs */ >
WARNING: multiple messages have this Message-ID (diff)
From: Yuri Benditovich <yuri.benditovich@daynix.com> To: Jason Wang <jasowang@redhat.com> Cc: "Michael S . Tsirkin" <mst@redhat.com>, Network Development <netdev@vger.kernel.org>, LKML <linux-kernel@vger.kernel.org>, virtualization@lists.linux-foundation.org, Yan Vugenfirer <yan@daynix.com>, Jakub Kicinski <kuba@kernel.org>, "David S. Miller" <davem@davemloft.net> Subject: Re: [PATCH 1/4] virtio-net: add definitions for host USO feature Date: Tue, 11 May 2021 11:12:16 +0300 [thread overview] Message-ID: <CAOEp5OdgYtP+W1thGsTGnvEPWrJ02s1HemskQpnMTUyYbsX4jQ@mail.gmail.com> (raw) In-Reply-To: <40938c20-5851-089b-c3c0-074bbd636970@redhat.com> On Tue, May 11, 2021 at 9:47 AM Jason Wang <jasowang@redhat.com> wrote: > > > 在 2021/5/11 下午12:42, Yuri Benditovich 写道: > > Define feature bit and GSO type according to the VIRTIO > > specification. > > > > Signed-off-by: Yuri Benditovich <yuri.benditovich@daynix.com> > > --- > > include/uapi/linux/virtio_net.h | 2 ++ > > 1 file changed, 2 insertions(+) > > > > diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h > > index 3f55a4215f11..a556ac735d7f 100644 > > --- a/include/uapi/linux/virtio_net.h > > +++ b/include/uapi/linux/virtio_net.h > > @@ -57,6 +57,7 @@ > > * Steering */ > > #define VIRTIO_NET_F_CTRL_MAC_ADDR 23 /* Set MAC address */ > > > > +#define VIRTIO_NET_F_HOST_USO 56 /* Host can handle USO packets */ This is the virtio-net feature > > #define VIRTIO_NET_F_HASH_REPORT 57 /* Supports hash report */ > > #define VIRTIO_NET_F_RSS 60 /* Supports RSS RX steering */ > > #define VIRTIO_NET_F_RSC_EXT 61 /* extended coalescing info */ > > @@ -130,6 +131,7 @@ struct virtio_net_hdr_v1 { > > #define VIRTIO_NET_HDR_GSO_TCPV4 1 /* GSO frame, IPv4 TCP (TSO) */ > > #define VIRTIO_NET_HDR_GSO_UDP 3 /* GSO frame, IPv4 UDP (UFO) */ > > #define VIRTIO_NET_HDR_GSO_TCPV6 4 /* GSO frame, IPv6 TCP */ > > +#define VIRTIO_NET_HDR_GSO_UDP_L4 5 /* GSO frame, IPv4 UDP (USO) */ This is respective GSO type > > > This is the gso_type not the feature actually. > > I wonder what's the reason for not > > 1) introducing a dedicated virtio-net feature bit for this > (VIRTIO_NET_F_GUEST_GSO_UDP_L4. This series is not for GUEST's feature, it is only for host feature. > 2) toggle the NETIF_F_GSO_UDP_L4 feature for tuntap based on the > negotiated feature. The NETIF_F_GSO_UDP_L4 would be required for the guest RX path. The guest TX path does not require any flags to be propagated, it only allows the guest to transmit large UDP packets and have them automatically splitted. (This is similar to HOST_UFO but does packet segmentation instead of fragmentation. GUEST_UFO indeed requires a respective NETIF flag, as it is unclear whether the guest is capable of receiving such packets). > > Thanks > > > > #define VIRTIO_NET_HDR_GSO_ECN 0x80 /* TCP has ECN set */ > > __u8 gso_type; > > __virtio16 hdr_len; /* Ethernet + IP + tcp/udp hdrs */ > _______________________________________________ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
next prev parent reply other threads:[~2021-05-11 8:12 UTC|newest] Thread overview: 62+ messages / expand[flat|nested] mbox.gz Atom feed top 2021-05-11 4:42 [PATCH 0/4] Add host USO support to TUN device Yuri Benditovich 2021-05-11 4:42 ` Yuri Benditovich 2021-05-11 4:42 ` [PATCH 1/4] virtio-net: add definitions for host USO feature Yuri Benditovich 2021-05-11 4:42 ` Yuri Benditovich 2021-05-11 6:47 ` Jason Wang 2021-05-11 6:47 ` Jason Wang 2021-05-11 8:12 ` Yuri Benditovich [this message] 2021-05-11 8:12 ` Yuri Benditovich 2021-05-11 8:24 ` Jason Wang 2021-05-11 8:24 ` Jason Wang 2021-05-11 9:21 ` Yuri Benditovich 2021-05-11 9:21 ` Yuri Benditovich 2021-05-12 1:21 ` Jason Wang 2021-05-12 1:21 ` Jason Wang 2021-05-11 4:42 ` [PATCH 2/4] virtio-net: add support of UDP segmentation (USO) on the host Yuri Benditovich 2021-05-11 4:42 ` Yuri Benditovich 2021-05-11 6:47 ` Jason Wang 2021-05-11 6:47 ` Jason Wang 2021-05-11 8:23 ` Yuri Benditovich 2021-05-11 8:23 ` Yuri Benditovich 2021-05-11 8:31 ` Jason Wang 2021-05-11 8:31 ` Jason Wang 2021-05-11 17:47 ` Willem de Bruijn 2021-05-11 17:47 ` Willem de Bruijn 2021-05-12 6:09 ` Yuri Benditovich 2021-05-12 6:09 ` Yuri Benditovich 2021-05-12 14:32 ` Willem de Bruijn 2021-05-12 14:32 ` Willem de Bruijn 2021-05-12 18:56 ` Yuri Benditovich 2021-05-12 18:56 ` Yuri Benditovich 2021-05-12 19:53 ` Willem de Bruijn 2021-05-12 19:53 ` Willem de Bruijn 2021-05-11 4:42 ` [PATCH 3/4] tun: define feature bit for USO support Yuri Benditovich 2021-05-11 4:42 ` Yuri Benditovich 2021-05-11 4:42 ` [PATCH 4/4] tun: indicate support for USO feature Yuri Benditovich 2021-05-11 4:42 ` Yuri Benditovich 2021-05-11 6:50 ` Jason Wang 2021-05-11 6:50 ` Jason Wang 2021-05-11 8:33 ` Yuri Benditovich 2021-05-11 8:33 ` Yuri Benditovich 2021-05-11 19:06 ` Yuri Benditovich 2021-05-11 19:06 ` Yuri Benditovich 2021-05-12 1:33 ` Jason Wang 2021-05-12 1:33 ` Jason Wang 2021-05-12 5:24 ` Yuri Benditovich 2021-05-12 5:24 ` Yuri Benditovich [not found] ` <CACGkMEsZBCzV+d_eLj1aYT+pkS5m1QAy7q8rUkNsdV0C8aL8tQ@mail.gmail.com> [not found] ` <CAOEp5OeSankfA6urXLW_fquSMrZ+WYXDtKNacort1UwR=WgxqA@mail.gmail.com> [not found] ` <CACGkMEt3bZrdqbWtWjSkXvv5v8iCHiN8hkD3T602RZnb6nPd9A@mail.gmail.com> [not found] ` <CAOEp5Odw=eaQWZCXr+U8PipPtO1Avjw-t3gEdKyvNYxuNa5TfQ@mail.gmail.com> [not found] ` <CACGkMEuqXaJxGqC+CLoq7k4XDu+W3E3Kk3WvG-D6tnn2K4ZPNA@mail.gmail.com> [not found] ` <CAOEp5OfB62SQzxMj_GkVD4EM=Z+xf43TPoTZwMbPPa3BsX2ooA@mail.gmail.com> 2021-05-13 7:04 ` Jason Wang 2021-05-13 7:04 ` Jason Wang 2021-05-13 8:14 ` Yuri Benditovich 2021-05-13 8:14 ` Yuri Benditovich 2021-05-13 20:43 ` Willem de Bruijn 2021-05-13 20:43 ` Willem de Bruijn 2021-05-14 5:48 ` Yuri Benditovich 2021-05-14 5:48 ` Yuri Benditovich 2021-05-13 20:34 ` Willem de Bruijn 2021-05-13 20:34 ` Willem de Bruijn 2021-05-14 7:16 ` Jason Wang 2021-05-14 7:16 ` Jason Wang 2021-05-14 7:38 ` Yuri Benditovich 2021-05-14 7:38 ` Yuri Benditovich 2021-05-14 12:41 ` Willem de Bruijn 2021-05-14 12:41 ` Willem de Bruijn
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=CAOEp5OdgYtP+W1thGsTGnvEPWrJ02s1HemskQpnMTUyYbsX4jQ@mail.gmail.com \ --to=yuri.benditovich@daynix.com \ --cc=davem@davemloft.net \ --cc=jasowang@redhat.com \ --cc=kuba@kernel.org \ --cc=linux-kernel@vger.kernel.org \ --cc=mst@redhat.com \ --cc=netdev@vger.kernel.org \ --cc=virtualization@lists.linux-foundation.org \ --cc=yan@daynix.com \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.