* Re: [dpdk-dev] [PATCH] vhost: support UDP Fragmentation Offload
2017-11-21 6:56 [dpdk-dev] [PATCH] vhost: support UDP Fragmentation Offload Jiayu Hu
@ 2017-11-21 7:12 ` Stephen Hemminger
2017-11-21 7:41 ` Hu, Jiayu
2017-12-05 14:57 ` Maxime Coquelin
` (4 subsequent siblings)
5 siblings, 1 reply; 12+ messages in thread
From: Stephen Hemminger @ 2017-11-21 7:12 UTC (permalink / raw)
To: Jiayu Hu; +Cc: dev, yliu, jianfeng.tan
On Tue, 21 Nov 2017 14:56:52 +0800
Jiayu Hu <jiayu.hu@intel.com> wrote:
> In virtio, UDP Fragmentation Offload (UFO) includes two parts: host UFO
> and guest UFO. Guest UFO means the frontend can receive large UDP packets,
> and host UFO means the backend can receive large UDP packets. This patch
> supports host UFO and guest UFO for vhost-user.
>
> Signed-off-by: Jiayu Hu <jiayu.hu@intel.com>
This may no longer be a desirable feature to implement.
UFO was just deprecated and removed from Linux.
It had no useful benefit.
^ permalink raw reply [flat|nested] 12+ messages in thread* Re: [dpdk-dev] [PATCH] vhost: support UDP Fragmentation Offload
2017-11-21 7:12 ` Stephen Hemminger
@ 2017-11-21 7:41 ` Hu, Jiayu
2017-11-21 14:33 ` Neil Horman
0 siblings, 1 reply; 12+ messages in thread
From: Hu, Jiayu @ 2017-11-21 7:41 UTC (permalink / raw)
To: Stephen Hemminger; +Cc: dev, yliu, Tan, Jianfeng
Hi Stephen,
> -----Original Message-----
> From: Stephen Hemminger [mailto:stephen@networkplumber.org]
> Sent: Tuesday, November 21, 2017 3:13 PM
> To: Hu, Jiayu <jiayu.hu@intel.com>
> Cc: dev@dpdk.org; yliu@fridaylinux.org; Tan, Jianfeng
> <jianfeng.tan@intel.com>
> Subject: Re: [dpdk-dev] [PATCH] vhost: support UDP Fragmentation Offload
>
> On Tue, 21 Nov 2017 14:56:52 +0800
> Jiayu Hu <jiayu.hu@intel.com> wrote:
>
> > In virtio, UDP Fragmentation Offload (UFO) includes two parts: host UFO
> > and guest UFO. Guest UFO means the frontend can receive large UDP
> packets,
> > and host UFO means the backend can receive large UDP packets. This patch
> > supports host UFO and guest UFO for vhost-user.
> >
> > Signed-off-by: Jiayu Hu <jiayu.hu@intel.com>
>
> This may no longer be a desirable feature to implement.
> UFO was just deprecated and removed from Linux.
> It had no useful benefit.
The main reason of supporting UFO is to make the backend live migration from
vhost-net to vhost-user possible. Host and guest UFO are default features for virtio-net,
and vhost-net supports both. But vhosy-user doesn't support them. If we want to
migrate from vhost-net to vhost-user, this features gap would cause live migration fail.
Thanks,
Jiayu
^ permalink raw reply [flat|nested] 12+ messages in thread
* Re: [dpdk-dev] [PATCH] vhost: support UDP Fragmentation Offload
2017-11-21 7:41 ` Hu, Jiayu
@ 2017-11-21 14:33 ` Neil Horman
0 siblings, 0 replies; 12+ messages in thread
From: Neil Horman @ 2017-11-21 14:33 UTC (permalink / raw)
To: Hu, Jiayu; +Cc: Stephen Hemminger, dev, yliu, Tan, Jianfeng
On Tue, Nov 21, 2017 at 07:41:00AM +0000, Hu, Jiayu wrote:
> Hi Stephen,
>
> > -----Original Message-----
> > From: Stephen Hemminger [mailto:stephen@networkplumber.org]
> > Sent: Tuesday, November 21, 2017 3:13 PM
> > To: Hu, Jiayu <jiayu.hu@intel.com>
> > Cc: dev@dpdk.org; yliu@fridaylinux.org; Tan, Jianfeng
> > <jianfeng.tan@intel.com>
> > Subject: Re: [dpdk-dev] [PATCH] vhost: support UDP Fragmentation Offload
> >
> > On Tue, 21 Nov 2017 14:56:52 +0800
> > Jiayu Hu <jiayu.hu@intel.com> wrote:
> >
> > > In virtio, UDP Fragmentation Offload (UFO) includes two parts: host UFO
> > > and guest UFO. Guest UFO means the frontend can receive large UDP
> > packets,
> > > and host UFO means the backend can receive large UDP packets. This patch
> > > supports host UFO and guest UFO for vhost-user.
> > >
> > > Signed-off-by: Jiayu Hu <jiayu.hu@intel.com>
> >
> > This may no longer be a desirable feature to implement.
> > UFO was just deprecated and removed from Linux.
> > It had no useful benefit.
>
> The main reason of supporting UFO is to make the backend live migration from
> vhost-net to vhost-user possible. Host and guest UFO are default features for virtio-net,
> and vhost-net supports both. But vhosy-user doesn't support them. If we want to
> migrate from vhost-net to vhost-user, this features gap would cause live migration fail.
>
> Thanks,
> Jiayu
>
Its not a widely used feature, but if it helps migrage people, its not a hard
feature to support
Acked-by: Neil Horman <nhorman@tuxdriver.com>
^ permalink raw reply [flat|nested] 12+ messages in thread
* Re: [dpdk-dev] [PATCH] vhost: support UDP Fragmentation Offload
2017-11-21 6:56 [dpdk-dev] [PATCH] vhost: support UDP Fragmentation Offload Jiayu Hu
2017-11-21 7:12 ` Stephen Hemminger
@ 2017-12-05 14:57 ` Maxime Coquelin
2017-12-06 8:36 ` Maxime Coquelin
` (3 subsequent siblings)
5 siblings, 0 replies; 12+ messages in thread
From: Maxime Coquelin @ 2017-12-05 14:57 UTC (permalink / raw)
To: Jiayu Hu, dev; +Cc: yliu, jianfeng.tan
On 11/21/2017 07:56 AM, Jiayu Hu wrote:
> In virtio, UDP Fragmentation Offload (UFO) includes two parts: host UFO
> and guest UFO. Guest UFO means the frontend can receive large UDP packets,
> and host UFO means the backend can receive large UDP packets. This patch
> supports host UFO and guest UFO for vhost-user.
>
> Signed-off-by: Jiayu Hu<jiayu.hu@intel.com>
> ---
> lib/librte_mbuf/rte_mbuf.h | 7 +++++++
> lib/librte_vhost/vhost.h | 2 ++
> lib/librte_vhost/virtio_net.c | 10 ++++++++++
> 3 files changed, 19 insertions(+)
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Thanks,
Maxime
^ permalink raw reply [flat|nested] 12+ messages in thread* Re: [dpdk-dev] [PATCH] vhost: support UDP Fragmentation Offload
2017-11-21 6:56 [dpdk-dev] [PATCH] vhost: support UDP Fragmentation Offload Jiayu Hu
2017-11-21 7:12 ` Stephen Hemminger
2017-12-05 14:57 ` Maxime Coquelin
@ 2017-12-06 8:36 ` Maxime Coquelin
2017-12-07 13:14 ` Hu, Jiayu
2017-12-25 1:48 ` Yao, Lei A
` (2 subsequent siblings)
5 siblings, 1 reply; 12+ messages in thread
From: Maxime Coquelin @ 2017-12-06 8:36 UTC (permalink / raw)
To: Jiayu Hu, dev; +Cc: yliu, jianfeng.tan
On 11/21/2017 07:56 AM, Jiayu Hu wrote:
> In virtio, UDP Fragmentation Offload (UFO) includes two parts: host UFO
> and guest UFO. Guest UFO means the frontend can receive large UDP packets,
> and host UFO means the backend can receive large UDP packets. This patch
> supports host UFO and guest UFO for vhost-user.
>
> Signed-off-by: Jiayu Hu <jiayu.hu@intel.com>
> ---
> lib/librte_mbuf/rte_mbuf.h | 7 +++++++
> lib/librte_vhost/vhost.h | 2 ++
> lib/librte_vhost/virtio_net.c | 10 ++++++++++
> 3 files changed, 19 insertions(+)
>
> diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h
> index ce8a05d..3d8cfc9 100644
> --- a/lib/librte_mbuf/rte_mbuf.h
> +++ b/lib/librte_mbuf/rte_mbuf.h
> @@ -209,6 +209,13 @@ extern "C" {
> /* add new TX flags here */
>
> /**
> + * UDP Fragmentation Offload flag. This flag is used for enabling UDP
> + * fragmentation in SW or in HW. When use UFO, mbuf->tso_segsz is used
> + * to store the MSS of UDP fragments.
> + */
> +#define PKT_TX_UDP_SEG (1ULL << 42)
> +
> +/**
> * Request security offload processing on the TX packet.
> */
> #define PKT_TX_SEC_OFFLOAD (1ULL << 43)
> diff --git a/lib/librte_vhost/vhost.h b/lib/librte_vhost/vhost.h
> index 1cc81c1..fc109ef 100644
> --- a/lib/librte_vhost/vhost.h
> +++ b/lib/librte_vhost/vhost.h
> @@ -206,10 +206,12 @@ struct vhost_msg {
> (1ULL << VHOST_USER_F_PROTOCOL_FEATURES) | \
> (1ULL << VIRTIO_NET_F_HOST_TSO4) | \
> (1ULL << VIRTIO_NET_F_HOST_TSO6) | \
> + (1ULL << VIRTIO_NET_F_HOST_UFO) | \
> (1ULL << VIRTIO_NET_F_CSUM) | \
> (1ULL << VIRTIO_NET_F_GUEST_CSUM) | \
> (1ULL << VIRTIO_NET_F_GUEST_TSO4) | \
> (1ULL << VIRTIO_NET_F_GUEST_TSO6) | \
> + (1ULL << VIRTIO_NET_F_GUEST_UFO) | \
I actually have the same question as for GSO.
Dos it impact performance as it seems enabled by default in QEMU?
How do you test it?
Thanks,
Maxime
> (1ULL << VIRTIO_RING_F_INDIRECT_DESC) | \
> (1ULL << VIRTIO_NET_F_MTU) | \
> (1ULL << VIRTIO_F_IOMMU_PLATFORM))
> diff --git a/lib/librte_vhost/virtio_net.c b/lib/librte_vhost/virtio_net.c
> index 6fee16e..3a3a0ad 100644
> --- a/lib/librte_vhost/virtio_net.c
> +++ b/lib/librte_vhost/virtio_net.c
> @@ -188,6 +188,11 @@ virtio_enqueue_offload(struct rte_mbuf *m_buf, struct virtio_net_hdr *net_hdr)
> net_hdr->gso_size = m_buf->tso_segsz;
> net_hdr->hdr_len = m_buf->l2_len + m_buf->l3_len
> + m_buf->l4_len;
> + } else if (m_buf->ol_flags & PKT_TX_UDP_SEG) {
> + net_hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP;
> + net_hdr->gso_size = m_buf->tso_segsz;
> + net_hdr->hdr_len = m_buf->l2_len + m_buf->l3_len +
> + m_buf->l4_len;
> } else {
> ASSIGN_UNLESS_EQUAL(net_hdr->gso_type, 0);
> ASSIGN_UNLESS_EQUAL(net_hdr->gso_size, 0);
> @@ -834,6 +839,11 @@ vhost_dequeue_offload(struct virtio_net_hdr *hdr, struct rte_mbuf *m)
> m->tso_segsz = hdr->gso_size;
> m->l4_len = (tcp_hdr->data_off & 0xf0) >> 2;
> break;
> + case VIRTIO_NET_HDR_GSO_UDP:
> + m->ol_flags |= PKT_TX_UDP_SEG;
> + m->tso_segsz = hdr->gso_size;
> + m->l4_len = sizeof(struct udp_hdr);
> + break;
> default:
> RTE_LOG(WARNING, VHOST_DATA,
> "unsupported gso type %u.\n", hdr->gso_type);
>
^ permalink raw reply [flat|nested] 12+ messages in thread* Re: [dpdk-dev] [PATCH] vhost: support UDP Fragmentation Offload
2017-12-06 8:36 ` Maxime Coquelin
@ 2017-12-07 13:14 ` Hu, Jiayu
0 siblings, 0 replies; 12+ messages in thread
From: Hu, Jiayu @ 2017-12-07 13:14 UTC (permalink / raw)
To: Maxime Coquelin, dev; +Cc: yliu, Tan, Jianfeng
Hi Maxime,
> -----Original Message-----
> From: Maxime Coquelin [mailto:maxime.coquelin@redhat.com]
> Sent: Wednesday, December 6, 2017 4:37 PM
> To: Hu, Jiayu <jiayu.hu@intel.com>; dev@dpdk.org
> Cc: yliu@fridaylinux.org; Tan, Jianfeng <jianfeng.tan@intel.com>
> Subject: Re: [dpdk-dev] [PATCH] vhost: support UDP Fragmentation Offload
>
>
>
> On 11/21/2017 07:56 AM, Jiayu Hu wrote:
> > In virtio, UDP Fragmentation Offload (UFO) includes two parts: host UFO
> > and guest UFO. Guest UFO means the frontend can receive large UDP
> packets,
> > and host UFO means the backend can receive large UDP packets. This patch
> > supports host UFO and guest UFO for vhost-user.
> >
> > Signed-off-by: Jiayu Hu <jiayu.hu@intel.com>
> > ---
> > lib/librte_mbuf/rte_mbuf.h | 7 +++++++
> > lib/librte_vhost/vhost.h | 2 ++
> > lib/librte_vhost/virtio_net.c | 10 ++++++++++
> > 3 files changed, 19 insertions(+)
> >
> > diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h
> > index ce8a05d..3d8cfc9 100644
> > --- a/lib/librte_mbuf/rte_mbuf.h
> > +++ b/lib/librte_mbuf/rte_mbuf.h
> > @@ -209,6 +209,13 @@ extern "C" {
> > /* add new TX flags here */
> >
> > /**
> > + * UDP Fragmentation Offload flag. This flag is used for enabling UDP
> > + * fragmentation in SW or in HW. When use UFO, mbuf->tso_segsz is used
> > + * to store the MSS of UDP fragments.
> > + */
> > +#define PKT_TX_UDP_SEG (1ULL << 42)
> > +
> > +/**
> > * Request security offload processing on the TX packet.
> > */
> > #define PKT_TX_SEC_OFFLOAD (1ULL << 43)
> > diff --git a/lib/librte_vhost/vhost.h b/lib/librte_vhost/vhost.h
> > index 1cc81c1..fc109ef 100644
> > --- a/lib/librte_vhost/vhost.h
> > +++ b/lib/librte_vhost/vhost.h
> > @@ -206,10 +206,12 @@ struct vhost_msg {
> > (1ULL <<
> VHOST_USER_F_PROTOCOL_FEATURES) | \
> > (1ULL << VIRTIO_NET_F_HOST_TSO4) | \
> > (1ULL << VIRTIO_NET_F_HOST_TSO6) | \
> > + (1ULL << VIRTIO_NET_F_HOST_UFO) | \
> > (1ULL << VIRTIO_NET_F_CSUM) | \
> > (1ULL << VIRTIO_NET_F_GUEST_CSUM) | \
> > (1ULL << VIRTIO_NET_F_GUEST_TSO4) | \
> > (1ULL << VIRTIO_NET_F_GUEST_TSO6) | \
> > + (1ULL << VIRTIO_NET_F_GUEST_UFO) | \
>
> I actually have the same question as for GSO.
> Dos it impact performance as it seems enabled by default in QEMU?
When enable host/guest UFO, the frontend and the backend can communicate
via large UDP packets, thus reducing the number of packets to be processed.
It's similar with TSO for virtio. Therefore, I think host/guest UFO can bring
performance gains.
> How do you test it?
We launch testpmd with two vhost-user ports, which connect to two VMs in one
server. When launch qemu, we enable host and guest UFO with command "host_ufo=on,
guest_ufo=on,csum=on". Then we run iperf in the two VMs to send large UDP packets.
If you use "show port xstats all" in testpmd, you can see the vhost-user port can receive
large UDP packets, which means host_ufo works. Additionally, if the forwarded large UDP
packets can be received by the VM, it means guest_ufo also works.
Thanks,
Jiayu
>
> Thanks,
> Maxime
>
> > (1ULL << VIRTIO_RING_F_INDIRECT_DESC)
> | \
> > (1ULL << VIRTIO_NET_F_MTU) | \
> > (1ULL << VIRTIO_F_IOMMU_PLATFORM))
> > diff --git a/lib/librte_vhost/virtio_net.c b/lib/librte_vhost/virtio_net.c
> > index 6fee16e..3a3a0ad 100644
> > --- a/lib/librte_vhost/virtio_net.c
> > +++ b/lib/librte_vhost/virtio_net.c
> > @@ -188,6 +188,11 @@ virtio_enqueue_offload(struct rte_mbuf *m_buf,
> struct virtio_net_hdr *net_hdr)
> > net_hdr->gso_size = m_buf->tso_segsz;
> > net_hdr->hdr_len = m_buf->l2_len + m_buf->l3_len
> > + m_buf->l4_len;
> > + } else if (m_buf->ol_flags & PKT_TX_UDP_SEG) {
> > + net_hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP;
> > + net_hdr->gso_size = m_buf->tso_segsz;
> > + net_hdr->hdr_len = m_buf->l2_len + m_buf->l3_len +
> > + m_buf->l4_len;
> > } else {
> > ASSIGN_UNLESS_EQUAL(net_hdr->gso_type, 0);
> > ASSIGN_UNLESS_EQUAL(net_hdr->gso_size, 0);
> > @@ -834,6 +839,11 @@ vhost_dequeue_offload(struct virtio_net_hdr
> *hdr, struct rte_mbuf *m)
> > m->tso_segsz = hdr->gso_size;
> > m->l4_len = (tcp_hdr->data_off & 0xf0) >> 2;
> > break;
> > + case VIRTIO_NET_HDR_GSO_UDP:
> > + m->ol_flags |= PKT_TX_UDP_SEG;
> > + m->tso_segsz = hdr->gso_size;
> > + m->l4_len = sizeof(struct udp_hdr);
> > + break;
> > default:
> > RTE_LOG(WARNING, VHOST_DATA,
> > "unsupported gso type %u.\n", hdr-
> >gso_type);
> >
^ permalink raw reply [flat|nested] 12+ messages in thread
* Re: [dpdk-dev] [PATCH] vhost: support UDP Fragmentation Offload
2017-11-21 6:56 [dpdk-dev] [PATCH] vhost: support UDP Fragmentation Offload Jiayu Hu
` (2 preceding siblings ...)
2017-12-06 8:36 ` Maxime Coquelin
@ 2017-12-25 1:48 ` Yao, Lei A
2017-12-27 14:34 ` Yuanhan Liu
2018-01-08 14:27 ` Yuanhan Liu
5 siblings, 0 replies; 12+ messages in thread
From: Yao, Lei A @ 2017-12-25 1:48 UTC (permalink / raw)
To: Hu, Jiayu, dev; +Cc: yliu, Tan, Jianfeng, Hu, Jiayu
> -----Original Message-----
> From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Jiayu Hu
> Sent: Tuesday, November 21, 2017 2:57 PM
> To: dev@dpdk.org
> Cc: yliu@fridaylinux.org; Tan, Jianfeng <jianfeng.tan@intel.com>; Hu, Jiayu
> <jiayu.hu@intel.com>
> Subject: [dpdk-dev] [PATCH] vhost: support UDP Fragmentation Offload
>
> In virtio, UDP Fragmentation Offload (UFO) includes two parts: host UFO
> and guest UFO. Guest UFO means the frontend can receive large UDP
> packets,
> and host UFO means the backend can receive large UDP packets. This patch
> supports host UFO and guest UFO for vhost-user.
>
> Signed-off-by: Jiayu Hu <jiayu.hu@intel.com>
Tested-by: Lei Yao<lei.a.yao@intel.com>
This patch has been tested on my server, with guest_ufo=on,host_ufo=on are
added to the qemu cmdlind, using vhost-user as backend, vm can send and receive
big UDP packets.
> ---
> lib/librte_mbuf/rte_mbuf.h | 7 +++++++
> lib/librte_vhost/vhost.h | 2 ++
> lib/librte_vhost/virtio_net.c | 10 ++++++++++
> 3 files changed, 19 insertions(+)
>
> diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h
> index ce8a05d..3d8cfc9 100644
> --- a/lib/librte_mbuf/rte_mbuf.h
> +++ b/lib/librte_mbuf/rte_mbuf.h
> @@ -209,6 +209,13 @@ extern "C" {
> /* add new TX flags here */
>
> /**
> + * UDP Fragmentation Offload flag. This flag is used for enabling UDP
> + * fragmentation in SW or in HW. When use UFO, mbuf->tso_segsz is used
> + * to store the MSS of UDP fragments.
> + */
> +#define PKT_TX_UDP_SEG (1ULL << 42)
> +
> +/**
> * Request security offload processing on the TX packet.
> */
> #define PKT_TX_SEC_OFFLOAD (1ULL << 43)
> diff --git a/lib/librte_vhost/vhost.h b/lib/librte_vhost/vhost.h
> index 1cc81c1..fc109ef 100644
> --- a/lib/librte_vhost/vhost.h
> +++ b/lib/librte_vhost/vhost.h
> @@ -206,10 +206,12 @@ struct vhost_msg {
> (1ULL <<
> VHOST_USER_F_PROTOCOL_FEATURES) | \
> (1ULL << VIRTIO_NET_F_HOST_TSO4) | \
> (1ULL << VIRTIO_NET_F_HOST_TSO6) | \
> + (1ULL << VIRTIO_NET_F_HOST_UFO) | \
> (1ULL << VIRTIO_NET_F_CSUM) | \
> (1ULL << VIRTIO_NET_F_GUEST_CSUM) | \
> (1ULL << VIRTIO_NET_F_GUEST_TSO4) | \
> (1ULL << VIRTIO_NET_F_GUEST_TSO6) | \
> + (1ULL << VIRTIO_NET_F_GUEST_UFO) | \
> (1ULL << VIRTIO_RING_F_INDIRECT_DESC) |
> \
> (1ULL << VIRTIO_NET_F_MTU) | \
> (1ULL << VIRTIO_F_IOMMU_PLATFORM))
> diff --git a/lib/librte_vhost/virtio_net.c b/lib/librte_vhost/virtio_net.c
> index 6fee16e..3a3a0ad 100644
> --- a/lib/librte_vhost/virtio_net.c
> +++ b/lib/librte_vhost/virtio_net.c
> @@ -188,6 +188,11 @@ virtio_enqueue_offload(struct rte_mbuf *m_buf,
> struct virtio_net_hdr *net_hdr)
> net_hdr->gso_size = m_buf->tso_segsz;
> net_hdr->hdr_len = m_buf->l2_len + m_buf->l3_len
> + m_buf->l4_len;
> + } else if (m_buf->ol_flags & PKT_TX_UDP_SEG) {
> + net_hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP;
> + net_hdr->gso_size = m_buf->tso_segsz;
> + net_hdr->hdr_len = m_buf->l2_len + m_buf->l3_len +
> + m_buf->l4_len;
> } else {
> ASSIGN_UNLESS_EQUAL(net_hdr->gso_type, 0);
> ASSIGN_UNLESS_EQUAL(net_hdr->gso_size, 0);
> @@ -834,6 +839,11 @@ vhost_dequeue_offload(struct virtio_net_hdr *hdr,
> struct rte_mbuf *m)
> m->tso_segsz = hdr->gso_size;
> m->l4_len = (tcp_hdr->data_off & 0xf0) >> 2;
> break;
> + case VIRTIO_NET_HDR_GSO_UDP:
> + m->ol_flags |= PKT_TX_UDP_SEG;
> + m->tso_segsz = hdr->gso_size;
> + m->l4_len = sizeof(struct udp_hdr);
> + break;
> default:
> RTE_LOG(WARNING, VHOST_DATA,
> "unsupported gso type %u.\n", hdr-
> >gso_type);
> --
> 2.7.4
^ permalink raw reply [flat|nested] 12+ messages in thread* Re: [dpdk-dev] [PATCH] vhost: support UDP Fragmentation Offload
2017-11-21 6:56 [dpdk-dev] [PATCH] vhost: support UDP Fragmentation Offload Jiayu Hu
` (3 preceding siblings ...)
2017-12-25 1:48 ` Yao, Lei A
@ 2017-12-27 14:34 ` Yuanhan Liu
2018-01-08 14:27 ` Yuanhan Liu
5 siblings, 0 replies; 12+ messages in thread
From: Yuanhan Liu @ 2017-12-27 14:34 UTC (permalink / raw)
To: Jiayu Hu, Olivier MATZ; +Cc: dev, jianfeng.tan
On Tue, Nov 21, 2017 at 02:56:52PM +0800, Jiayu Hu wrote:
> In virtio, UDP Fragmentation Offload (UFO) includes two parts: host UFO
> and guest UFO. Guest UFO means the frontend can receive large UDP packets,
> and host UFO means the backend can receive large UDP packets. This patch
> supports host UFO and guest UFO for vhost-user.
>
> Signed-off-by: Jiayu Hu <jiayu.hu@intel.com>
> ---
> lib/librte_mbuf/rte_mbuf.h | 7 +++++++
> lib/librte_vhost/vhost.h | 2 ++
> lib/librte_vhost/virtio_net.c | 10 ++++++++++
> 3 files changed, 19 insertions(+)
>
> diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h
> index ce8a05d..3d8cfc9 100644
> --- a/lib/librte_mbuf/rte_mbuf.h
> +++ b/lib/librte_mbuf/rte_mbuf.h
> @@ -209,6 +209,13 @@ extern "C" {
> /* add new TX flags here */
>
> /**
> + * UDP Fragmentation Offload flag. This flag is used for enabling UDP
> + * fragmentation in SW or in HW. When use UFO, mbuf->tso_segsz is used
> + * to store the MSS of UDP fragments.
> + */
> +#define PKT_TX_UDP_SEG (1ULL << 42)
This patch added a new mbuf flag, Olivier, do you have objections?
--yliu
^ permalink raw reply [flat|nested] 12+ messages in thread* Re: [dpdk-dev] [PATCH] vhost: support UDP Fragmentation Offload
2017-11-21 6:56 [dpdk-dev] [PATCH] vhost: support UDP Fragmentation Offload Jiayu Hu
` (4 preceding siblings ...)
2017-12-27 14:34 ` Yuanhan Liu
@ 2018-01-08 14:27 ` Yuanhan Liu
2018-01-16 11:20 ` Thomas Monjalon
5 siblings, 1 reply; 12+ messages in thread
From: Yuanhan Liu @ 2018-01-08 14:27 UTC (permalink / raw)
To: Jiayu Hu; +Cc: dev, jianfeng.tan
On Tue, Nov 21, 2017 at 02:56:52PM +0800, Jiayu Hu wrote:
> In virtio, UDP Fragmentation Offload (UFO) includes two parts: host UFO
> and guest UFO. Guest UFO means the frontend can receive large UDP packets,
> and host UFO means the backend can receive large UDP packets. This patch
> supports host UFO and guest UFO for vhost-user.
>
> Signed-off-by: Jiayu Hu <jiayu.hu@intel.com>
Applied to dpdk-next-virtio.
Thanks.
--yliu
^ permalink raw reply [flat|nested] 12+ messages in thread* Re: [dpdk-dev] [PATCH] vhost: support UDP Fragmentation Offload
2018-01-08 14:27 ` Yuanhan Liu
@ 2018-01-16 11:20 ` Thomas Monjalon
2018-01-16 12:21 ` Olivier Matz
0 siblings, 1 reply; 12+ messages in thread
From: Thomas Monjalon @ 2018-01-16 11:20 UTC (permalink / raw)
To: Jiayu Hu, olivier.matz; +Cc: dev, Yuanhan Liu, jianfeng.tan
08/01/2018 15:27, Yuanhan Liu:
> On Tue, Nov 21, 2017 at 02:56:52PM +0800, Jiayu Hu wrote:
> > In virtio, UDP Fragmentation Offload (UFO) includes two parts: host UFO
> > and guest UFO. Guest UFO means the frontend can receive large UDP packets,
> > and host UFO means the backend can receive large UDP packets. This patch
> > supports host UFO and guest UFO for vhost-user.
> >
> > Signed-off-by: Jiayu Hu <jiayu.hu@intel.com>
>
> Applied to dpdk-next-virtio.
Olivier Matz, mbuf maintainer, was not Cc'ed in this patch.
Olivier, can you confirm this new mbuf flag is OK?
^ permalink raw reply [flat|nested] 12+ messages in thread
* Re: [dpdk-dev] [PATCH] vhost: support UDP Fragmentation Offload
2018-01-16 11:20 ` Thomas Monjalon
@ 2018-01-16 12:21 ` Olivier Matz
0 siblings, 0 replies; 12+ messages in thread
From: Olivier Matz @ 2018-01-16 12:21 UTC (permalink / raw)
To: Thomas Monjalon; +Cc: Jiayu Hu, dev, Yuanhan Liu, jianfeng.tan
On Tue, Jan 16, 2018 at 12:20:48PM +0100, Thomas Monjalon wrote:
> 08/01/2018 15:27, Yuanhan Liu:
> > On Tue, Nov 21, 2017 at 02:56:52PM +0800, Jiayu Hu wrote:
> > > In virtio, UDP Fragmentation Offload (UFO) includes two parts: host UFO
> > > and guest UFO. Guest UFO means the frontend can receive large UDP packets,
> > > and host UFO means the backend can receive large UDP packets. This patch
> > > supports host UFO and guest UFO for vhost-user.
> > >
> > > Signed-off-by: Jiayu Hu <jiayu.hu@intel.com>
> >
> > Applied to dpdk-next-virtio.
>
> Olivier Matz, mbuf maintainer, was not Cc'ed in this patch.
> Olivier, can you confirm this new mbuf flag is OK?
Yuanhan CC'ed me, but I was quite busy at that time.
Even if it's to late:
Acked-by: Olivier Matz <olivier.matz@6wind.com>
^ permalink raw reply [flat|nested] 12+ messages in thread