vhost: Add VIRTIO_NET_F_RSC_EXT to vhost feature bits
PATCH 1/1 vhost: Add VIRTIO_NET_F_RSC_EXT to vhost feature bits
VIRTIO_NET_F_RSC_EXT is implemented in the rx data path, which vhost implements, so vhost needs to support the feature if it is ever to be enabled with vhost. The feature must be disabled otherwise.
--- hw/net/vhost_net.c | 2 ++ net/vhost-vdpa.c | 1 + 2 files changed, 3 insertions(+)
hw/net/vhost_net.c +2 -0
@@ -50,6 +50,7 @@ static const int kernel_feature_bits[] = {VIRTIO_F_RING_RESET ,VIRTIO_F_IN_ORDER ,VIRTIO_F_NOTIFICATION_DATA , +VIRTIO_NET_F_RSC_EXT ,VIRTIO_NET_F_HASH_REPORT , VHOST_INVALID_FEATURE_BIT };
@@ -81,6 +82,7 @@ static const int user_feature_bits[] = {VIRTIO_F_RING_RESET ,VIRTIO_F_IN_ORDER ,VIRTIO_NET_F_RSS , +VIRTIO_NET_F_RSC_EXT ,VIRTIO_NET_F_HASH_REPORT ,VIRTIO_NET_F_GUEST_USO4 , VIRTIO_NET_F_GUEST_USO6,
net/vhost-vdpa.c +1 -0
@@ -88,6 +88,7 @@ const int vdpa_feature_bits[] = {VIRTIO_NET_F_MQ ,VIRTIO_NET_F_MRG_RXBUF ,VIRTIO_NET_F_MTU , +VIRTIO_NET_F_RSC_EXT ,VIRTIO_NET_F_RSS ,VIRTIO_NET_F_STATUS , VIRTIO_RING_F_EVENT_IDX,
---
base-commit: 31669121a01a14732f57c49400bc239cf9fd505f
change-id: 20240802-rsc-e90fb452bd7f
Best regards,
Signature · 1 line
Akihiko Odaki <[email protected]>
At the moment kernel (vhost) and vhost user backends do not support this feature (and IMO they do not need to)
In order to support it they need to implement a) coalescing of segmented TCP packets and b) population of respective fields in host-to-guest packets (number of coalesced segments and counter of duplicated acks)
Just to remind - this feature is intended to be used without vhost and without migration
Thanks
Yuri
Quoted 54 lines · Akihiko Odaki
VIRTIO_NET_F_RSC_EXTis implemented in the rx data path, which vhost implements, so vhost needs to support the feature if it is ever to be enabled with vhost. The feature must be disabled otherwise.Fixes 2974e916df87 ("virtio-net: support RSC v4/v6 tcp traffic for Windows HCK")Reported-by Jason Wang <[email protected]>Signed-off-by Akihiko Odaki <[email protected]>--- hw/net/vhost_net.c | 2 ++ net/vhost-vdpa.c | 1 + 2 files changed, 3 insertions(+)hw/net/vhost_net.c +2
-0@@ -50,6 +50,7 @@ static const int kernel_feature_bits[] = {VIRTIO_F_RING_RESET ,VIRTIO_F_IN_ORDER ,VIRTIO_F_NOTIFICATION_DATA , +VIRTIO_NET_F_RSC_EXT ,VIRTIO_NET_F_HASH_REPORT , VHOST_INVALID_FEATURE_BIT };@@ -81,6 +82,7 @@ static const int user_feature_bits[] = {VIRTIO_F_RING_RESET ,VIRTIO_F_IN_ORDER ,VIRTIO_NET_F_RSS , +VIRTIO_NET_F_RSC_EXT ,VIRTIO_NET_F_HASH_REPORT ,VIRTIO_NET_F_GUEST_USO4 , VIRTIO_NET_F_GUEST_USO6,net/vhost-vdpa.c +1
-1@@ -88,6 +88,7 @@ const int vdpa_feature_bits[] = {VIRTIO_NET_F_MQ ,VIRTIO_NET_F_MRG_RXBUF ,VIRTIO_NET_F_MTU , +VIRTIO_NET_F_RSC_EXT ,VIRTIO_NET_F_RSS ,VIRTIO_NET_F_STATUS , VIRTIO_RING_F_EVENT_IDX, ---base-commit:
31669121a01a14732f57c49400bc239cf9fd505f
change-id: 20240802-rsc-e90fb452bd7fBest regards,
--
Akihiko Odaki <[email protected]>
Quoted 11 lines · Yuri Benditovich
At the moment kernel (vhost) and vhost user backends do not support this feature (and IMO they do not need to)
In order to support it they need to implement a) coalescing of segmented TCP packets and b) population of respective fields in host-to-guest packets (number of coalesced segments and counter of duplicated acks)
Just to remind - this feature is intended to be used without vhost and without migrationThanks
Yuri
it is off ny default so no big deal ...
if it's incompatiblr with vhost/migration I guess it is a good idea to make sure users do not enable it like this.
Quoted 9 lines · Akihiko Odaki
VIRTIO_NET_F_RSC_EXTis implemented in the rx data path, which vhost implements, so vhost needs to support the feature if it is ever to be enabled with vhost. The feature must be disabled otherwise.Fixes 2974e916df87 ("virtio-net: support RSC v4/v6 tcp traffic for Windows HCK")Reported-by Jason Wang <[email protected]>Signed-off-by Akihiko Odaki <[email protected]>---
Thanks