Hi David,
On 5/18/21 9:07 AM, David Marchand wrote:
> The net/vhost pmd does not comply with the ethdev offload API as it does
> not report rx/tx offload capabilities wrt TSO and checksum offloading.
> On the other hand, the net/vhost pmd lets guest negotiates TSO and
> checksum offloading.
>
> Changing the behavior for rx/tx offload flags handling won't
> improve/fix this situation and will break applications that might have
> been relying on implicit support of TSO in this driver.
>
> Revert this behavior change until we have a complete fix.
>
> Fixes: ca7036b4af3a ("vhost: fix offload flags in Rx path")
>
> Signed-off-by: David Marchand <david.march...@redhat.com>
> ---
> The full fix requires:
> - reporting rx/tx_offload_capa,
> - supporting sw TSO and checksums for the case when a virtual machine
> negotiates this feature, but the application does not configure
> DEV_[RT]X_OFFLOAD_* appropriate flags,
>
> ---
> drivers/net/vhost/rte_eth_vhost.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/net/vhost/rte_eth_vhost.c
> b/drivers/net/vhost/rte_eth_vhost.c
> index 8524898661..a202931e9a 100644
> --- a/drivers/net/vhost/rte_eth_vhost.c
> +++ b/drivers/net/vhost/rte_eth_vhost.c
> @@ -1505,7 +1505,7 @@ rte_pmd_vhost_probe(struct rte_vdev_device *dev)
> int ret = 0;
> char *iface_name;
> uint16_t queues;
> - uint64_t flags = RTE_VHOST_USER_NET_COMPLIANT_OL_FLAGS;
> + uint64_t flags = 0;
> uint64_t disable_flags = 0;
> int client_mode = 0;
> int iommu_support = 0;
>
As we discussed yesterday, I agree that's the best thing to do while
proper TSO support is implemented.
Reviewed-by: Maxime Coquelin <maxime.coque...@redhat.com>
Thanks,
Maxime
