diff options
author | Eli Cohen <elic@nvidia.com> | 2023-03-21 12:28:08 +0100 |
---|---|---|
committer | Michael S. Tsirkin <mst@redhat.com> | 2023-04-21 09:02:31 +0200 |
commit | 791a1cb7b8591ece6a5075dfed803da379e7ecd3 (patch) | |
tree | 0c7374c8edaf1d64f6a77f6275ca715b3796c57c /drivers/vdpa/mlx5/net/mlx5_vnet.c | |
parent | virtio_ring: Allow non power of 2 sizes for packed virtqueue (diff) | |
download | linux-791a1cb7b8591ece6a5075dfed803da379e7ecd3.tar.xz linux-791a1cb7b8591ece6a5075dfed803da379e7ecd3.zip |
vdpa/mlx5: Make VIRTIO_NET_F_MRG_RXBUF off by default
Following patch adds driver support for VIRTIO_NET_F_MRG_RXBUF.
Current firmware versions show degradation in packet rate when using
MRG_RXBUF. Users who favor memory saving over packet rate could enable
this feature but we want to keep it off by default.
One can still enable it when creating the vdpa device using vdpa tool by
providing features that include it.
For example:
$ vdpa dev add name vdpa0 mgmtdev pci/0000:86:00.2 device_features 0x300cb982b
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Eli Cohen <elic@nvidia.com>
Message-Id: <20230321112809.221432-2-elic@nvidia.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Si-Wei Liu <si-wei.liu@oracle.com>
Diffstat (limited to 'drivers/vdpa/mlx5/net/mlx5_vnet.c')
-rw-r--r-- | drivers/vdpa/mlx5/net/mlx5_vnet.c | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 97a16f7eb894..b5245956665b 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -3158,6 +3158,8 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name, return -EINVAL; } device_features &= add_config->device_features; + } else { + device_features &= ~BIT_ULL(VIRTIO_NET_F_MRG_RXBUF); } if (!(device_features & BIT_ULL(VIRTIO_F_VERSION_1) && device_features & BIT_ULL(VIRTIO_F_ACCESS_PLATFORM))) { |