On Fri, 10 Nov 2023 00:33:27 -0500, "Michael S. Tsirkin"
wrote:
> On Fri, Nov 10, 2023 at 09:47:16AM +0800, Xuan Zhuo wrote:
> > On Thu, 9 Nov 2023 07:00:51 -0500, "Michael S. Tsirkin"
> > wrote:
> > > On Thu, Nov 09, 2023 at 07:10:02PM +0800, Xuan Zhuo wrote:
> > > > On Thu, 9 Nov 2023 03:15:0
On Fri, 10 Nov 2023 00:32:50 -0500, "Michael S. Tsirkin"
wrote:
> On Fri, Nov 10, 2023 at 09:44:32AM +0800, Xuan Zhuo wrote:
> > On Thu, 9 Nov 2023 06:59:48 -0500, "Michael S. Tsirkin"
> > wrote:
> > > On Thu, Nov 09, 2023 at 07:16:08PM +0800, Xuan Zhuo wrote:
> > > > On Thu, 9 Nov 2023 06:11:4
On Fri, 10 Nov 2023 00:37:32 -0500, "Michael S. Tsirkin"
wrote:
> On Fri, Nov 10, 2023 at 09:58:45AM +0800, Xuan Zhuo wrote:
> > On Thu, 9 Nov 2023 07:06:16 -0500, "Michael S. Tsirkin"
> > wrote:
> > > On Mon, Nov 06, 2023 at 04:18:32PM +0800, Xuan Zhuo wrote:
> > > > For rq, we have three case
On Fri, Nov 10, 2023 at 09:58:45AM +0800, Xuan Zhuo wrote:
> On Thu, 9 Nov 2023 07:06:16 -0500, "Michael S. Tsirkin"
> wrote:
> > On Mon, Nov 06, 2023 at 04:18:32PM +0800, Xuan Zhuo wrote:
> > > For rq, we have three cases getting buffers from virtio core:
> > >
> > > 1. virtqueue_get_buf{,_ctx}
On Fri, Nov 10, 2023 at 09:47:16AM +0800, Xuan Zhuo wrote:
> On Thu, 9 Nov 2023 07:00:51 -0500, "Michael S. Tsirkin"
> wrote:
> > On Thu, Nov 09, 2023 at 07:10:02PM +0800, Xuan Zhuo wrote:
> > > On Thu, 9 Nov 2023 03:15:03 -0500, "Michael S. Tsirkin"
> > > wrote:
> > > > On Tue, Nov 07, 2023 at
On Fri, Nov 10, 2023 at 09:44:32AM +0800, Xuan Zhuo wrote:
> On Thu, 9 Nov 2023 06:59:48 -0500, "Michael S. Tsirkin"
> wrote:
> > On Thu, Nov 09, 2023 at 07:16:08PM +0800, Xuan Zhuo wrote:
> > > On Thu, 9 Nov 2023 06:11:49 -0500, "Michael S. Tsirkin"
> > > wrote:
> > > > On Tue, Nov 07, 2023 at
On Thu, 9 Nov 2023 03:12:27 -0500, "Michael S. Tsirkin" wrote:
> On Tue, Nov 07, 2023 at 11:12:22AM +0800, Xuan Zhuo wrote:
> > Implement the logic of filling rq with XSK buffers.
> >
> > Signed-off-by: Xuan Zhuo
> > ---
> > drivers/net/virtio/main.c | 4 ++-
> > drivers/net/virtio/virtio
On Thu, 9 Nov 2023 17:26:33 +0100, Maciej Fijalkowski
wrote:
> On Thu, Nov 09, 2023 at 07:11:46PM +0800, Xuan Zhuo wrote:
> > On Thu, 9 Nov 2023 03:12:27 -0500, "Michael S. Tsirkin"
> > wrote:
> > > On Tue, Nov 07, 2023 at 11:12:22AM +0800, Xuan Zhuo wrote:
> > > > Implement the logic of fillin
On Thu, 9 Nov 2023 07:06:16 -0500, "Michael S. Tsirkin" wrote:
> On Mon, Nov 06, 2023 at 04:18:32PM +0800, Xuan Zhuo wrote:
> > For rq, we have three cases getting buffers from virtio core:
> >
> > 1. virtqueue_get_buf{,_ctx}
> > 2. virtqueue_detach_unused_buf
> > 3. callback for virtqueue_resize
On Thu, 9 Nov 2023 06:58:48 -0500, "Michael S. Tsirkin" wrote:
> On Thu, Nov 09, 2023 at 07:06:23PM +0800, Xuan Zhuo wrote:
> > On Thu, 9 Nov 2023 03:09:00 -0500, "Michael S. Tsirkin"
> > wrote:
> > > On Tue, Nov 07, 2023 at 11:12:18AM +0800, Xuan Zhuo wrote:
> > > > The driver's tx napi is very
On Thu, 9 Nov 2023 07:00:51 -0500, "Michael S. Tsirkin" wrote:
> On Thu, Nov 09, 2023 at 07:10:02PM +0800, Xuan Zhuo wrote:
> > On Thu, 9 Nov 2023 03:15:03 -0500, "Michael S. Tsirkin"
> > wrote:
> > > On Tue, Nov 07, 2023 at 11:12:23AM +0800, Xuan Zhuo wrote:
> > > > When rq is bound with AF_XDP
On Thu, 9 Nov 2023 06:59:48 -0500, "Michael S. Tsirkin" wrote:
> On Thu, Nov 09, 2023 at 07:16:08PM +0800, Xuan Zhuo wrote:
> > On Thu, 9 Nov 2023 06:11:49 -0500, "Michael S. Tsirkin"
> > wrote:
> > > On Tue, Nov 07, 2023 at 11:12:20AM +0800, Xuan Zhuo wrote:
> > > > virtnet_free_old_xmit distin
On Thu, Nov 09, 2023 at 07:11:46PM +0800, Xuan Zhuo wrote:
> On Thu, 9 Nov 2023 03:12:27 -0500, "Michael S. Tsirkin"
> wrote:
> > On Tue, Nov 07, 2023 at 11:12:22AM +0800, Xuan Zhuo wrote:
> > > Implement the logic of filling rq with XSK buffers.
> > >
> > > Signed-off-by: Xuan Zhuo
> > > ---
>
On Mon, Nov 06, 2023 at 04:18:32PM +0800, Xuan Zhuo wrote:
> For rq, we have three cases getting buffers from virtio core:
>
> 1. virtqueue_get_buf{,_ctx}
> 2. virtqueue_detach_unused_buf
> 3. callback for virtqueue_resize
>
> But in commit 295525e29a5b("virtio_net: merge dma operations when
> fi
On Thu, Nov 09, 2023 at 07:10:02PM +0800, Xuan Zhuo wrote:
> On Thu, 9 Nov 2023 03:15:03 -0500, "Michael S. Tsirkin"
> wrote:
> > On Tue, Nov 07, 2023 at 11:12:23AM +0800, Xuan Zhuo wrote:
> > > When rq is bound with AF_XDP, the buffer dma is managed
> > > by the AF_XDP APIs. So the buffer got fr
On Thu, Nov 09, 2023 at 07:16:08PM +0800, Xuan Zhuo wrote:
> On Thu, 9 Nov 2023 06:11:49 -0500, "Michael S. Tsirkin"
> wrote:
> > On Tue, Nov 07, 2023 at 11:12:20AM +0800, Xuan Zhuo wrote:
> > > virtnet_free_old_xmit distinguishes three type ptr(skb, xdp frame, xsk
> > > buffer) by the last bits
On Thu, Nov 09, 2023 at 07:06:23PM +0800, Xuan Zhuo wrote:
> On Thu, 9 Nov 2023 03:09:00 -0500, "Michael S. Tsirkin"
> wrote:
> > On Tue, Nov 07, 2023 at 11:12:18AM +0800, Xuan Zhuo wrote:
> > > The driver's tx napi is very important for XSK. It is responsible for
> > > obtaining data from the XS
On Mon, 2023-11-06 at 16:18 +0800, Xuan Zhuo wrote:
> For rq, we have three cases getting buffers from virtio core:
>
> 1. virtqueue_get_buf{,_ctx}
> 2. virtqueue_detach_unused_buf
> 3. callback for virtqueue_resize
>
> But in commit 295525e29a5b("virtio_net: merge dma operations when
> filling m
On Thu, 9 Nov 2023 06:11:49 -0500, "Michael S. Tsirkin" wrote:
> On Tue, Nov 07, 2023 at 11:12:20AM +0800, Xuan Zhuo wrote:
> > virtnet_free_old_xmit distinguishes three type ptr(skb, xdp frame, xsk
> > buffer) by the last bits of the pointer.
> >
> > Signed-off-by: Xuan Zhuo
> > ---
> > drivers
On Thu, 9 Nov 2023 03:12:27 -0500, "Michael S. Tsirkin" wrote:
> On Tue, Nov 07, 2023 at 11:12:22AM +0800, Xuan Zhuo wrote:
> > Implement the logic of filling rq with XSK buffers.
> >
> > Signed-off-by: Xuan Zhuo
> > ---
> > drivers/net/virtio/main.c | 4 ++-
> > drivers/net/virtio/virtio
On Tue, Nov 07, 2023 at 11:12:20AM +0800, Xuan Zhuo wrote:
> virtnet_free_old_xmit distinguishes three type ptr(skb, xdp frame, xsk
> buffer) by the last bits of the pointer.
>
> Signed-off-by: Xuan Zhuo
> ---
> drivers/net/virtio/virtio_net.h | 18 --
> drivers/net/virtio/xsk.h
On Thu, 9 Nov 2023 03:15:03 -0500, "Michael S. Tsirkin" wrote:
> On Tue, Nov 07, 2023 at 11:12:23AM +0800, Xuan Zhuo wrote:
> > When rq is bound with AF_XDP, the buffer dma is managed
> > by the AF_XDP APIs. So the buffer got from the virtio core should
> > skip the dma unmap operation.
> >
> > Si
On Thu, 9 Nov 2023 03:09:00 -0500, "Michael S. Tsirkin" wrote:
> On Tue, Nov 07, 2023 at 11:12:18AM +0800, Xuan Zhuo wrote:
> > The driver's tx napi is very important for XSK. It is responsible for
> > obtaining data from the XSK queue and sending it out.
> >
> > At the beginning, we need to trigg
On Thu, 9 Nov 2023 14:37:38 +0800, Jason Wang wrote:
> On Tue, Nov 7, 2023 at 11:12 AM Xuan Zhuo wrote:
> >
> > If the xsk is enabling, the xsk tx will share the send queue.
> > But the xsk requires that the send queue use the premapped mode.
> > So the send queue must support premapped mode.
> >
On Thu, 9 Nov 2023 03:19:04 -0500, "Michael S. Tsirkin" wrote:
> On Tue, Nov 07, 2023 at 11:12:06AM +0800, Xuan Zhuo wrote:
> > ## AF_XDP
> >
> > XDP socket(AF_XDP) is an excellent bypass kernel network framework. The zero
> > copy feature of xsk (XDP socket) needs to be supported by the driver. T
在 2023/11/9 下午12:45, Jason Wang 写道:
On Thu, Nov 2, 2023 at 9:10 PM Heng Qi wrote:
We do not currently support tx dim, so respond to -EOPNOTSUPP.
Signed-off-by: Heng Qi
---
v1->v2:
- Use -EOPNOTSUPP instead of specific implementation.
drivers/net/virtio_net.c | 29 +++
在 2023/11/9 下午12:43, Jason Wang 写道:
On Thu, Nov 2, 2023 at 9:10 PM Heng Qi wrote:
By comparing the traffic information in the complete napi processes,
let the virtio-net driver automatically adjust the coalescing
moderation parameters of each receive queue.
Signed-off-by: Heng Qi
---
v1->v
On Tue, Nov 07, 2023 at 11:12:06AM +0800, Xuan Zhuo wrote:
> ## AF_XDP
>
> XDP socket(AF_XDP) is an excellent bypass kernel network framework. The zero
> copy feature of xsk (XDP socket) needs to be supported by the driver. The
> performance of zero copy is very good. mlx5 and intel ixgbe already
On Tue, Nov 07, 2023 at 11:12:23AM +0800, Xuan Zhuo wrote:
> When rq is bound with AF_XDP, the buffer dma is managed
> by the AF_XDP APIs. So the buffer got from the virtio core should
> skip the dma unmap operation.
>
> Signed-off-by: Xuan Zhuo
I don't get it - is this like a bugfix?
And why d
On Tue, Nov 07, 2023 at 11:12:22AM +0800, Xuan Zhuo wrote:
> Implement the logic of filling rq with XSK buffers.
>
> Signed-off-by: Xuan Zhuo
> ---
> drivers/net/virtio/main.c | 4 ++-
> drivers/net/virtio/virtio_net.h | 5
> drivers/net/virtio/xsk.c| 49
On Tue, Nov 07, 2023 at 11:12:18AM +0800, Xuan Zhuo wrote:
> The driver's tx napi is very important for XSK. It is responsible for
> obtaining data from the XSK queue and sending it out.
>
> At the beginning, we need to trigger tx napi.
>
> Signed-off-by: Xuan Zhuo
> ---
> drivers/net/virtio/ma
31 matches
Mail list logo