Re: [PATCH net-next v2 1/2] virtio_net: introduce ability to get reply info from device

2024-05-06 Thread Heng Qi
On Tue, 7 May 2024 14:24:19 +0800, Jason Wang wrote: > On Fri, Apr 26, 2024 at 2:54 PM Heng Qi wrote: > > > > From: Xuan Zhuo > > > > As the spec > > https://github.com/oasis-tcs/virtio-spec/commit/42f389989823039724f95bbbd243291ab0064f82 > > > > Based on the description provided in the above s

Re: [PATCH net-next 1/3] virtio_net: enable irq for the control vq

2024-05-06 Thread Heng Qi
On Tue, 7 May 2024 14:24:16 +0800, Jason Wang wrote: > On Tue, May 7, 2024 at 12:03 PM Heng Qi wrote: > > > > On Tue, 7 May 2024 11:15:22 +0800, Jason Wang wrote: > > > On Thu, Apr 25, 2024 at 8:59 PM Heng Qi wrote: > > > > > > > > Control vq polling request results consume more CPU. > > > > Es

Re: [PATCH net-next v6 0/6] Remove RTNL lock protection of CVQ

2024-05-06 Thread Jason Wang
On Mon, May 6, 2024 at 2:20 PM Heng Qi wrote: > > On Fri, 3 May 2024 23:24:39 +0300, Daniel Jurgens wrote: > > Currently the buffer used for control VQ commands is protected by the > > RTNL lock. Previously this wasn't a major concern because the control VQ > > was only used during device setup a

Re: [PATCH net-next v2 1/2] virtio_net: introduce ability to get reply info from device

2024-05-06 Thread Jason Wang
On Fri, Apr 26, 2024 at 2:54 PM Heng Qi wrote: > > From: Xuan Zhuo > > As the spec > https://github.com/oasis-tcs/virtio-spec/commit/42f389989823039724f95bbbd243291ab0064f82 > > Based on the description provided in the above specification, we have > enabled the virtio-net driver to support acqui

Re: [PATCH net-next 1/3] virtio_net: enable irq for the control vq

2024-05-06 Thread Jason Wang
On Tue, May 7, 2024 at 12:03 PM Heng Qi wrote: > > On Tue, 7 May 2024 11:15:22 +0800, Jason Wang wrote: > > On Thu, Apr 25, 2024 at 8:59 PM Heng Qi wrote: > > > > > > Control vq polling request results consume more CPU. > > > Especially when dim issues more control requests to the device, > > >

Re: [PATCH net-next v2 2/2] virtio_net: get init coalesce value when probe

2024-05-06 Thread Jason Wang
On Fri, Apr 26, 2024 at 2:54 PM Heng Qi wrote: > > Currently, virtio-net lacks a way to obtain the default coalesce > values of the device during the probe phase. That is, the device > may have default experience values, but the user uses "ethtool -c" > to query that the values are still 0. > > Th

Re: [PATCH net-next 1/3] virtio_net: enable irq for the control vq

2024-05-06 Thread Heng Qi
On Tue, 7 May 2024 11:15:22 +0800, Jason Wang wrote: > On Thu, Apr 25, 2024 at 8:59 PM Heng Qi wrote: > > > > Control vq polling request results consume more CPU. > > Especially when dim issues more control requests to the device, > > it's beneficial to the guest to enable control vq's irq. > > >

Re: [PATCH net-next 1/3] virtio_net: enable irq for the control vq

2024-05-06 Thread Jason Wang
On Thu, Apr 25, 2024 at 8:59 PM Heng Qi wrote: > > Control vq polling request results consume more CPU. > Especially when dim issues more control requests to the device, > it's beneficial to the guest to enable control vq's irq. > > Suggested-by: Jason Wang > Signed-off-by: Heng Qi > --- > driv