Hi Jakub,
On Mon, 14 Dec 2020 at 20:47, Jakub Kicinski wrote:
>
> On Mon, 14 Dec 2020 10:19:07 +0100 Loic Poulain wrote:
> > On Sat, 12 Dec 2020 at 21:55, Jakub Kicinski wrote:
> > > On Thu, 10 Dec 2020 12:15:51 +0100 Loic Poulain wrote:
> > > > The buffer allocation for RX path is currently don
On Mon, 14 Dec 2020 10:19:07 +0100 Loic Poulain wrote:
> On Sat, 12 Dec 2020 at 21:55, Jakub Kicinski wrote:
> > On Thu, 10 Dec 2020 12:15:51 +0100 Loic Poulain wrote:
> > > The buffer allocation for RX path is currently done by a work executed
> > > in the system workqueue. The work to do is qu
Hi Jakub,
On Sat, 12 Dec 2020 at 21:55, Jakub Kicinski wrote:
>
> On Thu, 10 Dec 2020 12:15:51 +0100 Loic Poulain wrote:
> > The buffer allocation for RX path is currently done by a work executed
> > in the system workqueue. The work to do is quite simple and consists
> > mostly in allocating and
On Thu, 10 Dec 2020 12:15:51 +0100 Loic Poulain wrote:
> The buffer allocation for RX path is currently done by a work executed
> in the system workqueue. The work to do is quite simple and consists
> mostly in allocating and queueing as much as possible buffers to the MHI
> RX channel.
>
> It app
The buffer allocation for RX path is currently done by a work executed
in the system workqueue. The work to do is quite simple and consists
mostly in allocating and queueing as much as possible buffers to the MHI
RX channel.
It appears that using a dedicated kthread would be more appropriate to
pr
