On Thu, Apr 10, 2025 at 3:00 PM Stefan Hajnoczi wrote:
>
> On Tue, Apr 8, 2025 at 10:55 AM Antoine Damhet wrote:
> >
> > This reverts commit 7987d2be5a8bc3a502f89ba8cf3ac3e09f64d1ce.
> >
> > The goal was to remove the need to patch the (const) input buffer
> > with a recomputed UDP checksum by co
On Tue, Apr 08, 2025 at 04:53:33PM +0200, Antoine Damhet wrote:
> This reverts commit 7987d2be5a8bc3a502f89ba8cf3ac3e09f64d1ce.
>
> The goal was to remove the need to patch the (const) input buffer
> with a recomputed UDP checksum by copying headers to a RW region and
> inject the checksum there.
On Mon, Apr 14, 2025 at 6:48 PM Michael S. Tsirkin wrote:
>
> On Thu, Apr 10, 2025 at 03:00:40PM -0400, Stefan Hajnoczi wrote:
> > On Tue, Apr 8, 2025 at 10:55 AM Antoine Damhet wrote:
> > >
> > > This reverts commit 7987d2be5a8bc3a502f89ba8cf3ac3e09f64d1ce.
> > >
> > > The goal was to remove the
On Thu, Apr 10, 2025 at 03:00:40PM -0400, Stefan Hajnoczi wrote:
> On Tue, Apr 8, 2025 at 10:55 AM Antoine Damhet wrote:
> >
> > This reverts commit 7987d2be5a8bc3a502f89ba8cf3ac3e09f64d1ce.
> >
> > The goal was to remove the need to patch the (const) input buffer
> > with a recomputed UDP checksu
On Tue, Apr 8, 2025 at 10:55 AM Antoine Damhet wrote:
>
> This reverts commit 7987d2be5a8bc3a502f89ba8cf3ac3e09f64d1ce.
>
> The goal was to remove the need to patch the (const) input buffer
> with a recomputed UDP checksum by copying headers to a RW region and
> inject the checksum there. The patc
This reverts commit 7987d2be5a8bc3a502f89ba8cf3ac3e09f64d1ce.
The goal was to remove the need to patch the (const) input buffer
with a recomputed UDP checksum by copying headers to a RW region and
inject the checksum there. The patch computed the checksum only from the
header fields (missing the r