On Tue, Feb 20, 2024 at 6:33 PM Paolo Abeni wrote:
>
> On Mon, 2024-02-19 at 19:33 +0100, Eric Dumazet wrote:
> > On Mon, Feb 19, 2024 at 7:04 PM Paolo Abeni wrote:
> > > Thanks for the head-up. This later option looks preferable, to avoid
> > > quit a bit of noise with _ONCE annotation. Is there
On Mon, 2024-02-19 at 19:33 +0100, Eric Dumazet wrote:
> On Mon, Feb 19, 2024 at 7:04 PM Paolo Abeni wrote:
> > Thanks for the head-up. This later option looks preferable, to avoid
> > quit a bit of noise with _ONCE annotation. Is there a syzkaller splat I
> > could look at? if it landed on the ML
On Mon, Feb 19, 2024 at 7:04 PM Paolo Abeni wrote:
>
> On Mon, 2024-02-19 at 18:35 +0100, Eric Dumazet wrote:
> > On Mon, Feb 19, 2024 at 6:21 PM Eric Dumazet wrote:
> > >
> > > On Thu, Feb 15, 2024 at 7:25 PM Matthieu Baerts (NGI0)
> > > wrote:
> > > >
> > > > From: Paolo Abeni
> > > >
> > > >
On Mon, 2024-02-19 at 18:35 +0100, Eric Dumazet wrote:
> On Mon, Feb 19, 2024 at 6:21 PM Eric Dumazet wrote:
> >
> > On Thu, Feb 15, 2024 at 7:25 PM Matthieu Baerts (NGI0)
> > wrote:
> > >
> > > From: Paolo Abeni
> > >
> > > Since the introduction of the subflow ULP diag interface, the
> > >
On Mon, Feb 19, 2024 at 6:21 PM Eric Dumazet wrote:
>
> On Thu, Feb 15, 2024 at 7:25 PM Matthieu Baerts (NGI0)
> wrote:
> >
> > From: Paolo Abeni
> >
> > Since the introduction of the subflow ULP diag interface, the
> > dump callback accessed all the subflow data with lockless.
> >
> > We need e
On Thu, Feb 15, 2024 at 7:25 PM Matthieu Baerts (NGI0)
wrote:
>
> From: Paolo Abeni
>
> Since the introduction of the subflow ULP diag interface, the
> dump callback accessed all the subflow data with lockless.
>
> We need either to annotate all the read and write operation accordingly,
> or acqu
From: Paolo Abeni
Since the introduction of the subflow ULP diag interface, the
dump callback accessed all the subflow data with lockless.
We need either to annotate all the read and write operation accordingly,
or acquire the subflow socket lock. Let's do latter, even if slower, to
avoid a diff
