Re: [PATCH] tcp: fix race condition when creating child sockets from syncookies

From: Ricardo Dias
Date: Fri Oct 23 2020 - 12:54:46 EST


On Fri, Oct 23, 2020 at 06:51:05PM +0200, Eric Dumazet wrote:
> On Fri, Oct 23, 2020 at 6:48 PM Ricardo Dias <rdias@xxxxxxxxxx> wrote:
> >
>
> > In that case, I can change the patch to only iterate the ehash bucket
> > only when the listening socket is using the loopback interface, correct?
>
> No, the fix should be generic.
>
> We could still have bad NIC, or bad configuration, spreading packets
> on random cpus ;)

Ah, got it!