Re: [PATCH] tcp: fix race condition when creating child sockets from syncookies
flat view
From: Eric Dumazet <hidden>
Date: 2020-10-23 16:51:32
Also in:
lkml
On Fri, Oct 23, 2020 at 6:48 PM Ricardo Dias [off-list ref] 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 ;)