netdev - Re: [PATCH v4 bpf-next 2/3] veth: rework veth_xdp_rcv

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20220312131806.1c2919ba@kicinski-fedora-pc1c0hjn.dhcp.thefacebook.com>
Date:   Sat, 12 Mar 2022 13:18:06 -0800
From:   Jakub Kicinski <kuba@...nel.org>
To:     Toke Høiland-Jørgensen <toke@...hat.com>
Cc:     Lorenzo Bianconi <lorenzo.bianconi@...hat.com>,
        Lorenzo Bianconi <lorenzo@...nel.org>, bpf@...r.kernel.org,
        netdev@...r.kernel.org, davem@...emloft.net, ast@...nel.org,
        daniel@...earbox.net, brouer@...hat.com, pabeni@...hat.com,
        echaudro@...hat.com, toshiaki.makita1@...il.com, andrii@...nel.org
Subject: Re: [PATCH v4 bpf-next 2/3] veth: rework veth_xdp_rcv_skb in order
 to accept non-linear skb

On Thu, 10 Mar 2022 20:06:40 +0100 Toke Høiland-Jørgensen wrote:
> >> So this always clones the skb if it has frags? Is that really needed?  
> >
> > if we look at skb_cow_data(), paged area is always considered not writable  
> 
> Ah, right, did not know that. Seems a bit odd, but OK.

Yeah, I think I pointed that out, I may well be wrong.

AFAICT frags which are not writable are not marked in any clear
way. We have SKBFL_SHARED_FRAG which seems pretty close but its
documented as an indication that the frag can be written under our
feet, not that we can't write to it. Subtly different. And (as
documented) it's only used when doing SW csums, as far as I can
grep.

Maybe someone else knows the semantics.