netdev - Re: [PATCH net] net: avoid an indirect call in ____sys

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]

Date:   Fri, 06 Dec 2019 19:22:21 +0100
From:   Paolo Abeni <pabeni@...hat.com>
To:     Eric Dumazet <edumazet@...gle.com>,
        "David S . Miller" <davem@...emloft.net>
Cc:     netdev <netdev@...r.kernel.org>,
        Eric Dumazet <eric.dumazet@...il.com>,
        David Laight <David.Laight@...lab.com>
Subject: Re: [PATCH net] net: avoid an indirect call in ____sys_recvmsg()

On Fri, 2019-12-06 at 09:38 -0800, Eric Dumazet wrote:
> CONFIG_RETPOLINE=y made indirect calls expensive.
> 
> gcc seems to add an indirect call in ____sys_recvmsg().
> 
> Rewriting the code slightly makes sure to avoid this indirection.
> 
> Alternative would be to not call sock_recvmsg() and instead
> use security_socket_recvmsg() and sock_recvmsg_nosec(),
> but this is less readable IMO.
> 
> Signed-off-by: Eric Dumazet <edumazet@...gle.com>
> Cc: Paolo Abeni <pabeni@...hat.com>
> Cc: David Laight <David.Laight@...lab.com>

I'm not sure this is -net material, but the code LGTM.

Acked-by: Paolo Abeni <pabeni@...hat.com>