netdev - Re: [PATCH net-next 1/4] indirect call wrappers: helpers to speed-up indirect calls of builtin

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: <8a3c6447-96a0-3c03-dae3-e7d6bbf42d49@solarflare.com>
Date:   Tue, 4 Dec 2018 17:13:01 +0000
From:   Edward Cree <ecree@...arflare.com>
To:     Paolo Abeni <pabeni@...hat.com>, <netdev@...r.kernel.org>
CC:     "David S. Miller" <davem@...emloft.net>,
        Eric Dumazet <eric.dumazet@...il.com>
Subject: Re: [PATCH net-next 1/4] indirect call wrappers: helpers to speed-up
 indirect calls of builtin

On 03/12/18 11:40, Paolo Abeni wrote:
> This header define a bunch of helpers that allow avoiding the
> retpoline overhead when calling builtin functions via function pointers.
> It boils down to explicitly comparing the function pointers to
> known builtin functions and eventually invoke directly the latter.
>
> The macros defined here implement the boilerplate for the above schema
> and will be used by the next patches.
>
> rfc -> v1:
>  - use branch prediction hint, as suggested by Eric
>
> Suggested-by: Eric Dumazet <Eric Dumazet edumazet@...gle.com>
> Signed-off-by: Paolo Abeni <pabeni@...hat.com>
> ---
I'm not sure I see the reason why this is done with numbers and
 'name ## NR', adding extra distance between the callsite and the
 list of callees.  In particular it means that each callable needs
 to specify its index.
Wouldn't it be simpler just to have
    #define INDIRECT_CALL_1(f, f1, ...) \
        (likely(f == f1) ? f1(__VA_ARGS__) : f(__VA_ARGS__))
    #define INDIRECT_CALL_2(f, f2, f1, ...) \
        (likely(f == f2) ? f2(__VA_ARGS__) : INDIRECT_CALL_1(f, f1, __VA_ARGS__))
etc.?  Removing the need for INDIRECT_CALLABLE_DECLARE_* entirely.

At least the commit message should explain the rationale for not
 doing things this way.

-Ed

PS: this has reminded me of my desire to try runtime creation of
 these kinds of branch tables with self-modifying code; is there
 any documentation on how to go about writing to kernel .text at
 runtime?  Last time I had a try at it I got very confused.