linux-kernel - Re: [PATCH bpf-next] bpf: make update_prog_stats always

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] [day] [month] [year] [list]

Message-ID: <CAADnVQLsV-Yfh+HGFZEEMvSUe8sh0j=e_hUYkj_XtVsW=toFCQ@mail.gmail.com>
Date: Wed, 18 Jun 2025 11:09:42 -0700
From: Alexei Starovoitov <alexei.starovoitov@...il.com>
To: Menglong Dong <menglong8.dong@...il.com>
Cc: Alexei Starovoitov <ast@...nel.org>, Daniel Borkmann <daniel@...earbox.net>, 
	John Fastabend <john.fastabend@...il.com>, Andrii Nakryiko <andrii@...nel.org>, 
	Martin KaFai Lau <martin.lau@...ux.dev>, Eduard <eddyz87@...il.com>, Song Liu <song@...nel.org>, 
	Yonghong Song <yonghong.song@...ux.dev>, KP Singh <kpsingh@...nel.org>, 
	Stanislav Fomichev <sdf@...ichev.me>, Hao Luo <haoluo@...gle.com>, Jiri Olsa <jolsa@...nel.org>, 
	bpf <bpf@...r.kernel.org>, LKML <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH bpf-next] bpf: make update_prog_stats always_inline

On Wed, Jun 18, 2025 at 11:06 AM Alexei Starovoitov
<alexei.starovoitov@...il.com> wrote:
>
> On Wed, Jun 18, 2025 at 1:58 AM Menglong Dong <menglong8.dong@...il.com> wrote:
> >
> > The function update_prog_stats() will be called in the bpf trampoline.
> > Make it always_inline to reduce the overhead.
>
> What kind of difference did you measure ?
>
> > Signed-off-by: Menglong Dong <dongml2@...natelecom.cn>
> > ---
> >  kernel/bpf/trampoline.c | 4 ++--
> >  1 file changed, 2 insertions(+), 2 deletions(-)
> >
> > diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
> > index c4b1a98ff726..134bcfd00b15 100644
> > --- a/kernel/bpf/trampoline.c
> > +++ b/kernel/bpf/trampoline.c
> > @@ -911,8 +911,8 @@ static u64 notrace __bpf_prog_enter_recur(struct bpf_prog *prog, struct bpf_tram
> >         return bpf_prog_start_time();
> >  }
> >
> > -static void notrace update_prog_stats(struct bpf_prog *prog,
> > -                                     u64 start)
> > +static __always_inline void notrace update_prog_stats(struct bpf_prog *prog,
> > +                                                     u64 start)
> >  {
>
> How about the following instead:
> diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
> index c4b1a98ff726..728bb2845f41 100644
> --- a/kernel/bpf/trampoline.c
> +++ b/kernel/bpf/trampoline.c
> @@ -911,28 +911,23 @@ static u64 notrace __bpf_prog_enter_recur(struct
> bpf_prog *prog, struct bpf_tram
>      return bpf_prog_start_time();
>  }
>
> -static void notrace update_prog_stats(struct bpf_prog *prog,
> -                      u64 start)
> +static noinline void notrace __update_prog_stats(struct bpf_prog *prog,
> +                         u64 start)
>  {
>      struct bpf_prog_stats *stats;
> -
> -    if (static_branch_unlikely(&bpf_stats_enabled_key) &&
> -        /* static_key could be enabled in __bpf_prog_enter*
> -         * and disabled in __bpf_prog_exit*.
> -         * And vice versa.
> -         * Hence check that 'start' is valid.
> -         */
> -        start > NO_START_TIME) {
> -        u64 duration = sched_clock() - start;
> -        unsigned long flags;
> -
> -        stats = this_cpu_ptr(prog->stats);
> -        flags = u64_stats_update_begin_irqsave(&stats->syncp);
> -        u64_stats_inc(&stats->cnt);
> -        u64_stats_add(&stats->nsecs, duration);
> -        u64_stats_update_end_irqrestore(&stats->syncp, flags);
> -    }
> +    u64 duration = sched_clock() - start;
> +    unsigned long flags;
> +
> +    stats = this_cpu_ptr(prog->stats);
> +    flags = u64_stats_update_begin_irqsave(&stats->syncp);
> +    u64_stats_inc(&stats->cnt);
> +    u64_stats_add(&stats->nsecs, duration);
> +    u64_stats_update_end_irqrestore(&stats->syncp, flags);
>  }
> +#define update_prog_stats(prog, start) \
> +    if (static_branch_unlikely(&bpf_stats_enabled_key) && \

Or make this one always_inline function of two lines
and don't bother with a macro.

> +        start > NO_START_TIME) \
> +        __update_prog_stats(prog, start)
>
>  static void notrace __bpf_prog_exit_recur(struct bpf_prog *prog, u64 start,
>                        struct bpf_tramp_run_ctx *run_ctx)
>
>
> Maybe
> if (start > NO_START_TIME)
> should stay within __update_prog_stats().
>
> pls run a few experiments.