Date:   Wed, 7 Sep 2022 17:55:23 -0700
From:   Song Liu <song@...nel.org>
To:     Punit Agrawal <punit.agrawal@...edance.com>
Cc:     Alexei Starovoitov <ast@...nel.org>, bpf <bpf@...r.kernel.org>,
        open list <linux-kernel@...r.kernel.org>,
        zhoufeng.zf@...edance.com, Daniel Borkmann <daniel@...earbox.net>,
        Andrii Nakryiko <andrii@...nel.org>,
        Martin KaFai Lau <martin.lau@...ux.dev>,
        Yonghong Song <yhs@...com>,
        John Fastabend <john.fastabend@...il.com>,
        KP Singh <kpsingh@...nel.org>, Jiri Olsa <jolsa@...nel.org>
Subject: Re: [PATCH v2] bpf: Simplify code by using for_each_cpu_wrap()

On Wed, Sep 7, 2022 at 8:58 AM Punit Agrawal
<punit.agrawal@...edance.com> wrote:
>
> In the percpu freelist code, it is a common pattern to iterate over
> the possible CPUs mask starting with the current CPU. The pattern is
> implemented using a hand rolled while loop with the loop variable
> increment being open-coded.
>
> Simplify the code by using for_each_cpu_wrap() helper to iterate over
> the possible cpus starting with the current CPU. As a result, some of
> the special-casing in the loop also gets simplified.
>
> No functional change intended.
>
> Signed-off-by: Punit Agrawal <punit.agrawal@...edance.com>
> ---
> v1 -> v2:
> * Fixed the incorrect transformation changing semantics of __pcpu_freelist_push_nmi()
>
> Previous version -
> v1: https://lore.kernel.org/all/20220817130807.68279-1-punit.agrawal@bytedance.com/
>
>  kernel/bpf/percpu_freelist.c | 48 ++++++++++++------------------------
>  1 file changed, 16 insertions(+), 32 deletions(-)
>
> diff --git a/kernel/bpf/percpu_freelist.c b/kernel/bpf/percpu_freelist.c
> index 00b874c8e889..b6e7f5c5b9ab 100644
> --- a/kernel/bpf/percpu_freelist.c
> +++ b/kernel/bpf/percpu_freelist.c
> @@ -58,23 +58,21 @@ static inline void ___pcpu_freelist_push_nmi(struct pcpu_freelist *s,
>  {
>         int cpu, orig_cpu;
>
> -       orig_cpu = cpu = raw_smp_processor_id();
> +       orig_cpu = raw_smp_processor_id();
>         while (1) {
> -               struct pcpu_freelist_head *head;
> +               for_each_cpu_wrap(cpu, cpu_possible_mask, orig_cpu) {
> +                       struct pcpu_freelist_head *head;
>
> -               head = per_cpu_ptr(s->freelist, cpu);
> -               if (raw_spin_trylock(&head->lock)) {
> -                       pcpu_freelist_push_node(head, node);
> -                       raw_spin_unlock(&head->lock);
> -                       return;
> +                       head = per_cpu_ptr(s->freelist, cpu);
> +                       if (raw_spin_trylock(&head->lock)) {
> +                               pcpu_freelist_push_node(head, node);
> +                               raw_spin_unlock(&head->lock);
> +                               return;
> +                       }
>                 }
> -               cpu = cpumask_next(cpu, cpu_possible_mask);
> -               if (cpu >= nr_cpu_ids)
> -                       cpu = 0;

I personally don't like nested loops here. Maybe we can keep
the original while loop and use cpumask_next_wrap()?

Thanks,
Song

>
>                 /* cannot lock any per cpu lock, try extralist */
> -               if (cpu == orig_cpu &&
> -                   pcpu_freelist_try_push_extra(s, node))
> +               if (pcpu_freelist_try_push_extra(s, node))
>                         return;
>         }
>  }
> @@ -125,13 +123,12 @@ static struct pcpu_freelist_node *___pcpu_freelist_pop(struct pcpu_freelist *s)
>  {
>         struct pcpu_freelist_head *head;
>         struct pcpu_freelist_node *node;
> -       int orig_cpu, cpu;
> +       int cpu;
>
> -       orig_cpu = cpu = raw_smp_processor_id();
> -       while (1) {
> +       for_each_cpu_wrap(cpu, cpu_possible_mask, raw_smp_processor_id()) {
>                 head = per_cpu_ptr(s->freelist, cpu);
>                 if (!READ_ONCE(head->first))
> -                       goto next_cpu;
> +                       continue;
>                 raw_spin_lock(&head->lock);
>                 node = head->first;
>                 if (node) {
> @@ -140,12 +137,6 @@ static struct pcpu_freelist_node *___pcpu_freelist_pop(struct pcpu_freelist *s)
>                         return node;
>                 }
>                 raw_spin_unlock(&head->lock);
> -next_cpu:
> -               cpu = cpumask_next(cpu, cpu_possible_mask);
> -               if (cpu >= nr_cpu_ids)
> -                       cpu = 0;
> -               if (cpu == orig_cpu)
> -                       break;
>         }
>
>         /* per cpu lists are all empty, try extralist */
> @@ -164,13 +155,12 @@ ___pcpu_freelist_pop_nmi(struct pcpu_freelist *s)
>  {
>         struct pcpu_freelist_head *head;
>         struct pcpu_freelist_node *node;
> -       int orig_cpu, cpu;
> +       int cpu;
>
> -       orig_cpu = cpu = raw_smp_processor_id();
> -       while (1) {
> +       for_each_cpu_wrap(cpu, cpu_possible_mask, raw_smp_processor_id()) {
>                 head = per_cpu_ptr(s->freelist, cpu);
>                 if (!READ_ONCE(head->first))
> -                       goto next_cpu;
> +                       continue;
>                 if (raw_spin_trylock(&head->lock)) {
>                         node = head->first;
>                         if (node) {
> @@ -180,12 +170,6 @@ ___pcpu_freelist_pop_nmi(struct pcpu_freelist *s)
>                         }
>                         raw_spin_unlock(&head->lock);
>                 }
> -next_cpu:
> -               cpu = cpumask_next(cpu, cpu_possible_mask);
> -               if (cpu >= nr_cpu_ids)
> -                       cpu = 0;
> -               if (cpu == orig_cpu)
> -                       break;
>         }
>
>         /* cannot pop from per cpu lists, try extralist */
> --
> 2.35.1
>

Powered by blists - more mailing lists