Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
MIME-Version: 1.0
References: <20221111132258.762033-1-xukuohai@huaweicloud.com>
In-Reply-To: <20221111132258.762033-1-xukuohai@huaweicloud.com>
From:   Andrii Nakryiko <andrii.nakryiko@gmail.com>
Date:   Fri, 11 Nov 2022 12:39:08 -0800
Message-ID: <CAEf4Bza8+8xDw9dSafVOswrAgLBGjaO_wcBEf+K+CkDEHubW-Q@mail.gmail.com>
Subject: Re: [PATCH bpf-next v5] bpf: Initialize same number of free nodes for
 each pcpu_freelist
To:     Xu Kuohai <xukuohai@huaweicloud.com>
Cc:     bpf@vger.kernel.org, linux-kernel@vger.kernel.org,
        Alexei Starovoitov <ast@kernel.org>,
        Daniel Borkmann <daniel@iogearbox.net>,
        Andrii Nakryiko <andrii@kernel.org>,
        Martin KaFai Lau <martin.lau@linux.dev>,
        Song Liu <song@kernel.org>, Yonghong Song <yhs@fb.com>,
        John Fastabend <john.fastabend@gmail.com>,
        KP Singh <kpsingh@kernel.org>,
        Stanislav Fomichev <sdf@google.com>,
        Hao Luo <haoluo@google.com>, Jiri Olsa <jolsa@kernel.org>,
        wuqiang <wuqiang.matt@bytedance.com>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

On Fri, Nov 11, 2022 at 5:06 AM Xu Kuohai <xukuohai@huaweicloud.com> wrote:
>
> From: Xu Kuohai <xukuohai@huawei.com>
>
> pcpu_freelist_populate() initializes nr_elems / num_possible_cpus() + 1
> free nodes for some CPUs, and then possibly one CPU with fewer nodes,
> followed by remaining cpus with 0 nodes. For example, when nr_elems == 256
> and num_possible_cpus() == 32, CPU 0~27 each gets 9 free nodes, CPU 28 gets
> 4 free nodes, CPU 29~31 get 0 free nodes, while in fact each CPU should get
> 8 nodes equally.
>
> This patch initializes nr_elems / num_possible_cpus() free nodes for each
> CPU firstly, then allocates the remaining free nodes by one for each CPU
> until no free nodes left.
>
> Signed-off-by: Xu Kuohai <xukuohai@huawei.com>
> Acked-by: Yonghong Song <yhs@fb.com>
> ---
> v5: Move "head = per_cpu_ptr ..." out of the i-loop as suggesetd by wuqiang

I've applied v4 (before seeing v5) with head moved out of innermost
loop. But I do prefer v4 anyways.

> v4: Remove unneeded min()
> v3: Simplify code as suggested by Andrii
> v2: Update commit message and add Yonghong's ack
> ---
>  kernel/bpf/percpu_freelist.c | 21 +++++++++------------
>  1 file changed, 9 insertions(+), 12 deletions(-)
>
> diff --git a/kernel/bpf/percpu_freelist.c b/kernel/bpf/percpu_freelist.c
> index b6e7f5c5b9ab..de336e3dffee 100644
> --- a/kernel/bpf/percpu_freelist.c
> +++ b/kernel/bpf/percpu_freelist.c
> @@ -100,22 +100,19 @@ void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size,
>                             u32 nr_elems)
>  {
>         struct pcpu_freelist_head *head;
> -       int i, cpu, pcpu_entries;
> +       unsigned int cpu_idx = 0, cpu, i, j, n, m;
>
> -       pcpu_entries = nr_elems / num_possible_cpus() + 1;
> -       i = 0;
> +       n = nr_elems / num_possible_cpus();
> +       m = nr_elems % num_possible_cpus();
>
>         for_each_possible_cpu(cpu) {
> -again:
>                 head = per_cpu_ptr(s->freelist, cpu);
> -               /* No locking required as this is not visible yet. */
> -               pcpu_freelist_push_node(head, buf);
> -               i++;
> -               buf += elem_size;
> -               if (i == nr_elems)
> -                       break;
> -               if (i % pcpu_entries)
> -                       goto again;
> +               j = n + (cpu_idx++ < m ? 1 : 0);
> +               for (i = 0; i < j; i++) {
> +                       /* No locking required as this is not visible yet. */
> +                       pcpu_freelist_push_node(head, buf);
> +                       buf += elem_size;
> +               }
>         }
>  }
>
> --
> 2.30.2
>