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 for Android: free password hash cracker in your pocket
[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <11b1c67e-ab07-5eed-0e2d-8c85f6a89725@huawei.com>
Date:   Thu, 10 Nov 2022 19:39:56 +0800
From:   Xu Kuohai <xukuohai@...wei.com>
To:     Andrii Nakryiko <andrii.nakryiko@...il.com>
CC:     <bpf@...r.kernel.org>, <linux-kernel@...r.kernel.org>,
        Alexei Starovoitov <ast@...nel.org>,
        Daniel Borkmann <daniel@...earbox.net>,
        Andrii Nakryiko <andrii@...nel.org>,
        Martin KaFai Lau <martin.lau@...ux.dev>,
        Song Liu <song@...nel.org>, Yonghong Song <yhs@...com>,
        John Fastabend <john.fastabend@...il.com>,
        KP Singh <kpsingh@...nel.org>,
        Stanislav Fomichev <sdf@...gle.com>,
        Hao Luo <haoluo@...gle.com>, Jiri Olsa <jolsa@...nel.org>
Subject: Re: [PATCH bpf-next v3] bpf: Initialize same number of free nodes for
 each pcpu_freelist

On 11/10/2022 2:23 PM, Xu Kuohai wrote:
> On 11/10/2022 12:05 PM, Andrii Nakryiko wrote:
>> On Wed, Nov 9, 2022 at 7:33 PM Xu Kuohai <xukuohai@...wei.com> wrote:
>>>
>>> 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@...wei.com>
>>> Acked-by: Yonghong Song <yhs@...com>
>>> ---
>>> v3: Simplify code as suggested by Andrii
>>> v2: Update commit message and add Yonghong's ack
>>> ---
>>>   kernel/bpf/percpu_freelist.c | 27 ++++++++++++++-------------
>>>   1 file changed, 14 insertions(+), 13 deletions(-)
>>>
>>> diff --git a/kernel/bpf/percpu_freelist.c b/kernel/bpf/percpu_freelist.c
>>> index b6e7f5c5b9ab..bd60070c079f 100644
>>> --- a/kernel/bpf/percpu_freelist.c
>>> +++ b/kernel/bpf/percpu_freelist.c
>>> @@ -100,22 +100,23 @@ 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, cpu_idx, 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();
>>> +
>>> +       cpu_idx = 0;
>>>
>>>          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 = min(n + (cpu_idx < m ? 1 : 0), nr_elems);
>>
>> why the min() here?
>>
> 
> to avoid out-of-bounds in case nr_elems is less than the total number of CPUs,
> seems not very necessary, but the original code avoids this as well, I just kept
> the logic
> 

sorry, no out-of-bounds here, when nr_elems is less than the total number of CPUs,
j will be 0 when cpu_idx >= m, will post v4

>>> +               for (i = 0; i < j; i++) {
>>> +                       head = per_cpu_ptr(s->freelist, cpu);
>>> +                       /* No locking required as this is not visible yet. */
>>> +                       pcpu_freelist_push_node(head, buf);
>>> +                       buf += elem_size;
>>> +               }
>>> +               nr_elems -= j;
>>> +               cpu_idx++;
>>>          }
>>>   }
>>>
>>> -- 
>>> 2.30.2
>>>
>> .
> 
> 
> .

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ