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: <20220722174829.3422466-1-yosryahmed@google.com>
 <20220722174829.3422466-5-yosryahmed@google.com> <CAP01T76p7CCj2i4X7PmZiG3G3-Bfx_ygnO0Eg+DnfwLHQiEPbA@mail.gmail.com>
 <CA+khW7g2kriOb7on0u_UpGpS2A0bftrQowTB0+AJ=S7rpLKaZA@mail.gmail.com> <639f575e-bc8c-46b9-b21b-bd9fbba835c1@fb.com>
In-Reply-To: <639f575e-bc8c-46b9-b21b-bd9fbba835c1@fb.com>
From:   Hao Luo <haoluo@google.com>
Date:   Thu, 28 Jul 2022 10:26:32 -0700
Message-ID: <CA+khW7gws1+bWQ2zpodVfAP_rtXv=8K3SSMLx4e9Lh4eKgtnmA@mail.gmail.com>
Subject: Re: [PATCH bpf-next v5 4/8] bpf: Introduce cgroup iter
To:     Yonghong Song <yhs@fb.com>
Cc:     Kumar Kartikeya Dwivedi <memxor@gmail.com>,
        Yosry Ahmed <yosryahmed@google.com>,
        Alexei Starovoitov <ast@kernel.org>,
        Daniel Borkmann <daniel@iogearbox.net>,
        Andrii Nakryiko <andrii@kernel.org>,
        Martin KaFai Lau <kafai@fb.com>,
        Song Liu <songliubraving@fb.com>, Tejun Heo <tj@kernel.org>,
        Zefan Li <lizefan.x@bytedance.com>,
        Johannes Weiner <hannes@cmpxchg.org>,
        Shuah Khan <shuah@kernel.org>,
        Michal Hocko <mhocko@kernel.org>,
        KP Singh <kpsingh@kernel.org>,
        Benjamin Tissoires <benjamin.tissoires@redhat.com>,
        John Fastabend <john.fastabend@gmail.com>,
        =?UTF-8?Q?Michal_Koutn=C3=BD?= <mkoutny@suse.com>,
        Roman Gushchin <roman.gushchin@linux.dev>,
        David Rientjes <rientjes@google.com>,
        Stanislav Fomichev <sdf@google.com>,
        Greg Thelen <gthelen@google.com>,
        Shakeel Butt <shakeelb@google.com>,
        linux-kernel@vger.kernel.org, netdev@vger.kernel.org,
        bpf@vger.kernel.org, cgroups@vger.kernel.org
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

On Wed, Jul 27, 2022 at 11:56 PM Yonghong Song <yhs@fb.com> wrote:
>
>
>
> On 7/22/22 1:33 PM, Hao Luo wrote:
> > On Fri, Jul 22, 2022 at 11:36 AM Kumar Kartikeya Dwivedi
> > <memxor@gmail.com> wrote:
> >>
> >> On Fri, 22 Jul 2022 at 19:52, Yosry Ahmed <yosryahmed@google.com> wrote:
<...>
> >>> +
> >>> +static int __cgroup_iter_seq_show(struct seq_file *seq,
> >>> +                                 struct cgroup_subsys_state *css, int in_stop);
> >>> +
> >>> +static void cgroup_iter_seq_stop(struct seq_file *seq, void *v)
> >>> +{
> >>> +       /* pass NULL to the prog for post-processing */
> >>> +       if (!v)
> >>> +               __cgroup_iter_seq_show(seq, NULL, true);
> >>> +       mutex_unlock(&cgroup_mutex);
> >>
> >> I'm just curious, but would it be a good optimization (maybe in a
> >> follow up) to move this mutex_unlock before the check on v? That
> >> allows you to store/buffer some info you want to print as a compressed
> >> struct in a map, then write the full text to the seq_file outside the
> >> cgroup_mutex lock in the post-processing invocation.
> >>
> >> It probably also allows you to walk the whole hierarchy, if one
> >> doesn't want to run into seq_file buffer limit (or it can decide what
> >> to print within the limit in the post processing invocation), or it
> >> can use some out of band way (ringbuf, hashmap, etc.) to send the data
> >> to userspace. But all of this can happen without holding cgroup_mutex
> >> lock.
> >
> > Thanks Kumar.
> >
> > It sounds like an idea, but the key thing is not about moving
> > cgroup_mutex unlock before the check IMHO. The user can achieve
> > compression using the current infra. Compression could actually be
> > done in the bpf program. user can define and output binary content and
> > implement a userspace library to parse/decompress when reading out the
> > data.
>
> Right mutex_unlock() can be moved to the beginning of the
> function since the cgroup is not used in
>    __cgroup_iter_seq_show(seq, NULL, true)

Ok. Will do.