[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAADnVQKzW0wuN3NfgCSqQKVqAVRdKVEYMyJg+SpH0ENKH6fnMA@mail.gmail.com>
Date: Tue, 7 Oct 2025 21:10:25 -0700
From: Alexei Starovoitov <alexei.starovoitov@...il.com>
To: Yafang Shao <laoar.shao@...il.com>
Cc: Andrew Morton <akpm@...ux-foundation.org>, David Hildenbrand <david@...hat.com>, ziy@...dia.com,
baolin.wang@...ux.alibaba.com, Lorenzo Stoakes <lorenzo.stoakes@...cle.com>,
Liam Howlett <Liam.Howlett@...cle.com>, npache@...hat.com, ryan.roberts@....com,
dev.jain@....com, Johannes Weiner <hannes@...xchg.org>, usamaarif642@...il.com,
gutierrez.asier@...wei-partners.com, Matthew Wilcox <willy@...radead.org>,
Alexei Starovoitov <ast@...nel.org>, Daniel Borkmann <daniel@...earbox.net>,
Andrii Nakryiko <andrii@...nel.org>, Amery Hung <ameryhung@...il.com>,
David Rientjes <rientjes@...gle.com>, Jonathan Corbet <corbet@....net>, 21cnbao@...il.com,
Shakeel Butt <shakeel.butt@...ux.dev>, Tejun Heo <tj@...nel.org>, lance.yang@...ux.dev,
Randy Dunlap <rdunlap@...radead.org>, bpf <bpf@...r.kernel.org>,
linux-mm <linux-mm@...ck.org>, "open list:DOCUMENTATION" <linux-doc@...r.kernel.org>,
LKML <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH v9 mm-new 03/11] mm: thp: add support for BPF based THP
order selection
On Tue, Oct 7, 2025 at 8:51 PM Yafang Shao <laoar.shao@...il.com> wrote:
>
> On Wed, Oct 8, 2025 at 11:25 AM Alexei Starovoitov
> <alexei.starovoitov@...il.com> wrote:
> >
> > On Tue, Oct 7, 2025 at 1:47 AM Yafang Shao <laoar.shao@...il.com> wrote:
> > > has shown that multiple attachments often introduce conflicts. This is
> > > precisely why system administrators prefer to manage BPF programs with
> > > a single manager—to avoid undefined behaviors from competing programs.
> >
> > I don't believe this a single bit.
>
> You should spend some time seeing how users are actually applying BPF
> in practice. Some information for you :
>
> https://github.com/bpfman/bpfman
> https://github.com/DataDog/ebpf-manager
> https://github.com/ccfos/huatuo
By seeing the above you learned the wrong lesson.
These orchestrators and many others were created because
we made mistakes in the kernel by not scoping the progs enough.
XDP is a prime example. It allows one program per netdev.
This was a massive mistake which we're still trying to fix.
> > hid-bpf initially went with fmod_ret approach, deleted the whole thing
> > and redesigned it with _scoped_ struct-ops.
>
> I see little value in embedding a bpf_thp_struct_ops into the
> task_struct. The benefits don't appear to justify the added
> complexity.
huh? where did I say that struct-ops should be embedded in task_struct ?
Powered by blists - more mailing lists