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: <20230615013645.7297-1-liangchen.linux@gmail.com> <20230614212031.7e1b6893@kernel.org>
In-Reply-To: <20230614212031.7e1b6893@kernel.org>
From:   Ilias Apalodimas <ilias.apalodimas@linaro.org>
Date:   Thu, 15 Jun 2023 13:49:02 +0300
Message-ID: <CAC_iWjJACJY4T2moyO3cy1_e+t72KYnsux4DUUJ-4bV=5emT-Q@mail.gmail.com>
Subject: Re: [PATCH net-next] page pool: not return page to alloc cache during
 pool destruction
To:     Jakub Kicinski <kuba@kernel.org>
Cc:     Liang Chen <liangchen.linux@gmail.com>, hawk@kernel.org,
        netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
        davem@davemloft.net, edumazet@google.com, pabeni@redhat.com
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

Hi Jakub,

On Thu, 15 Jun 2023 at 07:20, Jakub Kicinski <kuba@kernel.org> wrote:
>
> On Thu, 15 Jun 2023 09:36:45 +0800 Liang Chen wrote:
> > When destroying a page pool, the alloc cache and recycle ring are emptied.
> > If there are inflight pages, the retry process will periodically check the
> > recycle ring for recently returned pages, but not the alloc cache (alloc
> > cache is only emptied once). As a result, any pages returned to the alloc
> > cache after the page pool destruction will be stuck there and cause the
> > retry process to continuously look for inflight pages and report warnings.
> >
> > To safeguard against this situation, any pages returning to the alloc cache
> > after pool destruction should be prevented.
>
> Let's hear from the page pool maintainers but I think the driver
> is supposed to prevent allocations while pool is getting destroyed.
> Perhaps we can add DEBUG_NET_WARN_ON_ONCE() for this condition to
> prevent wasting cycles in production builds?

Yes the driver is supposed to do that, but OTOH I generally prefer
APIs that don't allow people to shoot themselves in the foot.  IIRC
this check run in fast path only in XDP mode right?  If this doesn't
affect performance,  I don't have any objections.  Jesper was trying
to refactor the destruction path, perhaps there's something in this
that affects his code?

Thanks
/Ilias