Re: [PATCH net-next] stmmac: align RX buffers

From: Matteo Croce <mcroce@linux.microsoft.com>
To: Marc Zyngier <maz@kernel.org>
Cc: Eric Dumazet <eric.dumazet@gmail.com>,
	Thierry Reding <thierry.reding@gmail.com>,
	netdev@vger.kernel.org,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
	linux-riscv <linux-riscv@lists.infradead.org>,
	Giuseppe Cavallaro <peppe.cavallaro@st.com>,
	Alexandre Torgue <alexandre.torgue@foss.st.com>,
	"David S. Miller" <davem@davemloft.net>,
	Jakub Kicinski <kuba@kernel.org>,
	Palmer Dabbelt <palmer@dabbelt.com>,
	Paul Walmsley <paul.walmsley@sifive.com>,
	Drew Fustini <drew@beagleboard.org>,
	Emil Renner Berthing <kernel@esmil.dk>,
	Jon Hunter <jonathanh@nvidia.com>, Will Deacon <will@kernel.org>
Subject: Re: [PATCH net-next] stmmac: align RX buffers
Date: Fri, 20 Aug 2021 18:38:14 +0200	[thread overview]
Message-ID: <CAFnufp2T75cvDLUx+ZyPQbkaNeY_S1OJ7KTJe=2EK-qXRNkwyw@mail.gmail.com> (raw)
In-Reply-To: <87fsv4qdzm.wl-maz@kernel.org>

On Fri, Aug 20, 2021 at 6:26 PM Marc Zyngier <maz@kernel.org> wrote:
>
> On Fri, 20 Aug 2021 11:37:03 +0100,
> Matteo Croce <mcroce@linux.microsoft.com> wrote:
> >
> > On Thu, Aug 19, 2021 at 6:29 PM Marc Zyngier <maz@kernel.org> wrote:
>
> [...]
>
> > > diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
> > > index fcdb1d20389b..244aa6579ef4 100644
> > > --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
> > > +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
> > > @@ -341,7 +341,7 @@ static inline unsigned int stmmac_rx_offset(struct stmmac_priv *priv)
> > >         if (stmmac_xdp_is_enabled(priv))
> > >                 return XDP_PACKET_HEADROOM + NET_IP_ALIGN;
> > >
> > > -       return NET_SKB_PAD + NET_IP_ALIGN;
> > > +       return 8 + NET_IP_ALIGN;
> > >  }
> > >
> > >  void stmmac_disable_rx_queue(struct stmmac_priv *priv, u32 queue);
> > >
> > > I don't see the system corrupting packets anymore. Is that exactly
> > > what you had in mind? This really seems to point to a basic buffer
> > > overflow.
>
> [...]
>
> > Sorry, I meant something like:
> >
> > -       return NET_SKB_PAD + NET_IP_ALIGN;
> > +       return 8;
> >
> > I had some hardware which DMA fails if the receive buffer was not word
> > aligned, but this seems not the case, as 8 + NET_IP_ALIGN = 10, and
> > it's not aligned too.
>
> No error in that case either, as expected. Given that NET_SKB_PAD is
> likely to expand to 64, it is likely a DMA buffer overflow which
> probably only triggers for large-ish packets.
>
> Now, we're almost at -rc7, and we don't have a solution in sight.
>
> Can we please revert this until we have an understanding of what is
> happening? I'll hopefully have more cycles to work on the issue once
> 5.14 is out, and hopefully the maintainers of this driver can chime in
> (they have been pretty quiet so far).
>
> Thanks,
>
>         M.
>
> --
> Without deviation from the norm, progress is not possible.

Last try, what about adding only NET_IP_ALIGN and leaving NET_SKB_PAD?

-       return NET_SKB_PAD + NET_IP_ALIGN;
+       return NET_IP_ALIGN;

I think that alloc_skb adds another NET_SKB_PAD anyway.

-- 
per aspera ad upstream