All of lore.kernel.org
 help / color / mirror / Atom feed
From: David Laight <david.laight.linux@gmail.com>
To: Pascal Kneuper <PKneuper@dspace.de>
Cc: kuba@kernel.org, andrew+netdev@lunn.ch, davem@davemloft.net,
	edumazet@google.com, pabeni@redhat.com,
	mcoquelin.stm32@gmail.com, alexandre.torgue@foss.st.com,
	rmk+kernel@armlinux.org.uk, maxime.chevallier@bootlin.com,
	0x1207@gmail.com, si.yanteng@linux.dev, larysa.zaremba@intel.com,
	aleksander.lobakin@intel.com, netdev@vger.kernel.org,
	linux-stm32@st-md-mailman.stormreply.com,
	linux-arm-kernel@lists.infradead.org,
	linux-kernel@vger.kernel.org, DBaldin@dspace.de
Subject: Re: [PATCH net v2] net: stmmac: restore NET_IP_ALIGN in the RX DMA offset
Date: Mon, 24 Aug 2026 15:23:12 +0100	[thread overview]
Message-ID: <20260824152312.3f6dd2b7@pumpkin> (raw)
In-Reply-To: <20260824125014.47862-1-PKneuper@dspace.de>

On Mon, 24 Aug 2026 14:50:14 +0200 (CEST)
Pascal Kneuper <PKneuper@dspace.de> wrote:

> Since the RX path was converted to zero-copy, the page pool page is handed
> to the stack directly as the skb head, and the offset the DMA engine writes
> at is what determines the alignment of the packet headers.
> 
> Before the conversion the payload was copied into an skb obtained from
> napi_alloc_skb(), which reserves NET_SKB_PAD + NET_IP_ALIGN. The
> conversion moved the headroom into stmmac_rx_offset() but did not carry
> over NET_IP_ALIGN, so on architectures where NET_IP_ALIGN is 2 the IP
> header now lands misaligned:
> 
>   64 (NET_SKB_PAD) + 14 (ethernet) + 20 (IP) = 98
> 
> Same for the XDP branch:
> 
>   256 (XDP_PACKET_HEADROOM) + 14 (ethernet) + 20 (IP) = 290
> 
> On ARM32 this is fatal, because ldm and ldrd trap on unaligned addresses
> even when CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS is set.

I suspect an alternative is mark the structure(s) as __packed
when CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS is set.
The compiler will then only use 'normal' memory instructions which
won't fault.
OTOH aligning the buffers is likely to be better.

David

> 
> Any received echo request panics the machine, e.g:
> 
>   Unhandled fault: alignment exception (0x001) at 0x81873062
>   Internal error: : 1 [#1] SMP ARM
>   Hardware name: Altera SOCFPGA Arria10
>   PC is at icmp_echo+0x38/0xa8
>   LR is at icmp_rcv+0x22c/0x370
>   Call trace:
>    icmp_echo from icmp_rcv+0x22c/0x370
>    icmp_rcv from ip_protocol_deliver_rcu+0x2c/0x224
>    ip_protocol_deliver_rcu from ip_local_deliver+0xc8/0x1a0
>    ip_local_deliver from ip_sublist_rcv_finish+0x3c/0x50
>    ip_sublist_rcv_finish from ip_list_rcv_finish+0x110/0x118
>    ip_list_rcv_finish from ip_list_rcv+0xc8/0xdc
>    ip_list_rcv from __netif_receive_skb_list_core+0x170/0x1c0
>    ...
>    napi_complete_done from stmmac_napi_poll_rx+0xcb0/0x1030
>   Code: e24dd068 e59020a0 e28dc010 e0822001 (e8920003)
>   Kernel panic - not syncing: Fatal exception in interrupt
> 
> The faulting instruction is the ldm of *icmp_hdr(skb) in icmp_echo().
> 
> Fix by adding NET_IP_ALIGN back to the RX offset, which restores the
> alignment the stack used to get.
> 
> Note that commit a955318fe67e ("stmmac: align RX buffers") made a similar
> change in 2021 and was reverted by commit 12d125b4574b ("stmmac: Revert
> "stmmac: align RX buffers"") because it caused packet corruption. That
> patch raised the offset from 0 without adjusting the buffer size
> accounting, so the DMA engine could arguably write past the end of the RX
> buffers, though this was never root caused.
> Commit df542f669307 ("net: stmmac: Switch to zero-copy in non-XDP RX
> path") since derives the page pool allocation from stmmac_rx_offset(), so
> the extra bytes are accounted for.
> 
> Fixes: df542f669307 ("net: stmmac: Switch to zero-copy in non-XDP RX path")
> Cc: Daniel Baldin <DBaldin@dspace.de>
> Assisted-by: GitHub-Copilot-CLI:claude-opus-5
> Signed-off-by: Pascal Kneuper <PKneuper@dspace.de>
> ---
> v2:
>  - also add NET_IP_ALIGN to the XDP branch, reproduced the same panic
>    with an XDP_PASS program attached (Jakub Kicinski)
>  - retitle accordingly, v1 was non-XDP only
> 
>  drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 4 ++--
>  1 file changed, 2 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
> index a71f0df263785..4d4b155d0d931 100644
> --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
> +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
> @@ -1527,9 +1527,9 @@ static void stmmac_display_rings(struct stmmac_priv *priv,
>  static unsigned int stmmac_rx_offset(struct stmmac_priv *priv)
>  {
>  	if (stmmac_xdp_is_enabled(priv))
> -		return XDP_PACKET_HEADROOM;
> +		return XDP_PACKET_HEADROOM + NET_IP_ALIGN;
>  
> -	return NET_SKB_PAD;
> +	return NET_SKB_PAD + NET_IP_ALIGN;
>  }
>  
>  static int stmmac_set_bfsize(int mtu)



  reply	other threads:[~2026-08-24 14:23 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-08-13  9:29 [PATCH net] net: stmmac: restore NET_IP_ALIGN in the non-XDP RX path Pascal Kneuper
2026-08-18  1:22 ` Jakub Kicinski
2026-08-24 12:13   ` Pascal Kneuper
2026-08-24 12:50 ` [PATCH net v2] net: stmmac: restore NET_IP_ALIGN in the RX DMA offset Pascal Kneuper
2026-08-24 14:23   ` David Laight [this message]
2026-08-27 19:40   ` patchwork-bot+netdevbpf
2026-09-08  8:16   ` Maxime Chevallier
     [not found]     ` <5aeb6fd1-f1c3-426d-a2c4-1ad45ddc8572@bootlin.com>
2026-09-09  8:57       ` Pascal Kneuper

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260824152312.3f6dd2b7@pumpkin \
    --to=david.laight.linux@gmail.com \
    --cc=0x1207@gmail.com \
    --cc=DBaldin@dspace.de \
    --cc=PKneuper@dspace.de \
    --cc=aleksander.lobakin@intel.com \
    --cc=alexandre.torgue@foss.st.com \
    --cc=andrew+netdev@lunn.ch \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=kuba@kernel.org \
    --cc=larysa.zaremba@intel.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-stm32@st-md-mailman.stormreply.com \
    --cc=maxime.chevallier@bootlin.com \
    --cc=mcoquelin.stm32@gmail.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=rmk+kernel@armlinux.org.uk \
    --cc=si.yanteng@linux.dev \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.