Devicetree
 help / color / mirror / Atom feed
From: sashiko-bot@kernel.org
To: "Wei Fang" <wei.fang@nxp.com>
Cc: Frank.Li@kernel.org, devicetree@vger.kernel.org, robh@kernel.org,
	imx@lists.linux.dev, conor+dt@kernel.org
Subject: Re: [PATCH v8 net-next 12/15] net: dsa: netc: add FDB, STP, MTU, port setup and host flooding support
Date: Tue, 19 May 2026 08:25:38 +0000	[thread overview]
Message-ID: <20260519082538.B0919C2BCC6@smtp.kernel.org> (raw)
In-Reply-To: <20260518082506.1318236-13-wei.fang@nxp.com>

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Medium] Stack-allocated byte arrays passed to ether_addr_copy() and ether_addr_equal() may not be 16-bit aligned, risking alignment faults.
--

commit eaa86c7415fcd30cddae2cda4bd6d4ca21da6e88
Author: Wei Fang <wei.fang@nxp.com>
Subject: net: dsa: netc: add FDB, STP, MTU, port setup and host flooding support

This commit expands the NETC switch driver with foundational features
including FDB, MDB, STP state handling, MTU configuration, and host
flooding support. The driver currently operates in standalone port mode.

> diff --git a/drivers/net/dsa/netc/netc_main.c b/drivers/net/dsa/netc/netc_main.c
> index 2141b3aa96b7a..9dcaa04d9a65e 100644
> --- a/drivers/net/dsa/netc/netc_main.c
> +++ b/drivers/net/dsa/netc/netc_main.c
[ ... ]
> @@ -367,6 +422,220 @@ static void netc_port_default_config(struct netc_port *np)
[ ... ]
> +static int netc_add_standalone_fdb_bcast_entry(struct netc_switch *priv)
> +{
> +	const u8 bcast[ETH_ALEN] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};

Since stack-allocated byte arrays are only guaranteed to be 1-byte aligned,
could this cause an unaligned access fault on architectures that trap on
strict alignment?

Looking at netc_port_set_fdb_entry(), this pointer is eventually passed to
netc_lookup_fdb_entry() which calls ether_addr_equal(), and to
netc_port_add_fdb_entry() which calls ether_addr_copy(). Both of these
helpers require their arguments to be at least 16-bit aligned.

Should this array be marked with __aligned(2), or could the code use
eth_broadcast_addr() instead?

[ ... ]
> +static int netc_port_add_host_flood_rule(struct netc_port *np,
> +					 bool uc, bool mc)
> +{
> +	const u8 dmac_mask[ETH_ALEN] = {0x1, 0, 0, 0, 0, 0};

Similarly, does this dmac_mask array need explicit 16-bit alignment?

It is passed directly to ether_addr_copy() below, which has the same 16-bit
alignment requirement:

> +	if (uc && !mc)
> +		ether_addr_copy(keye->dmac_mask, dmac_mask);
> +
> +	if (!uc && mc) {
> +		ether_addr_copy(keye->dmac, dmac_mask);
> +		ether_addr_copy(keye->dmac_mask, dmac_mask);
> +	}
[ ... ]

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260518082506.1318236-1-wei.fang@nxp.com?part=12

  reply	other threads:[~2026-05-19  8:25 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-05-18  8:24 [PATCH v8 net-next 00/15] Add preliminary NETC switch support for i.MX94 Wei Fang
2026-05-18  8:24 ` [PATCH v8 net-next 01/15] dt-bindings: net: dsa: update the description of 'dsa,member' property Wei Fang
2026-05-18  8:24 ` [PATCH v8 net-next 02/15] dt-bindings: net: dsa: add NETC switch Wei Fang
2026-05-19  8:25   ` sashiko-bot
2026-05-18  8:24 ` [PATCH v8 net-next 03/15] net: enetc: add pre-boot initialization for i.MX94 switch Wei Fang
2026-05-18  8:24 ` [PATCH v8 net-next 04/15] net: enetc: add basic operations to the FDB table Wei Fang
2026-05-18  8:24 ` [PATCH v8 net-next 05/15] net: enetc: add support for the "Add" operation to VLAN filter table Wei Fang
2026-05-18  8:24 ` [PATCH v8 net-next 06/15] net: enetc: add support for the "Update" operation to buffer pool table Wei Fang
2026-05-18  8:24 ` [PATCH v8 net-next 07/15] net: enetc: add support for "Add" and "Delete" operations to IPFT Wei Fang
2026-05-18  8:24 ` [PATCH v8 net-next 08/15] net: enetc: add multiple command BD rings support Wei Fang
2026-05-18  8:25 ` [PATCH v8 net-next 09/15] net: dsa: add NETC switch tag support Wei Fang
2026-05-19  8:25   ` sashiko-bot
2026-05-19  9:23     ` Wei Fang
2026-05-18  8:25 ` [PATCH v8 net-next 10/15] net: dsa: netc: introduce NXP NETC switch driver for i.MX94 Wei Fang
2026-05-19  8:25   ` sashiko-bot
2026-05-19  9:34     ` Wei Fang
2026-05-18  8:25 ` [PATCH v8 net-next 11/15] net: dsa: netc: add phylink MAC operations Wei Fang
2026-05-19  8:25   ` sashiko-bot
2026-05-19 10:00     ` Wei Fang
2026-05-18  8:25 ` [PATCH v8 net-next 12/15] net: dsa: netc: add FDB, STP, MTU, port setup and host flooding support Wei Fang
2026-05-19  8:25   ` sashiko-bot [this message]
2026-05-19  9:42     ` Wei Fang
2026-05-18  8:25 ` [PATCH v8 net-next 13/15] net: dsa: netc: initialize buffer pool table and implement flow-control Wei Fang
2026-05-18  8:25 ` [PATCH v8 net-next 14/15] net: dsa: netc: add support for the standardized counters Wei Fang
2026-05-19  8:25   ` sashiko-bot
2026-05-19 10:08     ` Wei Fang
2026-05-18  8:25 ` [PATCH v8 net-next 15/15] net: dsa: netc: add support for ethtool private statistics Wei Fang
2026-05-19  8:25   ` sashiko-bot
2026-05-19 10:07     ` Wei Fang

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=20260519082538.B0919C2BCC6@smtp.kernel.org \
    --to=sashiko-bot@kernel.org \
    --cc=Frank.Li@kernel.org \
    --cc=conor+dt@kernel.org \
    --cc=devicetree@vger.kernel.org \
    --cc=imx@lists.linux.dev \
    --cc=robh@kernel.org \
    --cc=sashiko-reviews@lists.linux.dev \
    --cc=wei.fang@nxp.com \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox