Linux-PHY Archive on lore.kernel.org

* Re: [PATCH v12 28/36] phy: rockchip: usbdp: Only enable USB3 when not in high-speed mode
From: sashiko-bot @ 2026-07-10 21:26 UTC (permalink / raw)
  To: Sebastian Reichel
  Cc: robh, conor+dt, linux-phy, vkoul, devicetree, neil.armstrong,
	olteanv
In-Reply-To: <20260710-rockchip-usbdp-cleanup-v12-28-8b41a9a9bef0@collabora.com>

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:

Pre-existing issues:
- [High] rk_udphy_power_on returns 0 (success) for unsupported modes, tricking callers into accessing unclocked PHY registers
--

--- Patch [28]: [PATCH v12 28/36] phy: rockchip: usbdp: Only enable USB3 when not in high-speed mode ---
commit fac8dba407b679ba8fc75d417de958451d90f46f
Author: Sebastian Reichel <sebastian.reichel@collabora.com>

phy: rockchip: usbdp: Only enable USB3 when not in high-speed mode

Ensure that USB3 mode is not accidently enabled during PHY re-init
for systems that are configured as high-speed only via DT.

Closes: https://sashiko.dev/#/message/20260626212424.C215E1F000E9%40smtp.kernel.org

> diff --git a/drivers/phy/rockchip/phy-rockchip-usbdp.c b/drivers/phy/rockchip/phy-rockchip-usbdp.c
> index 2099ae2e51d1c..af915cc377275 100644
> --- a/drivers/phy/rockchip/phy-rockchip-usbdp.c
> +++ b/drivers/phy/rockchip/phy-rockchip-usbdp.c
> @@ -1009,7 +1009,7 @@ static int rk_udphy_power_on(struct rk_udphy *udphy, u8 mode)
>  		if (ret)
>  			return ret;
>  

[Severity: High]
This is a pre-existing issue, but I noticed a potential problem in how
rk_udphy_power_on() handles unsupported modes.

At the beginning of rk_udphy_power_on(), if the hardware isn't configured
for the requested mode, the function logs an info message and returns 0:

	if (!(udphy->mode & mode)) {
		dev_info(udphy->dev, "mode 0x%02x is not support\n", mode);
		return 0;
	}

Because it returns success, callers might assume the PHY was successfully
powered up and clocked. For example, if we look at rk_udphy_dp_phy_power_on():

	ret = rk_udphy_power_on(udphy, UDPHY_MODE_DP);
	if (ret)
		return ret;

	rk_udphy_dp_lane_enable(udphy, udphy->dp_lanes);

If UDPHY_MODE_DP is requested but not supported (for instance, if the
device tree configures it as USB-only), rk_udphy_power_on() will skip
the setup sequence and return 0.

Would the caller then proceed to access unclocked memory-mapped registers
in rk_udphy_dp_lane_enable() and trigger a kernel panic (SError)?

Should rk_udphy_power_on() return an error code like -EOPNOTSUPP instead
of 0 when an unsupported mode is requested?

> -		if (udphy->mode & UDPHY_MODE_USB)
> +		if (!udphy->hs && udphy->mode & UDPHY_MODE_USB)
>  			rk_udphy_u3_port_disable(udphy, false);
>  		udphy->phy_needs_reinit = false;
>  	} else if (udphy->phy_needs_reinit) {

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260710-rockchip-usbdp-cleanup-v12-0-8b41a9a9bef0@collabora.com?part=28

-- 
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy

^ permalink raw reply