Re: [PATCH] net: phy: avoid undefined behavior in *_led_polarity_set()

[Andrew Lunn <andrew@lunn.ch>]

On Tue, Dec 17, 2024 at 09:10:34AM +0100, Arnd Bergmann wrote:
> From: Arnd Bergmann <arnd@arndb.de>
> 
> gcc runs into undefined behavior at the end of the three led_polarity_set()
> callback functions if it were called with a zero 'modes' argument and it
> just ends the function there without returning from it.
> 
> This gets flagged by 'objtool' as a function that continues on
> to the next one:
> 
> drivers/net/phy/aquantia/aquantia_leds.o: warning: objtool: aqr_phy_led_polarity_set+0xf: can't find jump dest instruction at .text+0x5d9
> drivers/net/phy/intel-xway.o: warning: objtool: xway_gphy_led_polarity_set() falls through to next function xway_gphy_config_init()
> drivers/net/phy/mxl-gpy.o: warning: objtool: gpy_led_polarity_set() falls through to next function gpy_led_hw_control_get()
> 
> There is no point to micro-optimize the behavior here to save a single-digit
> number of bytes in the kernel, so just change this to a "return -EINVAL"
> as we do when any unexpected bits are set.
> 
> Fixes: 1758af47b98c ("net: phy: intel-xway: add support for PHY LEDs")
> Fixes: 9d55e68b19f2 ("net: phy: aquantia: correctly describe LED polarity override")
> Fixes: eb89c79c1b8f ("net: phy: mxl-gpy: correctly describe LED polarity")
> Signed-off-by: Arnd Bergmann <arnd@arndb.de>

Reviewed-by: Andrew Lunn <andrew@lunn.ch>

    Andrew