RE: [PATCH RFC] pwm: keembay: Fix build failure with -Os

From: Ayyathurai, Vijayakannan
Date: Tue Nov 17 2020 - 12:29:17 EST


Hi Uwe,

> From: Uwe Kleine-König <u.kleine-koenig@xxxxxxxxxxxxxx>
> Sent: Monday, 16 November, 2020 5:08 PM
> Subject: [PATCH RFC] pwm: keembay: Fix build failure with -Os
>
> The driver used this construct:
>
> #define KMB_PWM_LEADIN_MASK GENMASK(30, 0)
>
> static inline void keembay_pwm_update_bits(struct keembay_pwm
> *priv, u32 mask,
> u32 val, u32 offset)
> {
> u32 buff = readl(priv->base + offset);
>
> buff = u32_replace_bits(buff, val, mask);
> writel(buff, priv->base + offset);
> }
>
> ...
> keembay_pwm_update_bits(priv, KMB_PWM_LEADIN_MASK, 0,
> KMB_PWM_LEADIN_OFFSET(pwm-
> >hwpwm));
>
> With CONFIG_CC_OPTIMIZE_FOR_SIZE the compiler (here: gcc 10.2.0) this
> triggers:
>
> In file included from /home/uwe/gsrc/linux/drivers/pwm/pwm-
> keembay.c:16:
> In function ‘field_multiplier’,
> inlined from ‘keembay_pwm_update_bits’ at
> /home/uwe/gsrc/linux/include/linux/bitfield.h:124:17:
> /home/uwe/gsrc/linux/include/linux/bitfield.h:119:3: error: call to
> ‘__bad_mask’ declared with attribute error: bad bitfield mask
> 119 | __bad_mask();
> | ^~~~~~~~~~~~
> In function ‘field_multiplier’,
> inlined from ‘keembay_pwm_update_bits’ at
> /home/uwe/gsrc/linux/include/linux/bitfield.h:154:1:
> /home/uwe/gsrc/linux/include/linux/bitfield.h:119:3: error: call to
> ‘__bad_mask’ declared with attribute error: bad bitfield mask
> 119 | __bad_mask();
> | ^~~~~~~~~~~~
>
> The compiler doesn't seem to be able to notice that with field being
> 0x3ffffff the expression
>
> if ((field | (field - 1)) & ((field | (field - 1)) + 1))
> __bad_mask();
>
> can be optimized away.
>
> So use __always_inline and document the problem in a comment to fix
> this.
>
> Reported-by: kernel test robot <lkp@xxxxxxxxx>
> Signed-off-by: Uwe Kleine-König <u.kleine-koenig@xxxxxxxxxxxxxx>

Thank you for spending time in resolving this build failure.

I shall prepare and share the next version of patch with your approach.

> ---
> Hello,
>
> I'm not sure this is the right fix. Maybe the bitfield stuff can be
> changed somehow to make this problem go away, too?
>
> Best regards
> Uwe
>
> drivers/pwm/pwm-keembay.c | 7 ++++++-
> 1 file changed, 6 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/pwm/pwm-keembay.c b/drivers/pwm/pwm-keembay.c
> index 2b6dd070daa4..cdfdef66ff8e 100644
> --- a/drivers/pwm/pwm-keembay.c
> +++ b/drivers/pwm/pwm-keembay.c
> @@ -63,7 +63,12 @@ static int keembay_clk_enable(struct device *dev,
> struct clk *clk)
> return devm_add_action_or_reset(dev, keembay_clk_unprepare, clk);
> }
>
> -static inline void keembay_pwm_update_bits(struct keembay_pwm *priv, u32
> mask,
> +/*
> + * With gcc 10, CONFIG_CC_OPTIMIZE_FOR_SIZE and only "inline" instead of
> + * "__always_inline" this fails to compile because the compiler doesn't notice
> + * for all valid masks (e.g. KMB_PWM_LEADIN_MASK) that they are ok.
> + */
> +static __always_inline void keembay_pwm_update_bits(struct
> keembay_pwm *priv, u32 mask,
> u32 val, u32 offset)
> {
> u32 buff = readl(priv->base + offset);
> --
> 2.28.0

Thanks,
Vijay