Re: [PATCH v8 2/3] pwm: Add Allwinner's D1/T113-S3/R329 SoCs PWM support

[Uwe Kleine-König]

hello Aleksandr,

On Wed, Jan 31, 2024 at 03:59:15PM +0300, Aleksandr Shubin wrote:
> +#include <linux/bitfield.h>
> +#include <linux/clk.h>
> +#include <linux/err.h>
> +#include <linux/io.h>
> +#include <linux/module.h>
> +#include <linux/of_device.h>

Some time ago there was some effort by Rob Herring to detangle the
headers platform_device.h, of_device.h and of.h. See for example commit
87e51b76c9db8c29cde573af0faf5a3e13e23960. I think you should use
linux/of.h instead of linux/of_device.h.

> +#include <linux/platform_device.h>
> +#include <linux/pwm.h>
> +#include <linux/reset.h>
> +
> +#define SUN20I_PWM_CLK_CFG(chan)		(0x20 + (((chan) >> 1) * 0x4))
> +#define SUN20I_PWM_CLK_CFG_SRC			GENMASK(8, 7)
> +#define SUN20I_PWM_CLK_CFG_DIV_M		GENMASK(3, 0)
> +#define SUN20I_PWM_CLK_DIV_M_MAX		8

SUN20I_PWM_CLK_CFG_DIV_M_MAX?

> +#define SUN20I_PWM_CLK_GATE			0x40
> +#define SUN20I_PWM_CLK_GATE_BYPASS(chan)	BIT((chan) + 16)
> +#define SUN20I_PWM_CLK_GATE_GATING(chan)	BIT(chan)
> +
> +#define SUN20I_PWM_ENABLE			0x80
> +#define SUN20I_PWM_ENABLE_EN(chan)		BIT(chan)
> +
> +#define SUN20I_PWM_CTL(chan)			(0x100 + (chan) * 0x20)
> +#define SUN20I_PWM_CTL_ACT_STA			BIT(8)
> +#define UN20I_PWM_CTL_PRESCAL_K		GENMASK(7, 0)
> +#define SUN20I_PWM_CTL_PRESCAL_K_MAX		0xff

This matches the theoretical maximum for GENMASK(7,0), so you could make
use of field_max(SUN20I_PWM_CTL_PRESCAL_K) here.

> +#define SUN20I_PWM_PERIOD(chan)			(0x104 + (chan) * 0x20)
> +#define SUN20I_PWM_PERIOD_ENTIRE_CYCLE		GENMASK(31, 16)
> +#define SUN20I_PWM_PERIOD_ACT_CYCLE		GENMASK(15, 0)
> +
> +#define SUN20I_PWM_PCNTR_SIZE			BIT(16)
> +
> +/**
> + * SUN20I_PWM_MAGIC is used to quickly compute the values of the clock dividers
> + * div_m (SUN20I_PWM_CLK_CFG_DIV_M) & prescale_k (SUN20I_PWM_CTL_PRESCAL_K)
> + * without using a loop. These dividers limit the # of cycles in a period
> + * to SUN20I_PWM_PCNTR_SIZE by applying a scaling factor of
> + * 1/(div_m * (prescale_k + 1)) to the clock source.
> + *
> + * SUN20I_PWM_MAGIC is derived by solving for div_m and prescale_k
> + * such that for a given requested period,
> + *
> + * i) div_m is minimized for any prescale_k ≤ SUN20I_PWM_CTL_PRESCAL_K_MAX,
> + * ii) prescale_k is minimized.
> + *
> + * The derivation proceeds as follows, with val = # of cycles for reqested

s/reqested/requested/

> + * period:
> + *
> + * for a given value of div_m we want the smallest prescale_k such that
> + *
> + * (val >> div_m) // (prescale_k + 1) ≤ 65536 (SUN20I_PWM_PCNTR_SIZE)
> + *
> + * This is equivalent to:
> + *
> + * (val >> div_m) ≤ 65536 * (prescale_k + 1) + prescale_k
> + * ⟺ (val >> div_m) ≤ 65537 * prescale_k + 65536
> + * ⟺ (val >> div_m) - 65536 ≤ 65537 * prescale_k
> + * ⟺ ((val >> div_m) - 65536) / 65537 ≤ prescale_k
> + *
> + * As prescale_k is integer, this becomes
> + *
> + * ((val >> div_m) - 65536) // 65537 ≤ prescale_k
> + *
> + * And is minimized at
> + *
> + * ((val >> div_m) - 65536) // 65537
> + *
> + * Now we pick the smallest div_m that satifies prescale_k ≤ 255
> + * (i.e SUN20I_PWM_CTL_PRESCAL_K_MAX),
> + *
> + * ((val >> div_m) - 65536) // 65537 ≤ 255
> + * ⟺ (val >> div_m) - 65536 ≤ 255 * 65537 + 65536
> + * ⟺ val >> div_m ≤ 255 * 65537 + 2 * 65536
> + * ⟺ val >> div_m < (255 * 65537 + 2 * 65536 + 1)
> + * ⟺ div_m = fls((val) / (255 * 65537 + 2 * 65536 + 1))
> + *
> + * Suggested by Uwe Kleine-König

Good man, I assume this is all sane then :-)

> + */
> +#define SUN20I_PWM_MAGIC			(255 * 65537 + 2 * 65536 + 1)
> +
> +struct sun20i_pwm_chip {
> +	struct clk *clk_bus, *clk_hosc, *clk_apb0;
> +	struct reset_control *rst;
> +	struct pwm_chip chip;
> +	void __iomem *base;
> +	/* Mutex to protect pwm apply state */
> +	struct mutex mutex;
> +};
> +
> +static inline struct sun20i_pwm_chip *to_sun20i_pwm_chip(struct pwm_chip *chip)
> +{
> +	return container_of(chip, struct sun20i_pwm_chip, chip);
> +}
> +
> +static inline u32 sun20i_pwm_readl(struct sun20i_pwm_chip *chip,
> +				   unsigned long offset)
> +{
> +	return readl(chip->base + offset);
> +}
> +
> +static inline void sun20i_pwm_writel(struct sun20i_pwm_chip *chip,
> +				     u32 val, unsigned long offset)
> +{
> +	writel(val, chip->base + offset);
> +}
> +
> +static int sun20i_pwm_get_state(struct pwm_chip *chip,
> +				struct pwm_device *pwm,
> +				struct pwm_state *state)
> +{
> +	struct sun20i_pwm_chip *sun20i_chip = to_sun20i_pwm_chip(chip);
> +	u16 ent_cycle, act_cycle, prescale_k;
> +	u64 clk_rate, tmp;
> +	u8 div_m;
> +	u32 val;
> +
> +	mutex_lock(&sun20i_chip->mutex);
> +
> +	val = sun20i_pwm_readl(sun20i_chip, SUN20I_PWM_CLK_CFG(pwm->hwpwm));
> +	div_m = FIELD_GET(SUN20I_PWM_CLK_CFG_DIV_M, val);
> +	if (div_m > SUN20I_PWM_CLK_DIV_M_MAX)
> +		div_m = SUN20I_PWM_CLK_DIV_M_MAX;
> +
> +	if (FIELD_GET(SUN20I_PWM_CLK_CFG_SRC, val) == 0)
> +		clk_rate = clk_get_rate(sun20i_chip->clk_hosc);
> +	else
> +		clk_rate = clk_get_rate(sun20i_chip->clk_apb0);
> +
> +	val = sun20i_pwm_readl(sun20i_chip, SUN20I_PWM_CTL(pwm->hwpwm));
> +	state->polarity = (SUN20I_PWM_CTL_ACT_STA & val) ?
> +			   PWM_POLARITY_NORMAL : PWM_POLARITY_INVERSED;
> +
> +	prescale_k = FIELD_GET(SUN20I_PWM_CTL_PRESCAL_K, val) + 1;
> +
> +	val = sun20i_pwm_readl(sun20i_chip, SUN20I_PWM_ENABLE);
> +	state->enabled = (SUN20I_PWM_ENABLE_EN(pwm->hwpwm) & val) ? true : false;
> +
> +	val = sun20i_pwm_readl(sun20i_chip, SUN20I_PWM_PERIOD(pwm->hwpwm));
> +
> +	mutex_unlock(&sun20i_chip->mutex);
> +
> +	act_cycle = FIELD_GET(SUN20I_PWM_PERIOD_ACT_CYCLE, val);
> +	ent_cycle = FIELD_GET(SUN20I_PWM_PERIOD_ENTIRE_CYCLE, val);
> +
> +	/*
> +	 * The duration of the active phase should not be longer
> +	 * than the duration of the period
> +	 */
> +	if (act_cycle > ent_cycle)
> +		act_cycle = ent_cycle;
> +
> +	tmp = ((u64)(act_cycle) * prescale_k << div_m) * NSEC_PER_SEC;
> +	state->duty_cycle = DIV_ROUND_UP_ULL(tmp, clk_rate);
> +	tmp = ((u64)(ent_cycle) * prescale_k << div_m) * NSEC_PER_SEC;
> +	state->period = DIV_ROUND_UP_ULL(tmp, clk_rate);

Please add a comment above this block that justifies assuming that the
multiplication doesn't overflow. Something like:

	We have act_cycle <= ent_cycle <= 0xffff, prescale_k <= 0x100,
	div_m <= 8. So the multiplication fits into an u64 without
	overflow.

> +
> +	return 0;
> +}
> +
> +static int sun20i_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
> +			    const struct pwm_state *state)
> +{
> +...
> +}

I didn't recheck all the logic in .apply in detail and will assume it is
sane for this round.

> +static const struct pwm_ops sun20i_pwm_ops = {
> +	.apply = sun20i_pwm_apply,
> +	.get_state = sun20i_pwm_get_state,
> +};
> +
> +static const struct of_device_id sun20i_pwm_dt_ids[] = {
> +	{ .compatible = "allwinner,sun20i-d1-pwm" },
> +	{ },
> +};
> +MODULE_DEVICE_TABLE(of, sun20i_pwm_dt_ids);
> +
> +static int sun20i_pwm_probe(struct platform_device *pdev)
> +{
> +	struct sun20i_pwm_chip *sun20i_chip;
> +	int ret;
> +
> +	sun20i_chip = devm_kzalloc(&pdev->dev, sizeof(*sun20i_chip), GFP_KERNEL);
> +	if (!sun20i_chip)
> +		return -ENOMEM;
> +
> +	sun20i_chip->base = devm_platform_ioremap_resource(pdev, 0);
> +	if (IS_ERR(sun20i_chip->base))
> +		return PTR_ERR(sun20i_chip->base);
> +
> +	sun20i_chip->clk_bus = devm_clk_get_enabled(&pdev->dev, "bus");
> +	if (IS_ERR(sun20i_chip->clk_bus))
> +		return dev_err_probe(&pdev->dev, PTR_ERR(sun20i_chip->clk_bus),
> +				     "failed to get bus clock\n");
> +
> +	sun20i_chip->clk_hosc = devm_clk_get_enabled(&pdev->dev, "hosc");
> +	if (IS_ERR(sun20i_chip->clk_hosc))
> +		return dev_err_probe(&pdev->dev, PTR_ERR(sun20i_chip->clk_hosc),
> +				     "failed to get hosc clock\n");
> +
> +	sun20i_chip->clk_apb0 = devm_clk_get_enabled(&pdev->dev, "apb0");
> +	if (IS_ERR(sun20i_chip->clk_apb0))
> +		return dev_err_probe(&pdev->dev, PTR_ERR(sun20i_chip->clk_apb0),
> +				     "failed to get apb0 clock\n");
> +
> +	sun20i_chip->rst = devm_reset_control_get_exclusive(&pdev->dev, NULL);
> +	if (IS_ERR(sun20i_chip->rst))
> +		return dev_err_probe(&pdev->dev, PTR_ERR(sun20i_chip->rst),
> +				     "failed to get bus reset\n");
> +
> +	ret = of_property_read_u32(pdev->dev.of_node, "allwinner,pwm-channels",
> +				   &sun20i_chip->chip.npwm);
> +	if (ret)
> +		sun20i_chip->chip.npwm = 8;
> +
> +	if (sun20i_chip->chip.npwm > 16)
> +		sun20i_chip->chip.npwm = 16;

Is it worth to emit an error message here? Something like:

	Limiting number of PWM lines from %u to 16

Best regards
Uwe

-- 
Pengutronix e.K.                           | Uwe Kleine-König            |
Industrial Linux Solutions                 | https://www.pengutronix.de/ |

Attachment: signature.asc
Description: PGP signature