pwm: meson: Simplify the calculation of the pre-divider and count

Replace the loop to calculate the pre-divider and count with two
separate div64_u64() calculations. This makes the code easier to read
and improves the precision.

Three example cases:
1) 32.768kHz LPO clock for the SDIO wifi chip on Khadas VIM
   clock input: 500MHz (FCLK_DIV4)
   period: 30518ns
   duty cycle: 15259ns
old algorithm: pre_div=0, cnt=15259
new algorithm: pre_div=0, cnt=15259
(no difference in calculated values)

2) PWM LED on Khadas VIM
   clock input: 24MHz (XTAL)
   period: 7812500ns
   duty cycle: 7812500ns
old algorithm: pre_div=2, cnt=62004
new algorithm: pre_div=2, cnt=62500
Using a scope (24MHz sampling rate) shows the actual difference:
- old: 7753000ns, off by -59500ns (0.7616%)
- new: 7815000ns, off by +2500ns (0.032%)

3) Theoretical case where pre_div is different
   clock input: 24MHz (XTAL)
   period: 2730624ns
   duty cycle: 1365312ns
old algorithm: pre_div=1, cnt=32768
new algorithm: pre_div=0, cnt=65534
Using a scope (24MHz sampling rate) shows the actual difference:
- old: 2731000ns
- new: 2731000ns
(my scope is not precise enough to measure the difference if there's
any)
Suggested-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Neil Armstrong <narmstrong@baylibre.com>
Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>

drivers/pwm/pwm-meson.c

@@ -12,6 +12,7 @@
 #include <linux/err.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
+#include <linux/math64.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
@@ -145,7 +146,6 @@ static int meson_pwm_calc(struct meson_pwm *meson, struct pwm_device *pwm,
 	struct meson_pwm_channel *channel = pwm_get_chip_data(pwm);
 	unsigned int duty, period, pre_div, cnt, duty_cnt;
 	unsigned long fin_freq = -1;
-	u64 fin_ps;
 
 	duty = state->duty_cycle;
 	period = state->period;
@@ -164,24 +164,19 @@ static int meson_pwm_calc(struct meson_pwm *meson, struct pwm_device *pwm,
 	}
 
 	dev_dbg(meson->chip.dev, "fin_freq: %lu Hz\n", fin_freq);
-	fin_ps = (u64)NSEC_PER_SEC * 1000;
-	do_div(fin_ps, fin_freq);
-
-	/* Calc pre_div with the period */
-	for (pre_div = 0; pre_div <= MISC_CLK_DIV_MASK; pre_div++) {
-		cnt = DIV_ROUND_CLOSEST_ULL((u64)period * 1000,
-					    fin_ps * (pre_div + 1));
-		dev_dbg(meson->chip.dev, "fin_ps=%llu pre_div=%u cnt=%u\n",
-			fin_ps, pre_div, cnt);
-		if (cnt <= 0xffff)
-			break;
-	}
 
+	pre_div = div64_u64(fin_freq * (u64)period, NSEC_PER_SEC * 0xffffLL);
 	if (pre_div > MISC_CLK_DIV_MASK) {
 		dev_err(meson->chip.dev, "unable to get period pre_div\n");
 		return -EINVAL;
 	}
 
+	cnt = div64_u64(fin_freq * (u64)period, NSEC_PER_SEC * (pre_div + 1));
+	if (cnt > 0xffff) {
+		dev_err(meson->chip.dev, "unable to get period cnt\n");
+		return -EINVAL;
+	}
+
 	dev_dbg(meson->chip.dev, "period=%u pre_div=%u cnt=%u\n", period,
 		pre_div, cnt);
 
@@ -195,8 +190,8 @@ static int meson_pwm_calc(struct meson_pwm *meson, struct pwm_device *pwm,
 		channel->lo = cnt;
 	} else {
 		/* Then check is we can have the duty with the same pre_div */
-		duty_cnt = DIV_ROUND_CLOSEST_ULL((u64)duty * 1000,
-						 fin_ps * (pre_div + 1));
+		duty_cnt = div64_u64(fin_freq * (u64)duty,
+				     NSEC_PER_SEC * (pre_div + 1));
 		if (duty_cnt > 0xffff) {
 			dev_err(meson->chip.dev, "unable to get duty cycle\n");
 			return -EINVAL;