[PATCH v4 1/3] ARM: shmobile: sh73a0: add support for adjusting CPU frequency

[Guennadi Liakhovetski]

On SH73A0 the output of PLL0 is supplied to two dividers, feeding clock to
the CPU core and SGX. Lower CPU frequencies allow the use of lower supply
voltages and thus reduce power consumption.

Signed-off-by: Guennadi Liakhovetski <g.liakhovetski+renesas at gmail.com>
---

v4: update Z-clock lookup name for the new version of the cpufreq-cpu0 
driver.

 arch/arm/mach-shmobile/clock-sh73a0.c |   95 ++++++++++++++++++++++++++++++++-
 1 files changed, 93 insertions(+), 2 deletions(-)

diff --git a/arch/arm/mach-shmobile/clock-sh73a0.c b/arch/arm/mach-shmobile/clock-sh73a0.c
index c992600..509be3e 100644
--- a/arch/arm/mach-shmobile/clock-sh73a0.c
+++ b/arch/arm/mach-shmobile/clock-sh73a0.c
@@ -282,6 +282,11 @@ enum { DIV4_I, DIV4_ZG, DIV4_M3, DIV4_B, DIV4_M1, DIV4_M2,
 
 static struct clk div4_clks[DIV4_NR] = {
 	[DIV4_I] = DIV4(FRQCRA, 20, 0xdff, CLK_ENABLE_ON_INIT),
+	/*
+	 * ZG clock is dividing PLL0 frequency to supply SGX. Make sure not to
+	 * exceed maximum frequencies of 201.5MHz for VDD_DVFS=1.175 and
+	 * 239.2MHz for VDD_DVFS=1.315V.
+	 */
 	[DIV4_ZG] = SH_CLK_DIV4(&pll0_clk, FRQCRA, 16, 0xd7f, CLK_ENABLE_ON_INIT),
 	[DIV4_M3] = DIV4(FRQCRA, 12, 0x1dff, CLK_ENABLE_ON_INIT),
 	[DIV4_B] = DIV4(FRQCRA, 8, 0xdff, CLK_ENABLE_ON_INIT),
@@ -308,6 +313,85 @@ static struct clk twd_clk = {
 	.ops = &twd_clk_ops,
 };
 
+static int (*div4_set_rate)(struct clk *clk, unsigned long rate);
+static unsigned long (*div4_recalc)(struct clk *clk);
+static long (*div4_round_rate)(struct clk *clk, unsigned long rate);
+
+static int zclk_set_rate(struct clk *clk, unsigned long rate)
+{
+	int ret;
+
+	if (!clk->parent || !__clk_get(clk->parent))
+		return -ENODEV;
+
+	if (readl(FRQCRB) & (1 << 31))
+		return -EBUSY;
+
+	if (rate == clk_get_rate(clk->parent)) {
+		/* 1:1 - switch off divider */
+		__raw_writel(__raw_readl(FRQCRB) & ~(1 << 28), FRQCRB);
+		/* nullify the divider to prepare for the next time */
+		ret = div4_set_rate(clk, rate / 2);
+		if (!ret)
+			ret = frqcr_kick();
+		if (ret > 0)
+			ret = 0;
+	} else {
+		/* Enable the divider */
+		__raw_writel(__raw_readl(FRQCRB) | (1 << 28), FRQCRB);
+
+		ret = frqcr_kick();
+		if (ret >= 0)
+			/*
+			 * set the divider - call the DIV4 method, it will kick
+			 * FRQCRB too
+			 */
+			ret = div4_set_rate(clk, rate);
+		if (ret < 0)
+			goto esetrate;
+	}
+
+esetrate:
+	__clk_put(clk->parent);
+	return ret;
+}
+
+static long zclk_round_rate(struct clk *clk, unsigned long rate)
+{
+	unsigned long div_freq = div4_round_rate(clk, rate),
+		parent_freq = clk_get_rate(clk->parent);
+
+	if (rate > div_freq && abs(parent_freq - rate) < rate - div_freq)
+		return parent_freq;
+
+	return div_freq;
+}
+
+static unsigned long zclk_recalc(struct clk *clk)
+{
+	/*
+	 * Must recalculate frequencies in case PLL0 has been changed, even if
+	 * the divisor is unused ATM!
+	 */
+	unsigned long div_freq = div4_recalc(clk);
+
+	if (__raw_readl(FRQCRB) & (1 << 28))
+		return div_freq;
+
+	return clk_get_rate(clk->parent);
+}
+
+static void zclk_extend(void)
+{
+	/* We extend the DIV4 clock with a 1:1 pass-through case */
+	div4_set_rate = div4_clks[DIV4_Z].ops->set_rate;
+	div4_round_rate = div4_clks[DIV4_Z].ops->round_rate;
+	div4_recalc = div4_clks[DIV4_Z].ops->recalc;
+	div4_clks[DIV4_Z].ops->set_rate = zclk_set_rate;
+	div4_clks[DIV4_Z].ops->round_rate = zclk_round_rate;
+	div4_clks[DIV4_Z].ops->recalc = zclk_recalc;
+}
+
 enum { DIV6_VCK1, DIV6_VCK2, DIV6_VCK3, DIV6_ZB1,
 	DIV6_FLCTL, DIV6_SDHI0, DIV6_SDHI1, DIV6_SDHI2,
 	DIV6_FSIA, DIV6_FSIB, DIV6_SUB,
@@ -506,7 +590,7 @@ static struct clk *late_main_clks[] = {
 };
 
 enum { MSTP001,
-	MSTP129, MSTP128, MSTP127, MSTP126, MSTP125, MSTP118, MSTP116, MSTP100,
+	MSTP129, MSTP128, MSTP127, MSTP126, MSTP125, MSTP118, MSTP116, MSTP112, MSTP100,
 	MSTP219, MSTP218, MSTP217,
 	MSTP207, MSTP206, MSTP204, MSTP203, MSTP202, MSTP201, MSTP200,
 	MSTP331, MSTP329, MSTP328, MSTP325, MSTP323, MSTP322,
@@ -527,6 +611,7 @@ static struct clk mstp_clks[MSTP_NR] = {
 	[MSTP125] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR1, 25, MSTPSR1, 0), /* TMU0 */
 	[MSTP118] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 18, MSTPSR1, 0), /* DSITX0 */
 	[MSTP116] = MSTP(&div4_clks[DIV4_HP], SMSTPCR1, 16, MSTPSR1, 0), /* IIC0 */
+	[MSTP112] = MSTP(&div4_clks[DIV4_ZG], SMSTPCR1, 12, MSTPSR1, 0), /* SGX */
 	[MSTP100] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 0, MSTPSR1, 0), /* LCDC0 */
 	[MSTP219] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 19, MSTPSR2, 0), /* SCIFA7 */
 	[MSTP218] = MSTP(&div4_clks[DIV4_HP], SMSTPCR2, 18, MSTPSR2, 0), /* SY-DMAC */
@@ -569,6 +654,9 @@ static struct clk_lookup lookups[] = {
 	CLKDEV_CON_ID("r_clk", &r_clk),
 	CLKDEV_DEV_ID("smp_twd", &twd_clk), /* smp_twd */
 
+	/* DIV4 clocks */
+	CLKDEV_DEV_ID("cpufreq-cpu0", &div4_clks[DIV4_Z]),
+
 	/* DIV6 clocks */
 	CLKDEV_CON_ID("vck1_clk", &div6_clks[DIV6_VCK1]),
 	CLKDEV_CON_ID("vck2_clk", &div6_clks[DIV6_VCK2]),
@@ -660,8 +748,11 @@ void __init sh73a0_clock_init(void)
 	for (k = 0; !ret && (k < ARRAY_SIZE(main_clks)); k++)
 		ret = clk_register(main_clks[k]);
 
-	if (!ret)
+	if (!ret) {
 		ret = sh_clk_div4_register(div4_clks, DIV4_NR, &div4_table);
+		if (!ret)
+			zclk_extend();
+	}
 
 	if (!ret)
 		ret = sh_clk_div6_reparent_register(div6_clks, DIV6_NR);
-- 
1.7.2.5