clk: sunxi-ng: sun50i: h6: Modify GPU clock configuration to support DFS

Using simple bash script it was discovered that not all CCU registers
can be safely used for DFS, e.g.:

    while true
    do
        devmem 0x3001030 4 0xb0003e02
        devmem 0x3001030 4 0xb0001e02
    done

Script above changes the GPU_PLL multiplier register value. While the
script is running, the user should interact with the user interface.

Using this method the following results were obtained:

| Register  | Name           | Bits  | Values | Result |
| --        | --             | --    | --     | --     |
| 0x3001030 | GPU_PLL.MULT   | 15..8 | 20-62  | OK     |
| 0x3001030 | GPU_PLL.INDIV  |     1 | 0-1    | OK     |
| 0x3001030 | GPU_PLL.OUTDIV |     0 | 0-1    | FAIL   |
| 0x3001670 | GPU_CLK.DIV    |  3..0 | ANY    | FAIL   |

DVFS started to work seamlessly once dividers which caused the
glitches were set to fixed values.
Signed-off-by: Roman Stratiienko <r.stratiienko@gmail.com>
Reviewed-by: Jernej Skrabec <jernej.skrabec@gmail.com>
Signed-off-by: Jernej Skrabec <jernej.skrabec@gmail.com>
Link: https://lore.kernel.org/r/20220705075226.359475-1-r.stratiienko@gmail.com

drivers/clk/sunxi-ng/ccu-sun50i-h6.c

@@ -95,13 +95,13 @@ static struct ccu_nkmp pll_periph1_clk = {
 	},
 };
 
+/* For GPU PLL, using an output divider for DFS causes system to fail */
 #define SUN50I_H6_PLL_GPU_REG		0x030
 static struct ccu_nkmp pll_gpu_clk = {
 	.enable		= BIT(31),
 	.lock		= BIT(28),
 	.n		= _SUNXI_CCU_MULT_MIN(8, 8, 12),
 	.m		= _SUNXI_CCU_DIV(1, 1), /* input divider */
-	.p		= _SUNXI_CCU_DIV(0, 1), /* output divider */
 	.common		= {
 		.reg		= 0x030,
 		.hw.init	= CLK_HW_INIT("pll-gpu", "osc24M",
@@ -294,9 +294,9 @@ static SUNXI_CCU_M_WITH_MUX_GATE(deinterlace_clk, "deinterlace",
 static SUNXI_CCU_GATE(bus_deinterlace_clk, "bus-deinterlace", "psi-ahb1-ahb2",
 		      0x62c, BIT(0), 0);
 
+/* Keep GPU_CLK divider const to avoid DFS instability. */
 static const char * const gpu_parents[] = { "pll-gpu" };
-static SUNXI_CCU_M_WITH_MUX_GATE(gpu_clk, "gpu", gpu_parents, 0x670,
-				       0, 3,	/* M */
+static SUNXI_CCU_MUX_WITH_GATE(gpu_clk, "gpu", gpu_parents, 0x670,
 				       24, 1,	/* mux */
 				       BIT(31),	/* gate */
 				       CLK_SET_RATE_PARENT);
@@ -1191,6 +1191,16 @@ static int sun50i_h6_ccu_probe(struct platform_device *pdev)
 	if (IS_ERR(reg))
 		return PTR_ERR(reg);
 
+	/* Force PLL_GPU output divider bits to 0 */
+	val = readl(reg + SUN50I_H6_PLL_GPU_REG);
+	val &= ~BIT(0);
+	writel(val, reg + SUN50I_H6_PLL_GPU_REG);
+
+	/* Force GPU_CLK divider bits to 0 */
+	val = readl(reg + gpu_clk.common.reg);
+	val &= ~GENMASK(3, 0);
+	writel(val, reg + gpu_clk.common.reg);
+
 	/* Enable the lock bits on all PLLs */
 	for (i = 0; i < ARRAY_SIZE(pll_regs); i++) {
 		val = readl(reg + pll_regs[i]);