fsi/fsi-master-gpio: Add "no-gpio-delays" option

This adds support for an optional device-tree property that
makes the driver skip all the delays around clocking the
GPIOs and set it in the device-tree of common POWER9 based
OpenPower platforms.

This useful on chips like the AST2500 where the GPIO block is
running at a fairly low clock frequency (25Mhz typically). In
this case, the delays are unnecessary and due to the low
precision of the timers, actually quite harmful in terms of
performance.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Reviewed-by: Christopher Bostic <cbostic@linux.vnet.ibm.com>
Tested-by: Joel Stanley <joel@jms.id.au>

arch/arm/boot/dts/aspeed-bmc-opp-romulus.dts

@@ -52,6 +52,7 @@ fsi: gpio-fsi {
 		compatible = "fsi-master-gpio", "fsi-master";
 		#address-cells = <2>;
 		#size-cells = <0>;
+		no-gpio-delays;
 
 		clock-gpios = <&gpio ASPEED_GPIO(AA, 0) GPIO_ACTIVE_HIGH>;
 		data-gpios = <&gpio ASPEED_GPIO(AA, 2) GPIO_ACTIVE_HIGH>;

arch/arm/boot/dts/aspeed-bmc-opp-witherspoon.dts

@@ -153,6 +153,7 @@ fsi: gpio-fsi {
 		compatible = "fsi-master-gpio", "fsi-master";
 		#address-cells = <2>;
 		#size-cells = <0>;
+		no-gpio-delays;
 
 		clock-gpios = <&gpio ASPEED_GPIO(AA, 0) GPIO_ACTIVE_HIGH>;
 		data-gpios = <&gpio ASPEED_GPIO(E, 0) GPIO_ACTIVE_HIGH>;

arch/arm/boot/dts/aspeed-bmc-opp-zaius.dts

@@ -91,6 +91,7 @@ fsi: gpio-fsi {
 		compatible = "fsi-master-gpio", "fsi-master";
 		#address-cells = <2>;
 		#size-cells = <0>;
+		no-gpio-delays;
 
 		trans-gpios = <&gpio ASPEED_GPIO(O, 6) GPIO_ACTIVE_HIGH>;
 		enable-gpios = <&gpio ASPEED_GPIO(D, 0) GPIO_ACTIVE_HIGH>;

drivers/fsi/fsi-master-gpio.c

@@ -62,6 +62,7 @@ struct fsi_master_gpio {
 	struct gpio_desc	*gpio_enable;	/* FSI enable */
 	struct gpio_desc	*gpio_mux;	/* Mux control */
 	bool			external_mode;
+	bool			no_delays;
 };
 
 #define CREATE_TRACE_POINTS
@@ -79,9 +80,11 @@ static void clock_toggle(struct fsi_master_gpio *master, int count)
 	int i;
 
 	for (i = 0; i < count; i++) {
-		ndelay(FSI_GPIO_STD_DLY);
+		if (!master->no_delays)
+			ndelay(FSI_GPIO_STD_DLY);
 		gpiod_set_value(master->gpio_clk, 0);
-		ndelay(FSI_GPIO_STD_DLY);
+		if (!master->no_delays)
+			ndelay(FSI_GPIO_STD_DLY);
 		gpiod_set_value(master->gpio_clk, 1);
 	}
 }
@@ -90,10 +93,12 @@ static int sda_clock_in(struct fsi_master_gpio *master)
 {
 	int in;
 
-	ndelay(FSI_GPIO_STD_DLY);
+	if (!master->no_delays)
+		ndelay(FSI_GPIO_STD_DLY);
 	gpiod_set_value(master->gpio_clk, 0);
 	in = gpiod_get_value(master->gpio_data);
-	ndelay(FSI_GPIO_STD_DLY);
+	if (!master->no_delays)
+		ndelay(FSI_GPIO_STD_DLY);
 	gpiod_set_value(master->gpio_clk, 1);
 	return in ? 1 : 0;
 }
@@ -677,6 +682,13 @@ static int fsi_master_gpio_probe(struct platform_device *pdev)
 	}
 	master->gpio_mux = gpio;
 
+	/*
+	 * Check if GPIO block is slow enought that no extra delays
+	 * are necessary. This improves performance on ast2500 by
+	 * an order of magnitude.
+	 */
+	master->no_delays = device_property_present(&pdev->dev, "no-gpio-delays");
+
 	master->master.n_links = 1;
 	master->master.flags = FSI_MASTER_FLAG_SWCLOCK;
 	master->master.read = fsi_master_gpio_read;