watchdog: intel-mid_wdt: Postpone IRQ handler registration till SCU is ready

When SCU is not ready and CONFIG_DEBUG_SHIRQ=y we got deferred probe followed
by fired test IRQ which immediately makes kernel panic. Fix this by delaying
IRQ handler registration till SCU is ready.

Fixes: 80ae679b ("watchdog: intel-mid_wdt: Convert to use new SCU IPC API")
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>

drivers/watchdog/intel-mid_wdt.c

@@ -154,6 +154,10 @@ static int mid_wdt_probe(struct platform_device *pdev)
 	watchdog_set_nowayout(wdt_dev, WATCHDOG_NOWAYOUT);
 	watchdog_set_drvdata(wdt_dev, mid);
 
+	mid->scu = devm_intel_scu_ipc_dev_get(dev);
+	if (!mid->scu)
+		return -EPROBE_DEFER;
+
 	ret = devm_request_irq(dev, pdata->irq, mid_wdt_irq,
 			       IRQF_SHARED | IRQF_NO_SUSPEND, "watchdog",
 			       wdt_dev);
@@ -162,10 +166,6 @@ static int mid_wdt_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	mid->scu = devm_intel_scu_ipc_dev_get(dev);
-	if (!mid->scu)
-		return -EPROBE_DEFER;
-
 	/*
 	 * The firmware followed by U-Boot leaves the watchdog running
 	 * with the default threshold which may vary. When we get here