diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index 5c25e6a72dbdda0a9c54949d1f5cf7826804585d..2f118ad43571e87616e7970155ee0a5cfb6d3349 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -114,6 +114,8 @@ void dwc3_set_prtcap(struct dwc3 *dwc, u32 mode)
 	dwc->current_dr_role = mode;
 }
 
+static int dwc3_core_soft_reset(struct dwc3 *dwc);
+
 static void __dwc3_set_mode(struct work_struct *work)
 {
 	struct dwc3 *dwc = work_to_dwc(work);
@@ -121,6 +123,8 @@ static void __dwc3_set_mode(struct work_struct *work)
 	int ret;
 	u32 reg;
 
+	mutex_lock(&dwc->mutex);
+
 	pm_runtime_get_sync(dwc->dev);
 
 	if (dwc->current_dr_role == DWC3_GCTL_PRTCAP_OTG)
@@ -154,6 +158,25 @@ static void __dwc3_set_mode(struct work_struct *work)
 		break;
 	}
 
+	/* For DRD host or device mode only */
+	if (dwc->desired_dr_role != DWC3_GCTL_PRTCAP_OTG) {
+		reg = dwc3_readl(dwc->regs, DWC3_GCTL);
+		reg |= DWC3_GCTL_CORESOFTRESET;
+		dwc3_writel(dwc->regs, DWC3_GCTL, reg);
+
+		/*
+		 * Wait for internal clocks to synchronized. DWC_usb31 and
+		 * DWC_usb32 may need at least 50ms (less for DWC_usb3). To
+		 * keep it consistent across different IPs, let's wait up to
+		 * 100ms before clearing GCTL.CORESOFTRESET.
+		 */
+		msleep(100);
+
+		reg = dwc3_readl(dwc->regs, DWC3_GCTL);
+		reg &= ~DWC3_GCTL_CORESOFTRESET;
+		dwc3_writel(dwc->regs, DWC3_GCTL, reg);
+	}
+
 	spin_lock_irqsave(&dwc->lock, flags);
 
 	dwc3_set_prtcap(dwc, dwc->desired_dr_role);
@@ -178,6 +201,8 @@ static void __dwc3_set_mode(struct work_struct *work)
 		}
 		break;
 	case DWC3_GCTL_PRTCAP_DEVICE:
+		dwc3_core_soft_reset(dwc);
+
 		dwc3_event_buffers_setup(dwc);
 
 		if (dwc->usb2_phy)
@@ -200,6 +225,7 @@ static void __dwc3_set_mode(struct work_struct *work)
 out:
 	pm_runtime_mark_last_busy(dwc->dev);
 	pm_runtime_put_autosuspend(dwc->dev);
+	mutex_unlock(&dwc->mutex);
 }
 
 void dwc3_set_mode(struct dwc3 *dwc, u32 mode)
@@ -1553,6 +1579,7 @@ static int dwc3_probe(struct platform_device *pdev)
 	dwc3_cache_hwparams(dwc);
 
 	spin_lock_init(&dwc->lock);
+	mutex_init(&dwc->mutex);
 
 	pm_runtime_set_active(dev);
 	pm_runtime_use_autosuspend(dev);
diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index 695ff2d791e413db3688b3535b9a4d5ce74a8a8d..7e3afa5378e874161d47a0c0474ec3a801907da5 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -13,6 +13,7 @@
 
 #include <linux/device.h>
 #include <linux/spinlock.h>
+#include <linux/mutex.h>
 #include <linux/ioport.h>
 #include <linux/list.h>
 #include <linux/bitops.h>
@@ -947,6 +948,7 @@ struct dwc3_scratchpad_array {
  * @scratch_addr: dma address of scratchbuf
  * @ep0_in_setup: one control transfer is completed and enter setup phase
  * @lock: for synchronizing
+ * @mutex: for mode switching
  * @dev: pointer to our struct device
  * @sysdev: pointer to the DMA-capable device
  * @xhci: pointer to our xHCI child
@@ -1088,6 +1090,9 @@ struct dwc3 {
 	/* device lock */
 	spinlock_t		lock;
 
+	/* mode switching lock */
+	struct mutex		mutex;
+
 	struct device		*dev;
 	struct device		*sysdev;