usb: dwc3: gadget: Wait for ep0 xfers to complete during dequeue

If a Setup packet is received but yet to DMA out, the controller will
not process the End Transfer command of any endpoint. Polling of its
DEPCMD.CmdAct may block setting up TRB for Setup packet, causing a
command timeout.

This may occur if the driver doesn’t service the completion interrupt of
the control status stage yet due to system latency, then it won’t
prepare TRB and start the transfer for the next Setup Stage. To the host
side, the control transfer had completed, and the host can send a new
Setup packet at this point.

In the meanwhile, if the driver receives an async call to dequeue a
request (triggering End Transfer) to any endpoint, then the driver will
service that End transfer first, blocking the control status stage
completion handler. Since no TRB is available for the Setup stage, the
Setup packet can’t be DMA’ed out and the End Transfer gets hung.

The driver must not block setting up of the Setup stage. So track and
only issue the End Transfer command only when there’s Setup TRB prepared
so that the controller can DMA out the Setup packet. Delay the End
transfer command if there's no Setup TRB available. This is applicable to
all DWC_usb3x IPs.

Co-developed-by: Wesley Cheng <quic_wcheng@quicinc.com>
Signed-off-by: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Signed-off-by: Wesley Cheng <quic_wcheng@quicinc.com>
Link: https://lore.kernel.org/r/20220309205402.4467-1-quic_wcheng@quicinc.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

drivers/usb/dwc3/core.h

@@ -737,6 +737,7 @@ struct dwc3_ep {
 #define DWC3_EP_FIRST_STREAM_PRIMED	BIT(10)
 #define DWC3_EP_PENDING_CLEAR_STALL	BIT(11)
 #define DWC3_EP_TXFIFO_RESIZED		BIT(12)
+#define DWC3_EP_DELAY_STOP             BIT(13)
 
 	/* This last one is specific to EP0 */
 #define DWC3_EP0_DIR_IN			BIT(31)

drivers/usb/dwc3/ep0.c

@@ -271,6 +271,7 @@ void dwc3_ep0_out_start(struct dwc3 *dwc)
 {
 	struct dwc3_ep			*dep;
 	int				ret;
+	int                             i;
 
 	complete(&dwc->ep0_in_setup);
 
@@ -279,6 +280,19 @@ void dwc3_ep0_out_start(struct dwc3 *dwc)
 			DWC3_TRBCTL_CONTROL_SETUP, false);
 	ret = dwc3_ep0_start_trans(dep);
 	WARN_ON(ret < 0);
+	for (i = 2; i < DWC3_ENDPOINTS_NUM; i++) {
+		struct dwc3_ep *dwc3_ep;
+
+		dwc3_ep = dwc->eps[i];
+		if (!dwc3_ep)
+			continue;
+
+		if (!(dwc3_ep->flags & DWC3_EP_DELAY_STOP))
+			continue;
+
+		dwc3_ep->flags &= ~DWC3_EP_DELAY_STOP;
+		dwc3_stop_active_transfer(dwc3_ep, true, true);
+	}
 }
 
 static struct dwc3_ep *dwc3_wIndex_to_dep(struct dwc3 *dwc, __le16 wIndex_le)

drivers/usb/dwc3/gadget.c

@@ -654,9 +654,6 @@ static int dwc3_gadget_set_ep_config(struct dwc3_ep *dep, unsigned int action)
 	return dwc3_send_gadget_ep_cmd(dep, DWC3_DEPCMD_SETEPCONFIG, &params);
 }
 
-static void dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force,
-		bool interrupt);
-
 /**
  * dwc3_gadget_calc_tx_fifo_size - calculates the txfifo size value
  * @dwc: pointer to the DWC3 context
@@ -1926,6 +1923,7 @@ static int __dwc3_gadget_ep_queue(struct dwc3_ep *dep, struct dwc3_request *req)
 	 */
 	if ((dep->flags & DWC3_EP_END_TRANSFER_PENDING) ||
 	    (dep->flags & DWC3_EP_WEDGE) ||
+	    (dep->flags & DWC3_EP_DELAY_STOP) ||
 	    (dep->flags & DWC3_EP_STALL)) {
 		dep->flags |= DWC3_EP_DELAY_START;
 		return 0;
@@ -2058,6 +2056,16 @@ static int dwc3_gadget_ep_dequeue(struct usb_ep *ep,
 		if (r == req) {
 			struct dwc3_request *t;
 
+			/*
+			 * If a Setup packet is received but yet to DMA out, the controller will
+			 * not process the End Transfer command of any endpoint. Polling of its
+			 * DEPCMD.CmdAct may block setting up TRB for Setup packet, causing a
+			 * timeout. Delay issuing the End Transfer command until the Setup TRB is
+			 * prepared.
+			 */
+			if (dwc->ep0state != EP0_SETUP_PHASE && !dwc->delayed_status)
+				dep->flags |= DWC3_EP_DELAY_STOP;
+
 			/* wait until it is processed */
 			dwc3_stop_active_transfer(dep, true, true);
 
@@ -2141,7 +2149,8 @@ int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value, int protocol)
 		list_for_each_entry_safe(req, tmp, &dep->started_list, list)
 			dwc3_gadget_move_cancelled_request(req, DWC3_REQUEST_STATUS_STALLED);
 
-		if (dep->flags & DWC3_EP_END_TRANSFER_PENDING) {
+		if (dep->flags & DWC3_EP_END_TRANSFER_PENDING ||
+		    (dep->flags & DWC3_EP_DELAY_STOP)) {
 			dep->flags |= DWC3_EP_PENDING_CLEAR_STALL;
 			return 0;
 		}
@@ -3621,10 +3630,11 @@ static void dwc3_reset_gadget(struct dwc3 *dwc)
 	}
 }
 
-static void dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force,
+void dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force,
 	bool interrupt)
 {
 	if (!(dep->flags & DWC3_EP_TRANSFER_STARTED) ||
+	    (dep->flags & DWC3_EP_DELAY_STOP) ||
 	    (dep->flags & DWC3_EP_END_TRANSFER_PENDING))
 		return;
 

drivers/usb/dwc3/gadget.h

@@ -116,6 +116,7 @@ int dwc3_gadget_ep0_queue(struct usb_ep *ep, struct usb_request *request,
 		gfp_t gfp_flags);
 int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value, int protocol);
 void dwc3_ep0_send_delayed_status(struct dwc3 *dwc);
+void dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force, bool interrupt);
 
 /**
  * dwc3_gadget_ep_get_transfer_index - Gets transfer index from HW