[PATCH v1] usb: dwc3: gadget: wait for End Transfer to complete

[Baolin Wang]

Instead of just delaying for 100us, we should
actually wait for End Transfer Command Complete
interrupt before moving on. Note that this should
only be done if we're dealing with one of the core
revisions that actually require the interrupt before
moving on.

[ felipe.balbi@xxxxxxxxxxxxxxx: minor improvements ]

Signed-off-by: Baolin Wang <baolin.wang@xxxxxxxxxx>
---
 drivers/usb/dwc3/core.h   |    8 ++++++++
 drivers/usb/dwc3/gadget.c |   47 +++++++++++++++++++++++++++++++++++++++++----
 2 files changed, 51 insertions(+), 4 deletions(-)

diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index 23765a1..c5fd862 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -26,6 +26,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/mm.h>
 #include <linux/debugfs.h>
+#include <linux/wait.h>
 
 #include <linux/usb/ch9.h>
 #include <linux/usb/gadget.h>
@@ -496,6 +497,7 @@ struct dwc3_event_buffer {
  * @endpoint: usb endpoint
  * @pending_list: list of pending requests for this endpoint
  * @started_list: list of started requests on this endpoint
+ * @wait_end_transfer: wait_queue_head_t for waiting on End Transfer complete
  * @lock: spinlock for endpoint request queue traversal
  * @regs: pointer to first endpoint register
  * @trb_pool: array of transaction buffers
@@ -521,6 +523,8 @@ struct dwc3_ep {
 	struct list_head	pending_list;
 	struct list_head	started_list;
 
+	wait_queue_head_t	wait_end_transfer;
+
 	spinlock_t		lock;
 	void __iomem		*regs;
 
@@ -537,6 +541,7 @@ struct dwc3_ep {
 #define DWC3_EP_BUSY		(1 << 4)
 #define DWC3_EP_PENDING_REQUEST	(1 << 5)
 #define DWC3_EP_MISSED_ISOC	(1 << 6)
+#define DWC3_EP_END_TRANSFER_PENDING	(1 << 7)
 
 	/* This last one is specific to EP0 */
 #define DWC3_EP0_DIR_IN		(1 << 31)
@@ -1044,6 +1049,9 @@ struct dwc3_event_depevt {
 #define DEPEVT_TRANSFER_BUS_EXPIRY	2
 
 	u32	parameters:16;
+
+/* For Command Complete Events */
+#define DEPEVT_PARAMETER_CMD(n)	(((n) & (0xf << 8)) >> 8)
 } __packed;
 
 /**
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 3722c90..018611d 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -570,11 +570,14 @@ static int __dwc3_gadget_ep_enable(struct dwc3_ep *dep,
 		dep->comp_desc = comp_desc;
 		dep->type = usb_endpoint_type(desc);
 		dep->flags |= DWC3_EP_ENABLED;
+		dep->flags &= ~DWC3_EP_END_TRANSFER_PENDING;
 
 		reg = dwc3_readl(dwc->regs, DWC3_DALEPENA);
 		reg |= DWC3_DALEPENA_EP(dep->number);
 		dwc3_writel(dwc->regs, DWC3_DALEPENA, reg);
 
+		init_waitqueue_head(&dep->wait_end_transfer);
+
 		if (usb_endpoint_xfer_control(desc))
 			return 0;
 
@@ -647,7 +650,7 @@ static int __dwc3_gadget_ep_disable(struct dwc3_ep *dep)
 	dep->endpoint.desc = NULL;
 	dep->comp_desc = NULL;
 	dep->type = 0;
-	dep->flags = 0;
+	dep->flags &= DWC3_EP_END_TRANSFER_PENDING;
 
 	return 0;
 }
@@ -1736,10 +1739,34 @@ static int dwc3_gadget_stop(struct usb_gadget *g)
 {
 	struct dwc3		*dwc = gadget_to_dwc(g);
 	unsigned long		flags;
+	int			epnum;
 
 	spin_lock_irqsave(&dwc->lock, flags);
 	__dwc3_gadget_stop(dwc);
 	dwc->gadget_driver	= NULL;
+
+	for (epnum = 2; epnum < DWC3_ENDPOINTS_NUM; epnum++) {
+		struct dwc3_ep  *dep = dwc->eps[epnum];
+
+		/*
+		 * If the dwc3 core has been in suspend state, we will never get
+		 * the command complete event, thus ignore.
+		 */
+		if (pm_runtime_suspended(dwc->dev))
+			break;
+
+		if (!dep)
+			continue;
+
+		if (!(dep->flags & DWC3_EP_END_TRANSFER_PENDING))
+			continue;
+
+
+		wait_event_lock_irq(dep->wait_end_transfer,
+				    !(dep->flags & DWC3_EP_END_TRANSFER_PENDING),
+				    dwc->lock);
+	}
+
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
 	free_irq(dwc->irq_gadget, dwc->ev_buf);
@@ -2105,10 +2132,12 @@ static void dwc3_endpoint_interrupt(struct dwc3 *dwc,
 {
 	struct dwc3_ep		*dep;
 	u8			epnum = event->endpoint_number;
+	u8			cmd;
 
 	dep = dwc->eps[epnum];
 
-	if (!(dep->flags & DWC3_EP_ENABLED))
+	if (!(dep->flags & DWC3_EP_ENABLED) &&
+	    !(dep->flags & DWC3_EP_END_TRANSFER_PENDING))
 		return;
 
 	if (epnum == 0 || epnum == 1) {
@@ -2180,6 +2209,13 @@ static void dwc3_endpoint_interrupt(struct dwc3 *dwc,
 		dwc3_trace(trace_dwc3_gadget, "%s FIFO Overrun", dep->name);
 		break;
 	case DWC3_DEPEVT_EPCMDCMPLT:
+		cmd = DEPEVT_PARAMETER_CMD(event->parameters);
+
+		if (cmd == DWC3_DEPCMD_ENDTRANSFER) {
+			dep->flags &= ~DWC3_EP_END_TRANSFER_PENDING;
+			wake_up(&dep->wait_end_transfer);
+		}
+
 		dwc3_trace(trace_dwc3_gadget, "Endpoint Command Complete");
 		break;
 	}
@@ -2233,7 +2269,8 @@ static void dwc3_stop_active_transfer(struct dwc3 *dwc, u32 epnum, bool force)
 
 	dep = dwc->eps[epnum];
 
-	if (!dep->resource_index)
+	if ((dep->flags & DWC3_EP_END_TRANSFER_PENDING) ||
+	    !dep->resource_index)
 		return;
 
 	/*
@@ -2277,8 +2314,10 @@ static void dwc3_stop_active_transfer(struct dwc3 *dwc, u32 epnum, bool force)
 	dep->resource_index = 0;
 	dep->flags &= ~DWC3_EP_BUSY;
 
-	if (dwc3_is_usb31(dwc) || dwc->revision < DWC3_REVISION_310A)
+	if (dwc3_is_usb31(dwc) || dwc->revision < DWC3_REVISION_310A) {
+		dep->flags |= DWC3_EP_END_TRANSFER_PENDING;
 		udelay(100);
+	}
 }
 
 static void dwc3_stop_active_transfers(struct dwc3 *dwc)
-- 
1.7.9.5