4 files changed, 57 insertions, 7 deletions

diff --git a/drivers/usb/gadget/udc/aspeed-vhub/ep0.c b/drivers/usb/gadget/udc/aspeed-vhub/ep0.c
index 20ffb03ff6ac..e2927fb083cf 100644
--- a/drivers/usb/gadget/udc/aspeed-vhub/ep0.c
+++ b/drivers/usb/gadget/udc/aspeed-vhub/ep0.c
@@ -108,6 +108,13 @@ void ast_vhub_ep0_handle_setup(struct ast_vhub_ep *ep)
 	/* Check our state, cancel pending requests if needed */
 	if (ep->ep0.state != ep0_state_token) {
 		EPDBG(ep, "wrong state\n");
+		ast_vhub_nuke(ep, -EIO);
+
+		/*
+		 * Accept the packet regardless, this seems to happen
+		 * when stalling a SETUP packet that has an OUT data
+		 * phase.
+		 */
 		ast_vhub_nuke(ep, 0);
 		goto stall;
 	}
@@ -212,6 +219,8 @@ static void ast_vhub_ep0_do_send(struct ast_vhub_ep *ep,
 	if (chunk && req->req.buf)
 		memcpy(ep->buf, req->req.buf + req->req.actual, chunk);
 
+	vhub_dma_workaround(ep->buf);
+
 	/* Remember chunk size and trigger send */
 	reg = VHUB_EP0_SET_TX_LEN(chunk);
 	writel(reg, ep->ep0.ctlstat);
@@ -224,7 +233,7 @@ static void ast_vhub_ep0_rx_prime(struct ast_vhub_ep *ep)
 	EPVDBG(ep, "rx prime\n");
 
 	/* Prime endpoint for receiving data */
-	writel(VHUB_EP0_RX_BUFF_RDY, ep->ep0.ctlstat + AST_VHUB_EP0_CTRL);
+	writel(VHUB_EP0_RX_BUFF_RDY, ep->ep0.ctlstat);
 }
 
 static void ast_vhub_ep0_do_receive(struct ast_vhub_ep *ep, struct ast_vhub_req *req,
diff --git a/drivers/usb/gadget/udc/aspeed-vhub/epn.c b/drivers/usb/gadget/udc/aspeed-vhub/epn.c
index 80c9feac5147..5939eb1e97f2 100644
--- a/drivers/usb/gadget/udc/aspeed-vhub/epn.c
+++ b/drivers/usb/gadget/udc/aspeed-vhub/epn.c
@@ -66,11 +66,16 @@ static void ast_vhub_epn_kick(struct ast_vhub_ep *ep, struct ast_vhub_req *req)
 	if (!req->req.dma) {
 
 		/* For IN transfers, copy data over first */
-		if (ep->epn.is_in)
+		if (ep->epn.is_in) {
 			memcpy(ep->buf, req->req.buf + act, chunk);
+			vhub_dma_workaround(ep->buf);
+		}
 		writel(ep->buf_dma, ep->epn.regs + AST_VHUB_EP_DESC_BASE);
-	} else
+	} else {
+		if (ep->epn.is_in)
+			vhub_dma_workaround(req->req.buf);
 		writel(req->req.dma + act, ep->epn.regs + AST_VHUB_EP_DESC_BASE);
+	}
 
 	/* Start DMA */
 	req->active = true;
@@ -161,6 +166,7 @@ static inline unsigned int ast_vhub_count_free_descs(struct ast_vhub_ep *ep)
 static void ast_vhub_epn_kick_desc(struct ast_vhub_ep *ep,
 				   struct ast_vhub_req *req)
 {
+	struct ast_vhub_desc *desc = NULL;
 	unsigned int act = req->act_count;
 	unsigned int len = req->req.length;
 	unsigned int chunk;
@@ -177,7 +183,6 @@ static void ast_vhub_epn_kick_desc(struct ast_vhub_ep *ep,
 
 	/* While we can create descriptors */
 	while (ast_vhub_count_free_descs(ep) && req->last_desc < 0) {
-		struct ast_vhub_desc *desc;
 		unsigned int d_num;
 
 		/* Grab next free descriptor */
@@ -227,6 +232,9 @@ static void ast_vhub_epn_kick_desc(struct ast_vhub_ep *ep,
 		req->act_count = act = act + chunk;
 	}
 
+	if (likely(desc))
+		vhub_dma_workaround(desc);
+
 	/* Tell HW about new descriptors */
 	writel(VHUB_EP_DMA_SET_CPU_WPTR(ep->epn.d_next),
 	       ep->epn.regs + AST_VHUB_EP_DESC_STATUS);
diff --git a/drivers/usb/gadget/udc/aspeed-vhub/vhub.h b/drivers/usb/gadget/udc/aspeed-vhub/vhub.h
index 2b040257bc1f..4ed03d33a5a9 100644
--- a/drivers/usb/gadget/udc/aspeed-vhub/vhub.h
+++ b/drivers/usb/gadget/udc/aspeed-vhub/vhub.h
@@ -462,6 +462,39 @@ enum std_req_rc {
 #define DDBG(d, fmt, ...)	do { } while(0)
 #endif
 
+static inline void vhub_dma_workaround(void *addr)
+{
+	/*
+	 * This works around a confirmed HW issue with the Aspeed chip.
+	 *
+	 * The core uses a different bus to memory than the AHB going to
+	 * the USB device controller. Due to the latter having a higher
+	 * priority than the core for arbitration on that bus, it's
+	 * possible for an MMIO to the device, followed by a DMA by the
+	 * device from memory to all be performed and services before
+	 * a previous store to memory gets completed.
+	 *
+	 * This the following scenario can happen:
+	 *
+	 *    - Driver writes to a DMA descriptor (Mbus)
+	 *    - Driver writes to the MMIO register to start the DMA (AHB)
+	 *    - The gadget sees the second write and sends a read of the
+	 *      descriptor to the memory controller (Mbus)
+	 *    - The gadget hits memory before the descriptor write
+	 *      causing it to read an obsolete value.
+	 *
+	 * Thankfully the problem is limited to the USB gadget device, other
+	 * masters in the SoC all have a lower priority than the core, thus
+	 * ensuring that the store by the core arrives first.
+	 *
+	 * The workaround consists of using a dummy read of the memory before
+	 * doing the MMIO writes. This will ensure that the previous writes
+	 * have been "pushed out".
+	 */
+	mb();
+	(void)__raw_readl((void __iomem *)addr);
+}
+
 /* core.c */
 void ast_vhub_done(struct ast_vhub_ep *ep, struct ast_vhub_req *req,
 		   int status);
diff --git a/drivers/usb/gadget/udc/r8a66597-udc.c b/drivers/usb/gadget/udc/r8a66597-udc.c
index a3ecce62662b..11e25a3f4f1f 100644
--- a/drivers/usb/gadget/udc/r8a66597-udc.c
+++ b/drivers/usb/gadget/udc/r8a66597-udc.c
@@ -832,11 +832,11 @@ static void init_controller(struct r8a66597 *r8a66597)
 
 		r8a66597_bset(r8a66597, XCKE, SYSCFG0);
 
-		msleep(3);
+		mdelay(3);
 
 		r8a66597_bset(r8a66597, PLLC, SYSCFG0);
 
-		msleep(1);
+		mdelay(1);
 
 		r8a66597_bset(r8a66597, SCKE, SYSCFG0);
 
@@ -1190,7 +1190,7 @@ __acquires(r8a66597->lock)
 	r8a66597->ep0_req->length = 2;
 	/* AV: what happens if we get called again before that gets through? */
 	spin_unlock(&r8a66597->lock);
-	r8a66597_queue(r8a66597->gadget.ep0, r8a66597->ep0_req, GFP_KERNEL);
+	r8a66597_queue(r8a66597->gadget.ep0, r8a66597->ep0_req, GFP_ATOMIC);
 	spin_lock(&r8a66597->lock);
 }