usb: gadget: aspeed: Workaround memory ordering issue

The Aspeed SoC has a memory ordering issue that (thankfully)
only affects the USB gadget device. A read back is necessary
after writing to memory and before letting the device DMA
from it.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Felipe Balbi <felipe.balbi@linux.intel.com>

drivers/usb/gadget/udc/aspeed-vhub/ep0.c

@@ -219,6 +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);

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);

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);