[PATCH] usb: ehci: make HC see up-to-date qh/qtd descriptor ASAP

@@ -995,6 +995,12 @@ static void qh_link_async (struct ehci_hcd *ehci, struct ehci_qh *qh)
 	head->qh_next.qh = qh;
 	head->hw->hw_next = dma;
 
+	/*
+	 * flush qh descriptor into memory immediately,
+	 * see comments in qh_append_tds.
+	 * */
+	ehci_sync_mem();
+
 	qh_get(qh);
 	qh->xacterrs = 0;
 	qh->qh_state = QH_STATE_LINKED;

@@ -1082,6 +1088,18 @@ static struct ehci_qh *qh_append_tds (
 			wmb ();
 			dummy->hw_token = token;
 
+			/*
+			 * Writing to dma coherent buffer on ARM may
+			 * be delayed to reach memory, so HC may not see
+			 * hw_token of dummy qtd in time, which can cause
+			 * the qtd transaction to be executed very late,
+			 * and degrade performance a lot. ehci_sync_mem
+			 * is added to flush 'token' immediatelly into
+			 * memory, so that ehci can execute the transaction
+			 * ASAP.
+			 * */
+			ehci_sync_mem();
+
 			urb->hcpriv = qh_get (qh);
 		}
 	}

@@ -738,6 +738,23 @@ static inline u32 hc32_to_cpup (const struct ehci_hcd *ehci, const __hc32 *x)
 
 #endif
 
+/*
+ * Writing to dma coherent memory on ARM may be delayed via L2
+ * writing buffer, so introduce the helper which can flush L2 writing
+ * buffer into memory immediately, especially used to flush ehci
+ * descriptor to memory.
+ * */
+#ifdef	CONFIG_ARM_DMA_MEM_BUFFERABLE
+static inline void ehci_sync_mem()
+{
+	mb();
+}
+#else
+static inline void ehci_sync_mem()
+{
+}
+#endif
+
 /*-------------------------------------------------------------------------*/
 
 #ifndef DEBUG