提交: f392cbf75615e9d8cb90ef5ffb8d4e752b7be3c7 - linux_3.x_apsh4a0a (git)

linux-3.0.x for AP-SH4A-0A Board

Commit MetaInfo

• 修訂: f392cbf75615e9d8cb90ef5ffb8d4e752b7be3c7 (tree)
• 時間: 2011-08-31 04:55:01
• 作者: Ming Lei <ming.lei@cano...>
• Commiter: Nicolas Pitre

Log Message

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

This patch introduces the helper of ehci_sync_mem to flush
qtd/qh into memory immediately on some ARM, so that HC can
see the up-to-date qtd/qh descriptor asap.

This patch fixs one performance bug on ARM Cortex A9 dual core
platform, which has been reported on quite a few ARM machines
(OMAP4, Tegra 2, snowball...), see details from link of
https://bugs.launchpad.net/bugs/709245.

The patch has been tested ok on OMAP4 panda A1 board, and the
performance of 'dd' over usb mass storage can be increased from
4~5MB/sec to 14~16MB/sec after applying this patch.

Cc: Russell King <[e-mail]>
Signed-off-by: Ming Lei <[e-mail]>
Signed-off-by: Alan Stern <[e-mail]>

Change Summary

• modified: drivers/usb/host/ehci-q.c
• modified: drivers/usb/host/ehci.h

差異

--- a/drivers/usb/host/ehci-q.c
+++ b/drivers/usb/host/ehci-q.c
@@ -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);
 		}
 	}

--- a/drivers/usb/host/ehci.h
+++ b/drivers/usb/host/ehci.h
@@ -736,6 +736,23 @@ 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