[PATCH] fsldma: fix issue of slow dma

[Li Yang]

From: Forrest Shi <b29237@xxxxxxxxxxxxx>

Fixed fsl dma slow issue by initializing dma mode register with
bandwidth control. It boosts dma performance and should works
with 85xx board.

Signed-off-by: Forrest Shi <b29237@xxxxxxxxxxxxx>
Signed-off-by: Li Yang <leoli@xxxxxxxxxxxxx>
---
 drivers/dma/fsldma.c |    6 ++++--
 drivers/dma/fsldma.h |    9 ++++++++-
 2 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c
index 286c3ac..e5e172d 100644
--- a/drivers/dma/fsldma.c
+++ b/drivers/dma/fsldma.c
@@ -50,9 +50,11 @@ static void dma_init(struct fsldma_chan *chan)
 		 * EIE - Error interrupt enable
 		 * EOSIE - End of segments interrupt enable (basic mode)
 		 * EOLNIE - End of links interrupt enable
+		 * BWC - Bandwidth sharing among channels
 		 */
-		DMA_OUT(chan, &chan->regs->mr, FSL_DMA_MR_EIE
-				| FSL_DMA_MR_EOLNIE | FSL_DMA_MR_EOSIE, 32);
+		DMA_OUT(chan, &chan->regs->mr, FSL_DMA_MR_BWC
+				| FSL_DMA_MR_EIE | FSL_DMA_MR_EOLNIE
+				| FSL_DMA_MR_EOSIE, 32);
 		break;
 	case FSL_DMA_IP_83XX:
 		/* Set the channel to below modes:
diff --git a/drivers/dma/fsldma.h b/drivers/dma/fsldma.h
index cb4d6ff..ba9f403 100644
--- a/drivers/dma/fsldma.h
+++ b/drivers/dma/fsldma.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2007 Freescale Semiconductor, Inc. All rights reserved.
+ * Copyright (C) 2007-2010 Freescale Semiconductor, Inc. All rights reserved.
  *
  * Author:
  *   Zhang Wei <wei.zhang@xxxxxxxxxxxxx>, Jul 2007
@@ -36,6 +36,13 @@
 #define FSL_DMA_MR_DAHE		0x00002000
 #define FSL_DMA_MR_SAHE		0x00001000
 
+/*
+ * Bandwidth/pause control determines how many bytes a given
+ * channel is allowed to transfer before the DMA engine pauses
+ * the current channel and switches to the next channel
+ */
+#define FSL_DMA_MR_BWC         0x08000000
+
 /* Special MR definition for MPC8349 */
 #define FSL_DMA_MR_EOTIE	0x00000080
 #define FSL_DMA_MR_PRC_RM	0x00000800
-- 
1.6.6-rc1.GIT


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/