Merge branch 'for_dan' of git://git.infradead.org/users/vkoul/slave-dma into dmaengine

* 'for_dan' of git://git.infradead.org/users/vkoul/slave-dma:
  drivers, pch_dma: Fix warning when CONFIG_PM=n.
  dmaengine/dw_dmac fix: use readl & writel instead of __raw_readl & __raw_writel
  avr32: at32ap700x: Specify DMA Flow Controller, Src and Dst msize
  dw_dmac: Setting Default Burst length for transfers as 16.
  dw_dmac: Allow src/dst msize & flow controller to be configured at runtime
  dw_dmac: Changing type of src_master and dest_master to u8.
  dw_dmac: Pass Channel Priority from platform_data
  dw_dmac: Pass Channel Allocation Order from platform_data
  dw_dmac: Mark all tx_descriptors with DMA_CRTL_ACK after xfer finish
  dw_dmac: Change value of DWC_MAX_COUNT to 4095.
  dw_dmac: Adding support for 64 bit access width for memcpy xfers
  dw_dmac: Calling dwc_scan_descriptors from dwc_tx_status() after taking lock
  dw_dmac: Move single descriptor from dwc->queue to dwc->active_list in dwc_complete_all
  dw_dmac: Replace module_init() with subsys_initcall()
  dw_dmac: Remove compilation dependency from AVR32 and put on HAVE_CLK
  dmaengine: mxs-dma: add dma support for i.MX23/28
  pch_dma: set the number of array correctly
  pch_dma: fix kernel error issue

9 files changed, 881 insertions, 50 deletions

diff --git a/arch/arm/mach-mxs/include/mach/dma.h b/arch/arm/mach-mxs/include/mach/dma.h
new file mode 100644
index 0000000..7f4aeea
--- /dev/null
+++ b/arch/arm/mach-mxs/include/mach/dma.h
@@ -0,0 +1,26 @@
+/*
+ * Copyright 2011 Freescale Semiconductor, Inc. All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __MACH_MXS_DMA_H__
+#define __MACH_MXS_DMA_H__
+
+struct mxs_dma_data {
+	int chan_irq;
+};
+
+static inline int mxs_dma_is_apbh(struct dma_chan *chan)
+{
+	return !strcmp(dev_name(chan->device->dev), "mxs-dma-apbh");
+}
+
+static inline int mxs_dma_is_apbx(struct dma_chan *chan)
+{
+	return !strcmp(dev_name(chan->device->dev), "mxs-dma-apbx");
+}
+
+#endif /* __MACH_MXS_DMA_H__ */
diff --git a/arch/avr32/mach-at32ap/at32ap700x.c b/arch/avr32/mach-at32ap/at32ap700x.c
index 2747cde..b4aaebd 100644
--- a/arch/avr32/mach-at32ap/at32ap700x.c
+++ b/arch/avr32/mach-at32ap/at32ap700x.c
@@ -2050,6 +2050,9 @@ at32_add_device_ac97c(unsigned int id, struct ac97c_platform_data *data,
 		rx_dws->cfg_lo &= ~(DWC_CFGL_HS_DST_POL | DWC_CFGL_HS_SRC_POL);
 		rx_dws->src_master = 0;
 		rx_dws->dst_master = 1;
+		rx_dws->src_msize = DW_DMA_MSIZE_1;
+		rx_dws->dst_msize = DW_DMA_MSIZE_1;
+		rx_dws->fc = DW_DMA_FC_D_P2M;
 	}
 
 	/* Check if DMA slave interface for playback should be configured. */
@@ -2060,6 +2063,9 @@ at32_add_device_ac97c(unsigned int id, struct ac97c_platform_data *data,
 		tx_dws->cfg_lo &= ~(DWC_CFGL_HS_DST_POL | DWC_CFGL_HS_SRC_POL);
 		rx_dws->src_master = 0;
 		rx_dws->dst_master = 1;
+		tx_dws->src_msize = DW_DMA_MSIZE_1;
+		tx_dws->dst_msize = DW_DMA_MSIZE_1;
+		tx_dws->fc = DW_DMA_FC_D_M2P;
 	}
 
 	if (platform_device_add_data(pdev, data,
@@ -2134,6 +2140,9 @@ at32_add_device_abdac(unsigned int id, struct atmel_abdac_pdata *data)
 	dws->cfg_lo &= ~(DWC_CFGL_HS_DST_POL | DWC_CFGL_HS_SRC_POL);
 	dws->src_master = 0;
 	dws->dst_master = 1;
+	dws->src_msize = DW_DMA_MSIZE_1;
+	dws->dst_msize = DW_DMA_MSIZE_1;
+	dws->fc = DW_DMA_FC_D_M2P;
 
 	if (platform_device_add_data(pdev, data,
 				sizeof(struct atmel_abdac_pdata)))
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 1c28816..d700895 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -82,7 +82,7 @@ config INTEL_IOP_ADMA
 
 config DW_DMAC
 	tristate "Synopsys DesignWare AHB DMA support"
-	depends on AVR32
+	depends on HAVE_CLK
 	select DMA_ENGINE
 	default y if CPU_AT32AP7000
 	help
@@ -227,6 +227,14 @@ config IMX_DMA
 	  Support the i.MX DMA engine. This engine is integrated into
 	  Freescale i.MX1/21/27 chips.
 
+config MXS_DMA
+	bool "MXS DMA support"
+	depends on SOC_IMX23 || SOC_IMX28
+	select DMA_ENGINE
+	help
+	  Support the MXS DMA engine. This engine including APBH-DMA
+	  and APBX-DMA is integrated into Freescale i.MX23/28 chips.
+
 config DMA_ENGINE
 	bool
 
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index 64b21f5..802b557 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -23,6 +23,7 @@ obj-$(CONFIG_COH901318) += coh901318.o coh901318_lli.o
 obj-$(CONFIG_AMCC_PPC440SPE_ADMA) += ppc4xx/
 obj-$(CONFIG_IMX_SDMA) += imx-sdma.o
 obj-$(CONFIG_IMX_DMA) += imx-dma.o
+obj-$(CONFIG_MXS_DMA) += mxs-dma.o
 obj-$(CONFIG_TIMB_DMA) += timb_dma.o
 obj-$(CONFIG_STE_DMA40) += ste_dma40.o ste_dma40_ll.o
 obj-$(CONFIG_PL330_DMA) += pl330.o
diff --git a/drivers/dma/dw_dmac.c b/drivers/dma/dw_dmac.c
index 08dab3b..9c25c7d 100644
--- a/drivers/dma/dw_dmac.c
+++ b/drivers/dma/dw_dmac.c
@@ -36,9 +36,11 @@
 		struct dw_dma_slave *__slave = (private);	\
 		int dms = __slave ? __slave->dst_master : 0;	\
 		int sms = __slave ? __slave->src_master : 1;	\
+		u8 smsize = __slave ? __slave->src_msize : DW_DMA_MSIZE_16; \
+		u8 dmsize = __slave ? __slave->dst_msize : DW_DMA_MSIZE_16; \
 								\
-		(DWC_CTLL_DST_MSIZE(0)				\
-		 | DWC_CTLL_SRC_MSIZE(0)			\
+		(DWC_CTLL_DST_MSIZE(dmsize)			\
+		 | DWC_CTLL_SRC_MSIZE(smsize)			\
 		 | DWC_CTLL_LLP_D_EN				\
 		 | DWC_CTLL_LLP_S_EN				\
 		 | DWC_CTLL_DMS(dms)				\
@@ -47,14 +49,13 @@
 
 /*
  * This is configuration-dependent and usually a funny size like 4095.
- * Let's round it down to the nearest power of two.
  *
  * Note that this is a transfer count, i.e. if we transfer 32-bit
- * words, we can do 8192 bytes per descriptor.
+ * words, we can do 16380 bytes per descriptor.
  *
  * This parameter is also system-specific.
  */
-#define DWC_MAX_COUNT	2048U
+#define DWC_MAX_COUNT	4095U
 
 /*
  * Number of descriptors to allocate for each channel. This should be
@@ -87,11 +88,6 @@ static struct dw_desc *dwc_first_active(struct dw_dma_chan *dwc)
 	return list_entry(dwc->active_list.next, struct dw_desc, desc_node);
 }
 
-static struct dw_desc *dwc_first_queued(struct dw_dma_chan *dwc)
-{
-	return list_entry(dwc->queue.next, struct dw_desc, desc_node);
-}
-
 static struct dw_desc *dwc_desc_get(struct dw_dma_chan *dwc)
 {
 	struct dw_desc *desc, *_desc;
@@ -204,6 +200,7 @@ dwc_descriptor_complete(struct dw_dma_chan *dwc, struct dw_desc *desc)
 	dma_async_tx_callback		callback;
 	void				*param;
 	struct dma_async_tx_descriptor	*txd = &desc->txd;
+	struct dw_desc			*child;
 
 	dev_vdbg(chan2dev(&dwc->chan), "descriptor %u complete\n", txd->cookie);
 
@@ -212,6 +209,12 @@ dwc_descriptor_complete(struct dw_dma_chan *dwc, struct dw_desc *desc)
 	param = txd->callback_param;
 
 	dwc_sync_desc_for_cpu(dwc, desc);
+
+	/* async_tx_ack */
+	list_for_each_entry(child, &desc->tx_list, desc_node)
+		async_tx_ack(&child->txd);
+	async_tx_ack(&desc->txd);
+
 	list_splice_init(&desc->tx_list, &dwc->free_list);
 	list_move(&desc->desc_node, &dwc->free_list);
 
@@ -262,10 +265,11 @@ static void dwc_complete_all(struct dw_dma *dw, struct dw_dma_chan *dwc)
 	 * Submit queued descriptors ASAP, i.e. before we go through
 	 * the completed ones.
 	 */
-	if (!list_empty(&dwc->queue))
-		dwc_dostart(dwc, dwc_first_queued(dwc));
 	list_splice_init(&dwc->active_list, &list);
-	list_splice_init(&dwc->queue, &dwc->active_list);
+	if (!list_empty(&dwc->queue)) {
+		list_move(dwc->queue.next, &dwc->active_list);
+		dwc_dostart(dwc, dwc_first_active(dwc));
+	}
 
 	list_for_each_entry_safe(desc, _desc, &list, desc_node)
 		dwc_descriptor_complete(dwc, desc);
@@ -325,8 +329,8 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
 		cpu_relax();
 
 	if (!list_empty(&dwc->queue)) {
-		dwc_dostart(dwc, dwc_first_queued(dwc));
-		list_splice_init(&dwc->queue, &dwc->active_list);
+		list_move(dwc->queue.next, &dwc->active_list);
+		dwc_dostart(dwc, dwc_first_active(dwc));
 	}
 }
 
@@ -352,7 +356,7 @@ static void dwc_handle_error(struct dw_dma *dw, struct dw_dma_chan *dwc)
 	 */
 	bad_desc = dwc_first_active(dwc);
 	list_del_init(&bad_desc->desc_node);
-	list_splice_init(&dwc->queue, dwc->active_list.prev);
+	list_move(dwc->queue.next, dwc->active_list.prev);
 
 	/* Clear the error flag and try to restart the controller */
 	dma_writel(dw, CLEAR.ERROR, dwc->mask);
@@ -547,8 +551,8 @@ static dma_cookie_t dwc_tx_submit(struct dma_async_tx_descriptor *tx)
 	if (list_empty(&dwc->active_list)) {
 		dev_vdbg(chan2dev(tx->chan), "tx_submit: started %u\n",
 				desc->txd.cookie);
-		dwc_dostart(dwc, desc);
 		list_add_tail(&desc->desc_node, &dwc->active_list);
+		dwc_dostart(dwc, dwc_first_active(dwc));
 	} else {
 		dev_vdbg(chan2dev(tx->chan), "tx_submit: queued %u\n",
 				desc->txd.cookie);
@@ -587,7 +591,9 @@ dwc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 	 * We can be a lot more clever here, but this should take care
 	 * of the most common optimization.
 	 */
-	if (!((src | dest  | len) & 3))
+	if (!((src | dest  | len) & 7))
+		src_width = dst_width = 3;
+	else if (!((src | dest  | len) & 3))
 		src_width = dst_width = 2;
 	else if (!((src | dest | len) & 1))
 		src_width = dst_width = 1;
@@ -679,7 +685,7 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 				| DWC_CTLL_DST_WIDTH(reg_width)
 				| DWC_CTLL_DST_FIX
 				| DWC_CTLL_SRC_INC
-				| DWC_CTLL_FC_M2P);
+				| DWC_CTLL_FC(dws->fc));
 		reg = dws->tx_reg;
 		for_each_sg(sgl, sg, sg_len, i) {
 			struct dw_desc	*desc;
@@ -724,7 +730,7 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 				| DWC_CTLL_SRC_WIDTH(reg_width)
 				| DWC_CTLL_DST_INC
 				| DWC_CTLL_SRC_FIX
-				| DWC_CTLL_FC_P2M);
+				| DWC_CTLL_FC(dws->fc));
 
 		reg = dws->rx_reg;
 		for_each_sg(sgl, sg, sg_len, i) {
@@ -840,7 +846,9 @@ dwc_tx_status(struct dma_chan *chan,
 
 	ret = dma_async_is_complete(cookie, last_complete, last_used);
 	if (ret != DMA_SUCCESS) {
+		spin_lock_bh(&dwc->lock);
 		dwc_scan_descriptors(to_dw_dma(chan->device), dwc);
+		spin_unlock_bh(&dwc->lock);
 
 		last_complete = dwc->completed;
 		last_used = chan->cookie;
@@ -895,8 +903,11 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan)
 		BUG_ON(!dws->dma_dev || dws->dma_dev != dw->dma.dev);
 
 		cfghi = dws->cfg_hi;
-		cfglo = dws->cfg_lo;
+		cfglo = dws->cfg_lo & ~DWC_CFGL_CH_PRIOR_MASK;
 	}
+
+	cfglo |= DWC_CFGL_CH_PRIOR(dwc->priority);
+
 	channel_writel(dwc, CFG_LO, cfglo);
 	channel_writel(dwc, CFG_HI, cfghi);
 
@@ -1137,7 +1148,7 @@ struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan,
 					| DWC_CTLL_SRC_WIDTH(reg_width)
 					| DWC_CTLL_DST_FIX
 					| DWC_CTLL_SRC_INC
-					| DWC_CTLL_FC_M2P
+					| DWC_CTLL_FC(dws->fc)
 					| DWC_CTLL_INT_EN);
 			break;
 		case DMA_FROM_DEVICE:
@@ -1148,7 +1159,7 @@ struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan,
 					| DWC_CTLL_DST_WIDTH(reg_width)
 					| DWC_CTLL_DST_INC
 					| DWC_CTLL_SRC_FIX
-					| DWC_CTLL_FC_P2M
+					| DWC_CTLL_FC(dws->fc)
 					| DWC_CTLL_INT_EN);
 			break;
 		default:
@@ -1313,7 +1324,17 @@ static int __init dw_probe(struct platform_device *pdev)
 		dwc->chan.device = &dw->dma;
 		dwc->chan.cookie = dwc->completed = 1;
 		dwc->chan.chan_id = i;
-		list_add_tail(&dwc->chan.device_node, &dw->dma.channels);
+		if (pdata->chan_allocation_order == CHAN_ALLOCATION_ASCENDING)
+			list_add_tail(&dwc->chan.device_node,
+					&dw->dma.channels);
+		else
+			list_add(&dwc->chan.device_node, &dw->dma.channels);
+
+		/* 7 is highest priority & 0 is lowest. */
+		if (pdata->chan_priority == CHAN_PRIORITY_ASCENDING)
+			dwc->priority = 7 - i;
+		else
+			dwc->priority = i;
 
 		dwc->ch_regs = &__dw_regs(dw)->CHAN[i];
 		spin_lock_init(&dwc->lock);
@@ -1455,7 +1476,7 @@ static int __init dw_init(void)
 {
 	return platform_driver_probe(&dw_driver, dw_probe);
 }
-module_init(dw_init);
+subsys_initcall(dw_init);
 
 static void __exit dw_exit(void)
 {
diff --git a/drivers/dma/dw_dmac_regs.h b/drivers/dma/dw_dmac_regs.h
index d9a939f..720f821 100644
--- a/drivers/dma/dw_dmac_regs.h
+++ b/drivers/dma/dw_dmac_regs.h
@@ -86,6 +86,7 @@ struct dw_dma_regs {
 #define DWC_CTLL_SRC_MSIZE(n)	((n)<<14)
 #define DWC_CTLL_S_GATH_EN	(1 << 17)	/* src gather, !FIX */
 #define DWC_CTLL_D_SCAT_EN	(1 << 18)	/* dst scatter, !FIX */
+#define DWC_CTLL_FC(n)		((n) << 20)
 #define DWC_CTLL_FC_M2M		(0 << 20)	/* mem-to-mem */
 #define DWC_CTLL_FC_M2P		(1 << 20)	/* mem-to-periph */
 #define DWC_CTLL_FC_P2M		(2 << 20)	/* periph-to-mem */
@@ -101,6 +102,8 @@ struct dw_dma_regs {
 #define DWC_CTLH_BLOCK_TS_MASK	0x00000fff
 
 /* Bitfields in CFG_LO. Platform-configurable bits are in <linux/dw_dmac.h> */
+#define DWC_CFGL_CH_PRIOR_MASK	(0x7 << 5)	/* priority mask */
+#define DWC_CFGL_CH_PRIOR(x)	((x) << 5)	/* priority */
 #define DWC_CFGL_CH_SUSP	(1 << 8)	/* pause xfer */
 #define DWC_CFGL_FIFO_EMPTY	(1 << 9)	/* pause xfer */
 #define DWC_CFGL_HS_DST		(1 << 10)	/* handshake w/dst */
@@ -134,6 +137,7 @@ struct dw_dma_chan {
 	struct dma_chan		chan;
 	void __iomem		*ch_regs;
 	u8			mask;
+	u8			priority;
 
 	spinlock_t		lock;
 
@@ -155,9 +159,9 @@ __dwc_regs(struct dw_dma_chan *dwc)
 }
 
 #define channel_readl(dwc, name) \
-	__raw_readl(&(__dwc_regs(dwc)->name))
+	readl(&(__dwc_regs(dwc)->name))
 #define channel_writel(dwc, name, val) \
-	__raw_writel((val), &(__dwc_regs(dwc)->name))
+	writel((val), &(__dwc_regs(dwc)->name))
 
 static inline struct dw_dma_chan *to_dw_dma_chan(struct dma_chan *chan)
 {
@@ -181,9 +185,9 @@ static inline struct dw_dma_regs __iomem *__dw_regs(struct dw_dma *dw)
 }
 
 #define dma_readl(dw, name) \
-	__raw_readl(&(__dw_regs(dw)->name))
+	readl(&(__dw_regs(dw)->name))
 #define dma_writel(dw, name, val) \
-	__raw_writel((val), &(__dw_regs(dw)->name))
+	writel((val), &(__dw_regs(dw)->name))
 
 #define channel_set_bit(dw, reg, mask) \
 	dma_writel(dw, reg, ((mask) << 8) | (mask))
diff --git a/drivers/dma/mxs-dma.c b/drivers/dma/mxs-dma.c
new file mode 100644
index 0000000..88aad4f
--- /dev/null
+++ b/drivers/dma/mxs-dma.c
@@ -0,0 +1,724 @@
+/*
+ * Copyright 2011 Freescale Semiconductor, Inc. All Rights Reserved.
+ *
+ * Refer to drivers/dma/imx-sdma.c
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/mm.h>
+#include <linux/interrupt.h>
+#include <linux/clk.h>
+#include <linux/wait.h>
+#include <linux/sched.h>
+#include <linux/semaphore.h>
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/slab.h>
+#include <linux/platform_device.h>
+#include <linux/dmaengine.h>
+#include <linux/delay.h>
+
+#include <asm/irq.h>
+#include <mach/mxs.h>
+#include <mach/dma.h>
+#include <mach/common.h>
+
+/*
+ * NOTE: The term "PIO" throughout the mxs-dma implementation means
+ * PIO mode of mxs apbh-dma and apbx-dma.  With this working mode,
+ * dma can program the controller registers of peripheral devices.
+ */
+
+#define MXS_DMA_APBH		0
+#define MXS_DMA_APBX		1
+#define dma_is_apbh()		(mxs_dma->dev_id == MXS_DMA_APBH)
+
+#define APBH_VERSION_LATEST	3
+#define apbh_is_old()		(mxs_dma->version < APBH_VERSION_LATEST)
+
+#define HW_APBHX_CTRL0				0x000
+#define BM_APBH_CTRL0_APB_BURST8_EN		(1 << 29)
+#define BM_APBH_CTRL0_APB_BURST_EN		(1 << 28)
+#define BP_APBH_CTRL0_CLKGATE_CHANNEL		8
+#define BP_APBH_CTRL0_RESET_CHANNEL		16
+#define HW_APBHX_CTRL1				0x010
+#define HW_APBHX_CTRL2				0x020
+#define HW_APBHX_CHANNEL_CTRL			0x030
+#define BP_APBHX_CHANNEL_CTRL_RESET_CHANNEL	16
+#define HW_APBH_VERSION				(cpu_is_mx23() ? 0x3f0 : 0x800)
+#define HW_APBX_VERSION				0x800
+#define BP_APBHX_VERSION_MAJOR			24
+#define HW_APBHX_CHn_NXTCMDAR(n) \
+	(((dma_is_apbh() && apbh_is_old()) ? 0x050 : 0x110) + (n) * 0x70)
+#define HW_APBHX_CHn_SEMA(n) \
+	(((dma_is_apbh() && apbh_is_old()) ? 0x080 : 0x140) + (n) * 0x70)
+
+/*
+ * ccw bits definitions
+ *
+ * COMMAND:		0..1	(2)
+ * CHAIN:		2	(1)
+ * IRQ:			3	(1)
+ * NAND_LOCK:		4	(1) - not implemented
+ * NAND_WAIT4READY:	5	(1) - not implemented
+ * DEC_SEM:		6	(1)
+ * WAIT4END:		7	(1)
+ * HALT_ON_TERMINATE:	8	(1)
+ * TERMINATE_FLUSH:	9	(1)
+ * RESERVED:		10..11	(2)
+ * PIO_NUM:		12..15	(4)
+ */
+#define BP_CCW_COMMAND		0
+#define BM_CCW_COMMAND		(3 << 0)
+#define CCW_CHAIN		(1 << 2)
+#define CCW_IRQ			(1 << 3)
+#define CCW_DEC_SEM		(1 << 6)
+#define CCW_WAIT4END		(1 << 7)
+#define CCW_HALT_ON_TERM	(1 << 8)
+#define CCW_TERM_FLUSH		(1 << 9)
+#define BP_CCW_PIO_NUM		12
+#define BM_CCW_PIO_NUM		(0xf << 12)
+
+#define BF_CCW(value, field)	(((value) << BP_CCW_##field) & BM_CCW_##field)
+
+#define MXS_DMA_CMD_NO_XFER	0
+#define MXS_DMA_CMD_WRITE	1
+#define MXS_DMA_CMD_READ	2
+#define MXS_DMA_CMD_DMA_SENSE	3	/* not implemented */
+
+struct mxs_dma_ccw {
+	u32		next;
+	u16		bits;
+	u16		xfer_bytes;
+#define MAX_XFER_BYTES	0xff00
+	u32		bufaddr;
+#define MXS_PIO_WORDS	16
+	u32		pio_words[MXS_PIO_WORDS];
+};
+
+#define NUM_CCW	(int)(PAGE_SIZE / sizeof(struct mxs_dma_ccw))
+
+struct mxs_dma_chan {
+	struct mxs_dma_engine		*mxs_dma;
+	struct dma_chan			chan;
+	struct dma_async_tx_descriptor	desc;
+	struct tasklet_struct		tasklet;
+	int				chan_irq;
+	struct mxs_dma_ccw		*ccw;
+	dma_addr_t			ccw_phys;
+	dma_cookie_t			last_completed;
+	enum dma_status			status;
+	unsigned int			flags;
+#define MXS_DMA_SG_LOOP			(1 << 0)
+};
+
+#define MXS_DMA_CHANNELS		16
+#define MXS_DMA_CHANNELS_MASK		0xffff
+
+struct mxs_dma_engine {
+	int				dev_id;
+	unsigned int			version;
+	void __iomem			*base;
+	struct clk			*clk;
+	struct dma_device		dma_device;
+	struct device_dma_parameters	dma_parms;
+	struct mxs_dma_chan		mxs_chans[MXS_DMA_CHANNELS];
+};
+
+static void mxs_dma_reset_chan(struct mxs_dma_chan *mxs_chan)
+{
+	struct mxs_dma_engine *mxs_dma = mxs_chan->mxs_dma;
+	int chan_id = mxs_chan->chan.chan_id;
+
+	if (dma_is_apbh() && apbh_is_old())
+		writel(1 << (chan_id + BP_APBH_CTRL0_RESET_CHANNEL),
+			mxs_dma->base + HW_APBHX_CTRL0 + MXS_SET_ADDR);
+	else
+		writel(1 << (chan_id + BP_APBHX_CHANNEL_CTRL_RESET_CHANNEL),
+			mxs_dma->base + HW_APBHX_CHANNEL_CTRL + MXS_SET_ADDR);
+}
+
+static void mxs_dma_enable_chan(struct mxs_dma_chan *mxs_chan)
+{
+	struct mxs_dma_engine *mxs_dma = mxs_chan->mxs_dma;
+	int chan_id = mxs_chan->chan.chan_id;
+
+	/* set cmd_addr up */
+	writel(mxs_chan->ccw_phys,
+		mxs_dma->base + HW_APBHX_CHn_NXTCMDAR(chan_id));
+
+	/* enable apbh channel clock */
+	if (dma_is_apbh()) {
+		if (apbh_is_old())
+			writel(1 << (chan_id + BP_APBH_CTRL0_CLKGATE_CHANNEL),
+				mxs_dma->base + HW_APBHX_CTRL0 + MXS_CLR_ADDR);
+		else
+			writel(1 << chan_id,
+				mxs_dma->base + HW_APBHX_CTRL0 + MXS_CLR_ADDR);
+	}
+
+	/* write 1 to SEMA to kick off the channel */
+	writel(1, mxs_dma->base + HW_APBHX_CHn_SEMA(chan_id));
+}
+
+static void mxs_dma_disable_chan(struct mxs_dma_chan *mxs_chan)
+{
+	struct mxs_dma_engine *mxs_dma = mxs_chan->mxs_dma;
+	int chan_id = mxs_chan->chan.chan_id;
+
+	/* disable apbh channel clock */
+	if (dma_is_apbh()) {
+		if (apbh_is_old())
+			writel(1 << (chan_id + BP_APBH_CTRL0_CLKGATE_CHANNEL),
+				mxs_dma->base + HW_APBHX_CTRL0 + MXS_SET_ADDR);
+		else
+			writel(1 << chan_id,
+				mxs_dma->base + HW_APBHX_CTRL0 + MXS_SET_ADDR);
+	}
+
+	mxs_chan->status = DMA_SUCCESS;
+}
+
+static void mxs_dma_pause_chan(struct mxs_dma_chan *mxs_chan)
+{
+	struct mxs_dma_engine *mxs_dma = mxs_chan->mxs_dma;
+	int chan_id = mxs_chan->chan.chan_id;
+
+	/* freeze the channel */
+	if (dma_is_apbh() && apbh_is_old())
+		writel(1 << chan_id,
+			mxs_dma->base + HW_APBHX_CTRL0 + MXS_SET_ADDR);
+	else
+		writel(1 << chan_id,
+			mxs_dma->base + HW_APBHX_CHANNEL_CTRL + MXS_SET_ADDR);
+
+	mxs_chan->status = DMA_PAUSED;
+}
+
+static void mxs_dma_resume_chan(struct mxs_dma_chan *mxs_chan)
+{
+	struct mxs_dma_engine *mxs_dma = mxs_chan->mxs_dma;
+	int chan_id = mxs_chan->chan.chan_id;
+
+	/* unfreeze the channel */
+	if (dma_is_apbh() && apbh_is_old())
+		writel(1 << chan_id,
+			mxs_dma->base + HW_APBHX_CTRL0 + MXS_CLR_ADDR);
+	else
+		writel(1 << chan_id,
+			mxs_dma->base + HW_APBHX_CHANNEL_CTRL + MXS_CLR_ADDR);
+
+	mxs_chan->status = DMA_IN_PROGRESS;
+}
+
+static dma_cookie_t mxs_dma_assign_cookie(struct mxs_dma_chan *mxs_chan)
+{
+	dma_cookie_t cookie = mxs_chan->chan.cookie;
+
+	if (++cookie < 0)
+		cookie = 1;
+
+	mxs_chan->chan.cookie = cookie;
+	mxs_chan->desc.cookie = cookie;
+
+	return cookie;
+}
+
+static struct mxs_dma_chan *to_mxs_dma_chan(struct dma_chan *chan)
+{
+	return container_of(chan, struct mxs_dma_chan, chan);
+}
+
+static dma_cookie_t mxs_dma_tx_submit(struct dma_async_tx_descriptor *tx)
+{
+	struct mxs_dma_chan *mxs_chan = to_mxs_dma_chan(tx->chan);
+
+	mxs_dma_enable_chan(mxs_chan);
+
+	return mxs_dma_assign_cookie(mxs_chan);
+}
+
+static void mxs_dma_tasklet(unsigned long data)
+{
+	struct mxs_dma_chan *mxs_chan = (struct mxs_dma_chan *) data;
+
+	if (mxs_chan->desc.callback)
+		mxs_chan->desc.callback(mxs_chan->desc.callback_param);
+}
+
+static irqreturn_t mxs_dma_int_handler(int irq, void *dev_id)
+{
+	struct mxs_dma_engine *mxs_dma = dev_id;
+	u32 stat1, stat2;
+
+	/* completion status */
+	stat1 = readl(mxs_dma->base + HW_APBHX_CTRL1);
+	stat1 &= MXS_DMA_CHANNELS_MASK;
+	writel(stat1, mxs_dma->base + HW_APBHX_CTRL1 + MXS_CLR_ADDR);
+
+	/* error status */
+	stat2 = readl(mxs_dma->base + HW_APBHX_CTRL2);
+	writel(stat2, mxs_dma->base + HW_APBHX_CTRL2 + MXS_CLR_ADDR);
+
+	/*
+	 * When both completion and error of termination bits set at the
+	 * same time, we do not take it as an error.  IOW, it only becomes
+	 * an error we need to handler here in case of ether it's (1) an bus
+	 * error or (2) a termination error with no completion.
+	 */
+	stat2 = ((stat2 >> MXS_DMA_CHANNELS) & stat2) | /* (1) */
+		(~(stat2 >> MXS_DMA_CHANNELS) & stat2 & ~stat1); /* (2) */
+
+	/* combine error and completion status for checking */
+	stat1 = (stat2 << MXS_DMA_CHANNELS) | stat1;
+	while (stat1) {
+		int channel = fls(stat1) - 1;
+		struct mxs_dma_chan *mxs_chan =
+			&mxs_dma->mxs_chans[channel % MXS_DMA_CHANNELS];
+
+		if (channel >= MXS_DMA_CHANNELS) {
+			dev_dbg(mxs_dma->dma_device.dev,
+				"%s: error in channel %d\n", __func__,
+				channel - MXS_DMA_CHANNELS);
+			mxs_chan->status = DMA_ERROR;
+			mxs_dma_reset_chan(mxs_chan);
+		} else {
+			if (mxs_chan->flags & MXS_DMA_SG_LOOP)
+				mxs_chan->status = DMA_IN_PROGRESS;
+			else
+				mxs_chan->status = DMA_SUCCESS;
+		}
+
+		stat1 &= ~(1 << channel);
+
+		if (mxs_chan->status == DMA_SUCCESS)
+			mxs_chan->last_completed = mxs_chan->desc.cookie;
+
+		/* schedule tasklet on this channel */
+		tasklet_schedule(&mxs_chan->tasklet);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int mxs_dma_alloc_chan_resources(struct dma_chan *chan)
+{
+	struct mxs_dma_chan *mxs_chan = to_mxs_dma_chan(chan);
+	struct mxs_dma_data *data = chan->private;
+	struct mxs_dma_engine *mxs_dma = mxs_chan->mxs_dma;
+	int ret;
+
+	if (!data)
+		return -EINVAL;
+
+	mxs_chan->chan_irq = data->chan_irq;
+
+	mxs_chan->ccw = dma_alloc_coherent(mxs_dma->dma_device.dev, PAGE_SIZE,
+				&mxs_chan->ccw_phys, GFP_KERNEL);
+	if (!mxs_chan->ccw) {
+		ret = -ENOMEM;
+		goto err_alloc;
+	}
+
+	memset(mxs_chan->ccw, 0, PAGE_SIZE);
+
+	ret = request_irq(mxs_chan->chan_irq, mxs_dma_int_handler,
+				0, "mxs-dma", mxs_dma);
+	if (ret)
+		goto err_irq;
+
+	ret = clk_enable(mxs_dma->clk);
+	if (ret)
+		goto err_clk;
+
+	mxs_dma_reset_chan(mxs_chan);
+
+	dma_async_tx_descriptor_init(&mxs_chan->desc, chan);
+	mxs_chan->desc.tx_submit = mxs_dma_tx_submit;
+
+	/* the descriptor is ready */
+	async_tx_ack(&mxs_chan->desc);
+
+	return 0;
+
+err_clk:
+	free_irq(mxs_chan->chan_irq, mxs_dma);
+err_irq:
+	dma_free_coherent(mxs_dma->dma_device.dev, PAGE_SIZE,
+			mxs_chan->ccw, mxs_chan->ccw_phys);
+err_alloc:
+	return ret;
+}
+
+static void mxs_dma_free_chan_resources(struct dma_chan *chan)
+{
+	struct mxs_dma_chan *mxs_chan = to_mxs_dma_chan(chan);
+	struct mxs_dma_engine *mxs_dma = mxs_chan->mxs_dma;
+
+	mxs_dma_disable_chan(mxs_chan);
+
+	free_irq(mxs_chan->chan_irq, mxs_dma);
+
+	dma_free_coherent(mxs_dma->dma_device.dev, PAGE_SIZE,
+			mxs_chan->ccw, mxs_chan->ccw_phys);
+
+	clk_disable(mxs_dma->clk);
+}
+
+static struct dma_async_tx_descriptor *mxs_dma_prep_slave_sg(
+		struct dma_chan *chan, struct scatterlist *sgl,
+		unsigned int sg_len, enum dma_data_direction direction,
+		unsigned long append)
+{
+	struct mxs_dma_chan *mxs_chan = to_mxs_dma_chan(chan);
+	struct mxs_dma_engine *mxs_dma = mxs_chan->mxs_dma;
+	struct mxs_dma_ccw *ccw;
+	struct scatterlist *sg;
+	int i, j;
+	u32 *pio;
+	static int idx;
+
+	if (mxs_chan->status == DMA_IN_PROGRESS && !append)
+		return NULL;
+
+	if (sg_len + (append ? idx : 0) > NUM_CCW) {
+		dev_err(mxs_dma->dma_device.dev,
+				"maximum number of sg exceeded: %d > %d\n",
+				sg_len, NUM_CCW);
+		goto err_out;
+	}
+
+	mxs_chan->status = DMA_IN_PROGRESS;
+	mxs_chan->flags = 0;
+
+	/*
+	 * If the sg is prepared with append flag set, the sg
+	 * will be appended to the last prepared sg.
+	 */
+	if (append) {
+		BUG_ON(idx < 1);
+		ccw = &mxs_chan->ccw[idx - 1];
+		ccw->next = mxs_chan->ccw_phys + sizeof(*ccw) * idx;
+		ccw->bits |= CCW_CHAIN;
+		ccw->bits &= ~CCW_IRQ;
+		ccw->bits &= ~CCW_DEC_SEM;
+		ccw->bits &= ~CCW_WAIT4END;
+	} else {
+		idx = 0;
+	}
+
+	if (direction == DMA_NONE) {
+		ccw = &mxs_chan->ccw[idx++];
+		pio = (u32 *) sgl;
+
+		for (j = 0; j < sg_len;)
+			ccw->pio_words[j++] = *pio++;
+
+		ccw->bits = 0;
+		ccw->bits |= CCW_IRQ;
+		ccw->bits |= CCW_DEC_SEM;
+		ccw->bits |= CCW_WAIT4END;
+		ccw->bits |= CCW_HALT_ON_TERM;
+		ccw->bits |= CCW_TERM_FLUSH;
+		ccw->bits |= BF_CCW(sg_len, PIO_NUM);
+		ccw->bits |= BF_CCW(MXS_DMA_CMD_NO_XFER, COMMAND);
+	} else {
+		for_each_sg(sgl, sg, sg_len, i) {
+			if (sg->length > MAX_XFER_BYTES) {
+				dev_err(mxs_dma->dma_device.dev, "maximum bytes for sg entry exceeded: %d > %d\n",
+						sg->length, MAX_XFER_BYTES);
+				goto err_out;
+			}
+
+			ccw = &mxs_chan->ccw[idx++];
+
+			ccw->next = mxs_chan->ccw_phys + sizeof(*ccw) * idx;
+			ccw->bufaddr = sg->dma_address;
+			ccw->xfer_bytes = sg->length;
+
+			ccw->bits = 0;
+			ccw->bits |= CCW_CHAIN;
+			ccw->bits |= CCW_HALT_ON_TERM;
+			ccw->bits |= CCW_TERM_FLUSH;
+			ccw->bits |= BF_CCW(direction == DMA_FROM_DEVICE ?
+					MXS_DMA_CMD_WRITE : MXS_DMA_CMD_READ,
+					COMMAND);
+
+			if (i + 1 == sg_len) {
+				ccw->bits &= ~CCW_CHAIN;
+				ccw->bits |= CCW_IRQ;
+				ccw->bits |= CCW_DEC_SEM;
+				ccw->bits |= CCW_WAIT4END;
+			}
+		}
+	}
+
+	return &mxs_chan->desc;
+
+err_out:
+	mxs_chan->status = DMA_ERROR;
+	return NULL;
+}
+
+static struct dma_async_tx_descriptor *mxs_dma_prep_dma_cyclic(
+		struct dma_chan *chan, dma_addr_t dma_addr, size_t buf_len,
+		size_t period_len, enum dma_data_direction direction)
+{
+	struct mxs_dma_chan *mxs_chan = to_mxs_dma_chan(chan);
+	struct mxs_dma_engine *mxs_dma = mxs_chan->mxs_dma;
+	int num_periods = buf_len / period_len;
+	int i = 0, buf = 0;
+
+	if (mxs_chan->status == DMA_IN_PROGRESS)
+		return NULL;
+
+	mxs_chan->status = DMA_IN_PROGRESS;
+	mxs_chan->flags |= MXS_DMA_SG_LOOP;
+
+	if (num_periods > NUM_CCW) {
+		dev_err(mxs_dma->dma_device.dev,
+				"maximum number of sg exceeded: %d > %d\n",
+				num_periods, NUM_CCW);
+		goto err_out;
+	}
+
+	if (period_len > MAX_XFER_BYTES) {
+		dev_err(mxs_dma->dma_device.dev,
+				"maximum period size exceeded: %d > %d\n",
+				period_len, MAX_XFER_BYTES);
+		goto err_out;
+	}
+
+	while (buf < buf_len) {
+		struct mxs_dma_ccw *ccw = &mxs_chan->ccw[i];
+
+		if (i + 1 == num_periods)
+			ccw->next = mxs_chan->ccw_phys;
+		else
+			ccw->next = mxs_chan->ccw_phys + sizeof(*ccw) * (i + 1);
+
+		ccw->bufaddr = dma_addr;
+		ccw->xfer_bytes = period_len;
+
+		ccw->bits = 0;
+		ccw->bits |= CCW_CHAIN;
+		ccw->bits |= CCW_IRQ;
+		ccw->bits |= CCW_HALT_ON_TERM;
+		ccw->bits |= CCW_TERM_FLUSH;
+		ccw->bits |= BF_CCW(direction == DMA_FROM_DEVICE ?
+				MXS_DMA_CMD_WRITE : MXS_DMA_CMD_READ, COMMAND);
+
+		dma_addr += period_len;
+		buf += period_len;
+
+		i++;
+	}
+
+	return &mxs_chan->desc;
+
+err_out:
+	mxs_chan->status = DMA_ERROR;
+	return NULL;
+}
+
+static int mxs_dma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
+		unsigned long arg)
+{
+	struct mxs_dma_chan *mxs_chan = to_mxs_dma_chan(chan);
+	int ret = 0;
+
+	switch (cmd) {
+	case DMA_TERMINATE_ALL:
+		mxs_dma_disable_chan(mxs_chan);
+		break;
+	case DMA_PAUSE:
+		mxs_dma_pause_chan(mxs_chan);
+		break;
+	case DMA_RESUME:
+		mxs_dma_resume_chan(mxs_chan);
+		break;
+	default:
+		ret = -ENOSYS;
+	}
+
+	return ret;
+}
+
+static enum dma_status mxs_dma_tx_status(struct dma_chan *chan,
+			dma_cookie_t cookie, struct dma_tx_state *txstate)
+{
+	struct mxs_dma_chan *mxs_chan = to_mxs_dma_chan(chan);
+	dma_cookie_t last_used;
+
+	last_used = chan->cookie;
+	dma_set_tx_state(txstate, mxs_chan->last_completed, last_used, 0);
+
+	return mxs_chan->status;
+}
+
+static void mxs_dma_issue_pending(struct dma_chan *chan)
+{
+	/*
+	 * Nothing to do. We only have a single descriptor.
+	 */
+}
+
+static int __init mxs_dma_init(struct mxs_dma_engine *mxs_dma)
+{
+	int ret;
+
+	ret = clk_enable(mxs_dma->clk);
+	if (ret)
+		goto err_out;
+
+	ret = mxs_reset_block(mxs_dma->base);
+	if (ret)
+		goto err_out;
+
+	/* only major version matters */
+	mxs_dma->version = readl(mxs_dma->base +
+				((mxs_dma->dev_id == MXS_DMA_APBX) ?
+				HW_APBX_VERSION : HW_APBH_VERSION)) >>
+				BP_APBHX_VERSION_MAJOR;
+
+	/* enable apbh burst */
+	if (dma_is_apbh()) {
+		writel(BM_APBH_CTRL0_APB_BURST_EN,
+			mxs_dma->base + HW_APBHX_CTRL0 + MXS_SET_ADDR);
+		writel(BM_APBH_CTRL0_APB_BURST8_EN,
+			mxs_dma->base + HW_APBHX_CTRL0 + MXS_SET_ADDR);
+	}
+
+	/* enable irq for all the channels */
+	writel(MXS_DMA_CHANNELS_MASK << MXS_DMA_CHANNELS,
+		mxs_dma->base + HW_APBHX_CTRL1 + MXS_SET_ADDR);
+
+	clk_disable(mxs_dma->clk);
+
+	return 0;
+
+err_out:
+	return ret;
+}
+
+static int __init mxs_dma_probe(struct platform_device *pdev)
+{
+	const struct platform_device_id *id_entry =
+				platform_get_device_id(pdev);
+	struct mxs_dma_engine *mxs_dma;
+	struct resource *iores;
+	int ret, i;
+
+	mxs_dma = kzalloc(sizeof(*mxs_dma), GFP_KERNEL);
+	if (!mxs_dma)
+		return -ENOMEM;
+
+	mxs_dma->dev_id = id_entry->driver_data;
+
+	iores = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+
+	if (!request_mem_region(iores->start, resource_size(iores),
+				pdev->name)) {
+		ret = -EBUSY;
+		goto err_request_region;
+	}
+
+	mxs_dma->base = ioremap(iores->start, resource_size(iores));
+	if (!mxs_dma->base) {
+		ret = -ENOMEM;
+		goto err_ioremap;
+	}
+
+	mxs_dma->clk = clk_get(&pdev->dev, NULL);
+	if (IS_ERR(mxs_dma->clk)) {
+		ret = PTR_ERR(mxs_dma->clk);
+		goto err_clk;
+	}
+
+	dma_cap_set(DMA_SLAVE, mxs_dma->dma_device.cap_mask);
+	dma_cap_set(DMA_CYCLIC, mxs_dma->dma_device.cap_mask);
+
+	INIT_LIST_HEAD(&mxs_dma->dma_device.channels);
+
+	/* Initialize channel parameters */
+	for (i = 0; i < MXS_DMA_CHANNELS; i++) {
+		struct mxs_dma_chan *mxs_chan = &mxs_dma->mxs_chans[i];
+
+		mxs_chan->mxs_dma = mxs_dma;
+		mxs_chan->chan.device = &mxs_dma->dma_device;
+
+		tasklet_init(&mxs_chan->tasklet, mxs_dma_tasklet,
+			     (unsigned long) mxs_chan);
+
+
+		/* Add the channel to mxs_chan list */
+		list_add_tail(&mxs_chan->chan.device_node,
+			&mxs_dma->dma_device.channels);
+	}
+
+	ret = mxs_dma_init(mxs_dma);
+	if (ret)
+		goto err_init;
+
+	mxs_dma->dma_device.dev = &pdev->dev;
+
+	/* mxs_dma gets 65535 bytes maximum sg size */
+	mxs_dma->dma_device.dev->dma_parms = &mxs_dma->dma_parms;
+	dma_set_max_seg_size(mxs_dma->dma_device.dev, MAX_XFER_BYTES);
+
+	mxs_dma->dma_device.device_alloc_chan_resources = mxs_dma_alloc_chan_resources;
+	mxs_dma->dma_device.device_free_chan_resources = mxs_dma_free_chan_resources;
+	mxs_dma->dma_device.device_tx_status = mxs_dma_tx_status;
+	mxs_dma->dma_device.device_prep_slave_sg = mxs_dma_prep_slave_sg;
+	mxs_dma->dma_device.device_prep_dma_cyclic = mxs_dma_prep_dma_cyclic;
+	mxs_dma->dma_device.device_control = mxs_dma_control;
+	mxs_dma->dma_device.device_issue_pending = mxs_dma_issue_pending;
+
+	ret = dma_async_device_register(&mxs_dma->dma_device);
+	if (ret) {
+		dev_err(mxs_dma->dma_device.dev, "unable to register\n");
+		goto err_init;
+	}
+
+	dev_info(mxs_dma->dma_device.dev, "initialized\n");
+
+	return 0;
+
+err_init:
+	clk_put(mxs_dma->clk);
+err_clk:
+	iounmap(mxs_dma->base);
+err_ioremap:
+	release_mem_region(iores->start, resource_size(iores));
+err_request_region:
+	kfree(mxs_dma);
+	return ret;
+}
+
+static struct platform_device_id mxs_dma_type[] = {
+	{
+		.name = "mxs-dma-apbh",
+		.driver_data = MXS_DMA_APBH,
+	}, {
+		.name = "mxs-dma-apbx",
+		.driver_data = MXS_DMA_APBX,
+	}
+};
+
+static struct platform_driver mxs_dma_driver = {
+	.driver		= {
+		.name	= "mxs-dma",
+	},
+	.id_table	= mxs_dma_type,
+};
+
+static int __init mxs_dma_module_init(void)
+{
+	return platform_driver_probe(&mxs_dma_driver, mxs_dma_probe);
+}
+subsys_initcall(mxs_dma_module_init);
diff --git a/drivers/dma/pch_dma.c b/drivers/dma/pch_dma.c
index 1c38418..8d8fef1 100644
--- a/drivers/dma/pch_dma.c
+++ b/drivers/dma/pch_dma.c
@@ -82,7 +82,7 @@ struct pch_dma_regs {
 	u32	dma_sts1;
 	u32	reserved2;
 	u32	reserved3;
-	struct pch_dma_desc_regs desc[0];
+	struct pch_dma_desc_regs desc[MAX_CHAN_NR];
 };
 
 struct pch_dma_desc {
@@ -124,7 +124,7 @@ struct pch_dma {
 	struct pci_pool		*pool;
 	struct pch_dma_regs	regs;
 	struct pch_dma_desc_regs ch_regs[MAX_CHAN_NR];
-	struct pch_dma_chan	channels[0];
+	struct pch_dma_chan	channels[MAX_CHAN_NR];
 };
 
 #define PCH_DMA_CTL0	0x00
@@ -366,7 +366,7 @@ static dma_cookie_t pd_tx_submit(struct dma_async_tx_descriptor *txd)
 	struct pch_dma_chan *pd_chan = to_pd_chan(txd->chan);
 	dma_cookie_t cookie;
 
-	spin_lock_bh(&pd_chan->lock);
+	spin_lock(&pd_chan->lock);
 	cookie = pdc_assign_cookie(pd_chan, desc);
 
 	if (list_empty(&pd_chan->active_list)) {
@@ -376,7 +376,7 @@ static dma_cookie_t pd_tx_submit(struct dma_async_tx_descriptor *txd)
 		list_add_tail(&desc->desc_node, &pd_chan->queue);
 	}
 
-	spin_unlock_bh(&pd_chan->lock);
+	spin_unlock(&pd_chan->lock);
 	return 0;
 }
 
@@ -386,7 +386,7 @@ static struct pch_dma_desc *pdc_alloc_desc(struct dma_chan *chan, gfp_t flags)
 	struct pch_dma *pd = to_pd(chan->device);
 	dma_addr_t addr;
 
-	desc = pci_pool_alloc(pd->pool, GFP_KERNEL, &addr);
+	desc = pci_pool_alloc(pd->pool, flags, &addr);
 	if (desc) {
 		memset(desc, 0, sizeof(struct pch_dma_desc));
 		INIT_LIST_HEAD(&desc->tx_list);
@@ -405,7 +405,7 @@ static struct pch_dma_desc *pdc_desc_get(struct pch_dma_chan *pd_chan)
 	struct pch_dma_desc *ret = NULL;
 	int i;
 
-	spin_lock_bh(&pd_chan->lock);
+	spin_lock(&pd_chan->lock);
 	list_for_each_entry_safe(desc, _d, &pd_chan->free_list, desc_node) {
 		i++;
 		if (async_tx_test_ack(&desc->txd)) {
@@ -415,15 +415,15 @@ static struct pch_dma_desc *pdc_desc_get(struct pch_dma_chan *pd_chan)
 		}
 		dev_dbg(chan2dev(&pd_chan->chan), "desc %p not ACKed\n", desc);
 	}
-	spin_unlock_bh(&pd_chan->lock);
+	spin_unlock(&pd_chan->lock);
 	dev_dbg(chan2dev(&pd_chan->chan), "scanned %d descriptors\n", i);
 
 	if (!ret) {
 		ret = pdc_alloc_desc(&pd_chan->chan, GFP_NOIO);
 		if (ret) {
-			spin_lock_bh(&pd_chan->lock);
+			spin_lock(&pd_chan->lock);
 			pd_chan->descs_allocated++;
-			spin_unlock_bh(&pd_chan->lock);
+			spin_unlock(&pd_chan->lock);
 		} else {
 			dev_err(chan2dev(&pd_chan->chan),
 				"failed to alloc desc\n");
@@ -437,10 +437,10 @@ static void pdc_desc_put(struct pch_dma_chan *pd_chan,
 			 struct pch_dma_desc *desc)
 {
 	if (desc) {
-		spin_lock_bh(&pd_chan->lock);
+		spin_lock(&pd_chan->lock);
 		list_splice_init(&desc->tx_list, &pd_chan->free_list);
 		list_add(&desc->desc_node, &pd_chan->free_list);
-		spin_unlock_bh(&pd_chan->lock);
+		spin_unlock(&pd_chan->lock);
 	}
 }
 
@@ -530,9 +530,9 @@ static void pd_issue_pending(struct dma_chan *chan)
 	struct pch_dma_chan *pd_chan = to_pd_chan(chan);
 
 	if (pdc_is_idle(pd_chan)) {
-		spin_lock_bh(&pd_chan->lock);
+		spin_lock(&pd_chan->lock);
 		pdc_advance_work(pd_chan);
-		spin_unlock_bh(&pd_chan->lock);
+		spin_unlock(&pd_chan->lock);
 	}
 }
 
@@ -592,7 +592,6 @@ static struct dma_async_tx_descriptor *pd_prep_slave_sg(struct dma_chan *chan,
 			goto err_desc_get;
 		}
 
-
 		if (!first) {
 			first = desc;
 		} else {
@@ -641,13 +640,13 @@ static int pd_device_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 
 	spin_unlock_bh(&pd_chan->lock);
 
-
 	return 0;
 }
 
 static void pdc_tasklet(unsigned long data)
 {
 	struct pch_dma_chan *pd_chan = (struct pch_dma_chan *)data;
+	unsigned long flags;
 
 	if (!pdc_is_idle(pd_chan)) {
 		dev_err(chan2dev(&pd_chan->chan),
@@ -655,12 +654,12 @@ static void pdc_tasklet(unsigned long data)
 		return;
 	}
 
-	spin_lock_bh(&pd_chan->lock);
+	spin_lock_irqsave(&pd_chan->lock, flags);
 	if (test_and_clear_bit(0, &pd_chan->err_status))
 		pdc_handle_error(pd_chan);
 	else
 		pdc_advance_work(pd_chan);
-	spin_unlock_bh(&pd_chan->lock);
+	spin_unlock_irqrestore(&pd_chan->lock, flags);
 }
 
 static irqreturn_t pd_irq(int irq, void *devid)
@@ -694,6 +693,7 @@ static irqreturn_t pd_irq(int irq, void *devid)
 	return ret;
 }
 
+#ifdef	CONFIG_PM
 static void pch_dma_save_regs(struct pch_dma *pd)
 {
 	struct pch_dma_chan *pd_chan;
@@ -771,6 +771,7 @@ static int pch_dma_resume(struct pci_dev *pdev)
 
 	return 0;
 }
+#endif
 
 static int __devinit pch_dma_probe(struct pci_dev *pdev,
 				   const struct pci_device_id *id)
diff --git a/include/linux/dw_dmac.h b/include/linux/dw_dmac.h
index deec66b..6998d93 100644
--- a/include/linux/dw_dmac.h
+++ b/include/linux/dw_dmac.h
@@ -22,6 +22,12 @@
 struct dw_dma_platform_data {
 	unsigned int	nr_channels;
 	bool		is_private;
+#define CHAN_ALLOCATION_ASCENDING	0	/* zero to seven */
+#define CHAN_ALLOCATION_DESCENDING	1	/* seven to zero */
+	unsigned char	chan_allocation_order;
+#define CHAN_PRIORITY_ASCENDING		0	/* chan0 highest */
+#define CHAN_PRIORITY_DESCENDING	1	/* chan7 highest */
+	unsigned char	chan_priority;
 };
 
 /**
@@ -36,6 +42,30 @@ enum dw_dma_slave_width {
 	DW_DMA_SLAVE_WIDTH_32BIT,
 };
 
+/* bursts size */
+enum dw_dma_msize {
+	DW_DMA_MSIZE_1,
+	DW_DMA_MSIZE_4,
+	DW_DMA_MSIZE_8,
+	DW_DMA_MSIZE_16,
+	DW_DMA_MSIZE_32,
+	DW_DMA_MSIZE_64,
+	DW_DMA_MSIZE_128,
+	DW_DMA_MSIZE_256,
+};
+
+/* flow controller */
+enum dw_dma_fc {
+	DW_DMA_FC_D_M2M,
+	DW_DMA_FC_D_M2P,
+	DW_DMA_FC_D_P2M,
+	DW_DMA_FC_D_P2P,
+	DW_DMA_FC_P_P2M,
+	DW_DMA_FC_SP_P2P,
+	DW_DMA_FC_P_M2P,
+	DW_DMA_FC_DP_P2P,
+};
+
 /**
  * struct dw_dma_slave - Controller-specific information about a slave
  *
@@ -47,6 +77,11 @@ enum dw_dma_slave_width {
  * @reg_width: peripheral register width
  * @cfg_hi: Platform-specific initializer for the CFG_HI register
  * @cfg_lo: Platform-specific initializer for the CFG_LO register
+ * @src_master: src master for transfers on allocated channel.
+ * @dst_master: dest master for transfers on allocated channel.
+ * @src_msize: src burst size.
+ * @dst_msize: dest burst size.
+ * @fc: flow controller for DMA transfer
  */
 struct dw_dma_slave {
 	struct device		*dma_dev;
@@ -55,8 +90,11 @@ struct dw_dma_slave {
 	enum dw_dma_slave_width	reg_width;
 	u32			cfg_hi;
 	u32			cfg_lo;
-	int			src_master;
-	int			dst_master;
+	u8			src_master;
+	u8			dst_master;
+	u8			src_msize;
+	u8			dst_msize;
+	u8			fc;
 };
 
 /* Platform-configurable bits in CFG_HI */
@@ -67,7 +105,6 @@ struct dw_dma_slave {
 #define DWC_CFGH_DST_PER(x)	((x) << 11)
 
 /* Platform-configurable bits in CFG_LO */
-#define DWC_CFGL_PRIO(x)	((x) << 5)	/* priority */
 #define DWC_CFGL_LOCK_CH_XFER	(0 << 12)	/* scope of LOCK_CH */
 #define DWC_CFGL_LOCK_CH_BLOCK	(1 << 12)
 #define DWC_CFGL_LOCK_CH_XACT	(2 << 12)