Merge branch 'next' of git://git.infradead.org/users/vkoul/slave-dma

Pull slave-dmaengine updates from Vinod Koul:
 "This time we have Andy updates on dw_dmac which is attempting to make
  this IP block available as PCI and platform device though not fully
  complete this time.

  We also have TI EDMA moving the dma driver to use dmaengine APIs, also
  have a new driver for mmp-tdma, along with bunch of small updates.

  Now for your excitement the merge is little unusual here, while
  merging the auto merge on linux-next picks wrong choice for pl330
  (drivers/dma/pl330.c) and this causes build failure.  The correct
  resolution is in linux-next.  (DMA: PL330: Fix build error) I didn't
  back merge your tree this time as you are better than me so no point
  in doing that for me :)"

Fixed the pl330 conflict as in linux-next, along with trivial header
file conflicts due to changed includes.

* 'next' of git://git.infradead.org/users/vkoul/slave-dma: (29 commits)
  dma: tegra: fix interrupt name issue with apb dma.
  dw_dmac: fix a regression in dwc_prep_dma_memcpy
  dw_dmac: introduce software emulation of LLP transfers
  dw_dmac: autoconfigure data_width or get it via platform data
  dw_dmac: autoconfigure block_size or use platform data
  dw_dmac: get number of channels from hardware if possible
  dw_dmac: fill optional encoded parameters in register structure
  dw_dmac: mark dwc_dump_chan_regs as inline
  DMA: PL330: return ENOMEM instead of 0 from pl330_alloc_chan_resources
  DMA: PL330: Remove redundant runtime_suspend/resume functions
  DMA: PL330: Remove controller clock enable/disable
  dmaengine: use kmem_cache_zalloc instead of kmem_cache_alloc/memset
  DMA: PL330: Set the capability of pdm0 and pdm1 as DMA_PRIVATE
  ARM: EXYNOS: Set the capability of pdm0 and pdm1 as DMA_PRIVATE
  dma: tegra: use list_move_tail instead of list_del/list_add_tail
  mxs/dma: Enlarge the CCW descriptor area to 4 pages
  dw_dmac: utilize slave_id to pass request line
  dmaengine: mmp_tdma: add dt support
  dmaengine: mmp-pdma support
  spi: davici - make davinci select edma
  ...

17 files changed, 2022 insertions, 361 deletions

diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index d06ea2950dd..677cd6e4e1a 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -208,6 +208,16 @@ config SIRF_DMA
 	help
 	  Enable support for the CSR SiRFprimaII DMA engine.
 
+config TI_EDMA
+	tristate "TI EDMA support"
+	depends on ARCH_DAVINCI
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	default n
+	help
+	  Enable support for the TI EDMA controller. This DMA
+	  engine is found on TI DaVinci and AM33xx parts.
+
 config ARCH_HAS_ASYNC_TX_FIND_CHANNEL
 	bool
 
@@ -292,6 +302,13 @@ config DMA_OMAP
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
 
+config MMP_PDMA
+	bool "MMP PDMA support"
+	depends on (ARCH_MMP || ARCH_PXA)
+	select DMA_ENGINE
+	help
+	  Support the MMP PDMA engine for PXA and MMP platfrom.
+
 config DMA_ENGINE
 	bool
 
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index 4cf6b128ab9..7428feaa870 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -23,6 +23,7 @@ obj-$(CONFIG_IMX_DMA) += imx-dma.o
 obj-$(CONFIG_MXS_DMA) += mxs-dma.o
 obj-$(CONFIG_TIMB_DMA) += timb_dma.o
 obj-$(CONFIG_SIRF_DMA) += sirf-dma.o
+obj-$(CONFIG_TI_EDMA) += edma.o
 obj-$(CONFIG_STE_DMA40) += ste_dma40.o ste_dma40_ll.o
 obj-$(CONFIG_TEGRA20_APB_DMA) += tegra20-apb-dma.o
 obj-$(CONFIG_PL330_DMA) += pl330.o
@@ -32,3 +33,4 @@ obj-$(CONFIG_EP93XX_DMA) += ep93xx_dma.o
 obj-$(CONFIG_DMA_SA11X0) += sa11x0-dma.o
 obj-$(CONFIG_MMP_TDMA) += mmp_tdma.o
 obj-$(CONFIG_DMA_OMAP) += omap-dma.o
+obj-$(CONFIG_MMP_PDMA) += mmp_pdma.o
diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c
index 6fbeebb9486..d1cc5791476 100644
--- a/drivers/dma/amba-pl08x.c
+++ b/drivers/dma/amba-pl08x.c
@@ -1892,6 +1892,7 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id)
 	pl08x->pd = dev_get_platdata(&adev->dev);
 	if (!pl08x->pd) {
 		dev_err(&adev->dev, "no platform data supplied\n");
+		ret = -EINVAL;
 		goto out_no_platdata;
 	}
 
@@ -1943,6 +1944,7 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id)
 		dev_err(&adev->dev, "%s failed to allocate "
 			"physical channel holders\n",
 			__func__);
+		ret = -ENOMEM;
 		goto out_no_phychans;
 	}
 
diff --git a/drivers/dma/dw_dmac.c b/drivers/dma/dw_dmac.c
index d3c5a5a88f1..c4b0eb3cde8 100644
--- a/drivers/dma/dw_dmac.c
+++ b/drivers/dma/dw_dmac.c
@@ -36,12 +36,22 @@
  * which does not support descriptor writeback.
  */
 
+static inline unsigned int dwc_get_dms(struct dw_dma_slave *slave)
+{
+	return slave ? slave->dst_master : 0;
+}
+
+static inline unsigned int dwc_get_sms(struct dw_dma_slave *slave)
+{
+	return slave ? slave->src_master : 1;
+}
+
 #define DWC_DEFAULT_CTLLO(_chan) ({				\
 		struct dw_dma_slave *__slave = (_chan->private);	\
 		struct dw_dma_chan *_dwc = to_dw_dma_chan(_chan);	\
 		struct dma_slave_config	*_sconfig = &_dwc->dma_sconfig;	\
-		int _dms = __slave ? __slave->dst_master : 0;	\
-		int _sms = __slave ? __slave->src_master : 1;	\
+		int _dms = dwc_get_dms(__slave);		\
+		int _sms = dwc_get_sms(__slave);		\
 		u8 _smsize = __slave ? _sconfig->src_maxburst :	\
 			DW_DMA_MSIZE_16;			\
 		u8 _dmsize = __slave ? _sconfig->dst_maxburst :	\
@@ -56,16 +66,6 @@
 	})
 
 /*
- * This is configuration-dependent and usually a funny size like 4095.
- *
- * Note that this is a transfer count, i.e. if we transfer 32-bit
- * words, we can do 16380 bytes per descriptor.
- *
- * This parameter is also system-specific.
- */
-#define DWC_MAX_COUNT	4095U
-
-/*
  * Number of descriptors to allocate for each channel. This should be
  * made configurable somehow; preferably, the clients (at least the
  * ones using slave transfers) should be able to give us a hint.
@@ -177,6 +177,11 @@ static void dwc_initialize(struct dw_dma_chan *dwc)
 
 		cfghi = dws->cfg_hi;
 		cfglo |= dws->cfg_lo & ~DWC_CFGL_CH_PRIOR_MASK;
+	} else {
+		if (dwc->dma_sconfig.direction == DMA_MEM_TO_DEV)
+			cfghi = DWC_CFGH_DST_PER(dwc->dma_sconfig.slave_id);
+		else if (dwc->dma_sconfig.direction == DMA_DEV_TO_MEM)
+			cfghi = DWC_CFGH_SRC_PER(dwc->dma_sconfig.slave_id);
 	}
 
 	channel_writel(dwc, CFG_LO, cfglo);
@@ -206,7 +211,7 @@ static inline unsigned int dwc_fast_fls(unsigned long long v)
 	return 0;
 }
 
-static void dwc_dump_chan_regs(struct dw_dma_chan *dwc)
+static inline void dwc_dump_chan_regs(struct dw_dma_chan *dwc)
 {
 	dev_err(chan2dev(&dwc->chan),
 		"  SAR: 0x%x DAR: 0x%x LLP: 0x%x CTL: 0x%x:%08x\n",
@@ -227,10 +232,29 @@ static inline void dwc_chan_disable(struct dw_dma *dw, struct dw_dma_chan *dwc)
 
 /*----------------------------------------------------------------------*/
 
+/* Perform single block transfer */
+static inline void dwc_do_single_block(struct dw_dma_chan *dwc,
+				       struct dw_desc *desc)
+{
+	struct dw_dma	*dw = to_dw_dma(dwc->chan.device);
+	u32		ctllo;
+
+	/* Software emulation of LLP mode relies on interrupts to continue
+	 * multi block transfer. */
+	ctllo = desc->lli.ctllo | DWC_CTLL_INT_EN;
+
+	channel_writel(dwc, SAR, desc->lli.sar);
+	channel_writel(dwc, DAR, desc->lli.dar);
+	channel_writel(dwc, CTL_LO, ctllo);
+	channel_writel(dwc, CTL_HI, desc->lli.ctlhi);
+	channel_set_bit(dw, CH_EN, dwc->mask);
+}
+
 /* Called with dwc->lock held and bh disabled */
 static void dwc_dostart(struct dw_dma_chan *dwc, struct dw_desc *first)
 {
 	struct dw_dma	*dw = to_dw_dma(dwc->chan.device);
+	unsigned long	was_soft_llp;
 
 	/* ASSERT:  channel is idle */
 	if (dma_readl(dw, CH_EN) & dwc->mask) {
@@ -242,6 +266,26 @@ static void dwc_dostart(struct dw_dma_chan *dwc, struct dw_desc *first)
 		return;
 	}
 
+	if (dwc->nollp) {
+		was_soft_llp = test_and_set_bit(DW_DMA_IS_SOFT_LLP,
+						&dwc->flags);
+		if (was_soft_llp) {
+			dev_err(chan2dev(&dwc->chan),
+				"BUG: Attempted to start new LLP transfer "
+				"inside ongoing one\n");
+			return;
+		}
+
+		dwc_initialize(dwc);
+
+		dwc->tx_list = &first->tx_list;
+		dwc->tx_node_active = first->tx_list.next;
+
+		dwc_do_single_block(dwc, first);
+
+		return;
+	}
+
 	dwc_initialize(dwc);
 
 	channel_writel(dwc, LLP, first->txd.phys);
@@ -553,8 +597,36 @@ static void dw_dma_tasklet(unsigned long data)
 			dwc_handle_cyclic(dw, dwc, status_err, status_xfer);
 		else if (status_err & (1 << i))
 			dwc_handle_error(dw, dwc);
-		else if (status_xfer & (1 << i))
+		else if (status_xfer & (1 << i)) {
+			unsigned long flags;
+
+			spin_lock_irqsave(&dwc->lock, flags);
+			if (test_bit(DW_DMA_IS_SOFT_LLP, &dwc->flags)) {
+				if (dwc->tx_node_active != dwc->tx_list) {
+					struct dw_desc *desc =
+						list_entry(dwc->tx_node_active,
+							   struct dw_desc,
+							   desc_node);
+
+					dma_writel(dw, CLEAR.XFER, dwc->mask);
+
+					/* move pointer to next descriptor */
+					dwc->tx_node_active =
+						dwc->tx_node_active->next;
+
+					dwc_do_single_block(dwc, desc);
+
+					spin_unlock_irqrestore(&dwc->lock, flags);
+					continue;
+				} else {
+					/* we are done here */
+					clear_bit(DW_DMA_IS_SOFT_LLP, &dwc->flags);
+				}
+			}
+			spin_unlock_irqrestore(&dwc->lock, flags);
+
 			dwc_scan_descriptors(dw, dwc);
+		}
 	}
 
 	/*
@@ -636,6 +708,7 @@ dwc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 		size_t len, unsigned long flags)
 {
 	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
+	struct dw_dma_slave	*dws = chan->private;
 	struct dw_desc		*desc;
 	struct dw_desc		*first;
 	struct dw_desc		*prev;
@@ -643,6 +716,7 @@ dwc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 	size_t			offset;
 	unsigned int		src_width;
 	unsigned int		dst_width;
+	unsigned int		data_width;
 	u32			ctllo;
 
 	dev_vdbg(chan2dev(chan),
@@ -655,7 +729,11 @@ dwc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 		return NULL;
 	}
 
-	src_width = dst_width = dwc_fast_fls(src | dest | len);
+	data_width = min_t(unsigned int, dwc->dw->data_width[dwc_get_sms(dws)],
+					 dwc->dw->data_width[dwc_get_dms(dws)]);
+
+	src_width = dst_width = min_t(unsigned int, data_width,
+				      dwc_fast_fls(src | dest | len));
 
 	ctllo = DWC_DEFAULT_CTLLO(chan)
 			| DWC_CTLL_DST_WIDTH(dst_width)
@@ -667,7 +745,7 @@ dwc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 
 	for (offset = 0; offset < len; offset += xfer_count << src_width) {
 		xfer_count = min_t(size_t, (len - offset) >> src_width,
-				DWC_MAX_COUNT);
+					   dwc->block_size);
 
 		desc = dwc_desc_get(dwc);
 		if (!desc)
@@ -725,6 +803,7 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	dma_addr_t		reg;
 	unsigned int		reg_width;
 	unsigned int		mem_width;
+	unsigned int		data_width;
 	unsigned int		i;
 	struct scatterlist	*sg;
 	size_t			total_len = 0;
@@ -748,6 +827,8 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		ctllo |= sconfig->device_fc ? DWC_CTLL_FC(DW_DMA_FC_P_M2P) :
 			DWC_CTLL_FC(DW_DMA_FC_D_M2P);
 
+		data_width = dwc->dw->data_width[dwc_get_sms(dws)];
+
 		for_each_sg(sgl, sg, sg_len, i) {
 			struct dw_desc	*desc;
 			u32		len, dlen, mem;
@@ -755,7 +836,8 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 			mem = sg_dma_address(sg);
 			len = sg_dma_len(sg);
 
-			mem_width = dwc_fast_fls(mem | len);
+			mem_width = min_t(unsigned int,
+					  data_width, dwc_fast_fls(mem | len));
 
 slave_sg_todev_fill_desc:
 			desc = dwc_desc_get(dwc);
@@ -768,8 +850,8 @@ slave_sg_todev_fill_desc:
 			desc->lli.sar = mem;
 			desc->lli.dar = reg;
 			desc->lli.ctllo = ctllo | DWC_CTLL_SRC_WIDTH(mem_width);
-			if ((len >> mem_width) > DWC_MAX_COUNT) {
-				dlen = DWC_MAX_COUNT << mem_width;
+			if ((len >> mem_width) > dwc->block_size) {
+				dlen = dwc->block_size << mem_width;
 				mem += dlen;
 				len -= dlen;
 			} else {
@@ -808,6 +890,8 @@ slave_sg_todev_fill_desc:
 		ctllo |= sconfig->device_fc ? DWC_CTLL_FC(DW_DMA_FC_P_P2M) :
 			DWC_CTLL_FC(DW_DMA_FC_D_P2M);
 
+		data_width = dwc->dw->data_width[dwc_get_dms(dws)];
+
 		for_each_sg(sgl, sg, sg_len, i) {
 			struct dw_desc	*desc;
 			u32		len, dlen, mem;
@@ -815,7 +899,8 @@ slave_sg_todev_fill_desc:
 			mem = sg_dma_address(sg);
 			len = sg_dma_len(sg);
 
-			mem_width = dwc_fast_fls(mem | len);
+			mem_width = min_t(unsigned int,
+					  data_width, dwc_fast_fls(mem | len));
 
 slave_sg_fromdev_fill_desc:
 			desc = dwc_desc_get(dwc);
@@ -828,8 +913,8 @@ slave_sg_fromdev_fill_desc:
 			desc->lli.sar = reg;
 			desc->lli.dar = mem;
 			desc->lli.ctllo = ctllo | DWC_CTLL_DST_WIDTH(mem_width);
-			if ((len >> reg_width) > DWC_MAX_COUNT) {
-				dlen = DWC_MAX_COUNT << reg_width;
+			if ((len >> reg_width) > dwc->block_size) {
+				dlen = dwc->block_size << reg_width;
 				mem += dlen;
 				len -= dlen;
 			} else {
@@ -945,6 +1030,8 @@ static int dwc_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 	} else if (cmd == DMA_TERMINATE_ALL) {
 		spin_lock_irqsave(&dwc->lock, flags);
 
+		clear_bit(DW_DMA_IS_SOFT_LLP, &dwc->flags);
+
 		dwc_chan_disable(dw, dwc);
 
 		dwc->paused = false;
@@ -1187,6 +1274,13 @@ struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan,
 	unsigned long			flags;
 
 	spin_lock_irqsave(&dwc->lock, flags);
+	if (dwc->nollp) {
+		spin_unlock_irqrestore(&dwc->lock, flags);
+		dev_dbg(chan2dev(&dwc->chan),
+				"channel doesn't support LLP transfers\n");
+		return ERR_PTR(-EINVAL);
+	}
+
 	if (!list_empty(&dwc->queue) || !list_empty(&dwc->active_list)) {
 		spin_unlock_irqrestore(&dwc->lock, flags);
 		dev_dbg(chan2dev(&dwc->chan),
@@ -1212,7 +1306,7 @@ struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan,
 	periods = buf_len / period_len;
 
 	/* Check for too big/unaligned periods and unaligned DMA buffer. */
-	if (period_len > (DWC_MAX_COUNT << reg_width))
+	if (period_len > (dwc->block_size << reg_width))
 		goto out_err;
 	if (unlikely(period_len & ((1 << reg_width) - 1)))
 		goto out_err;
@@ -1374,6 +1468,11 @@ static int __devinit dw_probe(struct platform_device *pdev)
 	struct resource		*io;
 	struct dw_dma		*dw;
 	size_t			size;
+	void __iomem		*regs;
+	bool			autocfg;
+	unsigned int		dw_params;
+	unsigned int		nr_channels;
+	unsigned int		max_blk_size = 0;
 	int			irq;
 	int			err;
 	int			i;
@@ -1390,32 +1489,46 @@ static int __devinit dw_probe(struct platform_device *pdev)
 	if (irq < 0)
 		return irq;
 
-	size = sizeof(struct dw_dma);
-	size += pdata->nr_channels * sizeof(struct dw_dma_chan);
-	dw = kzalloc(size, GFP_KERNEL);
+	regs = devm_request_and_ioremap(&pdev->dev, io);
+	if (!regs)
+		return -EBUSY;
+
+	dw_params = dma_read_byaddr(regs, DW_PARAMS);
+	autocfg = dw_params >> DW_PARAMS_EN & 0x1;
+
+	if (autocfg)
+		nr_channels = (dw_params >> DW_PARAMS_NR_CHAN & 0x7) + 1;
+	else
+		nr_channels = pdata->nr_channels;
+
+	size = sizeof(struct dw_dma) + nr_channels * sizeof(struct dw_dma_chan);
+	dw = devm_kzalloc(&pdev->dev, size, GFP_KERNEL);
 	if (!dw)
 		return -ENOMEM;
 
-	if (!request_mem_region(io->start, DW_REGLEN, pdev->dev.driver->name)) {
-		err = -EBUSY;
-		goto err_kfree;
-	}
+	dw->clk = devm_clk_get(&pdev->dev, "hclk");
+	if (IS_ERR(dw->clk))
+		return PTR_ERR(dw->clk);
+	clk_prepare_enable(dw->clk);
 
-	dw->regs = ioremap(io->start, DW_REGLEN);
-	if (!dw->regs) {
-		err = -ENOMEM;
-		goto err_release_r;
-	}
+	dw->regs = regs;
+
+	/* get hardware configuration parameters */
+	if (autocfg) {
+		max_blk_size = dma_readl(dw, MAX_BLK_SIZE);
 
-	dw->clk = clk_get(&pdev->dev, "hclk");
-	if (IS_ERR(dw->clk)) {
-		err = PTR_ERR(dw->clk);
-		goto err_clk;
+		dw->nr_masters = (dw_params >> DW_PARAMS_NR_MASTER & 3) + 1;
+		for (i = 0; i < dw->nr_masters; i++) {
+			dw->data_width[i] =
+				(dw_params >> DW_PARAMS_DATA_WIDTH(i) & 3) + 2;
+		}
+	} else {
+		dw->nr_masters = pdata->nr_masters;
+		memcpy(dw->data_width, pdata->data_width, 4);
 	}
-	clk_prepare_enable(dw->clk);
 
 	/* Calculate all channel mask before DMA setup */
-	dw->all_chan_mask = (1 << pdata->nr_channels) - 1;
+	dw->all_chan_mask = (1 << nr_channels) - 1;
 
 	/* force dma off, just in case */
 	dw_dma_off(dw);
@@ -1423,17 +1536,19 @@ static int __devinit dw_probe(struct platform_device *pdev)
 	/* disable BLOCK interrupts as well */
 	channel_clear_bit(dw, MASK.BLOCK, dw->all_chan_mask);
 
-	err = request_irq(irq, dw_dma_interrupt, 0, "dw_dmac", dw);
+	err = devm_request_irq(&pdev->dev, irq, dw_dma_interrupt, 0,
+			       "dw_dmac", dw);
 	if (err)
-		goto err_irq;
+		return err;
 
 	platform_set_drvdata(pdev, dw);
 
 	tasklet_init(&dw->tasklet, dw_dma_tasklet, (unsigned long)dw);
 
 	INIT_LIST_HEAD(&dw->dma.channels);
-	for (i = 0; i < pdata->nr_channels; i++) {
+	for (i = 0; i < nr_channels; i++) {
 		struct dw_dma_chan	*dwc = &dw->chan[i];
+		int			r = nr_channels - i - 1;
 
 		dwc->chan.device = &dw->dma;
 		dma_cookie_init(&dwc->chan);
@@ -1445,7 +1560,7 @@ static int __devinit dw_probe(struct platform_device *pdev)
 
 		/* 7 is highest priority & 0 is lowest. */
 		if (pdata->chan_priority == CHAN_PRIORITY_ASCENDING)
-			dwc->priority = pdata->nr_channels - i - 1;
+			dwc->priority = r;
 		else
 			dwc->priority = i;
 
@@ -1458,6 +1573,32 @@ static int __devinit dw_probe(struct platform_device *pdev)
 		INIT_LIST_HEAD(&dwc->free_list);
 
 		channel_clear_bit(dw, CH_EN, dwc->mask);
+
+		dwc->dw = dw;
+
+		/* hardware configuration */
+		if (autocfg) {
+			unsigned int dwc_params;
+
+			dwc_params = dma_read_byaddr(regs + r * sizeof(u32),
+						     DWC_PARAMS);
+
+			/* Decode maximum block size for given channel. The
+			 * stored 4 bit value represents blocks from 0x00 for 3
+			 * up to 0x0a for 4095. */
+			dwc->block_size =
+				(4 << ((max_blk_size >> 4 * i) & 0xf)) - 1;
+			dwc->nollp =
+				(dwc_params >> DWC_PARAMS_MBLK_EN & 0x1) == 0;
+		} else {
+			dwc->block_size = pdata->block_size;
+
+			/* Check if channel supports multi block transfer */
+			channel_writel(dwc, LLP, 0xfffffffc);
+			dwc->nollp =
+				(channel_readl(dwc, LLP) & 0xfffffffc) == 0;
+			channel_writel(dwc, LLP, 0);
+		}
 	}
 
 	/* Clear all interrupts on all channels. */
@@ -1486,35 +1627,21 @@ static int __devinit dw_probe(struct platform_device *pdev)
 	dma_writel(dw, CFG, DW_CFG_DMA_EN);
 
 	printk(KERN_INFO "%s: DesignWare DMA Controller, %d channels\n",
-			dev_name(&pdev->dev), pdata->nr_channels);
+			dev_name(&pdev->dev), nr_channels);
 
 	dma_async_device_register(&dw->dma);
 
 	return 0;
-
-err_irq:
-	clk_disable_unprepare(dw->clk);
-	clk_put(dw->clk);
-err_clk:
-	iounmap(dw->regs);
-	dw->regs = NULL;
-err_release_r:
-	release_resource(io);
-err_kfree:
-	kfree(dw);
-	return err;
 }
 
 static int __devexit dw_remove(struct platform_device *pdev)
 {
 	struct dw_dma		*dw = platform_get_drvdata(pdev);
 	struct dw_dma_chan	*dwc, *_dwc;
-	struct resource		*io;
 
 	dw_dma_off(dw);
 	dma_async_device_unregister(&dw->dma);
 
-	free_irq(platform_get_irq(pdev, 0), dw);
 	tasklet_kill(&dw->tasklet);
 
 	list_for_each_entry_safe(dwc, _dwc, &dw->dma.channels,
@@ -1523,17 +1650,6 @@ static int __devexit dw_remove(struct platform_device *pdev)
 		channel_clear_bit(dw, CH_EN, dwc->mask);
 	}
 
-	clk_disable_unprepare(dw->clk);
-	clk_put(dw->clk);
-
-	iounmap(dw->regs);
-	dw->regs = NULL;
-
-	io = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	release_mem_region(io->start, DW_REGLEN);
-
-	kfree(dw);
-
 	return 0;
 }
 
diff --git a/drivers/dma/dw_dmac_regs.h b/drivers/dma/dw_dmac_regs.h
index 50830bee087..ff39fa6cd2b 100644
--- a/drivers/dma/dw_dmac_regs.h
+++ b/drivers/dma/dw_dmac_regs.h
@@ -82,9 +82,39 @@ struct dw_dma_regs {
 	DW_REG(ID);
 	DW_REG(TEST);
 
+	/* reserved */
+	DW_REG(__reserved0);
+	DW_REG(__reserved1);
+
 	/* optional encoded params, 0x3c8..0x3f7 */
+	u32	__reserved;
+
+	/* per-channel configuration registers */
+	u32	DWC_PARAMS[DW_DMA_MAX_NR_CHANNELS];
+	u32	MULTI_BLK_TYPE;
+	u32	MAX_BLK_SIZE;
+
+	/* top-level parameters */
+	u32	DW_PARAMS;
 };
 
+/* To access the registers in early stage of probe */
+#define dma_read_byaddr(addr, name) \
+	readl((addr) + offsetof(struct dw_dma_regs, name))
+
+/* Bitfields in DW_PARAMS */
+#define DW_PARAMS_NR_CHAN	8		/* number of channels */
+#define DW_PARAMS_NR_MASTER	11		/* number of AHB masters */
+#define DW_PARAMS_DATA_WIDTH(n)	(15 + 2 * (n))
+#define DW_PARAMS_DATA_WIDTH1	15		/* master 1 data width */
+#define DW_PARAMS_DATA_WIDTH2	17		/* master 2 data width */
+#define DW_PARAMS_DATA_WIDTH3	19		/* master 3 data width */
+#define DW_PARAMS_DATA_WIDTH4	21		/* master 4 data width */
+#define DW_PARAMS_EN		28		/* encoded parameters */
+
+/* Bitfields in DWC_PARAMS */
+#define DWC_PARAMS_MBLK_EN	11		/* multi block transfer */
+
 /* Bitfields in CTL_LO */
 #define DWC_CTLL_INT_EN		(1 << 0)	/* irqs enabled? */
 #define DWC_CTLL_DST_WIDTH(n)	((n)<<1)	/* bytes per element */
@@ -140,10 +170,9 @@ struct dw_dma_regs {
 /* Bitfields in CFG */
 #define DW_CFG_DMA_EN		(1 << 0)
 
-#define DW_REGLEN		0x400
-
 enum dw_dmac_flags {
 	DW_DMA_IS_CYCLIC = 0,
+	DW_DMA_IS_SOFT_LLP = 1,
 };
 
 struct dw_dma_chan {
@@ -154,6 +183,10 @@ struct dw_dma_chan {
 	bool			paused;
 	bool			initialized;
 
+	/* software emulation of the LLP transfers */
+	struct list_head	*tx_list;
+	struct list_head	*tx_node_active;
+
 	spinlock_t		lock;
 
 	/* these other elements are all protected by lock */
@@ -165,8 +198,15 @@ struct dw_dma_chan {
 
 	unsigned int		descs_allocated;
 
+	/* hardware configuration */
+	unsigned int		block_size;
+	bool			nollp;
+
 	/* configuration passed via DMA_SLAVE_CONFIG */
 	struct dma_slave_config dma_sconfig;
+
+	/* backlink to dw_dma */
+	struct dw_dma		*dw;
 };
 
 static inline struct dw_dma_chan_regs __iomem *
@@ -193,6 +233,10 @@ struct dw_dma {
 
 	u8			all_chan_mask;
 
+	/* hardware configuration */
+	unsigned char		nr_masters;
+	unsigned char		data_width[4];
+
 	struct dw_dma_chan	chan[0];
 };
 
diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c
new file mode 100644
index 00000000000..05aea3ce850
--- /dev/null
+++ b/drivers/dma/edma.c
@@ -0,0 +1,671 @@
+/*
+ * TI EDMA DMA engine driver
+ *
+ * Copyright 2012 Texas Instruments
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+#include <mach/edma.h>
+
+#include "dmaengine.h"
+#include "virt-dma.h"
+
+/*
+ * This will go away when the private EDMA API is folded
+ * into this driver and the platform device(s) are
+ * instantiated in the arch code. We can only get away
+ * with this simplification because DA8XX may not be built
+ * in the same kernel image with other DaVinci parts. This
+ * avoids having to sprinkle dmaengine driver platform devices
+ * and data throughout all the existing board files.
+ */
+#ifdef CONFIG_ARCH_DAVINCI_DA8XX
+#define EDMA_CTLRS	2
+#define EDMA_CHANS	32
+#else
+#define EDMA_CTLRS	1
+#define EDMA_CHANS	64
+#endif /* CONFIG_ARCH_DAVINCI_DA8XX */
+
+/* Max of 16 segments per channel to conserve PaRAM slots */
+#define MAX_NR_SG		16
+#define EDMA_MAX_SLOTS		MAX_NR_SG
+#define EDMA_DESCRIPTORS	16
+
+struct edma_desc {
+	struct virt_dma_desc		vdesc;
+	struct list_head		node;
+	int				absync;
+	int				pset_nr;
+	struct edmacc_param		pset[0];
+};
+
+struct edma_cc;
+
+struct edma_chan {
+	struct virt_dma_chan		vchan;
+	struct list_head		node;
+	struct edma_desc		*edesc;
+	struct edma_cc			*ecc;
+	int				ch_num;
+	bool				alloced;
+	int				slot[EDMA_MAX_SLOTS];
+	dma_addr_t			addr;
+	int				addr_width;
+	int				maxburst;
+};
+
+struct edma_cc {
+	int				ctlr;
+	struct dma_device		dma_slave;
+	struct edma_chan		slave_chans[EDMA_CHANS];
+	int				num_slave_chans;
+	int				dummy_slot;
+};
+
+static inline struct edma_cc *to_edma_cc(struct dma_device *d)
+{
+	return container_of(d, struct edma_cc, dma_slave);
+}
+
+static inline struct edma_chan *to_edma_chan(struct dma_chan *c)
+{
+	return container_of(c, struct edma_chan, vchan.chan);
+}
+
+static inline struct edma_desc
+*to_edma_desc(struct dma_async_tx_descriptor *tx)
+{
+	return container_of(tx, struct edma_desc, vdesc.tx);
+}
+
+static void edma_desc_free(struct virt_dma_desc *vdesc)
+{
+	kfree(container_of(vdesc, struct edma_desc, vdesc));
+}
+
+/* Dispatch a queued descriptor to the controller (caller holds lock) */
+static void edma_execute(struct edma_chan *echan)
+{
+	struct virt_dma_desc *vdesc = vchan_next_desc(&echan->vchan);
+	struct edma_desc *edesc;
+	int i;
+
+	if (!vdesc) {
+		echan->edesc = NULL;
+		return;
+	}
+
+	list_del(&vdesc->node);
+
+	echan->edesc = edesc = to_edma_desc(&vdesc->tx);
+
+	/* Write descriptor PaRAM set(s) */
+	for (i = 0; i < edesc->pset_nr; i++) {
+		edma_write_slot(echan->slot[i], &edesc->pset[i]);
+		dev_dbg(echan->vchan.chan.device->dev,
+			"\n pset[%d]:\n"
+			"  chnum\t%d\n"
+			"  slot\t%d\n"
+			"  opt\t%08x\n"
+			"  src\t%08x\n"
+			"  dst\t%08x\n"
+			"  abcnt\t%08x\n"
+			"  ccnt\t%08x\n"
+			"  bidx\t%08x\n"
+			"  cidx\t%08x\n"
+			"  lkrld\t%08x\n",
+			i, echan->ch_num, echan->slot[i],
+			edesc->pset[i].opt,
+			edesc->pset[i].src,
+			edesc->pset[i].dst,
+			edesc->pset[i].a_b_cnt,
+			edesc->pset[i].ccnt,
+			edesc->pset[i].src_dst_bidx,
+			edesc->pset[i].src_dst_cidx,
+			edesc->pset[i].link_bcntrld);
+		/* Link to the previous slot if not the last set */
+		if (i != (edesc->pset_nr - 1))
+			edma_link(echan->slot[i], echan->slot[i+1]);
+		/* Final pset links to the dummy pset */
+		else
+			edma_link(echan->slot[i], echan->ecc->dummy_slot);
+	}
+
+	edma_start(echan->ch_num);
+}
+
+static int edma_terminate_all(struct edma_chan *echan)
+{
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	spin_lock_irqsave(&echan->vchan.lock, flags);
+
+	/*
+	 * Stop DMA activity: we assume the callback will not be called
+	 * after edma_dma() returns (even if it does, it will see
+	 * echan->edesc is NULL and exit.)
+	 */
+	if (echan->edesc) {
+		echan->edesc = NULL;
+		edma_stop(echan->ch_num);
+	}
+
+	vchan_get_all_descriptors(&echan->vchan, &head);
+	spin_unlock_irqrestore(&echan->vchan.lock, flags);
+	vchan_dma_desc_free_list(&echan->vchan, &head);
+
+	return 0;
+}
+
+
+static int edma_slave_config(struct edma_chan *echan,
+	struct dma_slave_config *config)
+{
+	if ((config->src_addr_width > DMA_SLAVE_BUSWIDTH_4_BYTES) ||
+	    (config->dst_addr_width > DMA_SLAVE_BUSWIDTH_4_BYTES))
+		return -EINVAL;
+
+	if (config->direction == DMA_MEM_TO_DEV) {
+		if (config->dst_addr)
+			echan->addr = config->dst_addr;
+		if (config->dst_addr_width)
+			echan->addr_width = config->dst_addr_width;
+		if (config->dst_maxburst)
+			echan->maxburst = config->dst_maxburst;
+	} else if (config->direction == DMA_DEV_TO_MEM) {
+		if (config->src_addr)
+			echan->addr = config->src_addr;
+		if (config->src_addr_width)
+			echan->addr_width = config->src_addr_width;
+		if (config->src_maxburst)
+			echan->maxburst = config->src_maxburst;
+	}
+
+	return 0;
+}
+
+static int edma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
+			unsigned long arg)
+{
+	int ret = 0;
+	struct dma_slave_config *config;
+	struct edma_chan *echan = to_edma_chan(chan);
+
+	switch (cmd) {
+	case DMA_TERMINATE_ALL:
+		edma_terminate_all(echan);
+		break;
+	case DMA_SLAVE_CONFIG:
+		config = (struct dma_slave_config *)arg;
+		ret = edma_slave_config(echan, config);
+		break;
+	default:
+		ret = -ENOSYS;
+	}
+
+	return ret;
+}
+
+static struct dma_async_tx_descriptor *edma_prep_slave_sg(
+	struct dma_chan *chan, struct scatterlist *sgl,
+	unsigned int sg_len, enum dma_transfer_direction direction,
+	unsigned long tx_flags, void *context)
+{
+	struct edma_chan *echan = to_edma_chan(chan);
+	struct device *dev = chan->device->dev;
+	struct edma_desc *edesc;
+	struct scatterlist *sg;
+	int i;
+	int acnt, bcnt, ccnt, src, dst, cidx;
+	int src_bidx, dst_bidx, src_cidx, dst_cidx;
+
+	if (unlikely(!echan || !sgl || !sg_len))
+		return NULL;
+
+	if (echan->addr_width == DMA_SLAVE_BUSWIDTH_UNDEFINED) {
+		dev_err(dev, "Undefined slave buswidth\n");
+		return NULL;
+	}
+
+	if (sg_len > MAX_NR_SG) {
+		dev_err(dev, "Exceeded max SG segments %d > %d\n",
+			sg_len, MAX_NR_SG);
+		return NULL;
+	}
+
+	edesc = kzalloc(sizeof(*edesc) + sg_len *
+		sizeof(edesc->pset[0]), GFP_ATOMIC);
+	if (!edesc) {
+		dev_dbg(dev, "Failed to allocate a descriptor\n");
+		return NULL;
+	}
+
+	edesc->pset_nr = sg_len;
+
+	for_each_sg(sgl, sg, sg_len, i) {
+		/* Allocate a PaRAM slot, if needed */
+		if (echan->slot[i] < 0) {
+			echan->slot[i] =
+				edma_alloc_slot(EDMA_CTLR(echan->ch_num),
+						EDMA_SLOT_ANY);
+			if (echan->slot[i] < 0) {
+				dev_err(dev, "Failed to allocate slot\n");
+				return NULL;
+			}
+		}
+
+		acnt = echan->addr_width;
+
+		/*
+		 * If the maxburst is equal to the fifo width, use
+		 * A-synced transfers. This allows for large contiguous
+		 * buffer transfers using only one PaRAM set.
+		 */
+		if (echan->maxburst == 1) {
+			edesc->absync = false;
+			ccnt = sg_dma_len(sg) / acnt / (SZ_64K - 1);
+			bcnt = sg_dma_len(sg) / acnt - ccnt * (SZ_64K - 1);
+			if (bcnt)
+				ccnt++;
+			else
+				bcnt = SZ_64K - 1;
+			cidx = acnt;
+		/*
+		 * If maxburst is greater than the fifo address_width,
+		 * use AB-synced transfers where A count is the fifo
+		 * address_width and B count is the maxburst. In this
+		 * case, we are limited to transfers of C count frames
+		 * of (address_width * maxburst) where C count is limited
+		 * to SZ_64K-1. This places an upper bound on the length
+		 * of an SG segment that can be handled.
+		 */
+		} else {
+			edesc->absync = true;
+			bcnt = echan->maxburst;
+			ccnt = sg_dma_len(sg) / (acnt * bcnt);
+			if (ccnt > (SZ_64K - 1)) {
+				dev_err(dev, "Exceeded max SG segment size\n");
+				return NULL;
+			}
+			cidx = acnt * bcnt;
+		}
+
+		if (direction == DMA_MEM_TO_DEV) {
+			src = sg_dma_address(sg);
+			dst = echan->addr;
+			src_bidx = acnt;
+			src_cidx = cidx;
+			dst_bidx = 0;
+			dst_cidx = 0;
+		} else {
+			src = echan->addr;
+			dst = sg_dma_address(sg);
+			src_bidx = 0;
+			src_cidx = 0;
+			dst_bidx = acnt;
+			dst_cidx = cidx;
+		}
+
+		edesc->pset[i].opt = EDMA_TCC(EDMA_CHAN_SLOT(echan->ch_num));
+		/* Configure A or AB synchronized transfers */
+		if (edesc->absync)
+			edesc->pset[i].opt |= SYNCDIM;
+		/* If this is the last set, enable completion interrupt flag */
+		if (i == sg_len - 1)
+			edesc->pset[i].opt |= TCINTEN;
+
+		edesc->pset[i].src = src;
+		edesc->pset[i].dst = dst;
+
+		edesc->pset[i].src_dst_bidx = (dst_bidx << 16) | src_bidx;
+		edesc->pset[i].src_dst_cidx = (dst_cidx << 16) | src_cidx;
+
+		edesc->pset[i].a_b_cnt = bcnt << 16 | acnt;
+		edesc->pset[i].ccnt = ccnt;
+		edesc->pset[i].link_bcntrld = 0xffffffff;
+
+	}
+
+	return vchan_tx_prep(&echan->vchan, &edesc->vdesc, tx_flags);
+}
+
+static void edma_callback(unsigned ch_num, u16 ch_status, void *data)
+{
+	struct edma_chan *echan = data;
+	struct device *dev = echan->vchan.chan.device->dev;
+	struct edma_desc *edesc;
+	unsigned long flags;
+
+	/* Stop the channel */
+	edma_stop(echan->ch_num);
+
+	switch (ch_status) {
+	case DMA_COMPLETE:
+		dev_dbg(dev, "transfer complete on channel %d\n", ch_num);
+
+		spin_lock_irqsave(&echan->vchan.lock, flags);
+
+		edesc = echan->edesc;
+		if (edesc) {
+			edma_execute(echan);
+			vchan_cookie_complete(&edesc->vdesc);
+		}
+
+		spin_unlock_irqrestore(&echan->vchan.lock, flags);
+
+		break;
+	case DMA_CC_ERROR:
+		dev_dbg(dev, "transfer error on channel %d\n", ch_num);
+		break;
+	default:
+		break;
+	}
+}
+
+/* Alloc channel resources */
+static int edma_alloc_chan_resources(struct dma_chan *chan)
+{
+	struct edma_chan *echan = to_edma_chan(chan);
+	struct device *dev = chan->device->dev;
+	int ret;
+	int a_ch_num;
+	LIST_HEAD(descs);
+
+	a_ch_num = edma_alloc_channel(echan->ch_num, edma_callback,
+					chan, EVENTQ_DEFAULT);
+
+	if (a_ch_num < 0) {
+		ret = -ENODEV;
+		goto err_no_chan;
+	}
+
+	if (a_ch_num != echan->ch_num) {
+		dev_err(dev, "failed to allocate requested channel %u:%u\n",
+			EDMA_CTLR(echan->ch_num),
+			EDMA_CHAN_SLOT(echan->ch_num));
+		ret = -ENODEV;
+		goto err_wrong_chan;
+	}
+
+	echan->alloced = true;
+	echan->slot[0] = echan->ch_num;
+
+	dev_info(dev, "allocated channel for %u:%u\n",
+		 EDMA_CTLR(echan->ch_num), EDMA_CHAN_SLOT(echan->ch_num));
+
+	return 0;
+
+err_wrong_chan:
+	edma_free_channel(a_ch_num);
+err_no_chan:
+	return ret;
+}
+
+/* Free channel resources */
+static void edma_free_chan_resources(struct dma_chan *chan)
+{
+	struct edma_chan *echan = to_edma_chan(chan);
+	struct device *dev = chan->device->dev;
+	int i;
+
+	/* Terminate transfers */
+	edma_stop(echan->ch_num);
+
+	vchan_free_chan_resources(&echan->vchan);
+
+	/* Free EDMA PaRAM slots */
+	for (i = 1; i < EDMA_MAX_SLOTS; i++) {
+		if (echan->slot[i] >= 0) {
+			edma_free_slot(echan->slot[i]);
+			echan->slot[i] = -1;
+		}
+	}
+
+	/* Free EDMA channel */
+	if (echan->alloced) {
+		edma_free_channel(echan->ch_num);
+		echan->alloced = false;
+	}
+
+	dev_info(dev, "freeing channel for %u\n", echan->ch_num);
+}
+
+/* Send pending descriptor to hardware */
+static void edma_issue_pending(struct dma_chan *chan)
+{
+	struct edma_chan *echan = to_edma_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&echan->vchan.lock, flags);
+	if (vchan_issue_pending(&echan->vchan) && !echan->edesc)
+		edma_execute(echan);
+	spin_unlock_irqrestore(&echan->vchan.lock, flags);
+}
+
+static size_t edma_desc_size(struct edma_desc *edesc)
+{
+	int i;
+	size_t size;
+
+	if (edesc->absync)
+		for (size = i = 0; i < edesc->pset_nr; i++)
+			size += (edesc->pset[i].a_b_cnt & 0xffff) *
+				(edesc->pset[i].a_b_cnt >> 16) *
+				 edesc->pset[i].ccnt;
+	else
+		size = (edesc->pset[0].a_b_cnt & 0xffff) *
+			(edesc->pset[0].a_b_cnt >> 16) +
+			(edesc->pset[0].a_b_cnt & 0xffff) *
+			(SZ_64K - 1) * edesc->pset[0].ccnt;
+
+	return size;
+}
+
+/* Check request completion status */
+static enum dma_status edma_tx_status(struct dma_chan *chan,
+				      dma_cookie_t cookie,
+				      struct dma_tx_state *txstate)
+{
+	struct edma_chan *echan = to_edma_chan(chan);
+	struct virt_dma_desc *vdesc;
+	enum dma_status ret;
+	unsigned long flags;
+
+	ret = dma_cookie_status(chan, cookie, txstate);
+	if (ret == DMA_SUCCESS || !txstate)
+		return ret;
+
+	spin_lock_irqsave(&echan->vchan.lock, flags);
+	vdesc = vchan_find_desc(&echan->vchan, cookie);
+	if (vdesc) {
+		txstate->residue = edma_desc_size(to_edma_desc(&vdesc->tx));
+	} else if (echan->edesc && echan->edesc->vdesc.tx.cookie == cookie) {
+		struct edma_desc *edesc = echan->edesc;
+		txstate->residue = edma_desc_size(edesc);
+	} else {
+		txstate->residue = 0;
+	}
+	spin_unlock_irqrestore(&echan->vchan.lock, flags);
+
+	return ret;
+}
+
+static void __init edma_chan_init(struct edma_cc *ecc,
+				  struct dma_device *dma,
+				  struct edma_chan *echans)
+{
+	int i, j;
+
+	for (i = 0; i < EDMA_CHANS; i++) {
+		struct edma_chan *echan = &echans[i];
+		echan->ch_num = EDMA_CTLR_CHAN(ecc->ctlr, i);
+		echan->ecc = ecc;
+		echan->vchan.desc_free = edma_desc_free;
+
+		vchan_init(&echan->vchan, dma);
+
+		INIT_LIST_HEAD(&echan->node);
+		for (j = 0; j < EDMA_MAX_SLOTS; j++)
+			echan->slot[j] = -1;
+	}
+}
+
+static void edma_dma_init(struct edma_cc *ecc, struct dma_device *dma,
+			  struct device *dev)
+{
+	dma->device_prep_slave_sg = edma_prep_slave_sg;
+	dma->device_alloc_chan_resources = edma_alloc_chan_resources;
+	dma->device_free_chan_resources = edma_free_chan_resources;
+	dma->device_issue_pending = edma_issue_pending;
+	dma->device_tx_status = edma_tx_status;
+	dma->device_control = edma_control;
+	dma->dev = dev;
+
+	INIT_LIST_HEAD(&dma->channels);
+}
+
+static int __devinit edma_probe(struct platform_device *pdev)
+{
+	struct edma_cc *ecc;
+	int ret;
+
+	ecc = devm_kzalloc(&pdev->dev, sizeof(*ecc), GFP_KERNEL);
+	if (!ecc) {
+		dev_err(&pdev->dev, "Can't allocate controller\n");
+		return -ENOMEM;
+	}
+
+	ecc->ctlr = pdev->id;
+	ecc->dummy_slot = edma_alloc_slot(ecc->ctlr, EDMA_SLOT_ANY);
+	if (ecc->dummy_slot < 0) {
+		dev_err(&pdev->dev, "Can't allocate PaRAM dummy slot\n");
+		return -EIO;
+	}
+
+	dma_cap_zero(ecc->dma_slave.cap_mask);
+	dma_cap_set(DMA_SLAVE, ecc->dma_slave.cap_mask);
+
+	edma_dma_init(ecc, &ecc->dma_slave, &pdev->dev);
+
+	edma_chan_init(ecc, &ecc->dma_slave, ecc->slave_chans);
+
+	ret = dma_async_device_register(&ecc->dma_slave);
+	if (ret)
+		goto err_reg1;
+
+	platform_set_drvdata(pdev, ecc);
+
+	dev_info(&pdev->dev, "TI EDMA DMA engine driver\n");
+
+	return 0;
+
+err_reg1:
+	edma_free_slot(ecc->dummy_slot);
+	return ret;
+}
+
+static int __devexit edma_remove(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct edma_cc *ecc = dev_get_drvdata(dev);
+
+	dma_async_device_unregister(&ecc->dma_slave);
+	edma_free_slot(ecc->dummy_slot);
+
+	return 0;
+}
+
+static struct platform_driver edma_driver = {
+	.probe		= edma_probe,
+	.remove		= __devexit_p(edma_remove),
+	.driver = {
+		.name = "edma-dma-engine",
+		.owner = THIS_MODULE,
+	},
+};
+
+bool edma_filter_fn(struct dma_chan *chan, void *param)
+{
+	if (chan->device->dev->driver == &edma_driver.driver) {
+		struct edma_chan *echan = to_edma_chan(chan);
+		unsigned ch_req = *(unsigned *)param;
+		return ch_req == echan->ch_num;
+	}
+	return false;
+}
+EXPORT_SYMBOL(edma_filter_fn);
+
+static struct platform_device *pdev0, *pdev1;
+
+static const struct platform_device_info edma_dev_info0 = {
+	.name = "edma-dma-engine",
+	.id = 0,
+	.dma_mask = DMA_BIT_MASK(32),
+};
+
+static const struct platform_device_info edma_dev_info1 = {
+	.name = "edma-dma-engine",
+	.id = 1,
+	.dma_mask = DMA_BIT_MASK(32),
+};
+
+static int edma_init(void)
+{
+	int ret = platform_driver_register(&edma_driver);
+
+	if (ret == 0) {
+		pdev0 = platform_device_register_full(&edma_dev_info0);
+		if (IS_ERR(pdev0)) {
+			platform_driver_unregister(&edma_driver);
+			ret = PTR_ERR(pdev0);
+			goto out;
+		}
+	}
+
+	if (EDMA_CTLRS == 2) {
+		pdev1 = platform_device_register_full(&edma_dev_info1);
+		if (IS_ERR(pdev1)) {
+			platform_driver_unregister(&edma_driver);
+			platform_device_unregister(pdev0);
+			ret = PTR_ERR(pdev1);
+		}
+	}
+
+out:
+	return ret;
+}
+subsys_initcall(edma_init);
+
+static void __exit edma_exit(void)
+{
+	platform_device_unregister(pdev0);
+	if (pdev1)
+		platform_device_unregister(pdev1);
+	platform_driver_unregister(&edma_driver);
+}
+module_exit(edma_exit);
+
+MODULE_AUTHOR("Matt Porter <mporter@ti.com>");
+MODULE_DESCRIPTION("TI EDMA DMA engine driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/ioat/dma_v2.c b/drivers/dma/ioat/dma_v2.c
index 86895760b59..b9d66785144 100644
--- a/drivers/dma/ioat/dma_v2.c
+++ b/drivers/dma/ioat/dma_v2.c
@@ -434,12 +434,11 @@ static struct ioat_ring_ent *ioat2_alloc_ring_ent(struct dma_chan *chan, gfp_t f
 		return NULL;
 	memset(hw, 0, sizeof(*hw));
 
-	desc = kmem_cache_alloc(ioat2_cache, flags);
+	desc = kmem_cache_zalloc(ioat2_cache, flags);
 	if (!desc) {
 		pci_pool_free(dma->dma_pool, hw, phys);
 		return NULL;
 	}
-	memset(desc, 0, sizeof(*desc));
 
 	dma_async_tx_descriptor_init(&desc->txd, chan);
 	desc->txd.tx_submit = ioat2_tx_submit_unlock;
diff --git a/drivers/dma/ioat/pci.c b/drivers/dma/ioat/pci.c
index 5e3a40f7994..c0573061b45 100644
--- a/drivers/dma/ioat/pci.c
+++ b/drivers/dma/ioat/pci.c
@@ -40,6 +40,17 @@ MODULE_VERSION(IOAT_DMA_VERSION);
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Intel Corporation");
 
+#define PCI_DEVICE_ID_INTEL_IOAT_IVB0	0x0e20
+#define PCI_DEVICE_ID_INTEL_IOAT_IVB1	0x0e21
+#define PCI_DEVICE_ID_INTEL_IOAT_IVB2	0x0e22
+#define PCI_DEVICE_ID_INTEL_IOAT_IVB3	0x0e23
+#define PCI_DEVICE_ID_INTEL_IOAT_IVB4	0x0e24
+#define PCI_DEVICE_ID_INTEL_IOAT_IVB5	0x0e25
+#define PCI_DEVICE_ID_INTEL_IOAT_IVB6	0x0e26
+#define PCI_DEVICE_ID_INTEL_IOAT_IVB7	0x0e27
+#define PCI_DEVICE_ID_INTEL_IOAT_IVB8	0x0e2e
+#define PCI_DEVICE_ID_INTEL_IOAT_IVB9	0x0e2f
+
 static struct pci_device_id ioat_pci_tbl[] = {
 	/* I/OAT v1 platforms */
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT) },
@@ -83,6 +94,17 @@ static struct pci_device_id ioat_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB8) },
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB9) },
 
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_IVB0) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_IVB1) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_IVB2) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_IVB3) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_IVB4) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_IVB5) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_IVB6) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_IVB7) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_IVB8) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_IVB9) },
+
 	{ 0, }
 };
 MODULE_DEVICE_TABLE(pci, ioat_pci_tbl);
diff --git a/drivers/dma/mmp_pdma.c b/drivers/dma/mmp_pdma.c
new file mode 100644
index 00000000000..14da1f403ed
--- /dev/null
+++ b/drivers/dma/mmp_pdma.c
@@ -0,0 +1,875 @@
+/*
+ * Copyright 2012 Marvell International Ltd.
+ *
+ * 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/module.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/interrupt.h>
+#include <linux/dma-mapping.h>
+#include <linux/slab.h>
+#include <linux/dmaengine.h>
+#include <linux/platform_device.h>
+#include <linux/device.h>
+#include <linux/platform_data/mmp_dma.h>
+#include <linux/dmapool.h>
+#include <linux/of_device.h>
+#include <linux/of.h>
+
+#include "dmaengine.h"
+
+#define DCSR		0x0000
+#define DALGN		0x00a0
+#define DINT		0x00f0
+#define DDADR		0x0200
+#define DSADR		0x0204
+#define DTADR		0x0208
+#define DCMD		0x020c
+
+#define DCSR_RUN	(1 << 31)	/* Run Bit (read / write) */
+#define DCSR_NODESC	(1 << 30)	/* No-Descriptor Fetch (read / write) */
+#define DCSR_STOPIRQEN	(1 << 29)	/* Stop Interrupt Enable (read / write) */
+#define DCSR_REQPEND	(1 << 8)	/* Request Pending (read-only) */
+#define DCSR_STOPSTATE	(1 << 3)	/* Stop State (read-only) */
+#define DCSR_ENDINTR	(1 << 2)	/* End Interrupt (read / write) */
+#define DCSR_STARTINTR	(1 << 1)	/* Start Interrupt (read / write) */
+#define DCSR_BUSERR	(1 << 0)	/* Bus Error Interrupt (read / write) */
+
+#define DCSR_EORIRQEN	(1 << 28)       /* End of Receive Interrupt Enable (R/W) */
+#define DCSR_EORJMPEN	(1 << 27)       /* Jump to next descriptor on EOR */
+#define DCSR_EORSTOPEN	(1 << 26)       /* STOP on an EOR */
+#define DCSR_SETCMPST	(1 << 25)       /* Set Descriptor Compare Status */
+#define DCSR_CLRCMPST	(1 << 24)       /* Clear Descriptor Compare Status */
+#define DCSR_CMPST	(1 << 10)       /* The Descriptor Compare Status */
+#define DCSR_EORINTR	(1 << 9)        /* The end of Receive */
+
+#define DRCMR_MAPVLD	(1 << 7)	/* Map Valid (read / write) */
+#define DRCMR_CHLNUM	0x1f		/* mask for Channel Number (read / write) */
+
+#define DDADR_DESCADDR	0xfffffff0	/* Address of next descriptor (mask) */
+#define DDADR_STOP	(1 << 0)	/* Stop (read / write) */
+
+#define DCMD_INCSRCADDR	(1 << 31)	/* Source Address Increment Setting. */
+#define DCMD_INCTRGADDR	(1 << 30)	/* Target Address Increment Setting. */
+#define DCMD_FLOWSRC	(1 << 29)	/* Flow Control by the source. */
+#define DCMD_FLOWTRG	(1 << 28)	/* Flow Control by the target. */
+#define DCMD_STARTIRQEN	(1 << 22)	/* Start Interrupt Enable */
+#define DCMD_ENDIRQEN	(1 << 21)	/* End Interrupt Enable */
+#define DCMD_ENDIAN	(1 << 18)	/* Device Endian-ness. */
+#define DCMD_BURST8	(1 << 16)	/* 8 byte burst */
+#define DCMD_BURST16	(2 << 16)	/* 16 byte burst */
+#define DCMD_BURST32	(3 << 16)	/* 32 byte burst */
+#define DCMD_WIDTH1	(1 << 14)	/* 1 byte width */
+#define DCMD_WIDTH2	(2 << 14)	/* 2 byte width (HalfWord) */
+#define DCMD_WIDTH4	(3 << 14)	/* 4 byte width (Word) */
+#define DCMD_LENGTH	0x01fff		/* length mask (max = 8K - 1) */
+
+#define PDMA_ALIGNMENT		3
+#define PDMA_MAX_DESC_BYTES	0x1000
+
+struct mmp_pdma_desc_hw {
+	u32 ddadr;	/* Points to the next descriptor + flags */
+	u32 dsadr;	/* DSADR value for the current transfer */
+	u32 dtadr;	/* DTADR value for the current transfer */
+	u32 dcmd;	/* DCMD value for the current transfer */
+} __aligned(32);
+
+struct mmp_pdma_desc_sw {
+	struct mmp_pdma_desc_hw desc;
+	struct list_head node;
+	struct list_head tx_list;
+	struct dma_async_tx_descriptor async_tx;
+};
+
+struct mmp_pdma_phy;
+
+struct mmp_pdma_chan {
+	struct device *dev;
+	struct dma_chan chan;
+	struct dma_async_tx_descriptor desc;
+	struct mmp_pdma_phy *phy;
+	enum dma_transfer_direction dir;
+
+	/* channel's basic info */
+	struct tasklet_struct tasklet;
+	u32 dcmd;
+	u32 drcmr;
+	u32 dev_addr;
+
+	/* list for desc */
+	spinlock_t desc_lock;		/* Descriptor list lock */
+	struct list_head chain_pending;	/* Link descriptors queue for pending */
+	struct list_head chain_running;	/* Link descriptors queue for running */
+	bool idle;			/* channel statue machine */
+
+	struct dma_pool *desc_pool;	/* Descriptors pool */
+};
+
+struct mmp_pdma_phy {
+	int idx;
+	void __iomem *base;
+	struct mmp_pdma_chan *vchan;
+};
+
+struct mmp_pdma_device {
+	int				dma_channels;
+	void __iomem			*base;
+	struct device			*dev;
+	struct dma_device		device;
+	struct mmp_pdma_phy		*phy;
+};
+
+#define tx_to_mmp_pdma_desc(tx) container_of(tx, struct mmp_pdma_desc_sw, async_tx)
+#define to_mmp_pdma_desc(lh) container_of(lh, struct mmp_pdma_desc_sw, node)
+#define to_mmp_pdma_chan(dchan) container_of(dchan, struct mmp_pdma_chan, chan)
+#define to_mmp_pdma_dev(dmadev) container_of(dmadev, struct mmp_pdma_device, device)
+
+static void set_desc(struct mmp_pdma_phy *phy, dma_addr_t addr)
+{
+	u32 reg = (phy->idx << 4) + DDADR;
+
+	writel(addr, phy->base + reg);
+}
+
+static void enable_chan(struct mmp_pdma_phy *phy)
+{
+	u32 reg;
+
+	if (!phy->vchan)
+		return;
+
+	reg = phy->vchan->drcmr;
+	reg = (((reg) < 64) ? 0x0100 : 0x1100) + (((reg) & 0x3f) << 2);
+	writel(DRCMR_MAPVLD | phy->idx, phy->base + reg);
+
+	reg = (phy->idx << 2) + DCSR;
+	writel(readl(phy->base + reg) | DCSR_RUN,
+					phy->base + reg);
+}
+
+static void disable_chan(struct mmp_pdma_phy *phy)
+{
+	u32 reg;
+
+	if (phy) {
+		reg = (phy->idx << 2) + DCSR;
+		writel(readl(phy->base + reg) & ~DCSR_RUN,
+						phy->base + reg);
+	}
+}
+
+static int clear_chan_irq(struct mmp_pdma_phy *phy)
+{
+	u32 dcsr;
+	u32 dint = readl(phy->base + DINT);
+	u32 reg = (phy->idx << 2) + DCSR;
+
+	if (dint & BIT(phy->idx)) {
+		/* clear irq */
+		dcsr = readl(phy->base + reg);
+		writel(dcsr, phy->base + reg);
+		if ((dcsr & DCSR_BUSERR) && (phy->vchan))
+			dev_warn(phy->vchan->dev, "DCSR_BUSERR\n");
+		return 0;
+	}
+	return -EAGAIN;
+}
+
+static irqreturn_t mmp_pdma_chan_handler(int irq, void *dev_id)
+{
+	struct mmp_pdma_phy *phy = dev_id;
+
+	if (clear_chan_irq(phy) == 0) {
+		tasklet_schedule(&phy->vchan->tasklet);
+		return IRQ_HANDLED;
+	} else
+		return IRQ_NONE;
+}
+
+static irqreturn_t mmp_pdma_int_handler(int irq, void *dev_id)
+{
+	struct mmp_pdma_device *pdev = dev_id;
+	struct mmp_pdma_phy *phy;
+	u32 dint = readl(pdev->base + DINT);
+	int i, ret;
+	int irq_num = 0;
+
+	while (dint) {
+		i = __ffs(dint);
+		dint &= (dint - 1);
+		phy = &pdev->phy[i];
+		ret = mmp_pdma_chan_handler(irq, phy);
+		if (ret == IRQ_HANDLED)
+			irq_num++;
+	}
+
+	if (irq_num)
+		return IRQ_HANDLED;
+	else
+		return IRQ_NONE;
+}
+
+/* lookup free phy channel as descending priority */
+static struct mmp_pdma_phy *lookup_phy(struct mmp_pdma_chan *pchan)
+{
+	int prio, i;
+	struct mmp_pdma_device *pdev = to_mmp_pdma_dev(pchan->chan.device);
+	struct mmp_pdma_phy *phy;
+
+	/*
+	 * dma channel priorities
+	 * ch 0 - 3,  16 - 19  <--> (0)
+	 * ch 4 - 7,  20 - 23  <--> (1)
+	 * ch 8 - 11, 24 - 27  <--> (2)
+	 * ch 12 - 15, 28 - 31  <--> (3)
+	 */
+	for (prio = 0; prio <= (((pdev->dma_channels - 1) & 0xf) >> 2); prio++) {
+		for (i = 0; i < pdev->dma_channels; i++) {
+			if (prio != ((i & 0xf) >> 2))
+				continue;
+			phy = &pdev->phy[i];
+			if (!phy->vchan) {
+				phy->vchan = pchan;
+				return phy;
+			}
+		}
+	}
+
+	return NULL;
+}
+
+/* desc->tx_list ==> pending list */
+static void append_pending_queue(struct mmp_pdma_chan *chan,
+					struct mmp_pdma_desc_sw *desc)
+{
+	struct mmp_pdma_desc_sw *tail =
+				to_mmp_pdma_desc(chan->chain_pending.prev);
+
+	if (list_empty(&chan->chain_pending))
+		goto out_splice;
+
+	/* one irq per queue, even appended */
+	tail->desc.ddadr = desc->async_tx.phys;
+	tail->desc.dcmd &= ~DCMD_ENDIRQEN;
+
+	/* softly link to pending list */
+out_splice:
+	list_splice_tail_init(&desc->tx_list, &chan->chain_pending);
+}
+
+/**
+ * start_pending_queue - transfer any pending transactions
+ * pending list ==> running list
+ */
+static void start_pending_queue(struct mmp_pdma_chan *chan)
+{
+	struct mmp_pdma_desc_sw *desc;
+
+	/* still in running, irq will start the pending list */
+	if (!chan->idle) {
+		dev_dbg(chan->dev, "DMA controller still busy\n");
+		return;
+	}
+
+	if (list_empty(&chan->chain_pending)) {
+		/* chance to re-fetch phy channel with higher prio */
+		if (chan->phy) {
+			chan->phy->vchan = NULL;
+			chan->phy = NULL;
+		}
+		dev_dbg(chan->dev, "no pending list\n");
+		return;
+	}
+
+	if (!chan->phy) {
+		chan->phy = lookup_phy(chan);
+		if (!chan->phy) {
+			dev_dbg(chan->dev, "no free dma channel\n");
+			return;
+		}
+	}
+
+	/*
+	 * pending -> running
+	 * reintilize pending list
+	 */
+	desc = list_first_entry(&chan->chain_pending,
+				struct mmp_pdma_desc_sw, node);
+	list_splice_tail_init(&chan->chain_pending, &chan->chain_running);
+
+	/*
+	 * Program the descriptor's address into the DMA controller,
+	 * then start the DMA transaction
+	 */
+	set_desc(chan->phy, desc->async_tx.phys);
+	enable_chan(chan->phy);
+	chan->idle = false;
+}
+
+
+/* desc->tx_list ==> pending list */
+static dma_cookie_t mmp_pdma_tx_submit(struct dma_async_tx_descriptor *tx)
+{
+	struct mmp_pdma_chan *chan = to_mmp_pdma_chan(tx->chan);
+	struct mmp_pdma_desc_sw *desc = tx_to_mmp_pdma_desc(tx);
+	struct mmp_pdma_desc_sw *child;
+	unsigned long flags;
+	dma_cookie_t cookie = -EBUSY;
+
+	spin_lock_irqsave(&chan->desc_lock, flags);
+
+	list_for_each_entry(child, &desc->tx_list, node) {
+		cookie = dma_cookie_assign(&child->async_tx);
+	}
+
+	append_pending_queue(chan, desc);
+
+	spin_unlock_irqrestore(&chan->desc_lock, flags);
+
+	return cookie;
+}
+
+struct mmp_pdma_desc_sw *mmp_pdma_alloc_descriptor(struct mmp_pdma_chan *chan)
+{
+	struct mmp_pdma_desc_sw *desc;
+	dma_addr_t pdesc;
+
+	desc = dma_pool_alloc(chan->desc_pool, GFP_ATOMIC, &pdesc);
+	if (!desc) {
+		dev_err(chan->dev, "out of memory for link descriptor\n");
+		return NULL;
+	}
+
+	memset(desc, 0, sizeof(*desc));
+	INIT_LIST_HEAD(&desc->tx_list);
+	dma_async_tx_descriptor_init(&desc->async_tx, &chan->chan);
+	/* each desc has submit */
+	desc->async_tx.tx_submit = mmp_pdma_tx_submit;
+	desc->async_tx.phys = pdesc;
+
+	return desc;
+}
+
+/**
+ * mmp_pdma_alloc_chan_resources - Allocate resources for DMA channel.
+ *
+ * This function will create a dma pool for descriptor allocation.
+ * Request irq only when channel is requested
+ * Return - The number of allocated descriptors.
+ */
+
+static int mmp_pdma_alloc_chan_resources(struct dma_chan *dchan)
+{
+	struct mmp_pdma_chan *chan = to_mmp_pdma_chan(dchan);
+
+	if (chan->desc_pool)
+		return 1;
+
+	chan->desc_pool =
+		dma_pool_create(dev_name(&dchan->dev->device), chan->dev,
+				  sizeof(struct mmp_pdma_desc_sw),
+				  __alignof__(struct mmp_pdma_desc_sw), 0);
+	if (!chan->desc_pool) {
+		dev_err(chan->dev, "unable to allocate descriptor pool\n");
+		return -ENOMEM;
+	}
+	if (chan->phy) {
+		chan->phy->vchan = NULL;
+		chan->phy = NULL;
+	}
+	chan->idle = true;
+	chan->dev_addr = 0;
+	return 1;
+}
+
+static void mmp_pdma_free_desc_list(struct mmp_pdma_chan *chan,
+				  struct list_head *list)
+{
+	struct mmp_pdma_desc_sw *desc, *_desc;
+
+	list_for_each_entry_safe(desc, _desc, list, node) {
+		list_del(&desc->node);
+		dma_pool_free(chan->desc_pool, desc, desc->async_tx.phys);
+	}
+}
+
+static void mmp_pdma_free_chan_resources(struct dma_chan *dchan)
+{
+	struct mmp_pdma_chan *chan = to_mmp_pdma_chan(dchan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&chan->desc_lock, flags);
+	mmp_pdma_free_desc_list(chan, &chan->chain_pending);
+	mmp_pdma_free_desc_list(chan, &chan->chain_running);
+	spin_unlock_irqrestore(&chan->desc_lock, flags);
+
+	dma_pool_destroy(chan->desc_pool);
+	chan->desc_pool = NULL;
+	chan->idle = true;
+	chan->dev_addr = 0;
+	if (chan->phy) {
+		chan->phy->vchan = NULL;
+		chan->phy = NULL;
+	}
+	return;
+}
+
+static struct dma_async_tx_descriptor *
+mmp_pdma_prep_memcpy(struct dma_chan *dchan,
+	dma_addr_t dma_dst, dma_addr_t dma_src,
+	size_t len, unsigned long flags)
+{
+	struct mmp_pdma_chan *chan;
+	struct mmp_pdma_desc_sw *first = NULL, *prev = NULL, *new;
+	size_t copy = 0;
+
+	if (!dchan)
+		return NULL;
+
+	if (!len)
+		return NULL;
+
+	chan = to_mmp_pdma_chan(dchan);
+
+	if (!chan->dir) {
+		chan->dir = DMA_MEM_TO_MEM;
+		chan->dcmd = DCMD_INCTRGADDR | DCMD_INCSRCADDR;
+		chan->dcmd |= DCMD_BURST32;
+	}
+
+	do {
+		/* Allocate the link descriptor from DMA pool */
+		new = mmp_pdma_alloc_descriptor(chan);
+		if (!new) {
+			dev_err(chan->dev, "no memory for desc\n");
+			goto fail;
+		}
+
+		copy = min_t(size_t, len, PDMA_MAX_DESC_BYTES);
+
+		new->desc.dcmd = chan->dcmd | (DCMD_LENGTH & copy);
+		new->desc.dsadr = dma_src;
+		new->desc.dtadr = dma_dst;
+
+		if (!first)
+			first = new;
+		else
+			prev->desc.ddadr = new->async_tx.phys;
+
+		new->async_tx.cookie = 0;
+		async_tx_ack(&new->async_tx);
+
+		prev = new;
+		len -= copy;
+
+		if (chan->dir == DMA_MEM_TO_DEV) {
+			dma_src += copy;
+		} else if (chan->dir == DMA_DEV_TO_MEM) {
+			dma_dst += copy;
+		} else if (chan->dir == DMA_MEM_TO_MEM) {
+			dma_src += copy;
+			dma_dst += copy;
+		}
+
+		/* Insert the link descriptor to the LD ring */
+		list_add_tail(&new->node, &first->tx_list);
+	} while (len);
+
+	first->async_tx.flags = flags; /* client is in control of this ack */
+	first->async_tx.cookie = -EBUSY;
+
+	/* last desc and fire IRQ */
+	new->desc.ddadr = DDADR_STOP;
+	new->desc.dcmd |= DCMD_ENDIRQEN;
+
+	return &first->async_tx;
+
+fail:
+	if (first)
+		mmp_pdma_free_desc_list(chan, &first->tx_list);
+	return NULL;
+}
+
+static struct dma_async_tx_descriptor *
+mmp_pdma_prep_slave_sg(struct dma_chan *dchan, struct scatterlist *sgl,
+			 unsigned int sg_len, enum dma_transfer_direction dir,
+			 unsigned long flags, void *context)
+{
+	struct mmp_pdma_chan *chan = to_mmp_pdma_chan(dchan);
+	struct mmp_pdma_desc_sw *first = NULL, *prev = NULL, *new = NULL;
+	size_t len, avail;
+	struct scatterlist *sg;
+	dma_addr_t addr;
+	int i;
+
+	if ((sgl == NULL) || (sg_len == 0))
+		return NULL;
+
+	for_each_sg(sgl, sg, sg_len, i) {
+		addr = sg_dma_address(sg);
+		avail = sg_dma_len(sgl);
+
+		do {
+			len = min_t(size_t, avail, PDMA_MAX_DESC_BYTES);
+
+			/* allocate and populate the descriptor */
+			new = mmp_pdma_alloc_descriptor(chan);
+			if (!new) {
+				dev_err(chan->dev, "no memory for desc\n");
+				goto fail;
+			}
+
+			new->desc.dcmd = chan->dcmd | (DCMD_LENGTH & len);
+			if (dir == DMA_MEM_TO_DEV) {
+				new->desc.dsadr = addr;
+				new->desc.dtadr = chan->dev_addr;
+			} else {
+				new->desc.dsadr = chan->dev_addr;
+				new->desc.dtadr = addr;
+			}
+
+			if (!first)
+				first = new;
+			else
+				prev->desc.ddadr = new->async_tx.phys;
+
+			new->async_tx.cookie = 0;
+			async_tx_ack(&new->async_tx);
+			prev = new;
+
+			/* Insert the link descriptor to the LD ring */
+			list_add_tail(&new->node, &first->tx_list);
+
+			/* update metadata */
+			addr += len;
+			avail -= len;
+		} while (avail);
+	}
+
+	first->async_tx.cookie = -EBUSY;
+	first->async_tx.flags = flags;
+
+	/* last desc and fire IRQ */
+	new->desc.ddadr = DDADR_STOP;
+	new->desc.dcmd |= DCMD_ENDIRQEN;
+
+	return &first->async_tx;
+
+fail:
+	if (first)
+		mmp_pdma_free_desc_list(chan, &first->tx_list);
+	return NULL;
+}
+
+static int mmp_pdma_control(struct dma_chan *dchan, enum dma_ctrl_cmd cmd,
+		unsigned long arg)
+{
+	struct mmp_pdma_chan *chan = to_mmp_pdma_chan(dchan);
+	struct dma_slave_config *cfg = (void *)arg;
+	unsigned long flags;
+	int ret = 0;
+	u32 maxburst = 0, addr = 0;
+	enum dma_slave_buswidth width = DMA_SLAVE_BUSWIDTH_UNDEFINED;
+
+	if (!dchan)
+		return -EINVAL;
+
+	switch (cmd) {
+	case DMA_TERMINATE_ALL:
+		disable_chan(chan->phy);
+		if (chan->phy) {
+			chan->phy->vchan = NULL;
+			chan->phy = NULL;
+		}
+		spin_lock_irqsave(&chan->desc_lock, flags);
+		mmp_pdma_free_desc_list(chan, &chan->chain_pending);
+		mmp_pdma_free_desc_list(chan, &chan->chain_running);
+		spin_unlock_irqrestore(&chan->desc_lock, flags);
+		chan->idle = true;
+		break;
+	case DMA_SLAVE_CONFIG:
+		if (cfg->direction == DMA_DEV_TO_MEM) {
+			chan->dcmd = DCMD_INCTRGADDR | DCMD_FLOWSRC;
+			maxburst = cfg->src_maxburst;
+			width = cfg->src_addr_width;
+			addr = cfg->src_addr;
+		} else if (cfg->direction == DMA_MEM_TO_DEV) {
+			chan->dcmd = DCMD_INCSRCADDR | DCMD_FLOWTRG;
+			maxburst = cfg->dst_maxburst;
+			width = cfg->dst_addr_width;
+			addr = cfg->dst_addr;
+		}
+
+		if (width == DMA_SLAVE_BUSWIDTH_1_BYTE)
+			chan->dcmd |= DCMD_WIDTH1;
+		else if (width == DMA_SLAVE_BUSWIDTH_2_BYTES)
+			chan->dcmd |= DCMD_WIDTH2;
+		else if (width == DMA_SLAVE_BUSWIDTH_4_BYTES)
+			chan->dcmd |= DCMD_WIDTH4;
+
+		if (maxburst == 8)
+			chan->dcmd |= DCMD_BURST8;
+		else if (maxburst == 16)
+			chan->dcmd |= DCMD_BURST16;
+		else if (maxburst == 32)
+			chan->dcmd |= DCMD_BURST32;
+
+		if (cfg) {
+			chan->dir = cfg->direction;
+			chan->drcmr = cfg->slave_id;
+		}
+		chan->dev_addr = addr;
+		break;
+	default:
+		return -ENOSYS;
+	}
+
+	return ret;
+}
+
+static enum dma_status mmp_pdma_tx_status(struct dma_chan *dchan,
+			dma_cookie_t cookie, struct dma_tx_state *txstate)
+{
+	struct mmp_pdma_chan *chan = to_mmp_pdma_chan(dchan);
+	enum dma_status ret;
+	unsigned long flags;
+
+	spin_lock_irqsave(&chan->desc_lock, flags);
+	ret = dma_cookie_status(dchan, cookie, txstate);
+	spin_unlock_irqrestore(&chan->desc_lock, flags);
+
+	return ret;
+}
+
+/**
+ * mmp_pdma_issue_pending - Issue the DMA start command
+ * pending list ==> running list
+ */
+static void mmp_pdma_issue_pending(struct dma_chan *dchan)
+{
+	struct mmp_pdma_chan *chan = to_mmp_pdma_chan(dchan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&chan->desc_lock, flags);
+	start_pending_queue(chan);
+	spin_unlock_irqrestore(&chan->desc_lock, flags);
+}
+
+/*
+ * dma_do_tasklet
+ * Do call back
+ * Start pending list
+ */
+static void dma_do_tasklet(unsigned long data)
+{
+	struct mmp_pdma_chan *chan = (struct mmp_pdma_chan *)data;
+	struct mmp_pdma_desc_sw *desc, *_desc;
+	LIST_HEAD(chain_cleanup);
+	unsigned long flags;
+
+	/* submit pending list; callback for each desc; free desc */
+
+	spin_lock_irqsave(&chan->desc_lock, flags);
+
+	/* update the cookie if we have some descriptors to cleanup */
+	if (!list_empty(&chan->chain_running)) {
+		dma_cookie_t cookie;
+
+		desc = to_mmp_pdma_desc(chan->chain_running.prev);
+		cookie = desc->async_tx.cookie;
+		dma_cookie_complete(&desc->async_tx);
+
+		dev_dbg(chan->dev, "completed_cookie=%d\n", cookie);
+	}
+
+	/*
+	 * move the descriptors to a temporary list so we can drop the lock
+	 * during the entire cleanup operation
+	 */
+	list_splice_tail_init(&chan->chain_running, &chain_cleanup);
+
+	/* the hardware is now idle and ready for more */
+	chan->idle = true;
+
+	/* Start any pending transactions automatically */
+	start_pending_queue(chan);
+	spin_unlock_irqrestore(&chan->desc_lock, flags);
+
+	/* Run the callback for each descriptor, in order */
+	list_for_each_entry_safe(desc, _desc, &chain_cleanup, node) {
+		struct dma_async_tx_descriptor *txd = &desc->async_tx;
+
+		/* Remove from the list of transactions */
+		list_del(&desc->node);
+		/* Run the link descriptor callback function */
+		if (txd->callback)
+			txd->callback(txd->callback_param);
+
+		dma_pool_free(chan->desc_pool, desc, txd->phys);
+	}
+}
+
+static int __devexit mmp_pdma_remove(struct platform_device *op)
+{
+	struct mmp_pdma_device *pdev = platform_get_drvdata(op);
+
+	dma_async_device_unregister(&pdev->device);
+	return 0;
+}
+
+static int __devinit mmp_pdma_chan_init(struct mmp_pdma_device *pdev,
+							int idx, int irq)
+{
+	struct mmp_pdma_phy *phy  = &pdev->phy[idx];
+	struct mmp_pdma_chan *chan;
+	int ret;
+
+	chan = devm_kzalloc(pdev->dev,
+			sizeof(struct mmp_pdma_chan), GFP_KERNEL);
+	if (chan == NULL)
+		return -ENOMEM;
+
+	phy->idx = idx;
+	phy->base = pdev->base;
+
+	if (irq) {
+		ret = devm_request_irq(pdev->dev, irq,
+			mmp_pdma_chan_handler, IRQF_DISABLED, "pdma", phy);
+		if (ret) {
+			dev_err(pdev->dev, "channel request irq fail!\n");
+			return ret;
+		}
+	}
+
+	spin_lock_init(&chan->desc_lock);
+	chan->dev = pdev->dev;
+	chan->chan.device = &pdev->device;
+	tasklet_init(&chan->tasklet, dma_do_tasklet, (unsigned long)chan);
+	INIT_LIST_HEAD(&chan->chain_pending);
+	INIT_LIST_HEAD(&chan->chain_running);
+
+	/* register virt channel to dma engine */
+	list_add_tail(&chan->chan.device_node,
+			&pdev->device.channels);
+
+	return 0;
+}
+
+static struct of_device_id mmp_pdma_dt_ids[] = {
+	{ .compatible = "marvell,pdma-1.0", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, mmp_pdma_dt_ids);
+
+static int __devinit mmp_pdma_probe(struct platform_device *op)
+{
+	struct mmp_pdma_device *pdev;
+	const struct of_device_id *of_id;
+	struct mmp_dma_platdata *pdata = dev_get_platdata(&op->dev);
+	struct resource *iores;
+	int i, ret, irq = 0;
+	int dma_channels = 0, irq_num = 0;
+
+	pdev = devm_kzalloc(&op->dev, sizeof(*pdev), GFP_KERNEL);
+	if (!pdev)
+		return -ENOMEM;
+	pdev->dev = &op->dev;
+
+	iores = platform_get_resource(op, IORESOURCE_MEM, 0);
+	if (!iores)
+		return -EINVAL;
+
+	pdev->base = devm_request_and_ioremap(pdev->dev, iores);
+	if (!pdev->base)
+		return -EADDRNOTAVAIL;
+
+	of_id = of_match_device(mmp_pdma_dt_ids, pdev->dev);
+	if (of_id)
+		of_property_read_u32(pdev->dev->of_node,
+				"#dma-channels", &dma_channels);
+	else if (pdata && pdata->dma_channels)
+		dma_channels = pdata->dma_channels;
+	else
+		dma_channels = 32;	/* default 32 channel */
+	pdev->dma_channels = dma_channels;
+
+	for (i = 0; i < dma_channels; i++) {
+		if (platform_get_irq(op, i) > 0)
+			irq_num++;
+	}
+
+	pdev->phy = devm_kzalloc(pdev->dev,
+		dma_channels * sizeof(struct mmp_pdma_chan), GFP_KERNEL);
+	if (pdev->phy == NULL)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&pdev->device.channels);
+
+	if (irq_num != dma_channels) {
+		/* all chan share one irq, demux inside */
+		irq = platform_get_irq(op, 0);
+		ret = devm_request_irq(pdev->dev, irq,
+			mmp_pdma_int_handler, IRQF_DISABLED, "pdma", pdev);
+		if (ret)
+			return ret;
+	}
+
+	for (i = 0; i < dma_channels; i++) {
+		irq = (irq_num != dma_channels) ? 0 : platform_get_irq(op, i);
+		ret = mmp_pdma_chan_init(pdev, i, irq);
+		if (ret)
+			return ret;
+	}
+
+	dma_cap_set(DMA_SLAVE, pdev->device.cap_mask);
+	dma_cap_set(DMA_MEMCPY, pdev->device.cap_mask);
+	dma_cap_set(DMA_SLAVE, pdev->device.cap_mask);
+	pdev->device.dev = &op->dev;
+	pdev->device.device_alloc_chan_resources = mmp_pdma_alloc_chan_resources;
+	pdev->device.device_free_chan_resources = mmp_pdma_free_chan_resources;
+	pdev->device.device_tx_status = mmp_pdma_tx_status;
+	pdev->device.device_prep_dma_memcpy = mmp_pdma_prep_memcpy;
+	pdev->device.device_prep_slave_sg = mmp_pdma_prep_slave_sg;
+	pdev->device.device_issue_pending = mmp_pdma_issue_pending;
+	pdev->device.device_control = mmp_pdma_control;
+	pdev->device.copy_align = PDMA_ALIGNMENT;
+
+	if (pdev->dev->coherent_dma_mask)
+		dma_set_mask(pdev->dev, pdev->dev->coherent_dma_mask);
+	else
+		dma_set_mask(pdev->dev, DMA_BIT_MASK(64));
+
+	ret = dma_async_device_register(&pdev->device);
+	if (ret) {
+		dev_err(pdev->device.dev, "unable to register\n");
+		return ret;
+	}
+
+	dev_info(pdev->device.dev, "initialized\n");
+	return 0;
+}
+
+static const struct platform_device_id mmp_pdma_id_table[] = {
+	{ "mmp-pdma", },
+	{ },
+};
+
+static struct platform_driver mmp_pdma_driver = {
+	.driver		= {
+		.name	= "mmp-pdma",
+		.owner  = THIS_MODULE,
+		.of_match_table = mmp_pdma_dt_ids,
+	},
+	.id_table	= mmp_pdma_id_table,
+	.probe		= mmp_pdma_probe,
+	.remove		= __devexit_p(mmp_pdma_remove),
+};
+
+module_platform_driver(mmp_pdma_driver);
+
+MODULE_DESCRIPTION("MARVELL MMP Periphera DMA Driver");
+MODULE_AUTHOR("Marvell International Ltd.");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/mmp_tdma.c b/drivers/dma/mmp_tdma.c
index 6d9c82e891d..f3e8d71bcbc 100644
--- a/drivers/dma/mmp_tdma.c
+++ b/drivers/dma/mmp_tdma.c
@@ -20,6 +20,7 @@
 #include <linux/device.h>
 #include <mach/regs-icu.h>
 #include <linux/platform_data/dma-mmp_tdma.h>
+#include <linux/of_device.h>
 
 #include "dmaengine.h"
 
@@ -127,7 +128,6 @@ struct mmp_tdma_device {
 	void __iomem			*base;
 	struct dma_device		device;
 	struct mmp_tdma_chan		*tdmac[TDMA_CHANNEL_NUM];
-	int				irq;
 };
 
 #define to_mmp_tdma_chan(dchan) container_of(dchan, struct mmp_tdma_chan, chan)
@@ -492,7 +492,7 @@ static int __devinit mmp_tdma_chan_init(struct mmp_tdma_device *tdev,
 		return -ENOMEM;
 	}
 	if (irq)
-		tdmac->irq = irq + idx;
+		tdmac->irq = irq;
 	tdmac->dev	   = tdev->dev;
 	tdmac->chan.device = &tdev->device;
 	tdmac->idx	   = idx;
@@ -505,34 +505,43 @@ static int __devinit mmp_tdma_chan_init(struct mmp_tdma_device *tdev,
 	/* add the channel to tdma_chan list */
 	list_add_tail(&tdmac->chan.device_node,
 			&tdev->device.channels);
-
 	return 0;
 }
 
+static struct of_device_id mmp_tdma_dt_ids[] = {
+	{ .compatible = "marvell,adma-1.0", .data = (void *)MMP_AUD_TDMA},
+	{ .compatible = "marvell,pxa910-squ", .data = (void *)PXA910_SQU},
+	{}
+};
+MODULE_DEVICE_TABLE(of, mmp_tdma_dt_ids);
+
 static int __devinit mmp_tdma_probe(struct platform_device *pdev)
 {
-	const struct platform_device_id *id = platform_get_device_id(pdev);
-	enum mmp_tdma_type type = id->driver_data;
+	enum mmp_tdma_type type;
+	const struct of_device_id *of_id;
 	struct mmp_tdma_device *tdev;
 	struct resource *iores;
 	int i, ret;
-	int irq = 0;
+	int irq = 0, irq_num = 0;
 	int chan_num = TDMA_CHANNEL_NUM;
 
+	of_id = of_match_device(mmp_tdma_dt_ids, &pdev->dev);
+	if (of_id)
+		type = (enum mmp_tdma_type) of_id->data;
+	else
+		type = platform_get_device_id(pdev)->driver_data;
+
 	/* always have couple channels */
 	tdev = devm_kzalloc(&pdev->dev, sizeof(*tdev), GFP_KERNEL);
 	if (!tdev)
 		return -ENOMEM;
 
 	tdev->dev = &pdev->dev;
-	iores = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
-	if (!iores)
-		return -EINVAL;
 
-	if (resource_size(iores) != chan_num)
-		tdev->irq = iores->start;
-	else
-		irq = iores->start;
+	for (i = 0; i < chan_num; i++) {
+		if (platform_get_irq(pdev, i) > 0)
+			irq_num++;
+	}
 
 	iores = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!iores)
@@ -542,25 +551,26 @@ static int __devinit mmp_tdma_probe(struct platform_device *pdev)
 	if (!tdev->base)
 		return -EADDRNOTAVAIL;
 
-	if (tdev->irq) {
-		ret = devm_request_irq(&pdev->dev, tdev->irq,
+	INIT_LIST_HEAD(&tdev->device.channels);
+
+	if (irq_num != chan_num) {
+		irq = platform_get_irq(pdev, 0);
+		ret = devm_request_irq(&pdev->dev, irq,
 			mmp_tdma_int_handler, IRQF_DISABLED, "tdma", tdev);
 		if (ret)
 			return ret;
 	}
 
-	dma_cap_set(DMA_SLAVE, tdev->device.cap_mask);
-	dma_cap_set(DMA_CYCLIC, tdev->device.cap_mask);
-
-	INIT_LIST_HEAD(&tdev->device.channels);
-
 	/* initialize channel parameters */
 	for (i = 0; i < chan_num; i++) {
+		irq = (irq_num != chan_num) ? 0 : platform_get_irq(pdev, i);
 		ret = mmp_tdma_chan_init(tdev, i, irq, type);
 		if (ret)
 			return ret;
 	}
 
+	dma_cap_set(DMA_SLAVE, tdev->device.cap_mask);
+	dma_cap_set(DMA_CYCLIC, tdev->device.cap_mask);
 	tdev->device.dev = &pdev->dev;
 	tdev->device.device_alloc_chan_resources =
 					mmp_tdma_alloc_chan_resources;
@@ -595,6 +605,7 @@ static struct platform_driver mmp_tdma_driver = {
 	.driver		= {
 		.name	= "mmp-tdma",
 		.owner  = THIS_MODULE,
+		.of_match_table = mmp_tdma_dt_ids,
 	},
 	.id_table	= mmp_tdma_id_table,
 	.probe		= mmp_tdma_probe,
diff --git a/drivers/dma/mxs-dma.c b/drivers/dma/mxs-dma.c
index 734a4eb84d6..9f02e794b12 100644
--- a/drivers/dma/mxs-dma.c
+++ b/drivers/dma/mxs-dma.c
@@ -101,7 +101,8 @@ struct mxs_dma_ccw {
 	u32		pio_words[MXS_PIO_WORDS];
 };
 
-#define NUM_CCW	(int)(PAGE_SIZE / sizeof(struct mxs_dma_ccw))
+#define CCW_BLOCK_SIZE	(4 * PAGE_SIZE)
+#define NUM_CCW	(int)(CCW_BLOCK_SIZE / sizeof(struct mxs_dma_ccw))
 
 struct mxs_dma_chan {
 	struct mxs_dma_engine		*mxs_dma;
@@ -354,14 +355,15 @@ static int mxs_dma_alloc_chan_resources(struct dma_chan *chan)
 
 	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);
+	mxs_chan->ccw = dma_alloc_coherent(mxs_dma->dma_device.dev,
+				CCW_BLOCK_SIZE, &mxs_chan->ccw_phys,
+				GFP_KERNEL);
 	if (!mxs_chan->ccw) {
 		ret = -ENOMEM;
 		goto err_alloc;
 	}
 
-	memset(mxs_chan->ccw, 0, PAGE_SIZE);
+	memset(mxs_chan->ccw, 0, CCW_BLOCK_SIZE);
 
 	if (mxs_chan->chan_irq != NO_IRQ) {
 		ret = request_irq(mxs_chan->chan_irq, mxs_dma_int_handler,
@@ -387,7 +389,7 @@ static int mxs_dma_alloc_chan_resources(struct dma_chan *chan)
 err_clk:
 	free_irq(mxs_chan->chan_irq, mxs_dma);
 err_irq:
-	dma_free_coherent(mxs_dma->dma_device.dev, PAGE_SIZE,
+	dma_free_coherent(mxs_dma->dma_device.dev, CCW_BLOCK_SIZE,
 			mxs_chan->ccw, mxs_chan->ccw_phys);
 err_alloc:
 	return ret;
@@ -402,7 +404,7 @@ static void mxs_dma_free_chan_resources(struct dma_chan *chan)
 
 	free_irq(mxs_chan->chan_irq, mxs_dma);
 
-	dma_free_coherent(mxs_dma->dma_device.dev, PAGE_SIZE,
+	dma_free_coherent(mxs_dma->dma_device.dev, CCW_BLOCK_SIZE,
 			mxs_chan->ccw, mxs_chan->ccw_phys);
 
 	clk_disable_unprepare(mxs_dma->clk);
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index 169c0dbd71a..665668b6f2b 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -23,7 +23,6 @@
 #include <linux/dmaengine.h>
 #include <linux/amba/bus.h>
 #include <linux/amba/pl330.h>
-#include <linux/pm_runtime.h>
 #include <linux/scatterlist.h>
 #include <linux/of.h>
 
@@ -586,8 +585,6 @@ struct dma_pl330_dmac {
 
 	/* Peripheral channels connected to this DMAC */
 	struct dma_pl330_chan *peripherals; /* keep at end */
-
-	struct clk *clk;
 };
 
 struct dma_pl330_desc {
@@ -2395,7 +2392,7 @@ static int pl330_alloc_chan_resources(struct dma_chan *chan)
 	pch->pl330_chid = pl330_request_channel(&pdmac->pif);
 	if (!pch->pl330_chid) {
 		spin_unlock_irqrestore(&pch->lock, flags);
-		return 0;
+		return -ENOMEM;
 	}
 
 	tasklet_init(&pch->task, pl330_tasklet, (unsigned long) pch);
@@ -2889,29 +2886,17 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 		goto probe_err1;
 	}
 
-	pdmac->clk = clk_get(&adev->dev, "dma");
-	if (IS_ERR(pdmac->clk)) {
-		dev_err(&adev->dev, "Cannot get operation clock.\n");
-		ret = -EINVAL;
-		goto probe_err2;
-	}
-
 	amba_set_drvdata(adev, pdmac);
 
-#ifndef CONFIG_PM_RUNTIME
-	/* enable dma clk */
-	clk_enable(pdmac->clk);
-#endif
-
 	irq = adev->irq[0];
 	ret = request_irq(irq, pl330_irq_handler, 0,
 			dev_name(&adev->dev), pi);
 	if (ret)
-		goto probe_err3;
+		goto probe_err2;
 
 	ret = pl330_add(pi);
 	if (ret)
-		goto probe_err4;
+		goto probe_err3;
 
 	INIT_LIST_HEAD(&pdmac->desc_pool);
 	spin_lock_init(&pdmac->pool_lock);
@@ -2933,7 +2918,7 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 	if (!pdmac->peripherals) {
 		ret = -ENOMEM;
 		dev_err(&adev->dev, "unable to allocate pdmac->peripherals\n");
-		goto probe_err5;
+		goto probe_err4;
 	}
 
 	for (i = 0; i < num_chan; i++) {
@@ -2961,6 +2946,7 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 		if (pi->pcfg.num_peri) {
 			dma_cap_set(DMA_SLAVE, pd->cap_mask);
 			dma_cap_set(DMA_CYCLIC, pd->cap_mask);
+			dma_cap_set(DMA_PRIVATE, pd->cap_mask);
 		}
 	}
 
@@ -2976,7 +2962,7 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 	ret = dma_async_device_register(pd);
 	if (ret) {
 		dev_err(&adev->dev, "unable to register DMAC\n");
-		goto probe_err5;
+		goto probe_err4;
 	}
 
 	dev_info(&adev->dev,
@@ -2989,15 +2975,10 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 
 	return 0;
 
-probe_err5:
-	pl330_del(pi);
 probe_err4:
-	free_irq(irq, pi);
+	pl330_del(pi);
 probe_err3:
-#ifndef CONFIG_PM_RUNTIME
-	clk_disable(pdmac->clk);
-#endif
-	clk_put(pdmac->clk);
+	free_irq(irq, pi);
 probe_err2:
 	iounmap(pi->base);
 probe_err1:
@@ -3044,10 +3025,6 @@ static int __devexit pl330_remove(struct amba_device *adev)
 	res = &adev->res;
 	release_mem_region(res->start, resource_size(res));
 
-#ifndef CONFIG_PM_RUNTIME
-	clk_disable(pdmac->clk);
-#endif
-
 	kfree(pdmac);
 
 	return 0;
@@ -3063,49 +3040,10 @@ static struct amba_id pl330_ids[] = {
 
 MODULE_DEVICE_TABLE(amba, pl330_ids);
 
-#ifdef CONFIG_PM_RUNTIME
-static int pl330_runtime_suspend(struct device *dev)
-{
-	struct dma_pl330_dmac *pdmac = dev_get_drvdata(dev);
-
-	if (!pdmac) {
-		dev_err(dev, "failed to get dmac\n");
-		return -ENODEV;
-	}
-
-	clk_disable(pdmac->clk);
-
-	return 0;
-}
-
-static int pl330_runtime_resume(struct device *dev)
-{
-	struct dma_pl330_dmac *pdmac = dev_get_drvdata(dev);
-
-	if (!pdmac) {
-		dev_err(dev, "failed to get dmac\n");
-		return -ENODEV;
-	}
-
-	clk_enable(pdmac->clk);
-
-	return 0;
-}
-#else
-#define pl330_runtime_suspend	NULL
-#define pl330_runtime_resume	NULL
-#endif /* CONFIG_PM_RUNTIME */
-
-static const struct dev_pm_ops pl330_pm_ops = {
-	.runtime_suspend = pl330_runtime_suspend,
-	.runtime_resume = pl330_runtime_resume,
-};
-
 static struct amba_driver pl330_driver = {
 	.drv = {
 		.owner = THIS_MODULE,
 		.name = "dma-pl330",
-		.pm = &pl330_pm_ops,
 	},
 	.id_table = pl330_ids,
 	.probe = pl330_probe,
diff --git a/drivers/dma/sirf-dma.c b/drivers/dma/sirf-dma.c
index 3eed8b35b0f..64385cde044 100644
--- a/drivers/dma/sirf-dma.c
+++ b/drivers/dma/sirf-dma.c
@@ -570,21 +570,19 @@ static int __devinit sirfsoc_dma_probe(struct platform_device *op)
 
 	if (of_property_read_u32(dn, "cell-index", &id)) {
 		dev_err(dev, "Fail to get DMAC index\n");
-		ret = -ENODEV;
-		goto free_mem;
+		return -ENODEV;
 	}
 
 	sdma->irq = irq_of_parse_and_map(dn, 0);
 	if (sdma->irq == NO_IRQ) {
 		dev_err(dev, "Error mapping IRQ!\n");
-		ret = -EINVAL;
-		goto free_mem;
+		return -EINVAL;
 	}
 
 	ret = of_address_to_resource(dn, 0, &res);
 	if (ret) {
 		dev_err(dev, "Error parsing memory region!\n");
-		goto free_mem;
+		goto irq_dispose;
 	}
 
 	regs_start = res.start;
@@ -597,12 +595,11 @@ static int __devinit sirfsoc_dma_probe(struct platform_device *op)
 		goto irq_dispose;
 	}
 
-	ret = devm_request_irq(dev, sdma->irq, &sirfsoc_dma_irq, 0, DRV_NAME,
-		sdma);
+	ret = request_irq(sdma->irq, &sirfsoc_dma_irq, 0, DRV_NAME, sdma);
 	if (ret) {
 		dev_err(dev, "Error requesting IRQ!\n");
 		ret = -EINVAL;
-		goto unmap_mem;
+		goto irq_dispose;
 	}
 
 	dma = &sdma->dma;
@@ -652,13 +649,9 @@ static int __devinit sirfsoc_dma_probe(struct platform_device *op)
 	return 0;
 
 free_irq:
-	devm_free_irq(dev, sdma->irq, sdma);
+	free_irq(sdma->irq, sdma);
 irq_dispose:
 	irq_dispose_mapping(sdma->irq);
-unmap_mem:
-	iounmap(sdma->base);
-free_mem:
-	devm_kfree(dev, sdma);
 	return ret;
 }
 
@@ -668,10 +661,8 @@ static int __devexit sirfsoc_dma_remove(struct platform_device *op)
 	struct sirfsoc_dma *sdma = dev_get_drvdata(dev);
 
 	dma_async_device_unregister(&sdma->dma);
-	devm_free_irq(dev, sdma->irq, sdma);
+	free_irq(sdma->irq, sdma);
 	irq_dispose_mapping(sdma->irq);
-	iounmap(sdma->base);
-	devm_kfree(dev, sdma);
 	return 0;
 }
 
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index eee8d9b9a20..ae55091c227 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -2921,19 +2921,23 @@ static struct d40_base * __init d40_hw_detect_init(struct platform_device *pdev)
 	struct d40_base *base = NULL;
 	int num_log_chans = 0;
 	int num_phy_chans;
+	int clk_ret = -EINVAL;
 	int i;
 	u32 pid;
 	u32 cid;
 	u8 rev;
 
 	clk = clk_get(&pdev->dev, NULL);
-
 	if (IS_ERR(clk)) {
 		d40_err(&pdev->dev, "No matching clock found\n");
 		goto failure;
 	}
 
-	clk_enable(clk);
+	clk_ret = clk_prepare_enable(clk);
+	if (clk_ret) {
+		d40_err(&pdev->dev, "Failed to prepare/enable clock\n");
+		goto failure;
+	}
 
 	/* Get IO for DMAC base address */
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "base");
@@ -3063,10 +3067,10 @@ static struct d40_base * __init d40_hw_detect_init(struct platform_device *pdev)
 	return base;
 
 failure:
-	if (!IS_ERR(clk)) {
-		clk_disable(clk);
+	if (!clk_ret)
+		clk_disable_unprepare(clk);
+	if (!IS_ERR(clk))
 		clk_put(clk);
-	}
 	if (virtbase)
 		iounmap(virtbase);
 	if (res)
diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c
index 45fbeed1c1a..528c62dd4b0 100644
--- a/drivers/dma/tegra20-apb-dma.c
+++ b/drivers/dma/tegra20-apb-dma.c
@@ -169,6 +169,7 @@ typedef void (*dma_isr_handler)(struct tegra_dma_channel *tdc,
 /* tegra_dma_channel: Channel specific information */
 struct tegra_dma_channel {
 	struct dma_chan		dma_chan;
+	char			name[30];
 	bool			config_init;
 	int			id;
 	int			irq;
@@ -475,8 +476,7 @@ static void tegra_dma_abort_all(struct tegra_dma_channel *tdc)
 	while (!list_empty(&tdc->pending_sg_req)) {
 		sgreq = list_first_entry(&tdc->pending_sg_req,
 						typeof(*sgreq), node);
-		list_del(&sgreq->node);
-		list_add_tail(&sgreq->node, &tdc->free_sg_req);
+		list_move_tail(&sgreq->node, &tdc->free_sg_req);
 		if (sgreq->last_sg) {
 			dma_desc = sgreq->dma_desc;
 			dma_desc->dma_status = DMA_ERROR;
@@ -570,8 +570,7 @@ static void handle_cont_sngl_cycle_dma_done(struct tegra_dma_channel *tdc,
 
 	/* If not last req then put at end of pending list */
 	if (!list_is_last(&sgreq->node, &tdc->pending_sg_req)) {
-		list_del(&sgreq->node);
-		list_add_tail(&sgreq->node, &tdc->pending_sg_req);
+		list_move_tail(&sgreq->node, &tdc->pending_sg_req);
 		sgreq->configured = false;
 		st = handle_continuous_head_request(tdc, sgreq, to_terminate);
 		if (!st)
@@ -1284,7 +1283,6 @@ static int __devinit tegra_dma_probe(struct platform_device *pdev)
 	INIT_LIST_HEAD(&tdma->dma_dev.channels);
 	for (i = 0; i < cdata->nr_channels; i++) {
 		struct tegra_dma_channel *tdc = &tdma->channels[i];
-		char irq_name[30];
 
 		tdc->chan_base_offset = TEGRA_APBDMA_CHANNEL_BASE_ADD_OFFSET +
 					i * TEGRA_APBDMA_CHANNEL_REGISTER_SIZE;
@@ -1296,9 +1294,9 @@ static int __devinit tegra_dma_probe(struct platform_device *pdev)
 			goto err_irq;
 		}
 		tdc->irq = res->start;
-		snprintf(irq_name, sizeof(irq_name), "apbdma.%d", i);
+		snprintf(tdc->name, sizeof(tdc->name), "apbdma.%d", i);
 		ret = devm_request_irq(&pdev->dev, tdc->irq,
-				tegra_dma_isr, 0, irq_name, tdc);
+				tegra_dma_isr, 0, tdc->name, tdc);
 		if (ret) {
 			dev_err(&pdev->dev,
 				"request_irq failed with err %d channel %d\n",
diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index 8c2ff2490d9..1acae359cab 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -134,6 +134,7 @@ config SPI_DAVINCI
 	tristate "Texas Instruments DaVinci/DA8x/OMAP-L/AM1x SoC SPI controller"
 	depends on ARCH_DAVINCI
 	select SPI_BITBANG
+	select TI_EDMA
 	help
 	  SPI master controller for DaVinci/DA8x/OMAP-L/AM1x SPI modules.
 
diff --git a/drivers/spi/spi-davinci.c b/drivers/spi/spi-davinci.c
index 3afe2f4f5b8..147dfa87a64 100644
--- a/drivers/spi/spi-davinci.c
+++ b/drivers/spi/spi-davinci.c
@@ -25,13 +25,14 @@
 #include <linux/platform_device.h>
 #include <linux/err.h>
 #include <linux/clk.h>
+#include <linux/dmaengine.h>
 #include <linux/dma-mapping.h>
+#include <linux/edma.h>
 #include <linux/spi/spi.h>
 #include <linux/spi/spi_bitbang.h>
 #include <linux/slab.h>
 
 #include <linux/platform_data/spi-davinci.h>
-#include <mach/edma.h>
 
 #define SPI_NO_RESOURCE		((resource_size_t)-1)
 
@@ -113,14 +114,6 @@
 #define SPIDEF		0x4c
 #define SPIFMT0		0x50
 
-/* We have 2 DMA channels per CS, one for RX and one for TX */
-struct davinci_spi_dma {
-	int			tx_channel;
-	int			rx_channel;
-	int			dummy_param_slot;
-	enum dma_event_q	eventq;
-};
-
 /* SPI Controller driver's private data. */
 struct davinci_spi {
 	struct spi_bitbang	bitbang;
@@ -134,11 +127,14 @@ struct davinci_spi {
 
 	const void		*tx;
 	void			*rx;
-#define SPI_TMP_BUFSZ	(SMP_CACHE_BYTES + 1)
-	u8			rx_tmp_buf[SPI_TMP_BUFSZ];
 	int			rcount;
 	int			wcount;
-	struct davinci_spi_dma	dma;
+
+	struct dma_chan		*dma_rx;
+	struct dma_chan		*dma_tx;
+	int			dma_rx_chnum;
+	int			dma_tx_chnum;
+
 	struct davinci_spi_platform_data *pdata;
 
 	void			(*get_rx)(u32 rx_data, struct davinci_spi *);
@@ -496,21 +492,23 @@ out:
 	return errors;
 }
 
-static void davinci_spi_dma_callback(unsigned lch, u16 status, void *data)
+static void davinci_spi_dma_rx_callback(void *data)
 {
-	struct davinci_spi *dspi = data;
-	struct davinci_spi_dma *dma = &dspi->dma;
+	struct davinci_spi *dspi = (struct davinci_spi *)data;
 
-	edma_stop(lch);
+	dspi->rcount = 0;
 
-	if (status == DMA_COMPLETE) {
-		if (lch == dma->rx_channel)
-			dspi->rcount = 0;
-		if (lch == dma->tx_channel)
-			dspi->wcount = 0;
-	}
+	if (!dspi->wcount && !dspi->rcount)
+		complete(&dspi->done);
+}
 
-	if ((!dspi->wcount && !dspi->rcount) || (status != DMA_COMPLETE))
+static void davinci_spi_dma_tx_callback(void *data)
+{
+	struct davinci_spi *dspi = (struct davinci_spi *)data;
+
+	dspi->wcount = 0;
+
+	if (!dspi->wcount && !dspi->rcount)
 		complete(&dspi->done);
 }
 
@@ -526,20 +524,20 @@ static void davinci_spi_dma_callback(unsigned lch, u16 status, void *data)
 static int davinci_spi_bufs(struct spi_device *spi, struct spi_transfer *t)
 {
 	struct davinci_spi *dspi;
-	int data_type, ret;
+	int data_type, ret = -ENOMEM;
 	u32 tx_data, spidat1;
 	u32 errors = 0;
 	struct davinci_spi_config *spicfg;
 	struct davinci_spi_platform_data *pdata;
 	unsigned uninitialized_var(rx_buf_count);
-	struct device *sdev;
+	void *dummy_buf = NULL;
+	struct scatterlist sg_rx, sg_tx;
 
 	dspi = spi_master_get_devdata(spi->master);
 	pdata = dspi->pdata;
 	spicfg = (struct davinci_spi_config *)spi->controller_data;
 	if (!spicfg)
 		spicfg = &davinci_spi_default_cfg;
-	sdev = dspi->bitbang.master->dev.parent;
 
 	/* convert len to words based on bits_per_word */
 	data_type = dspi->bytes_per_word[spi->chip_select];
@@ -567,112 +565,83 @@ static int davinci_spi_bufs(struct spi_device *spi, struct spi_transfer *t)
 		spidat1 |= tx_data & 0xFFFF;
 		iowrite32(spidat1, dspi->base + SPIDAT1);
 	} else {
-		struct davinci_spi_dma *dma;
-		unsigned long tx_reg, rx_reg;
-		struct edmacc_param param;
-		void *rx_buf;
-		int b, c;
-
-		dma = &dspi->dma;
-
-		tx_reg = (unsigned long)dspi->pbase + SPIDAT1;
-		rx_reg = (unsigned long)dspi->pbase + SPIBUF;
-
-		/*
-		 * Transmit DMA setup
-		 *
-		 * If there is transmit data, map the transmit buffer, set it
-		 * as the source of data and set the source B index to data
-		 * size. If there is no transmit data, set the transmit register
-		 * as the source of data, and set the source B index to zero.
-		 *
-		 * The destination is always the transmit register itself. And
-		 * the destination never increments.
-		 */
-
-		if (t->tx_buf) {
-			t->tx_dma = dma_map_single(&spi->dev, (void *)t->tx_buf,
-						t->len, DMA_TO_DEVICE);
-			if (dma_mapping_error(&spi->dev, t->tx_dma)) {
-				dev_dbg(sdev, "Unable to DMA map %d bytes"
-						"TX buffer\n", t->len);
-				return -ENOMEM;
-			}
-		}
-
-		/*
-		 * If number of words is greater than 65535, then we need
-		 * to configure a 3 dimension transfer.  Use the BCNTRLD
-		 * feature to allow for transfers that aren't even multiples
-		 * of 65535 (or any other possible b size) by first transferring
-		 * the remainder amount then grabbing the next N blocks of
-		 * 65535 words.
-		 */
-
-		c = dspi->wcount / (SZ_64K - 1);	/* N 65535 Blocks */
-		b = dspi->wcount - c * (SZ_64K - 1);	/* Remainder */
-		if (b)
-			c++;
+		struct dma_slave_config dma_rx_conf = {
+			.direction = DMA_DEV_TO_MEM,
+			.src_addr = (unsigned long)dspi->pbase + SPIBUF,
+			.src_addr_width = data_type,
+			.src_maxburst = 1,
+		};
+		struct dma_slave_config dma_tx_conf = {
+			.direction = DMA_MEM_TO_DEV,
+			.dst_addr = (unsigned long)dspi->pbase + SPIDAT1,
+			.dst_addr_width = data_type,
+			.dst_maxburst = 1,
+		};
+		struct dma_async_tx_descriptor *rxdesc;
+		struct dma_async_tx_descriptor *txdesc;
+		void *buf;
+
+		dummy_buf = kzalloc(t->len, GFP_KERNEL);
+		if (!dummy_buf)
+			goto err_alloc_dummy_buf;
+
+		dmaengine_slave_config(dspi->dma_rx, &dma_rx_conf);
+		dmaengine_slave_config(dspi->dma_tx, &dma_tx_conf);
+
+		sg_init_table(&sg_rx, 1);
+		if (!t->rx_buf)
+			buf = dummy_buf;
 		else
-			b = SZ_64K - 1;
-
-		param.opt = TCINTEN | EDMA_TCC(dma->tx_channel);
-		param.src = t->tx_buf ? t->tx_dma : tx_reg;
-		param.a_b_cnt = b << 16 | data_type;
-		param.dst = tx_reg;
-		param.src_dst_bidx = t->tx_buf ? data_type : 0;
-		param.link_bcntrld = 0xffffffff;
-		param.src_dst_cidx = t->tx_buf ? data_type : 0;
-		param.ccnt = c;
-		edma_write_slot(dma->tx_channel, &param);
-		edma_link(dma->tx_channel, dma->dummy_param_slot);
-
-		/*
-		 * Receive DMA setup
-		 *
-		 * If there is receive buffer, use it to receive data. If there
-		 * is none provided, use a temporary receive buffer. Set the
-		 * destination B index to 0 so effectively only one byte is used
-		 * in the temporary buffer (address does not increment).
-		 *
-		 * The source of receive data is the receive data register. The
-		 * source address never increments.
-		 */
-
-		if (t->rx_buf) {
-			rx_buf = t->rx_buf;
-			rx_buf_count = t->len;
-		} else {
-			rx_buf = dspi->rx_tmp_buf;
-			rx_buf_count = sizeof(dspi->rx_tmp_buf);
+			buf = t->rx_buf;
+		t->rx_dma = dma_map_single(&spi->dev, buf,
+				t->len, DMA_FROM_DEVICE);
+		if (!t->rx_dma) {
+			ret = -EFAULT;
+			goto err_rx_map;
 		}
+		sg_dma_address(&sg_rx) = t->rx_dma;
+		sg_dma_len(&sg_rx) = t->len;
 
-		t->rx_dma = dma_map_single(&spi->dev, rx_buf, rx_buf_count,
-							DMA_FROM_DEVICE);
-		if (dma_mapping_error(&spi->dev, t->rx_dma)) {
-			dev_dbg(sdev, "Couldn't DMA map a %d bytes RX buffer\n",
-								rx_buf_count);
-			if (t->tx_buf)
-				dma_unmap_single(&spi->dev, t->tx_dma, t->len,
-								DMA_TO_DEVICE);
-			return -ENOMEM;
+		sg_init_table(&sg_tx, 1);
+		if (!t->tx_buf)
+			buf = dummy_buf;
+		else
+			buf = (void *)t->tx_buf;
+		t->tx_dma = dma_map_single(&spi->dev, buf,
+				t->len, DMA_FROM_DEVICE);
+		if (!t->tx_dma) {
+			ret = -EFAULT;
+			goto err_tx_map;
 		}
-
-		param.opt = TCINTEN | EDMA_TCC(dma->rx_channel);
-		param.src = rx_reg;
-		param.a_b_cnt = b << 16 | data_type;
-		param.dst = t->rx_dma;
-		param.src_dst_bidx = (t->rx_buf ? data_type : 0) << 16;
-		param.link_bcntrld = 0xffffffff;
-		param.src_dst_cidx = (t->rx_buf ? data_type : 0) << 16;
-		param.ccnt = c;
-		edma_write_slot(dma->rx_channel, &param);
+		sg_dma_address(&sg_tx) = t->tx_dma;
+		sg_dma_len(&sg_tx) = t->len;
+
+		rxdesc = dmaengine_prep_slave_sg(dspi->dma_rx,
+				&sg_rx, 1, DMA_DEV_TO_MEM,
+				DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+		if (!rxdesc)
+			goto err_desc;
+
+		txdesc = dmaengine_prep_slave_sg(dspi->dma_tx,
+				&sg_tx, 1, DMA_MEM_TO_DEV,
+				DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+		if (!txdesc)
+			goto err_desc;
+
+		rxdesc->callback = davinci_spi_dma_rx_callback;
+		rxdesc->callback_param = (void *)dspi;
+		txdesc->callback = davinci_spi_dma_tx_callback;
+		txdesc->callback_param = (void *)dspi;
 
 		if (pdata->cshold_bug)
 			iowrite16(spidat1 >> 16, dspi->base + SPIDAT1 + 2);
 
-		edma_start(dma->rx_channel);
-		edma_start(dma->tx_channel);
+		dmaengine_submit(rxdesc);
+		dmaengine_submit(txdesc);
+
+		dma_async_issue_pending(dspi->dma_rx);
+		dma_async_issue_pending(dspi->dma_tx);
+
 		set_io_bits(dspi->base + SPIINT, SPIINT_DMA_REQ_EN);
 	}
 
@@ -690,15 +659,13 @@ static int davinci_spi_bufs(struct spi_device *spi, struct spi_transfer *t)
 
 	clear_io_bits(dspi->base + SPIINT, SPIINT_MASKALL);
 	if (spicfg->io_type == SPI_IO_TYPE_DMA) {
-
-		if (t->tx_buf)
-			dma_unmap_single(&spi->dev, t->tx_dma, t->len,
-								DMA_TO_DEVICE);
-
-		dma_unmap_single(&spi->dev, t->rx_dma, rx_buf_count,
-							DMA_FROM_DEVICE);
-
 		clear_io_bits(dspi->base + SPIINT, SPIINT_DMA_REQ_EN);
+
+		dma_unmap_single(&spi->dev, t->rx_dma,
+				t->len, DMA_FROM_DEVICE);
+		dma_unmap_single(&spi->dev, t->tx_dma,
+				t->len, DMA_TO_DEVICE);
+		kfree(dummy_buf);
 	}
 
 	clear_io_bits(dspi->base + SPIGCR1, SPIGCR1_SPIENA_MASK);
@@ -716,11 +683,20 @@ static int davinci_spi_bufs(struct spi_device *spi, struct spi_transfer *t)
 	}
 
 	if (dspi->rcount != 0 || dspi->wcount != 0) {
-		dev_err(sdev, "SPI data transfer error\n");
+		dev_err(&spi->dev, "SPI data transfer error\n");
 		return -EIO;
 	}
 
 	return t->len;
+
+err_desc:
+	dma_unmap_single(&spi->dev, t->tx_dma, t->len, DMA_TO_DEVICE);
+err_tx_map:
+	dma_unmap_single(&spi->dev, t->rx_dma, t->len, DMA_FROM_DEVICE);
+err_rx_map:
+	kfree(dummy_buf);
+err_alloc_dummy_buf:
+	return ret;
 }
 
 /**
@@ -751,39 +727,33 @@ static irqreturn_t davinci_spi_irq(s32 irq, void *data)
 
 static int davinci_spi_request_dma(struct davinci_spi *dspi)
 {
+	dma_cap_mask_t mask;
+	struct device *sdev = dspi->bitbang.master->dev.parent;
 	int r;
-	struct davinci_spi_dma *dma = &dspi->dma;
 
-	r = edma_alloc_channel(dma->rx_channel, davinci_spi_dma_callback, dspi,
-								dma->eventq);
-	if (r < 0) {
-		pr_err("Unable to request DMA channel for SPI RX\n");
-		r = -EAGAIN;
+	dma_cap_zero(mask);
+	dma_cap_set(DMA_SLAVE, mask);
+
+	dspi->dma_rx = dma_request_channel(mask, edma_filter_fn,
+					   &dspi->dma_rx_chnum);
+	if (!dspi->dma_rx) {
+		dev_err(sdev, "request RX DMA channel failed\n");
+		r = -ENODEV;
 		goto rx_dma_failed;
 	}
 
-	r = edma_alloc_channel(dma->tx_channel, davinci_spi_dma_callback, dspi,
-								dma->eventq);
-	if (r < 0) {
-		pr_err("Unable to request DMA channel for SPI TX\n");
-		r = -EAGAIN;
+	dspi->dma_tx = dma_request_channel(mask, edma_filter_fn,
+					   &dspi->dma_tx_chnum);
+	if (!dspi->dma_tx) {
+		dev_err(sdev, "request TX DMA channel failed\n");
+		r = -ENODEV;
 		goto tx_dma_failed;
 	}
 
-	r = edma_alloc_slot(EDMA_CTLR(dma->tx_channel), EDMA_SLOT_ANY);
-	if (r < 0) {
-		pr_err("Unable to request SPI TX DMA param slot\n");
-		r = -EAGAIN;
-		goto param_failed;
-	}
-	dma->dummy_param_slot = r;
-	edma_link(dma->dummy_param_slot, dma->dummy_param_slot);
-
 	return 0;
-param_failed:
-	edma_free_channel(dma->tx_channel);
+
 tx_dma_failed:
-	edma_free_channel(dma->rx_channel);
+	dma_release_channel(dspi->dma_rx);
 rx_dma_failed:
 	return r;
 }
@@ -898,9 +868,8 @@ static int __devinit davinci_spi_probe(struct platform_device *pdev)
 	dspi->bitbang.txrx_bufs = davinci_spi_bufs;
 	if (dma_rx_chan != SPI_NO_RESOURCE &&
 	    dma_tx_chan != SPI_NO_RESOURCE) {
-		dspi->dma.rx_channel = dma_rx_chan;
-		dspi->dma.tx_channel = dma_tx_chan;
-		dspi->dma.eventq = pdata->dma_event_q;
+		dspi->dma_rx_chnum = dma_rx_chan;
+		dspi->dma_tx_chnum = dma_tx_chan;
 
 		ret = davinci_spi_request_dma(dspi);
 		if (ret)
@@ -955,9 +924,8 @@ static int __devinit davinci_spi_probe(struct platform_device *pdev)
 	return ret;
 
 free_dma:
-	edma_free_channel(dspi->dma.tx_channel);
-	edma_free_channel(dspi->dma.rx_channel);
-	edma_free_slot(dspi->dma.dummy_param_slot);
+	dma_release_channel(dspi->dma_rx);
+	dma_release_channel(dspi->dma_tx);
 free_clk:
 	clk_disable(dspi->clk);
 	clk_put(dspi->clk);