Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/djbw/async_tx

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/djbw/async_tx: (66 commits)
  avr32: at32ap700x: fix typo in DMA master configuration
  dmaengine/dmatest: Pass timeout via module params
  dma: let IMX_DMA depend on IMX_HAVE_DMA_V1 instead of an explicit list of SoCs
  fsldma: make halt behave nicely on all supported controllers
  fsldma: reduce locking during descriptor cleanup
  fsldma: support async_tx dependencies and automatic unmapping
  fsldma: fix controller lockups
  fsldma: minor codingstyle and consistency fixes
  fsldma: improve link descriptor debugging
  fsldma: use channel name in printk output
  fsldma: move related helper functions near each other
  dmatest: fix automatic buffer unmap type
  drivers, pch_dma: Fix warning when CONFIG_PM=n.
  dmaengine/dw_dmac fix: use readl & writel instead of __raw_readl & __raw_writel
  avr32: at32ap700x: Specify DMA Flow Controller, Src and Dst msize
  dw_dmac: Setting Default Burst length for transfers as 16.
  dw_dmac: Allow src/dst msize & flow controller to be configured at runtime
  dw_dmac: Changing type of src_master and dest_master to u8.
  dw_dmac: Pass Channel Priority from platform_data
  dw_dmac: Pass Channel Allocation Order from platform_data
  ...

12 files changed, 1902 insertions, 1242 deletions

diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 1c28816152fa..a572600e44eb 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -82,7 +82,7 @@ config INTEL_IOP_ADMA
 
 config DW_DMAC
 	tristate "Synopsys DesignWare AHB DMA support"
-	depends on AVR32
+	depends on HAVE_CLK
 	select DMA_ENGINE
 	default y if CPU_AT32AP7000
 	help
@@ -221,12 +221,20 @@ config IMX_SDMA
 
 config IMX_DMA
 	tristate "i.MX DMA support"
-	depends on ARCH_MX1 || ARCH_MX21 || MACH_MX27
+	depends on IMX_HAVE_DMA_V1
 	select DMA_ENGINE
 	help
 	  Support the i.MX DMA engine. This engine is integrated into
 	  Freescale i.MX1/21/27 chips.
 
+config MXS_DMA
+	bool "MXS DMA support"
+	depends on SOC_IMX23 || SOC_IMX28
+	select DMA_ENGINE
+	help
+	  Support the MXS DMA engine. This engine including APBH-DMA
+	  and APBX-DMA is integrated into Freescale i.MX23/28 chips.
+
 config DMA_ENGINE
 	bool
 
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index 1be065a62f8c..836095ab3c5c 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -19,6 +19,7 @@ obj-$(CONFIG_COH901318) += coh901318.o coh901318_lli.o
 obj-$(CONFIG_AMCC_PPC440SPE_ADMA) += ppc4xx/
 obj-$(CONFIG_IMX_SDMA) += imx-sdma.o
 obj-$(CONFIG_IMX_DMA) += imx-dma.o
+obj-$(CONFIG_MXS_DMA) += mxs-dma.o
 obj-$(CONFIG_TIMB_DMA) += timb_dma.o
 obj-$(CONFIG_STE_DMA40) += ste_dma40.o ste_dma40_ll.o
 obj-$(CONFIG_PL330_DMA) += pl330.o
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index 5589358b684d..e0888cb538d4 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -54,6 +54,11 @@ module_param(pq_sources, uint, S_IRUGO);
 MODULE_PARM_DESC(pq_sources,
 		"Number of p+q source buffers (default: 3)");
 
+static int timeout = 3000;
+module_param(timeout, uint, S_IRUGO);
+MODULE_PARM_DESC(timeout, "Transfer Timeout in msec (default: 3000), \
+		Pass -1 for infinite timeout");
+
 /*
  * Initialization patterns. All bytes in the source buffer has bit 7
  * set, all bytes in the destination buffer has bit 7 cleared.
@@ -285,7 +290,12 @@ static int dmatest_func(void *data)
 
 	set_user_nice(current, 10);
 
-	flags = DMA_CTRL_ACK | DMA_COMPL_SKIP_DEST_UNMAP | DMA_PREP_INTERRUPT;
+	/*
+	 * src buffers are freed by the DMAEngine code with dma_unmap_single()
+	 * dst buffers are freed by ourselves below
+	 */
+	flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT
+	      | DMA_COMPL_SKIP_DEST_UNMAP | DMA_COMPL_SRC_UNMAP_SINGLE;
 
 	while (!kthread_should_stop()
 	       && !(iterations && total_tests >= iterations)) {
@@ -294,7 +304,7 @@ static int dmatest_func(void *data)
 		dma_addr_t dma_srcs[src_cnt];
 		dma_addr_t dma_dsts[dst_cnt];
 		struct completion cmp;
-		unsigned long tmo = msecs_to_jiffies(3000);
+		unsigned long tmo = msecs_to_jiffies(timeout);
 		u8 align = 0;
 
 		total_tests++;
diff --git a/drivers/dma/dw_dmac.c b/drivers/dma/dw_dmac.c
index a3991ab0d67e..9c25c7d099e4 100644
--- a/drivers/dma/dw_dmac.c
+++ b/drivers/dma/dw_dmac.c
@@ -32,26 +32,30 @@
  * which does not support descriptor writeback.
  */
 
-/* NOTE:  DMS+SMS is system-specific. We should get this information
- * from the platform code somehow.
- */
-#define DWC_DEFAULT_CTLLO	(DWC_CTLL_DST_MSIZE(0)		\
-				| DWC_CTLL_SRC_MSIZE(0)		\
-				| DWC_CTLL_DMS(0)		\
-				| DWC_CTLL_SMS(1)		\
-				| DWC_CTLL_LLP_D_EN		\
-				| DWC_CTLL_LLP_S_EN)
+#define DWC_DEFAULT_CTLLO(private) ({				\
+		struct dw_dma_slave *__slave = (private);	\
+		int dms = __slave ? __slave->dst_master : 0;	\
+		int sms = __slave ? __slave->src_master : 1;	\
+		u8 smsize = __slave ? __slave->src_msize : DW_DMA_MSIZE_16; \
+		u8 dmsize = __slave ? __slave->dst_msize : DW_DMA_MSIZE_16; \
+								\
+		(DWC_CTLL_DST_MSIZE(dmsize)			\
+		 | DWC_CTLL_SRC_MSIZE(smsize)			\
+		 | DWC_CTLL_LLP_D_EN				\
+		 | DWC_CTLL_LLP_S_EN				\
+		 | DWC_CTLL_DMS(dms)				\
+		 | DWC_CTLL_SMS(sms));				\
+	})
 
 /*
  * This is configuration-dependent and usually a funny size like 4095.
- * Let's round it down to the nearest power of two.
  *
  * Note that this is a transfer count, i.e. if we transfer 32-bit
- * words, we can do 8192 bytes per descriptor.
+ * words, we can do 16380 bytes per descriptor.
  *
  * This parameter is also system-specific.
  */
-#define DWC_MAX_COUNT	2048U
+#define DWC_MAX_COUNT	4095U
 
 /*
  * Number of descriptors to allocate for each channel. This should be
@@ -84,11 +88,6 @@ static struct dw_desc *dwc_first_active(struct dw_dma_chan *dwc)
 	return list_entry(dwc->active_list.next, struct dw_desc, desc_node);
 }
 
-static struct dw_desc *dwc_first_queued(struct dw_dma_chan *dwc)
-{
-	return list_entry(dwc->queue.next, struct dw_desc, desc_node);
-}
-
 static struct dw_desc *dwc_desc_get(struct dw_dma_chan *dwc)
 {
 	struct dw_desc *desc, *_desc;
@@ -201,6 +200,7 @@ dwc_descriptor_complete(struct dw_dma_chan *dwc, struct dw_desc *desc)
 	dma_async_tx_callback		callback;
 	void				*param;
 	struct dma_async_tx_descriptor	*txd = &desc->txd;
+	struct dw_desc			*child;
 
 	dev_vdbg(chan2dev(&dwc->chan), "descriptor %u complete\n", txd->cookie);
 
@@ -209,6 +209,12 @@ dwc_descriptor_complete(struct dw_dma_chan *dwc, struct dw_desc *desc)
 	param = txd->callback_param;
 
 	dwc_sync_desc_for_cpu(dwc, desc);
+
+	/* async_tx_ack */
+	list_for_each_entry(child, &desc->tx_list, desc_node)
+		async_tx_ack(&child->txd);
+	async_tx_ack(&desc->txd);
+
 	list_splice_init(&desc->tx_list, &dwc->free_list);
 	list_move(&desc->desc_node, &dwc->free_list);
 
@@ -259,10 +265,11 @@ static void dwc_complete_all(struct dw_dma *dw, struct dw_dma_chan *dwc)
 	 * Submit queued descriptors ASAP, i.e. before we go through
 	 * the completed ones.
 	 */
-	if (!list_empty(&dwc->queue))
-		dwc_dostart(dwc, dwc_first_queued(dwc));
 	list_splice_init(&dwc->active_list, &list);
-	list_splice_init(&dwc->queue, &dwc->active_list);
+	if (!list_empty(&dwc->queue)) {
+		list_move(dwc->queue.next, &dwc->active_list);
+		dwc_dostart(dwc, dwc_first_active(dwc));
+	}
 
 	list_for_each_entry_safe(desc, _desc, &list, desc_node)
 		dwc_descriptor_complete(dwc, desc);
@@ -291,6 +298,9 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
 		return;
 	}
 
+	if (list_empty(&dwc->active_list))
+		return;
+
 	dev_vdbg(chan2dev(&dwc->chan), "scan_descriptors: llp=0x%x\n", llp);
 
 	list_for_each_entry_safe(desc, _desc, &dwc->active_list, desc_node) {
@@ -319,8 +329,8 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
 		cpu_relax();
 
 	if (!list_empty(&dwc->queue)) {
-		dwc_dostart(dwc, dwc_first_queued(dwc));
-		list_splice_init(&dwc->queue, &dwc->active_list);
+		list_move(dwc->queue.next, &dwc->active_list);
+		dwc_dostart(dwc, dwc_first_active(dwc));
 	}
 }
 
@@ -346,7 +356,7 @@ static void dwc_handle_error(struct dw_dma *dw, struct dw_dma_chan *dwc)
 	 */
 	bad_desc = dwc_first_active(dwc);
 	list_del_init(&bad_desc->desc_node);
-	list_splice_init(&dwc->queue, dwc->active_list.prev);
+	list_move(dwc->queue.next, dwc->active_list.prev);
 
 	/* Clear the error flag and try to restart the controller */
 	dma_writel(dw, CLEAR.ERROR, dwc->mask);
@@ -541,8 +551,8 @@ static dma_cookie_t dwc_tx_submit(struct dma_async_tx_descriptor *tx)
 	if (list_empty(&dwc->active_list)) {
 		dev_vdbg(chan2dev(tx->chan), "tx_submit: started %u\n",
 				desc->txd.cookie);
-		dwc_dostart(dwc, desc);
 		list_add_tail(&desc->desc_node, &dwc->active_list);
+		dwc_dostart(dwc, dwc_first_active(dwc));
 	} else {
 		dev_vdbg(chan2dev(tx->chan), "tx_submit: queued %u\n",
 				desc->txd.cookie);
@@ -581,14 +591,16 @@ dwc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 	 * We can be a lot more clever here, but this should take care
 	 * of the most common optimization.
 	 */
-	if (!((src | dest  | len) & 3))
+	if (!((src | dest  | len) & 7))
+		src_width = dst_width = 3;
+	else if (!((src | dest  | len) & 3))
 		src_width = dst_width = 2;
 	else if (!((src | dest | len) & 1))
 		src_width = dst_width = 1;
 	else
 		src_width = dst_width = 0;
 
-	ctllo = DWC_DEFAULT_CTLLO
+	ctllo = DWC_DEFAULT_CTLLO(chan->private)
 			| DWC_CTLL_DST_WIDTH(dst_width)
 			| DWC_CTLL_SRC_WIDTH(src_width)
 			| DWC_CTLL_DST_INC
@@ -669,11 +681,11 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 
 	switch (direction) {
 	case DMA_TO_DEVICE:
-		ctllo = (DWC_DEFAULT_CTLLO
+		ctllo = (DWC_DEFAULT_CTLLO(chan->private)
 				| DWC_CTLL_DST_WIDTH(reg_width)
 				| DWC_CTLL_DST_FIX
 				| DWC_CTLL_SRC_INC
-				| DWC_CTLL_FC_M2P);
+				| DWC_CTLL_FC(dws->fc));
 		reg = dws->tx_reg;
 		for_each_sg(sgl, sg, sg_len, i) {
 			struct dw_desc	*desc;
@@ -714,11 +726,11 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		}
 		break;
 	case DMA_FROM_DEVICE:
-		ctllo = (DWC_DEFAULT_CTLLO
+		ctllo = (DWC_DEFAULT_CTLLO(chan->private)
 				| DWC_CTLL_SRC_WIDTH(reg_width)
 				| DWC_CTLL_DST_INC
 				| DWC_CTLL_SRC_FIX
-				| DWC_CTLL_FC_P2M);
+				| DWC_CTLL_FC(dws->fc));
 
 		reg = dws->rx_reg;
 		for_each_sg(sgl, sg, sg_len, i) {
@@ -834,7 +846,9 @@ dwc_tx_status(struct dma_chan *chan,
 
 	ret = dma_async_is_complete(cookie, last_complete, last_used);
 	if (ret != DMA_SUCCESS) {
+		spin_lock_bh(&dwc->lock);
 		dwc_scan_descriptors(to_dw_dma(chan->device), dwc);
+		spin_unlock_bh(&dwc->lock);
 
 		last_complete = dwc->completed;
 		last_used = chan->cookie;
@@ -889,8 +903,11 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan)
 		BUG_ON(!dws->dma_dev || dws->dma_dev != dw->dma.dev);
 
 		cfghi = dws->cfg_hi;
-		cfglo = dws->cfg_lo;
+		cfglo = dws->cfg_lo & ~DWC_CFGL_CH_PRIOR_MASK;
 	}
+
+	cfglo |= DWC_CFGL_CH_PRIOR(dwc->priority);
+
 	channel_writel(dwc, CFG_LO, cfglo);
 	channel_writel(dwc, CFG_HI, cfghi);
 
@@ -1126,23 +1143,23 @@ struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan,
 		case DMA_TO_DEVICE:
 			desc->lli.dar = dws->tx_reg;
 			desc->lli.sar = buf_addr + (period_len * i);
-			desc->lli.ctllo = (DWC_DEFAULT_CTLLO
+			desc->lli.ctllo = (DWC_DEFAULT_CTLLO(chan->private)
 					| DWC_CTLL_DST_WIDTH(reg_width)
 					| DWC_CTLL_SRC_WIDTH(reg_width)
 					| DWC_CTLL_DST_FIX
 					| DWC_CTLL_SRC_INC
-					| DWC_CTLL_FC_M2P
+					| DWC_CTLL_FC(dws->fc)
 					| DWC_CTLL_INT_EN);
 			break;
 		case DMA_FROM_DEVICE:
 			desc->lli.dar = buf_addr + (period_len * i);
 			desc->lli.sar = dws->rx_reg;
-			desc->lli.ctllo = (DWC_DEFAULT_CTLLO
+			desc->lli.ctllo = (DWC_DEFAULT_CTLLO(chan->private)
 					| DWC_CTLL_SRC_WIDTH(reg_width)
 					| DWC_CTLL_DST_WIDTH(reg_width)
 					| DWC_CTLL_DST_INC
 					| DWC_CTLL_SRC_FIX
-					| DWC_CTLL_FC_P2M
+					| DWC_CTLL_FC(dws->fc)
 					| DWC_CTLL_INT_EN);
 			break;
 		default:
@@ -1307,7 +1324,17 @@ static int __init dw_probe(struct platform_device *pdev)
 		dwc->chan.device = &dw->dma;
 		dwc->chan.cookie = dwc->completed = 1;
 		dwc->chan.chan_id = i;
-		list_add_tail(&dwc->chan.device_node, &dw->dma.channels);
+		if (pdata->chan_allocation_order == CHAN_ALLOCATION_ASCENDING)
+			list_add_tail(&dwc->chan.device_node,
+					&dw->dma.channels);
+		else
+			list_add(&dwc->chan.device_node, &dw->dma.channels);
+
+		/* 7 is highest priority & 0 is lowest. */
+		if (pdata->chan_priority == CHAN_PRIORITY_ASCENDING)
+			dwc->priority = 7 - i;
+		else
+			dwc->priority = i;
 
 		dwc->ch_regs = &__dw_regs(dw)->CHAN[i];
 		spin_lock_init(&dwc->lock);
@@ -1335,6 +1362,8 @@ static int __init dw_probe(struct platform_device *pdev)
 
 	dma_cap_set(DMA_MEMCPY, dw->dma.cap_mask);
 	dma_cap_set(DMA_SLAVE, dw->dma.cap_mask);
+	if (pdata->is_private)
+		dma_cap_set(DMA_PRIVATE, dw->dma.cap_mask);
 	dw->dma.dev = &pdev->dev;
 	dw->dma.device_alloc_chan_resources = dwc_alloc_chan_resources;
 	dw->dma.device_free_chan_resources = dwc_free_chan_resources;
@@ -1447,7 +1476,7 @@ static int __init dw_init(void)
 {
 	return platform_driver_probe(&dw_driver, dw_probe);
 }
-module_init(dw_init);
+subsys_initcall(dw_init);
 
 static void __exit dw_exit(void)
 {
diff --git a/drivers/dma/dw_dmac_regs.h b/drivers/dma/dw_dmac_regs.h
index d9a939f67f46..720f821527f8 100644
--- a/drivers/dma/dw_dmac_regs.h
+++ b/drivers/dma/dw_dmac_regs.h
@@ -86,6 +86,7 @@ struct dw_dma_regs {
 #define DWC_CTLL_SRC_MSIZE(n)	((n)<<14)
 #define DWC_CTLL_S_GATH_EN	(1 << 17)	/* src gather, !FIX */
 #define DWC_CTLL_D_SCAT_EN	(1 << 18)	/* dst scatter, !FIX */
+#define DWC_CTLL_FC(n)		((n) << 20)
 #define DWC_CTLL_FC_M2M		(0 << 20)	/* mem-to-mem */
 #define DWC_CTLL_FC_M2P		(1 << 20)	/* mem-to-periph */
 #define DWC_CTLL_FC_P2M		(2 << 20)	/* periph-to-mem */
@@ -101,6 +102,8 @@ struct dw_dma_regs {
 #define DWC_CTLH_BLOCK_TS_MASK	0x00000fff
 
 /* Bitfields in CFG_LO. Platform-configurable bits are in <linux/dw_dmac.h> */
+#define DWC_CFGL_CH_PRIOR_MASK	(0x7 << 5)	/* priority mask */
+#define DWC_CFGL_CH_PRIOR(x)	((x) << 5)	/* priority */
 #define DWC_CFGL_CH_SUSP	(1 << 8)	/* pause xfer */
 #define DWC_CFGL_FIFO_EMPTY	(1 << 9)	/* pause xfer */
 #define DWC_CFGL_HS_DST		(1 << 10)	/* handshake w/dst */
@@ -134,6 +137,7 @@ struct dw_dma_chan {
 	struct dma_chan		chan;
 	void __iomem		*ch_regs;
 	u8			mask;
+	u8			priority;
 
 	spinlock_t		lock;
 
@@ -155,9 +159,9 @@ __dwc_regs(struct dw_dma_chan *dwc)
 }
 
 #define channel_readl(dwc, name) \
-	__raw_readl(&(__dwc_regs(dwc)->name))
+	readl(&(__dwc_regs(dwc)->name))
 #define channel_writel(dwc, name, val) \
-	__raw_writel((val), &(__dwc_regs(dwc)->name))
+	writel((val), &(__dwc_regs(dwc)->name))
 
 static inline struct dw_dma_chan *to_dw_dma_chan(struct dma_chan *chan)
 {
@@ -181,9 +185,9 @@ static inline struct dw_dma_regs __iomem *__dw_regs(struct dw_dma *dw)
 }
 
 #define dma_readl(dw, name) \
-	__raw_readl(&(__dw_regs(dw)->name))
+	readl(&(__dw_regs(dw)->name))
 #define dma_writel(dw, name, val) \
-	__raw_writel((val), &(__dw_regs(dw)->name))
+	writel((val), &(__dw_regs(dw)->name))
 
 #define channel_set_bit(dw, reg, mask) \
 	dma_writel(dw, reg, ((mask) << 8) | (mask))
diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c
index e3854a8f0de0..6b396759e7f5 100644
--- a/drivers/dma/fsldma.c
+++ b/drivers/dma/fsldma.c
@@ -37,35 +37,16 @@
 
 #include "fsldma.h"
 
-static const char msg_ld_oom[] = "No free memory for link descriptor\n";
+#define chan_dbg(chan, fmt, arg...)					\
+	dev_dbg(chan->dev, "%s: " fmt, chan->name, ##arg)
+#define chan_err(chan, fmt, arg...)					\
+	dev_err(chan->dev, "%s: " fmt, chan->name, ##arg)
 
-static void dma_init(struct fsldma_chan *chan)
-{
-	/* Reset the channel */
-	DMA_OUT(chan, &chan->regs->mr, 0, 32);
+static const char msg_ld_oom[] = "No free memory for link descriptor";
 
-	switch (chan->feature & FSL_DMA_IP_MASK) {
-	case FSL_DMA_IP_85XX:
-		/* Set the channel to below modes:
-		 * EIE - Error interrupt enable
-		 * EOSIE - End of segments interrupt enable (basic mode)
-		 * EOLNIE - End of links interrupt enable
-		 * BWC - Bandwidth sharing among channels
-		 */
-		DMA_OUT(chan, &chan->regs->mr, FSL_DMA_MR_BWC
-				| FSL_DMA_MR_EIE | FSL_DMA_MR_EOLNIE
-				| FSL_DMA_MR_EOSIE, 32);
-		break;
-	case FSL_DMA_IP_83XX:
-		/* Set the channel to below modes:
-		 * EOTIE - End-of-transfer interrupt enable
-		 * PRC_RM - PCI read multiple
-		 */
-		DMA_OUT(chan, &chan->regs->mr, FSL_DMA_MR_EOTIE
-				| FSL_DMA_MR_PRC_RM, 32);
-		break;
-	}
-}
+/*
+ * Register Helpers
+ */
 
 static void set_sr(struct fsldma_chan *chan, u32 val)
 {
@@ -77,14 +58,38 @@ static u32 get_sr(struct fsldma_chan *chan)
 	return DMA_IN(chan, &chan->regs->sr, 32);
 }
 
+static void set_cdar(struct fsldma_chan *chan, dma_addr_t addr)
+{
+	DMA_OUT(chan, &chan->regs->cdar, addr | FSL_DMA_SNEN, 64);
+}
+
+static dma_addr_t get_cdar(struct fsldma_chan *chan)
+{
+	return DMA_IN(chan, &chan->regs->cdar, 64) & ~FSL_DMA_SNEN;
+}
+
+static u32 get_bcr(struct fsldma_chan *chan)
+{
+	return DMA_IN(chan, &chan->regs->bcr, 32);
+}
+
+/*
+ * Descriptor Helpers
+ */
+
 static void set_desc_cnt(struct fsldma_chan *chan,
 				struct fsl_dma_ld_hw *hw, u32 count)
 {
 	hw->count = CPU_TO_DMA(chan, count, 32);
 }
 
+static u32 get_desc_cnt(struct fsldma_chan *chan, struct fsl_desc_sw *desc)
+{
+	return DMA_TO_CPU(chan, desc->hw.count, 32);
+}
+
 static void set_desc_src(struct fsldma_chan *chan,
-				struct fsl_dma_ld_hw *hw, dma_addr_t src)
+			 struct fsl_dma_ld_hw *hw, dma_addr_t src)
 {
 	u64 snoop_bits;
 
@@ -93,8 +98,18 @@ static void set_desc_src(struct fsldma_chan *chan,
 	hw->src_addr = CPU_TO_DMA(chan, snoop_bits | src, 64);
 }
 
+static dma_addr_t get_desc_src(struct fsldma_chan *chan,
+			       struct fsl_desc_sw *desc)
+{
+	u64 snoop_bits;
+
+	snoop_bits = ((chan->feature & FSL_DMA_IP_MASK) == FSL_DMA_IP_85XX)
+		? ((u64)FSL_DMA_SATR_SREADTYPE_SNOOP_READ << 32) : 0;
+	return DMA_TO_CPU(chan, desc->hw.src_addr, 64) & ~snoop_bits;
+}
+
 static void set_desc_dst(struct fsldma_chan *chan,
-				struct fsl_dma_ld_hw *hw, dma_addr_t dst)
+			 struct fsl_dma_ld_hw *hw, dma_addr_t dst)
 {
 	u64 snoop_bits;
 
@@ -103,8 +118,18 @@ static void set_desc_dst(struct fsldma_chan *chan,
 	hw->dst_addr = CPU_TO_DMA(chan, snoop_bits | dst, 64);
 }
 
+static dma_addr_t get_desc_dst(struct fsldma_chan *chan,
+			       struct fsl_desc_sw *desc)
+{
+	u64 snoop_bits;
+
+	snoop_bits = ((chan->feature & FSL_DMA_IP_MASK) == FSL_DMA_IP_85XX)
+		? ((u64)FSL_DMA_DATR_DWRITETYPE_SNOOP_WRITE << 32) : 0;
+	return DMA_TO_CPU(chan, desc->hw.dst_addr, 64) & ~snoop_bits;
+}
+
 static void set_desc_next(struct fsldma_chan *chan,
-				struct fsl_dma_ld_hw *hw, dma_addr_t next)
+			  struct fsl_dma_ld_hw *hw, dma_addr_t next)
 {
 	u64 snoop_bits;
 
@@ -113,24 +138,46 @@ static void set_desc_next(struct fsldma_chan *chan,
 	hw->next_ln_addr = CPU_TO_DMA(chan, snoop_bits | next, 64);
 }
 
-static void set_cdar(struct fsldma_chan *chan, dma_addr_t addr)
+static void set_ld_eol(struct fsldma_chan *chan, struct fsl_desc_sw *desc)
 {
-	DMA_OUT(chan, &chan->regs->cdar, addr | FSL_DMA_SNEN, 64);
-}
+	u64 snoop_bits;
 
-static dma_addr_t get_cdar(struct fsldma_chan *chan)
-{
-	return DMA_IN(chan, &chan->regs->cdar, 64) & ~FSL_DMA_SNEN;
-}
+	snoop_bits = ((chan->feature & FSL_DMA_IP_MASK) == FSL_DMA_IP_83XX)
+		? FSL_DMA_SNEN : 0;
 
-static dma_addr_t get_ndar(struct fsldma_chan *chan)
-{
-	return DMA_IN(chan, &chan->regs->ndar, 64);
+	desc->hw.next_ln_addr = CPU_TO_DMA(chan,
+		DMA_TO_CPU(chan, desc->hw.next_ln_addr, 64) | FSL_DMA_EOL
+			| snoop_bits, 64);
 }
 
-static u32 get_bcr(struct fsldma_chan *chan)
+/*
+ * DMA Engine Hardware Control Helpers
+ */
+
+static void dma_init(struct fsldma_chan *chan)
 {
-	return DMA_IN(chan, &chan->regs->bcr, 32);
+	/* Reset the channel */
+	DMA_OUT(chan, &chan->regs->mr, 0, 32);
+
+	switch (chan->feature & FSL_DMA_IP_MASK) {
+	case FSL_DMA_IP_85XX:
+		/* Set the channel to below modes:
+		 * EIE - Error interrupt enable
+		 * EOLNIE - End of links interrupt enable
+		 * BWC - Bandwidth sharing among channels
+		 */
+		DMA_OUT(chan, &chan->regs->mr, FSL_DMA_MR_BWC
+				| FSL_DMA_MR_EIE | FSL_DMA_MR_EOLNIE, 32);
+		break;
+	case FSL_DMA_IP_83XX:
+		/* Set the channel to below modes:
+		 * EOTIE - End-of-transfer interrupt enable
+		 * PRC_RM - PCI read multiple
+		 */
+		DMA_OUT(chan, &chan->regs->mr, FSL_DMA_MR_EOTIE
+				| FSL_DMA_MR_PRC_RM, 32);
+		break;
+	}
 }
 
 static int dma_is_idle(struct fsldma_chan *chan)
@@ -139,25 +186,32 @@ static int dma_is_idle(struct fsldma_chan *chan)
 	return (!(sr & FSL_DMA_SR_CB)) || (sr & FSL_DMA_SR_CH);
 }
 
+/*
+ * Start the DMA controller
+ *
+ * Preconditions:
+ * - the CDAR register must point to the start descriptor
+ * - the MRn[CS] bit must be cleared
+ */
 static void dma_start(struct fsldma_chan *chan)
 {
 	u32 mode;
 
 	mode = DMA_IN(chan, &chan->regs->mr, 32);
 
-	if ((chan->feature & FSL_DMA_IP_MASK) == FSL_DMA_IP_85XX) {
-		if (chan->feature & FSL_DMA_CHAN_PAUSE_EXT) {
-			DMA_OUT(chan, &chan->regs->bcr, 0, 32);
-			mode |= FSL_DMA_MR_EMP_EN;
-		} else {
-			mode &= ~FSL_DMA_MR_EMP_EN;
-		}
+	if (chan->feature & FSL_DMA_CHAN_PAUSE_EXT) {
+		DMA_OUT(chan, &chan->regs->bcr, 0, 32);
+		mode |= FSL_DMA_MR_EMP_EN;
+	} else {
+		mode &= ~FSL_DMA_MR_EMP_EN;
 	}
 
-	if (chan->feature & FSL_DMA_CHAN_START_EXT)
+	if (chan->feature & FSL_DMA_CHAN_START_EXT) {
 		mode |= FSL_DMA_MR_EMS_EN;
-	else
+	} else {
+		mode &= ~FSL_DMA_MR_EMS_EN;
 		mode |= FSL_DMA_MR_CS;
+	}
 
 	DMA_OUT(chan, &chan->regs->mr, mode, 32);
 }
@@ -167,13 +221,26 @@ static void dma_halt(struct fsldma_chan *chan)
 	u32 mode;
 	int i;
 
+	/* read the mode register */
 	mode = DMA_IN(chan, &chan->regs->mr, 32);
-	mode |= FSL_DMA_MR_CA;
-	DMA_OUT(chan, &chan->regs->mr, mode, 32);
 
-	mode &= ~(FSL_DMA_MR_CS | FSL_DMA_MR_EMS_EN | FSL_DMA_MR_CA);
+	/*
+	 * The 85xx controller supports channel abort, which will stop
+	 * the current transfer. On 83xx, this bit is the transfer error
+	 * mask bit, which should not be changed.
+	 */
+	if ((chan->feature & FSL_DMA_IP_MASK) == FSL_DMA_IP_85XX) {
+		mode |= FSL_DMA_MR_CA;
+		DMA_OUT(chan, &chan->regs->mr, mode, 32);
+
+		mode &= ~FSL_DMA_MR_CA;
+	}
+
+	/* stop the DMA controller */
+	mode &= ~(FSL_DMA_MR_CS | FSL_DMA_MR_EMS_EN);
 	DMA_OUT(chan, &chan->regs->mr, mode, 32);
 
+	/* wait for the DMA controller to become idle */
 	for (i = 0; i < 100; i++) {
 		if (dma_is_idle(chan))
 			return;
@@ -182,20 +249,7 @@ static void dma_halt(struct fsldma_chan *chan)
 	}
 
 	if (!dma_is_idle(chan))
-		dev_err(chan->dev, "DMA halt timeout!\n");
-}
-
-static void set_ld_eol(struct fsldma_chan *chan,
-			struct fsl_desc_sw *desc)
-{
-	u64 snoop_bits;
-
-	snoop_bits = ((chan->feature & FSL_DMA_IP_MASK) == FSL_DMA_IP_83XX)
-		? FSL_DMA_SNEN : 0;
-
-	desc->hw.next_ln_addr = CPU_TO_DMA(chan,
-		DMA_TO_CPU(chan, desc->hw.next_ln_addr, 64) | FSL_DMA_EOL
-			| snoop_bits, 64);
+		chan_err(chan, "DMA halt timeout!\n");
 }
 
 /**
@@ -321,8 +375,7 @@ static void fsl_chan_toggle_ext_start(struct fsldma_chan *chan, int enable)
 		chan->feature &= ~FSL_DMA_CHAN_START_EXT;
 }
 
-static void append_ld_queue(struct fsldma_chan *chan,
-			    struct fsl_desc_sw *desc)
+static void append_ld_queue(struct fsldma_chan *chan, struct fsl_desc_sw *desc)
 {
 	struct fsl_desc_sw *tail = to_fsl_desc(chan->ld_pending.prev);
 
@@ -363,8 +416,8 @@ static dma_cookie_t fsl_dma_tx_submit(struct dma_async_tx_descriptor *tx)
 	cookie = chan->common.cookie;
 	list_for_each_entry(child, &desc->tx_list, node) {
 		cookie++;
-		if (cookie < 0)
-			cookie = 1;
+		if (cookie < DMA_MIN_COOKIE)
+			cookie = DMA_MIN_COOKIE;
 
 		child->async_tx.cookie = cookie;
 	}
@@ -385,15 +438,14 @@ static dma_cookie_t fsl_dma_tx_submit(struct dma_async_tx_descriptor *tx)
  *
  * Return - The descriptor allocated. NULL for failed.
  */
-static struct fsl_desc_sw *fsl_dma_alloc_descriptor(
-					struct fsldma_chan *chan)
+static struct fsl_desc_sw *fsl_dma_alloc_descriptor(struct fsldma_chan *chan)
 {
 	struct fsl_desc_sw *desc;
 	dma_addr_t pdesc;
 
 	desc = dma_pool_alloc(chan->desc_pool, GFP_ATOMIC, &pdesc);
 	if (!desc) {
-		dev_dbg(chan->dev, "out of memory for link desc\n");
+		chan_dbg(chan, "out of memory for link descriptor\n");
 		return NULL;
 	}
 
@@ -403,10 +455,13 @@ static struct fsl_desc_sw *fsl_dma_alloc_descriptor(
 	desc->async_tx.tx_submit = fsl_dma_tx_submit;
 	desc->async_tx.phys = pdesc;
 
+#ifdef FSL_DMA_LD_DEBUG
+	chan_dbg(chan, "LD %p allocated\n", desc);
+#endif
+
 	return desc;
 }
 
-
 /**
  * fsl_dma_alloc_chan_resources - Allocate resources for DMA channel.
  * @chan : Freescale DMA channel
@@ -427,13 +482,11 @@ static int fsl_dma_alloc_chan_resources(struct dma_chan *dchan)
 	 * We need the descriptor to be aligned to 32bytes
 	 * for meeting FSL DMA specification requirement.
 	 */
-	chan->desc_pool = dma_pool_create("fsl_dma_engine_desc_pool",
-					  chan->dev,
+	chan->desc_pool = dma_pool_create(chan->name, chan->dev,
 					  sizeof(struct fsl_desc_sw),
 					  __alignof__(struct fsl_desc_sw), 0);
 	if (!chan->desc_pool) {
-		dev_err(chan->dev, "unable to allocate channel %d "
-				   "descriptor pool\n", chan->id);
+		chan_err(chan, "unable to allocate descriptor pool\n");
 		return -ENOMEM;
 	}
 
@@ -455,6 +508,9 @@ static void fsldma_free_desc_list(struct fsldma_chan *chan,
 
 	list_for_each_entry_safe(desc, _desc, list, node) {
 		list_del(&desc->node);
+#ifdef FSL_DMA_LD_DEBUG
+		chan_dbg(chan, "LD %p free\n", desc);
+#endif
 		dma_pool_free(chan->desc_pool, desc, desc->async_tx.phys);
 	}
 }
@@ -466,6 +522,9 @@ static void fsldma_free_desc_list_reverse(struct fsldma_chan *chan,
 
 	list_for_each_entry_safe_reverse(desc, _desc, list, node) {
 		list_del(&desc->node);
+#ifdef FSL_DMA_LD_DEBUG
+		chan_dbg(chan, "LD %p free\n", desc);
+#endif
 		dma_pool_free(chan->desc_pool, desc, desc->async_tx.phys);
 	}
 }
@@ -479,7 +538,7 @@ static void fsl_dma_free_chan_resources(struct dma_chan *dchan)
 	struct fsldma_chan *chan = to_fsl_chan(dchan);
 	unsigned long flags;
 
-	dev_dbg(chan->dev, "Free all channel resources.\n");
+	chan_dbg(chan, "free all channel resources\n");
 	spin_lock_irqsave(&chan->desc_lock, flags);
 	fsldma_free_desc_list(chan, &chan->ld_pending);
 	fsldma_free_desc_list(chan, &chan->ld_running);
@@ -502,7 +561,7 @@ fsl_dma_prep_interrupt(struct dma_chan *dchan, unsigned long flags)
 
 	new = fsl_dma_alloc_descriptor(chan);
 	if (!new) {
-		dev_err(chan->dev, msg_ld_oom);
+		chan_err(chan, "%s\n", msg_ld_oom);
 		return NULL;
 	}
 
@@ -512,14 +571,15 @@ fsl_dma_prep_interrupt(struct dma_chan *dchan, unsigned long flags)
 	/* Insert the link descriptor to the LD ring */
 	list_add_tail(&new->node, &new->tx_list);
 
-	/* Set End-of-link to the last link descriptor of new list*/
+	/* Set End-of-link to the last link descriptor of new list */
 	set_ld_eol(chan, new);
 
 	return &new->async_tx;
 }
 
-static struct dma_async_tx_descriptor *fsl_dma_prep_memcpy(
-	struct dma_chan *dchan, dma_addr_t dma_dst, dma_addr_t dma_src,
+static struct dma_async_tx_descriptor *
+fsl_dma_prep_memcpy(struct dma_chan *dchan,
+	dma_addr_t dma_dst, dma_addr_t dma_src,
 	size_t len, unsigned long flags)
 {
 	struct fsldma_chan *chan;
@@ -539,12 +599,9 @@ static struct dma_async_tx_descriptor *fsl_dma_prep_memcpy(
 		/* Allocate the link descriptor from DMA pool */
 		new = fsl_dma_alloc_descriptor(chan);
 		if (!new) {
-			dev_err(chan->dev, msg_ld_oom);
+			chan_err(chan, "%s\n", msg_ld_oom);
 			goto fail;
 		}
-#ifdef FSL_DMA_LD_DEBUG
-		dev_dbg(chan->dev, "new link desc alloc %p\n", new);
-#endif
 
 		copy = min(len, (size_t)FSL_DMA_BCR_MAX_CNT);
 
@@ -572,7 +629,7 @@ static struct dma_async_tx_descriptor *fsl_dma_prep_memcpy(
 	new->async_tx.flags = flags; /* client is in control of this ack */
 	new->async_tx.cookie = -EBUSY;
 
-	/* Set End-of-link to the last link descriptor of new list*/
+	/* Set End-of-link to the last link descriptor of new list */
 	set_ld_eol(chan, new);
 
 	return &first->async_tx;
@@ -627,12 +684,9 @@ static struct dma_async_tx_descriptor *fsl_dma_prep_sg(struct dma_chan *dchan,
 		/* allocate and populate the descriptor */
 		new = fsl_dma_alloc_descriptor(chan);
 		if (!new) {
-			dev_err(chan->dev, msg_ld_oom);
+			chan_err(chan, "%s\n", msg_ld_oom);
 			goto fail;
 		}
-#ifdef FSL_DMA_LD_DEBUG
-		dev_dbg(chan->dev, "new link desc alloc %p\n", new);
-#endif
 
 		set_desc_cnt(chan, &new->hw, len);
 		set_desc_src(chan, &new->hw, src);
@@ -744,14 +798,15 @@ static int fsl_dma_device_control(struct dma_chan *dchan,
 
 	switch (cmd) {
 	case DMA_TERMINATE_ALL:
+		spin_lock_irqsave(&chan->desc_lock, flags);
+
 		/* Halt the DMA engine */
 		dma_halt(chan);
 
-		spin_lock_irqsave(&chan->desc_lock, flags);
-
 		/* Remove and free all of the descriptors in the LD queue */
 		fsldma_free_desc_list(chan, &chan->ld_pending);
 		fsldma_free_desc_list(chan, &chan->ld_running);
+		chan->idle = true;
 
 		spin_unlock_irqrestore(&chan->desc_lock, flags);
 		return 0;
@@ -789,140 +844,87 @@ static int fsl_dma_device_control(struct dma_chan *dchan,
 }
 
 /**
- * fsl_dma_update_completed_cookie - Update the completed cookie.
- * @chan : Freescale DMA channel
- *
- * CONTEXT: hardirq
- */
-static void fsl_dma_update_completed_cookie(struct fsldma_chan *chan)
-{
-	struct fsl_desc_sw *desc;
-	unsigned long flags;
-	dma_cookie_t cookie;
-
-	spin_lock_irqsave(&chan->desc_lock, flags);
-
-	if (list_empty(&chan->ld_running)) {
-		dev_dbg(chan->dev, "no running descriptors\n");
-		goto out_unlock;
-	}
-
-	/* Get the last descriptor, update the cookie to that */
-	desc = to_fsl_desc(chan->ld_running.prev);
-	if (dma_is_idle(chan))
-		cookie = desc->async_tx.cookie;
-	else {
-		cookie = desc->async_tx.cookie - 1;
-		if (unlikely(cookie < DMA_MIN_COOKIE))
-			cookie = DMA_MAX_COOKIE;
-	}
-
-	chan->completed_cookie = cookie;
-
-out_unlock:
-	spin_unlock_irqrestore(&chan->desc_lock, flags);
-}
-
-/**
- * fsldma_desc_status - Check the status of a descriptor
+ * fsldma_cleanup_descriptor - cleanup and free a single link descriptor
  * @chan: Freescale DMA channel
- * @desc: DMA SW descriptor
- *
- * This function will return the status of the given descriptor
- */
-static enum dma_status fsldma_desc_status(struct fsldma_chan *chan,
-					  struct fsl_desc_sw *desc)
-{
-	return dma_async_is_complete(desc->async_tx.cookie,
-				     chan->completed_cookie,
-				     chan->common.cookie);
-}
-
-/**
- * fsl_chan_ld_cleanup - Clean up link descriptors
- * @chan : Freescale DMA channel
+ * @desc: descriptor to cleanup and free
  *
- * This function clean up the ld_queue of DMA channel.
+ * This function is used on a descriptor which has been executed by the DMA
+ * controller. It will run any callbacks, submit any dependencies, and then
+ * free the descriptor.
  */
-static void fsl_chan_ld_cleanup(struct fsldma_chan *chan)
+static void fsldma_cleanup_descriptor(struct fsldma_chan *chan,
+				      struct fsl_desc_sw *desc)
 {
-	struct fsl_desc_sw *desc, *_desc;
-	unsigned long flags;
-
-	spin_lock_irqsave(&chan->desc_lock, flags);
-
-	dev_dbg(chan->dev, "chan completed_cookie = %d\n", chan->completed_cookie);
-	list_for_each_entry_safe(desc, _desc, &chan->ld_running, node) {
-		dma_async_tx_callback callback;
-		void *callback_param;
-