Merge tag 'dmaengine-4.9-rc1' of git://git.infradead.org/users/vkoul/slave-dma

Pull dmaengine updates from Vinod Koul:
 "This is bit large pile of code which bring in some nice additions:

   - Error reporting: we have added a new mechanism for users of
     dmaenegine to register a callback_result which tells them the
     result of the dma transaction. Right now only one user (ntb) is
     using it.

   - As we discussed on KS mailing list and pointed out NO_IRQ has no
     place in kernel, this also remove NO_IRQ from dmaengine subsystem
     (both arm and ppc users)

   - Support for IOMMU slave transfers and its implementation for arm.

   - To get better build coverage, enable COMPILE_TEST for bunch of
     driver, and fix the warning and sparse complaints on these.

   - Apart from above, usual updates spread across drivers"

* tag 'dmaengine-4.9-rc1' of git://git.infradead.org/users/vkoul/slave-dma: (169 commits)
  async_pq_val: fix DMA memory leak
  dmaengine: virt-dma: move function declarations
  dmaengine: omap-dma: Enable burst and data pack for SG
  DT: dmaengine: rcar-dmac: document R8A7743/5 support
  dmaengine: fsldma: Unmap region obtained by of_iomap
  dmaengine: jz4780: fix resource leaks on error exit return
  dma-debug: fix ia64 build, use PHYS_PFN
  dmaengine: coh901318: fix integer overflow when shifting more than 32 places
  dmaengine: edma: avoid uninitialized variable use
  dma-mapping: fix m32r build warning
  dma-mapping: fix ia64 build, use PHYS_PFN
  dmaengine: ti-dma-crossbar: enable COMPILE_TEST
  dmaengine: omap-dma: enable COMPILE_TEST
  dmaengine: edma: enable COMPILE_TEST
  dmaengine: ti-dma-crossbar: Fix of_device_id data parameter usage
  dmaengine: ti-dma-crossbar: Correct type for of_find_property() third parameter
  dmaengine/ARM: omap-dma: Fix the DMAengine compile test on non OMAP configs
  dmaengine: edma: Rename set_bits and remove unused clear_bits helper
  dmaengine: edma: Use correct type for of_find_property() third parameter
  dmaengine: edma: Fix of_device_id data parameter usage (legacy vs TPCC)
  ...

60 files changed, 1615 insertions, 728 deletions

diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 739f797b40d9..af63a6bcf564 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -102,7 +102,7 @@ config AXI_DMAC
 config COH901318
 	bool "ST-Ericsson COH901318 DMA support"
 	select DMA_ENGINE
-	depends on ARCH_U300
+	depends on ARCH_U300 || COMPILE_TEST
 	help
 	  Enable support for ST-Ericsson COH 901 318 DMA.
 
@@ -114,13 +114,13 @@ config DMA_BCM2835
 
 config DMA_JZ4740
 	tristate "JZ4740 DMA support"
-	depends on MACH_JZ4740
+	depends on MACH_JZ4740 || COMPILE_TEST
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
 
 config DMA_JZ4780
 	tristate "JZ4780 DMA support"
-	depends on MACH_JZ4780
+	depends on MACH_JZ4780 || COMPILE_TEST
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
 	help
@@ -130,14 +130,14 @@ config DMA_JZ4780
 
 config DMA_OMAP
 	tristate "OMAP DMA support"
-	depends on ARCH_OMAP
+	depends on ARCH_OMAP || COMPILE_TEST
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
-	select TI_DMA_CROSSBAR if SOC_DRA7XX
+	select TI_DMA_CROSSBAR if (SOC_DRA7XX || COMPILE_TEST)
 
 config DMA_SA11X0
 	tristate "SA-11x0 DMA support"
-	depends on ARCH_SA1100
+	depends on ARCH_SA1100 || COMPILE_TEST
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
 	help
@@ -150,7 +150,6 @@ config DMA_SUN4I
 	depends on MACH_SUN4I || MACH_SUN5I || MACH_SUN7I
 	default (MACH_SUN4I || MACH_SUN5I || MACH_SUN7I)
 	select DMA_ENGINE
-	select DMA_OF
 	select DMA_VIRTUAL_CHANNELS
 	help
 	  Enable support for the DMA controller present in the sun4i,
@@ -167,7 +166,7 @@ config DMA_SUN6I
 
 config EP93XX_DMA
 	bool "Cirrus Logic EP93xx DMA support"
-	depends on ARCH_EP93XX
+	depends on ARCH_EP93XX || COMPILE_TEST
 	select DMA_ENGINE
 	help
 	  Enable support for the Cirrus Logic EP93xx M2P/M2M DMA controller.
@@ -279,7 +278,7 @@ config INTEL_MIC_X100_DMA
 
 config K3_DMA
 	tristate "Hisilicon K3 DMA support"
-	depends on ARCH_HI3xxx
+	depends on ARCH_HI3xxx || ARCH_HISI || COMPILE_TEST
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
 	help
@@ -297,16 +296,16 @@ config LPC18XX_DMAMUX
 
 config MMP_PDMA
 	bool "MMP PDMA support"
-	depends on (ARCH_MMP || ARCH_PXA)
+	depends on ARCH_MMP || ARCH_PXA || COMPILE_TEST
 	select DMA_ENGINE
 	help
 	  Support the MMP PDMA engine for PXA and MMP platform.
 
 config MMP_TDMA
 	bool "MMP Two-Channel DMA support"
-	depends on ARCH_MMP
+	depends on ARCH_MMP || COMPILE_TEST
 	select DMA_ENGINE
-	select MMP_SRAM
+	select MMP_SRAM if ARCH_MMP
 	help
 	  Support the MMP Two-Channel DMA engine.
 	  This engine used for MMP Audio DMA and pxa910 SQU.
@@ -316,7 +315,6 @@ config MOXART_DMA
 	tristate "MOXART DMA support"
 	depends on ARCH_MOXART
 	select DMA_ENGINE
-	select DMA_OF
 	select DMA_VIRTUAL_CHANNELS
 	help
 	  Enable support for the MOXA ART SoC DMA controller.
@@ -439,9 +437,8 @@ config STE_DMA40
 
 config STM32_DMA
 	bool "STMicroelectronics STM32 DMA support"
-	depends on ARCH_STM32
+	depends on ARCH_STM32 || COMPILE_TEST
 	select DMA_ENGINE
-	select DMA_OF
 	select DMA_VIRTUAL_CHANNELS
 	help
 	  Enable support for the on-chip DMA controller on STMicroelectronics
@@ -451,7 +448,7 @@ config STM32_DMA
 
 config S3C24XX_DMAC
 	bool "Samsung S3C24XX DMA support"
-	depends on ARCH_S3C24XX
+	depends on ARCH_S3C24XX || COMPILE_TEST
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
 	help
@@ -483,10 +480,9 @@ config TEGRA20_APB_DMA
 
 config TEGRA210_ADMA
 	bool "NVIDIA Tegra210 ADMA support"
-	depends on ARCH_TEGRA_210_SOC
+	depends on (ARCH_TEGRA_210_SOC || COMPILE_TEST) && PM_CLK
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
-	select PM_CLK
 	help
 	  Support for the NVIDIA Tegra210 ADMA controller driver. The
 	  DMA controller has multiple DMA channels and is used to service
@@ -497,7 +493,7 @@ config TEGRA210_ADMA
 
 config TIMB_DMA
 	tristate "Timberdale FPGA DMA support"
-	depends on MFD_TIMBERDALE
+	depends on MFD_TIMBERDALE || COMPILE_TEST
 	select DMA_ENGINE
 	help
 	  Enable support for the Timberdale FPGA DMA engine.
@@ -515,10 +511,10 @@ config TI_DMA_CROSSBAR
 
 config TI_EDMA
 	bool "TI EDMA support"
-	depends on ARCH_DAVINCI || ARCH_OMAP || ARCH_KEYSTONE
+	depends on ARCH_DAVINCI || ARCH_OMAP || ARCH_KEYSTONE || COMPILE_TEST
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
-	select TI_DMA_CROSSBAR if ARCH_OMAP
+	select TI_DMA_CROSSBAR if (ARCH_OMAP || COMPILE_TEST)
 	default n
 	help
 	  Enable support for the TI EDMA controller. This DMA
@@ -561,7 +557,7 @@ config XILINX_ZYNQMP_DMA
 
 config ZX_DMA
 	tristate "ZTE ZX296702 DMA support"
-	depends on ARCH_ZX
+	depends on ARCH_ZX || COMPILE_TEST
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
 	help
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index 53d22eb73b56..a4c8f80db29d 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -473,15 +473,11 @@ atc_chain_complete(struct at_dma_chan *atchan, struct at_desc *desc)
 	/* for cyclic transfers,
 	 * no need to replay callback function while stopping */
 	if (!atc_chan_is_cyclic(atchan)) {
-		dma_async_tx_callback	callback = txd->callback;
-		void			*param = txd->callback_param;
-
 		/*
 		 * The API requires that no submissions are done from a
 		 * callback, so we don't need to drop the lock here
 		 */
-		if (callback)
-			callback(param);
+		dmaengine_desc_get_callback_invoke(txd, NULL);
 	}
 
 	dma_run_dependencies(txd);
@@ -598,15 +594,12 @@ static void atc_handle_cyclic(struct at_dma_chan *atchan)
 {
 	struct at_desc			*first = atc_first_active(atchan);
 	struct dma_async_tx_descriptor	*txd = &first->txd;
-	dma_async_tx_callback		callback = txd->callback;
-	void				*param = txd->callback_param;
 
 	dev_vdbg(chan2dev(&atchan->chan_common),
 			"new cyclic period llp 0x%08x\n",
 			channel_readl(atchan, DSCR));
 
-	if (callback)
-		callback(param);
+	dmaengine_desc_get_callback_invoke(txd, NULL);
 }
 
 /*--  IRQ & Tasklet  ---------------------------------------------------*/
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index 832cbd647145..b7d7f2d443a1 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -1572,8 +1572,8 @@ static void at_xdmac_handle_cyclic(struct at_xdmac_chan *atchan)
 	desc = list_first_entry(&atchan->xfers_list, struct at_xdmac_desc, xfer_node);
 	txd = &desc->tx_dma_desc;
 
-	if (txd->callback && (txd->flags & DMA_PREP_INTERRUPT))
-		txd->callback(txd->callback_param);
+	if (txd->flags & DMA_PREP_INTERRUPT)
+		dmaengine_desc_get_callback_invoke(txd, NULL);
 }
 
 static void at_xdmac_tasklet(unsigned long data)
@@ -1616,8 +1616,8 @@ static void at_xdmac_tasklet(unsigned long data)
 
 		if (!at_xdmac_chan_is_cyclic(atchan)) {
 			dma_cookie_complete(txd);
-			if (txd->callback && (txd->flags & DMA_PREP_INTERRUPT))
-				txd->callback(txd->callback_param);
+			if (txd->flags & DMA_PREP_INTERRUPT)
+				dmaengine_desc_get_callback_invoke(txd, NULL);
 		}
 
 		dma_run_dependencies(txd);
diff --git a/drivers/dma/bestcomm/bestcomm.c b/drivers/dma/bestcomm/bestcomm.c
index 7ce843723003..7a67b8345092 100644
--- a/drivers/dma/bestcomm/bestcomm.c
+++ b/drivers/dma/bestcomm/bestcomm.c
@@ -82,7 +82,7 @@ bcom_task_alloc(int bd_count, int bd_size, int priv_size)
 
 	/* Get IRQ of that task */
 	tsk->irq = irq_of_parse_and_map(bcom_eng->ofnode, tsk->tasknum);
-	if (tsk->irq == NO_IRQ)
+	if (!tsk->irq)
 		goto error;
 
 	/* Init the BDs, if needed */
@@ -104,7 +104,7 @@ bcom_task_alloc(int bd_count, int bd_size, int priv_size)
 
 error:
 	if (tsk) {
-		if (tsk->irq != NO_IRQ)
+		if (tsk->irq)
 			irq_dispose_mapping(tsk->irq);
 		bcom_sram_free(tsk->bd);
 		kfree(tsk->cookie);
diff --git a/drivers/dma/coh901318.c b/drivers/dma/coh901318.c
index e4acd63e42aa..74794c9859f6 100644
--- a/drivers/dma/coh901318.c
+++ b/drivers/dma/coh901318.c
@@ -1319,10 +1319,10 @@ static void coh901318_list_print(struct coh901318_chan *cohc,
 	int i = 0;
 
 	while (l) {
-		dev_vdbg(COHC_2_DEV(cohc), "i %d, lli %p, ctrl 0x%x, src 0x%x"
-			 ", dst 0x%x, link 0x%x virt_link_addr 0x%p\n",
-			 i, l, l->control, l->src_addr, l->dst_addr,
-			 l->link_addr, l->virt_link_addr);
+		dev_vdbg(COHC_2_DEV(cohc), "i %d, lli %p, ctrl 0x%x, src 0x%pad"
+			 ", dst 0x%pad, link 0x%pad virt_link_addr 0x%p\n",
+			 i, l, l->control, &l->src_addr, &l->dst_addr,
+			 &l->link_addr, l->virt_link_addr);
 		i++;
 		l = l->virt_link_addr;
 	}
@@ -1335,7 +1335,7 @@ static void coh901318_list_print(struct coh901318_chan *cohc,
 static struct coh901318_base *debugfs_dma_base;
 static struct dentry *dma_dentry;
 
-static int coh901318_debugfs_read(struct file *file, char __user *buf,
+static ssize_t coh901318_debugfs_read(struct file *file, char __user *buf,
 				  size_t count, loff_t *f_pos)
 {
 	u64 started_channels = debugfs_dma_base->pm.started_channels;
@@ -1352,9 +1352,10 @@ static int coh901318_debugfs_read(struct file *file, char __user *buf,
 
 	tmp += sprintf(tmp, "DMA -- enabled dma channels\n");
 
-	for (i = 0; i < U300_DMA_CHANNELS; i++)
-		if (started_channels & (1 << i))
+	for (i = 0; i < U300_DMA_CHANNELS; i++) {
+		if (started_channels & (1ULL << i))
 			tmp += sprintf(tmp, "channel %d\n", i);
+	}
 
 	tmp += sprintf(tmp, "Pool alloc nbr %d\n", pool_count);
 
@@ -1553,15 +1554,8 @@ coh901318_desc_submit(struct coh901318_chan *cohc, struct coh901318_desc *desc)
 static struct coh901318_desc *
 coh901318_first_active_get(struct coh901318_chan *cohc)
 {
-	struct coh901318_desc *d;
-
-	if (list_empty(&cohc->active))
-		return NULL;
-
-	d = list_first_entry(&cohc->active,
-			     struct coh901318_desc,
-			     node);
-	return d;
+	return list_first_entry_or_null(&cohc->active, struct coh901318_desc,
+					node);
 }
 
 static void
@@ -1579,15 +1573,8 @@ coh901318_desc_queue(struct coh901318_chan *cohc, struct coh901318_desc *desc)
 static struct coh901318_desc *
 coh901318_first_queued(struct coh901318_chan *cohc)
 {
-	struct coh901318_desc *d;
-
-	if (list_empty(&cohc->queue))
-		return NULL;
-
-	d = list_first_entry(&cohc->queue,
-			     struct coh901318_desc,
-			     node);
-	return d;
+	return list_first_entry_or_null(&cohc->queue, struct coh901318_desc,
+					node);
 }
 
 static inline u32 coh901318_get_bytes_in_lli(struct coh901318_lli *in_lli)
@@ -1766,7 +1753,7 @@ static int coh901318_resume(struct dma_chan *chan)
 
 bool coh901318_filter_id(struct dma_chan *chan, void *chan_id)
 {
-	unsigned int ch_nr = (unsigned int) chan_id;
+	unsigned long ch_nr = (unsigned long) chan_id;
 
 	if (ch_nr == to_coh901318_chan(chan)->id)
 		return true;
@@ -1888,8 +1875,7 @@ static void dma_tasklet(unsigned long data)
 	struct coh901318_chan *cohc = (struct coh901318_chan *) data;
 	struct coh901318_desc *cohd_fin;
 	unsigned long flags;
-	dma_async_tx_callback callback;
-	void *callback_param;
+	struct dmaengine_desc_callback cb;
 
 	dev_vdbg(COHC_2_DEV(cohc), "[%s] chan_id %d"
 		 " nbr_active_done %ld\n", __func__,
@@ -1904,8 +1890,7 @@ static void dma_tasklet(unsigned long data)
 		goto err;
 
 	/* locate callback to client */
-	callback = cohd_fin->desc.callback;
-	callback_param = cohd_fin->desc.callback_param;
+	dmaengine_desc_get_callback(&cohd_fin->desc, &cb);
 
 	/* sign this job as completed on the channel */
 	dma_cookie_complete(&cohd_fin->desc);
@@ -1920,8 +1905,7 @@ static void dma_tasklet(unsigned long data)
 	spin_unlock_irqrestore(&cohc->lock, flags);
 
 	/* Call the callback when we're done */
-	if (callback)
-		callback(callback_param);
+	dmaengine_desc_callback_invoke(&cb, NULL);
 
 	spin_lock_irqsave(&cohc->lock, flags);
 
@@ -2247,8 +2231,8 @@ coh901318_prep_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 	spin_lock_irqsave(&cohc->lock, flg);
 
 	dev_vdbg(COHC_2_DEV(cohc),
-		 "[%s] channel %d src 0x%x dest 0x%x size %d\n",
-		 __func__, cohc->id, src, dest, size);
+		 "[%s] channel %d src 0x%pad dest 0x%pad size %zu\n",
+		 __func__, cohc->id, &src, &dest, size);
 
 	if (flags & DMA_PREP_INTERRUPT)
 		/* Trigger interrupt after last lli */
@@ -2744,8 +2728,8 @@ static int __init coh901318_probe(struct platform_device *pdev)
 		goto err_register_of_dma;
 
 	platform_set_drvdata(pdev, base);
-	dev_info(&pdev->dev, "Initialized COH901318 DMA on virtual base 0x%08x\n",
-		(u32) base->virtbase);
+	dev_info(&pdev->dev, "Initialized COH901318 DMA on virtual base 0x%p\n",
+		base->virtbase);
 
 	return err;
 
diff --git a/drivers/dma/coh901318_lli.c b/drivers/dma/coh901318_lli.c
index 702112d547c8..d612b2e5abc4 100644
--- a/drivers/dma/coh901318_lli.c
+++ b/drivers/dma/coh901318_lli.c
@@ -75,7 +75,7 @@ coh901318_lli_alloc(struct coh901318_pool *pool, unsigned int len)
 	lli = head;
 	lli->phy_this = phy;
 	lli->link_addr = 0x00000000;
-	lli->virt_link_addr = 0x00000000U;
+	lli->virt_link_addr = NULL;
 
 	for (i = 1; i < len; i++) {
 		lli_prev = lli;
@@ -88,7 +88,7 @@ coh901318_lli_alloc(struct coh901318_pool *pool, unsigned int len)
 		DEBUGFS_POOL_COUNTER_ADD(pool, 1);
 		lli->phy_this = phy;
 		lli->link_addr = 0x00000000;
-		lli->virt_link_addr = 0x00000000U;
+		lli->virt_link_addr = NULL;
 
 		lli_prev->link_addr = phy;
 		lli_prev->virt_link_addr = lli;
diff --git a/drivers/dma/cppi41.c b/drivers/dma/cppi41.c
index 4b2317426c8e..bac5f023013b 100644
--- a/drivers/dma/cppi41.c
+++ b/drivers/dma/cppi41.c
@@ -108,6 +108,8 @@ struct cppi41_channel {
 	unsigned td_queued:1;
 	unsigned td_seen:1;
 	unsigned td_desc_seen:1;
+
+	struct list_head node;		/* Node for pending list */
 };
 
 struct cppi41_desc {
@@ -146,6 +148,9 @@ struct cppi41_dd {
 	const struct chan_queues *queues_tx;
 	struct chan_queues td_queue;
 
+	struct list_head pending;	/* Pending queued transfers */
+	spinlock_t lock;		/* Lock for pending list */
+
 	/* context for suspend/resume */
 	unsigned int dma_tdfdq;
 };
@@ -331,7 +336,11 @@ static irqreturn_t cppi41_irq(int irq, void *data)
 
 			c->residue = pd_trans_len(c->desc->pd6) - len;
 			dma_cookie_complete(&c->txd);
-			c->txd.callback(c->txd.callback_param);
+			dmaengine_desc_get_callback_invoke(&c->txd, NULL);
+
+			/* Paired with cppi41_dma_issue_pending */
+			pm_runtime_mark_last_busy(cdd->ddev.dev);
+			pm_runtime_put_autosuspend(cdd->ddev.dev);
 		}
 	}
 	return IRQ_HANDLED;
@@ -349,6 +358,12 @@ static dma_cookie_t cppi41_tx_submit(struct dma_async_tx_descriptor *tx)
 static int cppi41_dma_alloc_chan_resources(struct dma_chan *chan)
 {
 	struct cppi41_channel *c = to_cpp41_chan(chan);
+	struct cppi41_dd *cdd = c->cdd;
+	int error;
+
+	error = pm_runtime_get_sync(cdd->ddev.dev);
+	if (error < 0)
+		return error;
 
 	dma_cookie_init(chan);
 	dma_async_tx_descriptor_init(&c->txd, chan);
@@ -357,11 +372,26 @@ static int cppi41_dma_alloc_chan_resources(struct dma_chan *chan)
 	if (!c->is_tx)
 		cppi_writel(c->q_num, c->gcr_reg + RXHPCRA0);
 
+	pm_runtime_mark_last_busy(cdd->ddev.dev);
+	pm_runtime_put_autosuspend(cdd->ddev.dev);
+
 	return 0;
 }
 
 static void cppi41_dma_free_chan_resources(struct dma_chan *chan)
 {
+	struct cppi41_channel *c = to_cpp41_chan(chan);
+	struct cppi41_dd *cdd = c->cdd;
+	int error;
+
+	error = pm_runtime_get_sync(cdd->ddev.dev);
+	if (error < 0)
+		return;
+
+	WARN_ON(!list_empty(&cdd->pending));
+
+	pm_runtime_mark_last_busy(cdd->ddev.dev);
+	pm_runtime_put_autosuspend(cdd->ddev.dev);
 }
 
 static enum dma_status cppi41_dma_tx_status(struct dma_chan *chan,
@@ -386,21 +416,6 @@ static void push_desc_queue(struct cppi41_channel *c)
 	u32 desc_phys;
 	u32 reg;
 
-	desc_phys = lower_32_bits(c->desc_phys);
-	desc_num = (desc_phys - cdd->descs_phys) / sizeof(struct cppi41_desc);
-	WARN_ON(cdd->chan_busy[desc_num]);
-	cdd->chan_busy[desc_num] = c;
-
-	reg = (sizeof(struct cppi41_desc) - 24) / 4;
-	reg |= desc_phys;
-	cppi_writel(reg, cdd->qmgr_mem + QMGR_QUEUE_D(c->q_num));
-}
-
-static void cppi41_dma_issue_pending(struct dma_chan *chan)
-{
-	struct cppi41_channel *c = to_cpp41_chan(chan);
-	u32 reg;
-
 	c->residue = 0;
 
 	reg = GCR_CHAN_ENABLE;
@@ -418,7 +433,46 @@ static void cppi41_dma_issue_pending(struct dma_chan *chan)
 	 * before starting the dma engine.
 	 */
 	__iowmb();
-	push_desc_queue(c);
+
+	desc_phys = lower_32_bits(c->desc_phys);
+	desc_num = (desc_phys - cdd->descs_phys) / sizeof(struct cppi41_desc);
+	WARN_ON(cdd->chan_busy[desc_num]);
+	cdd->chan_busy[desc_num] = c;
+
+	reg = (sizeof(struct cppi41_desc) - 24) / 4;
+	reg |= desc_phys;
+	cppi_writel(reg, cdd->qmgr_mem + QMGR_QUEUE_D(c->q_num));
+}
+
+static void pending_desc(struct cppi41_channel *c)
+{
+	struct cppi41_dd *cdd = c->cdd;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cdd->lock, flags);
+	list_add_tail(&c->node, &cdd->pending);
+	spin_unlock_irqrestore(&cdd->lock, flags);
+}
+
+static void cppi41_dma_issue_pending(struct dma_chan *chan)
+{
+	struct cppi41_channel *c = to_cpp41_chan(chan);
+	struct cppi41_dd *cdd = c->cdd;
+	int error;
+
+	/* PM runtime paired with dmaengine_desc_get_callback_invoke */
+	error = pm_runtime_get(cdd->ddev.dev);
+	if ((error != -EINPROGRESS) && error < 0) {
+		dev_err(cdd->ddev.dev, "Failed to pm_runtime_get: %i\n",
+			error);
+
+		return;
+	}
+
+	if (likely(pm_runtime_active(cdd->ddev.dev)))
+		push_desc_queue(c);
+	else
+		pending_desc(c);
 }
 
 static u32 get_host_pd0(u32 length)
@@ -940,12 +994,18 @@ static int cppi41_dma_probe(struct platform_device *pdev)
 	cdd->ctrl_mem = of_iomap(dev->of_node, 1);
 	cdd->sched_mem = of_iomap(dev->of_node, 2);
 	cdd->qmgr_mem = of_iomap(dev->of_node, 3);
+	spin_lock_init(&cdd->lock);
+	INIT_LIST_HEAD(&cdd->pending);
+
+	platform_set_drvdata(pdev, cdd);
 
 	if (!cdd->usbss_mem || !cdd->ctrl_mem || !cdd->sched_mem ||
 			!cdd->qmgr_mem)
 		return -ENXIO;
 
 	pm_runtime_enable(dev);
+	pm_runtime_set_autosuspend_delay(dev, 100);
+	pm_runtime_use_autosuspend(dev);
 	ret = pm_runtime_get_sync(dev);
 	if (ret < 0)
 		goto err_get_sync;
@@ -985,7 +1045,9 @@ static int cppi41_dma_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_of;
 
-	platform_set_drvdata(pdev, cdd);
+	pm_runtime_mark_last_busy(dev);
+	pm_runtime_put_autosuspend(dev);
+
 	return 0;
 err_of:
 	dma_async_device_unregister(&cdd->ddev);
@@ -996,7 +1058,8 @@ err_irq:
 err_chans:
 	deinit_cppi41(dev, cdd);
 err_init_cppi:
-	pm_runtime_put(dev);
+	pm_runtime_dont_use_autosuspend(dev);
+	pm_runtime_put_sync(dev);
 err_get_sync:
 	pm_runtime_disable(dev);
 	iounmap(cdd->usbss_mem);
@@ -1021,13 +1084,13 @@ static int cppi41_dma_remove(struct platform_device *pdev)
 	iounmap(cdd->ctrl_mem);
 	iounmap(cdd->sched_mem);
 	iounmap(cdd->qmgr_mem);
-	pm_runtime_put(&pdev->dev);
+	pm_runtime_dont_use_autosuspend(&pdev->dev);
+	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 	return 0;
 }
 
-#ifdef CONFIG_PM_SLEEP
-static int cppi41_suspend(struct device *dev)
+static int __maybe_unused cppi41_suspend(struct device *dev)
 {
 	struct cppi41_dd *cdd = dev_get_drvdata(dev);
 
@@ -1038,7 +1101,7 @@ static int cppi41_suspend(struct device *dev)
 	return 0;
 }
 
-static int cppi41_resume(struct device *dev)
+static int __maybe_unused cppi41_resume(struct device *dev)
 {
 	struct cppi41_dd *cdd = dev_get_drvdata(dev);
 	struct cppi41_channel *c;
@@ -1062,9 +1125,38 @@ static int cppi41_resume(struct device *dev)
 
 	return 0;
 }
-#endif
 
-static SIMPLE_DEV_PM_OPS(cppi41_pm_ops, cppi41_suspend, cppi41_resume);
+static int __maybe_unused cppi41_runtime_suspend(struct device *dev)
+{
+	struct cppi41_dd *cdd = dev_get_drvdata(dev);
+
+	WARN_ON(!list_empty(&cdd->pending));
+
+	return 0;
+}
+
+static int __maybe_unused cppi41_runtime_resume(struct device *dev)
+{
+	struct cppi41_dd *cdd = dev_get_drvdata(dev);
+	struct cppi41_channel *c, *_c;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cdd->lock, flags);
+	list_for_each_entry_safe(c, _c, &cdd->pending, node) {
+		push_desc_queue(c);
+		list_del(&c->node);
+	}
+	spin_unlock_irqrestore(&cdd->lock, flags);
+
+	return 0;
+}
+
+static const struct dev_pm_ops cppi41_pm_ops = {
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(cppi41_suspend, cppi41_resume)
+	SET_RUNTIME_PM_OPS(cppi41_runtime_suspend,
+			   cppi41_runtime_resume,
+			   NULL)
+};
 
 static struct platform_driver cpp41_dma_driver = {
 	.probe  = cppi41_dma_probe,
diff --git a/drivers/dma/dma-jz4740.c b/drivers/dma/dma-jz4740.c
index 9689b36c005a..d50273fed715 100644
--- a/drivers/dma/dma-jz4740.c
+++ b/drivers/dma/dma-jz4740.c
@@ -21,8 +21,6 @@
 #include <linux/irq.h>
 #include <linux/clk.h>
 
-#include <asm/mach-jz4740/dma.h>
-
 #include "virt-dma.h"
 
 #define JZ_DMA_NR_CHANS 6
diff --git a/drivers/dma/dma-jz4780.c b/drivers/dma/dma-jz4780.c
index dade7c47ff18..7373b7a555ec 100644
--- a/drivers/dma/dma-jz4780.c
+++ b/drivers/dma/dma-jz4780.c
@@ -324,8 +324,10 @@ static struct dma_async_tx_descriptor *jz4780_dma_prep_slave_sg(
 					      sg_dma_address(&sgl[i]),
 					      sg_dma_len(&sgl[i]),
 					      direction);
-		if (err < 0)
+		if (err < 0) {
+			jz4780_dma_desc_free(&jzchan->desc->vdesc);
 			return NULL;
+		}
 
 		desc->desc[i].dcm |= JZ_DMA_DCM_TIE;
 
@@ -368,8 +370,10 @@ static struct dma_async_tx_descriptor *jz4780_dma_prep_dma_cyclic(
 	for (i = 0; i < periods; i++) {
 		err = jz4780_dma_setup_hwdesc(jzchan, &desc->desc[i], buf_addr,
 					      period_len, direction);
-		if (err < 0)
+		if (err < 0) {
+			jz4780_dma_desc_free(&jzchan->desc->vdesc);
 			return NULL;
+		}
 
 		buf_addr += period_len;
 
@@ -396,7 +400,7 @@ static struct dma_async_tx_descriptor *jz4780_dma_prep_dma_cyclic(
 	return vchan_tx_prep(&jzchan->vchan, &desc->vdesc, flags);
 }
 
-struct dma_async_tx_descriptor *jz4780_dma_prep_dma_memcpy(
+static struct dma_async_tx_descriptor *jz4780_dma_prep_dma_memcpy(
 	struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 	size_t len, unsigned long flags)
 {
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 8c9f45fd55fc..6b535262ac5d 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -997,6 +997,13 @@ int dma_async_device_register(struct dma_device *device)
 		}
 		chan->client_count = 0;
 	}
+
+	if (!chancnt) {
+		dev_err(device->dev, "%s: device has no channels!\n", __func__);
+		rc = -ENODEV;
+		goto err_out;
+	}
+
 	device->chancnt = chancnt;
 
 	mutex_lock(&dma_list_mutex);
diff --git a/drivers/dma/dmaengine.h b/drivers/dma/dmaengine.h
index 17f983a4e9ba..882ff9448c3b 100644
--- a/drivers/dma/dmaengine.h
+++ b/drivers/dma/dmaengine.h
@@ -86,4 +86,88 @@ static inline void dma_set_residue(struct dma_tx_state *state, u32 residue)
 		state->residue = residue;
 }
 
+struct dmaengine_desc_callback {
+	dma_async_tx_callback callback;
+	dma_async_tx_callback_result callback_result;
+	void *callback_param;
+};
+
+/**
+ * dmaengine_desc_get_callback - get the passed in callback function
+ * @tx: tx descriptor
+ * @cb: temp struct to hold the callback info
+ *
+ * Fill the passed in cb struct with what's available in the passed in
+ * tx descriptor struct
+ * No locking is required.
+ */
+static inline void
+dmaengine_desc_get_callback(struct dma_async_tx_descriptor *tx,
+			    struct dmaengine_desc_callback *cb)
+{
+	cb->callback = tx->callback;
+	cb->callback_result = tx->callback_result;
+	cb->callback_param = tx->callback_param;
+}
+
+/**
+ * dmaengine_desc_callback_invoke - call the callback function in cb struct
+ * @cb: temp struct that is holding the callback info
+ * @result: transaction result
+ *
+ * Call the callback function provided in the cb struct with the parameter
+ * in the cb struct.
+ * Locking is dependent on the driver.
+ */
+static inline void
+dmaengine_desc_callback_invoke(struct dmaengine_desc_callback *cb,
+			       const struct dmaengine_result *result)
+{
+	struct dmaengine_result dummy_result = {
+		.result = DMA_TRANS_NOERROR,
+		.residue = 0
+	};
+
+	if (cb->callback_result) {
+		if (!result)
+			result = &dummy_result;
+		cb->callback_result(cb->callback_param, result);
+	} else if (cb->callback) {
+		cb->callback(cb->callback_param);
+	}
+}
+
+/**
+ * dmaengine_desc_get_callback_invoke - get the callback in tx descriptor and
+ * 					then immediately call the callback.
+ * @tx: dma async tx descriptor
+ * @result: transaction result
+ *
+ * Call dmaengine_desc_get_callback() and dmaengine_desc_callback_invoke()
+ * in a single function since no work is necessary in between for the driver.
+ * Locking is dependent on the driver.
+ */
+static inline void
+dmaengine_desc_get_callback_invoke(struct dma_async_tx_descriptor *tx,
+				   const struct dmaengine_result *result)
+{
+	struct dmaengine_desc_callback cb;
+
+	dmaengine_desc_get_callback(tx, &cb);
+	dmaengine_desc_callback_invoke(&cb, result);
+}
+
+/**
+ * dmaengine_desc_callback_valid - verify the callback is valid in cb
+ * @cb: callback info struct
+ *
+ * Return a bool that verifies whether callback in cb is valid or not.
+ * No locking is required.
+ */
+static inline bool
+dmaengine_desc_callback_valid(struct dmaengine_desc_callback *cb)
+{
+	return (cb->callback) ? true : false;
+}
+
 #endif
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index 1245db5438e1..cf76fc6149e5 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -56,10 +56,10 @@ module_param(sg_buffers, uint, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(sg_buffers,
 		"Number of scatter gather buffers (default: 1)");
 
-static unsigned int dmatest = 1;
+static unsigned int dmatest;
 module_param(dmatest, uint, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(dmatest,
-		"dmatest 0-memcpy 1-slave_sg (default: 1)");
+		"dmatest 0-memcpy 1-slave_sg (default: 0)");
 
 static unsigned int xor_sources = 3;
 module_param(xor_sources, uint, S_IRUGO | S_IWUSR);
@@ -426,7 +426,9 @@ static int dmatest_func(void *data)
 	int			src_cnt;
 	int			dst_cnt;
 	int			i;
-	ktime_t			ktime;
+	ktime_t			ktime, start, diff;
+	ktime_t			filltime = ktime_set(0, 0);
+	ktime_t			comparetime = ktime_set(0, 0);
 	s64			runtime = 0;
 	unsigned long long	total_len = 0;
 
@@ -503,7 +505,7 @@ static int dmatest_func(void *data)
 		total_tests++;
 
 		/* honor alignment restrictions */
-		if (thread->type == DMA_MEMCPY)
+		if (thread->type == DMA_MEMCPY || thread->type == DMA_SG)
 			align = dev->copy_align;
 		else if (thread->type == DMA_XOR)
 			align = dev->xor_align;
@@ -531,6 +533,7 @@ static int dmatest_func(void *data)
 			src_off = 0;
 			dst_off = 0;
 		} else {
+			start = ktime_get();
 			src_off = dmatest_random() % (params->buf_size - len + 1);
 			dst_off = dmatest_random() % (params->buf_size - len + 1);
 
@@ -541,6 +544,9 @@ static int dmatest_func(void *data)
 					  params->buf_size);
 			dmatest_init_dsts(thread->dsts, dst_off, len,
 					  params->buf_size);
+
+			diff = ktime_sub(ktime_get(), start);
+			filltime = ktime_add(filltime, diff);
 		}
 
 		um = dmaengine_get_unmap_data(dev->dev, src_cnt+dst_cnt,
@@ -683,6 +689,7 @@ static int dmatest_func(void *data)
 			continue;
 		}
 
+		start = ktime_get();
 		pr_debug("%s: verifying source buffer...\n", current->comm);
 		error_count = dmatest_verify(thread->srcs, 0, src_off,
 				0, PATTERN_SRC, true);
@@ -703,6 +710,9 @@ static int dmatest_func(void *data)
 				params->buf_size, dst_off + len,
 				PATTERN_DST, false);
 
+		diff = ktime_sub(ktime_get(), start);
+		comparetime = ktime_add(comparetime, diff);
+
 		if (error_count) {
 			result("data error", total_tests, src_off, dst_off,
 			       len, error_count);
@@ -712,7 +722,10 @@ static int dmatest_func(void *data)
 				       dst_off, len, 0);
 		}
 	}
-	runtime = ktime_us_delta(ktime_get(), ktime);
+	ktime = ktime_sub(ktime_get(), ktime);
+	ktime = ktime_sub(ktime, comparetime);
+	ktime = ktime_sub(ktime, filltime);
+	runtime = ktime_to_us(ktime);
 
 	ret = 0;
 err_dstbuf:
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index da18b18561c4..c2c0a613cb7a 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -274,20 +274,19 @@ static void
 dwc_descriptor_complete(struct dw_dma_chan *dwc, struct dw_desc *desc,
 		bool callback_required)
 {
-	dma_async_tx_callback		callback = NULL;
-	void				*param = NULL;
 	struct dma_async_tx_descriptor	*txd = &desc->txd;
 	struct dw_desc			*child;
 	unsigned long			flags;
+	struct dmaengine_desc_callback	cb;
 
 	dev_vdbg(chan2dev(&dwc->chan), "descriptor %u complete\n", txd->cookie);
 
 	spin_lock_irqsave(&dwc->lock, flags);
 	dma_cookie_complete(txd);
-	if (callback_required) {
-		callback = txd->callback;
-		param = txd->callback_param;
-	}
+	if (callback_required)
+		dmaengine_desc_get_callback(txd, &cb);
+	else
+		memset(&cb, 0, sizeof(cb));
 
 	/* async_tx_ack */
 	list_for_each_entry(child, &desc->tx_list, desc_node)
@@ -296,8 +295,7 @@ dwc_descriptor_complete(struct dw_dma_chan *dwc, struct dw_desc *desc,
 	dwc_desc_put(dwc, desc);
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
-	if (callback)
-		callback(param);
+	dmaengine_desc_callback_invoke(&cb, NULL);
 }
 
 static void dwc_complete_all(struct dw_dma *dw, struct dw_dma_chan *dwc)
diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c
index 3d277fa76c1a..e18a58068bca 100644
--- a/drivers/dma/edma.c
+++ b/drivers/dma/edma.c
@@ -263,22 +263,29 @@ static const struct edmacc_param dummy_paramset = {
 
 #define EDMA_BINDING_LEGACY	0
 #define EDMA_BINDING_TPCC	1
+static const u32 edma_binding_type[] = {
+	[EDMA_BINDING_LEGACY] = EDMA_BINDING_LEGACY,
+	[EDMA_BINDING_TPCC] = EDMA_BINDING_TPCC,
+};
+
 static const struct of_device_id edma_of_ids[] = {
 	{
 		.compatible = "ti,edma3",
-		.data = (void *)EDMA_BINDING_LEGACY,
+		.data = &edma_binding_type[EDMA_BINDING_LEGACY],
 	},
 	{
 		.compatible = "ti,edma3-tpcc",
-		.data = (void *)EDMA_BINDING_TPCC,
+		.data = &edma_binding_type[EDMA_BINDING_TPCC],
 	},
 	{}
 };
+MODULE_DEVICE_TABLE(of, edma_of_ids);
 
 static const struct of_device_id edma_tptc_of_ids[] = {
 	{ .compatible = "ti,edma3-tptc", },
 	{}
 };
+MODULE_DEVICE_TABLE(of, edma_tptc_of_ids);
 
 static inline unsigned int edma_read(struct edma_cc *ecc, int offset)
 {
@@ -405,18 +412,12 @@ static inline void edma_param_or(struct edma_cc *ecc, int offset, int param_no,
 	edma_or(ecc, EDMA_PARM + offset + (param_no << 5), or);
 }
 
-static inline void set_bits(int offset, int len, unsigned long *p)
+static inline void edma_set_bits(int offset, int len, unsigned long *p)
 {
 	for (; len > 0; len--)
 		set_bit(offset + (len - 1), p);
 }
 
-static inline void clear_bits(int offset, int len, unsigned long *p)
-{
-	for (; len > 0; len--)
-		clear_bit(offset + (len - 1), p);
-}
-
 static void edma_assign_priority_to_queue(struct edma_cc *ecc, int queue_no,
 					  int priority)
 {
@@ -464,13 +465,15 @@ static void edma_write_slot(struct edma_cc *ecc, unsigned slot,
 	memcpy_toio(ecc->base + PARM_OFFSET(slot), param, PARM_SIZE);
 }
 
-static void edma_read_slot(struct edma_cc *ecc, unsigned slot,
+static int edma_read_slot(struct edma_cc *ecc, unsigned slot,
 			   struct edmacc_param *param)
 {
 	slot = EDMA_CHAN_SLOT(slot);
 	if (slot >= ecc->num_slots)
-		return;
+		return -EINVAL;
 	memcpy_fromio(param, ecc->base + PARM_OFFSET(slot), PARM_SIZE);
+
+	return 0;
 }
 
 /**
@@ -1476,13 +1479,15 @@ static void edma_error_handler(struct edma_chan *echan)
 	struct edma_cc *ecc = echan->ecc;
 	struct device *dev = echan->vchan.chan.device->dev;
 	struct edmacc_param p;
+	int err;
 
 	if (!echan->edesc)
 		return;
 
 	spin_lock(&echan->vchan.lock);
 
-	edma_read_slot(ecc, echan->slot[0], &p);
+	err = edma_read_slot(ecc, echan->slot[0], &p);
+
 	/*
 	 * Issue later based on missed flag which will be sure
 	 * to happen as:
@@ -1495,7 +1500,7 @@ static void edma_error_handler(struct edma_chan *echan)
 	 * lead to some nasty recursion when we are in a NULL
 	 * slot. So we avoid doing so and set the missed flag.
 	 */
-	if (p.a_b_cnt == 0 && p.ccnt == 0) {
+	if (err || (p.a_b_cnt == 0 && p.ccnt == 0)) {
 		dev_dbg(dev, "Error on null slot, setting miss\n");
 		echan->missed = 1;
 	} else {
@@ -2019,8 +2024,7 @@ static struct edma_soc_info *edma_setup_info_from_dt(struct device *dev,
 {
 	struct edma_soc_info *info;
 	struct property *prop;
-	size_t sz;
-	int ret;
+	int sz, ret;
 
 	info = devm_kzalloc(dev, sizeof(struct edma_soc_info), GFP_KERNEL);
 	if (!info)
@@ -2182,7 +2186,7 @@ static int edma_probe(struct platform_device *pdev)
 		const struct of_device_id *match;
 
 		match = of_match_node(edma_of_ids, node);
-		if (match && (u32)match->data == EDMA_BINDING_TPCC)
+		if (match && (*(u32 *)match->data) == EDMA_BINDING_TPCC)
 			legacy_mode = false;
 
 		info = edma_setup_info_from_dt(dev, legacy_mode);
@@ -2260,7 +2264,7 @@ static int edma_probe(struct platform_device *pdev)
 			for (i = 0; rsv_slots[i][0] != -1; i++) {
 				off = rsv_slots[i][0];
 				ln = rsv_slots[i][1];
-				set_bits(off, ln, ecc->slot_inuse);
+				edma_set_bits(off, ln, ecc->slot_inuse);
 			}
 		}
 	}
diff --git a/drivers/dma/ep93xx_dma.c b/drivers/dma/ep93xx_dma.c
index 21f08cc3352b..d37e8dda8079 100644
--- a/drivers/dma/ep93xx_dma.c
+++ b/drivers/dma/ep93xx_dma.c
@@ -262,10 +262,8 @@ static void ep93xx_dma_set_active(struct ep93xx_dma_chan *edmac,
 static struct ep93xx_dma_desc *
 ep93xx_dma_get_active(struct ep93xx_dma_chan *edmac)
 {
-	if (list_empty(&edmac->active))
-		return NULL;
-
-	return list_first_entry(&edmac->active, struct ep93xx_dma_desc, node);
+	return list_first_entry_or_null(&edmac->active,
+					struct ep93xx_dma_desc, node);
 }
 
 /**
@@ -739,10 +737,10 @@ static void ep93xx_dma_tasklet(unsigned long data)
 {
 	struct ep93xx_dma_chan *edmac = (struct ep93xx_dma_chan *)data;
 	struct ep93xx_dma_desc *desc, *d;
-	dma_async_tx_callback callback = NULL;
-	void *callback_param = NULL;
+	struct dmaengine_desc_callback cb;
 	LIST_HEAD(list);
 
+	memset(&cb, 0, sizeof(cb));
 	spin_lock_irq(&edmac->lock);
 	/*
 	 * If dma_terminate_all() was called before we get to run, the active
@@ -757,8 +755,7 @@ static void ep93xx_dma_tasklet(unsigned long data)
 				dma_cookie_complete(&desc->txd);
 			list_splice_init(&edmac->active, &list);
 		}
-		callback = desc->txd.callback;
-		callback_param = desc->txd.callback_param;
+		dmaengine_desc_get_callback(&desc->txd, &cb);
 	}
 	spin_unlock_irq(&edmac->lock);
 
@@ -771,8 +768,7 @@ static void ep93xx_dma_tasklet(unsigned long data)
 		ep93xx_dma_desc_put(edmac, desc);
 	}
 
-	if (callback)
-		callback(callback_param);
+	dmaengine_desc_callback_invoke(&cb, NULL);
 }
 
 static irqreturn_t ep93xx_dma_interrupt(int irq, void *dev_id)
@@ -1047,11 +1043,11 @@ ep93xx_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 
 	first = NULL;
 	for_each_sg(sgl, sg, sg_len, i) {
-		size_t sg_len = sg_dma_len(sg);
+		size_t len = sg_dma_len(sg);
 
-		if (sg_len > DMA_MAX_CHAN_BYTES) {
-			dev_warn(chan2dev(edmac), "too big transfer size %d\n",
-				 sg_len);
+		if (len > DMA_MAX_CHAN_BYTES) {
+			dev_warn(chan2dev(edmac), "too big transfer size %zu\n",
+				 len);
 			goto fail;
 		}
 
@@ -1068,7 +1064,7 @@ ep93xx_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 			desc->src_addr = edmac->runtime_addr;
 			desc->dst_addr = sg_dma_address(sg);
 		}
-		desc->size = sg_len;
+		desc->size = len;
 
 		if (!first)
 			first = desc;
@@ -1125,7 +1121,7 @@ ep93xx_dma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t dma_addr,
 	}
 
 	if (period_len > DMA_MAX_CHAN_BYTES) {
-		dev_warn(chan2dev(edmac), "too big period length %d\n",
+		dev_warn(chan2dev(edmac), "too big period length %zu\n",
 			 period_len);
 		return NULL;
 	}
diff --git a/drivers/dma/fsl_raid.c b/drivers/dma/fsl_raid.c
index de2a2a2b1d75..db2f9e1653a2 100644
--- a/drivers/dma/fsl_raid.c
+++ b/drivers/dma/fsl_raid.c
@@ -134,17 +134,9 @@ static void fsl_re_issue_pending(struct dma_chan *chan)
 
 static void fsl_re_desc_done(struct fsl_re_desc *desc)
 {
-	dma_async_tx_callback callback;
-	void *callback_param;
-
 	dma_cookie_complete(&desc->async_tx);
-
-	callback = desc->async_tx.callback;
-	callback_param = desc->async_tx.callback_param;
-	if (callback)
-		callback(callback_param);
-
 	dma_descriptor_unmap(&desc->async_tx);
+	dmaengine_desc_get_callback_invoke(&desc->async_tx, NULL);
 }
 
 static void fsl_re_cleanup_descs(struct fsl_re_chan *re_chan)
@@ -670,7 +662,7 @@ static int fsl_re_chan_probe(struct platform_device *ofdev,
 
 	/* read irq property from dts */
 	chan->irq = irq_of_parse_and_map(np, 0);
-	if (chan->irq == NO_IRQ) {
+	if (!chan->irq) {
 		dev_err(dev, "No IRQ defined for JR %d\n", q);
 		ret = -ENODEV;
 		goto err_free;
diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c
index 911b7177eb50..51c75bf2b9b6 100644
--- a/drivers/dma/fsldma.c
+++ b/drivers/dma/fsldma.c
@@ -516,13 +516,9 @@ static dma_cookie_t fsldma_run_tx_complete_actions(struct fsldma_chan *chan,
 	if (txd->cookie > 0) {
 		ret = txd->cookie;
 
-		/* Run the link descriptor callback function */
-		if (txd->callback) {
-			chan_dbg(chan, "LD %p callback\n", desc);
-			txd->callback(txd->callback_param);
-		}
-
 		dma_descriptor_unmap(txd);
+		/* Run the link descriptor callback function */
+		dmaengine_desc_get_callback_invoke(txd, NULL);
 	}
 
 	/* Run any dependencies */
@@ -1153,7 +1149,7 @@ static void fsldma_free_irqs(struct fsldma_device *fdev)
 	struct fsldma_chan *chan;
 	int i;
 
-	if (fdev->irq != NO_IRQ) {
+	if (fdev->irq) {
 		dev_dbg(fdev->dev, "free per-controller IRQ\n");
 		free_irq(fdev->irq, fdev);
 		return;
@@ -1161,7 +1157,7 @@ static void fsldma_free_irqs(struct fsldma_device *fdev)
 
 	for (i = 0; i < FSL_DMA_MAX_CHANS_PER_DEVICE; i++) {
 		chan = fdev->chan[i];
-		if (chan && chan->irq != NO_IRQ) {
+		if (chan && chan->irq) {
 			chan_dbg(chan, "free per-channel IRQ\n");
 			free_irq(chan->irq, chan);
 		}
@@ -1175,7 +1171,7 @@ static int fsldma_request_irqs(struct fsldma_device *fdev)
 	int i;
 
 	/* if we have a per-controller IRQ, use that */
-	if (fdev->irq != NO_IRQ) {
+	if (fdev->irq) {
 		dev_dbg(fdev->dev, "request per-controller IRQ\n");
 		ret = request_irq(fdev->irq, fsldma_ctrl_irq, IRQF_SHARED,
 				  "fsldma-controller", fdev);
@@ -1188,7 +1184,7 @@ static int fsldma_request_irqs(struct fsldma_device *fdev)
 		if (!chan)
 			continue;
 
-		if (chan->irq == NO_IRQ) {
+		if (!chan->irq) {
 			chan_err(chan, "interrupts property missing in device tree\n");
 			ret = -ENODEV;
 			goto out_unwind;
@@ -1211,7 +1207,7 @@ out_unwind:
 		if (!chan)
 			continue;
 
-		if (chan->irq == NO_IRQ)
+		if (!chan->irq)
 			continue;
 
 		free_irq(chan->irq, chan);
@@ -1311,7 +1307,7 @@ static int fsl_dma_chan_probe(struct fsldma_device *fdev,
 	list_add_tail(&chan->common.device_node, &fdev->common.channels);
 
 	dev_info(fdev->dev, "#%d (%s), irq %d\n", chan->id, compatible,
-		 chan->irq != NO_IRQ ? chan->irq : fdev->irq);
+		 chan->irq ? chan->irq : fdev->irq);
 
 	return 0;
 
@@ -1351,7 +1347,7 @@ static int fsldma_of_probe(struct platform_device *op)
 	if (!fdev->regs) {
 		dev_err(&op->dev, "unable to ioremap registers\n");
 		err = -ENOMEM;
-		goto out_free_fdev;
+		goto out_free;
 	}
 
 	/* map the channel IRQ if it exists, but don't hookup the handler yet */
@@ -1416,6 +1412,8 @@ static int fsldma_of_probe(struct platform_device *op)
 
 out_free_fdev:
 	irq_dispose_mapping(fdev->irq);
+	iounmap(fdev->regs);
+out_free:
 	kfree(fdev);
 out_return:
 	return err;
diff --git a/drivers/dma/imx-dma.c b/drivers/dma/imx-dma.c
index a960608c0a4d..ab0fb804fb1e 100644
--- a/drivers/dma/imx-dma.c
+++ b/drivers/dma/imx-dma.c
@@ -663,9 +663,7 @@ static void imxdma_tasklet(unsigned long data)
 out:
 	spin_unlock_irqrestore(&imxdma->lock, flags);
 
-	if (desc->desc.callback)
-		desc->desc.callback(desc->desc.callback_param);
-
+	dmaengine_desc_get_callback_invoke(&desc->desc, NULL);
 }
 
 static int imxdma_terminate_all(struct dma_chan *chan)
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index 3cb47386fbb9..b9629b2bfc05 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -184,7 +184,7 @@
 struct sdma_mode_count {
 	u32 count   : 16; /* size of the buffer pointed by this BD */
 	u32 status  :  8; /* E,R,I,C,W,D status bits stored here */
-	u32 command :  8; /* command mostlky used for channel 0 */
+	u32 command :  8; /* command mostly used for channel 0 */
 };
 
 /*
@@ -479,6 +479,24 @@ static struct sdma_driver_data sdma_imx6q = {
 	.script_addrs = &sdma_script_imx6q,
 };
 
+static struct sdma_script_start_addrs sdma_script_imx7d = {
+	.ap_2_ap_addr = 644,
+	.uart_2_mcu_addr = 819,
+	.mcu_2_app_addr = 749,
+	.uartsh_2_mcu_addr = 1034,
+	.mcu_2_shp_addr = 962,
+	.app_2_mcu_addr = 685,
+	.shp_2_mcu_addr = 893,
+	.spdif_2_mcu_addr = 1102,
+	.mcu_2_spdif_addr = 1136,
+};
+
+static struct sdma_driver_data sdma_imx7d = {
+	.chnenbl0 = SDMA_CHNENBL0_IMX35,
+	.num_events = 48,
+	.script_addrs = &sdma_script_imx7d,
+};
+
 static const struct platform_device_id sdma_devtypes[] = {
 	{
 		.name = "imx25-sdma",
@@ -499,6 +517,9 @@ static const struct platform_device_id sdma_devtypes[] = {
 		.name = "imx6q-sdma",
 		.driver_data = (unsigned long)&sdma_imx6q,
 	}, {
+		.name = "imx7d-sdma",
+		.driver_data = (unsigned long)&sdma_imx7d,
+	}, {
 		/* sentinel */
 	}
 };
@@ -511,6 +532,7 @@ static const struct of_device_id sdma_dt_ids[] = {
 	{ .compatible = "fsl,imx35-sdma", .data = &sdma_imx35, },
 	{ .compatible = "fsl,imx31-sdma", .data = &sdma_imx31, },
 	{ .compatible = "fsl,imx25-sdma", .data = &sdma_imx25, },
+	{ .compatible = "fsl,imx7d-sdma", .data = &sdma_imx7d, },
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, sdma_dt_ids);
@@ -686,8 +708,7 @@ static void sdma_update_channel_loop(struct sdma_channel *sdmac)
 		 * executed.
 		 */
 
-		if (sdmac->desc.callback)
-			sdmac->desc.callback(sdmac->desc.callback_param);
+		dmaengine_desc_get_callback_invoke(&sdmac->desc, NULL);
 
 		sdmac->buf_tail++;
 		sdmac->buf_tail %= sdmac->num_bd;
@@ -722,8 +743,8 @@ static void mxc_sdma_handle_channel_normal(unsigned long data)
 		sdmac->status = DMA_COMPLETE;
 
 	dma_cookie_complete(&sdmac->desc);
-	if (sdmac->desc.callback)
-		sdmac->desc.callback(sdmac->desc.callback_param);
+
+	dmaengine_desc_get_callback_invoke(&sdmac->desc, NULL);
 }
 
 static irqreturn_t sdma_int_handler(int irq, void *dev_id)
@@ -1387,6 +1408,7 @@ static void sdma_issue_pending(struct dma_chan *chan)
 #define SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V1	34
 #define SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V2	38
 #define SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V3	41
+#define SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V4	42
 
 static void sdma_add_scripts(struct sdma_engine *sdma,
 		const struct sdma_script_start_addrs *addr)
@@ -1436,6 +1458,9 @@ static void sdma_load_firmware(const struct firmware *fw, void *context)
 	case 3:
 		sdma->script_number = SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V3;
 		break;
+	case 4:
+		sdma->script_number = SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V4;
+		break;
 	default:
 		dev_err(sdma->dev, "unknown firmware version\n");
 		goto err_firmware;
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index bd09961443b1..49386ce04bf5 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -38,8 +38,54 @@
 
 #include "../dmaengine.h"
 
+static char *chanerr_str[] = {
+	"DMA Transfer Destination Address Error",
+	"Next Descriptor Address Error",
+	"Descriptor Error",
+	"Chan Address Value Error",
+	"CHANCMD Error",
+	"Chipset Uncorrectable Data Integrity Error",
+	"DMA Uncorrectable Data Integrity Error",
+	"Read Data Error",
+	"Write Data Error",
+	"Descriptor Control Error",
+	"Descriptor Transfer Size Error",
+	"Completion Address Error",
+	"Interrupt Configuration Error",
+	"Super extended descriptor Address Error",
+	"Unaffiliated Error",
+	"CRC or XOR P Error",
+	"XOR Q Error",
+	"Descriptor Count Error",
+	"DIF All F detect Error",
+	"Guard Tag verification Error",
+	"Application Tag verification Error",
+	"Reference Tag verification Error",
+	"Bundle Bit Error",
+	"Result DIF All F detect Error",
+	"Result Guard Tag verification Error",
+	"Result Application Tag verification Error",
+	"Result Reference Tag verification Error",
+	NULL
+};
+
 static void ioat_eh(struct ioatdma_chan *ioat_chan);
 
+static void ioat_print_chanerrs(struct ioatdma_chan *ioat_chan, u32 chanerr)
+{
+	int i;
+
+	for (i = 0; i < 32; i++) {
+		if ((chanerr >> i) & 1) {
+			if (chanerr_str[i]) {
+				dev_err(to_dev(ioat_chan), "Err(%d): %s\n",
+					i, chanerr_str[i]);
+			} else
+				break;
+		}
+	}
+}
+
 /**
  * ioat_dma_do_interrupt - handler used for single vector interrupt mode
  * @irq: interrupt id
@@ -568,12 +614,14 @@ static void __cleanup(struct ioatdma_chan *ioat_chan, dma_addr_t phys_complete)
 
 		tx = &desc->txd;
 		if (tx->cookie) {
+			struct dmaengine_result res;
+
 			dma_cookie_complete(tx);
 			dma_descriptor_unmap(tx);
-			if (tx->callback) {
-				tx->callback(tx->callback_param);
-				tx->callback = NULL;
-			}
+			res.result = DMA_TRANS_NOERROR;
+			dmaengine_desc_get_callback_invoke(tx, NULL);
+			tx->callback = NULL;
+			tx->callback_result = NULL;
 		}
 
 		if (tx->phys == phys_complete)
@@ -622,7 +670,8 @@ static void ioat_cleanup(struct ioatdma_chan *ioat_chan)
 	if (is_ioat_halted(*ioat_chan->completion)) {
 		u32 chanerr = readl(ioat_chan->reg_base + IOAT_CHANERR_OFFSET);
 
-		if (chanerr & IOAT_CHANERR_HANDLE_MASK) {
+		if (chanerr &
+		    (IOAT_CHANERR_HANDLE_MASK | IOAT_CHANERR_RECOVER_MASK)) {
 			mod_timer(&ioat_chan->timer, jiffies + IDLE_TIMEOUT);
 			ioat_eh(ioat_chan);
 		}
@@ -652,6 +701,61 @@ static void ioat_restart_channel(struct ioatdma_chan *ioat_chan)
 	__ioat_restart_chan(ioat_chan);
 }
 
+
+static void ioat_abort_descs(struct ioatdma_chan *ioat_chan)
+{
+	struct ioatdma_device *ioat_dma = ioat_chan->ioat_dma;
+	struct ioat_ring_ent *desc;
+	u16 active;
+	int idx = ioat_chan->tail, i;
+
+	/*
+	 * We assume that the failed descriptor has been processed.
+	 * Now we are just returning all the remaining submitted
+	 * descriptors to abort.
+	 */
+	active = ioat_ring_active(ioat_chan);
+
+	/* we skip the failed descriptor that tail points to */
+	for (i = 1; i < active; i++) {
+		struct dma_async_tx_descriptor *tx;
+
+		smp_read_barrier_depends();
+		prefetch(ioat_get_ring_ent(ioat_chan, idx + i + 1));
+		desc = ioat_get_ring_ent(ioat_chan, idx + i);
+
+		tx = &desc->txd;
+		if (tx->cookie) {
+			struct dmaengine_result res;
+
+			dma_cookie_complete(tx);
+			dma_descriptor_unmap(tx);
+			res.result = DMA_TRANS_ABORTED;
+			dmaengine_desc_get_callback_invoke(tx, &res);
+			tx->callback = NULL;
+			tx->callback_result = NULL;
+		}
+
+		/* skip extended descriptors */
+		if (desc_has_ext(desc)) {
+			WARN_ON(i + 1 >= active);
+			i++;
+		}
+
+		/* cleanup super extended descriptors */
+		if (desc->sed) {
+			ioat_free_sed(ioat_dma, desc->sed);
+			desc->sed = NULL;
+		}
+	}
+
+	smp_mb(); /* finish all descriptor reads before incrementing tail */
+	ioat_chan->tail = idx + active;
+
+	desc = ioat_get_ring_ent(ioat_chan, ioat_chan->tail);
+	ioat_chan->last_completion = *ioat_chan->completion = desc->txd.phys;
+}
+
 static void ioat_eh(struct ioatdma_chan *ioat_chan)
 {
 	struct pci_dev *pdev = to_pdev(ioat_chan);
@@ -662,6 +766,8 @@ static void ioat_eh(struct ioatdma_chan *ioat_chan)
 	u32 err_handled = 0;
 	u32 chanerr_int;
 	u32 chanerr;
+	bool abort = false;
+	struct dmaengine_result res;
 
 	/* cleanup so tail points to descriptor that caused the error */
 	if (ioat_cleanup_preamble(ioat_chan, &phys_complete))
@@ -697,30 +803,55 @@ static void ioat_eh(struct ioatdma_chan *ioat_chan)
 		break;
 	}
 
+	if (chanerr & IOAT_CHANERR_RECOVER_MASK) {
+		if (chanerr & IOAT_CHANERR_READ_DATA_ERR) {
+			res.result = DMA_TRANS_READ_FAILED;
+			err_handled |= IOAT_CHANERR_READ_DATA_ERR;
+		} else if (chanerr & IOAT_CHANERR_WRITE_DATA_ERR) {
+			res.result = DMA_TRANS_WRITE_FAILED;
+			err_handled |= IOAT_CHANERR_WRITE_DATA_ERR;
+		}
+
+		abort = true;
+	} else
+		res.result = DMA_TRANS_NOERROR;
+
 	/* fault on unhandled error or spurious halt */
 	if (chanerr ^ err_handled || chanerr == 0) {
 		dev_err(to_dev(ioat_chan), "%s: fatal error (%x:%x)\n",
 			__func__, chanerr, err_handled);
+		dev_err(to_dev(ioat_chan), "Errors handled:\n");
+		ioat_print_chanerrs(ioat_chan, err_handled);
+		dev_err(to_dev(ioat_chan), "Errors not handled:\n");
+		ioat_print_chanerrs(ioat_chan, (chanerr & ~err_handled));
+
 		BUG();
-	} else { /* cleanup the faulty descriptor */
-		tx = &desc->txd;
-		if (tx->cookie) {
-			dma_cookie_complete(tx);
-			dma_descriptor_unmap(tx);
-			if (tx->callback) {
-				tx->callback(tx->callback_param);
-				tx->callback = NULL;
-			}
-		}
 	}
 
-	writel(chanerr, ioat_chan->reg_base + IOAT_CHANERR_OFFSET);
-	pci_write_config_dword(pdev, IOAT_PCI_CHANERR_INT_OFFSET, chanerr_int);
+	/* cleanup the faulty descriptor since we are continuing */
+	tx = &desc->txd;
+	if (tx->cookie) {
+		dma_cookie_complete(tx);
+		dma_descriptor_unmap(tx);
+		dmaengine_desc_get_callback_invoke(tx, &res);
+		tx->callback = NULL;
+		tx->callback_result = NULL;
+	}
 
 	/* mark faulting descriptor as complete */
 	*ioat_chan->completion = desc->txd.phys;
 
 	spin_lock_bh(&ioat_chan->prep_lock);
+	/* we need abort all descriptors */
+	if (abort) {
+		ioat_abort_descs(ioat_chan);
+		/* clean up the channel, we could be in weird state */
+		ioat_reset_hw(ioat_chan);
+	}
+
+	writel(chanerr, ioat_chan->reg_base + IOAT_CHANERR_OFFSET);
+	pci_write_config_dword(pdev, IOAT_PCI_CHANERR_INT_OFFSET, chanerr_int);
+
 	ioat_restart_channel(ioat_chan);
 	spin_unlock_bh(&ioat_chan->prep_lock);
 }
@@ -753,10 +884,28 @@ void ioat_timer_event(unsigned long data)
 		chanerr = readl(ioat_chan->reg_base + IOAT_CHANERR_OFFSET);
 		dev_err(to_dev(ioat_chan), "%s: Channel halted (%x)\n",
 			__func__, chanerr);
-		if (test_bit(IOAT_RUN, &ioat_chan->state))
-			BUG_ON(is_ioat_bug(chanerr));
-		else /* we never got off the ground */
-			return;
+		dev_err(to_dev(ioat_chan), "Errors:\n");
+		ioat_print_chanerrs(ioat_chan, chanerr);
+
+		if (test_bit(IOAT_RUN, &ioat_chan->state)) {
+			spin_lock_bh(&ioat_chan->cleanup_lock);
+			spin_lock_bh(&ioat_chan->prep_lock);
+			set_bit(IOAT_CHAN_DOWN, &ioat_chan->state);
+			spin_unlock_bh(&ioat_chan->prep_lock);
+
+			ioat_abort_descs(ioat_chan);
+			dev_warn(to_dev(ioat_chan), "Reset channel...\n");
+			ioat_reset_hw(ioat_chan);
+			dev_warn(to_dev(ioat_chan), "Restart channel...\n");
+			ioat_restart_channel(ioat_chan);
+
+			spin_lock_bh(&ioat_chan->prep_lock);
+			clear_bit(IOAT_CHAN_DOWN, &ioat_chan->state);
+			spin_unlock_bh(&ioat_chan->prep_lock);
+			spin_unlock_bh(&ioat_chan->cleanup_lock);
+		}
+
+		return;
 	}
 
 	spin_lock_bh(&ioat_chan->cleanup_lock);
@@ -780,14 +929,26 @@ void ioat_timer_event(unsigned long data)
 		u32 chanerr;
 
 		chanerr = readl(ioat_chan->reg_base + IOAT_CHANERR_OFFSET);
-		dev_warn(to_dev(ioat_chan), "Restarting channel...\n");
-		dev_warn(to_dev(ioat_chan), "CHANSTS: %#Lx CHANERR: %#x\n",
-			 status, chanerr);
-		dev_warn(to_dev(ioat_chan), "Active descriptors: %d\n",
-			 ioat_ring_active(ioat_chan));
+		dev_err(to_dev(ioat_chan), "CHANSTS: %#Lx CHANERR: %#x\n",
+			status, chanerr);
+		dev_err(to_dev(ioat_chan), "Errors:\n");
+		ioat_print_chanerrs(ioat_chan, chanerr);
+
+		dev_dbg(to_dev(ioat_chan), "Active descriptors: %d\n",
+			ioat_ring_active(ioat_chan));
 
 		spin_lock_bh(&ioat_chan->prep_lock);
+		set_bit(IOAT_CHAN_DOWN, &ioat_chan->state);
+		spin_unlock_bh(&ioat_chan->prep_lock);
+
+		ioat_abort_descs(ioat_chan);
+		dev_warn(to_dev(ioat_chan), "Resetting channel...\n");
+		ioat_reset_hw(ioat_chan);
+		dev_warn(to_dev(ioat_chan), "Restarting channel...\n");
 		ioat_restart_channel(ioat_chan);
+
+		spin_lock_bh(&ioat_chan->prep_lock);
+		clear_bit(IOAT_CHAN_DOWN, &ioat_chan->state);
 		spin_unlock_bh(&ioat_chan->prep_lock);
 		spin_unlock_bh(&ioat_chan->cleanup_lock);
 		return;
diff --git a/drivers/dma/ioat/init.c b/drivers/dma/ioat/init.c
index 7145f7716a92..015f7110b96d 100644
--- a/drivers/dma/ioat/init.c
+++ b/drivers/dma/ioat/init.c
@@ -828,7 +828,7 @@ static int ioat_xor_val_self_test(struct ioatdma_device *ioat_dma)
 
 	dest_dma = dma_map_page(dev, dest, 0, PAGE_SIZE, DMA_FROM_DEVICE);
 	if (dma_mapping_error(dev, dest_dma))
-		goto dma_unmap;
+		goto free_resources;
 
 	for (i = 0; i < IOAT_NUM_SRC_TEST; i++)
 		dma_srcs[i] = DMA_ERROR_CODE;
diff --git a/drivers/dma/ioat/registers.h b/drivers/dma/ioat/registers.h
index 70534981a49b..48fa4cf9f64a 100644
--- a/drivers/dma/ioat/registers.h
+++ b/drivers/dma/ioat/registers.h
@@ -240,6 +240,8 @@
 #define IOAT_CHANERR_DESCRIPTOR_COUNT_ERR	0x40000
 
 #define IOAT_CHANERR_HANDLE_MASK (IOAT_CHANERR_XOR_P_OR_CRC_ERR | IOAT_CHANERR_XOR_Q_ERR)
+#define IOAT_CHANERR_RECOVER_MASK (IOAT_CHANERR_READ_DATA_ERR | \
+				   IOAT_CHANERR_WRITE_DATA_ERR)
 
 #define IOAT_CHANERR_MASK_OFFSET		0x2C	/* 32-bit Channel Error Register */
 
diff --git a/drivers/dma/iop-adma.c b/drivers/dma/iop-adma.c
index f039cfadf17b..a410657f7bcd 100644
--- a/drivers/dma/iop-adma.c
+++ b/drivers/dma/iop-adma.c
@@ -71,8 +71,7 @@ iop_adma_run_tx_complete_actions(struct iop_adma_desc_slot *desc,
 		/* call the callback (must not sleep or submit new
 		 * operations to this channel)
 		 */
-		if (tx->callback)
-			tx->callback(tx->callback_param);
+		dmaengine_desc_get_callback_invoke(tx, NULL);
 
 		dma_descriptor_unmap(tx);
 		if (desc->group_head)
diff --git a/drivers/dma/ipu/ipu_idmac.c b/drivers/dma/ipu/ipu_idmac.c
index b54f62de9232..ed76044ce4b9 100644
--- a/drivers/dma/ipu/ipu_idmac.c
+++ b/drivers/dma/ipu/ipu_idmac.c
@@ -1160,11 +1160,10 @@ static irqreturn_t idmac_interrupt(int irq, void *dev_id)
 	struct scatterlist **sg, *sgnext, *sgnew = NULL;
 	/* Next transfer descriptor */
 	struct idmac_tx_desc *desc, *descnew;
-	dma_async_tx_callback callback;
-	void *callback_param;
 	bool done = false;
 	u32 ready0, ready1, curbuf, err;
 	unsigned long flags;
+	struct dmaengine_desc_callback cb;
 
 	/* IDMAC has cleared the respective BUFx_RDY bit, we manage the buffer */
 
@@ -1278,12 +1277,12 @@ static irqreturn_t idmac_interrupt(int irq, void *dev_id)
 
 	if (likely(sgnew) &&
 	    ipu_submit_buffer(ichan, descnew, sgnew, ichan->active_buffer) < 0) {
-		callback = descnew->txd.callback;
-		callback_param = descnew->txd.callback_param;
+		dmaengine_desc_get_callback(&descnew->txd, &cb);
+
 		list_del_init(&descnew->list);
 		spin_unlock(&ichan->lock);
-		if (callback)
-			callback(callback_param);
+
+		dmaengine_desc_callback_invoke(&cb, NULL);
 		spin_lock(&ichan->lock);
 	}
 
@@ -1292,13 +1291,12 @@ static irqreturn_t idmac_interrupt(int irq, void *dev_id)
 	if (done)
 		dma_cookie_complete(&desc->txd);
 
-	callback = desc->txd.callback;
-	callback_param = desc->txd.callback_param;
+	dmaengine_desc_get_callback(&desc->txd, &cb);
 
 	spin_unlock(&ichan->lock);
 
-	if (done && (desc->txd.flags & DMA_PREP_INTERRUPT) && callback)
-		callback(callback_param);
+	if (done && (desc->txd.flags & DMA_PREP_INTERRUPT))
+		dmaengine_desc_callback_invoke(&cb, NULL);
 
 	return IRQ_HANDLED;
 }
diff --git a/drivers/dma/ipu/ipu_irq.c b/drivers/dma/ipu/ipu_irq.c
index 2bf37e68ad0f..dd184b50e5b4 100644
--- a/drivers/dma/ipu/ipu_irq.c
+++ b/drivers/dma/ipu/ipu_irq.c
@@ -286,22 +286,21 @@ static void ipu_irq_handler(struct irq_desc *desc)
 		raw_spin_unlock(&bank_lock);
 		while ((line = ffs(status))) {
 			struct ipu_irq_map *map;
-			unsigned int irq = NO_IRQ;
+			unsigned int irq;
 
 			line--;
 			status &= ~(1UL << line);
 
 			raw_spin_lock(&bank_lock);
 			map = src2map(32 * i + line);
-			if (map)
-				irq = map->irq;
-			raw_spin_unlock(&bank_lock);
-
 			if (!map) {
+				raw_spin_unlock(&bank_lock);
 				pr_err("IPU: Interrupt on unmapped source %u bank %d\n",
 				       line, i);
 				continue;
 			}
+			irq = map->irq;
+			raw_spin_unlock(&bank_lock);
 			generic_handle_irq(irq);
 		}
 	}
diff --git a/drivers/dma/k3dma.c b/drivers/dma/k3dma.c
index 39de8980128c..aabcb7934b05 100644
--- a/drivers/dma/k3dma.c
+++ b/drivers/dma/k3dma.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2013 Linaro Ltd.
+ * Copyright (c) 2013 - 2015 Linaro Ltd.
  * Copyright (c) 2013 Hisilicon Limited.
  *
  * This program is free software; you can redistribute it and/or modify
@@ -8,6 +8,8 @@
  */
 #include <linux/sched.h>
 #include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
 #include <linux/dmaengine.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
@@ -25,22 +27,28 @@
 
 #define DRIVER_NAME		"k3-dma"
 #define DMA_MAX_SIZE		0x1ffc
+#define DMA_CYCLIC_MAX_PERIOD	0x1000
+#define LLI_BLOCK_SIZE		(4 * PAGE_SIZE)
 
 #define INT_STAT		0x00
 #define INT_TC1			0x04
+#define INT_TC2			0x08
 #define INT_ERR1		0x0c
 #define INT_ERR2		0x10
 #define INT_TC1_MASK		0x18
+#define INT_TC2_MASK		0x1c
 #define INT_ERR1_MASK		0x20
 #define INT_ERR2_MASK		0x24
 #define INT_TC1_RAW		0x600
-#define INT_ERR1_RAW		0x608
-#define INT_ERR2_RAW		0x610
+#define INT_TC2_RAW		0x608
+#define INT_ERR1_RAW		0x610
+#define INT_ERR2_RAW		0x618
 #define CH_PRI			0x688
 #define CH_STAT			0x690
 #define CX_CUR_CNT		0x704
 #define CX_LLI			0x800
-#define CX_CNT			0x810
+#define CX_CNT1			0x80c
+#define CX_CNT0			0x810
 #define CX_SRC			0x814
 #define CX_DST			0x818
 #define CX_CFG			0x81c
@@ -49,6 +57,7 @@
 
 #define CX_LLI_CHAIN_EN		0x2
 #define CX_CFG_EN		0x1
+#define CX_CFG_NODEIRQ		BIT(1)
 #define CX_CFG_MEM2PER		(0x1 << 2)
 #define CX_CFG_PER2MEM		(0x2 << 2)
 #define CX_CFG_SRCINCR		(0x1 << 31)
@@ -68,7 +77,7 @@ struct k3_dma_desc_sw {
 	dma_addr_t		desc_hw_lli;
 	size_t			desc_num;
 	size_t			size;
-	struct k3_desc_hw	desc_hw[0];
+	struct k3_desc_hw	*desc_hw;
 };
 
 struct k3_dma_phy;
@@ -81,6 +90,7 @@ struct k3_dma_chan {
 	enum dma_transfer_direction dir;
 	dma_addr_t		dev_addr;
 	enum dma_status		status;
+	bool			cyclic;
 };
 
 struct k3_dma_phy {
@@ -100,6 +110,7 @@ struct k3_dma_dev {
 	struct k3_dma_phy	*phy;
 	struct k3_dma_chan	*chans;
 	struct clk		*clk;
+	struct dma_pool		*pool;
 	u32			dma_channels;
 	u32			dma_requests;
 	unsigned int		irq;
@@ -135,6 +146,7 @@ static void k3_dma_terminate_chan(struct k3_dma_phy *phy, struct k3_dma_dev *d)
 
 	val = 0x1 << phy->idx;
 	writel_relaxed(val, d->base + INT_TC1_RAW);
+	writel_relaxed(val, d->base + INT_TC2_RAW);
 	writel_relaxed(val, d->base + INT_ERR1_RAW);
 	writel_relaxed(val, d->base + INT_ERR2_RAW);
 }
@@ -142,7 +154,7 @@ static void k3_dma_terminate_chan(struct k3_dma_phy *phy, struct k3_dma_dev *d)
 static void k3_dma_set_desc(struct k3_dma_phy *phy, struct k3_desc_hw *hw)
 {
 	writel_relaxed(hw->lli, phy->base + CX_LLI);
-	writel_relaxed(hw->count, phy->base + CX_CNT);
+	writel_relaxed(hw->count, phy->base + CX_CNT0);
 	writel_relaxed(hw->saddr, phy->base + CX_SRC);
 	writel_relaxed(hw->daddr, phy->base + CX_DST);
 	writel_relaxed(AXI_CFG_DEFAULT, phy->base + AXI_CFG);
@@ -176,11 +188,13 @@ static void k3_dma_enable_dma(struct k3_dma_dev *d, bool on)
 
 		/* unmask irq */
 		writel_relaxed(0xffff, d->base + INT_TC1_MASK);
+		writel_relaxed(0xffff, d->base + INT_TC2_MASK);
 		writel_relaxed(0xffff, d->base + INT_ERR1_MASK);
 		writel_relaxed(0xffff, d->base + INT_ERR2_MASK);
 	} else {
 		/* mask irq */
 		writel_relaxed(0x0, d->base + INT_TC1_MASK);
+		writel_relaxed(0x0, d->base + INT_TC2_MASK);
 		writel_relaxed(0x0, d->base + INT_ERR1_MASK);
 		writel_relaxed(0x0, d->base + INT_ERR2_MASK);
 	}
@@ -193,22 +207,31 @@ static irqreturn_t k3_dma_int_handler(int irq, void *dev_id)
 	struct k3_dma_chan *c;
 	u32 stat = readl_relaxed(d->base + INT_STAT);
 	u32 tc1  = readl_relaxed(d->base + INT_TC1);
+	u32 tc2  = readl_relaxed(d->base + INT_TC2);
 	u32 err1 = readl_relaxed(d->base + INT_ERR1);
 	u32 err2 = readl_relaxed(d->base + INT_ERR2);
 	u32 i, irq_chan = 0;
 
 	while (stat) {
 		i = __ffs(stat);
-		stat &= (stat - 1);
-		if (likely(tc1 & BIT(i))) {
+		stat &= ~BIT(i);
+		if (likely(tc1 & BIT(i)) || (tc2 & BIT(i))) {
+			unsigned long flags;
+
 			p = &d->phy[i];
 			c = p->vchan;
-			if (c) {
-				unsigned long flags;
-
+			if (c && (tc1 & BIT(i))) {
 				spin_lock_irqsave(&c->vc.lock, flags);
 				vchan_cookie_complete(&p->ds_run->vd);
+				WARN_ON_ONCE(p->ds_done);
 				p->ds_done = p->ds_run;
+				p->ds_run = NULL;
+				spin_unlock_irqrestore(&c->vc.lock, flags);
+			}
+			if (c && (tc2 & BIT(i))) {
+				spin_lock_irqsave(&c->vc.lock, flags);
+				if (p->ds_run != NULL)
+					vchan_cyclic_callback(&p->ds_run->vd);
 				spin_unlock_irqrestore(&c->vc.lock, flags);
 			}
 			irq_chan |= BIT(i);
@@ -218,14 +241,17 @@ static irqreturn_t k3_dma_int_handler(int irq, void *dev_id)
 	}
 
 	writel_relaxed(irq_chan, d->base + INT_TC1_RAW);
+	writel_relaxed(irq_chan, d->base + INT_TC2_RAW);
 	writel_relaxed(err1, d->base + INT_ERR1_RAW);
 	writel_relaxed(err2, d->base + INT_ERR2_RAW);
 
-	if (irq_chan) {
+	if (irq_chan)
 		tasklet_schedule(&d->task);
+
+	if (irq_chan || err1 || err2)
 		return IRQ_HANDLED;
-	} else
-		return IRQ_NONE;
+
+	return IRQ_NONE;
 }
 
 static int k3_dma_start_txd(struct k3_dma_chan *c)
@@ -247,14 +273,14 @@ static int k3_dma_start_txd(struct k3_dma_chan *c)
 		 * so vc->desc_issued only contains desc pending
 		 */
 		list_del(&ds->vd.node);
+
+		WARN_ON_ONCE(c->phy->ds_run);
+		WARN_ON_ONCE(c->phy->ds_done);
 		c->phy->ds_run = ds;
-		c->phy->ds_done = NULL;
 		/* start dma */
 		k3_dma_set_desc(c->phy, &ds->desc_hw[0]);
 		return 0;
 	}
-	c->phy->ds_done = NULL;
-	c->phy->ds_run = NULL;
 	return -EAGAIN;
 }
 
@@ -351,7 +377,7 @@ static enum dma_status k3_dma_tx_status(struct dma_chan *chan,
 	 * its total size.
 	 */
 	vd = vchan_find_desc(&c->vc, cookie);
-	if (vd) {
+	if (vd && !c->cyclic) {
 		bytes = container_of(vd, struct k3_dma_desc_sw, vd)->size;
 	} else if ((!p) || (!p->ds_run)) {
 		bytes = 0;
@@ -361,7 +387,8 @@ static enum dma_status k3_dma_tx_status(struct dma_chan *chan,
 
 		bytes = k3_dma_get_curr_cnt(d, p);
 		clli = k3_dma_get_curr_lli(p);
-		index = (clli - ds->desc_hw_lli) / sizeof(struct k3_desc_hw);
+		index = ((clli - ds->desc_hw_lli) /
+				sizeof(struct k3_desc_hw)) + 1;
 		for (; index < ds->desc_num; index++) {
 			bytes += ds->desc_hw[index].count;
 			/* end of lli */
@@ -402,9 +429,10 @@ static void k3_dma_issue_pending(struct dma_chan *chan)
 static void k3_dma_fill_desc(struct k3_dma_desc_sw *ds, dma_addr_t dst,
 			dma_addr_t src, size_t len, u32 num, u32 ccfg)
 {
-	if ((num + 1) < ds->desc_num)
+	if (num != ds->desc_num - 1)
 		ds->desc_hw[num].lli = ds->desc_hw_lli + (num + 1) *
 			sizeof(struct k3_desc_hw);
+
 	ds->desc_hw[num].lli |= CX_LLI_CHAIN_EN;
 	ds->desc_hw[num].count = len;
 	ds->desc_hw[num].saddr = src;
@@ -412,6 +440,35 @@ static void k3_dma_fill_desc(struct k3_dma_desc_sw *ds, dma_addr_t dst,
 	ds->desc_hw[num].config = ccfg;
 }
 
+static struct k3_dma_desc_sw *k3_dma_alloc_desc_resource(int num,
+							struct dma_chan *chan)
+{
+	struct k3_dma_chan *c = to_k3_chan(chan);
+	struct k3_dma_desc_sw *ds;
+	struct k3_dma_dev *d = to_k3_dma(chan->device);
+	int lli_limit = LLI_BLOCK_SIZE / sizeof(struct k3_desc_hw);
+
+	if (num > lli_limit) {
+		dev_dbg(chan->device->dev, "vch %p: sg num %d exceed max %d\n",
+			&c->vc, num, lli_limit);
+		return NULL;
+	}
+
+	ds = kzalloc(sizeof(*ds), GFP_NOWAIT);
+	if (!ds)
+		return NULL;
+
+	ds->desc_hw = dma_pool_alloc(d->pool, GFP_NOWAIT, &ds->desc_hw_lli);
+	if (!ds->desc_hw) {
+		dev_dbg(chan->device->dev, "vch %p: dma alloc fail\n", &c->vc);
+		kfree(ds);
+		return NULL;
+	}
+	memset(ds->desc_hw, 0, sizeof(struct k3_desc_hw) * num);
+	ds->desc_num = num;
+	return ds;
+}
+
 static struct dma_async_tx_descriptor *k3_dma_prep_memcpy(
 	struct dma_chan *chan,	dma_addr_t dst, dma_addr_t src,
 	size_t len, unsigned long flags)
@@ -425,13 +482,13 @@ static struct dma_async_tx_descriptor *k3_dma_prep_memcpy(
 		return NULL;
 
 	num = DIV_ROUND_UP(len, DMA_MAX_SIZE);
-	ds = kzalloc(sizeof(*ds) + num * sizeof(ds->desc_hw[0]), GFP_ATOMIC);
+
+	ds = k3_dma_alloc_desc_resource(num, chan);
 	if (!ds)
 		return NULL;
 
-	ds->desc_hw_lli = __virt_to_phys((unsigned long)&ds->desc_hw[0]);
+	c->cyclic = 0;
 	ds->size = len;
-	ds->desc_num = num;
 	num = 0;
 
 	if (!c->ccfg) {
@@ -474,18 +531,17 @@ static struct dma_async_tx_descriptor *k3_dma_prep_slave_sg(
 	if (sgl == NULL)
 		return NULL;
 
+	c->cyclic = 0;
+
 	for_each_sg(sgl, sg, sglen, i) {
 		avail = sg_dma_len(sg);
 		if (avail > DMA_MAX_SIZE)
 			num += DIV_ROUND_UP(avail, DMA_MAX_SIZE) - 1;
 	}
 
-	ds = kzalloc(sizeof(*ds) + num * sizeof(ds->desc_hw[0]), GFP_ATOMIC);
+	ds = k3_dma_alloc_desc_resource(num, chan);
 	if (!ds)
 		return NULL;
-
-	ds->desc_hw_lli = __virt_to_phys((unsigned long)&ds->desc_hw[0]);
-	ds->desc_num = num;
 	num = 0;
 
 	for_each_sg(sgl, sg, sglen, i) {
@@ -516,6 +572,73 @@ static struct dma_async_tx_descriptor *k3_dma_prep_slave_sg(
 	return vchan_tx_prep(&c->vc, &ds->vd, flags);
 }
 
+static struct dma_async_tx_descriptor *
+k3_dma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr,
+		       size_t buf_len, size_t period_len,
+		       enum dma_transfer_direction dir,
+		       unsigned long flags)
+{
+	struct k3_dma_chan *c = to_k3_chan(chan);
+	struct k3_dma_desc_sw *ds;
+	size_t len, avail, total = 0;
+	dma_addr_t addr, src = 0, dst = 0;
+	int num = 1, since = 0;
+	size_t modulo = DMA_CYCLIC_MAX_PERIOD;
+	u32 en_tc2 = 0;
+
+	dev_dbg(chan->device->dev, "%s: buf %pad, dst %pad, buf len %zu, period_len = %zu, dir %d\n",
+	       __func__, &buf_addr, &to_k3_chan(chan)->dev_addr,
+	       buf_len, period_len, (int)dir);
+
+	avail = buf_len;
+	if (avail > modulo)
+		num += DIV_ROUND_UP(avail, modulo) - 1;
+
+	ds = k3_dma_alloc_desc_resource(num, chan);
+	if (!ds)
+		return NULL;
+
+	c->cyclic = 1;
+	addr = buf_addr;
+	avail = buf_len;
+	total = avail;
+	num = 0;
+
+	if (period_len < modulo)
+		modulo = period_len;
+
+	do {
+		len = min_t(size_t, avail, modulo);
+
+		if (dir == DMA_MEM_TO_DEV) {
+			src = addr;
+			dst = c->dev_addr;
+		} else if (dir == DMA_DEV_TO_MEM) {
+			src = c->dev_addr;
+			dst = addr;
+		}
+		since += len;
+		if (since >= period_len) {
+			/* descriptor asks for TC2 interrupt on completion */
+			en_tc2 = CX_CFG_NODEIRQ;
+			since -= period_len;
+		} else
+			en_tc2 = 0;
+
+		k3_dma_fill_desc(ds, dst, src, len, num++, c->ccfg | en_tc2);
+
+		addr += len;
+		avail -= len;
+	} while (avail);
+
+	/* "Cyclic" == end of link points back to start of link */
+	ds->desc_hw[num - 1].lli |= ds->desc_hw_lli;
+
+	ds->size = total;
+
+	return vchan_tx_prep(&c->vc, &ds->vd, flags);
+}
+
 static int k3_dma_config(struct dma_chan *chan,
 			 struct dma_slave_config *cfg)
 {
@@ -551,7 +674,7 @@ static int k3_dma_config(struct dma_chan *chan,
 	c->ccfg |= (val << 12) | (val << 16);
 
 	if ((maxburst == 0) || (maxburst > 16))
-		val = 16;
+		val = 15;
 	else
 		val = maxburst - 1;
 	c->ccfg |= (val << 20) | (val << 24);
@@ -563,6 +686,16 @@ static int k3_dma_config(struct dma_chan *chan,
 	return 0;
 }
 
+static void k3_dma_free_desc(struct virt_dma_desc *vd)
+{
+	struct k3_dma_desc_sw *ds =
+		container_of(vd, struct k3_dma_desc_sw, vd);
+	struct k3_dma_dev *d = to_k3_dma(vd->tx.chan->device);
+
+	dma_pool_free(d->pool, ds->desc_hw, ds->desc_hw_lli);
+	kfree(ds);
+}
+
 static int k3_dma_terminate_all(struct dma_chan *chan)
 {
 	struct k3_dma_chan *c = to_k3_chan(chan);
@@ -586,7 +719,15 @@ static int k3_dma_terminate_all(struct dma_chan *chan)
 		k3_dma_terminate_chan(p, d);
 		c->phy = NULL;
 		p->vchan = NULL;
-		p->ds_run = p->ds_done = NULL;
+		if (p->ds_run) {
+			k3_dma_free_desc(&p->ds_run->vd);
+			p->ds_run = NULL;
+		}
+		if (p->ds_done) {
+			k3_dma_free_desc(&p->ds_done->vd);
+			p->ds_done = NULL;
+		}
+
 	}
 	spin_unlock_irqrestore(&c->vc.lock, flags);
 	vchan_dma_desc_free_list(&c->vc, &head);
@@ -639,14 +780,6 @@ static int k3_dma_transfer_resume(struct dma_chan *chan)
 	return 0;
 }
 
-static void k3_dma_free_desc(struct virt_dma_desc *vd)
-{
-	struct k3_dma_desc_sw *ds =
-		container_of(vd, struct k3_dma_desc_sw, vd);
-
-	kfree(ds);
-}
-
 static const struct of_device_id k3_pdma_dt_ids[] = {
 	{ .compatible = "hisilicon,k3-dma-1.0", },
 	{}
@@ -706,6 +839,12 @@ static int k3_dma_probe(struct platform_device *op)
 
 	d->irq = irq;
 
+	/* A DMA memory pool for LLIs, align on 32-byte boundary */
+	d->pool = dmam_pool_create(DRIVER_NAME, &op->dev,
+					LLI_BLOCK_SIZE, 32, 0);
+	if (!d->pool)
+		return -ENOMEM;
+
 	/* init phy channel */
 	d->phy = devm_kzalloc(&op->dev,
 		d->dma_channels * sizeof(struct k3_dma_phy), GFP_KERNEL);
@@ -722,11 +861,13 @@ static int k3_dma_probe(struct platform_device *op)
 	INIT_LIST_HEAD(&d->slave.channels);
 	dma_cap_set(DMA_SLAVE, d->slave.cap_mask);
 	dma_cap_set(DMA_MEMCPY, d->slave.cap_mask);
+	dma_cap_set(DMA_CYCLIC, d->slave.cap_mask);
 	d->slave.dev = &op->dev;
 	d->slave.device_free_chan_resources = k3_dma_free_chan_resources;
 	d->slave.device_tx_status = k3_dma_tx_status;
 	d->slave.device_prep_dma_memcpy = k3_dma_prep_memcpy;
 	d->slave.device_prep_slave_sg = k3_dma_prep_slave_sg;
+	d->slave.device_prep_dma_cyclic = k3_dma_prep_dma_cyclic;
 	d->slave.device_issue_pending = k3_dma_issue_pending;
 	d->slave.device_config = k3_dma_config;
 	d->slave.device_pause = k3_dma_transfer_pause;
diff --git a/drivers/dma/mic_x100_dma.c b/drivers/dma/mic_x100_dma.c
index 1502b24b7c7d..818255844a3c 100644
--- a/drivers/dma/mic_x100_dma.c
+++ b/drivers/dma/mic_x100_dma.c
@@ -104,10 +104,8 @@ static void mic_dma_cleanup(struct mic_dma_chan *ch)
 		tx = &ch->tx_array[last_tail];
 		if (tx->cookie) {
 			dma_cookie_complete(tx);
-			if (tx->callback) {
-				tx->callback(tx->callback_param);
-				tx->callback = NULL;
-			}
+			dmaengine_desc_get_callback_invoke(tx, NULL);
+			tx->callback = NULL;
 		}
 		last_tail = mic_dma_hw_ring_inc(last_tail);
 	}
diff --git a/drivers/dma/mmp_pdma.c b/drivers/dma/mmp_pdma.c
index f4b25fb0d040..eb3a1f42ab06 100644
--- a/drivers/dma/mmp_pdma.c
+++ b/drivers/dma/mmp_pdma.c
@@ -864,19 +864,15 @@ static void dma_do_tasklet(unsigned long data)
 	struct mmp_pdma_desc_sw *desc, *_desc;
 	LIST_HEAD(chain_cleanup);
 	unsigned long flags;
+	struct dmaengine_desc_callback cb;
 
 	if (chan->cyclic_first) {
-		dma_async_tx_callback cb = NULL;
-		void *cb_data = NULL;
-
 		spin_lock_irqsave(&chan->desc_lock, flags);
 		desc = chan->cyclic_first;
-		cb = desc->async_tx.callback;
-		cb_data = desc->async_tx.callback_param;
+		dmaengine_desc_get_callback(&desc->async_tx, &cb);
 		spin_unlock_irqrestore(&chan->desc_lock, flags);
 
-		if (cb)
-			cb(cb_data);
+		dmaengine_desc_callback_invoke(&cb, NULL);
 
 		return;
 	}
@@ -921,8 +917,8 @@ static void dma_do_tasklet(unsigned long data)
 		/* Remove from the list of transactions */
 		list_del(&desc->node);
 		/* Run the link descriptor callback function */
-		if (txd->callback)
-			txd->callback(txd->callback_param);
+		dmaengine_desc_get_callback(txd, &cb);
+		dmaengine_desc_callback_invoke(&cb, NULL);
 
 		dma_pool_free(chan->desc_pool, desc, txd->phys);
 	}
diff --git a/drivers/dma/mmp_tdma.c b/drivers/dma/mmp_tdma.c
index b3441f57a364..13c68b6434ce 100644
--- a/drivers/dma/mmp_tdma.c
+++ b/drivers/dma/mmp_tdma.c
@@ -349,9 +349,7 @@ static void dma_do_tasklet(unsigned long data)
 {
 	struct mmp_tdma_chan *tdmac = (struct mmp_tdma_chan *)data;
 
-	if (tdmac->desc.callback)
-		tdmac->desc.callback(tdmac->desc.callback_param);
-
+	dmaengine_desc_get_callback_invoke(&tdmac->desc, NULL);
 }
 
 static void mmp_tdma_free_descriptor(struct mmp_tdma_chan *tdmac)
@@ -433,7 +431,7 @@ static struct dma_async_tx_descriptor *mmp_tdma_prep_dma_cyclic(
 
 	if (period_len > TDMA_MAX_XFER_BYTES) {
 		dev_err(tdmac->dev,
-				"maximum period size exceeded: %d > %d\n",
+				"maximum period size exceeded: %zu > %d\n",
 				period_len, TDMA_MAX_XFER_BYTES);
 		goto err_out;
 	}
diff --git a/drivers/dma/moxart-dma.c b/drivers/dma/moxart-dma.c
index a6e642792e5a..e1a5c2242f6f 100644
--- a/drivers/dma/moxart-dma.c
+++ b/drivers/dma/moxart-dma.c
@@ -579,7 +579,7 @@ static int moxart_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	irq = irq_of_parse_and_map(node, 0);
-	if (irq == NO_IRQ) {
+	if (!irq) {
 		dev_err(dev, "no IRQ resource\n");
 		return -EINVAL;
 	}
diff --git a/drivers/dma/mpc512x_dma.c b/drivers/dma/mpc512x_dma.c
index fa86592c7ae1..dde713461a95 100644
--- a/drivers/dma/mpc512x_dma.c
+++ b/drivers/dma/mpc512x_dma.c
@@ -411,8 +411,7 @@ static void mpc_dma_process_completed(struct mpc_dma *mdma)
 		list_for_each_entry(mdesc, &list, node) {
 			desc = &mdesc->desc;
 
-			if (desc->callback)
-				desc->callback(desc->callback_param);
+			dmaengine_desc_get_callback_invoke(desc, NULL);
 
 			last_cookie = desc->cookie;
 			dma_run_dependencies(desc);
@@ -926,7 +925,7 @@ static int mpc_dma_probe(struct platform_device *op)
 	}
 
 	mdma->irq = irq_of_parse_and_map(dn, 0);
-	if (mdma->irq == NO_IRQ) {
+	if (!mdma->irq) {
 		dev_err(dev, "Error mapping IRQ!\n");
 		retval = -EINVAL;
 		goto err;
@@ -935,7 +934,7 @@ static int mpc_dma_probe(struct platform_device *op)
 	if (of_device_is_compatible(dn, "fsl,mpc8308-dma")) {
 		mdma->is_mpc8308 = 1;
 		mdma->irq2 = irq_of_parse_and_map(dn, 1);
-		if (mdma->irq2 == NO_IRQ) {
+		if (!mdma->irq2) {
 			dev_err(dev, "Error mapping IRQ!\n");
 			retval = -EINVAL;
 			goto err_dispose1;
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index f4c9f98ec35e..23f75285a4d9 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -206,14 +206,11 @@ mv_desc_run_tx_complete_actions(struct mv_xor_desc_slot *desc,
 	if (desc->async_tx.cookie > 0) {
 		cookie = desc->async_tx.cookie;
 
+		dma_descriptor_unmap(&desc->async_tx);
 		/* call the callback (must not sleep or submit new
 		 * operations to this channel)
 		 */
-		if (desc->async_tx.callback)
-			desc->async_tx.callback(
-				desc->async_tx.callback_param);
-
-		dma_descriptor_unmap(&desc->async_tx);
+		dmaengine_desc_get_callback_invoke(&desc->async_tx, NULL);
 	}
 
 	/* run dependent operations */
@@ -470,12 +467,90 @@ static int mv_xor_alloc_chan_resources(struct dma_chan *chan)
 	return mv_chan->slots_allocated ? : -ENOMEM;
 }
 
+/*
+ * Check if source or destination is an PCIe/IO address (non-SDRAM) and add
+ * a new MBus window if necessary. Use a cache for these check so that
+ * the MMIO mapped registers don't have to be accessed for this check
+ * to speed up this process.
+ */
+static int mv_xor_add_io_win(struct mv_xor_chan *mv_chan, u32 addr)
+{
+	struct mv_xor_device *xordev = mv_chan->xordev;
+	void __iomem *base = mv_chan->mmr_high_base;
+	u32 win_enable;
+	u32 size;
+	u8 target, attr;
+	int ret;
+	int i;
+
+	/* Nothing needs to get done for the Armada 3700 */
+	if (xordev->xor_type == XOR_ARMADA_37XX)
+		return 0;
+
+	/*
+	 * Loop over the cached windows to check, if the requested area
+	 * is already mapped. If this the case, nothing needs to be done
+	 * and we can return.
+	 */
+	for (i = 0; i < WINDOW_COUNT; i++) {
+		if (addr >= xordev->win_start[i] &&
+		    addr <= xordev->win_end[i]) {
+			/* Window is already mapped */
+			return 0;
+		}
+	}
+
+	/*
+	 * The window is not mapped, so we need to create the new mapping
+	 */
+
+	/* If no IO window is found that addr has to be located in SDRAM */
+	ret = mvebu_mbus_get_io_win_info(addr, &size, &target, &attr);
+	if (ret < 0)
+		return 0;
+
+	/*
+	 * Mask the base addr 'addr' according to 'size' read back from the
+	 * MBus window. Otherwise we might end up with an address located
+	 * somewhere in the middle of this area here.
+	 */
+	size -= 1;
+	addr &= ~size;
+
+	/*
+	 * Reading one of both enabled register is enough, as they are always
+	 * programmed to the identical values
+	 */
+	win_enable = readl(base + WINDOW_BAR_ENABLE(0));
+
+	/* Set 'i' to the first free window to write the new values to */
+	i = ffs(~win_enable) - 1;
+	if (i >= WINDOW_COUNT)
+		return -ENOMEM;
+
+	writel((addr & 0xffff0000) | (attr << 8) | target,
+	       base + WINDOW_BASE(i));
+	writel(size & 0xffff0000, base + WINDOW_SIZE(i));
+
+	/* Fill the caching variables for later use */
+	xordev->win_start[i] = addr;
+	xordev->win_end[i] = addr + size;
+
+	win_enable |= (1 << i);
+	win_enable |= 3 << (16 + (2 * i));
+	writel(win_enable, base + WINDOW_BAR_ENABLE(0));
+	writel(win_enable, base + WINDOW_BAR_ENABLE(1));
+
+	return 0;
+}
+
 static struct dma_async_tx_descriptor *
 mv_xor_prep_dma_xor(struct dma_chan *chan, dma_addr_t dest, dma_addr_t *src,
 		    unsigned int src_cnt, size_t len, unsigned long flags)
 {
 	struct mv_xor_chan *mv_chan = to_mv_xor_chan(chan);
 	struct mv_xor_desc_slot *sw_desc;
+	int ret;
 
 	if (unlikely(len < MV_XOR_MIN_BYTE_COUNT))
 		return NULL;
@@ -486,6 +561,11 @@ mv_xor_prep_dma_xor(struct dma_chan *chan, dma_addr_t dest, dma_addr_t *src,
 		"%s src_cnt: %d len: %zu dest %pad flags: %ld\n",
 		__func__, src_cnt, len, &dest, flags);
 
+	/* Check if a new window needs to get added for 'dest' */
+	ret = mv_xor_add_io_win(mv_chan, dest);
+	if (ret)
+		return NULL;
+
 	sw_desc = mv_chan_alloc_slot(mv_chan);
 	if (sw_desc) {
 		sw_desc->type = DMA_XOR;
@@ -493,8 +573,13 @@ mv_xor_prep_dma_xor(struct dma_chan *chan, dma_addr_t dest, dma_addr_t *src,
 		mv_desc_init(sw_desc, dest, len, flags);
 		if (mv_chan->op_in_desc == XOR_MODE_IN_DESC)
 			mv_desc_set_mode(sw_desc);
-		while (src_cnt--)
+		while (src_cnt--) {
+			/* Check if a new window needs to get added for 'src' */
+			ret = mv_xor_add_io_win(mv_chan, src[src_cnt]);
+			if (ret)
+				return NULL;
 			mv_desc_set_src_addr(sw_desc, src_cnt, src[src_cnt]);
+		}
 	}
 
 	dev_dbg(mv_chan_to_devp(mv_chan),
@@ -959,6 +1044,7 @@ mv_xor_channel_add(struct mv_xor_device *xordev,
 		mv_chan->op_in_desc = XOR_MODE_IN_DESC;
 
 	dma_dev = &mv_chan->dmadev;
+	mv_chan->xordev = xordev;
 
 	/*
 	 * These source and destination dummy buffers are used to implement
@@ -1086,6 +1172,10 @@ mv_xor_conf_mbus_windows(struct mv_xor_device *xordev,
 		       dram->mbus_dram_target_id, base + WINDOW_BASE(i));
 		writel((cs->size - 1) & 0xffff0000, base + WINDOW_SIZE(i));
 
+		/* Fill the caching variables for later use */
+		xordev->win_start[i] = cs->base;
+		xordev->win_end[i] = cs->base + cs->size - 1;
+
 		win_enable |= (1 << i);
 		win_enable |= 3 << (16 + (2 * i));
 	}
diff --git a/drivers/dma/mv_xor.h b/drivers/dma/mv_xor.h
index bf56e082e7cd..88eeab222a23 100644
--- a/drivers/dma/mv_xor.h
+++ b/drivers/dma/mv_xor.h
@@ -80,12 +80,17 @@
 #define WINDOW_BAR_ENABLE(chan)	(0x40 + ((chan) << 2))
 #define WINDOW_OVERRIDE_CTRL(chan)	(0xA0 + ((chan) << 2))
 
+#define WINDOW_COUNT		8
+
 struct mv_xor_device {
 	void __iomem	     *xor_base;
 	void __iomem	     *xor_high_base;
 	struct clk	     *clk;
 	struct mv_xor_chan   *channels[MV_XOR_MAX_CHANNELS];
 	int		     xor_type;
+
+	u32                  win_start[WINDOW_COUNT];
+	u32                  win_end[WINDOW_COUNT];
 };
 
 /**
@@ -127,6 +132,8 @@ struct mv_xor_chan {
 	char			dummy_dst[MV_XOR_MIN_BYTE_COUNT];
 	dma_addr_t		dummy_src_addr, dummy_dst_addr;
 	u32                     saved_config_reg, saved_int_mask_reg;
+
+	struct mv_xor_device	*xordev;
 };
 
 /**
diff --git a/drivers/dma/mxs-dma.c b/drivers/dma/mxs-dma.c
index 60de35251da5..e217268c7098 100644
--- a/drivers/dma/mxs-dma.c
+++ b/drivers/dma/mxs-dma.c
@@ -326,8 +326,7 @@ static void mxs_dma_tasklet(unsigned long data)
 {
 	struct mxs_dma_chan *mxs_chan = (struct mxs_dma_chan *) data;
 
-	if (mxs_chan->desc.callback)
-		mxs_chan->desc.callback(mxs_chan->desc.callback_param);
+	dmaengine_desc_get_callback_invoke(&mxs_chan->desc, NULL);
 }
 
 static int mxs_dma_irq_to_chan(struct mxs_dma_engine *mxs_dma, int irq)
@@ -429,12 +428,10 @@ static int mxs_dma_alloc_chan_resources(struct dma_chan *chan)
 		goto err_alloc;
 	}
 
-	if (mxs_chan->chan_irq != NO_IRQ) {
-		ret = request_irq(mxs_chan->chan_irq, mxs_dma_int_handler,
-					0, "mxs-dma", mxs_dma);
-		if (ret)
-			goto err_irq;
-	}
+	ret = request_irq(mxs_chan->chan_irq, mxs_dma_int_handler,
+			  0, "mxs-dma", mxs_dma);
+	if (ret)
+		goto err_irq;
 
 	ret = clk_prepare_enable(mxs_dma->clk);
 	if (ret)
diff --git a/drivers/dma/nbpfaxi.c b/drivers/dma/nbpfaxi.c
index 08c45c185549..09de71519d37 100644
--- a/drivers/dma/nbpfaxi.c
+++ b/drivers/dma/nbpfaxi.c
@@ -1102,8 +1102,7 @@ static void nbpf_chan_tasklet(unsigned long data)
 {
 	struct nbpf_channel *chan = (struct nbpf_channel *)data;
 	struct nbpf_desc *desc, *tmp;
-	dma_async_tx_callback callback;
-	void *param;
+	struct dmaengine_desc_callback cb;
 
 	while (!list_empty(&chan->done)) {
 		bool found = false, must_put, recycling = false;
@@ -1151,14 +1150,12 @@ static void nbpf_chan_tasklet(unsigned long data)
 			must_put = false;
 		}
 
-		callback = desc->async_tx.callback;
-		param = desc->async_tx.callback_param;
+		dmaengine_desc_get_callback(&desc->async_tx, &cb);
 
 		/* ack and callback completed descriptor */
 		spin_unlock_irq(&chan->lock);
 
-		if (callback)
-			callback(param);
+		dmaengine_desc_callback_invoke(&cb, NULL);
 
 		if (must_put)
 			nbpf_desc_put(desc);
diff --git a/drivers/dma/omap-dma.c b/drivers/dma/omap-dma.c
index d99ca2b511c4..7ca27d4b1c54 100644
--- a/drivers/dma/omap-dma.c
+++ b/drivers/dma/omap-dma.c
@@ -8,6 +8,7 @@
 #include <linux/delay.h>
 #include <linux/dmaengine.h>
 #include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
@@ -32,10 +33,12 @@ struct omap_dmadev {
 	const struct omap_dma_reg *reg_map;
 	struct omap_system_dma_plat_info *plat;
 	bool legacy;
+	bool ll123_supported;
+	struct dma_pool *desc_pool;
 	unsigned dma_requests;
 	spinlock_t irq_lock;
 	uint32_t irq_enable_mask;
-	struct omap_chan *lch_map[OMAP_SDMA_CHANNELS];
+	struct omap_chan **lch_map;
 };
 
 struct omap_chan {
@@ -55,16 +58,40 @@ struct omap_chan {
 	unsigned sgidx;
 };
 
+#define DESC_NXT_SV_REFRESH	(0x1 << 24)
+#define DESC_NXT_SV_REUSE	(0x2 << 24)
+#define DESC_NXT_DV_REFRESH	(0x1 << 26)
+#define DESC_NXT_DV_REUSE	(0x2 << 26)
+#define DESC_NTYPE_TYPE2	(0x2 << 29)
+
+/* Type 2 descriptor with Source or Destination address update */
+struct omap_type2_desc {
+	uint32_t next_desc;
+	uint32_t en;
+	uint32_t addr; /* src or dst */
+	uint16_t fn;
+	uint16_t cicr;
+	int16_t cdei;
+	int16_t csei;
+	int32_t cdfi;
+	int32_t csfi;
+} __packed;
+
 struct omap_sg {
 	dma_addr_t addr;
 	uint32_t en;		/* number of elements (24-bit) */
 	uint32_t fn;		/* number of frames (16-bit) */
 	int32_t fi;		/* for double indexing */
 	int16_t ei;		/* for double indexing */
+
+	/* Linked list */
+	struct omap_type2_desc *t2_desc;
+	dma_addr_t t2_desc_paddr;
 };
 
 struct omap_desc {
 	struct virt_dma_desc vd;
+	bool using_ll;
 	enum dma_transfer_direction dir;
 	dma_addr_t dev_addr;
 
@@ -81,6 +108,9 @@ struct omap_desc {
 };
 
 enum {
+	CAPS_0_SUPPORT_LL123	= BIT(20),	/* Linked List type1/2/3 */
+	CAPS_0_SUPPORT_LL4	= BIT(21),	/* Linked List type4 */
+
 	CCR_FS			= BIT(5),
 	CCR_READ_PRIORITY	= BIT(6),
 	CCR_ENABLE		= BIT(7),
@@ -151,6 +181,19 @@ enum {
 	CICR_SUPER_BLOCK_IE	= BIT(14),	/* OMAP2+ only */
 
 	CLNK_CTRL_ENABLE_LNK	= BIT(15),
+
+	CDP_DST_VALID_INC	= 0 << 0,
+	CDP_DST_VALID_RELOAD	= 1 << 0,
+	CDP_DST_VALID_REUSE	= 2 << 0,
+	CDP_SRC_VALID_INC	= 0 << 2,
+	CDP_SRC_VALID_RELOAD	= 1 << 2,
+	CDP_SRC_VALID_REUSE	= 2 << 2,
+	CDP_NTYPE_TYPE1		= 1 << 4,
+	CDP_NTYPE_TYPE2		= 2 << 4,
+	CDP_NTYPE_TYPE3		= 3 << 4,
+	CDP_TMODE_NORMAL	= 0 << 8,
+	CDP_TMODE_LLIST		= 1 << 8,
+	CDP_FAST		= BIT(10),
 };
 
 static const unsigned es_bytes[] = {
@@ -180,7 +223,64 @@ static inline struct omap_desc *to_omap_dma_desc(struct dma_async_tx_descriptor
 
 static void omap_dma_desc_free(struct virt_dma_desc *vd)
 {
-	kfree(container_of(vd, struct omap_desc, vd));
+	struct omap_desc *d = to_omap_dma_desc(&vd->tx);
+
+	if (d->using_ll) {
+		struct omap_dmadev *od = to_omap_dma_dev(vd->tx.chan->device);
+		int i;
+
+		for (i = 0; i < d->sglen; i++) {
+			if (d->sg[i].t2_desc)
+				dma_pool_free(od->desc_pool, d->sg[i].t2_desc,
+					      d->sg[i].t2_desc_paddr);
+		}
+	}
+
+	kfree(d);
+}
+
+static void omap_dma_fill_type2_desc(struct omap_desc *d, int idx,
+				     enum dma_transfer_direction dir, bool last)
+{
+	struct omap_sg *sg = &d->sg[idx];
+	struct omap_type2_desc *t2_desc = sg->t2_desc;
+
+	if (idx)
+		d->sg[idx - 1].t2_desc->next_desc = sg->t2_desc_paddr;
+	if (last)
+		t2_desc->next_desc = 0xfffffffc;
+
+	t2_desc->en = sg->en;
+	t2_desc->addr = sg->addr;
+	t2_desc->fn = sg->fn & 0xffff;
+	t2_desc->cicr = d->cicr;
+	if (!last)
+		t2_desc->cicr &= ~CICR_BLOCK_IE;
+
+	switch (dir) {
+	case DMA_DEV_TO_MEM:
+		t2_desc->cdei = sg->ei;
+		t2_desc->csei = d->ei;
+		t2_desc->cdfi = sg->fi;
+		t2_desc->csfi = d->fi;
+
+		t2_desc->en |= DESC_NXT_DV_REFRESH;
+		t2_desc->en |= DESC_NXT_SV_REUSE;
+		break;
+	case DMA_MEM_TO_DEV:
+		t2_desc->cdei = d->ei;
+		t2_desc->csei = sg->ei;
+		t2_desc->cdfi = d->fi;
+		t2_desc->csfi = sg->fi;
+
+		t2_desc->en |= DESC_NXT_SV_REFRESH;
+		t2_desc->en |= DESC_NXT_DV_REUSE;
+		break;
+	default:
+		return;
+	}
+
+	t2_desc->en |= DESC_NTYPE_TYPE2;
 }
 
 static void omap_dma_write(uint32_t val, unsigned type, void __iomem *addr)
@@ -285,6 +385,7 @@ static void omap_dma_assign(struct omap_dmadev *od, struct omap_chan *c,
 static void omap_dma_start(struct omap_chan *c, struct omap_desc *d)
 {
 	struct omap_dmadev *od = to_omap_dma_dev(c->vc.chan.device);
+	uint16_t cicr = d->cicr;
 
 	if (__dma_omap15xx(od->plat->dma_attr))
 		omap_dma_chan_write(c, CPC, 0);
@@ -293,8 +394,27 @@ static void omap_dma_start(struct omap_chan *c, struct omap_desc *d)
 
 	omap_dma_clear_csr(c);
 
+	if (d->using_ll) {
+		uint32_t cdp = CDP_TMODE_LLIST | CDP_NTYPE_TYPE2 | CDP_FAST;
+
+		if (d->dir == DMA_DEV_TO_MEM)
+			cdp |= (CDP_DST_VALID_RELOAD | CDP_SRC_VALID_REUSE);
+		else
+			cdp |= (CDP_DST_VALID_REUSE | CDP_SRC_VALID_RELOAD);
+		omap_dma_chan_write(c, CDP, cdp);
+
+		omap_dma_chan_write(c, CNDP, d->sg[0].t2_desc_paddr);
+		omap_dma_chan_write(c, CCDN, 0);
+		omap_dma_chan_write(c, CCFN, 0xffff);
+		omap_dma_chan_write(c, CCEN, 0xffffff);
+
+		cicr &= ~CICR_BLOCK_IE;
+	} else if (od->ll123_supported) {
+		omap_dma_chan_write(c, CDP, 0);
+	}
+
 	/* Enable interrupts */
-	omap_dma_chan_write(c, CICR, d->cicr);
+	omap_dma_chan_write(c, CICR, cicr);
 
 	/* Enable channel */
 	omap_dma_chan_write(c, CCR, d->ccr | CCR_ENABLE);
@@ -365,10 +485,9 @@ static void omap_dma_stop(struct omap_chan *c)
 	c->running = false;
 }
 
-static void omap_dma_start_sg(struct omap_chan *c, struct omap_desc *d,
-	unsigned idx)
+static void omap_dma_start_sg(struct omap_chan *c, struct omap_desc *d)
 {
-	struct omap_sg *sg = d->sg + idx;
+	struct omap_sg *sg = d->sg + c->sgidx;
 	unsigned cxsa, cxei, cxfi;
 
 	if (d->dir == DMA_DEV_TO_MEM || d->dir == DMA_MEM_TO_MEM) {
@@ -388,6 +507,7 @@ static void omap_dma_start_sg(struct omap_chan *c, struct omap_desc *d,
 	omap_dma_chan_write(c, CFN, sg->fn);
 
 	omap_dma_start(c, d);
+	c->sgidx++;
 }
 
 static void omap_dma_start_desc(struct omap_chan *c)
@@ -433,7 +553,7 @@ static void omap_dma_start_desc(struct omap_chan *c)
 	omap_dma_chan_write(c, CSDP, d->csdp);
 	omap_dma_chan_write(c, CLNK_CTRL, d->clnk_ctrl);
 
-	omap_dma_start_sg(c, d, 0);
+	omap_dma_start_sg(c, d);
 }
 
 static void omap_dma_callback(int ch, u16 status, void *data)
@@ -445,15 +565,13 @@ static void omap_dma_callback(int ch, u16 status, void *data)
 	spin_lock_irqsave(&c->vc.lock, flags);
 	d = c->desc;
 	if (d) {
-		if (!c->cyclic) {
-			if (++c->sgidx < d->sglen) {
-				omap_dma_start_sg(c, d, c->sgidx);
-			} else {
-				omap_dma_start_desc(c);
-				vchan_cookie_complete(&d->vd);
-			}
-		} else {
+		if (c->cyclic) {
 			vchan_cyclic_callback(&d->vd);
+		} else if (d->using_ll || c->sgidx == d->sglen) {
+			omap_dma_start_desc(c);
+			vchan_cookie_complete(&d->vd);
+		} else {
+			omap_dma_start_sg(c, d);
 		}
 	}
 	spin_unlock_irqrestore(&c->vc.lock, flags);
@@ -503,6 +621,7 @@ static int omap_dma_alloc_chan_resources(struct dma_chan *chan)
 {
 	struct omap_dmadev *od = to_omap_dma_dev(chan->device);
 	struct omap_chan *c = to_omap_dma_chan(chan);
+	struct device *dev = od->ddev.dev;
 	int ret;
 
 	if (od->legacy) {
@@ -513,8 +632,7 @@ static int omap_dma_alloc_chan_resources(struct dma_chan *chan)
 				       &c->dma_ch);
 	}
 
-	dev_dbg(od->ddev.dev, "allocating channel %u for %u\n",
-		c->dma_ch, c->dma_sig);
+	dev_dbg(dev, "allocating channel %u for %u\n", c->dma_ch, c->dma_sig);
 
 	if (ret >= 0) {
 		omap_dma_assign(od, c, c->dma_ch);
@@ -570,7 +688,8 @@ static void omap_dma_free_chan_resources(struct dma_chan *chan)
 	vchan_free_chan_resources(&c->vc);
 	omap_free_dma(c->dma_ch);
 
-	dev_dbg(od->ddev.dev, "freeing channel for %u\n", c->dma_sig);
+	dev_dbg(od->ddev.dev, "freeing channel %u used for %u\n", c->dma_ch,
+		c->dma_sig);
 	c->dma_sig = 0;
 }
 
@@ -744,6 +863,7 @@ static struct dma_async_tx_descriptor *omap_dma_prep_slave_sg(
 	struct omap_desc *d;
 	dma_addr_t dev_addr;
 	unsigned i, es, en, frame_bytes;
+	bool ll_failed = false;
 	u32 burst;
 
 	if (dir == DMA_DEV_TO_MEM) {
@@ -784,13 +904,16 @@ static struct dma_async_tx_descriptor *omap_dma_prep_slave_sg(
 	d->es = es;
 
 	d->ccr = c->ccr | CCR_SYNC_FRAME;
-	if (dir == DMA_DEV_TO_MEM)
+	if (dir == DMA_DEV_TO_MEM) {
 		d->ccr |= CCR_DST_AMODE_POSTINC | CCR_SRC_AMODE_CONSTANT;
-	else
+		d->csdp = CSDP_DST_BURST_64 | CSDP_DST_PACKED;
+	} else {
 		d->ccr |= CCR_DST_AMODE_CONSTANT | CCR_SRC_AMODE_POSTINC;
+		d->csdp = CSDP_SRC_BURST_64 | CSDP_SRC_PACKED;
+	}
 
 	d->cicr = CICR_DROP_IE | CICR_BLOCK_IE;
-	d->csdp = es;
+	d->csdp |= es;
 
 	if (dma_omap1()) {
 		d->cicr |= CICR_TOUT_IE;
@@ -819,14 +942,47 @@ static struct dma_async_tx_descriptor *omap_dma_prep_slave_sg(
 	 */
 	en = burst;
 	frame_bytes = es_bytes[es] * en;
+
+	if (sglen >= 2)
+		d->using_ll = od->ll123_supported;
+
 	for_each_sg(sgl, sgent, sglen, i) {
-		d->sg[i].addr = sg_dma_address(sgent);
-		d->sg[i].en = en;
-		d->sg[i].fn = sg_dma_len(sgent) / frame_bytes;
+		struct omap_sg *osg = &d->sg[i];
+
+		osg->addr = sg_dma_address(sgent);
+		osg->en = en;
+		osg->fn = sg_dma_len(sgent) / frame_bytes;
+
+		if (d->using_ll) {
+			osg->t2_desc = dma_pool_alloc(od->desc_pool, GFP_ATOMIC,
+						      &osg->t2_desc_paddr);
+			if (!osg->t2_desc) {
+				dev_err(chan->device->dev,
+					"t2_desc[%d] allocation failed\n", i);
+				ll_failed = true;
+				d->using_ll = false;
+				continue;
+			}
+
+			omap_dma_fill_type2_desc(d, i, dir, (i == sglen - 1));
+		}
 	}
 
 	d->sglen = sglen;
 
+	/* Release the dma_pool entries if one allocation failed */
+	if (ll_failed) {
+		for (i = 0; i < d->sglen; i++) {
+			struct omap_sg *osg = &d->sg[i];
+
+			if (osg->t2_desc) {
+				dma_pool_free(od->desc_pool, osg->t2_desc,
+					      osg->t2_desc_paddr);
+				osg->t2_desc = NULL;
+			}
+		}
+	}
+
 	return vchan_tx_prep(&c->vc, &d->vd, tx_flags);
 }
 
@@ -1225,16 +1381,24 @@ static int omap_dma_probe(struct platform_device *pdev)
 	spin_lock_init(&od->lock);
 	spin_lock_init(&od->irq_lock);
 
-	od->dma_requests = OMAP_SDMA_REQUESTS;
-	if (pdev->dev.of_node && of_property_read_u32(pdev->dev.of_node,
-						      "dma-requests",
-						      &od->dma_requests)) {
+	if (!pdev->dev.of_node) {
+		od->dma_requests = od->plat->dma_attr->lch_count;
+		if (unlikely(!od->dma_requests))
+			od->dma_requests = OMAP_SDMA_REQUESTS;
+	} else if (of_property_read_u32(pdev->dev.of_node, "dma-requests",
+					&od->dma_requests)) {
 		dev_info(&pdev->dev,
 			 "Missing dma-requests property, using %u.\n",
 			 OMAP_SDMA_REQUESTS);
+		od->dma_requests = OMAP_SDMA_REQUESTS;
 	}
 
-	for (i = 0; i < OMAP_SDMA_CHANNELS; i++) {
+	od->lch_map = devm_kcalloc(&pdev->dev, od->dma_requests,
+				   sizeof(*od->lch_map), GFP_KERNEL);
+	if (!od->lch_map)
+		return -ENOMEM;
+
+	for (i = 0; i < od->dma_requests; i++) {
 		rc = omap_dma_chan_init(od);
 		if (rc) {
 			omap_dma_free(od);
@@ -1257,10 +1421,25 @@ static int omap_dma_probe(struct platform_device *pdev)
 			return rc;
 	}
 
+	if (omap_dma_glbl_read(od, CAPS_0) & CAPS_0_SUPPORT_LL123)
+		od->ll123_supported = true;
+
 	od->ddev.filter.map = od->plat->slave_map;
 	od->ddev.filter.mapcnt = od->plat->slavecnt;
 	od->ddev.filter.fn = omap_dma_filter_fn;
 
+	if (od->ll123_supported) {
+		od->desc_pool = dma_pool_create(dev_name(&pdev->dev),
+						&pdev->dev,
+						sizeof(struct omap_type2_desc),
+						4, 0);
+		if (!od->desc_pool) {
+			dev_err(&pdev->dev,
+				"unable to allocate descriptor pool\n");
+			od->ll123_supported = false;
+		}
+	}
+
 	rc = dma_async_device_register(&od->ddev);
 	if (rc) {
 		pr_warn("OMAP-DMA: failed to register slave DMA engine device: %d\n",
@@ -1284,7 +1463,8 @@ static int omap_dma_probe(struct platform_device *pdev)
 		}
 	}
 
-	dev_info(&pdev->dev, "OMAP DMA engine driver\n");
+	dev_info(&pdev->dev, "OMAP DMA engine driver%s\n",
+		 od->ll123_supported ? " (LinkedList1/2/3 supported)" : "");
 
 	return rc;
 }
@@ -1307,6 +1487,9 @@ static int omap_dma_remove(struct platform_device *pdev)
 		omap_dma_glbl_write(od, IRQENABLE_L0, 0);
 	}
 
+	if (od->ll123_supported)
+		dma_pool_destroy(od->desc_pool);
+
 	omap_dma_free(od);
 
 	return 0;
diff --git a/drivers/dma/pch_dma.c b/drivers/dma/pch_dma.c
index 113605f6fe20..df95727dc2fb 100644
--- a/drivers/dma/pch_dma.c
+++ b/drivers/dma/pch_dma.c
@@ -357,14 +357,13 @@ static void pdc_chain_complete(struct pch_dma_chan *pd_chan,
 			       struct pch_dma_desc *desc)
 {
 	struct dma_async_tx_descriptor *txd = &desc->txd;
-	dma_async_tx_callback callback = txd->callback;
-	void *param = txd->callback_param;
+	struct dmaengine_desc_callback cb;
 
+	dmaengine_desc_get_callback(txd, &cb);
 	list_splice_init(&desc->tx_list, &pd_chan->free_list);
 	list_move(&desc->desc_node, &pd_chan->free_list);
 
-	if (callback)
-		callback(param);
+	dmaengine_desc_callback_invoke(&cb, NULL);
 }
 
 static void pdc_complete_all(struct pch_dma_chan *pd_chan)
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index 4fc3ffbd5ca0..030fe05ed43b 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -2039,14 +2039,12 @@ static void pl330_tasklet(unsigned long data)
 	}
 
 	while (!list_empty(&pch->completed_list)) {
-		dma_async_tx_callback callback;
-		void *callback_param;
+		struct dmaengine_desc_callback cb;
 
 		desc = list_first_entry(&pch->completed_list,
 					struct dma_pl330_desc, node);
 
-		callback = desc->txd.callback;
-		callback_param = desc->txd.callback_param;
+		dmaengine_desc_get_callback(&desc->txd, &cb);
 
 		if (pch->cyclic) {
 			desc->status = PREP;
@@ -2064,9 +2062,9 @@ static void pl330_tasklet(unsigned long data)
 
 		dma_descriptor_unmap(&desc->txd);
 
-		if (callback) {
+		if (dmaengine_desc_callback_valid(&cb)) {
 			spin_unlock_irqrestore(&pch->lock, flags);
-			callback(callback_param);
+			dmaengine_desc_callback_invoke(&cb, NULL);
 			spin_lock_irqsave(&pch->lock, flags);
 		}
 	}
@@ -2274,7 +2272,7 @@ pl330_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 {
 	enum dma_status ret;
 	unsigned long flags;
-	struct dma_pl330_desc *desc, *running = NULL;
+	struct dma_pl330_desc *desc, *running = NULL, *last_enq = NULL;
 	struct dma_pl330_chan *pch = to_pchan(chan);
 	unsigned int transferred, residual = 0;
 
@@ -2287,10 +2285,13 @@ pl330_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 		goto out;
 
 	spin_lock_irqsave(&pch->lock, flags);
+	spin_lock(&pch->thread->dmac->lock);
 
 	if (pch->thread->req_running != -1)
 		running = pch->thread->req[pch->thread->req_running].desc;
 
+	last_enq = pch->thread->req[pch->thread->lstenq].desc;
+
 	/* Check in pending list */
 	list_for_each_entry(desc, &pch->work_list, node) {
 		if (desc->status == DONE)
@@ -2298,6 +2299,15 @@ pl330_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 		else if (running && desc == running)
 			transferred =
 				pl330_get_current_xferred_count(pch, desc);
+		else if (desc->status == BUSY)
+			/*
+			 * Busy but not running means either just enqueued,
+			 * or finished and not yet marked done
+			 */
+			if (desc == last_enq)
+				transferred = 0;
+			else
+				transferred = desc->bytes_requested;
 		else
 			transferred = 0;
 		residual += desc->bytes_requested - transferred;
@@ -2318,6 +2328,7 @@ pl330_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 		if (desc->last)
 			residual = 0;
 	}
+	spin_unlock(&pch->thread->dmac->lock);
 	spin_unlock_irqrestore(&pch->lock, flags);
 
 out:
diff --git a/drivers/dma/ppc4xx/adma.c b/drivers/dma/ppc4xx/adma.c
index da3688b94bdc..b1535b1fe95c 100644
--- a/drivers/dma/ppc4xx/adma.c
+++ b/drivers/dma/ppc4xx/adma.c
@@ -1482,14 +1482,11 @@ static dma_cookie_t ppc440spe_adma_run_tx_complete_actions(
 		cookie = desc->async_tx.cookie;
 		desc->async_tx.cookie = 0;
 
+		dma_descriptor_unmap(&desc->async_tx);
 		/* call the callback (must not sleep or submit new
 		 * operations to this channel)
 		 */
-		if (desc->async_tx.callback)
-			desc->async_tx.callback(
-				desc->async_tx.callback_param);
-
-		dma_descriptor_unmap(&desc->async_tx);
+		dmaengine_desc_get_callback_invoke(&desc->async_tx, NULL);
 	}
 
 	/* run dependent operations */
@@ -3891,7 +3888,7 @@ static int ppc440spe_adma_setup_irqs(struct ppc440spe_adma_device *adev,
 	np = ofdev->dev.of_node;
 	if (adev->id != PPC440SPE_XOR_ID) {
 		adev->err_irq = irq_of_parse_and_map(np, 1);
-		if (adev->err_irq == NO_IRQ) {
+		if (!adev->err_irq) {
 			dev_warn(adev->dev, "no err irq resource?\n");
 			*initcode = PPC_ADMA_INIT_IRQ2;
 			adev->err_irq = -ENXIO;
@@ -3902,7 +3899,7 @@ static int ppc440spe_adma_setup_irqs(struct ppc440spe_adma_device *adev,
 	}
 
 	adev->irq = irq_of_parse_and_map(np, 0);
-	if (adev->irq == NO_IRQ) {
+	if (!adev->irq) {
 		dev_err(adev->dev, "no irq resource\n");
 		*initcode = PPC_ADMA_INIT_IRQ1;
 		ret = -ENXIO;
diff --git a/drivers/dma/qcom/hidma.c b/drivers/dma/qcom/hidma.c
index b2374cd91e45..e244e10a94b5 100644
--- a/drivers/dma/qcom/hidma.c
+++ b/drivers/dma/qcom/hidma.c
@@ -111,6 +111,7 @@ static void hidma_process_completed(struct hidma_chan *mchan)
 	struct dma_async_tx_descriptor *desc;
 	dma_cookie_t last_cookie;
 	struct hidma_desc *mdesc;
+	struct hidma_desc *next;
 	unsigned long irqflags;
 	struct list_head list;
 
@@ -122,28 +123,36 @@ static void hidma_process_completed(struct hidma_chan *mchan)
 	spin_unlock_irqrestore(&mchan->lock, irqflags);
 
 	/* Execute callbacks and run dependencies */
-	list_for_each_entry(mdesc, &list, node) {
+	list_for_each_entry_safe(mdesc, next, &list, node) {
 		enum dma_status llstat;
+		struct dmaengine_desc_callback cb;
+		struct dmaengine_result result;
 
 		desc = &mdesc->desc;
+		last_cookie = desc->cookie;
 
 		spin_lock_irqsave(&mchan->lock, irqflags);
 		dma_cookie_complete(desc);
 		spin_unlock_irqrestore(&mchan->lock, irqflags);
 
 		llstat = hidma_ll_status(mdma->lldev, mdesc->tre_ch);
-		if (desc->callback && (llstat == DMA_COMPLETE))
-			desc->callback(desc->callback_param);
+		dmaengine_desc_get_callback(desc, &cb);
 
-		last_cookie = desc->cookie;
 		dma_run_dependencies(desc);
-	}
 
-	/* Free descriptors */
-	spin_lock_irqsave(&mchan->lock, irqflags);
-	list_splice_tail_init(&list, &mchan->free);
-	spin_unlock_irqrestore(&mchan->lock, irqflags);
+		spin_lock_irqsave(&mchan->lock, irqflags);
+		list_move(&mdesc->node, &mchan->free);
+
+		if (llstat == DMA_COMPLETE) {
+			mchan->last_success = last_cookie;
+			result.result = DMA_TRANS_NOERROR;
+		} else
+			result.result = DMA_TRANS_ABORTED;
+
+		spin_unlock_irqrestore(&mchan->lock, irqflags);
 
+		dmaengine_desc_callback_invoke(&cb, &result);
+	}
 }
 
 /*
@@ -238,6 +247,19 @@ static void hidma_issue_pending(struct dma_chan *dmach)
 		hidma_ll_start(dmadev->lldev);
 }
 
+static inline bool hidma_txn_is_success(dma_cookie_t cookie,
+		dma_cookie_t last_success, dma_cookie_t last_used)
+{
+	if (last_success <= last_used) {
+		if ((cookie <= last_success) || (cookie > last_used))
+			return true;
+	} else {
+		if ((cookie <= last_success) && (cookie > last_used))
+			return true;
+	}
+	return false;
+}
+
 static enum dma_status hidma_tx_status(struct dma_chan *dmach,
 				       dma_cookie_t cookie,
 				       struct dma_tx_state *txstate)
@@ -246,8 +268,13 @@ static enum dma_status hidma_tx_status(struct dma_chan *dmach,
 	enum dma_status ret;
 
 	ret = dma_cookie_status(dmach, cookie, txstate);
-	if (ret == DMA_COMPLETE)
-		return ret;
+	if (ret == DMA_COMPLETE) {
+		bool is_success;
+
+		is_success = hidma_txn_is_success(cookie, mchan->last_success,
+						  dmach->cookie);
+		return is_success ? ret : DMA_ERROR;
+	}
 
 	if (mchan->paused && (ret == DMA_IN_PROGRESS)) {
 		unsigned long flags;
@@ -398,6 +425,7 @@ static int hidma_terminate_channel(struct dma_chan *chan)
 	hidma_process_completed(mchan);
 
 	spin_lock_irqsave(&mchan->lock, irqflags);
+	mchan->last_success = 0;
 	list_splice_init(&mchan->active, &list);
 	list_splice_init(&mchan->prepared, &list);
 	list_splice_init(&mchan->completed, &list);
@@ -413,14 +441,9 @@ static int hidma_terminate_channel(struct dma_chan *chan)
 	/* return all user requests */
 	list_for_each_entry_safe(mdesc, tmp, &list, node) {
 		struct dma_async_tx_descriptor *txd = &mdesc->desc;
-		dma_async_tx_callback callback = mdesc->desc.callback;
-		void *param = mdesc->desc.callback_param;
 
 		dma_descriptor_unmap(txd);
-
-		if (callback)
-			callback(param);
-
+		dmaengine_desc_get_callback_invoke(txd, NULL);
 		dma_run_dependencies(txd);
 
 		/* move myself to free_list */
diff --git a/drivers/dma/qcom/hidma.h b/drivers/dma/qcom/hidma.h
index db413a5efc4e..e52e20716303 100644
--- a/drivers/dma/qcom/hidma.h
+++ b/drivers/dma/qcom/hidma.h
@@ -72,7 +72,6 @@ struct hidma_lldev {
 
 	u32 tre_write_offset;           /* TRE write location              */
 	struct tasklet_struct task;	/* task delivering notifications   */
-	struct tasklet_struct rst_task;	/* task to reset HW                */
 	DECLARE_KFIFO_PTR(handoff_fifo,
 		struct hidma_tre *);    /* pending TREs FIFO               */
 };
@@ -89,6 +88,7 @@ struct hidma_chan {
 	bool				allocated;
 	char				dbg_name[16];
 	u32				dma_sig;
+	dma_cookie_t			last_success;
 
 	/*
 	 * active descriptor on this channel
diff --git a/drivers/dma/qcom/hidma_ll.c b/drivers/dma/qcom/hidma_ll.c
index ad20dfb64c71..3224f24c577b 100644
--- a/drivers/dma/qcom/hidma_ll.c
+++ b/drivers/dma/qcom/hidma_ll.c
@@ -381,27 +381,6 @@ static int hidma_ll_reset(struct hidma_lldev *lldev)
 }
 
 /*
- * Abort all transactions and perform a reset.
- */
-static void hidma_ll_abort(unsigned long arg)
-{
-	struct hidma_lldev *lldev = (struct hidma_lldev *)arg;
-	u8 err_code = HIDMA_EVRE_STATUS_ERROR;
-	u8 err_info = 0xFF;
-	int rc;
-
-	hidma_cleanup_pending_tre(lldev, err_info, err_code);
-
-	/* reset the channel for recovery */
-	rc = hidma_ll_setup(lldev);
-	if (rc) {
-		dev_err(lldev->dev, "channel reinitialize failed after error\n");
-		return;
-	}
-	writel(ENABLE_IRQS, lldev->evca + HIDMA_EVCA_IRQ_EN_REG);
-}
-
-/*
  * The interrupt handler for HIDMA will try to consume as many pending
  * EVRE from the event queue as possible. Each EVRE has an associated
  * TRE that holds the user interface parameters. EVRE reports the
@@ -454,13 +433,18 @@ irqreturn_t hidma_ll_inthandler(int chirq, void *arg)
 
 	while (cause) {
 		if (cause & HIDMA_ERR_INT_MASK) {
-			dev_err(lldev->dev, "error 0x%x, resetting...\n",
+			dev_err(lldev->dev, "error 0x%x, disabling...\n",
 					cause);
 
 			/* Clear out pending interrupts */
 			writel(cause, lldev->evca + HIDMA_EVCA_IRQ_CLR_REG);
 
-			tasklet_schedule(&lldev->rst_task);
+			/* No further submissions. */
+			hidma_ll_disable(lldev);
+
+			/* Driver completes the txn and intimates the client.*/
+			hidma_cleanup_pending_tre(lldev, 0xFF,
+						  HIDMA_EVRE_STATUS_ERROR);
 			goto out;
 		}
 
@@ -808,7 +792,6 @@ struct hidma_lldev *hidma_ll_init(struct device *dev, u32 nr_tres,
 		return NULL;
 
 	spin_lock_init(&lldev->lock);
-	tasklet_init(&lldev->rst_task, hidma_ll_abort, (unsigned long)lldev);
 	tasklet_init(&lldev->task, hidma_ll_tre_complete, (unsigned long)lldev);
 	lldev->initialized = 1;
 	writel(ENABLE_IRQS, lldev->evca + HIDMA_EVCA_IRQ_EN_REG);
@@ -831,7 +814,6 @@ int hidma_ll_uninit(struct hidma_lldev *lldev)
 
 	required_bytes = sizeof(struct hidma_tre) * lldev->nr_tres;
 	tasklet_kill(&lldev->task);
-	tasklet_kill(&lldev->rst_task);
 	memset(lldev->trepool, 0, required_bytes);
 	lldev->trepool = NULL;
 	lldev->pending_tre_count = 0;
diff --git a/drivers/dma/s3c24xx-dma.c b/drivers/dma/s3c24xx-dma.c
index ce67075589f5..3c579abbabb7 100644
--- a/drivers/dma/s3c24xx-dma.c
+++ b/drivers/dma/s3c24xx-dma.c
@@ -823,11 +823,11 @@ static struct dma_async_tx_descriptor *s3c24xx_dma_prep_memcpy(
 	struct s3c24xx_sg *dsg;
 	int src_mod, dest_mod;
 
-	dev_dbg(&s3cdma->pdev->dev, "prepare memcpy of %d bytes from %s\n",
+	dev_dbg(&s3cdma->pdev->dev, "prepare memcpy of %zu bytes from %s\n",
 			len, s3cchan->name);
 
 	if ((len & S3C24XX_DCON_TC_MASK) != len) {
-		dev_err(&s3cdma->pdev->dev, "memcpy size %d to large\n", len);
+		dev_err(&s3cdma->pdev->dev, "memcpy size %zu to large\n", len);
 		return NULL;
 	}
 
@@ -1301,6 +1301,9 @@ static int s3c24xx_dma_probe(struct platform_device *pdev)
 	s3cdma->slave.device_prep_dma_cyclic = s3c24xx_dma_prep_dma_cyclic;
 	s3cdma->slave.device_config = s3c24xx_dma_set_runtime_config;
 	s3cdma->slave.device_terminate_all = s3c24xx_dma_terminate_all;
+	s3cdma->slave.filter.map = pdata->slave_map;
+	s3cdma->slave.filter.mapcnt = pdata->slavecnt;
+	s3cdma->slave.filter.fn = s3c24xx_dma_filter;
 
 	/* Register as many memcpy channels as there are physical channels */
 	ret = s3c24xx_dma_init_virtual_channels(s3cdma, &s3cdma->memcpy,
@@ -1418,7 +1421,7 @@ bool s3c24xx_dma_filter(struct dma_chan *chan, void *param)
 
 	s3cchan = to_s3c24xx_dma_chan(chan);
 
-	return s3cchan->id == (int)param;
+	return s3cchan->id == (uintptr_t)param;
 }
 EXPORT_SYMBOL(s3c24xx_dma_filter);
 
diff --git a/drivers/dma/sa11x0-dma.c b/drivers/dma/sa11x0-dma.c
index 43db255050d2..1adeb3265085 100644
--- a/drivers/dma/sa11x0-dma.c
+++ b/drivers/dma/sa11x0-dma.c
@@ -463,7 +463,7 @@ static enum dma_status sa11x0_dma_tx_status(struct dma_chan *chan,
 			dma_addr_t addr = sa11x0_dma_pos(p);
 			unsigned i;
 
-			dev_vdbg(d->slave.dev, "tx_status: addr:%x\n", addr);
+			dev_vdbg(d->slave.dev, "tx_status: addr:%pad\n", &addr);
 
 			for (i = 0; i < txd->sglen; i++) {
 				dev_vdbg(d->slave.dev, "tx_status: [%u] %x+%x\n",
@@ -491,7 +491,7 @@ static enum dma_status sa11x0_dma_tx_status(struct dma_chan *chan,
 	}
 	spin_unlock_irqrestore(&c->vc.lock, flags);
 
-	dev_vdbg(d->slave.dev, "tx_status: bytes 0x%zx\n", state->residue);
+	dev_vdbg(d->slave.dev, "tx_status: bytes 0x%x\n", state->residue);
 
 	return ret;
 }
@@ -551,8 +551,8 @@ static struct dma_async_tx_descriptor *sa11x0_dma_prep_slave_sg(
 		if (len > DMA_MAX_SIZE)
 			j += DIV_ROUND_UP(len, DMA_MAX_SIZE & ~DMA_ALIGN) - 1;
 		if (addr & DMA_ALIGN) {
-			dev_dbg(chan->device->dev, "vchan %p: bad buffer alignment: %08x\n",
-				&c->vc, addr);
+			dev_dbg(chan->device->dev, "vchan %p: bad buffer alignment: %pad\n",
+				&c->vc, &addr);
 			return NULL;
 		}
 	}
@@ -599,7 +599,7 @@ static struct dma_async_tx_descriptor *sa11x0_dma_prep_slave_sg(
 	txd->size = size;
 	txd->sglen = j;
 
-	dev_dbg(chan->device->dev, "vchan %p: txd %p: size %u nr %u\n",
+	dev_dbg(chan->device->dev, "vchan %p: txd %p: size %zu nr %u\n",
 		&c->vc, &txd->vd, txd->size, txd->sglen);
 
 	return vchan_tx_prep(&c->vc, &txd->vd, flags);
@@ -693,8 +693,8 @@ static int sa11x0_dma_device_config(struct dma_chan *chan,
 	if (maxburst == 8)
 		ddar |= DDAR_BS;
 
-	dev_dbg(c->vc.chan.device->dev, "vchan %p: dma_slave_config addr %x width %u burst %u\n",
-		&c->vc, addr, width, maxburst);
+	dev_dbg(c->vc.chan.device->dev, "vchan %p: dma_slave_config addr %pad width %u burst %u\n",
+		&c->vc, &addr, width, maxburst);
 
 	c->ddar = ddar | (addr & 0xf0000000) | (addr & 0x003ffffc) << 6;
 
diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c
index 0dd953884d1d..2e441d0ccd79 100644
--- a/drivers/dma/sh/rcar-dmac.c
+++ b/drivers/dma/sh/rcar-dmac.c
@@ -118,14 +118,34 @@ struct rcar_dmac_desc_page {
 	sizeof(struct rcar_dmac_xfer_chunk))
 
 /*
+ * struct rcar_dmac_chan_slave - Slave configuration
+ * @slave_addr: slave memory address
+ * @xfer_size: size (in bytes) of hardware transfers
+ */
+struct rcar_dmac_chan_slave {
+	phys_addr_t slave_addr;
+	unsigned int xfer_size;
+};
+
+/*
+ * struct rcar_dmac_chan_map - Map of slave device phys to dma address
+ * @addr: slave dma address
+ * @dir: direction of mapping
+ * @slave: slave configuration that is mapped
+ */
+struct rcar_dmac_chan_map {
+	dma_addr_t addr;
+	enum dma_data_direction dir;
+	struct rcar_dmac_chan_slave slave;
+};
+
+/*
  * struct rcar_dmac_chan - R-Car Gen2 DMA Controller Channel
  * @chan: base DMA channel object
  * @iomem: channel I/O memory base
  * @index: index of this channel in the controller
- * @src_xfer_size: size (in bytes) of hardware transfers on the source side
- * @dst_xfer_size: size (in bytes) of hardware transfers on the destination side
- * @src_slave_addr: slave source memory address
- * @dst_slave_addr: slave destination memory address
+ * @src: slave memory address and size on the source side
+ * @dst: slave memory address and size on the destination side
  * @mid_rid: hardware MID/RID for the DMA client using this channel
  * @lock: protects the channel CHCR register and the desc members
  * @desc.free: list of free descriptors
@@ -142,10 +162,9 @@ struct rcar_dmac_chan {
 	void __iomem *iomem;
 	unsigned int index;
 
-	unsigned int src_xfer_size;
-	unsigned int dst_xfer_size;
-	dma_addr_t src_slave_addr;
-	dma_addr_t dst_slave_addr;
+	struct rcar_dmac_chan_slave src;
+	struct rcar_dmac_chan_slave dst;
+	struct rcar_dmac_chan_map map;
 	int mid_rid;
 
 	spinlock_t lock;
@@ -793,13 +812,13 @@ static void rcar_dmac_chan_configure_desc(struct rcar_dmac_chan *chan,
 	case DMA_DEV_TO_MEM:
 		chcr = RCAR_DMACHCR_DM_INC | RCAR_DMACHCR_SM_FIXED
 		     | RCAR_DMACHCR_RS_DMARS;
-		xfer_size = chan->src_xfer_size;
+		xfer_size = chan->src.xfer_size;
 		break;
 
 	case DMA_MEM_TO_DEV:
 		chcr = RCAR_DMACHCR_DM_FIXED | RCAR_DMACHCR_SM_INC
 		     | RCAR_DMACHCR_RS_DMARS;
-		xfer_size = chan->dst_xfer_size;
+		xfer_size = chan->dst.xfer_size;
 		break;
 
 	case DMA_MEM_TO_MEM:
@@ -1023,13 +1042,65 @@ rcar_dmac_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dma_dest,
 				      DMA_MEM_TO_MEM, flags, false);
 }
 
+static int rcar_dmac_map_slave_addr(struct dma_chan *chan,
+				    enum dma_transfer_direction dir)
+{
+	struct rcar_dmac_chan *rchan = to_rcar_dmac_chan(chan);
+	struct rcar_dmac_chan_map *map = &rchan->map;
+	phys_addr_t dev_addr;
+	size_t dev_size;
+	enum dma_data_direction dev_dir;
+
+	if (dir == DMA_DEV_TO_MEM) {
+		dev_addr = rchan->src.slave_addr;
+		dev_size = rchan->src.xfer_size;
+		dev_dir = DMA_TO_DEVICE;
+	} else {
+		dev_addr = rchan->dst.slave_addr;
+		dev_size = rchan->dst.xfer_size;
+		dev_dir = DMA_FROM_DEVICE;
+	}
+
+	/* Reuse current map if possible. */
+	if (dev_addr == map->slave.slave_addr &&
+	    dev_size == map->slave.xfer_size &&
+	    dev_dir == map->dir)
+		return 0;
+
+	/* Remove old mapping if present. */
+	if (map->slave.xfer_size)
+		dma_unmap_resource(chan->device->dev, map->addr,
+				   map->slave.xfer_size, map->dir, 0);
+	map->slave.xfer_size = 0;
+
+	/* Create new slave address map. */
+	map->addr = dma_map_resource(chan->device->dev, dev_addr, dev_size,
+				     dev_dir, 0);
+
+	if (dma_mapping_error(chan->device->dev, map->addr)) {
+		dev_err(chan->device->dev,
+			"chan%u: failed to map %zx@%pap", rchan->index,
+			dev_size, &dev_addr);
+		return -EIO;
+	}
+
+	dev_dbg(chan->device->dev, "chan%u: map %zx@%pap to %pad dir: %s\n",
+		rchan->index, dev_size, &dev_addr, &map->addr,
+		dev_dir == DMA_TO_DEVICE ? "DMA_TO_DEVICE" : "DMA_FROM_DEVICE");
+
+	map->slave.slave_addr = dev_addr;
+	map->slave.xfer_size = dev_size;
+	map->dir = dev_dir;
+
+	return 0;
+}
+
 static struct dma_async_tx_descriptor *
 rcar_dmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 			unsigned int sg_len, enum dma_transfer_direction dir,
 			unsigned long flags, void *context)
 {
 	struct rcar_dmac_chan *rchan = to_rcar_dmac_chan(chan);
-	dma_addr_t dev_addr;
 
 	/* Someone calling slave DMA on a generic channel? */
 	if (rchan->mid_rid < 0 || !sg_len) {
@@ -1039,9 +1110,10 @@ rcar_dmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		return NULL;
 	}
 
-	dev_addr = dir == DMA_DEV_TO_MEM
-		 ? rchan->src_slave_addr : rchan->dst_slave_addr;
-	return rcar_dmac_chan_prep_sg(rchan, sgl, sg_len, dev_addr,
+	if (rcar_dmac_map_slave_addr(chan, dir))
+		return NULL;
+
+	return rcar_dmac_chan_prep_sg(rchan, sgl, sg_len, rchan->map.addr,
 				      dir, flags, false);
 }
 
@@ -1055,7 +1127,6 @@ rcar_dmac_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr,
 	struct rcar_dmac_chan *rchan = to_rcar_dmac_chan(chan);
 	struct dma_async_tx_descriptor *desc;
 	struct scatterlist *sgl;
-	dma_addr_t dev_addr;
 	unsigned int sg_len;
 	unsigned int i;
 
@@ -1067,6 +1138,9 @@ rcar_dmac_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr,
 		return NULL;
 	}
 
+	if (rcar_dmac_map_slave_addr(chan, dir))
+		return NULL;
+
 	sg_len = buf_len / period_len;
 	if (sg_len > RCAR_DMAC_MAX_SG_LEN) {
 		dev_err(chan->device->dev,
@@ -1094,9 +1168,7 @@ rcar_dmac_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr,
 		sg_dma_len(&sgl[i]) = period_len;
 	}
 
-	dev_addr = dir == DMA_DEV_TO_MEM
-		 ? rchan->src_slave_addr : rchan->dst_slave_addr;
-	desc = rcar_dmac_chan_prep_sg(rchan, sgl, sg_len, dev_addr,
+	desc = rcar_dmac_chan_prep_sg(rchan, sgl, sg_len, rchan->map.addr,
 				      dir, flags, true);
 
 	kfree(sgl);
@@ -1112,10 +1184,10 @@ static int rcar_dmac_device_config(struct dma_chan *chan,
 	 * We could lock this, but you shouldn't be configuring the
 	 * channel, while using it...
 	 */
-	rchan->src_slave_addr = cfg->src_addr;
-	rchan->dst_slave_addr = cfg->dst_addr;
-	rchan->src_xfer_size = cfg->src_addr_width;
-	rchan->dst_xfer_size = cfg->dst_addr_width;
+	rchan->src.slave_addr = cfg->src_addr;
+	rchan->dst.slave_addr = cfg->dst_addr;
+	rchan->src.xfer_size = cfg->src_addr_width;
+	rchan->dst.xfer_size = cfg->dst_addr_width;
 
 	return 0;
 }
@@ -1389,21 +1461,18 @@ static irqreturn_t rcar_dmac_isr_channel_thread(int irq, void *dev)
 {
 	struct rcar_dmac_chan *chan = dev;
 	struct rcar_dmac_desc *desc;
+	struct dmaengine_desc_callback cb;
 
 	spin_lock_irq(&chan->lock);
 
 	/* For cyclic transfers notify the user after every chunk. */
 	if (chan->desc.running && chan->desc.running->cyclic) {
-		dma_async_tx_callback callback;
-		void *callback_param;
-
 		desc = chan->desc.running;
-		callback = desc->async_tx.callback;
-		callback_param = desc->async_tx.callback_param;
+		dmaengine_desc_get_callback(&desc->async_tx, &cb);
 
-		if (callback) {
+		if (dmaengine_desc_callback_valid(&cb)) {
 			spin_unlock_irq(&chan->lock);
-			callback(callback_param);
+			dmaengine_desc_callback_invoke(&cb, NULL);
 			spin_lock_irq(&chan->lock);
 		}
 	}
@@ -1418,14 +1487,15 @@ static irqreturn_t rcar_dmac_isr_channel_thread(int irq, void *dev)
 		dma_cookie_complete(&desc->async_tx);
 		list_del(&desc->node);
 
-		if (desc->async_tx.callback) {
+		dmaengine_desc_get_callback(&desc->async_tx, &cb);
+		if (dmaengine_desc_callback_valid(&cb)) {
 			spin_unlock_irq(&chan->lock);
 			/*
 			 * We own the only reference to this descriptor, we can
 			 * safely dereference it without holding the channel
 			 * lock.
 			 */
-			desc->async_tx.callback(desc->async_tx.callback_param);
+			dmaengine_desc_callback_invoke(&cb, NULL);
 			spin_lock_irq(&chan->lock);
 		}
 
diff --git a/drivers/dma/sh/shdma-base.c b/drivers/dma/sh/shdma-base.c
index 10fcabad80f3..12fa48e380cf 100644
--- a/drivers/dma/sh/shdma-base.c
+++ b/drivers/dma/sh/shdma-base.c
@@ -330,10 +330,11 @@ static dma_async_tx_callback __ld_cleanup(struct shdma_chan *schan, bool all)
 	bool head_acked = false;
 	dma_cookie_t cookie = 0;
 	dma_async_tx_callback callback = NULL;
-	void *param = NULL;
+	struct dmaengine_desc_callback cb;
 	unsigned long flags;
 	LIST_HEAD(cyclic_list);
 
+	memset(&cb, 0, sizeof(cb));
 	spin_lock_irqsave(&schan->chan_lock, flags);
 	list_for_each_entry_safe(desc, _desc, &schan->ld_queue, node) {
 		struct dma_async_tx_descriptor *tx = &desc->async_tx;
@@ -367,8 +368,8 @@ static dma_async_tx_callback __ld_cleanup(struct shdma_chan *schan, bool all)
 		/* Call callback on the last chunk */
 		if (desc->mark == DESC_COMPLETED && tx->callback) {
 			desc->mark = DESC_WAITING;
+			dmaengine_desc_get_callback(tx, &cb);
 			callback = tx->callback;
-			param = tx->callback_param;
 			dev_dbg(schan->dev, "descriptor #%d@%p on %d callback\n",
 				tx->cookie, tx, schan->id);
 			BUG_ON(desc->chunks != 1);
@@ -430,8 +431,7 @@ static dma_async_tx_callback __ld_cleanup(struct shdma_chan *schan, bool all)
 
 	spin_unlock_irqrestore(&schan->chan_lock, flags);
 
-	if (callback)
-		callback(param);
+	dmaengine_desc_callback_invoke(&cb, NULL);
 
 	return callback;
 }
@@ -885,9 +885,9 @@ bool shdma_reset(struct shdma_dev *sdev)
 		/* Complete all  */
 		list_for_each_entry(sdesc, &dl, node) {
 			struct dma_async_tx_descriptor *tx = &sdesc->async_tx;
+
 			sdesc->mark = DESC_IDLE;
-			if (tx->callback)
-				tx->callback(tx->callback_param);
+			dmaengine_desc_get_callback_invoke(tx, NULL);
 		}
 
 		spin_lock(&schan->chan_lock);
diff --git a/drivers/dma/sirf-dma.c b/drivers/dma/sirf-dma.c
index d8bc3f2a71db..8f62edad51be 100644
--- a/drivers/dma/sirf-dma.c
+++ b/drivers/dma/sirf-dma.c
@@ -360,9 +360,7 @@ static void sirfsoc_dma_process_completed(struct sirfsoc_dma *sdma)
 			list_for_each_entry(sdesc, &list, node) {
 				desc = &sdesc->desc;
 
-				if (desc->callback)
-					desc->callback(desc->callback_param);
-
+				dmaengine_desc_get_callback_invoke(desc, NULL);
 				last_cookie = desc->cookie;
 				dma_run_dependencies(desc);
 			}
@@ -388,8 +386,7 @@ static void sirfsoc_dma_process_completed(struct sirfsoc_dma *sdma)
 
 			desc = &sdesc->desc;
 			while (happened_cyclic != schan->completed_cyclic) {
-				if (desc->callback)
-					desc->callback(desc->callback_param);
+				dmaengine_desc_get_callback_invoke(desc, NULL);
 				schan->completed_cyclic++;
 			}
 		}
@@ -869,7 +866,7 @@ static int sirfsoc_dma_probe(struct platform_device *op)
 	}
 
 	sdma->irq = irq_of_parse_and_map(dn, 0);
-	if (sdma->irq == NO_IRQ) {
+	if (!sdma->irq) {
 		dev_err(dev, "Error mapping IRQ!\n");
 		return -EINVAL;
 	}
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index 8b18e44a02d5..8684d11b29bb 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -874,7 +874,7 @@ static void d40_log_lli_to_lcxa(struct d40_chan *chan, struct d40_desc *desc)
 	}
 
 	if (curr_lcla < 0)
-		goto out;
+		goto set_current;
 
 	for (; lli_current < lli_len; lli_current++) {
 		unsigned int lcla_offset = chan->phy_chan->num * 1024 +
@@ -925,8 +925,7 @@ static void d40_log_lli_to_lcxa(struct d40_chan *chan, struct d40_desc *desc)
 			break;
 		}
 	}
-
-out:
+ set_current:
 	desc->lli_current = lli_current;
 }
 
@@ -941,15 +940,7 @@ static void d40_desc_load(struct d40_chan *d40c, struct d40_desc *d40d)
 
 static struct d40_desc *d40_first_active_get(struct d40_chan *d40c)
 {
-	struct d40_desc *d;
-
-	if (list_empty(&d40c->active))
-		return NULL;
-
-	d = list_first_entry(&d40c->active,
-			     struct d40_desc,
-			     node);
-	return d;
+	return list_first_entry_or_null(&d40c->active, struct d40_desc, node);
 }
 
 /* remove desc from current queue and add it to the pending_queue */
@@ -962,36 +953,18 @@ static void d40_desc_queue(struct d40_chan *d40c, struct d40_desc *desc)
 
 static struct d40_desc *d40_first_pending(struct d40_chan *d40c)
 {
-	struct d40_desc *d;
-
-	if (list_empty(&d40c->pending_queue))
-		return NULL;
-
-	d = list_first_entry(&d40c->pending_queue,
-			     struct d40_desc,
-			     node);
-	return d;
+	return list_first_entry_or_null(&d40c->pending_queue, struct d40_desc,
+					node);
 }
 
 static struct d40_desc *d40_first_queued(struct d40_chan *d40c)
 {
-	struct d40_desc *d;
-
-	if (list_empty(&d40c->queue))
-		return NULL;
-
-	d = list_first_entry(&d40c->queue,
-			     struct d40_desc,
-			     node);
-	return d;
+	return list_first_entry_or_null(&d40c->queue, struct d40_desc, node);
 }
 
 static struct d40_desc *d40_first_done(struct d40_chan *d40c)
 {
-	if (list_empty(&d40c->done))
-		return NULL;
-
-	return list_first_entry(&d40c->done, struct d40_desc, node);
+	return list_first_entry_or_null(&d40c->done, struct d40_desc, node);
 }
 
 static int d40_psize_2_burst_size(bool is_log, int psize)
@@ -1083,7 +1056,7 @@ static int __d40_execute_command_phy(struct d40_chan *d40c,
 			D40_CHAN_POS(d40c->phy_chan->num);
 
 		if (status == D40_DMA_SUSPENDED || status == D40_DMA_STOP)
-			goto done;
+			goto unlock;
 	}
 
 	wmask = 0xffffffff & ~(D40_CHAN_POS_MASK(d40c->phy_chan->num));
@@ -1119,7 +1092,7 @@ static int __d40_execute_command_phy(struct d40_chan *d40c,
 		}
 
 	}
-done:
+ unlock:
 	spin_unlock_irqrestore(&d40c->base->execmd_lock, flags);
 	return ret;
 }
@@ -1596,8 +1569,7 @@ static void dma_tasklet(unsigned long data)
 	struct d40_desc *d40d;
 	unsigned long flags;
 	bool callback_active;
-	dma_async_tx_callback callback;
-	void *callback_param;
+	struct dmaengine_desc_callback cb;
 
 	spin_lock_irqsave(&d40c->lock, flags);
 
@@ -1607,7 +1579,7 @@ static void dma_tasklet(unsigned long data)
 		/* Check if we have reached here for cyclic job */
 		d40d = d40_first_active_get(d40c);
 		if (d40d == NULL || !d40d->cyclic)
-			goto err;
+			goto check_pending_tx;
 	}
 
 	if (!d40d->cyclic)
@@ -1624,8 +1596,7 @@ static void dma_tasklet(unsigned long data)
 
 	/* Callback to client */
 	callback_active = !!(d40d->txd.flags & DMA_PREP_INTERRUPT);
-	callback = d40d->txd.callback;
-	callback_param = d40d->txd.callback_param;
+	dmaengine_desc_get_callback(&d40d->txd, &cb);
 
 	if (!d40d->cyclic) {
 		if (async_tx_test_ack(&d40d->txd)) {
@@ -1646,12 +1617,11 @@ static void dma_tasklet(unsigned long data)
 
 	spin_unlock_irqrestore(&d40c->lock, flags);
 
-	if (callback_active && callback)
-		callback(callback_param);
+	if (callback_active)
+		dmaengine_desc_callback_invoke(&cb, NULL);
 
 	return;
-
-err:
+ check_pending_tx:
 	/* Rescue manouver if receiving double interrupts */
 	if (d40c->pending_tx > 0)
 		d40c->pending_tx--;
@@ -1780,42 +1750,40 @@ static bool d40_alloc_mask_set(struct d40_phy_res *phy,
 		    phy->allocated_dst == D40_ALLOC_FREE) {
 			phy->allocated_dst = D40_ALLOC_PHY;
 			phy->allocated_src = D40_ALLOC_PHY;
-			goto found;
+			goto found_unlock;
 		} else
-			goto not_found;
+			goto not_found_unlock;
 	}
 
 	/* Logical channel */
 	if (is_src) {
 		if (phy->allocated_src == D40_ALLOC_PHY)
-			goto not_found;
+			goto not_found_unlock;
 
 		if (phy->allocated_src == D40_ALLOC_FREE)
 			phy->allocated_src = D40_ALLOC_LOG_FREE;
 
 		if (!(phy->allocated_src & BIT(log_event_line))) {
 			phy->allocated_src |= BIT(log_event_line);
-			goto found;
+			goto found_unlock;
 		} else
-			goto not_found;
+			goto not_found_unlock;
 	} else {
 		if (phy->allocated_dst == D40_ALLOC_PHY)
-			goto not_found;
+			goto not_found_unlock;
 
 		if (phy->allocated_dst == D40_ALLOC_FREE)
 			phy->allocated_dst = D40_ALLOC_LOG_FREE;
 
 		if (!(phy->allocated_dst & BIT(log_event_line))) {
 			phy->allocated_dst |= BIT(log_event_line);
-			goto found;
-		} else
-			goto not_found;
+			goto found_unlock;
+		}
 	}
-
-not_found:
+ not_found_unlock:
 	spin_unlock_irqrestore(&phy->lock, flags);
 	return false;
-found:
+ found_unlock:
 	spin_unlock_irqrestore(&phy->lock, flags);
 	return true;
 }
@@ -1831,7 +1799,7 @@ static bool d40_alloc_mask_free(struct d40_phy_res *phy, bool is_src,
 		phy->allocated_dst = D40_ALLOC_FREE;
 		phy->allocated_src = D40_ALLOC_FREE;
 		is_free = true;
-		goto out;
+		goto unlock;
 	}
 
 	/* Logical channel */
@@ -1847,8 +1815,7 @@ static bool d40_alloc_mask_free(struct d40_phy_res *phy, bool is_src,
 
 	is_free = ((phy->allocated_src | phy->allocated_dst) ==
 		   D40_ALLOC_FREE);
-
-out:
+ unlock:
 	spin_unlock_irqrestore(&phy->lock, flags);
 
 	return is_free;
@@ -2047,7 +2014,7 @@ static int d40_free_dma(struct d40_chan *d40c)
 	res = d40_channel_execute_command(d40c, D40_DMA_STOP);
 	if (res) {
 		chan_err(d40c, "stop failed\n");
-		goto out;
+		goto mark_last_busy;
 	}
 
 	d40_alloc_mask_free(phy, is_src, chan_is_logical(d40c) ? event : 0);
@@ -2065,8 +2032,7 @@ static int d40_free_dma(struct d40_chan *d40c)
 	d40c->busy = false;
 	d40c->phy_chan = NULL;
 	d40c->configured = false;
-out:
-
+ mark_last_busy:
 	pm_runtime_mark_last_busy(d40c->base->dev);
 	pm_runtime_put_autosuspend(d40c->base->dev);
 	return res;
@@ -2094,8 +2060,7 @@ static bool d40_is_paused(struct d40_chan *d40c)
 			D40_CHAN_POS(d40c->phy_chan->num);
 		if (status == D40_DMA_SUSPENDED || status == D40_DMA_STOP)
 			is_paused = true;
-
-		goto _exit;
+		goto unlock;
 	}
 
 	if (d40c->dma_cfg.dir == DMA_MEM_TO_DEV ||
@@ -2105,7 +2070,7 @@ static bool d40_is_paused(struct d40_chan *d40c)
 		status = readl(chanbase + D40_CHAN_REG_SSLNK);
 	} else {
 		chan_err(d40c, "Unknown direction\n");
-		goto _exit;
+		goto unlock;
 	}
 
 	status = (status & D40_EVENTLINE_MASK(event)) >>
@@ -2113,7 +2078,7 @@ static bool d40_is_paused(struct d40_chan *d40c)
 
 	if (status != D40_DMA_RUN)
 		is_paused = true;
-_exit:
+ unlock:
 	spin_unlock_irqrestore(&d40c->lock, flags);
 	return is_paused;
 
@@ -2198,7 +2163,7 @@ static struct d40_desc *
 d40_prep_desc(struct d40_chan *chan, struct scatterlist *sg,
 	      unsigned int sg_len, unsigned long dma_flags)
 {
-	struct stedma40_chan_cfg *cfg = &chan->dma_cfg;
+	struct stedma40_chan_cfg *cfg;
 	struct d40_desc *desc;
 	int ret;
 
@@ -2206,17 +2171,18 @@ d40_prep_desc(struct d40_chan *chan, struct scatterlist *sg,
 	if (!desc)
 		return NULL;
 
+	cfg = &chan->dma_cfg;
 	desc->lli_len = d40_sg_2_dmalen(sg, sg_len, cfg->src_info.data_width,
 					cfg->dst_info.data_width);
 	if (desc->lli_len < 0) {
 		chan_err(chan, "Unaligned size\n");
-		goto err;
+		goto free_desc;
 	}
 
 	ret = d40_pool_lli_alloc(chan, desc, desc->lli_len);
 	if (ret < 0) {
 		chan_err(chan, "Could not allocate lli\n");
-		goto err;
+		goto free_desc;
 	}
 
 	desc->lli_current = 0;
@@ -2226,8 +2192,7 @@ d40_prep_desc(struct d40_chan *chan, struct scatterlist *sg,
 	dma_async_tx_descriptor_init(&desc->txd, &chan->chan);
 
 	return desc;
-
-err:
+ free_desc:
 	d40_desc_free(chan, desc);
 	return NULL;
 }
@@ -2238,8 +2203,8 @@ d40_prep_sg(struct dma_chan *dchan, struct scatterlist *sg_src,
 	    enum dma_transfer_direction direction, unsigned long dma_flags)
 {
 	struct d40_chan *chan = container_of(dchan, struct d40_chan, chan);
-	dma_addr_t src_dev_addr = 0;
-	dma_addr_t dst_dev_addr = 0;
+	dma_addr_t src_dev_addr;
+	dma_addr_t dst_dev_addr;
 	struct d40_desc *desc;
 	unsigned long flags;
 	int ret;
@@ -2253,11 +2218,13 @@ d40_prep_sg(struct dma_chan *dchan, struct scatterlist *sg_src,
 
 	desc = d40_prep_desc(chan, sg_src, sg_len, dma_flags);
 	if (desc == NULL)
-		goto err;
+		goto unlock;
 
 	if (sg_next(&sg_src[sg_len - 1]) == sg_src)
 		desc->cyclic = true;
 
+	src_dev_addr = 0;
+	dst_dev_addr = 0;
 	if (direction == DMA_DEV_TO_MEM)
 		src_dev_addr = chan->runtime_addr;
 	else if (direction == DMA_MEM_TO_DEV)
@@ -2273,7 +2240,7 @@ d40_prep_sg(struct dma_chan *dchan, struct scatterlist *sg_src,
 	if (ret) {
 		chan_err(chan, "Failed to prepare %s sg job: %d\n",
 			 chan_is_logical(chan) ? "log" : "phy", ret);
-		goto err;
+		goto free_desc;
 	}
 
 	/*
@@ -2285,10 +2252,9 @@ d40_prep_sg(struct dma_chan *dchan, struct scatterlist *sg_src,
 	spin_unlock_irqrestore(&chan->lock, flags);
 
 	return &desc->txd;
-
-err:
-	if (desc)
-		d40_desc_free(chan, desc);
+ free_desc:
+	d40_desc_free(chan, desc);
+ unlock:
 	spin_unlock_irqrestore(&chan->lock, flags);
 	return NULL;
 }
@@ -2426,7 +2392,7 @@ static int d40_alloc_chan_resources(struct dma_chan *chan)
 		err = d40_config_memcpy(d40c);
 		if (err) {
 			chan_err(d40c, "Failed to configure memcpy channel\n");
-			goto fail;
+			goto mark_last_busy;
 		}
 	}
 
@@ -2434,7 +2400,7 @@ static int d40_alloc_chan_resources(struct dma_chan *chan)
 	if (err) {
 		chan_err(d40c, "Failed to allocate channel\n");
 		d40c->configured = false;
-		goto fail;
+		goto mark_last_busy;
 	}
 
 	pm_runtime_get_sync(d40c->base->dev);
@@ -2468,7 +2434,7 @@ static int d40_alloc_chan_resources(struct dma_chan *chan)
 	 */
 	if (is_free_phy)
 		d40_config_write(d40c);
-fail:
+ mark_last_busy:
 	pm_runtime_mark_last_busy(d40c->base->dev);
 	pm_runtime_put_autosuspend(d40c->base->dev);
 	spin_unlock_irqrestore(&d40c->lock, flags);
@@ -2891,7 +2857,7 @@ static int __init d40_dmaengine_init(struct d40_base *base,
 
 	if (err) {
 		d40_err(base->dev, "Failed to register slave channels\n");
-		goto failure1;
+		goto exit;
 	}
 
 	d40_chan_init(base, &base->dma_memcpy, base->log_chans,
@@ -2908,7 +2874,7 @@ static int __init d40_dmaengine_init(struct d40_base *base,
 	if (err) {
 		d40_err(base->dev,
 			"Failed to register memcpy only channels\n");
-		goto failure2;
+		goto unregister_slave;
 	}
 
 	d40_chan_init(base, &base->dma_both, base->phy_chans,
@@ -2926,14 +2892,14 @@ static int __init d40_dmaengine_init(struct d40_base *base,
 	if (err) {
 		d40_err(base->dev,
 			"Failed to register logical and physical capable channels\n");
-		goto failure3;
+		goto unregister_memcpy;
 	}
 	return 0;
-failure3:
+ unregister_memcpy:
 	dma_async_device_unregister(&base->dma_memcpy);
-failure2:
+ unregister_slave:
 	dma_async_device_unregister(&base->dma_slave);
-failure1:
+ exit:
 	return err;
 }
 
@@ -3144,11 +3110,11 @@ static int __init d40_phy_res_init(struct d40_base *base)
 static struct d40_base * __init d40_hw_detect_init(struct platform_device *pdev)
 {
 	struct stedma40_platform_data *plat_data = dev_get_platdata(&pdev->dev);
-	struct clk *clk = NULL;
-	void __iomem *virtbase = NULL;
-	struct resource *res = NULL;
-	struct d40_base *base = NULL;
-	int num_log_chans = 0;
+	struct clk *clk;
+	void __iomem *virtbase;
+	struct resource *res;
+	struct d40_base *base;
+	int num_log_chans;
 	int num_phy_chans;
 	int num_memcpy_chans;
 	int clk_ret = -EINVAL;
@@ -3160,27 +3126,27 @@ static struct d40_base * __init d40_hw_detect_init(struct platform_device *pdev)
 	clk = clk_get(&pdev->dev, NULL);
 	if (IS_ERR(clk)) {
 		d40_err(&pdev->dev, "No matching clock found\n");
-		goto failure;
+		goto check_prepare_enabled;
 	}
 
 	clk_ret = clk_prepare_enable(clk);
 	if (clk_ret) {
 		d40_err(&pdev->dev, "Failed to prepare/enable clock\n");
-		goto failure;
+		goto disable_unprepare;
 	}
 
 	/* Get IO for DMAC base address */
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "base");
 	if (!res)
-		goto failure;
+		goto disable_unprepare;
 
 	if (request_mem_region(res->start, resource_size(res),
 			       D40_NAME " I/O base") == NULL)
-		goto failure;
+		goto release_region;
 
 	virtbase = ioremap(res->start, resource_size(res));
 	if (!virtbase)
-		goto failure;
+		goto release_region;
 
 	/* This is just a regular AMBA PrimeCell ID actually */
 	for (pid = 0, i = 0; i < 4; i++)
@@ -3192,13 +3158,13 @@ static struct d40_base * __init d40_hw_detect_init(struct platform_device *pdev)
 
 	if (cid != AMBA_CID) {
 		d40_err(&pdev->dev, "Unknown hardware! No PrimeCell ID\n");
-		goto failure;
+		goto unmap_io;
 	}
 	if (AMBA_MANF_BITS(pid) != AMBA_VENDOR_ST) {
 		d40_err(&pdev->dev, "Unknown designer! Got %x wanted %x\n",
 			AMBA_MANF_BITS(pid),
 			AMBA_VENDOR_ST);
-		goto failure;
+		goto unmap_io;
 	}
 	/*
 	 * HW revision:
@@ -3212,7 +3178,7 @@ static struct d40_base * __init d40_hw_detect_init(struct platform_device *pdev)
 	rev = AMBA_REV_BITS(pid);
 	if (rev < 2) {
 		d40_err(&pdev->dev, "hardware revision: %d is not supported", rev);
-		goto failure;
+		goto unmap_io;
 	}
 
 	/* The number of physical channels on this HW */
@@ -3238,7 +3204,7 @@ static struct d40_base * __init d40_hw_detect_init(struct platform_device *pdev)
 		       sizeof(struct d40_chan), GFP_KERNEL);
 
 	if (base == NULL)
-		goto failure;
+		goto unmap_io;
 
 	base->rev = rev;
 	base->clk = clk;
@@ -3283,65 +3249,66 @@ static struct d40_base * __init d40_hw_detect_init(struct platform_device *pdev)
 		base->gen_dmac.init_reg_size = ARRAY_SIZE(dma_init_reg_v4a);
 	}
 
-	base->phy_res = kzalloc(num_phy_chans * sizeof(struct d40_phy_res),
+	base->phy_res = kcalloc(num_phy_chans,
+				sizeof(*base->phy_res),
 				GFP_KERNEL);
 	if (!base->phy_res)
-		goto failure;
+		goto free_base;
 
-	base->lookup_phy_chans = kzalloc(num_phy_chans *
-					 sizeof(struct d40_chan *),
+	base->lookup_phy_chans = kcalloc(num_phy_chans,
+					 sizeof(*base->lookup_phy_chans),
 					 GFP_KERNEL);
 	if (!base->lookup_phy_chans)
-		goto failure;
+		goto free_phy_res;
 
-	base->lookup_log_chans = kzalloc(num_log_chans *
-					 sizeof(struct d40_chan *),
+	base->lookup_log_chans = kcalloc(num_log_chans,
+					 sizeof(*base->lookup_log_chans),
 					 GFP_KERNEL);
 	if (!base->lookup_log_chans)
-		goto failure;
+		goto free_phy_chans;
 
-	base->reg_val_backup_chan = kmalloc(base->num_phy_chans *
-					    sizeof(d40_backup_regs_chan),
-					    GFP_KERNEL);
+	base->reg_val_backup_chan = kmalloc_array(base->num_phy_chans,
+						  sizeof(d40_backup_regs_chan),
+						  GFP_KERNEL);
 	if (!base->reg_val_backup_chan)
-		goto failure;
+		goto free_log_chans;
 
-	base->lcla_pool.alloc_map =
-		kzalloc(num_phy_chans * sizeof(struct d40_desc *)
-			* D40_LCLA_LINK_PER_EVENT_GRP, GFP_KERNEL);
+	base->lcla_pool.alloc_map = kcalloc(num_phy_chans
+					    * D40_LCLA_LINK_PER_EVENT_GRP,
+					    sizeof(*base->lcla_pool.alloc_map),
+					    GFP_KERNEL);
 	if (!base->lcla_pool.alloc_map)
-		goto failure;
+		goto free_backup_chan;
 
 	base->desc_slab = kmem_cache_create(D40_NAME, sizeof(struct d40_desc),
 					    0, SLAB_HWCACHE_ALIGN,
 					    NULL);
 	if (base->desc_slab == NULL)
-		goto failure;
+		goto free_map;
 
 	return base;
-
-failure:
+ free_map:
+	kfree(base->lcla_pool.alloc_map);
+ free_backup_chan:
+	kfree(base->reg_val_backup_chan);
+ free_log_chans:
+	kfree(base->lookup_log_chans);
+ free_phy_chans:
+	kfree(base->lookup_phy_chans);
+ free_phy_res:
+	kfree(base->phy_res);
+ free_base:
+	kfree(base);
+ unmap_io:
+	iounmap(virtbase);
+ release_region:
+	release_mem_region(res->start, resource_size(res));
+ check_prepare_enabled:
 	if (!clk_ret)
+ disable_unprepare:
 		clk_disable_unprepare(clk);
 	if (!IS_ERR(clk))
 		clk_put(clk);
-	if (virtbase)
-		iounmap(virtbase);
-	if (res)
-		release_mem_region(res->start,
-				   resource_size(res));
-	if (virtbase)
-		iounmap(virtbase);
-
-	if (base) {
-		kfree(base->lcla_pool.alloc_map);
-		kfree(base->reg_val_backup_chan);
-		kfree(base->lookup_log_chans);
-		kfree(base->lookup_phy_chans);
-		kfree(base->phy_res);
-		kfree(base);
-	}
-
 	return NULL;
 }
 
@@ -3404,20 +3371,18 @@ static int __init d40_lcla_allocate(struct d40_base *base)
 	struct d40_lcla_pool *pool = &base->lcla_pool;
 	unsigned long *page_list;
 	int i, j;
-	int ret = 0;
+	int ret;
 
 	/*
 	 * This is somewhat ugly. We need 8192 bytes that are 18 bit aligned,
 	 * To full fill this hardware requirement without wasting 256 kb
 	 * we allocate pages until we get an aligned one.
 	 */
-	page_list = kmalloc(sizeof(unsigned long) * MAX_LCLA_ALLOC_ATTEMPTS,
-			    GFP_KERNEL);
-
-	if (!page_list) {
-		ret = -ENOMEM;
-		goto failure;
-	}
+	page_list = kmalloc_array(MAX_LCLA_ALLOC_ATTEMPTS,
+				  sizeof(*page_list),
+				  GFP_KERNEL);
+	if (!page_list)
+		return -ENOMEM;
 
 	/* Calculating how many pages that are required */
 	base->lcla_pool.pages = SZ_1K * base->num_phy_chans / PAGE_SIZE;
@@ -3433,7 +3398,7 @@ static int __init d40_lcla_allocate(struct d40_base *base)
 
 			for (j = 0; j < i; j++)
 				free_pages(page_list[j], base->lcla_pool.pages);
-			goto failure;
+			goto free_page_list;
 		}
 
 		if ((virt_to_phys((void *)page_list[i]) &
@@ -3460,7 +3425,7 @@ static int __init d40_lcla_allocate(struct d40_base *base)
 							 GFP_KERNEL);
 		if (!base->lcla_pool.base_unaligned) {
 			ret = -ENOMEM;
-			goto failure;
+			goto free_page_list;
 		}
 
 		base->lcla_pool.base = PTR_ALIGN(base->lcla_pool.base_unaligned,
@@ -3473,12 +3438,13 @@ static int __init d40_lcla_allocate(struct d40_base *base)
 	if (dma_mapping_error(base->dev, pool->dma_addr)) {
 		pool->dma_addr = 0;
 		ret = -ENOMEM;
-		goto failure;
+		goto free_page_list;
 	}
 
 	writel(virt_to_phys(base->lcla_pool.base),
 	       base->virtbase + D40_DREG_LCLA);
-failure:
+	ret = 0;
+ free_page_list:
 	kfree(page_list);
 	return ret;
 }
@@ -3490,9 +3456,7 @@ static int __init d40_of_probe(struct platform_device *pdev,
 	int num_phy = 0, num_memcpy = 0, num_disabled = 0;
 	const __be32 *list;
 
-	pdata = devm_kzalloc(&pdev->dev,
-			     sizeof(struct stedma40_platform_data),
-			     GFP_KERNEL);
+	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
 	if (!pdata)
 		return -ENOMEM;
 
@@ -3574,7 +3538,7 @@ static int __init d40_probe(struct platform_device *pdev)
 	if (!res) {
 		ret = -ENOENT;
 		d40_err(&pdev->dev, "No \"lcpa\" memory resource\n");
-		goto failure;
+		goto destroy_cache;
 	}
 	base->lcpa_size = resource_size(res);
 	base->phy_lcpa = res->start;
@@ -3583,7 +3547,7 @@ static int __init d40_probe(struct platform_device *pdev)
 			       D40_NAME " I/O lcpa") == NULL) {
 		ret = -EBUSY;
 		d40_err(&pdev->dev, "Failed to request LCPA region %pR\n", res);
-		goto failure;
+		goto destroy_cache;
 	}
 
 	/* We make use of ESRAM memory for this. */
@@ -3599,7 +3563,7 @@ static int __init d40_probe(struct platform_device *pdev)
 	if (!base->lcpa_base) {
 		ret = -ENOMEM;
 		d40_err(&pdev->dev, "Failed to ioremap LCPA region\n");
-		goto failure;
+		goto destroy_cache;
 	}
 	/* If lcla has to be located in ESRAM we don't need to allocate */
 	if (base->plat_data->use_esram_lcla) {
@@ -3609,14 +3573,14 @@ static int __init d40_probe(struct platform_device *pdev)
 			ret = -ENOENT;
 			d40_err(&pdev->dev,
 				"No \"lcla_esram\" memory resource\n");
-			goto failure;
+			goto destroy_cache;
 		}
 		base->lcla_pool.base = ioremap(res->start,
 						resource_size(res));
 		if (!base->lcla_pool.base) {
 			ret = -ENOMEM;
 			d40_err(&pdev->dev, "Failed to ioremap LCLA region\n");
-			goto failure;
+			goto destroy_cache;
 		}
 		writel(res->start, base->virtbase + D40_DREG_LCLA);
 
@@ -3624,7 +3588,7 @@ static int __init d40_probe(struct platform_device *pdev)
 		ret = d40_lcla_allocate(base);
 		if (ret) {
 			d40_err(&pdev->dev, "Failed to allocate LCLA area\n");
-			goto failure;
+			goto destroy_cache;
 		}
 	}
 
@@ -3635,7 +3599,7 @@ static int __init d40_probe(struct platform_device *pdev)
 	ret = request_irq(base->irq, d40_handle_interrupt, 0, D40_NAME, base);
 	if (ret) {
 		d40_err(&pdev->dev, "No IRQ defined\n");
-		goto failure;
+		goto destroy_cache;
 	}
 
 	if (base->plat_data->use_esram_lcla) {
@@ -3645,7 +3609,7 @@ static int __init d40_probe(struct platform_device *pdev)
 			d40_err(&pdev->dev, "Failed to get lcpa_regulator\n");
 			ret = PTR_ERR(base->lcpa_regulator);
 			base->lcpa_regulator = NULL;
-			goto failure;
+			goto destroy_cache;
 		}
 
 		ret = regulator_enable(base->lcpa_regulator);
@@ -3654,7 +3618,7 @@ static int __init d40_probe(struct platform_device *pdev)
 				"Failed to enable lcpa_regulator\n");
 			regulator_put(base->lcpa_regulator);
 			base->lcpa_regulator = NULL;
-			goto failure;
+			goto destroy_cache;
 		}
 	}
 
@@ -3669,13 +3633,13 @@ static int __init d40_probe(struct platform_device *pdev)
 
 	ret = d40_dmaengine_init(base, num_reserved_chans);
 	if (ret)
-		goto failure;
+		goto destroy_cache;
 
 	base->dev->dma_parms = &base->dma_parms;
 	ret = dma_set_max_seg_size(base->dev, STEDMA40_MAX_SEG_SIZE);
 	if (ret) {
 		d40_err(&pdev->dev, "Failed to set dma max seg size\n");
-		goto failure;
+		goto destroy_cache;
 	}
 
 	d40_hw_init(base);
@@ -3689,8 +3653,7 @@ static int __init d40_probe(struct platform_device *pdev)
 
 	dev_info(base->dev, "initialized\n");
 	return 0;
-
-failure:
+ destroy_cache:
 	kmem_cache_destroy(base->desc_slab);
 	if (base->virtbase)
 		iounmap(base->virtbase);
@@ -3732,7 +3695,7 @@ failure:
 	kfree(base->lookup_phy_chans);
 	kfree(base->phy_res);
 	kfree(base);
-report_failure:
+ report_failure:
 	d40_err(&pdev->dev, "probe failed\n");
 	return ret;
 }
diff --git a/drivers/dma/stm32-dma.c b/drivers/dma/stm32-dma.c
index 047476a1383d..307547f4848d 100644
--- a/drivers/dma/stm32-dma.c
+++ b/drivers/dma/stm32-dma.c
@@ -954,7 +954,7 @@ static void stm32_dma_desc_free(struct virt_dma_desc *vdesc)
 	kfree(container_of(vdesc, struct stm32_dma_desc, vdesc));
 }
 
-void stm32_dma_set_config(struct stm32_dma_chan *chan,
+static void stm32_dma_set_config(struct stm32_dma_chan *chan,
 			  struct stm32_dma_cfg *cfg)
 {
 	stm32_dma_clear_reg(&chan->chan_reg);
diff --git a/drivers/dma/sun6i-dma.c b/drivers/dma/sun6i-dma.c
index 3835fcde3545..83461994e418 100644
--- a/drivers/dma/sun6i-dma.c
+++ b/drivers/dma/sun6i-dma.c
@@ -1011,6 +1011,12 @@ static struct sun6i_dma_config sun8i_a23_dma_cfg = {
 	.nr_max_vchans   = 37,
 };
 
+static struct sun6i_dma_config sun8i_a83t_dma_cfg = {
+	.nr_max_channels = 8,
+	.nr_max_requests = 28,
+	.nr_max_vchans   = 39,
+};
+
 /*
  * The H3 has 12 physical channels, a maximum DRQ port id of 27,
  * and a total of 34 usable source and destination endpoints.
@@ -1025,6 +1031,7 @@ static struct sun6i_dma_config sun8i_h3_dma_cfg = {
 static const struct of_device_id sun6i_dma_match[] = {
 	{ .compatible = "allwinner,sun6i-a31-dma", .data = &sun6i_a31_dma_cfg },
 	{ .compatible = "allwinner,sun8i-a23-dma", .data = &sun8i_a23_dma_cfg },
+	{ .compatible = "allwinner,sun8i-a83t-dma", .data = &sun8i_a83t_dma_cfg },
 	{ .compatible = "allwinner,sun8i-h3-dma", .data = &sun8i_h3_dma_cfg },
 	{ /* sentinel */ }
 };
diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c
index 6ab9eb98588a..3722b9d8d9fe 100644
--- a/drivers/dma/tegra20-apb-dma.c
+++ b/drivers/dma/tegra20-apb-dma.c
@@ -655,8 +655,7 @@ static void handle_cont_sngl_cycle_dma_done(struct tegra_dma_channel *tdc,
 static void tegra_dma_tasklet(unsigned long data)
 {
 	struct tegra_dma_channel *tdc = (struct tegra_dma_channel *)data;
-	dma_async_tx_callback callback = NULL;
-	void *callback_param = NULL;
+	struct dmaengine_desc_callback cb;
 	struct tegra_dma_desc *dma_desc;
 	unsigned long flags;
 	int cb_count;
@@ -666,13 +665,12 @@ static void tegra_dma_tasklet(unsigned long data)
 		dma_desc  = list_first_entry(&tdc->cb_desc,
 					typeof(*dma_desc), cb_node);
 		list_del(&dma_desc->cb_node);
-		callback = dma_desc->txd.callback;
-		callback_param = dma_desc->txd.callback_param;
+		dmaengine_desc_get_callback(&dma_desc->txd, &cb);
 		cb_count = dma_desc->cb_count;
 		dma_desc->cb_count = 0;
 		spin_unlock_irqrestore(&tdc->lock, flags);
-		while (cb_count-- && callback)
-			callback(callback_param);
+		while (cb_count--)
+			dmaengine_desc_callback_invoke(&cb, NULL);
 		spin_lock_irqsave(&tdc->lock, flags);
 	}
 	spin_unlock_irqrestore(&tdc->lock, flags);
diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c
index c4b121c4559d..b10cbaa82ff5 100644
--- a/drivers/dma/tegra210-adma.c
+++ b/drivers/dma/tegra210-adma.c
@@ -670,7 +670,6 @@ static int tegra_adma_probe(struct platform_device *pdev)
 	const struct tegra_adma_chip_data *cdata;
 	struct tegra_adma *tdma;
 	struct resource	*res;
-	struct clk *clk;
 	int ret, i;
 
 	cdata = of_device_get_match_data(&pdev->dev);
@@ -697,18 +696,9 @@ static int tegra_adma_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	clk = clk_get(&pdev->dev, "d_audio");
-	if (IS_ERR(clk)) {
-		dev_err(&pdev->dev, "ADMA clock not found\n");
-		ret = PTR_ERR(clk);
-		goto clk_destroy;
-	}
-
-	ret = pm_clk_add_clk(&pdev->dev, clk);
-	if (ret) {
-		clk_put(clk);
+	ret = of_pm_clk_add_clk(&pdev->dev, "d_audio");
+	if (ret)
 		goto clk_destroy;
-	}
 
 	pm_runtime_enable(&pdev->dev);
 
diff --git a/drivers/dma/ti-dma-crossbar.c b/drivers/dma/ti-dma-crossbar.c
index 5ae294b256a7..3f24aeb48c0e 100644
--- a/drivers/dma/ti-dma-crossbar.c
+++ b/drivers/dma/ti-dma-crossbar.c
@@ -18,15 +18,19 @@
 
 #define TI_XBAR_DRA7		0
 #define TI_XBAR_AM335X		1
+static const u32 ti_xbar_type[] = {
+	[TI_XBAR_DRA7] = TI_XBAR_DRA7,
+	[TI_XBAR_AM335X] = TI_XBAR_AM335X,
+};
 
 static const struct of_device_id ti_dma_xbar_match[] = {
 	{
 		.compatible = "ti,dra7-dma-crossbar",
-		.data = (void *)TI_XBAR_DRA7,
+		.data = &ti_xbar_type[TI_XBAR_DRA7],
 	},
 	{
 		.compatible = "ti,am335x-edma-crossbar",
-		.data = (void *)TI_XBAR_AM335X,
+		.data = &ti_xbar_type[TI_XBAR_AM335X],
 	},
 	{},
 };
@@ -190,9 +194,6 @@ static int ti_am335x_xbar_probe(struct platform_device *pdev)
 #define TI_DRA7_XBAR_OUTPUTS	127
 #define TI_DRA7_XBAR_INPUTS	256
 
-#define TI_XBAR_EDMA_OFFSET	0
-#define TI_XBAR_SDMA_OFFSET	1
-
 struct ti_dra7_xbar_data {
 	void __iomem *iomem;
 
@@ -280,18 +281,25 @@ static void *ti_dra7_xbar_route_allocate(struct of_phandle_args *dma_spec,
 	return map;
 }
 
+#define TI_XBAR_EDMA_OFFSET	0
+#define TI_XBAR_SDMA_OFFSET	1
+static const u32 ti_dma_offset[] = {
+	[TI_XBAR_EDMA_OFFSET] = 0,
+	[TI_XBAR_SDMA_OFFSET] = 1,
+};
+
 static const struct of_device_id ti_dra7_master_match[] = {
 	{
 		.compatible = "ti,omap4430-sdma",
-		.data = (void *)TI_XBAR_SDMA_OFFSET,
+		.data = &ti_dma_offset[TI_XBAR_SDMA_OFFSET],
 	},
 	{
 		.compatible = "ti,edma3",
-		.data = (void *)TI_XBAR_EDMA_OFFSET,
+		.data = &ti_dma_offset[TI_XBAR_EDMA_OFFSET],
 	},
 	{
 		.compatible = "ti,edma3-tpcc",
-		.data = (void *)TI_XBAR_EDMA_OFFSET,
+		.data = &ti_dma_offset[TI_XBAR_EDMA_OFFSET],
 	},
 	{},
 };
@@ -311,7 +319,7 @@ static int ti_dra7_xbar_probe(struct platform_device *pdev)
 	struct property *prop;
 	struct resource *res;
 	u32 safe_val;
-	size_t sz;
+	int sz;
 	void __iomem *iomem;
 	int i, ret;
 
@@ -395,7 +403,7 @@ static int ti_dra7_xbar_probe(struct platform_device *pdev)
 
 	xbar->dmarouter.dev = &pdev->dev;
 	xbar->dmarouter.route_free = ti_dra7_xbar_free;
-	xbar->dma_offset = (u32)match->data;
+	xbar->dma_offset = *(u32 *)match->data;
 
 	mutex_init(&xbar->mutex);
 	platform_set_drvdata(pdev, xbar);
@@ -428,7 +436,7 @@ static int ti_dma_xbar_probe(struct platform_device *pdev)
 	if (unlikely(!match))
 		return -EINVAL;
 
-	switch ((u32)match->data) {
+	switch (*(u32 *)match->data) {
 	case TI_XBAR_DRA7:
 		ret = ti_dra7_xbar_probe(pdev);
 		break;
diff --git a/drivers/dma/timb_dma.c b/drivers/dma/timb_dma.c
index e82745aa42a8..896bafb7a532 100644
--- a/drivers/dma/timb_dma.c
+++ b/drivers/dma/timb_dma.c
@@ -226,8 +226,7 @@ static void __td_start_dma(struct timb_dma_chan *td_chan)
 
 static void __td_finish(struct timb_dma_chan *td_chan)
 {
-	dma_async_tx_callback		callback;
-	void				*param;
+	struct dmaengine_desc_callback	cb;
 	struct dma_async_tx_descriptor	*txd;
 	struct timb_dma_desc		*td_desc;
 
@@ -252,8 +251,7 @@ static void __td_finish(struct timb_dma_chan *td_chan)
 	dma_cookie_complete(txd);
 	td_chan->ongoing = false;
 
-	callback = txd->callback;
-	param = txd->callback_param;
+	dmaengine_desc_get_callback(txd, &cb);
 
 	list_move(&td_desc->desc_node, &td_chan->free_list);
 
@@ -262,8 +260,7 @@ static void __td_finish(struct timb_dma_chan *td_chan)
 	 * The API requires that no submissions are done from a
 	 * callback, so we don't need to drop the lock here
 	 */
-	if (callback)
-		callback(param);
+	dmaengine_desc_callback_invoke(&cb, NULL);
 }
 
 static u32 __td_ier_mask(struct timb_dma *td)
diff --git a/drivers/dma/txx9dmac.c b/drivers/dma/txx9dmac.c
index 7632290e7c14..4d8c7b9078fd 100644
--- a/drivers/dma/txx9dmac.c
+++ b/drivers/dma/txx9dmac.c
@@ -403,16 +403,14 @@ static void
 txx9dmac_descriptor_complete(struct txx9dmac_chan *dc,
 			     struct txx9dmac_desc *desc)
 {
-	dma_async_tx_callback callback;
-	void *param;
+	struct dmaengine_desc_callback cb;
 	struct dma_async_tx_descriptor *txd = &desc->txd;
 
 	dev_vdbg(chan2dev(&dc->chan), "descriptor %u %p complete\n",
 		 txd->cookie, desc);
 
 	dma_cookie_complete(txd);
-	callback = txd->callback;
-	param = txd->callback_param;
+	dmaengine_desc_get_callback(txd, &cb);
 
 	txx9dmac_sync_desc_for_cpu(dc, desc);
 	list_splice_init(&desc->tx_list, &dc->free_list);
@@ -423,8 +421,7 @@ txx9dmac_descriptor_complete(struct txx9dmac_chan *dc,
 	 * The API requires that no submissions are done from a
 	 * callback, so we don't need to drop the lock here
 	 */
-	if (callback)
-		callback(param);
+	dmaengine_desc_callback_invoke(&cb, NULL);
 	dma_run_dependencies(txd);
 }
 
diff --git a/drivers/dma/virt-dma.c b/drivers/dma/virt-dma.c
index a35c211857dd..e47fc9b0944f 100644
--- a/drivers/dma/virt-dma.c
+++ b/drivers/dma/virt-dma.c
@@ -87,8 +87,7 @@ static void vchan_complete(unsigned long arg)
 {
 	struct virt_dma_chan *vc = (struct virt_dma_chan *)arg;
 	struct virt_dma_desc *vd;
-	dma_async_tx_callback cb = NULL;
-	void *cb_data = NULL;
+	struct dmaengine_desc_callback cb;
 	LIST_HEAD(head);
 
 	spin_lock_irq(&vc->lock);
@@ -96,18 +95,17 @@ static void vchan_complete(unsigned long arg)
 	vd = vc->cyclic;
 	if (vd) {
 		vc->cyclic = NULL;
-		cb = vd->tx.callback;
-		cb_data = vd->tx.callback_param;
+		dmaengine_desc_get_callback(&vd->tx, &cb);
+	} else {
+		memset(&cb, 0, sizeof(cb));
 	}
 	spin_unlock_irq(&vc->lock);
 
-	if (cb)
-		cb(cb_data);
+	dmaengine_desc_callback_invoke(&cb, NULL);
 
 	while (!list_empty(&head)) {
 		vd = list_first_entry(&head, struct virt_dma_desc, node);
-		cb = vd->tx.callback;
-		cb_data = vd->tx.callback_param;
+		dmaengine_desc_get_callback(&vd->tx, &cb);
 
 		list_del(&vd->node);
 		if (dmaengine_desc_test_reuse(&vd->tx))
@@ -115,8 +113,7 @@ static void vchan_complete(unsigned long arg)
 		else
 			vc->desc_free(vd);
 
-		if (cb)
-			cb(cb_data);
+		dmaengine_desc_callback_invoke(&cb, NULL);
 	}
 }
 
diff --git a/drivers/dma/virt-dma.h b/drivers/dma/virt-dma.h
index d9731ca5e262..3f776a46a29c 100644
--- a/drivers/dma/virt-dma.h
+++ b/drivers/dma/virt-dma.h
@@ -45,6 +45,8 @@ static inline struct virt_dma_chan *to_virt_chan(struct dma_chan *chan)
 void vchan_dma_desc_free_list(struct virt_dma_chan *vc, struct list_head *head);
 void vchan_init(struct virt_dma_chan *vc, struct dma_device *dmadev);
 struct virt_dma_desc *vchan_find_desc(struct virt_dma_chan *, dma_cookie_t);
+extern dma_cookie_t vchan_tx_submit(struct dma_async_tx_descriptor *);
+extern int vchan_tx_desc_free(struct dma_async_tx_descriptor *);
 
 /**
  * vchan_tx_prep - prepare a descriptor
@@ -55,8 +57,6 @@ struct virt_dma_desc *vchan_find_desc(struct virt_dma_chan *, dma_cookie_t);
 static inline struct dma_async_tx_descriptor *vchan_tx_prep(struct virt_dma_chan *vc,
 	struct virt_dma_desc *vd, unsigned long tx_flags)
 {
-	extern dma_cookie_t vchan_tx_submit(struct dma_async_tx_descriptor *);
-	extern int vchan_tx_desc_free(struct dma_async_tx_descriptor *);
 	unsigned long flags;
 
 	dma_async_tx_descriptor_init(&vd->tx, &vc->chan);
@@ -123,10 +123,8 @@ static inline void vchan_cyclic_callback(struct virt_dma_desc *vd)
  */
 static inline struct virt_dma_desc *vchan_next_desc(struct virt_dma_chan *vc)
 {
-	if (list_empty(&vc->desc_issued))
-		return NULL;
-
-	return list_first_entry(&vc->desc_issued, struct virt_dma_desc, node);
+	return list_first_entry_or_null(&vc->desc_issued,
+					struct virt_dma_desc, node);
 }
 
 /**
diff --git a/drivers/dma/xgene-dma.c b/drivers/dma/xgene-dma.c
index 9cb93c5b655d..8b693b712d0f 100644
--- a/drivers/dma/xgene-dma.c
+++ b/drivers/dma/xgene-dma.c
@@ -606,12 +606,10 @@ static void xgene_dma_run_tx_complete_actions(struct xgene_dma_chan *chan,
 		return;
 
 	dma_cookie_complete(tx);
+	dma_descriptor_unmap(tx);
 
 	/* Run the link descriptor callback function */
-	if (tx->callback)
-		tx->callback(tx->callback_param);
-
-	dma_descriptor_unmap(tx);
+	dmaengine_desc_get_callback_invoke(tx, NULL);
 
 	/* Run any dependencies */
 	dma_run_dependencies(tx);
diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c
index 4e223d094433..8288fe4d17c3 100644
--- a/drivers/dma/xilinx/xilinx_dma.c
+++ b/drivers/dma/xilinx/xilinx_dma.c
@@ -755,8 +755,7 @@ static void xilinx_dma_chan_desc_cleanup(struct xilinx_dma_chan *chan)
 	spin_lock_irqsave(&chan->lock, flags);
 
 	list_for_each_entry_safe(desc, next, &chan->done_list, node) {
-		dma_async_tx_callback callback;
-		void *callback_param;
+		struct dmaengine_desc_callback cb;
 
 		if (desc->cyclic) {
 			xilinx_dma_chan_handle_cyclic(chan, desc, &flags);
@@ -767,11 +766,10 @@ static void xilinx_dma_chan_desc_cleanup(struct xilinx_dma_chan *chan)
 		list_del(&desc->node);
 
 		/* Run the link descriptor callback function */
-		callback = desc->async_tx.callback;
-		callback_param = desc->async_tx.callback_param;
-		if (callback) {
+		dmaengine_desc_get_callback(&desc->async_tx, &cb);
+		if (dmaengine_desc_callback_valid(&cb)) {
 			spin_unlock_irqrestore(&chan->lock, flags);
-			callback(callback_param);
+			dmaengine_desc_callback_invoke(&cb, NULL);
 			spin_lock_irqsave(&chan->lock, flags);
 		}
 
diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
index d5c5894f252e..8601c10acf74 100644
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -102,13 +102,16 @@ struct ntb_queue_entry {
 	void *buf;
 	unsigned int len;
 	unsigned int flags;
+	int retries;
+	int errors;
+	unsigned int tx_index;
+	unsigned int rx_index;
 
 	struct ntb_transport_qp *qp;
 	union {
 		struct ntb_payload_header __iomem *tx_hdr;
 		struct ntb_payload_header *rx_hdr;
 	};
-	unsigned int index;
 };
 
 struct ntb_rx_info {
@@ -259,6 +262,12 @@ enum {
 static void ntb_transport_rxc_db(unsigned long data);
 static const struct ntb_ctx_ops ntb_transport_ops;
 static struct ntb_client ntb_transport_client;
+static int ntb_async_tx_submit(struct ntb_transport_qp *qp,
+			       struct ntb_queue_entry *entry);
+static void ntb_memcpy_tx(struct ntb_queue_entry *entry, void __iomem *offset);
+static int ntb_async_rx_submit(struct ntb_queue_entry *entry, void *offset);
+static void ntb_memcpy_rx(struct ntb_queue_entry *entry, void *offset);
+
 
 static int ntb_transport_bus_match(struct device *dev,
 				   struct device_driver *drv)
@@ -1229,7 +1238,7 @@ static void ntb_complete_rxc(struct ntb_transport_qp *qp)
 			break;
 
 		entry->rx_hdr->flags = 0;
-		iowrite32(entry->index, &qp->rx_info->entry);
+		iowrite32(entry->rx_index, &qp->rx_info->entry);
 
 		cb_data = entry->cb_data;
 		len = entry->len;
@@ -1247,10 +1256,36 @@ static void ntb_complete_rxc(struct ntb_transport_qp *qp)
 	spin_unlock_irqrestore(&qp->ntb_rx_q_lock, irqflags);
 }
 
-static void ntb_rx_copy_callback(void *data)
+static void ntb_rx_copy_callback(void *data,
+				 const struct dmaengine_result *res)
 {
 	struct ntb_queue_entry *entry = data;
 
+	/* we need to check DMA results if we are using DMA */
+	if (res) {
+		enum dmaengine_tx_result dma_err = res->result;
+
+		switch (dma_err) {
+		case DMA_TRANS_READ_FAILED:
+		case DMA_TRANS_WRITE_FAILED:
+			entry->errors++;
+		case DMA_TRANS_ABORTED:
+		{
+			struct ntb_transport_qp *qp = entry->qp;
+			void *offset = qp->rx_buff + qp->rx_max_frame *
+					qp->rx_index;
+
+			ntb_memcpy_rx(entry, offset);
+			qp->rx_memcpy++;
+			return;
+		}
+
+		case DMA_TRANS_NOERROR:
+		default:
+			break;
+		}
+	}
+
 	entry->flags |= DESC_DONE_FLAG;
 
 	ntb_complete_rxc(entry->qp);
@@ -1266,10 +1301,10 @@ static void ntb_memcpy_rx(struct ntb_queue_entry *entry, void *offset)
 	/* Ensure that the data is fully copied out before clearing the flag */
 	wmb();
 
-	ntb_rx_copy_callback(entry);
+	ntb_rx_copy_callback(entry, NULL);
 }
 
-static void ntb_async_rx(struct ntb_queue_entry *entry, void *offset)
+static int ntb_async_rx_submit(struct ntb_queue_entry *entry, void *offset)
 {
 	struct dma_async_tx_descriptor *txd;
 	struct ntb_transport_qp *qp = entry->qp;
@@ -1282,13 +1317,6 @@ static void ntb_async_rx(struct ntb_queue_entry *entry, void *offset)
 	int retries = 0;
 
 	len = entry->len;
-
-	if (!chan)
-		goto err;
-
-	if (len < copy_bytes)
-		goto err;
-
 	device = chan->device;
 	pay_off = (size_t)offset & ~PAGE_MASK;
 	buff_off = (size_t)buf & ~PAGE_MASK;
@@ -1316,7 +1344,8 @@ static void ntb_async_rx(struct ntb_queue_entry *entry, void *offset)
 	unmap->from_cnt = 1;
 
 	for (retries = 0; retries < DMA_RETRIES; retries++) {
-		txd = device->device_prep_dma_memcpy(chan, unmap->addr[1],
+		txd = device->device_prep_dma_memcpy(chan,
+						     unmap->addr[1],
 						     unmap->addr[0], len,
 						     DMA_PREP_INTERRUPT);
 		if (txd)
@@ -1331,7 +1360,7 @@ static void ntb_async_rx(struct ntb_queue_entry *entry, void *offset)
 		goto err_get_unmap;
 	}
 
-	txd->callback = ntb_rx_copy_callback;
+	txd->callback_result = ntb_rx_copy_callback;
 	txd->callback_param = entry;
 	dma_set_unmap(txd, unmap);
 
@@ -1345,13 +1374,38 @@ static void ntb_async_rx(struct ntb_queue_entry *entry, void *offset)
 
 	qp->rx_async++;
 
-	return;
+	return 0;
 
 err_set_unmap:
 	dmaengine_unmap_put(unmap);
 err_get_unmap:
 	dmaengine_unmap_put(unmap);
 err:
+	return -ENXIO;
+}
+
+static void ntb_async_rx(struct ntb_queue_entry *entry, void *offset)
+{
+	struct ntb_transport_qp *qp = entry->qp;
+	struct dma_chan *chan = qp->rx_dma_chan;
+	int res;
+
+	if (!chan)
+		goto err;
+
+	if (entry->len < copy_bytes)
+		goto err;
+
+	res = ntb_async_rx_submit(entry, offset);
+	if (res < 0)
+		goto err;
+
+	if (!entry->retries)
+		qp->rx_async++;
+
+	return;
+
+err:
 	ntb_memcpy_rx(entry, offset);
 	qp->rx_memcpy++;
 }
@@ -1397,7 +1451,7 @@ static int ntb_process_rxc(struct ntb_transport_qp *qp)
 	}
 
 	entry->rx_hdr = hdr;
-	entry->index = qp->rx_index;
+	entry->rx_index = qp->rx_index;
 
 	if (hdr->len > entry->len) {
 		dev_dbg(&qp->ndev->pdev->dev,
@@ -1467,12 +1521,39 @@ static void ntb_transport_rxc_db(unsigned long data)
 	}
 }
 
-static void ntb_tx_copy_callback(void *data)
+static void ntb_tx_copy_callback(void *data,
+				 const struct dmaengine_result *res)
 {
 	struct ntb_queue_entry *entry = data;
 	struct ntb_transport_qp *qp = entry->qp;
 	struct ntb_payload_header __iomem *hdr = entry->tx_hdr;
 
+	/* we need to check DMA results if we are using DMA */
+	if (res) {
+		enum dmaengine_tx_result dma_err = res->result;
+
+		switch (dma_err) {
+		case DMA_TRANS_READ_FAILED:
+		case DMA_TRANS_WRITE_FAILED:
+			entry->errors++;
+		case DMA_TRANS_ABORTED:
+		{
+			void __iomem *offset =
+				qp->tx_mw + qp->tx_max_frame *
+				entry->tx_index;
+
+			/* resubmit via CPU */
+			ntb_memcpy_tx(entry, offset);
+			qp->tx_memcpy++;
+			return;
+		}
+
+		case DMA_TRANS_NOERROR:
+		default:
+			break;
+		}
+	}
+
 	iowrite32(entry->flags | DESC_DONE_FLAG, &hdr->flags);
 
 	ntb_peer_db_set(qp->ndev, BIT_ULL(qp->qp_num));
@@ -1507,40 +1588,25 @@ static void ntb_memcpy_tx(struct ntb_queue_entry *entry, void __iomem *offset)
 	/* Ensure that the data is fully copied out before setting the flags */
 	wmb();
 
-	ntb_tx_copy_callback(entry);
+	ntb_tx_copy_callback(entry, NULL);
 }
 
-static void ntb_async_tx(struct ntb_transport_qp *qp,
-			 struct ntb_queue_entry *entry)
+static int ntb_async_tx_submit(struct ntb_transport_qp *qp,
+			       struct ntb_queue_entry *entry)
 {
-	struct ntb_payload_header __iomem *hdr;
 	struct dma_async_tx_descriptor *txd;
 	struct dma_chan *chan = qp->tx_dma_chan;
 	struct dma_device *device;
+	size_t len = entry->len;
+	void *buf = entry->buf;
 	size_t dest_off, buff_off;
 	struct dmaengine_unmap_data *unmap;
 	dma_addr_t dest;
 	dma_cookie_t cookie;
-	void __iomem *offset;
-	size_t len = entry->len;
-	void *buf = entry->buf;
 	int retries = 0;
 
-	offset = qp->tx_mw + qp->tx_max_frame * qp->tx_index;
-	hdr = offset + qp->tx_max_frame - sizeof(struct ntb_payload_header);
-	entry->tx_hdr = hdr;
-
-	iowrite32(entry->len, &hdr->len);
-	iowrite32((u32)qp->tx_pkts, &hdr->ver);
-
-	if (!chan)
-		goto err;
-
-	if (len < copy_bytes)
-		goto err;
-
 	device = chan->device;
-	dest = qp->tx_mw_phys + qp->tx_max_frame * qp->tx_index;
+	dest = qp->tx_mw_phys + qp->tx_max_frame * entry->tx_index;
 	buff_off = (size_t)buf & ~PAGE_MASK;
 	dest_off = (size_t)dest & ~PAGE_MASK;
 
@@ -1560,8 +1626,9 @@ static void ntb_async_tx(struct ntb_transport_qp *qp,
 	unmap->to_cnt = 1;
 
 	for (retries = 0; retries < DMA_RETRIES; retries++) {
-		txd = device->device_prep_dma_memcpy(chan, dest, unmap->addr[0],
-						     len, DMA_PREP_INTERRUPT);
+		txd = device->device_prep_dma_memcpy(chan, dest,
+						     unmap->addr[0], len,
+						     DMA_PREP_INTERRUPT);
 		if (txd)
 			break;
 
@@ -1574,7 +1641,7 @@ static void ntb_async_tx(struct ntb_transport_qp *qp,
 		goto err_get_unmap;
 	}
 
-	txd->callback = ntb_tx_copy_callback;
+	txd->callback_result = ntb_tx_copy_callback;
 	txd->callback_param = entry;
 	dma_set_unmap(txd, unmap);
 
@@ -1585,14 +1652,48 @@ static void ntb_async_tx(struct ntb_transport_qp *qp,
 	dmaengine_unmap_put(unmap);
 
 	dma_async_issue_pending(chan);
-	qp->tx_async++;
 
-	return;
+	return 0;
 err_set_unmap:
 	dmaengine_unmap_put(unmap);
 err_get_unmap:
 	dmaengine_unmap_put(unmap);
 err:
+	return -ENXIO;
+}
+
+static void ntb_async_tx(struct ntb_transport_qp *qp,
+			 struct ntb_queue_entry *entry)
+{
+	struct ntb_payload_header __iomem *hdr;
+	struct dma_chan *chan = qp->tx_dma_chan;
+	void __iomem *offset;
+	int res;
+
+	entry->tx_index = qp->tx_index;
+	offset = qp->tx_mw + qp->tx_max_frame * entry->tx_index;
+	hdr = offset + qp->tx_max_frame - sizeof(struct ntb_payload_header);
+	entry->tx_hdr = hdr;
+
+	iowrite32(entry->len, &hdr->len);
+	iowrite32((u32)qp->tx_pkts, &hdr->ver);
+
+	if (!chan)
+		goto err;
+
+	if (entry->len < copy_bytes)
+		goto err;
+
+	res = ntb_async_tx_submit(qp, entry);
+	if (res < 0)
+		goto err;
+
+	if (!entry->retries)
+		qp->tx_async++;
+
+	return;
+
+err:
 	ntb_memcpy_tx(entry, offset);
 	qp->tx_memcpy++;
 }
@@ -1928,6 +2029,9 @@ int ntb_transport_rx_enqueue(struct ntb_transport_qp *qp, void *cb, void *data,
 	entry->buf = data;
 	entry->len = len;
 	entry->flags = 0;
+	entry->retries = 0;
+	entry->errors = 0;
+	entry->rx_index = 0;
 
 	ntb_list_add(&qp->ntb_rx_q_lock, &entry->entry, &qp->rx_pend_q);
 
@@ -1970,6 +2074,9 @@ int ntb_transport_tx_enqueue(struct ntb_transport_qp *qp, void *cb, void *data,
 	entry->buf = data;
 	entry->len = len;
 	entry->flags = 0;
+	entry->errors = 0;
+	entry->retries = 0;
+	entry->tx_index = 0;
 
 	rc = ntb_process_tx(qp, entry);
 	if (rc)