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)