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

Pull slave-dmaengine changes from Vinod Koul:
 "This brings for slave dmaengine:

   - Change dma notification flag to DMA_COMPLETE from DMA_SUCCESS as
     dmaengine can only transfer and not verify validaty of dma
     transfers

   - Bunch of fixes across drivers:

      - cppi41 driver fixes from Daniel

      - 8 channel freescale dma engine support and updated bindings from
        Hongbo

      - msx-dma fixes and cleanup by Markus

   - DMAengine updates from Dan:

      - Bartlomiej and Dan finalized a rework of the dma address unmap
        implementation.

      - In the course of testing 1/ a collection of enhancements to
        dmatest fell out.  Notably basic performance statistics, and
        fixed / enhanced test control through new module parameters
        'run', 'wait', 'noverify', and 'verbose'.  Thanks to Andriy and
        Linus [Walleij] for their review.

      - Testing the raid related corner cases of 1/ triggered bugs in
        the recently added 16-source operation support in the ioatdma
        driver.

      - Some minor fixes / cleanups to mv_xor and ioatdma"

* 'next' of git://git.infradead.org/users/vkoul/slave-dma: (99 commits)
  dma: mv_xor: Fix mis-usage of mmio 'base' and 'high_base' registers
  dma: mv_xor: Remove unneeded NULL address check
  ioat: fix ioat3_irq_reinit
  ioat: kill msix_single_vector support
  raid6test: add new corner case for ioatdma driver
  ioatdma: clean up sed pool kmem_cache
  ioatdma: fix selection of 16 vs 8 source path
  ioatdma: fix sed pool selection
  ioatdma: Fix bug in selftest after removal of DMA_MEMSET.
  dmatest: verbose mode
  dmatest: convert to dmaengine_unmap_data
  dmatest: add a 'wait' parameter
  dmatest: add basic performance metrics
  dmatest: add support for skipping verification and random data setup
  dmatest: use pseudo random numbers
  dmatest: support xor-only, or pq-only channels in tests
  dmatest: restore ability to start test at module load and init
  dmatest: cleanup redundant "dmatest: " prefixes
  dmatest: replace stored results mechanism, with uniform messages
  Revert "dmatest: append verify result to results"
  ...

40 files changed, 1297 insertions, 1893 deletions

diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index dd2874ec1927..446687cc2334 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -89,14 +89,15 @@ config AT_HDMAC
 	  Support the Atmel AHB DMA controller.
 
 config FSL_DMA
-	tristate "Freescale Elo and Elo Plus DMA support"
+	tristate "Freescale Elo series DMA support"
 	depends on FSL_SOC
 	select DMA_ENGINE
 	select ASYNC_TX_ENABLE_CHANNEL_SWITCH
 	---help---
-	  Enable support for the Freescale Elo and Elo Plus DMA controllers.
-	  The Elo is the DMA controller on some 82xx and 83xx parts, and the
-	  Elo Plus is the DMA controller on 85xx and 86xx parts.
+	  Enable support for the Freescale Elo series DMA controllers.
+	  The Elo is the DMA controller on some mpc82xx and mpc83xx parts, the
+	  EloPlus is on mpc85xx and mpc86xx and Pxxx parts, and the Elo3 is on
+	  some Txxx and Bxxx parts.
 
 config MPC512X_DMA
 	tristate "Freescale MPC512x built-in DMA engine support"
diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c
index e51a9832ef0d..16a2aa28f856 100644
--- a/drivers/dma/amba-pl08x.c
+++ b/drivers/dma/amba-pl08x.c
@@ -1164,42 +1164,12 @@ static void pl08x_free_txd(struct pl08x_driver_data *pl08x,
 	kfree(txd);
 }
 
-static void pl08x_unmap_buffers(struct pl08x_txd *txd)
-{
-	struct device *dev = txd->vd.tx.chan->device->dev;
-	struct pl08x_sg *dsg;
-
-	if (!(txd->vd.tx.flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-		if (txd->vd.tx.flags & DMA_COMPL_SRC_UNMAP_SINGLE)
-			list_for_each_entry(dsg, &txd->dsg_list, node)
-				dma_unmap_single(dev, dsg->src_addr, dsg->len,
-						DMA_TO_DEVICE);
-		else {
-			list_for_each_entry(dsg, &txd->dsg_list, node)
-				dma_unmap_page(dev, dsg->src_addr, dsg->len,
-						DMA_TO_DEVICE);
-		}
-	}
-	if (!(txd->vd.tx.flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
-		if (txd->vd.tx.flags & DMA_COMPL_DEST_UNMAP_SINGLE)
-			list_for_each_entry(dsg, &txd->dsg_list, node)
-				dma_unmap_single(dev, dsg->dst_addr, dsg->len,
-						DMA_FROM_DEVICE);
-		else
-			list_for_each_entry(dsg, &txd->dsg_list, node)
-				dma_unmap_page(dev, dsg->dst_addr, dsg->len,
-						DMA_FROM_DEVICE);
-	}
-}
-
 static void pl08x_desc_free(struct virt_dma_desc *vd)
 {
 	struct pl08x_txd *txd = to_pl08x_txd(&vd->tx);
 	struct pl08x_dma_chan *plchan = to_pl08x_chan(vd->tx.chan);
 
-	if (!plchan->slave)
-		pl08x_unmap_buffers(txd);
-
+	dma_descriptor_unmap(txd);
 	if (!txd->done)
 		pl08x_release_mux(plchan);
 
@@ -1252,7 +1222,7 @@ static enum dma_status pl08x_dma_tx_status(struct dma_chan *chan,
 	size_t bytes = 0;
 
 	ret = dma_cookie_status(chan, cookie, txstate);
-	if (ret == DMA_SUCCESS)
+	if (ret == DMA_COMPLETE)
 		return ret;
 
 	/*
@@ -1267,7 +1237,7 @@ static enum dma_status pl08x_dma_tx_status(struct dma_chan *chan,
 
 	spin_lock_irqsave(&plchan->vc.lock, flags);
 	ret = dma_cookie_status(chan, cookie, txstate);
-	if (ret != DMA_SUCCESS) {
+	if (ret != DMA_COMPLETE) {
 		vd = vchan_find_desc(&plchan->vc, cookie);
 		if (vd) {
 			/* On the issued list, so hasn't been processed yet */
@@ -2138,8 +2108,7 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id)
 	writel(0x000000FF, pl08x->base + PL080_ERR_CLEAR);
 	writel(0x000000FF, pl08x->base + PL080_TC_CLEAR);
 
-	ret = request_irq(adev->irq[0], pl08x_irq, IRQF_DISABLED,
-			  DRIVER_NAME, pl08x);
+	ret = request_irq(adev->irq[0], pl08x_irq, 0, DRIVER_NAME, pl08x);
 	if (ret) {
 		dev_err(&adev->dev, "%s failed to request interrupt %d\n",
 			__func__, adev->irq[0]);
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index c787f38a186a..e2c04dc81e2a 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -344,31 +344,7 @@ atc_chain_complete(struct at_dma_chan *atchan, struct at_desc *desc)
 	/* move myself to free_list */
 	list_move(&desc->desc_node, &atchan->free_list);
 
-	/* unmap dma addresses (not on slave channels) */
-	if (!atchan->chan_common.private) {
-		struct device *parent = chan2parent(&atchan->chan_common);
-		if (!(txd->flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
-			if (txd->flags & DMA_COMPL_DEST_UNMAP_SINGLE)
-				dma_unmap_single(parent,
-						desc->lli.daddr,
-						desc->len, DMA_FROM_DEVICE);
-			else
-				dma_unmap_page(parent,
-						desc->lli.daddr,
-						desc->len, DMA_FROM_DEVICE);
-		}
-		if (!(txd->flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-			if (txd->flags & DMA_COMPL_SRC_UNMAP_SINGLE)
-				dma_unmap_single(parent,
-						desc->lli.saddr,
-						desc->len, DMA_TO_DEVICE);
-			else
-				dma_unmap_page(parent,
-						desc->lli.saddr,
-						desc->len, DMA_TO_DEVICE);
-		}
-	}
-
+	dma_descriptor_unmap(txd);
 	/* for cyclic transfers,
 	 * no need to replay callback function while stopping */
 	if (!atc_chan_is_cyclic(atchan)) {
@@ -1102,7 +1078,7 @@ atc_tx_status(struct dma_chan *chan,
 	int bytes = 0;
 
 	ret = dma_cookie_status(chan, cookie, txstate);
-	if (ret == DMA_SUCCESS)
+	if (ret == DMA_COMPLETE)
 		return ret;
 	/*
 	 * There's no point calculating the residue if there's
diff --git a/drivers/dma/coh901318.c b/drivers/dma/coh901318.c
index 31011d2a26fc..3c6716e0b78e 100644
--- a/drivers/dma/coh901318.c
+++ b/drivers/dma/coh901318.c
@@ -2369,7 +2369,7 @@ coh901318_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 	enum dma_status ret;
 
 	ret = dma_cookie_status(chan, cookie, txstate);
-	if (ret == DMA_SUCCESS)
+	if (ret == DMA_COMPLETE)
 		return ret;
 
 	dma_set_residue(txstate, coh901318_get_bytes_left(chan));
@@ -2694,7 +2694,7 @@ static int __init coh901318_probe(struct platform_device *pdev)
 	if (irq < 0)
 		return irq;
 
-	err = devm_request_irq(&pdev->dev, irq, dma_irq_handler, IRQF_DISABLED,
+	err = devm_request_irq(&pdev->dev, irq, dma_irq_handler, 0,
 			       "coh901318", base);
 	if (err)
 		return err;
diff --git a/drivers/dma/cppi41.c b/drivers/dma/cppi41.c
index 7c82b92f9b16..c29dacff66fa 100644
--- a/drivers/dma/cppi41.c
+++ b/drivers/dma/cppi41.c
@@ -141,6 +141,9 @@ struct cppi41_dd {
 	const struct chan_queues *queues_rx;
 	const struct chan_queues *queues_tx;
 	struct chan_queues td_queue;
+
+	/* context for suspend/resume */
+	unsigned int dma_tdfdq;
 };
 
 #define FIST_COMPLETION_QUEUE	93
@@ -263,6 +266,15 @@ static u32 pd_trans_len(u32 val)
 	return val & ((1 << (DESC_LENGTH_BITS_NUM + 1)) - 1);
 }
 
+static u32 cppi41_pop_desc(struct cppi41_dd *cdd, unsigned queue_num)
+{
+	u32 desc;
+
+	desc = cppi_readl(cdd->qmgr_mem + QMGR_QUEUE_D(queue_num));
+	desc &= ~0x1f;
+	return desc;
+}
+
 static irqreturn_t cppi41_irq(int irq, void *data)
 {
 	struct cppi41_dd *cdd = data;
@@ -300,8 +312,7 @@ static irqreturn_t cppi41_irq(int irq, void *data)
 			q_num = __fls(val);
 			val &= ~(1 << q_num);
 			q_num += 32 * i;
-			desc = cppi_readl(cdd->qmgr_mem + QMGR_QUEUE_D(q_num));
-			desc &= ~0x1f;
+			desc = cppi41_pop_desc(cdd, q_num);
 			c = desc_to_chan(cdd, desc);
 			if (WARN_ON(!c)) {
 				pr_err("%s() q %d desc %08x\n", __func__,
@@ -353,7 +364,7 @@ static enum dma_status cppi41_dma_tx_status(struct dma_chan *chan,
 
 	/* lock */
 	ret = dma_cookie_status(chan, cookie, txstate);
-	if (txstate && ret == DMA_SUCCESS)
+	if (txstate && ret == DMA_COMPLETE)
 		txstate->residue = c->residue;
 	/* unlock */
 
@@ -517,15 +528,6 @@ static void cppi41_compute_td_desc(struct cppi41_desc *d)
 	d->pd0 = DESC_TYPE_TEARD << DESC_TYPE;
 }
 
-static u32 cppi41_pop_desc(struct cppi41_dd *cdd, unsigned queue_num)
-{
-	u32 desc;
-
-	desc = cppi_readl(cdd->qmgr_mem + QMGR_QUEUE_D(queue_num));
-	desc &= ~0x1f;
-	return desc;
-}
-
 static int cppi41_tear_down_chan(struct cppi41_channel *c)
 {
 	struct cppi41_dd *cdd = c->cdd;
@@ -561,36 +563,26 @@ static int cppi41_tear_down_chan(struct cppi41_channel *c)
 		c->td_retry = 100;
 	}
 
-	if (!c->td_seen) {
-		unsigned td_comp_queue;
+	if (!c->td_seen || !c->td_desc_seen) {
 
-		if (c->is_tx)
-			td_comp_queue =  cdd->td_queue.complete;
-		else
-			td_comp_queue =  c->q_comp_num;
+		desc_phys = cppi41_pop_desc(cdd, cdd->td_queue.complete);
+		if (!desc_phys)
+			desc_phys = cppi41_pop_desc(cdd, c->q_comp_num);
 
-		desc_phys = cppi41_pop_desc(cdd, td_comp_queue);
-		if (desc_phys) {
-			__iormb();
+		if (desc_phys == c->desc_phys) {
+			c->td_desc_seen = 1;
+
+		} else if (desc_phys == td_desc_phys) {
+			u32 pd0;
 
-			if (desc_phys == td_desc_phys) {
-				u32 pd0;
-				pd0 = td->pd0;
-				WARN_ON((pd0 >> DESC_TYPE) != DESC_TYPE_TEARD);
-				WARN_ON(!c->is_tx && !(pd0 & TD_DESC_IS_RX));
-				WARN_ON((pd0 & 0x1f) != c->port_num);
-			} else {
-				WARN_ON_ONCE(1);
-			}
-			c->td_seen = 1;
-		}
-	}
-	if (!c->td_desc_seen) {
-		desc_phys = cppi41_pop_desc(cdd, c->q_comp_num);
-		if (desc_phys) {
 			__iormb();
-			WARN_ON(c->desc_phys != desc_phys);
-			c->td_desc_seen = 1;
+			pd0 = td->pd0;
+			WARN_ON((pd0 >> DESC_TYPE) != DESC_TYPE_TEARD);
+			WARN_ON(!c->is_tx && !(pd0 & TD_DESC_IS_RX));
+			WARN_ON((pd0 & 0x1f) != c->port_num);
+			c->td_seen = 1;
+		} else if (desc_phys) {
+			WARN_ON_ONCE(1);
 		}
 	}
 	c->td_retry--;
@@ -609,7 +601,7 @@ static int cppi41_tear_down_chan(struct cppi41_channel *c)
 
 	WARN_ON(!c->td_retry);
 	if (!c->td_desc_seen) {
-		desc_phys = cppi_readl(cdd->qmgr_mem + QMGR_QUEUE_D(c->q_num));
+		desc_phys = cppi41_pop_desc(cdd, c->q_num);
 		WARN_ON(!desc_phys);
 	}
 
@@ -674,14 +666,14 @@ static void cleanup_chans(struct cppi41_dd *cdd)
 	}
 }
 
-static int cppi41_add_chans(struct platform_device *pdev, struct cppi41_dd *cdd)
+static int cppi41_add_chans(struct device *dev, struct cppi41_dd *cdd)
 {
 	struct cppi41_channel *cchan;
 	int i;
 	int ret;
 	u32 n_chans;
 
-	ret = of_property_read_u32(pdev->dev.of_node, "#dma-channels",
+	ret = of_property_read_u32(dev->of_node, "#dma-channels",
 			&n_chans);
 	if (ret)
 		return ret;
@@ -719,7 +711,7 @@ err:
 	return -ENOMEM;
 }
 
-static void purge_descs(struct platform_device *pdev, struct cppi41_dd *cdd)
+static void purge_descs(struct device *dev, struct cppi41_dd *cdd)
 {
 	unsigned int mem_decs;
 	int i;
@@ -731,7 +723,7 @@ static void purge_descs(struct platform_device *pdev, struct cppi41_dd *cdd)
 		cppi_writel(0, cdd->qmgr_mem + QMGR_MEMBASE(i));
 		cppi_writel(0, cdd->qmgr_mem + QMGR_MEMCTRL(i));
 
-		dma_free_coherent(&pdev->dev, mem_decs, cdd->cd,
+		dma_free_coherent(dev, mem_decs, cdd->cd,
 				cdd->descs_phys);
 	}
 }
@@ -741,19 +733,19 @@ static void disable_sched(struct cppi41_dd *cdd)
 	cppi_writel(0, cdd->sched_mem + DMA_SCHED_CTRL);
 }
 
-static void deinit_cpii41(struct platform_device *pdev, struct cppi41_dd *cdd)
+static void deinit_cppi41(struct device *dev, struct cppi41_dd *cdd)
 {
 	disable_sched(cdd);
 
-	purge_descs(pdev, cdd);
+	purge_descs(dev, cdd);
 
 	cppi_writel(0, cdd->qmgr_mem + QMGR_LRAM0_BASE);
 	cppi_writel(0, cdd->qmgr_mem + QMGR_LRAM0_BASE);
-	dma_free_coherent(&pdev->dev, QMGR_SCRATCH_SIZE, cdd->qmgr_scratch,
+	dma_free_coherent(dev, QMGR_SCRATCH_SIZE, cdd->qmgr_scratch,
 			cdd->scratch_phys);
 }
 
-static int init_descs(struct platform_device *pdev, struct cppi41_dd *cdd)
+static int init_descs(struct device *dev, struct cppi41_dd *cdd)
 {
 	unsigned int desc_size;
 	unsigned int mem_decs;
@@ -777,7 +769,7 @@ static int init_descs(struct platform_device *pdev, struct cppi41_dd *cdd)
 		reg |= ilog2(ALLOC_DECS_NUM) - 5;
 
 		BUILD_BUG_ON(DESCS_AREAS != 1);
-		cdd->cd = dma_alloc_coherent(&pdev->dev, mem_decs,
+		cdd->cd = dma_alloc_coherent(dev, mem_decs,
 				&cdd->descs_phys, GFP_KERNEL);
 		if (!cdd->cd)
 			return -ENOMEM;
@@ -813,12 +805,12 @@ static void init_sched(struct cppi41_dd *cdd)
 	cppi_writel(reg, cdd->sched_mem + DMA_SCHED_CTRL);
 }
 
-static int init_cppi41(struct platform_device *pdev, struct cppi41_dd *cdd)
+static int init_cppi41(struct device *dev, struct cppi41_dd *cdd)
 {
 	int ret;
 
 	BUILD_BUG_ON(QMGR_SCRATCH_SIZE > ((1 << 14) - 1));
-	cdd->qmgr_scratch = dma_alloc_coherent(&pdev->dev, QMGR_SCRATCH_SIZE,
+	cdd->qmgr_scratch = dma_alloc_coherent(dev, QMGR_SCRATCH_SIZE,
 			&cdd->scratch_phys, GFP_KERNEL);
 	if (!cdd->qmgr_scratch)
 		return -ENOMEM;
@@ -827,7 +819,7 @@ static int init_cppi41(struct platform_device *pdev, struct cppi41_dd *cdd)
 	cppi_writel(QMGR_SCRATCH_SIZE, cdd->qmgr_mem + QMGR_LRAM_SIZE);
 	cppi_writel(0, cdd->qmgr_mem + QMGR_LRAM1_BASE);
 
-	ret = init_descs(pdev, cdd);
+	ret = init_descs(dev, cdd);
 	if (ret)
 		goto err_td;
 
@@ -835,7 +827,7 @@ static int init_cppi41(struct platform_device *pdev, struct cppi41_dd *cdd)
 	init_sched(cdd);
 	return 0;
 err_td:
-	deinit_cpii41(pdev, cdd);
+	deinit_cppi41(dev, cdd);
 	return ret;
 }
 
@@ -914,11 +906,11 @@ static const struct of_device_id cppi41_dma_ids[] = {
 };
 MODULE_DEVICE_TABLE(of, cppi41_dma_ids);
 
-static const struct cppi_glue_infos *get_glue_info(struct platform_device *pdev)
+static const struct cppi_glue_infos *get_glue_info(struct device *dev)
 {
 	const struct of_device_id *of_id;
 
-	of_id = of_match_node(cppi41_dma_ids, pdev->dev.of_node);
+	of_id = of_match_node(cppi41_dma_ids, dev->of_node);
 	if (!of_id)
 		return NULL;
 	return of_id->data;
@@ -927,11 +919,12 @@ static const struct cppi_glue_infos *get_glue_info(struct platform_device *pdev)
 static int cppi41_dma_probe(struct platform_device *pdev)
 {
 	struct cppi41_dd *cdd;
+	struct device *dev = &pdev->dev;
 	const struct cppi_glue_infos *glue_info;
 	int irq;
 	int ret;
 
-	glue_info = get_glue_info(pdev);
+	glue_info = get_glue_info(dev);
 	if (!glue_info)
 		return -EINVAL;
 
@@ -946,14 +939,14 @@ static int cppi41_dma_probe(struct platform_device *pdev)
 	cdd->ddev.device_issue_pending = cppi41_dma_issue_pending;
 	cdd->ddev.device_prep_slave_sg = cppi41_dma_prep_slave_sg;
 	cdd->ddev.device_control = cppi41_dma_control;
-	cdd->ddev.dev = &pdev->dev;
+	cdd->ddev.dev = dev;
 	INIT_LIST_HEAD(&cdd->ddev.channels);
 	cpp41_dma_info.dma_cap = cdd->ddev.cap_mask;
 
-	cdd->usbss_mem = of_iomap(pdev->dev.of_node, 0);
-	cdd->ctrl_mem = of_iomap(pdev->dev.of_node, 1);
-	cdd->sched_mem = of_iomap(pdev->dev.of_node, 2);
-	cdd->qmgr_mem = of_iomap(pdev->dev.of_node, 3);
+	cdd->usbss_mem = of_iomap(dev->of_node, 0);
+	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);
 
 	if (!cdd->usbss_mem || !cdd->ctrl_mem || !cdd->sched_mem ||
 			!cdd->qmgr_mem) {
@@ -961,31 +954,31 @@ static int cppi41_dma_probe(struct platform_device *pdev)
 		goto err_remap;
 	}
 
-	pm_runtime_enable(&pdev->dev);
-	ret = pm_runtime_get_sync(&pdev->dev);
-	if (ret)
+	pm_runtime_enable(dev);
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0)
 		goto err_get_sync;
 
 	cdd->queues_rx = glue_info->queues_rx;
 	cdd->queues_tx = glue_info->queues_tx;
 	cdd->td_queue = glue_info->td_queue;
 
-	ret = init_cppi41(pdev, cdd);
+	ret = init_cppi41(dev, cdd);
 	if (ret)
 		goto err_init_cppi;
 
-	ret = cppi41_add_chans(pdev, cdd);
+	ret = cppi41_add_chans(dev, cdd);
 	if (ret)
 		goto err_chans;
 
-	irq = irq_of_parse_and_map(pdev->dev.of_node, 0);
+	irq = irq_of_parse_and_map(dev->of_node, 0);
 	if (!irq)
 		goto err_irq;
 
 	cppi_writel(USBSS_IRQ_PD_COMP, cdd->usbss_mem + USBSS_IRQ_ENABLER);
 
 	ret = request_irq(irq, glue_info->isr, IRQF_SHARED,
-			dev_name(&pdev->dev), cdd);
+			dev_name(dev), cdd);
 	if (ret)
 		goto err_irq;
 	cdd->irq = irq;
@@ -994,7 +987,7 @@ static int cppi41_dma_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_dma_reg;
 
-	ret = of_dma_controller_register(pdev->dev.of_node,
+	ret = of_dma_controller_register(dev->of_node,
 			cppi41_dma_xlate, &cpp41_dma_info);
 	if (ret)
 		goto err_of;
@@ -1009,11 +1002,11 @@ err_irq:
 	cppi_writel(0, cdd->usbss_mem + USBSS_IRQ_CLEARR);
 	cleanup_chans(cdd);
 err_chans:
-	deinit_cpii41(pdev, cdd);
+	deinit_cppi41(dev, cdd);
 err_init_cppi:
-	pm_runtime_put(&pdev->dev);
+	pm_runtime_put(dev);
 err_get_sync:
-	pm_runtime_disable(&pdev->dev);
+	pm_runtime_disable(dev);
 	iounmap(cdd->usbss_mem);
 	iounmap(cdd->ctrl_mem);
 	iounmap(cdd->sched_mem);
@@ -1033,7 +1026,7 @@ static int cppi41_dma_remove(struct platform_device *pdev)
 	cppi_writel(0, cdd->usbss_mem + USBSS_IRQ_CLEARR);
 	free_irq(cdd->irq, cdd);
 	cleanup_chans(cdd);
-	deinit_cpii41(pdev, cdd);
+	deinit_cppi41(&pdev->dev, cdd);
 	iounmap(cdd->usbss_mem);
 	iounmap(cdd->ctrl_mem);
 	iounmap(cdd->sched_mem);
@@ -1044,12 +1037,53 @@ static int cppi41_dma_remove(struct platform_device *pdev)
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
+static int cppi41_suspend(struct device *dev)
+{
+	struct cppi41_dd *cdd = dev_get_drvdata(dev);
+
+	cdd->dma_tdfdq = cppi_readl(cdd->ctrl_mem + DMA_TDFDQ);
+	cppi_writel(0, cdd->usbss_mem + USBSS_IRQ_CLEARR);
+	disable_sched(cdd);
+
+	return 0;
+}
+
+static int cppi41_resume(struct device *dev)
+{
+	struct cppi41_dd *cdd = dev_get_drvdata(dev);
+	struct cppi41_channel *c;
+	int i;
+
+	for (i = 0; i < DESCS_AREAS; i++)
+		cppi_writel(cdd->descs_phys, cdd->qmgr_mem + QMGR_MEMBASE(i));
+
+	list_for_each_entry(c, &cdd->ddev.channels, chan.device_node)
+		if (!c->is_tx)
+			cppi_writel(c->q_num, c->gcr_reg + RXHPCRA0);
+
+	init_sched(cdd);
+
+	cppi_writel(cdd->dma_tdfdq, cdd->ctrl_mem + DMA_TDFDQ);
+	cppi_writel(cdd->scratch_phys, cdd->qmgr_mem + QMGR_LRAM0_BASE);
+	cppi_writel(QMGR_SCRATCH_SIZE, cdd->qmgr_mem + QMGR_LRAM_SIZE);
+	cppi_writel(0, cdd->qmgr_mem + QMGR_LRAM1_BASE);
+
+	cppi_writel(USBSS_IRQ_PD_COMP, cdd->usbss_mem + USBSS_IRQ_ENABLER);
+
+	return 0;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(cppi41_pm_ops, cppi41_suspend, cppi41_resume);
+
 static struct platform_driver cpp41_dma_driver = {
 	.probe  = cppi41_dma_probe,
 	.remove = cppi41_dma_remove,
 	.driver = {
 		.name = "cppi41-dma-engine",
 		.owner = THIS_MODULE,
+		.pm = &cppi41_pm_ops,
 		.of_match_table = of_match_ptr(cppi41_dma_ids),
 	},
 };
diff --git a/drivers/dma/dma-jz4740.c b/drivers/dma/dma-jz4740.c
index b0c0c8268d42..94c380f07538 100644
--- a/drivers/dma/dma-jz4740.c
+++ b/drivers/dma/dma-jz4740.c
@@ -491,7 +491,7 @@ static enum dma_status jz4740_dma_tx_status(struct dma_chan *c,
 	unsigned long flags;
 
 	status = dma_cookie_status(c, cookie, state);
-	if (status == DMA_SUCCESS || !state)
+	if (status == DMA_COMPLETE || !state)
 		return status;
 
 	spin_lock_irqsave(&chan->vchan.lock, flags);
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 9162ac80c18f..ea806bdc12ef 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -65,6 +65,7 @@
 #include <linux/acpi.h>
 #include <linux/acpi_dma.h>
 #include <linux/of_dma.h>
+#include <linux/mempool.h>
 
 static DEFINE_MUTEX(dma_list_mutex);
 static DEFINE_IDR(dma_idr);
@@ -901,98 +902,132 @@ void dma_async_device_unregister(struct dma_device *device)
 }
 EXPORT_SYMBOL(dma_async_device_unregister);
 
-/**
- * dma_async_memcpy_buf_to_buf - offloaded copy between virtual addresses
- * @chan: DMA channel to offload copy to
- * @dest: destination address (virtual)
- * @src: source address (virtual)
- * @len: length
- *
- * Both @dest and @src must be mappable to a bus address according to the
- * DMA mapping API rules for streaming mappings.
- * Both @dest and @src must stay memory resident (kernel memory or locked
- * user space pages).
- */
-dma_cookie_t
-dma_async_memcpy_buf_to_buf(struct dma_chan *chan, void *dest,
-			void *src, size_t len)
-{
-	struct dma_device *dev = chan->device;
-	struct dma_async_tx_descriptor *tx;
-	dma_addr_t dma_dest, dma_src;
-	dma_cookie_t cookie;
-	unsigned long flags;
+struct dmaengine_unmap_pool {
+	struct kmem_cache *cache;
+	const char *name;
+	mempool_t *pool;
+	size_t size;
+};
 
-	dma_src = dma_map_single(dev->dev, src, len, DMA_TO_DEVICE);
-	dma_dest = dma_map_single(dev->dev, dest, len, DMA_FROM_DEVICE);
-	flags = DMA_CTRL_ACK |
-		DMA_COMPL_SRC_UNMAP_SINGLE |
-		DMA_COMPL_DEST_UNMAP_SINGLE;
-	tx = dev->device_prep_dma_memcpy(chan, dma_dest, dma_src, len, flags);
+#define __UNMAP_POOL(x) { .size = x, .name = "dmaengine-unmap-" __stringify(x) }
+static struct dmaengine_unmap_pool unmap_pool[] = {
+	__UNMAP_POOL(2),
+	#if IS_ENABLED(CONFIG_ASYNC_TX_DMA)
+	__UNMAP_POOL(16),
+	__UNMAP_POOL(128),
+	__UNMAP_POOL(256),
+	#endif
+};
 
-	if (!tx) {
-		dma_unmap_single(dev->dev, dma_src, len, DMA_TO_DEVICE);
-		dma_unmap_single(dev->dev, dma_dest, len, DMA_FROM_DEVICE);
-		return -ENOMEM;
+static struct dmaengine_unmap_pool *__get_unmap_pool(int nr)
+{
+	int order = get_count_order(nr);
+
+	switch (order) {
+	case 0 ... 1:
+		return &unmap_pool[0];
+	case 2 ... 4:
+		return &unmap_pool[1];
+	case 5 ... 7:
+		return &unmap_pool[2];
+	case 8:
+		return &unmap_pool[3];
+	default:
+		BUG();
+		return NULL;
 	}
+}
 
-	tx->callback = NULL;
-	cookie = tx->tx_submit(tx);
+static void dmaengine_unmap(struct kref *kref)
+{
+	struct dmaengine_unmap_data *unmap = container_of(kref, typeof(*unmap), kref);
+	struct device *dev = unmap->dev;
+	int cnt, i;
+
+	cnt = unmap->to_cnt;
+	for (i = 0; i < cnt; i++)
+		dma_unmap_page(dev, unmap->addr[i], unmap->len,
+			       DMA_TO_DEVICE);
+	cnt += unmap->from_cnt;
+	for (; i < cnt; i++)
+		dma_unmap_page(dev, unmap->addr[i], unmap->len,
+			       DMA_FROM_DEVICE);
+	cnt += unmap->bidi_cnt;
+	for (; i < cnt; i++) {
+		if (unmap->addr[i] == 0)
+			continue;
+		dma_unmap_page(dev, unmap->addr[i], unmap->len,
+			       DMA_BIDIRECTIONAL);
+	}
+	mempool_free(unmap, __get_unmap_pool(cnt)->pool);
+}
 
-	preempt_disable();
-	__this_cpu_add(chan->local->bytes_transferred, len);
-	__this_cpu_inc(chan->local->memcpy_count);
-	preempt_enable();
+void dmaengine_unmap_put(struct dmaengine_unmap_data *unmap)
+{
+	if (unmap)
+		kref_put(&unmap->kref, dmaengine_unmap);
+}
+EXPORT_SYMBOL_GPL(dmaengine_unmap_put);
 
-	return cookie;
+static void dmaengine_destroy_unmap_pool(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(unmap_pool); i++) {
+		struct dmaengine_unmap_pool *p = &unmap_pool[i];
+
+