Merge tag 'dmaengine-4.5-rc1' of git://git.infradead.org/users/vkoul/slave-dma

Pull dmaengine updates from Vinod Koul:
 "This round we have few new features, new driver and updates to few
  drivers.

  The new features to dmaengine core are:
   - Synchronized transfer termination API to terminate the dmaengine
     transfers in synchronized and async fashion as required by users.
     We have its user now in ALSA dmaengine lib, img, at_xdma, axi_dmac
     drivers.
   - Universal API for channel request and start consolidation of
     request flows.  It's user is ompa-dma driver.
   - Introduce reuse of descriptors and use in pxa_dma driver

  Add/Remove:
   - New STM32 DMA driver
   - Removal of unused R-Car HPB-DMAC driver

  Updates:
   - ti-dma-crossbar updates for supporting eDMA
   - tegra-apb pm updates
   - idma64
   - mv_xor updates
   - ste_dma updates"

* tag 'dmaengine-4.5-rc1' of git://git.infradead.org/users/vkoul/slave-dma: (54 commits)
  dmaengine: mv_xor: add suspend/resume support
  dmaengine: mv_xor: de-duplicate mv_chan_set_mode*()
  dmaengine: mv_xor: remove mv_xor_chan->current_type field
  dmaengine: omap-dma: Add support for DMA filter mapping to slave devices
  dmaengine: edma: Add support for DMA filter mapping to slave devices
  dmaengine: core: Introduce new, universal API to request a channel
  dmaengine: core: Move and merge the code paths using private_candidate
  dmaengine: core: Skip mask matching when it is not provided to private_candidate
  dmaengine: mdc: Correct terminate_all handling
  dmaengine: edma: Add probe callback to edma_tptc_driver
  dmaengine: dw: fix potential memory leak in dw_dma_parse_dt()
  dmaengine: stm32-dma: Fix unchecked deference of chan->desc
  dmaengine: sh: Remove unused R-Car HPB-DMAC driver
  dmaengine: usb-dmac: Document SoC specific compatibility strings
  ste_dma40: Delete an unnecessary variable initialisation in d40_probe()
  ste_dma40: Delete another unnecessary check in d40_probe()
  ste_dma40: Delete an unnecessary check before the function call "kmem_cache_destroy"
  dmaengine: tegra-apb: Free interrupts before killing tasklets
  dmaengine: tegra-apb: Update driver to use GFP_NOWAIT
  dmaengine: tegra-apb: Only save channel state for those in use
  ...

32 files changed, 1771 insertions, 1044 deletions

diff --git a/drivers/dca/dca-core.c b/drivers/dca/dca-core.c
index 819dfda88236..7afbb28d6a0f 100644
--- a/drivers/dca/dca-core.c
+++ b/drivers/dca/dca-core.c
@@ -321,7 +321,8 @@ EXPORT_SYMBOL_GPL(dca_get_tag);
  * @ops - pointer to struct of dca operation function pointers
  * @priv_size - size of extra mem to be added for provider's needs
  */
-struct dca_provider *alloc_dca_provider(struct dca_ops *ops, int priv_size)
+struct dca_provider *alloc_dca_provider(const struct dca_ops *ops,
+					int priv_size)
 {
 	struct dca_provider *dca;
 	int alloc_size;
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index e6cd1a32025a..3a8ce67910c2 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -431,6 +431,18 @@ config STE_DMA40
 	help
 	  Support for ST-Ericsson DMA40 controller
 
+config STM32_DMA
+	bool "STMicroelectronics STM32 DMA support"
+	depends on ARCH_STM32
+	select DMA_ENGINE
+	select DMA_OF
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Enable support for the on-chip DMA controller on STMicroelectronics
+	  STM32 MCUs.
+	  If you have a board based on such a MCU and wish to use DMA say Y or M
+	  here.
+
 config S3C24XX_DMAC
 	tristate "Samsung S3C24XX DMA support"
 	depends on ARCH_S3C24XX
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index ef9c099bd2b6..2dd0a067a0ca 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -56,6 +56,7 @@ obj-$(CONFIG_QCOM_BAM_DMA) += qcom_bam_dma.o
 obj-$(CONFIG_RENESAS_DMA) += sh/
 obj-$(CONFIG_SIRF_DMA) += sirf-dma.o
 obj-$(CONFIG_STE_DMA40) += ste_dma40.o ste_dma40_ll.o
+obj-$(CONFIG_STM32_DMA) += stm32-dma.o
 obj-$(CONFIG_S3C24XX_DMAC) += s3c24xx-dma.o
 obj-$(CONFIG_TXX9_DMAC) += txx9dmac.o
 obj-$(CONFIG_TEGRA20_APB_DMA) += tegra20-apb-dma.o
diff --git a/drivers/dma/acpi-dma.c b/drivers/dma/acpi-dma.c
index 16d0daa058a5..eed6bda01790 100644
--- a/drivers/dma/acpi-dma.c
+++ b/drivers/dma/acpi-dma.c
@@ -15,6 +15,7 @@
 #include <linux/device.h>
 #include <linux/err.h>
 #include <linux/module.h>
+#include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
@@ -72,7 +73,9 @@ static int acpi_dma_parse_resource_group(const struct acpi_csrt_group *grp,
 	si = (const struct acpi_csrt_shared_info *)&grp[1];
 
 	/* Match device by MMIO and IRQ */
-	if (si->mmio_base_low != mem || si->gsi_interrupt != irq)
+	if (si->mmio_base_low != lower_32_bits(mem) ||
+	    si->mmio_base_high != upper_32_bits(mem) ||
+	    si->gsi_interrupt != irq)
 		return 0;
 
 	dev_dbg(&adev->dev, "matches with %.4s%04X (rev %u)\n",
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index 370c661c7d7b..39f59666f93f 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -863,8 +863,12 @@ at_xdmac_interleaved_queue_desc(struct dma_chan *chan,
 	 * access. Hopefully we can access DDR through both ports (at least on
 	 * SAMA5D4x), so we can use the same interface for source and dest,
 	 * that solves the fact we don't know the direction.
+	 * ERRATA: Even if useless for memory transfers, the PERID has to not
+	 * match the one of another channel. If not, it could lead to spurious
+	 * flag status.
 	 */
-	u32			chan_cc = AT_XDMAC_CC_DIF(0)
+	u32			chan_cc = AT_XDMAC_CC_PERID(0x3f)
+					| AT_XDMAC_CC_DIF(0)
 					| AT_XDMAC_CC_SIF(0)
 					| AT_XDMAC_CC_MBSIZE_SIXTEEN
 					| AT_XDMAC_CC_TYPE_MEM_TRAN;
@@ -1041,8 +1045,12 @@ at_xdmac_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 	 * access DDR through both ports (at least on SAMA5D4x), so we can use
 	 * the same interface for source and dest, that solves the fact we
 	 * don't know the direction.
+	 * ERRATA: Even if useless for memory transfers, the PERID has to not
+	 * match the one of another channel. If not, it could lead to spurious
+	 * flag status.
 	 */
-	u32			chan_cc = AT_XDMAC_CC_DAM_INCREMENTED_AM
+	u32			chan_cc = AT_XDMAC_CC_PERID(0x3f)
+					| AT_XDMAC_CC_DAM_INCREMENTED_AM
 					| AT_XDMAC_CC_SAM_INCREMENTED_AM
 					| AT_XDMAC_CC_DIF(0)
 					| AT_XDMAC_CC_SIF(0)
@@ -1143,8 +1151,12 @@ static struct at_xdmac_desc *at_xdmac_memset_create_desc(struct dma_chan *chan,
 	 * access. Hopefully we can access DDR through both ports (at least on
 	 * SAMA5D4x), so we can use the same interface for source and dest,
 	 * that solves the fact we don't know the direction.
+	 * ERRATA: Even if useless for memory transfers, the PERID has to not
+	 * match the one of another channel. If not, it could lead to spurious
+	 * flag status.
 	 */
-	u32			chan_cc = AT_XDMAC_CC_DAM_UBS_AM
+	u32			chan_cc = AT_XDMAC_CC_PERID(0x3f)
+					| AT_XDMAC_CC_DAM_UBS_AM
 					| AT_XDMAC_CC_SAM_INCREMENTED_AM
 					| AT_XDMAC_CC_DIF(0)
 					| AT_XDMAC_CC_SIF(0)
@@ -1998,8 +2010,6 @@ static int at_xdmac_remove(struct platform_device *pdev)
 	dma_async_device_unregister(&atxdmac->dma);
 	clk_disable_unprepare(atxdmac->clk);
 
-	synchronize_irq(atxdmac->irq);
-
 	free_irq(atxdmac->irq, atxdmac->dma.dev);
 
 	for (i = 0; i < atxdmac->dma.chancnt; i++) {
diff --git a/drivers/dma/dma-axi-dmac.c b/drivers/dma/dma-axi-dmac.c
index 5b2395e7e04d..c3468094393e 100644
--- a/drivers/dma/dma-axi-dmac.c
+++ b/drivers/dma/dma-axi-dmac.c
@@ -307,6 +307,13 @@ static int axi_dmac_terminate_all(struct dma_chan *c)
 	return 0;
 }
 
+static void axi_dmac_synchronize(struct dma_chan *c)
+{
+	struct axi_dmac_chan *chan = to_axi_dmac_chan(c);
+
+	vchan_synchronize(&chan->vchan);
+}
+
 static void axi_dmac_issue_pending(struct dma_chan *c)
 {
 	struct axi_dmac_chan *chan = to_axi_dmac_chan(c);
@@ -613,6 +620,7 @@ static int axi_dmac_probe(struct platform_device *pdev)
 	dma_dev->device_prep_dma_cyclic = axi_dmac_prep_dma_cyclic;
 	dma_dev->device_prep_interleaved_dma = axi_dmac_prep_interleaved;
 	dma_dev->device_terminate_all = axi_dmac_terminate_all;
+	dma_dev->device_synchronize = axi_dmac_synchronize;
 	dma_dev->dev = &pdev->dev;
 	dma_dev->chancnt = 1;
 	dma_dev->src_addr_widths = BIT(dmac->chan.src_width);
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 3ecec1445adf..c50a247be2e0 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -43,6 +43,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
 #include <linux/init.h>
 #include <linux/module.h>
@@ -265,8 +266,11 @@ static void dma_chan_put(struct dma_chan *chan)
 	module_put(dma_chan_to_owner(chan));
 
 	/* This channel is not in use anymore, free it */
-	if (!chan->client_count && chan->device->device_free_chan_resources)
+	if (!chan->client_count && chan->device->device_free_chan_resources) {
+		/* Make sure all operations have completed */
+		dmaengine_synchronize(chan);
 		chan->device->device_free_chan_resources(chan);
+	}
 
 	/* If the channel is used via a DMA request router, free the mapping */
 	if (chan->router && chan->router->route_free) {
@@ -493,6 +497,7 @@ int dma_get_slave_caps(struct dma_chan *chan, struct dma_slave_caps *caps)
 	caps->dst_addr_widths = device->dst_addr_widths;
 	caps->directions = device->directions;
 	caps->residue_granularity = device->residue_granularity;
+	caps->descriptor_reuse = device->descriptor_reuse;
 
 	/*
 	 * Some devices implement only pause (e.g. to get residuum) but no
@@ -511,7 +516,7 @@ static struct dma_chan *private_candidate(const dma_cap_mask_t *mask,
 {
 	struct dma_chan *chan;
 
-	if (!__dma_device_satisfies_mask(dev, mask)) {
+	if (mask && !__dma_device_satisfies_mask(dev, mask)) {
 		pr_debug("%s: wrong capabilities\n", __func__);
 		return NULL;
 	}
@@ -542,6 +547,42 @@ static struct dma_chan *private_candidate(const dma_cap_mask_t *mask,
 	return NULL;
 }
 
+static struct dma_chan *find_candidate(struct dma_device *device,
+				       const dma_cap_mask_t *mask,
+				       dma_filter_fn fn, void *fn_param)
+{
+	struct dma_chan *chan = private_candidate(mask, device, fn, fn_param);
+	int err;
+
+	if (chan) {
+		/* Found a suitable channel, try to grab, prep, and return it.
+		 * We first set DMA_PRIVATE to disable balance_ref_count as this
+		 * channel will not be published in the general-purpose
+		 * allocator
+		 */
+		dma_cap_set(DMA_PRIVATE, device->cap_mask);
+		device->privatecnt++;
+		err = dma_chan_get(chan);
+
+		if (err) {
+			if (err == -ENODEV) {
+				pr_debug("%s: %s module removed\n", __func__,
+					 dma_chan_name(chan));
+				list_del_rcu(&device->global_node);
+			} else
+				pr_debug("%s: failed to get %s: (%d)\n",
+					 __func__, dma_chan_name(chan), err);
+
+			if (--device->privatecnt == 0)
+				dma_cap_clear(DMA_PRIVATE, device->cap_mask);
+
+			chan = ERR_PTR(err);
+		}
+	}
+
+	return chan ? chan : ERR_PTR(-EPROBE_DEFER);
+}
+
 /**
  * dma_get_slave_channel - try to get specific channel exclusively
  * @chan: target channel
@@ -580,7 +621,6 @@ struct dma_chan *dma_get_any_slave_channel(struct dma_device *device)
 {
 	dma_cap_mask_t mask;
 	struct dma_chan *chan;
-	int err;
 
 	dma_cap_zero(mask);
 	dma_cap_set(DMA_SLAVE, mask);
@@ -588,23 +628,11 @@ struct dma_chan *dma_get_any_slave_channel(struct dma_device *device)
 	/* lock against __dma_request_channel */
 	mutex_lock(&dma_list_mutex);
 
-	chan = private_candidate(&mask, device, NULL, NULL);
-	if (chan) {
-		dma_cap_set(DMA_PRIVATE, device->cap_mask);
-		device->privatecnt++;
-		err = dma_chan_get(chan);
-		if (err) {
-			pr_debug("%s: failed to get %s: (%d)\n",
-				__func__, dma_chan_name(chan), err);
-			chan = NULL;
-			if (--device->privatecnt == 0)
-				dma_cap_clear(DMA_PRIVATE, device->cap_mask);
-		}
-	}
+	chan = find_candidate(device, &mask, NULL, NULL);
 
 	mutex_unlock(&dma_list_mutex);
 
-	return chan;
+	return IS_ERR(chan) ? NULL : chan;
 }
 EXPORT_SYMBOL_GPL(dma_get_any_slave_channel);
 
@@ -621,35 +649,15 @@ struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask,
 {
 	struct dma_device *device, *_d;
 	struct dma_chan *chan = NULL;
-	int err;
 
 	/* Find a channel */
 	mutex_lock(&dma_list_mutex);
 	list_for_each_entry_safe(device, _d, &dma_device_list, global_node) {
-		chan = private_candidate(mask, device, fn, fn_param);
-		if (chan) {
-			/* Found a suitable channel, try to grab, prep, and
-			 * return it.  We first set DMA_PRIVATE to disable
-			 * balance_ref_count as this channel will not be
-			 * published in the general-purpose allocator
-			 */
-			dma_cap_set(DMA_PRIVATE, device->cap_mask);
-			device->privatecnt++;
-			err = dma_chan_get(chan);
+		chan = find_candidate(device, mask, fn, fn_param);
+		if (!IS_ERR(chan))
+			break;
 
-			if (err == -ENODEV) {
-				pr_debug("%s: %s module removed\n",
-					 __func__, dma_chan_name(chan));
-				list_del_rcu(&device->global_node);
-			} else if (err)
-				pr_debug("%s: failed to get %s: (%d)\n",
-					 __func__, dma_chan_name(chan), err);
-			else
-				break;
-			if (--device->privatecnt == 0)
-				dma_cap_clear(DMA_PRIVATE, device->cap_mask);
-			chan = NULL;
-		}
+		chan = NULL;
 	}
 	mutex_unlock(&dma_list_mutex);
 
@@ -662,27 +670,73 @@ struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask,
 }
 EXPORT_SYMBOL_GPL(__dma_request_channel);
 
+static const struct dma_slave_map *dma_filter_match(struct dma_device *device,
+						    const char *name,
+						    struct device *dev)
+{
+	int i;
+
+	if (!device->filter.mapcnt)
+		return NULL;
+
+	for (i = 0; i < device->filter.mapcnt; i++) {
+		const struct dma_slave_map *map = &device->filter.map[i];
+
+		if (!strcmp(map->devname, dev_name(dev)) &&
+		    !strcmp(map->slave, name))
+			return map;
+	}
+
+	return NULL;
+}
+
 /**
- * dma_request_slave_channel_reason - try to allocate an exclusive slave channel
+ * dma_request_chan - try to allocate an exclusive slave channel
  * @dev:	pointer to client device structure
  * @name:	slave channel name
  *
  * Returns pointer to appropriate DMA channel on success or an error pointer.
  */
-struct dma_chan *dma_request_slave_channel_reason(struct device *dev,
-						  const char *name)
+struct dma_chan *dma_request_chan(struct device *dev, const char *name)
 {
+	struct dma_device *d, *_d;
+	struct dma_chan *chan = NULL;
+
 	/* If device-tree is present get slave info from here */
 	if (dev->of_node)
-		return of_dma_request_slave_channel(dev->of_node, name);
+		chan = of_dma_request_slave_channel(dev->of_node, name);
 
 	/* If device was enumerated by ACPI get slave info from here */
-	if (ACPI_HANDLE(dev))
-		return acpi_dma_request_slave_chan_by_name(dev, name);
+	if (has_acpi_companion(dev) && !chan)
+		chan = acpi_dma_request_slave_chan_by_name(dev, name);
+
+	if (chan) {
+		/* Valid channel found or requester need to be deferred */
+		if (!IS_ERR(chan) || PTR_ERR(chan) == -EPROBE_DEFER)
+			return chan;
+	}
 
-	return ERR_PTR(-ENODEV);
+	/* Try to find the channel via the DMA filter map(s) */
+	mutex_lock(&dma_list_mutex);
+	list_for_each_entry_safe(d, _d, &dma_device_list, global_node) {
+		dma_cap_mask_t mask;
+		const struct dma_slave_map *map = dma_filter_match(d, name, dev);
+
+		if (!map)
+			continue;
+
+		dma_cap_zero(mask);
+		dma_cap_set(DMA_SLAVE, mask);
+
+		chan = find_candidate(d, &mask, d->filter.fn, map->param);
+		if (!IS_ERR(chan))
+			break;
+	}
+	mutex_unlock(&dma_list_mutex);
+
+	return chan ? chan : ERR_PTR(-EPROBE_DEFER);
 }
-EXPORT_SYMBOL_GPL(dma_request_slave_channel_reason);
+EXPORT_SYMBOL_GPL(dma_request_chan);
 
 /**
  * dma_request_slave_channel - try to allocate an exclusive slave channel
@@ -694,17 +748,35 @@ EXPORT_SYMBOL_GPL(dma_request_slave_channel_reason);
 struct dma_chan *dma_request_slave_channel(struct device *dev,
 					   const char *name)
 {
-	struct dma_chan *ch = dma_request_slave_channel_reason(dev, name);
+	struct dma_chan *ch = dma_request_chan(dev, name);
 	if (IS_ERR(ch))
 		return NULL;
 
-	dma_cap_set(DMA_PRIVATE, ch->device->cap_mask);
-	ch->device->privatecnt++;
-
 	return ch;
 }
 EXPORT_SYMBOL_GPL(dma_request_slave_channel);
 
+/**
+ * dma_request_chan_by_mask - allocate a channel satisfying certain capabilities
+ * @mask: capabilities that the channel must satisfy
+ *
+ * Returns pointer to appropriate DMA channel on success or an error pointer.
+ */
+struct dma_chan *dma_request_chan_by_mask(const dma_cap_mask_t *mask)
+{
+	struct dma_chan *chan;
+
+	if (!mask)
+		return ERR_PTR(-ENODEV);
+
+	chan = __dma_request_channel(mask, NULL, NULL);
+	if (!chan)
+		chan = ERR_PTR(-ENODEV);
+
+	return chan;
+}
+EXPORT_SYMBOL_GPL(dma_request_chan_by_mask);
+
 void dma_release_channel(struct dma_chan *chan)
 {
 	mutex_lock(&dma_list_mutex);
diff --git a/drivers/dma/dw/platform.c b/drivers/dma/dw/platform.c
index 127093a0c0e8..26edbe3a27ac 100644
--- a/drivers/dma/dw/platform.c
+++ b/drivers/dma/dw/platform.c
@@ -103,18 +103,21 @@ dw_dma_parse_dt(struct platform_device *pdev)
 	struct device_node *np = pdev->dev.of_node;
 	struct dw_dma_platform_data *pdata;
 	u32 tmp, arr[DW_DMA_MAX_NR_MASTERS];
+	u32 nr_channels;
 
 	if (!np) {
 		dev_err(&pdev->dev, "Missing DT data\n");
 		return NULL;
 	}
 
+	if (of_property_read_u32(np, "dma-channels", &nr_channels))
+		return NULL;
+
 	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
 	if (!pdata)
 		return NULL;
 
-	if (of_property_read_u32(np, "dma-channels", &pdata->nr_channels))
-		return NULL;
+	pdata->nr_channels = nr_channels;
 
 	if (of_property_read_bool(np, "is_private"))
 		pdata->is_private = true;
diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c
index 16fe773fb846..50584015e046 100644
--- a/drivers/dma/edma.c
+++ b/drivers/dma/edma.c
@@ -2314,6 +2314,10 @@ static int edma_probe(struct platform_device *pdev)
 		edma_set_chmap(&ecc->slave_chans[i], ecc->dummy_slot);
 	}
 
+	ecc->dma_slave.filter.map = info->slave_map;
+	ecc->dma_slave.filter.mapcnt = info->slavecnt;
+	ecc->dma_slave.filter.fn = edma_filter_fn;
+
 	ret = dma_async_device_register(&ecc->dma_slave);
 	if (ret) {
 		dev_err(dev, "slave ddev registration failed (%d)\n", ret);
@@ -2421,7 +2425,13 @@ static struct platform_driver edma_driver = {
 	},
 };
 
+static int edma_tptc_probe(struct platform_device *pdev)
+{
+	return 0;
+}
+
 static struct platform_driver edma_tptc_driver = {
+	.probe		= edma_tptc_probe,
 	.driver = {
 		.name	= "edma3-tptc",
 		.of_match_table = edma_tptc_of_ids,
diff --git a/drivers/dma/fsl-edma.c b/drivers/dma/fsl-edma.c
index 915eec3cc279..be2e62b87948 100644
--- a/drivers/dma/fsl-edma.c
+++ b/drivers/dma/fsl-edma.c
@@ -116,6 +116,10 @@
 				BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | \
 				BIT(DMA_SLAVE_BUSWIDTH_4_BYTES) | \
 				BIT(DMA_SLAVE_BUSWIDTH_8_BYTES)
+enum fsl_edma_pm_state {
+	RUNNING = 0,
+	SUSPENDED,
+};
 
 struct fsl_edma_hw_tcd {
 	__le32	saddr;
@@ -147,6 +151,9 @@ struct fsl_edma_slave_config {
 struct fsl_edma_chan {
 	struct virt_dma_chan		vchan;
 	enum dma_status			status;
+	enum fsl_edma_pm_state		pm_state;
+	bool				idle;
+	u32				slave_id;
 	struct fsl_edma_engine		*edma;
 	struct fsl_edma_desc		*edesc;
 	struct fsl_edma_slave_config	fsc;
@@ -298,6 +305,7 @@ static int fsl_edma_terminate_all(struct dma_chan *chan)
 	spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
 	fsl_edma_disable_request(fsl_chan);
 	fsl_chan->edesc = NULL;
+	fsl_chan->idle = true;
 	vchan_get_all_descriptors(&fsl_chan->vchan, &head);
 	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
 	vchan_dma_desc_free_list(&fsl_chan->vchan, &head);
@@ -313,6 +321,7 @@ static int fsl_edma_pause(struct dma_chan *chan)
 	if (fsl_chan->edesc) {
 		fsl_edma_disable_request(fsl_chan);
 		fsl_chan->status = DMA_PAUSED;
+		fsl_chan->idle = true;
 	}
 	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
 	return 0;
@@ -327,6 +336,7 @@ static int fsl_edma_resume(struct dma_chan *chan)
 	if (fsl_chan->edesc) {
 		fsl_edma_enable_request(fsl_chan);
 		fsl_chan->status = DMA_IN_PROGRESS;
+		fsl_chan->idle = false;
 	}
 	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
 	return 0;
@@ -648,6 +658,7 @@ static void fsl_edma_xfer_desc(struct fsl_edma_chan *fsl_chan)
 	fsl_edma_set_tcd_regs(fsl_chan, fsl_chan->edesc->tcd[0].vtcd);
 	fsl_edma_enable_request(fsl_chan);
 	fsl_chan->status = DMA_IN_PROGRESS;
+	fsl_chan->idle = false;
 }
 
 static irqreturn_t fsl_edma_tx_handler(int irq, void *dev_id)
@@ -676,6 +687,7 @@ static irqreturn_t fsl_edma_tx_handler(int irq, void *dev_id)
 				vchan_cookie_complete(&fsl_chan->edesc->vdesc);
 				fsl_chan->edesc = NULL;
 				fsl_chan->status = DMA_COMPLETE;
+				fsl_chan->idle = true;
 			} else {
 				vchan_cyclic_callback(&fsl_chan->edesc->vdesc);
 			}
@@ -704,6 +716,7 @@ static irqreturn_t fsl_edma_err_handler(int irq, void *dev_id)
 			edma_writeb(fsl_edma, EDMA_CERR_CERR(ch),
 				fsl_edma->membase + EDMA_CERR);
 			fsl_edma->chans[ch].status = DMA_ERROR;
+			fsl_edma->chans[ch].idle = true;
 		}
 	}
 	return IRQ_HANDLED;
@@ -724,6 +737,12 @@ static void fsl_edma_issue_pending(struct dma_chan *chan)
 
 	spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
 
+	if (unlikely(fsl_chan->pm_state != RUNNING)) {
+		spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
+		/* cannot submit due to suspend */
+		return;
+	}
+
 	if (vchan_issue_pending(&fsl_chan->vchan) && !fsl_chan->edesc)
 		fsl_edma_xfer_desc(fsl_chan);
 
@@ -735,6 +754,7 @@ static struct dma_chan *fsl_edma_xlate(struct of_phandle_args *dma_spec,
 {
 	struct fsl_edma_engine *fsl_edma = ofdma->of_dma_data;
 	struct dma_chan *chan, *_chan;
+	struct fsl_edma_chan *fsl_chan;
 	unsigned long chans_per_mux = fsl_edma->n_chans / DMAMUX_NR;
 
 	if (dma_spec->args_count != 2)
@@ -748,8 +768,10 @@ static struct dma_chan *fsl_edma_xlate(struct of_phandle_args *dma_spec,
 			chan = dma_get_slave_channel(chan);
 			if (chan) {
 				chan->device->privatecnt++;
-				fsl_edma_chan_mux(to_fsl_edma_chan(chan),
-					dma_spec->args[1], true);
+				fsl_chan = to_fsl_edma_chan(chan);
+				fsl_chan->slave_id = dma_spec->args[1];
+				fsl_edma_chan_mux(fsl_chan, fsl_chan->slave_id,
+						true);
 				mutex_unlock(&fsl_edma->fsl_edma_mutex);
 				return chan;
 			}
@@ -888,7 +910,9 @@ static int fsl_edma_probe(struct platform_device *pdev)
 		struct fsl_edma_chan *fsl_chan = &fsl_edma->chans[i];
 
 		fsl_chan->edma = fsl_edma;
-
+		fsl_chan->pm_state = RUNNING;
+		fsl_chan->slave_id = 0;
+		fsl_chan->idle = true;
 		fsl_chan->vchan.desc_free = fsl_edma_free_desc;
 		vchan_init(&fsl_chan->vchan, &fsl_edma->dma_dev);
 
@@ -959,6 +983,60 @@ static int fsl_edma_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static int fsl_edma_suspend_late(struct device *dev)
+{
+	struct fsl_edma_engine *fsl_edma = dev_get_drvdata(dev);
+	struct fsl_edma_chan *fsl_chan;
+	unsigned long flags;
+	int i;
+
+	for (i = 0; i < fsl_edma->n_chans; i++) {
+		fsl_chan = &fsl_edma->chans[i];
+		spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
+		/* Make sure chan is idle or will force disable. */
+		if (unlikely(!fsl_chan->idle)) {
+			dev_warn(dev, "WARN: There is non-idle channel.");
+			fsl_edma_disable_request(fsl_chan);
+			fsl_edma_chan_mux(fsl_chan, 0, false);
+		}
+
+		fsl_chan->pm_state = SUSPENDED;
+		spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
+	}
+
+	return 0;
+}
+
+static int fsl_edma_resume_early(struct device *dev)
+{
+	struct fsl_edma_engine *fsl_edma = dev_get_drvdata(dev);
+	struct fsl_edma_chan *fsl_chan;
+	int i;
+
+	for (i = 0; i < fsl_edma->n_chans; i++) {
+		fsl_chan = &fsl_edma->chans[i];
+		fsl_chan->pm_state = RUNNING;
+		edma_writew(fsl_edma, 0x0, fsl_edma->membase + EDMA_TCD_CSR(i));
+		if (fsl_chan->slave_id != 0)
+			fsl_edma_chan_mux(fsl_chan, fsl_chan->slave_id, true);
+	}
+
+	edma_writel(fsl_edma, EDMA_CR_ERGA | EDMA_CR_ERCA,
+			fsl_edma->membase + EDMA_CR);
+
+	return 0;
+}
+
+/*
+ * eDMA provides the service to others, so it should be suspend late
+ * and resume early. When eDMA suspend, all of the clients should stop
+ * the DMA data transmission and let the channel idle.
+ */
+static const struct dev_pm_ops fsl_edma_pm_ops = {
+	.suspend_late   = fsl_edma_suspend_late,
+	.resume_early   = fsl_edma_resume_early,
+};
+
 static const struct of_device_id fsl_edma_dt_ids[] = {
 	{ .compatible = "fsl,vf610-edma", },
 	{ /* sentinel */ }
@@ -969,6 +1047,7 @@ static struct platform_driver fsl_edma_driver = {
 	.driver		= {
 		.name	= "fsl-edma",
 		.of_match_table = fsl_edma_dt_ids,
+		.pm     = &fsl_edma_pm_ops,
 	},
 	.probe          = fsl_edma_probe,
 	.remove		= fsl_edma_remove,
diff --git a/drivers/dma/hsu/hsu.c b/drivers/dma/hsu/hsu.c
index 823ad728aecf..eef145edb936 100644
--- a/drivers/dma/hsu/hsu.c
+++ b/drivers/dma/hsu/hsu.c
@@ -228,6 +228,8 @@ static struct dma_async_tx_descriptor *hsu_dma_prep_slave_sg(
 	for_each_sg(sgl, sg, sg_len, i) {
 		desc->sg[i].addr = sg_dma_address(sg);
 		desc->sg[i].len = sg_dma_len(sg);
+
+		desc->length += sg_dma_len(sg);
 	}
 
 	desc->nents = sg_len;
@@ -249,21 +251,10 @@ static void hsu_dma_issue_pending(struct dma_chan *chan)
 	spin_unlock_irqrestore(&hsuc->vchan.lock, flags);
 }
 
-static size_t hsu_dma_desc_size(struct hsu_dma_desc *desc)
-{
-	size_t bytes = 0;
-	unsigned int i;
-
-	for (i = desc->active; i < desc->nents; i++)
-		bytes += desc->sg[i].len;
-
-	return bytes;
-}
-
 static size_t hsu_dma_active_desc_size(struct hsu_dma_chan *hsuc)
 {
 	struct hsu_dma_desc *desc = hsuc->desc;
-	size_t bytes = hsu_dma_desc_size(desc);
+	size_t bytes = desc->length;
 	int i;
 
 	i = desc->active % HSU_DMA_CHAN_NR_DESC;
@@ -294,7 +285,7 @@ static enum dma_status hsu_dma_tx_status(struct dma_chan *chan,
 		dma_set_residue(state, bytes);
 		status = hsuc->desc->status;
 	} else if (vdesc) {
-		bytes = hsu_dma_desc_size(to_hsu_dma_desc(vdesc));
+		bytes = to_hsu_dma_desc(vdesc)->length;
 		dma_set_residue(state, bytes);
 	}
 	spin_unlock_irqrestore(&hsuc->vchan.lock, flags);
diff --git a/drivers/dma/hsu/hsu.h b/drivers/dma/hsu/hsu.h
index f06579c6d548..578a8ee8cd05 100644
--- a/drivers/dma/hsu/hsu.h
+++ b/drivers/dma/hsu/hsu.h
@@ -65,6 +65,7 @@ struct hsu_dma_desc {
 	enum dma_transfer_direction direction;
 	struct hsu_dma_sg *sg;
 	unsigned int nents;
+	size_t length;
 	unsigned int active;
 	enum dma_status status;
 };
diff --git a/drivers/dma/idma64.c b/drivers/dma/idma64.c
index 7d56b47e4fcf..3cb7b2c78197 100644
--- a/drivers/dma/idma64.c
+++ b/drivers/dma/idma64.c
@@ -178,20 +178,12 @@ static irqreturn_t idma64_irq(int irq, void *dev)
 	if (!status)
 		return IRQ_NONE;
 
-	/* Disable interrupts */
-	channel_clear_bit(idma64, MASK(XFER), idma64->all_chan_mask);
-	channel_clear_bit(idma64, MASK(ERROR), idma64->all_chan_mask);
-
 	status_xfer = dma_readl(idma64, RAW(XFER));
 	status_err = dma_readl(idma64, RAW(ERROR));
 
 	for (i = 0; i < idma64->dma.chancnt; i++)
 		idma64_chan_irq(idma64, i, status_err, status_xfer);
 
-	/* Re-enable interrupts */
-	channel_set_bit(idma64, MASK(XFER), idma64->all_chan_mask);
-	channel_set_bit(idma64, MASK(ERROR), idma64->all_chan_mask);
-
 	return IRQ_HANDLED;
 }
 
@@ -239,7 +231,7 @@ static void idma64_vdesc_free(struct virt_dma_desc *vdesc)
 	idma64_desc_free(idma64c, to_idma64_desc(vdesc));
 }