Merge tag 'v5.6' into next

Sync up with mainline to get device tree and other changes.

52 files changed, 12180 insertions, 386 deletions

diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 6fa1eba9d477..5142da401db3 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -239,6 +239,14 @@ config FSL_RAID
 	  the capability to offload memcpy, xor and pq computation
 	  for raid5/6.
 
+config HISI_DMA
+	tristate "HiSilicon DMA Engine support"
+	depends on ARM64 || (COMPILE_TEST && PCI_MSI)
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Support HiSilicon Kunpeng DMA engine.
+
 config IMG_MDC_DMA
 	tristate "IMG MDC support"
 	depends on MIPS || COMPILE_TEST
@@ -273,6 +281,19 @@ config INTEL_IDMA64
 	  Enable DMA support for Intel Low Power Subsystem such as found on
 	  Intel Skylake PCH.
 
+config INTEL_IDXD
+	tristate "Intel Data Accelerators support"
+	depends on PCI && X86_64
+	select DMA_ENGINE
+	select SBITMAP
+	help
+	  Enable support for the Intel(R) data accelerators present
+	  in Intel Xeon CPU.
+
+	  Say Y if you have such a platform.
+
+	  If unsure, say N.
+
 config INTEL_IOATDMA
 	tristate "Intel I/OAT DMA support"
 	depends on PCI && X86_64
@@ -497,6 +518,15 @@ config PXA_DMA
 	  16 to 32 channels for peripheral to memory or memory to memory
 	  transfers.
 
+config PLX_DMA
+	tristate "PLX ExpressLane PEX Switch DMA Engine Support"
+	depends on PCI
+	select DMA_ENGINE
+	help
+	  Some PLX ExpressLane PCI Switches support additional DMA engines.
+	  These are exposed via extra functions on the switch's
+	  upstream port. Each function exposes one DMA channel.
+
 config SIRF_DMA
 	tristate "CSR SiRFprimaII/SiRFmarco DMA support"
 	depends on ARCH_SIRF
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index 42d7e2fc64fa..1d908394fbea 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -35,12 +35,14 @@ obj-$(CONFIG_FSL_EDMA) += fsl-edma.o fsl-edma-common.o
 obj-$(CONFIG_MCF_EDMA) += mcf-edma.o fsl-edma-common.o
 obj-$(CONFIG_FSL_QDMA) += fsl-qdma.o
 obj-$(CONFIG_FSL_RAID) += fsl_raid.o
+obj-$(CONFIG_HISI_DMA) += hisi_dma.o
 obj-$(CONFIG_HSU_DMA) += hsu/
 obj-$(CONFIG_IMG_MDC_DMA) += img-mdc-dma.o
 obj-$(CONFIG_IMX_DMA) += imx-dma.o
 obj-$(CONFIG_IMX_SDMA) += imx-sdma.o
 obj-$(CONFIG_INTEL_IDMA64) += idma64.o
 obj-$(CONFIG_INTEL_IOATDMA) += ioat/
+obj-$(CONFIG_INTEL_IDXD) += idxd/
 obj-$(CONFIG_INTEL_IOP_ADMA) += iop-adma.o
 obj-$(CONFIG_INTEL_MIC_X100_DMA) += mic_x100_dma.o
 obj-$(CONFIG_K3_DMA) += k3dma.o
@@ -59,6 +61,7 @@ obj-$(CONFIG_NBPFAXI_DMA) += nbpfaxi.o
 obj-$(CONFIG_OWL_DMA) += owl-dma.o
 obj-$(CONFIG_PCH_DMA) += pch_dma.o
 obj-$(CONFIG_PL330_DMA) += pl330.o
+obj-$(CONFIG_PLX_DMA) += plx_dma.o
 obj-$(CONFIG_PPC_BESTCOMM) += bestcomm/
 obj-$(CONFIG_PXA_DMA) += pxa_dma.o
 obj-$(CONFIG_RENESAS_DMA) += sh/
diff --git a/drivers/dma/altera-msgdma.c b/drivers/dma/altera-msgdma.c
index 832aefbe7af9..539e785039ca 100644
--- a/drivers/dma/altera-msgdma.c
+++ b/drivers/dma/altera-msgdma.c
@@ -772,10 +772,10 @@ static int request_and_map(struct platform_device *pdev, const char *name,
 		return -EBUSY;
 	}
 
-	*ptr = devm_ioremap_nocache(device, region->start,
+	*ptr = devm_ioremap(device, region->start,
 				    resource_size(region));
 	if (*ptr == NULL) {
-		dev_err(device, "ioremap_nocache of %s failed!", name);
+		dev_err(device, "ioremap of %s failed!", name);
 		return -ENOMEM;
 	}
 
diff --git a/drivers/dma/bcm2835-dma.c b/drivers/dma/bcm2835-dma.c
index e4c593f48575..4768ef26013b 100644
--- a/drivers/dma/bcm2835-dma.c
+++ b/drivers/dma/bcm2835-dma.c
@@ -797,10 +797,7 @@ static int bcm2835_dma_terminate_all(struct dma_chan *chan)
 
 	/* stop DMA activity */
 	if (c->desc) {
-		if (c->desc->vd.tx.flags & DMA_PREP_INTERRUPT)
-			vchan_terminate_vdesc(&c->desc->vd);
-		else
-			vchan_vdesc_fini(&c->desc->vd);
+		vchan_terminate_vdesc(&c->desc->vd);
 		c->desc = NULL;
 		bcm2835_dma_abort(c);
 	}
diff --git a/drivers/dma/coh901318.c b/drivers/dma/coh901318.c
index e51d836afcc7..1092d4ce723e 100644
--- a/drivers/dma/coh901318.c
+++ b/drivers/dma/coh901318.c
@@ -1947,8 +1947,6 @@ static void dma_tc_handle(struct coh901318_chan *cohc)
 		return;
 	}
 
-	spin_lock(&cohc->lock);
-
 	/*
 	 * When we reach this point, at least one queue item
 	 * should have been moved over from cohc->queue to
@@ -1969,8 +1967,6 @@ static void dma_tc_handle(struct coh901318_chan *cohc)
 	if (coh901318_queue_start(cohc) == NULL)
 		cohc->busy = 0;
 
-	spin_unlock(&cohc->lock);
-
 	/*
 	 * This tasklet will remove items from cohc->active
 	 * and thus terminates them.
diff --git a/drivers/dma/dma-axi-dmac.c b/drivers/dma/dma-axi-dmac.c
index a0ee404b736e..f1d149e32839 100644
--- a/drivers/dma/dma-axi-dmac.c
+++ b/drivers/dma/dma-axi-dmac.c
@@ -830,6 +830,7 @@ static int axi_dmac_probe(struct platform_device *pdev)
 	struct dma_device *dma_dev;
 	struct axi_dmac *dmac;
 	struct resource *res;
+	struct regmap *regmap;
 	int ret;
 
 	dmac = devm_kzalloc(&pdev->dev, sizeof(*dmac), GFP_KERNEL);
@@ -921,10 +922,17 @@ static int axi_dmac_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, dmac);
 
-	devm_regmap_init_mmio(&pdev->dev, dmac->base, &axi_dmac_regmap_config);
+	regmap = devm_regmap_init_mmio(&pdev->dev, dmac->base,
+		 &axi_dmac_regmap_config);
+	if (IS_ERR(regmap)) {
+		ret = PTR_ERR(regmap);
+		goto err_free_irq;
+	}
 
 	return 0;
 
+err_free_irq:
+	free_irq(dmac->irq, dmac);
 err_unregister_of:
 	of_dma_controller_free(pdev->dev.of_node);
 err_unregister_device:
diff --git a/drivers/dma/dma-jz4780.c b/drivers/dma/dma-jz4780.c
index 44af435628f8..448f663da89c 100644
--- a/drivers/dma/dma-jz4780.c
+++ b/drivers/dma/dma-jz4780.c
@@ -1021,12 +1021,19 @@ static const struct jz4780_dma_soc_data x1000_dma_soc_data = {
 	.flags = JZ_SOC_DATA_PROGRAMMABLE_DMA,
 };
 
+static const struct jz4780_dma_soc_data x1830_dma_soc_data = {
+	.nb_channels = 32,
+	.transfer_ord_max = 7,
+	.flags = JZ_SOC_DATA_PROGRAMMABLE_DMA,
+};
+
 static const struct of_device_id jz4780_dma_dt_match[] = {
 	{ .compatible = "ingenic,jz4740-dma", .data = &jz4740_dma_soc_data },
 	{ .compatible = "ingenic,jz4725b-dma", .data = &jz4725b_dma_soc_data },
 	{ .compatible = "ingenic,jz4770-dma", .data = &jz4770_dma_soc_data },
 	{ .compatible = "ingenic,jz4780-dma", .data = &jz4780_dma_soc_data },
 	{ .compatible = "ingenic,x1000-dma", .data = &x1000_dma_soc_data },
+	{ .compatible = "ingenic,x1830-dma", .data = &x1830_dma_soc_data },
 	{},
 };
 MODULE_DEVICE_TABLE(of, jz4780_dma_dt_match);
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 03ac4b96117c..17909fd1820f 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -60,6 +60,8 @@ static long dmaengine_ref_count;
 
 /* --- sysfs implementation --- */
 
+#define DMA_SLAVE_NAME	"slave"
+
 /**
  * dev_to_dma_chan - convert a device pointer to its sysfs container object
  * @dev - device node
@@ -164,11 +166,152 @@ static struct class dma_devclass = {
 
 /* --- client and device registration --- */
 
-#define dma_device_satisfies_mask(device, mask) \
-	__dma_device_satisfies_mask((device), &(mask))
-static int
-__dma_device_satisfies_mask(struct dma_device *device,
-			    const dma_cap_mask_t *want)
+/**
+ * dma_cap_mask_all - enable iteration over all operation types
+ */
+static dma_cap_mask_t dma_cap_mask_all;
+
+/**
+ * dma_chan_tbl_ent - tracks channel allocations per core/operation
+ * @chan - associated channel for this entry
+ */
+struct dma_chan_tbl_ent {
+	struct dma_chan *chan;
+};
+
+/**
+ * channel_table - percpu lookup table for memory-to-memory offload providers
+ */
+static struct dma_chan_tbl_ent __percpu *channel_table[DMA_TX_TYPE_END];
+
+static int __init dma_channel_table_init(void)
+{
+	enum dma_transaction_type cap;
+	int err = 0;
+
+	bitmap_fill(dma_cap_mask_all.bits, DMA_TX_TYPE_END);
+
+	/* 'interrupt', 'private', and 'slave' are channel capabilities,
+	 * but are not associated with an operation so they do not need
+	 * an entry in the channel_table
+	 */
+	clear_bit(DMA_INTERRUPT, dma_cap_mask_all.bits);
+	clear_bit(DMA_PRIVATE, dma_cap_mask_all.bits);
+	clear_bit(DMA_SLAVE, dma_cap_mask_all.bits);
+
+	for_each_dma_cap_mask(cap, dma_cap_mask_all) {
+		channel_table[cap] = alloc_percpu(struct dma_chan_tbl_ent);
+		if (!channel_table[cap]) {
+			err = -ENOMEM;
+			break;
+		}
+	}
+
+	if (err) {
+		pr_err("dmaengine dma_channel_table_init failure: %d\n", err);
+		for_each_dma_cap_mask(cap, dma_cap_mask_all)
+			free_percpu(channel_table[cap]);
+	}
+
+	return err;
+}
+arch_initcall(dma_channel_table_init);
+
+/**
+ * dma_chan_is_local - returns true if the channel is in the same numa-node as
+ *	the cpu
+ */
+static bool dma_chan_is_local(struct dma_chan *chan, int cpu)
+{
+	int node = dev_to_node(chan->device->dev);
+	return node == NUMA_NO_NODE ||
+		cpumask_test_cpu(cpu, cpumask_of_node(node));
+}
+
+/**
+ * min_chan - returns the channel with min count and in the same numa-node as
+ *	the cpu
+ * @cap: capability to match
+ * @cpu: cpu index which the channel should be close to
+ *
+ * If some channels are close to the given cpu, the one with the lowest
+ * reference count is returned. Otherwise, cpu is ignored and only the
+ * reference count is taken into account.
+ * Must be called under dma_list_mutex.
+ */
+static struct dma_chan *min_chan(enum dma_transaction_type cap, int cpu)
+{
+	struct dma_device *device;
+	struct dma_chan *chan;
+	struct dma_chan *min = NULL;
+	struct dma_chan *localmin = NULL;
+
+	list_for_each_entry(device, &dma_device_list, global_node) {
+		if (!dma_has_cap(cap, device->cap_mask) ||
+		    dma_has_cap(DMA_PRIVATE, device->cap_mask))
+			continue;
+		list_for_each_entry(chan, &device->channels, device_node) {
+			if (!chan->client_count)
+				continue;
+			if (!min || chan->table_count < min->table_count)
+				min = chan;
+
+			if (dma_chan_is_local(chan, cpu))
+				if (!localmin ||
+				    chan->table_count < localmin->table_count)
+					localmin = chan;
+		}
+	}
+
+	chan = localmin ? localmin : min;
+
+	if (chan)
+		chan->table_count++;
+
+	return chan;
+}
+
+/**
+ * dma_channel_rebalance - redistribute the available channels
+ *
+ * Optimize for cpu isolation (each cpu gets a dedicated channel for an
+ * operation type) in the SMP case,  and operation isolation (avoid
+ * multi-tasking channels) in the non-SMP case.  Must be called under
+ * dma_list_mutex.
+ */
+static void dma_channel_rebalance(void)
+{
+	struct dma_chan *chan;
+	struct dma_device *device;
+	int cpu;
+	int cap;
+
+	/* undo the last distribution */
+	for_each_dma_cap_mask(cap, dma_cap_mask_all)
+		for_each_possible_cpu(cpu)
+			per_cpu_ptr(channel_table[cap], cpu)->chan = NULL;
+
+	list_for_each_entry(device, &dma_device_list, global_node) {
+		if (dma_has_cap(DMA_PRIVATE, device->cap_mask))
+			continue;
+		list_for_each_entry(chan, &device->channels, device_node)
+			chan->table_count = 0;
+	}
+
+	/* don't populate the channel_table if no clients are available */
+	if (!dmaengine_ref_count)
+		return;
+
+	/* redistribute available channels */
+	for_each_dma_cap_mask(cap, dma_cap_mask_all)
+		for_each_online_cpu(cpu) {
+			chan = min_chan(cap, cpu);
+			per_cpu_ptr(channel_table[cap], cpu)->chan = chan;
+		}
+}
+
+static int dma_device_satisfies_mask(struct dma_device *device,
+				     const dma_cap_mask_t *want)
 {
 	dma_cap_mask_t has;
 
@@ -179,7 +322,7 @@ __dma_device_satisfies_mask(struct dma_device *device,
 
 static struct module *dma_chan_to_owner(struct dma_chan *chan)
 {
-	return chan->device->dev->driver->owner;
+	return chan->device->owner;
 }
 
 /**
@@ -198,6 +341,23 @@ static void balance_ref_count(struct dma_chan *chan)
 	}
 }
 
+static void dma_device_release(struct kref *ref)
+{
+	struct dma_device *device = container_of(ref, struct dma_device, ref);
+
+	list_del_rcu(&device->global_node);
+	dma_channel_rebalance();
+
+	if (device->device_release)
+		device->device_release(device);
+}
+
+static void dma_device_put(struct dma_device *device)
+{
+	lockdep_assert_held(&dma_list_mutex);
+	kref_put(&device->ref, dma_device_release);
+}
+
 /**
  * dma_chan_get - try to grab a dma channel's parent driver module
  * @chan - channel to grab
@@ -218,6 +378,12 @@ static int dma_chan_get(struct dma_chan *chan)
 	if (!try_module_get(owner))
 		return -ENODEV;
 
+	ret = kref_get_unless_zero(&chan->device->ref);
+	if (!ret) {
+		ret = -ENODEV;
+		goto module_put_out;
+	}
+
 	/* allocate upon first client reference */
 	if (chan->device->device_alloc_chan_resources) {
 		ret = chan->device->device_alloc_chan_resources(chan);
@@ -233,6 +399,8 @@ out:
 	return 0;
 
 err_out:
+	dma_device_put(chan->device);
+module_put_out:
 	module_put(owner);
 	return ret;
 }
@@ -250,7 +418,6 @@ static void dma_chan_put(struct dma_chan *chan)
 		return;
 
 	chan->client_count--;
-	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) {
@@ -265,6 +432,9 @@ static void dma_chan_put(struct dma_chan *chan)
 		chan->router = NULL;
 		chan->route_data = NULL;
 	}
+
+	dma_device_put(chan->device);
+	module_put(dma_chan_to_owner(chan));
 }
 
 enum dma_status dma_sync_wait(struct dma_chan *chan, dma_cookie_t cookie)
@@ -289,57 +459,6 @@ enum dma_status dma_sync_wait(struct dma_chan *chan, dma_cookie_t cookie)
 EXPORT_SYMBOL(dma_sync_wait);
 
 /**
- * dma_cap_mask_all - enable iteration over all operation types
- */
-static dma_cap_mask_t dma_cap_mask_all;
-
-/**
- * dma_chan_tbl_ent - tracks channel allocations per core/operation
- * @chan - associated channel for this entry
- */
-struct dma_chan_tbl_ent {
-	struct dma_chan *chan;
-};
-
-/**
- * channel_table - percpu lookup table for memory-to-memory offload providers
- */
-static struct dma_chan_tbl_ent __percpu *channel_table[DMA_TX_TYPE_END];
-
-static int __init dma_channel_table_init(void)
-{
-	enum dma_transaction_type cap;
-	int err = 0;
-
-	bitmap_fill(dma_cap_mask_all.bits, DMA_TX_TYPE_END);
-
-	/* 'interrupt', 'private', and 'slave' are channel capabilities,
-	 * but are not associated with an operation so they do not need
-	 * an entry in the channel_table
-	 */
-	clear_bit(DMA_INTERRUPT, dma_cap_mask_all.bits);
-	clear_bit(DMA_PRIVATE, dma_cap_mask_all.bits);
-	clear_bit(DMA_SLAVE, dma_cap_mask_all.bits);
-
-	for_each_dma_cap_mask(cap, dma_cap_mask_all) {
-		channel_table[cap] = alloc_percpu(struct dma_chan_tbl_ent);
-		if (!channel_table[cap]) {
-			err = -ENOMEM;
-			break;
-		}
-	}
-
-	if (err) {
-		pr_err("initialization failure\n");
-		for_each_dma_cap_mask(cap, dma_cap_mask_all)
-			free_percpu(channel_table[cap]);
-	}
-
-	return err;
-}
-arch_initcall(dma_channel_table_init);
-
-/**
  * dma_find_channel - find a channel to carry out the operation
  * @tx_type: transaction type
  */
@@ -369,97 +488,6 @@ void dma_issue_pending_all(void)
 }
 EXPORT_SYMBOL(dma_issue_pending_all);
 
-/**
- * dma_chan_is_local - returns true if the channel is in the same numa-node as the cpu
- */
-static bool dma_chan_is_local(struct dma_chan *chan, int cpu)
-{
-	int node = dev_to_node(chan->device->dev);
-	return node == NUMA_NO_NODE ||
-		cpumask_test_cpu(cpu, cpumask_of_node(node));
-}
-
-/**
- * min_chan - returns the channel with min count and in the same numa-node as the cpu
- * @cap: capability to match
- * @cpu: cpu index which the channel should be close to
- *
- * If some channels are close to the given cpu, the one with the lowest
- * reference count is returned. Otherwise, cpu is ignored and only the
- * reference count is taken into account.
- * Must be called under dma_list_mutex.
- */
-static struct dma_chan *min_chan(enum dma_transaction_type cap, int cpu)
-{
-	struct dma_device *device;
-	struct dma_chan *chan;
-	struct dma_chan *min = NULL;
-	struct dma_chan *localmin = NULL;
-
-	list_for_each_entry(device, &dma_device_list, global_node) {
-		if (!dma_has_cap(cap, device->cap_mask) ||
-		    dma_has_cap(DMA_PRIVATE, device->cap_mask))
-			continue;
-		list_for_each_entry(chan, &device->channels, device_node) {
-			if (!chan->client_count)
-				continue;
-			if (!min || chan->table_count < min->table_count)
-				min = chan;
-
-			if (dma_chan_is_local(chan, cpu))
-				if (!localmin ||
-				    chan->table_count < localmin->table_count)
-					localmin = chan;
-		}
-	}
-
-	chan = localmin ? localmin : min;
-
-	if (chan)
-		chan->table_count++;
-
-	return chan;
-}
-
-/**
- * dma_channel_rebalance - redistribute the available channels
- *
- * Optimize for cpu isolation (each cpu gets a dedicated channel for an
- * operation type) in the SMP case,  and operation isolation (avoid
- * multi-tasking channels) in the non-SMP case.  Must be called under
- * dma_list_mutex.
- */
-static void dma_channel_rebalance(void)
-{
-	struct dma_chan *chan;
-	struct dma_device *device;
-	int cpu;
-	int cap;
-
-	/* undo the last distribution */
-	for_each_dma_cap_mask(cap, dma_cap_mask_all)
-		for_each_possible_cpu(cpu)
-			per_cpu_ptr(channel_table[cap], cpu)->chan = NULL;
-
-	list_for_each_entry(device, &dma_device_list, global_node) {
-		if (dma_has_cap(DMA_PRIVATE, device->cap_mask))
-			continue;
-		list_for_each_entry(chan, &device->channels, device_node)
-			chan->table_count = 0;
-	}
-
-	/* don't populate the channel_table if no clients are available */
-	if (!dmaengine_ref_count)
-		return;
-
-	/* redistribute available channels */
-	for_each_dma_cap_mask(cap, dma_cap_mask_all)
-		for_each_online_cpu(cpu) {
-			chan = min_chan(cap, cpu);
-			per_cpu_ptr(channel_table[cap], cpu)->chan = chan;
-		}
-}
-
 int dma_get_slave_caps(struct dma_chan *chan, struct dma_slave_caps *caps)
 {
 	struct dma_device *device;
@@ -502,7 +530,7 @@ static struct dma_chan *private_candidate(const dma_cap_mask_t *mask,
 {
 	struct dma_chan *chan;
 
-	if (mask && !__dma_device_satisfies_mask(dev, mask)) {
+	if (mask && !dma_device_satisfies_mask(dev, mask)) {
 		dev_dbg(dev->dev, "%s: wrong capabilities\n", __func__);
 		return NULL;
 	}
@@ -704,11 +732,11 @@ struct dma_chan *dma_request_chan(struct device *dev, const char *name)
 	if (has_acpi_companion(dev) && !chan)
 		chan = acpi_dma_request_slave_chan_by_name(dev, name);
 
-	if (chan) {
-		/* Valid channel found or requester needs to be deferred */
-		if (!IS_ERR(chan) || PTR_ERR(chan) == -EPROBE_DEFER)
-			return chan;
-	}
+	if (PTR_ERR(chan) == -EPROBE_DEFER)
+		return chan;
+
+	if (!IS_ERR_OR_NULL(chan))
+		goto found;
 
 	/* Try to find the channel via the DMA filter map(s) */
 	mutex_lock(&dma_list_mutex);
@@ -728,7 +756,22 @@ struct dma_chan *dma_request_chan(struct device *dev, const char *name)
 	}
 	mutex_unlock(&dma_list_mutex);
 
-	return chan ? chan : ERR_PTR(-EPROBE_DEFER);
+	if (IS_ERR_OR_NULL(chan))
+		return chan ? chan : ERR_PTR(-EPROBE_DEFER);
+
+found:
+	chan->name = kasprintf(GFP_KERNEL, "dma:%s", name);
+	if (!chan->name)
+		return chan;
+	chan->slave = dev;
+
+	if (sysfs_create_link(&chan->dev->device.kobj, &dev->kobj,
+			      DMA_SLAVE_NAME))
+		dev_warn(dev, "Cannot create DMA %s symlink\n", DMA_SLAVE_NAME);
+	if (sysfs_create_link(&dev->kobj, &chan->dev->device.kobj, chan->name))
+		dev_warn(dev, "Cannot create DMA %s symlink\n", chan->name);
+
+	return chan;
 }
 EXPORT_SYMBOL_GPL(dma_request_chan);
 
@@ -786,6 +829,14 @@ void dma_release_channel(struct dma_chan *chan)
 	/* drop PRIVATE cap enabled by __dma_request_channel() */
 	if (--chan->device->privatecnt == 0)
 		dma_cap_clear(DMA_PRIVATE, chan->device->cap_mask);
+
+	if (chan->slave) {
+		sysfs_remove_link(&chan->dev->device.kobj, DMA_SLAVE_NAME);
+		sysfs_remove_link(&chan->slave->kobj, chan->name);
+		kfree(chan->name);
+		chan->name = NULL;
+		chan->slave = NULL;
+	}
 	mutex_unlock(&dma_list_mutex);
 }
 EXPORT_SYMBOL_GPL(dma_release_channel);
@@ -834,14 +885,14 @@ EXPORT_SYMBOL(dmaengine_get);
  */
 void dmaengine_put(void)
 {
-	struct dma_device *device;
+	struct dma_device *device, *_d;
 	struct dma_chan *chan;
 
 	mutex_lock(&dma_list_mutex);
 	dmaengine_ref_count--;
 	BUG_ON(dmaengine_ref_count < 0);
 	/* drop channel references */
-	list_for_each_entry(device, &dma_device_list, global_node) {
+	list_for_each_entry_safe(device, _d, &dma_device_list, global_node) {
 		if (dma_has_cap(DMA_PRIVATE, device->cap_mask))
 			continue;
 		list_for_each_entry(chan, &device->channels, device_node)
@@ -900,15 +951,118 @@ static int get_dma_id(struct dma_device *device)
 	return 0;
 }
 
+static int __dma_async_device_channel_register(struct dma_device *device,
+					       struct dma_chan *chan,
+					       int chan_id)
+{
+	int rc = 0;
+	int chancnt = device->chancnt;
+	atomic_t *idr_ref;
+	struct dma_chan *tchan;
+
+	tchan = list_first_entry_or_null(&device->channels,
+					 struct dma_chan, device_node);
+	if (!tchan)
+		return -ENODEV;
+
+	if (tchan->dev) {
+		idr_ref = tchan->dev->idr_ref;
+	} else {
+		idr_ref = kmalloc(sizeof(*idr_ref), GFP_KERNEL);
+		if (!idr_ref)
+			return -ENOMEM;
+		atomic_set(idr_ref, 0);
+	}
+
+	chan->local = alloc_percpu(typeof(*chan->local));
+	if (!chan->local)
+		goto err_out;
+	chan->dev = kzalloc(sizeof(*chan->dev), GFP_KERNEL);
+	if (!chan->dev) {
+		free_percpu(chan->local);
+		chan->local = NULL;
+		goto err_out;
+	}
+
+	/*
+	 * When the chan_id is a negative value, we are dynamically adding
+	 * the channel. Otherwise we are static enumerating.
+	 */
+	chan->chan_id = chan_id < 0 ? chancnt : chan_id;
+	chan->dev->device.class = &dma_devclass;
+	chan->dev->device.parent = device->dev;
+	chan->dev->chan = chan;
+	chan->dev->idr_ref = idr_ref;
+	chan->dev->dev_id = device->dev_id;
+	atomic_inc(idr_ref);
+	dev_set_name(&chan->dev->device, "dma%dchan%d",
+		     device->dev_id, chan->chan_id);
+
+	rc = device_register(&chan->dev->device);
+	if (rc)
+		goto err_out;
+	chan->client_count = 0;
+	device->chancnt = chan->chan_id + 1;
+
+	return 0;
+
+ err_out:
+	free_percpu(chan->local);
+	kfree(chan->dev);
+	if (atomic_dec_return(idr_ref) == 0)
+		kfree(idr_ref);
+	return rc;
+}
+
+int dma_async_device_channel_register(struct dma_device *device,
+				      struct dma_chan *chan)
+{
+	int rc;
+
+	rc = __dma_async_device_channel_register(device, chan, -1);
+	if (rc < 0)
+		return rc;
+
+	dma_channel_rebalance();
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dma_async_device_channel_register);
+
+static void __dma_async_device_channel_unregister(struct dma_device *device,
+						  struct dma_chan *chan)
+{
+	WARN_ONCE(!device->device_release && chan->client_count,
+		  "%s called while %d clients hold a reference\n",
+		  __func__, chan->client_count);
+	mutex_lock(&dma_list_mutex);
+	list_del(&chan->device_node);
+	device->chancnt--;
+	chan->dev->chan = NULL;
+	mutex_unlock(&dma_list_mutex);
+	device_unregister(&chan->dev->device);
+	free_percpu(chan->local);
+}
+
+void dma_async_device_channel_unregister(struct dma_device *device,
+					 struct dma_chan *chan)
+{
+	__dma_async_device_channel_unregister(device, chan);
+	dma_channel_rebalance();
+}
+EXPORT_SYMBOL_GPL(dma_async_device_channel_unregister);
+
 /**
  * dma_async_device_register - registers DMA devices found
  * @device: &dma_device
+ *
+ * After calling this routine the structure should not be freed except in the
+ * device_release() callback which will be called after
+ * dma_async_device_unregister() is called and no further references are taken.
  */
 int dma_async_device_register(struct dma_device *device)
 {
-	int chancnt = 0, rc;
+	int rc, i = 0;
 	struct dma_chan* chan;
-	atomic_t *idr_ref;
 
 	if (!device)
 		return -ENODEV;
@@ -919,6 +1073,8 @@ int dma_async_device_register(struct dma_device *device)
 		return -EIO;
 	}
 
+	device->owner = device->dev->driver->owner;
+
 	if (dma_has_cap(DMA_MEMCPY, device->cap_mask) && !device->device_prep_dma_memcpy) {
 		dev_err(device->dev,
 			"Device claims capability %s, but op is not defined\n",
@@ -994,65 +1150,29 @@ int dma_async_device_register(struct dma_device *device)
 		return -EIO;
 	}
 
+	if (!device->device_release)
+		dev_dbg(device->dev,
+			 "WARN: Device release is not defined so it is not safe to unbind this driver while in use\n");
+
+	kref_init(&device->ref);
+
 	/* note: this only matters in the
 	 * CONFIG_ASYNC_TX_ENABLE_CHANNEL_SWITCH=n case
 	 */
 	if (device_has_all_tx_types(device))
 		dma_cap_set(DMA_ASYNC_TX, device->cap_mask);
 
-	idr_ref = kmalloc(sizeof(*idr_ref), GFP_KERNEL);
-	if (!idr_ref)
-		return -ENOMEM;
 	rc = get_dma_id(device);
-	if (rc != 0) {
-		kfree(idr_ref);
+	if (rc != 0)
 		return rc;
-	}
-
-	atomic_set(idr_ref, 0);
 
 	/* represent channels in sysfs. Probably want devs too */
 	list_for_each_entry(chan, &device->channels, device_node) {
-		rc = -ENOMEM;
-		chan->local = alloc_percpu(typeof(*chan->local));
-		if (chan->local == NULL)
-			goto err_out;
-		chan->dev = kzalloc(sizeof(*chan->dev), GFP_KERNEL);
-		if (chan->dev == NULL) {
-			free_percpu(chan->local);
-			chan->local = NULL;
+		rc = __dma_async_device_channel_register(device, chan, i++);
+		if (rc < 0)
 			goto err_out;
-		}
-
-		chan->chan_id = chancnt++;
-		chan->dev->device.class = &dma_devclass;
-		chan->dev->device.parent = device->dev;
-		chan->dev->chan = chan;
-		chan->dev->idr_ref = idr_ref;
-		chan->dev->dev_id = device->dev_id;
-		atomic_inc(idr_ref);
-		dev_set_name(&chan->dev->device, "dma%dchan%d",
-			     device->dev_id, chan->chan_id);
-
-		rc = device_register(&chan->dev->device);
-		if (rc) {
-			free_percpu(chan->local);
-			chan->local = NULL;
-			kfree(chan->dev);
-			atomic_dec(idr_ref);
-			goto err_out;
-		}
-		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);
 	/* take references on public channels */
 	if (dmaengine_ref_count && !dma_has_cap(DMA_PRIVATE, device->cap_mask))
@@ -1080,9 +1200,8 @@ int dma_async_device_register(struct dma_device *device)
 
 err_out:
 	/* if we never registered a channel just release the idr */
-	if (atomic_read(idr_ref) == 0) {
+	if (!device->chancnt) {
 		ida_free(&dma_ida, device->dev_id);
-		kfree(idr_ref);
 		return rc;
 	}
 
@@ -1108,23 +1227,20 @@ EXPORT_SYMBOL(dma_async_device_register);
  */
 void dma_async_device_unregister(struct dma_device *device)
 {
-	struct dma_chan *chan;
+	struct dma_chan *chan, *n;
+
+	list_for_each_entry_safe(chan, n, &device->channels, device_node)
+		__dma_async_device_channel_unregister(device, chan);
 
 	mutex_lock(&dma_list_mutex);
-	list_del_rcu(&device->global_node);
+	/*
+	 * setting DMA_PRIVATE ensures the device being torn down will not
+	 * be used in the channel_table
+	 */
+	dma_cap_set(DMA_PRIVATE, device->cap_mask);
 	dma_channel_rebalance();
+	dma_device_put(device);
 	mutex_unlock(&dma_list_mutex);
-
-	list_for_each_entry(chan, &device->channels, device_node) {
-		WARN_ONCE(chan->client_count,
-			  "%s called while %d clients hold a reference\n",
-			  __func__, chan->client_count);
-		mutex_lock(&dma_list_mutex);
-		chan->dev->chan = NULL;
-		mutex_unlock(&dma_list_mutex);
-		device_unregister(&chan->dev->device);
-		free_percpu(chan->local);
-	}
 }
 EXPORT_SYMBOL(dma_async_device_unregister);
 
@@ -1302,6 +1418,79 @@ void dma_async_tx_descriptor_init(struct dma_async_tx_descriptor *tx,
 }
 EXPORT_SYMBOL(dma_async_tx_descriptor_init);
 
+static inline int desc_check_and_set_metadata_mode(
+	struct dma_async_tx_descriptor *desc, enum dma_desc_metadata_mode mode)
+{
+	/* Make sure that the metadata mode is not mixed */
+	if (!desc->desc_metadata_mode) {
+		if (dmaengine_is_metadata_mode_supported(desc->chan, mode))
+			desc->desc_metadata_mode = mode;
+		else
+			return -ENOTSUPP;
+	} else if (desc->desc_metadata_mode != mode) {
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int dmaengine_desc_attach_metadata(struct dma_async_tx_descriptor *desc,
+				   void *data, size_t len)
+{
+	int ret;
+
+	if (!desc)
+		return -EINVAL;
+
+	ret = desc_check_and_set_metadata_mode(desc, DESC_METADATA_CLIENT);
+	if (ret)
+		return ret;
+
+	if (!desc->metadata_ops || !desc->metadata_ops->attach)
+		return -ENOTSUPP;
+
+	return desc->metadata_ops->attach(desc, data, len);
+}
+EXPORT_SYMBOL_GPL(dmaengine_desc_attach_metadata);
+
+void *dmaengine_desc_get_metadata_ptr(struct dma_async_tx_descriptor *desc,
+				      size_t *payload_len, size_t *max_len)
+{
+	int ret;
+
+	if (!desc)
+		return ERR_PTR(-EINVAL);
+
+	ret = desc_check_and_set_metadata_mode(desc, DESC_METADATA_ENGINE);
+	if (ret)
+		return ERR_PTR(ret);
+
+	if (!desc->metadata_ops || !desc->metadata_ops->get_ptr)
+		return ERR_PTR(-ENOTSUPP);
+
+	return desc->metadata_ops->get_ptr(desc, payload_len, max_len);
+}
+EXPORT_SYMBOL_GPL(dmaengine_desc_get_metadata_ptr);
+
+int dmaengine_desc_set_metadata_len(struct dma_async_tx_descriptor *desc,
+				    size_t payload_len)
+{
+	int ret;
+
+	if (!desc)
+		return -EINVAL;
+
+	ret = desc_check_and_set_metadata_mode(desc, DESC_METADATA_ENGINE);
+	if (ret)
+		return ret;
+
+	if (!desc->metadata_ops || !desc->metadata_ops->set_len)
+		return -ENOTSUPP;
+
+	return desc->metadata_ops->set_len(desc, payload_len);
+}
+EXPORT_SYMBOL_GPL(dmaengine_desc_set_metadata_len);
+
 /* dma_wait_for_async_tx - spin wait for a transaction to complete
  * @tx: in-flight transaction to wait on
  */
@@ -1373,5 +1562,3 @@ static int __init dma_bus_init(void)
 	return class_register(&dma_devclass);
 }
 arch_initcall(dma_bus_init);
-
-
diff --git a/drivers/dma/dmaengine.h b/drivers/dma/dmaengine.h
index 501c0b063f85..e8a320c9e57c 100644
--- a/drivers/dma/dmaengine.h
+++ b/drivers/dma/dmaengine.h
@@ -77,6 +77,7 @@ static inline enum dma_status dma_cookie_status(struct dma_chan *chan,
 		state->last = complete;
 		state->used = used;
 		state->residue = 0;
+		state->in_flight_bytes = 0;
 	}
 	return dma_async_is_complete(cookie, complete, used);
 }
@@ -87,6 +88,13 @@ static inline void dma_set_residue(struct dma_tx_state *state, u32 residue)
 		state->residue = residue;
 }
 
+static inline void dma_set_in_flight_bytes(struct dma_tx_state *state,
+					   u32 in_flight_bytes)
+{
+	if (state)
+		state->in_flight_bytes = in_flight_bytes;
+}
+
 struct dmaengine_desc_callback {
 	dma_async_tx_callback callback;
 	dma_async_tx_callback_result callback_result;
@@ -171,4 +179,7 @@ dmaengine_desc_callback_valid(struct dmaengine_desc_callback *cb)
 	return (cb->callback) ? true : false;
 }
 
+struct dma_chan *dma_get_slave_channel(struct dma_chan *chan);
+struct dma_chan *dma_get_any_slave_channel(struct dma_device *device);
+
 #endif
diff --git a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c
index a1ce307c502f..14c1ac26f866 100644
--- a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c
+++ b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c
@@ -636,14 +636,10 @@ static int dma_chan_terminate_all(struct dma_chan *dchan)
 
 	vchan_get_all_descriptors(&chan->vc, &head);
 
-	/*
-	 * As vchan_dma_desc_free_list can access to desc_allocated list
-	 * we need to call it in vc.lock context.
-	 */
-	vchan_dma_desc_free_list(&chan->vc, &head);
-
 	spin_unlock_irqrestore(&chan->vc.lock, flags);
 
+	vchan_dma_desc_free_list(&chan->vc, &head);
+
 	dev_vdbg(dchan2dev(dchan), "terminated: %s\n", axi_chan_name(chan));
 
 	return 0;
diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c
index b1a7ca91701a..5697c3622699 100644
--- a/drivers/dma/fsl-edma-common.c
+++ b/drivers/dma/fsl-edma-common.c
@@ -109,10 +109,15 @@ void fsl_edma_chan_mux(struct fsl_edma_chan *fsl_chan,
 	u32 ch = fsl_chan->vchan.chan.chan_id;
 	void __iomem *muxaddr;
 	unsigned int chans_per_mux, ch_off;
+	int endian_diff[4] = {3, 1, -1, -3};
 	u32 dmamux_nr = fsl_chan->edma->drvdata->dmamuxs;
 
 	chans_per_mux = fsl_chan->edma->n_chans / dmamux_nr;
 	ch_off = fsl_chan->vchan.chan.chan_id % chans_per_mux;
+
+	if (fsl_chan->edma->drvdata->mux_swap)
+		ch_off += endian_diff[ch_off % 4];
+
 	muxaddr = fsl_chan->edma->muxbase[ch / chans_per_mux];
 	slot = EDMAMUX_CHCFG_SOURCE(slot);
 
diff --git a/drivers/dma/fsl-edma-common.h b/drivers/dma/fsl-edma-common.h
index 5eaa2902ed39..67e422590c9a 100644
--- a/drivers/dma/fsl-edma-common.h
+++ b/drivers/dma/fsl-edma-common.h
@@ -147,6 +147,7 @@ struct fsl_edma_drvdata {
 	enum edma_version	version;
 	u32			dmamuxs;
 	bool			has_dmaclk;
+	bool			mux_swap;
 	int			(*setup_irq)(struct platform_device *pdev,
 					     struct fsl_edma_engine *fsl_edma);
 };
diff --git a/drivers/dma/fsl-edma.c b/drivers/dma/fsl-edma.c
index b626c06ac2e0..eff7ebd8cf35 100644
--- a/drivers/dma/fsl-edma.c
+++ b/drivers/dma/fsl-edma.c
@@ -233,6 +233,13 @@ static struct fsl_edma_drvdata vf610_data = {
 	.setup_irq = fsl_edma_irq_init,
 };
 
+static struct fsl_edma_drvdata ls1028a_data = {
+	.version = v1,
+	.dmamuxs = DMAMUX_NR,
+	.mux_swap = true,
+	.setup_irq = fsl_edma_irq_init,
+};
+
 static struct fsl_edma_drvdata imx7ulp_data = {
 	.version = v3,
 	.dmamuxs = 1,
@@ -242,6 +249,7 @@ static struct fsl_edma_drvdata imx7ulp_data = {
 
 static const struct of_device_id fsl_edma_dt_ids[] = {
 	{ .compatible = "fsl,vf610-edma", .data = &vf610_data},
+	{ .compatible = "fsl,ls1028a-edma", .data = &ls1028a_data},
 	{ .compatible = "fsl,imx7ulp-edma", .data = &imx7ulp_data},
 	{ /* sentinel */ }
 };
diff --git a/drivers/dma/fsl-qdma.c b/drivers/dma/fsl-qdma.c
index 89792083d62c..95cc0256b387 100644
--- a/drivers/dma/fsl-qdma.c
+++ b/drivers/dma/fsl-qdma.c
@@ -304,7 +304,7 @@ static void fsl_qdma_free_chan_resources(struct dma_chan *chan)
 
 	vchan_dma_desc_free_list(&fsl_chan->vchan, &head);
 
-	if (!fsl_queue->comp_pool && !fsl_queue->comp_pool)
+	if (!fsl_queue->comp_pool && !fsl_queue->desc_pool)
 		return;
 
 	list_for_each_entry_safe(comp_temp, _comp_temp,
diff --git a/drivers/dma/hisi_dma.c b/drivers/dma/hisi_dma.c
new file mode 100644
index 000000000000..ed3619266a48
--- /dev/null
+++ b/drivers/dma/hisi_dma.c
@@ -0,0 +1,611 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2019 HiSilicon Limited. */
+#include <linux/bitfield.h>
+#include <linux/dmaengine.h>
+#include <linux/init.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/spinlock.h>
+#include "virt-dma.h"
+
+#define HISI_DMA_SQ_BASE_L		0x0
+#define HISI_DMA_SQ_BASE_H		0x4
+#define HISI_DMA_SQ_DEPTH		0x8
+#define HISI_DMA_SQ_TAIL_PTR		0xc
+#define HISI_DMA_CQ_BASE_L		0x10
+#define HISI_DMA_CQ_BASE_H		0x14
+#define HISI_DMA_CQ_DEPTH		0x18
+#define HISI_DMA_CQ_HEAD_PTR		0x1c
+#define HISI_DMA_CTRL0			0x20
+#define HISI_DMA_CTRL0_QUEUE_EN_S	0
+#define HISI_DMA_CTRL0_QUEUE_PAUSE_S	4
+#define HISI_DMA_CTRL1			0x24
+#define HISI_DMA_CTRL1_QUEUE_RESET_S	0
+#define HISI_DMA_Q_FSM_STS		0x30
+#define HISI_DMA_FSM_STS_MASK		GENMASK(3, 0)
+#define HISI_DMA_INT_STS		0x40
+#define HISI_DMA_INT_STS_MASK		GENMASK(12, 0)
+#define HISI_DMA_INT_MSK		0x44
+#define HISI_DMA_MODE			0x217c
+#define HISI_DMA_OFFSET			0x100
+
+#define HISI_DMA_MSI_NUM		30
+#define HISI_DMA_CHAN_NUM		30
+#define HISI_DMA_Q_DEPTH_VAL		1024
+
+#define PCI_BAR_2			2
+
+enum hisi_dma_mode {
+	EP = 0,
+	RC,
+};
+
+enum hisi_dma_chan_status {
+	DISABLE = -1,
+	IDLE = 0,
+	RUN,
+	CPL,
+	PAUSE,
+	HALT,
+	ABORT,
+	WAIT,
+	BUFFCLR,
+};
+
+struct hisi_dma_sqe {
+	__le32 dw0;
+#define OPCODE_MASK			GENMASK(3, 0)
+#define OPCODE_SMALL_PACKAGE		0x1
+#define OPCODE_M2M			0x4
+#define LOCAL_IRQ_EN			BIT(8)
+#define ATTR_SRC_MASK			GENMASK(14, 12)
+	__le32 dw1;
+	__le32 dw2;
+#define ATTR_DST_MASK			GENMASK(26, 24)
+	__le32 length;
+	__le64 src_addr;
+	__le64 dst_addr;
+};
+
+struct hisi_dma_cqe {
+	__le32 rsv0;
+	__le32 rsv1;
+	__le16 sq_head;
+	__le16 rsv2;
+	__le16 rsv3;
+	__le16 w0;
+#define STATUS_MASK			GENMASK(15, 1)
+#define STATUS_SUCC			0x0
+#define VALID_BIT			BIT(0)
+};
+
+struct hisi_dma_desc {
+	struct virt_dma_desc vd;
+	struct hisi_dma_sqe sqe;
+};
+
+struct hisi_dma_chan {
+	struct virt_dma_chan vc;
+	struct hisi_dma_dev *hdma_dev;
+	struct hisi_dma_sqe *sq;
+	struct hisi_dma_cqe *cq;
+	dma_addr_t sq_dma;
+	dma_addr_t cq_dma;
+	u32 sq_tail;
+	u32 cq_head;
+	u32 qp_num;
+	enum hisi_dma_chan_status status;
+	struct hisi_dma_desc *desc;
+};
+
+struct hisi_dma_dev {
+	struct pci_dev *pdev;
+	void __iomem *base;
+	struct dma_device dma_dev;
+	u32 chan_num;
+	u32 chan_depth;
+	struct hisi_dma_chan chan[];
+};
+
+static inline struct hisi_dma_chan *to_hisi_dma_chan(struct dma_chan *c)
+{
+	return container_of(c, struct hisi_dma_chan, vc.chan);
+}
+
+static inline struct hisi_dma_desc *to_hisi_dma_desc(struct virt_dma_desc *vd)
+{
+	return container_of(vd, struct hisi_dma_desc, vd);
+}
+
+static inline void hisi_dma_chan_write(void __iomem *base, u32 reg, u32 index,
+				       u32 val)
+{
+	writel_relaxed(val, base + reg + index * HISI_DMA_OFFSET);
+}
+
+static inline void hisi_dma_update_bit(void __iomem *addr, u32 pos, bool val)
+{
+	u32 tmp;
+
+	tmp = readl_relaxed(addr);
+	tmp = val ? tmp | BIT(pos) : tmp & ~BIT(pos);
+	writel_relaxed(tmp, addr);
+}
+
+static void hisi_dma_free_irq_vectors(void *data)
+{
+	pci_free_irq_vectors(data);
+}
+
+static void hisi_dma_pause_dma(struct hisi_dma_dev *hdma_dev, u32 index,
+			       bool pause)
+{
+	void __iomem *addr = hdma_dev->base + HISI_DMA_CTRL0 + index *
+			     HISI_DMA_OFFSET;
+
+	hisi_dma_update_bit(addr, HISI_DMA_CTRL0_QUEUE_PAUSE_S, pause);
+}
+
+static void hisi_dma_enable_dma(struct hisi_dma_dev *hdma_dev, u32 index,
+				bool enable)
+{
+	void __iomem *addr = hdma_dev->base + HISI_DMA_CTRL0 + index *
+			     HISI_DMA_OFFSET;
+
+	hisi_dma_update_bit(addr, HISI_DMA_CTRL0_QUEUE_EN_S, enable);
+}
+
+static void hisi_dma_mask_irq(struct hisi_dma_dev *hdma_dev, u32 qp_index)
+{
+	hisi_dma_chan_write(hdma_dev->base, HISI_DMA_INT_MSK, qp_index,
+			    HISI_DMA_INT_STS_MASK);
+}
+
+static void hisi_dma_unmask_irq(struct hisi_dma_dev *hdma_dev, u32 qp_index)
+{
+	void __iomem *base = hdma_dev->base;
+
+	hisi_dma_chan_write(base, HISI_DMA_INT_STS, qp_index,
+			    HISI_DMA_INT_STS_MASK);
+	hisi_dma_chan_write(base, HISI_DMA_INT_MSK, qp_index, 0);
+}
+
+static void hisi_dma_do_reset(struct hisi_dma_dev *hdma_dev, u32 index)
+{
+	void __iomem *addr = hdma_dev->base + HISI_DMA_CTRL1 + index *
+			     HISI_DMA_OFFSET;
+
+	hisi_dma_update_bit(addr, HISI_DMA_CTRL1_QUEUE_RESET_S, 1);
+}
+
+static void hisi_dma_reset_qp_point(struct hisi_dma_dev *hdma_dev, u32 index)
+{
+	hisi_dma_chan_write(hdma_dev->base, HISI_DMA_SQ_TAIL_PTR, index, 0);
+	hisi_dma_chan_write(hdma_dev->base, HISI_DMA_CQ_HEAD_PTR, index, 0);
+}
+
+static void hisi_dma_reset_hw_chan(struct hisi_dma_chan *chan)
+{
+	struct hisi_dma_dev *hdma_dev = chan->hdma_dev;
+	u32 index = chan->qp_num, tmp;
+	int ret;
+
+	hisi_dma_pause_dma(hdma_dev, index, true);
+	hisi_dma_enable_dma(hdma_dev, index, false);
+	hisi_dma_mask_irq(hdma_dev, index);
+
+	ret = readl_relaxed_poll_timeout(hdma_dev->base +
+		HISI_DMA_Q_FSM_STS + index * HISI_DMA_OFFSET, tmp,
+		FIELD_GET(HISI_DMA_FSM_STS_MASK, tmp) != RUN, 10, 1000);
+	if (ret) {
+		dev_err(&hdma_dev->pdev->dev, "disable channel timeout!\n");
+		WARN_ON(1);
+	}
+
+	hisi_dma_do_reset(hdma_dev, index);
+	hisi_dma_reset_qp_point(hdma_dev, index);
+	hisi_dma_pause_dma(hdma_dev, index, false);
+	hisi_dma_enable_dma(hdma_dev, index, true);
+	hisi_dma_unmask_irq(hdma_dev, index);
+
+	ret = readl_relaxed_poll_timeout(hdma_dev->base +
+		HISI_DMA_Q_FSM_STS + index * HISI_DMA_OFFSET, tmp,
+		FIELD_GET(HISI_DMA_FSM_STS_MASK, tmp) == IDLE, 10, 1000);
+	if (ret) {
+		dev_err(&hdma_dev->pdev->dev, "reset channel timeout!\n");
+		WARN_ON(1);
+	}
+}
+
+static void hisi_dma_free_chan_resources(struct dma_chan *c)
+{
+	struct hisi_dma_chan *chan = to_hisi_dma_chan(c);
+	struct hisi_dma_dev *hdma_dev = chan->hdma_dev;
+
+	hisi_dma_reset_hw_chan(chan);
+	vchan_free_chan_resources(&chan->vc);
+
+	memset(chan->sq, 0, sizeof(struct hisi_dma_sqe) * hdma_dev->chan_depth);
+	memset(chan->cq, 0, sizeof(struct hisi_dma_cqe) * hdma_dev->chan_depth);
+	chan->sq_tail = 0;
+	chan->cq_head = 0;
+	chan->status = DISABLE;
+}
+
+static void hisi_dma_desc_free(struct virt_dma_desc *vd)
+{
+	kfree(to_hisi_dma_desc(vd));
+}
+
+static struct dma_async_tx_descriptor *
+hisi_dma_prep_dma_memcpy(struct dma_chan *c, dma_addr_t dst, dma_addr_t src,
+			 size_t len, unsigned long flags)
+{
+	struct hisi_dma_chan *chan = to_hisi_dma_chan(c);
+	struct hisi_dma_desc *desc;
+
+	desc = kzalloc(sizeof(*desc), GFP_NOWAIT);
+	if (!desc)
+		return NULL;
+
+	desc->sqe.length = cpu_to_le32(len);
+	desc->sqe.src_addr = cpu_to_le64(src);
+	desc->sqe.dst_addr = cpu_to_le64(dst);
+
+	return vchan_tx_prep(&chan->vc, &desc->vd, flags);
+}
+
+static enum dma_status
+hisi_dma_tx_status(struct dma_chan *c, dma_cookie_t cookie,
+		   struct dma_tx_state *txstate)
+{
+	return dma_cookie_status(c, cookie, txstate);
+}
+
+static void hisi_dma_start_transfer(struct hisi_dma_chan *chan)
+{
+	struct hisi_dma_sqe *sqe = chan->sq + chan->sq_tail;
+	struct hisi_dma_dev *hdma_dev = chan->hdma_dev;
+	struct hisi_dma_desc *desc;
+	struct virt_dma_desc *vd;
+
+	vd = vchan_next_desc(&chan->vc);
+	if (!vd) {
+		dev_err(&hdma_dev->pdev->dev, "no issued task!\n");
+		chan->desc = NULL;
+		return;
+	}
+	list_del(&vd->node);
+	desc = to_hisi_dma_desc(vd);
+	chan->desc = desc;
+
+	memcpy(sqe, &desc->sqe, sizeof(struct hisi_dma_sqe));
+
+	/* update other field in sqe */
+	sqe->dw0 = cpu_to_le32(FIELD_PREP(OPCODE_MASK, OPCODE_M2M));
+	sqe->dw0 |= cpu_to_le32(LOCAL_IRQ_EN);
+
+	/* make sure data has been updated in sqe */
+	wmb();
+
+	/* update sq tail, point to new sqe position */
+	chan->sq_tail = (chan->sq_tail + 1) % hdma_dev->chan_depth;
+
+	/* update sq_tail to trigger a new task */
+	hisi_dma_chan_write(hdma_dev->base, HISI_DMA_SQ_TAIL_PTR, chan->qp_num,
+			    chan->sq_tail);
+}
+
+static void hisi_dma_issue_pending(struct dma_chan *c)
+{
+	struct hisi_dma_chan *chan = to_hisi_dma_chan(c);
+	unsigned long flags;
+
+	spin_lock_irqsave(&chan->vc.lock, flags);
+
+	if (vchan_issue_pending(&chan->vc))
+		hisi_dma_start_transfer(chan);
+
+	spin_unlock_irqrestore(&chan->vc.lock, flags);
+}
+
+static int hisi_dma_terminate_all(struct dma_chan *c)
+{
+	struct hisi_dma_chan *chan = to_hisi_dma_chan(c);
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	spin_lock_irqsave(&chan->vc.lock, flags);
+
+	hisi_dma_pause_dma(chan->hdma_dev, chan->qp_num, true);
+	if (chan->desc) {
+		vchan_terminate_vdesc(&chan->desc->vd);
+		chan->desc = NULL;
+	}
+
+	vchan_get_all_descriptors(&chan->vc, &head);
+
+	spin_unlock_irqrestore(&chan->vc.lock, flags);
+
+	vchan_dma_desc_free_list(&chan->vc, &head);
+	hisi_dma_pause_dma(chan->hdma_dev, chan->qp_num, false);
+
+	return 0;
+}
+
+static void hisi_dma_synchronize(struct dma_chan *c)
+{
+	struct hisi_dma_chan *chan = to_hisi_dma_chan(c);
+
+	vchan_synchronize(&chan->vc);
+}
+
+static int hisi_dma_alloc_qps_mem(struct hisi_dma_dev *hdma_dev)
+{
+	size_t sq_size = sizeof(struct hisi_dma_sqe) * hdma_dev->chan_depth;
+	size_t cq_size = sizeof(struct hisi_dma_cqe) * hdma_dev->chan_depth;
+	struct device *dev = &hdma_dev->pdev->dev;
+	struct hisi_dma_chan *chan;
+	int i;
+
+	for (i = 0; i < hdma_dev->chan_num; i++) {
+		chan = &hdma_dev->chan[i];
+		chan->sq = dmam_alloc_coherent(dev, sq_size, &chan->sq_dma,
+					       GFP_KERNEL);
+		if (!chan->sq)
+			return -ENOMEM;
+
+		chan->cq = dmam_alloc_coherent(dev, cq_size, &chan->cq_dma,
+					       GFP_KERNEL);
+		if (!chan->cq)
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void hisi_dma_init_hw_qp(struct hisi_dma_dev *hdma_dev, u32 index)
+{
+	struct hisi_dma_chan *chan = &hdma_dev->chan[index];
+	u32 hw_depth = hdma_dev->chan_depth - 1;
+	void __iomem *base = hdma_dev->base;
+
+	/* set sq, cq base */
+	hisi_dma_chan_write(base, HISI_DMA_SQ_BASE_L, index,
+			    lower_32_bits(chan->sq_dma));
+	hisi_dma_chan_write(base, HISI_DMA_SQ_BASE_H, index,
+			    upper_32_bits(chan->sq_dma));
+	hisi_dma_chan_write(base, HISI_DMA_CQ_BASE_L, index,
+			    lower_32_bits(chan->cq_dma));
+	hisi_dma_chan_write(base, HISI_DMA_CQ_BASE_H, index,
+			    upper_32_bits(chan->cq_dma));
+
+	/* set sq, cq depth */
+	hisi_dma_chan_write(base, HISI_DMA_SQ_DEPTH, index, hw_depth);
+	hisi_dma_chan_write(base, HISI_DMA_CQ_DEPTH, index, hw_depth);
+
+	/* init sq tail and cq head */
+	hisi_dma_chan_write(base, HISI_DMA_SQ_TAIL_PTR, index, 0);
+	hisi_dma_chan_write(base, HISI_DMA_CQ_HEAD_PTR, index, 0);
+}
+
+static void hisi_dma_enable_qp(struct hisi_dma_dev *hdma_dev, u32 qp_index)
+{
+	hisi_dma_init_hw_qp(hdma_dev, qp_index);
+	hisi_dma_unmask_irq(hdma_dev, qp_index);
+	hisi_dma_enable_dma(hdma_dev, qp_index, true);
+}
+
+static void hisi_dma_disable_qp(struct hisi_dma_dev *hdma_dev, u32 qp_index)
+{
+	hisi_dma_reset_hw_chan(&hdma_dev->chan[qp_index]);
+}
+
+static void hisi_dma_enable_qps(struct hisi_dma_dev *hdma_dev)
+{
+	int i;
+
+	for (i = 0; i < hdma_dev->chan_num; i++) {
+		hdma_dev->chan[i].qp_num = i;
+		hdma_dev->chan[i].hdma_dev = hdma_dev;
+		hdma_dev->chan[i].vc.desc_free = hisi_dma_desc_free;
+		vchan_init(&hdma_dev->chan[i].vc, &hdma_dev->dma_dev);
+		hisi_dma_enable_qp(hdma_dev, i);
+	}
+}
+
+static void hisi_dma_disable_qps(struct hisi_dma_dev *hdma_dev)
+{
+	int i;
+
+	for (i = 0; i < hdma_dev->chan_num; i++) {
+		hisi_dma_disable_qp(hdma_dev, i);
+		tasklet_kill(&hdma_dev->chan[i].vc.task);
+	}
+}
+
+static irqreturn_t hisi_dma_irq(int irq, void *data)
+{
+	struct hisi_dma_chan *chan = data;
+	struct hisi_dma_dev *hdma_dev = chan->hdma_dev;
+	struct hisi_dma_desc *desc;
+	struct hisi_dma_cqe *cqe;
+	unsigned long flags;
+
+	spin_lock_irqsave(&chan->vc.lock, flags);
+
+	desc = chan->desc;
+	cqe = chan->cq + chan->cq_head;
+	if (desc) {
+		if (FIELD_GET(STATUS_MASK, cqe->w0) == STATUS_SUCC) {
+			chan->cq_head = (chan->cq_head + 1) %
+					hdma_dev->chan_depth;
+			hisi_dma_chan_write(hdma_dev->base,
+					    HISI_DMA_CQ_HEAD_PTR, chan->qp_num,
+					    chan->cq_head);
+			vchan_cookie_complete(&desc->vd);
+		} else {
+			dev_err(&hdma_dev->pdev->dev, "task error!\n");
+		}
+
+		chan->desc = NULL;
+	}
+
+	spin_unlock_irqrestore(&chan->vc.lock, flags);
+
+	return IRQ_HANDLED;
+}
+
+static int hisi_dma_request_qps_irq(struct hisi_dma_dev *hdma_dev)
+{
+	struct pci_dev *pdev = hdma_dev->pdev;
+	int i, ret;
+
+	for (i = 0; i < hdma_dev->chan_num; i++) {
+		ret = devm_request_irq(&pdev->dev, pci_irq_vector(pdev, i),
+				       hisi_dma_irq, IRQF_SHARED, "hisi_dma",
+				       &hdma_dev->chan[i]);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+/* This function enables all hw channels in a device */
+static int hisi_dma_enable_hw_channels(struct hisi_dma_dev *hdma_dev)
+{
+	int ret;
+
+	ret = hisi_dma_alloc_qps_mem(hdma_dev);
+	if (ret) {
+		dev_err(&hdma_dev->pdev->dev, "fail to allocate qp memory!\n");
+		return ret;
+	}
+
+	ret = hisi_dma_request_qps_irq(hdma_dev);
+	if (ret) {
+		dev_err(&hdma_dev->pdev->dev, "fail to request qp irq!\n");
+		return ret;
+	}
+
+	hisi_dma_enable_qps(hdma_dev);
+
+	return 0;
+}
+
+static void hisi_dma_disable_hw_channels(void *data)
+{
+	hisi_dma_disable_qps(data);
+}
+
+static void hisi_dma_set_mode(struct hisi_dma_dev *hdma_dev,
+			      enum hisi_dma_mode mode)
+{
+	writel_relaxed(mode == RC ? 1 : 0, hdma_dev->base + HISI_DMA_MODE);
+}
+
+static int hisi_dma_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct device *dev = &pdev->dev;
+	struct hisi_dma_dev *hdma_dev;
+	struct dma_device *dma_dev;
+	size_t dev_size;
+	int ret;
+
+	ret = pcim_enable_device(pdev);
+	if (ret) {
+		dev_err(dev, "failed to enable device mem!\n");
+		return ret;
+	}
+
+	ret = pcim_iomap_regions(pdev, 1 << PCI_BAR_2, pci_name(pdev));
+	if (ret) {
+		dev_err(dev, "failed to remap I/O region!\n");
+		return ret;
+	}
+
+	ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
+	if (ret)
+		return ret;
+
+	ret = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
+	if (ret)
+		return ret;
+
+	dev_size = sizeof(struct hisi_dma_chan) * HISI_DMA_CHAN_NUM +
+		   sizeof(*hdma_dev);
+	hdma_dev = devm_kzalloc(dev, dev_size, GFP_KERNEL);
+	if (!hdma_dev)
+		return -EINVAL;
+
+	hdma_dev->base = pcim_iomap_table(pdev)[PCI_BAR_2];
+	hdma_dev->pdev = pdev;
+	hdma_dev->chan_num = HISI_DMA_CHAN_NUM;
+	hdma_dev->chan_depth = HISI_DMA_Q_DEPTH_VAL;
+
+	pci_set_drvdata(pdev, hdma_dev);
+	pci_set_master(pdev);
+
+	ret = pci_alloc_irq_vectors(pdev, HISI_DMA_MSI_NUM, HISI_DMA_MSI_NUM,
+				    PCI_IRQ_MSI);
+	if (ret < 0) {
+		dev_err(dev, "Failed to allocate MSI vectors!\n");
+		return ret;
+	}
+
+	ret = devm_add_action_or_reset(dev, hisi_dma_free_irq_vectors, pdev);
+	if (ret)
+		return ret;
+
+	dma_dev = &hdma_dev->dma_dev;
+	dma_cap_set(DMA_MEMCPY, dma_dev->cap_mask);
+	dma_dev->device_free_chan_resources = hisi_dma_free_chan_resources;
+	dma_dev->device_prep_dma_memcpy = hisi_dma_prep_dma_memcpy;
+	dma_dev->device_tx_status = hisi_dma_tx_status;
+	dma_dev->device_issue_pending = hisi_dma_issue_pending;
+	dma_dev->device_terminate_all = hisi_dma_terminate_all;
+	dma_dev->device_synchronize = hisi_dma_synchronize;
+	dma_dev->directions = BIT(DMA_MEM_TO_MEM);
+	dma_dev->dev = dev;
+	INIT_LIST_HEAD(&dma_dev->channels);
+
+	hisi_dma_set_mode(hdma_dev, RC);
+
+	ret = hisi_dma_enable_hw_channels(hdma_dev);
+	if (ret < 0) {
+		dev_err(dev, "failed to enable hw channel!\n");
+		return ret;
+	}
+
+	ret = devm_add_action_or_reset(dev, hisi_dma_disable_hw_channels,
+				       hdma_dev);
+	if (ret)
+		return ret;
+
+	ret = dmaenginem_async_device_register(dma_dev);
+	if (ret < 0)
+		dev_err(dev, "failed to register device!\n");
+
+	return ret;
+}
+
+static const struct pci_device_id hisi_dma_pci_tbl[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, 0xa122) },
+	{ 0, }
+};
+
+static struct pci_driver hisi_dma_pci_driver = {
+	.name		= "hisi_dma",
+	.id_table	= hisi_dma_pci_tbl,
+	.probe		= hisi_dma_probe,
+};
+
+module_pci_driver(hisi_dma_pci_driver);
+
+MODULE_AUTHOR("Zhou Wang <wangzhou1@hisilicon.com>");
+MODULE_AUTHOR("Zhenfa Qiu <qiuzhenfa@hisilicon.com>");
+MODULE_DESCRIPTION("HiSilicon Kunpeng DMA controller driver");
+MODULE_LICENSE("GPL v2");
+MODULE_DEVICE_TABLE(pci, hisi_dma_pci_tbl);
diff --git a/drivers/dma/idxd/Makefile b/drivers/dma/idxd/Makefile
new file mode 100644
index 000000000000..8978b898d777
--- /dev/null
+++ b/drivers/dma/idxd/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_INTEL_IDXD) += idxd.o
+idxd-y := init.o irq.o device.o sysfs.o submit.o dma.o cdev.o
diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c
new file mode 100644
index 000000000000..989b7a25ca61
--- /dev/null
+++ b/drivers/dma/idxd/cdev.c
@@ -0,0 +1,302 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2019 Intel Corporation. All rights rsvd. */
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/device.h>
+#include <linux/sched/task.h>
+#include <linux/intel-svm.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
+#include <linux/cdev.h>
+#include <linux/fs.h>
+#include <linux/poll.h>
+#include <uapi/linux/idxd.h>
+#include "registers.h"
+#include "idxd.h"
+
+struct idxd_cdev_context {
+	const char *name;
+	dev_t devt;
+	struct ida minor_ida;
+};
+
+/*
+ * ictx is an array based off of accelerator types. enum idxd_type
+ * is used as index
+ */
+static struct idxd_cdev_context ictx[IDXD_TYPE_MAX] = {
+	{ .name = "dsa" },
+};
+
+struct idxd_user_context {
+	struct idxd_wq *wq;
+	struct task_struct *task;
+	unsigned int flags;
+};
+
+enum idxd_cdev_cleanup {
+	CDEV_NORMAL = 0,
+	CDEV_FAILED,
+};
+
+static void idxd_cdev_dev_release(struct device *dev)
+{
+	dev_dbg(dev, "releasing cdev device\n");
+	kfree(dev);
+}
+
+static struct device_type idxd_cdev_device_type = {
+	.name = "idxd_cdev",
+	.release = idxd_cdev_dev_release,
+};
+
+static inline struct idxd_cdev *inode_idxd_cdev(struct inode *inode)
+{
+	struct cdev *cdev = inode->i_cdev;
+
+	return container_of(cdev, struct idxd_cdev, cdev);
+}
+
+static inline struct idxd_wq *idxd_cdev_wq(struct idxd_cdev *idxd_cdev)
+{
+	return container_of(idxd_cdev, struct idxd_wq, idxd_cdev);
+}
+
+static inline struct idxd_wq *inode_wq(struct inode *inode)
+{
+	return idxd_cdev_wq(inode_idxd_cdev(inode));
+}
+
+static int idxd_cdev_open(struct inode *inode, struct file *filp)
+{
+	struct idxd_user_context *ctx;
+	struct idxd_device *idxd;
+	struct idxd_wq *wq;
+	struct device *dev;
+	struct idxd_cdev *idxd_cdev;
+
+	wq = inode_wq(inode);
+	idxd = wq->idxd;
+	dev = &idxd->pdev->dev;
+	idxd_cdev = &wq->idxd_cdev;
+
+	dev_dbg(dev, "%s called: %d\n", __func__, idxd_wq_refcount(wq));
+
+	if (idxd_wq_refcount(wq) > 0 && wq_dedicated(wq))
+		return -EBUSY;
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->wq = wq;
+	filp->private_data = ctx;
+	idxd_wq_get(wq);
+	return 0;
+}
+
+static int idxd_cdev_release(struct inode *node, struct file *filep)
+{
+	struct idxd_user_context *ctx = filep->private_data;
+	struct idxd_wq *wq = ctx->wq;
+	struct idxd_device *idxd = wq->idxd;
+	struct device *dev = &idxd->pdev->dev;
+
+	dev_dbg(dev, "%s called\n", __func__);
+	filep->private_data = NULL;
+
+	kfree(ctx);
+	idxd_wq_put(wq);
+	return 0;
+}
+
+static int check_vma(struct idxd_wq *wq, struct vm_area_struct *vma,
+		     const char *func)
+{
+	struct device *dev = &wq->idxd->pdev->dev;
+
+	if ((vma->vm_end - vma->vm_start) > PAGE_SIZE) {
+		dev_info_ratelimited(dev,
+				     "%s: %s: mapping too large: %lu\n",
+				     current->comm, func,
+				     vma->vm_end - vma->vm_start);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int idxd_cdev_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	struct idxd_user_context *ctx = filp->private_data;
+	struct idxd_wq *wq = ctx->wq;
+	struct idxd_device *idxd = wq->idxd;
+	struct pci_dev *pdev = idxd->pdev;
+	phys_addr_t base = pci_resource_start(pdev, IDXD_WQ_BAR);
+	unsigned long pfn;
+	int rc;
+
+	dev_dbg(&pdev->dev, "%s called\n", __func__);
+	rc = check_vma(wq, vma, __func__);
+
+	vma->vm_flags |= VM_DONTCOPY;
+	pfn = (base + idxd_get_wq_portal_full_offset(wq->id,
+				IDXD_PORTAL_LIMITED)) >> PAGE_SHIFT;
+	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+	vma->vm_private_data = ctx;
+
+	return io_remap_pfn_range(vma, vma->vm_start, pfn, PAGE_SIZE,
+			vma->vm_page_prot);
+}
+
+static __poll_t idxd_cdev_poll(struct file *filp,
+			       struct poll_table_struct *wait)
+{
+	struct idxd_user_context *ctx = filp->private_data;
+	struct idxd_wq *wq = ctx->wq;
+	struct idxd_device *idxd = wq->idxd;
+	struct idxd_cdev *idxd_cdev = &wq->idxd_cdev;
+	unsigned long flags;
+	__poll_t out = 0;
+
+	poll_wait(filp, &idxd_cdev->err_queue, wait);
+	spin_lock_irqsave(&idxd->dev_lock, flags);
+	if (idxd->sw_err.valid)
+		out = EPOLLIN | EPOLLRDNORM;
+	spin_unlock_irqrestore(&idxd->dev_lock, flags);
+
+	return out;
+}
+
+static const struct file_operations idxd_cdev_fops = {
+	.owner = THIS_MODULE,
+	.open = idxd_cdev_open,
+	.release = idxd_cdev_release,
+	.mmap = idxd_cdev_mmap,
+	.poll = idxd_cdev_poll,
+};
+
+int idxd_cdev_get_major(struct idxd_device *idxd)
+{
+	return MAJOR(ictx[idxd->type].devt);
+}
+
+static int idxd_wq_cdev_dev_setup(struct idxd_wq *wq)
+{
+	struct idxd_device *idxd = wq->idxd;
+	struct idxd_cdev *idxd_cdev = &wq->idxd_cdev;
+	struct idxd_cdev_context *cdev_ctx;
+	struct device *dev;
+	int minor, rc;
+
+	idxd_cdev->dev = kzalloc(sizeof(*idxd_cdev->dev), GFP_KERNEL);
+	if (!idxd_cdev->dev)
+		return -ENOMEM;
+
+	dev = idxd_cdev->dev;
+	dev->parent = &idxd->pdev->dev;
+	dev_set_name(dev, "%s/wq%u.%u", idxd_get_dev_name(idxd),
+		     idxd->id, wq->id);
+	dev->bus = idxd_get_bus_type(idxd);
+
+	cdev_ctx = &ictx[wq->idxd->type];
+	minor = ida_simple_get(&cdev_ctx->minor_ida, 0, MINORMASK, GFP_KERNEL);
+	if (minor < 0) {
+		rc = minor;
+		kfree(dev);
+		goto ida_err;
+	}
+
+	dev->devt = MKDEV(MAJOR(cdev_ctx->devt), minor);
+	dev->type = &idxd_cdev_device_type;
+	rc = device_register(dev);
+	if (rc < 0) {
+		dev_err(&idxd->pdev->dev, "device register failed\n");
+		goto dev_reg_err;
+	}
+	idxd_cdev->minor = minor;
+
+	return 0;
+
+ dev_reg_err:
+	ida_simple_remove(&cdev_ctx->minor_ida, MINOR(dev->devt));
+	put_device(dev);
+ ida_err:
+	idxd_cdev->dev = NULL;
+	return rc;
+}
+
+static void idxd_wq_cdev_cleanup(struct idxd_wq *wq,
+				 enum idxd_cdev_cleanup cdev_state)
+{
+	struct idxd_cdev *idxd_cdev = &wq->idxd_cdev;
+	struct idxd_cdev_context *cdev_ctx;
+
+	cdev_ctx = &ictx[wq->idxd->type];
+	if (cdev_state == CDEV_NORMAL)
+		cdev_del(&idxd_cdev->cdev);
+	device_unregister(idxd_cdev->dev);
+	/*
+	 * The device_type->release() will be called on the device and free
+	 * the allocated struct device. We can just forget it.
+	 */
+	ida_simple_remove(&cdev_ctx->minor_ida, idxd_cdev->minor);
+	idxd_cdev->dev = NULL;
+	idxd_cdev->minor = -1;
+}
+
+int idxd_wq_add_cdev(struct idxd_wq *wq)
+{
+	struct idxd_cdev *idxd_cdev = &wq->idxd_cdev;
+	struct cdev *cdev = &idxd_cdev->cdev;
+	struct device *dev;
+	int rc;
+
+	rc = idxd_wq_cdev_dev_setup(wq);
+	if (rc < 0)
+		return rc;
+
+	dev = idxd_cdev->dev;
+	cdev_init(cdev, &idxd_cdev_fops);
+	cdev_set_parent(cdev, &dev->kobj);
+	rc = cdev_add(cdev, dev->devt, 1);
+	if (rc) {
+		dev_dbg(&wq->idxd->pdev->dev, "cdev_add failed: %d\n", rc);
+		idxd_wq_cdev_cleanup(wq, CDEV_FAILED);
+		return rc;
+	}
+
+	init_waitqueue_head(&idxd_cdev->err_queue);
+	return 0;
+}
+
+void idxd_wq_del_cdev(struct idxd_wq *wq)
+{
+	idxd_wq_cdev_cleanup(wq, CDEV_NORMAL);
+}
+
+int idxd_cdev_register(void)
+{
+	int rc, i;
+
+	for (i = 0; i < IDXD_TYPE_MAX; i++) {
+		ida_init(&ictx[i].minor_ida);
+		rc = alloc_chrdev_region(&ictx[i].devt, 0, MINORMASK,
+					 ictx[i].name);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
+void idxd_cdev_remove(void)
+{
+	int i;
+
+	for (i = 0; i < IDXD_TYPE_MAX; i++) {
+		unregister_chrdev_region(ictx[i].devt, MINORMASK);
+		ida_destroy(&ictx[i].minor_ida);
+	}
+}
diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
new file mode 100644
index 000000000000..ada69e722f84
--- /dev/null
+++ b/drivers/dma/idxd/device.c
@@ -0,0 +1,693 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2019 Intel Corporation. All rights rsvd. */
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
+#include <linux/dmaengine.h>
+#include <uapi/linux/idxd.h>
+#include "../dmaengine.h"
+#include "idxd.h"
+#include "registers.h"
+
+static int idxd_cmd_wait(struct idxd_device *idxd, u32 *status, int timeout);
+static int idxd_cmd_send(struct idxd_device *idxd, int cmd_code, u32 operand);
+
+/* Interrupt control bits */
+int idxd_mask_msix_vector(struct idxd_device *idxd, int vec_id)
+{
+	struct pci_dev *pdev = idxd->pdev;
+	int msixcnt = pci_msix_vec_count(pdev);
+	union msix_perm perm;
+	u32 offset;
+
+	if (vec_id < 0 || vec_id >= msixcnt)
+		return -EINVAL;
+
+	offset = idxd->msix_perm_offset + vec_id * 8;
+	perm.bits = ioread32(idxd->reg_base + offset);
+	perm.ignore = 1;
+	iowrite32(perm.bits, idxd->reg_base + offset);
+
+	return 0;
+}
+
+void idxd_mask_msix_vectors(struct idxd_device *idxd)
+{
+	struct pci_dev *pdev = idxd->pdev;
+	int msixcnt = pci_msix_vec_count(pdev);
+	int i, rc;
+
+	for (i = 0; i < msixcnt; i++) {
+		rc = idxd_mask_msix_vector(idxd, i);
+		if (rc < 0)
+			dev_warn(&pdev->dev,
+				 "Failed disabling msix vec %d\n", i);
+	}
+}
+
+int idxd_unmask_msix_vector(struct idxd_device *idxd, int vec_id)
+{
+	struct pci_dev *pdev = idxd->pdev;
+	int msixcnt = pci_msix_vec_count(pdev);
+	union msix_perm perm;
+	u32 offset;
+
+	if (vec_id < 0 || vec_id >= msixcnt)
+		return -EINVAL;
+
+	offset = idxd->msix_perm_offset + vec_id * 8;
+	perm.bits = ioread32(idxd->reg_base + offset);
+	perm.ignore = 0;
+	iowrite32(perm.bits, idxd->reg_base + offset);
+
+	return 0;
+}
+
+void idxd_unmask_error_interrupts(struct idxd_device *idxd)
+{
+	union genctrl_reg genctrl;
+
+	genctrl.bits = ioread32(idxd->reg_base + IDXD_GENCTRL_OFFSET);
+	genctrl.softerr_int_en = 1;
+	iowrite32(genctrl.bits, idxd->reg_base + IDXD_GENCTRL_OFFSET);
+}
+
+void idxd_mask_error_interrupts(struct idxd_device *idxd)
+{
+	union genctrl_reg genctrl;
+
+	genctrl.bits = ioread32(idxd->reg_base + IDXD_GENCTRL_OFFSET);
+	genctrl.softerr_int_en = 0;
+	iowrite32(genctrl.bits, idxd->reg_base + IDXD_GENCTRL_OFFSET);
+}
+
+static void free_hw_descs(struct idxd_wq *wq)
+{
+	int i;
+
+	for (i = 0; i < wq->num_descs; i++)
+		kfree(wq->hw_descs[i]);
+
+	kfree(wq->hw_descs);
+}
+
+static int alloc_hw_descs(struct idxd_wq *wq, int num)
+{
+	struct device *dev = &wq->idxd->pdev->dev;
+	int i;
+	int node = dev_to_node(dev);
+
+	wq->hw_descs = kcalloc_node(num, sizeof(struct dsa_hw_desc *),
+				    GFP_KERNEL, node);
+	if (!wq->hw_descs)
+		return -ENOMEM;
+
+	for (i = 0; i < num; i++) {
+		wq->hw_descs[i] = kzalloc_node(sizeof(*wq->hw_descs[i]),
+					       GFP_KERNEL, node);
+		if (!wq->hw_descs[i]) {
+			free_hw_descs(wq);
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
+static void free_descs(struct idxd_wq *wq)
+{
+	int i;
+
+	for (i = 0; i < wq->num_descs; i++)
+		kfree(wq->descs[i]);
+
+	kfree(wq->descs);
+}
+
+static int alloc_descs(struct idxd_wq *wq, int num)
+{
+	struct device *dev = &wq->idxd->pdev->dev;
+	int i;
+	int node = dev_to_node(dev);
+
+	wq->descs = kcalloc_node(num, sizeof(struct idxd_desc *),
+				 GFP_KERNEL, node);
+	if (!wq->descs)
+		return -ENOMEM;
+
+	for (i = 0; i < num; i++) {
+		wq->descs[i] = kzalloc_node(sizeof(*wq->descs[i]),
+					    GFP_KERNEL, node);
+		if (!wq->descs[i]) {
+			free_descs(wq);
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
+/* WQ control bits */
+int idxd_wq_alloc_resources(struct idxd_wq *wq)
+{
+	struct idxd_device *idxd = wq->idxd;
+	struct idxd_group *group = wq->group;
+	struct device *dev = &idxd->pdev->dev;
+	int rc, num_descs, i;
+
+	if (wq->type != IDXD_WQT_KERNEL)
+		return 0;
+
+	num_descs = wq->size +
+		idxd->hw.gen_cap.max_descs_per_engine * group->num_engines;
+	wq->num_descs = num_descs;
+
+	rc = alloc_hw_descs(wq, num_descs);
+	if (rc < 0)
+		return rc;
+
+	wq->compls_size = num_descs * sizeof(struct dsa_completion_record);
+	wq->compls = dma_alloc_coherent(dev, wq->compls_size,
+					&wq->compls_addr, GFP_KERNEL);
+	if (!wq->compls) {
+		rc = -ENOMEM;
+		goto fail_alloc_compls;
+	}
+
+	rc = alloc_descs(wq, num_descs);
+	if (rc < 0)
+		goto fail_alloc_descs;
+
+	rc = sbitmap_init_node(&wq->sbmap, num_descs, -1, GFP_KERNEL,
+			       dev_to_node(dev));
+	if (rc < 0)
+		goto fail_sbitmap_init;
+
+	for (i = 0; i < num_descs; i++) {
+		struct idxd_desc *desc = wq->descs[i];
+
+		desc->hw = wq->hw_descs[i];
+		desc->completion = &wq->compls[i];
+		desc->compl_dma  = wq->compls_addr +
+			sizeof(struct dsa_completion_record) * i;
+		desc->id = i;
+		desc->wq = wq;
+
+		dma_async_tx_descriptor_init(&desc->txd, &wq->dma_chan);
+		desc->txd.tx_submit = idxd_dma_tx_submit;
+	}
+
+	return 0;
+
+ fail_sbitmap_init:
+	free_descs(wq);
+ fail_alloc_descs:
+	dma_free_coherent(dev, wq->compls_size, wq->compls, wq->compls_addr);
+ fail_alloc_compls:
+	free_hw_descs(wq);
+	return rc;
+}
+
+void idxd_wq_free_resources(struct idxd_wq *wq)
+{
+	struct device *dev = &wq->idxd->pdev->dev;
+
+	if (wq->type != IDXD_WQT_KERNEL)
+		return;
+
+	free_hw_descs(wq);
+	free_descs(wq);
+	dma_free_coherent(dev, wq->compls_size, wq->compls, wq->compls_addr);
+	sbitmap_free(&wq->sbmap);
+}
+
+int idxd_wq_enable(struct idxd_wq *wq)
+{
+	struct idxd_device *idxd = wq->idxd;
+	struct device *dev = &idxd->pdev->dev;
+	u32 status;
+	int rc;
+
+	lockdep_assert_held(&idxd->dev_lock);
+
+	if (wq->state == IDXD_WQ_ENABLED) {
+		dev_dbg(dev, "WQ %d already enabled\n", wq->id);
+		return -ENXIO;
+	}
+
+	rc = idxd_cmd_send(idxd, IDXD_CMD_ENABLE_WQ, wq->id);
+	if (rc < 0)
+		return rc;
+	rc = idxd_cmd_wait(idxd, &status, IDXD_REG_TIMEOUT);
+	if (rc < 0)
+		return rc;
+
+	if (status != IDXD_CMDSTS_SUCCESS &&
+	    status != IDXD_CMDSTS_ERR_WQ_ENABLED) {
+		dev_dbg(dev, "WQ enable failed: %#x\n", status);
+		return -ENXIO;
+	}
+
+	wq->state = IDXD_WQ_ENABLED;
+	dev_dbg(dev, "WQ %d enabled\n", wq->id);
+	return 0;
+}
+
+int idxd_wq_disable(struct idxd_wq *wq)
+{
+	struct idxd_device *idxd = wq->idxd;
+	struct device *dev = &idxd->pdev->dev;
+	u32 status, operand;
+	int rc;
+
+	lockdep_assert_held(&idxd->dev_lock);
+	dev_dbg(dev, "Disabling WQ %d\n", wq->id);
+
+	if (wq->state != IDXD_WQ_ENABLED) {
+		dev_dbg(dev, "WQ %d in wrong state: %d\n", wq->id, wq->state);
+		return 0;
+	}
+
+	operand = BIT(wq->id % 16) | ((wq->id / 16) << 16);
+	rc = idxd_cmd_send(idxd, IDXD_CMD_DISABLE_WQ, operand);
+	if (rc < 0)
+		return rc;
+	rc = idxd_cmd_wait(idxd, &status, IDXD_REG_TIMEOUT);
+	if (rc < 0)
+		return rc;
+
+	if (status != IDXD_CMDSTS_SUCCESS) {
+		dev_dbg(dev, "WQ disable failed: %#x\n", status);
+		return -ENXIO;
+	}
+
+	wq->state = IDXD_WQ_DISABLED;
+	dev_dbg(dev, "WQ %d disabled\n", wq->id);
+	return 0;
+}
+
+int idxd_wq_map_portal(struct idxd_wq *wq)
+{
+	struct idxd_device *idxd = wq->idxd;
+	struct pci_dev *pdev = idxd->pdev;
+	struct device *dev = &pdev->dev;
+	resource_size_t start;
+
+	start = pci_resource_start(pdev, IDXD_WQ_BAR);
+	start = start + wq->id * IDXD_PORTAL_SIZE;
+
+	wq->dportal = devm_ioremap(dev, start, IDXD_PORTAL_SIZE);
+	if (!wq->dportal)
+		return -ENOMEM;
+	dev_dbg(dev, "wq %d portal mapped at %p\n", wq->id, wq->dportal);
+
+	return 0;
+}
+
+void idxd_wq_unmap_portal(struct idxd_wq *wq)
+{
+	struct device *dev = &wq->idxd->pdev->dev;
+
+	devm_iounmap(dev, wq->dportal);
+}
+
+/* Device control bits */
+static inline bool idxd_is_enabled(struct idxd_device *idxd)
+{
+	union gensts_reg gensts;
+
+	gensts.bits = ioread32(idxd->reg_base + IDXD_GENSTATS_OFFSET);
+
+	if (gensts.state == IDXD_DEVICE_STATE_ENABLED)
+		return true;
+	return false;
+}
+
+static int idxd_cmd_wait(struct idxd_device *idxd, u32 *status, int timeout)
+{
+	u32 sts, to = timeout;
+
+	lockdep_assert_held(&idxd->dev_lock);
+	sts = ioread32(idxd->reg_base + IDXD_CMDSTS_OFFSET);
+	while (sts & IDXD_CMDSTS_ACTIVE && --to) {
+		cpu_relax();
+		sts = ioread32(idxd->reg_base + IDXD_CMDSTS_OFFSET);
+	}
+
+	if (to == 0 && sts & IDXD_CMDSTS_ACTIVE) {
+		dev_warn(&idxd->pdev->dev, "%s timed out!\n", __func__);
+		*status = 0;
+		return -EBUSY;
+	}
+
+	*status = sts;
+	return 0;
+}
+
+static int idxd_cmd_send(struct idxd_device *idxd, int cmd_code, u32 operand)
+{
+	union idxd_command_reg cmd;
+	int rc;
+	u32 status;
+
+	lockdep_assert_held(&idxd->dev_lock);
+	rc = idxd_cmd_wait(idxd, &status, IDXD_REG_TIMEOUT);
+	if (rc < 0)
+		return rc;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.cmd = cmd_code;
+	cmd.operand = operand;
+	dev_dbg(&idxd->pdev->dev, "%s: sending cmd: %#x op: %#x\n",
+		__func__, cmd_code, operand);
+	iowrite32(cmd.bits, idxd->reg_base + IDXD_CMD_OFFSET);
+
+	return 0;
+}
+
+int idxd_device_enable(struct idxd_device *idxd)
+{
+	struct device *dev = &idxd->pdev->dev;
+	int rc;
+	u32 status;
+
+	lockdep_assert_held(&idxd->dev_lock);
+	if (idxd_is_enabled(idxd)) {
+		dev_dbg(dev, "Device already enabled\n");
+		return -ENXIO;
+	}
+
+	rc = idxd_cmd_send(idxd, IDXD_CMD_ENABLE_DEVICE, 0);
+	if (rc < 0)
+		return rc;
+	rc = idxd_cmd_wait(idxd, &status, IDXD_REG_TIMEOUT);
+	if (rc < 0)
+		return rc;
+
+	/* If the command is successful or if the device was enabled */
+	if (status != IDXD_CMDSTS_SUCCESS &&
+	    status != IDXD_CMDSTS_ERR_DEV_ENABLED) {
+		dev_dbg(dev, "%s: err_code: %#x\n", __func__, status);
+		return -ENXIO;
+	}
+
+	idxd->state = IDXD_DEV_ENABLED;
+	return 0;
+}
+
+int idxd_device_disable(struct idxd_device *idxd)
+{
+	struct device *dev = &idxd->pdev->dev;
+	int rc;
+	u32 status;
+
+	lockdep_assert_held(&idxd->dev_lock);
+	if (!idxd_is_enabled(idxd)) {
+		dev_dbg(dev, "Device is not enabled\n");
+		return 0;
+	}
+
+	rc = idxd_cmd_send(idxd, IDXD_CMD_DISABLE_DEVICE, 0);
+	if (rc < 0)
+		return rc;
+	rc = idxd_cmd_wait(idxd, &status, IDXD_REG_TIMEOUT);
+	if (rc < 0)
+		return rc;
+
+	/* If the command is successful or if the device was disabled */
+	if (status != IDXD_CMDSTS_SUCCESS &&
+	    !(status & IDXD_CMDSTS_ERR_DIS_DEV_EN)) {
+		dev_dbg(dev, "%s: err_code: %#x\n", __func__, status);
+		rc = -ENXIO;
+		return rc;
+	}
+
+	idxd->state = IDXD_DEV_CONF_READY;
+	return 0;
+}
+
+int __idxd_device_reset(struct idxd_device *idxd)
+{
+	u32 status;
+	int rc;
+
+	rc = idxd_cmd_send(idxd, IDXD_CMD_RESET_DEVICE, 0);
+	if (rc < 0)
+		return rc;
+	rc = idxd_cmd_wait(idxd, &status, IDXD_REG_TIMEOUT);
+	if (rc < 0)
+		return rc;
+
+	return 0;
+}
+
+int idxd_device_reset(struct idxd_device *idxd)
+{
+	unsigned long flags;
+	int rc;
+
+	spin_lock_irqsave(&idxd->dev_lock, flags);
+	rc = __idxd_device_reset(idxd);
+	spin_unlock_irqrestore(&idxd->dev_lock, flags);
+	return rc;
+}
+
+/* Device configuration bits */
+static void idxd_group_config_write(struct idxd_group *group)
+{
+	struct idxd_device *idxd = group->idxd;
+	struct device *dev = &idxd->pdev->dev;
+	int i;
+	u32 grpcfg_offset;
+
+	dev_dbg(dev, "Writing group %d cfg registers\n", group->id);
+
+	/* setup GRPWQCFG */
+	for (i = 0; i < 4; i++) {
+		grpcfg_offset = idxd->grpcfg_offset +
+			group->id * 64 + i * sizeof(u64);
+		iowrite64(group->grpcfg.wqs[i],
+			  idxd->reg_base + grpcfg_offset);
+		dev_dbg(dev, "GRPCFG wq[%d:%d: %#x]: %#llx\n",
+			group->id, i, grpcfg_offset,
+			ioread64(idxd->reg_base + grpcfg_offset));
+	}
+
+	/* setup GRPENGCFG */
+	grpcfg_offset = idxd->grpcfg_offset + group->id * 64 + 32;
+	iowrite64(group->grpcfg.engines, idxd->reg_base + grpcfg_offset);
+	dev_dbg(dev, "GRPCFG engs[%d: %#x]: %#llx\n", group->id,
+		grpcfg_offset, ioread64(idxd->reg_base + grpcfg_offset));
+
+	/* setup GRPFLAGS */
+	grpcfg_offset = idxd->grpcfg_offset + group->id * 64 + 40;
+	iowrite32(group->grpcfg.flags.bits, idxd->reg_base + grpcfg_offset);
+	dev_dbg(dev, "GRPFLAGS flags[%d: %#x]: %#x\n",
+		group->id, grpcfg_offset,
+		ioread32(idxd->reg_base + grpcfg_offset));
+}
+
+static int idxd_groups_config_write(struct idxd_device *idxd)
+
+{
+	union gencfg_reg reg;
+	int i;
+	struct device *dev = &idxd->pdev->dev;
+
+	/* Setup bandwidth token limit */
+	if (idxd->token_limit) {
+		reg.bits = ioread32(idxd->reg_base + IDXD_GENCFG_OFFSET);
+		reg.token_limit = idxd->token_limit;
+		iowrite32(reg.bits, idxd->reg_base + IDXD_GENCFG_OFFSET);
+	}
+
+	dev_dbg(dev, "GENCFG(%#x): %#x\n", IDXD_GENCFG_OFFSET,
+		ioread32(idxd->reg_base + IDXD_GENCFG_OFFSET));
+
+	for (i = 0; i < idxd->max_groups; i++) {
+		struct idxd_group *group = &idxd->groups[i];
+
+		idxd_group_config_write(group);
+	}
+
+	return 0;
+}
+
+static int idxd_wq_config_write(struct idxd_wq *wq)
+{
+	struct idxd_device *idxd = wq->idxd;
+	struct device *dev = &idxd->pdev->dev;
+	u32 wq_offset;
+	int i;
+
+	if (!wq->group)
+		return 0;
+
+	memset(&wq->wqcfg, 0, sizeof(union wqcfg));
+
+	/* byte 0-3 */
+	wq->wqcfg.wq_size = wq->size;
+
+	if (wq->size == 0) {
+		dev_warn(dev, "Incorrect work queue size: 0\n");
+		return -EINVAL;
+	}
+
+	/* bytes 4-7 */
+	wq->wqcfg.wq_thresh = wq->threshold;
+
+	/* byte 8-11 */
+	wq->wqcfg.priv = !!(wq->type == IDXD_WQT_KERNEL);
+	wq->wqcfg.mode = 1;
+
+	wq->wqcfg.priority = wq->priority;
+
+	/* bytes 12-15 */
+	wq->wqcfg.max_xfer_shift = idxd->hw.gen_cap.max_xfer_shift;
+	wq->wqcfg.max_batch_shift = idxd->hw.gen_cap.max_batch_shift;
+
+	dev_dbg(dev, "WQ %d CFGs\n", wq->id);
+	for (i = 0; i < 8; i++) {
+		wq_offset = idxd->wqcfg_offset + wq->id * 32 + i * sizeof(u32);
+		iowrite32(wq->wqcfg.bits[i], idxd->reg_base + wq_offset);
+		dev_dbg(dev, "WQ[%d][%d][%#x]: %#x\n",
+			wq->id, i, wq_offset,
+			ioread32(idxd->reg_base + wq_offset));
+	}
+
+	return 0;
+}
+
+static int idxd_wqs_config_write(struct idxd_device *idxd)
+{
+	int i, rc;
+
+	for (i = 0; i < idxd->max_wqs; i++) {
+		struct idxd_wq *wq = &idxd->wqs[i];
+
+		rc = idxd_wq_config_write(wq);
+		if (rc < 0)
+			return rc;
+	}
+
+	return 0;
+}
+
+static void idxd_group_flags_setup(struct idxd_device *idxd)
+{
+	int i;
+
+	/* TC-A 0 and TC-B 1 should be defaults */
+	for (i = 0; i < idxd->max_groups; i++) {
+		struct idxd_group *group = &idxd->groups[i];
+
+		if (group->tc_a == -1)
+			group->grpcfg.flags.tc_a = 0;
+		else
+			group->grpcfg.flags.tc_a = group->tc_a;
+		if (group->tc_b == -1)
+			group->grpcfg.flags.tc_b = 1;
+		else
+			group->grpcfg.flags.tc_b = group->tc_b;
+		group->grpcfg.flags.use_token_limit = group->use_token_limit;
+		group->grpcfg.flags.tokens_reserved = group->tokens_reserved;
+		if (group->tokens_allowed)
+			group->grpcfg.flags.tokens_allowed =
+				group->tokens_allowed;
+		else
+			group->grpcfg.flags.tokens_allowed = idxd->max_tokens;
+	}
+}
+
+static int idxd_engines_setup(struct idxd_device *idxd)
+{
+	int i, engines = 0;
+	struct idxd_engine *eng;
+	struct idxd_group *group;
+
+	for (i = 0; i < idxd->max_groups; i++) {
+		group = &idxd->groups[i];
+		group->grpcfg.engines = 0;
+	}
+
+	for (i = 0; i < idxd->max_engines; i++) {
+		eng = &idxd->engines[i];
+		group = eng->group;
+
+		if (!group)
+			continue;
+
+		group->grpcfg.engines |= BIT(eng->id);
+		engines++;
+	}
+
+	if (!engines)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int idxd_wqs_setup(struct idxd_device *idxd)
+{
+	struct idxd_wq *wq;
+	struct idxd_group *group;
+	int i, j, configured = 0;
+	struct device *dev = &idxd->pdev->dev;
+
+	for (i = 0; i < idxd->max_groups; i++) {
+		group = &idxd->groups[i];
+		for (j = 0; j < 4; j++)
+			group->grpcfg.wqs[j] = 0;
+	}
+
+	for (i = 0; i < idxd->max_wqs; i++) {
+		wq = &idxd->wqs[i];
+		group = wq->group;
+
+		if (!wq->group)
+			continue;
+		if (!wq->size)
+			continue;
+
+		if (!wq_dedicated(wq)) {
+			dev_warn(dev, "No shared workqueue support.\n");
+			return -EINVAL;
+		}
+
+		group->grpcfg.wqs[wq->id / 64] |= BIT(wq->id % 64);
+		configured++;
+	}
+
+	if (configured == 0)
+		return -EINVAL;
+
+	return 0;
+}
+
+int idxd_device_config(struct idxd_device *idxd)
+{
+	int rc;
+
+	lockdep_assert_held(&idxd->dev_lock);
+	rc = idxd_wqs_setup(idxd);
+	if (rc < 0)
+		return rc;
+
+	rc = idxd_engines_setup(idxd);
+	if (rc < 0)
+		return rc;
+
+	idxd_group_flags_setup(idxd);
+
+	rc = idxd_wqs_config_write(idxd);
+	if (rc < 0)
+		return rc;
+
+	rc = idxd_groups_config_write(idxd);
+	if (rc < 0)
+		return rc;
+
+	return 0;
+}
diff --git a/drivers/dma/idxd/dma.c b/drivers/dma/idxd/dma.c
new file mode 100644
index 000000000000..c64c1429d160
--- /dev/null
+++ b/drivers/dma/idxd/dma.c
@@ -0,0 +1,217 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2019 Intel Corporation. All rights rsvd. */
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/device.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
+#include <linux/dmaengine.h>
+#include <uapi/linux/idxd.h>
+#include "../dmaengine.h"
+#include "registers.h"
+#include "idxd.h"
+
+static inline struct idxd_wq *to_idxd_wq(struct dma_chan *c)
+{
+	return container_of(c, struct idxd_wq, dma_chan);
+}
+
+void idxd_dma_complete_txd(struct idxd_desc *desc,
+			   enum idxd_complete_type comp_type)
+{
+	struct dma_async_tx_descriptor *tx;
+	struct dmaengine_result res;
+	int complete = 1;
+
+	if (desc->completion->status == DSA_COMP_SUCCESS)
+		res.result = DMA_TRANS_NOERROR;
+	else if (desc->completion->status)
+		res.result = DMA_TRANS_WRITE_FAILED;
+	else if (comp_type == IDXD_COMPLETE_ABORT)
+		res.result = DMA_TRANS_ABORTED;
+	else
+		complete = 0;
+
+	tx = &desc->txd;
+	if (complete && tx->cookie) {
+		dma_cookie_complete(tx);
+		dma_descriptor_unmap(tx);
+		dmaengine_desc_get_callback_invoke(tx, &res);
+		tx->callback = NULL;
+		tx->callback_result = NULL;
+	}
+}
+
+static void op_flag_setup(unsigned long flags, u32 *desc_flags)
+{
+	*desc_flags = IDXD_OP_FLAG_CRAV | IDXD_OP_FLAG_RCR;
+	if (flags & DMA_PREP_INTERRUPT)
+		*desc_flags |= IDXD_OP_FLAG_RCI;
+}
+
+static inline void set_completion_address(struct idxd_desc *desc,
+					  u64 *compl_addr)
+{
+		*compl_addr = desc->compl_dma;
+}
+
+static inline void idxd_prep_desc_common(struct idxd_wq *wq,
+					 struct dsa_hw_desc *hw, char opcode,
+					 u64 addr_f1, u64 addr_f2, u64 len,
+					 u64 compl, u32 flags)
+{
+	struct idxd_device *idxd = wq->idxd;
+
+	hw->flags = flags;
+	hw->opcode = opcode;
+	hw->src_addr = addr_f1;
+	hw->dst_addr = addr_f2;
+	hw->xfer_size = len;
+	hw->priv = !!(wq->type == IDXD_WQT_KERNEL);
+	hw->completion_addr = compl;
+
+	/*
+	 * Descriptor completion vectors are 1-8 for MSIX. We will round
+	 * robin through the 8 vectors.
+	 */
+	wq->vec_ptr = (wq->vec_ptr % idxd->num_wq_irqs) + 1;
+	hw->int_handle =  wq->vec_ptr;
+}
+
+static struct dma_async_tx_descriptor *
+idxd_dma_submit_memcpy(struct dma_chan *c, dma_addr_t dma_dest,
+		       dma_addr_t dma_src, size_t len, unsigned long flags)
+{
+	struct idxd_wq *wq = to_idxd_wq(c);
+	u32 desc_flags;
+	struct idxd_device *idxd = wq->idxd;
+	struct idxd_desc *desc;
+
+	if (wq->state != IDXD_WQ_ENABLED)
+		return NULL;
+
+	if (len > idxd->max_xfer_bytes)
+		return NULL;
+
+	op_flag_setup(flags, &desc_flags);
+	desc = idxd_alloc_desc(wq, IDXD_OP_BLOCK);
+	if (IS_ERR(desc))
+		return NULL;
+
+	idxd_prep_desc_common(wq, desc->hw, DSA_OPCODE_MEMMOVE,
+			      dma_src, dma_dest, len, desc->compl_dma,
+			      desc_flags);
+
+	desc->txd.flags = flags;
+
+	return &desc->txd;
+}
+
+static int idxd_dma_alloc_chan_resources(struct dma_chan *chan)
+{
+	struct idxd_wq *wq = to_idxd_wq(chan);
+	struct device *dev = &wq->idxd->pdev->dev;
+
+	idxd_wq_get(wq);
+	dev_dbg(dev, "%s: client_count: %d\n", __func__,
+		idxd_wq_refcount(wq));
+	return 0;
+}
+
+static void idxd_dma_free_chan_resources(struct dma_chan *chan)
+{
+	struct idxd_wq *wq = to_idxd_wq(chan);
+	struct device *dev = &wq->idxd->pdev->dev;
+
+	idxd_wq_put(wq);
+	dev_dbg(dev, "%s: client_count: %d\n", __func__,
+		idxd_wq_refcount(wq));
+}
+
+static enum dma_status idxd_dma_tx_status(struct dma_chan *dma_chan,
+					  dma_cookie_t cookie,
+					  struct dma_tx_state *txstate)
+{
+	return dma_cookie_status(dma_chan, cookie, txstate);
+}
+
+/*
+ * issue_pending() does not need to do anything since tx_submit() does the job
+ * already.
+ */
+static void idxd_dma_issue_pending(struct dma_chan *dma_chan)
+{
+}
+
+dma_cookie_t idxd_dma_tx_submit(struct dma_async_tx_descriptor *tx)
+{
+	struct dma_chan *c = tx->chan;
+	struct idxd_wq *wq = to_idxd_wq(c);
+	dma_cookie_t cookie;
+	int rc;
+	struct idxd_desc *desc = container_of(tx, struct idxd_desc, txd);
+
+	cookie = dma_cookie_assign(tx);
+
+	rc = idxd_submit_desc(wq, desc);
+	if (rc < 0) {
+		idxd_free_desc(wq, desc);
+		return rc;
+	}
+
+	return cookie;
+}
+
+static void idxd_dma_release(struct dma_device *device)
+{
+}
+
+int idxd_register_dma_device(struct idxd_device *idxd)
+{
+	struct dma_device *dma = &idxd->dma_dev;
+
+	INIT_LIST_HEAD(&dma->channels);
+	dma->dev = &idxd->pdev->dev;
+
+	dma->device_release = idxd_dma_release;
+
+	if (idxd->hw.opcap.bits[0] & IDXD_OPCAP_MEMMOVE) {
+		dma_cap_set(DMA_MEMCPY, dma->cap_mask);
+		dma->device_prep_dma_memcpy = idxd_dma_submit_memcpy;
+	}
+
+	dma->device_tx_status = idxd_dma_tx_status;
+	dma->device_issue_pending = idxd_dma_issue_pending;
+	dma->device_alloc_chan_resources = idxd_dma_alloc_chan_resources;
+	dma->device_free_chan_resources = idxd_dma_free_chan_resources;
+
+	return dma_async_device_register(&idxd->dma_dev);
+}
+
+void idxd_unregister_dma_device(struct idxd_device *idxd)
+{
+	dma_async_device_unregister(&idxd->dma_dev);
+}
+
+int idxd_register_dma_channel(struct idxd_wq *wq)
+{
+	struct idxd_device *idxd = wq->idxd;
+	struct dma_device *dma = &idxd->dma_dev;
+	struct dma_chan *chan = &wq->dma_chan;
+	int rc;
+
+	memset(&wq->dma_chan, 0, sizeof(struct dma_chan));
+	chan->device = dma;
+	list_add_tail(&chan->device_node, &dma->channels);
+	rc = dma_async_device_channel_register(dma, chan);
+	if (rc < 0)
+		return rc;
+
+	return 0;
+}
+
+void idxd_unregister_dma_channel(struct idxd_wq *wq)
+{
+	dma_async_device_channel_unregister(&wq->idxd->dma_dev, &wq->dma_chan);
+}
diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h
new file mode 100644
index 000000000000..b8f8a363b4a7
--- /dev/null
+++ b/drivers/dma/idxd/idxd.h
@@ -0,0 +1,316 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2019 Intel Corporation. All rights rsvd. */
+#ifndef _IDXD_H_
+#define _IDXD_H_
+
+#include <linux/sbitmap.h>
+#include <linux/dmaengine.h>
+#include <linux/percpu-rwsem.h>
+#include <linux/wait.h>
+#include <linux/cdev.h>
+#include "registers.h"
+
+#define IDXD_DRIVER_VERSION	"1.00"
+
+extern struct kmem_cache *idxd_desc_pool;
+
+#define IDXD_REG_TIMEOUT	50
+#define IDXD_DRAIN_TIMEOUT	5000
+
+enum idxd_type {
+	IDXD_TYPE_UNKNOWN = -1,
+	IDXD_TYPE_DSA = 0,
+	IDXD_TYPE_MAX
+};
+
+#define IDXD_NAME_SIZE		128
+
+struct idxd_device_driver {
+	struct device_driver drv;
+};
+
+struct idxd_irq_entry {
+	struct idxd_device *idxd;
+	int id;
+	struct llist_head pending_llist;
+	struct list_head work_list;
+};
+
+struct idxd_group {
+	struct device conf_dev;
+	struct idxd_device *idxd;
+	struct grpcfg grpcfg;
+	int id;
+	int num_engines;
+	int num_wqs;
+	bool use_token_limit;
+	u8 tokens_allowed;
+	u8 tokens_reserved;
+	int tc_a;
+	int tc_b;
+};
+
+#define IDXD_MAX_PRIORITY	0xf
+
+enum idxd_wq_state {
+	IDXD_WQ_DISABLED = 0,
+	IDXD_WQ_ENABLED,
+};
+
+enum idxd_wq_flag {
+	WQ_FLAG_DEDICATED = 0,
+};
+
+enum idxd_wq_type {
+	IDXD_WQT_NONE = 0,
+	IDXD_WQT_KERNEL,
+	IDXD_WQT_USER,
+};
+
+struct idxd_cdev {
+	struct cdev cdev;
+	struct device *dev;
+	int minor;
+	struct wait_queue_head err_queue;
+};
+
+#define IDXD_ALLOCATED_BATCH_SIZE	128U
+#define WQ_NAME_SIZE   1024
+#define WQ_TYPE_SIZE   10
+
+enum idxd_op_type {
+	IDXD_OP_BLOCK = 0,
+	IDXD_OP_NONBLOCK = 1,
+};
+
+enum idxd_complete_type {
+	IDXD_COMPLETE_NORMAL = 0,
+	IDXD_COMPLETE_ABORT,
+};
+
+struct idxd_wq {
+	void __iomem *dportal;
+	struct device conf_dev;
+	struct idxd_cdev idxd_cdev;
+	struct idxd_device *idxd;
+	int id;
+	enum idxd_wq_type type;
+	struct idxd_group *group;
+	int client_count;
+	struct mutex wq_lock;	/* mutex for workqueue */
+	u32 size;
+	u32 threshold;
+	u32 priority;
+	enum idxd_wq_state state;
+	unsigned long flags;
+	union wqcfg wqcfg;
+	atomic_t dq_count;	/* dedicated queue flow control */
+	u32 vec_ptr;		/* interrupt steering */
+	struct dsa_hw_desc **hw_descs;
+	int num_descs;
+	struct dsa_completion_record *compls;
+	dma_addr_t compls_addr;
+	int compls_size;
+	struct idxd_desc **descs;
+	struct sbitmap sbmap;
+	struct dma_chan dma_chan;
+	struct percpu_rw_semaphore submit_lock;
+	wait_queue_head_t submit_waitq;
+	char name[WQ_NAME_SIZE + 1];
+};
+
+struct idxd_engine {
+	struct device conf_dev;
+	int id;
+	struct idxd_group *group;
+	struct idxd_device *idxd;
+};
+
+/* shadow registers */
+struct idxd_hw {
+	u32 version;
+	union gen_cap_reg gen_cap;
+	union wq_cap_reg wq_cap;
+	union group_cap_reg group_cap;
+	union engine_cap_reg engine_cap;
+	struct opcap opcap;
+};
+
+enum idxd_device_state {
+	IDXD_DEV_HALTED = -1,
+	IDXD_DEV_DISABLED = 0,
+	IDXD_DEV_CONF_READY,
+	IDXD_DEV_ENABLED,
+};
+
+enum idxd_device_flag {
+	IDXD_FLAG_CONFIGURABLE = 0,
+};
+
+struct idxd_device {
+	enum idxd_type type;
+	struct device conf_dev;
+	struct list_head list;
+	struct idxd_hw hw;
+	enum idxd_device_state state;
+	unsigned long flags;
+	int id;
+	int major;
+
+	struct pci_dev *pdev;
+	void __iomem *reg_base;
+
+	spinlock_t dev_lock;	/* spinlock for device */
+	struct idxd_group *groups;
+	struct idxd_wq *wqs;
+	struct idxd_engine *engines;
+
+	int num_groups;
+
+	u32 msix_perm_offset;
+	u32 wqcfg_offset;
+	u32 grpcfg_offset;
+	u32 perfmon_offset;
+
+	u64 max_xfer_bytes;
+	u32 max_batch_size;
+	int max_groups;
+	int max_engines;
+	int max_tokens;
+	int max_wqs;
+	int max_wq_size;
+	int token_limit;
+	int nr_tokens;		/* non-reserved tokens */
+
+	union sw_err_reg sw_err;
+
+	struct msix_entry *msix_entries;
+	int num_wq_irqs;
+	struct idxd_irq_entry *irq_entries;
+
+	struct dma_device dma_dev;
+};
+
+/* IDXD software descriptor */
+struct idxd_desc {
+	struct dsa_hw_desc *hw;
+	dma_addr_t desc_dma;
+	struct dsa_completion_record *completion;
+	dma_addr_t compl_dma;
+	struct dma_async_tx_descriptor txd;
+	struct llist_node llnode;
+	struct list_head list;
+	int id;
+	struct idxd_wq *wq;
+};
+
+#define confdev_to_idxd(dev) container_of(dev, struct idxd_device, conf_dev)
+#define confdev_to_wq(dev) container_of(dev, struct idxd_wq, conf_dev)
+
+extern struct bus_type dsa_bus_type;
+
+static inline bool wq_dedicated(struct idxd_wq *wq)
+{
+	return test_bit(WQ_FLAG_DEDICATED, &wq->flags);
+}
+
+enum idxd_portal_prot {
+	IDXD_PORTAL_UNLIMITED = 0,
+	IDXD_PORTAL_LIMITED,
+};
+
+static inline int idxd_get_wq_portal_offset(enum idxd_portal_prot prot)
+{
+	return prot * 0x1000;
+}
+
+static inline int idxd_get_wq_portal_full_offset(int wq_id,
+						 enum idxd_portal_prot prot)
+{
+	return ((wq_id * 4) << PAGE_SHIFT) + idxd_get_wq_portal_offset(prot);
+}
+
+static inline void idxd_set_type(struct idxd_device *idxd)
+{
+	struct pci_dev *pdev = idxd->pdev;
+
+	if (pdev->device == PCI_DEVICE_ID_INTEL_DSA_SPR0)
+		idxd->type = IDXD_TYPE_DSA;
+	else
+		idxd->type = IDXD_TYPE_UNKNOWN;
+}
+
+static inline void idxd_wq_get(struct idxd_wq *wq)
+{
+	wq->client_count++;
+}
+
+static inline void idxd_wq_put(struct idxd_wq *wq)
+{
+	wq->client_count--;
+}
+
+static inline int idxd_wq_refcount(struct idxd_wq *wq)
+{
+	return wq->client_count;
+};
+
+const char *idxd_get_dev_name(struct idxd_device *idxd);
+int idxd_register_bus_type(void);
+void idxd_unregister_bus_type(void);
+int idxd_setup_sysfs(struct idxd_device *idxd);
+void idxd_cleanup_sysfs(struct idxd_device *idxd);
+int idxd_register_driver(void);
+void idxd_unregister_driver(void);
+struct bus_type *idxd_get_bus_type(struct idxd_device *idxd);
+
+/* device interrupt control */
+irqreturn_t idxd_irq_handler(int vec, void *data);
+irqreturn_t idxd_misc_thread(int vec, void *data);
+irqreturn_t idxd_wq_thread(int irq, void *data);
+void idxd_mask_error_interrupts(struct idxd_device *idxd);
+void idxd_unmask_error_interrupts(struct idxd_device *idxd);
+void idxd_mask_msix_vectors(struct idxd_device *idxd);
+int idxd_mask_msix_vector(struct idxd_device *idxd, int vec_id);
+int idxd_unmask_msix_vector(struct idxd_device *idxd, int vec_id);
+
+/* device control */
+int idxd_device_enable(struct idxd_device *idxd);
+int idxd_device_disable(struct idxd_device *idxd);
+int idxd_device_reset(struct idxd_device *idxd);
+int __idxd_device_reset(struct idxd_device *idxd);
+void idxd_device_cleanup(struct idxd_device *idxd);
+int idxd_device_config(struct idxd_device *idxd);
+void idxd_device_wqs_clear_state(struct idxd_device *idxd);
+
+/* work queue control */
+int idxd_wq_alloc_resources(struct idxd_wq *wq);
+void idxd_wq_free_resources(struct idxd_wq *wq);
+int idxd_wq_enable(struct idxd_wq *wq);
+int idxd_wq_disable(struct idxd_wq *wq);
+int idxd_wq_map_portal(struct idxd_wq *wq);
+void idxd_wq_unmap_portal(struct idxd_wq *wq);
+
+/* submission */
+int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc);
+struct idxd_desc *idxd_alloc_desc(struct idxd_wq *wq, enum idxd_op_type optype);
+void idxd_free_desc(struct idxd_wq *wq, struct idxd_desc *desc);
+
+/* dmaengine */
+int idxd_register_dma_device(struct idxd_device *idxd);
+void idxd_unregister_dma_device(struct idxd_device *idxd);
+int idxd_register_dma_channel(struct idxd_wq *wq);
+void idxd_unregister_dma_channel(struct idxd_wq *wq);
+void idxd_parse_completion_status(u8 status, enum dmaengine_tx_result *res);
+void idxd_dma_complete_txd(struct idxd_desc *desc,
+			   enum idxd_complete_type comp_type);
+dma_cookie_t idxd_dma_tx_submit(struct dma_async_tx_descriptor *tx);
+
+/* cdev */
+int idxd_cdev_register(void);
+void idxd_cdev_remove(void);
+int idxd_cdev_get_major(struct idxd_device *idxd);
+int idxd_wq_add_cdev(struct idxd_wq *wq);
+void idxd_wq_del_cdev(struct idxd_wq *wq);
+
+#endif
diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c
new file mode 100644
index 000000000000..7778c05deb5d
--- /dev/null
+++ b/drivers/dma/idxd/init.c
@@ -0,0 +1,533 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2019 Intel Corporation. All rights rsvd. */
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/pci.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/workqueue.h>
+#include <linux/aer.h>
+#include <linux/fs.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
+#include <linux/device.h>
+#include <linux/idr.h>
+#include <uapi/linux/idxd.h>
+#include <linux/dmaengine.h>
+#include "../dmaengine.h"
+#include "registers.h"
+#include "idxd.h"
+
+MODULE_VERSION(IDXD_DRIVER_VERSION);
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Intel Corporation");
+
+#define DRV_NAME "idxd"
+
+static struct idr idxd_idrs[IDXD_TYPE_MAX];
+static struct mutex idxd_idr_lock;
+
+static struct pci_device_id idxd_pci_tbl[] = {
+	/* DSA ver 1.0 platforms */
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_DSA_SPR0) },
+	{ 0, }
+};
+MODULE_DEVICE_TABLE(pci, idxd_pci_tbl);
+
+static char *idxd_name[] = {
+	"dsa",
+};
+
+const char *idxd_get_dev_name(struct idxd_device *idxd)
+{
+	return idxd_name[idxd->type];
+}
+
+static int idxd_setup_interrupts(struct idxd_device *idxd)
+{
+	struct pci_dev *pdev = idxd->pdev;
+	struct device *dev = &pdev->dev;
+	struct msix_entry *msix;
+	struct idxd_irq_entry *irq_entry;
+	int i, msixcnt;
+	int rc = 0;
+
+	msixcnt = pci_msix_vec_count(pdev);
+	if (msixcnt < 0) {
+		dev_err(dev, "Not MSI-X interrupt capable.\n");
+		goto err_no_irq;
+	}
+
+	idxd->msix_entries = devm_kzalloc(dev, sizeof(struct msix_entry) *
+			msixcnt, GFP_KERNEL);
+	if (!idxd->msix_entries) {
+		rc = -ENOMEM;
+		goto err_no_irq;
+	}
+
+	for (i = 0; i < msixcnt; i++)
+		idxd->msix_entries[i].entry = i;
+
+	rc = pci_enable_msix_exact(pdev, idxd->msix_entries, msixcnt);
+	if (rc) {
+		dev_err(dev, "Failed enabling %d MSIX entries.\n", msixcnt);
+		goto err_no_irq;
+	}
+	dev_dbg(dev, "Enabled %d msix vectors\n", msixcnt);
+
+	/*
+	 * We implement 1 completion list per MSI-X entry except for
+	 * entry 0, which is for errors and others.
+	 */
+	idxd->irq_entries = devm_kcalloc(dev, msixcnt,
+					 sizeof(struct idxd_irq_entry),
+					 GFP_KERNEL);
+	if (!idxd->irq_entries) {
+		rc = -ENOMEM;
+		goto err_no_irq;
+	}
+
+	for (i = 0; i < msixcnt; i++) {
+		idxd->irq_entries[i].id = i;
+		idxd->irq_entries[i].idxd = idxd;
+	}
+
+	msix = &idxd->msix_entries[0];
+	irq_entry = &idxd->irq_entries[0];
+	rc = devm_request_threaded_irq(dev, msix->vector, idxd_irq_handler,
+				       idxd_misc_thread, 0, "idxd-misc",
+				       irq_entry);
+	if (rc < 0) {
+		dev_err(dev, "Failed to allocate misc interrupt.\n");
+		goto err_no_irq;
+	}
+
+	dev_dbg(dev, "Allocated idxd-misc handler on msix vector %d\n",
+		msix->vector);
+
+	/* first MSI-X entry is not for wq interrupts */
+	idxd->num_wq_irqs = msixcnt - 1;
+
+	for (i = 1; i < msixcnt; i++) {
+		msix = &idxd->msix_entries[i];
+		irq_entry = &idxd->irq_entries[i];
+
+		init_llist_head(&idxd->irq_entries[i].pending_llist);
+		INIT_LIST_HEAD(&idxd->irq_entries[i].work_list);
+		rc = devm_request_threaded_irq(dev, msix->vector,
+					       idxd_irq_handler,
+					       idxd_wq_thread, 0,
+					       "idxd-portal", irq_entry);
+		if (rc < 0) {
+			dev_err(dev, "Failed to allocate irq %d.\n",
+				msix->vector);
+			goto err_no_irq;
+		}
+		dev_dbg(dev, "Allocated idxd-msix %d for vector %d\n",
+			i, msix->vector);
+	}
+
+	idxd_unmask_error_interrupts(idxd);
+
+	return 0;
+
+ err_no_irq:
+	/* Disable error interrupt generation */
+	idxd_mask_error_interrupts(idxd);
+	pci_disable_msix(pdev);
+	dev_err(dev, "No usable interrupts\n");
+	return rc;
+}
+
+static void idxd_wqs_free_lock(struct idxd_device *idxd)
+{
+	int i;
+
+	for (i = 0; i < idxd->max_wqs; i++) {
+		struct idxd_wq *wq = &idxd->wqs[i];
+
+		percpu_free_rwsem(&wq->submit_lock);
+	}
+}
+
+static int idxd_setup_internals(struct idxd_device *idxd)
+{
+	struct device *dev = &idxd->pdev->dev;
+	int i;
+
+	idxd->groups = devm_kcalloc(dev, idxd->max_groups,
+				    sizeof(struct idxd_group), GFP_KERNEL);
+	if (!idxd->groups)
+		return -ENOMEM;
+
+	for (i = 0; i < idxd->max_groups; i++) {
+		idxd->groups[i].idxd = idxd;
+		idxd->groups[i].id = i;
+		idxd->groups[i].tc_a = -1;
+		idxd->groups[i].tc_b = -1;
+	}
+
+	idxd->wqs = devm_kcalloc(dev, idxd->max_wqs, sizeof(struct idxd_wq),
+				 GFP_KERNEL);
+	if (!idxd->wqs)
+		return -ENOMEM;
+
+	idxd->engines = devm_kcalloc(dev, idxd->max_engines,
+				     sizeof(struct idxd_engine), GFP_KERNEL);
+	if (!idxd->engines)
+		return -ENOMEM;
+
+	for (i = 0; i < idxd->max_wqs; i++) {
+		struct idxd_wq *wq = &idxd->wqs[i];
+		int rc;
+
+		wq->id = i;
+		wq->idxd = idxd;
+		mutex_init(&wq->wq_lock);
+		atomic_set(&wq->dq_count, 0);
+		init_waitqueue_head(&wq->submit_waitq);
+		wq->idxd_cdev.minor = -1;
+		rc = percpu_init_rwsem(&wq->submit_lock);
+		if (rc < 0) {
+			idxd_wqs_free_lock(idxd);
+			return rc;
+		}
+	}
+
+	for (i = 0; i < idxd->max_engines; i++) {
+		idxd->engines[i].idxd = idxd;
+		idxd->engines[i].id = i;
+	}
+
+	return 0;
+}
+
+static void idxd_read_table_offsets(struct idxd_device *idxd)
+{
+	union offsets_reg offsets;
+	struct device *dev = &idxd->pdev->dev;
+
+	offsets.bits[0] = ioread64(idxd->reg_base + IDXD_TABLE_OFFSET);
+	offsets.bits[1] = ioread64(idxd->reg_base + IDXD_TABLE_OFFSET
+			+ sizeof(u64));
+	idxd->grpcfg_offset = offsets.grpcfg * 0x100;
+	dev_dbg(dev, "IDXD Group Config Offset: %#x\n", idxd->grpcfg_offset);
+	idxd->wqcfg_offset = offsets.wqcfg * 0x100;
+	dev_dbg(dev, "IDXD Work Queue Config Offset: %#x\n",
+		idxd->wqcfg_offset);
+	idxd->msix_perm_offset = offsets.msix_perm * 0x100;
+	dev_dbg(dev, "IDXD MSIX Permission Offset: %#x\n",
+		idxd->msix_perm_offset);
+	idxd->perfmon_offset = offsets.perfmon * 0x100;
+	dev_dbg(dev, "IDXD Perfmon Offset: %#x\n", idxd->perfmon_offset);
+}
+
+static void idxd_read_caps(struct idxd_device *idxd)
+{
+	struct device *dev = &idxd->pdev->dev;
+	int i;
+
+	/* reading generic capabilities */
+	idxd->hw.gen_cap.bits = ioread64(idxd->reg_base + IDXD_GENCAP_OFFSET);
+	dev_dbg(dev, "gen_cap: %#llx\n", idxd->hw.gen_cap.bits);
+	idxd->max_xfer_bytes = 1ULL << idxd->hw.gen_cap.max_xfer_shift;
+	dev_dbg(dev, "max xfer size: %llu bytes\n", idxd->max_xfer_bytes);
+	idxd->max_batch_size = 1U << idxd->hw.gen_cap.max_batch_shift;
+	dev_dbg(dev, "max batch size: %u\n", idxd->max_batch_size);
+	if (idxd->hw.gen_cap.config_en)
+		set_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags);
+
+	/* reading group capabilities */
+	idxd->hw.group_cap.bits =
+		ioread64(idxd->reg_base + IDXD_GRPCAP_OFFSET);
+	dev_dbg(dev, "group_cap: %#llx\n", idxd->hw.group_cap.bits);
+	idxd->max_groups = idxd->hw.group_cap.num_groups;
+	dev_dbg(dev, "max groups: %u\n", idxd->max_groups);
+	idxd->max_tokens = idxd->hw.group_cap.total_tokens;
+	dev_dbg(dev, "max tokens: %u\n", idxd->max_tokens);
+	idxd->nr_tokens = idxd->max_tokens;
+
+	/* read engine capabilities */
+	idxd->hw.engine_cap.bits =
+		ioread64(idxd->reg_base + IDXD_ENGCAP_OFFSET);
+	dev_dbg(dev, "engine_cap: %#llx\n", idxd->hw.engine_cap.bits);
+	idxd->max_engines = idxd->hw.engine_cap.num_engines;
+	dev_dbg(dev, "max engines: %u\n", idxd->max_engines);
+
+	/* read workqueue capabilities */
+	idxd->hw.wq_cap.bits = ioread64(idxd->reg_base + IDXD_WQCAP_OFFSET);
+	dev_dbg(dev, "wq_cap: %#llx\n", idxd->hw.wq_cap.bits);
+	idxd->max_wq_size = idxd->hw.wq_cap.total_wq_size;
+	dev_dbg(dev, "total workqueue size: %u\n", idxd->max_wq_size);
+	idxd->max_wqs = idxd->hw.wq_cap.num_wqs;
+	dev_dbg(dev, "max workqueues: %u\n", idxd->max_wqs);
+
+	/* reading operation capabilities */
+	for (i = 0; i < 4; i++) {
+		idxd->hw.opcap.bits[i] = ioread64(idxd->reg_base +
+				IDXD_OPCAP_OFFSET + i * sizeof(u64));
+		dev_dbg(dev, "opcap[%d]: %#llx\n", i, idxd->hw.opcap.bits[i]);
+	}
+}
+
+static struct idxd_device *idxd_alloc(struct pci_dev *pdev,
+				      void __iomem * const *iomap)
+{
+	struct device *dev = &pdev->dev;
+	struct idxd_device *idxd;
+
+	idxd = devm_kzalloc(dev, sizeof(struct idxd_device), GFP_KERNEL);
+	if (!idxd)
+		return NULL;
+
+	idxd->pdev = pdev;
+	idxd->reg_base = iomap[IDXD_MMIO_BAR];
+	spin_lock_init(&idxd->dev_lock);
+
+	return idxd;
+}
+
+static int idxd_probe(struct idxd_device *idxd)
+{
+	struct pci_dev *pdev = idxd->pdev;
+	struct device *dev = &pdev->dev;
+	int rc;
+
+	dev_dbg(dev, "%s entered and resetting device\n", __func__);
+	rc = idxd_device_reset(idxd);
+	if (rc < 0)
+		return rc;
+	dev_dbg(dev, "IDXD reset complete\n");
+
+	idxd_read_caps(idxd);
+	idxd_read_table_offsets(idxd);
+
+	rc = idxd_setup_internals(idxd);
+	if (rc)
+		goto err_setup;
+
+	rc = idxd_setup_interrupts(idxd);
+	if (rc)
+		goto err_setup;
+
+	dev_dbg(dev, "IDXD interrupt setup complete.\n");
+
+	mutex_lock(&idxd_idr_lock);
+	idxd->id = idr_alloc(&idxd_idrs[idxd->type], idxd, 0, 0, GFP_KERNEL);
+	mutex_unlock(&idxd_idr_lock);
+	if (idxd->id < 0) {
+		rc = -ENOMEM;
+		goto err_idr_fail;
+	}
+
+	idxd->major = idxd_cdev_get_major(idxd);
+
+	dev_dbg(dev, "IDXD device %d probed successfully\n", idxd->id);
+	return 0;
+
+ err_idr_fail:
+	idxd_mask_error_interrupts(idxd);
+	idxd_mask_msix_vectors(idxd);
+ err_setup:
+	return rc;
+}
+
+static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	void __iomem * const *iomap;
+	struct device *dev = &pdev->dev;
+	struct idxd_device *idxd;
+	int rc;
+	unsigned int mask;
+
+	rc = pcim_enable_device(pdev);
+	if (rc)
+		return rc;
+
+	dev_dbg(dev, "Mapping BARs\n");
+	mask = (1 << IDXD_MMIO_BAR);
+	rc = pcim_iomap_regions(pdev, mask, DRV_NAME);
+	if (rc)
+		return rc;
+
+	iomap = pcim_iomap_table(pdev);
+	if (!iomap)
+		return -ENOMEM;
+
+	dev_dbg(dev, "Set DMA masks\n");
+	rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
+	if (rc)
+		rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+	if (rc)
+		return rc;
+
+	rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
+	if (rc)
+		rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
+	if (rc)
+		return rc;
+
+	dev_dbg(dev, "Alloc IDXD context\n");
+	idxd = idxd_alloc(pdev, iomap);
+	if (!idxd)
+		return -ENOMEM;
+
+	idxd_set_type(idxd);
+
+	dev_dbg(dev, "Set PCI master\n");
+	pci_set_master(pdev);
+	pci_set_drvdata(pdev, idxd);
+
+	idxd->hw.version = ioread32(idxd->reg_base + IDXD_VER_OFFSET);
+	rc = idxd_probe(idxd);
+	if (rc) {
+		dev_err(dev, "Intel(R) IDXD DMA Engine init failed\n");
+		return -ENODEV;
+	}
+
+	rc = idxd_setup_sysfs(idxd);
+	if (rc) {
+		dev_err(dev, "IDXD sysfs setup failed\n");
+		return -ENODEV;
+	}
+
+	idxd->state = IDXD_DEV_CONF_READY;
+
+	dev_info(&pdev->dev, "Intel(R) Accelerator Device (v%x)\n",
+		 idxd->hw.version);
+
+	return 0;
+}
+
+static void idxd_flush_pending_llist(struct idxd_irq_entry *ie)
+{
+	struct idxd_desc *desc, *itr;
+	struct llist_node *head;
+
+	head = llist_del_all(&ie->pending_llist);
+	if (!head)
+		return;
+
+	llist_for_each_entry_safe(desc, itr, head, llnode) {
+		idxd_dma_complete_txd(desc, IDXD_COMPLETE_ABORT);
+		idxd_free_desc(desc->wq, desc);
+	}
+}
+
+static void idxd_flush_work_list(struct idxd_irq_entry *ie)
+{
+	struct idxd_desc *desc, *iter;
+
+	list_for_each_entry_safe(desc, iter, &ie->work_list, list) {
+		list_del(&desc->list);
+		idxd_dma_complete_txd(desc, IDXD_COMPLETE_ABORT);
+		idxd_free_desc(desc->wq, desc);
+	}
+}
+
+static void idxd_shutdown(struct pci_dev *pdev)
+{
+	struct idxd_device *idxd = pci_get_drvdata(pdev);
+	int rc, i;
+	struct idxd_irq_entry *irq_entry;
+	int msixcnt = pci_msix_vec_count(pdev);
+	unsigned long flags;
+
+	spin_lock_irqsave(&idxd->dev_lock, flags);
+	rc = idxd_device_disable(idxd);
+	spin_unlock_irqrestore(&idxd->dev_lock, flags);
+	if (rc)
+		dev_err(&pdev->dev, "Disabling device failed\n");
+
+	dev_dbg(&pdev->dev, "%s called\n", __func__);
+	idxd_mask_msix_vectors(idxd);
+	idxd_mask_error_interrupts(idxd);
+
+	for (i = 0; i < msixcnt; i++) {
+		irq_entry = &idxd->irq_entries[i];
+		synchronize_irq(idxd->msix_entries[i].vector);
+		if (i == 0)
+			continue;
+		idxd_flush_pending_llist(irq_entry);
+		idxd_flush_work_list(irq_entry);
+	}
+}
+
+static void idxd_remove(struct pci_dev *pdev)
+{
+	struct idxd_device *idxd = pci_get_drvdata(pdev);
+
+	dev_dbg(&pdev->dev, "%s called\n", __func__);
+	idxd_cleanup_sysfs(idxd);
+	idxd_shutdown(pdev);
+	idxd_wqs_free_lock(idxd);
+	mutex_lock(&idxd_idr_lock);
+	idr_remove(&idxd_idrs[idxd->type], idxd->id);
+	mutex_unlock(&idxd_idr_lock);
+}
+
+static struct pci_driver idxd_pci_driver = {
+	.name		= DRV_NAME,
+	.id_table	= idxd_pci_tbl,
+	.probe		= idxd_pci_probe,
+	.remove		= idxd_remove,
+	.shutdown	= idxd_shutdown,
+};
+
+static int __init idxd_init_module(void)
+{
+	int err, i;
+
+	/*
+	 * If the CPU does not support write512, there's no point in
+	 * enumerating the device. We can not utilize it.
+	 */
+	if (!boot_cpu_has(X86_FEATURE_MOVDIR64B)) {
+		pr_warn("idxd driver failed to load without MOVDIR64B.\n");
+		return -ENODEV;
+	}
+
+	pr_info("%s: Intel(R) Accelerator Devices Driver %s\n",
+		DRV_NAME, IDXD_DRIVER_VERSION);
+
+	mutex_init(&idxd_idr_lock);
+	for (i = 0; i < IDXD_TYPE_MAX; i++)
+		idr_init(&idxd_idrs[i]);
+
+	err = idxd_register_bus_type();
+	if (err < 0)
+		return err;
+
+	err = idxd_register_driver();
+	if (err < 0)
+		goto err_idxd_driver_register;
+
+	err = idxd_cdev_register();
+	if (err)
+		goto err_cdev_register;
+
+	err = pci_register_driver(&idxd_pci_driver);
+	if (err)
+		goto err_pci_register;
+
+	return 0;
+
+err_pci_register:
+	idxd_cdev_remove();
+err_cdev_register:
+	idxd_unregister_driver();
+err_idxd_driver_register:
+	idxd_unregister_bus_type();
+	return err;
+}
+module_init(idxd_init_module);
+
+static void __exit idxd_exit_module(void)
+{
+	pci_unregister_driver(&idxd_pci_driver);
+	idxd_cdev_remove();
+	idxd_unregister_bus_type();
+}
+module_exit(idxd_exit_module);
diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c
new file mode 100644
index 000000000000..d6fcd2e60103
--- /dev/null
+++ b/drivers/dma/idxd/irq.c
@@ -0,0 +1,261 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2019 Intel Corporation. All rights rsvd. */
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
+#include <linux/dmaengine.h>
+#include <uapi/linux/idxd.h>
+#include "../dmaengine.h"
+#include "idxd.h"
+#include "registers.h"
+
+void idxd_device_wqs_clear_state(struct idxd_device *idxd)
+{
+	int i;
+
+	lockdep_assert_held(&idxd->dev_lock);
+	for (i = 0; i < idxd->max_wqs; i++) {
+		struct idxd_wq *wq = &idxd->wqs[i];
+
+		wq->state = IDXD_WQ_DISABLED;
+	}
+}
+
+static int idxd_restart(struct idxd_device *idxd)
+{
+	int i, rc;
+
+	lockdep_assert_held(&idxd->dev_lock);
+
+	rc = __idxd_device_reset(idxd);
+	if (rc < 0)
+		goto out;
+
+	rc = idxd_device_config(idxd);
+	if (rc < 0)
+		goto out;
+
+	rc = idxd_device_enable(idxd);
+	if (rc < 0)
+		goto out;
+
+	for (i = 0; i < idxd->max_wqs; i++) {
+		struct idxd_wq *wq = &idxd->wqs[i];
+
+		if (wq->state == IDXD_WQ_ENABLED) {
+			rc = idxd_wq_enable(wq);
+			if (rc < 0) {
+				dev_warn(&idxd->pdev->dev,
+					 "Unable to re-enable wq %s\n",
+					 dev_name(&wq->conf_dev));
+			}
+		}
+	}
+
+	return 0;
+
+ out:
+	idxd_device_wqs_clear_state(idxd);
+	idxd->state = IDXD_DEV_HALTED;
+	return rc;
+}
+
+irqreturn_t idxd_irq_handler(int vec, void *data)
+{
+	struct idxd_irq_entry *irq_entry = data;
+	struct idxd_device *idxd = irq_entry->idxd;
+
+	idxd_mask_msix_vector(idxd, irq_entry->id);
+	return IRQ_WAKE_THREAD;
+}
+
+irqreturn_t idxd_misc_thread(int vec, void *data)
+{
+	struct idxd_irq_entry *irq_entry = data;
+	struct idxd_device *idxd = irq_entry->idxd;
+	struct device *dev = &idxd->pdev->dev;
+	union gensts_reg gensts;
+	u32 cause, val = 0;
+	int i, rc;
+	bool err = false;
+
+	cause = ioread32(idxd->reg_base + IDXD_INTCAUSE_OFFSET);
+
+	if (cause & IDXD_INTC_ERR) {
+		spin_lock_bh(&idxd->dev_lock);
+		for (i = 0; i < 4; i++)
+			idxd->sw_err.bits[i] = ioread64(idxd->reg_base +
+					IDXD_SWERR_OFFSET + i * sizeof(u64));
+		iowrite64(IDXD_SWERR_ACK, idxd->reg_base + IDXD_SWERR_OFFSET);
+
+		if (idxd->sw_err.valid && idxd->sw_err.wq_idx_valid) {
+			int id = idxd->sw_err.wq_idx;
+			struct idxd_wq *wq = &idxd->wqs[id];
+
+			if (wq->type == IDXD_WQT_USER)
+				wake_up_interruptible(&wq->idxd_cdev.err_queue);
+		} else {
+			int i;
+
+			for (i = 0; i < idxd->max_wqs; i++) {
+				struct idxd_wq *wq = &idxd->wqs[i];
+
+				if (wq->type == IDXD_WQT_USER)
+					wake_up_interruptible(&wq->idxd_cdev.err_queue);
+			}
+		}
+
+		spin_unlock_bh(&idxd->dev_lock);
+		val |= IDXD_INTC_ERR;
+
+		for (i = 0; i < 4; i++)
+			dev_warn(dev, "err[%d]: %#16.16llx\n",
+				 i, idxd->sw_err.bits[i]);
+		err = true;
+	}
+
+	if (cause & IDXD_INTC_CMD) {
+		/* Driver does use command interrupts */
+		val |= IDXD_INTC_CMD;
+	}
+
+	if (cause & IDXD_INTC_OCCUPY) {
+		/* Driver does not utilize occupancy interrupt */
+		val |= IDXD_INTC_OCCUPY;
+	}
+
+	if (cause & IDXD_INTC_PERFMON_OVFL) {
+		/*
+		 * Driver does not utilize perfmon counter overflow interrupt
+		 * yet.
+		 */
+		val |= IDXD_INTC_PERFMON_OVFL;
+	}
+
+	val ^= cause;
+	if (val)
+		dev_warn_once(dev, "Unexpected interrupt cause bits set: %#x\n",
+			      val);
+
+	iowrite32(cause, idxd->reg_base + IDXD_INTCAUSE_OFFSET);
+	if (!err)
+		return IRQ_HANDLED;
+
+	gensts.bits = ioread32(idxd->reg_base + IDXD_GENSTATS_OFFSET);
+	if (gensts.state == IDXD_DEVICE_STATE_HALT) {
+		spin_lock_bh(&idxd->dev_lock);
+		if (gensts.reset_type == IDXD_DEVICE_RESET_SOFTWARE) {
+			rc = idxd_restart(idxd);
+			if (rc < 0)
+				dev_err(&idxd->pdev->dev,
+					"idxd restart failed, device halt.");
+		} else {
+			idxd_device_wqs_clear_state(idxd);
+			idxd->state = IDXD_DEV_HALTED;
+			dev_err(&idxd->pdev->dev,
+				"idxd halted, need %s.\n",
+				gensts.reset_type == IDXD_DEVICE_RESET_FLR ?
+				"FLR" : "system reset");
+		}
+		spin_unlock_bh(&idxd->dev_lock);
+	}
+
+	idxd_unmask_msix_vector(idxd, irq_entry->id);
+	return IRQ_HANDLED;
+}
+
+static int irq_process_pending_llist(struct idxd_irq_entry *irq_entry,
+				     int *processed)
+{
+	struct idxd_desc *desc, *t;
+	struct llist_node *head;
+	int queued = 0;
+
+	head = llist_del_all(&irq_entry->pending_llist);
+	if (!head)
+		return 0;
+
+	llist_for_each_entry_safe(desc, t, head, llnode) {
+		if (desc->completion->status) {
+			idxd_dma_complete_txd(desc, IDXD_COMPLETE_NORMAL);
+			idxd_free_desc(desc->wq, desc);
+			(*processed)++;
+		} else {
+			list_add_tail(&desc->list, &irq_entry->work_list);
+			queued++;
+		}
+	}
+
+	return queued;
+}
+
+static int irq_process_work_list(struct idxd_irq_entry *irq_entry,
+				 int *processed)
+{
+	struct list_head *node, *next;
+	int queued = 0;
+
+	if (list_empty(&irq_entry->work_list))
+		return 0;
+
+	list_for_each_safe(node, next, &irq_entry->work_list) {
+		struct idxd_desc *desc =
+			container_of(node, struct idxd_desc, list);
+
+		if (desc->completion->status) {
+			list_del(&desc->list);
+			/* process and callback */
+			idxd_dma_complete_txd(desc, IDXD_COMPLETE_NORMAL);
+			idxd_free_desc(desc->wq, desc);
+			(*processed)++;
+		} else {
+			queued++;
+		}
+	}
+
+	return queued;
+}
+
+irqreturn_t idxd_wq_thread(int irq, void *data)
+{
+	struct idxd_irq_entry *irq_entry = data;
+	int rc, processed = 0, retry = 0;
+
+	/*
+	 * There are two lists we are processing. The pending_llist is where
+	 * submmiter adds all the submitted descriptor after sending it to
+	 * the workqueue. It's a lockless singly linked list. The work_list
+	 * is the common linux double linked list. We are in a scenario of
+	 * multiple producers and a single consumer. The producers are all
+	 * the kernel submitters of descriptors, and the consumer is the
+	 * kernel irq handler thread for the msix vector when using threaded
+	 * irq. To work with the restrictions of llist to remain lockless,
+	 * we are doing the following steps:
+	 * 1. Iterate through the work_list and process any completed
+	 *    descriptor. Delete the completed entries during iteration.
+	 * 2. llist_del_all() from the pending list.
+	 * 3. Iterate through the llist that was deleted from the pending list
+	 *    and process the completed entries.
+	 * 4. If the entry is still waiting on hardware, list_add_tail() to
+	 *    the work_list.
+	 * 5. Repeat until no more descriptors.
+	 */
+	do {
+		rc = irq_process_work_list(irq_entry, &processed);
+		if (rc != 0) {
+			retry++;
+			continue;
+		}
+
+		rc = irq_process_pending_llist(irq_entry, &processed);
+	} while (rc != 0 && retry != 10);
+
+	idxd_unmask_msix_vector(irq_entry->idxd, irq_entry->id);
+
+	if (processed == 0)
+		return IRQ_NONE;
+
+	return IRQ_HANDLED;
+}
diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h
new file mode 100644
index 000000000000..a39e7ae6b3d9
--- /dev/null
+++ b/drivers/dma/idxd/registers.h
@@ -0,0 +1,336 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2019 Intel Corporation. All rights rsvd. */
+#ifndef _IDXD_REGISTERS_H_
+#define _IDXD_REGISTERS_H_
+
+/* PCI Config */
+#define PCI_DEVICE_ID_INTEL_DSA_SPR0	0x0b25
+
+#define IDXD_MMIO_BAR		0
+#define IDXD_WQ_BAR		2
+#define IDXD_PORTAL_SIZE	0x4000
+
+/* MMIO Device BAR0 Registers */
+#define IDXD_VER_OFFSET			0x00
+#define IDXD_VER_MAJOR_MASK		0xf0
+#define IDXD_VER_MINOR_MASK		0x0f
+#define GET_IDXD_VER_MAJOR(x)		(((x) & IDXD_VER_MAJOR_MASK) >> 4)
+#define GET_IDXD_VER_MINOR(x)		((x) & IDXD_VER_MINOR_MASK)
+
+union gen_cap_reg {
+	struct {
+		u64 block_on_fault:1;
+		u64 overlap_copy:1;
+		u64 cache_control_mem:1;
+		u64 cache_control_cache:1;
+		u64 rsvd:3;
+		u64 int_handle_req:1;
+		u64 dest_readback:1;
+		u64 drain_readback:1;
+		u64 rsvd2:6;
+		u64 max_xfer_shift:5;
+		u64 max_batch_shift:4;
+		u64 max_ims_mult:6;
+		u64 config_en:1;
+		u64 max_descs_per_engine:8;
+		u64 rsvd3:24;
+	};
+	u64 bits;
+} __packed;
+#define IDXD_GENCAP_OFFSET		0x10
+
+union wq_cap_reg {
+	struct {
+		u64 total_wq_size:16;
+		u64 num_wqs:8;
+		u64 rsvd:24;
+		u64 shared_mode:1;
+		u64 dedicated_mode:1;
+		u64 rsvd2:1;
+		u64 priority:1;
+		u64 occupancy:1;
+		u64 occupancy_int:1;
+		u64 rsvd3:10;
+	};
+	u64 bits;
+} __packed;
+#define IDXD_WQCAP_OFFSET		0x20
+
+union group_cap_reg {
+	struct {
+		u64 num_groups:8;
+		u64 total_tokens:8;
+		u64 token_en:1;
+		u64 token_limit:1;
+		u64 rsvd:46;
+	};
+	u64 bits;
+} __packed;
+#define IDXD_GRPCAP_OFFSET		0x30
+
+union engine_cap_reg {
+	struct {
+		u64 num_engines:8;
+		u64 rsvd:56;
+	};
+	u64 bits;
+} __packed;
+
+#define IDXD_ENGCAP_OFFSET		0x38
+
+#define IDXD_OPCAP_NOOP			0x0001
+#define IDXD_OPCAP_BATCH			0x0002
+#define IDXD_OPCAP_MEMMOVE		0x0008
+struct opcap {
+	u64 bits[4];
+};
+
+#define IDXD_OPCAP_OFFSET		0x40
+
+#define IDXD_TABLE_OFFSET		0x60
+union offsets_reg {
+	struct {
+		u64 grpcfg:16;
+		u64 wqcfg:16;
+		u64 msix_perm:16;
+		u64 ims:16;
+		u64 perfmon:16;
+		u64 rsvd:48;
+	};
+	u64 bits[2];
+} __packed;
+
+#define IDXD_GENCFG_OFFSET		0x80
+union gencfg_reg {
+	struct {
+		u32 token_limit:8;
+		u32 rsvd:4;
+		u32 user_int_en:1;
+		u32 rsvd2:19;
+	};
+	u32 bits;
+} __packed;
+
+#define IDXD_GENCTRL_OFFSET		0x88
+union genctrl_reg {
+	struct {
+		u32 softerr_int_en:1;
+		u32 rsvd:31;
+	};
+	u32 bits;
+} __packed;
+
+#define IDXD_GENSTATS_OFFSET		0x90
+union gensts_reg {
+	struct {
+		u32 state:2;
+		u32 reset_type:2;
+		u32 rsvd:28;
+	};
+	u32 bits;
+} __packed;
+
+enum idxd_device_status_state {
+	IDXD_DEVICE_STATE_DISABLED = 0,
+	IDXD_DEVICE_STATE_ENABLED,
+	IDXD_DEVICE_STATE_DRAIN,
+	IDXD_DEVICE_STATE_HALT,
+};
+
+enum idxd_device_reset_type {
+	IDXD_DEVICE_RESET_SOFTWARE = 0,
+	IDXD_DEVICE_RESET_FLR,
+	IDXD_DEVICE_RESET_WARM,
+	IDXD_DEVICE_RESET_COLD,
+};
+
+#define IDXD_INTCAUSE_OFFSET		0x98
+#define IDXD_INTC_ERR			0x01
+#define IDXD_INTC_CMD			0x02
+#define IDXD_INTC_OCCUPY			0x04
+#define IDXD_INTC_PERFMON_OVFL		0x08
+
+#define IDXD_CMD_OFFSET			0xa0
+union idxd_command_reg {
+	struct {
+		u32 operand:20;
+		u32 cmd:5;
+		u32 rsvd:6;
+		u32 int_req:1;
+	};
+	u32 bits;
+} __packed;
+
+enum idxd_cmd {
+	IDXD_CMD_ENABLE_DEVICE = 1,
+	IDXD_CMD_DISABLE_DEVICE,
+	IDXD_CMD_DRAIN_ALL,
+	IDXD_CMD_ABORT_ALL,
+	IDXD_CMD_RESET_DEVICE,
+	IDXD_CMD_ENABLE_WQ,
+	IDXD_CMD_DISABLE_WQ,
+	IDXD_CMD_DRAIN_WQ,
+	IDXD_CMD_ABORT_WQ,
+	IDXD_CMD_RESET_WQ,
+	IDXD_CMD_DRAIN_PASID,
+	IDXD_CMD_ABORT_PASID,
+	IDXD_CMD_REQUEST_INT_HANDLE,
+};
+
+#define IDXD_CMDSTS_OFFSET		0xa8
+union cmdsts_reg {
+	struct {
+		u8 err;
+		u16 result;
+		u8 rsvd:7;
+		u8 active:1;
+	};
+	u32 bits;
+} __packed;
+#define IDXD_CMDSTS_ACTIVE		0x80000000
+
+enum idxd_cmdsts_err {
+	IDXD_CMDSTS_SUCCESS = 0,
+	IDXD_CMDSTS_INVAL_CMD,
+	IDXD_CMDSTS_INVAL_WQIDX,
+	IDXD_CMDSTS_HW_ERR,
+	/* enable device errors */
+	IDXD_CMDSTS_ERR_DEV_ENABLED = 0x10,
+	IDXD_CMDSTS_ERR_CONFIG,
+	IDXD_CMDSTS_ERR_BUSMASTER_EN,
+	IDXD_CMDSTS_ERR_PASID_INVAL,
+	IDXD_CMDSTS_ERR_WQ_SIZE_ERANGE,
+	IDXD_CMDSTS_ERR_GRP_CONFIG,
+	IDXD_CMDSTS_ERR_GRP_CONFIG2,
+	IDXD_CMDSTS_ERR_GRP_CONFIG3,
+	IDXD_CMDSTS_ERR_GRP_CONFIG4,
+	/* enable wq errors */
+	IDXD_CMDSTS_ERR_DEV_NOTEN = 0x20,
+	IDXD_CMDSTS_ERR_WQ_ENABLED,
+	IDXD_CMDSTS_ERR_WQ_SIZE,
+	IDXD_CMDSTS_ERR_WQ_PRIOR,
+	IDXD_CMDSTS_ERR_WQ_MODE,
+	IDXD_CMDSTS_ERR_BOF_EN,
+	IDXD_CMDSTS_ERR_PASID_EN,
+	IDXD_CMDSTS_ERR_MAX_BATCH_SIZE,
+	IDXD_CMDSTS_ERR_MAX_XFER_SIZE,
+	/* disable device errors */
+	IDXD_CMDSTS_ERR_DIS_DEV_EN = 0x31,
+	/* disable WQ, drain WQ, abort WQ, reset WQ */
+	IDXD_CMDSTS_ERR_DEV_NOT_EN,
+	/* request interrupt handle */
+	IDXD_CMDSTS_ERR_INVAL_INT_IDX = 0x41,
+	IDXD_CMDSTS_ERR_NO_HANDLE,
+};
+
+#define IDXD_SWERR_OFFSET		0xc0
+#define IDXD_SWERR_VALID		0x00000001
+#define IDXD_SWERR_OVERFLOW		0x00000002
+#define IDXD_SWERR_ACK			(IDXD_SWERR_VALID | IDXD_SWERR_OVERFLOW)
+union sw_err_reg {
+	struct {
+		u64 valid:1;
+		u64 overflow:1;
+		u64 desc_valid:1;
+		u64 wq_idx_valid:1;
+		u64 batch:1;
+		u64 fault_rw:1;
+		u64 priv:1;
+		u64 rsvd:1;
+		u64 error:8;
+		u64 wq_idx:8;
+		u64 rsvd2:8;
+		u64 operation:8;
+		u64 pasid:20;
+		u64 rsvd3:4;
+
+		u64 batch_idx:16;
+		u64 rsvd4:16;
+		u64 invalid_flags:32;
+
+		u64 fault_addr;
+
+		u64 rsvd5;
+	};
+	u64 bits[4];
+} __packed;
+
+union msix_perm {
+	struct {
+		u32 rsvd:2;
+		u32 ignore:1;
+		u32 pasid_en:1;
+		u32 rsvd2:8;
+		u32 pasid:20;
+	};
+	u32 bits;
+} __packed;
+
+union group_flags {
+	struct {
+		u32 tc_a:3;
+		u32 tc_b:3;
+		u32 rsvd:1;
+		u32 use_token_limit:1;
+		u32 tokens_reserved:8;
+		u32 rsvd2:4;
+		u32 tokens_allowed:8;
+		u32 rsvd3:4;
+	};
+	u32 bits;
+} __packed;
+
+struct grpcfg {
+	u64 wqs[4];
+	u64 engines;
+	union group_flags flags;
+} __packed;
+
+union wqcfg {
+	struct {
+		/* bytes 0-3 */
+		u16 wq_size;
+		u16 rsvd;
+
+		/* bytes 4-7 */
+		u16 wq_thresh;
+		u16 rsvd1;
+
+		/* bytes 8-11 */
+		u32 mode:1;	/* shared or dedicated */
+		u32 bof:1;	/* block on fault */
+		u32 rsvd2:2;
+		u32 priority:4;
+		u32 pasid:20;
+		u32 pasid_en:1;
+		u32 priv:1;
+		u32 rsvd3:2;
+
+		/* bytes 12-15 */
+		u32 max_xfer_shift:5;
+		u32 max_batch_shift:4;
+		u32 rsvd4:23;
+
+		/* bytes 16-19 */
+		u16 occupancy_inth;
+		u16 occupancy_table_sel:1;
+		u16 rsvd5:15;
+
+		/* bytes 20-23 */
+		u16 occupancy_limit;
+		u16 occupancy_int_en:1;
+		u16 rsvd6:15;
+
+		/* bytes 24-27 */
+		u16 occupancy;
+		u16 occupancy_int:1;
+		u16 rsvd7:12;
+		u16 mode_support:1;
+		u16 wq_state:2;
+
+		/* bytes 28-31 */
+		u32 rsvd8;
+	};
+	u32 bits[8];
+} __packed;
+#endif
diff --git a/drivers/dma/idxd/submit.c b/drivers/dma/idxd/submit.c
new file mode 100644
index 000000000000..45a0c5869a0a
--- /dev/null
+++ b/drivers/dma/idxd/submit.c
@@ -0,0 +1,95 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2019 Intel Corporation. All rights rsvd. */
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <uapi/linux/idxd.h>
+#include "idxd.h"
+#include "registers.h"
+
+struct idxd_desc *idxd_alloc_desc(struct idxd_wq *wq, enum idxd_op_type optype)
+{
+	struct idxd_desc *desc;
+	int idx;
+	struct idxd_device *idxd = wq->idxd;
+
+	if (idxd->state != IDXD_DEV_ENABLED)
+		return ERR_PTR(-EIO);
+
+	if (optype == IDXD_OP_BLOCK)
+		percpu_down_read(&wq->submit_lock);
+	else if (!percpu_down_read_trylock(&wq->submit_lock))
+		return ERR_PTR(-EBUSY);
+
+	if (!atomic_add_unless(&wq->dq_count, 1, wq->size)) {
+		int rc;
+
+		if (optype == IDXD_OP_NONBLOCK) {
+			percpu_up_read(&wq->submit_lock);
+			return ERR_PTR(-EAGAIN);
+		}
+
+		percpu_up_read(&wq->submit_lock);
+		percpu_down_write(&wq->submit_lock);
+		rc = wait_event_interruptible(wq->submit_waitq,
+					      atomic_add_unless(&wq->dq_count,
+								1, wq->size) ||
+					       idxd->state != IDXD_DEV_ENABLED);
+		percpu_up_write(&wq->submit_lock);
+		if (rc < 0)
+			return ERR_PTR(-EINTR);
+		if (idxd->state != IDXD_DEV_ENABLED)
+			return ERR_PTR(-EIO);
+	} else {
+		percpu_up_read(&wq->submit_lock);
+	}
+
+	idx = sbitmap_get(&wq->sbmap, 0, false);
+	if (idx < 0) {
+		atomic_dec(&wq->dq_count);
+		return ERR_PTR(-EAGAIN);
+	}
+
+	desc = wq->descs[idx];
+	memset(desc->hw, 0, sizeof(struct dsa_hw_desc));
+	memset(desc->completion, 0, sizeof(struct dsa_completion_record));
+	return desc;
+}
+
+void idxd_free_desc(struct idxd_wq *wq, struct idxd_desc *desc)
+{
+	atomic_dec(&wq->dq_count);
+
+	sbitmap_clear_bit(&wq->sbmap, desc->id);
+	wake_up(&wq->submit_waitq);
+}
+
+int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc)
+{
+	struct idxd_device *idxd = wq->idxd;
+	int vec = desc->hw->int_handle;
+	void __iomem *portal;
+
+	if (idxd->state != IDXD_DEV_ENABLED)
+		return -EIO;
+
+	portal = wq->dportal + idxd_get_wq_portal_offset(IDXD_PORTAL_UNLIMITED);
+	/*
+	 * The wmb() flushes writes to coherent DMA data before possibly
+	 * triggering a DMA read. The wmb() is necessary even on UP because
+	 * the recipient is a device.
+	 */
+	wmb();
+	iosubmit_cmds512(portal, desc->hw, 1);
+
+	/*
+	 * Pending the descriptor to the lockless list for the irq_entry
+	 * that we designated the descriptor to.
+	 */
+	if (desc->hw->flags & IDXD_OP_FLAG_RCI)
+		llist_add(&desc->llnode,
+			  &idxd->irq_entries[vec].pending_llist);
+
+	return 0;
+}
diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c
new file mode 100644
index 000000000000..6ca6e520a2fa
--- /dev/null
+++ b/drivers/dma/idxd/sysfs.c
@@ -0,0 +1,1547 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2019 Intel Corporation. All rights rsvd. */
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/device.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
+#include <uapi/linux/idxd.h>
+#include "registers.h"
+#include "idxd.h"
+
+static char *idxd_wq_type_names[] = {
+	[IDXD_WQT_NONE]		= "none",
+	[IDXD_WQT_KERNEL]	= "kernel",
+	[IDXD_WQT_USER]		= "user",
+};
+
+static void idxd_conf_device_release(struct device *dev)
+{
+	dev_dbg(dev, "%s for %s\n", __func__, dev_name(dev));
+}
+
+static struct device_type idxd_group_device_type = {
+	.name = "group",
+	.release = idxd_conf_device_release,
+};
+
+static struct device_type idxd_wq_device_type = {
+	.name = "wq",
+	.release = idxd_conf_device_release,
+};
+
+static struct device_type idxd_engine_device_type = {
+	.name = "engine",
+	.release = idxd_conf_device_release,
+};
+
+static struct device_type dsa_device_type = {
+	.name = "dsa",
+	.release = idxd_conf_device_release,
+};
+
+static inline bool is_dsa_dev(struct device *dev)
+{
+	return dev ? dev->type == &dsa_device_type : false;
+}
+
+static inline bool is_idxd_dev(struct device *dev)
+{
+	return is_dsa_dev(dev);
+}
+
+static inline bool is_idxd_wq_dev(struct device *dev)
+{
+	return dev ? dev->type == &idxd_wq_device_type : false;
+}
+
+static inline bool is_idxd_wq_dmaengine(struct idxd_wq *wq)
+{
+	if (wq->type == IDXD_WQT_KERNEL &&
+	    strcmp(wq->name, "dmaengine") == 0)
+		return true;
+	return false;
+}
+
+static inline bool is_idxd_wq_cdev(struct idxd_wq *wq)
+{
+	return wq->type == IDXD_WQT_USER;
+}
+
+static int idxd_config_bus_match(struct device *dev,
+				 struct device_driver *drv)
+{
+	int matched = 0;
+
+	if (is_idxd_dev(dev)) {
+		struct idxd_device *idxd = confdev_to_idxd(dev);
+
+		if (idxd->state != IDXD_DEV_CONF_READY)
+			return 0;
+		matched = 1;
+	} else if (is_idxd_wq_dev(dev)) {
+		struct idxd_wq *wq = confdev_to_wq(dev);
+		struct idxd_device *idxd = wq->idxd;
+
+		if (idxd->state < IDXD_DEV_CONF_READY)
+			return 0;
+
+		if (wq->state != IDXD_WQ_DISABLED) {
+			dev_dbg(dev, "%s not disabled\n", dev_name(dev));
+			return 0;
+		}
+		matched = 1;
+	}
+
+	if (matched)
+		dev_dbg(dev, "%s matched\n", dev_name(dev));
+
+	return matched;
+}
+
+static int idxd_config_bus_probe(struct device *dev)
+{
+	int rc;
+	unsigned long flags;
+
+	dev_dbg(dev, "%s called\n", __func__);
+
+	if (is_idxd_dev(dev)) {
+		struct idxd_device *idxd = confdev_to_idxd(dev);
+
+		if (idxd->state != IDXD_DEV_CONF_READY) {
+			dev_warn(dev, "Device not ready for config\n");
+			return -EBUSY;
+		}
+
+		if (!try_module_get(THIS_MODULE))
+			return -ENXIO;
+
+		spin_lock_irqsave(&idxd->dev_lock, flags);
+
+		/* Perform IDXD configuration and enabling */
+		rc = idxd_device_config(idxd);
+		if (rc < 0) {
+			spin_unlock_irqrestore(&idxd->dev_lock, flags);
+			module_put(THIS_MODULE);
+			dev_warn(dev, "Device config failed: %d\n", rc);
+			return rc;
+		}
+
+		/* start device */
+		rc = idxd_device_enable(idxd);
+		if (rc < 0) {
+			spin_unlock_irqrestore(&idxd->dev_lock, flags);
+			module_put(THIS_MODULE);
+			dev_warn(dev, "Device enable failed: %d\n", rc);
+			return rc;
+		}
+
+		spin_unlock_irqrestore(&idxd->dev_lock, flags);
+		dev_info(dev, "Device %s enabled\n", dev_name(dev));
+
+		rc = idxd_register_dma_device(idxd);
+		if (rc < 0) {
+			spin_unlock_irqrestore(&idxd->dev_lock, flags);
+			module_put(THIS_MODULE);
+			dev_dbg(dev, "Failed to register dmaengine device\n");
+			return rc;
+		}
+		return 0;
+	} else if (is_idxd_wq_dev(dev)) {
+		struct idxd_wq *wq = confdev_to_wq(dev);
+		struct idxd_device *idxd = wq->idxd;
+
+		mutex_lock(&wq->wq_lock);
+
+		if (idxd->state != IDXD_DEV_ENABLED) {
+			mutex_unlock(&wq->wq_lock);
+			dev_warn(dev, "Enabling while device not enabled.\n");
+			return -EPERM;
+		}
+
+		if (wq->state != IDXD_WQ_DISABLED) {
+			mutex_unlock(&wq->wq_lock);
+			dev_warn(dev, "WQ %d already enabled.\n", wq->id);
+			return -EBUSY;
+		}
+
+		if (!wq->group) {
+			mutex_unlock(&wq->wq_lock);
+			dev_warn(dev, "WQ not attached to group.\n");
+			return -EINVAL;
+		}
+
+		if (strlen(wq->name) == 0) {
+			mutex_unlock(&wq->wq_lock);
+			dev_warn(dev, "WQ name not set.\n");
+			return -EINVAL;
+		}
+
+		rc = idxd_wq_alloc_resources(wq);
+		if (rc < 0) {
+			mutex_unlock(&wq->wq_lock);
+			dev_warn(dev, "WQ resource alloc failed\n");
+			return rc;
+		}
+
+		spin_lock_irqsave(&idxd->dev_lock, flags);
+		rc = idxd_device_config(idxd);
+		if (rc < 0) {
+			spin_unlock_irqrestore(&idxd->dev_lock, flags);
+			mutex_unlock(&wq->wq_lock);
+			dev_warn(dev, "Writing WQ %d config failed: %d\n",
+				 wq->id, rc);
+			return rc;
+		}
+
+		rc = idxd_wq_enable(wq);
+		if (rc < 0) {
+			spin_unlock_irqrestore(&idxd->dev_lock, flags);
+			mutex_unlock(&wq->wq_lock);
+			dev_warn(dev, "WQ %d enabling failed: %d\n",
+				 wq->id, rc);
+			return rc;
+		}
+		spin_unlock_irqrestore(&idxd->dev_lock, flags);
+
+		rc = idxd_wq_map_portal(wq);
+		if (rc < 0) {
+			dev_warn(dev, "wq portal mapping failed: %d\n", rc);
+			rc = idxd_wq_disable(wq);
+			if (rc < 0)
+				dev_warn(dev, "IDXD wq disable failed\n");
+			spin_unlock_irqrestore(&idxd->dev_lock, flags);
+			mutex_unlock(&wq->wq_lock);
+			return rc;
+		}
+
+		wq->client_count = 0;
+
+		dev_info(dev, "wq %s enabled\n", dev_name(&wq->conf_dev));
+
+		if (is_idxd_wq_dmaengine(wq)) {
+			rc = idxd_register_dma_channel(wq);
+			if (rc < 0) {
+				dev_dbg(dev, "DMA channel register failed\n");
+				mutex_unlock(&wq->wq_lock);
+				return rc;
+			}
+		} else if (is_idxd_wq_cdev(wq)) {
+			rc = idxd_wq_add_cdev(wq);
+			if (rc < 0) {
+				dev_dbg(dev, "Cdev creation failed\n");
+				mutex_unlock(&wq->wq_lock);
+				return rc;
+			}
+		}
+
+		mutex_unlock(&wq->wq_lock);
+		return 0;
+	}
+
+	return -ENODEV;
+}
+
+static void disable_wq(struct idxd_wq *wq)
+{
+	struct idxd_device *idxd = wq->idxd;
+	struct device *dev = &idxd->pdev->dev;
+	unsigned long flags;
+	int rc;
+
+	mutex_lock(&wq->wq_lock);
+	dev_dbg(dev, "%s removing WQ %s\n", __func__, dev_name(&wq->conf_dev));
+	if (wq->state == IDXD_WQ_DISABLED) {
+		mutex_unlock(&wq->wq_lock);
+		return;
+	}
+
+	if (is_idxd_wq_dmaengine(wq))
+		idxd_unregister_dma_channel(wq);
+	else if (is_idxd_wq_cdev(wq))
+		idxd_wq_del_cdev(wq);
+
+	if (idxd_wq_refcount(wq))
+		dev_warn(dev, "Clients has claim on wq %d: %d\n",
+			 wq->id, idxd_wq_refcount(wq));
+
+	idxd_wq_unmap_portal(wq);
+
+	spin_lock_irqsave(&idxd->dev_lock, flags);
+	rc = idxd_wq_disable(wq);
+	spin_unlock_irqrestore(&idxd->dev_lock, flags);
+
+	idxd_wq_free_resources(wq);
+	wq->client_count = 0;
+	mutex_unlock(&wq->wq_lock);
+
+	if (rc < 0)
+		dev_warn(dev, "Failed to disable %s: %d\n",
+			 dev_name(&wq->conf_dev), rc);
+	else
+		dev_info(dev, "wq %s disabled\n", dev_name(&wq->conf_dev));
+}
+
+static int idxd_config_bus_remove(struct device *dev)
+{
+	int rc;
+	unsigned long flags;
+
+	dev_dbg(dev, "%s called for %s\n", __func__, dev_name(dev));
+
+	/* disable workqueue here */
+	if (is_idxd_wq_dev(dev)) {
+		struct idxd_wq *wq = confdev_to_wq(dev);
+
+		disable_wq(wq);
+	} else if (is_idxd_dev(dev)) {
+		struct idxd_device *idxd = confdev_to_idxd(dev);
+		int i;
+
+		dev_dbg(dev, "%s removing dev %s\n", __func__,
+			dev_name(&idxd->conf_dev));
+		for (i = 0; i < idxd->max_wqs; i++) {
+			struct idxd_wq *wq = &idxd->wqs[i];
+
+			if (wq->state == IDXD_WQ_DISABLED)
+				continue;
+			dev_warn(dev, "Active wq %d on disable %s.\n", i,
+				 dev_name(&idxd->conf_dev));
+			device_release_driver(&wq->conf_dev);
+		}
+
+		idxd_unregister_dma_device(idxd);
+		spin_lock_irqsave(&idxd->dev_lock, flags);
+		rc = idxd_device_disable(idxd);
+		spin_unlock_irqrestore(&idxd->dev_lock, flags);
+		module_put(THIS_MODULE);
+		if (rc < 0)
+			dev_warn(dev, "Device disable failed\n");
+		else
+			dev_info(dev, "Device %s disabled\n", dev_name(dev));
+
+	}
+
+	return 0;
+}
+
+static void idxd_config_bus_shutdown(struct device *dev)
+{
+	dev_dbg(dev, "%s called\n", __func__);
+}
+
+struct bus_type dsa_bus_type = {
+	.name = "dsa",
+	.match = idxd_config_bus_match,
+	.probe = idxd_config_bus_probe,
+	.remove = idxd_config_bus_remove,
+	.shutdown = idxd_config_bus_shutdown,
+};
+
+static struct bus_type *idxd_bus_types[] = {
+	&dsa_bus_type
+};
+
+static struct idxd_device_driver dsa_drv = {
+	.drv = {
+		.name = "dsa",
+		.bus = &dsa_bus_type,
+		.owner = THIS_MODULE,
+		.mod_name = KBUILD_MODNAME,
+	},
+};
+
+static struct idxd_device_driver *idxd_drvs[] = {
+	&dsa_drv
+};
+
+struct bus_type *idxd_get_bus_type(struct idxd_device *idxd)
+{
+	return idxd_bus_types[idxd->type];
+}
+
+static struct device_type *idxd_get_device_type(struct idxd_device *idxd)
+{
+	if (idxd->type == IDXD_TYPE_DSA)
+		return &dsa_device_type;
+	else
+		return NULL;
+}
+
+/* IDXD generic driver setup */
+int idxd_register_driver(void)
+{
+	int i, rc;
+
+	for (i = 0; i < IDXD_TYPE_MAX; i++) {
+		rc = driver_register(&idxd_drvs[i]->drv);
+		if (rc < 0)
+			goto drv_fail;
+	}
+
+	return 0;
+
+drv_fail:
+	for (; i > 0; i--)
+		driver_unregister(&idxd_drvs[i]->drv);
+	return rc;
+}
+
+void idxd_unregister_driver(void)
+{
+	int i;
+
+	for (i = 0; i < IDXD_TYPE_MAX; i++)
+		driver_unregister(&idxd_drvs[i]->drv);
+}
+
+/* IDXD engine attributes */
+static ssize_t engine_group_id_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	struct idxd_engine *engine =
+		container_of(dev, struct idxd_engine, conf_dev);
+
+	if (engine->group)
+		return sprintf(buf, "%d\n", engine->group->id);
+	else
+		return sprintf(buf, "%d\n", -1);
+}
+
+static ssize_t engine_group_id_store(struct device *dev,
+				     struct device_attribute *attr,
+				     const char *buf, size_t count)
+{
+	struct idxd_engine *engine =
+		container_of(dev, struct idxd_engine, conf_dev);
+	struct idxd_device *idxd = engine->idxd;
+	long id;
+	int rc;
+	struct idxd_group *prevg, *group;
+
+	rc = kstrtol(buf, 10, &id);
+	if (rc < 0)
+		return -EINVAL;
+
+	if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
+		return -EPERM;
+
+	if (id > idxd->max_groups - 1 || id < -1)
+		return -EINVAL;
+
+	if (id == -1) {
+		if (engine->group) {
+			engine->group->num_engines--;
+			engine->group = NULL;
+		}
+		return count;
+	}
+
+	group = &idxd->groups[id];
+	prevg = engine->group;
+
+	if (prevg)
+		prevg->num_engines--;
+	engine->group = &idxd->groups[id];
+	engine->group->num_engines++;
+
+	return count;
+}
+
+static struct device_attribute dev_attr_engine_group =
+		__ATTR(group_id, 0644, engine_group_id_show,
+		       engine_group_id_store);
+
+static struct attribute *idxd_engine_attributes[] = {
+	&dev_attr_engine_group.attr,
+	NULL,
+};
+
+static const struct attribute_group idxd_engine_attribute_group = {
+	.attrs = idxd_engine_attributes,
+};
+
+static const struct attribute_group *idxd_engine_attribute_groups[] = {
+	&idxd_engine_attribute_group,
+	NULL,
+};
+
+/* Group attributes */
+
+static void idxd_set_free_tokens(struct idxd_device *idxd)
+{
+	int i, tokens;
+
+	for (i = 0, tokens = 0; i < idxd->max_groups; i++) {
+		struct idxd_group *g = &idxd->groups[i];
+
+		tokens += g->tokens_reserved;
+	}
+
+	idxd->nr_tokens = idxd->max_tokens - tokens;
+}
+
+static ssize_t group_tokens_reserved_show(struct device *dev,
+					  struct device_attribute *attr,
+					  char *buf)
+{
+	struct idxd_group *group =
+		container_of(dev, struct idxd_group, conf_dev);
+
+	return sprintf(buf, "%u\n", group->tokens_reserved);
+}
+
+static ssize_t group_tokens_reserved_store(struct device *dev,
+					   struct device_attribute *attr,
+					   const char *buf, size_t count)
+{
+	struct idxd_group *group =
+		container_of(dev, struct idxd_group, conf_dev);
+	struct idxd_device *idxd = group->idxd;
+	unsigned long val;
+	int rc;
+
+	rc = kstrtoul(buf, 10, &val);
+	if (rc < 0)
+		return -EINVAL;
+
+	if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
+		return -EPERM;
+
+	if (idxd->state == IDXD_DEV_ENABLED)
+		return -EPERM;
+
+	if (idxd->token_limit == 0)
+		return -EPERM;
+
+	if (val > idxd->max_tokens)
+		return -EINVAL;
+
+	if (val > idxd->nr_tokens + group->tokens_reserved)
+		return -EINVAL;
+
+	group->tokens_reserved = val;
+	idxd_set_free_tokens(idxd);
+	return count;
+}
+
+static struct device_attribute dev_attr_group_tokens_reserved =
+		__ATTR(tokens_reserved, 0644, group_tokens_reserved_show,
+		       group_tokens_reserved_store);
+
+static ssize_t group_tokens_allowed_show(struct device *dev,
+					 struct device_attribute *attr,
+					 char *buf)
+{
+	struct idxd_group *group =
+		container_of(dev, struct idxd_group, conf_dev);
+
+	return sprintf(buf, "%u\n", group->tokens_allowed);
+}
+
+static ssize_t group_tokens_allowed_store(struct device *dev,
+					  struct device_attribute *attr,
+					  const char *buf, size_t count)
+{
+	struct idxd_group *group =
+		container_of(dev, struct idxd_group, conf_dev);
+	struct idxd_device *idxd = group->idxd;
+	unsigned long val;
+	int rc;
+
+	rc = kstrtoul(buf, 10, &val);
+	if (rc < 0)
+		return -EINVAL;
+
+	if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
+		return -EPERM;
+
+	if (idxd->state == IDXD_DEV_ENABLED)
+		return -EPERM;
+
+	if (idxd->token_limit == 0)
+		return -EPERM;
+	if (val < 4 * group->num_engines ||
+	    val > group->tokens_reserved + idxd->nr_tokens)
+		return -EINVAL;
+
+	group->tokens_allowed = val;
+	return count;
+}
+
+static struct device_attribute dev_attr_group_tokens_allowed =
+		__ATTR(tokens_allowed, 0644, group_tokens_allowed_show,
+		       group_tokens_allowed_store);
+
+static ssize_t group_use_token_limit_show(struct device *dev,
+					  struct device_attribute *attr,
+					  char *buf)
+{
+	struct idxd_group *group =
+		container_of(dev, struct idxd_group, conf_dev);
+
+	return sprintf(buf, "%u\n", group->use_token_limit);
+}
+
+static ssize_t group_use_token_limit_store(struct device *dev,
+					   struct device_attribute *attr,
+					   const char *buf, size_t count)
+{
+	struct idxd_group *group =
+		container_of(dev, struct idxd_group, conf_dev);
+	struct idxd_device *idxd = group->idxd;
+	unsigned long val;
+	int rc;
+
+	rc = kstrtoul(buf, 10, &val);
+	if (rc < 0)
+		return -EINVAL;
+
+	if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
+		return -EPERM;
+
+	if (idxd->state == IDXD_DEV_ENABLED)
+		return -EPERM;
+
+	if (idxd->token_limit == 0)
+		return -EPERM;
+
+	group->use_token_limit = !!val;
+	return count;
+}
+
+static struct device_attribute dev_attr_group_use_token_limit =
+		__ATTR(use_token_limit, 0644, group_use_token_limit_show,
+		       group_use_token_limit_store);
+
+static ssize_t group_engines_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	struct idxd_group *group =
+		container_of(dev, struct idxd_group, conf_dev);
+	int i, rc = 0;
+	char *tmp = buf;
+	struct idxd_device *idxd = group->idxd;
+
+	for (i = 0; i < idxd->max_engines; i++) {
+		struct idxd_engine *engine = &idxd->engines[i];
+
+		if (!engine->group)
+			continue;
+
+		if (engine->group->id == group->id)
+			rc += sprintf(tmp + rc, "engine%d.%d ",
+					idxd->id, engine->id);
+	}
+
+	rc--;
+	rc += sprintf(tmp + rc, "\n");
+
+	return rc;
+}
+
+static struct device_attribute dev_attr_group_engines =
+		__ATTR(engines, 0444, group_engines_show, NULL);
+
+static ssize_t group_work_queues_show(struct device *dev,
+				      struct device_attribute *attr, char *buf)
+{
+	struct idxd_group *group =
+		container_of(dev, struct idxd_group, conf_dev);
+	int i, rc = 0;
+	char *tmp = buf;
+	struct idxd_device *idxd = group->idxd;
+
+	for (i = 0; i < idxd->max_wqs; i++) {
+		struct idxd_wq *wq = &idxd->wqs[i];
+
+		if (!wq->group)
+			continue;
+
+		if (wq->group->id == group->id)
+			rc += sprintf(tmp + rc, "wq%d.%d ",
+					idxd->id, wq->id);
+	}
+
+	rc--;
+	rc += sprintf(tmp + rc, "\n");
+
+	return rc;
+}
+
+static struct device_attribute dev_attr_group_work_queues =
+		__ATTR(work_queues, 0444, group_work_queues_show, NULL);
+
+static ssize_t group_traffic_class_a_show(struct device *dev,
+					  struct device_attribute *attr,
+					  char *buf)
+{
+	struct idxd_group *group =
+		container_of(dev, struct idxd_group, conf_dev);
+
+	return sprintf(buf, "%d\n", group->tc_a);
+}
+
+static ssize_t group_traffic_class_a_store(struct device *dev,
+					   struct device_attribute *attr,
+					   const char *buf, size_t count)
+{
+	struct idxd_group *group =
+		container_of(dev, struct idxd_group, conf_dev);
+	struct idxd_device *idxd = group->idxd;
+	long val;
+	int rc;
+
+	rc = kstrtol(buf, 10, &val);
+	if (rc < 0)
+		return -EINVAL;
+
+	if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
+		return -EPERM;
+
+	if (idxd->state == IDXD_DEV_ENABLED)
+		return -EPERM;
+
+	if (val < 0 || val > 7)
+		return -EINVAL;
+
+	group->tc_a = val;
+	return count;
+}
+
+static struct device_attribute dev_attr_group_traffic_class_a =
+		__ATTR(traffic_class_a, 0644, group_traffic_class_a_show,
+		       group_traffic_class_a_store);
+
+static ssize_t group_traffic_class_b_show(struct device *dev,
+					  struct device_attribute *attr,
+					  char *buf)
+{
+	struct idxd_group *group =
+		container_of(dev, struct idxd_group, conf_dev);
+
+	return sprintf(buf, "%d\n", group->tc_b);
+}
+
+static ssize_t group_traffic_class_b_store(struct device *dev,
+					   struct device_attribute *attr,
+					   const char *buf, size_t count)
+{
+	struct idxd_group *group =
+		container_of(dev, struct idxd_group, conf_dev);
+	struct idxd_device *idxd = group->idxd;
+	long val;
+	int rc;
+
+	rc = kstrtol(buf, 10, &val);
+	if (rc < 0)
+		return -EINVAL;
+
+	if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
+		return -EPERM;
+
+	if (idxd->state == IDXD_DEV_ENABLED)
+		return -EPERM;
+
+	if (val < 0 || val > 7)
+		return -EINVAL;
+
+	group->tc_b = val;
+	return count;
+}
+
+static struct device_attribute dev_attr_group_traffic_class_b =
+		__ATTR(traffic_class_b, 0644, group_traffic_class_b_show,
+		       group_traffic_class_b_store);
+
+static struct attribute *idxd_group_attributes[] = {
+	&dev_attr_group_work_queues.attr,
+	&dev_attr_group_engines.attr,
+	&dev_attr_group_use_token_limit.attr,
+	&dev_attr_group_tokens_allowed.attr,
+	&dev_attr_group_tokens_reserved.attr,
+	&dev_attr_group_traffic_class_a.attr,
+	&dev_attr_group_traffic_class_b.attr,
+	NULL,
+};
+
+static const struct attribute_group idxd_group_attribute_group = {
+	.attrs = idxd_group_attributes,
+};
+
+static const struct attribute_group *idxd_group_attribute_groups[] = {
+	&idxd_group_attribute_group,
+	NULL,
+};
+
+/* IDXD work queue attribs */
+static ssize_t wq_clients_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
+
+	return sprintf(buf, "%d\n", wq->client_count);
+}
+
+static struct device_attribute dev_attr_wq_clients =
+		__ATTR(clients, 0444, wq_clients_show, NULL);
+
+static ssize_t wq_state_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
+
+	switch (wq->state) {
+	case IDXD_WQ_DISABLED:
+		return sprintf(buf, "disabled\n");
+	case IDXD_WQ_ENABLED:
+		return sprintf(buf, "enabled\n");
+	}
+
+	return sprintf(buf, "unknown\n");
+}
+
+static struct device_attribute dev_attr_wq_state =
+		__ATTR(state, 0444, wq_state_show, NULL);
+
+static ssize_t wq_group_id_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
+
+	if (wq->group)
+		return sprintf(buf, "%u\n", wq->group->id);
+	else
+		return sprintf(buf, "-1\n");
+}
+
+static ssize_t wq_group_id_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf, size_t count)
+{
+	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
+	struct idxd_device *idxd = wq->idxd;
+	long id;
+	int rc;
+	struct idxd_group *prevg, *group;
+
+	rc = kstrtol(buf, 10, &id);
+	if (rc < 0)
+		return -EINVAL;
+
+	if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
+		return -EPERM;
+
+	if (wq->state != IDXD_WQ_DISABLED)
+		return -EPERM;
+
+	if (id > idxd->max_groups - 1 || id < -1)
+		return -EINVAL;
+
+	if (id == -1) {
+		if (wq->group) {
+			wq->group->num_wqs--;
+			wq->group = NULL;
+		}
+		return count;
+	}
+
+	group = &idxd->groups[id];
+	prevg = wq->group;
+
+	if (prevg)
+		prevg->num_wqs--;
+	wq->group = group;
+	group->num_wqs++;
+	return count;
+}
+
+static struct device_attribute dev_attr_wq_group_id =
+		__ATTR(group_id, 0644, wq_group_id_show, wq_group_id_store);
+
+static ssize_t wq_mode_show(struct device *dev, struct device_attribute *attr,
+			    char *buf)
+{
+	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
+
+	return sprintf(buf, "%s\n",
+			wq_dedicated(wq) ? "dedicated" : "shared");
+}
+
+static ssize_t wq_mode_store(struct device *dev,
+			     struct device_attribute *attr, const char *buf,
+			     size_t count)
+{
+	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
+	struct idxd_device *idxd = wq->idxd;
+
+	if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
+		return -EPERM;
+
+	if (wq->state != IDXD_WQ_DISABLED)
+		return -EPERM;
+
+	if (sysfs_streq(buf, "dedicated")) {
+		set_bit(WQ_FLAG_DEDICATED, &wq->flags);
+		wq->threshold = 0;
+	} else {
+		return -EINVAL;
+	}
+
+	return count;
+}
+
+static struct device_attribute dev_attr_wq_mode =
+		__ATTR(mode, 0644, wq_mode_show, wq_mode_store);
+
+static ssize_t wq_size_show(struct device *dev, struct device_attribute *attr,
+			    char *buf)
+{
+	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
+
+	return sprintf(buf, "%u\n", wq->size);
+}
+
+static int total_claimed_wq_size(struct idxd_device *idxd)
+{
+	int i;
+	int wq_size = 0;
+
+	for (i = 0; i < idxd->max_wqs; i++) {
+		struct idxd_wq *wq = &idxd->wqs[i];
+
+		wq_size += wq->size;
+	}
+
+	return wq_size;
+}
+
+static ssize_t wq_size_store(struct device *dev,
+			     struct device_attribute *attr, const char *buf,
+			     size_t count)
+{
+	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
+	unsigned long size;
+	struct idxd_device *idxd = wq->idxd;
+	int rc;
+
+	rc = kstrtoul(buf, 10, &size);
+	if (rc < 0)
+		return -EINVAL;
+
+	if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
+		return -EPERM;
+
+	if (wq->state != IDXD_WQ_DISABLED)
+		return -EPERM;
+
+	if (size + total_claimed_wq_size(idxd) - wq->size > idxd->max_wq_size)
+		return -EINVAL;
+
+	wq->size = size;
+	return count;
+}
+
+static struct device_attribute dev_attr_wq_size =
+		__ATTR(size, 0644, wq_size_show, wq_size_store);
+
+static ssize_t wq_priority_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
+
+	return sprintf(buf, "%u\n", wq->priority);
+}
+
+static ssize_t wq_priority_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf, size_t count)
+{
+	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
+	unsigned long prio;
+	struct idxd_device *idxd = wq->idxd;
+	int rc;
+
+	rc = kstrtoul(buf, 10, &prio);
+	if (rc < 0)
+		return -EINVAL;
+
+	if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
+		return -EPERM;
+
+	if (wq->state != IDXD_WQ_DISABLED)
+		return -EPERM;
+
+	if (prio > IDXD_MAX_PRIORITY)
+		return -EINVAL;
+
+	wq->priority = prio;
+	return count;
+}
+
+static struct device_attribute dev_attr_wq_priority =
+		__ATTR(priority, 0644, wq_priority_show, wq_priority_store);
+
+static ssize_t wq_type_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
+
+	switch (wq->type) {
+	case IDXD_WQT_KERNEL:
+		return sprintf(buf, "%s\n",
+			       idxd_wq_type_names[IDXD_WQT_KERNEL]);
+	case IDXD_WQT_USER:
+		return sprintf(buf, "%s\n",
+			       idxd_wq_type_names[IDXD_WQT_USER]);
+	case IDXD_WQT_NONE:
+	default:
+		return sprintf(buf, "%s\n",
+			       idxd_wq_type_names[IDXD_WQT_NONE]);
+	}
+
+	return -EINVAL;
+}
+
+static ssize_t wq_type_store(struct device *dev,
+			     struct device_attribute *attr, const char *buf,
+			     size_t count)
+{
+	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
+	enum idxd_wq_type old_type;
+
+	if (wq->state != IDXD_WQ_DISABLED)
+		return -EPERM;
+
+	old_type = wq->type;
+	if (sysfs_streq(buf, idxd_wq_type_names[IDXD_WQT_NONE]))
+		wq->type = IDXD_WQT_NONE;
+	else if (sysfs_streq(buf, idxd_wq_type_names[IDXD_WQT_KERNEL]))
+		wq->type = IDXD_WQT_KERNEL;
+	else if (sysfs_streq(buf, idxd_wq_type_names[IDXD_WQT_USER]))
+		wq->type = IDXD_WQT_USER;
+	else
+		return -EINVAL;
+
+	/* If we are changing queue type, clear the name */
+	if (wq->type != old_type)
+		memset(wq->name, 0, WQ_NAME_SIZE + 1);
+
+	return count;
+}
+
+static struct device_attribute dev_attr_wq_type =
+		__ATTR(type, 0644, wq_type_show, wq_type_store);
+
+static ssize_t wq_name_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
+
+	return sprintf(buf, "%s\n", wq->name);
+}
+
+static ssize_t wq_name_store(struct device *dev,
+			     struct device_attribute *attr, const char *buf,
+			     size_t count)
+{
+	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
+
+	if (wq->state != IDXD_WQ_DISABLED)
+		return -EPERM;
+
+	if (strlen(buf) > WQ_NAME_SIZE || strlen(buf) == 0)
+		return -EINVAL;
+
+	memset(wq->name, 0, WQ_NAME_SIZE + 1);
+	strncpy(wq->name, buf, WQ_NAME_SIZE);
+	strreplace(wq->name, '\n', '\0');
+	return count;
+}
+
+static struct device_attribute dev_attr_wq_name =
+		__ATTR(name, 0644, wq_name_show, wq_name_store);
+
+static ssize_t wq_cdev_minor_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
+
+	return sprintf(buf, "%d\n", wq->idxd_cdev.minor);
+}
+
+static struct device_attribute dev_attr_wq_cdev_minor =
+		__ATTR(cdev_minor, 0444, wq_cdev_minor_show, NULL);
+
+static struct attribute *idxd_wq_attributes[] = {
+	&dev_attr_wq_clients.attr,
+	&dev_attr_wq_state.attr,
+	&dev_attr_wq_group_id.attr,
+	&dev_attr_wq_mode.attr,
+	&dev_attr_wq_size.attr,
+	&dev_attr_wq_priority.attr,
+	&dev_attr_wq_type.attr,
+	&dev_attr_wq_name.attr,
+	&dev_attr_wq_cdev_minor.attr,
+	NULL,
+};
+
+static const struct attribute_group idxd_wq_attribute_group = {
+	.attrs = idxd_wq_attributes,
+};
+
+static const struct attribute_group *idxd_wq_attribute_groups[] = {
+	&idxd_wq_attribute_group,
+	NULL,
+};
+
+/* IDXD device attribs */
+static ssize_t max_work_queues_size_show(struct device *dev,
+					 struct device_attribute *attr,
+					 char *buf)
+{
+	struct idxd_device *idxd =
+		container_of(dev, struct idxd_device, conf_dev);
+
+	return sprintf(buf, "%u\n", idxd->max_wq_size);
+}
+static DEVICE_ATTR_RO(max_work_queues_size);
+
+static ssize_t max_groups_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	struct idxd_device *idxd =
+		container_of(dev, struct idxd_device, conf_dev);
+
+	return sprintf(buf, "%u\n", idxd->max_groups);
+}
+static DEVICE_ATTR_RO(max_groups);
+
+static ssize_t max_work_queues_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	struct idxd_device *idxd =
+		container_of(dev, struct idxd_device, conf_dev);
+
+	return sprintf(buf, "%u\n", idxd->max_wqs);
+}
+static DEVICE_ATTR_RO(max_work_queues);
+
+static ssize_t max_engines_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct idxd_device *idxd =
+		container_of(dev, struct idxd_device, conf_dev);
+
+	return sprintf(buf, "%u\n", idxd->max_engines);
+}
+static DEVICE_ATTR_RO(max_engines);
+
+static ssize_t numa_node_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	struct idxd_device *idxd =
+		container_of(dev, struct idxd_device, conf_dev);
+
+	return sprintf(buf, "%d\n", dev_to_node(&idxd->pdev->dev));
+}
+static DEVICE_ATTR_RO(numa_node);
+
+static ssize_t max_batch_size_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct idxd_device *idxd =
+		container_of(dev, struct idxd_device, conf_dev);
+
+	return sprintf(buf, "%u\n", idxd->max_batch_size);
+}
+static DEVICE_ATTR_RO(max_batch_size);
+
+static ssize_t max_transfer_size_show(struct device *dev,
+				      struct device_attribute *attr,
+				      char *buf)
+{
+	struct idxd_device *idxd =
+		container_of(dev, struct idxd_device, conf_dev);
+
+	return sprintf(buf, "%llu\n", idxd->max_xfer_bytes);
+}
+static DEVICE_ATTR_RO(max_transfer_size);
+
+static ssize_t op_cap_show(struct device *dev,
+			   struct device_attribute *attr, char *buf)
+{
+	struct idxd_device *idxd =
+		container_of(dev, struct idxd_device, conf_dev);
+
+	return sprintf(buf, "%#llx\n", idxd->hw.opcap.bits[0]);
+}
+static DEVICE_ATTR_RO(op_cap);
+
+static ssize_t configurable_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	struct idxd_device *idxd =
+		container_of(dev, struct idxd_device, conf_dev);
+
+	return sprintf(buf, "%u\n",
+			test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags));
+}
+static DEVICE_ATTR_RO(configurable);
+
+static ssize_t clients_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	struct idxd_device *idxd =
+		container_of(dev, struct idxd_device, conf_dev);
+	unsigned long flags;
+	int count = 0, i;
+
+	spin_lock_irqsave(&idxd->dev_lock, flags);
+	for (i = 0; i < idxd->max_wqs; i++) {
+		struct idxd_wq *wq = &idxd->wqs[i];
+
+		count += wq->client_count;
+	}
+	spin_unlock_irqrestore(&idxd->dev_lock, flags);
+
+	return sprintf(buf, "%d\n", count);
+}
+static DEVICE_ATTR_RO(clients);
+
+static ssize_t state_show(struct device *dev,
+			  struct device_attribute *attr, char *buf)
+{
+	struct idxd_device *idxd =
+		container_of(dev, struct idxd_device, conf_dev);
+
+	switch (idxd->state) {
+	case IDXD_DEV_DISABLED:
+	case IDXD_DEV_CONF_READY:
+		return sprintf(buf, "disabled\n");
+	case IDXD_DEV_ENABLED:
+		return sprintf(buf, "enabled\n");
+	case IDXD_DEV_HALTED:
+		return sprintf(buf, "halted\n");
+	}
+
+	return sprintf(buf, "unknown\n");
+}
+static DEVICE_ATTR_RO(state);
+
+static ssize_t errors_show(struct device *dev,
+			   struct device_attribute *attr, char *buf)
+{
+	struct idxd_device *idxd =
+		container_of(dev, struct idxd_device, conf_dev);
+	int i, out = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&idxd->dev_lock, flags);
+	for (i = 0; i < 4; i++)
+		out += sprintf(buf + out, "%#018llx ", idxd->sw_err.bits[i]);
+	spin_unlock_irqrestore(&idxd->dev_lock, flags);
+	out--;
+	out += sprintf(buf + out, "\n");
+	return out;
+}
+static DEVICE_ATTR_RO(errors);
+
+static ssize_t max_tokens_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	struct idxd_device *idxd =
+		container_of(dev, struct idxd_device, conf_dev);
+
+	return sprintf(buf, "%u\n", idxd->max_tokens);
+}
+static DEVICE_ATTR_RO(max_tokens);
+
+static ssize_t token_limit_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct idxd_device *idxd =
+		container_of(dev, struct idxd_device, conf_dev);
+
+	return sprintf(buf, "%u\n", idxd->token_limit);
+}
+
+static ssize_t token_limit_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf, size_t count)
+{
+	struct idxd_device *idxd =
+		container_of(dev, struct idxd_device, conf_dev);
+	unsigned long val;
+	int rc;
+
+	rc = kstrtoul(buf, 10, &val);
+	if (rc < 0)
+		return -EINVAL;
+
+	if (idxd->state == IDXD_DEV_ENABLED)
+		return -EPERM;
+
+	if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
+		return -EPERM;
+
+	if (!idxd->hw.group_cap.token_limit)
+		return -EPERM;
+
+	if (val > idxd->hw.group_cap.total_tokens)
+		return -EINVAL;
+
+	idxd->token_limit = val;
+	return count;
+}
+static DEVICE_ATTR_RW(token_limit);
+
+static ssize_t cdev_major_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	struct idxd_device *idxd =
+		container_of(dev, struct idxd_device, conf_dev);
+
+	return sprintf(buf, "%u\n", idxd->major);
+}
+static DEVICE_ATTR_RO(cdev_major);
+
+static struct attribute *idxd_device_attributes[] = {
+	&dev_attr_max_groups.attr,
+	&dev_attr_max_work_queues.attr,
+	&dev_attr_max_work_queues_size.attr,
+	&dev_attr_max_engines.attr,
+	&dev_attr_numa_node.attr,
+	&dev_attr_max_batch_size.attr,
+	&dev_attr_max_transfer_size.attr,
+	&dev_attr_op_cap.attr,
+	&dev_attr_configurable.attr,
+	&dev_attr_clients.attr,
+	&dev_attr_state.attr,
+	&dev_attr_errors.attr,
+	&dev_attr_max_tokens.attr,
+	&dev_attr_token_limit.attr,
+	&dev_attr_cdev_major.attr,
+	NULL,
+};
+
+static const struct attribute_group idxd_device_attribute_group = {
+	.attrs = idxd_device_attributes,
+};
+
+static const struct attribute_group *idxd_attribute_groups[] = {
+	&idxd_device_attribute_group,
+	NULL,
+};
+
+static int idxd_setup_engine_sysfs(struct idxd_device *idxd)
+{
+	struct device *dev = &idxd->pdev->dev;
+	int i, rc;
+
+	for (i = 0; i < idxd->max_engines; i++) {
+		struct idxd_engine *engine = &idxd->engines[i];
+
+		engine->conf_dev.parent = &idxd->conf_dev;
+		dev_set_name(&engine->conf_dev, "engine%d.%d",
+			     idxd->id, engine->id);
+		engine->conf_dev.bus = idxd_get_bus_type(idxd);
+		engine->conf_dev.groups = idxd_engine_attribute_groups;
+		engine->conf_dev.type = &idxd_engine_device_type;
+		dev_dbg(dev, "Engine device register: %s\n",
+			dev_name(&engine->conf_dev));
+		rc = device_register(&engine->conf_dev);
+		if (rc < 0) {
+			put_device(&engine->conf_dev);
+			goto cleanup;
+		}
+	}
+
+	return 0;
+
+cleanup:
+	while (i--) {
+		struct idxd_engine *engine = &idxd->engines[i];
+
+		device_unregister(&engine->conf_dev);
+	}
+	return rc;
+}
+
+static int idxd_setup_group_sysfs(struct idxd_device *idxd)
+{
+	struct device *dev = &idxd->pdev->dev;
+	int i, rc;
+
+	for (i = 0; i < idxd->max_groups; i++) {
+		struct idxd_group *group = &idxd->groups[i];
+
+		group->conf_dev.parent = &idxd->conf_dev;
+		dev_set_name(&group->conf_dev, "group%d.%d",
+			     idxd->id, group->id);
+		group->conf_dev.bus = idxd_get_bus_type(idxd);
+		group->conf_dev.groups = idxd_group_attribute_groups;
+		group->conf_dev.type = &idxd_group_device_type;
+		dev_dbg(dev, "Group device register: %s\n",
+			dev_name(&group->conf_dev));
+		rc = device_register(&group->conf_dev);
+		if (rc < 0) {
+			put_device(&group->conf_dev);
+			goto cleanup;
+		}
+	}
+
+	return 0;
+
+cleanup:
+	while (i--) {
+		struct idxd_group *group = &idxd->groups[i];
+
+		device_unregister(&group->conf_dev);
+	}
+	return rc;
+}
+
+static int idxd_setup_wq_sysfs(struct idxd_device *idxd)
+{
+	struct device *dev = &idxd->pdev->dev;
+	int i, rc;
+
+	for (i = 0; i < idxd->max_wqs; i++) {
+		struct idxd_wq *wq = &idxd->wqs[i];
+
+		wq->conf_dev.parent = &idxd->conf_dev;
+		dev_set_name(&wq->conf_dev, "wq%d.%d", idxd->id, wq->id);
+		wq->conf_dev.bus = idxd_get_bus_type(idxd);
+		wq->conf_dev.groups = idxd_wq_attribute_groups;
+		wq->conf_dev.type = &idxd_wq_device_type;
+		dev_dbg(dev, "WQ device register: %s\n",
+			dev_name(&wq->conf_dev));
+		rc = device_register(&wq->conf_dev);
+		if (rc < 0) {
+			put_device(&wq->conf_dev);
+			goto cleanup;
+		}
+	}
+
+	return 0;
+
+cleanup:
+	while (i--) {
+		struct idxd_wq *wq = &idxd->wqs[i];
+
+		device_unregister(&wq->conf_dev);
+	}
+	return rc;
+}
+
+static int idxd_setup_device_sysfs(struct idxd_device *idxd)
+{
+	struct device *dev = &idxd->pdev->dev;
+	int rc;
+	char devname[IDXD_NAME_SIZE];
+
+	sprintf(devname, "%s%d", idxd_get_dev_name(idxd), idxd->id);
+	idxd->conf_dev.parent = dev;
+	dev_set_name(&idxd->conf_dev, "%s", devname);
+	idxd->conf_dev.bus = idxd_get_bus_type(idxd);
+	idxd->conf_dev.groups = idxd_attribute_groups;
+	idxd->conf_dev.type = idxd_get_device_type(idxd);
+
+	dev_dbg(dev, "IDXD device register: %s\n", dev_name(&idxd->conf_dev));
+	rc = device_register(&idxd->conf_dev);
+	if (rc < 0) {
+		put_device(&idxd->conf_dev);
+		return rc;
+	}
+
+	return 0;
+}
+
+int idxd_setup_sysfs(struct idxd_device *idxd)
+{
+	struct device *dev = &idxd->pdev->dev;
+	int rc;
+
+	rc = idxd_setup_device_sysfs(idxd);
+	if (rc < 0) {
+		dev_dbg(dev, "Device sysfs registering failed: %d\n", rc);
+		return rc;
+	}
+
+	rc = idxd_setup_wq_sysfs(idxd);
+	if (rc < 0) {
+		/* unregister conf dev */
+		dev_dbg(dev, "Work Queue sysfs registering failed: %d\n", rc);
+		return rc;
+	}
+
+	rc = idxd_setup_group_sysfs(idxd);
+	if (rc < 0) {
+		/* unregister conf dev */
+		dev_dbg(dev, "Group sysfs registering failed: %d\n", rc);
+		return rc;
+	}
+
+	rc = idxd_setup_engine_sysfs(idxd);
+	if (rc < 0) {
+		/* unregister conf dev */
+		dev_dbg(dev, "Engine sysfs registering failed: %d\n", rc);
+		return rc;
+	}
+
+	return 0;
+}
+
+void idxd_cleanup_sysfs(struct idxd_device *idxd)
+{
+	int i;
+
+	for (i = 0; i < idxd->max_wqs; i++) {
+		struct idxd_wq *wq = &idxd->wqs[i];
+
+		device_unregister(&wq->conf_dev);
+	}
+
+	for (i = 0; i < idxd->max_engines; i++) {
+		struct idxd_engine *engine = &idxd->engines[i];
+
+		device_unregister(&engine->conf_dev);
+	}
+
+	for (i = 0; i < idxd->max_groups; i++) {
+		struct idxd_group *group = &idxd->groups[i];
+
+		device_unregister(&group->conf_dev);
+	}
+
+	device_unregister(&idxd->conf_dev);
+}
+
+int idxd_register_bus_type(void)
+{
+	int i, rc;
+
+	for (i = 0; i < IDXD_TYPE_MAX; i++) {
+		rc = bus_register(idxd_bus_types[i]);
+		if (rc < 0)
+			goto bus_err;
+	}
+
+	return 0;
+
+bus_err:
+	for (; i > 0; i--)
+		bus_unregister(idxd_bus_types[i]);
+	return rc;
+}
+
+void idxd_unregister_bus_type(void)
+{
+	int i;
+
+	for (i = 0; i < IDXD_TYPE_MAX; i++)
+		bus_unregister(idxd_bus_types[i]);
+}
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index c27e206a764c..4d4477df4ede 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -760,12 +760,8 @@ static void sdma_start_desc(struct sdma_channel *sdmac)
 		return;
 	}
 	sdmac->desc = desc = to_sdma_desc(&vd->tx);
-	/*
-	 * Do not delete the node in desc_issued list in cyclic mode, otherwise
-	 * the desc allocated will never be freed in vchan_dma_desc_free_list
-	 */
-	if (!(sdmac->flags & IMX_DMA_SG_LOOP))
-		list_del(&vd->node);
+
+	list_del(&vd->node);
 
 	sdma->channel_control[channel].base_bd_ptr = desc->bd_phys;
 	sdma->channel_control[channel].current_bd_ptr = desc->bd_phys;
@@ -1071,20 +1067,27 @@ static void sdma_channel_terminate_work(struct work_struct *work)
 
 	spin_lock_irqsave(&sdmac->vc.lock, flags);
 	vchan_get_all_descriptors(&sdmac->vc, &head);
-	sdmac->desc = NULL;
 	spin_unlock_irqrestore(&sdmac->vc.lock, flags);
 	vchan_dma_desc_free_list(&sdmac->vc, &head);
 	sdmac->context_loaded = false;
 }
 
-static int sdma_disable_channel_async(struct dma_chan *chan)
+static int sdma_terminate_all(struct dma_chan *chan)
 {
 	struct sdma_channel *sdmac = to_sdma_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&sdmac->vc.lock, flags);
 
 	sdma_disable_channel(chan);
 
-	if (sdmac->desc)
+	if (sdmac->desc) {
+		vchan_terminate_vdesc(&sdmac->desc->vd);
+		sdmac->desc = NULL;
 		schedule_work(&sdmac->terminate_worker);
+	}
+
+	spin_unlock_irqrestore(&sdmac->vc.lock, flags);
 
 	return 0;
 }
@@ -1324,17 +1327,18 @@ static void sdma_free_chan_resources(struct dma_chan *chan)
 	struct sdma_channel *sdmac = to_sdma_chan(chan);
 	struct sdma_engine *sdma = sdmac->sdma;
 
-	sdma_disable_channel_async(chan);
+	sdma_terminate_all(chan);
 
 	sdma_channel_synchronize(chan);
 
-	if (sdmac->event_id0)
+	if (sdmac->event_id0 >= 0)
 		sdma_event_disable(sdmac, sdmac->event_id0);
 	if (sdmac->event_id1)
 		sdma_event_disable(sdmac, sdmac->event_id1);
 
 	sdmac->event_id0 = 0;
 	sdmac->event_id1 = 0;
+	sdmac->context_loaded = false;
 
 	sdma_set_channel_priority(sdmac, 0);
 
@@ -1628,7 +1632,7 @@ static int sdma_config(struct dma_chan *chan,
 	memcpy(&sdmac->slave_config, dmaengine_cfg, sizeof(*dmaengine_cfg));
 
 	/* Set ENBLn earlier to make sure dma request triggered after that */
-	if (sdmac->event_id0) {
+	if (sdmac->event_id0 >= 0) {
 		if (sdmac->event_id0 >= sdmac->sdma->drvdata->num_events)
 			return -EINVAL;
 		sdma_event_enable(sdmac, sdmac->event_id0);
@@ -1648,7 +1652,7 @@ static enum dma_status sdma_tx_status(struct dma_chan *chan,
 				      struct dma_tx_state *txstate)
 {
 	struct sdma_channel *sdmac = to_sdma_chan(chan);
-	struct sdma_desc *desc;
+	struct sdma_desc *desc = NULL;
 	u32 residue;
 	struct virt_dma_desc *vd;
 	enum dma_status ret;
@@ -1659,19 +1663,23 @@ static enum dma_status sdma_tx_status(struct dma_chan *chan,
 		return ret;
 
 	spin_lock_irqsave(&sdmac->vc.lock, flags);
+
 	vd = vchan_find_desc(&sdmac->vc, cookie);
-	if (vd) {
+	if (vd)
 		desc = to_sdma_desc(&vd->tx);
+	else if (sdmac->desc && sdmac->desc->vd.tx.cookie == cookie)
+		desc = sdmac->desc;
+
+	if (desc) {
 		if (sdmac->flags & IMX_DMA_SG_LOOP)
 			residue = (desc->num_bd - desc->buf_ptail) *
 				desc->period_len - desc->chn_real_count;
 		else
 			residue = desc->chn_count - desc->chn_real_count;
-	} else if (sdmac->desc && sdmac->desc->vd.tx.cookie == cookie) {
-		residue = sdmac->desc->chn_count - sdmac->desc->chn_real_count;
 	} else {
 		residue = 0;
 	}
+
 	spin_unlock_irqrestore(&sdmac->vc.lock, flags);
 
 	dma_set_tx_state(txstate, chan->completed_cookie, chan->cookie,
@@ -2103,7 +2111,7 @@ static int sdma_probe(struct platform_device *pdev)
 	sdma->dma_device.device_prep_slave_sg = sdma_prep_slave_sg;
 	sdma->dma_device.device_prep_dma_cyclic = sdma_prep_dma_cyclic;
 	sdma->dma_device.device_config = sdma_config;
-	sdma->dma_device.device_terminate_all = sdma_disable_channel_async;
+	sdma->dma_device.device_terminate_all = sdma_terminate_all;
 	sdma->dma_device.device_synchronize = sdma_channel_synchronize;
 	sdma->dma_device.src_addr_widths = SDMA_DMA_BUSWIDTHS;
 	sdma->dma_device.dst_addr_widths = SDMA_DMA_BUSWIDTHS;
diff --git a/drivers/dma/ioat/init.c b/drivers/dma/ioat/init.c
index a6a6dc432db8..60e9afbb896c 100644
--- a/drivers/dma/ioat/init.c
+++ b/drivers/dma/ioat/init.c
@@ -556,10 +556,6 @@ static void ioat_dma_remove(struct ioatdma_device *ioat_dma)
 	ioat_kobject_del(ioat_dma);
 
 	dma_async_device_unregister(dma);
-
-	dma_pool_destroy(ioat_dma->completion_pool);
-
-	INIT_LIST_HEAD(&dma->channels);
 }
 
 /**
@@ -589,7 +585,7 @@ static void ioat_enumerate_channels(struct ioatdma_device *ioat_dma)
 	dev_dbg(dev, "%s: xfercap = %d\n", __func__, 1 << xfercap_log);
 
 	for (i = 0; i < dma->chancnt; i++) {
-		ioat_chan = devm_kzalloc(dev, sizeof(*ioat_chan), GFP_KERNEL);
+		ioat_chan = kzalloc(sizeof(*ioat_chan), GFP_KERNEL);
 		if (!ioat_chan)
 			break;
 
@@ -624,12 +620,16 @@ static void ioat_free_chan_resources(struct dma_chan *c)
 		return;
 
 	ioat_stop(ioat_chan);
-	ioat_reset_hw(ioat_chan);
 
-	/* Put LTR to idle */
-	if (ioat_dma->version >= IOAT_VER_3_4)
-		writeb(IOAT_CHAN_LTR_SWSEL_IDLE,
-			ioat_chan->reg_base + IOAT_CHAN_LTR_SWSEL_OFFSET);
+	if (!test_bit(IOAT_CHAN_DOWN, &ioat_chan->state)) {
+		ioat_reset_hw(ioat_chan);
+
+		/* Put LTR to idle */
+		if (ioat_dma->version >= IOAT_VER_3_4)
+			writeb(IOAT_CHAN_LTR_SWSEL_IDLE,
+			       ioat_chan->reg_base +
+			       IOAT_CHAN_LTR_SWSEL_OFFSET);
+	}
 
 	spin_lock_bh(&ioat_chan->cleanup_lock);
 	spin_lock_bh(&ioat_chan->prep_lock);
@@ -1322,16 +1322,28 @@ static struct pci_driver ioat_pci_driver = {
 	.err_handler	= &ioat_err_handler,
 };
 
+static void release_ioatdma(struct dma_device *device)
+{
+	struct ioatdma_device *d = to_ioatdma_device(device);
+	int i;
+
+	for (i = 0; i < IOAT_MAX_CHANS; i++)
+		kfree(d->idx[i]);
+
+	dma_pool_destroy(d->completion_pool);
+	kfree(d);
+}
+
 static struct ioatdma_device *
 alloc_ioatdma(struct pci_dev *pdev, void __iomem *iobase)
 {
-	struct device *dev = &pdev->dev;
-	struct ioatdma_device *d = devm_kzalloc(dev, sizeof(*d), GFP_KERNEL);
+	struct ioatdma_device *d = kzalloc(sizeof(*d), GFP_KERNEL);
 
 	if (!d)
 		return NULL;
 	d->pdev = pdev;
 	d->reg_base = iobase;
+	d->dma_dev.device_release = release_ioatdma;
 	return d;
 }
 
@@ -1400,6 +1412,8 @@ static void ioat_remove(struct pci_dev *pdev)
 	if (!device)
 		return;
 
+	ioat_shutdown(pdev);
+
 	dev_err(&pdev->dev, "Removing dma and dca services\n");
 	if (device->dca) {
 		unregister_dca_provider(device->dca, &pdev->dev);
diff --git a/drivers/dma/mediatek/mtk-uart-apdma.c b/drivers/dma/mediatek/mtk-uart-apdma.c
index c20e6bd4e298..29f1223b285a 100644
--- a/drivers/dma/mediatek/mtk-uart-apdma.c
+++ b/drivers/dma/mediatek/mtk-uart-apdma.c
@@ -430,9 +430,10 @@ static int mtk_uart_apdma_terminate_all(struct dma_chan *chan)
 
 	spin_lock_irqsave(&c->vc.lock, flags);
 	vchan_get_all_descriptors(&c->vc, &head);
-	vchan_dma_desc_free_list(&c->vc, &head);
 	spin_unlock_irqrestore(&c->vc.lock, flags);
 
+	vchan_dma_desc_free_list(&c->vc, &head);
+
 	return 0;
 }
 
diff --git a/drivers/dma/mv_xor_v2.c b/drivers/dma/mv_xor_v2.c
index e3850f04f676..157c959311ea 100644
--- a/drivers/dma/mv_xor_v2.c
+++ b/drivers/dma/mv_xor_v2.c
@@ -750,7 +750,7 @@ static int mv_xor_v2_probe(struct platform_device *pdev)
 	}
 
 	xor_dev->clk = devm_clk_get(&pdev->dev, NULL);
-	if (IS_ERR(xor_dev->clk) && PTR_ERR(xor_dev->clk) == -EPROBE_DEFER) {
+	if (PTR_ERR(xor_dev->clk) == -EPROBE_DEFER) {
 		ret = EPROBE_DEFER;
 		goto disable_reg_clk;
 	}
diff --git a/drivers/dma/of-dma.c b/drivers/dma/of-dma.c
index c2d779daa4b5..b2c2b5e8093c 100644
--- a/drivers/dma/of-dma.c
+++ b/drivers/dma/of-dma.c
@@ -15,6 +15,8 @@
 #include <linux/of.h>
 #include <linux/of_dma.h>
 
+#include "dmaengine.h"
+
 static LIST_HEAD(of_dma_list);
 static DEFINE_MUTEX(of_dma_lock);
 
diff --git a/drivers/dma/owl-dma.c b/drivers/dma/owl-dma.c
index 023f951189a7..c683051257fd 100644
--- a/drivers/dma/owl-dma.c
+++ b/drivers/dma/owl-dma.c
@@ -674,10 +674,11 @@ static int owl_dma_terminate_all(struct dma_chan *chan)
 	}
 
 	vchan_get_all_descriptors(&vchan->vc, &head);
-	vchan_dma_desc_free_list(&vchan->vc, &head);
 
 	spin_unlock_irqrestore(&vchan->vc.lock, flags);
 
+	vchan_dma_desc_free_list(&vchan->vc, &head);
+
 	return 0;
 }
 
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index 6cce9ef61b29..88b884cbb7c1 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -2961,12 +2961,7 @@ static int __maybe_unused pl330_suspend(struct device *dev)
 {
 	struct amba_device *pcdev = to_amba_device(dev);
 
-	pm_runtime_disable(dev);
-
-	if (!pm_runtime_status_suspended(dev)) {
-		/* amba did not disable the clock */
-		amba_pclk_disable(pcdev);
-	}
+	pm_runtime_force_suspend(dev);
 	amba_pclk_unprepare(pcdev);
 
 	return 0;
@@ -2981,15 +2976,14 @@ static int __maybe_unused pl330_resume(struct device *dev)
 	if (ret)
 		return ret;
 
-	if (!pm_runtime_status_suspended(dev))
-		ret = amba_pclk_enable(pcdev);
-
-	pm_runtime_enable(dev);
+	pm_runtime_force_resume(dev);
 
 	return ret;
 }
 
-static SIMPLE_DEV_PM_OPS(pl330_pm, pl330_suspend, pl330_resume);
+static const struct dev_pm_ops pl330_pm = {
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(pl330_suspend, pl330_resume)
+};
 
 static int
 pl330_probe(struct amba_device *adev, const struct amba_id *id)
diff --git a/drivers/dma/plx_dma.c b/drivers/dma/plx_dma.c
new file mode 100644
index 000000000000..db4c5fd453a9
--- /dev/null
+++ b/drivers/dma/plx_dma.c
@@ -0,0 +1,639 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Microsemi Switchtec(tm) PCIe Management Driver
+ * Copyright (c) 2019, Logan Gunthorpe <logang@deltatee.com>
+ * Copyright (c) 2019, GigaIO Networks, Inc
+ */
+
+#include "dmaengine.h"
+
+#include <linux/circ_buf.h>
+#include <linux/dmaengine.h>
+#include <linux/kref.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+
+MODULE_DESCRIPTION("PLX ExpressLane PEX PCI Switch DMA Engine");
+MODULE_VERSION("0.1");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Logan Gunthorpe");
+
+#define PLX_REG_DESC_RING_ADDR			0x214
+#define PLX_REG_DESC_RING_ADDR_HI		0x218
+#define PLX_REG_DESC_RING_NEXT_ADDR		0x21C
+#define PLX_REG_DESC_RING_COUNT			0x220
+#define PLX_REG_DESC_RING_LAST_ADDR		0x224
+#define PLX_REG_DESC_RING_LAST_SIZE		0x228
+#define PLX_REG_PREF_LIMIT			0x234
+#define PLX_REG_CTRL				0x238
+#define PLX_REG_CTRL2				0x23A
+#define PLX_REG_INTR_CTRL			0x23C
+#define PLX_REG_INTR_STATUS			0x23E
+
+#define PLX_REG_PREF_LIMIT_PREF_FOUR		8
+
+#define PLX_REG_CTRL_GRACEFUL_PAUSE		BIT(0)
+#define PLX_REG_CTRL_ABORT			BIT(1)
+#define PLX_REG_CTRL_WRITE_BACK_EN		BIT(2)
+#define PLX_REG_CTRL_START			BIT(3)
+#define PLX_REG_CTRL_RING_STOP_MODE		BIT(4)
+#define PLX_REG_CTRL_DESC_MODE_BLOCK		(0 << 5)
+#define PLX_REG_CTRL_DESC_MODE_ON_CHIP		(1 << 5)
+#define PLX_REG_CTRL_DESC_MODE_OFF_CHIP		(2 << 5)
+#define PLX_REG_CTRL_DESC_INVALID		BIT(8)
+#define PLX_REG_CTRL_GRACEFUL_PAUSE_DONE	BIT(9)
+#define PLX_REG_CTRL_ABORT_DONE			BIT(10)
+#define PLX_REG_CTRL_IMM_PAUSE_DONE		BIT(12)
+#define PLX_REG_CTRL_IN_PROGRESS		BIT(30)
+
+#define PLX_REG_CTRL_RESET_VAL	(PLX_REG_CTRL_DESC_INVALID | \
+				 PLX_REG_CTRL_GRACEFUL_PAUSE_DONE | \
+				 PLX_REG_CTRL_ABORT_DONE | \
+				 PLX_REG_CTRL_IMM_PAUSE_DONE)
+
+#define PLX_REG_CTRL_START_VAL	(PLX_REG_CTRL_WRITE_BACK_EN | \
+				 PLX_REG_CTRL_DESC_MODE_OFF_CHIP | \
+				 PLX_REG_CTRL_START | \
+				 PLX_REG_CTRL_RESET_VAL)
+
+#define PLX_REG_CTRL2_MAX_TXFR_SIZE_64B		0
+#define PLX_REG_CTRL2_MAX_TXFR_SIZE_128B	1
+#define PLX_REG_CTRL2_MAX_TXFR_SIZE_256B	2
+#define PLX_REG_CTRL2_MAX_TXFR_SIZE_512B	3
+#define PLX_REG_CTRL2_MAX_TXFR_SIZE_1KB		4
+#define PLX_REG_CTRL2_MAX_TXFR_SIZE_2KB		5
+#define PLX_REG_CTRL2_MAX_TXFR_SIZE_4B		7
+
+#define PLX_REG_INTR_CRTL_ERROR_EN		BIT(0)
+#define PLX_REG_INTR_CRTL_INV_DESC_EN		BIT(1)
+#define PLX_REG_INTR_CRTL_ABORT_DONE_EN		BIT(3)
+#define PLX_REG_INTR_CRTL_PAUSE_DONE_EN		BIT(4)
+#define PLX_REG_INTR_CRTL_IMM_PAUSE_DONE_EN	BIT(5)
+
+#define PLX_REG_INTR_STATUS_ERROR		BIT(0)
+#define PLX_REG_INTR_STATUS_INV_DESC		BIT(1)
+#define PLX_REG_INTR_STATUS_DESC_DONE		BIT(2)
+#define PLX_REG_INTR_CRTL_ABORT_DONE		BIT(3)
+
+struct plx_dma_hw_std_desc {
+	__le32 flags_and_size;
+	__le16 dst_addr_hi;
+	__le16 src_addr_hi;
+	__le32 dst_addr_lo;
+	__le32 src_addr_lo;
+};
+
+#define PLX_DESC_SIZE_MASK		0x7ffffff
+#define PLX_DESC_FLAG_VALID		BIT(31)
+#define PLX_DESC_FLAG_INT_WHEN_DONE	BIT(30)
+
+#define PLX_DESC_WB_SUCCESS		BIT(30)
+#define PLX_DESC_WB_RD_FAIL		BIT(29)
+#define PLX_DESC_WB_WR_FAIL		BIT(28)
+
+#define PLX_DMA_RING_COUNT		2048
+
+struct plx_dma_desc {
+	struct dma_async_tx_descriptor txd;
+	struct plx_dma_hw_std_desc *hw;
+	u32 orig_size;
+};
+
+struct plx_dma_dev {
+	struct dma_device dma_dev;
+	struct dma_chan dma_chan;
+	struct pci_dev __rcu *pdev;
+	void __iomem *bar;
+	struct tasklet_struct desc_task;
+
+	spinlock_t ring_lock;
+	bool ring_active;
+	int head;
+	int tail;
+	struct plx_dma_hw_std_desc *hw_ring;
+	dma_addr_t hw_ring_dma;
+	struct plx_dma_desc **desc_ring;
+};
+
+static struct plx_dma_dev *chan_to_plx_dma_dev(struct dma_chan *c)
+{
+	return container_of(c, struct plx_dma_dev, dma_chan);
+}
+
+static struct plx_dma_desc *to_plx_desc(struct dma_async_tx_descriptor *txd)
+{
+	return container_of(txd, struct plx_dma_desc, txd);
+}
+
+static struct plx_dma_desc *plx_dma_get_desc(struct plx_dma_dev *plxdev, int i)
+{
+	return plxdev->desc_ring[i & (PLX_DMA_RING_COUNT - 1)];
+}
+
+static void plx_dma_process_desc(struct plx_dma_dev *plxdev)
+{
+	struct dmaengine_result res;
+	struct plx_dma_desc *desc;
+	u32 flags;
+
+	spin_lock_bh(&plxdev->ring_lock);
+
+	while (plxdev->tail != plxdev->head) {
+		desc = plx_dma_get_desc(plxdev, plxdev->tail);
+
+		flags = le32_to_cpu(READ_ONCE(desc->hw->flags_and_size));
+
+		if (flags & PLX_DESC_FLAG_VALID)
+			break;
+
+		res.residue = desc->orig_size - (flags & PLX_DESC_SIZE_MASK);
+
+		if (flags & PLX_DESC_WB_SUCCESS)
+			res.result = DMA_TRANS_NOERROR;
+		else if (flags & PLX_DESC_WB_WR_FAIL)
+			res.result = DMA_TRANS_WRITE_FAILED;
+		else
+			res.result = DMA_TRANS_READ_FAILED;
+
+		dma_cookie_complete(&desc->txd);
+		dma_descriptor_unmap(&desc->txd);
+		dmaengine_desc_get_callback_invoke(&desc->txd, &res);
+		desc->txd.callback = NULL;
+		desc->txd.callback_result = NULL;
+
+		plxdev->tail++;
+	}
+
+	spin_unlock_bh(&plxdev->ring_lock);
+}
+
+static void plx_dma_abort_desc(struct plx_dma_dev *plxdev)
+{
+	struct dmaengine_result res;
+	struct plx_dma_desc *desc;
+
+	plx_dma_process_desc(plxdev);
+
+	spin_lock_bh(&plxdev->ring_lock);
+
+	while (plxdev->tail != plxdev->head) {
+		desc = plx_dma_get_desc(plxdev, plxdev->tail);
+
+		res.residue = desc->orig_size;
+		res.result = DMA_TRANS_ABORTED;
+
+		dma_cookie_complete(&desc->txd);
+		dma_descriptor_unmap(&desc->txd);
+		dmaengine_desc_get_callback_invoke(&desc->txd, &res);
+		desc->txd.callback = NULL;
+		desc->txd.callback_result = NULL;
+
+		plxdev->tail++;
+	}
+
+	spin_unlock_bh(&plxdev->ring_lock);
+}
+
+static void __plx_dma_stop(struct plx_dma_dev *plxdev)
+{
+	unsigned long timeout = jiffies + msecs_to_jiffies(1000);
+	u32 val;
+
+	val = readl(plxdev->bar + PLX_REG_CTRL);
+	if (!(val & ~PLX_REG_CTRL_GRACEFUL_PAUSE))
+		return;
+
+	writel(PLX_REG_CTRL_RESET_VAL | PLX_REG_CTRL_GRACEFUL_PAUSE,
+	       plxdev->bar + PLX_REG_CTRL);
+
+	while (!time_after(jiffies, timeout)) {
+		val = readl(plxdev->bar + PLX_REG_CTRL);
+		if (val & PLX_REG_CTRL_GRACEFUL_PAUSE_DONE)
+			break;
+
+		cpu_relax();
+	}
+
+	if (!(val & PLX_REG_CTRL_GRACEFUL_PAUSE_DONE))
+		dev_err(plxdev->dma_dev.dev,
+			"Timeout waiting for graceful pause!\n");
+
+	writel(PLX_REG_CTRL_RESET_VAL | PLX_REG_CTRL_GRACEFUL_PAUSE,
+	       plxdev->bar + PLX_REG_CTRL);
+
+	writel(0, plxdev->bar + PLX_REG_DESC_RING_COUNT);
+	writel(0, plxdev->bar + PLX_REG_DESC_RING_ADDR);
+	writel(0, plxdev->bar + PLX_REG_DESC_RING_ADDR_HI);
+	writel(0, plxdev->bar + PLX_REG_DESC_RING_NEXT_ADDR);
+}
+
+static void plx_dma_stop(struct plx_dma_dev *plxdev)
+{
+	rcu_read_lock();
+	if (!rcu_dereference(plxdev->pdev)) {
+		rcu_read_unlock();
+		return;
+	}
+
+	__plx_dma_stop(plxdev);
+
+	rcu_read_unlock();
+}
+
+static void plx_dma_desc_task(unsigned long data)
+{
+	struct plx_dma_dev *plxdev = (void *)data;
+
+	plx_dma_process_desc(plxdev);
+}
+
+static struct dma_async_tx_descriptor *plx_dma_prep_memcpy(struct dma_chan *c,
+		dma_addr_t dma_dst, dma_addr_t dma_src, size_t len,
+		unsigned long flags)
+	__acquires(plxdev->ring_lock)
+{
+	struct plx_dma_dev *plxdev = chan_to_plx_dma_dev(c);
+	struct plx_dma_desc *plxdesc;
+
+	spin_lock_bh(&plxdev->ring_lock);
+	if (!plxdev->ring_active)
+		goto err_unlock;
+
+	if (!CIRC_SPACE(plxdev->head, plxdev->tail, PLX_DMA_RING_COUNT))
+		goto err_unlock;
+
+	if (len > PLX_DESC_SIZE_MASK)
+		goto err_unlock;
+
+	plxdesc = plx_dma_get_desc(plxdev, plxdev->head);
+	plxdev->head++;
+
+	plxdesc->hw->dst_addr_lo = cpu_to_le32(lower_32_bits(dma_dst));
+	plxdesc->hw->dst_addr_hi = cpu_to_le16(upper_32_bits(dma_dst));
+	plxdesc->hw->src_addr_lo = cpu_to_le32(lower_32_bits(dma_src));
+	plxdesc->hw->src_addr_hi = cpu_to_le16(upper_32_bits(dma_src));
+
+	plxdesc->orig_size = len;
+
+	if (flags & DMA_PREP_INTERRUPT)
+		len |= PLX_DESC_FLAG_INT_WHEN_DONE;
+
+	plxdesc->hw->flags_and_size = cpu_to_le32(len);
+	plxdesc->txd.flags = flags;
+
+	/* return with the lock held, it will be released in tx_submit */
+
+	return &plxdesc->txd;
+
+err_unlock:
+	/*
+	 * Keep sparse happy by restoring an even lock count on
+	 * this lock.
+	 */
+	__acquire(plxdev->ring_lock);
+
+	spin_unlock_bh(&plxdev->ring_lock);
+	return NULL;
+}
+
+static dma_cookie_t plx_dma_tx_submit(struct dma_async_tx_descriptor *desc)
+	__releases(plxdev->ring_lock)
+{
+	struct plx_dma_dev *plxdev = chan_to_plx_dma_dev(desc->chan);
+	struct plx_dma_desc *plxdesc = to_plx_desc(desc);
+	dma_cookie_t cookie;
+
+	cookie = dma_cookie_assign(desc);
+
+	/*
+	 * Ensure the descriptor updates are visible to the dma device
+	 * before setting the valid bit.
+	 */
+	wmb();
+
+	plxdesc->hw->flags_and_size |= cpu_to_le32(PLX_DESC_FLAG_VALID);
+
+	spin_unlock_bh(&plxdev->ring_lock);
+
+	return cookie;
+}
+
+static enum dma_status plx_dma_tx_status(struct dma_chan *chan,
+		dma_cookie_t cookie, struct dma_tx_state *txstate)
+{
+	struct plx_dma_dev *plxdev = chan_to_plx_dma_dev(chan);
+	enum dma_status ret;
+
+	ret = dma_cookie_status(chan, cookie, txstate);
+	if (ret == DMA_COMPLETE)
+		return ret;
+
+	plx_dma_process_desc(plxdev);
+
+	return dma_cookie_status(chan, cookie, txstate);
+}
+
+static void plx_dma_issue_pending(struct dma_chan *chan)
+{
+	struct plx_dma_dev *plxdev = chan_to_plx_dma_dev(chan);
+
+	rcu_read_lock();
+	if (!rcu_dereference(plxdev->pdev)) {
+		rcu_read_unlock();
+		return;
+	}
+
+	/*
+	 * Ensure the valid bits are visible before starting the
+	 * DMA engine.
+	 */
+	wmb();
+
+	writew(PLX_REG_CTRL_START_VAL, plxdev->bar + PLX_REG_CTRL);
+
+	rcu_read_unlock();
+}
+
+static irqreturn_t plx_dma_isr(int irq, void *devid)
+{
+	struct plx_dma_dev *plxdev = devid;
+	u32 status;
+
+	status = readw(plxdev->bar + PLX_REG_INTR_STATUS);
+
+	if (!status)
+		return IRQ_NONE;
+
+	if (status & PLX_REG_INTR_STATUS_DESC_DONE && plxdev->ring_active)
+		tasklet_schedule(&plxdev->desc_task);
+
+	writew(status, plxdev->bar + PLX_REG_INTR_STATUS);
+
+	return IRQ_HANDLED;
+}
+
+static int plx_dma_alloc_desc(struct plx_dma_dev *plxdev)
+{
+	struct plx_dma_desc *desc;
+	int i;
+
+	plxdev->desc_ring = kcalloc(PLX_DMA_RING_COUNT,
+				    sizeof(*plxdev->desc_ring), GFP_KERNEL);
+	if (!plxdev->desc_ring)
+		return -ENOMEM;
+
+	for (i = 0; i < PLX_DMA_RING_COUNT; i++) {
+		desc = kzalloc(sizeof(*desc), GFP_KERNEL);
+		if (!desc)
+			goto free_and_exit;
+
+		dma_async_tx_descriptor_init(&desc->txd, &plxdev->dma_chan);
+		desc->txd.tx_submit = plx_dma_tx_submit;
+		desc->hw = &plxdev->hw_ring[i];
+
+		plxdev->desc_ring[i] = desc;
+	}
+
+	return 0;
+
+free_and_exit:
+	for (i = 0; i < PLX_DMA_RING_COUNT; i++)
+		kfree(plxdev->desc_ring[i]);
+	kfree(plxdev->desc_ring);
+	return -ENOMEM;
+}
+
+static int plx_dma_alloc_chan_resources(struct dma_chan *chan)
+{
+	struct plx_dma_dev *plxdev = chan_to_plx_dma_dev(chan);
+	size_t ring_sz = PLX_DMA_RING_COUNT * sizeof(*plxdev->hw_ring);
+	int rc;
+
+	plxdev->head = plxdev->tail = 0;
+	plxdev->hw_ring = dma_alloc_coherent(plxdev->dma_dev.dev, ring_sz,
+					     &plxdev->hw_ring_dma, GFP_KERNEL);
+	if (!plxdev->hw_ring)
+		return -ENOMEM;
+
+	rc = plx_dma_alloc_desc(plxdev);
+	if (rc)
+		goto out_free_hw_ring;
+
+	rcu_read_lock();
+	if (!rcu_dereference(plxdev->pdev)) {
+		rcu_read_unlock();
+		rc = -ENODEV;
+		goto out_free_hw_ring;
+	}
+
+	writel(PLX_REG_CTRL_RESET_VAL, plxdev->bar + PLX_REG_CTRL);
+	writel(lower_32_bits(plxdev->hw_ring_dma),
+	       plxdev->bar + PLX_REG_DESC_RING_ADDR);
+	writel(upper_32_bits(plxdev->hw_ring_dma),
+	       plxdev->bar + PLX_REG_DESC_RING_ADDR_HI);
+	writel(lower_32_bits(plxdev->hw_ring_dma),
+	       plxdev->bar + PLX_REG_DESC_RING_NEXT_ADDR);
+	writel(PLX_DMA_RING_COUNT, plxdev->bar + PLX_REG_DESC_RING_COUNT);
+	writel(PLX_REG_PREF_LIMIT_PREF_FOUR, plxdev->bar + PLX_REG_PREF_LIMIT);
+
+	plxdev->ring_active = true;
+
+	rcu_read_unlock();
+
+	return PLX_DMA_RING_COUNT;
+
+out_free_hw_ring:
+	dma_free_coherent(plxdev->dma_dev.dev, ring_sz, plxdev->hw_ring,
+			  plxdev->hw_ring_dma);
+	return rc;
+}
+
+static void plx_dma_free_chan_resources(struct dma_chan *chan)
+{
+	struct plx_dma_dev *plxdev = chan_to_plx_dma_dev(chan);
+	size_t ring_sz = PLX_DMA_RING_COUNT * sizeof(*plxdev->hw_ring);
+	struct pci_dev *pdev;
+	int irq = -1;
+	int i;
+
+	spin_lock_bh(&plxdev->ring_lock);
+	plxdev->ring_active = false;
+	spin_unlock_bh(&plxdev->ring_lock);
+
+	plx_dma_stop(plxdev);
+
+	rcu_read_lock();
+	pdev = rcu_dereference(plxdev->pdev);
+	if (pdev)
+		irq = pci_irq_vector(pdev, 0);
+	rcu_read_unlock();
+
+	if (irq > 0)
+		synchronize_irq(irq);
+
+	tasklet_kill(&plxdev->desc_task);
+
+	plx_dma_abort_desc(plxdev);
+
+	for (i = 0; i < PLX_DMA_RING_COUNT; i++)
+		kfree(plxdev->desc_ring[i]);
+
+	kfree(plxdev->desc_ring);
+	dma_free_coherent(plxdev->dma_dev.dev, ring_sz, plxdev->hw_ring,
+			  plxdev->hw_ring_dma);
+
+}
+
+static void plx_dma_release(struct dma_device *dma_dev)
+{
+	struct plx_dma_dev *plxdev =
+		container_of(dma_dev, struct plx_dma_dev, dma_dev);
+
+	put_device(dma_dev->dev);
+	kfree(plxdev);
+}
+
+static int plx_dma_create(struct pci_dev *pdev)
+{
+	struct plx_dma_dev *plxdev;
+	struct dma_device *dma;
+	struct dma_chan *chan;
+	int rc;
+
+	plxdev = kzalloc(sizeof(*plxdev), GFP_KERNEL);
+	if (!plxdev)
+		return -ENOMEM;
+
+	rc = request_irq(pci_irq_vector(pdev, 0), plx_dma_isr, 0,
+			 KBUILD_MODNAME, plxdev);
+	if (rc) {
+		kfree(plxdev);
+		return rc;
+	}
+
+	spin_lock_init(&plxdev->ring_lock);
+	tasklet_init(&plxdev->desc_task, plx_dma_desc_task,
+		     (unsigned long)plxdev);
+
+	RCU_INIT_POINTER(plxdev->pdev, pdev);
+	plxdev->bar = pcim_iomap_table(pdev)[0];
+
+	dma = &plxdev->dma_dev;
+	dma->chancnt = 1;
+	INIT_LIST_HEAD(&dma->channels);
+	dma_cap_set(DMA_MEMCPY, dma->cap_mask);
+	dma->copy_align = DMAENGINE_ALIGN_1_BYTE;
+	dma->dev = get_device(&pdev->dev);
+
+	dma->device_alloc_chan_resources = plx_dma_alloc_chan_resources;
+	dma->device_free_chan_resources = plx_dma_free_chan_resources;
+	dma->device_prep_dma_memcpy = plx_dma_prep_memcpy;
+	dma->device_issue_pending = plx_dma_issue_pending;
+	dma->device_tx_status = plx_dma_tx_status;
+	dma->device_release = plx_dma_release;
+
+	chan = &plxdev->dma_chan;
+	chan->device = dma;
+	dma_cookie_init(chan);
+	list_add_tail(&chan->device_node, &dma->channels);
+
+	rc = dma_async_device_register(dma);
+	if (rc) {
+		pci_err(pdev, "Failed to register dma device: %d\n", rc);
+		free_irq(pci_irq_vector(pdev, 0),  plxdev);
+		kfree(plxdev);
+		return rc;
+	}
+
+	pci_set_drvdata(pdev, plxdev);
+
+	return 0;
+}
+
+static int plx_dma_probe(struct pci_dev *pdev,
+			 const struct pci_device_id *id)
+{
+	int rc;
+
+	rc = pcim_enable_device(pdev);
+	if (rc)
+		return rc;
+
+	rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(48));
+	if (rc)
+		rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+	if (rc)
+		return rc;
+
+	rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(48));
+	if (rc)
+		rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
+	if (rc)
+		return rc;
+
+	rc = pcim_iomap_regions(pdev, 1, KBUILD_MODNAME);
+	if (rc)
+		return rc;
+
+	rc = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES);
+	if (rc <= 0)
+		return rc;
+
+	pci_set_master(pdev);
+
+	rc = plx_dma_create(pdev);
+	if (rc)
+		goto err_free_irq_vectors;
+
+	pci_info(pdev, "PLX DMA Channel Registered\n");
+
+	return 0;
+
+err_free_irq_vectors:
+	pci_free_irq_vectors(pdev);
+	return rc;
+}
+
+static void plx_dma_remove(struct pci_dev *pdev)
+{
+	struct plx_dma_dev *plxdev = pci_get_drvdata(pdev);
+
+	free_irq(pci_irq_vector(pdev, 0),  plxdev);
+
+	rcu_assign_pointer(plxdev->pdev, NULL);
+	synchronize_rcu();
+
+	spin_lock_bh(&plxdev->ring_lock);
+	plxdev->ring_active = false;
+	spin_unlock_bh(&plxdev->ring_lock);
+
+	__plx_dma_stop(plxdev);
+	plx_dma_abort_desc(plxdev);
+
+	plxdev->bar = NULL;
+	dma_async_device_unregister(&plxdev->dma_dev);
+
+	pci_free_irq_vectors(pdev);
+}
+
+static const struct pci_device_id plx_dma_pci_tbl[] = {
+	{
+		.vendor		= PCI_VENDOR_ID_PLX,
+		.device		= 0x87D0,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.class		= PCI_CLASS_SYSTEM_OTHER << 8,
+		.class_mask	= 0xFFFFFFFF,
+	},
+	{0}
+};
+MODULE_DEVICE_TABLE(pci, plx_dma_pci_tbl);
+
+static struct pci_driver plx_dma_pci_driver = {
+	.name           = KBUILD_MODNAME,
+	.id_table       = plx_dma_pci_tbl,
+	.probe          = plx_dma_probe,
+	.remove		= plx_dma_remove,
+};
+module_pci_driver(plx_dma_pci_driver);
diff --git a/drivers/dma/s3c24xx-dma.c b/drivers/dma/s3c24xx-dma.c
index 43da8eeb18ef..8e14c72d03f0 100644
--- a/drivers/dma/s3c24xx-dma.c
+++ b/drivers/dma/s3c24xx-dma.c
@@ -519,15 +519,6 @@ static void s3c24xx_dma_start_next_txd(struct s3c24xx_dma_chan *s3cchan)
 	s3c24xx_dma_start_next_sg(s3cchan, txd);
 }
 
-static void s3c24xx_dma_free_txd_list(struct s3c24xx_dma_engine *s3cdma,
-				struct s3c24xx_dma_chan *s3cchan)
-{
-	LIST_HEAD(head);
-
-	vchan_get_all_descriptors(&s3cchan->vc, &head);
-	vchan_dma_desc_free_list(&s3cchan->vc, &head);
-}
-
 /*
  * Try to allocate a physical channel.  When successful, assign it to
  * this virtual channel, and initiate the next descriptor.  The
@@ -709,8 +700,9 @@ static int s3c24xx_dma_terminate_all(struct dma_chan *chan)
 {
 	struct s3c24xx_dma_chan *s3cchan = to_s3c24xx_dma_chan(chan);
 	struct s3c24xx_dma_engine *s3cdma = s3cchan->host;
+	LIST_HEAD(head);
 	unsigned long flags;
-	int ret = 0;
+	int ret;
 
 	spin_lock_irqsave(&s3cchan->vc.lock, flags);
 
@@ -734,7 +726,15 @@ static int s3c24xx_dma_terminate_all(struct dma_chan *chan)
 	}
 
 	/* Dequeue jobs not yet fired as well */
-	s3c24xx_dma_free_txd_list(s3cdma, s3cchan);
+
+	vchan_get_all_descriptors(&s3cchan->vc, &head);
+
+	spin_unlock_irqrestore(&s3cchan->vc.lock, flags);
+
+	vchan_dma_desc_free_list(&s3cchan->vc, &head);
+
+	return 0;
+
 unlock:
 	spin_unlock_irqrestore(&s3cchan->vc.lock, flags);
 
@@ -1198,7 +1198,7 @@ static int s3c24xx_dma_probe(struct platform_device *pdev)
 
 	/* Basic sanity check */
 	if (pdata->num_phy_channels > MAX_DMA_CHANNELS) {
-		dev_err(&pdev->dev, "to many dma channels %d, max %d\n",
+		dev_err(&pdev->dev, "too many dma channels %d, max %d\n",
 			pdata->num_phy_channels, MAX_DMA_CHANNELS);
 		return -EINVAL;
 	}
diff --git a/drivers/dma/sf-pdma/sf-pdma.c b/drivers/dma/sf-pdma/sf-pdma.c
index 465256fe8b1f..6d0bec947636 100644
--- a/drivers/dma/sf-pdma/sf-pdma.c
+++ b/drivers/dma/sf-pdma/sf-pdma.c
@@ -155,9 +155,9 @@ static void sf_pdma_free_chan_resources(struct dma_chan *dchan)
 	kfree(chan->desc);
 	chan->desc = NULL;
 	vchan_get_all_descriptors(&chan->vchan, &head);
-	vchan_dma_desc_free_list(&chan->vchan, &head);
 	sf_pdma_disclaim_chan(chan);
 	spin_unlock_irqrestore(&chan->vchan.lock, flags);
+	vchan_dma_desc_free_list(&chan->vchan, &head);
 }
 
 static size_t sf_pdma_desc_residue(struct sf_pdma_chan *chan,
@@ -220,8 +220,8 @@ static int sf_pdma_terminate_all(struct dma_chan *dchan)
 	chan->desc = NULL;
 	chan->xfer_err = false;
 	vchan_get_all_descriptors(&chan->vchan, &head);
-	vchan_dma_desc_free_list(&chan->vchan, &head);
 	spin_unlock_irqrestore(&chan->vchan.lock, flags);
+	vchan_dma_desc_free_list(&chan->vchan, &head);
 
 	return 0;
 }
diff --git a/drivers/dma/sun4i-dma.c b/drivers/dma/sun4i-dma.c
index e397a50058c8..bbc2bda3b902 100644
--- a/drivers/dma/sun4i-dma.c
+++ b/drivers/dma/sun4i-dma.c
@@ -669,43 +669,41 @@ sun4i_dma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf, size_t len,
 	dma_addr_t src, dest;
 	u32 endpoints;
 	int nr_periods, offset, plength, i;
+	u8 ram_type, io_mode, linear_mode;
 
 	if (!is_slave_direction(dir)) {
 		dev_err(chan2dev(chan), "Invalid DMA direction\n");
 		return NULL;
 	}
 
-	if (vchan->is_dedicated) {
-		/*
-		 * As we are using this just for audio data, we need to use
-		 * normal DMA. There is nothing stopping us from supporting
-		 * dedicated DMA here as well, so if a client comes up and
-		 * requires it, it will be simple to implement it.
-		 */
-		dev_err(chan2dev(chan),
-			"Cyclic transfers are only supported on Normal DMA\n");
-		return NULL;
-	}
-
 	contract = generate_dma_contract();
 	if (!contract)
 		return NULL;
 
 	contract->is_cyclic = 1;
 
-	/* Figure out the endpoints and the address we need */
+	if (vchan->is_dedicated) {
+		io_mode = SUN4I_DDMA_ADDR_MODE_IO;
+		linear_mode = SUN4I_DDMA_ADDR_MODE_LINEAR;
+		ram_type = SUN4I_DDMA_DRQ_TYPE_SDRAM;
+	} else {
+		io_mode = SUN4I_NDMA_ADDR_MODE_IO;
+		linear_mode = SUN4I_NDMA_ADDR_MODE_LINEAR;
+		ram_type = SUN4I_NDMA_DRQ_TYPE_SDRAM;
+	}
+
 	if (dir == DMA_MEM_TO_DEV) {
 		src = buf;
 		dest = sconfig->dst_addr;
-		endpoints = SUN4I_DMA_CFG_SRC_DRQ_TYPE(SUN4I_NDMA_DRQ_TYPE_SDRAM) |
-			    SUN4I_DMA_CFG_DST_DRQ_TYPE(vchan->endpoint) |
-			    SUN4I_DMA_CFG_DST_ADDR_MODE(SUN4I_NDMA_ADDR_MODE_IO);
+		endpoints = SUN4I_DMA_CFG_DST_DRQ_TYPE(vchan->endpoint) |
+			    SUN4I_DMA_CFG_DST_ADDR_MODE(io_mode) |
+			    SUN4I_DMA_CFG_SRC_DRQ_TYPE(ram_type);
 	} else {
 		src = sconfig->src_addr;
 		dest = buf;
-		endpoints = SUN4I_DMA_CFG_SRC_DRQ_TYPE(vchan->endpoint) |
-			    SUN4I_DMA_CFG_SRC_ADDR_MODE(SUN4I_NDMA_ADDR_MODE_IO) |
-			    SUN4I_DMA_CFG_DST_DRQ_TYPE(SUN4I_NDMA_DRQ_TYPE_SDRAM);
+		endpoints = SUN4I_DMA_CFG_DST_DRQ_TYPE(ram_type) |
+			    SUN4I_DMA_CFG_SRC_DRQ_TYPE(vchan->endpoint) |
+			    SUN4I_DMA_CFG_SRC_ADDR_MODE(io_mode);
 	}
 
 	/*
@@ -747,8 +745,13 @@ sun4i_dma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf, size_t len,
 			dest = buf + offset;
 
 		/* Make the promise */
-		promise = generate_ndma_promise(chan, src, dest,
-						plength, sconfig, dir);
+		if (vchan->is_dedicated)
+			promise = generate_ddma_promise(chan, src, dest,
+							plength, sconfig);
+		else
+			promise = generate_ndma_promise(chan, src, dest,
+							plength, sconfig, dir);
+
 		if (!promise) {
 			/* TODO: should we free everything? */
 			return NULL;
@@ -885,12 +888,13 @@ static int sun4i_dma_terminate_all(struct dma_chan *chan)
 	}
 
 	spin_lock_irqsave(&vchan->vc.lock, flags);
-	vchan_dma_desc_free_list(&vchan->vc, &head);
 	/* Clear these so the vchan is usable again */
 	vchan->processing = NULL;
 	vchan->pchan = NULL;
 	spin_unlock_irqrestore(&vchan->vc.lock, flags);
 
+	vchan_dma_desc_free_list(&vchan->vc, &head);
+
 	return 0;
 }
 
diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c
index 3a45079d11ec..4a750e29bfb5 100644
--- a/drivers/dma/tegra20-apb-dma.c
+++ b/drivers/dma/tegra20-apb-dma.c
@@ -281,7 +281,7 @@ static struct tegra_dma_desc *tegra_dma_desc_get(
 
 	/* Do not allocate if desc are waiting for ack */
 	list_for_each_entry(dma_desc, &tdc->free_dma_desc, node) {
-		if (async_tx_test_ack(&dma_desc->txd)) {
+		if (async_tx_test_ack(&dma_desc->txd) && !dma_desc->cb_count) {
 			list_del(&dma_desc->node);
 			spin_unlock_irqrestore(&tdc->lock, flags);
 			dma_desc->txd.flags = 0;
@@ -756,10 +756,6 @@ static int tegra_dma_terminate_all(struct dma_chan *dc)
 	bool was_busy;
 
 	spin_lock_irqsave(&tdc->lock, flags);
-	if (list_empty(&tdc->pending_sg_req)) {
-		spin_unlock_irqrestore(&tdc->lock, flags);
-		return 0;
-	}
 
 	if (!tdc->busy)
 		goto skip_dma_stop;
diff --git a/drivers/dma/ti/Kconfig b/drivers/dma/ti/Kconfig
index d507c24fbf31..f76e06651f80 100644
--- a/drivers/dma/ti/Kconfig
+++ b/drivers/dma/ti/Kconfig
@@ -34,5 +34,29 @@ config DMA_OMAP
 	  Enable support for the TI sDMA (System DMA or DMA4) controller. This
 	  DMA engine is found on OMAP and DRA7xx parts.
 
+config TI_K3_UDMA
+	bool "Texas Instruments UDMA support"
+	depends on ARCH_K3 || COMPILE_TEST
+	depends on TI_SCI_PROTOCOL
+	depends on TI_SCI_INTA_IRQCHIP
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	select TI_K3_RINGACC
+	select TI_K3_PSIL
+        help
+	  Enable support for the TI UDMA (Unified DMA) controller. This
+	  DMA engine is used in AM65x and j721e.
+
+config TI_K3_UDMA_GLUE_LAYER
+	bool "Texas Instruments UDMA Glue layer for non DMAengine users"
+	depends on ARCH_K3 || COMPILE_TEST
+	depends on TI_K3_UDMA
+	help
+	  Say y here to support the K3 NAVSS DMA glue interface
+	  If unsure, say N.
+
+config TI_K3_PSIL
+	bool
+
 config TI_DMA_CROSSBAR
 	bool
diff --git a/drivers/dma/ti/Makefile b/drivers/dma/ti/Makefile
index 113e59ec9c32..9a29a107e374 100644
--- a/drivers/dma/ti/Makefile
+++ b/drivers/dma/ti/Makefile
@@ -2,4 +2,7 @@
 obj-$(CONFIG_TI_CPPI41) += cppi41.o
 obj-$(CONFIG_TI_EDMA) += edma.o
 obj-$(CONFIG_DMA_OMAP) += omap-dma.o
+obj-$(CONFIG_TI_K3_UDMA) += k3-udma.o
+obj-$(CONFIG_TI_K3_UDMA_GLUE_LAYER) += k3-udma-glue.o
+obj-$(CONFIG_TI_K3_PSIL) += k3-psil.o k3-psil-am654.o k3-psil-j721e.o
 obj-$(CONFIG_TI_DMA_CROSSBAR) += dma-crossbar.o
diff --git a/drivers/dma/ti/edma.c b/drivers/dma/ti/edma.c
index 756a3c951dc7..03a7f647f7b2 100644
--- a/drivers/dma/ti/edma.c
+++ b/drivers/dma/ti/edma.c
@@ -2289,13 +2289,6 @@ static int edma_probe(struct platform_device *pdev)
 	if (!info)
 		return -ENODEV;
 
-	pm_runtime_enable(dev);
-	ret = pm_runtime_get_sync(dev);
-	if (ret < 0) {
-		dev_err(dev, "pm_runtime_get_sync() failed\n");
-		return ret;
-	}
-
 	ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32));
 	if (ret)
 		return ret;
@@ -2326,27 +2319,33 @@ static int edma_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, ecc);
 
+	pm_runtime_enable(dev);
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0) {
+		dev_err(dev, "pm_runtime_get_sync() failed\n");
+		pm_runtime_disable(dev);
+		return ret;
+	}
+
 	/* Get eDMA3 configuration from IP */
 	ret = edma_setup_from_hw(dev, info, ecc);
 	if (ret)
-		return ret;
+		goto err_disable_pm;
 
 	/* Allocate memory based on the information we got from the IP */
 	ecc->slave_chans = devm_kcalloc(dev, ecc->num_channels,
 					sizeof(*ecc->slave_chans), GFP_KERNEL);
-	if (!ecc->slave_chans)
-		return -ENOMEM;
 
 	ecc->slot_inuse = devm_kcalloc(dev, BITS_TO_LONGS(ecc->num_slots),
 				       sizeof(unsigned long), GFP_KERNEL);
-	if (!ecc->slot_inuse)
-		return -ENOMEM;
 
 	ecc->channels_mask = devm_kcalloc(dev,
 					   BITS_TO_LONGS(ecc->num_channels),
 					   sizeof(unsigned long), GFP_KERNEL);
-	if (!ecc->channels_mask)
-		return -ENOMEM;
+	if (!ecc->slave_chans || !ecc->slot_inuse || !ecc->channels_mask) {
+		ret = -ENOMEM;
+		goto err_disable_pm;
+	}
 
 	/* Mark all channels available initially */
 	bitmap_fill(ecc->channels_mask, ecc->num_channels);
@@ -2388,7 +2387,7 @@ static int edma_probe(struct platform_device *pdev)
 				       ecc);
 		if (ret) {
 			dev_err(dev, "CCINT (%d) failed --> %d\n", irq, ret);
-			return ret;
+			goto err_disable_pm;
 		}
 		ecc->ccint = irq;
 	}
@@ -2404,7 +2403,7 @@ static int edma_probe(struct platform_device *pdev)
 				       ecc);
 		if (ret) {
 			dev_err(dev, "CCERRINT (%d) failed --> %d\n", irq, ret);
-			return ret;
+			goto err_disable_pm;
 		}
 		ecc->ccerrint = irq;
 	}
@@ -2412,7 +2411,8 @@ static int edma_probe(struct platform_device *pdev)
 	ecc->dummy_slot = edma_alloc_slot(ecc, EDMA_SLOT_ANY);
 	if (ecc->dummy_slot < 0) {
 		dev_err(dev, "Can't allocate PaRAM dummy slot\n");
-		return ecc->dummy_slot;
+		ret = ecc->dummy_slot;
+		goto err_disable_pm;
 	}
 
 	queue_priority_mapping = info->queue_priority_mapping;
@@ -2512,6 +2512,9 @@ static int edma_probe(struct platform_device *pdev)
 
 err_reg1:
 	edma_free_slot(ecc, ecc->dummy_slot);
+err_disable_pm:
+	pm_runtime_put_sync(dev);
+	pm_runtime_disable(dev);
 	return ret;
 }
 
@@ -2542,6 +2545,8 @@ static int edma_remove(struct platform_device *pdev)
 	if (ecc->dma_memcpy)
 		dma_async_device_unregister(ecc->dma_memcpy);
 	edma_free_slot(ecc, ecc->dummy_slot);
+	pm_runtime_put_sync(dev);
+	pm_runtime_disable(dev);
 
 	return 0;
 }
diff --git a/drivers/dma/ti/k3-psil-am654.c b/drivers/dma/ti/k3-psil-am654.c
new file mode 100644
index 000000000000..a896a15908cf
--- /dev/null
+++ b/drivers/dma/ti/k3-psil-am654.c
@@ -0,0 +1,175 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com
+ *  Author: Peter Ujfalusi <peter.ujfalusi@ti.com>
+ */
+
+#include <linux/kernel.h>
+
+#include "k3-psil-priv.h"
+
+#define PSIL_PDMA_XY_TR(x)				\
+	{						\
+		.thread_id = x,				\
+		.ep_config = {				\
+			.ep_type = PSIL_EP_PDMA_XY,	\
+		},					\
+	}
+
+#define PSIL_PDMA_XY_PKT(x)				\
+	{						\
+		.thread_id = x,				\
+		.ep_config = {				\
+			.ep_type = PSIL_EP_PDMA_XY,	\
+			.pkt_mode = 1,			\
+		},					\
+	}
+
+#define PSIL_ETHERNET(x)				\
+	{						\
+		.thread_id = x,				\
+		.ep_config = {				\
+			.ep_type = PSIL_EP_NATIVE,	\
+			.pkt_mode = 1,			\
+			.needs_epib = 1,		\
+			.psd_size = 16,			\
+		},					\
+	}
+
+#define PSIL_SA2UL(x, tx)				\
+	{						\
+		.thread_id = x,				\
+		.ep_config = {				\
+			.ep_type = PSIL_EP_NATIVE,	\
+			.pkt_mode = 1,			\
+			.needs_epib = 1,		\
+			.psd_size = 64,			\
+			.notdpkt = tx,			\
+		},					\
+	}
+
+/* PSI-L source thread IDs, used for RX (DMA_DEV_TO_MEM) */
+static struct psil_ep am654_src_ep_map[] = {
+	/* SA2UL */
+	PSIL_SA2UL(0x4000, 0),
+	PSIL_SA2UL(0x4001, 0),
+	PSIL_SA2UL(0x4002, 0),
+	PSIL_SA2UL(0x4003, 0),
+	/* PRU_ICSSG0 */
+	PSIL_ETHERNET(0x4100),
+	PSIL_ETHERNET(0x4101),
+	PSIL_ETHERNET(0x4102),
+	PSIL_ETHERNET(0x4103),
+	/* PRU_ICSSG1 */
+	PSIL_ETHERNET(0x4200),
+	PSIL_ETHERNET(0x4201),
+	PSIL_ETHERNET(0x4202),
+	PSIL_ETHERNET(0x4203),
+	/* PRU_ICSSG2 */
+	PSIL_ETHERNET(0x4300),
+	PSIL_ETHERNET(0x4301),
+	PSIL_ETHERNET(0x4302),
+	PSIL_ETHERNET(0x4303),
+	/* PDMA0 - McASPs */
+	PSIL_PDMA_XY_TR(0x4400),
+	PSIL_PDMA_XY_TR(0x4401),
+	PSIL_PDMA_XY_TR(0x4402),
+	/* PDMA1 - SPI0-4 */
+	PSIL_PDMA_XY_PKT(0x4500),
+	PSIL_PDMA_XY_PKT(0x4501),
+	PSIL_PDMA_XY_PKT(0x4502),
+	PSIL_PDMA_XY_PKT(0x4503),
+	PSIL_PDMA_XY_PKT(0x4504),
+	PSIL_PDMA_XY_PKT(0x4505),
+	PSIL_PDMA_XY_PKT(0x4506),
+	PSIL_PDMA_XY_PKT(0x4507),
+	PSIL_PDMA_XY_PKT(0x4508),
+	PSIL_PDMA_XY_PKT(0x4509),
+	PSIL_PDMA_XY_PKT(0x450a),
+	PSIL_PDMA_XY_PKT(0x450b),
+	PSIL_PDMA_XY_PKT(0x450c),
+	PSIL_PDMA_XY_PKT(0x450d),
+	PSIL_PDMA_XY_PKT(0x450e),
+	PSIL_PDMA_XY_PKT(0x450f),
+	PSIL_PDMA_XY_PKT(0x4510),
+	PSIL_PDMA_XY_PKT(0x4511),
+	PSIL_PDMA_XY_PKT(0x4512),
+	PSIL_PDMA_XY_PKT(0x4513),
+	/* PDMA1 - USART0-2 */
+	PSIL_PDMA_XY_PKT(0x4514),
+	PSIL_PDMA_XY_PKT(0x4515),
+	PSIL_PDMA_XY_PKT(0x4516),
+	/* CPSW0 */
+	PSIL_ETHERNET(0x7000),
+	/* MCU_PDMA0 - ADCs */
+	PSIL_PDMA_XY_TR(0x7100),
+	PSIL_PDMA_XY_TR(0x7101),
+	PSIL_PDMA_XY_TR(0x7102),
+	PSIL_PDMA_XY_TR(0x7103),
+	/* MCU_PDMA1 - MCU_SPI0-2 */
+	PSIL_PDMA_XY_PKT(0x7200),
+	PSIL_PDMA_XY_PKT(0x7201),
+	PSIL_PDMA_XY_PKT(0x7202),
+	PSIL_PDMA_XY_PKT(0x7203),
+	PSIL_PDMA_XY_PKT(0x7204),
+	PSIL_PDMA_XY_PKT(0x7205),
+	PSIL_PDMA_XY_PKT(0x7206),
+	PSIL_PDMA_XY_PKT(0x7207),
+	PSIL_PDMA_XY_PKT(0x7208),
+	PSIL_PDMA_XY_PKT(0x7209),
+	PSIL_PDMA_XY_PKT(0x720a),
+	PSIL_PDMA_XY_PKT(0x720b),
+	/* MCU_PDMA1 - MCU_USART0 */
+	PSIL_PDMA_XY_PKT(0x7212),
+};
+
+/* PSI-L destination thread IDs, used for TX (DMA_MEM_TO_DEV) */
+static struct psil_ep am654_dst_ep_map[] = {
+	/* SA2UL */
+	PSIL_SA2UL(0xc000, 1),
+	PSIL_SA2UL(0xc001, 1),
+	/* PRU_ICSSG0 */
+	PSIL_ETHERNET(0xc100),
+	PSIL_ETHERNET(0xc101),
+	PSIL_ETHERNET(0xc102),
+	PSIL_ETHERNET(0xc103),
+	PSIL_ETHERNET(0xc104),
+	PSIL_ETHERNET(0xc105),
+	PSIL_ETHERNET(0xc106),
+	PSIL_ETHERNET(0xc107),
+	/* PRU_ICSSG1 */
+	PSIL_ETHERNET(0xc200),
+	PSIL_ETHERNET(0xc201),
+	PSIL_ETHERNET(0xc202),
+	PSIL_ETHERNET(0xc203),
+	PSIL_ETHERNET(0xc204),
+	PSIL_ETHERNET(0xc205),
+	PSIL_ETHERNET(0xc206),
+	PSIL_ETHERNET(0xc207),
+	/* PRU_ICSSG2 */
+	PSIL_ETHERNET(0xc300),
+	PSIL_ETHERNET(0xc301),
+	PSIL_ETHERNET(0xc302),
+	PSIL_ETHERNET(0xc303),
+	PSIL_ETHERNET(0xc304),
+	PSIL_ETHERNET(0xc305),
+	PSIL_ETHERNET(0xc306),
+	PSIL_ETHERNET(0xc307),
+	/* CPSW0 */
+	PSIL_ETHERNET(0xf000),
+	PSIL_ETHERNET(0xf001),
+	PSIL_ETHERNET(0xf002),
+	PSIL_ETHERNET(0xf003),
+	PSIL_ETHERNET(0xf004),
+	PSIL_ETHERNET(0xf005),
+	PSIL_ETHERNET(0xf006),
+	PSIL_ETHERNET(0xf007),
+};
+
+struct psil_ep_map am654_ep_map = {
+	.name = "am654",
+	.src = am654_src_ep_map,
+	.src_count = ARRAY_SIZE(am654_src_ep_map),
+	.dst = am654_dst_ep_map,
+	.dst_count = ARRAY_SIZE(am654_dst_ep_map),
+};
diff --git a/drivers/dma/ti/k3-psil-j721e.c b/drivers/dma/ti/k3-psil-j721e.c
new file mode 100644
index 000000000000..e3cfd5f66842
--- /dev/null
+++ b/drivers/dma/ti/k3-psil-j721e.c
@@ -0,0 +1,222 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com
+ *  Author: Peter Ujfalusi <peter.ujfalusi@ti.com>
+ */
+
+#include <linux/kernel.h>
+
+#include "k3-psil-priv.h"
+
+#define PSIL_PDMA_XY_TR(x)				\
+	{						\
+		.thread_id = x,				\
+		.ep_config = {				\
+			.ep_type = PSIL_EP_PDMA_XY,	\
+		},					\
+	}
+
+#define PSIL_PDMA_XY_PKT(x)				\
+	{						\
+		.thread_id = x,				\
+		.ep_config = {				\
+			.ep_type = PSIL_EP_PDMA_XY,	\
+			.pkt_mode = 1,			\
+		},					\
+	}
+
+#define PSIL_PDMA_MCASP(x)				\
+	{						\
+		.thread_id = x,				\
+		.ep_config = {				\
+			.ep_type = PSIL_EP_PDMA_XY,	\
+			.pdma_acc32 = 1,		\
+			.pdma_burst = 1,		\
+		},					\
+	}
+
+#define PSIL_ETHERNET(x)				\
+	{						\
+		.thread_id = x,				\
+		.ep_config = {				\
+			.ep_type = PSIL_EP_NATIVE,	\
+			.pkt_mode = 1,			\
+			.needs_epib = 1,		\
+			.psd_size = 16,			\
+		},					\
+	}
+
+#define PSIL_SA2UL(x, tx)				\
+	{						\
+		.thread_id = x,				\
+		.ep_config = {				\
+			.ep_type = PSIL_EP_NATIVE,	\
+			.pkt_mode = 1,			\
+			.needs_epib = 1,		\
+			.psd_size = 64,			\
+			.notdpkt = tx,			\
+		},					\
+	}
+
+/* PSI-L source thread IDs, used for RX (DMA_DEV_TO_MEM) */
+static struct psil_ep j721e_src_ep_map[] = {
+	/* SA2UL */
+	PSIL_SA2UL(0x4000, 0),
+	PSIL_SA2UL(0x4001, 0),
+	PSIL_SA2UL(0x4002, 0),
+	PSIL_SA2UL(0x4003, 0),
+	/* PRU_ICSSG0 */
+	PSIL_ETHERNET(0x4100),
+	PSIL_ETHERNET(0x4101),
+	PSIL_ETHERNET(0x4102),
+	PSIL_ETHERNET(0x4103),
+	/* PRU_ICSSG1 */
+	PSIL_ETHERNET(0x4200),
+	PSIL_ETHERNET(0x4201),
+	PSIL_ETHERNET(0x4202),
+	PSIL_ETHERNET(0x4203),
+	/* PDMA6 (PSIL_PDMA_MCASP_G0) - McASP0-2 */
+	PSIL_PDMA_MCASP(0x4400),
+	PSIL_PDMA_MCASP(0x4401),
+	PSIL_PDMA_MCASP(0x4402),
+	/* PDMA7 (PSIL_PDMA_MCASP_G1) - McASP3-11 */
+	PSIL_PDMA_MCASP(0x4500),
+	PSIL_PDMA_MCASP(0x4501),
+	PSIL_PDMA_MCASP(0x4502),
+	PSIL_PDMA_MCASP(0x4503),
+	PSIL_PDMA_MCASP(0x4504),
+	PSIL_PDMA_MCASP(0x4505),
+	PSIL_PDMA_MCASP(0x4506),
+	PSIL_PDMA_MCASP(0x4507),
+	PSIL_PDMA_MCASP(0x4508),
+	/* PDMA8 (PDMA_MISC_G0) - SPI0-1 */
+	PSIL_PDMA_XY_PKT(0x4600),
+	PSIL_PDMA_XY_PKT(0x4601),
+	PSIL_PDMA_XY_PKT(0x4602),
+	PSIL_PDMA_XY_PKT(0x4603),
+	PSIL_PDMA_XY_PKT(0x4604),
+	PSIL_PDMA_XY_PKT(0x4605),
+	PSIL_PDMA_XY_PKT(0x4606),
+	PSIL_PDMA_XY_PKT(0x4607),
+	/* PDMA9 (PDMA_MISC_G1) - SPI2-3 */
+	PSIL_PDMA_XY_PKT(0x460c),
+	PSIL_PDMA_XY_PKT(0x460d),
+	PSIL_PDMA_XY_PKT(0x460e),
+	PSIL_PDMA_XY_PKT(0x460f),
+	PSIL_PDMA_XY_PKT(0x4610),
+	PSIL_PDMA_XY_PKT(0x4611),
+	PSIL_PDMA_XY_PKT(0x4612),
+	PSIL_PDMA_XY_PKT(0x4613),
+	/* PDMA10 (PDMA_MISC_G2) - SPI4-5 */
+	PSIL_PDMA_XY_PKT(0x4618),
+	PSIL_PDMA_XY_PKT(0x4619),
+	PSIL_PDMA_XY_PKT(0x461a),
+	PSIL_PDMA_XY_PKT(0x461b),
+	PSIL_PDMA_XY_PKT(0x461c),
+	PSIL_PDMA_XY_PKT(0x461d),
+	PSIL_PDMA_XY_PKT(0x461e),
+	PSIL_PDMA_XY_PKT(0x461f),
+	/* PDMA11 (PDMA_MISC_G3) */
+	PSIL_PDMA_XY_PKT(0x4624),
+	PSIL_PDMA_XY_PKT(0x4625),
+	PSIL_PDMA_XY_PKT(0x4626),
+	PSIL_PDMA_XY_PKT(0x4627),
+	PSIL_PDMA_XY_PKT(0x4628),
+	PSIL_PDMA_XY_PKT(0x4629),
+	PSIL_PDMA_XY_PKT(0x4630),
+	PSIL_PDMA_XY_PKT(0x463a),
+	/* PDMA13 (PDMA_USART_G0) - UART0-1 */
+	PSIL_PDMA_XY_PKT(0x4700),
+	PSIL_PDMA_XY_PKT(0x4701),
+	/* PDMA14 (PDMA_USART_G1) - UART2-3 */
+	PSIL_PDMA_XY_PKT(0x4702),
+	PSIL_PDMA_XY_PKT(0x4703),
+	/* PDMA15 (PDMA_USART_G2) - UART4-9 */
+	PSIL_PDMA_XY_PKT(0x4704),
+	PSIL_PDMA_XY_PKT(0x4705),
+	PSIL_PDMA_XY_PKT(0x4706),
+	PSIL_PDMA_XY_PKT(0x4707),
+	PSIL_PDMA_XY_PKT(0x4708),
+	PSIL_PDMA_XY_PKT(0x4709),
+	/* CPSW9 */
+	PSIL_ETHERNET(0x4a00),
+	/* CPSW0 */
+	PSIL_ETHERNET(0x7000),
+	/* MCU_PDMA0 (MCU_PDMA_MISC_G0) - SPI0 */
+	PSIL_PDMA_XY_PKT(0x7100),
+	PSIL_PDMA_XY_PKT(0x7101),
+	PSIL_PDMA_XY_PKT(0x7102),
+	PSIL_PDMA_XY_PKT(0x7103),
+	/* MCU_PDMA1 (MCU_PDMA_MISC_G1) - SPI1-2 */
+	PSIL_PDMA_XY_PKT(0x7200),
+	PSIL_PDMA_XY_PKT(0x7201),
+	PSIL_PDMA_XY_PKT(0x7202),
+	PSIL_PDMA_XY_PKT(0x7203),
+	PSIL_PDMA_XY_PKT(0x7204),
+	PSIL_PDMA_XY_PKT(0x7205),
+	PSIL_PDMA_XY_PKT(0x7206),
+	PSIL_PDMA_XY_PKT(0x7207),
+	/* MCU_PDMA2 (MCU_PDMA_MISC_G2) - UART0 */
+	PSIL_PDMA_XY_PKT(0x7300),
+	/* MCU_PDMA_ADC - ADC0-1 */
+	PSIL_PDMA_XY_TR(0x7400),
+	PSIL_PDMA_XY_TR(0x7401),
+	PSIL_PDMA_XY_TR(0x7402),
+	PSIL_PDMA_XY_TR(0x7403),
+	/* SA2UL */
+	PSIL_SA2UL(0x7500, 0),
+	PSIL_SA2UL(0x7501, 0),
+};
+
+/* PSI-L destination thread IDs, used for TX (DMA_MEM_TO_DEV) */
+static struct psil_ep j721e_dst_ep_map[] = {
+	/* SA2UL */
+	PSIL_SA2UL(0xc000, 1),
+	PSIL_SA2UL(0xc001, 1),
+	/* PRU_ICSSG0 */
+	PSIL_ETHERNET(0xc100),
+	PSIL_ETHERNET(0xc101),
+	PSIL_ETHERNET(0xc102),
+	PSIL_ETHERNET(0xc103),
+	PSIL_ETHERNET(0xc104),
+	PSIL_ETHERNET(0xc105),
+	PSIL_ETHERNET(0xc106),
+	PSIL_ETHERNET(0xc107),
+	/* PRU_ICSSG1 */
+	PSIL_ETHERNET(0xc200),
+	PSIL_ETHERNET(0xc201),
+	PSIL_ETHERNET(0xc202),
+	PSIL_ETHERNET(0xc203),
+	PSIL_ETHERNET(0xc204),
+	PSIL_ETHERNET(0xc205),
+	PSIL_ETHERNET(0xc206),
+	PSIL_ETHERNET(0xc207),
+	/* CPSW9 */
+	PSIL_ETHERNET(0xca00),
+	PSIL_ETHERNET(0xca01),
+	PSIL_ETHERNET(0xca02),
+	PSIL_ETHERNET(0xca03),
+	PSIL_ETHERNET(0xca04),
+	PSIL_ETHERNET(0xca05),
+	PSIL_ETHERNET(0xca06),
+	PSIL_ETHERNET(0xca07),
+	/* CPSW0 */
+	PSIL_ETHERNET(0xf000),
+	PSIL_ETHERNET(0xf001),
+	PSIL_ETHERNET(0xf002),
+	PSIL_ETHERNET(0xf003),
+	PSIL_ETHERNET(0xf004),
+	PSIL_ETHERNET(0xf005),
+	PSIL_ETHERNET(0xf006),
+	PSIL_ETHERNET(0xf007),
+	/* SA2UL */
+	PSIL_SA2UL(0xf500, 1),
+};
+
+struct psil_ep_map j721e_ep_map = {
+	.name = "j721e",
+	.src = j721e_src_ep_map,
+	.src_count = ARRAY_SIZE(j721e_src_ep_map),
+	.dst = j721e_dst_ep_map,
+	.dst_count = ARRAY_SIZE(j721e_dst_ep_map),
+};
diff --git a/drivers/dma/ti/k3-psil-priv.h b/drivers/dma/ti/k3-psil-priv.h
new file mode 100644
index 000000000000..a1f389ca371e
--- /dev/null
+++ b/drivers/dma/ti/k3-psil-priv.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *  Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com
+ */
+
+#ifndef K3_PSIL_PRIV_H_
+#define K3_PSIL_PRIV_H_
+
+#include <linux/dma/k3-psil.h>
+
+struct psil_ep {
+	u32 thread_id;
+	struct psil_endpoint_config ep_config;
+};
+
+/**
+ * struct psil_ep_map - PSI-L thread ID configuration maps
+ * @name:	Name of the map, set it to the name of the SoC
+ * @src:	Array of source PSI-L thread configurations
+ * @src_count:	Number of entries in the src array
+ * @dst:	Array of destination PSI-L thread configurations
+ * @dst_count:	Number of entries in the dst array
+ *
+ * In case of symmetric configuration for a matching src/dst thread (for example
+ * 0x4400 and 0xc400) only the src configuration can be present. If no dst
+ * configuration found the code will look for (dst_thread_id & ~0x8000) to find
+ * the symmetric match.
+ */
+struct psil_ep_map {
+	char *name;
+	struct psil_ep	*src;
+	int src_count;
+	struct psil_ep	*dst;
+	int dst_count;
+};
+
+struct psil_endpoint_config *psil_get_ep_config(u32 thread_id);
+
+/* SoC PSI-L endpoint maps */
+extern struct psil_ep_map am654_ep_map;
+extern struct psil_ep_map j721e_ep_map;
+
+#endif /* K3_PSIL_PRIV_H_ */
diff --git a/drivers/dma/ti/k3-psil.c b/drivers/dma/ti/k3-psil.c
new file mode 100644
index 000000000000..d7b965049ccb
--- /dev/null
+++ b/drivers/dma/ti/k3-psil.c
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com
+ *  Author: Peter Ujfalusi <peter.ujfalusi@ti.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/init.h>
+#include <linux/mutex.h>
+#include <linux/of.h>
+
+#include "k3-psil-priv.h"
+
+static DEFINE_MUTEX(ep_map_mutex);
+static struct psil_ep_map *soc_ep_map;
+
+struct psil_endpoint_config *psil_get_ep_config(u32 thread_id)
+{
+	int i;
+
+	mutex_lock(&ep_map_mutex);
+	if (!soc_ep_map) {
+		if (of_machine_is_compatible("ti,am654")) {
+			soc_ep_map = &am654_ep_map;
+		} else if (of_machine_is_compatible("ti,j721e")) {
+			soc_ep_map = &j721e_ep_map;
+		} else {
+			pr_err("PSIL: No compatible machine found for map\n");
+			return ERR_PTR(-ENOTSUPP);
+		}
+		pr_debug("%s: Using map for %s\n", __func__, soc_ep_map->name);
+	}
+	mutex_unlock(&ep_map_mutex);
+
+	if (thread_id & K3_PSIL_DST_THREAD_ID_OFFSET && soc_ep_map->dst) {
+		/* check in destination thread map */
+		for (i = 0; i < soc_ep_map->dst_count; i++) {
+			if (soc_ep_map->dst[i].thread_id == thread_id)
+				return &soc_ep_map->dst[i].ep_config;
+		}
+	}
+
+	thread_id &= ~K3_PSIL_DST_THREAD_ID_OFFSET;
+	if (soc_ep_map->src) {
+		for (i = 0; i < soc_ep_map->src_count; i++) {
+			if (soc_ep_map->src[i].thread_id == thread_id)
+				return &soc_ep_map->src[i].ep_config;
+		}
+	}
+
+	return ERR_PTR(-ENOENT);
+}
+EXPORT_SYMBOL_GPL(psil_get_ep_config);
+
+int psil_set_new_ep_config(struct device *dev, const char *name,
+			   struct psil_endpoint_config *ep_config)
+{
+	struct psil_endpoint_config *dst_ep_config;
+	struct of_phandle_args dma_spec;
+	u32 thread_id;
+	int index;
+
+	if (!dev || !dev->of_node)
+		return -EINVAL;
+
+	index = of_property_match_string(dev->of_node, "dma-names", name);
+	if (index < 0)
+		return index;
+
+	if (of_parse_phandle_with_args(dev->of_node, "dmas", "#dma-cells",
+				       index, &dma_spec))
+		return -ENOENT;
+
+	thread_id = dma_spec.args[0];
+
+	dst_ep_config = psil_get_ep_config(thread_id);
+	if (IS_ERR(dst_ep_config)) {
+		pr_err("PSIL: thread ID 0x%04x not defined in map\n",
+		       thread_id);
+		of_node_put(dma_spec.np);
+		return PTR_ERR(dst_ep_config);
+	}
+
+	memcpy(dst_ep_config, ep_config, sizeof(*dst_ep_config));
+
+	of_node_put(dma_spec.np);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(psil_set_new_ep_config);
diff --git a/drivers/dma/ti/k3-udma-glue.c b/drivers/dma/ti/k3-udma-glue.c
new file mode 100644
index 000000000000..4d7561a1b3e3
--- /dev/null
+++ b/drivers/dma/ti/k3-udma-glue.c
@@ -0,0 +1,1207 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * K3 NAVSS DMA glue interface
+ *
+ * Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com
+ *
+ */
+
+#include <linux/atomic.h>
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/io.h>
+#include <linux/init.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/soc/ti/k3-ringacc.h>
+#include <linux/dma/ti-cppi5.h>
+#include <linux/dma/k3-udma-glue.h>
+
+#include "k3-udma.h"
+#include "k3-psil-priv.h"
+
+struct k3_udma_glue_common {
+	struct device *dev;
+	struct udma_dev *udmax;
+	const struct udma_tisci_rm *tisci_rm;
+	struct k3_ringacc *ringacc;
+	u32 src_thread;
+	u32 dst_thread;
+
+	u32  hdesc_size;
+	bool epib;
+	u32  psdata_size;
+	u32  swdata_size;
+};
+
+struct k3_udma_glue_tx_channel {
+	struct k3_udma_glue_common common;
+
+	struct udma_tchan *udma_tchanx;
+	int udma_tchan_id;
+
+	struct k3_ring *ringtx;
+	struct k3_ring *ringtxcq;
+
+	bool psil_paired;
+
+	int virq;
+
+	atomic_t free_pkts;
+	bool tx_pause_on_err;
+	bool tx_filt_einfo;
+	bool tx_filt_pswords;
+	bool tx_supr_tdpkt;
+};
+
+struct k3_udma_glue_rx_flow {
+	struct udma_rflow *udma_rflow;
+	int udma_rflow_id;
+	struct k3_ring *ringrx;
+	struct k3_ring *ringrxfdq;
+
+	int virq;
+};
+
+struct k3_udma_glue_rx_channel {
+	struct k3_udma_glue_common common;
+
+	struct udma_rchan *udma_rchanx;
+	int udma_rchan_id;
+	bool remote;
+
+	bool psil_paired;
+
+	u32  swdata_size;
+	int  flow_id_base;
+
+	struct k3_udma_glue_rx_flow *flows;
+	u32 flow_num;
+	u32 flows_ready;
+};
+
+#define K3_UDMAX_TDOWN_TIMEOUT_US 1000
+
+static int of_k3_udma_glue_parse(struct device_node *udmax_np,
+				 struct k3_udma_glue_common *common)
+{
+	common->ringacc = of_k3_ringacc_get_by_phandle(udmax_np,
+						       "ti,ringacc");
+	if (IS_ERR(common->ringacc))
+		return PTR_ERR(common->ringacc);
+
+	common->udmax = of_xudma_dev_get(udmax_np, NULL);
+	if (IS_ERR(common->udmax))
+		return PTR_ERR(common->udmax);
+
+	common->tisci_rm = xudma_dev_get_tisci_rm(common->udmax);
+
+	return 0;
+}
+
+static int of_k3_udma_glue_parse_chn(struct device_node *chn_np,
+		const char *name, struct k3_udma_glue_common *common,
+		bool tx_chn)
+{
+	struct psil_endpoint_config *ep_config;
+	struct of_phandle_args dma_spec;
+	u32 thread_id;
+	int ret = 0;
+	int index;
+
+	if (unlikely(!name))
+		return -EINVAL;
+
+	index = of_property_match_string(chn_np, "dma-names", name);
+	if (index < 0)
+		return index;
+
+	if (of_parse_phandle_with_args(chn_np, "dmas", "#dma-cells", index,
+				       &dma_spec))
+		return -ENOENT;
+
+	thread_id = dma_spec.args[0];
+
+	if (tx_chn && !(thread_id & K3_PSIL_DST_THREAD_ID_OFFSET)) {
+		ret = -EINVAL;
+		goto out_put_spec;
+	}
+
+	if (!tx_chn && (thread_id & K3_PSIL_DST_THREAD_ID_OFFSET)) {
+		ret = -EINVAL;
+		goto out_put_spec;
+	}
+
+	/* get psil endpoint config */
+	ep_config = psil_get_ep_config(thread_id);
+	if (IS_ERR(ep_config)) {
+		dev_err(common->dev,
+			"No configuration for psi-l thread 0x%04x\n",
+			thread_id);
+		ret = PTR_ERR(ep_config);
+		goto out_put_spec;
+	}
+
+	common->epib = ep_config->needs_epib;
+	common->psdata_size = ep_config->psd_size;
+
+	if (tx_chn)
+		common->dst_thread = thread_id;
+	else
+		common->src_thread = thread_id;
+
+	ret = of_k3_udma_glue_parse(dma_spec.np, common);
+
+out_put_spec:
+	of_node_put(dma_spec.np);
+	return ret;
+};
+
+static void k3_udma_glue_dump_tx_chn(struct k3_udma_glue_tx_channel *tx_chn)
+{
+	struct device *dev = tx_chn->common.dev;
+
+	dev_dbg(dev, "dump_tx_chn:\n"
+		"udma_tchan_id: %d\n"
+		"src_thread: %08x\n"
+		"dst_thread: %08x\n",
+		tx_chn->udma_tchan_id,
+		tx_chn->common.src_thread,
+		tx_chn->common.dst_thread);
+}
+
+static void k3_udma_glue_dump_tx_rt_chn(struct k3_udma_glue_tx_channel *chn,
+					char *mark)
+{
+	struct device *dev = chn->common.dev;
+
+	dev_dbg(dev, "=== dump ===> %s\n", mark);
+	dev_dbg(dev, "0x%08X: %08X\n", UDMA_TCHAN_RT_CTL_REG,
+		xudma_tchanrt_read(chn->udma_tchanx, UDMA_TCHAN_RT_CTL_REG));
+	dev_dbg(dev, "0x%08X: %08X\n", UDMA_TCHAN_RT_PEER_RT_EN_REG,
+		xudma_tchanrt_read(chn->udma_tchanx,
+				   UDMA_TCHAN_RT_PEER_RT_EN_REG));
+	dev_dbg(dev, "0x%08X: %08X\n", UDMA_TCHAN_RT_PCNT_REG,
+		xudma_tchanrt_read(chn->udma_tchanx, UDMA_TCHAN_RT_PCNT_REG));
+	dev_dbg(dev, "0x%08X: %08X\n", UDMA_TCHAN_RT_BCNT_REG,
+		xudma_tchanrt_read(chn->udma_tchanx, UDMA_TCHAN_RT_BCNT_REG));
+	dev_dbg(dev, "0x%08X: %08X\n", UDMA_TCHAN_RT_SBCNT_REG,
+		xudma_tchanrt_read(chn->udma_tchanx, UDMA_TCHAN_RT_SBCNT_REG));
+}
+
+static int k3_udma_glue_cfg_tx_chn(struct k3_udma_glue_tx_channel *tx_chn)
+{
+	const struct udma_tisci_rm *tisci_rm = tx_chn->common.tisci_rm;
+	struct ti_sci_msg_rm_udmap_tx_ch_cfg req;
+
+	memset(&req, 0, sizeof(req));
+
+	req.valid_params = TI_SCI_MSG_VALUE_RM_UDMAP_CH_PAUSE_ON_ERR_VALID |
+			TI_SCI_MSG_VALUE_RM_UDMAP_CH_TX_FILT_EINFO_VALID |
+			TI_SCI_MSG_VALUE_RM_UDMAP_CH_TX_FILT_PSWORDS_VALID |
+			TI_SCI_MSG_VALUE_RM_UDMAP_CH_CHAN_TYPE_VALID |
+			TI_SCI_MSG_VALUE_RM_UDMAP_CH_TX_SUPR_TDPKT_VALID |
+			TI_SCI_MSG_VALUE_RM_UDMAP_CH_FETCH_SIZE_VALID |
+			TI_SCI_MSG_VALUE_RM_UDMAP_CH_CQ_QNUM_VALID;
+	req.nav_id = tisci_rm->tisci_dev_id;
+	req.index = tx_chn->udma_tchan_id;
+	if (tx_chn->tx_pause_on_err)
+		req.tx_pause_on_err = 1;
+	if (tx_chn->tx_filt_einfo)
+		req.tx_filt_einfo = 1;
+	if (tx_chn->tx_filt_pswords)
+		req.tx_filt_pswords = 1;
+	req.tx_chan_type = TI_SCI_RM_UDMAP_CHAN_TYPE_PKT_PBRR;
+	if (tx_chn->tx_supr_tdpkt)
+		req.tx_supr_tdpkt = 1;
+	req.tx_fetch_size = tx_chn->common.hdesc_size >> 2;
+	req.txcq_qnum = k3_ringacc_get_ring_id(tx_chn->ringtxcq);
+
+	return tisci_rm->tisci_udmap_ops->tx_ch_cfg(tisci_rm->tisci, &req);
+}
+
+struct k3_udma_glue_tx_channel *k3_udma_glue_request_tx_chn(struct device *dev,
+		const char *name, struct k3_udma_glue_tx_channel_cfg *cfg)
+{
+	struct k3_udma_glue_tx_channel *tx_chn;
+	int ret;
+
+	tx_chn = devm_kzalloc(dev, sizeof(*tx_chn), GFP_KERNEL);
+	if (!tx_chn)
+		return ERR_PTR(-ENOMEM);
+
+	tx_chn->common.dev = dev;
+	tx_chn->common.swdata_size = cfg->swdata_size;
+	tx_chn->tx_pause_on_err = cfg->tx_pause_on_err;
+	tx_chn->tx_filt_einfo = cfg->tx_filt_einfo;
+	tx_chn->tx_filt_pswords = cfg->tx_filt_pswords;
+	tx_chn->tx_supr_tdpkt = cfg->tx_supr_tdpkt;
+
+	/* parse of udmap channel */
+	ret = of_k3_udma_glue_parse_chn(dev->of_node, name,
+					&tx_chn->common, true);
+	if (ret)
+		goto err;
+
+	tx_chn->common.hdesc_size = cppi5_hdesc_calc_size(tx_chn->common.epib,
+						tx_chn->common.psdata_size,
+						tx_chn->common.swdata_size);
+
+	/* request and cfg UDMAP TX channel */
+	tx_chn->udma_tchanx = xudma_tchan_get(tx_chn->common.udmax, -1);
+	if (IS_ERR(tx_chn->udma_tchanx)) {
+		ret = PTR_ERR(tx_chn->udma_tchanx);
+		dev_err(dev, "UDMAX tchanx get err %d\n", ret);
+		goto err;
+	}
+	tx_chn->udma_tchan_id = xudma_tchan_get_id(tx_chn->udma_tchanx);
+
+	atomic_set(&tx_chn->free_pkts, cfg->txcq_cfg.size);
+
+	/* request and cfg rings */
+	tx_chn->ringtx = k3_ringacc_request_ring(tx_chn->common.ringacc,
+						 tx_chn->udma_tchan_id, 0);
+	if (!tx_chn->ringtx) {
+		ret = -ENODEV;
+		dev_err(dev, "Failed to get TX ring %u\n",
+			tx_chn->udma_tchan_id);
+		goto err;
+	}
+
+	tx_chn->ringtxcq = k3_ringacc_request_ring(tx_chn->common.ringacc,
+						   -1, 0);
+	if (!tx_chn->ringtxcq) {
+		ret = -ENODEV;
+		dev_err(dev, "Failed to get TXCQ ring\n");
+		goto err;
+	}
+
+	ret = k3_ringacc_ring_cfg(tx_chn->ringtx, &cfg->tx_cfg);
+	if (ret) {
+		dev_err(dev, "Failed to cfg ringtx %d\n", ret);
+		goto err;
+	}
+
+	ret = k3_ringacc_ring_cfg(tx_chn->ringtxcq, &cfg->txcq_cfg);
+	if (ret) {
+		dev_err(dev, "Failed to cfg ringtx %d\n", ret);
+		goto err;
+	}
+
+	/* request and cfg psi-l */
+	tx_chn->common.src_thread =
+			xudma_dev_get_psil_base(tx_chn->common.udmax) +
+			tx_chn->udma_tchan_id;
+
+	ret = k3_udma_glue_cfg_tx_chn(tx_chn);
+	if (ret) {
+		dev_err(dev, "Failed to cfg tchan %d\n", ret);
+		goto err;
+	}
+
+	ret = xudma_navss_psil_pair(tx_chn->common.udmax,
+				    tx_chn->common.src_thread,
+				    tx_chn->common.dst_thread);
+	if (ret) {
+		dev_err(dev, "PSI-L request err %d\n", ret);
+		goto err;
+	}
+
+	tx_chn->psil_paired = true;
+
+	/* reset TX RT registers */
+	k3_udma_glue_disable_tx_chn(tx_chn);
+
+	k3_udma_glue_dump_tx_chn(tx_chn);
+
+	return tx_chn;
+
+err:
+	k3_udma_glue_release_tx_chn(tx_chn);
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_request_tx_chn);
+
+void k3_udma_glue_release_tx_chn(struct k3_udma_glue_tx_channel *tx_chn)
+{
+	if (tx_chn->psil_paired) {
+		xudma_navss_psil_unpair(tx_chn->common.udmax,
+					tx_chn->common.src_thread,
+					tx_chn->common.dst_thread);
+		tx_chn->psil_paired = false;
+	}
+
+	if (!IS_ERR_OR_NULL(tx_chn->udma_tchanx))
+		xudma_tchan_put(tx_chn->common.udmax,
+				tx_chn->udma_tchanx);
+
+	if (tx_chn->ringtxcq)
+		k3_ringacc_ring_free(tx_chn->ringtxcq);
+
+	if (tx_chn->ringtx)
+		k3_ringacc_ring_free(tx_chn->ringtx);
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_release_tx_chn);
+
+int k3_udma_glue_push_tx_chn(struct k3_udma_glue_tx_channel *tx_chn,
+			     struct cppi5_host_desc_t *desc_tx,
+			     dma_addr_t desc_dma)
+{
+	u32 ringtxcq_id;
+
+	if (!atomic_add_unless(&tx_chn->free_pkts, -1, 0))
+		return -ENOMEM;
+
+	ringtxcq_id = k3_ringacc_get_ring_id(tx_chn->ringtxcq);
+	cppi5_desc_set_retpolicy(&desc_tx->hdr, 0, ringtxcq_id);
+
+	return k3_ringacc_ring_push(tx_chn->ringtx, &desc_dma);
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_push_tx_chn);
+
+int k3_udma_glue_pop_tx_chn(struct k3_udma_glue_tx_channel *tx_chn,
+			    dma_addr_t *desc_dma)
+{
+	int ret;
+
+	ret = k3_ringacc_ring_pop(tx_chn->ringtxcq, desc_dma);
+	if (!ret)
+		atomic_inc(&tx_chn->free_pkts);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_pop_tx_chn);
+
+int k3_udma_glue_enable_tx_chn(struct k3_udma_glue_tx_channel *tx_chn)
+{
+	u32 txrt_ctl;
+
+	txrt_ctl = UDMA_PEER_RT_EN_ENABLE;
+	xudma_tchanrt_write(tx_chn->udma_tchanx,
+			    UDMA_TCHAN_RT_PEER_RT_EN_REG,
+			    txrt_ctl);
+
+	txrt_ctl = xudma_tchanrt_read(tx_chn->udma_tchanx,
+				      UDMA_TCHAN_RT_CTL_REG);
+	txrt_ctl |= UDMA_CHAN_RT_CTL_EN;
+	xudma_tchanrt_write(tx_chn->udma_tchanx, UDMA_TCHAN_RT_CTL_REG,
+			    txrt_ctl);
+
+	k3_udma_glue_dump_tx_rt_chn(tx_chn, "txchn en");
+	return 0;
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_enable_tx_chn);
+
+void k3_udma_glue_disable_tx_chn(struct k3_udma_glue_tx_channel *tx_chn)
+{
+	k3_udma_glue_dump_tx_rt_chn(tx_chn, "txchn dis1");
+
+	xudma_tchanrt_write(tx_chn->udma_tchanx, UDMA_TCHAN_RT_CTL_REG, 0);
+
+	xudma_tchanrt_write(tx_chn->udma_tchanx,
+			    UDMA_TCHAN_RT_PEER_RT_EN_REG, 0);
+	k3_udma_glue_dump_tx_rt_chn(tx_chn, "txchn dis2");
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_disable_tx_chn);
+
+void k3_udma_glue_tdown_tx_chn(struct k3_udma_glue_tx_channel *tx_chn,
+			       bool sync)
+{
+	int i = 0;
+	u32 val;
+
+	k3_udma_glue_dump_tx_rt_chn(tx_chn, "txchn tdown1");
+
+	xudma_tchanrt_write(tx_chn->udma_tchanx, UDMA_TCHAN_RT_CTL_REG,
+			    UDMA_CHAN_RT_CTL_EN | UDMA_CHAN_RT_CTL_TDOWN);
+
+	val = xudma_tchanrt_read(tx_chn->udma_tchanx, UDMA_TCHAN_RT_CTL_REG);
+
+	while (sync && (val & UDMA_CHAN_RT_CTL_EN)) {
+		val = xudma_tchanrt_read(tx_chn->udma_tchanx,
+					 UDMA_TCHAN_RT_CTL_REG);
+		udelay(1);
+		if (i > K3_UDMAX_TDOWN_TIMEOUT_US) {
+			dev_err(tx_chn->common.dev, "TX tdown timeout\n");
+			break;
+		}
+		i++;
+	}
+
+	val = xudma_tchanrt_read(tx_chn->udma_tchanx,
+				 UDMA_TCHAN_RT_PEER_RT_EN_REG);
+	if (sync && (val & UDMA_PEER_RT_EN_ENABLE))
+		dev_err(tx_chn->common.dev, "TX tdown peer not stopped\n");
+	k3_udma_glue_dump_tx_rt_chn(tx_chn, "txchn tdown2");
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_tdown_tx_chn);
+
+void k3_udma_glue_reset_tx_chn(struct k3_udma_glue_tx_channel *tx_chn,
+			       void *data,
+			       void (*cleanup)(void *data, dma_addr_t desc_dma))
+{
+	dma_addr_t desc_dma;
+	int occ_tx, i, ret;
+
+	/* reset TXCQ as it is not input for udma - expected to be empty */
+	if (tx_chn->ringtxcq)
+		k3_ringacc_ring_reset(tx_chn->ringtxcq);
+
+	/*
+	 * TXQ reset need to be special way as it is input for udma and its
+	 * state cached by udma, so:
+	 * 1) save TXQ occ
+	 * 2) clean up TXQ and call callback .cleanup() for each desc
+	 * 3) reset TXQ in a special way
+	 */
+	occ_tx = k3_ringacc_ring_get_occ(tx_chn->ringtx);
+	dev_dbg(tx_chn->common.dev, "TX reset occ_tx %u\n", occ_tx);
+
+	for (i = 0; i < occ_tx; i++) {
+		ret = k3_ringacc_ring_pop(tx_chn->ringtx, &desc_dma);
+		if (ret) {
+			dev_err(tx_chn->common.dev, "TX reset pop %d\n", ret);
+			break;
+		}
+		cleanup(data, desc_dma);
+	}
+
+	k3_ringacc_ring_reset_dma(tx_chn->ringtx, occ_tx);
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_reset_tx_chn);
+
+u32 k3_udma_glue_tx_get_hdesc_size(struct k3_udma_glue_tx_channel *tx_chn)
+{
+	return tx_chn->common.hdesc_size;
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_tx_get_hdesc_size);
+
+u32 k3_udma_glue_tx_get_txcq_id(struct k3_udma_glue_tx_channel *tx_chn)
+{
+	return k3_ringacc_get_ring_id(tx_chn->ringtxcq);
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_tx_get_txcq_id);
+
+int k3_udma_glue_tx_get_irq(struct k3_udma_glue_tx_channel *tx_chn)
+{
+	tx_chn->virq = k3_ringacc_get_ring_irq_num(tx_chn->ringtxcq);
+
+	return tx_chn->virq;
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_tx_get_irq);
+
+static int k3_udma_glue_cfg_rx_chn(struct k3_udma_glue_rx_channel *rx_chn)
+{
+	const struct udma_tisci_rm *tisci_rm = rx_chn->common.tisci_rm;
+	struct ti_sci_msg_rm_udmap_rx_ch_cfg req;
+	int ret;
+
+	memset(&req, 0, sizeof(req));
+
+	req.valid_params = TI_SCI_MSG_VALUE_RM_UDMAP_CH_FETCH_SIZE_VALID |
+			   TI_SCI_MSG_VALUE_RM_UDMAP_CH_CQ_QNUM_VALID |
+			   TI_SCI_MSG_VALUE_RM_UDMAP_CH_CHAN_TYPE_VALID |
+			   TI_SCI_MSG_VALUE_RM_UDMAP_CH_RX_FLOWID_START_VALID |
+			   TI_SCI_MSG_VALUE_RM_UDMAP_CH_RX_FLOWID_CNT_VALID;
+
+	req.nav_id = tisci_rm->tisci_dev_id;
+	req.index = rx_chn->udma_rchan_id;
+	req.rx_fetch_size = rx_chn->common.hdesc_size >> 2;
+	/*
+	 * TODO: we can't support rxcq_qnum/RCHAN[a]_RCQ cfg with current sysfw
+	 * and udmax impl, so just configure it to invalid value.
+	 * req.rxcq_qnum = k3_ringacc_get_ring_id(rx_chn->flows[0].ringrx);
+	 */
+	req.rxcq_qnum = 0xFFFF;
+	if (rx_chn->flow_num && rx_chn->flow_id_base != rx_chn->udma_rchan_id) {
+		/* Default flow + extra ones */
+		req.flowid_start = rx_chn->flow_id_base;
+		req.flowid_cnt = rx_chn->flow_num;
+	}
+	req.rx_chan_type = TI_SCI_RM_UDMAP_CHAN_TYPE_PKT_PBRR;
+
+	ret = tisci_rm->tisci_udmap_ops->rx_ch_cfg(tisci_rm->tisci, &req);
+	if (ret)
+		dev_err(rx_chn->common.dev, "rchan%d cfg failed %d\n",
+			rx_chn->udma_rchan_id, ret);
+
+	return ret;
+}
+
+static void k3_udma_glue_release_rx_flow(struct k3_udma_glue_rx_channel *rx_chn,
+					 u32 flow_num)
+{
+	struct k3_udma_glue_rx_flow *flow = &rx_chn->flows[flow_num];
+
+	if (IS_ERR_OR_NULL(flow->udma_rflow))
+		return;
+
+	if (flow->ringrxfdq)
+		k3_ringacc_ring_free(flow->ringrxfdq);
+
+	if (flow->ringrx)
+		k3_ringacc_ring_free(flow->ringrx);
+
+	xudma_rflow_put(rx_chn->common.udmax, flow->udma_rflow);
+	flow->udma_rflow = NULL;
+	rx_chn->flows_ready--;
+}
+
+static int k3_udma_glue_cfg_rx_flow(struct k3_udma_glue_rx_channel *rx_chn,
+				    u32 flow_idx,
+				    struct k3_udma_glue_rx_flow_cfg *flow_cfg)
+{
+	struct k3_udma_glue_rx_flow *flow = &rx_chn->flows[flow_idx];
+	const struct udma_tisci_rm *tisci_rm = rx_chn->common.tisci_rm;
+	struct device *dev = rx_chn->common.dev;
+	struct ti_sci_msg_rm_udmap_flow_cfg req;
+	int rx_ring_id;
+	int rx_ringfdq_id;
+	int ret = 0;
+
+	flow->udma_rflow = xudma_rflow_get(rx_chn->common.udmax,
+					   flow->udma_rflow_id);
+	if (IS_ERR(flow->udma_rflow)) {
+		ret = PTR_ERR(flow->udma_rflow);
+		dev_err(dev, "UDMAX rflow get err %d\n", ret);
+		return ret;
+	}
+
+	if (flow->udma_rflow_id != xudma_rflow_get_id(flow->udma_rflow)) {
+		ret = -ENODEV;
+		goto err_rflow_put;
+	}
+
+	/* request and cfg rings */
+	flow->ringrx = k3_ringacc_request_ring(rx_chn->common.ringacc,
+					       flow_cfg->ring_rxq_id, 0);
+	if (!flow->ringrx) {
+		ret = -ENODEV;
+		dev_err(dev, "Failed to get RX ring\n");
+		goto err_rflow_put;
+	}
+
+	flow->ringrxfdq = k3_ringacc_request_ring(rx_chn->common.ringacc,
+						  flow_cfg->ring_rxfdq0_id, 0);
+	if (!flow->ringrxfdq) {
+		ret = -ENODEV;
+		dev_err(dev, "Failed to get RXFDQ ring\n");
+		goto err_ringrx_free;
+	}
+
+	ret = k3_ringacc_ring_cfg(flow->ringrx, &flow_cfg->rx_cfg);
+	if (ret) {
+		dev_err(dev, "Failed to cfg ringrx %d\n", ret);
+		goto err_ringrxfdq_free;
+	}
+
+	ret = k3_ringacc_ring_cfg(flow->ringrxfdq, &flow_cfg->rxfdq_cfg);
+	if (ret) {
+		dev_err(dev, "Failed to cfg ringrxfdq %d\n", ret);
+		goto err_ringrxfdq_free;
+	}
+
+	if (rx_chn->remote) {
+		rx_ring_id = TI_SCI_RESOURCE_NULL;
+		rx_ringfdq_id = TI_SCI_RESOURCE_NULL;
+	} else {
+		rx_ring_id = k3_ringacc_get_ring_id(flow->ringrx);
+		rx_ringfdq_id = k3_ringacc_get_ring_id(flow->ringrxfdq);
+	}
+
+	memset(&req, 0, sizeof(req));
+
+	req.valid_params =
+			TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_EINFO_PRESENT_VALID |
+			TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_PSINFO_PRESENT_VALID |
+			TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_ERROR_HANDLING_VALID |
+			TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_DESC_TYPE_VALID |
+			TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_DEST_QNUM_VALID |
+			TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_SRC_TAG_HI_SEL_VALID |
+			TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_SRC_TAG_LO_SEL_VALID |
+			TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_DEST_TAG_HI_SEL_VALID |
+			TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_DEST_TAG_LO_SEL_VALID |
+			TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ0_SZ0_QNUM_VALID |
+			TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ1_QNUM_VALID |
+			TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ2_QNUM_VALID |
+			TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ3_QNUM_VALID;
+	req.nav_id = tisci_rm->tisci_dev_id;
+	req.flow_index = flow->udma_rflow_id;
+	if (rx_chn->common.epib)
+		req.rx_einfo_present = 1;
+	if (rx_chn->common.psdata_size)
+		req.rx_psinfo_present = 1;
+	if (flow_cfg->rx_error_handling)
+		req.rx_error_handling = 1;
+	req.rx_desc_type = 0;
+	req.rx_dest_qnum = rx_ring_id;
+	req.rx_src_tag_hi_sel = 0;
+	req.rx_src_tag_lo_sel = flow_cfg->src_tag_lo_sel;
+	req.rx_dest_tag_hi_sel = 0;
+	req.rx_dest_tag_lo_sel = 0;
+	req.rx_fdq0_sz0_qnum = rx_ringfdq_id;
+	req.rx_fdq1_qnum = rx_ringfdq_id;
+	req.rx_fdq2_qnum = rx_ringfdq_id;
+	req.rx_fdq3_qnum = rx_ringfdq_id;
+
+	ret = tisci_rm->tisci_udmap_ops->rx_flow_cfg(tisci_rm->tisci, &req);
+	if (ret) {
+		dev_err(dev, "flow%d config failed: %d\n", flow->udma_rflow_id,
+			ret);
+		goto err_ringrxfdq_free;
+	}
+
+	rx_chn->flows_ready++;
+	dev_dbg(dev, "flow%d config done. ready:%d\n",
+		flow->udma_rflow_id, rx_chn->flows_ready);
+
+	return 0;
+
+err_ringrxfdq_free:
+	k3_ringacc_ring_free(flow->ringrxfdq);
+
+err_ringrx_free:
+	k3_ringacc_ring_free(flow->ringrx);
+
+err_rflow_put:
+	xudma_rflow_put(rx_chn->common.udmax, flow->udma_rflow);
+	flow->udma_rflow = NULL;
+
+	return ret;
+}
+
+static void k3_udma_glue_dump_rx_chn(struct k3_udma_glue_rx_channel *chn)
+{
+	struct device *dev = chn->common.dev;
+
+	dev_dbg(dev, "dump_rx_chn:\n"
+		"udma_rchan_id: %d\n"
+		"src_thread: %08x\n"
+		"dst_thread: %08x\n"
+		"epib: %d\n"
+		"hdesc_size: %u\n"
+		"psdata_size: %u\n"
+		"swdata_size: %u\n"
+		"flow_id_base: %d\n"
+		"flow_num: %d\n",
+		chn->udma_rchan_id,
+		chn->common.src_thread,
+		chn->common.dst_thread,
+		chn->common.epib,
+		chn->common.hdesc_size,
+		chn->common.psdata_size,
+		chn->common.swdata_size,
+		chn->flow_id_base,
+		chn->flow_num);
+}
+
+static void k3_udma_glue_dump_rx_rt_chn(struct k3_udma_glue_rx_channel *chn,
+					char *mark)
+{
+	struct device *dev = chn->common.dev;
+
+	dev_dbg(dev, "=== dump ===> %s\n", mark);
+
+	dev_dbg(dev, "0x%08X: %08X\n", UDMA_RCHAN_RT_CTL_REG,
+		xudma_rchanrt_read(chn->udma_rchanx, UDMA_RCHAN_RT_CTL_REG));
+	dev_dbg(dev, "0x%08X: %08X\n", UDMA_RCHAN_RT_PEER_RT_EN_REG,
+		xudma_rchanrt_read(chn->udma_rchanx,
+				   UDMA_RCHAN_RT_PEER_RT_EN_REG));
+	dev_dbg(dev, "0x%08X: %08X\n", UDMA_RCHAN_RT_PCNT_REG,
+		xudma_rchanrt_read(chn->udma_rchanx, UDMA_RCHAN_RT_PCNT_REG));
+	dev_dbg(dev, "0x%08X: %08X\n", UDMA_RCHAN_RT_BCNT_REG,
+		xudma_rchanrt_read(chn->udma_rchanx, UDMA_RCHAN_RT_BCNT_REG));
+	dev_dbg(dev, "0x%08X: %08X\n", UDMA_RCHAN_RT_SBCNT_REG,
+		xudma_rchanrt_read(chn->udma_rchanx, UDMA_RCHAN_RT_SBCNT_REG));
+}
+
+static int
+k3_udma_glue_allocate_rx_flows(struct k3_udma_glue_rx_channel *rx_chn,
+			       struct k3_udma_glue_rx_channel_cfg *cfg)
+{
+	int ret;
+
+	/* default rflow */
+	if (cfg->flow_id_use_rxchan_id)
+		return 0;
+
+	/* not a GP rflows */
+	if (rx_chn->flow_id_base != -1 &&
+	    !xudma_rflow_is_gp(rx_chn->common.udmax, rx_chn->flow_id_base))
+		return 0;
+
+	/* Allocate range of GP rflows */
+	ret = xudma_alloc_gp_rflow_range(rx_chn->common.udmax,
+					 rx_chn->flow_id_base,
+					 rx_chn->flow_num);
+	if (ret < 0) {
+		dev_err(rx_chn->common.dev, "UDMAX reserve_rflow %d cnt:%d err: %d\n",
+			rx_chn->flow_id_base, rx_chn->flow_num, ret);
+		return ret;
+	}
+	rx_chn->flow_id_base = ret;
+
+	return 0;
+}
+
+static struct k3_udma_glue_rx_channel *
+k3_udma_glue_request_rx_chn_priv(struct device *dev, const char *name,
+				 struct k3_udma_glue_rx_channel_cfg *cfg)
+{
+	struct k3_udma_glue_rx_channel *rx_chn;
+	int ret, i;
+
+	if (cfg->flow_id_num <= 0)
+		return ERR_PTR(-EINVAL);
+
+	if (cfg->flow_id_num != 1 &&
+	    (cfg->def_flow_cfg || cfg->flow_id_use_rxchan_id))
+		return ERR_PTR(-EINVAL);
+
+	rx_chn = devm_kzalloc(dev, sizeof(*rx_chn), GFP_KERNEL);
+	if (!rx_chn)
+		return ERR_PTR(-ENOMEM);
+
+	rx_chn->common.dev = dev;
+	rx_chn->common.swdata_size = cfg->swdata_size;
+	rx_chn->remote = false;
+
+	/* parse of udmap channel */
+	ret = of_k3_udma_glue_parse_chn(dev->of_node, name,
+					&rx_chn->common, false);
+	if (ret)
+		goto err;
+
+	rx_chn->common.hdesc_size = cppi5_hdesc_calc_size(rx_chn->common.epib,
+						rx_chn->common.psdata_size,
+						rx_chn->common.swdata_size);
+
+	/* request and cfg UDMAP RX channel */
+	rx_chn->udma_rchanx = xudma_rchan_get(rx_chn->common.udmax, -1);
+	if (IS_ERR(rx_chn->udma_rchanx)) {
+		ret = PTR_ERR(rx_chn->udma_rchanx);
+		dev_err(dev, "UDMAX rchanx get err %d\n", ret);
+		goto err;
+	}
+	rx_chn->udma_rchan_id = xudma_rchan_get_id(rx_chn->udma_rchanx);
+
+	rx_chn->flow_num = cfg->flow_id_num;
+	rx_chn->flow_id_base = cfg->flow_id_base;
+
+	/* Use RX channel id as flow id: target dev can't generate flow_id */
+	if (cfg->flow_id_use_rxchan_id)
+		rx_chn->flow_id_base = rx_chn->udma_rchan_id;
+
+	rx_chn->flows = devm_kcalloc(dev, rx_chn->flow_num,
+				     sizeof(*rx_chn->flows), GFP_KERNEL);
+	if (!rx_chn->flows) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	ret = k3_udma_glue_allocate_rx_flows(rx_chn, cfg);
+	if (ret)
+		goto err;
+
+	for (i = 0; i < rx_chn->flow_num; i++)
+		rx_chn->flows[i].udma_rflow_id = rx_chn->flow_id_base + i;
+
+	/* request and cfg psi-l */
+	rx_chn->common.dst_thread =
+			xudma_dev_get_psil_base(rx_chn->common.udmax) +
+			rx_chn->udma_rchan_id;
+
+	ret = k3_udma_glue_cfg_rx_chn(rx_chn);
+	if (ret) {
+		dev_err(dev, "Failed to cfg rchan %d\n", ret);
+		goto err;
+	}
+
+	/* init default RX flow only if flow_num = 1 */
+	if (cfg->def_flow_cfg) {
+		ret = k3_udma_glue_cfg_rx_flow(rx_chn, 0, cfg->def_flow_cfg);
+		if (ret)
+			goto err;
+	}
+
+	ret = xudma_navss_psil_pair(rx_chn->common.udmax,
+				    rx_chn->common.src_thread,
+				    rx_chn->common.dst_thread);
+	if (ret) {
+		dev_err(dev, "PSI-L request err %d\n", ret);
+		goto err;
+	}
+
+	rx_chn->psil_paired = true;
+
+	/* reset RX RT registers */
+	k3_udma_glue_disable_rx_chn(rx_chn);
+
+	k3_udma_glue_dump_rx_chn(rx_chn);
+
+	return rx_chn;
+
+err:
+	k3_udma_glue_release_rx_chn(rx_chn);
+	return ERR_PTR(ret);
+}
+
+static struct k3_udma_glue_rx_channel *
+k3_udma_glue_request_remote_rx_chn(struct device *dev, const char *name,
+				   struct k3_udma_glue_rx_channel_cfg *cfg)
+{
+	struct k3_udma_glue_rx_channel *rx_chn;
+	int ret, i;
+
+	if (cfg->flow_id_num <= 0 ||
+	    cfg->flow_id_use_rxchan_id ||
+	    cfg->def_flow_cfg ||
+	    cfg->flow_id_base < 0)
+		return ERR_PTR(-EINVAL);
+
+	/*
+	 * Remote RX channel is under control of Remote CPU core, so
+	 * Linux can only request and manipulate by dedicated RX flows
+	 */
+
+	rx_chn = devm_kzalloc(dev, sizeof(*rx_chn), GFP_KERNEL);
+	if (!rx_chn)
+		return ERR_PTR(-ENOMEM);
+
+	rx_chn->common.dev = dev;
+	rx_chn->common.swdata_size = cfg->swdata_size;
+	rx_chn->remote = true;
+	rx_chn->udma_rchan_id = -1;
+	rx_chn->flow_num = cfg->flow_id_num;
+	rx_chn->flow_id_base = cfg->flow_id_base;
+	rx_chn->psil_paired = false;
+
+	/* parse of udmap channel */
+	ret = of_k3_udma_glue_parse_chn(dev->of_node, name,
+					&rx_chn->common, false);
+	if (ret)
+		goto err;
+
+	rx_chn->common.hdesc_size = cppi5_hdesc_calc_size(rx_chn->common.epib,
+						rx_chn->common.psdata_size,
+						rx_chn->common.swdata_size);
+
+	rx_chn->flows = devm_kcalloc(dev, rx_chn->flow_num,
+				     sizeof(*rx_chn->flows), GFP_KERNEL);
+	if (!rx_chn->flows) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	ret = k3_udma_glue_allocate_rx_flows(rx_chn, cfg);
+	if (ret)
+		goto err;
+
+	for (i = 0; i < rx_chn->flow_num; i++)
+		rx_chn->flows[i].udma_rflow_id = rx_chn->flow_id_base + i;
+
+	k3_udma_glue_dump_rx_chn(rx_chn);
+
+	return rx_chn;
+
+err:
+	k3_udma_glue_release_rx_chn(rx_chn);
+	return ERR_PTR(ret);
+}
+
+struct k3_udma_glue_rx_channel *
+k3_udma_glue_request_rx_chn(struct device *dev, const char *name,
+			    struct k3_udma_glue_rx_channel_cfg *cfg)
+{
+	if (cfg->remote)
+		return k3_udma_glue_request_remote_rx_chn(dev, name, cfg);
+	else
+		return k3_udma_glue_request_rx_chn_priv(dev, name, cfg);
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_request_rx_chn);
+
+void k3_udma_glue_release_rx_chn(struct k3_udma_glue_rx_channel *rx_chn)
+{
+	int i;
+
+	if (IS_ERR_OR_NULL(rx_chn->common.udmax))
+		return;
+
+	if (rx_chn->psil_paired) {
+		xudma_navss_psil_unpair(rx_chn->common.udmax,
+					rx_chn->common.src_thread,
+					rx_chn->common.dst_thread);
+		rx_chn->psil_paired = false;
+	}
+
+	for (i = 0; i < rx_chn->flow_num; i++)
+		k3_udma_glue_release_rx_flow(rx_chn, i);
+
+	if (xudma_rflow_is_gp(rx_chn->common.udmax, rx_chn->flow_id_base))
+		xudma_free_gp_rflow_range(rx_chn->common.udmax,
+					  rx_chn->flow_id_base,
+					  rx_chn->flow_num);
+
+	if (!IS_ERR_OR_NULL(rx_chn->udma_rchanx))
+		xudma_rchan_put(rx_chn->common.udmax,
+				rx_chn->udma_rchanx);
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_release_rx_chn);
+
+int k3_udma_glue_rx_flow_init(struct k3_udma_glue_rx_channel *rx_chn,
+			      u32 flow_idx,
+			      struct k3_udma_glue_rx_flow_cfg *flow_cfg)
+{
+	if (flow_idx >= rx_chn->flow_num)
+		return -EINVAL;
+
+	return k3_udma_glue_cfg_rx_flow(rx_chn, flow_idx, flow_cfg);
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_rx_flow_init);
+
+u32 k3_udma_glue_rx_flow_get_fdq_id(struct k3_udma_glue_rx_channel *rx_chn,
+				    u32 flow_idx)
+{
+	struct k3_udma_glue_rx_flow *flow;
+
+	if (flow_idx >= rx_chn->flow_num)
+		return -EINVAL;
+
+	flow = &rx_chn->flows[flow_idx];
+
+	return k3_ringacc_get_ring_id(flow->ringrxfdq);
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_rx_flow_get_fdq_id);
+
+u32 k3_udma_glue_rx_get_flow_id_base(struct k3_udma_glue_rx_channel *rx_chn)
+{
+	return rx_chn->flow_id_base;
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_rx_get_flow_id_base);
+
+int k3_udma_glue_rx_flow_enable(struct k3_udma_glue_rx_channel *rx_chn,
+				u32 flow_idx)
+{
+	struct k3_udma_glue_rx_flow *flow = &rx_chn->flows[flow_idx];
+	const struct udma_tisci_rm *tisci_rm = rx_chn->common.tisci_rm;
+	struct device *dev = rx_chn->common.dev;
+	struct ti_sci_msg_rm_udmap_flow_cfg req;
+	int rx_ring_id;
+	int rx_ringfdq_id;
+	int ret = 0;
+
+	if (!rx_chn->remote)
+		return -EINVAL;
+
+	rx_ring_id = k3_ringacc_get_ring_id(flow->ringrx);
+	rx_ringfdq_id = k3_ringacc_get_ring_id(flow->ringrxfdq);
+
+	memset(&req, 0, sizeof(req));
+
+	req.valid_params =
+			TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_DEST_QNUM_VALID |
+			TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ0_SZ0_QNUM_VALID |
+			TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ1_QNUM_VALID |
+			TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ2_QNUM_VALID |
+			TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ3_QNUM_VALID;
+	req.nav_id = tisci_rm->tisci_dev_id;
+	req.flow_index = flow->udma_rflow_id;
+	req.rx_dest_qnum = rx_ring_id;
+	req.rx_fdq0_sz0_qnum = rx_ringfdq_id;
+	req.rx_fdq1_qnum = rx_ringfdq_id;
+	req.rx_fdq2_qnum = rx_ringfdq_id;
+	req.rx_fdq3_qnum = rx_ringfdq_id;
+
+	ret = tisci_rm->tisci_udmap_ops->rx_flow_cfg(tisci_rm->tisci, &req);
+	if (ret) {
+		dev_err(dev, "flow%d enable failed: %d\n", flow->udma_rflow_id,
+			ret);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_rx_flow_enable);
+
+int k3_udma_glue_rx_flow_disable(struct k3_udma_glue_rx_channel *rx_chn,
+				 u32 flow_idx)
+{
+	struct k3_udma_glue_rx_flow *flow = &rx_chn->flows[flow_idx];
+	const struct udma_tisci_rm *tisci_rm = rx_chn->common.tisci_rm;
+	struct device *dev = rx_chn->common.dev;
+	struct ti_sci_msg_rm_udmap_flow_cfg req;
+	int ret = 0;
+
+	if (!rx_chn->remote)
+		return -EINVAL;
+
+	memset(&req, 0, sizeof(req));
+	req.valid_params =
+			TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_DEST_QNUM_VALID |
+			TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ0_SZ0_QNUM_VALID |
+			TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ1_QNUM_VALID |
+			TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ2_QNUM_VALID |
+			TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ3_QNUM_VALID;
+	req.nav_id = tisci_rm->tisci_dev_id;
+	req.flow_index = flow->udma_rflow_id;
+	req.rx_dest_qnum = TI_SCI_RESOURCE_NULL;
+	req.rx_fdq0_sz0_qnum = TI_SCI_RESOURCE_NULL;
+	req.rx_fdq1_qnum = TI_SCI_RESOURCE_NULL;
+	req.rx_fdq2_qnum = TI_SCI_RESOURCE_NULL;
+	req.rx_fdq3_qnum = TI_SCI_RESOURCE_NULL;
+
+	ret = tisci_rm->tisci_udmap_ops->rx_flow_cfg(tisci_rm->tisci, &req);
+	if (ret) {
+		dev_err(dev, "flow%d disable failed: %d\n", flow->udma_rflow_id,
+			ret);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_rx_flow_disable);
+
+int k3_udma_glue_enable_rx_chn(struct k3_udma_glue_rx_channel *rx_chn)
+{
+	u32 rxrt_ctl;
+
+	if (rx_chn->remote)
+		return -EINVAL;
+
+	if (rx_chn->flows_ready < rx_chn->flow_num)
+		return -EINVAL;
+
+	rxrt_ctl = xudma_rchanrt_read(rx_chn->udma_rchanx,
+				      UDMA_RCHAN_RT_CTL_REG);
+	rxrt_ctl |= UDMA_CHAN_RT_CTL_EN;
+	xudma_rchanrt_write(rx_chn->udma_rchanx, UDMA_RCHAN_RT_CTL_REG,
+			    rxrt_ctl);
+
+	xudma_rchanrt_write(rx_chn->udma_rchanx,
+			    UDMA_RCHAN_RT_PEER_RT_EN_REG,
+			    UDMA_PEER_RT_EN_ENABLE);
+
+	k3_udma_glue_dump_rx_rt_chn(rx_chn, "rxrt en");
+	return 0;
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_enable_rx_chn);
+
+void k3_udma_glue_disable_rx_chn(struct k3_udma_glue_rx_channel *rx_chn)
+{
+	k3_udma_glue_dump_rx_rt_chn(rx_chn, "rxrt dis1");
+
+	xudma_rchanrt_write(rx_chn->udma_rchanx,
+			    UDMA_RCHAN_RT_PEER_RT_EN_REG,
+			    0);
+	xudma_rchanrt_write(rx_chn->udma_rchanx, UDMA_RCHAN_RT_CTL_REG, 0);
+
+	k3_udma_glue_dump_rx_rt_chn(rx_chn, "rxrt dis2");
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_disable_rx_chn);
+
+void k3_udma_glue_tdown_rx_chn(struct k3_udma_glue_rx_channel *rx_chn,
+			       bool sync)
+{
+	int i = 0;
+	u32 val;
+
+	if (rx_chn->remote)
+		return;
+
+	k3_udma_glue_dump_rx_rt_chn(rx_chn, "rxrt tdown1");
+
+	xudma_rchanrt_write(rx_chn->udma_rchanx, UDMA_RCHAN_RT_PEER_RT_EN_REG,
+			    UDMA_PEER_RT_EN_ENABLE | UDMA_PEER_RT_EN_TEARDOWN);
+
+	val = xudma_rchanrt_read(rx_chn->udma_rchanx, UDMA_RCHAN_RT_CTL_REG);
+
+	while (sync && (val & UDMA_CHAN_RT_CTL_EN)) {
+		val = xudma_rchanrt_read(rx_chn->udma_rchanx,
+					 UDMA_RCHAN_RT_CTL_REG);
+		udelay(1);
+		if (i > K3_UDMAX_TDOWN_TIMEOUT_US) {
+			dev_err(rx_chn->common.dev, "RX tdown timeout\n");
+			break;
+		}
+		i++;
+	}
+
+	val = xudma_rchanrt_read(rx_chn->udma_rchanx,
+				 UDMA_RCHAN_RT_PEER_RT_EN_REG);
+	if (sync && (val & UDMA_PEER_RT_EN_ENABLE))
+		dev_err(rx_chn->common.dev, "TX tdown peer not stopped\n");
+	k3_udma_glue_dump_rx_rt_chn(rx_chn, "rxrt tdown2");
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_tdown_rx_chn);
+
+void k3_udma_glue_reset_rx_chn(struct k3_udma_glue_rx_channel *rx_chn,
+		u32 flow_num, void *data,
+		void (*cleanup)(void *data, dma_addr_t desc_dma), bool skip_fdq)
+{
+	struct k3_udma_glue_rx_flow *flow = &rx_chn->flows[flow_num];
+	struct device *dev = rx_chn->common.dev;
+	dma_addr_t desc_dma;
+	int occ_rx, i, ret;
+
+	/* reset RXCQ as it is not input for udma - expected to be empty */
+	occ_rx = k3_ringacc_ring_get_occ(flow->ringrx);
+	dev_dbg(dev, "RX reset flow %u occ_rx %u\n", flow_num, occ_rx);
+	if (flow->ringrx)
+		k3_ringacc_ring_reset(flow->ringrx);
+
+	/* Skip RX FDQ in case one FDQ is used for the set of flows */
+	if (skip_fdq)
+		return;
+
+	/*
+	 * RX FDQ reset need to be special way as it is input for udma and its
+	 * state cached by udma, so:
+	 * 1) save RX FDQ occ
+	 * 2) clean up RX FDQ and call callback .cleanup() for each desc
+	 * 3) reset RX FDQ in a special way
+	 */
+	occ_rx = k3_ringacc_ring_get_occ(flow->ringrxfdq);
+	dev_dbg(dev, "RX reset flow %u occ_rx_fdq %u\n", flow_num, occ_rx);
+
+	for (i = 0; i < occ_rx; i++) {
+		ret = k3_ringacc_ring_pop(flow->ringrxfdq, &desc_dma);
+		if (ret) {
+			dev_err(dev, "RX reset pop %d\n", ret);
+			break;
+		}
+		cleanup(data, desc_dma);
+	}
+
+	k3_ringacc_ring_reset_dma(flow->ringrxfdq, occ_rx);
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_reset_rx_chn);
+
+int k3_udma_glue_push_rx_chn(struct k3_udma_glue_rx_channel *rx_chn,
+			     u32 flow_num, struct cppi5_host_desc_t *desc_rx,
+			     dma_addr_t desc_dma)
+{
+	struct k3_udma_glue_rx_flow *flow = &rx_chn->flows[flow_num];
+
+	return k3_ringacc_ring_push(flow->ringrxfdq, &desc_dma);
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_push_rx_chn);
+
+int k3_udma_glue_pop_rx_chn(struct k3_udma_glue_rx_channel *rx_chn,
+			    u32 flow_num, dma_addr_t *desc_dma)
+{
+	struct k3_udma_glue_rx_flow *flow = &rx_chn->flows[flow_num];
+
+	return k3_ringacc_ring_pop(flow->ringrx, desc_dma);
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_pop_rx_chn);
+
+int k3_udma_glue_rx_get_irq(struct k3_udma_glue_rx_channel *rx_chn,
+			    u32 flow_num)
+{
+	struct k3_udma_glue_rx_flow *flow;
+
+	flow = &rx_chn->flows[flow_num];
+
+	flow->virq = k3_ringacc_get_ring_irq_num(flow->ringrx);
+
+	return flow->virq;
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_rx_get_irq);
diff --git a/drivers/dma/ti/k3-udma-private.c b/drivers/dma/ti/k3-udma-private.c
new file mode 100644
index 000000000000..0b8f3dd6b146
--- /dev/null
+++ b/drivers/dma/ti/k3-udma-private.c
@@ -0,0 +1,133 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com
+ *  Author: Peter Ujfalusi <peter.ujfalusi@ti.com>
+ */
+
+int xudma_navss_psil_pair(struct udma_dev *ud, u32 src_thread, u32 dst_thread)
+{
+	return navss_psil_pair(ud, src_thread, dst_thread);
+}
+EXPORT_SYMBOL(xudma_navss_psil_pair);
+
+int xudma_navss_psil_unpair(struct udma_dev *ud, u32 src_thread, u32 dst_thread)
+{
+	return navss_psil_unpair(ud, src_thread, dst_thread);
+}
+EXPORT_SYMBOL(xudma_navss_psil_unpair);
+
+struct udma_dev *of_xudma_dev_get(struct device_node *np, const char *property)
+{
+	struct device_node *udma_node = np;
+	struct platform_device *pdev;
+	struct udma_dev *ud;
+
+	if (property) {
+		udma_node = of_parse_phandle(np, property, 0);
+		if (!udma_node) {
+			pr_err("UDMA node is not found\n");
+			return ERR_PTR(-ENODEV);
+		}
+	}
+
+	pdev = of_find_device_by_node(udma_node);
+	if (!pdev) {
+		pr_debug("UDMA device not found\n");
+		return ERR_PTR(-EPROBE_DEFER);
+	}
+
+	if (np != udma_node)
+		of_node_put(udma_node);
+
+	ud = platform_get_drvdata(pdev);
+	if (!ud) {
+		pr_debug("UDMA has not been probed\n");
+		return ERR_PTR(-EPROBE_DEFER);
+	}
+
+	return ud;
+}
+EXPORT_SYMBOL(of_xudma_dev_get);
+
+u32 xudma_dev_get_psil_base(struct udma_dev *ud)
+{
+	return ud->psil_base;
+}
+EXPORT_SYMBOL(xudma_dev_get_psil_base);
+
+struct udma_tisci_rm *xudma_dev_get_tisci_rm(struct udma_dev *ud)
+{
+	return &ud->tisci_rm;
+}
+EXPORT_SYMBOL(xudma_dev_get_tisci_rm);
+
+int xudma_alloc_gp_rflow_range(struct udma_dev *ud, int from, int cnt)
+{
+	return __udma_alloc_gp_rflow_range(ud, from, cnt);
+}
+EXPORT_SYMBOL(xudma_alloc_gp_rflow_range);
+
+int xudma_free_gp_rflow_range(struct udma_dev *ud, int from, int cnt)
+{
+	return __udma_free_gp_rflow_range(ud, from, cnt);
+}
+EXPORT_SYMBOL(xudma_free_gp_rflow_range);
+
+bool xudma_rflow_is_gp(struct udma_dev *ud, int id)
+{
+	return !test_bit(id, ud->rflow_gp_map);
+}
+EXPORT_SYMBOL(xudma_rflow_is_gp);
+
+#define XUDMA_GET_PUT_RESOURCE(res)					\
+struct udma_##res *xudma_##res##_get(struct udma_dev *ud, int id)	\
+{									\
+	return __udma_reserve_##res(ud, false, id);			\
+}									\
+EXPORT_SYMBOL(xudma_##res##_get);					\
+									\
+void xudma_##res##_put(struct udma_dev *ud, struct udma_##res *p)	\
+{									\
+	clear_bit(p->id, ud->res##_map);				\
+}									\
+EXPORT_SYMBOL(xudma_##res##_put)
+XUDMA_GET_PUT_RESOURCE(tchan);
+XUDMA_GET_PUT_RESOURCE(rchan);
+
+struct udma_rflow *xudma_rflow_get(struct udma_dev *ud, int id)
+{
+	return __udma_get_rflow(ud, id);
+}
+EXPORT_SYMBOL(xudma_rflow_get);
+
+void xudma_rflow_put(struct udma_dev *ud, struct udma_rflow *p)
+{
+	__udma_put_rflow(ud, p);
+}
+EXPORT_SYMBOL(xudma_rflow_put);
+
+#define XUDMA_GET_RESOURCE_ID(res)					\
+int xudma_##res##_get_id(struct udma_##res *p)				\
+{									\
+	return p->id;							\
+}									\
+EXPORT_SYMBOL(xudma_##res##_get_id)
+XUDMA_GET_RESOURCE_ID(tchan);
+XUDMA_GET_RESOURCE_ID(rchan);
+XUDMA_GET_RESOURCE_ID(rflow);
+
+/* Exported register access functions */
+#define XUDMA_RT_IO_FUNCTIONS(res)					\
+u32 xudma_##res##rt_read(struct udma_##res *p, int reg)			\
+{									\
+	return udma_##res##rt_read(p, reg);				\
+}									\
+EXPORT_SYMBOL(xudma_##res##rt_read);					\
+									\
+void xudma_##res##rt_write(struct udma_##res *p, int reg, u32 val)	\
+{									\
+	udma_##res##rt_write(p, reg, val);				\
+}									\
+EXPORT_SYMBOL(xudma_##res##rt_write)
+XUDMA_RT_IO_FUNCTIONS(tchan);
+XUDMA_RT_IO_FUNCTIONS(rchan);
diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c
new file mode 100644
index 000000000000..0536866a58ce
--- /dev/null
+++ b/drivers/dma/ti/k3-udma.c
@@ -0,0 +1,3661 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com
+ *  Author: Peter Ujfalusi <peter.ujfalusi@ti.com>
+ */
+
+#include <linux/kernel.h>
+#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>
+#include <linux/list.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/of.h>
+#include <linux/of_dma.h>
+#include <linux/of_device.h>
+#include <linux/of_irq.h>
+#include <linux/workqueue.h>
+#include <linux/completion.h>
+#include <linux/soc/ti/k3-ringacc.h>
+#include <linux/soc/ti/ti_sci_protocol.h>
+#include <linux/soc/ti/ti_sci_inta_msi.h>
+#include <linux/dma/ti-cppi5.h>
+
+#include "../virt-dma.h"
+#include "k3-udma.h"
+#include "k3-psil-priv.h"
+
+struct udma_static_tr {
+	u8 elsize; /* RPSTR0 */
+	u16 elcnt; /* RPSTR0 */
+	u16 bstcnt; /* RPSTR1 */
+};
+
+#define K3_UDMA_MAX_RFLOWS		1024
+#define K3_UDMA_DEFAULT_RING_SIZE	16
+
+/* How SRC/DST tag should be updated by UDMA in the descriptor's Word 3 */
+#define UDMA_RFLOW_SRCTAG_NONE		0
+#define UDMA_RFLOW_SRCTAG_CFG_TAG	1
+#define UDMA_RFLOW_SRCTAG_FLOW_ID	2
+#define UDMA_RFLOW_SRCTAG_SRC_TAG	4
+
+#define UDMA_RFLOW_DSTTAG_NONE		0
+#define UDMA_RFLOW_DSTTAG_CFG_TAG	1
+#define UDMA_RFLOW_DSTTAG_FLOW_ID	2
+#define UDMA_RFLOW_DSTTAG_DST_TAG_LO	4
+#define UDMA_RFLOW_DSTTAG_DST_TAG_HI	5
+
+struct udma_chan;
+
+enum udma_mmr {
+	MMR_GCFG = 0,
+	MMR_RCHANRT,
+	MMR_TCHANRT,
+	MMR_LAST,
+};
+
+static const char * const mmr_names[] = { "gcfg", "rchanrt", "tchanrt" };
+
+struct udma_tchan {
+	void __iomem *reg_rt;
+
+	int id;
+	struct k3_ring *t_ring; /* Transmit ring */
+	struct k3_ring *tc_ring; /* Transmit Completion ring */
+};
+
+struct udma_rflow {
+	int id;
+	struct k3_ring *fd_ring; /* Free Descriptor ring */
+	struct k3_ring *r_ring; /* Receive ring */
+};
+
+struct udma_rchan {
+	void __iomem *reg_rt;
+
+	int id;
+};
+
+#define UDMA_FLAG_PDMA_ACC32		BIT(0)
+#define UDMA_FLAG_PDMA_BURST		BIT(1)
+
+struct udma_match_data {
+	u32 psil_base;
+	bool enable_memcpy_support;
+	u32 flags;
+	u32 statictr_z_mask;
+	u32 rchan_oes_offset;
+
+	u8 tpl_levels;
+	u32 level_start_idx[];
+};
+
+struct udma_hwdesc {
+	size_t cppi5_desc_size;
+	void *cppi5_desc_vaddr;
+	dma_addr_t cppi5_desc_paddr;
+
+	/* TR descriptor internal pointers */
+	void *tr_req_base;
+	struct cppi5_tr_resp_t *tr_resp_base;
+};
+
+struct udma_rx_flush {
+	struct udma_hwdesc hwdescs[2];
+
+	size_t buffer_size;
+	void *buffer_vaddr;
+	dma_addr_t buffer_paddr;
+};
+
+struct udma_dev {
+	struct dma_device ddev;
+	struct device *dev;
+	void __iomem *mmrs[MMR_LAST];
+	const struct udma_match_data *match_data;
+
+	size_t desc_align; /* alignment to use for descriptors */
+
+	struct udma_tisci_rm tisci_rm;
+
+	struct k3_ringacc *ringacc;
+
+	struct work_struct purge_work;
+	struct list_head desc_to_purge;
+	spinlock_t lock;
+
+	struct udma_rx_flush rx_flush;
+
+	int tchan_cnt;
+	int echan_cnt;
+	int rchan_cnt;
+	int rflow_cnt;
+	unsigned long *tchan_map;
+	unsigned long *rchan_map;
+	unsigned long *rflow_gp_map;
+	unsigned long *rflow_gp_map_allocated;
+	unsigned long *rflow_in_use;
+
+	struct udma_tchan *tchans;
+	struct udma_rchan *rchans;
+	struct udma_rflow *rflows;
+
+	struct udma_chan *channels;
+	u32 psil_base;
+};
+
+struct udma_desc {
+	struct virt_dma_desc vd;
+
+	bool terminated;
+
+	enum dma_transfer_direction dir;
+
+	struct udma_static_tr static_tr;
+	u32 residue;
+
+	unsigned int sglen;
+	unsigned int desc_idx; /* Only used for cyclic in packet mode */
+	unsigned int tr_idx;
+
+	u32 metadata_size;
+	void *metadata; /* pointer to provided metadata buffer (EPIP, PSdata) */
+
+	unsigned int hwdesc_count;
+	struct udma_hwdesc hwdesc[0];
+};
+
+enum udma_chan_state {
+	UDMA_CHAN_IS_IDLE = 0, /* not active, no teardown is in progress */
+	UDMA_CHAN_IS_ACTIVE, /* Normal operation */
+	UDMA_CHAN_IS_TERMINATING, /* channel is being terminated */
+};
+
+struct udma_tx_drain {
+	struct delayed_work work;
+	ktime_t tstamp;
+	u32 residue;
+};
+
+struct udma_chan_config {
+	bool pkt_mode; /* TR or packet */
+	bool needs_epib; /* EPIB is needed for the communication or not */
+	u32 psd_size; /* size of Protocol Specific Data */
+	u32 metadata_size; /* (needs_epib ? 16:0) + psd_size */
+	u32 hdesc_size; /* Size of a packet descriptor in packet mode */
+	bool notdpkt; /* Suppress sending TDC packet */
+	int remote_thread_id;
+	u32 src_thread;
+	u32 dst_thread;
+	enum psil_endpoint_type ep_type;
+	bool enable_acc32;
+	bool enable_burst;
+	enum udma_tp_level channel_tpl; /* Channel Throughput Level */
+
+	enum dma_transfer_direction dir;
+};
+
+struct udma_chan {
+	struct virt_dma_chan vc;
+	struct dma_slave_config	cfg;
+	struct udma_dev *ud;
+	struct udma_desc *desc;
+	struct udma_desc *terminated_desc;
+	struct udma_static_tr static_tr;
+	char *name;
+
+	struct udma_tchan *tchan;
+	struct udma_rchan *rchan;
+	struct udma_rflow *rflow;
+
+	bool psil_paired;
+
+	int irq_num_ring;
+	int irq_num_udma;
+
+	bool cyclic;
+	bool paused;
+
+	enum udma_chan_state state;
+	struct completion teardown_completed;
+
+	struct udma_tx_drain tx_drain;
+
+	u32 bcnt; /* number of bytes completed since the start of the channel */
+	u32 in_ring_cnt; /* number of descriptors in flight */
+
+	/* Channel configuration parameters */
+	struct udma_chan_config config;
+
+	/* dmapool for packet mode descriptors */
+	bool use_dma_pool;
+	struct dma_pool *hdesc_pool;
+
+	u32 id;
+};
+
+static inline struct udma_dev *to_udma_dev(struct dma_device *d)
+{
+	return container_of(d, struct udma_dev, ddev);
+}
+
+static inline struct udma_chan *to_udma_chan(struct dma_chan *c)
+{
+	return container_of(c, struct udma_chan, vc.chan);
+}
+
+static inline struct udma_desc *to_udma_desc(struct dma_async_tx_descriptor *t)
+{
+	return container_of(t, struct udma_desc, vd.tx);
+}
+
+/* Generic register access functions */
+static inline u32 udma_read(void __iomem *base, int reg)
+{
+	return readl(base + reg);
+}
+
+static inline void udma_write(void __iomem *base, int reg, u32 val)
+{
+	writel(val, base + reg);
+}
+
+static inline void udma_update_bits(void __iomem *base, int reg,
+				    u32 mask, u32 val)
+{
+	u32 tmp, orig;
+
+	orig = readl(base + reg);
+	tmp = orig & ~mask;
+	tmp |= (val & mask);
+
+	if (tmp != orig)
+		writel(tmp, base + reg);
+}
+
+/* TCHANRT */
+static inline u32 udma_tchanrt_read(struct udma_tchan *tchan, int reg)
+{
+	if (!tchan)
+		return 0;
+	return udma_read(tchan->reg_rt, reg);
+}
+
+static inline void udma_tchanrt_write(struct udma_tchan *tchan, int reg,
+				      u32 val)
+{
+	if (!tchan)
+		return;
+	udma_write(tchan->reg_rt, reg, val);
+}
+
+static inline void udma_tchanrt_update_bits(struct udma_tchan *tchan, int reg,
+					    u32 mask, u32 val)
+{
+	if (!tchan)
+		return;
+	udma_update_bits(tchan->reg_rt, reg, mask, val);
+}
+
+/* RCHANRT */
+static inline u32 udma_rchanrt_read(struct udma_rchan *rchan, int reg)
+{
+	if (!rchan)
+		return 0;
+	return udma_read(rchan->reg_rt, reg);
+}
+
+static inline void udma_rchanrt_write(struct udma_rchan *rchan, int reg,
+				      u32 val)
+{
+	if (!rchan)
+		return;
+	udma_write(rchan->reg_rt, reg, val);
+}
+
+static inline void udma_rchanrt_update_bits(struct udma_rchan *rchan, int reg,
+					    u32 mask, u32 val)
+{
+	if (!rchan)
+		return;
+	udma_update_bits(rchan->reg_rt, reg, mask, val);
+}
+
+static int navss_psil_pair(struct udma_dev *ud, u32 src_thread, u32 dst_thread)
+{
+	struct udma_tisci_rm *tisci_rm = &ud->tisci_rm;
+
+	dst_thread |= K3_PSIL_DST_THREAD_ID_OFFSET;
+	return tisci_rm->tisci_psil_ops->pair(tisci_rm->tisci,
+					      tisci_rm->tisci_navss_dev_id,
+					      src_thread, dst_thread);
+}
+
+static int navss_psil_unpair(struct udma_dev *ud, u32 src_thread,
+			     u32 dst_thread)
+{
+	struct udma_tisci_rm *tisci_rm = &ud->tisci_rm;
+
+	dst_thread |= K3_PSIL_DST_THREAD_ID_OFFSET;
+	return tisci_rm->tisci_psil_ops->unpair(tisci_rm->tisci,
+						tisci_rm->tisci_navss_dev_id,
+						src_thread, dst_thread);
+}
+
+static void udma_reset_uchan(struct udma_chan *uc)
+{
+	memset(&uc->config, 0, sizeof(uc->config));
+	uc->config.remote_thread_id = -1;
+	uc->state = UDMA_CHAN_IS_IDLE;
+}
+
+static void udma_dump_chan_stdata(struct udma_chan *uc)
+{
+	struct device *dev = uc->ud->dev;
+	u32 offset;
+	int i;
+
+	if (uc->config.dir == DMA_MEM_TO_DEV || uc->config.dir == DMA_MEM_TO_MEM) {
+		dev_dbg(dev, "TCHAN State data:\n");
+		for (i = 0; i < 32; i++) {
+			offset = UDMA_TCHAN_RT_STDATA_REG + i * 4;
+			dev_dbg(dev, "TRT_STDATA[%02d]: 0x%08x\n", i,
+				udma_tchanrt_read(uc->tchan, offset));
+		}
+	}
+
+	if (uc->config.dir == DMA_DEV_TO_MEM || uc->config.dir == DMA_MEM_TO_MEM) {
+		dev_dbg(dev, "RCHAN State data:\n");
+		for (i = 0; i < 32; i++) {
+			offset = UDMA_RCHAN_RT_STDATA_REG + i * 4;
+			dev_dbg(dev, "RRT_STDATA[%02d]: 0x%08x\n", i,
+				udma_rchanrt_read(uc->rchan, offset));
+		}
+	}
+}
+
+static inline dma_addr_t udma_curr_cppi5_desc_paddr(struct udma_desc *d,
+						    int idx)
+{
+	return d->hwdesc[idx].cppi5_desc_paddr;
+}
+
+static inline void *udma_curr_cppi5_desc_vaddr(struct udma_desc *d, int idx)
+{
+	return d->hwdesc[idx].cppi5_desc_vaddr;
+}
+
+static struct udma_desc *udma_udma_desc_from_paddr(struct udma_chan *uc,
+						   dma_addr_t paddr)
+{
+	struct udma_desc *d = uc->terminated_desc;
+
+	if (d) {
+		dma_addr_t desc_paddr = udma_curr_cppi5_desc_paddr(d,
+								   d->desc_idx);
+
+		if (desc_paddr != paddr)
+			d = NULL;
+	}
+
+	if (!d) {
+		d = uc->desc;
+		if (d) {
+			dma_addr_t desc_paddr = udma_curr_cppi5_desc_paddr(d,
+								d->desc_idx);
+
+			if (desc_paddr != paddr)
+				d = NULL;
+		}
+	}
+
+	return d;
+}
+
+static void udma_free_hwdesc(struct udma_chan *uc, struct udma_desc *d)
+{
+	if (uc->use_dma_pool) {
+		int i;
+
+		for (i = 0; i < d->hwdesc_count; i++) {
+			if (!d->hwdesc[i].cppi5_desc_vaddr)
+				continue;
+
+			dma_pool_free(uc->hdesc_pool,
+				      d->hwdesc[i].cppi5_desc_vaddr,
+				      d->hwdesc[i].cppi5_desc_paddr);
+
+			d->hwdesc[i].cppi5_desc_vaddr = NULL;
+		}
+	} else if (d->hwdesc[0].cppi5_desc_vaddr) {
+		struct udma_dev *ud = uc->ud;
+
+		dma_free_coherent(ud->dev, d->hwdesc[0].cppi5_desc_size,
+				  d->hwdesc[0].cppi5_desc_vaddr,
+				  d->hwdesc[0].cppi5_desc_paddr);
+
+		d->hwdesc[0].cppi5_desc_vaddr = NULL;
+	}
+}
+
+static void udma_purge_desc_work(struct work_struct *work)
+{
+	struct udma_dev *ud = container_of(work, typeof(*ud), purge_work);
+	struct virt_dma_desc *vd, *_vd;
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	spin_lock_irqsave(&ud->lock, flags);
+	list_splice_tail_init(&ud->desc_to_purge, &head);
+	spin_unlock_irqrestore(&ud->lock, flags);
+
+	list_for_each_entry_safe(vd, _vd, &head, node) {
+		struct udma_chan *uc = to_udma_chan(vd->tx.chan);
+		struct udma_desc *d = to_udma_desc(&vd->tx);
+
+		udma_free_hwdesc(uc, d);
+		list_del(&vd->node);
+		kfree(d);
+	}
+
+	/* If more to purge, schedule the work again */
+	if (!list_empty(&ud->desc_to_purge))
+		schedule_work(&ud->purge_work);
+}
+
+static void udma_desc_free(struct virt_dma_desc *vd)
+{
+	struct udma_dev *ud = to_udma_dev(vd->tx.chan->device);
+	struct udma_chan *uc = to_udma_chan(vd->tx.chan);
+	struct udma_desc *d = to_udma_desc(&vd->tx);
+	unsigned long flags;
+
+	if (uc->terminated_desc == d)
+		uc->terminated_desc = NULL;
+
+	if (uc->use_dma_pool) {
+		udma_free_hwdesc(uc, d);
+		kfree(d);
+		return;
+	}
+
+	spin_lock_irqsave(&ud->lock, flags);
+	list_add_tail(&vd->node, &ud->desc_to_purge);
+	spin_unlock_irqrestore(&ud->lock, flags);
+
+	schedule_work(&ud->purge_work);
+}
+
+static bool udma_is_chan_running(struct udma_chan *uc)
+{
+	u32 trt_ctl = 0;
+	u32 rrt_ctl = 0;
+
+	if (uc->tchan)
+		trt_ctl = udma_tchanrt_read(uc->tchan, UDMA_TCHAN_RT_CTL_REG);
+	if (uc->rchan)
+		rrt_ctl = udma_rchanrt_read(uc->rchan, UDMA_RCHAN_RT_CTL_REG);
+
+	if (trt_ctl & UDMA_CHAN_RT_CTL_EN || rrt_ctl & UDMA_CHAN_RT_CTL_EN)
+		return true;
+
+	return false;
+}
+
+static bool udma_is_chan_paused(struct udma_chan *uc)
+{
+	u32 val, pause_mask;
+
+	switch (uc->config.dir) {
+	case DMA_DEV_TO_MEM:
+		val = udma_rchanrt_read(uc->rchan,
+					UDMA_RCHAN_RT_PEER_RT_EN_REG);
+		pause_mask = UDMA_PEER_RT_EN_PAUSE;
+		break;
+	case DMA_MEM_TO_DEV:
+		val = udma_tchanrt_read(uc->tchan,
+					UDMA_TCHAN_RT_PEER_RT_EN_REG);
+		pause_mask = UDMA_PEER_RT_EN_PAUSE;
+		break;
+	case DMA_MEM_TO_MEM:
+		val = udma_tchanrt_read(uc->tchan, UDMA_TCHAN_RT_CTL_REG);
+		pause_mask = UDMA_CHAN_RT_CTL_PAUSE;
+		break;
+	default:
+		return false;
+	}
+
+	if (val & pause_mask)
+		return true;
+
+	return false;
+}
+
+static void udma_sync_for_device(struct udma_chan *uc, int idx)
+{
+	struct udma_desc *d = uc->desc;
+
+	if (uc->cyclic && uc->config.pkt_mode) {
+		dma_sync_single_for_device(uc->ud->dev,
+					   d->hwdesc[idx].cppi5_desc_paddr,
+					   d->hwdesc[idx].cppi5_desc_size,
+					   DMA_TO_DEVICE);
+	} else {
+		int i;
+
+		for (i = 0; i < d->hwdesc_count; i++) {
+			if (!d->hwdesc[i].cppi5_desc_vaddr)
+				continue;
+
+			dma_sync_single_for_device(uc->ud->dev,
+						d->hwdesc[i].cppi5_desc_paddr,
+						d->hwdesc[i].cppi5_desc_size,
+						DMA_TO_DEVICE);
+		}
+	}
+}
+
+static inline dma_addr_t udma_get_rx_flush_hwdesc_paddr(struct udma_chan *uc)
+{
+	return uc->ud->rx_flush.hwdescs[uc->config.pkt_mode].cppi5_desc_paddr;
+}
+
+static int udma_push_to_ring(struct udma_chan *uc, int idx)
+{
+	struct udma_desc *d = uc->desc;
+	struct k3_ring *ring = NULL;
+	dma_addr_t paddr;
+	int ret;
+
+	switch (uc->config.dir) {
+	case DMA_DEV_TO_MEM:
+		ring = uc->rflow->fd_ring;
+		break;
+	case DMA_MEM_TO_DEV:
+	case DMA_MEM_TO_MEM:
+		ring = uc->tchan->t_ring;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* RX flush packet: idx == -1 is only passed in case of DEV_TO_MEM */
+	if (idx == -1) {
+		paddr = udma_get_rx_flush_hwdesc_paddr(uc);
+	} else {
+		paddr = udma_curr_cppi5_desc_paddr(d, idx);
+
+		wmb(); /* Ensure that writes are not moved over this point */
+		udma_sync_for_device(uc, idx);
+	}
+
+	ret = k3_ringacc_ring_push(ring, &paddr);
+	if (!ret)
+		uc->in_ring_cnt++;
+
+	return ret;
+}
+
+static bool udma_desc_is_rx_flush(struct udma_chan *uc, dma_addr_t addr)
+{
+	if (uc->config.dir != DMA_DEV_TO_MEM)
+		return false;
+
+	if (addr == udma_get_rx_flush_hwdesc_paddr(uc))
+		return true;
+
+	return false;
+}
+
+static int udma_pop_from_ring(struct udma_chan *uc, dma_addr_t *addr)
+{
+	struct k3_ring *ring = NULL;
+	int ret = -ENOENT;
+
+	switch (uc->config.dir) {
+	case DMA_DEV_TO_MEM:
+		ring = uc->rflow->r_ring;
+		break;
+	case DMA_MEM_TO_DEV:
+	case DMA_MEM_TO_MEM:
+		ring = uc->tchan->tc_ring;
+		break;
+	default:
+		break;
+	}
+
+	if (ring && k3_ringacc_ring_get_occ(ring)) {
+		struct udma_desc *d = NULL;
+
+		ret = k3_ringacc_ring_pop(ring, addr);
+		if (ret)
+			return ret;
+
+		/* Teardown completion */
+		if (cppi5_desc_is_tdcm(*addr))
+			return ret;
+
+		/* Check for flush descriptor */
+		if (udma_desc_is_rx_flush(uc, *addr))
+			return -ENOENT;
+
+		d = udma_udma_desc_from_paddr(uc, *addr);
+
+		if (d)
+			dma_sync_single_for_cpu(uc->ud->dev, *addr,
+						d->hwdesc[0].cppi5_desc_size,
+						DMA_FROM_DEVICE);
+		rmb(); /* Ensure that reads are not moved before this point */
+
+		if (!ret)
+			uc->in_ring_cnt--;
+	}
+
+	return ret;
+}
+
+static void udma_reset_rings(struct udma_chan *uc)
+{
+	struct k3_ring *ring1 = NULL;
+	struct k3_ring *ring2 = NULL;
+
+	switch (uc->config.dir) {
+	case DMA_DEV_TO_MEM:
+		if (uc->rchan) {
+			ring1 = uc->rflow->fd_ring;
+			ring2 = uc->rflow->r_ring;
+		}
+		break;
+	case DMA_MEM_TO_DEV:
+	case DMA_MEM_TO_MEM:
+		if (uc->tchan) {
+			ring1 = uc->tchan->t_ring;
+			ring2 = uc->tchan->tc_ring;
+		}
+		break;
+	default:
+		break;
+	}
+
+	if (ring1)
+		k3_ringacc_ring_reset_dma(ring1,
+					  k3_ringacc_ring_get_occ(ring1));
+	if (ring2)
+		k3_ringacc_ring_reset(ring2);
+
+	/* make sure we are not leaking memory by stalled descriptor */
+	if (uc->terminated_desc) {
+		udma_desc_free(&uc->terminated_desc->vd);
+		uc->terminated_desc = NULL;
+	}
+
+	uc->in_ring_cnt = 0;
+}
+
+static void udma_reset_counters(struct udma_chan *uc)
+{
+	u32 val;
+
+	if (uc->tchan) {
+		val = udma_tchanrt_read(uc->tchan, UDMA_TCHAN_RT_BCNT_REG);
+		udma_tchanrt_write(uc->tchan, UDMA_TCHAN_RT_BCNT_REG, val);
+
+		val = udma_tchanrt_read(uc->tchan, UDMA_TCHAN_RT_SBCNT_REG);
+		udma_tchanrt_write(uc->tchan, UDMA_TCHAN_RT_SBCNT_REG, val);
+
+		val = udma_tchanrt_read(uc->tchan, UDMA_TCHAN_RT_PCNT_REG);
+		udma_tchanrt_write(uc->tchan, UDMA_TCHAN_RT_PCNT_REG, val);
+
+		val = udma_tchanrt_read(uc->tchan, UDMA_TCHAN_RT_PEER_BCNT_REG);
+		udma_tchanrt_write(uc->tchan, UDMA_TCHAN_RT_PEER_BCNT_REG, val);
+	}
+
+	if (uc->rchan) {
+		val = udma_rchanrt_read(uc->rchan, UDMA_RCHAN_RT_BCNT_REG);
+		udma_rchanrt_write(uc->rchan, UDMA_RCHAN_RT_BCNT_REG, val);
+
+		val = udma_rchanrt_read(uc->rchan, UDMA_RCHAN_RT_SBCNT_REG);
+		udma_rchanrt_write(uc->rchan, UDMA_RCHAN_RT_SBCNT_REG, val);
+
+		val = udma_rchanrt_read(uc->rchan, UDMA_RCHAN_RT_PCNT_REG);
+		udma_rchanrt_write(uc->rchan, UDMA_RCHAN_RT_PCNT_REG, val);
+
+		val = udma_rchanrt_read(uc->rchan, UDMA_RCHAN_RT_PEER_BCNT_REG);
+		udma_rchanrt_write(uc->rchan, UDMA_RCHAN_RT_PEER_BCNT_REG, val);
+	}
+
+	uc->bcnt = 0;
+}
+
+static int udma_reset_chan(struct udma_chan *uc, bool hard)
+{
+	switch (uc->config.dir) {
+	case DMA_DEV_TO_MEM:
+		udma_rchanrt_write(uc->rchan, UDMA_RCHAN_RT_PEER_RT_EN_REG, 0);
+		udma_rchanrt_write(uc->rchan, UDMA_RCHAN_RT_CTL_REG, 0);
+		break;
+	case DMA_MEM_TO_DEV:
+		udma_tchanrt_write(uc->tchan, UDMA_TCHAN_RT_CTL_REG, 0);
+		udma_tchanrt_write(uc->tchan, UDMA_TCHAN_RT_PEER_RT_EN_REG, 0);
+		break;
+	case DMA_MEM_TO_MEM:
+		udma_rchanrt_write(uc->rchan, UDMA_RCHAN_RT_CTL_REG, 0);
+		udma_tchanrt_write(uc->tchan, UDMA_TCHAN_RT_CTL_REG, 0);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Reset all counters */
+	udma_reset_counters(uc);
+
+	/* Hard reset: re-initialize the channel to reset */
+	if (hard) {
+		struct udma_chan_config ucc_backup;
+		int ret;
+
+		memcpy(&ucc_backup, &uc->config, sizeof(uc->config));
+		uc->ud->ddev.device_free_chan_resources(&uc->vc.chan);
+
+		/* restore the channel configuration */
+		memcpy(&uc->config, &ucc_backup, sizeof(uc->config));
+		ret = uc->ud->ddev.device_alloc_chan_resources(&uc->vc.chan);
+		if (ret)
+			return ret;
+
+		/*
+		 * Setting forced teardown after forced reset helps recovering
+		 * the rchan.
+		 */
+		if (uc->config.dir == DMA_DEV_TO_MEM)
+			udma_rchanrt_write(uc->rchan, UDMA_RCHAN_RT_CTL_REG,
+					   UDMA_CHAN_RT_CTL_EN |
+					   UDMA_CHAN_RT_CTL_TDOWN |
+					   UDMA_CHAN_RT_CTL_FTDOWN);
+	}
+	uc->state = UDMA_CHAN_IS_IDLE;
+
+	return 0;
+}
+
+static void udma_start_desc(struct udma_chan *uc)
+{
+	struct udma_chan_config *ucc = &uc->config;
+
+	if (ucc->pkt_mode && (uc->cyclic || ucc->dir == DMA_DEV_TO_MEM)) {
+		int i;
+
+		/* Push all descriptors to ring for packet mode cyclic or RX */
+		for (i = 0; i < uc->desc->sglen; i++)
+			udma_push_to_ring(uc, i);
+	} else {
+		udma_push_to_ring(uc, 0);
+	}
+}
+
+static bool udma_chan_needs_reconfiguration(struct udma_chan *uc)
+{
+	/* Only PDMAs have staticTR */
+	if (uc->config.ep_type == PSIL_EP_NATIVE)
+		return false;
+
+	/* Check if the staticTR configuration has changed for TX */
+	if (memcmp(&uc->static_tr, &uc->desc->static_tr, sizeof(uc->static_tr)))
+		return true;
+
+	return false;
+}
+
+static int udma_start(struct udma_chan *uc)
+{
+	struct virt_dma_desc *vd = vchan_next_desc(&uc->vc);
+
+	if (!vd) {
+		uc->desc = NULL;
+		return -ENOENT;
+	}
+
+	list_del(&vd->node);
+
+	uc->desc = to_udma_desc(&vd->tx);
+
+	/* Channel is already running and does not need reconfiguration */
+	if (udma_is_chan_running(uc) && !udma_chan_needs_reconfiguration(uc)) {
+		udma_start_desc(uc);
+		goto out;
+	}
+
+	/* Make sure that we clear the teardown bit, if it is set */
+	udma_reset_chan(uc, false);
+
+	/* Push descriptors before we start the channel */
+	udma_start_desc(uc);
+
+	switch (uc->desc->dir) {
+	case DMA_DEV_TO_MEM:
+		/* Config remote TR */
+		if (uc->config.ep_type == PSIL_EP_PDMA_XY) {
+			u32 val = PDMA_STATIC_TR_Y(uc->desc->static_tr.elcnt) |
+				  PDMA_STATIC_TR_X(uc->desc->static_tr.elsize);
+			const struct udma_match_data *match_data =
+							uc->ud->match_data;
+
+			if (uc->config.enable_acc32)
+				val |= PDMA_STATIC_TR_XY_ACC32;
+			if (uc->config.enable_burst)
+				val |= PDMA_STATIC_TR_XY_BURST;
+
+			udma_rchanrt_write(uc->rchan,
+				UDMA_RCHAN_RT_PEER_STATIC_TR_XY_REG, val);
+
+			udma_rchanrt_write(uc->rchan,
+				UDMA_RCHAN_RT_PEER_STATIC_TR_Z_REG,
+				PDMA_STATIC_TR_Z(uc->desc->static_tr.bstcnt,
+						 match_data->statictr_z_mask));
+
+			/* save the current staticTR configuration */
+			memcpy(&uc->static_tr, &uc->desc->static_tr,
+			       sizeof(uc->static_tr));
+		}
+
+		udma_rchanrt_write(uc->rchan, UDMA_RCHAN_RT_CTL_REG,
+				   UDMA_CHAN_RT_CTL_EN);
+
+		/* Enable remote */
+		udma_rchanrt_write(uc->rchan, UDMA_RCHAN_RT_PEER_RT_EN_REG,
+				   UDMA_PEER_RT_EN_ENABLE);
+
+		break;
+	case DMA_MEM_TO_DEV:
+		/* Config remote TR */
+		if (uc->config.ep_type == PSIL_EP_PDMA_XY) {
+			u32 val = PDMA_STATIC_TR_Y(uc->desc->static_tr.elcnt) |
+				  PDMA_STATIC_TR_X(uc->desc->static_tr.elsize);
+
+			if (uc->config.enable_acc32)
+				val |= PDMA_STATIC_TR_XY_ACC32;
+			if (uc->config.enable_burst)
+				val |= PDMA_STATIC_TR_XY_BURST;
+
+			udma_tchanrt_write(uc->tchan,
+				UDMA_TCHAN_RT_PEER_STATIC_TR_XY_REG, val);
+
+			/* save the current staticTR configuration */
+			memcpy(&uc->static_tr, &uc->desc->static_tr,
+			       sizeof(uc->static_tr));
+		}
+
+		/* Enable remote */
+		udma_tchanrt_write(uc->tchan, UDMA_TCHAN_RT_PEER_RT_EN_REG,
+				   UDMA_PEER_RT_EN_ENABLE);
+
+		udma_tchanrt_write(uc->tchan, UDMA_TCHAN_RT_CTL_REG,
+				   UDMA_CHAN_RT_CTL_EN);
+
+		break;
+	case DMA_MEM_TO_MEM:
+		udma_rchanrt_write(uc->rchan, UDMA_RCHAN_RT_CTL_REG,
+				   UDMA_CHAN_RT_CTL_EN);
+		udma_tchanrt_write(uc->tchan, UDMA_TCHAN_RT_CTL_REG,
+				   UDMA_CHAN_RT_CTL_EN);
+
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	uc->state = UDMA_CHAN_IS_ACTIVE;
+out:
+
+	return 0;
+}
+
+static int udma_stop(struct udma_chan *uc)
+{
+	enum udma_chan_state old_state = uc->state;
+
+	uc->state = UDMA_CHAN_IS_TERMINATING;
+	reinit_completion(&uc->teardown_completed);
+
+	switch (uc->config.dir) {
+	case DMA_DEV_TO_MEM:
+		if (!uc->cyclic && !uc->desc)
+			udma_push_to_ring(uc, -1);
+
+		udma_rchanrt_write(uc->rchan, UDMA_RCHAN_RT_PEER_RT_EN_REG,
+				   UDMA_PEER_RT_EN_ENABLE |
+				   UDMA_PEER_RT_EN_TEARDOWN);
+		break;
+	case DMA_MEM_TO_DEV:
+		udma_tchanrt_write(uc->tchan, UDMA_TCHAN_RT_PEER_RT_EN_REG,
+				   UDMA_PEER_RT_EN_ENABLE |
+				   UDMA_PEER_RT_EN_FLUSH);
+		udma_tchanrt_write(uc->tchan, UDMA_TCHAN_RT_CTL_REG,
+				   UDMA_CHAN_RT_CTL_EN |
+				   UDMA_CHAN_RT_CTL_TDOWN);
+		break;
+	case DMA_MEM_TO_MEM:
+		udma_tchanrt_write(uc->tchan, UDMA_TCHAN_RT_CTL_REG,
+				   UDMA_CHAN_RT_CTL_EN |
+				   UDMA_CHAN_RT_CTL_TDOWN);
+		break;
+	default:
+		uc->state = old_state;
+		complete_all(&uc->teardown_completed);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void udma_cyclic_packet_elapsed(struct udma_chan *uc)
+{
+	struct udma_desc *d = uc->desc;
+	struct cppi5_host_desc_t *h_desc;
+
+	h_desc = d->hwdesc[d->desc_idx].cppi5_desc_vaddr;
+	cppi5_hdesc_reset_to_original(h_desc);
+	udma_push_to_ring(uc, d->desc_idx);
+	d->desc_idx = (d->desc_idx + 1) % d->sglen;
+}
+
+static inline void udma_fetch_epib(struct udma_chan *uc, struct udma_desc *d)
+{
+	struct cppi5_host_desc_t *h_desc = d->hwdesc[0].cppi5_desc_vaddr;
+
+	memcpy(d->metadata, h_desc->epib, d->metadata_size);
+}
+
+static bool udma_is_desc_really_done(struct udma_chan *uc, struct udma_desc *d)
+{
+	u32 peer_bcnt, bcnt;
+
+	/* Only TX towards PDMA is affected */
+	if (uc->config.ep_type == PSIL_EP_NATIVE ||
+	    uc->config.dir != DMA_MEM_TO_DEV)
+		return true;
+
+	peer_bcnt = udma_tchanrt_read(uc->tchan, UDMA_TCHAN_RT_PEER_BCNT_REG);
+	bcnt = udma_tchanrt_read(uc->tchan, UDMA_TCHAN_RT_BCNT_REG);
+
+	/* Transfer is incomplete, store current residue and time stamp */
+	if (peer_bcnt < bcnt) {
+		uc->tx_drain.residue = bcnt - peer_bcnt;
+		uc->tx_drain.tstamp = ktime_get();
+		return false;
+	}
+
+	return true;
+}
+
+static void udma_check_tx_completion(struct work_struct *work)
+{
+	struct udma_chan *uc = container_of(work, typeof(*uc),
+					    tx_drain.work.work);
+	bool desc_done = true;
+	u32 residue_diff;
+	ktime_t time_diff;
+	unsigned long delay;
+
+	while (1) {
+		if (uc->desc) {
+			/* Get previous residue and time stamp */
+			residue_diff = uc->tx_drain.residue;
+			time_diff = uc->tx_drain.tstamp;
+			/*
+			 * Get current residue and time stamp or see if
+			 * transfer is complete
+			 */
+			desc_done = udma_is_desc_really_done(uc, uc->desc);
+		}
+
+		if (!desc_done) {
+			/*
+			 * Find the time delta and residue delta w.r.t
+			 * previous poll
+			 */
+			time_diff = ktime_sub(uc->tx_drain.tstamp,
+					      time_diff) + 1;
+			residue_diff -= uc->tx_drain.residue;
+			if (residue_diff) {
+				/*
+				 * Try to guess when we should check
+				 * next time by calculating rate at
+				 * which data is being drained at the
+				 * peer device
+				 */
+				delay = (time_diff / residue_diff) *
+					uc->tx_drain.residue;
+			} else {
+				/* No progress, check again in 1 second  */
+				schedule_delayed_work(&uc->tx_drain.work, HZ);
+				break;
+			}
+
+			usleep_range(ktime_to_us(delay),
+				     ktime_to_us(delay) + 10);
+			continue;
+		}
+
+		if (uc->desc) {
+			struct udma_desc *d = uc->desc;
+
+			uc->bcnt += d->residue;
+			udma_start(uc);
+			vchan_cookie_complete(&d->vd);
+			break;
+		}
+
+		break;
+	}
+}
+
+static irqreturn_t udma_ring_irq_handler(int irq, void *data)
+{
+	struct udma_chan *uc = data;
+	struct udma_desc *d;
+	unsigned long flags;
+	dma_addr_t paddr = 0;
+
+	if (udma_pop_from_ring(uc, &paddr) || !paddr)
+		return IRQ_HANDLED;
+
+	spin_lock_irqsave(&uc->vc.lock, flags);
+
+	/* Teardown completion message */
+	if (cppi5_desc_is_tdcm(paddr)) {
+		/* Compensate our internal pop/push counter */
+		uc->in_ring_cnt++;
+
+		complete_all(&uc->teardown_completed);
+
+		if (uc->terminated_desc) {
+			udma_desc_free(&uc->terminated_desc->vd);
+			uc->terminated_desc = NULL;
+		}
+
+		if (!uc->desc)
+			udma_start(uc);
+
+		goto out;
+	}
+
+	d = udma_udma_desc_from_paddr(uc, paddr);
+
+	if (d) {
+		dma_addr_t desc_paddr = udma_curr_cppi5_desc_paddr(d,
+								   d->desc_idx);
+		if (desc_paddr != paddr) {
+			dev_err(uc->ud->dev, "not matching descriptors!\n");
+			goto out;
+		}
+
+		if (d == uc->desc) {
+			/* active descriptor */
+			if (uc->cyclic) {
+				udma_cyclic_packet_elapsed(uc);
+				vchan_cyclic_callback(&d->vd);
+			} else {
+				if (udma_is_desc_really_done(uc, d)) {
+					uc->bcnt += d->residue;
+					udma_start(uc);
+					vchan_cookie_complete(&d->vd);
+				} else {
+					schedule_delayed_work(&uc->tx_drain.work,
+							      0);
+				}
+			}
+		} else {
+			/*
+			 * terminated descriptor, mark the descriptor as
+			 * completed to update the channel's cookie marker
+			 */
+			dma_cookie_complete(&d->vd.tx);
+		}
+	}
+out:
+	spin_unlock_irqrestore(&uc->vc.lock, flags);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t udma_udma_irq_handler(int irq, void *data)
+{
+	struct udma_chan *uc = data;
+	struct udma_desc *d;
+	unsigned long flags;
+
+	spin_lock_irqsave(&uc->vc.lock, flags);
+	d = uc->desc;
+	if (d) {
+		d->tr_idx = (d->tr_idx + 1) % d->sglen;
+
+		if (uc->cyclic) {
+			vchan_cyclic_callback(&d->vd);
+		} else {
+			/* TODO: figure out the real amount of data */
+			uc->bcnt += d->residue;
+			udma_start(uc);
+			vchan_cookie_complete(&d->vd);
+		}
+	}
+
+	spin_unlock_irqrestore(&uc->vc.lock, flags);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * __udma_alloc_gp_rflow_range - alloc range of GP RX flows
+ * @ud: UDMA device
+ * @from: Start the search from this flow id number
+ * @cnt: Number of consecutive flow ids to allocate
+ *
+ * Allocate range of RX flow ids for future use, those flows can be requested
+ * only using explicit flow id number. if @from is set to -1 it will try to find
+ * first free range. if @from is positive value it will force allocation only
+ * of the specified range of flows.
+ *
+ * Returns -ENOMEM if can't find free range.
+ * -EEXIST if requested range is busy.
+ * -EINVAL if wrong input values passed.
+ * Returns flow id on success.
+ */
+static int __udma_alloc_gp_rflow_range(struct udma_dev *ud, int from, int cnt)
+{
+	int start, tmp_from;
+	DECLARE_BITMAP(tmp, K3_UDMA_MAX_RFLOWS);
+
+	tmp_from = from;
+	if (tmp_from < 0)
+		tmp_from = ud->rchan_cnt;
+	/* default flows can't be allocated and accessible only by id */
+	if (tmp_from < ud->rchan_cnt)
+		return -EINVAL;
+
+	if (tmp_from + cnt > ud->rflow_cnt)
+		return -EINVAL;
+
+	bitmap_or(tmp, ud->rflow_gp_map, ud->rflow_gp_map_allocated,
+		  ud->rflow_cnt);
+
+	start = bitmap_find_next_zero_area(tmp,
+					   ud->rflow_cnt,
+					   tmp_from, cnt, 0);
+	if (start >= ud->rflow_cnt)
+		return -ENOMEM;
+
+	if (from >= 0 && start != from)
+		return -EEXIST;
+
+	bitmap_set(ud->rflow_gp_map_allocated, start, cnt);
+	return start;
+}
+
+static int __udma_free_gp_rflow_range(struct udma_dev *ud, int from, int cnt)
+{
+	if (from < ud->rchan_cnt)
+		return -EINVAL;
+	if (from + cnt > ud->rflow_cnt)
+		return -EINVAL;
+
+	bitmap_clear(ud->rflow_gp_map_allocated, from, cnt);
+	return 0;
+}
+
+static struct udma_rflow *__udma_get_rflow(struct udma_dev *ud, int id)
+{
+	/*
+	 * Attempt to request rflow by ID can be made for any rflow
+	 * if not in use with assumption that caller knows what's doing.
+	 * TI-SCI FW will perform additional permission check ant way, it's
+	 * safe
+	 */
+
+	if (id < 0 || id >= ud->rflow_cnt)
+		return ERR_PTR(-ENOENT);
+
+	if (test_bit(id, ud->rflow_in_use))
+		return ERR_PTR(-ENOENT);
+
+	/* GP rflow has to be allocated first */
+	if (!test_bit(id, ud->rflow_gp_map) &&
+	    !test_bit(id, ud->rflow_gp_map_allocated))
+		return ERR_PTR(-EINVAL);
+
+	dev_dbg(ud->dev, "get rflow%d\n", id);
+	set_bit(id, ud->rflow_in_use);
+	return &ud->rflows[id];
+}
+
+static void __udma_put_rflow(struct udma_dev *ud, struct udma_rflow *rflow)
+{
+	if (!test_bit(rflow->id, ud->rflow_in_use)) {
+		dev_err(ud->dev, "attempt to put unused rflow%d\n", rflow->id);
+		return;
+	}
+
+	dev_dbg(ud->dev, "put rflow%d\n", rflow->id);
+	clear_bit(rflow->id, ud->rflow_in_use);
+}
+
+#define UDMA_RESERVE_RESOURCE(res)					\
+static struct udma_##res *__udma_reserve_##res(struct udma_dev *ud,	\
+					       enum udma_tp_level tpl,	\
+					       int id)			\
+{									\
+	if (id >= 0) {							\
+		if (test_bit(id, ud->res##_map)) {			\
+			dev_err(ud->dev, "res##%d is in use\n", id);	\
+			return ERR_PTR(-ENOENT);			\
+		}							\
+	} else {							\
+		int start;						\
+									\
+		if (tpl >= ud->match_data->tpl_levels)			\
+			tpl = ud->match_data->tpl_levels - 1;		\
+									\
+		start = ud->match_data->level_start_idx[tpl];		\
+									\
+		id = find_next_zero_bit(ud->res##_map, ud->res##_cnt,	\
+					start);				\
+		if (id == ud->res##_cnt) {				\
+			return ERR_PTR(-ENOENT);			\
+		}							\
+	}								\
+									\
+	set_bit(id, ud->res##_map);					\
+	return &ud->res##s[id];						\
+}
+
+UDMA_RESERVE_RESOURCE(tchan);
+UDMA_RESERVE_RESOURCE(rchan);
+
+static int udma_get_tchan(struct udma_chan *uc)
+{
+	struct udma_dev *ud = uc->ud;
+
+	if (uc->tchan) {
+		dev_dbg(ud->dev, "chan%d: already have tchan%d allocated\n",
+			uc->id, uc->tchan->id);
+		return 0;
+	}
+
+	uc->tchan = __udma_reserve_tchan(ud, uc->config.channel_tpl, -1);
+	if (IS_ERR(uc->tchan))
+		return PTR_ERR(uc->tchan);
+
+	return 0;
+}
+
+static int udma_get_rchan(struct udma_chan *uc)
+{
+	struct udma_dev *ud = uc->ud;
+
+	if (uc->rchan) {
+		dev_dbg(ud->dev, "chan%d: already have rchan%d allocated\n",
+			uc->id, uc->rchan->id);
+		return 0;
+	}
+
+	uc->rchan = __udma_reserve_rchan(ud, uc->config.channel_tpl, -1);
+	if (IS_ERR(uc->rchan))
+		return PTR_ERR(uc->rchan);
+
+	return 0;
+}
+
+static int udma_get_chan_pair(struct udma_chan *uc)
+{
+	struct udma_dev *ud = uc->ud;
+	const struct udma_match_data *match_data = ud->match_data;
+	int chan_id, end;
+
+	if ((uc->tchan && uc->rchan) && uc->tchan->id == uc->rchan->id) {
+		dev_info(ud->dev, "chan%d: already have %d pair allocated\n",
+			 uc->id, uc->tchan->id);
+		return 0;
+	}
+
+	if (uc->tchan) {
+		dev_err(ud->dev, "chan%d: already have tchan%d allocated\n",
+			uc->id, uc->tchan->id);
+		return -EBUSY;
+	} else if (uc->rchan) {
+		dev_err(ud->dev, "chan%d: already have rchan%d allocated\n",
+			uc->id, uc->rchan->id);
+		return -EBUSY;
+	}
+
+	/* Can be optimized, but let's have it like this for now */
+	end = min(ud->tchan_cnt, ud->rchan_cnt);
+	/* Try to use the highest TPL channel pair for MEM_TO_MEM channels */
+	chan_id = match_data->level_start_idx[match_data->tpl_levels - 1];
+	for (; chan_id < end; chan_id++) {
+		if (!test_bit(chan_id, ud->tchan_map) &&
+		    !test_bit(chan_id, ud->rchan_map))
+			break;
+	}
+
+	if (chan_id == end)
+		return -ENOENT;
+
+	set_bit(chan_id, ud->tchan_map);
+	set_bit(chan_id, ud->rchan_map);
+	uc->tchan = &ud->tchans[chan_id];
+	uc->rchan = &ud->rchans[chan_id];
+
+	return 0;
+}
+
+static int udma_get_rflow(struct udma_chan *uc, int flow_id)
+{
+	struct udma_dev *ud = uc->ud;
+
+	if (!uc->rchan) {
+		dev_err(ud->dev, "chan%d: does not have rchan??\n", uc->id);
+		return -EINVAL;
+	}
+
+	if (uc->rflow) {
+		dev_dbg(ud->dev, "chan%d: already have rflow%d allocated\n",
+			uc->id, uc->rflow->id);
+		return 0;
+	}
+
+	uc->rflow = __udma_get_rflow(ud, flow_id);
+	if (IS_ERR(uc->rflow))
+		return PTR_ERR(uc->rflow);
+
+	return 0;
+}
+
+static void udma_put_rchan(struct udma_chan *uc)
+{
+	struct udma_dev *ud = uc->ud;
+
+	if (uc->rchan) {
+		dev_dbg(ud->dev, "chan%d: put rchan%d\n", uc->id,
+			uc->rchan->id);
+		clear_bit(uc->rchan->id, ud->rchan_map);
+		uc->rchan = NULL;
+	}
+}
+
+static void udma_put_tchan(struct udma_chan *uc)
+{
+	struct udma_dev *ud = uc->ud;
+
+	if (uc->tchan) {
+		dev_dbg(ud->dev, "chan%d: put tchan%d\n", uc->id,
+			uc->tchan->id);
+		clear_bit(uc->tchan->id, ud->tchan_map);
+		uc->tchan = NULL;
+	}
+}
+
+static void udma_put_rflow(struct udma_chan *uc)
+{
+	struct udma_dev *ud = uc->ud;
+
+	if (uc->rflow) {
+		dev_dbg(ud->dev, "chan%d: put rflow%d\n", uc->id,
+			uc->rflow->id);
+		__udma_put_rflow(ud, uc->rflow);
+		uc->rflow = NULL;
+	}
+}
+
+static void udma_free_tx_resources(struct udma_chan *uc)
+{
+	if (!uc->tchan)
+		return;
+
+	k3_ringacc_ring_free(uc->tchan->t_ring);
+	k3_ringacc_ring_free(uc->tchan->tc_ring);
+	uc->tchan->t_ring = NULL;
+	uc->tchan->tc_ring = NULL;
+
+	udma_put_tchan(uc);
+}
+
+static int udma_alloc_tx_resources(struct udma_chan *uc)
+{
+	struct k3_ring_cfg ring_cfg;
+	struct udma_dev *ud = uc->ud;
+	int ret;
+
+	ret = udma_get_tchan(uc);
+	if (ret)
+		return ret;
+
+	uc->tchan->t_ring = k3_ringacc_request_ring(ud->ringacc,
+						    uc->tchan->id, 0);
+	if (!uc->tchan->t_ring) {
+		ret = -EBUSY;
+		goto err_tx_ring;
+	}
+
+	uc->tchan->tc_ring = k3_ringacc_request_ring(ud->ringacc, -1, 0);
+	if (!uc->tchan->tc_ring) {
+		ret = -EBUSY;
+		goto err_txc_ring;
+	}
+
+	memset(&ring_cfg, 0, sizeof(ring_cfg));
+	ring_cfg.size = K3_UDMA_DEFAULT_RING_SIZE;
+	ring_cfg.elm_size = K3_RINGACC_RING_ELSIZE_8;
+	ring_cfg.mode = K3_RINGACC_RING_MODE_MESSAGE;
+
+	ret = k3_ringacc_ring_cfg(uc->tchan->t_ring, &ring_cfg);
+	ret |= k3_ringacc_ring_cfg(uc->tchan->tc_ring, &ring_cfg);
+
+	if (ret)
+		goto err_ringcfg;
+
+	return 0;
+
+err_ringcfg:
+	k3_ringacc_ring_free(uc->tchan->tc_ring);
+	uc->tchan->tc_ring = NULL;
+err_txc_ring:
+	k3_ringacc_ring_free(uc->tchan->t_ring);
+	uc->tchan->t_ring = NULL;
+err_tx_ring:
+	udma_put_tchan(uc);
+
+	return ret;
+}
+
+static void udma_free_rx_resources(struct udma_chan *uc)
+{
+	if (!uc->rchan)
+		return;
+
+	if (uc->rflow) {
+		struct udma_rflow *rflow = uc->rflow;
+
+		k3_ringacc_ring_free(rflow->fd_ring);
+		k3_ringacc_ring_free(rflow->r_ring);
+		rflow->fd_ring = NULL;
+		rflow->r_ring = NULL;
+
+		udma_put_rflow(uc);
+	}
+
+	udma_put_rchan(uc);
+}
+
+static int udma_alloc_rx_resources(struct udma_chan *uc)
+{
+	struct udma_dev *ud = uc->ud;
+	struct k3_ring_cfg ring_cfg;
+	struct udma_rflow *rflow;
+	int fd_ring_id;
+	int ret;
+
+	ret = udma_get_rchan(uc);
+	if (ret)
+		return ret;
+
+	/* For MEM_TO_MEM we don't need rflow or rings */
+	if (uc->config.dir == DMA_MEM_TO_MEM)
+		return 0;
+
+	ret = udma_get_rflow(uc, uc->rchan->id);
+	if (ret) {
+		ret = -EBUSY;
+		goto err_rflow;
+	}
+
+	rflow = uc->rflow;
+	fd_ring_id = ud->tchan_cnt + ud->echan_cnt + uc->rchan->id;
+	rflow->fd_ring = k3_ringacc_request_ring(ud->ringacc, fd_ring_id, 0);
+	if (!rflow->fd_ring) {
+		ret = -EBUSY;
+		goto err_rx_ring;
+	}
+
+	rflow->r_ring = k3_ringacc_request_ring(ud->ringacc, -1, 0);
+	if (!rflow->r_ring) {
+		ret = -EBUSY;
+		goto err_rxc_ring;
+	}
+
+	memset(&ring_cfg, 0, sizeof(ring_cfg));
+
+	if (uc->config.pkt_mode)
+		ring_cfg.size = SG_MAX_SEGMENTS;
+	else
+		ring_cfg.size = K3_UDMA_DEFAULT_RING_SIZE;
+
+	ring_cfg.elm_size = K3_RINGACC_RING_ELSIZE_8;
+	ring_cfg.mode = K3_RINGACC_RING_MODE_MESSAGE;
+
+	ret = k3_ringacc_ring_cfg(rflow->fd_ring, &ring_cfg);
+	ring_cfg.size = K3_UDMA_DEFAULT_RING_SIZE;
+	ret |= k3_ringacc_ring_cfg(rflow->r_ring, &ring_cfg);
+
+	if (ret)
+		goto err_ringcfg;
+
+	return 0;
+
+err_ringcfg:
+	k3_ringacc_ring_free(rflow->r_ring);
+	rflow->r_ring = NULL;
+err_rxc_ring:
+	k3_ringacc_ring_free(rflow->fd_ring);
+	rflow->fd_ring = NULL;
+err_rx_ring:
+	udma_put_rflow(uc);
+err_rflow:
+	udma_put_rchan(uc);
+
+	return ret;
+}
+
+#define TISCI_TCHAN_VALID_PARAMS (				\
+	TI_SCI_MSG_VALUE_RM_UDMAP_CH_PAUSE_ON_ERR_VALID |	\
+	TI_SCI_MSG_VALUE_RM_UDMAP_CH_TX_FILT_EINFO_VALID |	\
+	TI_SCI_MSG_VALUE_RM_UDMAP_CH_TX_FILT_PSWORDS_VALID |	\
+	TI_SCI_MSG_VALUE_RM_UDMAP_CH_CHAN_TYPE_VALID |		\
+	TI_SCI_MSG_VALUE_RM_UDMAP_CH_TX_SUPR_TDPKT_VALID |	\
+	TI_SCI_MSG_VALUE_RM_UDMAP_CH_FETCH_SIZE_VALID |		\
+	TI_SCI_MSG_VALUE_RM_UDMAP_CH_CQ_QNUM_VALID)
+
+#define TISCI_RCHAN_VALID_PARAMS (				\
+	TI_SCI_MSG_VALUE_RM_UDMAP_CH_PAUSE_ON_ERR_VALID |	\
+	TI_SCI_MSG_VALUE_RM_UDMAP_CH_FETCH_SIZE_VALID |		\
+	TI_SCI_MSG_VALUE_RM_UDMAP_CH_CQ_QNUM_VALID |		\
+	TI_SCI_MSG_VALUE_RM_UDMAP_CH_CHAN_TYPE_VALID |		\
+	TI_SCI_MSG_VALUE_RM_UDMAP_CH_RX_IGNORE_SHORT_VALID |	\
+	TI_SCI_MSG_VALUE_RM_UDMAP_CH_RX_IGNORE_LONG_VALID |	\
+	TI_SCI_MSG_VALUE_RM_UDMAP_CH_RX_FLOWID_START_VALID |	\
+	TI_SCI_MSG_VALUE_RM_UDMAP_CH_RX_FLOWID_CNT_VALID)
+
+static int udma_tisci_m2m_channel_config(struct udma_chan *uc)
+{
+	struct udma_dev *ud = uc->ud;
+	struct udma_tisci_rm *tisci_rm = &ud->tisci_rm;
+	const struct ti_sci_rm_udmap_ops *tisci_ops = tisci_rm->tisci_udmap_ops;
+	struct udma_tchan *tchan = uc->tchan;
+	struct udma_rchan *rchan = uc->rchan;
+	int ret = 0;
+
+	/* Non synchronized - mem to mem type of transfer */
+	int tc_ring = k3_ringacc_get_ring_id(tchan->tc_ring);
+	struct ti_sci_msg_rm_udmap_tx_ch_cfg req_tx = { 0 };
+	struct ti_sci_msg_rm_udmap_rx_ch_cfg req_rx = { 0 };
+
+	req_tx.valid_params = TISCI_TCHAN_VALID_PARAMS;
+	req_tx.nav_id = tisci_rm->tisci_dev_id;
+	req_tx.index = tchan->id;
+	req_tx.tx_chan_type = TI_SCI_RM_UDMAP_CHAN_TYPE_3RDP_BCOPY_PBRR;
+	req_tx.tx_fetch_size = sizeof(struct cppi5_desc_hdr_t) >> 2;
+	req_tx.txcq_qnum = tc_ring;
+
+	ret = tisci_ops->tx_ch_cfg(tisci_rm->tisci, &req_tx);
+	if (ret) {
+		dev_err(ud->dev, "tchan%d cfg failed %d\n", tchan->id, ret);
+		return ret;
+	}
+
+	req_rx.valid_params = TISCI_RCHAN_VALID_PARAMS;
+	req_rx.nav_id = tisci_rm->tisci_dev_id;
+	req_rx.index = rchan->id;
+	req_rx.rx_fetch_size = sizeof(struct cppi5_desc_hdr_t) >> 2;
+	req_rx.rxcq_qnum = tc_ring;
+	req_rx.rx_chan_type = TI_SCI_RM_UDMAP_CHAN_TYPE_3RDP_BCOPY_PBRR;
+
+	ret = tisci_ops->rx_ch_cfg(tisci_rm->tisci, &req_rx);
+	if (ret)
+		dev_err(ud->dev, "rchan%d alloc failed %d\n", rchan->id, ret);
+
+	return ret;
+}
+
+static int udma_tisci_tx_channel_config(struct udma_chan *uc)
+{
+	struct udma_dev *ud = uc->ud;
+	struct udma_tisci_rm *tisci_rm = &ud->tisci_rm;
+	const struct ti_sci_rm_udmap_ops *tisci_ops = tisci_rm->tisci_udmap_ops;
+	struct udma_tchan *tchan = uc->tchan;
+	int tc_ring = k3_ringacc_get_ring_id(tchan->tc_ring);
+	struct ti_sci_msg_rm_udmap_tx_ch_cfg req_tx = { 0 };
+	u32 mode, fetch_size;
+	int ret = 0;
+
+	if (uc->config.pkt_mode) {
+		mode = TI_SCI_RM_UDMAP_CHAN_TYPE_PKT_PBRR;
+		fetch_size = cppi5_hdesc_calc_size(uc->config.needs_epib,
+						   uc->config.psd_size, 0);
+	} else {
+		mode = TI_SCI_RM_UDMAP_CHAN_TYPE_3RDP_PBRR;
+		fetch_size = sizeof(struct cppi5_desc_hdr_t);
+	}
+
+	req_tx.valid_params = TISCI_TCHAN_VALID_PARAMS;
+	req_tx.nav_id = tisci_rm->tisci_dev_id;
+	req_tx.index = tchan->id;
+	req_tx.tx_chan_type = mode;
+	req_tx.tx_supr_tdpkt = uc->config.notdpkt;
+	req_tx.tx_fetch_size = fetch_size >> 2;
+	req_tx.txcq_qnum = tc_ring;
+
+	ret = tisci_ops->tx_ch_cfg(tisci_rm->tisci, &req_tx);
+	if (ret)
+		dev_err(ud->dev, "tchan%d cfg failed %d\n", tchan->id, ret);
+
+	return ret;
+}
+
+static int udma_tisci_rx_channel_config(struct udma_chan *uc)
+{
+	struct udma_dev *ud = uc->ud;
+	struct udma_tisci_rm *tisci_rm = &ud->tisci_rm;
+	const struct ti_sci_rm_udmap_ops *tisci_ops = tisci_rm->tisci_udmap_ops;
+	struct udma_rchan *rchan = uc->rchan;
+	int fd_ring = k3_ringacc_get_ring_id(uc->rflow->fd_ring);
+	int rx_ring = k3_ringacc_get_ring_id(uc->rflow->r_ring);
+	struct ti_sci_msg_rm_udmap_rx_ch_cfg req_rx = { 0 };
+	struct ti_sci_msg_rm_udmap_flow_cfg flow_req = { 0 };
+	u32 mode, fetch_size;
+	int ret = 0;
+
+	if (uc->config.pkt_mode) {
+		mode = TI_SCI_RM_UDMAP_CHAN_TYPE_PKT_PBRR;
+		fetch_size = cppi5_hdesc_calc_size(uc->config.needs_epib,
+						   uc->config.psd_size, 0);
+	} else {
+		mode = TI_SCI_RM_UDMAP_CHAN_TYPE_3RDP_PBRR;
+		fetch_size = sizeof(struct cppi5_desc_hdr_t);
+	}
+
+	req_rx.valid_params = TISCI_RCHAN_VALID_PARAMS;
+	req_rx.nav_id = tisci_rm->tisci_dev_id;
+	req_rx.index = rchan->id;
+	req_rx.rx_fetch_size =  fetch_size >> 2;
+	req_rx.rxcq_qnum = rx_ring;
+	req_rx.rx_chan_type = mode;
+
+	ret = tisci_ops->rx_ch_cfg(tisci_rm->tisci, &req_rx);
+	if (ret) {
+		dev_err(ud->dev, "rchan%d cfg failed %d\n", rchan->id, ret);
+		return ret;
+	}
+
+	flow_req.valid_params =
+		TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_EINFO_PRESENT_VALID |
+		TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_PSINFO_PRESENT_VALID |
+		TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_ERROR_HANDLING_VALID |
+		TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_DESC_TYPE_VALID |
+		TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_DEST_QNUM_VALID |
+		TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_SRC_TAG_HI_SEL_VALID |
+		TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_SRC_TAG_LO_SEL_VALID |
+		TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_DEST_TAG_HI_SEL_VALID |
+		TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_DEST_TAG_LO_SEL_VALID |
+		TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ0_SZ0_QNUM_VALID |
+		TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ1_QNUM_VALID |
+		TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ2_QNUM_VALID |
+		TI_SCI_MSG_VALUE_RM_UDMAP_FLOW_FDQ3_QNUM_VALID;
+
+	flow_req.nav_id = tisci_rm->tisci_dev_id;
+	flow_req.flow_index = rchan->id;
+
+	if (uc->config.needs_epib)
+		flow_req.rx_einfo_present = 1;
+	else
+		flow_req.rx_einfo_present = 0;
+	if (uc->config.psd_size)
+		flow_req.rx_psinfo_present = 1;
+	else
+		flow_req.rx_psinfo_present = 0;
+	flow_req.rx_error_handling = 1;
+	flow_req.rx_dest_qnum = rx_ring;
+	flow_req.rx_src_tag_hi_sel = UDMA_RFLOW_SRCTAG_NONE;
+	flow_req.rx_src_tag_lo_sel = UDMA_RFLOW_SRCTAG_SRC_TAG;
+	flow_req.rx_dest_tag_hi_sel = UDMA_RFLOW_DSTTAG_DST_TAG_HI;
+	flow_req.rx_dest_tag_lo_sel = UDMA_RFLOW_DSTTAG_DST_TAG_LO;
+	flow_req.rx_fdq0_sz0_qnum = fd_ring;
+	flow_req.rx_fdq1_qnum = fd_ring;
+	flow_req.rx_fdq2_qnum = fd_ring;
+	flow_req.rx_fdq3_qnum = fd_ring;
+
+	ret = tisci_ops->rx_flow_cfg(tisci_rm->tisci, &flow_req);
+
+	if (ret)
+		dev_err(ud->dev, "flow%d config failed: %d\n", rchan->id, ret);
+
+	return 0;
+}
+
+static int udma_alloc_chan_resources(struct dma_chan *chan)
+{
+	struct udma_chan *uc = to_udma_chan(chan);
+	struct udma_dev *ud = to_udma_dev(chan->device);
+	const struct udma_match_data *match_data = ud->match_data;
+	struct k3_ring *irq_ring;
+	u32 irq_udma_idx;
+	int ret;
+
+	if (uc->config.pkt_mode || uc->config.dir == DMA_MEM_TO_MEM) {
+		uc->use_dma_pool = true;
+		/* in case of MEM_TO_MEM we have maximum of two TRs */
+		if (uc->config.dir == DMA_MEM_TO_MEM) {
+			uc->config.hdesc_size = cppi5_trdesc_calc_size(
+					sizeof(struct cppi5_tr_type15_t), 2);
+			uc->config.pkt_mode = false;
+		}
+	}
+
+	if (uc->use_dma_pool) {
+		uc->hdesc_pool = dma_pool_create(uc->name, ud->ddev.dev,
+						 uc->config.hdesc_size,
+						 ud->desc_align,
+						 0);
+		if (!uc->hdesc_pool) {
+			dev_err(ud->ddev.dev,
+				"Descriptor pool allocation failed\n");
+			uc->use_dma_pool = false;
+			return -ENOMEM;
+		}
+	}
+
+	/*
+	 * Make sure that the completion is in a known state:
+	 * No teardown, the channel is idle
+	 */
+	reinit_completion(&uc->teardown_completed);
+	complete_all(&uc->teardown_completed);
+	uc->state = UDMA_CHAN_IS_IDLE;
+
+	switch (uc->config.dir) {
+	case DMA_MEM_TO_MEM:
+		/* Non synchronized - mem to mem type of transfer */
+		dev_dbg(uc->ud->dev, "%s: chan%d as MEM-to-MEM\n", __func__,
+			uc->id);
+
+		ret = udma_get_chan_pair(uc);
+		if (ret)
+			return ret;
+
+		ret = udma_alloc_tx_resources(uc);
+		if (ret)
+			return ret;
+
+		ret = udma_alloc_rx_resources(uc);
+		if (ret) {
+			udma_free_tx_resources(uc);
+			return ret;
+		}
+
+		uc->config.src_thread = ud->psil_base + uc->tchan->id;
+		uc->config.dst_thread = (ud->psil_base + uc->rchan->id) |
+					K3_PSIL_DST_THREAD_ID_OFFSET;
+
+		irq_ring = uc->tchan->tc_ring;
+		irq_udma_idx = uc->tchan->id;
+
+		ret = udma_tisci_m2m_channel_config(uc);
+		break;
+	case DMA_MEM_TO_DEV:
+		/* Slave transfer synchronized - mem to dev (TX) trasnfer */
+		dev_dbg(uc->ud->dev, "%s: chan%d as MEM-to-DEV\n", __func__,
+			uc->id);
+
+		ret = udma_alloc_tx_resources(uc);
+		if (ret) {
+			uc->config.remote_thread_id = -1;
+			return ret;
+		}
+
+		uc->config.src_thread = ud->psil_base + uc->tchan->id;
+		uc->config.dst_thread = uc->config.remote_thread_id;
+		uc->config.dst_thread |= K3_PSIL_DST_THREAD_ID_OFFSET;
+
+		irq_ring = uc->tchan->tc_ring;
+		irq_udma_idx = uc->tchan->id;
+
+		ret = udma_tisci_tx_channel_config(uc);
+		break;
+	case DMA_DEV_TO_MEM:
+		/* Slave transfer synchronized - dev to mem (RX) trasnfer */
+		dev_dbg(uc->ud->dev, "%s: chan%d as DEV-to-MEM\n", __func__,
+			uc->id);
+
+		ret = udma_alloc_rx_resources(uc);
+		if (ret) {
+			uc->config.remote_thread_id = -1;
+			return ret;
+		}
+
+		uc->config.src_thread = uc->config.remote_thread_id;
+		uc->config.dst_thread = (ud->psil_base + uc->rchan->id) |
+					K3_PSIL_DST_THREAD_ID_OFFSET;
+
+		irq_ring = uc->rflow->r_ring;
+		irq_udma_idx = match_data->rchan_oes_offset + uc->rchan->id;
+
+		ret = udma_tisci_rx_channel_config(uc);
+		break;
+	default:
+		/* Can not happen */
+		dev_err(uc->ud->dev, "%s: chan%d invalid direction (%u)\n",
+			__func__, uc->id, uc->config.dir);
+		return -EINVAL;
+	}
+
+	/* check if the channel configuration was successful */
+	if (ret)
+		goto err_res_free;
+
+	if (udma_is_chan_running(uc)) {
+		dev_warn(ud->dev, "chan%d: is running!\n", uc->id);
+		udma_stop(uc);
+		if (udma_is_chan_running(uc)) {
+			dev_err(ud->dev, "chan%d: won't stop!\n", uc->id);
+			goto err_res_free;
+		}
+	}
+
+	/* PSI-L pairing */
+	ret = navss_psil_pair(ud, uc->config.src_thread, uc->config.dst_thread);
+	if (ret) {
+		dev_err(ud->dev, "PSI-L pairing failed: 0x%04x -> 0x%04x\n",
+			uc->config.src_thread, uc->config.dst_thread);
+		goto err_res_free;
+	}
+
+	uc->psil_paired = true;
+
+	uc->irq_num_ring = k3_ringacc_get_ring_irq_num(irq_ring);
+	if (uc->irq_num_ring <= 0) {
+		dev_err(ud->dev, "Failed to get ring irq (index: %u)\n",
+			k3_ringacc_get_ring_id(irq_ring));
+		ret = -EINVAL;
+		goto err_psi_free;
+	}
+
+	ret = request_irq(uc->irq_num_ring, udma_ring_irq_handler,
+			  IRQF_TRIGGER_HIGH, uc->name, uc);
+	if (ret) {
+		dev_err(ud->dev, "chan%d: ring irq request failed\n", uc->id);
+		goto err_irq_free;
+	}
+
+	/* Event from UDMA (TR events) only needed for slave TR mode channels */
+	if (is_slave_direction(uc->config.dir) && !uc->config.pkt_mode) {
+		uc->irq_num_udma = ti_sci_inta_msi_get_virq(ud->dev,
+							    irq_udma_idx);
+		if (uc->irq_num_udma <= 0) {
+			dev_err(ud->dev, "Failed to get udma irq (index: %u)\n",
+				irq_udma_idx);
+			free_irq(uc->irq_num_ring, uc);
+			ret = -EINVAL;
+			goto err_irq_free;
+		}
+
+		ret = request_irq(uc->irq_num_udma, udma_udma_irq_handler, 0,
+				  uc->name, uc);
+		if (ret) {
+			dev_err(ud->dev, "chan%d: UDMA irq request failed\n",
+				uc->id);
+			free_irq(uc->irq_num_ring, uc);
+			goto err_irq_free;
+		}
+	} else {
+		uc->irq_num_udma = 0;
+	}
+
+	udma_reset_rings(uc);
+
+	INIT_DELAYED_WORK_ONSTACK(&uc->tx_drain.work,
+				  udma_check_tx_completion);
+	return 0;
+
+err_irq_free:
+	uc->irq_num_ring = 0;
+	uc->irq_num_udma = 0;
+err_psi_free:
+	navss_psil_unpair(ud, uc->config.src_thread, uc->config.dst_thread);
+	uc->psil_paired = false;
+err_res_free:
+	udma_free_tx_resources(uc);
+	udma_free_rx_resources(uc);
+
+	udma_reset_uchan(uc);
+
+	if (uc->use_dma_pool) {
+		dma_pool_destroy(uc->hdesc_pool);
+		uc->use_dma_pool = false;
+	}
+
+	return ret;
+}
+
+static int udma_slave_config(struct dma_chan *chan,
+			     struct dma_slave_config *cfg)
+{
+	struct udma_chan *uc = to_udma_chan(chan);
+
+	memcpy(&uc->cfg, cfg, sizeof(uc->cfg));
+
+	return 0;
+}
+
+static struct udma_desc *udma_alloc_tr_desc(struct udma_chan *uc,
+					    size_t tr_size, int tr_count,
+					    enum dma_transfer_direction dir)
+{
+	struct udma_hwdesc *hwdesc;
+	struct cppi5_desc_hdr_t *tr_desc;
+	struct udma_desc *d;
+	u32 reload_count = 0;
+	u32 ring_id;
+
+	switch (tr_size) {
+	case 16:
+	case 32:
+	case 64:
+	case 128:
+		break;
+	default:
+		dev_err(uc->ud->dev, "Unsupported TR size of %zu\n", tr_size);
+		return NULL;
+	}
+
+	/* We have only one descriptor containing multiple TRs */
+	d = kzalloc(sizeof(*d) + sizeof(d->hwdesc[0]), GFP_NOWAIT);
+	if (!d)
+		return NULL;
+
+	d->sglen = tr_count;
+
+	d->hwdesc_count = 1;
+	hwdesc = &d->hwdesc[0];
+
+	/* Allocate memory for DMA ring descriptor */
+	if (uc->use_dma_pool) {
+		hwdesc->cppi5_desc_size = uc->config.hdesc_size;
+		hwdesc->cppi5_desc_vaddr = dma_pool_zalloc(uc->hdesc_pool,
+						GFP_NOWAIT,
+						&hwdesc->cppi5_desc_paddr);
+	} else {
+		hwdesc->cppi5_desc_size = cppi5_trdesc_calc_size(tr_size,
+								 tr_count);
+		hwdesc->cppi5_desc_size = ALIGN(hwdesc->cppi5_desc_size,
+						uc->ud->desc_align);
+		hwdesc->cppi5_desc_vaddr = dma_alloc_coherent(uc->ud->dev,
+						hwdesc->cppi5_desc_size,
+						&hwdesc->cppi5_desc_paddr,
+						GFP_NOWAIT);
+	}
+
+	if (!hwdesc->cppi5_desc_vaddr) {
+		kfree(d);
+		return NULL;
+	}
+
+	/* Start of the TR req records */
+	hwdesc->tr_req_base = hwdesc->cppi5_desc_vaddr + tr_size;
+	/* Start address of the TR response array */
+	hwdesc->tr_resp_base = hwdesc->tr_req_base + tr_size * tr_count;
+
+	tr_desc = hwdesc->cppi5_desc_vaddr;
+
+	if (uc->cyclic)
+		reload_count = CPPI5_INFO0_TRDESC_RLDCNT_INFINITE;
+
+	if (dir == DMA_DEV_TO_MEM)
+		ring_id = k3_ringacc_get_ring_id(uc->rflow->r_ring);
+	else
+		ring_id = k3_ringacc_get_ring_id(uc->tchan->tc_ring);
+
+	cppi5_trdesc_init(tr_desc, tr_count, tr_size, 0, reload_count);
+	cppi5_desc_set_pktids(tr_desc, uc->id,
+			      CPPI5_INFO1_DESC_FLOWID_DEFAULT);
+	cppi5_desc_set_retpolicy(tr_desc, 0, ring_id);
+
+	return d;
+}
+
+/**
+ * udma_get_tr_counters - calculate TR counters for a given length
+ * @len: Length of the trasnfer
+ * @align_to: Preferred alignment
+ * @tr0_cnt0: First TR icnt0
+ * @tr0_cnt1: First TR icnt1
+ * @tr1_cnt0: Second (if used) TR icnt0
+ *
+ * For len < SZ_64K only one TR is enough, tr1_cnt0 is not updated
+ * For len >= SZ_64K two TRs are used in a simple way:
+ * First TR: SZ_64K-alignment blocks (tr0_cnt0, tr0_cnt1)
+ * Second TR: the remaining length (tr1_cnt0)
+ *
+ * Returns the number of TRs the length needs (1 or 2)
+ * -EINVAL if the length can not be supported
+ */
+static int udma_get_tr_counters(size_t len, unsigned long align_to,
+				u16 *tr0_cnt0, u16 *tr0_cnt1, u16 *tr1_cnt0)
+{
+	if (len < SZ_64K) {
+		*tr0_cnt0 = len;
+		*tr0_cnt1 = 1;
+
+		return 1;
+	}
+
+	if (align_to > 3)
+		align_to = 3;
+
+realign:
+	*tr0_cnt0 = SZ_64K - BIT(align_to);
+	if (len / *tr0_cnt0 >= SZ_64K) {
+		if (align_to) {
+			align_to--;
+			goto realign;
+		}
+		return -EINVAL;
+	}
+
+	*tr0_cnt1 = len / *tr0_cnt0;
+	*tr1_cnt0 = len % *tr0_cnt0;
+
+	return 2;
+}
+
+static struct udma_desc *
+udma_prep_slave_sg_tr(struct udma_chan *uc, struct scatterlist *sgl,
+		      unsigned int sglen, enum dma_transfer_direction dir,
+		      unsigned long tx_flags, void *context)
+{
+	struct scatterlist *sgent;
+	struct udma_desc *d;
+	struct cppi5_tr_type1_t *tr_req = NULL;
+	u16 tr0_cnt0, tr0_cnt1, tr1_cnt0;
+	unsigned int i;
+	size_t tr_size;
+	int num_tr = 0;
+	int tr_idx = 0;
+
+	if (!is_slave_direction(dir)) {
+		dev_err(uc->ud->dev, "Only slave cyclic is supported\n");
+		return NULL;
+	}
+
+	/* estimate the number of TRs we will need */
+	for_each_sg(sgl, sgent, sglen, i) {
+		if (sg_dma_len(sgent) < SZ_64K)
+			num_tr++;
+		else
+			num_tr += 2;
+	}
+
+	/* Now allocate and setup the descriptor. */
+	tr_size = sizeof(struct cppi5_tr_type1_t);
+	d = udma_alloc_tr_desc(uc, tr_size, num_tr, dir);
+	if (!d)
+		return NULL;
+
+	d->sglen = sglen;
+
+	tr_req = d->hwdesc[0].tr_req_base;
+	for_each_sg(sgl, sgent, sglen, i) {
+		dma_addr_t sg_addr = sg_dma_address(sgent);
+
+		num_tr = udma_get_tr_counters(sg_dma_len(sgent), __ffs(sg_addr),
+					      &tr0_cnt0, &tr0_cnt1, &tr1_cnt0);
+		if (num_tr < 0) {
+			dev_err(uc->ud->dev, "size %u is not supported\n",
+				sg_dma_len(sgent));
+			udma_free_hwdesc(uc, d);
+			kfree(d);
+			return NULL;
+		}
+
+		cppi5_tr_init(&tr_req[i].flags, CPPI5_TR_TYPE1, false, false,
+			      CPPI5_TR_EVENT_SIZE_COMPLETION, 0);
+		cppi5_tr_csf_set(&tr_req[i].flags, CPPI5_TR_CSF_SUPR_EVT);
+
+		tr_req[tr_idx].addr = sg_addr;
+		tr_req[tr_idx].icnt0 = tr0_cnt0;
+		tr_req[tr_idx].icnt1 = tr0_cnt1;
+		tr_req[tr_idx].dim1 = tr0_cnt0;
+		tr_idx++;
+
+		if (num_tr == 2) {
+			cppi5_tr_init(&tr_req[tr_idx].flags, CPPI5_TR_TYPE1,
+				      false, false,
+				      CPPI5_TR_EVENT_SIZE_COMPLETION, 0);
+			cppi5_tr_csf_set(&tr_req[tr_idx].flags,
+					 CPPI5_TR_CSF_SUPR_EVT);
+
+			tr_req[tr_idx].addr = sg_addr + tr0_cnt1 * tr0_cnt0;
+			tr_req[tr_idx].icnt0 = tr1_cnt0;
+			tr_req[tr_idx].icnt1 = 1;
+			tr_req[tr_idx].dim1 = tr1_cnt0;
+			tr_idx++;
+		}
+
+		d->residue += sg_dma_len(sgent);
+	}
+
+	cppi5_tr_csf_set(&tr_req[tr_idx - 1].flags, CPPI5_TR_CSF_EOP);
+
+	return d;
+}
+
+static int udma_configure_statictr(struct udma_chan *uc, struct udma_desc *d,
+				   enum dma_slave_buswidth dev_width,
+				   u16 elcnt)
+{
+	if (uc->config.ep_type != PSIL_EP_PDMA_XY)
+		return 0;
+
+	/* Bus width translates to the element size (ES) */
+	switch (dev_width) {
+	case DMA_SLAVE_BUSWIDTH_1_BYTE:
+		d->static_tr.elsize = 0;
+		break;
+	case DMA_SLAVE_BUSWIDTH_2_BYTES:
+		d->static_tr.elsize = 1;
+		break;
+	case DMA_SLAVE_BUSWIDTH_3_BYTES:
+		d->static_tr.elsize = 2;
+		break;
+	case DMA_SLAVE_BUSWIDTH_4_BYTES:
+		d->static_tr.elsize = 3;
+		break;
+	case DMA_SLAVE_BUSWIDTH_8_BYTES:
+		d->static_tr.elsize = 4;
+		break;
+	default: /* not reached */
+		return -EINVAL;
+	}
+
+	d->static_tr.elcnt = elcnt;
+
+	/*
+	 * PDMA must to close the packet when the channel is in packet mode.
+	 * For TR mode when the channel is not cyclic we also need PDMA to close
+	 * the packet otherwise the transfer will stall because PDMA holds on
+	 * the data it has received from the peripheral.
+	 */
+	if (uc->config.pkt_mode || !uc->cyclic) {
+		unsigned int div = dev_width * elcnt;
+
+		if (uc->cyclic)
+			d->static_tr.bstcnt = d->residue / d->sglen / div;
+		else
+			d->static_tr.bstcnt = d->residue / div;
+
+		if (uc->config.dir == DMA_DEV_TO_MEM &&
+		    d->static_tr.bstcnt > uc->ud->match_data->statictr_z_mask)
+			return -EINVAL;
+	} else {
+		d->static_tr.bstcnt = 0;
+	}
+
+	return 0;
+}
+
+static struct udma_desc *
+udma_prep_slave_sg_pkt(struct udma_chan *uc, struct scatterlist *sgl,
+		       unsigned int sglen, enum dma_transfer_direction dir,
+		       unsigned long tx_flags, void *context)
+{
+	struct scatterlist *sgent;
+	struct cppi5_host_desc_t *h_desc = NULL;
+	struct udma_desc *d;
+	u32 ring_id;
+	unsigned int i;
+
+	d = kzalloc(sizeof(*d) + sglen * sizeof(d->hwdesc[0]), GFP_NOWAIT);
+	if (!d)
+		return NULL;
+
+	d->sglen = sglen;
+	d->hwdesc_count = sglen;
+
+	if (dir == DMA_DEV_TO_MEM)
+		ring_id = k3_ringacc_get_ring_id(uc->rflow->r_ring);
+	else
+		ring_id = k3_ringacc_get_ring_id(uc->tchan->tc_ring);
+
+	for_each_sg(sgl, sgent, sglen, i) {
+		struct udma_hwdesc *hwdesc = &d->hwdesc[i];
+		dma_addr_t sg_addr = sg_dma_address(sgent);
+		struct cppi5_host_desc_t *desc;
+		size_t sg_len = sg_dma_len(sgent);
+
+		hwdesc->cppi5_desc_vaddr = dma_pool_zalloc(uc->hdesc_pool,
+						GFP_NOWAIT,
+						&hwdesc->cppi5_desc_paddr);
+		if (!hwdesc->cppi5_desc_vaddr) {
+			dev_err(uc->ud->dev,
+				"descriptor%d allocation failed\n", i);
+
+			udma_free_hwdesc(uc, d);
+			kfree(d);
+			return NULL;
+		}
+
+		d->residue += sg_len;
+		hwdesc->cppi5_desc_size = uc->config.hdesc_size;
+		desc = hwdesc->cppi5_desc_vaddr;
+
+		if (i == 0) {
+			cppi5_hdesc_init(desc, 0, 0);
+			/* Flow and Packed ID */
+			cppi5_desc_set_pktids(&desc->hdr, uc->id,
+					      CPPI5_INFO1_DESC_FLOWID_DEFAULT);
+			cppi5_desc_set_retpolicy(&desc->hdr, 0, ring_id);
+		} else {
+			cppi5_hdesc_reset_hbdesc(desc);
+			cppi5_desc_set_retpolicy(&desc->hdr, 0, 0xffff);
+		}
+
+		/* attach the sg buffer to the descriptor */
+		cppi5_hdesc_attach_buf(desc, sg_addr, sg_len, sg_addr, sg_len);
+
+		/* Attach link as host buffer descriptor */
+		if (h_desc)
+			cppi5_hdesc_link_hbdesc(h_desc,
+						hwdesc->cppi5_desc_paddr);
+
+		if (dir == DMA_MEM_TO_DEV)
+			h_desc = desc;
+	}
+
+	if (d->residue >= SZ_4M) {
+		dev_err(uc->ud->dev,
+			"%s: Transfer size %u is over the supported 4M range\n",
+			__func__, d->residue);
+		udma_free_hwdesc(uc, d);
+		kfree(d);
+		return NULL;
+	}
+
+	h_desc = d->hwdesc[0].cppi5_desc_vaddr;
+	cppi5_hdesc_set_pktlen(h_desc, d->residue);
+
+	return d;
+}
+
+static int udma_attach_metadata(struct dma_async_tx_descriptor *desc,
+				void *data, size_t len)
+{
+	struct udma_desc *d = to_udma_desc(desc);
+	struct udma_chan *uc = to_udma_chan(desc->chan);
+	struct cppi5_host_desc_t *h_desc;
+	u32 psd_size = len;
+	u32 flags = 0;
+
+	if (!uc->config.pkt_mode || !uc->config.metadata_size)
+		return -ENOTSUPP;
+
+	if (!data || len > uc->config.metadata_size)
+		return -EINVAL;
+
+	if (uc->config.needs_epib && len < CPPI5_INFO0_HDESC_EPIB_SIZE)
+		return -EINVAL;
+
+	h_desc = d->hwdesc[0].cppi5_desc_vaddr;
+	if (d->dir == DMA_MEM_TO_DEV)
+		memcpy(h_desc->epib, data, len);
+
+	if (uc->config.needs_epib)
+		psd_size -= CPPI5_INFO0_HDESC_EPIB_SIZE;
+
+	d->metadata = data;
+	d->metadata_size = len;
+	if (uc->config.needs_epib)
+		flags |= CPPI5_INFO0_HDESC_EPIB_PRESENT;
+
+	cppi5_hdesc_update_flags(h_desc, flags);
+	cppi5_hdesc_update_psdata_size(h_desc, psd_size);
+
+	return 0;
+}
+
+static void *udma_get_metadata_ptr(struct dma_async_tx_descriptor *desc,
+				   size_t *payload_len, size_t *max_len)
+{
+	struct udma_desc *d = to_udma_desc(desc);
+	struct udma_chan *uc = to_udma_chan(desc->chan);
+	struct cppi5_host_desc_t *h_desc;
+
+	if (!uc->config.pkt_mode || !uc->config.metadata_size)
+		return ERR_PTR(-ENOTSUPP);
+
+	h_desc = d->hwdesc[0].cppi5_desc_vaddr;
+
+	*max_len = uc->config.metadata_size;
+
+	*payload_len = cppi5_hdesc_epib_present(&h_desc->hdr) ?
+		       CPPI5_INFO0_HDESC_EPIB_SIZE : 0;
+	*payload_len += cppi5_hdesc_get_psdata_size(h_desc);
+
+	return h_desc->epib;
+}
+
+static int udma_set_metadata_len(struct dma_async_tx_descriptor *desc,
+				 size_t payload_len)
+{
+	struct udma_desc *d = to_udma_desc(desc);
+	struct udma_chan *uc = to_udma_chan(desc->chan);
+	struct cppi5_host_desc_t *h_desc;
+	u32 psd_size = payload_len;
+	u32 flags = 0;
+
+	if (!uc->config.pkt_mode || !uc->config.metadata_size)
+		return -ENOTSUPP;
+
+	if (payload_len > uc->config.metadata_size)
+		return -EINVAL;
+
+	if (uc->config.needs_epib && payload_len < CPPI5_INFO0_HDESC_EPIB_SIZE)
+		return -EINVAL;
+
+	h_desc = d->hwdesc[0].cppi5_desc_vaddr;
+
+	if (uc->config.needs_epib) {
+		psd_size -= CPPI5_INFO0_HDESC_EPIB_SIZE;
+		flags |= CPPI5_INFO0_HDESC_EPIB_PRESENT;
+	}
+
+	cppi5_hdesc_update_flags(h_desc, flags);
+	cppi5_hdesc_update_psdata_size(h_desc, psd_size);
+
+	return 0;
+}
+
+static struct dma_descriptor_metadata_ops metadata_ops = {
+	.attach = udma_attach_metadata,
+	.get_ptr = udma_get_metadata_ptr,
+	.set_len = udma_set_metadata_len,
+};
+
+static struct dma_async_tx_descriptor *
+udma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
+		   unsigned int sglen, enum dma_transfer_direction dir,
+		   unsigned long tx_flags, void *context)
+{
+	struct udma_chan *uc = to_udma_chan(chan);
+	enum dma_slave_buswidth dev_width;
+	struct udma_desc *d;
+	u32 burst;
+
+	if (dir != uc->config.dir) {
+		dev_err(chan->device->dev,
+			"%s: chan%d is for %s, not supporting %s\n",
+			__func__, uc->id,
+			dmaengine_get_direction_text(uc->config.dir),
+			dmaengine_get_direction_text(dir));
+		return NULL;
+	}
+
+	if (dir == DMA_DEV_TO_MEM) {
+		dev_width = uc->cfg.src_addr_width;
+		burst = uc->cfg.src_maxburst;
+	} else if (dir == DMA_MEM_TO_DEV) {
+		dev_width = uc->cfg.dst_addr_width;
+		burst = uc->cfg.dst_maxburst;
+	} else {
+		dev_err(chan->device->dev, "%s: bad direction?\n", __func__);
+		return NULL;
+	}
+
+	if (!burst)
+		burst = 1;
+
+	if (uc->config.pkt_mode)
+		d = udma_prep_slave_sg_pkt(uc, sgl, sglen, dir, tx_flags,
+					   context);
+	else
+		d = udma_prep_slave_sg_tr(uc, sgl, sglen, dir, tx_flags,
+					  context);
+
+	if (!d)
+		return NULL;
+
+	d->dir = dir;
+	d->desc_idx = 0;
+	d->tr_idx = 0;
+
+	/* static TR for remote PDMA */
+	if (udma_configure_statictr(uc, d, dev_width, burst)) {
+		dev_err(uc->ud->dev,
+			"%s: StaticTR Z is limited to maximum 4095 (%u)\n",
+			__func__, d->static_tr.bstcnt);
+
+		udma_free_hwdesc(uc, d);
+		kfree(d);
+		return NULL;
+	}
+
+	if (uc->config.metadata_size)
+		d->vd.tx.metadata_ops = &metadata_ops;
+
+	return vchan_tx_prep(&uc->vc, &d->vd, tx_flags);
+}
+
+static struct udma_desc *
+udma_prep_dma_cyclic_tr(struct udma_chan *uc, dma_addr_t buf_addr,
+			size_t buf_len, size_t period_len,
+			enum dma_transfer_direction dir, unsigned long flags)
+{
+	struct udma_desc *d;
+	size_t tr_size, period_addr;
+	struct cppi5_tr_type1_t *tr_req;
+	unsigned int periods = buf_len / period_len;
+	u16 tr0_cnt0, tr0_cnt1, tr1_cnt0;
+	unsigned int i;
+	int num_tr;
+
+	if (!is_slave_direction(dir)) {
+		dev_err(uc->ud->dev, "Only slave cyclic is supported\n");
+		return NULL;
+	}
+
+	num_tr = udma_get_tr_counters(period_len, __ffs(buf_addr), &tr0_cnt0,
+				      &tr0_cnt1, &tr1_cnt0);
+	if (num_tr < 0) {
+		dev_err(uc->ud->dev, "size %zu is not supported\n",
+			period_len);
+		return NULL;
+	}
+
+	/* Now allocate and setup the descriptor. */
+	tr_size = sizeof(struct cppi5_tr_type1_t);
+	d = udma_alloc_tr_desc(uc, tr_size, periods * num_tr, dir);
+	if (!d)
+		return NULL;
+
+	tr_req = d->hwdesc[0].tr_req_base;
+	period_addr = buf_addr;
+	for (i = 0; i < periods; i++) {
+		int tr_idx = i * num_tr;
+
+		cppi5_tr_init(&tr_req[tr_idx].flags, CPPI5_TR_TYPE1, false,
+			      false, CPPI5_TR_EVENT_SIZE_COMPLETION, 0);
+
+		tr_req[tr_idx].addr = period_addr;
+		tr_req[tr_idx].icnt0 = tr0_cnt0;
+		tr_req[tr_idx].icnt1 = tr0_cnt1;
+		tr_req[tr_idx].dim1 = tr0_cnt0;
+
+		if (num_tr == 2) {
+			cppi5_tr_csf_set(&tr_req[tr_idx].flags,
+					 CPPI5_TR_CSF_SUPR_EVT);
+			tr_idx++;
+
+			cppi5_tr_init(&tr_req[tr_idx].flags, CPPI5_TR_TYPE1,
+				      false, false,
+				      CPPI5_TR_EVENT_SIZE_COMPLETION, 0);
+
+			tr_req[tr_idx].addr = period_addr + tr0_cnt1 * tr0_cnt0;
+			tr_req[tr_idx].icnt0 = tr1_cnt0;
+			tr_req[tr_idx].icnt1 = 1;
+			tr_req[tr_idx].dim1 = tr1_cnt0;
+		}
+
+		if (!(flags & DMA_PREP_INTERRUPT))
+			cppi5_tr_csf_set(&tr_req[tr_idx].flags,
+					 CPPI5_TR_CSF_SUPR_EVT);
+
+		period_addr += period_len;
+	}
+
+	return d;
+}
+
+static struct udma_desc *
+udma_prep_dma_cyclic_pkt(struct udma_chan *uc, dma_addr_t buf_addr,
+			 size_t buf_len, size_t period_len,
+			 enum dma_transfer_direction dir, unsigned long flags)
+{
+	struct udma_desc *d;
+	u32 ring_id;
+	int i;
+	int periods = buf_len / period_len;
+
+	if (periods > (K3_UDMA_DEFAULT_RING_SIZE - 1))
+		return NULL;
+
+	if (period_len >= SZ_4M)
+		return NULL;
+
+	d = kzalloc(sizeof(*d) + periods * sizeof(d->hwdesc[0]), GFP_NOWAIT);
+	if (!d)
+		return NULL;
+
+	d->hwdesc_count = periods;
+
+	/* TODO: re-check this... */
+	if (dir == DMA_DEV_TO_MEM)
+		ring_id = k3_ringacc_get_ring_id(uc->rflow->r_ring);
+	else
+		ring_id = k3_ringacc_get_ring_id(uc->tchan->tc_ring);
+
+	for (i = 0; i < periods; i++) {
+		struct udma_hwdesc *hwdesc = &d->hwdesc[i];
+		dma_addr_t period_addr = buf_addr + (period_len * i);
+		struct cppi5_host_desc_t *h_desc;
+
+		hwdesc->cppi5_desc_vaddr = dma_pool_zalloc(uc->hdesc_pool,
+						GFP_NOWAIT,
+						&hwdesc->cppi5_desc_paddr);
+		if (!hwdesc->cppi5_desc_vaddr) {
+			dev_err(uc->ud->dev,
+				"descriptor%d allocation failed\n", i);
+
+			udma_free_hwdesc(uc, d);
+			kfree(d);
+			return NULL;
+		}
+
+		hwdesc->cppi5_desc_size = uc->config.hdesc_size;
+		h_desc = hwdesc->cppi5_desc_vaddr;
+
+		cppi5_hdesc_init(h_desc, 0, 0);
+		cppi5_hdesc_set_pktlen(h_desc, period_len);
+
+		/* Flow and Packed ID */
+		cppi5_desc_set_pktids(&h_desc->hdr, uc->id,
+				      CPPI5_INFO1_DESC_FLOWID_DEFAULT);
+		cppi5_desc_set_retpolicy(&h_desc->hdr, 0, ring_id);
+
+		/* attach each period to a new descriptor */
+		cppi5_hdesc_attach_buf(h_desc,
+				       period_addr, period_len,
+				       period_addr, period_len);
+	}
+
+	return d;
+}
+
+static struct dma_async_tx_descriptor *
+udma_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 udma_chan *uc = to_udma_chan(chan);
+	enum dma_slave_buswidth dev_width;
+	struct udma_desc *d;
+	u32 burst;
+
+	if (dir != uc->config.dir) {
+		dev_err(chan->device->dev,
+			"%s: chan%d is for %s, not supporting %s\n",
+			__func__, uc->id,
+			dmaengine_get_direction_text(uc->config.dir),
+			dmaengine_get_direction_text(dir));
+		return NULL;
+	}
+
+	uc->cyclic = true;
+
+	if (dir == DMA_DEV_TO_MEM) {
+		dev_width = uc->cfg.src_addr_width;
+		burst = uc->cfg.src_maxburst;
+	} else if (dir == DMA_MEM_TO_DEV) {
+		dev_width = uc->cfg.dst_addr_width;
+		burst = uc->cfg.dst_maxburst;
+	} else {
+		dev_err(uc->ud->dev, "%s: bad direction?\n", __func__);
+		return NULL;
+	}
+
+	if (!burst)
+		burst = 1;
+
+	if (uc->config.pkt_mode)
+		d = udma_prep_dma_cyclic_pkt(uc, buf_addr, buf_len, period_len,
+					     dir, flags);
+	else
+		d = udma_prep_dma_cyclic_tr(uc, buf_addr, buf_len, period_len,
+					    dir, flags);
+
+	if (!d)
+		return NULL;
+
+	d->sglen = buf_len / period_len;
+
+	d->dir = dir;
+	d->residue = buf_len;
+
+	/* static TR for remote PDMA */
+	if (udma_configure_statictr(uc, d, dev_width, burst)) {
+		dev_err(uc->ud->dev,
+			"%s: StaticTR Z is limited to maximum 4095 (%u)\n",
+			__func__, d->static_tr.bstcnt);
+
+		udma_free_hwdesc(uc, d);
+		kfree(d);
+		return NULL;
+	}
+
+	if (uc->config.metadata_size)
+		d->vd.tx.metadata_ops = &metadata_ops;
+
+	return vchan_tx_prep(&uc->vc, &d->vd, flags);
+}
+
+static struct dma_async_tx_descriptor *
+udma_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
+		     size_t len, unsigned long tx_flags)
+{
+	struct udma_chan *uc = to_udma_chan(chan);
+	struct udma_desc *d;
+	struct cppi5_tr_type15_t *tr_req;
+	int num_tr;
+	size_t tr_size = sizeof(struct cppi5_tr_type15_t);
+	u16 tr0_cnt0, tr0_cnt1, tr1_cnt0;
+
+	if (uc->config.dir != DMA_MEM_TO_MEM) {
+		dev_err(chan->device->dev,
+			"%s: chan%d is for %s, not supporting %s\n",
+			__func__, uc->id,
+			dmaengine_get_direction_text(uc->config.dir),
+			dmaengine_get_direction_text(DMA_MEM_TO_MEM));
+		return NULL;
+	}
+
+	num_tr = udma_get_tr_counters(len, __ffs(src | dest), &tr0_cnt0,
+				      &tr0_cnt1, &tr1_cnt0);
+	if (num_tr < 0) {
+		dev_err(uc->ud->dev, "size %zu is not supported\n",
+			len);
+		return NULL;
+	}
+
+	d = udma_alloc_tr_desc(uc, tr_size, num_tr, DMA_MEM_TO_MEM);
+	if (!d)
+		return NULL;
+
+	d->dir = DMA_MEM_TO_MEM;
+	d->desc_idx = 0;
+	d->tr_idx = 0;
+	d->residue = len;
+
+	tr_req = d->hwdesc[0].tr_req_base;
+
+	cppi5_tr_init(&tr_req[0].flags, CPPI5_TR_TYPE15, false, true,
+		      CPPI5_TR_EVENT_SIZE_COMPLETION, 0);
+	cppi5_tr_csf_set(&tr_req[0].flags, CPPI5_TR_CSF_SUPR_EVT);
+
+	tr_req[0].addr = src;
+	tr_req[0].icnt0 = tr0_cnt0;
+	tr_req[0].icnt1 = tr0_cnt1;
+	tr_req[0].icnt2 = 1;
+	tr_req[0].icnt3 = 1;
+	tr_req[0].dim1 = tr0_cnt0;
+
+	tr_req[0].daddr = dest;
+	tr_req[0].dicnt0 = tr0_cnt0;
+	tr_req[0].dicnt1 = tr0_cnt1;
+	tr_req[0].dicnt2 = 1;
+	tr_req[0].dicnt3 = 1;
+	tr_req[0].ddim1 = tr0_cnt0;
+
+	if (num_tr == 2) {
+		cppi5_tr_init(&tr_req[1].flags, CPPI5_TR_TYPE15, false, true,
+			      CPPI5_TR_EVENT_SIZE_COMPLETION, 0);
+		cppi5_tr_csf_set(&tr_req[1].flags, CPPI5_TR_CSF_SUPR_EVT);
+
+		tr_req[1].addr = src + tr0_cnt1 * tr0_cnt0;
+		tr_req[1].icnt0 = tr1_cnt0;
+		tr_req[1].icnt1 = 1;
+		tr_req[1].icnt2 = 1;
+		tr_req[1].icnt3 = 1;
+
+		tr_req[1].daddr = dest + tr0_cnt1 * tr0_cnt0;
+		tr_req[1].dicnt0 = tr1_cnt0;
+		tr_req[1].dicnt1 = 1;
+		tr_req[1].dicnt2 = 1;
+		tr_req[1].dicnt3 = 1;
+	}
+
+	cppi5_tr_csf_set(&tr_req[num_tr - 1].flags, CPPI5_TR_CSF_EOP);
+
+	if (uc->config.metadata_size)
+		d->vd.tx.metadata_ops = &metadata_ops;
+
+	return vchan_tx_prep(&uc->vc, &d->vd, tx_flags);
+}
+
+static void udma_issue_pending(struct dma_chan *chan)
+{
+	struct udma_chan *uc = to_udma_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&uc->vc.lock, flags);
+
+	/* If we have something pending and no active descriptor, then */
+	if (vchan_issue_pending(&uc->vc) && !uc->desc) {
+		/*
+		 * start a descriptor if the channel is NOT [marked as
+		 * terminating _and_ it is still running (teardown has not
+		 * completed yet)].
+		 */
+		if (!(uc->state == UDMA_CHAN_IS_TERMINATING &&
+		      udma_is_chan_running(uc)))
+			udma_start(uc);
+	}
+
+	spin_unlock_irqrestore(&uc->vc.lock, flags);
+}
+
+static enum dma_status udma_tx_status(struct dma_chan *chan,
+				      dma_cookie_t cookie,
+				      struct dma_tx_state *txstate)
+{
+	struct udma_chan *uc = to_udma_chan(chan);
+	enum dma_status ret;
+	unsigned long flags;
+
+	spin_lock_irqsave(&uc->vc.lock, flags);
+
+	ret = dma_cookie_status(chan, cookie, txstate);
+
+	if (!udma_is_chan_running(uc))
+		ret = DMA_COMPLETE;
+
+	if (ret == DMA_IN_PROGRESS && udma_is_chan_paused(uc))
+		ret = DMA_PAUSED;
+
+	if (ret == DMA_COMPLETE || !txstate)
+		goto out;
+
+	if (uc->desc && uc->desc->vd.tx.cookie == cookie) {
+		u32 peer_bcnt = 0;
+		u32 bcnt = 0;
+		u32 residue = uc->desc->residue;
+		u32 delay = 0;
+
+		if (uc->desc->dir == DMA_MEM_TO_DEV) {
+			bcnt = udma_tchanrt_read(uc->tchan,
+						 UDMA_TCHAN_RT_SBCNT_REG);
+
+			if (uc->config.ep_type != PSIL_EP_NATIVE) {
+				peer_bcnt = udma_tchanrt_read(uc->tchan,
+						UDMA_TCHAN_RT_PEER_BCNT_REG);
+
+				if (bcnt > peer_bcnt)
+					delay = bcnt - peer_bcnt;
+			}
+		} else if (uc->desc->dir == DMA_DEV_TO_MEM) {
+			bcnt = udma_rchanrt_read(uc->rchan,
+						 UDMA_RCHAN_RT_BCNT_REG);
+
+			if (uc->config.ep_type != PSIL_EP_NATIVE) {
+				peer_bcnt = udma_rchanrt_read(uc->rchan,
+						UDMA_RCHAN_RT_PEER_BCNT_REG);
+
+				if (peer_bcnt > bcnt)
+					delay = peer_bcnt - bcnt;
+			}
+		} else {
+			bcnt = udma_tchanrt_read(uc->tchan,
+						 UDMA_TCHAN_RT_BCNT_REG);
+		}
+
+		bcnt -= uc->bcnt;
+		if (bcnt && !(bcnt % uc->desc->residue))
+			residue = 0;
+		else
+			residue -= bcnt % uc->desc->residue;
+
+		if (!residue && (uc->config.dir == DMA_DEV_TO_MEM || !delay)) {
+			ret = DMA_COMPLETE;
+			delay = 0;
+		}
+
+		dma_set_residue(txstate, residue);
+		dma_set_in_flight_bytes(txstate, delay);
+
+	} else {
+		ret = DMA_COMPLETE;
+	}
+
+out:
+	spin_unlock_irqrestore(&uc->vc.lock, flags);
+	return ret;
+}
+
+static int udma_pause(struct dma_chan *chan)
+{
+	struct udma_chan *uc = to_udma_chan(chan);
+
+	/* pause the channel */
+	switch (uc->config.dir) {
+	case DMA_DEV_TO_MEM:
+		udma_rchanrt_update_bits(uc->rchan,
+					 UDMA_RCHAN_RT_PEER_RT_EN_REG,
+					 UDMA_PEER_RT_EN_PAUSE,
+					 UDMA_PEER_RT_EN_PAUSE);
+		break;
+	case DMA_MEM_TO_DEV:
+		udma_tchanrt_update_bits(uc->tchan,
+					 UDMA_TCHAN_RT_PEER_RT_EN_REG,
+					 UDMA_PEER_RT_EN_PAUSE,
+					 UDMA_PEER_RT_EN_PAUSE);
+		break;
+	case DMA_MEM_TO_MEM:
+		udma_tchanrt_update_bits(uc->tchan, UDMA_TCHAN_RT_CTL_REG,
+					 UDMA_CHAN_RT_CTL_PAUSE,
+					 UDMA_CHAN_RT_CTL_PAUSE);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int udma_resume(struct dma_chan *chan)
+{
+	struct udma_chan *uc = to_udma_chan(chan);
+
+	/* resume the channel */
+	switch (uc->config.dir) {
+	case DMA_DEV_TO_MEM:
+		udma_rchanrt_update_bits(uc->rchan,
+					 UDMA_RCHAN_RT_PEER_RT_EN_REG,
+					 UDMA_PEER_RT_EN_PAUSE, 0);
+
+		break;
+	case DMA_MEM_TO_DEV:
+		udma_tchanrt_update_bits(uc->tchan,
+					 UDMA_TCHAN_RT_PEER_RT_EN_REG,
+					 UDMA_PEER_RT_EN_PAUSE, 0);
+		break;
+	case DMA_MEM_TO_MEM:
+		udma_tchanrt_update_bits(uc->tchan, UDMA_TCHAN_RT_CTL_REG,
+					 UDMA_CHAN_RT_CTL_PAUSE, 0);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int udma_terminate_all(struct dma_chan *chan)
+{
+	struct udma_chan *uc = to_udma_chan(chan);
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	spin_lock_irqsave(&uc->vc.lock, flags);
+
+	if (udma_is_chan_running(uc))
+		udma_stop(uc);
+
+	if (uc->desc) {
+		uc->terminated_desc = uc->desc;
+		uc->desc = NULL;
+		uc->terminated_desc->terminated = true;
+		cancel_delayed_work(&uc->tx_drain.work);
+	}
+
+	uc->paused = false;
+
+	vchan_get_all_descriptors(&uc->vc, &head);
+	spin_unlock_irqrestore(&uc->vc.lock, flags);
+	vchan_dma_desc_free_list(&uc->vc, &head);
+
+	return 0;
+}
+
+static void udma_synchronize(struct dma_chan *chan)
+{
+	struct udma_chan *uc = to_udma_chan(chan);
+	unsigned long timeout = msecs_to_jiffies(1000);
+
+	vchan_synchronize(&uc->vc);
+
+	if (uc->state == UDMA_CHAN_IS_TERMINATING) {
+		timeout = wait_for_completion_timeout(&uc->teardown_completed,
+						      timeout);
+		if (!timeout) {
+			dev_warn(uc->ud->dev, "chan%d teardown timeout!\n",
+				 uc->id);
+			udma_dump_chan_stdata(uc);
+			udma_reset_chan(uc, true);
+		}
+	}
+
+	udma_reset_chan(uc, false);
+	if (udma_is_chan_running(uc))
+		dev_warn(uc->ud->dev, "chan%d refused to stop!\n", uc->id);
+
+	cancel_delayed_work_sync(&uc->tx_drain.work);
+	udma_reset_rings(uc);
+}
+
+static void udma_desc_pre_callback(struct virt_dma_chan *vc,
+				   struct virt_dma_desc *vd,
+				   struct dmaengine_result *result)
+{
+	struct udma_chan *uc = to_udma_chan(&vc->chan);
+	struct udma_desc *d;
+
+	if (!vd)
+		return;
+
+	d = to_udma_desc(&vd->tx);
+
+	if (d->metadata_size)
+		udma_fetch_epib(uc, d);
+
+	/* Provide residue information for the client */
+	if (result) {
+		void *desc_vaddr = udma_curr_cppi5_desc_vaddr(d, d->desc_idx);
+
+		if (cppi5_desc_get_type(desc_vaddr) ==
+		    CPPI5_INFO0_DESC_TYPE_VAL_HOST) {
+			result->residue = d->residue -
+					  cppi5_hdesc_get_pktlen(desc_vaddr);
+			if (result->residue)
+				result->result = DMA_TRANS_ABORTED;
+			else
+				result->result = DMA_TRANS_NOERROR;
+		} else {
+			result->residue = 0;
+			result->result = DMA_TRANS_NOERROR;
+		}
+	}
+}
+
+/*
+ * This tasklet handles the completion of a DMA descriptor by
+ * calling its callback and freeing it.
+ */
+static void udma_vchan_complete(unsigned long arg)
+{
+	struct virt_dma_chan *vc = (struct virt_dma_chan *)arg;
+	struct virt_dma_desc *vd, *_vd;
+	struct dmaengine_desc_callback cb;
+	LIST_HEAD(head);
+
+	spin_lock_irq(&vc->lock);
+	list_splice_tail_init(&vc->desc_completed, &head);
+	vd = vc->cyclic;
+	if (vd) {
+		vc->cyclic = NULL;
+		dmaengine_desc_get_callback(&vd->tx, &cb);
+	} else {
+		memset(&cb, 0, sizeof(cb));
+	}
+	spin_unlock_irq(&vc->lock);
+
+	udma_desc_pre_callback(vc, vd, NULL);
+	dmaengine_desc_callback_invoke(&cb, NULL);
+
+	list_for_each_entry_safe(vd, _vd, &head, node) {
+		struct dmaengine_result result;
+
+		dmaengine_desc_get_callback(&vd->tx, &cb);
+
+		list_del(&vd->node);
+
+		udma_desc_pre_callback(vc, vd, &result);
+		dmaengine_desc_callback_invoke(&cb, &result);
+
+		vchan_vdesc_fini(vd);
+	}
+}
+
+static void udma_free_chan_resources(struct dma_chan *chan)
+{
+	struct udma_chan *uc = to_udma_chan(chan);
+	struct udma_dev *ud = to_udma_dev(chan->device);
+
+	udma_terminate_all(chan);
+	if (uc->terminated_desc) {
+		udma_reset_chan(uc, false);
+		udma_reset_rings(uc);
+	}
+
+	cancel_delayed_work_sync(&uc->tx_drain.work);
+	destroy_delayed_work_on_stack(&uc->tx_drain.work);
+
+	if (uc->irq_num_ring > 0) {
+		free_irq(uc->irq_num_ring, uc);
+
+		uc->irq_num_ring = 0;
+	}
+	if (uc->irq_num_udma > 0) {
+		free_irq(uc->irq_num_udma, uc);
+
+		uc->irq_num_udma = 0;
+	}
+
+	/* Release PSI-L pairing */
+	if (uc->psil_paired) {
+		navss_psil_unpair(ud, uc->config.src_thread,
+				  uc->config.dst_thread);
+		uc->psil_paired = false;
+	}
+
+	vchan_free_chan_resources(&uc->vc);
+	tasklet_kill(&uc->vc.task);
+
+	udma_free_tx_resources(uc);
+	udma_free_rx_resources(uc);
+	udma_reset_uchan(uc);
+
+	if (uc->use_dma_pool) {
+		dma_pool_destroy(uc->hdesc_pool);
+		uc->use_dma_pool = false;
+	}
+}
+
+static struct platform_driver udma_driver;
+
+static bool udma_dma_filter_fn(struct dma_chan *chan, void *param)
+{
+	struct udma_chan_config *ucc;
+	struct psil_endpoint_config *ep_config;
+	struct udma_chan *uc;
+	struct udma_dev *ud;
+	u32 *args;
+
+	if (chan->device->dev->driver != &udma_driver.driver)
+		return false;
+
+	uc = to_udma_chan(chan);
+	ucc = &uc->config;
+	ud = uc->ud;
+	args = param;
+
+	ucc->remote_thread_id = args[0];
+
+	if (ucc->remote_thread_id & K3_PSIL_DST_THREAD_ID_OFFSET)
+		ucc->dir = DMA_MEM_TO_DEV;
+	else
+		ucc->dir = DMA_DEV_TO_MEM;
+
+	ep_config = psil_get_ep_config(ucc->remote_thread_id);
+	if (IS_ERR(ep_config)) {
+		dev_err(ud->dev, "No configuration for psi-l thread 0x%04x\n",
+			ucc->remote_thread_id);
+		ucc->dir = DMA_MEM_TO_MEM;
+		ucc->remote_thread_id = -1;
+		return false;
+	}
+
+	ucc->pkt_mode = ep_config->pkt_mode;
+	ucc->channel_tpl = ep_config->channel_tpl;
+	ucc->notdpkt = ep_config->notdpkt;
+	ucc->ep_type = ep_config->ep_type;
+
+	if (ucc->ep_type != PSIL_EP_NATIVE) {
+		const struct udma_match_data *match_data = ud->match_data;
+
+		if (match_data->flags & UDMA_FLAG_PDMA_ACC32)
+			ucc->enable_acc32 = ep_config->pdma_acc32;
+		if (match_data->flags & UDMA_FLAG_PDMA_BURST)
+			ucc->enable_burst = ep_config->pdma_burst;
+	}
+
+	ucc->needs_epib = ep_config->needs_epib;
+	ucc->psd_size = ep_config->psd_size;
+	ucc->metadata_size =
+			(ucc->needs_epib ? CPPI5_INFO0_HDESC_EPIB_SIZE : 0) +
+			ucc->psd_size;
+
+	if (ucc->pkt_mode)
+		ucc->hdesc_size = ALIGN(sizeof(struct cppi5_host_desc_t) +
+				 ucc->metadata_size, ud->desc_align);
+
+	dev_dbg(ud->dev, "chan%d: Remote thread: 0x%04x (%s)\n", uc->id,
+		ucc->remote_thread_id, dmaengine_get_direction_text(ucc->dir));
+
+	return true;
+}
+
+static struct dma_chan *udma_of_xlate(struct of_phandle_args *dma_spec,
+				      struct of_dma *ofdma)
+{
+	struct udma_dev *ud = ofdma->of_dma_data;
+	dma_cap_mask_t mask = ud->ddev.cap_mask;
+	struct dma_chan *chan;
+
+	if (dma_spec->args_count != 1)
+		return NULL;
+
+	chan = __dma_request_channel(&mask, udma_dma_filter_fn,
+				     &dma_spec->args[0], ofdma->of_node);
+	if (!chan) {
+		dev_err(ud->dev, "get channel fail in %s.\n", __func__);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return chan;
+}
+
+static struct udma_match_data am654_main_data = {
+	.psil_base = 0x1000,
+	.enable_memcpy_support = true,
+	.statictr_z_mask = GENMASK(11, 0),
+	.rchan_oes_offset = 0x2000,
+	.tpl_levels = 2,
+	.level_start_idx = {
+		[0] = 8, /* Normal channels */
+		[1] = 0, /* High Throughput channels */
+	},
+};
+
+static struct udma_match_data am654_mcu_data = {
+	.psil_base = 0x6000,
+	.enable_memcpy_support = true, /* TEST: DMA domains */
+	.statictr_z_mask = GENMASK(11, 0),
+	.rchan_oes_offset = 0x2000,
+	.tpl_levels = 2,
+	.level_start_idx = {
+		[0] = 2, /* Normal channels */
+		[1] = 0, /* High Throughput channels */
+	},
+};
+
+static struct udma_match_data j721e_main_data = {
+	.psil_base = 0x1000,
+	.enable_memcpy_support = true,
+	.flags = UDMA_FLAG_PDMA_ACC32 | UDMA_FLAG_PDMA_BURST,
+	.statictr_z_mask = GENMASK(23, 0),
+	.rchan_oes_offset = 0x400,
+	.tpl_levels = 3,
+	.level_start_idx = {
+		[0] = 16, /* Normal channels */
+		[1] = 4, /* High Throughput channels */
+		[2] = 0, /* Ultra High Throughput channels */
+	},
+};
+
+static struct udma_match_data j721e_mcu_data = {
+	.psil_base = 0x6000,
+	.enable_memcpy_support = false, /* MEM_TO_MEM is slow via MCU UDMA */
+	.flags = UDMA_FLAG_PDMA_ACC32 | UDMA_FLAG_PDMA_BURST,
+	.statictr_z_mask = GENMASK(23, 0),
+	.rchan_oes_offset = 0x400,
+	.tpl_levels = 2,
+	.level_start_idx = {
+		[0] = 2, /* Normal channels */
+		[1] = 0, /* High Throughput channels */
+	},
+};
+
+static const struct of_device_id udma_of_match[] = {
+	{
+		.compatible = "ti,am654-navss-main-udmap",
+		.data = &am654_main_data,
+	},
+	{
+		.compatible = "ti,am654-navss-mcu-udmap",
+		.data = &am654_mcu_data,
+	}, {
+		.compatible = "ti,j721e-navss-main-udmap",
+		.data = &j721e_main_data,
+	}, {
+		.compatible = "ti,j721e-navss-mcu-udmap",
+		.data = &j721e_mcu_data,
+	},
+	{ /* Sentinel */ },
+};
+
+static int udma_get_mmrs(struct platform_device *pdev, struct udma_dev *ud)
+{
+	struct resource *res;
+	int i;
+
+	for (i = 0; i < MMR_LAST; i++) {
+		res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+						   mmr_names[i]);
+		ud->mmrs[i] = devm_ioremap_resource(&pdev->dev, res);
+		if (IS_ERR(ud->mmrs[i]))
+			return PTR_ERR(ud->mmrs[i]);
+	}
+
+	return 0;
+}
+
+static int udma_setup_resources(struct udma_dev *ud)
+{
+	struct device *dev = ud->dev;
+	int ch_count, ret, i, j;
+	u32 cap2, cap3;
+	struct ti_sci_resource_desc *rm_desc;
+	struct ti_sci_resource *rm_res, irq_res;
+	struct udma_tisci_rm *tisci_rm = &ud->tisci_rm;
+	static const char * const range_names[] = { "ti,sci-rm-range-tchan",
+						    "ti,sci-rm-range-rchan",
+						    "ti,sci-rm-range-rflow" };
+
+	cap2 = udma_read(ud->mmrs[MMR_GCFG], 0x28);
+	cap3 = udma_read(ud->mmrs[MMR_GCFG], 0x2c);
+
+	ud->rflow_cnt = cap3 & 0x3fff;
+	ud->tchan_cnt = cap2 & 0x1ff;
+	ud->echan_cnt = (cap2 >> 9) & 0x1ff;
+	ud->rchan_cnt = (cap2 >> 18) & 0x1ff;
+	ch_count  = ud->tchan_cnt + ud->rchan_cnt;
+
+	ud->tchan_map = devm_kmalloc_array(dev, BITS_TO_LONGS(ud->tchan_cnt),
+					   sizeof(unsigned long), GFP_KERNEL);
+	ud->tchans = devm_kcalloc(dev, ud->tchan_cnt, sizeof(*ud->tchans),
+				  GFP_KERNEL);
+	ud->rchan_map = devm_kmalloc_array(dev, BITS_TO_LONGS(ud->rchan_cnt),
+					   sizeof(unsigned long), GFP_KERNEL);
+	ud->rchans = devm_kcalloc(dev, ud->rchan_cnt, sizeof(*ud->rchans),
+				  GFP_KERNEL);
+	ud->rflow_gp_map = devm_kmalloc_array(dev, BITS_TO_LONGS(ud->rflow_cnt),
+					      sizeof(unsigned long),
+					      GFP_KERNEL);
+	ud->rflow_gp_map_allocated = devm_kcalloc(dev,
+						  BITS_TO_LONGS(ud->rflow_cnt),
+						  sizeof(unsigned long),
+						  GFP_KERNEL);
+	ud->rflow_in_use = devm_kcalloc(dev, BITS_TO_LONGS(ud->rflow_cnt),
+					sizeof(unsigned long),
+					GFP_KERNEL);
+	ud->rflows = devm_kcalloc(dev, ud->rflow_cnt, sizeof(*ud->rflows),
+				  GFP_KERNEL);
+
+	if (!ud->tchan_map || !ud->rchan_map || !ud->rflow_gp_map ||
+	    !ud->rflow_gp_map_allocated || !ud->tchans || !ud->rchans ||
+	    !ud->rflows || !ud->rflow_in_use)
+		return -ENOMEM;
+
+	/*
+	 * RX flows with the same Ids as RX channels are reserved to be used
+	 * as default flows if remote HW can't generate flow_ids. Those
+	 * RX flows can be requested only explicitly by id.
+	 */
+	bitmap_set(ud->rflow_gp_map_allocated, 0, ud->rchan_cnt);
+
+	/* by default no GP rflows are assigned to Linux */
+	bitmap_set(ud->rflow_gp_map, 0, ud->rflow_cnt);
+
+	/* Get resource ranges from tisci */
+	for (i = 0; i < RM_RANGE_LAST; i++)
+		tisci_rm->rm_ranges[i] =
+			devm_ti_sci_get_of_resource(tisci_rm->tisci, dev,
+						    tisci_rm->tisci_dev_id,
+						    (char *)range_names[i]);
+
+	/* tchan ranges */
+	rm_res = tisci_rm->rm_ranges[RM_RANGE_TCHAN];
+	if (IS_ERR(rm_res)) {
+		bitmap_zero(ud->tchan_map, ud->tchan_cnt);
+	} else {
+		bitmap_fill(ud->tchan_map, ud->tchan_cnt);
+		for (i = 0; i < rm_res->sets; i++) {
+			rm_desc = &rm_res->desc[i];
+			bitmap_clear(ud->tchan_map, rm_desc->start,
+				     rm_desc->num);
+			dev_dbg(dev, "ti-sci-res: tchan: %d:%d\n",
+				rm_desc->start, rm_desc->num);
+		}
+	}
+	irq_res.sets = rm_res->sets;
+
+	/* rchan and matching default flow ranges */
+	rm_res = tisci_rm->rm_ranges[RM_RANGE_RCHAN];
+	if (IS_ERR(rm_res)) {
+		bitmap_zero(ud->rchan_map, ud->rchan_cnt);
+	} else {
+		bitmap_fill(ud->rchan_map, ud->rchan_cnt);
+		for (i = 0; i < rm_res->sets; i++) {
+			rm_desc = &rm_res->desc[i];
+			bitmap_clear(ud->rchan_map, rm_desc->start,
+				     rm_desc->num);
+			dev_dbg(dev, "ti-sci-res: rchan: %d:%d\n",
+				rm_desc->start, rm_desc->num);
+		}
+	}
+
+	irq_res.sets += rm_res->sets;
+	irq_res.desc = kcalloc(irq_res.sets, sizeof(*irq_res.desc), GFP_KERNEL);
+	rm_res = tisci_rm->rm_ranges[RM_RANGE_TCHAN];
+	for (i = 0; i < rm_res->sets; i++) {
+		irq_res.desc[i].start = rm_res->desc[i].start;
+		irq_res.desc[i].num = rm_res->desc[i].num;
+	}
+	rm_res = tisci_rm->rm_ranges[RM_RANGE_RCHAN];
+	for (j = 0; j < rm_res->sets; j++, i++) {
+		irq_res.desc[i].start = rm_res->desc[j].start +
+					ud->match_data->rchan_oes_offset;
+		irq_res.desc[i].num = rm_res->desc[j].num;
+	}
+	ret = ti_sci_inta_msi_domain_alloc_irqs(ud->dev, &irq_res);
+	kfree(irq_res.desc);
+	if (ret) {
+		dev_err(ud->dev, "Failed to allocate MSI interrupts\n");
+		return ret;
+	}
+
+	/* GP rflow ranges */
+	rm_res = tisci_rm->rm_ranges[RM_RANGE_RFLOW];
+	if (IS_ERR(rm_res)) {
+		/* all gp flows are assigned exclusively to Linux */
+		bitmap_clear(ud->rflow_gp_map, ud->rchan_cnt,
+			     ud->rflow_cnt - ud->rchan_cnt);
+	} else {
+		for (i = 0; i < rm_res->sets; i++) {
+			rm_desc = &rm_res->desc[i];
+			bitmap_clear(ud->rflow_gp_map, rm_desc->start,
+				     rm_desc->num);
+			dev_dbg(dev, "ti-sci-res: rflow: %d:%d\n",
+				rm_desc->start, rm_desc->num);
+		}
+	}
+
+	ch_count -= bitmap_weight(ud->tchan_map, ud->tchan_cnt);
+	ch_count -= bitmap_weight(ud->rchan_map, ud->rchan_cnt);
+	if (!ch_count)
+		return -ENODEV;
+
+	ud->channels = devm_kcalloc(dev, ch_count, sizeof(*ud->channels),
+				    GFP_KERNEL);
+	if (!ud->channels)
+		return -ENOMEM;
+
+	dev_info(dev, "Channels: %d (tchan: %u, rchan: %u, gp-rflow: %u)\n",
+		 ch_count,
+		 ud->tchan_cnt - bitmap_weight(ud->tchan_map, ud->tchan_cnt),
+		 ud->rchan_cnt - bitmap_weight(ud->rchan_map, ud->rchan_cnt),
+		 ud->rflow_cnt - bitmap_weight(ud->rflow_gp_map,
+					       ud->rflow_cnt));
+
+	return ch_count;
+}
+
+static int udma_setup_rx_flush(struct udma_dev *ud)
+{
+	struct udma_rx_flush *rx_flush = &ud->rx_flush;
+	struct cppi5_desc_hdr_t *tr_desc;
+	struct cppi5_tr_type1_t *tr_req;
+	struct cppi5_host_desc_t *desc;
+	struct device *dev = ud->dev;
+	struct udma_hwdesc *hwdesc;
+	size_t tr_size;
+
+	/* Allocate 1K buffer for discarded data on RX channel teardown */
+	rx_flush->buffer_size = SZ_1K;
+	rx_flush->buffer_vaddr = devm_kzalloc(dev, rx_flush->buffer_size,
+					      GFP_KERNEL);
+	if (!rx_flush->buffer_vaddr)
+		return -ENOMEM;
+
+	rx_flush->buffer_paddr = dma_map_single(dev, rx_flush->buffer_vaddr,
+						rx_flush->buffer_size,
+						DMA_TO_DEVICE);
+	if (dma_mapping_error(dev, rx_flush->buffer_paddr))
+		return -ENOMEM;
+
+	/* Set up descriptor to be used for TR mode */
+	hwdesc = &rx_flush->hwdescs[0];
+	tr_size = sizeof(struct cppi5_tr_type1_t);
+	hwdesc->cppi5_desc_size = cppi5_trdesc_calc_size(tr_size, 1);
+	hwdesc->cppi5_desc_size = ALIGN(hwdesc->cppi5_desc_size,
+					ud->desc_align);
+
+	hwdesc->cppi5_desc_vaddr = devm_kzalloc(dev, hwdesc->cppi5_desc_size,
+						GFP_KERNEL);
+	if (!hwdesc->cppi5_desc_vaddr)
+		return -ENOMEM;
+
+	hwdesc->cppi5_desc_paddr = dma_map_single(dev, hwdesc->cppi5_desc_vaddr,
+						  hwdesc->cppi5_desc_size,
+						  DMA_TO_DEVICE);
+	if (dma_mapping_error(dev, hwdesc->cppi5_desc_paddr))
+		return -ENOMEM;
+
+	/* Start of the TR req records */
+	hwdesc->tr_req_base = hwdesc->cppi5_desc_vaddr + tr_size;
+	/* Start address of the TR response array */
+	hwdesc->tr_resp_base = hwdesc->tr_req_base + tr_size;
+
+	tr_desc = hwdesc->cppi5_desc_vaddr;
+	cppi5_trdesc_init(tr_desc, 1, tr_size, 0, 0);
+	cppi5_desc_set_pktids(tr_desc, 0, CPPI5_INFO1_DESC_FLOWID_DEFAULT);
+	cppi5_desc_set_retpolicy(tr_desc, 0, 0);
+
+	tr_req = hwdesc->tr_req_base;
+	cppi5_tr_init(&tr_req->flags, CPPI5_TR_TYPE1, false, false,
+		      CPPI5_TR_EVENT_SIZE_COMPLETION, 0);
+	cppi5_tr_csf_set(&tr_req->flags, CPPI5_TR_CSF_SUPR_EVT);
+
+	tr_req->addr = rx_flush->buffer_paddr;
+	tr_req->icnt0 = rx_flush->buffer_size;
+	tr_req->icnt1 = 1;
+
+	/* Set up descriptor to be used for packet mode */
+	hwdesc = &rx_flush->hwdescs[1];
+	hwdesc->cppi5_desc_size = ALIGN(sizeof(struct cppi5_host_desc_t) +
+					CPPI5_INFO0_HDESC_EPIB_SIZE +
+					CPPI5_INFO0_HDESC_PSDATA_MAX_SIZE,
+					ud->desc_align);
+
+	hwdesc->cppi5_desc_vaddr = devm_kzalloc(dev, hwdesc->cppi5_desc_size,
+						GFP_KERNEL);
+	if (!hwdesc->cppi5_desc_vaddr)
+		return -ENOMEM;
+
+	hwdesc->cppi5_desc_paddr = dma_map_single(dev, hwdesc->cppi5_desc_vaddr,
+						  hwdesc->cppi5_desc_size,
+						  DMA_TO_DEVICE);
+	if (dma_mapping_error(dev, hwdesc->cppi5_desc_paddr))
+		return -ENOMEM;
+
+	desc = hwdesc->cppi5_desc_vaddr;
+	cppi5_hdesc_init(desc, 0, 0);
+	cppi5_desc_set_pktids(&desc->hdr, 0, CPPI5_INFO1_DESC_FLOWID_DEFAULT);
+	cppi5_desc_set_retpolicy(&desc->hdr, 0, 0);
+
+	cppi5_hdesc_attach_buf(desc,
+			       rx_flush->buffer_paddr, rx_flush->buffer_size,
+			       rx_flush->buffer_paddr, rx_flush->buffer_size);
+
+	dma_sync_single_for_device(dev, hwdesc->cppi5_desc_paddr,
+				   hwdesc->cppi5_desc_size, DMA_TO_DEVICE);
+	return 0;
+}
+
+#define TI_UDMAC_BUSWIDTHS	(BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | \
+				 BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | \
+				 BIT(DMA_SLAVE_BUSWIDTH_3_BYTES) | \
+				 BIT(DMA_SLAVE_BUSWIDTH_4_BYTES) | \
+				 BIT(DMA_SLAVE_BUSWIDTH_8_BYTES))
+
+static int udma_probe(struct platform_device *pdev)
+{
+	struct device_node *navss_node = pdev->dev.parent->of_node;
+	struct device *dev = &pdev->dev;
+	struct udma_dev *ud;
+	const struct of_device_id *match;
+	int i, ret;
+	int ch_count;
+
+	ret = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(48));
+	if (ret)
+		dev_err(dev, "failed to set dma mask stuff\n");
+
+	ud = devm_kzalloc(dev, sizeof(*ud), GFP_KERNEL);
+	if (!ud)
+		return -ENOMEM;
+
+	ret = udma_get_mmrs(pdev, ud);
+	if (ret)
+		return ret;
+
+	ud->tisci_rm.tisci = ti_sci_get_by_phandle(dev->of_node, "ti,sci");
+	if (IS_ERR(ud->tisci_rm.tisci))
+		return PTR_ERR(ud->tisci_rm.tisci);
+
+	ret = of_property_read_u32(dev->of_node, "ti,sci-dev-id",
+				   &ud->tisci_rm.tisci_dev_id);
+	if (ret) {
+		dev_err(dev, "ti,sci-dev-id read failure %d\n", ret);
+		return ret;
+	}
+	pdev->id = ud->tisci_rm.tisci_dev_id;
+
+	ret = of_property_read_u32(navss_node, "ti,sci-dev-id",
+				   &ud->tisci_rm.tisci_navss_dev_id);
+	if (ret) {
+		dev_err(dev, "NAVSS ti,sci-dev-id read failure %d\n", ret);
+		return ret;
+	}
+
+	ud->tisci_rm.tisci_udmap_ops = &ud->tisci_rm.tisci->ops.rm_udmap_ops;
+	ud->tisci_rm.tisci_psil_ops = &ud->tisci_rm.tisci->ops.rm_psil_ops;
+
+	ud->ringacc = of_k3_ringacc_get_by_phandle(dev->of_node, "ti,ringacc");
+	if (IS_ERR(ud->ringacc))
+		return PTR_ERR(ud->ringacc);
+
+	dev->msi_domain = of_msi_get_domain(dev, dev->of_node,
+					    DOMAIN_BUS_TI_SCI_INTA_MSI);
+	if (!dev->msi_domain) {
+		dev_err(dev, "Failed to get MSI domain\n");
+		return -EPROBE_DEFER;
+	}
+
+	match = of_match_node(udma_of_match, dev->of_node);
+	if (!match) {
+		dev_err(dev, "No compatible match found\n");
+		return -ENODEV;
+	}
+	ud->match_data = match->data;
+
+	dma_cap_set(DMA_SLAVE, ud->ddev.cap_mask);
+	dma_cap_set(DMA_CYCLIC, ud->ddev.cap_mask);
+
+	ud->ddev.device_alloc_chan_resources = udma_alloc_chan_resources;
+	ud->ddev.device_config = udma_slave_config;
+	ud->ddev.device_prep_slave_sg = udma_prep_slave_sg;
+	ud->ddev.device_prep_dma_cyclic = udma_prep_dma_cyclic;
+	ud->ddev.device_issue_pending = udma_issue_pending;
+	ud->ddev.device_tx_status = udma_tx_status;
+	ud->ddev.device_pause = udma_pause;
+	ud->ddev.device_resume = udma_resume;
+	ud->ddev.device_terminate_all = udma_terminate_all;
+	ud->ddev.device_synchronize = udma_synchronize;
+
+	ud->ddev.device_free_chan_resources = udma_free_chan_resources;
+	ud->ddev.src_addr_widths = TI_UDMAC_BUSWIDTHS;
+	ud->ddev.dst_addr_widths = TI_UDMAC_BUSWIDTHS;
+	ud->ddev.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
+	ud->ddev.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
+	ud->ddev.copy_align = DMAENGINE_ALIGN_8_BYTES;
+	ud->ddev.desc_metadata_modes = DESC_METADATA_CLIENT |
+				       DESC_METADATA_ENGINE;
+	if (ud->match_data->enable_memcpy_support) {
+		dma_cap_set(DMA_MEMCPY, ud->ddev.cap_mask);
+		ud->ddev.device_prep_dma_memcpy = udma_prep_dma_memcpy;
+		ud->ddev.directions |= BIT(DMA_MEM_TO_MEM);
+	}
+
+	ud->ddev.dev = dev;
+	ud->dev = dev;
+	ud->psil_base = ud->match_data->psil_base;
+
+	INIT_LIST_HEAD(&ud->ddev.channels);
+	INIT_LIST_HEAD(&ud->desc_to_purge);
+
+	ch_count = udma_setup_resources(ud);
+	if (ch_count <= 0)
+		return ch_count;
+
+	spin_lock_init(&ud->lock);
+	INIT_WORK(&ud->purge_work, udma_purge_desc_work);
+
+	ud->desc_align = 64;
+	if (ud->desc_align < dma_get_cache_alignment())
+		ud->desc_align = dma_get_cache_alignment();
+
+	ret = udma_setup_rx_flush(ud);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < ud->tchan_cnt; i++) {
+		struct udma_tchan *tchan = &ud->tchans[i];
+
+		tchan->id = i;
+		tchan->reg_rt = ud->mmrs[MMR_TCHANRT] + i * 0x1000;
+	}
+
+	for (i = 0; i < ud->rchan_cnt; i++) {
+		struct udma_rchan *rchan = &ud->rchans[i];
+
+		rchan->id = i;
+		rchan->reg_rt = ud->mmrs[MMR_RCHANRT] + i * 0x1000;
+	}
+
+	for (i = 0; i < ud->rflow_cnt; i++) {
+		struct udma_rflow *rflow = &ud->rflows[i];
+
+		rflow->id = i;
+	}
+
+	for (i = 0; i < ch_count; i++) {
+		struct udma_chan *uc = &ud->channels[i];
+
+		uc->ud = ud;
+		uc->vc.desc_free = udma_desc_free;
+		uc->id = i;
+		uc->tchan = NULL;
+		uc->rchan = NULL;
+		uc->config.remote_thread_id = -1;
+		uc->config.dir = DMA_MEM_TO_MEM;
+		uc->name = devm_kasprintf(dev, GFP_KERNEL, "%s chan%d",
+					  dev_name(dev), i);
+
+		vchan_init(&uc->vc, &ud->ddev);
+		/* Use custom vchan completion handling */
+		tasklet_init(&uc->vc.task, udma_vchan_complete,
+			     (unsigned long)&uc->vc);
+		init_completion(&uc->teardown_completed);
+	}
+
+	ret = dma_async_device_register(&ud->ddev);
+	if (ret) {
+		dev_err(dev, "failed to register slave DMA engine: %d\n", ret);
+		return ret;
+	}
+
+	platform_set_drvdata(pdev, ud);
+
+	ret = of_dma_controller_register(dev->of_node, udma_of_xlate, ud);
+	if (ret) {
+		dev_err(dev, "failed to register of_dma controller\n");
+		dma_async_device_unregister(&ud->ddev);
+	}
+
+	return ret;
+}
+
+static struct platform_driver udma_driver = {
+	.driver = {
+		.name	= "ti-udma",
+		.of_match_table = udma_of_match,
+		.suppress_bind_attrs = true,
+	},
+	.probe		= udma_probe,
+};
+builtin_platform_driver(udma_driver);
+
+/* Private interfaces to UDMA */
+#include "k3-udma-private.c"
diff --git a/drivers/dma/ti/k3-udma.h b/drivers/dma/ti/k3-udma.h
new file mode 100644
index 000000000000..128d8744a435
--- /dev/null
+++ b/drivers/dma/ti/k3-udma.h
@@ -0,0 +1,151 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *  Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com
+ */
+
+#ifndef K3_UDMA_H_
+#define K3_UDMA_H_
+
+#include <linux/soc/ti/ti_sci_protocol.h>
+
+/* Global registers */
+#define UDMA_REV_REG			0x0
+#define UDMA_PERF_CTL_REG		0x4
+#define UDMA_EMU_CTL_REG		0x8
+#define UDMA_PSIL_TO_REG		0x10
+#define UDMA_UTC_CTL_REG		0x1c
+#define UDMA_CAP_REG(i)			(0x20 + ((i) * 4))
+#define UDMA_RX_FLOW_ID_FW_OES_REG	0x80
+#define UDMA_RX_FLOW_ID_FW_STATUS_REG	0x88
+
+/* TX chan RT regs */
+#define UDMA_TCHAN_RT_CTL_REG		0x0
+#define UDMA_TCHAN_RT_SWTRIG_REG	0x8
+#define UDMA_TCHAN_RT_STDATA_REG	0x80
+
+#define UDMA_TCHAN_RT_PEER_REG(i)	(0x200 + ((i) * 0x4))
+#define UDMA_TCHAN_RT_PEER_STATIC_TR_XY_REG	\
+	UDMA_TCHAN_RT_PEER_REG(0)	/* PSI-L: 0x400 */
+#define UDMA_TCHAN_RT_PEER_STATIC_TR_Z_REG	\
+	UDMA_TCHAN_RT_PEER_REG(1)	/* PSI-L: 0x401 */
+#define UDMA_TCHAN_RT_PEER_BCNT_REG		\
+	UDMA_TCHAN_RT_PEER_REG(4)	/* PSI-L: 0x404 */
+#define UDMA_TCHAN_RT_PEER_RT_EN_REG		\
+	UDMA_TCHAN_RT_PEER_REG(8)	/* PSI-L: 0x408 */
+
+#define UDMA_TCHAN_RT_PCNT_REG		0x400
+#define UDMA_TCHAN_RT_BCNT_REG		0x408
+#define UDMA_TCHAN_RT_SBCNT_REG		0x410
+
+/* RX chan RT regs */
+#define UDMA_RCHAN_RT_CTL_REG		0x0
+#define UDMA_RCHAN_RT_SWTRIG_REG	0x8
+#define UDMA_RCHAN_RT_STDATA_REG	0x80
+
+#define UDMA_RCHAN_RT_PEER_REG(i)	(0x200 + ((i) * 0x4))
+#define UDMA_RCHAN_RT_PEER_STATIC_TR_XY_REG	\
+	UDMA_RCHAN_RT_PEER_REG(0)	/* PSI-L: 0x400 */
+#define UDMA_RCHAN_RT_PEER_STATIC_TR_Z_REG	\
+	UDMA_RCHAN_RT_PEER_REG(1)	/* PSI-L: 0x401 */
+#define UDMA_RCHAN_RT_PEER_BCNT_REG		\
+	UDMA_RCHAN_RT_PEER_REG(4)	/* PSI-L: 0x404 */
+#define UDMA_RCHAN_RT_PEER_RT_EN_REG		\
+	UDMA_RCHAN_RT_PEER_REG(8)	/* PSI-L: 0x408 */
+
+#define UDMA_RCHAN_RT_PCNT_REG		0x400
+#define UDMA_RCHAN_RT_BCNT_REG		0x408
+#define UDMA_RCHAN_RT_SBCNT_REG		0x410
+
+/* UDMA_TCHAN_RT_CTL_REG/UDMA_RCHAN_RT_CTL_REG */
+#define UDMA_CHAN_RT_CTL_EN		BIT(31)
+#define UDMA_CHAN_RT_CTL_TDOWN		BIT(30)
+#define UDMA_CHAN_RT_CTL_PAUSE		BIT(29)
+#define UDMA_CHAN_RT_CTL_FTDOWN		BIT(28)
+#define UDMA_CHAN_RT_CTL_ERROR		BIT(0)
+
+/* UDMA_TCHAN_RT_PEER_RT_EN_REG/UDMA_RCHAN_RT_PEER_RT_EN_REG (PSI-L: 0x408) */
+#define UDMA_PEER_RT_EN_ENABLE		BIT(31)
+#define UDMA_PEER_RT_EN_TEARDOWN	BIT(30)
+#define UDMA_PEER_RT_EN_PAUSE		BIT(29)
+#define UDMA_PEER_RT_EN_FLUSH		BIT(28)
+#define UDMA_PEER_RT_EN_IDLE		BIT(1)
+
+/*
+ * UDMA_TCHAN_RT_PEER_STATIC_TR_XY_REG /
+ * UDMA_RCHAN_RT_PEER_STATIC_TR_XY_REG
+ */
+#define PDMA_STATIC_TR_X_MASK		GENMASK(26, 24)
+#define PDMA_STATIC_TR_X_SHIFT		(24)
+#define PDMA_STATIC_TR_Y_MASK		GENMASK(11, 0)
+#define PDMA_STATIC_TR_Y_SHIFT		(0)
+
+#define PDMA_STATIC_TR_Y(x)	\
+	(((x) << PDMA_STATIC_TR_Y_SHIFT) & PDMA_STATIC_TR_Y_MASK)
+#define PDMA_STATIC_TR_X(x)	\
+	(((x) << PDMA_STATIC_TR_X_SHIFT) & PDMA_STATIC_TR_X_MASK)
+
+#define PDMA_STATIC_TR_XY_ACC32		BIT(30)
+#define PDMA_STATIC_TR_XY_BURST		BIT(31)
+
+/*
+ * UDMA_TCHAN_RT_PEER_STATIC_TR_Z_REG /
+ * UDMA_RCHAN_RT_PEER_STATIC_TR_Z_REG
+ */
+#define PDMA_STATIC_TR_Z(x, mask)	((x) & (mask))
+
+struct udma_dev;
+struct udma_tchan;
+struct udma_rchan;
+struct udma_rflow;
+
+enum udma_rm_range {
+	RM_RANGE_TCHAN = 0,
+	RM_RANGE_RCHAN,
+	RM_RANGE_RFLOW,
+	RM_RANGE_LAST,
+};
+
+struct udma_tisci_rm {
+	const struct ti_sci_handle *tisci;
+	const struct ti_sci_rm_udmap_ops *tisci_udmap_ops;
+	u32  tisci_dev_id;
+
+	/* tisci information for PSI-L thread pairing/unpairing */
+	const struct ti_sci_rm_psil_ops *tisci_psil_ops;
+	u32  tisci_navss_dev_id;
+
+	struct ti_sci_resource *rm_ranges[RM_RANGE_LAST];
+};
+
+/* Direct access to UDMA low lever resources for the glue layer */
+int xudma_navss_psil_pair(struct udma_dev *ud, u32 src_thread, u32 dst_thread);
+int xudma_navss_psil_unpair(struct udma_dev *ud, u32 src_thread,
+			    u32 dst_thread);
+
+struct udma_dev *of_xudma_dev_get(struct device_node *np, const char *property);
+void xudma_dev_put(struct udma_dev *ud);
+u32 xudma_dev_get_psil_base(struct udma_dev *ud);
+struct udma_tisci_rm *xudma_dev_get_tisci_rm(struct udma_dev *ud);
+
+int xudma_alloc_gp_rflow_range(struct udma_dev *ud, int from, int cnt);
+int xudma_free_gp_rflow_range(struct udma_dev *ud, int from, int cnt);
+
+struct udma_tchan *xudma_tchan_get(struct udma_dev *ud, int id);
+struct udma_rchan *xudma_rchan_get(struct udma_dev *ud, int id);
+struct udma_rflow *xudma_rflow_get(struct udma_dev *ud, int id);
+
+void xudma_tchan_put(struct udma_dev *ud, struct udma_tchan *p);
+void xudma_rchan_put(struct udma_dev *ud, struct udma_rchan *p);
+void xudma_rflow_put(struct udma_dev *ud, struct udma_rflow *p);
+
+int xudma_tchan_get_id(struct udma_tchan *p);
+int xudma_rchan_get_id(struct udma_rchan *p);
+int xudma_rflow_get_id(struct udma_rflow *p);
+
+u32 xudma_tchanrt_read(struct udma_tchan *tchan, int reg);
+void xudma_tchanrt_write(struct udma_tchan *tchan, int reg, u32 val);
+u32 xudma_rchanrt_read(struct udma_rchan *rchan, int reg);
+void xudma_rchanrt_write(struct udma_rchan *rchan, int reg, u32 val);
+bool xudma_rflow_is_gp(struct udma_dev *ud, int id);
+
+#endif /* K3_UDMA_H_ */
diff --git a/drivers/dma/ti/omap-dma.c b/drivers/dma/ti/omap-dma.c
index 6b6ba238b81a..a014ab96e673 100644
--- a/drivers/dma/ti/omap-dma.c
+++ b/drivers/dma/ti/omap-dma.c
@@ -2,6 +2,7 @@
 /*
  * OMAP DMAengine support
  */
+#include <linux/cpu_pm.h>
 #include <linux/delay.h>
 #include <linux/dmaengine.h>
 #include <linux/dma-mapping.h>
@@ -23,12 +24,33 @@
 #define OMAP_SDMA_REQUESTS	127
 #define OMAP_SDMA_CHANNELS	32
 
+struct omap_dma_config {
+	int lch_end;
+	unsigned int rw_priority:1;
+	unsigned int needs_busy_check:1;
+	unsigned int may_lose_context:1;
+	unsigned int needs_lch_clear:1;
+};
+
+struct omap_dma_context {
+	u32 irqenable_l0;
+	u32 irqenable_l1;
+	u32 ocp_sysconfig;
+	u32 gcr;
+};
+
 struct omap_dmadev {
 	struct dma_device ddev;
 	spinlock_t lock;
 	void __iomem *base;
 	const struct omap_dma_reg *reg_map;
 	struct omap_system_dma_plat_info *plat;
+	const struct omap_dma_config *cfg;
+	struct notifier_block nb;
+	struct omap_dma_context context;
+	int lch_count;
+	DECLARE_BITMAP(lch_bitmap, OMAP_SDMA_CHANNELS);
+	struct mutex lch_lock;		/* for assigning logical channels */
 	bool legacy;
 	bool ll123_supported;
 	struct dma_pool *desc_pool;
@@ -376,6 +398,19 @@ static unsigned omap_dma_get_csr(struct omap_chan *c)
 	return val;
 }
 
+static void omap_dma_clear_lch(struct omap_dmadev *od, int lch)
+{
+	struct omap_chan *c;
+	int i;
+
+	c = od->lch_map[lch];
+	if (!c)
+		return;
+
+	for (i = CSDP; i <= od->cfg->lch_end; i++)
+		omap_dma_chan_write(c, i, 0);
+}
+
 static void omap_dma_assign(struct omap_dmadev *od, struct omap_chan *c,
 	unsigned lch)
 {
@@ -633,6 +668,37 @@ static irqreturn_t omap_dma_irq(int irq, void *devid)
 	return IRQ_HANDLED;
 }
 
+static int omap_dma_get_lch(struct omap_dmadev *od, int *lch)
+{
+	int channel;
+
+	mutex_lock(&od->lch_lock);
+	channel = find_first_zero_bit(od->lch_bitmap, od->lch_count);
+	if (channel >= od->lch_count)
+		goto out_busy;
+	set_bit(channel, od->lch_bitmap);
+	mutex_unlock(&od->lch_lock);
+
+	omap_dma_clear_lch(od, channel);
+	*lch = channel;
+
+	return 0;
+
+out_busy:
+	mutex_unlock(&od->lch_lock);
+	*lch = -EINVAL;
+
+	return -EBUSY;
+}
+
+static void omap_dma_put_lch(struct omap_dmadev *od, int lch)
+{
+	omap_dma_clear_lch(od, lch);
+	mutex_lock(&od->lch_lock);
+	clear_bit(lch, od->lch_bitmap);
+	mutex_unlock(&od->lch_lock);
+}
+
 static int omap_dma_alloc_chan_resources(struct dma_chan *chan)
 {
 	struct omap_dmadev *od = to_omap_dma_dev(chan->device);
@@ -644,8 +710,7 @@ static int omap_dma_alloc_chan_resources(struct dma_chan *chan)
 		ret = omap_request_dma(c->dma_sig, "DMA engine",
 				       omap_dma_callback, c, &c->dma_ch);
 	} else {
-		ret = omap_request_dma(c->dma_sig, "DMA engine", NULL, NULL,
-				       &c->dma_ch);
+		ret = omap_dma_get_lch(od, &c->dma_ch);
 	}
 
 	dev_dbg(dev, "allocating channel %u for %u\n", c->dma_ch, c->dma_sig);
@@ -702,7 +767,11 @@ static void omap_dma_free_chan_resources(struct dma_chan *chan)
 	c->channel_base = NULL;
 	od->lch_map[c->dma_ch] = NULL;
 	vchan_free_chan_resources(&c->vc);
-	omap_free_dma(c->dma_ch);
+
+	if (od->legacy)
+		omap_free_dma(c->dma_ch);
+	else
+		omap_dma_put_lch(od, c->dma_ch);
 
 	dev_dbg(od->ddev.dev, "freeing channel %u used for %u\n", c->dma_ch,
 		c->dma_sig);
@@ -1453,16 +1522,128 @@ static void omap_dma_free(struct omap_dmadev *od)
 	}
 }
 
+/* Currently only used for omap2. For omap1, also a check for lcd_dma is needed */
+static int omap_dma_busy_notifier(struct notifier_block *nb,
+				  unsigned long cmd, void *v)
+{
+	struct omap_dmadev *od;
+	struct omap_chan *c;
+	int lch = -1;
+
+	od = container_of(nb, struct omap_dmadev, nb);
+
+	switch (cmd) {
+	case CPU_CLUSTER_PM_ENTER:
+		while (1) {
+			lch = find_next_bit(od->lch_bitmap, od->lch_count,
+					    lch + 1);
+			if (lch >= od->lch_count)
+				break;
+			c = od->lch_map[lch];
+			if (!c)
+				continue;
+			if (omap_dma_chan_read(c, CCR) & CCR_ENABLE)
+				return NOTIFY_BAD;
+		}
+		break;
+	case CPU_CLUSTER_PM_ENTER_FAILED:
+	case CPU_CLUSTER_PM_EXIT:
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+/*
+ * We are using IRQENABLE_L1, and legacy DMA code was using IRQENABLE_L0.
+ * As the DSP may be using IRQENABLE_L2 and L3, let's not touch those for
+ * now. Context save seems to be only currently needed on omap3.
+ */
+static void omap_dma_context_save(struct omap_dmadev *od)
+{
+	od->context.irqenable_l0 = omap_dma_glbl_read(od, IRQENABLE_L0);
+	od->context.irqenable_l1 = omap_dma_glbl_read(od, IRQENABLE_L1);
+	od->context.ocp_sysconfig = omap_dma_glbl_read(od, OCP_SYSCONFIG);
+	od->context.gcr = omap_dma_glbl_read(od, GCR);
+}
+
+static void omap_dma_context_restore(struct omap_dmadev *od)
+{
+	int i;
+
+	omap_dma_glbl_write(od, GCR, od->context.gcr);
+	omap_dma_glbl_write(od, OCP_SYSCONFIG, od->context.ocp_sysconfig);
+	omap_dma_glbl_write(od, IRQENABLE_L0, od->context.irqenable_l0);
+	omap_dma_glbl_write(od, IRQENABLE_L1, od->context.irqenable_l1);
+
+	/* Clear IRQSTATUS_L0 as legacy DMA code is no longer doing it */
+	if (od->plat->errata & DMA_ROMCODE_BUG)
+		omap_dma_glbl_write(od, IRQSTATUS_L0, 0);
+
+	/* Clear dma channels */
+	for (i = 0; i < od->lch_count; i++)
+		omap_dma_clear_lch(od, i);
+}
+
+/* Currently only used for omap3 */
+static int omap_dma_context_notifier(struct notifier_block *nb,
+				     unsigned long cmd, void *v)
+{
+	struct omap_dmadev *od;
+
+	od = container_of(nb, struct omap_dmadev, nb);
+
+	switch (cmd) {
+	case CPU_CLUSTER_PM_ENTER:
+		omap_dma_context_save(od);
+		break;
+	case CPU_CLUSTER_PM_ENTER_FAILED:
+	case CPU_CLUSTER_PM_EXIT:
+		omap_dma_context_restore(od);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static void omap_dma_init_gcr(struct omap_dmadev *od, int arb_rate,
+			      int max_fifo_depth, int tparams)
+{
+	u32 val;
+
+	/* Set only for omap2430 and later */
+	if (!od->cfg->rw_priority)
+		return;
+
+	if (max_fifo_depth == 0)
+		max_fifo_depth = 1;
+	if (arb_rate == 0)
+		arb_rate = 1;
+
+	val = 0xff & max_fifo_depth;
+	val |= (0x3 & tparams) << 12;
+	val |= (arb_rate & 0xff) << 16;
+
+	omap_dma_glbl_write(od, GCR, val);
+}
+
 #define OMAP_DMA_BUSWIDTHS	(BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | \
 				 BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | \
 				 BIT(DMA_SLAVE_BUSWIDTH_4_BYTES))
 
+/*
+ * No flags currently set for default configuration as omap1 is still
+ * using platform data.
+ */
+static const struct omap_dma_config default_cfg;
+
 static int omap_dma_probe(struct platform_device *pdev)
 {
+	const struct omap_dma_config *conf;
 	struct omap_dmadev *od;
 	struct resource *res;
 	int rc, i, irq;
-	u32 lch_count;
+	u32 val;
 
 	od = devm_kzalloc(&pdev->dev, sizeof(*od), GFP_KERNEL);
 	if (!od)
@@ -1473,9 +1654,21 @@ static int omap_dma_probe(struct platform_device *pdev)
 	if (IS_ERR(od->base))
 		return PTR_ERR(od->base);
 
-	od->plat = omap_get_plat_info();
-	if (!od->plat)
-		return -EPROBE_DEFER;
+	conf = of_device_get_match_data(&pdev->dev);
+	if (conf) {
+		od->cfg = conf;
+		od->plat = dev_get_platdata(&pdev->dev);
+		if (!od->plat) {
+			dev_err(&pdev->dev, "omap_system_dma_plat_info is missing");
+			return -ENODEV;
+		}
+	} else {
+		od->cfg = &default_cfg;
+
+		od->plat = omap_get_plat_info();
+		if (!od->plat)
+			return -EPROBE_DEFER;
+	}
 
 	od->reg_map = od->plat->reg_map;
 
@@ -1507,6 +1700,7 @@ static int omap_dma_probe(struct platform_device *pdev)
 	od->ddev.max_burst = SZ_16M - 1; /* CCEN: 24bit unsigned */
 	od->ddev.dev = &pdev->dev;
 	INIT_LIST_HEAD(&od->ddev.channels);
+	mutex_init(&od->lch_lock);
 	spin_lock_init(&od->lock);
 	spin_lock_init(&od->irq_lock);
 
@@ -1522,18 +1716,30 @@ static int omap_dma_probe(struct platform_device *pdev)
 
 	/* Number of available logical channels */
 	if (!pdev->dev.of_node) {
-		lch_count = od->plat->dma_attr->lch_count;
-		if (unlikely(!lch_count))
-			lch_count = OMAP_SDMA_CHANNELS;
+		od->lch_count = od->plat->dma_attr->lch_count;
+		if (unlikely(!od->lch_count))
+			od->lch_count = OMAP_SDMA_CHANNELS;
 	} else if (of_property_read_u32(pdev->dev.of_node, "dma-channels",
-					&lch_count)) {
+					&od->lch_count)) {
 		dev_info(&pdev->dev,
 			 "Missing dma-channels property, using %u.\n",
 			 OMAP_SDMA_CHANNELS);
-		lch_count = OMAP_SDMA_CHANNELS;
+		od->lch_count = OMAP_SDMA_CHANNELS;
+	}
+
+	/* Mask of allowed logical channels */
+	if (pdev->dev.of_node && !of_property_read_u32(pdev->dev.of_node,
+						       "dma-channel-mask",
+						       &val)) {
+		/* Tag channels not in mask as reserved */
+		val = ~val;
+		bitmap_from_arr32(od->lch_bitmap, &val, od->lch_count);
 	}
+	if (od->plat->dma_attr->dev_caps & HS_CHANNELS_RESERVED)
+		bitmap_set(od->lch_bitmap, 0, 2);
 
-	od->lch_map = devm_kcalloc(&pdev->dev, lch_count, sizeof(*od->lch_map),
+	od->lch_map = devm_kcalloc(&pdev->dev, od->lch_count,
+				   sizeof(*od->lch_map),
 				   GFP_KERNEL);
 	if (!od->lch_map)
 		return -ENOMEM;
@@ -1605,6 +1811,16 @@ static int omap_dma_probe(struct platform_device *pdev)
 		}
 	}
 
+	omap_dma_init_gcr(od, DMA_DEFAULT_ARB_RATE, DMA_DEFAULT_FIFO_DEPTH, 0);
+
+	if (od->cfg->needs_busy_check) {
+		od->nb.notifier_call = omap_dma_busy_notifier;
+		cpu_pm_register_notifier(&od->nb);
+	} else if (od->cfg->may_lose_context) {
+		od->nb.notifier_call = omap_dma_context_notifier;
+		cpu_pm_register_notifier(&od->nb);
+	}
+
 	dev_info(&pdev->dev, "OMAP DMA engine driver%s\n",
 		 od->ll123_supported ? " (LinkedList1/2/3 supported)" : "");
 
@@ -1616,6 +1832,9 @@ static int omap_dma_remove(struct platform_device *pdev)
 	struct omap_dmadev *od = platform_get_drvdata(pdev);
 	int irq;
 
+	if (od->cfg->may_lose_context)
+		cpu_pm_unregister_notifier(&od->nb);
+
 	if (pdev->dev.of_node)
 		of_dma_controller_free(pdev->dev.of_node);
 
@@ -1637,12 +1856,45 @@ static int omap_dma_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct omap_dma_config omap2420_data = {
+	.lch_end = CCFN,
+	.rw_priority = true,
+	.needs_lch_clear = true,
+	.needs_busy_check = true,
+};
+
+static const struct omap_dma_config omap2430_data = {
+	.lch_end = CCFN,
+	.rw_priority = true,
+	.needs_lch_clear = true,
+};
+
+static const struct omap_dma_config omap3430_data = {
+	.lch_end = CCFN,
+	.rw_priority = true,
+	.needs_lch_clear = true,
+	.may_lose_context = true,
+};
+
+static const struct omap_dma_config omap3630_data = {
+	.lch_end = CCDN,
+	.rw_priority = true,
+	.needs_lch_clear = true,
+	.may_lose_context = true,
+};
+
+static const struct omap_dma_config omap4_data = {
+	.lch_end = CCDN,
+	.rw_priority = true,
+	.needs_lch_clear = true,
+};
+
 static const struct of_device_id omap_dma_match[] = {
-	{ .compatible = "ti,omap2420-sdma", },
-	{ .compatible = "ti,omap2430-sdma", },
-	{ .compatible = "ti,omap3430-sdma", },
-	{ .compatible = "ti,omap3630-sdma", },
-	{ .compatible = "ti,omap4430-sdma", },
+	{ .compatible = "ti,omap2420-sdma", .data = &omap2420_data, },
+	{ .compatible = "ti,omap2430-sdma", .data = &omap2430_data, },
+	{ .compatible = "ti,omap3430-sdma", .data = &omap3430_data, },
+	{ .compatible = "ti,omap3630-sdma", .data = &omap3630_data, },
+	{ .compatible = "ti,omap4430-sdma", .data = &omap4_data, },
 	{},
 };
 MODULE_DEVICE_TABLE(of, omap_dma_match);
diff --git a/drivers/dma/virt-dma.c b/drivers/dma/virt-dma.c
index 256fc662c500..23e33a85f033 100644
--- a/drivers/dma/virt-dma.c
+++ b/drivers/dma/virt-dma.c
@@ -114,13 +114,8 @@ void vchan_dma_desc_free_list(struct virt_dma_chan *vc, struct list_head *head)
 	struct virt_dma_desc *vd, *_vd;
 
 	list_for_each_entry_safe(vd, _vd, head, node) {
-		if (dmaengine_desc_test_reuse(&vd->tx)) {
-			list_move_tail(&vd->node, &vc->desc_allocated);
-		} else {
-			dev_dbg(vc->chan.device->dev, "txd %p: freeing\n", vd);
-			list_del(&vd->node);
-			vc->desc_free(vd);
-		}
+		list_del(&vd->node);
+		vchan_vdesc_fini(vd);
 	}
 }
 EXPORT_SYMBOL_GPL(vchan_dma_desc_free_list);
@@ -134,6 +129,7 @@ void vchan_init(struct virt_dma_chan *vc, struct dma_device *dmadev)
 	INIT_LIST_HEAD(&vc->desc_submitted);
 	INIT_LIST_HEAD(&vc->desc_issued);
 	INIT_LIST_HEAD(&vc->desc_completed);
+	INIT_LIST_HEAD(&vc->desc_terminated);
 
 	tasklet_init(&vc->task, vchan_complete, (unsigned long)vc);
 
diff --git a/drivers/dma/virt-dma.h b/drivers/dma/virt-dma.h
index ab158bac03a7..e9f5250fbe4d 100644
--- a/drivers/dma/virt-dma.h
+++ b/drivers/dma/virt-dma.h
@@ -31,9 +31,9 @@ struct virt_dma_chan {
 	struct list_head desc_submitted;
 	struct list_head desc_issued;
 	struct list_head desc_completed;
+	struct list_head desc_terminated;
 
 	struct virt_dma_desc *cyclic;
-	struct virt_dma_desc *vd_terminated;
 };
 
 static inline struct virt_dma_chan *to_virt_chan(struct dma_chan *chan)
@@ -113,10 +113,15 @@ static inline void vchan_vdesc_fini(struct virt_dma_desc *vd)
 {
 	struct virt_dma_chan *vc = to_virt_chan(vd->tx.chan);
 
-	if (dmaengine_desc_test_reuse(&vd->tx))
+	if (dmaengine_desc_test_reuse(&vd->tx)) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&vc->lock, flags);
 		list_add(&vd->node, &vc->desc_allocated);
-	else
+		spin_unlock_irqrestore(&vc->lock, flags);
+	} else {
 		vc->desc_free(vd);
+	}
 }
 
 /**
@@ -141,11 +146,8 @@ static inline void vchan_terminate_vdesc(struct virt_dma_desc *vd)
 {
 	struct virt_dma_chan *vc = to_virt_chan(vd->tx.chan);
 
-	/* free up stuck descriptor */
-	if (vc->vd_terminated)
-		vchan_vdesc_fini(vc->vd_terminated);
+	list_add_tail(&vd->node, &vc->desc_terminated);
 
-	vc->vd_terminated = vd;
 	if (vc->cyclic == vd)
 		vc->cyclic = NULL;
 }
@@ -179,6 +181,7 @@ static inline void vchan_get_all_descriptors(struct virt_dma_chan *vc,
 	list_splice_tail_init(&vc->desc_submitted, head);
 	list_splice_tail_init(&vc->desc_issued, head);
 	list_splice_tail_init(&vc->desc_completed, head);
+	list_splice_tail_init(&vc->desc_terminated, head);
 }
 
 static inline void vchan_free_chan_resources(struct virt_dma_chan *vc)
@@ -207,16 +210,18 @@ static inline void vchan_free_chan_resources(struct virt_dma_chan *vc)
  */
 static inline void vchan_synchronize(struct virt_dma_chan *vc)
 {
+	LIST_HEAD(head);
 	unsigned long flags;
 
 	tasklet_kill(&vc->task);
 
 	spin_lock_irqsave(&vc->lock, flags);
-	if (vc->vd_terminated) {
-		vchan_vdesc_fini(vc->vd_terminated);
-		vc->vd_terminated = NULL;
-	}
+
+	list_splice_tail_init(&vc->desc_terminated, &head);
+
 	spin_unlock_irqrestore(&vc->lock, flags);
+
+	vchan_dma_desc_free_list(vc, &head);
 }
 
 #endif
diff --git a/drivers/dma/xilinx/zynqmp_dma.c b/drivers/dma/xilinx/zynqmp_dma.c
index 9c845c07b107..d47749a35863 100644
--- a/drivers/dma/xilinx/zynqmp_dma.c
+++ b/drivers/dma/xilinx/zynqmp_dma.c
@@ -123,10 +123,12 @@
 /* Max transfer size per descriptor */
 #define ZYNQMP_DMA_MAX_TRANS_LEN	0x40000000
 
+/* Max burst lengths */
+#define ZYNQMP_DMA_MAX_DST_BURST_LEN    32768U
+#define ZYNQMP_DMA_MAX_SRC_BURST_LEN    32768U
+
 /* Reset values for data attributes */
 #define ZYNQMP_DMA_AXCACHE_VAL		0xF
-#define ZYNQMP_DMA_ARLEN_RST_VAL	0xF
-#define ZYNQMP_DMA_AWLEN_RST_VAL	0xF
 
 #define ZYNQMP_DMA_SRC_ISSUE_RST_VAL	0x1F
 
@@ -534,17 +536,19 @@ static void zynqmp_dma_handle_ovfl_int(struct zynqmp_dma_chan *chan, u32 status)
 
 static void zynqmp_dma_config(struct zynqmp_dma_chan *chan)
 {
-	u32 val;
+	u32 val, burst_val;
 
 	val = readl(chan->regs + ZYNQMP_DMA_CTRL0);
 	val |= ZYNQMP_DMA_POINT_TYPE_SG;
 	writel(val, chan->regs + ZYNQMP_DMA_CTRL0);
 
 	val = readl(chan->regs + ZYNQMP_DMA_DATA_ATTR);
+	burst_val = __ilog2_u32(chan->src_burst_len);
 	val = (val & ~ZYNQMP_DMA_ARLEN) |
-		(chan->src_burst_len << ZYNQMP_DMA_ARLEN_OFST);
+		((burst_val << ZYNQMP_DMA_ARLEN_OFST) & ZYNQMP_DMA_ARLEN);
+	burst_val = __ilog2_u32(chan->dst_burst_len);
 	val = (val & ~ZYNQMP_DMA_AWLEN) |
-		(chan->dst_burst_len << ZYNQMP_DMA_AWLEN_OFST);
+		((burst_val << ZYNQMP_DMA_AWLEN_OFST) & ZYNQMP_DMA_AWLEN);
 	writel(val, chan->regs + ZYNQMP_DMA_DATA_ATTR);
 }
 
@@ -560,8 +564,10 @@ static int zynqmp_dma_device_config(struct dma_chan *dchan,
 {
 	struct zynqmp_dma_chan *chan = to_chan(dchan);
 
-	chan->src_burst_len = config->src_maxburst;
-	chan->dst_burst_len = config->dst_maxburst;
+	chan->src_burst_len = clamp(config->src_maxburst, 1U,
+		ZYNQMP_DMA_MAX_SRC_BURST_LEN);
+	chan->dst_burst_len = clamp(config->dst_maxburst, 1U,
+		ZYNQMP_DMA_MAX_DST_BURST_LEN);
 
 	return 0;
 }
@@ -887,8 +893,8 @@ static int zynqmp_dma_chan_probe(struct zynqmp_dma_device *zdev,
 		return PTR_ERR(chan->regs);
 
 	chan->bus_width = ZYNQMP_DMA_BUS_WIDTH_64;
-	chan->dst_burst_len = ZYNQMP_DMA_AWLEN_RST_VAL;
-	chan->src_burst_len = ZYNQMP_DMA_ARLEN_RST_VAL;
+	chan->dst_burst_len = ZYNQMP_DMA_MAX_DST_BURST_LEN;
+	chan->src_burst_len = ZYNQMP_DMA_MAX_SRC_BURST_LEN;
 	err = of_property_read_u32(node, "xlnx,bus-width", &chan->bus_width);
 	if (err < 0) {
 		dev_err(&pdev->dev, "missing xlnx,bus-width property\n");