Adding upstream version 5.10.209.upstream/5.10.209upstream

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

16 files changed, 13165 insertions, 0 deletions

diff --git a/drivers/dma/ti/Kconfig b/drivers/dma/ti/Kconfig
new file mode 100644
index 000000000..79618fac1
--- /dev/null
+++ b/drivers/dma/ti/Kconfig
@@ -0,0 +1,62 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Texas Instruments DMA drivers
+#
+
+config TI_CPPI41
+	tristate "Texas Instruments CPPI 4.1 DMA support"
+	depends on (ARCH_OMAP || ARCH_DAVINCI_DA8XX)
+	select DMA_ENGINE
+	help
+	  The Communications Port Programming Interface (CPPI) 4.1 DMA engine
+	  is currently used by the USB driver on AM335x and DA8xx platforms.
+
+config TI_EDMA
+	tristate "Texas Instruments EDMA support"
+	depends on ARCH_DAVINCI || ARCH_OMAP || ARCH_KEYSTONE || COMPILE_TEST
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	select TI_DMA_CROSSBAR if (ARCH_OMAP || COMPILE_TEST)
+	default y
+	help
+	  Enable support for the TI EDMA (Enhanced DMA) controller. This DMA
+	  engine is found on TI DaVinci, AM33xx, AM43xx, DRA7xx and Keystone 2
+	  parts.
+
+config DMA_OMAP
+	tristate "Texas Instruments sDMA (omap-dma) support"
+	depends on ARCH_OMAP || COMPILE_TEST
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	select TI_DMA_CROSSBAR if (SOC_DRA7XX || COMPILE_TEST)
+	default y
+	help
+	  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
+	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
+	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
new file mode 100644
index 000000000..0c67254ca
--- /dev/null
+++ b/drivers/dma/ti/Makefile
@@ -0,0 +1,11 @@
+# SPDX-License-Identifier: GPL-2.0
+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 \
+			    k3-psil-j7200.o
+obj-$(CONFIG_TI_DMA_CROSSBAR) += dma-crossbar.o
diff --git a/drivers/dma/ti/cppi41.c b/drivers/dma/ti/cppi41.c
new file mode 100644
index 000000000..8c2f7ebe9
--- /dev/null
+++ b/drivers/dma/ti/cppi41.c
@@ -0,0 +1,1257 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/delay.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/platform_device.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+#include <linux/of_dma.h>
+#include <linux/of_irq.h>
+#include <linux/dmapool.h>
+#include <linux/interrupt.h>
+#include <linux/of_address.h>
+#include <linux/pm_runtime.h>
+#include "../dmaengine.h"
+
+#define DESC_TYPE	27
+#define DESC_TYPE_HOST	0x10
+#define DESC_TYPE_TEARD	0x13
+
+#define TD_DESC_IS_RX	(1 << 16)
+#define TD_DESC_DMA_NUM	10
+
+#define DESC_LENGTH_BITS_NUM	21
+
+#define DESC_TYPE_USB	(5 << 26)
+#define DESC_PD_COMPLETE	(1 << 31)
+
+/* DMA engine */
+#define DMA_TDFDQ	4
+#define DMA_TXGCR(x)	(0x800 + (x) * 0x20)
+#define DMA_RXGCR(x)	(0x808 + (x) * 0x20)
+#define RXHPCRA0		4
+
+#define GCR_CHAN_ENABLE		(1 << 31)
+#define GCR_TEARDOWN		(1 << 30)
+#define GCR_STARV_RETRY		(1 << 24)
+#define GCR_DESC_TYPE_HOST	(1 << 14)
+
+/* DMA scheduler */
+#define DMA_SCHED_CTRL		0
+#define DMA_SCHED_CTRL_EN	(1 << 31)
+#define DMA_SCHED_WORD(x)	((x) * 4 + 0x800)
+
+#define SCHED_ENTRY0_CHAN(x)	((x) << 0)
+#define SCHED_ENTRY0_IS_RX	(1 << 7)
+
+#define SCHED_ENTRY1_CHAN(x)	((x) << 8)
+#define SCHED_ENTRY1_IS_RX	(1 << 15)
+
+#define SCHED_ENTRY2_CHAN(x)	((x) << 16)
+#define SCHED_ENTRY2_IS_RX	(1 << 23)
+
+#define SCHED_ENTRY3_CHAN(x)	((x) << 24)
+#define SCHED_ENTRY3_IS_RX	(1 << 31)
+
+/* Queue manager */
+/* 4 KiB of memory for descriptors, 2 for each endpoint */
+#define ALLOC_DECS_NUM		128
+#define DESCS_AREAS		1
+#define TOTAL_DESCS_NUM		(ALLOC_DECS_NUM * DESCS_AREAS)
+#define QMGR_SCRATCH_SIZE	(TOTAL_DESCS_NUM * 4)
+
+#define QMGR_LRAM0_BASE		0x80
+#define QMGR_LRAM_SIZE		0x84
+#define QMGR_LRAM1_BASE		0x88
+#define QMGR_MEMBASE(x)		(0x1000 + (x) * 0x10)
+#define QMGR_MEMCTRL(x)		(0x1004 + (x) * 0x10)
+#define QMGR_MEMCTRL_IDX_SH	16
+#define QMGR_MEMCTRL_DESC_SH	8
+
+#define QMGR_PEND(x)	(0x90 + (x) * 4)
+
+#define QMGR_PENDING_SLOT_Q(x)	(x / 32)
+#define QMGR_PENDING_BIT_Q(x)	(x % 32)
+
+#define QMGR_QUEUE_A(n)	(0x2000 + (n) * 0x10)
+#define QMGR_QUEUE_B(n)	(0x2004 + (n) * 0x10)
+#define QMGR_QUEUE_C(n)	(0x2008 + (n) * 0x10)
+#define QMGR_QUEUE_D(n)	(0x200c + (n) * 0x10)
+
+/* Packet Descriptor */
+#define PD2_ZERO_LENGTH		(1 << 19)
+
+struct cppi41_channel {
+	struct dma_chan chan;
+	struct dma_async_tx_descriptor txd;
+	struct cppi41_dd *cdd;
+	struct cppi41_desc *desc;
+	dma_addr_t desc_phys;
+	void __iomem *gcr_reg;
+	int is_tx;
+	u32 residue;
+
+	unsigned int q_num;
+	unsigned int q_comp_num;
+	unsigned int port_num;
+
+	unsigned td_retry;
+	unsigned td_queued:1;
+	unsigned td_seen:1;
+	unsigned td_desc_seen:1;
+
+	struct list_head node;		/* Node for pending list */
+};
+
+struct cppi41_desc {
+	u32 pd0;
+	u32 pd1;
+	u32 pd2;
+	u32 pd3;
+	u32 pd4;
+	u32 pd5;
+	u32 pd6;
+	u32 pd7;
+} __aligned(32);
+
+struct chan_queues {
+	u16 submit;
+	u16 complete;
+};
+
+struct cppi41_dd {
+	struct dma_device ddev;
+
+	void *qmgr_scratch;
+	dma_addr_t scratch_phys;
+
+	struct cppi41_desc *cd;
+	dma_addr_t descs_phys;
+	u32 first_td_desc;
+	struct cppi41_channel *chan_busy[ALLOC_DECS_NUM];
+
+	void __iomem *ctrl_mem;
+	void __iomem *sched_mem;
+	void __iomem *qmgr_mem;
+	unsigned int irq;
+	const struct chan_queues *queues_rx;
+	const struct chan_queues *queues_tx;
+	struct chan_queues td_queue;
+	u16 first_completion_queue;
+	u16 qmgr_num_pend;
+	u32 n_chans;
+	u8 platform;
+
+	struct list_head pending;	/* Pending queued transfers */
+	spinlock_t lock;		/* Lock for pending list */
+
+	/* context for suspend/resume */
+	unsigned int dma_tdfdq;
+
+	bool is_suspended;
+};
+
+static struct chan_queues am335x_usb_queues_tx[] = {
+	/* USB0 ENDP 1 */
+	[ 0] = { .submit = 32, .complete =  93},
+	[ 1] = { .submit = 34, .complete =  94},
+	[ 2] = { .submit = 36, .complete =  95},
+	[ 3] = { .submit = 38, .complete =  96},
+	[ 4] = { .submit = 40, .complete =  97},
+	[ 5] = { .submit = 42, .complete =  98},
+	[ 6] = { .submit = 44, .complete =  99},
+	[ 7] = { .submit = 46, .complete = 100},
+	[ 8] = { .submit = 48, .complete = 101},
+	[ 9] = { .submit = 50, .complete = 102},
+	[10] = { .submit = 52, .complete = 103},
+	[11] = { .submit = 54, .complete = 104},
+	[12] = { .submit = 56, .complete = 105},
+	[13] = { .submit = 58, .complete = 106},
+	[14] = { .submit = 60, .complete = 107},
+
+	/* USB1 ENDP1 */
+	[15] = { .submit = 62, .complete = 125},
+	[16] = { .submit = 64, .complete = 126},
+	[17] = { .submit = 66, .complete = 127},
+	[18] = { .submit = 68, .complete = 128},
+	[19] = { .submit = 70, .complete = 129},
+	[20] = { .submit = 72, .complete = 130},
+	[21] = { .submit = 74, .complete = 131},
+	[22] = { .submit = 76, .complete = 132},
+	[23] = { .submit = 78, .complete = 133},
+	[24] = { .submit = 80, .complete = 134},
+	[25] = { .submit = 82, .complete = 135},
+	[26] = { .submit = 84, .complete = 136},
+	[27] = { .submit = 86, .complete = 137},
+	[28] = { .submit = 88, .complete = 138},
+	[29] = { .submit = 90, .complete = 139},
+};
+
+static const struct chan_queues am335x_usb_queues_rx[] = {
+	/* USB0 ENDP 1 */
+	[ 0] = { .submit =  1, .complete = 109},
+	[ 1] = { .submit =  2, .complete = 110},
+	[ 2] = { .submit =  3, .complete = 111},
+	[ 3] = { .submit =  4, .complete = 112},
+	[ 4] = { .submit =  5, .complete = 113},
+	[ 5] = { .submit =  6, .complete = 114},
+	[ 6] = { .submit =  7, .complete = 115},
+	[ 7] = { .submit =  8, .complete = 116},
+	[ 8] = { .submit =  9, .complete = 117},
+	[ 9] = { .submit = 10, .complete = 118},
+	[10] = { .submit = 11, .complete = 119},
+	[11] = { .submit = 12, .complete = 120},
+	[12] = { .submit = 13, .complete = 121},
+	[13] = { .submit = 14, .complete = 122},
+	[14] = { .submit = 15, .complete = 123},
+
+	/* USB1 ENDP 1 */
+	[15] = { .submit = 16, .complete = 141},
+	[16] = { .submit = 17, .complete = 142},
+	[17] = { .submit = 18, .complete = 143},
+	[18] = { .submit = 19, .complete = 144},
+	[19] = { .submit = 20, .complete = 145},
+	[20] = { .submit = 21, .complete = 146},
+	[21] = { .submit = 22, .complete = 147},
+	[22] = { .submit = 23, .complete = 148},
+	[23] = { .submit = 24, .complete = 149},
+	[24] = { .submit = 25, .complete = 150},
+	[25] = { .submit = 26, .complete = 151},
+	[26] = { .submit = 27, .complete = 152},
+	[27] = { .submit = 28, .complete = 153},
+	[28] = { .submit = 29, .complete = 154},
+	[29] = { .submit = 30, .complete = 155},
+};
+
+static const struct chan_queues da8xx_usb_queues_tx[] = {
+	[0] = { .submit =  16, .complete = 24},
+	[1] = { .submit =  18, .complete = 24},
+	[2] = { .submit =  20, .complete = 24},
+	[3] = { .submit =  22, .complete = 24},
+};
+
+static const struct chan_queues da8xx_usb_queues_rx[] = {
+	[0] = { .submit =  1, .complete = 26},
+	[1] = { .submit =  3, .complete = 26},
+	[2] = { .submit =  5, .complete = 26},
+	[3] = { .submit =  7, .complete = 26},
+};
+
+struct cppi_glue_infos {
+	const struct chan_queues *queues_rx;
+	const struct chan_queues *queues_tx;
+	struct chan_queues td_queue;
+	u16 first_completion_queue;
+	u16 qmgr_num_pend;
+};
+
+static struct cppi41_channel *to_cpp41_chan(struct dma_chan *c)
+{
+	return container_of(c, struct cppi41_channel, chan);
+}
+
+static struct cppi41_channel *desc_to_chan(struct cppi41_dd *cdd, u32 desc)
+{
+	struct cppi41_channel *c;
+	u32 descs_size;
+	u32 desc_num;
+
+	descs_size = sizeof(struct cppi41_desc) * ALLOC_DECS_NUM;
+
+	if (!((desc >= cdd->descs_phys) &&
+			(desc < (cdd->descs_phys + descs_size)))) {
+		return NULL;
+	}
+
+	desc_num = (desc - cdd->descs_phys) / sizeof(struct cppi41_desc);
+	BUG_ON(desc_num >= ALLOC_DECS_NUM);
+	c = cdd->chan_busy[desc_num];
+	cdd->chan_busy[desc_num] = NULL;
+
+	/* Usecount for chan_busy[], paired with push_desc_queue() */
+	pm_runtime_put(cdd->ddev.dev);
+
+	return c;
+}
+
+static void cppi_writel(u32 val, void *__iomem *mem)
+{
+	__raw_writel(val, mem);
+}
+
+static u32 cppi_readl(void *__iomem *mem)
+{
+	return __raw_readl(mem);
+}
+
+static u32 pd_trans_len(u32 val)
+{
+	return val & ((1 << (DESC_LENGTH_BITS_NUM + 1)) - 1);
+}
+
+static u32 cppi41_pop_desc(struct cppi41_dd *cdd, unsigned queue_num)
+{
+	u32 desc;
+
+	desc = cppi_readl(cdd->qmgr_mem + QMGR_QUEUE_D(queue_num));
+	desc &= ~0x1f;
+	return desc;
+}
+
+static irqreturn_t cppi41_irq(int irq, void *data)
+{
+	struct cppi41_dd *cdd = data;
+	u16 first_completion_queue = cdd->first_completion_queue;
+	u16 qmgr_num_pend = cdd->qmgr_num_pend;
+	struct cppi41_channel *c;
+	int i;
+
+	for (i = QMGR_PENDING_SLOT_Q(first_completion_queue); i < qmgr_num_pend;
+			i++) {
+		u32 val;
+		u32 q_num;
+
+		val = cppi_readl(cdd->qmgr_mem + QMGR_PEND(i));
+		if (i == QMGR_PENDING_SLOT_Q(first_completion_queue) && val) {
+			u32 mask;
+			/* set corresponding bit for completetion Q 93 */
+			mask = 1 << QMGR_PENDING_BIT_Q(first_completion_queue);
+			/* not set all bits for queues less than Q 93 */
+			mask--;
+			/* now invert and keep only Q 93+ set */
+			val &= ~mask;
+		}
+
+		if (val)
+			__iormb();
+
+		while (val) {
+			u32 desc, len;
+
+			/*
+			 * This should never trigger, see the comments in
+			 * push_desc_queue()
+			 */
+			WARN_ON(cdd->is_suspended);
+
+			q_num = __fls(val);
+			val &= ~(1 << q_num);
+			q_num += 32 * i;
+			desc = cppi41_pop_desc(cdd, q_num);
+			c = desc_to_chan(cdd, desc);
+			if (WARN_ON(!c)) {
+				pr_err("%s() q %d desc %08x\n", __func__,
+						q_num, desc);
+				continue;
+			}
+
+			if (c->desc->pd2 & PD2_ZERO_LENGTH)
+				len = 0;
+			else
+				len = pd_trans_len(c->desc->pd0);
+
+			c->residue = pd_trans_len(c->desc->pd6) - len;
+			dma_cookie_complete(&c->txd);
+			dmaengine_desc_get_callback_invoke(&c->txd, NULL);
+		}
+	}
+	return IRQ_HANDLED;
+}
+
+static dma_cookie_t cppi41_tx_submit(struct dma_async_tx_descriptor *tx)
+{
+	dma_cookie_t cookie;
+
+	cookie = dma_cookie_assign(tx);
+
+	return cookie;
+}
+
+static int cppi41_dma_alloc_chan_resources(struct dma_chan *chan)
+{
+	struct cppi41_channel *c = to_cpp41_chan(chan);
+	struct cppi41_dd *cdd = c->cdd;
+	int error;
+
+	error = pm_runtime_get_sync(cdd->ddev.dev);
+	if (error < 0) {
+		dev_err(cdd->ddev.dev, "%s pm runtime get: %i\n",
+			__func__, error);
+		pm_runtime_put_noidle(cdd->ddev.dev);
+
+		return error;
+	}
+
+	dma_cookie_init(chan);
+	dma_async_tx_descriptor_init(&c->txd, chan);
+	c->txd.tx_submit = cppi41_tx_submit;
+
+	if (!c->is_tx)
+		cppi_writel(c->q_num, c->gcr_reg + RXHPCRA0);
+
+	pm_runtime_mark_last_busy(cdd->ddev.dev);
+	pm_runtime_put_autosuspend(cdd->ddev.dev);
+
+	return 0;
+}
+
+static void cppi41_dma_free_chan_resources(struct dma_chan *chan)
+{
+	struct cppi41_channel *c = to_cpp41_chan(chan);
+	struct cppi41_dd *cdd = c->cdd;
+	int error;
+
+	error = pm_runtime_get_sync(cdd->ddev.dev);
+	if (error < 0) {
+		pm_runtime_put_noidle(cdd->ddev.dev);
+
+		return;
+	}
+
+	WARN_ON(!list_empty(&cdd->pending));
+
+	pm_runtime_mark_last_busy(cdd->ddev.dev);
+	pm_runtime_put_autosuspend(cdd->ddev.dev);
+}
+
+static enum dma_status cppi41_dma_tx_status(struct dma_chan *chan,
+	dma_cookie_t cookie, struct dma_tx_state *txstate)
+{
+	struct cppi41_channel *c = to_cpp41_chan(chan);
+	enum dma_status ret;
+
+	ret = dma_cookie_status(chan, cookie, txstate);
+
+	dma_set_residue(txstate, c->residue);
+
+	return ret;
+}
+
+static void push_desc_queue(struct cppi41_channel *c)
+{
+	struct cppi41_dd *cdd = c->cdd;
+	u32 desc_num;
+	u32 desc_phys;
+	u32 reg;
+
+	c->residue = 0;
+
+	reg = GCR_CHAN_ENABLE;
+	if (!c->is_tx) {
+		reg |= GCR_STARV_RETRY;
+		reg |= GCR_DESC_TYPE_HOST;
+		reg |= c->q_comp_num;
+	}
+
+	cppi_writel(reg, c->gcr_reg);
+
+	/*
+	 * We don't use writel() but __raw_writel() so we have to make sure
+	 * that the DMA descriptor in coherent memory made to the main memory
+	 * before starting the dma engine.
+	 */
+	__iowmb();
+
+	/*
+	 * DMA transfers can take at least 200ms to complete with USB mass
+	 * storage connected. To prevent autosuspend timeouts, we must use
+	 * pm_runtime_get/put() when chan_busy[] is modified. This will get
+	 * cleared in desc_to_chan() or cppi41_stop_chan() depending on the
+	 * outcome of the transfer.
+	 */
+	pm_runtime_get(cdd->ddev.dev);
+
+	desc_phys = lower_32_bits(c->desc_phys);
+	desc_num = (desc_phys - cdd->descs_phys) / sizeof(struct cppi41_desc);
+	WARN_ON(cdd->chan_busy[desc_num]);
+	cdd->chan_busy[desc_num] = c;
+
+	reg = (sizeof(struct cppi41_desc) - 24) / 4;
+	reg |= desc_phys;
+	cppi_writel(reg, cdd->qmgr_mem + QMGR_QUEUE_D(c->q_num));
+}
+
+/*
+ * Caller must hold cdd->lock to prevent push_desc_queue()
+ * getting called out of order. We have both cppi41_dma_issue_pending()
+ * and cppi41_runtime_resume() call this function.
+ */
+static void cppi41_run_queue(struct cppi41_dd *cdd)
+{
+	struct cppi41_channel *c, *_c;
+
+	list_for_each_entry_safe(c, _c, &cdd->pending, node) {
+		push_desc_queue(c);
+		list_del(&c->node);
+	}
+}
+
+static void cppi41_dma_issue_pending(struct dma_chan *chan)
+{
+	struct cppi41_channel *c = to_cpp41_chan(chan);
+	struct cppi41_dd *cdd = c->cdd;
+	unsigned long flags;
+	int error;
+
+	error = pm_runtime_get(cdd->ddev.dev);
+	if ((error != -EINPROGRESS) && error < 0) {
+		pm_runtime_put_noidle(cdd->ddev.dev);
+		dev_err(cdd->ddev.dev, "Failed to pm_runtime_get: %i\n",
+			error);
+
+		return;
+	}
+
+	spin_lock_irqsave(&cdd->lock, flags);
+	list_add_tail(&c->node, &cdd->pending);
+	if (!cdd->is_suspended)
+		cppi41_run_queue(cdd);
+	spin_unlock_irqrestore(&cdd->lock, flags);
+
+	pm_runtime_mark_last_busy(cdd->ddev.dev);
+	pm_runtime_put_autosuspend(cdd->ddev.dev);
+}
+
+static u32 get_host_pd0(u32 length)
+{
+	u32 reg;
+
+	reg = DESC_TYPE_HOST << DESC_TYPE;
+	reg |= length;
+
+	return reg;
+}
+
+static u32 get_host_pd1(struct cppi41_channel *c)
+{
+	u32 reg;
+
+	reg = 0;
+
+	return reg;
+}
+
+static u32 get_host_pd2(struct cppi41_channel *c)
+{
+	u32 reg;
+
+	reg = DESC_TYPE_USB;
+	reg |= c->q_comp_num;
+
+	return reg;
+}
+
+static u32 get_host_pd3(u32 length)
+{
+	u32 reg;
+
+	/* PD3 = packet size */
+	reg = length;
+
+	return reg;
+}
+
+static u32 get_host_pd6(u32 length)
+{
+	u32 reg;
+
+	/* PD6 buffer size */
+	reg = DESC_PD_COMPLETE;
+	reg |= length;
+
+	return reg;
+}
+
+static u32 get_host_pd4_or_7(u32 addr)
+{
+	u32 reg;
+
+	reg = addr;
+
+	return reg;
+}
+
+static u32 get_host_pd5(void)
+{
+	u32 reg;
+
+	reg = 0;
+
+	return reg;
+}
+
+static struct dma_async_tx_descriptor *cppi41_dma_prep_slave_sg(
+	struct dma_chan *chan, struct scatterlist *sgl, unsigned sg_len,
+	enum dma_transfer_direction dir, unsigned long tx_flags, void *context)
+{
+	struct cppi41_channel *c = to_cpp41_chan(chan);
+	struct dma_async_tx_descriptor *txd = NULL;
+	struct cppi41_dd *cdd = c->cdd;
+	struct cppi41_desc *d;
+	struct scatterlist *sg;
+	unsigned int i;
+	int error;
+
+	error = pm_runtime_get(cdd->ddev.dev);
+	if (error < 0) {
+		pm_runtime_put_noidle(cdd->ddev.dev);
+
+		return NULL;
+	}
+
+	if (cdd->is_suspended)
+		goto err_out_not_ready;
+
+	d = c->desc;
+	for_each_sg(sgl, sg, sg_len, i) {
+		u32 addr;
+		u32 len;
+
+		/* We need to use more than one desc once musb supports sg */
+		addr = lower_32_bits(sg_dma_address(sg));
+		len = sg_dma_len(sg);
+
+		d->pd0 = get_host_pd0(len);
+		d->pd1 = get_host_pd1(c);
+		d->pd2 = get_host_pd2(c);
+		d->pd3 = get_host_pd3(len);
+		d->pd4 = get_host_pd4_or_7(addr);
+		d->pd5 = get_host_pd5();
+		d->pd6 = get_host_pd6(len);
+		d->pd7 = get_host_pd4_or_7(addr);
+
+		d++;
+	}
+
+	txd = &c->txd;
+
+err_out_not_ready:
+	pm_runtime_mark_last_busy(cdd->ddev.dev);
+	pm_runtime_put_autosuspend(cdd->ddev.dev);
+
+	return txd;
+}
+
+static void cppi41_compute_td_desc(struct cppi41_desc *d)
+{
+	d->pd0 = DESC_TYPE_TEARD << DESC_TYPE;
+}
+
+static int cppi41_tear_down_chan(struct cppi41_channel *c)
+{
+	struct dmaengine_result abort_result;
+	struct cppi41_dd *cdd = c->cdd;
+	struct cppi41_desc *td;
+	u32 reg;
+	u32 desc_phys;
+	u32 td_desc_phys;
+
+	td = cdd->cd;
+	td += cdd->first_td_desc;
+
+	td_desc_phys = cdd->descs_phys;
+	td_desc_phys += cdd->first_td_desc * sizeof(struct cppi41_desc);
+
+	if (!c->td_queued) {
+		cppi41_compute_td_desc(td);
+		__iowmb();
+
+		reg = (sizeof(struct cppi41_desc) - 24) / 4;
+		reg |= td_desc_phys;
+		cppi_writel(reg, cdd->qmgr_mem +
+				QMGR_QUEUE_D(cdd->td_queue.submit));
+
+		reg = GCR_CHAN_ENABLE;
+		if (!c->is_tx) {
+			reg |= GCR_STARV_RETRY;
+			reg |= GCR_DESC_TYPE_HOST;
+			reg |= cdd->td_queue.complete;
+		}
+		reg |= GCR_TEARDOWN;
+		cppi_writel(reg, c->gcr_reg);
+		c->td_queued = 1;
+		c->td_retry = 500;
+	}
+
+	if (!c->td_seen || !c->td_desc_seen) {
+
+		desc_phys = cppi41_pop_desc(cdd, cdd->td_queue.complete);
+		if (!desc_phys && c->is_tx)
+			desc_phys = cppi41_pop_desc(cdd, c->q_comp_num);
+
+		if (desc_phys == c->desc_phys) {
+			c->td_desc_seen = 1;
+
+		} else if (desc_phys == td_desc_phys) {
+			u32 pd0;
+
+			__iormb();
+			pd0 = td->pd0;
+			WARN_ON((pd0 >> DESC_TYPE) != DESC_TYPE_TEARD);
+			WARN_ON(!c->is_tx && !(pd0 & TD_DESC_IS_RX));
+			WARN_ON((pd0 & 0x1f) != c->port_num);
+			c->td_seen = 1;
+		} else if (desc_phys) {
+			WARN_ON_ONCE(1);
+		}
+	}
+	c->td_retry--;
+	/*
+	 * If the TX descriptor / channel is in use, the caller needs to poke
+	 * his TD bit multiple times. After that he hardware releases the
+	 * transfer descriptor followed by TD descriptor. Waiting seems not to
+	 * cause any difference.
+	 * RX seems to be thrown out right away. However once the TearDown
+	 * descriptor gets through we are done. If we have seens the transfer
+	 * descriptor before the TD we fetch it from enqueue, it has to be
+	 * there waiting for us.
+	 */
+	if (!c->td_seen && c->td_retry) {
+		udelay(1);
+		return -EAGAIN;
+	}
+	WARN_ON(!c->td_retry);
+
+	if (!c->td_desc_seen) {
+		desc_phys = cppi41_pop_desc(cdd, c->q_num);
+		if (!desc_phys)
+			desc_phys = cppi41_pop_desc(cdd, c->q_comp_num);
+		WARN_ON(!desc_phys);
+	}
+
+	c->td_queued = 0;
+	c->td_seen = 0;
+	c->td_desc_seen = 0;
+	cppi_writel(0, c->gcr_reg);
+
+	/* Invoke the callback to do the necessary clean-up */
+	abort_result.result = DMA_TRANS_ABORTED;
+	dma_cookie_complete(&c->txd);
+	dmaengine_desc_get_callback_invoke(&c->txd, &abort_result);
+
+	return 0;
+}
+
+static int cppi41_stop_chan(struct dma_chan *chan)
+{
+	struct cppi41_channel *c = to_cpp41_chan(chan);
+	struct cppi41_dd *cdd = c->cdd;
+	u32 desc_num;
+	u32 desc_phys;
+	int ret;
+
+	desc_phys = lower_32_bits(c->desc_phys);
+	desc_num = (desc_phys - cdd->descs_phys) / sizeof(struct cppi41_desc);
+	if (!cdd->chan_busy[desc_num]) {
+		struct cppi41_channel *cc, *_ct;
+
+		/*
+		 * channels might still be in the pendling list if
+		 * cppi41_dma_issue_pending() is called after
+		 * cppi41_runtime_suspend() is called
+		 */
+		list_for_each_entry_safe(cc, _ct, &cdd->pending, node) {
+			if (cc != c)
+				continue;
+			list_del(&cc->node);
+			break;
+		}
+		return 0;
+	}
+
+	ret = cppi41_tear_down_chan(c);
+	if (ret)
+		return ret;
+
+	WARN_ON(!cdd->chan_busy[desc_num]);
+	cdd->chan_busy[desc_num] = NULL;
+
+	/* Usecount for chan_busy[], paired with push_desc_queue() */
+	pm_runtime_put(cdd->ddev.dev);
+
+	return 0;
+}
+
+static int cppi41_add_chans(struct device *dev, struct cppi41_dd *cdd)
+{
+	struct cppi41_channel *cchan, *chans;
+	int i;
+	u32 n_chans = cdd->n_chans;
+
+	/*
+	 * The channels can only be used as TX or as RX. So we add twice
+	 * that much dma channels because USB can only do RX or TX.
+	 */
+	n_chans *= 2;
+
+	chans = devm_kcalloc(dev, n_chans, sizeof(*chans), GFP_KERNEL);
+	if (!chans)
+		return -ENOMEM;
+
+	for (i = 0; i < n_chans; i++) {
+		cchan = &chans[i];
+
+		cchan->cdd = cdd;
+		if (i & 1) {
+			cchan->gcr_reg = cdd->ctrl_mem + DMA_TXGCR(i >> 1);
+			cchan->is_tx = 1;
+		} else {
+			cchan->gcr_reg = cdd->ctrl_mem + DMA_RXGCR(i >> 1);
+			cchan->is_tx = 0;
+		}
+		cchan->port_num = i >> 1;
+		cchan->desc = &cdd->cd[i];
+		cchan->desc_phys = cdd->descs_phys;
+		cchan->desc_phys += i * sizeof(struct cppi41_desc);
+		cchan->chan.device = &cdd->ddev;
+		list_add_tail(&cchan->chan.device_node, &cdd->ddev.channels);
+	}
+	cdd->first_td_desc = n_chans;
+
+	return 0;
+}
+
+static void purge_descs(struct device *dev, struct cppi41_dd *cdd)
+{
+	unsigned int mem_decs;
+	int i;
+
+	mem_decs = ALLOC_DECS_NUM * sizeof(struct cppi41_desc);
+
+	for (i = 0; i < DESCS_AREAS; i++) {
+
+		cppi_writel(0, cdd->qmgr_mem + QMGR_MEMBASE(i));
+		cppi_writel(0, cdd->qmgr_mem + QMGR_MEMCTRL(i));
+
+		dma_free_coherent(dev, mem_decs, cdd->cd,
+				cdd->descs_phys);
+	}
+}
+
+static void disable_sched(struct cppi41_dd *cdd)
+{
+	cppi_writel(0, cdd->sched_mem + DMA_SCHED_CTRL);
+}
+
+static void deinit_cppi41(struct device *dev, struct cppi41_dd *cdd)
+{
+	disable_sched(cdd);
+
+	purge_descs(dev, cdd);
+
+	cppi_writel(0, cdd->qmgr_mem + QMGR_LRAM0_BASE);
+	cppi_writel(0, cdd->qmgr_mem + QMGR_LRAM0_BASE);
+	dma_free_coherent(dev, QMGR_SCRATCH_SIZE, cdd->qmgr_scratch,
+			cdd->scratch_phys);
+}
+
+static int init_descs(struct device *dev, struct cppi41_dd *cdd)
+{
+	unsigned int desc_size;
+	unsigned int mem_decs;
+	int i;
+	u32 reg;
+	u32 idx;
+
+	BUILD_BUG_ON(sizeof(struct cppi41_desc) &
+			(sizeof(struct cppi41_desc) - 1));
+	BUILD_BUG_ON(sizeof(struct cppi41_desc) < 32);
+	BUILD_BUG_ON(ALLOC_DECS_NUM < 32);
+
+	desc_size = sizeof(struct cppi41_desc);
+	mem_decs = ALLOC_DECS_NUM * desc_size;
+
+	idx = 0;
+	for (i = 0; i < DESCS_AREAS; i++) {
+
+		reg = idx << QMGR_MEMCTRL_IDX_SH;
+		reg |= (ilog2(desc_size) - 5) << QMGR_MEMCTRL_DESC_SH;
+		reg |= ilog2(ALLOC_DECS_NUM) - 5;
+
+		BUILD_BUG_ON(DESCS_AREAS != 1);
+		cdd->cd = dma_alloc_coherent(dev, mem_decs,
+				&cdd->descs_phys, GFP_KERNEL);
+		if (!cdd->cd)
+			return -ENOMEM;
+
+		cppi_writel(cdd->descs_phys, cdd->qmgr_mem + QMGR_MEMBASE(i));
+		cppi_writel(reg, cdd->qmgr_mem + QMGR_MEMCTRL(i));
+
+		idx += ALLOC_DECS_NUM;
+	}
+	return 0;
+}
+
+static void init_sched(struct cppi41_dd *cdd)
+{
+	unsigned ch;
+	unsigned word;
+	u32 reg;
+
+	word = 0;
+	cppi_writel(0, cdd->sched_mem + DMA_SCHED_CTRL);
+	for (ch = 0; ch < cdd->n_chans; ch += 2) {
+
+		reg = SCHED_ENTRY0_CHAN(ch);
+		reg |= SCHED_ENTRY1_CHAN(ch) | SCHED_ENTRY1_IS_RX;
+
+		reg |= SCHED_ENTRY2_CHAN(ch + 1);
+		reg |= SCHED_ENTRY3_CHAN(ch + 1) | SCHED_ENTRY3_IS_RX;
+		cppi_writel(reg, cdd->sched_mem + DMA_SCHED_WORD(word));
+		word++;
+	}
+	reg = cdd->n_chans * 2 - 1;
+	reg |= DMA_SCHED_CTRL_EN;
+	cppi_writel(reg, cdd->sched_mem + DMA_SCHED_CTRL);
+}
+
+static int init_cppi41(struct device *dev, struct cppi41_dd *cdd)
+{
+	int ret;
+
+	BUILD_BUG_ON(QMGR_SCRATCH_SIZE > ((1 << 14) - 1));
+	cdd->qmgr_scratch = dma_alloc_coherent(dev, QMGR_SCRATCH_SIZE,
+			&cdd->scratch_phys, GFP_KERNEL);
+	if (!cdd->qmgr_scratch)
+		return -ENOMEM;
+
+	cppi_writel(cdd->scratch_phys, cdd->qmgr_mem + QMGR_LRAM0_BASE);
+	cppi_writel(TOTAL_DESCS_NUM, cdd->qmgr_mem + QMGR_LRAM_SIZE);
+	cppi_writel(0, cdd->qmgr_mem + QMGR_LRAM1_BASE);
+
+	ret = init_descs(dev, cdd);
+	if (ret)
+		goto err_td;
+
+	cppi_writel(cdd->td_queue.submit, cdd->ctrl_mem + DMA_TDFDQ);
+	init_sched(cdd);
+
+	return 0;
+err_td:
+	deinit_cppi41(dev, cdd);
+	return ret;
+}
+
+static struct platform_driver cpp41_dma_driver;
+/*
+ * The param format is:
+ * X Y
+ * X: Port
+ * Y: 0 = RX else TX
+ */
+#define INFO_PORT	0
+#define INFO_IS_TX	1
+
+static bool cpp41_dma_filter_fn(struct dma_chan *chan, void *param)
+{
+	struct cppi41_channel *cchan;
+	struct cppi41_dd *cdd;
+	const struct chan_queues *queues;
+	u32 *num = param;
+
+	if (chan->device->dev->driver != &cpp41_dma_driver.driver)
+		return false;
+
+	cchan = to_cpp41_chan(chan);
+
+	if (cchan->port_num != num[INFO_PORT])
+		return false;
+
+	if (cchan->is_tx && !num[INFO_IS_TX])
+		return false;
+	cdd = cchan->cdd;
+	if (cchan->is_tx)
+		queues = cdd->queues_tx;
+	else
+		queues = cdd->queues_rx;
+
+	BUILD_BUG_ON(ARRAY_SIZE(am335x_usb_queues_rx) !=
+		     ARRAY_SIZE(am335x_usb_queues_tx));
+	if (WARN_ON(cchan->port_num >= ARRAY_SIZE(am335x_usb_queues_rx)))
+		return false;
+
+	cchan->q_num = queues[cchan->port_num].submit;
+	cchan->q_comp_num = queues[cchan->port_num].complete;
+	return true;
+}
+
+static struct of_dma_filter_info cpp41_dma_info = {
+	.filter_fn = cpp41_dma_filter_fn,
+};
+
+static struct dma_chan *cppi41_dma_xlate(struct of_phandle_args *dma_spec,
+		struct of_dma *ofdma)
+{
+	int count = dma_spec->args_count;
+	struct of_dma_filter_info *info = ofdma->of_dma_data;
+
+	if (!info || !info->filter_fn)
+		return NULL;
+
+	if (count != 2)
+		return NULL;
+
+	return dma_request_channel(info->dma_cap, info->filter_fn,
+			&dma_spec->args[0]);
+}
+
+static const struct cppi_glue_infos am335x_usb_infos = {
+	.queues_rx = am335x_usb_queues_rx,
+	.queues_tx = am335x_usb_queues_tx,
+	.td_queue = { .submit = 31, .complete = 0 },
+	.first_completion_queue = 93,
+	.qmgr_num_pend = 5,
+};
+
+static const struct cppi_glue_infos da8xx_usb_infos = {
+	.queues_rx = da8xx_usb_queues_rx,
+	.queues_tx = da8xx_usb_queues_tx,
+	.td_queue = { .submit = 31, .complete = 0 },
+	.first_completion_queue = 24,
+	.qmgr_num_pend = 2,
+};
+
+static const struct of_device_id cppi41_dma_ids[] = {
+	{ .compatible = "ti,am3359-cppi41", .data = &am335x_usb_infos},
+	{ .compatible = "ti,da830-cppi41", .data = &da8xx_usb_infos},
+	{},
+};
+MODULE_DEVICE_TABLE(of, cppi41_dma_ids);
+
+static const struct cppi_glue_infos *get_glue_info(struct device *dev)
+{
+	const struct of_device_id *of_id;
+
+	of_id = of_match_node(cppi41_dma_ids, dev->of_node);
+	if (!of_id)
+		return NULL;
+	return of_id->data;
+}
+
+#define CPPI41_DMA_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))
+
+static int cppi41_dma_probe(struct platform_device *pdev)
+{
+	struct cppi41_dd *cdd;
+	struct device *dev = &pdev->dev;
+	const struct cppi_glue_infos *glue_info;
+	struct resource *mem;
+	int index;
+	int irq;
+	int ret;
+
+	glue_info = get_glue_info(dev);
+	if (!glue_info)
+		return -EINVAL;
+
+	cdd = devm_kzalloc(&pdev->dev, sizeof(*cdd), GFP_KERNEL);
+	if (!cdd)
+		return -ENOMEM;
+
+	dma_cap_set(DMA_SLAVE, cdd->ddev.cap_mask);
+	cdd->ddev.device_alloc_chan_resources = cppi41_dma_alloc_chan_resources;
+	cdd->ddev.device_free_chan_resources = cppi41_dma_free_chan_resources;
+	cdd->ddev.device_tx_status = cppi41_dma_tx_status;
+	cdd->ddev.device_issue_pending = cppi41_dma_issue_pending;
+	cdd->ddev.device_prep_slave_sg = cppi41_dma_prep_slave_sg;
+	cdd->ddev.device_terminate_all = cppi41_stop_chan;
+	cdd->ddev.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
+	cdd->ddev.src_addr_widths = CPPI41_DMA_BUSWIDTHS;
+	cdd->ddev.dst_addr_widths = CPPI41_DMA_BUSWIDTHS;
+	cdd->ddev.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
+	cdd->ddev.dev = dev;
+	INIT_LIST_HEAD(&cdd->ddev.channels);
+	cpp41_dma_info.dma_cap = cdd->ddev.cap_mask;
+
+	index = of_property_match_string(dev->of_node,
+					 "reg-names", "controller");
+	if (index < 0)
+		return index;
+
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, index);
+	cdd->ctrl_mem = devm_ioremap_resource(dev, mem);
+	if (IS_ERR(cdd->ctrl_mem))
+		return PTR_ERR(cdd->ctrl_mem);
+
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, index + 1);
+	cdd->sched_mem = devm_ioremap_resource(dev, mem);
+	if (IS_ERR(cdd->sched_mem))
+		return PTR_ERR(cdd->sched_mem);
+
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, index + 2);
+	cdd->qmgr_mem = devm_ioremap_resource(dev, mem);
+	if (IS_ERR(cdd->qmgr_mem))
+		return PTR_ERR(cdd->qmgr_mem);
+
+	spin_lock_init(&cdd->lock);
+	INIT_LIST_HEAD(&cdd->pending);
+
+	platform_set_drvdata(pdev, cdd);
+
+	pm_runtime_enable(dev);
+	pm_runtime_set_autosuspend_delay(dev, 100);
+	pm_runtime_use_autosuspend(dev);
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0)
+		goto err_get_sync;
+
+	cdd->queues_rx = glue_info->queues_rx;
+	cdd->queues_tx = glue_info->queues_tx;
+	cdd->td_queue = glue_info->td_queue;
+	cdd->qmgr_num_pend = glue_info->qmgr_num_pend;
+	cdd->first_completion_queue = glue_info->first_completion_queue;
+
+	ret = of_property_read_u32(dev->of_node,
+				   "#dma-channels", &cdd->n_chans);
+	if (ret)
+		goto err_get_n_chans;
+
+	ret = init_cppi41(dev, cdd);
+	if (ret)
+		goto err_init_cppi;
+
+	ret = cppi41_add_chans(dev, cdd);
+	if (ret)
+		goto err_chans;
+
+	irq = irq_of_parse_and_map(dev->of_node, 0);
+	if (!irq) {
+		ret = -EINVAL;
+		goto err_chans;
+	}
+
+	ret = devm_request_irq(&pdev->dev, irq, cppi41_irq, IRQF_SHARED,
+			dev_name(dev), cdd);
+	if (ret)
+		goto err_chans;
+	cdd->irq = irq;
+
+	ret = dma_async_device_register(&cdd->ddev);
+	if (ret)
+		goto err_chans;
+
+	ret = of_dma_controller_register(dev->of_node,
+			cppi41_dma_xlate, &cpp41_dma_info);
+	if (ret)
+		goto err_of;
+
+	pm_runtime_mark_last_busy(dev);
+	pm_runtime_put_autosuspend(dev);
+
+	return 0;
+err_of:
+	dma_async_device_unregister(&cdd->ddev);
+err_chans:
+	deinit_cppi41(dev, cdd);
+err_init_cppi:
+	pm_runtime_dont_use_autosuspend(dev);
+err_get_n_chans:
+err_get_sync:
+	pm_runtime_put_sync(dev);
+	pm_runtime_disable(dev);
+	return ret;
+}
+
+static int cppi41_dma_remove(struct platform_device *pdev)
+{
+	struct cppi41_dd *cdd = platform_get_drvdata(pdev);
+	int error;
+
+	error = pm_runtime_get_sync(&pdev->dev);
+	if (error < 0)
+		dev_err(&pdev->dev, "%s could not pm_runtime_get: %i\n",
+			__func__, error);
+	of_dma_controller_free(pdev->dev.of_node);
+	dma_async_device_unregister(&cdd->ddev);
+
+	devm_free_irq(&pdev->dev, cdd->irq, cdd);
+	deinit_cppi41(&pdev->dev, cdd);
+	pm_runtime_dont_use_autosuspend(&pdev->dev);
+	pm_runtime_put_sync(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
+	return 0;
+}
+
+static int __maybe_unused cppi41_suspend(struct device *dev)
+{
+	struct cppi41_dd *cdd = dev_get_drvdata(dev);
+
+	cdd->dma_tdfdq = cppi_readl(cdd->ctrl_mem + DMA_TDFDQ);
+	disable_sched(cdd);
+
+	return 0;
+}
+
+static int __maybe_unused cppi41_resume(struct device *dev)
+{
+	struct cppi41_dd *cdd = dev_get_drvdata(dev);
+	struct cppi41_channel *c;
+	int i;
+
+	for (i = 0; i < DESCS_AREAS; i++)
+		cppi_writel(cdd->descs_phys, cdd->qmgr_mem + QMGR_MEMBASE(i));
+
+	list_for_each_entry(c, &cdd->ddev.channels, chan.device_node)
+		if (!c->is_tx)
+			cppi_writel(c->q_num, c->gcr_reg + RXHPCRA0);
+
+	init_sched(cdd);
+
+	cppi_writel(cdd->dma_tdfdq, cdd->ctrl_mem + DMA_TDFDQ);
+	cppi_writel(cdd->scratch_phys, cdd->qmgr_mem + QMGR_LRAM0_BASE);
+	cppi_writel(QMGR_SCRATCH_SIZE, cdd->qmgr_mem + QMGR_LRAM_SIZE);
+	cppi_writel(0, cdd->qmgr_mem + QMGR_LRAM1_BASE);
+
+	return 0;
+}
+
+static int __maybe_unused cppi41_runtime_suspend(struct device *dev)
+{
+	struct cppi41_dd *cdd = dev_get_drvdata(dev);
+	unsigned long flags;
+
+	spin_lock_irqsave(&cdd->lock, flags);
+	cdd->is_suspended = true;
+	WARN_ON(!list_empty(&cdd->pending));
+	spin_unlock_irqrestore(&cdd->lock, flags);
+
+	return 0;
+}
+
+static int __maybe_unused cppi41_runtime_resume(struct device *dev)
+{
+	struct cppi41_dd *cdd = dev_get_drvdata(dev);
+	unsigned long flags;
+
+	spin_lock_irqsave(&cdd->lock, flags);
+	cdd->is_suspended = false;
+	cppi41_run_queue(cdd);
+	spin_unlock_irqrestore(&cdd->lock, flags);
+
+	return 0;
+}
+
+static const struct dev_pm_ops cppi41_pm_ops = {
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(cppi41_suspend, cppi41_resume)
+	SET_RUNTIME_PM_OPS(cppi41_runtime_suspend,
+			   cppi41_runtime_resume,
+			   NULL)
+};
+
+static struct platform_driver cpp41_dma_driver = {
+	.probe  = cppi41_dma_probe,
+	.remove = cppi41_dma_remove,
+	.driver = {
+		.name = "cppi41-dma-engine",
+		.pm = &cppi41_pm_ops,
+		.of_match_table = of_match_ptr(cppi41_dma_ids),
+	},
+};
+
+module_platform_driver(cpp41_dma_driver);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Sebastian Andrzej Siewior <bigeasy@linutronix.de>");
diff --git a/drivers/dma/ti/dma-crossbar.c b/drivers/dma/ti/dma-crossbar.c
new file mode 100644
index 000000000..86ced7f2d
--- /dev/null
+++ b/drivers/dma/ti/dma-crossbar.c
@@ -0,0 +1,477 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  Copyright (C) 2015 Texas Instruments Incorporated - http://www.ti.com
+ *  Author: Peter Ujfalusi <peter.ujfalusi@ti.com>
+ */
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/io.h>
+#include <linux/of_address.h>
+#include <linux/of_device.h>
+#include <linux/of_dma.h>
+
+#define TI_XBAR_DRA7		0
+#define TI_XBAR_AM335X		1
+static const u32 ti_xbar_type[] = {
+	[TI_XBAR_DRA7] = TI_XBAR_DRA7,
+	[TI_XBAR_AM335X] = TI_XBAR_AM335X,
+};
+
+static const struct of_device_id ti_dma_xbar_match[] = {
+	{
+		.compatible = "ti,dra7-dma-crossbar",
+		.data = &ti_xbar_type[TI_XBAR_DRA7],
+	},
+	{
+		.compatible = "ti,am335x-edma-crossbar",
+		.data = &ti_xbar_type[TI_XBAR_AM335X],
+	},
+	{},
+};
+
+/* Crossbar on AM335x/AM437x family */
+#define TI_AM335X_XBAR_LINES	64
+
+struct ti_am335x_xbar_data {
+	void __iomem *iomem;
+
+	struct dma_router dmarouter;
+
+	u32 xbar_events; /* maximum number of events to select in xbar */
+	u32 dma_requests; /* number of DMA requests on eDMA */
+};
+
+struct ti_am335x_xbar_map {
+	u16 dma_line;
+	u8 mux_val;
+};
+
+static inline void ti_am335x_xbar_write(void __iomem *iomem, int event, u8 val)
+{
+	/*
+	 * TPCC_EVT_MUX_60_63 register layout is different than the
+	 * rest, in the sense, that event 63 is mapped to lowest byte
+	 * and event 60 is mapped to highest, handle it separately.
+	 */
+	if (event >= 60 && event <= 63)
+		writeb_relaxed(val, iomem + (63 - event % 4));
+	else
+		writeb_relaxed(val, iomem + event);
+}
+
+static void ti_am335x_xbar_free(struct device *dev, void *route_data)
+{
+	struct ti_am335x_xbar_data *xbar = dev_get_drvdata(dev);
+	struct ti_am335x_xbar_map *map = route_data;
+
+	dev_dbg(dev, "Unmapping XBAR event %u on channel %u\n",
+		map->mux_val, map->dma_line);
+
+	ti_am335x_xbar_write(xbar->iomem, map->dma_line, 0);
+	kfree(map);
+}
+
+static void *ti_am335x_xbar_route_allocate(struct of_phandle_args *dma_spec,
+					   struct of_dma *ofdma)
+{
+	struct platform_device *pdev = of_find_device_by_node(ofdma->of_node);
+	struct ti_am335x_xbar_data *xbar = platform_get_drvdata(pdev);
+	struct ti_am335x_xbar_map *map;
+
+	if (dma_spec->args_count != 3)
+		return ERR_PTR(-EINVAL);
+
+	if (dma_spec->args[2] >= xbar->xbar_events) {
+		dev_err(&pdev->dev, "Invalid XBAR event number: %d\n",
+			dma_spec->args[2]);
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (dma_spec->args[0] >= xbar->dma_requests) {
+		dev_err(&pdev->dev, "Invalid DMA request line number: %d\n",
+			dma_spec->args[0]);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/* The of_node_put() will be done in the core for the node */
+	dma_spec->np = of_parse_phandle(ofdma->of_node, "dma-masters", 0);
+	if (!dma_spec->np) {
+		dev_err(&pdev->dev, "Can't get DMA master\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	map = kzalloc(sizeof(*map), GFP_KERNEL);
+	if (!map) {
+		of_node_put(dma_spec->np);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	map->dma_line = (u16)dma_spec->args[0];
+	map->mux_val = (u8)dma_spec->args[2];
+
+	dma_spec->args[2] = 0;
+	dma_spec->args_count = 2;
+
+	dev_dbg(&pdev->dev, "Mapping XBAR event%u to DMA%u\n",
+		map->mux_val, map->dma_line);
+
+	ti_am335x_xbar_write(xbar->iomem, map->dma_line, map->mux_val);
+
+	return map;
+}
+
+static const struct of_device_id ti_am335x_master_match[] = {
+	{ .compatible = "ti,edma3-tpcc", },
+	{},
+};
+
+static int ti_am335x_xbar_probe(struct platform_device *pdev)
+{
+	struct device_node *node = pdev->dev.of_node;
+	const struct of_device_id *match;
+	struct device_node *dma_node;
+	struct ti_am335x_xbar_data *xbar;
+	void __iomem *iomem;
+	int i, ret;
+
+	if (!node)
+		return -ENODEV;
+
+	xbar = devm_kzalloc(&pdev->dev, sizeof(*xbar), GFP_KERNEL);
+	if (!xbar)
+		return -ENOMEM;
+
+	dma_node = of_parse_phandle(node, "dma-masters", 0);
+	if (!dma_node) {
+		dev_err(&pdev->dev, "Can't get DMA master node\n");
+		return -ENODEV;
+	}
+
+	match = of_match_node(ti_am335x_master_match, dma_node);
+	if (!match) {
+		dev_err(&pdev->dev, "DMA master is not supported\n");
+		of_node_put(dma_node);
+		return -EINVAL;
+	}
+
+	if (of_property_read_u32(dma_node, "dma-requests",
+				 &xbar->dma_requests)) {
+		dev_info(&pdev->dev,
+			 "Missing XBAR output information, using %u.\n",
+			 TI_AM335X_XBAR_LINES);
+		xbar->dma_requests = TI_AM335X_XBAR_LINES;
+	}
+	of_node_put(dma_node);
+
+	if (of_property_read_u32(node, "dma-requests", &xbar->xbar_events)) {
+		dev_info(&pdev->dev,
+			 "Missing XBAR input information, using %u.\n",
+			 TI_AM335X_XBAR_LINES);
+		xbar->xbar_events = TI_AM335X_XBAR_LINES;
+	}
+
+	iomem = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(iomem))
+		return PTR_ERR(iomem);
+
+	xbar->iomem = iomem;
+
+	xbar->dmarouter.dev = &pdev->dev;
+	xbar->dmarouter.route_free = ti_am335x_xbar_free;
+
+	platform_set_drvdata(pdev, xbar);
+
+	/* Reset the crossbar */
+	for (i = 0; i < xbar->dma_requests; i++)
+		ti_am335x_xbar_write(xbar->iomem, i, 0);
+
+	ret = of_dma_router_register(node, ti_am335x_xbar_route_allocate,
+				     &xbar->dmarouter);
+
+	return ret;
+}
+
+/* Crossbar on DRA7xx family */
+#define TI_DRA7_XBAR_OUTPUTS	127
+#define TI_DRA7_XBAR_INPUTS	256
+
+struct ti_dra7_xbar_data {
+	void __iomem *iomem;
+
+	struct dma_router dmarouter;
+	struct mutex mutex;
+	unsigned long *dma_inuse;
+
+	u16 safe_val; /* Value to rest the crossbar lines */
+	u32 xbar_requests; /* number of DMA requests connected to XBAR */
+	u32 dma_requests; /* number of DMA requests forwarded to DMA */
+	u32 dma_offset;
+};
+
+struct ti_dra7_xbar_map {
+	u16 xbar_in;
+	int xbar_out;
+};
+
+static inline void ti_dra7_xbar_write(void __iomem *iomem, int xbar, u16 val)
+{
+	writew_relaxed(val, iomem + (xbar * 2));
+}
+
+static void ti_dra7_xbar_free(struct device *dev, void *route_data)
+{
+	struct ti_dra7_xbar_data *xbar = dev_get_drvdata(dev);
+	struct ti_dra7_xbar_map *map = route_data;
+
+	dev_dbg(dev, "Unmapping XBAR%u (was routed to %d)\n",
+		map->xbar_in, map->xbar_out);
+
+	ti_dra7_xbar_write(xbar->iomem, map->xbar_out, xbar->safe_val);
+	mutex_lock(&xbar->mutex);
+	clear_bit(map->xbar_out, xbar->dma_inuse);
+	mutex_unlock(&xbar->mutex);
+	kfree(map);
+}
+
+static void *ti_dra7_xbar_route_allocate(struct of_phandle_args *dma_spec,
+					 struct of_dma *ofdma)
+{
+	struct platform_device *pdev = of_find_device_by_node(ofdma->of_node);
+	struct ti_dra7_xbar_data *xbar = platform_get_drvdata(pdev);
+	struct ti_dra7_xbar_map *map;
+
+	if (dma_spec->args[0] >= xbar->xbar_requests) {
+		dev_err(&pdev->dev, "Invalid XBAR request number: %d\n",
+			dma_spec->args[0]);
+		put_device(&pdev->dev);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/* The of_node_put() will be done in the core for the node */
+	dma_spec->np = of_parse_phandle(ofdma->of_node, "dma-masters", 0);
+	if (!dma_spec->np) {
+		dev_err(&pdev->dev, "Can't get DMA master\n");
+		put_device(&pdev->dev);
+		return ERR_PTR(-EINVAL);
+	}
+
+	map = kzalloc(sizeof(*map), GFP_KERNEL);
+	if (!map) {
+		of_node_put(dma_spec->np);
+		put_device(&pdev->dev);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	mutex_lock(&xbar->mutex);
+	map->xbar_out = find_first_zero_bit(xbar->dma_inuse,
+					    xbar->dma_requests);
+	if (map->xbar_out == xbar->dma_requests) {
+		mutex_unlock(&xbar->mutex);
+		dev_err(&pdev->dev, "Run out of free DMA requests\n");
+		kfree(map);
+		of_node_put(dma_spec->np);
+		put_device(&pdev->dev);
+		return ERR_PTR(-ENOMEM);
+	}
+	set_bit(map->xbar_out, xbar->dma_inuse);
+	mutex_unlock(&xbar->mutex);
+
+	map->xbar_in = (u16)dma_spec->args[0];
+
+	dma_spec->args[0] = map->xbar_out + xbar->dma_offset;
+
+	dev_dbg(&pdev->dev, "Mapping XBAR%u to DMA%d\n",
+		map->xbar_in, map->xbar_out);
+
+	ti_dra7_xbar_write(xbar->iomem, map->xbar_out, map->xbar_in);
+
+	return map;
+}
+
+#define TI_XBAR_EDMA_OFFSET	0
+#define TI_XBAR_SDMA_OFFSET	1
+static const u32 ti_dma_offset[] = {
+	[TI_XBAR_EDMA_OFFSET] = 0,
+	[TI_XBAR_SDMA_OFFSET] = 1,
+};
+
+static const struct of_device_id ti_dra7_master_match[] = {
+	{
+		.compatible = "ti,omap4430-sdma",
+		.data = &ti_dma_offset[TI_XBAR_SDMA_OFFSET],
+	},
+	{
+		.compatible = "ti,edma3",
+		.data = &ti_dma_offset[TI_XBAR_EDMA_OFFSET],
+	},
+	{
+		.compatible = "ti,edma3-tpcc",
+		.data = &ti_dma_offset[TI_XBAR_EDMA_OFFSET],
+	},
+	{},
+};
+
+static inline void ti_dra7_xbar_reserve(int offset, int len, unsigned long *p)
+{
+	for (; len > 0; len--)
+		set_bit(offset + (len - 1), p);
+}
+
+static int ti_dra7_xbar_probe(struct platform_device *pdev)
+{
+	struct device_node *node = pdev->dev.of_node;
+	const struct of_device_id *match;
+	struct device_node *dma_node;
+	struct ti_dra7_xbar_data *xbar;
+	struct property *prop;
+	u32 safe_val;
+	int sz;
+	void __iomem *iomem;
+	int i, ret;
+
+	if (!node)
+		return -ENODEV;
+
+	xbar = devm_kzalloc(&pdev->dev, sizeof(*xbar), GFP_KERNEL);
+	if (!xbar)
+		return -ENOMEM;
+
+	dma_node = of_parse_phandle(node, "dma-masters", 0);
+	if (!dma_node) {
+		dev_err(&pdev->dev, "Can't get DMA master node\n");
+		return -ENODEV;
+	}
+
+	match = of_match_node(ti_dra7_master_match, dma_node);
+	if (!match) {
+		dev_err(&pdev->dev, "DMA master is not supported\n");
+		of_node_put(dma_node);
+		return -EINVAL;
+	}
+
+	if (of_property_read_u32(dma_node, "dma-requests",
+				 &xbar->dma_requests)) {
+		dev_info(&pdev->dev,
+			 "Missing XBAR output information, using %u.\n",
+			 TI_DRA7_XBAR_OUTPUTS);
+		xbar->dma_requests = TI_DRA7_XBAR_OUTPUTS;
+	}
+	of_node_put(dma_node);
+
+	xbar->dma_inuse = devm_kcalloc(&pdev->dev,
+				       BITS_TO_LONGS(xbar->dma_requests),
+				       sizeof(unsigned long), GFP_KERNEL);
+	if (!xbar->dma_inuse)
+		return -ENOMEM;
+
+	if (of_property_read_u32(node, "dma-requests", &xbar->xbar_requests)) {
+		dev_info(&pdev->dev,
+			 "Missing XBAR input information, using %u.\n",
+			 TI_DRA7_XBAR_INPUTS);
+		xbar->xbar_requests = TI_DRA7_XBAR_INPUTS;
+	}
+
+	if (!of_property_read_u32(node, "ti,dma-safe-map", &safe_val))
+		xbar->safe_val = (u16)safe_val;
+
+
+	prop = of_find_property(node, "ti,reserved-dma-request-ranges", &sz);
+	if (prop) {
+		const char pname[] = "ti,reserved-dma-request-ranges";
+		u32 (*rsv_events)[2];
+		size_t nelm = sz / sizeof(*rsv_events);
+		int i;
+
+		if (!nelm)
+			return -EINVAL;
+
+		rsv_events = kcalloc(nelm, sizeof(*rsv_events), GFP_KERNEL);
+		if (!rsv_events)
+			return -ENOMEM;
+
+		ret = of_property_read_u32_array(node, pname, (u32 *)rsv_events,
+						 nelm * 2);
+		if (ret) {
+			kfree(rsv_events);
+			return ret;
+		}
+
+		for (i = 0; i < nelm; i++) {
+			ti_dra7_xbar_reserve(rsv_events[i][0], rsv_events[i][1],
+					     xbar->dma_inuse);
+		}
+		kfree(rsv_events);
+	}
+
+	iomem = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(iomem))
+		return PTR_ERR(iomem);
+
+	xbar->iomem = iomem;
+
+	xbar->dmarouter.dev = &pdev->dev;
+	xbar->dmarouter.route_free = ti_dra7_xbar_free;
+	xbar->dma_offset = *(u32 *)match->data;
+
+	mutex_init(&xbar->mutex);
+	platform_set_drvdata(pdev, xbar);
+
+	/* Reset the crossbar */
+	for (i = 0; i < xbar->dma_requests; i++) {
+		if (!test_bit(i, xbar->dma_inuse))
+			ti_dra7_xbar_write(xbar->iomem, i, xbar->safe_val);
+	}
+
+	ret = of_dma_router_register(node, ti_dra7_xbar_route_allocate,
+				     &xbar->dmarouter);
+	if (ret) {
+		/* Restore the defaults for the crossbar */
+		for (i = 0; i < xbar->dma_requests; i++) {
+			if (!test_bit(i, xbar->dma_inuse))
+				ti_dra7_xbar_write(xbar->iomem, i, i);
+		}
+	}
+
+	return ret;
+}
+
+static int ti_dma_xbar_probe(struct platform_device *pdev)
+{
+	const struct of_device_id *match;
+	int ret;
+
+	match = of_match_node(ti_dma_xbar_match, pdev->dev.of_node);
+	if (unlikely(!match))
+		return -EINVAL;
+
+	switch (*(u32 *)match->data) {
+	case TI_XBAR_DRA7:
+		ret = ti_dra7_xbar_probe(pdev);
+		break;
+	case TI_XBAR_AM335X:
+		ret = ti_am335x_xbar_probe(pdev);
+		break;
+	default:
+		dev_err(&pdev->dev, "Unsupported crossbar\n");
+		ret = -ENODEV;
+		break;
+	}
+
+	return ret;
+}
+
+static struct platform_driver ti_dma_xbar_driver = {
+	.driver = {
+		.name = "ti-dma-crossbar",
+		.of_match_table = of_match_ptr(ti_dma_xbar_match),
+	},
+	.probe	= ti_dma_xbar_probe,
+};
+
+static int omap_dmaxbar_init(void)
+{
+	return platform_driver_register(&ti_dma_xbar_driver);
+}
+arch_initcall(omap_dmaxbar_init);
diff --git a/drivers/dma/ti/edma.c b/drivers/dma/ti/edma.c
new file mode 100644
index 000000000..a1adc8d91
--- /dev/null
+++ b/drivers/dma/ti/edma.c
@@ -0,0 +1,2748 @@
+/*
+ * TI EDMA DMA engine driver
+ *
+ * Copyright 2012 Texas Instruments
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/bitmap.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/list.h>
+#include <linux/module.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_irq.h>
+#include <linux/of_address.h>
+#include <linux/of_device.h>
+#include <linux/pm_runtime.h>
+
+#include <linux/platform_data/edma.h>
+
+#include "../dmaengine.h"
+#include "../virt-dma.h"
+
+/* Offsets matching "struct edmacc_param" */
+#define PARM_OPT		0x00
+#define PARM_SRC		0x04
+#define PARM_A_B_CNT		0x08
+#define PARM_DST		0x0c
+#define PARM_SRC_DST_BIDX	0x10
+#define PARM_LINK_BCNTRLD	0x14
+#define PARM_SRC_DST_CIDX	0x18
+#define PARM_CCNT		0x1c
+
+#define PARM_SIZE		0x20
+
+/* Offsets for EDMA CC global channel registers and their shadows */
+#define SH_ER			0x00	/* 64 bits */
+#define SH_ECR			0x08	/* 64 bits */
+#define SH_ESR			0x10	/* 64 bits */
+#define SH_CER			0x18	/* 64 bits */
+#define SH_EER			0x20	/* 64 bits */
+#define SH_EECR			0x28	/* 64 bits */
+#define SH_EESR			0x30	/* 64 bits */
+#define SH_SER			0x38	/* 64 bits */
+#define SH_SECR			0x40	/* 64 bits */
+#define SH_IER			0x50	/* 64 bits */
+#define SH_IECR			0x58	/* 64 bits */
+#define SH_IESR			0x60	/* 64 bits */
+#define SH_IPR			0x68	/* 64 bits */
+#define SH_ICR			0x70	/* 64 bits */
+#define SH_IEVAL		0x78
+#define SH_QER			0x80
+#define SH_QEER			0x84
+#define SH_QEECR		0x88
+#define SH_QEESR		0x8c
+#define SH_QSER			0x90
+#define SH_QSECR		0x94
+#define SH_SIZE			0x200
+
+/* Offsets for EDMA CC global registers */
+#define EDMA_REV		0x0000
+#define EDMA_CCCFG		0x0004
+#define EDMA_QCHMAP		0x0200	/* 8 registers */
+#define EDMA_DMAQNUM		0x0240	/* 8 registers (4 on OMAP-L1xx) */
+#define EDMA_QDMAQNUM		0x0260
+#define EDMA_QUETCMAP		0x0280
+#define EDMA_QUEPRI		0x0284
+#define EDMA_EMR		0x0300	/* 64 bits */
+#define EDMA_EMCR		0x0308	/* 64 bits */
+#define EDMA_QEMR		0x0310
+#define EDMA_QEMCR		0x0314
+#define EDMA_CCERR		0x0318
+#define EDMA_CCERRCLR		0x031c
+#define EDMA_EEVAL		0x0320
+#define EDMA_DRAE		0x0340	/* 4 x 64 bits*/
+#define EDMA_QRAE		0x0380	/* 4 registers */
+#define EDMA_QUEEVTENTRY	0x0400	/* 2 x 16 registers */
+#define EDMA_QSTAT		0x0600	/* 2 registers */
+#define EDMA_QWMTHRA		0x0620
+#define EDMA_QWMTHRB		0x0624
+#define EDMA_CCSTAT		0x0640
+
+#define EDMA_M			0x1000	/* global channel registers */
+#define EDMA_ECR		0x1008
+#define EDMA_ECRH		0x100C
+#define EDMA_SHADOW0		0x2000	/* 4 shadow regions */
+#define EDMA_PARM		0x4000	/* PaRAM entries */
+
+#define PARM_OFFSET(param_no)	(EDMA_PARM + ((param_no) << 5))
+
+#define EDMA_DCHMAP		0x0100  /* 64 registers */
+
+/* CCCFG register */
+#define GET_NUM_DMACH(x)	(x & 0x7) /* bits 0-2 */
+#define GET_NUM_QDMACH(x)	((x & 0x70) >> 4) /* bits 4-6 */
+#define GET_NUM_PAENTRY(x)	((x & 0x7000) >> 12) /* bits 12-14 */
+#define GET_NUM_EVQUE(x)	((x & 0x70000) >> 16) /* bits 16-18 */
+#define GET_NUM_REGN(x)		((x & 0x300000) >> 20) /* bits 20-21 */
+#define CHMAP_EXIST		BIT(24)
+
+/* CCSTAT register */
+#define EDMA_CCSTAT_ACTV	BIT(4)
+
+/*
+ * Max of 20 segments per channel to conserve PaRAM slots
+ * Also note that MAX_NR_SG should be atleast the no.of periods
+ * that are required for ASoC, otherwise DMA prep calls will
+ * fail. Today davinci-pcm is the only user of this driver and
+ * requires atleast 17 slots, so we setup the default to 20.
+ */
+#define MAX_NR_SG		20
+#define EDMA_MAX_SLOTS		MAX_NR_SG
+#define EDMA_DESCRIPTORS	16
+
+#define EDMA_CHANNEL_ANY		-1	/* for edma_alloc_channel() */
+#define EDMA_SLOT_ANY			-1	/* for edma_alloc_slot() */
+#define EDMA_CONT_PARAMS_ANY		 1001
+#define EDMA_CONT_PARAMS_FIXED_EXACT	 1002
+#define EDMA_CONT_PARAMS_FIXED_NOT_EXACT 1003
+
+/*
+ * 64bit array registers are split into two 32bit registers:
+ * reg0: channel/event 0-31
+ * reg1: channel/event 32-63
+ *
+ * bit 5 in the channel number tells the array index (0/1)
+ * bit 0-4 (0x1f) is the bit offset within the register
+ */
+#define EDMA_REG_ARRAY_INDEX(channel)	((channel) >> 5)
+#define EDMA_CHANNEL_BIT(channel)	(BIT((channel) & 0x1f))
+
+/* PaRAM slots are laid out like this */
+struct edmacc_param {
+	u32 opt;
+	u32 src;
+	u32 a_b_cnt;
+	u32 dst;
+	u32 src_dst_bidx;
+	u32 link_bcntrld;
+	u32 src_dst_cidx;
+	u32 ccnt;
+} __packed;
+
+/* fields in edmacc_param.opt */
+#define SAM		BIT(0)
+#define DAM		BIT(1)
+#define SYNCDIM		BIT(2)
+#define STATIC		BIT(3)
+#define EDMA_FWID	(0x07 << 8)
+#define TCCMODE		BIT(11)
+#define EDMA_TCC(t)	((t) << 12)
+#define TCINTEN		BIT(20)
+#define ITCINTEN	BIT(21)
+#define TCCHEN		BIT(22)
+#define ITCCHEN		BIT(23)
+
+struct edma_pset {
+	u32				len;
+	dma_addr_t			addr;
+	struct edmacc_param		param;
+};
+
+struct edma_desc {
+	struct virt_dma_desc		vdesc;
+	struct list_head		node;
+	enum dma_transfer_direction	direction;
+	int				cyclic;
+	bool				polled;
+	int				absync;
+	int				pset_nr;
+	struct edma_chan		*echan;
+	int				processed;
+
+	/*
+	 * The following 4 elements are used for residue accounting.
+	 *
+	 * - processed_stat: the number of SG elements we have traversed
+	 * so far to cover accounting. This is updated directly to processed
+	 * during edma_callback and is always <= processed, because processed
+	 * refers to the number of pending transfer (programmed to EDMA
+	 * controller), where as processed_stat tracks number of transfers
+	 * accounted for so far.
+	 *
+	 * - residue: The amount of bytes we have left to transfer for this desc
+	 *
+	 * - residue_stat: The residue in bytes of data we have covered
+	 * so far for accounting. This is updated directly to residue
+	 * during callbacks to keep it current.
+	 *
+	 * - sg_len: Tracks the length of the current intermediate transfer,
+	 * this is required to update the residue during intermediate transfer
+	 * completion callback.
+	 */
+	int				processed_stat;
+	u32				sg_len;
+	u32				residue;
+	u32				residue_stat;
+
+	struct edma_pset		pset[];
+};
+
+struct edma_cc;
+
+struct edma_tc {
+	struct device_node		*node;
+	u16				id;
+};
+
+struct edma_chan {
+	struct virt_dma_chan		vchan;
+	struct list_head		node;
+	struct edma_desc		*edesc;
+	struct edma_cc			*ecc;
+	struct edma_tc			*tc;
+	int				ch_num;
+	bool				alloced;
+	bool				hw_triggered;
+	int				slot[EDMA_MAX_SLOTS];
+	int				missed;
+	struct dma_slave_config		cfg;
+};
+
+struct edma_cc {
+	struct device			*dev;
+	struct edma_soc_info		*info;
+	void __iomem			*base;
+	int				id;
+	bool				legacy_mode;
+
+	/* eDMA3 resource information */
+	unsigned			num_channels;
+	unsigned			num_qchannels;
+	unsigned			num_region;
+	unsigned			num_slots;
+	unsigned			num_tc;
+	bool				chmap_exist;
+	enum dma_event_q		default_queue;
+
+	unsigned int			ccint;
+	unsigned int			ccerrint;
+
+	/*
+	 * The slot_inuse bit for each PaRAM slot is clear unless the slot is
+	 * in use by Linux or if it is allocated to be used by DSP.
+	 */
+	unsigned long *slot_inuse;
+
+	/*
+	 * For tracking reserved channels used by DSP.
+	 * If the bit is cleared, the channel is allocated to be used by DSP
+	 * and Linux must not touch it.
+	 */
+	unsigned long *channels_mask;
+
+	struct dma_device		dma_slave;
+	struct dma_device		*dma_memcpy;
+	struct edma_chan		*slave_chans;
+	struct edma_tc			*tc_list;
+	int				dummy_slot;
+};
+
+/* dummy param set used to (re)initialize parameter RAM slots */
+static const struct edmacc_param dummy_paramset = {
+	.link_bcntrld = 0xffff,
+	.ccnt = 1,
+};
+
+#define EDMA_BINDING_LEGACY	0
+#define EDMA_BINDING_TPCC	1
+static const u32 edma_binding_type[] = {
+	[EDMA_BINDING_LEGACY] = EDMA_BINDING_LEGACY,
+	[EDMA_BINDING_TPCC] = EDMA_BINDING_TPCC,
+};
+
+static const struct of_device_id edma_of_ids[] = {
+	{
+		.compatible = "ti,edma3",
+		.data = &edma_binding_type[EDMA_BINDING_LEGACY],
+	},
+	{
+		.compatible = "ti,edma3-tpcc",
+		.data = &edma_binding_type[EDMA_BINDING_TPCC],
+	},
+	{}
+};
+MODULE_DEVICE_TABLE(of, edma_of_ids);
+
+static const struct of_device_id edma_tptc_of_ids[] = {
+	{ .compatible = "ti,edma3-tptc", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, edma_tptc_of_ids);
+
+static inline unsigned int edma_read(struct edma_cc *ecc, int offset)
+{
+	return (unsigned int)__raw_readl(ecc->base + offset);
+}
+
+static inline void edma_write(struct edma_cc *ecc, int offset, int val)
+{
+	__raw_writel(val, ecc->base + offset);
+}
+
+static inline void edma_modify(struct edma_cc *ecc, int offset, unsigned and,
+			       unsigned or)
+{
+	unsigned val = edma_read(ecc, offset);
+
+	val &= and;
+	val |= or;
+	edma_write(ecc, offset, val);
+}
+
+static inline void edma_and(struct edma_cc *ecc, int offset, unsigned and)
+{
+	unsigned val = edma_read(ecc, offset);
+
+	val &= and;
+	edma_write(ecc, offset, val);
+}
+
+static inline void edma_or(struct edma_cc *ecc, int offset, unsigned or)
+{
+	unsigned val = edma_read(ecc, offset);
+
+	val |= or;
+	edma_write(ecc, offset, val);
+}
+
+static inline unsigned int edma_read_array(struct edma_cc *ecc, int offset,
+					   int i)
+{
+	return edma_read(ecc, offset + (i << 2));
+}
+
+static inline void edma_write_array(struct edma_cc *ecc, int offset, int i,
+				    unsigned val)
+{
+	edma_write(ecc, offset + (i << 2), val);
+}
+
+static inline void edma_modify_array(struct edma_cc *ecc, int offset, int i,
+				     unsigned and, unsigned or)
+{
+	edma_modify(ecc, offset + (i << 2), and, or);
+}
+
+static inline void edma_or_array(struct edma_cc *ecc, int offset, int i,
+				 unsigned or)
+{
+	edma_or(ecc, offset + (i << 2), or);
+}
+
+static inline void edma_or_array2(struct edma_cc *ecc, int offset, int i, int j,
+				  unsigned or)
+{
+	edma_or(ecc, offset + ((i * 2 + j) << 2), or);
+}
+
+static inline void edma_write_array2(struct edma_cc *ecc, int offset, int i,
+				     int j, unsigned val)
+{
+	edma_write(ecc, offset + ((i * 2 + j) << 2), val);
+}
+
+static inline unsigned int edma_shadow0_read(struct edma_cc *ecc, int offset)
+{
+	return edma_read(ecc, EDMA_SHADOW0 + offset);
+}
+
+static inline unsigned int edma_shadow0_read_array(struct edma_cc *ecc,
+						   int offset, int i)
+{
+	return edma_read(ecc, EDMA_SHADOW0 + offset + (i << 2));
+}
+
+static inline void edma_shadow0_write(struct edma_cc *ecc, int offset,
+				      unsigned val)
+{
+	edma_write(ecc, EDMA_SHADOW0 + offset, val);
+}
+
+static inline void edma_shadow0_write_array(struct edma_cc *ecc, int offset,
+					    int i, unsigned val)
+{
+	edma_write(ecc, EDMA_SHADOW0 + offset + (i << 2), val);
+}
+
+static inline unsigned int edma_param_read(struct edma_cc *ecc, int offset,
+					   int param_no)
+{
+	return edma_read(ecc, EDMA_PARM + offset + (param_no << 5));
+}
+
+static inline void edma_param_write(struct edma_cc *ecc, int offset,
+				    int param_no, unsigned val)
+{
+	edma_write(ecc, EDMA_PARM + offset + (param_no << 5), val);
+}
+
+static inline void edma_param_modify(struct edma_cc *ecc, int offset,
+				     int param_no, unsigned and, unsigned or)
+{
+	edma_modify(ecc, EDMA_PARM + offset + (param_no << 5), and, or);
+}
+
+static inline void edma_param_and(struct edma_cc *ecc, int offset, int param_no,
+				  unsigned and)
+{
+	edma_and(ecc, EDMA_PARM + offset + (param_no << 5), and);
+}
+
+static inline void edma_param_or(struct edma_cc *ecc, int offset, int param_no,
+				 unsigned or)
+{
+	edma_or(ecc, EDMA_PARM + offset + (param_no << 5), or);
+}
+
+static void edma_assign_priority_to_queue(struct edma_cc *ecc, int queue_no,
+					  int priority)
+{
+	int bit = queue_no * 4;
+
+	edma_modify(ecc, EDMA_QUEPRI, ~(0x7 << bit), ((priority & 0x7) << bit));
+}
+
+static void edma_set_chmap(struct edma_chan *echan, int slot)
+{
+	struct edma_cc *ecc = echan->ecc;
+	int channel = EDMA_CHAN_SLOT(echan->ch_num);
+
+	if (ecc->chmap_exist) {
+		slot = EDMA_CHAN_SLOT(slot);
+		edma_write_array(ecc, EDMA_DCHMAP, channel, (slot << 5));
+	}
+}
+
+static void edma_setup_interrupt(struct edma_chan *echan, bool enable)
+{
+	struct edma_cc *ecc = echan->ecc;
+	int channel = EDMA_CHAN_SLOT(echan->ch_num);
+	int idx = EDMA_REG_ARRAY_INDEX(channel);
+	int ch_bit = EDMA_CHANNEL_BIT(channel);
+
+	if (enable) {
+		edma_shadow0_write_array(ecc, SH_ICR, idx, ch_bit);
+		edma_shadow0_write_array(ecc, SH_IESR, idx, ch_bit);
+	} else {
+		edma_shadow0_write_array(ecc, SH_IECR, idx, ch_bit);
+	}
+}
+
+/*
+ * paRAM slot management functions
+ */
+static void edma_write_slot(struct edma_cc *ecc, unsigned slot,
+			    const struct edmacc_param *param)
+{
+	slot = EDMA_CHAN_SLOT(slot);
+	if (slot >= ecc->num_slots)
+		return;
+	memcpy_toio(ecc->base + PARM_OFFSET(slot), param, PARM_SIZE);
+}
+
+static int edma_read_slot(struct edma_cc *ecc, unsigned slot,
+			   struct edmacc_param *param)
+{
+	slot = EDMA_CHAN_SLOT(slot);
+	if (slot >= ecc->num_slots)
+		return -EINVAL;
+	memcpy_fromio(param, ecc->base + PARM_OFFSET(slot), PARM_SIZE);
+
+	return 0;
+}
+
+/**
+ * edma_alloc_slot - allocate DMA parameter RAM
+ * @ecc: pointer to edma_cc struct
+ * @slot: specific slot to allocate; negative for "any unused slot"
+ *
+ * This allocates a parameter RAM slot, initializing it to hold a
+ * dummy transfer.  Slots allocated using this routine have not been
+ * mapped to a hardware DMA channel, and will normally be used by
+ * linking to them from a slot associated with a DMA channel.
+ *
+ * Normal use is to pass EDMA_SLOT_ANY as the @slot, but specific
+ * slots may be allocated on behalf of DSP firmware.
+ *
+ * Returns the number of the slot, else negative errno.
+ */
+static int edma_alloc_slot(struct edma_cc *ecc, int slot)
+{
+	if (slot >= 0) {
+		slot = EDMA_CHAN_SLOT(slot);
+		/* Requesting entry paRAM slot for a HW triggered channel. */
+		if (ecc->chmap_exist && slot < ecc->num_channels)
+			slot = EDMA_SLOT_ANY;
+	}
+
+	if (slot < 0) {
+		if (ecc->chmap_exist)
+			slot = 0;
+		else
+			slot = ecc->num_channels;
+		for (;;) {
+			slot = find_next_zero_bit(ecc->slot_inuse,
+						  ecc->num_slots,
+						  slot);
+			if (slot == ecc->num_slots)
+				return -ENOMEM;
+			if (!test_and_set_bit(slot, ecc->slot_inuse))
+				break;
+		}
+	} else if (slot >= ecc->num_slots) {
+		return -EINVAL;
+	} else if (test_and_set_bit(slot, ecc->slot_inuse)) {
+		return -EBUSY;
+	}
+
+	edma_write_slot(ecc, slot, &dummy_paramset);
+
+	return EDMA_CTLR_CHAN(ecc->id, slot);
+}
+
+static void edma_free_slot(struct edma_cc *ecc, unsigned slot)
+{
+	slot = EDMA_CHAN_SLOT(slot);
+	if (slot >= ecc->num_slots)
+		return;
+
+	edma_write_slot(ecc, slot, &dummy_paramset);
+	clear_bit(slot, ecc->slot_inuse);
+}
+
+/**
+ * edma_link - link one parameter RAM slot to another
+ * @ecc: pointer to edma_cc struct
+ * @from: parameter RAM slot originating the link
+ * @to: parameter RAM slot which is the link target
+ *
+ * The originating slot should not be part of any active DMA transfer.
+ */
+static void edma_link(struct edma_cc *ecc, unsigned from, unsigned to)
+{
+	if (unlikely(EDMA_CTLR(from) != EDMA_CTLR(to)))
+		dev_warn(ecc->dev, "Ignoring eDMA instance for linking\n");
+
+	from = EDMA_CHAN_SLOT(from);
+	to = EDMA_CHAN_SLOT(to);
+	if (from >= ecc->num_slots || to >= ecc->num_slots)
+		return;
+
+	edma_param_modify(ecc, PARM_LINK_BCNTRLD, from, 0xffff0000,
+			  PARM_OFFSET(to));
+}
+
+/**
+ * edma_get_position - returns the current transfer point
+ * @ecc: pointer to edma_cc struct
+ * @slot: parameter RAM slot being examined
+ * @dst:  true selects the dest position, false the source
+ *
+ * Returns the position of the current active slot
+ */
+static dma_addr_t edma_get_position(struct edma_cc *ecc, unsigned slot,
+				    bool dst)
+{
+	u32 offs;
+
+	slot = EDMA_CHAN_SLOT(slot);
+	offs = PARM_OFFSET(slot);
+	offs += dst ? PARM_DST : PARM_SRC;
+
+	return edma_read(ecc, offs);
+}
+
+/*
+ * Channels with event associations will be triggered by their hardware
+ * events, and channels without such associations will be triggered by
+ * software.  (At this writing there is no interface for using software
+ * triggers except with channels that don't support hardware triggers.)
+ */
+static void edma_start(struct edma_chan *echan)
+{
+	struct edma_cc *ecc = echan->ecc;
+	int channel = EDMA_CHAN_SLOT(echan->ch_num);
+	int idx = EDMA_REG_ARRAY_INDEX(channel);
+	int ch_bit = EDMA_CHANNEL_BIT(channel);
+
+	if (!echan->hw_triggered) {
+		/* EDMA channels without event association */
+		dev_dbg(ecc->dev, "ESR%d %08x\n", idx,
+			edma_shadow0_read_array(ecc, SH_ESR, idx));
+		edma_shadow0_write_array(ecc, SH_ESR, idx, ch_bit);
+	} else {
+		/* EDMA channel with event association */
+		dev_dbg(ecc->dev, "ER%d %08x\n", idx,
+			edma_shadow0_read_array(ecc, SH_ER, idx));
+		/* Clear any pending event or error */
+		edma_write_array(ecc, EDMA_ECR, idx, ch_bit);
+		edma_write_array(ecc, EDMA_EMCR, idx, ch_bit);
+		/* Clear any SER */
+		edma_shadow0_write_array(ecc, SH_SECR, idx, ch_bit);
+		edma_shadow0_write_array(ecc, SH_EESR, idx, ch_bit);
+		dev_dbg(ecc->dev, "EER%d %08x\n", idx,
+			edma_shadow0_read_array(ecc, SH_EER, idx));
+	}
+}
+
+static void edma_stop(struct edma_chan *echan)
+{
+	struct edma_cc *ecc = echan->ecc;
+	int channel = EDMA_CHAN_SLOT(echan->ch_num);
+	int idx = EDMA_REG_ARRAY_INDEX(channel);
+	int ch_bit = EDMA_CHANNEL_BIT(channel);
+
+	edma_shadow0_write_array(ecc, SH_EECR, idx, ch_bit);
+	edma_shadow0_write_array(ecc, SH_ECR, idx, ch_bit);
+	edma_shadow0_write_array(ecc, SH_SECR, idx, ch_bit);
+	edma_write_array(ecc, EDMA_EMCR, idx, ch_bit);
+
+	/* clear possibly pending completion interrupt */
+	edma_shadow0_write_array(ecc, SH_ICR, idx, ch_bit);
+
+	dev_dbg(ecc->dev, "EER%d %08x\n", idx,
+		edma_shadow0_read_array(ecc, SH_EER, idx));
+
+	/* REVISIT:  consider guarding against inappropriate event
+	 * chaining by overwriting with dummy_paramset.
+	 */
+}
+
+/*
+ * Temporarily disable EDMA hardware events on the specified channel,
+ * preventing them from triggering new transfers
+ */
+static void edma_pause(struct edma_chan *echan)
+{
+	int channel = EDMA_CHAN_SLOT(echan->ch_num);
+
+	edma_shadow0_write_array(echan->ecc, SH_EECR,
+				 EDMA_REG_ARRAY_INDEX(channel),
+				 EDMA_CHANNEL_BIT(channel));
+}
+
+/* Re-enable EDMA hardware events on the specified channel.  */
+static void edma_resume(struct edma_chan *echan)
+{
+	int channel = EDMA_CHAN_SLOT(echan->ch_num);
+
+	edma_shadow0_write_array(echan->ecc, SH_EESR,
+				 EDMA_REG_ARRAY_INDEX(channel),
+				 EDMA_CHANNEL_BIT(channel));
+}
+
+static void edma_trigger_channel(struct edma_chan *echan)
+{
+	struct edma_cc *ecc = echan->ecc;
+	int channel = EDMA_CHAN_SLOT(echan->ch_num);
+	int idx = EDMA_REG_ARRAY_INDEX(channel);
+	int ch_bit = EDMA_CHANNEL_BIT(channel);
+
+	edma_shadow0_write_array(ecc, SH_ESR, idx, ch_bit);
+
+	dev_dbg(ecc->dev, "ESR%d %08x\n", idx,
+		edma_shadow0_read_array(ecc, SH_ESR, idx));
+}
+
+static void edma_clean_channel(struct edma_chan *echan)
+{
+	struct edma_cc *ecc = echan->ecc;
+	int channel = EDMA_CHAN_SLOT(echan->ch_num);
+	int idx = EDMA_REG_ARRAY_INDEX(channel);
+	int ch_bit = EDMA_CHANNEL_BIT(channel);
+
+	dev_dbg(ecc->dev, "EMR%d %08x\n", idx,
+		edma_read_array(ecc, EDMA_EMR, idx));
+	edma_shadow0_write_array(ecc, SH_ECR, idx, ch_bit);
+	/* Clear the corresponding EMR bits */
+	edma_write_array(ecc, EDMA_EMCR, idx, ch_bit);
+	/* Clear any SER */
+	edma_shadow0_write_array(ecc, SH_SECR, idx, ch_bit);
+	edma_write(ecc, EDMA_CCERRCLR, BIT(16) | BIT(1) | BIT(0));
+}
+
+/* Move channel to a specific event queue */
+static void edma_assign_channel_eventq(struct edma_chan *echan,
+				       enum dma_event_q eventq_no)
+{
+	struct edma_cc *ecc = echan->ecc;
+	int channel = EDMA_CHAN_SLOT(echan->ch_num);
+	int bit = (channel & 0x7) * 4;
+
+	/* default to low priority queue */
+	if (eventq_no == EVENTQ_DEFAULT)
+		eventq_no = ecc->default_queue;
+	if (eventq_no >= ecc->num_tc)
+		return;
+
+	eventq_no &= 7;
+	edma_modify_array(ecc, EDMA_DMAQNUM, (channel >> 3), ~(0x7 << bit),
+			  eventq_no << bit);
+}
+
+static int edma_alloc_channel(struct edma_chan *echan,
+			      enum dma_event_q eventq_no)
+{
+	struct edma_cc *ecc = echan->ecc;
+	int channel = EDMA_CHAN_SLOT(echan->ch_num);
+
+	if (!test_bit(echan->ch_num, ecc->channels_mask)) {
+		dev_err(ecc->dev, "Channel%d is reserved, can not be used!\n",
+			echan->ch_num);
+		return -EINVAL;
+	}
+
+	/* ensure access through shadow region 0 */
+	edma_or_array2(ecc, EDMA_DRAE, 0, EDMA_REG_ARRAY_INDEX(channel),
+		       EDMA_CHANNEL_BIT(channel));
+
+	/* ensure no events are pending */
+	edma_stop(echan);
+
+	edma_setup_interrupt(echan, true);
+
+	edma_assign_channel_eventq(echan, eventq_no);
+
+	return 0;
+}
+
+static void edma_free_channel(struct edma_chan *echan)
+{
+	/* ensure no events are pending */
+	edma_stop(echan);
+	/* REVISIT should probably take out of shadow region 0 */
+	edma_setup_interrupt(echan, false);
+}
+
+static inline struct edma_cc *to_edma_cc(struct dma_device *d)
+{
+	return container_of(d, struct edma_cc, dma_slave);
+}
+
+static inline struct edma_chan *to_edma_chan(struct dma_chan *c)
+{
+	return container_of(c, struct edma_chan, vchan.chan);
+}
+
+static inline struct edma_desc *to_edma_desc(struct dma_async_tx_descriptor *tx)
+{
+	return container_of(tx, struct edma_desc, vdesc.tx);
+}
+
+static void edma_desc_free(struct virt_dma_desc *vdesc)
+{
+	kfree(container_of(vdesc, struct edma_desc, vdesc));
+}
+
+/* Dispatch a queued descriptor to the controller (caller holds lock) */
+static void edma_execute(struct edma_chan *echan)
+{
+	struct edma_cc *ecc = echan->ecc;
+	struct virt_dma_desc *vdesc;
+	struct edma_desc *edesc;
+	struct device *dev = echan->vchan.chan.device->dev;
+	int i, j, left, nslots;
+
+	if (!echan->edesc) {
+		/* Setup is needed for the first transfer */
+		vdesc = vchan_next_desc(&echan->vchan);
+		if (!vdesc)
+			return;
+		list_del(&vdesc->node);
+		echan->edesc = to_edma_desc(&vdesc->tx);
+	}
+
+	edesc = echan->edesc;
+
+	/* Find out how many left */
+	left = edesc->pset_nr - edesc->processed;
+	nslots = min(MAX_NR_SG, left);
+	edesc->sg_len = 0;
+
+	/* Write descriptor PaRAM set(s) */
+	for (i = 0; i < nslots; i++) {
+		j = i + edesc->processed;
+		edma_write_slot(ecc, echan->slot[i], &edesc->pset[j].param);
+		edesc->sg_len += edesc->pset[j].len;
+		dev_vdbg(dev,
+			 "\n pset[%d]:\n"
+			 "  chnum\t%d\n"
+			 "  slot\t%d\n"
+			 "  opt\t%08x\n"
+			 "  src\t%08x\n"
+			 "  dst\t%08x\n"
+			 "  abcnt\t%08x\n"
+			 "  ccnt\t%08x\n"
+			 "  bidx\t%08x\n"
+			 "  cidx\t%08x\n"
+			 "  lkrld\t%08x\n",
+			 j, echan->ch_num, echan->slot[i],
+			 edesc->pset[j].param.opt,
+			 edesc->pset[j].param.src,
+			 edesc->pset[j].param.dst,
+			 edesc->pset[j].param.a_b_cnt,
+			 edesc->pset[j].param.ccnt,
+			 edesc->pset[j].param.src_dst_bidx,
+			 edesc->pset[j].param.src_dst_cidx,
+			 edesc->pset[j].param.link_bcntrld);
+		/* Link to the previous slot if not the last set */
+		if (i != (nslots - 1))
+			edma_link(ecc, echan->slot[i], echan->slot[i + 1]);
+	}
+
+	edesc->processed += nslots;
+
+	/*
+	 * If this is either the last set in a set of SG-list transactions
+	 * then setup a link to the dummy slot, this results in all future
+	 * events being absorbed and that's OK because we're done
+	 */
+	if (edesc->processed == edesc->pset_nr) {
+		if (edesc->cyclic)
+			edma_link(ecc, echan->slot[nslots - 1], echan->slot[1]);
+		else
+			edma_link(ecc, echan->slot[nslots - 1],
+				  echan->ecc->dummy_slot);
+	}
+
+	if (echan->missed) {
+		/*
+		 * This happens due to setup times between intermediate
+		 * transfers in long SG lists which have to be broken up into
+		 * transfers of MAX_NR_SG
+		 */
+		dev_dbg(dev, "missed event on channel %d\n", echan->ch_num);
+		edma_clean_channel(echan);
+		edma_stop(echan);
+		edma_start(echan);
+		edma_trigger_channel(echan);
+		echan->missed = 0;
+	} else if (edesc->processed <= MAX_NR_SG) {
+		dev_dbg(dev, "first transfer starting on channel %d\n",
+			echan->ch_num);
+		edma_start(echan);
+	} else {
+		dev_dbg(dev, "chan: %d: completed %d elements, resuming\n",
+			echan->ch_num, edesc->processed);
+		edma_resume(echan);
+	}
+}
+
+static int edma_terminate_all(struct dma_chan *chan)
+{
+	struct edma_chan *echan = to_edma_chan(chan);
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	spin_lock_irqsave(&echan->vchan.lock, flags);
+
+	/*
+	 * Stop DMA activity: we assume the callback will not be called
+	 * after edma_dma() returns (even if it does, it will see
+	 * echan->edesc is NULL and exit.)
+	 */
+	if (echan->edesc) {
+		edma_stop(echan);
+		/* Move the cyclic channel back to default queue */
+		if (!echan->tc && echan->edesc->cyclic)
+			edma_assign_channel_eventq(echan, EVENTQ_DEFAULT);
+
+		vchan_terminate_vdesc(&echan->edesc->vdesc);
+		echan->edesc = NULL;
+	}
+
+	vchan_get_all_descriptors(&echan->vchan, &head);
+	spin_unlock_irqrestore(&echan->vchan.lock, flags);
+	vchan_dma_desc_free_list(&echan->vchan, &head);
+
+	return 0;
+}
+
+static void edma_synchronize(struct dma_chan *chan)
+{
+	struct edma_chan *echan = to_edma_chan(chan);
+
+	vchan_synchronize(&echan->vchan);
+}
+
+static int edma_slave_config(struct dma_chan *chan,
+	struct dma_slave_config *cfg)
+{
+	struct edma_chan *echan = to_edma_chan(chan);
+
+	if (cfg->src_addr_width == DMA_SLAVE_BUSWIDTH_8_BYTES ||
+	    cfg->dst_addr_width == DMA_SLAVE_BUSWIDTH_8_BYTES)
+		return -EINVAL;
+
+	if (cfg->src_maxburst > chan->device->max_burst ||
+	    cfg->dst_maxburst > chan->device->max_burst)
+		return -EINVAL;
+
+	memcpy(&echan->cfg, cfg, sizeof(echan->cfg));
+
+	return 0;
+}
+
+static int edma_dma_pause(struct dma_chan *chan)
+{
+	struct edma_chan *echan = to_edma_chan(chan);
+
+	if (!echan->edesc)
+		return -EINVAL;
+
+	edma_pause(echan);
+	return 0;
+}
+
+static int edma_dma_resume(struct dma_chan *chan)
+{
+	struct edma_chan *echan = to_edma_chan(chan);
+
+	edma_resume(echan);
+	return 0;
+}
+
+/*
+ * A PaRAM set configuration abstraction used by other modes
+ * @chan: Channel who's PaRAM set we're configuring
+ * @pset: PaRAM set to initialize and setup.
+ * @src_addr: Source address of the DMA
+ * @dst_addr: Destination address of the DMA
+ * @burst: In units of dev_width, how much to send
+ * @dev_width: How much is the dev_width
+ * @dma_length: Total length of the DMA transfer
+ * @direction: Direction of the transfer
+ */
+static int edma_config_pset(struct dma_chan *chan, struct edma_pset *epset,
+			    dma_addr_t src_addr, dma_addr_t dst_addr, u32 burst,
+			    unsigned int acnt, unsigned int dma_length,
+			    enum dma_transfer_direction direction)
+{
+	struct edma_chan *echan = to_edma_chan(chan);
+	struct device *dev = chan->device->dev;
+	struct edmacc_param *param = &epset->param;
+	int bcnt, ccnt, cidx;
+	int src_bidx, dst_bidx, src_cidx, dst_cidx;
+	int absync;
+
+	/* src/dst_maxburst == 0 is the same case as src/dst_maxburst == 1 */
+	if (!burst)
+		burst = 1;
+	/*
+	 * If the maxburst is equal to the fifo width, use
+	 * A-synced transfers. This allows for large contiguous
+	 * buffer transfers using only one PaRAM set.
+	 */
+	if (burst == 1) {
+		/*
+		 * For the A-sync case, bcnt and ccnt are the remainder
+		 * and quotient respectively of the division of:
+		 * (dma_length / acnt) by (SZ_64K -1). This is so
+		 * that in case bcnt over flows, we have ccnt to use.
+		 * Note: In A-sync tranfer only, bcntrld is used, but it
+		 * only applies for sg_dma_len(sg) >= SZ_64K.
+		 * In this case, the best way adopted is- bccnt for the
+		 * first frame will be the remainder below. Then for
+		 * every successive frame, bcnt will be SZ_64K-1. This
+		 * is assured as bcntrld = 0xffff in end of function.
+		 */
+		absync = false;
+		ccnt = dma_length / acnt / (SZ_64K - 1);
+		bcnt = dma_length / acnt - ccnt * (SZ_64K - 1);
+		/*
+		 * If bcnt is non-zero, we have a remainder and hence an
+		 * extra frame to transfer, so increment ccnt.
+		 */
+		if (bcnt)
+			ccnt++;
+		else
+			bcnt = SZ_64K - 1;
+		cidx = acnt;
+	} else {
+		/*
+		 * If maxburst is greater than the fifo address_width,
+		 * use AB-synced transfers where A count is the fifo
+		 * address_width and B count is the maxburst. In this
+		 * case, we are limited to transfers of C count frames
+		 * of (address_width * maxburst) where C count is limited
+		 * to SZ_64K-1. This places an upper bound on the length
+		 * of an SG segment that can be handled.
+		 */
+		absync = true;
+		bcnt = burst;
+		ccnt = dma_length / (acnt * bcnt);
+		if (ccnt > (SZ_64K - 1)) {
+			dev_err(dev, "Exceeded max SG segment size\n");
+			return -EINVAL;
+		}
+		cidx = acnt * bcnt;
+	}
+
+	epset->len = dma_length;
+
+	if (direction == DMA_MEM_TO_DEV) {
+		src_bidx = acnt;
+		src_cidx = cidx;
+		dst_bidx = 0;
+		dst_cidx = 0;
+		epset->addr = src_addr;
+	} else if (direction == DMA_DEV_TO_MEM)  {
+		src_bidx = 0;
+		src_cidx = 0;
+		dst_bidx = acnt;
+		dst_cidx = cidx;
+		epset->addr = dst_addr;
+	} else if (direction == DMA_MEM_TO_MEM)  {
+		src_bidx = acnt;
+		src_cidx = cidx;
+		dst_bidx = acnt;
+		dst_cidx = cidx;
+		epset->addr = src_addr;
+	} else {
+		dev_err(dev, "%s: direction not implemented yet\n", __func__);
+		return -EINVAL;
+	}
+
+	param->opt = EDMA_TCC(EDMA_CHAN_SLOT(echan->ch_num));
+	/* Configure A or AB synchronized transfers */
+	if (absync)
+		param->opt |= SYNCDIM;
+
+	param->src = src_addr;
+	param->dst = dst_addr;
+
+	param->src_dst_bidx = (dst_bidx << 16) | src_bidx;
+	param->src_dst_cidx = (dst_cidx << 16) | src_cidx;
+
+	param->a_b_cnt = bcnt << 16 | acnt;
+	param->ccnt = ccnt;
+	/*
+	 * Only time when (bcntrld) auto reload is required is for
+	 * A-sync case, and in this case, a requirement of reload value
+	 * of SZ_64K-1 only is assured. 'link' is initially set to NULL
+	 * and then later will be populated by edma_execute.
+	 */
+	param->link_bcntrld = 0xffffffff;
+	return absync;
+}
+
+static struct dma_async_tx_descriptor *edma_prep_slave_sg(
+	struct dma_chan *chan, struct scatterlist *sgl,
+	unsigned int sg_len, enum dma_transfer_direction direction,
+	unsigned long tx_flags, void *context)
+{
+	struct edma_chan *echan = to_edma_chan(chan);
+	struct device *dev = chan->device->dev;
+	struct edma_desc *edesc;
+	dma_addr_t src_addr = 0, dst_addr = 0;
+	enum dma_slave_buswidth dev_width;
+	u32 burst;
+	struct scatterlist *sg;
+	int i, nslots, ret;
+
+	if (unlikely(!echan || !sgl || !sg_len))
+		return NULL;
+
+	if (direction == DMA_DEV_TO_MEM) {
+		src_addr = echan->cfg.src_addr;
+		dev_width = echan->cfg.src_addr_width;
+		burst = echan->cfg.src_maxburst;
+	} else if (direction == DMA_MEM_TO_DEV) {
+		dst_addr = echan->cfg.dst_addr;
+		dev_width = echan->cfg.dst_addr_width;
+		burst = echan->cfg.dst_maxburst;
+	} else {
+		dev_err(dev, "%s: bad direction: %d\n", __func__, direction);
+		return NULL;
+	}
+
+	if (dev_width == DMA_SLAVE_BUSWIDTH_UNDEFINED) {
+		dev_err(dev, "%s: Undefined slave buswidth\n", __func__);
+		return NULL;
+	}
+
+	edesc = kzalloc(struct_size(edesc, pset, sg_len), GFP_ATOMIC);
+	if (!edesc)
+		return NULL;
+
+	edesc->pset_nr = sg_len;
+	edesc->residue = 0;
+	edesc->direction = direction;
+	edesc->echan = echan;
+
+	/* Allocate a PaRAM slot, if needed */
+	nslots = min_t(unsigned, MAX_NR_SG, sg_len);
+
+	for (i = 0; i < nslots; i++) {
+		if (echan->slot[i] < 0) {
+			echan->slot[i] =
+				edma_alloc_slot(echan->ecc, EDMA_SLOT_ANY);
+			if (echan->slot[i] < 0) {
+				kfree(edesc);
+				dev_err(dev, "%s: Failed to allocate slot\n",
+					__func__);
+				return NULL;
+			}
+		}
+	}
+
+	/* Configure PaRAM sets for each SG */
+	for_each_sg(sgl, sg, sg_len, i) {
+		/* Get address for each SG */
+		if (direction == DMA_DEV_TO_MEM)
+			dst_addr = sg_dma_address(sg);
+		else
+			src_addr = sg_dma_address(sg);
+
+		ret = edma_config_pset(chan, &edesc->pset[i], src_addr,
+				       dst_addr, burst, dev_width,
+				       sg_dma_len(sg), direction);
+		if (ret < 0) {
+			kfree(edesc);
+			return NULL;
+		}
+
+		edesc->absync = ret;
+		edesc->residue += sg_dma_len(sg);
+
+		if (i == sg_len - 1)
+			/* Enable completion interrupt */
+			edesc->pset[i].param.opt |= TCINTEN;
+		else if (!((i+1) % MAX_NR_SG))
+			/*
+			 * Enable early completion interrupt for the
+			 * intermediateset. In this case the driver will be
+			 * notified when the paRAM set is submitted to TC. This
+			 * will allow more time to set up the next set of slots.
+			 */
+			edesc->pset[i].param.opt |= (TCINTEN | TCCMODE);
+	}
+	edesc->residue_stat = edesc->residue;
+
+	return vchan_tx_prep(&echan->vchan, &edesc->vdesc, tx_flags);
+}
+
+static struct dma_async_tx_descriptor *edma_prep_dma_memcpy(
+	struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
+	size_t len, unsigned long tx_flags)
+{
+	int ret, nslots;
+	struct edma_desc *edesc;
+	struct device *dev = chan->device->dev;
+	struct edma_chan *echan = to_edma_chan(chan);
+	unsigned int width, pset_len, array_size;
+
+	if (unlikely(!echan || !len))
+		return NULL;
+
+	/* Align the array size (acnt block) with the transfer properties */
+	switch (__ffs((src | dest | len))) {
+	case 0:
+		array_size = SZ_32K - 1;
+		break;
+	case 1:
+		array_size = SZ_32K - 2;
+		break;
+	default:
+		array_size = SZ_32K - 4;
+		break;
+	}
+
+	if (len < SZ_64K) {
+		/*
+		 * Transfer size less than 64K can be handled with one paRAM
+		 * slot and with one burst.
+		 * ACNT = length
+		 */
+		width = len;
+		pset_len = len;
+		nslots = 1;
+	} else {
+		/*
+		 * Transfer size bigger than 64K will be handled with maximum of
+		 * two paRAM slots.
+		 * slot1: (full_length / 32767) times 32767 bytes bursts.
+		 *	  ACNT = 32767, length1: (full_length / 32767) * 32767
+		 * slot2: the remaining amount of data after slot1.
+		 *	  ACNT = full_length - length1, length2 = ACNT
+		 *
+		 * When the full_length is multibple of 32767 one slot can be
+		 * used to complete the transfer.
+		 */
+		width = array_size;
+		pset_len = rounddown(len, width);
+		/* One slot is enough for lengths multiple of (SZ_32K -1) */
+		if (unlikely(pset_len == len))
+			nslots = 1;
+		else
+			nslots = 2;
+	}
+
+	edesc = kzalloc(struct_size(edesc, pset, nslots), GFP_ATOMIC);
+	if (!edesc)
+		return NULL;
+
+	edesc->pset_nr = nslots;
+	edesc->residue = edesc->residue_stat = len;
+	edesc->direction = DMA_MEM_TO_MEM;
+	edesc->echan = echan;
+
+	ret = edma_config_pset(chan, &edesc->pset[0], src, dest, 1,
+			       width, pset_len, DMA_MEM_TO_MEM);
+	if (ret < 0) {
+		kfree(edesc);
+		return NULL;
+	}
+
+	edesc->absync = ret;
+
+	edesc->pset[0].param.opt |= ITCCHEN;
+	if (nslots == 1) {
+		/* Enable transfer complete interrupt if requested */
+		if (tx_flags & DMA_PREP_INTERRUPT)
+			edesc->pset[0].param.opt |= TCINTEN;
+	} else {
+		/* Enable transfer complete chaining for the first slot */
+		edesc->pset[0].param.opt |= TCCHEN;
+
+		if (echan->slot[1] < 0) {
+			echan->slot[1] = edma_alloc_slot(echan->ecc,
+							 EDMA_SLOT_ANY);
+			if (echan->slot[1] < 0) {
+				kfree(edesc);
+				dev_err(dev, "%s: Failed to allocate slot\n",
+					__func__);
+				return NULL;
+			}
+		}
+		dest += pset_len;
+		src += pset_len;
+		pset_len = width = len % array_size;
+
+		ret = edma_config_pset(chan, &edesc->pset[1], src, dest, 1,
+				       width, pset_len, DMA_MEM_TO_MEM);
+		if (ret < 0) {
+			kfree(edesc);
+			return NULL;
+		}
+
+		edesc->pset[1].param.opt |= ITCCHEN;
+		/* Enable transfer complete interrupt if requested */
+		if (tx_flags & DMA_PREP_INTERRUPT)
+			edesc->pset[1].param.opt |= TCINTEN;
+	}
+
+	if (!(tx_flags & DMA_PREP_INTERRUPT))
+		edesc->polled = true;
+
+	return vchan_tx_prep(&echan->vchan, &edesc->vdesc, tx_flags);
+}
+
+static struct dma_async_tx_descriptor *
+edma_prep_dma_interleaved(struct dma_chan *chan,
+			  struct dma_interleaved_template *xt,
+			  unsigned long tx_flags)
+{
+	struct device *dev = chan->device->dev;
+	struct edma_chan *echan = to_edma_chan(chan);
+	struct edmacc_param *param;
+	struct edma_desc *edesc;
+	size_t src_icg, dst_icg;
+	int src_bidx, dst_bidx;
+
+	/* Slave mode is not supported */
+	if (is_slave_direction(xt->dir))
+		return NULL;
+
+	if (xt->frame_size != 1 || xt->numf == 0)
+		return NULL;
+
+	if (xt->sgl[0].size > SZ_64K || xt->numf > SZ_64K)
+		return NULL;
+
+	src_icg = dmaengine_get_src_icg(xt, &xt->sgl[0]);
+	if (src_icg) {
+		src_bidx = src_icg + xt->sgl[0].size;
+	} else if (xt->src_inc) {
+		src_bidx = xt->sgl[0].size;
+	} else {
+		dev_err(dev, "%s: SRC constant addressing is not supported\n",
+			__func__);
+		return NULL;
+	}
+
+	dst_icg = dmaengine_get_dst_icg(xt, &xt->sgl[0]);
+	if (dst_icg) {
+		dst_bidx = dst_icg + xt->sgl[0].size;
+	} else if (xt->dst_inc) {
+		dst_bidx = xt->sgl[0].size;
+	} else {
+		dev_err(dev, "%s: DST constant addressing is not supported\n",
+			__func__);
+		return NULL;
+	}
+
+	if (src_bidx > SZ_64K || dst_bidx > SZ_64K)
+		return NULL;
+
+	edesc = kzalloc(struct_size(edesc, pset, 1), GFP_ATOMIC);
+	if (!edesc)
+		return NULL;
+
+	edesc->direction = DMA_MEM_TO_MEM;
+	edesc->echan = echan;
+	edesc->pset_nr = 1;
+
+	param = &edesc->pset[0].param;
+
+	param->src = xt->src_start;
+	param->dst = xt->dst_start;
+	param->a_b_cnt = xt->numf << 16 | xt->sgl[0].size;
+	param->ccnt = 1;
+	param->src_dst_bidx = (dst_bidx << 16) | src_bidx;
+	param->src_dst_cidx = 0;
+
+	param->opt = EDMA_TCC(EDMA_CHAN_SLOT(echan->ch_num));
+	param->opt |= ITCCHEN;
+	/* Enable transfer complete interrupt if requested */
+	if (tx_flags & DMA_PREP_INTERRUPT)
+		param->opt |= TCINTEN;
+	else
+		edesc->polled = true;
+
+	return vchan_tx_prep(&echan->vchan, &edesc->vdesc, tx_flags);
+}
+
+static struct dma_async_tx_descriptor *edma_prep_dma_cyclic(
+	struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
+	size_t period_len, enum dma_transfer_direction direction,
+	unsigned long tx_flags)
+{
+	struct edma_chan *echan = to_edma_chan(chan);
+	struct device *dev = chan->device->dev;
+	struct edma_desc *edesc;
+	dma_addr_t src_addr, dst_addr;
+	enum dma_slave_buswidth dev_width;
+	bool use_intermediate = false;
+	u32 burst;
+	int i, ret, nslots;
+
+	if (unlikely(!echan || !buf_len || !period_len))
+		return NULL;
+
+	if (direction == DMA_DEV_TO_MEM) {
+		src_addr = echan->cfg.src_addr;
+		dst_addr = buf_addr;
+		dev_width = echan->cfg.src_addr_width;
+		burst = echan->cfg.src_maxburst;
+	} else if (direction == DMA_MEM_TO_DEV) {
+		src_addr = buf_addr;
+		dst_addr = echan->cfg.dst_addr;
+		dev_width = echan->cfg.dst_addr_width;
+		burst = echan->cfg.dst_maxburst;
+	} else {
+		dev_err(dev, "%s: bad direction: %d\n", __func__, direction);
+		return NULL;
+	}
+
+	if (dev_width == DMA_SLAVE_BUSWIDTH_UNDEFINED) {
+		dev_err(dev, "%s: Undefined slave buswidth\n", __func__);
+		return NULL;
+	}
+
+	if (unlikely(buf_len % period_len)) {
+		dev_err(dev, "Period should be multiple of Buffer length\n");
+		return NULL;
+	}
+
+	nslots = (buf_len / period_len) + 1;
+
+	/*
+	 * Cyclic DMA users such as audio cannot tolerate delays introduced
+	 * by cases where the number of periods is more than the maximum
+	 * number of SGs the EDMA driver can handle at a time. For DMA types
+	 * such as Slave SGs, such delays are tolerable and synchronized,
+	 * but the synchronization is difficult to achieve with Cyclic and
+	 * cannot be guaranteed, so we error out early.
+	 */
+	if (nslots > MAX_NR_SG) {
+		/*
+		 * If the burst and period sizes are the same, we can put
+		 * the full buffer into a single period and activate
+		 * intermediate interrupts. This will produce interrupts
+		 * after each burst, which is also after each desired period.
+		 */
+		if (burst == period_len) {
+			period_len = buf_len;
+			nslots = 2;
+			use_intermediate = true;
+		} else {
+			return NULL;
+		}
+	}
+
+	edesc = kzalloc(struct_size(edesc, pset, nslots), GFP_ATOMIC);
+	if (!edesc)
+		return NULL;
+
+	edesc->cyclic = 1;
+	edesc->pset_nr = nslots;
+	edesc->residue = edesc->residue_stat = buf_len;
+	edesc->direction = direction;
+	edesc->echan = echan;
+
+	dev_dbg(dev, "%s: channel=%d nslots=%d period_len=%zu buf_len=%zu\n",
+		__func__, echan->ch_num, nslots, period_len, buf_len);
+
+	for (i = 0; i < nslots; i++) {
+		/* Allocate a PaRAM slot, if needed */
+		if (echan->slot[i] < 0) {
+			echan->slot[i] =
+				edma_alloc_slot(echan->ecc, EDMA_SLOT_ANY);
+			if (echan->slot[i] < 0) {
+				kfree(edesc);
+				dev_err(dev, "%s: Failed to allocate slot\n",
+					__func__);
+				return NULL;
+			}
+		}
+
+		if (i == nslots - 1) {
+			memcpy(&edesc->pset[i], &edesc->pset[0],
+			       sizeof(edesc->pset[0]));
+			break;
+		}
+
+		ret = edma_config_pset(chan, &edesc->pset[i], src_addr,
+				       dst_addr, burst, dev_width, period_len,
+				       direction);
+		if (ret < 0) {
+			kfree(edesc);
+			return NULL;
+		}
+
+		if (direction == DMA_DEV_TO_MEM)
+			dst_addr += period_len;
+		else
+			src_addr += period_len;
+
+		dev_vdbg(dev, "%s: Configure period %d of buf:\n", __func__, i);
+		dev_vdbg(dev,
+			"\n pset[%d]:\n"
+			"  chnum\t%d\n"
+			"  slot\t%d\n"
+			"  opt\t%08x\n"
+			"  src\t%08x\n"
+			"  dst\t%08x\n"
+			"  abcnt\t%08x\n"
+			"  ccnt\t%08x\n"
+			"  bidx\t%08x\n"
+			"  cidx\t%08x\n"
+			"  lkrld\t%08x\n",
+			i, echan->ch_num, echan->slot[i],
+			edesc->pset[i].param.opt,
+			edesc->pset[i].param.src,
+			edesc->pset[i].param.dst,
+			edesc->pset[i].param.a_b_cnt,
+			edesc->pset[i].param.ccnt,
+			edesc->pset[i].param.src_dst_bidx,
+			edesc->pset[i].param.src_dst_cidx,
+			edesc->pset[i].param.link_bcntrld);
+
+		edesc->absync = ret;
+
+		/*
+		 * Enable period interrupt only if it is requested
+		 */
+		if (tx_flags & DMA_PREP_INTERRUPT) {
+			edesc->pset[i].param.opt |= TCINTEN;
+
+			/* Also enable intermediate interrupts if necessary */
+			if (use_intermediate)
+				edesc->pset[i].param.opt |= ITCINTEN;
+		}
+	}
+
+	/* Place the cyclic channel to highest priority queue */
+	if (!echan->tc)
+		edma_assign_channel_eventq(echan, EVENTQ_0);
+
+	return vchan_tx_prep(&echan->vchan, &edesc->vdesc, tx_flags);
+}
+
+static void edma_completion_handler(struct edma_chan *echan)
+{
+	struct device *dev = echan->vchan.chan.device->dev;
+	struct edma_desc *edesc;
+
+	spin_lock(&echan->vchan.lock);
+	edesc = echan->edesc;
+	if (edesc) {
+		if (edesc->cyclic) {
+			vchan_cyclic_callback(&edesc->vdesc);
+			spin_unlock(&echan->vchan.lock);
+			return;
+		} else if (edesc->processed == edesc->pset_nr) {
+			edesc->residue = 0;
+			edma_stop(echan);
+			vchan_cookie_complete(&edesc->vdesc);
+			echan->edesc = NULL;
+
+			dev_dbg(dev, "Transfer completed on channel %d\n",
+				echan->ch_num);
+		} else {
+			dev_dbg(dev, "Sub transfer completed on channel %d\n",
+				echan->ch_num);
+
+			edma_pause(echan);
+
+			/* Update statistics for tx_status */
+			edesc->residue -= edesc->sg_len;
+			edesc->residue_stat = edesc->residue;
+			edesc->processed_stat = edesc->processed;
+		}
+		edma_execute(echan);
+	}
+
+	spin_unlock(&echan->vchan.lock);
+}
+
+/* eDMA interrupt handler */
+static irqreturn_t dma_irq_handler(int irq, void *data)
+{
+	struct edma_cc *ecc = data;
+	int ctlr;
+	u32 sh_ier;
+	u32 sh_ipr;
+	u32 bank;
+
+	ctlr = ecc->id;
+	if (ctlr < 0)
+		return IRQ_NONE;
+
+	dev_vdbg(ecc->dev, "dma_irq_handler\n");
+
+	sh_ipr = edma_shadow0_read_array(ecc, SH_IPR, 0);
+	if (!sh_ipr) {
+		sh_ipr = edma_shadow0_read_array(ecc, SH_IPR, 1);
+		if (!sh_ipr)
+			return IRQ_NONE;
+		sh_ier = edma_shadow0_read_array(ecc, SH_IER, 1);
+		bank = 1;
+	} else {
+		sh_ier = edma_shadow0_read_array(ecc, SH_IER, 0);
+		bank = 0;
+	}
+
+	do {
+		u32 slot;
+		u32 channel;
+
+		slot = __ffs(sh_ipr);
+		sh_ipr &= ~(BIT(slot));
+
+		if (sh_ier & BIT(slot)) {
+			channel = (bank << 5) | slot;
+			/* Clear the corresponding IPR bits */
+			edma_shadow0_write_array(ecc, SH_ICR, bank, BIT(slot));
+			edma_completion_handler(&ecc->slave_chans[channel]);
+		}
+	} while (sh_ipr);
+
+	edma_shadow0_write(ecc, SH_IEVAL, 1);
+	return IRQ_HANDLED;
+}
+
+static void edma_error_handler(struct edma_chan *echan)
+{
+	struct edma_cc *ecc = echan->ecc;
+	struct device *dev = echan->vchan.chan.device->dev;
+	struct edmacc_param p;
+	int err;
+
+	if (!echan->edesc)
+		return;
+
+	spin_lock(&echan->vchan.lock);
+
+	err = edma_read_slot(ecc, echan->slot[0], &p);
+
+	/*
+	 * Issue later based on missed flag which will be sure
+	 * to happen as:
+	 * (1) we finished transmitting an intermediate slot and
+	 *     edma_execute is coming up.
+	 * (2) or we finished current transfer and issue will
+	 *     call edma_execute.
+	 *
+	 * Important note: issuing can be dangerous here and
+	 * lead to some nasty recursion when we are in a NULL
+	 * slot. So we avoid doing so and set the missed flag.
+	 */
+	if (err || (p.a_b_cnt == 0 && p.ccnt == 0)) {
+		dev_dbg(dev, "Error on null slot, setting miss\n");
+		echan->missed = 1;
+	} else {
+		/*
+		 * The slot is already programmed but the event got
+		 * missed, so its safe to issue it here.
+		 */
+		dev_dbg(dev, "Missed event, TRIGGERING\n");
+		edma_clean_channel(echan);
+		edma_stop(echan);
+		edma_start(echan);
+		edma_trigger_channel(echan);
+	}
+	spin_unlock(&echan->vchan.lock);
+}
+
+static inline bool edma_error_pending(struct edma_cc *ecc)
+{
+	if (edma_read_array(ecc, EDMA_EMR, 0) ||
+	    edma_read_array(ecc, EDMA_EMR, 1) ||
+	    edma_read(ecc, EDMA_QEMR) || edma_read(ecc, EDMA_CCERR))
+		return true;
+
+	return false;
+}
+
+/* eDMA error interrupt handler */
+static irqreturn_t dma_ccerr_handler(int irq, void *data)
+{
+	struct edma_cc *ecc = data;
+	int i, j;
+	int ctlr;
+	unsigned int cnt = 0;
+	unsigned int val;
+
+	ctlr = ecc->id;
+	if (ctlr < 0)
+		return IRQ_NONE;
+
+	dev_vdbg(ecc->dev, "dma_ccerr_handler\n");
+
+	if (!edma_error_pending(ecc)) {
+		/*
+		 * The registers indicate no pending error event but the irq
+		 * handler has been called.
+		 * Ask eDMA to re-evaluate the error registers.
+		 */
+		dev_err(ecc->dev, "%s: Error interrupt without error event!\n",
+			__func__);
+		edma_write(ecc, EDMA_EEVAL, 1);
+		return IRQ_NONE;
+	}
+
+	while (1) {
+		/* Event missed register(s) */
+		for (j = 0; j < 2; j++) {
+			unsigned long emr;
+
+			val = edma_read_array(ecc, EDMA_EMR, j);
+			if (!val)
+				continue;
+
+			dev_dbg(ecc->dev, "EMR%d 0x%08x\n", j, val);
+			emr = val;
+			for (i = find_next_bit(&emr, 32, 0); i < 32;
+			     i = find_next_bit(&emr, 32, i + 1)) {
+				int k = (j << 5) + i;
+
+				/* Clear the corresponding EMR bits */
+				edma_write_array(ecc, EDMA_EMCR, j, BIT(i));
+				/* Clear any SER */
+				edma_shadow0_write_array(ecc, SH_SECR, j,
+							 BIT(i));
+				edma_error_handler(&ecc->slave_chans[k]);
+			}
+		}
+
+		val = edma_read(ecc, EDMA_QEMR);
+		if (val) {
+			dev_dbg(ecc->dev, "QEMR 0x%02x\n", val);
+			/* Not reported, just clear the interrupt reason. */
+			edma_write(ecc, EDMA_QEMCR, val);
+			edma_shadow0_write(ecc, SH_QSECR, val);
+		}
+
+		val = edma_read(ecc, EDMA_CCERR);
+		if (val) {
+			dev_warn(ecc->dev, "CCERR 0x%08x\n", val);
+			/* Not reported, just clear the interrupt reason. */
+			edma_write(ecc, EDMA_CCERRCLR, val);
+		}
+
+		if (!edma_error_pending(ecc))
+			break;
+		cnt++;
+		if (cnt > 10)
+			break;
+	}
+	edma_write(ecc, EDMA_EEVAL, 1);
+	return IRQ_HANDLED;
+}
+
+/* Alloc channel resources */
+static int edma_alloc_chan_resources(struct dma_chan *chan)
+{
+	struct edma_chan *echan = to_edma_chan(chan);
+	struct edma_cc *ecc = echan->ecc;
+	struct device *dev = ecc->dev;
+	enum dma_event_q eventq_no = EVENTQ_DEFAULT;
+	int ret;
+
+	if (echan->tc) {
+		eventq_no = echan->tc->id;
+	} else if (ecc->tc_list) {
+		/* memcpy channel */
+		echan->tc = &ecc->tc_list[ecc->info->default_queue];
+		eventq_no = echan->tc->id;
+	}
+
+	ret = edma_alloc_channel(echan, eventq_no);
+	if (ret)
+		return ret;
+
+	echan->slot[0] = edma_alloc_slot(ecc, echan->ch_num);
+	if (echan->slot[0] < 0) {
+		dev_err(dev, "Entry slot allocation failed for channel %u\n",
+			EDMA_CHAN_SLOT(echan->ch_num));
+		ret = echan->slot[0];
+		goto err_slot;
+	}
+
+	/* Set up channel -> slot mapping for the entry slot */
+	edma_set_chmap(echan, echan->slot[0]);
+	echan->alloced = true;
+
+	dev_dbg(dev, "Got eDMA channel %d for virt channel %d (%s trigger)\n",
+		EDMA_CHAN_SLOT(echan->ch_num), chan->chan_id,
+		echan->hw_triggered ? "HW" : "SW");
+
+	return 0;
+
+err_slot:
+	edma_free_channel(echan);
+	return ret;
+}
+
+/* Free channel resources */
+static void edma_free_chan_resources(struct dma_chan *chan)
+{
+	struct edma_chan *echan = to_edma_chan(chan);
+	struct device *dev = echan->ecc->dev;
+	int i;
+
+	/* Terminate transfers */
+	edma_stop(echan);
+
+	vchan_free_chan_resources(&echan->vchan);
+
+	/* Free EDMA PaRAM slots */
+	for (i = 0; i < EDMA_MAX_SLOTS; i++) {
+		if (echan->slot[i] >= 0) {
+			edma_free_slot(echan->ecc, echan->slot[i]);
+			echan->slot[i] = -1;
+		}
+	}
+
+	/* Set entry slot to the dummy slot */
+	edma_set_chmap(echan, echan->ecc->dummy_slot);
+
+	/* Free EDMA channel */
+	if (echan->alloced) {
+		edma_free_channel(echan);
+		echan->alloced = false;
+	}
+
+	echan->tc = NULL;
+	echan->hw_triggered = false;
+
+	dev_dbg(dev, "Free eDMA channel %d for virt channel %d\n",
+		EDMA_CHAN_SLOT(echan->ch_num), chan->chan_id);
+}
+
+/* Send pending descriptor to hardware */
+static void edma_issue_pending(struct dma_chan *chan)
+{
+	struct edma_chan *echan = to_edma_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&echan->vchan.lock, flags);
+	if (vchan_issue_pending(&echan->vchan) && !echan->edesc)
+		edma_execute(echan);
+	spin_unlock_irqrestore(&echan->vchan.lock, flags);
+}
+
+/*
+ * This limit exists to avoid a possible infinite loop when waiting for proof
+ * that a particular transfer is completed. This limit can be hit if there
+ * are large bursts to/from slow devices or the CPU is never able to catch
+ * the DMA hardware idle. On an AM335x transfering 48 bytes from the UART
+ * RX-FIFO, as many as 55 loops have been seen.
+ */
+#define EDMA_MAX_TR_WAIT_LOOPS 1000
+
+static u32 edma_residue(struct edma_desc *edesc)
+{
+	bool dst = edesc->direction == DMA_DEV_TO_MEM;
+	int loop_count = EDMA_MAX_TR_WAIT_LOOPS;
+	struct edma_chan *echan = edesc->echan;
+	struct edma_pset *pset = edesc->pset;
+	dma_addr_t done, pos, pos_old;
+	int channel = EDMA_CHAN_SLOT(echan->ch_num);
+	int idx = EDMA_REG_ARRAY_INDEX(channel);
+	int ch_bit = EDMA_CHANNEL_BIT(channel);
+	int event_reg;
+	int i;
+
+	/*
+	 * We always read the dst/src position from the first RamPar
+	 * pset. That's the one which is active now.
+	 */
+	pos = edma_get_position(echan->ecc, echan->slot[0], dst);
+
+	/*
+	 * "pos" may represent a transfer request that is still being
+	 * processed by the EDMACC or EDMATC. We will busy wait until
+	 * any one of the situations occurs:
+	 *   1. while and event is pending for the channel
+	 *   2. a position updated
+	 *   3. we hit the loop limit
+	 */
+	if (is_slave_direction(edesc->direction))
+		event_reg = SH_ER;
+	else
+		event_reg = SH_ESR;
+
+	pos_old = pos;
+	while (edma_shadow0_read_array(echan->ecc, event_reg, idx) & ch_bit) {
+		pos = edma_get_position(echan->ecc, echan->slot[0], dst);
+		if (pos != pos_old)
+			break;
+
+		if (!--loop_count) {
+			dev_dbg_ratelimited(echan->vchan.chan.device->dev,
+				"%s: timeout waiting for PaRAM update\n",
+				__func__);
+			break;
+		}
+
+		cpu_relax();
+	}
+
+	/*
+	 * Cyclic is simple. Just subtract pset[0].addr from pos.
+	 *
+	 * We never update edesc->residue in the cyclic case, so we
+	 * can tell the remaining room to the end of the circular
+	 * buffer.
+	 */
+	if (edesc->cyclic) {
+		done = pos - pset->addr;
+		edesc->residue_stat = edesc->residue - done;
+		return edesc->residue_stat;
+	}
+
+	/*
+	 * If the position is 0, then EDMA loaded the closing dummy slot, the
+	 * transfer is completed
+	 */
+	if (!pos)
+		return 0;
+	/*
+	 * For SG operation we catch up with the last processed
+	 * status.
+	 */
+	pset += edesc->processed_stat;
+
+	for (i = edesc->processed_stat; i < edesc->processed; i++, pset++) {
+		/*
+		 * If we are inside this pset address range, we know
+		 * this is the active one. Get the current delta and
+		 * stop walking the psets.
+		 */
+		if (pos >= pset->addr && pos < pset->addr + pset->len)
+			return edesc->residue_stat - (pos - pset->addr);
+
+		/* Otherwise mark it done and update residue_stat. */
+		edesc->processed_stat++;
+		edesc->residue_stat -= pset->len;
+	}
+	return edesc->residue_stat;
+}
+
+/* Check request completion status */
+static enum dma_status edma_tx_status(struct dma_chan *chan,
+				      dma_cookie_t cookie,
+				      struct dma_tx_state *txstate)
+{
+	struct edma_chan *echan = to_edma_chan(chan);
+	struct dma_tx_state txstate_tmp;
+	enum dma_status ret;
+	unsigned long flags;
+
+	ret = dma_cookie_status(chan, cookie, txstate);
+
+	if (ret == DMA_COMPLETE)
+		return ret;
+
+	/* Provide a dummy dma_tx_state for completion checking */
+	if (!txstate)
+		txstate = &txstate_tmp;
+
+	spin_lock_irqsave(&echan->vchan.lock, flags);
+	if (echan->edesc && echan->edesc->vdesc.tx.cookie == cookie) {
+		txstate->residue = edma_residue(echan->edesc);
+	} else {
+		struct virt_dma_desc *vdesc = vchan_find_desc(&echan->vchan,
+							      cookie);
+
+		if (vdesc)
+			txstate->residue = to_edma_desc(&vdesc->tx)->residue;
+		else
+			txstate->residue = 0;
+	}
+
+	/*
+	 * Mark the cookie completed if the residue is 0 for non cyclic
+	 * transfers
+	 */
+	if (ret != DMA_COMPLETE && !txstate->residue &&
+	    echan->edesc && echan->edesc->polled &&
+	    echan->edesc->vdesc.tx.cookie == cookie) {
+		edma_stop(echan);
+		vchan_cookie_complete(&echan->edesc->vdesc);
+		echan->edesc = NULL;
+		edma_execute(echan);
+		ret = DMA_COMPLETE;
+	}
+
+	spin_unlock_irqrestore(&echan->vchan.lock, flags);
+
+	return ret;
+}
+
+static bool edma_is_memcpy_channel(int ch_num, s32 *memcpy_channels)
+{
+	if (!memcpy_channels)
+		return false;
+	while (*memcpy_channels != -1) {
+		if (*memcpy_channels == ch_num)
+			return true;
+		memcpy_channels++;
+	}
+	return false;
+}
+
+#define EDMA_DMA_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))
+
+static void edma_dma_init(struct edma_cc *ecc, bool legacy_mode)
+{
+	struct dma_device *s_ddev = &ecc->dma_slave;
+	struct dma_device *m_ddev = NULL;
+	s32 *memcpy_channels = ecc->info->memcpy_channels;
+	int i, j;
+
+	dma_cap_zero(s_ddev->cap_mask);
+	dma_cap_set(DMA_SLAVE, s_ddev->cap_mask);
+	dma_cap_set(DMA_CYCLIC, s_ddev->cap_mask);
+	if (ecc->legacy_mode && !memcpy_channels) {
+		dev_warn(ecc->dev,
+			 "Legacy memcpy is enabled, things might not work\n");
+
+		dma_cap_set(DMA_MEMCPY, s_ddev->cap_mask);
+		dma_cap_set(DMA_INTERLEAVE, s_ddev->cap_mask);
+		s_ddev->device_prep_dma_memcpy = edma_prep_dma_memcpy;
+		s_ddev->device_prep_interleaved_dma = edma_prep_dma_interleaved;
+		s_ddev->directions = BIT(DMA_MEM_TO_MEM);
+	}
+
+	s_ddev->device_prep_slave_sg = edma_prep_slave_sg;
+	s_ddev->device_prep_dma_cyclic = edma_prep_dma_cyclic;
+	s_ddev->device_alloc_chan_resources = edma_alloc_chan_resources;
+	s_ddev->device_free_chan_resources = edma_free_chan_resources;
+	s_ddev->device_issue_pending = edma_issue_pending;
+	s_ddev->device_tx_status = edma_tx_status;
+	s_ddev->device_config = edma_slave_config;
+	s_ddev->device_pause = edma_dma_pause;
+	s_ddev->device_resume = edma_dma_resume;
+	s_ddev->device_terminate_all = edma_terminate_all;
+	s_ddev->device_synchronize = edma_synchronize;
+
+	s_ddev->src_addr_widths = EDMA_DMA_BUSWIDTHS;
+	s_ddev->dst_addr_widths = EDMA_DMA_BUSWIDTHS;
+	s_ddev->directions |= (BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV));
+	s_ddev->residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
+	s_ddev->max_burst = SZ_32K - 1; /* CIDX: 16bit signed */
+
+	s_ddev->dev = ecc->dev;
+	INIT_LIST_HEAD(&s_ddev->channels);
+
+	if (memcpy_channels) {
+		m_ddev = devm_kzalloc(ecc->dev, sizeof(*m_ddev), GFP_KERNEL);
+		if (!m_ddev) {
+			dev_warn(ecc->dev, "memcpy is disabled due to OoM\n");
+			memcpy_channels = NULL;
+			goto ch_setup;
+		}
+		ecc->dma_memcpy = m_ddev;
+
+		dma_cap_zero(m_ddev->cap_mask);
+		dma_cap_set(DMA_MEMCPY, m_ddev->cap_mask);
+		dma_cap_set(DMA_INTERLEAVE, m_ddev->cap_mask);
+
+		m_ddev->device_prep_dma_memcpy = edma_prep_dma_memcpy;
+		m_ddev->device_prep_interleaved_dma = edma_prep_dma_interleaved;
+		m_ddev->device_alloc_chan_resources = edma_alloc_chan_resources;
+		m_ddev->device_free_chan_resources = edma_free_chan_resources;
+		m_ddev->device_issue_pending = edma_issue_pending;
+		m_ddev->device_tx_status = edma_tx_status;
+		m_ddev->device_config = edma_slave_config;
+		m_ddev->device_pause = edma_dma_pause;
+		m_ddev->device_resume = edma_dma_resume;
+		m_ddev->device_terminate_all = edma_terminate_all;
+		m_ddev->device_synchronize = edma_synchronize;
+
+		m_ddev->src_addr_widths = EDMA_DMA_BUSWIDTHS;
+		m_ddev->dst_addr_widths = EDMA_DMA_BUSWIDTHS;
+		m_ddev->directions = BIT(DMA_MEM_TO_MEM);
+		m_ddev->residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
+
+		m_ddev->dev = ecc->dev;
+		INIT_LIST_HEAD(&m_ddev->channels);
+	} else if (!ecc->legacy_mode) {
+		dev_info(ecc->dev, "memcpy is disabled\n");
+	}
+
+ch_setup:
+	for (i = 0; i < ecc->num_channels; i++) {
+		struct edma_chan *echan = &ecc->slave_chans[i];
+		echan->ch_num = EDMA_CTLR_CHAN(ecc->id, i);
+		echan->ecc = ecc;
+		echan->vchan.desc_free = edma_desc_free;
+
+		if (m_ddev && edma_is_memcpy_channel(i, memcpy_channels))
+			vchan_init(&echan->vchan, m_ddev);
+		else
+			vchan_init(&echan->vchan, s_ddev);
+
+		INIT_LIST_HEAD(&echan->node);
+		for (j = 0; j < EDMA_MAX_SLOTS; j++)
+			echan->slot[j] = -1;
+	}
+}
+
+static int edma_setup_from_hw(struct device *dev, struct edma_soc_info *pdata,
+			      struct edma_cc *ecc)
+{
+	int i;
+	u32 value, cccfg;
+	s8 (*queue_priority_map)[2];
+
+	/* Decode the eDMA3 configuration from CCCFG register */
+	cccfg = edma_read(ecc, EDMA_CCCFG);
+
+	value = GET_NUM_REGN(cccfg);
+	ecc->num_region = BIT(value);
+
+	value = GET_NUM_DMACH(cccfg);
+	ecc->num_channels = BIT(value + 1);
+
+	value = GET_NUM_QDMACH(cccfg);
+	ecc->num_qchannels = value * 2;
+
+	value = GET_NUM_PAENTRY(cccfg);
+	ecc->num_slots = BIT(value + 4);
+
+	value = GET_NUM_EVQUE(cccfg);
+	ecc->num_tc = value + 1;
+
+	ecc->chmap_exist = (cccfg & CHMAP_EXIST) ? true : false;
+
+	dev_dbg(dev, "eDMA3 CC HW configuration (cccfg: 0x%08x):\n", cccfg);
+	dev_dbg(dev, "num_region: %u\n", ecc->num_region);
+	dev_dbg(dev, "num_channels: %u\n", ecc->num_channels);
+	dev_dbg(dev, "num_qchannels: %u\n", ecc->num_qchannels);
+	dev_dbg(dev, "num_slots: %u\n", ecc->num_slots);
+	dev_dbg(dev, "num_tc: %u\n", ecc->num_tc);
+	dev_dbg(dev, "chmap_exist: %s\n", ecc->chmap_exist ? "yes" : "no");
+
+	/* Nothing need to be done if queue priority is provided */
+	if (pdata->queue_priority_mapping)
+		return 0;
+
+	/*
+	 * Configure TC/queue priority as follows:
+	 * Q0 - priority 0
+	 * Q1 - priority 1
+	 * Q2 - priority 2
+	 * ...
+	 * The meaning of priority numbers: 0 highest priority, 7 lowest
+	 * priority. So Q0 is the highest priority queue and the last queue has
+	 * the lowest priority.
+	 */
+	queue_priority_map = devm_kcalloc(dev, ecc->num_tc + 1, sizeof(s8),
+					  GFP_KERNEL);
+	if (!queue_priority_map)
+		return -ENOMEM;
+
+	for (i = 0; i < ecc->num_tc; i++) {
+		queue_priority_map[i][0] = i;
+		queue_priority_map[i][1] = i;
+	}
+	queue_priority_map[i][0] = -1;
+	queue_priority_map[i][1] = -1;
+
+	pdata->queue_priority_mapping = queue_priority_map;
+	/* Default queue has the lowest priority */
+	pdata->default_queue = i - 1;
+
+	return 0;
+}
+
+#if IS_ENABLED(CONFIG_OF)
+static int edma_xbar_event_map(struct device *dev, struct edma_soc_info *pdata,
+			       size_t sz)
+{
+	const char pname[] = "ti,edma-xbar-event-map";
+	struct resource res;
+	void __iomem *xbar;
+	s16 (*xbar_chans)[2];
+	size_t nelm = sz / sizeof(s16);
+	u32 shift, offset, mux;
+	int ret, i;
+
+	xbar_chans = devm_kcalloc(dev, nelm + 2, sizeof(s16), GFP_KERNEL);
+	if (!xbar_chans)
+		return -ENOMEM;
+
+	ret = of_address_to_resource(dev->of_node, 1, &res);
+	if (ret)
+		return -ENOMEM;
+
+	xbar = devm_ioremap(dev, res.start, resource_size(&res));
+	if (!xbar)
+		return -ENOMEM;
+
+	ret = of_property_read_u16_array(dev->of_node, pname, (u16 *)xbar_chans,
+					 nelm);
+	if (ret)
+		return -EIO;
+
+	/* Invalidate last entry for the other user of this mess */
+	nelm >>= 1;
+	xbar_chans[nelm][0] = -1;
+	xbar_chans[nelm][1] = -1;
+
+	for (i = 0; i < nelm; i++) {
+		shift = (xbar_chans[i][1] & 0x03) << 3;
+		offset = xbar_chans[i][1] & 0xfffffffc;
+		mux = readl(xbar + offset);
+		mux &= ~(0xff << shift);
+		mux |= xbar_chans[i][0] << shift;
+		writel(mux, (xbar + offset));
+	}
+
+	pdata->xbar_chans = (const s16 (*)[2]) xbar_chans;
+	return 0;
+}
+
+static struct edma_soc_info *edma_setup_info_from_dt(struct device *dev,
+						     bool legacy_mode)
+{
+	struct edma_soc_info *info;
+	struct property *prop;
+	int sz, ret;
+
+	info = devm_kzalloc(dev, sizeof(struct edma_soc_info), GFP_KERNEL);
+	if (!info)
+		return ERR_PTR(-ENOMEM);
+
+	if (legacy_mode) {
+		prop = of_find_property(dev->of_node, "ti,edma-xbar-event-map",
+					&sz);
+		if (prop) {
+			ret = edma_xbar_event_map(dev, info, sz);
+			if (ret)
+				return ERR_PTR(ret);
+		}
+		return info;
+	}
+
+	/* Get the list of channels allocated to be used for memcpy */
+	prop = of_find_property(dev->of_node, "ti,edma-memcpy-channels", &sz);
+	if (prop) {
+		const char pname[] = "ti,edma-memcpy-channels";
+		size_t nelm = sz / sizeof(s32);
+		s32 *memcpy_ch;
+
+		memcpy_ch = devm_kcalloc(dev, nelm + 1, sizeof(s32),
+					 GFP_KERNEL);
+		if (!memcpy_ch)
+			return ERR_PTR(-ENOMEM);
+
+		ret = of_property_read_u32_array(dev->of_node, pname,
+						 (u32 *)memcpy_ch, nelm);
+		if (ret)
+			return ERR_PTR(ret);
+
+		memcpy_ch[nelm] = -1;
+		info->memcpy_channels = memcpy_ch;
+	}
+
+	prop = of_find_property(dev->of_node, "ti,edma-reserved-slot-ranges",
+				&sz);
+	if (prop) {
+		const char pname[] = "ti,edma-reserved-slot-ranges";
+		u32 (*tmp)[2];
+		s16 (*rsv_slots)[2];
+		size_t nelm = sz / sizeof(*tmp);
+		struct edma_rsv_info *rsv_info;
+		int i;
+
+		if (!nelm)
+			return info;
+
+		tmp = kcalloc(nelm, sizeof(*tmp), GFP_KERNEL);
+		if (!tmp)
+			return ERR_PTR(-ENOMEM);
+
+		rsv_info = devm_kzalloc(dev, sizeof(*rsv_info), GFP_KERNEL);
+		if (!rsv_info) {
+			kfree(tmp);
+			return ERR_PTR(-ENOMEM);
+		}
+
+		rsv_slots = devm_kcalloc(dev, nelm + 1, sizeof(*rsv_slots),
+					 GFP_KERNEL);
+		if (!rsv_slots) {
+			kfree(tmp);
+			return ERR_PTR(-ENOMEM);
+		}
+
+		ret = of_property_read_u32_array(dev->of_node, pname,
+						 (u32 *)tmp, nelm * 2);
+		if (ret) {
+			kfree(tmp);
+			return ERR_PTR(ret);
+		}
+
+		for (i = 0; i < nelm; i++) {
+			rsv_slots[i][0] = tmp[i][0];
+			rsv_slots[i][1] = tmp[i][1];
+		}
+		rsv_slots[nelm][0] = -1;
+		rsv_slots[nelm][1] = -1;
+
+		info->rsv = rsv_info;
+		info->rsv->rsv_slots = (const s16 (*)[2])rsv_slots;
+
+		kfree(tmp);
+	}
+
+	return info;
+}
+
+static struct dma_chan *of_edma_xlate(struct of_phandle_args *dma_spec,
+				      struct of_dma *ofdma)
+{
+	struct edma_cc *ecc = ofdma->of_dma_data;
+	struct dma_chan *chan = NULL;
+	struct edma_chan *echan;
+	int i;
+
+	if (!ecc || dma_spec->args_count < 1)
+		return NULL;
+
+	for (i = 0; i < ecc->num_channels; i++) {
+		echan = &ecc->slave_chans[i];
+		if (echan->ch_num == dma_spec->args[0]) {
+			chan = &echan->vchan.chan;
+			break;
+		}
+	}
+
+	if (!chan)
+		return NULL;
+
+	if (echan->ecc->legacy_mode && dma_spec->args_count == 1)
+		goto out;
+
+	if (!echan->ecc->legacy_mode && dma_spec->args_count == 2 &&
+	    dma_spec->args[1] < echan->ecc->num_tc) {
+		echan->tc = &echan->ecc->tc_list[dma_spec->args[1]];
+		goto out;
+	}
+
+	return NULL;
+out:
+	/* The channel is going to be used as HW synchronized */
+	echan->hw_triggered = true;
+	return dma_get_slave_channel(chan);
+}
+#else
+static struct edma_soc_info *edma_setup_info_from_dt(struct device *dev,
+						     bool legacy_mode)
+{
+	return ERR_PTR(-EINVAL);
+}
+
+static struct dma_chan *of_edma_xlate(struct of_phandle_args *dma_spec,
+				      struct of_dma *ofdma)
+{
+	return NULL;
+}
+#endif
+
+static bool edma_filter_fn(struct dma_chan *chan, void *param);
+
+static int edma_probe(struct platform_device *pdev)
+{
+	struct edma_soc_info	*info = pdev->dev.platform_data;
+	s8			(*queue_priority_mapping)[2];
+	const s16		(*reserved)[2];
+	int			i, irq;
+	char			*irq_name;
+	struct resource		*mem;
+	struct device_node	*node = pdev->dev.of_node;
+	struct device		*dev = &pdev->dev;
+	struct edma_cc		*ecc;
+	bool			legacy_mode = true;
+	int ret;
+
+	if (node) {
+		const struct of_device_id *match;
+
+		match = of_match_node(edma_of_ids, node);
+		if (match && (*(u32 *)match->data) == EDMA_BINDING_TPCC)
+			legacy_mode = false;
+
+		info = edma_setup_info_from_dt(dev, legacy_mode);
+		if (IS_ERR(info)) {
+			dev_err(dev, "failed to get DT data\n");
+			return PTR_ERR(info);
+		}
+	}
+
+	if (!info)
+		return -ENODEV;
+
+	ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32));
+	if (ret)
+		return ret;
+
+	ecc = devm_kzalloc(dev, sizeof(*ecc), GFP_KERNEL);
+	if (!ecc)
+		return -ENOMEM;
+
+	ecc->dev = dev;
+	ecc->id = pdev->id;
+	ecc->legacy_mode = legacy_mode;
+	/* When booting with DT the pdev->id is -1 */
+	if (ecc->id < 0)
+		ecc->id = 0;
+
+	mem = platform_get_resource_byname(pdev, IORESOURCE_MEM, "edma3_cc");
+	if (!mem) {
+		dev_dbg(dev, "mem resource not found, using index 0\n");
+		mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+		if (!mem) {
+			dev_err(dev, "no mem resource?\n");
+			return -ENODEV;
+		}
+	}
+	ecc->base = devm_ioremap_resource(dev, mem);
+	if (IS_ERR(ecc->base))
+		return PTR_ERR(ecc->base);
+
+	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)
+		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);
+
+	ecc->slot_inuse = devm_kcalloc(dev, BITS_TO_LONGS(ecc->num_slots),
+				       sizeof(unsigned long), GFP_KERNEL);
+
+	ecc->channels_mask = devm_kcalloc(dev,
+					   BITS_TO_LONGS(ecc->num_channels),
+					   sizeof(unsigned long), GFP_KERNEL);
+	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);
+
+	ecc->default_queue = info->default_queue;
+
+	if (info->rsv) {
+		/* Set the reserved slots in inuse list */
+		reserved = info->rsv->rsv_slots;
+		if (reserved) {
+			for (i = 0; reserved[i][0] != -1; i++)
+				bitmap_set(ecc->slot_inuse, reserved[i][0],
+					   reserved[i][1]);
+		}
+
+		/* Clear channels not usable for Linux */
+		reserved = info->rsv->rsv_chans;
+		if (reserved) {
+			for (i = 0; reserved[i][0] != -1; i++)
+				bitmap_clear(ecc->channels_mask, reserved[i][0],
+					     reserved[i][1]);
+		}
+	}
+
+	for (i = 0; i < ecc->num_slots; i++) {
+		/* Reset only unused - not reserved - paRAM slots */
+		if (!test_bit(i, ecc->slot_inuse))
+			edma_write_slot(ecc, i, &dummy_paramset);
+	}
+
+	irq = platform_get_irq_byname(pdev, "edma3_ccint");
+	if (irq < 0 && node)
+		irq = irq_of_parse_and_map(node, 0);
+
+	if (irq > 0) {
+		irq_name = devm_kasprintf(dev, GFP_KERNEL, "%s_ccint",
+					  dev_name(dev));
+		ret = devm_request_irq(dev, irq, dma_irq_handler, 0, irq_name,
+				       ecc);
+		if (ret) {
+			dev_err(dev, "CCINT (%d) failed --> %d\n", irq, ret);
+			goto err_disable_pm;
+		}
+		ecc->ccint = irq;
+	}
+
+	irq = platform_get_irq_byname(pdev, "edma3_ccerrint");
+	if (irq < 0 && node)
+		irq = irq_of_parse_and_map(node, 2);
+
+	if (irq > 0) {
+		irq_name = devm_kasprintf(dev, GFP_KERNEL, "%s_ccerrint",
+					  dev_name(dev));
+		ret = devm_request_irq(dev, irq, dma_ccerr_handler, 0, irq_name,
+				       ecc);
+		if (ret) {
+			dev_err(dev, "CCERRINT (%d) failed --> %d\n", irq, ret);
+			goto err_disable_pm;
+		}
+		ecc->ccerrint = irq;
+	}
+
+	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");
+		ret = ecc->dummy_slot;
+		goto err_disable_pm;
+	}
+
+	queue_priority_mapping = info->queue_priority_mapping;
+
+	if (!ecc->legacy_mode) {
+		int lowest_priority = 0;
+		unsigned int array_max;
+		struct of_phandle_args tc_args;
+
+		ecc->tc_list = devm_kcalloc(dev, ecc->num_tc,
+					    sizeof(*ecc->tc_list), GFP_KERNEL);
+		if (!ecc->tc_list) {
+			ret = -ENOMEM;
+			goto err_reg1;
+		}
+
+		for (i = 0;; i++) {
+			ret = of_parse_phandle_with_fixed_args(node, "ti,tptcs",
+							       1, i, &tc_args);
+			if (ret || i == ecc->num_tc)
+				break;
+
+			ecc->tc_list[i].node = tc_args.np;
+			ecc->tc_list[i].id = i;
+			queue_priority_mapping[i][1] = tc_args.args[0];
+			if (queue_priority_mapping[i][1] > lowest_priority) {
+				lowest_priority = queue_priority_mapping[i][1];
+				info->default_queue = i;
+			}
+		}
+
+		/* See if we have optional dma-channel-mask array */
+		array_max = DIV_ROUND_UP(ecc->num_channels, BITS_PER_TYPE(u32));
+		ret = of_property_read_variable_u32_array(node,
+						"dma-channel-mask",
+						(u32 *)ecc->channels_mask,
+						1, array_max);
+		if (ret > 0 && ret != array_max)
+			dev_warn(dev, "dma-channel-mask is not complete.\n");
+		else if (ret == -EOVERFLOW || ret == -ENODATA)
+			dev_warn(dev,
+				 "dma-channel-mask is out of range or empty\n");
+	}
+
+	/* Event queue priority mapping */
+	for (i = 0; queue_priority_mapping[i][0] != -1; i++)
+		edma_assign_priority_to_queue(ecc, queue_priority_mapping[i][0],
+					      queue_priority_mapping[i][1]);
+
+	edma_write_array2(ecc, EDMA_DRAE, 0, 0, 0x0);
+	edma_write_array2(ecc, EDMA_DRAE, 0, 1, 0x0);
+	edma_write_array(ecc, EDMA_QRAE, 0, 0x0);
+
+	ecc->info = info;
+
+	/* Init the dma device and channels */
+	edma_dma_init(ecc, legacy_mode);
+
+	for (i = 0; i < ecc->num_channels; i++) {
+		/* Do not touch reserved channels */
+		if (!test_bit(i, ecc->channels_mask))
+			continue;
+
+		/* Assign all channels to the default queue */
+		edma_assign_channel_eventq(&ecc->slave_chans[i],
+					   info->default_queue);
+		/* Set entry slot to the dummy slot */
+		edma_set_chmap(&ecc->slave_chans[i], ecc->dummy_slot);
+	}
+
+	ecc->dma_slave.filter.map = info->slave_map;
+	ecc->dma_slave.filter.mapcnt = info->slavecnt;
+	ecc->dma_slave.filter.fn = edma_filter_fn;
+
+	ret = dma_async_device_register(&ecc->dma_slave);
+	if (ret) {
+		dev_err(dev, "slave ddev registration failed (%d)\n", ret);
+		goto err_reg1;
+	}
+
+	if (ecc->dma_memcpy) {
+		ret = dma_async_device_register(ecc->dma_memcpy);
+		if (ret) {
+			dev_err(dev, "memcpy ddev registration failed (%d)\n",
+				ret);
+			dma_async_device_unregister(&ecc->dma_slave);
+			goto err_reg1;
+		}
+	}
+
+	if (node)
+		of_dma_controller_register(node, of_edma_xlate, ecc);
+
+	dev_info(dev, "TI EDMA DMA engine driver\n");
+
+	return 0;
+
+err_reg1:
+	edma_free_slot(ecc, ecc->dummy_slot);
+err_disable_pm:
+	pm_runtime_put_sync(dev);
+	pm_runtime_disable(dev);
+	return ret;
+}
+
+static void edma_cleanupp_vchan(struct dma_device *dmadev)
+{
+	struct edma_chan *echan, *_echan;
+
+	list_for_each_entry_safe(echan, _echan,
+			&dmadev->channels, vchan.chan.device_node) {
+		list_del(&echan->vchan.chan.device_node);
+		tasklet_kill(&echan->vchan.task);
+	}
+}
+
+static int edma_remove(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct edma_cc *ecc = dev_get_drvdata(dev);
+
+	devm_free_irq(dev, ecc->ccint, ecc);
+	devm_free_irq(dev, ecc->ccerrint, ecc);
+
+	edma_cleanupp_vchan(&ecc->dma_slave);
+
+	if (dev->of_node)
+		of_dma_controller_free(dev->of_node);
+	dma_async_device_unregister(&ecc->dma_slave);
+	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;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int edma_pm_suspend(struct device *dev)
+{
+	struct edma_cc *ecc = dev_get_drvdata(dev);
+	struct edma_chan *echan = ecc->slave_chans;
+	int i;
+
+	for (i = 0; i < ecc->num_channels; i++) {
+		if (echan[i].alloced)
+			edma_setup_interrupt(&echan[i], false);
+	}
+
+	return 0;
+}
+
+static int edma_pm_resume(struct device *dev)
+{
+	struct edma_cc *ecc = dev_get_drvdata(dev);
+	struct edma_chan *echan = ecc->slave_chans;
+	int i;
+	s8 (*queue_priority_mapping)[2];
+
+	/* re initialize dummy slot to dummy param set */
+	edma_write_slot(ecc, ecc->dummy_slot, &dummy_paramset);
+
+	queue_priority_mapping = ecc->info->queue_priority_mapping;
+
+	/* Event queue priority mapping */
+	for (i = 0; queue_priority_mapping[i][0] != -1; i++)
+		edma_assign_priority_to_queue(ecc, queue_priority_mapping[i][0],
+					      queue_priority_mapping[i][1]);
+
+	for (i = 0; i < ecc->num_channels; i++) {
+		if (echan[i].alloced) {
+			/* ensure access through shadow region 0 */
+			edma_or_array2(ecc, EDMA_DRAE, 0,
+				       EDMA_REG_ARRAY_INDEX(i),
+				       EDMA_CHANNEL_BIT(i));
+
+			edma_setup_interrupt(&echan[i], true);
+
+			/* Set up channel -> slot mapping for the entry slot */
+			edma_set_chmap(&echan[i], echan[i].slot[0]);
+		}
+	}
+
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops edma_pm_ops = {
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(edma_pm_suspend, edma_pm_resume)
+};
+
+static struct platform_driver edma_driver = {
+	.probe		= edma_probe,
+	.remove		= edma_remove,
+	.driver = {
+		.name	= "edma",
+		.pm	= &edma_pm_ops,
+		.of_match_table = edma_of_ids,
+	},
+};
+
+static int edma_tptc_probe(struct platform_device *pdev)
+{
+	pm_runtime_enable(&pdev->dev);
+	return pm_runtime_get_sync(&pdev->dev);
+}
+
+static struct platform_driver edma_tptc_driver = {
+	.probe		= edma_tptc_probe,
+	.driver = {
+		.name	= "edma3-tptc",
+		.of_match_table = edma_tptc_of_ids,
+	},
+};
+
+static bool edma_filter_fn(struct dma_chan *chan, void *param)
+{
+	bool match = false;
+
+	if (chan->device->dev->driver == &edma_driver.driver) {
+		struct edma_chan *echan = to_edma_chan(chan);
+		unsigned ch_req = *(unsigned *)param;
+		if (ch_req == echan->ch_num) {
+			/* The channel is going to be used as HW synchronized */
+			echan->hw_triggered = true;
+			match = true;
+		}
+	}
+	return match;
+}
+
+static int edma_init(void)
+{
+	int ret;
+
+	ret = platform_driver_register(&edma_tptc_driver);
+	if (ret)
+		return ret;
+
+	return platform_driver_register(&edma_driver);
+}
+subsys_initcall(edma_init);
+
+static void __exit edma_exit(void)
+{
+	platform_driver_unregister(&edma_driver);
+	platform_driver_unregister(&edma_tptc_driver);
+}
+module_exit(edma_exit);
+
+MODULE_AUTHOR("Matt Porter <matt.porter@linaro.org>");
+MODULE_DESCRIPTION("TI EDMA DMA engine driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/ti/k3-psil-am654.c b/drivers/dma/ti/k3-psil-am654.c
new file mode 100644
index 000000000..a896a1590
--- /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-j7200.c b/drivers/dma/ti/k3-psil-j7200.c
new file mode 100644
index 000000000..5ea63ea74
--- /dev/null
+++ b/drivers/dma/ti/k3-psil-j7200.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_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 j7200_src_ep_map[] = {
+	/* PDMA_MCASP - McASP0-2 */
+	PSIL_PDMA_MCASP(0x4400),
+	PSIL_PDMA_MCASP(0x4401),
+	PSIL_PDMA_MCASP(0x4402),
+	/* PDMA_SPI_G0 - SPI0-3 */
+	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),
+	PSIL_PDMA_XY_PKT(0x4608),
+	PSIL_PDMA_XY_PKT(0x4609),
+	PSIL_PDMA_XY_PKT(0x460a),
+	PSIL_PDMA_XY_PKT(0x460b),
+	PSIL_PDMA_XY_PKT(0x460c),
+	PSIL_PDMA_XY_PKT(0x460d),
+	PSIL_PDMA_XY_PKT(0x460e),
+	PSIL_PDMA_XY_PKT(0x460f),
+	/* PDMA_SPI_G1 - SPI4-7 */
+	PSIL_PDMA_XY_PKT(0x4610),
+	PSIL_PDMA_XY_PKT(0x4611),
+	PSIL_PDMA_XY_PKT(0x4612),
+	PSIL_PDMA_XY_PKT(0x4613),
+	PSIL_PDMA_XY_PKT(0x4614),
+	PSIL_PDMA_XY_PKT(0x4615),
+	PSIL_PDMA_XY_PKT(0x4616),
+	PSIL_PDMA_XY_PKT(0x4617),
+	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),
+	/* PDMA_USART_G0 - UART0-1 */
+	PSIL_PDMA_XY_PKT(0x4700),
+	PSIL_PDMA_XY_PKT(0x4701),
+	/* PDMA_USART_G1 - UART2-3 */
+	PSIL_PDMA_XY_PKT(0x4702),
+	PSIL_PDMA_XY_PKT(0x4703),
+	/* 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),
+	/* CPSW5 */
+	PSIL_ETHERNET(0x4a00),
+	/* CPSW0 */
+	PSIL_ETHERNET(0x7000),
+	/* 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_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_PDMA_MISC_G2 - UART0 */
+	PSIL_PDMA_XY_PKT(0x7300),
+	/* MCU_PDMA_ADC - ADC0-1 */
+	PSIL_PDMA_XY_TR(0x7400),
+	PSIL_PDMA_XY_TR(0x7401),
+	/* SA2UL */
+	PSIL_SA2UL(0x7500, 0),
+	PSIL_SA2UL(0x7501, 0),
+	PSIL_SA2UL(0x7502, 0),
+	PSIL_SA2UL(0x7503, 0),
+};
+
+/* PSI-L destination thread IDs, used for TX (DMA_MEM_TO_DEV) */
+static struct psil_ep j7200_dst_ep_map[] = {
+	/* CPSW5 */
+	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),
+	PSIL_SA2UL(0xf501, 1),
+};
+
+struct psil_ep_map j7200_ep_map = {
+	.name = "j7200",
+	.src = j7200_src_ep_map,
+	.src_count = ARRAY_SIZE(j7200_src_ep_map),
+	.dst = j7200_dst_ep_map,
+	.dst_count = ARRAY_SIZE(j7200_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 000000000..7580870ed
--- /dev/null
+++ b/drivers/dma/ti/k3-psil-j721e.c
@@ -0,0 +1,225 @@
+// 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),
+	PSIL_SA2UL(0x7502, 0),
+	PSIL_SA2UL(0x7503, 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),
+	PSIL_SA2UL(0xf501, 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 000000000..b4b0fb359
--- /dev/null
+++ b/drivers/dma/ti/k3-psil-priv.h
@@ -0,0 +1,44 @@
+/* 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;
+extern struct psil_ep_map j7200_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 000000000..837853aab
--- /dev/null
+++ b/drivers/dma/ti/k3-psil.c
@@ -0,0 +1,100 @@
+// 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 <linux/sys_soc.h>
+
+#include "k3-psil-priv.h"
+
+static DEFINE_MUTEX(ep_map_mutex);
+static const struct psil_ep_map *soc_ep_map;
+
+static const struct soc_device_attribute k3_soc_devices[] = {
+	{ .family = "AM65X", .data = &am654_ep_map },
+	{ .family = "J721E", .data = &j721e_ep_map },
+	{ .family = "J7200", .data = &j7200_ep_map },
+	{ /* sentinel */ }
+};
+
+struct psil_endpoint_config *psil_get_ep_config(u32 thread_id)
+{
+	int i;
+
+	mutex_lock(&ep_map_mutex);
+	if (!soc_ep_map) {
+		const struct soc_device_attribute *soc;
+
+		soc = soc_device_match(k3_soc_devices);
+		if (soc) {
+			soc_ep_map = soc->data;
+		} else {
+			pr_err("PSIL: No compatible machine found for map\n");
+			mutex_unlock(&ep_map_mutex);
+			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 000000000..a367584f0
--- /dev/null
+++ b/drivers/dma/ti/k3-udma-glue.c
@@ -0,0 +1,1191 @@
+// 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;
+	u32  atype;
+};
+
+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 (dma_spec.args_count == 2) {
+		if (dma_spec.args[1] > 2) {
+			dev_err(common->dev, "Invalid channel atype: %u\n",
+				dma_spec.args[1]);
+			ret = -EINVAL;
+			goto out_put_spec;
+		}
+		common->atype = dma_spec.args[1];
+	}
+
+	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_CHAN_RT_CTL_REG,
+		xudma_tchanrt_read(chn->udma_tchanx, UDMA_CHAN_RT_CTL_REG));
+	dev_dbg(dev, "0x%08X: %08X\n", UDMA_CHAN_RT_PEER_RT_EN_REG,
+		xudma_tchanrt_read(chn->udma_tchanx,
+				   UDMA_CHAN_RT_PEER_RT_EN_REG));
+	dev_dbg(dev, "0x%08X: %08X\n", UDMA_CHAN_RT_PCNT_REG,
+		xudma_tchanrt_read(chn->udma_tchanx, UDMA_CHAN_RT_PCNT_REG));
+	dev_dbg(dev, "0x%08X: %08X\n", UDMA_CHAN_RT_BCNT_REG,
+		xudma_tchanrt_read(chn->udma_tchanx, UDMA_CHAN_RT_BCNT_REG));
+	dev_dbg(dev, "0x%08X: %08X\n", UDMA_CHAN_RT_SBCNT_REG,
+		xudma_tchanrt_read(chn->udma_tchanx, UDMA_CHAN_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 |
+			TI_SCI_MSG_VALUE_RM_UDMAP_CH_ATYPE_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);
+	req.tx_atype = tx_chn->common.atype;
+
+	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 */
+	ret =  k3_ringacc_request_rings_pair(tx_chn->common.ringacc,
+					     tx_chn->udma_tchan_id, -1,
+					     &tx_chn->ringtx,
+					     &tx_chn->ringtxcq);
+	if (ret) {
+		dev_err(dev, "Failed to get TX/TXCQ rings %d\n", ret);
+		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)
+{
+	xudma_tchanrt_write(tx_chn->udma_tchanx, UDMA_CHAN_RT_PEER_RT_EN_REG,
+			    UDMA_PEER_RT_EN_ENABLE);
+
+	xudma_tchanrt_write(tx_chn->udma_tchanx, UDMA_CHAN_RT_CTL_REG,
+			    UDMA_CHAN_RT_CTL_EN);
+
+	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_CHAN_RT_CTL_REG, 0);
+
+	xudma_tchanrt_write(tx_chn->udma_tchanx,
+			    UDMA_CHAN_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_CHAN_RT_CTL_REG,
+			    UDMA_CHAN_RT_CTL_EN | UDMA_CHAN_RT_CTL_TDOWN);
+
+	val = xudma_tchanrt_read(tx_chn->udma_tchanx, UDMA_CHAN_RT_CTL_REG);
+
+	while (sync && (val & UDMA_CHAN_RT_CTL_EN)) {
+		val = xudma_tchanrt_read(tx_chn->udma_tchanx,
+					 UDMA_CHAN_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_CHAN_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 |
+			   TI_SCI_MSG_VALUE_RM_UDMAP_CH_ATYPE_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;
+	req.rx_atype = rx_chn->common.atype;
+
+	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 */
+	ret =  k3_ringacc_request_rings_pair(rx_chn->common.ringacc,
+					     flow_cfg->ring_rxfdq0_id,
+					     flow_cfg->ring_rxq_id,
+					     &flow->ringrxfdq,
+					     &flow->ringrx);
+	if (ret) {
+		dev_err(dev, "Failed to get RX/RXFDQ rings %d\n", ret);
+		goto err_rflow_put;
+	}
+
+	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);
+	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_CHAN_RT_CTL_REG,
+		xudma_rchanrt_read(chn->udma_rchanx, UDMA_CHAN_RT_CTL_REG));
+	dev_dbg(dev, "0x%08X: %08X\n", UDMA_CHAN_RT_PEER_RT_EN_REG,
+		xudma_rchanrt_read(chn->udma_rchanx,
+				   UDMA_CHAN_RT_PEER_RT_EN_REG));
+	dev_dbg(dev, "0x%08X: %08X\n", UDMA_CHAN_RT_PCNT_REG,
+		xudma_rchanrt_read(chn->udma_rchanx, UDMA_CHAN_RT_PCNT_REG));
+	dev_dbg(dev, "0x%08X: %08X\n", UDMA_CHAN_RT_BCNT_REG,
+		xudma_rchanrt_read(chn->udma_rchanx, UDMA_CHAN_RT_BCNT_REG));
+	dev_dbg(dev, "0x%08X: %08X\n", UDMA_CHAN_RT_SBCNT_REG,
+		xudma_rchanrt_read(chn->udma_rchanx, UDMA_CHAN_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)
+{
+	if (rx_chn->remote)
+		return -EINVAL;
+
+	if (rx_chn->flows_ready < rx_chn->flow_num)
+		return -EINVAL;
+
+	xudma_rchanrt_write(rx_chn->udma_rchanx, UDMA_CHAN_RT_CTL_REG,
+			    UDMA_CHAN_RT_CTL_EN);
+
+	xudma_rchanrt_write(rx_chn->udma_rchanx, UDMA_CHAN_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_CHAN_RT_PEER_RT_EN_REG, 0);
+	xudma_rchanrt_write(rx_chn->udma_rchanx, UDMA_CHAN_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_CHAN_RT_PEER_RT_EN_REG,
+			    UDMA_PEER_RT_EN_ENABLE | UDMA_PEER_RT_EN_TEARDOWN);
+
+	val = xudma_rchanrt_read(rx_chn->udma_rchanx, UDMA_CHAN_RT_CTL_REG);
+
+	while (sync && (val & UDMA_CHAN_RT_CTL_EN)) {
+		val = xudma_rchanrt_read(rx_chn->udma_rchanx,
+					 UDMA_CHAN_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_CHAN_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 000000000..dadab2fec
--- /dev/null
+++ b/drivers/dma/ti/k3-udma-private.c
@@ -0,0 +1,138 @@
+// 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 (np != udma_node)
+		of_node_put(udma_node);
+
+	if (!pdev) {
+		pr_debug("UDMA device not found\n");
+		return ERR_PTR(-EPROBE_DEFER);
+	}
+
+	ud = platform_get_drvdata(pdev);
+	if (!ud) {
+		pr_debug("UDMA has not been probed\n");
+		put_device(&pdev->dev);
+		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, UDMA_TP_NORMAL, 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)			\
+{									\
+	if (!p)								\
+		return 0;						\
+	return udma_read(p->reg_rt, reg);				\
+}									\
+EXPORT_SYMBOL(xudma_##res##rt_read);					\
+									\
+void xudma_##res##rt_write(struct udma_##res *p, int reg, u32 val)	\
+{									\
+	if (!p)								\
+		return;							\
+	udma_write(p->reg_rt, 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 000000000..d3902784c
--- /dev/null
+++ b/drivers/dma/ti/k3-udma.c
@@ -0,0 +1,3699 @@
+// 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/sys_soc.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;
+};
+
+struct udma_soc_data {
+	u32 rchan_oes_offset;
+};
+
+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;
+	const struct udma_soc_data *soc_data;
+
+	u8 tpl_levels;
+	u32 tpl_start_idx[3];
+
+	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;
+	u32 atype;
+};
+
+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[];
+};
+
+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 atype;
+	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 */
+
+	/* 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_chan *uc, int reg)
+{
+	if (!uc->tchan)
+		return 0;
+	return udma_read(uc->tchan->reg_rt, reg);
+}
+
+static inline void udma_tchanrt_write(struct udma_chan *uc, int reg, u32 val)
+{
+	if (!uc->tchan)
+		return;
+	udma_write(uc->tchan->reg_rt, reg, val);
+}
+
+static inline void udma_tchanrt_update_bits(struct udma_chan *uc, int reg,
+					    u32 mask, u32 val)
+{
+	if (!uc->tchan)
+		return;
+	udma_update_bits(uc->tchan->reg_rt, reg, mask, val);
+}
+
+/* RCHANRT */
+static inline u32 udma_rchanrt_read(struct udma_chan *uc, int reg)
+{
+	if (!uc->rchan)
+		return 0;
+	return udma_read(uc->rchan->reg_rt, reg);
+}
+
+static inline void udma_rchanrt_write(struct udma_chan *uc, int reg, u32 val)
+{
+	if (!uc->rchan)
+		return;
+	udma_write(uc->rchan->reg_rt, reg, val);
+}
+
+static inline void udma_rchanrt_update_bits(struct udma_chan *uc, int reg,
+					    u32 mask, u32 val)
+{
+	if (!uc->rchan)
+		return;
+	udma_update_bits(uc->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_CHAN_RT_STDATA_REG + i * 4;
+			dev_dbg(dev, "TRT_STDATA[%02d]: 0x%08x\n", i,
+				udma_tchanrt_read(uc, 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_CHAN_RT_STDATA_REG + i * 4;
+			dev_dbg(dev, "RRT_STDATA[%02d]: 0x%08x\n", i,
+				udma_rchanrt_read(uc, 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, UDMA_CHAN_RT_CTL_REG);
+	if (uc->rchan)
+		rrt_ctl = udma_rchanrt_read(uc, UDMA_CHAN_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, UDMA_CHAN_RT_PEER_RT_EN_REG);
+		pause_mask = UDMA_PEER_RT_EN_PAUSE;
+		break;
+	case DMA_MEM_TO_DEV:
+		val = udma_tchanrt_read(uc, UDMA_CHAN_RT_PEER_RT_EN_REG);
+		pause_mask = UDMA_PEER_RT_EN_PAUSE;
+		break;
+	case DMA_MEM_TO_MEM:
+		val = udma_tchanrt_read(uc, UDMA_CHAN_RT_CTL_REG);
+		pause_mask = UDMA_CHAN_RT_CTL_PAUSE;
+		break;
+	default:
+		return false;
+	}
+
+	if (val & pause_mask)
+		return true;
+
+	return false;
+}
+
+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;
+
+	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 */
+	}
+
+	return k3_ringacc_ring_push(ring, &paddr);
+}
+
+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;
+
+	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:
+		return -ENOENT;
+	}
+
+	ret = k3_ringacc_ring_pop(ring, addr);
+	if (ret)
+		return ret;
+
+	rmb(); /* Ensure that reads are not moved before this point */
+
+	/* Teardown completion */
+	if (cppi5_desc_is_tdcm(*addr))
+		return 0;
+
+	/* Check for flush descriptor */
+	if (udma_desc_is_rx_flush(uc, *addr))
+		return -ENOENT;
+
+	return 0;
+}
+
+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;
+	}
+}
+
+static void udma_reset_counters(struct udma_chan *uc)
+{
+	u32 val;
+
+	if (uc->tchan) {
+		val = udma_tchanrt_read(uc, UDMA_CHAN_RT_BCNT_REG);
+		udma_tchanrt_write(uc, UDMA_CHAN_RT_BCNT_REG, val);
+
+		val = udma_tchanrt_read(uc, UDMA_CHAN_RT_SBCNT_REG);
+		udma_tchanrt_write(uc, UDMA_CHAN_RT_SBCNT_REG, val);
+
+		val = udma_tchanrt_read(uc, UDMA_CHAN_RT_PCNT_REG);
+		udma_tchanrt_write(uc, UDMA_CHAN_RT_PCNT_REG, val);
+
+		val = udma_tchanrt_read(uc, UDMA_CHAN_RT_PEER_BCNT_REG);
+		udma_tchanrt_write(uc, UDMA_CHAN_RT_PEER_BCNT_REG, val);
+	}
+
+	if (uc->rchan) {
+		val = udma_rchanrt_read(uc, UDMA_CHAN_RT_BCNT_REG);
+		udma_rchanrt_write(uc, UDMA_CHAN_RT_BCNT_REG, val);
+
+		val = udma_rchanrt_read(uc, UDMA_CHAN_RT_SBCNT_REG);
+		udma_rchanrt_write(uc, UDMA_CHAN_RT_SBCNT_REG, val);
+
+		val = udma_rchanrt_read(uc, UDMA_CHAN_RT_PCNT_REG);
+		udma_rchanrt_write(uc, UDMA_CHAN_RT_PCNT_REG, val);
+
+		val = udma_rchanrt_read(uc, UDMA_CHAN_RT_PEER_BCNT_REG);
+		udma_rchanrt_write(uc, UDMA_CHAN_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, UDMA_CHAN_RT_PEER_RT_EN_REG, 0);
+		udma_rchanrt_write(uc, UDMA_CHAN_RT_CTL_REG, 0);
+		break;
+	case DMA_MEM_TO_DEV:
+		udma_tchanrt_write(uc, UDMA_CHAN_RT_CTL_REG, 0);
+		udma_tchanrt_write(uc, UDMA_CHAN_RT_PEER_RT_EN_REG, 0);
+		break;
+	case DMA_MEM_TO_MEM:
+		udma_rchanrt_write(uc, UDMA_CHAN_RT_CTL_REG, 0);
+		udma_tchanrt_write(uc, UDMA_CHAN_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, UDMA_CHAN_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,
+					   UDMA_CHAN_RT_PEER_STATIC_TR_XY_REG,
+					   val);
+
+			udma_rchanrt_write(uc,
+				UDMA_CHAN_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, UDMA_CHAN_RT_CTL_REG,
+				   UDMA_CHAN_RT_CTL_EN);
+
+		/* Enable remote */
+		udma_rchanrt_write(uc, UDMA_CHAN_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,
+					   UDMA_CHAN_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, UDMA_CHAN_RT_PEER_RT_EN_REG,
+				   UDMA_PEER_RT_EN_ENABLE);
+
+		udma_tchanrt_write(uc, UDMA_CHAN_RT_CTL_REG,
+				   UDMA_CHAN_RT_CTL_EN);
+
+		break;
+	case DMA_MEM_TO_MEM:
+		udma_rchanrt_write(uc, UDMA_CHAN_RT_CTL_REG,
+				   UDMA_CHAN_RT_CTL_EN);
+		udma_tchanrt_write(uc, UDMA_CHAN_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, UDMA_CHAN_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, UDMA_CHAN_RT_PEER_RT_EN_REG,
+				   UDMA_PEER_RT_EN_ENABLE |
+				   UDMA_PEER_RT_EN_FLUSH);
+		udma_tchanrt_write(uc, UDMA_CHAN_RT_CTL_REG,
+				   UDMA_CHAN_RT_CTL_EN |
+				   UDMA_CHAN_RT_CTL_TDOWN);
+		break;
+	case DMA_MEM_TO_MEM:
+		udma_tchanrt_write(uc, UDMA_CHAN_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, UDMA_CHAN_RT_PEER_BCNT_REG);
+	bcnt = udma_tchanrt_read(uc, UDMA_CHAN_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)) {
+		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->tpl_levels)				\
+			tpl = ud->tpl_levels - 1;			\
+									\
+		start = ud->tpl_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);
+
+	return PTR_ERR_OR_ZERO(uc->tchan);
+}
+
+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);
+
+	return PTR_ERR_OR_ZERO(uc->rchan);
+}
+
+static int udma_get_chan_pair(struct udma_chan *uc)
+{
+	struct udma_dev *ud = uc->ud;
+	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 = ud->tpl_start_idx[ud->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);
+
+	return PTR_ERR_OR_ZERO(uc->rflow);
+}
+
+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;
+
+	ret = k3_ringacc_request_rings_pair(ud->ringacc, uc->tchan->id, -1,
+					    &uc->tchan->t_ring,
+					    &uc->tchan->tc_ring);
+	if (ret) {
+		ret = -EBUSY;
+		goto err_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;
+	k3_ringacc_ring_free(uc->tchan->t_ring);
+	uc->tchan->t_ring = NULL;
+err_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;
+	ret = k3_ringacc_request_rings_pair(ud->ringacc, fd_ring_id, -1,
+					    &rflow->fd_ring, &rflow->r_ring);
+	if (ret) {
+		ret = -EBUSY;
+		goto err_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;
+	k3_ringacc_ring_free(rflow->fd_ring);
+	rflow->fd_ring = NULL;
+err_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 |		\
+	TI_SCI_MSG_VALUE_RM_UDMAP_CH_ATYPE_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 |	\
+	TI_SCI_MSG_VALUE_RM_UDMAP_CH_ATYPE_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;
+	req_tx.tx_atype = ud->atype;
+
+	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;
+	req_rx.rx_atype = ud->atype;
+
+	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;
+	req_tx.tx_atype = uc->config.atype;
+
+	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;
+	req_rx.rx_atype = uc->config.atype;
+
+	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_soc_data *soc_data = ud->soc_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;
+			ret = -ENOMEM;
+			goto err_cleanup;
+		}
+	}
+
+	/*
+	 * 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)
+			goto err_cleanup;
+
+		ret = udma_alloc_tx_resources(uc);
+		if (ret) {
+			udma_put_rchan(uc);
+			goto err_cleanup;
+		}
+
+		ret = udma_alloc_rx_resources(uc);
+		if (ret) {
+			udma_free_tx_resources(uc);
+			goto err_cleanup;
+		}
+
+		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)
+			goto err_cleanup;
+
+		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)
+			goto err_cleanup;
+
+		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 = soc_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);
+		ret = -EINVAL;
+		goto err_cleanup;
+
+	}
+
+	/* 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_reset_chan(uc, false);
+		if (udma_is_chan_running(uc)) {
+			dev_err(ud->dev, "chan%d: won't stop!\n", uc->id);
+			ret = -EBUSY;
+			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);
+
+	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);
+err_cleanup:
+	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;
+
+	/* 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[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;
+		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_SUPR_EVT | 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(struct_size(d, hwdesc, sglen), 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;
+
+	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(struct_size(d, hwdesc, periods), 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_SUPR_EVT | 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, UDMA_CHAN_RT_SBCNT_REG);
+
+			if (uc->config.ep_type != PSIL_EP_NATIVE) {
+				peer_bcnt = udma_tchanrt_read(uc,
+						UDMA_CHAN_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, UDMA_CHAN_RT_BCNT_REG);
+
+			if (uc->config.ep_type != PSIL_EP_NATIVE) {
+				peer_bcnt = udma_rchanrt_read(uc,
+						UDMA_CHAN_RT_PEER_BCNT_REG);
+
+				if (peer_bcnt > bcnt)
+					delay = peer_bcnt - bcnt;
+			}
+		} else {
+			bcnt = udma_tchanrt_read(uc, UDMA_CHAN_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, UDMA_CHAN_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, UDMA_CHAN_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, UDMA_CHAN_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, UDMA_CHAN_RT_PEER_RT_EN_REG,
+					 UDMA_PEER_RT_EN_PAUSE, 0);
+
+		break;
+	case DMA_MEM_TO_DEV:
+		udma_tchanrt_update_bits(uc, UDMA_CHAN_RT_PEER_RT_EN_REG,
+					 UDMA_PEER_RT_EN_PAUSE, 0);
+		break;
+	case DMA_MEM_TO_MEM:
+		udma_tchanrt_update_bits(uc, UDMA_CHAN_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(struct tasklet_struct *t)
+{
+	struct virt_dma_chan *vc = from_tasklet(vc, t, task);
+	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);
+
+	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;
+
+struct udma_filter_param {
+	int remote_thread_id;
+	u32 atype;
+};
+
+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_filter_param *filter_param;
+	struct udma_chan *uc;
+	struct udma_dev *ud;
+
+	if (chan->device->dev->driver != &udma_driver.driver)
+		return false;
+
+	uc = to_udma_chan(chan);
+	ucc = &uc->config;
+	ud = uc->ud;
+	filter_param = param;
+
+	if (filter_param->atype > 2) {
+		dev_err(ud->dev, "Invalid channel atype: %u\n",
+			filter_param->atype);
+		return false;
+	}
+
+	ucc->remote_thread_id = filter_param->remote_thread_id;
+	ucc->atype = filter_param->atype;
+
+	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;
+		ucc->atype = 0;
+		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 udma_filter_param filter_param;
+	struct dma_chan *chan;
+
+	if (dma_spec->args_count != 1 && dma_spec->args_count != 2)
+		return NULL;
+
+	filter_param.remote_thread_id = dma_spec->args[0];
+	if (dma_spec->args_count == 2)
+		filter_param.atype = dma_spec->args[1];
+	else
+		filter_param.atype = 0;
+
+	chan = __dma_request_channel(&mask, udma_dma_filter_fn, &filter_param,
+				     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),
+};
+
+static struct udma_match_data am654_mcu_data = {
+	.psil_base = 0x6000,
+	.enable_memcpy_support = false,
+	.statictr_z_mask = GENMASK(11, 0),
+};
+
+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),
+};
+
+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),
+};
+
+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 struct udma_soc_data am654_soc_data = {
+	.rchan_oes_offset = 0x200,
+};
+
+static struct udma_soc_data j721e_soc_data = {
+	.rchan_oes_offset = 0x400,
+};
+
+static struct udma_soc_data j7200_soc_data = {
+	.rchan_oes_offset = 0x80,
+};
+
+static const struct soc_device_attribute k3_soc_devices[] = {
+	{ .family = "AM65X", .data = &am654_soc_data },
+	{ .family = "J721E", .data = &j721e_soc_data },
+	{ .family = "J7200", .data = &j7200_soc_data },
+	{ /* sentinel */ }
+};
+
+static int udma_get_mmrs(struct platform_device *pdev, struct udma_dev *ud)
+{
+	int i;
+
+	for (i = 0; i < MMR_LAST; i++) {
+		ud->mmrs[i] = devm_platform_ioremap_resource_byname(pdev, mmr_names[i]);
+		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], UDMA_CAP_REG(2));
+	cap3 = udma_read(ud->mmrs[MMR_GCFG], UDMA_CAP_REG(3));
+
+	ud->rflow_cnt = UDMA_CAP3_RFLOW_CNT(cap3);
+	ud->tchan_cnt = UDMA_CAP2_TCHAN_CNT(cap2);
+	ud->echan_cnt = UDMA_CAP2_ECHAN_CNT(cap2);
+	ud->rchan_cnt = UDMA_CAP2_RCHAN_CNT(cap2);
+	ch_count  = ud->tchan_cnt + ud->rchan_cnt;
+
+	/* Set up the throughput level start indexes */
+	if (of_device_is_compatible(dev->of_node,
+				    "ti,am654-navss-main-udmap")) {
+		ud->tpl_levels = 2;
+		ud->tpl_start_idx[0] = 8;
+	} else if (of_device_is_compatible(dev->of_node,
+					   "ti,am654-navss-mcu-udmap")) {
+		ud->tpl_levels = 2;
+		ud->tpl_start_idx[0] = 2;
+	} else if (UDMA_CAP3_UCHAN_CNT(cap3)) {
+		ud->tpl_levels = 3;
+		ud->tpl_start_idx[1] = UDMA_CAP3_UCHAN_CNT(cap3);
+		ud->tpl_start_idx[0] = UDMA_CAP3_HCHAN_CNT(cap3);
+	} else if (UDMA_CAP3_HCHAN_CNT(cap3)) {
+		ud->tpl_levels = 2;
+		ud->tpl_start_idx[0] = UDMA_CAP3_HCHAN_CNT(cap3);
+	} else {
+		ud->tpl_levels = 1;
+	}
+
+	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->soc_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;
+
+	dma_sync_single_for_device(dev, hwdesc->cppi5_desc_paddr,
+				   hwdesc->cppi5_desc_size, DMA_TO_DEVICE);
+
+	/* 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;
+}
+
+#ifdef CONFIG_DEBUG_FS
+static void udma_dbg_summary_show_chan(struct seq_file *s,
+				       struct dma_chan *chan)
+{
+	struct udma_chan *uc = to_udma_chan(chan);
+	struct udma_chan_config *ucc = &uc->config;
+
+	seq_printf(s, " %-13s| %s", dma_chan_name(chan),
+		   chan->dbg_client_name ?: "in-use");
+	seq_printf(s, " (%s, ", dmaengine_get_direction_text(uc->config.dir));
+
+	switch (uc->config.dir) {
+	case DMA_MEM_TO_MEM:
+		seq_printf(s, "chan%d pair [0x%04x -> 0x%04x], ", uc->tchan->id,
+			   ucc->src_thread, ucc->dst_thread);
+		break;
+	case DMA_DEV_TO_MEM:
+		seq_printf(s, "rchan%d [0x%04x -> 0x%04x], ", uc->rchan->id,
+			   ucc->src_thread, ucc->dst_thread);
+		break;
+	case DMA_MEM_TO_DEV:
+		seq_printf(s, "tchan%d [0x%04x -> 0x%04x], ", uc->tchan->id,
+			   ucc->src_thread, ucc->dst_thread);
+		break;
+	default:
+		seq_printf(s, ")\n");
+		return;
+	}
+
+	if (ucc->ep_type == PSIL_EP_NATIVE) {
+		seq_printf(s, "PSI-L Native");
+		if (ucc->metadata_size) {
+			seq_printf(s, "[%s", ucc->needs_epib ? " EPIB" : "");
+			if (ucc->psd_size)
+				seq_printf(s, " PSDsize:%u", ucc->psd_size);
+			seq_printf(s, " ]");
+		}
+	} else {
+		seq_printf(s, "PDMA");
+		if (ucc->enable_acc32 || ucc->enable_burst)
+			seq_printf(s, "[%s%s ]",
+				   ucc->enable_acc32 ? " ACC32" : "",
+				   ucc->enable_burst ? " BURST" : "");
+	}
+
+	seq_printf(s, ", %s)\n", ucc->pkt_mode ? "Packet mode" : "TR mode");
+}
+
+static void udma_dbg_summary_show(struct seq_file *s,
+				  struct dma_device *dma_dev)
+{
+	struct dma_chan *chan;
+
+	list_for_each_entry(chan, &dma_dev->channels, device_node) {
+		if (chan->client_count)
+			udma_dbg_summary_show_chan(s, chan);
+	}
+}
+#endif /* CONFIG_DEBUG_FS */
+
+#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;
+	const struct soc_device_attribute *soc;
+	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;
+	}
+
+	ret = of_property_read_u32(dev->of_node, "ti,udma-atype", &ud->atype);
+	if (!ret && ud->atype > 2) {
+		dev_err(dev, "Invalid atype: %u\n", ud->atype);
+		return -EINVAL;
+	}
+
+	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;
+
+	soc = soc_device_match(k3_soc_devices);
+	if (!soc) {
+		dev_err(dev, "No compatible SoC found\n");
+		return -ENODEV;
+	}
+	ud->soc_data = soc->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;
+#ifdef CONFIG_DEBUG_FS
+	ud->ddev.dbg_summary_show = udma_dbg_summary_show;
+#endif
+
+	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_setup(&uc->vc.task, udma_vchan_complete);
+		init_completion(&uc->teardown_completed);
+		INIT_DELAYED_WORK(&uc->tx_drain.work, udma_check_tx_completion);
+	}
+
+	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 000000000..09c4529e0
--- /dev/null
+++ b/drivers/dma/ti/k3-udma.h
@@ -0,0 +1,140 @@
+/* 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
+
+/* TCHANRT/RCHANRT registers */
+#define UDMA_CHAN_RT_CTL_REG		0x0
+#define UDMA_CHAN_RT_SWTRIG_REG		0x8
+#define UDMA_CHAN_RT_STDATA_REG		0x80
+
+#define UDMA_CHAN_RT_PEER_REG(i)	(0x200 + ((i) * 0x4))
+#define UDMA_CHAN_RT_PEER_STATIC_TR_XY_REG	\
+	UDMA_CHAN_RT_PEER_REG(0)	/* PSI-L: 0x400 */
+#define UDMA_CHAN_RT_PEER_STATIC_TR_Z_REG	\
+	UDMA_CHAN_RT_PEER_REG(1)	/* PSI-L: 0x401 */
+#define UDMA_CHAN_RT_PEER_BCNT_REG		\
+	UDMA_CHAN_RT_PEER_REG(4)	/* PSI-L: 0x404 */
+#define UDMA_CHAN_RT_PEER_RT_EN_REG		\
+	UDMA_CHAN_RT_PEER_REG(8)	/* PSI-L: 0x408 */
+
+#define UDMA_CHAN_RT_PCNT_REG		0x400
+#define UDMA_CHAN_RT_BCNT_REG		0x408
+#define UDMA_CHAN_RT_SBCNT_REG		0x410
+
+/* UDMA_CAP Registers */
+#define UDMA_CAP2_TCHAN_CNT(val)	((val) & 0x1ff)
+#define UDMA_CAP2_ECHAN_CNT(val)	(((val) >> 9) & 0x1ff)
+#define UDMA_CAP2_RCHAN_CNT(val)	(((val) >> 18) & 0x1ff)
+#define UDMA_CAP3_RFLOW_CNT(val)	((val) & 0x3fff)
+#define UDMA_CAP3_HCHAN_CNT(val)	(((val) >> 14) & 0x1ff)
+#define UDMA_CAP3_UCHAN_CNT(val)	(((val) >> 23) & 0x1ff)
+
+/* UDMA_CHAN_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_CHAN_RT_PEER_RT_EN_REG */
+#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
new file mode 100644
index 000000000..268a08058
--- /dev/null
+++ b/drivers/dma/ti/omap-dma.c
@@ -0,0 +1,1950 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * OMAP DMAengine support
+ */
+#include <linux/cpu_pm.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/module.h>
+#include <linux/omap-dma.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/of_dma.h>
+#include <linux/of_device.h>
+
+#include "../virt-dma.h"
+
+#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;
+	unsigned dma_requests;
+	spinlock_t irq_lock;
+	uint32_t irq_enable_mask;
+	struct omap_chan **lch_map;
+};
+
+struct omap_chan {
+	struct virt_dma_chan vc;
+	void __iomem *channel_base;
+	const struct omap_dma_reg *reg_map;
+	uint32_t ccr;
+
+	struct dma_slave_config	cfg;
+	unsigned dma_sig;
+	bool cyclic;
+	bool paused;
+	bool running;
+
+	int dma_ch;
+	struct omap_desc *desc;
+	unsigned sgidx;
+};
+
+#define DESC_NXT_SV_REFRESH	(0x1 << 24)
+#define DESC_NXT_SV_REUSE	(0x2 << 24)
+#define DESC_NXT_DV_REFRESH	(0x1 << 26)
+#define DESC_NXT_DV_REUSE	(0x2 << 26)
+#define DESC_NTYPE_TYPE2	(0x2 << 29)
+
+/* Type 2 descriptor with Source or Destination address update */
+struct omap_type2_desc {
+	uint32_t next_desc;
+	uint32_t en;
+	uint32_t addr; /* src or dst */
+	uint16_t fn;
+	uint16_t cicr;
+	int16_t cdei;
+	int16_t csei;
+	int32_t cdfi;
+	int32_t csfi;
+} __packed;
+
+struct omap_sg {
+	dma_addr_t addr;
+	uint32_t en;		/* number of elements (24-bit) */
+	uint32_t fn;		/* number of frames (16-bit) */
+	int32_t fi;		/* for double indexing */
+	int16_t ei;		/* for double indexing */
+
+	/* Linked list */
+	struct omap_type2_desc *t2_desc;
+	dma_addr_t t2_desc_paddr;
+};
+
+struct omap_desc {
+	struct virt_dma_desc vd;
+	bool using_ll;
+	enum dma_transfer_direction dir;
+	dma_addr_t dev_addr;
+	bool polled;
+
+	int32_t fi;		/* for OMAP_DMA_SYNC_PACKET / double indexing */
+	int16_t ei;		/* for double indexing */
+	uint8_t es;		/* CSDP_DATA_TYPE_xxx */
+	uint32_t ccr;		/* CCR value */
+	uint16_t clnk_ctrl;	/* CLNK_CTRL value */
+	uint16_t cicr;		/* CICR value */
+	uint32_t csdp;		/* CSDP value */
+
+	unsigned sglen;
+	struct omap_sg sg[];
+};
+
+enum {
+	CAPS_0_SUPPORT_LL123	= BIT(20),	/* Linked List type1/2/3 */
+	CAPS_0_SUPPORT_LL4	= BIT(21),	/* Linked List type4 */
+
+	CCR_FS			= BIT(5),
+	CCR_READ_PRIORITY	= BIT(6),
+	CCR_ENABLE		= BIT(7),
+	CCR_AUTO_INIT		= BIT(8),	/* OMAP1 only */
+	CCR_REPEAT		= BIT(9),	/* OMAP1 only */
+	CCR_OMAP31_DISABLE	= BIT(10),	/* OMAP1 only */
+	CCR_SUSPEND_SENSITIVE	= BIT(8),	/* OMAP2+ only */
+	CCR_RD_ACTIVE		= BIT(9),	/* OMAP2+ only */
+	CCR_WR_ACTIVE		= BIT(10),	/* OMAP2+ only */
+	CCR_SRC_AMODE_CONSTANT	= 0 << 12,
+	CCR_SRC_AMODE_POSTINC	= 1 << 12,
+	CCR_SRC_AMODE_SGLIDX	= 2 << 12,
+	CCR_SRC_AMODE_DBLIDX	= 3 << 12,
+	CCR_DST_AMODE_CONSTANT	= 0 << 14,
+	CCR_DST_AMODE_POSTINC	= 1 << 14,
+	CCR_DST_AMODE_SGLIDX	= 2 << 14,
+	CCR_DST_AMODE_DBLIDX	= 3 << 14,
+	CCR_CONSTANT_FILL	= BIT(16),
+	CCR_TRANSPARENT_COPY	= BIT(17),
+	CCR_BS			= BIT(18),
+	CCR_SUPERVISOR		= BIT(22),
+	CCR_PREFETCH		= BIT(23),
+	CCR_TRIGGER_SRC		= BIT(24),
+	CCR_BUFFERING_DISABLE	= BIT(25),
+	CCR_WRITE_PRIORITY	= BIT(26),
+	CCR_SYNC_ELEMENT	= 0,
+	CCR_SYNC_FRAME		= CCR_FS,
+	CCR_SYNC_BLOCK		= CCR_BS,
+	CCR_SYNC_PACKET		= CCR_BS | CCR_FS,
+
+	CSDP_DATA_TYPE_8	= 0,
+	CSDP_DATA_TYPE_16	= 1,
+	CSDP_DATA_TYPE_32	= 2,
+	CSDP_SRC_PORT_EMIFF	= 0 << 2, /* OMAP1 only */
+	CSDP_SRC_PORT_EMIFS	= 1 << 2, /* OMAP1 only */
+	CSDP_SRC_PORT_OCP_T1	= 2 << 2, /* OMAP1 only */
+	CSDP_SRC_PORT_TIPB	= 3 << 2, /* OMAP1 only */
+	CSDP_SRC_PORT_OCP_T2	= 4 << 2, /* OMAP1 only */
+	CSDP_SRC_PORT_MPUI	= 5 << 2, /* OMAP1 only */
+	CSDP_SRC_PACKED		= BIT(6),
+	CSDP_SRC_BURST_1	= 0 << 7,
+	CSDP_SRC_BURST_16	= 1 << 7,
+	CSDP_SRC_BURST_32	= 2 << 7,
+	CSDP_SRC_BURST_64	= 3 << 7,
+	CSDP_DST_PORT_EMIFF	= 0 << 9, /* OMAP1 only */
+	CSDP_DST_PORT_EMIFS	= 1 << 9, /* OMAP1 only */
+	CSDP_DST_PORT_OCP_T1	= 2 << 9, /* OMAP1 only */
+	CSDP_DST_PORT_TIPB	= 3 << 9, /* OMAP1 only */
+	CSDP_DST_PORT_OCP_T2	= 4 << 9, /* OMAP1 only */
+	CSDP_DST_PORT_MPUI	= 5 << 9, /* OMAP1 only */
+	CSDP_DST_PACKED		= BIT(13),
+	CSDP_DST_BURST_1	= 0 << 14,
+	CSDP_DST_BURST_16	= 1 << 14,
+	CSDP_DST_BURST_32	= 2 << 14,
+	CSDP_DST_BURST_64	= 3 << 14,
+	CSDP_WRITE_NON_POSTED	= 0 << 16,
+	CSDP_WRITE_POSTED	= 1 << 16,
+	CSDP_WRITE_LAST_NON_POSTED = 2 << 16,
+
+	CICR_TOUT_IE		= BIT(0),	/* OMAP1 only */
+	CICR_DROP_IE		= BIT(1),
+	CICR_HALF_IE		= BIT(2),
+	CICR_FRAME_IE		= BIT(3),
+	CICR_LAST_IE		= BIT(4),
+	CICR_BLOCK_IE		= BIT(5),
+	CICR_PKT_IE		= BIT(7),	/* OMAP2+ only */
+	CICR_TRANS_ERR_IE	= BIT(8),	/* OMAP2+ only */
+	CICR_SUPERVISOR_ERR_IE	= BIT(10),	/* OMAP2+ only */
+	CICR_MISALIGNED_ERR_IE	= BIT(11),	/* OMAP2+ only */
+	CICR_DRAIN_IE		= BIT(12),	/* OMAP2+ only */
+	CICR_SUPER_BLOCK_IE	= BIT(14),	/* OMAP2+ only */
+
+	CLNK_CTRL_ENABLE_LNK	= BIT(15),
+
+	CDP_DST_VALID_INC	= 0 << 0,
+	CDP_DST_VALID_RELOAD	= 1 << 0,
+	CDP_DST_VALID_REUSE	= 2 << 0,
+	CDP_SRC_VALID_INC	= 0 << 2,
+	CDP_SRC_VALID_RELOAD	= 1 << 2,
+	CDP_SRC_VALID_REUSE	= 2 << 2,
+	CDP_NTYPE_TYPE1		= 1 << 4,
+	CDP_NTYPE_TYPE2		= 2 << 4,
+	CDP_NTYPE_TYPE3		= 3 << 4,
+	CDP_TMODE_NORMAL	= 0 << 8,
+	CDP_TMODE_LLIST		= 1 << 8,
+	CDP_FAST		= BIT(10),
+};
+
+static const unsigned es_bytes[] = {
+	[CSDP_DATA_TYPE_8] = 1,
+	[CSDP_DATA_TYPE_16] = 2,
+	[CSDP_DATA_TYPE_32] = 4,
+};
+
+static bool omap_dma_filter_fn(struct dma_chan *chan, void *param);
+static struct of_dma_filter_info omap_dma_info = {
+	.filter_fn = omap_dma_filter_fn,
+};
+
+static inline struct omap_dmadev *to_omap_dma_dev(struct dma_device *d)
+{
+	return container_of(d, struct omap_dmadev, ddev);
+}
+
+static inline struct omap_chan *to_omap_dma_chan(struct dma_chan *c)
+{
+	return container_of(c, struct omap_chan, vc.chan);
+}
+
+static inline struct omap_desc *to_omap_dma_desc(struct dma_async_tx_descriptor *t)
+{
+	return container_of(t, struct omap_desc, vd.tx);
+}
+
+static void omap_dma_desc_free(struct virt_dma_desc *vd)
+{
+	struct omap_desc *d = to_omap_dma_desc(&vd->tx);
+
+	if (d->using_ll) {
+		struct omap_dmadev *od = to_omap_dma_dev(vd->tx.chan->device);
+		int i;
+
+		for (i = 0; i < d->sglen; i++) {
+			if (d->sg[i].t2_desc)
+				dma_pool_free(od->desc_pool, d->sg[i].t2_desc,
+					      d->sg[i].t2_desc_paddr);
+		}
+	}
+
+	kfree(d);
+}
+
+static void omap_dma_fill_type2_desc(struct omap_desc *d, int idx,
+				     enum dma_transfer_direction dir, bool last)
+{
+	struct omap_sg *sg = &d->sg[idx];
+	struct omap_type2_desc *t2_desc = sg->t2_desc;
+
+	if (idx)
+		d->sg[idx - 1].t2_desc->next_desc = sg->t2_desc_paddr;
+	if (last)
+		t2_desc->next_desc = 0xfffffffc;
+
+	t2_desc->en = sg->en;
+	t2_desc->addr = sg->addr;
+	t2_desc->fn = sg->fn & 0xffff;
+	t2_desc->cicr = d->cicr;
+	if (!last)
+		t2_desc->cicr &= ~CICR_BLOCK_IE;
+
+	switch (dir) {
+	case DMA_DEV_TO_MEM:
+		t2_desc->cdei = sg->ei;
+		t2_desc->csei = d->ei;
+		t2_desc->cdfi = sg->fi;
+		t2_desc->csfi = d->fi;
+
+		t2_desc->en |= DESC_NXT_DV_REFRESH;
+		t2_desc->en |= DESC_NXT_SV_REUSE;
+		break;
+	case DMA_MEM_TO_DEV:
+		t2_desc->cdei = d->ei;
+		t2_desc->csei = sg->ei;
+		t2_desc->cdfi = d->fi;
+		t2_desc->csfi = sg->fi;
+
+		t2_desc->en |= DESC_NXT_SV_REFRESH;
+		t2_desc->en |= DESC_NXT_DV_REUSE;
+		break;
+	default:
+		return;
+	}
+
+	t2_desc->en |= DESC_NTYPE_TYPE2;
+}
+
+static void omap_dma_write(uint32_t val, unsigned type, void __iomem *addr)
+{
+	switch (type) {
+	case OMAP_DMA_REG_16BIT:
+		writew_relaxed(val, addr);
+		break;
+	case OMAP_DMA_REG_2X16BIT:
+		writew_relaxed(val, addr);
+		writew_relaxed(val >> 16, addr + 2);
+		break;
+	case OMAP_DMA_REG_32BIT:
+		writel_relaxed(val, addr);
+		break;
+	default:
+		WARN_ON(1);
+	}
+}
+
+static unsigned omap_dma_read(unsigned type, void __iomem *addr)
+{
+	unsigned val;
+
+	switch (type) {
+	case OMAP_DMA_REG_16BIT:
+		val = readw_relaxed(addr);
+		break;
+	case OMAP_DMA_REG_2X16BIT:
+		val = readw_relaxed(addr);
+		val |= readw_relaxed(addr + 2) << 16;
+		break;
+	case OMAP_DMA_REG_32BIT:
+		val = readl_relaxed(addr);
+		break;
+	default:
+		WARN_ON(1);
+		val = 0;
+	}
+
+	return val;
+}
+
+static void omap_dma_glbl_write(struct omap_dmadev *od, unsigned reg, unsigned val)
+{
+	const struct omap_dma_reg *r = od->reg_map + reg;
+
+	WARN_ON(r->stride);
+
+	omap_dma_write(val, r->type, od->base + r->offset);
+}
+
+static unsigned omap_dma_glbl_read(struct omap_dmadev *od, unsigned reg)
+{
+	const struct omap_dma_reg *r = od->reg_map + reg;
+
+	WARN_ON(r->stride);
+
+	return omap_dma_read(r->type, od->base + r->offset);
+}
+
+static void omap_dma_chan_write(struct omap_chan *c, unsigned reg, unsigned val)
+{
+	const struct omap_dma_reg *r = c->reg_map + reg;
+
+	omap_dma_write(val, r->type, c->channel_base + r->offset);
+}
+
+static unsigned omap_dma_chan_read(struct omap_chan *c, unsigned reg)
+{
+	const struct omap_dma_reg *r = c->reg_map + reg;
+
+	return omap_dma_read(r->type, c->channel_base + r->offset);
+}
+
+static void omap_dma_clear_csr(struct omap_chan *c)
+{
+	if (dma_omap1())
+		omap_dma_chan_read(c, CSR);
+	else
+		omap_dma_chan_write(c, CSR, ~0);
+}
+
+static unsigned omap_dma_get_csr(struct omap_chan *c)
+{
+	unsigned val = omap_dma_chan_read(c, CSR);
+
+	if (!dma_omap1())
+		omap_dma_chan_write(c, CSR, val);
+
+	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)
+{
+	c->channel_base = od->base + od->plat->channel_stride * lch;
+
+	od->lch_map[lch] = c;
+}
+
+static void omap_dma_start(struct omap_chan *c, struct omap_desc *d)
+{
+	struct omap_dmadev *od = to_omap_dma_dev(c->vc.chan.device);
+	uint16_t cicr = d->cicr;
+
+	if (__dma_omap15xx(od->plat->dma_attr))
+		omap_dma_chan_write(c, CPC, 0);
+	else
+		omap_dma_chan_write(c, CDAC, 0);
+
+	omap_dma_clear_csr(c);
+
+	if (d->using_ll) {
+		uint32_t cdp = CDP_TMODE_LLIST | CDP_NTYPE_TYPE2 | CDP_FAST;
+
+		if (d->dir == DMA_DEV_TO_MEM)
+			cdp |= (CDP_DST_VALID_RELOAD | CDP_SRC_VALID_REUSE);
+		else
+			cdp |= (CDP_DST_VALID_REUSE | CDP_SRC_VALID_RELOAD);
+		omap_dma_chan_write(c, CDP, cdp);
+
+		omap_dma_chan_write(c, CNDP, d->sg[0].t2_desc_paddr);
+		omap_dma_chan_write(c, CCDN, 0);
+		omap_dma_chan_write(c, CCFN, 0xffff);
+		omap_dma_chan_write(c, CCEN, 0xffffff);
+
+		cicr &= ~CICR_BLOCK_IE;
+	} else if (od->ll123_supported) {
+		omap_dma_chan_write(c, CDP, 0);
+	}
+
+	/* Enable interrupts */
+	omap_dma_chan_write(c, CICR, cicr);
+
+	/* Enable channel */
+	omap_dma_chan_write(c, CCR, d->ccr | CCR_ENABLE);
+
+	c->running = true;
+}
+
+static void omap_dma_drain_chan(struct omap_chan *c)
+{
+	int i;
+	u32 val;
+
+	/* Wait for sDMA FIFO to drain */
+	for (i = 0; ; i++) {
+		val = omap_dma_chan_read(c, CCR);
+		if (!(val & (CCR_RD_ACTIVE | CCR_WR_ACTIVE)))
+			break;
+
+		if (i > 100)
+			break;
+
+		udelay(5);
+	}
+
+	if (val & (CCR_RD_ACTIVE | CCR_WR_ACTIVE))
+		dev_err(c->vc.chan.device->dev,
+			"DMA drain did not complete on lch %d\n",
+			c->dma_ch);
+}
+
+static int omap_dma_stop(struct omap_chan *c)
+{
+	struct omap_dmadev *od = to_omap_dma_dev(c->vc.chan.device);
+	uint32_t val;
+
+	/* disable irq */
+	omap_dma_chan_write(c, CICR, 0);
+
+	omap_dma_clear_csr(c);
+
+	val = omap_dma_chan_read(c, CCR);
+	if (od->plat->errata & DMA_ERRATA_i541 && val & CCR_TRIGGER_SRC) {
+		uint32_t sysconfig;
+
+		sysconfig = omap_dma_glbl_read(od, OCP_SYSCONFIG);
+		val = sysconfig & ~DMA_SYSCONFIG_MIDLEMODE_MASK;
+		val |= DMA_SYSCONFIG_MIDLEMODE(DMA_IDLEMODE_NO_IDLE);
+		omap_dma_glbl_write(od, OCP_SYSCONFIG, val);
+
+		val = omap_dma_chan_read(c, CCR);
+		val &= ~CCR_ENABLE;
+		omap_dma_chan_write(c, CCR, val);
+
+		if (!(c->ccr & CCR_BUFFERING_DISABLE))
+			omap_dma_drain_chan(c);
+
+		omap_dma_glbl_write(od, OCP_SYSCONFIG, sysconfig);
+	} else {
+		if (!(val & CCR_ENABLE))
+			return -EINVAL;
+
+		val &= ~CCR_ENABLE;
+		omap_dma_chan_write(c, CCR, val);
+
+		if (!(c->ccr & CCR_BUFFERING_DISABLE))
+			omap_dma_drain_chan(c);
+	}
+
+	mb();
+
+	if (!__dma_omap15xx(od->plat->dma_attr) && c->cyclic) {
+		val = omap_dma_chan_read(c, CLNK_CTRL);
+
+		if (dma_omap1())
+			val |= 1 << 14; /* set the STOP_LNK bit */
+		else
+			val &= ~CLNK_CTRL_ENABLE_LNK;
+
+		omap_dma_chan_write(c, CLNK_CTRL, val);
+	}
+	c->running = false;
+	return 0;
+}
+
+static void omap_dma_start_sg(struct omap_chan *c, struct omap_desc *d)
+{
+	struct omap_sg *sg = d->sg + c->sgidx;
+	unsigned cxsa, cxei, cxfi;
+
+	if (d->dir == DMA_DEV_TO_MEM || d->dir == DMA_MEM_TO_MEM) {
+		cxsa = CDSA;
+		cxei = CDEI;
+		cxfi = CDFI;
+	} else {
+		cxsa = CSSA;
+		cxei = CSEI;
+		cxfi = CSFI;
+	}
+
+	omap_dma_chan_write(c, cxsa, sg->addr);
+	omap_dma_chan_write(c, cxei, sg->ei);
+	omap_dma_chan_write(c, cxfi, sg->fi);
+	omap_dma_chan_write(c, CEN, sg->en);
+	omap_dma_chan_write(c, CFN, sg->fn);
+
+	omap_dma_start(c, d);
+	c->sgidx++;
+}
+
+static void omap_dma_start_desc(struct omap_chan *c)
+{
+	struct virt_dma_desc *vd = vchan_next_desc(&c->vc);
+	struct omap_desc *d;
+	unsigned cxsa, cxei, cxfi;
+
+	if (!vd) {
+		c->desc = NULL;
+		return;
+	}
+
+	list_del(&vd->node);
+
+	c->desc = d = to_omap_dma_desc(&vd->tx);
+	c->sgidx = 0;
+
+	/*
+	 * This provides the necessary barrier to ensure data held in
+	 * DMA coherent memory is visible to the DMA engine prior to
+	 * the transfer starting.
+	 */
+	mb();
+
+	omap_dma_chan_write(c, CCR, d->ccr);
+	if (dma_omap1())
+		omap_dma_chan_write(c, CCR2, d->ccr >> 16);
+
+	if (d->dir == DMA_DEV_TO_MEM || d->dir == DMA_MEM_TO_MEM) {
+		cxsa = CSSA;
+		cxei = CSEI;
+		cxfi = CSFI;
+	} else {
+		cxsa = CDSA;
+		cxei = CDEI;
+		cxfi = CDFI;
+	}
+
+	omap_dma_chan_write(c, cxsa, d->dev_addr);
+	omap_dma_chan_write(c, cxei, d->ei);
+	omap_dma_chan_write(c, cxfi, d->fi);
+	omap_dma_chan_write(c, CSDP, d->csdp);
+	omap_dma_chan_write(c, CLNK_CTRL, d->clnk_ctrl);
+
+	omap_dma_start_sg(c, d);
+}
+
+static void omap_dma_callback(int ch, u16 status, void *data)
+{
+	struct omap_chan *c = data;
+	struct omap_desc *d;
+	unsigned long flags;
+
+	spin_lock_irqsave(&c->vc.lock, flags);
+	d = c->desc;
+	if (d) {
+		if (c->cyclic) {
+			vchan_cyclic_callback(&d->vd);
+		} else if (d->using_ll || c->sgidx == d->sglen) {
+			omap_dma_start_desc(c);
+			vchan_cookie_complete(&d->vd);
+		} else {
+			omap_dma_start_sg(c, d);
+		}
+	}
+	spin_unlock_irqrestore(&c->vc.lock, flags);
+}
+
+static irqreturn_t omap_dma_irq(int irq, void *devid)
+{
+	struct omap_dmadev *od = devid;
+	unsigned status, channel;
+
+	spin_lock(&od->irq_lock);
+
+	status = omap_dma_glbl_read(od, IRQSTATUS_L1);
+	status &= od->irq_enable_mask;
+	if (status == 0) {
+		spin_unlock(&od->irq_lock);
+		return IRQ_NONE;
+	}
+
+	while ((channel = ffs(status)) != 0) {
+		unsigned mask, csr;
+		struct omap_chan *c;
+
+		channel -= 1;
+		mask = BIT(channel);
+		status &= ~mask;
+
+		c = od->lch_map[channel];
+		if (c == NULL) {
+			/* This should never happen */
+			dev_err(od->ddev.dev, "invalid channel %u\n", channel);
+			continue;
+		}
+
+		csr = omap_dma_get_csr(c);
+		omap_dma_glbl_write(od, IRQSTATUS_L1, mask);
+
+		omap_dma_callback(channel, csr, c);
+	}
+
+	spin_unlock(&od->irq_lock);
+
+	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);
+	struct omap_chan *c = to_omap_dma_chan(chan);
+	struct device *dev = od->ddev.dev;
+	int ret;
+
+	if (od->legacy) {
+		ret = omap_request_dma(c->dma_sig, "DMA engine",
+				       omap_dma_callback, c, &c->dma_ch);
+	} else {
+		ret = omap_dma_get_lch(od, &c->dma_ch);
+	}
+
+	dev_dbg(dev, "allocating channel %u for %u\n", c->dma_ch, c->dma_sig);
+
+	if (ret >= 0) {
+		omap_dma_assign(od, c, c->dma_ch);
+
+		if (!od->legacy) {
+			unsigned val;
+
+			spin_lock_irq(&od->irq_lock);
+			val = BIT(c->dma_ch);
+			omap_dma_glbl_write(od, IRQSTATUS_L1, val);
+			od->irq_enable_mask |= val;
+			omap_dma_glbl_write(od, IRQENABLE_L1, od->irq_enable_mask);
+
+			val = omap_dma_glbl_read(od, IRQENABLE_L0);
+			val &= ~BIT(c->dma_ch);
+			omap_dma_glbl_write(od, IRQENABLE_L0, val);
+			spin_unlock_irq(&od->irq_lock);
+		}
+	}
+
+	if (dma_omap1()) {
+		if (__dma_omap16xx(od->plat->dma_attr)) {
+			c->ccr = CCR_OMAP31_DISABLE;
+			/* Duplicate what plat-omap/dma.c does */
+			c->ccr |= c->dma_ch + 1;
+		} else {
+			c->ccr = c->dma_sig & 0x1f;
+		}
+	} else {
+		c->ccr = c->dma_sig & 0x1f;
+		c->ccr |= (c->dma_sig & ~0x1f) << 14;
+	}
+	if (od->plat->errata & DMA_ERRATA_IFRAME_BUFFERING)
+		c->ccr |= CCR_BUFFERING_DISABLE;
+
+	return ret;
+}
+
+static void omap_dma_free_chan_resources(struct dma_chan *chan)
+{
+	struct omap_dmadev *od = to_omap_dma_dev(chan->device);
+	struct omap_chan *c = to_omap_dma_chan(chan);
+
+	if (!od->legacy) {
+		spin_lock_irq(&od->irq_lock);
+		od->irq_enable_mask &= ~BIT(c->dma_ch);
+		omap_dma_glbl_write(od, IRQENABLE_L1, od->irq_enable_mask);
+		spin_unlock_irq(&od->irq_lock);
+	}
+
+	c->channel_base = NULL;
+	od->lch_map[c->dma_ch] = NULL;
+	vchan_free_chan_resources(&c->vc);
+
+	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);
+	c->dma_sig = 0;
+}
+
+static size_t omap_dma_sg_size(struct omap_sg *sg)
+{
+	return sg->en * sg->fn;
+}
+
+static size_t omap_dma_desc_size(struct omap_desc *d)
+{
+	unsigned i;
+	size_t size;
+
+	for (size = i = 0; i < d->sglen; i++)
+		size += omap_dma_sg_size(&d->sg[i]);
+
+	return size * es_bytes[d->es];
+}
+
+static size_t omap_dma_desc_size_pos(struct omap_desc *d, dma_addr_t addr)
+{
+	unsigned i;
+	size_t size, es_size = es_bytes[d->es];
+
+	for (size = i = 0; i < d->sglen; i++) {
+		size_t this_size = omap_dma_sg_size(&d->sg[i]) * es_size;
+
+		if (size)
+			size += this_size;
+		else if (addr >= d->sg[i].addr &&
+			 addr < d->sg[i].addr + this_size)
+			size += d->sg[i].addr + this_size - addr;
+	}
+	return size;
+}
+
+/*
+ * OMAP 3.2/3.3 erratum: sometimes 0 is returned if CSAC/CDAC is
+ * read before the DMA controller finished disabling the channel.
+ */
+static uint32_t omap_dma_chan_read_3_3(struct omap_chan *c, unsigned reg)
+{
+	struct omap_dmadev *od = to_omap_dma_dev(c->vc.chan.device);
+	uint32_t val;
+
+	val = omap_dma_chan_read(c, reg);
+	if (val == 0 && od->plat->errata & DMA_ERRATA_3_3)
+		val = omap_dma_chan_read(c, reg);
+
+	return val;
+}
+
+static dma_addr_t omap_dma_get_src_pos(struct omap_chan *c)
+{
+	struct omap_dmadev *od = to_omap_dma_dev(c->vc.chan.device);
+	dma_addr_t addr, cdac;
+
+	if (__dma_omap15xx(od->plat->dma_attr)) {
+		addr = omap_dma_chan_read(c, CPC);
+	} else {
+		addr = omap_dma_chan_read_3_3(c, CSAC);
+		cdac = omap_dma_chan_read_3_3(c, CDAC);
+
+		/*
+		 * CDAC == 0 indicates that the DMA transfer on the channel has
+		 * not been started (no data has been transferred so far).
+		 * Return the programmed source start address in this case.
+		 */
+		if (cdac == 0)
+			addr = omap_dma_chan_read(c, CSSA);
+	}
+
+	if (dma_omap1())
+		addr |= omap_dma_chan_read(c, CSSA) & 0xffff0000;
+
+	return addr;
+}
+
+static dma_addr_t omap_dma_get_dst_pos(struct omap_chan *c)
+{
+	struct omap_dmadev *od = to_omap_dma_dev(c->vc.chan.device);
+	dma_addr_t addr;
+
+	if (__dma_omap15xx(od->plat->dma_attr)) {
+		addr = omap_dma_chan_read(c, CPC);
+	} else {
+		addr = omap_dma_chan_read_3_3(c, CDAC);
+
+		/*
+		 * CDAC == 0 indicates that the DMA transfer on the channel
+		 * has not been started (no data has been transferred so
+		 * far).  Return the programmed destination start address in
+		 * this case.
+		 */
+		if (addr == 0)
+			addr = omap_dma_chan_read(c, CDSA);
+	}
+
+	if (dma_omap1())
+		addr |= omap_dma_chan_read(c, CDSA) & 0xffff0000;
+
+	return addr;
+}
+
+static enum dma_status omap_dma_tx_status(struct dma_chan *chan,
+	dma_cookie_t cookie, struct dma_tx_state *txstate)
+{
+	struct omap_chan *c = to_omap_dma_chan(chan);
+	enum dma_status ret;
+	unsigned long flags;
+	struct omap_desc *d = NULL;
+
+	ret = dma_cookie_status(chan, cookie, txstate);
+	if (ret == DMA_COMPLETE)
+		return ret;
+
+	spin_lock_irqsave(&c->vc.lock, flags);
+	if (c->desc && c->desc->vd.tx.cookie == cookie)
+		d = c->desc;
+
+	if (!txstate)
+		goto out;
+
+	if (d) {
+		dma_addr_t pos;
+
+		if (d->dir == DMA_MEM_TO_DEV)
+			pos = omap_dma_get_src_pos(c);
+		else if (d->dir == DMA_DEV_TO_MEM  || d->dir == DMA_MEM_TO_MEM)
+			pos = omap_dma_get_dst_pos(c);
+		else
+			pos = 0;
+
+		txstate->residue = omap_dma_desc_size_pos(d, pos);
+	} else {
+		struct virt_dma_desc *vd = vchan_find_desc(&c->vc, cookie);
+
+		if (vd)
+			txstate->residue = omap_dma_desc_size(
+						to_omap_dma_desc(&vd->tx));
+		else
+			txstate->residue = 0;
+	}
+
+out:
+	if (ret == DMA_IN_PROGRESS && c->paused) {
+		ret = DMA_PAUSED;
+	} else if (d && d->polled && c->running) {
+		uint32_t ccr = omap_dma_chan_read(c, CCR);
+		/*
+		 * The channel is no longer active, set the return value
+		 * accordingly and mark it as completed
+		 */
+		if (!(ccr & CCR_ENABLE)) {
+			ret = DMA_COMPLETE;
+			omap_dma_start_desc(c);
+			vchan_cookie_complete(&d->vd);
+		}
+	}
+
+	spin_unlock_irqrestore(&c->vc.lock, flags);
+
+	return ret;
+}
+
+static void omap_dma_issue_pending(struct dma_chan *chan)
+{
+	struct omap_chan *c = to_omap_dma_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&c->vc.lock, flags);
+	if (vchan_issue_pending(&c->vc) && !c->desc)
+		omap_dma_start_desc(c);
+	spin_unlock_irqrestore(&c->vc.lock, flags);
+}
+
+static struct dma_async_tx_descriptor *omap_dma_prep_slave_sg(
+	struct dma_chan *chan, struct scatterlist *sgl, unsigned sglen,
+	enum dma_transfer_direction dir, unsigned long tx_flags, void *context)
+{
+	struct omap_dmadev *od = to_omap_dma_dev(chan->device);
+	struct omap_chan *c = to_omap_dma_chan(chan);
+	enum dma_slave_buswidth dev_width;
+	struct scatterlist *sgent;
+	struct omap_desc *d;
+	dma_addr_t dev_addr;
+	unsigned i, es, en, frame_bytes;
+	bool ll_failed = false;
+	u32 burst;
+	u32 port_window, port_window_bytes;
+
+	if (dir == DMA_DEV_TO_MEM) {
+		dev_addr = c->cfg.src_addr;
+		dev_width = c->cfg.src_addr_width;
+		burst = c->cfg.src_maxburst;
+		port_window = c->cfg.src_port_window_size;
+	} else if (dir == DMA_MEM_TO_DEV) {
+		dev_addr = c->cfg.dst_addr;
+		dev_width = c->cfg.dst_addr_width;
+		burst = c->cfg.dst_maxburst;
+		port_window = c->cfg.dst_port_window_size;
+	} else {
+		dev_err(chan->device->dev, "%s: bad direction?\n", __func__);
+		return NULL;
+	}
+
+	/* Bus width translates to the element size (ES) */
+	switch (dev_width) {
+	case DMA_SLAVE_BUSWIDTH_1_BYTE:
+		es = CSDP_DATA_TYPE_8;
+		break;
+	case DMA_SLAVE_BUSWIDTH_2_BYTES:
+		es = CSDP_DATA_TYPE_16;
+		break;
+	case DMA_SLAVE_BUSWIDTH_4_BYTES:
+		es = CSDP_DATA_TYPE_32;
+		break;
+	default: /* not reached */
+		return NULL;
+	}
+
+	/* Now allocate and setup the descriptor. */
+	d = kzalloc(struct_size(d, sg, sglen), GFP_ATOMIC);
+	if (!d)
+		return NULL;
+
+	d->dir = dir;
+	d->dev_addr = dev_addr;
+	d->es = es;
+
+	/* When the port_window is used, one frame must cover the window */
+	if (port_window) {
+		burst = port_window;
+		port_window_bytes = port_window * es_bytes[es];
+
+		d->ei = 1;
+		/*
+		 * One frame covers the port_window and by  configure
+		 * the source frame index to be -1 * (port_window - 1)
+		 * we instruct the sDMA that after a frame is processed
+		 * it should move back to the start of the window.
+		 */
+		d->fi = -(port_window_bytes - 1);
+	}
+
+	d->ccr = c->ccr | CCR_SYNC_FRAME;
+	if (dir == DMA_DEV_TO_MEM) {
+		d->csdp = CSDP_DST_BURST_64 | CSDP_DST_PACKED;
+
+		d->ccr |= CCR_DST_AMODE_POSTINC;
+		if (port_window) {
+			d->ccr |= CCR_SRC_AMODE_DBLIDX;
+
+			if (port_window_bytes >= 64)
+				d->csdp |= CSDP_SRC_BURST_64;
+			else if (port_window_bytes >= 32)
+				d->csdp |= CSDP_SRC_BURST_32;
+			else if (port_window_bytes >= 16)
+				d->csdp |= CSDP_SRC_BURST_16;
+
+		} else {
+			d->ccr |= CCR_SRC_AMODE_CONSTANT;
+		}
+	} else {
+		d->csdp = CSDP_SRC_BURST_64 | CSDP_SRC_PACKED;
+
+		d->ccr |= CCR_SRC_AMODE_POSTINC;
+		if (port_window) {
+			d->ccr |= CCR_DST_AMODE_DBLIDX;
+
+			if (port_window_bytes >= 64)
+				d->csdp |= CSDP_DST_BURST_64;
+			else if (port_window_bytes >= 32)
+				d->csdp |= CSDP_DST_BURST_32;
+			else if (port_window_bytes >= 16)
+				d->csdp |= CSDP_DST_BURST_16;
+		} else {
+			d->ccr |= CCR_DST_AMODE_CONSTANT;
+		}
+	}
+
+	d->cicr = CICR_DROP_IE | CICR_BLOCK_IE;
+	d->csdp |= es;
+
+	if (dma_omap1()) {
+		d->cicr |= CICR_TOUT_IE;
+
+		if (dir == DMA_DEV_TO_MEM)
+			d->csdp |= CSDP_DST_PORT_EMIFF | CSDP_SRC_PORT_TIPB;
+		else
+			d->csdp |= CSDP_DST_PORT_TIPB | CSDP_SRC_PORT_EMIFF;
+	} else {
+		if (dir == DMA_DEV_TO_MEM)
+			d->ccr |= CCR_TRIGGER_SRC;
+
+		d->cicr |= CICR_MISALIGNED_ERR_IE | CICR_TRANS_ERR_IE;
+
+		if (port_window)
+			d->csdp |= CSDP_WRITE_LAST_NON_POSTED;
+	}
+	if (od->plat->errata & DMA_ERRATA_PARALLEL_CHANNELS)
+		d->clnk_ctrl = c->dma_ch;
+
+	/*
+	 * Build our scatterlist entries: each contains the address,
+	 * the number of elements (EN) in each frame, and the number of
+	 * frames (FN).  Number of bytes for this entry = ES * EN * FN.
+	 *
+	 * Burst size translates to number of elements with frame sync.
+	 * Note: DMA engine defines burst to be the number of dev-width
+	 * transfers.
+	 */
+	en = burst;
+	frame_bytes = es_bytes[es] * en;
+
+	if (sglen >= 2)
+		d->using_ll = od->ll123_supported;
+
+	for_each_sg(sgl, sgent, sglen, i) {
+		struct omap_sg *osg = &d->sg[i];
+
+		osg->addr = sg_dma_address(sgent);
+		osg->en = en;
+		osg->fn = sg_dma_len(sgent) / frame_bytes;
+
+		if (d->using_ll) {
+			osg->t2_desc = dma_pool_alloc(od->desc_pool, GFP_ATOMIC,
+						      &osg->t2_desc_paddr);
+			if (!osg->t2_desc) {
+				dev_err(chan->device->dev,
+					"t2_desc[%d] allocation failed\n", i);
+				ll_failed = true;
+				d->using_ll = false;
+				continue;
+			}
+
+			omap_dma_fill_type2_desc(d, i, dir, (i == sglen - 1));
+		}
+	}
+
+	d->sglen = sglen;
+
+	/* Release the dma_pool entries if one allocation failed */
+	if (ll_failed) {
+		for (i = 0; i < d->sglen; i++) {
+			struct omap_sg *osg = &d->sg[i];
+
+			if (osg->t2_desc) {
+				dma_pool_free(od->desc_pool, osg->t2_desc,
+					      osg->t2_desc_paddr);
+				osg->t2_desc = NULL;
+			}
+		}
+	}
+
+	return vchan_tx_prep(&c->vc, &d->vd, tx_flags);
+}
+
+static struct dma_async_tx_descriptor *omap_dma_prep_dma_cyclic(
+	struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
+	size_t period_len, enum dma_transfer_direction dir, unsigned long flags)
+{
+	struct omap_dmadev *od = to_omap_dma_dev(chan->device);
+	struct omap_chan *c = to_omap_dma_chan(chan);
+	enum dma_slave_buswidth dev_width;
+	struct omap_desc *d;
+	dma_addr_t dev_addr;
+	unsigned es;
+	u32 burst;
+
+	if (dir == DMA_DEV_TO_MEM) {
+		dev_addr = c->cfg.src_addr;
+		dev_width = c->cfg.src_addr_width;
+		burst = c->cfg.src_maxburst;
+	} else if (dir == DMA_MEM_TO_DEV) {
+		dev_addr = c->cfg.dst_addr;
+		dev_width = c->cfg.dst_addr_width;
+		burst = c->cfg.dst_maxburst;
+	} else {
+		dev_err(chan->device->dev, "%s: bad direction?\n", __func__);
+		return NULL;
+	}
+
+	/* Bus width translates to the element size (ES) */
+	switch (dev_width) {
+	case DMA_SLAVE_BUSWIDTH_1_BYTE:
+		es = CSDP_DATA_TYPE_8;
+		break;
+	case DMA_SLAVE_BUSWIDTH_2_BYTES:
+		es = CSDP_DATA_TYPE_16;
+		break;
+	case DMA_SLAVE_BUSWIDTH_4_BYTES:
+		es = CSDP_DATA_TYPE_32;
+		break;
+	default: /* not reached */
+		return NULL;
+	}
+
+	/* Now allocate and setup the descriptor. */
+	d = kzalloc(sizeof(*d) + sizeof(d->sg[0]), GFP_ATOMIC);
+	if (!d)
+		return NULL;
+
+	d->dir = dir;
+	d->dev_addr = dev_addr;
+	d->fi = burst;
+	d->es = es;
+	d->sg[0].addr = buf_addr;
+	d->sg[0].en = period_len / es_bytes[es];
+	d->sg[0].fn = buf_len / period_len;
+	d->sglen = 1;
+
+	d->ccr = c->ccr;
+	if (dir == DMA_DEV_TO_MEM)
+		d->ccr |= CCR_DST_AMODE_POSTINC | CCR_SRC_AMODE_CONSTANT;
+	else
+		d->ccr |= CCR_DST_AMODE_CONSTANT | CCR_SRC_AMODE_POSTINC;
+
+	d->cicr = CICR_DROP_IE;
+	if (flags & DMA_PREP_INTERRUPT)
+		d->cicr |= CICR_FRAME_IE;
+
+	d->csdp = es;
+
+	if (dma_omap1()) {
+		d->cicr |= CICR_TOUT_IE;
+
+		if (dir == DMA_DEV_TO_MEM)
+			d->csdp |= CSDP_DST_PORT_EMIFF | CSDP_SRC_PORT_MPUI;
+		else
+			d->csdp |= CSDP_DST_PORT_MPUI | CSDP_SRC_PORT_EMIFF;
+	} else {
+		if (burst)
+			d->ccr |= CCR_SYNC_PACKET;
+		else
+			d->ccr |= CCR_SYNC_ELEMENT;
+
+		if (dir == DMA_DEV_TO_MEM) {
+			d->ccr |= CCR_TRIGGER_SRC;
+			d->csdp |= CSDP_DST_PACKED;
+		} else {
+			d->csdp |= CSDP_SRC_PACKED;
+		}
+
+		d->cicr |= CICR_MISALIGNED_ERR_IE | CICR_TRANS_ERR_IE;
+
+		d->csdp |= CSDP_DST_BURST_64 | CSDP_SRC_BURST_64;
+	}
+
+	if (__dma_omap15xx(od->plat->dma_attr))
+		d->ccr |= CCR_AUTO_INIT | CCR_REPEAT;
+	else
+		d->clnk_ctrl = c->dma_ch | CLNK_CTRL_ENABLE_LNK;
+
+	c->cyclic = true;
+
+	return vchan_tx_prep(&c->vc, &d->vd, flags);
+}
+
+static struct dma_async_tx_descriptor *omap_dma_prep_dma_memcpy(
+	struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
+	size_t len, unsigned long tx_flags)
+{
+	struct omap_chan *c = to_omap_dma_chan(chan);
+	struct omap_desc *d;
+	uint8_t data_type;
+
+	d = kzalloc(sizeof(*d) + sizeof(d->sg[0]), GFP_ATOMIC);
+	if (!d)
+		return NULL;
+
+	data_type = __ffs((src | dest | len));
+	if (data_type > CSDP_DATA_TYPE_32)
+		data_type = CSDP_DATA_TYPE_32;
+
+	d->dir = DMA_MEM_TO_MEM;
+	d->dev_addr = src;
+	d->fi = 0;
+	d->es = data_type;
+	d->sg[0].en = len / BIT(data_type);
+	d->sg[0].fn = 1;
+	d->sg[0].addr = dest;
+	d->sglen = 1;
+	d->ccr = c->ccr;
+	d->ccr |= CCR_DST_AMODE_POSTINC | CCR_SRC_AMODE_POSTINC;
+
+	if (tx_flags & DMA_PREP_INTERRUPT)
+		d->cicr |= CICR_FRAME_IE;
+	else
+		d->polled = true;
+
+	d->csdp = data_type;
+
+	if (dma_omap1()) {
+		d->cicr |= CICR_TOUT_IE;
+		d->csdp |= CSDP_DST_PORT_EMIFF | CSDP_SRC_PORT_EMIFF;
+	} else {
+		d->csdp |= CSDP_DST_PACKED | CSDP_SRC_PACKED;
+		d->cicr |= CICR_MISALIGNED_ERR_IE | CICR_TRANS_ERR_IE;
+		d->csdp |= CSDP_DST_BURST_64 | CSDP_SRC_BURST_64;
+	}
+
+	return vchan_tx_prep(&c->vc, &d->vd, tx_flags);
+}
+
+static struct dma_async_tx_descriptor *omap_dma_prep_dma_interleaved(
+	struct dma_chan *chan, struct dma_interleaved_template *xt,
+	unsigned long flags)
+{
+	struct omap_chan *c = to_omap_dma_chan(chan);
+	struct omap_desc *d;
+	struct omap_sg *sg;
+	uint8_t data_type;
+	size_t src_icg, dst_icg;
+
+	/* Slave mode is not supported */
+	if (is_slave_direction(xt->dir))
+		return NULL;
+
+	if (xt->frame_size != 1 || xt->numf == 0)
+		return NULL;
+
+	d = kzalloc(sizeof(*d) + sizeof(d->sg[0]), GFP_ATOMIC);
+	if (!d)
+		return NULL;
+
+	data_type = __ffs((xt->src_start | xt->dst_start | xt->sgl[0].size));
+	if (data_type > CSDP_DATA_TYPE_32)
+		data_type = CSDP_DATA_TYPE_32;
+
+	sg = &d->sg[0];
+	d->dir = DMA_MEM_TO_MEM;
+	d->dev_addr = xt->src_start;
+	d->es = data_type;
+	sg->en = xt->sgl[0].size / BIT(data_type);
+	sg->fn = xt->numf;
+	sg->addr = xt->dst_start;
+	d->sglen = 1;
+	d->ccr = c->ccr;
+
+	src_icg = dmaengine_get_src_icg(xt, &xt->sgl[0]);
+	dst_icg = dmaengine_get_dst_icg(xt, &xt->sgl[0]);
+	if (src_icg) {
+		d->ccr |= CCR_SRC_AMODE_DBLIDX;
+		d->ei = 1;
+		d->fi = src_icg + 1;
+	} else if (xt->src_inc) {
+		d->ccr |= CCR_SRC_AMODE_POSTINC;
+		d->fi = 0;
+	} else {
+		dev_err(chan->device->dev,
+			"%s: SRC constant addressing is not supported\n",
+			__func__);
+		kfree(d);
+		return NULL;
+	}
+
+	if (dst_icg) {
+		d->ccr |= CCR_DST_AMODE_DBLIDX;
+		sg->ei = 1;
+		sg->fi = dst_icg + 1;
+	} else if (xt->dst_inc) {
+		d->ccr |= CCR_DST_AMODE_POSTINC;
+		sg->fi = 0;
+	} else {
+		dev_err(chan->device->dev,
+			"%s: DST constant addressing is not supported\n",
+			__func__);
+		kfree(d);
+		return NULL;
+	}
+
+	d->cicr = CICR_DROP_IE | CICR_FRAME_IE;
+
+	d->csdp = data_type;
+
+	if (dma_omap1()) {
+		d->cicr |= CICR_TOUT_IE;
+		d->csdp |= CSDP_DST_PORT_EMIFF | CSDP_SRC_PORT_EMIFF;
+	} else {
+		d->csdp |= CSDP_DST_PACKED | CSDP_SRC_PACKED;
+		d->cicr |= CICR_MISALIGNED_ERR_IE | CICR_TRANS_ERR_IE;
+		d->csdp |= CSDP_DST_BURST_64 | CSDP_SRC_BURST_64;
+	}
+
+	return vchan_tx_prep(&c->vc, &d->vd, flags);
+}
+
+static int omap_dma_slave_config(struct dma_chan *chan, struct dma_slave_config *cfg)
+{
+	struct omap_chan *c = to_omap_dma_chan(chan);
+
+	if (cfg->src_addr_width == DMA_SLAVE_BUSWIDTH_8_BYTES ||
+	    cfg->dst_addr_width == DMA_SLAVE_BUSWIDTH_8_BYTES)
+		return -EINVAL;
+
+	if (cfg->src_maxburst > chan->device->max_burst ||
+	    cfg->dst_maxburst > chan->device->max_burst)
+		return -EINVAL;
+
+	memcpy(&c->cfg, cfg, sizeof(c->cfg));
+
+	return 0;
+}
+
+static int omap_dma_terminate_all(struct dma_chan *chan)
+{
+	struct omap_chan *c = to_omap_dma_chan(chan);
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	spin_lock_irqsave(&c->vc.lock, flags);
+
+	/*
+	 * Stop DMA activity: we assume the callback will not be called
+	 * after omap_dma_stop() returns (even if it does, it will see
+	 * c->desc is NULL and exit.)
+	 */
+	if (c->desc) {
+		vchan_terminate_vdesc(&c->desc->vd);
+		c->desc = NULL;
+		/* Avoid stopping the dma twice */
+		if (!c->paused)
+			omap_dma_stop(c);
+	}
+
+	c->cyclic = false;
+	c->paused = false;
+
+	vchan_get_all_descriptors(&c->vc, &head);
+	spin_unlock_irqrestore(&c->vc.lock, flags);
+	vchan_dma_desc_free_list(&c->vc, &head);
+
+	return 0;
+}
+
+static void omap_dma_synchronize(struct dma_chan *chan)
+{
+	struct omap_chan *c = to_omap_dma_chan(chan);
+
+	vchan_synchronize(&c->vc);
+}
+
+static int omap_dma_pause(struct dma_chan *chan)
+{
+	struct omap_chan *c = to_omap_dma_chan(chan);
+	struct omap_dmadev *od = to_omap_dma_dev(chan->device);
+	unsigned long flags;
+	int ret = -EINVAL;
+	bool can_pause = false;
+
+	spin_lock_irqsave(&od->irq_lock, flags);
+
+	if (!c->desc)
+		goto out;
+
+	if (c->cyclic)
+		can_pause = true;
+
+	/*
+	 * We do not allow DMA_MEM_TO_DEV transfers to be paused.
+	 * From the AM572x TRM, 16.1.4.18 Disabling a Channel During Transfer:
+	 * "When a channel is disabled during a transfer, the channel undergoes
+	 * an abort, unless it is hardware-source-synchronized …".
+	 * A source-synchronised channel is one where the fetching of data is
+	 * under control of the device. In other words, a device-to-memory
+	 * transfer. So, a destination-synchronised channel (which would be a
+	 * memory-to-device transfer) undergoes an abort if the the CCR_ENABLE
+	 * bit is cleared.
+	 * From 16.1.4.20.4.6.2 Abort: "If an abort trigger occurs, the channel
+	 * aborts immediately after completion of current read/write
+	 * transactions and then the FIFO is cleaned up." The term "cleaned up"
+	 * is not defined. TI recommends to check that RD_ACTIVE and WR_ACTIVE
+	 * are both clear _before_ disabling the channel, otherwise data loss
+	 * will occur.
+	 * The problem is that if the channel is active, then device activity
+	 * can result in DMA activity starting between reading those as both
+	 * clear and the write to DMA_CCR to clear the enable bit hitting the
+	 * hardware. If the DMA hardware can't drain the data in its FIFO to the
+	 * destination, then data loss "might" occur (say if we write to an UART
+	 * and the UART is not accepting any further data).
+	 */
+	else if (c->desc->dir == DMA_DEV_TO_MEM)
+		can_pause = true;
+
+	if (can_pause && !c->paused) {
+		ret = omap_dma_stop(c);
+		if (!ret)
+			c->paused = true;
+	}
+out:
+	spin_unlock_irqrestore(&od->irq_lock, flags);
+
+	return ret;
+}
+
+static int omap_dma_resume(struct dma_chan *chan)
+{
+	struct omap_chan *c = to_omap_dma_chan(chan);
+	struct omap_dmadev *od = to_omap_dma_dev(chan->device);
+	unsigned long flags;
+	int ret = -EINVAL;
+
+	spin_lock_irqsave(&od->irq_lock, flags);
+
+	if (c->paused && c->desc) {
+		mb();
+
+		/* Restore channel link register */
+		omap_dma_chan_write(c, CLNK_CTRL, c->desc->clnk_ctrl);
+
+		omap_dma_start(c, c->desc);
+		c->paused = false;
+		ret = 0;
+	}
+	spin_unlock_irqrestore(&od->irq_lock, flags);
+
+	return ret;
+}
+
+static int omap_dma_chan_init(struct omap_dmadev *od)
+{
+	struct omap_chan *c;
+
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return -ENOMEM;
+
+	c->reg_map = od->reg_map;
+	c->vc.desc_free = omap_dma_desc_free;
+	vchan_init(&c->vc, &od->ddev);
+
+	return 0;
+}
+
+static void omap_dma_free(struct omap_dmadev *od)
+{
+	while (!list_empty(&od->ddev.channels)) {
+		struct omap_chan *c = list_first_entry(&od->ddev.channels,
+			struct omap_chan, vc.chan.device_node);
+
+		list_del(&c->vc.chan.device_node);
+		tasklet_kill(&c->vc.task);
+		kfree(c);
+	}
+}
+
+/* Currently used by omap2 & 3 to block deeper SoC idle states */
+static bool omap_dma_busy(struct omap_dmadev *od)
+{
+	struct omap_chan *c;
+	int lch = -1;
+
+	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 true;
+	}
+
+	return false;
+}
+
+/* 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;
+
+	od = container_of(nb, struct omap_dmadev, nb);
+
+	switch (cmd) {
+	case CPU_CLUSTER_PM_ENTER:
+		if (omap_dma_busy(od))
+			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:
+		if (omap_dma_busy(od))
+			return NOTIFY_BAD;
+		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 val;
+
+	od = devm_kzalloc(&pdev->dev, sizeof(*od), GFP_KERNEL);
+	if (!od)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	od->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(od->base))
+		return PTR_ERR(od->base);
+
+	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;
+
+	dma_cap_set(DMA_SLAVE, od->ddev.cap_mask);
+	dma_cap_set(DMA_CYCLIC, od->ddev.cap_mask);
+	dma_cap_set(DMA_MEMCPY, od->ddev.cap_mask);
+	dma_cap_set(DMA_INTERLEAVE, od->ddev.cap_mask);
+	od->ddev.device_alloc_chan_resources = omap_dma_alloc_chan_resources;
+	od->ddev.device_free_chan_resources = omap_dma_free_chan_resources;
+	od->ddev.device_tx_status = omap_dma_tx_status;
+	od->ddev.device_issue_pending = omap_dma_issue_pending;
+	od->ddev.device_prep_slave_sg = omap_dma_prep_slave_sg;
+	od->ddev.device_prep_dma_cyclic = omap_dma_prep_dma_cyclic;
+	od->ddev.device_prep_dma_memcpy = omap_dma_prep_dma_memcpy;
+	od->ddev.device_prep_interleaved_dma = omap_dma_prep_dma_interleaved;
+	od->ddev.device_config = omap_dma_slave_config;
+	od->ddev.device_pause = omap_dma_pause;
+	od->ddev.device_resume = omap_dma_resume;
+	od->ddev.device_terminate_all = omap_dma_terminate_all;
+	od->ddev.device_synchronize = omap_dma_synchronize;
+	od->ddev.src_addr_widths = OMAP_DMA_BUSWIDTHS;
+	od->ddev.dst_addr_widths = OMAP_DMA_BUSWIDTHS;
+	od->ddev.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
+	if (__dma_omap15xx(od->plat->dma_attr))
+		od->ddev.residue_granularity =
+				DMA_RESIDUE_GRANULARITY_DESCRIPTOR;
+	else
+		od->ddev.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
+	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);
+
+	/* Number of DMA requests */
+	od->dma_requests = OMAP_SDMA_REQUESTS;
+	if (pdev->dev.of_node && of_property_read_u32(pdev->dev.of_node,
+						      "dma-requests",
+						      &od->dma_requests)) {
+		dev_info(&pdev->dev,
+			 "Missing dma-requests property, using %u.\n",
+			 OMAP_SDMA_REQUESTS);
+	}
+
+	/* Number of available logical channels */
+	if (!pdev->dev.of_node) {
+		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",
+					&od->lch_count)) {
+		dev_info(&pdev->dev,
+			 "Missing dma-channels property, using %u.\n",
+			 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, od->lch_count,
+				   sizeof(*od->lch_map),
+				   GFP_KERNEL);
+	if (!od->lch_map)
+		return -ENOMEM;
+
+	for (i = 0; i < od->dma_requests; i++) {
+		rc = omap_dma_chan_init(od);
+		if (rc) {
+			omap_dma_free(od);
+			return rc;
+		}
+	}
+
+	irq = platform_get_irq(pdev, 1);
+	if (irq <= 0) {
+		dev_info(&pdev->dev, "failed to get L1 IRQ: %d\n", irq);
+		od->legacy = true;
+	} else {
+		/* Disable all interrupts */
+		od->irq_enable_mask = 0;
+		omap_dma_glbl_write(od, IRQENABLE_L1, 0);
+
+		rc = devm_request_irq(&pdev->dev, irq, omap_dma_irq,
+				      IRQF_SHARED, "omap-dma-engine", od);
+		if (rc) {
+			omap_dma_free(od);
+			return rc;
+		}
+	}
+
+	if (omap_dma_glbl_read(od, CAPS_0) & CAPS_0_SUPPORT_LL123)
+		od->ll123_supported = true;
+
+	od->ddev.filter.map = od->plat->slave_map;
+	od->ddev.filter.mapcnt = od->plat->slavecnt;
+	od->ddev.filter.fn = omap_dma_filter_fn;
+
+	if (od->ll123_supported) {
+		od->desc_pool = dma_pool_create(dev_name(&pdev->dev),
+						&pdev->dev,
+						sizeof(struct omap_type2_desc),
+						4, 0);
+		if (!od->desc_pool) {
+			dev_err(&pdev->dev,
+				"unable to allocate descriptor pool\n");
+			od->ll123_supported = false;
+		}
+	}
+
+	rc = dma_async_device_register(&od->ddev);
+	if (rc) {
+		pr_warn("OMAP-DMA: failed to register slave DMA engine device: %d\n",
+			rc);
+		omap_dma_free(od);
+		return rc;
+	}
+
+	platform_set_drvdata(pdev, od);
+
+	if (pdev->dev.of_node) {
+		omap_dma_info.dma_cap = od->ddev.cap_mask;
+
+		/* Device-tree DMA controller registration */
+		rc = of_dma_controller_register(pdev->dev.of_node,
+				of_dma_simple_xlate, &omap_dma_info);
+		if (rc) {
+			pr_warn("OMAP-DMA: failed to register DMA controller\n");
+			dma_async_device_unregister(&od->ddev);
+			omap_dma_free(od);
+		}
+	}
+
+	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)" : "");
+
+	return rc;
+}
+
+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);
+
+	irq = platform_get_irq(pdev, 1);
+	devm_free_irq(&pdev->dev, irq, od);
+
+	dma_async_device_unregister(&od->ddev);
+
+	if (!od->legacy) {
+		/* Disable all interrupts */
+		omap_dma_glbl_write(od, IRQENABLE_L0, 0);
+	}
+
+	if (od->ll123_supported)
+		dma_pool_destroy(od->desc_pool);
+
+	omap_dma_free(od);
+
+	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", .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);
+
+static struct platform_driver omap_dma_driver = {
+	.probe	= omap_dma_probe,
+	.remove	= omap_dma_remove,
+	.driver = {
+		.name = "omap-dma-engine",
+		.of_match_table = omap_dma_match,
+	},
+};
+
+static bool omap_dma_filter_fn(struct dma_chan *chan, void *param)
+{
+	if (chan->device->dev->driver == &omap_dma_driver.driver) {
+		struct omap_dmadev *od = to_omap_dma_dev(chan->device);
+		struct omap_chan *c = to_omap_dma_chan(chan);
+		unsigned req = *(unsigned *)param;
+
+		if (req <= od->dma_requests) {
+			c->dma_sig = req;
+			return true;
+		}
+	}
+	return false;
+}
+
+static int omap_dma_init(void)
+{
+	return platform_driver_register(&omap_dma_driver);
+}
+subsys_initcall(omap_dma_init);
+
+static void __exit omap_dma_exit(void)
+{
+	platform_driver_unregister(&omap_dma_driver);
+}
+module_exit(omap_dma_exit);
+
+MODULE_AUTHOR("Russell King");
+MODULE_LICENSE("GPL");
diff --git a/drivers/dma/timb_dma.c b/drivers/dma/timb_dma.c
new file mode 100644
index 000000000..3f524be69
--- /dev/null
+++ b/drivers/dma/timb_dma.c
@@ -0,0 +1,773 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * timb_dma.c timberdale FPGA DMA driver
+ * Copyright (c) 2010 Intel Corporation
+ */
+
+/* Supports:
+ * Timberdale FPGA DMA engine
+ */
+
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#include <linux/timb_dma.h>
+
+#include "dmaengine.h"
+
+#define DRIVER_NAME "timb-dma"
+
+/* Global DMA registers */
+#define TIMBDMA_ACR		0x34
+#define TIMBDMA_32BIT_ADDR	0x01
+
+#define TIMBDMA_ISR		0x080000
+#define TIMBDMA_IPR		0x080004
+#define TIMBDMA_IER		0x080008
+
+/* Channel specific registers */
+/* RX instances base addresses are 0x00, 0x40, 0x80 ...
+ * TX instances base addresses are 0x18, 0x58, 0x98 ...
+ */
+#define TIMBDMA_INSTANCE_OFFSET		0x40
+#define TIMBDMA_INSTANCE_TX_OFFSET	0x18
+
+/* RX registers, relative the instance base */
+#define TIMBDMA_OFFS_RX_DHAR	0x00
+#define TIMBDMA_OFFS_RX_DLAR	0x04
+#define TIMBDMA_OFFS_RX_LR	0x0C
+#define TIMBDMA_OFFS_RX_BLR	0x10
+#define TIMBDMA_OFFS_RX_ER	0x14
+#define TIMBDMA_RX_EN		0x01
+/* bytes per Row, video specific register
+ * which is placed after the TX registers...
+ */
+#define TIMBDMA_OFFS_RX_BPRR	0x30
+
+/* TX registers, relative the instance base */
+#define TIMBDMA_OFFS_TX_DHAR	0x00
+#define TIMBDMA_OFFS_TX_DLAR	0x04
+#define TIMBDMA_OFFS_TX_BLR	0x0C
+#define TIMBDMA_OFFS_TX_LR	0x14
+
+
+#define TIMB_DMA_DESC_SIZE	8
+
+struct timb_dma_desc {
+	struct list_head		desc_node;
+	struct dma_async_tx_descriptor	txd;
+	u8				*desc_list;
+	unsigned int			desc_list_len;
+	bool				interrupt;
+};
+
+struct timb_dma_chan {
+	struct dma_chan		chan;
+	void __iomem		*membase;
+	spinlock_t		lock; /* Used to protect data structures,
+					especially the lists and descriptors,
+					from races between the tasklet and calls
+					from above */
+	bool			ongoing;
+	struct list_head	active_list;
+	struct list_head	queue;
+	struct list_head	free_list;
+	unsigned int		bytes_per_line;
+	enum dma_transfer_direction	direction;
+	unsigned int		descs; /* Descriptors to allocate */
+	unsigned int		desc_elems; /* number of elems per descriptor */
+};
+
+struct timb_dma {
+	struct dma_device	dma;
+	void __iomem		*membase;
+	struct tasklet_struct	tasklet;
+	struct timb_dma_chan	channels[];
+};
+
+static struct device *chan2dev(struct dma_chan *chan)
+{
+	return &chan->dev->device;
+}
+static struct device *chan2dmadev(struct dma_chan *chan)
+{
+	return chan2dev(chan)->parent->parent;
+}
+
+static struct timb_dma *tdchantotd(struct timb_dma_chan *td_chan)
+{
+	int id = td_chan->chan.chan_id;
+	return (struct timb_dma *)((u8 *)td_chan -
+		id * sizeof(struct timb_dma_chan) - sizeof(struct timb_dma));
+}
+
+/* Must be called with the spinlock held */
+static void __td_enable_chan_irq(struct timb_dma_chan *td_chan)
+{
+	int id = td_chan->chan.chan_id;
+	struct timb_dma *td = tdchantotd(td_chan);
+	u32 ier;
+
+	/* enable interrupt for this channel */
+	ier = ioread32(td->membase + TIMBDMA_IER);
+	ier |= 1 << id;
+	dev_dbg(chan2dev(&td_chan->chan), "Enabling irq: %d, IER: 0x%x\n", id,
+		ier);
+	iowrite32(ier, td->membase + TIMBDMA_IER);
+}
+
+/* Should be called with the spinlock held */
+static bool __td_dma_done_ack(struct timb_dma_chan *td_chan)
+{
+	int id = td_chan->chan.chan_id;
+	struct timb_dma *td = (struct timb_dma *)((u8 *)td_chan -
+		id * sizeof(struct timb_dma_chan) - sizeof(struct timb_dma));
+	u32 isr;
+	bool done = false;
+
+	dev_dbg(chan2dev(&td_chan->chan), "Checking irq: %d, td: %p\n", id, td);
+
+	isr = ioread32(td->membase + TIMBDMA_ISR) & (1 << id);
+	if (isr) {
+		iowrite32(isr, td->membase + TIMBDMA_ISR);
+		done = true;
+	}
+
+	return done;
+}
+
+static int td_fill_desc(struct timb_dma_chan *td_chan, u8 *dma_desc,
+	struct scatterlist *sg, bool last)
+{
+	if (sg_dma_len(sg) > USHRT_MAX) {
+		dev_err(chan2dev(&td_chan->chan), "Too big sg element\n");
+		return -EINVAL;
+	}
+
+	/* length must be word aligned */
+	if (sg_dma_len(sg) % sizeof(u32)) {
+		dev_err(chan2dev(&td_chan->chan), "Incorrect length: %d\n",
+			sg_dma_len(sg));
+		return -EINVAL;
+	}
+
+	dev_dbg(chan2dev(&td_chan->chan), "desc: %p, addr: 0x%llx\n",
+		dma_desc, (unsigned long long)sg_dma_address(sg));
+
+	dma_desc[7] = (sg_dma_address(sg) >> 24) & 0xff;
+	dma_desc[6] = (sg_dma_address(sg) >> 16) & 0xff;
+	dma_desc[5] = (sg_dma_address(sg) >> 8) & 0xff;
+	dma_desc[4] = (sg_dma_address(sg) >> 0) & 0xff;
+
+	dma_desc[3] = (sg_dma_len(sg) >> 8) & 0xff;
+	dma_desc[2] = (sg_dma_len(sg) >> 0) & 0xff;
+
+	dma_desc[1] = 0x00;
+	dma_desc[0] = 0x21 | (last ? 0x02 : 0); /* tran, valid */
+
+	return 0;
+}
+
+/* Must be called with the spinlock held */
+static void __td_start_dma(struct timb_dma_chan *td_chan)
+{
+	struct timb_dma_desc *td_desc;
+
+	if (td_chan->ongoing) {
+		dev_err(chan2dev(&td_chan->chan),
+			"Transfer already ongoing\n");
+		return;
+	}
+
+	td_desc = list_entry(td_chan->active_list.next, struct timb_dma_desc,
+		desc_node);
+
+	dev_dbg(chan2dev(&td_chan->chan),
+		"td_chan: %p, chan: %d, membase: %p\n",
+		td_chan, td_chan->chan.chan_id, td_chan->membase);
+
+	if (td_chan->direction == DMA_DEV_TO_MEM) {
+
+		/* descriptor address */
+		iowrite32(0, td_chan->membase + TIMBDMA_OFFS_RX_DHAR);
+		iowrite32(td_desc->txd.phys, td_chan->membase +
+			TIMBDMA_OFFS_RX_DLAR);
+		/* Bytes per line */
+		iowrite32(td_chan->bytes_per_line, td_chan->membase +
+			TIMBDMA_OFFS_RX_BPRR);
+		/* enable RX */
+		iowrite32(TIMBDMA_RX_EN, td_chan->membase + TIMBDMA_OFFS_RX_ER);
+	} else {
+		/* address high */
+		iowrite32(0, td_chan->membase + TIMBDMA_OFFS_TX_DHAR);
+		iowrite32(td_desc->txd.phys, td_chan->membase +
+			TIMBDMA_OFFS_TX_DLAR);
+	}
+
+	td_chan->ongoing = true;
+
+	if (td_desc->interrupt)
+		__td_enable_chan_irq(td_chan);
+}
+
+static void __td_finish(struct timb_dma_chan *td_chan)
+{
+	struct dmaengine_desc_callback	cb;
+	struct dma_async_tx_descriptor	*txd;
+	struct timb_dma_desc		*td_desc;
+
+	/* can happen if the descriptor is canceled */
+	if (list_empty(&td_chan->active_list))
+		return;
+
+	td_desc = list_entry(td_chan->active_list.next, struct timb_dma_desc,
+		desc_node);
+	txd = &td_desc->txd;
+
+	dev_dbg(chan2dev(&td_chan->chan), "descriptor %u complete\n",
+		txd->cookie);
+
+	/* make sure to stop the transfer */
+	if (td_chan->direction == DMA_DEV_TO_MEM)
+		iowrite32(0, td_chan->membase + TIMBDMA_OFFS_RX_ER);
+/* Currently no support for stopping DMA transfers
+	else
+		iowrite32(0, td_chan->membase + TIMBDMA_OFFS_TX_DLAR);
+*/
+	dma_cookie_complete(txd);
+	td_chan->ongoing = false;
+
+	dmaengine_desc_get_callback(txd, &cb);
+
+	list_move(&td_desc->desc_node, &td_chan->free_list);
+
+	dma_descriptor_unmap(txd);
+	/*
+	 * The API requires that no submissions are done from a
+	 * callback, so we don't need to drop the lock here
+	 */
+	dmaengine_desc_callback_invoke(&cb, NULL);
+}
+
+static u32 __td_ier_mask(struct timb_dma *td)
+{
+	int i;
+	u32 ret = 0;
+
+	for (i = 0; i < td->dma.chancnt; i++) {
+		struct timb_dma_chan *td_chan = td->channels + i;
+		if (td_chan->ongoing) {
+			struct timb_dma_desc *td_desc =
+				list_entry(td_chan->active_list.next,
+				struct timb_dma_desc, desc_node);
+			if (td_desc->interrupt)
+				ret |= 1 << i;
+		}
+	}
+
+	return ret;
+}
+
+static void __td_start_next(struct timb_dma_chan *td_chan)
+{
+	struct timb_dma_desc *td_desc;
+
+	BUG_ON(list_empty(&td_chan->queue));
+	BUG_ON(td_chan->ongoing);
+
+	td_desc = list_entry(td_chan->queue.next, struct timb_dma_desc,
+		desc_node);
+
+	dev_dbg(chan2dev(&td_chan->chan), "%s: started %u\n",
+		__func__, td_desc->txd.cookie);
+
+	list_move(&td_desc->desc_node, &td_chan->active_list);
+	__td_start_dma(td_chan);
+}
+
+static dma_cookie_t td_tx_submit(struct dma_async_tx_descriptor *txd)
+{
+	struct timb_dma_desc *td_desc = container_of(txd, struct timb_dma_desc,
+		txd);
+	struct timb_dma_chan *td_chan = container_of(txd->chan,
+		struct timb_dma_chan, chan);
+	dma_cookie_t cookie;
+
+	spin_lock_bh(&td_chan->lock);
+	cookie = dma_cookie_assign(txd);
+
+	if (list_empty(&td_chan->active_list)) {
+		dev_dbg(chan2dev(txd->chan), "%s: started %u\n", __func__,
+			txd->cookie);
+		list_add_tail(&td_desc->desc_node, &td_chan->active_list);
+		__td_start_dma(td_chan);
+	} else {
+		dev_dbg(chan2dev(txd->chan), "tx_submit: queued %u\n",
+			txd->cookie);
+
+		list_add_tail(&td_desc->desc_node, &td_chan->queue);
+	}
+
+	spin_unlock_bh(&td_chan->lock);
+
+	return cookie;
+}
+
+static struct timb_dma_desc *td_alloc_init_desc(struct timb_dma_chan *td_chan)
+{
+	struct dma_chan *chan = &td_chan->chan;
+	struct timb_dma_desc *td_desc;
+	int err;
+
+	td_desc = kzalloc(sizeof(struct timb_dma_desc), GFP_KERNEL);
+	if (!td_desc)
+		goto out;
+
+	td_desc->desc_list_len = td_chan->desc_elems * TIMB_DMA_DESC_SIZE;
+
+	td_desc->desc_list = kzalloc(td_desc->desc_list_len, GFP_KERNEL);
+	if (!td_desc->desc_list)
+		goto err;
+
+	dma_async_tx_descriptor_init(&td_desc->txd, chan);
+	td_desc->txd.tx_submit = td_tx_submit;
+	td_desc->txd.flags = DMA_CTRL_ACK;
+
+	td_desc->txd.phys = dma_map_single(chan2dmadev(chan),
+		td_desc->desc_list, td_desc->desc_list_len, DMA_TO_DEVICE);
+
+	err = dma_mapping_error(chan2dmadev(chan), td_desc->txd.phys);
+	if (err) {
+		dev_err(chan2dev(chan), "DMA mapping error: %d\n", err);
+		goto err;
+	}
+
+	return td_desc;
+err:
+	kfree(td_desc->desc_list);
+	kfree(td_desc);
+out:
+	return NULL;
+
+}
+
+static void td_free_desc(struct timb_dma_desc *td_desc)
+{
+	dev_dbg(chan2dev(td_desc->txd.chan), "Freeing desc: %p\n", td_desc);
+	dma_unmap_single(chan2dmadev(td_desc->txd.chan), td_desc->txd.phys,
+		td_desc->desc_list_len, DMA_TO_DEVICE);
+
+	kfree(td_desc->desc_list);
+	kfree(td_desc);
+}
+
+static void td_desc_put(struct timb_dma_chan *td_chan,
+	struct timb_dma_desc *td_desc)
+{
+	dev_dbg(chan2dev(&td_chan->chan), "Putting desc: %p\n", td_desc);
+
+	spin_lock_bh(&td_chan->lock);
+	list_add(&td_desc->desc_node, &td_chan->free_list);
+	spin_unlock_bh(&td_chan->lock);
+}
+
+static struct timb_dma_desc *td_desc_get(struct timb_dma_chan *td_chan)
+{
+	struct timb_dma_desc *td_desc, *_td_desc;
+	struct timb_dma_desc *ret = NULL;
+
+	spin_lock_bh(&td_chan->lock);
+	list_for_each_entry_safe(td_desc, _td_desc, &td_chan->free_list,
+		desc_node) {
+		if (async_tx_test_ack(&td_desc->txd)) {
+			list_del(&td_desc->desc_node);
+			ret = td_desc;
+			break;
+		}
+		dev_dbg(chan2dev(&td_chan->chan), "desc %p not ACKed\n",
+			td_desc);
+	}
+	spin_unlock_bh(&td_chan->lock);
+
+	return ret;
+}
+
+static int td_alloc_chan_resources(struct dma_chan *chan)
+{
+	struct timb_dma_chan *td_chan =
+		container_of(chan, struct timb_dma_chan, chan);
+	int i;
+
+	dev_dbg(chan2dev(chan), "%s: entry\n", __func__);
+
+	BUG_ON(!list_empty(&td_chan->free_list));
+	for (i = 0; i < td_chan->descs; i++) {
+		struct timb_dma_desc *td_desc = td_alloc_init_desc(td_chan);
+		if (!td_desc) {
+			if (i)
+				break;
+			else {
+				dev_err(chan2dev(chan),
+					"Couldn't allocate any descriptors\n");
+				return -ENOMEM;
+			}
+		}
+
+		td_desc_put(td_chan, td_desc);
+	}
+
+	spin_lock_bh(&td_chan->lock);
+	dma_cookie_init(chan);
+	spin_unlock_bh(&td_chan->lock);
+
+	return 0;
+}
+
+static void td_free_chan_resources(struct dma_chan *chan)
+{
+	struct timb_dma_chan *td_chan =
+		container_of(chan, struct timb_dma_chan, chan);
+	struct timb_dma_desc *td_desc, *_td_desc;
+	LIST_HEAD(list);
+
+	dev_dbg(chan2dev(chan), "%s: Entry\n", __func__);
+
+	/* check that all descriptors are free */
+	BUG_ON(!list_empty(&td_chan->active_list));
+	BUG_ON(!list_empty(&td_chan->queue));
+
+	spin_lock_bh(&td_chan->lock);
+	list_splice_init(&td_chan->free_list, &list);
+	spin_unlock_bh(&td_chan->lock);
+
+	list_for_each_entry_safe(td_desc, _td_desc, &list, desc_node) {
+		dev_dbg(chan2dev(chan), "%s: Freeing desc: %p\n", __func__,
+			td_desc);
+		td_free_desc(td_desc);
+	}
+}
+
+static enum dma_status td_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
+				    struct dma_tx_state *txstate)
+{
+	enum dma_status ret;
+
+	dev_dbg(chan2dev(chan), "%s: Entry\n", __func__);
+
+	ret = dma_cookie_status(chan, cookie, txstate);
+
+	dev_dbg(chan2dev(chan), "%s: exit, ret: %d\n", 	__func__, ret);
+
+	return ret;
+}
+
+static void td_issue_pending(struct dma_chan *chan)
+{
+	struct timb_dma_chan *td_chan =
+		container_of(chan, struct timb_dma_chan, chan);
+
+	dev_dbg(chan2dev(chan), "%s: Entry\n", __func__);
+	spin_lock_bh(&td_chan->lock);
+
+	if (!list_empty(&td_chan->active_list))
+		/* transfer ongoing */
+		if (__td_dma_done_ack(td_chan))
+			__td_finish(td_chan);
+
+	if (list_empty(&td_chan->active_list) && !list_empty(&td_chan->queue))
+		__td_start_next(td_chan);
+
+	spin_unlock_bh(&td_chan->lock);
+}
+
+static struct dma_async_tx_descriptor *td_prep_slave_sg(struct dma_chan *chan,
+	struct scatterlist *sgl, unsigned int sg_len,
+	enum dma_transfer_direction direction, unsigned long flags,
+	void *context)
+{
+	struct timb_dma_chan *td_chan =
+		container_of(chan, struct timb_dma_chan, chan);
+	struct timb_dma_desc *td_desc;
+	struct scatterlist *sg;
+	unsigned int i;
+	unsigned int desc_usage = 0;
+
+	if (!sgl || !sg_len) {
+		dev_err(chan2dev(chan), "%s: No SG list\n", __func__);
+		return NULL;
+	}
+
+	/* even channels are for RX, odd for TX */
+	if (td_chan->direction != direction) {
+		dev_err(chan2dev(chan),
+			"Requesting channel in wrong direction\n");
+		return NULL;
+	}
+
+	td_desc = td_desc_get(td_chan);
+	if (!td_desc) {
+		dev_err(chan2dev(chan), "Not enough descriptors available\n");
+		return NULL;
+	}
+
+	td_desc->interrupt = (flags & DMA_PREP_INTERRUPT) != 0;
+
+	for_each_sg(sgl, sg, sg_len, i) {
+		int err;
+		if (desc_usage > td_desc->desc_list_len) {
+			dev_err(chan2dev(chan), "No descriptor space\n");
+			return NULL;
+		}
+
+		err = td_fill_desc(td_chan, td_desc->desc_list + desc_usage, sg,
+			i == (sg_len - 1));
+		if (err) {
+			dev_err(chan2dev(chan), "Failed to update desc: %d\n",
+				err);
+			td_desc_put(td_chan, td_desc);
+			return NULL;
+		}
+		desc_usage += TIMB_DMA_DESC_SIZE;
+	}
+
+	dma_sync_single_for_device(chan2dmadev(chan), td_desc->txd.phys,
+		td_desc->desc_list_len, DMA_TO_DEVICE);
+
+	return &td_desc->txd;
+}
+
+static int td_terminate_all(struct dma_chan *chan)
+{
+	struct timb_dma_chan *td_chan =
+		container_of(chan, struct timb_dma_chan, chan);
+	struct timb_dma_desc *td_desc, *_td_desc;
+
+	dev_dbg(chan2dev(chan), "%s: Entry\n", __func__);
+
+	/* first the easy part, put the queue into the free list */
+	spin_lock_bh(&td_chan->lock);
+	list_for_each_entry_safe(td_desc, _td_desc, &td_chan->queue,
+		desc_node)
+		list_move(&td_desc->desc_node, &td_chan->free_list);
+
+	/* now tear down the running */
+	__td_finish(td_chan);
+	spin_unlock_bh(&td_chan->lock);
+
+	return 0;
+}
+
+static void td_tasklet(struct tasklet_struct *t)
+{
+	struct timb_dma *td = from_tasklet(td, t, tasklet);
+	u32 isr;
+	u32 ipr;
+	u32 ier;
+	int i;
+
+	isr = ioread32(td->membase + TIMBDMA_ISR);
+	ipr = isr & __td_ier_mask(td);
+
+	/* ack the interrupts */
+	iowrite32(ipr, td->membase + TIMBDMA_ISR);
+
+	for (i = 0; i < td->dma.chancnt; i++)
+		if (ipr & (1 << i)) {
+			struct timb_dma_chan *td_chan = td->channels + i;
+			spin_lock(&td_chan->lock);
+			__td_finish(td_chan);
+			if (!list_empty(&td_chan->queue))
+				__td_start_next(td_chan);
+			spin_unlock(&td_chan->lock);
+		}
+
+	ier = __td_ier_mask(td);
+	iowrite32(ier, td->membase + TIMBDMA_IER);
+}
+
+
+static irqreturn_t td_irq(int irq, void *devid)
+{
+	struct timb_dma *td = devid;
+	u32 ipr = ioread32(td->membase + TIMBDMA_IPR);
+
+	if (ipr) {
+		/* disable interrupts, will be re-enabled in tasklet */
+		iowrite32(0, td->membase + TIMBDMA_IER);
+
+		tasklet_schedule(&td->tasklet);
+
+		return IRQ_HANDLED;
+	} else
+		return IRQ_NONE;
+}
+
+
+static int td_probe(struct platform_device *pdev)
+{
+	struct timb_dma_platform_data *pdata = dev_get_platdata(&pdev->dev);
+	struct timb_dma *td;
+	struct resource *iomem;
+	int irq;
+	int err;
+	int i;
+
+	if (!pdata) {
+		dev_err(&pdev->dev, "No platform data\n");
+		return -EINVAL;
+	}
+
+	iomem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!iomem)
+		return -EINVAL;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
+	if (!request_mem_region(iomem->start, resource_size(iomem),
+		DRIVER_NAME))
+		return -EBUSY;
+
+	td  = kzalloc(struct_size(td, channels, pdata->nr_channels),
+		      GFP_KERNEL);
+	if (!td) {
+		err = -ENOMEM;
+		goto err_release_region;
+	}
+
+	dev_dbg(&pdev->dev, "Allocated TD: %p\n", td);
+
+	td->membase = ioremap(iomem->start, resource_size(iomem));
+	if (!td->membase) {
+		dev_err(&pdev->dev, "Failed to remap I/O memory\n");
+		err = -ENOMEM;
+		goto err_free_mem;
+	}
+
+	/* 32bit addressing */
+	iowrite32(TIMBDMA_32BIT_ADDR, td->membase + TIMBDMA_ACR);
+
+	/* disable and clear any interrupts */
+	iowrite32(0x0, td->membase + TIMBDMA_IER);
+	iowrite32(0xFFFFFFFF, td->membase + TIMBDMA_ISR);
+
+	tasklet_setup(&td->tasklet, td_tasklet);
+
+	err = request_irq(irq, td_irq, IRQF_SHARED, DRIVER_NAME, td);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to request IRQ\n");
+		goto err_tasklet_kill;
+	}
+
+	td->dma.device_alloc_chan_resources	= td_alloc_chan_resources;
+	td->dma.device_free_chan_resources	= td_free_chan_resources;
+	td->dma.device_tx_status		= td_tx_status;
+	td->dma.device_issue_pending		= td_issue_pending;
+
+	dma_cap_set(DMA_SLAVE, td->dma.cap_mask);
+	dma_cap_set(DMA_PRIVATE, td->dma.cap_mask);
+	td->dma.device_prep_slave_sg = td_prep_slave_sg;
+	td->dma.device_terminate_all = td_terminate_all;
+
+	td->dma.dev = &pdev->dev;
+
+	INIT_LIST_HEAD(&td->dma.channels);
+
+	for (i = 0; i < pdata->nr_channels; i++) {
+		struct timb_dma_chan *td_chan = &td->channels[i];
+		struct timb_dma_platform_data_channel *pchan =
+			pdata->channels + i;
+
+		/* even channels are RX, odd are TX */
+		if ((i % 2) == pchan->rx) {
+			dev_err(&pdev->dev, "Wrong channel configuration\n");
+			err = -EINVAL;
+			goto err_free_irq;
+		}
+
+		td_chan->chan.device = &td->dma;
+		dma_cookie_init(&td_chan->chan);
+		spin_lock_init(&td_chan->lock);
+		INIT_LIST_HEAD(&td_chan->active_list);
+		INIT_LIST_HEAD(&td_chan->queue);
+		INIT_LIST_HEAD(&td_chan->free_list);
+
+		td_chan->descs = pchan->descriptors;
+		td_chan->desc_elems = pchan->descriptor_elements;
+		td_chan->bytes_per_line = pchan->bytes_per_line;
+		td_chan->direction = pchan->rx ? DMA_DEV_TO_MEM :
+			DMA_MEM_TO_DEV;
+
+		td_chan->membase = td->membase +
+			(i / 2) * TIMBDMA_INSTANCE_OFFSET +
+			(pchan->rx ? 0 : TIMBDMA_INSTANCE_TX_OFFSET);
+
+		dev_dbg(&pdev->dev, "Chan: %d, membase: %p\n",
+			i, td_chan->membase);
+
+		list_add_tail(&td_chan->chan.device_node, &td->dma.channels);
+	}
+
+	err = dma_async_device_register(&td->dma);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to register async device\n");
+		goto err_free_irq;
+	}
+
+	platform_set_drvdata(pdev, td);
+
+	dev_dbg(&pdev->dev, "Probe result: %d\n", err);
+	return err;
+
+err_free_irq:
+	free_irq(irq, td);
+err_tasklet_kill:
+	tasklet_kill(&td->tasklet);
+	iounmap(td->membase);
+err_free_mem:
+	kfree(td);
+err_release_region:
+	release_mem_region(iomem->start, resource_size(iomem));
+
+	return err;
+
+}
+
+static int td_remove(struct platform_device *pdev)
+{
+	struct timb_dma *td = platform_get_drvdata(pdev);
+	struct resource *iomem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	int irq = platform_get_irq(pdev, 0);
+
+	dma_async_device_unregister(&td->dma);
+	free_irq(irq, td);
+	tasklet_kill(&td->tasklet);
+	iounmap(td->membase);
+	kfree(td);
+	release_mem_region(iomem->start, resource_size(iomem));
+
+	dev_dbg(&pdev->dev, "Removed...\n");
+	return 0;
+}
+
+static struct platform_driver td_driver = {
+	.driver = {
+		.name	= DRIVER_NAME,
+	},
+	.probe	= td_probe,
+	.remove	= td_remove,
+};
+
+module_platform_driver(td_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Timberdale DMA controller driver");
+MODULE_AUTHOR("Pelagicore AB <info@pelagicore.com>");
+MODULE_ALIAS("platform:"DRIVER_NAME);