Merge tag 'dmaengine-5.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine

Pull dmaengine updates from Vinod Koul:
 "The last dmaengine updates for this year :)

  This contains couple of new drivers, new device support and updates to
  bunch of drivers.

  New drivers/devices:
   - Qualcomm ADM driver
   - Qualcomm GPI driver
   - Allwinner A100 DMA support
   - Microchip Sama7g5 support
   - Mediatek MT8516 apdma

  Updates:
   - more updates to idxd driver and support for IAX config
   - runtime PM support for dw driver
   - TI drivers"

* tag 'dmaengine-5.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine: (75 commits)
  soc: ti: k3-ringacc: Use correct error casting in k3_ringacc_dmarings_init
  dmaengine: ti: k3-udma-glue: Add support for K3 PKTDMA
  dmaengine: ti: k3-udma: Initial support for K3 PKTDMA
  dmaengine: ti: k3-udma: Add support for BCDMA channel TPL handling
  dmaengine: ti: k3-udma: Initial support for K3 BCDMA
  soc: ti: k3-ringacc: add AM64 DMA rings support.
  dmaengine: ti: Add support for k3 event routers
  dmaengine: ti: k3-psil: Add initial map for AM64
  dmaengine: ti: k3-psil: Extend psil_endpoint_config for K3 PKTDMA
  dt-bindings: dma: ti: Add document for K3 PKTDMA
  dt-bindings: dma: ti: Add document for K3 BCDMA
  dmaengine: dmatest: Use dmaengine_get_dma_device
  dmaengine: doc: client: Update for dmaengine_get_dma_device() usage
  dmaengine: Add support for per channel coherency handling
  dmaengine: of-dma: Add support for optional router configuration callback
  dmaengine: ti: k3-udma-glue: Configure the dma_dev for rings
  dmaengine: ti: k3-udma-glue: Get the ringacc from udma_dev
  dmaengine: ti: k3-udma-glue: Add function to get device pointer for DMA API
  dmaengine: ti: k3-udma: Add support for second resource range from sysfw
  dmaengine: ti: k3-udma: Wait for peer teardown completion if supported
  ...

9 files changed, 2334 insertions, 225 deletions

diff --git a/drivers/dma/ti/Makefile b/drivers/dma/ti/Makefile
index 0c67254caee6..bd496efadff7 100644
--- a/drivers/dma/ti/Makefile
+++ b/drivers/dma/ti/Makefile
@@ -7,5 +7,6 @@ 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
+			    k3-psil-j7200.o \
+			    k3-psil-am64.o
 obj-$(CONFIG_TI_DMA_CROSSBAR) += dma-crossbar.o
diff --git a/drivers/dma/ti/dma-crossbar.c b/drivers/dma/ti/dma-crossbar.c
index 4ba8fa5d9c36..71d24fc07c00 100644
--- a/drivers/dma/ti/dma-crossbar.c
+++ b/drivers/dma/ti/dma-crossbar.c
@@ -122,7 +122,7 @@ static void *ti_am335x_xbar_route_allocate(struct of_phandle_args *dma_spec,
 	return map;
 }
 
-static const struct of_device_id ti_am335x_master_match[] = {
+static const struct of_device_id ti_am335x_master_match[] __maybe_unused = {
 	{ .compatible = "ti,edma3-tpcc", },
 	{},
 };
@@ -292,7 +292,7 @@ static const u32 ti_dma_offset[] = {
 	[TI_XBAR_SDMA_OFFSET] = 1,
 };
 
-static const struct of_device_id ti_dra7_master_match[] = {
+static const struct of_device_id ti_dra7_master_match[] __maybe_unused = {
 	{
 		.compatible = "ti,omap4430-sdma",
 		.data = &ti_dma_offset[TI_XBAR_SDMA_OFFSET],
@@ -460,7 +460,7 @@ static int ti_dma_xbar_probe(struct platform_device *pdev)
 static struct platform_driver ti_dma_xbar_driver = {
 	.driver = {
 		.name = "ti-dma-crossbar",
-		.of_match_table = of_match_ptr(ti_dma_xbar_match),
+		.of_match_table = ti_dma_xbar_match,
 	},
 	.probe	= ti_dma_xbar_probe,
 };
diff --git a/drivers/dma/ti/k3-psil-am64.c b/drivers/dma/ti/k3-psil-am64.c
new file mode 100644
index 000000000000..9fdeaa11a4fc
--- /dev/null
+++ b/drivers/dma/ti/k3-psil-am64.c
@@ -0,0 +1,158 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Copyright (C) 2020 Texas Instruments Incorporated - https://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,		\
+			.mapped_channel_id = -1,		\
+			.default_flow_id = -1,			\
+		},						\
+	}
+
+#define PSIL_PDMA_XY_PKT(x)					\
+	{							\
+		.thread_id = x,					\
+		.ep_config = {					\
+			.ep_type = PSIL_EP_PDMA_XY,		\
+			.mapped_channel_id = -1,		\
+			.default_flow_id = -1,			\
+			.pkt_mode = 1,				\
+		},						\
+	}
+
+#define PSIL_ETHERNET(x, ch, flow_base, flow_cnt)		\
+	{							\
+		.thread_id = x,					\
+		.ep_config = {					\
+			.ep_type = PSIL_EP_NATIVE,		\
+			.pkt_mode = 1,				\
+			.needs_epib = 1,			\
+			.psd_size = 16,				\
+			.mapped_channel_id = ch,		\
+			.flow_start = flow_base,		\
+			.flow_num = flow_cnt,			\
+			.default_flow_id = flow_base,		\
+		},						\
+	}
+
+#define PSIL_SAUL(x, ch, flow_base, flow_cnt, default_flow, tx)	\
+	{							\
+		.thread_id = x,					\
+		.ep_config = {					\
+			.ep_type = PSIL_EP_NATIVE,		\
+			.pkt_mode = 1,				\
+			.needs_epib = 1,			\
+			.psd_size = 64,				\
+			.mapped_channel_id = ch,		\
+			.flow_start = flow_base,		\
+			.flow_num = flow_cnt,			\
+			.default_flow_id = default_flow,	\
+			.notdpkt = tx,				\
+		},						\
+	}
+
+/* PSI-L source thread IDs, used for RX (DMA_DEV_TO_MEM) */
+static struct psil_ep am64_src_ep_map[] = {
+	/* SAUL */
+	PSIL_SAUL(0x4000, 17, 32, 8, 32, 0),
+	PSIL_SAUL(0x4001, 18, 32, 8, 33, 0),
+	PSIL_SAUL(0x4002, 19, 40, 8, 40, 0),
+	PSIL_SAUL(0x4003, 20, 40, 8, 41, 0),
+	/* ICSS_G0 */
+	PSIL_ETHERNET(0x4100, 21, 48, 16),
+	PSIL_ETHERNET(0x4101, 22, 64, 16),
+	PSIL_ETHERNET(0x4102, 23, 80, 16),
+	PSIL_ETHERNET(0x4103, 24, 96, 16),
+	/* ICSS_G1 */
+	PSIL_ETHERNET(0x4200, 25, 112, 16),
+	PSIL_ETHERNET(0x4201, 26, 128, 16),
+	PSIL_ETHERNET(0x4202, 27, 144, 16),
+	PSIL_ETHERNET(0x4203, 28, 160, 16),
+	/* PDMA_MAIN0 - SPI0-3 */
+	PSIL_PDMA_XY_PKT(0x4300),
+	PSIL_PDMA_XY_PKT(0x4301),
+	PSIL_PDMA_XY_PKT(0x4302),
+	PSIL_PDMA_XY_PKT(0x4303),
+	PSIL_PDMA_XY_PKT(0x4304),
+	PSIL_PDMA_XY_PKT(0x4305),
+	PSIL_PDMA_XY_PKT(0x4306),
+	PSIL_PDMA_XY_PKT(0x4307),
+	PSIL_PDMA_XY_PKT(0x4308),
+	PSIL_PDMA_XY_PKT(0x4309),
+	PSIL_PDMA_XY_PKT(0x430a),
+	PSIL_PDMA_XY_PKT(0x430b),
+	PSIL_PDMA_XY_PKT(0x430c),
+	PSIL_PDMA_XY_PKT(0x430d),
+	PSIL_PDMA_XY_PKT(0x430e),
+	PSIL_PDMA_XY_PKT(0x430f),
+	/* PDMA_MAIN0 - USART0-1 */
+	PSIL_PDMA_XY_PKT(0x4310),
+	PSIL_PDMA_XY_PKT(0x4311),
+	/* PDMA_MAIN1 - SPI4 */
+	PSIL_PDMA_XY_PKT(0x4400),
+	PSIL_PDMA_XY_PKT(0x4401),
+	PSIL_PDMA_XY_PKT(0x4402),
+	PSIL_PDMA_XY_PKT(0x4403),
+	/* PDMA_MAIN1 - USART2-6 */
+	PSIL_PDMA_XY_PKT(0x4404),
+	PSIL_PDMA_XY_PKT(0x4405),
+	PSIL_PDMA_XY_PKT(0x4406),
+	PSIL_PDMA_XY_PKT(0x4407),
+	PSIL_PDMA_XY_PKT(0x4408),
+	/* PDMA_MAIN1 - ADCs */
+	PSIL_PDMA_XY_TR(0x440f),
+	PSIL_PDMA_XY_TR(0x4410),
+	/* CPSW2 */
+	PSIL_ETHERNET(0x4500, 16, 16, 16),
+};
+
+/* PSI-L destination thread IDs, used for TX (DMA_MEM_TO_DEV) */
+static struct psil_ep am64_dst_ep_map[] = {
+	/* SAUL */
+	PSIL_SAUL(0xc000, 24, 80, 8, 80, 1),
+	PSIL_SAUL(0xc001, 25, 88, 8, 88, 1),
+	/* ICSS_G0 */
+	PSIL_ETHERNET(0xc100, 26, 96, 1),
+	PSIL_ETHERNET(0xc101, 27, 97, 1),
+	PSIL_ETHERNET(0xc102, 28, 98, 1),
+	PSIL_ETHERNET(0xc103, 29, 99, 1),
+	PSIL_ETHERNET(0xc104, 30, 100, 1),
+	PSIL_ETHERNET(0xc105, 31, 101, 1),
+	PSIL_ETHERNET(0xc106, 32, 102, 1),
+	PSIL_ETHERNET(0xc107, 33, 103, 1),
+	/* ICSS_G1 */
+	PSIL_ETHERNET(0xc200, 34, 104, 1),
+	PSIL_ETHERNET(0xc201, 35, 105, 1),
+	PSIL_ETHERNET(0xc202, 36, 106, 1),
+	PSIL_ETHERNET(0xc203, 37, 107, 1),
+	PSIL_ETHERNET(0xc204, 38, 108, 1),
+	PSIL_ETHERNET(0xc205, 39, 109, 1),
+	PSIL_ETHERNET(0xc206, 40, 110, 1),
+	PSIL_ETHERNET(0xc207, 41, 111, 1),
+	/* CPSW2 */
+	PSIL_ETHERNET(0xc500, 16, 16, 8),
+	PSIL_ETHERNET(0xc501, 17, 24, 8),
+	PSIL_ETHERNET(0xc502, 18, 32, 8),
+	PSIL_ETHERNET(0xc503, 19, 40, 8),
+	PSIL_ETHERNET(0xc504, 20, 48, 8),
+	PSIL_ETHERNET(0xc505, 21, 56, 8),
+	PSIL_ETHERNET(0xc506, 22, 64, 8),
+	PSIL_ETHERNET(0xc507, 23, 72, 8),
+};
+
+struct psil_ep_map am64_ep_map = {
+	.name = "am64",
+	.src = am64_src_ep_map,
+	.src_count = ARRAY_SIZE(am64_src_ep_map),
+	.dst = am64_dst_ep_map,
+	.dst_count = ARRAY_SIZE(am64_dst_ep_map),
+};
diff --git a/drivers/dma/ti/k3-psil-priv.h b/drivers/dma/ti/k3-psil-priv.h
index b4b0fb359eff..b74e192e3c2d 100644
--- a/drivers/dma/ti/k3-psil-priv.h
+++ b/drivers/dma/ti/k3-psil-priv.h
@@ -40,5 +40,6 @@ struct psil_endpoint_config *psil_get_ep_config(u32 thread_id);
 extern struct psil_ep_map am654_ep_map;
 extern struct psil_ep_map j721e_ep_map;
 extern struct psil_ep_map j7200_ep_map;
+extern struct psil_ep_map am64_ep_map;
 
 #endif /* K3_PSIL_PRIV_H_ */
diff --git a/drivers/dma/ti/k3-psil.c b/drivers/dma/ti/k3-psil.c
index 837853aab95a..13ce7367d870 100644
--- a/drivers/dma/ti/k3-psil.c
+++ b/drivers/dma/ti/k3-psil.c
@@ -20,6 +20,7 @@ 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 },
+	{ .family = "AM64X", .data = &am64_ep_map },
 	{ /* sentinel */ }
 };
 
diff --git a/drivers/dma/ti/k3-udma-glue.c b/drivers/dma/ti/k3-udma-glue.c
index a367584f0d7b..4fdd9f06b723 100644
--- a/drivers/dma/ti/k3-udma-glue.c
+++ b/drivers/dma/ti/k3-udma-glue.c
@@ -22,6 +22,7 @@
 
 struct k3_udma_glue_common {
 	struct device *dev;
+	struct device chan_dev;
 	struct udma_dev *udmax;
 	const struct udma_tisci_rm *tisci_rm;
 	struct k3_ringacc *ringacc;
@@ -32,7 +33,8 @@ struct k3_udma_glue_common {
 	bool epib;
 	u32  psdata_size;
 	u32  swdata_size;
-	u32  atype;
+	u32  atype_asel;
+	struct psil_endpoint_config *ep_config;
 };
 
 struct k3_udma_glue_tx_channel {
@@ -53,6 +55,8 @@ struct k3_udma_glue_tx_channel {
 	bool tx_filt_einfo;
 	bool tx_filt_pswords;
 	bool tx_supr_tdpkt;
+
+	int udma_tflow_id;
 };
 
 struct k3_udma_glue_rx_flow {
@@ -81,20 +85,26 @@ struct k3_udma_glue_rx_channel {
 	u32 flows_ready;
 };
 
+static void k3_udma_chan_dev_release(struct device *dev)
+{
+	/* The struct containing the device is devm managed */
+}
+
+static struct class k3_udma_glue_devclass = {
+	.name		= "k3_udma_glue_chan",
+	.dev_release	= k3_udma_chan_dev_release,
+};
+
 #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->ringacc = xudma_get_ringacc(common->udmax);
 	common->tisci_rm = xudma_dev_get_tisci_rm(common->udmax);
 
 	return 0;
@@ -104,7 +114,6 @@ 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;
@@ -121,15 +130,26 @@ static int of_k3_udma_glue_parse_chn(struct device_node *chn_np,
 				       &dma_spec))
 		return -ENOENT;
 
+	ret = of_k3_udma_glue_parse(dma_spec.np, common);
+	if (ret)
+		goto out_put_spec;
+
 	thread_id = dma_spec.args[0];
 	if (dma_spec.args_count == 2) {
-		if (dma_spec.args[1] > 2) {
+		if (dma_spec.args[1] > 2 && !xudma_is_pktdma(common->udmax)) {
 			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 (dma_spec.args[1] > 15 && xudma_is_pktdma(common->udmax)) {
+			dev_err(common->dev, "Invalid channel asel: %u\n",
+				dma_spec.args[1]);
+			ret = -EINVAL;
+			goto out_put_spec;
+		}
+
+		common->atype_asel = dma_spec.args[1];
 	}
 
 	if (tx_chn && !(thread_id & K3_PSIL_DST_THREAD_ID_OFFSET)) {
@@ -143,25 +163,23 @@ static int of_k3_udma_glue_parse_chn(struct device_node *chn_np,
 	}
 
 	/* get psil endpoint config */
-	ep_config = psil_get_ep_config(thread_id);
-	if (IS_ERR(ep_config)) {
+	common->ep_config = psil_get_ep_config(thread_id);
+	if (IS_ERR(common->ep_config)) {
 		dev_err(common->dev,
 			"No configuration for psi-l thread 0x%04x\n",
 			thread_id);
-		ret = PTR_ERR(ep_config);
+		ret = PTR_ERR(common->ep_config);
 		goto out_put_spec;
 	}
 
-	common->epib = ep_config->needs_epib;
-	common->psdata_size = ep_config->psd_size;
+	common->epib = common->ep_config->needs_epib;
+	common->psdata_size = common->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;
@@ -227,7 +245,7 @@ static int k3_udma_glue_cfg_tx_chn(struct k3_udma_glue_tx_channel *tx_chn)
 		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;
+	req.tx_atype = tx_chn->common.atype_asel;
 
 	return tisci_rm->tisci_udmap_ops->tx_ch_cfg(tisci_rm->tisci, &req);
 }
@@ -259,8 +277,14 @@ struct k3_udma_glue_tx_channel *k3_udma_glue_request_tx_chn(struct device *dev,
 						tx_chn->common.psdata_size,
 						tx_chn->common.swdata_size);
 
+	if (xudma_is_pktdma(tx_chn->common.udmax))
+		tx_chn->udma_tchan_id = tx_chn->common.ep_config->mapped_channel_id;
+	else
+		tx_chn->udma_tchan_id = -1;
+
 	/* request and cfg UDMAP TX channel */
-	tx_chn->udma_tchanx = xudma_tchan_get(tx_chn->common.udmax, -1);
+	tx_chn->udma_tchanx = xudma_tchan_get(tx_chn->common.udmax,
+					      tx_chn->udma_tchan_id);
 	if (IS_ERR(tx_chn->udma_tchanx)) {
 		ret = PTR_ERR(tx_chn->udma_tchanx);
 		dev_err(dev, "UDMAX tchanx get err %d\n", ret);
@@ -268,11 +292,34 @@ struct k3_udma_glue_tx_channel *k3_udma_glue_request_tx_chn(struct device *dev,
 	}
 	tx_chn->udma_tchan_id = xudma_tchan_get_id(tx_chn->udma_tchanx);
 
+	tx_chn->common.chan_dev.class = &k3_udma_glue_devclass;
+	tx_chn->common.chan_dev.parent = xudma_get_device(tx_chn->common.udmax);
+	dev_set_name(&tx_chn->common.chan_dev, "tchan%d-0x%04x",
+		     tx_chn->udma_tchan_id, tx_chn->common.dst_thread);
+	ret = device_register(&tx_chn->common.chan_dev);
+	if (ret) {
+		dev_err(dev, "Channel Device registration failed %d\n", ret);
+		tx_chn->common.chan_dev.parent = NULL;
+		goto err;
+	}
+
+	if (xudma_is_pktdma(tx_chn->common.udmax)) {
+		/* prepare the channel device as coherent */
+		tx_chn->common.chan_dev.dma_coherent = true;
+		dma_coerce_mask_and_coherent(&tx_chn->common.chan_dev,
+					     DMA_BIT_MASK(48));
+	}
+
 	atomic_set(&tx_chn->free_pkts, cfg->txcq_cfg.size);
 
+	if (xudma_is_pktdma(tx_chn->common.udmax))
+		tx_chn->udma_tflow_id = tx_chn->common.ep_config->default_flow_id;
+	else
+		tx_chn->udma_tflow_id = tx_chn->udma_tchan_id;
+
 	/* request and cfg rings */
 	ret =  k3_ringacc_request_rings_pair(tx_chn->common.ringacc,
-					     tx_chn->udma_tchan_id, -1,
+					     tx_chn->udma_tflow_id, -1,
 					     &tx_chn->ringtx,
 					     &tx_chn->ringtxcq);
 	if (ret) {
@@ -280,6 +327,16 @@ struct k3_udma_glue_tx_channel *k3_udma_glue_request_tx_chn(struct device *dev,
 		goto err;
 	}
 
+	/* Set the dma_dev for the rings to be configured */
+	cfg->tx_cfg.dma_dev = k3_udma_glue_tx_get_dma_device(tx_chn);
+	cfg->txcq_cfg.dma_dev = cfg->tx_cfg.dma_dev;
+
+	/* Set the ASEL value for DMA rings of PKTDMA */
+	if (xudma_is_pktdma(tx_chn->common.udmax)) {
+		cfg->tx_cfg.asel = tx_chn->common.atype_asel;
+		cfg->txcq_cfg.asel = tx_chn->common.atype_asel;
+	}
+
 	ret = k3_ringacc_ring_cfg(tx_chn->ringtx, &cfg->tx_cfg);
 	if (ret) {
 		dev_err(dev, "Failed to cfg ringtx %d\n", ret);
@@ -303,19 +360,6 @@ struct k3_udma_glue_tx_channel *k3_udma_glue_request_tx_chn(struct device *dev,
 		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;
@@ -344,6 +388,11 @@ void k3_udma_glue_release_tx_chn(struct k3_udma_glue_tx_channel *tx_chn)
 
 	if (tx_chn->ringtx)
 		k3_ringacc_ring_free(tx_chn->ringtx);
+
+	if (tx_chn->common.chan_dev.parent) {
+		device_unregister(&tx_chn->common.chan_dev);
+		tx_chn->common.chan_dev.parent = NULL;
+	}
 }
 EXPORT_SYMBOL_GPL(k3_udma_glue_release_tx_chn);
 
@@ -378,6 +427,18 @@ EXPORT_SYMBOL_GPL(k3_udma_glue_pop_tx_chn);
 
 int k3_udma_glue_enable_tx_chn(struct k3_udma_glue_tx_channel *tx_chn)
 {
+	int ret;
+
+	ret = xudma_navss_psil_pair(tx_chn->common.udmax,
+				    tx_chn->common.src_thread,
+				    tx_chn->common.dst_thread);
+	if (ret) {
+		dev_err(tx_chn->common.dev, "PSI-L request err %d\n", ret);
+		return ret;
+	}
+
+	tx_chn->psil_paired = true;
+
 	xudma_tchanrt_write(tx_chn->udma_tchanx, UDMA_CHAN_RT_PEER_RT_EN_REG,
 			    UDMA_PEER_RT_EN_ENABLE);
 
@@ -398,6 +459,13 @@ void k3_udma_glue_disable_tx_chn(struct k3_udma_glue_tx_channel *tx_chn)
 	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");
+
+	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;
+	}
 }
 EXPORT_SYMBOL_GPL(k3_udma_glue_disable_tx_chn);
 
@@ -437,13 +505,10 @@ 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))
 {
+	struct device *dev = tx_chn->common.dev;
 	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:
@@ -452,17 +517,20 @@ void k3_udma_glue_reset_tx_chn(struct k3_udma_glue_tx_channel *tx_chn,
 	 * 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);
+	dev_dbg(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);
+			if (ret != -ENODATA)
+				dev_err(dev, "TX reset pop %d\n", ret);
 			break;
 		}
 		cleanup(data, desc_dma);
 	}
 
+	/* reset TXCQ as it is not input for udma - expected to be empty */
+	k3_ringacc_ring_reset(tx_chn->ringtxcq);
 	k3_ringacc_ring_reset_dma(tx_chn->ringtx, occ_tx);
 }
 EXPORT_SYMBOL_GPL(k3_udma_glue_reset_tx_chn);
@@ -481,12 +549,50 @@ 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);
+	if (xudma_is_pktdma(tx_chn->common.udmax)) {
+		tx_chn->virq = xudma_pktdma_tflow_get_irq(tx_chn->common.udmax,
+							  tx_chn->udma_tflow_id);
+	} else {
+		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);
 
+struct device *
+	k3_udma_glue_tx_get_dma_device(struct k3_udma_glue_tx_channel *tx_chn)
+{
+	if (xudma_is_pktdma(tx_chn->common.udmax) &&
+	    (tx_chn->common.atype_asel == 14 || tx_chn->common.atype_asel == 15))
+		return &tx_chn->common.chan_dev;
+
+	return xudma_get_device(tx_chn->common.udmax);
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_tx_get_dma_device);
+
+void k3_udma_glue_tx_dma_to_cppi5_addr(struct k3_udma_glue_tx_channel *tx_chn,
+				       dma_addr_t *addr)
+{
+	if (!xudma_is_pktdma(tx_chn->common.udmax) ||
+	    !tx_chn->common.atype_asel)
+		return;
+
+	*addr |= (u64)tx_chn->common.atype_asel << K3_ADDRESS_ASEL_SHIFT;
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_tx_dma_to_cppi5_addr);
+
+void k3_udma_glue_tx_cppi5_to_dma_addr(struct k3_udma_glue_tx_channel *tx_chn,
+				       dma_addr_t *addr)
+{
+	if (!xudma_is_pktdma(tx_chn->common.udmax) ||
+	    !tx_chn->common.atype_asel)
+		return;
+
+	*addr &= (u64)GENMASK(K3_ADDRESS_ASEL_SHIFT - 1, 0);
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_tx_cppi5_to_dma_addr);
+
 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;
@@ -498,8 +604,6 @@ static int k3_udma_glue_cfg_rx_chn(struct k3_udma_glue_rx_channel *rx_chn)
 	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;
@@ -511,13 +615,16 @@ static int k3_udma_glue_cfg_rx_chn(struct k3_udma_glue_rx_channel *rx_chn)
 	 * 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) {
+	if (!xudma_is_pktdma(rx_chn->common.udmax) && rx_chn->flow_num &&
+	    rx_chn->flow_id_base != rx_chn->udma_rchan_id) {
 		/* Default flow + extra ones */
+		req.valid_params |= TI_SCI_MSG_VALUE_RM_UDMAP_CH_RX_FLOWID_START_VALID |
+				    TI_SCI_MSG_VALUE_RM_UDMAP_CH_RX_FLOWID_CNT_VALID;
 		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;
+	req.rx_atype = rx_chn->common.atype_asel;
 
 	ret = tisci_rm->tisci_udmap_ops->rx_ch_cfg(tisci_rm->tisci, &req);
 	if (ret)
@@ -571,10 +678,18 @@ static int k3_udma_glue_cfg_rx_flow(struct k3_udma_glue_rx_channel *rx_chn,
 		goto err_rflow_put;
 	}
 
+	if (xudma_is_pktdma(rx_chn->common.udmax)) {
+		rx_ringfdq_id = flow->udma_rflow_id +
+				xudma_get_rflow_ring_offset(rx_chn->common.udmax);
+		rx_ring_id = 0;
+	} else {
+		rx_ring_id = flow_cfg->ring_rxq_id;
+		rx_ringfdq_id = flow_cfg->ring_rxfdq0_id;
+	}
+
 	/* request and cfg rings */
 	ret =  k3_ringacc_request_rings_pair(rx_chn->common.ringacc,
-					     flow_cfg->ring_rxfdq0_id,
-					     flow_cfg->ring_rxq_id,
+					     rx_ringfdq_id, rx_ring_id,
 					     &flow->ringrxfdq,
 					     &flow->ringrx);
 	if (ret) {
@@ -582,6 +697,16 @@ static int k3_udma_glue_cfg_rx_flow(struct k3_udma_glue_rx_channel *rx_chn,
 		goto err_rflow_put;
 	}
 
+	/* Set the dma_dev for the rings to be configured */
+	flow_cfg->rx_cfg.dma_dev = k3_udma_glue_rx_get_dma_device(rx_chn);
+	flow_cfg->rxfdq_cfg.dma_dev = flow_cfg->rx_cfg.dma_dev;
+
+	/* Set the ASEL value for DMA rings of PKTDMA */
+	if (xudma_is_pktdma(rx_chn->common.udmax)) {
+		flow_cfg->rx_cfg.asel = rx_chn->common.atype_asel;
+		flow_cfg->rxfdq_cfg.asel = rx_chn->common.atype_asel;
+	}
+
 	ret = k3_ringacc_ring_cfg(flow->ringrx, &flow_cfg->rx_cfg);
 	if (ret) {
 		dev_err(dev, "Failed to cfg ringrx %d\n", ret);
@@ -740,6 +865,7 @@ 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;
+	struct psil_endpoint_config *ep_cfg;
 	int ret, i;
 
 	if (cfg->flow_id_num <= 0)
@@ -767,8 +893,16 @@ k3_udma_glue_request_rx_chn_priv(struct device *dev, const char *name,
 						rx_chn->common.psdata_size,
 						rx_chn->common.swdata_size);
 
+	ep_cfg = rx_chn->common.ep_config;
+
+	if (xudma_is_pktdma(rx_chn->common.udmax))
+		rx_chn->udma_rchan_id = ep_cfg->mapped_channel_id;
+	else
+		rx_chn->udma_rchan_id = -1;
+
 	/* request and cfg UDMAP RX channel */
-	rx_chn->udma_rchanx = xudma_rchan_get(rx_chn->common.udmax, -1);
+	rx_chn->udma_rchanx = xudma_rchan_get(rx_chn->common.udmax,
+					      rx_chn->udma_rchan_id);
 	if (IS_ERR(rx_chn->udma_rchanx)) {
 		ret = PTR_ERR(rx_chn->udma_rchanx);
 		dev_err(dev, "UDMAX rchanx get err %d\n", ret);
@@ -776,12 +910,48 @@ k3_udma_glue_request_rx_chn_priv(struct device *dev, const char *name,
 	}
 	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;
+	rx_chn->common.chan_dev.class = &k3_udma_glue_devclass;
+	rx_chn->common.chan_dev.parent = xudma_get_device(rx_chn->common.udmax);
+	dev_set_name(&rx_chn->common.chan_dev, "rchan%d-0x%04x",
+		     rx_chn->udma_rchan_id, rx_chn->common.src_thread);
+	ret = device_register(&rx_chn->common.chan_dev);
+	if (ret) {
+		dev_err(dev, "Channel Device registration failed %d\n", ret);
+		rx_chn->common.chan_dev.parent = NULL;
+		goto err;
+	}
 
-	/* 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;
+	if (xudma_is_pktdma(rx_chn->common.udmax)) {
+		/* prepare the channel device as coherent */
+		rx_chn->common.chan_dev.dma_coherent = true;
+		dma_coerce_mask_and_coherent(&rx_chn->common.chan_dev,
+					     DMA_BIT_MASK(48));
+	}
+
+	if (xudma_is_pktdma(rx_chn->common.udmax)) {
+		int flow_start = cfg->flow_id_base;
+		int flow_end;
+
+		if (flow_start == -1)
+			flow_start = ep_cfg->flow_start;
+
+		flow_end = flow_start + cfg->flow_id_num - 1;
+		if (flow_start < ep_cfg->flow_start ||
+		    flow_end > (ep_cfg->flow_start + ep_cfg->flow_num - 1)) {
+			dev_err(dev, "Invalid flow range requested\n");
+			ret = -EINVAL;
+			goto err;
+		}
+		rx_chn->flow_id_base = flow_start;
+	} else {
+		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->flow_num = cfg->flow_id_num;
 
 	rx_chn->flows = devm_kcalloc(dev, rx_chn->flow_num,
 				     sizeof(*rx_chn->flows), GFP_KERNEL);
@@ -815,19 +985,6 @@ k3_udma_glue_request_rx_chn_priv(struct device *dev, const char *name,
 			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;
@@ -884,6 +1041,24 @@ k3_udma_glue_request_remote_rx_chn(struct device *dev, const char *name,
 		goto err;
 	}
 
+	rx_chn->common.chan_dev.class = &k3_udma_glue_devclass;
+	rx_chn->common.chan_dev.parent = xudma_get_device(rx_chn->common.udmax);
+	dev_set_name(&rx_chn->common.chan_dev, "rchan_remote-0x%04x",
+		     rx_chn->common.src_thread);
+	ret = device_register(&rx_chn->common.chan_dev);
+	if (ret) {
+		dev_err(dev, "Channel Device registration failed %d\n", ret);
+		rx_chn->common.chan_dev.parent = NULL;
+		goto err;
+	}
+
+	if (xudma_is_pktdma(rx_chn->common.udmax)) {
+		/* prepare the channel device as coherent */
+		rx_chn->common.chan_dev.dma_coherent = true;
+		dma_coerce_mask_and_coherent(&rx_chn->common.chan_dev,
+					     DMA_BIT_MASK(48));
+	}
+
 	ret = k3_udma_glue_allocate_rx_flows(rx_chn, cfg);
 	if (ret)
 		goto err;
@@ -936,6 +1111,11 @@ void k3_udma_glue_release_rx_chn(struct k3_udma_glue_rx_channel *rx_chn)
 	if (!IS_ERR_OR_NULL(rx_chn->udma_rchanx))
 		xudma_rchan_put(rx_chn->common.udmax,
 				rx_chn->udma_rchanx);
+
+	if (rx_chn->common.chan_dev.parent) {
+		device_unregister(&rx_chn->common.chan_dev);
+		rx_chn->common.chan_dev.parent = NULL;
+	}
 }
 EXPORT_SYMBOL_GPL(k3_udma_glue_release_rx_chn);
 
@@ -1052,12 +1232,24 @@ EXPORT_SYMBOL_GPL(k3_udma_glue_rx_flow_disable);
 
 int k3_udma_glue_enable_rx_chn(struct k3_udma_glue_rx_channel *rx_chn)
 {
+	int ret;
+
 	if (rx_chn->remote)
 		return -EINVAL;
 
 	if (rx_chn->flows_ready < rx_chn->flow_num)
 		return -EINVAL;
 
+	ret = xudma_navss_psil_pair(rx_chn->common.udmax,
+				    rx_chn->common.src_thread,
+				    rx_chn->common.dst_thread);
+	if (ret) {
+		dev_err(rx_chn->common.dev, "PSI-L request err %d\n", ret);
+		return ret;
+	}
+
+	rx_chn->psil_paired = true;
+
 	xudma_rchanrt_write(rx_chn->udma_rchanx, UDMA_CHAN_RT_CTL_REG,
 			    UDMA_CHAN_RT_CTL_EN);
 
@@ -1078,6 +1270,13 @@ void k3_udma_glue_disable_rx_chn(struct k3_udma_glue_rx_channel *rx_chn)
 	xudma_rchanrt_write(rx_chn->udma_rchanx, UDMA_CHAN_RT_CTL_REG, 0);
 
 	k3_udma_glue_dump_rx_rt_chn(rx_chn, "rxrt dis2");
+
+	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;
+	}
 }
 EXPORT_SYMBOL_GPL(k3_udma_glue_disable_rx_chn);
 
@@ -1128,12 +1327,10 @@ void k3_udma_glue_reset_rx_chn(struct k3_udma_glue_rx_channel *rx_chn,
 	/* 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;
+		goto do_reset;
 
 	/*
 	 * RX FDQ reset need to be special way as it is input for udma and its
@@ -1148,13 +1345,17 @@ void k3_udma_glue_reset_rx_chn(struct k3_udma_glue_rx_channel *rx_chn,
 	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);
+			if (ret != -ENODATA)
+				dev_err(dev, "RX reset pop %d\n", ret);
 			break;
 		}
 		cleanup(data, desc_dma);
 	}
 
 	k3_ringacc_ring_reset_dma(flow->ringrxfdq, occ_rx);
+
+do_reset:
+	k3_ringacc_ring_reset(flow->ringrx);
 }
 EXPORT_SYMBOL_GPL(k3_udma_glue_reset_rx_chn);
 
@@ -1184,8 +1385,52 @@ int k3_udma_glue_rx_get_irq(struct k3_udma_glue_rx_channel *rx_chn,
 
 	flow = &rx_chn->flows[flow_num];
 
-	flow->virq = k3_ringacc_get_ring_irq_num(flow->ringrx);
+	if (xudma_is_pktdma(rx_chn->common.udmax)) {
+		flow->virq = xudma_pktdma_rflow_get_irq(rx_chn->common.udmax,
+							flow->udma_rflow_id);
+	} else {
+		flow->virq = k3_ringacc_get_ring_irq_num(flow->ringrx);
+	}
 
 	return flow->virq;
 }
 EXPORT_SYMBOL_GPL(k3_udma_glue_rx_get_irq);
+
+struct device *
+	k3_udma_glue_rx_get_dma_device(struct k3_udma_glue_rx_channel *rx_chn)
+{
+	if (xudma_is_pktdma(rx_chn->common.udmax) &&
+	    (rx_chn->common.atype_asel == 14 || rx_chn->common.atype_asel == 15))
+		return &rx_chn->common.chan_dev;
+
+	return xudma_get_device(rx_chn->common.udmax);
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_rx_get_dma_device);
+
+void k3_udma_glue_rx_dma_to_cppi5_addr(struct k3_udma_glue_rx_channel *rx_chn,
+				       dma_addr_t *addr)
+{
+	if (!xudma_is_pktdma(rx_chn->common.udmax) ||
+	    !rx_chn->common.atype_asel)
+		return;
+
+	*addr |= (u64)rx_chn->common.atype_asel << K3_ADDRESS_ASEL_SHIFT;
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_rx_dma_to_cppi5_addr);
+
+void k3_udma_glue_rx_cppi5_to_dma_addr(struct k3_udma_glue_rx_channel *rx_chn,
+				       dma_addr_t *addr)
+{
+	if (!xudma_is_pktdma(rx_chn->common.udmax) ||
+	    !rx_chn->common.atype_asel)
+		return;
+
+	*addr &= (u64)GENMASK(K3_ADDRESS_ASEL_SHIFT - 1, 0);
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_rx_cppi5_to_dma_addr);
+
+static int __init k3_udma_glue_class_init(void)
+{
+	return class_register(&k3_udma_glue_devclass);
+}
+arch_initcall(k3_udma_glue_class_init);
diff --git a/drivers/dma/ti/k3-udma-private.c b/drivers/dma/ti/k3-udma-private.c
index 8563a392f30b..aada84f40723 100644
--- a/drivers/dma/ti/k3-udma-private.c
+++ b/drivers/dma/ti/k3-udma-private.c
@@ -50,6 +50,18 @@ struct udma_dev *of_xudma_dev_get(struct device_node *np, const char *property)
 }
 EXPORT_SYMBOL(of_xudma_dev_get);
 
+struct device *xudma_get_device(struct udma_dev *ud)
+{
+	return ud->dev;
+}
+EXPORT_SYMBOL(xudma_get_device);
+
+struct k3_ringacc *xudma_get_ringacc(struct udma_dev *ud)
+{
+	return ud->ringacc;
+}
+EXPORT_SYMBOL(xudma_get_ringacc);
+
 u32 xudma_dev_get_psil_base(struct udma_dev *ud)
 {
 	return ud->psil_base;
@@ -76,6 +88,9 @@ EXPORT_SYMBOL(xudma_free_gp_rflow_range);
 
 bool xudma_rflow_is_gp(struct udma_dev *ud, int id)
 {
+	if (!ud->rflow_gp_map)
+		return false;
+
 	return !test_bit(id, ud->rflow_gp_map);
 }
 EXPORT_SYMBOL(xudma_rflow_is_gp);
@@ -107,6 +122,12 @@ void xudma_rflow_put(struct udma_dev *ud, struct udma_rflow *p)
 }
 EXPORT_SYMBOL(xudma_rflow_put);
 
+int xudma_get_rflow_ring_offset(struct udma_dev *ud)
+{
+	return ud->tflow_cnt;
+}
+EXPORT_SYMBOL(xudma_get_rflow_ring_offset);
+
 #define XUDMA_GET_RESOURCE_ID(res)					\
 int xudma_##res##_get_id(struct udma_##res *p)				\
 {									\
@@ -136,3 +157,27 @@ void xudma_##res##rt_write(struct udma_##res *p, int reg, u32 val)	\
 EXPORT_SYMBOL(xudma_##res##rt_write)
 XUDMA_RT_IO_FUNCTIONS(tchan);
 XUDMA_RT_IO_FUNCTIONS(rchan);
+
+int xudma_is_pktdma(struct udma_dev *ud)
+{
+	return ud->match_data->type == DMA_TYPE_PKTDMA;
+}
+EXPORT_SYMBOL(xudma_is_pktdma);
+
+int xudma_pktdma_tflow_get_irq(struct udma_dev *ud, int udma_tflow_id)
+{
+	const struct udma_oes_offsets *oes = &ud->soc_data->oes;
+
+	return ti_sci_inta_msi_get_virq(ud->dev, udma_tflow_id +
+					oes->pktdma_tchan_flow);
+}
+EXPORT_SYMBOL(xudma_pktdma_tflow_get_irq);
+
+int xudma_pktdma_rflow_get_irq(struct udma_dev *ud, int udma_rflow_id)
+{
+	const struct udma_oes_offsets *oes = &ud->soc_data->oes;
+
+	return ti_sci_inta_msi_get_virq(ud->dev, udma_rflow_id +
+					oes->pktdma_rchan_flow);
+}
+EXPORT_SYMBOL(xudma_pktdma_rflow_get_irq);
diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c
index 82cf6c77f5c9..87157cbae1b8 100644
--- a/drivers/dma/ti/k3-udma.c
+++ b/drivers/dma/ti/k3-udma.c
@@ -26,6 +26,7 @@
 #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/k3-event-router.h>
 #include <linux/dma/ti-cppi5.h>
 
 #include "../virt-dma.h"
@@ -55,14 +56,26 @@ struct udma_static_tr {
 
 struct udma_chan;
 
+enum k3_dma_type {
+	DMA_TYPE_UDMA = 0,
+	DMA_TYPE_BCDMA,
+	DMA_TYPE_PKTDMA,
+};
+
 enum udma_mmr {
 	MMR_GCFG = 0,
+	MMR_BCHANRT,
 	MMR_RCHANRT,
 	MMR_TCHANRT,
 	MMR_LAST,
 };
 
-static const char * const mmr_names[] = { "gcfg", "rchanrt", "tchanrt" };
+static const char * const mmr_names[] = {
+	[MMR_GCFG] = "gcfg",
+	[MMR_BCHANRT] = "bchanrt",
+	[MMR_RCHANRT] = "rchanrt",
+	[MMR_TCHANRT] = "tchanrt",
+};
 
 struct udma_tchan {
 	void __iomem *reg_rt;
@@ -70,8 +83,12 @@ struct udma_tchan {
 	int id;
 	struct k3_ring *t_ring; /* Transmit ring */
 	struct k3_ring *tc_ring; /* Transmit Completion ring */
+	int tflow_id; /* applicable only for PKTDMA */
+
 };
 
+#define udma_bchan udma_tchan
+
 struct udma_rflow {
 	int id;
 	struct k3_ring *fd_ring; /* Free Descriptor ring */
@@ -84,10 +101,29 @@ struct udma_rchan {
 	int id;
 };
 
+struct udma_oes_offsets {
+	/* K3 UDMA Output Event Offset */
+	u32 udma_rchan;
+
+	/* BCDMA Output Event Offsets */
+	u32 bcdma_bchan_data;
+	u32 bcdma_bchan_ring;
+	u32 bcdma_tchan_data;
+	u32 bcdma_tchan_ring;
+	u32 bcdma_rchan_data;
+	u32 bcdma_rchan_ring;
+
+	/* PKTDMA Output Event Offsets */
+	u32 pktdma_tchan_flow;
+	u32 pktdma_rchan_flow;
+};
+
 #define UDMA_FLAG_PDMA_ACC32		BIT(0)
 #define UDMA_FLAG_PDMA_BURST		BIT(1)
+#define UDMA_FLAG_TDTYPE		BIT(2)
 
 struct udma_match_data {
+	enum k3_dma_type type;
 	u32 psil_base;
 	bool enable_memcpy_support;
 	u32 flags;
@@ -95,7 +131,8 @@ struct udma_match_data {
 };
 
 struct udma_soc_data {
-	u32 rchan_oes_offset;
+	struct udma_oes_offsets oes;
+	u32 bcdma_trigger_event_offset;
 };
 
 struct udma_hwdesc {
@@ -116,6 +153,11 @@ struct udma_rx_flush {
 	dma_addr_t buffer_paddr;
 };
 
+struct udma_tpl {
+	u8 levels;
+	u32 start_idx[3];
+};
+
 struct udma_dev {
 	struct dma_device ddev;
 	struct device *dev;
@@ -123,8 +165,9 @@ struct udma_dev {
 	const struct udma_match_data *match_data;
 	const struct udma_soc_data *soc_data;
 
-	u8 tpl_levels;
-	u32 tpl_start_idx[3];
+	struct udma_tpl bchan_tpl;
+	struct udma_tpl tchan_tpl;
+	struct udma_tpl rchan_tpl;
 
 	size_t desc_align; /* alignment to use for descriptors */
 
@@ -138,16 +181,21 @@ struct udma_dev {
 
 	struct udma_rx_flush rx_flush;
 
+	int bchan_cnt;
 	int tchan_cnt;
 	int echan_cnt;
 	int rchan_cnt;
 	int rflow_cnt;
+	int tflow_cnt;
+	unsigned long *bchan_map;
 	unsigned long *tchan_map;
 	unsigned long *rchan_map;
 	unsigned long *rflow_gp_map;
 	unsigned long *rflow_gp_map_allocated;
 	unsigned long *rflow_in_use;
+	unsigned long *tflow_map;
 
+	struct udma_bchan *bchans;
 	struct udma_tchan *tchans;
 	struct udma_rchan *rchans;
 	struct udma_rflow *rflows;
@@ -155,6 +203,7 @@ struct udma_dev {
 	struct udma_chan *channels;
 	u32 psil_base;
 	u32 atype;
+	u32 asel;
 };
 
 struct udma_desc {
@@ -199,6 +248,7 @@ struct udma_chan_config {
 	bool notdpkt; /* Suppress sending TDC packet */
 	int remote_thread_id;
 	u32 atype;
+	u32 asel;
 	u32 src_thread;
 	u32 dst_thread;
 	enum psil_endpoint_type ep_type;
@@ -206,6 +256,13 @@ struct udma_chan_config {
 	bool enable_burst;
 	enum udma_tp_level channel_tpl; /* Channel Throughput Level */
 
+	u32 tr_trigger_type;
+
+	/* PKDMA mapped channel */
+	int mapped_channel_id;
+	/* PKTDMA default tflow or rflow for mapped channel */
+	int default_flow_id;
+
 	enum dma_transfer_direction dir;
 };
 
@@ -213,11 +270,13 @@ struct udma_chan {
 	struct virt_dma_chan vc;
 	struct dma_slave_config	cfg;
 	struct udma_dev *ud;
+	struct device *dma_dev;
 	struct udma_desc *desc;
 	struct udma_desc *terminated_desc;
 	struct udma_static_tr static_tr;
 	char *name;
 
+	struct udma_bchan *bchan;
 	struct udma_tchan *tchan;
 	struct udma_rchan *rchan;
 	struct udma_rflow *rflow;
@@ -353,10 +412,36 @@ static int navss_psil_unpair(struct udma_dev *ud, u32 src_thread,
 						src_thread, dst_thread);
 }
 
+static void k3_configure_chan_coherency(struct dma_chan *chan, u32 asel)
+{
+	struct device *chan_dev = &chan->dev->device;
+
+	if (asel == 0) {
+		/* No special handling for the channel */
+		chan->dev->chan_dma_dev = false;
+
+		chan_dev->dma_coherent = false;
+		chan_dev->dma_parms = NULL;
+	} else if (asel == 14 || asel == 15) {
+		chan->dev->chan_dma_dev = true;
+
+		chan_dev->dma_coherent = true;
+		dma_coerce_mask_and_coherent(chan_dev, DMA_BIT_MASK(48));
+		chan_dev->dma_parms = chan_dev->parent->dma_parms;
+	} else {
+		dev_warn(chan->device->dev, "Invalid ASEL value: %u\n", asel);
+
+		chan_dev->dma_coherent = false;
+		chan_dev->dma_parms = NULL;
+	}
+}
+
 static void udma_reset_uchan(struct udma_chan *uc)
 {
 	memset(&uc->config, 0, sizeof(uc->config));
 	uc->config.remote_thread_id = -1;
+	uc->config.mapped_channel_id = -1;
+	uc->config.default_flow_id = -1;
 	uc->state = UDMA_CHAN_IS_IDLE;
 }
 
@@ -439,9 +524,7 @@ static void udma_free_hwdesc(struct udma_chan *uc, struct udma_desc *d)
 			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,
+		dma_free_coherent(uc->dma_dev, d->hwdesc[0].cppi5_desc_size,
 				  d->hwdesc[0].cppi5_desc_vaddr,
 				  d->hwdesc[0].cppi5_desc_paddr);
 
@@ -670,8 +753,10 @@ static void udma_reset_counters(struct udma_chan *uc)
 		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->bchan) {
+			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) {
@@ -746,10 +831,16 @@ 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)) {
+	if (uc->ud->match_data->type == DMA_TYPE_UDMA && ucc->pkt_mode &&
+	    (uc->cyclic || ucc->dir == DMA_DEV_TO_MEM)) {
 		int i;
 
-		/* Push all descriptors to ring for packet mode cyclic or RX */
+		/*
+		 * UDMA only: Push all descriptors to ring for packet mode
+		 * cyclic or RX
+		 * PKTDMA supports pre-linked descriptor and cyclic is not
+		 * supported
+		 */
 		for (i = 0; i < uc->desc->sglen; i++)
 			udma_push_to_ring(uc, i);
 	} else {
@@ -1020,13 +1111,12 @@ 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);
+	spin_lock(&uc->vc.lock);
 
 	/* Teardown completion message */
 	if (cppi5_desc_is_tdcm(paddr)) {
@@ -1077,7 +1167,7 @@ static irqreturn_t udma_ring_irq_handler(int irq, void *data)
 		}
 	}
 out:
-	spin_unlock_irqrestore(&uc->vc.lock, flags);
+	spin_unlock(&uc->vc.lock);
 
 	return IRQ_HANDLED;
 }
@@ -1086,9 +1176,8 @@ 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);
+	spin_lock(&uc->vc.lock);
 	d = uc->desc;
 	if (d) {
 		d->tr_idx = (d->tr_idx + 1) % d->sglen;
@@ -1103,7 +1192,7 @@ static irqreturn_t udma_udma_irq_handler(int irq, void *data)
 		}
 	}
 
-	spin_unlock_irqrestore(&uc->vc.lock, flags);
+	spin_unlock(&uc->vc.lock);
 
 	return IRQ_HANDLED;
 }
@@ -1181,10 +1270,12 @@ static struct udma_rflow *__udma_get_rflow(struct udma_dev *ud, int id)
 	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);
+	if (ud->rflow_gp_map) {
+		/* 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);
@@ -1215,10 +1306,10 @@ static struct udma_##res *__udma_reserve_##res(struct udma_dev *ud,	\
 	} else {							\
 		int start;						\
 									\
-		if (tpl >= ud->tpl_levels)				\
-			tpl = ud->tpl_levels - 1;			\
+		if (tpl >= ud->res##_tpl.levels)			\
+			tpl = ud->res##_tpl.levels - 1;			\
 									\
-		start = ud->tpl_start_idx[tpl];				\
+		start = ud->res##_tpl.start_idx[tpl];			\
 									\
 		id = find_next_zero_bit(ud->res##_map, ud->res##_cnt,	\
 					start);				\
@@ -1231,9 +1322,39 @@ static struct udma_##res *__udma_reserve_##res(struct udma_dev *ud,	\
 	return &ud->res##s[id];						\
 }
 
+UDMA_RESERVE_RESOURCE(bchan);
 UDMA_RESERVE_RESOURCE(tchan);
 UDMA_RESERVE_RESOURCE(rchan);
 
+static int bcdma_get_bchan(struct udma_chan *uc)
+{
+	struct udma_dev *ud = uc->ud;
+	enum udma_tp_level tpl;
+
+	if (uc->bchan) {
+		dev_dbg(ud->dev, "chan%d: already have bchan%d allocated\n",
+			uc->id, uc->bchan->id);
+		return 0;
+	}
+
+	/*
+	 * Use normal channels for peripherals, and highest TPL channel for
+	 * mem2mem
+	 */
+	if (uc->config.tr_trigger_type)
+		tpl = 0;
+	else
+		tpl = ud->bchan_tpl.levels - 1;
+
+	uc->bchan = __udma_reserve_bchan(ud, tpl, -1);
+	if (IS_ERR(uc->bchan))
+		return PTR_ERR(uc->bchan);
+
+	uc->tchan = uc->bchan;
+
+	return 0;
+}
+
 static int udma_get_tchan(struct udma_chan *uc)
 {
 	struct udma_dev *ud = uc->ud;
@@ -1244,9 +1365,39 @@ static int udma_get_tchan(struct udma_chan *uc)
 		return 0;
 	}
 
-	uc->tchan = __udma_reserve_tchan(ud, uc->config.channel_tpl, -1);
+	/*
+	 * mapped_channel_id is -1 for UDMA, BCDMA and PKTDMA unmapped channels.
+	 * For PKTDMA mapped channels it is configured to a channel which must
+	 * be used to service the peripheral.
+	 */
+	uc->tchan = __udma_reserve_tchan(ud, uc->config.channel_tpl,
+					 uc->config.mapped_channel_id);
+	if (IS_ERR(uc->tchan))
+		return PTR_ERR(uc->tchan);
+
+	if (ud->tflow_cnt) {
+		int tflow_id;
+
+		/* Only PKTDMA have support for tx flows */
+		if (uc->config.default_flow_id >= 0)
+			tflow_id = uc->config.default_flow_id;
+		else
+			tflow_id = uc->tchan->id;
+
+		if (test_bit(tflow_id, ud->tflow_map)) {
+			dev_err(ud->dev, "tflow%d is in use\n", tflow_id);
+			clear_bit(uc->tchan->id, ud->tchan_map);
+			uc->tchan = NULL;
+			return -ENOENT;
+		}
 
-	return PTR_ERR_OR_ZERO(uc->tchan);
+		uc->tchan->tflow_id = tflow_id;
+		set_bit(tflow_id, ud->tflow_map);
+	} else {
+		uc->tchan->tflow_id = -1;
+	}
+
+	return 0;
 }
 
 static int udma_get_rchan(struct udma_chan *uc)
@@ -1259,7 +1410,13 @@ static int udma_get_rchan(struct udma_chan *uc)
 		return 0;
 	}
 
-	uc->rchan = __udma_reserve_rchan(ud, uc->config.channel_tpl, -1);
+	/*
+	 * mapped_channel_id is -1 for UDMA, BCDMA and PKTDMA unmapped channels.
+	 * For PKTDMA mapped channels it is configured to a channel which must
+	 * be used to service the peripheral.
+	 */
+	uc->rchan = __udma_reserve_rchan(ud, uc->config.channel_tpl,
+					 uc->config.mapped_channel_id);
 
 	return PTR_ERR_OR_ZERO(uc->rchan);
 }
@@ -1287,8 +1444,11 @@ static int udma_get_chan_pair(struct udma_chan *uc)
 
 	/* 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];
+	/*
+	 * Try to use the highest TPL channel pair for MEM_TO_MEM channels
+	 * Note: in UDMAP the channel TPL is symmetric between tchan and rchan
+	 */
+	chan_id = ud->tchan_tpl.start_idx[ud->tchan_tpl.levels - 1];
 	for (; chan_id < end; chan_id++) {
 		if (!test_bit(chan_id, ud->tchan_map) &&
 		    !test_bit(chan_id, ud->rchan_map))
@@ -1303,6 +1463,9 @@ static int udma_get_chan_pair(struct udma_chan *uc)
 	uc->tchan = &ud->tchans[chan_id];
 	uc->rchan = &ud->rchans[chan_id];
 
+	/* UDMA does not use tx flows */
+	uc->tchan->tflow_id = -1;
+
 	return 0;
 }
 
@@ -1326,6 +1489,19 @@ static int udma_get_rflow(struct udma_chan *uc, int flow_id)
 	return PTR_ERR_OR_ZERO(uc->rflow);
 }
 
+static void bcdma_put_bchan(struct udma_chan *uc)
+{
+	struct udma_dev *ud = uc->ud;
+
+	if (uc->bchan) {
+		dev_dbg(ud->dev, "chan%d: put bchan%d\n", uc->id,
+			uc->bchan->id);
+		clear_bit(uc->bchan->id, ud->bchan_map);
+		uc->bchan = NULL;
+		uc->tchan = NULL;
+	}
+}
+
 static void udma_put_rchan(struct udma_chan *uc)
 {
 	struct udma_dev *ud = uc->ud;
@@ -1346,6 +1522,10 @@ static void udma_put_tchan(struct udma_chan *uc)
 		dev_dbg(ud->dev, "chan%d: put tchan%d\n", uc->id,
 			uc->tchan->id);
 		clear_bit(uc->tchan->id, ud->tchan_map);
+
+		if (uc->tchan->tflow_id >= 0)
+			clear_bit(uc->tchan->tflow_id, ud->tflow_map);
+
 		uc->tchan = NULL;
 	}
 }
@@ -1362,6 +1542,65 @@ static void udma_put_rflow(struct udma_chan *uc)
 	}
 }
 
+static void bcdma_free_bchan_resources(struct udma_chan *uc)
+{
+	if (!uc->bchan)
+		return;
+
+	k3_ringacc_ring_free(uc->bchan->tc_ring);
+	k3_ringacc_ring_free(uc->bchan->t_ring);
+	uc->bchan->tc_ring = NULL;
+	uc->bchan->t_ring = NULL;
+	k3_configure_chan_coherency(&uc->vc.chan, 0);
+
+	bcdma_put_bchan(uc);
+}
+
+static int bcdma_alloc_bchan_resources(struct udma_chan *uc)
+{
+	struct k3_ring_cfg ring_cfg;
+	struct udma_dev *ud = uc->ud;
+	int ret;
+
+	ret = bcdma_get_bchan(uc);
+	if (ret)
+		return ret;
+
+	ret = k3_ringacc_request_rings_pair(ud->ringacc, uc->bchan->id, -1,
+					    &uc->bchan->t_ring,
+					    &uc->bchan->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_RING;
+
+	k3_configure_chan_coherency(&uc->vc.chan, ud->asel);
+	ring_cfg.asel = ud->asel;
+	ring_cfg.dma_dev = dmaengine_get_dma_device(&uc->vc.chan);
+
+	ret = k3_ringacc_ring_cfg(uc->bchan->t_ring, &ring_cfg);
+	if (ret)
+		goto err_ringcfg;
+
+	return 0;
+
+err_ringcfg:
+	k3_ringacc_ring_free(uc->bchan->tc_ring);
+	uc->bchan->tc_ring = NULL;
+	k3_ringacc_ring_free(uc->bchan->t_ring);
+	uc->bchan->t_ring = NULL;
+	k3_configure_chan_coherency(&uc->vc.chan, 0);
+err_ring:
+	bcdma_put_bchan(uc);
+
+	return ret;
+}
+
 static void udma_free_tx_resources(struct udma_chan *uc)
 {
 	if (!uc->tchan)
@@ -1379,15 +1618,22 @@ static int udma_alloc_tx_resources(struct udma_chan *uc)
 {
 	struct k3_ring_cfg ring_cfg;
 	struct udma_dev *ud = uc->ud;
-	int ret;
+	struct udma_tchan *tchan;
+	int ring_idx, 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);
+	tchan = uc->tchan;
+	if (tchan->tflow_id >= 0)
+		ring_idx = tchan->tflow_id;
+	else
+		ring_idx = ud->bchan_cnt + tchan->id;
+
+	ret = k3_ringacc_request_rings_pair(ud->ringacc, ring_idx, -1,
+					    &tchan->t_ring,
+					    &tchan->tc_ring);
 	if (ret) {
 		ret = -EBUSY;
 		goto err_ring;
@@ -1396,10 +1642,18 @@ static int udma_alloc_tx_resources(struct udma_chan *uc)
 	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;
+	if (ud->match_data->type == DMA_TYPE_UDMA) {
+		ring_cfg.mode = K3_RINGACC_RING_MODE_MESSAGE;
+	} else {
+		ring_cfg.mode = K3_RINGACC_RING_MODE_RING;
+
+		k3_configure_chan_coherency(&uc->vc.chan, uc->config.asel);
+		ring_cfg.asel = uc->config.asel;
+		ring_cfg.dma_dev = dmaengine_get_dma_device(&uc->vc.chan);
+	}
 
-	ret = k3_ringacc_ring_cfg(uc->tchan->t_ring, &ring_cfg);
-	ret |= k3_ringacc_ring_cfg(uc->tchan->tc_ring, &ring_cfg);
+	ret = k3_ringacc_ring_cfg(tchan->t_ring, &ring_cfg);
+	ret |= k3_ringacc_ring_cfg(tchan->tc_ring, &ring_cfg);
 
 	if (ret)
 		goto err_ringcfg;
@@ -1452,14 +1706,23 @@ static int udma_alloc_rx_resources(struct udma_chan *uc)
 	if (uc->config.dir == DMA_MEM_TO_MEM)
 		return 0;
 
-	ret = udma_get_rflow(uc, uc->rchan->id);
+	if (uc->config.default_flow_id >= 0)
+		ret = udma_get_rflow(uc, uc->config.default_flow_id);
+	else
+		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;
+	if (ud->tflow_cnt)
+		fd_ring_id = ud->tflow_cnt + rflow->id;
+	else
+		fd_ring_id = ud->bchan_cnt + 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) {
@@ -1469,15 +1732,25 @@ static int udma_alloc_rx_resources(struct udma_chan *uc)
 
 	memset(&ring_cfg, 0, sizeof(ring_cfg));
 
-	if (uc->config.pkt_mode)
-		ring_cfg.size = SG_MAX_SEGMENTS;
-	else
+	ring_cfg.elm_size = K3_RINGACC_RING_ELSIZE_8;
+	if (ud->match_data->type == DMA_TYPE_UDMA) {
+		if (uc->config.pkt_mode)
+			ring_cfg.size = SG_MAX_SEGMENTS;
+		else
+			ring_cfg.size = K3_UDMA_DEFAULT_RING_SIZE;
+
+		ring_cfg.mode = K3_RINGACC_RING_MODE_MESSAGE;
+	} else {
 		ring_cfg.size = K3_UDMA_DEFAULT_RING_SIZE;
+		ring_cfg.mode = K3_RINGACC_RING_MODE_RING;
 
-	ring_cfg.elm_size = K3_RINGACC_RING_ELSIZE_8;
-	ring_cfg.mode = K3_RINGACC_RING_MODE_MESSAGE;
+		k3_configure_chan_coherency(&uc->vc.chan, uc->config.asel);
+		ring_cfg.asel = uc->config.asel;
+		ring_cfg.dma_dev = dmaengine_get_dma_device(&uc->vc.chan);
+	}
 
 	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);
 
@@ -1499,7 +1772,18 @@ err_rflow:
 	return ret;
 }
 
-#define TISCI_TCHAN_VALID_PARAMS (				\
+#define TISCI_BCDMA_BCHAN_VALID_PARAMS (			\
+	TI_SCI_MSG_VALUE_RM_UDMAP_CH_PAUSE_ON_ERR_VALID |	\
+	TI_SCI_MSG_VALUE_RM_UDMAP_CH_EXTENDED_CH_TYPE_VALID)
+
+#define TISCI_BCDMA_TCHAN_VALID_PARAMS (			\
+	TI_SCI_MSG_VALUE_RM_UDMAP_CH_PAUSE_ON_ERR_VALID |	\
+	TI_SCI_MSG_VALUE_RM_UDMAP_CH_TX_SUPR_TDPKT_VALID)
+
+#define TISCI_BCDMA_RCHAN_VALID_PARAMS (			\
+	TI_SCI_MSG_VALUE_RM_UDMAP_CH_PAUSE_ON_ERR_VALID)
+
+#define TISCI_UDMA_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 |	\
@@ -1509,7 +1793,7 @@ err_rflow:
 	TI_SCI_MSG_VALUE_RM_UDMAP_CH_CQ_QNUM_VALID |		\
 	TI_SCI_MSG_VALUE_RM_UDMAP_CH_ATYPE_VALID)
 
-#define TISCI_RCHAN_VALID_PARAMS (				\
+#define TISCI_UDMA_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 |		\
@@ -1534,7 +1818,7 @@ static int udma_tisci_m2m_channel_config(struct udma_chan *uc)
 	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.valid_params = TISCI_UDMA_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;
@@ -1548,7 +1832,7 @@ static int udma_tisci_m2m_channel_config(struct udma_chan *uc)
 		return ret;
 	}
 
-	req_rx.valid_params = TISCI_RCHAN_VALID_PARAMS;
+	req_rx.valid_params = TISCI_UDMA_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;
@@ -1563,6 +1847,27 @@ static int udma_tisci_m2m_channel_config(struct udma_chan *uc)
 	return ret;
 }
 
+static int bcdma_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 ti_sci_msg_rm_udmap_tx_ch_cfg req_tx = { 0 };
+	struct udma_bchan *bchan = uc->bchan;
+	int ret = 0;
+
+	req_tx.valid_params = TISCI_BCDMA_BCHAN_VALID_PARAMS;
+	req_tx.nav_id = tisci_rm->tisci_dev_id;
+	req_tx.extended_ch_type = TI_SCI_RM_BCDMA_EXTENDED_CH_TYPE_BCHAN;
+	req_tx.index = bchan->id;
+
+	ret = tisci_ops->tx_ch_cfg(tisci_rm->tisci, &req_tx);
+	if (ret)
+		dev_err(ud->dev, "bchan%d cfg failed %d\n", bchan->id, ret);
+
+	return ret;
+}
+
 static int udma_tisci_tx_channel_config(struct udma_chan *uc)
 {
 	struct udma_dev *ud = uc->ud;
@@ -1583,7 +1888,7 @@ static int udma_tisci_tx_channel_config(struct udma_chan *uc)
 		fetch_size = sizeof(struct cppi5_desc_hdr_t);
 	}
 
-	req_tx.valid_params = TISCI_TCHAN_VALID_PARAMS;
+	req_tx.valid_params = TISCI_UDMA_TCHAN_VALID_PARAMS;
 	req_tx.nav_id = tisci_rm->tisci_dev_id;
 	req_tx.index = tchan->id;
 	req_tx.tx_chan_type = mode;
@@ -1591,6 +1896,13 @@ static int udma_tisci_tx_channel_config(struct udma_chan *uc)
 	req_tx.tx_fetch_size = fetch_size >> 2;
 	req_tx.txcq_qnum = tc_ring;
 	req_tx.tx_atype = uc->config.atype;
+	if (uc->config.ep_type == PSIL_EP_PDMA_XY &&
+	    ud->match_data->flags & UDMA_FLAG_TDTYPE) {
+		/* wait for peer to complete the teardown for PDMAs */
+		req_tx.valid_params |=
+				TI_SCI_MSG_VALUE_RM_UDMAP_CH_TX_TDTYPE_VALID;
+		req_tx.tx_tdtype = 1;
+	}
 
 	ret = tisci_ops->tx_ch_cfg(tisci_rm->tisci, &req_tx);
 	if (ret)
@@ -1599,6 +1911,35 @@ static int udma_tisci_tx_channel_config(struct udma_chan *uc)
 	return ret;
 }
 
+static int bcdma_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;
+	struct ti_sci_msg_rm_udmap_tx_ch_cfg req_tx = { 0 };
+	int ret = 0;
+
+	req_tx.valid_params = TISCI_BCDMA_TCHAN_VALID_PARAMS;
+	req_tx.nav_id = tisci_rm->tisci_dev_id;
+	req_tx.index = tchan->id;
+	req_tx.tx_supr_tdpkt = uc->config.notdpkt;
+	if (ud->match_data->flags & UDMA_FLAG_TDTYPE) {
+		/* wait for peer to complete the teardown for PDMAs */
+		req_tx.valid_params |=
+				TI_SCI_MSG_VALUE_RM_UDMAP_CH_TX_TDTYPE_VALID;
+		req_tx.tx_tdtype = 1;
+	}
+
+	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;
+}
+
+#define pktdma_tisci_tx_channel_config bcdma_tisci_tx_channel_config
+
 static int udma_tisci_rx_channel_config(struct udma_chan *uc)
 {
 	struct udma_dev *ud = uc->ud;
@@ -1621,7 +1962,7 @@ static int udma_tisci_rx_channel_config(struct udma_chan *uc)
 		fetch_size = sizeof(struct cppi5_desc_hdr_t);
 	}
 
-	req_rx.valid_params = TISCI_RCHAN_VALID_PARAMS;
+	req_rx.valid_params = TISCI_UDMA_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;
@@ -1680,6 +2021,72 @@ static int udma_tisci_rx_channel_config(struct udma_chan *uc)
 	return 0;
 }
 
+static int bcdma_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;
+	struct ti_sci_msg_rm_udmap_rx_ch_cfg req_rx = { 0 };
+	int ret = 0;
+
+	req_rx.valid_params = TISCI_BCDMA_RCHAN_VALID_PARAMS;
+	req_rx.nav_id = tisci_rm->tisci_dev_id;
+	req_rx.index = rchan->id;
+
+	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;
+}
+
+static int pktdma_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 ti_sci_msg_rm_udmap_rx_ch_cfg req_rx = { 0 };
+	struct ti_sci_msg_rm_udmap_flow_cfg flow_req = { 0 };
+	int ret = 0;
+
+	req_rx.valid_params = TISCI_BCDMA_RCHAN_VALID_PARAMS;
+	req_rx.nav_id = tisci_rm->tisci_dev_id;
+	req_rx.index = uc->rchan->id;
+
+	ret = tisci_ops->rx_ch_cfg(tisci_rm->tisci, &req_rx);
+	if (ret) {
+		dev_err(ud->dev, "rchan%d cfg failed %d\n", uc->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;
+
+	flow_req.nav_id = tisci_rm->tisci_dev_id;
+	flow_req.flow_index = uc->rflow->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;
+
+	ret = tisci_ops->rx_flow_cfg(tisci_rm->tisci, &flow_req);
+
+	if (ret)
+		dev_err(ud->dev, "flow%d config failed: %d\n", uc->rflow->id,
+			ret);
+
+	return ret;
+}
+
 static int udma_alloc_chan_resources(struct dma_chan *chan)
 {
 	struct udma_chan *uc = to_udma_chan(chan);
@@ -1689,6 +2096,8 @@ static int udma_alloc_chan_resources(struct dma_chan *chan)
 	u32 irq_udma_idx;
 	int ret;
 
+	uc->dma_dev = ud->dev;
+
 	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 */
@@ -1784,7 +2193,7 @@ static int udma_alloc_chan_resources(struct dma_chan *chan)
 					K3_PSIL_DST_THREAD_ID_OFFSET;
 
 		irq_ring = uc->rflow->r_ring;
-		irq_udma_idx = soc_data->rchan_oes_offset + uc->rchan->id;
+		irq_udma_idx = soc_data->oes.udma_rchan + uc->rchan->id;
 
 		ret = udma_tisci_rx_channel_config(uc);
 		break;
@@ -1884,6 +2293,369 @@ err_cleanup:
 	return ret;
 }
 
+static int bcdma_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_oes_offsets *oes = &ud->soc_data->oes;
+	u32 irq_udma_idx, irq_ring_idx;
+	int ret;
+
+	/* Only TR mode is supported */
+	uc->config.pkt_mode = false;
+
+	/*
+	 * 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 = bcdma_alloc_bchan_resources(uc);
+		if (ret)
+			return ret;
+
+		irq_ring_idx = uc->bchan->id + oes->bcdma_bchan_ring;
+		irq_udma_idx = uc->bchan->id + oes->bcdma_bchan_data;
+
+		ret = bcdma_tisci_m2m_channel_config(uc);
+		break;
+	case DMA_MEM_TO_DEV:
+		/* Slave transfer synchronized - mem to dev (TX) trasnfer */
+		dev_dbg(uc->ud->dev, "%s: chan%d as MEM-to-DEV\n", __func__,
+			uc->id);
+
+		ret = udma_alloc_tx_resources(uc);
+		if (ret) {
+			uc->config.remote_thread_id = -1;
+			return ret;
+		}
+
+		uc->config.src_thread = ud->psil_base + uc->tchan->id;
+		uc->config.dst_thread = uc->config.remote_thread_id;
+		uc->config.dst_thread |= K3_PSIL_DST_THREAD_ID_OFFSET;
+
+		irq_ring_idx = uc->tchan->id + oes->bcdma_tchan_ring;
+		irq_udma_idx = uc->tchan->id + oes->bcdma_tchan_data;
+
+		ret = bcdma_tisci_tx_channel_config(uc);
+		break;
+	case DMA_DEV_TO_MEM:
+		/* Slave transfer synchronized - dev to mem (RX) trasnfer */
+		dev_dbg(uc->ud->dev, "%s: chan%d as DEV-to-MEM\n", __func__,
+			uc->id);
+
+		ret = udma_alloc_rx_resources(uc);
+		if (ret) {
+			uc->config.remote_thread_id = -1;
+			return ret;
+		}
+
+		uc->config.src_thread = uc->config.remote_thread_id;
+		uc->config.dst_thread = (ud->psil_base + uc->rchan->id) |
+					K3_PSIL_DST_THREAD_ID_OFFSET;
+
+		irq_ring_idx = uc->rchan->id + oes->bcdma_rchan_ring;
+		irq_udma_idx = uc->rchan->id + oes->bcdma_rchan_data;
+
+		ret = bcdma_tisci_rx_channel_config(uc);
+		break;
+	default:
+		/* Can not happen */
+		dev_err(uc->ud->dev, "%s: chan%d invalid direction (%u)\n",
+			__func__, uc->id, uc->config.dir);
+		return -EINVAL;
+	}
+
+	/* check if the channel configuration was successful */
+	if (ret)
+		goto err_res_free;
+
+	if (udma_is_chan_running(uc)) {
+		dev_warn(ud->dev, "chan%d: is running!\n", uc->id);
+		udma_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;
+		}
+	}
+
+	uc->dma_dev = dmaengine_get_dma_device(chan);
+	if (uc->config.dir == DMA_MEM_TO_MEM  && !uc->config.tr_trigger_type) {
+		uc->config.hdesc_size = cppi5_trdesc_calc_size(
+					sizeof(struct cppi5_tr_type15_t), 2);
+
+		uc->hdesc_pool = dma_pool_create(uc->name, ud->ddev.dev,
+						 uc->config.hdesc_size,
+						 ud->desc_align,
+						 0);
+		if (!uc->hdesc_pool) {
+			dev_err(ud->ddev.dev,
+				"Descriptor pool allocation failed\n");
+			uc->use_dma_pool = false;
+			return -ENOMEM;
+		}
+
+		uc->use_dma_pool = true;
+	} else if (uc->config.dir != DMA_MEM_TO_MEM) {
+		/* 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 = ti_sci_inta_msi_get_virq(ud->dev, irq_ring_idx);
+	if (uc->irq_num_ring <= 0) {
+		dev_err(ud->dev, "Failed to get ring irq (index: %u)\n",
+			irq_ring_idx);
+		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 BCDMA (TR events) only needed for slave channels */
+	if (is_slave_direction(uc->config.dir)) {
+		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 bcdma 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: BCDMA irq request failed\n",
+				uc->id);
+			free_irq(uc->irq_num_ring, uc);
+			goto err_irq_free;
+		}
+	} else {
+		uc->irq_num_udma = 0;
+	}
+
+	udma_reset_rings(uc);
+
+	INIT_DELAYED_WORK_ONSTACK(&uc->tx_drain.work,
+				  udma_check_tx_completion);
+	return 0;
+
+err_irq_free:
+	uc->irq_num_ring = 0;
+	uc->irq_num_udma = 0;
+err_psi_free:
+	if (uc->psil_paired)
+		navss_psil_unpair(ud, uc->config.src_thread,
+				  uc->config.dst_thread);
+	uc->psil_paired = false;
+err_res_free:
+	bcdma_free_bchan_resources(uc);
+	udma_free_tx_resources(uc);
+	udma_free_rx_resources(uc);
+
+	udma_reset_uchan(uc);
+
+	if (uc->use_dma_pool) {
+		dma_pool_destroy(uc->hdesc_pool);
+		uc->use_dma_pool = false;
+	}
+
+	return ret;
+}
+
+static int bcdma_router_config(struct dma_chan *chan)
+{
+	struct k3_event_route_data *router_data = chan->route_data;
+	struct udma_chan *uc = to_udma_chan(chan);
+	u32 trigger_event;
+
+	if (!uc->bchan)
+		return -EINVAL;
+
+	if (uc->config.tr_trigger_type != 1 && uc->config.tr_trigger_type != 2)
+		return -EINVAL;
+
+	trigger_event = uc->ud->soc_data->bcdma_trigger_event_offset;
+	trigger_event += (uc->bchan->id * 2) + uc->config.tr_trigger_type - 1;
+
+	return router_data->set_event(router_data->priv, trigger_event);
+}
+
+static int pktdma_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_oes_offsets *oes = &ud->soc_data->oes;
+	u32 irq_ring_idx;
+	int ret;
+
+	/*
+	 * 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_DEV:
+		/* Slave transfer synchronized - mem to dev (TX) trasnfer */
+		dev_dbg(uc->ud->dev, "%s: chan%d as MEM-to-DEV\n", __func__,
+			uc->id);
+
+		ret = udma_alloc_tx_resources(uc);
+		if (ret) {
+			uc->config.remote_thread_id = -1;
+			return ret;
+		}
+
+		uc->config.src_thread = ud->psil_base + uc->tchan->id;
+		uc->config.dst_thread = uc->config.remote_thread_id;
+		uc->config.dst_thread |= K3_PSIL_DST_THREAD_ID_OFFSET;
+
+		irq_ring_idx = uc->tchan->tflow_id + oes->pktdma_tchan_flow;
+
+		ret = pktdma_tisci_tx_channel_config(uc);
+		break;
+	case DMA_DEV_TO_MEM:
+		/* Slave transfer synchronized - dev to mem (RX) trasnfer */
+		dev_dbg(uc->ud->dev, "%s: chan%d as DEV-to-MEM\n", __func__,
+			uc->id);
+
+		ret = udma_alloc_rx_resources(uc);
+		if (ret) {
+			uc->config.remote_thread_id = -1;
+			return ret;
+		}
+
+		uc->config.src_thread = uc->config.remote_thread_id;
+		uc->config.dst_thread = (ud->psil_base + uc->rchan->id) |
+					K3_PSIL_DST_THREAD_ID_OFFSET;
+
+		irq_ring_idx = uc->rflow->id + oes->pktdma_rchan_flow;
+
+		ret = pktdma_tisci_rx_channel_config(uc);
+		break;
+	default:
+		/* Can not happen */
+		dev_err(uc->ud->dev, "%s: chan%d invalid direction (%u)\n",
+			__func__, uc->id, uc->config.dir);
+		return -EINVAL;
+	}
+
+	/* check if the channel configuration was successful */
+	if (ret)
+		goto err_res_free;
+
+	if (udma_is_chan_running(uc)) {
+		dev_warn(ud->dev, "chan%d: is running!\n", uc->id);
+		udma_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;
+		}
+	}
+
+	uc->dma_dev = dmaengine_get_dma_device(chan);
+	uc->hdesc_pool = dma_pool_create(uc->name, uc->dma_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_res_free;
+	}
+
+	uc->use_dma_pool = true;
+
+	/* 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 = ti_sci_inta_msi_get_virq(ud->dev, irq_ring_idx);
+	if (uc->irq_num_ring <= 0) {
+		dev_err(ud->dev, "Failed to get ring irq (index: %u)\n",
+			irq_ring_idx);
+		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;
+	}
+
+	uc->irq_num_udma = 0;
+
+	udma_reset_rings(uc);
+
+	INIT_DELAYED_WORK_ONSTACK(&uc->tx_drain.work,
+				  udma_check_tx_completion);
+
+	if (uc->tchan)
+		dev_dbg(ud->dev,
+			"chan%d: tchan%d, tflow%d, Remote thread: 0x%04x\n",
+			uc->id, uc->tchan->id, uc->tchan->tflow_id,
+			uc->config.remote_thread_id);
+	else if (uc->rchan)
+		dev_dbg(ud->dev,
+			"chan%d: rchan%d, rflow%d, Remote thread: 0x%04x\n",
+			uc->id, uc->rchan->id, uc->rflow->id,
+			uc->config.remote_thread_id);
+	return 0;
+
+err_irq_free:
+	uc->irq_num_ring = 0;
+err_psi_free:
+	navss_psil_unpair(ud, uc->config.src_thread, uc->config.dst_thread);
+	uc->psil_paired = false;
+err_res_free:
+	udma_free_tx_resources(uc);
+	udma_free_rx_resources(uc);
+
+	udma_reset_uchan(uc);
+
+	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)
 {
@@ -2028,6 +2800,7 @@ udma_prep_slave_sg_tr(struct udma_chan *uc, struct scatterlist *sgl,
 	size_t tr_size;
 	int num_tr = 0;
 	int tr_idx = 0;
+	u64 asel;
 
 	/* estimate the number of TRs we will need */
 	for_each_sg(sgl, sgent, sglen, i) {
@@ -2045,6 +2818,11 @@ udma_prep_slave_sg_tr(struct udma_chan *uc, struct scatterlist *sgl,
 
 	d->sglen = sglen;
 
+	if (uc->ud->match_data->type == DMA_TYPE_UDMA)
+		asel = 0;
+	else
+		asel = (u64)uc->config.asel << K3_ADDRESS_ASEL_SHIFT;
+
 	tr_req = d->hwdesc[0].tr_req_base;
 	for_each_sg(sgl, sgent, sglen, i) {
 		dma_addr_t sg_addr = sg_dma_address(sgent);
@@ -2063,6 +2841,7 @@ udma_prep_slave_sg_tr(struct udma_chan *uc, struct scatterlist *sgl,
 			      false, CPPI5_TR_EVENT_SIZE_COMPLETION, 0);
 		cppi5_tr_csf_set(&tr_req[tr_idx].flags, CPPI5_TR_CSF_SUPR_EVT);
 
+		sg_addr |= asel;
 		tr_req[tr_idx].addr = sg_addr;
 		tr_req[tr_idx].icnt0 = tr0_cnt0;
 		tr_req[tr_idx].icnt1 = tr0_cnt1;
@@ -2092,6 +2871,205 @@ udma_prep_slave_sg_tr(struct udma_chan *uc, struct scatterlist *sgl,
 	return d;
 }
 
+static struct udma_desc *
+udma_prep_slave_sg_triggered_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 cppi5_tr_type15_t *tr_req = NULL;
+	enum dma_slave_buswidth dev_width;
+	u16 tr_cnt0, tr_cnt1;
+	dma_addr_t dev_addr;
+	struct udma_desc *d;
+	unsigned int i;
+	size_t tr_size, sg_len;
+	int num_tr = 0;
+	int tr_idx = 0;
+	u32 burst, trigger_size, port_window;
+	u64 asel;
+
+	if (dir == DMA_DEV_TO_MEM) {
+		dev_addr = uc->cfg.src_addr;
+		dev_width = uc->cfg.src_addr_width;
+		burst = uc->cfg.src_maxburst;
+		port_window = uc->cfg.src_port_window_size;
+	} else if (dir == DMA_MEM_TO_DEV) {
+		dev_addr = uc->cfg.dst_addr;
+		dev_width = uc->cfg.dst_addr_width;
+		burst = uc->cfg.dst_maxburst;
+		port_window = uc->cfg.dst_port_window_size;
+	} else {
+		dev_err(uc->ud->dev, "%s: bad direction?\n", __func__);
+		return NULL;
+	}
+
+	if (!burst)
+		burst = 1;
+
+	if (port_window) {
+		if (port_window != burst) {
+			dev_err(uc->ud->dev,
+				"The burst must be equal to port_window\n");
+			return NULL;
+		}
+
+		tr_cnt0 = dev_width * port_window;
+		tr_cnt1 = 1;
+	} else {
+		tr_cnt0 = dev_width;
+		tr_cnt1 = burst;
+	}
+	trigger_size = tr_cnt0 * tr_cnt1;
+
+	/* estimate the number of TRs we will need */
+	for_each_sg(sgl, sgent, sglen, i) {
+		sg_len = sg_dma_len(sgent);
+
+		if (sg_len % trigger_size) {
+			dev_err(uc->ud->dev,
+				"Not aligned SG entry (%zu for %u)\n", sg_len,
+				trigger_size);
+			return NULL;
+		}
+
+		if (sg_len / trigger_size < SZ_64K)
+			num_tr++;
+		else
+			num_tr += 2;
+	}
+
+	/* Now allocate and setup the descriptor. */
+	tr_size = sizeof(struct cppi5_tr_type15_t);
+	d = udma_alloc_tr_desc(uc, tr_size, num_tr, dir);
+	if (!d)
+		return NULL;
+
+	d->sglen = sglen;
+
+	if (uc->ud->match_data->type == DMA_TYPE_UDMA) {
+		asel = 0;
+	} else {
+		asel = (u64)uc->config.asel << K3_ADDRESS_ASEL_SHIFT;
+		dev_addr |= asel;
+	}
+
+	tr_req = d->hwdesc[0].tr_req_base;
+	for_each_sg(sgl, sgent, sglen, i) {
+		u16 tr0_cnt2, tr0_cnt3, tr1_cnt2;
+		dma_addr_t sg_addr = sg_dma_address(sgent);
+
+		sg_len = sg_dma_len(sgent);
+		num_tr = udma_get_tr_counters(sg_len / trigger_size, 0,
+					      &tr0_cnt2, &tr0_cnt3, &tr1_cnt2);
+		if (num_tr < 0) {
+			dev_err(uc->ud->dev, "size %zu is not supported\n",
+				sg_len);
+			udma_free_hwdesc(uc, d);
+			kfree(d);
+			return NULL;
+		}
+
+		cppi5_tr_init(&tr_req[tr_idx].flags, CPPI5_TR_TYPE15, false,
+			      true, CPPI5_TR_EVENT_SIZE_COMPLETION, 0);
+		cppi5_tr_csf_set(&tr_req[tr_idx].flags, CPPI5_TR_CSF_SUPR_EVT);
+		cppi5_tr_set_trigger(&tr_req[tr_idx].flags,
+				     uc->config.tr_trigger_type,
+				     CPPI5_TR_TRIGGER_TYPE_ICNT2_DEC, 0, 0);
+
+		sg_addr |= asel;
+		if (dir == DMA_DEV_TO_MEM) {
+			tr_req[tr_idx].addr = dev_addr;
+			tr_req[tr_idx].icnt0 = tr_cnt0;
+			tr_req[tr_idx].icnt1 = tr_cnt1;
+			tr_req[tr_idx].icnt2 = tr0_cnt2;
+			tr_req[tr_idx].icnt3 = tr0_cnt3;
+			tr_req[tr_idx].dim1 = (-1) * tr_cnt0;
+
+			tr_req[tr_idx].daddr = sg_addr;
+			tr_req[tr_idx].dicnt0 = tr_cnt0;
+			tr_req[tr_idx].dicnt1 = tr_cnt1;
+			tr_req[tr_idx].dicnt2 = tr0_cnt2;
+			tr_req[tr_idx].dicnt3 = tr0_cnt3;
+			tr_req[tr_idx].ddim1 = tr_cnt0;
+			tr_req[tr_idx].ddim2 = trigger_size;
+			tr_req[tr_idx].ddim3 = trigger_size * tr0_cnt2;
+		} else {
+			tr_req[tr_idx].addr = sg_addr;
+			tr_req[tr_idx].icnt0 = tr_cnt0;
+			tr_req[tr_idx].icnt1 = tr_cnt1;
+			tr_req[tr_idx].icnt2 = tr0_cnt2;
+			tr_req[tr_idx].icnt3 = tr0_cnt3;
+			tr_req[tr_idx].dim1 = tr_cnt0;
+			tr_req[tr_idx].dim2 = trigger_size;
+			tr_req[tr_idx].dim3 = trigger_size * tr0_cnt2;
+
+			tr_req[tr_idx].daddr = dev_addr;
+			tr_req[tr_idx].dicnt0 = tr_cnt0;
+			tr_req[tr_idx].dicnt1 = tr_cnt1;
+			tr_req[tr_idx].dicnt2 = tr0_cnt2;
+			tr_req[tr_idx].dicnt3 = tr0_cnt3;
+			tr_req[tr_idx].ddim1 = (-1) * tr_cnt0;
+		}
+
+		tr_idx++;
+
+		if (num_tr == 2) {
+			cppi5_tr_init(&tr_req[tr_idx].flags, CPPI5_TR_TYPE15,
+				      false, true,
+				      CPPI5_TR_EVENT_SIZE_COMPLETION, 0);
+			cppi5_tr_csf_set(&tr_req[tr_idx].flags,
+					 CPPI5_TR_CSF_SUPR_EVT);
+			cppi5_tr_set_trigger(&tr_req[tr_idx].flags,
+					     uc->config.tr_trigger_type,
+					     CPPI5_TR_TRIGGER_TYPE_ICNT2_DEC,
+					     0, 0);
+
+			sg_addr += trigger_size * tr0_cnt2 * tr0_cnt3;
+			if (dir == DMA_DEV_TO_MEM) {
+				tr_req[tr_idx].addr = dev_addr;
+				tr_req[tr_idx].icnt0 = tr_cnt0;
+				tr_req[tr_idx].icnt1 = tr_cnt1;
+				tr_req[tr_idx].icnt2 = tr1_cnt2;
+				tr_req[tr_idx].icnt3 = 1;
+				tr_req[tr_idx].dim1 = (-1) * tr_cnt0;
+
+				tr_req[tr_idx].daddr = sg_addr;
+				tr_req[tr_idx].dicnt0 = tr_cnt0;
+				tr_req[tr_idx].dicnt1 = tr_cnt1;
+				tr_req[tr_idx].dicnt2 = tr1_cnt2;
+				tr_req[tr_idx].dicnt3 = 1;
+				tr_req[tr_idx].ddim1 = tr_cnt0;
+				tr_req[tr_idx].ddim2 = trigger_size;
+			} else {
+				tr_req[tr_idx].addr = sg_addr;
+				tr_req[tr_idx].icnt0 = tr_cnt0;
+				tr_req[tr_idx].icnt1 = tr_cnt1;
+				tr_req[tr_idx].icnt2 = tr1_cnt2;
+				tr_req[tr_idx].icnt3 = 1;
+				tr_req[tr_idx].dim1 = tr_cnt0;
+				tr_req[tr_idx].dim2 = trigger_size;
+
+				tr_req[tr_idx].daddr = dev_addr;
+				tr_req[tr_idx].dicnt0 = tr_cnt0;
+				tr_req[tr_idx].dicnt1 = tr_cnt1;
+				tr_req[tr_idx].dicnt2 = tr1_cnt2;
+				tr_req[tr_idx].dicnt3 = 1;
+				tr_req[tr_idx].ddim1 = (-1) * tr_cnt0;
+			}
+			tr_idx++;
+		}
+
+		d->residue += sg_len;
+	}
+
+	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)
@@ -2156,6 +3134,7 @@ udma_prep_slave_sg_pkt(struct udma_chan *uc, struct scatterlist *sgl,
 	struct udma_desc *d;
 	u32 ring_id;
 	unsigned int i;
+	u64 asel;
 
 	d = kzalloc(struct_size(d, hwdesc, sglen), GFP_NOWAIT);
 	if (!d)
@@ -2169,6 +3148,11 @@ udma_prep_slave_sg_pkt(struct udma_chan *uc, struct scatterlist *sgl,
 	else
 		ring_id = k3_ringacc_get_ring_id(uc->tchan->tc_ring);
 
+	if (uc->ud->match_data->type == DMA_TYPE_UDMA)
+		asel = 0;
+	else
+		asel = (u64)uc->config.asel << K3_ADDRESS_ASEL_SHIFT;
+
 	for_each_sg(sgl, sgent, sglen, i) {
 		struct udma_hwdesc *hwdesc = &d->hwdesc[i];
 		dma_addr_t sg_addr = sg_dma_address(sgent);
@@ -2203,14 +3187,16 @@ udma_prep_slave_sg_pkt(struct udma_chan *uc, struct scatterlist *sgl,
 		}
 
 		/* attach the sg buffer to the descriptor */
+		sg_addr |= asel;
 		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);
+						hwdesc->cppi5_desc_paddr | asel);
 
-		if (dir == DMA_MEM_TO_DEV)
+		if (uc->ud->match_data->type == DMA_TYPE_PKTDMA ||
+		    dir == DMA_MEM_TO_DEV)
 			h_desc = desc;
 	}
 
@@ -2333,7 +3319,8 @@ udma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	struct udma_desc *d;
 	u32 burst;
 
-	if (dir != uc->config.dir) {
+	if (dir != uc->config.dir &&
+	    (uc->config.dir == DMA_MEM_TO_MEM && !uc->config.tr_trigger_type)) {
 		dev_err(chan->device->dev,
 			"%s: chan%d is for %s, not supporting %s\n",
 			__func__, uc->id,
@@ -2359,9 +3346,12 @@ udma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	if (uc->config.pkt_mode)
 		d = udma_prep_slave_sg_pkt(uc, sgl, sglen, dir, tx_flags,
 					   context);
-	else
+	else if (is_slave_direction(uc->config.dir))
 		d = udma_prep_slave_sg_tr(uc, sgl, sglen, dir, tx_flags,
 					  context);
+	else
+		d = udma_prep_slave_sg_triggered_tr(uc, sgl, sglen, dir,
+						    tx_flags, context);
 
 	if (!d)
 		return NULL;
@@ -2415,7 +3405,12 @@ udma_prep_dma_cyclic_tr(struct udma_chan *uc, dma_addr_t buf_addr,
 		return NULL;
 
 	tr_req = d->hwdesc[0].tr_req_base;
-	period_addr = buf_addr;
+	if (uc->ud->match_data->type == DMA_TYPE_UDMA)
+		period_addr = buf_addr;
+	else
+		period_addr = buf_addr |
+			((u64)uc->config.asel << K3_ADDRESS_ASEL_SHIFT);
+
 	for (i = 0; i < periods; i++) {
 		int tr_idx = i * num_tr;
 
@@ -2480,6 +3475,9 @@ udma_prep_dma_cyclic_pkt(struct udma_chan *uc, dma_addr_t buf_addr,
 	else
 		ring_id = k3_ringacc_get_ring_id(uc->tchan->tc_ring);
 
+	if (uc->ud->match_data->type != DMA_TYPE_UDMA)
+		buf_addr |= (u64)uc->config.asel << K3_ADDRESS_ASEL_SHIFT;
+
 	for (i = 0; i < periods; i++) {
 		struct udma_hwdesc *hwdesc = &d->hwdesc[i];
 		dma_addr_t period_addr = buf_addr + (period_len * i);
@@ -2621,6 +3619,11 @@ udma_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 	d->tr_idx = 0;
 	d->residue = len;
 
+	if (uc->ud->match_data->type != DMA_TYPE_UDMA) {
+		src |= (u64)uc->ud->asel << K3_ADDRESS_ASEL_SHIFT;
+		dest |= (u64)uc->ud->asel << K3_ADDRESS_ASEL_SHIFT;
+	}
+
 	tr_req = d->hwdesc[0].tr_req_base;
 
 	cppi5_tr_init(&tr_req[0].flags, CPPI5_TR_TYPE15, false, true,
@@ -2978,6 +3981,7 @@ static void udma_free_chan_resources(struct dma_chan *chan)
 	vchan_free_chan_resources(&uc->vc);
 	tasklet_kill(&uc->vc.task);
 
+	bcdma_free_bchan_resources(uc);
 	udma_free_tx_resources(uc);
 	udma_free_rx_resources(uc);
 	udma_reset_uchan(uc);
@@ -2989,10 +3993,14 @@ static void udma_free_chan_resources(struct dma_chan *chan)
 }
 
 static struct platform_driver udma_driver;
+static struct platform_driver bcdma_driver;
+static struct platform_driver pktdma_driver;
 
 struct udma_filter_param {
 	int remote_thread_id;
 	u32 atype;
+	u32 asel;
+	u32 tr_trigger_type;
 };
 
 static bool udma_dma_filter_fn(struct dma_chan *chan, void *param)
@@ -3003,7 +4011,9 @@ static bool udma_dma_filter_fn(struct dma_chan *chan, void *param)
 	struct udma_chan *uc;
 	struct udma_dev *ud;
 
-	if (chan->device->dev->driver != &udma_driver.driver)
+	if (chan->device->dev->driver != &udma_driver.driver &&
+	    chan->device->dev->driver != &bcdma_driver.driver &&
+	    chan->device->dev->driver != &pktdma_driver.driver)
 		return false;
 
 	uc = to_udma_chan(chan);
@@ -3017,13 +4027,25 @@ static bool udma_dma_filter_fn(struct dma_chan *chan, void *param)
 		return false;
 	}
 
+	if (filter_param->asel > 15) {
+		dev_err(ud->dev, "Invalid channel asel: %u\n",
+			filter_param->asel);
+		return false;
+	}
+
 	ucc->remote_thread_id = filter_param->remote_thread_id;
 	ucc->atype = filter_param->atype;
+	ucc->asel = filter_param->asel;
+	ucc->tr_trigger_type = filter_param->tr_trigger_type;
 
-	if (ucc->remote_thread_id & K3_PSIL_DST_THREAD_ID_OFFSET)
+	if (ucc->tr_trigger_type) {
+		ucc->dir = DMA_MEM_TO_MEM;
+		goto triggered_bchan;
+	} else if (ucc->remote_thread_id & K3_PSIL_DST_THREAD_ID_OFFSET) {
 		ucc->dir = DMA_MEM_TO_DEV;
-	else
+	} else {
 		ucc->dir = DMA_DEV_TO_MEM;
+	}
 
 	ep_config = psil_get_ep_config(ucc->remote_thread_id);
 	if (IS_ERR(ep_config)) {
@@ -3032,6 +4054,19 @@ static bool udma_dma_filter_fn(struct dma_chan *chan, void *param)
 		ucc->dir = DMA_MEM_TO_MEM;
 		ucc->remote_thread_id = -1;
 		ucc->atype = 0;
+		ucc->asel = 0;
+		return false;
+	}
+
+	if (ud->match_data->type == DMA_TYPE_BCDMA &&
+	    ep_config->pkt_mode) {
+		dev_err(ud->dev,
+			"Only TR mode is supported (psi-l thread 0x%04x)\n",
+			ucc->remote_thread_id);
+		ucc->dir = DMA_MEM_TO_MEM;
+		ucc->remote_thread_id = -1;
+		ucc->atype = 0;
+		ucc->asel = 0;
 		return false;
 	}
 
@@ -3040,6 +4075,15 @@ static bool udma_dma_filter_fn(struct dma_chan *chan, void *param)
 	ucc->notdpkt = ep_config->notdpkt;
 	ucc->ep_type = ep_config->ep_type;
 
+	if (ud->match_data->type == DMA_TYPE_PKTDMA &&
+	    ep_config->mapped_channel_id >= 0) {
+		ucc->mapped_channel_id = ep_config->mapped_channel_id;
+		ucc->default_flow_id = ep_config->default_flow_id;
+	} else {
+		ucc->mapped_channel_id = -1;
+		ucc->default_flow_id = -1;
+	}
+
 	if (ucc->ep_type != PSIL_EP_NATIVE) {
 		const struct udma_match_data *match_data = ud->match_data;
 
@@ -3063,6 +4107,13 @@ static bool udma_dma_filter_fn(struct dma_chan *chan, void *param)
 		ucc->remote_thread_id, dmaengine_get_direction_text(ucc->dir));
 
 	return true;
+
+triggered_bchan:
+	dev_dbg(ud->dev, "chan%d: triggered channel (type: %u)\n", uc->id,
+		ucc->tr_trigger_type);
+
+	return true;
+
 }
 
 static struct dma_chan *udma_of_xlate(struct of_phandle_args *dma_spec,
@@ -3073,14 +4124,33 @@ static struct dma_chan *udma_of_xlate(struct of_phandle_args *dma_spec,
 	struct udma_filter_param filter_param;
 	struct dma_chan *chan;
 
-	if (dma_spec->args_count != 1 && dma_spec->args_count != 2)
-		return NULL;
+	if (ud->match_data->type == DMA_TYPE_BCDMA) {
+		if (dma_spec->args_count != 3)
+			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.tr_trigger_type = dma_spec->args[0];
+		filter_param.remote_thread_id = dma_spec->args[1];
+		filter_param.asel = dma_spec->args[2];
 		filter_param.atype = 0;
+	} else {
+		if (dma_spec->args_count != 1 && dma_spec->args_count != 2)
+			return NULL;
+
+		filter_param.remote_thread_id = dma_spec->args[0];
+		filter_param.tr_trigger_type = 0;
+		if (dma_spec->args_count == 2) {
+			if (ud->match_data->type == DMA_TYPE_UDMA) {
+				filter_param.atype = dma_spec->args[1];
+				filter_param.asel = 0;
+			} else {
+				filter_param.atype = 0;
+				filter_param.asel = dma_spec->args[1];
+			}
+		} else {
+			filter_param.atype = 0;
+			filter_param.asel = 0;
+		}
+	}
 
 	chan = __dma_request_channel(&mask, udma_dma_filter_fn, &filter_param,
 				     ofdma->of_node);
@@ -3093,28 +4163,48 @@ static struct dma_chan *udma_of_xlate(struct of_phandle_args *dma_spec,
 }
 
 static struct udma_match_data am654_main_data = {
+	.type = DMA_TYPE_UDMA,
 	.psil_base = 0x1000,
 	.enable_memcpy_support = true,
 	.statictr_z_mask = GENMASK(11, 0),
 };
 
 static struct udma_match_data am654_mcu_data = {
+	.type = DMA_TYPE_UDMA,
 	.psil_base = 0x6000,
 	.enable_memcpy_support = false,
 	.statictr_z_mask = GENMASK(11, 0),
 };
 
 static struct udma_match_data j721e_main_data = {
+	.type = DMA_TYPE_UDMA,
 	.psil_base = 0x1000,
 	.enable_memcpy_support = true,
-	.flags = UDMA_FLAG_PDMA_ACC32 | UDMA_FLAG_PDMA_BURST,
+	.flags = UDMA_FLAG_PDMA_ACC32 | UDMA_FLAG_PDMA_BURST | UDMA_FLAG_TDTYPE,
 	.statictr_z_mask = GENMASK(23, 0),
 };
 
 static struct udma_match_data j721e_mcu_data = {
+	.type = DMA_TYPE_UDMA,
 	.psil_base = 0x6000,
 	.enable_memcpy_support = false, /* MEM_TO_MEM is slow via MCU UDMA */
-	.flags = UDMA_FLAG_PDMA_ACC32 | UDMA_FLAG_PDMA_BURST,
+	.flags = UDMA_FLAG_PDMA_ACC32 | UDMA_FLAG_PDMA_BURST | UDMA_FLAG_TDTYPE,
+	.statictr_z_mask = GENMASK(23, 0),
+};
+
+static struct udma_match_data am64_bcdma_data = {
+	.type = DMA_TYPE_BCDMA,
+	.psil_base = 0x2000, /* for tchan and rchan, not applicable to bchan */
+	.enable_memcpy_support = true, /* Supported via bchan */
+	.flags = UDMA_FLAG_PDMA_ACC32 | UDMA_FLAG_PDMA_BURST | UDMA_FLAG_TDTYPE,
+	.statictr_z_mask = GENMASK(23, 0),
+};
+
+static struct udma_match_data am64_pktdma_data = {
+	.type = DMA_TYPE_PKTDMA,
+	.psil_base = 0x1000,
+	.enable_memcpy_support = false, /* PKTDMA does not support MEM_TO_MEM */
+	.flags = UDMA_FLAG_PDMA_ACC32 | UDMA_FLAG_PDMA_BURST | UDMA_FLAG_TDTYPE,
 	.statictr_z_mask = GENMASK(23, 0),
 };
 
@@ -3136,30 +4226,105 @@ static const struct of_device_id udma_of_match[] = {
 	{ /* Sentinel */ },
 };
 
+static const struct of_device_id bcdma_of_match[] = {
+	{
+		.compatible = "ti,am64-dmss-bcdma",
+		.data = &am64_bcdma_data,
+	},
+	{ /* Sentinel */ },
+};
+
+static const struct of_device_id pktdma_of_match[] = {
+	{
+		.compatible = "ti,am64-dmss-pktdma",
+		.data = &am64_pktdma_data,
+	},
+	{ /* Sentinel */ },
+};
+
 static struct udma_soc_data am654_soc_data = {
-	.rchan_oes_offset = 0x200,
+	.oes = {
+		.udma_rchan = 0x200,
+	},
 };
 
 static struct udma_soc_data j721e_soc_data = {
-	.rchan_oes_offset = 0x400,
+	.oes = {
+		.udma_rchan = 0x400,
+	},
 };
 
 static struct udma_soc_data j7200_soc_data = {
-	.rchan_oes_offset = 0x80,
+	.oes = {
+		.udma_rchan = 0x80,
+	},
+};
+
+static struct udma_soc_data am64_soc_data = {
+	.oes = {
+		.bcdma_bchan_data = 0x2200,
+		.bcdma_bchan_ring = 0x2400,
+		.bcdma_tchan_data = 0x2800,
+		.bcdma_tchan_ring = 0x2a00,
+		.bcdma_rchan_data = 0x2e00,
+		.bcdma_rchan_ring = 0x3000,
+		.pktdma_tchan_flow = 0x1200,
+		.pktdma_rchan_flow = 0x1600,
+	},
+	.bcdma_trigger_event_offset = 0xc400,
 };
 
 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 },
+	{ .family = "AM64X", .data = &am64_soc_data },
 	{ /* sentinel */ }
 };
 
 static int udma_get_mmrs(struct platform_device *pdev, struct udma_dev *ud)
 {
+	u32 cap2, cap3, cap4;
 	int i;
 
-	for (i = 0; i < MMR_LAST; i++) {
+	ud->mmrs[MMR_GCFG] = devm_platform_ioremap_resource_byname(pdev, mmr_names[MMR_GCFG]);
+	if (IS_ERR(ud->mmrs[MMR_GCFG]))
+		return PTR_ERR(ud->mmrs[MMR_GCFG]);
+
+	cap2 = udma_read(ud->mmrs[MMR_GCFG], 0x28);
+	cap3 = udma_read(ud->mmrs[MMR_GCFG], 0x2c);
+
+	switch (ud->match_data->type) {
+	case DMA_TYPE_UDMA:
+		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);
+		break;
+	case DMA_TYPE_BCDMA:
+		ud->bchan_cnt = BCDMA_CAP2_BCHAN_CNT(cap2);
+		ud->tchan_cnt = BCDMA_CAP2_TCHAN_CNT(cap2);
+		ud->rchan_cnt = BCDMA_CAP2_RCHAN_CNT(cap2);
+		break;
+	case DMA_TYPE_PKTDMA:
+		cap4 = udma_read(ud->mmrs[MMR_GCFG], 0x30);
+		ud->tchan_cnt = UDMA_CAP2_TCHAN_CNT(cap2);
+		ud->rchan_cnt = UDMA_CAP2_RCHAN_CNT(cap2);
+		ud->rflow_cnt = UDMA_CAP3_RFLOW_CNT(cap3);
+		ud->tflow_cnt = PKTDMA_CAP4_TFLOW_CNT(cap4);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	for (i = 1; i < MMR_LAST; i++) {
+		if (i == MMR_BCHANRT && ud->bchan_cnt == 0)
+			continue;
+		if (i == MMR_TCHANRT && ud->tchan_cnt == 0)
+			continue;
+		if (i == MMR_RCHANRT && ud->rchan_cnt == 0)
+			continue;
+
 		ud->mmrs[i] = devm_platform_ioremap_resource_byname(pdev, mmr_names[i]);
 		if (IS_ERR(ud->mmrs[i]))
 			return PTR_ERR(ud->mmrs[i]);
@@ -3168,48 +4333,58 @@ static int udma_get_mmrs(struct platform_device *pdev, struct udma_dev *ud)
 	return 0;
 }
 
+static void udma_mark_resource_ranges(struct udma_dev *ud, unsigned long *map,
+				      struct ti_sci_resource_desc *rm_desc,
+				      char *name)
+{
+	bitmap_clear(map, rm_desc->start, rm_desc->num);
+	bitmap_clear(map, rm_desc->start_sec, rm_desc->num_sec);
+	dev_dbg(ud->dev, "ti_sci resource range for %s: %d:%d | %d:%d\n", name,
+		rm_desc->start, rm_desc->num, rm_desc->start_sec,
+		rm_desc->num_sec);
+}
+
+static const char * const range_names[] = {
+	[RM_RANGE_BCHAN] = "ti,sci-rm-range-bchan",
+	[RM_RANGE_TCHAN] = "ti,sci-rm-range-tchan",
+	[RM_RANGE_RCHAN] = "ti,sci-rm-range-rchan",
+	[RM_RANGE_RFLOW] = "ti,sci-rm-range-rflow",
+	[RM_RANGE_TFLOW] = "ti,sci-rm-range-tflow",
+};
+
 static int udma_setup_resources(struct udma_dev *ud)
 {
+	int ret, i, j;
 	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;
+	u32 cap3;
 
 	/* Set up the throughput level start indexes */
+	cap3 = udma_read(ud->mmrs[MMR_GCFG], 0x2c);
 	if (of_device_is_compatible(dev->of_node,
 				    "ti,am654-navss-main-udmap")) {
-		ud->tpl_levels = 2;
-		ud->tpl_start_idx[0] = 8;
+		ud->tchan_tpl.levels = 2;
+		ud->tchan_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;
+		ud->tchan_tpl.levels = 2;
+		ud->tchan_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] = ud->tpl_start_idx[1] +
-				       UDMA_CAP3_HCHAN_CNT(cap3);
+		ud->tchan_tpl.levels = 3;
+		ud->tchan_tpl.start_idx[1] = UDMA_CAP3_UCHAN_CNT(cap3);
+		ud->tchan_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);
+		ud->tchan_tpl.levels = 2;
+		ud->tchan_tpl.start_idx[0] = UDMA_CAP3_HCHAN_CNT(cap3);
 	} else {
-		ud->tpl_levels = 1;
+		ud->tchan_tpl.levels = 1;
 	}
 
+	ud->rchan_tpl.levels = ud->tchan_tpl.levels;
+	ud->rchan_tpl.start_idx[0] = ud->tchan_tpl.start_idx[0];
+	ud->rchan_tpl.start_idx[1] = ud->tchan_tpl.start_idx[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),
@@ -3247,11 +4422,15 @@ static int udma_setup_resources(struct udma_dev *ud)
 	bitmap_set(ud->rflow_gp_map, 0, ud->rflow_cnt);
 
 	/* Get resource ranges from tisci */
-	for (i = 0; i < RM_RANGE_LAST; i++)
+	for (i = 0; i < RM_RANGE_LAST; i++) {
+		if (i == RM_RANGE_BCHAN || i == RM_RANGE_TFLOW)
+			continue;
+
 		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];
@@ -3259,13 +4438,9 @@ static int udma_setup_resources(struct udma_dev *ud)
 		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);
-		}
+		for (i = 0; i < rm_res->sets; i++)
+			udma_mark_resource_ranges(ud, ud->tchan_map,
+						  &rm_res->desc[i], "tchan");
 	}
 	irq_res.sets = rm_res->sets;
 
@@ -3275,13 +4450,9 @@ static int udma_setup_resources(struct udma_dev *ud)
 		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);
-		}
+		for (i = 0; i < rm_res->sets; i++)
+			udma_mark_resource_ranges(ud, ud->rchan_map,
+						  &rm_res->desc[i], "rchan");
 	}
 
 	irq_res.sets += rm_res->sets;
@@ -3290,12 +4461,21 @@ static int udma_setup_resources(struct udma_dev *ud)
 	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;
+		irq_res.desc[i].start_sec = rm_res->desc[i].start_sec;
+		irq_res.desc[i].num_sec = rm_res->desc[i].num_sec;
 	}
 	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;
+		if (rm_res->desc[j].num) {
+			irq_res.desc[i].start = rm_res->desc[j].start +
+					ud->soc_data->oes.udma_rchan;
+			irq_res.desc[i].num = rm_res->desc[j].num;
+		}
+		if (rm_res->desc[j].num_sec) {
+			irq_res.desc[i].start_sec = rm_res->desc[j].start_sec +
+					ud->soc_data->oes.udma_rchan;
+			irq_res.desc[i].num_sec = rm_res->desc[j].num_sec;
+		}
 	}
 	ret = ti_sci_inta_msi_domain_alloc_irqs(ud->dev, &irq_res);
 	kfree(irq_res.desc);
@@ -3311,15 +4491,344 @@ static int udma_setup_resources(struct udma_dev *ud)
 		bitmap_clear(ud->rflow_gp_map, ud->rchan_cnt,
 			     ud->rflow_cnt - ud->rchan_cnt);
 	} else {
+		for (i = 0; i < rm_res->sets; i++)
+			udma_mark_resource_ranges(ud, ud->rflow_gp_map,
+						  &rm_res->desc[i], "gp-rflow");
+	}
+
+	return 0;
+}
+
+static int bcdma_setup_resources(struct udma_dev *ud)
+{
+	int ret, i, j;
+	struct device *dev = ud->dev;
+	struct ti_sci_resource *rm_res, irq_res;
+	struct udma_tisci_rm *tisci_rm = &ud->tisci_rm;
+	const struct udma_oes_offsets *oes = &ud->soc_data->oes;
+	u32 cap;
+
+	/* Set up the throughput level start indexes */
+	cap = udma_read(ud->mmrs[MMR_GCFG], 0x2c);
+	if (BCDMA_CAP3_UBCHAN_CNT(cap)) {
+		ud->bchan_tpl.levels = 3;
+		ud->bchan_tpl.start_idx[1] = BCDMA_CAP3_UBCHAN_CNT(cap);
+		ud->bchan_tpl.start_idx[0] = BCDMA_CAP3_HBCHAN_CNT(cap);
+	} else if (BCDMA_CAP3_HBCHAN_CNT(cap)) {
+		ud->bchan_tpl.levels = 2;
+		ud->bchan_tpl.start_idx[0] = BCDMA_CAP3_HBCHAN_CNT(cap);
+	} else {
+		ud->bchan_tpl.levels = 1;
+	}
+
+	cap = udma_read(ud->mmrs[MMR_GCFG], 0x30);
+	if (BCDMA_CAP4_URCHAN_CNT(cap)) {
+		ud->rchan_tpl.levels = 3;
+		ud->rchan_tpl.start_idx[1] = BCDMA_CAP4_URCHAN_CNT(cap);
+		ud->rchan_tpl.start_idx[0] = BCDMA_CAP4_HRCHAN_CNT(cap);
+	} else if (BCDMA_CAP4_HRCHAN_CNT(cap)) {
+		ud->rchan_tpl.levels = 2;
+		ud->rchan_tpl.start_idx[0] = BCDMA_CAP4_HRCHAN_CNT(cap);
+	} else {
+		ud->rchan_tpl.levels = 1;
+	}
+
+	if (BCDMA_CAP4_UTCHAN_CNT(cap)) {
+		ud->tchan_tpl.levels = 3;
+		ud->tchan_tpl.start_idx[1] = BCDMA_CAP4_UTCHAN_CNT(cap);
+		ud->tchan_tpl.start_idx[0] = BCDMA_CAP4_HTCHAN_CNT(cap);
+	} else if (BCDMA_CAP4_HTCHAN_CNT(cap)) {
+		ud->tchan_tpl.levels = 2;
+		ud->tchan_tpl.start_idx[0] = BCDMA_CAP4_HTCHAN_CNT(cap);
+	} else {
+		ud->tchan_tpl.levels = 1;
+	}
+
+	ud->bchan_map = devm_kmalloc_array(dev, BITS_TO_LONGS(ud->bchan_cnt),
+					   sizeof(unsigned long), GFP_KERNEL);
+	ud->bchans = devm_kcalloc(dev, ud->bchan_cnt, sizeof(*ud->bchans),
+				  GFP_KERNEL);
+	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);
+	/* BCDMA do not really have flows, but the driver expect it */
+	ud->rflow_in_use = devm_kcalloc(dev, BITS_TO_LONGS(ud->rchan_cnt),
+					sizeof(unsigned long),
+					GFP_KERNEL);
+	ud->rflows = devm_kcalloc(dev, ud->rchan_cnt, sizeof(*ud->rflows),
+				  GFP_KERNEL);
+
+	if (!ud->bchan_map || !ud->tchan_map || !ud->rchan_map ||
+	    !ud->rflow_in_use || !ud->bchans || !ud->tchans || !ud->rchans ||
+	    !ud->rflows)
+		return -ENOMEM;
+
+	/* Get resource ranges from tisci */
+	for (i = 0; i < RM_RANGE_LAST; i++) {
+		if (i == RM_RANGE_RFLOW || i == RM_RANGE_TFLOW)
+			continue;
+		if (i == RM_RANGE_BCHAN && ud->bchan_cnt == 0)
+			continue;
+		if (i == RM_RANGE_TCHAN && ud->tchan_cnt == 0)
+			continue;
+		if (i == RM_RANGE_RCHAN && ud->rchan_cnt == 0)
+			continue;
+
+		tisci_rm->rm_ranges[i] =
+			devm_ti_sci_get_of_resource(tisci_rm->tisci, dev,
+						    tisci_rm->tisci_dev_id,
+						    (char *)range_names[i]);
+	}
+
+	irq_res.sets = 0;
+
+	/* bchan ranges */
+	if (ud->bchan_cnt) {
+		rm_res = tisci_rm->rm_ranges[RM_RANGE_BCHAN];
+		if (IS_ERR(rm_res)) {
+			bitmap_zero(ud->bchan_map, ud->bchan_cnt);
+		} else {
+			bitmap_fill(ud->bchan_map, ud->bchan_cnt);
+			for (i = 0; i < rm_res->sets; i++)
+				udma_mark_resource_ranges(ud, ud->bchan_map,
+							  &rm_res->desc[i],
+							  "bchan");
+		}
+		irq_res.sets += rm_res->sets;
+	}
+
+	/* tchan ranges */
+	if (ud->tchan_cnt) {
+		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++)
+				udma_mark_resource_ranges(ud, ud->tchan_map,
+							  &rm_res->desc[i],
+							  "tchan");
+		}
+		irq_res.sets += rm_res->sets * 2;
+	}
+
+	/* rchan ranges */
+	if (ud->rchan_cnt) {
+		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++)
+				udma_mark_resource_ranges(ud, ud->rchan_map,
+							  &rm_res->desc[i],
+							  "rchan");
+		}
+		irq_res.sets += rm_res->sets * 2;
+	}
+
+	irq_res.desc = kcalloc(irq_res.sets, sizeof(*irq_res.desc), GFP_KERNEL);
+	if (ud->bchan_cnt) {
+		rm_res = tisci_rm->rm_ranges[RM_RANGE_BCHAN];
 		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);
+			irq_res.desc[i].start = rm_res->desc[i].start +
+						oes->bcdma_bchan_ring;
+			irq_res.desc[i].num = rm_res->desc[i].num;
+		}
+	}
+	if (ud->tchan_cnt) {
+		rm_res = tisci_rm->rm_ranges[RM_RANGE_TCHAN];
+		for (j = 0; j < rm_res->sets; j++, i += 2) {
+			irq_res.desc[i].start = rm_res->desc[j].start +
+						oes->bcdma_tchan_data;
+			irq_res.desc[i].num = rm_res->desc[j].num;
+
+			irq_res.desc[i + 1].start = rm_res->desc[j].start +
+						oes->bcdma_tchan_ring;
+			irq_res.desc[i + 1].num = rm_res->desc[j].num;
+		}
+	}
+	if (ud->rchan_cnt) {
+		rm_res = tisci_rm->rm_ranges[RM_RANGE_RCHAN];
+		for (j = 0; j < rm_res->sets; j++, i += 2) {
+			irq_res.desc[i].start = rm_res->desc[j].start +
+						oes->bcdma_rchan_data;
+			irq_res.desc[i].num = rm_res->desc[j].num;
+
+			irq_res.desc[i + 1].start = rm_res->desc[j].start +
+						oes->bcdma_rchan_ring;
+			irq_res.desc[i + 1].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;
+	}
+
+	return 0;
+}
+
+static int pktdma_setup_resources(struct udma_dev *ud)
+{
+	int ret, i, j;
+	struct device *dev = ud->dev;
+	struct ti_sci_resource *rm_res, irq_res;
+	struct udma_tisci_rm *tisci_rm = &ud->tisci_rm;
+	const struct udma_oes_offsets *oes = &ud->soc_data->oes;
+	u32 cap3;
+
+	/* Set up the throughput level start indexes */
+	cap3 = udma_read(ud->mmrs[MMR_GCFG], 0x2c);
+	if (UDMA_CAP3_UCHAN_CNT(cap3)) {
+		ud->tchan_tpl.levels = 3;
+		ud->tchan_tpl.start_idx[1] = UDMA_CAP3_UCHAN_CNT(cap3);
+		ud->tchan_tpl.start_idx[0] = UDMA_CAP3_HCHAN_CNT(cap3);
+	} else if (UDMA_CAP3_HCHAN_CNT(cap3)) {
+		ud->tchan_tpl.levels = 2;
+		ud->tchan_tpl.start_idx[0] = UDMA_CAP3_HCHAN_CNT(cap3);
+	} else {
+		ud->tchan_tpl.levels = 1;
+	}
+
+	ud->tchan_tpl.levels = ud->tchan_tpl.levels;
+	ud->tchan_tpl.start_idx[0] = ud->tchan_tpl.start_idx[0];
+	ud->tchan_tpl.start_idx[1] = ud->tchan_tpl.start_idx[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_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);
+	ud->tflow_map = devm_kmalloc_array(dev, BITS_TO_LONGS(ud->tflow_cnt),
+					   sizeof(unsigned long), GFP_KERNEL);
+
+	if (!ud->tchan_map || !ud->rchan_map || !ud->tflow_map || !ud->tchans ||
+	    !ud->rchans || !ud->rflows || !ud->rflow_in_use)
+		return -ENOMEM;
+
+	/* Get resource ranges from tisci */
+	for (i = 0; i < RM_RANGE_LAST; i++) {
+		if (i == RM_RANGE_BCHAN)
+			continue;
+
+		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++)
+			udma_mark_resource_ranges(ud, ud->tchan_map,
+						  &rm_res->desc[i], "tchan");
+	}
+
+	/* rchan 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++)
+			udma_mark_resource_ranges(ud, ud->rchan_map,
+						  &rm_res->desc[i], "rchan");
+	}
+
+	/* rflow ranges */
+	rm_res = tisci_rm->rm_ranges[RM_RANGE_RFLOW];
+	if (IS_ERR(rm_res)) {
+		/* all rflows are assigned exclusively to Linux */
+		bitmap_zero(ud->rflow_in_use, ud->rflow_cnt);
+	} else {
+		bitmap_fill(ud->rflow_in_use, ud->rflow_cnt);
+		for (i = 0; i < rm_res->sets; i++)
+			udma_mark_resource_ranges(ud, ud->rflow_in_use,
+						  &rm_res->desc[i], "rflow");
+	}
+	irq_res.sets = rm_res->sets;
+
+	/* tflow ranges */
+	rm_res = tisci_rm->rm_ranges[RM_RANGE_TFLOW];
+	if (IS_ERR(rm_res)) {
+		/* all tflows are assigned exclusively to Linux */
+		bitmap_zero(ud->tflow_map, ud->tflow_cnt);
+	} else {
+		bitmap_fill(ud->tflow_map, ud->tflow_cnt);
+		for (i = 0; i < rm_res->sets; i++)
+			udma_mark_resource_ranges(ud, ud->tflow_map,
+						  &rm_res->desc[i], "tflow");
+	}
+	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_TFLOW];
+	for (i = 0; i < rm_res->sets; i++) {
+		irq_res.desc[i].start = rm_res->desc[i].start +
+					oes->pktdma_tchan_flow;
+		irq_res.desc[i].num = rm_res->desc[i].num;
+	}
+	rm_res = tisci_rm->rm_ranges[RM_RANGE_RFLOW];
+	for (j = 0; j < rm_res->sets; j++, i++) {
+		irq_res.desc[i].start = rm_res->desc[j].start +
+					oes->pktdma_rchan_flow;
+		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;
+	}
+
+	return 0;
+}
+
+static int setup_resources(struct udma_dev *ud)
+{
+	struct device *dev = ud->dev;
+	int ch_count, ret;
+
+	switch (ud->match_data->type) {
+	case DMA_TYPE_UDMA:
+		ret = udma_setup_resources(ud);
+		break;
+	case DMA_TYPE_BCDMA:
+		ret = bcdma_setup_resources(ud);
+		break;
+	case DMA_TYPE_PKTDMA:
+		ret = pktdma_setup_resources(ud);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (ret)
+		return ret;
+
+	ch_count  = ud->bchan_cnt + ud->tchan_cnt + ud->rchan_cnt;
+	if (ud->bchan_cnt)
+		ch_count -= bitmap_weight(ud->bchan_map, ud->bchan_cnt);
 	ch_count -= bitmap_weight(ud->tchan_map, ud->tchan_cnt);
 	ch_count -= bitmap_weight(ud->rchan_map, ud->rchan_cnt);
 	if (!ch_count)
@@ -3330,12 +4839,40 @@ static int udma_setup_resources(struct udma_dev *ud)
 	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));
+	switch (ud->match_data->type) {
+	case DMA_TYPE_UDMA:
+		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));
+		break;
+	case DMA_TYPE_BCDMA:
+		dev_info(dev,
+			 "Channels: %d (bchan: %u, tchan: %u, rchan: %u)\n",
+			 ch_count,
+			 ud->bchan_cnt - bitmap_weight(ud->bchan_map,
+						       ud->bchan_cnt),
+			 ud->tchan_cnt - bitmap_weight(ud->tchan_map,
+						       ud->tchan_cnt),
+			 ud->rchan_cnt - bitmap_weight(ud->rchan_map,
+						       ud->rchan_cnt));
+		break;
+	case DMA_TYPE_PKTDMA:
+		dev_info(dev,
+			 "Channels: %d (tchan: %u, rchan: %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));
+	default:
+		break;
+	}
 
 	return ch_count;
 }
@@ -3444,20 +4981,33 @@ static void udma_dbg_summary_show_chan(struct seq_file *s,
 
 	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));
+	if (ucc->tr_trigger_type)
+		seq_puts(s, " (triggered, ");
+	else
+		seq_printf(s, " (%s, ",
+			   dmaengine_get_direction_text(uc->config.dir));
 
 	switch (uc->config.dir) {
 	case DMA_MEM_TO_MEM:
+		if (uc->ud->match_data->type == DMA_TYPE_BCDMA) {
+			seq_printf(s, "bchan%d)\n", uc->bchan->id);
+			return;
+		}
+
 		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);
+		if (uc->ud->match_data->type == DMA_TYPE_PKTDMA)
+			seq_printf(s, "rflow%d, ", uc->rflow->id);
 		break;
 	case DMA_MEM_TO_DEV:
 		seq_printf(s, "tchan%d [0x%04x -> 0x%04x], ", uc->tchan->id,
 			   ucc->src_thread, ucc->dst_thread);
+		if (uc->ud->match_data->type == DMA_TYPE_PKTDMA)
+			seq_printf(s, "tflow%d, ", uc->tchan->tflow_id);
 		break;
 	default:
 		seq_printf(s, ")\n");
@@ -3519,6 +5069,25 @@ static int udma_probe(struct platform_device *pdev)
 	if (!ud)
 		return -ENOMEM;
 
+	match = of_match_node(udma_of_match, dev->of_node);
+	if (!match)
+		match = of_match_node(bcdma_of_match, dev->of_node);
+	if (!match) {
+		match = of_match_node(pktdma_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;
+
 	ret = udma_get_mmrs(pdev, ud);
 	if (ret)
 		return ret;
@@ -3542,16 +5111,44 @@ static int udma_probe(struct platform_device *pdev)
 		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;
+	if (ud->match_data->type == DMA_TYPE_UDMA) {
+		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;
+		}
+	} else {
+		ret = of_property_read_u32(dev->of_node, "ti,asel",
+					   &ud->asel);
+		if (!ret && ud->asel > 15) {
+			dev_err(dev, "Invalid asel: %u\n", ud->asel);
+			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 (ud->match_data->type == DMA_TYPE_UDMA) {
+		ud->ringacc = of_k3_ringacc_get_by_phandle(dev->of_node, "ti,ringacc");
+	} else {
+		struct k3_ringacc_init_data ring_init_data;
+
+		ring_init_data.tisci = ud->tisci_rm.tisci;
+		ring_init_data.tisci_dev_id = ud->tisci_rm.tisci_dev_id;
+		if (ud->match_data->type == DMA_TYPE_BCDMA) {
+			ring_init_data.num_rings = ud->bchan_cnt +
+						   ud->tchan_cnt +
+						   ud->rchan_cnt;
+		} else {
+			ring_init_data.num_rings = ud->rflow_cnt +
+						   ud->tflow_cnt;
+		}
+
+		ud->ringacc = k3_ringacc_dmarings_init(pdev, &ring_init_data);
+	}
+
 	if (IS_ERR(ud->ringacc))
 		return PTR_ERR(ud->ringacc);
 
@@ -3562,27 +5159,15 @@ static int udma_probe(struct platform_device *pdev)
 		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);
+	/* cyclic operation is not supported via PKTDMA */
+	if (ud->match_data->type != DMA_TYPE_PKTDMA) {
+		dma_cap_set(DMA_CYCLIC, ud->ddev.cap_mask);
+		ud->ddev.device_prep_dma_cyclic = udma_prep_dma_cyclic;
+	}
 
-	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;
@@ -3593,7 +5178,25 @@ static int udma_probe(struct platform_device *pdev)
 	ud->ddev.dbg_summary_show = udma_dbg_summary_show;
 #endif
 
+	switch (ud->match_data->type) {
+	case DMA_TYPE_UDMA:
+		ud->ddev.device_alloc_chan_resources =
+					udma_alloc_chan_resources;
+		break;
+	case DMA_TYPE_BCDMA:
+		ud->ddev.device_alloc_chan_resources =
+					bcdma_alloc_chan_resources;
+		ud->ddev.device_router_config = bcdma_router_config;
+		break;
+	case DMA_TYPE_PKTDMA:
+		ud->ddev.device_alloc_chan_resources =
+					pktdma_alloc_chan_resources;
+		break;
+	default:
+		return -EINVAL;
+	}
 	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);
@@ -3601,7 +5204,8 @@ static int udma_probe(struct platform_device *pdev)
 	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) {
+	if (ud->match_data->enable_memcpy_support &&
+	    !(ud->match_data->type == DMA_TYPE_BCDMA && ud->bchan_cnt == 0)) {
 		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);
@@ -3614,7 +5218,7 @@ static int udma_probe(struct platform_device *pdev)
 	INIT_LIST_HEAD(&ud->ddev.channels);
 	INIT_LIST_HEAD(&ud->desc_to_purge);
 
-	ch_count = udma_setup_resources(ud);
+	ch_count = setup_resources(ud);
 	if (ch_count <= 0)
 		return ch_count;
 
@@ -3629,6 +5233,13 @@ static int udma_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	for (i = 0; i < ud->bchan_cnt; i++) {
+		struct udma_bchan *bchan = &ud->bchans[i];
+
+		bchan->id = i;
+		bchan->reg_rt = ud->mmrs[MMR_BCHANRT] + i * 0x1000;
+	}
+
 	for (i = 0; i < ud->tchan_cnt; i++) {
 		struct udma_tchan *tchan = &ud->tchans[i];
 
@@ -3655,9 +5266,12 @@ static int udma_probe(struct platform_device *pdev)
 		uc->ud = ud;
 		uc->vc.desc_free = udma_desc_free;
 		uc->id = i;
+		uc->bchan = NULL;
 		uc->tchan = NULL;
 		uc->rchan = NULL;
 		uc->config.remote_thread_id = -1;
+		uc->config.mapped_channel_id = -1;
+		uc->config.default_flow_id = -1;
 		uc->config.dir = DMA_MEM_TO_MEM;
 		uc->name = devm_kasprintf(dev, GFP_KERNEL, "%s chan%d",
 					  dev_name(dev), i);
@@ -3696,5 +5310,25 @@ static struct platform_driver udma_driver = {
 };
 builtin_platform_driver(udma_driver);
 
+static struct platform_driver bcdma_driver = {
+	.driver = {
+		.name	= "ti-bcdma",
+		.of_match_table = bcdma_of_match,
+		.suppress_bind_attrs = true,
+	},
+	.probe		= udma_probe,
+};
+builtin_platform_driver(bcdma_driver);
+
+static struct platform_driver pktdma_driver = {
+	.driver = {
+		.name	= "ti-pktdma",
+		.of_match_table = pktdma_of_match,
+		.suppress_bind_attrs = true,
+	},
+	.probe		= udma_probe,
+};
+builtin_platform_driver(pktdma_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
index 09c4529e013d..d349c6d482ae 100644
--- a/drivers/dma/ti/k3-udma.h
+++ b/drivers/dma/ti/k3-udma.h
@@ -18,7 +18,7 @@
 #define UDMA_RX_FLOW_ID_FW_OES_REG	0x80
 #define UDMA_RX_FLOW_ID_FW_STATUS_REG	0x88
 
-/* TCHANRT/RCHANRT registers */
+/* BCHANRT/TCHANRT/RCHANRT registers */
 #define UDMA_CHAN_RT_CTL_REG		0x0
 #define UDMA_CHAN_RT_SWTRIG_REG		0x8
 #define UDMA_CHAN_RT_STDATA_REG		0x80
@@ -45,6 +45,18 @@
 #define UDMA_CAP3_HCHAN_CNT(val)	(((val) >> 14) & 0x1ff)
 #define UDMA_CAP3_UCHAN_CNT(val)	(((val) >> 23) & 0x1ff)
 
+#define BCDMA_CAP2_BCHAN_CNT(val)	((val) & 0x1ff)
+#define BCDMA_CAP2_TCHAN_CNT(val)	(((val) >> 9) & 0x1ff)
+#define BCDMA_CAP2_RCHAN_CNT(val)	(((val) >> 18) & 0x1ff)
+#define BCDMA_CAP3_HBCHAN_CNT(val)	(((val) >> 14) & 0x1ff)
+#define BCDMA_CAP3_UBCHAN_CNT(val)	(((val) >> 23) & 0x1ff)
+#define BCDMA_CAP4_HRCHAN_CNT(val)	((val) & 0xff)
+#define BCDMA_CAP4_URCHAN_CNT(val)	(((val) >> 8) & 0xff)
+#define BCDMA_CAP4_HTCHAN_CNT(val)	(((val) >> 16) & 0xff)
+#define BCDMA_CAP4_UTCHAN_CNT(val)	(((val) >> 24) & 0xff)
+
+#define PKTDMA_CAP4_TFLOW_CNT(val)	((val) & 0x3fff)
+
 /* UDMA_CHAN_RT_CTL_REG */
 #define UDMA_CHAN_RT_CTL_EN		BIT(31)
 #define UDMA_CHAN_RT_CTL_TDOWN		BIT(30)
@@ -82,15 +94,20 @@
  */
 #define PDMA_STATIC_TR_Z(x, mask)	((x) & (mask))
 
+/* Address Space Select */
+#define K3_ADDRESS_ASEL_SHIFT		48
+
 struct udma_dev;
 struct udma_tchan;
 struct udma_rchan;
 struct udma_rflow;
 
 enum udma_rm_range {
-	RM_RANGE_TCHAN = 0,
+	RM_RANGE_BCHAN = 0,
+	RM_RANGE_TCHAN,
 	RM_RANGE_RCHAN,
 	RM_RANGE_RFLOW,
+	RM_RANGE_TFLOW,
 	RM_RANGE_LAST,
 };
 
@@ -112,6 +129,8 @@ 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);
+struct device *xudma_get_device(struct udma_dev *ud);
+struct k3_ringacc *xudma_get_ringacc(struct udma_dev *ud);
 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);
@@ -136,5 +155,10 @@ 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);
+int xudma_get_rflow_ring_offset(struct udma_dev *ud);
+
+int xudma_is_pktdma(struct udma_dev *ud);
 
+int xudma_pktdma_tflow_get_irq(struct udma_dev *ud, int udma_tflow_id);
+int xudma_pktdma_rflow_get_irq(struct udma_dev *ud, int udma_rflow_id);
 #endif /* K3_UDMA_H_ */