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 ...
author: Linus Torvalds 2020-12-17 12:52:23 -0800
committer: Linus Torvalds 2020-12-17 12:52:23 -0800
commit: 6daa90439e91bb9a71864b02f7d0af8587ea889a (patch)
tree: cd747a40f9aac87089d3d73de9d42c5863fe7896 /drivers/dma
parent: 83005cd6bc76eef7bbf46b55bbb00ccc9534c38c (diff)
parent: 115ff12aecfd55376d704fa2c0a2d117e5827f9f (diff)
51 files changed, 6584 insertions, 549 deletions
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 90284ffda58a..d242c7632621 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -296,6 +296,16 @@ config INTEL_IDXD
 
 	  If unsure, say N.
 
+# Config symbol that collects all the dependencies that's necessary to
+# support shared virtual memory for the devices supported by idxd.
+config INTEL_IDXD_SVM
+	bool "Accelerator Shared Virtual Memory Support"
+	depends on INTEL_IDXD
+	depends on INTEL_IOMMU_SVM
+	depends on PCI_PRI
+	depends on PCI_PASID
+	depends on PCI_IOV
+
 config INTEL_IOATDMA
 	tristate "Intel I/OAT DMA support"
 	depends on PCI && X86_64
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index 3b53115db268..fe45ad5d06c4 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -30,7 +30,24 @@
 #define		AT_XDMAC_FIFO_SZ(i)	(((i) >> 5) & 0x7FF)		/* Number of Bytes */
 #define		AT_XDMAC_NB_REQ(i)	((((i) >> 16) & 0x3F) + 1)	/* Number of Peripheral Requests Minus One */
 #define AT_XDMAC_GCFG		0x04	/* Global Configuration Register */
+#define		AT_XDMAC_WRHP(i)		(((i) & 0xF) << 4)
+#define		AT_XDMAC_WRMP(i)		(((i) & 0xF) << 8)
+#define		AT_XDMAC_WRLP(i)		(((i) & 0xF) << 12)
+#define		AT_XDMAC_RDHP(i)		(((i) & 0xF) << 16)
+#define		AT_XDMAC_RDMP(i)		(((i) & 0xF) << 20)
+#define		AT_XDMAC_RDLP(i)		(((i) & 0xF) << 24)
+#define		AT_XDMAC_RDSG(i)		(((i) & 0xF) << 28)
+#define AT_XDMAC_GCFG_M2M	(AT_XDMAC_RDLP(0xF) | AT_XDMAC_WRLP(0xF))
+#define AT_XDMAC_GCFG_P2M	(AT_XDMAC_RDSG(0x1) | AT_XDMAC_RDHP(0x3) | \
+				AT_XDMAC_WRHP(0x5))
 #define AT_XDMAC_GWAC		0x08	/* Global Weighted Arbiter Configuration Register */
+#define		AT_XDMAC_PW0(i)		(((i) & 0xF) << 0)
+#define		AT_XDMAC_PW1(i)		(((i) & 0xF) << 4)
+#define		AT_XDMAC_PW2(i)		(((i) & 0xF) << 8)
+#define		AT_XDMAC_PW3(i)		(((i) & 0xF) << 12)
+#define AT_XDMAC_GWAC_M2M	0
+#define AT_XDMAC_GWAC_P2M	(AT_XDMAC_PW0(0xF) | AT_XDMAC_PW2(0xF))
+
 #define AT_XDMAC_GIE		0x0C	/* Global Interrupt Enable Register */
 #define AT_XDMAC_GID		0x10	/* Global Interrupt Disable Register */
 #define AT_XDMAC_GIM		0x14	/* Global Interrupt Mask Register */
@@ -38,13 +55,6 @@
 #define AT_XDMAC_GE		0x1C	/* Global Channel Enable Register */
 #define AT_XDMAC_GD		0x20	/* Global Channel Disable Register */
 #define AT_XDMAC_GS		0x24	/* Global Channel Status Register */
-#define AT_XDMAC_GRS		0x28	/* Global Channel Read Suspend Register */
-#define AT_XDMAC_GWS		0x2C	/* Global Write Suspend Register */
-#define AT_XDMAC_GRWS		0x30	/* Global Channel Read Write Suspend Register */
-#define AT_XDMAC_GRWR		0x34	/* Global Channel Read Write Resume Register */
-#define AT_XDMAC_GSWR		0x38	/* Global Channel Software Request Register */
-#define AT_XDMAC_GSWS		0x3C	/* Global channel Software Request Status Register */
-#define AT_XDMAC_GSWF		0x40	/* Global Channel Software Flush Request Register */
 #define AT_XDMAC_VERSION	0xFFC	/* XDMAC Version Register */
 
 /* Channel relative registers offsets */
@@ -150,8 +160,6 @@
 #define AT_XDMAC_CSUS		0x30	/* Channel Source Microblock Stride */
 #define AT_XDMAC_CDUS		0x34	/* Channel Destination Microblock Stride */
 
-#define AT_XDMAC_CHAN_REG_BASE	0x50	/* Channel registers base address */
-
 /* Microblock control members */
 #define AT_XDMAC_MBR_UBC_UBLEN_MAX	0xFFFFFFUL	/* Maximum Microblock Length */
 #define AT_XDMAC_MBR_UBC_NDE		(0x1 << 24)	/* Next Descriptor Enable */
@@ -179,6 +187,29 @@ enum atc_status {
 	AT_XDMAC_CHAN_IS_PAUSED,
 };
 
+struct at_xdmac_layout {
+	/* Global Channel Read Suspend Register */
+	u8				grs;
+	/* Global Write Suspend Register */
+	u8				gws;
+	/* Global Channel Read Write Suspend Register */
+	u8				grws;
+	/* Global Channel Read Write Resume Register */
+	u8				grwr;
+	/* Global Channel Software Request Register */
+	u8				gswr;
+	/* Global channel Software Request Status Register */
+	u8				gsws;
+	/* Global Channel Software Flush Request Register */
+	u8				gswf;
+	/* Channel reg base */
+	u8				chan_cc_reg_base;
+	/* Source/Destination Interface must be specified or not */
+	bool				sdif;
+	/* AXI queue priority configuration supported */
+	bool				axi_config;
+};
+
 /* ----- Channels ----- */
 struct at_xdmac_chan {
 	struct dma_chan			chan;
@@ -212,6 +243,7 @@ struct at_xdmac {
 	struct clk		*clk;
 	u32			save_gim;
 	struct dma_pool		*at_xdmac_desc_pool;
+	const struct at_xdmac_layout	*layout;
 	struct at_xdmac_chan	chan[];
 };
 
@@ -244,9 +276,35 @@ struct at_xdmac_desc {
 	struct list_head		xfer_node;
 } __aligned(sizeof(u64));
 
+static const struct at_xdmac_layout at_xdmac_sama5d4_layout = {
+	.grs = 0x28,
+	.gws = 0x2C,
+	.grws = 0x30,
+	.grwr = 0x34,
+	.gswr = 0x38,
+	.gsws = 0x3C,
+	.gswf = 0x40,
+	.chan_cc_reg_base = 0x50,
+	.sdif = true,
+	.axi_config = false,
+};
+
+static const struct at_xdmac_layout at_xdmac_sama7g5_layout = {
+	.grs = 0x30,
+	.gws = 0x38,
+	.grws = 0x40,
+	.grwr = 0x44,
+	.gswr = 0x48,
+	.gsws = 0x4C,
+	.gswf = 0x50,
+	.chan_cc_reg_base = 0x60,
+	.sdif = false,
+	.axi_config = true,
+};
+
 static inline void __iomem *at_xdmac_chan_reg_base(struct at_xdmac *atxdmac, unsigned int chan_nb)
 {
-	return atxdmac->regs + (AT_XDMAC_CHAN_REG_BASE + chan_nb * 0x40);
+	return atxdmac->regs + (atxdmac->layout->chan_cc_reg_base + chan_nb * 0x40);
 }
 
 #define at_xdmac_read(atxdmac, reg) readl_relaxed((atxdmac)->regs + (reg))
@@ -345,8 +403,10 @@ static void at_xdmac_start_xfer(struct at_xdmac_chan *atchan,
 	first->active_xfer = true;
 
 	/* Tell xdmac where to get the first descriptor. */
-	reg = AT_XDMAC_CNDA_NDA(first->tx_dma_desc.phys)
-	      | AT_XDMAC_CNDA_NDAIF(atchan->memif);
+	reg = AT_XDMAC_CNDA_NDA(first->tx_dma_desc.phys);
+	if (atxdmac->layout->sdif)
+		reg |= AT_XDMAC_CNDA_NDAIF(atchan->memif);
+
 	at_xdmac_chan_write(atchan, AT_XDMAC_CNDA, reg);
 
 	/*
@@ -541,6 +601,7 @@ static int at_xdmac_compute_chan_conf(struct dma_chan *chan,
 				      enum dma_transfer_direction direction)
 {
 	struct at_xdmac_chan	*atchan = to_at_xdmac_chan(chan);
+	struct at_xdmac		*atxdmac = to_at_xdmac(atchan->chan.device);
 	int			csize, dwidth;
 
 	if (direction == DMA_DEV_TO_MEM) {
@@ -548,12 +609,14 @@ static int at_xdmac_compute_chan_conf(struct dma_chan *chan,
 			AT91_XDMAC_DT_PERID(atchan->perid)
 			| AT_XDMAC_CC_DAM_INCREMENTED_AM
 			| AT_XDMAC_CC_SAM_FIXED_AM
-			| AT_XDMAC_CC_DIF(atchan->memif)
-			| AT_XDMAC_CC_SIF(atchan->perif)
 			| AT_XDMAC_CC_SWREQ_HWR_CONNECTED
 			| AT_XDMAC_CC_DSYNC_PER2MEM
 			| AT_XDMAC_CC_MBSIZE_SIXTEEN
 			| AT_XDMAC_CC_TYPE_PER_TRAN;
+		if (atxdmac->layout->sdif)
+			atchan->cfg |= AT_XDMAC_CC_DIF(atchan->memif) |
+				       AT_XDMAC_CC_SIF(atchan->perif);
+
 		csize = ffs(atchan->sconfig.src_maxburst) - 1;
 		if (csize < 0) {
 			dev_err(chan2dev(chan), "invalid src maxburst value\n");
@@ -571,12 +634,14 @@ static int at_xdmac_compute_chan_conf(struct dma_chan *chan,
 			AT91_XDMAC_DT_PERID(atchan->perid)
 			| AT_XDMAC_CC_DAM_FIXED_AM
 			| AT_XDMAC_CC_SAM_INCREMENTED_AM
-			| AT_XDMAC_CC_DIF(atchan->perif)
-			| AT_XDMAC_CC_SIF(atchan->memif)
 			| AT_XDMAC_CC_SWREQ_HWR_CONNECTED
 			| AT_XDMAC_CC_DSYNC_MEM2PER
 			| AT_XDMAC_CC_MBSIZE_SIXTEEN
 			| AT_XDMAC_CC_TYPE_PER_TRAN;
+		if (atxdmac->layout->sdif)
+			atchan->cfg |= AT_XDMAC_CC_DIF(atchan->perif) |
+				       AT_XDMAC_CC_SIF(atchan->memif);
+
 		csize = ffs(atchan->sconfig.dst_maxburst) - 1;
 		if (csize < 0) {
 			dev_err(chan2dev(chan), "invalid src maxburst value\n");
@@ -866,10 +931,12 @@ at_xdmac_interleaved_queue_desc(struct dma_chan *chan,
 	 * ERRATA: Even if useless for memory transfers, the PERID has to not
 	 * match the one of another channel. If not, it could lead to spurious
 	 * flag status.
+	 * For SAMA7G5x case, the SIF and DIF fields are no longer used.
+	 * Thus, no need to have the SIF/DIF interfaces here.
+	 * For SAMA5D4x and SAMA5D2x the SIF and DIF are already configured as
+	 * zero.
 	 */
-	u32			chan_cc = AT_XDMAC_CC_PERID(0x3f)
-					| AT_XDMAC_CC_DIF(0)
-					| AT_XDMAC_CC_SIF(0)
+	u32			chan_cc = AT_XDMAC_CC_PERID(0x7f)
 					| AT_XDMAC_CC_MBSIZE_SIXTEEN
 					| AT_XDMAC_CC_TYPE_MEM_TRAN;
 
@@ -1048,12 +1115,14 @@ at_xdmac_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 	 * ERRATA: Even if useless for memory transfers, the PERID has to not
 	 * match the one of another channel. If not, it could lead to spurious
 	 * flag status.
+	 * For SAMA7G5x case, the SIF and DIF fields are no longer used.
+	 * Thus, no need to have the SIF/DIF interfaces here.
+	 * For SAMA5D4x and SAMA5D2x the SIF and DIF are already configured as
+	 * zero.
 	 */
-	u32			chan_cc = AT_XDMAC_CC_PERID(0x3f)
+	u32			chan_cc = AT_XDMAC_CC_PERID(0x7f)
 					| AT_XDMAC_CC_DAM_INCREMENTED_AM
 					| AT_XDMAC_CC_SAM_INCREMENTED_AM
-					| AT_XDMAC_CC_DIF(0)
-					| AT_XDMAC_CC_SIF(0)
 					| AT_XDMAC_CC_MBSIZE_SIXTEEN
 					| AT_XDMAC_CC_TYPE_MEM_TRAN;
 	unsigned long		irqflags;
@@ -1154,12 +1223,14 @@ static struct at_xdmac_desc *at_xdmac_memset_create_desc(struct dma_chan *chan,
 	 * ERRATA: Even if useless for memory transfers, the PERID has to not
 	 * match the one of another channel. If not, it could lead to spurious
 	 * flag status.
+	 * For SAMA7G5x case, the SIF and DIF fields are no longer used.
+	 * Thus, no need to have the SIF/DIF interfaces here.
+	 * For SAMA5D4x and SAMA5D2x the SIF and DIF are already configured as
+	 * zero.
 	 */
-	u32			chan_cc = AT_XDMAC_CC_PERID(0x3f)
+	u32			chan_cc = AT_XDMAC_CC_PERID(0x7f)
 					| AT_XDMAC_CC_DAM_UBS_AM
 					| AT_XDMAC_CC_SAM_INCREMENTED_AM
-					| AT_XDMAC_CC_DIF(0)
-					| AT_XDMAC_CC_SIF(0)
 					| AT_XDMAC_CC_MBSIZE_SIXTEEN
 					| AT_XDMAC_CC_MEMSET_HW_MODE
 					| AT_XDMAC_CC_TYPE_MEM_TRAN;
@@ -1438,7 +1509,7 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 	mask = AT_XDMAC_CC_TYPE | AT_XDMAC_CC_DSYNC;
 	value = AT_XDMAC_CC_TYPE_PER_TRAN | AT_XDMAC_CC_DSYNC_PER2MEM;
 	if ((desc->lld.mbr_cfg & mask) == value) {
-		at_xdmac_write(atxdmac, AT_XDMAC_GSWF, atchan->mask);
+		at_xdmac_write(atxdmac, atxdmac->layout->gswf, atchan->mask);
 		while (!(at_xdmac_chan_read(atchan, AT_XDMAC_CIS) & AT_XDMAC_CIS_FIS))
 			cpu_relax();
 	}
@@ -1496,7 +1567,7 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 	 * FIFO flush ensures that data are really written.
 	 */
 	if ((desc->lld.mbr_cfg & mask) == value) {
-		at_xdmac_write(atxdmac, AT_XDMAC_GSWF, atchan->mask);
+		at_xdmac_write(atxdmac, atxdmac->layout->gswf, atchan->mask);
 		while (!(at_xdmac_chan_read(atchan, AT_XDMAC_CIS) & AT_XDMAC_CIS_FIS))
 			cpu_relax();
 	}
@@ -1761,7 +1832,7 @@ static int at_xdmac_device_pause(struct dma_chan *chan)
 		return 0;
 
 	spin_lock_irqsave(&atchan->lock, flags);
-	at_xdmac_write(atxdmac, AT_XDMAC_GRWS, atchan->mask);
+	at_xdmac_write(atxdmac, atxdmac->layout->grws, atchan->mask);
 	while (at_xdmac_chan_read(atchan, AT_XDMAC_CC)
 	       & (AT_XDMAC_CC_WRIP | AT_XDMAC_CC_RDIP))
 		cpu_relax();
@@ -1784,7 +1855,7 @@ static int at_xdmac_device_resume(struct dma_chan *chan)
 		return 0;
 	}
 
-	at_xdmac_write(atxdmac, AT_XDMAC_GRWR, atchan->mask);
+	at_xdmac_write(atxdmac, atxdmac->layout->grwr, atchan->mask);
 	clear_bit(AT_XDMAC_CHAN_IS_PAUSED, &atchan->status);
 	spin_unlock_irqrestore(&atchan->lock, flags);
 
@@ -1947,6 +2018,30 @@ static int atmel_xdmac_resume(struct device *dev)
 }
 #endif /* CONFIG_PM_SLEEP */
 
+static void at_xdmac_axi_config(struct platform_device *pdev)
+{
+	struct at_xdmac	*atxdmac = (struct at_xdmac *)platform_get_drvdata(pdev);
+	bool dev_m2m = false;
+	u32 dma_requests;
+
+	if (!atxdmac->layout->axi_config)
+		return; /* Not supported */
+
+	if (!of_property_read_u32(pdev->dev.of_node, "dma-requests",
+				  &dma_requests)) {
+		dev_info(&pdev->dev, "controller in mem2mem mode.\n");
+		dev_m2m = true;
+	}
+
+	if (dev_m2m) {
+		at_xdmac_write(atxdmac, AT_XDMAC_GCFG, AT_XDMAC_GCFG_M2M);
+		at_xdmac_write(atxdmac, AT_XDMAC_GWAC, AT_XDMAC_GWAC_M2M);
+	} else {
+		at_xdmac_write(atxdmac, AT_XDMAC_GCFG, AT_XDMAC_GCFG_P2M);
+		at_xdmac_write(atxdmac, AT_XDMAC_GWAC, AT_XDMAC_GWAC_P2M);
+	}
+}
+
 static int at_xdmac_probe(struct platform_device *pdev)
 {
 	struct at_xdmac	*atxdmac;
@@ -1986,6 +2081,10 @@ static int at_xdmac_probe(struct platform_device *pdev)
 	atxdmac->regs = base;
 	atxdmac->irq = irq;
 
+	atxdmac->layout = of_device_get_match_data(&pdev->dev);
+	if (!atxdmac->layout)
+		return -ENODEV;
+
 	atxdmac->clk = devm_clk_get(&pdev->dev, "dma_clk");
 	if (IS_ERR(atxdmac->clk)) {
 		dev_err(&pdev->dev, "can't get dma_clk\n");
@@ -2087,6 +2186,8 @@ static int at_xdmac_probe(struct platform_device *pdev)
 	dev_info(&pdev->dev, "%d channels, mapped at 0x%p\n",
 		 nr_channels, atxdmac->regs);
 
+	at_xdmac_axi_config(pdev);
+
 	return 0;
 
 err_dma_unregister:
@@ -2128,6 +2229,10 @@ static const struct dev_pm_ops atmel_xdmac_dev_pm_ops = {
 static const struct of_device_id atmel_xdmac_dt_ids[] = {
 	{
 		.compatible = "atmel,sama5d4-dma",
+		.data = &at_xdmac_sama5d4_layout,
+	}, {
+		.compatible = "microchip,sama7g5-dma",
+		.data = &at_xdmac_sama7g5_layout,
 	}, {
 		/* sentinel */
 	}
diff --git a/drivers/dma/dma-jz4780.c b/drivers/dma/dma-jz4780.c
index a608efaa435f..612d353648cf 100644
--- a/drivers/dma/dma-jz4780.c
+++ b/drivers/dma/dma-jz4780.c
@@ -1044,7 +1044,7 @@ static struct platform_driver jz4780_dma_driver = {
 	.remove		= jz4780_dma_remove,
 	.driver	= {
 		.name	= "jz4780-dma",
-		.of_match_table = of_match_ptr(jz4780_dma_dt_match),
+		.of_match_table = jz4780_dma_dt_match,
 	},
 };
 
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index a3a172173e34..f696246f57fd 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -573,6 +573,7 @@ static int dmatest_func(void *data)
 	struct dmatest_params	*params;
 	struct dma_chan		*chan;
 	struct dma_device	*dev;
+	struct device		*dma_dev;
 	unsigned int		error_count;
 	unsigned int		failed_tests = 0;
 	unsigned int		total_tests = 0;
@@ -606,6 +607,8 @@ static int dmatest_func(void *data)
 	params = &info->params;
 	chan = thread->chan;
 	dev = chan->device;
+	dma_dev = dmaengine_get_dma_device(chan);
+
 	src = &thread->src;
 	dst = &thread->dst;
 	if (thread->type == DMA_MEMCPY) {
@@ -730,7 +733,7 @@ static int dmatest_func(void *data)
 			filltime = ktime_add(filltime, diff);
 		}
 
-		um = dmaengine_get_unmap_data(dev->dev, src->cnt + dst->cnt,
+		um = dmaengine_get_unmap_data(dma_dev, src->cnt + dst->cnt,
 					      GFP_KERNEL);
 		if (!um) {
 			failed_tests++;
@@ -745,10 +748,10 @@ static int dmatest_func(void *data)
 			struct page *pg = virt_to_page(buf);
 			unsigned long pg_off = offset_in_page(buf);
 
-			um->addr[i] = dma_map_page(dev->dev, pg, pg_off,
+			um->addr[i] = dma_map_page(dma_dev, pg, pg_off,
 						   um->len, DMA_TO_DEVICE);
 			srcs[i] = um->addr[i] + src->off;
-			ret = dma_mapping_error(dev->dev, um->addr[i]);
+			ret = dma_mapping_error(dma_dev, um->addr[i]);
 			if (ret) {
 				result("src mapping error", total_tests,
 				       src->off, dst->off, len, ret);
@@ -763,9 +766,9 @@ static int dmatest_func(void *data)
 			struct page *pg = virt_to_page(buf);
 			unsigned long pg_off = offset_in_page(buf);
 
-			dsts[i] = dma_map_page(dev->dev, pg, pg_off, um->len,
+			dsts[i] = dma_map_page(dma_dev, pg, pg_off, um->len,
 					       DMA_BIDIRECTIONAL);
-			ret = dma_mapping_error(dev->dev, dsts[i]);
+			ret = dma_mapping_error(dma_dev, dsts[i]);
 			if (ret) {
 				result("dst mapping error", total_tests,
 				       src->off, dst->off, len, ret);
diff --git a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c
index 14c1ac26f866..e164f3295f5d 100644
--- a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c
+++ b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c
@@ -992,7 +992,7 @@ static struct platform_driver dw_driver = {
 	.remove		= dw_remove,
 	.driver = {
 		.name	= KBUILD_MODNAME,
-		.of_match_table = of_match_ptr(dw_dma_of_id_table),
+		.of_match_table = dw_dma_of_id_table,
 		.pm = &dw_axi_dma_pm_ops,
 	},
 };
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index 7ab83fe601ed..19a23767533a 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -982,8 +982,11 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan)
 
 	dev_vdbg(chan2dev(chan), "%s\n", __func__);
 
+	pm_runtime_get_sync(dw->dma.dev);
+
 	/* ASSERT:  channel is idle */
 	if (dma_readl(dw, CH_EN) & dwc->mask) {
+		pm_runtime_put_sync_suspend(dw->dma.dev);
 		dev_dbg(chan2dev(chan), "DMA channel not idle?\n");
 		return -EIO;
 	}
@@ -1000,6 +1003,7 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan)
 	 * We need controller-specific data to set up slave transfers.
 	 */
 	if (chan->private && !dw_dma_filter(chan, chan->private)) {
+		pm_runtime_put_sync_suspend(dw->dma.dev);
 		dev_warn(chan2dev(chan), "Wrong controller-specific data\n");
 		return -EINVAL;
 	}
@@ -1043,6 +1047,8 @@ static void dwc_free_chan_resources(struct dma_chan *chan)
 	if (!dw->in_use)
 		do_dw_dma_off(dw);
 
+	pm_runtime_put_sync_suspend(dw->dma.dev);
+
 	dev_vdbg(chan2dev(chan), "%s: done\n", __func__);
 }
 
diff --git a/drivers/dma/hisi_dma.c b/drivers/dma/hisi_dma.c
index e1a958ae7925..a259ee010e9b 100644
--- a/drivers/dma/hisi_dma.c
+++ b/drivers/dma/hisi_dma.c
@@ -431,9 +431,8 @@ static irqreturn_t hisi_dma_irq(int irq, void *data)
 	struct hisi_dma_dev *hdma_dev = chan->hdma_dev;
 	struct hisi_dma_desc *desc;
 	struct hisi_dma_cqe *cqe;
-	unsigned long flags;
 
-	spin_lock_irqsave(&chan->vc.lock, flags);
+	spin_lock(&chan->vc.lock);
 
 	desc = chan->desc;
 	cqe = chan->cq + chan->cq_head;
@@ -452,7 +451,7 @@ static irqreturn_t hisi_dma_irq(int irq, void *data)
 		chan->desc = NULL;
 	}
 
-	spin_unlock_irqrestore(&chan->vc.lock, flags);
+	spin_unlock(&chan->vc.lock);
 
 	return IRQ_HANDLED;
 }
diff --git a/drivers/dma/idma64.c b/drivers/dma/idma64.c
index f5a84c846394..f4c07ad3be15 100644
--- a/drivers/dma/idma64.c
+++ b/drivers/dma/idma64.c
@@ -667,9 +667,7 @@ static int idma64_platform_remove(struct platform_device *pdev)
 	return idma64_remove(chip);
 }
 
-#ifdef CONFIG_PM_SLEEP
-
-static int idma64_pm_suspend(struct device *dev)
+static int __maybe_unused idma64_pm_suspend(struct device *dev)
 {
 	struct idma64_chip *chip = dev_get_drvdata(dev);
 
@@ -677,7 +675,7 @@ static int idma64_pm_suspend(struct device *dev)
 	return 0;
 }
 
-static int idma64_pm_resume(struct device *dev)
+static int __maybe_unused idma64_pm_resume(struct device *dev)
 {
 	struct idma64_chip *chip = dev_get_drvdata(dev);
 
@@ -685,8 +683,6 @@ static int idma64_pm_resume(struct device *dev)
 	return 0;
 }
 
-#endif /* CONFIG_PM_SLEEP */
-
 static const struct dev_pm_ops idma64_dev_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(idma64_pm_suspend, idma64_pm_resume)
 };
diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c
index c3976156db2f..0db9b82ed8cf 100644
--- a/drivers/dma/idxd/cdev.c
+++ b/drivers/dma/idxd/cdev.c
@@ -11,6 +11,7 @@
 #include <linux/cdev.h>
 #include <linux/fs.h>
 #include <linux/poll.h>
+#include <linux/iommu.h>
 #include <uapi/linux/idxd.h>
 #include "registers.h"
 #include "idxd.h"
@@ -27,12 +28,15 @@ struct idxd_cdev_context {
  */
 static struct idxd_cdev_context ictx[IDXD_TYPE_MAX] = {
 	{ .name = "dsa" },
+	{ .name = "iax" }
 };
 
 struct idxd_user_context {
 	struct idxd_wq *wq;
 	struct task_struct *task;
+	unsigned int pasid;
 	unsigned int flags;
+	struct iommu_sva *sva;
 };
 
 enum idxd_cdev_cleanup {
@@ -75,6 +79,8 @@ static int idxd_cdev_open(struct inode *inode, struct file *filp)
 	struct idxd_wq *wq;
 	struct device *dev;
 	int rc = 0;
+	struct iommu_sva *sva;
+	unsigned int pasid;
 
 	wq = inode_wq(inode);
 	idxd = wq->idxd;
@@ -95,6 +101,34 @@ static int idxd_cdev_open(struct inode *inode, struct file *filp)
 
 	ctx->wq = wq;
 	filp->private_data = ctx;
+
+	if (device_pasid_enabled(idxd)) {
+		sva = iommu_sva_bind_device(dev, current->mm, NULL);
+		if (IS_ERR(sva)) {
+			rc = PTR_ERR(sva);
+			dev_err(dev, "pasid allocation failed: %d\n", rc);
+			goto failed;
+		}
+
+		pasid = iommu_sva_get_pasid(sva);
+		if (pasid == IOMMU_PASID_INVALID) {
+			iommu_sva_unbind_device(sva);
+			goto failed;
+		}
+
+		ctx->sva = sva;
+		ctx->pasid = pasid;
+
+		if (wq_dedicated(wq)) {
+			rc = idxd_wq_set_pasid(wq, pasid);
+			if (rc < 0) {
+				iommu_sva_unbind_device(sva);
+				dev_err(dev, "wq set pasid failed: %d\n", rc);
+				goto failed;
+			}
+		}
+	}
+
 	idxd_wq_get(wq);
 	mutex_unlock(&wq->wq_lock);
 	return 0;
@@ -111,13 +145,27 @@ static int idxd_cdev_release(struct inode *node, struct file *filep)
 	struct idxd_wq *wq = ctx->wq;
 	struct idxd_device *idxd = wq->idxd;
 	struct device *dev = &idxd->pdev->dev;
+	int rc;
 
 	dev_dbg(dev, "%s called\n", __func__);
 	filep->private_data = NULL;
 
 	/* Wait for in-flight operations to complete. */
-	idxd_wq_drain(wq);
+	if (wq_shared(wq)) {
+		idxd_device_drain_pasid(idxd, ctx->pasid);
+	} else {
+		if (device_pasid_enabled(idxd)) {
+			/* The wq disable in the disable pasid function will drain the wq */
+			rc = idxd_wq_disable_pasid(wq);
+			if (rc < 0)
+				dev_err(dev, "wq disable pasid failed.\n");
+		} else {
+			idxd_wq_drain(wq);
+		}
+	}
 
+	if (ctx->sva)
+		iommu_sva_unbind_device(ctx->sva);
 	kfree(ctx);
 	mutex_lock(&wq->wq_lock);
 	idxd_wq_put(wq);
diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index 663344987e3f..95f94a3ed6be 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -131,6 +131,8 @@ int idxd_wq_alloc_resources(struct idxd_wq *wq)
 	struct idxd_device *idxd = wq->idxd;
 	struct device *dev = &idxd->pdev->dev;
 	int rc, num_descs, i;
+	int align;
+	u64 tmp;
 
 	if (wq->type != IDXD_WQT_KERNEL)
 		return 0;
@@ -142,14 +144,27 @@ int idxd_wq_alloc_resources(struct idxd_wq *wq)
 	if (rc < 0)
 		return rc;
 
-	wq->compls_size = num_descs * sizeof(struct dsa_completion_record);
-	wq->compls = dma_alloc_coherent(dev, wq->compls_size,
-					&wq->compls_addr, GFP_KERNEL);
-	if (!wq->compls) {
+	if (idxd->type == IDXD_TYPE_DSA)
+		align = 32;
+	else if (idxd->type == IDXD_TYPE_IAX)
+		align = 64;
+	else
+		return -ENODEV;
+
+	wq->compls_size = num_descs * idxd->compl_size + align;
+	wq->compls_raw = dma_alloc_coherent(dev, wq->compls_size,
+					    &wq->compls_addr_raw, GFP_KERNEL);
+	if (!wq->compls_raw) {
 		rc = -ENOMEM;
 		goto fail_alloc_compls;
 	}
 
+	/* Adjust alignment */
+	wq->compls_addr = (wq->compls_addr_raw + (align - 1)) & ~(align - 1);
+	tmp = (u64)wq->compls_raw;
+	tmp = (tmp + (align - 1)) & ~(align - 1);
+	wq->compls = (struct dsa_completion_record *)tmp;
+
 	rc = alloc_descs(wq, num_descs);
 	if (rc < 0)
 		goto fail_alloc_descs;
@@ -163,9 +178,11 @@ int idxd_wq_alloc_resources(struct idxd_wq *wq)
 		struct idxd_desc *desc = wq->descs[i];
 
 		desc->hw = wq->hw_descs[i];
-		desc->completion = &wq->compls[i];
-		desc->compl_dma  = wq->compls_addr +
-			sizeof(struct dsa_completion_record) * i;
+		if (idxd->type == IDXD_TYPE_DSA)
+			desc->completion = &wq->compls[i];
+		else if (idxd->type == IDXD_TYPE_IAX)
+			desc->iax_completion = &wq->iax_compls[i];
+		desc->compl_dma = wq->compls_addr + idxd->compl_size * i;
 		desc->id = i;
 		desc->wq = wq;
 		desc->cpu = -1;
@@ -178,7 +195,8 @@ int idxd_wq_alloc_resources(struct idxd_wq *wq)
  fail_sbitmap_init:
 	free_descs(wq);
  fail_alloc_descs:
-	dma_free_coherent(dev, wq->compls_size, wq->compls, wq->compls_addr);
+	dma_free_coherent(dev, wq->compls_size, wq->compls_raw,
+			  wq->compls_addr_raw);
  fail_alloc_compls:
 	free_hw_descs(wq);
 	return rc;
@@ -193,7 +211,8 @@ void idxd_wq_free_resources(struct idxd_wq *wq)
 
 	free_hw_descs(wq);
 	free_descs(wq);
-	dma_free_coherent(dev, wq->compls_size, wq->compls, wq->compls_addr);
+	dma_free_coherent(dev, wq->compls_size, wq->compls_raw,
+			  wq->compls_addr_raw);
 	sbitmap_queue_free(&wq->sbq);
 }
 
@@ -273,10 +292,9 @@ int idxd_wq_map_portal(struct idxd_wq *wq)
 	start = pci_resource_start(pdev, IDXD_WQ_BAR);
 	start += idxd_get_wq_portal_full_offset(wq->id, IDXD_PORTAL_LIMITED);
 
-	wq->dportal = devm_ioremap(dev, start, IDXD_PORTAL_SIZE);
-	if (!wq->dportal)
+	wq->portal = devm_ioremap(dev, start, IDXD_PORTAL_SIZE);
+	if (!wq->portal)
 		return -ENOMEM;
-	dev_dbg(dev, "wq %d portal mapped at %p\n", wq->id, wq->dportal);
 
 	return 0;
 }
@@ -285,7 +303,61 @@ void idxd_wq_unmap_portal(struct idxd_wq *wq)
 {
 	struct device *dev = &wq->idxd->pdev->dev;
 
-	devm_iounmap(dev, wq->dportal);
+	devm_iounmap(dev, wq->portal);
+}
+
+int idxd_wq_set_pasid(struct idxd_wq *wq, int pasid)
+{
+	struct idxd_device *idxd = wq->idxd;
+	int rc;
+	union wqcfg wqcfg;
+	unsigned int offset;
+	unsigned long flags;
+
+	rc = idxd_wq_disable(wq);
+	if (rc < 0)
+		return rc;
+
+	offset = WQCFG_OFFSET(idxd, wq->id, WQCFG_PASID_IDX);
+	spin_lock_irqsave(&idxd->dev_lock, flags);
+	wqcfg.bits[WQCFG_PASID_IDX] = ioread32(idxd->reg_base + offset);
+	wqcfg.pasid_en = 1;
+	wqcfg.pasid = pasid;
+	iowrite32(wqcfg.bits[WQCFG_PASID_IDX], idxd->reg_base + offset);
+	spin_unlock_irqrestore(&idxd->dev_lock, flags);
+
+	rc = idxd_wq_enable(wq);
+	if (rc < 0)
+		return rc;
+
+	return 0;
+}
+
+int idxd_wq_disable_pasid(struct idxd_wq *wq)
+{
+	struct idxd_device *idxd = wq->idxd;
+	int rc;
+	union wqcfg wqcfg;
+	unsigned int offset;
+	unsigned long flags;
+
+	rc = idxd_wq_disable(wq);
+	if (rc < 0)
+		return rc;
+
+	offset = WQCFG_OFFSET(idxd, wq->id, WQCFG_PASID_IDX);
+	spin_lock_irqsave(&idxd->dev_lock, flags);
+	wqcfg.bits[WQCFG_PASID_IDX] = ioread32(idxd->reg_base + offset);
+	wqcfg.pasid_en = 0;
+	wqcfg.pasid = 0;
+	iowrite32(wqcfg.bits[WQCFG_PASID_IDX], idxd->reg_base + offset);
+	spin_unlock_irqrestore(&idxd->dev_lock, flags);
+
+	rc = idxd_wq_enable(wq);
+	if (rc < 0)
+		return rc;
+
+	return 0;
 }
 
 void idxd_wq_disable_cleanup(struct idxd_wq *wq)
@@ -301,6 +373,7 @@ void idxd_wq_disable_cleanup(struct idxd_wq *wq)
 	wq->group = NULL;
 	wq->threshold = 0;
 	wq->priority = 0;
+	wq->ats_dis = 0;
 	clear_bit(WQ_FLAG_DEDICATED, &wq->flags);
 	memset(wq->name, 0, WQ_NAME_SIZE);
 
@@ -468,6 +541,17 @@ void idxd_device_reset(struct idxd_device *idxd)
 	spin_unlock_irqrestore(&idxd->dev_lock, flags);
 }
 
+void idxd_device_drain_pasid(struct idxd_device *idxd, int pasid)
+{
+	struct device *dev = &idxd->pdev->dev;
+	u32 operand;
+
+	operand = pasid;
+	dev_dbg(dev, "cmd: %u operand: %#x\n", IDXD_CMD_DRAIN_PASID, operand);
+	idxd_cmd_exec(idxd, IDXD_CMD_DRAIN_PASID, operand, NULL);
+	dev_dbg(dev, "pasid %d drained\n", pasid);
+}
+
 /* Device configuration bits */
 static void idxd_group_config_write(struct idxd_group *group)
 {
@@ -479,24 +563,22 @@ static void idxd_group_config_write(struct idxd_group *group)
 	dev_dbg(dev, "Writing group %d cfg registers\n", group->id);
 
 	/* setup GRPWQCFG */
-	for (i = 0; i < 4; i++) {
-		grpcfg_offset = idxd->grpcfg_offset +
-			group->id * 64 + i * sizeof(u64);
-		iowrite64(group->grpcfg.wqs[i],
-			  idxd->reg_base + grpcfg_offset);
+	for (i = 0; i < GRPWQCFG_STRIDES; i++) {
+		grpcfg_offset = GRPWQCFG_OFFSET(idxd, group->id, i);
+		iowrite64(group->grpcfg.wqs[i], idxd->reg_base + grpcfg_offset);
 		dev_dbg(dev, "GRPCFG wq[%d:%d: %#x]: %#llx\n",
 			group->id, i, grpcfg_offset,
 			ioread64(idxd->reg_base + grpcfg_offset));
 	}
 
 	/* setup GRPENGCFG */
-	grpcfg_offset = idxd->grpcfg_offset + group->id * 64 + 32;
+	grpcfg_offset = GRPENGCFG_OFFSET(idxd, group->id);
 	iowrite64(group->grpcfg.engines, idxd->reg_base + grpcfg_offset);
 	dev_dbg(dev, "GRPCFG engs[%d: %#x]: %#llx\n", group->id,
 		grpcfg_offset, ioread64(idxd->reg_base + grpcfg_offset));
 
 	/* setup GRPFLAGS */
-	grpcfg_offset = idxd->grpcfg_offset + group->id * 64 + 40;
+	grpcfg_offset = GRPFLGCFG_OFFSET(idxd, group->id);
 	iowrite32(group->grpcfg.flags.bits, idxd->reg_base + grpcfg_offset);
 	dev_dbg(dev, "GRPFLAGS flags[%d: %#x]: %#x\n",
 		group->id, grpcfg_offset,
@@ -554,9 +636,24 @@ static int idxd_wq_config_write(struct idxd_wq *wq)
 
 	/* byte 8-11 */
 	wq->wqcfg->priv = !!(wq->type == IDXD_WQT_KERNEL);
-	wq->wqcfg->mode = 1;
+	if (wq_dedicated(wq))
+		wq->wqcfg->mode = 1;
+
+	if (device_pasid_enabled(idxd)) {
+		wq->wqcfg->pasid_en = 1;
+		if (wq->type == IDXD_WQT_KERNEL && wq_dedicated(wq))
+			wq->wqcfg->pasid = idxd->pasid;
+	}
+
 	wq->wqcfg->priority = wq->priority;
 
+	if (idxd->hw.gen_cap.block_on_fault &&
+	    test_bit(WQ_FLAG_BLOCK_ON_FAULT, &wq->flags))
+		wq->wqcfg->bof = 1;
+
+	if (idxd->hw.wq_cap.wq_ats_support)
+		wq->wqcfg->wq_ats_disable = wq->ats_dis;
+
 	/* bytes 12-15 */
 	wq->wqcfg->max_xfer_shift = ilog2(wq->max_xfer_bytes);
 	wq->wqcfg->max_batch_shift = ilog2(wq->max_batch_size);
@@ -664,8 +761,8 @@ static int idxd_wqs_setup(struct idxd_device *idxd)
 		if (!wq->size)
 			continue;
 
-		if (!wq_dedicated(wq)) {
-			dev_warn(dev, "No shared workqueue support.\n");
+		if (wq_shared(wq) && !device_swq_supported(idxd)) {
+			dev_warn(dev, "No shared wq support but configured.\n");
 			return -EINVAL;
 		}
 
diff --git a/drivers/dma/idxd/dma.c b/drivers/dma/idxd/dma.c
index 0c892cbd72e0..8ed2773d8285 100644
--- a/drivers/dma/idxd/dma.c
+++ b/drivers/dma/idxd/dma.c
@@ -61,8 +61,6 @@ static inline void idxd_prep_desc_common(struct idxd_wq *wq,
 					 u64 addr_f1, u64 addr_f2, u64 len,
 					 u64 compl, u32 flags)
 {
-	struct idxd_device *idxd = wq->idxd;
-
 	hw->flags = flags;
 	hw->opcode = opcode;
 	hw->src_addr = addr_f1;
@@ -70,13 +68,6 @@ static inline void idxd_prep_desc_common(struct idxd_wq *wq,
 	hw->xfer_size = len;
 	hw->priv = !!(wq->type == IDXD_WQT_KERNEL);
 	hw->completion_addr = compl;
-
-	/*
-	 * Descriptor completion vectors are 1-8 for MSIX. We will round
-	 * robin through the 8 vectors.
-	 */
-	wq->vec_ptr = (wq->vec_ptr % idxd->num_wq_irqs) + 1;
-	hw->int_handle =  wq->vec_ptr;
 }
 
 static struct dma_async_tx_descriptor *
diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h
index d48f193daacc..5a50e91c71bf 100644
--- a/drivers/dma/idxd/idxd.h
+++ b/drivers/dma/idxd/idxd.h
@@ -20,7 +20,8 @@ extern struct kmem_cache *idxd_desc_pool;
 enum idxd_type {
 	IDXD_TYPE_UNKNOWN = -1,
 	IDXD_TYPE_DSA = 0,
-	IDXD_TYPE_MAX
+	IDXD_TYPE_IAX,
+	IDXD_TYPE_MAX,
 };
 
 #define IDXD_NAME_SIZE		128
@@ -34,6 +35,11 @@ struct idxd_irq_entry {
 	int id;
 	struct llist_head pending_llist;
 	struct list_head work_list;
+	/*
+	 * Lock to protect access between irq thread process descriptor
+	 * and irq thread processing error descriptor.
+	 */
+	spinlock_t list_lock;
 };
 
 struct idxd_group {
@@ -59,6 +65,7 @@ enum idxd_wq_state {
 
 enum idxd_wq_flag {
 	WQ_FLAG_DEDICATED = 0,
+	WQ_FLAG_BLOCK_ON_FAULT,
 };
 
 enum idxd_wq_type {
@@ -86,10 +93,11 @@ enum idxd_op_type {
 enum idxd_complete_type {
 	IDXD_COMPLETE_NORMAL = 0,
 	IDXD_COMPLETE_ABORT,
+	IDXD_COMPLETE_DEV_FAIL,
 };
 
 struct idxd_wq {
-	void __iomem *dportal;
+	void __iomem *portal;
 	struct device conf_dev;
 	struct idxd_cdev idxd_cdev;
 	struct idxd_device *idxd;
@@ -107,8 +115,13 @@ struct idxd_wq {
 	u32 vec_ptr;		/* interrupt steering */
 	struct dsa_hw_desc **hw_descs;
 	int num_descs;
-	struct dsa_completion_record *compls;
+	union {
+		struct dsa_completion_record *compls;
+		struct iax_completion_record *iax_compls;
+	};
+	void *compls_raw;
 	dma_addr_t compls_addr;
+	dma_addr_t compls_addr_raw;
 	int compls_size;
 	struct idxd_desc **descs;
 	struct sbitmap_queue sbq;
@@ -116,6 +129,7 @@ struct idxd_wq {
 	char name[WQ_NAME_SIZE + 1];
 	u64 max_xfer_bytes;
 	u32 max_batch_size;
+	bool ats_dis;
 };
 
 struct idxd_engine {
@@ -145,6 +159,7 @@ enum idxd_device_state {
 enum idxd_device_flag {
 	IDXD_FLAG_CONFIGURABLE = 0,
 	IDXD_FLAG_CMD_RUNNING,
+	IDXD_FLAG_PASID_ENABLED,
 };
 
 struct idxd_device {
@@ -167,6 +182,9 @@ struct idxd_device {
 	struct idxd_wq *wqs;
 	struct idxd_engine *engines;
 
+	struct iommu_sva *sva;
+	unsigned int pasid;
+
 	int num_groups;
 
 	u32 msix_perm_offset;
@@ -184,6 +202,7 @@ struct idxd_device {
 	int token_limit;
 	int nr_tokens;		/* non-reserved tokens */
 	unsigned int wqcfg_size;
+	int compl_size;
 
 	union sw_err_reg sw_err;
 	wait_queue_head_t cmd_waitq;
@@ -198,9 +217,15 @@ struct idxd_device {
 
 /* IDXD software descriptor */
 struct idxd_desc {
-	struct dsa_hw_desc *hw;
+	union {
+		struct dsa_hw_desc *hw;
+		struct iax_hw_desc *iax_hw;
+	};
 	dma_addr_t desc_dma;
-	struct dsa_completion_record *completion;
+	union {
+		struct dsa_completion_record *completion;
+		struct iax_completion_record *iax_completion;
+	};
 	dma_addr_t compl_dma;
 	struct dma_async_tx_descriptor txd;
 	struct llist_node llnode;
@@ -214,12 +239,30 @@ struct idxd_desc {
 #define confdev_to_wq(dev) container_of(dev, struct idxd_wq, conf_dev)
 
 extern struct bus_type dsa_bus_type;
+extern struct bus_type iax_bus_type;
+
+extern bool support_enqcmd;
 
 static inline bool wq_dedicated(struct idxd_wq *wq)
 {
 	return test_bit(WQ_FLAG_DEDICATED, &wq->flags);
 }
 
+static inline bool wq_shared(struct idxd_wq *wq)
+{
+	return !test_bit(WQ_FLAG_DEDICATED, &wq->flags);
+}
+
+static inline bool device_pasid_enabled(struct idxd_device *idxd)
+{
+	return test_bit(IDXD_FLAG_PASID_ENABLED, &idxd->flags);
+}
+
+static inline bool device_swq_supported(struct idxd_device *idxd)
+{
+	return (support_enqcmd && device_pasid_enabled(idxd));
+}
+
 enum idxd_portal_prot {
 	IDXD_PORTAL_UNLIMITED = 0,
 	IDXD_PORTAL_LIMITED,
@@ -242,6 +285,8 @@ static inline void idxd_set_type(struct idxd_device *idxd)
 
 	if (pdev->device == PCI_DEVICE_ID_INTEL_DSA_SPR0)
 		idxd->type = IDXD_TYPE_DSA;
+	else if (pdev->device == PCI_DEVICE_ID_INTEL_IAX_SPR0)
+		idxd->type = IDXD_TYPE_IAX;
 	else
 		idxd->type = IDXD_TYPE_UNKNOWN;
 }
@@ -288,6 +333,7 @@ void idxd_device_reset(struct idxd_device *idxd);
 void idxd_device_cleanup(struct idxd_device *idxd);
 int idxd_device_config(struct idxd_device *idxd);
 void idxd_device_wqs_clear_state(struct idxd_device *idxd);
+void idxd_device_drain_pasid(struct idxd_device *idxd, int pasid);
 
 /* work queue control */
 int idxd_wq_alloc_resources(struct idxd_wq *wq);
@@ -298,6 +344,8 @@ void idxd_wq_drain(struct idxd_wq *wq);
 int idxd_wq_map_portal(struct idxd_wq *wq);
 void idxd_wq_unmap_portal(struct idxd_wq *wq);
 void idxd_wq_disable_cleanup(struct idxd_wq *wq);
+int idxd_wq_set_pasid(struct idxd_wq *wq, int pasid);
+int idxd_wq_disable_pasid(struct idxd_wq *wq);
 
 /* submission */
 int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc);
diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c
index 0a4432b063b5..2c051e07c34c 100644
--- a/drivers/dma/idxd/init.c
+++ b/drivers/dma/idxd/init.c
@@ -14,6 +14,8 @@
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include <linux/device.h>
 #include <linux/idr.h>
+#include <linux/intel-svm.h>
+#include <linux/iommu.h>
 #include <uapi/linux/idxd.h>
 #include <linux/dmaengine.h>
 #include "../dmaengine.h"
@@ -26,18 +28,24 @@ MODULE_AUTHOR("Intel Corporation");
 
 #define DRV_NAME "idxd"
 
+bool support_enqcmd;
+
 static struct idr idxd_idrs[IDXD_TYPE_MAX];
 static struct mutex idxd_idr_lock;
 
 static struct pci_device_id idxd_pci_tbl[] = {
 	/* DSA ver 1.0 platforms */
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_DSA_SPR0) },
+
+	/* IAX ver 1.0 platforms */
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IAX_SPR0) },
 	{ 0, }
 };
 MODULE_DEVICE_TABLE(pci, idxd_pci_tbl);
 
 static char *idxd_name[] = {
 	"dsa",
+	"iax"
 };
 
 const char *idxd_get_dev_name(struct idxd_device *idxd)
@@ -53,6 +61,7 @@ static int idxd_setup_interrupts(struct idxd_device *idxd)
 	struct idxd_irq_entry *irq_entry;
 	int i, msixcnt;
 	int rc = 0;
+	union msix_perm mperm;
 
 	msixcnt = pci_msix_vec_count(pdev);
 	if (msixcnt < 0) {
@@ -92,6 +101,7 @@ static int idxd_setup_interrupts(struct idxd_device *idxd)
 	for (i = 0; i < msixcnt; i++) {
 		idxd->irq_entries[i].id = i;
 		idxd->irq_entries[i].idxd = idxd;
+		spin_lock_init(&idxd->irq_entries[i].list_lock);
 	}
 
 	msix = &idxd->msix_entries[0];
@@ -131,6 +141,13 @@ static int idxd_setup_interrupts(struct idxd_device *idxd)
 
 	idxd_unmask_error_interrupts(idxd);
 
+	/* Setup MSIX permission table */
+	mperm.bits = 0;
+	mperm.pasid = idxd->pasid;
+	mperm.pasid_en = device_pasid_enabled(idxd);
+	for (i = 1; i < msixcnt; i++)
+		iowrite32(mperm.bits, idxd->reg_base + idxd->msix_perm_offset + i * 8);
+
 	return 0;
 
  err_no_irq:
@@ -201,17 +218,14 @@ static void idxd_read_table_offsets(struct idxd_device *idxd)
 	struct device *dev = &idxd->pdev->dev;
 
 	offsets.bits[0] = ioread64(idxd->reg_base + IDXD_TABLE_OFFSET);
-	offsets.bits[1] = ioread64(idxd->reg_base + IDXD_TABLE_OFFSET
-			+ sizeof(u64));
-	idxd->grpcfg_offset = offsets.grpcfg * 0x100;
+	offsets.bits[1] = ioread64(idxd->reg_base + IDXD_TABLE_OFFSET + sizeof(u64));
+	idxd->grpcfg_offset = offsets.grpcfg * IDXD_TABLE_MULT;
 	dev_dbg(dev, "IDXD Group Config Offset: %#x\n", idxd->grpcfg_offset);
-	idxd->wqcfg_offset = offsets.wqcfg * 0x100;
-	dev_dbg(dev, "IDXD Work Queue Config Offset: %#x\n",
-		idxd->wqcfg_offset);
-	idxd->msix_perm_offset = offsets.msix_perm * 0x100;
-	dev_dbg(dev, "IDXD MSIX Permission Offset: %#x\n",
-		idxd->msix_perm_offset);
-	idxd->perfmon_offset = offsets.perfmon * 0x100;
+	idxd->wqcfg_offset = offsets.wqcfg * IDXD_TABLE_MULT;
+	dev_dbg(dev, "IDXD Work Queue Config Offset: %#x\n", idxd->wqcfg_offset);
+	idxd->msix_perm_offset = offsets.msix_perm * IDXD_TABLE_MULT;
+	dev_dbg(dev, "IDXD MSIX Permission Offset: %#x\n", idxd->msix_perm_offset);
+	idxd->perfmon_offset = offsets.perfmon * IDXD_TABLE_MULT;
 	dev_dbg(dev, "IDXD Perfmon Offset: %#x\n", idxd->perfmon_offset);
 }
 
@@ -265,8 +279,7 @@ static void idxd_read_caps(struct idxd_device *idxd)
 	}
 }
 
-static struct idxd_device *idxd_alloc(struct pci_dev *pdev,
-				      void __iomem * const *iomap)
+static struct idxd_device *idxd_alloc(struct pci_dev *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct idxd_device *idxd;
@@ -276,12 +289,45 @@ static struct idxd_device *idxd_alloc(struct pci_dev *pdev,
 		return NULL;
 
 	idxd->pdev = pdev;
-	idxd->reg_base = iomap[IDXD_MMIO_BAR];
 	spin_lock_init(&idxd->dev_lock);
 
 	return idxd;
 }
 
+static int idxd_enable_system_pasid(struct idxd_device *idxd)
+{
+	int flags;
+	unsigned int pasid;
+	struct iommu_sva *sva;
+
+	flags = SVM_FLAG_SUPERVISOR_MODE;
+
+	sva = iommu_sva_bind_device(&idxd->pdev->dev, NULL, &flags);
+	if (IS_ERR(sva)) {
+		dev_warn(&idxd->pdev->dev,
+			 "iommu sva bind failed: %ld\n", PTR_ERR(sva));
+		return PTR_ERR(sva);
+	}
+
+	pasid = iommu_sva_get_pasid(sva);
+	if (pasid == IOMMU_PASID_INVALID) {
+		iommu_sva_unbind_device(sva);
+		return -ENODEV;
+	}
+
+	idxd->sva = sva;
+	idxd->pasid = pasid;
+	dev_dbg(&idxd->pdev->dev, "system pasid: %u\n", pasid);
+	return 0;
+}
+
+static void idxd_disable_system_pasid(struct idxd_device *idxd)
+{
+
+	iommu_sva_unbind_device(idxd->sva);
+	idxd->sva = NULL;
+}
+
 static int idxd_probe(struct idxd_device *idxd)
 {
 	struct pci_dev *pdev = idxd->pdev;
@@ -292,6 +338,14 @@ static int idxd_probe(struct idxd_device *idxd)
 	idxd_device_init_reset(idxd);
 	dev_dbg(dev, "IDXD reset complete\n");
 
+	if (IS_ENABLED(CONFIG_INTEL_IDXD_SVM)) {
+		rc = idxd_enable_system_pasid(idxd);
+		if (rc < 0)
+			dev_warn(dev, "Failed to enable PASID. No SVA support: %d\n", rc);
+		else
+			set_bit(IDXD_FLAG_PASID_ENABLED, &idxd->flags);
+	}
+
 	idxd_read_caps(idxd);
 	idxd_read_table_offsets(idxd);
 
@@ -322,29 +376,37 @@ static int idxd_probe(struct idxd_device *idxd)
 	idxd_mask_error_interrupts(idxd);
 	idxd_mask_msix_vectors(idxd);
  err_setup:
+	if (device_pasid_enabled(idxd))
+		idxd_disable_system_pasid(idxd);
 	return rc;
 }
 
+static void idxd_type_init(struct idxd_device *idxd)
+{
+	if (idxd->type == IDXD_TYPE_DSA)
+		idxd->compl_size = sizeof(struct dsa_completion_record);
+	else if (idxd->type == IDXD_TYPE_IAX)
+		idxd->compl_size = sizeof(struct iax_completion_record);
+}
+
 static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
-	void __iomem * const *iomap;
 	struct device *dev = &pdev->dev;
 	struct idxd_device *idxd;
 	int rc;
-	unsigned int mask;
 
 	rc = pcim_enable_device(pdev);
 	if (rc)
 		return rc;
 
-	dev_dbg(dev, "Mapping BARs\n");
-	mask = (1 << IDXD_MMIO_BAR);
-	rc = pcim_iomap_regions(pdev, mask, DRV_NAME);
-	if (rc)
-		return rc;
+	dev_dbg(dev, "Alloc IDXD context\n");
+	idxd = idxd_alloc(pdev);
+	if (!idxd)
+		return -ENOMEM;
 
-	iomap = pcim_iomap_table(pdev);
-	if (!iomap)
+	dev_dbg(dev, "Mapping BARs\n");
+	idxd->reg_base = pcim_iomap(pdev, IDXD_MMIO_BAR, 0);
+	if (!idxd->reg_base)
 		return -ENOMEM;
 
 	dev_dbg(dev, "Set DMA masks\n");
@@ -360,13 +422,10 @@ static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (rc)
 		return rc;
 
-	dev_dbg(dev, "Alloc IDXD context\n");
-	idxd = idxd_alloc(pdev, iomap);
-	if (!idxd)
-		return -ENOMEM;
-
 	idxd_set_type(idxd);
 
+	idxd_type_init(idxd);
+
 	dev_dbg(dev, "Set PCI master\n");
 	pci_set_master(pdev);
 	pci_set_drvdata(pdev, idxd);
@@ -452,6 +511,8 @@ static void idxd_remove(struct pci_dev *pdev)
 	dev_dbg(&pdev->dev, "%s called\n", __func__);
 	idxd_cleanup_sysfs(idxd);
 	idxd_shutdown(pdev);
+	if (device_pasid_enabled(idxd))
+		idxd_disable_system_pasid(idxd);
 	mutex_lock(&idxd_idr_lock);
 	idr_remove(&idxd_idrs[idxd->type], idxd->id);
 	mutex_unlock(&idxd_idr_lock);
@@ -470,7 +531,7 @@ static int __init idxd_init_module(void)
 	int err, i;
 
 	/*
-	 * If the CPU does not support write512, there's no point in
+	 * If the CPU does not support MOVDIR64B or ENQCMDS, there's no point in
 	 * enumerating the device. We can not utilize it.
 	 */
 	if (!boot_cpu_has(X86_FEATURE_MOVDIR64B)) {
@@ -478,8 +539,10 @@ static int __init idxd_init_module(void)
 		return -ENODEV;
 	}
 
-	pr_info("%s: Intel(R) Accelerator Devices Driver %s\n",
-		DRV_NAME, IDXD_DRIVER_VERSION);
+	if (!boot_cpu_has(X86_FEATURE_ENQCMD))
+		pr_warn("Platform does not have ENQCMD(S) support.\n");
+	else
+		support_enqcmd = true;
 
 	mutex_init(&idxd_idr_lock);
 	for (i = 0; i < IDXD_TYPE_MAX; i++)
diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c
index 17a65a13fb64..593a2f6ed16c 100644
--- a/drivers/dma/idxd/irq.c
+++ b/drivers/dma/idxd/irq.c
@@ -11,6 +11,24 @@
 #include "idxd.h"
 #include "registers.h"
 
+enum irq_work_type {
+	IRQ_WORK_NORMAL = 0,
+	IRQ_WORK_PROCESS_FAULT,
+};
+
+struct idxd_fault {
+	struct work_struct work;
+	u64 addr;
+	struct idxd_device *idxd;
+};
+
+static int irq_process_work_list(struct idxd_irq_entry *irq_entry,
+				 enum irq_work_type wtype,
+				 int *processed, u64 data);
+static int irq_process_pending_llist(struct idxd_irq_entry *irq_entry,
+				     enum irq_work_type wtype,
+				     int *processed, u64 data);
+
 static void idxd_device_reinit(struct work_struct *work)
 {
 	struct idxd_device *idxd = container_of(work, struct idxd_device, work);
@@ -44,6 +62,46 @@ static void idxd_device_reinit(struct work_struct *work)
 	idxd_device_wqs_clear_state(idxd);
 }
 
+static void idxd_device_fault_work(struct work_struct *work)
+{
+	struct idxd_fault *fault = container_of(work, struct idxd_fault, work);
+	struct idxd_irq_entry *ie;
+	int i;
+	int processed;
+	int irqcnt = fault->idxd->num_wq_irqs + 1;
+
+	for (i = 1; i < irqcnt; i++) {
+		ie = &fault->idxd->irq_entries[i];
+		irq_process_work_list(ie, IRQ_WORK_PROCESS_FAULT,
+				      &processed, fault->addr);
+		if (processed)
+			break;
+
+		irq_process_pending_llist(ie, IRQ_WORK_PROCESS_FAULT,
+					  &processed, fault->addr);
+		if (processed)
+			break;
+	}
+
+	kfree(fault);
+}
+
+static int idxd_device_schedule_fault_process(struct idxd_device *idxd,
+					      u64 fault_addr)
+{
+	struct idxd_fault *fault;
+
+	fault = kmalloc(sizeof(*fault), GFP_ATOMIC);
+	if (!fault)
+		return -ENOMEM;
+
+	fault->addr = fault_addr;
+	fault->idxd = idxd;
+	INIT_WORK(&fault->work, idxd_device_fault_work);
+	queue_work(idxd->wq, &fault->work);
+	return 0;
+}
+
 irqreturn_t idxd_irq_handler(int vec, void *data)
 {
 	struct idxd_irq_entry *irq_entry = data;
@@ -125,6 +183,15 @@ irqreturn_t idxd_misc_thread(int vec, void *data)
 	if (!err)
 		goto out;
 
+	/*
+	 * This case should rarely happen and typically is due to software
+	 * programming error by the driver.
+	 */
+	if (idxd->sw_err.valid &&
+	    idxd->sw_err.desc_valid &&
+	    idxd->sw_err.fault_addr)
+		idxd_device_schedule_fault_process(idxd, idxd->sw_err.fault_addr);
+
 	gensts.bits = ioread32(idxd->reg_base + IDXD_GENSTATS_OFFSET);
 	if (gensts.state == IDXD_DEVICE_STATE_HALT) {
 		idxd->state = IDXD_DEV_HALTED;
@@ -152,57 +219,110 @@ irqreturn_t idxd_misc_thread(int vec, void *data)
 	return IRQ_HANDLED;
 }
 
+static bool process_fault(struct idxd_desc *desc, u64 fault_addr)
+{
+	/*
+	 * Completion address can be bad as well. Check fault address match for descriptor
+	 * and completion address.
+	 */
+	if ((u64)desc->hw == fault_addr ||
+	    (u64)desc->completion == fault_addr) {
+		idxd_dma_complete_txd(desc, IDXD_COMPLETE_DEV_FAIL);
+		return true;
+	}
+
+	return false;
+}
+
+static bool complete_desc(struct idxd_desc *desc)
+{
+	if (desc->completion->status) {
+		idxd_dma_complete_txd(desc, IDXD_COMPLETE_NORMAL);
+		return true;
+	}
+
+	return false;
+}
+
 static int irq_process_pending_llist(struct idxd_irq_entry *irq_entry,
-				     int *processed)
+				     enum irq_work_type wtype,
+				     int *processed, u64 data)
 {
 	struct idxd_desc *desc, *t;
 	struct llist_node *head;
 	int queued = 0;
+	bool completed = false;
+	unsigned long flags;
 
 	*processed = 0;
 	head = llist_del_all(&irq_entry->pending_llist);
 	if (!head)
-		return 0;
+		goto out;
 
 	llist_for_each_entry_safe(desc, t, head, llnode) {
-		if (desc->completion->status) {
-			idxd_dma_complete_txd(desc, IDXD_COMPLETE_NORMAL);
+		if (wtype == IRQ_WORK_NORMAL)
+			completed = complete_desc(desc);
+		else if (wtype == IRQ_WORK_PROCESS_FAULT)
+			completed = process_fault(desc, data);
+
+		if (completed) {
 			idxd_free_desc(desc->wq, desc);
 			(*processed)++;
+			if (wtype == IRQ_WORK_PROCESS_FAULT)
+				break;
 		} else {
-			list_add_tail(&desc->list, &irq_entry->work_list);
+			spin_lock_irqsave(&irq_entry->list_lock, flags);
+			list_add_tail(&desc->list,
+				      &irq_entry->work_list);
+			spin_unlock_irqrestore(&irq_entry->list_lock, flags);
 			queued++;
 		}
 	}
 
+ out:
 	return queued;
 }
 
 static int irq_process_work_list(struct idxd_irq_entry *irq_entry,
-				 int *processed)
+				 enum irq_work_type wtype,
+				 int *processed, u64 data)
 {
 	struct list_head *node, *next;
 	int queued = 0;
+	bool completed = false;
+	unsigned long flags;
 
 	*processed = 0;
+	spin_lock_irqsave(&irq_entry->list_lock, flags);
 	if (list_empty(&irq_entry->work_list))
-		return 0;
+		goto out;
 
 	list_for_each_safe(node, next, &irq_entry->work_list) {
 		struct idxd_desc *desc =
 			container_of(node, struct idxd_desc, list);
 
-		if (desc->completion->status) {
+		spin_unlock_irqrestore(&irq_entry->list_lock, flags);
+		if (wtype == IRQ_WORK_NORMAL)
+			completed = complete_desc(desc);
+		else if (wtype == IRQ_WORK_PROCESS_FAULT)
+			completed = process_fault(desc, data);
+
+		if (completed) {
+			spin_lock_irqsave(&irq_entry->list_lock, flags);
 			list_del(&desc->list);
-			/* process and callback */
-			idxd_dma_complete_txd(desc, IDXD_COMPLETE_NORMAL);
+			spin_unlock_irqrestore(&irq_entry->list_lock, flags);
 			idxd_free_desc(desc->wq, desc);
 			(*processed)++;
+			if (wtype == IRQ_WORK_PROCESS_FAULT)
+				return queued;
 		} else {
 			queued++;
 		}
+		spin_lock_irqsave(&irq_entry->list_lock, flags);
 	}
 
+ out:
+	spin_unlock_irqrestore(&irq_entry->list_lock, flags);
 	return queued;
 }
 
@@ -230,12 +350,14 @@ static int idxd_desc_process(struct idxd_irq_entry *irq_entry)
 	 * 5. Repeat until no more descriptors.
 	 */
 	do {
-		rc = irq_process_work_list(irq_entry, &processed);
+		rc = irq_process_work_list(irq_entry, IRQ_WORK_NORMAL,
+					   &processed, 0);
 		total += processed;
 		if (rc != 0)
 			continue;
 
-		rc = irq_process_pending_llist(irq_entry, &processed);
+		rc = irq_process_pending_llist(irq_entry, IRQ_WORK_NORMAL,
+					       &processed, 0);
 		total += processed;
 	} while (rc != 0);
 
diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h
index 54390334c243..751ecb4f9f81 100644
--- a/drivers/dma/idxd/registers.h
+++ b/drivers/dma/idxd/registers.h
@@ -5,6 +5,7 @@
 
 /* PCI Config */
 #define PCI_DEVICE_ID_INTEL_DSA_SPR0	0x0b25
+#define PCI_DEVICE_ID_INTEL_IAX_SPR0	0x0cfe
 
 #define IDXD_MMIO_BAR		0
 #define IDXD_WQ_BAR		2
@@ -47,7 +48,7 @@ union wq_cap_reg {
 		u64 rsvd:20;
 		u64 shared_mode:1;
 		u64 dedicated_mode:1;
-		u64 rsvd2:1;
+		u64 wq_ats_support:1;
 		u64 priority:1;
 		u64 occupancy:1;
 		u64 occupancy_int:1;
@@ -102,6 +103,8 @@ union offsets_reg {
 	u64 bits[2];
 } __packed;
 
+#define IDXD_TABLE_MULT			0x100
+
 #define IDXD_GENCFG_OFFSET		0x80
 union gencfg_reg {
 	struct {
@@ -301,7 +304,8 @@ union wqcfg {
 		/* bytes 8-11 */
 		u32 mode:1;	/* shared or dedicated */
 		u32 bof:1;	/* block on fault */
-		u32 rsvd2:2;
+		u32 wq_ats_disable:1;
+		u32 rsvd2:1;
 		u32 priority:4;
 		u32 pasid:20;
 		u32 pasid_en:1;
@@ -336,6 +340,8 @@ union wqcfg {
 	u32 bits[8];
 } __packed;
 
+#define WQCFG_PASID_IDX                2
+
 /*
  * This macro calculates the offset into the WQCFG register
  * idxd - struct idxd *
@@ -354,4 +360,22 @@ union wqcfg {
 
 #define WQCFG_STRIDES(_idxd_dev) ((_idxd_dev)->wqcfg_size / sizeof(u32))
 
+#define GRPCFG_SIZE		64
+#define GRPWQCFG_STRIDES	4
+
+/*
+ * This macro calculates the offset into the GRPCFG register
+ * idxd - struct idxd *
+ * n - wq id
+ * ofs - the index of the 32b dword for the config register
+ *
+ * The WQCFG register block is divided into groups per each wq. The n index
+ * allows us to move to the register group that's for that particular wq.
+ * Each register is 32bits. The ofs gives us the number of register to access.
+ */
+#define GRPWQCFG_OFFSET(idxd_dev, n, ofs) ((idxd_dev)->grpcfg_offset +\
+					   (n) * GRPCFG_SIZE + sizeof(u64) * (ofs))
+#define GRPENGCFG_OFFSET(idxd_dev, n) ((idxd_dev)->grpcfg_offset + (n) * GRPCFG_SIZE + 32)
+#define GRPFLGCFG_OFFSET(idxd_dev, n) ((idxd_dev)->grpcfg_offset + (n) * GRPCFG_SIZE + 40)
+
 #endif
diff --git a/drivers/dma/idxd/submit.c b/drivers/dma/idxd/submit.c
index 417048e3c42a..a7a61bcc17d5 100644
--- a/drivers/dma/idxd/submit.c
+++ b/drivers/dma/idxd/submit.c
@@ -11,11 +11,22 @@
 static struct idxd_desc *__get_desc(struct idxd_wq *wq, int idx, int cpu)
 {
 	struct idxd_desc *desc;
+	struct idxd_device *idxd = wq->idxd;
 
 	desc = wq->descs[idx];
 	memset(desc->hw, 0, sizeof(struct dsa_hw_desc));
-	memset(desc->completion, 0, sizeof(struct dsa_completion_record));
+	memset(desc->completion, 0, idxd->compl_size);
 	desc->cpu = cpu;
+
+	if (device_pasid_enabled(idxd))
+		desc->hw->pasid = idxd->pasid;
+
+	/*
+	 * Descriptor completion vectors are 1-8 for MSIX. We will round
+	 * robin through the 8 vectors.
+	 */
+	wq->vec_ptr = (wq->vec_ptr % idxd->num_wq_irqs) + 1;
+	desc->hw->int_handle = wq->vec_ptr;
 	return desc;
 }
 
@@ -70,18 +81,32 @@ int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc)
 	struct idxd_device *idxd = wq->idxd;
 	int vec = desc->hw->int_handle;
 	void __iomem *portal;
+	int rc;
 
 	if (idxd->state != IDXD_DEV_ENABLED)
 		return -EIO;
 
-	portal = wq->dportal;
+	portal = wq->portal;
+
 	/*
-	 * The wmb() flushes writes to coherent DMA data before possibly
-	 * triggering a DMA read. The wmb() is necessary even on UP because
-	 * the recipient is a device.
+	 * The wmb() flushes writes to coherent DMA data before
+	 * possibly triggering a DMA read. The wmb() is necessary
+	 * even on UP because the recipient is a device.
 	 */
 	wmb();
-	iosubmit_cmds512(portal, desc->hw, 1);
+	if (wq_dedicated(wq)) {
+		iosubmit_cmds512(portal, desc->hw, 1);
+	} else {
+		/*
+		 * It's not likely that we would receive queue full rejection
+		 * since the descriptor allocation gates at wq size. If we
+		 * receive a -EAGAIN, that means something went wrong such as the
+		 * device is not accepting descriptor at all.
+		 */
+		rc = enqcmds(portal, desc->hw);
+		if (rc < 0)
+			return rc;
+	}
 
 	/*
 	 * Pending the descriptor to the lockless list for the irq_entry
diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c
index 07a5db06a29a..266423a2cabc 100644
--- a/drivers/dma/idxd/sysfs.c
+++ b/drivers/dma/idxd/sysfs.c
@@ -41,14 +41,24 @@ static struct device_type dsa_device_type = {
 	.release = idxd_conf_device_release,
 };
 
+static struct device_type iax_device_type = {
+	.name = "iax",
+	.release = idxd_conf_device_release,
+};
+
 static inline bool is_dsa_dev(struct device *dev)
 {
 	return dev ? dev->type == &dsa_device_type : false;
 }
 
+static inline bool is_iax_dev(struct device *dev)
+{
+	return dev ? dev->type == &iax_device_type : false;
+}
+
 static inline bool is_idxd_dev(struct device *dev)
 {
-	return is_dsa_dev(dev);
+	return is_dsa_dev(dev) || is_iax_dev(dev);
 }
 
 static inline bool is_idxd_wq_dev(struct device *dev)
@@ -175,6 +185,30 @@ static int idxd_config_bus_probe(struct device *dev)
 			return -EINVAL;
 		}
 
+		/* Shared WQ checks */
+		if (wq_shared(wq)) {
+			if (!device_swq_supported(idxd)) {
+				dev_warn(dev,
+					 "PASID not enabled and shared WQ.\n");
+				mutex_unlock(&wq->wq_lock);
+				return -ENXIO;
+			}
+			/*
+			 * Shared wq with the threshold set to 0 means the user
+			 * did not set the threshold or transitioned from a
+			 * dedicated wq but did not set threshold. A value
+			 * of 0 would effectively disable the shared wq. The
+			 * driver does not allow a value of 0 to be set for
+			 * threshold via sysfs.
+			 */
+			if (wq->threshold == 0) {
+				dev_warn(dev,
+					 "Shared WQ and threshold 0.\n");
+				mutex_unlock(&wq->wq_lock);
+				return -EINVAL;
+			}
+		}
+
 		rc = idxd_wq_alloc_resources(wq);
 		if (rc < 0) {
 			mutex_unlock(&wq->wq_lock);
@@ -335,8 +369,17 @@ struct bus_type dsa_bus_type = {
 	.shutdown = idxd_config_bus_shutdown,
 };
 
+struct bus_type iax_bus_type = {
+	.name = "iax",
+	.match = idxd_config_bus_match,
+	.probe = idxd_config_bus_probe,
+	.remove = idxd_config_bus_remove,
+	.shutdown = idxd_config_bus_shutdown,
+};
+
 static struct bus_type *idxd_bus_types[] = {
-	&dsa_bus_type
+	&dsa_bus_type,
+	&iax_bus_type
 };
 
 static struct idxd_device_driver dsa_drv = {
@@ -348,8 +391,18 @@ static struct idxd_device_driver dsa_drv = {
 	},
 };
 
+static struct idxd_device_driver iax_drv = {
+	.drv = {
+		.name = "iax",
+		.bus = &iax_bus_type,
+		.owner = THIS_MODULE,
+		.mod_name = KBUILD_MODNAME,
+	},
+};
+
 static struct idxd_device_driver *idxd_drvs[] = {
-	&dsa_drv
+	&dsa_drv,
+	&iax_drv
 };
 
 struct bus_type *idxd_get_bus_type(struct idxd_device *idxd)
@@ -361,6 +414,8 @@ static struct device_type *idxd_get_device_type(struct idxd_device *idxd)
 {
 	if (idxd->type == IDXD_TYPE_DSA)
 		return &dsa_device_type;
+	else if (idxd->type == IDXD_TYPE_IAX)
+		return &iax_device_type;
 	else
 		return NULL;
 }
@@ -501,6 +556,9 @@ static ssize_t group_tokens_reserved_store(struct device *dev,
 	if (rc < 0)
 		return -EINVAL;
 
+	if (idxd->type == IDXD_TYPE_IAX)
+		return -EOPNOTSUPP;
+
 	if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
 		return -EPERM;
 
@@ -546,6 +604,9 @@ static ssize_t group_tokens_allowed_store(struct device *dev,
 	if (rc < 0)
 		return -EINVAL;
 
+	if (idxd->type == IDXD_TYPE_IAX)
+		return -EOPNOTSUPP;
+
 	if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
 		return -EPERM;
 
@@ -588,6 +649,9 @@ static ssize_t group_use_token_limit_store(struct device *dev,
 	if (rc < 0)
 		return -EINVAL;
 
+	if (idxd->type == IDXD_TYPE_IAX)
+		return -EOPNOTSUPP;
+
 	if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
 		return -EPERM;
 
@@ -875,6 +939,8 @@ static ssize_t wq_mode_store(struct device *dev,
 	if (sysfs_streq(buf, "dedicated")) {
 		set_bit(WQ_FLAG_DEDICATED, &wq->flags);
 		wq->threshold = 0;
+	} else if (sysfs_streq(buf, "shared") && device_swq_supported(idxd)) {
+		clear_bit(WQ_FLAG_DEDICATED, &wq->flags);
 	} else {
 		return -EINVAL;
 	}
@@ -973,6 +1039,87 @@ static ssize_t wq_priority_store(struct device *dev,
 static struct device_attribute dev_attr_wq_priority =
 		__ATTR(priority, 0644, wq_priority_show, wq_priority_store);
 
+static ssize_t wq_block_on_fault_show(struct device *dev,
+				      struct device_attribute *attr, char *buf)
+{
+	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
+
+	return sprintf(buf, "%u\n",
+		       test_bit(WQ_FLAG_BLOCK_ON_FAULT, &wq->flags));
+}
+
+static ssize_t wq_block_on_fault_store(struct device *dev,
+				       struct device_attribute *attr,
+				       const char *buf, size_t count)
+{
+	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
+	struct idxd_device *idxd = wq->idxd;
+	bool bof;
+	int rc;
+
+	if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
+		return -EPERM;
+
+	if (wq->state != IDXD_WQ_DISABLED)
+		return -ENXIO;
+
+	rc = kstrtobool(buf, &bof);
+	if (rc < 0)
+		return rc;
+
+	if (bof)
+		set_bit(WQ_FLAG_BLOCK_ON_FAULT, &wq->flags);
+	else
+		clear_bit(WQ_FLAG_BLOCK_ON_FAULT, &wq->flags);
+
+	return count;
+}
+
+static struct device_attribute dev_attr_wq_block_on_fault =
+		__ATTR(block_on_fault, 0644, wq_block_on_fault_show,
+		       wq_block_on_fault_store);
+
+static ssize_t wq_threshold_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
+
+	return sprintf(buf, "%u\n", wq->threshold);
+}
+
+static ssize_t wq_threshold_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t count)
+{
+	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
+	struct idxd_device *idxd = wq->idxd;
+	unsigned int val;
+	int rc;
+
+	rc = kstrtouint(buf, 0, &val);
+	if (rc < 0)
+		return -EINVAL;
+
+	if (val > wq->size || val <= 0)
+		return -EINVAL;
+
+	if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
+		return -EPERM;
+
+	if (wq->state != IDXD_WQ_DISABLED)
+		return -ENXIO;
+
+	if (test_bit(WQ_FLAG_DEDICATED, &wq->flags))
+		return -EINVAL;
+
+	wq->threshold = val;
+
+	return count;
+}
+
+static struct device_attribute dev_attr_wq_threshold =
+		__ATTR(threshold, 0644, wq_threshold_show, wq_threshold_store);
+
 static ssize_t wq_type_show(struct device *dev,
 			    struct device_attribute *attr, char *buf)
 {
@@ -1044,6 +1191,13 @@ static ssize_t wq_name_store(struct device *dev,
 	if (strlen(buf) > WQ_NAME_SIZE || strlen(buf) == 0)
 		return -EINVAL;
 
+	/*
+	 * This is temporarily placed here until we have SVM support for
+	 * dmaengine.
+	 */
+	if (wq->type == IDXD_WQT_KERNEL && device_pasid_enabled(wq->idxd))
+		return -EOPNOTSUPP;
+
 	memset(wq->name, 0, WQ_NAME_SIZE + 1);
 	strncpy(wq->name, buf, WQ_NAME_SIZE);
 	strreplace(wq->name, '\n', '\0');
@@ -1147,6 +1301,39 @@ static ssize_t wq_max_batch_size_store(struct device *dev, struct device_attribu
 static struct device_attribute dev_attr_wq_max_batch_size =
 		__ATTR(max_batch_size, 0644, wq_max_batch_size_show, wq_max_batch_size_store);
 
+static ssize_t wq_ats_disable_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
+
+	return sprintf(buf, "%u\n", wq->ats_dis);
+}
+
+static ssize_t wq_ats_disable_store(struct device *dev, struct device_attribute *attr,
+				    const char *buf, size_t count)
+{
+	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
+	struct idxd_device *idxd = wq->idxd;
+	bool ats_dis;
+	int rc;
+
+	if (wq->state != IDXD_WQ_DISABLED)
+		return -EPERM;
+
+	if (!idxd->hw.wq_cap.wq_ats_support)
+		return -EOPNOTSUPP;
+
+	rc = kstrtobool(buf, &ats_dis);
+	if (rc < 0)
+		return rc;
+
+	wq->ats_dis = ats_dis;
+
+	return count;
+}
+
+static struct device_attribute dev_attr_wq_ats_disable =
+		__ATTR(ats_disable, 0644, wq_ats_disable_show, wq_ats_disable_store);
+
 static struct attribute *idxd_wq_attributes[] = {
 	&dev_attr_wq_clients.attr,
 	&dev_attr_wq_state.attr,
@@ -1154,11 +1341,14 @@ static struct attribute *idxd_wq_attributes[] = {
 	&dev_attr_wq_mode.attr,
 	&dev_attr_wq_size.attr,
 	&dev_attr_wq_priority.attr,
+	&dev_attr_wq_block_on_fault.attr,
+	&dev_attr_wq_threshold.attr,
 	&dev_attr_wq_type.attr,
 	&dev_attr_wq_name.attr,
 	&dev_attr_wq_cdev_minor.attr,
 	&dev_attr_wq_max_transfer_size.attr,
 	&dev_attr_wq_max_batch_size.attr,
+	&dev_attr_wq_ats_disable.attr,
 	NULL,
 };
 
@@ -1305,6 +1495,16 @@ static ssize_t clients_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(clients);
 
+static ssize_t pasid_enabled_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	struct idxd_device *idxd =
+		container_of(dev, struct idxd_device, conf_dev);
+
+	return sprintf(buf, "%u\n", device_pasid_enabled(idxd));
+}
+static DEVICE_ATTR_RO(pasid_enabled);
+
 static ssize_t state_show(struct device *dev,
 			  struct device_attribute *attr, char *buf)
 {
@@ -1424,6 +1624,7 @@ static struct attribute *idxd_device_attributes[] = {
 	&dev_attr_gen_cap.attr,
 	&dev_attr_configurable.attr,
 	&dev_attr_clients.attr,
+	&dev_attr_pasid_enabled.attr,
 	&dev_attr_state.attr,
 	&dev_attr_errors.attr,
 	&dev_attr_max_tokens.attr,
diff --git a/drivers/dma/imx-dma.c b/drivers/dma/imx-dma.c
index 670db04b0757..7f116bbcfad2 100644
--- a/drivers/dma/imx-dma.c
+++ b/drivers/dma/imx-dma.c
@@ -191,32 +191,13 @@ struct imxdma_filter_data {
 	int			 request;
 };
 
-static const struct platform_device_id imx_dma_devtype[] = {
-	{
-		.name = "imx1-dma",
-		.driver_data = IMX1_DMA,
-	}, {
-		.name = "imx21-dma",
-		.driver_data = IMX21_DMA,
-	}, {
-		.name = "imx27-dma",
-		.driver_data = IMX27_DMA,
-	}, {
-		/* sentinel */
-	}
-};
-MODULE_DEVICE_TABLE(platform, imx_dma_devtype);
-
 static const struct of_device_id imx_dma_of_dev_id[] = {
 	{
-		.compatible = "fsl,imx1-dma",
-		.data = &imx_dma_devtype[IMX1_DMA],
+		.compatible = "fsl,imx1-dma", .data = (const void *)IMX1_DMA,
 	}, {
-		.compatible = "fsl,imx21-dma",
-		.data = &imx_dma_devtype[IMX21_DMA],
+		.compatible = "fsl,imx21-dma", .data = (const void *)IMX21_DMA,
 	}, {
-		.compatible = "fsl,imx27-dma",
-		.data = &imx_dma_devtype[IMX27_DMA],
+		.compatible = "fsl,imx27-dma", .data = (const void *)IMX27_DMA,
 	}, {
 		/* sentinel */
 	}
@@ -1056,20 +1037,15 @@ static int __init imxdma_probe(struct platform_device *pdev)
 {
 	struct imxdma_engine *imxdma;
 	struct resource *res;
-	const struct of_device_id *of_id;
 	int ret, i;
 	int irq, irq_err;
 
-	of_id = of_match_device(imx_dma_of_dev_id, &pdev->dev);
-	if (of_id)
-		pdev->id_entry = of_id->data;
-
 	imxdma = devm_kzalloc(&pdev->dev, sizeof(*imxdma), GFP_KERNEL);
 	if (!imxdma)
 		return -ENOMEM;
 
 	imxdma->dev = &pdev->dev;
-	imxdma->devtype = pdev->id_entry->driver_data;
+	imxdma->devtype = (enum imx_dma_type)of_device_get_match_data(&pdev->dev);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	imxdma->base = devm_ioremap_resource(&pdev->dev, res);
@@ -1263,7 +1239,6 @@ static struct platform_driver imxdma_driver = {
 		.name	= "imx-dma",
 		.of_match_table = imx_dma_of_dev_id,
 	},
-	.id_table	= imx_dma_devtype,
 	.remove		= imxdma_remove,
 };
 
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index 16b908c77db3..41ba21eea7c8 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -566,37 +566,6 @@ static struct sdma_driver_data sdma_imx8mq = {
 	.check_ratio = 1,
 };
 
-static const struct platform_device_id sdma_devtypes[] = {
-	{
-		.name = "imx25-sdma",
-		.driver_data = (unsigned long)&sdma_imx25,
-	}, {
-		.name = "imx31-sdma",
-		.driver_data = (unsigned long)&sdma_imx31,
-	}, {
-		.name = "imx35-sdma",
-		.driver_data = (unsigned long)&sdma_imx35,
-	}, {
-		.name = "imx51-sdma",
-		.driver_data = (unsigned long)&sdma_imx51,
-	}, {
-		.name = "imx53-sdma",
-		.driver_data = (unsigned long)&sdma_imx53,
-	}, {
-		.name = "imx6q-sdma",
-		.driver_data = (unsigned long)&sdma_imx6q,
-	}, {
-		.name = "imx7d-sdma",
-		.driver_data = (unsigned long)&sdma_imx7d,
-	}, {
-		.name = "imx8mq-sdma",
-		.driver_data = (unsigned long)&sdma_imx8mq,
-	}, {
-		/* sentinel */
-	}
-};
-MODULE_DEVICE_TABLE(platform, sdma_devtypes);
-
 static const struct of_device_id sdma_dt_ids[] = {
 	{ .compatible = "fsl,imx6q-sdma", .data = &sdma_imx6q, },
 	{ .compatible = "fsl,imx53-sdma", .data = &sdma_imx53, },
@@ -1998,11 +1967,7 @@ static int sdma_probe(struct platform_device *pdev)
 	s32 *saddr_arr;
 	const struct sdma_driver_data *drvdata = NULL;
 
-	if (of_id)
-		drvdata = of_id->data;
-	else if (pdev->id_entry)
-		drvdata = (void *)pdev->id_entry->driver_data;
-
+	drvdata = of_id->data;
 	if (!drvdata) {
 		dev_err(&pdev->dev, "unable to find driver data\n");
 		return -EINVAL;
@@ -2211,7 +2176,6 @@ static struct platform_driver sdma_driver = {
 		.name	= "imx-sdma",
 		.of_match_table = sdma_dt_ids,
 	},
-	.id_table	= sdma_devtypes,
 	.remove		= sdma_remove,
 	.probe		= sdma_probe,
 };
diff --git a/drivers/dma/ipu/ipu_idmac.c b/drivers/dma/ipu/ipu_idmac.c
index 38036db284cb..104ad420abbe 100644
--- a/drivers/dma/ipu/ipu_idmac.c
+++ b/drivers/dma/ipu/ipu_idmac.c
@@ -1160,14 +1160,13 @@ static irqreturn_t idmac_interrupt(int irq, void *dev_id)
 	struct idmac_tx_desc *desc, *descnew;
 	bool done = false;
 	u32 ready0, ready1, curbuf, err;
-	unsigned long flags;
 	struct dmaengine_desc_callback cb;
 
 	/* IDMAC has cleared the respective BUFx_RDY bit, we manage the buffer */
 
 	dev_dbg(dev, "IDMAC irq %d, buf %d\n", irq, ichan->active_buffer);
 
-	spin_lock_irqsave(&ipu_data.lock, flags);
+	spin_lock(&ipu_data.lock);
 
 	ready0	= idmac_read_ipureg(&ipu_data, IPU_CHA_BUF0_RDY);
 	ready1	= idmac_read_ipureg(&ipu_data, IPU_CHA_BUF1_RDY);
@@ -1176,7 +1175,7 @@ static irqreturn_t idmac_interrupt(int irq, void *dev_id)
 
 	if (err & (1 << chan_id)) {
 		idmac_write_ipureg(&ipu_data, 1 << chan_id, IPU_INT_STAT_4);
-		spin_unlock_irqrestore(&ipu_data.lock, flags);
+		spin_unlock(&ipu_data.lock);
 		/*
 		 * Doing this
 		 * ichan->sg[0] = ichan->sg[1] = NULL;
@@ -1188,7 +1187,7 @@ static irqreturn_t idmac_interrupt(int irq, void *dev_id)
 			 chan_id, ready0, ready1, curbuf);
 		return IRQ_HANDLED;
 	}
-	spin_unlock_irqrestore(&ipu_data.lock, flags);
+	spin_unlock(&ipu_data.lock);
 
 	/* Other interrupts do not interfere with this channel */
 	spin_lock(&ichan->lock);
@@ -1251,9 +1250,9 @@ static irqreturn_t idmac_interrupt(int irq, void *dev_id)
 		if (unlikely(sgnew)) {
 			ipu_submit_buffer(ichan, descnew, sgnew, !ichan->active_buffer);
 		} else {
-			spin_lock_irqsave(&ipu_data.lock, flags);
+			spin_lock(&ipu_data.lock);
 			ipu_ic_disable_task(&ipu_data, chan_id);
-			spin_unlock_irqrestore(&ipu_data.lock, flags);
+			spin_unlock(&ipu_data.lock);
 			ichan->status = IPU_CHANNEL_READY;
 			/* Continue to check for complete descriptor */
 		}
diff --git a/drivers/dma/k3dma.c b/drivers/dma/k3dma.c
index f609a84c493c..d0b2e601e3e5 100644
--- a/drivers/dma/k3dma.c
+++ b/drivers/dma/k3dma.c
@@ -223,24 +223,23 @@ static irqreturn_t k3_dma_int_handler(int irq, void *dev_id)
 		i = __ffs(stat);
 		stat &= ~BIT(i);
 		if (likely(tc1 & BIT(i)) || (tc2 & BIT(i))) {
-			unsigned long flags;
 
 			p = &d->phy[i];
 			c = p->vchan;
 			if (c && (tc1 & BIT(i))) {
-				spin_lock_irqsave(&c->vc.lock, flags);
+				spin_lock(&c->vc.lock);
 				if (p->ds_run != NULL) {
 					vchan_cookie_complete(&p->ds_run->vd);
 					p->ds_done = p->ds_run;
 					p->ds_run = NULL;
 				}
-				spin_unlock_irqrestore(&c->vc.lock, flags);
+				spin_unlock(&c->vc.lock);
 			}
 			if (c && (tc2 & BIT(i))) {
-				spin_lock_irqsave(&c->vc.lock, flags);
+				spin_lock(&c->vc.lock);
 				if (p->ds_run != NULL)
 					vchan_cyclic_callback(&p->ds_run->vd);
-				spin_unlock_irqrestore(&c->vc.lock, flags);
+				spin_unlock(&c->vc.lock);
 			}
 			irq_chan |= BIT(i);
 		}
diff --git a/drivers/dma/milbeaut-xdmac.c b/drivers/dma/milbeaut-xdmac.c
index 85a597228fb0..584c931e807a 100644
--- a/drivers/dma/milbeaut-xdmac.c
+++ b/drivers/dma/milbeaut-xdmac.c
@@ -160,10 +160,9 @@ static irqreturn_t milbeaut_xdmac_interrupt(int irq, void *dev_id)
 {
 	struct milbeaut_xdmac_chan *mc = dev_id;
 	struct milbeaut_xdmac_desc *md;
-	unsigned long flags;
 	u32 val;
 
-	spin_lock_irqsave(&mc->vc.lock, flags);
+	spin_lock(&mc->vc.lock);
 
 	/* Ack and Stop */
 	val = FIELD_PREP(M10V_XDDSD_IS_MASK, 0x0);
@@ -177,7 +176,7 @@ static irqreturn_t milbeaut_xdmac_interrupt(int irq, void *dev_id)
 
 	milbeaut_xdmac_start(mc);
 out:
-	spin_unlock_irqrestore(&mc->vc.lock, flags);
+	spin_unlock(&mc->vc.lock);
 	return IRQ_HANDLED;
 }
 
diff --git a/drivers/dma/moxart-dma.c b/drivers/dma/moxart-dma.c
index 347146a6e1d0..74755093e14b 100644
--- a/drivers/dma/moxart-dma.c
+++ b/drivers/dma/moxart-dma.c
@@ -524,7 +524,6 @@ static irqreturn_t moxart_dma_interrupt(int irq, void *devid)
 	struct moxart_dmadev *mc = devid;
 	struct moxart_chan *ch = &mc->slave_chans[0];
 	unsigned int i;
-	unsigned long flags;
 	u32 ctrl;
 
 	dev_dbg(chan2dev(&ch->vc.chan), "%s\n", __func__);
@@ -541,14 +540,14 @@ static irqreturn_t moxart_dma_interrupt(int irq, void *devid)
 		if (ctrl & APB_DMA_FIN_INT_STS) {
 			ctrl &= ~APB_DMA_FIN_INT_STS;
 			if (ch->desc) {
-				spin_lock_irqsave(&ch->vc.lock, flags);
+				spin_lock(&ch->vc.lock);
 				if (++ch->sgidx < ch->desc->sglen) {
 					moxart_dma_start_sg(ch, ch->sgidx);
 				} else {
 					vchan_cookie_complete(&ch->desc->vd);
 					moxart_dma_start_desc(&ch->vc.chan);
 				}
-				spin_unlock_irqrestore(&ch->vc.lock, flags);
+				spin_unlock(&ch->vc.lock);
 			}
 		}
 
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index 00cd1335eeba..23b232b57518 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -1455,7 +1455,7 @@ static struct platform_driver mv_xor_driver = {
 	.resume         = mv_xor_resume,
 	.driver		= {
 		.name	        = MV_XOR_NAME,
-		.of_match_table = of_match_ptr(mv_xor_dt_ids),
+		.of_match_table = mv_xor_dt_ids,
 	},
 };
 
diff --git a/drivers/dma/mv_xor_v2.c b/drivers/dma/mv_xor_v2.c
index 2753a6b916f6..9b0d463f89bb 100644
--- a/drivers/dma/mv_xor_v2.c
+++ b/drivers/dma/mv_xor_v2.c
@@ -771,8 +771,10 @@ static int mv_xor_v2_probe(struct platform_device *pdev)
 		goto disable_clk;
 
 	msi_desc = first_msi_entry(&pdev->dev);
-	if (!msi_desc)
+	if (!msi_desc) {
+		ret = -ENODEV;
 		goto free_msi_irqs;
+	}
 	xor_dev->msi_desc = msi_desc;
 
 	ret = devm_request_irq(&pdev->dev, msi_desc->irq,
diff --git a/drivers/dma/mxs-dma.c b/drivers/dma/mxs-dma.c
index 65f816b40c32..994fc4d2aca4 100644
--- a/drivers/dma/mxs-dma.c
+++ b/drivers/dma/mxs-dma.c
@@ -167,29 +167,11 @@ static struct mxs_dma_type mxs_dma_types[] = {
 	}
 };
 
-static const struct platform_device_id mxs_dma_ids[] = {
-	{
-		.name = "imx23-dma-apbh",
-		.driver_data = (kernel_ulong_t) &mxs_dma_types[0],
-	}, {
-		.name = "imx23-dma-apbx",
-		.driver_data = (kernel_ulong_t) &mxs_dma_types[1],
-	}, {
-		.name = "imx28-dma-apbh",
-		.driver_data = (kernel_ulong_t) &mxs_dma_types[2],
-	}, {
-		.name = "imx28-dma-apbx",
-		.driver_data = (kernel_ulong_t) &mxs_dma_types[3],
-	}, {
-		/* end of list */
-	}
-};
-
 static const struct of_device_id mxs_dma_dt_ids[] = {
-	{ .compatible = "fsl,imx23-dma-apbh", .data = &mxs_dma_ids[0], },
-	{ .compatible = "fsl,imx23-dma-apbx", .data = &mxs_dma_ids[1], },
-	{ .compatible = "fsl,imx28-dma-apbh", .data = &mxs_dma_ids[2], },
-	{ .compatible = "fsl,imx28-dma-apbx", .data = &mxs_dma_ids[3], },
+	{ .compatible = "fsl,imx23-dma-apbh", .data = &mxs_dma_types[0], },
+	{ .compatible = "fsl,imx23-dma-apbx", .data = &mxs_dma_types[1], },
+	{ .compatible = "fsl,imx28-dma-apbh", .data = &mxs_dma_types[2], },
+	{ .compatible = "fsl,imx28-dma-apbx", .data = &mxs_dma_types[3], },
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, mxs_dma_dt_ids);
@@ -762,8 +744,6 @@ static struct dma_chan *mxs_dma_xlate(struct of_phandle_args *dma_spec,
 static int __init mxs_dma_probe(struct platform_device *pdev)
 {
 	struct device_node *np = pdev->dev.of_node;
-	const struct platform_device_id *id_entry;
-	const struct of_device_id *of_id;
 	const struct mxs_dma_type *dma_type;
 	struct mxs_dma_engine *mxs_dma;
 	struct resource *iores;
@@ -779,13 +759,7 @@ static int __init mxs_dma_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	of_id = of_match_device(mxs_dma_dt_ids, &pdev->dev);
-	if (of_id)
-		id_entry = of_id->data;
-	else
-		id_entry = platform_get_device_id(pdev);
-
-	dma_type = (struct mxs_dma_type *)id_entry->driver_data;
+	dma_type = (struct mxs_dma_type *)of_device_get_match_data(&pdev->dev);
 	mxs_dma->type = dma_type->type;
 	mxs_dma->dev_id = dma_type->id;
 
@@ -865,7 +839,6 @@ static struct platform_driver mxs_dma_driver = {
 		.name	= "mxs-dma",
 		.of_match_table = mxs_dma_dt_ids,
 	},
-	.id_table	= mxs_dma_ids,
 };
 
 static int __init mxs_dma_module_init(void)
diff --git a/drivers/dma/of-dma.c b/drivers/dma/of-dma.c
index 8a4f608904b9..ec00b20ae8e4 100644
--- a/drivers/dma/of-dma.c
+++ b/drivers/dma/of-dma.c
@@ -75,8 +75,18 @@ static struct dma_chan *of_dma_router_xlate(struct of_phandle_args *dma_spec,
 		ofdma->dma_router->route_free(ofdma->dma_router->dev,
 					      route_data);
 	} else {
+		int ret = 0;
+
 		chan->router = ofdma->dma_router;
 		chan->route_data = route_data;
+
+		if (chan->device->device_router_config)
+			ret = chan->device->device_router_config(chan);
+
+		if (ret) {
+			dma_release_channel(chan);
+			chan = ERR_PTR(ret);
+		}
 	}
 
 	/*
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index 0f5c19370f6d..bc0f66af0f11 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -1527,8 +1527,6 @@ static int pl330_submit_req(struct pl330_thread *thrd,
 
 	/* First dry run to check if req is acceptable */
 	ret = _setup_req(pl330, 1, thrd, idx, &xs);
-	if (ret < 0)
-		goto xfer_exit;
 
 	if (ret > pl330->mcbufsz / 2) {
 		dev_info(pl330->ddma.dev, "%s:%d Try increasing mcbufsz (%i/%i)\n",
diff --git a/drivers/dma/ppc4xx/adma.c b/drivers/dma/ppc4xx/adma.c
index 71cdaaa8134c..df7704053d91 100644
--- a/drivers/dma/ppc4xx/adma.c
+++ b/drivers/dma/ppc4xx/adma.c
@@ -69,7 +69,7 @@ struct ppc_dma_chan_ref {
 };
 
 /* The list of channels exported by ppc440spe ADMA */
-struct list_head
+static struct list_head
 ppc440spe_adma_chan_list = LIST_HEAD_INIT(ppc440spe_adma_chan_list);
 
 /* This flag is set when want to refetch the xor chain in the interrupt
@@ -559,7 +559,6 @@ static void ppc440spe_desc_set_src_mult(struct ppc440spe_adma_desc_slot *desc,
 			int sg_index, unsigned char mult_value)
 {
 	struct dma_cdb *dma_hw_desc;
-	struct xor_cb *xor_hw_desc;
 	u32 *psgu;
 
 	switch (chan->device->id) {
@@ -590,7 +589,6 @@ static void ppc440spe_desc_set_src_mult(struct ppc440spe_adma_desc_slot *desc,
 		*psgu |= cpu_to_le32(mult_value << mult_index);
 		break;
 	case PPC440SPE_XOR_ID:
-		xor_hw_desc = desc->hw_desc;
 		break;
 	default:
 		BUG();
diff --git a/drivers/dma/pxa_dma.c b/drivers/dma/pxa_dma.c
index 349fb312c872..4a2a796e348c 100644
--- a/drivers/dma/pxa_dma.c
+++ b/drivers/dma/pxa_dma.c
@@ -606,7 +606,6 @@ static irqreturn_t pxad_chan_handler(int irq, void *dev_id)
 	struct pxad_chan *chan = phy->vchan;
 	struct virt_dma_desc *vd, *tmp;
 	unsigned int dcsr;
-	unsigned long flags;
 	bool vd_completed;
 	dma_cookie_t last_started = 0;
 
@@ -616,7 +615,7 @@ static irqreturn_t pxad_chan_handler(int irq, void *dev_id)
 	if (dcsr & PXA_DCSR_RUN)
 		return IRQ_NONE;
 
-	spin_lock_irqsave(&chan->vc.lock, flags);
+	spin_lock(&chan->vc.lock);
 	list_for_each_entry_safe(vd, tmp, &chan->vc.desc_issued, node) {
 		vd_completed = is_desc_completed(vd);
 		dev_dbg(&chan->vc.chan.dev->device,
@@ -658,7 +657,7 @@ static irqreturn_t pxad_chan_handler(int irq, void *dev_id)
 			pxad_launch_chan(chan, to_pxad_sw_desc(vd));
 		}
 	}
-	spin_unlock_irqrestore(&chan->vc.lock, flags);
+	spin_unlock(&chan->vc.lock);
 	wake_up(&chan->wq_state);
 
 	return IRQ_HANDLED;
diff --git a/drivers/dma/qcom/Kconfig b/drivers/dma/qcom/Kconfig
index 3bcb689162c6..365f94eb3b08 100644
--- a/drivers/dma/qcom/Kconfig
+++ b/drivers/dma/qcom/Kconfig
@@ -1,4 +1,15 @@
 # SPDX-License-Identifier: GPL-2.0-only
+config QCOM_ADM
+	tristate "Qualcomm ADM support"
+	depends on (ARCH_QCOM || COMPILE_TEST) && !PHYS_ADDR_T_64BIT
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Enable support for the Qualcomm Application Data Mover (ADM) DMA
+	  controller, as present on MSM8x60, APQ8064, and IPQ8064 devices.
+	  This controller provides DMA capabilities for both general purpose
+	  and on-chip peripheral devices.
+
 config QCOM_BAM_DMA
 	tristate "QCOM BAM DMA support"
 	depends on ARCH_QCOM || (COMPILE_TEST && OF && ARM)
@@ -8,6 +19,18 @@ config QCOM_BAM_DMA
 	  Enable support for the QCOM BAM DMA controller.  This controller
 	  provides DMA capabilities for a variety of on-chip devices.
 
+config QCOM_GPI_DMA
+        tristate "Qualcomm Technologies GPI DMA support"
+        depends on ARCH_QCOM
+        select DMA_ENGINE
+        select DMA_VIRTUAL_CHANNELS
+        help
+          Enable support for the QCOM GPI DMA controller. This controller
+          provides DMA capabilities for a variety of peripheral buses such
+          as I2C, UART, and SPI. By using GPI dmaengine driver, bus drivers
+          can use a standardize interface that is protocol independent to
+          transfer data between DDR and peripheral.
+
 config QCOM_HIDMA_MGMT
 	tristate "Qualcomm Technologies HIDMA Management support"
 	select DMA_ENGINE
diff --git a/drivers/dma/qcom/Makefile b/drivers/dma/qcom/Makefile
index 1ae92da88b0c..50f1e7014693 100644
--- a/drivers/dma/qcom/Makefile
+++ b/drivers/dma/qcom/Makefile
@@ -1,5 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_QCOM_ADM) += qcom_adm.o
 obj-$(CONFIG_QCOM_BAM_DMA) += bam_dma.o
+obj-$(CONFIG_QCOM_GPI_DMA) += gpi.o
 obj-$(CONFIG_QCOM_HIDMA_MGMT) += hdma_mgmt.o
 hdma_mgmt-objs	 := hidma_mgmt.o hidma_mgmt_sys.o
 obj-$(CONFIG_QCOM_HIDMA) +=  hdma.o
diff --git a/drivers/dma/qcom/bam_dma.c b/drivers/dma/qcom/bam_dma.c
index 4eeb8bb27279..d5773d474d8f 100644
--- a/drivers/dma/qcom/bam_dma.c
+++ b/drivers/dma/qcom/bam_dma.c
@@ -875,7 +875,7 @@ static irqreturn_t bam_dma_irq(int irq, void *data)
 
 	ret = bam_pm_runtime_get_sync(bdev->dev);
 	if (ret < 0)
-		return ret;
+		return IRQ_NONE;
 
 	if (srcs & BAM_IRQ) {
 		clr_mask = readl_relaxed(bam_addr(bdev, 0, BAM_IRQ_STTS));
diff --git a/drivers/dma/qcom/gpi.c b/drivers/dma/qcom/gpi.c
new file mode 100644
index 000000000000..d2334f535de2
--- /dev/null
+++ b/drivers/dma/qcom/gpi.c
@@ -0,0 +1,2303 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2017-2020, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2020, Linaro Limited
+ */
+
+#include <dt-bindings/dma/qcom-gpi.h>
+#include <linux/bitfield.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmaengine.h>
+#include <linux/module.h>
+#include <linux/of_dma.h>
+#include <linux/platform_device.h>
+#include <linux/dma/qcom-gpi-dma.h>
+#include <linux/scatterlist.h>
+#include <linux/slab.h>
+#include "../dmaengine.h"
+#include "../virt-dma.h"
+
+#define TRE_TYPE_DMA		0x10
+#define TRE_TYPE_GO		0x20
+#define TRE_TYPE_CONFIG0	0x22
+
+/* TRE flags */
+#define TRE_FLAGS_CHAIN		BIT(0)
+#define TRE_FLAGS_IEOB		BIT(8)
+#define TRE_FLAGS_IEOT		BIT(9)
+#define TRE_FLAGS_BEI		BIT(10)
+#define TRE_FLAGS_LINK		BIT(11)
+#define TRE_FLAGS_TYPE		GENMASK(23, 16)
+
+/* SPI CONFIG0 WD0 */
+#define TRE_SPI_C0_WORD_SZ	GENMASK(4, 0)
+#define TRE_SPI_C0_LOOPBACK	BIT(8)
+#define TRE_SPI_C0_CS		BIT(11)
+#define TRE_SPI_C0_CPHA		BIT(12)
+#define TRE_SPI_C0_CPOL		BIT(13)
+#define TRE_SPI_C0_TX_PACK	BIT(24)
+#define TRE_SPI_C0_RX_PACK	BIT(25)
+
+/* CONFIG0 WD2 */
+#define TRE_C0_CLK_DIV		GENMASK(11, 0)
+#define TRE_C0_CLK_SRC		GENMASK(19, 16)
+
+/* SPI GO WD0 */
+#define TRE_SPI_GO_CMD		GENMASK(4, 0)
+#define TRE_SPI_GO_CS		GENMASK(10, 8)
+#define TRE_SPI_GO_FRAG		BIT(26)
+
+/* GO WD2 */
+#define TRE_RX_LEN		GENMASK(23, 0)
+
+/* I2C Config0 WD0 */
+#define TRE_I2C_C0_TLOW		GENMASK(7, 0)
+#define TRE_I2C_C0_THIGH	GENMASK(15, 8)
+#define TRE_I2C_C0_TCYL		GENMASK(23, 16)
+#define TRE_I2C_C0_TX_PACK	BIT(24)
+#define TRE_I2C_C0_RX_PACK      BIT(25)
+
+/* I2C GO WD0 */
+#define TRE_I2C_GO_CMD          GENMASK(4, 0)
+#define TRE_I2C_GO_ADDR		GENMASK(14, 8)
+#define TRE_I2C_GO_STRETCH	BIT(26)
+
+/* DMA TRE */
+#define TRE_DMA_LEN		GENMASK(23, 0)
+
+/* Register offsets from gpi-top */
+#define GPII_n_CH_k_CNTXT_0_OFFS(n, k)	(0x20000 + (0x4000 * (n)) + (0x80 * (k)))
+#define GPII_n_CH_k_CNTXT_0_EL_SIZE	GENMASK(31, 24)
+#define GPII_n_CH_k_CNTXT_0_CHSTATE	GENMASK(23, 20)
+#define GPII_n_CH_k_CNTXT_0_ERIDX	GENMASK(18, 14)
+#define GPII_n_CH_k_CNTXT_0_DIR		BIT(3)
+#define GPII_n_CH_k_CNTXT_0_PROTO	GENMASK(2, 0)
+
+#define GPII_n_CH_k_CNTXT_0(el_size, erindex, dir, chtype_proto)  \
+	(FIELD_PREP(GPII_n_CH_k_CNTXT_0_EL_SIZE, el_size)	| \
+	 FIELD_PREP(GPII_n_CH_k_CNTXT_0_ERIDX, erindex)		| \
+	 FIELD_PREP(GPII_n_CH_k_CNTXT_0_DIR, dir)		| \
+	 FIELD_PREP(GPII_n_CH_k_CNTXT_0_PROTO, chtype_proto))
+
+#define GPI_CHTYPE_DIR_IN	(0)
+#define GPI_CHTYPE_DIR_OUT	(1)
+
+#define GPI_CHTYPE_PROTO_GPI	(0x2)
+
+#define GPII_n_CH_k_DOORBELL_0_OFFS(n, k)	(0x22000 + (0x4000 * (n)) + (0x8 * (k)))
+#define GPII_n_CH_CMD_OFFS(n)			(0x23008 + (0x4000 * (n)))
+#define GPII_n_CH_CMD_OPCODE			GENMASK(31, 24)
+#define GPII_n_CH_CMD_CHID			GENMASK(7, 0)
+#define GPII_n_CH_CMD(opcode, chid)				 \
+		     (FIELD_PREP(GPII_n_CH_CMD_OPCODE, opcode) | \
+		      FIELD_PREP(GPII_n_CH_CMD_CHID, chid))
+
+#define GPII_n_CH_CMD_ALLOCATE		(0)
+#define GPII_n_CH_CMD_START		(1)
+#define GPII_n_CH_CMD_STOP		(2)
+#define GPII_n_CH_CMD_RESET		(9)
+#define GPII_n_CH_CMD_DE_ALLOC		(10)
+#define GPII_n_CH_CMD_UART_SW_STALE	(32)
+#define GPII_n_CH_CMD_UART_RFR_READY	(33)
+#define GPII_n_CH_CMD_UART_RFR_NOT_READY (34)
+
+/* EV Context Array */
+#define GPII_n_EV_CH_k_CNTXT_0_OFFS(n, k) (0x21000 + (0x4000 * (n)) + (0x80 * (k)))
+#define GPII_n_EV_k_CNTXT_0_EL_SIZE	GENMASK(31, 24)
+#define GPII_n_EV_k_CNTXT_0_CHSTATE	GENMASK(23, 20)
+#define GPII_n_EV_k_CNTXT_0_INTYPE	BIT(16)
+#define GPII_n_EV_k_CNTXT_0_CHTYPE	GENMASK(3, 0)
+
+#define GPII_n_EV_k_CNTXT_0(el_size, inttype, chtype)		\
+	(FIELD_PREP(GPII_n_EV_k_CNTXT_0_EL_SIZE, el_size) |	\
+	 FIELD_PREP(GPII_n_EV_k_CNTXT_0_INTYPE, inttype)  |	\
+	 FIELD_PREP(GPII_n_EV_k_CNTXT_0_CHTYPE, chtype))
+
+#define GPI_INTTYPE_IRQ		(1)
+#define GPI_CHTYPE_GPI_EV	(0x2)
+
+enum CNTXT_OFFS {
+	CNTXT_0_CONFIG = 0x0,
+	CNTXT_1_R_LENGTH = 0x4,
+	CNTXT_2_RING_BASE_LSB = 0x8,
+	CNTXT_3_RING_BASE_MSB = 0xC,
+	CNTXT_4_RING_RP_LSB = 0x10,
+	CNTXT_5_RING_RP_MSB = 0x14,
+	CNTXT_6_RING_WP_LSB = 0x18,
+	CNTXT_7_RING_WP_MSB = 0x1C,
+	CNTXT_8_RING_INT_MOD = 0x20,
+	CNTXT_9_RING_INTVEC = 0x24,
+	CNTXT_10_RING_MSI_LSB = 0x28,
+	CNTXT_11_RING_MSI_MSB = 0x2C,
+	CNTXT_12_RING_RP_UPDATE_LSB = 0x30,
+	CNTXT_13_RING_RP_UPDATE_MSB = 0x34,
+};
+
+#define GPII_n_EV_CH_k_DOORBELL_0_OFFS(n, k)	(0x22100 + (0x4000 * (n)) + (0x8 * (k)))
+#define GPII_n_EV_CH_CMD_OFFS(n)		(0x23010 + (0x4000 * (n)))
+#define GPII_n_EV_CMD_OPCODE			GENMASK(31, 24)
+#define GPII_n_EV_CMD_CHID			GENMASK(7, 0)
+#define GPII_n_EV_CMD(opcode, chid)				 \
+		     (FIELD_PREP(GPII_n_EV_CMD_OPCODE, opcode) | \
+		      FIELD_PREP(GPII_n_EV_CMD_CHID, chid))
+
+#define GPII_n_EV_CH_CMD_ALLOCATE		(0x00)
+#define GPII_n_EV_CH_CMD_RESET			(0x09)
+#define GPII_n_EV_CH_CMD_DE_ALLOC		(0x0A)
+
+#define GPII_n_CNTXT_TYPE_IRQ_OFFS(n)		(0x23080 + (0x4000 * (n)))
+
+/* mask type register */
+#define GPII_n_CNTXT_TYPE_IRQ_MSK_OFFS(n)	(0x23088 + (0x4000 * (n)))
+#define GPII_n_CNTXT_TYPE_IRQ_MSK_BMSK		GENMASK(6, 0)
+#define GPII_n_CNTXT_TYPE_IRQ_MSK_GENERAL	BIT(6)
+#define GPII_n_CNTXT_TYPE_IRQ_MSK_IEOB		BIT(3)
+#define GPII_n_CNTXT_TYPE_IRQ_MSK_GLOB		BIT(2)
+#define GPII_n_CNTXT_TYPE_IRQ_MSK_EV_CTRL	BIT(1)
+#define GPII_n_CNTXT_TYPE_IRQ_MSK_CH_CTRL	BIT(0)
+
+#define GPII_n_CNTXT_SRC_GPII_CH_IRQ_OFFS(n)	(0x23090 + (0x4000 * (n)))
+#define GPII_n_CNTXT_SRC_EV_CH_IRQ_OFFS(n)	(0x23094 + (0x4000 * (n)))
+
+/* Mask channel control interrupt register */
+#define GPII_n_CNTXT_SRC_CH_IRQ_MSK_OFFS(n)	(0x23098 + (0x4000 * (n)))
+#define GPII_n_CNTXT_SRC_CH_IRQ_MSK_BMSK	GENMASK(1, 0)
+
+/* Mask event control interrupt register */
+#define GPII_n_CNTXT_SRC_EV_CH_IRQ_MSK_OFFS(n)	(0x2309C + (0x4000 * (n)))
+#define GPII_n_CNTXT_SRC_EV_CH_IRQ_MSK_BMSK	BIT(0)
+
+#define GPII_n_CNTXT_SRC_CH_IRQ_CLR_OFFS(n)	(0x230A0 + (0x4000 * (n)))
+#define GPII_n_CNTXT_SRC_EV_CH_IRQ_CLR_OFFS(n)	(0x230A4 + (0x4000 * (n)))
+
+/* Mask event interrupt register */
+#define GPII_n_CNTXT_SRC_IEOB_IRQ_MSK_OFFS(n)	(0x230B8 + (0x4000 * (n)))
+#define GPII_n_CNTXT_SRC_IEOB_IRQ_MSK_BMSK	BIT(0)
+
+#define GPII_n_CNTXT_SRC_IEOB_IRQ_CLR_OFFS(n)	(0x230C0 + (0x4000 * (n)))
+#define GPII_n_CNTXT_GLOB_IRQ_STTS_OFFS(n)	(0x23100 + (0x4000 * (n)))
+#define GPI_GLOB_IRQ_ERROR_INT_MSK		BIT(0)
+
+/* GPII specific Global - Enable bit register */
+#define GPII_n_CNTXT_GLOB_IRQ_EN_OFFS(n)	(0x23108 + (0x4000 * (n)))
+#define GPII_n_CNTXT_GLOB_IRQ_CLR_OFFS(n)	(0x23110 + (0x4000 * (n)))
+#define GPII_n_CNTXT_GPII_IRQ_STTS_OFFS(n)	(0x23118 + (0x4000 * (n)))
+
+/* GPII general interrupt - Enable bit register */
+#define GPII_n_CNTXT_GPII_IRQ_EN_OFFS(n)	(0x23120 + (0x4000 * (n)))
+#define GPII_n_CNTXT_GPII_IRQ_EN_BMSK		GENMASK(3, 0)
+
+#define GPII_n_CNTXT_GPII_IRQ_CLR_OFFS(n)	(0x23128 + (0x4000 * (n)))
+
+/* GPII Interrupt Type register */
+#define GPII_n_CNTXT_INTSET_OFFS(n)		(0x23180 + (0x4000 * (n)))
+#define GPII_n_CNTXT_INTSET_BMSK		BIT(0)
+
+#define GPII_n_CNTXT_MSI_BASE_LSB_OFFS(n)	(0x23188 + (0x4000 * (n)))
+#define GPII_n_CNTXT_MSI_BASE_MSB_OFFS(n)	(0x2318C + (0x4000 * (n)))
+#define GPII_n_CNTXT_SCRATCH_0_OFFS(n)		(0x23400 + (0x4000 * (n)))
+#define GPII_n_CNTXT_SCRATCH_1_OFFS(n)		(0x23404 + (0x4000 * (n)))
+
+#define GPII_n_ERROR_LOG_OFFS(n)		(0x23200 + (0x4000 * (n)))
+
+/* QOS Registers */
+#define GPII_n_CH_k_QOS_OFFS(n, k)		(0x2005C + (0x4000 * (n)) + (0x80 * (k)))
+
+/* Scratch registers */
+#define GPII_n_CH_k_SCRATCH_0_OFFS(n, k)	(0x20060 + (0x4000 * (n)) + (0x80 * (k)))
+#define GPII_n_CH_k_SCRATCH_0_SEID		GENMASK(2, 0)
+#define GPII_n_CH_k_SCRATCH_0_PROTO		GENMASK(7, 4)
+#define GPII_n_CH_k_SCRATCH_0_PAIR		GENMASK(20, 16)
+#define GPII_n_CH_k_SCRATCH_0(pair, proto, seid)		\
+			     (FIELD_PREP(GPII_n_CH_k_SCRATCH_0_PAIR, pair)	| \
+			      FIELD_PREP(GPII_n_CH_k_SCRATCH_0_PROTO, proto)	| \
+			      FIELD_PREP(GPII_n_CH_k_SCRATCH_0_SEID, seid))
+#define GPII_n_CH_k_SCRATCH_1_OFFS(n, k)	(0x20064 + (0x4000 * (n)) + (0x80 * (k)))
+#define GPII_n_CH_k_SCRATCH_2_OFFS(n, k)	(0x20068 + (0x4000 * (n)) + (0x80 * (k)))
+#define GPII_n_CH_k_SCRATCH_3_OFFS(n, k)	(0x2006C + (0x4000 * (n)) + (0x80 * (k)))
+
+struct __packed gpi_tre {
+	u32 dword[4];
+};
+
+enum msm_gpi_tce_code {
+	MSM_GPI_TCE_SUCCESS = 1,
+	MSM_GPI_TCE_EOT = 2,
+	MSM_GPI_TCE_EOB = 4,
+	MSM_GPI_TCE_UNEXP_ERR = 16,
+};
+
+#define CMD_TIMEOUT_MS		(250)
+
+#define MAX_CHANNELS_PER_GPII	(2)
+#define GPI_TX_CHAN		(0)
+#define GPI_RX_CHAN		(1)
+#define STATE_IGNORE		(U32_MAX)
+#define EV_FACTOR		(2)
+#define REQ_OF_DMA_ARGS		(5) /* # of arguments required from client */
+#define CHAN_TRES		64
+
+struct __packed xfer_compl_event {
+	u64 ptr;
+	u32 length:24;
+	u8 code;
+	u16 status;
+	u8 type;
+	u8 chid;
+};
+
+struct __packed immediate_data_event {
+	u8 data_bytes[8];
+	u8 length:4;
+	u8 resvd:4;
+	u16 tre_index;
+	u8 code;
+	u16 status;
+	u8 type;
+	u8 chid;
+};
+
+struct __packed qup_notif_event {
+	u32 status;
+	u32 time;
+	u32 count:24;
+	u8 resvd;
+	u16 resvd1;
+	u8 type;
+	u8 chid;
+};
+
+struct __packed gpi_ere {
+	u32 dword[4];
+};
+
+enum GPI_EV_TYPE {
+	XFER_COMPLETE_EV_TYPE = 0x22,
+	IMMEDIATE_DATA_EV_TYPE = 0x30,
+	QUP_NOTIF_EV_TYPE = 0x31,
+	STALE_EV_TYPE = 0xFF,
+};
+
+union __packed gpi_event {
+	struct __packed xfer_compl_event xfer_compl_event;
+	struct __packed immediate_data_event immediate_data_event;
+	struct __packed qup_notif_event qup_notif_event;
+	struct __packed gpi_ere gpi_ere;
+};
+
+enum gpii_irq_settings {
+	DEFAULT_IRQ_SETTINGS,
+	MASK_IEOB_SETTINGS,
+};
+
+enum gpi_ev_state {
+	DEFAULT_EV_CH_STATE = 0,
+	EV_STATE_NOT_ALLOCATED = DEFAULT_EV_CH_STATE,
+	EV_STATE_ALLOCATED,
+	MAX_EV_STATES
+};
+
+static const char *const gpi_ev_state_str[MAX_EV_STATES] = {
+	[EV_STATE_NOT_ALLOCATED] = "NOT ALLOCATED",
+	[EV_STATE_ALLOCATED] = "ALLOCATED",
+};
+
+#define TO_GPI_EV_STATE_STR(_state) (((_state) >= MAX_EV_STATES) ? \
+				    "INVALID" : gpi_ev_state_str[(_state)])
+
+enum gpi_ch_state {
+	DEFAULT_CH_STATE = 0x0,
+	CH_STATE_NOT_ALLOCATED = DEFAULT_CH_STATE,
+	CH_STATE_ALLOCATED = 0x1,
+	CH_STATE_STARTED = 0x2,
+	CH_STATE_STOPPED = 0x3,
+	CH_STATE_STOP_IN_PROC = 0x4,
+	CH_STATE_ERROR = 0xf,
+	MAX_CH_STATES
+};
+
+enum gpi_cmd {
+	GPI_CH_CMD_BEGIN,
+	GPI_CH_CMD_ALLOCATE = GPI_CH_CMD_BEGIN,
+	GPI_CH_CMD_START,
+	GPI_CH_CMD_STOP,
+	GPI_CH_CMD_RESET,
+	GPI_CH_CMD_DE_ALLOC,
+	GPI_CH_CMD_UART_SW_STALE,
+	GPI_CH_CMD_UART_RFR_READY,
+	GPI_CH_CMD_UART_RFR_NOT_READY,
+	GPI_CH_CMD_END = GPI_CH_CMD_UART_RFR_NOT_READY,
+	GPI_EV_CMD_BEGIN,
+	GPI_EV_CMD_ALLOCATE = GPI_EV_CMD_BEGIN,
+	GPI_EV_CMD_RESET,
+	GPI_EV_CMD_DEALLOC,
+	GPI_EV_CMD_END = GPI_EV_CMD_DEALLOC,
+	GPI_MAX_CMD,
+};
+
+#define IS_CHAN_CMD(_cmd) ((_cmd) <= GPI_CH_CMD_END)
+
+static const char *const gpi_cmd_str[GPI_MAX_CMD] = {
+	[GPI_CH_CMD_ALLOCATE] = "CH ALLOCATE",
+	[GPI_CH_CMD_START] = "CH START",
+	[GPI_CH_CMD_STOP] = "CH STOP",
+	[GPI_CH_CMD_RESET] = "CH_RESET",
+	[GPI_CH_CMD_DE_ALLOC] = "DE ALLOC",
+	[GPI_CH_CMD_UART_SW_STALE] = "UART SW STALE",
+	[GPI_CH_CMD_UART_RFR_READY] = "UART RFR READY",
+	[GPI_CH_CMD_UART_RFR_NOT_READY] = "UART RFR NOT READY",
+	[GPI_EV_CMD_ALLOCATE] = "EV ALLOCATE",
+	[GPI_EV_CMD_RESET] = "EV RESET",
+	[GPI_EV_CMD_DEALLOC] = "EV DEALLOC",
+};
+
+#define TO_GPI_CMD_STR(_cmd) (((_cmd) >= GPI_MAX_CMD) ? "INVALID" : \
+				  gpi_cmd_str[(_cmd)])
+
+/*
+ * @DISABLE_STATE: no register access allowed
+ * @CONFIG_STATE:  client has configured the channel
+ * @PREP_HARDWARE: register access is allowed
+ *		   however, no processing EVENTS
+ * @ACTIVE_STATE: channels are fully operational
+ * @PREPARE_TERMINATE: graceful termination of channels
+ *		       register access is allowed
+ * @PAUSE_STATE: channels are active, but not processing any events
+ */
+enum gpi_pm_state {
+	DISABLE_STATE,
+	CONFIG_STATE,
+	PREPARE_HARDWARE,
+	ACTIVE_STATE,
+	PREPARE_TERMINATE,
+	PAUSE_STATE,
+	MAX_PM_STATE
+};
+
+#define REG_ACCESS_VALID(_pm_state) ((_pm_state) >= PREPARE_HARDWARE)
+
+static const char *const gpi_pm_state_str[MAX_PM_STATE] = {
+	[DISABLE_STATE] = "DISABLE",
+	[CONFIG_STATE] = "CONFIG",
+	[PREPARE_HARDWARE] = "PREPARE HARDWARE",
+	[ACTIVE_STATE] = "ACTIVE",
+	[PREPARE_TERMINATE] = "PREPARE TERMINATE",
+	[PAUSE_STATE] = "PAUSE",
+};
+
+#define TO_GPI_PM_STR(_state) (((_state) >= MAX_PM_STATE) ? \
+			      "INVALID" : gpi_pm_state_str[(_state)])
+
+static const struct {
+	enum gpi_cmd gpi_cmd;
+	u32 opcode;
+	u32 state;
+} gpi_cmd_info[GPI_MAX_CMD] = {
+	{
+		GPI_CH_CMD_ALLOCATE,
+		GPII_n_CH_CMD_ALLOCATE,
+		CH_STATE_ALLOCATED,
+	},
+	{
+		GPI_CH_CMD_START,
+		GPII_n_CH_CMD_START,
+		CH_STATE_STARTED,
+	},
+	{
+		GPI_CH_CMD_STOP,
+		GPII_n_CH_CMD_STOP,
+		CH_STATE_STOPPED,
+	},
+	{
+		GPI_CH_CMD_RESET,
+		GPII_n_CH_CMD_RESET,
+		CH_STATE_ALLOCATED,
+	},
+	{
+		GPI_CH_CMD_DE_ALLOC,
+		GPII_n_CH_CMD_DE_ALLOC,
+		CH_STATE_NOT_ALLOCATED,
+	},
+	{
+		GPI_CH_CMD_UART_SW_STALE,
+		GPII_n_CH_CMD_UART_SW_STALE,
+		STATE_IGNORE,
+	},
+	{
+		GPI_CH_CMD_UART_RFR_READY,
+		GPII_n_CH_CMD_UART_RFR_READY,
+		STATE_IGNORE,
+	},
+	{
+		GPI_CH_CMD_UART_RFR_NOT_READY,
+		GPII_n_CH_CMD_UART_RFR_NOT_READY,
+		STATE_IGNORE,
+	},
+	{
+		GPI_EV_CMD_ALLOCATE,
+		GPII_n_EV_CH_CMD_ALLOCATE,
+		EV_STATE_ALLOCATED,
+	},
+	{
+		GPI_EV_CMD_RESET,
+		GPII_n_EV_CH_CMD_RESET,
+		EV_STATE_ALLOCATED,
+	},
+	{
+		GPI_EV_CMD_DEALLOC,
+		GPII_n_EV_CH_CMD_DE_ALLOC,
+		EV_STATE_NOT_ALLOCATED,
+	},
+};
+
+struct gpi_ring {
+	void *pre_aligned;
+	size_t alloc_size;
+	phys_addr_t phys_addr;
+	dma_addr_t dma_handle;
+	void *base;
+	void *wp;
+	void *rp;
+	u32 len;
+	u32 el_size;
+	u32 elements;
+	bool configured;
+};
+
+struct gpi_dev {
+	struct dma_device dma_device;
+	struct device *dev;
+	struct resource *res;
+	void __iomem *regs;
+	void __iomem *ee_base; /*ee register base address*/
+	u32 max_gpii; /* maximum # of gpii instances available per gpi block */
+	u32 gpii_mask; /* gpii instances available for apps */
+	u32 ev_factor; /* ev ring length factor */
+	struct gpii *gpiis;
+};
+
+struct reg_info {
+	char *name;
+	u32 offset;
+	u32 val;
+};
+
+struct gchan {
+	struct virt_dma_chan vc;
+	u32 chid;
+	u32 seid;
+	u32 protocol;
+	struct gpii *gpii;
+	enum gpi_ch_state ch_state;
+	enum gpi_pm_state pm_state;
+	void __iomem *ch_cntxt_base_reg;
+	void __iomem *ch_cntxt_db_reg;
+	void __iomem *ch_cmd_reg;
+	u32 dir;
+	struct gpi_ring ch_ring;
+	void *config;
+};
+
+struct gpii {
+	u32 gpii_id;
+	struct gchan gchan[MAX_CHANNELS_PER_GPII];
+	struct gpi_dev *gpi_dev;
+	int irq;
+	void __iomem *regs; /* points to gpi top */
+	void __iomem *ev_cntxt_base_reg;
+	void __iomem *ev_cntxt_db_reg;
+	void __iomem *ev_ring_rp_lsb_reg;
+	void __iomem *ev_cmd_reg;
+	void __iomem *ieob_clr_reg;
+	struct mutex ctrl_lock;
+	enum gpi_ev_state ev_state;
+	bool configured_irq;
+	enum gpi_pm_state pm_state;
+	rwlock_t pm_lock;
+	struct gpi_ring ev_ring;
+	struct tasklet_struct ev_task; /* event processing tasklet */
+	struct completion cmd_completion;
+	enum gpi_cmd gpi_cmd;
+	u32 cntxt_type_irq_msk;
+	bool ieob_set;
+};
+
+#define MAX_TRE 3
+
+struct gpi_desc {
+	struct virt_dma_desc vd;
+	size_t len;
+	void *db; /* DB register to program */
+	struct gchan *gchan;
+	struct gpi_tre tre[MAX_TRE];
+	u32 num_tre;
+};
+
+static const u32 GPII_CHAN_DIR[MAX_CHANNELS_PER_GPII] = {
+	GPI_CHTYPE_DIR_OUT, GPI_CHTYPE_DIR_IN
+};
+
+static irqreturn_t gpi_handle_irq(int irq, void *data);
+static void gpi_ring_recycle_ev_element(struct gpi_ring *ring);
+static int gpi_ring_add_element(struct gpi_ring *ring, void **wp);
+static void gpi_process_events(struct gpii *gpii);
+
+static inline struct gchan *to_gchan(struct dma_chan *dma_chan)
+{
+	return container_of(dma_chan, struct gchan, vc.chan);
+}
+
+static inline struct gpi_desc *to_gpi_desc(struct virt_dma_desc *vd)
+{
+	return container_of(vd, struct gpi_desc, vd);
+}
+
+static inline phys_addr_t to_physical(const struct gpi_ring *const ring,
+				      void *addr)
+{
+	return ring->phys_addr + (addr - ring->base);
+}
+
+static inline void *to_virtual(const struct gpi_ring *const ring, phys_addr_t addr)
+{
+	return ring->base + (addr - ring->phys_addr);
+}
+
+static inline u32 gpi_read_reg(struct gpii *gpii, void __iomem *addr)
+{
+	return readl_relaxed(addr);
+}
+
+static inline void gpi_write_reg(struct gpii *gpii, void __iomem *addr, u32 val)
+{
+	writel_relaxed(val, addr);
+}
+
+/* gpi_write_reg_field - write to specific bit field */
+static inline void gpi_write_reg_field(struct gpii *gpii, void __iomem *addr,
+				       u32 mask, u32 shift, u32 val)
+{
+	u32 tmp = gpi_read_reg(gpii, addr);
+
+	tmp &= ~mask;
+	val = tmp | ((val << shift) & mask);
+	gpi_write_reg(gpii, addr, val);
+}
+
+static inline void
+gpi_update_reg(struct gpii *gpii, u32 offset, u32 mask, u32 val)
+{
+	void __iomem *addr = gpii->regs + offset;
+	u32 tmp = gpi_read_reg(gpii, addr);
+
+	tmp &= ~mask;
+	tmp |= u32_encode_bits(val, mask);
+
+	gpi_write_reg(gpii, addr, tmp);
+}
+
+static void gpi_disable_interrupts(struct gpii *gpii)
+{
+	gpi_update_reg(gpii, GPII_n_CNTXT_TYPE_IRQ_MSK_OFFS(gpii->gpii_id),
+		       GPII_n_CNTXT_TYPE_IRQ_MSK_BMSK, 0);
+	gpi_update_reg(gpii, GPII_n_CNTXT_SRC_IEOB_IRQ_MSK_OFFS(gpii->gpii_id),
+		       GPII_n_CNTXT_SRC_IEOB_IRQ_MSK_BMSK, 0);
+	gpi_update_reg(gpii, GPII_n_CNTXT_SRC_CH_IRQ_MSK_OFFS(gpii->gpii_id),
+		       GPII_n_CNTXT_SRC_CH_IRQ_MSK_BMSK, 0);
+	gpi_update_reg(gpii, GPII_n_CNTXT_SRC_EV_CH_IRQ_MSK_OFFS(gpii->gpii_id),
+		       GPII_n_CNTXT_SRC_EV_CH_IRQ_MSK_BMSK, 0);
+	gpi_update_reg(gpii, GPII_n_CNTXT_GLOB_IRQ_EN_OFFS(gpii->gpii_id),
+		       GPII_n_CNTXT_GPII_IRQ_EN_BMSK, 0);
+	gpi_update_reg(gpii, GPII_n_CNTXT_GPII_IRQ_EN_OFFS(gpii->gpii_id),
+		       GPII_n_CNTXT_GPII_IRQ_EN_BMSK, 0);
+	gpi_update_reg(gpii, GPII_n_CNTXT_INTSET_OFFS(gpii->gpii_id),
+		       GPII_n_CNTXT_INTSET_BMSK, 0);
+
+	gpii->cntxt_type_irq_msk = 0;
+	devm_free_irq(gpii->gpi_dev->dev, gpii->irq, gpii);
+	gpii->configured_irq = false;
+}
+
+/* configure and enable interrupts */
+static int gpi_config_interrupts(struct gpii *gpii, enum gpii_irq_settings settings, bool mask)
+{
+	const u32 enable = (GPII_n_CNTXT_TYPE_IRQ_MSK_GENERAL |
+			      GPII_n_CNTXT_TYPE_IRQ_MSK_IEOB |
+			      GPII_n_CNTXT_TYPE_IRQ_MSK_GLOB |
+			      GPII_n_CNTXT_TYPE_IRQ_MSK_EV_CTRL |
+			      GPII_n_CNTXT_TYPE_IRQ_MSK_CH_CTRL);
+	int ret;
+
+	if (!gpii->configured_irq) {
+		ret = devm_request_irq(gpii->gpi_dev->dev, gpii->irq,
+				       gpi_handle_irq, IRQF_TRIGGER_HIGH,
+				       "gpi-dma", gpii);
+		if (ret < 0) {
+			dev_err(gpii->gpi_dev->dev, "error request irq:%d ret:%d\n",
+				gpii->irq, ret);
+			return ret;
+		}
+	}
+
+	if (settings == MASK_IEOB_SETTINGS) {
+		/*
+		 * GPII only uses one EV ring per gpii so we can globally
+		 * enable/disable IEOB interrupt
+		 */
+		if (mask)
+			gpii->cntxt_type_irq_msk |= GPII_n_CNTXT_TYPE_IRQ_MSK_IEOB;
+		else
+			gpii->cntxt_type_irq_msk &= ~(GPII_n_CNTXT_TYPE_IRQ_MSK_IEOB);
+		gpi_update_reg(gpii, GPII_n_CNTXT_TYPE_IRQ_MSK_OFFS(gpii->gpii_id),
+			       GPII_n_CNTXT_TYPE_IRQ_MSK_BMSK, gpii->cntxt_type_irq_msk);
+	} else {
+		gpi_update_reg(gpii, GPII_n_CNTXT_TYPE_IRQ_MSK_OFFS(gpii->gpii_id),
+			       GPII_n_CNTXT_TYPE_IRQ_MSK_BMSK, enable);
+		gpi_update_reg(gpii, GPII_n_CNTXT_SRC_IEOB_IRQ_MSK_OFFS(gpii->gpii_id),
+			       GPII_n_CNTXT_SRC_IEOB_IRQ_MSK_BMSK,
+			       GPII_n_CNTXT_SRC_IEOB_IRQ_MSK_BMSK);
+		gpi_update_reg(gpii, GPII_n_CNTXT_SRC_CH_IRQ_MSK_OFFS(gpii->gpii_id),
+			       GPII_n_CNTXT_SRC_CH_IRQ_MSK_BMSK,
+			       GPII_n_CNTXT_SRC_CH_IRQ_MSK_BMSK);
+		gpi_update_reg(gpii, GPII_n_CNTXT_SRC_EV_CH_IRQ_MSK_OFFS(gpii->gpii_id),
+			       GPII_n_CNTXT_SRC_EV_CH_IRQ_MSK_BMSK,
+			       GPII_n_CNTXT_SRC_EV_CH_IRQ_MSK_BMSK);
+		gpi_update_reg(gpii, GPII_n_CNTXT_GLOB_IRQ_EN_OFFS(gpii->gpii_id),
+			       GPII_n_CNTXT_GPII_IRQ_EN_BMSK,
+			       GPII_n_CNTXT_GPII_IRQ_EN_BMSK);
+		gpi_update_reg(gpii, GPII_n_CNTXT_GPII_IRQ_EN_OFFS(gpii->gpii_id),
+			       GPII_n_CNTXT_GPII_IRQ_EN_BMSK, GPII_n_CNTXT_GPII_IRQ_EN_BMSK);
+		gpi_update_reg(gpii, GPII_n_CNTXT_MSI_BASE_LSB_OFFS(gpii->gpii_id), U32_MAX, 0);
+		gpi_update_reg(gpii, GPII_n_CNTXT_MSI_BASE_MSB_OFFS(gpii->gpii_id), U32_MAX, 0);
+		gpi_update_reg(gpii, GPII_n_CNTXT_SCRATCH_0_OFFS(gpii->gpii_id), U32_MAX, 0);
+		gpi_update_reg(gpii, GPII_n_CNTXT_SCRATCH_1_OFFS(gpii->gpii_id), U32_MAX, 0);
+		gpi_update_reg(gpii, GPII_n_CNTXT_INTSET_OFFS(gpii->gpii_id),
+			       GPII_n_CNTXT_INTSET_BMSK, 1);
+		gpi_update_reg(gpii, GPII_n_ERROR_LOG_OFFS(gpii->gpii_id), U32_MAX, 0);
+
+		gpii->cntxt_type_irq_msk = enable;
+	}
+
+	gpii->configured_irq = true;
+	return 0;
+}
+
+/* Sends gpii event or channel command */
+static int gpi_send_cmd(struct gpii *gpii, struct gchan *gchan,
+			enum gpi_cmd gpi_cmd)
+{
+	u32 chid = MAX_CHANNELS_PER_GPII;
+	unsigned long timeout;
+	void __iomem *cmd_reg;
+	u32 cmd;
+
+	if (gpi_cmd >= GPI_MAX_CMD)
+		return -EINVAL;
+	if (IS_CHAN_CMD(gpi_cmd))
+		chid = gchan->chid;
+
+	dev_dbg(gpii->gpi_dev->dev,
+		"sending cmd: %s:%u\n", TO_GPI_CMD_STR(gpi_cmd), chid);
+
+	/* send opcode and wait for completion */
+	reinit_completion(&gpii->cmd_completion);
+	gpii->gpi_cmd = gpi_cmd;
+
+	cmd_reg = IS_CHAN_CMD(gpi_cmd) ? gchan->ch_cmd_reg : gpii->ev_cmd_reg;
+	cmd = IS_CHAN_CMD(gpi_cmd) ? GPII_n_CH_CMD(gpi_cmd_info[gpi_cmd].opcode, chid) :
+				     GPII_n_EV_CMD(gpi_cmd_info[gpi_cmd].opcode, 0);
+	gpi_write_reg(gpii, cmd_reg, cmd);
+	timeout = wait_for_completion_timeout(&gpii->cmd_completion,
+					      msecs_to_jiffies(CMD_TIMEOUT_MS));
+	if (!timeout) {
+		dev_err(gpii->gpi_dev->dev, "cmd: %s completion timeout:%u\n",
+			TO_GPI_CMD_STR(gpi_cmd), chid);
+		return -EIO;
+	}
+
+	/* confirm new ch state is correct , if the cmd is a state change cmd */
+	if (gpi_cmd_info[gpi_cmd].state == STATE_IGNORE)
+		return 0;
+
+	if (IS_CHAN_CMD(gpi_cmd) && gchan->ch_state == gpi_cmd_info[gpi_cmd].state)
+		return 0;
+
+	if (!IS_CHAN_CMD(gpi_cmd) && gpii->ev_state == gpi_cmd_info[gpi_cmd].state)
+		return 0;
+
+	return -EIO;
+}
+
+/* program transfer ring DB register */
+static inline void gpi_write_ch_db(struct gchan *gchan,
+				   struct gpi_ring *ring, void *wp)
+{
+	struct gpii *gpii = gchan->gpii;
+	phys_addr_t p_wp;
+
+	p_wp = to_physical(ring, wp);
+	gpi_write_reg(gpii, gchan->ch_cntxt_db_reg, p_wp);
+}
+
+/* program event ring DB register */
+static inline void gpi_write_ev_db(struct gpii *gpii,
+				   struct gpi_ring *ring, void *wp)
+{
+	phys_addr_t p_wp;
+
+	p_wp = ring->phys_addr + (wp - ring->base);
+	gpi_write_reg(gpii, gpii->ev_cntxt_db_reg, p_wp);
+}
+
+/* process transfer completion interrupt */
+static void gpi_process_ieob(struct gpii *gpii)
+{
+	gpi_write_reg(gpii, gpii->ieob_clr_reg, BIT(0));
+
+	gpi_config_interrupts(gpii, MASK_IEOB_SETTINGS, 0);
+	tasklet_hi_schedule(&gpii->ev_task);
+}
+
+/* process channel control interrupt */
+static void gpi_process_ch_ctrl_irq(struct gpii *gpii)
+{
+	u32 gpii_id = gpii->gpii_id;
+	u32 offset = GPII_n_CNTXT_SRC_GPII_CH_IRQ_OFFS(gpii_id);
+	u32 ch_irq = gpi_read_reg(gpii, gpii->regs + offset);
+	struct gchan *gchan;
+	u32 chid, state;
+
+	/* clear the status */
+	offset = GPII_n_CNTXT_SRC_CH_IRQ_CLR_OFFS(gpii_id);
+	gpi_write_reg(gpii, gpii->regs + offset, (u32)ch_irq);
+
+	for (chid = 0; chid < MAX_CHANNELS_PER_GPII; chid++) {
+		if (!(BIT(chid) & ch_irq))
+			continue;
+
+		gchan = &gpii->gchan[chid];
+		state = gpi_read_reg(gpii, gchan->ch_cntxt_base_reg +
+				     CNTXT_0_CONFIG);
+		state = FIELD_GET(GPII_n_CH_k_CNTXT_0_CHSTATE, state);
+
+		/*
+		 * CH_CMD_DEALLOC cmd always successful. However cmd does
+		 * not change hardware status. So overwriting software state
+		 * to default state.
+		 */
+		if (gpii->gpi_cmd == GPI_CH_CMD_DE_ALLOC)
+			state = DEFAULT_CH_STATE;
+		gchan->ch_state = state;
+
+		/*
+		 * Triggering complete all if ch_state is not a stop in process.
+		 * Stop in process is a transition state and we will wait for
+		 * stop interrupt before notifying.
+		 */
+		if (gchan->ch_state != CH_STATE_STOP_IN_PROC)
+			complete_all(&gpii->cmd_completion);
+	}
+}
+
+/* processing gpi general error interrupts */
+static void gpi_process_gen_err_irq(struct gpii *gpii)
+{
+	u32 gpii_id = gpii->gpii_id;
+	u32 offset = GPII_n_CNTXT_GPII_IRQ_STTS_OFFS(gpii_id);
+	u32 irq_stts = gpi_read_reg(gpii, gpii->regs + offset);
+
+	/* clear the status */
+	dev_dbg(gpii->gpi_dev->dev, "irq_stts:0x%x\n", irq_stts);
+
+	/* Clear the register */
+	offset = GPII_n_CNTXT_GPII_IRQ_CLR_OFFS(gpii_id);
+	gpi_write_reg(gpii, gpii->regs + offset, irq_stts);
+}
+
+/* processing gpi level error interrupts */
+static void gpi_process_glob_err_irq(struct gpii *gpii)
+{
+	u32 gpii_id = gpii->gpii_id;
+	u32 offset = GPII_n_CNTXT_GLOB_IRQ_STTS_OFFS(gpii_id);
+	u32 irq_stts = gpi_read_reg(gpii, gpii->regs + offset);
+
+	offset = GPII_n_CNTXT_GLOB_IRQ_CLR_OFFS(gpii_id);
+	gpi_write_reg(gpii, gpii->regs + offset, irq_stts);
+
+	/* only error interrupt should be set */
+	if (irq_stts & ~GPI_GLOB_IRQ_ERROR_INT_MSK) {
+		dev_err(gpii->gpi_dev->dev, "invalid error status:0x%x\n", irq_stts);
+		return;
+	}
+
+	offset = GPII_n_ERROR_LOG_OFFS(gpii_id);
+	gpi_write_reg(gpii, gpii->regs + offset, 0);
+}
+
+/* gpii interrupt handler */
+static irqreturn_t gpi_handle_irq(int irq, void *data)
+{
+	struct gpii *gpii = data;
+	u32 gpii_id = gpii->gpii_id;
+	u32 type, offset;
+	unsigned long flags;
+
+	read_lock_irqsave(&gpii->pm_lock, flags);
+
+	/*
+	 * States are out of sync to receive interrupt
+	 * while software state is in DISABLE state, bailing out.
+	 */
+	if (!REG_ACCESS_VALID(gpii->pm_state)) {
+		dev_err(gpii->gpi_dev->dev, "receive interrupt while in %s state\n",
+			TO_GPI_PM_STR(gpii->pm_state));
+		goto exit_irq;
+	}
+
+	offset = GPII_n_CNTXT_TYPE_IRQ_OFFS(gpii->gpii_id);
+	type = gpi_read_reg(gpii, gpii->regs + offset);
+
+	do {
+		/* global gpii error */
+		if (type & GPII_n_CNTXT_TYPE_IRQ_MSK_GLOB) {
+			gpi_process_glob_err_irq(gpii);
+			type &= ~(GPII_n_CNTXT_TYPE_IRQ_MSK_GLOB);
+		}
+
+		/* transfer complete interrupt */
+		if (type & GPII_n_CNTXT_TYPE_IRQ_MSK_IEOB) {
+			gpi_process_ieob(gpii);
+			type &= ~GPII_n_CNTXT_TYPE_IRQ_MSK_IEOB;
+		}
+
+		/* event control irq */
+		if (type & GPII_n_CNTXT_TYPE_IRQ_MSK_EV_CTRL) {
+			u32 ev_state;
+			u32 ev_ch_irq;
+
+			dev_dbg(gpii->gpi_dev->dev,
+				"processing EV CTRL interrupt\n");
+			offset = GPII_n_CNTXT_SRC_EV_CH_IRQ_OFFS(gpii_id);
+			ev_ch_irq = gpi_read_reg(gpii, gpii->regs + offset);
+
+			offset = GPII_n_CNTXT_SRC_EV_CH_IRQ_CLR_OFFS
+				(gpii_id);
+			gpi_write_reg(gpii, gpii->regs + offset, ev_ch_irq);
+			ev_state = gpi_read_reg(gpii, gpii->ev_cntxt_base_reg +
+						CNTXT_0_CONFIG);
+			ev_state = FIELD_GET(GPII_n_EV_k_CNTXT_0_CHSTATE, ev_state);
+
+			/*
+			 * CMD EV_CMD_DEALLOC is always successful. However
+			 * cmd does not change hardware status. So overwriting
+			 * software state to default state.
+			 */
+			if (gpii->gpi_cmd == GPI_EV_CMD_DEALLOC)
+				ev_state = DEFAULT_EV_CH_STATE;
+
+			gpii->ev_state = ev_state;
+			dev_dbg(gpii->gpi_dev->dev, "setting EV state to %s\n",
+				TO_GPI_EV_STATE_STR(gpii->ev_state));
+			complete_all(&gpii->cmd_completion);
+			type &= ~(GPII_n_CNTXT_TYPE_IRQ_MSK_EV_CTRL);
+		}
+
+		/* channel control irq */
+		if (type & GPII_n_CNTXT_TYPE_IRQ_MSK_CH_CTRL) {
+			dev_dbg(gpii->gpi_dev->dev, "process CH CTRL interrupts\n");
+			gpi_process_ch_ctrl_irq(gpii);
+			type &= ~(GPII_n_CNTXT_TYPE_IRQ_MSK_CH_CTRL);
+		}
+
+		if (type) {
+			dev_err(gpii->gpi_dev->dev, "Unhandled interrupt status:0x%x\n", type);
+			gpi_process_gen_err_irq(gpii);
+			goto exit_irq;
+		}
+
+		offset = GPII_n_CNTXT_TYPE_IRQ_OFFS(gpii->gpii_id);
+		type = gpi_read_reg(gpii, gpii->regs + offset);
+	} while (type);
+
+exit_irq:
+	read_unlock_irqrestore(&gpii->pm_lock, flags);
+
+	return IRQ_HANDLED;
+}
+
+/* process DMA Immediate completion data events */
+static void gpi_process_imed_data_event(struct gchan *gchan,
+					struct immediate_data_event *imed_event)
+{
+	struct gpii *gpii = gchan->gpii;
+	struct gpi_ring *ch_ring = &gchan->ch_ring;
+	void *tre = ch_ring->base + (ch_ring->el_size * imed_event->tre_index);
+	struct dmaengine_result result;
+	struct gpi_desc *gpi_desc;
+	struct virt_dma_desc *vd;
+	unsigned long flags;
+	u32 chid;
+
+	/*
+	 * If channel not active don't process event
+	 */
+	if (gchan->pm_state != ACTIVE_STATE) {
+		dev_err(gpii->gpi_dev->dev, "skipping processing event because ch @ %s state\n",
+			TO_GPI_PM_STR(gchan->pm_state));
+		return;
+	}
+
+	spin_lock_irqsave(&gchan->vc.lock, flags);
+	vd = vchan_next_desc(&gchan->vc);
+	if (!vd) {
+		struct gpi_ere *gpi_ere;
+		struct gpi_tre *gpi_tre;
+
+		spin_unlock_irqrestore(&gchan->vc.lock, flags);
+		dev_dbg(gpii->gpi_dev->dev, "event without a pending descriptor!\n");
+		gpi_ere = (struct gpi_ere *)imed_event;
+		dev_dbg(gpii->gpi_dev->dev,
+			"Event: %08x %08x %08x %08x\n",
+			gpi_ere->dword[0], gpi_ere->dword[1],
+			gpi_ere->dword[2], gpi_ere->dword[3]);
+		gpi_tre = tre;
+		dev_dbg(gpii->gpi_dev->dev,
+			"Pending TRE: %08x %08x %08x %08x\n",
+			gpi_tre->dword[0], gpi_tre->dword[1],
+			gpi_tre->dword[2], gpi_tre->dword[3]);
+		return;
+	}
+	gpi_desc = to_gpi_desc(vd);
+	spin_unlock_irqrestore(&gchan->vc.lock, flags);
+
+	/*
+	 * RP pointed by Event is to last TRE processed,
+	 * we need to update ring rp to tre + 1
+	 */
+	tre += ch_ring->el_size;
+	if (tre >= (ch_ring->base + ch_ring->len))
+		tre = ch_ring->base;
+	ch_ring->rp = tre;
+
+	/* make sure rp updates are immediately visible to all cores */
+	smp_wmb();
+
+	chid = imed_event->chid;
+	if (imed_event->code == MSM_GPI_TCE_EOT && gpii->ieob_set) {
+		if (chid == GPI_RX_CHAN)
+			goto gpi_free_desc;
+		else
+			return;
+	}
+
+	if (imed_event->code == MSM_GPI_TCE_UNEXP_ERR)
+		result.result = DMA_TRANS_ABORTED;
+	else
+		result.result = DMA_TRANS_NOERROR;
+	result.residue = gpi_desc->len - imed_event->length;
+
+	dma_cookie_complete(&vd->tx);
+	dmaengine_desc_get_callback_invoke(&vd->tx, &result);
+
+gpi_free_desc:
+	spin_lock_irqsave(&gchan->vc.lock, flags);
+	list_del(&vd->node);
+	spin_unlock_irqrestore(&gchan->vc.lock, flags);
+	kfree(gpi_desc);
+	gpi_desc = NULL;
+}
+
+/* processing transfer completion events */
+static void gpi_process_xfer_compl_event(struct gchan *gchan,
+					 struct xfer_compl_event *compl_event)
+{
+	struct gpii *gpii = gchan->gpii;
+	struct gpi_ring *ch_ring = &gchan->ch_ring;
+	void *ev_rp = to_virtual(ch_ring, compl_event->ptr);
+	struct virt_dma_desc *vd;
+	struct gpi_desc *gpi_desc;
+	struct dmaengine_result result;
+	unsigned long flags;
+	u32 chid;
+
+	/* only process events on active channel */
+	if (unlikely(gchan->pm_state != ACTIVE_STATE)) {
+		dev_err(gpii->gpi_dev->dev, "skipping processing event because ch @ %s state\n",
+			TO_GPI_PM_STR(gchan->pm_state));
+		return;
+	}
+
+	spin_lock_irqsave(&gchan->vc.lock, flags);
+	vd = vchan_next_desc(&gchan->vc);
+	if (!vd) {
+		struct gpi_ere *gpi_ere;
+
+		spin_unlock_irqrestore(&gchan->vc.lock, flags);
+		dev_err(gpii->gpi_dev->dev, "Event without a pending descriptor!\n");
+		gpi_ere = (struct gpi_ere *)compl_event;
+		dev_err(gpii->gpi_dev->dev,
+			"Event: %08x %08x %08x %08x\n",
+			gpi_ere->dword[0], gpi_ere->dword[1],
+			gpi_ere->dword[2], gpi_ere->dword[3]);
+		return;
+	}
+
+	gpi_desc = to_gpi_desc(vd);
+	spin_unlock_irqrestore(&gchan->vc.lock, flags);
+
+	/*
+	 * RP pointed by Event is to last TRE processed,
+	 * we need to update ring rp to ev_rp + 1
+	 */
+	ev_rp += ch_ring->el_size;
+	if (ev_rp >= (ch_ring->base + ch_ring->len))
+		ev_rp = ch_ring->base;
+	ch_ring->rp = ev_rp;
+
+	/* update must be visible to other cores */
+	smp_wmb();
+
+	chid = compl_event->chid;
+	if (compl_event->code == MSM_GPI_TCE_EOT && gpii->ieob_set) {
+		if (chid == GPI_RX_CHAN)
+			goto gpi_free_desc;
+		else
+			return;
+	}
+
+	if (compl_event->code == MSM_GPI_TCE_UNEXP_ERR) {
+		dev_err(gpii->gpi_dev->dev, "Error in Transaction\n");
+		result.result = DMA_TRANS_ABORTED;
+	} else {
+		dev_dbg(gpii->gpi_dev->dev, "Transaction Success\n");
+		result.result = DMA_TRANS_NOERROR;
+	}
+	result.residue = gpi_desc->len - compl_event->length;
+	dev_dbg(gpii->gpi_dev->dev, "Residue %d\n", result.residue);
+
+	dma_cookie_complete(&vd->tx);
+	dmaengine_desc_get_callback_invoke(&vd->tx, &result);
+
+gpi_free_desc:
+	spin_lock_irqsave(&gchan->vc.lock, flags);
+	list_del(&vd->node);
+	spin_unlock_irqrestore(&gchan->vc.lock, flags);
+	kfree(gpi_desc);
+	gpi_desc = NULL;
+}
+
+/* process all events */
+static void gpi_process_events(struct gpii *gpii)
+{
+	struct gpi_ring *ev_ring = &gpii->ev_ring;
+	phys_addr_t cntxt_rp;
+	void *rp;
+	union gpi_event *gpi_event;
+	struct gchan *gchan;
+	u32 chid, type;
+
+	cntxt_rp = gpi_read_reg(gpii, gpii->ev_ring_rp_lsb_reg);
+	rp = to_virtual(ev_ring, cntxt_rp);
+
+	do {
+		while (rp != ev_ring->rp) {
+			gpi_event = ev_ring->rp;
+			chid = gpi_event->xfer_compl_event.chid;
+			type = gpi_event->xfer_compl_event.type;
+
+			dev_dbg(gpii->gpi_dev->dev,
+				"Event: CHID:%u, type:%x %08x %08x %08x %08x\n",
+				chid, type, gpi_event->gpi_ere.dword[0],
+				gpi_event->gpi_ere.dword[1], gpi_event->gpi_ere.dword[2],
+				gpi_event->gpi_ere.dword[3]);
+
+			switch (type) {
+			case XFER_COMPLETE_EV_TYPE:
+				gchan = &gpii->gchan[chid];
+				gpi_process_xfer_compl_event(gchan,
+							     &gpi_event->xfer_compl_event);
+				break;
+			case STALE_EV_TYPE:
+				dev_dbg(gpii->gpi_dev->dev, "stale event, not processing\n");
+				break;
+			case IMMEDIATE_DATA_EV_TYPE:
+				gchan = &gpii->gchan[chid];
+				gpi_process_imed_data_event(gchan,
+							    &gpi_event->immediate_data_event);
+				break;
+			case QUP_NOTIF_EV_TYPE:
+				dev_dbg(gpii->gpi_dev->dev, "QUP_NOTIF_EV_TYPE\n");
+				break;
+			default:
+				dev_dbg(gpii->gpi_dev->dev,
+					"not supported event type:0x%x\n", type);
+			}
+			gpi_ring_recycle_ev_element(ev_ring);
+		}
+		gpi_write_ev_db(gpii, ev_ring, ev_ring->wp);
+
+		/* clear pending IEOB events */
+		gpi_write_reg(gpii, gpii->ieob_clr_reg, BIT(0));
+
+		cntxt_rp = gpi_read_reg(gpii, gpii->ev_ring_rp_lsb_reg);
+		rp = to_virtual(ev_ring, cntxt_rp);
+
+	} while (rp != ev_ring->rp);
+}
+
+/* processing events using tasklet */
+static void gpi_ev_tasklet(unsigned long data)
+{
+	struct gpii *gpii = (struct gpii *)data;
+
+	read_lock_bh(&gpii->pm_lock);
+	if (!REG_ACCESS_VALID(gpii->pm_state)) {
+		read_unlock_bh(&gpii->pm_lock);
+		dev_err(gpii->gpi_dev->dev, "not processing any events, pm_state:%s\n",
+			TO_GPI_PM_STR(gpii->pm_state));
+		return;
+	}
+
+	/* process the events */
+	gpi_process_events(gpii);
+
+	/* enable IEOB, switching back to interrupts */
+	gpi_config_interrupts(gpii, MASK_IEOB_SETTINGS, 1);
+	read_unlock_bh(&gpii->pm_lock);
+}
+
+/* marks all pending events for the channel as stale */
+static void gpi_mark_stale_events(struct gchan *gchan)
+{
+	struct gpii *gpii = gchan->gpii;
+	struct gpi_ring *ev_ring = &gpii->ev_ring;
+	u32 cntxt_rp, local_rp;
+	void *ev_rp;
+
+	cntxt_rp = gpi_read_reg(gpii, gpii->ev_ring_rp_lsb_reg);
+
+	ev_rp = ev_ring->rp;
+	local_rp = (u32)to_physical(ev_ring, ev_rp);
+	while (local_rp != cntxt_rp) {
+		union gpi_event *gpi_event = ev_rp;
+		u32 chid = gpi_event->xfer_compl_event.chid;
+
+		if (chid == gchan->chid)
+			gpi_event->xfer_compl_event.type = STALE_EV_TYPE;
+		ev_rp += ev_ring->el_size;
+		if (ev_rp >= (ev_ring->base + ev_ring->len))
+			ev_rp = ev_ring->base;
+		cntxt_rp = gpi_read_reg(gpii, gpii->ev_ring_rp_lsb_reg);
+		local_rp = (u32)to_physical(ev_ring, ev_rp);
+	}
+}
+
+/* reset sw state and issue channel reset or de-alloc */
+static int gpi_reset_chan(struct gchan *gchan, enum gpi_cmd gpi_cmd)
+{
+	struct gpii *gpii = gchan->gpii;
+	struct gpi_ring *ch_ring = &gchan->ch_ring;
+	unsigned long flags;
+	LIST_HEAD(list);
+	int ret;
+
+	ret = gpi_send_cmd(gpii, gchan, gpi_cmd);
+	if (ret) {
+		dev_err(gpii->gpi_dev->dev, "Error with cmd:%s ret:%d\n",
+			TO_GPI_CMD_STR(gpi_cmd), ret);
+		return ret;
+	}
+
+	/* initialize the local ring ptrs */
+	ch_ring->rp = ch_ring->base;
+	ch_ring->wp = ch_ring->base;
+
+	/* visible to other cores */
+	smp_wmb();
+
+	/* check event ring for any stale events */
+	write_lock_irq(&gpii->pm_lock);
+	gpi_mark_stale_events(gchan);
+
+	/* remove all async descriptors */
+	spin_lock_irqsave(&gchan->vc.lock, flags);
+	vchan_get_all_descriptors(&gchan->vc, &list);
+	spin_unlock_irqrestore(&gchan->vc.lock, flags);
+	write_unlock_irq(&gpii->pm_lock);
+	vchan_dma_desc_free_list(&gchan->vc, &list);
+
+	return 0;
+}
+
+static int gpi_start_chan(struct gchan *gchan)
+{
+	struct gpii *gpii = gchan->gpii;
+	int ret;
+
+	ret = gpi_send_cmd(gpii, gchan, GPI_CH_CMD_START);
+	if (ret) {
+		dev_err(gpii->gpi_dev->dev, "Error with cmd:%s ret:%d\n",
+			TO_GPI_CMD_STR(GPI_CH_CMD_START), ret);
+		return ret;
+	}
+
+	/* gpii CH is active now */
+	write_lock_irq(&gpii->pm_lock);
+	gchan->pm_state = ACTIVE_STATE;
+	write_unlock_irq(&gpii->pm_lock);
+
+	return 0;
+}
+
+static int gpi_stop_chan(struct gchan *gchan)
+{
+	struct gpii *gpii = gchan->gpii;
+	int ret;
+
+	ret = gpi_send_cmd(gpii, gchan, GPI_CH_CMD_STOP);
+	if (ret) {
+		dev_err(gpii->gpi_dev->dev, "Error with cmd:%s ret:%d\n",
+			TO_GPI_CMD_STR(GPI_CH_CMD_STOP), ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+/* allocate and configure the transfer channel */
+static int gpi_alloc_chan(struct gchan *chan, bool send_alloc_cmd)
+{
+	struct gpii *gpii = chan->gpii;
+	struct gpi_ring *ring = &chan->ch_ring;
+	int ret;
+	u32 id = gpii->gpii_id;
+	u32 chid = chan->chid;
+	u32 pair_chid = !chid;
+
+	if (send_alloc_cmd) {
+		ret = gpi_send_cmd(gpii, chan, GPI_CH_CMD_ALLOCATE);
+		if (ret) {
+			dev_err(gpii->gpi_dev->dev, "Error with cmd:%s ret:%d\n",
+				TO_GPI_CMD_STR(GPI_CH_CMD_ALLOCATE), ret);
+			return ret;
+		}
+	}
+
+	gpi_write_reg(gpii, chan->ch_cntxt_base_reg + CNTXT_0_CONFIG,
+		      GPII_n_CH_k_CNTXT_0(ring->el_size, 0, chan->dir, GPI_CHTYPE_PROTO_GPI));
+	gpi_write_reg(gpii, chan->ch_cntxt_base_reg + CNTXT_1_R_LENGTH, ring->len);
+	gpi_write_reg(gpii, chan->ch_cntxt_base_reg + CNTXT_2_RING_BASE_LSB, ring->phys_addr);
+	gpi_write_reg(gpii, chan->ch_cntxt_base_reg + CNTXT_3_RING_BASE_MSB,
+		      upper_32_bits(ring->phys_addr));
+	gpi_write_reg(gpii, chan->ch_cntxt_db_reg + CNTXT_5_RING_RP_MSB - CNTXT_4_RING_RP_LSB,
+		      upper_32_bits(ring->phys_addr));
+	gpi_write_reg(gpii, gpii->regs + GPII_n_CH_k_SCRATCH_0_OFFS(id, chid),
+		      GPII_n_CH_k_SCRATCH_0(pair_chid, chan->protocol, chan->seid));
+	gpi_write_reg(gpii, gpii->regs + GPII_n_CH_k_SCRATCH_1_OFFS(id, chid), 0);
+	gpi_write_reg(gpii, gpii->regs + GPII_n_CH_k_SCRATCH_2_OFFS(id, chid), 0);
+	gpi_write_reg(gpii, gpii->regs + GPII_n_CH_k_SCRATCH_3_OFFS(id, chid), 0);
+	gpi_write_reg(gpii, gpii->regs + GPII_n_CH_k_QOS_OFFS(id, chid), 1);
+
+	/* flush all the writes */
+	wmb();
+	return 0;
+}
+
+/* allocate and configure event ring */
+static int gpi_alloc_ev_chan(struct gpii *gpii)
+{
+	struct gpi_ring *ring = &gpii->ev_ring;
+	void __iomem *base = gpii->ev_cntxt_base_reg;
+	int ret;
+
+	ret = gpi_send_cmd(gpii, NULL, GPI_EV_CMD_ALLOCATE);
+	if (ret) {
+		dev_err(gpii->gpi_dev->dev, "error with cmd:%s ret:%d\n",
+			TO_GPI_CMD_STR(GPI_EV_CMD_ALLOCATE), ret);
+		return ret;
+	}
+
+	/* program event context */
+	gpi_write_reg(gpii, base + CNTXT_0_CONFIG,
+		      GPII_n_EV_k_CNTXT_0(ring->el_size, GPI_INTTYPE_IRQ, GPI_CHTYPE_GPI_EV));
+	gpi_write_reg(gpii, base + CNTXT_1_R_LENGTH, ring->len);
+	gpi_write_reg(gpii, base + CNTXT_2_RING_BASE_LSB, lower_32_bits(ring->phys_addr));
+	gpi_write_reg(gpii, base + CNTXT_3_RING_BASE_MSB, upper_32_bits(ring->phys_addr));
+	gpi_write_reg(gpii, gpii->ev_cntxt_db_reg + CNTXT_5_RING_RP_MSB - CNTXT_4_RING_RP_LSB,
+		      upper_32_bits(ring->phys_addr));
+	gpi_write_reg(gpii, base + CNTXT_8_RING_INT_MOD, 0);
+	gpi_write_reg(gpii, base + CNTXT_10_RING_MSI_LSB, 0);
+	gpi_write_reg(gpii, base + CNTXT_11_RING_MSI_MSB, 0);
+	gpi_write_reg(gpii, base + CNTXT_8_RING_INT_MOD, 0);
+	gpi_write_reg(gpii, base + CNTXT_12_RING_RP_UPDATE_LSB, 0);
+	gpi_write_reg(gpii, base + CNTXT_13_RING_RP_UPDATE_MSB, 0);
+
+	/* add events to ring */
+	ring->wp = (ring->base + ring->len - ring->el_size);
+
+	/* flush all the writes */
+	wmb();
+
+	/* gpii is active now */
+	write_lock_irq(&gpii->pm_lock);
+	gpii->pm_state = ACTIVE_STATE;
+	write_unlock_irq(&gpii->pm_lock);
+	gpi_write_ev_db(gpii, ring, ring->wp);
+
+	return 0;
+}
+
+/* calculate # of ERE/TRE available to queue */
+static int gpi_ring_num_elements_avail(const struct gpi_ring * const ring)
+{
+	int elements = 0;
+
+	if (ring->wp < ring->rp) {
+		elements = ((ring->rp - ring->wp) / ring->el_size) - 1;
+	} else {
+		elements = (ring->rp - ring->base) / ring->el_size;
+		elements += ((ring->base + ring->len - ring->wp) / ring->el_size) - 1;
+	}
+
+	return elements;
+}
+
+static int gpi_ring_add_element(struct gpi_ring *ring, void **wp)
+{
+	if (gpi_ring_num_elements_avail(ring) <= 0)
+		return -ENOMEM;
+
+	*wp = ring->wp;
+	ring->wp += ring->el_size;
+	if (ring->wp  >= (ring->base + ring->len))
+		ring->wp = ring->base;
+
+	/* visible to other cores */
+	smp_wmb();
+
+	return 0;
+}
+
+static void gpi_ring_recycle_ev_element(struct gpi_ring *ring)
+{
+	/* Update the WP */
+	ring->wp += ring->el_size;
+	if (ring->wp  >= (ring->base + ring->len))
+		ring->wp = ring->base;
+
+	/* Update the RP */
+	ring->rp += ring->el_size;
+	if (ring->rp  >= (ring->base + ring->len))
+		ring->rp = ring->base;
+
+	/* visible to other cores */
+	smp_wmb();
+}
+
+static void gpi_free_ring(struct gpi_ring *ring,
+			  struct gpii *gpii)
+{
+	dma_free_coherent(gpii->gpi_dev->dev, ring->alloc_size,
+			  ring->pre_aligned, ring->dma_handle);
+	memset(ring, 0, sizeof(*ring));
+}
+
+/* allocate memory for transfer and event rings */
+static int gpi_alloc_ring(struct gpi_ring *ring, u32 elements,
+			  u32 el_size, struct gpii *gpii)
+{
+	u64 len = elements * el_size;
+	int bit;
+
+	/* ring len must be power of 2 */
+	bit = find_last_bit((unsigned long *)&len, 32);
+	if (((1 << bit) - 1) & len)
+		bit++;
+	len = 1 << bit;
+	ring->alloc_size = (len + (len - 1));
+	dev_dbg(gpii->gpi_dev->dev,
+		"#el:%u el_size:%u len:%u actual_len:%llu alloc_size:%lu\n",
+		  elements, el_size, (elements * el_size), len,
+		  ring->alloc_size);
+
+	ring->pre_aligned = dma_alloc_coherent(gpii->gpi_dev->dev,
+					       ring->alloc_size,
+					       &ring->dma_handle, GFP_KERNEL);
+	if (!ring->pre_aligned) {
+		dev_err(gpii->gpi_dev->dev, "could not alloc size:%lu mem for ring\n",
+			ring->alloc_size);
+		return -ENOMEM;
+	}
+
+	/* align the physical mem */
+	ring->phys_addr = (ring->dma_handle + (len - 1)) & ~(len - 1);
+	ring->base = ring->pre_aligned + (ring->phys_addr - ring->dma_handle);
+	ring->rp = ring->base;
+	ring->wp = ring->base;
+	ring->len = len;
+	ring->el_size = el_size;
+	ring->elements = ring->len / ring->el_size;
+	memset(ring->base, 0, ring->len);
+	ring->configured = true;
+
+	/* update to other cores */
+	smp_wmb();
+
+	dev_dbg(gpii->gpi_dev->dev,
+		"phy_pre:0x%0llx phy_alig:0x%0llx len:%u el_size:%u elements:%u\n",
+		ring->dma_handle, ring->phys_addr, ring->len,
+		ring->el_size, ring->elements);
+
+	return 0;
+}
+
+/* copy tre into transfer ring */
+static void gpi_queue_xfer(struct gpii *gpii, struct gchan *gchan,
+			   struct gpi_tre *gpi_tre, void **wp)
+{
+	struct gpi_tre *ch_tre;
+	int ret;
+
+	/* get next tre location we can copy */
+	ret = gpi_ring_add_element(&gchan->ch_ring, (void **)&ch_tre);
+	if (unlikely(ret)) {
+		dev_err(gpii->gpi_dev->dev, "Error adding ring element to xfer ring\n");
+		return;
+	}
+
+	/* copy the tre info */
+	memcpy(ch_tre, gpi_tre, sizeof(*ch_tre));
+	*wp = ch_tre;
+}
+
+/* reset and restart transfer channel */
+static int gpi_terminate_all(struct dma_chan *chan)
+{
+	struct gchan *gchan = to_gchan(chan);
+	struct gpii *gpii = gchan->gpii;
+	int schid, echid, i;
+	int ret = 0;
+
+	mutex_lock(&gpii->ctrl_lock);
+
+	/*
+	 * treat both channels as a group if its protocol is not UART
+	 * STOP, RESET, or START needs to be in lockstep
+	 */
+	schid = (gchan->protocol == QCOM_GPI_UART) ? gchan->chid : 0;
+	echid = (gchan->protocol == QCOM_GPI_UART) ? schid + 1 : MAX_CHANNELS_PER_GPII;
+
+	/* stop the channel */
+	for (i = schid; i < echid; i++) {
+		gchan = &gpii->gchan[i];
+
+		/* disable ch state so no more TRE processing */
+		write_lock_irq(&gpii->pm_lock);
+		gchan->pm_state = PREPARE_TERMINATE;
+		write_unlock_irq(&gpii->pm_lock);
+
+		/* send command to Stop the channel */
+		ret = gpi_stop_chan(gchan);
+	}
+
+	/* reset the channels (clears any pending tre) */
+	for (i = schid; i < echid; i++) {
+		gchan = &gpii->gchan[i];
+
+		ret = gpi_reset_chan(gchan, GPI_CH_CMD_RESET);
+		if (ret) {
+			dev_err(gpii->gpi_dev->dev, "Error resetting channel ret:%d\n", ret);
+			goto terminate_exit;
+		}
+
+		/* reprogram channel CNTXT */
+		ret = gpi_alloc_chan(gchan, false);
+		if (ret) {
+			dev_err(gpii->gpi_dev->dev, "Error alloc_channel ret:%d\n", ret);
+			goto terminate_exit;
+		}
+	}
+
+	/* restart the channels */
+	for (i = schid; i < echid; i++) {
+		gchan = &gpii->gchan[i];
+
+		ret = gpi_start_chan(gchan);
+		if (ret) {
+			dev_err(gpii->gpi_dev->dev, "Error Starting Channel ret:%d\n", ret);
+			goto terminate_exit;
+		}
+	}
+
+terminate_exit:
+	mutex_unlock(&gpii->ctrl_lock);
+	return ret;
+}
+
+/* pause dma transfer for all channels */
+static int gpi_pause(struct dma_chan *chan)
+{
+	struct gchan *gchan = to_gchan(chan);
+	struct gpii *gpii = gchan->gpii;
+	int i, ret;
+
+	mutex_lock(&gpii->ctrl_lock);
+
+	/*
+	 * pause/resume are per gpii not per channel, so
+	 * client needs to call pause only once
+	 */
+	if (gpii->pm_state == PAUSE_STATE) {
+		dev_dbg(gpii->gpi_dev->dev, "channel is already paused\n");
+		mutex_unlock(&gpii->ctrl_lock);
+		return 0;
+	}
+
+	/* send stop command to stop the channels */
+	for (i = 0; i < MAX_CHANNELS_PER_GPII; i++) {
+		ret = gpi_stop_chan(&gpii->gchan[i]);
+		if (ret) {
+			mutex_unlock(&gpii->ctrl_lock);
+			return ret;
+		}
+	}
+
+	disable_irq(gpii->irq);
+
+	/* Wait for threads to complete out */
+	tasklet_kill(&gpii->ev_task);
+
+	write_lock_irq(&gpii->pm_lock);
+	gpii->pm_state = PAUSE_STATE;
+	write_unlock_irq(&gpii->pm_lock);
+	mutex_unlock(&gpii->ctrl_lock);
+
+	return 0;
+}
+
+/* resume dma transfer */
+static int gpi_resume(struct dma_chan *chan)
+{
+	struct gchan *gchan = to_gchan(chan);
+	struct gpii *gpii = gchan->gpii;
+	int i, ret;
+
+	mutex_lock(&gpii->ctrl_lock);
+	if (gpii->pm_state == ACTIVE_STATE) {
+		dev_dbg(gpii->gpi_dev->dev, "channel is already active\n");
+		mutex_unlock(&gpii->ctrl_lock);
+		return 0;
+	}
+
+	enable_irq(gpii->irq);
+
+	/* send start command to start the channels */
+	for (i = 0; i < MAX_CHANNELS_PER_GPII; i++) {
+		ret = gpi_send_cmd(gpii, &gpii->gchan[i], GPI_CH_CMD_START);
+		if (ret) {
+			dev_err(gpii->gpi_dev->dev, "Error starting chan, ret:%d\n", ret);
+			mutex_unlock(&gpii->ctrl_lock);
+			return ret;
+		}
+	}
+
+	write_lock_irq(&gpii->pm_lock);
+	gpii->pm_state = ACTIVE_STATE;
+	write_unlock_irq(&gpii->pm_lock);
+	mutex_unlock(&gpii->ctrl_lock);
+
+	return 0;
+}
+
+static void gpi_desc_free(struct virt_dma_desc *vd)
+{
+	struct gpi_desc *gpi_desc = to_gpi_desc(vd);
+
+	kfree(gpi_desc);
+	gpi_desc = NULL;
+}
+
+static int
+gpi_peripheral_config(struct dma_chan *chan, struct dma_slave_config *config)
+{
+	struct gchan *gchan = to_gchan(chan);
+
+	if (!config->peripheral_config)
+		return -EINVAL;
+
+	gchan->config = krealloc(gchan->config, config->peripheral_size, GFP_NOWAIT);
+	if (!gchan->config)
+		return -ENOMEM;
+
+	memcpy(gchan->config, config->peripheral_config, config->peripheral_size);
+
+	return 0;
+}
+
+static int gpi_create_i2c_tre(struct gchan *chan, struct gpi_desc *desc,
+			      struct scatterlist *sgl, enum dma_transfer_direction direction)
+{
+	struct gpi_i2c_config *i2c = chan->config;
+	struct device *dev = chan->gpii->gpi_dev->dev;
+	unsigned int tre_idx = 0;
+	dma_addr_t address;
+	struct gpi_tre *tre;
+	unsigned int i;
+
+	/* first create config tre if applicable */
+	if (i2c->set_config) {
+		tre = &desc->tre[tre_idx];
+		tre_idx++;
+
+		tre->dword[0] = u32_encode_bits(i2c->low_count, TRE_I2C_C0_TLOW);
+		tre->dword[0] |= u32_encode_bits(i2c->high_count, TRE_I2C_C0_THIGH);
+		tre->dword[0] |= u32_encode_bits(i2c->cycle_count, TRE_I2C_C0_TCYL);
+		tre->dword[0] |= u32_encode_bits(i2c->pack_enable, TRE_I2C_C0_TX_PACK);
+		tre->dword[0] |= u32_encode_bits(i2c->pack_enable, TRE_I2C_C0_RX_PACK);
+
+		tre->dword[1] = 0;
+
+		tre->dword[2] = u32_encode_bits(i2c->clk_div, TRE_C0_CLK_DIV);
+
+		tre->dword[3] = u32_encode_bits(TRE_TYPE_CONFIG0, TRE_FLAGS_TYPE);
+		tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_CHAIN);
+	}
+
+	/* create the GO tre for Tx */
+	if (i2c->op == I2C_WRITE) {
+		tre = &desc->tre[tre_idx];
+		tre_idx++;
+
+		if (i2c->multi_msg)
+			tre->dword[0] = u32_encode_bits(I2C_READ, TRE_I2C_GO_CMD);
+		else
+			tre->dword[0] = u32_encode_bits(i2c->op, TRE_I2C_GO_CMD);
+
+		tre->dword[0] |= u32_encode_bits(i2c->addr, TRE_I2C_GO_ADDR);
+		tre->dword[0] |= u32_encode_bits(i2c->stretch, TRE_I2C_GO_STRETCH);
+
+		tre->dword[1] = 0;
+		tre->dword[2] = u32_encode_bits(i2c->rx_len, TRE_RX_LEN);
+
+		tre->dword[3] = u32_encode_bits(TRE_TYPE_GO, TRE_FLAGS_TYPE);
+
+		if (i2c->multi_msg)
+			tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_LINK);
+		else
+			tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_CHAIN);
+	}
+
+	if (i2c->op == I2C_READ || i2c->multi_msg == false) {
+		/* create the DMA TRE */
+		tre = &desc->tre[tre_idx];
+		tre_idx++;
+
+		address = sg_dma_address(sgl);
+		tre->dword[0] = lower_32_bits(address);
+		tre->dword[1] = upper_32_bits(address);
+
+		tre->dword[2] = u32_encode_bits(sg_dma_len(sgl), TRE_DMA_LEN);
+
+		tre->dword[3] = u32_encode_bits(TRE_TYPE_DMA, TRE_FLAGS_TYPE);
+		tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_IEOT);
+	};
+
+	for (i = 0; i < tre_idx; i++)
+		dev_dbg(dev, "TRE:%d %x:%x:%x:%x\n", i, desc->tre[i].dword[0],
+			desc->tre[i].dword[1], desc->tre[i].dword[2], desc->tre[i].dword[3]);
+
+	return tre_idx;
+}
+
+static int gpi_create_spi_tre(struct gchan *chan, struct gpi_desc *desc,
+			      struct scatterlist *sgl, enum dma_transfer_direction direction)
+{
+	struct gpi_spi_config *spi = chan->config;
+	struct device *dev = chan->gpii->gpi_dev->dev;
+	unsigned int tre_idx = 0;
+	dma_addr_t address;
+	struct gpi_tre *tre;
+	unsigned int i;
+
+	/* first create config tre if applicable */
+	if (direction == DMA_MEM_TO_DEV && spi->set_config) {
+		tre = &desc->tre[tre_idx];
+		tre_idx++;
+
+		tre->dword[0] = u32_encode_bits(spi->word_len, TRE_SPI_C0_WORD_SZ);
+		tre->dword[0] |= u32_encode_bits(spi->loopback_en, TRE_SPI_C0_LOOPBACK);
+		tre->dword[0] |= u32_encode_bits(spi->clock_pol_high, TRE_SPI_C0_CPOL);
+		tre->dword[0] |= u32_encode_bits(spi->data_pol_high, TRE_SPI_C0_CPHA);
+		tre->dword[0] |= u32_encode_bits(spi->pack_en, TRE_SPI_C0_TX_PACK);
+		tre->dword[0] |= u32_encode_bits(spi->pack_en, TRE_SPI_C0_RX_PACK);
+
+		tre->dword[1] = 0;
+
+		tre->dword[2] = u32_encode_bits(spi->clk_div, TRE_C0_CLK_DIV);
+		tre->dword[2] |= u32_encode_bits(spi->clk_src, TRE_C0_CLK_SRC);
+
+		tre->dword[3] = u32_encode_bits(TRE_TYPE_CONFIG0, TRE_FLAGS_TYPE);
+		tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_CHAIN);
+	}
+
+	/* create the GO tre for Tx */
+	if (direction == DMA_MEM_TO_DEV) {
+		tre = &desc->tre[tre_idx];
+		tre_idx++;
+
+		tre->dword[0] = u32_encode_bits(spi->fragmentation, TRE_SPI_GO_FRAG);
+		tre->dword[0] |= u32_encode_bits(spi->cs, TRE_SPI_GO_CS);
+		tre->dword[0] |= u32_encode_bits(spi->cmd, TRE_SPI_GO_CMD);
+
+		tre->dword[1] = 0;
+
+		tre->dword[2] = u32_encode_bits(spi->rx_len, TRE_RX_LEN);
+
+		tre->dword[3] = u32_encode_bits(TRE_TYPE_GO, TRE_FLAGS_TYPE);
+		if (spi->cmd == SPI_RX)
+			tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_IEOB);
+		else
+			tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_CHAIN);
+	}
+
+	/* create the dma tre */
+	tre = &desc->tre[tre_idx];
+	tre_idx++;
+
+	address = sg_dma_address(sgl);
+	tre->dword[0] = lower_32_bits(address);
+	tre->dword[1] = upper_32_bits(address);
+
+	tre->dword[2] = u32_encode_bits(sg_dma_len(sgl), TRE_DMA_LEN);
+
+	tre->dword[3] = u32_encode_bits(TRE_TYPE_DMA, TRE_FLAGS_TYPE);
+	if (direction == DMA_MEM_TO_DEV)
+		tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_IEOT);
+
+	for (i = 0; i < tre_idx; i++)
+		dev_dbg(dev, "TRE:%d %x:%x:%x:%x\n", i, desc->tre[i].dword[0],
+			desc->tre[i].dword[1], desc->tre[i].dword[2], desc->tre[i].dword[3]);
+
+	return tre_idx;
+}
+
+/* copy tre into transfer ring */
+static struct dma_async_tx_descriptor *
+gpi_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
+		  unsigned int sg_len, enum dma_transfer_direction direction,
+		  unsigned long flags, void *context)
+{
+	struct gchan *gchan = to_gchan(chan);
+	struct gpii *gpii = gchan->gpii;
+	struct device *dev = gpii->gpi_dev->dev;
+	struct gpi_ring *ch_ring = &gchan->ch_ring;
+	struct gpi_desc *gpi_desc;
+	u32 nr, nr_tre = 0;
+	u8 set_config;
+	int i;
+
+	gpii->ieob_set = false;
+	if (!is_slave_direction(direction)) {
+		dev_err(gpii->gpi_dev->dev, "invalid dma direction: %d\n", direction);
+		return NULL;
+	}
+
+	if (sg_len > 1) {
+		dev_err(dev, "Multi sg sent, we support only one atm: %d\n", sg_len);
+		return NULL;
+	}
+
+	nr_tre = 3;
+	set_config = *(u32 *)gchan->config;
+	if (!set_config)
+		nr_tre = 2;
+	if (direction == DMA_DEV_TO_MEM) /* rx */
+		nr_tre = 1;
+
+	/* calculate # of elements required & available */
+	nr = gpi_ring_num_elements_avail(ch_ring);
+	if (nr < nr_tre) {
+		dev_err(dev, "not enough space in ring, avail:%u required:%u\n", nr, nr_tre);
+		return NULL;
+	}
+
+	gpi_desc = kzalloc(sizeof(*gpi_desc), GFP_NOWAIT);
+	if (!gpi_desc)
+		return NULL;
+
+	/* create TREs for xfer */
+	if (gchan->protocol == QCOM_GPI_SPI) {
+		i = gpi_create_spi_tre(gchan, gpi_desc, sgl, direction);
+	} else if (gchan->protocol == QCOM_GPI_I2C) {
+		i = gpi_create_i2c_tre(gchan, gpi_desc, sgl, direction);
+	} else {
+		dev_err(dev, "invalid peripheral: %d\n", gchan->protocol);
+		kfree(gpi_desc);
+		return NULL;
+	}
+
+	/* set up the descriptor */
+	gpi_desc->gchan = gchan;
+	gpi_desc->len = sg_dma_len(sgl);
+	gpi_desc->num_tre  = i;
+
+	return vchan_tx_prep(&gchan->vc, &gpi_desc->vd, flags);
+}
+
+/* rings transfer ring db to being transfer */
+static void gpi_issue_pending(struct dma_chan *chan)
+{
+	struct gchan *gchan = to_gchan(chan);
+	struct gpii *gpii = gchan->gpii;
+	unsigned long flags, pm_lock_flags;
+	struct virt_dma_desc *vd = NULL;
+	struct gpi_desc *gpi_desc;
+	struct gpi_ring *ch_ring = &gchan->ch_ring;
+	void *tre, *wp = NULL;
+	int i;
+
+	read_lock_irqsave(&gpii->pm_lock, pm_lock_flags);
+
+	/* move all submitted discriptors to issued list */
+	spin_lock_irqsave(&gchan->vc.lock, flags);
+	if (vchan_issue_pending(&gchan->vc))
+		vd = list_last_entry(&gchan->vc.desc_issued,
+				     struct virt_dma_desc, node);
+	spin_unlock_irqrestore(&gchan->vc.lock, flags);
+
+	/* nothing to do list is empty */
+	if (!vd) {
+		read_unlock_irqrestore(&gpii->pm_lock, pm_lock_flags);
+		return;
+	}
+
+	gpi_desc = to_gpi_desc(vd);
+	for (i = 0; i < gpi_desc->num_tre; i++) {
+		tre = &gpi_desc->tre[i];
+		gpi_queue_xfer(gpii, gchan, tre, &wp);
+	}
+
+	gpi_desc->db = ch_ring->wp;
+	gpi_write_ch_db(gchan, &gchan->ch_ring, gpi_desc->db);
+	read_unlock_irqrestore(&gpii->pm_lock, pm_lock_flags);
+}
+
+static int gpi_ch_init(struct gchan *gchan)
+{
+	struct gpii *gpii = gchan->gpii;
+	const int ev_factor = gpii->gpi_dev->ev_factor;
+	u32 elements;
+	int i = 0, ret = 0;
+
+	gchan->pm_state = CONFIG_STATE;
+
+	/* check if both channels are configured before continue */
+	for (i = 0; i < MAX_CHANNELS_PER_GPII; i++)
+		if (gpii->gchan[i].pm_state != CONFIG_STATE)
+			goto exit_gpi_init;
+
+	/* protocol must be same for both channels */
+	if (gpii->gchan[0].protocol != gpii->gchan[1].protocol) {
+		dev_err(gpii->gpi_dev->dev, "protocol did not match protocol %u != %u\n",
+			gpii->gchan[0].protocol, gpii->gchan[1].protocol);
+		ret = -EINVAL;
+		goto exit_gpi_init;
+	}
+
+	/* allocate memory for event ring */
+	elements = CHAN_TRES << ev_factor;
+	ret = gpi_alloc_ring(&gpii->ev_ring, elements,
+			     sizeof(union gpi_event), gpii);
+	if (ret)
+		goto exit_gpi_init;
+
+	/* configure interrupts */
+	write_lock_irq(&gpii->pm_lock);
+	gpii->pm_state = PREPARE_HARDWARE;
+	write_unlock_irq(&gpii->pm_lock);
+	ret = gpi_config_interrupts(gpii, DEFAULT_IRQ_SETTINGS, 0);
+	if (ret) {
+		dev_err(gpii->gpi_dev->dev, "error config. interrupts, ret:%d\n", ret);
+		goto error_config_int;
+	}
+
+	/* allocate event rings */
+	ret = gpi_alloc_ev_chan(gpii);
+	if (ret) {
+		dev_err(gpii->gpi_dev->dev, "error alloc_ev_chan:%d\n", ret);
+		goto error_alloc_ev_ring;
+	}
+
+	/* Allocate all channels */
+	for (i = 0; i < MAX_CHANNELS_PER_GPII; i++) {
+		ret = gpi_alloc_chan(&gpii->gchan[i], true);
+		if (ret) {
+			dev_err(gpii->gpi_dev->dev, "Error allocating chan:%d\n", ret);
+			goto error_alloc_chan;
+		}
+	}
+
+	/* start channels  */
+	for (i = 0; i < MAX_CHANNELS_PER_GPII; i++) {
+		ret = gpi_start_chan(&gpii->gchan[i]);
+		if (ret) {
+			dev_err(gpii->gpi_dev->dev, "Error start chan:%d\n", ret);
+			goto error_start_chan;
+		}
+	}
+	return ret;
+
+error_start_chan:
+	for (i = i - 1; i >= 0; i++) {
+		gpi_stop_chan(&gpii->gchan[i]);
+		gpi_send_cmd(gpii, gchan, GPI_CH_CMD_RESET);
+	}
+	i = 2;
+error_alloc_chan:
+	for (i = i - 1; i >= 0; i--)
+		gpi_reset_chan(gchan, GPI_CH_CMD_DE_ALLOC);
+error_alloc_ev_ring:
+	gpi_disable_interrupts(gpii);
+error_config_int:
+	gpi_free_ring(&gpii->ev_ring, gpii);
+exit_gpi_init:
+	mutex_unlock(&gpii->ctrl_lock);
+	return ret;
+}
+
+/* release all channel resources */
+static void gpi_free_chan_resources(struct dma_chan *chan)
+{
+	struct gchan *gchan = to_gchan(chan);
+	struct gpii *gpii = gchan->gpii;
+	enum gpi_pm_state cur_state;
+	int ret, i;
+
+	mutex_lock(&gpii->ctrl_lock);
+
+	cur_state = gchan->pm_state;
+
+	/* disable ch state so no more TRE processing for this channel */
+	write_lock_irq(&gpii->pm_lock);
+	gchan->pm_state = PREPARE_TERMINATE;
+	write_unlock_irq(&gpii->pm_lock);
+
+	/* attempt to do graceful hardware shutdown */
+	if (cur_state == ACTIVE_STATE) {
+		gpi_stop_chan(gchan);
+
+		ret = gpi_send_cmd(gpii, gchan, GPI_CH_CMD_RESET);
+		if (ret)
+			dev_err(gpii->gpi_dev->dev, "error resetting channel:%d\n", ret);
+
+		gpi_reset_chan(gchan, GPI_CH_CMD_DE_ALLOC);
+	}
+
+	/* free all allocated memory */
+	gpi_free_ring(&gchan->ch_ring, gpii);
+	vchan_free_chan_resources(&gchan->vc);
+	kfree(gchan->config);
+
+	write_lock_irq(&gpii->pm_lock);
+	gchan->pm_state = DISABLE_STATE;
+	write_unlock_irq(&gpii->pm_lock);
+
+	/* if other rings are still active exit */
+	for (i = 0; i < MAX_CHANNELS_PER_GPII; i++)
+		if (gpii->gchan[i].ch_ring.configured)
+			goto exit_free;
+
+	/* deallocate EV Ring */
+	cur_state = gpii->pm_state;
+	write_lock_irq(&gpii->pm_lock);
+	gpii->pm_state = PREPARE_TERMINATE;
+	write_unlock_irq(&gpii->pm_lock);
+
+	/* wait for threads to complete out */
+	tasklet_kill(&gpii->ev_task);
+
+	/* send command to de allocate event ring */
+	if (cur_state == ACTIVE_STATE)
+		gpi_send_cmd(gpii, NULL, GPI_EV_CMD_DEALLOC);
+
+	gpi_free_ring(&gpii->ev_ring, gpii);
+
+	/* disable interrupts */
+	if (cur_state == ACTIVE_STATE)
+		gpi_disable_interrupts(gpii);
+
+	/* set final state to disable */
+	write_lock_irq(&gpii->pm_lock);
+	gpii->pm_state = DISABLE_STATE;
+	write_unlock_irq(&gpii->pm_lock);
+
+exit_free:
+	mutex_unlock(&gpii->ctrl_lock);
+}
+
+/* allocate channel resources */
+static int gpi_alloc_chan_resources(struct dma_chan *chan)
+{
+	struct gchan *gchan = to_gchan(chan);
+	struct gpii *gpii = gchan->gpii;
+	int ret;
+
+	mutex_lock(&gpii->ctrl_lock);
+
+	/* allocate memory for transfer ring */
+	ret = gpi_alloc_ring(&gchan->ch_ring, CHAN_TRES,
+			     sizeof(struct gpi_tre), gpii);
+	if (ret)
+		goto xfer_alloc_err;
+
+	ret = gpi_ch_init(gchan);
+
+	mutex_unlock(&gpii->ctrl_lock);
+
+	return ret;
+xfer_alloc_err:
+	mutex_unlock(&gpii->ctrl_lock);
+
+	return ret;
+}
+
+static int gpi_find_avail_gpii(struct gpi_dev *gpi_dev, u32 seid)
+{
+	struct gchan *tx_chan, *rx_chan;
+	unsigned int gpii;
+
+	/* check if same seid is already configured for another chid */
+	for (gpii = 0; gpii < gpi_dev->max_gpii; gpii++) {
+		if (!((1 << gpii) & gpi_dev->gpii_mask))
+			continue;
+
+		tx_chan = &gpi_dev->gpiis[gpii].gchan[GPI_TX_CHAN];
+		rx_chan = &gpi_dev->gpiis[gpii].gchan[GPI_RX_CHAN];
+
+		if (rx_chan->vc.chan.client_count && rx_chan->seid == seid)
+			return gpii;
+		if (tx_chan->vc.chan.client_count && tx_chan->seid == seid)
+			return gpii;
+	}
+
+	/* no channels configured with same seid, return next avail gpii */
+	for (gpii = 0; gpii < gpi_dev->max_gpii; gpii++) {
+		if (!((1 << gpii) & gpi_dev->gpii_mask))
+			continue;
+
+		tx_chan = &gpi_dev->gpiis[gpii].gchan[GPI_TX_CHAN];
+		rx_chan = &gpi_dev->gpiis[gpii].gchan[GPI_RX_CHAN];
+
+		/* check if gpii is configured */
+		if (tx_chan->vc.chan.client_count ||
+		    rx_chan->vc.chan.client_count)
+			continue;
+
+		/* found a free gpii */
+		return gpii;
+	}
+
+	/* no gpii instance available to use */
+	return -EIO;
+}
+
+/* gpi_of_dma_xlate: open client requested channel */
+static struct dma_chan *gpi_of_dma_xlate(struct of_phandle_args *args,
+					 struct of_dma *of_dma)
+{
+	struct gpi_dev *gpi_dev = (struct gpi_dev *)of_dma->of_dma_data;
+	u32 seid, chid;
+	int gpii;
+	struct gchan *gchan;
+
+	if (args->args_count < 3) {
+		dev_err(gpi_dev->dev, "gpii require minimum 2 args, client passed:%d args\n",
+			args->args_count);
+		return NULL;
+	}
+
+	chid = args->args[0];
+	if (chid >= MAX_CHANNELS_PER_GPII) {
+		dev_err(gpi_dev->dev, "gpii channel:%d not valid\n", chid);
+		return NULL;
+	}
+
+	seid = args->args[1];
+
+	/* find next available gpii to use */
+	gpii = gpi_find_avail_gpii(gpi_dev, seid);
+	if (gpii < 0) {
+		dev_err(gpi_dev->dev, "no available gpii instances\n");
+		return NULL;
+	}
+
+	gchan = &gpi_dev->gpiis[gpii].gchan[chid];
+	if (gchan->vc.chan.client_count) {
+		dev_err(gpi_dev->dev, "gpii:%d chid:%d seid:%d already configured\n",
+			gpii, chid, gchan->seid);
+		return NULL;
+	}
+
+	gchan->seid = seid;
+	gchan->protocol = args->args[2];
+
+	return dma_get_slave_channel(&gchan->vc.chan);
+}
+
+static int gpi_probe(struct platform_device *pdev)
+{
+	struct gpi_dev *gpi_dev;
+	unsigned int i;
+	int ret;
+
+	gpi_dev = devm_kzalloc(&pdev->dev, sizeof(*gpi_dev), GFP_KERNEL);
+	if (!gpi_dev)
+		return -ENOMEM;
+
+	gpi_dev->dev = &pdev->dev;
+	gpi_dev->res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	gpi_dev->regs = devm_ioremap_resource(gpi_dev->dev, gpi_dev->res);
+	if (IS_ERR(gpi_dev->regs))
+		return PTR_ERR(gpi_dev->regs);
+	gpi_dev->ee_base = gpi_dev->regs;
+
+	ret = of_property_read_u32(gpi_dev->dev->of_node, "dma-channels",
+				   &gpi_dev->max_gpii);
+	if (ret) {
+		dev_err(gpi_dev->dev, "missing 'max-no-gpii' DT node\n");
+		return ret;
+	}
+
+	ret = of_property_read_u32(gpi_dev->dev->of_node, "dma-channel-mask",
+				   &gpi_dev->gpii_mask);
+	if (ret) {
+		dev_err(gpi_dev->dev, "missing 'gpii-mask' DT node\n");
+		return ret;
+	}
+
+	gpi_dev->ev_factor = EV_FACTOR;
+
+	ret = dma_set_mask(gpi_dev->dev, DMA_BIT_MASK(64));
+	if (ret) {
+		dev_err(gpi_dev->dev, "Error setting dma_mask to 64, ret:%d\n", ret);
+		return ret;
+	}
+
+	gpi_dev->gpiis = devm_kzalloc(gpi_dev->dev, sizeof(*gpi_dev->gpiis) *
+				      gpi_dev->max_gpii, GFP_KERNEL);
+	if (!gpi_dev->gpiis)
+		return -ENOMEM;
+
+	/* setup all the supported gpii */
+	INIT_LIST_HEAD(&gpi_dev->dma_device.channels);
+	for (i = 0; i < gpi_dev->max_gpii; i++) {
+		struct gpii *gpii = &gpi_dev->gpiis[i];
+		int chan;
+
+		if (!((1 << i) & gpi_dev->gpii_mask))
+			continue;
+
+		/* set up ev cntxt register map */
+		gpii->ev_cntxt_base_reg = gpi_dev->ee_base + GPII_n_EV_CH_k_CNTXT_0_OFFS(i, 0);
+		gpii->ev_cntxt_db_reg = gpi_dev->ee_base + GPII_n_EV_CH_k_DOORBELL_0_OFFS(i, 0);
+		gpii->ev_ring_rp_lsb_reg = gpii->ev_cntxt_base_reg + CNTXT_4_RING_RP_LSB;
+		gpii->ev_cmd_reg = gpi_dev->ee_base + GPII_n_EV_CH_CMD_OFFS(i);
+		gpii->ieob_clr_reg = gpi_dev->ee_base + GPII_n_CNTXT_SRC_IEOB_IRQ_CLR_OFFS(i);
+
+		/* set up irq */
+		ret = platform_get_irq(pdev, i);
+		if (ret < 0) {
+			dev_err(gpi_dev->dev, "platform_get_irq failed for %d:%d\n", i, ret);
+			return ret;
+		}
+		gpii->irq = ret;
+
+		/* set up channel specific register info */
+		for (chan = 0; chan < MAX_CHANNELS_PER_GPII; chan++) {
+			struct gchan *gchan = &gpii->gchan[chan];
+
+			/* set up ch cntxt register map */
+			gchan->ch_cntxt_base_reg = gpi_dev->ee_base +
+				GPII_n_CH_k_CNTXT_0_OFFS(i, chan);
+			gchan->ch_cntxt_db_reg = gpi_dev->ee_base +
+				GPII_n_CH_k_DOORBELL_0_OFFS(i, chan);
+			gchan->ch_cmd_reg = gpi_dev->ee_base + GPII_n_CH_CMD_OFFS(i);
+
+			/* vchan setup */
+			vchan_init(&gchan->vc, &gpi_dev->dma_device);
+			gchan->vc.desc_free = gpi_desc_free;
+			gchan->chid = chan;
+			gchan->gpii = gpii;
+			gchan->dir = GPII_CHAN_DIR[chan];
+		}
+		mutex_init(&gpii->ctrl_lock);
+		rwlock_init(&gpii->pm_lock);
+		tasklet_init(&gpii->ev_task, gpi_ev_tasklet,
+			     (unsigned long)gpii);
+		init_completion(&gpii->cmd_completion);
+		gpii->gpii_id = i;
+		gpii->regs = gpi_dev->ee_base;
+		gpii->gpi_dev = gpi_dev;
+	}
+
+	platform_set_drvdata(pdev, gpi_dev);
+
+	/* clear and Set capabilities */
+	dma_cap_zero(gpi_dev->dma_device.cap_mask);
+	dma_cap_set(DMA_SLAVE, gpi_dev->dma_device.cap_mask);
+
+	/* configure dmaengine apis */
+	gpi_dev->dma_device.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
+	gpi_dev->dma_device.residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR;
+	gpi_dev->dma_device.src_addr_widths = DMA_SLAVE_BUSWIDTH_8_BYTES;
+	gpi_dev->dma_device.dst_addr_widths = DMA_SLAVE_BUSWIDTH_8_BYTES;
+	gpi_dev->dma_device.device_alloc_chan_resources = gpi_alloc_chan_resources;
+	gpi_dev->dma_device.device_free_chan_resources = gpi_free_chan_resources;
+	gpi_dev->dma_device.device_tx_status = dma_cookie_status;
+	gpi_dev->dma_device.device_issue_pending = gpi_issue_pending;
+	gpi_dev->dma_device.device_prep_slave_sg = gpi_prep_slave_sg;
+	gpi_dev->dma_device.device_config = gpi_peripheral_config;
+	gpi_dev->dma_device.device_terminate_all = gpi_terminate_all;
+	gpi_dev->dma_device.dev = gpi_dev->dev;
+	gpi_dev->dma_device.device_pause = gpi_pause;
+	gpi_dev->dma_device.device_resume = gpi_resume;
+
+	/* register with dmaengine framework */
+	ret = dma_async_device_register(&gpi_dev->dma_device);
+	if (ret) {
+		dev_err(gpi_dev->dev, "async_device_register failed ret:%d", ret);
+		return ret;
+	}
+
+	ret = of_dma_controller_register(gpi_dev->dev->of_node,
+					 gpi_of_dma_xlate, gpi_dev);
+	if (ret) {
+		dev_err(gpi_dev->dev, "of_dma_controller_reg failed ret:%d", ret);
+		return ret;
+	}
+
+	return ret;
+}
+
+static const struct of_device_id gpi_of_match[] = {
+	{ .compatible = "qcom,sdm845-gpi-dma" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, gpi_of_match);
+
+static struct platform_driver gpi_driver = {
+	.probe = gpi_probe,
+	.driver = {
+		.name = KBUILD_MODNAME,
+		.of_match_table = gpi_of_match,
+	},
+};
+
+static int __init gpi_init(void)
+{
+	return platform_driver_register(&gpi_driver);
+}
+subsys_initcall(gpi_init)
+
+MODULE_DESCRIPTION("QCOM GPI DMA engine driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/qcom/qcom_adm.c b/drivers/dma/qcom/qcom_adm.c
new file mode 100644
index 000000000000..ee78bed8d60d
--- /dev/null
+++ b/drivers/dma/qcom/qcom_adm.c
@@ -0,0 +1,905 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2013-2015, The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_dma.h>
+#include <linux/platform_device.h>
+#include <linux/reset.h>
+#include <linux/scatterlist.h>
+#include <linux/slab.h>
+
+#include "../dmaengine.h"
+#include "../virt-dma.h"
+
+/* ADM registers - calculated from channel number and security domain */
+#define ADM_CHAN_MULTI			0x4
+#define ADM_CI_MULTI			0x4
+#define ADM_CRCI_MULTI			0x4
+#define ADM_EE_MULTI			0x800
+#define ADM_CHAN_OFFS(chan)		(ADM_CHAN_MULTI * (chan))
+#define ADM_EE_OFFS(ee)			(ADM_EE_MULTI * (ee))
+#define ADM_CHAN_EE_OFFS(chan, ee)	(ADM_CHAN_OFFS(chan) + ADM_EE_OFFS(ee))
+#define ADM_CHAN_OFFS(chan)		(ADM_CHAN_MULTI * (chan))
+#define ADM_CI_OFFS(ci)			(ADM_CHAN_OFF(ci))
+#define ADM_CH_CMD_PTR(chan, ee)	(ADM_CHAN_EE_OFFS(chan, ee))
+#define ADM_CH_RSLT(chan, ee)		(0x40 + ADM_CHAN_EE_OFFS(chan, ee))
+#define ADM_CH_FLUSH_STATE0(chan, ee)	(0x80 + ADM_CHAN_EE_OFFS(chan, ee))
+#define ADM_CH_STATUS_SD(chan, ee)	(0x200 + ADM_CHAN_EE_OFFS(chan, ee))
+#define ADM_CH_CONF(chan)		(0x240 + ADM_CHAN_OFFS(chan))
+#define ADM_CH_RSLT_CONF(chan, ee)	(0x300 + ADM_CHAN_EE_OFFS(chan, ee))
+#define ADM_SEC_DOMAIN_IRQ_STATUS(ee)	(0x380 + ADM_EE_OFFS(ee))
+#define ADM_CI_CONF(ci)			(0x390 + (ci) * ADM_CI_MULTI)
+#define ADM_GP_CTL			0x3d8
+#define ADM_CRCI_CTL(crci, ee)		(0x400 + (crci) * ADM_CRCI_MULTI + \
+						ADM_EE_OFFS(ee))
+
+/* channel status */
+#define ADM_CH_STATUS_VALID		BIT(1)
+
+/* channel result */
+#define ADM_CH_RSLT_VALID		BIT(31)
+#define ADM_CH_RSLT_ERR			BIT(3)
+#define ADM_CH_RSLT_FLUSH		BIT(2)
+#define ADM_CH_RSLT_TPD			BIT(1)
+
+/* channel conf */
+#define ADM_CH_CONF_SHADOW_EN		BIT(12)
+#define ADM_CH_CONF_MPU_DISABLE		BIT(11)
+#define ADM_CH_CONF_PERM_MPU_CONF	BIT(9)
+#define ADM_CH_CONF_FORCE_RSLT_EN	BIT(7)
+#define ADM_CH_CONF_SEC_DOMAIN(ee)	((((ee) & 0x3) << 4) | (((ee) & 0x4) << 11))
+
+/* channel result conf */
+#define ADM_CH_RSLT_CONF_FLUSH_EN	BIT(1)
+#define ADM_CH_RSLT_CONF_IRQ_EN		BIT(0)
+
+/* CRCI CTL */
+#define ADM_CRCI_CTL_MUX_SEL		BIT(18)
+#define ADM_CRCI_CTL_RST		BIT(17)
+
+/* CI configuration */
+#define ADM_CI_RANGE_END(x)		((x) << 24)
+#define ADM_CI_RANGE_START(x)		((x) << 16)
+#define ADM_CI_BURST_4_WORDS		BIT(2)
+#define ADM_CI_BURST_8_WORDS		BIT(3)
+
+/* GP CTL */
+#define ADM_GP_CTL_LP_EN		BIT(12)
+#define ADM_GP_CTL_LP_CNT(x)		((x) << 8)
+
+/* Command pointer list entry */
+#define ADM_CPLE_LP			BIT(31)
+#define ADM_CPLE_CMD_PTR_LIST		BIT(29)
+
+/* Command list entry */
+#define ADM_CMD_LC			BIT(31)
+#define ADM_CMD_DST_CRCI(n)		(((n) & 0xf) << 7)
+#define ADM_CMD_SRC_CRCI(n)		(((n) & 0xf) << 3)
+
+#define ADM_CMD_TYPE_SINGLE		0x0
+#define ADM_CMD_TYPE_BOX		0x3
+
+#define ADM_CRCI_MUX_SEL		BIT(4)
+#define ADM_DESC_ALIGN			8
+#define ADM_MAX_XFER			(SZ_64K - 1)
+#define ADM_MAX_ROWS			(SZ_64K - 1)
+#define ADM_MAX_CHANNELS		16
+
+struct adm_desc_hw_box {
+	u32 cmd;
+	u32 src_addr;
+	u32 dst_addr;
+	u32 row_len;
+	u32 num_rows;
+	u32 row_offset;
+};
+
+struct adm_desc_hw_single {
+	u32 cmd;
+	u32 src_addr;
+	u32 dst_addr;
+	u32 len;
+};
+
+struct adm_async_desc {
+	struct virt_dma_desc vd;
+	struct adm_device *adev;
+
+	size_t length;
+	enum dma_transfer_direction dir;
+	dma_addr_t dma_addr;
+	size_t dma_len;
+
+	void *cpl;
+	dma_addr_t cp_addr;
+	u32 crci;
+	u32 mux;
+	u32 blk_size;
+};
+
+struct adm_chan {
+	struct virt_dma_chan vc;
+	struct adm_device *adev;
+
+	/* parsed from DT */
+	u32 id;			/* channel id */
+
+	struct adm_async_desc *curr_txd;
+	struct dma_slave_config slave;
+	struct list_head node;
+
+	int error;
+	int initialized;
+};
+
+static inline struct adm_chan *to_adm_chan(struct dma_chan *common)
+{
+	return container_of(common, struct adm_chan, vc.chan);
+}
+
+struct adm_device {
+	void __iomem *regs;
+	struct device *dev;
+	struct dma_device common;
+	struct device_dma_parameters dma_parms;
+	struct adm_chan *channels;
+
+	u32 ee;
+
+	struct clk *core_clk;
+	struct clk *iface_clk;
+
+	struct reset_control *clk_reset;
+	struct reset_control *c0_reset;
+	struct reset_control *c1_reset;
+	struct reset_control *c2_reset;
+	int irq;
+};
+
+/**
+ * adm_free_chan - Frees dma resources associated with the specific channel
+ *
+ * @chan: dma channel
+ *
+ * Free all allocated descriptors associated with this channel
+ */
+static void adm_free_chan(struct dma_chan *chan)
+{
+	/* free all queued descriptors */
+	vchan_free_chan_resources(to_virt_chan(chan));
+}
+
+/**
+ * adm_get_blksize - Get block size from burst value
+ *
+ * @burst: Burst size of transaction
+ */
+static int adm_get_blksize(unsigned int burst)
+{
+	int ret;
+
+	switch (burst) {
+	case 16:
+	case 32:
+	case 64:
+	case 128:
+		ret = ffs(burst >> 4) - 1;
+		break;
+	case 192:
+		ret = 4;
+		break;
+	case 256:
+		ret = 5;
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+/**
+ * adm_process_fc_descriptors - Process descriptors for flow controlled xfers
+ *
+ * @achan: ADM channel
+ * @desc: Descriptor memory pointer
+ * @sg: Scatterlist entry
+ * @crci: CRCI value
+ * @burst: Burst size of transaction
+ * @direction: DMA transfer direction
+ */
+static void *adm_process_fc_descriptors(struct adm_chan *achan, void *desc,
+					struct scatterlist *sg, u32 crci,
+					u32 burst,
+					enum dma_transfer_direction direction)
+{
+	struct adm_desc_hw_box *box_desc = NULL;
+	struct adm_desc_hw_single *single_desc;
+	u32 remainder = sg_dma_len(sg);
+	u32 rows, row_offset, crci_cmd;
+	u32 mem_addr = sg_dma_address(sg);
+	u32 *incr_addr = &mem_addr;
+	u32 *src, *dst;
+
+	if (direction == DMA_DEV_TO_MEM) {
+		crci_cmd = ADM_CMD_SRC_CRCI(crci);
+		row_offset = burst;
+		src = &achan->slave.src_addr;
+		dst = &mem_addr;
+	} else {
+		crci_cmd = ADM_CMD_DST_CRCI(crci);
+		row_offset = burst << 16;
+		src = &mem_addr;
+		dst = &achan->slave.dst_addr;
+	}
+
+	while (remainder >= burst) {
+		box_desc = desc;
+		box_desc->cmd = ADM_CMD_TYPE_BOX | crci_cmd;
+		box_desc->row_offset = row_offset;
+		box_desc->src_addr = *src;
+		box_desc->dst_addr = *dst;
+
+		rows = remainder / burst;
+		rows = min_t(u32, rows, ADM_MAX_ROWS);
+		box_desc->num_rows = rows << 16 | rows;
+		box_desc->row_len = burst << 16 | burst;
+
+		*incr_addr += burst * rows;
+		remainder -= burst * rows;
+		desc += sizeof(*box_desc);
+	}
+
+	/* if leftover bytes, do one single descriptor */
+	if (remainder) {
+		single_desc = desc;
+		single_desc->cmd = ADM_CMD_TYPE_SINGLE | crci_cmd;
+		single_desc->len = remainder;
+		single_desc->src_addr = *src;
+		single_desc->dst_addr = *dst;
+		desc += sizeof(*single_desc);
+
+		if (sg_is_last(sg))
+			single_desc->cmd |= ADM_CMD_LC;
+	} else {
+		if (box_desc && sg_is_last(sg))
+			box_desc->cmd |= ADM_CMD_LC;
+	}
+
+	return desc;
+}
+
+/**
+ * adm_process_non_fc_descriptors - Process descriptors for non-fc xfers
+ *
+ * @achan: ADM channel
+ * @desc: Descriptor memory pointer
+ * @sg: Scatterlist entry
+ * @direction: DMA transfer direction
+ */
+static void *adm_process_non_fc_descriptors(struct adm_chan *achan, void *desc,
+					    struct scatterlist *sg,
+					    enum dma_transfer_direction direction)
+{
+	struct adm_desc_hw_single *single_desc;
+	u32 remainder = sg_dma_len(sg);
+	u32 mem_addr = sg_dma_address(sg);
+	u32 *incr_addr = &mem_addr;
+	u32 *src, *dst;
+
+	if (direction == DMA_DEV_TO_MEM) {
+		src = &achan->slave.src_addr;
+		dst = &mem_addr;
+	} else {
+		src = &mem_addr;
+		dst = &achan->slave.dst_addr;
+	}
+
+	do {
+		single_desc = desc;
+		single_desc->cmd = ADM_CMD_TYPE_SINGLE;
+		single_desc->src_addr = *src;
+		single_desc->dst_addr = *dst;
+		single_desc->len = (remainder > ADM_MAX_XFER) ?
+				ADM_MAX_XFER : remainder;
+
+		remainder -= single_desc->len;
+		*incr_addr += single_desc->len;
+		desc += sizeof(*single_desc);
+	} while (remainder);
+
+	/* set last command if this is the end of the whole transaction */
+	if (sg_is_last(sg))
+		single_desc->cmd |= ADM_CMD_LC;
+
+	return desc;
+}
+
+/**
+ * adm_prep_slave_sg - Prep slave sg transaction
+ *
+ * @chan: dma channel
+ * @sgl: scatter gather list
+ * @sg_len: length of sg
+ * @direction: DMA transfer direction
+ * @flags: DMA flags
+ * @context: transfer context (unused)
+ */
+static struct dma_async_tx_descriptor *adm_prep_slave_sg(struct dma_chan *chan,
+							 struct scatterlist *sgl,
+							 unsigned int sg_len,
+							 enum dma_transfer_direction direction,
+							 unsigned long flags,
+							 void *context)
+{
+	struct adm_chan *achan = to_adm_chan(chan);
+	struct adm_device *adev = achan->adev;
+	struct adm_async_desc *async_desc;
+	struct scatterlist *sg;
+	dma_addr_t cple_addr;
+	u32 i, burst;
+	u32 single_count = 0, box_count = 0, crci = 0;
+	void *desc;
+	u32 *cple;
+	int blk_size = 0;
+
+	if (!is_slave_direction(direction)) {
+		dev_err(adev->dev, "invalid dma direction\n");
+		return NULL;
+	}
+
+	/*
+	 * get burst value from slave configuration
+	 */
+	burst = (direction == DMA_MEM_TO_DEV) ?
+		achan->slave.dst_maxburst :
+		achan->slave.src_maxburst;
+
+	/* if using flow control, validate burst and crci values */
+	if (achan->slave.device_fc) {
+		blk_size = adm_get_blksize(burst);
+		if (blk_size < 0) {
+			dev_err(adev->dev, "invalid burst value: %d\n",
+				burst);
+			return ERR_PTR(-EINVAL);
+		}
+
+		crci = achan->slave.slave_id & 0xf;
+		if (!crci || achan->slave.slave_id > 0x1f) {
+			dev_err(adev->dev, "invalid crci value\n");
+			return ERR_PTR(-EINVAL);
+		}
+	}
+
+	/* iterate through sgs and compute allocation size of structures */
+	for_each_sg(sgl, sg, sg_len, i) {
+		if (achan->slave.device_fc) {
+			box_count += DIV_ROUND_UP(sg_dma_len(sg) / burst,
+						  ADM_MAX_ROWS);
+			if (sg_dma_len(sg) % burst)
+				single_count++;
+		} else {
+			single_count += DIV_ROUND_UP(sg_dma_len(sg),
+						     ADM_MAX_XFER);
+		}
+	}
+
+	async_desc = kzalloc(sizeof(*async_desc), GFP_NOWAIT);
+	if (!async_desc)
+		return ERR_PTR(-ENOMEM);
+
+	if (crci)
+		async_desc->mux = achan->slave.slave_id & ADM_CRCI_MUX_SEL ?
+					ADM_CRCI_CTL_MUX_SEL : 0;
+	async_desc->crci = crci;
+	async_desc->blk_size = blk_size;
+	async_desc->dma_len = single_count * sizeof(struct adm_desc_hw_single) +
+				box_count * sizeof(struct adm_desc_hw_box) +
+				sizeof(*cple) + 2 * ADM_DESC_ALIGN;
+
+	async_desc->cpl = kzalloc(async_desc->dma_len, GFP_NOWAIT);
+	if (!async_desc->cpl)
+		goto free;
+
+	async_desc->adev = adev;
+
+	/* both command list entry and descriptors must be 8 byte aligned */
+	cple = PTR_ALIGN(async_desc->cpl, ADM_DESC_ALIGN);
+	desc = PTR_ALIGN(cple + 1, ADM_DESC_ALIGN);
+
+	for_each_sg(sgl, sg, sg_len, i) {
+		async_desc->length += sg_dma_len(sg);
+
+		if (achan->slave.device_fc)
+			desc = adm_process_fc_descriptors(achan, desc, sg, crci,
+							  burst, direction);
+		else
+			desc = adm_process_non_fc_descriptors(achan, desc, sg,
+							      direction);
+	}
+
+	async_desc->dma_addr = dma_map_single(adev->dev, async_desc->cpl,
+					      async_desc->dma_len,
+					      DMA_TO_DEVICE);
+	if (dma_mapping_error(adev->dev, async_desc->dma_addr))
+		goto free;
+
+	cple_addr = async_desc->dma_addr + ((void *)cple - async_desc->cpl);
+
+	/* init cmd list */
+	dma_sync_single_for_cpu(adev->dev, cple_addr, sizeof(*cple),
+				DMA_TO_DEVICE);
+	*cple = ADM_CPLE_LP;
+	*cple |= (async_desc->dma_addr + ADM_DESC_ALIGN) >> 3;
+	dma_sync_single_for_device(adev->dev, cple_addr, sizeof(*cple),
+				   DMA_TO_DEVICE);
+
+	return vchan_tx_prep(&achan->vc, &async_desc->vd, flags);
+
+free:
+	kfree(async_desc);
+	return ERR_PTR(-ENOMEM);
+}
+
+/**
+ * adm_terminate_all - terminate all transactions on a channel
+ * @chan: dma channel
+ *
+ * Dequeues and frees all transactions, aborts current transaction
+ * No callbacks are done
+ *
+ */
+static int adm_terminate_all(struct dma_chan *chan)
+{
+	struct adm_chan *achan = to_adm_chan(chan);
+	struct adm_device *adev = achan->adev;
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	spin_lock_irqsave(&achan->vc.lock, flags);
+	vchan_get_all_descriptors(&achan->vc, &head);
+
+	/* send flush command to terminate current transaction */
+	writel_relaxed(0x0,
+		       adev->regs + ADM_CH_FLUSH_STATE0(achan->id, adev->ee));
+
+	spin_unlock_irqrestore(&achan->vc.lock, flags);
+
+	vchan_dma_desc_free_list(&achan->vc, &head);
+
+	return 0;
+}
+
+static int adm_slave_config(struct dma_chan *chan, struct dma_slave_config *cfg)
+{
+	struct adm_chan *achan = to_adm_chan(chan);
+	unsigned long flag;
+
+	spin_lock_irqsave(&achan->vc.lock, flag);
+	memcpy(&achan->slave, cfg, sizeof(struct dma_slave_config));
+	spin_unlock_irqrestore(&achan->vc.lock, flag);
+
+	return 0;
+}
+
+/**
+ * adm_start_dma - start next transaction
+ * @achan: ADM dma channel
+ */
+static void adm_start_dma(struct adm_chan *achan)
+{
+	struct virt_dma_desc *vd = vchan_next_desc(&achan->vc);
+	struct adm_device *adev = achan->adev;
+	struct adm_async_desc *async_desc;
+
+	lockdep_assert_held(&achan->vc.lock);
+
+	if (!vd)
+		return;
+
+	list_del(&vd->node);
+
+	/* write next command list out to the CMD FIFO */
+	async_desc = container_of(vd, struct adm_async_desc, vd);
+	achan->curr_txd = async_desc;
+
+	/* reset channel error */
+	achan->error = 0;
+
+	if (!achan->initialized) {
+		/* enable interrupts */
+		writel(ADM_CH_CONF_SHADOW_EN |
+		       ADM_CH_CONF_PERM_MPU_CONF |
+		       ADM_CH_CONF_MPU_DISABLE |
+		       ADM_CH_CONF_SEC_DOMAIN(adev->ee),
+		       adev->regs + ADM_CH_CONF(achan->id));
+
+		writel(ADM_CH_RSLT_CONF_IRQ_EN | ADM_CH_RSLT_CONF_FLUSH_EN,
+		       adev->regs + ADM_CH_RSLT_CONF(achan->id, adev->ee));
+
+		achan->initialized = 1;
+	}
+
+	/* set the crci block size if this transaction requires CRCI */
+	if (async_desc->crci) {
+		writel(async_desc->mux | async_desc->blk_size,
+		       adev->regs + ADM_CRCI_CTL(async_desc->crci, adev->ee));
+	}
+
+	/* make sure IRQ enable doesn't get reordered */
+	wmb();
+
+	/* write next command list out to the CMD FIFO */
+	writel(ALIGN(async_desc->dma_addr, ADM_DESC_ALIGN) >> 3,
+	       adev->regs + ADM_CH_CMD_PTR(achan->id, adev->ee));
+}
+
+/**
+ * adm_dma_irq - irq handler for ADM controller
+ * @irq: IRQ of interrupt
+ * @data: callback data
+ *
+ * IRQ handler for the bam controller
+ */
+static irqreturn_t adm_dma_irq(int irq, void *data)
+{
+	struct adm_device *adev = data;
+	u32 srcs, i;
+	struct adm_async_desc *async_desc;
+	unsigned long flags;
+
+	srcs = readl_relaxed(adev->regs +
+			ADM_SEC_DOMAIN_IRQ_STATUS(adev->ee));
+
+	for (i = 0; i < ADM_MAX_CHANNELS; i++) {
+		struct adm_chan *achan = &adev->channels[i];
+		u32 status, result;
+
+		if (srcs & BIT(i)) {
+			status = readl_relaxed(adev->regs +
+					       ADM_CH_STATUS_SD(i, adev->ee));
+
+			/* if no result present, skip */
+			if (!(status & ADM_CH_STATUS_VALID))
+				continue;
+
+			result = readl_relaxed(adev->regs +
+				ADM_CH_RSLT(i, adev->ee));
+
+			/* no valid results, skip */
+			if (!(result & ADM_CH_RSLT_VALID))
+				continue;
+
+			/* flag error if transaction was flushed or failed */
+			if (result & (ADM_CH_RSLT_ERR | ADM_CH_RSLT_FLUSH))
+				achan->error = 1;
+
+			spin_lock_irqsave(&achan->vc.lock, flags);
+			async_desc = achan->curr_txd;
+
+			achan->curr_txd = NULL;
+
+			if (async_desc) {
+				vchan_cookie_complete(&async_desc->vd);
+
+				/* kick off next DMA */
+				adm_start_dma(achan);
+			}
+
+			spin_unlock_irqrestore(&achan->vc.lock, flags);
+		}
+	}
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * adm_tx_status - returns status of transaction
+ * @chan: dma channel
+ * @cookie: transaction cookie
+ * @txstate: DMA transaction state
+ *
+ * Return status of dma transaction
+ */
+static enum dma_status adm_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
+				     struct dma_tx_state *txstate)
+{
+	struct adm_chan *achan = to_adm_chan(chan);
+	struct virt_dma_desc *vd;
+	enum dma_status ret;
+	unsigned long flags;
+	size_t residue = 0;
+
+	ret = dma_cookie_status(chan, cookie, txstate);
+	if (ret == DMA_COMPLETE || !txstate)
+		return ret;
+
+	spin_lock_irqsave(&achan->vc.lock, flags);
+
+	vd = vchan_find_desc(&achan->vc, cookie);
+	if (vd)
+		residue = container_of(vd, struct adm_async_desc, vd)->length;
+
+	spin_unlock_irqrestore(&achan->vc.lock, flags);
+
+	/*
+	 * residue is either the full length if it is in the issued list, or 0
+	 * if it is in progress.  We have no reliable way of determining
+	 * anything inbetween
+	 */
+	dma_set_residue(txstate, residue);
+
+	if (achan->error)
+		return DMA_ERROR;
+
+	return ret;
+}
+
+/**
+ * adm_issue_pending - starts pending transactions
+ * @chan: dma channel
+ *
+ * Issues all pending transactions and starts DMA
+ */
+static void adm_issue_pending(struct dma_chan *chan)
+{
+	struct adm_chan *achan = to_adm_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&achan->vc.lock, flags);
+
+	if (vchan_issue_pending(&achan->vc) && !achan->curr_txd)
+		adm_start_dma(achan);
+	spin_unlock_irqrestore(&achan->vc.lock, flags);
+}
+
+/**
+ * adm_dma_free_desc - free descriptor memory
+ * @vd: virtual descriptor
+ *
+ */
+static void adm_dma_free_desc(struct virt_dma_desc *vd)
+{
+	struct adm_async_desc *async_desc = container_of(vd,
+			struct adm_async_desc, vd);
+
+	dma_unmap_single(async_desc->adev->dev, async_desc->dma_addr,
+			 async_desc->dma_len, DMA_TO_DEVICE);
+	kfree(async_desc->cpl);
+	kfree(async_desc);
+}
+
+static void adm_channel_init(struct adm_device *adev, struct adm_chan *achan,
+			     u32 index)
+{
+	achan->id = index;
+	achan->adev = adev;
+
+	vchan_init(&achan->vc, &adev->common);
+	achan->vc.desc_free = adm_dma_free_desc;
+}
+
+static int adm_dma_probe(struct platform_device *pdev)
+{
+	struct adm_device *adev;
+	int ret;
+	u32 i;
+
+	adev = devm_kzalloc(&pdev->dev, sizeof(*adev), GFP_KERNEL);
+	if (!adev)
+		return -ENOMEM;
+
+	adev->dev = &pdev->dev;
+
+	adev->regs = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(adev->regs))
+		return PTR_ERR(adev->regs);
+
+	adev->irq = platform_get_irq(pdev, 0);
+	if (adev->irq < 0)
+		return adev->irq;
+
+	ret = of_property_read_u32(pdev->dev.of_node, "qcom,ee", &adev->ee);
+	if (ret) {
+		dev_err(adev->dev, "Execution environment unspecified\n");
+		return ret;
+	}
+
+	adev->core_clk = devm_clk_get(adev->dev, "core");
+	if (IS_ERR(adev->core_clk))
+		return PTR_ERR(adev->core_clk);
+
+	adev->iface_clk = devm_clk_get(adev->dev, "iface");
+	if (IS_ERR(adev->iface_clk))
+		return PTR_ERR(adev->iface_clk);
+
+	adev->clk_reset = devm_reset_control_get_exclusive(&pdev->dev, "clk");
+	if (IS_ERR(adev->clk_reset)) {
+		dev_err(adev->dev, "failed to get ADM0 reset\n");
+		return PTR_ERR(adev->clk_reset);
+	}
+
+	adev->c0_reset = devm_reset_control_get_exclusive(&pdev->dev, "c0");
+	if (IS_ERR(adev->c0_reset)) {
+		dev_err(adev->dev, "failed to get ADM0 C0 reset\n");
+		return PTR_ERR(adev->c0_reset);
+	}
+
+	adev->c1_reset = devm_reset_control_get_exclusive(&pdev->dev, "c1");
+	if (IS_ERR(adev->c1_reset)) {
+		dev_err(adev->dev, "failed to get ADM0 C1 reset\n");
+		return PTR_ERR(adev->c1_reset);
+	}
+
+	adev->c2_reset = devm_reset_control_get_exclusive(&pdev->dev, "c2");
+	if (IS_ERR(adev->c2_reset)) {
+		dev_err(adev->dev, "failed to get ADM0 C2 reset\n");
+		return PTR_ERR(adev->c2_reset);
+	}
+
+	ret = clk_prepare_enable(adev->core_clk);
+	if (ret) {
+		dev_err(adev->dev, "failed to prepare/enable core clock\n");
+		return ret;
+	}
+
+	ret = clk_prepare_enable(adev->iface_clk);
+	if (ret) {
+		dev_err(adev->dev, "failed to prepare/enable iface clock\n");
+		goto err_disable_core_clk;
+	}
+
+	reset_control_assert(adev->clk_reset);
+	reset_control_assert(adev->c0_reset);
+	reset_control_assert(adev->c1_reset);
+	reset_control_assert(adev->c2_reset);
+
+	udelay(2);
+
+	reset_control_deassert(adev->clk_reset);
+	reset_control_deassert(adev->c0_reset);
+	reset_control_deassert(adev->c1_reset);
+	reset_control_deassert(adev->c2_reset);
+
+	adev->channels = devm_kcalloc(adev->dev, ADM_MAX_CHANNELS,
+				      sizeof(*adev->channels), GFP_KERNEL);
+
+	if (!adev->channels) {
+		ret = -ENOMEM;
+		goto err_disable_clks;
+	}
+
+	/* allocate and initialize channels */
+	INIT_LIST_HEAD(&adev->common.channels);
+
+	for (i = 0; i < ADM_MAX_CHANNELS; i++)
+		adm_channel_init(adev, &adev->channels[i], i);
+
+	/* reset CRCIs */
+	for (i = 0; i < 16; i++)
+		writel(ADM_CRCI_CTL_RST, adev->regs +
+			ADM_CRCI_CTL(i, adev->ee));
+
+	/* configure client interfaces */
+	writel(ADM_CI_RANGE_START(0x40) | ADM_CI_RANGE_END(0xb0) |
+	       ADM_CI_BURST_8_WORDS, adev->regs + ADM_CI_CONF(0));
+	writel(ADM_CI_RANGE_START(0x2a) | ADM_CI_RANGE_END(0x2c) |
+	       ADM_CI_BURST_8_WORDS, adev->regs + ADM_CI_CONF(1));
+	writel(ADM_CI_RANGE_START(0x12) | ADM_CI_RANGE_END(0x28) |
+	       ADM_CI_BURST_8_WORDS, adev->regs + ADM_CI_CONF(2));
+	writel(ADM_GP_CTL_LP_EN | ADM_GP_CTL_LP_CNT(0xf),
+	       adev->regs + ADM_GP_CTL);
+
+	ret = devm_request_irq(adev->dev, adev->irq, adm_dma_irq,
+			       0, "adm_dma", adev);
+	if (ret)
+		goto err_disable_clks;
+
+	platform_set_drvdata(pdev, adev);
+
+	adev->common.dev = adev->dev;
+	adev->common.dev->dma_parms = &adev->dma_parms;
+
+	/* set capabilities */
+	dma_cap_zero(adev->common.cap_mask);
+	dma_cap_set(DMA_SLAVE, adev->common.cap_mask);
+	dma_cap_set(DMA_PRIVATE, adev->common.cap_mask);
+
+	/* initialize dmaengine apis */
+	adev->common.directions = BIT(DMA_DEV_TO_MEM | DMA_MEM_TO_DEV);
+	adev->common.residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR;
+	adev->common.src_addr_widths = DMA_SLAVE_BUSWIDTH_4_BYTES;
+	adev->common.dst_addr_widths = DMA_SLAVE_BUSWIDTH_4_BYTES;
+	adev->common.device_free_chan_resources = adm_free_chan;
+	adev->common.device_prep_slave_sg = adm_prep_slave_sg;
+	adev->common.device_issue_pending = adm_issue_pending;
+	adev->common.device_tx_status = adm_tx_status;
+	adev->common.device_terminate_all = adm_terminate_all;
+	adev->common.device_config = adm_slave_config;
+
+	ret = dma_async_device_register(&adev->common);
+	if (ret) {
+		dev_err(adev->dev, "failed to register dma async device\n");
+		goto err_disable_clks;
+	}
+
+	ret = of_dma_controller_register(pdev->dev.of_node,
+					 of_dma_xlate_by_chan_id,
+					 &adev->common);
+	if (ret)
+		goto err_unregister_dma;
+
+	return 0;
+
+err_unregister_dma:
+	dma_async_device_unregister(&adev->common);
+err_disable_clks:
+	clk_disable_unprepare(adev->iface_clk);
+err_disable_core_clk:
+	clk_disable_unprepare(adev->core_clk);
+
+	return ret;
+}
+
+static int adm_dma_remove(struct platform_device *pdev)
+{
+	struct adm_device *adev = platform_get_drvdata(pdev);
+	struct adm_chan *achan;
+	u32 i;
+
+	of_dma_controller_free(pdev->dev.of_node);
+	dma_async_device_unregister(&adev->common);
+
+	for (i = 0; i < ADM_MAX_CHANNELS; i++) {
+		achan = &adev->channels[i];
+
+		/* mask IRQs for this channel/EE pair */
+		writel(0, adev->regs + ADM_CH_RSLT_CONF(achan->id, adev->ee));
+
+		tasklet_kill(&adev->channels[i].vc.task);
+		adm_terminate_all(&adev->channels[i].vc.chan);
+	}
+
+	devm_free_irq(adev->dev, adev->irq, adev);
+
+	clk_disable_unprepare(adev->core_clk);
+	clk_disable_unprepare(adev->iface_clk);
+
+	return 0;
+}
+
+static const struct of_device_id adm_of_match[] = {
+	{ .compatible = "qcom,adm", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, adm_of_match);
+
+static struct platform_driver adm_dma_driver = {
+	.probe = adm_dma_probe,
+	.remove = adm_dma_remove,
+	.driver = {
+		.name = "adm-dma-engine",
+		.of_match_table = adm_of_match,
+	},
+};
+
+module_platform_driver(adm_dma_driver);
+
+MODULE_AUTHOR("Andy Gross <agross@codeaurora.org>");
+MODULE_DESCRIPTION("QCOM ADM DMA engine driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/sf-pdma/sf-pdma.c b/drivers/dma/sf-pdma/sf-pdma.c
index 528deb5d9f31..c4c4e8575764 100644
--- a/drivers/dma/sf-pdma/sf-pdma.c
+++ b/drivers/dma/sf-pdma/sf-pdma.c
@@ -326,10 +326,9 @@ static irqreturn_t sf_pdma_done_isr(int irq, void *dev_id)
 {
 	struct sf_pdma_chan *chan = dev_id;
 	struct pdma_regs *regs = &chan->regs;
-	unsigned long flags;
 	u64 residue;
 
-	spin_lock_irqsave(&chan->vchan.lock, flags);
+	spin_lock(&chan->vchan.lock);
 	writel((readl(regs->ctrl)) & ~PDMA_DONE_STATUS_MASK, regs->ctrl);
 	residue = readq(regs->residue);
 
@@ -346,7 +345,7 @@ static irqreturn_t sf_pdma_done_isr(int irq, void *dev_id)
 		sf_pdma_xfer_desc(chan);
 	}
 
-	spin_unlock_irqrestore(&chan->vchan.lock, flags);
+	spin_unlock(&chan->vchan.lock);
 
 	return IRQ_HANDLED;
 }
@@ -355,11 +354,10 @@ static irqreturn_t sf_pdma_err_isr(int irq, void *dev_id)
 {
 	struct sf_pdma_chan *chan = dev_id;
 	struct pdma_regs *regs = &chan->regs;
-	unsigned long flags;
 
-	spin_lock_irqsave(&chan->lock, flags);
+	spin_lock(&chan->lock);
 	writel((readl(regs->ctrl)) & ~PDMA_ERR_STATUS_MASK, regs->ctrl);
-	spin_unlock_irqrestore(&chan->lock, flags);
+	spin_unlock(&chan->lock);
 
 	tasklet_schedule(&chan->err_tasklet);
 
@@ -584,7 +582,7 @@ static struct platform_driver sf_pdma_driver = {
 	.remove		= sf_pdma_remove,
 	.driver		= {
 		.name	= "sf-pdma",
-		.of_match_table = of_match_ptr(sf_pdma_dt_ids),
+		.of_match_table = sf_pdma_dt_ids,
 	},
 };
 
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index 77ab1f4730be..4256e55bbf25 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -1643,13 +1643,12 @@ static irqreturn_t d40_handle_interrupt(int irq, void *data)
 	u32 row;
 	long chan = -1;
 	struct d40_chan *d40c;
-	unsigned long flags;
 	struct d40_base *base = data;
 	u32 *regs = base->regs_interrupt;
 	struct d40_interrupt_lookup *il = base->gen_dmac.il;
 	u32 il_size = base->gen_dmac.il_size;
 
-	spin_lock_irqsave(&base->interrupt_lock, flags);
+	spin_lock(&base->interrupt_lock);
 
 	/* Read interrupt status of both logical and physical channels */
 	for (i = 0; i < il_size; i++)
@@ -1694,7 +1693,7 @@ static irqreturn_t d40_handle_interrupt(int irq, void *data)
 		spin_unlock(&d40c->lock);
 	}
 
-	spin_unlock_irqrestore(&base->interrupt_lock, flags);
+	spin_unlock(&base->interrupt_lock);
 
 	return IRQ_HANDLED;
 }
diff --git a/drivers/dma/stm32-dma.c b/drivers/dma/stm32-dma.c
index d0055d2f0b9a..f54ecb123a52 100644
--- a/drivers/dma/stm32-dma.c
+++ b/drivers/dma/stm32-dma.c
@@ -264,9 +264,11 @@ static int stm32_dma_get_width(struct stm32_dma_chan *chan,
 }
 
 static enum dma_slave_buswidth stm32_dma_get_max_width(u32 buf_len,
+						       dma_addr_t buf_addr,
 						       u32 threshold)
 {
 	enum dma_slave_buswidth max_width;
+	u64 addr = buf_addr;
 
 	if (threshold == STM32_DMA_FIFO_THRESHOLD_FULL)
 		max_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
@@ -277,6 +279,9 @@ static enum dma_slave_buswidth stm32_dma_get_max_width(u32 buf_len,
 	       max_width > DMA_SLAVE_BUSWIDTH_1_BYTE)
 		max_width = max_width >> 1;
 
+	if (do_div(addr, max_width))
+		max_width = DMA_SLAVE_BUSWIDTH_1_BYTE;
+
 	return max_width;
 }
 
@@ -648,21 +653,12 @@ static irqreturn_t stm32_dma_chan_irq(int irq, void *devid)
 	scr = stm32_dma_read(dmadev, STM32_DMA_SCR(chan->id));
 	sfcr = stm32_dma_read(dmadev, STM32_DMA_SFCR(chan->id));
 
-	if (status & STM32_DMA_TCI) {
-		stm32_dma_irq_clear(chan, STM32_DMA_TCI);
-		if (scr & STM32_DMA_SCR_TCIE)
-			stm32_dma_handle_chan_done(chan);
-		status &= ~STM32_DMA_TCI;
-	}
-	if (status & STM32_DMA_HTI) {
-		stm32_dma_irq_clear(chan, STM32_DMA_HTI);
-		status &= ~STM32_DMA_HTI;
-	}
 	if (status & STM32_DMA_FEI) {
 		stm32_dma_irq_clear(chan, STM32_DMA_FEI);
 		status &= ~STM32_DMA_FEI;
 		if (sfcr & STM32_DMA_SFCR_FEIE) {
-			if (!(scr & STM32_DMA_SCR_EN))
+			if (!(scr & STM32_DMA_SCR_EN) &&
+			    !(status & STM32_DMA_TCI))
 				dev_err(chan2dev(chan), "FIFO Error\n");
 			else
 				dev_dbg(chan2dev(chan), "FIFO over/underrun\n");
@@ -674,6 +670,19 @@ static irqreturn_t stm32_dma_chan_irq(int irq, void *devid)
 		if (sfcr & STM32_DMA_SCR_DMEIE)
 			dev_dbg(chan2dev(chan), "Direct mode overrun\n");
 	}
+
+	if (status & STM32_DMA_TCI) {
+		stm32_dma_irq_clear(chan, STM32_DMA_TCI);
+		if (scr & STM32_DMA_SCR_TCIE)
+			stm32_dma_handle_chan_done(chan);
+		status &= ~STM32_DMA_TCI;
+	}
+
+	if (status & STM32_DMA_HTI) {
+		stm32_dma_irq_clear(chan, STM32_DMA_HTI);
+		status &= ~STM32_DMA_HTI;
+	}
+
 	if (status) {
 		stm32_dma_irq_clear(chan, status);
 		dev_err(chan2dev(chan), "DMA error: status=0x%08x\n", status);
@@ -703,7 +712,7 @@ static void stm32_dma_issue_pending(struct dma_chan *c)
 static int stm32_dma_set_xfer_param(struct stm32_dma_chan *chan,
 				    enum dma_transfer_direction direction,
 				    enum dma_slave_buswidth *buswidth,
-				    u32 buf_len)
+				    u32 buf_len, dma_addr_t buf_addr)
 {
 	enum dma_slave_buswidth src_addr_width, dst_addr_width;
 	int src_bus_width, dst_bus_width;
@@ -735,7 +744,8 @@ static int stm32_dma_set_xfer_param(struct stm32_dma_chan *chan,
 			return dst_burst_size;
 
 		/* Set memory data size */
-		src_addr_width = stm32_dma_get_max_width(buf_len, fifoth);
+		src_addr_width = stm32_dma_get_max_width(buf_len, buf_addr,
+							 fifoth);
 		chan->mem_width = src_addr_width;
 		src_bus_width = stm32_dma_get_width(chan, src_addr_width);
 		if (src_bus_width < 0)
@@ -784,7 +794,8 @@ static int stm32_dma_set_xfer_param(struct stm32_dma_chan *chan,
 			return src_burst_size;
 
 		/* Set memory data size */
-		dst_addr_width = stm32_dma_get_max_width(buf_len, fifoth);
+		dst_addr_width = stm32_dma_get_max_width(buf_len, buf_addr,
+							 fifoth);
 		chan->mem_width = dst_addr_width;
 		dst_bus_width = stm32_dma_get_width(chan, dst_addr_width);
 		if (dst_bus_width < 0)
@@ -872,7 +883,8 @@ static struct dma_async_tx_descriptor *stm32_dma_prep_slave_sg(
 
 	for_each_sg(sgl, sg, sg_len, i) {
 		ret = stm32_dma_set_xfer_param(chan, direction, &buswidth,
-					       sg_dma_len(sg));
+					       sg_dma_len(sg),
+					       sg_dma_address(sg));
 		if (ret < 0)
 			goto err;
 
@@ -940,7 +952,8 @@ static struct dma_async_tx_descriptor *stm32_dma_prep_dma_cyclic(
 		return NULL;
 	}
 
-	ret = stm32_dma_set_xfer_param(chan, direction, &buswidth, period_len);
+	ret = stm32_dma_set_xfer_param(chan, direction, &buswidth, period_len,
+				       buf_addr);
 	if (ret < 0)
 		return NULL;
 
@@ -1216,6 +1229,8 @@ static void stm32_dma_free_chan_resources(struct dma_chan *c)
 	pm_runtime_put(dmadev->ddev.dev);
 
 	vchan_free_chan_resources(to_virt_chan(c));
+	stm32_dma_clear_reg(&chan->chan_reg);
+	chan->threshold = 0;
 }
 
 static void stm32_dma_desc_free(struct virt_dma_desc *vdesc)
diff --git a/drivers/dma/stm32-dmamux.c b/drivers/dma/stm32-dmamux.c
index a10ccd964376..ef0d0555103d 100644
--- a/drivers/dma/stm32-dmamux.c
+++ b/drivers/dma/stm32-dmamux.c
@@ -168,7 +168,7 @@ error_chan_id:
 	return ERR_PTR(ret);
 }
 
-static const struct of_device_id stm32_stm32dma_master_match[] = {
+static const struct of_device_id stm32_stm32dma_master_match[] __maybe_unused = {
 	{ .compatible = "st,stm32-dma", },
 	{},
 };
diff --git a/drivers/dma/stm32-mdma.c b/drivers/dma/stm32-mdma.c
index 08cfbfab837b..e4637ec786d3 100644
--- a/drivers/dma/stm32-mdma.c
+++ b/drivers/dma/stm32-mdma.c
@@ -339,7 +339,7 @@ static struct stm32_mdma_desc *stm32_mdma_alloc_desc(
 	struct stm32_mdma_desc *desc;
 	int i;
 
-	desc = kzalloc(offsetof(typeof(*desc), node[count]), GFP_NOWAIT);
+	desc = kzalloc(struct_size(desc, node, count), GFP_NOWAIT);
 	if (!desc)
 		return NULL;
 
@@ -1346,7 +1346,7 @@ static irqreturn_t stm32_mdma_irq_handler(int irq, void *devid)
 {
 	struct stm32_mdma_device *dmadev = devid;
 	struct stm32_mdma_chan *chan = devid;
-	u32 reg, id, ien, status, flag;
+	u32 reg, id, ccr, ien, status;
 
 	/* Find out which channel generates the interrupt */
 	status = readl_relaxed(dmadev->base + STM32_MDMA_GISR0);
@@ -1368,67 +1368,71 @@ static irqreturn_t stm32_mdma_irq_handler(int irq, void *devid)
 
 	chan = &dmadev->chan[id];
 	if (!chan) {
-		dev_dbg(mdma2dev(dmadev), "MDMA channel not initialized\n");
-		goto exit;
+		dev_warn(mdma2dev(dmadev), "MDMA channel not initialized\n");
+		return IRQ_NONE;
 	}
 
 	/* Handle interrupt for the channel */
 	spin_lock(&chan->vchan.lock);
-	status = stm32_mdma_read(dmadev, STM32_MDMA_CISR(chan->id));
-	ien = stm32_mdma_read(dmadev, STM32_MDMA_CCR(chan->id));
-	ien &= STM32_MDMA_CCR_IRQ_MASK;
-	ien >>= 1;
+	status = stm32_mdma_read(dmadev, STM32_MDMA_CISR(id));
+	/* Mask Channel ReQuest Active bit which can be set in case of MEM2MEM */
+	status &= ~STM32_MDMA_CISR_CRQA;
+	ccr = stm32_mdma_read(dmadev, STM32_MDMA_CCR(id));
+	ien = (ccr & STM32_MDMA_CCR_IRQ_MASK) >> 1;
 
 	if (!(status & ien)) {
 		spin_unlock(&chan->vchan.lock);
-		dev_dbg(chan2dev(chan),
-			"spurious it (status=0x%04x, ien=0x%04x)\n",
-			status, ien);
+		dev_warn(chan2dev(chan),
+			 "spurious it (status=0x%04x, ien=0x%04x)\n",
+			 status, ien);
 		return IRQ_NONE;
 	}
 
-	flag = __ffs(status & ien);
-	reg = STM32_MDMA_CIFCR(chan->id);
+	reg = STM32_MDMA_CIFCR(id);
 
-	switch (1 << flag) {
-	case STM32_MDMA_CISR_TEIF:
-		id = chan->id;
-		status = readl_relaxed(dmadev->base + STM32_MDMA_CESR(id));
-		dev_err(chan2dev(chan), "Transfer Err: stat=0x%08x\n", status);
+	if (status & STM32_MDMA_CISR_TEIF) {
+		dev_err(chan2dev(chan), "Transfer Err: stat=0x%08x\n",
+			readl_relaxed(dmadev->base + STM32_MDMA_CESR(id)));
 		stm32_mdma_set_bits(dmadev, reg, STM32_MDMA_CIFCR_CTEIF);
-		break;
+		status &= ~STM32_MDMA_CISR_TEIF;
+	}
 
-	case STM32_MDMA_CISR_CTCIF:
+	if (status & STM32_MDMA_CISR_CTCIF) {
 		stm32_mdma_set_bits(dmadev, reg, STM32_MDMA_CIFCR_CCTCIF);
+		status &= ~STM32_MDMA_CISR_CTCIF;
 		stm32_mdma_xfer_end(chan);
-		break;
+	}
 
-	case STM32_MDMA_CISR_BRTIF:
+	if (status & STM32_MDMA_CISR_BRTIF) {
 		stm32_mdma_set_bits(dmadev, reg, STM32_MDMA_CIFCR_CBRTIF);
-		break;
+		status &= ~STM32_MDMA_CISR_BRTIF;
+	}
 
-	case STM32_MDMA_CISR_BTIF:
+	if (status & STM32_MDMA_CISR_BTIF) {
 		stm32_mdma_set_bits(dmadev, reg, STM32_MDMA_CIFCR_CBTIF);
+		status &= ~STM32_MDMA_CISR_BTIF;
 		chan->curr_hwdesc++;
 		if (chan->desc && chan->desc->cyclic) {
 			if (chan->curr_hwdesc == chan->desc->count)
 				chan->curr_hwdesc = 0;
 			vchan_cyclic_callback(&chan->desc->vdesc);
 		}
-		break;
+	}
 
-	case STM32_MDMA_CISR_TCIF:
+	if (status & STM32_MDMA_CISR_TCIF) {
 		stm32_mdma_set_bits(dmadev, reg, STM32_MDMA_CIFCR_CLTCIF);
-		break;
+		status &= ~STM32_MDMA_CISR_TCIF;
+	}
 
-	default:
-		dev_err(chan2dev(chan), "it %d unhandled (status=0x%04x)\n",
-			1 << flag, status);
+	if (status) {
+		stm32_mdma_set_bits(dmadev, reg, status);
+		dev_err(chan2dev(chan), "DMA error: status=0x%08x\n", status);
+		if (!(ccr & STM32_MDMA_CCR_EN))
+			dev_err(chan2dev(chan), "chan disabled by HW\n");
 	}
 
 	spin_unlock(&chan->vchan.lock);
 
-exit:
 	return IRQ_HANDLED;
 }
 
diff --git a/drivers/dma/sun6i-dma.c b/drivers/dma/sun6i-dma.c
index f5f9c86c50bc..5cadd4d2b824 100644
--- a/drivers/dma/sun6i-dma.c
+++ b/drivers/dma/sun6i-dma.c
@@ -1174,6 +1174,30 @@ static struct sun6i_dma_config sun50i_a64_dma_cfg = {
 };
 
 /*
+ * TODO: Add support for more than 4g physical addressing.
+ *
+ * The A100 binding uses the number of dma channels from the
+ * device tree node.
+ */
+static struct sun6i_dma_config sun50i_a100_dma_cfg = {
+	.clock_autogate_enable = sun6i_enable_clock_autogate_h3,
+	.set_burst_length = sun6i_set_burst_length_h3,
+	.set_drq          = sun6i_set_drq_h6,
+	.set_mode         = sun6i_set_mode_h6,
+	.src_burst_lengths = BIT(1) | BIT(4) | BIT(8) | BIT(16),
+	.dst_burst_lengths = BIT(1) | BIT(4) | BIT(8) | BIT(16),
+	.src_addr_widths   = BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) |
+			     BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) |
+			     BIT(DMA_SLAVE_BUSWIDTH_4_BYTES) |
+			     BIT(DMA_SLAVE_BUSWIDTH_8_BYTES),
+	.dst_addr_widths   = BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) |
+			     BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) |
+			     BIT(DMA_SLAVE_BUSWIDTH_4_BYTES) |
+			     BIT(DMA_SLAVE_BUSWIDTH_8_BYTES),
+	.has_mbus_clk = true,
+};
+
+/*
  * The H6 binding uses the number of dma channels from the
  * device tree node.
  */
@@ -1225,6 +1249,7 @@ static const struct of_device_id sun6i_dma_match[] = {
 	{ .compatible = "allwinner,sun8i-h3-dma", .data = &sun8i_h3_dma_cfg },
 	{ .compatible = "allwinner,sun8i-v3s-dma", .data = &sun8i_v3s_dma_cfg },
 	{ .compatible = "allwinner,sun50i-a64-dma", .data = &sun50i_a64_dma_cfg },
+	{ .compatible = "allwinner,sun50i-a100-dma", .data = &sun50i_a100_dma_cfg },
 	{ .compatible = "allwinner,sun50i-h6-dma", .data = &sun50i_h6_dma_cfg },
 	{ /* sentinel */ }
 };
diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c
index c5fa2ef74abc..4735742e826d 100644
--- a/drivers/dma/tegra210-adma.c
+++ b/drivers/dma/tegra210-adma.c
@@ -408,19 +408,18 @@ static irqreturn_t tegra_adma_isr(int irq, void *dev_id)
 {
 	struct tegra_adma_chan *tdc = dev_id;
 	unsigned long status;
-	unsigned long flags;
 
-	spin_lock_irqsave(&tdc->vc.lock, flags);
+	spin_lock(&tdc->vc.lock);
 
 	status = tegra_adma_irq_clear(tdc);
 	if (status == 0 || !tdc->desc) {
-		spin_unlock_irqrestore(&tdc->vc.lock, flags);
+		spin_unlock(&tdc->vc.lock);
 		return IRQ_NONE;
 	}
 
 	vchan_cyclic_callback(&tdc->desc->vd);
 
-	spin_unlock_irqrestore(&tdc->vc.lock, flags);
+	spin_unlock(&tdc->vc.lock);
 
 	return IRQ_HANDLED;
 }
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_ */
author	Linus Torvalds	2020-12-17 12:52:23 -0800
committer	Linus Torvalds	2020-12-17 12:52:23 -0800
commit	6daa90439e91bb9a71864b02f7d0af8587ea889a (patch)
tree	cd747a40f9aac87089d3d73de9d42c5863fe7896 /drivers/dma
parent	83005cd6bc76eef7bbf46b55bbb00ccc9534c38c (diff)
parent	115ff12aecfd55376d704fa2c0a2d117e5827f9f (diff)