Merge drm/drm-next into drm-misc-next

Backmerging to get v6.9-rc2 changes into drm-misc-next.

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>

26 files changed, 632 insertions, 228 deletions

diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index e928f2ca0f1e..002a5ec80620 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -643,16 +643,16 @@ config TEGRA20_APB_DMA
 
 config TEGRA210_ADMA
 	tristate "NVIDIA Tegra210 ADMA support"
-	depends on (ARCH_TEGRA_210_SOC || COMPILE_TEST)
+	depends on (ARCH_TEGRA || COMPILE_TEST)
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
 	help
-	  Support for the NVIDIA Tegra210 ADMA controller driver. The
-	  DMA controller has multiple DMA channels and is used to service
-	  various audio clients in the Tegra210 audio processing engine
-	  (APE). This DMA controller transfers data from memory to
-	  peripheral and vice versa. It does not support memory to
-	  memory data transfer.
+	  Support for the NVIDIA Tegra210/Tegra186/Tegra194/Tegra234 ADMA
+	  controller driver. The DMA controller has multiple DMA channels
+	  and is used to service various audio clients in the Tegra210
+	  audio processing engine (APE). This DMA controller transfers
+	  data from memory to peripheral and vice versa. It does not
+	  support memory to memory data transfer.
 
 config TIMB_DMA
 	tristate "Timberdale FPGA DMA support"
diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c
index eea8bd33b4b7..fbf048f432bf 100644
--- a/drivers/dma/amba-pl08x.c
+++ b/drivers/dma/amba-pl08x.c
@@ -2239,7 +2239,7 @@ static int pl08x_resume(struct dma_chan *chan)
 bool pl08x_filter_id(struct dma_chan *chan, void *chan_id)
 {
 	struct pl08x_dma_chan *plchan;
-	char *name = chan_id;
+	const char *name = chan_id;
 
 	/* Reject channels for devices not bound to this driver */
 	if (chan->device->dev->driver != &pl08x_amba_driver.drv)
diff --git a/drivers/dma/bestcomm/sram.c b/drivers/dma/bestcomm/sram.c
index 0553956f7456..ad74d57cc3ab 100644
--- a/drivers/dma/bestcomm/sram.c
+++ b/drivers/dma/bestcomm/sram.c
@@ -90,13 +90,8 @@ int bcom_sram_init(struct device_node *sram_node, char *owner)
 	bcom_sram->rh = rh_create(4);
 
 	/* Attach the free zones */
-#if 0
-	/* Currently disabled ... for future use only */
-	reg_addr_p = of_get_property(sram_node, "available", &psize);
-#else
 	regaddr_p = NULL;
 	psize = 0;
-#endif
 
 	if (!regaddr_p || !psize) {
 		/* Attach the whole zone */
diff --git a/drivers/dma/dw-edma/dw-edma-v0-core.c b/drivers/dma/dw-edma/dw-edma-v0-core.c
index b38786f0ad79..b75fdaffad9a 100644
--- a/drivers/dma/dw-edma/dw-edma-v0-core.c
+++ b/drivers/dma/dw-edma/dw-edma-v0-core.c
@@ -346,6 +346,20 @@ static void dw_edma_v0_core_write_chunk(struct dw_edma_chunk *chunk)
 	dw_edma_v0_write_ll_link(chunk, i, control, chunk->ll_region.paddr);
 }
 
+static void dw_edma_v0_sync_ll_data(struct dw_edma_chunk *chunk)
+{
+	/*
+	 * In case of remote eDMA engine setup, the DW PCIe RP/EP internal
+	 * configuration registers and application memory are normally accessed
+	 * over different buses. Ensure LL-data reaches the memory before the
+	 * doorbell register is toggled by issuing the dummy-read from the remote
+	 * LL memory in a hope that the MRd TLP will return only after the
+	 * last MWr TLP is completed
+	 */
+	if (!(chunk->chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL))
+		readl(chunk->ll_region.vaddr.io);
+}
+
 static void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
 {
 	struct dw_edma_chan *chan = chunk->chan;
@@ -412,6 +426,9 @@ static void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
 		SET_CH_32(dw, chan->dir, chan->id, llp.msb,
 			  upper_32_bits(chunk->ll_region.paddr));
 	}
+
+	dw_edma_v0_sync_ll_data(chunk);
+
 	/* Doorbell */
 	SET_RW_32(dw, chan->dir, doorbell,
 		  FIELD_PREP(EDMA_V0_DOORBELL_CH_MASK, chan->id));
diff --git a/drivers/dma/dw-edma/dw-hdma-v0-core.c b/drivers/dma/dw-edma/dw-hdma-v0-core.c
index 00b735a0202a..10e8f0715114 100644
--- a/drivers/dma/dw-edma/dw-hdma-v0-core.c
+++ b/drivers/dma/dw-edma/dw-hdma-v0-core.c
@@ -65,18 +65,12 @@ static void dw_hdma_v0_core_off(struct dw_edma *dw)
 
 static u16 dw_hdma_v0_core_ch_count(struct dw_edma *dw, enum dw_edma_dir dir)
 {
-	u32 num_ch = 0;
-	int id;
-
-	for (id = 0; id < HDMA_V0_MAX_NR_CH; id++) {
-		if (GET_CH_32(dw, id, dir, ch_en) & BIT(0))
-			num_ch++;
-	}
-
-	if (num_ch > HDMA_V0_MAX_NR_CH)
-		num_ch = HDMA_V0_MAX_NR_CH;
-
-	return (u16)num_ch;
+	/*
+	 * The HDMA IP have no way to know the number of hardware channels
+	 * available, we set it to maximum channels and let the platform
+	 * set the right number of channels.
+	 */
+	return HDMA_V0_MAX_NR_CH;
 }
 
 static enum dma_status dw_hdma_v0_core_ch_status(struct dw_edma_chan *chan)
@@ -228,6 +222,20 @@ static void dw_hdma_v0_core_write_chunk(struct dw_edma_chunk *chunk)
 	dw_hdma_v0_write_ll_link(chunk, i, control, chunk->ll_region.paddr);
 }
 
+static void dw_hdma_v0_sync_ll_data(struct dw_edma_chunk *chunk)
+{
+	/*
+	 * In case of remote HDMA engine setup, the DW PCIe RP/EP internal
+	 * configuration registers and application memory are normally accessed
+	 * over different buses. Ensure LL-data reaches the memory before the
+	 * doorbell register is toggled by issuing the dummy-read from the remote
+	 * LL memory in a hope that the MRd TLP will return only after the
+	 * last MWr TLP is completed
+	 */
+	if (!(chunk->chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL))
+		readl(chunk->ll_region.vaddr.io);
+}
+
 static void dw_hdma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
 {
 	struct dw_edma_chan *chan = chunk->chan;
@@ -242,7 +250,9 @@ static void dw_hdma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
 		/* Interrupt enable&unmask - done, abort */
 		tmp = GET_CH_32(dw, chan->dir, chan->id, int_setup) |
 		      HDMA_V0_STOP_INT_MASK | HDMA_V0_ABORT_INT_MASK |
-		      HDMA_V0_LOCAL_STOP_INT_EN | HDMA_V0_LOCAL_STOP_INT_EN;
+		      HDMA_V0_LOCAL_STOP_INT_EN | HDMA_V0_LOCAL_ABORT_INT_EN;
+		if (!(dw->chip->flags & DW_EDMA_CHIP_LOCAL))
+			tmp |= HDMA_V0_REMOTE_STOP_INT_EN | HDMA_V0_REMOTE_ABORT_INT_EN;
 		SET_CH_32(dw, chan->dir, chan->id, int_setup, tmp);
 		/* Channel control */
 		SET_CH_32(dw, chan->dir, chan->id, control1, HDMA_V0_LINKLIST_EN);
@@ -256,6 +266,9 @@ static void dw_hdma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
 	/* Set consumer cycle */
 	SET_CH_32(dw, chan->dir, chan->id, cycle_sync,
 		  HDMA_V0_CONSUMER_CYCLE_STAT | HDMA_V0_CONSUMER_CYCLE_BIT);
+
+	dw_hdma_v0_sync_ll_data(chunk);
+
 	/* Doorbell */
 	SET_CH_32(dw, chan->dir, chan->id, doorbell, HDMA_V0_DOORBELL_START);
 }
diff --git a/drivers/dma/dw-edma/dw-hdma-v0-regs.h b/drivers/dma/dw-edma/dw-hdma-v0-regs.h
index a974abdf8aaf..eab5fd7177e5 100644
--- a/drivers/dma/dw-edma/dw-hdma-v0-regs.h
+++ b/drivers/dma/dw-edma/dw-hdma-v0-regs.h
@@ -15,7 +15,7 @@
 #define HDMA_V0_LOCAL_ABORT_INT_EN		BIT(6)
 #define HDMA_V0_REMOTE_ABORT_INT_EN		BIT(5)
 #define HDMA_V0_LOCAL_STOP_INT_EN		BIT(4)
-#define HDMA_V0_REMOTEL_STOP_INT_EN		BIT(3)
+#define HDMA_V0_REMOTE_STOP_INT_EN		BIT(3)
 #define HDMA_V0_ABORT_INT_MASK			BIT(2)
 #define HDMA_V0_STOP_INT_MASK			BIT(0)
 #define HDMA_V0_LINKLIST_EN			BIT(0)
diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c
index b53f46245c37..b18faa7cfedb 100644
--- a/drivers/dma/fsl-edma-common.c
+++ b/drivers/dma/fsl-edma-common.c
@@ -97,8 +97,8 @@ static void fsl_edma3_enable_request(struct fsl_edma_chan *fsl_chan)
 		 * ch_mux: With the exception of 0, attempts to write a value
 		 * already in use will be forced to 0.
 		 */
-		if (!edma_readl_chreg(fsl_chan, ch_mux))
-			edma_writel_chreg(fsl_chan, fsl_chan->srcid, ch_mux);
+		if (!edma_readl(fsl_chan->edma, fsl_chan->mux_addr))
+			edma_writel(fsl_chan->edma, fsl_chan->srcid, fsl_chan->mux_addr);
 	}
 
 	val = edma_readl_chreg(fsl_chan, ch_csr);
@@ -134,7 +134,7 @@ static void fsl_edma3_disable_request(struct fsl_edma_chan *fsl_chan)
 	flags = fsl_edma_drvflags(fsl_chan);
 
 	if (flags & FSL_EDMA_DRV_HAS_CHMUX)
-		edma_writel_chreg(fsl_chan, 0, ch_mux);
+		edma_writel(fsl_chan->edma, 0, fsl_chan->mux_addr);
 
 	val &= ~EDMA_V3_CH_CSR_ERQ;
 	edma_writel_chreg(fsl_chan, val, ch_csr);
@@ -351,39 +351,45 @@ static size_t fsl_edma_desc_residue(struct fsl_edma_chan *fsl_chan,
 {
 	struct fsl_edma_desc *edesc = fsl_chan->edesc;
 	enum dma_transfer_direction dir = edesc->dirn;
-	dma_addr_t cur_addr, dma_addr;
+	dma_addr_t cur_addr, dma_addr, old_addr;
 	size_t len, size;
 	u32 nbytes = 0;
 	int i;
 
 	/* calculate the total size in this desc */
 	for (len = i = 0; i < fsl_chan->edesc->n_tcds; i++) {
-		nbytes = le32_to_cpu(edesc->tcd[i].vtcd->nbytes);
+		nbytes = fsl_edma_get_tcd_to_cpu(fsl_chan, edesc->tcd[i].vtcd, nbytes);
 		if (nbytes & (EDMA_V3_TCD_NBYTES_DMLOE | EDMA_V3_TCD_NBYTES_SMLOE))
 			nbytes = EDMA_V3_TCD_NBYTES_MLOFF_NBYTES(nbytes);
-		len += nbytes * le16_to_cpu(edesc->tcd[i].vtcd->biter);
+		len += nbytes * fsl_edma_get_tcd_to_cpu(fsl_chan, edesc->tcd[i].vtcd, biter);
 	}
 
 	if (!in_progress)
 		return len;
 
-	if (dir == DMA_MEM_TO_DEV)
-		cur_addr = edma_read_tcdreg(fsl_chan, saddr);
-	else
-		cur_addr = edma_read_tcdreg(fsl_chan, daddr);
+	/* 64bit read is not atomic, need read retry when high 32bit changed */
+	do {
+		if (dir == DMA_MEM_TO_DEV) {
+			old_addr = edma_read_tcdreg(fsl_chan, saddr);
+			cur_addr = edma_read_tcdreg(fsl_chan, saddr);
+		} else {
+			old_addr = edma_read_tcdreg(fsl_chan, daddr);
+			cur_addr = edma_read_tcdreg(fsl_chan, daddr);
+		}
+	} while (upper_32_bits(cur_addr) != upper_32_bits(old_addr));
 
 	/* figure out the finished and calculate the residue */
 	for (i = 0; i < fsl_chan->edesc->n_tcds; i++) {
-		nbytes = le32_to_cpu(edesc->tcd[i].vtcd->nbytes);
+		nbytes = fsl_edma_get_tcd_to_cpu(fsl_chan, edesc->tcd[i].vtcd, nbytes);
 		if (nbytes & (EDMA_V3_TCD_NBYTES_DMLOE | EDMA_V3_TCD_NBYTES_SMLOE))
 			nbytes = EDMA_V3_TCD_NBYTES_MLOFF_NBYTES(nbytes);
 
-		size = nbytes * le16_to_cpu(edesc->tcd[i].vtcd->biter);
+		size = nbytes * fsl_edma_get_tcd_to_cpu(fsl_chan, edesc->tcd[i].vtcd, biter);
 
 		if (dir == DMA_MEM_TO_DEV)
-			dma_addr = le32_to_cpu(edesc->tcd[i].vtcd->saddr);
+			dma_addr = fsl_edma_get_tcd_to_cpu(fsl_chan, edesc->tcd[i].vtcd, saddr);
 		else
-			dma_addr = le32_to_cpu(edesc->tcd[i].vtcd->daddr);
+			dma_addr = fsl_edma_get_tcd_to_cpu(fsl_chan, edesc->tcd[i].vtcd, daddr);
 
 		len -= size;
 		if (cur_addr >= dma_addr && cur_addr < dma_addr + size) {
@@ -426,8 +432,7 @@ enum dma_status fsl_edma_tx_status(struct dma_chan *chan,
 	return fsl_chan->status;
 }
 
-static void fsl_edma_set_tcd_regs(struct fsl_edma_chan *fsl_chan,
-				  struct fsl_edma_hw_tcd *tcd)
+static void fsl_edma_set_tcd_regs(struct fsl_edma_chan *fsl_chan, void *tcd)
 {
 	u16 csr = 0;
 
@@ -439,26 +444,26 @@ static void fsl_edma_set_tcd_regs(struct fsl_edma_chan *fsl_chan,
 	 */
 	edma_write_tcdreg(fsl_chan, 0, csr);
 
-	edma_write_tcdreg(fsl_chan, tcd->saddr, saddr);
-	edma_write_tcdreg(fsl_chan, tcd->daddr, daddr);
+	edma_cp_tcd_to_reg(fsl_chan, tcd, saddr);
+	edma_cp_tcd_to_reg(fsl_chan, tcd, daddr);
 
-	edma_write_tcdreg(fsl_chan, tcd->attr, attr);
-	edma_write_tcdreg(fsl_chan, tcd->soff, soff);
+	edma_cp_tcd_to_reg(fsl_chan, tcd, attr);
+	edma_cp_tcd_to_reg(fsl_chan, tcd, soff);
 
-	edma_write_tcdreg(fsl_chan, tcd->nbytes, nbytes);
-	edma_write_tcdreg(fsl_chan, tcd->slast, slast);
+	edma_cp_tcd_to_reg(fsl_chan, tcd, nbytes);
+	edma_cp_tcd_to_reg(fsl_chan, tcd, slast);
 
-	edma_write_tcdreg(fsl_chan, tcd->citer, citer);
-	edma_write_tcdreg(fsl_chan, tcd->biter, biter);
-	edma_write_tcdreg(fsl_chan, tcd->doff, doff);
+	edma_cp_tcd_to_reg(fsl_chan, tcd, citer);
+	edma_cp_tcd_to_reg(fsl_chan, tcd, biter);
+	edma_cp_tcd_to_reg(fsl_chan, tcd, doff);
 
-	edma_write_tcdreg(fsl_chan, tcd->dlast_sga, dlast_sga);
+	edma_cp_tcd_to_reg(fsl_chan, tcd, dlast_sga);
 
-	csr = le16_to_cpu(tcd->csr);
+	csr = fsl_edma_get_tcd_to_cpu(fsl_chan, tcd, csr);
 
 	if (fsl_chan->is_sw) {
 		csr |= EDMA_TCD_CSR_START;
-		tcd->csr = cpu_to_le16(csr);
+		fsl_edma_set_tcd_to_le(fsl_chan, tcd, csr, csr);
 	}
 
 	/*
@@ -473,14 +478,14 @@ static void fsl_edma_set_tcd_regs(struct fsl_edma_chan *fsl_chan,
 		edma_writel_chreg(fsl_chan, edma_readl_chreg(fsl_chan, ch_csr), ch_csr);
 
 
-	edma_write_tcdreg(fsl_chan, tcd->csr, csr);
+	edma_cp_tcd_to_reg(fsl_chan, tcd, csr);
 }
 
 static inline
 void fsl_edma_fill_tcd(struct fsl_edma_chan *fsl_chan,
-		       struct fsl_edma_hw_tcd *tcd, u32 src, u32 dst,
-		       u16 attr, u16 soff, u32 nbytes, u32 slast, u16 citer,
-		       u16 biter, u16 doff, u32 dlast_sga, bool major_int,
+		       struct fsl_edma_hw_tcd *tcd, dma_addr_t src, dma_addr_t dst,
+		       u16 attr, u16 soff, u32 nbytes, dma_addr_t slast, u16 citer,
+		       u16 biter, u16 doff, dma_addr_t dlast_sga, bool major_int,
 		       bool disable_req, bool enable_sg)
 {
 	struct dma_slave_config *cfg = &fsl_chan->cfg;
@@ -493,17 +498,17 @@ void fsl_edma_fill_tcd(struct fsl_edma_chan *fsl_chan,
 	 * So we put the value in little endian in memory, waiting
 	 * for fsl_edma_set_tcd_regs doing the swap.
 	 */
-	tcd->saddr = cpu_to_le32(src);
-	tcd->daddr = cpu_to_le32(dst);
+	fsl_edma_set_tcd_to_le(fsl_chan, tcd, src, saddr);
+	fsl_edma_set_tcd_to_le(fsl_chan, tcd, dst, daddr);
 
-	tcd->attr = cpu_to_le16(attr);
+	fsl_edma_set_tcd_to_le(fsl_chan, tcd, attr, attr);
 
-	tcd->soff = cpu_to_le16(soff);
+	fsl_edma_set_tcd_to_le(fsl_chan, tcd, soff, soff);
 
 	if (fsl_chan->is_multi_fifo) {
 		/* set mloff to support multiple fifo */
 		burst = cfg->direction == DMA_DEV_TO_MEM ?
-				cfg->src_addr_width : cfg->dst_addr_width;
+				cfg->src_maxburst : cfg->dst_maxburst;
 		nbytes |= EDMA_V3_TCD_NBYTES_MLOFF(-(burst * 4));
 		/* enable DMLOE/SMLOE */
 		if (cfg->direction == DMA_MEM_TO_DEV) {
@@ -515,15 +520,16 @@ void fsl_edma_fill_tcd(struct fsl_edma_chan *fsl_chan,
 		}
 	}
 
-	tcd->nbytes = cpu_to_le32(nbytes);
-	tcd->slast = cpu_to_le32(slast);
+	fsl_edma_set_tcd_to_le(fsl_chan, tcd, nbytes, nbytes);
+	fsl_edma_set_tcd_to_le(fsl_chan, tcd, slast, slast);
+
+	fsl_edma_set_tcd_to_le(fsl_chan, tcd, EDMA_TCD_CITER_CITER(citer), citer);
+	fsl_edma_set_tcd_to_le(fsl_chan, tcd, doff, doff);
 
-	tcd->citer = cpu_to_le16(EDMA_TCD_CITER_CITER(citer));
-	tcd->doff = cpu_to_le16(doff);
+	fsl_edma_set_tcd_to_le(fsl_chan, tcd, dlast_sga, dlast_sga);
 
-	tcd->dlast_sga = cpu_to_le32(dlast_sga);
+	fsl_edma_set_tcd_to_le(fsl_chan, tcd, EDMA_TCD_BITER_BITER(biter), biter);
 
-	tcd->biter = cpu_to_le16(EDMA_TCD_BITER_BITER(biter));
 	if (major_int)
 		csr |= EDMA_TCD_CSR_INT_MAJOR;
 
@@ -539,7 +545,7 @@ void fsl_edma_fill_tcd(struct fsl_edma_chan *fsl_chan,
 	if (fsl_chan->is_sw)
 		csr |= EDMA_TCD_CSR_START;
 
-	tcd->csr = cpu_to_le16(csr);
+	fsl_edma_set_tcd_to_le(fsl_chan, tcd, csr, csr);
 }
 
 static struct fsl_edma_desc *fsl_edma_alloc_desc(struct fsl_edma_chan *fsl_chan,
@@ -580,8 +586,9 @@ struct dma_async_tx_descriptor *fsl_edma_prep_dma_cyclic(
 	dma_addr_t dma_buf_next;
 	bool major_int = true;
 	int sg_len, i;
-	u32 src_addr, dst_addr, last_sg, nbytes;
+	dma_addr_t src_addr, dst_addr, last_sg;
 	u16 soff, doff, iter;
+	u32 nbytes;
 
 	if (!is_slave_direction(direction))
 		return NULL;
@@ -653,8 +660,9 @@ struct dma_async_tx_descriptor *fsl_edma_prep_slave_sg(
 	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
 	struct fsl_edma_desc *fsl_desc;
 	struct scatterlist *sg;
-	u32 src_addr, dst_addr, last_sg, nbytes;
+	dma_addr_t src_addr, dst_addr, last_sg;
 	u16 soff, doff, iter;
+	u32 nbytes;
 	int i;
 
 	if (!is_slave_direction(direction))
@@ -803,7 +811,8 @@ int fsl_edma_alloc_chan_resources(struct dma_chan *chan)
 	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
 
 	fsl_chan->tcd_pool = dma_pool_create("tcd_pool", chan->device->dev,
-				sizeof(struct fsl_edma_hw_tcd),
+				fsl_edma_drvflags(fsl_chan) & FSL_EDMA_DRV_TCD64 ?
+				sizeof(struct fsl_edma_hw_tcd64) : sizeof(struct fsl_edma_hw_tcd),
 				32, 0);
 	return 0;
 }
diff --git a/drivers/dma/fsl-edma-common.h b/drivers/dma/fsl-edma-common.h
index bb5221158a77..7bf0aba471a8 100644
--- a/drivers/dma/fsl-edma-common.h
+++ b/drivers/dma/fsl-edma-common.h
@@ -30,8 +30,9 @@
 #define EDMA_TCD_ATTR_SSIZE(x)		(((x) & GENMASK(2, 0)) << 8)
 #define EDMA_TCD_ATTR_SMOD(x)		(((x) & GENMASK(4, 0)) << 11)
 
-#define EDMA_TCD_CITER_CITER(x)		((x) & GENMASK(14, 0))
-#define EDMA_TCD_BITER_BITER(x)		((x) & GENMASK(14, 0))
+#define EDMA_TCD_ITER_MASK		GENMASK(14, 0)
+#define EDMA_TCD_CITER_CITER(x)		((x) & EDMA_TCD_ITER_MASK)
+#define EDMA_TCD_BITER_BITER(x)		((x) & EDMA_TCD_ITER_MASK)
 
 #define EDMA_TCD_CSR_START		BIT(0)
 #define EDMA_TCD_CSR_INT_MAJOR		BIT(1)
@@ -87,6 +88,20 @@ struct fsl_edma_hw_tcd {
 	__le16	biter;
 };
 
+struct fsl_edma_hw_tcd64 {
+	__le64  saddr;
+	__le16  soff;
+	__le16  attr;
+	__le32  nbytes;
+	__le64  slast;
+	__le64  daddr;
+	__le64  dlast_sga;
+	__le16  doff;
+	__le16  citer;
+	__le16  csr;
+	__le16  biter;
+} __packed;
+
 struct fsl_edma3_ch_reg {
 	__le32	ch_csr;
 	__le32	ch_es;
@@ -96,7 +111,10 @@ struct fsl_edma3_ch_reg {
 	__le32	ch_mux;
 	__le32  ch_mattr; /* edma4, reserved for edma3 */
 	__le32  ch_reserved;
-	struct fsl_edma_hw_tcd tcd;
+	union {
+		struct fsl_edma_hw_tcd tcd;
+		struct fsl_edma_hw_tcd64 tcd64;
+	};
 } __packed;
 
 /*
@@ -125,7 +143,7 @@ struct edma_regs {
 
 struct fsl_edma_sw_tcd {
 	dma_addr_t			ptcd;
-	struct fsl_edma_hw_tcd		*vtcd;
+	void				*vtcd;
 };
 
 struct fsl_edma_chan {
@@ -144,7 +162,8 @@ struct fsl_edma_chan {
 	u32				dma_dev_size;
 	enum dma_data_direction		dma_dir;
 	char				chan_name[32];
-	struct fsl_edma_hw_tcd __iomem *tcd;
+	void __iomem			*tcd;
+	void __iomem			*mux_addr;
 	u32				real_count;
 	struct work_struct		issue_worker;
 	struct platform_device		*pdev;
@@ -187,6 +206,7 @@ struct fsl_edma_desc {
 #define FSL_EDMA_DRV_CLEAR_DONE_E_SG	BIT(13)
 /* Need clean CHn_CSR DONE before enable TCD's MAJORELINK */
 #define FSL_EDMA_DRV_CLEAR_DONE_E_LINK	BIT(14)
+#define FSL_EDMA_DRV_TCD64		BIT(15)
 
 #define FSL_EDMA_DRV_EDMA3	(FSL_EDMA_DRV_SPLIT_REG |	\
 				 FSL_EDMA_DRV_BUS_8BYTE |	\
@@ -206,6 +226,8 @@ struct fsl_edma_drvdata {
 	u32			chreg_off;
 	u32			chreg_space_sz;
 	u32			flags;
+	u32			mux_off;	/* channel mux register offset */
+	u32			mux_skip;	/* how much skip for each channel */
 	int			(*setup_irq)(struct platform_device *pdev,
 					     struct fsl_edma_engine *fsl_edma);
 };
@@ -228,23 +250,108 @@ struct fsl_edma_engine {
 	struct fsl_edma_chan	chans[] __counted_by(n_chans);
 };
 
-#define edma_read_tcdreg(chan, __name)				\
-(sizeof(chan->tcd->__name) == sizeof(u32) ?			\
-	edma_readl(chan->edma, &chan->tcd->__name) :		\
-	edma_readw(chan->edma, &chan->tcd->__name))
-
-#define edma_write_tcdreg(chan, val, __name)			\
-(sizeof(chan->tcd->__name) == sizeof(u32) ?			\
-	edma_writel(chan->edma, (u32 __force)val, &chan->tcd->__name) :	\
-	edma_writew(chan->edma, (u16 __force)val, &chan->tcd->__name))
+#define edma_read_tcdreg_c(chan, _tcd,  __name)				\
+(sizeof((_tcd)->__name) == sizeof(u64) ?				\
+	edma_readq(chan->edma, &(_tcd)->__name) :			\
+		((sizeof((_tcd)->__name) == sizeof(u32)) ?		\
+			edma_readl(chan->edma, &(_tcd)->__name) :	\
+			edma_readw(chan->edma, &(_tcd)->__name)		\
+		))
+
+#define edma_read_tcdreg(chan, __name)								\
+((fsl_edma_drvflags(chan) & FSL_EDMA_DRV_TCD64) ?						\
+	edma_read_tcdreg_c(chan, ((struct fsl_edma_hw_tcd64 __iomem *)chan->tcd), __name) :	\
+	edma_read_tcdreg_c(chan, ((struct fsl_edma_hw_tcd __iomem *)chan->tcd), __name)		\
+)
+
+#define edma_write_tcdreg_c(chan, _tcd, _val, __name)				\
+do {										\
+	switch (sizeof(_tcd->__name)) {						\
+	case sizeof(u64):							\
+		edma_writeq(chan->edma, (u64 __force)_val, &_tcd->__name);	\
+		break;								\
+	case sizeof(u32):							\
+		edma_writel(chan->edma, (u32 __force)_val, &_tcd->__name);	\
+		break;								\
+	case sizeof(u16):							\
+		edma_writew(chan->edma, (u16 __force)_val, &_tcd->__name);	\
+		break;								\
+	case sizeof(u8):							\
+		edma_writeb(chan->edma, (u8 __force)_val, &_tcd->__name);	\
+		break;								\
+	}									\
+} while (0)
+
+#define edma_write_tcdreg(chan, val, __name)							   \
+do {												   \
+	struct fsl_edma_hw_tcd64 __iomem *tcd64_r = (struct fsl_edma_hw_tcd64 __iomem *)chan->tcd; \
+	struct fsl_edma_hw_tcd __iomem *tcd_r = (struct fsl_edma_hw_tcd __iomem *)chan->tcd;	   \
+												   \
+	if (fsl_edma_drvflags(chan) & FSL_EDMA_DRV_TCD64)					   \
+		edma_write_tcdreg_c(chan, tcd64_r, val, __name);				   \
+	else											   \
+		edma_write_tcdreg_c(chan, tcd_r, val, __name);					   \
+} while (0)
+
+#define edma_cp_tcd_to_reg(chan, __tcd, __name)							   \
+do {	\
+	struct fsl_edma_hw_tcd64 __iomem *tcd64_r = (struct fsl_edma_hw_tcd64 __iomem *)chan->tcd; \
+	struct fsl_edma_hw_tcd __iomem *tcd_r = (struct fsl_edma_hw_tcd __iomem *)chan->tcd;	   \
+	struct fsl_edma_hw_tcd64 *tcd64_m = (struct fsl_edma_hw_tcd64 *)__tcd;			   \
+	struct fsl_edma_hw_tcd *tcd_m = (struct fsl_edma_hw_tcd *)__tcd;			   \
+												   \
+	if (fsl_edma_drvflags(chan) & FSL_EDMA_DRV_TCD64)					   \
+		edma_write_tcdreg_c(chan, tcd64_r,  tcd64_m->__name, __name);			   \
+	else											   \
+		edma_write_tcdreg_c(chan, tcd_r, tcd_m->__name, __name);			   \
+} while (0)
 
 #define edma_readl_chreg(chan, __name)				\
 	edma_readl(chan->edma,					\
-		   (void __iomem *)&(container_of(chan->tcd, struct fsl_edma3_ch_reg, tcd)->__name))
+		   (void __iomem *)&(container_of(((__force void *)chan->tcd),\
+						  struct fsl_edma3_ch_reg, tcd)->__name))
 
 #define edma_writel_chreg(chan, val,  __name)			\
 	edma_writel(chan->edma, val,				\
-		   (void __iomem *)&(container_of(chan->tcd, struct fsl_edma3_ch_reg, tcd)->__name))
+		   (void __iomem *)&(container_of(((__force void *)chan->tcd),\
+						  struct fsl_edma3_ch_reg, tcd)->__name))
+
+#define fsl_edma_get_tcd(_chan, _tcd, _field)			\
+(fsl_edma_drvflags(_chan) & FSL_EDMA_DRV_TCD64 ? (((struct fsl_edma_hw_tcd64 *)_tcd)->_field) : \
+						 (((struct fsl_edma_hw_tcd *)_tcd)->_field))
+
+#define fsl_edma_le_to_cpu(x)						\
+(sizeof(x) == sizeof(u64) ? le64_to_cpu((__force __le64)(x)) :		\
+	(sizeof(x) == sizeof(u32) ? le32_to_cpu((__force __le32)(x)) :	\
+				    le16_to_cpu((__force __le16)(x))))
+
+#define fsl_edma_get_tcd_to_cpu(_chan, _tcd, _field)				\
+(fsl_edma_drvflags(_chan) & FSL_EDMA_DRV_TCD64 ?				\
+	fsl_edma_le_to_cpu(((struct fsl_edma_hw_tcd64 *)_tcd)->_field) :	\
+	fsl_edma_le_to_cpu(((struct fsl_edma_hw_tcd *)_tcd)->_field))
+
+#define fsl_edma_set_tcd_to_le_c(_tcd, _val, _field)					\
+do {											\
+	switch (sizeof((_tcd)->_field)) {						\
+	case sizeof(u64):								\
+		*(__force __le64 *)(&((_tcd)->_field)) = cpu_to_le64(_val);		\
+		break;									\
+	case sizeof(u32):								\
+		*(__force __le32 *)(&((_tcd)->_field)) = cpu_to_le32(_val);		\
+		break;									\
+	case sizeof(u16):								\
+		*(__force __le16 *)(&((_tcd)->_field)) = cpu_to_le16(_val);		\
+		break;									\
+	}										\
+} while (0)
+
+#define fsl_edma_set_tcd_to_le(_chan, _tcd, _val, _field)	\
+do {								\
+	if (fsl_edma_drvflags(_chan) & FSL_EDMA_DRV_TCD64)	\
+		fsl_edma_set_tcd_to_le_c((struct fsl_edma_hw_tcd64 *)_tcd, _val, _field);	\
+	else											\
+		fsl_edma_set_tcd_to_le_c((struct fsl_edma_hw_tcd *)_tcd, _val, _field);		\
+} while (0)
 
 /*
  * R/W functions for big- or little-endian registers:
@@ -252,6 +359,21 @@ struct fsl_edma_engine {
  * For the big-endian IP module, the offset for 8-bit or 16-bit registers
  * should also be swapped opposite to that in little-endian IP.
  */
+static inline u64 edma_readq(struct fsl_edma_engine *edma, void __iomem *addr)
+{
+	u64 l, h;
+
+	if (edma->big_endian) {
+		l = ioread32be(addr);
+		h = ioread32be(addr + 4);
+	} else {
+		l = ioread32(addr);
+		h = ioread32(addr + 4);
+	}
+
+	return (h << 32) | l;
+}
+
 static inline u32 edma_readl(struct fsl_edma_engine *edma, void __iomem *addr)
 {
 	if (edma->big_endian)
@@ -297,6 +419,18 @@ static inline void edma_writel(struct fsl_edma_engine *edma,
 		iowrite32(val, addr);
 }
 
+static inline void edma_writeq(struct fsl_edma_engine *edma,
+			       u64 val, void __iomem *addr)
+{
+	if (edma->big_endian) {
+		iowrite32be(val & 0xFFFFFFFF, addr);
+		iowrite32be(val >> 32, addr + 4);
+	} else {
+		iowrite32(val & 0xFFFFFFFF, addr);
+		iowrite32(val >> 32, addr + 4);
+	}
+}
+
 static inline struct fsl_edma_chan *to_fsl_edma_chan(struct dma_chan *chan)
 {
 	return container_of(chan, struct fsl_edma_chan, vchan.chan);
diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c
index 45cc419b1b4a..402f0058a180 100644
--- a/drivers/dma/fsl-edma-main.c
+++ b/drivers/dma/fsl-edma-main.c
@@ -10,6 +10,7 @@
  */
 
 #include <dt-bindings/dma/fsl-edma.h>
+#include <linux/bitfield.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
 #include <linux/clk.h>
@@ -359,6 +360,18 @@ static struct fsl_edma_drvdata imx93_data4 = {
 	.flags = FSL_EDMA_DRV_HAS_CHMUX | FSL_EDMA_DRV_HAS_DMACLK | FSL_EDMA_DRV_EDMA4,
 	.chreg_space_sz = 0x8000,
 	.chreg_off = 0x10000,
+	.mux_off = 0x10000 + offsetof(struct fsl_edma3_ch_reg, ch_mux),
+	.mux_skip = 0x8000,
+	.setup_irq = fsl_edma3_irq_init,
+};
+
+static struct fsl_edma_drvdata imx95_data5 = {
+	.flags = FSL_EDMA_DRV_HAS_CHMUX | FSL_EDMA_DRV_HAS_DMACLK | FSL_EDMA_DRV_EDMA4 |
+		 FSL_EDMA_DRV_TCD64,
+	.chreg_space_sz = 0x8000,
+	.chreg_off = 0x10000,
+	.mux_off = 0x200,
+	.mux_skip = sizeof(u32),
 	.setup_irq = fsl_edma3_irq_init,
 };
 
@@ -370,6 +383,7 @@ static const struct of_device_id fsl_edma_dt_ids[] = {
 	{ .compatible = "fsl,imx8qm-adma", .data = &imx8qm_audio_data},
 	{ .compatible = "fsl,imx93-edma3", .data = &imx93_data3},
 	{ .compatible = "fsl,imx93-edma4", .data = &imx93_data4},
+	{ .compatible = "fsl,imx95-edma5", .data = &imx95_data5},
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, fsl_edma_dt_ids);
@@ -510,6 +524,9 @@ static int fsl_edma_probe(struct platform_device *pdev)
 			return ret;
 	}
 
+	if (drvdata->flags & FSL_EDMA_DRV_TCD64)
+		dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+
 	INIT_LIST_HEAD(&fsl_edma->dma_dev.channels);
 	for (i = 0; i < fsl_edma->n_chans; i++) {
 		struct fsl_edma_chan *fsl_chan = &fsl_edma->chans[i];
@@ -532,11 +549,12 @@ static int fsl_edma_probe(struct platform_device *pdev)
 				offsetof(struct fsl_edma3_ch_reg, tcd) : 0;
 		fsl_chan->tcd = fsl_edma->membase
 				+ i * drvdata->chreg_space_sz + drvdata->chreg_off + len;
+		fsl_chan->mux_addr = fsl_edma->membase + drvdata->mux_off + i * drvdata->mux_skip;
 
 		fsl_chan->pdev = pdev;
 		vchan_init(&fsl_chan->vchan, &fsl_edma->dma_dev);
 
-		edma_write_tcdreg(fsl_chan, 0, csr);
+		edma_write_tcdreg(fsl_chan, cpu_to_le32(0), csr);
 		fsl_edma_chan_mux(fsl_chan, 0, false);
 	}
 
@@ -582,7 +600,8 @@ static int fsl_edma_probe(struct platform_device *pdev)
 					DMAENGINE_ALIGN_32_BYTES;
 
 	/* Per worst case 'nbytes = 1' take CITER as the max_seg_size */
-	dma_set_max_seg_size(fsl_edma->dma_dev.dev, 0x3fff);
+	dma_set_max_seg_size(fsl_edma->dma_dev.dev,
+			     FIELD_GET(EDMA_TCD_ITER_MASK, EDMA_TCD_ITER_MASK));
 
 	fsl_edma->dma_dev.residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT;
 
diff --git a/drivers/dma/fsl-qdma.c b/drivers/dma/fsl-qdma.c
index f405c77060ad..5005e138fc23 100644
--- a/drivers/dma/fsl-qdma.c
+++ b/drivers/dma/fsl-qdma.c
@@ -109,6 +109,7 @@
 #define FSL_QDMA_CMD_WTHROTL_OFFSET	20
 #define FSL_QDMA_CMD_DSEN_OFFSET	19
 #define FSL_QDMA_CMD_LWC_OFFSET		16
+#define FSL_QDMA_CMD_PF			BIT(17)
 
 /* Field definition for Descriptor status */
 #define QDMA_CCDF_STATUS_RTE		BIT(5)
@@ -160,6 +161,10 @@ struct fsl_qdma_format {
 			u8 __reserved1[2];
 			u8 cfg8b_w1;
 		} __packed;
+		struct {
+			__le32 __reserved2;
+			__le32 cmd;
+		} __packed;
 		__le64 data;
 	};
 } __packed;
@@ -354,7 +359,6 @@ static void fsl_qdma_free_chan_resources(struct dma_chan *chan)
 static void fsl_qdma_comp_fill_memcpy(struct fsl_qdma_comp *fsl_comp,
 				      dma_addr_t dst, dma_addr_t src, u32 len)
 {
-	u32 cmd;
 	struct fsl_qdma_format *sdf, *ddf;
 	struct fsl_qdma_format *ccdf, *csgf_desc, *csgf_src, *csgf_dest;
 
@@ -383,14 +387,11 @@ static void fsl_qdma_comp_fill_memcpy(struct fsl_qdma_comp *fsl_comp,
 	/* This entry is the last entry. */
 	qdma_csgf_set_f(csgf_dest, len);
 	/* Descriptor Buffer */
-	cmd = cpu_to_le32(FSL_QDMA_CMD_RWTTYPE <<
-			  FSL_QDMA_CMD_RWTTYPE_OFFSET);
-	sdf->data = QDMA_SDDF_CMD(cmd);
-
-	cmd = cpu_to_le32(FSL_QDMA_CMD_RWTTYPE <<
-			  FSL_QDMA_CMD_RWTTYPE_OFFSET);
-	cmd |= cpu_to_le32(FSL_QDMA_CMD_LWC << FSL_QDMA_CMD_LWC_OFFSET);
-	ddf->data = QDMA_SDDF_CMD(cmd);
+	sdf->cmd = cpu_to_le32((FSL_QDMA_CMD_RWTTYPE << FSL_QDMA_CMD_RWTTYPE_OFFSET) |
+			       FSL_QDMA_CMD_PF);
+
+	ddf->cmd = cpu_to_le32((FSL_QDMA_CMD_RWTTYPE << FSL_QDMA_CMD_RWTTYPE_OFFSET) |
+			       (FSL_QDMA_CMD_LWC << FSL_QDMA_CMD_LWC_OFFSET));
 }
 
 /*
@@ -624,7 +625,7 @@ static int fsl_qdma_halt(struct fsl_qdma_engine *fsl_qdma)
 
 static int
 fsl_qdma_queue_transfer_complete(struct fsl_qdma_engine *fsl_qdma,
-				 void *block,
+				 __iomem void *block,
 				 int id)
 {
 	bool duplicate;
@@ -1196,10 +1197,6 @@ static int fsl_qdma_probe(struct platform_device *pdev)
 	if (!fsl_qdma->queue)
 		return -ENOMEM;
 
-	ret = fsl_qdma_irq_init(pdev, fsl_qdma);
-	if (ret)
-		return ret;
-
 	fsl_qdma->irq_base = platform_get_irq_byname(pdev, "qdma-queue0");
 	if (fsl_qdma->irq_base < 0)
 		return fsl_qdma->irq_base;
@@ -1238,16 +1235,19 @@ static int fsl_qdma_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, fsl_qdma);
 
-	ret = dma_async_device_register(&fsl_qdma->dma_dev);
+	ret = fsl_qdma_reg_init(fsl_qdma);
 	if (ret) {
-		dev_err(&pdev->dev,
-			"Can't register NXP Layerscape qDMA engine.\n");
+		dev_err(&pdev->dev, "Can't Initialize the qDMA engine.\n");
 		return ret;
 	}
 
-	ret = fsl_qdma_reg_init(fsl_qdma);
+	ret = fsl_qdma_irq_init(pdev, fsl_qdma);
+	if (ret)
+		return ret;
+
+	ret = dma_async_device_register(&fsl_qdma->dma_dev);
 	if (ret) {
-		dev_err(&pdev->dev, "Can't Initialize the qDMA engine.\n");
+		dev_err(&pdev->dev, "Can't register NXP Layerscape qDMA engine.\n");
 		return ret;
 	}
 
diff --git a/drivers/dma/idxd/bus.c b/drivers/dma/idxd/bus.c
index 0c9e689a2e77..b83b27e04f2a 100644
--- a/drivers/dma/idxd/bus.c
+++ b/drivers/dma/idxd/bus.c
@@ -72,7 +72,7 @@ static int idxd_bus_uevent(const struct device *dev, struct kobj_uevent_env *env
 	return add_uevent_var(env, "MODALIAS=" IDXD_DEVICES_MODALIAS_FMT, 0);
 }
 
-struct bus_type dsa_bus_type = {
+const struct bus_type dsa_bus_type = {
 	.name = "dsa",
 	.match = idxd_config_bus_match,
 	.probe = idxd_config_bus_probe,
diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c
index 77f8885cf407..8078ab9acfbc 100644
--- a/drivers/dma/idxd/cdev.c
+++ b/drivers/dma/idxd/cdev.c
@@ -152,7 +152,7 @@ static void idxd_file_dev_release(struct device *dev)
 	mutex_unlock(&wq->wq_lock);
 }
 
-static struct device_type idxd_cdev_file_type = {
+static const struct device_type idxd_cdev_file_type = {
 	.name = "idxd_file",
 	.release = idxd_file_dev_release,
 	.groups = cdev_file_attribute_groups,
@@ -169,7 +169,7 @@ static void idxd_cdev_dev_release(struct device *dev)
 	kfree(idxd_cdev);
 }
 
-static struct device_type idxd_cdev_device_type = {
+static const struct device_type idxd_cdev_device_type = {
 	.name = "idxd_cdev",
 	.release = idxd_cdev_dev_release,
 };
@@ -345,7 +345,7 @@ static void idxd_cdev_evl_drain_pasid(struct idxd_wq *wq, u32 pasid)
 	spin_lock(&evl->lock);
 	status.bits = ioread64(idxd->reg_base + IDXD_EVLSTATUS_OFFSET);
 	t = status.tail;
-	h = evl->head;
+	h = status.head;
 	size = evl->size;
 
 	while (h != t) {
diff --git a/drivers/dma/idxd/debugfs.c b/drivers/dma/idxd/debugfs.c
index 9cfbd9b14c4c..f3f25ee676f3 100644
--- a/drivers/dma/idxd/debugfs.c
+++ b/drivers/dma/idxd/debugfs.c
@@ -68,9 +68,9 @@ static int debugfs_evl_show(struct seq_file *s, void *d)
 
 	spin_lock(&evl->lock);
 
-	h = evl->head;
 	evl_status.bits = ioread64(idxd->reg_base + IDXD_EVLSTATUS_OFFSET);
 	t = evl_status.tail;
+	h = evl_status.head;
 	evl_size = evl->size;
 
 	seq_printf(s, "Event Log head %u tail %u interrupt pending %u\n\n",
diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h
index 47de3f93ff1e..a4099a1e2340 100644
--- a/drivers/dma/idxd/idxd.h
+++ b/drivers/dma/idxd/idxd.h
@@ -282,7 +282,7 @@ typedef int (*load_device_defaults_fn_t) (struct idxd_device *idxd);
 struct idxd_driver_data {
 	const char *name_prefix;
 	enum idxd_type type;
-	struct device_type *dev_type;
+	const struct device_type *dev_type;
 	int compl_size;
 	int align;
 	int evl_cr_off;
@@ -300,7 +300,6 @@ struct idxd_evl {
 	unsigned int log_size;
 	/* The number of entries in the event log. */
 	u16 size;
-	u16 head;
 	unsigned long *bmap;
 	bool batch_fail[IDXD_MAX_BATCH_IDENT];
 };
@@ -516,15 +515,15 @@ static inline void idxd_set_user_intr(struct idxd_device *idxd, bool enable)
 	iowrite32(reg.bits, idxd->reg_base + IDXD_GENCFG_OFFSET);
 }
 
-extern struct bus_type dsa_bus_type;
+extern const struct bus_type dsa_bus_type;
 
 extern bool support_enqcmd;
 extern struct ida idxd_ida;
-extern struct device_type dsa_device_type;
-extern struct device_type iax_device_type;
-extern struct device_type idxd_wq_device_type;
-extern struct device_type idxd_engine_device_type;
-extern struct device_type idxd_group_device_type;
+extern const struct device_type dsa_device_type;
+extern const struct device_type iax_device_type;
+extern const struct device_type idxd_wq_device_type;
+extern const struct device_type idxd_engine_device_type;
+extern const struct device_type idxd_group_device_type;
 
 static inline bool is_dsa_dev(struct idxd_dev *idxd_dev)
 {
diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c
index 14df1f1347a8..4954adc6bb60 100644
--- a/drivers/dma/idxd/init.c
+++ b/drivers/dma/idxd/init.c
@@ -343,7 +343,9 @@ static void idxd_cleanup_internals(struct idxd_device *idxd)
 static int idxd_init_evl(struct idxd_device *idxd)
 {
 	struct device *dev = &idxd->pdev->dev;
+	unsigned int evl_cache_size;
 	struct idxd_evl *evl;
+	const char *idxd_name;
 
 	if (idxd->hw.gen_cap.evl_support == 0)
 		return 0;
@@ -355,9 +357,16 @@ static int idxd_init_evl(struct idxd_device *idxd)
 	spin_lock_init(&evl->lock);
 	evl->size = IDXD_EVL_SIZE_MIN;
 
-	idxd->evl_cache = kmem_cache_create(dev_name(idxd_confdev(idxd)),
-					    sizeof(struct idxd_evl_fault) + evl_ent_size(idxd),
-					    0, 0, NULL);
+	idxd_name = dev_name(idxd_confdev(idxd));
+	evl_cache_size = sizeof(struct idxd_evl_fault) + evl_ent_size(idxd);
+	/*
+	 * Since completion record in evl_cache will be copied to user
+	 * when handling completion record page fault, need to create
+	 * the cache suitable for user copy.
+	 */
+	idxd->evl_cache = kmem_cache_create_usercopy(idxd_name, evl_cache_size,
+						     0, 0, 0, evl_cache_size,
+						     NULL);
 	if (!idxd->evl_cache) {
 		kfree(evl);
 		return -ENOMEM;
diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c
index c8a0aa874b11..348aa21389a9 100644
--- a/drivers/dma/idxd/irq.c
+++ b/drivers/dma/idxd/irq.c
@@ -367,9 +367,9 @@ static void process_evl_entries(struct idxd_device *idxd)
 	/* Clear interrupt pending bit */
 	iowrite32(evl_status.bits_upper32,
 		  idxd->reg_base + IDXD_EVLSTATUS_OFFSET + sizeof(u32));
-	h = evl->head;
 	evl_status.bits = ioread64(idxd->reg_base + IDXD_EVLSTATUS_OFFSET);
 	t = evl_status.tail;
+	h = evl_status.head;
 	size = idxd->evl->size;
 
 	while (h != t) {
@@ -378,7 +378,6 @@ static void process_evl_entries(struct idxd_device *idxd)
 		h = (h + 1) % size;
 	}
 
-	evl->head = h;
 	evl_status.head = h;
 	iowrite32(evl_status.bits_lower32, idxd->reg_base + IDXD_EVLSTATUS_OFFSET);
 	spin_unlock(&evl->lock);
diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c
index 523ae0dff7d4..7f28f01be672 100644
--- a/drivers/dma/idxd/sysfs.c
+++ b/drivers/dma/idxd/sysfs.c
@@ -91,7 +91,7 @@ static void idxd_conf_engine_release(struct device *dev)
 	kfree(engine);
 }
 
-struct device_type idxd_engine_device_type = {
+const struct device_type idxd_engine_device_type = {
 	.name = "engine",
 	.release = idxd_conf_engine_release,
 	.groups = idxd_engine_attribute_groups,
@@ -577,7 +577,7 @@ static void idxd_conf_group_release(struct device *dev)
 	kfree(group);
 }
 
-struct device_type idxd_group_device_type = {
+const struct device_type idxd_group_device_type = {
 	.name = "group",
 	.release = idxd_conf_group_release,
 	.groups = idxd_group_attribute_groups,
@@ -1369,7 +1369,7 @@ static void idxd_conf_wq_release(struct device *dev)
 	kfree(wq);
 }
 
-struct device_type idxd_wq_device_type = {
+const struct device_type idxd_wq_device_type = {
 	.name = "wq",
 	.release = idxd_conf_wq_release,
 	.groups = idxd_wq_attribute_groups,
@@ -1798,13 +1798,13 @@ static void idxd_conf_device_release(struct device *dev)
 	kfree(idxd);
 }
 
-struct device_type dsa_device_type = {
+const struct device_type dsa_device_type = {
 	.name = "dsa",
 	.release = idxd_conf_device_release,
 	.groups = idxd_attribute_groups,
 };
 
-struct device_type iax_device_type = {
+const struct device_type iax_device_type = {
 	.name = "iax",
 	.release = idxd_conf_device_release,
 	.groups = idxd_attribute_groups,
diff --git a/drivers/dma/mcf-edma-main.c b/drivers/dma/mcf-edma-main.c
index ab21455d9c3a..dba631783876 100644
--- a/drivers/dma/mcf-edma-main.c
+++ b/drivers/dma/mcf-edma-main.c
@@ -202,7 +202,7 @@ static int mcf_edma_probe(struct platform_device *pdev)
 		vchan_init(&mcf_chan->vchan, &mcf_edma->dma_dev);
 		mcf_chan->tcd = mcf_edma->membase + EDMA_TCD
 				+ i * sizeof(struct fsl_edma_hw_tcd);
-		iowrite32(0x0, &mcf_chan->tcd->csr);
+		edma_write_tcdreg(mcf_chan, cpu_to_le32(0), csr);
 	}
 
 	iowrite32(~0, regs->inth);
diff --git a/drivers/dma/mv_xor_v2.c b/drivers/dma/mv_xor_v2.c
index 1ebfbe88e733..97ebc791a30b 100644
--- a/drivers/dma/mv_xor_v2.c
+++ b/drivers/dma/mv_xor_v2.c
@@ -747,8 +747,8 @@ static int mv_xor_v2_probe(struct platform_device *pdev)
 	if (IS_ERR(xor_dev->clk))
 		return PTR_ERR(xor_dev->clk);
 
-	ret = platform_msi_domain_alloc_irqs(&pdev->dev, 1,
-					     mv_xor_v2_set_msi_msg);
+	ret = platform_device_msi_init_and_alloc_irqs(&pdev->dev, 1,
+						      mv_xor_v2_set_msi_msg);
 	if (ret)
 		return ret;
 
@@ -851,7 +851,7 @@ free_hw_desq:
 			  xor_dev->desc_size * MV_XOR_V2_DESC_NUM,
 			  xor_dev->hw_desq_virt, xor_dev->hw_desq);
 free_msi_irqs:
-	platform_msi_domain_free_irqs(&pdev->dev);
+	platform_device_msi_free_irqs_all(&pdev->dev);
 	return ret;
 }
 
@@ -867,7 +867,7 @@ static void mv_xor_v2_remove(struct platform_device *pdev)
 
 	devm_free_irq(&pdev->dev, xor_dev->irq, xor_dev);
 
-	platform_msi_domain_free_irqs(&pdev->dev);
+	platform_device_msi_free_irqs_all(&pdev->dev);
 
 	tasklet_kill(&xor_dev->irq_tasklet);
 }
diff --git a/drivers/dma/of-dma.c b/drivers/dma/of-dma.c
index 775a7f408b9a..e588fff9f21d 100644
--- a/drivers/dma/of-dma.c
+++ b/drivers/dma/of-dma.c
@@ -29,7 +29,7 @@ static DEFINE_MUTEX(of_dma_lock);
  * to the DMA data stored is retuned. A NULL pointer is returned if no match is
  * found.
  */
-static struct of_dma *of_dma_find_controller(struct of_phandle_args *dma_spec)
+static struct of_dma *of_dma_find_controller(const struct of_phandle_args *dma_spec)
 {
 	struct of_dma *ofdma;
 
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index c29744bfdf2c..5f6d7f1e095f 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -2588,6 +2588,7 @@ static struct dma_pl330_desc *pluck_desc(struct list_head *pool,
 
 		desc->status = PREP;
 		desc->txd.callback = NULL;
+		desc->txd.callback_result = NULL;
 	}
 
 	spin_unlock_irqrestore(lock, flags);
diff --git a/drivers/dma/ptdma/ptdma-dmaengine.c b/drivers/dma/ptdma/ptdma-dmaengine.c
index 1aa65e5de0f3..f79240734807 100644
--- a/drivers/dma/ptdma/ptdma-dmaengine.c
+++ b/drivers/dma/ptdma/ptdma-dmaengine.c
@@ -385,8 +385,6 @@ int pt_dmaengine_register(struct pt_device *pt)
 	chan->vc.desc_free = pt_do_cleanup;
 	vchan_init(&chan->vc, dma_dev);
 
-	dma_set_mask_and_coherent(pt->dev, DMA_BIT_MASK(64));
-
 	ret = dma_async_device_register(dma_dev);
 	if (ret)
 		goto err_reg;
diff --git a/drivers/dma/qcom/hidma.c b/drivers/dma/qcom/hidma.c
index d63b93dc7047..202ac95227cb 100644
--- a/drivers/dma/qcom/hidma.c
+++ b/drivers/dma/qcom/hidma.c
@@ -696,7 +696,7 @@ static void hidma_free_msis(struct hidma_dev *dmadev)
 			devm_free_irq(dev, virq, &dmadev->lldev);
 	}
 
-	platform_msi_domain_free_irqs(dev);
+	platform_device_msi_free_irqs_all(dev);
 #endif
 }
 
@@ -706,8 +706,8 @@ static int hidma_request_msi(struct hidma_dev *dmadev,
 #ifdef CONFIG_GENERIC_MSI_IRQ
 	int rc, i, virq;
 
-	rc = platform_msi_domain_alloc_irqs(&pdev->dev, HIDMA_MSI_INTS,
-					    hidma_write_msi_msg);
+	rc = platform_device_msi_init_and_alloc_irqs(&pdev->dev, HIDMA_MSI_INTS,
+						     hidma_write_msi_msg);
 	if (rc)
 		return rc;
 
diff --git a/drivers/dma/ti/k3-psil-j721s2.c b/drivers/dma/ti/k3-psil-j721s2.c
index 1d5430fc5724..ba08bdcdcd2b 100644
--- a/drivers/dma/ti/k3-psil-j721s2.c
+++ b/drivers/dma/ti/k3-psil-j721s2.c
@@ -57,6 +57,14 @@
 		},					\
 	}
 
+#define PSIL_CSI2RX(x)					\
+	{						\
+		.thread_id = x,				\
+		.ep_config = {				\
+			.ep_type = PSIL_EP_NATIVE,	\
+		},					\
+	}
+
 /* PSI-L source thread IDs, used for RX (DMA_DEV_TO_MEM) */
 static struct psil_ep j721s2_src_ep_map[] = {
 	/* PDMA_MCASP - McASP0-4 */
@@ -114,6 +122,71 @@ static struct psil_ep j721s2_src_ep_map[] = {
 	PSIL_PDMA_XY_PKT(0x4707),
 	PSIL_PDMA_XY_PKT(0x4708),
 	PSIL_PDMA_XY_PKT(0x4709),
+	/* CSI2RX */
+	PSIL_CSI2RX(0x4940),
+	PSIL_CSI2RX(0x4941),
+	PSIL_CSI2RX(0x4942),
+	PSIL_CSI2RX(0x4943),
+	PSIL_CSI2RX(0x4944),
+	PSIL_CSI2RX(0x4945),
+	PSIL_CSI2RX(0x4946),
+	PSIL_CSI2RX(0x4947),
+	PSIL_CSI2RX(0x4948),
+	PSIL_CSI2RX(0x4949),
+	PSIL_CSI2RX(0x494a),
+	PSIL_CSI2RX(0x494b),
+	PSIL_CSI2RX(0x494c),
+	PSIL_CSI2RX(0x494d),
+	PSIL_CSI2RX(0x494e),
+	PSIL_CSI2RX(0x494f),
+	PSIL_CSI2RX(0x4950),
+	PSIL_CSI2RX(0x4951),
+	PSIL_CSI2RX(0x4952),
+	PSIL_CSI2RX(0x4953),
+	PSIL_CSI2RX(0x4954),
+	PSIL_CSI2RX(0x4955),
+	PSIL_CSI2RX(0x4956),
+	PSIL_CSI2RX(0x4957),
+	PSIL_CSI2RX(0x4958),
+	PSIL_CSI2RX(0x4959),
+	PSIL_CSI2RX(0x495a),
+	PSIL_CSI2RX(0x495b),
+	PSIL_CSI2RX(0x495c),
+	PSIL_CSI2RX(0x495d),
+	PSIL_CSI2RX(0x495e),
+	PSIL_CSI2RX(0x495f),
+	PSIL_CSI2RX(0x4960),
+	PSIL_CSI2RX(0x4961),
+	PSIL_CSI2RX(0x4962),
+	PSIL_CSI2RX(0x4963),
+	PSIL_CSI2RX(0x4964),
+	PSIL_CSI2RX(0x4965),
+	PSIL_CSI2RX(0x4966),
+	PSIL_CSI2RX(0x4967),
+	PSIL_CSI2RX(0x4968),
+	PSIL_CSI2RX(0x4969),
+	PSIL_CSI2RX(0x496a),
+	PSIL_CSI2RX(0x496b),
+	PSIL_CSI2RX(0x496c),
+	PSIL_CSI2RX(0x496d),
+	PSIL_CSI2RX(0x496e),
+	PSIL_CSI2RX(0x496f),
+	PSIL_CSI2RX(0x4970),
+	PSIL_CSI2RX(0x4971),
+	PSIL_CSI2RX(0x4972),
+	PSIL_CSI2RX(0x4973),
+	PSIL_CSI2RX(0x4974),
+	PSIL_CSI2RX(0x4975),
+	PSIL_CSI2RX(0x4976),
+	PSIL_CSI2RX(0x4977),
+	PSIL_CSI2RX(0x4978),
+	PSIL_CSI2RX(0x4979),
+	PSIL_CSI2RX(0x497a),
+	PSIL_CSI2RX(0x497b),
+	PSIL_CSI2RX(0x497c),
+	PSIL_CSI2RX(0x497d),
+	PSIL_CSI2RX(0x497e),
+	PSIL_CSI2RX(0x497f),
 	/* MAIN SA2UL */
 	PSIL_SA2UL(0x4a40, 0),
 	PSIL_SA2UL(0x4a41, 0),
diff --git a/drivers/dma/ti/k3-udma-glue.c b/drivers/dma/ti/k3-udma-glue.c
index c278d5facf7d..c9b93055dc9d 100644
--- a/drivers/dma/ti/k3-udma-glue.c
+++ b/drivers/dma/ti/k3-udma-glue.c
@@ -111,6 +111,35 @@ static int of_k3_udma_glue_parse(struct device_node *udmax_np,
 	return 0;
 }
 
+static int of_k3_udma_glue_parse_chn_common(struct k3_udma_glue_common *common, u32 thread_id,
+					    bool tx_chn)
+{
+	if (tx_chn && !(thread_id & K3_PSIL_DST_THREAD_ID_OFFSET))
+		return -EINVAL;
+
+	if (!tx_chn && (thread_id & K3_PSIL_DST_THREAD_ID_OFFSET))
+		return -EINVAL;
+
+	/* get psil endpoint 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);
+		return PTR_ERR(common->ep_config);
+	}
+
+	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;
+
+	return 0;
+}
+
 static int of_k3_udma_glue_parse_chn(struct device_node *chn_np,
 		const char *name, struct k3_udma_glue_common *common,
 		bool tx_chn)
@@ -153,38 +182,32 @@ static int of_k3_udma_glue_parse_chn(struct device_node *chn_np,
 		common->atype_asel = dma_spec.args[1];
 	}
 
-	if (tx_chn && !(thread_id & K3_PSIL_DST_THREAD_ID_OFFSET)) {
-		ret = -EINVAL;
-		goto out_put_spec;
-	}
+	ret = of_k3_udma_glue_parse_chn_common(common, thread_id, tx_chn);
 
-	if (!tx_chn && (thread_id & K3_PSIL_DST_THREAD_ID_OFFSET)) {
-		ret = -EINVAL;
-		goto out_put_spec;
-	}
+out_put_spec:
+	of_node_put(dma_spec.np);
+	return ret;
+}
 
-	/* get psil endpoint 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(common->ep_config);
-		goto out_put_spec;
-	}
+static int
+of_k3_udma_glue_parse_chn_by_id(struct device_node *udmax_np, struct k3_udma_glue_common *common,
+				bool tx_chn, u32 thread_id)
+{
+	int ret = 0;
 
-	common->epib = common->ep_config->needs_epib;
-	common->psdata_size = common->ep_config->psd_size;
+	if (unlikely(!udmax_np))
+		return -EINVAL;
 
-	if (tx_chn)
-		common->dst_thread = thread_id;
-	else
-		common->src_thread = thread_id;
+	ret = of_k3_udma_glue_parse(udmax_np, common);
+	if (ret)
+		goto out_put_spec;
+
+	ret = of_k3_udma_glue_parse_chn_common(common, thread_id, tx_chn);
 
 out_put_spec:
-	of_node_put(dma_spec.np);
+	of_node_put(udmax_np);
 	return ret;
-};
+}
 
 static void k3_udma_glue_dump_tx_chn(struct k3_udma_glue_tx_channel *tx_chn)
 {
@@ -251,29 +274,13 @@ static int k3_udma_glue_cfg_tx_chn(struct k3_udma_glue_tx_channel *tx_chn)
 	return tisci_rm->tisci_udmap_ops->tx_ch_cfg(tisci_rm->tisci, &req);
 }
 
-struct k3_udma_glue_tx_channel *k3_udma_glue_request_tx_chn(struct device *dev,
-		const char *name, struct k3_udma_glue_tx_channel_cfg *cfg)
+static int
+k3_udma_glue_request_tx_chn_common(struct device *dev,
+				   struct k3_udma_glue_tx_channel *tx_chn,
+				   struct k3_udma_glue_tx_channel_cfg *cfg)
 {
-	struct k3_udma_glue_tx_channel *tx_chn;
 	int ret;
 
-	tx_chn = devm_kzalloc(dev, sizeof(*tx_chn), GFP_KERNEL);
-	if (!tx_chn)
-		return ERR_PTR(-ENOMEM);
-
-	tx_chn->common.dev = dev;
-	tx_chn->common.swdata_size = cfg->swdata_size;
-	tx_chn->tx_pause_on_err = cfg->tx_pause_on_err;
-	tx_chn->tx_filt_einfo = cfg->tx_filt_einfo;
-	tx_chn->tx_filt_pswords = cfg->tx_filt_pswords;
-	tx_chn->tx_supr_tdpkt = cfg->tx_supr_tdpkt;
-
-	/* parse of udmap channel */
-	ret = of_k3_udma_glue_parse_chn(dev->of_node, name,
-					&tx_chn->common, true);
-	if (ret)
-		goto err;
-
 	tx_chn->common.hdesc_size = cppi5_hdesc_calc_size(tx_chn->common.epib,
 						tx_chn->common.psdata_size,
 						tx_chn->common.swdata_size);
@@ -289,7 +296,7 @@ struct k3_udma_glue_tx_channel *k3_udma_glue_request_tx_chn(struct device *dev,
 	if (IS_ERR(tx_chn->udma_tchanx)) {
 		ret = PTR_ERR(tx_chn->udma_tchanx);
 		dev_err(dev, "UDMAX tchanx get err %d\n", ret);
-		goto err;
+		return ret;
 	}
 	tx_chn->udma_tchan_id = xudma_tchan_get_id(tx_chn->udma_tchanx);
 
@@ -302,7 +309,7 @@ struct k3_udma_glue_tx_channel *k3_udma_glue_request_tx_chn(struct device *dev,
 		dev_err(dev, "Channel Device registration failed %d\n", ret);
 		put_device(&tx_chn->common.chan_dev);
 		tx_chn->common.chan_dev.parent = NULL;
-		goto err;
+		return ret;
 	}
 
 	if (xudma_is_pktdma(tx_chn->common.udmax)) {
@@ -326,7 +333,7 @@ struct k3_udma_glue_tx_channel *k3_udma_glue_request_tx_chn(struct device *dev,
 					     &tx_chn->ringtxcq);
 	if (ret) {
 		dev_err(dev, "Failed to get TX/TXCQ rings %d\n", ret);
-		goto err;
+		return ret;
 	}
 
 	/* Set the dma_dev for the rings to be configured */
@@ -342,13 +349,13 @@ struct k3_udma_glue_tx_channel *k3_udma_glue_request_tx_chn(struct device *dev,
 	ret = k3_ringacc_ring_cfg(tx_chn->ringtx, &cfg->tx_cfg);
 	if (ret) {
 		dev_err(dev, "Failed to cfg ringtx %d\n", ret);
-		goto err;
+		return ret;
 	}
 
 	ret = k3_ringacc_ring_cfg(tx_chn->ringtxcq, &cfg->txcq_cfg);
 	if (ret) {
 		dev_err(dev, "Failed to cfg ringtx %d\n", ret);
-		goto err;
+		return ret;
 	}
 
 	/* request and cfg psi-l */
@@ -359,11 +366,42 @@ struct k3_udma_glue_tx_channel *k3_udma_glue_request_tx_chn(struct device *dev,
 	ret = k3_udma_glue_cfg_tx_chn(tx_chn);
 	if (ret) {
 		dev_err(dev, "Failed to cfg tchan %d\n", ret);
-		goto err;
+		return ret;
 	}
 
 	k3_udma_glue_dump_tx_chn(tx_chn);
 
+	return 0;
+}
+
+struct k3_udma_glue_tx_channel *
+k3_udma_glue_request_tx_chn(struct device *dev, const char *name,
+			    struct k3_udma_glue_tx_channel_cfg *cfg)
+{
+	struct k3_udma_glue_tx_channel *tx_chn;
+	int ret;
+
+	tx_chn = devm_kzalloc(dev, sizeof(*tx_chn), GFP_KERNEL);
+	if (!tx_chn)
+		return ERR_PTR(-ENOMEM);
+
+	tx_chn->common.dev = dev;
+	tx_chn->common.swdata_size = cfg->swdata_size;
+	tx_chn->tx_pause_on_err = cfg->tx_pause_on_err;
+	tx_chn->tx_filt_einfo = cfg->tx_filt_einfo;
+	tx_chn->tx_filt_pswords = cfg->tx_filt_pswords;
+	tx_chn->tx_supr_tdpkt = cfg->tx_supr_tdpkt;
+
+	/* parse of udmap channel */
+	ret = of_k3_udma_glue_parse_chn(dev->of_node, name,
+					&tx_chn->common, true);
+	if (ret)
+		goto err;
+
+	ret = k3_udma_glue_request_tx_chn_common(dev, tx_chn, cfg);
+	if (ret)
+		goto err;
+
 	return tx_chn;
 
 err:
@@ -372,6 +410,41 @@ err:
 }
 EXPORT_SYMBOL_GPL(k3_udma_glue_request_tx_chn);
 
+struct k3_udma_glue_tx_channel *
+k3_udma_glue_request_tx_chn_for_thread_id(struct device *dev,
+					  struct k3_udma_glue_tx_channel_cfg *cfg,
+					  struct device_node *udmax_np, u32 thread_id)
+{
+	struct k3_udma_glue_tx_channel *tx_chn;
+	int ret;
+
+	tx_chn = devm_kzalloc(dev, sizeof(*tx_chn), GFP_KERNEL);
+	if (!tx_chn)
+		return ERR_PTR(-ENOMEM);
+
+	tx_chn->common.dev = dev;
+	tx_chn->common.swdata_size = cfg->swdata_size;
+	tx_chn->tx_pause_on_err = cfg->tx_pause_on_err;
+	tx_chn->tx_filt_einfo = cfg->tx_filt_einfo;
+	tx_chn->tx_filt_pswords = cfg->tx_filt_pswords;
+	tx_chn->tx_supr_tdpkt = cfg->tx_supr_tdpkt;
+
+	ret = of_k3_udma_glue_parse_chn_by_id(udmax_np, &tx_chn->common, true, thread_id);
+	if (ret)
+		goto err;
+
+	ret = k3_udma_glue_request_tx_chn_common(dev, tx_chn, cfg);
+	if (ret)
+		goto err;
+
+	return tx_chn;
+
+err:
+	k3_udma_glue_release_tx_chn(tx_chn);
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_request_tx_chn_for_thread_id);
+
 void k3_udma_glue_release_tx_chn(struct k3_udma_glue_tx_channel *tx_chn)
 {
 	if (tx_chn->psil_paired) {
@@ -1000,12 +1073,59 @@ err:
 	return ERR_PTR(ret);
 }
 
+static int
+k3_udma_glue_request_remote_rx_chn_common(struct k3_udma_glue_rx_channel *rx_chn,
+					  struct k3_udma_glue_rx_channel_cfg *cfg,
+					  struct device *dev)
+{
+	int ret, i;
+
+	rx_chn->common.hdesc_size = cppi5_hdesc_calc_size(rx_chn->common.epib,
+						rx_chn->common.psdata_size,
+						rx_chn->common.swdata_size);
+
+	rx_chn->flows = devm_kcalloc(dev, rx_chn->flow_num,
+				     sizeof(*rx_chn->flows), GFP_KERNEL);
+	if (!rx_chn->flows)
+		return -ENOMEM;
+
+	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-0x%02x",
+		     rx_chn->common.src_thread, rx_chn->flow_id_base);
+	ret = device_register(&rx_chn->common.chan_dev);
+	if (ret) {
+		dev_err(dev, "Channel Device registration failed %d\n", ret);
+		put_device(&rx_chn->common.chan_dev);
+		rx_chn->common.chan_dev.parent = NULL;
+		return ret;
+	}
+
+	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)
+		return ret;
+
+	for (i = 0; i < rx_chn->flow_num; i++)
+		rx_chn->flows[i].udma_rflow_id = rx_chn->flow_id_base + i;
+
+	k3_udma_glue_dump_rx_chn(rx_chn);
+
+	return 0;
+}
+
 static struct k3_udma_glue_rx_channel *
 k3_udma_glue_request_remote_rx_chn(struct device *dev, const char *name,
 				   struct k3_udma_glue_rx_channel_cfg *cfg)
 {
 	struct k3_udma_glue_rx_channel *rx_chn;
-	int ret, i;
+	int ret;
 
 	if (cfg->flow_id_num <= 0 ||
 	    cfg->flow_id_use_rxchan_id ||
@@ -1036,44 +1156,55 @@ k3_udma_glue_request_remote_rx_chn(struct device *dev, const char *name,
 	if (ret)
 		goto err;
 
-	rx_chn->common.hdesc_size = cppi5_hdesc_calc_size(rx_chn->common.epib,
-						rx_chn->common.psdata_size,
-						rx_chn->common.swdata_size);
-
-	rx_chn->flows = devm_kcalloc(dev, rx_chn->flow_num,
-				     sizeof(*rx_chn->flows), GFP_KERNEL);
-	if (!rx_chn->flows) {
-		ret = -ENOMEM;
+	ret = k3_udma_glue_request_remote_rx_chn_common(rx_chn, cfg, dev);
+	if (ret)
 		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);
-		put_device(&rx_chn->common.chan_dev);
-		rx_chn->common.chan_dev.parent = NULL;
-		goto err;
-	}
+	return rx_chn;
 
-	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));
-	}
+err:
+	k3_udma_glue_release_rx_chn(rx_chn);
+	return ERR_PTR(ret);
+}
 
-	ret = k3_udma_glue_allocate_rx_flows(rx_chn, cfg);
+struct k3_udma_glue_rx_channel *
+k3_udma_glue_request_remote_rx_chn_for_thread_id(struct device *dev,
+						 struct k3_udma_glue_rx_channel_cfg *cfg,
+						 struct device_node *udmax_np, u32 thread_id)
+{
+	struct k3_udma_glue_rx_channel *rx_chn;
+	int ret;
+
+	if (cfg->flow_id_num <= 0 ||
+	    cfg->flow_id_use_rxchan_id ||
+	    cfg->def_flow_cfg ||
+	    cfg->flow_id_base < 0)
+		return ERR_PTR(-EINVAL);
+
+	/*
+	 * Remote RX channel is under control of Remote CPU core, so
+	 * Linux can only request and manipulate by dedicated RX flows
+	 */
+
+	rx_chn = devm_kzalloc(dev, sizeof(*rx_chn), GFP_KERNEL);
+	if (!rx_chn)
+		return ERR_PTR(-ENOMEM);
+
+	rx_chn->common.dev = dev;
+	rx_chn->common.swdata_size = cfg->swdata_size;
+	rx_chn->remote = true;
+	rx_chn->udma_rchan_id = -1;
+	rx_chn->flow_num = cfg->flow_id_num;
+	rx_chn->flow_id_base = cfg->flow_id_base;
+	rx_chn->psil_paired = false;
+
+	ret = of_k3_udma_glue_parse_chn_by_id(udmax_np, &rx_chn->common, false, thread_id);
 	if (ret)
 		goto err;
 
-	for (i = 0; i < rx_chn->flow_num; i++)
-		rx_chn->flows[i].udma_rflow_id = rx_chn->flow_id_base + i;
-
-	k3_udma_glue_dump_rx_chn(rx_chn);
+	ret = k3_udma_glue_request_remote_rx_chn_common(rx_chn, cfg, dev);
+	if (ret)
+		goto err;
 
 	return rx_chn;
 
@@ -1081,6 +1212,7 @@ err:
 	k3_udma_glue_release_rx_chn(rx_chn);
 	return ERR_PTR(ret);
 }
+EXPORT_SYMBOL_GPL(k3_udma_glue_request_remote_rx_chn_for_thread_id);
 
 struct k3_udma_glue_rx_channel *
 k3_udma_glue_request_rx_chn(struct device *dev, const char *name,
diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c
index e40696f6f864..5eb51ae93e89 100644
--- a/drivers/dma/xilinx/xilinx_dma.c
+++ b/drivers/dma/xilinx/xilinx_dma.c
@@ -112,7 +112,9 @@
 
 /* Register Direct Mode Registers */
 #define XILINX_DMA_REG_VSIZE			0x0000
+#define XILINX_DMA_VSIZE_MASK			GENMASK(12, 0)
 #define XILINX_DMA_REG_HSIZE			0x0004
+#define XILINX_DMA_HSIZE_MASK			GENMASK(15, 0)
 
 #define XILINX_DMA_REG_FRMDLY_STRIDE		0x0008
 #define XILINX_DMA_FRMDLY_STRIDE_FRMDLY_SHIFT	24
@@ -2050,6 +2052,10 @@ xilinx_vdma_dma_prep_interleaved(struct dma_chan *dchan,
 	if (!xt->numf || !xt->sgl[0].size)
 		return NULL;
 
+	if (xt->numf & ~XILINX_DMA_VSIZE_MASK ||
+	    xt->sgl[0].size & ~XILINX_DMA_HSIZE_MASK)
+		return NULL;
+
 	if (xt->frame_size != 1)
 		return NULL;