Adding upstream version 6.8.9.upstream/6.8.9

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

41 files changed, 1930 insertions, 333 deletions

diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index de6eb370d4..002a5ec806 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -378,6 +378,20 @@ config LPC18XX_DMAMUX
 	  Enable support for DMA on NXP LPC18xx/43xx platforms
 	  with PL080 and multiplexed DMA request lines.
 
+config LS2X_APB_DMA
+	tristate "Loongson LS2X APB DMA support"
+	depends on LOONGARCH || COMPILE_TEST
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Support for the Loongson LS2X APB DMA controller driver. The
+	  DMA controller is having single DMA channel which can be
+	  configured for different peripherals like audio, nand, sdio
+	  etc which is in APB bus.
+
+	  This DMA controller transfers data from memory to peripheral fifo.
+	  It does not support memory to memory data transfer.
+
 config MCF_EDMA
 	tristate "Freescale eDMA engine support, ColdFire mcf5441x SoCs"
 	depends on M5441x || COMPILE_TEST
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index 83553a97a0..dfd40d14e4 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -48,6 +48,7 @@ obj-$(CONFIG_INTEL_IOATDMA) += ioat/
 obj-y += idxd/
 obj-$(CONFIG_K3_DMA) += k3dma.o
 obj-$(CONFIG_LPC18XX_DMAMUX) += lpc18xx-dmamux.o
+obj-$(CONFIG_LS2X_APB_DMA) += ls2x-apb-dma.o
 obj-$(CONFIG_MILBEAUT_HDMAC) += milbeaut-hdmac.o
 obj-$(CONFIG_MILBEAUT_XDMAC) += milbeaut-xdmac.o
 obj-$(CONFIG_MMP_PDMA) += mmp_pdma.o
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index fb89ecbf0c..40052d1bd0 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -222,8 +222,14 @@ struct atdma_sg {
  * @vd: pointer to the virtual dma descriptor.
  * @atchan: pointer to the atmel dma channel.
  * @total_len: total transaction byte count
- * @sg_len: number of sg entries.
+ * @sglen: number of sg entries.
  * @sg: array of sgs.
+ * @boundary: number of transfers to perform before the automatic address increment operation
+ * @dst_hole: value to add to the destination address when the boundary has been reached
+ * @src_hole: value to add to the source address when the boundary has been reached
+ * @memset_buffer: buffer used for the memset operation
+ * @memset_paddr: physical address of the buffer used for the memset operation
+ * @memset_vaddr: virtual address of the buffer used for the memset operation
  */
 struct at_desc {
 	struct				virt_dma_desc vd;
@@ -245,7 +251,10 @@ struct at_desc {
 /*--  Channels  --------------------------------------------------------*/
 
 /**
- * atc_status - information bits stored in channel status flag
+ * enum atc_status - information bits stored in channel status flag
+ *
+ * @ATC_IS_PAUSED: If channel is pauses
+ * @ATC_IS_CYCLIC: If channel is cyclic
  *
  * Manipulated with atomic operations.
  */
@@ -282,7 +291,6 @@ struct at_dma_chan {
 	u32			save_cfg;
 	u32			save_dscr;
 	struct dma_slave_config	dma_sconfig;
-	bool			cyclic;
 	struct at_desc		*desc;
 };
 
@@ -328,12 +336,12 @@ static inline u8 convert_buswidth(enum dma_slave_buswidth addr_width)
 /**
  * struct at_dma - internal representation of an Atmel HDMA Controller
  * @dma_device: dmaengine dma_device object members
- * @atdma_devtype: identifier of DMA controller compatibility
- * @ch_regs: memory mapped register base
+ * @regs: memory mapped register base
  * @clk: dma controller clock
  * @save_imr: interrupt mask register that is saved on suspend/resume cycle
  * @all_chan_mask: all channels availlable in a mask
  * @lli_pool: hw lli table
+ * @memset_pool: hw memset pool
  * @chan: channels table to store at_dma_chan structures
  */
 struct at_dma {
@@ -626,6 +634,9 @@ static inline u32 atc_calc_bytes_left(u32 current_len, u32 ctrla)
 
 /**
  * atc_get_llis_residue - Get residue for a hardware linked list transfer
+ * @atchan: pointer to an atmel hdmac channel.
+ * @desc: pointer to the descriptor for which the residue is calculated.
+ * @residue: residue to be set to dma_tx_state.
  *
  * Calculate the residue by removing the length of the Linked List Item (LLI)
  * already transferred from the total length. To get the current LLI we can use
@@ -661,10 +672,8 @@ static inline u32 atc_calc_bytes_left(u32 current_len, u32 ctrla)
  * two DSCR values are different, we read again the CTRLA then the DSCR till two
  * consecutive read values from DSCR are equal or till the maximum trials is
  * reach. This algorithm is very unlikely not to find a stable value for DSCR.
- * @atchan: pointer to an atmel hdmac channel.
- * @desc: pointer to the descriptor for which the residue is calculated.
- * @residue: residue to be set to dma_tx_state.
- * Returns 0 on success, -errno otherwise.
+ *
+ * Returns: %0 on success, -errno otherwise.
  */
 static int atc_get_llis_residue(struct at_dma_chan *atchan,
 				struct at_desc *desc, u32 *residue)
@@ -731,7 +740,8 @@ static int atc_get_llis_residue(struct at_dma_chan *atchan,
  * @chan: DMA channel
  * @cookie: transaction identifier to check status of
  * @residue: residue to be updated.
- * Return 0 on success, -errono otherwise.
+ *
+ * Return: %0 on success, -errno otherwise.
  */
 static int atc_get_residue(struct dma_chan *chan, dma_cookie_t cookie,
 			   u32 *residue)
@@ -1710,7 +1720,7 @@ static void atc_issue_pending(struct dma_chan *chan)
  * atc_alloc_chan_resources - allocate resources for DMA channel
  * @chan: allocate descriptor resources for this channel
  *
- * return - the number of allocated descriptors
+ * Return: the number of allocated descriptors
  */
 static int atc_alloc_chan_resources(struct dma_chan *chan)
 {
diff --git a/drivers/dma/dma-axi-dmac.c b/drivers/dma/dma-axi-dmac.c
index 2457a420c1..4e339c04fc 100644
--- a/drivers/dma/dma-axi-dmac.c
+++ b/drivers/dma/dma-axi-dmac.c
@@ -81,9 +81,13 @@
 #define AXI_DMAC_REG_CURRENT_DEST_ADDR	0x438
 #define AXI_DMAC_REG_PARTIAL_XFER_LEN	0x44c
 #define AXI_DMAC_REG_PARTIAL_XFER_ID	0x450
+#define AXI_DMAC_REG_CURRENT_SG_ID	0x454
+#define AXI_DMAC_REG_SG_ADDRESS		0x47c
+#define AXI_DMAC_REG_SG_ADDRESS_HIGH	0x4bc
 
 #define AXI_DMAC_CTRL_ENABLE		BIT(0)
 #define AXI_DMAC_CTRL_PAUSE		BIT(1)
+#define AXI_DMAC_CTRL_ENABLE_SG		BIT(2)
 
 #define AXI_DMAC_IRQ_SOT		BIT(0)
 #define AXI_DMAC_IRQ_EOT		BIT(1)
@@ -97,20 +101,35 @@
 /* The maximum ID allocated by the hardware is 31 */
 #define AXI_DMAC_SG_UNUSED 32U
 
+/* Flags for axi_dmac_hw_desc.flags */
+#define AXI_DMAC_HW_FLAG_LAST		BIT(0)
+#define AXI_DMAC_HW_FLAG_IRQ		BIT(1)
+
+struct axi_dmac_hw_desc {
+	u32 flags;
+	u32 id;
+	u64 dest_addr;
+	u64 src_addr;
+	u64 next_sg_addr;
+	u32 y_len;
+	u32 x_len;
+	u32 src_stride;
+	u32 dst_stride;
+	u64 __pad[2];
+};
+
 struct axi_dmac_sg {
-	dma_addr_t src_addr;
-	dma_addr_t dest_addr;
-	unsigned int x_len;
-	unsigned int y_len;
-	unsigned int dest_stride;
-	unsigned int src_stride;
-	unsigned int id;
 	unsigned int partial_len;
 	bool schedule_when_free;
+
+	struct axi_dmac_hw_desc *hw;
+	dma_addr_t hw_phys;
 };
 
 struct axi_dmac_desc {
 	struct virt_dma_desc vdesc;
+	struct axi_dmac_chan *chan;
+
 	bool cyclic;
 	bool have_partial_xfer;
 
@@ -139,6 +158,7 @@ struct axi_dmac_chan {
 	bool hw_partial_xfer;
 	bool hw_cyclic;
 	bool hw_2d;
+	bool hw_sg;
 };
 
 struct axi_dmac {
@@ -213,9 +233,11 @@ static void axi_dmac_start_transfer(struct axi_dmac_chan *chan)
 	unsigned int flags = 0;
 	unsigned int val;
 
-	val = axi_dmac_read(dmac, AXI_DMAC_REG_START_TRANSFER);
-	if (val) /* Queue is full, wait for the next SOT IRQ */
-		return;
+	if (!chan->hw_sg) {
+		val = axi_dmac_read(dmac, AXI_DMAC_REG_START_TRANSFER);
+		if (val) /* Queue is full, wait for the next SOT IRQ */
+			return;
+	}
 
 	desc = chan->next_desc;
 
@@ -229,14 +251,15 @@ static void axi_dmac_start_transfer(struct axi_dmac_chan *chan)
 	sg = &desc->sg[desc->num_submitted];
 
 	/* Already queued in cyclic mode. Wait for it to finish */
-	if (sg->id != AXI_DMAC_SG_UNUSED) {
+	if (sg->hw->id != AXI_DMAC_SG_UNUSED) {
 		sg->schedule_when_free = true;
 		return;
 	}
 
-	desc->num_submitted++;
-	if (desc->num_submitted == desc->num_sgs ||
-	    desc->have_partial_xfer) {
+	if (chan->hw_sg) {
+		chan->next_desc = NULL;
+	} else if (++desc->num_submitted == desc->num_sgs ||
+		   desc->have_partial_xfer) {
 		if (desc->cyclic)
 			desc->num_submitted = 0; /* Start again */
 		else
@@ -246,32 +269,42 @@ static void axi_dmac_start_transfer(struct axi_dmac_chan *chan)
 		chan->next_desc = desc;
 	}
 
-	sg->id = axi_dmac_read(dmac, AXI_DMAC_REG_TRANSFER_ID);
+	sg->hw->id = axi_dmac_read(dmac, AXI_DMAC_REG_TRANSFER_ID);
 
-	if (axi_dmac_dest_is_mem(chan)) {
-		axi_dmac_write(dmac, AXI_DMAC_REG_DEST_ADDRESS, sg->dest_addr);
-		axi_dmac_write(dmac, AXI_DMAC_REG_DEST_STRIDE, sg->dest_stride);
-	}
+	if (!chan->hw_sg) {
+		if (axi_dmac_dest_is_mem(chan)) {
+			axi_dmac_write(dmac, AXI_DMAC_REG_DEST_ADDRESS, sg->hw->dest_addr);
+			axi_dmac_write(dmac, AXI_DMAC_REG_DEST_STRIDE, sg->hw->dst_stride);
+		}
 
-	if (axi_dmac_src_is_mem(chan)) {
-		axi_dmac_write(dmac, AXI_DMAC_REG_SRC_ADDRESS, sg->src_addr);
-		axi_dmac_write(dmac, AXI_DMAC_REG_SRC_STRIDE, sg->src_stride);
+		if (axi_dmac_src_is_mem(chan)) {
+			axi_dmac_write(dmac, AXI_DMAC_REG_SRC_ADDRESS, sg->hw->src_addr);
+			axi_dmac_write(dmac, AXI_DMAC_REG_SRC_STRIDE, sg->hw->src_stride);
+		}
 	}
 
 	/*
 	 * If the hardware supports cyclic transfers and there is no callback to
-	 * call and only a single segment, enable hw cyclic mode to avoid
-	 * unnecessary interrupts.
+	 * call, enable hw cyclic mode to avoid unnecessary interrupts.
 	 */
-	if (chan->hw_cyclic && desc->cyclic && !desc->vdesc.tx.callback &&
-		desc->num_sgs == 1)
-		flags |= AXI_DMAC_FLAG_CYCLIC;
+	if (chan->hw_cyclic && desc->cyclic && !desc->vdesc.tx.callback) {
+		if (chan->hw_sg)
+			desc->sg[desc->num_sgs - 1].hw->flags &= ~AXI_DMAC_HW_FLAG_IRQ;
+		else if (desc->num_sgs == 1)
+			flags |= AXI_DMAC_FLAG_CYCLIC;
+	}
 
 	if (chan->hw_partial_xfer)
 		flags |= AXI_DMAC_FLAG_PARTIAL_REPORT;
 
-	axi_dmac_write(dmac, AXI_DMAC_REG_X_LENGTH, sg->x_len - 1);
-	axi_dmac_write(dmac, AXI_DMAC_REG_Y_LENGTH, sg->y_len - 1);
+	if (chan->hw_sg) {
+		axi_dmac_write(dmac, AXI_DMAC_REG_SG_ADDRESS, (u32)sg->hw_phys);
+		axi_dmac_write(dmac, AXI_DMAC_REG_SG_ADDRESS_HIGH,
+			       (u64)sg->hw_phys >> 32);
+	} else {
+		axi_dmac_write(dmac, AXI_DMAC_REG_X_LENGTH, sg->hw->x_len);
+		axi_dmac_write(dmac, AXI_DMAC_REG_Y_LENGTH, sg->hw->y_len);
+	}
 	axi_dmac_write(dmac, AXI_DMAC_REG_FLAGS, flags);
 	axi_dmac_write(dmac, AXI_DMAC_REG_START_TRANSFER, 1);
 }
@@ -286,9 +319,9 @@ static inline unsigned int axi_dmac_total_sg_bytes(struct axi_dmac_chan *chan,
 	struct axi_dmac_sg *sg)
 {
 	if (chan->hw_2d)
-		return sg->x_len * sg->y_len;
+		return (sg->hw->x_len + 1) * (sg->hw->y_len + 1);
 	else
-		return sg->x_len;
+		return (sg->hw->x_len + 1);
 }
 
 static void axi_dmac_dequeue_partial_xfers(struct axi_dmac_chan *chan)
@@ -307,9 +340,9 @@ static void axi_dmac_dequeue_partial_xfers(struct axi_dmac_chan *chan)
 		list_for_each_entry(desc, &chan->active_descs, vdesc.node) {
 			for (i = 0; i < desc->num_sgs; i++) {
 				sg = &desc->sg[i];
-				if (sg->id == AXI_DMAC_SG_UNUSED)
+				if (sg->hw->id == AXI_DMAC_SG_UNUSED)
 					continue;
-				if (sg->id == id) {
+				if (sg->hw->id == id) {
 					desc->have_partial_xfer = true;
 					sg->partial_len = len;
 					found_sg = true;
@@ -348,6 +381,9 @@ static void axi_dmac_compute_residue(struct axi_dmac_chan *chan,
 	rslt->result = DMA_TRANS_NOERROR;
 	rslt->residue = 0;
 
+	if (chan->hw_sg)
+		return;
+
 	/*
 	 * We get here if the last completed segment is partial, which
 	 * means we can compute the residue from that segment onwards
@@ -374,36 +410,47 @@ static bool axi_dmac_transfer_done(struct axi_dmac_chan *chan,
 	    (completed_transfers & AXI_DMAC_FLAG_PARTIAL_XFER_DONE))
 		axi_dmac_dequeue_partial_xfers(chan);
 
-	do {
-		sg = &active->sg[active->num_completed];
-		if (sg->id == AXI_DMAC_SG_UNUSED) /* Not yet submitted */
-			break;
-		if (!(BIT(sg->id) & completed_transfers))
-			break;
-		active->num_completed++;
-		sg->id = AXI_DMAC_SG_UNUSED;
-		if (sg->schedule_when_free) {
-			sg->schedule_when_free = false;
-			start_next = true;
+	if (chan->hw_sg) {
+		if (active->cyclic) {
+			vchan_cyclic_callback(&active->vdesc);
+		} else {
+			list_del(&active->vdesc.node);
+			vchan_cookie_complete(&active->vdesc);
+			active = axi_dmac_active_desc(chan);
+			start_next = !!active;
 		}
+	} else {
+		do {
+			sg = &active->sg[active->num_completed];
+			if (sg->hw->id == AXI_DMAC_SG_UNUSED) /* Not yet submitted */
+				break;
+			if (!(BIT(sg->hw->id) & completed_transfers))
+				break;
+			active->num_completed++;
+			sg->hw->id = AXI_DMAC_SG_UNUSED;
+			if (sg->schedule_when_free) {
+				sg->schedule_when_free = false;
+				start_next = true;
+			}
 
-		if (sg->partial_len)
-			axi_dmac_compute_residue(chan, active);
+			if (sg->partial_len)
+				axi_dmac_compute_residue(chan, active);
 
-		if (active->cyclic)
-			vchan_cyclic_callback(&active->vdesc);
+			if (active->cyclic)
+				vchan_cyclic_callback(&active->vdesc);
 
-		if (active->num_completed == active->num_sgs ||
-		    sg->partial_len) {
-			if (active->cyclic) {
-				active->num_completed = 0; /* wrap around */
-			} else {
-				list_del(&active->vdesc.node);
-				vchan_cookie_complete(&active->vdesc);
-				active = axi_dmac_active_desc(chan);
+			if (active->num_completed == active->num_sgs ||
+			    sg->partial_len) {
+				if (active->cyclic) {
+					active->num_completed = 0; /* wrap around */
+				} else {
+					list_del(&active->vdesc.node);
+					vchan_cookie_complete(&active->vdesc);
+					active = axi_dmac_active_desc(chan);
+				}
 			}
-		}
-	} while (active);
+		} while (active);
+	}
 
 	return start_next;
 }
@@ -467,8 +514,12 @@ static void axi_dmac_issue_pending(struct dma_chan *c)
 	struct axi_dmac_chan *chan = to_axi_dmac_chan(c);
 	struct axi_dmac *dmac = chan_to_axi_dmac(chan);
 	unsigned long flags;
+	u32 ctrl = AXI_DMAC_CTRL_ENABLE;
 
-	axi_dmac_write(dmac, AXI_DMAC_REG_CTRL, AXI_DMAC_CTRL_ENABLE);
+	if (chan->hw_sg)
+		ctrl |= AXI_DMAC_CTRL_ENABLE_SG;
+
+	axi_dmac_write(dmac, AXI_DMAC_REG_CTRL, ctrl);
 
 	spin_lock_irqsave(&chan->vchan.lock, flags);
 	if (vchan_issue_pending(&chan->vchan))
@@ -476,22 +527,58 @@ static void axi_dmac_issue_pending(struct dma_chan *c)
 	spin_unlock_irqrestore(&chan->vchan.lock, flags);
 }
 
-static struct axi_dmac_desc *axi_dmac_alloc_desc(unsigned int num_sgs)
+static struct axi_dmac_desc *
+axi_dmac_alloc_desc(struct axi_dmac_chan *chan, unsigned int num_sgs)
 {
+	struct axi_dmac *dmac = chan_to_axi_dmac(chan);
+	struct device *dev = dmac->dma_dev.dev;
+	struct axi_dmac_hw_desc *hws;
 	struct axi_dmac_desc *desc;
+	dma_addr_t hw_phys;
 	unsigned int i;
 
 	desc = kzalloc(struct_size(desc, sg, num_sgs), GFP_NOWAIT);
 	if (!desc)
 		return NULL;
 	desc->num_sgs = num_sgs;
+	desc->chan = chan;
+
+	hws = dma_alloc_coherent(dev, PAGE_ALIGN(num_sgs * sizeof(*hws)),
+				&hw_phys, GFP_ATOMIC);
+	if (!hws) {
+		kfree(desc);
+		return NULL;
+	}
 
-	for (i = 0; i < num_sgs; i++)
-		desc->sg[i].id = AXI_DMAC_SG_UNUSED;
+	for (i = 0; i < num_sgs; i++) {
+		desc->sg[i].hw = &hws[i];
+		desc->sg[i].hw_phys = hw_phys + i * sizeof(*hws);
+
+		hws[i].id = AXI_DMAC_SG_UNUSED;
+		hws[i].flags = 0;
+
+		/* Link hardware descriptors */
+		hws[i].next_sg_addr = hw_phys + (i + 1) * sizeof(*hws);
+	}
+
+	/* The last hardware descriptor will trigger an interrupt */
+	desc->sg[num_sgs - 1].hw->flags = AXI_DMAC_HW_FLAG_LAST | AXI_DMAC_HW_FLAG_IRQ;
 
 	return desc;
 }
 
+static void axi_dmac_free_desc(struct axi_dmac_desc *desc)
+{
+	struct axi_dmac *dmac = chan_to_axi_dmac(desc->chan);
+	struct device *dev = dmac->dma_dev.dev;
+	struct axi_dmac_hw_desc *hw = desc->sg[0].hw;
+	dma_addr_t hw_phys = desc->sg[0].hw_phys;
+
+	dma_free_coherent(dev, PAGE_ALIGN(desc->num_sgs * sizeof(*hw)),
+			  hw, hw_phys);
+	kfree(desc);
+}
+
 static struct axi_dmac_sg *axi_dmac_fill_linear_sg(struct axi_dmac_chan *chan,
 	enum dma_transfer_direction direction, dma_addr_t addr,
 	unsigned int num_periods, unsigned int period_len,
@@ -508,26 +595,24 @@ static struct axi_dmac_sg *axi_dmac_fill_linear_sg(struct axi_dmac_chan *chan,
 	segment_size = ((segment_size - 1) | chan->length_align_mask) + 1;
 
 	for (i = 0; i < num_periods; i++) {
-		len = period_len;
-
-		while (len > segment_size) {
+		for (len = period_len; len > segment_size; sg++) {
 			if (direction == DMA_DEV_TO_MEM)
-				sg->dest_addr = addr;
+				sg->hw->dest_addr = addr;
 			else
-				sg->src_addr = addr;
-			sg->x_len = segment_size;
-			sg->y_len = 1;
-			sg++;
+				sg->hw->src_addr = addr;
+			sg->hw->x_len = segment_size - 1;
+			sg->hw->y_len = 0;
+			sg->hw->flags = 0;
 			addr += segment_size;
 			len -= segment_size;
 		}
 
 		if (direction == DMA_DEV_TO_MEM)
-			sg->dest_addr = addr;
+			sg->hw->dest_addr = addr;
 		else
-			sg->src_addr = addr;
-		sg->x_len = len;
-		sg->y_len = 1;
+			sg->hw->src_addr = addr;
+		sg->hw->x_len = len - 1;
+		sg->hw->y_len = 0;
 		sg++;
 		addr += len;
 	}
@@ -554,7 +639,7 @@ static struct dma_async_tx_descriptor *axi_dmac_prep_slave_sg(
 	for_each_sg(sgl, sg, sg_len, i)
 		num_sgs += DIV_ROUND_UP(sg_dma_len(sg), chan->max_length);
 
-	desc = axi_dmac_alloc_desc(num_sgs);
+	desc = axi_dmac_alloc_desc(chan, num_sgs);
 	if (!desc)
 		return NULL;
 
@@ -563,7 +648,7 @@ static struct dma_async_tx_descriptor *axi_dmac_prep_slave_sg(
 	for_each_sg(sgl, sg, sg_len, i) {
 		if (!axi_dmac_check_addr(chan, sg_dma_address(sg)) ||
 		    !axi_dmac_check_len(chan, sg_dma_len(sg))) {
-			kfree(desc);
+			axi_dmac_free_desc(desc);
 			return NULL;
 		}
 
@@ -583,7 +668,7 @@ static struct dma_async_tx_descriptor *axi_dmac_prep_dma_cyclic(
 {
 	struct axi_dmac_chan *chan = to_axi_dmac_chan(c);
 	struct axi_dmac_desc *desc;
-	unsigned int num_periods, num_segments;
+	unsigned int num_periods, num_segments, num_sgs;
 
 	if (direction != chan->direction)
 		return NULL;
@@ -597,11 +682,16 @@ static struct dma_async_tx_descriptor *axi_dmac_prep_dma_cyclic(
 
 	num_periods = buf_len / period_len;
 	num_segments = DIV_ROUND_UP(period_len, chan->max_length);
+	num_sgs = num_periods * num_segments;
 
-	desc = axi_dmac_alloc_desc(num_periods * num_segments);
+	desc = axi_dmac_alloc_desc(chan, num_sgs);
 	if (!desc)
 		return NULL;
 
+	/* Chain the last descriptor to the first, and remove its "last" flag */
+	desc->sg[num_sgs - 1].hw->next_sg_addr = desc->sg[0].hw_phys;
+	desc->sg[num_sgs - 1].hw->flags &= ~AXI_DMAC_HW_FLAG_LAST;
+
 	axi_dmac_fill_linear_sg(chan, direction, buf_addr, num_periods,
 		period_len, desc->sg);
 
@@ -653,26 +743,26 @@ static struct dma_async_tx_descriptor *axi_dmac_prep_interleaved(
 			return NULL;
 	}
 
-	desc = axi_dmac_alloc_desc(1);
+	desc = axi_dmac_alloc_desc(chan, 1);
 	if (!desc)
 		return NULL;
 
 	if (axi_dmac_src_is_mem(chan)) {
-		desc->sg[0].src_addr = xt->src_start;
-		desc->sg[0].src_stride = xt->sgl[0].size + src_icg;
+		desc->sg[0].hw->src_addr = xt->src_start;
+		desc->sg[0].hw->src_stride = xt->sgl[0].size + src_icg;
 	}
 
 	if (axi_dmac_dest_is_mem(chan)) {
-		desc->sg[0].dest_addr = xt->dst_start;
-		desc->sg[0].dest_stride = xt->sgl[0].size + dst_icg;
+		desc->sg[0].hw->dest_addr = xt->dst_start;
+		desc->sg[0].hw->dst_stride = xt->sgl[0].size + dst_icg;
 	}
 
 	if (chan->hw_2d) {
-		desc->sg[0].x_len = xt->sgl[0].size;
-		desc->sg[0].y_len = xt->numf;
+		desc->sg[0].hw->x_len = xt->sgl[0].size - 1;
+		desc->sg[0].hw->y_len = xt->numf - 1;
 	} else {
-		desc->sg[0].x_len = xt->sgl[0].size * xt->numf;
-		desc->sg[0].y_len = 1;
+		desc->sg[0].hw->x_len = xt->sgl[0].size * xt->numf - 1;
+		desc->sg[0].hw->y_len = 0;
 	}
 
 	if (flags & DMA_CYCLIC)
@@ -688,7 +778,7 @@ static void axi_dmac_free_chan_resources(struct dma_chan *c)
 
 static void axi_dmac_desc_free(struct virt_dma_desc *vdesc)
 {
-	kfree(container_of(vdesc, struct axi_dmac_desc, vdesc));
+	axi_dmac_free_desc(to_axi_dmac_desc(vdesc));
 }
 
 static bool axi_dmac_regmap_rdwr(struct device *dev, unsigned int reg)
@@ -714,6 +804,9 @@ static bool axi_dmac_regmap_rdwr(struct device *dev, unsigned int reg)
 	case AXI_DMAC_REG_CURRENT_DEST_ADDR:
 	case AXI_DMAC_REG_PARTIAL_XFER_LEN:
 	case AXI_DMAC_REG_PARTIAL_XFER_ID:
+	case AXI_DMAC_REG_CURRENT_SG_ID:
+	case AXI_DMAC_REG_SG_ADDRESS:
+	case AXI_DMAC_REG_SG_ADDRESS_HIGH:
 		return true;
 	default:
 		return false;
@@ -866,6 +959,10 @@ static int axi_dmac_detect_caps(struct axi_dmac *dmac, unsigned int version)
 	if (axi_dmac_read(dmac, AXI_DMAC_REG_FLAGS) == AXI_DMAC_FLAG_CYCLIC)
 		chan->hw_cyclic = true;
 
+	axi_dmac_write(dmac, AXI_DMAC_REG_SG_ADDRESS, 0xffffffff);
+	if (axi_dmac_read(dmac, AXI_DMAC_REG_SG_ADDRESS))
+		chan->hw_sg = true;
+
 	axi_dmac_write(dmac, AXI_DMAC_REG_Y_LENGTH, 1);
 	if (axi_dmac_read(dmac, AXI_DMAC_REG_Y_LENGTH) == 1)
 		chan->hw_2d = true;
@@ -911,6 +1008,7 @@ static int axi_dmac_probe(struct platform_device *pdev)
 	struct axi_dmac *dmac;
 	struct regmap *regmap;
 	unsigned int version;
+	u32 irq_mask = 0;
 	int ret;
 
 	dmac = devm_kzalloc(&pdev->dev, sizeof(*dmac), GFP_KERNEL);
@@ -966,6 +1064,7 @@ static int axi_dmac_probe(struct platform_device *pdev)
 	dma_dev->dst_addr_widths = BIT(dmac->chan.dest_width);
 	dma_dev->directions = BIT(dmac->chan.direction);
 	dma_dev->residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR;
+	dma_dev->max_sg_burst = 31; /* 31 SGs maximum in one burst */
 	INIT_LIST_HEAD(&dma_dev->channels);
 
 	dmac->chan.vchan.desc_free = axi_dmac_desc_free;
@@ -977,7 +1076,10 @@ static int axi_dmac_probe(struct platform_device *pdev)
 
 	dma_dev->copy_align = (dmac->chan.address_align_mask + 1);
 
-	axi_dmac_write(dmac, AXI_DMAC_REG_IRQ_MASK, 0x00);
+	if (dmac->chan.hw_sg)
+		irq_mask |= AXI_DMAC_IRQ_SOT;
+
+	axi_dmac_write(dmac, AXI_DMAC_REG_IRQ_MASK, irq_mask);
 
 	if (of_dma_is_coherent(pdev->dev.of_node)) {
 		ret = axi_dmac_read(dmac, AXI_DMAC_REG_COHERENCY_DESC);
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index ffe621695e..a4f6088378 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -21,6 +21,10 @@
 #include <linux/slab.h>
 #include <linux/wait.h>
 
+static bool nobounce;
+module_param(nobounce, bool, 0644);
+MODULE_PARM_DESC(nobounce, "Prevent using swiotlb buffer (default: use swiotlb buffer)");
+
 static unsigned int test_buf_size = 16384;
 module_param(test_buf_size, uint, 0644);
 MODULE_PARM_DESC(test_buf_size, "Size of the memcpy test buffer");
@@ -90,6 +94,7 @@ MODULE_PARM_DESC(polled, "Use polling for completion instead of interrupts");
 
 /**
  * struct dmatest_params - test parameters.
+ * @nobounce:		prevent using swiotlb buffer
  * @buf_size:		size of the memcpy test buffer
  * @channel:		bus ID of the channel to test
  * @device:		bus ID of the DMA Engine to test
@@ -106,6 +111,7 @@ MODULE_PARM_DESC(polled, "Use polling for completion instead of interrupts");
  * @polled:		use polling for completion instead of interrupts
  */
 struct dmatest_params {
+	bool		nobounce;
 	unsigned int	buf_size;
 	char		channel[20];
 	char		device[32];
@@ -215,6 +221,7 @@ struct dmatest_done {
 struct dmatest_data {
 	u8		**raw;
 	u8		**aligned;
+	gfp_t		gfp_flags;
 	unsigned int	cnt;
 	unsigned int	off;
 };
@@ -533,7 +540,7 @@ static int dmatest_alloc_test_data(struct dmatest_data *d,
 		goto err;
 
 	for (i = 0; i < d->cnt; i++) {
-		d->raw[i] = kmalloc(buf_size + align, GFP_KERNEL);
+		d->raw[i] = kmalloc(buf_size + align, d->gfp_flags);
 		if (!d->raw[i])
 			goto err;
 
@@ -655,6 +662,13 @@ static int dmatest_func(void *data)
 		goto err_free_coefs;
 	}
 
+	src->gfp_flags = GFP_KERNEL;
+	dst->gfp_flags = GFP_KERNEL;
+	if (params->nobounce) {
+		src->gfp_flags = GFP_DMA;
+		dst->gfp_flags = GFP_DMA;
+	}
+
 	if (dmatest_alloc_test_data(src, buf_size, align) < 0)
 		goto err_free_coefs;
 
@@ -1093,6 +1107,7 @@ static void add_threaded_test(struct dmatest_info *info)
 	struct dmatest_params *params = &info->params;
 
 	/* Copy test parameters */
+	params->nobounce = nobounce;
 	params->buf_size = test_buf_size;
 	strscpy(params->channel, strim(test_channel), sizeof(params->channel));
 	strscpy(params->device, strim(test_device), sizeof(params->device));
diff --git a/drivers/dma/fsl-qdma.c b/drivers/dma/fsl-qdma.c
index 7a24279318..5005e138fc 100644
--- a/drivers/dma/fsl-qdma.c
+++ b/drivers/dma/fsl-qdma.c
@@ -161,6 +161,10 @@ struct fsl_qdma_format {
 			u8 __reserved1[2];
 			u8 cfg8b_w1;
 		} __packed;
+		struct {
+			__le32 __reserved2;
+			__le32 cmd;
+		} __packed;
 		__le64 data;
 	};
 } __packed;
@@ -355,7 +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;
 
@@ -384,15 +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) |
-			  FSL_QDMA_CMD_PF;
-	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));
 }
 
 /*
@@ -570,10 +569,9 @@ static struct fsl_qdma_queue
 					      status_size,
 					      &status_head->bus_addr,
 					      GFP_KERNEL);
-	if (!status_head->cq) {
-		devm_kfree(&pdev->dev, status_head);
+	if (!status_head->cq)
 		return NULL;
-	}
+
 	status_head->n_cq = status_size;
 	status_head->virt_head = status_head->cq;
 	status_head->virt_tail = status_head->cq;
@@ -627,7 +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;
diff --git a/drivers/dma/idma64.c b/drivers/dma/idma64.c
index 78a938969d..1398814d8f 100644
--- a/drivers/dma/idma64.c
+++ b/drivers/dma/idma64.c
@@ -171,6 +171,10 @@ static irqreturn_t idma64_irq(int irq, void *dev)
 	u32 status_err;
 	unsigned short i;
 
+	/* Since IRQ may be shared, check if DMA controller is powered on */
+	if (status == GENMASK(31, 0))
+		return IRQ_NONE;
+
 	dev_vdbg(idma64->dma.dev, "%s: status=%#x\n", __func__, status);
 
 	/* Check if we have any interrupt from the DMA controller */
diff --git a/drivers/dma/idxd/Makefile b/drivers/dma/idxd/Makefile
index c5e679070e..2b4a0d406e 100644
--- a/drivers/dma/idxd/Makefile
+++ b/drivers/dma/idxd/Makefile
@@ -4,7 +4,7 @@ obj-$(CONFIG_INTEL_IDXD_BUS) += idxd_bus.o
 idxd_bus-y := bus.o
 
 obj-$(CONFIG_INTEL_IDXD) += idxd.o
-idxd-y := init.o irq.o device.o sysfs.o submit.o dma.o cdev.o debugfs.o
+idxd-y := init.o irq.o device.o sysfs.o submit.o dma.o cdev.o debugfs.o defaults.o
 
 idxd-$(CONFIG_INTEL_IDXD_PERFMON) += perfmon.o
 
diff --git a/drivers/dma/idxd/bus.c b/drivers/dma/idxd/bus.c
index 6f84621053..0c9e689a2e 100644
--- a/drivers/dma/idxd/bus.c
+++ b/drivers/dma/idxd/bus.c
@@ -67,11 +67,17 @@ static void idxd_config_bus_remove(struct device *dev)
 	idxd_drv->remove(idxd_dev);
 }
 
+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 = {
 	.name = "dsa",
 	.match = idxd_config_bus_match,
 	.probe = idxd_config_bus_probe,
 	.remove = idxd_config_bus_remove,
+	.uevent = idxd_bus_uevent,
 };
 EXPORT_SYMBOL_GPL(dsa_bus_type);
 
diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c
index 3dd25a9a04..59456f2177 100644
--- a/drivers/dma/idxd/cdev.c
+++ b/drivers/dma/idxd/cdev.c
@@ -165,7 +165,7 @@ static void idxd_cdev_dev_release(struct device *dev)
 	struct idxd_wq *wq = idxd_cdev->wq;
 
 	cdev_ctx = &ictx[wq->idxd->data->type];
-	ida_simple_remove(&cdev_ctx->minor_ida, idxd_cdev->minor);
+	ida_free(&cdev_ctx->minor_ida, idxd_cdev->minor);
 	kfree(idxd_cdev);
 }
 
@@ -342,7 +342,7 @@ static void idxd_cdev_evl_drain_pasid(struct idxd_wq *wq, u32 pasid)
 	if (!evl)
 		return;
 
-	spin_lock(&evl->lock);
+	mutex_lock(&evl->lock);
 	status.bits = ioread64(idxd->reg_base + IDXD_EVLSTATUS_OFFSET);
 	t = status.tail;
 	h = status.head;
@@ -354,9 +354,8 @@ static void idxd_cdev_evl_drain_pasid(struct idxd_wq *wq, u32 pasid)
 			set_bit(h, evl->bmap);
 		h = (h + 1) % size;
 	}
-	spin_unlock(&evl->lock);
-
 	drain_workqueue(wq->wq);
+	mutex_unlock(&evl->lock);
 }
 
 static int idxd_cdev_release(struct inode *node, struct file *filep)
@@ -463,7 +462,7 @@ int idxd_wq_add_cdev(struct idxd_wq *wq)
 	cdev = &idxd_cdev->cdev;
 	dev = cdev_dev(idxd_cdev);
 	cdev_ctx = &ictx[wq->idxd->data->type];
-	minor = ida_simple_get(&cdev_ctx->minor_ida, 0, MINORMASK, GFP_KERNEL);
+	minor = ida_alloc_max(&cdev_ctx->minor_ida, MINORMASK, GFP_KERNEL);
 	if (minor < 0) {
 		kfree(idxd_cdev);
 		return minor;
@@ -550,7 +549,7 @@ static int idxd_user_drv_probe(struct idxd_dev *idxd_dev)
 	}
 
 	wq->type = IDXD_WQT_USER;
-	rc = drv_enable_wq(wq);
+	rc = idxd_drv_enable_wq(wq);
 	if (rc < 0)
 		goto err;
 
@@ -565,7 +564,7 @@ static int idxd_user_drv_probe(struct idxd_dev *idxd_dev)
 	return 0;
 
 err_cdev:
-	drv_disable_wq(wq);
+	idxd_drv_disable_wq(wq);
 err:
 	destroy_workqueue(wq->wq);
 	wq->type = IDXD_WQT_NONE;
@@ -580,7 +579,7 @@ static void idxd_user_drv_remove(struct idxd_dev *idxd_dev)
 
 	mutex_lock(&wq->wq_lock);
 	idxd_wq_del_cdev(wq);
-	drv_disable_wq(wq);
+	idxd_drv_disable_wq(wq);
 	wq->type = IDXD_WQT_NONE;
 	destroy_workqueue(wq->wq);
 	wq->wq = NULL;
diff --git a/drivers/dma/idxd/debugfs.c b/drivers/dma/idxd/debugfs.c
index f3f25ee676..ad4245cb30 100644
--- a/drivers/dma/idxd/debugfs.c
+++ b/drivers/dma/idxd/debugfs.c
@@ -66,7 +66,7 @@ static int debugfs_evl_show(struct seq_file *s, void *d)
 	if (!evl || !evl->log)
 		return 0;
 
-	spin_lock(&evl->lock);
+	mutex_lock(&evl->lock);
 
 	evl_status.bits = ioread64(idxd->reg_base + IDXD_EVLSTATUS_OFFSET);
 	t = evl_status.tail;
@@ -87,7 +87,7 @@ static int debugfs_evl_show(struct seq_file *s, void *d)
 		dump_event_entry(idxd, s, i, &count, processed);
 	}
 
-	spin_unlock(&evl->lock);
+	mutex_unlock(&evl->lock);
 	return 0;
 }
 
diff --git a/drivers/dma/idxd/defaults.c b/drivers/dma/idxd/defaults.c
new file mode 100644
index 0000000000..c607ae8dd1
--- /dev/null
+++ b/drivers/dma/idxd/defaults.c
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2023 Intel Corporation. All rights rsvd. */
+#include <linux/kernel.h>
+#include "idxd.h"
+
+int idxd_load_iaa_device_defaults(struct idxd_device *idxd)
+{
+	struct idxd_engine *engine;
+	struct idxd_group *group;
+	struct idxd_wq *wq;
+
+	if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
+		return 0;
+
+	wq = idxd->wqs[0];
+
+	if (wq->state != IDXD_WQ_DISABLED)
+		return -EPERM;
+
+	/* set mode to "dedicated" */
+	set_bit(WQ_FLAG_DEDICATED, &wq->flags);
+	wq->threshold = 0;
+
+	/* only setting up 1 wq, so give it all the wq space */
+	wq->size = idxd->max_wq_size;
+
+	/* set priority to 10 */
+	wq->priority = 10;
+
+	/* set type to "kernel" */
+	wq->type = IDXD_WQT_KERNEL;
+
+	/* set wq group to 0 */
+	group = idxd->groups[0];
+	wq->group = group;
+	group->num_wqs++;
+
+	/* set name to "iaa_crypto" */
+	memset(wq->name, 0, WQ_NAME_SIZE + 1);
+	strscpy(wq->name, "iaa_crypto", WQ_NAME_SIZE + 1);
+
+	/* set driver_name to "crypto" */
+	memset(wq->driver_name, 0, DRIVER_NAME_SIZE + 1);
+	strscpy(wq->driver_name, "crypto", DRIVER_NAME_SIZE + 1);
+
+	engine = idxd->engines[0];
+
+	/* set engine group to 0 */
+	engine->group = idxd->groups[0];
+	engine->group->num_engines++;
+
+	return 0;
+}
diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index fa0f880bea..c41ef195ee 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -161,6 +161,7 @@ int idxd_wq_alloc_resources(struct idxd_wq *wq)
 	free_hw_descs(wq);
 	return rc;
 }
+EXPORT_SYMBOL_NS_GPL(idxd_wq_alloc_resources, IDXD);
 
 void idxd_wq_free_resources(struct idxd_wq *wq)
 {
@@ -174,6 +175,7 @@ void idxd_wq_free_resources(struct idxd_wq *wq)
 	dma_free_coherent(dev, wq->compls_size, wq->compls, wq->compls_addr);
 	sbitmap_queue_free(&wq->sbq);
 }
+EXPORT_SYMBOL_NS_GPL(idxd_wq_free_resources, IDXD);
 
 int idxd_wq_enable(struct idxd_wq *wq)
 {
@@ -405,6 +407,7 @@ int idxd_wq_init_percpu_ref(struct idxd_wq *wq)
 	reinit_completion(&wq->wq_resurrect);
 	return 0;
 }
+EXPORT_SYMBOL_NS_GPL(idxd_wq_init_percpu_ref, IDXD);
 
 void __idxd_wq_quiesce(struct idxd_wq *wq)
 {
@@ -414,6 +417,7 @@ void __idxd_wq_quiesce(struct idxd_wq *wq)
 	complete_all(&wq->wq_resurrect);
 	wait_for_completion(&wq->wq_dead);
 }
+EXPORT_SYMBOL_NS_GPL(__idxd_wq_quiesce, IDXD);
 
 void idxd_wq_quiesce(struct idxd_wq *wq)
 {
@@ -421,6 +425,7 @@ void idxd_wq_quiesce(struct idxd_wq *wq)
 	__idxd_wq_quiesce(wq);
 	mutex_unlock(&wq->wq_lock);
 }
+EXPORT_SYMBOL_NS_GPL(idxd_wq_quiesce, IDXD);
 
 /* Device control bits */
 static inline bool idxd_is_enabled(struct idxd_device *idxd)
@@ -770,7 +775,7 @@ static int idxd_device_evl_setup(struct idxd_device *idxd)
 		goto err_alloc;
 	}
 
-	spin_lock(&evl->lock);
+	mutex_lock(&evl->lock);
 	evl->log = addr;
 	evl->dma = dma_addr;
 	evl->log_size = size;
@@ -791,7 +796,7 @@ static int idxd_device_evl_setup(struct idxd_device *idxd)
 	gencfg.evl_en = 1;
 	iowrite32(gencfg.bits, idxd->reg_base + IDXD_GENCFG_OFFSET);
 
-	spin_unlock(&evl->lock);
+	mutex_unlock(&evl->lock);
 	return 0;
 
 err_alloc:
@@ -814,7 +819,7 @@ static void idxd_device_evl_free(struct idxd_device *idxd)
 	if (!gencfg.evl_en)
 		return;
 
-	spin_lock(&evl->lock);
+	mutex_lock(&evl->lock);
 	gencfg.evl_en = 0;
 	iowrite32(gencfg.bits, idxd->reg_base + IDXD_GENCFG_OFFSET);
 
@@ -831,7 +836,7 @@ static void idxd_device_evl_free(struct idxd_device *idxd)
 	evl_dma = evl->dma;
 	evl->log = NULL;
 	evl->size = IDXD_EVL_SIZE_MIN;
-	spin_unlock(&evl->lock);
+	mutex_unlock(&evl->lock);
 
 	dma_free_coherent(dev, evl_log_size, evl_log, evl_dma);
 }
@@ -1273,7 +1278,7 @@ static void idxd_flush_pending_descs(struct idxd_irq_entry *ie)
 		tx = &desc->txd;
 		tx->callback = NULL;
 		tx->callback_result = NULL;
-		idxd_dma_complete_txd(desc, ctype, true);
+		idxd_dma_complete_txd(desc, ctype, true, NULL, NULL);
 	}
 }
 
@@ -1357,7 +1362,7 @@ err_irq:
 	return rc;
 }
 
-int drv_enable_wq(struct idxd_wq *wq)
+int idxd_drv_enable_wq(struct idxd_wq *wq)
 {
 	struct idxd_device *idxd = wq->idxd;
 	struct device *dev = &idxd->pdev->dev;
@@ -1489,8 +1494,9 @@ err_map_portal:
 err:
 	return rc;
 }
+EXPORT_SYMBOL_NS_GPL(idxd_drv_enable_wq, IDXD);
 
-void drv_disable_wq(struct idxd_wq *wq)
+void idxd_drv_disable_wq(struct idxd_wq *wq)
 {
 	struct idxd_device *idxd = wq->idxd;
 	struct device *dev = &idxd->pdev->dev;
@@ -1510,6 +1516,7 @@ void drv_disable_wq(struct idxd_wq *wq)
 	wq->type = IDXD_WQT_NONE;
 	wq->client_count = 0;
 }
+EXPORT_SYMBOL_NS_GPL(idxd_drv_disable_wq, IDXD);
 
 int idxd_device_drv_probe(struct idxd_dev *idxd_dev)
 {
diff --git a/drivers/dma/idxd/dma.c b/drivers/dma/idxd/dma.c
index 47a01893cf..cd835eabd3 100644
--- a/drivers/dma/idxd/dma.c
+++ b/drivers/dma/idxd/dma.c
@@ -22,7 +22,7 @@ static inline struct idxd_wq *to_idxd_wq(struct dma_chan *c)
 
 void idxd_dma_complete_txd(struct idxd_desc *desc,
 			   enum idxd_complete_type comp_type,
-			   bool free_desc)
+			   bool free_desc, void *ctx, u32 *status)
 {
 	struct idxd_device *idxd = desc->wq->idxd;
 	struct dma_async_tx_descriptor *tx;
@@ -314,7 +314,7 @@ static int idxd_dmaengine_drv_probe(struct idxd_dev *idxd_dev)
 
 	wq->type = IDXD_WQT_KERNEL;
 
-	rc = drv_enable_wq(wq);
+	rc = idxd_drv_enable_wq(wq);
 	if (rc < 0) {
 		dev_dbg(dev, "Enable wq %d failed: %d\n", wq->id, rc);
 		rc = -ENXIO;
@@ -333,7 +333,7 @@ static int idxd_dmaengine_drv_probe(struct idxd_dev *idxd_dev)
 	return 0;
 
 err_dma:
-	drv_disable_wq(wq);
+	idxd_drv_disable_wq(wq);
 err:
 	wq->type = IDXD_WQT_NONE;
 	mutex_unlock(&wq->wq_lock);
@@ -347,7 +347,7 @@ static void idxd_dmaengine_drv_remove(struct idxd_dev *idxd_dev)
 	mutex_lock(&wq->wq_lock);
 	__idxd_wq_quiesce(wq);
 	idxd_unregister_dma_channel(wq);
-	drv_disable_wq(wq);
+	idxd_drv_disable_wq(wq);
 	mutex_unlock(&wq->wq_lock);
 }
 
@@ -359,6 +359,7 @@ static enum idxd_dev_type dev_types[] = {
 struct idxd_device_driver idxd_dmaengine_drv = {
 	.probe = idxd_dmaengine_drv_probe,
 	.remove = idxd_dmaengine_drv_remove,
+	.desc_complete = idxd_dma_complete_txd,
 	.name = "dmaengine",
 	.type = dev_types,
 };
diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h
index 96062ae39f..df91472f0f 100644
--- a/drivers/dma/idxd/idxd.h
+++ b/drivers/dma/idxd/idxd.h
@@ -13,6 +13,7 @@
 #include <linux/bitmap.h>
 #include <linux/perf_event.h>
 #include <linux/iommu.h>
+#include <linux/crypto.h>
 #include <uapi/linux/idxd.h>
 #include "registers.h"
 
@@ -57,11 +58,23 @@ enum idxd_type {
 #define IDXD_ENQCMDS_RETRIES		32
 #define IDXD_ENQCMDS_MAX_RETRIES	64
 
+enum idxd_complete_type {
+	IDXD_COMPLETE_NORMAL = 0,
+	IDXD_COMPLETE_ABORT,
+	IDXD_COMPLETE_DEV_FAIL,
+};
+
+struct idxd_desc;
+
 struct idxd_device_driver {
 	const char *name;
 	enum idxd_dev_type *type;
 	int (*probe)(struct idxd_dev *idxd_dev);
 	void (*remove)(struct idxd_dev *idxd_dev);
+	void (*desc_complete)(struct idxd_desc *desc,
+			      enum idxd_complete_type comp_type,
+			      bool free_desc,
+			      void *ctx, u32 *status);
 	struct device_driver drv;
 };
 
@@ -174,12 +187,6 @@ enum idxd_op_type {
 	IDXD_OP_NONBLOCK = 1,
 };
 
-enum idxd_complete_type {
-	IDXD_COMPLETE_NORMAL = 0,
-	IDXD_COMPLETE_ABORT,
-	IDXD_COMPLETE_DEV_FAIL,
-};
-
 struct idxd_dma_chan {
 	struct dma_chan chan;
 	struct idxd_wq *wq;
@@ -270,6 +277,8 @@ struct idxd_dma_dev {
 	struct dma_device dma;
 };
 
+typedef int (*load_device_defaults_fn_t) (struct idxd_device *idxd);
+
 struct idxd_driver_data {
 	const char *name_prefix;
 	enum idxd_type type;
@@ -279,11 +288,12 @@ struct idxd_driver_data {
 	int evl_cr_off;
 	int cr_status_off;
 	int cr_result_off;
+	load_device_defaults_fn_t load_device_defaults;
 };
 
 struct idxd_evl {
 	/* Lock to protect event log access. */
-	spinlock_t lock;
+	struct mutex lock;
 	void *log;
 	dma_addr_t dma;
 	/* Total size of event log = number of entries * entry size. */
@@ -377,6 +387,14 @@ static inline unsigned int evl_size(struct idxd_device *idxd)
 	return idxd->evl->size * evl_ent_size(idxd);
 }
 
+struct crypto_ctx {
+	struct acomp_req *req;
+	struct crypto_tfm *tfm;
+	dma_addr_t src_addr;
+	dma_addr_t dst_addr;
+	bool compress;
+};
+
 /* IDXD software descriptor */
 struct idxd_desc {
 	union {
@@ -389,7 +407,10 @@ struct idxd_desc {
 		struct iax_completion_record *iax_completion;
 	};
 	dma_addr_t compl_dma;
-	struct dma_async_tx_descriptor txd;
+	union {
+		struct dma_async_tx_descriptor txd;
+		struct crypto_ctx crypto;
+	};
 	struct llist_node llnode;
 	struct list_head list;
 	int id;
@@ -416,6 +437,15 @@ enum idxd_completion_status {
 #define idxd_dev_to_idxd(idxd_dev) container_of(idxd_dev, struct idxd_device, idxd_dev)
 #define idxd_dev_to_wq(idxd_dev) container_of(idxd_dev, struct idxd_wq, idxd_dev)
 
+static inline struct idxd_device_driver *wq_to_idxd_drv(struct idxd_wq *wq)
+{
+	struct device *dev = wq_confdev(wq);
+	struct idxd_device_driver *idxd_drv =
+		container_of(dev->driver, struct idxd_device_driver, drv);
+
+	return idxd_drv;
+}
+
 static inline struct idxd_device *confdev_to_idxd(struct device *dev)
 {
 	struct idxd_dev *idxd_dev = confdev_to_idxd_dev(dev);
@@ -617,6 +647,16 @@ static inline int idxd_wq_refcount(struct idxd_wq *wq)
 	return wq->client_count;
 };
 
+static inline void idxd_wq_set_private(struct idxd_wq *wq, void *private)
+{
+	dev_set_drvdata(wq_confdev(wq), private);
+}
+
+static inline void *idxd_wq_get_private(struct idxd_wq *wq)
+{
+	return dev_get_drvdata(wq_confdev(wq));
+}
+
 /*
  * Intel IAA does not support batch processing.
  * The max batch size of device, max batch size of wq and
@@ -654,6 +694,9 @@ static inline int idxd_wq_driver_name_match(struct idxd_wq *wq, struct device *d
 	return (strncmp(wq->driver_name, dev->driver->name, strlen(dev->driver->name)) == 0);
 }
 
+#define MODULE_ALIAS_IDXD_DEVICE(type) MODULE_ALIAS("idxd:t" __stringify(type) "*")
+#define IDXD_DEVICES_MODALIAS_FMT "idxd:t%d"
+
 int __must_check __idxd_driver_register(struct idxd_device_driver *idxd_drv,
 					struct module *module, const char *mod_name);
 #define idxd_driver_register(driver) \
@@ -664,6 +707,24 @@ void idxd_driver_unregister(struct idxd_device_driver *idxd_drv);
 #define module_idxd_driver(__idxd_driver) \
 	module_driver(__idxd_driver, idxd_driver_register, idxd_driver_unregister)
 
+void idxd_free_desc(struct idxd_wq *wq, struct idxd_desc *desc);
+void idxd_dma_complete_txd(struct idxd_desc *desc,
+			   enum idxd_complete_type comp_type,
+			   bool free_desc, void *ctx, u32 *status);
+
+static inline void idxd_desc_complete(struct idxd_desc *desc,
+				      enum idxd_complete_type comp_type,
+				      bool free_desc)
+{
+	struct idxd_device_driver *drv;
+	u32 status;
+
+	drv = wq_to_idxd_drv(desc->wq);
+	if (drv->desc_complete)
+		drv->desc_complete(desc, comp_type, free_desc,
+				   &desc->txd, &status);
+}
+
 int idxd_register_bus_type(void);
 void idxd_unregister_bus_type(void);
 int idxd_register_devices(struct idxd_device *idxd);
@@ -671,6 +732,7 @@ void idxd_unregister_devices(struct idxd_device *idxd);
 void idxd_wqs_quiesce(struct idxd_device *idxd);
 bool idxd_queue_int_handle_resubmit(struct idxd_desc *desc);
 void multi_u64_to_bmap(unsigned long *bmap, u64 *val, int count);
+int idxd_load_iaa_device_defaults(struct idxd_device *idxd);
 
 /* device interrupt control */
 irqreturn_t idxd_misc_thread(int vec, void *data);
@@ -681,8 +743,8 @@ void idxd_unmask_error_interrupts(struct idxd_device *idxd);
 /* device control */
 int idxd_device_drv_probe(struct idxd_dev *idxd_dev);
 void idxd_device_drv_remove(struct idxd_dev *idxd_dev);
-int drv_enable_wq(struct idxd_wq *wq);
-void drv_disable_wq(struct idxd_wq *wq);
+int idxd_drv_enable_wq(struct idxd_wq *wq);
+void idxd_drv_disable_wq(struct idxd_wq *wq);
 int idxd_device_init_reset(struct idxd_device *idxd);
 int idxd_device_enable(struct idxd_device *idxd);
 int idxd_device_disable(struct idxd_device *idxd);
@@ -717,14 +779,11 @@ int idxd_wq_request_irq(struct idxd_wq *wq);
 /* submission */
 int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc);
 struct idxd_desc *idxd_alloc_desc(struct idxd_wq *wq, enum idxd_op_type optype);
-void idxd_free_desc(struct idxd_wq *wq, struct idxd_desc *desc);
 int idxd_enqcmds(struct idxd_wq *wq, void __iomem *portal, const void *desc);
 
 /* dmaengine */
 int idxd_register_dma_device(struct idxd_device *idxd);
 void idxd_unregister_dma_device(struct idxd_device *idxd);
-void idxd_dma_complete_txd(struct idxd_desc *desc,
-			   enum idxd_complete_type comp_type, bool free_desc);
 
 /* cdev */
 int idxd_cdev_register(void);
diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c
index d09a8553ea..264c4e47d7 100644
--- a/drivers/dma/idxd/init.c
+++ b/drivers/dma/idxd/init.c
@@ -59,6 +59,7 @@ static struct idxd_driver_data idxd_driver_data[] = {
 		.evl_cr_off = offsetof(struct iax_evl_entry, cr),
 		.cr_status_off = offsetof(struct iax_completion_record, status),
 		.cr_result_off = offsetof(struct iax_completion_record, error_code),
+		.load_device_defaults = idxd_load_iaa_device_defaults,
 	},
 };
 
@@ -353,7 +354,7 @@ static int idxd_init_evl(struct idxd_device *idxd)
 	if (!evl)
 		return -ENOMEM;
 
-	spin_lock_init(&evl->lock);
+	mutex_init(&evl->lock);
 	evl->size = IDXD_EVL_SIZE_MIN;
 
 	idxd_name = dev_name(idxd_confdev(idxd));
@@ -754,6 +755,12 @@ static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err;
 	}
 
+	if (data->load_device_defaults) {
+		rc = data->load_device_defaults(idxd);
+		if (rc)
+			dev_warn(dev, "IDXD loading device defaults failed\n");
+	}
+
 	rc = idxd_register_devices(idxd);
 	if (rc) {
 		dev_err(dev, "IDXD sysfs setup failed\n");
diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c
index 3bdfc1797f..8dc029c865 100644
--- a/drivers/dma/idxd/irq.c
+++ b/drivers/dma/idxd/irq.c
@@ -123,7 +123,7 @@ static void idxd_abort_invalid_int_handle_descs(struct idxd_irq_entry *ie)
 
 	list_for_each_entry_safe(d, t, &flist, list) {
 		list_del(&d->list);
-		idxd_dma_complete_txd(d, IDXD_COMPLETE_ABORT, true);
+		idxd_desc_complete(d, IDXD_COMPLETE_ABORT, true);
 	}
 }
 
@@ -363,7 +363,7 @@ static void process_evl_entries(struct idxd_device *idxd)
 	evl_status.bits = 0;
 	evl_status.int_pending = 1;
 
-	spin_lock(&evl->lock);
+	mutex_lock(&evl->lock);
 	/* Clear interrupt pending bit */
 	iowrite32(evl_status.bits_upper32,
 		  idxd->reg_base + IDXD_EVLSTATUS_OFFSET + sizeof(u32));
@@ -380,7 +380,7 @@ static void process_evl_entries(struct idxd_device *idxd)
 
 	evl_status.head = h;
 	iowrite32(evl_status.bits_lower32, idxd->reg_base + IDXD_EVLSTATUS_OFFSET);
-	spin_unlock(&evl->lock);
+	mutex_unlock(&evl->lock);
 }
 
 irqreturn_t idxd_misc_thread(int vec, void *data)
@@ -533,7 +533,7 @@ static void idxd_int_handle_resubmit_work(struct work_struct *work)
 		 */
 		if (rc != -EAGAIN) {
 			desc->completion->status = IDXD_COMP_DESC_ABORT;
-			idxd_dma_complete_txd(desc, IDXD_COMPLETE_ABORT, false);
+			idxd_desc_complete(desc, IDXD_COMPLETE_ABORT, false);
 		}
 		idxd_free_desc(wq, desc);
 	}
@@ -574,11 +574,11 @@ static void irq_process_pending_llist(struct idxd_irq_entry *irq_entry)
 			 * and 0xff, which DSA_COMP_STATUS_MASK can mask out.
 			 */
 			if (unlikely(desc->completion->status == IDXD_COMP_DESC_ABORT)) {
-				idxd_dma_complete_txd(desc, IDXD_COMPLETE_ABORT, true);
+				idxd_desc_complete(desc, IDXD_COMPLETE_ABORT, true);
 				continue;
 			}
 
-			idxd_dma_complete_txd(desc, IDXD_COMPLETE_NORMAL, true);
+			idxd_desc_complete(desc, IDXD_COMPLETE_NORMAL, true);
 		} else {
 			spin_lock(&irq_entry->list_lock);
 			list_add_tail(&desc->list,
@@ -617,11 +617,11 @@ static void irq_process_work_list(struct idxd_irq_entry *irq_entry)
 		 * and 0xff, which DSA_COMP_STATUS_MASK can mask out.
 		 */
 		if (unlikely(desc->completion->status == IDXD_COMP_DESC_ABORT)) {
-			idxd_dma_complete_txd(desc, IDXD_COMPLETE_ABORT, true);
+			idxd_desc_complete(desc, IDXD_COMPLETE_ABORT, true);
 			continue;
 		}
 
-		idxd_dma_complete_txd(desc, IDXD_COMPLETE_NORMAL, true);
+		idxd_desc_complete(desc, IDXD_COMPLETE_NORMAL, true);
 	}
 }
 
diff --git a/drivers/dma/idxd/perfmon.c b/drivers/dma/idxd/perfmon.c
index fdda6d6042..5e94247e1e 100644
--- a/drivers/dma/idxd/perfmon.c
+++ b/drivers/dma/idxd/perfmon.c
@@ -528,14 +528,11 @@ static int perf_event_cpu_offline(unsigned int cpu, struct hlist_node *node)
 		return 0;
 
 	target = cpumask_any_but(cpu_online_mask, cpu);
-
 	/* migrate events if there is a valid target */
-	if (target < nr_cpu_ids)
+	if (target < nr_cpu_ids) {
 		cpumask_set_cpu(target, &perfmon_dsa_cpu_mask);
-	else
-		target = -1;
-
-	perf_pmu_migrate_context(&idxd_pmu->pmu, cpu, target);
+		perf_pmu_migrate_context(&idxd_pmu->pmu, cpu, target);
+	}
 
 	return 0;
 }
diff --git a/drivers/dma/idxd/submit.c b/drivers/dma/idxd/submit.c
index 3f922518e3..817a564413 100644
--- a/drivers/dma/idxd/submit.c
+++ b/drivers/dma/idxd/submit.c
@@ -61,6 +61,7 @@ struct idxd_desc *idxd_alloc_desc(struct idxd_wq *wq, enum idxd_op_type optype)
 
 	return __get_desc(wq, idx, cpu);
 }
+EXPORT_SYMBOL_NS_GPL(idxd_alloc_desc, IDXD);
 
 void idxd_free_desc(struct idxd_wq *wq, struct idxd_desc *desc)
 {
@@ -69,6 +70,7 @@ void idxd_free_desc(struct idxd_wq *wq, struct idxd_desc *desc)
 	desc->cpu = -1;
 	sbitmap_queue_clear(&wq->sbq, desc->id, cpu);
 }
+EXPORT_SYMBOL_NS_GPL(idxd_free_desc, IDXD);
 
 static struct idxd_desc *list_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie,
 					 struct idxd_desc *desc)
@@ -125,7 +127,8 @@ static void llist_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie,
 	spin_unlock(&ie->list_lock);
 
 	if (found)
-		idxd_dma_complete_txd(found, IDXD_COMPLETE_ABORT, false);
+		idxd_dma_complete_txd(found, IDXD_COMPLETE_ABORT, false,
+				      NULL, NULL);
 
 	/*
 	 * completing the descriptor will return desc to allocator and
@@ -135,7 +138,8 @@ static void llist_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie,
 	 */
 	list_for_each_entry_safe(d, t, &flist, list) {
 		list_del_init(&d->list);
-		idxd_dma_complete_txd(found, IDXD_COMPLETE_ABORT, true);
+		idxd_dma_complete_txd(found, IDXD_COMPLETE_ABORT, true,
+				      NULL, NULL);
 	}
 }
 
@@ -215,3 +219,4 @@ int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc)
 	percpu_ref_put(&wq->wq_active);
 	return 0;
 }
+EXPORT_SYMBOL_NS_GPL(idxd_submit_desc, IDXD);
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index f81ecf5863..9b42f5e96b 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -421,9 +421,7 @@ struct sdma_desc {
  * @shp_addr:		value for gReg[6]
  * @per_addr:		value for gReg[2]
  * @status:		status of dma channel
- * @context_loaded:	ensure context is only loaded once
  * @data:		specific sdma interface structure
- * @bd_pool:		dma_pool for bd
  * @terminate_worker:	used to call back into terminate work function
  * @terminated:		terminated list
  * @is_ram_script:	flag for script in ram
@@ -486,8 +484,6 @@ struct sdma_channel {
  * @num_script_addrs:	Number of script addresses in this image
  * @ram_code_start:	offset of SDMA ram image in this firmware image
  * @ram_code_size:	size of SDMA ram image
- * @script_addrs:	Stores the start address of the SDMA scripts
- *			(in SDMA memory space)
  */
 struct sdma_firmware_header {
 	u32	magic;
diff --git a/drivers/dma/ls2x-apb-dma.c b/drivers/dma/ls2x-apb-dma.c
new file mode 100644
index 0000000000..a49913f3ed
--- /dev/null
+++ b/drivers/dma/ls2x-apb-dma.c
@@ -0,0 +1,705 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Driver for the Loongson LS2X APB DMA Controller
+ *
+ * Copyright (C) 2017-2023 Loongson Corporation
+ */
+
+#include <linux/clk.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_dma.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#include "dmaengine.h"
+#include "virt-dma.h"
+
+/* Global Configuration Register */
+#define LDMA_ORDER_ERG		0x0
+
+/* Bitfield definitions */
+
+/* Bitfields in Global Configuration Register */
+#define LDMA_64BIT_EN		BIT(0) /* 1: 64 bit support */
+#define LDMA_UNCOHERENT_EN	BIT(1) /* 0: cache, 1: uncache */
+#define LDMA_ASK_VALID		BIT(2)
+#define LDMA_START		BIT(3) /* DMA start operation */
+#define LDMA_STOP		BIT(4) /* DMA stop operation */
+#define LDMA_CONFIG_MASK	GENMASK(4, 0) /* DMA controller config bits mask */
+
+/* Bitfields in ndesc_addr field of HW decriptor */
+#define LDMA_DESC_EN		BIT(0) /*1: The next descriptor is valid */
+#define LDMA_DESC_ADDR_LOW	GENMASK(31, 1)
+
+/* Bitfields in cmd field of HW decriptor */
+#define LDMA_INT		BIT(1) /* Enable DMA interrupts */
+#define LDMA_DATA_DIRECTION	BIT(12) /* 1: write to device, 0: read from device */
+
+#define LDMA_SLAVE_BUSWIDTHS	(BIT(DMA_SLAVE_BUSWIDTH_4_BYTES) | \
+				 BIT(DMA_SLAVE_BUSWIDTH_8_BYTES))
+
+#define LDMA_MAX_TRANS_LEN	U32_MAX
+
+/*--  descriptors  -----------------------------------------------------*/
+
+/*
+ * struct ls2x_dma_hw_desc - DMA HW descriptor
+ * @ndesc_addr: the next descriptor low address.
+ * @mem_addr: memory low address.
+ * @apb_addr: device buffer address.
+ * @len: length of a piece of carried content, in words.
+ * @step_len: length between two moved memory data blocks.
+ * @step_times: number of blocks to be carried in a single DMA operation.
+ * @cmd: descriptor command or state.
+ * @stats: DMA status.
+ * @high_ndesc_addr: the next descriptor high address.
+ * @high_mem_addr: memory high address.
+ * @reserved: reserved
+ */
+struct ls2x_dma_hw_desc {
+	u32 ndesc_addr;
+	u32 mem_addr;
+	u32 apb_addr;
+	u32 len;
+	u32 step_len;
+	u32 step_times;
+	u32 cmd;
+	u32 stats;
+	u32 high_ndesc_addr;
+	u32 high_mem_addr;
+	u32 reserved[2];
+} __packed;
+
+/*
+ * struct ls2x_dma_sg - ls2x dma scatter gather entry
+ * @hw: the pointer to DMA HW descriptor.
+ * @llp: physical address of the DMA HW descriptor.
+ * @phys: destination or source address(mem).
+ * @len: number of Bytes to read.
+ */
+struct ls2x_dma_sg {
+	struct ls2x_dma_hw_desc	*hw;
+	dma_addr_t		llp;
+	dma_addr_t		phys;
+	u32			len;
+};
+
+/*
+ * struct ls2x_dma_desc - software descriptor
+ * @vdesc: pointer to the virtual dma descriptor.
+ * @cyclic: flag to dma cyclic
+ * @burst_size: burst size of transaction, in words.
+ * @desc_num: number of sg entries.
+ * @direction: transfer direction, to or from device.
+ * @status: dma controller status.
+ * @sg: array of sgs.
+ */
+struct ls2x_dma_desc {
+	struct virt_dma_desc		vdesc;
+	bool				cyclic;
+	size_t				burst_size;
+	u32				desc_num;
+	enum dma_transfer_direction	direction;
+	enum dma_status			status;
+	struct ls2x_dma_sg		sg[] __counted_by(desc_num);
+};
+
+/*--  Channels  --------------------------------------------------------*/
+
+/*
+ * struct ls2x_dma_chan - internal representation of an LS2X APB DMA channel
+ * @vchan: virtual dma channel entry.
+ * @desc: pointer to the ls2x sw dma descriptor.
+ * @pool: hw desc table
+ * @irq: irq line
+ * @sconfig: configuration for slave transfers, passed via .device_config
+ */
+struct ls2x_dma_chan {
+	struct virt_dma_chan	vchan;
+	struct ls2x_dma_desc	*desc;
+	void			*pool;
+	int			irq;
+	struct dma_slave_config	sconfig;
+};
+
+/*--  Controller  ------------------------------------------------------*/
+
+/*
+ * struct ls2x_dma_priv - LS2X APB DMAC specific information
+ * @ddev: dmaengine dma_device object members
+ * @dma_clk: DMAC clock source
+ * @regs: memory mapped register base
+ * @lchan: channel to store ls2x_dma_chan structures
+ */
+struct ls2x_dma_priv {
+	struct dma_device	ddev;
+	struct clk		*dma_clk;
+	void __iomem		*regs;
+	struct ls2x_dma_chan	lchan;
+};
+
+/*--  Helper functions  ------------------------------------------------*/
+
+static inline struct ls2x_dma_desc *to_ldma_desc(struct virt_dma_desc *vdesc)
+{
+	return container_of(vdesc, struct ls2x_dma_desc, vdesc);
+}
+
+static inline struct ls2x_dma_chan *to_ldma_chan(struct dma_chan *chan)
+{
+	return container_of(chan, struct ls2x_dma_chan, vchan.chan);
+}
+
+static inline struct ls2x_dma_priv *to_ldma_priv(struct dma_device *ddev)
+{
+	return container_of(ddev, struct ls2x_dma_priv, ddev);
+}
+
+static struct device *chan2dev(struct dma_chan *chan)
+{
+	return &chan->dev->device;
+}
+
+static void ls2x_dma_desc_free(struct virt_dma_desc *vdesc)
+{
+	struct ls2x_dma_chan *lchan = to_ldma_chan(vdesc->tx.chan);
+	struct ls2x_dma_desc *desc = to_ldma_desc(vdesc);
+	int i;
+
+	for (i = 0; i < desc->desc_num; i++) {
+		if (desc->sg[i].hw)
+			dma_pool_free(lchan->pool, desc->sg[i].hw,
+				      desc->sg[i].llp);
+	}
+
+	kfree(desc);
+}
+
+static void ls2x_dma_write_cmd(struct ls2x_dma_chan *lchan, bool cmd)
+{
+	struct ls2x_dma_priv *priv = to_ldma_priv(lchan->vchan.chan.device);
+	u64 val;
+
+	val = lo_hi_readq(priv->regs + LDMA_ORDER_ERG) & ~LDMA_CONFIG_MASK;
+	val |= LDMA_64BIT_EN | cmd;
+	lo_hi_writeq(val, priv->regs + LDMA_ORDER_ERG);
+}
+
+static void ls2x_dma_start_transfer(struct ls2x_dma_chan *lchan)
+{
+	struct ls2x_dma_priv *priv = to_ldma_priv(lchan->vchan.chan.device);
+	struct ls2x_dma_sg *ldma_sg;
+	struct virt_dma_desc *vdesc;
+	u64 val;
+
+	/* Get the next descriptor */
+	vdesc = vchan_next_desc(&lchan->vchan);
+	if (!vdesc) {
+		lchan->desc = NULL;
+		return;
+	}
+
+	list_del(&vdesc->node);
+	lchan->desc = to_ldma_desc(vdesc);
+	ldma_sg = &lchan->desc->sg[0];
+
+	/* Start DMA */
+	lo_hi_writeq(0, priv->regs + LDMA_ORDER_ERG);
+	val = (ldma_sg->llp & ~LDMA_CONFIG_MASK) | LDMA_64BIT_EN | LDMA_START;
+	lo_hi_writeq(val, priv->regs + LDMA_ORDER_ERG);
+}
+
+static size_t ls2x_dmac_detect_burst(struct ls2x_dma_chan *lchan)
+{
+	u32 maxburst, buswidth;
+
+	/* Reject definitely invalid configurations */
+	if ((lchan->sconfig.src_addr_width & LDMA_SLAVE_BUSWIDTHS) &&
+	    (lchan->sconfig.dst_addr_width & LDMA_SLAVE_BUSWIDTHS))
+		return 0;
+
+	if (lchan->sconfig.direction == DMA_MEM_TO_DEV) {
+		maxburst = lchan->sconfig.dst_maxburst;
+		buswidth = lchan->sconfig.dst_addr_width;
+	} else {
+		maxburst = lchan->sconfig.src_maxburst;
+		buswidth = lchan->sconfig.src_addr_width;
+	}
+
+	/* If maxburst is zero, fallback to LDMA_MAX_TRANS_LEN */
+	return maxburst ? (maxburst * buswidth) >> 2 : LDMA_MAX_TRANS_LEN;
+}
+
+static void ls2x_dma_fill_desc(struct ls2x_dma_chan *lchan, u32 sg_index,
+			       struct ls2x_dma_desc *desc)
+{
+	struct ls2x_dma_sg *ldma_sg = &desc->sg[sg_index];
+	u32 num_segments, segment_size;
+
+	if (desc->direction == DMA_MEM_TO_DEV) {
+		ldma_sg->hw->cmd = LDMA_INT | LDMA_DATA_DIRECTION;
+		ldma_sg->hw->apb_addr = lchan->sconfig.dst_addr;
+	} else {
+		ldma_sg->hw->cmd = LDMA_INT;
+		ldma_sg->hw->apb_addr = lchan->sconfig.src_addr;
+	}
+
+	ldma_sg->hw->mem_addr = lower_32_bits(ldma_sg->phys);
+	ldma_sg->hw->high_mem_addr = upper_32_bits(ldma_sg->phys);
+
+	/* Split into multiple equally sized segments if necessary */
+	num_segments = DIV_ROUND_UP((ldma_sg->len + 3) >> 2, desc->burst_size);
+	segment_size = DIV_ROUND_UP((ldma_sg->len + 3) >> 2, num_segments);
+
+	/* Word count register takes input in words */
+	ldma_sg->hw->len = segment_size;
+	ldma_sg->hw->step_times = num_segments;
+	ldma_sg->hw->step_len = 0;
+
+	/* lets make a link list */
+	if (sg_index) {
+		desc->sg[sg_index - 1].hw->ndesc_addr = ldma_sg->llp | LDMA_DESC_EN;
+		desc->sg[sg_index - 1].hw->high_ndesc_addr = upper_32_bits(ldma_sg->llp);
+	}
+}
+
+/*--  DMA Engine API  --------------------------------------------------*/
+
+/*
+ * ls2x_dma_alloc_chan_resources - allocate resources for DMA channel
+ * @chan: allocate descriptor resources for this channel
+ *
+ * return - the number of allocated descriptors
+ */
+static int ls2x_dma_alloc_chan_resources(struct dma_chan *chan)
+{
+	struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+
+	/* Create a pool of consistent memory blocks for hardware descriptors */
+	lchan->pool = dma_pool_create(dev_name(chan2dev(chan)),
+				      chan->device->dev, PAGE_SIZE,
+				      __alignof__(struct ls2x_dma_hw_desc), 0);
+	if (!lchan->pool) {
+		dev_err(chan2dev(chan), "No memory for descriptors\n");
+		return -ENOMEM;
+	}
+
+	return 1;
+}
+
+/*
+ * ls2x_dma_free_chan_resources - free all channel resources
+ * @chan: DMA channel
+ */
+static void ls2x_dma_free_chan_resources(struct dma_chan *chan)
+{
+	struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+
+	vchan_free_chan_resources(to_virt_chan(chan));
+	dma_pool_destroy(lchan->pool);
+	lchan->pool = NULL;
+}
+
+/*
+ * ls2x_dma_prep_slave_sg - prepare descriptors for a DMA_SLAVE transaction
+ * @chan: DMA channel
+ * @sgl: scatterlist to transfer to/from
+ * @sg_len: number of entries in @scatterlist
+ * @direction: DMA direction
+ * @flags: tx descriptor status flags
+ * @context: transaction context (ignored)
+ *
+ * Return: Async transaction descriptor on success and NULL on failure
+ */
+static struct dma_async_tx_descriptor *
+ls2x_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
+		       u32 sg_len, enum dma_transfer_direction direction,
+		       unsigned long flags, void *context)
+{
+	struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+	struct ls2x_dma_desc *desc;
+	struct scatterlist *sg;
+	size_t burst_size;
+	int i;
+
+	if (unlikely(!sg_len || !is_slave_direction(direction)))
+		return NULL;
+
+	burst_size = ls2x_dmac_detect_burst(lchan);
+	if (!burst_size)
+		return NULL;
+
+	desc = kzalloc(struct_size(desc, sg, sg_len), GFP_NOWAIT);
+	if (!desc)
+		return NULL;
+
+	desc->desc_num = sg_len;
+	desc->direction = direction;
+	desc->burst_size = burst_size;
+
+	for_each_sg(sgl, sg, sg_len, i) {
+		struct ls2x_dma_sg *ldma_sg = &desc->sg[i];
+
+		/* Allocate DMA capable memory for hardware descriptor */
+		ldma_sg->hw = dma_pool_alloc(lchan->pool, GFP_NOWAIT, &ldma_sg->llp);
+		if (!ldma_sg->hw) {
+			desc->desc_num = i;
+			ls2x_dma_desc_free(&desc->vdesc);
+			return NULL;
+		}
+
+		ldma_sg->phys = sg_dma_address(sg);
+		ldma_sg->len = sg_dma_len(sg);
+
+		ls2x_dma_fill_desc(lchan, i, desc);
+	}
+
+	/* Setting the last descriptor enable bit */
+	desc->sg[sg_len - 1].hw->ndesc_addr &= ~LDMA_DESC_EN;
+	desc->status = DMA_IN_PROGRESS;
+
+	return vchan_tx_prep(&lchan->vchan, &desc->vdesc, flags);
+}
+
+/*
+ * ls2x_dma_prep_dma_cyclic - prepare the cyclic DMA transfer
+ * @chan: the DMA channel to prepare
+ * @buf_addr: physical DMA address where the buffer starts
+ * @buf_len: total number of bytes for the entire buffer
+ * @period_len: number of bytes for each period
+ * @direction: transfer direction, to or from device
+ * @flags: tx descriptor status flags
+ *
+ * Return: Async transaction descriptor on success and NULL on failure
+ */
+static struct dma_async_tx_descriptor *
+ls2x_dma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
+			 size_t period_len, enum dma_transfer_direction direction,
+			 unsigned long flags)
+{
+	struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+	struct ls2x_dma_desc *desc;
+	size_t burst_size;
+	u32 num_periods;
+	int i;
+
+	if (unlikely(!buf_len || !period_len))
+		return NULL;
+
+	if (unlikely(!is_slave_direction(direction)))
+		return NULL;
+
+	burst_size = ls2x_dmac_detect_burst(lchan);
+	if (!burst_size)
+		return NULL;
+
+	num_periods = buf_len / period_len;
+	desc = kzalloc(struct_size(desc, sg, num_periods), GFP_NOWAIT);
+	if (!desc)
+		return NULL;
+
+	desc->desc_num = num_periods;
+	desc->direction = direction;
+	desc->burst_size = burst_size;
+
+	/* Build cyclic linked list */
+	for (i = 0; i < num_periods; i++) {
+		struct ls2x_dma_sg *ldma_sg = &desc->sg[i];
+
+		/* Allocate DMA capable memory for hardware descriptor */
+		ldma_sg->hw = dma_pool_alloc(lchan->pool, GFP_NOWAIT, &ldma_sg->llp);
+		if (!ldma_sg->hw) {
+			desc->desc_num = i;
+			ls2x_dma_desc_free(&desc->vdesc);
+			return NULL;
+		}
+
+		ldma_sg->phys = buf_addr + period_len * i;
+		ldma_sg->len = period_len;
+
+		ls2x_dma_fill_desc(lchan, i, desc);
+	}
+
+	/* Lets make a cyclic list */
+	desc->sg[num_periods - 1].hw->ndesc_addr = desc->sg[0].llp | LDMA_DESC_EN;
+	desc->sg[num_periods - 1].hw->high_ndesc_addr = upper_32_bits(desc->sg[0].llp);
+	desc->cyclic = true;
+	desc->status = DMA_IN_PROGRESS;
+
+	return vchan_tx_prep(&lchan->vchan, &desc->vdesc, flags);
+}
+
+/*
+ * ls2x_slave_config - set slave configuration for channel
+ * @chan: dma channel
+ * @cfg: slave configuration
+ *
+ * Sets slave configuration for channel
+ */
+static int ls2x_dma_slave_config(struct dma_chan *chan,
+				 struct dma_slave_config *config)
+{
+	struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+
+	memcpy(&lchan->sconfig, config, sizeof(*config));
+	return 0;
+}
+
+/*
+ * ls2x_dma_issue_pending - push pending transactions to the hardware
+ * @chan: channel
+ *
+ * When this function is called, all pending transactions are pushed to the
+ * hardware and executed.
+ */
+static void ls2x_dma_issue_pending(struct dma_chan *chan)
+{
+	struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&lchan->vchan.lock, flags);
+	if (vchan_issue_pending(&lchan->vchan) && !lchan->desc)
+		ls2x_dma_start_transfer(lchan);
+	spin_unlock_irqrestore(&lchan->vchan.lock, flags);
+}
+
+/*
+ * ls2x_dma_terminate_all - terminate all transactions
+ * @chan: channel
+ *
+ * Stops all DMA transactions.
+ */
+static int ls2x_dma_terminate_all(struct dma_chan *chan)
+{
+	struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	spin_lock_irqsave(&lchan->vchan.lock, flags);
+	/* Setting stop cmd */
+	ls2x_dma_write_cmd(lchan, LDMA_STOP);
+	if (lchan->desc) {
+		vchan_terminate_vdesc(&lchan->desc->vdesc);
+		lchan->desc = NULL;
+	}
+
+	vchan_get_all_descriptors(&lchan->vchan, &head);
+	spin_unlock_irqrestore(&lchan->vchan.lock, flags);
+
+	vchan_dma_desc_free_list(&lchan->vchan, &head);
+	return 0;
+}
+
+/*
+ * ls2x_dma_synchronize - Synchronizes the termination of transfers to the
+ * current context.
+ * @chan: channel
+ */
+static void ls2x_dma_synchronize(struct dma_chan *chan)
+{
+	struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+
+	vchan_synchronize(&lchan->vchan);
+}
+
+static int ls2x_dma_pause(struct dma_chan *chan)
+{
+	struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&lchan->vchan.lock, flags);
+	if (lchan->desc && lchan->desc->status == DMA_IN_PROGRESS) {
+		ls2x_dma_write_cmd(lchan, LDMA_STOP);
+		lchan->desc->status = DMA_PAUSED;
+	}
+	spin_unlock_irqrestore(&lchan->vchan.lock, flags);
+
+	return 0;
+}
+
+static int ls2x_dma_resume(struct dma_chan *chan)
+{
+	struct ls2x_dma_chan *lchan = to_ldma_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&lchan->vchan.lock, flags);
+	if (lchan->desc && lchan->desc->status == DMA_PAUSED) {
+		lchan->desc->status = DMA_IN_PROGRESS;
+		ls2x_dma_write_cmd(lchan, LDMA_START);
+	}
+	spin_unlock_irqrestore(&lchan->vchan.lock, flags);
+
+	return 0;
+}
+
+/*
+ * ls2x_dma_isr - LS2X DMA Interrupt handler
+ * @irq: IRQ number
+ * @dev_id: Pointer to ls2x_dma_chan
+ *
+ * Return: IRQ_HANDLED/IRQ_NONE
+ */
+static irqreturn_t ls2x_dma_isr(int irq, void *dev_id)
+{
+	struct ls2x_dma_chan *lchan = dev_id;
+	struct ls2x_dma_desc *desc;
+
+	spin_lock(&lchan->vchan.lock);
+	desc = lchan->desc;
+	if (desc) {
+		if (desc->cyclic) {
+			vchan_cyclic_callback(&desc->vdesc);
+		} else {
+			desc->status = DMA_COMPLETE;
+			vchan_cookie_complete(&desc->vdesc);
+			ls2x_dma_start_transfer(lchan);
+		}
+
+		/* ls2x_dma_start_transfer() updates lchan->desc */
+		if (!lchan->desc)
+			ls2x_dma_write_cmd(lchan, LDMA_STOP);
+	}
+	spin_unlock(&lchan->vchan.lock);
+
+	return IRQ_HANDLED;
+}
+
+static int ls2x_dma_chan_init(struct platform_device *pdev,
+			      struct ls2x_dma_priv *priv)
+{
+	struct ls2x_dma_chan *lchan = &priv->lchan;
+	struct device *dev = &pdev->dev;
+	int ret;
+
+	lchan->irq = platform_get_irq(pdev, 0);
+	if (lchan->irq < 0)
+		return lchan->irq;
+
+	ret = devm_request_irq(dev, lchan->irq, ls2x_dma_isr, IRQF_TRIGGER_RISING,
+			       dev_name(&pdev->dev), lchan);
+	if (ret)
+		return ret;
+
+	/* Initialize channels related values */
+	INIT_LIST_HEAD(&priv->ddev.channels);
+	lchan->vchan.desc_free = ls2x_dma_desc_free;
+	vchan_init(&lchan->vchan, &priv->ddev);
+
+	return 0;
+}
+
+/*
+ * ls2x_dma_probe - Driver probe function
+ * @pdev: Pointer to the platform_device structure
+ *
+ * Return: '0' on success and failure value on error
+ */
+static int ls2x_dma_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct ls2x_dma_priv *priv;
+	struct dma_device *ddev;
+	int ret;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->regs = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(priv->regs))
+		return dev_err_probe(dev, PTR_ERR(priv->regs),
+				     "devm_platform_ioremap_resource failed.\n");
+
+	priv->dma_clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(priv->dma_clk))
+		return dev_err_probe(dev, PTR_ERR(priv->dma_clk), "devm_clk_get failed.\n");
+
+	ret = clk_prepare_enable(priv->dma_clk);
+	if (ret)
+		return dev_err_probe(dev, ret, "clk_prepare_enable failed.\n");
+
+	ret = ls2x_dma_chan_init(pdev, priv);
+	if (ret)
+		goto disable_clk;
+
+	ddev = &priv->ddev;
+	ddev->dev = dev;
+	dma_cap_zero(ddev->cap_mask);
+	dma_cap_set(DMA_SLAVE, ddev->cap_mask);
+	dma_cap_set(DMA_CYCLIC, ddev->cap_mask);
+
+	ddev->device_alloc_chan_resources = ls2x_dma_alloc_chan_resources;
+	ddev->device_free_chan_resources = ls2x_dma_free_chan_resources;
+	ddev->device_tx_status = dma_cookie_status;
+	ddev->device_issue_pending = ls2x_dma_issue_pending;
+	ddev->device_prep_slave_sg = ls2x_dma_prep_slave_sg;
+	ddev->device_prep_dma_cyclic = ls2x_dma_prep_dma_cyclic;
+	ddev->device_config = ls2x_dma_slave_config;
+	ddev->device_terminate_all = ls2x_dma_terminate_all;
+	ddev->device_synchronize = ls2x_dma_synchronize;
+	ddev->device_pause = ls2x_dma_pause;
+	ddev->device_resume = ls2x_dma_resume;
+
+	ddev->src_addr_widths = LDMA_SLAVE_BUSWIDTHS;
+	ddev->dst_addr_widths = LDMA_SLAVE_BUSWIDTHS;
+	ddev->directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
+
+	ret = dma_async_device_register(&priv->ddev);
+	if (ret < 0)
+		goto disable_clk;
+
+	ret = of_dma_controller_register(dev->of_node, of_dma_xlate_by_chan_id, priv);
+	if (ret < 0)
+		goto unregister_dmac;
+
+	platform_set_drvdata(pdev, priv);
+
+	dev_info(dev, "Loongson LS2X APB DMA driver registered successfully.\n");
+	return 0;
+
+unregister_dmac:
+	dma_async_device_unregister(&priv->ddev);
+disable_clk:
+	clk_disable_unprepare(priv->dma_clk);
+
+	return ret;
+}
+
+/*
+ * ls2x_dma_remove - Driver remove function
+ * @pdev: Pointer to the platform_device structure
+ */
+static void ls2x_dma_remove(struct platform_device *pdev)
+{
+	struct ls2x_dma_priv *priv = platform_get_drvdata(pdev);
+
+	of_dma_controller_free(pdev->dev.of_node);
+	dma_async_device_unregister(&priv->ddev);
+	clk_disable_unprepare(priv->dma_clk);
+}
+
+static const struct of_device_id ls2x_dma_of_match_table[] = {
+	{ .compatible = "loongson,ls2k1000-apbdma" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, ls2x_dma_of_match_table);
+
+static struct platform_driver ls2x_dmac_driver = {
+	.probe		= ls2x_dma_probe,
+	.remove_new	= ls2x_dma_remove,
+	.driver = {
+		.name	= "ls2x-apbdma",
+		.of_match_table	= ls2x_dma_of_match_table,
+	},
+};
+module_platform_driver(ls2x_dmac_driver);
+
+MODULE_DESCRIPTION("Loongson LS2X APB DMA Controller driver");
+MODULE_AUTHOR("Loongson Technology Corporation Limited");
+MODULE_LICENSE("GPL");
diff --git a/drivers/dma/milbeaut-hdmac.c b/drivers/dma/milbeaut-hdmac.c
index 1b0a958926..7b41c67097 100644
--- a/drivers/dma/milbeaut-hdmac.c
+++ b/drivers/dma/milbeaut-hdmac.c
@@ -531,7 +531,7 @@ disable_clk:
 	return ret;
 }
 
-static int milbeaut_hdmac_remove(struct platform_device *pdev)
+static void milbeaut_hdmac_remove(struct platform_device *pdev)
 {
 	struct milbeaut_hdmac_device *mdev = platform_get_drvdata(pdev);
 	struct dma_chan *chan;
@@ -546,16 +546,21 @@ static int milbeaut_hdmac_remove(struct platform_device *pdev)
 	 */
 	list_for_each_entry(chan, &mdev->ddev.channels, device_node) {
 		ret = dmaengine_terminate_sync(chan);
-		if (ret)
-			return ret;
+		if (ret) {
+			/*
+			 * This results in resource leakage and maybe also
+			 * use-after-free errors as e.g. *mdev is kfreed.
+			 */
+			dev_alert(&pdev->dev, "Failed to terminate channel %d (%pe)\n",
+				  chan->chan_id, ERR_PTR(ret));
+			return;
+		}
 		milbeaut_hdmac_free_chan_resources(chan);
 	}
 
 	of_dma_controller_free(pdev->dev.of_node);
 	dma_async_device_unregister(&mdev->ddev);
 	clk_disable_unprepare(mdev->clk);
-
-	return 0;
 }
 
 static const struct of_device_id milbeaut_hdmac_match[] = {
@@ -566,7 +571,7 @@ MODULE_DEVICE_TABLE(of, milbeaut_hdmac_match);
 
 static struct platform_driver milbeaut_hdmac_driver = {
 	.probe = milbeaut_hdmac_probe,
-	.remove = milbeaut_hdmac_remove,
+	.remove_new = milbeaut_hdmac_remove,
 	.driver = {
 		.name = "milbeaut-m10v-hdmac",
 		.of_match_table = milbeaut_hdmac_match,
diff --git a/drivers/dma/milbeaut-xdmac.c b/drivers/dma/milbeaut-xdmac.c
index d29d01e730..2cce529b44 100644
--- a/drivers/dma/milbeaut-xdmac.c
+++ b/drivers/dma/milbeaut-xdmac.c
@@ -368,7 +368,7 @@ disable_xdmac:
 	return ret;
 }
 
-static int milbeaut_xdmac_remove(struct platform_device *pdev)
+static void milbeaut_xdmac_remove(struct platform_device *pdev)
 {
 	struct milbeaut_xdmac_device *mdev = platform_get_drvdata(pdev);
 	struct dma_chan *chan;
@@ -383,8 +383,15 @@ static int milbeaut_xdmac_remove(struct platform_device *pdev)
 	 */
 	list_for_each_entry(chan, &mdev->ddev.channels, device_node) {
 		ret = dmaengine_terminate_sync(chan);
-		if (ret)
-			return ret;
+		if (ret) {
+			/*
+			 * This results in resource leakage and maybe also
+			 * use-after-free errors as e.g. *mdev is kfreed.
+			 */
+			dev_alert(&pdev->dev, "Failed to terminate channel %d (%pe)\n",
+				  chan->chan_id, ERR_PTR(ret));
+			return;
+		}
 		milbeaut_xdmac_free_chan_resources(chan);
 	}
 
@@ -392,8 +399,6 @@ static int milbeaut_xdmac_remove(struct platform_device *pdev)
 	dma_async_device_unregister(&mdev->ddev);
 
 	disable_xdmac(mdev);
-
-	return 0;
 }
 
 static const struct of_device_id milbeaut_xdmac_match[] = {
@@ -404,7 +409,7 @@ MODULE_DEVICE_TABLE(of, milbeaut_xdmac_match);
 
 static struct platform_driver milbeaut_xdmac_driver = {
 	.probe = milbeaut_xdmac_probe,
-	.remove = milbeaut_xdmac_remove,
+	.remove_new = milbeaut_xdmac_remove,
 	.driver = {
 		.name = "milbeaut-m10v-xdmac",
 		.of_match_table = milbeaut_xdmac_match,
diff --git a/drivers/dma/owl-dma.c b/drivers/dma/owl-dma.c
index 4e76c4ec2d..e001f4f7aa 100644
--- a/drivers/dma/owl-dma.c
+++ b/drivers/dma/owl-dma.c
@@ -250,7 +250,7 @@ static void pchan_update(struct owl_dma_pchan *pchan, u32 reg,
 	else
 		regval &= ~val;
 
-	writel(val, pchan->base + reg);
+	writel(regval, pchan->base + reg);
 }
 
 static void pchan_writel(struct owl_dma_pchan *pchan, u32 reg, u32 data)
@@ -274,7 +274,7 @@ static void dma_update(struct owl_dma *od, u32 reg, u32 val, bool state)
 	else
 		regval &= ~val;
 
-	writel(val, od->base + reg);
+	writel(regval, od->base + reg);
 }
 
 static void dma_writel(struct owl_dma *od, u32 reg, u32 data)
diff --git a/drivers/dma/sf-pdma/sf-pdma.c b/drivers/dma/sf-pdma/sf-pdma.c
index 3125a2f162..4284736111 100644
--- a/drivers/dma/sf-pdma/sf-pdma.c
+++ b/drivers/dma/sf-pdma/sf-pdma.c
@@ -20,10 +20,13 @@
 #include <linux/mod_devicetable.h>
 #include <linux/dma-mapping.h>
 #include <linux/of.h>
+#include <linux/of_dma.h>
 #include <linux/slab.h>
 
 #include "sf-pdma.h"
 
+#define PDMA_QUIRK_NO_STRICT_ORDERING   BIT(0)
+
 #ifndef readq
 static inline unsigned long long readq(void __iomem *addr)
 {
@@ -65,7 +68,7 @@ static struct sf_pdma_desc *sf_pdma_alloc_desc(struct sf_pdma_chan *chan)
 static void sf_pdma_fill_desc(struct sf_pdma_desc *desc,
 			      u64 dst, u64 src, u64 size)
 {
-	desc->xfer_type = PDMA_FULL_SPEED;
+	desc->xfer_type =  desc->chan->pdma->transfer_type;
 	desc->xfer_size = size;
 	desc->dst_addr = dst;
 	desc->src_addr = src;
@@ -492,6 +495,7 @@ static void sf_pdma_setup_chans(struct sf_pdma *pdma)
 
 static int sf_pdma_probe(struct platform_device *pdev)
 {
+	const struct sf_pdma_driver_platdata *ddata;
 	struct sf_pdma *pdma;
 	int ret, n_chans;
 	const enum dma_slave_buswidth widths =
@@ -517,6 +521,14 @@ static int sf_pdma_probe(struct platform_device *pdev)
 
 	pdma->n_chans = n_chans;
 
+	pdma->transfer_type = PDMA_FULL_SPEED | PDMA_STRICT_ORDERING;
+
+	ddata  = device_get_match_data(&pdev->dev);
+	if (ddata) {
+		if (ddata->quirks & PDMA_QUIRK_NO_STRICT_ORDERING)
+			pdma->transfer_type &= ~PDMA_STRICT_ORDERING;
+	}
+
 	pdma->membase = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(pdma->membase))
 		return PTR_ERR(pdma->membase);
@@ -563,7 +575,20 @@ static int sf_pdma_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	ret = of_dma_controller_register(pdev->dev.of_node,
+					 of_dma_xlate_by_chan_id, pdma);
+	if (ret < 0) {
+		dev_err(&pdev->dev,
+			"Can't register SiFive Platform OF_DMA. (%d)\n", ret);
+		goto err_unregister;
+	}
+
 	return 0;
+
+err_unregister:
+	dma_async_device_unregister(&pdma->dma_dev);
+
+	return ret;
 }
 
 static void sf_pdma_remove(struct platform_device *pdev)
@@ -583,12 +608,25 @@ static void sf_pdma_remove(struct platform_device *pdev)
 		tasklet_kill(&ch->err_tasklet);
 	}
 
+	if (pdev->dev.of_node)
+		of_dma_controller_free(pdev->dev.of_node);
+
 	dma_async_device_unregister(&pdma->dma_dev);
 }
 
+static const struct sf_pdma_driver_platdata mpfs_pdma = {
+	.quirks = PDMA_QUIRK_NO_STRICT_ORDERING,
+};
+
 static const struct of_device_id sf_pdma_dt_ids[] = {
-	{ .compatible = "sifive,fu540-c000-pdma" },
-	{ .compatible = "sifive,pdma0" },
+	{
+		.compatible = "sifive,fu540-c000-pdma",
+	}, {
+		.compatible = "sifive,pdma0",
+	}, {
+		.compatible = "microchip,mpfs-pdma",
+		.data	    = &mpfs_pdma,
+	},
 	{},
 };
 MODULE_DEVICE_TABLE(of, sf_pdma_dt_ids);
diff --git a/drivers/dma/sf-pdma/sf-pdma.h b/drivers/dma/sf-pdma/sf-pdma.h
index d05772b5d8..215e07183d 100644
--- a/drivers/dma/sf-pdma/sf-pdma.h
+++ b/drivers/dma/sf-pdma/sf-pdma.h
@@ -48,7 +48,8 @@
 #define PDMA_ERR_STATUS_MASK				GENMASK(31, 31)
 
 /* Transfer Type */
-#define PDMA_FULL_SPEED					0xFF000008
+#define PDMA_FULL_SPEED					0xFF000000
+#define PDMA_STRICT_ORDERING				BIT(3)
 
 /* Error Recovery */
 #define MAX_RETRY					1
@@ -112,8 +113,13 @@ struct sf_pdma {
 	struct dma_device       dma_dev;
 	void __iomem            *membase;
 	void __iomem            *mappedbase;
+	u32			transfer_type;
 	u32			n_chans;
 	struct sf_pdma_chan	chans[] __counted_by(n_chans);
 };
 
+struct sf_pdma_driver_platdata {
+	u32 quirks;
+};
+
 #endif /* _SF_PDMA_H */
diff --git a/drivers/dma/sh/rz-dmac.c b/drivers/dma/sh/rz-dmac.c
index fea5bda34b..1f1e86ba5c 100644
--- a/drivers/dma/sh/rz-dmac.c
+++ b/drivers/dma/sh/rz-dmac.c
@@ -755,11 +755,11 @@ static struct dma_chan *rz_dmac_of_xlate(struct of_phandle_args *dma_spec,
 
 static int rz_dmac_chan_probe(struct rz_dmac *dmac,
 			      struct rz_dmac_chan *channel,
-			      unsigned int index)
+			      u8 index)
 {
 	struct platform_device *pdev = to_platform_device(dmac->dev);
 	struct rz_lmdesc *lmdesc;
-	char pdev_irqname[5];
+	char pdev_irqname[6];
 	char *irqname;
 	int ret;
 
@@ -767,7 +767,7 @@ static int rz_dmac_chan_probe(struct rz_dmac *dmac,
 	channel->mid_rid = -EINVAL;
 
 	/* Request the channel interrupt. */
-	sprintf(pdev_irqname, "ch%u", index);
+	scnprintf(pdev_irqname, sizeof(pdev_irqname), "ch%u", index);
 	channel->irq = platform_get_irq_byname(pdev, pdev_irqname);
 	if (channel->irq < 0)
 		return channel->irq;
@@ -845,9 +845,9 @@ static int rz_dmac_probe(struct platform_device *pdev)
 	struct dma_device *engine;
 	struct rz_dmac *dmac;
 	int channel_num;
-	unsigned int i;
 	int ret;
 	int irq;
+	u8 i;
 
 	dmac = devm_kzalloc(&pdev->dev, sizeof(*dmac), GFP_KERNEL);
 	if (!dmac)
diff --git a/drivers/dma/sh/usb-dmac.c b/drivers/dma/sh/usb-dmac.c
index a9b4302f60..f7cd0cad05 100644
--- a/drivers/dma/sh/usb-dmac.c
+++ b/drivers/dma/sh/usb-dmac.c
@@ -706,10 +706,10 @@ static const struct dev_pm_ops usb_dmac_pm = {
 
 static int usb_dmac_chan_probe(struct usb_dmac *dmac,
 			       struct usb_dmac_chan *uchan,
-			       unsigned int index)
+			       u8 index)
 {
 	struct platform_device *pdev = to_platform_device(dmac->dev);
-	char pdev_irqname[5];
+	char pdev_irqname[6];
 	char *irqname;
 	int ret;
 
@@ -717,7 +717,7 @@ static int usb_dmac_chan_probe(struct usb_dmac *dmac,
 	uchan->iomem = dmac->iomem + USB_DMAC_CHAN_OFFSET(index);
 
 	/* Request the channel interrupt. */
-	sprintf(pdev_irqname, "ch%u", index);
+	scnprintf(pdev_irqname, sizeof(pdev_irqname), "ch%u", index);
 	uchan->irq = platform_get_irq_byname(pdev, pdev_irqname);
 	if (uchan->irq < 0)
 		return -ENODEV;
@@ -768,8 +768,8 @@ static int usb_dmac_probe(struct platform_device *pdev)
 	const enum dma_slave_buswidth widths = USB_DMAC_SLAVE_BUSWIDTH;
 	struct dma_device *engine;
 	struct usb_dmac *dmac;
-	unsigned int i;
 	int ret;
+	u8 i;
 
 	dmac = devm_kzalloc(&pdev->dev, sizeof(*dmac), GFP_KERNEL);
 	if (!dmac)
@@ -869,7 +869,7 @@ static void usb_dmac_chan_remove(struct usb_dmac *dmac,
 static void usb_dmac_remove(struct platform_device *pdev)
 {
 	struct usb_dmac *dmac = platform_get_drvdata(pdev);
-	int i;
+	u8 i;
 
 	for (i = 0; i < dmac->n_channels; ++i)
 		usb_dmac_chan_remove(dmac, &dmac->channels[i]);
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index 002833fb1f..2c48929914 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -31,13 +31,11 @@
 /**
  * struct stedma40_platform_data - Configuration struct for the dma device.
  *
- * @dev_tx: mapping between destination event line and io address
- * @dev_rx: mapping between source event line and io address
  * @disabled_channels: A vector, ending with -1, that marks physical channels
  * that are for different reasons not available for the driver.
  * @soft_lli_chans: A vector, that marks physical channels will use LLI by SW
  * which avoids HW bug that exists in some versions of the controller.
- * SoftLLI introduces relink overhead that could impact performace for
+ * SoftLLI introduces relink overhead that could impact performance for
  * certain use cases.
  * @num_of_soft_lli_chans: The number of channels that needs to be configured
  * to use SoftLLI.
@@ -184,7 +182,7 @@ static __maybe_unused u32 d40_backup_regs[] = {
 
 /*
  * since 9540 and 8540 has the same HW revision
- * use v4a for 9540 or ealier
+ * use v4a for 9540 or earlier
  * use v4b for 8540 or later
  * HW revision:
  * DB8500ed has revision 0
@@ -411,7 +409,7 @@ struct d40_desc {
  *
  * @base: The virtual address of LCLA. 18 bit aligned.
  * @dma_addr: DMA address, if mapped
- * @base_unaligned: The orignal kmalloc pointer, if kmalloc is used.
+ * @base_unaligned: The original kmalloc pointer, if kmalloc is used.
  * This pointer is only there for clean-up on error.
  * @pages: The number of pages needed for all physical channels.
  * Only used later for clean-up on error
@@ -1655,7 +1653,7 @@ static void dma_tasklet(struct tasklet_struct *t)
 
 	return;
  check_pending_tx:
-	/* Rescue manouver if receiving double interrupts */
+	/* Rescue maneuver if receiving double interrupts */
 	if (d40c->pending_tx > 0)
 		d40c->pending_tx--;
 	spin_unlock_irqrestore(&d40c->lock, flags);
@@ -3412,7 +3410,7 @@ static int __init d40_lcla_allocate(struct d40_base *base)
 		base->lcla_pool.base = (void *)page_list[i];
 	} else {
 		/*
-		 * After many attempts and no succees with finding the correct
+		 * After many attempts and no success with finding the correct
 		 * alignment, try with allocating a big buffer.
 		 */
 		dev_warn(base->dev,
diff --git a/drivers/dma/tegra186-gpc-dma.c b/drivers/dma/tegra186-gpc-dma.c
index fa4d4142a6..3642508e88 100644
--- a/drivers/dma/tegra186-gpc-dma.c
+++ b/drivers/dma/tegra186-gpc-dma.c
@@ -746,6 +746,9 @@ static int tegra_dma_get_residual(struct tegra_dma_channel *tdc)
 	bytes_xfer = dma_desc->bytes_xfer +
 		     sg_req[dma_desc->sg_idx].len - (wcount * 4);
 
+	if (dma_desc->bytes_req == bytes_xfer)
+		return 0;
+
 	residual = dma_desc->bytes_req - (bytes_xfer % dma_desc->bytes_req);
 
 	return residual;
@@ -1348,8 +1351,8 @@ static int tegra_dma_program_sid(struct tegra_dma_channel *tdc, int stream_id)
 static int tegra_dma_probe(struct platform_device *pdev)
 {
 	const struct tegra_dma_chip_data *cdata = NULL;
-	struct iommu_fwspec *iommu_spec;
-	unsigned int stream_id, i;
+	unsigned int i;
+	u32 stream_id;
 	struct tegra_dma *tdma;
 	int ret;
 
@@ -1378,12 +1381,10 @@ static int tegra_dma_probe(struct platform_device *pdev)
 
 	tdma->dma_dev.dev = &pdev->dev;
 
-	iommu_spec = dev_iommu_fwspec_get(&pdev->dev);
-	if (!iommu_spec) {
+	if (!tegra_dev_iommu_get_stream_id(&pdev->dev, &stream_id)) {
 		dev_err(&pdev->dev, "Missing iommu stream-id\n");
 		return -EINVAL;
 	}
-	stream_id = iommu_spec->ids[0] & 0xffff;
 
 	ret = device_property_read_u32(&pdev->dev, "dma-channel-mask",
 				       &tdma->chan_mask);
diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c
index 7a0586633b..24ad7077c5 100644
--- a/drivers/dma/tegra210-adma.c
+++ b/drivers/dma/tegra210-adma.c
@@ -153,6 +153,7 @@ struct tegra_adma {
 	void __iomem			*base_addr;
 	struct clk			*ahub_clk;
 	unsigned int			nr_channels;
+	unsigned long			*dma_chan_mask;
 	unsigned long			rx_requests_reserved;
 	unsigned long			tx_requests_reserved;
 
@@ -741,6 +742,10 @@ static int __maybe_unused tegra_adma_runtime_suspend(struct device *dev)
 
 	for (i = 0; i < tdma->nr_channels; i++) {
 		tdc = &tdma->channels[i];
+		/* skip for reserved channels */
+		if (!tdc->tdma)
+			continue;
+
 		ch_reg = &tdc->ch_regs;
 		ch_reg->cmd = tdma_ch_read(tdc, ADMA_CH_CMD);
 		/* skip if channel is not active */
@@ -779,6 +784,9 @@ static int __maybe_unused tegra_adma_runtime_resume(struct device *dev)
 
 	for (i = 0; i < tdma->nr_channels; i++) {
 		tdc = &tdma->channels[i];
+		/* skip for reserved channels */
+		if (!tdc->tdma)
+			continue;
 		ch_reg = &tdc->ch_regs;
 		/* skip if channel was not active earlier */
 		if (!ch_reg->cmd)
@@ -867,10 +875,31 @@ static int tegra_adma_probe(struct platform_device *pdev)
 		return PTR_ERR(tdma->ahub_clk);
 	}
 
+	tdma->dma_chan_mask = devm_kzalloc(&pdev->dev,
+					   BITS_TO_LONGS(tdma->nr_channels) * sizeof(unsigned long),
+					   GFP_KERNEL);
+	if (!tdma->dma_chan_mask)
+		return -ENOMEM;
+
+	/* Enable all channels by default */
+	bitmap_fill(tdma->dma_chan_mask, tdma->nr_channels);
+
+	ret = of_property_read_u32_array(pdev->dev.of_node, "dma-channel-mask",
+					 (u32 *)tdma->dma_chan_mask,
+					 BITS_TO_U32(tdma->nr_channels));
+	if (ret < 0 && (ret != -EINVAL)) {
+		dev_err(&pdev->dev, "dma-channel-mask is not complete.\n");
+		return ret;
+	}
+
 	INIT_LIST_HEAD(&tdma->dma_dev.channels);
 	for (i = 0; i < tdma->nr_channels; i++) {
 		struct tegra_adma_chan *tdc = &tdma->channels[i];
 
+		/* skip for reserved channels */
+		if (!test_bit(i, tdma->dma_chan_mask))
+			continue;
+
 		tdc->chan_addr = tdma->base_addr + cdata->ch_base_offset
 				 + (cdata->ch_reg_size * i);
 
@@ -957,8 +986,10 @@ static void tegra_adma_remove(struct platform_device *pdev)
 	of_dma_controller_free(pdev->dev.of_node);
 	dma_async_device_unregister(&tdma->dma_dev);
 
-	for (i = 0; i < tdma->nr_channels; ++i)
-		irq_dispose_mapping(tdma->channels[i].irq);
+	for (i = 0; i < tdma->nr_channels; ++i) {
+		if (tdma->channels[i].irq)
+			irq_dispose_mapping(tdma->channels[i].irq);
+	}
 
 	pm_runtime_disable(&pdev->dev);
 }
diff --git a/drivers/dma/ti/Makefile b/drivers/dma/ti/Makefile
index acc950bf60..d376c117ce 100644
--- a/drivers/dma/ti/Makefile
+++ b/drivers/dma/ti/Makefile
@@ -12,6 +12,7 @@ k3-psil-lib-objs := k3-psil.o \
 		    k3-psil-j721s2.o \
 		    k3-psil-am62.o \
 		    k3-psil-am62a.o \
-		    k3-psil-j784s4.o
+		    k3-psil-j784s4.o \
+		    k3-psil-am62p.o
 obj-$(CONFIG_TI_K3_PSIL) += k3-psil-lib.o
 obj-$(CONFIG_TI_DMA_CROSSBAR) += dma-crossbar.o
diff --git a/drivers/dma/ti/k3-psil-am62p.c b/drivers/dma/ti/k3-psil-am62p.c
new file mode 100644
index 0000000000..0f338e16d9
--- /dev/null
+++ b/drivers/dma/ti/k3-psil-am62p.c
@@ -0,0 +1,325 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Copyright (C) 2023 Texas Instruments Incorporated - https://www.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,				\
+		},						\
+	}
+
+#define PSIL_PDMA_MCASP(x)				\
+	{						\
+		.thread_id = x,				\
+		.ep_config = {				\
+			.ep_type = PSIL_EP_PDMA_XY,	\
+			.pdma_acc32 = 1,		\
+			.pdma_burst = 1,		\
+		},					\
+	}
+
+#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 am62p_src_ep_map[] = {
+	/* SAUL */
+	PSIL_SAUL(0x7504, 20, 35, 8, 35, 0),
+	PSIL_SAUL(0x7505, 21, 35, 8, 36, 0),
+	PSIL_SAUL(0x7506, 22, 43, 8, 43, 0),
+	PSIL_SAUL(0x7507, 23, 43, 8, 44, 0),
+	/* PDMA_MAIN0 - SPI0-2 */
+	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),
+	/* PDMA_MAIN1 - UART0-6 */
+	PSIL_PDMA_XY_PKT(0x4400),
+	PSIL_PDMA_XY_PKT(0x4401),
+	PSIL_PDMA_XY_PKT(0x4402),
+	PSIL_PDMA_XY_PKT(0x4403),
+	PSIL_PDMA_XY_PKT(0x4404),
+	PSIL_PDMA_XY_PKT(0x4405),
+	PSIL_PDMA_XY_PKT(0x4406),
+	/* PDMA_MAIN2 - MCASP0-2 */
+	PSIL_PDMA_MCASP(0x4500),
+	PSIL_PDMA_MCASP(0x4501),
+	PSIL_PDMA_MCASP(0x4502),
+	/* CPSW3G */
+	PSIL_ETHERNET(0x4600, 19, 19, 16),
+	/* CSI2RX */
+	PSIL_CSI2RX(0x5000),
+	PSIL_CSI2RX(0x5001),
+	PSIL_CSI2RX(0x5002),
+	PSIL_CSI2RX(0x5003),
+	PSIL_CSI2RX(0x5004),
+	PSIL_CSI2RX(0x5005),
+	PSIL_CSI2RX(0x5006),
+	PSIL_CSI2RX(0x5007),
+	PSIL_CSI2RX(0x5008),
+	PSIL_CSI2RX(0x5009),
+	PSIL_CSI2RX(0x500a),
+	PSIL_CSI2RX(0x500b),
+	PSIL_CSI2RX(0x500c),
+	PSIL_CSI2RX(0x500d),
+	PSIL_CSI2RX(0x500e),
+	PSIL_CSI2RX(0x500f),
+	PSIL_CSI2RX(0x5010),
+	PSIL_CSI2RX(0x5011),
+	PSIL_CSI2RX(0x5012),
+	PSIL_CSI2RX(0x5013),
+	PSIL_CSI2RX(0x5014),
+	PSIL_CSI2RX(0x5015),
+	PSIL_CSI2RX(0x5016),
+	PSIL_CSI2RX(0x5017),
+	PSIL_CSI2RX(0x5018),
+	PSIL_CSI2RX(0x5019),
+	PSIL_CSI2RX(0x501a),
+	PSIL_CSI2RX(0x501b),
+	PSIL_CSI2RX(0x501c),
+	PSIL_CSI2RX(0x501d),
+	PSIL_CSI2RX(0x501e),
+	PSIL_CSI2RX(0x501f),
+	PSIL_CSI2RX(0x5000),
+	PSIL_CSI2RX(0x5001),
+	PSIL_CSI2RX(0x5002),
+	PSIL_CSI2RX(0x5003),
+	PSIL_CSI2RX(0x5004),
+	PSIL_CSI2RX(0x5005),
+	PSIL_CSI2RX(0x5006),
+	PSIL_CSI2RX(0x5007),
+	PSIL_CSI2RX(0x5008),
+	PSIL_CSI2RX(0x5009),
+	PSIL_CSI2RX(0x500a),
+	PSIL_CSI2RX(0x500b),
+	PSIL_CSI2RX(0x500c),
+	PSIL_CSI2RX(0x500d),
+	PSIL_CSI2RX(0x500e),
+	PSIL_CSI2RX(0x500f),
+	PSIL_CSI2RX(0x5010),
+	PSIL_CSI2RX(0x5011),
+	PSIL_CSI2RX(0x5012),
+	PSIL_CSI2RX(0x5013),
+	PSIL_CSI2RX(0x5014),
+	PSIL_CSI2RX(0x5015),
+	PSIL_CSI2RX(0x5016),
+	PSIL_CSI2RX(0x5017),
+	PSIL_CSI2RX(0x5018),
+	PSIL_CSI2RX(0x5019),
+	PSIL_CSI2RX(0x501a),
+	PSIL_CSI2RX(0x501b),
+	PSIL_CSI2RX(0x501c),
+	PSIL_CSI2RX(0x501d),
+	PSIL_CSI2RX(0x501e),
+	PSIL_CSI2RX(0x501f),
+	/* CSIRX 1-3 (only for J722S) */
+	PSIL_CSI2RX(0x5100),
+	PSIL_CSI2RX(0x5101),
+	PSIL_CSI2RX(0x5102),
+	PSIL_CSI2RX(0x5103),
+	PSIL_CSI2RX(0x5104),
+	PSIL_CSI2RX(0x5105),
+	PSIL_CSI2RX(0x5106),
+	PSIL_CSI2RX(0x5107),
+	PSIL_CSI2RX(0x5108),
+	PSIL_CSI2RX(0x5109),
+	PSIL_CSI2RX(0x510a),
+	PSIL_CSI2RX(0x510b),
+	PSIL_CSI2RX(0x510c),
+	PSIL_CSI2RX(0x510d),
+	PSIL_CSI2RX(0x510e),
+	PSIL_CSI2RX(0x510f),
+	PSIL_CSI2RX(0x5110),
+	PSIL_CSI2RX(0x5111),
+	PSIL_CSI2RX(0x5112),
+	PSIL_CSI2RX(0x5113),
+	PSIL_CSI2RX(0x5114),
+	PSIL_CSI2RX(0x5115),
+	PSIL_CSI2RX(0x5116),
+	PSIL_CSI2RX(0x5117),
+	PSIL_CSI2RX(0x5118),
+	PSIL_CSI2RX(0x5119),
+	PSIL_CSI2RX(0x511a),
+	PSIL_CSI2RX(0x511b),
+	PSIL_CSI2RX(0x511c),
+	PSIL_CSI2RX(0x511d),
+	PSIL_CSI2RX(0x511e),
+	PSIL_CSI2RX(0x511f),
+	PSIL_CSI2RX(0x5200),
+	PSIL_CSI2RX(0x5201),
+	PSIL_CSI2RX(0x5202),
+	PSIL_CSI2RX(0x5203),
+	PSIL_CSI2RX(0x5204),
+	PSIL_CSI2RX(0x5205),
+	PSIL_CSI2RX(0x5206),
+	PSIL_CSI2RX(0x5207),
+	PSIL_CSI2RX(0x5208),
+	PSIL_CSI2RX(0x5209),
+	PSIL_CSI2RX(0x520a),
+	PSIL_CSI2RX(0x520b),
+	PSIL_CSI2RX(0x520c),
+	PSIL_CSI2RX(0x520d),
+	PSIL_CSI2RX(0x520e),
+	PSIL_CSI2RX(0x520f),
+	PSIL_CSI2RX(0x5210),
+	PSIL_CSI2RX(0x5211),
+	PSIL_CSI2RX(0x5212),
+	PSIL_CSI2RX(0x5213),
+	PSIL_CSI2RX(0x5214),
+	PSIL_CSI2RX(0x5215),
+	PSIL_CSI2RX(0x5216),
+	PSIL_CSI2RX(0x5217),
+	PSIL_CSI2RX(0x5218),
+	PSIL_CSI2RX(0x5219),
+	PSIL_CSI2RX(0x521a),
+	PSIL_CSI2RX(0x521b),
+	PSIL_CSI2RX(0x521c),
+	PSIL_CSI2RX(0x521d),
+	PSIL_CSI2RX(0x521e),
+	PSIL_CSI2RX(0x521f),
+	PSIL_CSI2RX(0x5300),
+	PSIL_CSI2RX(0x5301),
+	PSIL_CSI2RX(0x5302),
+	PSIL_CSI2RX(0x5303),
+	PSIL_CSI2RX(0x5304),
+	PSIL_CSI2RX(0x5305),
+	PSIL_CSI2RX(0x5306),
+	PSIL_CSI2RX(0x5307),
+	PSIL_CSI2RX(0x5308),
+	PSIL_CSI2RX(0x5309),
+	PSIL_CSI2RX(0x530a),
+	PSIL_CSI2RX(0x530b),
+	PSIL_CSI2RX(0x530c),
+	PSIL_CSI2RX(0x530d),
+	PSIL_CSI2RX(0x530e),
+	PSIL_CSI2RX(0x530f),
+	PSIL_CSI2RX(0x5310),
+	PSIL_CSI2RX(0x5311),
+	PSIL_CSI2RX(0x5312),
+	PSIL_CSI2RX(0x5313),
+	PSIL_CSI2RX(0x5314),
+	PSIL_CSI2RX(0x5315),
+	PSIL_CSI2RX(0x5316),
+	PSIL_CSI2RX(0x5317),
+	PSIL_CSI2RX(0x5318),
+	PSIL_CSI2RX(0x5319),
+	PSIL_CSI2RX(0x531a),
+	PSIL_CSI2RX(0x531b),
+	PSIL_CSI2RX(0x531c),
+	PSIL_CSI2RX(0x531d),
+	PSIL_CSI2RX(0x531e),
+	PSIL_CSI2RX(0x531f),
+};
+
+/* PSI-L destination thread IDs, used for TX (DMA_MEM_TO_DEV) */
+static struct psil_ep am62p_dst_ep_map[] = {
+	/* SAUL */
+	PSIL_SAUL(0xf500, 27, 83, 8, 83, 1),
+	PSIL_SAUL(0xf501, 28, 91, 8, 91, 1),
+	/* PDMA_MAIN0 - SPI0-2 */
+	PSIL_PDMA_XY_PKT(0xc300),
+	PSIL_PDMA_XY_PKT(0xc301),
+	PSIL_PDMA_XY_PKT(0xc302),
+	PSIL_PDMA_XY_PKT(0xc303),
+	PSIL_PDMA_XY_PKT(0xc304),
+	PSIL_PDMA_XY_PKT(0xc305),
+	PSIL_PDMA_XY_PKT(0xc306),
+	PSIL_PDMA_XY_PKT(0xc307),
+	PSIL_PDMA_XY_PKT(0xc308),
+	PSIL_PDMA_XY_PKT(0xc309),
+	PSIL_PDMA_XY_PKT(0xc30a),
+	PSIL_PDMA_XY_PKT(0xc30b),
+	/* PDMA_MAIN1 - UART0-6 */
+	PSIL_PDMA_XY_PKT(0xc400),
+	PSIL_PDMA_XY_PKT(0xc401),
+	PSIL_PDMA_XY_PKT(0xc402),
+	PSIL_PDMA_XY_PKT(0xc403),
+	PSIL_PDMA_XY_PKT(0xc404),
+	PSIL_PDMA_XY_PKT(0xc405),
+	PSIL_PDMA_XY_PKT(0xc406),
+	/* PDMA_MAIN2 - MCASP0-2 */
+	PSIL_PDMA_MCASP(0xc500),
+	PSIL_PDMA_MCASP(0xc501),
+	PSIL_PDMA_MCASP(0xc502),
+	/* CPSW3G */
+	PSIL_ETHERNET(0xc600, 19, 19, 8),
+	PSIL_ETHERNET(0xc601, 20, 27, 8),
+	PSIL_ETHERNET(0xc602, 21, 35, 8),
+	PSIL_ETHERNET(0xc603, 22, 43, 8),
+	PSIL_ETHERNET(0xc604, 23, 51, 8),
+	PSIL_ETHERNET(0xc605, 24, 59, 8),
+	PSIL_ETHERNET(0xc606, 25, 67, 8),
+	PSIL_ETHERNET(0xc607, 26, 75, 8),
+};
+
+struct psil_ep_map am62p_ep_map = {
+	.name = "am62p",
+	.src = am62p_src_ep_map,
+	.src_count = ARRAY_SIZE(am62p_src_ep_map),
+	.dst = am62p_dst_ep_map,
+	.dst_count = ARRAY_SIZE(am62p_dst_ep_map),
+};
diff --git a/drivers/dma/ti/k3-psil-priv.h b/drivers/dma/ti/k3-psil-priv.h
index c383723d1c..a577be97e3 100644
--- a/drivers/dma/ti/k3-psil-priv.h
+++ b/drivers/dma/ti/k3-psil-priv.h
@@ -45,5 +45,6 @@ extern struct psil_ep_map j721s2_ep_map;
 extern struct psil_ep_map am62_ep_map;
 extern struct psil_ep_map am62a_ep_map;
 extern struct psil_ep_map j784s4_ep_map;
+extern struct psil_ep_map am62p_ep_map;
 
 #endif /* K3_PSIL_PRIV_H_ */
diff --git a/drivers/dma/ti/k3-psil.c b/drivers/dma/ti/k3-psil.c
index c11389d67a..25148d9524 100644
--- a/drivers/dma/ti/k3-psil.c
+++ b/drivers/dma/ti/k3-psil.c
@@ -26,6 +26,8 @@ static const struct soc_device_attribute k3_soc_devices[] = {
 	{ .family = "AM62X", .data = &am62_ep_map },
 	{ .family = "AM62AX", .data = &am62a_ep_map },
 	{ .family = "J784S4", .data = &j784s4_ep_map },
+	{ .family = "AM62PX", .data = &am62p_ep_map },
+	{ .family = "J722S", .data = &am62p_ep_map },
 	{ /* sentinel */ }
 };
 
diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c
index 037f1408e7..6400d06588 100644
--- a/drivers/dma/ti/k3-udma.c
+++ b/drivers/dma/ti/k3-udma.c
@@ -4447,6 +4447,8 @@ static const struct soc_device_attribute k3_soc_devices[] = {
 	{ .family = "AM62X", .data = &am64_soc_data },
 	{ .family = "AM62AX", .data = &am64_soc_data },
 	{ .family = "J784S4", .data = &j721e_soc_data },
+	{ .family = "AM62PX", .data = &am64_soc_data },
+	{ .family = "J722S", .data = &am64_soc_data },
 	{ /* sentinel */ }
 };
 
diff --git a/drivers/dma/uniphier-mdmac.c b/drivers/dma/uniphier-mdmac.c
index 618839df07..ad7125f6e2 100644
--- a/drivers/dma/uniphier-mdmac.c
+++ b/drivers/dma/uniphier-mdmac.c
@@ -453,7 +453,7 @@ disable_clk:
 	return ret;
 }
 
-static int uniphier_mdmac_remove(struct platform_device *pdev)
+static void uniphier_mdmac_remove(struct platform_device *pdev)
 {
 	struct uniphier_mdmac_device *mdev = platform_get_drvdata(pdev);
 	struct dma_chan *chan;
@@ -468,16 +468,21 @@ static int uniphier_mdmac_remove(struct platform_device *pdev)
 	 */
 	list_for_each_entry(chan, &mdev->ddev.channels, device_node) {
 		ret = dmaengine_terminate_sync(chan);
-		if (ret)
-			return ret;
+		if (ret) {
+			/*
+			 * This results in resource leakage and maybe also
+			 * use-after-free errors as e.g. *mdev is kfreed.
+			 */
+			dev_alert(&pdev->dev, "Failed to terminate channel %d (%pe)\n",
+				  chan->chan_id, ERR_PTR(ret));
+			return;
+		}
 		uniphier_mdmac_free_chan_resources(chan);
 	}
 
 	of_dma_controller_free(pdev->dev.of_node);
 	dma_async_device_unregister(&mdev->ddev);
 	clk_disable_unprepare(mdev->clk);
-
-	return 0;
 }
 
 static const struct of_device_id uniphier_mdmac_match[] = {
@@ -488,7 +493,7 @@ MODULE_DEVICE_TABLE(of, uniphier_mdmac_match);
 
 static struct platform_driver uniphier_mdmac_driver = {
 	.probe = uniphier_mdmac_probe,
-	.remove = uniphier_mdmac_remove,
+	.remove_new = uniphier_mdmac_remove,
 	.driver = {
 		.name = "uniphier-mio-dmac",
 		.of_match_table = uniphier_mdmac_match,
diff --git a/drivers/dma/uniphier-xdmac.c b/drivers/dma/uniphier-xdmac.c
index 3a8ee2b173..3ce2dc2ad9 100644
--- a/drivers/dma/uniphier-xdmac.c
+++ b/drivers/dma/uniphier-xdmac.c
@@ -563,7 +563,7 @@ out_unregister_dmac:
 	return ret;
 }
 
-static int uniphier_xdmac_remove(struct platform_device *pdev)
+static void uniphier_xdmac_remove(struct platform_device *pdev)
 {
 	struct uniphier_xdmac_device *xdev = platform_get_drvdata(pdev);
 	struct dma_device *ddev = &xdev->ddev;
@@ -579,15 +579,20 @@ static int uniphier_xdmac_remove(struct platform_device *pdev)
 	 */
 	list_for_each_entry(chan, &ddev->channels, device_node) {
 		ret = dmaengine_terminate_sync(chan);
-		if (ret)
-			return ret;
+		if (ret) {
+			/*
+			 * This results in resource leakage and maybe also
+			 * use-after-free errors as e.g. *xdev is kfreed.
+			 */
+			dev_alert(&pdev->dev, "Failed to terminate channel %d (%pe)\n",
+				  chan->chan_id, ERR_PTR(ret));
+			return;
+		}
 		uniphier_xdmac_free_chan_resources(chan);
 	}
 
 	of_dma_controller_free(pdev->dev.of_node);
 	dma_async_device_unregister(ddev);
-
-	return 0;
 }
 
 static const struct of_device_id uniphier_xdmac_match[] = {
@@ -598,7 +603,7 @@ MODULE_DEVICE_TABLE(of, uniphier_xdmac_match);
 
 static struct platform_driver uniphier_xdmac_driver = {
 	.probe = uniphier_xdmac_probe,
-	.remove = uniphier_xdmac_remove,
+	.remove_new = uniphier_xdmac_remove,
 	.driver = {
 		.name = "uniphier-xdmac",
 		.of_match_table = uniphier_xdmac_match,
diff --git a/drivers/dma/xilinx/xdma-regs.h b/drivers/dma/xilinx/xdma-regs.h
index e641a5083e..6ad08878e9 100644
--- a/drivers/dma/xilinx/xdma-regs.h
+++ b/drivers/dma/xilinx/xdma-regs.h
@@ -64,9 +64,10 @@ struct xdma_hw_desc {
 	__le64		next_desc;
 };
 
-#define XDMA_DESC_SIZE		sizeof(struct xdma_hw_desc)
-#define XDMA_DESC_BLOCK_SIZE	(XDMA_DESC_SIZE * XDMA_DESC_ADJACENT)
-#define XDMA_DESC_BLOCK_ALIGN	4096
+#define XDMA_DESC_SIZE			sizeof(struct xdma_hw_desc)
+#define XDMA_DESC_BLOCK_SIZE		(XDMA_DESC_SIZE * XDMA_DESC_ADJACENT)
+#define XDMA_DESC_BLOCK_ALIGN		32
+#define XDMA_DESC_BLOCK_BOUNDARY	4096
 
 /*
  * Channel registers
@@ -76,6 +77,7 @@ struct xdma_hw_desc {
 #define XDMA_CHAN_CONTROL_W1S		0x8
 #define XDMA_CHAN_CONTROL_W1C		0xc
 #define XDMA_CHAN_STATUS		0x40
+#define XDMA_CHAN_STATUS_RC		0x44
 #define XDMA_CHAN_COMPLETED_DESC	0x48
 #define XDMA_CHAN_ALIGNMENTS		0x4c
 #define XDMA_CHAN_INTR_ENABLE		0x90
@@ -101,6 +103,7 @@ struct xdma_hw_desc {
 #define CHAN_CTRL_IE_MAGIC_STOPPED		BIT(4)
 #define CHAN_CTRL_IE_IDLE_STOPPED		BIT(6)
 #define CHAN_CTRL_IE_READ_ERROR			GENMASK(13, 9)
+#define CHAN_CTRL_IE_WRITE_ERROR		GENMASK(18, 14)
 #define CHAN_CTRL_IE_DESC_ERROR			GENMASK(23, 19)
 #define CHAN_CTRL_NON_INCR_ADDR			BIT(25)
 #define CHAN_CTRL_POLL_MODE_WB			BIT(26)
@@ -111,8 +114,20 @@ struct xdma_hw_desc {
 			 CHAN_CTRL_IE_DESC_ALIGN_MISMATCH |		\
 			 CHAN_CTRL_IE_MAGIC_STOPPED |			\
 			 CHAN_CTRL_IE_READ_ERROR |			\
+			 CHAN_CTRL_IE_WRITE_ERROR |			\
 			 CHAN_CTRL_IE_DESC_ERROR)
 
+/* bits of the channel status register */
+#define XDMA_CHAN_STATUS_BUSY			BIT(0)
+
+#define XDMA_CHAN_STATUS_MASK CHAN_CTRL_START
+
+#define XDMA_CHAN_ERROR_MASK (CHAN_CTRL_IE_DESC_ALIGN_MISMATCH |	\
+			      CHAN_CTRL_IE_MAGIC_STOPPED |		\
+			      CHAN_CTRL_IE_READ_ERROR |			\
+			      CHAN_CTRL_IE_WRITE_ERROR |		\
+			      CHAN_CTRL_IE_DESC_ERROR)
+
 /* bits of the channel interrupt enable mask */
 #define CHAN_IM_DESC_ERROR			BIT(19)
 #define CHAN_IM_READ_ERROR			BIT(9)
@@ -134,18 +149,6 @@ struct xdma_hw_desc {
 #define XDMA_SGDMA_DESC_ADJ	0x4088
 #define XDMA_SGDMA_DESC_CREDIT	0x408c
 
-/* bits of the SG DMA control register */
-#define XDMA_CTRL_RUN_STOP			BIT(0)
-#define XDMA_CTRL_IE_DESC_STOPPED		BIT(1)
-#define XDMA_CTRL_IE_DESC_COMPLETED		BIT(2)
-#define XDMA_CTRL_IE_DESC_ALIGN_MISMATCH	BIT(3)
-#define XDMA_CTRL_IE_MAGIC_STOPPED		BIT(4)
-#define XDMA_CTRL_IE_IDLE_STOPPED		BIT(6)
-#define XDMA_CTRL_IE_READ_ERROR			GENMASK(13, 9)
-#define XDMA_CTRL_IE_DESC_ERROR			GENMASK(23, 19)
-#define XDMA_CTRL_NON_INCR_ADDR			BIT(25)
-#define XDMA_CTRL_POLL_MODE_WB			BIT(26)
-
 /*
  * interrupt registers
  */
diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c
index 2c9c72d4b5..5a3a3293b2 100644
--- a/drivers/dma/xilinx/xdma.c
+++ b/drivers/dma/xilinx/xdma.c
@@ -71,6 +71,8 @@ struct xdma_chan {
 	enum dma_transfer_direction	dir;
 	struct dma_slave_config		cfg;
 	u32				irq;
+	struct completion		last_interrupt;
+	bool				stop_requested;
 };
 
 /**
@@ -78,27 +80,31 @@ struct xdma_chan {
  * @vdesc: Virtual DMA descriptor
  * @chan: DMA channel pointer
  * @dir: Transferring direction of the request
- * @dev_addr: Physical address on DMA device side
  * @desc_blocks: Hardware descriptor blocks
  * @dblk_num: Number of hardware descriptor blocks
  * @desc_num: Number of hardware descriptors
  * @completed_desc_num: Completed hardware descriptors
  * @cyclic: Cyclic transfer vs. scatter-gather
+ * @interleaved_dma: Interleaved DMA transfer
  * @periods: Number of periods in the cyclic transfer
  * @period_size: Size of a period in bytes in cyclic transfers
+ * @frames_left: Number of frames left in interleaved DMA transfer
+ * @error: tx error flag
  */
 struct xdma_desc {
 	struct virt_dma_desc		vdesc;
 	struct xdma_chan		*chan;
 	enum dma_transfer_direction	dir;
-	u64				dev_addr;
 	struct xdma_desc_block		*desc_blocks;
 	u32				dblk_num;
 	u32				desc_num;
 	u32				completed_desc_num;
 	bool				cyclic;
+	bool				interleaved_dma;
 	u32				periods;
 	u32				period_size;
+	u32				frames_left;
+	bool				error;
 };
 
 #define XDMA_DEV_STATUS_REG_DMA		BIT(0)
@@ -276,6 +282,7 @@ xdma_alloc_desc(struct xdma_chan *chan, u32 desc_num, bool cyclic)
 	sw_desc->chan = chan;
 	sw_desc->desc_num = desc_num;
 	sw_desc->cyclic = cyclic;
+	sw_desc->error = false;
 	dblk_num = DIV_ROUND_UP(desc_num, XDMA_DESC_ADJACENT);
 	sw_desc->desc_blocks = kcalloc(dblk_num, sizeof(*sw_desc->desc_blocks),
 				       GFP_NOWAIT);
@@ -371,10 +378,30 @@ static int xdma_xfer_start(struct xdma_chan *xchan)
 		return ret;
 
 	xchan->busy = true;
+	xchan->stop_requested = false;
+	reinit_completion(&xchan->last_interrupt);
+
 	return 0;
 }
 
 /**
+ * xdma_xfer_stop - Stop DMA transfer
+ * @xchan: DMA channel pointer
+ */
+static int xdma_xfer_stop(struct xdma_chan *xchan)
+{
+	int ret;
+	struct xdma_device *xdev = xchan->xdev_hdl;
+
+	/* clear run stop bit to prevent any further auto-triggering */
+	ret = regmap_write(xdev->rmap, xchan->base + XDMA_CHAN_CONTROL_W1C,
+			   CHAN_CTRL_RUN_STOP);
+	if (ret)
+		return ret;
+	return ret;
+}
+
+/**
  * xdma_alloc_channels - Detect and allocate DMA channels
  * @xdev: DMA device pointer
  * @dir: Channel direction
@@ -444,6 +471,8 @@ static int xdma_alloc_channels(struct xdma_device *xdev,
 		xchan->xdev_hdl = xdev;
 		xchan->base = base + i * XDMA_CHAN_STRIDE;
 		xchan->dir = dir;
+		xchan->stop_requested = false;
+		init_completion(&xchan->last_interrupt);
 
 		ret = xdma_channel_init(xchan);
 		if (ret)
@@ -476,6 +505,92 @@ static void xdma_issue_pending(struct dma_chan *chan)
 }
 
 /**
+ * xdma_terminate_all - Terminate all transactions
+ * @chan: DMA channel pointer
+ */
+static int xdma_terminate_all(struct dma_chan *chan)
+{
+	struct xdma_chan *xdma_chan = to_xdma_chan(chan);
+	struct virt_dma_desc *vd;
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	xdma_xfer_stop(xdma_chan);
+
+	spin_lock_irqsave(&xdma_chan->vchan.lock, flags);
+
+	xdma_chan->busy = false;
+	xdma_chan->stop_requested = true;
+	vd = vchan_next_desc(&xdma_chan->vchan);
+	if (vd) {
+		list_del(&vd->node);
+		dma_cookie_complete(&vd->tx);
+		vchan_terminate_vdesc(vd);
+	}
+	vchan_get_all_descriptors(&xdma_chan->vchan, &head);
+	list_splice_tail(&head, &xdma_chan->vchan.desc_terminated);
+
+	spin_unlock_irqrestore(&xdma_chan->vchan.lock, flags);
+
+	return 0;
+}
+
+/**
+ * xdma_synchronize - Synchronize terminated transactions
+ * @chan: DMA channel pointer
+ */
+static void xdma_synchronize(struct dma_chan *chan)
+{
+	struct xdma_chan *xdma_chan = to_xdma_chan(chan);
+	struct xdma_device *xdev = xdma_chan->xdev_hdl;
+	int st = 0;
+
+	/* If the engine continues running, wait for the last interrupt */
+	regmap_read(xdev->rmap, xdma_chan->base + XDMA_CHAN_STATUS, &st);
+	if (st & XDMA_CHAN_STATUS_BUSY)
+		wait_for_completion_timeout(&xdma_chan->last_interrupt, msecs_to_jiffies(1000));
+
+	vchan_synchronize(&xdma_chan->vchan);
+}
+
+/**
+ * xdma_fill_descs - Fill hardware descriptors with contiguous memory block addresses
+ * @sw_desc: tx descriptor state container
+ * @src_addr: Value for a ->src_addr field of a first descriptor
+ * @dst_addr: Value for a ->dst_addr field of a first descriptor
+ * @size: Total size of a contiguous memory block
+ * @filled_descs_num: Number of filled hardware descriptors for corresponding sw_desc
+ */
+static inline u32 xdma_fill_descs(struct xdma_desc *sw_desc, u64 src_addr,
+				  u64 dst_addr, u32 size, u32 filled_descs_num)
+{
+	u32 left = size, len, desc_num = filled_descs_num;
+	struct xdma_desc_block *dblk;
+	struct xdma_hw_desc *desc;
+
+	dblk = sw_desc->desc_blocks + (desc_num / XDMA_DESC_ADJACENT);
+	desc = dblk->virt_addr;
+	desc += desc_num & XDMA_DESC_ADJACENT_MASK;
+	do {
+		len = min_t(u32, left, XDMA_DESC_BLEN_MAX);
+		/* set hardware descriptor */
+		desc->bytes = cpu_to_le32(len);
+		desc->src_addr = cpu_to_le64(src_addr);
+		desc->dst_addr = cpu_to_le64(dst_addr);
+		if (!(++desc_num & XDMA_DESC_ADJACENT_MASK))
+			desc = (++dblk)->virt_addr;
+		else
+			desc++;
+
+		src_addr += len;
+		dst_addr += len;
+		left -= len;
+	} while (left);
+
+	return desc_num - filled_descs_num;
+}
+
+/**
  * xdma_prep_device_sg - prepare a descriptor for a DMA transaction
  * @chan: DMA channel pointer
  * @sgl: Transfer scatter gather list
@@ -491,13 +606,10 @@ xdma_prep_device_sg(struct dma_chan *chan, struct scatterlist *sgl,
 {
 	struct xdma_chan *xdma_chan = to_xdma_chan(chan);
 	struct dma_async_tx_descriptor *tx_desc;
-	u32 desc_num = 0, i, len, rest;
-	struct xdma_desc_block *dblk;
-	struct xdma_hw_desc *desc;
 	struct xdma_desc *sw_desc;
-	u64 dev_addr, *src, *dst;
+	u32 desc_num = 0, i;
+	u64 addr, dev_addr, *src, *dst;
 	struct scatterlist *sg;
-	u64 addr;
 
 	for_each_sg(sgl, sg, sg_len, i)
 		desc_num += DIV_ROUND_UP(sg_dma_len(sg), XDMA_DESC_BLEN_MAX);
@@ -506,6 +618,8 @@ xdma_prep_device_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	if (!sw_desc)
 		return NULL;
 	sw_desc->dir = dir;
+	sw_desc->cyclic = false;
+	sw_desc->interleaved_dma = false;
 
 	if (dir == DMA_MEM_TO_DEV) {
 		dev_addr = xdma_chan->cfg.dst_addr;
@@ -517,32 +631,11 @@ xdma_prep_device_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		dst = &addr;
 	}
 
-	dblk = sw_desc->desc_blocks;
-	desc = dblk->virt_addr;
-	desc_num = 1;
+	desc_num = 0;
 	for_each_sg(sgl, sg, sg_len, i) {
 		addr = sg_dma_address(sg);
-		rest = sg_dma_len(sg);
-
-		do {
-			len = min_t(u32, rest, XDMA_DESC_BLEN_MAX);
-			/* set hardware descriptor */
-			desc->bytes = cpu_to_le32(len);
-			desc->src_addr = cpu_to_le64(*src);
-			desc->dst_addr = cpu_to_le64(*dst);
-
-			if (!(desc_num & XDMA_DESC_ADJACENT_MASK)) {
-				dblk++;
-				desc = dblk->virt_addr;
-			} else {
-				desc++;
-			}
-
-			desc_num++;
-			dev_addr += len;
-			addr += len;
-			rest -= len;
-		} while (rest);
+		desc_num += xdma_fill_descs(sw_desc, *src, *dst, sg_dma_len(sg), desc_num);
+		dev_addr += sg_dma_len(sg);
 	}
 
 	tx_desc = vchan_tx_prep(&xdma_chan->vchan, &sw_desc->vdesc, flags);
@@ -576,9 +669,9 @@ xdma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t address,
 	struct xdma_device *xdev = xdma_chan->xdev_hdl;
 	unsigned int periods = size / period_size;
 	struct dma_async_tx_descriptor *tx_desc;
-	struct xdma_desc_block *dblk;
-	struct xdma_hw_desc *desc;
 	struct xdma_desc *sw_desc;
+	u64 addr, dev_addr, *src, *dst;
+	u32 desc_num;
 	unsigned int i;
 
 	/*
@@ -602,22 +695,23 @@ xdma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t address,
 	sw_desc->periods = periods;
 	sw_desc->period_size = period_size;
 	sw_desc->dir = dir;
+	sw_desc->interleaved_dma = false;
 
-	dblk = sw_desc->desc_blocks;
-	desc = dblk->virt_addr;
+	addr = address;
+	if (dir == DMA_MEM_TO_DEV) {
+		dev_addr = xdma_chan->cfg.dst_addr;
+		src = &addr;
+		dst = &dev_addr;
+	} else {
+		dev_addr = xdma_chan->cfg.src_addr;
+		src = &dev_addr;
+		dst = &addr;
+	}
 
-	/* fill hardware descriptor */
+	desc_num = 0;
 	for (i = 0; i < periods; i++) {
-		desc->bytes = cpu_to_le32(period_size);
-		if (dir == DMA_MEM_TO_DEV) {
-			desc->src_addr = cpu_to_le64(address + i * period_size);
-			desc->dst_addr = cpu_to_le64(xdma_chan->cfg.dst_addr);
-		} else {
-			desc->src_addr = cpu_to_le64(xdma_chan->cfg.src_addr);
-			desc->dst_addr = cpu_to_le64(address + i * period_size);
-		}
-
-		desc++;
+		desc_num += xdma_fill_descs(sw_desc, *src, *dst, period_size, desc_num);
+		addr += period_size;
 	}
 
 	tx_desc = vchan_tx_prep(&xdma_chan->vchan, &sw_desc->vdesc, flags);
@@ -633,6 +727,57 @@ failed:
 }
 
 /**
+ * xdma_prep_interleaved_dma - Prepare virtual descriptor for interleaved DMA transfers
+ * @chan: DMA channel
+ * @xt: DMA transfer template
+ * @flags: tx flags
+ */
+static struct dma_async_tx_descriptor *
+xdma_prep_interleaved_dma(struct dma_chan *chan,
+			  struct dma_interleaved_template *xt,
+			  unsigned long flags)
+{
+	int i;
+	u32 desc_num = 0, period_size = 0;
+	struct dma_async_tx_descriptor *tx_desc;
+	struct xdma_chan *xchan = to_xdma_chan(chan);
+	struct xdma_desc *sw_desc;
+	u64 src_addr, dst_addr;
+
+	for (i = 0; i < xt->frame_size; ++i)
+		desc_num += DIV_ROUND_UP(xt->sgl[i].size, XDMA_DESC_BLEN_MAX);
+
+	sw_desc = xdma_alloc_desc(xchan, desc_num, false);
+	if (!sw_desc)
+		return NULL;
+	sw_desc->dir = xt->dir;
+	sw_desc->interleaved_dma = true;
+	sw_desc->cyclic = flags & DMA_PREP_REPEAT;
+	sw_desc->frames_left = xt->numf;
+	sw_desc->periods = xt->numf;
+
+	desc_num = 0;
+	src_addr = xt->src_start;
+	dst_addr = xt->dst_start;
+	for (i = 0; i < xt->frame_size; ++i) {
+		desc_num += xdma_fill_descs(sw_desc, src_addr, dst_addr, xt->sgl[i].size, desc_num);
+		src_addr += dmaengine_get_src_icg(xt, &xt->sgl[i]) + (xt->src_inc ?
+							      xt->sgl[i].size : 0);
+		dst_addr += dmaengine_get_dst_icg(xt, &xt->sgl[i]) + (xt->dst_inc ?
+							      xt->sgl[i].size : 0);
+		period_size += xt->sgl[i].size;
+	}
+	sw_desc->period_size = period_size;
+
+	tx_desc = vchan_tx_prep(&xchan->vchan, &sw_desc->vdesc, flags);
+	if (tx_desc)
+		return tx_desc;
+
+	xdma_free_desc(&sw_desc->vdesc);
+	return NULL;
+}
+
+/**
  * xdma_device_config - Configure the DMA channel
  * @chan: DMA channel
  * @cfg: channel configuration
@@ -677,9 +822,8 @@ static int xdma_alloc_chan_resources(struct dma_chan *chan)
 		return -EINVAL;
 	}
 
-	xdma_chan->desc_pool = dma_pool_create(dma_chan_name(chan),
-					       dev, XDMA_DESC_BLOCK_SIZE,
-					       XDMA_DESC_BLOCK_ALIGN, 0);
+	xdma_chan->desc_pool = dma_pool_create(dma_chan_name(chan), dev, XDMA_DESC_BLOCK_SIZE,
+					       XDMA_DESC_BLOCK_ALIGN, XDMA_DESC_BLOCK_BOUNDARY);
 	if (!xdma_chan->desc_pool) {
 		xdma_err(xdev, "unable to allocate descriptor pool");
 		return -ENOMEM;
@@ -706,20 +850,20 @@ static enum dma_status xdma_tx_status(struct dma_chan *chan, dma_cookie_t cookie
 	spin_lock_irqsave(&xdma_chan->vchan.lock, flags);
 
 	vd = vchan_find_desc(&xdma_chan->vchan, cookie);
-	if (vd)
-		desc = to_xdma_desc(vd);
-	if (!desc || !desc->cyclic) {
-		spin_unlock_irqrestore(&xdma_chan->vchan.lock, flags);
-		return ret;
-	}
-
-	period_idx = desc->completed_desc_num % desc->periods;
-	residue = (desc->periods - period_idx) * desc->period_size;
+	if (!vd)
+		goto out;
 
+	desc = to_xdma_desc(vd);
+	if (desc->error) {
+		ret = DMA_ERROR;
+	} else if (desc->cyclic) {
+		period_idx = desc->completed_desc_num % desc->periods;
+		residue = (desc->periods - period_idx) * desc->period_size;
+		dma_set_residue(state, residue);
+	}
+out:
 	spin_unlock_irqrestore(&xdma_chan->vchan.lock, flags);
 
-	dma_set_residue(state, residue);
-
 	return ret;
 }
 
@@ -732,11 +876,15 @@ static irqreturn_t xdma_channel_isr(int irq, void *dev_id)
 {
 	struct xdma_chan *xchan = dev_id;
 	u32 complete_desc_num = 0;
-	struct xdma_device *xdev;
-	struct virt_dma_desc *vd;
+	struct xdma_device *xdev = xchan->xdev_hdl;
+	struct virt_dma_desc *vd, *next_vd;
 	struct xdma_desc *desc;
 	int ret;
 	u32 st;
+	bool repeat_tx;
+
+	if (xchan->stop_requested)
+		complete(&xchan->last_interrupt);
 
 	spin_lock(&xchan->vchan.lock);
 
@@ -745,47 +893,76 @@ static irqreturn_t xdma_channel_isr(int irq, void *dev_id)
 	if (!vd)
 		goto out;
 
-	xchan->busy = false;
+	/* Clear-on-read the status register */
+	ret = regmap_read(xdev->rmap, xchan->base + XDMA_CHAN_STATUS_RC, &st);
+	if (ret)
+		goto out;
+
 	desc = to_xdma_desc(vd);
-	xdev = xchan->xdev_hdl;
+
+	st &= XDMA_CHAN_STATUS_MASK;
+	if ((st & XDMA_CHAN_ERROR_MASK) ||
+	    !(st & (CHAN_CTRL_IE_DESC_COMPLETED | CHAN_CTRL_IE_DESC_STOPPED))) {
+		desc->error = true;
+		xdma_err(xdev, "channel error, status register value: 0x%x", st);
+		goto out;
+	}
 
 	ret = regmap_read(xdev->rmap, xchan->base + XDMA_CHAN_COMPLETED_DESC,
 			  &complete_desc_num);
 	if (ret)
 		goto out;
 
-	if (desc->cyclic) {
-		desc->completed_desc_num = complete_desc_num;
-
-		ret = regmap_read(xdev->rmap, xchan->base + XDMA_CHAN_STATUS,
-				  &st);
-		if (ret)
+	if (desc->interleaved_dma) {
+		xchan->busy = false;
+		desc->completed_desc_num += complete_desc_num;
+		if (complete_desc_num == XDMA_DESC_BLOCK_NUM * XDMA_DESC_ADJACENT) {
+			xdma_xfer_start(xchan);
 			goto out;
+		}
 
-		regmap_write(xdev->rmap, xchan->base + XDMA_CHAN_STATUS, st);
+		/* last desc of any frame */
+		desc->frames_left--;
+		if (desc->frames_left)
+			goto out;
 
-		vchan_cyclic_callback(vd);
-		goto out;
-	}
+		/* last desc of the last frame  */
+		repeat_tx = vd->tx.flags & DMA_PREP_REPEAT;
+		next_vd = list_first_entry_or_null(&vd->node, struct virt_dma_desc, node);
+		if (next_vd)
+			repeat_tx = repeat_tx && !(next_vd->tx.flags & DMA_PREP_LOAD_EOT);
+		if (repeat_tx) {
+			desc->frames_left = desc->periods;
+			desc->completed_desc_num = 0;
+			vchan_cyclic_callback(vd);
+		} else {
+			list_del(&vd->node);
+			vchan_cookie_complete(vd);
+		}
+		/* start (or continue) the tx of a first desc on the vc.desc_issued list, if any */
+		xdma_xfer_start(xchan);
+	} else if (!desc->cyclic) {
+		xchan->busy = false;
+		desc->completed_desc_num += complete_desc_num;
+
+		/* if all data blocks are transferred, remove and complete the request */
+		if (desc->completed_desc_num == desc->desc_num) {
+			list_del(&vd->node);
+			vchan_cookie_complete(vd);
+			goto out;
+		}
 
-	desc->completed_desc_num += complete_desc_num;
+		if (desc->completed_desc_num > desc->desc_num ||
+		    complete_desc_num != XDMA_DESC_BLOCK_NUM * XDMA_DESC_ADJACENT)
+			goto out;
 
-	/*
-	 * if all data blocks are transferred, remove and complete the request
-	 */
-	if (desc->completed_desc_num == desc->desc_num) {
-		list_del(&vd->node);
-		vchan_cookie_complete(vd);
-		goto out;
+		/* transfer the rest of data */
+		xdma_xfer_start(xchan);
+	} else {
+		desc->completed_desc_num = complete_desc_num;
+		vchan_cyclic_callback(vd);
 	}
 
-	if (desc->completed_desc_num > desc->desc_num ||
-	    complete_desc_num != XDMA_DESC_BLOCK_NUM * XDMA_DESC_ADJACENT)
-		goto out;
-
-	/* transfer the rest of data (SG only) */
-	xdma_xfer_start(xchan);
-
 out:
 	spin_unlock(&xchan->vchan.lock);
 	return IRQ_HANDLED;
@@ -1082,6 +1259,9 @@ static int xdma_probe(struct platform_device *pdev)
 	dma_cap_set(DMA_SLAVE, xdev->dma_dev.cap_mask);
 	dma_cap_set(DMA_PRIVATE, xdev->dma_dev.cap_mask);
 	dma_cap_set(DMA_CYCLIC, xdev->dma_dev.cap_mask);
+	dma_cap_set(DMA_INTERLEAVE, xdev->dma_dev.cap_mask);
+	dma_cap_set(DMA_REPEAT, xdev->dma_dev.cap_mask);
+	dma_cap_set(DMA_LOAD_EOT, xdev->dma_dev.cap_mask);
 
 	xdev->dma_dev.dev = &pdev->dev;
 	xdev->dma_dev.residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT;
@@ -1091,10 +1271,13 @@ static int xdma_probe(struct platform_device *pdev)
 	xdev->dma_dev.device_prep_slave_sg = xdma_prep_device_sg;
 	xdev->dma_dev.device_config = xdma_device_config;
 	xdev->dma_dev.device_issue_pending = xdma_issue_pending;
+	xdev->dma_dev.device_terminate_all = xdma_terminate_all;
+	xdev->dma_dev.device_synchronize = xdma_synchronize;
 	xdev->dma_dev.filter.map = pdata->device_map;
 	xdev->dma_dev.filter.mapcnt = pdata->device_map_cnt;
 	xdev->dma_dev.filter.fn = xdma_filter_fn;
 	xdev->dma_dev.device_prep_dma_cyclic = xdma_prep_dma_cyclic;
+	xdev->dma_dev.device_prep_interleaved_dma = xdma_prep_interleaved_dma;
 
 	ret = dma_async_device_register(&xdev->dma_dev);
 	if (ret) {
diff --git a/drivers/dma/xilinx/xilinx_dpdma.c b/drivers/dma/xilinx/xilinx_dpdma.c
index 69587d85a7..eb0637d903 100644
--- a/drivers/dma/xilinx/xilinx_dpdma.c
+++ b/drivers/dma/xilinx/xilinx_dpdma.c
@@ -214,7 +214,8 @@ struct xilinx_dpdma_tx_desc {
  * @running: true if the channel is running
  * @first_frame: flag for the first frame of stream
  * @video_group: flag if multi-channel operation is needed for video channels
- * @lock: lock to access struct xilinx_dpdma_chan
+ * @lock: lock to access struct xilinx_dpdma_chan. Must be taken before
+ *        @vchan.lock, if both are to be held.
  * @desc_pool: descriptor allocation pool
  * @err_task: error IRQ bottom half handler
  * @desc: References to descriptors being processed
@@ -309,7 +310,7 @@ static ssize_t xilinx_dpdma_debugfs_desc_done_irq_read(char *buf)
 
 	out_str_len = strlen(XILINX_DPDMA_DEBUGFS_UINT16_MAX_STR);
 	out_str_len = min_t(size_t, XILINX_DPDMA_DEBUGFS_READ_MAX_SIZE,
-			    out_str_len);
+			    out_str_len + 1);
 	snprintf(buf, out_str_len, "%d",
 		 dpdma_debugfs.xilinx_dpdma_irq_done_count);
 
@@ -1097,12 +1098,14 @@ static void xilinx_dpdma_chan_vsync_irq(struct  xilinx_dpdma_chan *chan)
 	 * Complete the active descriptor, if any, promote the pending
 	 * descriptor to active, and queue the next transfer, if any.
 	 */
+	spin_lock(&chan->vchan.lock);
 	if (chan->desc.active)
 		vchan_cookie_complete(&chan->desc.active->vdesc);
 	chan->desc.active = pending;
 	chan->desc.pending = NULL;
 
 	xilinx_dpdma_chan_queue_transfer(chan);
+	spin_unlock(&chan->vchan.lock);
 
 out:
 	spin_unlock_irqrestore(&chan->lock, flags);
@@ -1264,10 +1267,12 @@ static void xilinx_dpdma_issue_pending(struct dma_chan *dchan)
 	struct xilinx_dpdma_chan *chan = to_xilinx_chan(dchan);
 	unsigned long flags;
 
-	spin_lock_irqsave(&chan->vchan.lock, flags);
+	spin_lock_irqsave(&chan->lock, flags);
+	spin_lock(&chan->vchan.lock);
 	if (vchan_issue_pending(&chan->vchan))
 		xilinx_dpdma_chan_queue_transfer(chan);
-	spin_unlock_irqrestore(&chan->vchan.lock, flags);
+	spin_unlock(&chan->vchan.lock);
+	spin_unlock_irqrestore(&chan->lock, flags);
 }
 
 static int xilinx_dpdma_config(struct dma_chan *dchan,
@@ -1495,7 +1500,9 @@ static void xilinx_dpdma_chan_err_task(struct tasklet_struct *t)
 		    XILINX_DPDMA_EINTR_CHAN_ERR_MASK << chan->id);
 
 	spin_lock_irqsave(&chan->lock, flags);
+	spin_lock(&chan->vchan.lock);
 	xilinx_dpdma_chan_queue_transfer(chan);
+	spin_unlock(&chan->vchan.lock);
 	spin_unlock_irqrestore(&chan->lock, flags);
 }