1 files changed, 605 insertions, 93 deletions

diff --git a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c
index e164f3295f5d..d9e4ac3edb4e 100644
--- a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c
+++ b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c
@@ -12,15 +12,20 @@
 #include <linux/device.h>
 #include <linux/dmaengine.h>
 #include <linux/dmapool.h>
+#include <linux/dma-mapping.h>
 #include <linux/err.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_dma.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/property.h>
+#include <linux/slab.h>
 #include <linux/types.h>
 
 #include "dw-axi-dmac.h"
@@ -195,43 +200,56 @@ static inline const char *axi_chan_name(struct axi_dma_chan *chan)
 	return dma_chan_name(&chan->vc.chan);
 }
 
-static struct axi_dma_desc *axi_desc_get(struct axi_dma_chan *chan)
+static struct axi_dma_desc *axi_desc_alloc(u32 num)
 {
-	struct dw_axi_dma *dw = chan->chip->dw;
 	struct axi_dma_desc *desc;
+
+	desc = kzalloc(sizeof(*desc), GFP_NOWAIT);
+	if (!desc)
+		return NULL;
+
+	desc->hw_desc = kcalloc(num, sizeof(*desc->hw_desc), GFP_NOWAIT);
+	if (!desc->hw_desc) {
+		kfree(desc);
+		return NULL;
+	}
+
+	return desc;
+}
+
+static struct axi_dma_lli *axi_desc_get(struct axi_dma_chan *chan,
+					dma_addr_t *addr)
+{
+	struct axi_dma_lli *lli;
 	dma_addr_t phys;
 
-	desc = dma_pool_zalloc(dw->desc_pool, GFP_NOWAIT, &phys);
-	if (unlikely(!desc)) {
+	lli = dma_pool_zalloc(chan->desc_pool, GFP_NOWAIT, &phys);
+	if (unlikely(!lli)) {
 		dev_err(chan2dev(chan), "%s: not enough descriptors available\n",
 			axi_chan_name(chan));
 		return NULL;
 	}
 
 	atomic_inc(&chan->descs_allocated);
-	INIT_LIST_HEAD(&desc->xfer_list);
-	desc->vd.tx.phys = phys;
-	desc->chan = chan;
+	*addr = phys;
 
-	return desc;
+	return lli;
 }
 
 static void axi_desc_put(struct axi_dma_desc *desc)
 {
 	struct axi_dma_chan *chan = desc->chan;
-	struct dw_axi_dma *dw = chan->chip->dw;
-	struct axi_dma_desc *child, *_next;
-	unsigned int descs_put = 0;
+	int count = atomic_read(&chan->descs_allocated);
+	struct axi_dma_hw_desc *hw_desc;
+	int descs_put;
 
-	list_for_each_entry_safe(child, _next, &desc->xfer_list, xfer_list) {
-		list_del(&child->xfer_list);
-		dma_pool_free(dw->desc_pool, child, child->vd.tx.phys);
-		descs_put++;
+	for (descs_put = 0; descs_put < count; descs_put++) {
+		hw_desc = &desc->hw_desc[descs_put];
+		dma_pool_free(chan->desc_pool, hw_desc->lli, hw_desc->llp);
 	}
 
-	dma_pool_free(dw->desc_pool, desc, desc->vd.tx.phys);
-	descs_put++;
-
+	kfree(desc->hw_desc);
+	kfree(desc);
 	atomic_sub(descs_put, &chan->descs_allocated);
 	dev_vdbg(chan2dev(chan), "%s: %d descs put, %d still allocated\n",
 		axi_chan_name(chan), descs_put,
@@ -248,19 +266,41 @@ dma_chan_tx_status(struct dma_chan *dchan, dma_cookie_t cookie,
 		  struct dma_tx_state *txstate)
 {
 	struct axi_dma_chan *chan = dchan_to_axi_dma_chan(dchan);
-	enum dma_status ret;
+	struct virt_dma_desc *vdesc;
+	enum dma_status status;
+	u32 completed_length;
+	unsigned long flags;
+	u32 completed_blocks;
+	size_t bytes = 0;
+	u32 length;
+	u32 len;
 
-	ret = dma_cookie_status(dchan, cookie, txstate);
+	status = dma_cookie_status(dchan, cookie, txstate);
+	if (status == DMA_COMPLETE || !txstate)
+		return status;
 
-	if (chan->is_paused && ret == DMA_IN_PROGRESS)
-		ret = DMA_PAUSED;
+	spin_lock_irqsave(&chan->vc.lock, flags);
 
-	return ret;
+	vdesc = vchan_find_desc(&chan->vc, cookie);
+	if (vdesc) {
+		length = vd_to_axi_desc(vdesc)->length;
+		completed_blocks = vd_to_axi_desc(vdesc)->completed_blocks;
+		len = vd_to_axi_desc(vdesc)->hw_desc[0].len;
+		completed_length = completed_blocks * len;
+		bytes = length - completed_length;
+	} else {
+		bytes = vd_to_axi_desc(vdesc)->length;
+	}
+
+	spin_unlock_irqrestore(&chan->vc.lock, flags);
+	dma_set_residue(txstate, bytes);
+
+	return status;
 }
 
-static void write_desc_llp(struct axi_dma_desc *desc, dma_addr_t adr)
+static void write_desc_llp(struct axi_dma_hw_desc *desc, dma_addr_t adr)
 {
-	desc->lli.llp = cpu_to_le64(adr);
+	desc->lli->llp = cpu_to_le64(adr);
 }
 
 static void write_chan_llp(struct axi_dma_chan *chan, dma_addr_t adr)
@@ -268,6 +308,29 @@ static void write_chan_llp(struct axi_dma_chan *chan, dma_addr_t adr)
 	axi_chan_iowrite64(chan, CH_LLP, adr);
 }
 
+static void dw_axi_dma_set_byte_halfword(struct axi_dma_chan *chan, bool set)
+{
+	u32 offset = DMAC_APB_BYTE_WR_CH_EN;
+	u32 reg_width, val;
+
+	if (!chan->chip->apb_regs) {
+		dev_dbg(chan->chip->dev, "apb_regs not initialized\n");
+		return;
+	}
+
+	reg_width = __ffs(chan->config.dst_addr_width);
+	if (reg_width == DWAXIDMAC_TRANS_WIDTH_16)
+		offset = DMAC_APB_HALFWORD_WR_CH_EN;
+
+	val = ioread32(chan->chip->apb_regs + offset);
+
+	if (set)
+		val |= BIT(chan->id);
+	else
+		val &= ~BIT(chan->id);
+
+	iowrite32(val, chan->chip->apb_regs + offset);
+}
 /* Called in chan locked context */
 static void axi_chan_block_xfer_start(struct axi_dma_chan *chan,
 				      struct axi_dma_desc *first)
@@ -293,9 +356,26 @@ static void axi_chan_block_xfer_start(struct axi_dma_chan *chan,
 	       priority << CH_CFG_H_PRIORITY_POS |
 	       DWAXIDMAC_HS_SEL_HW << CH_CFG_H_HS_SEL_DST_POS |
 	       DWAXIDMAC_HS_SEL_HW << CH_CFG_H_HS_SEL_SRC_POS);
+	switch (chan->direction) {
+	case DMA_MEM_TO_DEV:
+		dw_axi_dma_set_byte_halfword(chan, true);
+		reg |= (chan->config.device_fc ?
+			DWAXIDMAC_TT_FC_MEM_TO_PER_DST :
+			DWAXIDMAC_TT_FC_MEM_TO_PER_DMAC)
+			<< CH_CFG_H_TT_FC_POS;
+		break;
+	case DMA_DEV_TO_MEM:
+		reg |= (chan->config.device_fc ?
+			DWAXIDMAC_TT_FC_PER_TO_MEM_SRC :
+			DWAXIDMAC_TT_FC_PER_TO_MEM_DMAC)
+			<< CH_CFG_H_TT_FC_POS;
+		break;
+	default:
+		break;
+	}
 	axi_chan_iowrite32(chan, CH_CFG_H, reg);
 
-	write_chan_llp(chan, first->vd.tx.phys | lms);
+	write_chan_llp(chan, first->hw_desc[0].llp | lms);
 
 	irq_mask = DWAXIDMAC_IRQ_DMA_TRF | DWAXIDMAC_IRQ_ALL_ERR;
 	axi_chan_irq_sig_set(chan, irq_mask);
@@ -333,6 +413,13 @@ static void dma_chan_issue_pending(struct dma_chan *dchan)
 	spin_unlock_irqrestore(&chan->vc.lock, flags);
 }
 
+static void dw_axi_dma_synchronize(struct dma_chan *dchan)
+{
+	struct axi_dma_chan *chan = dchan_to_axi_dma_chan(dchan);
+
+	vchan_synchronize(&chan->vc);
+}
+
 static int dma_chan_alloc_chan_resources(struct dma_chan *dchan)
 {
 	struct axi_dma_chan *chan = dchan_to_axi_dma_chan(dchan);
@@ -344,6 +431,15 @@ static int dma_chan_alloc_chan_resources(struct dma_chan *dchan)
 		return -EBUSY;
 	}
 
+	/* LLI address must be aligned to a 64-byte boundary */
+	chan->desc_pool = dma_pool_create(dev_name(chan2dev(chan)),
+					  chan->chip->dev,
+					  sizeof(struct axi_dma_lli),
+					  64, 0);
+	if (!chan->desc_pool) {
+		dev_err(chan2dev(chan), "No memory for descriptors\n");
+		return -ENOMEM;
+	}
 	dev_vdbg(dchan2dev(dchan), "%s: allocating\n", axi_chan_name(chan));
 
 	pm_runtime_get(chan->chip->dev);
@@ -365,6 +461,8 @@ static void dma_chan_free_chan_resources(struct dma_chan *dchan)
 
 	vchan_free_chan_resources(&chan->vc);
 
+	dma_pool_destroy(chan->desc_pool);
+	chan->desc_pool = NULL;
 	dev_vdbg(dchan2dev(dchan),
 		 "%s: free resources, descriptor still allocated: %u\n",
 		 axi_chan_name(chan), atomic_read(&chan->descs_allocated));
@@ -372,73 +470,398 @@ static void dma_chan_free_chan_resources(struct dma_chan *dchan)
 	pm_runtime_put(chan->chip->dev);
 }
 
+static void dw_axi_dma_set_hw_channel(struct axi_dma_chip *chip,
+				      u32 handshake_num, bool set)
+{
+	unsigned long start = 0;
+	unsigned long reg_value;
+	unsigned long reg_mask;
+	unsigned long reg_set;
+	unsigned long mask;
+	unsigned long val;
+
+	if (!chip->apb_regs) {
+		dev_dbg(chip->dev, "apb_regs not initialized\n");
+		return;
+	}
+
+	/*
+	 * An unused DMA channel has a default value of 0x3F.
+	 * Lock the DMA channel by assign a handshake number to the channel.
+	 * Unlock the DMA channel by assign 0x3F to the channel.
+	 */
+	if (set) {
+		reg_set = UNUSED_CHANNEL;
+		val = handshake_num;
+	} else {
+		reg_set = handshake_num;
+		val = UNUSED_CHANNEL;
+	}
+
+	reg_value = lo_hi_readq(chip->apb_regs + DMAC_APB_HW_HS_SEL_0);
+
+	for_each_set_clump8(start, reg_mask, &reg_value, 64) {
+		if (reg_mask == reg_set) {
+			mask = GENMASK_ULL(start + 7, start);
+			reg_value &= ~mask;
+			reg_value |= rol64(val, start);
+			lo_hi_writeq(reg_value,
+				     chip->apb_regs + DMAC_APB_HW_HS_SEL_0);
+			break;
+		}
+	}
+}
+
 /*
  * If DW_axi_dmac sees CHx_CTL.ShadowReg_Or_LLI_Last bit of the fetched LLI
  * as 1, it understands that the current block is the final block in the
  * transfer and completes the DMA transfer operation at the end of current
  * block transfer.
  */
-static void set_desc_last(struct axi_dma_desc *desc)
+static void set_desc_last(struct axi_dma_hw_desc *desc)
 {
 	u32 val;
 
-	val = le32_to_cpu(desc->lli.ctl_hi);
+	val = le32_to_cpu(desc->lli->ctl_hi);
 	val |= CH_CTL_H_LLI_LAST;
-	desc->lli.ctl_hi = cpu_to_le32(val);
+	desc->lli->ctl_hi = cpu_to_le32(val);
 }
 
-static void write_desc_sar(struct axi_dma_desc *desc, dma_addr_t adr)
+static void write_desc_sar(struct axi_dma_hw_desc *desc, dma_addr_t adr)
 {
-	desc->lli.sar = cpu_to_le64(adr);
+	desc->lli->sar = cpu_to_le64(adr);
 }
 
-static void write_desc_dar(struct axi_dma_desc *desc, dma_addr_t adr)
+static void write_desc_dar(struct axi_dma_hw_desc *desc, dma_addr_t adr)
 {
-	desc->lli.dar = cpu_to_le64(adr);
+	desc->lli->dar = cpu_to_le64(adr);
 }
 
-static void set_desc_src_master(struct axi_dma_desc *desc)
+static void set_desc_src_master(struct axi_dma_hw_desc *desc)
 {
 	u32 val;
 
 	/* Select AXI0 for source master */
-	val = le32_to_cpu(desc->lli.ctl_lo);
+	val = le32_to_cpu(desc->lli->ctl_lo);
 	val &= ~CH_CTL_L_SRC_MAST;
-	desc->lli.ctl_lo = cpu_to_le32(val);
+	desc->lli->ctl_lo = cpu_to_le32(val);
 }
 
-static void set_desc_dest_master(struct axi_dma_desc *desc)
+static void set_desc_dest_master(struct axi_dma_hw_desc *hw_desc,
+				 struct axi_dma_desc *desc)
 {
 	u32 val;
 
 	/* Select AXI1 for source master if available */
-	val = le32_to_cpu(desc->lli.ctl_lo);
+	val = le32_to_cpu(hw_desc->lli->ctl_lo);
 	if (desc->chan->chip->dw->hdata->nr_masters > 1)
 		val |= CH_CTL_L_DST_MAST;
 	else
 		val &= ~CH_CTL_L_DST_MAST;
 
-	desc->lli.ctl_lo = cpu_to_le32(val);
+	hw_desc->lli->ctl_lo = cpu_to_le32(val);
+}
+
+static int dw_axi_dma_set_hw_desc(struct axi_dma_chan *chan,
+				  struct axi_dma_hw_desc *hw_desc,
+				  dma_addr_t mem_addr, size_t len)
+{
+	unsigned int data_width = BIT(chan->chip->dw->hdata->m_data_width);
+	unsigned int reg_width;
+	unsigned int mem_width;
+	dma_addr_t device_addr;
+	size_t axi_block_ts;
+	size_t block_ts;
+	u32 ctllo, ctlhi;
+	u32 burst_len;
+
+	axi_block_ts = chan->chip->dw->hdata->block_size[chan->id];
+
+	mem_width = __ffs(data_width | mem_addr | len);
+	if (mem_width > DWAXIDMAC_TRANS_WIDTH_32)
+		mem_width = DWAXIDMAC_TRANS_WIDTH_32;
+
+	if (!IS_ALIGNED(mem_addr, 4)) {
+		dev_err(chan->chip->dev, "invalid buffer alignment\n");
+		return -EINVAL;
+	}
+
+	switch (chan->direction) {
+	case DMA_MEM_TO_DEV:
+		reg_width = __ffs(chan->config.dst_addr_width);
+		device_addr = chan->config.dst_addr;
+		ctllo = reg_width << CH_CTL_L_DST_WIDTH_POS |
+			mem_width << CH_CTL_L_SRC_WIDTH_POS |
+			DWAXIDMAC_CH_CTL_L_NOINC << CH_CTL_L_DST_INC_POS |
+			DWAXIDMAC_CH_CTL_L_INC << CH_CTL_L_SRC_INC_POS;
+		block_ts = len >> mem_width;
+		break;
+	case DMA_DEV_TO_MEM:
+		reg_width = __ffs(chan->config.src_addr_width);
+		device_addr = chan->config.src_addr;
+		ctllo = reg_width << CH_CTL_L_SRC_WIDTH_POS |
+			mem_width << CH_CTL_L_DST_WIDTH_POS |
+			DWAXIDMAC_CH_CTL_L_INC << CH_CTL_L_DST_INC_POS |
+			DWAXIDMAC_CH_CTL_L_NOINC << CH_CTL_L_SRC_INC_POS;
+		block_ts = len >> reg_width;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (block_ts > axi_block_ts)
+		return -EINVAL;
+
+	hw_desc->lli = axi_desc_get(chan, &hw_desc->llp);
+	if (unlikely(!hw_desc->lli))
+		return -ENOMEM;
+
+	ctlhi = CH_CTL_H_LLI_VALID;
+
+	if (chan->chip->dw->hdata->restrict_axi_burst_len) {
+		burst_len = chan->chip->dw->hdata->axi_rw_burst_len;
+		ctlhi |= CH_CTL_H_ARLEN_EN | CH_CTL_H_AWLEN_EN |
+			 burst_len << CH_CTL_H_ARLEN_POS |
+			 burst_len << CH_CTL_H_AWLEN_POS;
+	}
+
+	hw_desc->lli->ctl_hi = cpu_to_le32(ctlhi);
+
+	if (chan->direction == DMA_MEM_TO_DEV) {
+		write_desc_sar(hw_desc, mem_addr);
+		write_desc_dar(hw_desc, device_addr);
+	} else {
+		write_desc_sar(hw_desc, device_addr);
+		write_desc_dar(hw_desc, mem_addr);
+	}
+
+	hw_desc->lli->block_ts_lo = cpu_to_le32(block_ts - 1);
+
+	ctllo |= DWAXIDMAC_BURST_TRANS_LEN_4 << CH_CTL_L_DST_MSIZE_POS |
+		 DWAXIDMAC_BURST_TRANS_LEN_4 << CH_CTL_L_SRC_MSIZE_POS;
+	hw_desc->lli->ctl_lo = cpu_to_le32(ctllo);
+
+	set_desc_src_master(hw_desc);
+
+	hw_desc->len = len;
+	return 0;
+}
+
+static size_t calculate_block_len(struct axi_dma_chan *chan,
+				  dma_addr_t dma_addr, size_t buf_len,
+				  enum dma_transfer_direction direction)
+{
+	u32 data_width, reg_width, mem_width;
+	size_t axi_block_ts, block_len;
+
+	axi_block_ts = chan->chip->dw->hdata->block_size[chan->id];
+
+	switch (direction) {
+	case DMA_MEM_TO_DEV:
+		data_width = BIT(chan->chip->dw->hdata->m_data_width);
+		mem_width = __ffs(data_width | dma_addr | buf_len);
+		if (mem_width > DWAXIDMAC_TRANS_WIDTH_32)
+			mem_width = DWAXIDMAC_TRANS_WIDTH_32;
+
+		block_len = axi_block_ts << mem_width;
+		break;
+	case DMA_DEV_TO_MEM:
+		reg_width = __ffs(chan->config.src_addr_width);
+		block_len = axi_block_ts << reg_width;
+		break;
+	default:
+		block_len = 0;
+	}
+
+	return block_len;
+}
+
+static struct dma_async_tx_descriptor *
+dw_axi_dma_chan_prep_cyclic(struct dma_chan *dchan, dma_addr_t dma_addr,
+			    size_t buf_len, size_t period_len,
+			    enum dma_transfer_direction direction,
+			    unsigned long flags)
+{
+	struct axi_dma_chan *chan = dchan_to_axi_dma_chan(dchan);
+	struct axi_dma_hw_desc *hw_desc = NULL;
+	struct axi_dma_desc *desc = NULL;
+	dma_addr_t src_addr = dma_addr;
+	u32 num_periods, num_segments;
+	size_t axi_block_len;
+	u32 total_segments;
+	u32 segment_len;
+	unsigned int i;
+	int status;
+	u64 llp = 0;
+	u8 lms = 0; /* Select AXI0 master for LLI fetching */
+
+	num_periods = buf_len / period_len;
+
+	axi_block_len = calculate_block_len(chan, dma_addr, buf_len, direction);
+	if (axi_block_len == 0)
+		return NULL;
+
+	num_segments = DIV_ROUND_UP(period_len, axi_block_len);
+	segment_len = DIV_ROUND_UP(period_len, num_segments);
+
+	total_segments = num_periods * num_segments;
+
+	desc = axi_desc_alloc(total_segments);
+	if (unlikely(!desc))
+		goto err_desc_get;
+
+	chan->direction = direction;
+	desc->chan = chan;
+	chan->cyclic = true;
+	desc->length = 0;
+	desc->period_len = period_len;
+
+	for (i = 0; i < total_segments; i++) {
+		hw_desc = &desc->hw_desc[i];
+
+		status = dw_axi_dma_set_hw_desc(chan, hw_desc, src_addr,
+						segment_len);
+		if (status < 0)
+			goto err_desc_get;
+
+		desc->length += hw_desc->len;
+		/* Set end-of-link to the linked descriptor, so that cyclic
+		 * callback function can be triggered during interrupt.
+		 */
+		set_desc_last(hw_desc);
+
+		src_addr += segment_len;
+	}
+
+	llp = desc->hw_desc[0].llp;
+
+	/* Managed transfer list */
+	do {
+		hw_desc = &desc->hw_desc[--total_segments];
+		write_desc_llp(hw_desc, llp | lms);
+		llp = hw_desc->llp;
+	} while (total_segments);
+
+	dw_axi_dma_set_hw_channel(chan->chip, chan->hw_handshake_num, true);
+
+	return vchan_tx_prep(&chan->vc, &desc->vd, flags);
+
+err_desc_get:
+	if (desc)
+		axi_desc_put(desc);
+
+	return NULL;
+}
+
+static struct dma_async_tx_descriptor *
+dw_axi_dma_chan_prep_slave_sg(struct dma_chan *dchan, struct scatterlist *sgl,
+			      unsigned int sg_len,
+			      enum dma_transfer_direction direction,
+			      unsigned long flags, void *context)
+{
+	struct axi_dma_chan *chan = dchan_to_axi_dma_chan(dchan);
+	struct axi_dma_hw_desc *hw_desc = NULL;
+	struct axi_dma_desc *desc = NULL;
+	u32 num_segments, segment_len;
+	unsigned int loop = 0;
+	struct scatterlist *sg;
+	size_t axi_block_len;
+	u32 len, num_sgs = 0;
+	unsigned int i;
+	dma_addr_t mem;
+	int status;
+	u64 llp = 0;
+	u8 lms = 0; /* Select AXI0 master for LLI fetching */
+
+	if (unlikely(!is_slave_direction(direction) || !sg_len))
+		return NULL;
+
+	mem = sg_dma_address(sgl);
+	len = sg_dma_len(sgl);
+
+	axi_block_len = calculate_block_len(chan, mem, len, direction);
+	if (axi_block_len == 0)
+		return NULL;
+
+	for_each_sg(sgl, sg, sg_len, i)
+		num_sgs += DIV_ROUND_UP(sg_dma_len(sg), axi_block_len);
+
+	desc = axi_desc_alloc(num_sgs);
+	if (unlikely(!desc))
+		goto err_desc_get;
+
+	desc->chan = chan;
+	desc->length = 0;
+	chan->direction = direction;
+
+	for_each_sg(sgl, sg, sg_len, i) {
+		mem = sg_dma_address(sg);
+		len = sg_dma_len(sg);
+		num_segments = DIV_ROUND_UP(sg_dma_len(sg), axi_block_len);
+		segment_len = DIV_ROUND_UP(sg_dma_len(sg), num_segments);
+
+		do {
+			hw_desc = &desc->hw_desc[loop++];
+			status = dw_axi_dma_set_hw_desc(chan, hw_desc, mem, segment_len);
+			if (status < 0)
+				goto err_desc_get;
+
+			desc->length += hw_desc->len;
+			len -= segment_len;
+			mem += segment_len;
+		} while (len >= segment_len);
+	}
+
+	/* Set end-of-link to the last link descriptor of list */
+	set_desc_last(&desc->hw_desc[num_sgs - 1]);
+
+	/* Managed transfer list */
+	do {
+		hw_desc = &desc->hw_desc[--num_sgs];
+		write_desc_llp(hw_desc, llp | lms);
+		llp = hw_desc->llp;
+	} while (num_sgs);
+
+	dw_axi_dma_set_hw_channel(chan->chip, chan->hw_handshake_num, true);
+
+	return vchan_tx_prep(&chan->vc, &desc->vd, flags);
+
+err_desc_get:
+	if (desc)
+		axi_desc_put(desc);
+
+	return NULL;
 }
 
 static struct dma_async_tx_descriptor *
 dma_chan_prep_dma_memcpy(struct dma_chan *dchan, dma_addr_t dst_adr,
 			 dma_addr_t src_adr, size_t len, unsigned long flags)
 {
-	struct axi_dma_desc *first = NULL, *desc = NULL, *prev = NULL;
 	struct axi_dma_chan *chan = dchan_to_axi_dma_chan(dchan);
 	size_t block_ts, max_block_ts, xfer_len;
-	u32 xfer_width, reg;
+	struct axi_dma_hw_desc *hw_desc = NULL;
+	struct axi_dma_desc *desc = NULL;
+	u32 xfer_width, reg, num;
+	u64 llp = 0;
 	u8 lms = 0; /* Select AXI0 master for LLI fetching */
 
 	dev_dbg(chan2dev(chan), "%s: memcpy: src: %pad dst: %pad length: %zd flags: %#lx",
 		axi_chan_name(chan), &src_adr, &dst_adr, len, flags);
 
 	max_block_ts = chan->chip->dw->hdata->block_size[chan->id];
+	xfer_width = axi_chan_get_xfer_width(chan, src_adr, dst_adr, len);
+	num = DIV_ROUND_UP(len, max_block_ts << xfer_width);
+	desc = axi_desc_alloc(num);
+	if (unlikely(!desc))
+		goto err_desc_get;
 
+	desc->chan = chan;
+	num = 0;
+	desc->length = 0;
 	while (len) {
 		xfer_len = len;
 
+		hw_desc = &desc->hw_desc[num];
 		/*
 		 * Take care for the alignment.
 		 * Actually source and destination widths can be different, but
@@ -457,13 +880,13 @@ dma_chan_prep_dma_memcpy(struct dma_chan *dchan, dma_addr_t dst_adr,
 			xfer_len = max_block_ts << xfer_width;
 		}
 
-		desc = axi_desc_get(chan);
-		if (unlikely(!desc))
+		hw_desc->lli = axi_desc_get(chan, &hw_desc->llp);
+		if (unlikely(!hw_desc->lli))
 			goto err_desc_get;
 
-		write_desc_sar(desc, src_adr);
-		write_desc_dar(desc, dst_adr);
-		desc->lli.block_ts_lo = cpu_to_le32(block_ts - 1);
+		write_desc_sar(hw_desc, src_adr);
+		write_desc_dar(hw_desc, dst_adr);
+		hw_desc->lli->block_ts_lo = cpu_to_le32(block_ts - 1);
 
 		reg = CH_CTL_H_LLI_VALID;
 		if (chan->chip->dw->hdata->restrict_axi_burst_len) {
@@ -474,7 +897,7 @@ dma_chan_prep_dma_memcpy(struct dma_chan *dchan, dma_addr_t dst_adr,
 				CH_CTL_H_AWLEN_EN |
 				burst_len << CH_CTL_H_AWLEN_POS);
 		}
-		desc->lli.ctl_hi = cpu_to_le32(reg);
+		hw_desc->lli->ctl_hi = cpu_to_le32(reg);
 
 		reg = (DWAXIDMAC_BURST_TRANS_LEN_4 << CH_CTL_L_DST_MSIZE_POS |
 		       DWAXIDMAC_BURST_TRANS_LEN_4 << CH_CTL_L_SRC_MSIZE_POS |
@@ -482,62 +905,68 @@ dma_chan_prep_dma_memcpy(struct dma_chan *dchan, dma_addr_t dst_adr,
 		       xfer_width << CH_CTL_L_SRC_WIDTH_POS |
 		       DWAXIDMAC_CH_CTL_L_INC << CH_CTL_L_DST_INC_POS |
 		       DWAXIDMAC_CH_CTL_L_INC << CH_CTL_L_SRC_INC_POS);
-		desc->lli.ctl_lo = cpu_to_le32(reg);
+		hw_desc->lli->ctl_lo = cpu_to_le32(reg);
 
-		set_desc_src_master(desc);
-		set_desc_dest_master(desc);
-
-		/* Manage transfer list (xfer_list) */
-		if (!first) {
-			first = desc;
-		} else {
-			list_add_tail(&desc->xfer_list, &first->xfer_list);
-			write_desc_llp(prev, desc->vd.tx.phys | lms);
-		}
-		prev = desc;
+		set_desc_src_master(hw_desc);
+		set_desc_dest_master(hw_desc, desc);
 
+		hw_desc->len = xfer_len;
+		desc->length += hw_desc->len;
 		/* update the length and addresses for the next loop cycle */
 		len -= xfer_len;
 		dst_adr += xfer_len;
 		src_adr += xfer_len;
+		num++;
 	}
 
-	/* Total len of src/dest sg == 0, so no descriptor were allocated */
-	if (unlikely(!first))
-		return NULL;
-
 	/* Set end-of-link to the last link descriptor of list */
-	set_desc_last(desc);
+	set_desc_last(&desc->hw_desc[num - 1]);
+	/* Managed transfer list */
+	do {
+		hw_desc = &desc->hw_desc[--num];
+		write_desc_llp(hw_desc, llp | lms);
+		llp = hw_desc->llp;
+	} while (num);
 
-	return vchan_tx_prep(&chan->vc, &first->vd, flags);
+	return vchan_tx_prep(&chan->vc, &desc->vd, flags);
 
 err_desc_get:
-	if (first)
-		axi_desc_put(first);
+	if (desc)
+		axi_desc_put(desc);
 	return NULL;
 }
 
+static int dw_axi_dma_chan_slave_config(struct dma_chan *dchan,
+					struct dma_slave_config *config)
+{
+	struct axi_dma_chan *chan = dchan_to_axi_dma_chan(dchan);
+
+	memcpy(&chan->config, config, sizeof(*config));
+
+	return 0;
+}
+
 static void axi_chan_dump_lli(struct axi_dma_chan *chan,
-			      struct axi_dma_desc *desc)
+			      struct axi_dma_hw_desc *desc)
 {
 	dev_err(dchan2dev(&chan->vc.chan),
 		"SAR: 0x%llx DAR: 0x%llx LLP: 0x%llx BTS 0x%x CTL: 0x%x:%08x",
-		le64_to_cpu(desc->lli.sar),
-		le64_to_cpu(desc->lli.dar),
-		le64_to_cpu(desc->lli.llp),
-		le32_to_cpu(desc->lli.block_ts_lo),
-		le32_to_cpu(desc->lli.ctl_hi),
-		le32_to_cpu(desc->lli.ctl_lo));
+		le64_to_cpu(desc->lli->sar),
+		le64_to_cpu(desc->lli->dar),
+		le64_to_cpu(desc->lli->llp),
+		le32_to_cpu(desc->lli->block_ts_lo),
+		le32_to_cpu(desc->lli->ctl_hi),
+		le32_to_cpu(desc->lli->ctl_lo));
 }
 
 static void axi_chan_list_dump_lli(struct axi_dma_chan *chan,
 				   struct axi_dma_desc *desc_head)
 {
-	struct axi_dma_desc *desc;
+	int count = atomic_read(&chan->descs_allocated);
+	int i;
 
-	axi_chan_dump_lli(chan, desc_head);
-	list_for_each_entry(desc, &desc_head->xfer_list, xfer_list)
-		axi_chan_dump_lli(chan, desc);
+	for (i = 0; i < count; i++)
+		axi_chan_dump_lli(chan, &desc_head->hw_desc[i]);
 }
 
 static noinline void axi_chan_handle_err(struct axi_dma_chan *chan, u32 status)
@@ -570,8 +999,13 @@ static noinline void axi_chan_handle_err(struct axi_dma_chan *chan, u32 status)
 
 static void axi_chan_block_xfer_complete(struct axi_dma_chan *chan)
 {
+	int count = atomic_read(&chan->descs_allocated);
+	struct axi_dma_hw_desc *hw_desc;
+	struct axi_dma_desc *desc;
 	struct virt_dma_desc *vd;
 	unsigned long flags;
+	u64 llp;
+	int i;
 
 	spin_lock_irqsave(&chan->vc.lock, flags);
 	if (unlikely(axi_chan_is_hw_enable(chan))) {
@@ -582,12 +1016,34 @@ static void axi_chan_block_xfer_complete(struct axi_dma_chan *chan)
 
 	/* The completed descriptor currently is in the head of vc list */
 	vd = vchan_next_desc(&chan->vc);
-	/* Remove the completed descriptor from issued list before completing */
-	list_del(&vd->node);
-	vchan_cookie_complete(vd);
 
-	/* Submit queued descriptors after processing the completed ones */
-	axi_chan_start_first_queued(chan);
+	if (chan->cyclic) {
+		desc = vd_to_axi_desc(vd);
+		if (desc) {
+			llp = lo_hi_readq(chan->chan_regs + CH_LLP);
+			for (i = 0; i < count; i++) {
+				hw_desc = &desc->hw_desc[i];
+				if (hw_desc->llp == llp) {
+					axi_chan_irq_clear(chan, hw_desc->lli->status_lo);
+					hw_desc->lli->ctl_hi |= CH_CTL_H_LLI_VALID;
+					desc->completed_blocks = i;
+
+					if (((hw_desc->len * (i + 1)) % desc->period_len) == 0)
+						vchan_cyclic_callback(vd);
+					break;
+				}
+			}
+
+			axi_chan_enable(chan);
+		}
+	} else {
+		/* Remove the completed descriptor from issued list before completing */
+		list_del(&vd->node);
+		vchan_cookie_complete(vd);
+
+		/* Submit queued descriptors after processing the completed ones */
+		axi_chan_start_first_queued(chan);
+	}
 
 	spin_unlock_irqrestore(&chan->vc.lock, flags);
 }
@@ -627,15 +1083,31 @@ static irqreturn_t dw_axi_dma_interrupt(int irq, void *dev_id)
 static int dma_chan_terminate_all(struct dma_chan *dchan)
 {
 	struct axi_dma_chan *chan = dchan_to_axi_dma_chan(dchan);
+	u32 chan_active = BIT(chan->id) << DMAC_CHAN_EN_SHIFT;
 	unsigned long flags;
+	u32 val;
+	int ret;
 	LIST_HEAD(head);
 
-	spin_lock_irqsave(&chan->vc.lock, flags);
-
 	axi_chan_disable(chan);
 
+	ret = readl_poll_timeout_atomic(chan->chip->regs + DMAC_CHEN, val,
+					!(val & chan_active), 1000, 10000);
+	if (ret == -ETIMEDOUT)
+		dev_warn(dchan2dev(dchan),
+			 "%s failed to stop\n", axi_chan_name(chan));
+
+	if (chan->direction != DMA_MEM_TO_MEM)
+		dw_axi_dma_set_hw_channel(chan->chip,
+					  chan->hw_handshake_num, false);
+	if (chan->direction == DMA_MEM_TO_DEV)
+		dw_axi_dma_set_byte_halfword(chan, false);
+
+	spin_lock_irqsave(&chan->vc.lock, flags);
+
 	vchan_get_all_descriptors(&chan->vc, &head);
 
+	chan->cyclic = false;
 	spin_unlock_irqrestore(&chan->vc.lock, flags);
 
 	vchan_dma_desc_free_list(&chan->vc, &head);
@@ -746,6 +1218,22 @@ static int __maybe_unused axi_dma_runtime_resume(struct device *dev)
 	return axi_dma_resume(chip);
 }
 
+static struct dma_chan *dw_axi_dma_of_xlate(struct of_phandle_args *dma_spec,
+					    struct of_dma *ofdma)
+{
+	struct dw_axi_dma *dw = ofdma->of_dma_data;
+	struct axi_dma_chan *chan;
+	struct dma_chan *dchan;
+
+	dchan = dma_get_any_slave_channel(&dw->dma);
+	if (!dchan)
+		return NULL;
+
+	chan = dchan_to_axi_dma_chan(dchan);
+	chan->hw_handshake_num = dma_spec->args[0];
+	return dchan;
+}
+
 static int parse_device_properties(struct axi_dma_chip *chip)
 {
 	struct device *dev = chip->dev;
@@ -816,6 +1304,7 @@ static int parse_device_properties(struct axi_dma_chip *chip)
 
 static int dw_probe(struct platform_device *pdev)
 {
+	struct device_node *node = pdev->dev.of_node;
 	struct axi_dma_chip *chip;
 	struct resource *mem;
 	struct dw_axi_dma *dw;
@@ -848,6 +1337,12 @@ static int dw_probe(struct platform_device *pdev)
 	if (IS_ERR(chip->regs))
 		return PTR_ERR(chip->regs);
 
+	if (of_device_is_compatible(node, "intel,kmb-axi-dma")) {
+		chip->apb_regs = devm_platform_ioremap_resource(pdev, 1);
+		if (IS_ERR(chip->apb_regs))
+			return PTR_ERR(chip->apb_regs);
+	}
+
 	chip->core_clk = devm_clk_get(chip->dev, "core-clk");
 	if (IS_ERR(chip->core_clk))
 		return PTR_ERR(chip->core_clk);
@@ -870,13 +1365,6 @@ static int dw_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	/* Lli address must be aligned to a 64-byte boundary */
-	dw->desc_pool = dmam_pool_create(KBUILD_MODNAME, chip->dev,
-					 sizeof(struct axi_dma_desc), 64, 0);
-	if (!dw->desc_pool) {
-		dev_err(chip->dev, "No memory for descriptors dma pool\n");
-		return -ENOMEM;
-	}
 
 	INIT_LIST_HEAD(&dw->dma.channels);
 	for (i = 0; i < hdata->nr_channels; i++) {
@@ -893,13 +1381,16 @@ static int dw_probe(struct platform_device *pdev)
 
 	/* Set capabilities */
 	dma_cap_set(DMA_MEMCPY, dw->dma.cap_mask);
+	dma_cap_set(DMA_SLAVE, dw->dma.cap_mask);
+	dma_cap_set(DMA_CYCLIC, dw->dma.cap_mask);
 
 	/* DMA capabilities */
 	dw->dma.chancnt = hdata->nr_channels;
 	dw->dma.src_addr_widths = AXI_DMA_BUSWIDTHS;
 	dw->dma.dst_addr_widths = AXI_DMA_BUSWIDTHS;
 	dw->dma.directions = BIT(DMA_MEM_TO_MEM);
-	dw->dma.residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR;
+	dw->dma.directions |= BIT(DMA_MEM_TO_DEV) | BIT(DMA_DEV_TO_MEM);
+	dw->dma.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
 
 	dw->dma.dev = chip->dev;
 	dw->dma.device_tx_status = dma_chan_tx_status;
@@ -912,7 +1403,18 @@ static int dw_probe(struct platform_device *pdev)
 	dw->dma.device_free_chan_resources = dma_chan_free_chan_resources;
 
 	dw->dma.device_prep_dma_memcpy = dma_chan_prep_dma_memcpy;
+	dw->dma.device_synchronize = dw_axi_dma_synchronize;
+	dw->dma.device_config = dw_axi_dma_chan_slave_config;
+	dw->dma.device_prep_slave_sg = dw_axi_dma_chan_prep_slave_sg;
+	dw->dma.device_prep_dma_cyclic = dw_axi_dma_chan_prep_cyclic;
 
+	/*
+	 * Synopsis DesignWare AxiDMA datasheet mentioned Maximum
+	 * supported blocks is 1024. Device register width is 4 bytes.
+	 * Therefore, set constraint to 1024 * 4.
+	 */
+	dw->dma.dev->dma_parms = &dw->dma_parms;
+	dma_set_max_seg_size(&pdev->dev, MAX_BLOCK_SIZE);
 	platform_set_drvdata(pdev, chip);
 
 	pm_runtime_enable(chip->dev);
@@ -935,6 +1437,13 @@ static int dw_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_pm_disable;
 
+	/* Register with OF helpers for DMA lookups */
+	ret = of_dma_controller_register(pdev->dev.of_node,
+					 dw_axi_dma_of_xlate, dw);
+	if (ret < 0)
+		dev_warn(&pdev->dev,
+			 "Failed to register OF DMA controller, fallback to MEM_TO_MEM mode\n");
+
 	dev_info(chip->dev, "DesignWare AXI DMA Controller, %d channels\n",
 		 dw->hdata->nr_channels);
 
@@ -968,6 +1477,8 @@ static int dw_remove(struct platform_device *pdev)
 
 	devm_free_irq(chip->dev, chip->irq, chip);
 
+	of_dma_controller_free(chip->dev->of_node);
+
 	list_for_each_entry_safe(chan, _chan, &dw->dma.channels,
 			vc.chan.device_node) {
 		list_del(&chan->vc.chan.device_node);
@@ -983,6 +1494,7 @@ static const struct dev_pm_ops dw_axi_dma_pm_ops = {
 
 static const struct of_device_id dw_dma_of_id_table[] = {
 	{ .compatible = "snps,axi-dma-1.01a" },
+	{ .compatible = "intel,kmb-axi-dma" },
 	{}
 };
 MODULE_DEVICE_TABLE(of, dw_dma_of_id_table);