Adding upstream version 4.19.249.upstream/4.19.249

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

7 files changed, 2395 insertions, 0 deletions

diff --git a/drivers/dma/dw/Kconfig b/drivers/dma/dw/Kconfig
new file mode 100644
index 000000000..070860ec0
--- /dev/null
+++ b/drivers/dma/dw/Kconfig
@@ -0,0 +1,25 @@
+#
+# DMA engine configuration for dw
+#
+
+config DW_DMAC_CORE
+	tristate
+	select DMA_ENGINE
+
+config DW_DMAC
+	tristate "Synopsys DesignWare AHB DMA platform driver"
+	depends on HAS_IOMEM
+	select DW_DMAC_CORE
+	help
+	  Support the Synopsys DesignWare AHB DMA controller. This
+	  can be integrated in chips such as the Intel Cherrytrail.
+
+config DW_DMAC_PCI
+	tristate "Synopsys DesignWare AHB DMA PCI driver"
+	depends on PCI
+	depends on HAS_IOMEM
+	select DW_DMAC_CORE
+	help
+	  Support the Synopsys DesignWare AHB DMA controller on the
+	  platforms that enumerate it as a PCI device. For example,
+	  Intel Medfield has integrated this GPDMA controller.
diff --git a/drivers/dma/dw/Makefile b/drivers/dma/dw/Makefile
new file mode 100644
index 000000000..2b949c2e4
--- /dev/null
+++ b/drivers/dma/dw/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_DW_DMAC_CORE)	+= dw_dmac_core.o
+dw_dmac_core-objs	:= core.o
+
+obj-$(CONFIG_DW_DMAC)		+= dw_dmac.o
+dw_dmac-objs		:= platform.o
+
+obj-$(CONFIG_DW_DMAC_PCI)	+= dw_dmac_pci.o
+dw_dmac_pci-objs	:= pci.o
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
new file mode 100644
index 000000000..055d83b6c
--- /dev/null
+++ b/drivers/dma/dw/core.c
@@ -0,0 +1,1441 @@
+/*
+ * Core driver for the Synopsys DesignWare DMA Controller
+ *
+ * Copyright (C) 2007-2008 Atmel Corporation
+ * Copyright (C) 2010-2011 ST Microelectronics
+ * Copyright (C) 2013 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/bitops.h>
+#include <linux/delay.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/pm_runtime.h>
+
+#include "../dmaengine.h"
+#include "internal.h"
+
+/*
+ * This supports the Synopsys "DesignWare AHB Central DMA Controller",
+ * (DW_ahb_dmac) which is used with various AMBA 2.0 systems (not all
+ * of which use ARM any more).  See the "Databook" from Synopsys for
+ * information beyond what licensees probably provide.
+ *
+ * The driver has been tested with the Atmel AT32AP7000, which does not
+ * support descriptor writeback.
+ */
+
+#define DWC_DEFAULT_CTLLO(_chan) ({				\
+		struct dw_dma_chan *_dwc = to_dw_dma_chan(_chan);	\
+		struct dma_slave_config	*_sconfig = &_dwc->dma_sconfig;	\
+		bool _is_slave = is_slave_direction(_dwc->direction);	\
+		u8 _smsize = _is_slave ? _sconfig->src_maxburst :	\
+			DW_DMA_MSIZE_16;			\
+		u8 _dmsize = _is_slave ? _sconfig->dst_maxburst :	\
+			DW_DMA_MSIZE_16;			\
+		u8 _dms = (_dwc->direction == DMA_MEM_TO_DEV) ?		\
+			_dwc->dws.p_master : _dwc->dws.m_master;	\
+		u8 _sms = (_dwc->direction == DMA_DEV_TO_MEM) ?		\
+			_dwc->dws.p_master : _dwc->dws.m_master;	\
+								\
+		(DWC_CTLL_DST_MSIZE(_dmsize)			\
+		 | DWC_CTLL_SRC_MSIZE(_smsize)			\
+		 | DWC_CTLL_LLP_D_EN				\
+		 | DWC_CTLL_LLP_S_EN				\
+		 | DWC_CTLL_DMS(_dms)				\
+		 | DWC_CTLL_SMS(_sms));				\
+	})
+
+/* The set of bus widths supported by the DMA controller */
+#define DW_DMA_BUSWIDTHS			  \
+	BIT(DMA_SLAVE_BUSWIDTH_UNDEFINED)	| \
+	BIT(DMA_SLAVE_BUSWIDTH_1_BYTE)		| \
+	BIT(DMA_SLAVE_BUSWIDTH_2_BYTES)		| \
+	BIT(DMA_SLAVE_BUSWIDTH_4_BYTES)
+
+/*----------------------------------------------------------------------*/
+
+static struct device *chan2dev(struct dma_chan *chan)
+{
+	return &chan->dev->device;
+}
+
+static struct dw_desc *dwc_first_active(struct dw_dma_chan *dwc)
+{
+	return to_dw_desc(dwc->active_list.next);
+}
+
+static dma_cookie_t dwc_tx_submit(struct dma_async_tx_descriptor *tx)
+{
+	struct dw_desc		*desc = txd_to_dw_desc(tx);
+	struct dw_dma_chan	*dwc = to_dw_dma_chan(tx->chan);
+	dma_cookie_t		cookie;
+	unsigned long		flags;
+
+	spin_lock_irqsave(&dwc->lock, flags);
+	cookie = dma_cookie_assign(tx);
+
+	/*
+	 * REVISIT: We should attempt to chain as many descriptors as
+	 * possible, perhaps even appending to those already submitted
+	 * for DMA. But this is hard to do in a race-free manner.
+	 */
+
+	list_add_tail(&desc->desc_node, &dwc->queue);
+	spin_unlock_irqrestore(&dwc->lock, flags);
+	dev_vdbg(chan2dev(tx->chan), "%s: queued %u\n",
+		 __func__, desc->txd.cookie);
+
+	return cookie;
+}
+
+static struct dw_desc *dwc_desc_get(struct dw_dma_chan *dwc)
+{
+	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
+	struct dw_desc *desc;
+	dma_addr_t phys;
+
+	desc = dma_pool_zalloc(dw->desc_pool, GFP_ATOMIC, &phys);
+	if (!desc)
+		return NULL;
+
+	dwc->descs_allocated++;
+	INIT_LIST_HEAD(&desc->tx_list);
+	dma_async_tx_descriptor_init(&desc->txd, &dwc->chan);
+	desc->txd.tx_submit = dwc_tx_submit;
+	desc->txd.flags = DMA_CTRL_ACK;
+	desc->txd.phys = phys;
+	return desc;
+}
+
+static void dwc_desc_put(struct dw_dma_chan *dwc, struct dw_desc *desc)
+{
+	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
+	struct dw_desc *child, *_next;
+
+	if (unlikely(!desc))
+		return;
+
+	list_for_each_entry_safe(child, _next, &desc->tx_list, desc_node) {
+		list_del(&child->desc_node);
+		dma_pool_free(dw->desc_pool, child, child->txd.phys);
+		dwc->descs_allocated--;
+	}
+
+	dma_pool_free(dw->desc_pool, desc, desc->txd.phys);
+	dwc->descs_allocated--;
+}
+
+static void dwc_initialize_chan_idma32(struct dw_dma_chan *dwc)
+{
+	u32 cfghi = 0;
+	u32 cfglo = 0;
+
+	/* Set default burst alignment */
+	cfglo |= IDMA32C_CFGL_DST_BURST_ALIGN | IDMA32C_CFGL_SRC_BURST_ALIGN;
+
+	/* Low 4 bits of the request lines */
+	cfghi |= IDMA32C_CFGH_DST_PER(dwc->dws.dst_id & 0xf);
+	cfghi |= IDMA32C_CFGH_SRC_PER(dwc->dws.src_id & 0xf);
+
+	/* Request line extension (2 bits) */
+	cfghi |= IDMA32C_CFGH_DST_PER_EXT(dwc->dws.dst_id >> 4 & 0x3);
+	cfghi |= IDMA32C_CFGH_SRC_PER_EXT(dwc->dws.src_id >> 4 & 0x3);
+
+	channel_writel(dwc, CFG_LO, cfglo);
+	channel_writel(dwc, CFG_HI, cfghi);
+}
+
+static void dwc_initialize_chan_dw(struct dw_dma_chan *dwc)
+{
+	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
+	u32 cfghi = DWC_CFGH_FIFO_MODE;
+	u32 cfglo = DWC_CFGL_CH_PRIOR(dwc->priority);
+	bool hs_polarity = dwc->dws.hs_polarity;
+
+	cfghi |= DWC_CFGH_DST_PER(dwc->dws.dst_id);
+	cfghi |= DWC_CFGH_SRC_PER(dwc->dws.src_id);
+	cfghi |= DWC_CFGH_PROTCTL(dw->pdata->protctl);
+
+	/* Set polarity of handshake interface */
+	cfglo |= hs_polarity ? DWC_CFGL_HS_DST_POL | DWC_CFGL_HS_SRC_POL : 0;
+
+	channel_writel(dwc, CFG_LO, cfglo);
+	channel_writel(dwc, CFG_HI, cfghi);
+}
+
+static void dwc_initialize(struct dw_dma_chan *dwc)
+{
+	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
+
+	if (test_bit(DW_DMA_IS_INITIALIZED, &dwc->flags))
+		return;
+
+	if (dw->pdata->is_idma32)
+		dwc_initialize_chan_idma32(dwc);
+	else
+		dwc_initialize_chan_dw(dwc);
+
+	/* Enable interrupts */
+	channel_set_bit(dw, MASK.XFER, dwc->mask);
+	channel_set_bit(dw, MASK.ERROR, dwc->mask);
+
+	set_bit(DW_DMA_IS_INITIALIZED, &dwc->flags);
+}
+
+/*----------------------------------------------------------------------*/
+
+static inline void dwc_dump_chan_regs(struct dw_dma_chan *dwc)
+{
+	dev_err(chan2dev(&dwc->chan),
+		"  SAR: 0x%x DAR: 0x%x LLP: 0x%x CTL: 0x%x:%08x\n",
+		channel_readl(dwc, SAR),
+		channel_readl(dwc, DAR),
+		channel_readl(dwc, LLP),
+		channel_readl(dwc, CTL_HI),
+		channel_readl(dwc, CTL_LO));
+}
+
+static inline void dwc_chan_disable(struct dw_dma *dw, struct dw_dma_chan *dwc)
+{
+	channel_clear_bit(dw, CH_EN, dwc->mask);
+	while (dma_readl(dw, CH_EN) & dwc->mask)
+		cpu_relax();
+}
+
+static u32 bytes2block(struct dw_dma_chan *dwc, size_t bytes,
+			  unsigned int width, size_t *len)
+{
+	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
+	u32 block;
+
+	/* Always in bytes for iDMA 32-bit */
+	if (dw->pdata->is_idma32)
+		width = 0;
+
+	if ((bytes >> width) > dwc->block_size) {
+		block = dwc->block_size;
+		*len = block << width;
+	} else {
+		block = bytes >> width;
+		*len = bytes;
+	}
+
+	return block;
+}
+
+static size_t block2bytes(struct dw_dma_chan *dwc, u32 block, u32 width)
+{
+	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
+
+	if (dw->pdata->is_idma32)
+		return IDMA32C_CTLH_BLOCK_TS(block);
+
+	return DWC_CTLH_BLOCK_TS(block) << width;
+}
+
+/*----------------------------------------------------------------------*/
+
+/* Perform single block transfer */
+static inline void dwc_do_single_block(struct dw_dma_chan *dwc,
+				       struct dw_desc *desc)
+{
+	struct dw_dma	*dw = to_dw_dma(dwc->chan.device);
+	u32		ctllo;
+
+	/*
+	 * Software emulation of LLP mode relies on interrupts to continue
+	 * multi block transfer.
+	 */
+	ctllo = lli_read(desc, ctllo) | DWC_CTLL_INT_EN;
+
+	channel_writel(dwc, SAR, lli_read(desc, sar));
+	channel_writel(dwc, DAR, lli_read(desc, dar));
+	channel_writel(dwc, CTL_LO, ctllo);
+	channel_writel(dwc, CTL_HI, lli_read(desc, ctlhi));
+	channel_set_bit(dw, CH_EN, dwc->mask);
+
+	/* Move pointer to next descriptor */
+	dwc->tx_node_active = dwc->tx_node_active->next;
+}
+
+/* Called with dwc->lock held and bh disabled */
+static void dwc_dostart(struct dw_dma_chan *dwc, struct dw_desc *first)
+{
+	struct dw_dma	*dw = to_dw_dma(dwc->chan.device);
+	u8		lms = DWC_LLP_LMS(dwc->dws.m_master);
+	unsigned long	was_soft_llp;
+
+	/* ASSERT:  channel is idle */
+	if (dma_readl(dw, CH_EN) & dwc->mask) {
+		dev_err(chan2dev(&dwc->chan),
+			"%s: BUG: Attempted to start non-idle channel\n",
+			__func__);
+		dwc_dump_chan_regs(dwc);
+
+		/* The tasklet will hopefully advance the queue... */
+		return;
+	}
+
+	if (dwc->nollp) {
+		was_soft_llp = test_and_set_bit(DW_DMA_IS_SOFT_LLP,
+						&dwc->flags);
+		if (was_soft_llp) {
+			dev_err(chan2dev(&dwc->chan),
+				"BUG: Attempted to start new LLP transfer inside ongoing one\n");
+			return;
+		}
+
+		dwc_initialize(dwc);
+
+		first->residue = first->total_len;
+		dwc->tx_node_active = &first->tx_list;
+
+		/* Submit first block */
+		dwc_do_single_block(dwc, first);
+
+		return;
+	}
+
+	dwc_initialize(dwc);
+
+	channel_writel(dwc, LLP, first->txd.phys | lms);
+	channel_writel(dwc, CTL_LO, DWC_CTLL_LLP_D_EN | DWC_CTLL_LLP_S_EN);
+	channel_writel(dwc, CTL_HI, 0);
+	channel_set_bit(dw, CH_EN, dwc->mask);
+}
+
+static void dwc_dostart_first_queued(struct dw_dma_chan *dwc)
+{
+	struct dw_desc *desc;
+
+	if (list_empty(&dwc->queue))
+		return;
+
+	list_move(dwc->queue.next, &dwc->active_list);
+	desc = dwc_first_active(dwc);
+	dev_vdbg(chan2dev(&dwc->chan), "%s: started %u\n", __func__, desc->txd.cookie);
+	dwc_dostart(dwc, desc);
+}
+
+/*----------------------------------------------------------------------*/
+
+static void
+dwc_descriptor_complete(struct dw_dma_chan *dwc, struct dw_desc *desc,
+		bool callback_required)
+{
+	struct dma_async_tx_descriptor	*txd = &desc->txd;
+	struct dw_desc			*child;
+	unsigned long			flags;
+	struct dmaengine_desc_callback	cb;
+
+	dev_vdbg(chan2dev(&dwc->chan), "descriptor %u complete\n", txd->cookie);
+
+	spin_lock_irqsave(&dwc->lock, flags);
+	dma_cookie_complete(txd);
+	if (callback_required)
+		dmaengine_desc_get_callback(txd, &cb);
+	else
+		memset(&cb, 0, sizeof(cb));
+
+	/* async_tx_ack */
+	list_for_each_entry(child, &desc->tx_list, desc_node)
+		async_tx_ack(&child->txd);
+	async_tx_ack(&desc->txd);
+	dwc_desc_put(dwc, desc);
+	spin_unlock_irqrestore(&dwc->lock, flags);
+
+	dmaengine_desc_callback_invoke(&cb, NULL);
+}
+
+static void dwc_complete_all(struct dw_dma *dw, struct dw_dma_chan *dwc)
+{
+	struct dw_desc *desc, *_desc;
+	LIST_HEAD(list);
+	unsigned long flags;
+
+	spin_lock_irqsave(&dwc->lock, flags);
+	if (dma_readl(dw, CH_EN) & dwc->mask) {
+		dev_err(chan2dev(&dwc->chan),
+			"BUG: XFER bit set, but channel not idle!\n");
+
+		/* Try to continue after resetting the channel... */
+		dwc_chan_disable(dw, dwc);
+	}
+
+	/*
+	 * Submit queued descriptors ASAP, i.e. before we go through
+	 * the completed ones.
+	 */
+	list_splice_init(&dwc->active_list, &list);
+	dwc_dostart_first_queued(dwc);
+
+	spin_unlock_irqrestore(&dwc->lock, flags);
+
+	list_for_each_entry_safe(desc, _desc, &list, desc_node)
+		dwc_descriptor_complete(dwc, desc, true);
+}
+
+/* Returns how many bytes were already received from source */
+static inline u32 dwc_get_sent(struct dw_dma_chan *dwc)
+{
+	u32 ctlhi = channel_readl(dwc, CTL_HI);
+	u32 ctllo = channel_readl(dwc, CTL_LO);
+
+	return block2bytes(dwc, ctlhi, ctllo >> 4 & 7);
+}
+
+static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
+{
+	dma_addr_t llp;
+	struct dw_desc *desc, *_desc;
+	struct dw_desc *child;
+	u32 status_xfer;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dwc->lock, flags);
+	llp = channel_readl(dwc, LLP);
+	status_xfer = dma_readl(dw, RAW.XFER);
+
+	if (status_xfer & dwc->mask) {
+		/* Everything we've submitted is done */
+		dma_writel(dw, CLEAR.XFER, dwc->mask);
+
+		if (test_bit(DW_DMA_IS_SOFT_LLP, &dwc->flags)) {
+			struct list_head *head, *active = dwc->tx_node_active;
+
+			/*
+			 * We are inside first active descriptor.
+			 * Otherwise something is really wrong.
+			 */
+			desc = dwc_first_active(dwc);
+
+			head = &desc->tx_list;
+			if (active != head) {
+				/* Update residue to reflect last sent descriptor */
+				if (active == head->next)
+					desc->residue -= desc->len;
+				else
+					desc->residue -= to_dw_desc(active->prev)->len;
+
+				child = to_dw_desc(active);
+
+				/* Submit next block */
+				dwc_do_single_block(dwc, child);
+
+				spin_unlock_irqrestore(&dwc->lock, flags);
+				return;
+			}
+
+			/* We are done here */
+			clear_bit(DW_DMA_IS_SOFT_LLP, &dwc->flags);
+		}
+
+		spin_unlock_irqrestore(&dwc->lock, flags);
+
+		dwc_complete_all(dw, dwc);
+		return;
+	}
+
+	if (list_empty(&dwc->active_list)) {
+		spin_unlock_irqrestore(&dwc->lock, flags);
+		return;
+	}
+
+	if (test_bit(DW_DMA_IS_SOFT_LLP, &dwc->flags)) {
+		dev_vdbg(chan2dev(&dwc->chan), "%s: soft LLP mode\n", __func__);
+		spin_unlock_irqrestore(&dwc->lock, flags);
+		return;
+	}
+
+	dev_vdbg(chan2dev(&dwc->chan), "%s: llp=%pad\n", __func__, &llp);
+
+	list_for_each_entry_safe(desc, _desc, &dwc->active_list, desc_node) {
+		/* Initial residue value */
+		desc->residue = desc->total_len;
+
+		/* Check first descriptors addr */
+		if (desc->txd.phys == DWC_LLP_LOC(llp)) {
+			spin_unlock_irqrestore(&dwc->lock, flags);
+			return;
+		}
+
+		/* Check first descriptors llp */
+		if (lli_read(desc, llp) == llp) {
+			/* This one is currently in progress */
+			desc->residue -= dwc_get_sent(dwc);
+			spin_unlock_irqrestore(&dwc->lock, flags);
+			return;
+		}
+
+		desc->residue -= desc->len;
+		list_for_each_entry(child, &desc->tx_list, desc_node) {
+			if (lli_read(child, llp) == llp) {
+				/* Currently in progress */
+				desc->residue -= dwc_get_sent(dwc);
+				spin_unlock_irqrestore(&dwc->lock, flags);
+				return;
+			}
+			desc->residue -= child->len;
+		}
+
+		/*
+		 * No descriptors so far seem to be in progress, i.e.
+		 * this one must be done.
+		 */
+		spin_unlock_irqrestore(&dwc->lock, flags);
+		dwc_descriptor_complete(dwc, desc, true);
+		spin_lock_irqsave(&dwc->lock, flags);
+	}
+
+	dev_err(chan2dev(&dwc->chan),
+		"BUG: All descriptors done, but channel not idle!\n");
+
+	/* Try to continue after resetting the channel... */
+	dwc_chan_disable(dw, dwc);
+
+	dwc_dostart_first_queued(dwc);
+	spin_unlock_irqrestore(&dwc->lock, flags);
+}
+
+static inline void dwc_dump_lli(struct dw_dma_chan *dwc, struct dw_desc *desc)
+{
+	dev_crit(chan2dev(&dwc->chan), "  desc: s0x%x d0x%x l0x%x c0x%x:%x\n",
+		 lli_read(desc, sar),
+		 lli_read(desc, dar),
+		 lli_read(desc, llp),
+		 lli_read(desc, ctlhi),
+		 lli_read(desc, ctllo));
+}
+
+static void dwc_handle_error(struct dw_dma *dw, struct dw_dma_chan *dwc)
+{
+	struct dw_desc *bad_desc;
+	struct dw_desc *child;
+	unsigned long flags;
+
+	dwc_scan_descriptors(dw, dwc);
+
+	spin_lock_irqsave(&dwc->lock, flags);
+
+	/*
+	 * The descriptor currently at the head of the active list is
+	 * borked. Since we don't have any way to report errors, we'll
+	 * just have to scream loudly and try to carry on.
+	 */
+	bad_desc = dwc_first_active(dwc);
+	list_del_init(&bad_desc->desc_node);
+	list_move(dwc->queue.next, dwc->active_list.prev);
+
+	/* Clear the error flag and try to restart the controller */
+	dma_writel(dw, CLEAR.ERROR, dwc->mask);
+	if (!list_empty(&dwc->active_list))
+		dwc_dostart(dwc, dwc_first_active(dwc));
+
+	/*
+	 * WARN may seem harsh, but since this only happens
+	 * when someone submits a bad physical address in a
+	 * descriptor, we should consider ourselves lucky that the
+	 * controller flagged an error instead of scribbling over
+	 * random memory locations.
+	 */
+	dev_WARN(chan2dev(&dwc->chan), "Bad descriptor submitted for DMA!\n"
+				       "  cookie: %d\n", bad_desc->txd.cookie);
+	dwc_dump_lli(dwc, bad_desc);
+	list_for_each_entry(child, &bad_desc->tx_list, desc_node)
+		dwc_dump_lli(dwc, child);
+
+	spin_unlock_irqrestore(&dwc->lock, flags);
+
+	/* Pretend the descriptor completed successfully */
+	dwc_descriptor_complete(dwc, bad_desc, true);
+}
+
+static void dw_dma_tasklet(unsigned long data)
+{
+	struct dw_dma *dw = (struct dw_dma *)data;
+	struct dw_dma_chan *dwc;
+	u32 status_xfer;
+	u32 status_err;
+	unsigned int i;
+
+	status_xfer = dma_readl(dw, RAW.XFER);
+	status_err = dma_readl(dw, RAW.ERROR);
+
+	dev_vdbg(dw->dma.dev, "%s: status_err=%x\n", __func__, status_err);
+
+	for (i = 0; i < dw->dma.chancnt; i++) {
+		dwc = &dw->chan[i];
+		if (test_bit(DW_DMA_IS_CYCLIC, &dwc->flags))
+			dev_vdbg(dw->dma.dev, "Cyclic xfer is not implemented\n");
+		else if (status_err & (1 << i))
+			dwc_handle_error(dw, dwc);
+		else if (status_xfer & (1 << i))
+			dwc_scan_descriptors(dw, dwc);
+	}
+
+	/* Re-enable interrupts */
+	channel_set_bit(dw, MASK.XFER, dw->all_chan_mask);
+	channel_set_bit(dw, MASK.ERROR, dw->all_chan_mask);
+}
+
+static irqreturn_t dw_dma_interrupt(int irq, void *dev_id)
+{
+	struct dw_dma *dw = dev_id;
+	u32 status;
+
+	/* Check if we have any interrupt from the DMAC which is not in use */
+	if (!dw->in_use)
+		return IRQ_NONE;
+
+	status = dma_readl(dw, STATUS_INT);
+	dev_vdbg(dw->dma.dev, "%s: status=0x%x\n", __func__, status);
+
+	/* Check if we have any interrupt from the DMAC */
+	if (!status)
+		return IRQ_NONE;
+
+	/*
+	 * Just disable the interrupts. We'll turn them back on in the
+	 * softirq handler.
+	 */
+	channel_clear_bit(dw, MASK.XFER, dw->all_chan_mask);
+	channel_clear_bit(dw, MASK.BLOCK, dw->all_chan_mask);
+	channel_clear_bit(dw, MASK.ERROR, dw->all_chan_mask);
+
+	status = dma_readl(dw, STATUS_INT);
+	if (status) {
+		dev_err(dw->dma.dev,
+			"BUG: Unexpected interrupts pending: 0x%x\n",
+			status);
+
+		/* Try to recover */
+		channel_clear_bit(dw, MASK.XFER, (1 << 8) - 1);
+		channel_clear_bit(dw, MASK.BLOCK, (1 << 8) - 1);
+		channel_clear_bit(dw, MASK.SRC_TRAN, (1 << 8) - 1);
+		channel_clear_bit(dw, MASK.DST_TRAN, (1 << 8) - 1);
+		channel_clear_bit(dw, MASK.ERROR, (1 << 8) - 1);
+	}
+
+	tasklet_schedule(&dw->tasklet);
+
+	return IRQ_HANDLED;
+}
+
+/*----------------------------------------------------------------------*/
+
+static struct dma_async_tx_descriptor *
+dwc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
+		size_t len, unsigned long flags)
+{
+	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
+	struct dw_dma		*dw = to_dw_dma(chan->device);
+	struct dw_desc		*desc;
+	struct dw_desc		*first;
+	struct dw_desc		*prev;
+	size_t			xfer_count;
+	size_t			offset;
+	u8			m_master = dwc->dws.m_master;
+	unsigned int		src_width;
+	unsigned int		dst_width;
+	unsigned int		data_width = dw->pdata->data_width[m_master];
+	u32			ctllo;
+	u8			lms = DWC_LLP_LMS(m_master);
+
+	dev_vdbg(chan2dev(chan),
+			"%s: d%pad s%pad l0x%zx f0x%lx\n", __func__,
+			&dest, &src, len, flags);
+
+	if (unlikely(!len)) {
+		dev_dbg(chan2dev(chan), "%s: length is zero!\n", __func__);
+		return NULL;
+	}
+
+	dwc->direction = DMA_MEM_TO_MEM;
+
+	src_width = dst_width = __ffs(data_width | src | dest | len);
+
+	ctllo = DWC_DEFAULT_CTLLO(chan)
+			| DWC_CTLL_DST_WIDTH(dst_width)
+			| DWC_CTLL_SRC_WIDTH(src_width)
+			| DWC_CTLL_DST_INC
+			| DWC_CTLL_SRC_INC
+			| DWC_CTLL_FC_M2M;
+	prev = first = NULL;
+
+	for (offset = 0; offset < len; offset += xfer_count) {
+		desc = dwc_desc_get(dwc);
+		if (!desc)
+			goto err_desc_get;
+
+		lli_write(desc, sar, src + offset);
+		lli_write(desc, dar, dest + offset);
+		lli_write(desc, ctllo, ctllo);
+		lli_write(desc, ctlhi, bytes2block(dwc, len - offset, src_width, &xfer_count));
+		desc->len = xfer_count;
+
+		if (!first) {
+			first = desc;
+		} else {
+			lli_write(prev, llp, desc->txd.phys | lms);
+			list_add_tail(&desc->desc_node, &first->tx_list);
+		}
+		prev = desc;
+	}
+
+	if (flags & DMA_PREP_INTERRUPT)
+		/* Trigger interrupt after last block */
+		lli_set(prev, ctllo, DWC_CTLL_INT_EN);
+
+	prev->lli.llp = 0;
+	lli_clear(prev, ctllo, DWC_CTLL_LLP_D_EN | DWC_CTLL_LLP_S_EN);
+	first->txd.flags = flags;
+	first->total_len = len;
+
+	return &first->txd;
+
+err_desc_get:
+	dwc_desc_put(dwc, first);
+	return NULL;
+}
+
+static struct dma_async_tx_descriptor *
+dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
+		unsigned int sg_len, enum dma_transfer_direction direction,
+		unsigned long flags, void *context)
+{
+	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
+	struct dw_dma		*dw = to_dw_dma(chan->device);
+	struct dma_slave_config	*sconfig = &dwc->dma_sconfig;
+	struct dw_desc		*prev;
+	struct dw_desc		*first;
+	u32			ctllo;
+	u8			m_master = dwc->dws.m_master;
+	u8			lms = DWC_LLP_LMS(m_master);
+	dma_addr_t		reg;
+	unsigned int		reg_width;
+	unsigned int		mem_width;
+	unsigned int		data_width = dw->pdata->data_width[m_master];
+	unsigned int		i;
+	struct scatterlist	*sg;
+	size_t			total_len = 0;
+
+	dev_vdbg(chan2dev(chan), "%s\n", __func__);
+
+	if (unlikely(!is_slave_direction(direction) || !sg_len))
+		return NULL;
+
+	dwc->direction = direction;
+
+	prev = first = NULL;
+
+	switch (direction) {
+	case DMA_MEM_TO_DEV:
+		reg_width = __ffs(sconfig->dst_addr_width);
+		reg = sconfig->dst_addr;
+		ctllo = (DWC_DEFAULT_CTLLO(chan)
+				| DWC_CTLL_DST_WIDTH(reg_width)
+				| DWC_CTLL_DST_FIX
+				| DWC_CTLL_SRC_INC);
+
+		ctllo |= sconfig->device_fc ? DWC_CTLL_FC(DW_DMA_FC_P_M2P) :
+			DWC_CTLL_FC(DW_DMA_FC_D_M2P);
+
+		for_each_sg(sgl, sg, sg_len, i) {
+			struct dw_desc	*desc;
+			u32		len, mem;
+			size_t		dlen;
+
+			mem = sg_dma_address(sg);
+			len = sg_dma_len(sg);
+
+			mem_width = __ffs(data_width | mem | len);
+
+slave_sg_todev_fill_desc:
+			desc = dwc_desc_get(dwc);
+			if (!desc)
+				goto err_desc_get;
+
+			lli_write(desc, sar, mem);
+			lli_write(desc, dar, reg);
+			lli_write(desc, ctlhi, bytes2block(dwc, len, mem_width, &dlen));
+			lli_write(desc, ctllo, ctllo | DWC_CTLL_SRC_WIDTH(mem_width));
+			desc->len = dlen;
+
+			if (!first) {
+				first = desc;
+			} else {
+				lli_write(prev, llp, desc->txd.phys | lms);
+				list_add_tail(&desc->desc_node, &first->tx_list);
+			}
+			prev = desc;
+
+			mem += dlen;
+			len -= dlen;
+			total_len += dlen;
+
+			if (len)
+				goto slave_sg_todev_fill_desc;
+		}
+		break;
+	case DMA_DEV_TO_MEM:
+		reg_width = __ffs(sconfig->src_addr_width);
+		reg = sconfig->src_addr;
+		ctllo = (DWC_DEFAULT_CTLLO(chan)
+				| DWC_CTLL_SRC_WIDTH(reg_width)
+				| DWC_CTLL_DST_INC
+				| DWC_CTLL_SRC_FIX);
+
+		ctllo |= sconfig->device_fc ? DWC_CTLL_FC(DW_DMA_FC_P_P2M) :
+			DWC_CTLL_FC(DW_DMA_FC_D_P2M);
+
+		for_each_sg(sgl, sg, sg_len, i) {
+			struct dw_desc	*desc;
+			u32		len, mem;
+			size_t		dlen;
+
+			mem = sg_dma_address(sg);
+			len = sg_dma_len(sg);
+
+slave_sg_fromdev_fill_desc:
+			desc = dwc_desc_get(dwc);
+			if (!desc)
+				goto err_desc_get;
+
+			lli_write(desc, sar, reg);
+			lli_write(desc, dar, mem);
+			lli_write(desc, ctlhi, bytes2block(dwc, len, reg_width, &dlen));
+			mem_width = __ffs(data_width | mem | dlen);
+			lli_write(desc, ctllo, ctllo | DWC_CTLL_DST_WIDTH(mem_width));
+			desc->len = dlen;
+
+			if (!first) {
+				first = desc;
+			} else {
+				lli_write(prev, llp, desc->txd.phys | lms);
+				list_add_tail(&desc->desc_node, &first->tx_list);
+			}
+			prev = desc;
+
+			mem += dlen;
+			len -= dlen;
+			total_len += dlen;
+
+			if (len)
+				goto slave_sg_fromdev_fill_desc;
+		}
+		break;
+	default:
+		return NULL;
+	}
+
+	if (flags & DMA_PREP_INTERRUPT)
+		/* Trigger interrupt after last block */
+		lli_set(prev, ctllo, DWC_CTLL_INT_EN);
+
+	prev->lli.llp = 0;
+	lli_clear(prev, ctllo, DWC_CTLL_LLP_D_EN | DWC_CTLL_LLP_S_EN);
+	first->total_len = total_len;
+
+	return &first->txd;
+
+err_desc_get:
+	dev_err(chan2dev(chan),
+		"not enough descriptors available. Direction %d\n", direction);
+	dwc_desc_put(dwc, first);
+	return NULL;
+}
+
+bool dw_dma_filter(struct dma_chan *chan, void *param)
+{
+	struct dw_dma_chan *dwc = to_dw_dma_chan(chan);
+	struct dw_dma_slave *dws = param;
+
+	if (dws->dma_dev != chan->device->dev)
+		return false;
+
+	/* We have to copy data since dws can be temporary storage */
+	memcpy(&dwc->dws, dws, sizeof(struct dw_dma_slave));
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(dw_dma_filter);
+
+static int dwc_config(struct dma_chan *chan, struct dma_slave_config *sconfig)
+{
+	struct dw_dma_chan *dwc = to_dw_dma_chan(chan);
+	struct dma_slave_config *sc = &dwc->dma_sconfig;
+	struct dw_dma *dw = to_dw_dma(chan->device);
+	/*
+	 * Fix sconfig's burst size according to dw_dmac. We need to convert
+	 * them as:
+	 * 1 -> 0, 4 -> 1, 8 -> 2, 16 -> 3.
+	 *
+	 * NOTE: burst size 2 is not supported by DesignWare controller.
+	 *       iDMA 32-bit supports it.
+	 */
+	u32 s = dw->pdata->is_idma32 ? 1 : 2;
+
+	/* Check if chan will be configured for slave transfers */
+	if (!is_slave_direction(sconfig->direction))
+		return -EINVAL;
+
+	memcpy(&dwc->dma_sconfig, sconfig, sizeof(*sconfig));
+	dwc->direction = sconfig->direction;
+
+	sc->src_maxburst = sc->src_maxburst > 1 ? fls(sc->src_maxburst) - s : 0;
+	sc->dst_maxburst = sc->dst_maxburst > 1 ? fls(sc->dst_maxburst) - s : 0;
+
+	return 0;
+}
+
+static void dwc_chan_pause(struct dw_dma_chan *dwc, bool drain)
+{
+	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
+	unsigned int		count = 20;	/* timeout iterations */
+	u32			cfglo;
+
+	cfglo = channel_readl(dwc, CFG_LO);
+	if (dw->pdata->is_idma32) {
+		if (drain)
+			cfglo |= IDMA32C_CFGL_CH_DRAIN;
+		else
+			cfglo &= ~IDMA32C_CFGL_CH_DRAIN;
+	}
+	channel_writel(dwc, CFG_LO, cfglo | DWC_CFGL_CH_SUSP);
+	while (!(channel_readl(dwc, CFG_LO) & DWC_CFGL_FIFO_EMPTY) && count--)
+		udelay(2);
+
+	set_bit(DW_DMA_IS_PAUSED, &dwc->flags);
+}
+
+static int dwc_pause(struct dma_chan *chan)
+{
+	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
+	unsigned long		flags;
+
+	spin_lock_irqsave(&dwc->lock, flags);
+	dwc_chan_pause(dwc, false);
+	spin_unlock_irqrestore(&dwc->lock, flags);
+
+	return 0;
+}
+
+static inline void dwc_chan_resume(struct dw_dma_chan *dwc)
+{
+	u32 cfglo = channel_readl(dwc, CFG_LO);
+
+	channel_writel(dwc, CFG_LO, cfglo & ~DWC_CFGL_CH_SUSP);
+
+	clear_bit(DW_DMA_IS_PAUSED, &dwc->flags);
+}
+
+static int dwc_resume(struct dma_chan *chan)
+{
+	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
+	unsigned long		flags;
+
+	spin_lock_irqsave(&dwc->lock, flags);
+
+	if (test_bit(DW_DMA_IS_PAUSED, &dwc->flags))
+		dwc_chan_resume(dwc);
+
+	spin_unlock_irqrestore(&dwc->lock, flags);
+
+	return 0;
+}
+
+static int dwc_terminate_all(struct dma_chan *chan)
+{
+	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
+	struct dw_dma		*dw = to_dw_dma(chan->device);
+	struct dw_desc		*desc, *_desc;
+	unsigned long		flags;
+	LIST_HEAD(list);
+
+	spin_lock_irqsave(&dwc->lock, flags);
+
+	clear_bit(DW_DMA_IS_SOFT_LLP, &dwc->flags);
+
+	dwc_chan_pause(dwc, true);
+
+	dwc_chan_disable(dw, dwc);
+
+	dwc_chan_resume(dwc);
+
+	/* active_list entries will end up before queued entries */
+	list_splice_init(&dwc->queue, &list);
+	list_splice_init(&dwc->active_list, &list);
+
+	spin_unlock_irqrestore(&dwc->lock, flags);
+
+	/* Flush all pending and queued descriptors */
+	list_for_each_entry_safe(desc, _desc, &list, desc_node)
+		dwc_descriptor_complete(dwc, desc, false);
+
+	return 0;
+}
+
+static struct dw_desc *dwc_find_desc(struct dw_dma_chan *dwc, dma_cookie_t c)
+{
+	struct dw_desc *desc;
+
+	list_for_each_entry(desc, &dwc->active_list, desc_node)
+		if (desc->txd.cookie == c)
+			return desc;
+
+	return NULL;
+}
+
+static u32 dwc_get_residue(struct dw_dma_chan *dwc, dma_cookie_t cookie)
+{
+	struct dw_desc *desc;
+	unsigned long flags;
+	u32 residue;
+
+	spin_lock_irqsave(&dwc->lock, flags);
+
+	desc = dwc_find_desc(dwc, cookie);
+	if (desc) {
+		if (desc == dwc_first_active(dwc)) {
+			residue = desc->residue;
+			if (test_bit(DW_DMA_IS_SOFT_LLP, &dwc->flags) && residue)
+				residue -= dwc_get_sent(dwc);
+		} else {
+			residue = desc->total_len;
+		}
+	} else {
+		residue = 0;
+	}
+
+	spin_unlock_irqrestore(&dwc->lock, flags);
+	return residue;
+}
+
+static enum dma_status
+dwc_tx_status(struct dma_chan *chan,
+	      dma_cookie_t cookie,
+	      struct dma_tx_state *txstate)
+{
+	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
+	enum dma_status		ret;
+
+	ret = dma_cookie_status(chan, cookie, txstate);
+	if (ret == DMA_COMPLETE)
+		return ret;
+
+	dwc_scan_descriptors(to_dw_dma(chan->device), dwc);
+
+	ret = dma_cookie_status(chan, cookie, txstate);
+	if (ret == DMA_COMPLETE)
+		return ret;
+
+	dma_set_residue(txstate, dwc_get_residue(dwc, cookie));
+
+	if (test_bit(DW_DMA_IS_PAUSED, &dwc->flags) && ret == DMA_IN_PROGRESS)
+		return DMA_PAUSED;
+
+	return ret;
+}
+
+static void dwc_issue_pending(struct dma_chan *chan)
+{
+	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
+	unsigned long		flags;
+
+	spin_lock_irqsave(&dwc->lock, flags);
+	if (list_empty(&dwc->active_list))
+		dwc_dostart_first_queued(dwc);
+	spin_unlock_irqrestore(&dwc->lock, flags);
+}
+
+/*----------------------------------------------------------------------*/
+
+/*
+ * Program FIFO size of channels.
+ *
+ * By default full FIFO (512 bytes) is assigned to channel 0. Here we
+ * slice FIFO on equal parts between channels.
+ */
+static void idma32_fifo_partition(struct dw_dma *dw)
+{
+	u64 value = IDMA32C_FP_PSIZE_CH0(64) | IDMA32C_FP_PSIZE_CH1(64) |
+		    IDMA32C_FP_UPDATE;
+	u64 fifo_partition = 0;
+
+	if (!dw->pdata->is_idma32)
+		return;
+
+	/* Fill FIFO_PARTITION low bits (Channels 0..1, 4..5) */
+	fifo_partition |= value << 0;
+
+	/* Fill FIFO_PARTITION high bits (Channels 2..3, 6..7) */
+	fifo_partition |= value << 32;
+
+	/* Program FIFO Partition registers - 64 bytes per channel */
+	idma32_writeq(dw, FIFO_PARTITION1, fifo_partition);
+	idma32_writeq(dw, FIFO_PARTITION0, fifo_partition);
+}
+
+static void dw_dma_off(struct dw_dma *dw)
+{
+	unsigned int i;
+
+	dma_writel(dw, CFG, 0);
+
+	channel_clear_bit(dw, MASK.XFER, dw->all_chan_mask);
+	channel_clear_bit(dw, MASK.BLOCK, dw->all_chan_mask);
+	channel_clear_bit(dw, MASK.SRC_TRAN, dw->all_chan_mask);
+	channel_clear_bit(dw, MASK.DST_TRAN, dw->all_chan_mask);
+	channel_clear_bit(dw, MASK.ERROR, dw->all_chan_mask);
+
+	while (dma_readl(dw, CFG) & DW_CFG_DMA_EN)
+		cpu_relax();
+
+	for (i = 0; i < dw->dma.chancnt; i++)
+		clear_bit(DW_DMA_IS_INITIALIZED, &dw->chan[i].flags);
+}
+
+static void dw_dma_on(struct dw_dma *dw)
+{
+	dma_writel(dw, CFG, DW_CFG_DMA_EN);
+}
+
+static int dwc_alloc_chan_resources(struct dma_chan *chan)
+{
+	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
+	struct dw_dma		*dw = to_dw_dma(chan->device);
+
+	dev_vdbg(chan2dev(chan), "%s\n", __func__);
+
+	/* ASSERT:  channel is idle */
+	if (dma_readl(dw, CH_EN) & dwc->mask) {
+		dev_dbg(chan2dev(chan), "DMA channel not idle?\n");
+		return -EIO;
+	}
+
+	dma_cookie_init(chan);
+
+	/*
+	 * NOTE: some controllers may have additional features that we
+	 * need to initialize here, like "scatter-gather" (which
+	 * doesn't mean what you think it means), and status writeback.
+	 */
+
+	/*
+	 * We need controller-specific data to set up slave transfers.
+	 */
+	if (chan->private && !dw_dma_filter(chan, chan->private)) {
+		dev_warn(chan2dev(chan), "Wrong controller-specific data\n");
+		return -EINVAL;
+	}
+
+	/* Enable controller here if needed */
+	if (!dw->in_use)
+		dw_dma_on(dw);
+	dw->in_use |= dwc->mask;
+
+	return 0;
+}
+
+static void dwc_free_chan_resources(struct dma_chan *chan)
+{
+	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
+	struct dw_dma		*dw = to_dw_dma(chan->device);
+	unsigned long		flags;
+	LIST_HEAD(list);
+
+	dev_dbg(chan2dev(chan), "%s: descs allocated=%u\n", __func__,
+			dwc->descs_allocated);
+
+	/* ASSERT:  channel is idle */
+	BUG_ON(!list_empty(&dwc->active_list));
+	BUG_ON(!list_empty(&dwc->queue));
+	BUG_ON(dma_readl(to_dw_dma(chan->device), CH_EN) & dwc->mask);
+
+	spin_lock_irqsave(&dwc->lock, flags);
+
+	/* Clear custom channel configuration */
+	memset(&dwc->dws, 0, sizeof(struct dw_dma_slave));
+
+	clear_bit(DW_DMA_IS_INITIALIZED, &dwc->flags);
+
+	/* Disable interrupts */
+	channel_clear_bit(dw, MASK.XFER, dwc->mask);
+	channel_clear_bit(dw, MASK.BLOCK, dwc->mask);
+	channel_clear_bit(dw, MASK.ERROR, dwc->mask);
+
+	spin_unlock_irqrestore(&dwc->lock, flags);
+
+	/* Disable controller in case it was a last user */
+	dw->in_use &= ~dwc->mask;
+	if (!dw->in_use)
+		dw_dma_off(dw);
+
+	dev_vdbg(chan2dev(chan), "%s: done\n", __func__);
+}
+
+int dw_dma_probe(struct dw_dma_chip *chip)
+{
+	struct dw_dma_platform_data *pdata;
+	struct dw_dma		*dw;
+	bool			autocfg = false;
+	unsigned int		dw_params;
+	unsigned int		i;
+	int			err;
+
+	dw = devm_kzalloc(chip->dev, sizeof(*dw), GFP_KERNEL);
+	if (!dw)
+		return -ENOMEM;
+
+	dw->pdata = devm_kzalloc(chip->dev, sizeof(*dw->pdata), GFP_KERNEL);
+	if (!dw->pdata)
+		return -ENOMEM;
+
+	dw->regs = chip->regs;
+	chip->dw = dw;
+
+	pm_runtime_get_sync(chip->dev);
+
+	if (!chip->pdata) {
+		dw_params = dma_readl(dw, DW_PARAMS);
+		dev_dbg(chip->dev, "DW_PARAMS: 0x%08x\n", dw_params);
+
+		autocfg = dw_params >> DW_PARAMS_EN & 1;
+		if (!autocfg) {
+			err = -EINVAL;
+			goto err_pdata;
+		}
+
+		/* Reassign the platform data pointer */
+		pdata = dw->pdata;
+
+		/* Get hardware configuration parameters */
+		pdata->nr_channels = (dw_params >> DW_PARAMS_NR_CHAN & 7) + 1;
+		pdata->nr_masters = (dw_params >> DW_PARAMS_NR_MASTER & 3) + 1;
+		for (i = 0; i < pdata->nr_masters; i++) {
+			pdata->data_width[i] =
+				4 << (dw_params >> DW_PARAMS_DATA_WIDTH(i) & 3);
+		}
+		pdata->block_size = dma_readl(dw, MAX_BLK_SIZE);
+
+		/* Fill platform data with the default values */
+		pdata->is_private = true;
+		pdata->is_memcpy = true;
+		pdata->chan_allocation_order = CHAN_ALLOCATION_ASCENDING;
+		pdata->chan_priority = CHAN_PRIORITY_ASCENDING;
+	} else if (chip->pdata->nr_channels > DW_DMA_MAX_NR_CHANNELS) {
+		err = -EINVAL;
+		goto err_pdata;
+	} else {
+		memcpy(dw->pdata, chip->pdata, sizeof(*dw->pdata));
+
+		/* Reassign the platform data pointer */
+		pdata = dw->pdata;
+	}
+
+	dw->chan = devm_kcalloc(chip->dev, pdata->nr_channels, sizeof(*dw->chan),
+				GFP_KERNEL);
+	if (!dw->chan) {
+		err = -ENOMEM;
+		goto err_pdata;
+	}
+
+	/* Calculate all channel mask before DMA setup */
+	dw->all_chan_mask = (1 << pdata->nr_channels) - 1;
+
+	/* Force dma off, just in case */
+	dw_dma_off(dw);
+
+	idma32_fifo_partition(dw);
+
+	/* Device and instance ID for IRQ and DMA pool */
+	if (pdata->is_idma32)
+		snprintf(dw->name, sizeof(dw->name), "idma32:dmac%d", chip->id);
+	else
+		snprintf(dw->name, sizeof(dw->name), "dw:dmac%d", chip->id);
+
+	/* Create a pool of consistent memory blocks for hardware descriptors */
+	dw->desc_pool = dmam_pool_create(dw->name, chip->dev,
+					 sizeof(struct dw_desc), 4, 0);
+	if (!dw->desc_pool) {
+		dev_err(chip->dev, "No memory for descriptors dma pool\n");
+		err = -ENOMEM;
+		goto err_pdata;
+	}
+
+	tasklet_init(&dw->tasklet, dw_dma_tasklet, (unsigned long)dw);
+
+	err = request_irq(chip->irq, dw_dma_interrupt, IRQF_SHARED,
+			  dw->name, dw);
+	if (err)
+		goto err_pdata;
+
+	INIT_LIST_HEAD(&dw->dma.channels);
+	for (i = 0; i < pdata->nr_channels; i++) {
+		struct dw_dma_chan	*dwc = &dw->chan[i];
+
+		dwc->chan.device = &dw->dma;
+		dma_cookie_init(&dwc->chan);
+		if (pdata->chan_allocation_order == CHAN_ALLOCATION_ASCENDING)
+			list_add_tail(&dwc->chan.device_node,
+					&dw->dma.channels);
+		else
+			list_add(&dwc->chan.device_node, &dw->dma.channels);
+
+		/* 7 is highest priority & 0 is lowest. */
+		if (pdata->chan_priority == CHAN_PRIORITY_ASCENDING)
+			dwc->priority = pdata->nr_channels - i - 1;
+		else
+			dwc->priority = i;
+
+		dwc->ch_regs = &__dw_regs(dw)->CHAN[i];
+		spin_lock_init(&dwc->lock);
+		dwc->mask = 1 << i;
+
+		INIT_LIST_HEAD(&dwc->active_list);
+		INIT_LIST_HEAD(&dwc->queue);
+
+		channel_clear_bit(dw, CH_EN, dwc->mask);
+
+		dwc->direction = DMA_TRANS_NONE;
+
+		/* Hardware configuration */
+		if (autocfg) {
+			unsigned int r = DW_DMA_MAX_NR_CHANNELS - i - 1;
+			void __iomem *addr = &__dw_regs(dw)->DWC_PARAMS[r];
+			unsigned int dwc_params = readl(addr);
+
+			dev_dbg(chip->dev, "DWC_PARAMS[%d]: 0x%08x\n", i,
+					   dwc_params);
+
+			/*
+			 * Decode maximum block size for given channel. The
+			 * stored 4 bit value represents blocks from 0x00 for 3
+			 * up to 0x0a for 4095.
+			 */
+			dwc->block_size =
+				(4 << ((pdata->block_size >> 4 * i) & 0xf)) - 1;
+			dwc->nollp =
+				(dwc_params >> DWC_PARAMS_MBLK_EN & 0x1) == 0;
+		} else {
+			dwc->block_size = pdata->block_size;
+			dwc->nollp = !pdata->multi_block[i];
+		}
+	}
+
+	/* Clear all interrupts on all channels. */
+	dma_writel(dw, CLEAR.XFER, dw->all_chan_mask);
+	dma_writel(dw, CLEAR.BLOCK, dw->all_chan_mask);
+	dma_writel(dw, CLEAR.SRC_TRAN, dw->all_chan_mask);
+	dma_writel(dw, CLEAR.DST_TRAN, dw->all_chan_mask);
+	dma_writel(dw, CLEAR.ERROR, dw->all_chan_mask);
+
+	/* Set capabilities */
+	dma_cap_set(DMA_SLAVE, dw->dma.cap_mask);
+	if (pdata->is_private)
+		dma_cap_set(DMA_PRIVATE, dw->dma.cap_mask);
+	if (pdata->is_memcpy)
+		dma_cap_set(DMA_MEMCPY, dw->dma.cap_mask);
+
+	dw->dma.dev = chip->dev;
+	dw->dma.device_alloc_chan_resources = dwc_alloc_chan_resources;
+	dw->dma.device_free_chan_resources = dwc_free_chan_resources;
+
+	dw->dma.device_prep_dma_memcpy = dwc_prep_dma_memcpy;
+	dw->dma.device_prep_slave_sg = dwc_prep_slave_sg;
+
+	dw->dma.device_config = dwc_config;
+	dw->dma.device_pause = dwc_pause;
+	dw->dma.device_resume = dwc_resume;
+	dw->dma.device_terminate_all = dwc_terminate_all;
+
+	dw->dma.device_tx_status = dwc_tx_status;
+	dw->dma.device_issue_pending = dwc_issue_pending;
+
+	/* DMA capabilities */
+	dw->dma.src_addr_widths = DW_DMA_BUSWIDTHS;
+	dw->dma.dst_addr_widths = DW_DMA_BUSWIDTHS;
+	dw->dma.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV) |
+			     BIT(DMA_MEM_TO_MEM);
+	dw->dma.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
+
+	err = dma_async_device_register(&dw->dma);
+	if (err)
+		goto err_dma_register;
+
+	dev_info(chip->dev, "DesignWare DMA Controller, %d channels\n",
+		 pdata->nr_channels);
+
+	pm_runtime_put_sync_suspend(chip->dev);
+
+	return 0;
+
+err_dma_register:
+	free_irq(chip->irq, dw);
+err_pdata:
+	pm_runtime_put_sync_suspend(chip->dev);
+	return err;
+}
+EXPORT_SYMBOL_GPL(dw_dma_probe);
+
+int dw_dma_remove(struct dw_dma_chip *chip)
+{
+	struct dw_dma		*dw = chip->dw;
+	struct dw_dma_chan	*dwc, *_dwc;
+
+	pm_runtime_get_sync(chip->dev);
+
+	dw_dma_off(dw);
+	dma_async_device_unregister(&dw->dma);
+
+	free_irq(chip->irq, dw);
+	tasklet_kill(&dw->tasklet);
+
+	list_for_each_entry_safe(dwc, _dwc, &dw->dma.channels,
+			chan.device_node) {
+		list_del(&dwc->chan.device_node);
+		channel_clear_bit(dw, CH_EN, dwc->mask);
+	}
+
+	pm_runtime_put_sync_suspend(chip->dev);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dw_dma_remove);
+
+int dw_dma_disable(struct dw_dma_chip *chip)
+{
+	struct dw_dma *dw = chip->dw;
+
+	dw_dma_off(dw);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dw_dma_disable);
+
+int dw_dma_enable(struct dw_dma_chip *chip)
+{
+	struct dw_dma *dw = chip->dw;
+
+	idma32_fifo_partition(dw);
+
+	dw_dma_on(dw);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dw_dma_enable);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Synopsys DesignWare DMA Controller core driver");
+MODULE_AUTHOR("Haavard Skinnemoen (Atmel)");
+MODULE_AUTHOR("Viresh Kumar <vireshk@kernel.org>");
diff --git a/drivers/dma/dw/internal.h b/drivers/dma/dw/internal.h
new file mode 100644
index 000000000..41439732f
--- /dev/null
+++ b/drivers/dma/dw/internal.h
@@ -0,0 +1,23 @@
+/*
+ * Driver for the Synopsys DesignWare DMA Controller
+ *
+ * Copyright (C) 2013 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _DMA_DW_INTERNAL_H
+#define _DMA_DW_INTERNAL_H
+
+#include <linux/dma/dw.h>
+
+#include "regs.h"
+
+int dw_dma_disable(struct dw_dma_chip *chip);
+int dw_dma_enable(struct dw_dma_chip *chip);
+
+extern bool dw_dma_filter(struct dma_chan *chan, void *param);
+
+#endif /* _DMA_DW_INTERNAL_H */
diff --git a/drivers/dma/dw/pci.c b/drivers/dma/dw/pci.c
new file mode 100644
index 000000000..7778ed705
--- /dev/null
+++ b/drivers/dma/dw/pci.c
@@ -0,0 +1,149 @@
+/*
+ * PCI driver for the Synopsys DesignWare DMA Controller
+ *
+ * Copyright (C) 2013 Intel Corporation
+ * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/device.h>
+
+#include "internal.h"
+
+static struct dw_dma_platform_data mrfld_pdata = {
+	.nr_channels = 8,
+	.is_private = true,
+	.is_memcpy = true,
+	.is_idma32 = true,
+	.chan_allocation_order = CHAN_ALLOCATION_ASCENDING,
+	.chan_priority = CHAN_PRIORITY_ASCENDING,
+	.block_size = 131071,
+	.nr_masters = 1,
+	.data_width = {4},
+};
+
+static int dw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *pid)
+{
+	const struct dw_dma_platform_data *pdata = (void *)pid->driver_data;
+	struct dw_dma_chip *chip;
+	int ret;
+
+	ret = pcim_enable_device(pdev);
+	if (ret)
+		return ret;
+
+	ret = pcim_iomap_regions(pdev, 1 << 0, pci_name(pdev));
+	if (ret) {
+		dev_err(&pdev->dev, "I/O memory remapping failed\n");
+		return ret;
+	}
+
+	pci_set_master(pdev);
+	pci_try_set_mwi(pdev);
+
+	ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+	if (ret)
+		return ret;
+
+	ret = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
+	if (ret)
+		return ret;
+
+	chip = devm_kzalloc(&pdev->dev, sizeof(*chip), GFP_KERNEL);
+	if (!chip)
+		return -ENOMEM;
+
+	chip->dev = &pdev->dev;
+	chip->id = pdev->devfn;
+	chip->regs = pcim_iomap_table(pdev)[0];
+	chip->irq = pdev->irq;
+	chip->pdata = pdata;
+
+	ret = dw_dma_probe(chip);
+	if (ret)
+		return ret;
+
+	pci_set_drvdata(pdev, chip);
+
+	return 0;
+}
+
+static void dw_pci_remove(struct pci_dev *pdev)
+{
+	struct dw_dma_chip *chip = pci_get_drvdata(pdev);
+	int ret;
+
+	ret = dw_dma_remove(chip);
+	if (ret)
+		dev_warn(&pdev->dev, "can't remove device properly: %d\n", ret);
+}
+
+#ifdef CONFIG_PM_SLEEP
+
+static int dw_pci_suspend_late(struct device *dev)
+{
+	struct pci_dev *pci = to_pci_dev(dev);
+	struct dw_dma_chip *chip = pci_get_drvdata(pci);
+
+	return dw_dma_disable(chip);
+};
+
+static int dw_pci_resume_early(struct device *dev)
+{
+	struct pci_dev *pci = to_pci_dev(dev);
+	struct dw_dma_chip *chip = pci_get_drvdata(pci);
+
+	return dw_dma_enable(chip);
+};
+
+#endif /* CONFIG_PM_SLEEP */
+
+static const struct dev_pm_ops dw_pci_dev_pm_ops = {
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(dw_pci_suspend_late, dw_pci_resume_early)
+};
+
+static const struct pci_device_id dw_pci_id_table[] = {
+	/* Medfield (GPDMA) */
+	{ PCI_VDEVICE(INTEL, 0x0827) },
+
+	/* BayTrail */
+	{ PCI_VDEVICE(INTEL, 0x0f06) },
+	{ PCI_VDEVICE(INTEL, 0x0f40) },
+
+	/* Merrifield iDMA 32-bit (GPDMA) */
+	{ PCI_VDEVICE(INTEL, 0x11a2), (kernel_ulong_t)&mrfld_pdata },
+
+	/* Braswell */
+	{ PCI_VDEVICE(INTEL, 0x2286) },
+	{ PCI_VDEVICE(INTEL, 0x22c0) },
+
+	/* Haswell */
+	{ PCI_VDEVICE(INTEL, 0x9c60) },
+
+	/* Broadwell */
+	{ PCI_VDEVICE(INTEL, 0x9ce0) },
+
+	{ }
+};
+MODULE_DEVICE_TABLE(pci, dw_pci_id_table);
+
+static struct pci_driver dw_pci_driver = {
+	.name		= "dw_dmac_pci",
+	.id_table	= dw_pci_id_table,
+	.probe		= dw_pci_probe,
+	.remove		= dw_pci_remove,
+	.driver	= {
+		.pm	= &dw_pci_dev_pm_ops,
+	},
+};
+
+module_pci_driver(dw_pci_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Synopsys DesignWare DMA Controller PCI driver");
+MODULE_AUTHOR("Andy Shevchenko <andriy.shevchenko@linux.intel.com>");
diff --git a/drivers/dma/dw/platform.c b/drivers/dma/dw/platform.c
new file mode 100644
index 000000000..62218ea08
--- /dev/null
+++ b/drivers/dma/dw/platform.c
@@ -0,0 +1,364 @@
+/*
+ * Platform driver for the Synopsys DesignWare DMA Controller
+ *
+ * Copyright (C) 2007-2008 Atmel Corporation
+ * Copyright (C) 2010-2011 ST Microelectronics
+ * Copyright (C) 2013 Intel Corporation
+ *
+ * Some parts of this driver are derived from the original dw_dmac.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/clk.h>
+#include <linux/pm_runtime.h>
+#include <linux/platform_device.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/of.h>
+#include <linux/of_dma.h>
+#include <linux/acpi.h>
+#include <linux/acpi_dma.h>
+
+#include "internal.h"
+
+#define DRV_NAME	"dw_dmac"
+
+static struct dma_chan *dw_dma_of_xlate(struct of_phandle_args *dma_spec,
+					struct of_dma *ofdma)
+{
+	struct dw_dma *dw = ofdma->of_dma_data;
+	struct dw_dma_slave slave = {
+		.dma_dev = dw->dma.dev,
+	};
+	dma_cap_mask_t cap;
+
+	if (dma_spec->args_count != 3)
+		return NULL;
+
+	slave.src_id = dma_spec->args[0];
+	slave.dst_id = dma_spec->args[0];
+	slave.m_master = dma_spec->args[1];
+	slave.p_master = dma_spec->args[2];
+
+	if (WARN_ON(slave.src_id >= DW_DMA_MAX_NR_REQUESTS ||
+		    slave.dst_id >= DW_DMA_MAX_NR_REQUESTS ||
+		    slave.m_master >= dw->pdata->nr_masters ||
+		    slave.p_master >= dw->pdata->nr_masters))
+		return NULL;
+
+	dma_cap_zero(cap);
+	dma_cap_set(DMA_SLAVE, cap);
+
+	/* TODO: there should be a simpler way to do this */
+	return dma_request_channel(cap, dw_dma_filter, &slave);
+}
+
+#ifdef CONFIG_ACPI
+static bool dw_dma_acpi_filter(struct dma_chan *chan, void *param)
+{
+	struct acpi_dma_spec *dma_spec = param;
+	struct dw_dma_slave slave = {
+		.dma_dev = dma_spec->dev,
+		.src_id = dma_spec->slave_id,
+		.dst_id = dma_spec->slave_id,
+		.m_master = 0,
+		.p_master = 1,
+	};
+
+	return dw_dma_filter(chan, &slave);
+}
+
+static void dw_dma_acpi_controller_register(struct dw_dma *dw)
+{
+	struct device *dev = dw->dma.dev;
+	struct acpi_dma_filter_info *info;
+	int ret;
+
+	info = devm_kzalloc(dev, sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return;
+
+	dma_cap_zero(info->dma_cap);
+	dma_cap_set(DMA_SLAVE, info->dma_cap);
+	info->filter_fn = dw_dma_acpi_filter;
+
+	ret = acpi_dma_controller_register(dev, acpi_dma_simple_xlate, info);
+	if (ret)
+		dev_err(dev, "could not register acpi_dma_controller\n");
+}
+
+static void dw_dma_acpi_controller_free(struct dw_dma *dw)
+{
+	struct device *dev = dw->dma.dev;
+
+	acpi_dma_controller_free(dev);
+}
+#else /* !CONFIG_ACPI */
+static inline void dw_dma_acpi_controller_register(struct dw_dma *dw) {}
+static inline void dw_dma_acpi_controller_free(struct dw_dma *dw) {}
+#endif /* !CONFIG_ACPI */
+
+#ifdef CONFIG_OF
+static struct dw_dma_platform_data *
+dw_dma_parse_dt(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct dw_dma_platform_data *pdata;
+	u32 tmp, arr[DW_DMA_MAX_NR_MASTERS], mb[DW_DMA_MAX_NR_CHANNELS];
+	u32 nr_masters;
+	u32 nr_channels;
+
+	if (!np) {
+		dev_err(&pdev->dev, "Missing DT data\n");
+		return NULL;
+	}
+
+	if (of_property_read_u32(np, "dma-masters", &nr_masters))
+		return NULL;
+	if (nr_masters < 1 || nr_masters > DW_DMA_MAX_NR_MASTERS)
+		return NULL;
+
+	if (of_property_read_u32(np, "dma-channels", &nr_channels))
+		return NULL;
+	if (nr_channels > DW_DMA_MAX_NR_CHANNELS)
+		return NULL;
+
+	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata)
+		return NULL;
+
+	pdata->nr_masters = nr_masters;
+	pdata->nr_channels = nr_channels;
+
+	if (of_property_read_bool(np, "is_private"))
+		pdata->is_private = true;
+
+	/*
+	 * All known devices, which use DT for configuration, support
+	 * memory-to-memory transfers. So enable it by default.
+	 */
+	pdata->is_memcpy = true;
+
+	if (!of_property_read_u32(np, "chan_allocation_order", &tmp))
+		pdata->chan_allocation_order = (unsigned char)tmp;
+
+	if (!of_property_read_u32(np, "chan_priority", &tmp))
+		pdata->chan_priority = tmp;
+
+	if (!of_property_read_u32(np, "block_size", &tmp))
+		pdata->block_size = tmp;
+
+	if (!of_property_read_u32_array(np, "data-width", arr, nr_masters)) {
+		for (tmp = 0; tmp < nr_masters; tmp++)
+			pdata->data_width[tmp] = arr[tmp];
+	} else if (!of_property_read_u32_array(np, "data_width", arr, nr_masters)) {
+		for (tmp = 0; tmp < nr_masters; tmp++)
+			pdata->data_width[tmp] = BIT(arr[tmp] & 0x07);
+	}
+
+	if (!of_property_read_u32_array(np, "multi-block", mb, nr_channels)) {
+		for (tmp = 0; tmp < nr_channels; tmp++)
+			pdata->multi_block[tmp] = mb[tmp];
+	} else {
+		for (tmp = 0; tmp < nr_channels; tmp++)
+			pdata->multi_block[tmp] = 1;
+	}
+
+	if (!of_property_read_u32(np, "snps,dma-protection-control", &tmp)) {
+		if (tmp > CHAN_PROTCTL_MASK)
+			return NULL;
+		pdata->protctl = tmp;
+	}
+
+	return pdata;
+}
+#else
+static inline struct dw_dma_platform_data *
+dw_dma_parse_dt(struct platform_device *pdev)
+{
+	return NULL;
+}
+#endif
+
+static int dw_probe(struct platform_device *pdev)
+{
+	struct dw_dma_chip *chip;
+	struct device *dev = &pdev->dev;
+	struct resource *mem;
+	const struct dw_dma_platform_data *pdata;
+	int err;
+
+	chip = devm_kzalloc(dev, sizeof(*chip), GFP_KERNEL);
+	if (!chip)
+		return -ENOMEM;
+
+	chip->irq = platform_get_irq(pdev, 0);
+	if (chip->irq < 0)
+		return chip->irq;
+
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	chip->regs = devm_ioremap_resource(dev, mem);
+	if (IS_ERR(chip->regs))
+		return PTR_ERR(chip->regs);
+
+	err = dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+	if (err)
+		return err;
+
+	pdata = dev_get_platdata(dev);
+	if (!pdata)
+		pdata = dw_dma_parse_dt(pdev);
+
+	chip->dev = dev;
+	chip->id = pdev->id;
+	chip->pdata = pdata;
+
+	chip->clk = devm_clk_get(chip->dev, "hclk");
+	if (IS_ERR(chip->clk))
+		return PTR_ERR(chip->clk);
+	err = clk_prepare_enable(chip->clk);
+	if (err)
+		return err;
+
+	pm_runtime_enable(&pdev->dev);
+
+	err = dw_dma_probe(chip);
+	if (err)
+		goto err_dw_dma_probe;
+
+	platform_set_drvdata(pdev, chip);
+
+	if (pdev->dev.of_node) {
+		err = of_dma_controller_register(pdev->dev.of_node,
+						 dw_dma_of_xlate, chip->dw);
+		if (err)
+			dev_err(&pdev->dev,
+				"could not register of_dma_controller\n");
+	}
+
+	if (ACPI_HANDLE(&pdev->dev))
+		dw_dma_acpi_controller_register(chip->dw);
+
+	return 0;
+
+err_dw_dma_probe:
+	pm_runtime_disable(&pdev->dev);
+	clk_disable_unprepare(chip->clk);
+	return err;
+}
+
+static int dw_remove(struct platform_device *pdev)
+{
+	struct dw_dma_chip *chip = platform_get_drvdata(pdev);
+
+	if (ACPI_HANDLE(&pdev->dev))
+		dw_dma_acpi_controller_free(chip->dw);
+
+	if (pdev->dev.of_node)
+		of_dma_controller_free(pdev->dev.of_node);
+
+	dw_dma_remove(chip);
+	pm_runtime_disable(&pdev->dev);
+	clk_disable_unprepare(chip->clk);
+
+	return 0;
+}
+
+static void dw_shutdown(struct platform_device *pdev)
+{
+	struct dw_dma_chip *chip = platform_get_drvdata(pdev);
+
+	/*
+	 * We have to call dw_dma_disable() to stop any ongoing transfer. On
+	 * some platforms we can't do that since DMA device is powered off.
+	 * Moreover we have no possibility to check if the platform is affected
+	 * or not. That's why we call pm_runtime_get_sync() / pm_runtime_put()
+	 * unconditionally. On the other hand we can't use
+	 * pm_runtime_suspended() because runtime PM framework is not fully
+	 * used by the driver.
+	 */
+	pm_runtime_get_sync(chip->dev);
+	dw_dma_disable(chip);
+	pm_runtime_put_sync_suspend(chip->dev);
+
+	clk_disable_unprepare(chip->clk);
+}
+
+#ifdef CONFIG_OF
+static const struct of_device_id dw_dma_of_id_table[] = {
+	{ .compatible = "snps,dma-spear1340" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, dw_dma_of_id_table);
+#endif
+
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id dw_dma_acpi_id_table[] = {
+	{ "INTL9C60", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(acpi, dw_dma_acpi_id_table);
+#endif
+
+#ifdef CONFIG_PM_SLEEP
+
+static int dw_suspend_late(struct device *dev)
+{
+	struct dw_dma_chip *chip = dev_get_drvdata(dev);
+
+	dw_dma_disable(chip);
+	clk_disable_unprepare(chip->clk);
+
+	return 0;
+}
+
+static int dw_resume_early(struct device *dev)
+{
+	struct dw_dma_chip *chip = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_prepare_enable(chip->clk);
+	if (ret)
+		return ret;
+
+	return dw_dma_enable(chip);
+}
+
+#endif /* CONFIG_PM_SLEEP */
+
+static const struct dev_pm_ops dw_dev_pm_ops = {
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(dw_suspend_late, dw_resume_early)
+};
+
+static struct platform_driver dw_driver = {
+	.probe		= dw_probe,
+	.remove		= dw_remove,
+	.shutdown       = dw_shutdown,
+	.driver = {
+		.name	= DRV_NAME,
+		.pm	= &dw_dev_pm_ops,
+		.of_match_table = of_match_ptr(dw_dma_of_id_table),
+		.acpi_match_table = ACPI_PTR(dw_dma_acpi_id_table),
+	},
+};
+
+static int __init dw_init(void)
+{
+	return platform_driver_register(&dw_driver);
+}
+subsys_initcall(dw_init);
+
+static void __exit dw_exit(void)
+{
+	platform_driver_unregister(&dw_driver);
+}
+module_exit(dw_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Synopsys DesignWare DMA Controller platform driver");
+MODULE_ALIAS("platform:" DRV_NAME);
diff --git a/drivers/dma/dw/regs.h b/drivers/dma/dw/regs.h
new file mode 100644
index 000000000..646c9c960
--- /dev/null
+++ b/drivers/dma/dw/regs.h
@@ -0,0 +1,384 @@
+/*
+ * Driver for the Synopsys DesignWare AHB DMA Controller
+ *
+ * Copyright (C) 2005-2007 Atmel Corporation
+ * Copyright (C) 2010-2011 ST Microelectronics
+ * Copyright (C) 2016 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/bitops.h>
+#include <linux/interrupt.h>
+#include <linux/dmaengine.h>
+
+#include <linux/io-64-nonatomic-hi-lo.h>
+
+#include "internal.h"
+
+#define DW_DMA_MAX_NR_REQUESTS	16
+
+/* flow controller */
+enum dw_dma_fc {
+	DW_DMA_FC_D_M2M,
+	DW_DMA_FC_D_M2P,
+	DW_DMA_FC_D_P2M,
+	DW_DMA_FC_D_P2P,
+	DW_DMA_FC_P_P2M,
+	DW_DMA_FC_SP_P2P,
+	DW_DMA_FC_P_M2P,
+	DW_DMA_FC_DP_P2P,
+};
+
+/*
+ * Redefine this macro to handle differences between 32- and 64-bit
+ * addressing, big vs. little endian, etc.
+ */
+#define DW_REG(name)		u32 name; u32 __pad_##name
+
+/* Hardware register definitions. */
+struct dw_dma_chan_regs {
+	DW_REG(SAR);		/* Source Address Register */
+	DW_REG(DAR);		/* Destination Address Register */
+	DW_REG(LLP);		/* Linked List Pointer */
+	u32	CTL_LO;		/* Control Register Low */
+	u32	CTL_HI;		/* Control Register High */
+	DW_REG(SSTAT);
+	DW_REG(DSTAT);
+	DW_REG(SSTATAR);
+	DW_REG(DSTATAR);
+	u32	CFG_LO;		/* Configuration Register Low */
+	u32	CFG_HI;		/* Configuration Register High */
+	DW_REG(SGR);
+	DW_REG(DSR);
+};
+
+struct dw_dma_irq_regs {
+	DW_REG(XFER);
+	DW_REG(BLOCK);
+	DW_REG(SRC_TRAN);
+	DW_REG(DST_TRAN);
+	DW_REG(ERROR);
+};
+
+struct dw_dma_regs {
+	/* per-channel registers */
+	struct dw_dma_chan_regs	CHAN[DW_DMA_MAX_NR_CHANNELS];
+
+	/* irq handling */
+	struct dw_dma_irq_regs	RAW;		/* r */
+	struct dw_dma_irq_regs	STATUS;		/* r (raw & mask) */
+	struct dw_dma_irq_regs	MASK;		/* rw (set = irq enabled) */
+	struct dw_dma_irq_regs	CLEAR;		/* w (ack, affects "raw") */
+
+	DW_REG(STATUS_INT);			/* r */
+
+	/* software handshaking */
+	DW_REG(REQ_SRC);
+	DW_REG(REQ_DST);
+	DW_REG(SGL_REQ_SRC);
+	DW_REG(SGL_REQ_DST);
+	DW_REG(LAST_SRC);
+	DW_REG(LAST_DST);
+
+	/* miscellaneous */
+	DW_REG(CFG);
+	DW_REG(CH_EN);
+	DW_REG(ID);
+	DW_REG(TEST);
+
+	/* iDMA 32-bit support */
+	DW_REG(CLASS_PRIORITY0);
+	DW_REG(CLASS_PRIORITY1);
+
+	/* optional encoded params, 0x3c8..0x3f7 */
+	u32	__reserved;
+
+	/* per-channel configuration registers */
+	u32	DWC_PARAMS[DW_DMA_MAX_NR_CHANNELS];
+	u32	MULTI_BLK_TYPE;
+	u32	MAX_BLK_SIZE;
+
+	/* top-level parameters */
+	u32	DW_PARAMS;
+
+	/* component ID */
+	u32	COMP_TYPE;
+	u32	COMP_VERSION;
+
+	/* iDMA 32-bit support */
+	DW_REG(FIFO_PARTITION0);
+	DW_REG(FIFO_PARTITION1);
+
+	DW_REG(SAI_ERR);
+	DW_REG(GLOBAL_CFG);
+};
+
+/* Bitfields in DW_PARAMS */
+#define DW_PARAMS_NR_CHAN	8		/* number of channels */
+#define DW_PARAMS_NR_MASTER	11		/* number of AHB masters */
+#define DW_PARAMS_DATA_WIDTH(n)	(15 + 2 * (n))
+#define DW_PARAMS_DATA_WIDTH1	15		/* master 1 data width */
+#define DW_PARAMS_DATA_WIDTH2	17		/* master 2 data width */
+#define DW_PARAMS_DATA_WIDTH3	19		/* master 3 data width */
+#define DW_PARAMS_DATA_WIDTH4	21		/* master 4 data width */
+#define DW_PARAMS_EN		28		/* encoded parameters */
+
+/* Bitfields in DWC_PARAMS */
+#define DWC_PARAMS_MBLK_EN	11		/* multi block transfer */
+
+/* bursts size */
+enum dw_dma_msize {
+	DW_DMA_MSIZE_1,
+	DW_DMA_MSIZE_4,
+	DW_DMA_MSIZE_8,
+	DW_DMA_MSIZE_16,
+	DW_DMA_MSIZE_32,
+	DW_DMA_MSIZE_64,
+	DW_DMA_MSIZE_128,
+	DW_DMA_MSIZE_256,
+};
+
+/* Bitfields in LLP */
+#define DWC_LLP_LMS(x)		((x) & 3)	/* list master select */
+#define DWC_LLP_LOC(x)		((x) & ~3)	/* next lli */
+
+/* Bitfields in CTL_LO */
+#define DWC_CTLL_INT_EN		(1 << 0)	/* irqs enabled? */
+#define DWC_CTLL_DST_WIDTH(n)	((n)<<1)	/* bytes per element */
+#define DWC_CTLL_SRC_WIDTH(n)	((n)<<4)
+#define DWC_CTLL_DST_INC	(0<<7)		/* DAR update/not */
+#define DWC_CTLL_DST_DEC	(1<<7)
+#define DWC_CTLL_DST_FIX	(2<<7)
+#define DWC_CTLL_SRC_INC	(0<<9)		/* SAR update/not */
+#define DWC_CTLL_SRC_DEC	(1<<9)
+#define DWC_CTLL_SRC_FIX	(2<<9)
+#define DWC_CTLL_DST_MSIZE(n)	((n)<<11)	/* burst, #elements */
+#define DWC_CTLL_SRC_MSIZE(n)	((n)<<14)
+#define DWC_CTLL_S_GATH_EN	(1 << 17)	/* src gather, !FIX */
+#define DWC_CTLL_D_SCAT_EN	(1 << 18)	/* dst scatter, !FIX */
+#define DWC_CTLL_FC(n)		((n) << 20)
+#define DWC_CTLL_FC_M2M		(0 << 20)	/* mem-to-mem */
+#define DWC_CTLL_FC_M2P		(1 << 20)	/* mem-to-periph */
+#define DWC_CTLL_FC_P2M		(2 << 20)	/* periph-to-mem */
+#define DWC_CTLL_FC_P2P		(3 << 20)	/* periph-to-periph */
+/* plus 4 transfer types for peripheral-as-flow-controller */
+#define DWC_CTLL_DMS(n)		((n)<<23)	/* dst master select */
+#define DWC_CTLL_SMS(n)		((n)<<25)	/* src master select */
+#define DWC_CTLL_LLP_D_EN	(1 << 27)	/* dest block chain */
+#define DWC_CTLL_LLP_S_EN	(1 << 28)	/* src block chain */
+
+/* Bitfields in CTL_HI */
+#define DWC_CTLH_BLOCK_TS_MASK	GENMASK(11, 0)
+#define DWC_CTLH_BLOCK_TS(x)	((x) & DWC_CTLH_BLOCK_TS_MASK)
+#define DWC_CTLH_DONE		(1 << 12)
+
+/* Bitfields in CFG_LO */
+#define DWC_CFGL_CH_PRIOR_MASK	(0x7 << 5)	/* priority mask */
+#define DWC_CFGL_CH_PRIOR(x)	((x) << 5)	/* priority */
+#define DWC_CFGL_CH_SUSP	(1 << 8)	/* pause xfer */
+#define DWC_CFGL_FIFO_EMPTY	(1 << 9)	/* pause xfer */
+#define DWC_CFGL_HS_DST		(1 << 10)	/* handshake w/dst */
+#define DWC_CFGL_HS_SRC		(1 << 11)	/* handshake w/src */
+#define DWC_CFGL_LOCK_CH_XFER	(0 << 12)	/* scope of LOCK_CH */
+#define DWC_CFGL_LOCK_CH_BLOCK	(1 << 12)
+#define DWC_CFGL_LOCK_CH_XACT	(2 << 12)
+#define DWC_CFGL_LOCK_BUS_XFER	(0 << 14)	/* scope of LOCK_BUS */
+#define DWC_CFGL_LOCK_BUS_BLOCK	(1 << 14)
+#define DWC_CFGL_LOCK_BUS_XACT	(2 << 14)
+#define DWC_CFGL_LOCK_CH	(1 << 15)	/* channel lockout */
+#define DWC_CFGL_LOCK_BUS	(1 << 16)	/* busmaster lockout */
+#define DWC_CFGL_HS_DST_POL	(1 << 18)	/* dst handshake active low */
+#define DWC_CFGL_HS_SRC_POL	(1 << 19)	/* src handshake active low */
+#define DWC_CFGL_MAX_BURST(x)	((x) << 20)
+#define DWC_CFGL_RELOAD_SAR	(1 << 30)
+#define DWC_CFGL_RELOAD_DAR	(1 << 31)
+
+/* Bitfields in CFG_HI */
+#define DWC_CFGH_FCMODE		(1 << 0)
+#define DWC_CFGH_FIFO_MODE	(1 << 1)
+#define DWC_CFGH_PROTCTL(x)	((x) << 2)
+#define DWC_CFGH_PROTCTL_DATA	(0 << 2)	/* data access - always set */
+#define DWC_CFGH_PROTCTL_PRIV	(1 << 2)	/* privileged -> AHB HPROT[1] */
+#define DWC_CFGH_PROTCTL_BUFFER	(2 << 2)	/* bufferable -> AHB HPROT[2] */
+#define DWC_CFGH_PROTCTL_CACHE	(4 << 2)	/* cacheable  -> AHB HPROT[3] */
+#define DWC_CFGH_DS_UPD_EN	(1 << 5)
+#define DWC_CFGH_SS_UPD_EN	(1 << 6)
+#define DWC_CFGH_SRC_PER(x)	((x) << 7)
+#define DWC_CFGH_DST_PER(x)	((x) << 11)
+
+/* Bitfields in SGR */
+#define DWC_SGR_SGI(x)		((x) << 0)
+#define DWC_SGR_SGC(x)		((x) << 20)
+
+/* Bitfields in DSR */
+#define DWC_DSR_DSI(x)		((x) << 0)
+#define DWC_DSR_DSC(x)		((x) << 20)
+
+/* Bitfields in CFG */
+#define DW_CFG_DMA_EN		(1 << 0)
+
+/* iDMA 32-bit support */
+
+/* Bitfields in CTL_HI */
+#define IDMA32C_CTLH_BLOCK_TS_MASK	GENMASK(16, 0)
+#define IDMA32C_CTLH_BLOCK_TS(x)	((x) & IDMA32C_CTLH_BLOCK_TS_MASK)
+#define IDMA32C_CTLH_DONE		(1 << 17)
+
+/* Bitfields in CFG_LO */
+#define IDMA32C_CFGL_DST_BURST_ALIGN	(1 << 0)	/* dst burst align */
+#define IDMA32C_CFGL_SRC_BURST_ALIGN	(1 << 1)	/* src burst align */
+#define IDMA32C_CFGL_CH_DRAIN		(1 << 10)	/* drain FIFO */
+#define IDMA32C_CFGL_DST_OPT_BL		(1 << 20)	/* optimize dst burst length */
+#define IDMA32C_CFGL_SRC_OPT_BL		(1 << 21)	/* optimize src burst length */
+
+/* Bitfields in CFG_HI */
+#define IDMA32C_CFGH_SRC_PER(x)		((x) << 0)
+#define IDMA32C_CFGH_DST_PER(x)		((x) << 4)
+#define IDMA32C_CFGH_RD_ISSUE_THD(x)	((x) << 8)
+#define IDMA32C_CFGH_RW_ISSUE_THD(x)	((x) << 18)
+#define IDMA32C_CFGH_SRC_PER_EXT(x)	((x) << 28)	/* src peripheral extension */
+#define IDMA32C_CFGH_DST_PER_EXT(x)	((x) << 30)	/* dst peripheral extension */
+
+/* Bitfields in FIFO_PARTITION */
+#define IDMA32C_FP_PSIZE_CH0(x)		((x) << 0)
+#define IDMA32C_FP_PSIZE_CH1(x)		((x) << 13)
+#define IDMA32C_FP_UPDATE		(1 << 26)
+
+enum dw_dmac_flags {
+	DW_DMA_IS_CYCLIC = 0,
+	DW_DMA_IS_SOFT_LLP = 1,
+	DW_DMA_IS_PAUSED = 2,
+	DW_DMA_IS_INITIALIZED = 3,
+};
+
+struct dw_dma_chan {
+	struct dma_chan			chan;
+	void __iomem			*ch_regs;
+	u8				mask;
+	u8				priority;
+	enum dma_transfer_direction	direction;
+
+	/* software emulation of the LLP transfers */
+	struct list_head	*tx_node_active;
+
+	spinlock_t		lock;
+
+	/* these other elements are all protected by lock */
+	unsigned long		flags;
+	struct list_head	active_list;
+	struct list_head	queue;
+
+	unsigned int		descs_allocated;
+
+	/* hardware configuration */
+	unsigned int		block_size;
+	bool			nollp;
+
+	/* custom slave configuration */
+	struct dw_dma_slave	dws;
+
+	/* configuration passed via .device_config */
+	struct dma_slave_config dma_sconfig;
+};
+
+static inline struct dw_dma_chan_regs __iomem *
+__dwc_regs(struct dw_dma_chan *dwc)
+{
+	return dwc->ch_regs;
+}
+
+#define channel_readl(dwc, name) \
+	readl(&(__dwc_regs(dwc)->name))
+#define channel_writel(dwc, name, val) \
+	writel((val), &(__dwc_regs(dwc)->name))
+
+static inline struct dw_dma_chan *to_dw_dma_chan(struct dma_chan *chan)
+{
+	return container_of(chan, struct dw_dma_chan, chan);
+}
+
+struct dw_dma {
+	struct dma_device	dma;
+	char			name[20];
+	void __iomem		*regs;
+	struct dma_pool		*desc_pool;
+	struct tasklet_struct	tasklet;
+
+	/* channels */
+	struct dw_dma_chan	*chan;
+	u8			all_chan_mask;
+	u8			in_use;
+
+	/* platform data */
+	struct dw_dma_platform_data	*pdata;
+};
+
+static inline struct dw_dma_regs __iomem *__dw_regs(struct dw_dma *dw)
+{
+	return dw->regs;
+}
+
+#define dma_readl(dw, name) \
+	readl(&(__dw_regs(dw)->name))
+#define dma_writel(dw, name, val) \
+	writel((val), &(__dw_regs(dw)->name))
+
+#define idma32_readq(dw, name)				\
+	hi_lo_readq(&(__dw_regs(dw)->name))
+#define idma32_writeq(dw, name, val)			\
+	hi_lo_writeq((val), &(__dw_regs(dw)->name))
+
+#define channel_set_bit(dw, reg, mask) \
+	dma_writel(dw, reg, ((mask) << 8) | (mask))
+#define channel_clear_bit(dw, reg, mask) \
+	dma_writel(dw, reg, ((mask) << 8) | 0)
+
+static inline struct dw_dma *to_dw_dma(struct dma_device *ddev)
+{
+	return container_of(ddev, struct dw_dma, dma);
+}
+
+/* LLI == Linked List Item; a.k.a. DMA block descriptor */
+struct dw_lli {
+	/* values that are not changed by hardware */
+	__le32		sar;
+	__le32		dar;
+	__le32		llp;		/* chain to next lli */
+	__le32		ctllo;
+	/* values that may get written back: */
+	__le32		ctlhi;
+	/* sstat and dstat can snapshot peripheral register state.
+	 * silicon config may discard either or both...
+	 */
+	__le32		sstat;
+	__le32		dstat;
+};
+
+struct dw_desc {
+	/* FIRST values the hardware uses */
+	struct dw_lli			lli;
+
+#define lli_set(d, reg, v)		((d)->lli.reg |= cpu_to_le32(v))
+#define lli_clear(d, reg, v)		((d)->lli.reg &= ~cpu_to_le32(v))
+#define lli_read(d, reg)		le32_to_cpu((d)->lli.reg)
+#define lli_write(d, reg, v)		((d)->lli.reg = cpu_to_le32(v))
+
+	/* THEN values for driver housekeeping */
+	struct list_head		desc_node;
+	struct list_head		tx_list;
+	struct dma_async_tx_descriptor	txd;
+	size_t				len;
+	size_t				total_len;
+	u32				residue;
+};
+
+#define to_dw_desc(h)	list_entry(h, struct dw_desc, desc_node)
+
+static inline struct dw_desc *
+txd_to_dw_desc(struct dma_async_tx_descriptor *txd)
+{
+	return container_of(txd, struct dw_desc, txd);
+}