Merge branch 'amd-iommu/2.6.32' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/linux-2.6-iommu into core/iommu

8 files changed, 1608 insertions, 12 deletions

diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 070357aaedb..81e1020fb51 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -4,7 +4,7 @@
 
 menuconfig DMADEVICES
 	bool "DMA Engine support"
-	depends on !HIGHMEM64G && HAS_DMA
+	depends on HAS_DMA
 	help
 	  DMA engines can do asynchronous data transfers without
 	  involving the host CPU.  Currently, this framework can be
@@ -46,6 +46,14 @@ config DW_DMAC
 	  Support the Synopsys DesignWare AHB DMA controller.  This
 	  can be integrated in chips such as the Atmel AT32ap7000.
 
+config AT_HDMAC
+	tristate "Atmel AHB DMA support"
+	depends on ARCH_AT91SAM9RL
+	select DMA_ENGINE
+	help
+	  Support the Atmel AHB DMA controller.  This can be integrated in
+	  chips such as the Atmel AT91SAM9RL.
+
 config FSL_DMA
 	tristate "Freescale Elo and Elo Plus DMA support"
 	depends on FSL_SOC
@@ -108,7 +116,7 @@ config NET_DMA
 
 config ASYNC_TX_DMA
 	bool "Async_tx: Offload support for the async_tx api"
-	depends on DMA_ENGINE
+	depends on DMA_ENGINE && !HIGHMEM64G
 	help
 	  This allows the async_tx api to take advantage of offload engines for
 	  memcpy, memset, xor, and raid6 p+q operations.  If your platform has
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index a0b6564800c..40e1e008357 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -7,5 +7,6 @@ obj-$(CONFIG_INTEL_IOP_ADMA) += iop-adma.o
 obj-$(CONFIG_FSL_DMA) += fsldma.o
 obj-$(CONFIG_MV_XOR) += mv_xor.o
 obj-$(CONFIG_DW_DMAC) += dw_dmac.o
+obj-$(CONFIG_AT_HDMAC) += at_hdmac.o
 obj-$(CONFIG_MX3_IPU) += ipu/
 obj-$(CONFIG_TXX9_DMAC) += txx9dmac.o
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
new file mode 100644
index 00000000000..9a1e5fb412e
--- /dev/null
+++ b/drivers/dma/at_hdmac.c
@@ -0,0 +1,1213 @@
+/*
+ * Driver for the Atmel AHB DMA Controller (aka HDMA or DMAC on AT91 systems)
+ *
+ * Copyright (C) 2008 Atmel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ *
+ * This supports the Atmel AHB DMA Controller,
+ *
+ * The driver has currently been tested with the Atmel AT91SAM9RL
+ * and AT91SAM9G45 series.
+ */
+
+#include <linux/clk.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+
+#include "at_hdmac_regs.h"
+
+/*
+ * Glossary
+ * --------
+ *
+ * at_hdmac		: Name of the ATmel AHB DMA Controller
+ * at_dma_ / atdma	: ATmel DMA controller entity related
+ * atc_	/ atchan	: ATmel DMA Channel entity related
+ */
+
+#define	ATC_DEFAULT_CFG		(ATC_FIFOCFG_HALFFIFO)
+#define	ATC_DEFAULT_CTRLA	(0)
+#define	ATC_DEFAULT_CTRLB	(ATC_SIF(0)	\
+				|ATC_DIF(1))
+
+/*
+ * Initial number of descriptors to allocate for each channel. This could
+ * be increased during dma usage.
+ */
+static unsigned int init_nr_desc_per_channel = 64;
+module_param(init_nr_desc_per_channel, uint, 0644);
+MODULE_PARM_DESC(init_nr_desc_per_channel,
+		 "initial descriptors per channel (default: 64)");
+
+
+/* prototypes */
+static dma_cookie_t atc_tx_submit(struct dma_async_tx_descriptor *tx);
+
+
+/*----------------------------------------------------------------------*/
+
+static struct at_desc *atc_first_active(struct at_dma_chan *atchan)
+{
+	return list_first_entry(&atchan->active_list,
+				struct at_desc, desc_node);
+}
+
+static struct at_desc *atc_first_queued(struct at_dma_chan *atchan)
+{
+	return list_first_entry(&atchan->queue,
+				struct at_desc, desc_node);
+}
+
+/**
+ * atc_alloc_descriptor - allocate and return an initilized descriptor
+ * @chan: the channel to allocate descriptors for
+ * @gfp_flags: GFP allocation flags
+ *
+ * Note: The ack-bit is positioned in the descriptor flag at creation time
+ *       to make initial allocation more convenient. This bit will be cleared
+ *       and control will be given to client at usage time (during
+ *       preparation functions).
+ */
+static struct at_desc *atc_alloc_descriptor(struct dma_chan *chan,
+					    gfp_t gfp_flags)
+{
+	struct at_desc	*desc = NULL;
+	struct at_dma	*atdma = to_at_dma(chan->device);
+	dma_addr_t phys;
+
+	desc = dma_pool_alloc(atdma->dma_desc_pool, gfp_flags, &phys);
+	if (desc) {
+		memset(desc, 0, sizeof(struct at_desc));
+		dma_async_tx_descriptor_init(&desc->txd, chan);
+		/* txd.flags will be overwritten in prep functions */
+		desc->txd.flags = DMA_CTRL_ACK;
+		desc->txd.tx_submit = atc_tx_submit;
+		desc->txd.phys = phys;
+	}
+
+	return desc;
+}
+
+/**
+ * atc_desc_get - get a unsused descriptor from free_list
+ * @atchan: channel we want a new descriptor for
+ */
+static struct at_desc *atc_desc_get(struct at_dma_chan *atchan)
+{
+	struct at_desc *desc, *_desc;
+	struct at_desc *ret = NULL;
+	unsigned int i = 0;
+	LIST_HEAD(tmp_list);
+
+	spin_lock_bh(&atchan->lock);
+	list_for_each_entry_safe(desc, _desc, &atchan->free_list, desc_node) {
+		i++;
+		if (async_tx_test_ack(&desc->txd)) {
+			list_del(&desc->desc_node);
+			ret = desc;
+			break;
+		}
+		dev_dbg(chan2dev(&atchan->chan_common),
+				"desc %p not ACKed\n", desc);
+	}
+	spin_unlock_bh(&atchan->lock);
+	dev_vdbg(chan2dev(&atchan->chan_common),
+		"scanned %u descriptors on freelist\n", i);
+
+	/* no more descriptor available in initial pool: create one more */
+	if (!ret) {
+		ret = atc_alloc_descriptor(&atchan->chan_common, GFP_ATOMIC);
+		if (ret) {
+			spin_lock_bh(&atchan->lock);
+			atchan->descs_allocated++;
+			spin_unlock_bh(&atchan->lock);
+		} else {
+			dev_err(chan2dev(&atchan->chan_common),
+					"not enough descriptors available\n");
+		}
+	}
+
+	return ret;
+}
+
+/**
+ * atc_desc_put - move a descriptor, including any children, to the free list
+ * @atchan: channel we work on
+ * @desc: descriptor, at the head of a chain, to move to free list
+ */
+static void atc_desc_put(struct at_dma_chan *atchan, struct at_desc *desc)
+{
+	if (desc) {
+		struct at_desc *child;
+
+		spin_lock_bh(&atchan->lock);
+		list_for_each_entry(child, &desc->txd.tx_list, desc_node)
+			dev_vdbg(chan2dev(&atchan->chan_common),
+					"moving child desc %p to freelist\n",
+					child);
+		list_splice_init(&desc->txd.tx_list, &atchan->free_list);
+		dev_vdbg(chan2dev(&atchan->chan_common),
+			 "moving desc %p to freelist\n", desc);
+		list_add(&desc->desc_node, &atchan->free_list);
+		spin_unlock_bh(&atchan->lock);
+	}
+}
+
+/**
+ * atc_assign_cookie - compute and assign new cookie
+ * @atchan: channel we work on
+ * @desc: descriptor to asign cookie for
+ *
+ * Called with atchan->lock held and bh disabled
+ */
+static dma_cookie_t
+atc_assign_cookie(struct at_dma_chan *atchan, struct at_desc *desc)
+{
+	dma_cookie_t cookie = atchan->chan_common.cookie;
+
+	if (++cookie < 0)
+		cookie = 1;
+
+	atchan->chan_common.cookie = cookie;
+	desc->txd.cookie = cookie;
+
+	return cookie;
+}
+
+/**
+ * atc_dostart - starts the DMA engine for real
+ * @atchan: the channel we want to start
+ * @first: first descriptor in the list we want to begin with
+ *
+ * Called with atchan->lock held and bh disabled
+ */
+static void atc_dostart(struct at_dma_chan *atchan, struct at_desc *first)
+{
+	struct at_dma	*atdma = to_at_dma(atchan->chan_common.device);
+
+	/* ASSERT:  channel is idle */
+	if (atc_chan_is_enabled(atchan)) {
+		dev_err(chan2dev(&atchan->chan_common),
+			"BUG: Attempted to start non-idle channel\n");
+		dev_err(chan2dev(&atchan->chan_common),
+			"  channel: s0x%x d0x%x ctrl0x%x:0x%x l0x%x\n",
+			channel_readl(atchan, SADDR),
+			channel_readl(atchan, DADDR),
+			channel_readl(atchan, CTRLA),
+			channel_readl(atchan, CTRLB),
+			channel_readl(atchan, DSCR));
+
+		/* The tasklet will hopefully advance the queue... */
+		return;
+	}
+
+	vdbg_dump_regs(atchan);
+
+	/* clear any pending interrupt */
+	while (dma_readl(atdma, EBCISR))
+		cpu_relax();
+
+	channel_writel(atchan, SADDR, 0);
+	channel_writel(atchan, DADDR, 0);
+	channel_writel(atchan, CTRLA, 0);
+	channel_writel(atchan, CTRLB, 0);
+	channel_writel(atchan, DSCR, first->txd.phys);
+	dma_writel(atdma, CHER, atchan->mask);
+
+	vdbg_dump_regs(atchan);
+}
+
+/**
+ * atc_chain_complete - finish work for one transaction chain
+ * @atchan: channel we work on
+ * @desc: descriptor at the head of the chain we want do complete
+ *
+ * Called with atchan->lock held and bh disabled */
+static void
+atc_chain_complete(struct at_dma_chan *atchan, struct at_desc *desc)
+{
+	dma_async_tx_callback		callback;
+	void				*param;
+	struct dma_async_tx_descriptor	*txd = &desc->txd;
+
+	dev_vdbg(chan2dev(&atchan->chan_common),
+		"descriptor %u complete\n", txd->cookie);
+
+	atchan->completed_cookie = txd->cookie;
+	callback = txd->callback;
+	param = txd->callback_param;
+
+	/* move children to free_list */
+	list_splice_init(&txd->tx_list, &atchan->free_list);
+	/* move myself to free_list */
+	list_move(&desc->desc_node, &atchan->free_list);
+
+	/* unmap dma addresses */
+	if (!(txd->flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
+		if (txd->flags & DMA_COMPL_DEST_UNMAP_SINGLE)
+			dma_unmap_single(chan2parent(&atchan->chan_common),
+					desc->lli.daddr,
+					desc->len, DMA_FROM_DEVICE);
+		else
+			dma_unmap_page(chan2parent(&atchan->chan_common),
+					desc->lli.daddr,
+					desc->len, DMA_FROM_DEVICE);
+	}
+	if (!(txd->flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
+		if (txd->flags & DMA_COMPL_SRC_UNMAP_SINGLE)
+			dma_unmap_single(chan2parent(&atchan->chan_common),
+					desc->lli.saddr,
+					desc->len, DMA_TO_DEVICE);
+		else
+			dma_unmap_page(chan2parent(&atchan->chan_common),
+					desc->lli.saddr,
+					desc->len, DMA_TO_DEVICE);
+	}
+
+	/*
+	 * The API requires that no submissions are done from a
+	 * callback, so we don't need to drop the lock here
+	 */
+	if (callback)
+		callback(param);
+
+	dma_run_dependencies(txd);
+}
+
+/**
+ * atc_complete_all - finish work for all transactions
+ * @atchan: channel to complete transactions for
+ *
+ * Eventually submit queued descriptors if any
+ *
+ * Assume channel is idle while calling this function
+ * Called with atchan->lock held and bh disabled
+ */
+static void atc_complete_all(struct at_dma_chan *atchan)
+{
+	struct at_desc *desc, *_desc;
+	LIST_HEAD(list);
+
+	dev_vdbg(chan2dev(&atchan->chan_common), "complete all\n");
+
+	BUG_ON(atc_chan_is_enabled(atchan));
+
+	/*
+	 * Submit queued descriptors ASAP, i.e. before we go through
+	 * the completed ones.
+	 */
+	if (!list_empty(&atchan->queue))
+		atc_dostart(atchan, atc_first_queued(atchan));
+	/* empty active_list now it is completed */
+	list_splice_init(&atchan->active_list, &list);
+	/* empty queue list by moving descriptors (if any) to active_list */
+	list_splice_init(&atchan->queue, &atchan->active_list);
+
+	list_for_each_entry_safe(desc, _desc, &list, desc_node)
+		atc_chain_complete(atchan, desc);
+}
+
+/**
+ * atc_cleanup_descriptors - cleanup up finished descriptors in active_list
+ * @atchan: channel to be cleaned up
+ *
+ * Called with atchan->lock held and bh disabled
+ */
+static void atc_cleanup_descriptors(struct at_dma_chan *atchan)
+{
+	struct at_desc	*desc, *_desc;
+	struct at_desc	*child;
+
+	dev_vdbg(chan2dev(&atchan->chan_common), "cleanup descriptors\n");
+
+	list_for_each_entry_safe(desc, _desc, &atchan->active_list, desc_node) {
+		if (!(desc->lli.ctrla & ATC_DONE))
+			/* This one is currently in progress */
+			return;
+
+		list_for_each_entry(child, &desc->txd.tx_list, desc_node)
+			if (!(child->lli.ctrla & ATC_DONE))
+				/* Currently in progress */
+				return;
+
+		/*
+		 * No descriptors so far seem to be in progress, i.e.
+		 * this chain must be done.
+		 */
+		atc_chain_complete(atchan, desc);
+	}
+}
+
+/**
+ * atc_advance_work - at the end of a transaction, move forward
+ * @atchan: channel where the transaction ended
+ *
+ * Called with atchan->lock held and bh disabled
+ */
+static void atc_advance_work(struct at_dma_chan *atchan)
+{
+	dev_vdbg(chan2dev(&atchan->chan_common), "advance_work\n");
+
+	if (list_empty(&atchan->active_list) ||
+	    list_is_singular(&atchan->active_list)) {
+		atc_complete_all(atchan);
+	} else {
+		atc_chain_complete(atchan, atc_first_active(atchan));
+		/* advance work */
+		atc_dostart(atchan, atc_first_active(atchan));
+	}
+}
+
+
+/**
+ * atc_handle_error - handle errors reported by DMA controller
+ * @atchan: channel where error occurs
+ *
+ * Called with atchan->lock held and bh disabled
+ */
+static void atc_handle_error(struct at_dma_chan *atchan)
+{
+	struct at_desc *bad_desc;
+	struct at_desc *child;
+
+	/*
+	 * The descriptor currently at the head of the active list is
+	 * broked. Since we don't have any way to report errors, we'll
+	 * just have to scream loudly and try to carry on.
+	 */
+	bad_desc = atc_first_active(atchan);
+	list_del_init(&bad_desc->desc_node);
+
+	/* As we are stopped, take advantage to push queued descriptors
+	 * in active_list */
+	list_splice_init(&atchan->queue, atchan->active_list.prev);
+
+	/* Try to restart the controller */
+	if (!list_empty(&atchan->active_list))
+		atc_dostart(atchan, atc_first_active(atchan));
+
+	/*
+	 * KERN_CRITICAL 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_crit(chan2dev(&atchan->chan_common),
+			"Bad descriptor submitted for DMA!\n");
+	dev_crit(chan2dev(&atchan->chan_common),
+			"  cookie: %d\n", bad_desc->txd.cookie);
+	atc_dump_lli(atchan, &bad_desc->lli);
+	list_for_each_entry(child, &bad_desc->txd.tx_list, desc_node)
+		atc_dump_lli(atchan, &child->lli);
+
+	/* Pretend the descriptor completed successfully */
+	atc_chain_complete(atchan, bad_desc);
+}
+
+
+/*--  IRQ & Tasklet  ---------------------------------------------------*/
+
+static void atc_tasklet(unsigned long data)
+{
+	struct at_dma_chan *atchan = (struct at_dma_chan *)data;
+
+	/* Channel cannot be enabled here */
+	if (atc_chan_is_enabled(atchan)) {
+		dev_err(chan2dev(&atchan->chan_common),
+			"BUG: channel enabled in tasklet\n");
+		return;
+	}
+
+	spin_lock(&atchan->lock);
+	if (test_and_clear_bit(0, &atchan->error_status))
+		atc_handle_error(atchan);
+	else
+		atc_advance_work(atchan);
+
+	spin_unlock(&atchan->lock);
+}
+
+static irqreturn_t at_dma_interrupt(int irq, void *dev_id)
+{
+	struct at_dma		*atdma = (struct at_dma *)dev_id;
+	struct at_dma_chan	*atchan;
+	int			i;
+	u32			status, pending, imr;
+	int			ret = IRQ_NONE;
+
+	do {
+		imr = dma_readl(atdma, EBCIMR);
+		status = dma_readl(atdma, EBCISR);
+		pending = status & imr;
+
+		if (!pending)
+			break;
+
+		dev_vdbg(atdma->dma_common.dev,
+			"interrupt: status = 0x%08x, 0x%08x, 0x%08x\n",
+			 status, imr, pending);
+
+		for (i = 0; i < atdma->dma_common.chancnt; i++) {
+			atchan = &atdma->chan[i];
+			if (pending & (AT_DMA_CBTC(i) | AT_DMA_ERR(i))) {
+				if (pending & AT_DMA_ERR(i)) {
+					/* Disable channel on AHB error */
+					dma_writel(atdma, CHDR, atchan->mask);
+					/* Give information to tasklet */
+					set_bit(0, &atchan->error_status);
+				}
+				tasklet_schedule(&atchan->tasklet);
+				ret = IRQ_HANDLED;
+			}
+		}
+
+	} while (pending);
+
+	return ret;
+}
+
+
+/*--  DMA Engine API  --------------------------------------------------*/
+
+/**
+ * atc_tx_submit - set the prepared descriptor(s) to be executed by the engine
+ * @desc: descriptor at the head of the transaction chain
+ *
+ * Queue chain if DMA engine is working already
+ *
+ * Cookie increment and adding to active_list or queue must be atomic
+ */
+static dma_cookie_t atc_tx_submit(struct dma_async_tx_descriptor *tx)
+{
+	struct at_desc		*desc = txd_to_at_desc(tx);
+	struct at_dma_chan	*atchan = to_at_dma_chan(tx->chan);
+	dma_cookie_t		cookie;
+
+	spin_lock_bh(&atchan->lock);
+	cookie = atc_assign_cookie(atchan, desc);
+
+	if (list_empty(&atchan->active_list)) {
+		dev_vdbg(chan2dev(tx->chan), "tx_submit: started %u\n",
+				desc->txd.cookie);
+		atc_dostart(atchan, desc);
+		list_add_tail(&desc->desc_node, &atchan->active_list);
+	} else {
+		dev_vdbg(chan2dev(tx->chan), "tx_submit: queued %u\n",
+				desc->txd.cookie);
+		list_add_tail(&desc->desc_node, &atchan->queue);
+	}
+
+	spin_unlock_bh(&atchan->lock);
+
+	return cookie;
+}
+
+/**
+ * atc_prep_dma_memcpy - prepare a memcpy operation
+ * @chan: the channel to prepare operation on
+ * @dest: operation virtual destination address
+ * @src: operation virtual source address
+ * @len: operation length
+ * @flags: tx descriptor status flags
+ */
+static struct dma_async_tx_descriptor *
+atc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
+		size_t len, unsigned long flags)
+{
+	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
+	struct at_desc		*desc = NULL;
+	struct at_desc		*first = NULL;
+	struct at_desc		*prev = NULL;
+	size_t			xfer_count;
+	size_t			offset;
+	unsigned int		src_width;
+	unsigned int		dst_width;
+	u32			ctrla;
+	u32			ctrlb;
+
+	dev_vdbg(chan2dev(chan), "prep_dma_memcpy: d0x%x s0x%x l0x%zx f0x%lx\n",
+			dest, src, len, flags);
+
+	if (unlikely(!len)) {
+		dev_dbg(chan2dev(chan), "prep_dma_memcpy: length is zero!\n");
+		return NULL;
+	}
+
+	ctrla =   ATC_DEFAULT_CTRLA;
+	ctrlb =   ATC_DEFAULT_CTRLB
+		| ATC_SRC_ADDR_MODE_INCR
+		| ATC_DST_ADDR_MODE_INCR
+		| ATC_FC_MEM2MEM;
+
+	/*
+	 * We can be a lot more clever here, but this should take care
+	 * of the most common optimization.
+	 */
+	if (!((src | dest  | len) & 3)) {
+		ctrla |= ATC_SRC_WIDTH_WORD | ATC_DST_WIDTH_WORD;
+		src_width = dst_width = 2;
+	} else if (!((src | dest | len) & 1)) {
+		ctrla |= ATC_SRC_WIDTH_HALFWORD | ATC_DST_WIDTH_HALFWORD;
+		src_width = dst_width = 1;
+	} else {
+		ctrla |= ATC_SRC_WIDTH_BYTE | ATC_DST_WIDTH_BYTE;
+		src_width = dst_width = 0;
+	}
+
+	for (offset = 0; offset < len; offset += xfer_count << src_width) {
+		xfer_count = min_t(size_t, (len - offset) >> src_width,
+				ATC_BTSIZE_MAX);
+
+		desc = atc_desc_get(atchan);
+		if (!desc)
+			goto err_desc_get;
+
+		desc->lli.saddr = src + offset;
+		desc->lli.daddr = dest + offset;
+		desc->lli.ctrla = ctrla | xfer_count;
+		desc->lli.ctrlb = ctrlb;
+
+		desc->txd.cookie = 0;
+		async_tx_ack(&desc->txd);
+
+		if (!first) {
+			first = desc;
+		} else {
+			/* inform the HW lli about chaining */
+			prev->lli.dscr = desc->txd.phys;
+			/* insert the link descriptor to the LD ring */
+			list_add_tail(&desc->desc_node,
+					&first->txd.tx_list);
+		}
+		prev = desc;
+	}
+
+	/* First descriptor of the chain embedds additional information */
+	first->txd.cookie = -EBUSY;
+	first->len = len;
+
+	/* set end-of-link to the last link descriptor of list*/
+	set_desc_eol(desc);
+
+	desc->txd.flags = flags; /* client is in control of this ack */
+
+	return &first->txd;
+
+err_desc_get:
+	atc_desc_put(atchan, first);
+	return NULL;
+}
+
+
+/**
+ * atc_prep_slave_sg - prepare descriptors for a DMA_SLAVE transaction
+ * @chan: DMA channel
+ * @sgl: scatterlist to transfer to/from
+ * @sg_len: number of entries in @scatterlist
+ * @direction: DMA direction
+ * @flags: tx descriptor status flags
+ */
+static struct dma_async_tx_descriptor *
+atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
+		unsigned int sg_len, enum dma_data_direction direction,
+		unsigned long flags)
+{
+	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
+	struct at_dma_slave	*atslave = chan->private;
+	struct at_desc		*first = NULL;
+	struct at_desc		*prev = NULL;
+	u32			ctrla;
+	u32			ctrlb;
+	dma_addr_t		reg;
+	unsigned int		reg_width;
+	unsigned int		mem_width;
+	unsigned int		i;
+	struct scatterlist	*sg;
+	size_t			total_len = 0;
+
+	dev_vdbg(chan2dev(chan), "prep_slave_sg: %s f0x%lx\n",
+			direction == DMA_TO_DEVICE ? "TO DEVICE" : "FROM DEVICE",
+			flags);
+
+	if (unlikely(!atslave || !sg_len)) {
+		dev_dbg(chan2dev(chan), "prep_dma_memcpy: length is zero!\n");
+		return NULL;
+	}
+
+	reg_width = atslave->reg_width;
+
+	sg_len = dma_map_sg(chan2parent(chan), sgl, sg_len, direction);
+
+	ctrla = ATC_DEFAULT_CTRLA | atslave->ctrla;
+	ctrlb = ATC_DEFAULT_CTRLB | ATC_IEN;
+
+	switch (direction) {
+	case DMA_TO_DEVICE:
+		ctrla |=  ATC_DST_WIDTH(reg_width);
+		ctrlb |=  ATC_DST_ADDR_MODE_FIXED
+			| ATC_SRC_ADDR_MODE_INCR
+			| ATC_FC_MEM2PER;
+		reg = atslave->tx_reg;
+		for_each_sg(sgl, sg, sg_len, i) {
+			struct at_desc	*desc;
+			u32		len;
+			u32		mem;
+
+			desc = atc_desc_get(atchan);
+			if (!desc)
+				goto err_desc_get;
+
+			mem = sg_phys(sg);
+			len = sg_dma_len(sg);
+			mem_width = 2;
+			if (unlikely(mem & 3 || len & 3))
+				mem_width = 0;
+
+			desc->lli.saddr = mem;
+			desc->lli.daddr = reg;
+			desc->lli.ctrla = ctrla
+					| ATC_SRC_WIDTH(mem_width)
+					| len >> mem_width;
+			desc->lli.ctrlb = ctrlb;
+
+			if (!first) {
+				first = desc;
+			} else {
+				/* inform the HW lli about chaining */
+				prev->lli.dscr = desc->txd.phys;
+				/* insert the link descriptor to the LD ring */
+				list_add_tail(&desc->desc_node,
+						&first->txd.tx_list);
+			}
+			prev = desc;
+			total_len += len;
+		}
+		break;
+	case DMA_FROM_DEVICE:
+		ctrla |=  ATC_SRC_WIDTH(reg_width);
+		ctrlb |=  ATC_DST_ADDR_MODE_INCR
+			| ATC_SRC_ADDR_MODE_FIXED
+			| ATC_FC_PER2MEM;
+
+		reg = atslave->rx_reg;
+		for_each_sg(sgl, sg, sg_len, i) {
+			struct at_desc	*desc;
+			u32		len;
+			u32		mem;
+
+			desc = atc_desc_get(atchan);
+			if (!desc)
+				goto err_desc_get;
+
+			mem = sg_phys(sg);
+			len = sg_dma_len(sg);
+			mem_width = 2;
+			if (unlikely(mem & 3 || len & 3))
+				mem_width = 0;
+
+			desc->lli.saddr = reg;
+			desc->lli.daddr = mem;
+			desc->lli.ctrla = ctrla
+					| ATC_DST_WIDTH(mem_width)
+					| len >> mem_width;
+			desc->lli.ctrlb = ctrlb;
+
+			if (!first) {
+				first = desc;
+			} else {
+				/* inform the HW lli about chaining */
+				prev->lli.dscr = desc->txd.phys;
+				/* insert the link descriptor to the LD ring */
+				list_add_tail(&desc->desc_node,
+						&first->txd.tx_list);
+			}
+			prev = desc;
+			total_len += len;
+		}
+		break;
+	default:
+		return NULL;
+	}
+
+	/* set end-of-link to the last link descriptor of list*/
+	set_desc_eol(prev);
+
+	/* First descriptor of the chain embedds additional information */
+	first->txd.cookie = -EBUSY;
+	first->len = total_len;
+
+	/* last link descriptor of list is responsible of flags */
+	prev->txd.flags = flags; /* client is in control of this ack */
+
+	return &first->txd;
+
+err_desc_get:
+	dev_err(chan2dev(chan), "not enough descriptors available\n");
+	atc_desc_put(atchan, first);
+	return NULL;
+}
+
+static void atc_terminate_all(struct dma_chan *chan)
+{
+	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
+	struct at_dma		*atdma = to_at_dma(chan->device);
+	struct at_desc		*desc, *_desc;
+	LIST_HEAD(list);
+
+	/*
+	 * This is only called when something went wrong elsewhere, so
+	 * we don't really care about the data. Just disable the
+	 * channel. We still have to poll the channel enable bit due
+	 * to AHB/HSB limitations.
+	 */
+	spin_lock_bh(&atchan->lock);
+
+	dma_writel(atdma, CHDR, atchan->mask);
+
+	/* confirm that this channel is disabled */
+	while (dma_readl(atdma, CHSR) & atchan->mask)
+		cpu_relax();
+
+	/* active_list entries will end up before queued entries */
+	list_splice_init(&atchan->queue, &list);
+	list_splice_init(&atchan->active_list, &list);
+
+	spin_unlock_bh(&atchan->lock);
+
+	/* Flush all pending and queued descriptors */
+	list_for_each_entry_safe(desc, _desc, &list, desc_node)
+		atc_chain_complete(atchan, desc);
+}
+
+/**
+ * atc_is_tx_complete - poll for transaction completion
+ * @chan: DMA channel
+ * @cookie: transaction identifier to check status of
+ * @done: if not %NULL, updated with last completed transaction
+ * @used: if not %NULL, updated with last used transaction
+ *
+ * If @done and @used are passed in, upon return they reflect the driver
+ * internal state and can be used with dma_async_is_complete() to check
+ * the status of multiple cookies without re-checking hardware state.
+ */
+static enum dma_status
+atc_is_tx_complete(struct dma_chan *chan,
+		dma_cookie_t cookie,
+		dma_cookie_t *done, dma_cookie_t *used)
+{
+	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
+	dma_cookie_t		last_used;
+	dma_cookie_t		last_complete;
+	enum dma_status		ret;
+
+	dev_vdbg(chan2dev(chan), "is_tx_complete: %d (d%d, u%d)\n",
+			cookie, done ? *done : 0, used ? *used : 0);
+
+	spin_lock_bh(atchan->lock);
+
+	last_complete = atchan->completed_cookie;
+	last_used = chan->cookie;
+
+	ret = dma_async_is_complete(cookie, last_complete, last_used);
+	if (ret != DMA_SUCCESS) {
+		atc_cleanup_descriptors(atchan);
+
+		last_complete = atchan->completed_cookie;
+		last_used = chan->cookie;
+
+		ret = dma_async_is_complete(cookie, last_complete, last_used);
+	}
+
+	spin_unlock_bh(atchan->lock);
+
+	if (done)
+		*done = last_complete;
+	if (used)
+		*used = last_used;
+
+	return ret;
+}
+
+/**
+ * atc_issue_pending - try to finish work
+ * @chan: target DMA channel
+ */
+static void atc_issue_pending(struct dma_chan *chan)
+{
+	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
+
+	dev_vdbg(chan2dev(chan), "issue_pending\n");
+
+	if (!atc_chan_is_enabled(atchan)) {
+		spin_lock_bh(&atchan->lock);
+		atc_advance_work(atchan);
+		spin_unlock_bh(&atchan->lock);
+	}
+}
+
+/**
+ * atc_alloc_chan_resources - allocate resources for DMA channel
+ * @chan: allocate descriptor resources for this channel
+ * @client: current client requesting the channel be ready for requests
+ *
+ * return - the number of allocated descriptors
+ */
+static int atc_alloc_chan_resources(struct dma_chan *chan)
+{
+	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
+	struct at_dma		*atdma = to_at_dma(chan->device);
+	struct at_desc		*desc;
+	struct at_dma_slave	*atslave;
+	int			i;
+	u32			cfg;
+	LIST_HEAD(tmp_list);
+
+	dev_vdbg(chan2dev(chan), "alloc_chan_resources\n");
+
+	/* ASSERT:  channel is idle */
+	if (atc_chan_is_enabled(atchan)) {
+		dev_dbg(chan2dev(chan), "DMA channel not idle ?\n");
+		return -EIO;
+	}
+
+	cfg = ATC_DEFAULT_CFG;
+
+	atslave = chan->private;
+	if (atslave) {
+		/*
+		 * We need controller-specific data to set up slave
+		 * transfers.
+		 */
+		BUG_ON(!atslave->dma_dev || atslave->dma_dev != atdma->dma_common.dev);
+
+		/* if cfg configuration specified take it instad of default */
+		if (atslave->cfg)
+			cfg = atslave->cfg;
+	}
+
+	/* have we already been set up?
+	 * reconfigure channel but no need to reallocate descriptors */
+	if (!list_empty(&atchan->free_list))
+		return atchan->descs_allocated;
+
+	/* Allocate initial pool of descriptors */
+	for (i = 0; i < init_nr_desc_per_channel; i++) {
+		desc = atc_alloc_descriptor(chan, GFP_KERNEL);
+		if (!desc) {
+			dev_err(atdma->dma_common.dev,
+				"Only %d initial descriptors\n", i);
+			break;
+		}
+		list_add_tail(&desc->desc_node, &tmp_list);
+	}
+
+	spin_lock_bh(&atchan->lock);
+	atchan->descs_allocated = i;
+	list_splice(&tmp_list, &atchan->free_list);
+	atchan->completed_cookie = chan->cookie = 1;
+	spin_unlock_bh(&atchan->lock);
+
+	/* channel parameters */
+	channel_writel(atchan, CFG, cfg);
+
+	dev_dbg(chan2dev(chan),
+		"alloc_chan_resources: allocated %d descriptors\n",
+		atchan->descs_allocated);
+
+	return atchan->descs_allocated;
+}
+
+/**
+ * atc_free_chan_resources - free all channel resources
+ * @chan: DMA channel
+ */
+static void atc_free_chan_resources(struct dma_chan *chan)
+{
+	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
+	struct at_dma		*atdma = to_at_dma(chan->device);
+	struct at_desc		*desc, *_desc;
+	LIST_HEAD(list);
+
+	dev_dbg(chan2dev(chan), "free_chan_resources: (descs allocated=%u)\n",
+		atchan->descs_allocated);
+
+	/* ASSERT:  channel is idle */
+	BUG_ON(!list_empty(&atchan->active_list));
+	BUG_ON(!list_empty(&atchan->queue));
+	BUG_ON(atc_chan_is_enabled(atchan));
+
+	list_for_each_entry_safe(desc, _desc, &atchan->free_list, desc_node) {
+		dev_vdbg(chan2dev(chan), "  freeing descriptor %p\n", desc);
+		list_del(&desc->desc_node);
+		/* free link descriptor */
+		dma_pool_free(atdma->dma_desc_pool, desc, desc->txd.phys);
+	}
+	list_splice_init(&atchan->free_list, &list);
+	atchan->descs_allocated = 0;
+
+	dev_vdbg(chan2dev(chan), "free_chan_resources: done\n");
+}
+
+
+/*--  Module Management  -----------------------------------------------*/
+
+/**
+ * at_dma_off - disable DMA controller
+ * @atdma: the Atmel HDAMC device
+ */
+static void at_dma_off(struct at_dma *atdma)
+{
+	dma_writel(atdma, EN, 0);
+
+	/* disable all interrupts */
+	dma_writel(atdma, EBCIDR, -1L);
+
+	/* confirm that all channels are disabled */
+	while (dma_readl(atdma, CHSR) & atdma->all_chan_mask)
+		cpu_relax();
+}
+
+static int __init at_dma_probe(struct platform_device *pdev)
+{
+	struct at_dma_platform_data *pdata;
+	struct resource		*io;
+	struct at_dma		*atdma;
+	size_t			size;
+	int			irq;
+	int			err;
+	int			i;
+
+	/* get DMA Controller parameters from platform */
+	pdata = pdev->dev.platform_data;
+	if (!pdata || pdata->nr_channels > AT_DMA_MAX_NR_CHANNELS)
+		return -EINVAL;
+
+	io = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!io)
+		return -EINVAL;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
+	size = sizeof(struct at_dma);
+	size += pdata->nr_channels * sizeof(struct at_dma_chan);
+	atdma = kzalloc(size, GFP_KERNEL);
+	if (!atdma)
+		return -ENOMEM;
+
+	/* discover transaction capabilites from the platform data */
+	atdma->dma_common.cap_mask = pdata->cap_mask;
+	atdma->all_chan_mask = (1 << pdata->nr_channels) - 1;
+
+	size = io->end - io->start + 1;
+	if (!request_mem_region(io->start, size, pdev->dev.driver->name)) {
+		err = -EBUSY;
+		goto err_kfree;
+	}
+
+	atdma->regs = ioremap(io->start, size);
+	if (!atdma->regs) {
+		err = -ENOMEM;
+		goto err_release_r;
+	}
+
+	atdma->clk = clk_get(&pdev->dev, "dma_clk");
+	if (IS_ERR(atdma->clk)) {
+		err = PTR_ERR(atdma->clk);
+		goto err_clk;
+	}
+	clk_enable(atdma->clk);
+
+	/* force dma off, just in case */
+	at_dma_off(atdma);
+
+	err = request_irq(irq, at_dma_interrupt, 0, "at_hdmac", atdma);
+	if (err)
+		goto err_irq;
+
+	platform_set_drvdata(pdev, atdma);
+
+	/* create a pool of consistent memory blocks for hardware descriptors */
+	atdma->dma_desc_pool = dma_pool_create("at_hdmac_desc_pool",
+			&pdev->dev, sizeof(struct at_desc),
+			4 /* word alignment */, 0);
+	if (!atdma->dma_desc_pool) {
+		dev_err(&pdev->dev, "No memory for descriptors dma pool\n");
+		err = -ENOMEM;
+		goto err_pool_create;
+	}
+
+	/* clear any pending interrupt */
+	while (dma_readl(atdma, EBCISR))
+		cpu_relax();
+
+	/* initialize channels related values */
+	INIT_LIST_HEAD(&atdma->dma_common.channels);
+	for (i = 0; i < pdata->nr_channels; i++, atdma->dma_common.chancnt++) {
+		struct at_dma_chan	*atchan = &atdma->chan[i];
+
+		atchan->chan_common.device = &atdma->dma_common;
+		atchan->chan_common.cookie = atchan->completed_cookie = 1;
+		atchan->chan_common.chan_id = i;
+		list_add_tail(&atchan->chan_common.device_node,
+				&atdma->dma_common.channels);
+
+		atchan->ch_regs = atdma->regs + ch_regs(i);
+		spin_lock_init(&atchan->lock);
+		atchan->mask = 1 << i;
+
+		INIT_LIST_HEAD(&atchan->active_list);
+		INIT_LIST_HEAD(&atchan->queue);
+		INIT_LIST_HEAD(&atchan->free_list);
+
+		tasklet_init(&atchan->tasklet, atc_tasklet,
+				(unsigned long)atchan);
+		atc_enable_irq(atchan);
+	}
+
+	/* set base routines */
+	atdma->dma_common.device_alloc_chan_resources = atc_alloc_chan_resources;
+	atdma->dma_common.device_free_chan_resources = atc_free_chan_resources;
+	atdma->dma_common.device_is_tx_complete = atc_is_tx_complete;
+	atdma->dma_common.device_issue_pending = atc_issue_pending;
+	atdma->dma_common.dev = &pdev->dev;
+
+	/* set prep routines based on capability */
+	if (dma_has_cap(DMA_MEMCPY, atdma->dma_common.cap_mask))
+		atdma->dma_common.device_prep_dma_memcpy = atc_prep_dma_memcpy;
+
+	if (dma_has_cap(DMA_SLAVE, atdma->dma_common.cap_mask)) {
+		atdma->dma_common.device_prep_slave_sg = atc_prep_slave_sg;
+		atdma->dma_common.device_terminate_all = atc_terminate_all;
+	}
+
+	dma_writel(atdma, EN, AT_DMA_ENABLE);
+
+	dev_info(&pdev->dev, "Atmel AHB DMA Controller ( %s%s), %d channels\n",
+	  dma_has_cap(DMA_MEMCPY, atdma->dma_common.cap_mask) ? "cpy " : "",
+	  dma_has_cap(DMA_SLAVE, atdma->dma_common.cap_mask)  ? "slave " : "",
+	  atdma->dma_common.chancnt);
+
+	dma_async_device_register(&atdma->dma_common);
+
+	return 0;
+
+err_pool_create:
+	platform_set_drvdata(pdev, NULL);
+	free_irq(platform_get_irq(pdev, 0), atdma);
+err_irq:
+	clk_disable(atdma->clk);
+	clk_put(atdma->clk);
+err_clk:
+	iounmap(atdma->regs);
+	atdma->regs = NULL;
+err_release_r:
+	release_mem_region(io->start, size);
+err_kfree:
+	kfree(atdma);
+	return err;
+}
+
+static int __exit at_dma_remove(struct platform_device *pdev)
+{
+	struct at_dma		*atdma = platform_get_drvdata(pdev);
+	struct dma_chan		*chan, *_chan;
+	struct resource		*io;
+
+	at_dma_off(atdma);
+	dma_async_device_unregister(&atdma->dma_common);
+
+	dma_pool_destroy(atdma->dma_desc_pool);
+	platform_set_drvdata(pdev, NULL);
+	free_irq(platform_get_irq(pdev, 0), atdma);
+
+	list_for_each_entry_safe(chan, _chan, &atdma->dma_common.channels,
+			device_node) {
+		struct at_dma_chan	*atchan = to_at_dma_chan(chan);
+
+		/* Disable interrupts */
+		atc_disable_irq(atchan);
+		tasklet_disable(&atchan->tasklet);
+
+		tasklet_kill(&atchan->tasklet);
+		list_del(&chan->device_node);
+	}
+
+	clk_disable(atdma->clk);
+	clk_put(atdma->clk);
+
+	iounmap(atdma->regs);
+	atdma->regs = NULL;
+
+	io = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	release_mem_region(io->start, io->end - io->start + 1);
+
+	kfree(atdma);
+
+	return 0;
+}
+
+static void at_dma_shutdown(struct platform_device *pdev)
+{
+	struct at_dma	*atdma = platform_get_drvdata(pdev);
+
+	at_dma_off(platform_get_drvdata(pdev));
+	clk_disable(atdma->clk);
+}
+
+static int at_dma_suspend_late(struct platform_device *pdev, pm_message_t mesg)
+{
+	struct at_dma	*atdma = platform_get_drvdata(pdev);
+
+	at_dma_off(platform_get_drvdata(pdev));
+	clk_disable(atdma->clk);
+	return 0;
+}
+
+static int at_dma_resume_early(struct platform_device *pdev)
+{
+	struct at_dma	*atdma = platform_get_drvdata(pdev);
+
+	clk_enable(atdma->clk);
+	dma_writel(atdma, EN, AT_DMA_ENABLE);
+	return 0;
+
+}
+
+static struct platform_driver at_dma_driver = {
+	.remove		= __exit_p(at_dma_remove),
+	.shutdown	= at_dma_shutdown,
+	.suspend_late	= at_dma_suspend_late,
+	.resume_early	= at_dma_resume_early,
+	.driver = {
+		.name	= "at_hdmac",
+	},
+};
+
+static int __init at_dma_init(void)
+{
+	return platform_driver_probe(&at_dma_driver, at_dma_probe);
+}
+module_init(at_dma_init);
+
+static void __exit at_dma_exit(void)
+{
+	platform_driver_unregister(&at_dma_driver);
+}
+module_exit(at_dma_exit);
+
+MODULE_DESCRIPTION("Atmel AHB DMA Controller driver");
+MODULE_AUTHOR("Nicolas Ferre <nicolas.ferre@atmel.com>");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:at_hdmac");
diff --git a/drivers/dma/at_hdmac_regs.h b/drivers/dma/at_hdmac_regs.h
new file mode 100644
index 00000000000..4c972afc49e
--- /dev/null
+++ b/drivers/dma/at_hdmac_regs.h
@@ -0,0 +1,353 @@
+/*
+ * Header file for the Atmel AHB DMA Controller driver
+ *
+ * Copyright (C) 2008 Atmel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+#ifndef AT_HDMAC_REGS_H
+#define	AT_HDMAC_REGS_H
+
+#include <mach/at_hdmac.h>
+
+#define	AT_DMA_MAX_NR_CHANNELS	8
+
+
+#define	AT_DMA_GCFG	0x00	/* Global Configuration Register */
+#define		AT_DMA_IF_BIGEND(i)	(0x1 << (i))	/* AHB-Lite Interface i in Big-endian mode */
+#define		AT_DMA_ARB_CFG	(0x1 << 4)	/* Arbiter mode. */
+#define			AT_DMA_ARB_CFG_FIXED		(0x0 << 4)
+#define			AT_DMA_ARB_CFG_ROUND_ROBIN	(0x1 << 4)
+
+#define	AT_DMA_EN	0x04	/* Controller Enable Register */
+#define		AT_DMA_ENABLE	(0x1 << 0)
+
+#define	AT_DMA_SREQ	0x08	/* Software Single Request Register */
+#define		AT_DMA_SSREQ(x)	(0x1 << ((x) << 1))		/* Request a source single transfer on channel x */
+#define		AT_DMA_DSREQ(x)	(0x1 << (1 + ((x) << 1)))	/* Request a destination single transfer on channel x */
+
+#define	AT_DMA_CREQ	0x0C	/* Software Chunk Transfer Request Register */
+#define		AT_DMA_SCREQ(x)	(0x1 << ((x) << 1))		/* Request a source chunk transfer on channel x */
+#define		AT_DMA_DCREQ(x)	(0x1 << (1 + ((x) << 1)))	/* Request a destination chunk transfer on channel x */
+
+#define	AT_DMA_LAST	0x10	/* Software Last Transfer Flag Register */
+#define		AT_DMA_SLAST(x)	(0x1 << ((x) << 1))		/* This src rq is last tx of buffer on channel x */
+#define		AT_DMA_DLAST(x)	(0x1 << (1 + ((x) << 1)))	/* This dst rq is last tx of buffer on channel x */
+
+#define	AT_DMA_SYNC	0x14	/* Request Synchronization Register */
+#define		AT_DMA_SYR(h)	(0x1 << (h))			/* Synchronize handshake line h */
+
+/* Error, Chained Buffer transfer completed and Buffer transfer completed Interrupt registers */
+#define	AT_DMA_EBCIER	0x18	/* Enable register */
+#define	AT_DMA_EBCIDR	0x1C	/* Disable register */
+#define	AT_DMA_EBCIMR	0x20	/* Mask Register */
+#define	AT_DMA_EBCISR	0x24	/* Status Register */
+#define		AT_DMA_CBTC_OFFSET	8
+#define		AT_DMA_ERR_OFFSET	16
+#define		AT_DMA_BTC(x)	(0x1 << (x))
+#define		AT_DMA_CBTC(x)	(0x1 << (AT_DMA_CBTC_OFFSET + (x)))
+#define		AT_DMA_ERR(x)	(0x1 << (AT_DMA_ERR_OFFSET + (x)))
+
+#define	AT_DMA_CHER	0x28	/* Channel Handler Enable Register */
+#define		AT_DMA_ENA(x)	(0x1 << (x))
+#define		AT_DMA_SUSP(x)	(0x1 << ( 8 + (x)))
+#define		AT_DMA_KEEP(x)	(0x1 << (24 + (x)))
+
+#define	AT_DMA_CHDR	0x2C	/* Channel Handler Disable Register */
+#define		AT_DMA_DIS(x)	(0x1 << (x))
+#define		AT_DMA_RES(x)	(0x1 << ( 8 + (x)))
+
+#define	AT_DMA_CHSR	0x30	/* Channel Handler Status Register */
+#define		AT_DMA_EMPT(x)	(0x1 << (16 + (x)))
+#define		AT_DMA_STAL(x)	(0x1 << (24 + (x)))
+
+
+#define	AT_DMA_CH_REGS_BASE	0x3C	/* Channel registers base address */
+#define	ch_regs(x)	(AT_DMA_CH_REGS_BASE + (x) * 0x28) /* Channel x base addr */
+
+/* Hardware register offset for each channel */
+#define	ATC_SADDR_OFFSET	0x00	/* Source Address Register */
+#define	ATC_DADDR_OFFSET	0x04	/* Destination Address Register */
+#define	ATC_DSCR_OFFSET		0x08	/* Descriptor Address Register */
+#define	ATC_CTRLA_OFFSET	0x0C	/* Control A Register */
+#define	ATC_CTRLB_OFFSET	0x10	/* Control B Register */
+#define	ATC_CFG_OFFSET		0x14	/* Configuration Register */
+#define	ATC_SPIP_OFFSET		0x18	/* Src PIP Configuration Register */
+#define	ATC_DPIP_OFFSET		0x1C	/* Dst PIP Configuration Register */
+
+
+/* Bitfield definitions */
+
+/* Bitfields in DSCR */
+#define	ATC_DSCR_IF(i)		(0x3 & (i))	/* Dsc feched via AHB-Lite Interface i */
+
+/* Bitfields in CTRLA */
+#define	ATC_BTSIZE_MAX		0xFFFFUL	/* Maximum Buffer Transfer Size */
+#define	ATC_BTSIZE(x)		(ATC_BTSIZE_MAX & (x)) /* Buffer Transfer Size */
+/* Chunck Tranfer size definitions are in at_hdmac.h */
+#define	ATC_SRC_WIDTH_MASK	(0x3 << 24)	/* Source Single Transfer Size */
+#define		ATC_SRC_WIDTH(x)	((x) << 24)
+#define		ATC_SRC_WIDTH_BYTE	(0x0 << 24)
+#define		ATC_SRC_WIDTH_HALFWORD	(0x1 << 24)
+#define		ATC_SRC_WIDTH_WORD	(0x2 << 24)
+#define	ATC_DST_WIDTH_MASK	(0x3 << 28)	/* Destination Single Transfer Size */
+#define		ATC_DST_WIDTH(x)	((x) << 28)
+#define		ATC_DST_WIDTH_BYTE	(0x0 << 28)
+#define		ATC_DST_WIDTH_HALFWORD	(0x1 << 28)
+#define		ATC_DST_WIDTH_WORD	(0x2 << 28)
+#define	ATC_DONE		(0x1 << 31)	/* Tx Done (only written back in descriptor) */
+
+/* Bitfields in CTRLB */
+#define	ATC_SIF(i)		(0x3 & (i))	/* Src tx done via AHB-Lite Interface i */
+#define	ATC_DIF(i)		((0x3 & (i)) <<  4)	/* Dst tx done via AHB-Lite Interface i */
+#define	ATC_SRC_PIP		(0x1 <<  8)	/* Source Picture-in-Picture enabled */
+#define	ATC_DST_PIP		(0x1 << 12)	/* Destination Picture-in-Picture enabled */
+#define	ATC_SRC_DSCR_DIS	(0x1 << 16)	/* Src Descriptor fetch disable */
+#define	ATC_DST_DSCR_DIS	(0x1 << 20)	/* Dst Descriptor fetch disable */
+#define	ATC_FC_MASK		(0x7 << 21)	/* Choose Flow Controller */
+#define		ATC_FC_MEM2MEM		(0x0 << 21)	/* Mem-to-Mem (DMA) */
+#define		ATC_FC_MEM2PER		(0x1 << 21)	/* Mem-to-Periph (DMA) */
+#define		ATC_FC_PER2MEM		(0x2 << 21)	/* Periph-to-Mem (DMA) */
+#define		ATC_FC_PER2PER		(0x3 << 21)	/* Periph-to-Periph (DMA) */
+#define		ATC_FC_PER2MEM_PER	(0x4 << 21)	/* Periph-to-Mem (Peripheral) */
+#define		ATC_FC_MEM2PER_PER	(0x5 << 21)	/* Mem-to-Periph (Peripheral) */
+#define		ATC_FC_PER2PER_SRCPER	(0x6 << 21)	/* Periph-to-Periph (Src Peripheral) */
+#define		ATC_FC_PER2PER_DSTPER	(0x7 << 21)	/* Periph-to-Periph (Dst Peripheral) */
+#define	ATC_SRC_ADDR_MODE_MASK	(0x3 << 24)
+#define		ATC_SRC_ADDR_MODE_INCR	(0x0 << 24)	/* Incrementing Mode */
+#define		ATC_SRC_ADDR_MODE_DECR	(0x1 << 24)	/* Decrementing Mode */
+#define		ATC_SRC_ADDR_MODE_FIXED	(0x2 << 24)	/* Fixed Mode */
+#define	ATC_DST_ADDR_MODE_MASK	(0x3 << 28)
+#define		ATC_DST_ADDR_MODE_INCR	(0x0 << 28)	/* Incrementing Mode */
+#define		ATC_DST_ADDR_MODE_DECR	(0x1 << 28)	/* Decrementing Mode */
+#define		ATC_DST_ADDR_MODE_FIXED	(0x2 << 28)	/* Fixed Mode */
+#define	ATC_IEN			(0x1 << 30)	/* BTC interrupt enable (active low) */
+#define	ATC_AUTO		(0x1 << 31)	/* Auto multiple buffer tx enable */
+
+/* Bitfields in CFG */
+/* are in at_hdmac.h */
+
+/* Bitfields in SPIP */
+#define	ATC_SPIP_HOLE(x)	(0xFFFFU & (x))
+#define	ATC_SPIP_BOUNDARY(x)	((0x3FF & (x)) << 16)
+
+/* Bitfields in DPIP */
+#define	ATC_DPIP_HOLE(x)	(0xFFFFU & (x))
+#define	ATC_DPIP_BOUNDARY(x)	((0x3FF & (x)) << 16)
+
+
+/*--  descriptors  -----------------------------------------------------*/
+
+/* LLI == Linked List Item; aka DMA buffer descriptor */
+struct at_lli {
+	/* values that are not changed by hardware */
+	dma_addr_t	saddr;
+	dma_addr_t	daddr;
+	/* value that may get written back: */
+	u32		ctrla;
+	/* more values that are not changed by hardware */
+	u32		ctrlb;
+	dma_addr_t	dscr;	/* chain to next lli */
+};
+
+/**
+ * struct at_desc - software descriptor
+ * @at_lli: hardware lli structure
+ * @txd: support for the async_tx api
+ * @desc_node: node on the channed descriptors list
+ * @len: total transaction bytecount
+ */
+struct at_desc {
+	/* FIRST values the hardware uses */
+	struct at_lli			lli;
+
+	/* THEN values for driver housekeeping */
+	struct dma_async_tx_descriptor	txd;
+	struct list_head		desc_node;
+	size_t				len;
+};
+
+static inline struct at_desc *
+txd_to_at_desc(struct dma_async_tx_descriptor *txd)
+{
+	return container_of(txd, struct at_desc, txd);
+}
+
+
+/*--  Channels  --------------------------------------------------------*/
+
+/**
+ * struct at_dma_chan - internal representation of an Atmel HDMAC channel
+ * @chan_common: common dmaengine channel object members
+ * @device: parent device
+ * @ch_regs: memory mapped register base
+ * @mask: channel index in a mask
+ * @error_status: transmit error status information from irq handler
+ *                to tasklet (use atomic operations)
+ * @tasklet: bottom half to finish transaction work
+ * @lock: serializes enqueue/dequeue operations to descriptors lists
+ * @completed_cookie: identifier for the most recently completed operation
+ * @active_list: list of descriptors dmaengine is being running on
+ * @queue: list of descriptors ready to be submitted to engine
+ * @free_list: list of descriptors usable by the channel
+ * @descs_allocated: records the actual size of the descriptor pool
+ */
+struct at_dma_chan {
+	struct dma_chan		chan_common;
+	struct at_dma		*device;
+	void __iomem		*ch_regs;
+	u8			mask;
+	unsigned long		error_status;
+	struct tasklet_struct	tasklet;
+
+	spinlock_t		lock;
+
+	/* these other elements are all protected by lock */
+	dma_cookie_t		completed_cookie;
+	struct list_head	active_list;
+	struct list_head	queue;
+	struct list_head	free_list;
+	unsigned int		descs_allocated;
+};
+
+#define	channel_readl(atchan, name) \
+	__raw_readl((atchan)->ch_regs + ATC_##name##_OFFSET)
+
+#define	channel_writel(atchan, name, val) \
+	__raw_writel((val), (atchan)->ch_regs + ATC_##name##_OFFSET)
+
+static inline struct at_dma_chan *to_at_dma_chan(struct dma_chan *dchan)
+{
+	return container_of(dchan, struct at_dma_chan, chan_common);
+}
+
+
+/*--  Controller  ------------------------------------------------------*/
+
+/**
+ * struct at_dma - internal representation of an Atmel HDMA Controller
+ * @chan_common: common dmaengine dma_device object members
+ * @ch_regs: memory mapped register base
+ * @clk: dma controller clock
+ * @all_chan_mask: all channels availlable in a mask
+ * @dma_desc_pool: base of DMA descriptor region (DMA address)
+ * @chan: channels table to store at_dma_chan structures
+ */
+struct at_dma {
+	struct dma_device	dma_common;
+	void __iomem		*regs;
+	struct clk		*clk;
+
+	u8			all_chan_mask;
+
+	struct dma_pool		*dma_desc_pool;
+	/* AT THE END channels table */
+	struct at_dma_chan	chan[0];
+};
+
+#define	dma_readl(atdma, name) \
+	__raw_readl((atdma)->regs + AT_DMA_##name)
+#define	dma_writel(atdma, name, val) \
+	__raw_writel((val), (atdma)->regs + AT_DMA_##name)
+
+static inline struct at_dma *to_at_dma(struct dma_device *ddev)
+{
+	return container_of(ddev, struct at_dma, dma_common);
+}
+
+
+/*--  Helper functions  ------------------------------------------------*/
+
+static struct device *chan2dev(struct dma_chan *chan)
+{
+	return &chan->dev->device;
+}
+static struct device *chan2parent(struct dma_chan *chan)
+{
+	return chan->dev->device.parent;
+}
+
+#if defined(VERBOSE_DEBUG)
+static void vdbg_dump_regs(struct at_dma_chan *atchan)
+{
+	struct at_dma	*atdma = to_at_dma(atchan->chan_common.device);
+
+	dev_err(chan2dev(&atchan->chan_common),
+		"  channel %d : imr = 0x%x, chsr = 0x%x\n",
+		atchan->chan_common.chan_id,
+		dma_readl(atdma, EBCIMR),
+		dma_readl(atdma, CHSR));
+
+	dev_err(chan2dev(&atchan->chan_common),
+		"  channel: s0x%x d0x%x ctrl0x%x:0x%x cfg0x%x l0x%x\n",
+		channel_readl(atchan, SADDR),
+		channel_readl(atchan, DADDR),
+		channel_readl(atchan, CTRLA),
+		channel_readl(atchan, CTRLB),
+		channel_readl(atchan, CFG),
+		channel_readl(atchan, DSCR));
+}
+#else
+static void vdbg_dump_regs(struct at_dma_chan *atchan) {}
+#endif
+
+static void atc_dump_lli(struct at_dma_chan *atchan, struct at_lli *lli)
+{
+	dev_printk(KERN_CRIT, chan2dev(&atchan->chan_common),
+			"  desc: s0x%x d0x%x ctrl0x%x:0x%x l0x%x\n",
+			lli->saddr, lli->daddr,
+			lli->ctrla, lli->ctrlb, lli->dscr);
+}
+
+
+static void atc_setup_irq(struct at_dma_chan *atchan, int on)
+{
+	struct at_dma	*atdma = to_at_dma(atchan->chan_common.device);
+	u32		ebci;
+
+	/* enable interrupts on buffer chain completion & error */
+	ebci =    AT_DMA_CBTC(atchan->chan_common.chan_id)
+		| AT_DMA_ERR(atchan->chan_common.chan_id);
+	if (on)
+		dma_writel(atdma, EBCIER, ebci);
+	else
+		dma_writel(atdma, EBCIDR, ebci);
+}
+
+static inline void atc_enable_irq(struct at_dma_chan *atchan)
+{
+	atc_setup_irq(atchan, 1);
+}
+
+static inline void atc_disable_irq(struct at_dma_chan *atchan)
+{
+	atc_setup_irq(atchan, 0);
+}
+
+
+/**
+ * atc_chan_is_enabled - test if given channel is enabled
+ * @atchan: channel we want to test status
+ */
+static inline int atc_chan_is_enabled(struct at_dma_chan *atchan)
+{
+	struct at_dma	*atdma = to_at_dma(atchan->chan_common.device);
+
+	return !!(dma_readl(atdma, CHSR) & atchan->mask);
+}
+
+
+/**
+ * set_desc_eol - set end-of-link to descriptor so it will end transfer
+ * @desc: descriptor, signle or at the end of a chain, to end chain on
+ */
+static void set_desc_eol(struct at_desc *desc)
+{
+	desc->lli.ctrlb |= ATC_SRC_DSCR_DIS | ATC_DST_DSCR_DIS;
+	desc->lli.dscr = 0;
+}
+
+#endif /* AT_HDMAC_REGS_H */
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index fb7da5141e9..d93017fc787 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -38,6 +38,11 @@ module_param(max_channels, uint, S_IRUGO);
 MODULE_PARM_DESC(max_channels,
 		"Maximum number of channels to use (default: all)");
 
+static unsigned int iterations;
+module_param(iterations, uint, S_IRUGO);
+MODULE_PARM_DESC(iterations,
+		"Iterations before stopping test (default: infinite)");
+
 static unsigned int xor_sources = 3;
 module_param(xor_sources, uint, S_IRUGO);
 MODULE_PARM_DESC(xor_sources,
@@ -114,7 +119,7 @@ static void dmatest_init_srcs(u8 **bufs, unsigned int start, unsigned int len)
 			buf[i] = PATTERN_SRC | (~i & PATTERN_COUNT_MASK);
 		for ( ; i < start + len; i++)
 			buf[i] = PATTERN_SRC | PATTERN_COPY
-				| (~i & PATTERN_COUNT_MASK);;
+				| (~i & PATTERN_COUNT_MASK);
 		for ( ; i < test_buf_size; i++)
 			buf[i] = PATTERN_SRC | (~i & PATTERN_COUNT_MASK);
 		buf++;
@@ -270,7 +275,8 @@ static int dmatest_func(void *data)
 
 	flags = DMA_CTRL_ACK | DMA_COMPL_SKIP_DEST_UNMAP | DMA_PREP_INTERRUPT;
 
-	while (!kthread_should_stop()) {
+	while (!kthread_should_stop()
+	       && !(iterations && total_tests >= iterations)) {
 		struct dma_device *dev = chan->device;
 		struct dma_async_tx_descriptor *tx = NULL;
 		dma_addr_t dma_srcs[src_cnt];
@@ -416,6 +422,13 @@ err_srcbuf:
 err_srcs:
 	pr_notice("%s: terminating after %u tests, %u failures (status %d)\n",
 			thread_name, total_tests, failed_tests, ret);
+
+	if (iterations > 0)
+		while (!kthread_should_stop()) {
+			DECLARE_WAIT_QUEUE_HEAD(wait_dmatest_exit);
+			interruptible_sleep_on(&wait_dmatest_exit);
+		}
+
 	return ret;
 }
 
@@ -495,11 +508,11 @@ static int dmatest_add_channel(struct dma_chan *chan)
 
 	if (dma_has_cap(DMA_MEMCPY, dma_dev->cap_mask)) {
 		cnt = dmatest_add_threads(dtc, DMA_MEMCPY);
-		thread_count += cnt > 0 ?: 0;
+		thread_count += cnt > 0 ? cnt : 0;
 	}
 	if (dma_has_cap(DMA_XOR, dma_dev->cap_mask)) {
 		cnt = dmatest_add_threads(dtc, DMA_XOR);
-		thread_count += cnt > 0 ?: 0;
+		thread_count += cnt > 0 ? cnt : 0;
 	}
 
 	pr_info("dmatest: Started %u threads using %s\n",
diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c
index f18d1bde043..ef87a898414 100644
--- a/drivers/dma/fsldma.c
+++ b/drivers/dma/fsldma.c
@@ -12,6 +12,11 @@
  *   also fit for MPC8560, MPC8555, MPC8548, MPC8641, and etc.
  *   The support for MPC8349 DMA contorller is also added.
  *
+ * This driver instructs the DMA controller to issue the PCI Read Multiple
+ * command for PCI read operations, instead of using the default PCI Read Line
+ * command. Please be aware that this setting may result in read pre-fetching
+ * on some platforms.
+ *
  * This is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation; either version 2 of the License, or
@@ -49,9 +54,10 @@ static void dma_init(struct fsl_dma_chan *fsl_chan)
 	case FSL_DMA_IP_83XX:
 		/* Set the channel to below modes:
 		 * EOTIE - End-of-transfer interrupt enable
+		 * PRC_RM - PCI read multiple
 		 */
-		DMA_OUT(fsl_chan, &fsl_chan->reg_base->mr, FSL_DMA_MR_EOTIE,
-				32);
+		DMA_OUT(fsl_chan, &fsl_chan->reg_base->mr, FSL_DMA_MR_EOTIE
+				| FSL_DMA_MR_PRC_RM, 32);
 		break;
 	}
 
@@ -136,15 +142,16 @@ static int dma_is_idle(struct fsl_dma_chan *fsl_chan)
 
 static void dma_start(struct fsl_dma_chan *fsl_chan)
 {
-	u32 mr_set = 0;;
+	u32 mr_set = 0;
 
 	if (fsl_chan->feature & FSL_DMA_CHAN_PAUSE_EXT) {
 		DMA_OUT(fsl_chan, &fsl_chan->reg_base->bcr, 0, 32);
 		mr_set |= FSL_DMA_MR_EMP_EN;
-	} else
+	} else if ((fsl_chan->feature & FSL_DMA_IP_MASK) == FSL_DMA_IP_85XX) {
 		DMA_OUT(fsl_chan, &fsl_chan->reg_base->mr,
 			DMA_IN(fsl_chan, &fsl_chan->reg_base->mr, 32)
 				& ~FSL_DMA_MR_EMP_EN, 32);
+	}
 
 	if (fsl_chan->feature & FSL_DMA_CHAN_START_EXT)
 		mr_set |= FSL_DMA_MR_EMS_EN;
@@ -871,9 +878,9 @@ static int __devinit fsl_dma_chan_probe(struct fsl_dma_device *fdev,
 
 	switch (new_fsl_chan->feature & FSL_DMA_IP_MASK) {
 	case FSL_DMA_IP_85XX:
-		new_fsl_chan->toggle_ext_start = fsl_chan_toggle_ext_start;
 		new_fsl_chan->toggle_ext_pause = fsl_chan_toggle_ext_pause;
 	case FSL_DMA_IP_83XX:
+		new_fsl_chan->toggle_ext_start = fsl_chan_toggle_ext_start;
 		new_fsl_chan->set_src_loop_size = fsl_chan_set_src_loop_size;
 		new_fsl_chan->set_dest_loop_size = fsl_chan_set_dest_loop_size;
 	}
diff --git a/drivers/dma/fsldma.h b/drivers/dma/fsldma.h
index 4f21a512d84..dc7f2686579 100644
--- a/drivers/dma/fsldma.h
+++ b/drivers/dma/fsldma.h
@@ -38,6 +38,7 @@
 
 /* Special MR definition for MPC8349 */
 #define FSL_DMA_MR_EOTIE	0x00000080
+#define FSL_DMA_MR_PRC_RM	0x00000800
 
 #define FSL_DMA_SR_CH		0x00000020
 #define FSL_DMA_SR_PE		0x00000010
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index ddab94f5122..3f23eabe09f 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -1176,7 +1176,7 @@ static int __devinit mv_xor_probe(struct platform_device *pdev)
 	if (dma_has_cap(DMA_MEMSET, dma_dev->cap_mask))
 		dma_dev->device_prep_dma_memset = mv_xor_prep_dma_memset;
 	if (dma_has_cap(DMA_XOR, dma_dev->cap_mask)) {
-		dma_dev->max_xor = 8;                  ;
+		dma_dev->max_xor = 8;
 		dma_dev->device_prep_dma_xor = mv_xor_prep_dma_xor;
 	}