Merge branch 'dmaengine' into async-tx-next

Conflicts:
	crypto/async_tx/async_xor.c
	drivers/dma/ioat/dma_v2.h
	drivers/dma/ioat/pci.c
	drivers/md/raid5.c

drivers/dma/Kconfig

@@ -50,6 +50,14 @@ 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
@@ -85,6 +93,14 @@ config MX3_IPU_IRQS
 	  To avoid bloating the irq_desc[] array we allocate a sufficient
 	  number of IRQ slots and map them dynamically to specific sources.
 
+config TXX9_DMAC
+	tristate "Toshiba TXx9 SoC DMA support"
+	depends on MACH_TX49XX || MACH_TX39XX
+	select DMA_ENGINE
+	help
+	  Support the TXx9 SoC internal DMA controller.  This can be
+	  integrated in chips such as the Toshiba TX4927/38/39.
+
 config DMA_ENGINE
 	bool
 
@@ -104,7 +120,7 @@ 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

drivers/dma/Makefile

@@ -6,4 +6,6 @@ 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

drivers/dma/at_hdmac_regs.h

@@ -0,0 +1,354 @@
+/*
+ * 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 list_head		tx_list;
+	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 */

drivers/dma/dmaengine.c

@@ -977,7 +977,6 @@ void dma_async_tx_descriptor_init(struct dma_async_tx_descriptor *tx,
 {
 	tx->chan = chan;
 	spin_lock_init(&tx->lock);
-	INIT_LIST_HEAD(&tx->tx_list);
 }
 EXPORT_SYMBOL(dma_async_tx_descriptor_init);
 

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,
@@ -119,7 +124,7 @@ 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++;
@@ -281,7 +286,8 @@ 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];
@@ -450,6 +456,13 @@ 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;
 }
 
@@ -531,11 +544,11 @@ 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;
 	}
 	if (dma_has_cap(DMA_PQ, dma_dev->cap_mask)) {
 		cnt = dmatest_add_threads(dtc, DMA_PQ);

drivers/dma/dw_dmac.c

@@ -116,7 +116,7 @@ static void dwc_sync_desc_for_cpu(struct dw_dma_chan *dwc, struct dw_desc *desc)
 {
 	struct dw_desc	*child;
 
-	list_for_each_entry(child, &desc->txd.tx_list, desc_node)
+	list_for_each_entry(child, &desc->tx_list, desc_node)
 		dma_sync_single_for_cpu(chan2parent(&dwc->chan),
 				child->txd.phys, sizeof(child->lli),
 				DMA_TO_DEVICE);
@@ -137,11 +137,11 @@ static void dwc_desc_put(struct dw_dma_chan *dwc, struct dw_desc *desc)
 		dwc_sync_desc_for_cpu(dwc, desc);
 
 		spin_lock_bh(&dwc->lock);
-		list_for_each_entry(child, &desc->txd.tx_list, desc_node)
+		list_for_each_entry(child, &desc->tx_list, desc_node)
 			dev_vdbg(chan2dev(&dwc->chan),
 					"moving child desc %p to freelist\n",
 					child);
-		list_splice_init(&desc->txd.tx_list, &dwc->free_list);
+		list_splice_init(&desc->tx_list, &dwc->free_list);
 		dev_vdbg(chan2dev(&dwc->chan), "moving desc %p to freelist\n", desc);
 		list_add(&desc->desc_node, &dwc->free_list);
 		spin_unlock_bh(&dwc->lock);
@@ -209,19 +209,28 @@ dwc_descriptor_complete(struct dw_dma_chan *dwc, struct dw_desc *desc)
 	param = txd->callback_param;
 
 	dwc_sync_desc_for_cpu(dwc, desc);
-	list_splice_init(&txd->tx_list, &dwc->free_list);
+	list_splice_init(&desc->tx_list, &dwc->free_list);
 	list_move(&desc->desc_node, &dwc->free_list);
 
-	/*
-	 * We use dma_unmap_page() regardless of how the buffers were
-	 * mapped before they were submitted...
-	 */
-	if (!(txd->flags & DMA_COMPL_SKIP_DEST_UNMAP))
-		dma_unmap_page(chan2parent(&dwc->chan), desc->lli.dar,
-			       desc->len, DMA_FROM_DEVICE);
-	if (!(txd->flags & DMA_COMPL_SKIP_SRC_UNMAP))
-		dma_unmap_page(chan2parent(&dwc->chan), desc->lli.sar,
-			       desc->len, DMA_TO_DEVICE);
+	if (!dwc->chan.private) {
+		struct device *parent = chan2parent(&dwc->chan);
+		if (!(txd->flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
+			if (txd->flags & DMA_COMPL_DEST_UNMAP_SINGLE)
+				dma_unmap_single(parent, desc->lli.dar,
+						desc->len, DMA_FROM_DEVICE);
+			else
+				dma_unmap_page(parent, desc->lli.dar,
+						desc->len, DMA_FROM_DEVICE);
+		}
+		if (!(txd->flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
+			if (txd->flags & DMA_COMPL_SRC_UNMAP_SINGLE)
+				dma_unmap_single(parent, desc->lli.sar,
+						desc->len, DMA_TO_DEVICE);
+			else
+				dma_unmap_page(parent, desc->lli.sar,
+						desc->len, DMA_TO_DEVICE);
+		}
+	}
 
 	/*
 	 * The API requires that no submissions are done from a
@@ -289,7 +298,7 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
 			/* This one is currently in progress */
 			return;
 
-		list_for_each_entry(child, &desc->txd.tx_list, desc_node)
+		list_for_each_entry(child, &desc->tx_list, desc_node)
 			if (child->lli.llp == llp)
 				/* Currently in progress */
 				return;
@@ -356,7 +365,7 @@ static void dwc_handle_error(struct dw_dma *dw, struct dw_dma_chan *dwc)
 	dev_printk(KERN_CRIT, chan2dev(&dwc->chan),
 			"  cookie: %d\n", bad_desc->txd.cookie);
 	dwc_dump_lli(dwc, &bad_desc->lli);
-	list_for_each_entry(child, &bad_desc->txd.tx_list, desc_node)
+	list_for_each_entry(child, &bad_desc->tx_list, desc_node)
 		dwc_dump_lli(dwc, &child->lli);
 
 	/* Pretend the descriptor completed successfully */
@@ -608,7 +617,7 @@ dwc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 					prev->txd.phys, sizeof(prev->lli),
 					DMA_TO_DEVICE);
 			list_add_tail(&desc->desc_node,
-					&first->txd.tx_list);
+					&first->tx_list);
 		}
 		prev = desc;
 	}
@@ -658,8 +667,6 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	reg_width = dws->reg_width;
 	prev = first = NULL;
 
-	sg_len = dma_map_sg(chan2parent(chan), sgl, sg_len, direction);
-
 	switch (direction) {
 	case DMA_TO_DEVICE:
 		ctllo = (DWC_DEFAULT_CTLLO
@@ -700,7 +707,7 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 						sizeof(prev->lli),
 						DMA_TO_DEVICE);
 				list_add_tail(&desc->desc_node,
-						&first->txd.tx_list);
+						&first->tx_list);
 			}
 			prev = desc;
 			total_len += len;
@@ -746,7 +753,7 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 						sizeof(prev->lli),
 						DMA_TO_DEVICE);
 				list_add_tail(&desc->desc_node,
-						&first->txd.tx_list);
+						&first->tx_list);
 			}
 			prev = desc;
 			total_len += len;
@@ -902,6 +909,7 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan)
 			break;
 		}
 
+		INIT_LIST_HEAD(&desc->tx_list);
 		dma_async_tx_descriptor_init(&desc->txd, chan);
 		desc->txd.tx_submit = dwc_tx_submit;
 		desc->txd.flags = DMA_CTRL_ACK;

drivers/dma/dw_dmac_regs.h

@@ -217,6 +217,7 @@ struct dw_desc {
 
 	/* THEN values for driver housekeeping */
 	struct list_head		desc_node;
+	struct list_head		tx_list;
 	struct dma_async_tx_descriptor	txd;
 	size_t				len;
 };

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
@@ -29,6 +34,7 @@
 #include <linux/dmapool.h>
 #include <linux/of_platform.h>
 
+#include <asm/fsldma.h>
 #include "fsldma.h"
 
 static void dma_init(struct fsl_dma_chan *fsl_chan)
@@ -49,9 +55,10 @@ 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 +143,16 @@ 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;
@@ -272,29 +280,41 @@ static void fsl_chan_set_dest_loop_size(struct fsl_dma_chan *fsl_chan, int size)
 	}
 }
 
+/**
+ * fsl_chan_set_request_count - Set DMA Request Count for external control
+ * @fsl_chan : Freescale DMA channel
+ * @size     : Number of bytes to transfer in a single request
+ *
+ * The Freescale DMA channel can be controlled by the external signal DREQ#.
+ * The DMA request count is how many bytes are allowed to transfer before
+ * pausing the channel, after which a new assertion of DREQ# resumes channel
+ * operation.
+ *
+ * A size of 0 disables external pause control. The maximum size is 1024.
+ */
+static void fsl_chan_set_request_count(struct fsl_dma_chan *fsl_chan, int size)
+{
+	BUG_ON(size > 1024);
+	DMA_OUT(fsl_chan, &fsl_chan->reg_base->mr,
+		DMA_IN(fsl_chan, &fsl_chan->reg_base->mr, 32)
+			| ((__ilog2(size) << 24) & 0x0f000000),
+		32);
+}
+
 /**
  * fsl_chan_toggle_ext_pause - Toggle channel external pause status
  * @fsl_chan : Freescale DMA channel
- * @size     : Pause control size, 0 for disable external pause control.
- *             The maximum is 1024.
+ * @enable   : 0 is disabled, 1 is enabled.
  *
- * The Freescale DMA channel can be controlled by the external
- * signal DREQ#. The pause control size is how many bytes are allowed
- * to transfer before pausing the channel, after which a new assertion
- * of DREQ# resumes channel operation.
+ * The Freescale DMA channel can be controlled by the external signal DREQ#.
+ * The DMA Request Count feature should be used in addition to this feature
+ * to set the number of bytes to transfer before pausing the channel.
  */
-static void fsl_chan_toggle_ext_pause(struct fsl_dma_chan *fsl_chan, int size)
+static void fsl_chan_toggle_ext_pause(struct fsl_dma_chan *fsl_chan, int enable)
 {
-	if (size > 1024)
-		return;
-
-	if (size) {
-		DMA_OUT(fsl_chan, &fsl_chan->reg_base->mr,
-			DMA_IN(fsl_chan, &fsl_chan->reg_base->mr, 32)
-				| ((__ilog2(size) << 24) & 0x0f000000),
-			32);
+	if (enable)
 		fsl_chan->feature |= FSL_DMA_CHAN_PAUSE_EXT;
-	} else
+	else
 		fsl_chan->feature &= ~FSL_DMA_CHAN_PAUSE_EXT;
 }
 
@@ -319,7 +339,8 @@ static void fsl_chan_toggle_ext_start(struct fsl_dma_chan *fsl_chan, int enable)
 static dma_cookie_t fsl_dma_tx_submit(struct dma_async_tx_descriptor *tx)
 {
 	struct fsl_dma_chan *fsl_chan = to_fsl_chan(tx->chan);
-	struct fsl_desc_sw *desc;
+	struct fsl_desc_sw *desc = tx_to_fsl_desc(tx);
+	struct fsl_desc_sw *child;
 	unsigned long flags;
 	dma_cookie_t cookie;
 
@@ -327,7 +348,7 @@ static dma_cookie_t fsl_dma_tx_submit(struct dma_async_tx_descriptor *tx)
 	spin_lock_irqsave(&fsl_chan->desc_lock, flags);
 
 	cookie = fsl_chan->common.cookie;
-	list_for_each_entry(desc, &tx->tx_list, node) {
+	list_for_each_entry(child, &desc->tx_list, node) {
 		cookie++;
 		if (cookie < 0)
 			cookie = 1;
@@ -336,8 +357,8 @@ static dma_cookie_t fsl_dma_tx_submit(struct dma_async_tx_descriptor *tx)
 	}
 
 	fsl_chan->common.cookie = cookie;
-	append_ld_queue(fsl_chan, tx_to_fsl_desc(tx));
-	list_splice_init(&tx->tx_list, fsl_chan->ld_queue.prev);
+	append_ld_queue(fsl_chan, desc);
+	list_splice_init(&desc->tx_list, fsl_chan->ld_queue.prev);
 
 	spin_unlock_irqrestore(&fsl_chan->desc_lock, flags);
 
@@ -359,6 +380,7 @@ static struct fsl_desc_sw *fsl_dma_alloc_descriptor(
 	desc_sw = dma_pool_alloc(fsl_chan->desc_pool, GFP_ATOMIC, &pdesc);
 	if (desc_sw) {
 		memset(desc_sw, 0, sizeof(struct fsl_desc_sw));
+		INIT_LIST_HEAD(&desc_sw->tx_list);
 		dma_async_tx_descriptor_init(&desc_sw->async_tx,
 						&fsl_chan->common);
 		desc_sw->async_tx.tx_submit = fsl_dma_tx_submit;
@@ -448,7 +470,7 @@ fsl_dma_prep_interrupt(struct dma_chan *chan, unsigned long flags)
 	new->async_tx.flags = flags;
 
 	/* Insert the link descriptor to the LD ring */
-	list_add_tail(&new->node, &new->async_tx.tx_list);
+	list_add_tail(&new->node, &new->tx_list);
 
 	/* Set End-of-link to the last link descriptor of new list*/
 	set_ld_eol(fsl_chan, new);
@@ -506,7 +528,7 @@ static struct dma_async_tx_descriptor *fsl_dma_prep_memcpy(
 		dma_dest += copy;
 
 		/* Insert the link descriptor to the LD ring */
-		list_add_tail(&new->node, &first->async_tx.tx_list);
+		list_add_tail(&new->node, &first->tx_list);
 	} while (len);
 
 	new->async_tx.flags = flags; /* client is in control of this ack */
@@ -521,7 +543,7 @@ fail:
 	if (!first)
 		return NULL;
 
-	list = &first->async_tx.tx_list;
+	list = &first->tx_list;
 	list_for_each_entry_safe_reverse(new, prev, list, node) {
 		list_del(&new->node);
 		dma_pool_free(fsl_chan->desc_pool, new, new->async_tx.phys);
@@ -530,6 +552,229 @@ fail:
 	return NULL;
 }
 
+/**
+ * fsl_dma_prep_slave_sg - prepare descriptors for a DMA_SLAVE transaction
+ * @chan: DMA channel
+ * @sgl: scatterlist to transfer to/from
+ * @sg_len: number of entries in @scatterlist
+ * @direction: DMA direction
+ * @flags: DMAEngine flags
+ *
+ * Prepare a set of descriptors for a DMA_SLAVE transaction. Following the
+ * DMA_SLAVE API, this gets the device-specific information from the
+ * chan->private variable.
+ */
+static struct dma_async_tx_descriptor *fsl_dma_prep_slave_sg(
+	struct dma_chan *chan, struct scatterlist *sgl, unsigned int sg_len,
+	enum dma_data_direction direction, unsigned long flags)
+{
+	struct fsl_dma_chan *fsl_chan;
+	struct fsl_desc_sw *first = NULL, *prev = NULL, *new = NULL;
+	struct fsl_dma_slave *slave;
+	struct list_head *tx_list;
+	size_t copy;
+
+	int i;
+	struct scatterlist *sg;
+	size_t sg_used;
+	size_t hw_used;
+	struct fsl_dma_hw_addr *hw;
+	dma_addr_t dma_dst, dma_src;
+
+	if (!chan)
+		return NULL;
+
+	if (!chan->private)
+		return NULL;
+
+	fsl_chan = to_fsl_chan(chan);
+	slave = chan->private;
+
+	if (list_empty(&slave->addresses))
+		return NULL;
+
+	hw = list_first_entry(&slave->addresses, struct fsl_dma_hw_addr, entry);
+	hw_used = 0;
+
+	/*
+	 * Build the hardware transaction to copy from the scatterlist to
+	 * the hardware, or from the hardware to the scatterlist
+	 *
+	 * If you are copying from the hardware to the scatterlist and it
+	 * takes two hardware entries to fill an entire page, then both
+	 * hardware entries will be coalesced into the same page
+	 *
+	 * If you are copying from the scatterlist to the hardware and a
+	 * single page can fill two hardware entries, then the data will
+	 * be read out of the page into the first hardware entry, and so on
+	 */
+	for_each_sg(sgl, sg, sg_len, i) {
+		sg_used = 0;
+
+		/* Loop until the entire scatterlist entry is used */
+		while (sg_used < sg_dma_len(sg)) {
+
+			/*
+			 * If we've used up the current hardware address/length
+			 * pair, we need to load a new one
+			 *
+			 * This is done in a while loop so that descriptors with
+			 * length == 0 will be skipped
+			 */
+			while (hw_used >= hw->length) {
+
+				/*
+				 * If the current hardware entry is the last
+				 * entry in the list, we're finished
+				 */
+				if (list_is_last(&hw->entry, &slave->addresses))
+					goto finished;
+
+				/* Get the next hardware address/length pair */
+				hw = list_entry(hw->entry.next,
+						struct fsl_dma_hw_addr, entry);
+				hw_used = 0;
+			}
+
+			/* Allocate the link descriptor from DMA pool */
+			new = fsl_dma_alloc_descriptor(fsl_chan);
+			if (!new) {
+				dev_err(fsl_chan->dev, "No free memory for "
+						       "link descriptor\n");
+				goto fail;
+			}
+#ifdef FSL_DMA_LD_DEBUG
+			dev_dbg(fsl_chan->dev, "new link desc alloc %p\n", new);
+#endif
+
+			/*
+			 * Calculate the maximum number of bytes to transfer,
+			 * making sure it is less than the DMA controller limit
+			 */
+			copy = min_t(size_t, sg_dma_len(sg) - sg_used,
+					     hw->length - hw_used);
+			copy = min_t(size_t, copy, FSL_DMA_BCR_MAX_CNT);
+
+			/*
+			 * DMA_FROM_DEVICE
+			 * from the hardware to the scatterlist
+			 *
+			 * DMA_TO_DEVICE
+			 * from the scatterlist to the hardware
+			 */
+			if (direction == DMA_FROM_DEVICE) {
+				dma_src = hw->address + hw_used;
+				dma_dst = sg_dma_address(sg) + sg_used;
+			} else {
+				dma_src = sg_dma_address(sg) + sg_used;
+				dma_dst = hw->address + hw_used;
+			}
+
+			/* Fill in the descriptor */
+			set_desc_cnt(fsl_chan, &new->hw, copy);
+			set_desc_src(fsl_chan, &new->hw, dma_src);
+			set_desc_dest(fsl_chan, &new->hw, dma_dst);
+
+			/*
+			 * If this is not the first descriptor, chain the
+			 * current descriptor after the previous descriptor
+			 */
+			if (!first) {
+				first = new;
+			} else {
+				set_desc_next(fsl_chan, &prev->hw,
+					      new->async_tx.phys);
+			}
+
+			new->async_tx.cookie = 0;
+			async_tx_ack(&new->async_tx);
+
+			prev = new;
+			sg_used += copy;
+			hw_used += copy;
+
+			/* Insert the link descriptor into the LD ring */
+			list_add_tail(&new->node, &first->tx_list);
+		}
+	}
+
+finished:
+
+	/* All of the hardware address/length pairs had length == 0 */
+	if (!first || !new)
+		return NULL;
+
+	new->async_tx.flags = flags;
+	new->async_tx.cookie = -EBUSY;
+
+	/* Set End-of-link to the last link descriptor of new list */
+	set_ld_eol(fsl_chan, new);
+
+	/* Enable extra controller features */
+	if (fsl_chan->set_src_loop_size)
+		fsl_chan->set_src_loop_size(fsl_chan, slave->src_loop_size);
+
+	if (fsl_chan->set_dest_loop_size)
+		fsl_chan->set_dest_loop_size(fsl_chan, slave->dst_loop_size);
+
+	if (fsl_chan->toggle_ext_start)
+		fsl_chan->toggle_ext_start(fsl_chan, slave->external_start);
+
+	if (fsl_chan->toggle_ext_pause)
+		fsl_chan->toggle_ext_pause(fsl_chan, slave->external_pause);
+
+	if (fsl_chan->set_request_count)
+		fsl_chan->set_request_count(fsl_chan, slave->request_count);
+
+	return &first->async_tx;
+
+fail:
+	/* If first was not set, then we failed to allocate the very first
+	 * descriptor, and we're done */
+	if (!first)
+		return NULL;
+
+	/*
+	 * First is set, so all of the descriptors we allocated have been added
+	 * to first->tx_list, INCLUDING "first" itself. Therefore we
+	 * must traverse the list backwards freeing each descriptor in turn
+	 *
+	 * We're re-using variables for the loop, oh well
+	 */
+	tx_list = &first->tx_list;
+	list_for_each_entry_safe_reverse(new, prev, tx_list, node) {
+		list_del_init(&new->node);
+		dma_pool_free(fsl_chan->desc_pool, new, new->async_tx.phys);
+	}
+
+	return NULL;
+}
+
+static void fsl_dma_device_terminate_all(struct dma_chan *chan)
+{
+	struct fsl_dma_chan *fsl_chan;
+	struct fsl_desc_sw *desc, *tmp;
+	unsigned long flags;
+
+	if (!chan)
+		return;
+
+	fsl_chan = to_fsl_chan(chan);
+
+	/* Halt the DMA engine */
+	dma_halt(fsl_chan);
+
+	spin_lock_irqsave(&fsl_chan->desc_lock, flags);
+
+	/* Remove and free all of the descriptors in the LD queue */
+	list_for_each_entry_safe(desc, tmp, &fsl_chan->ld_queue, node) {
+		list_del(&desc->node);
+		dma_pool_free(fsl_chan->desc_pool, desc, desc->async_tx.phys);
+	}
+
+	spin_unlock_irqrestore(&fsl_chan->desc_lock, flags);
+}
+
 /**
  * fsl_dma_update_completed_cookie - Update the completed cookie.
  * @fsl_chan : Freescale DMA channel
@@ -871,11 +1116,12 @@ 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;
+		new_fsl_chan->set_request_count = fsl_chan_set_request_count;
 	}
 
 	spin_lock_init(&new_fsl_chan->desc_lock);
@@ -955,12 +1201,15 @@ static int __devinit of_fsl_dma_probe(struct of_device *dev,
 
 	dma_cap_set(DMA_MEMCPY, fdev->common.cap_mask);
 	dma_cap_set(DMA_INTERRUPT, fdev->common.cap_mask);
+	dma_cap_set(DMA_SLAVE, fdev->common.cap_mask);
 	fdev->common.device_alloc_chan_resources = fsl_dma_alloc_chan_resources;
 	fdev->common.device_free_chan_resources = fsl_dma_free_chan_resources;
 	fdev->common.device_prep_dma_interrupt = fsl_dma_prep_interrupt;
 	fdev->common.device_prep_dma_memcpy = fsl_dma_prep_memcpy;
 	fdev->common.device_is_tx_complete = fsl_dma_is_complete;
 	fdev->common.device_issue_pending = fsl_dma_memcpy_issue_pending;
+	fdev->common.device_prep_slave_sg = fsl_dma_prep_slave_sg;
+	fdev->common.device_terminate_all = fsl_dma_device_terminate_all;
 	fdev->common.dev = &dev->dev;
 
 	fdev->irq = irq_of_parse_and_map(dev->node, 0);

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
@@ -89,6 +90,7 @@ struct fsl_dma_ld_hw {
 struct fsl_desc_sw {
 	struct fsl_dma_ld_hw hw;
 	struct list_head node;
+	struct list_head tx_list;
 	struct dma_async_tx_descriptor async_tx;
 	struct list_head *ld;
 	void *priv;
@@ -142,10 +144,11 @@ struct fsl_dma_chan {
 	struct tasklet_struct tasklet;
 	u32 feature;
 
-	void (*toggle_ext_pause)(struct fsl_dma_chan *fsl_chan, int size);
+	void (*toggle_ext_pause)(struct fsl_dma_chan *fsl_chan, int enable);
 	void (*toggle_ext_start)(struct fsl_dma_chan *fsl_chan, int enable);
 	void (*set_src_loop_size)(struct fsl_dma_chan *fsl_chan, int size);
 	void (*set_dest_loop_size)(struct fsl_dma_chan *fsl_chan, int size);
+	void (*set_request_count)(struct fsl_dma_chan *fsl_chan, int size);
 };
 
 #define to_fsl_chan(chan) container_of(chan, struct fsl_dma_chan, common)

drivers/dma/ioat/dma.c

@@ -251,12 +251,12 @@ static dma_cookie_t ioat1_tx_submit(struct dma_async_tx_descriptor *tx)
 	dev_dbg(to_dev(&ioat->base), "%s: cookie: %d\n", __func__, cookie);
 
 	/* write address into NextDescriptor field of last desc in chain */
-	first = to_ioat_desc(tx->tx_list.next);
+	first = to_ioat_desc(desc->tx_list.next);
 	chain_tail = to_ioat_desc(ioat->used_desc.prev);
 	/* make descriptor updates globally visible before chaining */
 	wmb();
 	chain_tail->hw->next = first->txd.phys;
-	list_splice_tail_init(&tx->tx_list, &ioat->used_desc);
+	list_splice_tail_init(&desc->tx_list, &ioat->used_desc);
 	dump_desc_dbg(ioat, chain_tail);
 	dump_desc_dbg(ioat, first);
 
@@ -298,6 +298,7 @@ ioat_dma_alloc_descriptor(struct ioat_dma_chan *ioat, gfp_t flags)
 
 	memset(desc, 0, sizeof(*desc));
 
+	INIT_LIST_HEAD(&desc_sw->tx_list);
 	dma_async_tx_descriptor_init(&desc_sw->txd, &ioat->base.common);
 	desc_sw->txd.tx_submit = ioat1_tx_submit;
 	desc_sw->hw = desc;
@@ -522,7 +523,7 @@ ioat1_dma_prep_memcpy(struct dma_chan *c, dma_addr_t dma_dest,
 
 	desc->txd.flags = flags;
 	desc->len = total_len;
-	list_splice(&chain, &desc->txd.tx_list);
+	list_splice(&chain, &desc->tx_list);
 	hw->ctl_f.int_en = !!(flags & DMA_PREP_INTERRUPT);
 	hw->ctl_f.compl_write = 1;
 	hw->tx_cnt = tx_cnt;

drivers/dma/ioat/dma.h

@@ -171,7 +171,7 @@ ioat_is_complete(struct dma_chan *c, dma_cookie_t cookie,
  * struct ioat_desc_sw - wrapper around hardware descriptor
  * @hw: hardware DMA descriptor (for memcpy)
  * @node: this descriptor will either be on the free list,
- *     or attached to a transaction list (async_tx.tx_list)
+ *     or attached to a transaction list (tx_list)
  * @txd: the generic software descriptor for all engines
  * @id: identifier for debug
  */
@@ -179,6 +179,7 @@ struct ioat_desc_sw {
 	struct ioat_dma_descriptor *hw;
 	struct list_head node;
 	size_t len;
+	struct list_head tx_list;
 	struct dma_async_tx_descriptor txd;
 	#ifdef DEBUG
 	int id;

drivers/dma/ioat/dma_v2.c

@@ -397,11 +397,12 @@ static struct ioat_ring_ent *ioat2_alloc_ring_ent(struct dma_chan *chan, gfp_t f
 		return NULL;
 	memset(hw, 0, sizeof(*hw));
 
-	desc = kzalloc(sizeof(*desc), flags);
+	desc = kmem_cache_alloc(ioat2_cache, flags);
 	if (!desc) {
 		pci_pool_free(dma->dma_pool, hw, phys);
 		return NULL;
 	}
+	memset(desc, 0, sizeof(*desc));
 
 	dma_async_tx_descriptor_init(&desc->txd, chan);
 	desc->txd.tx_submit = ioat2_tx_submit_unlock;
@@ -416,7 +417,7 @@ static void ioat2_free_ring_ent(struct ioat_ring_ent *desc, struct dma_chan *cha
 
 	dma = to_ioatdma_device(chan->device);
 	pci_pool_free(dma->dma_pool, desc->hw, desc->txd.phys);
-	kfree(desc);
+	kmem_cache_free(ioat2_cache, desc);
 }
 
 static struct ioat_ring_ent **ioat2_alloc_ring(struct dma_chan *c, int order, gfp_t flags)

drivers/dma/ioat/dma_v2.h

@@ -142,8 +142,8 @@ struct ioat_ring_ent {
 		struct ioat_pq_update_descriptor *pqu;
 		struct ioat_raw_descriptor *raw;
 	};
-	struct dma_async_tx_descriptor txd;
 	size_t len;
+	struct dma_async_tx_descriptor txd;
 	enum sum_check_flags *result;
 	#ifdef DEBUG
 	int id;
@@ -186,4 +186,5 @@ void __ioat2_issue_pending(struct ioat2_dma_chan *ioat);
 void ioat2_cleanup_tasklet(unsigned long data);
 void ioat2_timer_event(unsigned long data);
 extern struct kobj_type ioat2_ktype;
+extern struct kmem_cache *ioat2_cache;
 #endif /* IOATDMA_V2_H */

drivers/dma/ioat/pci.c

@@ -83,6 +83,8 @@ static int ioat_dca_enabled = 1;
 module_param(ioat_dca_enabled, int, 0644);
 MODULE_PARM_DESC(ioat_dca_enabled, "control support of dca service (default: 1)");
 
+struct kmem_cache *ioat2_cache;
+
 #define DRV_NAME "ioatdma"
 
 static struct pci_driver ioat_pci_driver = {
@@ -182,15 +184,27 @@ static void __devexit ioat_remove(struct pci_dev *pdev)
 
 static int __init ioat_init_module(void)
 {
+	int err;
+
 	pr_info("%s: Intel(R) QuickData Technology Driver %s\n",
 		DRV_NAME, IOAT_DMA_VERSION);
 
-	return pci_register_driver(&ioat_pci_driver);
+	ioat2_cache = kmem_cache_create("ioat2", sizeof(struct ioat_ring_ent),
+					0, SLAB_HWCACHE_ALIGN, NULL);
+	if (!ioat2_cache)
+		return -ENOMEM;
+
+	err = pci_register_driver(&ioat_pci_driver);
+	if (err)
+		kmem_cache_destroy(ioat2_cache);
+
+	return err;
 }
 module_init(ioat_init_module);
 
 static void __exit ioat_exit_module(void)
 {
 	pci_unregister_driver(&ioat_pci_driver);
+	kmem_cache_destroy(ioat2_cache);
 }
 module_exit(ioat_exit_module);

drivers/dma/iop-adma.c

@@ -421,7 +421,7 @@ retry:
 			}
 			alloc_tail->group_head = alloc_start;
 			alloc_tail->async_tx.cookie = -EBUSY;
-			list_splice(&chain, &alloc_tail->async_tx.tx_list);
+			list_splice(&chain, &alloc_tail->tx_list);
 			iop_chan->last_used = last_used;
 			iop_desc_clear_next_desc(alloc_start);
 			iop_desc_clear_next_desc(alloc_tail);
@@ -480,7 +480,7 @@ iop_adma_tx_submit(struct dma_async_tx_descriptor *tx)
 
 	old_chain_tail = list_entry(iop_chan->chain.prev,
 		struct iop_adma_desc_slot, chain_node);
-	list_splice_init(&sw_desc->async_tx.tx_list,
+	list_splice_init(&sw_desc->tx_list,
 			 &old_chain_tail->chain_node);
 
 	/* fix up the hardware chain */
@@ -547,6 +547,7 @@ static int iop_adma_alloc_chan_resources(struct dma_chan *chan)
 
 		dma_async_tx_descriptor_init(&slot->async_tx, chan);
 		slot->async_tx.tx_submit = iop_adma_tx_submit;
+		INIT_LIST_HEAD(&slot->tx_list);
 		INIT_LIST_HEAD(&slot->chain_node);
 		INIT_LIST_HEAD(&slot->slot_node);
 		hw_desc = (char *) iop_chan->device->dma_desc_pool;
@@ -1642,7 +1643,7 @@ static void iop_chan_start_null_memcpy(struct iop_adma_chan *iop_chan)
 	if (sw_desc) {
 		grp_start = sw_desc->group_head;
 
-		list_splice_init(&sw_desc->async_tx.tx_list, &iop_chan->chain);
+		list_splice_init(&sw_desc->tx_list, &iop_chan->chain);
 		async_tx_ack(&sw_desc->async_tx);
 		iop_desc_init_memcpy(grp_start, 0);
 		iop_desc_set_byte_count(grp_start, iop_chan, 0);
@@ -1698,7 +1699,7 @@ static void iop_chan_start_null_xor(struct iop_adma_chan *iop_chan)
 	sw_desc = iop_adma_alloc_slots(iop_chan, slot_cnt, slots_per_op);
 	if (sw_desc) {
 		grp_start = sw_desc->group_head;
-		list_splice_init(&sw_desc->async_tx.tx_list, &iop_chan->chain);
+		list_splice_init(&sw_desc->tx_list, &iop_chan->chain);
 		async_tx_ack(&sw_desc->async_tx);
 		iop_desc_init_null_xor(grp_start, 2, 0);
 		iop_desc_set_byte_count(grp_start, iop_chan, 0);

drivers/dma/mv_xor.c

@@ -517,7 +517,7 @@ retry:
 			}
 			alloc_tail->group_head = alloc_start;
 			alloc_tail->async_tx.cookie = -EBUSY;
-			list_splice(&chain, &alloc_tail->async_tx.tx_list);
+			list_splice(&chain, &alloc_tail->tx_list);
 			mv_chan->last_used = last_used;
 			mv_desc_clear_next_desc(alloc_start);
 			mv_desc_clear_next_desc(alloc_tail);
@@ -565,14 +565,14 @@ mv_xor_tx_submit(struct dma_async_tx_descriptor *tx)
 	cookie = mv_desc_assign_cookie(mv_chan, sw_desc);
 
 	if (list_empty(&mv_chan->chain))
-		list_splice_init(&sw_desc->async_tx.tx_list, &mv_chan->chain);
+		list_splice_init(&sw_desc->tx_list, &mv_chan->chain);
 	else {
 		new_hw_chain = 0;
 
 		old_chain_tail = list_entry(mv_chan->chain.prev,
 					    struct mv_xor_desc_slot,
 					    chain_node);
-		list_splice_init(&grp_start->async_tx.tx_list,
+		list_splice_init(&grp_start->tx_list,
 				 &old_chain_tail->chain_node);
 
 		if (!mv_can_chain(grp_start))
@@ -632,6 +632,7 @@ static int mv_xor_alloc_chan_resources(struct dma_chan *chan)
 		slot->async_tx.tx_submit = mv_xor_tx_submit;
 		INIT_LIST_HEAD(&slot->chain_node);
 		INIT_LIST_HEAD(&slot->slot_node);
+		INIT_LIST_HEAD(&slot->tx_list);
 		hw_desc = (char *) mv_chan->device->dma_desc_pool;
 		slot->async_tx.phys =
 			(dma_addr_t) &hw_desc[idx * MV_XOR_SLOT_SIZE];
@@ -1176,7 +1177,7 @@ 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;
 	}
 

drivers/dma/mv_xor.h

@@ -126,9 +126,8 @@ struct mv_xor_chan {
  * @idx: pool index
  * @unmap_src_cnt: number of xor sources
  * @unmap_len: transaction bytecount
+ * @tx_list: list of slots that make up a multi-descriptor transaction
  * @async_tx: support for the async_tx api
- * @group_list: list of slots that make up a multi-descriptor transaction
- *	for example transfer lengths larger than the supported hw max
  * @xor_check_result: result of zero sum
  * @crc32_result: result crc calculation
  */
@@ -145,6 +144,7 @@ struct mv_xor_desc_slot {
 	u16			unmap_src_cnt;
 	u32			value;
 	size_t			unmap_len;
+	struct list_head	tx_list;
 	struct dma_async_tx_descriptor	async_tx;
 	union {
 		u32		*xor_check_result;

drivers/dma/txx9dmac.h

@@ -0,0 +1,308 @@
+/*
+ * Driver for the TXx9 SoC DMA Controller
+ *
+ * Copyright (C) 2009 Atsushi Nemoto
+ *
+ * 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 TXX9DMAC_H
+#define TXX9DMAC_H
+
+#include <linux/dmaengine.h>
+#include <asm/txx9/dmac.h>
+
+/*
+ * Design Notes:
+ *
+ * This DMAC have four channels and one FIFO buffer.  Each channel can
+ * be configured for memory-memory or device-memory transfer, but only
+ * one channel can do alignment-free memory-memory transfer at a time
+ * while the channel should occupy the FIFO buffer for effective
+ * transfers.
+ *
+ * Instead of dynamically assign the FIFO buffer to channels, I chose
+ * make one dedicated channel for memory-memory transfer.  The
+ * dedicated channel is public.  Other channels are private and used
+ * for slave transfer.  Some devices in the SoC are wired to certain
+ * DMA channel.
+ */
+
+#ifdef CONFIG_MACH_TX49XX
+static inline bool txx9_dma_have_SMPCHN(void)
+{
+	return true;
+}
+#define TXX9_DMA_USE_SIMPLE_CHAIN
+#else
+static inline bool txx9_dma_have_SMPCHN(void)
+{
+	return false;
+}
+#endif
+
+#ifdef __LITTLE_ENDIAN
+#ifdef CONFIG_MACH_TX49XX
+#define CCR_LE	TXX9_DMA_CCR_LE
+#define MCR_LE	0
+#else
+#define CCR_LE	0
+#define MCR_LE	TXX9_DMA_MCR_LE
+#endif
+#else
+#define CCR_LE	0
+#define MCR_LE	0
+#endif
+
+/*
+ * Redefine this macro to handle differences between 32- and 64-bit
+ * addressing, big vs. little endian, etc.
+ */
+#ifdef __BIG_ENDIAN
+#define TXX9_DMA_REG32(name)		u32 __pad_##name; u32 name
+#else
+#define TXX9_DMA_REG32(name)		u32 name; u32 __pad_##name
+#endif
+
+/* Hardware register definitions. */
+struct txx9dmac_cregs {
+#if defined(CONFIG_32BIT) && !defined(CONFIG_64BIT_PHYS_ADDR)
+	TXX9_DMA_REG32(CHAR);	/* Chain Address Register */
+#else
+	u64 CHAR;		/* Chain Address Register */
+#endif
+	u64 SAR;		/* Source Address Register */
+	u64 DAR;		/* Destination Address Register */
+	TXX9_DMA_REG32(CNTR);	/* Count Register */
+	TXX9_DMA_REG32(SAIR);	/* Source Address Increment Register */
+	TXX9_DMA_REG32(DAIR);	/* Destination Address Increment Register */
+	TXX9_DMA_REG32(CCR);	/* Channel Control Register */
+	TXX9_DMA_REG32(CSR);	/* Channel Status Register */
+};
+struct txx9dmac_cregs32 {
+	u32 CHAR;
+	u32 SAR;
+	u32 DAR;
+	u32 CNTR;
+	u32 SAIR;
+	u32 DAIR;
+	u32 CCR;
+	u32 CSR;
+};
+
+struct txx9dmac_regs {
+	/* per-channel registers */
+	struct txx9dmac_cregs	CHAN[TXX9_DMA_MAX_NR_CHANNELS];
+	u64	__pad[9];
+	u64	MFDR;		/* Memory Fill Data Register */
+	TXX9_DMA_REG32(MCR);	/* Master Control Register */
+};
+struct txx9dmac_regs32 {
+	struct txx9dmac_cregs32	CHAN[TXX9_DMA_MAX_NR_CHANNELS];
+	u32	__pad[9];
+	u32	MFDR;
+	u32	MCR;
+};
+
+/* bits for MCR */
+#define TXX9_DMA_MCR_EIS(ch)	(0x10000000<<(ch))
+#define TXX9_DMA_MCR_DIS(ch)	(0x01000000<<(ch))
+#define TXX9_DMA_MCR_RSFIF	0x00000080
+#define TXX9_DMA_MCR_FIFUM(ch)	(0x00000008<<(ch))
+#define TXX9_DMA_MCR_LE		0x00000004
+#define TXX9_DMA_MCR_RPRT	0x00000002
+#define TXX9_DMA_MCR_MSTEN	0x00000001
+
+/* bits for CCRn */
+#define TXX9_DMA_CCR_IMMCHN	0x20000000
+#define TXX9_DMA_CCR_USEXFSZ	0x10000000
+#define TXX9_DMA_CCR_LE		0x08000000
+#define TXX9_DMA_CCR_DBINH	0x04000000
+#define TXX9_DMA_CCR_SBINH	0x02000000
+#define TXX9_DMA_CCR_CHRST	0x01000000
+#define TXX9_DMA_CCR_RVBYTE	0x00800000
+#define TXX9_DMA_CCR_ACKPOL	0x00400000
+#define TXX9_DMA_CCR_REQPL	0x00200000
+#define TXX9_DMA_CCR_EGREQ	0x00100000
+#define TXX9_DMA_CCR_CHDN	0x00080000
+#define TXX9_DMA_CCR_DNCTL	0x00060000
+#define TXX9_DMA_CCR_EXTRQ	0x00010000
+#define TXX9_DMA_CCR_INTRQD	0x0000e000
+#define TXX9_DMA_CCR_INTENE	0x00001000
+#define TXX9_DMA_CCR_INTENC	0x00000800
+#define TXX9_DMA_CCR_INTENT	0x00000400
+#define TXX9_DMA_CCR_CHNEN	0x00000200
+#define TXX9_DMA_CCR_XFACT	0x00000100
+#define TXX9_DMA_CCR_SMPCHN	0x00000020
+#define TXX9_DMA_CCR_XFSZ(order)	(((order) << 2) & 0x0000001c)
+#define TXX9_DMA_CCR_XFSZ_1	TXX9_DMA_CCR_XFSZ(0)
+#define TXX9_DMA_CCR_XFSZ_2	TXX9_DMA_CCR_XFSZ(1)
+#define TXX9_DMA_CCR_XFSZ_4	TXX9_DMA_CCR_XFSZ(2)
+#define TXX9_DMA_CCR_XFSZ_8	TXX9_DMA_CCR_XFSZ(3)
+#define TXX9_DMA_CCR_XFSZ_X4	TXX9_DMA_CCR_XFSZ(4)
+#define TXX9_DMA_CCR_XFSZ_X8	TXX9_DMA_CCR_XFSZ(5)
+#define TXX9_DMA_CCR_XFSZ_X16	TXX9_DMA_CCR_XFSZ(6)
+#define TXX9_DMA_CCR_XFSZ_X32	TXX9_DMA_CCR_XFSZ(7)
+#define TXX9_DMA_CCR_MEMIO	0x00000002
+#define TXX9_DMA_CCR_SNGAD	0x00000001
+
+/* bits for CSRn */
+#define TXX9_DMA_CSR_CHNEN	0x00000400
+#define TXX9_DMA_CSR_STLXFER	0x00000200
+#define TXX9_DMA_CSR_XFACT	0x00000100
+#define TXX9_DMA_CSR_ABCHC	0x00000080
+#define TXX9_DMA_CSR_NCHNC	0x00000040
+#define TXX9_DMA_CSR_NTRNFC	0x00000020
+#define TXX9_DMA_CSR_EXTDN	0x00000010
+#define TXX9_DMA_CSR_CFERR	0x00000008
+#define TXX9_DMA_CSR_CHERR	0x00000004
+#define TXX9_DMA_CSR_DESERR	0x00000002
+#define TXX9_DMA_CSR_SORERR	0x00000001
+
+struct txx9dmac_chan {
+	struct dma_chan		chan;
+	struct dma_device	dma;
+	struct txx9dmac_dev	*ddev;
+	void __iomem		*ch_regs;
+	struct tasklet_struct	tasklet;
+	int			irq;
+	u32			ccr;
+
+	spinlock_t		lock;
+
+	/* these other elements are all protected by lock */
+	dma_cookie_t		completed;
+	struct list_head	active_list;
+	struct list_head	queue;
+	struct list_head	free_list;
+
+	unsigned int		descs_allocated;
+};
+
+struct txx9dmac_dev {
+	void __iomem		*regs;
+	struct tasklet_struct	tasklet;
+	int			irq;
+	struct txx9dmac_chan	*chan[TXX9_DMA_MAX_NR_CHANNELS];
+	bool			have_64bit_regs;
+	unsigned int		descsize;
+};
+
+static inline bool __is_dmac64(const struct txx9dmac_dev *ddev)
+{
+	return ddev->have_64bit_regs;
+}
+
+static inline bool is_dmac64(const struct txx9dmac_chan *dc)
+{
+	return __is_dmac64(dc->ddev);
+}
+
+#ifdef TXX9_DMA_USE_SIMPLE_CHAIN
+/* Hardware descriptor definition. (for simple-chain) */
+struct txx9dmac_hwdesc {
+#if defined(CONFIG_32BIT) && !defined(CONFIG_64BIT_PHYS_ADDR)
+	TXX9_DMA_REG32(CHAR);
+#else
+	u64 CHAR;
+#endif
+	u64 SAR;
+	u64 DAR;
+	TXX9_DMA_REG32(CNTR);
+};
+struct txx9dmac_hwdesc32 {
+	u32 CHAR;
+	u32 SAR;
+	u32 DAR;
+	u32 CNTR;
+};
+#else
+#define txx9dmac_hwdesc txx9dmac_cregs
+#define txx9dmac_hwdesc32 txx9dmac_cregs32
+#endif
+
+struct txx9dmac_desc {
+	/* FIRST values the hardware uses */
+	union {
+		struct txx9dmac_hwdesc hwdesc;
+		struct txx9dmac_hwdesc32 hwdesc32;
+	};
+
+	/* THEN values for driver housekeeping */
+	struct list_head		desc_node ____cacheline_aligned;
+	struct list_head		tx_list;
+	struct dma_async_tx_descriptor	txd;
+	size_t				len;
+};
+
+#ifdef TXX9_DMA_USE_SIMPLE_CHAIN
+
+static inline bool txx9dmac_chan_INTENT(struct txx9dmac_chan *dc)
+{
+	return (dc->ccr & TXX9_DMA_CCR_INTENT) != 0;
+}
+
+static inline void txx9dmac_chan_set_INTENT(struct txx9dmac_chan *dc)
+{
+	dc->ccr |= TXX9_DMA_CCR_INTENT;
+}
+
+static inline void txx9dmac_desc_set_INTENT(struct txx9dmac_dev *ddev,
+					    struct txx9dmac_desc *desc)
+{
+}
+
+static inline void txx9dmac_chan_set_SMPCHN(struct txx9dmac_chan *dc)
+{
+	dc->ccr |= TXX9_DMA_CCR_SMPCHN;
+}
+
+static inline void txx9dmac_desc_set_nosimple(struct txx9dmac_dev *ddev,
+					      struct txx9dmac_desc *desc,
+					      u32 sair, u32 dair, u32 ccr)
+{
+}
+
+#else /* TXX9_DMA_USE_SIMPLE_CHAIN */
+
+static inline bool txx9dmac_chan_INTENT(struct txx9dmac_chan *dc)
+{
+	return true;
+}
+
+static void txx9dmac_chan_set_INTENT(struct txx9dmac_chan *dc)
+{
+}
+
+static inline void txx9dmac_desc_set_INTENT(struct txx9dmac_dev *ddev,
+					    struct txx9dmac_desc *desc)
+{
+	if (__is_dmac64(ddev))
+		desc->hwdesc.CCR |= TXX9_DMA_CCR_INTENT;
+	else
+		desc->hwdesc32.CCR |= TXX9_DMA_CCR_INTENT;
+}
+
+static inline void txx9dmac_chan_set_SMPCHN(struct txx9dmac_chan *dc)
+{
+}
+
+static inline void txx9dmac_desc_set_nosimple(struct txx9dmac_dev *ddev,
+					      struct txx9dmac_desc *desc,
+					      u32 sai, u32 dai, u32 ccr)
+{
+	if (__is_dmac64(ddev)) {
+		desc->hwdesc.SAIR = sai;
+		desc->hwdesc.DAIR = dai;
+		desc->hwdesc.CCR = ccr;
+	} else {
+		desc->hwdesc32.SAIR = sai;
+		desc->hwdesc32.DAIR = dai;
+		desc->hwdesc32.CCR = ccr;
+	}
+}
+
+#endif /* TXX9_DMA_USE_SIMPLE_CHAIN */
+
+#endif /* TXX9DMAC_H */