Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/djbw/async_tx

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/djbw/async_tx: (66 commits)
  avr32: at32ap700x: fix typo in DMA master configuration
  dmaengine/dmatest: Pass timeout via module params
  dma: let IMX_DMA depend on IMX_HAVE_DMA_V1 instead of an explicit list of SoCs
  fsldma: make halt behave nicely on all supported controllers
  fsldma: reduce locking during descriptor cleanup
  fsldma: support async_tx dependencies and automatic unmapping
  fsldma: fix controller lockups
  fsldma: minor codingstyle and consistency fixes
  fsldma: improve link descriptor debugging
  fsldma: use channel name in printk output
  fsldma: move related helper functions near each other
  dmatest: fix automatic buffer unmap type
  drivers, pch_dma: Fix warning when CONFIG_PM=n.
  dmaengine/dw_dmac fix: use readl & writel instead of __raw_readl & __raw_writel
  avr32: at32ap700x: Specify DMA Flow Controller, Src and Dst msize
  dw_dmac: Setting Default Burst length for transfers as 16.
  dw_dmac: Allow src/dst msize & flow controller to be configured at runtime
  dw_dmac: Changing type of src_master and dest_master to u8.
  dw_dmac: Pass Channel Priority from platform_data
  dw_dmac: Pass Channel Allocation Order from platform_data
  ...

arch/arm/mach-mxs/include/mach/dma.h

+/*
+ * Copyright 2011 Freescale Semiconductor, Inc. All Rights Reserved.
+ *
+ * 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 __MACH_MXS_DMA_H__
+#define __MACH_MXS_DMA_H__
+
+struct mxs_dma_data {
+	int chan_irq;
+};
+
+static inline int mxs_dma_is_apbh(struct dma_chan *chan)
+{
+	return !strcmp(dev_name(chan->device->dev), "mxs-dma-apbh");
+}
+
+static inline int mxs_dma_is_apbx(struct dma_chan *chan)
+{
+	return !strcmp(dev_name(chan->device->dev), "mxs-dma-apbx");
+}
+
+#endif /* __MACH_MXS_DMA_H__ */

arch/arm/plat-nomadik/include/plat/ste_dma40.h

@@ -104,6 +104,8 @@ struct stedma40_half_channel_info {
  *
  * @dir: MEM 2 MEM, PERIPH 2 MEM , MEM 2 PERIPH, PERIPH 2 PERIPH
  * @high_priority: true if high-priority
+ * @realtime: true if realtime mode is to be enabled.  Only available on DMA40
+ * version 3+, i.e DB8500v2+
  * @mode: channel mode: physical, logical, or operation
  * @mode_opt: options for the chosen channel mode
  * @src_dev_type: Src device type
@@ -119,6 +121,7 @@ struct stedma40_half_channel_info {
 struct stedma40_chan_cfg {
 	enum stedma40_xfer_dir			 dir;
 	bool					 high_priority;
+	bool					 realtime;
 	enum stedma40_mode			 mode;
 	enum stedma40_mode_opt			 mode_opt;
 	int					 src_dev_type;
@@ -168,25 +171,6 @@ struct stedma40_platform_data {
 
 bool stedma40_filter(struct dma_chan *chan, void *data);
 
-/**
- * stedma40_memcpy_sg() - extension of the dma framework, memcpy to/from
- * scattergatter lists.
- *
- * @chan: dmaengine handle
- * @sgl_dst: Destination scatter list
- * @sgl_src: Source scatter list
- * @sgl_len: The length of each scatterlist. Both lists must be of equal length
- * and each element must match the corresponding element in the other scatter
- * list.
- * @flags: is actually enum dma_ctrl_flags. See dmaengine.h
- */
-
-struct dma_async_tx_descriptor *stedma40_memcpy_sg(struct dma_chan *chan,
-						   struct scatterlist *sgl_dst,
-						   struct scatterlist *sgl_src,
-						   unsigned int sgl_len,
-						   unsigned long flags);
-
 /**
  * stedma40_slave_mem() - Transfers a raw data buffer to or from a slave
  * (=device)

arch/avr32/mach-at32ap/at32ap700x.c

@@ -2048,6 +2048,11 @@ at32_add_device_ac97c(unsigned int id, struct ac97c_platform_data *data,
 		rx_dws->reg_width = DW_DMA_SLAVE_WIDTH_16BIT;
 		rx_dws->cfg_hi = DWC_CFGH_SRC_PER(3);
 		rx_dws->cfg_lo &= ~(DWC_CFGL_HS_DST_POL | DWC_CFGL_HS_SRC_POL);
+		rx_dws->src_master = 0;
+		rx_dws->dst_master = 1;
+		rx_dws->src_msize = DW_DMA_MSIZE_1;
+		rx_dws->dst_msize = DW_DMA_MSIZE_1;
+		rx_dws->fc = DW_DMA_FC_D_P2M;
 	}
 
 	/* Check if DMA slave interface for playback should be configured. */
@@ -2056,6 +2061,11 @@ at32_add_device_ac97c(unsigned int id, struct ac97c_platform_data *data,
 		tx_dws->reg_width = DW_DMA_SLAVE_WIDTH_16BIT;
 		tx_dws->cfg_hi = DWC_CFGH_DST_PER(4);
 		tx_dws->cfg_lo &= ~(DWC_CFGL_HS_DST_POL | DWC_CFGL_HS_SRC_POL);
+		tx_dws->src_master = 0;
+		tx_dws->dst_master = 1;
+		tx_dws->src_msize = DW_DMA_MSIZE_1;
+		tx_dws->dst_msize = DW_DMA_MSIZE_1;
+		tx_dws->fc = DW_DMA_FC_D_M2P;
 	}
 
 	if (platform_device_add_data(pdev, data,
@@ -2128,6 +2138,11 @@ at32_add_device_abdac(unsigned int id, struct atmel_abdac_pdata *data)
 	dws->reg_width = DW_DMA_SLAVE_WIDTH_32BIT;
 	dws->cfg_hi = DWC_CFGH_DST_PER(2);
 	dws->cfg_lo &= ~(DWC_CFGL_HS_DST_POL | DWC_CFGL_HS_SRC_POL);
+	dws->src_master = 0;
+	dws->dst_master = 1;
+	dws->src_msize = DW_DMA_MSIZE_1;
+	dws->dst_msize = DW_DMA_MSIZE_1;
+	dws->fc = DW_DMA_FC_D_M2P;
 
 	if (platform_device_add_data(pdev, data,
 				sizeof(struct atmel_abdac_pdata)))

drivers/dma/Kconfig

@@ -82,7 +82,7 @@ config INTEL_IOP_ADMA
 
 config DW_DMAC
 	tristate "Synopsys DesignWare AHB DMA support"
-	depends on AVR32
+	depends on HAVE_CLK
 	select DMA_ENGINE
 	default y if CPU_AT32AP7000
 	help
@@ -221,12 +221,20 @@ config IMX_SDMA
 
 config IMX_DMA
 	tristate "i.MX DMA support"
-	depends on ARCH_MX1 || ARCH_MX21 || MACH_MX27
+	depends on IMX_HAVE_DMA_V1
 	select DMA_ENGINE
 	help
 	  Support the i.MX DMA engine. This engine is integrated into
 	  Freescale i.MX1/21/27 chips.
 
+config MXS_DMA
+	bool "MXS DMA support"
+	depends on SOC_IMX23 || SOC_IMX28
+	select DMA_ENGINE
+	help
+	  Support the MXS DMA engine. This engine including APBH-DMA
+	  and APBX-DMA is integrated into Freescale i.MX23/28 chips.
+
 config DMA_ENGINE
 	bool
 

drivers/dma/Makefile

@@ -19,6 +19,7 @@ obj-$(CONFIG_COH901318) += coh901318.o coh901318_lli.o
 obj-$(CONFIG_AMCC_PPC440SPE_ADMA) += ppc4xx/
 obj-$(CONFIG_IMX_SDMA) += imx-sdma.o
 obj-$(CONFIG_IMX_DMA) += imx-dma.o
+obj-$(CONFIG_MXS_DMA) += mxs-dma.o
 obj-$(CONFIG_TIMB_DMA) += timb_dma.o
 obj-$(CONFIG_STE_DMA40) += ste_dma40.o ste_dma40_ll.o
 obj-$(CONFIG_PL330_DMA) += pl330.o

drivers/dma/dmatest.c

@@ -54,6 +54,11 @@ module_param(pq_sources, uint, S_IRUGO);
 MODULE_PARM_DESC(pq_sources,
 		"Number of p+q source buffers (default: 3)");
 
+static int timeout = 3000;
+module_param(timeout, uint, S_IRUGO);
+MODULE_PARM_DESC(timeout, "Transfer Timeout in msec (default: 3000), \
+		Pass -1 for infinite timeout");
+
 /*
  * Initialization patterns. All bytes in the source buffer has bit 7
  * set, all bytes in the destination buffer has bit 7 cleared.
@@ -285,7 +290,12 @@ static int dmatest_func(void *data)
 
 	set_user_nice(current, 10);
 
-	flags = DMA_CTRL_ACK | DMA_COMPL_SKIP_DEST_UNMAP | DMA_PREP_INTERRUPT;
+	/*
+	 * src buffers are freed by the DMAEngine code with dma_unmap_single()
+	 * dst buffers are freed by ourselves below
+	 */
+	flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT
+	      | DMA_COMPL_SKIP_DEST_UNMAP | DMA_COMPL_SRC_UNMAP_SINGLE;
 
 	while (!kthread_should_stop()
 	       && !(iterations && total_tests >= iterations)) {
@@ -294,7 +304,7 @@ static int dmatest_func(void *data)
 		dma_addr_t dma_srcs[src_cnt];
 		dma_addr_t dma_dsts[dst_cnt];
 		struct completion cmp;
-		unsigned long tmo = msecs_to_jiffies(3000);
+		unsigned long tmo = msecs_to_jiffies(timeout);
 		u8 align = 0;
 
 		total_tests++;

drivers/dma/dw_dmac.c

@@ -32,26 +32,30 @@
  * which does not support descriptor writeback.
  */
 
-/* NOTE:  DMS+SMS is system-specific. We should get this information
- * from the platform code somehow.
- */
-#define DWC_DEFAULT_CTLLO	(DWC_CTLL_DST_MSIZE(0)		\
-				| DWC_CTLL_SRC_MSIZE(0)		\
-				| DWC_CTLL_DMS(0)		\
-				| DWC_CTLL_SMS(1)		\
+#define DWC_DEFAULT_CTLLO(private) ({				\
+		struct dw_dma_slave *__slave = (private);	\
+		int dms = __slave ? __slave->dst_master : 0;	\
+		int sms = __slave ? __slave->src_master : 1;	\
+		u8 smsize = __slave ? __slave->src_msize : DW_DMA_MSIZE_16; \
+		u8 dmsize = __slave ? __slave->dst_msize : DW_DMA_MSIZE_16; \
+								\
+		(DWC_CTLL_DST_MSIZE(dmsize)			\
+		 | DWC_CTLL_SRC_MSIZE(smsize)			\
 		 | DWC_CTLL_LLP_D_EN				\
-				| DWC_CTLL_LLP_S_EN)
+		 | DWC_CTLL_LLP_S_EN				\
+		 | DWC_CTLL_DMS(dms)				\
+		 | DWC_CTLL_SMS(sms));				\
+	})
 
 /*
  * This is configuration-dependent and usually a funny size like 4095.
- * Let's round it down to the nearest power of two.
  *
  * Note that this is a transfer count, i.e. if we transfer 32-bit
- * words, we can do 8192 bytes per descriptor.
+ * words, we can do 16380 bytes per descriptor.
  *
  * This parameter is also system-specific.
  */
-#define DWC_MAX_COUNT	2048U
+#define DWC_MAX_COUNT	4095U
 
 /*
  * Number of descriptors to allocate for each channel. This should be
@@ -84,11 +88,6 @@ static struct dw_desc *dwc_first_active(struct dw_dma_chan *dwc)
 	return list_entry(dwc->active_list.next, struct dw_desc, desc_node);
 }
 
-static struct dw_desc *dwc_first_queued(struct dw_dma_chan *dwc)
-{
-	return list_entry(dwc->queue.next, struct dw_desc, desc_node);
-}
-
 static struct dw_desc *dwc_desc_get(struct dw_dma_chan *dwc)
 {
 	struct dw_desc *desc, *_desc;
@@ -201,6 +200,7 @@ dwc_descriptor_complete(struct dw_dma_chan *dwc, struct dw_desc *desc)
 	dma_async_tx_callback		callback;
 	void				*param;
 	struct dma_async_tx_descriptor	*txd = &desc->txd;
+	struct dw_desc			*child;
 
 	dev_vdbg(chan2dev(&dwc->chan), "descriptor %u complete\n", txd->cookie);
 
@@ -209,6 +209,12 @@ dwc_descriptor_complete(struct dw_dma_chan *dwc, struct dw_desc *desc)
 	param = txd->callback_param;
 
 	dwc_sync_desc_for_cpu(dwc, desc);
+
+	/* async_tx_ack */
+	list_for_each_entry(child, &desc->tx_list, desc_node)
+		async_tx_ack(&child->txd);
+	async_tx_ack(&desc->txd);
+
 	list_splice_init(&desc->tx_list, &dwc->free_list);
 	list_move(&desc->desc_node, &dwc->free_list);
 
@@ -259,10 +265,11 @@ static void dwc_complete_all(struct dw_dma *dw, struct dw_dma_chan *dwc)
 	 * Submit queued descriptors ASAP, i.e. before we go through
 	 * the completed ones.
 	 */
-	if (!list_empty(&dwc->queue))
-		dwc_dostart(dwc, dwc_first_queued(dwc));
 	list_splice_init(&dwc->active_list, &list);
-	list_splice_init(&dwc->queue, &dwc->active_list);
+	if (!list_empty(&dwc->queue)) {
+		list_move(dwc->queue.next, &dwc->active_list);
+		dwc_dostart(dwc, dwc_first_active(dwc));
+	}
 
 	list_for_each_entry_safe(desc, _desc, &list, desc_node)
 		dwc_descriptor_complete(dwc, desc);
@@ -291,6 +298,9 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
 		return;
 	}
 
+	if (list_empty(&dwc->active_list))
+		return;
+
 	dev_vdbg(chan2dev(&dwc->chan), "scan_descriptors: llp=0x%x\n", llp);
 
 	list_for_each_entry_safe(desc, _desc, &dwc->active_list, desc_node) {
@@ -319,8 +329,8 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
 		cpu_relax();
 
 	if (!list_empty(&dwc->queue)) {
-		dwc_dostart(dwc, dwc_first_queued(dwc));
-		list_splice_init(&dwc->queue, &dwc->active_list);
+		list_move(dwc->queue.next, &dwc->active_list);
+		dwc_dostart(dwc, dwc_first_active(dwc));
 	}
 }
 
@@ -346,7 +356,7 @@ static void dwc_handle_error(struct dw_dma *dw, struct dw_dma_chan *dwc)
 	 */
 	bad_desc = dwc_first_active(dwc);
 	list_del_init(&bad_desc->desc_node);
-	list_splice_init(&dwc->queue, dwc->active_list.prev);
+	list_move(dwc->queue.next, dwc->active_list.prev);
 
 	/* Clear the error flag and try to restart the controller */
 	dma_writel(dw, CLEAR.ERROR, dwc->mask);
@@ -541,8 +551,8 @@ static dma_cookie_t dwc_tx_submit(struct dma_async_tx_descriptor *tx)
 	if (list_empty(&dwc->active_list)) {
 		dev_vdbg(chan2dev(tx->chan), "tx_submit: started %u\n",
 				desc->txd.cookie);
-		dwc_dostart(dwc, desc);
 		list_add_tail(&desc->desc_node, &dwc->active_list);
+		dwc_dostart(dwc, dwc_first_active(dwc));
 	} else {
 		dev_vdbg(chan2dev(tx->chan), "tx_submit: queued %u\n",
 				desc->txd.cookie);
@@ -581,14 +591,16 @@ dwc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 	 * We can be a lot more clever here, but this should take care
 	 * of the most common optimization.
 	 */
-	if (!((src | dest  | len) & 3))
+	if (!((src | dest  | len) & 7))
+		src_width = dst_width = 3;
+	else if (!((src | dest  | len) & 3))
 		src_width = dst_width = 2;
 	else if (!((src | dest | len) & 1))
 		src_width = dst_width = 1;
 	else
 		src_width = dst_width = 0;
 
-	ctllo = DWC_DEFAULT_CTLLO
+	ctllo = DWC_DEFAULT_CTLLO(chan->private)
 			| DWC_CTLL_DST_WIDTH(dst_width)
 			| DWC_CTLL_SRC_WIDTH(src_width)
 			| DWC_CTLL_DST_INC
@@ -669,11 +681,11 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 
 	switch (direction) {
 	case DMA_TO_DEVICE:
-		ctllo = (DWC_DEFAULT_CTLLO
+		ctllo = (DWC_DEFAULT_CTLLO(chan->private)
 				| DWC_CTLL_DST_WIDTH(reg_width)
 				| DWC_CTLL_DST_FIX
 				| DWC_CTLL_SRC_INC
-				| DWC_CTLL_FC_M2P);
+				| DWC_CTLL_FC(dws->fc));
 		reg = dws->tx_reg;
 		for_each_sg(sgl, sg, sg_len, i) {
 			struct dw_desc	*desc;
@@ -714,11 +726,11 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		}
 		break;
 	case DMA_FROM_DEVICE:
-		ctllo = (DWC_DEFAULT_CTLLO
+		ctllo = (DWC_DEFAULT_CTLLO(chan->private)
 				| DWC_CTLL_SRC_WIDTH(reg_width)
 				| DWC_CTLL_DST_INC
 				| DWC_CTLL_SRC_FIX
-				| DWC_CTLL_FC_P2M);
+				| DWC_CTLL_FC(dws->fc));
 
 		reg = dws->rx_reg;
 		for_each_sg(sgl, sg, sg_len, i) {
@@ -834,7 +846,9 @@ dwc_tx_status(struct dma_chan *chan,
 
 	ret = dma_async_is_complete(cookie, last_complete, last_used);
 	if (ret != DMA_SUCCESS) {
+		spin_lock_bh(&dwc->lock);
 		dwc_scan_descriptors(to_dw_dma(chan->device), dwc);
+		spin_unlock_bh(&dwc->lock);
 
 		last_complete = dwc->completed;
 		last_used = chan->cookie;
@@ -889,8 +903,11 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan)
 		BUG_ON(!dws->dma_dev || dws->dma_dev != dw->dma.dev);
 
 		cfghi = dws->cfg_hi;
-		cfglo = dws->cfg_lo;
+		cfglo = dws->cfg_lo & ~DWC_CFGL_CH_PRIOR_MASK;
 	}
+
+	cfglo |= DWC_CFGL_CH_PRIOR(dwc->priority);
+
 	channel_writel(dwc, CFG_LO, cfglo);
 	channel_writel(dwc, CFG_HI, cfghi);
 
@@ -1126,23 +1143,23 @@ struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan,
 		case DMA_TO_DEVICE:
 			desc->lli.dar = dws->tx_reg;
 			desc->lli.sar = buf_addr + (period_len * i);
-			desc->lli.ctllo = (DWC_DEFAULT_CTLLO
+			desc->lli.ctllo = (DWC_DEFAULT_CTLLO(chan->private)
 					| DWC_CTLL_DST_WIDTH(reg_width)
 					| DWC_CTLL_SRC_WIDTH(reg_width)
 					| DWC_CTLL_DST_FIX
 					| DWC_CTLL_SRC_INC
-					| DWC_CTLL_FC_M2P
+					| DWC_CTLL_FC(dws->fc)
 					| DWC_CTLL_INT_EN);
 			break;
 		case DMA_FROM_DEVICE:
 			desc->lli.dar = buf_addr + (period_len * i);
 			desc->lli.sar = dws->rx_reg;
-			desc->lli.ctllo = (DWC_DEFAULT_CTLLO
+			desc->lli.ctllo = (DWC_DEFAULT_CTLLO(chan->private)
 					| DWC_CTLL_SRC_WIDTH(reg_width)
 					| DWC_CTLL_DST_WIDTH(reg_width)
 					| DWC_CTLL_DST_INC
 					| DWC_CTLL_SRC_FIX
-					| DWC_CTLL_FC_P2M
+					| DWC_CTLL_FC(dws->fc)
 					| DWC_CTLL_INT_EN);
 			break;
 		default:
@@ -1307,7 +1324,17 @@ static int __init dw_probe(struct platform_device *pdev)
 		dwc->chan.device = &dw->dma;
 		dwc->chan.cookie = dwc->completed = 1;
 		dwc->chan.chan_id = i;
-		list_add_tail(&dwc->chan.device_node, &dw->dma.channels);
+		if (pdata->chan_allocation_order == CHAN_ALLOCATION_ASCENDING)
+			list_add_tail(&dwc->chan.device_node,
+					&dw->dma.channels);
+		else
+			list_add(&dwc->chan.device_node, &dw->dma.channels);
+
+		/* 7 is highest priority & 0 is lowest. */
+		if (pdata->chan_priority == CHAN_PRIORITY_ASCENDING)
+			dwc->priority = 7 - i;
+		else
+			dwc->priority = i;
 
 		dwc->ch_regs = &__dw_regs(dw)->CHAN[i];
 		spin_lock_init(&dwc->lock);
@@ -1335,6 +1362,8 @@ static int __init dw_probe(struct platform_device *pdev)
 
 	dma_cap_set(DMA_MEMCPY, dw->dma.cap_mask);
 	dma_cap_set(DMA_SLAVE, dw->dma.cap_mask);
+	if (pdata->is_private)
+		dma_cap_set(DMA_PRIVATE, dw->dma.cap_mask);
 	dw->dma.dev = &pdev->dev;
 	dw->dma.device_alloc_chan_resources = dwc_alloc_chan_resources;
 	dw->dma.device_free_chan_resources = dwc_free_chan_resources;
@@ -1447,7 +1476,7 @@ static int __init dw_init(void)
 {
 	return platform_driver_probe(&dw_driver, dw_probe);
 }
-module_init(dw_init);
+subsys_initcall(dw_init);
 
 static void __exit dw_exit(void)
 {

drivers/dma/dw_dmac_regs.h

@@ -86,6 +86,7 @@ struct dw_dma_regs {
 #define DWC_CTLL_SRC_MSIZE(n)	((n)<<14)
 #define DWC_CTLL_S_GATH_EN	(1 << 17)	/* src gather, !FIX */
 #define DWC_CTLL_D_SCAT_EN	(1 << 18)	/* dst scatter, !FIX */
+#define DWC_CTLL_FC(n)		((n) << 20)
 #define DWC_CTLL_FC_M2M		(0 << 20)	/* mem-to-mem */
 #define DWC_CTLL_FC_M2P		(1 << 20)	/* mem-to-periph */
 #define DWC_CTLL_FC_P2M		(2 << 20)	/* periph-to-mem */
@@ -101,6 +102,8 @@ struct dw_dma_regs {
 #define DWC_CTLH_BLOCK_TS_MASK	0x00000fff
 
 /* Bitfields in CFG_LO. Platform-configurable bits are in <linux/dw_dmac.h> */
+#define DWC_CFGL_CH_PRIOR_MASK	(0x7 << 5)	/* priority mask */
+#define DWC_CFGL_CH_PRIOR(x)	((x) << 5)	/* priority */
 #define DWC_CFGL_CH_SUSP	(1 << 8)	/* pause xfer */
 #define DWC_CFGL_FIFO_EMPTY	(1 << 9)	/* pause xfer */
 #define DWC_CFGL_HS_DST		(1 << 10)	/* handshake w/dst */
@@ -134,6 +137,7 @@ struct dw_dma_chan {
 	struct dma_chan		chan;
 	void __iomem		*ch_regs;
 	u8			mask;
+	u8			priority;
 
 	spinlock_t		lock;
 
@@ -155,9 +159,9 @@ __dwc_regs(struct dw_dma_chan *dwc)
 }
 
 #define channel_readl(dwc, name) \
-	__raw_readl(&(__dwc_regs(dwc)->name))
+	readl(&(__dwc_regs(dwc)->name))
 #define channel_writel(dwc, name, val) \
-	__raw_writel((val), &(__dwc_regs(dwc)->name))
+	writel((val), &(__dwc_regs(dwc)->name))
 
 static inline struct dw_dma_chan *to_dw_dma_chan(struct dma_chan *chan)
 {
@@ -181,9 +185,9 @@ static inline struct dw_dma_regs __iomem *__dw_regs(struct dw_dma *dw)
 }
 
 #define dma_readl(dw, name) \
-	__raw_readl(&(__dw_regs(dw)->name))
+	readl(&(__dw_regs(dw)->name))
 #define dma_writel(dw, name, val) \
-	__raw_writel((val), &(__dw_regs(dw)->name))
+	writel((val), &(__dw_regs(dw)->name))
 
 #define channel_set_bit(dw, reg, mask) \
 	dma_writel(dw, reg, ((mask) << 8) | (mask))

drivers/dma/fsldma.h

@@ -135,6 +135,7 @@ struct fsldma_device {
 #define FSL_DMA_CHAN_START_EXT	0x00002000
 
 struct fsldma_chan {
+	char name[8];			/* Channel name */
 	struct fsldma_chan_regs __iomem *regs;
 	dma_cookie_t completed_cookie;	/* The maximum cookie completed */
 	spinlock_t desc_lock;		/* Descriptor operation lock */
@@ -147,6 +148,7 @@ struct fsldma_chan {
 	int id;				/* Raw id of this channel */
 	struct tasklet_struct tasklet;
 	u32 feature;
+	bool idle;			/* DMA controller is idle */
 
 	void (*toggle_ext_pause)(struct fsldma_chan *fsl_chan, int enable);
 	void (*toggle_ext_start)(struct fsldma_chan *fsl_chan, int enable);

drivers/dma/pch_dma.c

@@ -82,7 +82,7 @@ struct pch_dma_regs {
 	u32	dma_sts1;
 	u32	reserved2;
 	u32	reserved3;
-	struct pch_dma_desc_regs desc[0];
+	struct pch_dma_desc_regs desc[MAX_CHAN_NR];
 };
 
 struct pch_dma_desc {
@@ -124,7 +124,7 @@ struct pch_dma {
 	struct pci_pool		*pool;
 	struct pch_dma_regs	regs;
 	struct pch_dma_desc_regs ch_regs[MAX_CHAN_NR];
-	struct pch_dma_chan	channels[0];
+	struct pch_dma_chan	channels[MAX_CHAN_NR];
 };
 
 #define PCH_DMA_CTL0	0x00
@@ -366,7 +366,7 @@ static dma_cookie_t pd_tx_submit(struct dma_async_tx_descriptor *txd)
 	struct pch_dma_chan *pd_chan = to_pd_chan(txd->chan);
 	dma_cookie_t cookie;
 
-	spin_lock_bh(&pd_chan->lock);
+	spin_lock(&pd_chan->lock);
 	cookie = pdc_assign_cookie(pd_chan, desc);
 
 	if (list_empty(&pd_chan->active_list)) {
@@ -376,7 +376,7 @@ static dma_cookie_t pd_tx_submit(struct dma_async_tx_descriptor *txd)
 		list_add_tail(&desc->desc_node, &pd_chan->queue);
 	}
 
-	spin_unlock_bh(&pd_chan->lock);
+	spin_unlock(&pd_chan->lock);
 	return 0;
 }
 
@@ -386,7 +386,7 @@ static struct pch_dma_desc *pdc_alloc_desc(struct dma_chan *chan, gfp_t flags)
 	struct pch_dma *pd = to_pd(chan->device);
 	dma_addr_t addr;
 
-	desc = pci_pool_alloc(pd->pool, GFP_KERNEL, &addr);
+	desc = pci_pool_alloc(pd->pool, flags, &addr);
 	if (desc) {
 		memset(desc, 0, sizeof(struct pch_dma_desc));
 		INIT_LIST_HEAD(&desc->tx_list);
@@ -405,7 +405,7 @@ static struct pch_dma_desc *pdc_desc_get(struct pch_dma_chan *pd_chan)
 	struct pch_dma_desc *ret = NULL;
 	int i;
 
-	spin_lock_bh(&pd_chan->lock);
+	spin_lock(&pd_chan->lock);
 	list_for_each_entry_safe(desc, _d, &pd_chan->free_list, desc_node) {
 		i++;
 		if (async_tx_test_ack(&desc->txd)) {
@@ -415,15 +415,15 @@ static struct pch_dma_desc *pdc_desc_get(struct pch_dma_chan *pd_chan)
 		}
 		dev_dbg(chan2dev(&pd_chan->chan), "desc %p not ACKed\n", desc);
 	}
-	spin_unlock_bh(&pd_chan->lock);
+	spin_unlock(&pd_chan->lock);
 	dev_dbg(chan2dev(&pd_chan->chan), "scanned %d descriptors\n", i);
 
 	if (!ret) {
 		ret = pdc_alloc_desc(&pd_chan->chan, GFP_NOIO);
 		if (ret) {
-			spin_lock_bh(&pd_chan->lock);
+			spin_lock(&pd_chan->lock);
 			pd_chan->descs_allocated++;
-			spin_unlock_bh(&pd_chan->lock);
+			spin_unlock(&pd_chan->lock);
 		} else {
 			dev_err(chan2dev(&pd_chan->chan),
 				"failed to alloc desc\n");
@@ -437,10 +437,10 @@ static void pdc_desc_put(struct pch_dma_chan *pd_chan,
 			 struct pch_dma_desc *desc)
 {
 	if (desc) {
-		spin_lock_bh(&pd_chan->lock);
+		spin_lock(&pd_chan->lock);
 		list_splice_init(&desc->tx_list, &pd_chan->free_list);
 		list_add(&desc->desc_node, &pd_chan->free_list);
-		spin_unlock_bh(&pd_chan->lock);
+		spin_unlock(&pd_chan->lock);
 	}
 }
 
@@ -530,9 +530,9 @@ static void pd_issue_pending(struct dma_chan *chan)
 	struct pch_dma_chan *pd_chan = to_pd_chan(chan);
 
 	if (pdc_is_idle(pd_chan)) {
-		spin_lock_bh(&pd_chan->lock);
+		spin_lock(&pd_chan->lock);
 		pdc_advance_work(pd_chan);
-		spin_unlock_bh(&pd_chan->lock);
+		spin_unlock(&pd_chan->lock);
 	}
 }
 
@@ -592,7 +592,6 @@ static struct dma_async_tx_descriptor *pd_prep_slave_sg(struct dma_chan *chan,
 			goto err_desc_get;
 		}
 
-
 		if (!first) {
 			first = desc;
 		} else {
@@ -641,13 +640,13 @@ static int pd_device_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 
 	spin_unlock_bh(&pd_chan->lock);
 
-
 	return 0;
 }
 
 static void pdc_tasklet(unsigned long data)
 {
 	struct pch_dma_chan *pd_chan = (struct pch_dma_chan *)data;
+	unsigned long flags;
 
 	if (!pdc_is_idle(pd_chan)) {
 		dev_err(chan2dev(&pd_chan->chan),
@@ -655,12 +654,12 @@ static void pdc_tasklet(unsigned long data)
 		return;
 	}
 
-	spin_lock_bh(&pd_chan->lock);
+	spin_lock_irqsave(&pd_chan->lock, flags);
 	if (test_and_clear_bit(0, &pd_chan->err_status))
 		pdc_handle_error(pd_chan);
 	else
 		pdc_advance_work(pd_chan);
-	spin_unlock_bh(&pd_chan->lock);
+	spin_unlock_irqrestore(&pd_chan->lock, flags);
 }
 
 static irqreturn_t pd_irq(int irq, void *devid)
@@ -694,6 +693,7 @@ static irqreturn_t pd_irq(int irq, void *devid)
 	return ret;
 }
 
+#ifdef	CONFIG_PM
 static void pch_dma_save_regs(struct pch_dma *pd)
 {
 	struct pch_dma_chan *pd_chan;
@@ -771,6 +771,7 @@ static int pch_dma_resume(struct pci_dev *pdev)
 
 	return 0;
 }
+#endif
 
 static int __devinit pch_dma_probe(struct pci_dev *pdev,
 				   const struct pci_device_id *id)

drivers/dma/ste_dma40_ll.h

@@ -163,6 +163,22 @@
 #define D40_DREG_LCEIS1		0x0B4
 #define D40_DREG_LCEIS2		0x0B8
 #define D40_DREG_LCEIS3		0x0BC
+#define D40_DREG_PSEG1		0x110
+#define D40_DREG_PSEG2		0x114
+#define D40_DREG_PSEG3		0x118
+#define D40_DREG_PSEG4		0x11C
+#define D40_DREG_PCEG1		0x120
+#define D40_DREG_PCEG2		0x124
+#define D40_DREG_PCEG3		0x128
+#define D40_DREG_PCEG4		0x12C
+#define D40_DREG_RSEG1		0x130
+#define D40_DREG_RSEG2		0x134
+#define D40_DREG_RSEG3		0x138
+#define D40_DREG_RSEG4		0x13C
+#define D40_DREG_RCEG1		0x140
+#define D40_DREG_RCEG2		0x144
+#define D40_DREG_RCEG3		0x148
+#define D40_DREG_RCEG4		0x14C
 #define D40_DREG_STFU		0xFC8
 #define D40_DREG_ICFG		0xFCC
 #define D40_DREG_PERIPHID0	0xFE0
@@ -277,6 +293,13 @@ struct d40_def_lcsp {
 
 /* Physical channels */
 
+enum d40_lli_flags {
+	LLI_ADDR_INC	= 1 << 0,
+	LLI_TERM_INT	= 1 << 1,
+	LLI_CYCLIC	= 1 << 2,
+	LLI_LAST_LINK	= 1 << 3,
+};
+
 void d40_phy_cfg(struct stedma40_chan_cfg *cfg,
 		 u32 *src_cfg,
 		 u32 *dst_cfg,
@@ -292,46 +315,15 @@ int d40_phy_sg_to_lli(struct scatterlist *sg,
 		      struct d40_phy_lli *lli,
 		      dma_addr_t lli_phys,
 		      u32 reg_cfg,
-		      u32 data_width1,
-		      u32 data_width2,
-		      int psize);
-
-struct d40_phy_lli *d40_phy_buf_to_lli(struct d40_phy_lli *lli,
-				       dma_addr_t data,
-				       u32 data_size,
-				       int psize,
-				       dma_addr_t next_lli,
-				       u32 reg_cfg,
-				       bool term_int,
-				       u32 data_width1,
-				       u32 data_width2,
-				       bool is_device);
-
-void d40_phy_lli_write(void __iomem *virtbase,
-		       u32 phy_chan_num,
-		       struct d40_phy_lli *lli_dst,
-		       struct d40_phy_lli *lli_src);
+		      struct stedma40_half_channel_info *info,
+		      struct stedma40_half_channel_info *otherinfo,
+		      unsigned long flags);
 
 /* Logical channels */
 
-struct d40_log_lli *d40_log_buf_to_lli(struct d40_log_lli *lli_sg,
-				       dma_addr_t addr,
-				       int size,
-				       u32 lcsp13, /* src or dst*/
-				       u32 data_width1, u32 data_width2,
-				       bool addr_inc);
-
-int d40_log_sg_to_dev(struct scatterlist *sg,
-		      int sg_len,
-		      struct d40_log_lli_bidir *lli,
-		      struct d40_def_lcsp *lcsp,
-		      u32 src_data_width,
-		      u32 dst_data_width,
-		      enum dma_data_direction direction,
-		      dma_addr_t dev_addr);
-
 int d40_log_sg_to_lli(struct scatterlist *sg,
 		      int sg_len,
+		      dma_addr_t dev_addr,
 		      struct d40_log_lli *lli_sg,
 		      u32 lcsp13, /* src or dst*/
 		      u32 data_width1, u32 data_width2);
@@ -339,11 +331,11 @@ int d40_log_sg_to_lli(struct scatterlist *sg,
 void d40_log_lli_lcpa_write(struct d40_log_lli_full *lcpa,
 			    struct d40_log_lli *lli_dst,
 			    struct d40_log_lli *lli_src,
-			    int next);
+			    int next, unsigned int flags);
 
 void d40_log_lli_lcla_write(struct d40_log_lli *lcla,
 			    struct d40_log_lli *lli_dst,
 			    struct d40_log_lli *lli_src,
-			    int next);
+			    int next, unsigned int flags);
 
 #endif /* STE_DMA40_LLI_H */

include/linux/dw_dmac.h

@@ -16,9 +16,18 @@
 /**
  * struct dw_dma_platform_data - Controller configuration parameters
  * @nr_channels: Number of channels supported by hardware (max 8)
+ * @is_private: The device channels should be marked as private and not for
+ *	by the general purpose DMA channel allocator.
  */
 struct dw_dma_platform_data {
 	unsigned int	nr_channels;
+	bool		is_private;
+#define CHAN_ALLOCATION_ASCENDING	0	/* zero to seven */
+#define CHAN_ALLOCATION_DESCENDING	1	/* seven to zero */
+	unsigned char	chan_allocation_order;
+#define CHAN_PRIORITY_ASCENDING		0	/* chan0 highest */
+#define CHAN_PRIORITY_DESCENDING	1	/* chan7 highest */
+	unsigned char	chan_priority;
 };
 
 /**
@@ -33,6 +42,30 @@ enum dw_dma_slave_width {
 	DW_DMA_SLAVE_WIDTH_32BIT,
 };
 
+/* bursts size */
+enum dw_dma_msize {
+	DW_DMA_MSIZE_1,
+	DW_DMA_MSIZE_4,
+	DW_DMA_MSIZE_8,
+	DW_DMA_MSIZE_16,
+	DW_DMA_MSIZE_32,
+	DW_DMA_MSIZE_64,
+	DW_DMA_MSIZE_128,
+	DW_DMA_MSIZE_256,
+};
+
+/* flow controller */
+enum dw_dma_fc {
+	DW_DMA_FC_D_M2M,
+	DW_DMA_FC_D_M2P,
+	DW_DMA_FC_D_P2M,
+	DW_DMA_FC_D_P2P,
+	DW_DMA_FC_P_P2M,
+	DW_DMA_FC_SP_P2P,
+	DW_DMA_FC_P_M2P,
+	DW_DMA_FC_DP_P2P,
+};
+
 /**
  * struct dw_dma_slave - Controller-specific information about a slave
  *
@@ -44,6 +77,11 @@ enum dw_dma_slave_width {
  * @reg_width: peripheral register width
  * @cfg_hi: Platform-specific initializer for the CFG_HI register
  * @cfg_lo: Platform-specific initializer for the CFG_LO register
+ * @src_master: src master for transfers on allocated channel.
+ * @dst_master: dest master for transfers on allocated channel.
+ * @src_msize: src burst size.
+ * @dst_msize: dest burst size.
+ * @fc: flow controller for DMA transfer
  */
 struct dw_dma_slave {
 	struct device		*dma_dev;
@@ -52,6 +90,11 @@ struct dw_dma_slave {
 	enum dw_dma_slave_width	reg_width;
 	u32			cfg_hi;
 	u32			cfg_lo;
+	u8			src_master;
+	u8			dst_master;
+	u8			src_msize;
+	u8			dst_msize;
+	u8			fc;
 };
 
 /* Platform-configurable bits in CFG_HI */
@@ -62,7 +105,6 @@ struct dw_dma_slave {
 #define DWC_CFGH_DST_PER(x)	((x) << 11)
 
 /* Platform-configurable bits in CFG_LO */
-#define DWC_CFGL_PRIO(x)	((x) << 5)	/* priority */
 #define DWC_CFGL_LOCK_CH_XFER	(0 << 12)	/* scope of LOCK_CH */
 #define DWC_CFGL_LOCK_CH_BLOCK	(1 << 12)
 #define DWC_CFGL_LOCK_CH_XACT	(2 << 12)