Merge branch 'for_dan' of git://git.infradead.org/users/vkoul/slave-d…

…ma into dmaengine

* 'for_dan' of git://git.infradead.org/users/vkoul/slave-dma:
  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
  dw_dmac: Mark all tx_descriptors with DMA_CRTL_ACK after xfer finish
  dw_dmac: Change value of DWC_MAX_COUNT to 4095.
  dw_dmac: Adding support for 64 bit access width for memcpy xfers
  dw_dmac: Calling dwc_scan_descriptors from dwc_tx_status() after taking lock
  dw_dmac: Move single descriptor from dwc->queue to dwc->active_list in dwc_complete_all
  dw_dmac: Replace module_init() with subsys_initcall()
  dw_dmac: Remove compilation dependency from AVR32 and put on HAVE_CLK
  dmaengine: mxs-dma: add dma support for i.MX23/28
  pch_dma: set the number of array correctly
  pch_dma: fix kernel error issue

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

@@ -0,0 +1,26 @@
+/*
+ * 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/avr32/mach-at32ap/at32ap700x.c

@@ -2050,6 +2050,9 @@ at32_add_device_ac97c(unsigned int id, struct ac97c_platform_data *data,
 		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. */
@@ -2060,6 +2063,9 @@ at32_add_device_ac97c(unsigned int id, struct ac97c_platform_data *data,
 		tx_dws->cfg_lo &= ~(DWC_CFGL_HS_DST_POL | DWC_CFGL_HS_SRC_POL);
 		rx_dws->src_master = 0;
 		rx_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,
@@ -2134,6 +2140,9 @@ at32_add_device_abdac(unsigned int id, struct atmel_abdac_pdata *data)
 	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
@@ -227,6 +227,14 @@ config IMX_DMA
 	  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

@@ -23,6 +23,7 @@ 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/dw_dmac.c

@@ -36,9 +36,11 @@
 		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(0)				\
-		 | DWC_CTLL_SRC_MSIZE(0)			\
+		(DWC_CTLL_DST_MSIZE(dmsize)			\
+		 | DWC_CTLL_SRC_MSIZE(smsize)			\
 		 | DWC_CTLL_LLP_D_EN				\
 		 | DWC_CTLL_LLP_S_EN				\
 		 | DWC_CTLL_DMS(dms)				\
@@ -47,14 +49,13 @@
 
 /*
  * 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
@@ -87,11 +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;
@@ -204,6 +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);
 
@@ -212,6 +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);
 
@@ -262,10 +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);
@@ -325,8 +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));
 	}
 }
 
@@ -352,7 +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);
@@ -547,8 +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);
@@ -587,7 +591,9 @@ 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;
@@ -679,7 +685,7 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 				| 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;
@@ -724,7 +730,7 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 				| 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) {
@@ -840,7 +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;
@@ -895,8 +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);
 
@@ -1137,7 +1148,7 @@ struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan,
 					| 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:
@@ -1148,7 +1159,7 @@ struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan,
 					| 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:
@@ -1313,7 +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);
@@ -1455,7 +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))