Merge branches 'dma-omap', 'dma-pl08x' and 'dma-sa11x0' into dmaengine
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 56000b3..1f7ba35 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -612,3 +612,14 @@
 Why:	Unsupported/unmaintained/unused since 2.6
 
 ----------------------------
+
+What:	OMAP private DMA implementation
+When:	2013
+Why:	We have a DMA engine implementation; all users should be updated
+	to use this rather than persisting with the old APIs.  The old APIs
+	block merging the old DMA engine implementation into the DMA
+	engine driver.
+Who:	Russell King <linux@arm.linux.org.uk>,
+	Santosh Shilimkar <santosh.shilimkar@ti.com>
+
+----------------------------
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index 9854ff4..3b391b2 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -194,6 +194,8 @@
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_TWL92330=y
 CONFIG_RTC_DRV_TWL4030=y
+CONFIG_DMADEVICES=y
+CONFIG_DMA_OMAP=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
 # CONFIG_EXT3_FS_XATTR is not set
diff --git a/arch/arm/mach-omap1/board-h2-mmc.c b/arch/arm/mach-omap1/board-h2-mmc.c
index da0e37d..e1362ce 100644
--- a/arch/arm/mach-omap1/board-h2-mmc.c
+++ b/arch/arm/mach-omap1/board-h2-mmc.c
@@ -54,7 +54,6 @@
 	.nr_slots                       = 1,
 	.init				= mmc_late_init,
 	.cleanup			= mmc_cleanup,
-	.dma_mask			= 0xffffffff,
 	.slots[0]       = {
 		.set_power              = mmc_set_power,
 		.ocr_mask               = MMC_VDD_32_33 | MMC_VDD_33_34,
diff --git a/arch/arm/mach-omap1/board-h3-mmc.c b/arch/arm/mach-omap1/board-h3-mmc.c
index f8242aa..c74daac 100644
--- a/arch/arm/mach-omap1/board-h3-mmc.c
+++ b/arch/arm/mach-omap1/board-h3-mmc.c
@@ -36,7 +36,6 @@
  */
 static struct omap_mmc_platform_data mmc1_data = {
 	.nr_slots                       = 1,
-	.dma_mask			= 0xffffffff,
 	.slots[0]       = {
 		.set_power              = mmc_set_power,
 		.ocr_mask               = MMC_VDD_32_33 | MMC_VDD_33_34,
diff --git a/arch/arm/mach-omap1/board-nokia770.c b/arch/arm/mach-omap1/board-nokia770.c
index 7212ae9..c54b45f 100644
--- a/arch/arm/mach-omap1/board-nokia770.c
+++ b/arch/arm/mach-omap1/board-nokia770.c
@@ -185,7 +185,6 @@
 
 static struct omap_mmc_platform_data nokia770_mmc2_data = {
 	.nr_slots                       = 1,
-	.dma_mask			= 0xffffffff,
 	.max_freq                       = 12000000,
 	.slots[0]       = {
 		.set_power		= nokia770_mmc_set_power,
diff --git a/arch/arm/mach-omap2/board-n8x0.c b/arch/arm/mach-omap2/board-n8x0.c
index 2c5d0ed..677357f 100644
--- a/arch/arm/mach-omap2/board-n8x0.c
+++ b/arch/arm/mach-omap2/board-n8x0.c
@@ -468,7 +468,6 @@
 	.cleanup			= n8x0_mmc_cleanup,
 	.shutdown			= n8x0_mmc_shutdown,
 	.max_freq			= 24000000,
-	.dma_mask			= 0xffffffff,
 	.slots[0] = {
 		.wires			= 4,
 		.set_power		= n8x0_mmc_set_power,
diff --git a/arch/arm/mach-omap2/hsmmc.c b/arch/arm/mach-omap2/hsmmc.c
index be697d4..a9675d8 100644
--- a/arch/arm/mach-omap2/hsmmc.c
+++ b/arch/arm/mach-omap2/hsmmc.c
@@ -315,7 +315,6 @@
 	mmc->slots[0].caps = c->caps;
 	mmc->slots[0].pm_caps = c->pm_caps;
 	mmc->slots[0].internal_clock = !c->ext_clock;
-	mmc->dma_mask = 0xffffffff;
 	mmc->max_freq = c->max_freq;
 	if (cpu_is_omap44xx())
 		mmc->reg_offset = OMAP4_MMC_REG_OFFSET;
diff --git a/arch/arm/mach-spear3xx/spear300.c b/arch/arm/mach-spear3xx/spear300.c
index 0f882ec..6ec3005 100644
--- a/arch/arm/mach-spear3xx/spear300.c
+++ b/arch/arm/mach-spear3xx/spear300.c
@@ -120,182 +120,156 @@
 		.min_signal = 2,
 		.max_signal = 2,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "uart0_tx",
 		.min_signal = 3,
 		.max_signal = 3,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ssp0_rx",
 		.min_signal = 8,
 		.max_signal = 8,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ssp0_tx",
 		.min_signal = 9,
 		.max_signal = 9,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "i2c_rx",
 		.min_signal = 10,
 		.max_signal = 10,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "i2c_tx",
 		.min_signal = 11,
 		.max_signal = 11,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "irda",
 		.min_signal = 12,
 		.max_signal = 12,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "adc",
 		.min_signal = 13,
 		.max_signal = 13,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "to_jpeg",
 		.min_signal = 14,
 		.max_signal = 14,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "from_jpeg",
 		.min_signal = 15,
 		.max_signal = 15,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras0_rx",
 		.min_signal = 0,
 		.max_signal = 0,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras0_tx",
 		.min_signal = 1,
 		.max_signal = 1,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras1_rx",
 		.min_signal = 2,
 		.max_signal = 2,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras1_tx",
 		.min_signal = 3,
 		.max_signal = 3,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras2_rx",
 		.min_signal = 4,
 		.max_signal = 4,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras2_tx",
 		.min_signal = 5,
 		.max_signal = 5,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras3_rx",
 		.min_signal = 6,
 		.max_signal = 6,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras3_tx",
 		.min_signal = 7,
 		.max_signal = 7,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras4_rx",
 		.min_signal = 8,
 		.max_signal = 8,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras4_tx",
 		.min_signal = 9,
 		.max_signal = 9,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras5_rx",
 		.min_signal = 10,
 		.max_signal = 10,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras5_tx",
 		.min_signal = 11,
 		.max_signal = 11,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras6_rx",
 		.min_signal = 12,
 		.max_signal = 12,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras6_tx",
 		.min_signal = 13,
 		.max_signal = 13,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras7_rx",
 		.min_signal = 14,
 		.max_signal = 14,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras7_tx",
 		.min_signal = 15,
 		.max_signal = 15,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	},
 };
diff --git a/arch/arm/mach-spear3xx/spear310.c b/arch/arm/mach-spear3xx/spear310.c
index bbcf457..1d0e435 100644
--- a/arch/arm/mach-spear3xx/spear310.c
+++ b/arch/arm/mach-spear3xx/spear310.c
@@ -205,182 +205,156 @@
 		.min_signal = 2,
 		.max_signal = 2,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "uart0_tx",
 		.min_signal = 3,
 		.max_signal = 3,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ssp0_rx",
 		.min_signal = 8,
 		.max_signal = 8,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ssp0_tx",
 		.min_signal = 9,
 		.max_signal = 9,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "i2c_rx",
 		.min_signal = 10,
 		.max_signal = 10,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "i2c_tx",
 		.min_signal = 11,
 		.max_signal = 11,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "irda",
 		.min_signal = 12,
 		.max_signal = 12,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "adc",
 		.min_signal = 13,
 		.max_signal = 13,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "to_jpeg",
 		.min_signal = 14,
 		.max_signal = 14,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "from_jpeg",
 		.min_signal = 15,
 		.max_signal = 15,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "uart1_rx",
 		.min_signal = 0,
 		.max_signal = 0,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "uart1_tx",
 		.min_signal = 1,
 		.max_signal = 1,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "uart2_rx",
 		.min_signal = 2,
 		.max_signal = 2,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "uart2_tx",
 		.min_signal = 3,
 		.max_signal = 3,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "uart3_rx",
 		.min_signal = 4,
 		.max_signal = 4,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "uart3_tx",
 		.min_signal = 5,
 		.max_signal = 5,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "uart4_rx",
 		.min_signal = 6,
 		.max_signal = 6,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "uart4_tx",
 		.min_signal = 7,
 		.max_signal = 7,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "uart5_rx",
 		.min_signal = 8,
 		.max_signal = 8,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "uart5_tx",
 		.min_signal = 9,
 		.max_signal = 9,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras5_rx",
 		.min_signal = 10,
 		.max_signal = 10,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras5_tx",
 		.min_signal = 11,
 		.max_signal = 11,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras6_rx",
 		.min_signal = 12,
 		.max_signal = 12,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras6_tx",
 		.min_signal = 13,
 		.max_signal = 13,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras7_rx",
 		.min_signal = 14,
 		.max_signal = 14,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras7_tx",
 		.min_signal = 15,
 		.max_signal = 15,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	},
 };
diff --git a/arch/arm/mach-spear3xx/spear320.c b/arch/arm/mach-spear3xx/spear320.c
index 88d483b..fd823c6 100644
--- a/arch/arm/mach-spear3xx/spear320.c
+++ b/arch/arm/mach-spear3xx/spear320.c
@@ -213,182 +213,156 @@
 		.min_signal = 2,
 		.max_signal = 2,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "uart0_tx",
 		.min_signal = 3,
 		.max_signal = 3,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ssp0_rx",
 		.min_signal = 8,
 		.max_signal = 8,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ssp0_tx",
 		.min_signal = 9,
 		.max_signal = 9,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "i2c0_rx",
 		.min_signal = 10,
 		.max_signal = 10,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "i2c0_tx",
 		.min_signal = 11,
 		.max_signal = 11,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "irda",
 		.min_signal = 12,
 		.max_signal = 12,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "adc",
 		.min_signal = 13,
 		.max_signal = 13,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "to_jpeg",
 		.min_signal = 14,
 		.max_signal = 14,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "from_jpeg",
 		.min_signal = 15,
 		.max_signal = 15,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ssp1_rx",
 		.min_signal = 0,
 		.max_signal = 0,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	}, {
 		.bus_id = "ssp1_tx",
 		.min_signal = 1,
 		.max_signal = 1,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	}, {
 		.bus_id = "ssp2_rx",
 		.min_signal = 2,
 		.max_signal = 2,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	}, {
 		.bus_id = "ssp2_tx",
 		.min_signal = 3,
 		.max_signal = 3,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	}, {
 		.bus_id = "uart1_rx",
 		.min_signal = 4,
 		.max_signal = 4,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	}, {
 		.bus_id = "uart1_tx",
 		.min_signal = 5,
 		.max_signal = 5,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	}, {
 		.bus_id = "uart2_rx",
 		.min_signal = 6,
 		.max_signal = 6,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	}, {
 		.bus_id = "uart2_tx",
 		.min_signal = 7,
 		.max_signal = 7,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	}, {
 		.bus_id = "i2c1_rx",
 		.min_signal = 8,
 		.max_signal = 8,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	}, {
 		.bus_id = "i2c1_tx",
 		.min_signal = 9,
 		.max_signal = 9,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	}, {
 		.bus_id = "i2c2_rx",
 		.min_signal = 10,
 		.max_signal = 10,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	}, {
 		.bus_id = "i2c2_tx",
 		.min_signal = 11,
 		.max_signal = 11,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	}, {
 		.bus_id = "i2s_rx",
 		.min_signal = 12,
 		.max_signal = 12,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	}, {
 		.bus_id = "i2s_tx",
 		.min_signal = 13,
 		.max_signal = 13,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	}, {
 		.bus_id = "rs485_rx",
 		.min_signal = 14,
 		.max_signal = 14,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	}, {
 		.bus_id = "rs485_tx",
 		.min_signal = 15,
 		.max_signal = 15,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	},
 };
diff --git a/arch/arm/mach-spear3xx/spear3xx.c b/arch/arm/mach-spear3xx/spear3xx.c
index 0f41bd1..d6cd840 100644
--- a/arch/arm/mach-spear3xx/spear3xx.c
+++ b/arch/arm/mach-spear3xx/spear3xx.c
@@ -46,7 +46,8 @@
 struct pl08x_platform_data pl080_plat_data = {
 	.memcpy_channel = {
 		.bus_id = "memcpy",
-		.cctl = (PL080_BSIZE_16 << PL080_CONTROL_SB_SIZE_SHIFT | \
+		.cctl_memcpy =
+			(PL080_BSIZE_16 << PL080_CONTROL_SB_SIZE_SHIFT | \
 			PL080_BSIZE_16 << PL080_CONTROL_DB_SIZE_SHIFT | \
 			PL080_WIDTH_32BIT << PL080_CONTROL_SWIDTH_SHIFT | \
 			PL080_WIDTH_32BIT << PL080_CONTROL_DWIDTH_SHIFT | \
diff --git a/arch/arm/mach-spear6xx/spear6xx.c b/arch/arm/mach-spear6xx/spear6xx.c
index 2e2e359..b59ae53 100644
--- a/arch/arm/mach-spear6xx/spear6xx.c
+++ b/arch/arm/mach-spear6xx/spear6xx.c
@@ -36,336 +36,288 @@
 		.min_signal = 0,
 		.max_signal = 0,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ssp1_tx",
 		.min_signal = 1,
 		.max_signal = 1,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "uart0_rx",
 		.min_signal = 2,
 		.max_signal = 2,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "uart0_tx",
 		.min_signal = 3,
 		.max_signal = 3,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "uart1_rx",
 		.min_signal = 4,
 		.max_signal = 4,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "uart1_tx",
 		.min_signal = 5,
 		.max_signal = 5,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ssp2_rx",
 		.min_signal = 6,
 		.max_signal = 6,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	}, {
 		.bus_id = "ssp2_tx",
 		.min_signal = 7,
 		.max_signal = 7,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	}, {
 		.bus_id = "ssp0_rx",
 		.min_signal = 8,
 		.max_signal = 8,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ssp0_tx",
 		.min_signal = 9,
 		.max_signal = 9,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "i2c_rx",
 		.min_signal = 10,
 		.max_signal = 10,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "i2c_tx",
 		.min_signal = 11,
 		.max_signal = 11,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "irda",
 		.min_signal = 12,
 		.max_signal = 12,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "adc",
 		.min_signal = 13,
 		.max_signal = 13,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	}, {
 		.bus_id = "to_jpeg",
 		.min_signal = 14,
 		.max_signal = 14,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "from_jpeg",
 		.min_signal = 15,
 		.max_signal = 15,
 		.muxval = 0,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras0_rx",
 		.min_signal = 0,
 		.max_signal = 0,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras0_tx",
 		.min_signal = 1,
 		.max_signal = 1,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras1_rx",
 		.min_signal = 2,
 		.max_signal = 2,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras1_tx",
 		.min_signal = 3,
 		.max_signal = 3,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras2_rx",
 		.min_signal = 4,
 		.max_signal = 4,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras2_tx",
 		.min_signal = 5,
 		.max_signal = 5,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras3_rx",
 		.min_signal = 6,
 		.max_signal = 6,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras3_tx",
 		.min_signal = 7,
 		.max_signal = 7,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras4_rx",
 		.min_signal = 8,
 		.max_signal = 8,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras4_tx",
 		.min_signal = 9,
 		.max_signal = 9,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras5_rx",
 		.min_signal = 10,
 		.max_signal = 10,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras5_tx",
 		.min_signal = 11,
 		.max_signal = 11,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras6_rx",
 		.min_signal = 12,
 		.max_signal = 12,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras6_tx",
 		.min_signal = 13,
 		.max_signal = 13,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras7_rx",
 		.min_signal = 14,
 		.max_signal = 14,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ras7_tx",
 		.min_signal = 15,
 		.max_signal = 15,
 		.muxval = 1,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB1,
 	}, {
 		.bus_id = "ext0_rx",
 		.min_signal = 0,
 		.max_signal = 0,
 		.muxval = 2,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	}, {
 		.bus_id = "ext0_tx",
 		.min_signal = 1,
 		.max_signal = 1,
 		.muxval = 2,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	}, {
 		.bus_id = "ext1_rx",
 		.min_signal = 2,
 		.max_signal = 2,
 		.muxval = 2,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	}, {
 		.bus_id = "ext1_tx",
 		.min_signal = 3,
 		.max_signal = 3,
 		.muxval = 2,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	}, {
 		.bus_id = "ext2_rx",
 		.min_signal = 4,
 		.max_signal = 4,
 		.muxval = 2,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	}, {
 		.bus_id = "ext2_tx",
 		.min_signal = 5,
 		.max_signal = 5,
 		.muxval = 2,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	}, {
 		.bus_id = "ext3_rx",
 		.min_signal = 6,
 		.max_signal = 6,
 		.muxval = 2,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	}, {
 		.bus_id = "ext3_tx",
 		.min_signal = 7,
 		.max_signal = 7,
 		.muxval = 2,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	}, {
 		.bus_id = "ext4_rx",
 		.min_signal = 8,
 		.max_signal = 8,
 		.muxval = 2,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	}, {
 		.bus_id = "ext4_tx",
 		.min_signal = 9,
 		.max_signal = 9,
 		.muxval = 2,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	}, {
 		.bus_id = "ext5_rx",
 		.min_signal = 10,
 		.max_signal = 10,
 		.muxval = 2,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	}, {
 		.bus_id = "ext5_tx",
 		.min_signal = 11,
 		.max_signal = 11,
 		.muxval = 2,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	}, {
 		.bus_id = "ext6_rx",
 		.min_signal = 12,
 		.max_signal = 12,
 		.muxval = 2,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	}, {
 		.bus_id = "ext6_tx",
 		.min_signal = 13,
 		.max_signal = 13,
 		.muxval = 2,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	}, {
 		.bus_id = "ext7_rx",
 		.min_signal = 14,
 		.max_signal = 14,
 		.muxval = 2,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	}, {
 		.bus_id = "ext7_tx",
 		.min_signal = 15,
 		.max_signal = 15,
 		.muxval = 2,
-		.cctl = 0,
 		.periph_buses = PL08X_AHB2,
 	},
 };
@@ -373,7 +325,8 @@
 struct pl08x_platform_data pl080_plat_data = {
 	.memcpy_channel = {
 		.bus_id = "memcpy",
-		.cctl = (PL080_BSIZE_16 << PL080_CONTROL_SB_SIZE_SHIFT | \
+		.cctl_memcpy =
+			(PL080_BSIZE_16 << PL080_CONTROL_SB_SIZE_SHIFT | \
 			PL080_BSIZE_16 << PL080_CONTROL_DB_SIZE_SHIFT | \
 			PL080_WIDTH_32BIT << PL080_CONTROL_SWIDTH_SHIFT | \
 			PL080_WIDTH_32BIT << PL080_CONTROL_DWIDTH_SHIFT | \
diff --git a/arch/arm/plat-omap/include/plat/mmc.h b/arch/arm/plat-omap/include/plat/mmc.h
index 5493bd9..eb3e4d5 100644
--- a/arch/arm/plat-omap/include/plat/mmc.h
+++ b/arch/arm/plat-omap/include/plat/mmc.h
@@ -81,8 +81,6 @@
 	/* Return context loss count due to PM states changing */
 	int (*get_context_loss_count)(struct device *dev);
 
-	u64 dma_mask;
-
 	/* Integrating attributes from the omap_hwmod layer */
 	u8 controller_flags;
 
diff --git a/arch/arm/plat-spear/include/plat/pl080.h b/arch/arm/plat-spear/include/plat/pl080.h
index 2bc6b54..eb6590d 100644
--- a/arch/arm/plat-spear/include/plat/pl080.h
+++ b/arch/arm/plat-spear/include/plat/pl080.h
@@ -14,8 +14,8 @@
 #ifndef __PLAT_PL080_H
 #define __PLAT_PL080_H
 
-struct pl08x_dma_chan;
-int pl080_get_signal(struct pl08x_dma_chan *ch);
-void pl080_put_signal(struct pl08x_dma_chan *ch);
+struct pl08x_channel_data;
+int pl080_get_signal(const struct pl08x_channel_data *cd);
+void pl080_put_signal(const struct pl08x_channel_data *cd, int signal);
 
 #endif /* __PLAT_PL080_H */
diff --git a/arch/arm/plat-spear/pl080.c b/arch/arm/plat-spear/pl080.c
index 12cf27f..cfa1199 100644
--- a/arch/arm/plat-spear/pl080.c
+++ b/arch/arm/plat-spear/pl080.c
@@ -27,9 +27,8 @@
 	unsigned char val;
 } signals[16] = {{0, 0}, };
 
-int pl080_get_signal(struct pl08x_dma_chan *ch)
+int pl080_get_signal(const struct pl08x_channel_data *cd)
 {
-	const struct pl08x_channel_data *cd = ch->cd;
 	unsigned int signal = cd->min_signal, val;
 	unsigned long flags;
 
@@ -63,18 +62,17 @@
 	return signal;
 }
 
-void pl080_put_signal(struct pl08x_dma_chan *ch)
+void pl080_put_signal(const struct pl08x_channel_data *cd, int signal)
 {
-	const struct pl08x_channel_data *cd = ch->cd;
 	unsigned long flags;
 
 	spin_lock_irqsave(&lock, flags);
 
 	/* if signal is not used */
-	if (!signals[cd->min_signal].busy)
+	if (!signals[signal].busy)
 		BUG();
 
-	signals[cd->min_signal].busy--;
+	signals[signal].busy--;
 
 	spin_unlock_irqrestore(&lock, flags);
 }
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index eb2b60e..6f93365 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -53,6 +53,7 @@
 	bool "ARM PrimeCell PL080 or PL081 support"
 	depends on ARM_AMBA && EXPERIMENTAL
 	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
 	help
 	  Platform has a PL08x DMAC device
 	  which can provide DMA engine support
@@ -261,6 +262,12 @@
 	  SA-1110 SoCs.  This DMA engine can only be used with on-chip
 	  devices.
 
+config DMA_OMAP
+	tristate "OMAP DMA support"
+	depends on ARCH_OMAP
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+
 config DMA_ENGINE
 	bool
 
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index fc05f7d..ddc291a 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -29,3 +29,4 @@
 obj-$(CONFIG_AMBA_PL08X) += amba-pl08x.o
 obj-$(CONFIG_EP93XX_DMA) += ep93xx_dma.o
 obj-$(CONFIG_DMA_SA11X0) += sa11x0-dma.o
+obj-$(CONFIG_DMA_OMAP) += omap-dma.o
diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c
index 49ecbbb..6fbeebb 100644
--- a/drivers/dma/amba-pl08x.c
+++ b/drivers/dma/amba-pl08x.c
@@ -86,10 +86,12 @@
 #include <asm/hardware/pl080.h>
 
 #include "dmaengine.h"
+#include "virt-dma.h"
 
 #define DRIVER_NAME	"pl08xdmac"
 
 static struct amba_driver pl08x_amba_driver;
+struct pl08x_driver_data;
 
 /**
  * struct vendor_data - vendor-specific config parameters for PL08x derivatives
@@ -119,6 +121,123 @@
 };
 
 /**
+ * struct pl08x_bus_data - information of source or destination
+ * busses for a transfer
+ * @addr: current address
+ * @maxwidth: the maximum width of a transfer on this bus
+ * @buswidth: the width of this bus in bytes: 1, 2 or 4
+ */
+struct pl08x_bus_data {
+	dma_addr_t addr;
+	u8 maxwidth;
+	u8 buswidth;
+};
+
+/**
+ * struct pl08x_phy_chan - holder for the physical channels
+ * @id: physical index to this channel
+ * @lock: a lock to use when altering an instance of this struct
+ * @serving: the virtual channel currently being served by this physical
+ * channel
+ * @locked: channel unavailable for the system, e.g. dedicated to secure
+ * world
+ */
+struct pl08x_phy_chan {
+	unsigned int id;
+	void __iomem *base;
+	spinlock_t lock;
+	struct pl08x_dma_chan *serving;
+	bool locked;
+};
+
+/**
+ * struct pl08x_sg - structure containing data per sg
+ * @src_addr: src address of sg
+ * @dst_addr: dst address of sg
+ * @len: transfer len in bytes
+ * @node: node for txd's dsg_list
+ */
+struct pl08x_sg {
+	dma_addr_t src_addr;
+	dma_addr_t dst_addr;
+	size_t len;
+	struct list_head node;
+};
+
+/**
+ * struct pl08x_txd - wrapper for struct dma_async_tx_descriptor
+ * @vd: virtual DMA descriptor
+ * @dsg_list: list of children sg's
+ * @llis_bus: DMA memory address (physical) start for the LLIs
+ * @llis_va: virtual memory address start for the LLIs
+ * @cctl: control reg values for current txd
+ * @ccfg: config reg values for current txd
+ * @done: this marks completed descriptors, which should not have their
+ *   mux released.
+ */
+struct pl08x_txd {
+	struct virt_dma_desc vd;
+	struct list_head dsg_list;
+	dma_addr_t llis_bus;
+	struct pl08x_lli *llis_va;
+	/* Default cctl value for LLIs */
+	u32 cctl;
+	/*
+	 * Settings to be put into the physical channel when we
+	 * trigger this txd.  Other registers are in llis_va[0].
+	 */
+	u32 ccfg;
+	bool done;
+};
+
+/**
+ * struct pl08x_dma_chan_state - holds the PL08x specific virtual channel
+ * states
+ * @PL08X_CHAN_IDLE: the channel is idle
+ * @PL08X_CHAN_RUNNING: the channel has allocated a physical transport
+ * channel and is running a transfer on it
+ * @PL08X_CHAN_PAUSED: the channel has allocated a physical transport
+ * channel, but the transfer is currently paused
+ * @PL08X_CHAN_WAITING: the channel is waiting for a physical transport
+ * channel to become available (only pertains to memcpy channels)
+ */
+enum pl08x_dma_chan_state {
+	PL08X_CHAN_IDLE,
+	PL08X_CHAN_RUNNING,
+	PL08X_CHAN_PAUSED,
+	PL08X_CHAN_WAITING,
+};
+
+/**
+ * struct pl08x_dma_chan - this structure wraps a DMA ENGINE channel
+ * @vc: wrappped virtual channel
+ * @phychan: the physical channel utilized by this channel, if there is one
+ * @name: name of channel
+ * @cd: channel platform data
+ * @runtime_addr: address for RX/TX according to the runtime config
+ * @at: active transaction on this channel
+ * @lock: a lock for this channel data
+ * @host: a pointer to the host (internal use)
+ * @state: whether the channel is idle, paused, running etc
+ * @slave: whether this channel is a device (slave) or for memcpy
+ * @signal: the physical DMA request signal which this channel is using
+ * @mux_use: count of descriptors using this DMA request signal setting
+ */
+struct pl08x_dma_chan {
+	struct virt_dma_chan vc;
+	struct pl08x_phy_chan *phychan;
+	const char *name;
+	const struct pl08x_channel_data *cd;
+	struct dma_slave_config cfg;
+	struct pl08x_txd *at;
+	struct pl08x_driver_data *host;
+	enum pl08x_dma_chan_state state;
+	bool slave;
+	int signal;
+	unsigned mux_use;
+};
+
+/**
  * struct pl08x_driver_data - the local state holder for the PL08x
  * @slave: slave engine for this instance
  * @memcpy: memcpy engine for this instance
@@ -128,7 +247,6 @@
  * @pd: platform data passed in from the platform/machine
  * @phy_chans: array of data for the physical channels
  * @pool: a pool for the LLI descriptors
- * @pool_ctr: counter of LLIs in the pool
  * @lli_buses: bitmask to or in to LLI pointer selecting AHB port for LLI
  * fetches
  * @mem_buses: set to indicate memory transfers on AHB2.
@@ -143,10 +261,8 @@
 	struct pl08x_platform_data *pd;
 	struct pl08x_phy_chan *phy_chans;
 	struct dma_pool *pool;
-	int pool_ctr;
 	u8 lli_buses;
 	u8 mem_buses;
-	spinlock_t lock;
 };
 
 /*
@@ -162,12 +278,51 @@
 
 static inline struct pl08x_dma_chan *to_pl08x_chan(struct dma_chan *chan)
 {
-	return container_of(chan, struct pl08x_dma_chan, chan);
+	return container_of(chan, struct pl08x_dma_chan, vc.chan);
 }
 
 static inline struct pl08x_txd *to_pl08x_txd(struct dma_async_tx_descriptor *tx)
 {
-	return container_of(tx, struct pl08x_txd, tx);
+	return container_of(tx, struct pl08x_txd, vd.tx);
+}
+
+/*
+ * Mux handling.
+ *
+ * This gives us the DMA request input to the PL08x primecell which the
+ * peripheral described by the channel data will be routed to, possibly
+ * via a board/SoC specific external MUX.  One important point to note
+ * here is that this does not depend on the physical channel.
+ */
+static int pl08x_request_mux(struct pl08x_dma_chan *plchan)
+{
+	const struct pl08x_platform_data *pd = plchan->host->pd;
+	int ret;
+
+	if (plchan->mux_use++ == 0 && pd->get_signal) {
+		ret = pd->get_signal(plchan->cd);
+		if (ret < 0) {
+			plchan->mux_use = 0;
+			return ret;
+		}
+
+		plchan->signal = ret;
+	}
+	return 0;
+}
+
+static void pl08x_release_mux(struct pl08x_dma_chan *plchan)
+{
+	const struct pl08x_platform_data *pd = plchan->host->pd;
+
+	if (plchan->signal >= 0) {
+		WARN_ON(plchan->mux_use == 0);
+
+		if (--plchan->mux_use == 0 && pd->put_signal) {
+			pd->put_signal(plchan->cd, plchan->signal);
+			plchan->signal = -1;
+		}
+	}
 }
 
 /*
@@ -189,20 +344,25 @@
  * been set when the LLIs were constructed.  Poke them into the hardware
  * and start the transfer.
  */
-static void pl08x_start_txd(struct pl08x_dma_chan *plchan,
-	struct pl08x_txd *txd)
+static void pl08x_start_next_txd(struct pl08x_dma_chan *plchan)
 {
 	struct pl08x_driver_data *pl08x = plchan->host;
 	struct pl08x_phy_chan *phychan = plchan->phychan;
-	struct pl08x_lli *lli = &txd->llis_va[0];
+	struct virt_dma_desc *vd = vchan_next_desc(&plchan->vc);
+	struct pl08x_txd *txd = to_pl08x_txd(&vd->tx);
+	struct pl08x_lli *lli;
 	u32 val;
 
+	list_del(&txd->vd.node);
+
 	plchan->at = txd;
 
 	/* Wait for channel inactive */
 	while (pl08x_phy_channel_busy(phychan))
 		cpu_relax();
 
+	lli = &txd->llis_va[0];
+
 	dev_vdbg(&pl08x->adev->dev,
 		"WRITE channel %d: csrc=0x%08x, cdst=0x%08x, "
 		"clli=0x%08x, cctl=0x%08x, ccfg=0x%08x\n",
@@ -311,10 +471,8 @@
 {
 	struct pl08x_phy_chan *ch;
 	struct pl08x_txd *txd;
-	unsigned long flags;
 	size_t bytes = 0;
 
-	spin_lock_irqsave(&plchan->lock, flags);
 	ch = plchan->phychan;
 	txd = plchan->at;
 
@@ -354,18 +512,6 @@
 		}
 	}
 
-	/* Sum up all queued transactions */
-	if (!list_empty(&plchan->pend_list)) {
-		struct pl08x_txd *txdi;
-		list_for_each_entry(txdi, &plchan->pend_list, node) {
-			struct pl08x_sg *dsg;
-			list_for_each_entry(dsg, &txd->dsg_list, node)
-				bytes += dsg->len;
-		}
-	}
-
-	spin_unlock_irqrestore(&plchan->lock, flags);
-
 	return bytes;
 }
 
@@ -391,7 +537,6 @@
 
 		if (!ch->locked && !ch->serving) {
 			ch->serving = virt_chan;
-			ch->signal = -1;
 			spin_unlock_irqrestore(&ch->lock, flags);
 			break;
 		}
@@ -404,25 +549,114 @@
 		return NULL;
 	}
 
-	pm_runtime_get_sync(&pl08x->adev->dev);
 	return ch;
 }
 
+/* Mark the physical channel as free.  Note, this write is atomic. */
 static inline void pl08x_put_phy_channel(struct pl08x_driver_data *pl08x,
 					 struct pl08x_phy_chan *ch)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&ch->lock, flags);
-
-	/* Stop the channel and clear its interrupts */
-	pl08x_terminate_phy_chan(pl08x, ch);
-
-	pm_runtime_put(&pl08x->adev->dev);
-
-	/* Mark it as free */
 	ch->serving = NULL;
-	spin_unlock_irqrestore(&ch->lock, flags);
+}
+
+/*
+ * Try to allocate a physical channel.  When successful, assign it to
+ * this virtual channel, and initiate the next descriptor.  The
+ * virtual channel lock must be held at this point.
+ */
+static void pl08x_phy_alloc_and_start(struct pl08x_dma_chan *plchan)
+{
+	struct pl08x_driver_data *pl08x = plchan->host;
+	struct pl08x_phy_chan *ch;
+
+	ch = pl08x_get_phy_channel(pl08x, plchan);
+	if (!ch) {
+		dev_dbg(&pl08x->adev->dev, "no physical channel available for xfer on %s\n", plchan->name);
+		plchan->state = PL08X_CHAN_WAITING;
+		return;
+	}
+
+	dev_dbg(&pl08x->adev->dev, "allocated physical channel %d for xfer on %s\n",
+		ch->id, plchan->name);
+
+	plchan->phychan = ch;
+	plchan->state = PL08X_CHAN_RUNNING;
+	pl08x_start_next_txd(plchan);
+}
+
+static void pl08x_phy_reassign_start(struct pl08x_phy_chan *ch,
+	struct pl08x_dma_chan *plchan)
+{
+	struct pl08x_driver_data *pl08x = plchan->host;
+
+	dev_dbg(&pl08x->adev->dev, "reassigned physical channel %d for xfer on %s\n",
+		ch->id, plchan->name);
+
+	/*
+	 * We do this without taking the lock; we're really only concerned
+	 * about whether this pointer is NULL or not, and we're guaranteed
+	 * that this will only be called when it _already_ is non-NULL.
+	 */
+	ch->serving = plchan;
+	plchan->phychan = ch;
+	plchan->state = PL08X_CHAN_RUNNING;
+	pl08x_start_next_txd(plchan);
+}
+
+/*
+ * Free a physical DMA channel, potentially reallocating it to another
+ * virtual channel if we have any pending.
+ */
+static void pl08x_phy_free(struct pl08x_dma_chan *plchan)
+{
+	struct pl08x_driver_data *pl08x = plchan->host;
+	struct pl08x_dma_chan *p, *next;
+
+ retry:
+	next = NULL;
+
+	/* Find a waiting virtual channel for the next transfer. */
+	list_for_each_entry(p, &pl08x->memcpy.channels, vc.chan.device_node)
+		if (p->state == PL08X_CHAN_WAITING) {
+			next = p;
+			break;
+		}
+
+	if (!next) {
+		list_for_each_entry(p, &pl08x->slave.channels, vc.chan.device_node)
+			if (p->state == PL08X_CHAN_WAITING) {
+				next = p;
+				break;
+			}
+	}
+
+	/* Ensure that the physical channel is stopped */
+	pl08x_terminate_phy_chan(pl08x, plchan->phychan);
+
+	if (next) {
+		bool success;
+
+		/*
+		 * Eww.  We know this isn't going to deadlock
+		 * but lockdep probably doesn't.
+		 */
+		spin_lock(&next->vc.lock);
+		/* Re-check the state now that we have the lock */
+		success = next->state == PL08X_CHAN_WAITING;
+		if (success)
+			pl08x_phy_reassign_start(plchan->phychan, next);
+		spin_unlock(&next->vc.lock);
+
+		/* If the state changed, try to find another channel */
+		if (!success)
+			goto retry;
+	} else {
+		/* No more jobs, so free up the physical channel */
+		pl08x_put_phy_channel(pl08x, plchan->phychan);
+	}
+
+	plchan->phychan = NULL;
+	plchan->state = PL08X_CHAN_IDLE;
 }
 
 /*
@@ -585,8 +819,6 @@
 		return 0;
 	}
 
-	pl08x->pool_ctr++;
-
 	bd.txd = txd;
 	bd.lli_bus = (pl08x->lli_buses & PL08X_AHB2) ? PL080_LLI_LM_AHB2 : 0;
 	cctl = txd->cctl;
@@ -802,18 +1034,14 @@
 	return num_llis;
 }
 
-/* You should call this with the struct pl08x lock held */
 static void pl08x_free_txd(struct pl08x_driver_data *pl08x,
 			   struct pl08x_txd *txd)
 {
 	struct pl08x_sg *dsg, *_dsg;
 
-	/* Free the LLI */
 	if (txd->llis_va)
 		dma_pool_free(pl08x->pool, txd->llis_va, txd->llis_bus);
 
-	pl08x->pool_ctr--;
-
 	list_for_each_entry_safe(dsg, _dsg, &txd->dsg_list, node) {
 		list_del(&dsg->node);
 		kfree(dsg);
@@ -822,18 +1050,60 @@
 	kfree(txd);
 }
 
+static void pl08x_unmap_buffers(struct pl08x_txd *txd)
+{
+	struct device *dev = txd->vd.tx.chan->device->dev;
+	struct pl08x_sg *dsg;
+
+	if (!(txd->vd.tx.flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
+		if (txd->vd.tx.flags & DMA_COMPL_SRC_UNMAP_SINGLE)
+			list_for_each_entry(dsg, &txd->dsg_list, node)
+				dma_unmap_single(dev, dsg->src_addr, dsg->len,
+						DMA_TO_DEVICE);
+		else {
+			list_for_each_entry(dsg, &txd->dsg_list, node)
+				dma_unmap_page(dev, dsg->src_addr, dsg->len,
+						DMA_TO_DEVICE);
+		}
+	}
+	if (!(txd->vd.tx.flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
+		if (txd->vd.tx.flags & DMA_COMPL_DEST_UNMAP_SINGLE)
+			list_for_each_entry(dsg, &txd->dsg_list, node)
+				dma_unmap_single(dev, dsg->dst_addr, dsg->len,
+						DMA_FROM_DEVICE);
+		else
+			list_for_each_entry(dsg, &txd->dsg_list, node)
+				dma_unmap_page(dev, dsg->dst_addr, dsg->len,
+						DMA_FROM_DEVICE);
+	}
+}
+
+static void pl08x_desc_free(struct virt_dma_desc *vd)
+{
+	struct pl08x_txd *txd = to_pl08x_txd(&vd->tx);
+	struct pl08x_dma_chan *plchan = to_pl08x_chan(vd->tx.chan);
+
+	if (!plchan->slave)
+		pl08x_unmap_buffers(txd);
+
+	if (!txd->done)
+		pl08x_release_mux(plchan);
+
+	pl08x_free_txd(plchan->host, txd);
+}
+
 static void pl08x_free_txd_list(struct pl08x_driver_data *pl08x,
 				struct pl08x_dma_chan *plchan)
 {
-	struct pl08x_txd *txdi = NULL;
-	struct pl08x_txd *next;
+	LIST_HEAD(head);
+	struct pl08x_txd *txd;
 
-	if (!list_empty(&plchan->pend_list)) {
-		list_for_each_entry_safe(txdi,
-					 next, &plchan->pend_list, node) {
-			list_del(&txdi->node);
-			pl08x_free_txd(pl08x, txdi);
-		}
+	vchan_get_all_descriptors(&plchan->vc, &head);
+
+	while (!list_empty(&head)) {
+		txd = list_first_entry(&head, struct pl08x_txd, vd.node);
+		list_del(&txd->vd.node);
+		pl08x_desc_free(&txd->vd);
 	}
 }
 
@@ -847,108 +1117,8 @@
 
 static void pl08x_free_chan_resources(struct dma_chan *chan)
 {
-}
-
-/*
- * This should be called with the channel plchan->lock held
- */
-static int prep_phy_channel(struct pl08x_dma_chan *plchan,
-			    struct pl08x_txd *txd)
-{
-	struct pl08x_driver_data *pl08x = plchan->host;
-	struct pl08x_phy_chan *ch;
-	int ret;
-
-	/* Check if we already have a channel */
-	if (plchan->phychan) {
-		ch = plchan->phychan;
-		goto got_channel;
-	}
-
-	ch = pl08x_get_phy_channel(pl08x, plchan);
-	if (!ch) {
-		/* No physical channel available, cope with it */
-		dev_dbg(&pl08x->adev->dev, "no physical channel available for xfer on %s\n", plchan->name);
-		return -EBUSY;
-	}
-
-	/*
-	 * OK we have a physical channel: for memcpy() this is all we
-	 * need, but for slaves the physical signals may be muxed!
-	 * Can the platform allow us to use this channel?
-	 */
-	if (plchan->slave && pl08x->pd->get_signal) {
-		ret = pl08x->pd->get_signal(plchan);
-		if (ret < 0) {
-			dev_dbg(&pl08x->adev->dev,
-				"unable to use physical channel %d for transfer on %s due to platform restrictions\n",
-				ch->id, plchan->name);
-			/* Release physical channel & return */
-			pl08x_put_phy_channel(pl08x, ch);
-			return -EBUSY;
-		}
-		ch->signal = ret;
-	}
-
-	plchan->phychan = ch;
-	dev_dbg(&pl08x->adev->dev, "allocated physical channel %d and signal %d for xfer on %s\n",
-		 ch->id,
-		 ch->signal,
-		 plchan->name);
-
-got_channel:
-	/* Assign the flow control signal to this channel */
-	if (txd->direction == DMA_MEM_TO_DEV)
-		txd->ccfg |= ch->signal << PL080_CONFIG_DST_SEL_SHIFT;
-	else if (txd->direction == DMA_DEV_TO_MEM)
-		txd->ccfg |= ch->signal << PL080_CONFIG_SRC_SEL_SHIFT;
-
-	plchan->phychan_hold++;
-
-	return 0;
-}
-
-static void release_phy_channel(struct pl08x_dma_chan *plchan)
-{
-	struct pl08x_driver_data *pl08x = plchan->host;
-
-	if ((plchan->phychan->signal >= 0) && pl08x->pd->put_signal) {
-		pl08x->pd->put_signal(plchan);
-		plchan->phychan->signal = -1;
-	}
-	pl08x_put_phy_channel(pl08x, plchan->phychan);
-	plchan->phychan = NULL;
-}
-
-static dma_cookie_t pl08x_tx_submit(struct dma_async_tx_descriptor *tx)
-{
-	struct pl08x_dma_chan *plchan = to_pl08x_chan(tx->chan);
-	struct pl08x_txd *txd = to_pl08x_txd(tx);
-	unsigned long flags;
-	dma_cookie_t cookie;
-
-	spin_lock_irqsave(&plchan->lock, flags);
-	cookie = dma_cookie_assign(tx);
-
-	/* Put this onto the pending list */
-	list_add_tail(&txd->node, &plchan->pend_list);
-
-	/*
-	 * If there was no physical channel available for this memcpy,
-	 * stack the request up and indicate that the channel is waiting
-	 * for a free physical channel.
-	 */
-	if (!plchan->slave && !plchan->phychan) {
-		/* Do this memcpy whenever there is a channel ready */
-		plchan->state = PL08X_CHAN_WAITING;
-		plchan->waiting = txd;
-	} else {
-		plchan->phychan_hold--;
-	}
-
-	spin_unlock_irqrestore(&plchan->lock, flags);
-
-	return cookie;
+	/* Ensure all queued descriptors are freed */
+	vchan_free_chan_resources(to_virt_chan(chan));
 }
 
 static struct dma_async_tx_descriptor *pl08x_prep_dma_interrupt(
@@ -968,23 +1138,53 @@
 		dma_cookie_t cookie, struct dma_tx_state *txstate)
 {
 	struct pl08x_dma_chan *plchan = to_pl08x_chan(chan);
+	struct virt_dma_desc *vd;
+	unsigned long flags;
 	enum dma_status ret;
+	size_t bytes = 0;
 
 	ret = dma_cookie_status(chan, cookie, txstate);
 	if (ret == DMA_SUCCESS)
 		return ret;
 
 	/*
+	 * There's no point calculating the residue if there's
+	 * no txstate to store the value.
+	 */
+	if (!txstate) {
+		if (plchan->state == PL08X_CHAN_PAUSED)
+			ret = DMA_PAUSED;
+		return ret;
+	}
+
+	spin_lock_irqsave(&plchan->vc.lock, flags);
+	ret = dma_cookie_status(chan, cookie, txstate);
+	if (ret != DMA_SUCCESS) {
+		vd = vchan_find_desc(&plchan->vc, cookie);
+		if (vd) {
+			/* On the issued list, so hasn't been processed yet */
+			struct pl08x_txd *txd = to_pl08x_txd(&vd->tx);
+			struct pl08x_sg *dsg;
+
+			list_for_each_entry(dsg, &txd->dsg_list, node)
+				bytes += dsg->len;
+		} else {
+			bytes = pl08x_getbytes_chan(plchan);
+		}
+	}
+	spin_unlock_irqrestore(&plchan->vc.lock, flags);
+
+	/*
 	 * This cookie not complete yet
 	 * Get number of bytes left in the active transactions and queue
 	 */
-	dma_set_residue(txstate, pl08x_getbytes_chan(plchan));
+	dma_set_residue(txstate, bytes);
 
-	if (plchan->state == PL08X_CHAN_PAUSED)
-		return DMA_PAUSED;
+	if (plchan->state == PL08X_CHAN_PAUSED && ret == DMA_IN_PROGRESS)
+		ret = DMA_PAUSED;
 
 	/* Whether waiting or running, we're in progress */
-	return DMA_IN_PROGRESS;
+	return ret;
 }
 
 /* PrimeCell DMA extension */
@@ -1080,38 +1280,14 @@
 	return burst_sizes[i].reg;
 }
 
-static int dma_set_runtime_config(struct dma_chan *chan,
-				  struct dma_slave_config *config)
+static u32 pl08x_get_cctl(struct pl08x_dma_chan *plchan,
+	enum dma_slave_buswidth addr_width, u32 maxburst)
 {
-	struct pl08x_dma_chan *plchan = to_pl08x_chan(chan);
-	struct pl08x_driver_data *pl08x = plchan->host;
-	enum dma_slave_buswidth addr_width;
-	u32 width, burst, maxburst;
-	u32 cctl = 0;
-
-	if (!plchan->slave)
-		return -EINVAL;
-
-	/* Transfer direction */
-	plchan->runtime_direction = config->direction;
-	if (config->direction == DMA_MEM_TO_DEV) {
-		addr_width = config->dst_addr_width;
-		maxburst = config->dst_maxburst;
-	} else if (config->direction == DMA_DEV_TO_MEM) {
-		addr_width = config->src_addr_width;
-		maxburst = config->src_maxburst;
-	} else {
-		dev_err(&pl08x->adev->dev,
-			"bad runtime_config: alien transfer direction\n");
-		return -EINVAL;
-	}
+	u32 width, burst, cctl = 0;
 
 	width = pl08x_width(addr_width);
-	if (width == ~0) {
-		dev_err(&pl08x->adev->dev,
-			"bad runtime_config: alien address width\n");
-		return -EINVAL;
-	}
+	if (width == ~0)
+		return ~0;
 
 	cctl |= width << PL080_CONTROL_SWIDTH_SHIFT;
 	cctl |= width << PL080_CONTROL_DWIDTH_SHIFT;
@@ -1128,28 +1304,23 @@
 	cctl |= burst << PL080_CONTROL_SB_SIZE_SHIFT;
 	cctl |= burst << PL080_CONTROL_DB_SIZE_SHIFT;
 
-	plchan->device_fc = config->device_fc;
+	return pl08x_cctl(cctl);
+}
 
-	if (plchan->runtime_direction == DMA_DEV_TO_MEM) {
-		plchan->src_addr = config->src_addr;
-		plchan->src_cctl = pl08x_cctl(cctl) | PL080_CONTROL_DST_INCR |
-			pl08x_select_bus(plchan->cd->periph_buses,
-					 pl08x->mem_buses);
-	} else {
-		plchan->dst_addr = config->dst_addr;
-		plchan->dst_cctl = pl08x_cctl(cctl) | PL080_CONTROL_SRC_INCR |
-			pl08x_select_bus(pl08x->mem_buses,
-					 plchan->cd->periph_buses);
-	}
+static int dma_set_runtime_config(struct dma_chan *chan,
+				  struct dma_slave_config *config)
+{
+	struct pl08x_dma_chan *plchan = to_pl08x_chan(chan);
 
-	dev_dbg(&pl08x->adev->dev,
-		"configured channel %s (%s) for %s, data width %d, "
-		"maxburst %d words, LE, CCTL=0x%08x\n",
-		dma_chan_name(chan), plchan->name,
-		(config->direction == DMA_DEV_TO_MEM) ? "RX" : "TX",
-		addr_width,
-		maxburst,
-		cctl);
+	if (!plchan->slave)
+		return -EINVAL;
+
+	/* Reject definitely invalid configurations */
+	if (config->src_addr_width == DMA_SLAVE_BUSWIDTH_8_BYTES ||
+	    config->dst_addr_width == DMA_SLAVE_BUSWIDTH_8_BYTES)
+		return -EINVAL;
+
+	plchan->cfg = *config;
 
 	return 0;
 }
@@ -1163,95 +1334,19 @@
 	struct pl08x_dma_chan *plchan = to_pl08x_chan(chan);
 	unsigned long flags;
 
-	spin_lock_irqsave(&plchan->lock, flags);
-	/* Something is already active, or we're waiting for a channel... */
-	if (plchan->at || plchan->state == PL08X_CHAN_WAITING) {
-		spin_unlock_irqrestore(&plchan->lock, flags);
-		return;
+	spin_lock_irqsave(&plchan->vc.lock, flags);
+	if (vchan_issue_pending(&plchan->vc)) {
+		if (!plchan->phychan && plchan->state != PL08X_CHAN_WAITING)
+			pl08x_phy_alloc_and_start(plchan);
 	}
-
-	/* Take the first element in the queue and execute it */
-	if (!list_empty(&plchan->pend_list)) {
-		struct pl08x_txd *next;
-
-		next = list_first_entry(&plchan->pend_list,
-					struct pl08x_txd,
-					node);
-		list_del(&next->node);
-		plchan->state = PL08X_CHAN_RUNNING;
-
-		pl08x_start_txd(plchan, next);
-	}
-
-	spin_unlock_irqrestore(&plchan->lock, flags);
+	spin_unlock_irqrestore(&plchan->vc.lock, flags);
 }
 
-static int pl08x_prep_channel_resources(struct pl08x_dma_chan *plchan,
-					struct pl08x_txd *txd)
-{
-	struct pl08x_driver_data *pl08x = plchan->host;
-	unsigned long flags;
-	int num_llis, ret;
-
-	num_llis = pl08x_fill_llis_for_desc(pl08x, txd);
-	if (!num_llis) {
-		spin_lock_irqsave(&plchan->lock, flags);
-		pl08x_free_txd(pl08x, txd);
-		spin_unlock_irqrestore(&plchan->lock, flags);
-		return -EINVAL;
-	}
-
-	spin_lock_irqsave(&plchan->lock, flags);
-
-	/*
-	 * See if we already have a physical channel allocated,
-	 * else this is the time to try to get one.
-	 */
-	ret = prep_phy_channel(plchan, txd);
-	if (ret) {
-		/*
-		 * No physical channel was available.
-		 *
-		 * memcpy transfers can be sorted out at submission time.
-		 *
-		 * Slave transfers may have been denied due to platform
-		 * channel muxing restrictions.  Since there is no guarantee
-		 * that this will ever be resolved, and the signal must be
-		 * acquired AFTER acquiring the physical channel, we will let
-		 * them be NACK:ed with -EBUSY here. The drivers can retry
-		 * the prep() call if they are eager on doing this using DMA.
-		 */
-		if (plchan->slave) {
-			pl08x_free_txd_list(pl08x, plchan);
-			pl08x_free_txd(pl08x, txd);
-			spin_unlock_irqrestore(&plchan->lock, flags);
-			return -EBUSY;
-		}
-	} else
-		/*
-		 * Else we're all set, paused and ready to roll, status
-		 * will switch to PL08X_CHAN_RUNNING when we call
-		 * issue_pending(). If there is something running on the
-		 * channel already we don't change its state.
-		 */
-		if (plchan->state == PL08X_CHAN_IDLE)
-			plchan->state = PL08X_CHAN_PAUSED;
-
-	spin_unlock_irqrestore(&plchan->lock, flags);
-
-	return 0;
-}
-
-static struct pl08x_txd *pl08x_get_txd(struct pl08x_dma_chan *plchan,
-	unsigned long flags)
+static struct pl08x_txd *pl08x_get_txd(struct pl08x_dma_chan *plchan)
 {
 	struct pl08x_txd *txd = kzalloc(sizeof(*txd), GFP_NOWAIT);
 
 	if (txd) {
-		dma_async_tx_descriptor_init(&txd->tx, &plchan->chan);
-		txd->tx.flags = flags;
-		txd->tx.tx_submit = pl08x_tx_submit;
-		INIT_LIST_HEAD(&txd->node);
 		INIT_LIST_HEAD(&txd->dsg_list);
 
 		/* Always enable error and terminal interrupts */
@@ -1274,7 +1369,7 @@
 	struct pl08x_sg *dsg;
 	int ret;
 
-	txd = pl08x_get_txd(plchan, flags);
+	txd = pl08x_get_txd(plchan);
 	if (!txd) {
 		dev_err(&pl08x->adev->dev,
 			"%s no memory for descriptor\n", __func__);
@@ -1290,14 +1385,13 @@
 	}
 	list_add_tail(&dsg->node, &txd->dsg_list);
 
-	txd->direction = DMA_NONE;
 	dsg->src_addr = src;
 	dsg->dst_addr = dest;
 	dsg->len = len;
 
 	/* Set platform data for m2m */
 	txd->ccfg |= PL080_FLOW_MEM2MEM << PL080_CONFIG_FLOW_CONTROL_SHIFT;
-	txd->cctl = pl08x->pd->memcpy_channel.cctl &
+	txd->cctl = pl08x->pd->memcpy_channel.cctl_memcpy &
 			~(PL080_CONTROL_DST_AHB2 | PL080_CONTROL_SRC_AHB2);
 
 	/* Both to be incremented or the code will break */
@@ -1307,11 +1401,13 @@
 		txd->cctl |= pl08x_select_bus(pl08x->mem_buses,
 					      pl08x->mem_buses);
 
-	ret = pl08x_prep_channel_resources(plchan, txd);
-	if (ret)
+	ret = pl08x_fill_llis_for_desc(plchan->host, txd);
+	if (!ret) {
+		pl08x_free_txd(pl08x, txd);
 		return NULL;
+	}
 
-	return &txd->tx;
+	return vchan_tx_prep(&plchan->vc, &txd->vd, flags);
 }
 
 static struct dma_async_tx_descriptor *pl08x_prep_slave_sg(
@@ -1324,36 +1420,40 @@
 	struct pl08x_txd *txd;
 	struct pl08x_sg *dsg;
 	struct scatterlist *sg;
+	enum dma_slave_buswidth addr_width;
 	dma_addr_t slave_addr;
 	int ret, tmp;
+	u8 src_buses, dst_buses;
+	u32 maxburst, cctl;
 
 	dev_dbg(&pl08x->adev->dev, "%s prepare transaction of %d bytes from %s\n",
 			__func__, sg_dma_len(sgl), plchan->name);
 
-	txd = pl08x_get_txd(plchan, flags);
+	txd = pl08x_get_txd(plchan);
 	if (!txd) {
 		dev_err(&pl08x->adev->dev, "%s no txd\n", __func__);
 		return NULL;
 	}
 
-	if (direction != plchan->runtime_direction)
-		dev_err(&pl08x->adev->dev, "%s DMA setup does not match "
-			"the direction configured for the PrimeCell\n",
-			__func__);
-
 	/*
 	 * Set up addresses, the PrimeCell configured address
 	 * will take precedence since this may configure the
 	 * channel target address dynamically at runtime.
 	 */
-	txd->direction = direction;
-
 	if (direction == DMA_MEM_TO_DEV) {
-		txd->cctl = plchan->dst_cctl;
-		slave_addr = plchan->dst_addr;
+		cctl = PL080_CONTROL_SRC_INCR;
+		slave_addr = plchan->cfg.dst_addr;
+		addr_width = plchan->cfg.dst_addr_width;
+		maxburst = plchan->cfg.dst_maxburst;
+		src_buses = pl08x->mem_buses;
+		dst_buses = plchan->cd->periph_buses;
 	} else if (direction == DMA_DEV_TO_MEM) {
-		txd->cctl = plchan->src_cctl;
-		slave_addr = plchan->src_addr;
+		cctl = PL080_CONTROL_DST_INCR;
+		slave_addr = plchan->cfg.src_addr;
+		addr_width = plchan->cfg.src_addr_width;
+		maxburst = plchan->cfg.src_maxburst;
+		src_buses = plchan->cd->periph_buses;
+		dst_buses = pl08x->mem_buses;
 	} else {
 		pl08x_free_txd(pl08x, txd);
 		dev_err(&pl08x->adev->dev,
@@ -1361,7 +1461,17 @@
 		return NULL;
 	}
 
-	if (plchan->device_fc)
+	cctl |= pl08x_get_cctl(plchan, addr_width, maxburst);
+	if (cctl == ~0) {
+		pl08x_free_txd(pl08x, txd);
+		dev_err(&pl08x->adev->dev,
+			"DMA slave configuration botched?\n");
+		return NULL;
+	}
+
+	txd->cctl = cctl | pl08x_select_bus(src_buses, dst_buses);
+
+	if (plchan->cfg.device_fc)
 		tmp = (direction == DMA_MEM_TO_DEV) ? PL080_FLOW_MEM2PER_PER :
 			PL080_FLOW_PER2MEM_PER;
 	else
@@ -1370,9 +1480,28 @@
 
 	txd->ccfg |= tmp << PL080_CONFIG_FLOW_CONTROL_SHIFT;
 
+	ret = pl08x_request_mux(plchan);
+	if (ret < 0) {
+		pl08x_free_txd(pl08x, txd);
+		dev_dbg(&pl08x->adev->dev,
+			"unable to mux for transfer on %s due to platform restrictions\n",
+			plchan->name);
+		return NULL;
+	}
+
+	dev_dbg(&pl08x->adev->dev, "allocated DMA request signal %d for xfer on %s\n",
+		 plchan->signal, plchan->name);
+
+	/* Assign the flow control signal to this channel */
+	if (direction == DMA_MEM_TO_DEV)
+		txd->ccfg |= plchan->signal << PL080_CONFIG_DST_SEL_SHIFT;
+	else
+		txd->ccfg |= plchan->signal << PL080_CONFIG_SRC_SEL_SHIFT;
+
 	for_each_sg(sgl, sg, sg_len, tmp) {
 		dsg = kzalloc(sizeof(struct pl08x_sg), GFP_NOWAIT);
 		if (!dsg) {
+			pl08x_release_mux(plchan);
 			pl08x_free_txd(pl08x, txd);
 			dev_err(&pl08x->adev->dev, "%s no mem for pl080 sg\n",
 					__func__);
@@ -1390,11 +1519,14 @@
 		}
 	}
 
-	ret = pl08x_prep_channel_resources(plchan, txd);
-	if (ret)
+	ret = pl08x_fill_llis_for_desc(plchan->host, txd);
+	if (!ret) {
+		pl08x_release_mux(plchan);
+		pl08x_free_txd(pl08x, txd);
 		return NULL;
+	}
 
-	return &txd->tx;
+	return vchan_tx_prep(&plchan->vc, &txd->vd, flags);
 }
 
 static int pl08x_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
@@ -1415,9 +1547,9 @@
 	 * Anything succeeds on channels with no physical allocation and
 	 * no queued transfers.
 	 */
-	spin_lock_irqsave(&plchan->lock, flags);
+	spin_lock_irqsave(&plchan->vc.lock, flags);
 	if (!plchan->phychan && !plchan->at) {
-		spin_unlock_irqrestore(&plchan->lock, flags);
+		spin_unlock_irqrestore(&plchan->vc.lock, flags);
 		return 0;
 	}
 
@@ -1426,18 +1558,15 @@
 		plchan->state = PL08X_CHAN_IDLE;
 
 		if (plchan->phychan) {
-			pl08x_terminate_phy_chan(pl08x, plchan->phychan);
-
 			/*
 			 * Mark physical channel as free and free any slave
 			 * signal
 			 */
-			release_phy_channel(plchan);
-			plchan->phychan_hold = 0;
+			pl08x_phy_free(plchan);
 		}
 		/* Dequeue jobs and free LLIs */
 		if (plchan->at) {
-			pl08x_free_txd(pl08x, plchan->at);
+			pl08x_desc_free(&plchan->at->vd);
 			plchan->at = NULL;
 		}
 		/* Dequeue jobs not yet fired as well */
@@ -1457,7 +1586,7 @@
 		break;
 	}
 
-	spin_unlock_irqrestore(&plchan->lock, flags);
+	spin_unlock_irqrestore(&plchan->vc.lock, flags);
 
 	return ret;
 }
@@ -1494,123 +1623,6 @@
 	writel(PL080_CONFIG_ENABLE, pl08x->base + PL080_CONFIG);
 }
 
-static void pl08x_unmap_buffers(struct pl08x_txd *txd)
-{
-	struct device *dev = txd->tx.chan->device->dev;
-	struct pl08x_sg *dsg;
-
-	if (!(txd->tx.flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-		if (txd->tx.flags & DMA_COMPL_SRC_UNMAP_SINGLE)
-			list_for_each_entry(dsg, &txd->dsg_list, node)
-				dma_unmap_single(dev, dsg->src_addr, dsg->len,
-						DMA_TO_DEVICE);
-		else {
-			list_for_each_entry(dsg, &txd->dsg_list, node)
-				dma_unmap_page(dev, dsg->src_addr, dsg->len,
-						DMA_TO_DEVICE);
-		}
-	}
-	if (!(txd->tx.flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
-		if (txd->tx.flags & DMA_COMPL_DEST_UNMAP_SINGLE)
-			list_for_each_entry(dsg, &txd->dsg_list, node)
-				dma_unmap_single(dev, dsg->dst_addr, dsg->len,
-						DMA_FROM_DEVICE);
-		else
-			list_for_each_entry(dsg, &txd->dsg_list, node)
-				dma_unmap_page(dev, dsg->dst_addr, dsg->len,
-						DMA_FROM_DEVICE);
-	}
-}
-
-static void pl08x_tasklet(unsigned long data)
-{
-	struct pl08x_dma_chan *plchan = (struct pl08x_dma_chan *) data;
-	struct pl08x_driver_data *pl08x = plchan->host;
-	struct pl08x_txd *txd;
-	unsigned long flags;
-
-	spin_lock_irqsave(&plchan->lock, flags);
-
-	txd = plchan->at;
-	plchan->at = NULL;
-
-	if (txd) {
-		/* Update last completed */
-		dma_cookie_complete(&txd->tx);
-	}
-
-	/* If a new descriptor is queued, set it up plchan->at is NULL here */
-	if (!list_empty(&plchan->pend_list)) {
-		struct pl08x_txd *next;
-
-		next = list_first_entry(&plchan->pend_list,
-					struct pl08x_txd,
-					node);
-		list_del(&next->node);
-
-		pl08x_start_txd(plchan, next);
-	} else if (plchan->phychan_hold) {
-		/*
-		 * This channel is still in use - we have a new txd being
-		 * prepared and will soon be queued.  Don't give up the
-		 * physical channel.
-		 */
-	} else {
-		struct pl08x_dma_chan *waiting = NULL;
-
-		/*
-		 * No more jobs, so free up the physical channel
-		 * Free any allocated signal on slave transfers too
-		 */
-		release_phy_channel(plchan);
-		plchan->state = PL08X_CHAN_IDLE;
-
-		/*
-		 * And NOW before anyone else can grab that free:d up
-		 * physical channel, see if there is some memcpy pending
-		 * that seriously needs to start because of being stacked
-		 * up while we were choking the physical channels with data.
-		 */
-		list_for_each_entry(waiting, &pl08x->memcpy.channels,
-				    chan.device_node) {
-			if (waiting->state == PL08X_CHAN_WAITING &&
-				waiting->waiting != NULL) {
-				int ret;
-
-				/* This should REALLY not fail now */
-				ret = prep_phy_channel(waiting,
-						       waiting->waiting);
-				BUG_ON(ret);
-				waiting->phychan_hold--;
-				waiting->state = PL08X_CHAN_RUNNING;
-				waiting->waiting = NULL;
-				pl08x_issue_pending(&waiting->chan);
-				break;
-			}
-		}
-	}
-
-	spin_unlock_irqrestore(&plchan->lock, flags);
-
-	if (txd) {
-		dma_async_tx_callback callback = txd->tx.callback;
-		void *callback_param = txd->tx.callback_param;
-
-		/* Don't try to unmap buffers on slave channels */
-		if (!plchan->slave)
-			pl08x_unmap_buffers(txd);
-
-		/* Free the descriptor */
-		spin_lock_irqsave(&plchan->lock, flags);
-		pl08x_free_txd(pl08x, txd);
-		spin_unlock_irqrestore(&plchan->lock, flags);
-
-		/* Callback to signal completion */
-		if (callback)
-			callback(callback_param);
-	}
-}
-
 static irqreturn_t pl08x_irq(int irq, void *dev)
 {
 	struct pl08x_driver_data *pl08x = dev;
@@ -1635,6 +1647,7 @@
 			/* Locate physical channel */
 			struct pl08x_phy_chan *phychan = &pl08x->phy_chans[i];
 			struct pl08x_dma_chan *plchan = phychan->serving;
+			struct pl08x_txd *tx;
 
 			if (!plchan) {
 				dev_err(&pl08x->adev->dev,
@@ -1643,8 +1656,29 @@
 				continue;
 			}
 
-			/* Schedule tasklet on this channel */
-			tasklet_schedule(&plchan->tasklet);
+			spin_lock(&plchan->vc.lock);
+			tx = plchan->at;
+			if (tx) {
+				plchan->at = NULL;
+				/*
+				 * This descriptor is done, release its mux
+				 * reservation.
+				 */
+				pl08x_release_mux(plchan);
+				tx->done = true;
+				vchan_cookie_complete(&tx->vd);
+
+				/*
+				 * And start the next descriptor (if any),
+				 * otherwise free this channel.
+				 */
+				if (vchan_next_desc(&plchan->vc))
+					pl08x_start_next_txd(plchan);
+				else
+					pl08x_phy_free(plchan);
+			}
+			spin_unlock(&plchan->vc.lock);
+
 			mask |= (1 << i);
 		}
 	}
@@ -1654,16 +1688,10 @@
 
 static void pl08x_dma_slave_init(struct pl08x_dma_chan *chan)
 {
-	u32 cctl = pl08x_cctl(chan->cd->cctl);
-
 	chan->slave = true;
 	chan->name = chan->cd->bus_id;
-	chan->src_addr = chan->cd->addr;
-	chan->dst_addr = chan->cd->addr;
-	chan->src_cctl = cctl | PL080_CONTROL_DST_INCR |
-		pl08x_select_bus(chan->cd->periph_buses, chan->host->mem_buses);
-	chan->dst_cctl = cctl | PL080_CONTROL_SRC_INCR |
-		pl08x_select_bus(chan->host->mem_buses, chan->cd->periph_buses);
+	chan->cfg.src_addr = chan->cd->addr;
+	chan->cfg.dst_addr = chan->cd->addr;
 }
 
 /*
@@ -1693,6 +1721,7 @@
 
 		chan->host = pl08x;
 		chan->state = PL08X_CHAN_IDLE;
+		chan->signal = -1;
 
 		if (slave) {
 			chan->cd = &pl08x->pd->slave_channels[i];
@@ -1705,26 +1734,12 @@
 				return -ENOMEM;
 			}
 		}
-		if (chan->cd->circular_buffer) {
-			dev_err(&pl08x->adev->dev,
-				"channel %s: circular buffers not supported\n",
-				chan->name);
-			kfree(chan);
-			continue;
-		}
 		dev_dbg(&pl08x->adev->dev,
 			 "initialize virtual channel \"%s\"\n",
 			 chan->name);
 
-		chan->chan.device = dmadev;
-		dma_cookie_init(&chan->chan);
-
-		spin_lock_init(&chan->lock);
-		INIT_LIST_HEAD(&chan->pend_list);
-		tasklet_init(&chan->tasklet, pl08x_tasklet,
-			     (unsigned long) chan);
-
-		list_add_tail(&chan->chan.device_node, &dmadev->channels);
+		chan->vc.desc_free = pl08x_desc_free;
+		vchan_init(&chan->vc, dmadev);
 	}
 	dev_info(&pl08x->adev->dev, "initialized %d virtual %s channels\n",
 		 i, slave ? "slave" : "memcpy");
@@ -1737,8 +1752,8 @@
 	struct pl08x_dma_chan *next;
 
 	list_for_each_entry_safe(chan,
-				 next, &dmadev->channels, chan.device_node) {
-		list_del(&chan->chan.device_node);
+				 next, &dmadev->channels, vc.chan.device_node) {
+		list_del(&chan->vc.chan.device_node);
 		kfree(chan);
 	}
 }
@@ -1791,7 +1806,7 @@
 	seq_printf(s, "\nPL08x virtual memcpy channels:\n");
 	seq_printf(s, "CHANNEL:\tSTATE:\n");
 	seq_printf(s, "--------\t------\n");
-	list_for_each_entry(chan, &pl08x->memcpy.channels, chan.device_node) {
+	list_for_each_entry(chan, &pl08x->memcpy.channels, vc.chan.device_node) {
 		seq_printf(s, "%s\t\t%s\n", chan->name,
 			   pl08x_state_str(chan->state));
 	}
@@ -1799,7 +1814,7 @@
 	seq_printf(s, "\nPL08x virtual slave channels:\n");
 	seq_printf(s, "CHANNEL:\tSTATE:\n");
 	seq_printf(s, "--------\t------\n");
-	list_for_each_entry(chan, &pl08x->slave.channels, chan.device_node) {
+	list_for_each_entry(chan, &pl08x->slave.channels, vc.chan.device_node) {
 		seq_printf(s, "%s\t\t%s\n", chan->name,
 			   pl08x_state_str(chan->state));
 	}
@@ -1851,9 +1866,6 @@
 		goto out_no_pl08x;
 	}
 
-	pm_runtime_set_active(&adev->dev);
-	pm_runtime_enable(&adev->dev);
-
 	/* Initialize memcpy engine */
 	dma_cap_set(DMA_MEMCPY, pl08x->memcpy.cap_mask);
 	pl08x->memcpy.dev = &adev->dev;
@@ -1903,8 +1915,6 @@
 		goto out_no_lli_pool;
 	}
 
-	spin_lock_init(&pl08x->lock);
-
 	pl08x->base = ioremap(adev->res.start, resource_size(&adev->res));
 	if (!pl08x->base) {
 		ret = -ENOMEM;
@@ -1942,7 +1952,6 @@
 		ch->id = i;
 		ch->base = pl08x->base + PL080_Cx_BASE(i);
 		spin_lock_init(&ch->lock);
-		ch->signal = -1;
 
 		/*
 		 * Nomadik variants can have channels that are locked
@@ -2007,7 +2016,6 @@
 		 amba_part(adev), amba_rev(adev),
 		 (unsigned long long)adev->res.start, adev->irq[0]);
 
-	pm_runtime_put(&adev->dev);
 	return 0;
 
 out_no_slave_reg:
@@ -2026,9 +2034,6 @@
 	dma_pool_destroy(pl08x->pool);
 out_no_lli_pool:
 out_no_platdata:
-	pm_runtime_put(&adev->dev);
-	pm_runtime_disable(&adev->dev);
-
 	kfree(pl08x);
 out_no_pl08x:
 	amba_release_regions(adev);
diff --git a/drivers/dma/omap-dma.c b/drivers/dma/omap-dma.c
new file mode 100644
index 0000000..ae05618
--- /dev/null
+++ b/drivers/dma/omap-dma.c
@@ -0,0 +1,669 @@
+/*
+ * OMAP DMAengine support
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/omap-dma.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+#include "virt-dma.h"
+#include <plat/dma.h>
+
+struct omap_dmadev {
+	struct dma_device ddev;
+	spinlock_t lock;
+	struct tasklet_struct task;
+	struct list_head pending;
+};
+
+struct omap_chan {
+	struct virt_dma_chan vc;
+	struct list_head node;
+
+	struct dma_slave_config	cfg;
+	unsigned dma_sig;
+	bool cyclic;
+
+	int dma_ch;
+	struct omap_desc *desc;
+	unsigned sgidx;
+};
+
+struct omap_sg {
+	dma_addr_t addr;
+	uint32_t en;		/* number of elements (24-bit) */
+	uint32_t fn;		/* number of frames (16-bit) */
+};
+
+struct omap_desc {
+	struct virt_dma_desc vd;
+	enum dma_transfer_direction dir;
+	dma_addr_t dev_addr;
+
+	int16_t fi;		/* for OMAP_DMA_SYNC_PACKET */
+	uint8_t es;		/* OMAP_DMA_DATA_TYPE_xxx */
+	uint8_t sync_mode;	/* OMAP_DMA_SYNC_xxx */
+	uint8_t sync_type;	/* OMAP_DMA_xxx_SYNC* */
+	uint8_t periph_port;	/* Peripheral port */
+
+	unsigned sglen;
+	struct omap_sg sg[0];
+};
+
+static const unsigned es_bytes[] = {
+	[OMAP_DMA_DATA_TYPE_S8] = 1,
+	[OMAP_DMA_DATA_TYPE_S16] = 2,
+	[OMAP_DMA_DATA_TYPE_S32] = 4,
+};
+
+static inline struct omap_dmadev *to_omap_dma_dev(struct dma_device *d)
+{
+	return container_of(d, struct omap_dmadev, ddev);
+}
+
+static inline struct omap_chan *to_omap_dma_chan(struct dma_chan *c)
+{
+	return container_of(c, struct omap_chan, vc.chan);
+}
+
+static inline struct omap_desc *to_omap_dma_desc(struct dma_async_tx_descriptor *t)
+{
+	return container_of(t, struct omap_desc, vd.tx);
+}
+
+static void omap_dma_desc_free(struct virt_dma_desc *vd)
+{
+	kfree(container_of(vd, struct omap_desc, vd));
+}
+
+static void omap_dma_start_sg(struct omap_chan *c, struct omap_desc *d,
+	unsigned idx)
+{
+	struct omap_sg *sg = d->sg + idx;
+
+	if (d->dir == DMA_DEV_TO_MEM)
+		omap_set_dma_dest_params(c->dma_ch, OMAP_DMA_PORT_EMIFF,
+			OMAP_DMA_AMODE_POST_INC, sg->addr, 0, 0);
+	else
+		omap_set_dma_src_params(c->dma_ch, OMAP_DMA_PORT_EMIFF,
+			OMAP_DMA_AMODE_POST_INC, sg->addr, 0, 0);
+
+	omap_set_dma_transfer_params(c->dma_ch, d->es, sg->en, sg->fn,
+		d->sync_mode, c->dma_sig, d->sync_type);
+
+	omap_start_dma(c->dma_ch);
+}
+
+static void omap_dma_start_desc(struct omap_chan *c)
+{
+	struct virt_dma_desc *vd = vchan_next_desc(&c->vc);
+	struct omap_desc *d;
+
+	if (!vd) {
+		c->desc = NULL;
+		return;
+	}
+
+	list_del(&vd->node);
+
+	c->desc = d = to_omap_dma_desc(&vd->tx);
+	c->sgidx = 0;
+
+	if (d->dir == DMA_DEV_TO_MEM)
+		omap_set_dma_src_params(c->dma_ch, d->periph_port,
+			OMAP_DMA_AMODE_CONSTANT, d->dev_addr, 0, d->fi);
+	else
+		omap_set_dma_dest_params(c->dma_ch, d->periph_port,
+			OMAP_DMA_AMODE_CONSTANT, d->dev_addr, 0, d->fi);
+
+	omap_dma_start_sg(c, d, 0);
+}
+
+static void omap_dma_callback(int ch, u16 status, void *data)
+{
+	struct omap_chan *c = data;
+	struct omap_desc *d;
+	unsigned long flags;
+
+	spin_lock_irqsave(&c->vc.lock, flags);
+	d = c->desc;
+	if (d) {
+		if (!c->cyclic) {
+			if (++c->sgidx < d->sglen) {
+				omap_dma_start_sg(c, d, c->sgidx);
+			} else {
+				omap_dma_start_desc(c);
+				vchan_cookie_complete(&d->vd);
+			}
+		} else {
+			vchan_cyclic_callback(&d->vd);
+		}
+	}
+	spin_unlock_irqrestore(&c->vc.lock, flags);
+}
+
+/*
+ * This callback schedules all pending channels.  We could be more
+ * clever here by postponing allocation of the real DMA channels to
+ * this point, and freeing them when our virtual channel becomes idle.
+ *
+ * We would then need to deal with 'all channels in-use'
+ */
+static void omap_dma_sched(unsigned long data)
+{
+	struct omap_dmadev *d = (struct omap_dmadev *)data;
+	LIST_HEAD(head);
+
+	spin_lock_irq(&d->lock);
+	list_splice_tail_init(&d->pending, &head);
+	spin_unlock_irq(&d->lock);
+
+	while (!list_empty(&head)) {
+		struct omap_chan *c = list_first_entry(&head,
+			struct omap_chan, node);
+
+		spin_lock_irq(&c->vc.lock);
+		list_del_init(&c->node);
+		omap_dma_start_desc(c);
+		spin_unlock_irq(&c->vc.lock);
+	}
+}
+
+static int omap_dma_alloc_chan_resources(struct dma_chan *chan)
+{
+	struct omap_chan *c = to_omap_dma_chan(chan);
+
+	dev_info(c->vc.chan.device->dev, "allocating channel for %u\n", c->dma_sig);
+
+	return omap_request_dma(c->dma_sig, "DMA engine",
+		omap_dma_callback, c, &c->dma_ch);
+}
+
+static void omap_dma_free_chan_resources(struct dma_chan *chan)
+{
+	struct omap_chan *c = to_omap_dma_chan(chan);
+
+	vchan_free_chan_resources(&c->vc);
+	omap_free_dma(c->dma_ch);
+
+	dev_info(c->vc.chan.device->dev, "freeing channel for %u\n", c->dma_sig);
+}
+
+static size_t omap_dma_sg_size(struct omap_sg *sg)
+{
+	return sg->en * sg->fn;
+}
+
+static size_t omap_dma_desc_size(struct omap_desc *d)
+{
+	unsigned i;
+	size_t size;
+
+	for (size = i = 0; i < d->sglen; i++)
+		size += omap_dma_sg_size(&d->sg[i]);
+
+	return size * es_bytes[d->es];
+}
+
+static size_t omap_dma_desc_size_pos(struct omap_desc *d, dma_addr_t addr)
+{
+	unsigned i;
+	size_t size, es_size = es_bytes[d->es];
+
+	for (size = i = 0; i < d->sglen; i++) {
+		size_t this_size = omap_dma_sg_size(&d->sg[i]) * es_size;
+
+		if (size)
+			size += this_size;
+		else if (addr >= d->sg[i].addr &&
+			 addr < d->sg[i].addr + this_size)
+			size += d->sg[i].addr + this_size - addr;
+	}
+	return size;
+}
+
+static enum dma_status omap_dma_tx_status(struct dma_chan *chan,
+	dma_cookie_t cookie, struct dma_tx_state *txstate)
+{
+	struct omap_chan *c = to_omap_dma_chan(chan);
+	struct virt_dma_desc *vd;
+	enum dma_status ret;
+	unsigned long flags;
+
+	ret = dma_cookie_status(chan, cookie, txstate);
+	if (ret == DMA_SUCCESS || !txstate)
+		return ret;
+
+	spin_lock_irqsave(&c->vc.lock, flags);
+	vd = vchan_find_desc(&c->vc, cookie);
+	if (vd) {
+		txstate->residue = omap_dma_desc_size(to_omap_dma_desc(&vd->tx));
+	} else if (c->desc && c->desc->vd.tx.cookie == cookie) {
+		struct omap_desc *d = c->desc;
+		dma_addr_t pos;
+
+		if (d->dir == DMA_MEM_TO_DEV)
+			pos = omap_get_dma_src_pos(c->dma_ch);
+		else if (d->dir == DMA_DEV_TO_MEM)
+			pos = omap_get_dma_dst_pos(c->dma_ch);
+		else
+			pos = 0;
+
+		txstate->residue = omap_dma_desc_size_pos(d, pos);
+	} else {
+		txstate->residue = 0;
+	}
+	spin_unlock_irqrestore(&c->vc.lock, flags);
+
+	return ret;
+}
+
+static void omap_dma_issue_pending(struct dma_chan *chan)
+{
+	struct omap_chan *c = to_omap_dma_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&c->vc.lock, flags);
+	if (vchan_issue_pending(&c->vc) && !c->desc) {
+		struct omap_dmadev *d = to_omap_dma_dev(chan->device);
+		spin_lock(&d->lock);
+		if (list_empty(&c->node))
+			list_add_tail(&c->node, &d->pending);
+		spin_unlock(&d->lock);
+		tasklet_schedule(&d->task);
+	}
+	spin_unlock_irqrestore(&c->vc.lock, flags);
+}
+
+static struct dma_async_tx_descriptor *omap_dma_prep_slave_sg(
+	struct dma_chan *chan, struct scatterlist *sgl, unsigned sglen,
+	enum dma_transfer_direction dir, unsigned long tx_flags, void *context)
+{
+	struct omap_chan *c = to_omap_dma_chan(chan);
+	enum dma_slave_buswidth dev_width;
+	struct scatterlist *sgent;
+	struct omap_desc *d;
+	dma_addr_t dev_addr;
+	unsigned i, j = 0, es, en, frame_bytes, sync_type;
+	u32 burst;
+
+	if (dir == DMA_DEV_TO_MEM) {
+		dev_addr = c->cfg.src_addr;
+		dev_width = c->cfg.src_addr_width;
+		burst = c->cfg.src_maxburst;
+		sync_type = OMAP_DMA_SRC_SYNC;
+	} else if (dir == DMA_MEM_TO_DEV) {
+		dev_addr = c->cfg.dst_addr;
+		dev_width = c->cfg.dst_addr_width;
+		burst = c->cfg.dst_maxburst;
+		sync_type = OMAP_DMA_DST_SYNC;
+	} else {
+		dev_err(chan->device->dev, "%s: bad direction?\n", __func__);
+		return NULL;
+	}
+
+	/* Bus width translates to the element size (ES) */
+	switch (dev_width) {
+	case DMA_SLAVE_BUSWIDTH_1_BYTE:
+		es = OMAP_DMA_DATA_TYPE_S8;
+		break;
+	case DMA_SLAVE_BUSWIDTH_2_BYTES:
+		es = OMAP_DMA_DATA_TYPE_S16;
+		break;
+	case DMA_SLAVE_BUSWIDTH_4_BYTES:
+		es = OMAP_DMA_DATA_TYPE_S32;
+		break;
+	default: /* not reached */
+		return NULL;
+	}
+
+	/* Now allocate and setup the descriptor. */
+	d = kzalloc(sizeof(*d) + sglen * sizeof(d->sg[0]), GFP_ATOMIC);
+	if (!d)
+		return NULL;
+
+	d->dir = dir;
+	d->dev_addr = dev_addr;
+	d->es = es;
+	d->sync_mode = OMAP_DMA_SYNC_FRAME;
+	d->sync_type = sync_type;
+	d->periph_port = OMAP_DMA_PORT_TIPB;
+
+	/*
+	 * Build our scatterlist entries: each contains the address,
+	 * the number of elements (EN) in each frame, and the number of
+	 * frames (FN).  Number of bytes for this entry = ES * EN * FN.
+	 *
+	 * Burst size translates to number of elements with frame sync.
+	 * Note: DMA engine defines burst to be the number of dev-width
+	 * transfers.
+	 */
+	en = burst;
+	frame_bytes = es_bytes[es] * en;
+	for_each_sg(sgl, sgent, sglen, i) {
+		d->sg[j].addr = sg_dma_address(sgent);
+		d->sg[j].en = en;
+		d->sg[j].fn = sg_dma_len(sgent) / frame_bytes;
+		j++;
+	}
+
+	d->sglen = j;
+
+	return vchan_tx_prep(&c->vc, &d->vd, tx_flags);
+}
+
+static struct dma_async_tx_descriptor *omap_dma_prep_dma_cyclic(
+	struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
+	size_t period_len, enum dma_transfer_direction dir, void *context)
+{
+	struct omap_chan *c = to_omap_dma_chan(chan);
+	enum dma_slave_buswidth dev_width;
+	struct omap_desc *d;
+	dma_addr_t dev_addr;
+	unsigned es, sync_type;
+	u32 burst;
+
+	if (dir == DMA_DEV_TO_MEM) {
+		dev_addr = c->cfg.src_addr;
+		dev_width = c->cfg.src_addr_width;
+		burst = c->cfg.src_maxburst;
+		sync_type = OMAP_DMA_SRC_SYNC;
+	} else if (dir == DMA_MEM_TO_DEV) {
+		dev_addr = c->cfg.dst_addr;
+		dev_width = c->cfg.dst_addr_width;
+		burst = c->cfg.dst_maxburst;
+		sync_type = OMAP_DMA_DST_SYNC;
+	} else {
+		dev_err(chan->device->dev, "%s: bad direction?\n", __func__);
+		return NULL;
+	}
+
+	/* Bus width translates to the element size (ES) */
+	switch (dev_width) {
+	case DMA_SLAVE_BUSWIDTH_1_BYTE:
+		es = OMAP_DMA_DATA_TYPE_S8;
+		break;
+	case DMA_SLAVE_BUSWIDTH_2_BYTES:
+		es = OMAP_DMA_DATA_TYPE_S16;
+		break;
+	case DMA_SLAVE_BUSWIDTH_4_BYTES:
+		es = OMAP_DMA_DATA_TYPE_S32;
+		break;
+	default: /* not reached */
+		return NULL;
+	}
+
+	/* Now allocate and setup the descriptor. */
+	d = kzalloc(sizeof(*d) + sizeof(d->sg[0]), GFP_ATOMIC);
+	if (!d)
+		return NULL;
+
+	d->dir = dir;
+	d->dev_addr = dev_addr;
+	d->fi = burst;
+	d->es = es;
+	d->sync_mode = OMAP_DMA_SYNC_PACKET;
+	d->sync_type = sync_type;
+	d->periph_port = OMAP_DMA_PORT_MPUI;
+	d->sg[0].addr = buf_addr;
+	d->sg[0].en = period_len / es_bytes[es];
+	d->sg[0].fn = buf_len / period_len;
+	d->sglen = 1;
+
+	if (!c->cyclic) {
+		c->cyclic = true;
+		omap_dma_link_lch(c->dma_ch, c->dma_ch);
+		omap_enable_dma_irq(c->dma_ch, OMAP_DMA_FRAME_IRQ);
+		omap_disable_dma_irq(c->dma_ch, OMAP_DMA_BLOCK_IRQ);
+	}
+
+	if (!cpu_class_is_omap1()) {
+		omap_set_dma_src_burst_mode(c->dma_ch, OMAP_DMA_DATA_BURST_16);
+		omap_set_dma_dest_burst_mode(c->dma_ch, OMAP_DMA_DATA_BURST_16);
+	}
+
+	return vchan_tx_prep(&c->vc, &d->vd, DMA_CTRL_ACK | DMA_PREP_INTERRUPT);
+}
+
+static int omap_dma_slave_config(struct omap_chan *c, struct dma_slave_config *cfg)
+{
+	if (cfg->src_addr_width == DMA_SLAVE_BUSWIDTH_8_BYTES ||
+	    cfg->dst_addr_width == DMA_SLAVE_BUSWIDTH_8_BYTES)
+		return -EINVAL;
+
+	memcpy(&c->cfg, cfg, sizeof(c->cfg));
+
+	return 0;
+}
+
+static int omap_dma_terminate_all(struct omap_chan *c)
+{
+	struct omap_dmadev *d = to_omap_dma_dev(c->vc.chan.device);
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	spin_lock_irqsave(&c->vc.lock, flags);
+
+	/* Prevent this channel being scheduled */
+	spin_lock(&d->lock);
+	list_del_init(&c->node);
+	spin_unlock(&d->lock);
+
+	/*
+	 * Stop DMA activity: we assume the callback will not be called
+	 * after omap_stop_dma() returns (even if it does, it will see
+	 * c->desc is NULL and exit.)
+	 */
+	if (c->desc) {
+		c->desc = NULL;
+		omap_stop_dma(c->dma_ch);
+	}
+
+	if (c->cyclic) {
+		c->cyclic = false;
+		omap_dma_unlink_lch(c->dma_ch, c->dma_ch);
+	}
+
+	vchan_get_all_descriptors(&c->vc, &head);
+	spin_unlock_irqrestore(&c->vc.lock, flags);
+	vchan_dma_desc_free_list(&c->vc, &head);
+
+	return 0;
+}
+
+static int omap_dma_pause(struct omap_chan *c)
+{
+	/* FIXME: not supported by platform private API */
+	return -EINVAL;
+}
+
+static int omap_dma_resume(struct omap_chan *c)
+{
+	/* FIXME: not supported by platform private API */
+	return -EINVAL;
+}
+
+static int omap_dma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
+	unsigned long arg)
+{
+	struct omap_chan *c = to_omap_dma_chan(chan);
+	int ret;
+
+	switch (cmd) {
+	case DMA_SLAVE_CONFIG:
+		ret = omap_dma_slave_config(c, (struct dma_slave_config *)arg);
+		break;
+
+	case DMA_TERMINATE_ALL:
+		ret = omap_dma_terminate_all(c);
+		break;
+
+	case DMA_PAUSE:
+		ret = omap_dma_pause(c);
+		break;
+
+	case DMA_RESUME:
+		ret = omap_dma_resume(c);
+		break;
+
+	default:
+		ret = -ENXIO;
+		break;
+	}
+
+	return ret;
+}
+
+static int omap_dma_chan_init(struct omap_dmadev *od, int dma_sig)
+{
+	struct omap_chan *c;
+
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return -ENOMEM;
+
+	c->dma_sig = dma_sig;
+	c->vc.desc_free = omap_dma_desc_free;
+	vchan_init(&c->vc, &od->ddev);
+	INIT_LIST_HEAD(&c->node);
+
+	od->ddev.chancnt++;
+
+	return 0;
+}
+
+static void omap_dma_free(struct omap_dmadev *od)
+{
+	tasklet_kill(&od->task);
+	while (!list_empty(&od->ddev.channels)) {
+		struct omap_chan *c = list_first_entry(&od->ddev.channels,
+			struct omap_chan, vc.chan.device_node);
+
+		list_del(&c->vc.chan.device_node);
+		tasklet_kill(&c->vc.task);
+		kfree(c);
+	}
+	kfree(od);
+}
+
+static int omap_dma_probe(struct platform_device *pdev)
+{
+	struct omap_dmadev *od;
+	int rc, i;
+
+	od = kzalloc(sizeof(*od), GFP_KERNEL);
+	if (!od)
+		return -ENOMEM;
+
+	dma_cap_set(DMA_SLAVE, od->ddev.cap_mask);
+	dma_cap_set(DMA_CYCLIC, od->ddev.cap_mask);
+	od->ddev.device_alloc_chan_resources = omap_dma_alloc_chan_resources;
+	od->ddev.device_free_chan_resources = omap_dma_free_chan_resources;
+	od->ddev.device_tx_status = omap_dma_tx_status;
+	od->ddev.device_issue_pending = omap_dma_issue_pending;
+	od->ddev.device_prep_slave_sg = omap_dma_prep_slave_sg;
+	od->ddev.device_prep_dma_cyclic = omap_dma_prep_dma_cyclic;
+	od->ddev.device_control = omap_dma_control;
+	od->ddev.dev = &pdev->dev;
+	INIT_LIST_HEAD(&od->ddev.channels);
+	INIT_LIST_HEAD(&od->pending);
+	spin_lock_init(&od->lock);
+
+	tasklet_init(&od->task, omap_dma_sched, (unsigned long)od);
+
+	for (i = 0; i < 127; i++) {
+		rc = omap_dma_chan_init(od, i);
+		if (rc) {
+			omap_dma_free(od);
+			return rc;
+		}
+	}
+
+	rc = dma_async_device_register(&od->ddev);
+	if (rc) {
+		pr_warn("OMAP-DMA: failed to register slave DMA engine device: %d\n",
+			rc);
+		omap_dma_free(od);
+	} else {
+		platform_set_drvdata(pdev, od);
+	}
+
+	dev_info(&pdev->dev, "OMAP DMA engine driver\n");
+
+	return rc;
+}
+
+static int omap_dma_remove(struct platform_device *pdev)
+{
+	struct omap_dmadev *od = platform_get_drvdata(pdev);
+
+	dma_async_device_unregister(&od->ddev);
+	omap_dma_free(od);
+
+	return 0;
+}
+
+static struct platform_driver omap_dma_driver = {
+	.probe	= omap_dma_probe,
+	.remove	= omap_dma_remove,
+	.driver = {
+		.name = "omap-dma-engine",
+		.owner = THIS_MODULE,
+	},
+};
+
+bool omap_dma_filter_fn(struct dma_chan *chan, void *param)
+{
+	if (chan->device->dev->driver == &omap_dma_driver.driver) {
+		struct omap_chan *c = to_omap_dma_chan(chan);
+		unsigned req = *(unsigned *)param;
+
+		return req == c->dma_sig;
+	}
+	return false;
+}
+EXPORT_SYMBOL_GPL(omap_dma_filter_fn);
+
+static struct platform_device *pdev;
+
+static const struct platform_device_info omap_dma_dev_info = {
+	.name = "omap-dma-engine",
+	.id = -1,
+	.dma_mask = DMA_BIT_MASK(32),
+};
+
+static int omap_dma_init(void)
+{
+	int rc = platform_driver_register(&omap_dma_driver);
+
+	if (rc == 0) {
+		pdev = platform_device_register_full(&omap_dma_dev_info);
+		if (IS_ERR(pdev)) {
+			platform_driver_unregister(&omap_dma_driver);
+			rc = PTR_ERR(pdev);
+		}
+	}
+	return rc;
+}
+subsys_initcall(omap_dma_init);
+
+static void __exit omap_dma_exit(void)
+{
+	platform_device_unregister(pdev);
+	platform_driver_unregister(&omap_dma_driver);
+}
+module_exit(omap_dma_exit);
+
+MODULE_AUTHOR("Russell King");
+MODULE_LICENSE("GPL");
diff --git a/drivers/mmc/host/omap.c b/drivers/mmc/host/omap.c
index 3e8dcf8..50e08f0 100644
--- a/drivers/mmc/host/omap.c
+++ b/drivers/mmc/host/omap.c
@@ -17,10 +17,12 @@
 #include <linux/ioport.h>
 #include <linux/platform_device.h>
 #include <linux/interrupt.h>
+#include <linux/dmaengine.h>
 #include <linux/dma-mapping.h>
 #include <linux/delay.h>
 #include <linux/spinlock.h>
 #include <linux/timer.h>
+#include <linux/omap-dma.h>
 #include <linux/mmc/host.h>
 #include <linux/mmc/card.h>
 #include <linux/clk.h>
@@ -128,6 +130,10 @@
 	unsigned char		id; /* 16xx chips have 2 MMC blocks */
 	struct clk *		iclk;
 	struct clk *		fclk;
+	struct dma_chan		*dma_rx;
+	u32			dma_rx_burst;
+	struct dma_chan		*dma_tx;
+	u32			dma_tx_burst;
 	struct resource		*mem_res;
 	void __iomem		*virt_base;
 	unsigned int		phys_base;
@@ -153,12 +159,8 @@
 
 	unsigned		use_dma:1;
 	unsigned		brs_received:1, dma_done:1;
-	unsigned		dma_is_read:1;
 	unsigned		dma_in_use:1;
-	int			dma_ch;
 	spinlock_t		dma_lock;
-	struct timer_list	dma_timer;
-	unsigned		dma_len;
 
 	struct mmc_omap_slot    *slots[OMAP_MMC_MAX_SLOTS];
 	struct mmc_omap_slot    *current_slot;
@@ -406,18 +408,25 @@
 		     int abort)
 {
 	enum dma_data_direction dma_data_dir;
+	struct device *dev = mmc_dev(host->mmc);
+	struct dma_chan *c;
 
-	BUG_ON(host->dma_ch < 0);
-	if (data->error)
-		omap_stop_dma(host->dma_ch);
-	/* Release DMA channel lazily */
-	mod_timer(&host->dma_timer, jiffies + HZ);
-	if (data->flags & MMC_DATA_WRITE)
+	if (data->flags & MMC_DATA_WRITE) {
 		dma_data_dir = DMA_TO_DEVICE;
-	else
+		c = host->dma_tx;
+	} else {
 		dma_data_dir = DMA_FROM_DEVICE;
-	dma_unmap_sg(mmc_dev(host->mmc), data->sg, host->sg_len,
-		     dma_data_dir);
+		c = host->dma_rx;
+	}
+	if (c) {
+		if (data->error) {
+			dmaengine_terminate_all(c);
+			/* Claim nothing transferred on error... */
+			data->bytes_xfered = 0;
+		}
+		dev = c->device->dev;
+	}
+	dma_unmap_sg(dev, data->sg, host->sg_len, dma_data_dir);
 }
 
 static void mmc_omap_send_stop_work(struct work_struct *work)
@@ -525,16 +534,6 @@
 }
 
 static void
-mmc_omap_dma_timer(unsigned long data)
-{
-	struct mmc_omap_host *host = (struct mmc_omap_host *) data;
-
-	BUG_ON(host->dma_ch < 0);
-	omap_free_dma(host->dma_ch);
-	host->dma_ch = -1;
-}
-
-static void
 mmc_omap_dma_done(struct mmc_omap_host *host, struct mmc_data *data)
 {
 	unsigned long flags;
@@ -891,159 +890,15 @@
 		  jiffies + msecs_to_jiffies(OMAP_MMC_COVER_POLL_DELAY));
 }
 
-/* Prepare to transfer the next segment of a scatterlist */
-static void
-mmc_omap_prepare_dma(struct mmc_omap_host *host, struct mmc_data *data)
+static void mmc_omap_dma_callback(void *priv)
 {
-	int dma_ch = host->dma_ch;
-	unsigned long data_addr;
-	u16 buf, frame;
-	u32 count;
-	struct scatterlist *sg = &data->sg[host->sg_idx];
-	int src_port = 0;
-	int dst_port = 0;
-	int sync_dev = 0;
+	struct mmc_omap_host *host = priv;
+	struct mmc_data *data = host->data;
 
-	data_addr = host->phys_base + OMAP_MMC_REG(host, DATA);
-	frame = data->blksz;
-	count = sg_dma_len(sg);
+	/* If we got to the end of DMA, assume everything went well */
+	data->bytes_xfered += data->blocks * data->blksz;
 
-	if ((data->blocks == 1) && (count > data->blksz))
-		count = frame;
-
-	host->dma_len = count;
-
-	/* FIFO is 16x2 bytes on 15xx, and 32x2 bytes on 16xx and 24xx.
-	 * Use 16 or 32 word frames when the blocksize is at least that large.
-	 * Blocksize is usually 512 bytes; but not for some SD reads.
-	 */
-	if (cpu_is_omap15xx() && frame > 32)
-		frame = 32;
-	else if (frame > 64)
-		frame = 64;
-	count /= frame;
-	frame >>= 1;
-
-	if (!(data->flags & MMC_DATA_WRITE)) {
-		buf = 0x800f | ((frame - 1) << 8);
-
-		if (cpu_class_is_omap1()) {
-			src_port = OMAP_DMA_PORT_TIPB;
-			dst_port = OMAP_DMA_PORT_EMIFF;
-		}
-		if (cpu_is_omap24xx())
-			sync_dev = OMAP24XX_DMA_MMC1_RX;
-
-		omap_set_dma_src_params(dma_ch, src_port,
-					OMAP_DMA_AMODE_CONSTANT,
-					data_addr, 0, 0);
-		omap_set_dma_dest_params(dma_ch, dst_port,
-					 OMAP_DMA_AMODE_POST_INC,
-					 sg_dma_address(sg), 0, 0);
-		omap_set_dma_dest_data_pack(dma_ch, 1);
-		omap_set_dma_dest_burst_mode(dma_ch, OMAP_DMA_DATA_BURST_4);
-	} else {
-		buf = 0x0f80 | ((frame - 1) << 0);
-
-		if (cpu_class_is_omap1()) {
-			src_port = OMAP_DMA_PORT_EMIFF;
-			dst_port = OMAP_DMA_PORT_TIPB;
-		}
-		if (cpu_is_omap24xx())
-			sync_dev = OMAP24XX_DMA_MMC1_TX;
-
-		omap_set_dma_dest_params(dma_ch, dst_port,
-					 OMAP_DMA_AMODE_CONSTANT,
-					 data_addr, 0, 0);
-		omap_set_dma_src_params(dma_ch, src_port,
-					OMAP_DMA_AMODE_POST_INC,
-					sg_dma_address(sg), 0, 0);
-		omap_set_dma_src_data_pack(dma_ch, 1);
-		omap_set_dma_src_burst_mode(dma_ch, OMAP_DMA_DATA_BURST_4);
-	}
-
-	/* Max limit for DMA frame count is 0xffff */
-	BUG_ON(count > 0xffff);
-
-	OMAP_MMC_WRITE(host, BUF, buf);
-	omap_set_dma_transfer_params(dma_ch, OMAP_DMA_DATA_TYPE_S16,
-				     frame, count, OMAP_DMA_SYNC_FRAME,
-				     sync_dev, 0);
-}
-
-/* A scatterlist segment completed */
-static void mmc_omap_dma_cb(int lch, u16 ch_status, void *data)
-{
-	struct mmc_omap_host *host = (struct mmc_omap_host *) data;
-	struct mmc_data *mmcdat = host->data;
-
-	if (unlikely(host->dma_ch < 0)) {
-		dev_err(mmc_dev(host->mmc),
-			"DMA callback while DMA not enabled\n");
-		return;
-	}
-	/* FIXME: We really should do something to _handle_ the errors */
-	if (ch_status & OMAP1_DMA_TOUT_IRQ) {
-		dev_err(mmc_dev(host->mmc),"DMA timeout\n");
-		return;
-	}
-	if (ch_status & OMAP_DMA_DROP_IRQ) {
-		dev_err(mmc_dev(host->mmc), "DMA sync error\n");
-		return;
-	}
-	if (!(ch_status & OMAP_DMA_BLOCK_IRQ)) {
-		return;
-	}
-	mmcdat->bytes_xfered += host->dma_len;
-	host->sg_idx++;
-	if (host->sg_idx < host->sg_len) {
-		mmc_omap_prepare_dma(host, host->data);
-		omap_start_dma(host->dma_ch);
-	} else
-		mmc_omap_dma_done(host, host->data);
-}
-
-static int mmc_omap_get_dma_channel(struct mmc_omap_host *host, struct mmc_data *data)
-{
-	const char *dma_dev_name;
-	int sync_dev, dma_ch, is_read, r;
-
-	is_read = !(data->flags & MMC_DATA_WRITE);
-	del_timer_sync(&host->dma_timer);
-	if (host->dma_ch >= 0) {
-		if (is_read == host->dma_is_read)
-			return 0;
-		omap_free_dma(host->dma_ch);
-		host->dma_ch = -1;
-	}
-
-	if (is_read) {
-		if (host->id == 0) {
-			sync_dev = OMAP_DMA_MMC_RX;
-			dma_dev_name = "MMC1 read";
-		} else {
-			sync_dev = OMAP_DMA_MMC2_RX;
-			dma_dev_name = "MMC2 read";
-		}
-	} else {
-		if (host->id == 0) {
-			sync_dev = OMAP_DMA_MMC_TX;
-			dma_dev_name = "MMC1 write";
-		} else {
-			sync_dev = OMAP_DMA_MMC2_TX;
-			dma_dev_name = "MMC2 write";
-		}
-	}
-	r = omap_request_dma(sync_dev, dma_dev_name, mmc_omap_dma_cb,
-			     host, &dma_ch);
-	if (r != 0) {
-		dev_dbg(mmc_dev(host->mmc), "omap_request_dma() failed with %d\n", r);
-		return r;
-	}
-	host->dma_ch = dma_ch;
-	host->dma_is_read = is_read;
-
-	return 0;
+	mmc_omap_dma_done(host, data);
 }
 
 static inline void set_cmd_timeout(struct mmc_omap_host *host, struct mmc_request *req)
@@ -1118,33 +973,85 @@
 
 	host->sg_idx = 0;
 	if (use_dma) {
-		if (mmc_omap_get_dma_channel(host, data) == 0) {
-			enum dma_data_direction dma_data_dir;
+		enum dma_data_direction dma_data_dir;
+		struct dma_async_tx_descriptor *tx;
+		struct dma_chan *c;
+		u32 burst, *bp;
+		u16 buf;
 
-			if (data->flags & MMC_DATA_WRITE)
-				dma_data_dir = DMA_TO_DEVICE;
-			else
-				dma_data_dir = DMA_FROM_DEVICE;
+		/*
+		 * FIFO is 16x2 bytes on 15xx, and 32x2 bytes on 16xx
+		 * and 24xx. Use 16 or 32 word frames when the
+		 * blocksize is at least that large. Blocksize is
+		 * usually 512 bytes; but not for some SD reads.
+		 */
+		burst = cpu_is_omap15xx() ? 32 : 64;
+		if (burst > data->blksz)
+			burst = data->blksz;
 
-			host->sg_len = dma_map_sg(mmc_dev(host->mmc), data->sg,
-						sg_len, dma_data_dir);
-			host->total_bytes_left = 0;
-			mmc_omap_prepare_dma(host, req->data);
-			host->brs_received = 0;
-			host->dma_done = 0;
-			host->dma_in_use = 1;
-		} else
-			use_dma = 0;
+		burst >>= 1;
+
+		if (data->flags & MMC_DATA_WRITE) {
+			c = host->dma_tx;
+			bp = &host->dma_tx_burst;
+			buf = 0x0f80 | (burst - 1) << 0;
+			dma_data_dir = DMA_TO_DEVICE;
+		} else {
+			c = host->dma_rx;
+			bp = &host->dma_rx_burst;
+			buf = 0x800f | (burst - 1) << 8;
+			dma_data_dir = DMA_FROM_DEVICE;
+		}
+
+		if (!c)
+			goto use_pio;
+
+		/* Only reconfigure if we have a different burst size */
+		if (*bp != burst) {
+			struct dma_slave_config cfg;
+
+			cfg.src_addr = host->phys_base + OMAP_MMC_REG(host, DATA);
+			cfg.dst_addr = host->phys_base + OMAP_MMC_REG(host, DATA);
+			cfg.src_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
+			cfg.dst_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
+			cfg.src_maxburst = burst;
+			cfg.dst_maxburst = burst;
+
+			if (dmaengine_slave_config(c, &cfg))
+				goto use_pio;
+
+			*bp = burst;
+		}
+
+		host->sg_len = dma_map_sg(c->device->dev, data->sg, sg_len,
+					  dma_data_dir);
+		if (host->sg_len == 0)
+			goto use_pio;
+
+		tx = dmaengine_prep_slave_sg(c, data->sg, host->sg_len,
+			data->flags & MMC_DATA_WRITE ? DMA_MEM_TO_DEV : DMA_DEV_TO_MEM,
+			DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+		if (!tx)
+			goto use_pio;
+
+		OMAP_MMC_WRITE(host, BUF, buf);
+
+		tx->callback = mmc_omap_dma_callback;
+		tx->callback_param = host;
+		dmaengine_submit(tx);
+		host->brs_received = 0;
+		host->dma_done = 0;
+		host->dma_in_use = 1;
+		return;
 	}
+ use_pio:
 
 	/* Revert to PIO? */
-	if (!use_dma) {
-		OMAP_MMC_WRITE(host, BUF, 0x1f1f);
-		host->total_bytes_left = data->blocks * block_size;
-		host->sg_len = sg_len;
-		mmc_omap_sg_to_buf(host);
-		host->dma_in_use = 0;
-	}
+	OMAP_MMC_WRITE(host, BUF, 0x1f1f);
+	host->total_bytes_left = data->blocks * block_size;
+	host->sg_len = sg_len;
+	mmc_omap_sg_to_buf(host);
+	host->dma_in_use = 0;
 }
 
 static void mmc_omap_start_request(struct mmc_omap_host *host,
@@ -1157,8 +1064,12 @@
 	/* only touch fifo AFTER the controller readies it */
 	mmc_omap_prepare_data(host, req);
 	mmc_omap_start_command(host, req->cmd);
-	if (host->dma_in_use)
-		omap_start_dma(host->dma_ch);
+	if (host->dma_in_use) {
+		struct dma_chan *c = host->data->flags & MMC_DATA_WRITE ?
+				host->dma_tx : host->dma_rx;
+
+		dma_async_issue_pending(c);
+	}
 }
 
 static void mmc_omap_request(struct mmc_host *mmc, struct mmc_request *req)
@@ -1400,6 +1311,8 @@
 	struct omap_mmc_platform_data *pdata = pdev->dev.platform_data;
 	struct mmc_omap_host *host = NULL;
 	struct resource *res;
+	dma_cap_mask_t mask;
+	unsigned sig;
 	int i, ret = 0;
 	int irq;
 
@@ -1439,7 +1352,6 @@
 	setup_timer(&host->clk_timer, mmc_omap_clk_timer, (unsigned long) host);
 
 	spin_lock_init(&host->dma_lock);
-	setup_timer(&host->dma_timer, mmc_omap_dma_timer, (unsigned long) host);
 	spin_lock_init(&host->slot_lock);
 	init_waitqueue_head(&host->slot_wq);
 
@@ -1450,11 +1362,7 @@
 	host->id = pdev->id;
 	host->mem_res = res;
 	host->irq = irq;
-
 	host->use_dma = 1;
-	host->dev->dma_mask = &pdata->dma_mask;
-	host->dma_ch = -1;
-
 	host->irq = irq;
 	host->phys_base = host->mem_res->start;
 	host->virt_base = ioremap(res->start, resource_size(res));
@@ -1474,9 +1382,48 @@
 		goto err_free_iclk;
 	}
 
+	dma_cap_zero(mask);
+	dma_cap_set(DMA_SLAVE, mask);
+
+	host->dma_tx_burst = -1;
+	host->dma_rx_burst = -1;
+
+	if (cpu_is_omap24xx())
+		sig = host->id == 0 ? OMAP24XX_DMA_MMC1_TX : OMAP24XX_DMA_MMC2_TX;
+	else
+		sig = host->id == 0 ? OMAP_DMA_MMC_TX : OMAP_DMA_MMC2_TX;
+	host->dma_tx = dma_request_channel(mask, omap_dma_filter_fn, &sig);
+#if 0
+	if (!host->dma_tx) {
+		dev_err(host->dev, "unable to obtain TX DMA engine channel %u\n",
+			sig);
+		goto err_dma;
+	}
+#else
+	if (!host->dma_tx)
+		dev_warn(host->dev, "unable to obtain TX DMA engine channel %u\n",
+			sig);
+#endif
+	if (cpu_is_omap24xx())
+		sig = host->id == 0 ? OMAP24XX_DMA_MMC1_RX : OMAP24XX_DMA_MMC2_RX;
+	else
+		sig = host->id == 0 ? OMAP_DMA_MMC_RX : OMAP_DMA_MMC2_RX;
+	host->dma_rx = dma_request_channel(mask, omap_dma_filter_fn, &sig);
+#if 0
+	if (!host->dma_rx) {
+		dev_err(host->dev, "unable to obtain RX DMA engine channel %u\n",
+			sig);
+		goto err_dma;
+	}
+#else
+	if (!host->dma_rx)
+		dev_warn(host->dev, "unable to obtain RX DMA engine channel %u\n",
+			sig);
+#endif
+
 	ret = request_irq(host->irq, mmc_omap_irq, 0, DRIVER_NAME, host);
 	if (ret)
-		goto err_free_fclk;
+		goto err_free_dma;
 
 	if (pdata->init != NULL) {
 		ret = pdata->init(&pdev->dev);
@@ -1510,7 +1457,11 @@
 		pdata->cleanup(&pdev->dev);
 err_free_irq:
 	free_irq(host->irq, host);
-err_free_fclk:
+err_free_dma:
+	if (host->dma_tx)
+		dma_release_channel(host->dma_tx);
+	if (host->dma_rx)
+		dma_release_channel(host->dma_rx);
 	clk_put(host->fclk);
 err_free_iclk:
 	clk_disable(host->iclk);
@@ -1545,6 +1496,11 @@
 	clk_disable(host->iclk);
 	clk_put(host->iclk);
 
+	if (host->dma_tx)
+		dma_release_channel(host->dma_tx);
+	if (host->dma_rx)
+		dma_release_channel(host->dma_rx);
+
 	iounmap(host->virt_base);
 	release_mem_region(pdev->resource[0].start,
 			   pdev->resource[0].end - pdev->resource[0].start + 1);
diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c
index 389a3ee..823d21c 100644
--- a/drivers/mmc/host/omap_hsmmc.c
+++ b/drivers/mmc/host/omap_hsmmc.c
@@ -19,6 +19,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/debugfs.h>
+#include <linux/dmaengine.h>
 #include <linux/seq_file.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
@@ -29,6 +30,7 @@
 #include <linux/of.h>
 #include <linux/of_gpio.h>
 #include <linux/of_device.h>
+#include <linux/omap-dma.h>
 #include <linux/mmc/host.h>
 #include <linux/mmc/core.h>
 #include <linux/mmc/mmc.h>
@@ -37,7 +39,6 @@
 #include <linux/gpio.h>
 #include <linux/regulator/consumer.h>
 #include <linux/pm_runtime.h>
-#include <plat/dma.h>
 #include <mach/hardware.h>
 #include <plat/board.h>
 #include <plat/mmc.h>
@@ -166,7 +167,8 @@
 	int			suspended;
 	int			irq;
 	int			use_dma, dma_ch;
-	int			dma_line_tx, dma_line_rx;
+	struct dma_chan		*tx_chan;
+	struct dma_chan		*rx_chan;
 	int			slot_id;
 	int			response_busy;
 	int			context_loss;
@@ -797,6 +799,12 @@
 		return DMA_FROM_DEVICE;
 }
 
+static struct dma_chan *omap_hsmmc_get_dma_chan(struct omap_hsmmc_host *host,
+	struct mmc_data *data)
+{
+	return data->flags & MMC_DATA_WRITE ? host->tx_chan : host->rx_chan;
+}
+
 static void omap_hsmmc_request_done(struct omap_hsmmc_host *host, struct mmc_request *mrq)
 {
 	int dma_ch;
@@ -889,10 +897,13 @@
 	spin_unlock_irqrestore(&host->irq_lock, flags);
 
 	if (host->use_dma && dma_ch != -1) {
-		dma_unmap_sg(mmc_dev(host->mmc), host->data->sg,
-			host->data->sg_len,
+		struct dma_chan *chan = omap_hsmmc_get_dma_chan(host, host->data);
+
+		dmaengine_terminate_all(chan);
+		dma_unmap_sg(chan->device->dev,
+			host->data->sg, host->data->sg_len,
 			omap_hsmmc_get_dma_dir(host, host->data));
-		omap_free_dma(dma_ch);
+
 		host->data->host_cookie = 0;
 	}
 	host->data = NULL;
@@ -1190,90 +1201,29 @@
 	return IRQ_HANDLED;
 }
 
-static int omap_hsmmc_get_dma_sync_dev(struct omap_hsmmc_host *host,
-				     struct mmc_data *data)
+static void omap_hsmmc_dma_callback(void *param)
 {
-	int sync_dev;
-
-	if (data->flags & MMC_DATA_WRITE)
-		sync_dev = host->dma_line_tx;
-	else
-		sync_dev = host->dma_line_rx;
-	return sync_dev;
-}
-
-static void omap_hsmmc_config_dma_params(struct omap_hsmmc_host *host,
-				       struct mmc_data *data,
-				       struct scatterlist *sgl)
-{
-	int blksz, nblk, dma_ch;
-
-	dma_ch = host->dma_ch;
-	if (data->flags & MMC_DATA_WRITE) {
-		omap_set_dma_dest_params(dma_ch, 0, OMAP_DMA_AMODE_CONSTANT,
-			(host->mapbase + OMAP_HSMMC_DATA), 0, 0);
-		omap_set_dma_src_params(dma_ch, 0, OMAP_DMA_AMODE_POST_INC,
-			sg_dma_address(sgl), 0, 0);
-	} else {
-		omap_set_dma_src_params(dma_ch, 0, OMAP_DMA_AMODE_CONSTANT,
-			(host->mapbase + OMAP_HSMMC_DATA), 0, 0);
-		omap_set_dma_dest_params(dma_ch, 0, OMAP_DMA_AMODE_POST_INC,
-			sg_dma_address(sgl), 0, 0);
-	}
-
-	blksz = host->data->blksz;
-	nblk = sg_dma_len(sgl) / blksz;
-
-	omap_set_dma_transfer_params(dma_ch, OMAP_DMA_DATA_TYPE_S32,
-			blksz / 4, nblk, OMAP_DMA_SYNC_FRAME,
-			omap_hsmmc_get_dma_sync_dev(host, data),
-			!(data->flags & MMC_DATA_WRITE));
-
-	omap_start_dma(dma_ch);
-}
-
-/*
- * DMA call back function
- */
-static void omap_hsmmc_dma_cb(int lch, u16 ch_status, void *cb_data)
-{
-	struct omap_hsmmc_host *host = cb_data;
+	struct omap_hsmmc_host *host = param;
+	struct dma_chan *chan;
 	struct mmc_data *data;
-	int dma_ch, req_in_progress;
-	unsigned long flags;
+	int req_in_progress;
 
-	if (!(ch_status & OMAP_DMA_BLOCK_IRQ)) {
-		dev_warn(mmc_dev(host->mmc), "unexpected dma status %x\n",
-			ch_status);
-		return;
-	}
-
-	spin_lock_irqsave(&host->irq_lock, flags);
+	spin_lock_irq(&host->irq_lock);
 	if (host->dma_ch < 0) {
-		spin_unlock_irqrestore(&host->irq_lock, flags);
+		spin_unlock_irq(&host->irq_lock);
 		return;
 	}
 
 	data = host->mrq->data;
-	host->dma_sg_idx++;
-	if (host->dma_sg_idx < host->dma_len) {
-		/* Fire up the next transfer. */
-		omap_hsmmc_config_dma_params(host, data,
-					   data->sg + host->dma_sg_idx);
-		spin_unlock_irqrestore(&host->irq_lock, flags);
-		return;
-	}
-
+	chan = omap_hsmmc_get_dma_chan(host, data);
 	if (!data->host_cookie)
-		dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len,
+		dma_unmap_sg(chan->device->dev,
+			     data->sg, data->sg_len,
 			     omap_hsmmc_get_dma_dir(host, data));
 
 	req_in_progress = host->req_in_progress;
-	dma_ch = host->dma_ch;
 	host->dma_ch = -1;
-	spin_unlock_irqrestore(&host->irq_lock, flags);
-
-	omap_free_dma(dma_ch);
+	spin_unlock_irq(&host->irq_lock);
 
 	/* If DMA has finished after TC, complete the request */
 	if (!req_in_progress) {
@@ -1286,7 +1236,8 @@
 
 static int omap_hsmmc_pre_dma_transfer(struct omap_hsmmc_host *host,
 				       struct mmc_data *data,
-				       struct omap_hsmmc_next *next)
+				       struct omap_hsmmc_next *next,
+				       struct dma_chan *chan)
 {
 	int dma_len;
 
@@ -1301,8 +1252,7 @@
 	/* Check if next job is already prepared */
 	if (next ||
 	    (!next && data->host_cookie != host->next_data.cookie)) {
-		dma_len = dma_map_sg(mmc_dev(host->mmc), data->sg,
-				     data->sg_len,
+		dma_len = dma_map_sg(chan->device->dev, data->sg, data->sg_len,
 				     omap_hsmmc_get_dma_dir(host, data));
 
 	} else {
@@ -1329,8 +1279,11 @@
 static int omap_hsmmc_start_dma_transfer(struct omap_hsmmc_host *host,
 					struct mmc_request *req)
 {
-	int dma_ch = 0, ret = 0, i;
+	struct dma_slave_config cfg;
+	struct dma_async_tx_descriptor *tx;
+	int ret = 0, i;
 	struct mmc_data *data = req->data;
+	struct dma_chan *chan;
 
 	/* Sanity check: all the SG entries must be aligned by block size. */
 	for (i = 0; i < data->sg_len; i++) {
@@ -1348,22 +1301,41 @@
 
 	BUG_ON(host->dma_ch != -1);
 
-	ret = omap_request_dma(omap_hsmmc_get_dma_sync_dev(host, data),
-			       "MMC/SD", omap_hsmmc_dma_cb, host, &dma_ch);
-	if (ret != 0) {
-		dev_err(mmc_dev(host->mmc),
-			"%s: omap_request_dma() failed with %d\n",
-			mmc_hostname(host->mmc), ret);
-		return ret;
-	}
-	ret = omap_hsmmc_pre_dma_transfer(host, data, NULL);
+	chan = omap_hsmmc_get_dma_chan(host, data);
+
+	cfg.src_addr = host->mapbase + OMAP_HSMMC_DATA;
+	cfg.dst_addr = host->mapbase + OMAP_HSMMC_DATA;
+	cfg.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+	cfg.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+	cfg.src_maxburst = data->blksz / 4;
+	cfg.dst_maxburst = data->blksz / 4;
+
+	ret = dmaengine_slave_config(chan, &cfg);
 	if (ret)
 		return ret;
 
-	host->dma_ch = dma_ch;
-	host->dma_sg_idx = 0;
+	ret = omap_hsmmc_pre_dma_transfer(host, data, NULL, chan);
+	if (ret)
+		return ret;
 
-	omap_hsmmc_config_dma_params(host, data, data->sg);
+	tx = dmaengine_prep_slave_sg(chan, data->sg, data->sg_len,
+		data->flags & MMC_DATA_WRITE ? DMA_MEM_TO_DEV : DMA_DEV_TO_MEM,
+		DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+	if (!tx) {
+		dev_err(mmc_dev(host->mmc), "prep_slave_sg() failed\n");
+		/* FIXME: cleanup */
+		return -1;
+	}
+
+	tx->callback = omap_hsmmc_dma_callback;
+	tx->callback_param = host;
+
+	/* Does not fail */
+	dmaengine_submit(tx);
+
+	host->dma_ch = 1;
+
+	dma_async_issue_pending(chan);
 
 	return 0;
 }
@@ -1445,11 +1417,11 @@
 	struct omap_hsmmc_host *host = mmc_priv(mmc);
 	struct mmc_data *data = mrq->data;
 
-	if (host->use_dma) {
-		if (data->host_cookie)
-			dma_unmap_sg(mmc_dev(host->mmc), data->sg,
-				     data->sg_len,
-				     omap_hsmmc_get_dma_dir(host, data));
+	if (host->use_dma && data->host_cookie) {
+		struct dma_chan *c = omap_hsmmc_get_dma_chan(host, data);
+
+		dma_unmap_sg(c->device->dev, data->sg, data->sg_len,
+			     omap_hsmmc_get_dma_dir(host, data));
 		data->host_cookie = 0;
 	}
 }
@@ -1464,10 +1436,13 @@
 		return ;
 	}
 
-	if (host->use_dma)
+	if (host->use_dma) {
+		struct dma_chan *c = omap_hsmmc_get_dma_chan(host, mrq->data);
+
 		if (omap_hsmmc_pre_dma_transfer(host, mrq->data,
-						&host->next_data))
+						&host->next_data, c))
 			mrq->data->host_cookie = 0;
+	}
 }
 
 /*
@@ -1800,6 +1775,8 @@
 	struct resource *res;
 	int ret, irq;
 	const struct of_device_id *match;
+	dma_cap_mask_t mask;
+	unsigned tx_req, rx_req;
 
 	match = of_match_device(of_match_ptr(omap_mmc_of_match), &pdev->dev);
 	if (match) {
@@ -1844,7 +1821,6 @@
 	host->pdata	= pdata;
 	host->dev	= &pdev->dev;
 	host->use_dma	= 1;
-	host->dev->dma_mask = &pdata->dma_mask;
 	host->dma_ch	= -1;
 	host->irq	= irq;
 	host->slot_id	= 0;
@@ -1933,14 +1909,31 @@
 		dev_err(mmc_dev(host->mmc), "cannot get DMA TX channel\n");
 		goto err_irq;
 	}
-	host->dma_line_tx = res->start;
+	tx_req = res->start;
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_DMA, "rx");
 	if (!res) {
 		dev_err(mmc_dev(host->mmc), "cannot get DMA RX channel\n");
 		goto err_irq;
 	}
-	host->dma_line_rx = res->start;
+	rx_req = res->start;
+
+	dma_cap_zero(mask);
+	dma_cap_set(DMA_SLAVE, mask);
+
+	host->rx_chan = dma_request_channel(mask, omap_dma_filter_fn, &rx_req);
+	if (!host->rx_chan) {
+		dev_err(mmc_dev(host->mmc), "unable to obtain RX DMA engine channel %u\n", rx_req);
+		ret = -ENXIO;
+		goto err_irq;
+	}
+
+	host->tx_chan = dma_request_channel(mask, omap_dma_filter_fn, &tx_req);
+	if (!host->tx_chan) {
+		dev_err(mmc_dev(host->mmc), "unable to obtain TX DMA engine channel %u\n", tx_req);
+		ret = -ENXIO;
+		goto err_irq;
+	}
 
 	/* Request IRQ for MMC operations */
 	ret = request_irq(host->irq, omap_hsmmc_irq, 0,
@@ -2019,6 +2012,10 @@
 err_irq_cd_init:
 	free_irq(host->irq, host);
 err_irq:
+	if (host->tx_chan)
+		dma_release_channel(host->tx_chan);
+	if (host->rx_chan)
+		dma_release_channel(host->rx_chan);
 	pm_runtime_put_sync(host->dev);
 	pm_runtime_disable(host->dev);
 	clk_put(host->fclk);
@@ -2054,6 +2051,11 @@
 	if (mmc_slot(host).card_detect_irq)
 		free_irq(mmc_slot(host).card_detect_irq, host);
 
+	if (host->tx_chan)
+		dma_release_channel(host->tx_chan);
+	if (host->rx_chan)
+		dma_release_channel(host->rx_chan);
+
 	pm_runtime_put_sync(host->dev);
 	pm_runtime_disable(host->dev);
 	clk_put(host->fclk);
diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c
index d7f681d..e9309b3 100644
--- a/drivers/mtd/nand/omap2.c
+++ b/drivers/mtd/nand/omap2.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/platform_device.h>
+#include <linux/dmaengine.h>
 #include <linux/dma-mapping.h>
 #include <linux/delay.h>
 #include <linux/module.h>
@@ -18,6 +19,7 @@
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/nand.h>
 #include <linux/mtd/partitions.h>
+#include <linux/omap-dma.h>
 #include <linux/io.h>
 #include <linux/slab.h>
 
@@ -123,7 +125,7 @@
 	int				gpmc_cs;
 	unsigned long			phys_base;
 	struct completion		comp;
-	int				dma_ch;
+	struct dma_chan			*dma;
 	int				gpmc_irq;
 	enum {
 		OMAP_NAND_IO_READ = 0,	/* read */
@@ -336,12 +338,10 @@
 }
 
 /*
- * omap_nand_dma_cb: callback on the completion of dma transfer
- * @lch: logical channel
- * @ch_satuts: channel status
+ * omap_nand_dma_callback: callback on the completion of dma transfer
  * @data: pointer to completion data structure
  */
-static void omap_nand_dma_cb(int lch, u16 ch_status, void *data)
+static void omap_nand_dma_callback(void *data)
 {
 	complete((struct completion *) data);
 }
@@ -358,17 +358,13 @@
 {
 	struct omap_nand_info *info = container_of(mtd,
 					struct omap_nand_info, mtd);
+	struct dma_async_tx_descriptor *tx;
 	enum dma_data_direction dir = is_write ? DMA_TO_DEVICE :
 							DMA_FROM_DEVICE;
-	dma_addr_t dma_addr;
-	int ret;
+	struct scatterlist sg;
 	unsigned long tim, limit;
-
-	/* The fifo depth is 64 bytes max.
-	 * But configure the FIFO-threahold to 32 to get a sync at each frame
-	 * and frame length is 32 bytes.
-	 */
-	int buf_len = len >> 6;
+	unsigned n;
+	int ret;
 
 	if (addr >= high_memory) {
 		struct page *p1;
@@ -382,40 +378,33 @@
 		addr = page_address(p1) + ((size_t)addr & ~PAGE_MASK);
 	}
 
-	dma_addr = dma_map_single(&info->pdev->dev, addr, len, dir);
-	if (dma_mapping_error(&info->pdev->dev, dma_addr)) {
+	sg_init_one(&sg, addr, len);
+	n = dma_map_sg(info->dma->device->dev, &sg, 1, dir);
+	if (n == 0) {
 		dev_err(&info->pdev->dev,
 			"Couldn't DMA map a %d byte buffer\n", len);
 		goto out_copy;
 	}
 
-	if (is_write) {
-	    omap_set_dma_dest_params(info->dma_ch, 0, OMAP_DMA_AMODE_CONSTANT,
-						info->phys_base, 0, 0);
-	    omap_set_dma_src_params(info->dma_ch, 0, OMAP_DMA_AMODE_POST_INC,
-							dma_addr, 0, 0);
-	    omap_set_dma_transfer_params(info->dma_ch, OMAP_DMA_DATA_TYPE_S32,
-					0x10, buf_len, OMAP_DMA_SYNC_FRAME,
-					OMAP24XX_DMA_GPMC, OMAP_DMA_DST_SYNC);
-	} else {
-	    omap_set_dma_src_params(info->dma_ch, 0, OMAP_DMA_AMODE_CONSTANT,
-						info->phys_base, 0, 0);
-	    omap_set_dma_dest_params(info->dma_ch, 0, OMAP_DMA_AMODE_POST_INC,
-							dma_addr, 0, 0);
-	    omap_set_dma_transfer_params(info->dma_ch, OMAP_DMA_DATA_TYPE_S32,
-					0x10, buf_len, OMAP_DMA_SYNC_FRAME,
-					OMAP24XX_DMA_GPMC, OMAP_DMA_SRC_SYNC);
-	}
-	/*  configure and start prefetch transfer */
+	tx = dmaengine_prep_slave_sg(info->dma, &sg, n,
+		is_write ? DMA_MEM_TO_DEV : DMA_DEV_TO_MEM,
+		DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+	if (!tx)
+		goto out_copy_unmap;
+
+	tx->callback = omap_nand_dma_callback;
+	tx->callback_param = &info->comp;
+	dmaengine_submit(tx);
+
+	/* configure and start prefetch transfer */
 	ret = gpmc_prefetch_enable(info->gpmc_cs,
-			PREFETCH_FIFOTHRESHOLD_MAX, 0x1, len, is_write);
+		PREFETCH_FIFOTHRESHOLD_MAX, 0x1, len, is_write);
 	if (ret)
 		/* PFPW engine is busy, use cpu copy method */
 		goto out_copy_unmap;
 
 	init_completion(&info->comp);
-
-	omap_start_dma(info->dma_ch);
+	dma_async_issue_pending(info->dma);
 
 	/* setup and start DMA using dma_addr */
 	wait_for_completion(&info->comp);
@@ -427,11 +416,11 @@
 	/* disable and stop the PFPW engine */
 	gpmc_prefetch_reset(info->gpmc_cs);
 
-	dma_unmap_single(&info->pdev->dev, dma_addr, len, dir);
+	dma_unmap_sg(info->dma->device->dev, &sg, 1, dir);
 	return 0;
 
 out_copy_unmap:
-	dma_unmap_single(&info->pdev->dev, dma_addr, len, dir);
+	dma_unmap_sg(info->dma->device->dev, &sg, 1, dir);
 out_copy:
 	if (info->nand.options & NAND_BUSWIDTH_16)
 		is_write == 0 ? omap_read_buf16(mtd, (u_char *) addr, len)
@@ -1164,6 +1153,8 @@
 	struct omap_nand_platform_data	*pdata;
 	int				err;
 	int				i, offset;
+	dma_cap_mask_t mask;
+	unsigned sig;
 
 	pdata = pdev->dev.platform_data;
 	if (pdata == NULL) {
@@ -1244,18 +1235,31 @@
 		break;
 
 	case NAND_OMAP_PREFETCH_DMA:
-		err = omap_request_dma(OMAP24XX_DMA_GPMC, "NAND",
-				omap_nand_dma_cb, &info->comp, &info->dma_ch);
-		if (err < 0) {
-			info->dma_ch = -1;
-			dev_err(&pdev->dev, "DMA request failed!\n");
+		dma_cap_zero(mask);
+		dma_cap_set(DMA_SLAVE, mask);
+		sig = OMAP24XX_DMA_GPMC;
+		info->dma = dma_request_channel(mask, omap_dma_filter_fn, &sig);
+		if (!info->dma) {
+			dev_err(&pdev->dev, "DMA engine request failed\n");
+			err = -ENXIO;
 			goto out_release_mem_region;
 		} else {
-			omap_set_dma_dest_burst_mode(info->dma_ch,
-					OMAP_DMA_DATA_BURST_16);
-			omap_set_dma_src_burst_mode(info->dma_ch,
-					OMAP_DMA_DATA_BURST_16);
+			struct dma_slave_config cfg;
+			int rc;
 
+			memset(&cfg, 0, sizeof(cfg));
+			cfg.src_addr = info->phys_base;
+			cfg.dst_addr = info->phys_base;
+			cfg.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+			cfg.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+			cfg.src_maxburst = 16;
+			cfg.dst_maxburst = 16;
+			rc = dmaengine_slave_config(info->dma, &cfg);
+			if (rc) {
+				dev_err(&pdev->dev, "DMA engine slave config failed: %d\n",
+					rc);
+				goto out_release_mem_region;
+			}
 			info->nand.read_buf   = omap_read_buf_dma_pref;
 			info->nand.write_buf  = omap_write_buf_dma_pref;
 		}
@@ -1358,6 +1362,8 @@
 	return 0;
 
 out_release_mem_region:
+	if (info->dma)
+		dma_release_channel(info->dma);
 	release_mem_region(info->phys_base, NAND_IO_SIZE);
 out_free_info:
 	kfree(info);
@@ -1373,8 +1379,8 @@
 	omap3_free_bch(&info->mtd);
 
 	platform_set_drvdata(pdev, NULL);
-	if (info->dma_ch != -1)
-		omap_free_dma(info->dma_ch);
+	if (info->dma)
+		dma_release_channel(info->dma);
 
 	if (info->gpmc_irq)
 		free_irq(info->gpmc_irq, info);
diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c
index 0c73dd4..26a99ae 100644
--- a/drivers/spi/spi-omap2-mcspi.c
+++ b/drivers/spi/spi-omap2-mcspi.c
@@ -28,6 +28,8 @@
 #include <linux/device.h>
 #include <linux/delay.h>
 #include <linux/dma-mapping.h>
+#include <linux/dmaengine.h>
+#include <linux/omap-dma.h>
 #include <linux/platform_device.h>
 #include <linux/err.h>
 #include <linux/clk.h>
@@ -39,7 +41,6 @@
 
 #include <linux/spi/spi.h>
 
-#include <plat/dma.h>
 #include <plat/clock.h>
 #include <plat/mcspi.h>
 
@@ -93,8 +94,8 @@
 
 /* We have 2 DMA channels per CS, one for RX and one for TX */
 struct omap2_mcspi_dma {
-	int dma_tx_channel;
-	int dma_rx_channel;
+	struct dma_chan *dma_tx;
+	struct dma_chan *dma_rx;
 
 	int dma_tx_sync_dev;
 	int dma_rx_sync_dev;
@@ -300,20 +301,46 @@
 	return 0;
 }
 
+static void omap2_mcspi_rx_callback(void *data)
+{
+	struct spi_device *spi = data;
+	struct omap2_mcspi *mcspi = spi_master_get_devdata(spi->master);
+	struct omap2_mcspi_dma *mcspi_dma = &mcspi->dma_channels[spi->chip_select];
+
+	complete(&mcspi_dma->dma_rx_completion);
+
+	/* We must disable the DMA RX request */
+	omap2_mcspi_set_dma_req(spi, 1, 0);
+}
+
+static void omap2_mcspi_tx_callback(void *data)
+{
+	struct spi_device *spi = data;
+	struct omap2_mcspi *mcspi = spi_master_get_devdata(spi->master);
+	struct omap2_mcspi_dma *mcspi_dma = &mcspi->dma_channels[spi->chip_select];
+
+	complete(&mcspi_dma->dma_tx_completion);
+
+	/* We must disable the DMA TX request */
+	omap2_mcspi_set_dma_req(spi, 0, 0);
+}
+
 static unsigned
 omap2_mcspi_txrx_dma(struct spi_device *spi, struct spi_transfer *xfer)
 {
 	struct omap2_mcspi	*mcspi;
 	struct omap2_mcspi_cs	*cs = spi->controller_state;
 	struct omap2_mcspi_dma  *mcspi_dma;
-	unsigned int		count, c;
-	unsigned long		base, tx_reg, rx_reg;
-	int			word_len, data_type, element_count;
+	unsigned int		count;
+	int			word_len, element_count;
 	int			elements = 0;
 	u32			l;
 	u8			* rx;
 	const u8		* tx;
 	void __iomem		*chstat_reg;
+	struct dma_slave_config	cfg;
+	enum dma_slave_buswidth width;
+	unsigned es;
 
 	mcspi = spi_master_get_devdata(spi->master);
 	mcspi_dma = &mcspi->dma_channels[spi->chip_select];
@@ -321,68 +348,92 @@
 
 	chstat_reg = cs->base + OMAP2_MCSPI_CHSTAT0;
 
+	if (cs->word_len <= 8) {
+		width = DMA_SLAVE_BUSWIDTH_1_BYTE;
+		es = 1;
+	} else if (cs->word_len <= 16) {
+		width = DMA_SLAVE_BUSWIDTH_2_BYTES;
+		es = 2;
+	} else {
+		width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+		es = 4;
+	}
+
+	memset(&cfg, 0, sizeof(cfg));
+	cfg.src_addr = cs->phys + OMAP2_MCSPI_RX0;
+	cfg.dst_addr = cs->phys + OMAP2_MCSPI_TX0;
+	cfg.src_addr_width = width;
+	cfg.dst_addr_width = width;
+	cfg.src_maxburst = 1;
+	cfg.dst_maxburst = 1;
+
+	if (xfer->tx_buf && mcspi_dma->dma_tx) {
+		struct dma_async_tx_descriptor *tx;
+		struct scatterlist sg;
+
+		dmaengine_slave_config(mcspi_dma->dma_tx, &cfg);
+
+		sg_init_table(&sg, 1);
+		sg_dma_address(&sg) = xfer->tx_dma;
+		sg_dma_len(&sg) = xfer->len;
+
+		tx = dmaengine_prep_slave_sg(mcspi_dma->dma_tx, &sg, 1,
+			DMA_MEM_TO_DEV, DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+		if (tx) {
+			tx->callback = omap2_mcspi_tx_callback;
+			tx->callback_param = spi;
+			dmaengine_submit(tx);
+		} else {
+			/* FIXME: fall back to PIO? */
+		}
+	}
+
+	if (xfer->rx_buf && mcspi_dma->dma_rx) {
+		struct dma_async_tx_descriptor *tx;
+		struct scatterlist sg;
+		size_t len = xfer->len - es;
+
+		dmaengine_slave_config(mcspi_dma->dma_rx, &cfg);
+
+		if (l & OMAP2_MCSPI_CHCONF_TURBO)
+			len -= es;
+
+		sg_init_table(&sg, 1);
+		sg_dma_address(&sg) = xfer->rx_dma;
+		sg_dma_len(&sg) = len;
+
+		tx = dmaengine_prep_slave_sg(mcspi_dma->dma_rx, &sg, 1,
+			DMA_DEV_TO_MEM, DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+		if (tx) {
+			tx->callback = omap2_mcspi_rx_callback;
+			tx->callback_param = spi;
+			dmaengine_submit(tx);
+		} else {
+			/* FIXME: fall back to PIO? */
+		}
+	}
+
 	count = xfer->len;
-	c = count;
 	word_len = cs->word_len;
 
-	base = cs->phys;
-	tx_reg = base + OMAP2_MCSPI_TX0;
-	rx_reg = base + OMAP2_MCSPI_RX0;
 	rx = xfer->rx_buf;
 	tx = xfer->tx_buf;
 
 	if (word_len <= 8) {
-		data_type = OMAP_DMA_DATA_TYPE_S8;
 		element_count = count;
 	} else if (word_len <= 16) {
-		data_type = OMAP_DMA_DATA_TYPE_S16;
 		element_count = count >> 1;
 	} else /* word_len <= 32 */ {
-		data_type = OMAP_DMA_DATA_TYPE_S32;
 		element_count = count >> 2;
 	}
 
 	if (tx != NULL) {
-		omap_set_dma_transfer_params(mcspi_dma->dma_tx_channel,
-				data_type, element_count, 1,
-				OMAP_DMA_SYNC_ELEMENT,
-				mcspi_dma->dma_tx_sync_dev, 0);
-
-		omap_set_dma_dest_params(mcspi_dma->dma_tx_channel, 0,
-				OMAP_DMA_AMODE_CONSTANT,
-				tx_reg, 0, 0);
-
-		omap_set_dma_src_params(mcspi_dma->dma_tx_channel, 0,
-				OMAP_DMA_AMODE_POST_INC,
-				xfer->tx_dma, 0, 0);
-	}
-
-	if (rx != NULL) {
-		elements = element_count - 1;
-		if (l & OMAP2_MCSPI_CHCONF_TURBO)
-			elements--;
-
-		omap_set_dma_transfer_params(mcspi_dma->dma_rx_channel,
-				data_type, elements, 1,
-				OMAP_DMA_SYNC_ELEMENT,
-				mcspi_dma->dma_rx_sync_dev, 1);
-
-		omap_set_dma_src_params(mcspi_dma->dma_rx_channel, 0,
-				OMAP_DMA_AMODE_CONSTANT,
-				rx_reg, 0, 0);
-
-		omap_set_dma_dest_params(mcspi_dma->dma_rx_channel, 0,
-				OMAP_DMA_AMODE_POST_INC,
-				xfer->rx_dma, 0, 0);
-	}
-
-	if (tx != NULL) {
-		omap_start_dma(mcspi_dma->dma_tx_channel);
+		dma_async_issue_pending(mcspi_dma->dma_tx);
 		omap2_mcspi_set_dma_req(spi, 0, 1);
 	}
 
 	if (rx != NULL) {
-		omap_start_dma(mcspi_dma->dma_rx_channel);
+		dma_async_issue_pending(mcspi_dma->dma_rx);
 		omap2_mcspi_set_dma_req(spi, 1, 1);
 	}
 
@@ -406,7 +457,10 @@
 		dma_unmap_single(&spi->dev, xfer->rx_dma, count, DMA_FROM_DEVICE);
 		omap2_mcspi_set_enable(spi, 0);
 
+		elements = element_count - 1;
+
 		if (l & OMAP2_MCSPI_CHCONF_TURBO) {
+			elements--;
 
 			if (likely(mcspi_read_cs_reg(spi, OMAP2_MCSPI_CHSTAT0)
 				   & OMAP2_MCSPI_CHSTAT_RXS)) {
@@ -723,64 +777,38 @@
 	return 0;
 }
 
-static void omap2_mcspi_dma_rx_callback(int lch, u16 ch_status, void *data)
-{
-	struct spi_device	*spi = data;
-	struct omap2_mcspi	*mcspi;
-	struct omap2_mcspi_dma	*mcspi_dma;
-
-	mcspi = spi_master_get_devdata(spi->master);
-	mcspi_dma = &(mcspi->dma_channels[spi->chip_select]);
-
-	complete(&mcspi_dma->dma_rx_completion);
-
-	/* We must disable the DMA RX request */
-	omap2_mcspi_set_dma_req(spi, 1, 0);
-}
-
-static void omap2_mcspi_dma_tx_callback(int lch, u16 ch_status, void *data)
-{
-	struct spi_device	*spi = data;
-	struct omap2_mcspi	*mcspi;
-	struct omap2_mcspi_dma	*mcspi_dma;
-
-	mcspi = spi_master_get_devdata(spi->master);
-	mcspi_dma = &(mcspi->dma_channels[spi->chip_select]);
-
-	complete(&mcspi_dma->dma_tx_completion);
-
-	/* We must disable the DMA TX request */
-	omap2_mcspi_set_dma_req(spi, 0, 0);
-}
-
 static int omap2_mcspi_request_dma(struct spi_device *spi)
 {
 	struct spi_master	*master = spi->master;
 	struct omap2_mcspi	*mcspi;
 	struct omap2_mcspi_dma	*mcspi_dma;
+	dma_cap_mask_t mask;
+	unsigned sig;
 
 	mcspi = spi_master_get_devdata(master);
 	mcspi_dma = mcspi->dma_channels + spi->chip_select;
 
-	if (omap_request_dma(mcspi_dma->dma_rx_sync_dev, "McSPI RX",
-			omap2_mcspi_dma_rx_callback, spi,
-			&mcspi_dma->dma_rx_channel)) {
-		dev_err(&spi->dev, "no RX DMA channel for McSPI\n");
-		return -EAGAIN;
-	}
-
-	if (omap_request_dma(mcspi_dma->dma_tx_sync_dev, "McSPI TX",
-			omap2_mcspi_dma_tx_callback, spi,
-			&mcspi_dma->dma_tx_channel)) {
-		omap_free_dma(mcspi_dma->dma_rx_channel);
-		mcspi_dma->dma_rx_channel = -1;
-		dev_err(&spi->dev, "no TX DMA channel for McSPI\n");
-		return -EAGAIN;
-	}
-
 	init_completion(&mcspi_dma->dma_rx_completion);
 	init_completion(&mcspi_dma->dma_tx_completion);
 
+	dma_cap_zero(mask);
+	dma_cap_set(DMA_SLAVE, mask);
+	sig = mcspi_dma->dma_rx_sync_dev;
+	mcspi_dma->dma_rx = dma_request_channel(mask, omap_dma_filter_fn, &sig);
+	if (!mcspi_dma->dma_rx) {
+		dev_err(&spi->dev, "no RX DMA engine channel for McSPI\n");
+		return -EAGAIN;
+	}
+
+	sig = mcspi_dma->dma_tx_sync_dev;
+	mcspi_dma->dma_tx = dma_request_channel(mask, omap_dma_filter_fn, &sig);
+	if (!mcspi_dma->dma_tx) {
+		dev_err(&spi->dev, "no TX DMA engine channel for McSPI\n");
+		dma_release_channel(mcspi_dma->dma_rx);
+		mcspi_dma->dma_rx = NULL;
+		return -EAGAIN;
+	}
+
 	return 0;
 }
 
@@ -812,8 +840,7 @@
 		list_add_tail(&cs->node, &ctx->cs);
 	}
 
-	if (mcspi_dma->dma_rx_channel == -1
-			|| mcspi_dma->dma_tx_channel == -1) {
+	if (!mcspi_dma->dma_rx || !mcspi_dma->dma_tx) {
 		ret = omap2_mcspi_request_dma(spi);
 		if (ret < 0)
 			return ret;
@@ -848,13 +875,13 @@
 	if (spi->chip_select < spi->master->num_chipselect) {
 		mcspi_dma = &mcspi->dma_channels[spi->chip_select];
 
-		if (mcspi_dma->dma_rx_channel != -1) {
-			omap_free_dma(mcspi_dma->dma_rx_channel);
-			mcspi_dma->dma_rx_channel = -1;
+		if (mcspi_dma->dma_rx) {
+			dma_release_channel(mcspi_dma->dma_rx);
+			mcspi_dma->dma_rx = NULL;
 		}
-		if (mcspi_dma->dma_tx_channel != -1) {
-			omap_free_dma(mcspi_dma->dma_tx_channel);
-			mcspi_dma->dma_tx_channel = -1;
+		if (mcspi_dma->dma_tx) {
+			dma_release_channel(mcspi_dma->dma_tx);
+			mcspi_dma->dma_tx = NULL;
 		}
 	}
 }
@@ -1174,7 +1201,6 @@
 			break;
 		}
 
-		mcspi->dma_channels[i].dma_rx_channel = -1;
 		mcspi->dma_channels[i].dma_rx_sync_dev = dma_res->start;
 		sprintf(dma_ch_name, "tx%d", i);
 		dma_res = platform_get_resource_byname(pdev, IORESOURCE_DMA,
@@ -1185,7 +1211,6 @@
 			break;
 		}
 
-		mcspi->dma_channels[i].dma_tx_channel = -1;
 		mcspi->dma_channels[i].dma_tx_sync_dev = dma_res->start;
 	}
 
diff --git a/include/linux/amba/pl08x.h b/include/linux/amba/pl08x.h
index 0254901..2a5f64a 100644
--- a/include/linux/amba/pl08x.h
+++ b/include/linux/amba/pl08x.h
@@ -21,8 +21,9 @@
 #include <linux/dmaengine.h>
 #include <linux/interrupt.h>
 
-struct pl08x_lli;
 struct pl08x_driver_data;
+struct pl08x_phy_chan;
+struct pl08x_txd;
 
 /* Bitmasks for selecting AHB ports for DMA transfers */
 enum {
@@ -46,170 +47,29 @@
  * devices with static assignments
  * @muxval: a number usually used to poke into some mux regiser to
  * mux in the signal to this channel
- * @cctl_opt: default options for the channel control register
+ * @cctl_memcpy: options for the channel control register for memcpy
+ *  *** not used for slave channels ***
  * @addr: source/target address in physical memory for this DMA channel,
  * can be the address of a FIFO register for burst requests for example.
  * This can be left undefined if the PrimeCell API is used for configuring
  * this.
- * @circular_buffer: whether the buffer passed in is circular and
- * shall simply be looped round round (like a record baby round
- * round round round)
  * @single: the device connected to this channel will request single DMA
  * transfers, not bursts. (Bursts are default.)
  * @periph_buses: the device connected to this channel is accessible via
  * these buses (use PL08X_AHB1 | PL08X_AHB2).
  */
 struct pl08x_channel_data {
-	char *bus_id;
+	const char *bus_id;
 	int min_signal;
 	int max_signal;
 	u32 muxval;
-	u32 cctl;
+	u32 cctl_memcpy;
 	dma_addr_t addr;
-	bool circular_buffer;
 	bool single;
 	u8 periph_buses;
 };
 
 /**
- * Struct pl08x_bus_data - information of source or destination
- * busses for a transfer
- * @addr: current address
- * @maxwidth: the maximum width of a transfer on this bus
- * @buswidth: the width of this bus in bytes: 1, 2 or 4
- */
-struct pl08x_bus_data {
-	dma_addr_t addr;
-	u8 maxwidth;
-	u8 buswidth;
-};
-
-/**
- * struct pl08x_phy_chan - holder for the physical channels
- * @id: physical index to this channel
- * @lock: a lock to use when altering an instance of this struct
- * @signal: the physical signal (aka channel) serving this physical channel
- * right now
- * @serving: the virtual channel currently being served by this physical
- * channel
- * @locked: channel unavailable for the system, e.g. dedicated to secure
- * world
- */
-struct pl08x_phy_chan {
-	unsigned int id;
-	void __iomem *base;
-	spinlock_t lock;
-	int signal;
-	struct pl08x_dma_chan *serving;
-	bool locked;
-};
-
-/**
- * struct pl08x_sg - structure containing data per sg
- * @src_addr: src address of sg
- * @dst_addr: dst address of sg
- * @len: transfer len in bytes
- * @node: node for txd's dsg_list
- */
-struct pl08x_sg {
-	dma_addr_t src_addr;
-	dma_addr_t dst_addr;
-	size_t len;
-	struct list_head node;
-};
-
-/**
- * struct pl08x_txd - wrapper for struct dma_async_tx_descriptor
- * @tx: async tx descriptor
- * @node: node for txd list for channels
- * @dsg_list: list of children sg's
- * @direction: direction of transfer
- * @llis_bus: DMA memory address (physical) start for the LLIs
- * @llis_va: virtual memory address start for the LLIs
- * @cctl: control reg values for current txd
- * @ccfg: config reg values for current txd
- */
-struct pl08x_txd {
-	struct dma_async_tx_descriptor tx;
-	struct list_head node;
-	struct list_head dsg_list;
-	enum dma_transfer_direction direction;
-	dma_addr_t llis_bus;
-	struct pl08x_lli *llis_va;
-	/* Default cctl value for LLIs */
-	u32 cctl;
-	/*
-	 * Settings to be put into the physical channel when we
-	 * trigger this txd.  Other registers are in llis_va[0].
-	 */
-	u32 ccfg;
-};
-
-/**
- * struct pl08x_dma_chan_state - holds the PL08x specific virtual channel
- * states
- * @PL08X_CHAN_IDLE: the channel is idle
- * @PL08X_CHAN_RUNNING: the channel has allocated a physical transport
- * channel and is running a transfer on it
- * @PL08X_CHAN_PAUSED: the channel has allocated a physical transport
- * channel, but the transfer is currently paused
- * @PL08X_CHAN_WAITING: the channel is waiting for a physical transport
- * channel to become available (only pertains to memcpy channels)
- */
-enum pl08x_dma_chan_state {
-	PL08X_CHAN_IDLE,
-	PL08X_CHAN_RUNNING,
-	PL08X_CHAN_PAUSED,
-	PL08X_CHAN_WAITING,
-};
-
-/**
- * struct pl08x_dma_chan - this structure wraps a DMA ENGINE channel
- * @chan: wrappped abstract channel
- * @phychan: the physical channel utilized by this channel, if there is one
- * @phychan_hold: if non-zero, hold on to the physical channel even if we
- * have no pending entries
- * @tasklet: tasklet scheduled by the IRQ to handle actual work etc
- * @name: name of channel
- * @cd: channel platform data
- * @runtime_addr: address for RX/TX according to the runtime config
- * @runtime_direction: current direction of this channel according to
- * runtime config
- * @pend_list: queued transactions pending on this channel
- * @at: active transaction on this channel
- * @lock: a lock for this channel data
- * @host: a pointer to the host (internal use)
- * @state: whether the channel is idle, paused, running etc
- * @slave: whether this channel is a device (slave) or for memcpy
- * @device_fc: Flow Controller Settings for ccfg register. Only valid for slave
- * channels. Fill with 'true' if peripheral should be flow controller. Direction
- * will be selected at Runtime.
- * @waiting: a TX descriptor on this channel which is waiting for a physical
- * channel to become available
- */
-struct pl08x_dma_chan {
-	struct dma_chan chan;
-	struct pl08x_phy_chan *phychan;
-	int phychan_hold;
-	struct tasklet_struct tasklet;
-	char *name;
-	const struct pl08x_channel_data *cd;
-	dma_addr_t src_addr;
-	dma_addr_t dst_addr;
-	u32 src_cctl;
-	u32 dst_cctl;
-	enum dma_transfer_direction runtime_direction;
-	struct list_head pend_list;
-	struct pl08x_txd *at;
-	spinlock_t lock;
-	struct pl08x_driver_data *host;
-	enum pl08x_dma_chan_state state;
-	bool slave;
-	bool device_fc;
-	struct pl08x_txd *waiting;
-};
-
-/**
  * struct pl08x_platform_data - the platform configuration for the PL08x
  * PrimeCells.
  * @slave_channels: the channels defined for the different devices on the
@@ -229,8 +89,8 @@
 	const struct pl08x_channel_data *slave_channels;
 	unsigned int num_slave_channels;
 	struct pl08x_channel_data memcpy_channel;
-	int (*get_signal)(struct pl08x_dma_chan *);
-	void (*put_signal)(struct pl08x_dma_chan *);
+	int (*get_signal)(const struct pl08x_channel_data *);
+	void (*put_signal)(const struct pl08x_channel_data *, int);
 	u8 lli_buses;
 	u8 mem_buses;
 };
diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h
new file mode 100644
index 0000000..eb475a8
--- /dev/null
+++ b/include/linux/omap-dma.h
@@ -0,0 +1,22 @@
+/*
+ * OMAP DMA Engine support
+ *
+ * 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 __LINUX_OMAP_DMA_H
+#define __LINUX_OMAP_DMA_H
+
+struct dma_chan;
+
+#if defined(CONFIG_DMA_OMAP) || defined(CONFIG_DMA_OMAP_MODULE)
+bool omap_dma_filter_fn(struct dma_chan *, void *);
+#else
+static inline bool omap_dma_filter_fn(struct dma_chan *c, void *d)
+{
+	return false;
+}
+#endif
+
+#endif