diff --git a/Documentation/devicetree/bindings/dma/nbpfaxi.txt b/Documentation/devicetree/bindings/dma/nbpfaxi.txt
index d5e2522..d2e1e62 100644
--- a/Documentation/devicetree/bindings/dma/nbpfaxi.txt
+++ b/Documentation/devicetree/bindings/dma/nbpfaxi.txt
@@ -23,6 +23,14 @@
 #define NBPF_SLAVE_RQ_LEVEL	4
 
 Optional properties:
+- max-burst-mem-read:	limit burst size for memory reads
+  (DMA_MEM_TO_MEM/DMA_MEM_TO_DEV) to this value, specified in bytes, rather
+  than using the maximum burst size allowed by the hardware's buffer size.
+- max-burst-mem-write:	limit burst size for memory writes
+  (DMA_DEV_TO_MEM/DMA_MEM_TO_MEM) to this value, specified in bytes, rather
+  than using the maximum burst size allowed by the hardware's buffer size.
+  If both max-burst-mem-read and max-burst-mem-write are set, DMA_MEM_TO_MEM
+  will use the lower value.
 
 You can use dma-channels and dma-requests as described in dma.txt, although they
 won't be used, this information is derived from the compatibility string.
diff --git a/Documentation/devicetree/bindings/dma/qcom_hidma_mgmt.txt b/Documentation/devicetree/bindings/dma/qcom_hidma_mgmt.txt
index fd5618b..55492c2 100644
--- a/Documentation/devicetree/bindings/dma/qcom_hidma_mgmt.txt
+++ b/Documentation/devicetree/bindings/dma/qcom_hidma_mgmt.txt
@@ -5,13 +5,13 @@
 environments.
 
 Each HIDMA HW instance consists of multiple DMA channels. These channels
-share the same bandwidth. The bandwidth utilization can be parititioned
+share the same bandwidth. The bandwidth utilization can be partitioned
 among channels based on the priority and weight assignments.
 
 There are only two priority levels and 15 weigh assignments possible.
 
 Other parameters here determine how much of the system bus this HIDMA
-instance can use like maximum read/write request and and number of bytes to
+instance can use like maximum read/write request and number of bytes to
 read/write in a single burst.
 
 Main node required properties:
@@ -47,12 +47,18 @@
 the channel nodes appear on their own, not under a management node.
 
 Required properties:
-- compatible: must contain "qcom,hidma-1.0"
+- compatible: must contain "qcom,hidma-1.0" for initial HW or "qcom,hidma-1.1"
+for MSI capable HW.
 - reg: Addresses for the transfer and event channel
 - interrupts: Should contain the event interrupt
 - desc-count: Number of asynchronous requests this channel can handle
 - iommus: required a iommu node
 
+Optional properties for MSI:
+- msi-parent : See the generic MSI binding described in
+ devicetree/bindings/interrupt-controller/msi.txt for a description of the
+ msi-parent property.
+
 Example:
 
 Hypervisor OS configuration:
diff --git a/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.txt b/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.txt
index 5f2ce66..3316a9c 100644
--- a/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.txt
+++ b/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.txt
@@ -24,6 +24,7 @@
 		- "renesas,dmac-r8a7793" (R-Car M2-N)
 		- "renesas,dmac-r8a7794" (R-Car E2)
 		- "renesas,dmac-r8a7795" (R-Car H3)
+		- "renesas,dmac-r8a7796" (R-Car M3-W)
 
 - reg: base address and length of the registers block for the DMAC
 
diff --git a/Documentation/devicetree/bindings/dma/snps-dma.txt b/Documentation/devicetree/bindings/dma/snps-dma.txt
index 0f55832..4775c66f 100644
--- a/Documentation/devicetree/bindings/dma/snps-dma.txt
+++ b/Documentation/devicetree/bindings/dma/snps-dma.txt
@@ -27,6 +27,8 @@
   that services interrupts for this device
 - is_private: The device channels should be marked as private and not for by the
   general purpose DMA channel allocator. False if not passed.
+- multi-block: Multi block transfers supported by hardware. Array property with
+  one cell per channel. 0: not supported, 1 (default): supported.
 
 Example:
 
diff --git a/Documentation/dmaengine/client.txt b/Documentation/dmaengine/client.txt
index 9e33189..c72b456 100644
--- a/Documentation/dmaengine/client.txt
+++ b/Documentation/dmaengine/client.txt
@@ -37,8 +37,8 @@
 2. Set slave and controller specific parameters
 
    Next step is always to pass some specific information to the DMA
-   driver.  Most of the generic information which a slave DMA can use
-   is in struct dma_slave_config.  This allows the clients to specify
+   driver. Most of the generic information which a slave DMA can use
+   is in struct dma_slave_config. This allows the clients to specify
    DMA direction, DMA addresses, bus widths, DMA burst lengths etc
    for the peripheral.
 
@@ -52,7 +52,7 @@
 				  struct dma_slave_config *config)
 
    Please see the dma_slave_config structure definition in dmaengine.h
-   for a detailed explanation of the struct members.  Please note
+   for a detailed explanation of the struct members. Please note
    that the 'direction' member will be going away as it duplicates the
    direction given in the prepare call.
 
@@ -101,7 +101,7 @@
 	desc = dmaengine_prep_slave_sg(chan, sgl, nr_sg, direction, flags);
 
    Once a descriptor has been obtained, the callback information can be
-   added and the descriptor must then be submitted.  Some DMA engine
+   added and the descriptor must then be submitted. Some DMA engine
    drivers may hold a spinlock between a successful preparation and
    submission so it is important that these two operations are closely
    paired.
@@ -138,7 +138,7 @@
    activity via other DMA engine calls not covered in this document.
 
    dmaengine_submit() will not start the DMA operation, it merely adds
-   it to the pending queue.  For this, see step 5, dma_async_issue_pending.
+   it to the pending queue. For this, see step 5, dma_async_issue_pending.
 
 5. Issue pending DMA requests and wait for callback notification
 
@@ -184,13 +184,13 @@
 
 3. int dmaengine_resume(struct dma_chan *chan)
 
-   Resume a previously paused DMA channel.  It is invalid to resume a
+   Resume a previously paused DMA channel. It is invalid to resume a
    channel which is not currently paused.
 
 4. enum dma_status dma_async_is_tx_complete(struct dma_chan *chan,
         dma_cookie_t cookie, dma_cookie_t *last, dma_cookie_t *used)
 
-   This can be used to check the status of the channel.  Please see
+   This can be used to check the status of the channel. Please see
    the documentation in include/linux/dmaengine.h for a more complete
    description of this API.
 
@@ -200,7 +200,7 @@
 
    Note:
 	Not all DMA engine drivers can return reliable information for
-	a running DMA channel.  It is recommended that DMA engine users
+	a running DMA channel. It is recommended that DMA engine users
 	pause or stop (via dmaengine_terminate_all()) the channel before
 	using this API.
 
diff --git a/Documentation/dmaengine/dmatest.txt b/Documentation/dmaengine/dmatest.txt
index dd77a81..fb683c7 100644
--- a/Documentation/dmaengine/dmatest.txt
+++ b/Documentation/dmaengine/dmatest.txt
@@ -34,7 +34,7 @@
 	% ls -1 /sys/class/dma/
 
 Once started a message like "dmatest: Started 1 threads using dma0chan0" is
-emitted.  After that only test failure messages are reported until the test
+emitted. After that only test failure messages are reported until the test
 stops.
 
 Note that running a new test will not stop any in progress test.
@@ -43,11 +43,11 @@
 	% cat /sys/module/dmatest/parameters/run
 
 To wait for test completion userpace can poll 'run' until it is false, or use
-the wait parameter.  Specifying 'wait=1' when loading the module causes module
+the wait parameter. Specifying 'wait=1' when loading the module causes module
 initialization to pause until a test run has completed, while reading
 /sys/module/dmatest/parameters/wait waits for any running test to complete
-before returning.  For example, the following scripts wait for 42 tests
-to complete before exiting.  Note that if 'iterations' is set to 'infinite' then
+before returning. For example, the following scripts wait for 42 tests
+to complete before exiting. Note that if 'iterations' is set to 'infinite' then
 waiting is disabled.
 
 Example:
@@ -81,7 +81,7 @@
 
 The message format is unified across the different types of errors. A number in
 the parens represents additional information, e.g. error code, error counter,
-or status.  A test thread also emits a summary line at completion listing the
+or status. A test thread also emits a summary line at completion listing the
 number of tests executed, number that failed, and a result code.
 
 Example:
diff --git a/Documentation/dmaengine/provider.txt b/Documentation/dmaengine/provider.txt
index c4fd475..e33bc1c 100644
--- a/Documentation/dmaengine/provider.txt
+++ b/Documentation/dmaengine/provider.txt
@@ -384,7 +384,7 @@
     - The descriptor should be prepared for reuse by invoking
       dmaengine_desc_set_reuse() which will set DMA_CTRL_REUSE.
     - dmaengine_desc_set_reuse() will succeed only when channel support
-      reusable descriptor as exhibited by capablities
+      reusable descriptor as exhibited by capabilities
     - As a consequence, if a device driver wants to skip the dma_map_sg() and
       dma_unmap_sg() in between 2 transfers, because the DMA'd data wasn't used,
       it can resubmit the transfer right after its completion.
diff --git a/Documentation/dmaengine/pxa_dma.txt b/Documentation/dmaengine/pxa_dma.txt
index 413ef9c..0736d44 100644
--- a/Documentation/dmaengine/pxa_dma.txt
+++ b/Documentation/dmaengine/pxa_dma.txt
@@ -29,7 +29,7 @@
 
   d) Bandwidth guarantee
      The PXA architecture has 4 levels of DMAs priorities : high, normal, low.
-     The high prorities get twice as much bandwidth as the normal, which get twice
+     The high priorities get twice as much bandwidth as the normal, which get twice
      as much as the low priorities.
      A driver should be able to request a priority, especially the real-time
      ones such as pxa_camera with (big) throughputs.
diff --git a/arch/arc/boot/dts/abilis_tb10x.dtsi b/arch/arc/boot/dts/abilis_tb10x.dtsi
index de53f5c..3121536 100644
--- a/arch/arc/boot/dts/abilis_tb10x.dtsi
+++ b/arch/arc/boot/dts/abilis_tb10x.dtsi
@@ -129,6 +129,7 @@
 			data-width = <4>;
 			clocks = <&ahb_clk>;
 			clock-names = "hclk";
+			multi-block = <1 1 1 1 1 1>;
 		};
 
 		i2c0: i2c@FF120000 {
diff --git a/arch/arm/boot/dts/spear13xx.dtsi b/arch/arm/boot/dts/spear13xx.dtsi
index 449acf0..17ea0ab 100644
--- a/arch/arm/boot/dts/spear13xx.dtsi
+++ b/arch/arm/boot/dts/spear13xx.dtsi
@@ -118,6 +118,7 @@
 			block_size = <0xfff>;
 			dma-masters = <2>;
 			data-width = <8 8>;
+			multi-block = <1 1 1 1 1 1 1 1>;
 		};
 
 		dma@eb000000 {
@@ -134,6 +135,7 @@
 			chan_priority = <1>;
 			block_size = <0xfff>;
 			data-width = <8 8>;
+			multi-block = <1 1 1 1 1 1 1 1>;
 		};
 
 		fsmc: flash@b0000000 {
diff --git a/arch/arm/mach-s3c64xx/pl080.c b/arch/arm/mach-s3c64xx/pl080.c
index 89c5a62..261820a 100644
--- a/arch/arm/mach-s3c64xx/pl080.c
+++ b/arch/arm/mach-s3c64xx/pl080.c
@@ -117,6 +117,25 @@ static struct pl08x_channel_data s3c64xx_dma0_info[] = {
 	}
 };
 
+static const struct dma_slave_map s3c64xx_dma0_slave_map[] = {
+	{ "s3c6400-uart.0", "tx", &s3c64xx_dma0_info[0] },
+	{ "s3c6400-uart.0", "rx", &s3c64xx_dma0_info[1] },
+	{ "s3c6400-uart.1", "tx", &s3c64xx_dma0_info[2] },
+	{ "s3c6400-uart.1", "rx", &s3c64xx_dma0_info[3] },
+	{ "s3c6400-uart.2", "tx", &s3c64xx_dma0_info[4] },
+	{ "s3c6400-uart.2", "rx", &s3c64xx_dma0_info[5] },
+	{ "s3c6400-uart.3", "tx", &s3c64xx_dma0_info[6] },
+	{ "s3c6400-uart.3", "rx", &s3c64xx_dma0_info[7] },
+	{ "samsung-pcm.0", "tx", &s3c64xx_dma0_info[8] },
+	{ "samsung-pcm.0", "rx", &s3c64xx_dma0_info[9] },
+	{ "samsung-i2s.0", "tx", &s3c64xx_dma0_info[10] },
+	{ "samsung-i2s.0", "rx", &s3c64xx_dma0_info[11] },
+	{ "s3c6410-spi.0", "tx", &s3c64xx_dma0_info[12] },
+	{ "s3c6410-spi.0", "rx", &s3c64xx_dma0_info[13] },
+	{ "samsung-i2s.2", "tx", &s3c64xx_dma0_info[14] },
+	{ "samsung-i2s.2", "rx", &s3c64xx_dma0_info[15] },
+};
+
 struct pl08x_platform_data s3c64xx_dma0_plat_data = {
 	.memcpy_channel = {
 		.bus_id = "memcpy",
@@ -134,6 +153,8 @@ struct pl08x_platform_data s3c64xx_dma0_plat_data = {
 	.put_xfer_signal = pl08x_put_xfer_signal,
 	.slave_channels = s3c64xx_dma0_info,
 	.num_slave_channels = ARRAY_SIZE(s3c64xx_dma0_info),
+	.slave_map = s3c64xx_dma0_slave_map,
+	.slave_map_len = ARRAY_SIZE(s3c64xx_dma0_slave_map),
 };
 
 static AMBA_AHB_DEVICE(s3c64xx_dma0, "dma-pl080s.0", 0,
@@ -207,6 +228,15 @@ static struct pl08x_channel_data s3c64xx_dma1_info[] = {
 	},
 };
 
+static const struct dma_slave_map s3c64xx_dma1_slave_map[] = {
+	{ "samsung-pcm.1", "tx", &s3c64xx_dma1_info[0] },
+	{ "samsung-pcm.1", "rx", &s3c64xx_dma1_info[1] },
+	{ "samsung-i2s.1", "tx", &s3c64xx_dma1_info[2] },
+	{ "samsung-i2s.1", "rx", &s3c64xx_dma1_info[3] },
+	{ "s3c6410-spi.1", "tx", &s3c64xx_dma1_info[4] },
+	{ "s3c6410-spi.1", "rx", &s3c64xx_dma1_info[5] },
+};
+
 struct pl08x_platform_data s3c64xx_dma1_plat_data = {
 	.memcpy_channel = {
 		.bus_id = "memcpy",
@@ -224,6 +254,8 @@ struct pl08x_platform_data s3c64xx_dma1_plat_data = {
 	.put_xfer_signal = pl08x_put_xfer_signal,
 	.slave_channels = s3c64xx_dma1_info,
 	.num_slave_channels = ARRAY_SIZE(s3c64xx_dma1_info),
+	.slave_map = s3c64xx_dma1_slave_map,
+	.slave_map_len = ARRAY_SIZE(s3c64xx_dma1_slave_map),
 };
 
 static AMBA_AHB_DEVICE(s3c64xx_dma1, "dma-pl080s.1", 0,
diff --git a/arch/arm/plat-samsung/devs.c b/arch/arm/plat-samsung/devs.c
index e93aa67..cf7b95f 100644
--- a/arch/arm/plat-samsung/devs.c
+++ b/arch/arm/plat-samsung/devs.c
@@ -1124,15 +1124,6 @@ void __init s3c64xx_spi0_set_platdata(int (*cfg_gpio)(void), int src_clk_nr,
 	pd.num_cs = num_cs;
 	pd.src_clk_nr = src_clk_nr;
 	pd.cfg_gpio = (cfg_gpio) ? cfg_gpio : s3c64xx_spi0_cfg_gpio;
-	pd.dma_tx = (void *)DMACH_SPI0_TX;
-	pd.dma_rx = (void *)DMACH_SPI0_RX;
-#if defined(CONFIG_PL330_DMA)
-	pd.filter = pl330_filter;
-#elif defined(CONFIG_S3C64XX_PL080)
-	pd.filter = pl08x_filter_id;
-#elif defined(CONFIG_S3C24XX_DMAC)
-	pd.filter = s3c24xx_dma_filter;
-#endif
 
 	s3c_set_platdata(&pd, sizeof(pd), &s3c64xx_device_spi0);
 }
@@ -1169,14 +1160,6 @@ void __init s3c64xx_spi1_set_platdata(int (*cfg_gpio)(void), int src_clk_nr,
 	pd.num_cs = num_cs;
 	pd.src_clk_nr = src_clk_nr;
 	pd.cfg_gpio = (cfg_gpio) ? cfg_gpio : s3c64xx_spi1_cfg_gpio;
-	pd.dma_tx = (void *)DMACH_SPI1_TX;
-	pd.dma_rx = (void *)DMACH_SPI1_RX;
-#if defined(CONFIG_PL330_DMA)
-	pd.filter = pl330_filter;
-#elif defined(CONFIG_S3C64XX_PL080)
-	pd.filter = pl08x_filter_id;
-#endif
-
 
 	s3c_set_platdata(&pd, sizeof(pd), &s3c64xx_device_spi1);
 }
@@ -1213,13 +1196,6 @@ void __init s3c64xx_spi2_set_platdata(int (*cfg_gpio)(void), int src_clk_nr,
 	pd.num_cs = num_cs;
 	pd.src_clk_nr = src_clk_nr;
 	pd.cfg_gpio = (cfg_gpio) ? cfg_gpio : s3c64xx_spi2_cfg_gpio;
-	pd.dma_tx = (void *)DMACH_SPI2_TX;
-	pd.dma_rx = (void *)DMACH_SPI2_RX;
-#if defined(CONFIG_PL330_DMA)
-	pd.filter = pl330_filter;
-#elif defined(CONFIG_S3C64XX_PL080)
-	pd.filter = pl08x_filter_id;
-#endif
 
 	s3c_set_platdata(&pd, sizeof(pd), &s3c64xx_device_spi2);
 }
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 2154ea3..263495d 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -494,7 +494,7 @@
 	  or vice versa. It does not support memory to memory data transfer.
 
 config TEGRA210_ADMA
-	bool "NVIDIA Tegra210 ADMA support"
+	tristate "NVIDIA Tegra210 ADMA support"
 	depends on (ARCH_TEGRA_210_SOC || COMPILE_TEST) && PM_CLK
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c
index 939a7c3..0b7c6ce 100644
--- a/drivers/dma/amba-pl08x.c
+++ b/drivers/dma/amba-pl08x.c
@@ -1793,6 +1793,13 @@ bool pl08x_filter_id(struct dma_chan *chan, void *chan_id)
 }
 EXPORT_SYMBOL_GPL(pl08x_filter_id);
 
+static bool pl08x_filter_fn(struct dma_chan *chan, void *chan_id)
+{
+	struct pl08x_dma_chan *plchan = to_pl08x_chan(chan);
+
+	return plchan->cd == chan_id;
+}
+
 /*
  * Just check that the device is there and active
  * TODO: turn this bit on/off depending on the number of physical channels
@@ -2307,6 +2314,10 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id)
 			ret = -EINVAL;
 			goto out_no_platdata;
 		}
+	} else {
+		pl08x->slave.filter.map = pl08x->pd->slave_map;
+		pl08x->slave.filter.mapcnt = pl08x->pd->slave_map_len;
+		pl08x->slave.filter.fn = pl08x_filter_fn;
 	}
 
 	/* By default, AHB1 only.  If dualmaster, from platform */
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index a4c8f80..1baf340 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -111,9 +111,8 @@ static struct at_desc *atc_alloc_descriptor(struct dma_chan *chan,
 	struct at_dma	*atdma = to_at_dma(chan->device);
 	dma_addr_t phys;
 
-	desc = dma_pool_alloc(atdma->dma_desc_pool, gfp_flags, &phys);
+	desc = dma_pool_zalloc(atdma->dma_desc_pool, gfp_flags, &phys);
 	if (desc) {
-		memset(desc, 0, sizeof(struct at_desc));
 		INIT_LIST_HEAD(&desc->tx_list);
 		dma_async_tx_descriptor_init(&desc->txd, chan);
 		/* txd.flags will be overwritten in prep functions */
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index b7d7f2d..7d4e0bc 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -221,7 +221,6 @@ struct at_xdmac {
 	int			irq;
 	struct clk		*clk;
 	u32			save_gim;
-	u32			save_gs;
 	struct dma_pool		*at_xdmac_desc_pool;
 	struct at_xdmac_chan	chan[0];
 };
@@ -444,9 +443,8 @@ static struct at_xdmac_desc *at_xdmac_alloc_desc(struct dma_chan *chan,
 	struct at_xdmac		*atxdmac = to_at_xdmac(chan->device);
 	dma_addr_t		phys;
 
-	desc = dma_pool_alloc(atxdmac->at_xdmac_desc_pool, gfp_flags, &phys);
+	desc = dma_pool_zalloc(atxdmac->at_xdmac_desc_pool, gfp_flags, &phys);
 	if (desc) {
-		memset(desc, 0, sizeof(*desc));
 		INIT_LIST_HEAD(&desc->descs_list);
 		dma_async_tx_descriptor_init(&desc->tx_dma_desc, chan);
 		desc->tx_dma_desc.tx_submit = at_xdmac_tx_submit;
@@ -1896,7 +1894,6 @@ static int atmel_xdmac_resume(struct device *dev)
 	}
 
 	at_xdmac_write(atxdmac, AT_XDMAC_GIE, atxdmac->save_gim);
-	at_xdmac_write(atxdmac, AT_XDMAC_GE, atxdmac->save_gs);
 	list_for_each_entry_safe(chan, _chan, &atxdmac->dma.channels, device_node) {
 		atchan = to_at_xdmac_chan(chan);
 		at_xdmac_chan_write(atchan, AT_XDMAC_CC, atchan->save_cc);
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index cf76fc6..451f899 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -164,7 +164,9 @@ struct dmatest_thread {
 	struct task_struct	*task;
 	struct dma_chan		*chan;
 	u8			**srcs;
+	u8			**usrcs;
 	u8			**dsts;
+	u8			**udsts;
 	enum dma_transaction_type type;
 	bool			done;
 };
@@ -431,6 +433,7 @@ static int dmatest_func(void *data)
 	ktime_t			comparetime = ktime_set(0, 0);
 	s64			runtime = 0;
 	unsigned long long	total_len = 0;
+	u8			align = 0;
 
 	set_freezable();
 
@@ -441,20 +444,24 @@ static int dmatest_func(void *data)
 	params = &info->params;
 	chan = thread->chan;
 	dev = chan->device;
-	if (thread->type == DMA_MEMCPY)
+	if (thread->type == DMA_MEMCPY) {
+		align = dev->copy_align;
 		src_cnt = dst_cnt = 1;
-	else if (thread->type == DMA_SG)
+	} else if (thread->type == DMA_SG) {
+		align = dev->copy_align;
 		src_cnt = dst_cnt = sg_buffers;
-	else if (thread->type == DMA_XOR) {
+	} else if (thread->type == DMA_XOR) {
 		/* force odd to ensure dst = src */
 		src_cnt = min_odd(params->xor_sources | 1, dev->max_xor);
 		dst_cnt = 1;
+		align = dev->xor_align;
 	} else if (thread->type == DMA_PQ) {
 		/* force odd to ensure dst = src */
 		src_cnt = min_odd(params->pq_sources | 1, dma_maxpq(dev, 0));
 		dst_cnt = 2;
+		align = dev->pq_align;
 
-		pq_coefs = kmalloc(params->pq_sources+1, GFP_KERNEL);
+		pq_coefs = kmalloc(params->pq_sources + 1, GFP_KERNEL);
 		if (!pq_coefs)
 			goto err_thread_type;
 
@@ -463,23 +470,47 @@ static int dmatest_func(void *data)
 	} else
 		goto err_thread_type;
 
-	thread->srcs = kcalloc(src_cnt+1, sizeof(u8 *), GFP_KERNEL);
+	thread->srcs = kcalloc(src_cnt + 1, sizeof(u8 *), GFP_KERNEL);
 	if (!thread->srcs)
 		goto err_srcs;
+
+	thread->usrcs = kcalloc(src_cnt + 1, sizeof(u8 *), GFP_KERNEL);
+	if (!thread->usrcs)
+		goto err_usrcs;
+
 	for (i = 0; i < src_cnt; i++) {
-		thread->srcs[i] = kmalloc(params->buf_size, GFP_KERNEL);
-		if (!thread->srcs[i])
+		thread->usrcs[i] = kmalloc(params->buf_size + align,
+					   GFP_KERNEL);
+		if (!thread->usrcs[i])
 			goto err_srcbuf;
+
+		/* align srcs to alignment restriction */
+		if (align)
+			thread->srcs[i] = PTR_ALIGN(thread->usrcs[i], align);
+		else
+			thread->srcs[i] = thread->usrcs[i];
 	}
 	thread->srcs[i] = NULL;
 
-	thread->dsts = kcalloc(dst_cnt+1, sizeof(u8 *), GFP_KERNEL);
+	thread->dsts = kcalloc(dst_cnt + 1, sizeof(u8 *), GFP_KERNEL);
 	if (!thread->dsts)
 		goto err_dsts;
+
+	thread->udsts = kcalloc(dst_cnt + 1, sizeof(u8 *), GFP_KERNEL);
+	if (!thread->udsts)
+		goto err_udsts;
+
 	for (i = 0; i < dst_cnt; i++) {
-		thread->dsts[i] = kmalloc(params->buf_size, GFP_KERNEL);
-		if (!thread->dsts[i])
+		thread->udsts[i] = kmalloc(params->buf_size + align,
+					   GFP_KERNEL);
+		if (!thread->udsts[i])
 			goto err_dstbuf;
+
+		/* align dsts to alignment restriction */
+		if (align)
+			thread->dsts[i] = PTR_ALIGN(thread->udsts[i], align);
+		else
+			thread->dsts[i] = thread->udsts[i];
 	}
 	thread->dsts[i] = NULL;
 
@@ -498,20 +529,11 @@ static int dmatest_func(void *data)
 		dma_addr_t srcs[src_cnt];
 		dma_addr_t *dsts;
 		unsigned int src_off, dst_off, len;
-		u8 align = 0;
 		struct scatterlist tx_sg[src_cnt];
 		struct scatterlist rx_sg[src_cnt];
 
 		total_tests++;
 
-		/* honor alignment restrictions */
-		if (thread->type == DMA_MEMCPY || thread->type == DMA_SG)
-			align = dev->copy_align;
-		else if (thread->type == DMA_XOR)
-			align = dev->xor_align;
-		else if (thread->type == DMA_PQ)
-			align = dev->pq_align;
-
 		if (1 << align > params->buf_size) {
 			pr_err("%u-byte buffer too small for %d-byte alignment\n",
 			       params->buf_size, 1 << align);
@@ -549,7 +571,7 @@ static int dmatest_func(void *data)
 			filltime = ktime_add(filltime, diff);
 		}
 
-		um = dmaengine_get_unmap_data(dev->dev, src_cnt+dst_cnt,
+		um = dmaengine_get_unmap_data(dev->dev, src_cnt + dst_cnt,
 					      GFP_KERNEL);
 		if (!um) {
 			failed_tests++;
@@ -729,13 +751,17 @@ static int dmatest_func(void *data)
 
 	ret = 0;
 err_dstbuf:
-	for (i = 0; thread->dsts[i]; i++)
-		kfree(thread->dsts[i]);
+	for (i = 0; thread->udsts[i]; i++)
+		kfree(thread->udsts[i]);
+	kfree(thread->udsts);
+err_udsts:
 	kfree(thread->dsts);
 err_dsts:
 err_srcbuf:
-	for (i = 0; thread->srcs[i]; i++)
-		kfree(thread->srcs[i]);
+	for (i = 0; thread->usrcs[i]; i++)
+		kfree(thread->usrcs[i]);
+	kfree(thread->usrcs);
+err_usrcs:
 	kfree(thread->srcs);
 err_srcs:
 	kfree(pq_coefs);
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index c2c0a61..e5adf5d 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -1569,7 +1569,7 @@ int dw_dma_probe(struct dw_dma_chip *chip)
 				(dwc_params >> DWC_PARAMS_MBLK_EN & 0x1) == 0;
 		} else {
 			dwc->block_size = pdata->block_size;
-			dwc->nollp = pdata->is_nollp;
+			dwc->nollp = !pdata->multi_block[i];
 		}
 	}
 
diff --git a/drivers/dma/dw/platform.c b/drivers/dma/dw/platform.c
index 5bda0eb..b1655e4 100644
--- a/drivers/dma/dw/platform.c
+++ b/drivers/dma/dw/platform.c
@@ -102,7 +102,7 @@ dw_dma_parse_dt(struct platform_device *pdev)
 {
 	struct device_node *np = pdev->dev.of_node;
 	struct dw_dma_platform_data *pdata;
-	u32 tmp, arr[DW_DMA_MAX_NR_MASTERS];
+	u32 tmp, arr[DW_DMA_MAX_NR_MASTERS], mb[DW_DMA_MAX_NR_CHANNELS];
 	u32 nr_masters;
 	u32 nr_channels;
 
@@ -118,6 +118,8 @@ dw_dma_parse_dt(struct platform_device *pdev)
 
 	if (of_property_read_u32(np, "dma-channels", &nr_channels))
 		return NULL;
+	if (nr_channels > DW_DMA_MAX_NR_CHANNELS)
+		return NULL;
 
 	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
 	if (!pdata)
@@ -129,6 +131,12 @@ dw_dma_parse_dt(struct platform_device *pdev)
 	if (of_property_read_bool(np, "is_private"))
 		pdata->is_private = true;
 
+	/*
+	 * All known devices, which use DT for configuration, support
+	 * memory-to-memory transfers. So enable it by default.
+	 */
+	pdata->is_memcpy = true;
+
 	if (!of_property_read_u32(np, "chan_allocation_order", &tmp))
 		pdata->chan_allocation_order = (unsigned char)tmp;
 
@@ -146,6 +154,14 @@ dw_dma_parse_dt(struct platform_device *pdev)
 			pdata->data_width[tmp] = BIT(arr[tmp] & 0x07);
 	}
 
+	if (!of_property_read_u32_array(np, "multi-block", mb, nr_channels)) {
+		for (tmp = 0; tmp < nr_channels; tmp++)
+			pdata->multi_block[tmp] = mb[tmp];
+	} else {
+		for (tmp = 0; tmp < nr_channels; tmp++)
+			pdata->multi_block[tmp] = 1;
+	}
+
 	return pdata;
 }
 #else
diff --git a/drivers/dma/dw/regs.h b/drivers/dma/dw/regs.h
index f65dd10..4e0128c 100644
--- a/drivers/dma/dw/regs.h
+++ b/drivers/dma/dw/regs.h
@@ -12,7 +12,8 @@
 #include <linux/interrupt.h>
 #include <linux/dmaengine.h>
 
-#define DW_DMA_MAX_NR_CHANNELS	8
+#include "internal.h"
+
 #define DW_DMA_MAX_NR_REQUESTS	16
 
 /* flow controller */
diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c
index 77242b3..3879f80 100644
--- a/drivers/dma/edma.c
+++ b/drivers/dma/edma.c
@@ -2451,6 +2451,9 @@ static int edma_pm_resume(struct device *dev)
 	int i;
 	s8 (*queue_priority_mapping)[2];
 
+	/* re initialize dummy slot to dummy param set */
+	edma_write_slot(ecc, ecc->dummy_slot, &dummy_paramset);
+
 	queue_priority_mapping = ecc->info->queue_priority_mapping;
 
 	/* Event queue priority mapping */
diff --git a/drivers/dma/fsl_raid.c b/drivers/dma/fsl_raid.c
index db2f9e1..90d29f9 100644
--- a/drivers/dma/fsl_raid.c
+++ b/drivers/dma/fsl_raid.c
@@ -881,6 +881,7 @@ static struct of_device_id fsl_re_ids[] = {
 	{ .compatible = "fsl,raideng-v1.0", },
 	{}
 };
+MODULE_DEVICE_TABLE(of, fsl_re_ids);
 
 static struct platform_driver fsl_re_driver = {
 	.driver = {
diff --git a/drivers/dma/hsu/pci.c b/drivers/dma/hsu/pci.c
index b51639f..4875fa4 100644
--- a/drivers/dma/hsu/pci.c
+++ b/drivers/dma/hsu/pci.c
@@ -77,13 +77,15 @@ static int hsu_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (!chip)
 		return -ENOMEM;
 
+	ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES);
+	if (ret < 0)
+		return ret;
+
 	chip->dev = &pdev->dev;
 	chip->regs = pcim_iomap_table(pdev)[0];
 	chip->length = pci_resource_len(pdev, 0);
 	chip->offset = HSU_PCI_CHAN_OFFSET;
-	chip->irq = pdev->irq;
-
-	pci_enable_msi(pdev);
+	chip->irq = pci_irq_vector(pdev, 0);
 
 	ret = hsu_dma_probe(chip);
 	if (ret)
diff --git a/drivers/dma/img-mdc-dma.c b/drivers/dma/img-mdc-dma.c
index 624f1e1..54db141 100644
--- a/drivers/dma/img-mdc-dma.c
+++ b/drivers/dma/img-mdc-dma.c
@@ -292,7 +292,7 @@ static struct dma_async_tx_descriptor *mdc_prep_dma_memcpy(
 	struct mdc_dma *mdma = mchan->mdma;
 	struct mdc_tx_desc *mdesc;
 	struct mdc_hw_list_desc *curr, *prev = NULL;
-	dma_addr_t curr_phys, prev_phys;
+	dma_addr_t curr_phys;
 
 	if (!len)
 		return NULL;
@@ -324,7 +324,6 @@ static struct dma_async_tx_descriptor *mdc_prep_dma_memcpy(
 				     xfer_size);
 
 		prev = curr;
-		prev_phys = curr_phys;
 
 		mdesc->list_len++;
 		src += xfer_size;
@@ -375,7 +374,7 @@ static struct dma_async_tx_descriptor *mdc_prep_dma_cyclic(
 	struct mdc_dma *mdma = mchan->mdma;
 	struct mdc_tx_desc *mdesc;
 	struct mdc_hw_list_desc *curr, *prev = NULL;
-	dma_addr_t curr_phys, prev_phys;
+	dma_addr_t curr_phys;
 
 	if (!buf_len && !period_len)
 		return NULL;
@@ -430,7 +429,6 @@ static struct dma_async_tx_descriptor *mdc_prep_dma_cyclic(
 			}
 
 			prev = curr;
-			prev_phys = curr_phys;
 
 			mdesc->list_len++;
 			buf_addr += xfer_size;
@@ -458,7 +456,7 @@ static struct dma_async_tx_descriptor *mdc_prep_slave_sg(
 	struct mdc_tx_desc *mdesc;
 	struct scatterlist *sg;
 	struct mdc_hw_list_desc *curr, *prev = NULL;
-	dma_addr_t curr_phys, prev_phys;
+	dma_addr_t curr_phys;
 	unsigned int i;
 
 	if (!sgl)
@@ -509,7 +507,6 @@ static struct dma_async_tx_descriptor *mdc_prep_slave_sg(
 			}
 
 			prev = curr;
-			prev_phys = curr_phys;
 
 			mdesc->list_len++;
 			mdesc->list_xfer_size += xfer_size;
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index b9629b2..d1651a5 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -298,6 +298,7 @@ struct sdma_engine;
  * @event_id1		for channels that use 2 events
  * @word_size		peripheral access size
  * @buf_tail		ID of the buffer that was processed
+ * @buf_ptail		ID of the previous buffer that was processed
  * @num_bd		max NUM_BD. number of descriptors currently handling
  */
 struct sdma_channel {
@@ -309,6 +310,7 @@ struct sdma_channel {
 	unsigned int			event_id1;
 	enum dma_slave_buswidth		word_size;
 	unsigned int			buf_tail;
+	unsigned int			buf_ptail;
 	unsigned int			num_bd;
 	unsigned int			period_len;
 	struct sdma_buffer_descriptor	*bd;
@@ -700,6 +702,8 @@ static void sdma_update_channel_loop(struct sdma_channel *sdmac)
 		sdmac->chn_real_count = bd->mode.count;
 		bd->mode.status |= BD_DONE;
 		bd->mode.count = sdmac->period_len;
+		sdmac->buf_ptail = sdmac->buf_tail;
+		sdmac->buf_tail = (sdmac->buf_tail + 1) % sdmac->num_bd;
 
 		/*
 		 * The callback is called from the interrupt context in order
@@ -710,9 +714,6 @@ static void sdma_update_channel_loop(struct sdma_channel *sdmac)
 
 		dmaengine_desc_get_callback_invoke(&sdmac->desc, NULL);
 
-		sdmac->buf_tail++;
-		sdmac->buf_tail %= sdmac->num_bd;
-
 		if (error)
 			sdmac->status = old_status;
 	}
@@ -1186,6 +1187,8 @@ static struct dma_async_tx_descriptor *sdma_prep_slave_sg(
 	sdmac->flags = 0;
 
 	sdmac->buf_tail = 0;
+	sdmac->buf_ptail = 0;
+	sdmac->chn_real_count = 0;
 
 	dev_dbg(sdma->dev, "setting up %d entries for channel %d.\n",
 			sg_len, channel);
@@ -1288,6 +1291,8 @@ static struct dma_async_tx_descriptor *sdma_prep_dma_cyclic(
 	sdmac->status = DMA_IN_PROGRESS;
 
 	sdmac->buf_tail = 0;
+	sdmac->buf_ptail = 0;
+	sdmac->chn_real_count = 0;
 	sdmac->period_len = period_len;
 
 	sdmac->flags |= IMX_DMA_SG_LOOP;
@@ -1385,7 +1390,7 @@ static enum dma_status sdma_tx_status(struct dma_chan *chan,
 	u32 residue;
 
 	if (sdmac->flags & IMX_DMA_SG_LOOP)
-		residue = (sdmac->num_bd - sdmac->buf_tail) *
+		residue = (sdmac->num_bd - sdmac->buf_ptail) *
 			   sdmac->period_len - sdmac->chn_real_count;
 	else
 		residue = sdmac->chn_count - sdmac->chn_real_count;
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index 49386ce0..a371b07 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -39,6 +39,7 @@
 #include "../dmaengine.h"
 
 static char *chanerr_str[] = {
+	"DMA Transfer Source Address Error",
 	"DMA Transfer Destination Address Error",
 	"Next Descriptor Address Error",
 	"Descriptor Error",
@@ -66,7 +67,6 @@ static char *chanerr_str[] = {
 	"Result Guard Tag verification Error",
 	"Result Application Tag verification Error",
 	"Result Reference Tag verification Error",
-	NULL
 };
 
 static void ioat_eh(struct ioatdma_chan *ioat_chan);
@@ -75,13 +75,10 @@ static void ioat_print_chanerrs(struct ioatdma_chan *ioat_chan, u32 chanerr)
 {
 	int i;
 
-	for (i = 0; i < 32; i++) {
+	for (i = 0; i < ARRAY_SIZE(chanerr_str); i++) {
 		if ((chanerr >> i) & 1) {
-			if (chanerr_str[i]) {
-				dev_err(to_dev(ioat_chan), "Err(%d): %s\n",
-					i, chanerr_str[i]);
-			} else
-				break;
+			dev_err(to_dev(ioat_chan), "Err(%d): %s\n",
+				i, chanerr_str[i]);
 		}
 	}
 }
@@ -341,15 +338,12 @@ ioat_alloc_ring_ent(struct dma_chan *chan, int idx, gfp_t flags)
 {
 	struct ioat_dma_descriptor *hw;
 	struct ioat_ring_ent *desc;
-	struct ioatdma_device *ioat_dma;
 	struct ioatdma_chan *ioat_chan = to_ioat_chan(chan);
 	int chunk;
 	dma_addr_t phys;
 	u8 *pos;
 	off_t offs;
 
-	ioat_dma = to_ioatdma_device(chan->device);
-
 	chunk = idx / IOAT_DESCS_PER_2M;
 	idx &= (IOAT_DESCS_PER_2M - 1);
 	offs = idx * IOAT_DESC_SZ;
@@ -614,11 +608,8 @@ static void __cleanup(struct ioatdma_chan *ioat_chan, dma_addr_t phys_complete)
 
 		tx = &desc->txd;
 		if (tx->cookie) {
-			struct dmaengine_result res;
-
 			dma_cookie_complete(tx);
 			dma_descriptor_unmap(tx);
-			res.result = DMA_TRANS_NOERROR;
 			dmaengine_desc_get_callback_invoke(tx, NULL);
 			tx->callback = NULL;
 			tx->callback_result = NULL;
diff --git a/drivers/dma/ioat/init.c b/drivers/dma/ioat/init.c
index 015f711..90eddd9 100644
--- a/drivers/dma/ioat/init.c
+++ b/drivers/dma/ioat/init.c
@@ -340,11 +340,13 @@ static int ioat_dma_self_test(struct ioatdma_device *ioat_dma)
 	dma_src = dma_map_single(dev, src, IOAT_TEST_SIZE, DMA_TO_DEVICE);
 	if (dma_mapping_error(dev, dma_src)) {
 		dev_err(dev, "mapping src buffer failed\n");
+		err = -ENOMEM;
 		goto free_resources;
 	}
 	dma_dest = dma_map_single(dev, dest, IOAT_TEST_SIZE, DMA_FROM_DEVICE);
 	if (dma_mapping_error(dev, dma_dest)) {
 		dev_err(dev, "mapping dest buffer failed\n");
+		err = -ENOMEM;
 		goto unmap_src;
 	}
 	flags = DMA_PREP_INTERRUPT;
@@ -827,16 +829,20 @@ static int ioat_xor_val_self_test(struct ioatdma_device *ioat_dma)
 	op = IOAT_OP_XOR;
 
 	dest_dma = dma_map_page(dev, dest, 0, PAGE_SIZE, DMA_FROM_DEVICE);
-	if (dma_mapping_error(dev, dest_dma))
+	if (dma_mapping_error(dev, dest_dma)) {
+		err = -ENOMEM;
 		goto free_resources;
+	}
 
 	for (i = 0; i < IOAT_NUM_SRC_TEST; i++)
 		dma_srcs[i] = DMA_ERROR_CODE;
 	for (i = 0; i < IOAT_NUM_SRC_TEST; i++) {
 		dma_srcs[i] = dma_map_page(dev, xor_srcs[i], 0, PAGE_SIZE,
 					   DMA_TO_DEVICE);
-		if (dma_mapping_error(dev, dma_srcs[i]))
+		if (dma_mapping_error(dev, dma_srcs[i])) {
+			err = -ENOMEM;
 			goto dma_unmap;
+		}
 	}
 	tx = dma->device_prep_dma_xor(dma_chan, dest_dma, dma_srcs,
 				      IOAT_NUM_SRC_TEST, PAGE_SIZE,
@@ -904,8 +910,10 @@ static int ioat_xor_val_self_test(struct ioatdma_device *ioat_dma)
 	for (i = 0; i < IOAT_NUM_SRC_TEST + 1; i++) {
 		dma_srcs[i] = dma_map_page(dev, xor_val_srcs[i], 0, PAGE_SIZE,
 					   DMA_TO_DEVICE);
-		if (dma_mapping_error(dev, dma_srcs[i]))
+		if (dma_mapping_error(dev, dma_srcs[i])) {
+			err = -ENOMEM;
 			goto dma_unmap;
+		}
 	}
 	tx = dma->device_prep_dma_xor_val(dma_chan, dma_srcs,
 					  IOAT_NUM_SRC_TEST + 1, PAGE_SIZE,
@@ -957,8 +965,10 @@ static int ioat_xor_val_self_test(struct ioatdma_device *ioat_dma)
 	for (i = 0; i < IOAT_NUM_SRC_TEST + 1; i++) {
 		dma_srcs[i] = dma_map_page(dev, xor_val_srcs[i], 0, PAGE_SIZE,
 					   DMA_TO_DEVICE);
-		if (dma_mapping_error(dev, dma_srcs[i]))
+		if (dma_mapping_error(dev, dma_srcs[i])) {
+			err = -ENOMEM;
 			goto dma_unmap;
+		}
 	}
 	tx = dma->device_prep_dma_xor_val(dma_chan, dma_srcs,
 					  IOAT_NUM_SRC_TEST + 1, PAGE_SIZE,
@@ -1071,7 +1081,6 @@ static int ioat3_dma_probe(struct ioatdma_device *ioat_dma, int dca)
 	struct dma_device *dma;
 	struct dma_chan *c;
 	struct ioatdma_chan *ioat_chan;
-	bool is_raid_device = false;
 	int err;
 	u16 val16;
 
@@ -1095,7 +1104,6 @@ static int ioat3_dma_probe(struct ioatdma_device *ioat_dma, int dca)
 		ioat_dma->cap &= ~(IOAT_CAP_XOR|IOAT_CAP_PQ);
 
 	if (ioat_dma->cap & IOAT_CAP_XOR) {
-		is_raid_device = true;
 		dma->max_xor = 8;
 
 		dma_cap_set(DMA_XOR, dma->cap_mask);
@@ -1106,7 +1114,6 @@ static int ioat3_dma_probe(struct ioatdma_device *ioat_dma, int dca)
 	}
 
 	if (ioat_dma->cap & IOAT_CAP_PQ) {
-		is_raid_device = true;
 
 		dma->device_prep_dma_pq = ioat_prep_pq;
 		dma->device_prep_dma_pq_val = ioat_prep_pq_val;
diff --git a/drivers/dma/k3dma.c b/drivers/dma/k3dma.c
index aabcb79..01e25c6 100644
--- a/drivers/dma/k3dma.c
+++ b/drivers/dma/k3dma.c
@@ -458,13 +458,12 @@ static struct k3_dma_desc_sw *k3_dma_alloc_desc_resource(int num,
 	if (!ds)
 		return NULL;
 
-	ds->desc_hw = dma_pool_alloc(d->pool, GFP_NOWAIT, &ds->desc_hw_lli);
+	ds->desc_hw = dma_pool_zalloc(d->pool, GFP_NOWAIT, &ds->desc_hw_lli);
 	if (!ds->desc_hw) {
 		dev_dbg(chan->device->dev, "vch %p: dma alloc fail\n", &c->vc);
 		kfree(ds);
 		return NULL;
 	}
-	memset(ds->desc_hw, 0, sizeof(struct k3_desc_hw) * num);
 	ds->desc_num = num;
 	return ds;
 }
diff --git a/drivers/dma/mic_x100_dma.c b/drivers/dma/mic_x100_dma.c
index 8182558..5ba5714 100644
--- a/drivers/dma/mic_x100_dma.c
+++ b/drivers/dma/mic_x100_dma.c
@@ -554,9 +554,7 @@ static int mic_dma_init(struct mic_dma_device *mic_dma_dev,
 	int ret;
 
 	for (i = first_chan; i < first_chan + MIC_DMA_NUM_CHAN; i++) {
-		unsigned long data;
 		ch = &mic_dma_dev->mic_ch[i];
-		data = (unsigned long)ch;
 		ch->ch_num = i;
 		ch->owner = owner;
 		spin_lock_init(&ch->cleanup_lock);
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index 23f7528..0cb951b 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -68,6 +68,36 @@ static void mv_desc_init(struct mv_xor_desc_slot *desc,
 	hw_desc->byte_count = byte_count;
 }
 
+/* Populate the descriptor */
+static void mv_xor_config_sg_ll_desc(struct mv_xor_desc_slot *desc,
+				     dma_addr_t dma_src, dma_addr_t dma_dst,
+				     u32 len, struct mv_xor_desc_slot *prev)
+{
+	struct mv_xor_desc *hw_desc = desc->hw_desc;
+
+	hw_desc->status = XOR_DESC_DMA_OWNED;
+	hw_desc->phy_next_desc = 0;
+	/* Configure for XOR with only one src address -> MEMCPY */
+	hw_desc->desc_command = XOR_DESC_OPERATION_XOR | (0x1 << 0);
+	hw_desc->phy_dest_addr = dma_dst;
+	hw_desc->phy_src_addr[0] = dma_src;
+	hw_desc->byte_count = len;
+
+	if (prev) {
+		struct mv_xor_desc *hw_prev = prev->hw_desc;
+
+		hw_prev->phy_next_desc = desc->async_tx.phys;
+	}
+}
+
+static void mv_xor_desc_config_eod(struct mv_xor_desc_slot *desc)
+{
+	struct mv_xor_desc *hw_desc = desc->hw_desc;
+
+	/* Enable end-of-descriptor interrupt */
+	hw_desc->desc_command |= XOR_DESC_EOD_INT_EN;
+}
+
 static void mv_desc_set_mode(struct mv_xor_desc_slot *desc)
 {
 	struct mv_xor_desc *hw_desc = desc->hw_desc;
@@ -228,8 +258,13 @@ mv_chan_clean_completed_slots(struct mv_xor_chan *mv_chan)
 	list_for_each_entry_safe(iter, _iter, &mv_chan->completed_slots,
 				 node) {
 
-		if (async_tx_test_ack(&iter->async_tx))
+		if (async_tx_test_ack(&iter->async_tx)) {
 			list_move_tail(&iter->node, &mv_chan->free_slots);
+			if (!list_empty(&iter->sg_tx_list)) {
+				list_splice_tail_init(&iter->sg_tx_list,
+							&mv_chan->free_slots);
+			}
+		}
 	}
 	return 0;
 }
@@ -244,11 +279,20 @@ mv_desc_clean_slot(struct mv_xor_desc_slot *desc,
 	/* the client is allowed to attach dependent operations
 	 * until 'ack' is set
 	 */
-	if (!async_tx_test_ack(&desc->async_tx))
+	if (!async_tx_test_ack(&desc->async_tx)) {
 		/* move this slot to the completed_slots */
 		list_move_tail(&desc->node, &mv_chan->completed_slots);
-	else
+		if (!list_empty(&desc->sg_tx_list)) {
+			list_splice_tail_init(&desc->sg_tx_list,
+					      &mv_chan->completed_slots);
+		}
+	} else {
 		list_move_tail(&desc->node, &mv_chan->free_slots);
+		if (!list_empty(&desc->sg_tx_list)) {
+			list_splice_tail_init(&desc->sg_tx_list,
+					      &mv_chan->free_slots);
+		}
+	}
 
 	return 0;
 }
@@ -450,6 +494,7 @@ static int mv_xor_alloc_chan_resources(struct dma_chan *chan)
 		dma_async_tx_descriptor_init(&slot->async_tx, chan);
 		slot->async_tx.tx_submit = mv_xor_tx_submit;
 		INIT_LIST_HEAD(&slot->node);
+		INIT_LIST_HEAD(&slot->sg_tx_list);
 		dma_desc = mv_chan->dma_desc_pool;
 		slot->async_tx.phys = dma_desc + idx * MV_XOR_SLOT_SIZE;
 		slot->idx = idx++;
@@ -617,6 +662,132 @@ mv_xor_prep_dma_interrupt(struct dma_chan *chan, unsigned long flags)
 	return mv_xor_prep_dma_xor(chan, dest, &src, 1, len, flags);
 }
 
+/**
+ * mv_xor_prep_dma_sg - prepare descriptors for a memory sg transaction
+ * @chan: DMA channel
+ * @dst_sg: Destination scatter list
+ * @dst_sg_len: Number of entries in destination scatter list
+ * @src_sg: Source scatter list
+ * @src_sg_len: Number of entries in source scatter list
+ * @flags: transfer ack flags
+ *
+ * Return: Async transaction descriptor on success and NULL on failure
+ */
+static struct dma_async_tx_descriptor *
+mv_xor_prep_dma_sg(struct dma_chan *chan, struct scatterlist *dst_sg,
+		   unsigned int dst_sg_len, struct scatterlist *src_sg,
+		   unsigned int src_sg_len, unsigned long flags)
+{
+	struct mv_xor_chan *mv_chan = to_mv_xor_chan(chan);
+	struct mv_xor_desc_slot *new;
+	struct mv_xor_desc_slot *first = NULL;
+	struct mv_xor_desc_slot *prev = NULL;
+	size_t len, dst_avail, src_avail;
+	dma_addr_t dma_dst, dma_src;
+	int desc_cnt = 0;
+	int ret;
+
+	dev_dbg(mv_chan_to_devp(mv_chan),
+		"%s dst_sg_len: %d src_sg_len: %d flags: %ld\n",
+		__func__, dst_sg_len, src_sg_len, flags);
+
+	dst_avail = sg_dma_len(dst_sg);
+	src_avail = sg_dma_len(src_sg);
+
+	/* Run until we are out of scatterlist entries */
+	while (true) {
+		/* Allocate and populate the descriptor */
+		desc_cnt++;
+		new = mv_chan_alloc_slot(mv_chan);
+		if (!new) {
+			dev_err(mv_chan_to_devp(mv_chan),
+				"Out of descriptors (desc_cnt=%d)!\n",
+				desc_cnt);
+			goto err;
+		}
+
+		len = min_t(size_t, src_avail, dst_avail);
+		len = min_t(size_t, len, MV_XOR_MAX_BYTE_COUNT);
+		if (len == 0)
+			goto fetch;
+
+		if (len < MV_XOR_MIN_BYTE_COUNT) {
+			dev_err(mv_chan_to_devp(mv_chan),
+				"Transfer size of %zu too small!\n", len);
+			goto err;
+		}
+
+		dma_dst = sg_dma_address(dst_sg) + sg_dma_len(dst_sg) -
+			dst_avail;
+		dma_src = sg_dma_address(src_sg) + sg_dma_len(src_sg) -
+			src_avail;
+
+		/* Check if a new window needs to get added for 'dst' */
+		ret = mv_xor_add_io_win(mv_chan, dma_dst);
+		if (ret)
+			goto err;
+
+		/* Check if a new window needs to get added for 'src' */
+		ret = mv_xor_add_io_win(mv_chan, dma_src);
+		if (ret)
+			goto err;
+
+		/* Populate the descriptor */
+		mv_xor_config_sg_ll_desc(new, dma_src, dma_dst, len, prev);
+		prev = new;
+		dst_avail -= len;
+		src_avail -= len;
+
+		if (!first)
+			first = new;
+		else
+			list_move_tail(&new->node, &first->sg_tx_list);
+
+fetch:
+		/* Fetch the next dst scatterlist entry */
+		if (dst_avail == 0) {
+			if (dst_sg_len == 0)
+				break;
+
+			/* Fetch the next entry: if there are no more: done */
+			dst_sg = sg_next(dst_sg);
+			if (dst_sg == NULL)
+				break;
+
+			dst_sg_len--;
+			dst_avail = sg_dma_len(dst_sg);
+		}
+
+		/* Fetch the next src scatterlist entry */
+		if (src_avail == 0) {
+			if (src_sg_len == 0)
+				break;
+
+			/* Fetch the next entry: if there are no more: done */
+			src_sg = sg_next(src_sg);
+			if (src_sg == NULL)
+				break;
+
+			src_sg_len--;
+			src_avail = sg_dma_len(src_sg);
+		}
+	}
+
+	/* Set the EOD flag in the last descriptor */
+	mv_xor_desc_config_eod(new);
+	first->async_tx.flags = flags;
+
+	return &first->async_tx;
+
+err:
+	/* Cleanup: Move all descriptors back into the free list */
+	spin_lock_bh(&mv_chan->lock);
+	mv_desc_clean_slot(first, mv_chan);
+	spin_unlock_bh(&mv_chan->lock);
+
+	return NULL;
+}
+
 static void mv_xor_free_chan_resources(struct dma_chan *chan)
 {
 	struct mv_xor_chan *mv_chan = to_mv_xor_chan(chan);
@@ -1083,6 +1254,8 @@ mv_xor_channel_add(struct mv_xor_device *xordev,
 		dma_dev->device_prep_dma_interrupt = mv_xor_prep_dma_interrupt;
 	if (dma_has_cap(DMA_MEMCPY, dma_dev->cap_mask))
 		dma_dev->device_prep_dma_memcpy = mv_xor_prep_dma_memcpy;
+	if (dma_has_cap(DMA_SG, dma_dev->cap_mask))
+		dma_dev->device_prep_dma_sg = mv_xor_prep_dma_sg;
 	if (dma_has_cap(DMA_XOR, dma_dev->cap_mask)) {
 		dma_dev->max_xor = 8;
 		dma_dev->device_prep_dma_xor = mv_xor_prep_dma_xor;
@@ -1132,10 +1305,11 @@ mv_xor_channel_add(struct mv_xor_device *xordev,
 			goto err_free_irq;
 	}
 
-	dev_info(&pdev->dev, "Marvell XOR (%s): ( %s%s%s)\n",
+	dev_info(&pdev->dev, "Marvell XOR (%s): ( %s%s%s%s)\n",
 		 mv_chan->op_in_desc ? "Descriptor Mode" : "Registers Mode",
 		 dma_has_cap(DMA_XOR, dma_dev->cap_mask) ? "xor " : "",
 		 dma_has_cap(DMA_MEMCPY, dma_dev->cap_mask) ? "cpy " : "",
+		 dma_has_cap(DMA_SG, dma_dev->cap_mask) ? "sg " : "",
 		 dma_has_cap(DMA_INTERRUPT, dma_dev->cap_mask) ? "intr " : "");
 
 	dma_async_device_register(dma_dev);
@@ -1378,6 +1552,7 @@ static int mv_xor_probe(struct platform_device *pdev)
 
 			dma_cap_zero(cap_mask);
 			dma_cap_set(DMA_MEMCPY, cap_mask);
+			dma_cap_set(DMA_SG, cap_mask);
 			dma_cap_set(DMA_XOR, cap_mask);
 			dma_cap_set(DMA_INTERRUPT, cap_mask);
 
@@ -1455,12 +1630,7 @@ static struct platform_driver mv_xor_driver = {
 	},
 };
 
-
-static int __init mv_xor_init(void)
-{
-	return platform_driver_register(&mv_xor_driver);
-}
-device_initcall(mv_xor_init);
+builtin_platform_driver(mv_xor_driver);
 
 /*
 MODULE_AUTHOR("Saeed Bishara <saeed@marvell.com>");
diff --git a/drivers/dma/mv_xor.h b/drivers/dma/mv_xor.h
index 88eeab2..cf921dd 100644
--- a/drivers/dma/mv_xor.h
+++ b/drivers/dma/mv_xor.h
@@ -148,6 +148,7 @@ struct mv_xor_chan {
  */
 struct mv_xor_desc_slot {
 	struct list_head	node;
+	struct list_head	sg_tx_list;
 	enum dma_transaction_type	type;
 	void			*hw_desc;
 	u16			idx;
diff --git a/drivers/dma/nbpfaxi.c b/drivers/dma/nbpfaxi.c
index 09de715..3f45b9b 100644
--- a/drivers/dma/nbpfaxi.c
+++ b/drivers/dma/nbpfaxi.c
@@ -225,6 +225,8 @@ struct nbpf_channel {
 struct nbpf_device {
 	struct dma_device dma_dev;
 	void __iomem *base;
+	u32 max_burst_mem_read;
+	u32 max_burst_mem_write;
 	struct clk *clk;
 	const struct nbpf_config *config;
 	unsigned int eirq;
@@ -425,10 +427,33 @@ static void nbpf_chan_configure(struct nbpf_channel *chan)
 	nbpf_chan_write(chan, NBPF_CHAN_CFG, NBPF_CHAN_CFG_DMS | chan->dmarq_cfg);
 }
 
-static u32 nbpf_xfer_ds(struct nbpf_device *nbpf, size_t size)
+static u32 nbpf_xfer_ds(struct nbpf_device *nbpf, size_t size,
+			enum dma_transfer_direction direction)
 {
+	int max_burst = nbpf->config->buffer_size * 8;
+
+	if (nbpf->max_burst_mem_read || nbpf->max_burst_mem_write) {
+		switch (direction) {
+		case DMA_MEM_TO_MEM:
+			max_burst = min_not_zero(nbpf->max_burst_mem_read,
+						 nbpf->max_burst_mem_write);
+			break;
+		case DMA_MEM_TO_DEV:
+			if (nbpf->max_burst_mem_read)
+				max_burst = nbpf->max_burst_mem_read;
+			break;
+		case DMA_DEV_TO_MEM:
+			if (nbpf->max_burst_mem_write)
+				max_burst = nbpf->max_burst_mem_write;
+			break;
+		case DMA_DEV_TO_DEV:
+		default:
+			break;
+		}
+	}
+
 	/* Maximum supported bursts depend on the buffer size */
-	return min_t(int, __ffs(size), ilog2(nbpf->config->buffer_size * 8));
+	return min_t(int, __ffs(size), ilog2(max_burst));
 }
 
 static size_t nbpf_xfer_size(struct nbpf_device *nbpf,
@@ -458,7 +483,7 @@ static size_t nbpf_xfer_size(struct nbpf_device *nbpf,
 		size = burst;
 	}
 
-	return nbpf_xfer_ds(nbpf, size);
+	return nbpf_xfer_ds(nbpf, size, DMA_TRANS_NONE);
 }
 
 /*
@@ -507,7 +532,7 @@ static int nbpf_prep_one(struct nbpf_link_desc *ldesc,
 	 * transfers we enable the SBE bit and terminate the transfer in our
 	 * .device_pause handler.
 	 */
-	mem_xfer = nbpf_xfer_ds(chan->nbpf, size);
+	mem_xfer = nbpf_xfer_ds(chan->nbpf, size, direction);
 
 	switch (direction) {
 	case DMA_DEV_TO_MEM:
@@ -1313,6 +1338,11 @@ static int nbpf_probe(struct platform_device *pdev)
 	if (IS_ERR(nbpf->clk))
 		return PTR_ERR(nbpf->clk);
 
+	of_property_read_u32(np, "max-burst-mem-read",
+			     &nbpf->max_burst_mem_read);
+	of_property_read_u32(np, "max-burst-mem-write",
+			     &nbpf->max_burst_mem_write);
+
 	nbpf->config = cfg;
 
 	for (i = 0; irqs < ARRAY_SIZE(irqbuf); i++) {
diff --git a/drivers/dma/omap-dma.c b/drivers/dma/omap-dma.c
index 7ca27d4..ac68666 100644
--- a/drivers/dma/omap-dma.c
+++ b/drivers/dma/omap-dma.c
@@ -166,6 +166,9 @@ enum {
 	CSDP_DST_BURST_16	= 1 << 14,
 	CSDP_DST_BURST_32	= 2 << 14,
 	CSDP_DST_BURST_64	= 3 << 14,
+	CSDP_WRITE_NON_POSTED	= 0 << 16,
+	CSDP_WRITE_POSTED	= 1 << 16,
+	CSDP_WRITE_LAST_NON_POSTED = 2 << 16,
 
 	CICR_TOUT_IE		= BIT(0),	/* OMAP1 only */
 	CICR_DROP_IE		= BIT(1),
@@ -422,7 +425,30 @@ static void omap_dma_start(struct omap_chan *c, struct omap_desc *d)
 	c->running = true;
 }
 
-static void omap_dma_stop(struct omap_chan *c)
+static void omap_dma_drain_chan(struct omap_chan *c)
+{
+	int i;
+	u32 val;
+
+	/* Wait for sDMA FIFO to drain */
+	for (i = 0; ; i++) {
+		val = omap_dma_chan_read(c, CCR);
+		if (!(val & (CCR_RD_ACTIVE | CCR_WR_ACTIVE)))
+			break;
+
+		if (i > 100)
+			break;
+
+		udelay(5);
+	}
+
+	if (val & (CCR_RD_ACTIVE | CCR_WR_ACTIVE))
+		dev_err(c->vc.chan.device->dev,
+			"DMA drain did not complete on lch %d\n",
+			c->dma_ch);
+}
+
+static int omap_dma_stop(struct omap_chan *c)
 {
 	struct omap_dmadev *od = to_omap_dma_dev(c->vc.chan.device);
 	uint32_t val;
@@ -435,7 +461,6 @@ static void omap_dma_stop(struct omap_chan *c)
 	val = omap_dma_chan_read(c, CCR);
 	if (od->plat->errata & DMA_ERRATA_i541 && val & CCR_TRIGGER_SRC) {
 		uint32_t sysconfig;
-		unsigned i;
 
 		sysconfig = omap_dma_glbl_read(od, OCP_SYSCONFIG);
 		val = sysconfig & ~DMA_SYSCONFIG_MIDLEMODE_MASK;
@@ -446,27 +471,19 @@ static void omap_dma_stop(struct omap_chan *c)
 		val &= ~CCR_ENABLE;
 		omap_dma_chan_write(c, CCR, val);
 
-		/* Wait for sDMA FIFO to drain */
-		for (i = 0; ; i++) {
-			val = omap_dma_chan_read(c, CCR);
-			if (!(val & (CCR_RD_ACTIVE | CCR_WR_ACTIVE)))
-				break;
-
-			if (i > 100)
-				break;
-
-			udelay(5);
-		}
-
-		if (val & (CCR_RD_ACTIVE | CCR_WR_ACTIVE))
-			dev_err(c->vc.chan.device->dev,
-				"DMA drain did not complete on lch %d\n",
-			        c->dma_ch);
+		if (!(c->ccr & CCR_BUFFERING_DISABLE))
+			omap_dma_drain_chan(c);
 
 		omap_dma_glbl_write(od, OCP_SYSCONFIG, sysconfig);
 	} else {
+		if (!(val & CCR_ENABLE))
+			return -EINVAL;
+
 		val &= ~CCR_ENABLE;
 		omap_dma_chan_write(c, CCR, val);
+
+		if (!(c->ccr & CCR_BUFFERING_DISABLE))
+			omap_dma_drain_chan(c);
 	}
 
 	mb();
@@ -481,8 +498,8 @@ static void omap_dma_stop(struct omap_chan *c)
 
 		omap_dma_chan_write(c, CLNK_CTRL, val);
 	}
-
 	c->running = false;
+	return 0;
 }
 
 static void omap_dma_start_sg(struct omap_chan *c, struct omap_desc *d)
@@ -836,6 +853,8 @@ static enum dma_status omap_dma_tx_status(struct dma_chan *chan,
 	} else {
 		txstate->residue = 0;
 	}
+	if (ret == DMA_IN_PROGRESS && c->paused)
+		ret = DMA_PAUSED;
 	spin_unlock_irqrestore(&c->vc.lock, flags);
 
 	return ret;
@@ -865,15 +884,18 @@ static struct dma_async_tx_descriptor *omap_dma_prep_slave_sg(
 	unsigned i, es, en, frame_bytes;
 	bool ll_failed = false;
 	u32 burst;
+	u32 port_window, port_window_bytes;
 
 	if (dir == DMA_DEV_TO_MEM) {
 		dev_addr = c->cfg.src_addr;
 		dev_width = c->cfg.src_addr_width;
 		burst = c->cfg.src_maxburst;
+		port_window = c->cfg.src_port_window_size;
 	} 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;
+		port_window = c->cfg.dst_port_window_size;
 	} else {
 		dev_err(chan->device->dev, "%s: bad direction?\n", __func__);
 		return NULL;
@@ -894,6 +916,12 @@ static struct dma_async_tx_descriptor *omap_dma_prep_slave_sg(
 		return NULL;
 	}
 
+	/* When the port_window is used, one frame must cover the window */
+	if (port_window) {
+		burst = port_window;
+		port_window_bytes = port_window * es_bytes[es];
+	}
+
 	/* Now allocate and setup the descriptor. */
 	d = kzalloc(sizeof(*d) + sglen * sizeof(d->sg[0]), GFP_ATOMIC);
 	if (!d)
@@ -905,11 +933,45 @@ static struct dma_async_tx_descriptor *omap_dma_prep_slave_sg(
 
 	d->ccr = c->ccr | CCR_SYNC_FRAME;
 	if (dir == DMA_DEV_TO_MEM) {
-		d->ccr |= CCR_DST_AMODE_POSTINC | CCR_SRC_AMODE_CONSTANT;
 		d->csdp = CSDP_DST_BURST_64 | CSDP_DST_PACKED;
+
+		d->ccr |= CCR_DST_AMODE_POSTINC;
+		if (port_window) {
+			d->ccr |= CCR_SRC_AMODE_DBLIDX;
+			d->ei = 1;
+			/*
+			 * One frame covers the port_window and by  configure
+			 * the source frame index to be -1 * (port_window - 1)
+			 * we instruct the sDMA that after a frame is processed
+			 * it should move back to the start of the window.
+			 */
+			d->fi = -(port_window_bytes - 1);
+
+			if (port_window_bytes >= 64)
+				d->csdp = CSDP_SRC_BURST_64 | CSDP_SRC_PACKED;
+			else if (port_window_bytes >= 32)
+				d->csdp = CSDP_SRC_BURST_32 | CSDP_SRC_PACKED;
+			else if (port_window_bytes >= 16)
+				d->csdp = CSDP_SRC_BURST_16 | CSDP_SRC_PACKED;
+		} else {
+			d->ccr |= CCR_SRC_AMODE_CONSTANT;
+		}
 	} else {
-		d->ccr |= CCR_DST_AMODE_CONSTANT | CCR_SRC_AMODE_POSTINC;
 		d->csdp = CSDP_SRC_BURST_64 | CSDP_SRC_PACKED;
+
+		d->ccr |= CCR_SRC_AMODE_POSTINC;
+		if (port_window) {
+			d->ccr |= CCR_DST_AMODE_DBLIDX;
+
+			if (port_window_bytes >= 64)
+				d->csdp = CSDP_DST_BURST_64 | CSDP_DST_PACKED;
+			else if (port_window_bytes >= 32)
+				d->csdp = CSDP_DST_BURST_32 | CSDP_DST_PACKED;
+			else if (port_window_bytes >= 16)
+				d->csdp = CSDP_DST_BURST_16 | CSDP_DST_PACKED;
+		} else {
+			d->ccr |= CCR_DST_AMODE_CONSTANT;
+		}
 	}
 
 	d->cicr = CICR_DROP_IE | CICR_BLOCK_IE;
@@ -927,6 +989,9 @@ static struct dma_async_tx_descriptor *omap_dma_prep_slave_sg(
 			d->ccr |= CCR_TRIGGER_SRC;
 
 		d->cicr |= CICR_MISALIGNED_ERR_IE | CICR_TRANS_ERR_IE;
+
+		if (port_window)
+			d->csdp |= CSDP_WRITE_LAST_NON_POSTED;
 	}
 	if (od->plat->errata & DMA_ERRATA_PARALLEL_CHANNELS)
 		d->clnk_ctrl = c->dma_ch;
@@ -952,6 +1017,16 @@ static struct dma_async_tx_descriptor *omap_dma_prep_slave_sg(
 		osg->addr = sg_dma_address(sgent);
 		osg->en = en;
 		osg->fn = sg_dma_len(sgent) / frame_bytes;
+		if (port_window && dir == DMA_MEM_TO_DEV) {
+			osg->ei = 1;
+			/*
+			 * One frame covers the port_window and by  configure
+			 * the source frame index to be -1 * (port_window - 1)
+			 * we instruct the sDMA that after a frame is processed
+			 * it should move back to the start of the window.
+			 */
+			osg->fi = -(port_window_bytes - 1);
+		}
 
 		if (d->using_ll) {
 			osg->t2_desc = dma_pool_alloc(od->desc_pool, GFP_ATOMIC,
@@ -1247,10 +1322,8 @@ static int omap_dma_terminate_all(struct dma_chan *chan)
 			omap_dma_stop(c);
 	}
 
-	if (c->cyclic) {
-		c->cyclic = false;
-		c->paused = false;
-	}
+	c->cyclic = false;
+	c->paused = false;
 
 	vchan_get_all_descriptors(&c->vc, &head);
 	spin_unlock_irqrestore(&c->vc.lock, flags);
@@ -1269,28 +1342,66 @@ static void omap_dma_synchronize(struct dma_chan *chan)
 static int omap_dma_pause(struct dma_chan *chan)
 {
 	struct omap_chan *c = to_omap_dma_chan(chan);
+	struct omap_dmadev *od = to_omap_dma_dev(chan->device);
+	unsigned long flags;
+	int ret = -EINVAL;
+	bool can_pause = false;
 
-	/* Pause/Resume only allowed with cyclic mode */
-	if (!c->cyclic)
-		return -EINVAL;
+	spin_lock_irqsave(&od->irq_lock, flags);
 
-	if (!c->paused) {
-		omap_dma_stop(c);
-		c->paused = true;
+	if (!c->desc)
+		goto out;
+
+	if (c->cyclic)
+		can_pause = true;
+
+	/*
+	 * We do not allow DMA_MEM_TO_DEV transfers to be paused.
+	 * From the AM572x TRM, 16.1.4.18 Disabling a Channel During Transfer:
+	 * "When a channel is disabled during a transfer, the channel undergoes
+	 * an abort, unless it is hardware-source-synchronized …".
+	 * A source-synchronised channel is one where the fetching of data is
+	 * under control of the device. In other words, a device-to-memory
+	 * transfer. So, a destination-synchronised channel (which would be a
+	 * memory-to-device transfer) undergoes an abort if the the CCR_ENABLE
+	 * bit is cleared.
+	 * From 16.1.4.20.4.6.2 Abort: "If an abort trigger occurs, the channel
+	 * aborts immediately after completion of current read/write
+	 * transactions and then the FIFO is cleaned up." The term "cleaned up"
+	 * is not defined. TI recommends to check that RD_ACTIVE and WR_ACTIVE
+	 * are both clear _before_ disabling the channel, otherwise data loss
+	 * will occur.
+	 * The problem is that if the channel is active, then device activity
+	 * can result in DMA activity starting between reading those as both
+	 * clear and the write to DMA_CCR to clear the enable bit hitting the
+	 * hardware. If the DMA hardware can't drain the data in its FIFO to the
+	 * destination, then data loss "might" occur (say if we write to an UART
+	 * and the UART is not accepting any further data).
+	 */
+	else if (c->desc->dir == DMA_DEV_TO_MEM)
+		can_pause = true;
+
+	if (can_pause && !c->paused) {
+		ret = omap_dma_stop(c);
+		if (!ret)
+			c->paused = true;
 	}
+out:
+	spin_unlock_irqrestore(&od->irq_lock, flags);
 
-	return 0;
+	return ret;
 }
 
 static int omap_dma_resume(struct dma_chan *chan)
 {
 	struct omap_chan *c = to_omap_dma_chan(chan);
+	struct omap_dmadev *od = to_omap_dma_dev(chan->device);
+	unsigned long flags;
+	int ret = -EINVAL;
 
-	/* Pause/Resume only allowed with cyclic mode */
-	if (!c->cyclic)
-		return -EINVAL;
+	spin_lock_irqsave(&od->irq_lock, flags);
 
-	if (c->paused) {
+	if (c->paused && c->desc) {
 		mb();
 
 		/* Restore channel link register */
@@ -1298,9 +1409,11 @@ static int omap_dma_resume(struct dma_chan *chan)
 
 		omap_dma_start(c, c->desc);
 		c->paused = false;
+		ret = 0;
 	}
+	spin_unlock_irqrestore(&od->irq_lock, flags);
 
-	return 0;
+	return ret;
 }
 
 static int omap_dma_chan_init(struct omap_dmadev *od)
diff --git a/drivers/dma/pch_dma.c b/drivers/dma/pch_dma.c
index df95727d..f9028e9 100644
--- a/drivers/dma/pch_dma.c
+++ b/drivers/dma/pch_dma.c
@@ -417,10 +417,8 @@ static dma_cookie_t pd_tx_submit(struct dma_async_tx_descriptor *txd)
 {
 	struct pch_dma_desc *desc = to_pd_desc(txd);
 	struct pch_dma_chan *pd_chan = to_pd_chan(txd->chan);
-	dma_cookie_t cookie;
 
 	spin_lock(&pd_chan->lock);
-	cookie = dma_cookie_assign(txd);
 
 	if (list_empty(&pd_chan->active_list)) {
 		list_add_tail(&desc->desc_node, &pd_chan->active_list);
@@ -439,9 +437,8 @@ static struct pch_dma_desc *pdc_alloc_desc(struct dma_chan *chan, gfp_t flags)
 	struct pch_dma *pd = to_pd(chan->device);
 	dma_addr_t addr;
 
-	desc = pci_pool_alloc(pd->pool, flags, &addr);
+	desc = pci_pool_zalloc(pd->pool, flags, &addr);
 	if (desc) {
-		memset(desc, 0, sizeof(struct pch_dma_desc));
 		INIT_LIST_HEAD(&desc->tx_list);
 		dma_async_tx_descriptor_init(&desc->txd, chan);
 		desc->txd.tx_submit = pd_tx_submit;
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index 030fe05..87fd015 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -570,7 +570,8 @@ static inline u32 _emit_ADDH(unsigned dry_run, u8 buf[],
 
 	buf[0] = CMD_DMAADDH;
 	buf[0] |= (da << 1);
-	*((__le16 *)&buf[1]) = cpu_to_le16(val);
+	buf[1] = val;
+	buf[2] = val >> 8;
 
 	PL330_DBGCMD_DUMP(SZ_DMAADDH, "\tDMAADDH %s %u\n",
 		da == 1 ? "DA" : "SA", val);
@@ -724,7 +725,10 @@ static inline u32 _emit_MOV(unsigned dry_run, u8 buf[],
 
 	buf[0] = CMD_DMAMOV;
 	buf[1] = dst;
-	*((__le32 *)&buf[2]) = cpu_to_le32(val);
+	buf[2] = val;
+	buf[3] = val >> 8;
+	buf[4] = val >> 16;
+	buf[5] = val >> 24;
 
 	PL330_DBGCMD_DUMP(SZ_DMAMOV, "\tDMAMOV %s 0x%x\n",
 		dst == SAR ? "SAR" : (dst == DAR ? "DAR" : "CCR"), val);
@@ -899,10 +903,11 @@ static inline u32 _emit_GO(unsigned dry_run, u8 buf[],
 
 	buf[0] = CMD_DMAGO;
 	buf[0] |= (ns << 1);
-
 	buf[1] = chan & 0x7;
-
-	*((__le32 *)&buf[2]) = cpu_to_le32(addr);
+	buf[2] = addr;
+	buf[3] = addr >> 8;
+	buf[4] = addr >> 16;
+	buf[5] = addr >> 24;
 
 	return SZ_DMAGO;
 }
@@ -1883,11 +1888,8 @@ static int dmac_alloc_resources(struct pl330_dmac *pl330)
 
 static int pl330_add(struct pl330_dmac *pl330)
 {
-	void __iomem *regs;
 	int i, ret;
 
-	regs = pl330->base;
-
 	/* Check if we can handle this DMAC */
 	if ((pl330->pcfg.periph_id & 0xfffff) != PERIPH_ID_VAL) {
 		dev_err(pl330->ddma.dev, "PERIPH_ID 0x%x !\n",
@@ -2263,6 +2265,11 @@ static int pl330_get_current_xferred_count(struct dma_pl330_chan *pch,
 	}
 	pm_runtime_mark_last_busy(pch->dmac->ddma.dev);
 	pm_runtime_put_autosuspend(pl330->ddma.dev);
+
+	/* If DMAMOV hasn't finished yet, SAR/DAR can be zero */
+	if (!val)
+		return 0;
+
 	return val - addr;
 }
 
diff --git a/drivers/dma/pxa_dma.c b/drivers/dma/pxa_dma.c
index 3f56f9c..b53fb61 100644
--- a/drivers/dma/pxa_dma.c
+++ b/drivers/dma/pxa_dma.c
@@ -413,15 +413,6 @@ static inline void pxad_init_debugfs(struct pxad_device *pdev) {}
 static inline void pxad_cleanup_debugfs(struct pxad_device *pdev) {}
 #endif
 
-/*
- * In the transition phase where legacy pxa handling is done at the same time as
- * mmp_dma, the DMA physical channel split between the 2 DMA providers is done
- * through legacy_reserved. Legacy code reserves DMA channels by settings
- * corresponding bits in legacy_reserved.
- */
-static u32 legacy_reserved;
-static u32 legacy_unavailable;
-
 static struct pxad_phy *lookup_phy(struct pxad_chan *pchan)
 {
 	int prio, i;
@@ -442,14 +433,10 @@ static struct pxad_phy *lookup_phy(struct pxad_chan *pchan)
 		for (i = 0; i < pdev->nr_chans; i++) {
 			if (prio != (i & 0xf) >> 2)
 				continue;
-			if ((i < 32) && (legacy_reserved & BIT(i)))
-				continue;
 			phy = &pdev->phys[i];
 			if (!phy->vchan) {
 				phy->vchan = pchan;
 				found = phy;
-				if (i < 32)
-					legacy_unavailable |= BIT(i);
 				goto out_unlock;
 			}
 		}
@@ -469,7 +456,6 @@ static void pxad_free_phy(struct pxad_chan *chan)
 	struct pxad_device *pdev = to_pxad_dev(chan->vc.chan.device);
 	unsigned long flags;
 	u32 reg;
-	int i;
 
 	dev_dbg(&chan->vc.chan.dev->device,
 		"%s(): freeing\n", __func__);
@@ -483,9 +469,6 @@ static void pxad_free_phy(struct pxad_chan *chan)
 	}
 
 	spin_lock_irqsave(&pdev->phy_lock, flags);
-	for (i = 0; i < 32; i++)
-		if (chan->phy == &pdev->phys[i])
-			legacy_unavailable &= ~BIT(i);
 	chan->phy->vchan = NULL;
 	chan->phy = NULL;
 	spin_unlock_irqrestore(&pdev->phy_lock, flags);
@@ -739,8 +722,6 @@ static irqreturn_t pxad_int_handler(int irq, void *dev_id)
 		i = __ffs(dint);
 		dint &= (dint - 1);
 		phy = &pdev->phys[i];
-		if ((i < 32) && (legacy_reserved & BIT(i)))
-			continue;
 		if (pxad_chan_handler(irq, phy) == IRQ_HANDLED)
 			ret = IRQ_HANDLED;
 	}
@@ -1522,15 +1503,6 @@ bool pxad_filter_fn(struct dma_chan *chan, void *param)
 }
 EXPORT_SYMBOL_GPL(pxad_filter_fn);
 
-int pxad_toggle_reserved_channel(int legacy_channel)
-{
-	if (legacy_unavailable & (BIT(legacy_channel)))
-		return -EBUSY;
-	legacy_reserved ^= BIT(legacy_channel);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(pxad_toggle_reserved_channel);
-
 module_platform_driver(pxad_driver);
 
 MODULE_DESCRIPTION("Marvell PXA Peripheral DMA Driver");
diff --git a/drivers/dma/qcom/hidma.c b/drivers/dma/qcom/hidma.c
index e244e10..3c982c9 100644
--- a/drivers/dma/qcom/hidma.c
+++ b/drivers/dma/qcom/hidma.c
@@ -56,6 +56,7 @@
 #include <linux/irq.h>
 #include <linux/atomic.h>
 #include <linux/pm_runtime.h>
+#include <linux/msi.h>
 
 #include "../dmaengine.h"
 #include "hidma.h"
@@ -70,6 +71,7 @@
 #define HIDMA_ERR_INFO_SW			0xFF
 #define HIDMA_ERR_CODE_UNEXPECTED_TERMINATE	0x0
 #define HIDMA_NR_DEFAULT_DESC			10
+#define HIDMA_MSI_INTS				11
 
 static inline struct hidma_dev *to_hidma_dev(struct dma_device *dmadev)
 {
@@ -553,6 +555,17 @@ static irqreturn_t hidma_chirq_handler(int chirq, void *arg)
 	return hidma_ll_inthandler(chirq, lldev);
 }
 
+#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN
+static irqreturn_t hidma_chirq_handler_msi(int chirq, void *arg)
+{
+	struct hidma_lldev **lldevp = arg;
+	struct hidma_dev *dmadev = to_hidma_dev_from_lldev(lldevp);
+
+	return hidma_ll_inthandler_msi(chirq, *lldevp,
+				       1 << (chirq - dmadev->msi_virqbase));
+}
+#endif
+
 static ssize_t hidma_show_values(struct device *dev,
 				 struct device_attribute *attr, char *buf)
 {
@@ -567,8 +580,13 @@ static ssize_t hidma_show_values(struct device *dev,
 	return strlen(buf);
 }
 
-static int hidma_create_sysfs_entry(struct hidma_dev *dev, char *name,
-				    int mode)
+static inline void  hidma_sysfs_uninit(struct hidma_dev *dev)
+{
+	device_remove_file(dev->ddev.dev, dev->chid_attrs);
+}
+
+static struct device_attribute*
+hidma_create_sysfs_entry(struct hidma_dev *dev, char *name, int mode)
 {
 	struct device_attribute *attrs;
 	char *name_copy;
@@ -576,18 +594,125 @@ static int hidma_create_sysfs_entry(struct hidma_dev *dev, char *name,
 	attrs = devm_kmalloc(dev->ddev.dev, sizeof(struct device_attribute),
 			     GFP_KERNEL);
 	if (!attrs)
-		return -ENOMEM;
+		return NULL;
 
 	name_copy = devm_kstrdup(dev->ddev.dev, name, GFP_KERNEL);
 	if (!name_copy)
-		return -ENOMEM;
+		return NULL;
 
 	attrs->attr.name = name_copy;
 	attrs->attr.mode = mode;
 	attrs->show = hidma_show_values;
 	sysfs_attr_init(&attrs->attr);
 
-	return device_create_file(dev->ddev.dev, attrs);
+	return attrs;
+}
+
+static int hidma_sysfs_init(struct hidma_dev *dev)
+{
+	dev->chid_attrs = hidma_create_sysfs_entry(dev, "chid", S_IRUGO);
+	if (!dev->chid_attrs)
+		return -ENOMEM;
+
+	return device_create_file(dev->ddev.dev, dev->chid_attrs);
+}
+
+#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN
+static void hidma_write_msi_msg(struct msi_desc *desc, struct msi_msg *msg)
+{
+	struct device *dev = msi_desc_to_dev(desc);
+	struct hidma_dev *dmadev = dev_get_drvdata(dev);
+
+	if (!desc->platform.msi_index) {
+		writel(msg->address_lo, dmadev->dev_evca + 0x118);
+		writel(msg->address_hi, dmadev->dev_evca + 0x11C);
+		writel(msg->data, dmadev->dev_evca + 0x120);
+	}
+}
+#endif
+
+static void hidma_free_msis(struct hidma_dev *dmadev)
+{
+#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN
+	struct device *dev = dmadev->ddev.dev;
+	struct msi_desc *desc;
+
+	/* free allocated MSI interrupts above */
+	for_each_msi_entry(desc, dev)
+		devm_free_irq(dev, desc->irq, &dmadev->lldev);
+
+	platform_msi_domain_free_irqs(dev);
+#endif
+}
+
+static int hidma_request_msi(struct hidma_dev *dmadev,
+			     struct platform_device *pdev)
+{
+#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN
+	int rc;
+	struct msi_desc *desc;
+	struct msi_desc *failed_desc = NULL;
+
+	rc = platform_msi_domain_alloc_irqs(&pdev->dev, HIDMA_MSI_INTS,
+					    hidma_write_msi_msg);
+	if (rc)
+		return rc;
+
+	for_each_msi_entry(desc, &pdev->dev) {
+		if (!desc->platform.msi_index)
+			dmadev->msi_virqbase = desc->irq;
+
+		rc = devm_request_irq(&pdev->dev, desc->irq,
+				       hidma_chirq_handler_msi,
+				       0, "qcom-hidma-msi",
+				       &dmadev->lldev);
+		if (rc) {
+			failed_desc = desc;
+			break;
+		}
+	}
+
+	if (rc) {
+		/* free allocated MSI interrupts above */
+		for_each_msi_entry(desc, &pdev->dev) {
+			if (desc == failed_desc)
+				break;
+			devm_free_irq(&pdev->dev, desc->irq,
+				      &dmadev->lldev);
+		}
+	} else {
+		/* Add callback to free MSIs on teardown */
+		hidma_ll_setup_irq(dmadev->lldev, true);
+
+	}
+	if (rc)
+		dev_warn(&pdev->dev,
+			 "failed to request MSI irq, falling back to wired IRQ\n");
+	return rc;
+#else
+	return -EINVAL;
+#endif
+}
+
+static bool hidma_msi_capable(struct device *dev)
+{
+	struct acpi_device *adev = ACPI_COMPANION(dev);
+	const char *of_compat;
+	int ret = -EINVAL;
+
+	if (!adev || acpi_disabled) {
+		ret = device_property_read_string(dev, "compatible",
+						  &of_compat);
+		if (ret)
+			return false;
+
+		ret = strcmp(of_compat, "qcom,hidma-1.1");
+	} else {
+#ifdef CONFIG_ACPI
+		ret = strcmp(acpi_device_hid(adev), "QCOM8062");
+#endif
+	}
+	return ret == 0;
 }
 
 static int hidma_probe(struct platform_device *pdev)
@@ -599,6 +724,7 @@ static int hidma_probe(struct platform_device *pdev)
 	void __iomem *evca;
 	void __iomem *trca;
 	int rc;
+	bool msi;
 
 	pm_runtime_set_autosuspend_delay(&pdev->dev, HIDMA_AUTOSUSPEND_TIMEOUT);
 	pm_runtime_use_autosuspend(&pdev->dev);
@@ -660,6 +786,12 @@ static int hidma_probe(struct platform_device *pdev)
 	dmadev->ddev.device_terminate_all = hidma_terminate_all;
 	dmadev->ddev.copy_align = 8;
 
+	/*
+	 * Determine the MSI capability of the platform. Old HW doesn't
+	 * support MSI.
+	 */
+	msi = hidma_msi_capable(&pdev->dev);
+
 	device_property_read_u32(&pdev->dev, "desc-count",
 				 &dmadev->nr_descriptors);
 
@@ -688,10 +820,17 @@ static int hidma_probe(struct platform_device *pdev)
 		goto dmafree;
 	}
 
-	rc = devm_request_irq(&pdev->dev, chirq, hidma_chirq_handler, 0,
-			      "qcom-hidma", dmadev->lldev);
-	if (rc)
-		goto uninit;
+	platform_set_drvdata(pdev, dmadev);
+	if (msi)
+		rc = hidma_request_msi(dmadev, pdev);
+
+	if (!msi || rc) {
+		hidma_ll_setup_irq(dmadev->lldev, false);
+		rc = devm_request_irq(&pdev->dev, chirq, hidma_chirq_handler,
+				      0, "qcom-hidma", dmadev->lldev);
+		if (rc)
+			goto uninit;
+	}
 
 	INIT_LIST_HEAD(&dmadev->ddev.channels);
 	rc = hidma_chan_init(dmadev, 0);
@@ -705,14 +844,16 @@ static int hidma_probe(struct platform_device *pdev)
 	dmadev->irq = chirq;
 	tasklet_init(&dmadev->task, hidma_issue_task, (unsigned long)dmadev);
 	hidma_debug_init(dmadev);
-	hidma_create_sysfs_entry(dmadev, "chid", S_IRUGO);
+	hidma_sysfs_init(dmadev);
 	dev_info(&pdev->dev, "HI-DMA engine driver registration complete\n");
-	platform_set_drvdata(pdev, dmadev);
 	pm_runtime_mark_last_busy(dmadev->ddev.dev);
 	pm_runtime_put_autosuspend(dmadev->ddev.dev);
 	return 0;
 
 uninit:
+	if (msi)
+		hidma_free_msis(dmadev);
+
 	hidma_debug_uninit(dmadev);
 	hidma_ll_uninit(dmadev->lldev);
 dmafree:
@@ -730,8 +871,13 @@ static int hidma_remove(struct platform_device *pdev)
 
 	pm_runtime_get_sync(dmadev->ddev.dev);
 	dma_async_device_unregister(&dmadev->ddev);
-	devm_free_irq(dmadev->ddev.dev, dmadev->irq, dmadev->lldev);
+	if (!dmadev->lldev->msi_support)
+		devm_free_irq(dmadev->ddev.dev, dmadev->irq, dmadev->lldev);
+	else
+		hidma_free_msis(dmadev);
+
 	tasklet_kill(&dmadev->task);
+	hidma_sysfs_uninit(dmadev);
 	hidma_debug_uninit(dmadev);
 	hidma_ll_uninit(dmadev->lldev);
 	hidma_free(dmadev);
@@ -746,12 +892,15 @@ static int hidma_remove(struct platform_device *pdev)
 #if IS_ENABLED(CONFIG_ACPI)
 static const struct acpi_device_id hidma_acpi_ids[] = {
 	{"QCOM8061"},
+	{"QCOM8062"},
 	{},
 };
+MODULE_DEVICE_TABLE(acpi, hidma_acpi_ids);
 #endif
 
 static const struct of_device_id hidma_match[] = {
 	{.compatible = "qcom,hidma-1.0",},
+	{.compatible = "qcom,hidma-1.1",},
 	{},
 };
 MODULE_DEVICE_TABLE(of, hidma_match);
diff --git a/drivers/dma/qcom/hidma.h b/drivers/dma/qcom/hidma.h
index e52e207..c7d0142 100644
--- a/drivers/dma/qcom/hidma.h
+++ b/drivers/dma/qcom/hidma.h
@@ -46,6 +46,7 @@ struct hidma_tre {
 };
 
 struct hidma_lldev {
+	bool msi_support;		/* flag indicating MSI support    */
 	bool initialized;		/* initialized flag               */
 	u8 trch_state;			/* trch_state of the device	  */
 	u8 evch_state;			/* evch_state of the device	  */
@@ -58,7 +59,7 @@ struct hidma_lldev {
 	void __iomem *evca;		/* Event Channel address          */
 	struct hidma_tre
 		**pending_tre_list;	/* Pointers to pending TREs	  */
-	s32 pending_tre_count;		/* Number of TREs pending	  */
+	atomic_t pending_tre_count;	/* Number of TREs pending	  */
 
 	void *tre_ring;			/* TRE ring			  */
 	dma_addr_t tre_dma;		/* TRE ring to be shared with HW  */
@@ -114,6 +115,7 @@ struct hidma_dev {
 	int				irq;
 	int				chidx;
 	u32				nr_descriptors;
+	int				msi_virqbase;
 
 	struct hidma_lldev		*lldev;
 	void				__iomem *dev_trca;
@@ -128,6 +130,9 @@ struct hidma_dev {
 	struct dentry			*debugfs;
 	struct dentry			*stats;
 
+	/* sysfs entry for the channel id */
+	struct device_attribute		*chid_attrs;
+
 	/* Task delivering issue_pending */
 	struct tasklet_struct		task;
 };
@@ -145,12 +150,14 @@ int hidma_ll_disable(struct hidma_lldev *lldev);
 int hidma_ll_enable(struct hidma_lldev *llhndl);
 void hidma_ll_set_transfer_params(struct hidma_lldev *llhndl, u32 tre_ch,
 	dma_addr_t src, dma_addr_t dest, u32 len, u32 flags);
+void hidma_ll_setup_irq(struct hidma_lldev *lldev, bool msi);
 int hidma_ll_setup(struct hidma_lldev *lldev);
 struct hidma_lldev *hidma_ll_init(struct device *dev, u32 max_channels,
 			void __iomem *trca, void __iomem *evca,
 			u8 chidx);
 int hidma_ll_uninit(struct hidma_lldev *llhndl);
 irqreturn_t hidma_ll_inthandler(int irq, void *arg);
+irqreturn_t hidma_ll_inthandler_msi(int irq, void *arg, int cause);
 void hidma_cleanup_pending_tre(struct hidma_lldev *llhndl, u8 err_info,
 				u8 err_code);
 int hidma_debug_init(struct hidma_dev *dmadev);
diff --git a/drivers/dma/qcom/hidma_dbg.c b/drivers/dma/qcom/hidma_dbg.c
index fa827e5..3bdcb80 100644
--- a/drivers/dma/qcom/hidma_dbg.c
+++ b/drivers/dma/qcom/hidma_dbg.c
@@ -74,7 +74,8 @@ static void hidma_ll_devstats(struct seq_file *s, void *llhndl)
 	seq_printf(s, "tre_ring_handle=%pap\n", &lldev->tre_dma);
 	seq_printf(s, "tre_ring_size = 0x%x\n", lldev->tre_ring_size);
 	seq_printf(s, "tre_processed_off = 0x%x\n", lldev->tre_processed_off);
-	seq_printf(s, "pending_tre_count=%d\n", lldev->pending_tre_count);
+	seq_printf(s, "pending_tre_count=%d\n",
+			atomic_read(&lldev->pending_tre_count));
 	seq_printf(s, "evca=%p\n", lldev->evca);
 	seq_printf(s, "evre_ring=%p\n", lldev->evre_ring);
 	seq_printf(s, "evre_ring_handle=%pap\n", &lldev->evre_dma);
@@ -164,7 +165,6 @@ static const struct file_operations hidma_dma_fops = {
 void hidma_debug_uninit(struct hidma_dev *dmadev)
 {
 	debugfs_remove_recursive(dmadev->debugfs);
-	debugfs_remove_recursive(dmadev->stats);
 }
 
 int hidma_debug_init(struct hidma_dev *dmadev)
diff --git a/drivers/dma/qcom/hidma_ll.c b/drivers/dma/qcom/hidma_ll.c
index 3224f24..6645bdf 100644
--- a/drivers/dma/qcom/hidma_ll.c
+++ b/drivers/dma/qcom/hidma_ll.c
@@ -198,13 +198,16 @@ static void hidma_ll_tre_complete(unsigned long arg)
 	}
 }
 
-static int hidma_post_completed(struct hidma_lldev *lldev, int tre_iterator,
-				u8 err_info, u8 err_code)
+static int hidma_post_completed(struct hidma_lldev *lldev, u8 err_info,
+				u8 err_code)
 {
 	struct hidma_tre *tre;
 	unsigned long flags;
+	u32 tre_iterator;
 
 	spin_lock_irqsave(&lldev->lock, flags);
+
+	tre_iterator = lldev->tre_processed_off;
 	tre = lldev->pending_tre_list[tre_iterator / HIDMA_TRE_SIZE];
 	if (!tre) {
 		spin_unlock_irqrestore(&lldev->lock, flags);
@@ -218,12 +221,14 @@ static int hidma_post_completed(struct hidma_lldev *lldev, int tre_iterator,
 	 * Keep track of pending TREs that SW is expecting to receive
 	 * from HW. We got one now. Decrement our counter.
 	 */
-	lldev->pending_tre_count--;
-	if (lldev->pending_tre_count < 0) {
+	if (atomic_dec_return(&lldev->pending_tre_count) < 0) {
 		dev_warn(lldev->dev, "tre count mismatch on completion");
-		lldev->pending_tre_count = 0;
+		atomic_set(&lldev->pending_tre_count, 0);
 	}
 
+	HIDMA_INCREMENT_ITERATOR(tre_iterator, HIDMA_TRE_SIZE,
+				 lldev->tre_ring_size);
+	lldev->tre_processed_off = tre_iterator;
 	spin_unlock_irqrestore(&lldev->lock, flags);
 
 	tre->err_info = err_info;
@@ -245,13 +250,11 @@ static int hidma_post_completed(struct hidma_lldev *lldev, int tre_iterator,
 static int hidma_handle_tre_completion(struct hidma_lldev *lldev)
 {
 	u32 evre_ring_size = lldev->evre_ring_size;
-	u32 tre_ring_size = lldev->tre_ring_size;
 	u32 err_info, err_code, evre_write_off;
-	u32 tre_iterator, evre_iterator;
+	u32 evre_iterator;
 	u32 num_completed = 0;
 
 	evre_write_off = readl_relaxed(lldev->evca + HIDMA_EVCA_WRITE_PTR_REG);
-	tre_iterator = lldev->tre_processed_off;
 	evre_iterator = lldev->evre_processed_off;
 
 	if ((evre_write_off > evre_ring_size) ||
@@ -274,12 +277,9 @@ static int hidma_handle_tre_completion(struct hidma_lldev *lldev)
 		err_code =
 		    (cfg >> HIDMA_EVRE_CODE_BIT_POS) & HIDMA_EVRE_CODE_MASK;
 
-		if (hidma_post_completed(lldev, tre_iterator, err_info,
-					 err_code))
+		if (hidma_post_completed(lldev, err_info, err_code))
 			break;
 
-		HIDMA_INCREMENT_ITERATOR(tre_iterator, HIDMA_TRE_SIZE,
-					 tre_ring_size);
 		HIDMA_INCREMENT_ITERATOR(evre_iterator, HIDMA_EVRE_SIZE,
 					 evre_ring_size);
 
@@ -291,21 +291,22 @@ static int hidma_handle_tre_completion(struct hidma_lldev *lldev)
 		evre_write_off =
 		    readl_relaxed(lldev->evca + HIDMA_EVCA_WRITE_PTR_REG);
 		num_completed++;
+
+		/*
+		 * An error interrupt might have arrived while we are processing
+		 * the completed interrupt.
+		 */
+		if (!hidma_ll_isenabled(lldev))
+			break;
 	}
 
 	if (num_completed) {
 		u32 evre_read_off = (lldev->evre_processed_off +
 				     HIDMA_EVRE_SIZE * num_completed);
-		u32 tre_read_off = (lldev->tre_processed_off +
-				    HIDMA_TRE_SIZE * num_completed);
-
 		evre_read_off = evre_read_off % evre_ring_size;
-		tre_read_off = tre_read_off % tre_ring_size;
-
 		writel(evre_read_off, lldev->evca + HIDMA_EVCA_DOORBELL_REG);
 
 		/* record the last processed tre offset */
-		lldev->tre_processed_off = tre_read_off;
 		lldev->evre_processed_off = evre_read_off;
 	}
 
@@ -315,27 +316,10 @@ static int hidma_handle_tre_completion(struct hidma_lldev *lldev)
 void hidma_cleanup_pending_tre(struct hidma_lldev *lldev, u8 err_info,
 			       u8 err_code)
 {
-	u32 tre_iterator;
-	u32 tre_ring_size = lldev->tre_ring_size;
-	int num_completed = 0;
-	u32 tre_read_off;
-
-	tre_iterator = lldev->tre_processed_off;
-	while (lldev->pending_tre_count) {
-		if (hidma_post_completed(lldev, tre_iterator, err_info,
-					 err_code))
+	while (atomic_read(&lldev->pending_tre_count)) {
+		if (hidma_post_completed(lldev, err_info, err_code))
 			break;
-		HIDMA_INCREMENT_ITERATOR(tre_iterator, HIDMA_TRE_SIZE,
-					 tre_ring_size);
-		num_completed++;
 	}
-	tre_read_off = (lldev->tre_processed_off +
-			HIDMA_TRE_SIZE * num_completed);
-
-	tre_read_off = tre_read_off % tre_ring_size;
-
-	/* record the last processed tre offset */
-	lldev->tre_processed_off = tre_read_off;
 }
 
 static int hidma_ll_reset(struct hidma_lldev *lldev)
@@ -412,12 +396,24 @@ static int hidma_ll_reset(struct hidma_lldev *lldev)
  * requests traditionally to the destination, this concept does not apply
  * here for this HW.
  */
-irqreturn_t hidma_ll_inthandler(int chirq, void *arg)
+static void hidma_ll_int_handler_internal(struct hidma_lldev *lldev, int cause)
 {
-	struct hidma_lldev *lldev = arg;
-	u32 status;
-	u32 enable;
-	u32 cause;
+	if (cause & HIDMA_ERR_INT_MASK) {
+		dev_err(lldev->dev, "error 0x%x, disabling...\n",
+				cause);
+
+		/* Clear out pending interrupts */
+		writel(cause, lldev->evca + HIDMA_EVCA_IRQ_CLR_REG);
+
+		/* No further submissions. */
+		hidma_ll_disable(lldev);
+
+		/* Driver completes the txn and intimates the client.*/
+		hidma_cleanup_pending_tre(lldev, 0xFF,
+					  HIDMA_EVRE_STATUS_ERROR);
+
+		return;
+	}
 
 	/*
 	 * Fine tuned for this HW...
@@ -426,35 +422,28 @@ irqreturn_t hidma_ll_inthandler(int chirq, void *arg)
 	 * read and write accessors are used for performance reasons due to
 	 * interrupt delivery guarantees. Do not copy this code blindly and
 	 * expect that to work.
+	 *
+	 * Try to consume as many EVREs as possible.
 	 */
+	hidma_handle_tre_completion(lldev);
+
+	/* We consumed TREs or there are pending TREs or EVREs. */
+	writel_relaxed(cause, lldev->evca + HIDMA_EVCA_IRQ_CLR_REG);
+}
+
+irqreturn_t hidma_ll_inthandler(int chirq, void *arg)
+{
+	struct hidma_lldev *lldev = arg;
+	u32 status;
+	u32 enable;
+	u32 cause;
+
 	status = readl_relaxed(lldev->evca + HIDMA_EVCA_IRQ_STAT_REG);
 	enable = readl_relaxed(lldev->evca + HIDMA_EVCA_IRQ_EN_REG);
 	cause = status & enable;
 
 	while (cause) {
-		if (cause & HIDMA_ERR_INT_MASK) {
-			dev_err(lldev->dev, "error 0x%x, disabling...\n",
-					cause);
-
-			/* Clear out pending interrupts */
-			writel(cause, lldev->evca + HIDMA_EVCA_IRQ_CLR_REG);
-
-			/* No further submissions. */
-			hidma_ll_disable(lldev);
-
-			/* Driver completes the txn and intimates the client.*/
-			hidma_cleanup_pending_tre(lldev, 0xFF,
-						  HIDMA_EVRE_STATUS_ERROR);
-			goto out;
-		}
-
-		/*
-		 * Try to consume as many EVREs as possible.
-		 */
-		hidma_handle_tre_completion(lldev);
-
-		/* We consumed TREs or there are pending TREs or EVREs. */
-		writel_relaxed(cause, lldev->evca + HIDMA_EVCA_IRQ_CLR_REG);
+		hidma_ll_int_handler_internal(lldev, cause);
 
 		/*
 		 * Another interrupt might have arrived while we are
@@ -465,7 +454,14 @@ irqreturn_t hidma_ll_inthandler(int chirq, void *arg)
 		cause = status & enable;
 	}
 
-out:
+	return IRQ_HANDLED;
+}
+
+irqreturn_t hidma_ll_inthandler_msi(int chirq, void *arg, int cause)
+{
+	struct hidma_lldev *lldev = arg;
+
+	hidma_ll_int_handler_internal(lldev, cause);
 	return IRQ_HANDLED;
 }
 
@@ -548,7 +544,7 @@ void hidma_ll_queue_request(struct hidma_lldev *lldev, u32 tre_ch)
 	tre->err_code = 0;
 	tre->err_info = 0;
 	tre->queued = 1;
-	lldev->pending_tre_count++;
+	atomic_inc(&lldev->pending_tre_count);
 	lldev->tre_write_offset = (lldev->tre_write_offset + HIDMA_TRE_SIZE)
 					% lldev->tre_ring_size;
 	spin_unlock_irqrestore(&lldev->lock, flags);
@@ -564,19 +560,8 @@ int hidma_ll_disable(struct hidma_lldev *lldev)
 	u32 val;
 	int ret;
 
-	val = readl(lldev->evca + HIDMA_EVCA_CTRLSTS_REG);
-	lldev->evch_state = HIDMA_CH_STATE(val);
-	val = readl(lldev->trca + HIDMA_TRCA_CTRLSTS_REG);
-	lldev->trch_state = HIDMA_CH_STATE(val);
-
-	/* already suspended by this OS */
-	if ((lldev->trch_state == HIDMA_CH_SUSPENDED) ||
-	    (lldev->evch_state == HIDMA_CH_SUSPENDED))
-		return 0;
-
-	/* already stopped by the manager */
-	if ((lldev->trch_state == HIDMA_CH_STOPPED) ||
-	    (lldev->evch_state == HIDMA_CH_STOPPED))
+	/* The channel needs to be in working state */
+	if (!hidma_ll_isenabled(lldev))
 		return 0;
 
 	val = readl(lldev->trca + HIDMA_TRCA_CTRLSTS_REG);
@@ -654,7 +639,7 @@ int hidma_ll_setup(struct hidma_lldev *lldev)
 	u32 val;
 	u32 nr_tres = lldev->nr_tres;
 
-	lldev->pending_tre_count = 0;
+	atomic_set(&lldev->pending_tre_count, 0);
 	lldev->tre_processed_off = 0;
 	lldev->evre_processed_off = 0;
 	lldev->tre_write_offset = 0;
@@ -691,17 +676,36 @@ int hidma_ll_setup(struct hidma_lldev *lldev)
 	writel(HIDMA_EVRE_SIZE * nr_tres,
 			lldev->evca + HIDMA_EVCA_RING_LEN_REG);
 
-	/* support IRQ only for now */
+	/* configure interrupts */
+	hidma_ll_setup_irq(lldev, lldev->msi_support);
+
+	rc = hidma_ll_enable(lldev);
+	if (rc)
+		return rc;
+
+	return rc;
+}
+
+void hidma_ll_setup_irq(struct hidma_lldev *lldev, bool msi)
+{
+	u32 val;
+
+	lldev->msi_support = msi;
+
+	/* disable interrupts again after reset */
+	writel(0, lldev->evca + HIDMA_EVCA_IRQ_CLR_REG);
+	writel(0, lldev->evca + HIDMA_EVCA_IRQ_EN_REG);
+
+	/* support IRQ by default */
 	val = readl(lldev->evca + HIDMA_EVCA_INTCTRL_REG);
 	val &= ~0xF;
-	val |= 0x1;
+	if (!lldev->msi_support)
+		val = val | 0x1;
 	writel(val, lldev->evca + HIDMA_EVCA_INTCTRL_REG);
 
 	/* clear all pending interrupts and enable them */
 	writel(ENABLE_IRQS, lldev->evca + HIDMA_EVCA_IRQ_CLR_REG);
 	writel(ENABLE_IRQS, lldev->evca + HIDMA_EVCA_IRQ_EN_REG);
-
-	return hidma_ll_enable(lldev);
 }
 
 struct hidma_lldev *hidma_ll_init(struct device *dev, u32 nr_tres,
@@ -816,7 +820,7 @@ int hidma_ll_uninit(struct hidma_lldev *lldev)
 	tasklet_kill(&lldev->task);
 	memset(lldev->trepool, 0, required_bytes);
 	lldev->trepool = NULL;
-	lldev->pending_tre_count = 0;
+	atomic_set(&lldev->pending_tre_count, 0);
 	lldev->tre_write_offset = 0;
 
 	rc = hidma_ll_reset(lldev);
diff --git a/drivers/dma/qcom/hidma_mgmt.c b/drivers/dma/qcom/hidma_mgmt.c
index 82f36e4..f847d32 100644
--- a/drivers/dma/qcom/hidma_mgmt.c
+++ b/drivers/dma/qcom/hidma_mgmt.c
@@ -282,6 +282,7 @@ static const struct acpi_device_id hidma_mgmt_acpi_ids[] = {
 	{"QCOM8060"},
 	{},
 };
+MODULE_DEVICE_TABLE(acpi, hidma_mgmt_acpi_ids);
 #endif
 
 static const struct of_device_id hidma_mgmt_match[] = {
@@ -375,8 +376,15 @@ static int __init hidma_mgmt_of_populate_channels(struct device_node *np)
 			ret = PTR_ERR(new_pdev);
 			goto out;
 		}
+		of_node_get(child);
+		new_pdev->dev.of_node = child;
 		of_dma_configure(&new_pdev->dev, child);
-
+		/*
+		 * It is assumed that calling of_msi_configure is safe on
+		 * platforms with or without MSI support.
+		 */
+		of_msi_configure(&new_pdev->dev, child);
+		of_node_put(child);
 		kfree(res);
 		res = NULL;
 	}
@@ -395,7 +403,6 @@ static int __init hidma_mgmt_init(void)
 	for_each_matching_node(child, hidma_mgmt_match) {
 		/* device tree based firmware here */
 		hidma_mgmt_of_populate_channels(child);
-		of_node_put(child);
 	}
 #endif
 	platform_driver_register(&hidma_mgmt_driver);
diff --git a/drivers/dma/s3c24xx-dma.c b/drivers/dma/s3c24xx-dma.c
index 3c579ab..f04c470 100644
--- a/drivers/dma/s3c24xx-dma.c
+++ b/drivers/dma/s3c24xx-dma.c
@@ -289,16 +289,11 @@ static
 struct s3c24xx_dma_phy *s3c24xx_dma_get_phy(struct s3c24xx_dma_chan *s3cchan)
 {
 	struct s3c24xx_dma_engine *s3cdma = s3cchan->host;
-	const struct s3c24xx_dma_platdata *pdata = s3cdma->pdata;
-	struct s3c24xx_dma_channel *cdata;
 	struct s3c24xx_dma_phy *phy = NULL;
 	unsigned long flags;
 	int i;
 	int ret;
 
-	if (s3cchan->slave)
-		cdata = &pdata->channels[s3cchan->id];
-
 	for (i = 0; i < s3cdma->pdata->num_phy_channels; i++) {
 		phy = &s3cdma->phy_chans[i];
 
diff --git a/drivers/dma/sh/usb-dmac.c b/drivers/dma/sh/usb-dmac.c
index 06ecdc3..72c6497 100644
--- a/drivers/dma/sh/usb-dmac.c
+++ b/drivers/dma/sh/usb-dmac.c
@@ -652,7 +652,6 @@ static bool usb_dmac_chan_filter(struct dma_chan *chan, void *arg)
 static struct dma_chan *usb_dmac_of_xlate(struct of_phandle_args *dma_spec,
 					  struct of_dma *ofdma)
 {
-	struct usb_dmac_chan *uchan;
 	struct dma_chan *chan;
 	dma_cap_mask_t mask;
 
@@ -667,8 +666,6 @@ static struct dma_chan *usb_dmac_of_xlate(struct of_phandle_args *dma_spec,
 	if (!chan)
 		return NULL;
 
-	uchan = to_usb_dmac_chan(chan);
-
 	return chan;
 }
 
diff --git a/drivers/dma/sirf-dma.c b/drivers/dma/sirf-dma.c
index 8f62eda..a0733ac 100644
--- a/drivers/dma/sirf-dma.c
+++ b/drivers/dma/sirf-dma.c
@@ -1011,7 +1011,6 @@ static int __maybe_unused sirfsoc_dma_pm_suspend(struct device *dev)
 {
 	struct sirfsoc_dma *sdma = dev_get_drvdata(dev);
 	struct sirfsoc_dma_regs *save = &sdma->regs_save;
-	struct sirfsoc_dma_desc *sdesc;
 	struct sirfsoc_dma_chan *schan;
 	int ch;
 	int ret;
@@ -1044,9 +1043,6 @@ static int __maybe_unused sirfsoc_dma_pm_suspend(struct device *dev)
 		schan = &sdma->channels[ch];
 		if (list_empty(&schan->active))
 			continue;
-		sdesc = list_first_entry(&schan->active,
-			struct sirfsoc_dma_desc,
-			node);
 		save->ctrl[ch] = readl_relaxed(sdma->base +
 			ch * 0x10 + SIRFSOC_DMA_CH_CTRL);
 	}
diff --git a/drivers/dma/stm32-dma.c b/drivers/dma/stm32-dma.c
index 307547f..3688d08 100644
--- a/drivers/dma/stm32-dma.c
+++ b/drivers/dma/stm32-dma.c
@@ -527,13 +527,12 @@ static irqreturn_t stm32_dma_chan_irq(int irq, void *devid)
 {
 	struct stm32_dma_chan *chan = devid;
 	struct stm32_dma_device *dmadev = stm32_dma_get_dev(chan);
-	u32 status, scr, sfcr;
+	u32 status, scr;
 
 	spin_lock(&chan->vchan.lock);
 
 	status = stm32_dma_irq_status(chan);
 	scr = stm32_dma_read(dmadev, STM32_DMA_SCR(chan->id));
-	sfcr = stm32_dma_read(dmadev, STM32_DMA_SFCR(chan->id));
 
 	if ((status & STM32_DMA_TCI) && (scr & STM32_DMA_SCR_TCIE)) {
 		stm32_dma_irq_clear(chan, STM32_DMA_TCI);
@@ -574,15 +573,12 @@ static int stm32_dma_set_xfer_param(struct stm32_dma_chan *chan,
 	int src_bus_width, dst_bus_width;
 	int src_burst_size, dst_burst_size;
 	u32 src_maxburst, dst_maxburst;
-	dma_addr_t src_addr, dst_addr;
 	u32 dma_scr = 0;
 
 	src_addr_width = chan->dma_sconfig.src_addr_width;
 	dst_addr_width = chan->dma_sconfig.dst_addr_width;
 	src_maxburst = chan->dma_sconfig.src_maxburst;
 	dst_maxburst = chan->dma_sconfig.dst_maxburst;
-	src_addr = chan->dma_sconfig.src_addr;
-	dst_addr = chan->dma_sconfig.dst_addr;
 
 	switch (direction) {
 	case DMA_MEM_TO_DEV:
diff --git a/drivers/dma/zx296702_dma.c b/drivers/dma/zx296702_dma.c
index 245d759..380276d 100644
--- a/drivers/dma/zx296702_dma.c
+++ b/drivers/dma/zx296702_dma.c
@@ -435,13 +435,12 @@ static struct zx_dma_desc_sw *zx_alloc_desc_resource(int num,
 	if (!ds)
 		return NULL;
 
-	ds->desc_hw = dma_pool_alloc(d->pool, GFP_NOWAIT, &ds->desc_hw_lli);
+	ds->desc_hw = dma_pool_zalloc(d->pool, GFP_NOWAIT, &ds->desc_hw_lli);
 	if (!ds->desc_hw) {
 		dev_dbg(chan->device->dev, "vch %p: dma alloc fail\n", &c->vc);
 		kfree(ds);
 		return NULL;
 	}
-	memset(ds->desc_hw, 0, sizeof(struct zx_desc_hw) * num);
 	ds->desc_num = num;
 	return ds;
 }
diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index 393fea8..3fda9a3 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -697,3 +697,4 @@ void of_msi_configure(struct device *dev, struct device_node *np)
 	dev_set_msi_domain(dev,
 			   of_msi_get_domain(dev, np, DOMAIN_BUS_PLATFORM_MSI));
 }
+EXPORT_SYMBOL_GPL(of_msi_configure);
diff --git a/drivers/spi/spi-s3c64xx.c b/drivers/spi/spi-s3c64xx.c
index 3c09e94..28dfdce 100644
--- a/drivers/spi/spi-s3c64xx.c
+++ b/drivers/spi/spi-s3c64xx.c
@@ -341,27 +341,20 @@ static void s3c64xx_spi_set_cs(struct spi_device *spi, bool enable)
 static int s3c64xx_spi_prepare_transfer(struct spi_master *spi)
 {
 	struct s3c64xx_spi_driver_data *sdd = spi_master_get_devdata(spi);
-	dma_filter_fn filter = sdd->cntrlr_info->filter;
 	struct device *dev = &sdd->pdev->dev;
-	dma_cap_mask_t mask;
 
 	if (is_polling(sdd))
 		return 0;
 
-	dma_cap_zero(mask);
-	dma_cap_set(DMA_SLAVE, mask);
-
 	/* Acquire DMA channels */
-	sdd->rx_dma.ch = dma_request_slave_channel_compat(mask, filter,
-			   sdd->cntrlr_info->dma_rx, dev, "rx");
+	sdd->rx_dma.ch = dma_request_slave_channel(dev, "rx");
 	if (!sdd->rx_dma.ch) {
 		dev_err(dev, "Failed to get RX DMA channel\n");
 		return -EBUSY;
 	}
 	spi->dma_rx = sdd->rx_dma.ch;
 
-	sdd->tx_dma.ch = dma_request_slave_channel_compat(mask, filter,
-			   sdd->cntrlr_info->dma_tx, dev, "tx");
+	sdd->tx_dma.ch = dma_request_slave_channel(dev, "tx");
 	if (!sdd->tx_dma.ch) {
 		dev_err(dev, "Failed to get TX DMA channel\n");
 		dma_release_channel(sdd->rx_dma.ch);
@@ -1091,11 +1084,6 @@ static int s3c64xx_spi_probe(struct platform_device *pdev)
 
 	sdd->cur_bpw = 8;
 
-	if (!sdd->pdev->dev.of_node && (!sci->dma_tx || !sci->dma_rx)) {
-		dev_warn(&pdev->dev, "Unable to get SPI tx/rx DMA data. Switching to poll mode\n");
-		sdd->port_conf->quirks = S3C64XX_SPI_QUIRK_POLL;
-	}
-
 	sdd->tx_dma.direction = DMA_MEM_TO_DEV;
 	sdd->rx_dma.direction = DMA_DEV_TO_MEM;
 
@@ -1205,9 +1193,8 @@ static int s3c64xx_spi_probe(struct platform_device *pdev)
 
 	dev_dbg(&pdev->dev, "Samsung SoC SPI Driver loaded for Bus SPI-%d with %d Slaves attached\n",
 					sdd->port_id, master->num_chipselect);
-	dev_dbg(&pdev->dev, "\tIOmem=[%pR]\tFIFO %dbytes\tDMA=[Rx-%p, Tx-%p]\n",
-					mem_res, (FIFO_LVL_MASK(sdd) >> 1) + 1,
-					sci->dma_rx, sci->dma_tx);
+	dev_dbg(&pdev->dev, "\tIOmem=[%pR]\tFIFO %dbytes\n",
+					mem_res, (FIFO_LVL_MASK(sdd) >> 1) + 1);
 
 	pm_runtime_mark_last_busy(&pdev->dev);
 	pm_runtime_put_autosuspend(&pdev->dev);
diff --git a/drivers/tty/serial/8250/8250_lpss.c b/drivers/tty/serial/8250/8250_lpss.c
index f607946..58cbb30 100644
--- a/drivers/tty/serial/8250/8250_lpss.c
+++ b/drivers/tty/serial/8250/8250_lpss.c
@@ -157,12 +157,12 @@ static int byt_serial_setup(struct lpss8250 *lpss, struct uart_port *port)
 static const struct dw_dma_platform_data qrk_serial_dma_pdata = {
 	.nr_channels = 2,
 	.is_private = true,
-	.is_nollp = true,
 	.chan_allocation_order = CHAN_ALLOCATION_ASCENDING,
 	.chan_priority = CHAN_PRIORITY_ASCENDING,
 	.block_size = 4095,
 	.nr_masters = 1,
 	.data_width = {4},
+	.multi_block = {0},
 };
 
 static void qrk_serial_setup_dma(struct lpss8250 *lpss, struct uart_port *port)
diff --git a/include/linux/amba/pl08x.h b/include/linux/amba/pl08x.h
index 27e9ec8..5308eae 100644
--- a/include/linux/amba/pl08x.h
+++ b/include/linux/amba/pl08x.h
@@ -84,6 +84,8 @@ struct pl08x_channel_data {
  * running any DMA transfer and multiplexing can be recycled
  * @lli_buses: buses which LLIs can be fetched from: PL08X_AHB1 | PL08X_AHB2
  * @mem_buses: buses which memory can be accessed from: PL08X_AHB1 | PL08X_AHB2
+ * @slave_map: DMA slave matching table
+ * @slave_map_len: number of elements in @slave_map
  */
 struct pl08x_platform_data {
 	struct pl08x_channel_data *slave_channels;
@@ -93,6 +95,8 @@ struct pl08x_platform_data {
 	void (*put_xfer_signal)(const struct pl08x_channel_data *, int);
 	u8 lli_buses;
 	u8 mem_buses;
+	const struct dma_slave_map *slave_map;
+	int slave_map_len;
 };
 
 #ifdef CONFIG_AMBA_PL08X
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index cc535a4..feee6ec 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -336,6 +336,12 @@ enum dma_slave_buswidth {
  * may or may not be applicable on memory sources.
  * @dst_maxburst: same as src_maxburst but for destination target
  * mutatis mutandis.
+ * @src_port_window_size: The length of the register area in words the data need
+ * to be accessed on the device side. It is only used for devices which is using
+ * an area instead of a single register to receive the data. Typically the DMA
+ * loops in this area in order to transfer the data.
+ * @dst_port_window_size: same as src_port_window_size but for the destination
+ * port.
  * @device_fc: Flow Controller Settings. Only valid for slave channels. Fill
  * with 'true' if peripheral should be flow controller. Direction will be
  * selected at Runtime.
@@ -363,6 +369,8 @@ struct dma_slave_config {
 	enum dma_slave_buswidth dst_addr_width;
 	u32 src_maxburst;
 	u32 dst_maxburst;
+	u32 src_port_window_size;
+	u32 dst_port_window_size;
 	bool device_fc;
 	unsigned int slave_id;
 };
diff --git a/include/linux/platform_data/dma-dw.h b/include/linux/platform_data/dma-dw.h
index 5f0e11e..e69e415 100644
--- a/include/linux/platform_data/dma-dw.h
+++ b/include/linux/platform_data/dma-dw.h
@@ -14,6 +14,7 @@
 #include <linux/device.h>
 
 #define DW_DMA_MAX_NR_MASTERS	4
+#define DW_DMA_MAX_NR_CHANNELS	8
 
 /**
  * struct dw_dma_slave - Controller-specific information about a slave
@@ -40,19 +41,18 @@ struct dw_dma_slave {
  * @is_private: The device channels should be marked as private and not for
  *	by the general purpose DMA channel allocator.
  * @is_memcpy: The device channels do support memory-to-memory transfers.
- * @is_nollp: The device channels does not support multi block transfers.
  * @chan_allocation_order: Allocate channels starting from 0 or 7
  * @chan_priority: Set channel priority increasing from 0 to 7 or 7 to 0.
  * @block_size: Maximum block size supported by the controller
  * @nr_masters: Number of AHB masters supported by the controller
  * @data_width: Maximum data width supported by hardware per AHB master
  *		(in bytes, power of 2)
+ * @multi_block: Multi block transfers supported by hardware per channel.
  */
 struct dw_dma_platform_data {
 	unsigned int	nr_channels;
 	bool		is_private;
 	bool		is_memcpy;
-	bool		is_nollp;
 #define CHAN_ALLOCATION_ASCENDING	0	/* zero to seven */
 #define CHAN_ALLOCATION_DESCENDING	1	/* seven to zero */
 	unsigned char	chan_allocation_order;
@@ -62,6 +62,7 @@ struct dw_dma_platform_data {
 	unsigned int	block_size;
 	unsigned char	nr_masters;
 	unsigned char	data_width[DW_DMA_MAX_NR_MASTERS];
+	unsigned char	multi_block[DW_DMA_MAX_NR_CHANNELS];
 };
 
 #endif /* _PLATFORM_DATA_DMA_DW_H */
diff --git a/include/linux/platform_data/spi-s3c64xx.h b/include/linux/platform_data/spi-s3c64xx.h
index 5c1e21c..da79774 100644
--- a/include/linux/platform_data/spi-s3c64xx.h
+++ b/include/linux/platform_data/spi-s3c64xx.h
@@ -40,9 +40,6 @@ struct s3c64xx_spi_info {
 	int num_cs;
 	bool no_cs;
 	int (*cfg_gpio)(void);
-	dma_filter_fn filter;
-	void *dma_tx;
-	void *dma_rx;
 };
 
 /**