Merge branch 'next' of git://git.infradead.org/users/vkoul/slave-dma

Pull slave-dmaengine changes from Vinod Koul:
 "This brings for slave dmaengine:

   - Change dma notification flag to DMA_COMPLETE from DMA_SUCCESS as
     dmaengine can only transfer and not verify validaty of dma
     transfers

   - Bunch of fixes across drivers:

      - cppi41 driver fixes from Daniel

      - 8 channel freescale dma engine support and updated bindings from
        Hongbo

      - msx-dma fixes and cleanup by Markus

   - DMAengine updates from Dan:

      - Bartlomiej and Dan finalized a rework of the dma address unmap
        implementation.

      - In the course of testing 1/ a collection of enhancements to
        dmatest fell out.  Notably basic performance statistics, and
        fixed / enhanced test control through new module parameters
        'run', 'wait', 'noverify', and 'verbose'.  Thanks to Andriy and
        Linus [Walleij] for their review.

      - Testing the raid related corner cases of 1/ triggered bugs in
        the recently added 16-source operation support in the ioatdma
        driver.

      - Some minor fixes / cleanups to mv_xor and ioatdma"

* 'next' of git://git.infradead.org/users/vkoul/slave-dma: (99 commits)
  dma: mv_xor: Fix mis-usage of mmio 'base' and 'high_base' registers
  dma: mv_xor: Remove unneeded NULL address check
  ioat: fix ioat3_irq_reinit
  ioat: kill msix_single_vector support
  raid6test: add new corner case for ioatdma driver
  ioatdma: clean up sed pool kmem_cache
  ioatdma: fix selection of 16 vs 8 source path
  ioatdma: fix sed pool selection
  ioatdma: Fix bug in selftest after removal of DMA_MEMSET.
  dmatest: verbose mode
  dmatest: convert to dmaengine_unmap_data
  dmatest: add a 'wait' parameter
  dmatest: add basic performance metrics
  dmatest: add support for skipping verification and random data setup
  dmatest: use pseudo random numbers
  dmatest: support xor-only, or pq-only channels in tests
  dmatest: restore ability to start test at module load and init
  dmatest: cleanup redundant "dmatest: " prefixes
  dmatest: replace stored results mechanism, with uniform messages
  Revert "dmatest: append verify result to results"
  ...
diff --git a/Documentation/devicetree/bindings/dma/atmel-dma.txt b/Documentation/devicetree/bindings/dma/atmel-dma.txt
index e1f343c..f69bcf5 100644
--- a/Documentation/devicetree/bindings/dma/atmel-dma.txt
+++ b/Documentation/devicetree/bindings/dma/atmel-dma.txt
@@ -28,7 +28,7 @@
 dependent:
   - bit 7-0: peripheral identifier for the hardware handshaking interface. The
   identifier can be different for tx and rx.
-  - bit 11-8: FIFO configuration. 0 for half FIFO, 1 for ALAP, 1 for ASAP.
+  - bit 11-8: FIFO configuration. 0 for half FIFO, 1 for ALAP, 2 for ASAP.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/dma.txt b/Documentation/devicetree/bindings/powerpc/fsl/dma.txt
index 2a4b4bc..7fc1b01 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/dma.txt
+++ b/Documentation/devicetree/bindings/powerpc/fsl/dma.txt
@@ -1,33 +1,30 @@
-* Freescale 83xx DMA Controller
+* Freescale DMA Controllers
 
-Freescale PowerPC 83xx have on chip general purpose DMA controllers.
+** Freescale Elo DMA Controller
+   This is a little-endian 4-channel DMA controller, used in Freescale mpc83xx
+   series chips such as mpc8315, mpc8349, mpc8379 etc.
 
 Required properties:
 
-- compatible        : compatible list, contains 2 entries, first is
-		 "fsl,CHIP-dma", where CHIP is the processor
-		 (mpc8349, mpc8360, etc.) and the second is
-		 "fsl,elo-dma"
-- reg               : <registers mapping for DMA general status reg>
-- ranges		: Should be defined as specified in 1) to describe the
-		  DMA controller channels.
+- compatible        : must include "fsl,elo-dma"
+- reg               : DMA General Status Register, i.e. DGSR which contains
+                      status for all the 4 DMA channels
+- ranges            : describes the mapping between the address space of the
+                      DMA channels and the address space of the DMA controller
 - cell-index        : controller index.  0 for controller @ 0x8100
-- interrupts        : <interrupt mapping for DMA IRQ>
+- interrupts        : interrupt specifier for DMA IRQ
 - interrupt-parent  : optional, if needed for interrupt mapping
 
-
 - DMA channel nodes:
-        - compatible        : compatible list, contains 2 entries, first is
-			 "fsl,CHIP-dma-channel", where CHIP is the processor
-			 (mpc8349, mpc8350, etc.) and the second is
-			 "fsl,elo-dma-channel". However, see note below.
-        - reg               : <registers mapping for channel>
-        - cell-index        : dma channel index starts at 0.
+        - compatible        : must include "fsl,elo-dma-channel"
+                              However, see note below.
+        - reg               : DMA channel specific registers
+        - cell-index        : DMA channel index starts at 0.
 
 Optional properties:
-        - interrupts        : <interrupt mapping for DMA channel IRQ>
-			  (on 83xx this is expected to be identical to
-			   the interrupts property of the parent node)
+        - interrupts        : interrupt specifier for DMA channel IRQ
+                              (on 83xx this is expected to be identical to
+                              the interrupts property of the parent node)
         - interrupt-parent  : optional, if needed for interrupt mapping
 
 Example:
@@ -70,30 +67,27 @@
 		};
 	};
 
-* Freescale 85xx/86xx DMA Controller
-
-Freescale PowerPC 85xx/86xx have on chip general purpose DMA controllers.
+** Freescale EloPlus DMA Controller
+   This is a 4-channel DMA controller with extended addresses and chaining,
+   mainly used in Freescale mpc85xx/86xx, Pxxx and BSC series chips, such as
+   mpc8540, mpc8641 p4080, bsc9131 etc.
 
 Required properties:
 
-- compatible        : compatible list, contains 2 entries, first is
-		 "fsl,CHIP-dma", where CHIP is the processor
-		 (mpc8540, mpc8540, etc.) and the second is
-		 "fsl,eloplus-dma"
-- reg               : <registers mapping for DMA general status reg>
+- compatible        : must include "fsl,eloplus-dma"
+- reg               : DMA General Status Register, i.e. DGSR which contains
+                      status for all the 4 DMA channels
 - cell-index        : controller index.  0 for controller @ 0x21000,
                                          1 for controller @ 0xc000
-- ranges		: Should be defined as specified in 1) to describe the
-		  DMA controller channels.
+- ranges            : describes the mapping between the address space of the
+                      DMA channels and the address space of the DMA controller
 
 - DMA channel nodes:
-        - compatible        : compatible list, contains 2 entries, first is
-			 "fsl,CHIP-dma-channel", where CHIP is the processor
-			 (mpc8540, mpc8560, etc.) and the second is
-			 "fsl,eloplus-dma-channel". However, see note below.
-        - cell-index        : dma channel index starts at 0.
-        - reg               : <registers mapping for channel>
-        - interrupts        : <interrupt mapping for DMA channel IRQ>
+        - compatible        : must include "fsl,eloplus-dma-channel"
+                              However, see note below.
+        - cell-index        : DMA channel index starts at 0.
+        - reg               : DMA channel specific registers
+        - interrupts        : interrupt specifier for DMA channel IRQ
         - interrupt-parent  : optional, if needed for interrupt mapping
 
 Example:
@@ -134,6 +128,76 @@
 		};
 	};
 
+** Freescale Elo3 DMA Controller
+   DMA controller which has same function as EloPlus except that Elo3 has 8
+   channels while EloPlus has only 4, it is used in Freescale Txxx and Bxxx
+   series chips, such as t1040, t4240, b4860.
+
+Required properties:
+
+- compatible        : must include "fsl,elo3-dma"
+- reg               : contains two entries for DMA General Status Registers,
+                      i.e. DGSR0 which includes status for channel 1~4, and
+                      DGSR1 for channel 5~8
+- ranges            : describes the mapping between the address space of the
+                      DMA channels and the address space of the DMA controller
+
+- DMA channel nodes:
+        - compatible        : must include "fsl,eloplus-dma-channel"
+        - reg               : DMA channel specific registers
+        - interrupts        : interrupt specifier for DMA channel IRQ
+        - interrupt-parent  : optional, if needed for interrupt mapping
+
+Example:
+dma@100300 {
+	#address-cells = <1>;
+	#size-cells = <1>;
+	compatible = "fsl,elo3-dma";
+	reg = <0x100300 0x4>,
+	      <0x100600 0x4>;
+	ranges = <0x0 0x100100 0x500>;
+	dma-channel@0 {
+		compatible = "fsl,eloplus-dma-channel";
+		reg = <0x0 0x80>;
+		interrupts = <28 2 0 0>;
+	};
+	dma-channel@80 {
+		compatible = "fsl,eloplus-dma-channel";
+		reg = <0x80 0x80>;
+		interrupts = <29 2 0 0>;
+	};
+	dma-channel@100 {
+		compatible = "fsl,eloplus-dma-channel";
+		reg = <0x100 0x80>;
+		interrupts = <30 2 0 0>;
+	};
+	dma-channel@180 {
+		compatible = "fsl,eloplus-dma-channel";
+		reg = <0x180 0x80>;
+		interrupts = <31 2 0 0>;
+	};
+	dma-channel@300 {
+		compatible = "fsl,eloplus-dma-channel";
+		reg = <0x300 0x80>;
+		interrupts = <76 2 0 0>;
+	};
+	dma-channel@380 {
+		compatible = "fsl,eloplus-dma-channel";
+		reg = <0x380 0x80>;
+		interrupts = <77 2 0 0>;
+	};
+	dma-channel@400 {
+		compatible = "fsl,eloplus-dma-channel";
+		reg = <0x400 0x80>;
+		interrupts = <78 2 0 0>;
+	};
+	dma-channel@480 {
+		compatible = "fsl,eloplus-dma-channel";
+		reg = <0x480 0x80>;
+		interrupts = <79 2 0 0>;
+	};
+};
+
 Note on DMA channel compatible properties: The compatible property must say
 "fsl,elo-dma-channel" or "fsl,eloplus-dma-channel" to be used by the Elo DMA
 driver (fsldma).  Any DMA channel used by fsldma cannot be used by another
diff --git a/Documentation/dmatest.txt b/Documentation/dmatest.txt
index a2b5663..dd77a81 100644
--- a/Documentation/dmatest.txt
+++ b/Documentation/dmatest.txt
@@ -15,39 +15,48 @@
 
 	Part 2 - When dmatest is built as a module...
 
-After mounting debugfs and loading the module, the /sys/kernel/debug/dmatest
-folder with nodes will be created. There are two important files located. First
-is the 'run' node that controls run and stop phases of the test, and the second
-one, 'results', is used to get the test case results.
-
-Note that in this case test will not run on load automatically.
-
 Example of usage:
+	% modprobe dmatest channel=dma0chan0 timeout=2000 iterations=1 run=1
+
+...or:
+	% modprobe dmatest
 	% echo dma0chan0 > /sys/module/dmatest/parameters/channel
 	% echo 2000 > /sys/module/dmatest/parameters/timeout
 	% echo 1 > /sys/module/dmatest/parameters/iterations
-	% echo 1 > /sys/kernel/debug/dmatest/run
+	% echo 1 > /sys/module/dmatest/parameters/run
+
+...or on the kernel command line:
+
+	dmatest.channel=dma0chan0 dmatest.timeout=2000 dmatest.iterations=1 dmatest.run=1
 
 Hint: available channel list could be extracted by running the following
 command:
 	% ls -1 /sys/class/dma/
 
-After a while you will start to get messages about current status or error like
-in the original code.
+Once started a message like "dmatest: Started 1 threads using dma0chan0" is
+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.
 
-The following command should return actual state of the test.
-	% cat /sys/kernel/debug/dmatest/run
+The following command returns the state of the test.
+	% cat /sys/module/dmatest/parameters/run
 
-To wait for test done the user may perform a busy loop that checks the state.
+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
+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
+waiting is disabled.
 
-	% while [ $(cat /sys/kernel/debug/dmatest/run) = "Y" ]
-	> do
-	> 	echo -n "."
-	> 	sleep 1
-	> done
-	> echo
+Example:
+	% modprobe dmatest run=1 iterations=42 wait=1
+	% modprobe -r dmatest
+...or:
+	% modprobe dmatest run=1 iterations=42
+	% cat /sys/module/dmatest/parameters/wait
+	% modprobe -r dmatest
 
 	Part 3 - When built-in in the kernel...
 
@@ -62,21 +71,22 @@
 
 	Part 4 - Gathering the test results
 
-The module provides a storage for the test results in the memory. The gathered
-data could be used after test is done.
+Test results are printed to the kernel log buffer with the format:
 
-The special file 'results' in the debugfs represents gathered data of the in
-progress test. The messages collected are printed to the kernel log as well.
+"dmatest: result <channel>: <test id>: '<error msg>' with src_off=<val> dst_off=<val> len=<val> (<err code>)"
 
 Example of output:
-	% cat /sys/kernel/debug/dmatest/results
-	dma0chan0-copy0: #1: No errors with src_off=0x7bf dst_off=0x8ad len=0x3fea (0)
+	% dmesg | tail -n 1
+	dmatest: result dma0chan0-copy0: #1: No errors with src_off=0x7bf dst_off=0x8ad len=0x3fea (0)
 
 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.
+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.
 
-Comparison between buffers is stored to the dedicated structure.
+Example:
+	% dmesg | tail -n 1
+	dmatest: dma0chan0-copy0: summary 1 test, 0 failures 1000 iops 100000 KB/s (0)
 
-Note that the verify result is now accessible only via file 'results' in the
-debugfs.
+The details of a data miscompare error are also emitted, but do not follow the
+above format.
diff --git a/arch/arm/common/edma.c b/arch/arm/common/edma.c
index 8e1a024..41bca32 100644
--- a/arch/arm/common/edma.c
+++ b/arch/arm/common/edma.c
@@ -404,7 +404,7 @@
 					BIT(slot));
 			if (edma_cc[ctlr]->intr_data[channel].callback)
 				edma_cc[ctlr]->intr_data[channel].callback(
-					channel, DMA_COMPLETE,
+					channel, EDMA_DMA_COMPLETE,
 					edma_cc[ctlr]->intr_data[channel].data);
 		}
 	} while (sh_ipr);
@@ -459,7 +459,7 @@
 								callback) {
 						edma_cc[ctlr]->intr_data[k].
 						callback(k,
-						DMA_CC_ERROR,
+						EDMA_DMA_CC_ERROR,
 						edma_cc[ctlr]->intr_data
 						[k].data);
 					}
diff --git a/arch/arm/include/asm/hardware/iop3xx-adma.h b/arch/arm/include/asm/hardware/iop3xx-adma.h
index 9b28f12..240b29e 100644
--- a/arch/arm/include/asm/hardware/iop3xx-adma.h
+++ b/arch/arm/include/asm/hardware/iop3xx-adma.h
@@ -393,36 +393,6 @@
 	return slot_cnt;
 }
 
-static inline int iop_desc_is_pq(struct iop_adma_desc_slot *desc)
-{
-	return 0;
-}
-
-static inline u32 iop_desc_get_dest_addr(struct iop_adma_desc_slot *desc,
-					struct iop_adma_chan *chan)
-{
-	union iop3xx_desc hw_desc = { .ptr = desc->hw_desc, };
-
-	switch (chan->device->id) {
-	case DMA0_ID:
-	case DMA1_ID:
-		return hw_desc.dma->dest_addr;
-	case AAU_ID:
-		return hw_desc.aau->dest_addr;
-	default:
-		BUG();
-	}
-	return 0;
-}
-
-
-static inline u32 iop_desc_get_qdest_addr(struct iop_adma_desc_slot *desc,
-					  struct iop_adma_chan *chan)
-{
-	BUG();
-	return 0;
-}
-
 static inline u32 iop_desc_get_byte_count(struct iop_adma_desc_slot *desc,
 					struct iop_adma_chan *chan)
 {
diff --git a/arch/arm/include/asm/hardware/iop_adma.h b/arch/arm/include/asm/hardware/iop_adma.h
index 122f86d..250760e 100644
--- a/arch/arm/include/asm/hardware/iop_adma.h
+++ b/arch/arm/include/asm/hardware/iop_adma.h
@@ -82,8 +82,6 @@
  * @slot_cnt: total slots used in an transaction (group of operations)
  * @slots_per_op: number of slots per operation
  * @idx: pool index
- * @unmap_src_cnt: number of xor sources
- * @unmap_len: transaction bytecount
  * @tx_list: list of descriptors that are associated with one operation
  * @async_tx: support for the async_tx api
  * @group_list: list of slots that make up a multi-descriptor transaction
@@ -99,8 +97,6 @@
 	u16 slot_cnt;
 	u16 slots_per_op;
 	u16 idx;
-	u16 unmap_src_cnt;
-	size_t unmap_len;
 	struct list_head tx_list;
 	struct dma_async_tx_descriptor async_tx;
 	union {
diff --git a/arch/arm/mach-iop13xx/include/mach/adma.h b/arch/arm/mach-iop13xx/include/mach/adma.h
index 6d3782d..a86fd0e 100644
--- a/arch/arm/mach-iop13xx/include/mach/adma.h
+++ b/arch/arm/mach-iop13xx/include/mach/adma.h
@@ -218,20 +218,6 @@
 #define iop_chan_pq_slot_count iop_chan_xor_slot_count
 #define iop_chan_pq_zero_sum_slot_count iop_chan_xor_slot_count
 
-static inline u32 iop_desc_get_dest_addr(struct iop_adma_desc_slot *desc,
-					struct iop_adma_chan *chan)
-{
-	struct iop13xx_adma_desc_hw *hw_desc = desc->hw_desc;
-	return hw_desc->dest_addr;
-}
-
-static inline u32 iop_desc_get_qdest_addr(struct iop_adma_desc_slot *desc,
-					  struct iop_adma_chan *chan)
-{
-	struct iop13xx_adma_desc_hw *hw_desc = desc->hw_desc;
-	return hw_desc->q_dest_addr;
-}
-
 static inline u32 iop_desc_get_byte_count(struct iop_adma_desc_slot *desc,
 					struct iop_adma_chan *chan)
 {
@@ -350,18 +336,6 @@
 	hw_desc->desc_ctrl = u_desc_ctrl.value;
 }
 
-static inline int iop_desc_is_pq(struct iop_adma_desc_slot *desc)
-{
-	struct iop13xx_adma_desc_hw *hw_desc = desc->hw_desc;
-	union {
-		u32 value;
-		struct iop13xx_adma_desc_ctrl field;
-	} u_desc_ctrl;
-
-	u_desc_ctrl.value = hw_desc->desc_ctrl;
-	return u_desc_ctrl.field.pq_xfer_en;
-}
-
 static inline void
 iop_desc_init_pq_zero_sum(struct iop_adma_desc_slot *desc, int src_cnt,
 			  unsigned long flags)
diff --git a/arch/powerpc/boot/dts/fsl/b4si-post.dtsi b/arch/powerpc/boot/dts/fsl/b4si-post.dtsi
index 4c617bf..4f6e482 100644
--- a/arch/powerpc/boot/dts/fsl/b4si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/b4si-post.dtsi
@@ -223,13 +223,13 @@
 		reg = <0xe2000 0x1000>;
 	};
 
-/include/ "qoriq-dma-0.dtsi"
+/include/ "elo3-dma-0.dtsi"
 	dma@100300 {
 		fsl,iommu-parent = <&pamu0>;
 		fsl,liodn-reg = <&guts 0x580>; /* DMA1LIODNR */
 	};
 
-/include/ "qoriq-dma-1.dtsi"
+/include/ "elo3-dma-1.dtsi"
 	dma@101300 {
 		fsl,iommu-parent = <&pamu0>;
 		fsl,liodn-reg = <&guts 0x584>; /* DMA2LIODNR */
diff --git a/arch/powerpc/boot/dts/fsl/elo3-dma-0.dtsi b/arch/powerpc/boot/dts/fsl/elo3-dma-0.dtsi
new file mode 100644
index 0000000..3c210e0
--- /dev/null
+++ b/arch/powerpc/boot/dts/fsl/elo3-dma-0.dtsi
@@ -0,0 +1,82 @@
+/*
+ * QorIQ Elo3 DMA device tree stub [ controller @ offset 0x100000 ]
+ *
+ * Copyright 2013 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+dma0: dma@100300 {
+	#address-cells = <1>;
+	#size-cells = <1>;
+	compatible = "fsl,elo3-dma";
+	reg = <0x100300 0x4>,
+	      <0x100600 0x4>;
+	ranges = <0x0 0x100100 0x500>;
+	dma-channel@0 {
+		compatible = "fsl,eloplus-dma-channel";
+		reg = <0x0 0x80>;
+		interrupts = <28 2 0 0>;
+	};
+	dma-channel@80 {
+		compatible = "fsl,eloplus-dma-channel";
+		reg = <0x80 0x80>;
+		interrupts = <29 2 0 0>;
+	};
+	dma-channel@100 {
+		compatible = "fsl,eloplus-dma-channel";
+		reg = <0x100 0x80>;
+		interrupts = <30 2 0 0>;
+	};
+	dma-channel@180 {
+		compatible = "fsl,eloplus-dma-channel";
+		reg = <0x180 0x80>;
+		interrupts = <31 2 0 0>;
+	};
+	dma-channel@300 {
+		compatible = "fsl,eloplus-dma-channel";
+		reg = <0x300 0x80>;
+		interrupts = <76 2 0 0>;
+	};
+	dma-channel@380 {
+		compatible = "fsl,eloplus-dma-channel";
+		reg = <0x380 0x80>;
+		interrupts = <77 2 0 0>;
+	};
+	dma-channel@400 {
+		compatible = "fsl,eloplus-dma-channel";
+		reg = <0x400 0x80>;
+		interrupts = <78 2 0 0>;
+	};
+	dma-channel@480 {
+		compatible = "fsl,eloplus-dma-channel";
+		reg = <0x480 0x80>;
+		interrupts = <79 2 0 0>;
+	};
+};
diff --git a/arch/powerpc/boot/dts/fsl/elo3-dma-1.dtsi b/arch/powerpc/boot/dts/fsl/elo3-dma-1.dtsi
new file mode 100644
index 0000000..cccf3bb
--- /dev/null
+++ b/arch/powerpc/boot/dts/fsl/elo3-dma-1.dtsi
@@ -0,0 +1,82 @@
+/*
+ * QorIQ Elo3 DMA device tree stub [ controller @ offset 0x101000 ]
+ *
+ * Copyright 2013 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+dma1: dma@101300 {
+	#address-cells = <1>;
+	#size-cells = <1>;
+	compatible = "fsl,elo3-dma";
+	reg = <0x101300 0x4>,
+	      <0x101600 0x4>;
+	ranges = <0x0 0x101100 0x500>;
+	dma-channel@0 {
+		compatible = "fsl,eloplus-dma-channel";
+		reg = <0x0 0x80>;
+		interrupts = <32 2 0 0>;
+	};
+	dma-channel@80 {
+		compatible = "fsl,eloplus-dma-channel";
+		reg = <0x80 0x80>;
+		interrupts = <33 2 0 0>;
+	};
+	dma-channel@100 {
+		compatible = "fsl,eloplus-dma-channel";
+		reg = <0x100 0x80>;
+		interrupts = <34 2 0 0>;
+	};
+	dma-channel@180 {
+		compatible = "fsl,eloplus-dma-channel";
+		reg = <0x180 0x80>;
+		interrupts = <35 2 0 0>;
+	};
+	dma-channel@300 {
+		compatible = "fsl,eloplus-dma-channel";
+		reg = <0x300 0x80>;
+		interrupts = <80 2 0 0>;
+	};
+	dma-channel@380 {
+		compatible = "fsl,eloplus-dma-channel";
+		reg = <0x380 0x80>;
+		interrupts = <81 2 0 0>;
+	};
+	dma-channel@400 {
+		compatible = "fsl,eloplus-dma-channel";
+		reg = <0x400 0x80>;
+		interrupts = <82 2 0 0>;
+	};
+	dma-channel@480 {
+		compatible = "fsl,eloplus-dma-channel";
+		reg = <0x480 0x80>;
+		interrupts = <83 2 0 0>;
+	};
+};
diff --git a/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi b/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi
index 510afa3..4143a97 100644
--- a/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi
@@ -387,8 +387,8 @@
 		reg	   = <0xea000 0x4000>;
 	};
 
-/include/ "qoriq-dma-0.dtsi"
-/include/ "qoriq-dma-1.dtsi"
+/include/ "elo3-dma-0.dtsi"
+/include/ "elo3-dma-1.dtsi"
 
 /include/ "qoriq-espi-0.dtsi"
 	spi@110000 {
diff --git a/crypto/async_tx/async_memcpy.c b/crypto/async_tx/async_memcpy.c
index 9e62fef..f8c0b8d 100644
--- a/crypto/async_tx/async_memcpy.c
+++ b/crypto/async_tx/async_memcpy.c
@@ -50,33 +50,36 @@
 						      &dest, 1, &src, 1, len);
 	struct dma_device *device = chan ? chan->device : NULL;
 	struct dma_async_tx_descriptor *tx = NULL;
+	struct dmaengine_unmap_data *unmap = NULL;
 
-	if (device && is_dma_copy_aligned(device, src_offset, dest_offset, len)) {
-		dma_addr_t dma_dest, dma_src;
+	if (device)
+		unmap = dmaengine_get_unmap_data(device->dev, 2, GFP_NOIO);
+
+	if (unmap && is_dma_copy_aligned(device, src_offset, dest_offset, len)) {
 		unsigned long dma_prep_flags = 0;
 
 		if (submit->cb_fn)
 			dma_prep_flags |= DMA_PREP_INTERRUPT;
 		if (submit->flags & ASYNC_TX_FENCE)
 			dma_prep_flags |= DMA_PREP_FENCE;
-		dma_dest = dma_map_page(device->dev, dest, dest_offset, len,
-					DMA_FROM_DEVICE);
 
-		dma_src = dma_map_page(device->dev, src, src_offset, len,
-				       DMA_TO_DEVICE);
+		unmap->to_cnt = 1;
+		unmap->addr[0] = dma_map_page(device->dev, src, src_offset, len,
+					      DMA_TO_DEVICE);
+		unmap->from_cnt = 1;
+		unmap->addr[1] = dma_map_page(device->dev, dest, dest_offset, len,
+					      DMA_FROM_DEVICE);
+		unmap->len = len;
 
-		tx = device->device_prep_dma_memcpy(chan, dma_dest, dma_src,
-						    len, dma_prep_flags);
-		if (!tx) {
-			dma_unmap_page(device->dev, dma_dest, len,
-				       DMA_FROM_DEVICE);
-			dma_unmap_page(device->dev, dma_src, len,
-				       DMA_TO_DEVICE);
-		}
+		tx = device->device_prep_dma_memcpy(chan, unmap->addr[1],
+						    unmap->addr[0], len,
+						    dma_prep_flags);
 	}
 
 	if (tx) {
 		pr_debug("%s: (async) len: %zu\n", __func__, len);
+
+		dma_set_unmap(tx, unmap);
 		async_tx_submit(chan, tx, submit);
 	} else {
 		void *dest_buf, *src_buf;
@@ -96,6 +99,8 @@
 		async_tx_sync_epilog(submit);
 	}
 
+	dmaengine_unmap_put(unmap);
+
 	return tx;
 }
 EXPORT_SYMBOL_GPL(async_memcpy);
diff --git a/crypto/async_tx/async_pq.c b/crypto/async_tx/async_pq.c
index 91d5d38..d05327c 100644
--- a/crypto/async_tx/async_pq.c
+++ b/crypto/async_tx/async_pq.c
@@ -46,49 +46,24 @@
  * do_async_gen_syndrome - asynchronously calculate P and/or Q
  */
 static __async_inline struct dma_async_tx_descriptor *
-do_async_gen_syndrome(struct dma_chan *chan, struct page **blocks,
-		      const unsigned char *scfs, unsigned int offset, int disks,
-		      size_t len, dma_addr_t *dma_src,
+do_async_gen_syndrome(struct dma_chan *chan,
+		      const unsigned char *scfs, int disks,
+		      struct dmaengine_unmap_data *unmap,
+		      enum dma_ctrl_flags dma_flags,
 		      struct async_submit_ctl *submit)
 {
 	struct dma_async_tx_descriptor *tx = NULL;
 	struct dma_device *dma = chan->device;
-	enum dma_ctrl_flags dma_flags = 0;
 	enum async_tx_flags flags_orig = submit->flags;
 	dma_async_tx_callback cb_fn_orig = submit->cb_fn;
 	dma_async_tx_callback cb_param_orig = submit->cb_param;
 	int src_cnt = disks - 2;
-	unsigned char coefs[src_cnt];
 	unsigned short pq_src_cnt;
 	dma_addr_t dma_dest[2];
 	int src_off = 0;
-	int idx;
-	int i;
 
-	/* DMAs use destinations as sources, so use BIDIRECTIONAL mapping */
-	if (P(blocks, disks))
-		dma_dest[0] = dma_map_page(dma->dev, P(blocks, disks), offset,
-					   len, DMA_BIDIRECTIONAL);
-	else
-		dma_flags |= DMA_PREP_PQ_DISABLE_P;
-	if (Q(blocks, disks))
-		dma_dest[1] = dma_map_page(dma->dev, Q(blocks, disks), offset,
-					   len, DMA_BIDIRECTIONAL);
-	else
-		dma_flags |= DMA_PREP_PQ_DISABLE_Q;
-
-	/* convert source addresses being careful to collapse 'empty'
-	 * sources and update the coefficients accordingly
-	 */
-	for (i = 0, idx = 0; i < src_cnt; i++) {
-		if (blocks[i] == NULL)
-			continue;
-		dma_src[idx] = dma_map_page(dma->dev, blocks[i], offset, len,
-					    DMA_TO_DEVICE);
-		coefs[idx] = scfs[i];
-		idx++;
-	}
-	src_cnt = idx;
+	if (submit->flags & ASYNC_TX_FENCE)
+		dma_flags |= DMA_PREP_FENCE;
 
 	while (src_cnt > 0) {
 		submit->flags = flags_orig;
@@ -100,28 +75,25 @@
 		if (src_cnt > pq_src_cnt) {
 			submit->flags &= ~ASYNC_TX_ACK;
 			submit->flags |= ASYNC_TX_FENCE;
-			dma_flags |= DMA_COMPL_SKIP_DEST_UNMAP;
 			submit->cb_fn = NULL;
 			submit->cb_param = NULL;
 		} else {
-			dma_flags &= ~DMA_COMPL_SKIP_DEST_UNMAP;
 			submit->cb_fn = cb_fn_orig;
 			submit->cb_param = cb_param_orig;
 			if (cb_fn_orig)
 				dma_flags |= DMA_PREP_INTERRUPT;
 		}
-		if (submit->flags & ASYNC_TX_FENCE)
-			dma_flags |= DMA_PREP_FENCE;
 
-		/* Since we have clobbered the src_list we are committed
-		 * to doing this asynchronously.  Drivers force forward
-		 * progress in case they can not provide a descriptor
+		/* Drivers force forward progress in case they can not provide
+		 * a descriptor
 		 */
 		for (;;) {
+			dma_dest[0] = unmap->addr[disks - 2];
+			dma_dest[1] = unmap->addr[disks - 1];
 			tx = dma->device_prep_dma_pq(chan, dma_dest,
-						     &dma_src[src_off],
+						     &unmap->addr[src_off],
 						     pq_src_cnt,
-						     &coefs[src_off], len,
+						     &scfs[src_off], unmap->len,
 						     dma_flags);
 			if (likely(tx))
 				break;
@@ -129,6 +101,7 @@
 			dma_async_issue_pending(chan);
 		}
 
+		dma_set_unmap(tx, unmap);
 		async_tx_submit(chan, tx, submit);
 		submit->depend_tx = tx;
 
@@ -188,10 +161,6 @@
  * set to NULL those buffers will be replaced with the raid6_zero_page
  * in the synchronous path and omitted in the hardware-asynchronous
  * path.
- *
- * 'blocks' note: if submit->scribble is NULL then the contents of
- * 'blocks' may be overwritten to perform address conversions
- * (dma_map_page() or page_address()).
  */
 struct dma_async_tx_descriptor *
 async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
@@ -202,26 +171,69 @@
 						      &P(blocks, disks), 2,
 						      blocks, src_cnt, len);
 	struct dma_device *device = chan ? chan->device : NULL;
-	dma_addr_t *dma_src = NULL;
+	struct dmaengine_unmap_data *unmap = NULL;
 
 	BUG_ON(disks > 255 || !(P(blocks, disks) || Q(blocks, disks)));
 
-	if (submit->scribble)
-		dma_src = submit->scribble;
-	else if (sizeof(dma_addr_t) <= sizeof(struct page *))
-		dma_src = (dma_addr_t *) blocks;
+	if (device)
+		unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOIO);
 
-	if (dma_src && device &&
+	if (unmap &&
 	    (src_cnt <= dma_maxpq(device, 0) ||
 	     dma_maxpq(device, DMA_PREP_CONTINUE) > 0) &&
 	    is_dma_pq_aligned(device, offset, 0, len)) {
+		struct dma_async_tx_descriptor *tx;
+		enum dma_ctrl_flags dma_flags = 0;
+		unsigned char coefs[src_cnt];
+		int i, j;
+
 		/* run the p+q asynchronously */
 		pr_debug("%s: (async) disks: %d len: %zu\n",
 			 __func__, disks, len);
-		return do_async_gen_syndrome(chan, blocks, raid6_gfexp, offset,
-					     disks, len, dma_src, submit);
+
+		/* convert source addresses being careful to collapse 'empty'
+		 * sources and update the coefficients accordingly
+		 */
+		unmap->len = len;
+		for (i = 0, j = 0; i < src_cnt; i++) {
+			if (blocks[i] == NULL)
+				continue;
+			unmap->addr[j] = dma_map_page(device->dev, blocks[i], offset,
+						      len, DMA_TO_DEVICE);
+			coefs[j] = raid6_gfexp[i];
+			unmap->to_cnt++;
+			j++;
+		}
+
+		/*
+		 * DMAs use destinations as sources,
+		 * so use BIDIRECTIONAL mapping
+		 */
+		unmap->bidi_cnt++;
+		if (P(blocks, disks))
+			unmap->addr[j++] = dma_map_page(device->dev, P(blocks, disks),
+							offset, len, DMA_BIDIRECTIONAL);
+		else {
+			unmap->addr[j++] = 0;
+			dma_flags |= DMA_PREP_PQ_DISABLE_P;
+		}
+
+		unmap->bidi_cnt++;
+		if (Q(blocks, disks))
+			unmap->addr[j++] = dma_map_page(device->dev, Q(blocks, disks),
+						       offset, len, DMA_BIDIRECTIONAL);
+		else {
+			unmap->addr[j++] = 0;
+			dma_flags |= DMA_PREP_PQ_DISABLE_Q;
+		}
+
+		tx = do_async_gen_syndrome(chan, coefs, j, unmap, dma_flags, submit);
+		dmaengine_unmap_put(unmap);
+		return tx;
 	}
 
+	dmaengine_unmap_put(unmap);
+
 	/* run the pq synchronously */
 	pr_debug("%s: (sync) disks: %d len: %zu\n", __func__, disks, len);
 
@@ -277,50 +289,60 @@
 	struct dma_async_tx_descriptor *tx;
 	unsigned char coefs[disks-2];
 	enum dma_ctrl_flags dma_flags = submit->cb_fn ? DMA_PREP_INTERRUPT : 0;
-	dma_addr_t *dma_src = NULL;
-	int src_cnt = 0;
+	struct dmaengine_unmap_data *unmap = NULL;
 
 	BUG_ON(disks < 4);
 
-	if (submit->scribble)
-		dma_src = submit->scribble;
-	else if (sizeof(dma_addr_t) <= sizeof(struct page *))
-		dma_src = (dma_addr_t *) blocks;
+	if (device)
+		unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOIO);
 
-	if (dma_src && device && disks <= dma_maxpq(device, 0) &&
+	if (unmap && disks <= dma_maxpq(device, 0) &&
 	    is_dma_pq_aligned(device, offset, 0, len)) {
 		struct device *dev = device->dev;
-		dma_addr_t *pq = &dma_src[disks-2];
-		int i;
+		dma_addr_t pq[2];
+		int i, j = 0, src_cnt = 0;
 
 		pr_debug("%s: (async) disks: %d len: %zu\n",
 			 __func__, disks, len);
-		if (!P(blocks, disks))
+
+		unmap->len = len;
+		for (i = 0; i < disks-2; i++)
+			if (likely(blocks[i])) {
+				unmap->addr[j] = dma_map_page(dev, blocks[i],
+							      offset, len,
+							      DMA_TO_DEVICE);
+				coefs[j] = raid6_gfexp[i];
+				unmap->to_cnt++;
+				src_cnt++;
+				j++;
+			}
+
+		if (!P(blocks, disks)) {
+			pq[0] = 0;
 			dma_flags |= DMA_PREP_PQ_DISABLE_P;
-		else
+		} else {
 			pq[0] = dma_map_page(dev, P(blocks, disks),
 					     offset, len,
 					     DMA_TO_DEVICE);
-		if (!Q(blocks, disks))
+			unmap->addr[j++] = pq[0];
+			unmap->to_cnt++;
+		}
+		if (!Q(blocks, disks)) {
+			pq[1] = 0;
 			dma_flags |= DMA_PREP_PQ_DISABLE_Q;
-		else
+		} else {
 			pq[1] = dma_map_page(dev, Q(blocks, disks),
 					     offset, len,
 					     DMA_TO_DEVICE);
+			unmap->addr[j++] = pq[1];
+			unmap->to_cnt++;
+		}
 
 		if (submit->flags & ASYNC_TX_FENCE)
 			dma_flags |= DMA_PREP_FENCE;
-		for (i = 0; i < disks-2; i++)
-			if (likely(blocks[i])) {
-				dma_src[src_cnt] = dma_map_page(dev, blocks[i],
-								offset, len,
-								DMA_TO_DEVICE);
-				coefs[src_cnt] = raid6_gfexp[i];
-				src_cnt++;
-			}
-
 		for (;;) {
-			tx = device->device_prep_dma_pq_val(chan, pq, dma_src,
+			tx = device->device_prep_dma_pq_val(chan, pq,
+							    unmap->addr,
 							    src_cnt,
 							    coefs,
 							    len, pqres,
@@ -330,6 +352,8 @@
 			async_tx_quiesce(&submit->depend_tx);
 			dma_async_issue_pending(chan);
 		}
+
+		dma_set_unmap(tx, unmap);
 		async_tx_submit(chan, tx, submit);
 
 		return tx;
diff --git a/crypto/async_tx/async_raid6_recov.c b/crypto/async_tx/async_raid6_recov.c
index a9f08a6..934a849 100644
--- a/crypto/async_tx/async_raid6_recov.c
+++ b/crypto/async_tx/async_raid6_recov.c
@@ -26,6 +26,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/raid/pq.h>
 #include <linux/async_tx.h>
+#include <linux/dmaengine.h>
 
 static struct dma_async_tx_descriptor *
 async_sum_product(struct page *dest, struct page **srcs, unsigned char *coef,
@@ -34,35 +35,45 @@
 	struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ,
 						      &dest, 1, srcs, 2, len);
 	struct dma_device *dma = chan ? chan->device : NULL;
+	struct dmaengine_unmap_data *unmap = NULL;
 	const u8 *amul, *bmul;
 	u8 ax, bx;
 	u8 *a, *b, *c;
 
-	if (dma) {
-		dma_addr_t dma_dest[2];
-		dma_addr_t dma_src[2];
+	if (dma)
+		unmap = dmaengine_get_unmap_data(dma->dev, 3, GFP_NOIO);
+
+	if (unmap) {
 		struct device *dev = dma->dev;
+		dma_addr_t pq[2];
 		struct dma_async_tx_descriptor *tx;
 		enum dma_ctrl_flags dma_flags = DMA_PREP_PQ_DISABLE_P;
 
 		if (submit->flags & ASYNC_TX_FENCE)
 			dma_flags |= DMA_PREP_FENCE;
-		dma_dest[1] = dma_map_page(dev, dest, 0, len, DMA_BIDIRECTIONAL);
-		dma_src[0] = dma_map_page(dev, srcs[0], 0, len, DMA_TO_DEVICE);
-		dma_src[1] = dma_map_page(dev, srcs[1], 0, len, DMA_TO_DEVICE);
-		tx = dma->device_prep_dma_pq(chan, dma_dest, dma_src, 2, coef,
+		unmap->addr[0] = dma_map_page(dev, srcs[0], 0, len, DMA_TO_DEVICE);
+		unmap->addr[1] = dma_map_page(dev, srcs[1], 0, len, DMA_TO_DEVICE);
+		unmap->to_cnt = 2;
+
+		unmap->addr[2] = dma_map_page(dev, dest, 0, len, DMA_BIDIRECTIONAL);
+		unmap->bidi_cnt = 1;
+		/* engine only looks at Q, but expects it to follow P */
+		pq[1] = unmap->addr[2];
+
+		unmap->len = len;
+		tx = dma->device_prep_dma_pq(chan, pq, unmap->addr, 2, coef,
 					     len, dma_flags);
 		if (tx) {
+			dma_set_unmap(tx, unmap);
 			async_tx_submit(chan, tx, submit);
+			dmaengine_unmap_put(unmap);
 			return tx;
 		}
 
 		/* could not get a descriptor, unmap and fall through to
 		 * the synchronous path
 		 */
-		dma_unmap_page(dev, dma_dest[1], len, DMA_BIDIRECTIONAL);
-		dma_unmap_page(dev, dma_src[0], len, DMA_TO_DEVICE);
-		dma_unmap_page(dev, dma_src[1], len, DMA_TO_DEVICE);
+		dmaengine_unmap_put(unmap);
 	}
 
 	/* run the operation synchronously */
@@ -89,23 +100,38 @@
 	struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ,
 						      &dest, 1, &src, 1, len);
 	struct dma_device *dma = chan ? chan->device : NULL;
+	struct dmaengine_unmap_data *unmap = NULL;
 	const u8 *qmul; /* Q multiplier table */
 	u8 *d, *s;
 
-	if (dma) {
+	if (dma)
+		unmap = dmaengine_get_unmap_data(dma->dev, 3, GFP_NOIO);
+
+	if (unmap) {
 		dma_addr_t dma_dest[2];
-		dma_addr_t dma_src[1];
 		struct device *dev = dma->dev;
 		struct dma_async_tx_descriptor *tx;
 		enum dma_ctrl_flags dma_flags = DMA_PREP_PQ_DISABLE_P;
 
 		if (submit->flags & ASYNC_TX_FENCE)
 			dma_flags |= DMA_PREP_FENCE;
-		dma_dest[1] = dma_map_page(dev, dest, 0, len, DMA_BIDIRECTIONAL);
-		dma_src[0] = dma_map_page(dev, src, 0, len, DMA_TO_DEVICE);
-		tx = dma->device_prep_dma_pq(chan, dma_dest, dma_src, 1, &coef,
-					     len, dma_flags);
+		unmap->addr[0] = dma_map_page(dev, src, 0, len, DMA_TO_DEVICE);
+		unmap->to_cnt++;
+		unmap->addr[1] = dma_map_page(dev, dest, 0, len, DMA_BIDIRECTIONAL);
+		dma_dest[1] = unmap->addr[1];
+		unmap->bidi_cnt++;
+		unmap->len = len;
+
+		/* this looks funny, but the engine looks for Q at
+		 * dma_dest[1] and ignores dma_dest[0] as a dest
+		 * due to DMA_PREP_PQ_DISABLE_P
+		 */
+		tx = dma->device_prep_dma_pq(chan, dma_dest, unmap->addr,
+					     1, &coef, len, dma_flags);
+
 		if (tx) {
+			dma_set_unmap(tx, unmap);
+			dmaengine_unmap_put(unmap);
 			async_tx_submit(chan, tx, submit);
 			return tx;
 		}
@@ -113,8 +139,7 @@
 		/* could not get a descriptor, unmap and fall through to
 		 * the synchronous path
 		 */
-		dma_unmap_page(dev, dma_dest[1], len, DMA_BIDIRECTIONAL);
-		dma_unmap_page(dev, dma_src[0], len, DMA_TO_DEVICE);
+		dmaengine_unmap_put(unmap);
 	}
 
 	/* no channel available, or failed to allocate a descriptor, so
diff --git a/crypto/async_tx/async_tx.c b/crypto/async_tx/async_tx.c
index 7be3424..39ea479 100644
--- a/crypto/async_tx/async_tx.c
+++ b/crypto/async_tx/async_tx.c
@@ -128,7 +128,7 @@
 		}
 		device->device_issue_pending(chan);
 	} else {
-		if (dma_wait_for_async_tx(depend_tx) != DMA_SUCCESS)
+		if (dma_wait_for_async_tx(depend_tx) != DMA_COMPLETE)
 			panic("%s: DMA error waiting for depend_tx\n",
 			      __func__);
 		tx->tx_submit(tx);
@@ -280,7 +280,7 @@
 		 * we are referring to the correct operation
 		 */
 		BUG_ON(async_tx_test_ack(*tx));
-		if (dma_wait_for_async_tx(*tx) != DMA_SUCCESS)
+		if (dma_wait_for_async_tx(*tx) != DMA_COMPLETE)
 			panic("%s: DMA error waiting for transaction\n",
 			      __func__);
 		async_tx_ack(*tx);
diff --git a/crypto/async_tx/async_xor.c b/crypto/async_tx/async_xor.c
index 8ade0a0..3c562f5 100644
--- a/crypto/async_tx/async_xor.c
+++ b/crypto/async_tx/async_xor.c
@@ -33,48 +33,31 @@
 
 /* do_async_xor - dma map the pages and perform the xor with an engine */
 static __async_inline struct dma_async_tx_descriptor *
-do_async_xor(struct dma_chan *chan, struct page *dest, struct page **src_list,
-	     unsigned int offset, int src_cnt, size_t len, dma_addr_t *dma_src,
+do_async_xor(struct dma_chan *chan, struct dmaengine_unmap_data *unmap,
 	     struct async_submit_ctl *submit)
 {
 	struct dma_device *dma = chan->device;
 	struct dma_async_tx_descriptor *tx = NULL;
-	int src_off = 0;
-	int i;
 	dma_async_tx_callback cb_fn_orig = submit->cb_fn;
 	void *cb_param_orig = submit->cb_param;
 	enum async_tx_flags flags_orig = submit->flags;
-	enum dma_ctrl_flags dma_flags;
-	int xor_src_cnt = 0;
-	dma_addr_t dma_dest;
-
-	/* map the dest bidrectional in case it is re-used as a source */
-	dma_dest = dma_map_page(dma->dev, dest, offset, len, DMA_BIDIRECTIONAL);
-	for (i = 0; i < src_cnt; i++) {
-		/* only map the dest once */
-		if (!src_list[i])
-			continue;
-		if (unlikely(src_list[i] == dest)) {
-			dma_src[xor_src_cnt++] = dma_dest;
-			continue;
-		}
-		dma_src[xor_src_cnt++] = dma_map_page(dma->dev, src_list[i], offset,
-						      len, DMA_TO_DEVICE);
-	}
-	src_cnt = xor_src_cnt;
+	enum dma_ctrl_flags dma_flags = 0;
+	int src_cnt = unmap->to_cnt;
+	int xor_src_cnt;
+	dma_addr_t dma_dest = unmap->addr[unmap->to_cnt];
+	dma_addr_t *src_list = unmap->addr;
 
 	while (src_cnt) {
+		dma_addr_t tmp;
+
 		submit->flags = flags_orig;
-		dma_flags = 0;
 		xor_src_cnt = min(src_cnt, (int)dma->max_xor);
-		/* if we are submitting additional xors, leave the chain open,
-		 * clear the callback parameters, and leave the destination
-		 * buffer mapped
+		/* if we are submitting additional xors, leave the chain open
+		 * and clear the callback parameters
 		 */
 		if (src_cnt > xor_src_cnt) {
 			submit->flags &= ~ASYNC_TX_ACK;
 			submit->flags |= ASYNC_TX_FENCE;
-			dma_flags = DMA_COMPL_SKIP_DEST_UNMAP;
 			submit->cb_fn = NULL;
 			submit->cb_param = NULL;
 		} else {
@@ -85,12 +68,18 @@
 			dma_flags |= DMA_PREP_INTERRUPT;
 		if (submit->flags & ASYNC_TX_FENCE)
 			dma_flags |= DMA_PREP_FENCE;
-		/* Since we have clobbered the src_list we are committed
-		 * to doing this asynchronously.  Drivers force forward progress
-		 * in case they can not provide a descriptor
+
+		/* Drivers force forward progress in case they can not provide a
+		 * descriptor
 		 */
-		tx = dma->device_prep_dma_xor(chan, dma_dest, &dma_src[src_off],
-					      xor_src_cnt, len, dma_flags);
+		tmp = src_list[0];
+		if (src_list > unmap->addr)
+			src_list[0] = dma_dest;
+		tx = dma->device_prep_dma_xor(chan, dma_dest, src_list,
+					      xor_src_cnt, unmap->len,
+					      dma_flags);
+		src_list[0] = tmp;
+
 
 		if (unlikely(!tx))
 			async_tx_quiesce(&submit->depend_tx);
@@ -99,22 +88,21 @@
 		while (unlikely(!tx)) {
 			dma_async_issue_pending(chan);
 			tx = dma->device_prep_dma_xor(chan, dma_dest,
-						      &dma_src[src_off],
-						      xor_src_cnt, len,
+						      src_list,
+						      xor_src_cnt, unmap->len,
 						      dma_flags);
 		}
 
+		dma_set_unmap(tx, unmap);
 		async_tx_submit(chan, tx, submit);
 		submit->depend_tx = tx;
 
 		if (src_cnt > xor_src_cnt) {
 			/* drop completed sources */
 			src_cnt -= xor_src_cnt;
-			src_off += xor_src_cnt;
-
 			/* use the intermediate result a source */
-			dma_src[--src_off] = dma_dest;
 			src_cnt++;
+			src_list += xor_src_cnt - 1;
 		} else
 			break;
 	}
@@ -189,22 +177,40 @@
 	struct dma_chan *chan = async_tx_find_channel(submit, DMA_XOR,
 						      &dest, 1, src_list,
 						      src_cnt, len);
-	dma_addr_t *dma_src = NULL;
+	struct dma_device *device = chan ? chan->device : NULL;
+	struct dmaengine_unmap_data *unmap = NULL;
 
 	BUG_ON(src_cnt <= 1);
 
-	if (submit->scribble)
-		dma_src = submit->scribble;
-	else if (sizeof(dma_addr_t) <= sizeof(struct page *))
-		dma_src = (dma_addr_t *) src_list;
+	if (device)
+		unmap = dmaengine_get_unmap_data(device->dev, src_cnt+1, GFP_NOIO);
 
-	if (dma_src && chan && is_dma_xor_aligned(chan->device, offset, 0, len)) {
+	if (unmap && is_dma_xor_aligned(device, offset, 0, len)) {
+		struct dma_async_tx_descriptor *tx;
+		int i, j;
+
 		/* run the xor asynchronously */
 		pr_debug("%s (async): len: %zu\n", __func__, len);
 
-		return do_async_xor(chan, dest, src_list, offset, src_cnt, len,
-				    dma_src, submit);
+		unmap->len = len;
+		for (i = 0, j = 0; i < src_cnt; i++) {
+			if (!src_list[i])
+				continue;
+			unmap->to_cnt++;
+			unmap->addr[j++] = dma_map_page(device->dev, src_list[i],
+							offset, len, DMA_TO_DEVICE);
+		}
+
+		/* map it bidirectional as it may be re-used as a source */
+		unmap->addr[j] = dma_map_page(device->dev, dest, offset, len,
+					      DMA_BIDIRECTIONAL);
+		unmap->bidi_cnt = 1;
+
+		tx = do_async_xor(chan, unmap, submit);
+		dmaengine_unmap_put(unmap);
+		return tx;
 	} else {
+		dmaengine_unmap_put(unmap);
 		/* run the xor synchronously */
 		pr_debug("%s (sync): len: %zu\n", __func__, len);
 		WARN_ONCE(chan, "%s: no space for dma address conversion\n",
@@ -268,16 +274,14 @@
 	struct dma_chan *chan = xor_val_chan(submit, dest, src_list, src_cnt, len);
 	struct dma_device *device = chan ? chan->device : NULL;
 	struct dma_async_tx_descriptor *tx = NULL;
-	dma_addr_t *dma_src = NULL;
+	struct dmaengine_unmap_data *unmap = NULL;
 
 	BUG_ON(src_cnt <= 1);
 
-	if (submit->scribble)
-		dma_src = submit->scribble;
-	else if (sizeof(dma_addr_t) <= sizeof(struct page *))
-		dma_src = (dma_addr_t *) src_list;
+	if (device)
+		unmap = dmaengine_get_unmap_data(device->dev, src_cnt, GFP_NOIO);
 
-	if (dma_src && device && src_cnt <= device->max_xor &&
+	if (unmap && src_cnt <= device->max_xor &&
 	    is_dma_xor_aligned(device, offset, 0, len)) {
 		unsigned long dma_prep_flags = 0;
 		int i;
@@ -288,11 +292,15 @@
 			dma_prep_flags |= DMA_PREP_INTERRUPT;
 		if (submit->flags & ASYNC_TX_FENCE)
 			dma_prep_flags |= DMA_PREP_FENCE;
-		for (i = 0; i < src_cnt; i++)
-			dma_src[i] = dma_map_page(device->dev, src_list[i],
-						  offset, len, DMA_TO_DEVICE);
 
-		tx = device->device_prep_dma_xor_val(chan, dma_src, src_cnt,
+		for (i = 0; i < src_cnt; i++) {
+			unmap->addr[i] = dma_map_page(device->dev, src_list[i],
+						      offset, len, DMA_TO_DEVICE);
+			unmap->to_cnt++;
+		}
+		unmap->len = len;
+
+		tx = device->device_prep_dma_xor_val(chan, unmap->addr, src_cnt,
 						     len, result,
 						     dma_prep_flags);
 		if (unlikely(!tx)) {
@@ -301,11 +309,11 @@
 			while (!tx) {
 				dma_async_issue_pending(chan);
 				tx = device->device_prep_dma_xor_val(chan,
-					dma_src, src_cnt, len, result,
+					unmap->addr, src_cnt, len, result,
 					dma_prep_flags);
 			}
 		}
-
+		dma_set_unmap(tx, unmap);
 		async_tx_submit(chan, tx, submit);
 	} else {
 		enum async_tx_flags flags_orig = submit->flags;
@@ -327,6 +335,7 @@
 		async_tx_sync_epilog(submit);
 		submit->flags = flags_orig;
 	}
+	dmaengine_unmap_put(unmap);
 
 	return tx;
 }
diff --git a/crypto/async_tx/raid6test.c b/crypto/async_tx/raid6test.c
index 4a92bac..dad95f4 100644
--- a/crypto/async_tx/raid6test.c
+++ b/crypto/async_tx/raid6test.c
@@ -28,7 +28,7 @@
 #undef pr
 #define pr(fmt, args...) pr_info("raid6test: " fmt, ##args)
 
-#define NDISKS 16 /* Including P and Q */
+#define NDISKS 64 /* Including P and Q */
 
 static struct page *dataptrs[NDISKS];
 static addr_conv_t addr_conv[NDISKS];
@@ -219,6 +219,14 @@
 		err += test(11, &tests);
 		err += test(12, &tests);
 	}
+
+	/* the 24 disk case is special for ioatdma as it is the boudary point
+	 * at which it needs to switch from 8-source ops to 16-source
+	 * ops for continuation (assumes DMA_HAS_PQ_CONTINUE is not set)
+	 */
+	if (NDISKS > 24)
+		err += test(24, &tests);
+
 	err += test(NDISKS, &tests);
 
 	pr("\n");
diff --git a/drivers/ata/pata_arasan_cf.c b/drivers/ata/pata_arasan_cf.c
index 853f610..e88690e 100644
--- a/drivers/ata/pata_arasan_cf.c
+++ b/drivers/ata/pata_arasan_cf.c
@@ -396,8 +396,7 @@
 	struct dma_async_tx_descriptor *tx;
 	struct dma_chan *chan = acdev->dma_chan;
 	dma_cookie_t cookie;
-	unsigned long flags = DMA_PREP_INTERRUPT | DMA_COMPL_SKIP_SRC_UNMAP |
-		DMA_COMPL_SKIP_DEST_UNMAP;
+	unsigned long flags = DMA_PREP_INTERRUPT;
 	int ret = 0;
 
 	tx = chan->device->device_prep_dma_memcpy(chan, dest, src, len, flags);
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index dd2874ec..446687c 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -89,14 +89,15 @@
 	  Support the Atmel AHB DMA controller.
 
 config FSL_DMA
-	tristate "Freescale Elo and Elo Plus DMA support"
+	tristate "Freescale Elo series DMA support"
 	depends on FSL_SOC
 	select DMA_ENGINE
 	select ASYNC_TX_ENABLE_CHANNEL_SWITCH
 	---help---
-	  Enable support for the Freescale Elo and Elo Plus DMA controllers.
-	  The Elo is the DMA controller on some 82xx and 83xx parts, and the
-	  Elo Plus is the DMA controller on 85xx and 86xx parts.
+	  Enable support for the Freescale Elo series DMA controllers.
+	  The Elo is the DMA controller on some mpc82xx and mpc83xx parts, the
+	  EloPlus is on mpc85xx and mpc86xx and Pxxx parts, and the Elo3 is on
+	  some Txxx and Bxxx parts.
 
 config MPC512X_DMA
 	tristate "Freescale MPC512x built-in DMA engine support"
diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c
index e51a983..16a2aa2 100644
--- a/drivers/dma/amba-pl08x.c
+++ b/drivers/dma/amba-pl08x.c
@@ -1164,42 +1164,12 @@
 	kfree(txd);
 }
 
-static void pl08x_unmap_buffers(struct pl08x_txd *txd)
-{
-	struct device *dev = txd->vd.tx.chan->device->dev;
-	struct pl08x_sg *dsg;
-
-	if (!(txd->vd.tx.flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-		if (txd->vd.tx.flags & DMA_COMPL_SRC_UNMAP_SINGLE)
-			list_for_each_entry(dsg, &txd->dsg_list, node)
-				dma_unmap_single(dev, dsg->src_addr, dsg->len,
-						DMA_TO_DEVICE);
-		else {
-			list_for_each_entry(dsg, &txd->dsg_list, node)
-				dma_unmap_page(dev, dsg->src_addr, dsg->len,
-						DMA_TO_DEVICE);
-		}
-	}
-	if (!(txd->vd.tx.flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
-		if (txd->vd.tx.flags & DMA_COMPL_DEST_UNMAP_SINGLE)
-			list_for_each_entry(dsg, &txd->dsg_list, node)
-				dma_unmap_single(dev, dsg->dst_addr, dsg->len,
-						DMA_FROM_DEVICE);
-		else
-			list_for_each_entry(dsg, &txd->dsg_list, node)
-				dma_unmap_page(dev, dsg->dst_addr, dsg->len,
-						DMA_FROM_DEVICE);
-	}
-}
-
 static void pl08x_desc_free(struct virt_dma_desc *vd)
 {
 	struct pl08x_txd *txd = to_pl08x_txd(&vd->tx);
 	struct pl08x_dma_chan *plchan = to_pl08x_chan(vd->tx.chan);
 
-	if (!plchan->slave)
-		pl08x_unmap_buffers(txd);
-
+	dma_descriptor_unmap(txd);
 	if (!txd->done)
 		pl08x_release_mux(plchan);
 
@@ -1252,7 +1222,7 @@
 	size_t bytes = 0;
 
 	ret = dma_cookie_status(chan, cookie, txstate);
-	if (ret == DMA_SUCCESS)
+	if (ret == DMA_COMPLETE)
 		return ret;
 
 	/*
@@ -1267,7 +1237,7 @@
 
 	spin_lock_irqsave(&plchan->vc.lock, flags);
 	ret = dma_cookie_status(chan, cookie, txstate);
-	if (ret != DMA_SUCCESS) {
+	if (ret != DMA_COMPLETE) {
 		vd = vchan_find_desc(&plchan->vc, cookie);
 		if (vd) {
 			/* On the issued list, so hasn't been processed yet */
@@ -2138,8 +2108,7 @@
 	writel(0x000000FF, pl08x->base + PL080_ERR_CLEAR);
 	writel(0x000000FF, pl08x->base + PL080_TC_CLEAR);
 
-	ret = request_irq(adev->irq[0], pl08x_irq, IRQF_DISABLED,
-			  DRIVER_NAME, pl08x);
+	ret = request_irq(adev->irq[0], pl08x_irq, 0, DRIVER_NAME, pl08x);
 	if (ret) {
 		dev_err(&adev->dev, "%s failed to request interrupt %d\n",
 			__func__, adev->irq[0]);
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index c787f38..e2c04dc 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -344,31 +344,7 @@
 	/* move myself to free_list */
 	list_move(&desc->desc_node, &atchan->free_list);
 
-	/* unmap dma addresses (not on slave channels) */
-	if (!atchan->chan_common.private) {
-		struct device *parent = chan2parent(&atchan->chan_common);
-		if (!(txd->flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
-			if (txd->flags & DMA_COMPL_DEST_UNMAP_SINGLE)
-				dma_unmap_single(parent,
-						desc->lli.daddr,
-						desc->len, DMA_FROM_DEVICE);
-			else
-				dma_unmap_page(parent,
-						desc->lli.daddr,
-						desc->len, DMA_FROM_DEVICE);
-		}
-		if (!(txd->flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-			if (txd->flags & DMA_COMPL_SRC_UNMAP_SINGLE)
-				dma_unmap_single(parent,
-						desc->lli.saddr,
-						desc->len, DMA_TO_DEVICE);
-			else
-				dma_unmap_page(parent,
-						desc->lli.saddr,
-						desc->len, DMA_TO_DEVICE);
-		}
-	}
-
+	dma_descriptor_unmap(txd);
 	/* for cyclic transfers,
 	 * no need to replay callback function while stopping */
 	if (!atc_chan_is_cyclic(atchan)) {
@@ -1102,7 +1078,7 @@
 	int bytes = 0;
 
 	ret = dma_cookie_status(chan, cookie, txstate);
-	if (ret == DMA_SUCCESS)
+	if (ret == DMA_COMPLETE)
 		return ret;
 	/*
 	 * There's no point calculating the residue if there's
diff --git a/drivers/dma/coh901318.c b/drivers/dma/coh901318.c
index 31011d2..3c6716e 100644
--- a/drivers/dma/coh901318.c
+++ b/drivers/dma/coh901318.c
@@ -2369,7 +2369,7 @@
 	enum dma_status ret;
 
 	ret = dma_cookie_status(chan, cookie, txstate);
-	if (ret == DMA_SUCCESS)
+	if (ret == DMA_COMPLETE)
 		return ret;
 
 	dma_set_residue(txstate, coh901318_get_bytes_left(chan));
@@ -2694,7 +2694,7 @@
 	if (irq < 0)
 		return irq;
 
-	err = devm_request_irq(&pdev->dev, irq, dma_irq_handler, IRQF_DISABLED,
+	err = devm_request_irq(&pdev->dev, irq, dma_irq_handler, 0,
 			       "coh901318", base);
 	if (err)
 		return err;
diff --git a/drivers/dma/cppi41.c b/drivers/dma/cppi41.c
index 7c82b92..c29dacf 100644
--- a/drivers/dma/cppi41.c
+++ b/drivers/dma/cppi41.c
@@ -141,6 +141,9 @@
 	const struct chan_queues *queues_rx;
 	const struct chan_queues *queues_tx;
 	struct chan_queues td_queue;
+
+	/* context for suspend/resume */
+	unsigned int dma_tdfdq;
 };
 
 #define FIST_COMPLETION_QUEUE	93
@@ -263,6 +266,15 @@
 	return val & ((1 << (DESC_LENGTH_BITS_NUM + 1)) - 1);
 }
 
+static u32 cppi41_pop_desc(struct cppi41_dd *cdd, unsigned queue_num)
+{
+	u32 desc;
+
+	desc = cppi_readl(cdd->qmgr_mem + QMGR_QUEUE_D(queue_num));
+	desc &= ~0x1f;
+	return desc;
+}
+
 static irqreturn_t cppi41_irq(int irq, void *data)
 {
 	struct cppi41_dd *cdd = data;
@@ -300,8 +312,7 @@
 			q_num = __fls(val);
 			val &= ~(1 << q_num);
 			q_num += 32 * i;
-			desc = cppi_readl(cdd->qmgr_mem + QMGR_QUEUE_D(q_num));
-			desc &= ~0x1f;
+			desc = cppi41_pop_desc(cdd, q_num);
 			c = desc_to_chan(cdd, desc);
 			if (WARN_ON(!c)) {
 				pr_err("%s() q %d desc %08x\n", __func__,
@@ -353,7 +364,7 @@
 
 	/* lock */
 	ret = dma_cookie_status(chan, cookie, txstate);
-	if (txstate && ret == DMA_SUCCESS)
+	if (txstate && ret == DMA_COMPLETE)
 		txstate->residue = c->residue;
 	/* unlock */
 
@@ -517,15 +528,6 @@
 	d->pd0 = DESC_TYPE_TEARD << DESC_TYPE;
 }
 
-static u32 cppi41_pop_desc(struct cppi41_dd *cdd, unsigned queue_num)
-{
-	u32 desc;
-
-	desc = cppi_readl(cdd->qmgr_mem + QMGR_QUEUE_D(queue_num));
-	desc &= ~0x1f;
-	return desc;
-}
-
 static int cppi41_tear_down_chan(struct cppi41_channel *c)
 {
 	struct cppi41_dd *cdd = c->cdd;
@@ -561,36 +563,26 @@
 		c->td_retry = 100;
 	}
 
-	if (!c->td_seen) {
-		unsigned td_comp_queue;
+	if (!c->td_seen || !c->td_desc_seen) {
 
-		if (c->is_tx)
-			td_comp_queue =  cdd->td_queue.complete;
-		else
-			td_comp_queue =  c->q_comp_num;
+		desc_phys = cppi41_pop_desc(cdd, cdd->td_queue.complete);
+		if (!desc_phys)
+			desc_phys = cppi41_pop_desc(cdd, c->q_comp_num);
 
-		desc_phys = cppi41_pop_desc(cdd, td_comp_queue);
-		if (desc_phys) {
-			__iormb();
-
-			if (desc_phys == td_desc_phys) {
-				u32 pd0;
-				pd0 = td->pd0;
-				WARN_ON((pd0 >> DESC_TYPE) != DESC_TYPE_TEARD);
-				WARN_ON(!c->is_tx && !(pd0 & TD_DESC_IS_RX));
-				WARN_ON((pd0 & 0x1f) != c->port_num);
-			} else {
-				WARN_ON_ONCE(1);
-			}
-			c->td_seen = 1;
-		}
-	}
-	if (!c->td_desc_seen) {
-		desc_phys = cppi41_pop_desc(cdd, c->q_comp_num);
-		if (desc_phys) {
-			__iormb();
-			WARN_ON(c->desc_phys != desc_phys);
+		if (desc_phys == c->desc_phys) {
 			c->td_desc_seen = 1;
+
+		} else if (desc_phys == td_desc_phys) {
+			u32 pd0;
+
+			__iormb();
+			pd0 = td->pd0;
+			WARN_ON((pd0 >> DESC_TYPE) != DESC_TYPE_TEARD);
+			WARN_ON(!c->is_tx && !(pd0 & TD_DESC_IS_RX));
+			WARN_ON((pd0 & 0x1f) != c->port_num);
+			c->td_seen = 1;
+		} else if (desc_phys) {
+			WARN_ON_ONCE(1);
 		}
 	}
 	c->td_retry--;
@@ -609,7 +601,7 @@
 
 	WARN_ON(!c->td_retry);
 	if (!c->td_desc_seen) {
-		desc_phys = cppi_readl(cdd->qmgr_mem + QMGR_QUEUE_D(c->q_num));
+		desc_phys = cppi41_pop_desc(cdd, c->q_num);
 		WARN_ON(!desc_phys);
 	}
 
@@ -674,14 +666,14 @@
 	}
 }
 
-static int cppi41_add_chans(struct platform_device *pdev, struct cppi41_dd *cdd)
+static int cppi41_add_chans(struct device *dev, struct cppi41_dd *cdd)
 {
 	struct cppi41_channel *cchan;
 	int i;
 	int ret;
 	u32 n_chans;
 
-	ret = of_property_read_u32(pdev->dev.of_node, "#dma-channels",
+	ret = of_property_read_u32(dev->of_node, "#dma-channels",
 			&n_chans);
 	if (ret)
 		return ret;
@@ -719,7 +711,7 @@
 	return -ENOMEM;
 }
 
-static void purge_descs(struct platform_device *pdev, struct cppi41_dd *cdd)
+static void purge_descs(struct device *dev, struct cppi41_dd *cdd)
 {
 	unsigned int mem_decs;
 	int i;
@@ -731,7 +723,7 @@
 		cppi_writel(0, cdd->qmgr_mem + QMGR_MEMBASE(i));
 		cppi_writel(0, cdd->qmgr_mem + QMGR_MEMCTRL(i));
 
-		dma_free_coherent(&pdev->dev, mem_decs, cdd->cd,
+		dma_free_coherent(dev, mem_decs, cdd->cd,
 				cdd->descs_phys);
 	}
 }
@@ -741,19 +733,19 @@
 	cppi_writel(0, cdd->sched_mem + DMA_SCHED_CTRL);
 }
 
-static void deinit_cpii41(struct platform_device *pdev, struct cppi41_dd *cdd)
+static void deinit_cppi41(struct device *dev, struct cppi41_dd *cdd)
 {
 	disable_sched(cdd);
 
-	purge_descs(pdev, cdd);
+	purge_descs(dev, cdd);
 
 	cppi_writel(0, cdd->qmgr_mem + QMGR_LRAM0_BASE);
 	cppi_writel(0, cdd->qmgr_mem + QMGR_LRAM0_BASE);
-	dma_free_coherent(&pdev->dev, QMGR_SCRATCH_SIZE, cdd->qmgr_scratch,
+	dma_free_coherent(dev, QMGR_SCRATCH_SIZE, cdd->qmgr_scratch,
 			cdd->scratch_phys);
 }
 
-static int init_descs(struct platform_device *pdev, struct cppi41_dd *cdd)
+static int init_descs(struct device *dev, struct cppi41_dd *cdd)
 {
 	unsigned int desc_size;
 	unsigned int mem_decs;
@@ -777,7 +769,7 @@
 		reg |= ilog2(ALLOC_DECS_NUM) - 5;
 
 		BUILD_BUG_ON(DESCS_AREAS != 1);
-		cdd->cd = dma_alloc_coherent(&pdev->dev, mem_decs,
+		cdd->cd = dma_alloc_coherent(dev, mem_decs,
 				&cdd->descs_phys, GFP_KERNEL);
 		if (!cdd->cd)
 			return -ENOMEM;
@@ -813,12 +805,12 @@
 	cppi_writel(reg, cdd->sched_mem + DMA_SCHED_CTRL);
 }
 
-static int init_cppi41(struct platform_device *pdev, struct cppi41_dd *cdd)
+static int init_cppi41(struct device *dev, struct cppi41_dd *cdd)
 {
 	int ret;
 
 	BUILD_BUG_ON(QMGR_SCRATCH_SIZE > ((1 << 14) - 1));
-	cdd->qmgr_scratch = dma_alloc_coherent(&pdev->dev, QMGR_SCRATCH_SIZE,
+	cdd->qmgr_scratch = dma_alloc_coherent(dev, QMGR_SCRATCH_SIZE,
 			&cdd->scratch_phys, GFP_KERNEL);
 	if (!cdd->qmgr_scratch)
 		return -ENOMEM;
@@ -827,7 +819,7 @@
 	cppi_writel(QMGR_SCRATCH_SIZE, cdd->qmgr_mem + QMGR_LRAM_SIZE);
 	cppi_writel(0, cdd->qmgr_mem + QMGR_LRAM1_BASE);
 
-	ret = init_descs(pdev, cdd);
+	ret = init_descs(dev, cdd);
 	if (ret)
 		goto err_td;
 
@@ -835,7 +827,7 @@
 	init_sched(cdd);
 	return 0;
 err_td:
-	deinit_cpii41(pdev, cdd);
+	deinit_cppi41(dev, cdd);
 	return ret;
 }
 
@@ -914,11 +906,11 @@
 };
 MODULE_DEVICE_TABLE(of, cppi41_dma_ids);
 
-static const struct cppi_glue_infos *get_glue_info(struct platform_device *pdev)
+static const struct cppi_glue_infos *get_glue_info(struct device *dev)
 {
 	const struct of_device_id *of_id;
 
-	of_id = of_match_node(cppi41_dma_ids, pdev->dev.of_node);
+	of_id = of_match_node(cppi41_dma_ids, dev->of_node);
 	if (!of_id)
 		return NULL;
 	return of_id->data;
@@ -927,11 +919,12 @@
 static int cppi41_dma_probe(struct platform_device *pdev)
 {
 	struct cppi41_dd *cdd;
+	struct device *dev = &pdev->dev;
 	const struct cppi_glue_infos *glue_info;
 	int irq;
 	int ret;
 
-	glue_info = get_glue_info(pdev);
+	glue_info = get_glue_info(dev);
 	if (!glue_info)
 		return -EINVAL;
 
@@ -946,14 +939,14 @@
 	cdd->ddev.device_issue_pending = cppi41_dma_issue_pending;
 	cdd->ddev.device_prep_slave_sg = cppi41_dma_prep_slave_sg;
 	cdd->ddev.device_control = cppi41_dma_control;
-	cdd->ddev.dev = &pdev->dev;
+	cdd->ddev.dev = dev;
 	INIT_LIST_HEAD(&cdd->ddev.channels);
 	cpp41_dma_info.dma_cap = cdd->ddev.cap_mask;
 
-	cdd->usbss_mem = of_iomap(pdev->dev.of_node, 0);
-	cdd->ctrl_mem = of_iomap(pdev->dev.of_node, 1);
-	cdd->sched_mem = of_iomap(pdev->dev.of_node, 2);
-	cdd->qmgr_mem = of_iomap(pdev->dev.of_node, 3);
+	cdd->usbss_mem = of_iomap(dev->of_node, 0);
+	cdd->ctrl_mem = of_iomap(dev->of_node, 1);
+	cdd->sched_mem = of_iomap(dev->of_node, 2);
+	cdd->qmgr_mem = of_iomap(dev->of_node, 3);
 
 	if (!cdd->usbss_mem || !cdd->ctrl_mem || !cdd->sched_mem ||
 			!cdd->qmgr_mem) {
@@ -961,31 +954,31 @@
 		goto err_remap;
 	}
 
-	pm_runtime_enable(&pdev->dev);
-	ret = pm_runtime_get_sync(&pdev->dev);
-	if (ret)
+	pm_runtime_enable(dev);
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0)
 		goto err_get_sync;
 
 	cdd->queues_rx = glue_info->queues_rx;
 	cdd->queues_tx = glue_info->queues_tx;
 	cdd->td_queue = glue_info->td_queue;
 
-	ret = init_cppi41(pdev, cdd);
+	ret = init_cppi41(dev, cdd);
 	if (ret)
 		goto err_init_cppi;
 
-	ret = cppi41_add_chans(pdev, cdd);
+	ret = cppi41_add_chans(dev, cdd);
 	if (ret)
 		goto err_chans;
 
-	irq = irq_of_parse_and_map(pdev->dev.of_node, 0);
+	irq = irq_of_parse_and_map(dev->of_node, 0);
 	if (!irq)
 		goto err_irq;
 
 	cppi_writel(USBSS_IRQ_PD_COMP, cdd->usbss_mem + USBSS_IRQ_ENABLER);
 
 	ret = request_irq(irq, glue_info->isr, IRQF_SHARED,
-			dev_name(&pdev->dev), cdd);
+			dev_name(dev), cdd);
 	if (ret)
 		goto err_irq;
 	cdd->irq = irq;
@@ -994,7 +987,7 @@
 	if (ret)
 		goto err_dma_reg;
 
-	ret = of_dma_controller_register(pdev->dev.of_node,
+	ret = of_dma_controller_register(dev->of_node,
 			cppi41_dma_xlate, &cpp41_dma_info);
 	if (ret)
 		goto err_of;
@@ -1009,11 +1002,11 @@
 	cppi_writel(0, cdd->usbss_mem + USBSS_IRQ_CLEARR);
 	cleanup_chans(cdd);
 err_chans:
-	deinit_cpii41(pdev, cdd);
+	deinit_cppi41(dev, cdd);
 err_init_cppi:
-	pm_runtime_put(&pdev->dev);
+	pm_runtime_put(dev);
 err_get_sync:
-	pm_runtime_disable(&pdev->dev);
+	pm_runtime_disable(dev);
 	iounmap(cdd->usbss_mem);
 	iounmap(cdd->ctrl_mem);
 	iounmap(cdd->sched_mem);
@@ -1033,7 +1026,7 @@
 	cppi_writel(0, cdd->usbss_mem + USBSS_IRQ_CLEARR);
 	free_irq(cdd->irq, cdd);
 	cleanup_chans(cdd);
-	deinit_cpii41(pdev, cdd);
+	deinit_cppi41(&pdev->dev, cdd);
 	iounmap(cdd->usbss_mem);
 	iounmap(cdd->ctrl_mem);
 	iounmap(cdd->sched_mem);
@@ -1044,12 +1037,53 @@
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
+static int cppi41_suspend(struct device *dev)
+{
+	struct cppi41_dd *cdd = dev_get_drvdata(dev);
+
+	cdd->dma_tdfdq = cppi_readl(cdd->ctrl_mem + DMA_TDFDQ);
+	cppi_writel(0, cdd->usbss_mem + USBSS_IRQ_CLEARR);
+	disable_sched(cdd);
+
+	return 0;
+}
+
+static int cppi41_resume(struct device *dev)
+{
+	struct cppi41_dd *cdd = dev_get_drvdata(dev);
+	struct cppi41_channel *c;
+	int i;
+
+	for (i = 0; i < DESCS_AREAS; i++)
+		cppi_writel(cdd->descs_phys, cdd->qmgr_mem + QMGR_MEMBASE(i));
+
+	list_for_each_entry(c, &cdd->ddev.channels, chan.device_node)
+		if (!c->is_tx)
+			cppi_writel(c->q_num, c->gcr_reg + RXHPCRA0);
+
+	init_sched(cdd);
+
+	cppi_writel(cdd->dma_tdfdq, cdd->ctrl_mem + DMA_TDFDQ);
+	cppi_writel(cdd->scratch_phys, cdd->qmgr_mem + QMGR_LRAM0_BASE);
+	cppi_writel(QMGR_SCRATCH_SIZE, cdd->qmgr_mem + QMGR_LRAM_SIZE);
+	cppi_writel(0, cdd->qmgr_mem + QMGR_LRAM1_BASE);
+
+	cppi_writel(USBSS_IRQ_PD_COMP, cdd->usbss_mem + USBSS_IRQ_ENABLER);
+
+	return 0;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(cppi41_pm_ops, cppi41_suspend, cppi41_resume);
+
 static struct platform_driver cpp41_dma_driver = {
 	.probe  = cppi41_dma_probe,
 	.remove = cppi41_dma_remove,
 	.driver = {
 		.name = "cppi41-dma-engine",
 		.owner = THIS_MODULE,
+		.pm = &cppi41_pm_ops,
 		.of_match_table = of_match_ptr(cppi41_dma_ids),
 	},
 };
diff --git a/drivers/dma/dma-jz4740.c b/drivers/dma/dma-jz4740.c
index b0c0c82..94c380f 100644
--- a/drivers/dma/dma-jz4740.c
+++ b/drivers/dma/dma-jz4740.c
@@ -491,7 +491,7 @@
 	unsigned long flags;
 
 	status = dma_cookie_status(c, cookie, state);
-	if (status == DMA_SUCCESS || !state)
+	if (status == DMA_COMPLETE || !state)
 		return status;
 
 	spin_lock_irqsave(&chan->vchan.lock, flags);
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 9162ac8..ea806bd 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -65,6 +65,7 @@
 #include <linux/acpi.h>
 #include <linux/acpi_dma.h>
 #include <linux/of_dma.h>
+#include <linux/mempool.h>
 
 static DEFINE_MUTEX(dma_list_mutex);
 static DEFINE_IDR(dma_idr);
@@ -901,98 +902,132 @@
 }
 EXPORT_SYMBOL(dma_async_device_unregister);
 
-/**
- * dma_async_memcpy_buf_to_buf - offloaded copy between virtual addresses
- * @chan: DMA channel to offload copy to
- * @dest: destination address (virtual)
- * @src: source address (virtual)
- * @len: length
- *
- * Both @dest and @src must be mappable to a bus address according to the
- * DMA mapping API rules for streaming mappings.
- * Both @dest and @src must stay memory resident (kernel memory or locked
- * user space pages).
- */
-dma_cookie_t
-dma_async_memcpy_buf_to_buf(struct dma_chan *chan, void *dest,
-			void *src, size_t len)
+struct dmaengine_unmap_pool {
+	struct kmem_cache *cache;
+	const char *name;
+	mempool_t *pool;
+	size_t size;
+};
+
+#define __UNMAP_POOL(x) { .size = x, .name = "dmaengine-unmap-" __stringify(x) }
+static struct dmaengine_unmap_pool unmap_pool[] = {
+	__UNMAP_POOL(2),
+	#if IS_ENABLED(CONFIG_ASYNC_TX_DMA)
+	__UNMAP_POOL(16),
+	__UNMAP_POOL(128),
+	__UNMAP_POOL(256),
+	#endif
+};
+
+static struct dmaengine_unmap_pool *__get_unmap_pool(int nr)
 {
-	struct dma_device *dev = chan->device;
-	struct dma_async_tx_descriptor *tx;
-	dma_addr_t dma_dest, dma_src;
-	dma_cookie_t cookie;
-	unsigned long flags;
+	int order = get_count_order(nr);
 
-	dma_src = dma_map_single(dev->dev, src, len, DMA_TO_DEVICE);
-	dma_dest = dma_map_single(dev->dev, dest, len, DMA_FROM_DEVICE);
-	flags = DMA_CTRL_ACK |
-		DMA_COMPL_SRC_UNMAP_SINGLE |
-		DMA_COMPL_DEST_UNMAP_SINGLE;
-	tx = dev->device_prep_dma_memcpy(chan, dma_dest, dma_src, len, flags);
+	switch (order) {
+	case 0 ... 1:
+		return &unmap_pool[0];
+	case 2 ... 4:
+		return &unmap_pool[1];
+	case 5 ... 7:
+		return &unmap_pool[2];
+	case 8:
+		return &unmap_pool[3];
+	default:
+		BUG();
+		return NULL;
+	}
+}
 
-	if (!tx) {
-		dma_unmap_single(dev->dev, dma_src, len, DMA_TO_DEVICE);
-		dma_unmap_single(dev->dev, dma_dest, len, DMA_FROM_DEVICE);
-		return -ENOMEM;
+static void dmaengine_unmap(struct kref *kref)
+{
+	struct dmaengine_unmap_data *unmap = container_of(kref, typeof(*unmap), kref);
+	struct device *dev = unmap->dev;
+	int cnt, i;
+
+	cnt = unmap->to_cnt;
+	for (i = 0; i < cnt; i++)
+		dma_unmap_page(dev, unmap->addr[i], unmap->len,
+			       DMA_TO_DEVICE);
+	cnt += unmap->from_cnt;
+	for (; i < cnt; i++)
+		dma_unmap_page(dev, unmap->addr[i], unmap->len,
+			       DMA_FROM_DEVICE);
+	cnt += unmap->bidi_cnt;
+	for (; i < cnt; i++) {
+		if (unmap->addr[i] == 0)
+			continue;
+		dma_unmap_page(dev, unmap->addr[i], unmap->len,
+			       DMA_BIDIRECTIONAL);
+	}
+	mempool_free(unmap, __get_unmap_pool(cnt)->pool);
+}
+
+void dmaengine_unmap_put(struct dmaengine_unmap_data *unmap)
+{
+	if (unmap)
+		kref_put(&unmap->kref, dmaengine_unmap);
+}
+EXPORT_SYMBOL_GPL(dmaengine_unmap_put);
+
+static void dmaengine_destroy_unmap_pool(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(unmap_pool); i++) {
+		struct dmaengine_unmap_pool *p = &unmap_pool[i];
+
+		if (p->pool)
+			mempool_destroy(p->pool);
+		p->pool = NULL;
+		if (p->cache)
+			kmem_cache_destroy(p->cache);
+		p->cache = NULL;
+	}
+}
+
+static int __init dmaengine_init_unmap_pool(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(unmap_pool); i++) {
+		struct dmaengine_unmap_pool *p = &unmap_pool[i];
+		size_t size;
+
+		size = sizeof(struct dmaengine_unmap_data) +
+		       sizeof(dma_addr_t) * p->size;
+
+		p->cache = kmem_cache_create(p->name, size, 0,
+					     SLAB_HWCACHE_ALIGN, NULL);
+		if (!p->cache)
+			break;
+		p->pool = mempool_create_slab_pool(1, p->cache);
+		if (!p->pool)
+			break;
 	}
 
-	tx->callback = NULL;
-	cookie = tx->tx_submit(tx);
+	if (i == ARRAY_SIZE(unmap_pool))
+		return 0;
 
-	preempt_disable();
-	__this_cpu_add(chan->local->bytes_transferred, len);
-	__this_cpu_inc(chan->local->memcpy_count);
-	preempt_enable();
-
-	return cookie;
+	dmaengine_destroy_unmap_pool();
+	return -ENOMEM;
 }
-EXPORT_SYMBOL(dma_async_memcpy_buf_to_buf);
 
-/**
- * dma_async_memcpy_buf_to_pg - offloaded copy from address to page
- * @chan: DMA channel to offload copy to
- * @page: destination page
- * @offset: offset in page to copy to
- * @kdata: source address (virtual)
- * @len: length
- *
- * Both @page/@offset and @kdata must be mappable to a bus address according
- * to the DMA mapping API rules for streaming mappings.
- * Both @page/@offset and @kdata must stay memory resident (kernel memory or
- * locked user space pages)
- */
-dma_cookie_t
-dma_async_memcpy_buf_to_pg(struct dma_chan *chan, struct page *page,
-			unsigned int offset, void *kdata, size_t len)
+struct dmaengine_unmap_data *
+dmaengine_get_unmap_data(struct device *dev, int nr, gfp_t flags)
 {
-	struct dma_device *dev = chan->device;
-	struct dma_async_tx_descriptor *tx;
-	dma_addr_t dma_dest, dma_src;
-	dma_cookie_t cookie;
-	unsigned long flags;
+	struct dmaengine_unmap_data *unmap;
 
-	dma_src = dma_map_single(dev->dev, kdata, len, DMA_TO_DEVICE);
-	dma_dest = dma_map_page(dev->dev, page, offset, len, DMA_FROM_DEVICE);
-	flags = DMA_CTRL_ACK | DMA_COMPL_SRC_UNMAP_SINGLE;
-	tx = dev->device_prep_dma_memcpy(chan, dma_dest, dma_src, len, flags);
+	unmap = mempool_alloc(__get_unmap_pool(nr)->pool, flags);
+	if (!unmap)
+		return NULL;
 
-	if (!tx) {
-		dma_unmap_single(dev->dev, dma_src, len, DMA_TO_DEVICE);
-		dma_unmap_page(dev->dev, dma_dest, len, DMA_FROM_DEVICE);
-		return -ENOMEM;
-	}
+	memset(unmap, 0, sizeof(*unmap));
+	kref_init(&unmap->kref);
+	unmap->dev = dev;
 
-	tx->callback = NULL;
-	cookie = tx->tx_submit(tx);
-
-	preempt_disable();
-	__this_cpu_add(chan->local->bytes_transferred, len);
-	__this_cpu_inc(chan->local->memcpy_count);
-	preempt_enable();
-
-	return cookie;
+	return unmap;
 }
-EXPORT_SYMBOL(dma_async_memcpy_buf_to_pg);
+EXPORT_SYMBOL(dmaengine_get_unmap_data);
 
 /**
  * dma_async_memcpy_pg_to_pg - offloaded copy from page to page
@@ -1015,24 +1050,33 @@
 {
 	struct dma_device *dev = chan->device;
 	struct dma_async_tx_descriptor *tx;
-	dma_addr_t dma_dest, dma_src;
+	struct dmaengine_unmap_data *unmap;
 	dma_cookie_t cookie;
 	unsigned long flags;
 
-	dma_src = dma_map_page(dev->dev, src_pg, src_off, len, DMA_TO_DEVICE);
-	dma_dest = dma_map_page(dev->dev, dest_pg, dest_off, len,
-				DMA_FROM_DEVICE);
+	unmap = dmaengine_get_unmap_data(dev->dev, 2, GFP_NOIO);
+	if (!unmap)
+		return -ENOMEM;
+
+	unmap->to_cnt = 1;
+	unmap->from_cnt = 1;
+	unmap->addr[0] = dma_map_page(dev->dev, src_pg, src_off, len,
+				      DMA_TO_DEVICE);
+	unmap->addr[1] = dma_map_page(dev->dev, dest_pg, dest_off, len,
+				      DMA_FROM_DEVICE);
+	unmap->len = len;
 	flags = DMA_CTRL_ACK;
-	tx = dev->device_prep_dma_memcpy(chan, dma_dest, dma_src, len, flags);
+	tx = dev->device_prep_dma_memcpy(chan, unmap->addr[1], unmap->addr[0],
+					 len, flags);
 
 	if (!tx) {
-		dma_unmap_page(dev->dev, dma_src, len, DMA_TO_DEVICE);
-		dma_unmap_page(dev->dev, dma_dest, len, DMA_FROM_DEVICE);
+		dmaengine_unmap_put(unmap);
 		return -ENOMEM;
 	}
 
-	tx->callback = NULL;
+	dma_set_unmap(tx, unmap);
 	cookie = tx->tx_submit(tx);
+	dmaengine_unmap_put(unmap);
 
 	preempt_disable();
 	__this_cpu_add(chan->local->bytes_transferred, len);
@@ -1043,6 +1087,52 @@
 }
 EXPORT_SYMBOL(dma_async_memcpy_pg_to_pg);
 
+/**
+ * dma_async_memcpy_buf_to_buf - offloaded copy between virtual addresses
+ * @chan: DMA channel to offload copy to
+ * @dest: destination address (virtual)
+ * @src: source address (virtual)
+ * @len: length
+ *
+ * Both @dest and @src must be mappable to a bus address according to the
+ * DMA mapping API rules for streaming mappings.
+ * Both @dest and @src must stay memory resident (kernel memory or locked
+ * user space pages).
+ */
+dma_cookie_t
+dma_async_memcpy_buf_to_buf(struct dma_chan *chan, void *dest,
+			    void *src, size_t len)
+{
+	return dma_async_memcpy_pg_to_pg(chan, virt_to_page(dest),
+					 (unsigned long) dest & ~PAGE_MASK,
+					 virt_to_page(src),
+					 (unsigned long) src & ~PAGE_MASK, len);
+}
+EXPORT_SYMBOL(dma_async_memcpy_buf_to_buf);
+
+/**
+ * dma_async_memcpy_buf_to_pg - offloaded copy from address to page
+ * @chan: DMA channel to offload copy to
+ * @page: destination page
+ * @offset: offset in page to copy to
+ * @kdata: source address (virtual)
+ * @len: length
+ *
+ * Both @page/@offset and @kdata must be mappable to a bus address according
+ * to the DMA mapping API rules for streaming mappings.
+ * Both @page/@offset and @kdata must stay memory resident (kernel memory or
+ * locked user space pages)
+ */
+dma_cookie_t
+dma_async_memcpy_buf_to_pg(struct dma_chan *chan, struct page *page,
+			   unsigned int offset, void *kdata, size_t len)
+{
+	return dma_async_memcpy_pg_to_pg(chan, page, offset,
+					 virt_to_page(kdata),
+					 (unsigned long) kdata & ~PAGE_MASK, len);
+}
+EXPORT_SYMBOL(dma_async_memcpy_buf_to_pg);
+
 void dma_async_tx_descriptor_init(struct dma_async_tx_descriptor *tx,
 	struct dma_chan *chan)
 {
@@ -1062,7 +1152,7 @@
 	unsigned long dma_sync_wait_timeout = jiffies + msecs_to_jiffies(5000);
 
 	if (!tx)
-		return DMA_SUCCESS;
+		return DMA_COMPLETE;
 
 	while (tx->cookie == -EBUSY) {
 		if (time_after_eq(jiffies, dma_sync_wait_timeout)) {
@@ -1116,6 +1206,10 @@
 
 static int __init dma_bus_init(void)
 {
+	int err = dmaengine_init_unmap_pool();
+
+	if (err)
+		return err;
 	return class_register(&dma_devclass);
 }
 arch_initcall(dma_bus_init);
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index 92f796c..20f9a3a 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -8,6 +8,8 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/delay.h>
 #include <linux/dma-mapping.h>
 #include <linux/dmaengine.h>
@@ -19,10 +21,6 @@
 #include <linux/random.h>
 #include <linux/slab.h>
 #include <linux/wait.h>
-#include <linux/ctype.h>
-#include <linux/debugfs.h>
-#include <linux/uaccess.h>
-#include <linux/seq_file.h>
 
 static unsigned int test_buf_size = 16384;
 module_param(test_buf_size, uint, S_IRUGO | S_IWUSR);
@@ -68,92 +66,13 @@
 MODULE_PARM_DESC(timeout, "Transfer Timeout in msec (default: 3000), "
 		 "Pass -1 for infinite timeout");
 
-/* Maximum amount of mismatched bytes in buffer to print */
-#define MAX_ERROR_COUNT		32
+static bool noverify;
+module_param(noverify, bool, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(noverify, "Disable random data setup and verification");
 
-/*
- * Initialization patterns. All bytes in the source buffer has bit 7
- * set, all bytes in the destination buffer has bit 7 cleared.
- *
- * Bit 6 is set for all bytes which are to be copied by the DMA
- * engine. Bit 5 is set for all bytes which are to be overwritten by
- * the DMA engine.
- *
- * The remaining bits are the inverse of a counter which increments by
- * one for each byte address.
- */
-#define PATTERN_SRC		0x80
-#define PATTERN_DST		0x00
-#define PATTERN_COPY		0x40
-#define PATTERN_OVERWRITE	0x20
-#define PATTERN_COUNT_MASK	0x1f
-
-enum dmatest_error_type {
-	DMATEST_ET_OK,
-	DMATEST_ET_MAP_SRC,
-	DMATEST_ET_MAP_DST,
-	DMATEST_ET_PREP,
-	DMATEST_ET_SUBMIT,
-	DMATEST_ET_TIMEOUT,
-	DMATEST_ET_DMA_ERROR,
-	DMATEST_ET_DMA_IN_PROGRESS,
-	DMATEST_ET_VERIFY,
-	DMATEST_ET_VERIFY_BUF,
-};
-
-struct dmatest_verify_buffer {
-	unsigned int	index;
-	u8		expected;
-	u8		actual;
-};
-
-struct dmatest_verify_result {
-	unsigned int			error_count;
-	struct dmatest_verify_buffer	data[MAX_ERROR_COUNT];
-	u8				pattern;
-	bool				is_srcbuf;
-};
-
-struct dmatest_thread_result {
-	struct list_head	node;
-	unsigned int		n;
-	unsigned int		src_off;
-	unsigned int		dst_off;
-	unsigned int		len;
-	enum dmatest_error_type	type;
-	union {
-		unsigned long			data;
-		dma_cookie_t			cookie;
-		enum dma_status			status;
-		int				error;
-		struct dmatest_verify_result	*vr;
-	};
-};
-
-struct dmatest_result {
-	struct list_head	node;
-	char			*name;
-	struct list_head	results;
-};
-
-struct dmatest_info;
-
-struct dmatest_thread {
-	struct list_head	node;
-	struct dmatest_info	*info;
-	struct task_struct	*task;
-	struct dma_chan		*chan;
-	u8			**srcs;
-	u8			**dsts;
-	enum dma_transaction_type type;
-	bool			done;
-};
-
-struct dmatest_chan {
-	struct list_head	node;
-	struct dma_chan		*chan;
-	struct list_head	threads;
-};
+static bool verbose;
+module_param(verbose, bool, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(verbose, "Enable \"success\" result messages (default: off)");
 
 /**
  * struct dmatest_params - test parameters.
@@ -177,6 +96,7 @@
 	unsigned int	xor_sources;
 	unsigned int	pq_sources;
 	int		timeout;
+	bool		noverify;
 };
 
 /**
@@ -184,7 +104,7 @@
  * @params:		test parameters
  * @lock:		access protection to the fields of this structure
  */
-struct dmatest_info {
+static struct dmatest_info {
 	/* Test parameters */
 	struct dmatest_params	params;
 
@@ -192,16 +112,95 @@
 	struct list_head	channels;
 	unsigned int		nr_channels;
 	struct mutex		lock;
-
-	/* debugfs related stuff */
-	struct dentry		*root;
-
-	/* Test results */
-	struct list_head	results;
-	struct mutex		results_lock;
+	bool			did_init;
+} test_info = {
+	.channels = LIST_HEAD_INIT(test_info.channels),
+	.lock = __MUTEX_INITIALIZER(test_info.lock),
 };
 
-static struct dmatest_info test_info;
+static int dmatest_run_set(const char *val, const struct kernel_param *kp);
+static int dmatest_run_get(char *val, const struct kernel_param *kp);
+static struct kernel_param_ops run_ops = {
+	.set = dmatest_run_set,
+	.get = dmatest_run_get,
+};
+static bool dmatest_run;
+module_param_cb(run, &run_ops, &dmatest_run, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(run, "Run the test (default: false)");
+
+/* Maximum amount of mismatched bytes in buffer to print */
+#define MAX_ERROR_COUNT		32
+
+/*
+ * Initialization patterns. All bytes in the source buffer has bit 7
+ * set, all bytes in the destination buffer has bit 7 cleared.
+ *
+ * Bit 6 is set for all bytes which are to be copied by the DMA
+ * engine. Bit 5 is set for all bytes which are to be overwritten by
+ * the DMA engine.
+ *
+ * The remaining bits are the inverse of a counter which increments by
+ * one for each byte address.
+ */
+#define PATTERN_SRC		0x80
+#define PATTERN_DST		0x00
+#define PATTERN_COPY		0x40
+#define PATTERN_OVERWRITE	0x20
+#define PATTERN_COUNT_MASK	0x1f
+
+struct dmatest_thread {
+	struct list_head	node;
+	struct dmatest_info	*info;
+	struct task_struct	*task;
+	struct dma_chan		*chan;
+	u8			**srcs;
+	u8			**dsts;
+	enum dma_transaction_type type;
+	bool			done;
+};
+
+struct dmatest_chan {
+	struct list_head	node;
+	struct dma_chan		*chan;
+	struct list_head	threads;
+};
+
+static DECLARE_WAIT_QUEUE_HEAD(thread_wait);
+static bool wait;
+
+static bool is_threaded_test_run(struct dmatest_info *info)
+{
+	struct dmatest_chan *dtc;
+
+	list_for_each_entry(dtc, &info->channels, node) {
+		struct dmatest_thread *thread;
+
+		list_for_each_entry(thread, &dtc->threads, node) {
+			if (!thread->done)
+				return true;
+		}
+	}
+
+	return false;
+}
+
+static int dmatest_wait_get(char *val, const struct kernel_param *kp)
+{
+	struct dmatest_info *info = &test_info;
+	struct dmatest_params *params = &info->params;
+
+	if (params->iterations)
+		wait_event(thread_wait, !is_threaded_test_run(info));
+	wait = true;
+	return param_get_bool(val, kp);
+}
+
+static struct kernel_param_ops wait_ops = {
+	.get = dmatest_wait_get,
+	.set = param_set_bool,
+};
+module_param_cb(wait, &wait_ops, &wait, S_IRUGO);
+MODULE_PARM_DESC(wait, "Wait for tests to complete (default: false)");
 
 static bool dmatest_match_channel(struct dmatest_params *params,
 		struct dma_chan *chan)
@@ -223,7 +222,7 @@
 {
 	unsigned long buf;
 
-	get_random_bytes(&buf, sizeof(buf));
+	prandom_bytes(&buf, sizeof(buf));
 	return buf;
 }
 
@@ -262,9 +261,31 @@
 	}
 }
 
-static unsigned int dmatest_verify(struct dmatest_verify_result *vr, u8 **bufs,
-		unsigned int start, unsigned int end, unsigned int counter,
-		u8 pattern, bool is_srcbuf)
+static void dmatest_mismatch(u8 actual, u8 pattern, unsigned int index,
+		unsigned int counter, bool is_srcbuf)
+{
+	u8		diff = actual ^ pattern;
+	u8		expected = pattern | (~counter & PATTERN_COUNT_MASK);
+	const char	*thread_name = current->comm;
+
+	if (is_srcbuf)
+		pr_warn("%s: srcbuf[0x%x] overwritten! Expected %02x, got %02x\n",
+			thread_name, index, expected, actual);
+	else if ((pattern & PATTERN_COPY)
+			&& (diff & (PATTERN_COPY | PATTERN_OVERWRITE)))
+		pr_warn("%s: dstbuf[0x%x] not copied! Expected %02x, got %02x\n",
+			thread_name, index, expected, actual);
+	else if (diff & PATTERN_SRC)
+		pr_warn("%s: dstbuf[0x%x] was copied! Expected %02x, got %02x\n",
+			thread_name, index, expected, actual);
+	else
+		pr_warn("%s: dstbuf[0x%x] mismatch! Expected %02x, got %02x\n",
+			thread_name, index, expected, actual);
+}
+
+static unsigned int dmatest_verify(u8 **bufs, unsigned int start,
+		unsigned int end, unsigned int counter, u8 pattern,
+		bool is_srcbuf)
 {
 	unsigned int i;
 	unsigned int error_count = 0;
@@ -272,7 +293,6 @@
 	u8 expected;
 	u8 *buf;
 	unsigned int counter_orig = counter;
-	struct dmatest_verify_buffer *vb;
 
 	for (; (buf = *bufs); bufs++) {
 		counter = counter_orig;
@@ -280,12 +300,9 @@
 			actual = buf[i];
 			expected = pattern | (~counter & PATTERN_COUNT_MASK);
 			if (actual != expected) {
-				if (error_count < MAX_ERROR_COUNT && vr) {
-					vb = &vr->data[error_count];
-					vb->index = i;
-					vb->expected = expected;
-					vb->actual = actual;
-				}
+				if (error_count < MAX_ERROR_COUNT)
+					dmatest_mismatch(actual, pattern, i,
+							 counter, is_srcbuf);
 				error_count++;
 			}
 			counter++;
@@ -293,7 +310,7 @@
 	}
 
 	if (error_count > MAX_ERROR_COUNT)
-		pr_warning("%s: %u errors suppressed\n",
+		pr_warn("%s: %u errors suppressed\n",
 			current->comm, error_count - MAX_ERROR_COUNT);
 
 	return error_count;
@@ -313,20 +330,6 @@
 	wake_up_all(done->wait);
 }
 
-static inline void unmap_src(struct device *dev, dma_addr_t *addr, size_t len,
-			     unsigned int count)
-{
-	while (count--)
-		dma_unmap_single(dev, addr[count], len, DMA_TO_DEVICE);
-}
-
-static inline void unmap_dst(struct device *dev, dma_addr_t *addr, size_t len,
-			     unsigned int count)
-{
-	while (count--)
-		dma_unmap_single(dev, addr[count], len, DMA_BIDIRECTIONAL);
-}
-
 static unsigned int min_odd(unsigned int x, unsigned int y)
 {
 	unsigned int val = min(x, y);
@@ -334,172 +337,49 @@
 	return val % 2 ? val : val - 1;
 }
 
-static char *verify_result_get_one(struct dmatest_verify_result *vr,
-		unsigned int i)
+static void result(const char *err, unsigned int n, unsigned int src_off,
+		   unsigned int dst_off, unsigned int len, unsigned long data)
 {
-	struct dmatest_verify_buffer *vb = &vr->data[i];
-	u8 diff = vb->actual ^ vr->pattern;
-	static char buf[512];
-	char *msg;
-
-	if (vr->is_srcbuf)
-		msg = "srcbuf overwritten!";
-	else if ((vr->pattern & PATTERN_COPY)
-			&& (diff & (PATTERN_COPY | PATTERN_OVERWRITE)))
-		msg = "dstbuf not copied!";
-	else if (diff & PATTERN_SRC)
-		msg = "dstbuf was copied!";
-	else
-		msg = "dstbuf mismatch!";
-
-	snprintf(buf, sizeof(buf) - 1, "%s [0x%x] Expected %02x, got %02x", msg,
-		 vb->index, vb->expected, vb->actual);
-
-	return buf;
+	pr_info("%s: result #%u: '%s' with src_off=0x%x dst_off=0x%x len=0x%x (%lu)",
+		current->comm, n, err, src_off, dst_off, len, data);
 }
 
-static char *thread_result_get(const char *name,
-		struct dmatest_thread_result *tr)
+static void dbg_result(const char *err, unsigned int n, unsigned int src_off,
+		       unsigned int dst_off, unsigned int len,
+		       unsigned long data)
 {
-	static const char * const messages[] = {
-		[DMATEST_ET_OK]			= "No errors",
-		[DMATEST_ET_MAP_SRC]		= "src mapping error",
-		[DMATEST_ET_MAP_DST]		= "dst mapping error",
-		[DMATEST_ET_PREP]		= "prep error",
-		[DMATEST_ET_SUBMIT]		= "submit error",
-		[DMATEST_ET_TIMEOUT]		= "test timed out",
-		[DMATEST_ET_DMA_ERROR]		=
-			"got completion callback (DMA_ERROR)",
-		[DMATEST_ET_DMA_IN_PROGRESS]	=
-			"got completion callback (DMA_IN_PROGRESS)",
-		[DMATEST_ET_VERIFY]		= "errors",
-		[DMATEST_ET_VERIFY_BUF]		= "verify errors",
-	};
-	static char buf[512];
-
-	snprintf(buf, sizeof(buf) - 1,
-		 "%s: #%u: %s with src_off=0x%x ""dst_off=0x%x len=0x%x (%lu)",
-		 name, tr->n, messages[tr->type], tr->src_off, tr->dst_off,
-		 tr->len, tr->data);
-
-	return buf;
+	pr_debug("%s: result #%u: '%s' with src_off=0x%x dst_off=0x%x len=0x%x (%lu)",
+		   current->comm, n, err, src_off, dst_off, len, data);
 }
 
-static int thread_result_add(struct dmatest_info *info,
-		struct dmatest_result *r, enum dmatest_error_type type,
-		unsigned int n, unsigned int src_off, unsigned int dst_off,
-		unsigned int len, unsigned long data)
+#define verbose_result(err, n, src_off, dst_off, len, data) ({ \
+	if (verbose) \
+		result(err, n, src_off, dst_off, len, data); \
+	else \
+		dbg_result(err, n, src_off, dst_off, len, data); \
+})
+
+static unsigned long long dmatest_persec(s64 runtime, unsigned int val)
 {
-	struct dmatest_thread_result *tr;
+	unsigned long long per_sec = 1000000;
 
-	tr = kzalloc(sizeof(*tr), GFP_KERNEL);
-	if (!tr)
-		return -ENOMEM;
+	if (runtime <= 0)
+		return 0;
 
-	tr->type = type;
-	tr->n = n;
-	tr->src_off = src_off;
-	tr->dst_off = dst_off;
-	tr->len = len;
-	tr->data = data;
+	/* drop precision until runtime is 32-bits */
+	while (runtime > UINT_MAX) {
+		runtime >>= 1;
+		per_sec <<= 1;
+	}
 
-	mutex_lock(&info->results_lock);
-	list_add_tail(&tr->node, &r->results);
-	mutex_unlock(&info->results_lock);
-
-	if (tr->type == DMATEST_ET_OK)
-		pr_debug("%s\n", thread_result_get(r->name, tr));
-	else
-		pr_warn("%s\n", thread_result_get(r->name, tr));
-
-	return 0;
+	per_sec *= val;
+	do_div(per_sec, runtime);
+	return per_sec;
 }
 
-static unsigned int verify_result_add(struct dmatest_info *info,
-		struct dmatest_result *r, unsigned int n,
-		unsigned int src_off, unsigned int dst_off, unsigned int len,
-		u8 **bufs, int whence, unsigned int counter, u8 pattern,
-		bool is_srcbuf)
+static unsigned long long dmatest_KBs(s64 runtime, unsigned long long len)
 {
-	struct dmatest_verify_result *vr;
-	unsigned int error_count;
-	unsigned int buf_off = is_srcbuf ? src_off : dst_off;
-	unsigned int start, end;
-
-	if (whence < 0) {
-		start = 0;
-		end = buf_off;
-	} else if (whence > 0) {
-		start = buf_off + len;
-		end = info->params.buf_size;
-	} else {
-		start = buf_off;
-		end = buf_off + len;
-	}
-
-	vr = kmalloc(sizeof(*vr), GFP_KERNEL);
-	if (!vr) {
-		pr_warn("dmatest: No memory to store verify result\n");
-		return dmatest_verify(NULL, bufs, start, end, counter, pattern,
-				      is_srcbuf);
-	}
-
-	vr->pattern = pattern;
-	vr->is_srcbuf = is_srcbuf;
-
-	error_count = dmatest_verify(vr, bufs, start, end, counter, pattern,
-				     is_srcbuf);
-	if (error_count) {
-		vr->error_count = error_count;
-		thread_result_add(info, r, DMATEST_ET_VERIFY_BUF, n, src_off,
-				  dst_off, len, (unsigned long)vr);
-		return error_count;
-	}
-
-	kfree(vr);
-	return 0;
-}
-
-static void result_free(struct dmatest_info *info, const char *name)
-{
-	struct dmatest_result *r, *_r;
-
-	mutex_lock(&info->results_lock);
-	list_for_each_entry_safe(r, _r, &info->results, node) {
-		struct dmatest_thread_result *tr, *_tr;
-
-		if (name && strcmp(r->name, name))
-			continue;
-
-		list_for_each_entry_safe(tr, _tr, &r->results, node) {
-			if (tr->type == DMATEST_ET_VERIFY_BUF)
-				kfree(tr->vr);
-			list_del(&tr->node);
-			kfree(tr);
-		}
-
-		kfree(r->name);
-		list_del(&r->node);
-		kfree(r);
-	}
-
-	mutex_unlock(&info->results_lock);
-}
-
-static struct dmatest_result *result_init(struct dmatest_info *info,
-		const char *name)
-{
-	struct dmatest_result *r;
-
-	r = kzalloc(sizeof(*r), GFP_KERNEL);
-	if (r) {
-		r->name = kstrdup(name, GFP_KERNEL);
-		INIT_LIST_HEAD(&r->results);
-		mutex_lock(&info->results_lock);
-		list_add_tail(&r->node, &info->results);
-		mutex_unlock(&info->results_lock);
-	}
-	return r;
+	return dmatest_persec(runtime, len >> 10);
 }
 
 /*
@@ -525,7 +405,6 @@
 	struct dmatest_params	*params;
 	struct dma_chan		*chan;
 	struct dma_device	*dev;
-	const char		*thread_name;
 	unsigned int		src_off, dst_off, len;
 	unsigned int		error_count;
 	unsigned int		failed_tests = 0;
@@ -538,9 +417,10 @@
 	int			src_cnt;
 	int			dst_cnt;
 	int			i;
-	struct dmatest_result	*result;
+	ktime_t			ktime;
+	s64			runtime = 0;
+	unsigned long long	total_len = 0;
 
-	thread_name = current->comm;
 	set_freezable();
 
 	ret = -ENOMEM;
@@ -570,10 +450,6 @@
 	} else
 		goto err_thread_type;
 
-	result = result_init(info, thread_name);
-	if (!result)
-		goto err_srcs;
-
 	thread->srcs = kcalloc(src_cnt+1, sizeof(u8 *), GFP_KERNEL);
 	if (!thread->srcs)
 		goto err_srcs;
@@ -597,17 +473,17 @@
 	set_user_nice(current, 10);
 
 	/*
-	 * src buffers are freed by the DMAEngine code with dma_unmap_single()
-	 * dst buffers are freed by ourselves below
+	 * src and dst buffers are freed by ourselves below
 	 */
-	flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT
-	      | DMA_COMPL_SKIP_DEST_UNMAP | DMA_COMPL_SRC_UNMAP_SINGLE;
+	flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT;
 
+	ktime = ktime_get();
 	while (!kthread_should_stop()
 	       && !(params->iterations && total_tests >= params->iterations)) {
 		struct dma_async_tx_descriptor *tx = NULL;
-		dma_addr_t dma_srcs[src_cnt];
-		dma_addr_t dma_dsts[dst_cnt];
+		struct dmaengine_unmap_data *um;
+		dma_addr_t srcs[src_cnt];
+		dma_addr_t *dsts;
 		u8 align = 0;
 
 		total_tests++;
@@ -626,81 +502,103 @@
 			break;
 		}
 
-		len = dmatest_random() % params->buf_size + 1;
+		if (params->noverify) {
+			len = params->buf_size;
+			src_off = 0;
+			dst_off = 0;
+		} else {
+			len = dmatest_random() % params->buf_size + 1;
+			len = (len >> align) << align;
+			if (!len)
+				len = 1 << align;
+			src_off = dmatest_random() % (params->buf_size - len + 1);
+			dst_off = dmatest_random() % (params->buf_size - len + 1);
+
+			src_off = (src_off >> align) << align;
+			dst_off = (dst_off >> align) << align;
+
+			dmatest_init_srcs(thread->srcs, src_off, len,
+					  params->buf_size);
+			dmatest_init_dsts(thread->dsts, dst_off, len,
+					  params->buf_size);
+		}
+
 		len = (len >> align) << align;
 		if (!len)
 			len = 1 << align;
-		src_off = dmatest_random() % (params->buf_size - len + 1);
-		dst_off = dmatest_random() % (params->buf_size - len + 1);
+		total_len += len;
 
-		src_off = (src_off >> align) << align;
-		dst_off = (dst_off >> align) << align;
+		um = dmaengine_get_unmap_data(dev->dev, src_cnt+dst_cnt,
+					      GFP_KERNEL);
+		if (!um) {
+			failed_tests++;
+			result("unmap data NULL", total_tests,
+			       src_off, dst_off, len, ret);
+			continue;
+		}
 
-		dmatest_init_srcs(thread->srcs, src_off, len, params->buf_size);
-		dmatest_init_dsts(thread->dsts, dst_off, len, params->buf_size);
-
+		um->len = params->buf_size;
 		for (i = 0; i < src_cnt; i++) {
-			u8 *buf = thread->srcs[i] + src_off;
+			unsigned long buf = (unsigned long) thread->srcs[i];
+			struct page *pg = virt_to_page(buf);
+			unsigned pg_off = buf & ~PAGE_MASK;
 
-			dma_srcs[i] = dma_map_single(dev->dev, buf, len,
-						     DMA_TO_DEVICE);
-			ret = dma_mapping_error(dev->dev, dma_srcs[i]);
+			um->addr[i] = dma_map_page(dev->dev, pg, pg_off,
+						   um->len, DMA_TO_DEVICE);
+			srcs[i] = um->addr[i] + src_off;
+			ret = dma_mapping_error(dev->dev, um->addr[i]);
 			if (ret) {
-				unmap_src(dev->dev, dma_srcs, len, i);
-				thread_result_add(info, result,
-						  DMATEST_ET_MAP_SRC,
-						  total_tests, src_off, dst_off,
-						  len, ret);
+				dmaengine_unmap_put(um);
+				result("src mapping error", total_tests,
+				       src_off, dst_off, len, ret);
 				failed_tests++;
 				continue;
 			}
+			um->to_cnt++;
 		}
 		/* map with DMA_BIDIRECTIONAL to force writeback/invalidate */
+		dsts = &um->addr[src_cnt];
 		for (i = 0; i < dst_cnt; i++) {
-			dma_dsts[i] = dma_map_single(dev->dev, thread->dsts[i],
-						     params->buf_size,
-						     DMA_BIDIRECTIONAL);
-			ret = dma_mapping_error(dev->dev, dma_dsts[i]);
+			unsigned long buf = (unsigned long) thread->dsts[i];
+			struct page *pg = virt_to_page(buf);
+			unsigned pg_off = buf & ~PAGE_MASK;
+
+			dsts[i] = dma_map_page(dev->dev, pg, pg_off, um->len,
+					       DMA_BIDIRECTIONAL);
+			ret = dma_mapping_error(dev->dev, dsts[i]);
 			if (ret) {
-				unmap_src(dev->dev, dma_srcs, len, src_cnt);
-				unmap_dst(dev->dev, dma_dsts, params->buf_size,
-					  i);
-				thread_result_add(info, result,
-						  DMATEST_ET_MAP_DST,
-						  total_tests, src_off, dst_off,
-						  len, ret);
+				dmaengine_unmap_put(um);
+				result("dst mapping error", total_tests,
+				       src_off, dst_off, len, ret);
 				failed_tests++;
 				continue;
 			}
+			um->bidi_cnt++;
 		}
 
 		if (thread->type == DMA_MEMCPY)
 			tx = dev->device_prep_dma_memcpy(chan,
-							 dma_dsts[0] + dst_off,
-							 dma_srcs[0], len,
-							 flags);
+							 dsts[0] + dst_off,
+							 srcs[0], len, flags);
 		else if (thread->type == DMA_XOR)
 			tx = dev->device_prep_dma_xor(chan,
-						      dma_dsts[0] + dst_off,
-						      dma_srcs, src_cnt,
+						      dsts[0] + dst_off,
+						      srcs, src_cnt,
 						      len, flags);
 		else if (thread->type == DMA_PQ) {
 			dma_addr_t dma_pq[dst_cnt];
 
 			for (i = 0; i < dst_cnt; i++)
-				dma_pq[i] = dma_dsts[i] + dst_off;
-			tx = dev->device_prep_dma_pq(chan, dma_pq, dma_srcs,
+				dma_pq[i] = dsts[i] + dst_off;
+			tx = dev->device_prep_dma_pq(chan, dma_pq, srcs,
 						     src_cnt, pq_coefs,
 						     len, flags);
 		}
 
 		if (!tx) {
-			unmap_src(dev->dev, dma_srcs, len, src_cnt);
-			unmap_dst(dev->dev, dma_dsts, params->buf_size,
-				  dst_cnt);
-			thread_result_add(info, result, DMATEST_ET_PREP,
-					  total_tests, src_off, dst_off,
-					  len, 0);
+			dmaengine_unmap_put(um);
+			result("prep error", total_tests, src_off,
+			       dst_off, len, ret);
 			msleep(100);
 			failed_tests++;
 			continue;
@@ -712,9 +610,9 @@
 		cookie = tx->tx_submit(tx);
 
 		if (dma_submit_error(cookie)) {
-			thread_result_add(info, result, DMATEST_ET_SUBMIT,
-					  total_tests, src_off, dst_off,
-					  len, cookie);
+			dmaengine_unmap_put(um);
+			result("submit error", total_tests, src_off,
+			       dst_off, len, ret);
 			msleep(100);
 			failed_tests++;
 			continue;
@@ -735,59 +633,59 @@
 			 * free it this time?" dancing.  For now, just
 			 * leave it dangling.
 			 */
-			thread_result_add(info, result, DMATEST_ET_TIMEOUT,
-					  total_tests, src_off, dst_off,
-					  len, 0);
+			dmaengine_unmap_put(um);
+			result("test timed out", total_tests, src_off, dst_off,
+			       len, 0);
 			failed_tests++;
 			continue;
-		} else if (status != DMA_SUCCESS) {
-			enum dmatest_error_type type = (status == DMA_ERROR) ?
-				DMATEST_ET_DMA_ERROR : DMATEST_ET_DMA_IN_PROGRESS;
-			thread_result_add(info, result, type,
-					  total_tests, src_off, dst_off,
-					  len, status);
+		} else if (status != DMA_COMPLETE) {
+			dmaengine_unmap_put(um);
+			result(status == DMA_ERROR ?
+			       "completion error status" :
+			       "completion busy status", total_tests, src_off,
+			       dst_off, len, ret);
 			failed_tests++;
 			continue;
 		}
 
-		/* Unmap by myself (see DMA_COMPL_SKIP_DEST_UNMAP above) */
-		unmap_dst(dev->dev, dma_dsts, params->buf_size, dst_cnt);
+		dmaengine_unmap_put(um);
 
-		error_count = 0;
+		if (params->noverify) {
+			verbose_result("test passed", total_tests, src_off,
+				       dst_off, len, 0);
+			continue;
+		}
 
-		pr_debug("%s: verifying source buffer...\n", thread_name);
-		error_count += verify_result_add(info, result, total_tests,
-				src_off, dst_off, len, thread->srcs, -1,
+		pr_debug("%s: verifying source buffer...\n", current->comm);
+		error_count = dmatest_verify(thread->srcs, 0, src_off,
 				0, PATTERN_SRC, true);
-		error_count += verify_result_add(info, result, total_tests,
-				src_off, dst_off, len, thread->srcs, 0,
-				src_off, PATTERN_SRC | PATTERN_COPY, true);
-		error_count += verify_result_add(info, result, total_tests,
-				src_off, dst_off, len, thread->srcs, 1,
-				src_off + len, PATTERN_SRC, true);
+		error_count += dmatest_verify(thread->srcs, src_off,
+				src_off + len, src_off,
+				PATTERN_SRC | PATTERN_COPY, true);
+		error_count += dmatest_verify(thread->srcs, src_off + len,
+				params->buf_size, src_off + len,
+				PATTERN_SRC, true);
 
-		pr_debug("%s: verifying dest buffer...\n", thread_name);
-		error_count += verify_result_add(info, result, total_tests,
-				src_off, dst_off, len, thread->dsts, -1,
+		pr_debug("%s: verifying dest buffer...\n", current->comm);
+		error_count += dmatest_verify(thread->dsts, 0, dst_off,
 				0, PATTERN_DST, false);
-		error_count += verify_result_add(info, result, total_tests,
-				src_off, dst_off, len, thread->dsts, 0,
-				src_off, PATTERN_SRC | PATTERN_COPY, false);
-		error_count += verify_result_add(info, result, total_tests,
-				src_off, dst_off, len, thread->dsts, 1,
-				dst_off + len, PATTERN_DST, false);
+		error_count += dmatest_verify(thread->dsts, dst_off,
+				dst_off + len, src_off,
+				PATTERN_SRC | PATTERN_COPY, false);
+		error_count += dmatest_verify(thread->dsts, dst_off + len,
+				params->buf_size, dst_off + len,
+				PATTERN_DST, false);
 
 		if (error_count) {
-			thread_result_add(info, result, DMATEST_ET_VERIFY,
-					  total_tests, src_off, dst_off,
-					  len, error_count);
+			result("data error", total_tests, src_off, dst_off,
+			       len, error_count);
 			failed_tests++;
 		} else {
-			thread_result_add(info, result, DMATEST_ET_OK,
-					  total_tests, src_off, dst_off,
-					  len, 0);
+			verbose_result("test passed", total_tests, src_off,
+				       dst_off, len, 0);
 		}
 	}
+	runtime = ktime_us_delta(ktime_get(), ktime);
 
 	ret = 0;
 	for (i = 0; thread->dsts[i]; i++)
@@ -802,20 +700,17 @@
 err_srcs:
 	kfree(pq_coefs);
 err_thread_type:
-	pr_notice("%s: terminating after %u tests, %u failures (status %d)\n",
-			thread_name, total_tests, failed_tests, ret);
+	pr_info("%s: summary %u tests, %u failures %llu iops %llu KB/s (%d)\n",
+		current->comm, total_tests, failed_tests,
+		dmatest_persec(runtime, total_tests),
+		dmatest_KBs(runtime, total_len), ret);
 
 	/* terminate all transfers on specified channels */
 	if (ret)
 		dmaengine_terminate_all(chan);
 
 	thread->done = true;
-
-	if (params->iterations > 0)
-		while (!kthread_should_stop()) {
-			DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wait_dmatest_exit);
-			interruptible_sleep_on(&wait_dmatest_exit);
-		}
+	wake_up(&thread_wait);
 
 	return ret;
 }
@@ -828,9 +723,10 @@
 
 	list_for_each_entry_safe(thread, _thread, &dtc->threads, node) {
 		ret = kthread_stop(thread->task);
-		pr_debug("dmatest: thread %s exited with status %d\n",
-				thread->task->comm, ret);
+		pr_debug("thread %s exited with status %d\n",
+			 thread->task->comm, ret);
 		list_del(&thread->node);
+		put_task_struct(thread->task);
 		kfree(thread);
 	}
 
@@ -861,27 +757,27 @@
 	for (i = 0; i < params->threads_per_chan; i++) {
 		thread = kzalloc(sizeof(struct dmatest_thread), GFP_KERNEL);
 		if (!thread) {
-			pr_warning("dmatest: No memory for %s-%s%u\n",
-				   dma_chan_name(chan), op, i);
-
+			pr_warn("No memory for %s-%s%u\n",
+				dma_chan_name(chan), op, i);
 			break;
 		}
 		thread->info = info;
 		thread->chan = dtc->chan;
 		thread->type = type;
 		smp_wmb();
-		thread->task = kthread_run(dmatest_func, thread, "%s-%s%u",
+		thread->task = kthread_create(dmatest_func, thread, "%s-%s%u",
 				dma_chan_name(chan), op, i);
 		if (IS_ERR(thread->task)) {
-			pr_warning("dmatest: Failed to run thread %s-%s%u\n",
-					dma_chan_name(chan), op, i);
+			pr_warn("Failed to create thread %s-%s%u\n",
+				dma_chan_name(chan), op, i);
 			kfree(thread);
 			break;
 		}
 
 		/* srcbuf and dstbuf are allocated by the thread itself */
-
+		get_task_struct(thread->task);
 		list_add_tail(&thread->node, &dtc->threads);
+		wake_up_process(thread->task);
 	}
 
 	return i;
@@ -897,7 +793,7 @@
 
 	dtc = kmalloc(sizeof(struct dmatest_chan), GFP_KERNEL);
 	if (!dtc) {
-		pr_warning("dmatest: No memory for %s\n", dma_chan_name(chan));
+		pr_warn("No memory for %s\n", dma_chan_name(chan));
 		return -ENOMEM;
 	}
 
@@ -917,7 +813,7 @@
 		thread_count += cnt > 0 ? cnt : 0;
 	}
 
-	pr_info("dmatest: Started %u threads using %s\n",
+	pr_info("Started %u threads using %s\n",
 		thread_count, dma_chan_name(chan));
 
 	list_add_tail(&dtc->node, &info->channels);
@@ -937,20 +833,20 @@
 		return true;
 }
 
-static int __run_threaded_test(struct dmatest_info *info)
+static void request_channels(struct dmatest_info *info,
+			     enum dma_transaction_type type)
 {
 	dma_cap_mask_t mask;
-	struct dma_chan *chan;
-	struct dmatest_params *params = &info->params;
-	int err = 0;
 
 	dma_cap_zero(mask);
-	dma_cap_set(DMA_MEMCPY, mask);
+	dma_cap_set(type, mask);
 	for (;;) {
+		struct dmatest_params *params = &info->params;
+		struct dma_chan *chan;
+
 		chan = dma_request_channel(mask, filter, params);
 		if (chan) {
-			err = dmatest_add_channel(info, chan);
-			if (err) {
+			if (dmatest_add_channel(info, chan)) {
 				dma_release_channel(chan);
 				break; /* add_channel failed, punt */
 			}
@@ -960,57 +856,12 @@
 		    info->nr_channels >= params->max_channels)
 			break; /* we have all we need */
 	}
-	return err;
 }
 
-#ifndef MODULE
-static int run_threaded_test(struct dmatest_info *info)
-{
-	int ret;
-
-	mutex_lock(&info->lock);
-	ret = __run_threaded_test(info);
-	mutex_unlock(&info->lock);
-	return ret;
-}
-#endif
-
-static void __stop_threaded_test(struct dmatest_info *info)
-{
-	struct dmatest_chan *dtc, *_dtc;
-	struct dma_chan *chan;
-
-	list_for_each_entry_safe(dtc, _dtc, &info->channels, node) {
-		list_del(&dtc->node);
-		chan = dtc->chan;
-		dmatest_cleanup_channel(dtc);
-		pr_debug("dmatest: dropped channel %s\n", dma_chan_name(chan));
-		dma_release_channel(chan);
-	}
-
-	info->nr_channels = 0;
-}
-
-static void stop_threaded_test(struct dmatest_info *info)
-{
-	mutex_lock(&info->lock);
-	__stop_threaded_test(info);
-	mutex_unlock(&info->lock);
-}
-
-static int __restart_threaded_test(struct dmatest_info *info, bool run)
+static void run_threaded_test(struct dmatest_info *info)
 {
 	struct dmatest_params *params = &info->params;
 
-	/* Stop any running test first */
-	__stop_threaded_test(info);
-
-	if (run == false)
-		return 0;
-
-	/* Clear results from previous run */
-	result_free(info, NULL);
-
 	/* Copy test parameters */
 	params->buf_size = test_buf_size;
 	strlcpy(params->channel, strim(test_channel), sizeof(params->channel));
@@ -1021,166 +872,102 @@
 	params->xor_sources = xor_sources;
 	params->pq_sources = pq_sources;
 	params->timeout = timeout;
+	params->noverify = noverify;
+
+	request_channels(info, DMA_MEMCPY);
+	request_channels(info, DMA_XOR);
+	request_channels(info, DMA_PQ);
+}
+
+static void stop_threaded_test(struct dmatest_info *info)
+{
+	struct dmatest_chan *dtc, *_dtc;
+	struct dma_chan *chan;
+
+	list_for_each_entry_safe(dtc, _dtc, &info->channels, node) {
+		list_del(&dtc->node);
+		chan = dtc->chan;
+		dmatest_cleanup_channel(dtc);
+		pr_debug("dropped channel %s\n", dma_chan_name(chan));
+		dma_release_channel(chan);
+	}
+
+	info->nr_channels = 0;
+}
+
+static void restart_threaded_test(struct dmatest_info *info, bool run)
+{
+	/* we might be called early to set run=, defer running until all
+	 * parameters have been evaluated
+	 */
+	if (!info->did_init)
+		return;
+
+	/* Stop any running test first */
+	stop_threaded_test(info);
 
 	/* Run test with new parameters */
-	return __run_threaded_test(info);
+	run_threaded_test(info);
 }
 
-static bool __is_threaded_test_run(struct dmatest_info *info)
+static int dmatest_run_get(char *val, const struct kernel_param *kp)
 {
-	struct dmatest_chan *dtc;
-
-	list_for_each_entry(dtc, &info->channels, node) {
-		struct dmatest_thread *thread;
-
-		list_for_each_entry(thread, &dtc->threads, node) {
-			if (!thread->done)
-				return true;
-		}
-	}
-
-	return false;
-}
-
-static ssize_t dtf_read_run(struct file *file, char __user *user_buf,
-		size_t count, loff_t *ppos)
-{
-	struct dmatest_info *info = file->private_data;
-	char buf[3];
+	struct dmatest_info *info = &test_info;
 
 	mutex_lock(&info->lock);
-
-	if (__is_threaded_test_run(info)) {
-		buf[0] = 'Y';
+	if (is_threaded_test_run(info)) {
+		dmatest_run = true;
 	} else {
-		__stop_threaded_test(info);
-		buf[0] = 'N';
+		stop_threaded_test(info);
+		dmatest_run = false;
 	}
+	mutex_unlock(&info->lock);
+
+	return param_get_bool(val, kp);
+}
+
+static int dmatest_run_set(const char *val, const struct kernel_param *kp)
+{
+	struct dmatest_info *info = &test_info;
+	int ret;
+
+	mutex_lock(&info->lock);
+	ret = param_set_bool(val, kp);
+	if (ret) {
+		mutex_unlock(&info->lock);
+		return ret;
+	}
+
+	if (is_threaded_test_run(info))
+		ret = -EBUSY;
+	else if (dmatest_run)
+		restart_threaded_test(info, dmatest_run);
 
 	mutex_unlock(&info->lock);
-	buf[1] = '\n';
-	buf[2] = 0x00;
-	return simple_read_from_buffer(user_buf, count, ppos, buf, 2);
-}
 
-static ssize_t dtf_write_run(struct file *file, const char __user *user_buf,
-		size_t count, loff_t *ppos)
-{
-	struct dmatest_info *info = file->private_data;
-	char buf[16];
-	bool bv;
-	int ret = 0;
-
-	if (copy_from_user(buf, user_buf, min(count, (sizeof(buf) - 1))))
-		return -EFAULT;
-
-	if (strtobool(buf, &bv) == 0) {
-		mutex_lock(&info->lock);
-
-		if (__is_threaded_test_run(info))
-			ret = -EBUSY;
-		else
-			ret = __restart_threaded_test(info, bv);
-
-		mutex_unlock(&info->lock);
-	}
-
-	return ret ? ret : count;
-}
-
-static const struct file_operations dtf_run_fops = {
-	.read	= dtf_read_run,
-	.write	= dtf_write_run,
-	.open	= simple_open,
-	.llseek	= default_llseek,
-};
-
-static int dtf_results_show(struct seq_file *sf, void *data)
-{
-	struct dmatest_info *info = sf->private;
-	struct dmatest_result *result;
-	struct dmatest_thread_result *tr;
-	unsigned int i;
-
-	mutex_lock(&info->results_lock);
-	list_for_each_entry(result, &info->results, node) {
-		list_for_each_entry(tr, &result->results, node) {
-			seq_printf(sf, "%s\n",
-				thread_result_get(result->name, tr));
-			if (tr->type == DMATEST_ET_VERIFY_BUF) {
-				for (i = 0; i < tr->vr->error_count; i++) {
-					seq_printf(sf, "\t%s\n",
-						verify_result_get_one(tr->vr, i));
-				}
-			}
-		}
-	}
-
-	mutex_unlock(&info->results_lock);
-	return 0;
-}
-
-static int dtf_results_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, dtf_results_show, inode->i_private);
-}
-
-static const struct file_operations dtf_results_fops = {
-	.open		= dtf_results_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static int dmatest_register_dbgfs(struct dmatest_info *info)
-{
-	struct dentry *d;
-
-	d = debugfs_create_dir("dmatest", NULL);
-	if (IS_ERR(d))
-		return PTR_ERR(d);
-	if (!d)
-		goto err_root;
-
-	info->root = d;
-
-	/* Run or stop threaded test */
-	debugfs_create_file("run", S_IWUSR | S_IRUGO, info->root, info,
-			    &dtf_run_fops);
-
-	/* Results of test in progress */
-	debugfs_create_file("results", S_IRUGO, info->root, info,
-			    &dtf_results_fops);
-
-	return 0;
-
-err_root:
-	pr_err("dmatest: Failed to initialize debugfs\n");
-	return -ENOMEM;
+	return ret;
 }
 
 static int __init dmatest_init(void)
 {
 	struct dmatest_info *info = &test_info;
-	int ret;
+	struct dmatest_params *params = &info->params;
 
-	memset(info, 0, sizeof(*info));
+	if (dmatest_run) {
+		mutex_lock(&info->lock);
+		run_threaded_test(info);
+		mutex_unlock(&info->lock);
+	}
 
-	mutex_init(&info->lock);
-	INIT_LIST_HEAD(&info->channels);
+	if (params->iterations && wait)
+		wait_event(thread_wait, !is_threaded_test_run(info));
 
-	mutex_init(&info->results_lock);
-	INIT_LIST_HEAD(&info->results);
+	/* module parameters are stable, inittime tests are started,
+	 * let userspace take over 'run' control
+	 */
+	info->did_init = true;
 
-	ret = dmatest_register_dbgfs(info);
-	if (ret)
-		return ret;
-
-#ifdef MODULE
 	return 0;
-#else
-	return run_threaded_test(info);
-#endif
 }
 /* when compiled-in wait for drivers to load first */
 late_initcall(dmatest_init);
@@ -1189,9 +976,9 @@
 {
 	struct dmatest_info *info = &test_info;
 
-	debugfs_remove_recursive(info->root);
+	mutex_lock(&info->lock);
 	stop_threaded_test(info);
-	result_free(info, NULL);
+	mutex_unlock(&info->lock);
 }
 module_exit(dmatest_exit);
 
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index 89eb89f..7516be4 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -85,10 +85,6 @@
 {
 	return &chan->dev->device;
 }
-static struct device *chan2parent(struct dma_chan *chan)
-{
-	return chan->dev->device.parent;
-}
 
 static struct dw_desc *dwc_first_active(struct dw_dma_chan *dwc)
 {
@@ -311,26 +307,7 @@
 	list_splice_init(&desc->tx_list, &dwc->free_list);
 	list_move(&desc->desc_node, &dwc->free_list);
 
-	if (!is_slave_direction(dwc->direction)) {
-		struct device *parent = chan2parent(&dwc->chan);
-		if (!(txd->flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
-			if (txd->flags & DMA_COMPL_DEST_UNMAP_SINGLE)
-				dma_unmap_single(parent, desc->lli.dar,
-					desc->total_len, DMA_FROM_DEVICE);
-			else
-				dma_unmap_page(parent, desc->lli.dar,
-					desc->total_len, DMA_FROM_DEVICE);
-		}
-		if (!(txd->flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-			if (txd->flags & DMA_COMPL_SRC_UNMAP_SINGLE)
-				dma_unmap_single(parent, desc->lli.sar,
-					desc->total_len, DMA_TO_DEVICE);
-			else
-				dma_unmap_page(parent, desc->lli.sar,
-					desc->total_len, DMA_TO_DEVICE);
-		}
-	}
-
+	dma_descriptor_unmap(txd);
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
 	if (callback)
@@ -1098,13 +1075,13 @@
 	enum dma_status		ret;
 
 	ret = dma_cookie_status(chan, cookie, txstate);
-	if (ret == DMA_SUCCESS)
+	if (ret == DMA_COMPLETE)
 		return ret;
 
 	dwc_scan_descriptors(to_dw_dma(chan->device), dwc);
 
 	ret = dma_cookie_status(chan, cookie, txstate);
-	if (ret != DMA_SUCCESS)
+	if (ret != DMA_COMPLETE)
 		dma_set_residue(txstate, dwc_get_residue(dwc));
 
 	if (dwc->paused && ret == DMA_IN_PROGRESS)
diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c
index bef8a36..2539ea0 100644
--- a/drivers/dma/edma.c
+++ b/drivers/dma/edma.c
@@ -46,14 +46,21 @@
 #define EDMA_CHANS	64
 #endif /* CONFIG_ARCH_DAVINCI_DA8XX */
 
-/* Max of 16 segments per channel to conserve PaRAM slots */
-#define MAX_NR_SG		16
+/*
+ * Max of 20 segments per channel to conserve PaRAM slots
+ * Also note that MAX_NR_SG should be atleast the no.of periods
+ * that are required for ASoC, otherwise DMA prep calls will
+ * fail. Today davinci-pcm is the only user of this driver and
+ * requires atleast 17 slots, so we setup the default to 20.
+ */
+#define MAX_NR_SG		20
 #define EDMA_MAX_SLOTS		MAX_NR_SG
 #define EDMA_DESCRIPTORS	16
 
 struct edma_desc {
 	struct virt_dma_desc		vdesc;
 	struct list_head		node;
+	int				cyclic;
 	int				absync;
 	int				pset_nr;
 	int				processed;
@@ -167,8 +174,13 @@
 	 * then setup a link to the dummy slot, this results in all future
 	 * events being absorbed and that's OK because we're done
 	 */
-	if (edesc->processed == edesc->pset_nr)
-		edma_link(echan->slot[nslots-1], echan->ecc->dummy_slot);
+	if (edesc->processed == edesc->pset_nr) {
+		if (edesc->cyclic)
+			edma_link(echan->slot[nslots-1], echan->slot[1]);
+		else
+			edma_link(echan->slot[nslots-1],
+				  echan->ecc->dummy_slot);
+	}
 
 	edma_resume(echan->ch_num);
 
@@ -250,6 +262,117 @@
 	return ret;
 }
 
+/*
+ * A PaRAM set configuration abstraction used by other modes
+ * @chan: Channel who's PaRAM set we're configuring
+ * @pset: PaRAM set to initialize and setup.
+ * @src_addr: Source address of the DMA
+ * @dst_addr: Destination address of the DMA
+ * @burst: In units of dev_width, how much to send
+ * @dev_width: How much is the dev_width
+ * @dma_length: Total length of the DMA transfer
+ * @direction: Direction of the transfer
+ */
+static int edma_config_pset(struct dma_chan *chan, struct edmacc_param *pset,
+	dma_addr_t src_addr, dma_addr_t dst_addr, u32 burst,
+	enum dma_slave_buswidth dev_width, unsigned int dma_length,
+	enum dma_transfer_direction direction)
+{
+	struct edma_chan *echan = to_edma_chan(chan);
+	struct device *dev = chan->device->dev;
+	int acnt, bcnt, ccnt, cidx;
+	int src_bidx, dst_bidx, src_cidx, dst_cidx;
+	int absync;
+
+	acnt = dev_width;
+	/*
+	 * If the maxburst is equal to the fifo width, use
+	 * A-synced transfers. This allows for large contiguous
+	 * buffer transfers using only one PaRAM set.
+	 */
+	if (burst == 1) {
+		/*
+		 * For the A-sync case, bcnt and ccnt are the remainder
+		 * and quotient respectively of the division of:
+		 * (dma_length / acnt) by (SZ_64K -1). This is so
+		 * that in case bcnt over flows, we have ccnt to use.
+		 * Note: In A-sync tranfer only, bcntrld is used, but it
+		 * only applies for sg_dma_len(sg) >= SZ_64K.
+		 * In this case, the best way adopted is- bccnt for the
+		 * first frame will be the remainder below. Then for
+		 * every successive frame, bcnt will be SZ_64K-1. This
+		 * is assured as bcntrld = 0xffff in end of function.
+		 */
+		absync = false;
+		ccnt = dma_length / acnt / (SZ_64K - 1);
+		bcnt = dma_length / acnt - ccnt * (SZ_64K - 1);
+		/*
+		 * If bcnt is non-zero, we have a remainder and hence an
+		 * extra frame to transfer, so increment ccnt.
+		 */
+		if (bcnt)
+			ccnt++;
+		else
+			bcnt = SZ_64K - 1;
+		cidx = acnt;
+	} else {
+		/*
+		 * If maxburst is greater than the fifo address_width,
+		 * use AB-synced transfers where A count is the fifo
+		 * address_width and B count is the maxburst. In this
+		 * case, we are limited to transfers of C count frames
+		 * of (address_width * maxburst) where C count is limited
+		 * to SZ_64K-1. This places an upper bound on the length
+		 * of an SG segment that can be handled.
+		 */
+		absync = true;
+		bcnt = burst;
+		ccnt = dma_length / (acnt * bcnt);
+		if (ccnt > (SZ_64K - 1)) {
+			dev_err(dev, "Exceeded max SG segment size\n");
+			return -EINVAL;
+		}
+		cidx = acnt * bcnt;
+	}
+
+	if (direction == DMA_MEM_TO_DEV) {
+		src_bidx = acnt;
+		src_cidx = cidx;
+		dst_bidx = 0;
+		dst_cidx = 0;
+	} else if (direction == DMA_DEV_TO_MEM)  {
+		src_bidx = 0;
+		src_cidx = 0;
+		dst_bidx = acnt;
+		dst_cidx = cidx;
+	} else {
+		dev_err(dev, "%s: direction not implemented yet\n", __func__);
+		return -EINVAL;
+	}
+
+	pset->opt = EDMA_TCC(EDMA_CHAN_SLOT(echan->ch_num));
+	/* Configure A or AB synchronized transfers */
+	if (absync)
+		pset->opt |= SYNCDIM;
+
+	pset->src = src_addr;
+	pset->dst = dst_addr;
+
+	pset->src_dst_bidx = (dst_bidx << 16) | src_bidx;
+	pset->src_dst_cidx = (dst_cidx << 16) | src_cidx;
+
+	pset->a_b_cnt = bcnt << 16 | acnt;
+	pset->ccnt = ccnt;
+	/*
+	 * Only time when (bcntrld) auto reload is required is for
+	 * A-sync case, and in this case, a requirement of reload value
+	 * of SZ_64K-1 only is assured. 'link' is initially set to NULL
+	 * and then later will be populated by edma_execute.
+	 */
+	pset->link_bcntrld = 0xffffffff;
+	return absync;
+}
+
 static struct dma_async_tx_descriptor *edma_prep_slave_sg(
 	struct dma_chan *chan, struct scatterlist *sgl,
 	unsigned int sg_len, enum dma_transfer_direction direction,
@@ -258,23 +381,21 @@
 	struct edma_chan *echan = to_edma_chan(chan);
 	struct device *dev = chan->device->dev;
 	struct edma_desc *edesc;
-	dma_addr_t dev_addr;
+	dma_addr_t src_addr = 0, dst_addr = 0;
 	enum dma_slave_buswidth dev_width;
 	u32 burst;
 	struct scatterlist *sg;
-	int acnt, bcnt, ccnt, src, dst, cidx;
-	int src_bidx, dst_bidx, src_cidx, dst_cidx;
-	int i, nslots;
+	int i, nslots, ret;
 
 	if (unlikely(!echan || !sgl || !sg_len))
 		return NULL;
 
 	if (direction == DMA_DEV_TO_MEM) {
-		dev_addr = echan->cfg.src_addr;
+		src_addr = echan->cfg.src_addr;
 		dev_width = echan->cfg.src_addr_width;
 		burst = echan->cfg.src_maxburst;
 	} else if (direction == DMA_MEM_TO_DEV) {
-		dev_addr = echan->cfg.dst_addr;
+		dst_addr = echan->cfg.dst_addr;
 		dev_width = echan->cfg.dst_addr_width;
 		burst = echan->cfg.dst_maxburst;
 	} else {
@@ -307,7 +428,6 @@
 			if (echan->slot[i] < 0) {
 				kfree(edesc);
 				dev_err(dev, "Failed to allocate slot\n");
-				kfree(edesc);
 				return NULL;
 			}
 		}
@@ -315,64 +435,21 @@
 
 	/* Configure PaRAM sets for each SG */
 	for_each_sg(sgl, sg, sg_len, i) {
+		/* Get address for each SG */
+		if (direction == DMA_DEV_TO_MEM)
+			dst_addr = sg_dma_address(sg);
+		else
+			src_addr = sg_dma_address(sg);
 
-		acnt = dev_width;
-
-		/*
-		 * If the maxburst is equal to the fifo width, use
-		 * A-synced transfers. This allows for large contiguous
-		 * buffer transfers using only one PaRAM set.
-		 */
-		if (burst == 1) {
-			edesc->absync = false;
-			ccnt = sg_dma_len(sg) / acnt / (SZ_64K - 1);
-			bcnt = sg_dma_len(sg) / acnt - ccnt * (SZ_64K - 1);
-			if (bcnt)
-				ccnt++;
-			else
-				bcnt = SZ_64K - 1;
-			cidx = acnt;
-		/*
-		 * If maxburst is greater than the fifo address_width,
-		 * use AB-synced transfers where A count is the fifo
-		 * address_width and B count is the maxburst. In this
-		 * case, we are limited to transfers of C count frames
-		 * of (address_width * maxburst) where C count is limited
-		 * to SZ_64K-1. This places an upper bound on the length
-		 * of an SG segment that can be handled.
-		 */
-		} else {
-			edesc->absync = true;
-			bcnt = burst;
-			ccnt = sg_dma_len(sg) / (acnt * bcnt);
-			if (ccnt > (SZ_64K - 1)) {
-				dev_err(dev, "Exceeded max SG segment size\n");
-				kfree(edesc);
-				return NULL;
-			}
-			cidx = acnt * bcnt;
+		ret = edma_config_pset(chan, &edesc->pset[i], src_addr,
+				       dst_addr, burst, dev_width,
+				       sg_dma_len(sg), direction);
+		if (ret < 0) {
+			kfree(edesc);
+			return NULL;
 		}
 
-		if (direction == DMA_MEM_TO_DEV) {
-			src = sg_dma_address(sg);
-			dst = dev_addr;
-			src_bidx = acnt;
-			src_cidx = cidx;
-			dst_bidx = 0;
-			dst_cidx = 0;
-		} else {
-			src = dev_addr;
-			dst = sg_dma_address(sg);
-			src_bidx = 0;
-			src_cidx = 0;
-			dst_bidx = acnt;
-			dst_cidx = cidx;
-		}
-
-		edesc->pset[i].opt = EDMA_TCC(EDMA_CHAN_SLOT(echan->ch_num));
-		/* Configure A or AB synchronized transfers */
-		if (edesc->absync)
-			edesc->pset[i].opt |= SYNCDIM;
+		edesc->absync = ret;
 
 		/* If this is the last in a current SG set of transactions,
 		   enable interrupts so that next set is processed */
@@ -382,17 +459,138 @@
 		/* If this is the last set, enable completion interrupt flag */
 		if (i == sg_len - 1)
 			edesc->pset[i].opt |= TCINTEN;
+	}
 
-		edesc->pset[i].src = src;
-		edesc->pset[i].dst = dst;
+	return vchan_tx_prep(&echan->vchan, &edesc->vdesc, tx_flags);
+}
 
-		edesc->pset[i].src_dst_bidx = (dst_bidx << 16) | src_bidx;
-		edesc->pset[i].src_dst_cidx = (dst_cidx << 16) | src_cidx;
+static struct dma_async_tx_descriptor *edma_prep_dma_cyclic(
+	struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
+	size_t period_len, enum dma_transfer_direction direction,
+	unsigned long tx_flags, void *context)
+{
+	struct edma_chan *echan = to_edma_chan(chan);
+	struct device *dev = chan->device->dev;
+	struct edma_desc *edesc;
+	dma_addr_t src_addr, dst_addr;
+	enum dma_slave_buswidth dev_width;
+	u32 burst;
+	int i, ret, nslots;
 
-		edesc->pset[i].a_b_cnt = bcnt << 16 | acnt;
-		edesc->pset[i].ccnt = ccnt;
-		edesc->pset[i].link_bcntrld = 0xffffffff;
+	if (unlikely(!echan || !buf_len || !period_len))
+		return NULL;
 
+	if (direction == DMA_DEV_TO_MEM) {
+		src_addr = echan->cfg.src_addr;
+		dst_addr = buf_addr;
+		dev_width = echan->cfg.src_addr_width;
+		burst = echan->cfg.src_maxburst;
+	} else if (direction == DMA_MEM_TO_DEV) {
+		src_addr = buf_addr;
+		dst_addr = echan->cfg.dst_addr;
+		dev_width = echan->cfg.dst_addr_width;
+		burst = echan->cfg.dst_maxburst;
+	} else {
+		dev_err(dev, "%s: bad direction?\n", __func__);
+		return NULL;
+	}
+
+	if (dev_width == DMA_SLAVE_BUSWIDTH_UNDEFINED) {
+		dev_err(dev, "Undefined slave buswidth\n");
+		return NULL;
+	}
+
+	if (unlikely(buf_len % period_len)) {
+		dev_err(dev, "Period should be multiple of Buffer length\n");
+		return NULL;
+	}
+
+	nslots = (buf_len / period_len) + 1;
+
+	/*
+	 * Cyclic DMA users such as audio cannot tolerate delays introduced
+	 * by cases where the number of periods is more than the maximum
+	 * number of SGs the EDMA driver can handle at a time. For DMA types
+	 * such as Slave SGs, such delays are tolerable and synchronized,
+	 * but the synchronization is difficult to achieve with Cyclic and
+	 * cannot be guaranteed, so we error out early.
+	 */
+	if (nslots > MAX_NR_SG)
+		return NULL;
+
+	edesc = kzalloc(sizeof(*edesc) + nslots *
+		sizeof(edesc->pset[0]), GFP_ATOMIC);
+	if (!edesc) {
+		dev_dbg(dev, "Failed to allocate a descriptor\n");
+		return NULL;
+	}
+
+	edesc->cyclic = 1;
+	edesc->pset_nr = nslots;
+
+	dev_dbg(dev, "%s: nslots=%d\n", __func__, nslots);
+	dev_dbg(dev, "%s: period_len=%d\n", __func__, period_len);
+	dev_dbg(dev, "%s: buf_len=%d\n", __func__, buf_len);
+
+	for (i = 0; i < nslots; i++) {
+		/* Allocate a PaRAM slot, if needed */
+		if (echan->slot[i] < 0) {
+			echan->slot[i] =
+				edma_alloc_slot(EDMA_CTLR(echan->ch_num),
+						EDMA_SLOT_ANY);
+			if (echan->slot[i] < 0) {
+				dev_err(dev, "Failed to allocate slot\n");
+				return NULL;
+			}
+		}
+
+		if (i == nslots - 1) {
+			memcpy(&edesc->pset[i], &edesc->pset[0],
+			       sizeof(edesc->pset[0]));
+			break;
+		}
+
+		ret = edma_config_pset(chan, &edesc->pset[i], src_addr,
+				       dst_addr, burst, dev_width, period_len,
+				       direction);
+		if (ret < 0)
+			return NULL;
+
+		if (direction == DMA_DEV_TO_MEM)
+			dst_addr += period_len;
+		else
+			src_addr += period_len;
+
+		dev_dbg(dev, "%s: Configure period %d of buf:\n", __func__, i);
+		dev_dbg(dev,
+			"\n pset[%d]:\n"
+			"  chnum\t%d\n"
+			"  slot\t%d\n"
+			"  opt\t%08x\n"
+			"  src\t%08x\n"
+			"  dst\t%08x\n"
+			"  abcnt\t%08x\n"
+			"  ccnt\t%08x\n"
+			"  bidx\t%08x\n"
+			"  cidx\t%08x\n"
+			"  lkrld\t%08x\n",
+			i, echan->ch_num, echan->slot[i],
+			edesc->pset[i].opt,
+			edesc->pset[i].src,
+			edesc->pset[i].dst,
+			edesc->pset[i].a_b_cnt,
+			edesc->pset[i].ccnt,
+			edesc->pset[i].src_dst_bidx,
+			edesc->pset[i].src_dst_cidx,
+			edesc->pset[i].link_bcntrld);
+
+		edesc->absync = ret;
+
+		/*
+		 * Enable interrupts for every period because callback
+		 * has to be called for every period.
+		 */
+		edesc->pset[i].opt |= TCINTEN;
 	}
 
 	return vchan_tx_prep(&echan->vchan, &edesc->vdesc, tx_flags);
@@ -406,30 +604,34 @@
 	unsigned long flags;
 	struct edmacc_param p;
 
-	/* Pause the channel */
-	edma_pause(echan->ch_num);
+	edesc = echan->edesc;
+
+	/* Pause the channel for non-cyclic */
+	if (!edesc || (edesc && !edesc->cyclic))
+		edma_pause(echan->ch_num);
 
 	switch (ch_status) {
-	case DMA_COMPLETE:
+	case EDMA_DMA_COMPLETE:
 		spin_lock_irqsave(&echan->vchan.lock, flags);
 
-		edesc = echan->edesc;
 		if (edesc) {
-			if (edesc->processed == edesc->pset_nr) {
+			if (edesc->cyclic) {
+				vchan_cyclic_callback(&edesc->vdesc);
+			} else if (edesc->processed == edesc->pset_nr) {
 				dev_dbg(dev, "Transfer complete, stopping channel %d\n", ch_num);
 				edma_stop(echan->ch_num);
 				vchan_cookie_complete(&edesc->vdesc);
+				edma_execute(echan);
 			} else {
 				dev_dbg(dev, "Intermediate transfer complete on channel %d\n", ch_num);
+				edma_execute(echan);
 			}
-
-			edma_execute(echan);
 		}
 
 		spin_unlock_irqrestore(&echan->vchan.lock, flags);
 
 		break;
-	case DMA_CC_ERROR:
+	case EDMA_DMA_CC_ERROR:
 		spin_lock_irqsave(&echan->vchan.lock, flags);
 
 		edma_read_slot(EDMA_CHAN_SLOT(echan->slot[0]), &p);
@@ -579,7 +781,7 @@
 	unsigned long flags;
 
 	ret = dma_cookie_status(chan, cookie, txstate);
-	if (ret == DMA_SUCCESS || !txstate)
+	if (ret == DMA_COMPLETE || !txstate)
 		return ret;
 
 	spin_lock_irqsave(&echan->vchan.lock, flags);
@@ -619,6 +821,7 @@
 			  struct device *dev)
 {
 	dma->device_prep_slave_sg = edma_prep_slave_sg;
+	dma->device_prep_dma_cyclic = edma_prep_dma_cyclic;
 	dma->device_alloc_chan_resources = edma_alloc_chan_resources;
 	dma->device_free_chan_resources = edma_free_chan_resources;
 	dma->device_issue_pending = edma_issue_pending;
diff --git a/drivers/dma/ep93xx_dma.c b/drivers/dma/ep93xx_dma.c
index 591cd8c..cb4bf68 100644
--- a/drivers/dma/ep93xx_dma.c
+++ b/drivers/dma/ep93xx_dma.c
@@ -733,28 +733,6 @@
 	spin_unlock_irqrestore(&edmac->lock, flags);
 }
 
-static void ep93xx_dma_unmap_buffers(struct ep93xx_dma_desc *desc)
-{
-	struct device *dev = desc->txd.chan->device->dev;
-
-	if (!(desc->txd.flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-		if (desc->txd.flags & DMA_COMPL_SRC_UNMAP_SINGLE)
-			dma_unmap_single(dev, desc->src_addr, desc->size,
-					 DMA_TO_DEVICE);
-		else
-			dma_unmap_page(dev, desc->src_addr, desc->size,
-				       DMA_TO_DEVICE);
-	}
-	if (!(desc->txd.flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
-		if (desc->txd.flags & DMA_COMPL_DEST_UNMAP_SINGLE)
-			dma_unmap_single(dev, desc->dst_addr, desc->size,
-					 DMA_FROM_DEVICE);
-		else
-			dma_unmap_page(dev, desc->dst_addr, desc->size,
-				       DMA_FROM_DEVICE);
-	}
-}
-
 static void ep93xx_dma_tasklet(unsigned long data)
 {
 	struct ep93xx_dma_chan *edmac = (struct ep93xx_dma_chan *)data;
@@ -787,13 +765,7 @@
 
 	/* Now we can release all the chained descriptors */
 	list_for_each_entry_safe(desc, d, &list, node) {
-		/*
-		 * For the memcpy channels the API requires us to unmap the
-		 * buffers unless requested otherwise.
-		 */
-		if (!edmac->chan.private)
-			ep93xx_dma_unmap_buffers(desc);
-
+		dma_descriptor_unmap(&desc->txd);
 		ep93xx_dma_desc_put(edmac, desc);
 	}
 
diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c
index 61517dd..7086a16 100644
--- a/drivers/dma/fsldma.c
+++ b/drivers/dma/fsldma.c
@@ -870,22 +870,7 @@
 	/* Run any dependencies */
 	dma_run_dependencies(txd);
 
-	/* Unmap the dst buffer, if requested */
-	if (!(txd->flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
-		if (txd->flags & DMA_COMPL_DEST_UNMAP_SINGLE)
-			dma_unmap_single(dev, dst, len, DMA_FROM_DEVICE);
-		else
-			dma_unmap_page(dev, dst, len, DMA_FROM_DEVICE);
-	}
-
-	/* Unmap the src buffer, if requested */
-	if (!(txd->flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-		if (txd->flags & DMA_COMPL_SRC_UNMAP_SINGLE)
-			dma_unmap_single(dev, src, len, DMA_TO_DEVICE);
-		else
-			dma_unmap_page(dev, src, len, DMA_TO_DEVICE);
-	}
-
+	dma_descriptor_unmap(txd);
 #ifdef FSL_DMA_LD_DEBUG
 	chan_dbg(chan, "LD %p free\n", desc);
 #endif
@@ -1255,7 +1240,9 @@
 	WARN_ON(fdev->feature != chan->feature);
 
 	chan->dev = fdev->dev;
-	chan->id = ((res.start - 0x100) & 0xfff) >> 7;
+	chan->id = (res.start & 0xfff) < 0x300 ?
+		   ((res.start - 0x100) & 0xfff) >> 7 :
+		   ((res.start - 0x200) & 0xfff) >> 7;
 	if (chan->id >= FSL_DMA_MAX_CHANS_PER_DEVICE) {
 		dev_err(fdev->dev, "too many channels for device\n");
 		err = -EINVAL;
@@ -1428,6 +1415,7 @@
 }
 
 static const struct of_device_id fsldma_of_ids[] = {
+	{ .compatible = "fsl,elo3-dma", },
 	{ .compatible = "fsl,eloplus-dma", },
 	{ .compatible = "fsl,elo-dma", },
 	{}
@@ -1449,7 +1437,7 @@
 
 static __init int fsldma_init(void)
 {
-	pr_info("Freescale Elo / Elo Plus DMA driver\n");
+	pr_info("Freescale Elo series DMA driver\n");
 	return platform_driver_register(&fsldma_of_driver);
 }
 
@@ -1461,5 +1449,5 @@
 subsys_initcall(fsldma_init);
 module_exit(fsldma_exit);
 
-MODULE_DESCRIPTION("Freescale Elo / Elo Plus DMA driver");
+MODULE_DESCRIPTION("Freescale Elo series DMA driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/dma/fsldma.h b/drivers/dma/fsldma.h
index f5c3879..1ffc244 100644
--- a/drivers/dma/fsldma.h
+++ b/drivers/dma/fsldma.h
@@ -112,7 +112,7 @@
 };
 
 struct fsldma_chan;
-#define FSL_DMA_MAX_CHANS_PER_DEVICE 4
+#define FSL_DMA_MAX_CHANS_PER_DEVICE 8
 
 struct fsldma_device {
 	void __iomem *regs;	/* DGSR register base */
diff --git a/drivers/dma/imx-dma.c b/drivers/dma/imx-dma.c
index 55852c0..6f9ac20 100644
--- a/drivers/dma/imx-dma.c
+++ b/drivers/dma/imx-dma.c
@@ -572,9 +572,11 @@
 
 		imx_dmav1_writel(imxdma, d->len, DMA_CNTR(imxdmac->channel));
 
-		dev_dbg(imxdma->dev, "%s channel: %d dest=0x%08x src=0x%08x "
-			"dma_length=%d\n", __func__, imxdmac->channel,
-			d->dest, d->src, d->len);
+		dev_dbg(imxdma->dev,
+			"%s channel: %d dest=0x%08llx src=0x%08llx dma_length=%zu\n",
+			__func__, imxdmac->channel,
+			(unsigned long long)d->dest,
+			(unsigned long long)d->src, d->len);
 
 		break;
 	/* Cyclic transfer is the same as slave_sg with special sg configuration. */
@@ -586,20 +588,22 @@
 			imx_dmav1_writel(imxdma, imxdmac->ccr_from_device,
 					 DMA_CCR(imxdmac->channel));
 
-			dev_dbg(imxdma->dev, "%s channel: %d sg=%p sgcount=%d "
-				"total length=%d dev_addr=0x%08x (dev2mem)\n",
-				__func__, imxdmac->channel, d->sg, d->sgcount,
-				d->len, imxdmac->per_address);
+			dev_dbg(imxdma->dev,
+				"%s channel: %d sg=%p sgcount=%d total length=%zu dev_addr=0x%08llx (dev2mem)\n",
+				__func__, imxdmac->channel,
+				d->sg, d->sgcount, d->len,
+				(unsigned long long)imxdmac->per_address);
 		} else if (d->direction == DMA_MEM_TO_DEV) {
 			imx_dmav1_writel(imxdma, imxdmac->per_address,
 					 DMA_DAR(imxdmac->channel));
 			imx_dmav1_writel(imxdma, imxdmac->ccr_to_device,
 					 DMA_CCR(imxdmac->channel));
 
-			dev_dbg(imxdma->dev, "%s channel: %d sg=%p sgcount=%d "
-				"total length=%d dev_addr=0x%08x (mem2dev)\n",
-				__func__, imxdmac->channel, d->sg, d->sgcount,
-				d->len, imxdmac->per_address);
+			dev_dbg(imxdma->dev,
+				"%s channel: %d sg=%p sgcount=%d total length=%zu dev_addr=0x%08llx (mem2dev)\n",
+				__func__, imxdmac->channel,
+				d->sg, d->sgcount, d->len,
+				(unsigned long long)imxdmac->per_address);
 		} else {
 			dev_err(imxdma->dev, "%s channel: %d bad dma mode\n",
 				__func__, imxdmac->channel);
@@ -771,7 +775,7 @@
 		desc->desc.tx_submit = imxdma_tx_submit;
 		/* txd.flags will be overwritten in prep funcs */
 		desc->desc.flags = DMA_CTRL_ACK;
-		desc->status = DMA_SUCCESS;
+		desc->status = DMA_COMPLETE;
 
 		list_add_tail(&desc->node, &imxdmac->ld_free);
 		imxdmac->descs_allocated++;
@@ -870,7 +874,7 @@
 	int i;
 	unsigned int periods = buf_len / period_len;
 
-	dev_dbg(imxdma->dev, "%s channel: %d buf_len=%d period_len=%d\n",
+	dev_dbg(imxdma->dev, "%s channel: %d buf_len=%zu period_len=%zu\n",
 			__func__, imxdmac->channel, buf_len, period_len);
 
 	if (list_empty(&imxdmac->ld_free) ||
@@ -926,8 +930,9 @@
 	struct imxdma_engine *imxdma = imxdmac->imxdma;
 	struct imxdma_desc *desc;
 
-	dev_dbg(imxdma->dev, "%s channel: %d src=0x%x dst=0x%x len=%d\n",
-			__func__, imxdmac->channel, src, dest, len);
+	dev_dbg(imxdma->dev, "%s channel: %d src=0x%llx dst=0x%llx len=%zu\n",
+		__func__, imxdmac->channel, (unsigned long long)src,
+		(unsigned long long)dest, len);
 
 	if (list_empty(&imxdmac->ld_free) ||
 	    imxdma_chan_is_doing_cyclic(imxdmac))
@@ -956,9 +961,10 @@
 	struct imxdma_engine *imxdma = imxdmac->imxdma;
 	struct imxdma_desc *desc;
 
-	dev_dbg(imxdma->dev, "%s channel: %d src_start=0x%x dst_start=0x%x\n"
-		"   src_sgl=%s dst_sgl=%s numf=%d frame_size=%d\n", __func__,
-		imxdmac->channel, xt->src_start, xt->dst_start,
+	dev_dbg(imxdma->dev, "%s channel: %d src_start=0x%llx dst_start=0x%llx\n"
+		"   src_sgl=%s dst_sgl=%s numf=%zu frame_size=%zu\n", __func__,
+		imxdmac->channel, (unsigned long long)xt->src_start,
+		(unsigned long long) xt->dst_start,
 		xt->src_sgl ? "true" : "false", xt->dst_sgl ? "true" : "false",
 		xt->numf, xt->frame_size);
 
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index c1fd504..c75679d 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -638,7 +638,7 @@
 	if (error)
 		sdmac->status = DMA_ERROR;
 	else
-		sdmac->status = DMA_SUCCESS;
+		sdmac->status = DMA_COMPLETE;
 
 	dma_cookie_complete(&sdmac->desc);
 	if (sdmac->desc.callback)
@@ -1089,8 +1089,8 @@
 			param &= ~BD_CONT;
 		}
 
-		dev_dbg(sdma->dev, "entry %d: count: %d dma: 0x%08x %s%s\n",
-				i, count, sg->dma_address,
+		dev_dbg(sdma->dev, "entry %d: count: %d dma: %#llx %s%s\n",
+				i, count, (u64)sg->dma_address,
 				param & BD_WRAP ? "wrap" : "",
 				param & BD_INTR ? " intr" : "");
 
@@ -1163,8 +1163,8 @@
 		if (i + 1 == num_periods)
 			param |= BD_WRAP;
 
-		dev_dbg(sdma->dev, "entry %d: count: %d dma: 0x%08x %s%s\n",
-				i, period_len, dma_addr,
+		dev_dbg(sdma->dev, "entry %d: count: %d dma: %#llx %s%s\n",
+				i, period_len, (u64)dma_addr,
 				param & BD_WRAP ? "wrap" : "",
 				param & BD_INTR ? " intr" : "");
 
diff --git a/drivers/dma/intel_mid_dma.c b/drivers/dma/intel_mid_dma.c
index a975ebe..1aab813 100644
--- a/drivers/dma/intel_mid_dma.c
+++ b/drivers/dma/intel_mid_dma.c
@@ -309,7 +309,7 @@
 		callback_txd(param_txd);
 	}
 	if (midc->raw_tfr) {
-		desc->status = DMA_SUCCESS;
+		desc->status = DMA_COMPLETE;
 		if (desc->lli != NULL) {
 			pci_pool_free(desc->lli_pool, desc->lli,
 						desc->lli_phys);
@@ -481,7 +481,7 @@
 	enum dma_status ret;
 
 	ret = dma_cookie_status(chan, cookie, txstate);
-	if (ret != DMA_SUCCESS) {
+	if (ret != DMA_COMPLETE) {
 		spin_lock_bh(&midc->lock);
 		midc_scan_descriptors(to_middma_device(chan->device), midc);
 		spin_unlock_bh(&midc->lock);
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index 5ff6fc1..1a49c7776 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -531,21 +531,6 @@
 	writew(IOAT_CHANCTRL_RUN, ioat->base.reg_base + IOAT_CHANCTRL_OFFSET);
 }
 
-void ioat_dma_unmap(struct ioat_chan_common *chan, enum dma_ctrl_flags flags,
-		    size_t len, struct ioat_dma_descriptor *hw)
-{
-	struct pci_dev *pdev = chan->device->pdev;
-	size_t offset = len - hw->size;
-
-	if (!(flags & DMA_COMPL_SKIP_DEST_UNMAP))
-		ioat_unmap(pdev, hw->dst_addr - offset, len,
-			   PCI_DMA_FROMDEVICE, flags, 1);
-
-	if (!(flags & DMA_COMPL_SKIP_SRC_UNMAP))
-		ioat_unmap(pdev, hw->src_addr - offset, len,
-			   PCI_DMA_TODEVICE, flags, 0);
-}
-
 dma_addr_t ioat_get_current_completion(struct ioat_chan_common *chan)
 {
 	dma_addr_t phys_complete;
@@ -602,7 +587,7 @@
 		dump_desc_dbg(ioat, desc);
 		if (tx->cookie) {
 			dma_cookie_complete(tx);
-			ioat_dma_unmap(chan, tx->flags, desc->len, desc->hw);
+			dma_descriptor_unmap(tx);
 			ioat->active -= desc->hw->tx_cnt;
 			if (tx->callback) {
 				tx->callback(tx->callback_param);
@@ -733,7 +718,7 @@
 	enum dma_status ret;
 
 	ret = dma_cookie_status(c, cookie, txstate);
-	if (ret == DMA_SUCCESS)
+	if (ret == DMA_COMPLETE)
 		return ret;
 
 	device->cleanup_fn((unsigned long) c);
@@ -833,8 +818,7 @@
 
 	dma_src = dma_map_single(dev, src, IOAT_TEST_SIZE, DMA_TO_DEVICE);
 	dma_dest = dma_map_single(dev, dest, IOAT_TEST_SIZE, DMA_FROM_DEVICE);
-	flags = DMA_COMPL_SKIP_SRC_UNMAP | DMA_COMPL_SKIP_DEST_UNMAP |
-		DMA_PREP_INTERRUPT;
+	flags = DMA_PREP_INTERRUPT;
 	tx = device->common.device_prep_dma_memcpy(dma_chan, dma_dest, dma_src,
 						   IOAT_TEST_SIZE, flags);
 	if (!tx) {
@@ -859,7 +843,7 @@
 
 	if (tmo == 0 ||
 	    dma->device_tx_status(dma_chan, cookie, NULL)
-					!= DMA_SUCCESS) {
+					!= DMA_COMPLETE) {
 		dev_err(dev, "Self-test copy timed out, disabling\n");
 		err = -ENODEV;
 		goto unmap_dma;
@@ -885,8 +869,7 @@
 module_param_string(ioat_interrupt_style, ioat_interrupt_style,
 		    sizeof(ioat_interrupt_style), 0644);
 MODULE_PARM_DESC(ioat_interrupt_style,
-		 "set ioat interrupt style: msix (default), "
-		 "msix-single-vector, msi, intx)");
+		 "set ioat interrupt style: msix (default), msi, intx");
 
 /**
  * ioat_dma_setup_interrupts - setup interrupt handler
@@ -904,8 +887,6 @@
 
 	if (!strcmp(ioat_interrupt_style, "msix"))
 		goto msix;
-	if (!strcmp(ioat_interrupt_style, "msix-single-vector"))
-		goto msix_single_vector;
 	if (!strcmp(ioat_interrupt_style, "msi"))
 		goto msi;
 	if (!strcmp(ioat_interrupt_style, "intx"))
@@ -920,10 +901,8 @@
 		device->msix_entries[i].entry = i;
 
 	err = pci_enable_msix(pdev, device->msix_entries, msixcnt);
-	if (err < 0)
+	if (err)
 		goto msi;
-	if (err > 0)
-		goto msix_single_vector;
 
 	for (i = 0; i < msixcnt; i++) {
 		msix = &device->msix_entries[i];
@@ -937,29 +916,13 @@
 				chan = ioat_chan_by_index(device, j);
 				devm_free_irq(dev, msix->vector, chan);
 			}
-			goto msix_single_vector;
+			goto msi;
 		}
 	}
 	intrctrl |= IOAT_INTRCTRL_MSIX_VECTOR_CONTROL;
 	device->irq_mode = IOAT_MSIX;
 	goto done;
 
-msix_single_vector:
-	msix = &device->msix_entries[0];
-	msix->entry = 0;
-	err = pci_enable_msix(pdev, device->msix_entries, 1);
-	if (err)
-		goto msi;
-
-	err = devm_request_irq(dev, msix->vector, ioat_dma_do_interrupt, 0,
-			       "ioat-msix", device);
-	if (err) {
-		pci_disable_msix(pdev);
-		goto msi;
-	}
-	device->irq_mode = IOAT_MSIX_SINGLE;
-	goto done;
-
 msi:
 	err = pci_enable_msi(pdev);
 	if (err)
@@ -971,7 +934,7 @@
 		pci_disable_msi(pdev);
 		goto intx;
 	}
-	device->irq_mode = IOAT_MSIX;
+	device->irq_mode = IOAT_MSI;
 	goto done;
 
 intx:
diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h
index 54fb7b9..11fb877 100644
--- a/drivers/dma/ioat/dma.h
+++ b/drivers/dma/ioat/dma.h
@@ -52,7 +52,6 @@
 enum ioat_irq_mode {
 	IOAT_NOIRQ = 0,
 	IOAT_MSIX,
-	IOAT_MSIX_SINGLE,
 	IOAT_MSI,
 	IOAT_INTX
 };
@@ -83,7 +82,6 @@
 	struct pci_pool *completion_pool;
 #define MAX_SED_POOLS	5
 	struct dma_pool *sed_hw_pool[MAX_SED_POOLS];
-	struct kmem_cache *sed_pool;
 	struct dma_device common;
 	u8 version;
 	struct msix_entry msix_entries[4];
@@ -342,16 +340,6 @@
 	return !!err;
 }
 
-static inline void ioat_unmap(struct pci_dev *pdev, dma_addr_t addr, size_t len,
-			      int direction, enum dma_ctrl_flags flags, bool dst)
-{
-	if ((dst && (flags & DMA_COMPL_DEST_UNMAP_SINGLE)) ||
-	    (!dst && (flags & DMA_COMPL_SRC_UNMAP_SINGLE)))
-		pci_unmap_single(pdev, addr, len, direction);
-	else
-		pci_unmap_page(pdev, addr, len, direction);
-}
-
 int ioat_probe(struct ioatdma_device *device);
 int ioat_register(struct ioatdma_device *device);
 int ioat1_dma_probe(struct ioatdma_device *dev, int dca);
@@ -363,8 +351,6 @@
 		       struct ioat_chan_common *chan, int idx);
 enum dma_status ioat_dma_tx_status(struct dma_chan *c, dma_cookie_t cookie,
 				   struct dma_tx_state *txstate);
-void ioat_dma_unmap(struct ioat_chan_common *chan, enum dma_ctrl_flags flags,
-		    size_t len, struct ioat_dma_descriptor *hw);
 bool ioat_cleanup_preamble(struct ioat_chan_common *chan,
 			   dma_addr_t *phys_complete);
 void ioat_kobject_add(struct ioatdma_device *device, struct kobj_type *type);
diff --git a/drivers/dma/ioat/dma_v2.c b/drivers/dma/ioat/dma_v2.c
index b925e1b..5d3affe 100644
--- a/drivers/dma/ioat/dma_v2.c
+++ b/drivers/dma/ioat/dma_v2.c
@@ -148,7 +148,7 @@
 		tx = &desc->txd;
 		dump_desc_dbg(ioat, desc);
 		if (tx->cookie) {
-			ioat_dma_unmap(chan, tx->flags, desc->len, desc->hw);
+			dma_descriptor_unmap(tx);
 			dma_cookie_complete(tx);
 			if (tx->callback) {
 				tx->callback(tx->callback_param);
diff --git a/drivers/dma/ioat/dma_v2.h b/drivers/dma/ioat/dma_v2.h
index 212d584..4702927 100644
--- a/drivers/dma/ioat/dma_v2.h
+++ b/drivers/dma/ioat/dma_v2.h
@@ -157,7 +157,6 @@
 
 int ioat2_dma_probe(struct ioatdma_device *dev, int dca);
 int ioat3_dma_probe(struct ioatdma_device *dev, int dca);
-void ioat3_dma_remove(struct ioatdma_device *dev);
 struct dca_provider *ioat2_dca_init(struct pci_dev *pdev, void __iomem *iobase);
 struct dca_provider *ioat3_dca_init(struct pci_dev *pdev, void __iomem *iobase);
 int ioat2_check_space_lock(struct ioat2_dma_chan *ioat, int num_descs);
diff --git a/drivers/dma/ioat/dma_v3.c b/drivers/dma/ioat/dma_v3.c
index d8ececaf..820817e9 100644
--- a/drivers/dma/ioat/dma_v3.c
+++ b/drivers/dma/ioat/dma_v3.c
@@ -67,6 +67,8 @@
 #include "dma.h"
 #include "dma_v2.h"
 
+extern struct kmem_cache *ioat3_sed_cache;
+
 /* ioat hardware assumes at least two sources for raid operations */
 #define src_cnt_to_sw(x) ((x) + 2)
 #define src_cnt_to_hw(x) ((x) - 2)
@@ -87,22 +89,8 @@
 static const u8 pq16_idx_to_field[] = { 1, 4, 1, 2, 3, 4, 5, 6, 7,
 					0, 1, 2, 3, 4, 5, 6 };
 
-/*
- * technically sources 1 and 2 do not require SED, but the op will have
- * at least 9 descriptors so that's irrelevant.
- */
-static const u8 pq16_idx_to_sed[] = { 0, 0, 0, 0, 0, 0, 0, 0, 0,
-				      1, 1, 1, 1, 1, 1, 1 };
-
 static void ioat3_eh(struct ioat2_dma_chan *ioat);
 
-static dma_addr_t xor_get_src(struct ioat_raw_descriptor *descs[2], int idx)
-{
-	struct ioat_raw_descriptor *raw = descs[xor_idx_to_desc >> idx & 1];
-
-	return raw->field[xor_idx_to_field[idx]];
-}
-
 static void xor_set_src(struct ioat_raw_descriptor *descs[2],
 			dma_addr_t addr, u32 offset, int idx)
 {
@@ -135,12 +123,6 @@
 	pq->coef[idx] = coef;
 }
 
-static int sed_get_pq16_pool_idx(int src_cnt)
-{
-
-	return pq16_idx_to_sed[src_cnt];
-}
-
 static bool is_jf_ioat(struct pci_dev *pdev)
 {
 	switch (pdev->device) {
@@ -272,7 +254,7 @@
 	struct ioat_sed_ent *sed;
 	gfp_t flags = __GFP_ZERO | GFP_ATOMIC;
 
-	sed = kmem_cache_alloc(device->sed_pool, flags);
+	sed = kmem_cache_alloc(ioat3_sed_cache, flags);
 	if (!sed)
 		return NULL;
 
@@ -280,7 +262,7 @@
 	sed->hw = dma_pool_alloc(device->sed_hw_pool[hw_pool],
 				 flags, &sed->dma);
 	if (!sed->hw) {
-		kmem_cache_free(device->sed_pool, sed);
+		kmem_cache_free(ioat3_sed_cache, sed);
 		return NULL;
 	}
 
@@ -293,165 +275,7 @@
 		return;
 
 	dma_pool_free(device->sed_hw_pool[sed->hw_pool], sed->hw, sed->dma);
-	kmem_cache_free(device->sed_pool, sed);
-}
-
-static void ioat3_dma_unmap(struct ioat2_dma_chan *ioat,
-			    struct ioat_ring_ent *desc, int idx)
-{
-	struct ioat_chan_common *chan = &ioat->base;
-	struct pci_dev *pdev = chan->device->pdev;
-	size_t len = desc->len;
-	size_t offset = len - desc->hw->size;
-	struct dma_async_tx_descriptor *tx = &desc->txd;
-	enum dma_ctrl_flags flags = tx->flags;
-
-	switch (desc->hw->ctl_f.op) {
-	case IOAT_OP_COPY:
-		if (!desc->hw->ctl_f.null) /* skip 'interrupt' ops */
-			ioat_dma_unmap(chan, flags, len, desc->hw);
-		break;
-	case IOAT_OP_XOR_VAL:
-	case IOAT_OP_XOR: {
-		struct ioat_xor_descriptor *xor = desc->xor;
-		struct ioat_ring_ent *ext;
-		struct ioat_xor_ext_descriptor *xor_ex = NULL;
-		int src_cnt = src_cnt_to_sw(xor->ctl_f.src_cnt);
-		struct ioat_raw_descriptor *descs[2];
-		int i;
-
-		if (src_cnt > 5) {
-			ext = ioat2_get_ring_ent(ioat, idx + 1);
-			xor_ex = ext->xor_ex;
-		}
-
-		if (!(flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-			descs[0] = (struct ioat_raw_descriptor *) xor;
-			descs[1] = (struct ioat_raw_descriptor *) xor_ex;
-			for (i = 0; i < src_cnt; i++) {
-				dma_addr_t src = xor_get_src(descs, i);
-
-				ioat_unmap(pdev, src - offset, len,
-					   PCI_DMA_TODEVICE, flags, 0);
-			}
-
-			/* dest is a source in xor validate operations */
-			if (xor->ctl_f.op == IOAT_OP_XOR_VAL) {
-				ioat_unmap(pdev, xor->dst_addr - offset, len,
-					   PCI_DMA_TODEVICE, flags, 1);
-				break;
-			}
-		}
-
-		if (!(flags & DMA_COMPL_SKIP_DEST_UNMAP))
-			ioat_unmap(pdev, xor->dst_addr - offset, len,
-				   PCI_DMA_FROMDEVICE, flags, 1);
-		break;
-	}
-	case IOAT_OP_PQ_VAL:
-	case IOAT_OP_PQ: {
-		struct ioat_pq_descriptor *pq = desc->pq;
-		struct ioat_ring_ent *ext;
-		struct ioat_pq_ext_descriptor *pq_ex = NULL;
-		int src_cnt = src_cnt_to_sw(pq->ctl_f.src_cnt);
-		struct ioat_raw_descriptor *descs[2];
-		int i;
-
-		if (src_cnt > 3) {
-			ext = ioat2_get_ring_ent(ioat, idx + 1);
-			pq_ex = ext->pq_ex;
-		}
-
-		/* in the 'continue' case don't unmap the dests as sources */
-		if (dmaf_p_disabled_continue(flags))
-			src_cnt--;
-		else if (dmaf_continue(flags))
-			src_cnt -= 3;
-
-		if (!(flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-			descs[0] = (struct ioat_raw_descriptor *) pq;
-			descs[1] = (struct ioat_raw_descriptor *) pq_ex;
-			for (i = 0; i < src_cnt; i++) {
-				dma_addr_t src = pq_get_src(descs, i);
-
-				ioat_unmap(pdev, src - offset, len,
-					   PCI_DMA_TODEVICE, flags, 0);
-			}
-
-			/* the dests are sources in pq validate operations */
-			if (pq->ctl_f.op == IOAT_OP_XOR_VAL) {
-				if (!(flags & DMA_PREP_PQ_DISABLE_P))
-					ioat_unmap(pdev, pq->p_addr - offset,
-						   len, PCI_DMA_TODEVICE, flags, 0);
-				if (!(flags & DMA_PREP_PQ_DISABLE_Q))
-					ioat_unmap(pdev, pq->q_addr - offset,
-						   len, PCI_DMA_TODEVICE, flags, 0);
-				break;
-			}
-		}
-
-		if (!(flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
-			if (!(flags & DMA_PREP_PQ_DISABLE_P))
-				ioat_unmap(pdev, pq->p_addr - offset, len,
-					   PCI_DMA_BIDIRECTIONAL, flags, 1);
-			if (!(flags & DMA_PREP_PQ_DISABLE_Q))
-				ioat_unmap(pdev, pq->q_addr - offset, len,
-					   PCI_DMA_BIDIRECTIONAL, flags, 1);
-		}
-		break;
-	}
-	case IOAT_OP_PQ_16S:
-	case IOAT_OP_PQ_VAL_16S: {
-		struct ioat_pq_descriptor *pq = desc->pq;
-		int src_cnt = src16_cnt_to_sw(pq->ctl_f.src_cnt);
-		struct ioat_raw_descriptor *descs[4];
-		int i;
-
-		/* in the 'continue' case don't unmap the dests as sources */
-		if (dmaf_p_disabled_continue(flags))
-			src_cnt--;
-		else if (dmaf_continue(flags))
-			src_cnt -= 3;
-
-		if (!(flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-			descs[0] = (struct ioat_raw_descriptor *)pq;
-			descs[1] = (struct ioat_raw_descriptor *)(desc->sed->hw);
-			descs[2] = (struct ioat_raw_descriptor *)(&desc->sed->hw->b[0]);
-			for (i = 0; i < src_cnt; i++) {
-				dma_addr_t src = pq16_get_src(descs, i);
-
-				ioat_unmap(pdev, src - offset, len,
-					   PCI_DMA_TODEVICE, flags, 0);
-			}
-
-			/* the dests are sources in pq validate operations */
-			if (pq->ctl_f.op == IOAT_OP_XOR_VAL) {
-				if (!(flags & DMA_PREP_PQ_DISABLE_P))
-					ioat_unmap(pdev, pq->p_addr - offset,
-						   len, PCI_DMA_TODEVICE,
-						   flags, 0);
-				if (!(flags & DMA_PREP_PQ_DISABLE_Q))
-					ioat_unmap(pdev, pq->q_addr - offset,
-						   len, PCI_DMA_TODEVICE,
-						   flags, 0);
-				break;
-			}
-		}
-
-		if (!(flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
-			if (!(flags & DMA_PREP_PQ_DISABLE_P))
-				ioat_unmap(pdev, pq->p_addr - offset, len,
-					   PCI_DMA_BIDIRECTIONAL, flags, 1);
-			if (!(flags & DMA_PREP_PQ_DISABLE_Q))
-				ioat_unmap(pdev, pq->q_addr - offset, len,
-					   PCI_DMA_BIDIRECTIONAL, flags, 1);
-		}
-		break;
-	}
-	default:
-		dev_err(&pdev->dev, "%s: unknown op type: %#x\n",
-			__func__, desc->hw->ctl_f.op);
-	}
+	kmem_cache_free(ioat3_sed_cache, sed);
 }
 
 static bool desc_has_ext(struct ioat_ring_ent *desc)
@@ -577,7 +401,7 @@
 		tx = &desc->txd;
 		if (tx->cookie) {
 			dma_cookie_complete(tx);
-			ioat3_dma_unmap(ioat, desc, idx + i);
+			dma_descriptor_unmap(tx);
 			if (tx->callback) {
 				tx->callback(tx->callback_param);
 				tx->callback = NULL;
@@ -807,7 +631,7 @@
 	enum dma_status ret;
 
 	ret = dma_cookie_status(c, cookie, txstate);
-	if (ret == DMA_SUCCESS)
+	if (ret == DMA_COMPLETE)
 		return ret;
 
 	ioat3_cleanup(ioat);
@@ -1129,9 +953,6 @@
 	u8 op;
 	int i, s, idx, num_descs;
 
-	/* this function only handles src_cnt 9 - 16 */
-	BUG_ON(src_cnt < 9);
-
 	/* this function is only called with 9-16 sources */
 	op = result ? IOAT_OP_PQ_VAL_16S : IOAT_OP_PQ_16S;
 
@@ -1159,8 +980,7 @@
 
 		descs[0] = (struct ioat_raw_descriptor *) pq;
 
-		desc->sed = ioat3_alloc_sed(device,
-					    sed_get_pq16_pool_idx(src_cnt));
+		desc->sed = ioat3_alloc_sed(device, (src_cnt-2) >> 3);
 		if (!desc->sed) {
 			dev_err(to_dev(chan),
 				"%s: no free sed entries\n", __func__);
@@ -1218,13 +1038,21 @@
 	return &desc->txd;
 }
 
+static int src_cnt_flags(unsigned int src_cnt, unsigned long flags)
+{
+	if (dmaf_p_disabled_continue(flags))
+		return src_cnt + 1;
+	else if (dmaf_continue(flags))
+		return src_cnt + 3;
+	else
+		return src_cnt;
+}
+
 static struct dma_async_tx_descriptor *
 ioat3_prep_pq(struct dma_chan *chan, dma_addr_t *dst, dma_addr_t *src,
 	      unsigned int src_cnt, const unsigned char *scf, size_t len,
 	      unsigned long flags)
 {
-	struct dma_device *dma = chan->device;
-
 	/* specify valid address for disabled result */
 	if (flags & DMA_PREP_PQ_DISABLE_P)
 		dst[0] = dst[1];
@@ -1244,7 +1072,7 @@
 		single_source_coef[0] = scf[0];
 		single_source_coef[1] = 0;
 
-		return (src_cnt > 8) && (dma->max_pq > 8) ?
+		return src_cnt_flags(src_cnt, flags) > 8 ?
 			__ioat3_prep_pq16_lock(chan, NULL, dst, single_source,
 					       2, single_source_coef, len,
 					       flags) :
@@ -1252,7 +1080,7 @@
 					     single_source_coef, len, flags);
 
 	} else {
-		return (src_cnt > 8) && (dma->max_pq > 8) ?
+		return src_cnt_flags(src_cnt, flags) > 8 ?
 			__ioat3_prep_pq16_lock(chan, NULL, dst, src, src_cnt,
 					       scf, len, flags) :
 			__ioat3_prep_pq_lock(chan, NULL, dst, src, src_cnt,
@@ -1265,8 +1093,6 @@
 		  unsigned int src_cnt, const unsigned char *scf, size_t len,
 		  enum sum_check_flags *pqres, unsigned long flags)
 {
-	struct dma_device *dma = chan->device;
-
 	/* specify valid address for disabled result */
 	if (flags & DMA_PREP_PQ_DISABLE_P)
 		pq[0] = pq[1];
@@ -1278,7 +1104,7 @@
 	 */
 	*pqres = 0;
 
-	return (src_cnt > 8) && (dma->max_pq > 8) ?
+	return src_cnt_flags(src_cnt, flags) > 8 ?
 		__ioat3_prep_pq16_lock(chan, pqres, pq, src, src_cnt, scf, len,
 				       flags) :
 		__ioat3_prep_pq_lock(chan, pqres, pq, src, src_cnt, scf, len,
@@ -1289,7 +1115,6 @@
 ioat3_prep_pqxor(struct dma_chan *chan, dma_addr_t dst, dma_addr_t *src,
 		 unsigned int src_cnt, size_t len, unsigned long flags)
 {
-	struct dma_device *dma = chan->device;
 	unsigned char scf[src_cnt];
 	dma_addr_t pq[2];
 
@@ -1298,7 +1123,7 @@
 	flags |= DMA_PREP_PQ_DISABLE_Q;
 	pq[1] = dst; /* specify valid address for disabled result */
 
-	return (src_cnt > 8) && (dma->max_pq > 8) ?
+	return src_cnt_flags(src_cnt, flags) > 8 ?
 		__ioat3_prep_pq16_lock(chan, NULL, pq, src, src_cnt, scf, len,
 				       flags) :
 		__ioat3_prep_pq_lock(chan, NULL, pq, src, src_cnt, scf, len,
@@ -1310,7 +1135,6 @@
 		     unsigned int src_cnt, size_t len,
 		     enum sum_check_flags *result, unsigned long flags)
 {
-	struct dma_device *dma = chan->device;
 	unsigned char scf[src_cnt];
 	dma_addr_t pq[2];
 
@@ -1324,8 +1148,7 @@
 	flags |= DMA_PREP_PQ_DISABLE_Q;
 	pq[1] = pq[0]; /* specify valid address for disabled result */
 
-
-	return (src_cnt > 8) && (dma->max_pq > 8) ?
+	return src_cnt_flags(src_cnt, flags) > 8 ?
 		__ioat3_prep_pq16_lock(chan, result, pq, &src[1], src_cnt - 1,
 				       scf, len, flags) :
 		__ioat3_prep_pq_lock(chan, result, pq, &src[1], src_cnt - 1,
@@ -1444,9 +1267,7 @@
 					   DMA_TO_DEVICE);
 	tx = dma->device_prep_dma_xor(dma_chan, dest_dma, dma_srcs,
 				      IOAT_NUM_SRC_TEST, PAGE_SIZE,
-				      DMA_PREP_INTERRUPT |
-				      DMA_COMPL_SKIP_SRC_UNMAP |
-				      DMA_COMPL_SKIP_DEST_UNMAP);
+				      DMA_PREP_INTERRUPT);
 
 	if (!tx) {
 		dev_err(dev, "Self-test xor prep failed\n");
@@ -1468,7 +1289,7 @@
 
 	tmo = wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000));
 
-	if (dma->device_tx_status(dma_chan, cookie, NULL) != DMA_SUCCESS) {
+	if (dma->device_tx_status(dma_chan, cookie, NULL) != DMA_COMPLETE) {
 		dev_err(dev, "Self-test xor timed out\n");
 		err = -ENODEV;
 		goto dma_unmap;
@@ -1507,9 +1328,7 @@
 					   DMA_TO_DEVICE);
 	tx = dma->device_prep_dma_xor_val(dma_chan, dma_srcs,
 					  IOAT_NUM_SRC_TEST + 1, PAGE_SIZE,
-					  &xor_val_result, DMA_PREP_INTERRUPT |
-					  DMA_COMPL_SKIP_SRC_UNMAP |
-					  DMA_COMPL_SKIP_DEST_UNMAP);
+					  &xor_val_result, DMA_PREP_INTERRUPT);
 	if (!tx) {
 		dev_err(dev, "Self-test zero prep failed\n");
 		err = -ENODEV;
@@ -1530,7 +1349,7 @@
 
 	tmo = wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000));
 
-	if (dma->device_tx_status(dma_chan, cookie, NULL) != DMA_SUCCESS) {
+	if (dma->device_tx_status(dma_chan, cookie, NULL) != DMA_COMPLETE) {
 		dev_err(dev, "Self-test validate timed out\n");
 		err = -ENODEV;
 		goto dma_unmap;
@@ -1545,6 +1364,8 @@
 		goto free_resources;
 	}
 
+	memset(page_address(dest), 0, PAGE_SIZE);
+
 	/* test for non-zero parity sum */
 	op = IOAT_OP_XOR_VAL;
 
@@ -1554,9 +1375,7 @@
 					   DMA_TO_DEVICE);
 	tx = dma->device_prep_dma_xor_val(dma_chan, dma_srcs,
 					  IOAT_NUM_SRC_TEST + 1, PAGE_SIZE,
-					  &xor_val_result, DMA_PREP_INTERRUPT |
-					  DMA_COMPL_SKIP_SRC_UNMAP |
-					  DMA_COMPL_SKIP_DEST_UNMAP);
+					  &xor_val_result, DMA_PREP_INTERRUPT);
 	if (!tx) {
 		dev_err(dev, "Self-test 2nd zero prep failed\n");
 		err = -ENODEV;
@@ -1577,7 +1396,7 @@
 
 	tmo = wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000));
 
-	if (dma->device_tx_status(dma_chan, cookie, NULL) != DMA_SUCCESS) {
+	if (dma->device_tx_status(dma_chan, cookie, NULL) != DMA_COMPLETE) {
 		dev_err(dev, "Self-test 2nd validate timed out\n");
 		err = -ENODEV;
 		goto dma_unmap;
@@ -1630,52 +1449,36 @@
 
 static int ioat3_irq_reinit(struct ioatdma_device *device)
 {
-	int msixcnt = device->common.chancnt;
 	struct pci_dev *pdev = device->pdev;
-	int i;
-	struct msix_entry *msix;
-	struct ioat_chan_common *chan;
-	int err = 0;
+	int irq = pdev->irq, i;
+
+	if (!is_bwd_ioat(pdev))
+		return 0;
 
 	switch (device->irq_mode) {
 	case IOAT_MSIX:
+		for (i = 0; i < device->common.chancnt; i++) {
+			struct msix_entry *msix = &device->msix_entries[i];
+			struct ioat_chan_common *chan;
 
-		for (i = 0; i < msixcnt; i++) {
-			msix = &device->msix_entries[i];
 			chan = ioat_chan_by_index(device, i);
 			devm_free_irq(&pdev->dev, msix->vector, chan);
 		}
 
 		pci_disable_msix(pdev);
 		break;
-
-	case IOAT_MSIX_SINGLE:
-		msix = &device->msix_entries[0];
-		chan = ioat_chan_by_index(device, 0);
-		devm_free_irq(&pdev->dev, msix->vector, chan);
-		pci_disable_msix(pdev);
-		break;
-
 	case IOAT_MSI:
-		chan = ioat_chan_by_index(device, 0);
-		devm_free_irq(&pdev->dev, pdev->irq, chan);
 		pci_disable_msi(pdev);
-		break;
-
+		/* fall through */
 	case IOAT_INTX:
-		chan = ioat_chan_by_index(device, 0);
-		devm_free_irq(&pdev->dev, pdev->irq, chan);
+		devm_free_irq(&pdev->dev, irq, device);
 		break;
-
 	default:
 		return 0;
 	}
-
 	device->irq_mode = IOAT_NOIRQ;
 
-	err = ioat_dma_setup_interrupts(device);
-
-	return err;
+	return ioat_dma_setup_interrupts(device);
 }
 
 static int ioat3_reset_hw(struct ioat_chan_common *chan)
@@ -1718,14 +1521,12 @@
 	}
 
 	err = ioat2_reset_sync(chan, msecs_to_jiffies(200));
-	if (err) {
-		dev_err(&pdev->dev, "Failed to reset!\n");
-		return err;
-	}
-
-	if (device->irq_mode != IOAT_NOIRQ && is_bwd_ioat(pdev))
+	if (!err)
 		err = ioat3_irq_reinit(device);
 
+	if (err)
+		dev_err(&pdev->dev, "Failed to reset: %d\n", err);
+
 	return err;
 }
 
@@ -1835,21 +1636,15 @@
 		char pool_name[14];
 		int i;
 
-		/* allocate sw descriptor pool for SED */
-		device->sed_pool = kmem_cache_create("ioat_sed",
-				sizeof(struct ioat_sed_ent), 0, 0, NULL);
-		if (!device->sed_pool)
-			return -ENOMEM;
-
 		for (i = 0; i < MAX_SED_POOLS; i++) {
 			snprintf(pool_name, 14, "ioat_hw%d_sed", i);
 
 			/* allocate SED DMA pool */
-			device->sed_hw_pool[i] = dma_pool_create(pool_name,
+			device->sed_hw_pool[i] = dmam_pool_create(pool_name,
 					&pdev->dev,
 					SED_SIZE * (i + 1), 64, 0);
 			if (!device->sed_hw_pool[i])
-				goto sed_pool_cleanup;
+				return -ENOMEM;
 
 		}
 	}
@@ -1875,28 +1670,4 @@
 		device->dca = ioat3_dca_init(pdev, device->reg_base);
 
 	return 0;
-
-sed_pool_cleanup:
-	if (device->sed_pool) {
-		int i;
-		kmem_cache_destroy(device->sed_pool);
-
-		for (i = 0; i < MAX_SED_POOLS; i++)
-			if (device->sed_hw_pool[i])
-				dma_pool_destroy(device->sed_hw_pool[i]);
-	}
-
-	return -ENOMEM;
-}
-
-void ioat3_dma_remove(struct ioatdma_device *device)
-{
-	if (device->sed_pool) {
-		int i;
-		kmem_cache_destroy(device->sed_pool);
-
-		for (i = 0; i < MAX_SED_POOLS; i++)
-			if (device->sed_hw_pool[i])
-				dma_pool_destroy(device->sed_hw_pool[i]);
-	}
 }
diff --git a/drivers/dma/ioat/pci.c b/drivers/dma/ioat/pci.c
index 2c8d560..1d051cd 100644
--- a/drivers/dma/ioat/pci.c
+++ b/drivers/dma/ioat/pci.c
@@ -123,6 +123,7 @@
 MODULE_PARM_DESC(ioat_dca_enabled, "control support of dca service (default: 1)");
 
 struct kmem_cache *ioat2_cache;
+struct kmem_cache *ioat3_sed_cache;
 
 #define DRV_NAME "ioatdma"
 
@@ -207,9 +208,6 @@
 	if (!device)
 		return;
 
-	if (device->version >= IOAT_VER_3_0)
-		ioat3_dma_remove(device);
-
 	dev_err(&pdev->dev, "Removing dma and dca services\n");
 	if (device->dca) {
 		unregister_dca_provider(device->dca, &pdev->dev);
@@ -221,7 +219,7 @@
 
 static int __init ioat_init_module(void)
 {
-	int err;
+	int err = -ENOMEM;
 
 	pr_info("%s: Intel(R) QuickData Technology Driver %s\n",
 		DRV_NAME, IOAT_DMA_VERSION);
@@ -231,9 +229,21 @@
 	if (!ioat2_cache)
 		return -ENOMEM;
 
+	ioat3_sed_cache = KMEM_CACHE(ioat_sed_ent, 0);
+	if (!ioat3_sed_cache)
+		goto err_ioat2_cache;
+
 	err = pci_register_driver(&ioat_pci_driver);
 	if (err)
-		kmem_cache_destroy(ioat2_cache);
+		goto err_ioat3_cache;
+
+	return 0;
+
+ err_ioat3_cache:
+	kmem_cache_destroy(ioat3_sed_cache);
+
+ err_ioat2_cache:
+	kmem_cache_destroy(ioat2_cache);
 
 	return err;
 }
diff --git a/drivers/dma/iop-adma.c b/drivers/dma/iop-adma.c
index dd8b44a..c56137b 100644
--- a/drivers/dma/iop-adma.c
+++ b/drivers/dma/iop-adma.c
@@ -61,80 +61,6 @@
 	}
 }
 
-static void
-iop_desc_unmap(struct iop_adma_chan *iop_chan, struct iop_adma_desc_slot *desc)
-{
-	struct dma_async_tx_descriptor *tx = &desc->async_tx;
-	struct iop_adma_desc_slot *unmap = desc->group_head;
-	struct device *dev = &iop_chan->device->pdev->dev;
-	u32 len = unmap->unmap_len;
-	enum dma_ctrl_flags flags = tx->flags;
-	u32 src_cnt;
-	dma_addr_t addr;
-	dma_addr_t dest;
-
-	src_cnt = unmap->unmap_src_cnt;
-	dest = iop_desc_get_dest_addr(unmap, iop_chan);
-	if (!(flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
-		enum dma_data_direction dir;
-
-		if (src_cnt > 1) /* is xor? */
-			dir = DMA_BIDIRECTIONAL;
-		else
-			dir = DMA_FROM_DEVICE;
-
-		dma_unmap_page(dev, dest, len, dir);
-	}
-
-	if (!(flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-		while (src_cnt--) {
-			addr = iop_desc_get_src_addr(unmap, iop_chan, src_cnt);
-			if (addr == dest)
-				continue;
-			dma_unmap_page(dev, addr, len, DMA_TO_DEVICE);
-		}
-	}
-	desc->group_head = NULL;
-}
-
-static void
-iop_desc_unmap_pq(struct iop_adma_chan *iop_chan, struct iop_adma_desc_slot *desc)
-{
-	struct dma_async_tx_descriptor *tx = &desc->async_tx;
-	struct iop_adma_desc_slot *unmap = desc->group_head;
-	struct device *dev = &iop_chan->device->pdev->dev;
-	u32 len = unmap->unmap_len;
-	enum dma_ctrl_flags flags = tx->flags;
-	u32 src_cnt = unmap->unmap_src_cnt;
-	dma_addr_t pdest = iop_desc_get_dest_addr(unmap, iop_chan);
-	dma_addr_t qdest = iop_desc_get_qdest_addr(unmap, iop_chan);
-	int i;
-
-	if (tx->flags & DMA_PREP_CONTINUE)
-		src_cnt -= 3;
-
-	if (!(flags & DMA_COMPL_SKIP_DEST_UNMAP) && !desc->pq_check_result) {
-		dma_unmap_page(dev, pdest, len, DMA_BIDIRECTIONAL);
-		dma_unmap_page(dev, qdest, len, DMA_BIDIRECTIONAL);
-	}
-
-	if (!(flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-		dma_addr_t addr;
-
-		for (i = 0; i < src_cnt; i++) {
-			addr = iop_desc_get_src_addr(unmap, iop_chan, i);
-			dma_unmap_page(dev, addr, len, DMA_TO_DEVICE);
-		}
-		if (desc->pq_check_result) {
-			dma_unmap_page(dev, pdest, len, DMA_TO_DEVICE);
-			dma_unmap_page(dev, qdest, len, DMA_TO_DEVICE);
-		}
-	}
-
-	desc->group_head = NULL;
-}
-
-
 static dma_cookie_t
 iop_adma_run_tx_complete_actions(struct iop_adma_desc_slot *desc,
 	struct iop_adma_chan *iop_chan, dma_cookie_t cookie)
@@ -152,15 +78,9 @@
 		if (tx->callback)
 			tx->callback(tx->callback_param);
 
-		/* unmap dma addresses
-		 * (unmap_single vs unmap_page?)
-		 */
-		if (desc->group_head && desc->unmap_len) {
-			if (iop_desc_is_pq(desc))
-				iop_desc_unmap_pq(iop_chan, desc);
-			else
-				iop_desc_unmap(iop_chan, desc);
-		}
+		dma_descriptor_unmap(tx);
+		if (desc->group_head)
+			desc->group_head = NULL;
 	}
 
 	/* run dependent operations */
@@ -591,7 +511,6 @@
 	if (sw_desc) {
 		grp_start = sw_desc->group_head;
 		iop_desc_init_interrupt(grp_start, iop_chan);
-		grp_start->unmap_len = 0;
 		sw_desc->async_tx.flags = flags;
 	}
 	spin_unlock_bh(&iop_chan->lock);
@@ -623,8 +542,6 @@
 		iop_desc_set_byte_count(grp_start, iop_chan, len);
 		iop_desc_set_dest_addr(grp_start, iop_chan, dma_dest);
 		iop_desc_set_memcpy_src_addr(grp_start, dma_src);
-		sw_desc->unmap_src_cnt = 1;
-		sw_desc->unmap_len = len;
 		sw_desc->async_tx.flags = flags;
 	}
 	spin_unlock_bh(&iop_chan->lock);
@@ -657,8 +574,6 @@
 		iop_desc_init_xor(grp_start, src_cnt, flags);
 		iop_desc_set_byte_count(grp_start, iop_chan, len);
 		iop_desc_set_dest_addr(grp_start, iop_chan, dma_dest);
-		sw_desc->unmap_src_cnt = src_cnt;
-		sw_desc->unmap_len = len;
 		sw_desc->async_tx.flags = flags;
 		while (src_cnt--)
 			iop_desc_set_xor_src_addr(grp_start, src_cnt,
@@ -694,8 +609,6 @@
 		grp_start->xor_check_result = result;
 		pr_debug("\t%s: grp_start->xor_check_result: %p\n",
 			__func__, grp_start->xor_check_result);
-		sw_desc->unmap_src_cnt = src_cnt;
-		sw_desc->unmap_len = len;
 		sw_desc->async_tx.flags = flags;
 		while (src_cnt--)
 			iop_desc_set_zero_sum_src_addr(grp_start, src_cnt,
@@ -748,8 +661,6 @@
 			dst[0] = dst[1] & 0x7;
 
 		iop_desc_set_pq_addr(g, dst);
-		sw_desc->unmap_src_cnt = src_cnt;
-		sw_desc->unmap_len = len;
 		sw_desc->async_tx.flags = flags;
 		for (i = 0; i < src_cnt; i++)
 			iop_desc_set_pq_src_addr(g, i, src[i], scf[i]);
@@ -804,8 +715,6 @@
 		g->pq_check_result = pqres;
 		pr_debug("\t%s: g->pq_check_result: %p\n",
 			__func__, g->pq_check_result);
-		sw_desc->unmap_src_cnt = src_cnt+2;
-		sw_desc->unmap_len = len;
 		sw_desc->async_tx.flags = flags;
 		while (src_cnt--)
 			iop_desc_set_pq_zero_sum_src_addr(g, src_cnt,
@@ -864,7 +773,7 @@
 	int ret;
 
 	ret = dma_cookie_status(chan, cookie, txstate);
-	if (ret == DMA_SUCCESS)
+	if (ret == DMA_COMPLETE)
 		return ret;
 
 	iop_adma_slot_cleanup(iop_chan);
@@ -983,7 +892,7 @@
 	msleep(1);
 
 	if (iop_adma_status(dma_chan, cookie, NULL) !=
-			DMA_SUCCESS) {
+			DMA_COMPLETE) {
 		dev_err(dma_chan->device->dev,
 			"Self-test copy timed out, disabling\n");
 		err = -ENODEV;
@@ -1083,7 +992,7 @@
 	msleep(8);
 
 	if (iop_adma_status(dma_chan, cookie, NULL) !=
-		DMA_SUCCESS) {
+		DMA_COMPLETE) {
 		dev_err(dma_chan->device->dev,
 			"Self-test xor timed out, disabling\n");
 		err = -ENODEV;
@@ -1129,7 +1038,7 @@
 	iop_adma_issue_pending(dma_chan);
 	msleep(8);
 
-	if (iop_adma_status(dma_chan, cookie, NULL) != DMA_SUCCESS) {
+	if (iop_adma_status(dma_chan, cookie, NULL) != DMA_COMPLETE) {
 		dev_err(dma_chan->device->dev,
 			"Self-test zero sum timed out, disabling\n");
 		err = -ENODEV;
@@ -1158,7 +1067,7 @@
 	iop_adma_issue_pending(dma_chan);
 	msleep(8);
 
-	if (iop_adma_status(dma_chan, cookie, NULL) != DMA_SUCCESS) {
+	if (iop_adma_status(dma_chan, cookie, NULL) != DMA_COMPLETE) {
 		dev_err(dma_chan->device->dev,
 			"Self-test non-zero sum timed out, disabling\n");
 		err = -ENODEV;
@@ -1254,7 +1163,7 @@
 	msleep(8);
 
 	if (iop_adma_status(dma_chan, cookie, NULL) !=
-		DMA_SUCCESS) {
+		DMA_COMPLETE) {
 		dev_err(dev, "Self-test pq timed out, disabling\n");
 		err = -ENODEV;
 		goto free_resources;
@@ -1291,7 +1200,7 @@
 	msleep(8);
 
 	if (iop_adma_status(dma_chan, cookie, NULL) !=
-		DMA_SUCCESS) {
+		DMA_COMPLETE) {
 		dev_err(dev, "Self-test pq-zero-sum timed out, disabling\n");
 		err = -ENODEV;
 		goto free_resources;
@@ -1323,7 +1232,7 @@
 	msleep(8);
 
 	if (iop_adma_status(dma_chan, cookie, NULL) !=
-		DMA_SUCCESS) {
+		DMA_COMPLETE) {
 		dev_err(dev, "Self-test !pq-zero-sum timed out, disabling\n");
 		err = -ENODEV;
 		goto free_resources;
diff --git a/drivers/dma/ipu/ipu_idmac.c b/drivers/dma/ipu/ipu_idmac.c
index cb9c0bc..128ca14 100644
--- a/drivers/dma/ipu/ipu_idmac.c
+++ b/drivers/dma/ipu/ipu_idmac.c
@@ -1232,8 +1232,10 @@
 	desc = list_entry(ichan->queue.next, struct idmac_tx_desc, list);
 	descnew = desc;
 
-	dev_dbg(dev, "IDMAC irq %d, dma 0x%08x, next dma 0x%08x, current %d, curbuf 0x%08x\n",
-		irq, sg_dma_address(*sg), sgnext ? sg_dma_address(sgnext) : 0, ichan->active_buffer, curbuf);
+	dev_dbg(dev, "IDMAC irq %d, dma %#llx, next dma %#llx, current %d, curbuf %#x\n",
+		irq, (u64)sg_dma_address(*sg),
+		sgnext ? (u64)sg_dma_address(sgnext) : 0,
+		ichan->active_buffer, curbuf);
 
 	/* Find the descriptor of sgnext */
 	sgnew = idmac_sg_next(ichan, &descnew, *sg);
diff --git a/drivers/dma/k3dma.c b/drivers/dma/k3dma.c
index a2c330f..e260754 100644
--- a/drivers/dma/k3dma.c
+++ b/drivers/dma/k3dma.c
@@ -344,7 +344,7 @@
 	size_t bytes = 0;
 
 	ret = dma_cookie_status(&c->vc.chan, cookie, state);
-	if (ret == DMA_SUCCESS)
+	if (ret == DMA_COMPLETE)
 		return ret;
 
 	spin_lock_irqsave(&c->vc.lock, flags);
@@ -693,7 +693,7 @@
 
 	irq = platform_get_irq(op, 0);
 	ret = devm_request_irq(&op->dev, irq,
-			k3_dma_int_handler, IRQF_DISABLED, DRIVER_NAME, d);
+			k3_dma_int_handler, 0, DRIVER_NAME, d);
 	if (ret)
 		return ret;
 
diff --git a/drivers/dma/mmp_pdma.c b/drivers/dma/mmp_pdma.c
index ff8d7827..dcb1e05 100644
--- a/drivers/dma/mmp_pdma.c
+++ b/drivers/dma/mmp_pdma.c
@@ -798,8 +798,7 @@
 		 * move the descriptors to a temporary list so we can drop
 		 * the lock during the entire cleanup operation
 		 */
-		list_del(&desc->node);
-		list_add(&desc->node, &chain_cleanup);
+		list_move(&desc->node, &chain_cleanup);
 
 		/*
 		 * Look for the first list entry which has the ENDIRQEN flag
@@ -863,7 +862,7 @@
 
 	if (irq) {
 		ret = devm_request_irq(pdev->dev, irq,
-			mmp_pdma_chan_handler, IRQF_DISABLED, "pdma", phy);
+			mmp_pdma_chan_handler, 0, "pdma", phy);
 		if (ret) {
 			dev_err(pdev->dev, "channel request irq fail!\n");
 			return ret;
@@ -970,7 +969,7 @@
 		/* all chan share one irq, demux inside */
 		irq = platform_get_irq(op, 0);
 		ret = devm_request_irq(pdev->dev, irq,
-			mmp_pdma_int_handler, IRQF_DISABLED, "pdma", pdev);
+			mmp_pdma_int_handler, 0, "pdma", pdev);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/dma/mmp_tdma.c b/drivers/dma/mmp_tdma.c
index d3b6358..3ddacc1 100644
--- a/drivers/dma/mmp_tdma.c
+++ b/drivers/dma/mmp_tdma.c
@@ -62,6 +62,11 @@
 #define TDCR_BURSTSZ_16B	(0x3 << 6)
 #define TDCR_BURSTSZ_32B	(0x6 << 6)
 #define TDCR_BURSTSZ_64B	(0x7 << 6)
+#define TDCR_BURSTSZ_SQU_1B		(0x5 << 6)
+#define TDCR_BURSTSZ_SQU_2B		(0x6 << 6)
+#define TDCR_BURSTSZ_SQU_4B		(0x0 << 6)
+#define TDCR_BURSTSZ_SQU_8B		(0x1 << 6)
+#define TDCR_BURSTSZ_SQU_16B	(0x3 << 6)
 #define TDCR_BURSTSZ_SQU_32B	(0x7 << 6)
 #define TDCR_BURSTSZ_128B	(0x5 << 6)
 #define TDCR_DSTDIR_MSK		(0x3 << 4)	/* Dst Direction */
@@ -158,7 +163,7 @@
 	/* disable irq */
 	writel(0, tdmac->reg_base + TDIMR);
 
-	tdmac->status = DMA_SUCCESS;
+	tdmac->status = DMA_COMPLETE;
 }
 
 static void mmp_tdma_resume_chan(struct mmp_tdma_chan *tdmac)
@@ -228,8 +233,31 @@
 			return -EINVAL;
 		}
 	} else if (tdmac->type == PXA910_SQU) {
-		tdcr |= TDCR_BURSTSZ_SQU_32B;
 		tdcr |= TDCR_SSPMOD;
+
+		switch (tdmac->burst_sz) {
+		case 1:
+			tdcr |= TDCR_BURSTSZ_SQU_1B;
+			break;
+		case 2:
+			tdcr |= TDCR_BURSTSZ_SQU_2B;
+			break;
+		case 4:
+			tdcr |= TDCR_BURSTSZ_SQU_4B;
+			break;
+		case 8:
+			tdcr |= TDCR_BURSTSZ_SQU_8B;
+			break;
+		case 16:
+			tdcr |= TDCR_BURSTSZ_SQU_16B;
+			break;
+		case 32:
+			tdcr |= TDCR_BURSTSZ_SQU_32B;
+			break;
+		default:
+			dev_err(tdmac->dev, "mmp_tdma: unknown burst size.\n");
+			return -EINVAL;
+		}
 	}
 
 	writel(tdcr, tdmac->reg_base + TDCR);
@@ -324,7 +352,7 @@
 
 	if (tdmac->irq) {
 		ret = devm_request_irq(tdmac->dev, tdmac->irq,
-			mmp_tdma_chan_handler, IRQF_DISABLED, "tdma", tdmac);
+			mmp_tdma_chan_handler, 0, "tdma", tdmac);
 		if (ret)
 			return ret;
 	}
@@ -365,7 +393,7 @@
 	int num_periods = buf_len / period_len;
 	int i = 0, buf = 0;
 
-	if (tdmac->status != DMA_SUCCESS)
+	if (tdmac->status != DMA_COMPLETE)
 		return NULL;
 
 	if (period_len > TDMA_MAX_XFER_BYTES) {
@@ -499,7 +527,7 @@
 	tdmac->idx	   = idx;
 	tdmac->type	   = type;
 	tdmac->reg_base	   = (unsigned long)tdev->base + idx * 4;
-	tdmac->status = DMA_SUCCESS;
+	tdmac->status = DMA_COMPLETE;
 	tdev->tdmac[tdmac->idx] = tdmac;
 	tasklet_init(&tdmac->tasklet, dma_do_tasklet, (unsigned long)tdmac);
 
@@ -554,7 +582,7 @@
 	if (irq_num != chan_num) {
 		irq = platform_get_irq(pdev, 0);
 		ret = devm_request_irq(&pdev->dev, irq,
-			mmp_tdma_int_handler, IRQF_DISABLED, "tdma", tdev);
+			mmp_tdma_int_handler, 0, "tdma", tdev);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index 536dcb8..7807f0e 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -60,14 +60,6 @@
 	return hw_desc->phy_dest_addr;
 }
 
-static u32 mv_desc_get_src_addr(struct mv_xor_desc_slot *desc,
-				int src_idx)
-{
-	struct mv_xor_desc *hw_desc = desc->hw_desc;
-	return hw_desc->phy_src_addr[mv_phy_src_idx(src_idx)];
-}
-
-
 static void mv_desc_set_byte_count(struct mv_xor_desc_slot *desc,
 				   u32 byte_count)
 {
@@ -278,42 +270,9 @@
 			desc->async_tx.callback(
 				desc->async_tx.callback_param);
 
-		/* unmap dma addresses
-		 * (unmap_single vs unmap_page?)
-		 */
-		if (desc->group_head && desc->unmap_len) {
-			struct mv_xor_desc_slot *unmap = desc->group_head;
-			struct device *dev = mv_chan_to_devp(mv_chan);
-			u32 len = unmap->unmap_len;
-			enum dma_ctrl_flags flags = desc->async_tx.flags;
-			u32 src_cnt;
-			dma_addr_t addr;
-			dma_addr_t dest;
-
-			src_cnt = unmap->unmap_src_cnt;
-			dest = mv_desc_get_dest_addr(unmap);
-			if (!(flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
-				enum dma_data_direction dir;
-
-				if (src_cnt > 1) /* is xor ? */
-					dir = DMA_BIDIRECTIONAL;
-				else
-					dir = DMA_FROM_DEVICE;
-				dma_unmap_page(dev, dest, len, dir);
-			}
-
-			if (!(flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-				while (src_cnt--) {
-					addr = mv_desc_get_src_addr(unmap,
-								    src_cnt);
-					if (addr == dest)
-						continue;
-					dma_unmap_page(dev, addr, len,
-						       DMA_TO_DEVICE);
-				}
-			}
+		dma_descriptor_unmap(&desc->async_tx);
+		if (desc->group_head)
 			desc->group_head = NULL;
-		}
 	}
 
 	/* run dependent operations */
@@ -749,7 +708,7 @@
 	enum dma_status ret;
 
 	ret = dma_cookie_status(chan, cookie, txstate);
-	if (ret == DMA_SUCCESS) {
+	if (ret == DMA_COMPLETE) {
 		mv_xor_clean_completed_slots(mv_chan);
 		return ret;
 	}
@@ -874,7 +833,7 @@
 	msleep(1);
 
 	if (mv_xor_status(dma_chan, cookie, NULL) !=
-	    DMA_SUCCESS) {
+	    DMA_COMPLETE) {
 		dev_err(dma_chan->device->dev,
 			"Self-test copy timed out, disabling\n");
 		err = -ENODEV;
@@ -968,7 +927,7 @@
 	msleep(8);
 
 	if (mv_xor_status(dma_chan, cookie, NULL) !=
-	    DMA_SUCCESS) {
+	    DMA_COMPLETE) {
 		dev_err(dma_chan->device->dev,
 			"Self-test xor timed out, disabling\n");
 		err = -ENODEV;
@@ -1076,10 +1035,7 @@
 	}
 
 	mv_chan->mmr_base = xordev->xor_base;
-	if (!mv_chan->mmr_base) {
-		ret = -ENOMEM;
-		goto err_free_dma;
-	}
+	mv_chan->mmr_high_base = xordev->xor_high_base;
 	tasklet_init(&mv_chan->irq_tasklet, mv_xor_tasklet, (unsigned long)
 		     mv_chan);
 
@@ -1138,7 +1094,7 @@
 mv_xor_conf_mbus_windows(struct mv_xor_device *xordev,
 			 const struct mbus_dram_target_info *dram)
 {
-	void __iomem *base = xordev->xor_base;
+	void __iomem *base = xordev->xor_high_base;
 	u32 win_enable = 0;
 	int i;
 
diff --git a/drivers/dma/mv_xor.h b/drivers/dma/mv_xor.h
index 06b067f..d074922 100644
--- a/drivers/dma/mv_xor.h
+++ b/drivers/dma/mv_xor.h
@@ -34,13 +34,13 @@
 #define XOR_OPERATION_MODE_MEMCPY	2
 #define XOR_DESCRIPTOR_SWAP		BIT(14)
 
-#define XOR_CURR_DESC(chan)	(chan->mmr_base + 0x210 + (chan->idx * 4))
-#define XOR_NEXT_DESC(chan)	(chan->mmr_base + 0x200 + (chan->idx * 4))
-#define XOR_BYTE_COUNT(chan)	(chan->mmr_base + 0x220 + (chan->idx * 4))
-#define XOR_DEST_POINTER(chan)	(chan->mmr_base + 0x2B0 + (chan->idx * 4))
-#define XOR_BLOCK_SIZE(chan)	(chan->mmr_base + 0x2C0 + (chan->idx * 4))
-#define XOR_INIT_VALUE_LOW(chan)	(chan->mmr_base + 0x2E0)
-#define XOR_INIT_VALUE_HIGH(chan)	(chan->mmr_base + 0x2E4)
+#define XOR_CURR_DESC(chan)	(chan->mmr_high_base + 0x10 + (chan->idx * 4))
+#define XOR_NEXT_DESC(chan)	(chan->mmr_high_base + 0x00 + (chan->idx * 4))
+#define XOR_BYTE_COUNT(chan)	(chan->mmr_high_base + 0x20 + (chan->idx * 4))
+#define XOR_DEST_POINTER(chan)	(chan->mmr_high_base + 0xB0 + (chan->idx * 4))
+#define XOR_BLOCK_SIZE(chan)	(chan->mmr_high_base + 0xC0 + (chan->idx * 4))
+#define XOR_INIT_VALUE_LOW(chan)	(chan->mmr_high_base + 0xE0)
+#define XOR_INIT_VALUE_HIGH(chan)	(chan->mmr_high_base + 0xE4)
 
 #define XOR_CONFIG(chan)	(chan->mmr_base + 0x10 + (chan->idx * 4))
 #define XOR_ACTIVATION(chan)	(chan->mmr_base + 0x20 + (chan->idx * 4))
@@ -50,11 +50,11 @@
 #define XOR_ERROR_ADDR(chan)	(chan->mmr_base + 0x60)
 #define XOR_INTR_MASK_VALUE	0x3F5
 
-#define WINDOW_BASE(w)		(0x250 + ((w) << 2))
-#define WINDOW_SIZE(w)		(0x270 + ((w) << 2))
-#define WINDOW_REMAP_HIGH(w)	(0x290 + ((w) << 2))
-#define WINDOW_BAR_ENABLE(chan)	(0x240 + ((chan) << 2))
-#define WINDOW_OVERRIDE_CTRL(chan)	(0x2A0 + ((chan) << 2))
+#define WINDOW_BASE(w)		(0x50 + ((w) << 2))
+#define WINDOW_SIZE(w)		(0x70 + ((w) << 2))
+#define WINDOW_REMAP_HIGH(w)	(0x90 + ((w) << 2))
+#define WINDOW_BAR_ENABLE(chan)	(0x40 + ((chan) << 2))
+#define WINDOW_OVERRIDE_CTRL(chan)	(0xA0 + ((chan) << 2))
 
 struct mv_xor_device {
 	void __iomem	     *xor_base;
@@ -82,6 +82,7 @@
 	int			pending;
 	spinlock_t		lock; /* protects the descriptor slot pool */
 	void __iomem		*mmr_base;
+	void __iomem		*mmr_high_base;
 	unsigned int		idx;
 	int                     irq;
 	enum dma_transaction_type	current_type;
diff --git a/drivers/dma/mxs-dma.c b/drivers/dma/mxs-dma.c
index ccd13df..ead4913 100644
--- a/drivers/dma/mxs-dma.c
+++ b/drivers/dma/mxs-dma.c
@@ -27,6 +27,7 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/of_dma.h>
+#include <linux/list.h>
 
 #include <asm/irq.h>
 
@@ -57,6 +58,9 @@
 	(((dma_is_apbh(d) && apbh_is_old(d)) ? 0x050 : 0x110) + (n) * 0x70)
 #define HW_APBHX_CHn_SEMA(d, n) \
 	(((dma_is_apbh(d) && apbh_is_old(d)) ? 0x080 : 0x140) + (n) * 0x70)
+#define HW_APBHX_CHn_BAR(d, n) \
+	(((dma_is_apbh(d) && apbh_is_old(d)) ? 0x070 : 0x130) + (n) * 0x70)
+#define HW_APBX_CHn_DEBUG1(d, n) (0x150 + (n) * 0x70)
 
 /*
  * ccw bits definitions
@@ -115,7 +119,9 @@
 	int				desc_count;
 	enum dma_status			status;
 	unsigned int			flags;
+	bool				reset;
 #define MXS_DMA_SG_LOOP			(1 << 0)
+#define MXS_DMA_USE_SEMAPHORE		(1 << 1)
 };
 
 #define MXS_DMA_CHANNELS		16
@@ -201,12 +207,47 @@
 	struct mxs_dma_engine *mxs_dma = mxs_chan->mxs_dma;
 	int chan_id = mxs_chan->chan.chan_id;
 
-	if (dma_is_apbh(mxs_dma) && apbh_is_old(mxs_dma))
+	/*
+	 * mxs dma channel resets can cause a channel stall. To recover from a
+	 * channel stall, we have to reset the whole DMA engine. To avoid this,
+	 * we use cyclic DMA with semaphores, that are enhanced in
+	 * mxs_dma_int_handler. To reset the channel, we can simply stop writing
+	 * into the semaphore counter.
+	 */
+	if (mxs_chan->flags & MXS_DMA_USE_SEMAPHORE &&
+			mxs_chan->flags & MXS_DMA_SG_LOOP) {
+		mxs_chan->reset = true;
+	} else if (dma_is_apbh(mxs_dma) && apbh_is_old(mxs_dma)) {
 		writel(1 << (chan_id + BP_APBH_CTRL0_RESET_CHANNEL),
 			mxs_dma->base + HW_APBHX_CTRL0 + STMP_OFFSET_REG_SET);
-	else
+	} else {
+		unsigned long elapsed = 0;
+		const unsigned long max_wait = 50000; /* 50ms */
+		void __iomem *reg_dbg1 = mxs_dma->base +
+				HW_APBX_CHn_DEBUG1(mxs_dma, chan_id);
+
+		/*
+		 * On i.MX28 APBX, the DMA channel can stop working if we reset
+		 * the channel while it is in READ_FLUSH (0x08) state.
+		 * We wait here until we leave the state. Then we trigger the
+		 * reset. Waiting a maximum of 50ms, the kernel shouldn't crash
+		 * because of this.
+		 */
+		while ((readl(reg_dbg1) & 0xf) == 0x8 && elapsed < max_wait) {
+			udelay(100);
+			elapsed += 100;
+		}
+
+		if (elapsed >= max_wait)
+			dev_err(&mxs_chan->mxs_dma->pdev->dev,
+					"Failed waiting for the DMA channel %d to leave state READ_FLUSH, trying to reset channel in READ_FLUSH state now\n",
+					chan_id);
+
 		writel(1 << (chan_id + BP_APBHX_CHANNEL_CTRL_RESET_CHANNEL),
 			mxs_dma->base + HW_APBHX_CHANNEL_CTRL + STMP_OFFSET_REG_SET);
+	}
+
+	mxs_chan->status = DMA_COMPLETE;
 }
 
 static void mxs_dma_enable_chan(struct mxs_dma_chan *mxs_chan)
@@ -219,12 +260,21 @@
 		mxs_dma->base + HW_APBHX_CHn_NXTCMDAR(mxs_dma, chan_id));
 
 	/* write 1 to SEMA to kick off the channel */
-	writel(1, mxs_dma->base + HW_APBHX_CHn_SEMA(mxs_dma, chan_id));
+	if (mxs_chan->flags & MXS_DMA_USE_SEMAPHORE &&
+			mxs_chan->flags & MXS_DMA_SG_LOOP) {
+		/* A cyclic DMA consists of at least 2 segments, so initialize
+		 * the semaphore with 2 so we have enough time to add 1 to the
+		 * semaphore if we need to */
+		writel(2, mxs_dma->base + HW_APBHX_CHn_SEMA(mxs_dma, chan_id));
+	} else {
+		writel(1, mxs_dma->base + HW_APBHX_CHn_SEMA(mxs_dma, chan_id));
+	}
+	mxs_chan->reset = false;
 }
 
 static void mxs_dma_disable_chan(struct mxs_dma_chan *mxs_chan)
 {
-	mxs_chan->status = DMA_SUCCESS;
+	mxs_chan->status = DMA_COMPLETE;
 }
 
 static void mxs_dma_pause_chan(struct mxs_dma_chan *mxs_chan)
@@ -272,58 +322,88 @@
 		mxs_chan->desc.callback(mxs_chan->desc.callback_param);
 }
 
+static int mxs_dma_irq_to_chan(struct mxs_dma_engine *mxs_dma, int irq)
+{
+	int i;
+
+	for (i = 0; i != mxs_dma->nr_channels; ++i)
+		if (mxs_dma->mxs_chans[i].chan_irq == irq)
+			return i;
+
+	return -EINVAL;
+}
+
 static irqreturn_t mxs_dma_int_handler(int irq, void *dev_id)
 {
 	struct mxs_dma_engine *mxs_dma = dev_id;
-	u32 stat1, stat2;
+	struct mxs_dma_chan *mxs_chan;
+	u32 completed;
+	u32 err;
+	int chan = mxs_dma_irq_to_chan(mxs_dma, irq);
+
+	if (chan < 0)
+		return IRQ_NONE;
 
 	/* completion status */
-	stat1 = readl(mxs_dma->base + HW_APBHX_CTRL1);
-	stat1 &= MXS_DMA_CHANNELS_MASK;
-	writel(stat1, mxs_dma->base + HW_APBHX_CTRL1 + STMP_OFFSET_REG_CLR);
+	completed = readl(mxs_dma->base + HW_APBHX_CTRL1);
+	completed = (completed >> chan) & 0x1;
+
+	/* Clear interrupt */
+	writel((1 << chan),
+			mxs_dma->base + HW_APBHX_CTRL1 + STMP_OFFSET_REG_CLR);
 
 	/* error status */
-	stat2 = readl(mxs_dma->base + HW_APBHX_CTRL2);
-	writel(stat2, mxs_dma->base + HW_APBHX_CTRL2 + STMP_OFFSET_REG_CLR);
+	err = readl(mxs_dma->base + HW_APBHX_CTRL2);
+	err &= (1 << (MXS_DMA_CHANNELS + chan)) | (1 << chan);
+
+	/*
+	 * error status bit is in the upper 16 bits, error irq bit in the lower
+	 * 16 bits. We transform it into a simpler error code:
+	 * err: 0x00 = no error, 0x01 = TERMINATION, 0x02 = BUS_ERROR
+	 */
+	err = (err >> (MXS_DMA_CHANNELS + chan)) + (err >> chan);
+
+	/* Clear error irq */
+	writel((1 << chan),
+			mxs_dma->base + HW_APBHX_CTRL2 + STMP_OFFSET_REG_CLR);
 
 	/*
 	 * When both completion and error of termination bits set at the
 	 * same time, we do not take it as an error.  IOW, it only becomes
-	 * an error we need to handle here in case of either it's (1) a bus
-	 * error or (2) a termination error with no completion.
+	 * an error we need to handle here in case of either it's a bus
+	 * error or a termination error with no completion. 0x01 is termination
+	 * error, so we can subtract err & completed to get the real error case.
 	 */
-	stat2 = ((stat2 >> MXS_DMA_CHANNELS) & stat2) | /* (1) */
-		(~(stat2 >> MXS_DMA_CHANNELS) & stat2 & ~stat1); /* (2) */
+	err -= err & completed;
 
-	/* combine error and completion status for checking */
-	stat1 = (stat2 << MXS_DMA_CHANNELS) | stat1;
-	while (stat1) {
-		int channel = fls(stat1) - 1;
-		struct mxs_dma_chan *mxs_chan =
-			&mxs_dma->mxs_chans[channel % MXS_DMA_CHANNELS];
+	mxs_chan = &mxs_dma->mxs_chans[chan];
 
-		if (channel >= MXS_DMA_CHANNELS) {
-			dev_dbg(mxs_dma->dma_device.dev,
-				"%s: error in channel %d\n", __func__,
-				channel - MXS_DMA_CHANNELS);
-			mxs_chan->status = DMA_ERROR;
-			mxs_dma_reset_chan(mxs_chan);
+	if (err) {
+		dev_dbg(mxs_dma->dma_device.dev,
+			"%s: error in channel %d\n", __func__,
+			chan);
+		mxs_chan->status = DMA_ERROR;
+		mxs_dma_reset_chan(mxs_chan);
+	} else if (mxs_chan->status != DMA_COMPLETE) {
+		if (mxs_chan->flags & MXS_DMA_SG_LOOP) {
+			mxs_chan->status = DMA_IN_PROGRESS;
+			if (mxs_chan->flags & MXS_DMA_USE_SEMAPHORE)
+				writel(1, mxs_dma->base +
+					HW_APBHX_CHn_SEMA(mxs_dma, chan));
 		} else {
-			if (mxs_chan->flags & MXS_DMA_SG_LOOP)
-				mxs_chan->status = DMA_IN_PROGRESS;
-			else
-				mxs_chan->status = DMA_SUCCESS;
+			mxs_chan->status = DMA_COMPLETE;
 		}
-
-		stat1 &= ~(1 << channel);
-
-		if (mxs_chan->status == DMA_SUCCESS)
-			dma_cookie_complete(&mxs_chan->desc);
-
-		/* schedule tasklet on this channel */
-		tasklet_schedule(&mxs_chan->tasklet);
 	}
 
+	if (mxs_chan->status == DMA_COMPLETE) {
+		if (mxs_chan->reset)
+			return IRQ_HANDLED;
+		dma_cookie_complete(&mxs_chan->desc);
+	}
+
+	/* schedule tasklet on this channel */
+	tasklet_schedule(&mxs_chan->tasklet);
+
 	return IRQ_HANDLED;
 }
 
@@ -523,6 +603,7 @@
 
 	mxs_chan->status = DMA_IN_PROGRESS;
 	mxs_chan->flags |= MXS_DMA_SG_LOOP;
+	mxs_chan->flags |= MXS_DMA_USE_SEMAPHORE;
 
 	if (num_periods > NUM_CCW) {
 		dev_err(mxs_dma->dma_device.dev,
@@ -554,6 +635,7 @@
 		ccw->bits |= CCW_IRQ;
 		ccw->bits |= CCW_HALT_ON_TERM;
 		ccw->bits |= CCW_TERM_FLUSH;
+		ccw->bits |= CCW_DEC_SEM;
 		ccw->bits |= BF_CCW(direction == DMA_DEV_TO_MEM ?
 				MXS_DMA_CMD_WRITE : MXS_DMA_CMD_READ, COMMAND);
 
@@ -599,8 +681,24 @@
 			dma_cookie_t cookie, struct dma_tx_state *txstate)
 {
 	struct mxs_dma_chan *mxs_chan = to_mxs_dma_chan(chan);
+	struct mxs_dma_engine *mxs_dma = mxs_chan->mxs_dma;
+	u32 residue = 0;
 
-	dma_set_tx_state(txstate, chan->completed_cookie, chan->cookie, 0);
+	if (mxs_chan->status == DMA_IN_PROGRESS &&
+			mxs_chan->flags & MXS_DMA_SG_LOOP) {
+		struct mxs_dma_ccw *last_ccw;
+		u32 bar;
+
+		last_ccw = &mxs_chan->ccw[mxs_chan->desc_count - 1];
+		residue = last_ccw->xfer_bytes + last_ccw->bufaddr;
+
+		bar = readl(mxs_dma->base +
+				HW_APBHX_CHn_BAR(mxs_dma, chan->chan_id));
+		residue -= bar;
+	}
+
+	dma_set_tx_state(txstate, chan->completed_cookie, chan->cookie,
+			residue);
 
 	return mxs_chan->status;
 }
diff --git a/drivers/dma/omap-dma.c b/drivers/dma/omap-dma.c
index ec3fc4f..2f66cf4 100644
--- a/drivers/dma/omap-dma.c
+++ b/drivers/dma/omap-dma.c
@@ -248,7 +248,7 @@
 	unsigned long flags;
 
 	ret = dma_cookie_status(chan, cookie, txstate);
-	if (ret == DMA_SUCCESS || !txstate)
+	if (ret == DMA_COMPLETE || !txstate)
 		return ret;
 
 	spin_lock_irqsave(&c->vc.lock, flags);
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index df8b10f..cdf0483 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -2268,6 +2268,8 @@
 			list_move_tail(&desc->node, &pch->dmac->desc_pool);
 		}
 
+		dma_descriptor_unmap(&desc->txd);
+
 		if (callback) {
 			spin_unlock_irqrestore(&pch->lock, flags);
 			callback(callback_param);
@@ -2314,7 +2316,7 @@
 		return false;
 
 	peri_id = chan->private;
-	return *peri_id == (unsigned)param;
+	return *peri_id == (unsigned long)param;
 }
 EXPORT_SYMBOL(pl330_filter);
 
@@ -2926,16 +2928,23 @@
 
 	amba_set_drvdata(adev, pdmac);
 
-	irq = adev->irq[0];
-	ret = request_irq(irq, pl330_irq_handler, 0,
-			dev_name(&adev->dev), pi);
-	if (ret)
-		return ret;
+	for (i = 0; i < AMBA_NR_IRQS; i++) {
+		irq = adev->irq[i];
+		if (irq) {
+			ret = devm_request_irq(&adev->dev, irq,
+					       pl330_irq_handler, 0,
+					       dev_name(&adev->dev), pi);
+			if (ret)
+				return ret;
+		} else {
+			break;
+		}
+	}
 
 	pi->pcfg.periph_id = adev->periphid;
 	ret = pl330_add(pi);
 	if (ret)
-		goto probe_err1;
+		return ret;
 
 	INIT_LIST_HEAD(&pdmac->desc_pool);
 	spin_lock_init(&pdmac->pool_lock);
@@ -3033,8 +3042,6 @@
 
 	return 0;
 probe_err3:
-	amba_set_drvdata(adev, NULL);
-
 	/* Idle the DMAC */
 	list_for_each_entry_safe(pch, _p, &pdmac->ddma.channels,
 			chan.device_node) {
@@ -3048,8 +3055,6 @@
 	}
 probe_err2:
 	pl330_del(pi);
-probe_err1:
-	free_irq(irq, pi);
 
 	return ret;
 }
@@ -3059,7 +3064,6 @@
 	struct dma_pl330_dmac *pdmac = amba_get_drvdata(adev);
 	struct dma_pl330_chan *pch, *_p;
 	struct pl330_info *pi;
-	int irq;
 
 	if (!pdmac)
 		return 0;
@@ -3068,7 +3072,6 @@
 		of_dma_controller_free(adev->dev.of_node);
 
 	dma_async_device_unregister(&pdmac->ddma);
-	amba_set_drvdata(adev, NULL);
 
 	/* Idle the DMAC */
 	list_for_each_entry_safe(pch, _p, &pdmac->ddma.channels,
@@ -3086,9 +3089,6 @@
 
 	pl330_del(pi);
 
-	irq = adev->irq[0];
-	free_irq(irq, pi);
-
 	return 0;
 }
 
diff --git a/drivers/dma/ppc4xx/adma.c b/drivers/dma/ppc4xx/adma.c
index e24b5ef..8da48c6 100644
--- a/drivers/dma/ppc4xx/adma.c
+++ b/drivers/dma/ppc4xx/adma.c
@@ -804,218 +804,6 @@
 }
 
 /**
- * ppc440spe_desc_get_src_addr - extract the source address from the descriptor
- */
-static u32 ppc440spe_desc_get_src_addr(struct ppc440spe_adma_desc_slot *desc,
-				struct ppc440spe_adma_chan *chan, int src_idx)
-{
-	struct dma_cdb *dma_hw_desc;
-	struct xor_cb *xor_hw_desc;
-
-	switch (chan->device->id) {
-	case PPC440SPE_DMA0_ID:
-	case PPC440SPE_DMA1_ID:
-		dma_hw_desc = desc->hw_desc;
-		/* May have 0, 1, 2, or 3 sources */
-		switch (dma_hw_desc->opc) {
-		case DMA_CDB_OPC_NO_OP:
-		case DMA_CDB_OPC_DFILL128:
-			return 0;
-		case DMA_CDB_OPC_DCHECK128:
-			if (unlikely(src_idx)) {
-				printk(KERN_ERR "%s: try to get %d source for"
-				    " DCHECK128\n", __func__, src_idx);
-				BUG();
-			}
-			return le32_to_cpu(dma_hw_desc->sg1l);
-		case DMA_CDB_OPC_MULTICAST:
-		case DMA_CDB_OPC_MV_SG1_SG2:
-			if (unlikely(src_idx > 2)) {
-				printk(KERN_ERR "%s: try to get %d source from"
-				    " DMA descr\n", __func__, src_idx);
-				BUG();
-			}
-			if (src_idx) {
-				if (le32_to_cpu(dma_hw_desc->sg1u) &
-				    DMA_CUED_XOR_WIN_MSK) {
-					u8 region;
-
-					if (src_idx == 1)
-						return le32_to_cpu(
-						    dma_hw_desc->sg1l) +
-							desc->unmap_len;
-
-					region = (le32_to_cpu(
-					    dma_hw_desc->sg1u)) >>
-						DMA_CUED_REGION_OFF;
-
-					region &= DMA_CUED_REGION_MSK;
-					switch (region) {
-					case DMA_RXOR123:
-						return le32_to_cpu(
-						    dma_hw_desc->sg1l) +
-							(desc->unmap_len << 1);
-					case DMA_RXOR124:
-						return le32_to_cpu(
-						    dma_hw_desc->sg1l) +
-							(desc->unmap_len * 3);
-					case DMA_RXOR125:
-						return le32_to_cpu(
-						    dma_hw_desc->sg1l) +
-							(desc->unmap_len << 2);
-					default:
-						printk(KERN_ERR
-						    "%s: try to"
-						    " get src3 for region %02x"
-						    "PPC440SPE_DESC_RXOR12?\n",
-						    __func__, region);
-						BUG();
-					}
-				} else {
-					printk(KERN_ERR
-						"%s: try to get %d"
-						" source for non-cued descr\n",
-						__func__, src_idx);
-					BUG();
-				}
-			}
-			return le32_to_cpu(dma_hw_desc->sg1l);
-		default:
-			printk(KERN_ERR "%s: unknown OPC 0x%02x\n",
-				__func__, dma_hw_desc->opc);
-			BUG();
-		}
-		return le32_to_cpu(dma_hw_desc->sg1l);
-	case PPC440SPE_XOR_ID:
-		/* May have up to 16 sources */
-		xor_hw_desc = desc->hw_desc;
-		return xor_hw_desc->ops[src_idx].l;
-	}
-	return 0;
-}
-
-/**
- * ppc440spe_desc_get_dest_addr - extract the destination address from the
- * descriptor
- */
-static u32 ppc440spe_desc_get_dest_addr(struct ppc440spe_adma_desc_slot *desc,
-				struct ppc440spe_adma_chan *chan, int idx)
-{
-	struct dma_cdb *dma_hw_desc;
-	struct xor_cb *xor_hw_desc;
-
-	switch (chan->device->id) {
-	case PPC440SPE_DMA0_ID:
-	case PPC440SPE_DMA1_ID:
-		dma_hw_desc = desc->hw_desc;
-
-		if (likely(!idx))
-			return le32_to_cpu(dma_hw_desc->sg2l);
-		return le32_to_cpu(dma_hw_desc->sg3l);
-	case PPC440SPE_XOR_ID:
-		xor_hw_desc = desc->hw_desc;
-		return xor_hw_desc->cbtal;
-	}
-	return 0;
-}
-
-/**
- * ppc440spe_desc_get_src_num - extract the number of source addresses from
- * the descriptor
- */
-static u32 ppc440spe_desc_get_src_num(struct ppc440spe_adma_desc_slot *desc,
-				struct ppc440spe_adma_chan *chan)
-{
-	struct dma_cdb *dma_hw_desc;
-	struct xor_cb *xor_hw_desc;
-
-	switch (chan->device->id) {
-	case PPC440SPE_DMA0_ID:
-	case PPC440SPE_DMA1_ID:
-		dma_hw_desc = desc->hw_desc;
-
-		switch (dma_hw_desc->opc) {
-		case DMA_CDB_OPC_NO_OP:
-		case DMA_CDB_OPC_DFILL128:
-			return 0;
-		case DMA_CDB_OPC_DCHECK128:
-			return 1;
-		case DMA_CDB_OPC_MV_SG1_SG2:
-		case DMA_CDB_OPC_MULTICAST:
-			/*
-			 * Only for RXOR operations we have more than
-			 * one source
-			 */
-			if (le32_to_cpu(dma_hw_desc->sg1u) &
-			    DMA_CUED_XOR_WIN_MSK) {
-				/* RXOR op, there are 2 or 3 sources */
-				if (((le32_to_cpu(dma_hw_desc->sg1u) >>
-				    DMA_CUED_REGION_OFF) &
-				      DMA_CUED_REGION_MSK) == DMA_RXOR12) {
-					/* RXOR 1-2 */
-					return 2;
-				} else {
-					/* RXOR 1-2-3/1-2-4/1-2-5 */
-					return 3;
-				}
-			}
-			return 1;
-		default:
-			printk(KERN_ERR "%s: unknown OPC 0x%02x\n",
-				__func__, dma_hw_desc->opc);
-			BUG();
-		}
-	case PPC440SPE_XOR_ID:
-		/* up to 16 sources */
-		xor_hw_desc = desc->hw_desc;
-		return xor_hw_desc->cbc & XOR_CDCR_OAC_MSK;
-	default:
-		BUG();
-	}
-	return 0;
-}
-
-/**
- * ppc440spe_desc_get_dst_num - get the number of destination addresses in
- * this descriptor
- */
-static u32 ppc440spe_desc_get_dst_num(struct ppc440spe_adma_desc_slot *desc,
-				struct ppc440spe_adma_chan *chan)
-{
-	struct dma_cdb *dma_hw_desc;
-
-	switch (chan->device->id) {
-	case PPC440SPE_DMA0_ID:
-	case PPC440SPE_DMA1_ID:
-		/* May be 1 or 2 destinations */
-		dma_hw_desc = desc->hw_desc;
-		switch (dma_hw_desc->opc) {
-		case DMA_CDB_OPC_NO_OP:
-		case DMA_CDB_OPC_DCHECK128:
-			return 0;
-		case DMA_CDB_OPC_MV_SG1_SG2:
-		case DMA_CDB_OPC_DFILL128:
-			return 1;
-		case DMA_CDB_OPC_MULTICAST:
-			if (desc->dst_cnt == 2)
-				return 2;
-			else
-				return 1;
-		default:
-			printk(KERN_ERR "%s: unknown OPC 0x%02x\n",
-				__func__, dma_hw_desc->opc);
-			BUG();
-		}
-	case PPC440SPE_XOR_ID:
-		/* Always only 1 destination */
-		return 1;
-	default:
-		BUG();
-	}
-	return 0;
-}
-
-/**
  * ppc440spe_desc_get_link - get the address of the descriptor that
  * follows this one
  */
@@ -1707,43 +1495,6 @@
 	}
 }
 
-static void ppc440spe_adma_unmap(struct ppc440spe_adma_chan *chan,
-				 struct ppc440spe_adma_desc_slot *desc)
-{
-	u32 src_cnt, dst_cnt;
-	dma_addr_t addr;
-
-	/*
-	 * get the number of sources & destination
-	 * included in this descriptor and unmap
-	 * them all
-	 */
-	src_cnt = ppc440spe_desc_get_src_num(desc, chan);
-	dst_cnt = ppc440spe_desc_get_dst_num(desc, chan);
-
-	/* unmap destinations */
-	if (!(desc->async_tx.flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
-		while (dst_cnt--) {
-			addr = ppc440spe_desc_get_dest_addr(
-				desc, chan, dst_cnt);
-			dma_unmap_page(chan->device->dev,
-					addr, desc->unmap_len,
-					DMA_FROM_DEVICE);
-		}
-	}
-
-	/* unmap sources */
-	if (!(desc->async_tx.flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-		while (src_cnt--) {
-			addr = ppc440spe_desc_get_src_addr(
-				desc, chan, src_cnt);
-			dma_unmap_page(chan->device->dev,
-					addr, desc->unmap_len,
-					DMA_TO_DEVICE);
-		}
-	}
-}
-
 /**
  * ppc440spe_adma_run_tx_complete_actions - call functions to be called
  * upon completion
@@ -1767,26 +1518,7 @@
 			desc->async_tx.callback(
 				desc->async_tx.callback_param);
 
-		/* unmap dma addresses
-		 * (unmap_single vs unmap_page?)
-		 *
-		 * actually, ppc's dma_unmap_page() functions are empty, so
-		 * the following code is just for the sake of completeness
-		 */
-		if (chan && chan->needs_unmap && desc->group_head &&
-		     desc->unmap_len) {
-			struct ppc440spe_adma_desc_slot *unmap =
-							desc->group_head;
-			/* assume 1 slot per op always */
-			u32 slot_count = unmap->slot_cnt;
-
-			/* Run through the group list and unmap addresses */
-			for (i = 0; i < slot_count; i++) {
-				BUG_ON(!unmap);
-				ppc440spe_adma_unmap(chan, unmap);
-				unmap = unmap->hw_next;
-			}
-		}
+		dma_descriptor_unmap(&desc->async_tx);
 	}
 
 	/* run dependent operations */
@@ -3893,7 +3625,7 @@
 
 	ppc440spe_chan = to_ppc440spe_adma_chan(chan);
 	ret = dma_cookie_status(chan, cookie, txstate);
-	if (ret == DMA_SUCCESS)
+	if (ret == DMA_COMPLETE)
 		return ret;
 
 	ppc440spe_adma_slot_cleanup(ppc440spe_chan);
diff --git a/drivers/dma/sa11x0-dma.c b/drivers/dma/sa11x0-dma.c
index 461a91a..ab26d46 100644
--- a/drivers/dma/sa11x0-dma.c
+++ b/drivers/dma/sa11x0-dma.c
@@ -436,7 +436,7 @@
 	enum dma_status ret;
 
 	ret = dma_cookie_status(&c->vc.chan, cookie, state);
-	if (ret == DMA_SUCCESS)
+	if (ret == DMA_COMPLETE)
 		return ret;
 
 	if (!state)
diff --git a/drivers/dma/sh/shdma-base.c b/drivers/dma/sh/shdma-base.c
index d94ab59..2e7b394 100644
--- a/drivers/dma/sh/shdma-base.c
+++ b/drivers/dma/sh/shdma-base.c
@@ -724,7 +724,7 @@
 	 * If we don't find cookie on the queue, it has been aborted and we have
 	 * to report error
 	 */
-	if (status != DMA_SUCCESS) {
+	if (status != DMA_COMPLETE) {
 		struct shdma_desc *sdesc;
 		status = DMA_ERROR;
 		list_for_each_entry(sdesc, &schan->ld_queue, node)
diff --git a/drivers/dma/sh/shdmac.c b/drivers/dma/sh/shdmac.c
index 1069e88..0d765c0 100644
--- a/drivers/dma/sh/shdmac.c
+++ b/drivers/dma/sh/shdmac.c
@@ -685,7 +685,7 @@
 static int sh_dmae_probe(struct platform_device *pdev)
 {
 	const struct sh_dmae_pdata *pdata;
-	unsigned long irqflags = IRQF_DISABLED,
+	unsigned long irqflags = 0,
 		chan_flag[SH_DMAE_MAX_CHANNELS] = {};
 	int errirq, chan_irq[SH_DMAE_MAX_CHANNELS];
 	int err, i, irq_cnt = 0, irqres = 0, irq_cap = 0;
@@ -838,7 +838,7 @@
 				    IORESOURCE_IRQ_SHAREABLE)
 					chan_flag[irq_cnt] = IRQF_SHARED;
 				else
-					chan_flag[irq_cnt] = IRQF_DISABLED;
+					chan_flag[irq_cnt] = 0;
 				dev_dbg(&pdev->dev,
 					"Found IRQ %d for channel %d\n",
 					i, irq_cnt);
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index 82d2b97..b8c031b 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -14,6 +14,7 @@
 #include <linux/platform_device.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
+#include <linux/log2.h>
 #include <linux/pm.h>
 #include <linux/pm_runtime.h>
 #include <linux/err.h>
@@ -2626,7 +2627,7 @@
 	}
 
 	ret = dma_cookie_status(chan, cookie, txstate);
-	if (ret != DMA_SUCCESS)
+	if (ret != DMA_COMPLETE)
 		dma_set_residue(txstate, stedma40_residue(chan));
 
 	if (d40_is_paused(d40c))
@@ -2796,8 +2797,8 @@
 	    src_addr_width >  DMA_SLAVE_BUSWIDTH_8_BYTES   ||
 	    dst_addr_width <= DMA_SLAVE_BUSWIDTH_UNDEFINED ||
 	    dst_addr_width >  DMA_SLAVE_BUSWIDTH_8_BYTES   ||
-	    ((src_addr_width > 1) && (src_addr_width & 1)) ||
-	    ((dst_addr_width > 1) && (dst_addr_width & 1)))
+	    !is_power_of_2(src_addr_width) ||
+	    !is_power_of_2(dst_addr_width))
 		return -EINVAL;
 
 	cfg->src_info.data_width = src_addr_width;
diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c
index 5d4986e..73654e3 100644
--- a/drivers/dma/tegra20-apb-dma.c
+++ b/drivers/dma/tegra20-apb-dma.c
@@ -570,7 +570,7 @@
 
 	list_del(&sgreq->node);
 	if (sgreq->last_sg) {
-		dma_desc->dma_status = DMA_SUCCESS;
+		dma_desc->dma_status = DMA_COMPLETE;
 		dma_cookie_complete(&dma_desc->txd);
 		if (!dma_desc->cb_count)
 			list_add_tail(&dma_desc->cb_node, &tdc->cb_desc);
@@ -768,7 +768,7 @@
 	unsigned int residual;
 
 	ret = dma_cookie_status(dc, cookie, txstate);
-	if (ret == DMA_SUCCESS)
+	if (ret == DMA_COMPLETE)
 		return ret;
 
 	spin_lock_irqsave(&tdc->lock, flags);
@@ -1018,7 +1018,7 @@
 	return &dma_desc->txd;
 }
 
-struct dma_async_tx_descriptor *tegra_dma_prep_dma_cyclic(
+static struct dma_async_tx_descriptor *tegra_dma_prep_dma_cyclic(
 	struct dma_chan *dc, dma_addr_t buf_addr, size_t buf_len,
 	size_t period_len, enum dma_transfer_direction direction,
 	unsigned long flags, void *context)
diff --git a/drivers/dma/timb_dma.c b/drivers/dma/timb_dma.c
index 28af214..4506a7b 100644
--- a/drivers/dma/timb_dma.c
+++ b/drivers/dma/timb_dma.c
@@ -154,38 +154,6 @@
 	return done;
 }
 
-static void __td_unmap_desc(struct timb_dma_chan *td_chan, const u8 *dma_desc,
-	bool single)
-{
-	dma_addr_t addr;
-	int len;
-
-	addr = (dma_desc[7] << 24) | (dma_desc[6] << 16) | (dma_desc[5] << 8) |
-		dma_desc[4];
-
-	len = (dma_desc[3] << 8) | dma_desc[2];
-
-	if (single)
-		dma_unmap_single(chan2dev(&td_chan->chan), addr, len,
-			DMA_TO_DEVICE);
-	else
-		dma_unmap_page(chan2dev(&td_chan->chan), addr, len,
-			DMA_TO_DEVICE);
-}
-
-static void __td_unmap_descs(struct timb_dma_desc *td_desc, bool single)
-{
-	struct timb_dma_chan *td_chan = container_of(td_desc->txd.chan,
-		struct timb_dma_chan, chan);
-	u8 *descs;
-
-	for (descs = td_desc->desc_list; ; descs += TIMB_DMA_DESC_SIZE) {
-		__td_unmap_desc(td_chan, descs, single);
-		if (descs[0] & 0x02)
-			break;
-	}
-}
-
 static int td_fill_desc(struct timb_dma_chan *td_chan, u8 *dma_desc,
 	struct scatterlist *sg, bool last)
 {
@@ -293,10 +261,7 @@
 
 	list_move(&td_desc->desc_node, &td_chan->free_list);
 
-	if (!(txd->flags & DMA_COMPL_SKIP_SRC_UNMAP))
-		__td_unmap_descs(td_desc,
-			txd->flags & DMA_COMPL_SRC_UNMAP_SINGLE);
-
+	dma_descriptor_unmap(txd);
 	/*
 	 * The API requires that no submissions are done from a
 	 * callback, so we don't need to drop the lock here
diff --git a/drivers/dma/txx9dmac.c b/drivers/dma/txx9dmac.c
index 71e8e77..bae6c29 100644
--- a/drivers/dma/txx9dmac.c
+++ b/drivers/dma/txx9dmac.c
@@ -419,30 +419,7 @@
 	list_splice_init(&desc->tx_list, &dc->free_list);
 	list_move(&desc->desc_node, &dc->free_list);
 
-	if (!ds) {
-		dma_addr_t dmaaddr;
-		if (!(txd->flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
-			dmaaddr = is_dmac64(dc) ?
-				desc->hwdesc.DAR : desc->hwdesc32.DAR;
-			if (txd->flags & DMA_COMPL_DEST_UNMAP_SINGLE)
-				dma_unmap_single(chan2parent(&dc->chan),
-					dmaaddr, desc->len, DMA_FROM_DEVICE);
-			else
-				dma_unmap_page(chan2parent(&dc->chan),
-					dmaaddr, desc->len, DMA_FROM_DEVICE);
-		}
-		if (!(txd->flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-			dmaaddr = is_dmac64(dc) ?
-				desc->hwdesc.SAR : desc->hwdesc32.SAR;
-			if (txd->flags & DMA_COMPL_SRC_UNMAP_SINGLE)
-				dma_unmap_single(chan2parent(&dc->chan),
-					dmaaddr, desc->len, DMA_TO_DEVICE);
-			else
-				dma_unmap_page(chan2parent(&dc->chan),
-					dmaaddr, desc->len, DMA_TO_DEVICE);
-		}
-	}
-
+	dma_descriptor_unmap(txd);
 	/*
 	 * The API requires that no submissions are done from a
 	 * callback, so we don't need to drop the lock here
@@ -962,8 +939,8 @@
 	enum dma_status ret;
 
 	ret = dma_cookie_status(chan, cookie, txstate);
-	if (ret == DMA_SUCCESS)
-		return DMA_SUCCESS;
+	if (ret == DMA_COMPLETE)
+		return DMA_COMPLETE;
 
 	spin_lock_bh(&dc->lock);
 	txx9dmac_scan_descriptors(dc);
diff --git a/drivers/media/platform/m2m-deinterlace.c b/drivers/media/platform/m2m-deinterlace.c
index 36513e8..65cab70 100644
--- a/drivers/media/platform/m2m-deinterlace.c
+++ b/drivers/media/platform/m2m-deinterlace.c
@@ -341,8 +341,7 @@
 	ctx->xt->dir = DMA_MEM_TO_MEM;
 	ctx->xt->src_sgl = false;
 	ctx->xt->dst_sgl = true;
-	flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT |
-		DMA_COMPL_SKIP_DEST_UNMAP | DMA_COMPL_SKIP_SRC_UNMAP;
+	flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT;
 
 	tx = dmadev->device_prep_interleaved_dma(chan, ctx->xt, flags);
 	if (tx == NULL) {
diff --git a/drivers/media/platform/timblogiw.c b/drivers/media/platform/timblogiw.c
index 6a74ce0..ccdadd6 100644
--- a/drivers/media/platform/timblogiw.c
+++ b/drivers/media/platform/timblogiw.c
@@ -565,7 +565,7 @@
 
 	desc = dmaengine_prep_slave_sg(fh->chan,
 		buf->sg, sg_elems, DMA_DEV_TO_MEM,
-		DMA_PREP_INTERRUPT | DMA_COMPL_SKIP_SRC_UNMAP);
+		DMA_PREP_INTERRUPT);
 	if (!desc) {
 		spin_lock_irq(&fh->queue_lock);
 		list_del_init(&vb->queue);
diff --git a/drivers/misc/carma/carma-fpga.c b/drivers/misc/carma/carma-fpga.c
index 08b18f3..9e2b985 100644
--- a/drivers/misc/carma/carma-fpga.c
+++ b/drivers/misc/carma/carma-fpga.c
@@ -633,8 +633,7 @@
 	struct dma_async_tx_descriptor *tx;
 	dma_cookie_t cookie;
 	dma_addr_t dst, src;
-	unsigned long dma_flags = DMA_COMPL_SKIP_DEST_UNMAP |
-				  DMA_COMPL_SKIP_SRC_UNMAP;
+	unsigned long dma_flags = 0;
 
 	dst_sg = buf->vb.sglist;
 	dst_nents = buf->vb.sglen;
diff --git a/drivers/mtd/nand/atmel_nand.c b/drivers/mtd/nand/atmel_nand.c
index d78a97d..59f08c4 100644
--- a/drivers/mtd/nand/atmel_nand.c
+++ b/drivers/mtd/nand/atmel_nand.c
@@ -375,8 +375,7 @@
 
 	dma_dev = host->dma_chan->device;
 
-	flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT | DMA_COMPL_SKIP_SRC_UNMAP |
-		DMA_COMPL_SKIP_DEST_UNMAP;
+	flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT;
 
 	phys_addr = dma_map_single(dma_dev->dev, p, len, dir);
 	if (dma_mapping_error(dma_dev->dev, phys_addr)) {
diff --git a/drivers/mtd/nand/fsmc_nand.c b/drivers/mtd/nand/fsmc_nand.c
index 3dc1a75..8b27522 100644
--- a/drivers/mtd/nand/fsmc_nand.c
+++ b/drivers/mtd/nand/fsmc_nand.c
@@ -573,8 +573,6 @@
 	dma_dev = chan->device;
 	dma_addr = dma_map_single(dma_dev->dev, buffer, len, direction);
 
-	flags |= DMA_COMPL_SKIP_SRC_UNMAP | DMA_COMPL_SKIP_DEST_UNMAP;
-
 	if (direction == DMA_TO_DEVICE) {
 		dma_src = dma_addr;
 		dma_dst = host->data_pa;
diff --git a/drivers/net/ethernet/micrel/ks8842.c b/drivers/net/ethernet/micrel/ks8842.c
index 0951f7a..822616e 100644
--- a/drivers/net/ethernet/micrel/ks8842.c
+++ b/drivers/net/ethernet/micrel/ks8842.c
@@ -459,8 +459,7 @@
 		sg_dma_len(&ctl->sg) += 4 - sg_dma_len(&ctl->sg) % 4;
 
 	ctl->adesc = dmaengine_prep_slave_sg(ctl->chan,
-		&ctl->sg, 1, DMA_MEM_TO_DEV,
-		DMA_PREP_INTERRUPT | DMA_COMPL_SKIP_SRC_UNMAP);
+		&ctl->sg, 1, DMA_MEM_TO_DEV, DMA_PREP_INTERRUPT);
 	if (!ctl->adesc)
 		return NETDEV_TX_BUSY;
 
@@ -571,8 +570,7 @@
 		sg_dma_len(sg) = DMA_BUFFER_SIZE;
 
 		ctl->adesc = dmaengine_prep_slave_sg(ctl->chan,
-			sg, 1, DMA_DEV_TO_MEM,
-			DMA_PREP_INTERRUPT | DMA_COMPL_SKIP_SRC_UNMAP);
+			sg, 1, DMA_DEV_TO_MEM, DMA_PREP_INTERRUPT);
 
 		if (!ctl->adesc)
 			goto out;
diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
index 12a9e83..d0222f1 100644
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -1034,10 +1034,9 @@
 	struct dma_chan *chan = qp->dma_chan;
 	struct dma_device *device;
 	size_t pay_off, buff_off;
-	dma_addr_t src, dest;
+	struct dmaengine_unmap_data *unmap;
 	dma_cookie_t cookie;
 	void *buf = entry->buf;
-	unsigned long flags;
 
 	entry->len = len;
 
@@ -1045,35 +1044,49 @@
 		goto err;
 
 	if (len < copy_bytes) 
-		goto err1;
+		goto err_wait;
 
 	device = chan->device;
 	pay_off = (size_t) offset & ~PAGE_MASK;
 	buff_off = (size_t) buf & ~PAGE_MASK;
 
 	if (!is_dma_copy_aligned(device, pay_off, buff_off, len))
-		goto err1;
+		goto err_wait;
 
-	dest = dma_map_single(device->dev, buf, len, DMA_FROM_DEVICE);
-	if (dma_mapping_error(device->dev, dest))
-		goto err1;
+	unmap = dmaengine_get_unmap_data(device->dev, 2, GFP_NOWAIT);
+	if (!unmap)
+		goto err_wait;
 
-	src = dma_map_single(device->dev, offset, len, DMA_TO_DEVICE);
-	if (dma_mapping_error(device->dev, src))
-		goto err2;
+	unmap->len = len;
+	unmap->addr[0] = dma_map_page(device->dev, virt_to_page(offset),
+				      pay_off, len, DMA_TO_DEVICE);
+	if (dma_mapping_error(device->dev, unmap->addr[0]))
+		goto err_get_unmap;
 
-	flags = DMA_COMPL_DEST_UNMAP_SINGLE | DMA_COMPL_SRC_UNMAP_SINGLE |
-		DMA_PREP_INTERRUPT;
-	txd = device->device_prep_dma_memcpy(chan, dest, src, len, flags);
+	unmap->to_cnt = 1;
+
+	unmap->addr[1] = dma_map_page(device->dev, virt_to_page(buf),
+				      buff_off, len, DMA_FROM_DEVICE);
+	if (dma_mapping_error(device->dev, unmap->addr[1]))
+		goto err_get_unmap;
+
+	unmap->from_cnt = 1;
+
+	txd = device->device_prep_dma_memcpy(chan, unmap->addr[1],
+					     unmap->addr[0], len,
+					     DMA_PREP_INTERRUPT);
 	if (!txd)
-		goto err3;
+		goto err_get_unmap;
 
 	txd->callback = ntb_rx_copy_callback;
 	txd->callback_param = entry;
+	dma_set_unmap(txd, unmap);
 
 	cookie = dmaengine_submit(txd);
 	if (dma_submit_error(cookie))
-		goto err3;
+		goto err_set_unmap;
+
+	dmaengine_unmap_put(unmap);
 
 	qp->last_cookie = cookie;
 
@@ -1081,11 +1094,11 @@
 
 	return;
 
-err3:
-	dma_unmap_single(device->dev, src, len, DMA_TO_DEVICE);
-err2:
-	dma_unmap_single(device->dev, dest, len, DMA_FROM_DEVICE);
-err1:
+err_set_unmap:
+	dmaengine_unmap_put(unmap);
+err_get_unmap:
+	dmaengine_unmap_put(unmap);
+err_wait:
 	/* If the callbacks come out of order, the writing of the index to the
 	 * last completed will be out of order.  This may result in the
 	 * receive stalling forever.
@@ -1245,12 +1258,12 @@
 	struct dma_chan *chan = qp->dma_chan;
 	struct dma_device *device;
 	size_t dest_off, buff_off;
-	dma_addr_t src, dest;
+	struct dmaengine_unmap_data *unmap;
+	dma_addr_t dest;
 	dma_cookie_t cookie;
 	void __iomem *offset;
 	size_t len = entry->len;
 	void *buf = entry->buf;
-	unsigned long flags;
 
 	offset = qp->tx_mw + qp->tx_max_frame * qp->tx_index;
 	hdr = offset + qp->tx_max_frame - sizeof(struct ntb_payload_header);
@@ -1273,28 +1286,41 @@
 	if (!is_dma_copy_aligned(device, buff_off, dest_off, len))
 		goto err;
 
-	src = dma_map_single(device->dev, buf, len, DMA_TO_DEVICE);
-	if (dma_mapping_error(device->dev, src))
+	unmap = dmaengine_get_unmap_data(device->dev, 1, GFP_NOWAIT);
+	if (!unmap)
 		goto err;
 
-	flags = DMA_COMPL_SRC_UNMAP_SINGLE | DMA_PREP_INTERRUPT;
-	txd = device->device_prep_dma_memcpy(chan, dest, src, len, flags);
+	unmap->len = len;
+	unmap->addr[0] = dma_map_page(device->dev, virt_to_page(buf),
+				      buff_off, len, DMA_TO_DEVICE);
+	if (dma_mapping_error(device->dev, unmap->addr[0]))
+		goto err_get_unmap;
+
+	unmap->to_cnt = 1;
+
+	txd = device->device_prep_dma_memcpy(chan, dest, unmap->addr[0], len,
+					     DMA_PREP_INTERRUPT);
 	if (!txd)
-		goto err1;
+		goto err_get_unmap;
 
 	txd->callback = ntb_tx_copy_callback;
 	txd->callback_param = entry;
+	dma_set_unmap(txd, unmap);
 
 	cookie = dmaengine_submit(txd);
 	if (dma_submit_error(cookie))
-		goto err1;
+		goto err_set_unmap;
+
+	dmaengine_unmap_put(unmap);
 
 	dma_async_issue_pending(chan);
 	qp->tx_async++;
 
 	return;
-err1:
-	dma_unmap_single(device->dev, src, len, DMA_TO_DEVICE);
+err_set_unmap:
+	dmaengine_unmap_put(unmap);
+err_get_unmap:
+	dmaengine_unmap_put(unmap);
 err:
 	ntb_memcpy_tx(entry, offset);
 	qp->tx_memcpy++;
diff --git a/drivers/spi/spi-dw-mid.c b/drivers/spi/spi-dw-mid.c
index b9f0192..6d207af 100644
--- a/drivers/spi/spi-dw-mid.c
+++ b/drivers/spi/spi-dw-mid.c
@@ -150,7 +150,7 @@
 				&dws->tx_sgl,
 				1,
 				DMA_MEM_TO_DEV,
-				DMA_PREP_INTERRUPT | DMA_COMPL_SKIP_DEST_UNMAP);
+				DMA_PREP_INTERRUPT);
 	txdesc->callback = dw_spi_dma_done;
 	txdesc->callback_param = dws;
 
@@ -173,7 +173,7 @@
 				&dws->rx_sgl,
 				1,
 				DMA_DEV_TO_MEM,
-				DMA_PREP_INTERRUPT | DMA_COMPL_SKIP_DEST_UNMAP);
+				DMA_PREP_INTERRUPT);
 	rxdesc->callback = dw_spi_dma_done;
 	rxdesc->callback_param = dws;
 
diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c
index 5377502..7d8103c 100644
--- a/drivers/tty/serial/sh-sci.c
+++ b/drivers/tty/serial/sh-sci.c
@@ -1433,7 +1433,7 @@
 	desc = s->desc_rx[new];
 
 	if (dma_async_is_tx_complete(s->chan_rx, s->active_rx, NULL, NULL) !=
-	    DMA_SUCCESS) {
+	    DMA_COMPLETE) {
 		/* Handle incomplete DMA receive */
 		struct dma_chan *chan = s->chan_rx;
 		struct shdma_desc *sh_desc = container_of(desc,
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 0bc7275..41cf0c3 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -45,13 +45,13 @@
 
 /**
  * enum dma_status - DMA transaction status
- * @DMA_SUCCESS: transaction completed successfully
+ * @DMA_COMPLETE: transaction completed
  * @DMA_IN_PROGRESS: transaction not yet processed
  * @DMA_PAUSED: transaction is paused
  * @DMA_ERROR: transaction failed
  */
 enum dma_status {
-	DMA_SUCCESS,
+	DMA_COMPLETE,
 	DMA_IN_PROGRESS,
 	DMA_PAUSED,
 	DMA_ERROR,
@@ -171,12 +171,6 @@
  * @DMA_CTRL_ACK - if clear, the descriptor cannot be reused until the client
  *  acknowledges receipt, i.e. has has a chance to establish any dependency
  *  chains
- * @DMA_COMPL_SKIP_SRC_UNMAP - set to disable dma-unmapping the source buffer(s)
- * @DMA_COMPL_SKIP_DEST_UNMAP - set to disable dma-unmapping the destination(s)
- * @DMA_COMPL_SRC_UNMAP_SINGLE - set to do the source dma-unmapping as single
- * 	(if not set, do the source dma-unmapping as page)
- * @DMA_COMPL_DEST_UNMAP_SINGLE - set to do the destination dma-unmapping as single
- * 	(if not set, do the destination dma-unmapping as page)
  * @DMA_PREP_PQ_DISABLE_P - prevent generation of P while generating Q
  * @DMA_PREP_PQ_DISABLE_Q - prevent generation of Q while generating P
  * @DMA_PREP_CONTINUE - indicate to a driver that it is reusing buffers as
@@ -188,14 +182,10 @@
 enum dma_ctrl_flags {
 	DMA_PREP_INTERRUPT = (1 << 0),
 	DMA_CTRL_ACK = (1 << 1),
-	DMA_COMPL_SKIP_SRC_UNMAP = (1 << 2),
-	DMA_COMPL_SKIP_DEST_UNMAP = (1 << 3),
-	DMA_COMPL_SRC_UNMAP_SINGLE = (1 << 4),
-	DMA_COMPL_DEST_UNMAP_SINGLE = (1 << 5),
-	DMA_PREP_PQ_DISABLE_P = (1 << 6),
-	DMA_PREP_PQ_DISABLE_Q = (1 << 7),
-	DMA_PREP_CONTINUE = (1 << 8),
-	DMA_PREP_FENCE = (1 << 9),
+	DMA_PREP_PQ_DISABLE_P = (1 << 2),
+	DMA_PREP_PQ_DISABLE_Q = (1 << 3),
+	DMA_PREP_CONTINUE = (1 << 4),
+	DMA_PREP_FENCE = (1 << 5),
 };
 
 /**
@@ -413,6 +403,17 @@
 typedef bool (*dma_filter_fn)(struct dma_chan *chan, void *filter_param);
 
 typedef void (*dma_async_tx_callback)(void *dma_async_param);
+
+struct dmaengine_unmap_data {
+	u8 to_cnt;
+	u8 from_cnt;
+	u8 bidi_cnt;
+	struct device *dev;
+	struct kref kref;
+	size_t len;
+	dma_addr_t addr[0];
+};
+
 /**
  * struct dma_async_tx_descriptor - async transaction descriptor
  * ---dma generic offload fields---
@@ -438,6 +439,7 @@
 	dma_cookie_t (*tx_submit)(struct dma_async_tx_descriptor *tx);
 	dma_async_tx_callback callback;
 	void *callback_param;
+	struct dmaengine_unmap_data *unmap;
 #ifdef CONFIG_ASYNC_TX_ENABLE_CHANNEL_SWITCH
 	struct dma_async_tx_descriptor *next;
 	struct dma_async_tx_descriptor *parent;
@@ -445,6 +447,40 @@
 #endif
 };
 
+#ifdef CONFIG_DMA_ENGINE
+static inline void dma_set_unmap(struct dma_async_tx_descriptor *tx,
+				 struct dmaengine_unmap_data *unmap)
+{
+	kref_get(&unmap->kref);
+	tx->unmap = unmap;
+}
+
+struct dmaengine_unmap_data *
+dmaengine_get_unmap_data(struct device *dev, int nr, gfp_t flags);
+void dmaengine_unmap_put(struct dmaengine_unmap_data *unmap);
+#else
+static inline void dma_set_unmap(struct dma_async_tx_descriptor *tx,
+				 struct dmaengine_unmap_data *unmap)
+{
+}
+static inline struct dmaengine_unmap_data *
+dmaengine_get_unmap_data(struct device *dev, int nr, gfp_t flags)
+{
+	return NULL;
+}
+static inline void dmaengine_unmap_put(struct dmaengine_unmap_data *unmap)
+{
+}
+#endif
+
+static inline void dma_descriptor_unmap(struct dma_async_tx_descriptor *tx)
+{
+	if (tx->unmap) {
+		dmaengine_unmap_put(tx->unmap);
+		tx->unmap = NULL;
+	}
+}
+
 #ifndef CONFIG_ASYNC_TX_ENABLE_CHANNEL_SWITCH
 static inline void txd_lock(struct dma_async_tx_descriptor *txd)
 {
@@ -979,10 +1015,10 @@
 {
 	if (last_complete <= last_used) {
 		if ((cookie <= last_complete) || (cookie > last_used))
-			return DMA_SUCCESS;
+			return DMA_COMPLETE;
 	} else {
 		if ((cookie <= last_complete) && (cookie > last_used))
-			return DMA_SUCCESS;
+			return DMA_COMPLETE;
 	}
 	return DMA_IN_PROGRESS;
 }
@@ -1013,11 +1049,11 @@
 }
 static inline enum dma_status dma_sync_wait(struct dma_chan *chan, dma_cookie_t cookie)
 {
-	return DMA_SUCCESS;
+	return DMA_COMPLETE;
 }
 static inline enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx)
 {
-	return DMA_SUCCESS;
+	return DMA_COMPLETE;
 }
 static inline void dma_issue_pending_all(void)
 {
diff --git a/include/linux/platform_data/edma.h b/include/linux/platform_data/edma.h
index 179fb91b..f50821c 100644
--- a/include/linux/platform_data/edma.h
+++ b/include/linux/platform_data/edma.h
@@ -67,10 +67,10 @@
 #define ITCCHEN		BIT(23)
 
 /*ch_status paramater of callback function possible values*/
-#define DMA_COMPLETE 1
-#define DMA_CC_ERROR 2
-#define DMA_TC1_ERROR 3
-#define DMA_TC2_ERROR 4
+#define EDMA_DMA_COMPLETE 1
+#define EDMA_DMA_CC_ERROR 2
+#define EDMA_DMA_TC1_ERROR 3
+#define EDMA_DMA_TC2_ERROR 4
 
 enum address_mode {
 	INCR = 0,
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 3dc0c6c..c4638e6 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1425,7 +1425,7 @@
 	do {
 		if (dma_async_is_tx_complete(tp->ucopy.dma_chan,
 					      last_issued, &done,
-					      &used) == DMA_SUCCESS) {
+					      &used) == DMA_COMPLETE) {
 			/* Safe to free early-copied skbs now */
 			__skb_queue_purge(&sk->sk_async_wait_queue);
 			break;
@@ -1433,7 +1433,7 @@
 			struct sk_buff *skb;
 			while ((skb = skb_peek(&sk->sk_async_wait_queue)) &&
 			       (dma_async_is_complete(skb->dma_cookie, done,
-						      used) == DMA_SUCCESS)) {
+						      used) == DMA_COMPLETE)) {
 				__skb_dequeue(&sk->sk_async_wait_queue);
 				kfree_skb(skb);
 			}
diff --git a/sound/soc/davinci/davinci-pcm.c b/sound/soc/davinci/davinci-pcm.c
index fa64cd8..fb5d107f 100644
--- a/sound/soc/davinci/davinci-pcm.c
+++ b/sound/soc/davinci/davinci-pcm.c
@@ -238,7 +238,7 @@
 	print_buf_info(prtd->ram_channel, "i ram_channel");
 	pr_debug("davinci_pcm: link=%d, status=0x%x\n", link, ch_status);
 
-	if (unlikely(ch_status != DMA_COMPLETE))
+	if (unlikely(ch_status != EDMA_DMA_COMPLETE))
 		return;
 
 	if (snd_pcm_running(substream)) {