Merge tag 'dmaengine-4.5-rc1' of git://git.infradead.org/users/vkoul/slave-dma

Pull dmaengine updates from Vinod Koul:
 "This round we have few new features, new driver and updates to few
  drivers.

  The new features to dmaengine core are:
   - Synchronized transfer termination API to terminate the dmaengine
     transfers in synchronized and async fashion as required by users.
     We have its user now in ALSA dmaengine lib, img, at_xdma, axi_dmac
     drivers.
   - Universal API for channel request and start consolidation of
     request flows.  It's user is ompa-dma driver.
   - Introduce reuse of descriptors and use in pxa_dma driver

  Add/Remove:
   - New STM32 DMA driver
   - Removal of unused R-Car HPB-DMAC driver

  Updates:
   - ti-dma-crossbar updates for supporting eDMA
   - tegra-apb pm updates
   - idma64
   - mv_xor updates
   - ste_dma updates"

* tag 'dmaengine-4.5-rc1' of git://git.infradead.org/users/vkoul/slave-dma: (54 commits)
  dmaengine: mv_xor: add suspend/resume support
  dmaengine: mv_xor: de-duplicate mv_chan_set_mode*()
  dmaengine: mv_xor: remove mv_xor_chan->current_type field
  dmaengine: omap-dma: Add support for DMA filter mapping to slave devices
  dmaengine: edma: Add support for DMA filter mapping to slave devices
  dmaengine: core: Introduce new, universal API to request a channel
  dmaengine: core: Move and merge the code paths using private_candidate
  dmaengine: core: Skip mask matching when it is not provided to private_candidate
  dmaengine: mdc: Correct terminate_all handling
  dmaengine: edma: Add probe callback to edma_tptc_driver
  dmaengine: dw: fix potential memory leak in dw_dma_parse_dt()
  dmaengine: stm32-dma: Fix unchecked deference of chan->desc
  dmaengine: sh: Remove unused R-Car HPB-DMAC driver
  dmaengine: usb-dmac: Document SoC specific compatibility strings
  ste_dma40: Delete an unnecessary variable initialisation in d40_probe()
  ste_dma40: Delete another unnecessary check in d40_probe()
  ste_dma40: Delete an unnecessary check before the function call "kmem_cache_destroy"
  dmaengine: tegra-apb: Free interrupts before killing tasklets
  dmaengine: tegra-apb: Update driver to use GFP_NOWAIT
  dmaengine: tegra-apb: Only save channel state for those in use
  ...

Documentation/devicetree/bindings/dma/renesas,usb-dmac.txt

 * Renesas USB DMA Controller Device Tree bindings
 
 Required Properties:
-- compatible: must contain "renesas,usb-dmac"
+-compatible: "renesas,<soctype>-usb-dmac", "renesas,usb-dmac" as fallback.
+	Examples with soctypes are:
+	  - "renesas,r8a7790-usb-dmac" (R-Car H2)
+	  - "renesas,r8a7791-usb-dmac" (R-Car M2-W)
+	  - "renesas,r8a7793-usb-dmac" (R-Car M2-N)
+	  - "renesas,r8a7794-usb-dmac" (R-Car E2)
+	  - "renesas,r8a7795-usb-dmac" (R-Car H3)
 - reg: base address and length of the registers block for the DMAC
 - interrupts: interrupt specifiers for the DMAC, one for each entry in
   interrupt-names.
@@ -15,7 +21,7 @@ Required Properties:
 Example: R8A7790 (R-Car H2) USB-DMACs
 
 	usb_dmac0: dma-controller@e65a0000 {
-		compatible = "renesas,usb-dmac";
+		compatible = "renesas,r8a7790-usb-dmac", "renesas,usb-dmac";
 		reg = <0 0xe65a0000 0 0x100>;
 		interrupts = <0 109 IRQ_TYPE_LEVEL_HIGH
 			      0 109 IRQ_TYPE_LEVEL_HIGH>;

Documentation/devicetree/bindings/dma/stm32-dma.txt

+* STMicroelectronics STM32 DMA controller
+
+The STM32 DMA is a general-purpose direct memory access controller capable of
+supporting 8 independent DMA channels. Each channel can have up to 8 requests.
+
+Required properties:
+- compatible: Should be "st,stm32-dma"
+- reg: Should contain DMA registers location and length. This should include
+  all of the per-channel registers.
+- interrupts: Should contain all of the per-channel DMA interrupts in
+  ascending order with respect to the DMA channel index.
+- clocks: Should contain the input clock of the DMA instance.
+- #dma-cells : Must be <4>. See DMA client paragraph for more details.
+
+Optional properties:
+- resets: Reference to a reset controller asserting the DMA controller
+- st,mem2mem: boolean; if defined, it indicates that the controller supports
+  memory-to-memory transfer
+
+Example:
+
+	dma2: dma-controller@40026400 {
+		compatible = "st,stm32-dma";
+		reg = <0x40026400 0x400>;
+		interrupts = <56>,
+			     <57>,
+			     <58>,
+			     <59>,
+			     <60>,
+			     <68>,
+			     <69>,
+			     <70>;
+		clocks = <&clk_hclk>;
+		#dma-cells = <4>;
+		st,mem2mem;
+		resets = <&rcc 150>;
+	};
+
+* DMA client
+
+DMA clients connected to the STM32 DMA controller must use the format
+described in the dma.txt file, using a five-cell specifier for each
+channel: a phandle plus four integer cells.
+The four cells in order are:
+
+1. The channel id
+2. The request line number
+3. A 32bit mask specifying the DMA channel configuration which are device
+   dependent:
+  -bit 9: Peripheral Increment Address
+	0x0: no address increment between transfers
+	0x1: increment address between transfers
+ -bit 10: Memory Increment Address
+	0x0: no address increment between transfers
+	0x1: increment address between transfers
+ -bit 15: Peripheral Increment Offset Size
+	0x0: offset size is linked to the peripheral bus width
+	0x1: offset size is fixed to 4 (32-bit alignment)
+ -bit 16-17: Priority level
+	0x0: low
+	0x1: medium
+	0x2: high
+	0x3: very high
+5. A 32bit mask specifying the DMA FIFO threshold configuration which are device
+   dependent:
+ -bit 0-1: Fifo threshold
+	0x0: 1/4 full FIFO
+	0x1: 1/2 full FIFO
+	0x2: 3/4 full FIFO
+	0x3: full FIFO
+
+Example:
+
+	usart1: serial@40011000 {
+		compatible = "st,stm32-usart", "st,stm32-uart";
+		reg = <0x40011000 0x400>;
+		interrupts = <37>;
+		clocks = <&clk_pclk2>;
+		dmas = <&dma2 2 4 0x10400 0x3>,
+		       <&dma2 7 5 0x10200 0x3>;
+		dma-names = "rx", "tx";
+	};

Documentation/devicetree/bindings/dma/ti-dma-crossbar.txt

@@ -14,6 +14,10 @@ The DMA controller node need to have the following poroperties:
 
 Optional properties:
 - ti,dma-safe-map: Safe routing value for unused request lines
+- ti,reserved-dma-request-ranges: DMA request ranges which should not be used
+		when mapping xbar input to DMA request, they are either
+		allocated to be used by for example the DSP or they are used as
+		memcpy channels in eDMA.
 
 Notes:
 When requesting channel via ti,dra7-dma-crossbar, the DMA clinet must request
@@ -46,6 +50,8 @@ sdma_xbar: dma-router@4a002b78 {
 	#dma-cells = <1>;
 	dma-requests = <205>;
 	ti,dma-safe-map = <0>;
+	/* Protect the sDMA request ranges: 10-14 and 100-126 */
+	ti,reserved-dma-request-ranges = <10 5>, <100 27>;
 	dma-masters = <&sdma>;
 };
 

Documentation/dmaengine/client.txt

@@ -22,25 +22,14 @@ The slave DMA usage consists of following steps:
    Channel allocation is slightly different in the slave DMA context,
    client drivers typically need a channel from a particular DMA
    controller only and even in some cases a specific channel is desired.
-   To request a channel dma_request_channel() API is used.
+   To request a channel dma_request_chan() API is used.
 
    Interface:
-	struct dma_chan *dma_request_channel(dma_cap_mask_t mask,
-			dma_filter_fn filter_fn,
-			void *filter_param);
-   where dma_filter_fn is defined as:
-	typedef bool (*dma_filter_fn)(struct dma_chan *chan, void *filter_param);
+	struct dma_chan *dma_request_chan(struct device *dev, const char *name);
 
-   The 'filter_fn' parameter is optional, but highly recommended for
-   slave and cyclic channels as they typically need to obtain a specific
-   DMA channel.
-
-   When the optional 'filter_fn' parameter is NULL, dma_request_channel()
-   simply returns the first channel that satisfies the capability mask.
-
-   Otherwise, the 'filter_fn' routine will be called once for each free
-   channel which has a capability in 'mask'.  'filter_fn' is expected to
-   return 'true' when the desired DMA channel is found.
+   Which will find and return the 'name' DMA channel associated with the 'dev'
+   device. The association is done via DT, ACPI or board file based
+   dma_slave_map matching table.
 
    A channel allocated via this interface is exclusive to the caller,
    until dma_release_channel() is called.
@@ -128,7 +117,7 @@ The slave DMA usage consists of following steps:
 	transaction.
 
 	For cyclic DMA, a callback function may wish to terminate the
-	DMA via dmaengine_terminate_all().
+	DMA via dmaengine_terminate_async().
 
 	Therefore, it is important that DMA engine drivers drop any
 	locks before calling the callback function which may cause a
@@ -166,12 +155,29 @@ The slave DMA usage consists of following steps:
 
 Further APIs:
 
-1. int dmaengine_terminate_all(struct dma_chan *chan)
+1. int dmaengine_terminate_sync(struct dma_chan *chan)
+   int dmaengine_terminate_async(struct dma_chan *chan)
+   int dmaengine_terminate_all(struct dma_chan *chan) /* DEPRECATED */
 
    This causes all activity for the DMA channel to be stopped, and may
    discard data in the DMA FIFO which hasn't been fully transferred.
    No callback functions will be called for any incomplete transfers.
 
+   Two variants of this function are available.
+
+   dmaengine_terminate_async() might not wait until the DMA has been fully
+   stopped or until any running complete callbacks have finished. But it is
+   possible to call dmaengine_terminate_async() from atomic context or from
+   within a complete callback. dmaengine_synchronize() must be called before it
+   is safe to free the memory accessed by the DMA transfer or free resources
+   accessed from within the complete callback.
+
+   dmaengine_terminate_sync() will wait for the transfer and any running
+   complete callbacks to finish before it returns. But the function must not be
+   called from atomic context or from within a complete callback.
+
+   dmaengine_terminate_all() is deprecated and should not be used in new code.
+
 2. int dmaengine_pause(struct dma_chan *chan)
 
    This pauses activity on the DMA channel without data loss.
@@ -197,3 +203,20 @@ Further APIs:
 	a running DMA channel.  It is recommended that DMA engine users
 	pause or stop (via dmaengine_terminate_all()) the channel before
 	using this API.
+
+5. void dmaengine_synchronize(struct dma_chan *chan)
+
+  Synchronize the termination of the DMA channel to the current context.
+
+  This function should be used after dmaengine_terminate_async() to synchronize
+  the termination of the DMA channel to the current context. The function will
+  wait for the transfer and any running complete callbacks to finish before it
+  returns.
+
+  If dmaengine_terminate_async() is used to stop the DMA channel this function
+  must be called before it is safe to free memory accessed by previously
+  submitted descriptors or to free any resources accessed within the complete
+  callback of previously submitted descriptors.
+
+  The behavior of this function is undefined if dma_async_issue_pending() has
+  been called between dmaengine_terminate_async() and this function.

Documentation/dmaengine/provider.txt

@@ -327,8 +327,24 @@ supported.
 
    * device_terminate_all
      - Aborts all the pending and ongoing transfers on the channel
-     - This command should operate synchronously on the channel,
-       terminating right away all the channels
+     - For aborted transfers the complete callback should not be called
+     - Can be called from atomic context or from within a complete
+       callback of a descriptor. Must not sleep. Drivers must be able
+       to handle this correctly.
+     - Termination may be asynchronous. The driver does not have to
+       wait until the currently active transfer has completely stopped.
+       See device_synchronize.
+
+   * device_synchronize
+     - Must synchronize the termination of a channel to the current
+       context.
+     - Must make sure that memory for previously submitted
+       descriptors is no longer accessed by the DMA controller.
+     - Must make sure that all complete callbacks for previously
+       submitted descriptors have finished running and none are
+       scheduled to run.
+     - May sleep.
+
 
 Misc notes (stuff that should be documented, but don't really know
 where to put them)

arch/arm/configs/stm32_defconfig

@@ -54,6 +54,8 @@ CONFIG_NEW_LEDS=y
 CONFIG_LEDS_CLASS=y
 CONFIG_LEDS_TRIGGERS=y
 CONFIG_LEDS_TRIGGER_HEARTBEAT=y
+CONFIG_DMADEVICES=y
+CONFIG_STM32_DMA=y
 # CONFIG_FILE_LOCKING is not set
 # CONFIG_DNOTIFY is not set
 # CONFIG_INOTIFY_USER is not set

drivers/dca/dca-core.c

@@ -321,7 +321,8 @@ EXPORT_SYMBOL_GPL(dca_get_tag);
  * @ops - pointer to struct of dca operation function pointers
  * @priv_size - size of extra mem to be added for provider's needs
  */
-struct dca_provider *alloc_dca_provider(struct dca_ops *ops, int priv_size)
+struct dca_provider *alloc_dca_provider(const struct dca_ops *ops,
+					int priv_size)
 {
 	struct dca_provider *dca;
 	int alloc_size;

drivers/dma/Kconfig

@@ -431,6 +431,18 @@ config STE_DMA40
 	help
 	  Support for ST-Ericsson DMA40 controller
 
+config STM32_DMA
+	bool "STMicroelectronics STM32 DMA support"
+	depends on ARCH_STM32
+	select DMA_ENGINE
+	select DMA_OF
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Enable support for the on-chip DMA controller on STMicroelectronics
+	  STM32 MCUs.
+	  If you have a board based on such a MCU and wish to use DMA say Y or M
+	  here.
+
 config S3C24XX_DMAC
 	tristate "Samsung S3C24XX DMA support"
 	depends on ARCH_S3C24XX

drivers/dma/Makefile

@@ -56,6 +56,7 @@ obj-$(CONFIG_QCOM_BAM_DMA) += qcom_bam_dma.o
 obj-$(CONFIG_RENESAS_DMA) += sh/
 obj-$(CONFIG_SIRF_DMA) += sirf-dma.o
 obj-$(CONFIG_STE_DMA40) += ste_dma40.o ste_dma40_ll.o
+obj-$(CONFIG_STM32_DMA) += stm32-dma.o
 obj-$(CONFIG_S3C24XX_DMAC) += s3c24xx-dma.o
 obj-$(CONFIG_TXX9_DMAC) += txx9dmac.o
 obj-$(CONFIG_TEGRA20_APB_DMA) += tegra20-apb-dma.o

drivers/dma/acpi-dma.c

@@ -15,6 +15,7 @@
 #include <linux/device.h>
 #include <linux/err.h>
 #include <linux/module.h>
+#include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
@@ -72,7 +73,9 @@ static int acpi_dma_parse_resource_group(const struct acpi_csrt_group *grp,
 	si = (const struct acpi_csrt_shared_info *)&grp[1];
 
 	/* Match device by MMIO and IRQ */
-	if (si->mmio_base_low != mem || si->gsi_interrupt != irq)
+	if (si->mmio_base_low != lower_32_bits(mem) ||
+	    si->mmio_base_high != upper_32_bits(mem) ||
+	    si->gsi_interrupt != irq)
 		return 0;
 
 	dev_dbg(&adev->dev, "matches with %.4s%04X (rev %u)\n",

drivers/dma/at_xdmac.c

@@ -863,8 +863,12 @@ at_xdmac_interleaved_queue_desc(struct dma_chan *chan,
 	 * access. Hopefully we can access DDR through both ports (at least on
 	 * SAMA5D4x), so we can use the same interface for source and dest,
 	 * that solves the fact we don't know the direction.
+	 * ERRATA: Even if useless for memory transfers, the PERID has to not
+	 * match the one of another channel. If not, it could lead to spurious
+	 * flag status.
 	 */
-	u32			chan_cc = AT_XDMAC_CC_DIF(0)
+	u32			chan_cc = AT_XDMAC_CC_PERID(0x3f)
+					| AT_XDMAC_CC_DIF(0)
 					| AT_XDMAC_CC_SIF(0)
 					| AT_XDMAC_CC_MBSIZE_SIXTEEN
 					| AT_XDMAC_CC_TYPE_MEM_TRAN;
@@ -1041,8 +1045,12 @@ at_xdmac_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 	 * access DDR through both ports (at least on SAMA5D4x), so we can use
 	 * the same interface for source and dest, that solves the fact we
 	 * don't know the direction.
+	 * ERRATA: Even if useless for memory transfers, the PERID has to not
+	 * match the one of another channel. If not, it could lead to spurious
+	 * flag status.
 	 */
-	u32			chan_cc = AT_XDMAC_CC_DAM_INCREMENTED_AM
+	u32			chan_cc = AT_XDMAC_CC_PERID(0x3f)
+					| AT_XDMAC_CC_DAM_INCREMENTED_AM
 					| AT_XDMAC_CC_SAM_INCREMENTED_AM
 					| AT_XDMAC_CC_DIF(0)
 					| AT_XDMAC_CC_SIF(0)
@@ -1143,8 +1151,12 @@ static struct at_xdmac_desc *at_xdmac_memset_create_desc(struct dma_chan *chan,
 	 * access. Hopefully we can access DDR through both ports (at least on
 	 * SAMA5D4x), so we can use the same interface for source and dest,
 	 * that solves the fact we don't know the direction.
+	 * ERRATA: Even if useless for memory transfers, the PERID has to not
+	 * match the one of another channel. If not, it could lead to spurious
+	 * flag status.
 	 */
-	u32			chan_cc = AT_XDMAC_CC_DAM_UBS_AM
+	u32			chan_cc = AT_XDMAC_CC_PERID(0x3f)
+					| AT_XDMAC_CC_DAM_UBS_AM
 					| AT_XDMAC_CC_SAM_INCREMENTED_AM
 					| AT_XDMAC_CC_DIF(0)
 					| AT_XDMAC_CC_SIF(0)
@@ -1998,8 +2010,6 @@ static int at_xdmac_remove(struct platform_device *pdev)
 	dma_async_device_unregister(&atxdmac->dma);
 	clk_disable_unprepare(atxdmac->clk);
 
-	synchronize_irq(atxdmac->irq);
-
 	free_irq(atxdmac->irq, atxdmac->dma.dev);
 
 	for (i = 0; i < atxdmac->dma.chancnt; i++) {

drivers/dma/dma-axi-dmac.c

@@ -307,6 +307,13 @@ static int axi_dmac_terminate_all(struct dma_chan *c)
 	return 0;
 }
 
+static void axi_dmac_synchronize(struct dma_chan *c)
+{
+	struct axi_dmac_chan *chan = to_axi_dmac_chan(c);
+
+	vchan_synchronize(&chan->vchan);
+}
+
 static void axi_dmac_issue_pending(struct dma_chan *c)
 {
 	struct axi_dmac_chan *chan = to_axi_dmac_chan(c);
@@ -613,6 +620,7 @@ static int axi_dmac_probe(struct platform_device *pdev)
 	dma_dev->device_prep_dma_cyclic = axi_dmac_prep_dma_cyclic;
 	dma_dev->device_prep_interleaved_dma = axi_dmac_prep_interleaved;
 	dma_dev->device_terminate_all = axi_dmac_terminate_all;
+	dma_dev->device_synchronize = axi_dmac_synchronize;
 	dma_dev->dev = &pdev->dev;
 	dma_dev->chancnt = 1;
 	dma_dev->src_addr_widths = BIT(dmac->chan.src_width);

drivers/dma/dmaengine.c

@@ -43,6 +43,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
 #include <linux/init.h>
 #include <linux/module.h>
@@ -265,8 +266,11 @@ static void dma_chan_put(struct dma_chan *chan)
 	module_put(dma_chan_to_owner(chan));
 
 	/* This channel is not in use anymore, free it */
-	if (!chan->client_count && chan->device->device_free_chan_resources)
+	if (!chan->client_count && chan->device->device_free_chan_resources) {
+		/* Make sure all operations have completed */
+		dmaengine_synchronize(chan);
 		chan->device->device_free_chan_resources(chan);
+	}
 
 	/* If the channel is used via a DMA request router, free the mapping */
 	if (chan->router && chan->router->route_free) {
@@ -493,6 +497,7 @@ int dma_get_slave_caps(struct dma_chan *chan, struct dma_slave_caps *caps)
 	caps->dst_addr_widths = device->dst_addr_widths;
 	caps->directions = device->directions;
 	caps->residue_granularity = device->residue_granularity;
+	caps->descriptor_reuse = device->descriptor_reuse;
 
 	/*
 	 * Some devices implement only pause (e.g. to get residuum) but no
@@ -511,7 +516,7 @@ static struct dma_chan *private_candidate(const dma_cap_mask_t *mask,
 {
 	struct dma_chan *chan;
 
-	if (!__dma_device_satisfies_mask(dev, mask)) {
+	if (mask && !__dma_device_satisfies_mask(dev, mask)) {
 		pr_debug("%s: wrong capabilities\n", __func__);
 		return NULL;
 	}
@@ -542,6 +547,42 @@ static struct dma_chan *private_candidate(const dma_cap_mask_t *mask,
 	return NULL;
 }
 
+static struct dma_chan *find_candidate(struct dma_device *device,
+				       const dma_cap_mask_t *mask,
+				       dma_filter_fn fn, void *fn_param)
+{
+	struct dma_chan *chan = private_candidate(mask, device, fn, fn_param);
+	int err;
+
+	if (chan) {
+		/* Found a suitable channel, try to grab, prep, and return it.
+		 * We first set DMA_PRIVATE to disable balance_ref_count as this
+		 * channel will not be published in the general-purpose
+		 * allocator
+		 */
+		dma_cap_set(DMA_PRIVATE, device->cap_mask);
+		device->privatecnt++;
+		err = dma_chan_get(chan);
+
+		if (err) {
+			if (err == -ENODEV) {
+				pr_debug("%s: %s module removed\n", __func__,
+					 dma_chan_name(chan));
+				list_del_rcu(&device->global_node);
+			} else
+				pr_debug("%s: failed to get %s: (%d)\n",
+					 __func__, dma_chan_name(chan), err);
+
+			if (--device->privatecnt == 0)
+				dma_cap_clear(DMA_PRIVATE, device->cap_mask);
+
+			chan = ERR_PTR(err);
+		}
+	}
+
+	return chan ? chan : ERR_PTR(-EPROBE_DEFER);
+}
+
 /**
  * dma_get_slave_channel - try to get specific channel exclusively
  * @chan: target channel
@@ -580,7 +621,6 @@ struct dma_chan *dma_get_any_slave_channel(struct dma_device *device)
 {
 	dma_cap_mask_t mask;
 	struct dma_chan *chan;
-	int err;
 
 	dma_cap_zero(mask);
 	dma_cap_set(DMA_SLAVE, mask);
@@ -588,23 +628,11 @@ struct dma_chan *dma_get_any_slave_channel(struct dma_device *device)
 	/* lock against __dma_request_channel */
 	mutex_lock(&dma_list_mutex);
 
-	chan = private_candidate(&mask, device, NULL, NULL);
-	if (chan) {
-		dma_cap_set(DMA_PRIVATE, device->cap_mask);
-		device->privatecnt++;
-		err = dma_chan_get(chan);
-		if (err) {
-			pr_debug("%s: failed to get %s: (%d)\n",
-				__func__, dma_chan_name(chan), err);
-			chan = NULL;
-			if (--device->privatecnt == 0)
-				dma_cap_clear(DMA_PRIVATE, device->cap_mask);
-		}
-	}
+	chan = find_candidate(device, &mask, NULL, NULL);
 
 	mutex_unlock(&dma_list_mutex);
 
-	return chan;
+	return IS_ERR(chan) ? NULL : chan;
 }
 EXPORT_SYMBOL_GPL(dma_get_any_slave_channel);
 
@@ -621,35 +649,15 @@ struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask,
 {
 	struct dma_device *device, *_d;
 	struct dma_chan *chan = NULL;
-	int err;
 
 	/* Find a channel */
 	mutex_lock(&dma_list_mutex);
 	list_for_each_entry_safe(device, _d, &dma_device_list, global_node) {
-		chan = private_candidate(mask, device, fn, fn_param);
-		if (chan) {
-			/* Found a suitable channel, try to grab, prep, and
-			 * return it.  We first set DMA_PRIVATE to disable
-			 * balance_ref_count as this channel will not be
-			 * published in the general-purpose allocator
-			 */
-			dma_cap_set(DMA_PRIVATE, device->cap_mask);
-			device->privatecnt++;
-			err = dma_chan_get(chan);
+		chan = find_candidate(device, mask, fn, fn_param);
+		if (!IS_ERR(chan))
+			break;
 
-			if (err == -ENODEV) {
-				pr_debug("%s: %s module removed\n",
-					 __func__, dma_chan_name(chan));
-				list_del_rcu(&device->global_node);
-			} else if (err)
-				pr_debug("%s: failed to get %s: (%d)\n",
-					 __func__, dma_chan_name(chan), err);
-			else
-				break;
-			if (--device->privatecnt == 0)
-				dma_cap_clear(DMA_PRIVATE, device->cap_mask);
-			chan = NULL;
-		}
+		chan = NULL;
 	}
 	mutex_unlock(&dma_list_mutex);
 
@@ -662,27 +670,73 @@ struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask,
 }
 EXPORT_SYMBOL_GPL(__dma_request_channel);
 
+static const struct dma_slave_map *dma_filter_match(struct dma_device *device,
+						    const char *name,
+						    struct device *dev)
+{
+	int i;
+
+	if (!device->filter.mapcnt)
+		return NULL;
+
+	for (i = 0; i < device->filter.mapcnt; i++) {
+		const struct dma_slave_map *map = &device->filter.map[i];
+
+		if (!strcmp(map->devname, dev_name(dev)) &&
+		    !strcmp(map->slave, name))
+			return map;
+	}
+
+	return NULL;
+}
+
 /**
- * dma_request_slave_channel_reason - try to allocate an exclusive slave channel
+ * dma_request_chan - try to allocate an exclusive slave channel
  * @dev:	pointer to client device structure
  * @name:	slave channel name
  *
  * Returns pointer to appropriate DMA channel on success or an error pointer.
  */
-struct dma_chan *dma_request_slave_channel_reason(struct device *dev,
-						  const char *name)
+struct dma_chan *dma_request_chan(struct device *dev, const char *name)
 {
+	struct dma_device *d, *_d;
+	struct dma_chan *chan = NULL;
+
 	/* If device-tree is present get slave info from here */
 	if (dev->of_node)
-		return of_dma_request_slave_channel(dev->of_node, name);
+		chan = of_dma_request_slave_channel(dev->of_node, name);
 
 	/* If device was enumerated by ACPI get slave info from here */
-	if (ACPI_HANDLE(dev))
-		return acpi_dma_request_slave_chan_by_name(dev, name);
+	if (has_acpi_companion(dev) && !chan)
+		chan = acpi_dma_request_slave_chan_by_name(dev, name);
+
+	if (chan) {
+		/* Valid channel found or requester need to be deferred */
+		if (!IS_ERR(chan) || PTR_ERR(chan) == -EPROBE_DEFER)
+			return chan;
+	}
 
-	return ERR_PTR(-ENODEV);
+	/* Try to find the channel via the DMA filter map(s) */
+	mutex_lock(&dma_list_mutex);
+	list_for_each_entry_safe(d, _d, &dma_device_list, global_node) {
+		dma_cap_mask_t mask;
+		const struct dma_slave_map *map = dma_filter_match(d, name, dev);
+
+		if (!map)
+			continue;
+
+		dma_cap_zero(mask);
+		dma_cap_set(DMA_SLAVE, mask);
+
+		chan = find_candidate(d, &mask, d->filter.fn, map->param);
+		if (!IS_ERR(chan))
+			break;
+	}
+	mutex_unlock(&dma_list_mutex);
+
+	return chan ? chan : ERR_PTR(-EPROBE_DEFER);
 }
-EXPORT_SYMBOL_GPL(dma_request_slave_channel_reason);
+EXPORT_SYMBOL_GPL(dma_request_chan);
 
 /**
  * dma_request_slave_channel - try to allocate an exclusive slave channel
@@ -694,17 +748,35 @@ EXPORT_SYMBOL_GPL(dma_request_slave_channel_reason);
 struct dma_chan *dma_request_slave_channel(struct device *dev,
 					   const char *name)
 {
-	struct dma_chan *ch = dma_request_slave_channel_reason(dev, name);
+	struct dma_chan *ch = dma_request_chan(dev, name);
 	if (IS_ERR(ch))
 		return NULL;
 
-	dma_cap_set(DMA_PRIVATE, ch->device->cap_mask);
-	ch->device->privatecnt++;
-
 	return ch;
 }
 EXPORT_SYMBOL_GPL(dma_request_slave_channel);
 
+/**
+ * dma_request_chan_by_mask - allocate a channel satisfying certain capabilities
+ * @mask: capabilities that the channel must satisfy
+ *
+ * Returns pointer to appropriate DMA channel on success or an error pointer.
+ */
+struct dma_chan *dma_request_chan_by_mask(const dma_cap_mask_t *mask)
+{
+	struct dma_chan *chan;
+
+	if (!mask)
+		return ERR_PTR(-ENODEV);
+
+	chan = __dma_request_channel(mask, NULL, NULL);
+	if (!chan)
+		chan = ERR_PTR(-ENODEV);
+
+	return chan;
+}
+EXPORT_SYMBOL_GPL(dma_request_chan_by_mask);
+
 void dma_release_channel(struct dma_chan *chan)
 {
 	mutex_lock(&dma_list_mutex);

drivers/dma/dw/platform.c

@@ -103,18 +103,21 @@ dw_dma_parse_dt(struct platform_device *pdev)
 	struct device_node *np = pdev->dev.of_node;
 	struct dw_dma_platform_data *pdata;
 	u32 tmp, arr[DW_DMA_MAX_NR_MASTERS];
+	u32 nr_channels;
 
 	if (!np) {
 		dev_err(&pdev->dev, "Missing DT data\n");
 		return NULL;
 	}
 
+	if (of_property_read_u32(np, "dma-channels", &nr_channels))
+		return NULL;
+
 	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
 	if (!pdata)
 		return NULL;
 
-	if (of_property_read_u32(np, "dma-channels", &pdata->nr_channels))
-		return NULL;
+	pdata->nr_channels = nr_channels;
 
 	if (of_property_read_bool(np, "is_private"))
 		pdata->is_private = true;

drivers/dma/edma.c

@@ -2314,6 +2314,10 @@ static int edma_probe(struct platform_device *pdev)
 		edma_set_chmap(&ecc->slave_chans[i], ecc->dummy_slot);
 	}
 
+	ecc->dma_slave.filter.map = info->slave_map;
+	ecc->dma_slave.filter.mapcnt = info->slavecnt;
+	ecc->dma_slave.filter.fn = edma_filter_fn;
+
 	ret = dma_async_device_register(&ecc->dma_slave);
 	if (ret) {
 		dev_err(dev, "slave ddev registration failed (%d)\n", ret);
@@ -2421,7 +2425,13 @@ static struct platform_driver edma_driver = {
 	},
 };
 
+static int edma_tptc_probe(struct platform_device *pdev)
+{
+	return 0;
+}
+
 static struct platform_driver edma_tptc_driver = {
+	.probe		= edma_tptc_probe,
 	.driver = {
 		.name	= "edma3-tptc",
 		.of_match_table = edma_tptc_of_ids,

drivers/dma/fsl-edma.c

@@ -116,6 +116,10 @@
 				BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | \
 				BIT(DMA_SLAVE_BUSWIDTH_4_BYTES) | \
 				BIT(DMA_SLAVE_BUSWIDTH_8_BYTES)
+enum fsl_edma_pm_state {
+	RUNNING = 0,
+	SUSPENDED,
+};
 
 struct fsl_edma_hw_tcd {
 	__le32	saddr;
@@ -147,6 +151,9 @@ struct fsl_edma_slave_config {
 struct fsl_edma_chan {
 	struct virt_dma_chan		vchan;
 	enum dma_status			status;
+	enum fsl_edma_pm_state		pm_state;
+	bool				idle;
+	u32				slave_id;
 	struct fsl_edma_engine		*edma;
 	struct fsl_edma_desc		*edesc;
 	struct fsl_edma_slave_config	fsc;
@@ -298,6 +305,7 @@ static int fsl_edma_terminate_all(struct dma_chan *chan)
 	spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
 	fsl_edma_disable_request(fsl_chan);
 	fsl_chan->edesc = NULL;
+	fsl_chan->idle = true;
 	vchan_get_all_descriptors(&fsl_chan->vchan, &head);
 	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
 	vchan_dma_desc_free_list(&fsl_chan->vchan, &head);
@@ -313,6 +321,7 @@ static int fsl_edma_pause(struct dma_chan *chan)
 	if (fsl_chan->edesc) {
 		fsl_edma_disable_request(fsl_chan);
 		fsl_chan->status = DMA_PAUSED;
+		fsl_chan->idle = true;
 	}
 	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
 	return 0;
@@ -327,6 +336,7 @@ static int fsl_edma_resume(struct dma_chan *chan)
 	if (fsl_chan->edesc) {
 		fsl_edma_enable_request(fsl_chan);
 		fsl_chan->status = DMA_IN_PROGRESS;
+		fsl_chan->idle = false;
 	}
 	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
 	return 0;
@@ -648,6 +658,7 @@ static void fsl_edma_xfer_desc(struct fsl_edma_chan *fsl_chan)
 	fsl_edma_set_tcd_regs(fsl_chan, fsl_chan->edesc->tcd[0].vtcd);
 	fsl_edma_enable_request(fsl_chan);
 	fsl_chan->status = DMA_IN_PROGRESS;
+	fsl_chan->idle = false;
 }
 
 static irqreturn_t fsl_edma_tx_handler(int irq, void *dev_id)
@@ -676,6 +687,7 @@ static irqreturn_t fsl_edma_tx_handler(int irq, void *dev_id)
 				vchan_cookie_complete(&fsl_chan->edesc->vdesc);
 				fsl_chan->edesc = NULL;
 				fsl_chan->status = DMA_COMPLETE;
+				fsl_chan->idle = true;
 			} else {
 				vchan_cyclic_callback(&fsl_chan->edesc->vdesc);
 			}
@@ -704,6 +716,7 @@ static irqreturn_t fsl_edma_err_handler(int irq, void *dev_id)
 			edma_writeb(fsl_edma, EDMA_CERR_CERR(ch),
 				fsl_edma->membase + EDMA_CERR);
 			fsl_edma->chans[ch].status = DMA_ERROR;
+			fsl_edma->chans[ch].idle = true;
 		}
 	}
 	return IRQ_HANDLED;
@@ -724,6 +737,12 @@ static void fsl_edma_issue_pending(struct dma_chan *chan)
 
 	spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
 
+	if (unlikely(fsl_chan->pm_state != RUNNING)) {
+		spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
+		/* cannot submit due to suspend */
+		return;
+	}
+
 	if (vchan_issue_pending(&fsl_chan->vchan) && !fsl_chan->edesc)
 		fsl_edma_xfer_desc(fsl_chan);
 
@@ -735,6 +754,7 @@ static struct dma_chan *fsl_edma_xlate(struct of_phandle_args *dma_spec,
 {
 	struct fsl_edma_engine *fsl_edma = ofdma->of_dma_data;
 	struct dma_chan *chan, *_chan;
+	struct fsl_edma_chan *fsl_chan;
 	unsigned long chans_per_mux = fsl_edma->n_chans / DMAMUX_NR;
 
 	if (dma_spec->args_count != 2)
@@ -748,8 +768,10 @@ static struct dma_chan *fsl_edma_xlate(struct of_phandle_args *dma_spec,
 			chan = dma_get_slave_channel(chan);
 			if (chan) {
 				chan->device->privatecnt++;
-				fsl_edma_chan_mux(to_fsl_edma_chan(chan),
-					dma_spec->args[1], true);
+				fsl_chan = to_fsl_edma_chan(chan);
+				fsl_chan->slave_id = dma_spec->args[1];
+				fsl_edma_chan_mux(fsl_chan, fsl_chan->slave_id,
+						true);
 				mutex_unlock(&fsl_edma->fsl_edma_mutex);
 				return chan;
 			}
@@ -888,7 +910,9 @@ static int fsl_edma_probe(struct platform_device *pdev)
 		struct fsl_edma_chan *fsl_chan = &fsl_edma->chans[i];
 
 		fsl_chan->edma = fsl_edma;
-
+		fsl_chan->pm_state = RUNNING;
+		fsl_chan->slave_id = 0;
+		fsl_chan->idle = true;
 		fsl_chan->vchan.desc_free = fsl_edma_free_desc;
 		vchan_init(&fsl_chan->vchan, &fsl_edma->dma_dev);
 
@@ -959,6 +983,60 @@ static int fsl_edma_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static int fsl_edma_suspend_late(struct device *dev)
+{
+	struct fsl_edma_engine *fsl_edma = dev_get_drvdata(dev);
+	struct fsl_edma_chan *fsl_chan;
+	unsigned long flags;
+	int i;
+
+	for (i = 0; i < fsl_edma->n_chans; i++) {
+		fsl_chan = &fsl_edma->chans[i];
+		spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
+		/* Make sure chan is idle or will force disable. */
+		if (unlikely(!fsl_chan->idle)) {
+			dev_warn(dev, "WARN: There is non-idle channel.");
+			fsl_edma_disable_request(fsl_chan);
+			fsl_edma_chan_mux(fsl_chan, 0, false);
+		}
+
+		fsl_chan->pm_state = SUSPENDED;
+		spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
+	}
+
+	return 0;
+}
+
+static int fsl_edma_resume_early(struct device *dev)
+{
+	struct fsl_edma_engine *fsl_edma = dev_get_drvdata(dev);
+	struct fsl_edma_chan *fsl_chan;
+	int i;
+
+	for (i = 0; i < fsl_edma->n_chans; i++) {
+		fsl_chan = &fsl_edma->chans[i];
+		fsl_chan->pm_state = RUNNING;
+		edma_writew(fsl_edma, 0x0, fsl_edma->membase + EDMA_TCD_CSR(i));
+		if (fsl_chan->slave_id != 0)
+			fsl_edma_chan_mux(fsl_chan, fsl_chan->slave_id, true);
+	}
+
+	edma_writel(fsl_edma, EDMA_CR_ERGA | EDMA_CR_ERCA,
+			fsl_edma->membase + EDMA_CR);
+
+	return 0;
+}
+
+/*
+ * eDMA provides the service to others, so it should be suspend late
+ * and resume early. When eDMA suspend, all of the clients should stop
+ * the DMA data transmission and let the channel idle.
+ */
+static const struct dev_pm_ops fsl_edma_pm_ops = {
+	.suspend_late   = fsl_edma_suspend_late,
+	.resume_early   = fsl_edma_resume_early,
+};
+
 static const struct of_device_id fsl_edma_dt_ids[] = {
 	{ .compatible = "fsl,vf610-edma", },
 	{ /* sentinel */ }
@@ -969,6 +1047,7 @@ static struct platform_driver fsl_edma_driver = {
 	.driver		= {
 		.name	= "fsl-edma",
 		.of_match_table = fsl_edma_dt_ids,
+		.pm     = &fsl_edma_pm_ops,
 	},
 	.probe          = fsl_edma_probe,
 	.remove		= fsl_edma_remove,

drivers/dma/hsu/hsu.c

@@ -228,6 +228,8 @@ static struct dma_async_tx_descriptor *hsu_dma_prep_slave_sg(
 	for_each_sg(sgl, sg, sg_len, i) {
 		desc->sg[i].addr = sg_dma_address(sg);
 		desc->sg[i].len = sg_dma_len(sg);
+
+		desc->length += sg_dma_len(sg);
 	}
 
 	desc->nents = sg_len;
@@ -249,21 +251,10 @@ static void hsu_dma_issue_pending(struct dma_chan *chan)
 	spin_unlock_irqrestore(&hsuc->vchan.lock, flags);
 }
 
-static size_t hsu_dma_desc_size(struct hsu_dma_desc *desc)
-{
-	size_t bytes = 0;
-	unsigned int i;
-
-	for (i = desc->active; i < desc->nents; i++)
-		bytes += desc->sg[i].len;
-
-	return bytes;
-}
-
 static size_t hsu_dma_active_desc_size(struct hsu_dma_chan *hsuc)
 {
 	struct hsu_dma_desc *desc = hsuc->desc;
-	size_t bytes = hsu_dma_desc_size(desc);
+	size_t bytes = desc->length;
 	int i;
 
 	i = desc->active % HSU_DMA_CHAN_NR_DESC;
@@ -294,7 +285,7 @@ static enum dma_status hsu_dma_tx_status(struct dma_chan *chan,
 		dma_set_residue(state, bytes);
 		status = hsuc->desc->status;
 	} else if (vdesc) {
-		bytes = hsu_dma_desc_size(to_hsu_dma_desc(vdesc));
+		bytes = to_hsu_dma_desc(vdesc)->length;
 		dma_set_residue(state, bytes);
 	}
 	spin_unlock_irqrestore(&hsuc->vchan.lock, flags);

drivers/dma/hsu/hsu.h

@@ -65,6 +65,7 @@ struct hsu_dma_desc {
 	enum dma_transfer_direction direction;
 	struct hsu_dma_sg *sg;
 	unsigned int nents;
+	size_t length;
 	unsigned int active;
 	enum dma_status status;
 };

drivers/dma/idma64.c

@@ -178,20 +178,12 @@ static irqreturn_t idma64_irq(int irq, void *dev)
 	if (!status)
 		return IRQ_NONE;
 
-	/* Disable interrupts */
-	channel_clear_bit(idma64, MASK(XFER), idma64->all_chan_mask);
-	channel_clear_bit(idma64, MASK(ERROR), idma64->all_chan_mask);
-
 	status_xfer = dma_readl(idma64, RAW(XFER));
 	status_err = dma_readl(idma64, RAW(ERROR));
 
 	for (i = 0; i < idma64->dma.chancnt; i++)
 		idma64_chan_irq(idma64, i, status_err, status_xfer);
 
-	/* Re-enable interrupts */
-	channel_set_bit(idma64, MASK(XFER), idma64->all_chan_mask);
-	channel_set_bit(idma64, MASK(ERROR), idma64->all_chan_mask);
-
 	return IRQ_HANDLED;
 }
 
@@ -239,7 +231,7 @@ static void idma64_vdesc_free(struct virt_dma_desc *vdesc)
 	idma64_desc_free(idma64c, to_idma64_desc(vdesc));
 }
 
-static u64 idma64_hw_desc_fill(struct idma64_hw_desc *hw,
+static void idma64_hw_desc_fill(struct idma64_hw_desc *hw,
 		struct dma_slave_config *config,
 		enum dma_transfer_direction direction, u64 llp)
 {
@@ -276,26 +268,26 @@ static u64 idma64_hw_desc_fill(struct idma64_hw_desc *hw,
 		     IDMA64C_CTLL_SRC_WIDTH(src_width);
 
 	lli->llp = llp;
-	return hw->llp;
 }
 
 static void idma64_desc_fill(struct idma64_chan *idma64c,
 		struct idma64_desc *desc)
 {
 	struct dma_slave_config *config = &idma64c->config;
-	struct idma64_hw_desc *hw = &desc->hw[desc->ndesc - 1];
+	unsigned int i = desc->ndesc;
+	struct idma64_hw_desc *hw = &desc->hw[i - 1];
 	struct idma64_lli *lli = hw->lli;
 	u64 llp = 0;
-	unsigned int i = desc->ndesc;
 
 	/* Fill the hardware descriptors and link them to a list */
 	do {
 		hw = &desc->hw[--i];
-		llp = idma64_hw_desc_fill(hw, config, desc->direction, llp);
+		idma64_hw_desc_fill(hw, config, desc->direction, llp);
+		llp = hw->llp;
 		desc->length += hw->len;
 	} while (i);
 
-	/* Trigger interrupt after last block */
+	/* Trigger an interrupt after the last block is transfered */
 	lli->ctllo |= IDMA64C_CTLL_INT_EN;
 }
 
@@ -596,6 +588,8 @@ static int idma64_probe(struct idma64_chip *chip)
 
 	idma64->dma.dev = chip->dev;
 
+	dma_set_max_seg_size(idma64->dma.dev, IDMA64C_CTLH_BLOCK_TS_MASK);
+
 	ret = dma_async_device_register(&idma64->dma);
 	if (ret)
 		return ret;

drivers/dma/idma64.h

@@ -54,7 +54,8 @@
 #define IDMA64C_CTLL_LLP_S_EN		(1 << 28)	/* src block chain */
 
 /* Bitfields in CTL_HI */
-#define IDMA64C_CTLH_BLOCK_TS(x)	((x) & ((1 << 17) - 1))
+#define IDMA64C_CTLH_BLOCK_TS_MASK	((1 << 17) - 1)
+#define IDMA64C_CTLH_BLOCK_TS(x)	((x) & IDMA64C_CTLH_BLOCK_TS_MASK)
 #define IDMA64C_CTLH_DONE		(1 << 17)
 
 /* Bitfields in CFG_LO */

drivers/dma/img-mdc-dma.c

@@ -651,6 +651,48 @@ static enum dma_status mdc_tx_status(struct dma_chan *chan,
 	return ret;
 }
 
+static unsigned int mdc_get_new_events(struct mdc_chan *mchan)
+{
+	u32 val, processed, done1, done2;
+	unsigned int ret;
+
+	val = mdc_chan_readl(mchan, MDC_CMDS_PROCESSED);
+	processed = (val >> MDC_CMDS_PROCESSED_CMDS_PROCESSED_SHIFT) &
+				MDC_CMDS_PROCESSED_CMDS_PROCESSED_MASK;
+	/*
+	 * CMDS_DONE may have incremented between reading CMDS_PROCESSED
+	 * and clearing INT_ACTIVE.  Re-read CMDS_PROCESSED to ensure we
+	 * didn't miss a command completion.
+	 */
+	do {
+		val = mdc_chan_readl(mchan, MDC_CMDS_PROCESSED);
+
+		done1 = (val >> MDC_CMDS_PROCESSED_CMDS_DONE_SHIFT) &
+			MDC_CMDS_PROCESSED_CMDS_DONE_MASK;
+
+		val &= ~((MDC_CMDS_PROCESSED_CMDS_PROCESSED_MASK <<
+			  MDC_CMDS_PROCESSED_CMDS_PROCESSED_SHIFT) |
+			 MDC_CMDS_PROCESSED_INT_ACTIVE);
+
+		val |= done1 << MDC_CMDS_PROCESSED_CMDS_PROCESSED_SHIFT;
+
+		mdc_chan_writel(mchan, val, MDC_CMDS_PROCESSED);
+
+		val = mdc_chan_readl(mchan, MDC_CMDS_PROCESSED);
+
+		done2 = (val >> MDC_CMDS_PROCESSED_CMDS_DONE_SHIFT) &
+			MDC_CMDS_PROCESSED_CMDS_DONE_MASK;
+	} while (done1 != done2);
+
+	if (done1 >= processed)
+		ret = done1 - processed;
+	else
+		ret = ((MDC_CMDS_PROCESSED_CMDS_PROCESSED_MASK + 1) -
+			processed) + done1;
+
+	return ret;
+}
+
 static int mdc_terminate_all(struct dma_chan *chan)
 {
 	struct mdc_chan *mchan = to_mdc_chan(chan);
@@ -667,6 +709,8 @@ static int mdc_terminate_all(struct dma_chan *chan)
 	mchan->desc = NULL;
 	vchan_get_all_descriptors(&mchan->vc, &head);
 
+	mdc_get_new_events(mchan);
+
 	spin_unlock_irqrestore(&mchan->vc.lock, flags);
 
 	if (mdesc)
@@ -703,35 +747,17 @@ static irqreturn_t mdc_chan_irq(int irq, void *dev_id)
 {
 	struct mdc_chan *mchan = (struct mdc_chan *)dev_id;
 	struct mdc_tx_desc *mdesc;
-	u32 val, processed, done1, done2;
-	unsigned int i;
+	unsigned int i, new_events;
 
 	spin_lock(&mchan->vc.lock);
 
-	val = mdc_chan_readl(mchan, MDC_CMDS_PROCESSED);
-	processed = (val >> MDC_CMDS_PROCESSED_CMDS_PROCESSED_SHIFT) &
-		MDC_CMDS_PROCESSED_CMDS_PROCESSED_MASK;
-	/*
-	 * CMDS_DONE may have incremented between reading CMDS_PROCESSED
-	 * and clearing INT_ACTIVE.  Re-read CMDS_PROCESSED to ensure we
-	 * didn't miss a command completion.
-	 */
-	do {
-		val = mdc_chan_readl(mchan, MDC_CMDS_PROCESSED);
-		done1 = (val >> MDC_CMDS_PROCESSED_CMDS_DONE_SHIFT) &
-			MDC_CMDS_PROCESSED_CMDS_DONE_MASK;
-		val &= ~((MDC_CMDS_PROCESSED_CMDS_PROCESSED_MASK <<
-			  MDC_CMDS_PROCESSED_CMDS_PROCESSED_SHIFT) |
-			 MDC_CMDS_PROCESSED_INT_ACTIVE);
-		val |= done1 << MDC_CMDS_PROCESSED_CMDS_PROCESSED_SHIFT;
-		mdc_chan_writel(mchan, val, MDC_CMDS_PROCESSED);
-		val = mdc_chan_readl(mchan, MDC_CMDS_PROCESSED);
-		done2 = (val >> MDC_CMDS_PROCESSED_CMDS_DONE_SHIFT) &
-			MDC_CMDS_PROCESSED_CMDS_DONE_MASK;
-	} while (done1 != done2);
-
 	dev_dbg(mdma2dev(mchan->mdma), "IRQ on channel %d\n", mchan->chan_nr);
 
+	new_events = mdc_get_new_events(mchan);
+
+	if (!new_events)
+		goto out;
+
 	mdesc = mchan->desc;
 	if (!mdesc) {
 		dev_warn(mdma2dev(mchan->mdma),
@@ -740,8 +766,7 @@ static irqreturn_t mdc_chan_irq(int irq, void *dev_id)
 		goto out;
 	}
 
-	for (i = processed; i != done1;
-	     i = (i + 1) % (MDC_CMDS_PROCESSED_CMDS_PROCESSED_MASK + 1)) {
+	for (i = 0; i < new_events; i++) {
 		/*
 		 * The first interrupt in a transfer indicates that the
 		 * command list has been loaded, not that a command has
@@ -979,7 +1004,6 @@ static int mdc_dma_remove(struct platform_device *pdev)
 				 vc.chan.device_node) {
 		list_del(&mchan->vc.chan.device_node);
 
-		synchronize_irq(mchan->irq);
 		devm_free_irq(&pdev->dev, mchan->irq, mchan);
 
 		tasklet_kill(&mchan->vc.task);

drivers/dma/ioat/dca.c

@@ -224,7 +224,7 @@ static u8 ioat_dca_get_tag(struct dca_provider *dca,
 	return tag;
 }
 
-static struct dca_ops ioat_dca_ops = {
+static const struct dca_ops ioat_dca_ops = {
 	.add_requester		= ioat_dca_add_requester,
 	.remove_requester	= ioat_dca_remove_requester,
 	.get_tag		= ioat_dca_get_tag,

drivers/dma/ioat/dma.h

@@ -235,43 +235,11 @@ ioat_chan_by_index(struct ioatdma_device *ioat_dma, int index)
 	return ioat_dma->idx[index];
 }
 
-static inline u64 ioat_chansts_32(struct ioatdma_chan *ioat_chan)
-{
-	u8 ver = ioat_chan->ioat_dma->version;
-	u64 status;
-	u32 status_lo;
-
-	/* We need to read the low address first as this causes the
-	 * chipset to latch the upper bits for the subsequent read
-	 */
-	status_lo = readl(ioat_chan->reg_base + IOAT_CHANSTS_OFFSET_LOW(ver));
-	status = readl(ioat_chan->reg_base + IOAT_CHANSTS_OFFSET_HIGH(ver));
-	status <<= 32;
-	status |= status_lo;
-
-	return status;
-}
-
-#if BITS_PER_LONG == 64
-
 static inline u64 ioat_chansts(struct ioatdma_chan *ioat_chan)
 {
-	u8 ver = ioat_chan->ioat_dma->version;
-	u64 status;
-
-	 /* With IOAT v3.3 the status register is 64bit.  */
-	if (ver >= IOAT_VER_3_3)
-		status = readq(ioat_chan->reg_base + IOAT_CHANSTS_OFFSET(ver));
-	else
-		status = ioat_chansts_32(ioat_chan);
-
-	return status;
+	return readq(ioat_chan->reg_base + IOAT_CHANSTS_OFFSET);
 }
 
-#else
-#define ioat_chansts ioat_chansts_32
-#endif
-
 static inline u64 ioat_chansts_to_addr(u64 status)
 {
 	return status & IOAT_CHANSTS_COMPLETED_DESCRIPTOR_ADDR;

drivers/dma/ioat/registers.h

@@ -99,19 +99,9 @@
 #define IOAT_DMA_COMP_V1			0x0001	/* Compatibility with DMA version 1 */
 #define IOAT_DMA_COMP_V2			0x0002	/* Compatibility with DMA version 2 */
 
-
-#define IOAT1_CHANSTS_OFFSET		0x04	/* 64-bit Channel Status Register */
-#define IOAT2_CHANSTS_OFFSET		0x08	/* 64-bit Channel Status Register */
-#define IOAT_CHANSTS_OFFSET(ver)		((ver) < IOAT_VER_2_0 \
-						? IOAT1_CHANSTS_OFFSET : IOAT2_CHANSTS_OFFSET)
-#define IOAT1_CHANSTS_OFFSET_LOW	0x04
-#define IOAT2_CHANSTS_OFFSET_LOW	0x08
-#define IOAT_CHANSTS_OFFSET_LOW(ver)		((ver) < IOAT_VER_2_0 \
-						? IOAT1_CHANSTS_OFFSET_LOW : IOAT2_CHANSTS_OFFSET_LOW)
-#define IOAT1_CHANSTS_OFFSET_HIGH	0x08
-#define IOAT2_CHANSTS_OFFSET_HIGH	0x0C
-#define IOAT_CHANSTS_OFFSET_HIGH(ver)		((ver) < IOAT_VER_2_0 \
-						? IOAT1_CHANSTS_OFFSET_HIGH : IOAT2_CHANSTS_OFFSET_HIGH)
+/* IOAT1 define left for i7300_idle driver to not fail compiling */
+#define IOAT1_CHANSTS_OFFSET		0x04
+#define IOAT_CHANSTS_OFFSET		0x08	/* 64-bit Channel Status Register */
 #define IOAT_CHANSTS_COMPLETED_DESCRIPTOR_ADDR	(~0x3fULL)
 #define IOAT_CHANSTS_SOFT_ERR			0x10ULL
 #define IOAT_CHANSTS_UNAFFILIATED_ERR		0x8ULL

drivers/dma/mv_xor.c

@@ -139,46 +139,10 @@ static void mv_chan_clear_err_status(struct mv_xor_chan *chan)
 }
 
 static void mv_chan_set_mode(struct mv_xor_chan *chan,
-			     enum dma_transaction_type type)
+			     u32 op_mode)
 {
-	u32 op_mode;
 	u32 config = readl_relaxed(XOR_CONFIG(chan));
 
-	switch (type) {
-	case DMA_XOR:
-		op_mode = XOR_OPERATION_MODE_XOR;
-		break;
-	case DMA_MEMCPY:
-		op_mode = XOR_OPERATION_MODE_MEMCPY;
-		break;
-	default:
-		dev_err(mv_chan_to_devp(chan),
-			"error: unsupported operation %d\n",
-			type);
-		BUG();
-		return;
-	}
-
-	config &= ~0x7;
-	config |= op_mode;
-
-#if defined(__BIG_ENDIAN)
-	config |= XOR_DESCRIPTOR_SWAP;
-#else
-	config &= ~XOR_DESCRIPTOR_SWAP;
-#endif
-
-	writel_relaxed(config, XOR_CONFIG(chan));
-	chan->current_type = type;
-}
-
-static void mv_chan_set_mode_to_desc(struct mv_xor_chan *chan)
-{
-	u32 op_mode;
-	u32 config = readl_relaxed(XOR_CONFIG(chan));
-
-	op_mode = XOR_OPERATION_MODE_IN_DESC;
-
 	config &= ~0x7;
 	config |= op_mode;
 
@@ -1043,9 +1007,9 @@ mv_xor_channel_add(struct mv_xor_device *xordev,
 	mv_chan_unmask_interrupts(mv_chan);
 
 	if (mv_chan->op_in_desc == XOR_MODE_IN_DESC)
-		mv_chan_set_mode_to_desc(mv_chan);
+		mv_chan_set_mode(mv_chan, XOR_OPERATION_MODE_IN_DESC);
 	else
-		mv_chan_set_mode(mv_chan, DMA_XOR);
+		mv_chan_set_mode(mv_chan, XOR_OPERATION_MODE_XOR);
 
 	spin_lock_init(&mv_chan->lock);
 	INIT_LIST_HEAD(&mv_chan->chain);
@@ -1121,6 +1085,57 @@ mv_xor_conf_mbus_windows(struct mv_xor_device *xordev,
 	writel(0, base + WINDOW_OVERRIDE_CTRL(1));
 }
 
+/*
+ * Since this XOR driver is basically used only for RAID5, we don't
+ * need to care about synchronizing ->suspend with DMA activity,
+ * because the DMA engine will naturally be quiet due to the block
+ * devices being suspended.
+ */
+static int mv_xor_suspend(struct platform_device *pdev, pm_message_t state)
+{
+	struct mv_xor_device *xordev = platform_get_drvdata(pdev);
+	int i;
+
+	for (i = 0; i < MV_XOR_MAX_CHANNELS; i++) {
+		struct mv_xor_chan *mv_chan = xordev->channels[i];
+
+		if (!mv_chan)
+			continue;
+
+		mv_chan->saved_config_reg =
+			readl_relaxed(XOR_CONFIG(mv_chan));
+		mv_chan->saved_int_mask_reg =
+			readl_relaxed(XOR_INTR_MASK(mv_chan));
+	}
+
+	return 0;
+}
+
+static int mv_xor_resume(struct platform_device *dev)
+{
+	struct mv_xor_device *xordev = platform_get_drvdata(dev);
+	const struct mbus_dram_target_info *dram;
+	int i;
+
+	for (i = 0; i < MV_XOR_MAX_CHANNELS; i++) {
+		struct mv_xor_chan *mv_chan = xordev->channels[i];
+
+		if (!mv_chan)
+			continue;
+
+		writel_relaxed(mv_chan->saved_config_reg,
+			       XOR_CONFIG(mv_chan));
+		writel_relaxed(mv_chan->saved_int_mask_reg,
+			       XOR_INTR_MASK(mv_chan));
+	}
+
+	dram = mv_mbus_dram_info();
+	if (dram)
+		mv_xor_conf_mbus_windows(xordev, dram);
+
+	return 0;
+}
+
 static const struct of_device_id mv_xor_dt_ids[] = {
 	{ .compatible = "marvell,orion-xor", .data = (void *)XOR_MODE_IN_REG },
 	{ .compatible = "marvell,armada-380-xor", .data = (void *)XOR_MODE_IN_DESC },
@@ -1282,6 +1297,8 @@ static int mv_xor_probe(struct platform_device *pdev)
 
 static struct platform_driver mv_xor_driver = {
 	.probe		= mv_xor_probe,
+	.suspend        = mv_xor_suspend,
+	.resume         = mv_xor_resume,
 	.driver		= {
 		.name	        = MV_XOR_NAME,
 		.of_match_table = of_match_ptr(mv_xor_dt_ids),

drivers/dma/mv_xor.h

@@ -110,7 +110,6 @@ struct mv_xor_chan {
 	void __iomem		*mmr_high_base;
 	unsigned int		idx;
 	int                     irq;
-	enum dma_transaction_type	current_type;
 	struct list_head	chain;
 	struct list_head	free_slots;
 	struct list_head	allocated_slots;
@@ -126,6 +125,7 @@ struct mv_xor_chan {
 	char			dummy_src[MV_XOR_MIN_BYTE_COUNT];
 	char			dummy_dst[MV_XOR_MIN_BYTE_COUNT];
 	dma_addr_t		dummy_src_addr, dummy_dst_addr;
+	u32                     saved_config_reg, saved_int_mask_reg;
 };
 
 /**

drivers/dma/omap-dma.c

@@ -28,8 +28,6 @@
 struct omap_dmadev {
 	struct dma_device ddev;
 	spinlock_t lock;
-	struct tasklet_struct task;
-	struct list_head pending;
 	void __iomem *base;
 	const struct omap_dma_reg *reg_map;
 	struct omap_system_dma_plat_info *plat;
@@ -42,7 +40,6 @@ struct omap_dmadev {
 
 struct omap_chan {
 	struct virt_dma_chan vc;
-	struct list_head node;
 	void __iomem *channel_base;
 	const struct omap_dma_reg *reg_map;
 	uint32_t ccr;
@@ -454,33 +451,6 @@ static void omap_dma_callback(int ch, u16 status, void *data)
 	spin_unlock_irqrestore(&c->vc.lock, flags);
 }
 
-/*
- * This callback schedules all pending channels.  We could be more
- * clever here by postponing allocation of the real DMA channels to
- * this point, and freeing them when our virtual channel becomes idle.
- *
- * We would then need to deal with 'all channels in-use'
- */
-static void omap_dma_sched(unsigned long data)
-{
-	struct omap_dmadev *d = (struct omap_dmadev *)data;
-	LIST_HEAD(head);
-
-	spin_lock_irq(&d->lock);
-	list_splice_tail_init(&d->pending, &head);
-	spin_unlock_irq(&d->lock);
-
-	while (!list_empty(&head)) {
-		struct omap_chan *c = list_first_entry(&head,
-			struct omap_chan, node);
-
-		spin_lock_irq(&c->vc.lock);
-		list_del_init(&c->node);
-		omap_dma_start_desc(c);
-		spin_unlock_irq(&c->vc.lock);
-	}
-}
-
 static irqreturn_t omap_dma_irq(int irq, void *devid)
 {
 	struct omap_dmadev *od = devid;
@@ -703,8 +673,14 @@ static enum dma_status omap_dma_tx_status(struct dma_chan *chan,
 	struct omap_chan *c = to_omap_dma_chan(chan);
 	struct virt_dma_desc *vd;
 	enum dma_status ret;
+	uint32_t ccr;
 	unsigned long flags;
 
+	ccr = omap_dma_chan_read(c, CCR);
+	/* The channel is no longer active, handle the completion right away */
+	if (!(ccr & CCR_ENABLE))
+		omap_dma_callback(c->dma_ch, 0, c);
+
 	ret = dma_cookie_status(chan, cookie, txstate);
 	if (ret == DMA_COMPLETE || !txstate)
 		return ret;
@@ -719,7 +695,7 @@ static enum dma_status omap_dma_tx_status(struct dma_chan *chan,
 
 		if (d->dir == DMA_MEM_TO_DEV)
 			pos = omap_dma_get_src_pos(c);
-		else if (d->dir == DMA_DEV_TO_MEM)
+		else if (d->dir == DMA_DEV_TO_MEM  || d->dir == DMA_MEM_TO_MEM)
 			pos = omap_dma_get_dst_pos(c);
 		else
 			pos = 0;
@@ -739,22 +715,8 @@ static void omap_dma_issue_pending(struct dma_chan *chan)
 	unsigned long flags;
 
 	spin_lock_irqsave(&c->vc.lock, flags);
-	if (vchan_issue_pending(&c->vc) && !c->desc) {
-		/*
-		 * c->cyclic is used only by audio and in this case the DMA need
-		 * to be started without delay.
-		 */
-		if (!c->cyclic) {
-			struct omap_dmadev *d = to_omap_dma_dev(chan->device);
-			spin_lock(&d->lock);
-			if (list_empty(&c->node))
-				list_add_tail(&c->node, &d->pending);
-			spin_unlock(&d->lock);
-			tasklet_schedule(&d->task);
-		} else {
-			omap_dma_start_desc(c);
-		}
-	}
+	if (vchan_issue_pending(&c->vc) && !c->desc)
+		omap_dma_start_desc(c);
 	spin_unlock_irqrestore(&c->vc.lock, flags);
 }
 
@@ -768,7 +730,7 @@ static struct dma_async_tx_descriptor *omap_dma_prep_slave_sg(
 	struct scatterlist *sgent;
 	struct omap_desc *d;
 	dma_addr_t dev_addr;
-	unsigned i, j = 0, es, en, frame_bytes;
+	unsigned i, es, en, frame_bytes;
 	u32 burst;
 
 	if (dir == DMA_DEV_TO_MEM) {
@@ -845,13 +807,12 @@ static struct dma_async_tx_descriptor *omap_dma_prep_slave_sg(
 	en = burst;
 	frame_bytes = es_bytes[es] * en;
 	for_each_sg(sgl, sgent, sglen, i) {
-		d->sg[j].addr = sg_dma_address(sgent);
-		d->sg[j].en = en;
-		d->sg[j].fn = sg_dma_len(sgent) / frame_bytes;
-		j++;
+		d->sg[i].addr = sg_dma_address(sgent);
+		d->sg[i].en = en;
+		d->sg[i].fn = sg_dma_len(sgent) / frame_bytes;
 	}
 
-	d->sglen = j;
+	d->sglen = sglen;
 
 	return vchan_tx_prep(&c->vc, &d->vd, tx_flags);
 }
@@ -1018,17 +979,11 @@ static int omap_dma_slave_config(struct dma_chan *chan, struct dma_slave_config
 static int omap_dma_terminate_all(struct dma_chan *chan)
 {
 	struct omap_chan *c = to_omap_dma_chan(chan);
-	struct omap_dmadev *d = to_omap_dma_dev(c->vc.chan.device);
 	unsigned long flags;
 	LIST_HEAD(head);
 
 	spin_lock_irqsave(&c->vc.lock, flags);
 
-	/* Prevent this channel being scheduled */
-	spin_lock(&d->lock);
-	list_del_init(&c->node);
-	spin_unlock(&d->lock);
-
 	/*
 	 * Stop DMA activity: we assume the callback will not be called
 	 * after omap_dma_stop() returns (even if it does, it will see
@@ -1102,14 +1057,12 @@ static int omap_dma_chan_init(struct omap_dmadev *od)
 	c->reg_map = od->reg_map;
 	c->vc.desc_free = omap_dma_desc_free;
 	vchan_init(&c->vc, &od->ddev);
-	INIT_LIST_HEAD(&c->node);
 
 	return 0;
 }
 
 static void omap_dma_free(struct omap_dmadev *od)
 {
-	tasklet_kill(&od->task);
 	while (!list_empty(&od->ddev.channels)) {
 		struct omap_chan *c = list_first_entry(&od->ddev.channels,
 			struct omap_chan, vc.chan.device_node);
@@ -1165,12 +1118,9 @@ static int omap_dma_probe(struct platform_device *pdev)
 	od->ddev.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
 	od->ddev.dev = &pdev->dev;
 	INIT_LIST_HEAD(&od->ddev.channels);
-	INIT_LIST_HEAD(&od->pending);
 	spin_lock_init(&od->lock);
 	spin_lock_init(&od->irq_lock);
 
-	tasklet_init(&od->task, omap_dma_sched, (unsigned long)od);
-
 	od->dma_requests = OMAP_SDMA_REQUESTS;
 	if (pdev->dev.of_node && of_property_read_u32(pdev->dev.of_node,
 						      "dma-requests",
@@ -1203,6 +1153,10 @@ static int omap_dma_probe(struct platform_device *pdev)
 			return rc;
 	}
 
+	od->ddev.filter.map = od->plat->slave_map;
+	od->ddev.filter.mapcnt = od->plat->slavecnt;
+	od->ddev.filter.fn = omap_dma_filter_fn;
+
 	rc = dma_async_device_register(&od->ddev);
 	if (rc) {
 		pr_warn("OMAP-DMA: failed to register slave DMA engine device: %d\n",

drivers/dma/pxa_dma.c

@@ -1414,6 +1414,7 @@ static int pxad_probe(struct platform_device *op)
 	pdev->slave.dst_addr_widths = widths;
 	pdev->slave.directions = BIT(DMA_MEM_TO_DEV) | BIT(DMA_DEV_TO_MEM);
 	pdev->slave.residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR;
+	pdev->slave.descriptor_reuse = true;
 
 	pdev->slave.dev = &op->dev;
 	ret = pxad_init_dmadev(op, pdev, dma_channels);

drivers/dma/sh/Kconfig

@@ -47,12 +47,6 @@ config RCAR_DMAC
 	  This driver supports the general purpose DMA controller found in the
 	  Renesas R-Car second generation SoCs.
 
-config RCAR_HPB_DMAE
-	tristate "Renesas R-Car HPB DMAC support"
-	depends on SH_DMAE_BASE
-	help
-	  Enable support for the Renesas R-Car series DMA controllers.
-
 config RENESAS_USB_DMAC
 	tristate "Renesas USB-DMA Controller"
 	depends on ARCH_SHMOBILE || COMPILE_TEST

drivers/dma/sh/Makefile

@@ -14,6 +14,5 @@ shdma-objs := $(shdma-y)
 obj-$(CONFIG_SH_DMAE) += shdma.o
 
 obj-$(CONFIG_RCAR_DMAC) += rcar-dmac.o
-obj-$(CONFIG_RCAR_HPB_DMAE) += rcar-hpbdma.o
 obj-$(CONFIG_RENESAS_USB_DMAC) += usb-dmac.o
 obj-$(CONFIG_SUDMAC) += sudmac.o

drivers/dma/sh/usb-dmac.c

@@ -448,7 +448,7 @@ usb_dmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 static int usb_dmac_chan_terminate_all(struct dma_chan *chan)
 {
 	struct usb_dmac_chan *uchan = to_usb_dmac_chan(chan);
-	struct usb_dmac_desc *desc;
+	struct usb_dmac_desc *desc, *_desc;
 	unsigned long flags;
 	LIST_HEAD(head);
 	LIST_HEAD(list);
@@ -459,7 +459,7 @@ static int usb_dmac_chan_terminate_all(struct dma_chan *chan)
 	if (uchan->desc)
 		uchan->desc = NULL;
 	list_splice_init(&uchan->desc_got, &list);
-	list_for_each_entry(desc, &list, node)
+	list_for_each_entry_safe(desc, _desc, &list, node)
 		list_move_tail(&desc->node, &uchan->desc_freed);
 	spin_unlock_irqrestore(&uchan->vc.lock, flags);
 	vchan_dma_desc_free_list(&uchan->vc, &head);

drivers/dma/ste_dma40.c

@@ -3543,8 +3543,8 @@ static int __init d40_probe(struct platform_device *pdev)
 	struct stedma40_platform_data *plat_data = dev_get_platdata(&pdev->dev);
 	struct device_node *np = pdev->dev.of_node;
 	int ret = -ENOENT;
-	struct d40_base *base = NULL;
-	struct resource *res = NULL;
+	struct d40_base *base;
+	struct resource *res;
 	int num_reserved_chans;
 	u32 val;
 
@@ -3552,17 +3552,17 @@ static int __init d40_probe(struct platform_device *pdev)
 		if (np) {
 			if (d40_of_probe(pdev, np)) {
 				ret = -ENOMEM;
-				goto failure;
+				goto report_failure;
 			}
 		} else {
 			d40_err(&pdev->dev, "No pdata or Device Tree provided\n");
-			goto failure;
+			goto report_failure;
 		}
 	}
 
 	base = d40_hw_detect_init(pdev);
 	if (!base)
-		goto failure;
+		goto report_failure;
 
 	num_reserved_chans = d40_phy_res_init(base);
 
@@ -3693,51 +3693,48 @@ static int __init d40_probe(struct platform_device *pdev)
 	return 0;
 
 failure:
-	if (base) {
-		if (base->desc_slab)
-			kmem_cache_destroy(base->desc_slab);
-		if (base->virtbase)
-			iounmap(base->virtbase);
-
-		if (base->lcla_pool.base && base->plat_data->use_esram_lcla) {
-			iounmap(base->lcla_pool.base);
-			base->lcla_pool.base = NULL;
-		}
+	kmem_cache_destroy(base->desc_slab);
+	if (base->virtbase)
+		iounmap(base->virtbase);
 
-		if (base->lcla_pool.dma_addr)
-			dma_unmap_single(base->dev, base->lcla_pool.dma_addr,
-					 SZ_1K * base->num_phy_chans,
-					 DMA_TO_DEVICE);
-
-		if (!base->lcla_pool.base_unaligned && base->lcla_pool.base)
-			free_pages((unsigned long)base->lcla_pool.base,
-				   base->lcla_pool.pages);
-
-		kfree(base->lcla_pool.base_unaligned);
-
-		if (base->phy_lcpa)
-			release_mem_region(base->phy_lcpa,
-					   base->lcpa_size);
-		if (base->phy_start)
-			release_mem_region(base->phy_start,
-					   base->phy_size);
-		if (base->clk) {
-			clk_disable_unprepare(base->clk);
-			clk_put(base->clk);
-		}
+	if (base->lcla_pool.base && base->plat_data->use_esram_lcla) {
+		iounmap(base->lcla_pool.base);
+		base->lcla_pool.base = NULL;
+	}
 
-		if (base->lcpa_regulator) {
-			regulator_disable(base->lcpa_regulator);
-			regulator_put(base->lcpa_regulator);
-		}
+	if (base->lcla_pool.dma_addr)
+		dma_unmap_single(base->dev, base->lcla_pool.dma_addr,
+				 SZ_1K * base->num_phy_chans,
+				 DMA_TO_DEVICE);
 
-		kfree(base->lcla_pool.alloc_map);
-		kfree(base->lookup_log_chans);
-		kfree(base->lookup_phy_chans);
-		kfree(base->phy_res);
-		kfree(base);
+	if (!base->lcla_pool.base_unaligned && base->lcla_pool.base)
+		free_pages((unsigned long)base->lcla_pool.base,
+			   base->lcla_pool.pages);
+
+	kfree(base->lcla_pool.base_unaligned);
+
+	if (base->phy_lcpa)
+		release_mem_region(base->phy_lcpa,
+				   base->lcpa_size);
+	if (base->phy_start)
+		release_mem_region(base->phy_start,
+				   base->phy_size);
+	if (base->clk) {
+		clk_disable_unprepare(base->clk);
+		clk_put(base->clk);
+	}
+
+	if (base->lcpa_regulator) {
+		regulator_disable(base->lcpa_regulator);
+		regulator_put(base->lcpa_regulator);
 	}
 
+	kfree(base->lcla_pool.alloc_map);
+	kfree(base->lookup_log_chans);
+	kfree(base->lookup_phy_chans);
+	kfree(base->phy_res);
+	kfree(base);
+report_failure:
 	d40_err(&pdev->dev, "probe failed\n");
 	return ret;
 }

drivers/dma/tegra20-apb-dma.c

@@ -296,7 +296,7 @@ static struct tegra_dma_desc *tegra_dma_desc_get(
 	spin_unlock_irqrestore(&tdc->lock, flags);
 
 	/* Allocate DMA desc */
-	dma_desc = kzalloc(sizeof(*dma_desc), GFP_ATOMIC);
+	dma_desc = kzalloc(sizeof(*dma_desc), GFP_NOWAIT);
 	if (!dma_desc) {
 		dev_err(tdc2dev(tdc), "dma_desc alloc failed\n");
 		return NULL;
@@ -336,7 +336,7 @@ static struct tegra_dma_sg_req *tegra_dma_sg_req_get(
 	}
 	spin_unlock_irqrestore(&tdc->lock, flags);
 
-	sg_req = kzalloc(sizeof(struct tegra_dma_sg_req), GFP_ATOMIC);
+	sg_req = kzalloc(sizeof(struct tegra_dma_sg_req), GFP_NOWAIT);
 	if (!sg_req)
 		dev_err(tdc2dev(tdc), "sg_req alloc failed\n");
 	return sg_req;
@@ -1186,10 +1186,12 @@ static int tegra_dma_alloc_chan_resources(struct dma_chan *dc)
 
 	dma_cookie_init(&tdc->dma_chan);
 	tdc->config_init = false;
-	ret = clk_prepare_enable(tdma->dma_clk);
+
+	ret = pm_runtime_get_sync(tdma->dev);
 	if (ret < 0)
-		dev_err(tdc2dev(tdc), "clk_prepare_enable failed: %d\n", ret);
-	return ret;
+		return ret;
+
+	return 0;
 }
 
 static void tegra_dma_free_chan_resources(struct dma_chan *dc)
@@ -1232,7 +1234,7 @@ static void tegra_dma_free_chan_resources(struct dma_chan *dc)
 		list_del(&sg_req->node);
 		kfree(sg_req);
 	}
-	clk_disable_unprepare(tdma->dma_clk);
+	pm_runtime_put(tdma->dev);
 
 	tdc->slave_id = 0;
 }
@@ -1356,20 +1358,14 @@ static int tegra_dma_probe(struct platform_device *pdev)
 	spin_lock_init(&tdma->global_lock);
 
 	pm_runtime_enable(&pdev->dev);
-	if (!pm_runtime_enabled(&pdev->dev)) {
+	if (!pm_runtime_enabled(&pdev->dev))
 		ret = tegra_dma_runtime_resume(&pdev->dev);
-		if (ret) {
-			dev_err(&pdev->dev, "dma_runtime_resume failed %d\n",
-				ret);
-			goto err_pm_disable;
-		}
-	}
+	else
+		ret = pm_runtime_get_sync(&pdev->dev);
 
-	/* Enable clock before accessing registers */
-	ret = clk_prepare_enable(tdma->dma_clk);
 	if (ret < 0) {
-		dev_err(&pdev->dev, "clk_prepare_enable failed: %d\n", ret);
-		goto err_pm_disable;
+		pm_runtime_disable(&pdev->dev);
+		return ret;
 	}
 
 	/* Reset DMA controller */
@@ -1382,7 +1378,7 @@ static int tegra_dma_probe(struct platform_device *pdev)
 	tdma_write(tdma, TEGRA_APBDMA_CONTROL, 0);
 	tdma_write(tdma, TEGRA_APBDMA_IRQ_MASK_SET, 0xFFFFFFFFul);
 
-	clk_disable_unprepare(tdma->dma_clk);
+	pm_runtime_put(&pdev->dev);
 
 	INIT_LIST_HEAD(&tdma->dma_dev.channels);
 	for (i = 0; i < cdata->nr_channels; i++) {
@@ -1400,8 +1396,7 @@ static int tegra_dma_probe(struct platform_device *pdev)
 		}
 		tdc->irq = res->start;
 		snprintf(tdc->name, sizeof(tdc->name), "apbdma.%d", i);
-		ret = devm_request_irq(&pdev->dev, tdc->irq,
-				tegra_dma_isr, 0, tdc->name, tdc);
+		ret = request_irq(tdc->irq, tegra_dma_isr, 0, tdc->name, tdc);
 		if (ret) {
 			dev_err(&pdev->dev,
 				"request_irq failed with err %d channel %d\n",
@@ -1482,10 +1477,11 @@ static int tegra_dma_probe(struct platform_device *pdev)
 err_irq:
 	while (--i >= 0) {
 		struct tegra_dma_channel *tdc = &tdma->channels[i];
+
+		free_irq(tdc->irq, tdc);
 		tasklet_kill(&tdc->tasklet);
 	}
 
-err_pm_disable:
 	pm_runtime_disable(&pdev->dev);
 	if (!pm_runtime_status_suspended(&pdev->dev))
 		tegra_dma_runtime_suspend(&pdev->dev);
@@ -1502,6 +1498,7 @@ static int tegra_dma_remove(struct platform_device *pdev)
 
 	for (i = 0; i < tdma->chip_data->nr_channels; ++i) {
 		tdc = &tdma->channels[i];
+		free_irq(tdc->irq, tdc);
 		tasklet_kill(&tdc->tasklet);
 	}
 
@@ -1514,8 +1511,7 @@ static int tegra_dma_remove(struct platform_device *pdev)
 
 static int tegra_dma_runtime_suspend(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct tegra_dma *tdma = platform_get_drvdata(pdev);
+	struct tegra_dma *tdma = dev_get_drvdata(dev);
 
 	clk_disable_unprepare(tdma->dma_clk);
 	return 0;
@@ -1523,8 +1519,7 @@ static int tegra_dma_runtime_suspend(struct device *dev)
 
 static int tegra_dma_runtime_resume(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct tegra_dma *tdma = platform_get_drvdata(pdev);
+	struct tegra_dma *tdma = dev_get_drvdata(dev);
 	int ret;
 
 	ret = clk_prepare_enable(tdma->dma_clk);
@@ -1543,7 +1538,7 @@ static int tegra_dma_pm_suspend(struct device *dev)
 	int ret;
 
 	/* Enable clock before accessing register */
-	ret = tegra_dma_runtime_resume(dev);
+	ret = pm_runtime_get_sync(dev);
 	if (ret < 0)
 		return ret;
 
@@ -1552,15 +1547,22 @@ static int tegra_dma_pm_suspend(struct device *dev)
 		struct tegra_dma_channel *tdc = &tdma->channels[i];
 		struct tegra_dma_channel_regs *ch_reg = &tdc->channel_reg;
 
+		/* Only save the state of DMA channels that are in use */
+		if (!tdc->config_init)
+			continue;
+
 		ch_reg->csr = tdc_read(tdc, TEGRA_APBDMA_CHAN_CSR);
 		ch_reg->ahb_ptr = tdc_read(tdc, TEGRA_APBDMA_CHAN_AHBPTR);
 		ch_reg->apb_ptr = tdc_read(tdc, TEGRA_APBDMA_CHAN_APBPTR);
 		ch_reg->ahb_seq = tdc_read(tdc, TEGRA_APBDMA_CHAN_AHBSEQ);
 		ch_reg->apb_seq = tdc_read(tdc, TEGRA_APBDMA_CHAN_APBSEQ);
+		if (tdma->chip_data->support_separate_wcount_reg)
+			ch_reg->wcount = tdc_read(tdc,
+						  TEGRA_APBDMA_CHAN_WCOUNT);
 	}
 
 	/* Disable clock */
-	tegra_dma_runtime_suspend(dev);
+	pm_runtime_put(dev);
 	return 0;
 }
 
@@ -1571,7 +1573,7 @@ static int tegra_dma_pm_resume(struct device *dev)
 	int ret;
 
 	/* Enable clock before accessing register */
-	ret = tegra_dma_runtime_resume(dev);
+	ret = pm_runtime_get_sync(dev);
 	if (ret < 0)
 		return ret;
 
@@ -1583,6 +1585,13 @@ static int tegra_dma_pm_resume(struct device *dev)
 		struct tegra_dma_channel *tdc = &tdma->channels[i];
 		struct tegra_dma_channel_regs *ch_reg = &tdc->channel_reg;
 
+		/* Only restore the state of DMA channels that are in use */
+		if (!tdc->config_init)
+			continue;
+
+		if (tdma->chip_data->support_separate_wcount_reg)
+			tdc_write(tdc, TEGRA_APBDMA_CHAN_WCOUNT,
+				  ch_reg->wcount);
 		tdc_write(tdc, TEGRA_APBDMA_CHAN_APBSEQ, ch_reg->apb_seq);
 		tdc_write(tdc, TEGRA_APBDMA_CHAN_APBPTR, ch_reg->apb_ptr);
 		tdc_write(tdc, TEGRA_APBDMA_CHAN_AHBSEQ, ch_reg->ahb_seq);
@@ -1592,16 +1601,14 @@ static int tegra_dma_pm_resume(struct device *dev)
 	}
 
 	/* Disable clock */
-	tegra_dma_runtime_suspend(dev);
+	pm_runtime_put(dev);
 	return 0;
 }
 #endif
 
 static const struct dev_pm_ops tegra_dma_dev_pm_ops = {
-#ifdef CONFIG_PM
-	.runtime_suspend = tegra_dma_runtime_suspend,
-	.runtime_resume = tegra_dma_runtime_resume,
-#endif
+	SET_RUNTIME_PM_OPS(tegra_dma_runtime_suspend, tegra_dma_runtime_resume,
+			   NULL)
 	SET_SYSTEM_SLEEP_PM_OPS(tegra_dma_pm_suspend, tegra_dma_pm_resume)
 };
 

drivers/dma/ti-dma-crossbar.c

@@ -12,7 +12,6 @@
 #include <linux/init.h>
 #include <linux/list.h>
 #include <linux/io.h>
-#include <linux/idr.h>
 #include <linux/of_address.h>
 #include <linux/of_device.h>
 #include <linux/of_dma.h>
@@ -198,7 +197,8 @@ struct ti_dra7_xbar_data {
 	void __iomem *iomem;
 
 	struct dma_router dmarouter;
-	struct idr map_idr;
+	struct mutex mutex;
+	unsigned long *dma_inuse;
 
 	u16 safe_val; /* Value to rest the crossbar lines */
 	u32 xbar_requests; /* number of DMA requests connected to XBAR */
@@ -225,7 +225,9 @@ static void ti_dra7_xbar_free(struct device *dev, void *route_data)
 		map->xbar_in, map->xbar_out);
 
 	ti_dra7_xbar_write(xbar->iomem, map->xbar_out, xbar->safe_val);
-	idr_remove(&xbar->map_idr, map->xbar_out);
+	mutex_lock(&xbar->mutex);
+	clear_bit(map->xbar_out, xbar->dma_inuse);
+	mutex_unlock(&xbar->mutex);
 	kfree(map);
 }
 
@@ -255,8 +257,17 @@ static void *ti_dra7_xbar_route_allocate(struct of_phandle_args *dma_spec,
 		return ERR_PTR(-ENOMEM);
 	}
 
-	map->xbar_out = idr_alloc(&xbar->map_idr, NULL, 0, xbar->dma_requests,
-				  GFP_KERNEL);
+	mutex_lock(&xbar->mutex);
+	map->xbar_out = find_first_zero_bit(xbar->dma_inuse,
+					    xbar->dma_requests);
+	mutex_unlock(&xbar->mutex);
+	if (map->xbar_out == xbar->dma_requests) {
+		dev_err(&pdev->dev, "Run out of free DMA requests\n");
+		kfree(map);
+		return ERR_PTR(-ENOMEM);
+	}
+	set_bit(map->xbar_out, xbar->dma_inuse);
+
 	map->xbar_in = (u16)dma_spec->args[0];
 
 	dma_spec->args[0] = map->xbar_out + xbar->dma_offset;
@@ -278,17 +289,29 @@ static const struct of_device_id ti_dra7_master_match[] = {
 		.compatible = "ti,edma3",
 		.data = (void *)TI_XBAR_EDMA_OFFSET,
 	},
+	{
+		.compatible = "ti,edma3-tpcc",
+		.data = (void *)TI_XBAR_EDMA_OFFSET,
+	},
 	{},
 };
 
+static inline void ti_dra7_xbar_reserve(int offset, int len, unsigned long *p)
+{
+	for (; len > 0; len--)
+		clear_bit(offset + (len - 1), p);
+}
+
 static int ti_dra7_xbar_probe(struct platform_device *pdev)
 {
 	struct device_node *node = pdev->dev.of_node;
 	const struct of_device_id *match;
 	struct device_node *dma_node;
 	struct ti_dra7_xbar_data *xbar;
+	struct property *prop;
 	struct resource *res;
 	u32 safe_val;
+	size_t sz;
 	void __iomem *iomem;
 	int i, ret;
 
@@ -299,8 +322,6 @@ static int ti_dra7_xbar_probe(struct platform_device *pdev)
 	if (!xbar)
 		return -ENOMEM;
 
-	idr_init(&xbar->map_idr);
-
 	dma_node = of_parse_phandle(node, "dma-masters", 0);
 	if (!dma_node) {
 		dev_err(&pdev->dev, "Can't get DMA master node\n");
@@ -322,6 +343,12 @@ static int ti_dra7_xbar_probe(struct platform_device *pdev)
 	}
 	of_node_put(dma_node);
 
+	xbar->dma_inuse = devm_kcalloc(&pdev->dev,
+				       BITS_TO_LONGS(xbar->dma_requests),
+				       sizeof(unsigned long), GFP_KERNEL);
+	if (!xbar->dma_inuse)
+		return -ENOMEM;
+
 	if (of_property_read_u32(node, "dma-requests", &xbar->xbar_requests)) {
 		dev_info(&pdev->dev,
 			 "Missing XBAR input information, using %u.\n",
@@ -332,6 +359,33 @@ static int ti_dra7_xbar_probe(struct platform_device *pdev)
 	if (!of_property_read_u32(node, "ti,dma-safe-map", &safe_val))
 		xbar->safe_val = (u16)safe_val;
 
+
+	prop = of_find_property(node, "ti,reserved-dma-request-ranges", &sz);
+	if (prop) {
+		const char pname[] = "ti,reserved-dma-request-ranges";
+		u32 (*rsv_events)[2];
+		size_t nelm = sz / sizeof(*rsv_events);
+		int i;
+
+		if (!nelm)
+			return -EINVAL;
+
+		rsv_events = kcalloc(nelm, sizeof(*rsv_events), GFP_KERNEL);
+		if (!rsv_events)
+			return -ENOMEM;
+
+		ret = of_property_read_u32_array(node, pname, (u32 *)rsv_events,
+						 nelm * 2);
+		if (ret)
+			return ret;
+
+		for (i = 0; i < nelm; i++) {
+			ti_dra7_xbar_reserve(rsv_events[i][0], rsv_events[i][1],
+					     xbar->dma_inuse);
+		}
+		kfree(rsv_events);
+	}
+
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	iomem = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(iomem))
@@ -343,18 +397,23 @@ static int ti_dra7_xbar_probe(struct platform_device *pdev)
 	xbar->dmarouter.route_free = ti_dra7_xbar_free;
 	xbar->dma_offset = (u32)match->data;
 
+	mutex_init(&xbar->mutex);
 	platform_set_drvdata(pdev, xbar);
 
 	/* Reset the crossbar */
-	for (i = 0; i < xbar->dma_requests; i++)
-		ti_dra7_xbar_write(xbar->iomem, i, xbar->safe_val);
+	for (i = 0; i < xbar->dma_requests; i++) {
+		if (!test_bit(i, xbar->dma_inuse))
+			ti_dra7_xbar_write(xbar->iomem, i, xbar->safe_val);
+	}
 
 	ret = of_dma_router_register(node, ti_dra7_xbar_route_allocate,
 				     &xbar->dmarouter);
 	if (ret) {
 		/* Restore the defaults for the crossbar */
-		for (i = 0; i < xbar->dma_requests; i++)
-			ti_dra7_xbar_write(xbar->iomem, i, i);
+		for (i = 0; i < xbar->dma_requests; i++) {
+			if (!test_bit(i, xbar->dma_inuse))
+				ti_dra7_xbar_write(xbar->iomem, i, i);
+		}
 	}
 
 	return ret;

drivers/dma/virt-dma.c

@@ -29,7 +29,7 @@ dma_cookie_t vchan_tx_submit(struct dma_async_tx_descriptor *tx)
 	spin_lock_irqsave(&vc->lock, flags);
 	cookie = dma_cookie_assign(tx);
 
-	list_add_tail(&vd->node, &vc->desc_submitted);
+	list_move_tail(&vd->node, &vc->desc_submitted);
 	spin_unlock_irqrestore(&vc->lock, flags);
 
 	dev_dbg(vc->chan.device->dev, "vchan %p: txd %p[%x]: submitted\n",
@@ -39,6 +39,33 @@ dma_cookie_t vchan_tx_submit(struct dma_async_tx_descriptor *tx)
 }
 EXPORT_SYMBOL_GPL(vchan_tx_submit);
 
+/**
+ * vchan_tx_desc_free - free a reusable descriptor
+ * @tx: the transfer
+ *
+ * This function frees a previously allocated reusable descriptor. The only
+ * other way is to clear the DMA_CTRL_REUSE flag and submit one last time the
+ * transfer.
+ *
+ * Returns 0 upon success
+ */
+int vchan_tx_desc_free(struct dma_async_tx_descriptor *tx)
+{
+	struct virt_dma_chan *vc = to_virt_chan(tx->chan);
+	struct virt_dma_desc *vd = to_virt_desc(tx);
+	unsigned long flags;
+
+	spin_lock_irqsave(&vc->lock, flags);
+	list_del(&vd->node);
+	spin_unlock_irqrestore(&vc->lock, flags);
+
+	dev_dbg(vc->chan.device->dev, "vchan %p: txd %p[%x]: freeing\n",
+		vc, vd, vd->tx.cookie);
+	vc->desc_free(vd);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(vchan_tx_desc_free);
+
 struct virt_dma_desc *vchan_find_desc(struct virt_dma_chan *vc,
 	dma_cookie_t cookie)
 {
@@ -83,8 +110,10 @@ static void vchan_complete(unsigned long arg)
 		cb_data = vd->tx.callback_param;
 
 		list_del(&vd->node);
-
-		vc->desc_free(vd);
+		if (dmaengine_desc_test_reuse(&vd->tx))
+			list_add(&vd->node, &vc->desc_allocated);
+		else
+			vc->desc_free(vd);
 
 		if (cb)
 			cb(cb_data);
@@ -96,9 +125,13 @@ void vchan_dma_desc_free_list(struct virt_dma_chan *vc, struct list_head *head)
 	while (!list_empty(head)) {
 		struct virt_dma_desc *vd = list_first_entry(head,
 			struct virt_dma_desc, node);
-		list_del(&vd->node);
-		dev_dbg(vc->chan.device->dev, "txd %p: freeing\n", vd);
-		vc->desc_free(vd);
+		if (dmaengine_desc_test_reuse(&vd->tx)) {
+			list_move_tail(&vd->node, &vc->desc_allocated);
+		} else {
+			dev_dbg(vc->chan.device->dev, "txd %p: freeing\n", vd);
+			list_del(&vd->node);
+			vc->desc_free(vd);
+		}
 	}
 }
 EXPORT_SYMBOL_GPL(vchan_dma_desc_free_list);
@@ -108,6 +141,7 @@ void vchan_init(struct virt_dma_chan *vc, struct dma_device *dmadev)
 	dma_cookie_init(&vc->chan);
 
 	spin_lock_init(&vc->lock);
+	INIT_LIST_HEAD(&vc->desc_allocated);
 	INIT_LIST_HEAD(&vc->desc_submitted);
 	INIT_LIST_HEAD(&vc->desc_issued);
 	INIT_LIST_HEAD(&vc->desc_completed);

drivers/dma/virt-dma.h

@@ -29,6 +29,7 @@ struct virt_dma_chan {
 	spinlock_t lock;
 
 	/* protected by vc.lock */
+	struct list_head desc_allocated;
 	struct list_head desc_submitted;
 	struct list_head desc_issued;
 	struct list_head desc_completed;
@@ -55,10 +56,17 @@ static inline struct dma_async_tx_descriptor *vchan_tx_prep(struct virt_dma_chan
 	struct virt_dma_desc *vd, unsigned long tx_flags)
 {
 	extern dma_cookie_t vchan_tx_submit(struct dma_async_tx_descriptor *);
+	extern int vchan_tx_desc_free(struct dma_async_tx_descriptor *);
+	unsigned long flags;
 
 	dma_async_tx_descriptor_init(&vd->tx, &vc->chan);
 	vd->tx.flags = tx_flags;
 	vd->tx.tx_submit = vchan_tx_submit;
+	vd->tx.desc_free = vchan_tx_desc_free;
+
+	spin_lock_irqsave(&vc->lock, flags);
+	list_add_tail(&vd->node, &vc->desc_allocated);
+	spin_unlock_irqrestore(&vc->lock, flags);
 
 	return &vd->tx;
 }
@@ -134,6 +142,7 @@ static inline struct virt_dma_desc *vchan_next_desc(struct virt_dma_chan *vc)
 static inline void vchan_get_all_descriptors(struct virt_dma_chan *vc,
 	struct list_head *head)
 {
+	list_splice_tail_init(&vc->desc_allocated, head);
 	list_splice_tail_init(&vc->desc_submitted, head);
 	list_splice_tail_init(&vc->desc_issued, head);
 	list_splice_tail_init(&vc->desc_completed, head);
@@ -141,14 +150,30 @@ static inline void vchan_get_all_descriptors(struct virt_dma_chan *vc,
 
 static inline void vchan_free_chan_resources(struct virt_dma_chan *vc)
 {
+	struct virt_dma_desc *vd;
 	unsigned long flags;
 	LIST_HEAD(head);
 
 	spin_lock_irqsave(&vc->lock, flags);
 	vchan_get_all_descriptors(vc, &head);
+	list_for_each_entry(vd, &head, node)
+		dmaengine_desc_clear_reuse(&vd->tx);
 	spin_unlock_irqrestore(&vc->lock, flags);
 
 	vchan_dma_desc_free_list(vc, &head);
 }
 
+/**
+ * vchan_synchronize() - synchronize callback execution to the current context
+ * @vc: virtual channel to synchronize
+ *
+ * Makes sure that all scheduled or active callbacks have finished running. For
+ * proper operation the caller has to ensure that no new callbacks are scheduled
+ * after the invocation of this function started.
+ */
+static inline void vchan_synchronize(struct virt_dma_chan *vc)
+{
+	tasklet_kill(&vc->task);
+}
+
 #endif

include/linux/dca.h

@@ -34,7 +34,7 @@ void dca_unregister_notify(struct notifier_block *nb);
 
 struct dca_provider {
 	struct list_head	node;
-	struct dca_ops		*ops;
+	const struct dca_ops	*ops;
 	struct device 		*cd;
 	int			 id;
 };
@@ -53,7 +53,8 @@ struct dca_ops {
 	int	(*dev_managed)      (struct dca_provider *, struct device *);
 };
 
-struct dca_provider *alloc_dca_provider(struct dca_ops *ops, int priv_size);
+struct dca_provider *alloc_dca_provider(const struct dca_ops *ops,
+					int priv_size);
 void free_dca_provider(struct dca_provider *dca);
 int register_dca_provider(struct dca_provider *dca, struct device *dev);
 void unregister_dca_provider(struct dca_provider *dca, struct device *dev);

include/linux/dmaengine.h

@@ -606,12 +606,39 @@ enum dmaengine_alignment {
 	DMAENGINE_ALIGN_64_BYTES = 6,
 };
 
+/**
+ * struct dma_slave_map - associates slave device and it's slave channel with
+ * parameter to be used by a filter function
+ * @devname: name of the device
+ * @slave: slave channel name
+ * @param: opaque parameter to pass to struct dma_filter.fn
+ */
+struct dma_slave_map {
+	const char *devname;
+	const char *slave;
+	void *param;
+};
+
+/**
+ * struct dma_filter - information for slave device/channel to filter_fn/param
+ * mapping
+ * @fn: filter function callback
+ * @mapcnt: number of slave device/channel in the map
+ * @map: array of channel to filter mapping data
+ */
+struct dma_filter {
+	dma_filter_fn fn;
+	int mapcnt;
+	const struct dma_slave_map *map;
+};
+
 /**
  * struct dma_device - info on the entity supplying DMA services
  * @chancnt: how many DMA channels are supported
  * @privatecnt: how many DMA channels are requested by dma_request_channel
  * @channels: the list of struct dma_chan
  * @global_node: list_head for global dma_device_list
+ * @filter: information for device/slave to filter function/param mapping
  * @cap_mask: one or more dma_capability flags
  * @max_xor: maximum number of xor sources, 0 if no capability
  * @max_pq: maximum number of PQ sources and PQ-continue capability
@@ -654,11 +681,14 @@ enum dmaengine_alignment {
  *	paused. Returns 0 or an error code
  * @device_terminate_all: Aborts all transfers on a channel. Returns 0
  *	or an error code
+ * @device_synchronize: Synchronizes the termination of a transfers to the
+ *  current context.
  * @device_tx_status: poll for transaction completion, the optional
  *	txstate parameter can be supplied with a pointer to get a
  *	struct with auxiliary transfer status information, otherwise the call
  *	will just return a simple status code
  * @device_issue_pending: push pending transactions to hardware
+ * @descriptor_reuse: a submitted transfer can be resubmitted after completion
  */
 struct dma_device {
 
@@ -666,6 +696,7 @@ struct dma_device {
 	unsigned int privatecnt;
 	struct list_head channels;
 	struct list_head global_node;
+	struct dma_filter filter;
 	dma_cap_mask_t  cap_mask;
 	unsigned short max_xor;
 	unsigned short max_pq;
@@ -681,6 +712,7 @@ struct dma_device {
 	u32 src_addr_widths;
 	u32 dst_addr_widths;
 	u32 directions;
+	bool descriptor_reuse;
 	enum dma_residue_granularity residue_granularity;
 
 	int (*device_alloc_chan_resources)(struct dma_chan *chan);
@@ -737,6 +769,7 @@ struct dma_device {
 	int (*device_pause)(struct dma_chan *chan);
 	int (*device_resume)(struct dma_chan *chan);
 	int (*device_terminate_all)(struct dma_chan *chan);
+	void (*device_synchronize)(struct dma_chan *chan);
 
 	enum dma_status (*device_tx_status)(struct dma_chan *chan,
 					    dma_cookie_t cookie,
@@ -828,6 +861,13 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_sg(
 			src_sg, src_nents, flags);
 }
 
+/**
+ * dmaengine_terminate_all() - Terminate all active DMA transfers
+ * @chan: The channel for which to terminate the transfers
+ *
+ * This function is DEPRECATED use either dmaengine_terminate_sync() or
+ * dmaengine_terminate_async() instead.
+ */
 static inline int dmaengine_terminate_all(struct dma_chan *chan)
 {
 	if (chan->device->device_terminate_all)
@@ -836,6 +876,88 @@ static inline int dmaengine_terminate_all(struct dma_chan *chan)
 	return -ENOSYS;
 }
 
+/**
+ * dmaengine_terminate_async() - Terminate all active DMA transfers
+ * @chan: The channel for which to terminate the transfers
+ *
+ * Calling this function will terminate all active and pending descriptors
+ * that have previously been submitted to the channel. It is not guaranteed
+ * though that the transfer for the active descriptor has stopped when the
+ * function returns. Furthermore it is possible the complete callback of a
+ * submitted transfer is still running when this function returns.
+ *
+ * dmaengine_synchronize() needs to be called before it is safe to free
+ * any memory that is accessed by previously submitted descriptors or before
+ * freeing any resources accessed from within the completion callback of any
+ * perviously submitted descriptors.
+ *
+ * This function can be called from atomic context as well as from within a
+ * complete callback of a descriptor submitted on the same channel.
+ *
+ * If none of the two conditions above apply consider using
+ * dmaengine_terminate_sync() instead.
+ */
+static inline int dmaengine_terminate_async(struct dma_chan *chan)
+{
+	if (chan->device->device_terminate_all)
+		return chan->device->device_terminate_all(chan);
+
+	return -EINVAL;
+}
+
+/**
+ * dmaengine_synchronize() - Synchronize DMA channel termination
+ * @chan: The channel to synchronize
+ *
+ * Synchronizes to the DMA channel termination to the current context. When this
+ * function returns it is guaranteed that all transfers for previously issued
+ * descriptors have stopped and and it is safe to free the memory assoicated
+ * with them. Furthermore it is guaranteed that all complete callback functions
+ * for a previously submitted descriptor have finished running and it is safe to
+ * free resources accessed from within the complete callbacks.
+ *
+ * The behavior of this function is undefined if dma_async_issue_pending() has
+ * been called between dmaengine_terminate_async() and this function.
+ *
+ * This function must only be called from non-atomic context and must not be
+ * called from within a complete callback of a descriptor submitted on the same
+ * channel.
+ */
+static inline void dmaengine_synchronize(struct dma_chan *chan)
+{
+	might_sleep();
+
+	if (chan->device->device_synchronize)
+		chan->device->device_synchronize(chan);
+}
+
+/**
+ * dmaengine_terminate_sync() - Terminate all active DMA transfers
+ * @chan: The channel for which to terminate the transfers
+ *
+ * Calling this function will terminate all active and pending transfers
+ * that have previously been submitted to the channel. It is similar to
+ * dmaengine_terminate_async() but guarantees that the DMA transfer has actually
+ * stopped and that all complete callbacks have finished running when the
+ * function returns.
+ *
+ * This function must only be called from non-atomic context and must not be
+ * called from within a complete callback of a descriptor submitted on the same
+ * channel.
+ */
+static inline int dmaengine_terminate_sync(struct dma_chan *chan)
+{
+	int ret;
+
+	ret = dmaengine_terminate_async(chan);
+	if (ret)
+		return ret;
+
+	dmaengine_synchronize(chan);
+
+	return 0;
+}
+
 static inline int dmaengine_pause(struct dma_chan *chan)
 {
 	if (chan->device->device_pause)
@@ -1140,9 +1262,11 @@ enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx);
 void dma_issue_pending_all(void);
 struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask,
 					dma_filter_fn fn, void *fn_param);
-struct dma_chan *dma_request_slave_channel_reason(struct device *dev,
-						  const char *name);
 struct dma_chan *dma_request_slave_channel(struct device *dev, const char *name);
+
+struct dma_chan *dma_request_chan(struct device *dev, const char *name);
+struct dma_chan *dma_request_chan_by_mask(const dma_cap_mask_t *mask);
+
 void dma_release_channel(struct dma_chan *chan);
 int dma_get_slave_caps(struct dma_chan *chan, struct dma_slave_caps *caps);
 #else
@@ -1166,16 +1290,21 @@ static inline struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask,
 {
 	return NULL;
 }
-static inline struct dma_chan *dma_request_slave_channel_reason(
-					struct device *dev, const char *name)
-{
-	return ERR_PTR(-ENODEV);
-}
 static inline struct dma_chan *dma_request_slave_channel(struct device *dev,
 							 const char *name)
 {
 	return NULL;
 }
+static inline struct dma_chan *dma_request_chan(struct device *dev,
+						const char *name)
+{
+	return ERR_PTR(-ENODEV);
+}
+static inline struct dma_chan *dma_request_chan_by_mask(
+						const dma_cap_mask_t *mask)
+{
+	return ERR_PTR(-ENODEV);
+}
 static inline void dma_release_channel(struct dma_chan *chan)
 {
 }
@@ -1186,6 +1315,8 @@ static inline int dma_get_slave_caps(struct dma_chan *chan,
 }
 #endif
 
+#define dma_request_slave_channel_reason(dev, name) dma_request_chan(dev, name)
+
 static inline int dmaengine_desc_set_reuse(struct dma_async_tx_descriptor *tx)
 {
 	struct dma_slave_caps caps;

include/linux/omap-dma.h

@@ -267,6 +267,9 @@ struct omap_dma_reg {
 	u8	type;
 };
 
+#define SDMA_FILTER_PARAM(hw_req)	((int[]) { (hw_req) })
+struct dma_slave_map;
+
 /* System DMA platform data structure */
 struct omap_system_dma_plat_info {
 	const struct omap_dma_reg *reg_map;
@@ -278,6 +281,9 @@ struct omap_system_dma_plat_info {
 	void (*clear_dma)(int lch);
 	void (*dma_write)(u32 val, int reg, int lch);
 	u32 (*dma_read)(int reg, int lch);
+
+	const struct dma_slave_map *slave_map;
+	int slavecnt;
 };
 
 #ifdef CONFIG_ARCH_OMAP2PLUS

include/linux/platform_data/dma-rcar-hpbdma.h

-/*
- * Copyright (C) 2011-2013 Renesas Electronics Corporation
- * Copyright (C) 2013 Cogent Embedded, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation.
- */
-
-#ifndef __DMA_RCAR_HPBDMA_H
-#define __DMA_RCAR_HPBDMA_H
-
-#include <linux/bitops.h>
-#include <linux/types.h>
-
-/* Transmit sizes and respective register values */
-enum {
-	XMIT_SZ_8BIT	= 0,
-	XMIT_SZ_16BIT	= 1,
-	XMIT_SZ_32BIT	= 2,
-	XMIT_SZ_MAX
-};
-
-/* DMA control register (DCR) bits */
-#define HPB_DMAE_DCR_DTAMD		(1u << 26)
-#define HPB_DMAE_DCR_DTAC		(1u << 25)
-#define HPB_DMAE_DCR_DTAU		(1u << 24)
-#define HPB_DMAE_DCR_DTAU1		(1u << 23)
-#define HPB_DMAE_DCR_SWMD		(1u << 22)
-#define HPB_DMAE_DCR_BTMD		(1u << 21)
-#define HPB_DMAE_DCR_PKMD		(1u << 20)
-#define HPB_DMAE_DCR_CT			(1u << 18)
-#define HPB_DMAE_DCR_ACMD		(1u << 17)
-#define HPB_DMAE_DCR_DIP		(1u << 16)
-#define HPB_DMAE_DCR_SMDL		(1u << 13)
-#define HPB_DMAE_DCR_SPDAM		(1u << 12)
-#define HPB_DMAE_DCR_SDRMD_MASK		(3u << 10)
-#define HPB_DMAE_DCR_SDRMD_MOD		(0u << 10)
-#define HPB_DMAE_DCR_SDRMD_AUTO		(1u << 10)
-#define HPB_DMAE_DCR_SDRMD_TIMER	(2u << 10)
-#define HPB_DMAE_DCR_SPDS_MASK		(3u << 8)
-#define HPB_DMAE_DCR_SPDS_8BIT		(0u << 8)
-#define HPB_DMAE_DCR_SPDS_16BIT		(1u << 8)
-#define HPB_DMAE_DCR_SPDS_32BIT		(2u << 8)
-#define HPB_DMAE_DCR_DMDL		(1u << 5)
-#define HPB_DMAE_DCR_DPDAM		(1u << 4)
-#define HPB_DMAE_DCR_DDRMD_MASK		(3u << 2)
-#define HPB_DMAE_DCR_DDRMD_MOD		(0u << 2)
-#define HPB_DMAE_DCR_DDRMD_AUTO		(1u << 2)
-#define HPB_DMAE_DCR_DDRMD_TIMER	(2u << 2)
-#define HPB_DMAE_DCR_DPDS_MASK		(3u << 0)
-#define HPB_DMAE_DCR_DPDS_8BIT		(0u << 0)
-#define HPB_DMAE_DCR_DPDS_16BIT		(1u << 0)
-#define HPB_DMAE_DCR_DPDS_32BIT		(2u << 0)
-
-/* Asynchronous reset register (ASYNCRSTR) bits */
-#define HPB_DMAE_ASYNCRSTR_ASRST41	BIT(10)
-#define HPB_DMAE_ASYNCRSTR_ASRST40	BIT(9)
-#define HPB_DMAE_ASYNCRSTR_ASRST39	BIT(8)
-#define HPB_DMAE_ASYNCRSTR_ASRST27	BIT(7)
-#define HPB_DMAE_ASYNCRSTR_ASRST26	BIT(6)
-#define HPB_DMAE_ASYNCRSTR_ASRST25	BIT(5)
-#define HPB_DMAE_ASYNCRSTR_ASRST24	BIT(4)
-#define HPB_DMAE_ASYNCRSTR_ASRST23	BIT(3)
-#define HPB_DMAE_ASYNCRSTR_ASRST22	BIT(2)
-#define HPB_DMAE_ASYNCRSTR_ASRST21	BIT(1)
-#define HPB_DMAE_ASYNCRSTR_ASRST20	BIT(0)
-
-struct hpb_dmae_slave_config {
-	unsigned int	id;
-	dma_addr_t	addr;
-	u32		dcr;
-	u32		port;
-	u32		rstr;
-	u32		mdr;
-	u32		mdm;
-	u32		flags;
-#define	HPB_DMAE_SET_ASYNC_RESET	BIT(0)
-#define	HPB_DMAE_SET_ASYNC_MODE		BIT(1)
-	u32		dma_ch;
-};
-
-#define HPB_DMAE_CHANNEL(_irq, _s_id)	\
-{					\
-	.ch_irq		= _irq,		\
-	.s_id		= _s_id,	\
-}
-
-struct hpb_dmae_channel {
-	unsigned int	ch_irq;
-	unsigned int	s_id;
-};
-
-struct hpb_dmae_pdata {
-	const struct hpb_dmae_slave_config *slaves;
-	int num_slaves;
-	const struct hpb_dmae_channel *channels;
-	int num_channels;
-	const unsigned int ts_shift[XMIT_SZ_MAX];
-	int num_hw_channels;
-};
-
-#endif

include/linux/platform_data/edma.h

@@ -53,12 +53,16 @@ enum dma_event_q {
 #define EDMA_CTLR(i)			((i) >> 16)
 #define EDMA_CHAN_SLOT(i)		((i) & 0xffff)
 
+#define EDMA_FILTER_PARAM(ctlr, chan)	((int[]) { EDMA_CTLR_CHAN(ctlr, chan) })
+
 struct edma_rsv_info {
 
 	const s16	(*rsv_chans)[2];
 	const s16	(*rsv_slots)[2];
 };
 
+struct dma_slave_map;
+
 /* platform_data for EDMA driver */
 struct edma_soc_info {
 	/*
@@ -76,6 +80,9 @@ struct edma_soc_info {
 
 	s8	(*queue_priority_mapping)[2];
 	const s16	(*xbar_chans)[2];
+
+	const struct dma_slave_map *slave_map;
+	int slavecnt;
 };
 
 #endif

sound/core/pcm_dmaengine.c

@@ -202,13 +202,13 @@ int snd_dmaengine_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 		if (runtime->info & SNDRV_PCM_INFO_PAUSE)
 			dmaengine_pause(prtd->dma_chan);
 		else
-			dmaengine_terminate_all(prtd->dma_chan);
+			dmaengine_terminate_async(prtd->dma_chan);
 		break;
 	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
 		dmaengine_pause(prtd->dma_chan);
 		break;
 	case SNDRV_PCM_TRIGGER_STOP:
-		dmaengine_terminate_all(prtd->dma_chan);
+		dmaengine_terminate_async(prtd->dma_chan);
 		break;
 	default:
 		return -EINVAL;
@@ -346,6 +346,7 @@ int snd_dmaengine_pcm_close(struct snd_pcm_substream *substream)
 {
 	struct dmaengine_pcm_runtime_data *prtd = substream_to_prtd(substream);
 
+	dmaengine_synchronize(prtd->dma_chan);
 	kfree(prtd);
 
 	return 0;
@@ -362,9 +363,11 @@ int snd_dmaengine_pcm_close_release_chan(struct snd_pcm_substream *substream)
 {
 	struct dmaengine_pcm_runtime_data *prtd = substream_to_prtd(substream);
 
+	dmaengine_synchronize(prtd->dma_chan);
 	dma_release_channel(prtd->dma_chan);
+	kfree(prtd);
 
-	return snd_dmaengine_pcm_close(substream);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(snd_dmaengine_pcm_close_release_chan);