Merge branch 'topic/virt-dma' into for-linus
diff --git a/Documentation/devicetree/bindings/dma/qcom_hidma_mgmt.txt b/Documentation/devicetree/bindings/dma/qcom_hidma_mgmt.txt
index 55492c2..5d93d6d 100644
--- a/Documentation/devicetree/bindings/dma/qcom_hidma_mgmt.txt
+++ b/Documentation/devicetree/bindings/dma/qcom_hidma_mgmt.txt
@@ -47,8 +47,8 @@
 the channel nodes appear on their own, not under a management node.
 
 Required properties:
-- compatible: must contain "qcom,hidma-1.0" for initial HW or "qcom,hidma-1.1"
-for MSI capable HW.
+- compatible: must contain "qcom,hidma-1.0" for initial HW or
+  "qcom,hidma-1.1"/"qcom,hidma-1.2" for MSI capable HW.
 - reg: Addresses for the transfer and event channel
 - interrupts: Should contain the event interrupt
 - desc-count: Number of asynchronous requests this channel can handle
diff --git a/Documentation/driver-api/dmaengine/provider.rst b/Documentation/driver-api/dmaengine/provider.rst
index 814acb4..dfc4486 100644
--- a/Documentation/driver-api/dmaengine/provider.rst
+++ b/Documentation/driver-api/dmaengine/provider.rst
@@ -111,40 +111,36 @@
 structure. Any of the usual memory allocators will do, but you'll also
 need to initialize a few fields in there:
 
-- channels: should be initialized as a list using the
+- ``channels``: should be initialized as a list using the
   INIT_LIST_HEAD macro for example
 
-- src_addr_widths:
+- ``src_addr_widths``:
   should contain a bitmask of the supported source transfer width
 
-- dst_addr_widths:
+- ``dst_addr_widths``:
   should contain a bitmask of the supported destination transfer width
 
-- directions:
+- ``directions``:
   should contain a bitmask of the supported slave directions
   (i.e. excluding mem2mem transfers)
 
-- residue_granularity:
+- ``residue_granularity``:
+  granularity of the transfer residue reported to dma_set_residue.
+  This can be either:
 
-  - Granularity of the transfer residue reported to dma_set_residue.
-    This can be either:
+  - Descriptor:
+    your device doesn't support any kind of residue
+    reporting. The framework will only know that a particular
+    transaction descriptor is done.
 
-  - Descriptor
+  - Segment:
+    your device is able to report which chunks have been transferred
 
-    - Your device doesn't support any kind of residue
-      reporting. The framework will only know that a particular
-      transaction descriptor is done.
+  - Burst:
+    your device is able to report which burst have been transferred
 
-      - Segment
-
-        - Your device is able to report which chunks have been transferred
-
-      - Burst
-
-        - Your device is able to report which burst have been transferred
-
-  - dev: should hold the pointer to the ``struct device`` associated
-    to your current driver instance.
+- ``dev``: should hold the pointer to the ``struct device`` associated
+  to your current driver instance.
 
 Supported transaction types
 ---------------------------
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 4d0979e..f87ed3b 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -785,6 +785,24 @@ const struct acpi_device_id *acpi_match_device(const struct acpi_device_id *ids,
 }
 EXPORT_SYMBOL_GPL(acpi_match_device);
 
+void *acpi_get_match_data(const struct device *dev)
+{
+	const struct acpi_device_id *match;
+
+	if (!dev->driver)
+		return NULL;
+
+	if (!dev->driver->acpi_match_table)
+		return NULL;
+
+	match = acpi_match_device(dev->driver->acpi_match_table, dev);
+	if (!match)
+		return NULL;
+
+	return (void *)match->driver_data;
+}
+EXPORT_SYMBOL_GPL(acpi_get_match_data);
+
 int acpi_match_device_ids(struct acpi_device *device,
 			  const struct acpi_device_id *ids)
 {
diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index e26ea20..466d150 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -1271,9 +1271,17 @@ static int acpi_fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode,
 	return 0;
 }
 
+static void *
+acpi_fwnode_device_get_match_data(const struct fwnode_handle *fwnode,
+				  const struct device *dev)
+{
+	return acpi_get_match_data(dev);
+}
+
 #define DECLARE_ACPI_FWNODE_OPS(ops) \
 	const struct fwnode_operations ops = {				\
 		.device_is_available = acpi_fwnode_device_is_available, \
+		.device_get_match_data = acpi_fwnode_device_get_match_data, \
 		.property_present = acpi_fwnode_property_present,	\
 		.property_read_int_array =				\
 			acpi_fwnode_property_read_int_array,		\
diff --git a/drivers/base/property.c b/drivers/base/property.c
index 851b1b6..09eaac9 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -1340,3 +1340,10 @@ int fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode,
 	return fwnode_call_int_op(fwnode, graph_parse_endpoint, endpoint);
 }
 EXPORT_SYMBOL(fwnode_graph_parse_endpoint);
+
+void *device_get_match_data(struct device *dev)
+{
+	return fwnode_call_ptr_op(dev_fwnode(dev), device_get_match_data,
+				  dev);
+}
+EXPORT_SYMBOL_GPL(device_get_match_data);
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index fbab271..a861b5b 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -708,7 +708,7 @@ atc_prep_dma_interleaved(struct dma_chan *chan,
 			 unsigned long flags)
 {
 	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
-	struct data_chunk	*first = xt->sgl;
+	struct data_chunk	*first;
 	struct at_desc		*desc = NULL;
 	size_t			xfer_count;
 	unsigned int		dwidth;
@@ -720,6 +720,8 @@ atc_prep_dma_interleaved(struct dma_chan *chan,
 	if (unlikely(!xt || xt->numf != 1 || !xt->frame_size))
 		return NULL;
 
+	first = xt->sgl;
+
 	dev_info(chan2dev(chan),
 		 "%s: src=%pad, dest=%pad, numf=%d, frame_size=%d, flags=0x%lx\n",
 		__func__, &xt->src_start, &xt->dst_start, xt->numf,
diff --git a/drivers/dma/cppi41.c b/drivers/dma/cppi41.c
index f7e965f..d9bee65 100644
--- a/drivers/dma/cppi41.c
+++ b/drivers/dma/cppi41.c
@@ -934,7 +934,7 @@ static bool cpp41_dma_filter_fn(struct dma_chan *chan, void *param)
 
 	BUILD_BUG_ON(ARRAY_SIZE(am335x_usb_queues_rx) !=
 		     ARRAY_SIZE(am335x_usb_queues_tx));
-	if (WARN_ON(cchan->port_num > ARRAY_SIZE(am335x_usb_queues_rx)))
+	if (WARN_ON(cchan->port_num >= ARRAY_SIZE(am335x_usb_queues_rx)))
 		return false;
 
 	cchan->q_num = queues[cchan->port_num].submit;
diff --git a/drivers/dma/dma-jz4740.c b/drivers/dma/dma-jz4740.c
index d50273f..afd5e10 100644
--- a/drivers/dma/dma-jz4740.c
+++ b/drivers/dma/dma-jz4740.c
@@ -555,7 +555,7 @@ static int jz4740_dma_probe(struct platform_device *pdev)
 
 	ret = dma_async_device_register(dd);
 	if (ret)
-		return ret;
+		goto err_clk;
 
 	irq = platform_get_irq(pdev, 0);
 	ret = request_irq(irq, jz4740_dma_irq, 0, dev_name(&pdev->dev), dmadev);
@@ -568,6 +568,8 @@ static int jz4740_dma_probe(struct platform_device *pdev)
 
 err_unregister:
 	dma_async_device_unregister(dd);
+err_clk:
+	clk_disable_unprepare(dmadev->clk);
 	return ret;
 }
 
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index 47edc7f..80cc2be 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -155,6 +155,12 @@ MODULE_PARM_DESC(run, "Run the test (default: false)");
 #define PATTERN_COUNT_MASK	0x1f
 #define PATTERN_MEMSET_IDX	0x01
 
+/* poor man's completion - we want to use wait_event_freezable() on it */
+struct dmatest_done {
+	bool			done;
+	wait_queue_head_t	*wait;
+};
+
 struct dmatest_thread {
 	struct list_head	node;
 	struct dmatest_info	*info;
@@ -165,6 +171,8 @@ struct dmatest_thread {
 	u8			**dsts;
 	u8			**udsts;
 	enum dma_transaction_type type;
+	wait_queue_head_t done_wait;
+	struct dmatest_done test_done;
 	bool			done;
 };
 
@@ -342,18 +350,25 @@ static unsigned int dmatest_verify(u8 **bufs, unsigned int start,
 	return error_count;
 }
 
-/* poor man's completion - we want to use wait_event_freezable() on it */
-struct dmatest_done {
-	bool			done;
-	wait_queue_head_t	*wait;
-};
 
 static void dmatest_callback(void *arg)
 {
 	struct dmatest_done *done = arg;
-
-	done->done = true;
-	wake_up_all(done->wait);
+	struct dmatest_thread *thread =
+		container_of(done, struct dmatest_thread, test_done);
+	if (!thread->done) {
+		done->done = true;
+		wake_up_all(done->wait);
+	} else {
+		/*
+		 * If thread->done, it means that this callback occurred
+		 * after the parent thread has cleaned up. This can
+		 * happen in the case that driver doesn't implement
+		 * the terminate_all() functionality and a dma operation
+		 * did not occur within the timeout period
+		 */
+		WARN(1, "dmatest: Kernel memory may be corrupted!!\n");
+	}
 }
 
 static unsigned int min_odd(unsigned int x, unsigned int y)
@@ -424,9 +439,8 @@ static unsigned long long dmatest_KBs(s64 runtime, unsigned long long len)
  */
 static int dmatest_func(void *data)
 {
-	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(done_wait);
 	struct dmatest_thread	*thread = data;
-	struct dmatest_done	done = { .wait = &done_wait };
+	struct dmatest_done	*done = &thread->test_done;
 	struct dmatest_info	*info;
 	struct dmatest_params	*params;
 	struct dma_chan		*chan;
@@ -673,9 +687,9 @@ static int dmatest_func(void *data)
 			continue;
 		}
 
-		done.done = false;
+		done->done = false;
 		tx->callback = dmatest_callback;
-		tx->callback_param = &done;
+		tx->callback_param = done;
 		cookie = tx->tx_submit(tx);
 
 		if (dma_submit_error(cookie)) {
@@ -688,21 +702,12 @@ static int dmatest_func(void *data)
 		}
 		dma_async_issue_pending(chan);
 
-		wait_event_freezable_timeout(done_wait, done.done,
+		wait_event_freezable_timeout(thread->done_wait, done->done,
 					     msecs_to_jiffies(params->timeout));
 
 		status = dma_async_is_tx_complete(chan, cookie, NULL, NULL);
 
-		if (!done.done) {
-			/*
-			 * We're leaving the timed out dma operation with
-			 * dangling pointer to done_wait.  To make this
-			 * correct, we'll need to allocate wait_done for
-			 * each test iteration and perform "who's gonna
-			 * free it this time?" dancing.  For now, just
-			 * leave it dangling.
-			 */
-			WARN(1, "dmatest: Kernel stack may be corrupted!!\n");
+		if (!done->done) {
 			dmaengine_unmap_put(um);
 			result("test timed out", total_tests, src_off, dst_off,
 			       len, 0);
@@ -789,7 +794,7 @@ static int dmatest_func(void *data)
 		dmatest_KBs(runtime, total_len), ret);
 
 	/* terminate all transfers on specified channels */
-	if (ret)
+	if (ret || failed_tests)
 		dmaengine_terminate_all(chan);
 
 	thread->done = true;
@@ -849,6 +854,8 @@ static int dmatest_add_threads(struct dmatest_info *info,
 		thread->info = info;
 		thread->chan = dtc->chan;
 		thread->type = type;
+		thread->test_done.wait = &thread->done_wait;
+		init_waitqueue_head(&thread->done_wait);
 		smp_wmb();
 		thread->task = kthread_create(dmatest_func, thread, "%s-%s%u",
 				dma_chan_name(chan), op, i);
diff --git a/drivers/dma/fsl-edma.c b/drivers/dma/fsl-edma.c
index 6775f2c..c756886 100644
--- a/drivers/dma/fsl-edma.c
+++ b/drivers/dma/fsl-edma.c
@@ -863,11 +863,11 @@ static void fsl_edma_irq_exit(
 	}
 }
 
-static void fsl_disable_clocks(struct fsl_edma_engine *fsl_edma)
+static void fsl_disable_clocks(struct fsl_edma_engine *fsl_edma, int nr_clocks)
 {
 	int i;
 
-	for (i = 0; i < DMAMUX_NR; i++)
+	for (i = 0; i < nr_clocks; i++)
 		clk_disable_unprepare(fsl_edma->muxclk[i]);
 }
 
@@ -904,25 +904,25 @@ static int fsl_edma_probe(struct platform_device *pdev)
 
 		res = platform_get_resource(pdev, IORESOURCE_MEM, 1 + i);
 		fsl_edma->muxbase[i] = devm_ioremap_resource(&pdev->dev, res);
-		if (IS_ERR(fsl_edma->muxbase[i]))
+		if (IS_ERR(fsl_edma->muxbase[i])) {
+			/* on error: disable all previously enabled clks */
+			fsl_disable_clocks(fsl_edma, i);
 			return PTR_ERR(fsl_edma->muxbase[i]);
+		}
 
 		sprintf(clkname, "dmamux%d", i);
 		fsl_edma->muxclk[i] = devm_clk_get(&pdev->dev, clkname);
 		if (IS_ERR(fsl_edma->muxclk[i])) {
 			dev_err(&pdev->dev, "Missing DMAMUX block clock.\n");
+			/* on error: disable all previously enabled clks */
+			fsl_disable_clocks(fsl_edma, i);
 			return PTR_ERR(fsl_edma->muxclk[i]);
 		}
 
 		ret = clk_prepare_enable(fsl_edma->muxclk[i]);
-		if (ret) {
-			/* disable only clks which were enabled on error */
-			for (; i >= 0; i--)
-				clk_disable_unprepare(fsl_edma->muxclk[i]);
-
-			dev_err(&pdev->dev, "DMAMUX clk block failed.\n");
-			return ret;
-		}
+		if (ret)
+			/* on error: disable all previously enabled clks */
+			fsl_disable_clocks(fsl_edma, i);
 
 	}
 
@@ -976,7 +976,7 @@ static int fsl_edma_probe(struct platform_device *pdev)
 	if (ret) {
 		dev_err(&pdev->dev,
 			"Can't register Freescale eDMA engine. (%d)\n", ret);
-		fsl_disable_clocks(fsl_edma);
+		fsl_disable_clocks(fsl_edma, DMAMUX_NR);
 		return ret;
 	}
 
@@ -985,7 +985,7 @@ static int fsl_edma_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev,
 			"Can't register Freescale eDMA of_dma. (%d)\n", ret);
 		dma_async_device_unregister(&fsl_edma->dma_dev);
-		fsl_disable_clocks(fsl_edma);
+		fsl_disable_clocks(fsl_edma, DMAMUX_NR);
 		return ret;
 	}
 
@@ -1015,7 +1015,7 @@ static int fsl_edma_remove(struct platform_device *pdev)
 	fsl_edma_cleanup_vchan(&fsl_edma->dma_dev);
 	of_dma_controller_free(np);
 	dma_async_device_unregister(&fsl_edma->dma_dev);
-	fsl_disable_clocks(fsl_edma);
+	fsl_disable_clocks(fsl_edma, DMAMUX_NR);
 
 	return 0;
 }
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index 2184881..e7db24c 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -1939,4 +1939,10 @@ module_platform_driver(sdma_driver);
 
 MODULE_AUTHOR("Sascha Hauer, Pengutronix <s.hauer@pengutronix.de>");
 MODULE_DESCRIPTION("i.MX SDMA driver");
+#if IS_ENABLED(CONFIG_SOC_IMX6Q)
+MODULE_FIRMWARE("imx/sdma/sdma-imx6q.bin");
+#endif
+#if IS_ENABLED(CONFIG_SOC_IMX7D)
+MODULE_FIRMWARE("imx/sdma/sdma-imx7d.bin");
+#endif
 MODULE_LICENSE("GPL");
diff --git a/drivers/dma/ioat/init.c b/drivers/dma/ioat/init.c
index 2f31d3d..7792a91 100644
--- a/drivers/dma/ioat/init.c
+++ b/drivers/dma/ioat/init.c
@@ -390,7 +390,7 @@ static int ioat_dma_self_test(struct ioatdma_device *ioat_dma)
 	if (memcmp(src, dest, IOAT_TEST_SIZE)) {
 		dev_err(dev, "Self-test copy failed compare, disabling\n");
 		err = -ENODEV;
-		goto free_resources;
+		goto unmap_dma;
 	}
 
 unmap_dma:
diff --git a/drivers/dma/mic_x100_dma.c b/drivers/dma/mic_x100_dma.c
index 5ba5714..94d7bd7 100644
--- a/drivers/dma/mic_x100_dma.c
+++ b/drivers/dma/mic_x100_dma.c
@@ -480,9 +480,7 @@ static int mic_dma_setup_irq(struct mic_dma_chan *ch)
 		to_mbus_hw_ops(ch)->request_threaded_irq(to_mbus_device(ch),
 			mic_dma_intr_handler, mic_dma_thread_fn,
 			"mic dma_channel", ch, ch->ch_num);
-	if (IS_ERR(ch->cookie))
-		return PTR_ERR(ch->cookie);
-	return 0;
+	return PTR_ERR_OR_ZERO(ch->cookie);
 }
 
 static inline void mic_dma_free_irq(struct mic_dma_chan *ch)
diff --git a/drivers/dma/qcom/hidma.c b/drivers/dma/qcom/hidma.c
index e366985..963cc52 100644
--- a/drivers/dma/qcom/hidma.c
+++ b/drivers/dma/qcom/hidma.c
@@ -50,6 +50,7 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/of_dma.h>
+#include <linux/of_device.h>
 #include <linux/property.h>
 #include <linux/delay.h>
 #include <linux/acpi.h>
@@ -104,6 +105,10 @@ static unsigned int nr_desc_prm;
 module_param(nr_desc_prm, uint, 0644);
 MODULE_PARM_DESC(nr_desc_prm, "number of descriptors (default: 0)");
 
+enum hidma_cap {
+	HIDMA_MSI_CAP = 1,
+	HIDMA_IDENTITY_CAP,
+};
 
 /* process completed descriptors */
 static void hidma_process_completed(struct hidma_chan *mchan)
@@ -736,25 +741,12 @@ static int hidma_request_msi(struct hidma_dev *dmadev,
 #endif
 }
 
-static bool hidma_msi_capable(struct device *dev)
+static bool hidma_test_capability(struct device *dev, enum hidma_cap test_cap)
 {
-	struct acpi_device *adev = ACPI_COMPANION(dev);
-	const char *of_compat;
-	int ret = -EINVAL;
+	enum hidma_cap cap;
 
-	if (!adev || acpi_disabled) {
-		ret = device_property_read_string(dev, "compatible",
-						  &of_compat);
-		if (ret)
-			return false;
-
-		ret = strcmp(of_compat, "qcom,hidma-1.1");
-	} else {
-#ifdef CONFIG_ACPI
-		ret = strcmp(acpi_device_hid(adev), "QCOM8062");
-#endif
-	}
-	return ret == 0;
+	cap = (enum hidma_cap) device_get_match_data(dev);
+	return cap ? ((cap & test_cap) > 0) : 0;
 }
 
 static int hidma_probe(struct platform_device *pdev)
@@ -834,8 +826,7 @@ static int hidma_probe(struct platform_device *pdev)
 	 * Determine the MSI capability of the platform. Old HW doesn't
 	 * support MSI.
 	 */
-	msi = hidma_msi_capable(&pdev->dev);
-
+	msi = hidma_test_capability(&pdev->dev, HIDMA_MSI_CAP);
 	device_property_read_u32(&pdev->dev, "desc-count",
 				 &dmadev->nr_descriptors);
 
@@ -848,7 +839,10 @@ static int hidma_probe(struct platform_device *pdev)
 	if (!dmadev->nr_descriptors)
 		dmadev->nr_descriptors = HIDMA_NR_DEFAULT_DESC;
 
-	dmadev->chidx = readl(dmadev->dev_trca + 0x28);
+	if (hidma_test_capability(&pdev->dev, HIDMA_IDENTITY_CAP))
+		dmadev->chidx = readl(dmadev->dev_trca + 0x40);
+	else
+		dmadev->chidx = readl(dmadev->dev_trca + 0x28);
 
 	/* Set DMA mask to 64 bits. */
 	rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
@@ -953,7 +947,8 @@ static int hidma_remove(struct platform_device *pdev)
 #if IS_ENABLED(CONFIG_ACPI)
 static const struct acpi_device_id hidma_acpi_ids[] = {
 	{"QCOM8061"},
-	{"QCOM8062"},
+	{"QCOM8062", HIDMA_MSI_CAP},
+	{"QCOM8063", (HIDMA_MSI_CAP | HIDMA_IDENTITY_CAP)},
 	{},
 };
 MODULE_DEVICE_TABLE(acpi, hidma_acpi_ids);
@@ -961,7 +956,9 @@ MODULE_DEVICE_TABLE(acpi, hidma_acpi_ids);
 
 static const struct of_device_id hidma_match[] = {
 	{.compatible = "qcom,hidma-1.0",},
-	{.compatible = "qcom,hidma-1.1",},
+	{.compatible = "qcom,hidma-1.1", .data = (void *)(HIDMA_MSI_CAP),},
+	{.compatible = "qcom,hidma-1.2",
+	 .data = (void *)(HIDMA_MSI_CAP | HIDMA_IDENTITY_CAP),},
 	{},
 };
 MODULE_DEVICE_TABLE(of, hidma_match);
diff --git a/drivers/dma/qcom/hidma_ll.c b/drivers/dma/qcom/hidma_ll.c
index 4999e26..7c6e2ff 100644
--- a/drivers/dma/qcom/hidma_ll.c
+++ b/drivers/dma/qcom/hidma_ll.c
@@ -393,6 +393,8 @@ static int hidma_ll_reset(struct hidma_lldev *lldev)
  */
 static void hidma_ll_int_handler_internal(struct hidma_lldev *lldev, int cause)
 {
+	unsigned long irqflags;
+
 	if (cause & HIDMA_ERR_INT_MASK) {
 		dev_err(lldev->dev, "error 0x%x, disabling...\n",
 				cause);
@@ -410,6 +412,10 @@ static void hidma_ll_int_handler_internal(struct hidma_lldev *lldev, int cause)
 		return;
 	}
 
+	spin_lock_irqsave(&lldev->lock, irqflags);
+	writel_relaxed(cause, lldev->evca + HIDMA_EVCA_IRQ_CLR_REG);
+	spin_unlock_irqrestore(&lldev->lock, irqflags);
+
 	/*
 	 * Fine tuned for this HW...
 	 *
@@ -421,9 +427,6 @@ static void hidma_ll_int_handler_internal(struct hidma_lldev *lldev, int cause)
 	 * Try to consume as many EVREs as possible.
 	 */
 	hidma_handle_tre_completion(lldev);
-
-	/* We consumed TREs or there are pending TREs or EVREs. */
-	writel_relaxed(cause, lldev->evca + HIDMA_EVCA_IRQ_CLR_REG);
 }
 
 irqreturn_t hidma_ll_inthandler(int chirq, void *arg)
diff --git a/drivers/dma/qcom/hidma_mgmt.c b/drivers/dma/qcom/hidma_mgmt.c
index 7335e2e..000c7019 100644
--- a/drivers/dma/qcom/hidma_mgmt.c
+++ b/drivers/dma/qcom/hidma_mgmt.c
@@ -17,6 +17,7 @@
 #include <linux/acpi.h>
 #include <linux/of.h>
 #include <linux/property.h>
+#include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
 #include <linux/module.h>
@@ -356,59 +357,29 @@ static int __init hidma_mgmt_of_populate_channels(struct device_node *np)
 {
 	struct platform_device *pdev_parent = of_find_device_by_node(np);
 	struct platform_device_info pdevinfo;
-	struct of_phandle_args out_irq;
 	struct device_node *child;
-	struct resource *res = NULL;
-	const __be32 *cell;
-	int ret = 0, size, i, num;
-	u64 addr, addr_size;
+	struct resource *res;
+	int ret = 0;
+
+	/* allocate a resource array */
+	res = kcalloc(3, sizeof(*res), GFP_KERNEL);
+	if (!res)
+		return -ENOMEM;
 
 	for_each_available_child_of_node(np, child) {
-		struct resource *res_iter;
 		struct platform_device *new_pdev;
 
-		cell = of_get_property(child, "reg", &size);
-		if (!cell) {
-			ret = -EINVAL;
-			goto out;
-		}
-
-		size /= sizeof(*cell);
-		num = size /
-			(of_n_addr_cells(child) + of_n_size_cells(child)) + 1;
-
-		/* allocate a resource array */
-		res = kcalloc(num, sizeof(*res), GFP_KERNEL);
-		if (!res) {
-			ret = -ENOMEM;
-			goto out;
-		}
-
-		/* read each reg value */
-		i = 0;
-		res_iter = res;
-		while (i < size) {
-			addr = of_read_number(&cell[i],
-					      of_n_addr_cells(child));
-			i += of_n_addr_cells(child);
-
-			addr_size = of_read_number(&cell[i],
-						   of_n_size_cells(child));
-			i += of_n_size_cells(child);
-
-			res_iter->start = addr;
-			res_iter->end = res_iter->start + addr_size - 1;
-			res_iter->flags = IORESOURCE_MEM;
-			res_iter++;
-		}
-
-		ret = of_irq_parse_one(child, 0, &out_irq);
-		if (ret)
+		ret = of_address_to_resource(child, 0, &res[0]);
+		if (!ret)
 			goto out;
 
-		res_iter->start = irq_create_of_mapping(&out_irq);
-		res_iter->name = "hidma event irq";
-		res_iter->flags = IORESOURCE_IRQ;
+		ret = of_address_to_resource(child, 1, &res[1]);
+		if (!ret)
+			goto out;
+
+		ret = of_irq_to_resource(child, 0, &res[2]);
+		if (ret <= 0)
+			goto out;
 
 		memset(&pdevinfo, 0, sizeof(pdevinfo));
 		pdevinfo.fwnode = &child->fwnode;
@@ -416,7 +387,7 @@ static int __init hidma_mgmt_of_populate_channels(struct device_node *np)
 		pdevinfo.name = child->name;
 		pdevinfo.id = object_counter++;
 		pdevinfo.res = res;
-		pdevinfo.num_res = num;
+		pdevinfo.num_res = 3;
 		pdevinfo.data = NULL;
 		pdevinfo.size_data = 0;
 		pdevinfo.dma_mask = DMA_BIT_MASK(64);
@@ -434,8 +405,6 @@ static int __init hidma_mgmt_of_populate_channels(struct device_node *np)
 		 */
 		of_msi_configure(&new_pdev->dev, child);
 		of_node_put(child);
-		kfree(res);
-		res = NULL;
 	}
 out:
 	kfree(res);
diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c
index 2b2c7db..3bbd11d 100644
--- a/drivers/dma/sh/rcar-dmac.c
+++ b/drivers/dma/sh/rcar-dmac.c
@@ -10,6 +10,7 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/delay.h>
 #include <linux/dma-mapping.h>
 #include <linux/dmaengine.h>
 #include <linux/interrupt.h>
@@ -741,6 +742,41 @@ static int rcar_dmac_fill_hwdesc(struct rcar_dmac_chan *chan,
 /* -----------------------------------------------------------------------------
  * Stop and reset
  */
+static void rcar_dmac_chcr_de_barrier(struct rcar_dmac_chan *chan)
+{
+	u32 chcr;
+	unsigned int i;
+
+	/*
+	 * Ensure that the setting of the DE bit is actually 0 after
+	 * clearing it.
+	 */
+	for (i = 0; i < 1024; i++) {
+		chcr = rcar_dmac_chan_read(chan, RCAR_DMACHCR);
+		if (!(chcr & RCAR_DMACHCR_DE))
+			return;
+		udelay(1);
+	}
+
+	dev_err(chan->chan.device->dev, "CHCR DE check error\n");
+}
+
+static void rcar_dmac_sync_tcr(struct rcar_dmac_chan *chan)
+{
+	u32 chcr = rcar_dmac_chan_read(chan, RCAR_DMACHCR);
+
+	if (!(chcr & RCAR_DMACHCR_DE))
+		return;
+
+	/* set DE=0 and flush remaining data */
+	rcar_dmac_chan_write(chan, RCAR_DMACHCR, (chcr & ~RCAR_DMACHCR_DE));
+
+	/* make sure all remaining data was flushed */
+	rcar_dmac_chcr_de_barrier(chan);
+
+	/* back DE */
+	rcar_dmac_chan_write(chan, RCAR_DMACHCR, chcr);
+}
 
 static void rcar_dmac_chan_halt(struct rcar_dmac_chan *chan)
 {
@@ -749,6 +785,7 @@ static void rcar_dmac_chan_halt(struct rcar_dmac_chan *chan)
 	chcr &= ~(RCAR_DMACHCR_DSE | RCAR_DMACHCR_DSIE | RCAR_DMACHCR_IE |
 		  RCAR_DMACHCR_TE | RCAR_DMACHCR_DE);
 	rcar_dmac_chan_write(chan, RCAR_DMACHCR, chcr);
+	rcar_dmac_chcr_de_barrier(chan);
 }
 
 static void rcar_dmac_chan_reinit(struct rcar_dmac_chan *chan)
@@ -1309,8 +1346,11 @@ static unsigned int rcar_dmac_chan_get_residue(struct rcar_dmac_chan *chan,
 		residue += chunk->size;
 	}
 
+	if (desc->direction == DMA_DEV_TO_MEM)
+		rcar_dmac_sync_tcr(chan);
+
 	/* Add the residue for the current chunk. */
-	residue += rcar_dmac_chan_read(chan, RCAR_DMATCR) << desc->xfer_shift;
+	residue += rcar_dmac_chan_read(chan, RCAR_DMATCRB) << desc->xfer_shift;
 
 	return residue;
 }
@@ -1481,6 +1521,8 @@ static irqreturn_t rcar_dmac_isr_channel(int irq, void *dev)
 	if (chcr & RCAR_DMACHCR_TE)
 		mask |= RCAR_DMACHCR_DE;
 	rcar_dmac_chan_write(chan, RCAR_DMACHCR, chcr & ~mask);
+	if (mask & RCAR_DMACHCR_DE)
+		rcar_dmac_chcr_de_barrier(chan);
 
 	if (chcr & RCAR_DMACHCR_DSE)
 		ret |= rcar_dmac_isr_desc_stage_end(chan);
diff --git a/drivers/dma/sprd-dma.c b/drivers/dma/sprd-dma.c
index b652071..b106e8a 100644
--- a/drivers/dma/sprd-dma.c
+++ b/drivers/dma/sprd-dma.c
@@ -710,7 +710,7 @@ static int sprd_dma_config(struct dma_chan *chan, struct sprd_dma_desc *sdesc,
 	return 0;
 }
 
-struct dma_async_tx_descriptor *
+static struct dma_async_tx_descriptor *
 sprd_dma_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 			 size_t len, unsigned long flags)
 {
diff --git a/drivers/dma/stm32-dmamux.c b/drivers/dma/stm32-dmamux.c
index d5db0f6..4dbb30c 100644
--- a/drivers/dma/stm32-dmamux.c
+++ b/drivers/dma/stm32-dmamux.c
@@ -253,9 +253,6 @@ static int stm32_dmamux_probe(struct platform_device *pdev)
 	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res)
-		return -ENODEV;
-
 	iomem = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(iomem))
 		return PTR_ERR(iomem);
diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c
index b9d75a5..9a558e3 100644
--- a/drivers/dma/tegra20-apb-dma.c
+++ b/drivers/dma/tegra20-apb-dma.c
@@ -353,7 +353,8 @@ static int tegra_dma_slave_config(struct dma_chan *dc,
 	}
 
 	memcpy(&tdc->dma_sconfig, sconfig, sizeof(*sconfig));
-	if (tdc->slave_id == TEGRA_APBDMA_SLAVE_ID_INVALID) {
+	if (tdc->slave_id == TEGRA_APBDMA_SLAVE_ID_INVALID &&
+	    sconfig->device_fc) {
 		if (sconfig->slave_id > TEGRA_APBDMA_CSR_REQ_SEL_MASK)
 			return -EINVAL;
 		tdc->slave_id = sconfig->slave_id;
@@ -970,8 +971,13 @@ static struct dma_async_tx_descriptor *tegra_dma_prep_slave_sg(
 					TEGRA_APBDMA_AHBSEQ_WRAP_SHIFT;
 	ahb_seq |= TEGRA_APBDMA_AHBSEQ_BUS_WIDTH_32;
 
-	csr |= TEGRA_APBDMA_CSR_ONCE | TEGRA_APBDMA_CSR_FLOW;
-	csr |= tdc->slave_id << TEGRA_APBDMA_CSR_REQ_SEL_SHIFT;
+	csr |= TEGRA_APBDMA_CSR_ONCE;
+
+	if (tdc->slave_id != TEGRA_APBDMA_SLAVE_ID_INVALID) {
+		csr |= TEGRA_APBDMA_CSR_FLOW;
+		csr |= tdc->slave_id << TEGRA_APBDMA_CSR_REQ_SEL_SHIFT;
+	}
+
 	if (flags & DMA_PREP_INTERRUPT)
 		csr |= TEGRA_APBDMA_CSR_IE_EOC;
 
@@ -1110,10 +1116,13 @@ static struct dma_async_tx_descriptor *tegra_dma_prep_dma_cyclic(
 					TEGRA_APBDMA_AHBSEQ_WRAP_SHIFT;
 	ahb_seq |= TEGRA_APBDMA_AHBSEQ_BUS_WIDTH_32;
 
-	csr |= TEGRA_APBDMA_CSR_FLOW;
+	if (tdc->slave_id != TEGRA_APBDMA_SLAVE_ID_INVALID) {
+		csr |= TEGRA_APBDMA_CSR_FLOW;
+		csr |= tdc->slave_id << TEGRA_APBDMA_CSR_REQ_SEL_SHIFT;
+	}
+
 	if (flags & DMA_PREP_INTERRUPT)
 		csr |= TEGRA_APBDMA_CSR_IE_EOC;
-	csr |= tdc->slave_id << TEGRA_APBDMA_CSR_REQ_SEL_SHIFT;
 
 	apb_seq |= TEGRA_APBDMA_APBSEQ_WRAP_WORD_1;
 
diff --git a/drivers/dma/ti-dma-crossbar.c b/drivers/dma/ti-dma-crossbar.c
index 7df910e..9272b17 100644
--- a/drivers/dma/ti-dma-crossbar.c
+++ b/drivers/dma/ti-dma-crossbar.c
@@ -54,7 +54,15 @@ struct ti_am335x_xbar_map {
 
 static inline void ti_am335x_xbar_write(void __iomem *iomem, int event, u8 val)
 {
-	writeb_relaxed(val, iomem + event);
+	/*
+	 * TPCC_EVT_MUX_60_63 register layout is different than the
+	 * rest, in the sense, that event 63 is mapped to lowest byte
+	 * and event 60 is mapped to highest, handle it separately.
+	 */
+	if (event >= 60 && event <= 63)
+		writeb_relaxed(val, iomem + (63 - event % 4));
+	else
+		writeb_relaxed(val, iomem + event);
 }
 
 static void ti_am335x_xbar_free(struct device *dev, void *route_data)
diff --git a/drivers/dma/timb_dma.c b/drivers/dma/timb_dma.c
index 896bafb..395c698 100644
--- a/drivers/dma/timb_dma.c
+++ b/drivers/dma/timb_dma.c
@@ -422,7 +422,7 @@ static int td_alloc_chan_resources(struct dma_chan *chan)
 				break;
 			else {
 				dev_err(chan2dev(chan),
-					"Couldnt allocate any descriptors\n");
+					"Couldn't allocate any descriptors\n");
 				return -ENOMEM;
 			}
 		}
diff --git a/drivers/of/property.c b/drivers/of/property.c
index 8ad33a4..f25d363 100644
--- a/drivers/of/property.c
+++ b/drivers/of/property.c
@@ -981,10 +981,18 @@ static int of_fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode,
 	return 0;
 }
 
+static void *
+of_fwnode_device_get_match_data(const struct fwnode_handle *fwnode,
+				const struct device *dev)
+{
+	return (void *)of_device_get_match_data(dev);
+}
+
 const struct fwnode_operations of_fwnode_ops = {
 	.get = of_fwnode_get,
 	.put = of_fwnode_put,
 	.device_is_available = of_fwnode_device_is_available,
+	.device_get_match_data = of_fwnode_device_get_match_data,
 	.property_present = of_fwnode_property_present,
 	.property_read_int_array = of_fwnode_property_read_int_array,
 	.property_read_string_array = of_fwnode_property_read_string_array,
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index dc1ebfe..9278737 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -584,6 +584,7 @@ extern int acpi_nvs_for_each_region(int (*func)(__u64, __u64, void *),
 const struct acpi_device_id *acpi_match_device(const struct acpi_device_id *ids,
 					       const struct device *dev);
 
+void *acpi_get_match_data(const struct device *dev);
 extern bool acpi_driver_match_device(struct device *dev,
 				     const struct device_driver *drv);
 int acpi_device_uevent_modalias(struct device *, struct kobj_uevent_env *);
@@ -755,6 +756,11 @@ static inline const struct acpi_device_id *acpi_match_device(
 	return NULL;
 }
 
+static inline void *acpi_get_match_data(const struct device *dev)
+{
+	return NULL;
+}
+
 static inline bool acpi_driver_match_device(struct device *dev,
 					    const struct device_driver *drv)
 {
diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h
index 411a84c..4fa1a48 100644
--- a/include/linux/fwnode.h
+++ b/include/linux/fwnode.h
@@ -15,6 +15,7 @@
 #include <linux/types.h>
 
 struct fwnode_operations;
+struct device;
 
 struct fwnode_handle {
 	struct fwnode_handle *secondary;
@@ -51,6 +52,7 @@ struct fwnode_reference_args {
  * struct fwnode_operations - Operations for fwnode interface
  * @get: Get a reference to an fwnode.
  * @put: Put a reference to an fwnode.
+ * @device_get_match_data: Return the device driver match data.
  * @property_present: Return true if a property is present.
  * @property_read_integer_array: Read an array of integer properties. Return
  *				 zero on success, a negative error code
@@ -71,6 +73,8 @@ struct fwnode_operations {
 	struct fwnode_handle *(*get)(struct fwnode_handle *fwnode);
 	void (*put)(struct fwnode_handle *fwnode);
 	bool (*device_is_available)(const struct fwnode_handle *fwnode);
+	void *(*device_get_match_data)(const struct fwnode_handle *fwnode,
+				       const struct device *dev);
 	bool (*property_present)(const struct fwnode_handle *fwnode,
 				 const char *propname);
 	int (*property_read_int_array)(const struct fwnode_handle *fwnode,
diff --git a/include/linux/property.h b/include/linux/property.h
index f6189a3..6653ed4 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -275,6 +275,8 @@ bool device_dma_supported(struct device *dev);
 
 enum dev_dma_attr device_get_dma_attr(struct device *dev);
 
+void *device_get_match_data(struct device *dev);
+
 int device_get_phy_mode(struct device *dev);
 
 void *device_get_mac_address(struct device *dev, char *addr, int alen);