Merge tag 'dmaengine-5.8-rc1' of git://git.infradead.org/users/vkoul/slave-dma

Pull dmaengine updates from Vinod Koul:
 "A fairly small dmaengine update which includes mostly driver updates
  (dmatest, dw-edma, ioat, mmp-tdma and k3-udma) along with Renesas
  binding update to json-schema"

* tag 'dmaengine-5.8-rc1' of git://git.infradead.org/users/vkoul/slave-dma: (39 commits)
  dmaengine: imx-sdma: initialize all script addresses
  dmaengine: ti: k3-udma: Use proper return code in alloc_chan_resources
  dmaengine: ti: k3-udma: Remove udma_chan.in_ring_cnt
  dmaengine: ti: k3-udma: Add missing dma_sync call for rx flush descriptor
  dmaengine: at_xdmac: Replace zero-length array with flexible-array
  dmaengine: at_hdmac: Replace zero-length array with flexible-array
  dmaengine: qcom: bam_dma: Replace zero-length array with flexible-array
  dmaengine: ti: k3-udma: Use PTR_ERR_OR_ZERO() to simplify code
  dmaengine: moxart-dma: Drop pointless static qualifier in moxart_probe()
  dmaengine: sf-pdma: Simplify the error handling path in 'sf_pdma_probe()'
  dmaengine: qcom_hidma: use true,false for bool variable
  dmaengine: dw-edma: support local dma device transfer semantics
  dmaengine: Fix doc strings to satisfy validation script
  dmaengine: Include dmaengine.h into dmaengine.c
  dmaengine: dmatest: Describe members of struct dmatest_info
  dmaengine: dmatest: Describe members of struct dmatest_params
  dmaengine: dmatest: Allow negative timeout value to specify infinite wait
  Revert "dmaengine: dmatest: timeout value of -1 should specify infinite wait"
  dmaengine: stm32-dma: direct mode support through device tree
  dt-bindings: dma: add direct mode support through device tree in stm32-dma
  ...

21 files changed, 272 insertions, 184 deletions

diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 023db6883d0518..e9ed9165de403a 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -106,7 +106,7 @@ config AXI_DMAC
 	select REGMAP_MMIO
 	help
 	  Enable support for the Analog Devices AXI-DMAC peripheral. This DMA
-	  controller is often used in Analog Device's reference designs for FPGA
+	  controller is often used in Analog Devices' reference designs for FPGA
 	  platforms.
 
 config BCM_SBA_RAID
@@ -395,12 +395,10 @@ config MMP_TDMA
 	bool "MMP Two-Channel DMA support"
 	depends on ARCH_MMP || COMPILE_TEST
 	select DMA_ENGINE
-	select MMP_SRAM if ARCH_MMP
 	select GENERIC_ALLOCATOR
 	help
 	  Support the MMP Two-Channel DMA engine.
 	  This engine used for MMP Audio DMA and pxa910 SQU.
-	  It needs sram driver under mach-mmp.
 
 config MOXART_DMA
 	tristate "MOXART DMA support"
diff --git a/drivers/dma/at_hdmac_regs.h b/drivers/dma/at_hdmac_regs.h
index 397692e937b31b..80fc2fe8c77ea9 100644
--- a/drivers/dma/at_hdmac_regs.h
+++ b/drivers/dma/at_hdmac_regs.h
@@ -331,7 +331,7 @@ struct at_dma {
 	struct dma_pool		*dma_desc_pool;
 	struct dma_pool		*memset_pool;
 	/* AT THE END channels table */
-	struct at_dma_chan	chan[0];
+	struct at_dma_chan	chan[];
 };
 
 #define	dma_readl(atdma, name) \
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index bb0eaf38b59450..fd92f048c49185 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -212,7 +212,7 @@ struct at_xdmac {
 	struct clk		*clk;
 	u32			save_gim;
 	struct dma_pool		*at_xdmac_desc_pool;
-	struct at_xdmac_chan	chan[0];
+	struct at_xdmac_chan	chan[];
 };
 
 
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index d31076d9ef2588..2b06a7a8629d6d 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -53,6 +53,8 @@
 #include <linux/mempool.h>
 #include <linux/numa.h>
 
+#include "dmaengine.h"
+
 static DEFINE_MUTEX(dma_list_mutex);
 static DEFINE_IDA(dma_ida);
 static LIST_HEAD(dma_device_list);
@@ -145,9 +147,9 @@ static inline void dmaengine_debug_unregister(struct dma_device *dma_dev) { }
 
 /**
  * dev_to_dma_chan - convert a device pointer to its sysfs container object
- * @dev - device node
+ * @dev:	device node
  *
- * Must be called under dma_list_mutex
+ * Must be called under dma_list_mutex.
  */
 static struct dma_chan *dev_to_dma_chan(struct device *dev)
 {
@@ -243,22 +245,18 @@ static struct class dma_devclass = {
 
 /* --- client and device registration --- */
 
-/**
- * dma_cap_mask_all - enable iteration over all operation types
- */
+/* enable iteration over all operation types */
 static dma_cap_mask_t dma_cap_mask_all;
 
 /**
- * dma_chan_tbl_ent - tracks channel allocations per core/operation
- * @chan - associated channel for this entry
+ * struct dma_chan_tbl_ent - tracks channel allocations per core/operation
+ * @chan:	associated channel for this entry
  */
 struct dma_chan_tbl_ent {
 	struct dma_chan *chan;
 };
 
-/**
- * channel_table - percpu lookup table for memory-to-memory offload providers
- */
+/* percpu lookup table for memory-to-memory offload providers */
 static struct dma_chan_tbl_ent __percpu *channel_table[DMA_TX_TYPE_END];
 
 static int __init dma_channel_table_init(void)
@@ -295,8 +293,11 @@ static int __init dma_channel_table_init(void)
 arch_initcall(dma_channel_table_init);
 
 /**
- * dma_chan_is_local - returns true if the channel is in the same numa-node as
- *	the cpu
+ * dma_chan_is_local - checks if the channel is in the same NUMA-node as the CPU
+ * @chan:	DMA channel to test
+ * @cpu:	CPU index which the channel should be close to
+ *
+ * Returns true if the channel is in the same NUMA-node as the CPU.
  */
 static bool dma_chan_is_local(struct dma_chan *chan, int cpu)
 {
@@ -306,14 +307,14 @@ static bool dma_chan_is_local(struct dma_chan *chan, int cpu)
 }
 
 /**
- * min_chan - returns the channel with min count and in the same numa-node as
- *	the cpu
- * @cap: capability to match
- * @cpu: cpu index which the channel should be close to
+ * min_chan - finds the channel with min count and in the same NUMA-node as the CPU
+ * @cap:	capability to match
+ * @cpu:	CPU index which the channel should be close to
  *
- * If some channels are close to the given cpu, the one with the lowest
- * reference count is returned. Otherwise, cpu is ignored and only the
+ * If some channels are close to the given CPU, the one with the lowest
+ * reference count is returned. Otherwise, CPU is ignored and only the
  * reference count is taken into account.
+ *
  * Must be called under dma_list_mutex.
  */
 static struct dma_chan *min_chan(enum dma_transaction_type cap, int cpu)
@@ -351,10 +352,11 @@ static struct dma_chan *min_chan(enum dma_transaction_type cap, int cpu)
 /**
  * dma_channel_rebalance - redistribute the available channels
  *
- * Optimize for cpu isolation (each cpu gets a dedicated channel for an
- * operation type) in the SMP case,  and operation isolation (avoid
- * multi-tasking channels) in the non-SMP case.  Must be called under
- * dma_list_mutex.
+ * Optimize for CPU isolation (each CPU gets a dedicated channel for an
+ * operation type) in the SMP case, and operation isolation (avoid
+ * multi-tasking channels) in the non-SMP case.
+ *
+ * Must be called under dma_list_mutex.
  */
 static void dma_channel_rebalance(void)
 {
@@ -404,9 +406,9 @@ static struct module *dma_chan_to_owner(struct dma_chan *chan)
 
 /**
  * balance_ref_count - catch up the channel reference count
- * @chan - channel to balance ->client_count versus dmaengine_ref_count
+ * @chan:	channel to balance ->client_count versus dmaengine_ref_count
  *
- * balance_ref_count must be called under dma_list_mutex
+ * Must be called under dma_list_mutex.
  */
 static void balance_ref_count(struct dma_chan *chan)
 {
@@ -436,10 +438,10 @@ static void dma_device_put(struct dma_device *device)
 }
 
 /**
- * dma_chan_get - try to grab a dma channel's parent driver module
- * @chan - channel to grab
+ * dma_chan_get - try to grab a DMA channel's parent driver module
+ * @chan:	channel to grab
  *
- * Must be called under dma_list_mutex
+ * Must be called under dma_list_mutex.
  */
 static int dma_chan_get(struct dma_chan *chan)
 {
@@ -483,10 +485,10 @@ module_put_out:
 }
 
 /**
- * dma_chan_put - drop a reference to a dma channel's parent driver module
- * @chan - channel to release
+ * dma_chan_put - drop a reference to a DMA channel's parent driver module
+ * @chan:	channel to release
  *
- * Must be called under dma_list_mutex
+ * Must be called under dma_list_mutex.
  */
 static void dma_chan_put(struct dma_chan *chan)
 {
@@ -537,7 +539,7 @@ EXPORT_SYMBOL(dma_sync_wait);
 
 /**
  * dma_find_channel - find a channel to carry out the operation
- * @tx_type: transaction type
+ * @tx_type:	transaction type
  */
 struct dma_chan *dma_find_channel(enum dma_transaction_type tx_type)
 {
@@ -677,7 +679,7 @@ static struct dma_chan *find_candidate(struct dma_device *device,
 
 /**
  * dma_get_slave_channel - try to get specific channel exclusively
- * @chan: target channel
+ * @chan:	target channel
  */
 struct dma_chan *dma_get_slave_channel(struct dma_chan *chan)
 {
@@ -731,10 +733,10 @@ EXPORT_SYMBOL_GPL(dma_get_any_slave_channel);
 
 /**
  * __dma_request_channel - try to allocate an exclusive channel
- * @mask: capabilities that the channel must satisfy
- * @fn: optional callback to disposition available channels
- * @fn_param: opaque parameter to pass to dma_filter_fn
- * @np: device node to look for DMA channels
+ * @mask:	capabilities that the channel must satisfy
+ * @fn:		optional callback to disposition available channels
+ * @fn_param:	opaque parameter to pass to dma_filter_fn()
+ * @np:		device node to look for DMA channels
  *
  * Returns pointer to appropriate DMA channel on success or NULL.
  */
@@ -877,7 +879,7 @@ 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
+ * @mask:	capabilities that the channel must satisfy
  *
  * Returns pointer to appropriate DMA channel on success or an error pointer.
  */
@@ -968,7 +970,7 @@ void dmaengine_get(void)
 EXPORT_SYMBOL(dmaengine_get);
 
 /**
- * dmaengine_put - let dma drivers be removed when ref_count == 0
+ * dmaengine_put - let DMA drivers be removed when ref_count == 0
  */
 void dmaengine_put(void)
 {
@@ -1132,7 +1134,7 @@ EXPORT_SYMBOL_GPL(dma_async_device_channel_unregister);
 
 /**
  * dma_async_device_register - registers DMA devices found
- * @device: &dma_device
+ * @device:	pointer to &struct dma_device
  *
  * After calling this routine the structure should not be freed except in the
  * device_release() callback which will be called after
@@ -1304,7 +1306,7 @@ EXPORT_SYMBOL(dma_async_device_register);
 
 /**
  * dma_async_device_unregister - unregister a DMA device
- * @device: &dma_device
+ * @device:	pointer to &struct dma_device
  *
  * This routine is called by dma driver exit routines, dmaengine holds module
  * references to prevent it being called while channels are in use.
@@ -1341,7 +1343,7 @@ static void dmam_device_release(struct device *dev, void *res)
 
 /**
  * dmaenginem_async_device_register - registers DMA devices found
- * @device: &dma_device
+ * @device:	pointer to &struct dma_device
  *
  * The operation is managed and will be undone on driver detach.
  */
@@ -1578,8 +1580,9 @@ int dmaengine_desc_set_metadata_len(struct dma_async_tx_descriptor *desc,
 }
 EXPORT_SYMBOL_GPL(dmaengine_desc_set_metadata_len);
 
-/* dma_wait_for_async_tx - spin wait for a transaction to complete
- * @tx: in-flight transaction to wait on
+/**
+ * dma_wait_for_async_tx - spin wait for a transaction to complete
+ * @tx:		in-flight transaction to wait on
  */
 enum dma_status
 dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx)
@@ -1602,9 +1605,12 @@ dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx)
 }
 EXPORT_SYMBOL_GPL(dma_wait_for_async_tx);
 
-/* dma_run_dependencies - helper routine for dma drivers to process
- *	(start) dependent operations on their target channel
- * @tx: transaction with dependencies
+/**
+ * dma_run_dependencies - process dependent operations on the target channel
+ * @tx:		transaction with dependencies
+ *
+ * Helper routine for DMA drivers to process (start) dependent operations
+ * on their target channel.
  */
 void dma_run_dependencies(struct dma_async_tx_descriptor *tx)
 {
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index 0425984db118a9..b175229a4b01d7 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -60,9 +60,9 @@ MODULE_PARM_DESC(pq_sources,
 		"Number of p+q source buffers (default: 3)");
 
 static int timeout = 3000;
-module_param(timeout, uint, S_IRUGO | S_IWUSR);
+module_param(timeout, int, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(timeout, "Transfer Timeout in msec (default: 3000), "
-		 "Pass 0xFFFFFFFF (4294967295) for maximum timeout");
+		 "Pass -1 for infinite timeout");
 
 static bool noverify;
 module_param(noverify, bool, S_IRUGO | S_IWUSR);
@@ -72,10 +72,6 @@ static bool norandom;
 module_param(norandom, bool, 0644);
 MODULE_PARM_DESC(norandom, "Disable random offset setup (default: random)");
 
-static bool polled;
-module_param(polled, bool, S_IRUGO | S_IWUSR);
-MODULE_PARM_DESC(polled, "Use polling for completion instead of interrupts");
-
 static bool verbose;
 module_param(verbose, bool, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(verbose, "Enable \"success\" result messages (default: off)");
@@ -88,6 +84,10 @@ static unsigned int transfer_size;
 module_param(transfer_size, uint, 0644);
 MODULE_PARM_DESC(transfer_size, "Optional custom transfer size in bytes (default: not used (0))");
 
+static bool polled;
+module_param(polled, bool, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(polled, "Use polling for completion instead of interrupts");
+
 /**
  * struct dmatest_params - test parameters.
  * @buf_size:		size of the memcpy test buffer
@@ -98,7 +98,12 @@ MODULE_PARM_DESC(transfer_size, "Optional custom transfer size in bytes (default
  * @iterations:		iterations before stopping test
  * @xor_sources:	number of xor source buffers
  * @pq_sources:		number of p+q source buffers
- * @timeout:		transfer timeout in msec, 0 - 0xFFFFFFFF (4294967295)
+ * @timeout:		transfer timeout in msec, -1 for infinite timeout
+ * @noverify:		disable data verification
+ * @norandom:		disable random offset setup
+ * @alignment:		custom data address alignment taken as 2^alignment
+ * @transfer_size:	custom transfer size in bytes
+ * @polled:		use polling for completion instead of interrupts
  */
 struct dmatest_params {
 	unsigned int	buf_size;
@@ -109,7 +114,7 @@ struct dmatest_params {
 	unsigned int	iterations;
 	unsigned int	xor_sources;
 	unsigned int	pq_sources;
-	unsigned int	timeout;
+	int		timeout;
 	bool		noverify;
 	bool		norandom;
 	int		alignment;
@@ -120,7 +125,10 @@ struct dmatest_params {
 /**
  * struct dmatest_info - test information.
  * @params:		test parameters
+ * @channels:		channels under test
+ * @nr_channels:	number of channels under test
  * @lock:		access protection to the fields of this structure
+ * @did_init:		module has been initialized completely
  */
 static struct dmatest_info {
 	/* Test parameters */
diff --git a/drivers/dma/dw-edma/dw-edma-core.c b/drivers/dma/dw-edma/dw-edma-core.c
index ff392c01bad1f6..ed430ad9b3dd8e 100644
--- a/drivers/dma/dw-edma/dw-edma-core.c
+++ b/drivers/dma/dw-edma/dw-edma-core.c
@@ -13,8 +13,9 @@
 #include <linux/dmaengine.h>
 #include <linux/err.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/dma/edma.h>
-#include <linux/pci.h>
+#include <linux/dma-mapping.h>
 
 #include "dw-edma-core.h"
 #include "dw-edma-v0-core.h"
@@ -322,7 +323,7 @@ static struct dma_async_tx_descriptor *
 dw_edma_device_transfer(struct dw_edma_transfer *xfer)
 {
 	struct dw_edma_chan *chan = dchan2dw_edma_chan(xfer->dchan);
-	enum dma_transfer_direction direction = xfer->direction;
+	enum dma_transfer_direction dir = xfer->direction;
 	phys_addr_t src_addr, dst_addr;
 	struct scatterlist *sg = NULL;
 	struct dw_edma_chunk *chunk;
@@ -331,10 +332,26 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer)
 	u32 cnt;
 	int i;
 
-	if ((direction == DMA_MEM_TO_DEV && chan->dir == EDMA_DIR_WRITE) ||
-	    (direction == DMA_DEV_TO_MEM && chan->dir == EDMA_DIR_READ))
+	if (!chan->configured)
 		return NULL;
 
+	switch (chan->config.direction) {
+	case DMA_DEV_TO_MEM: /* local dma */
+		if (dir == DMA_DEV_TO_MEM && chan->dir == EDMA_DIR_READ)
+			break;
+		return NULL;
+	case DMA_MEM_TO_DEV: /* local dma */
+		if (dir == DMA_MEM_TO_DEV && chan->dir == EDMA_DIR_WRITE)
+			break;
+		return NULL;
+	default: /* remote dma */
+		if (dir == DMA_MEM_TO_DEV && chan->dir == EDMA_DIR_READ)
+			break;
+		if (dir == DMA_DEV_TO_MEM && chan->dir == EDMA_DIR_WRITE)
+			break;
+		return NULL;
+	}
+
 	if (xfer->cyclic) {
 		if (!xfer->xfer.cyclic.len || !xfer->xfer.cyclic.cnt)
 			return NULL;
@@ -343,9 +360,6 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer)
 			return NULL;
 	}
 
-	if (!chan->configured)
-		return NULL;
-
 	desc = dw_edma_alloc_desc(chan);
 	if (unlikely(!desc))
 		goto err_alloc;
@@ -386,7 +400,7 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer)
 		chunk->ll_region.sz += burst->sz;
 		desc->alloc_sz += burst->sz;
 
-		if (direction == DMA_DEV_TO_MEM) {
+		if (chan->dir == EDMA_DIR_WRITE) {
 			burst->sar = src_addr;
 			if (xfer->cyclic) {
 				burst->dar = xfer->xfer.cyclic.paddr;
@@ -773,6 +787,7 @@ static int dw_edma_irq_request(struct dw_edma_chip *chip,
 	u32 rd_mask = 1;
 	int i, err = 0;
 	u32 ch_cnt;
+	int irq;
 
 	ch_cnt = dw->wr_ch_cnt + dw->rd_ch_cnt;
 
@@ -781,16 +796,16 @@ static int dw_edma_irq_request(struct dw_edma_chip *chip,
 
 	if (dw->nr_irqs == 1) {
 		/* Common IRQ shared among all channels */
-		err = request_irq(pci_irq_vector(to_pci_dev(dev), 0),
-				  dw_edma_interrupt_common,
+		irq = dw->ops->irq_vector(dev, 0);
+		err = request_irq(irq, dw_edma_interrupt_common,
 				  IRQF_SHARED, dw->name, &dw->irq[0]);
 		if (err) {
 			dw->nr_irqs = 0;
 			return err;
 		}
 
-		get_cached_msi_msg(pci_irq_vector(to_pci_dev(dev), 0),
-				   &dw->irq[0].msi);
+		if (irq_get_msi_desc(irq))
+			get_cached_msi_msg(irq, &dw->irq[0].msi);
 	} else {
 		/* Distribute IRQs equally among all channels */
 		int tmp = dw->nr_irqs;
@@ -804,7 +819,8 @@ static int dw_edma_irq_request(struct dw_edma_chip *chip,
 		dw_edma_add_irq_mask(&rd_mask, *rd_alloc, dw->rd_ch_cnt);
 
 		for (i = 0; i < (*wr_alloc + *rd_alloc); i++) {
-			err = request_irq(pci_irq_vector(to_pci_dev(dev), i),
+			irq = dw->ops->irq_vector(dev, i);
+			err = request_irq(irq,
 					  i < *wr_alloc ?
 						dw_edma_interrupt_write :
 						dw_edma_interrupt_read,
@@ -815,8 +831,8 @@ static int dw_edma_irq_request(struct dw_edma_chip *chip,
 				return err;
 			}
 
-			get_cached_msi_msg(pci_irq_vector(to_pci_dev(dev), i),
-					   &dw->irq[i].msi);
+			if (irq_get_msi_desc(irq))
+				get_cached_msi_msg(irq, &dw->irq[i].msi);
 		}
 
 		dw->nr_irqs = i;
@@ -827,12 +843,23 @@ static int dw_edma_irq_request(struct dw_edma_chip *chip,
 
 int dw_edma_probe(struct dw_edma_chip *chip)
 {
-	struct device *dev = chip->dev;
-	struct dw_edma *dw = chip->dw;
+	struct device *dev;
+	struct dw_edma *dw;
 	u32 wr_alloc = 0;
 	u32 rd_alloc = 0;
 	int i, err;
 
+	if (!chip)
+		return -EINVAL;
+
+	dev = chip->dev;
+	if (!dev)
+		return -EINVAL;
+
+	dw = chip->dw;
+	if (!dw || !dw->irq || !dw->ops || !dw->ops->irq_vector)
+		return -EINVAL;
+
 	raw_spin_lock_init(&dw->lock);
 
 	/* Find out how many write channels are supported by hardware */
@@ -884,7 +911,7 @@ int dw_edma_probe(struct dw_edma_chip *chip)
 
 err_irq_free:
 	for (i = (dw->nr_irqs - 1); i >= 0; i--)
-		free_irq(pci_irq_vector(to_pci_dev(dev), i), &dw->irq[i]);
+		free_irq(dw->ops->irq_vector(dev, i), &dw->irq[i]);
 
 	dw->nr_irqs = 0;
 
@@ -904,7 +931,7 @@ int dw_edma_remove(struct dw_edma_chip *chip)
 
 	/* Free irqs */
 	for (i = (dw->nr_irqs - 1); i >= 0; i--)
-		free_irq(pci_irq_vector(to_pci_dev(dev), i), &dw->irq[i]);
+		free_irq(dw->ops->irq_vector(dev, i), &dw->irq[i]);
 
 	/* Power management */
 	pm_runtime_disable(dev);
diff --git a/drivers/dma/dw-edma/dw-edma-core.h b/drivers/dma/dw-edma/dw-edma-core.h
index 4e5f9f6e901bae..31fc50d317928a 100644
--- a/drivers/dma/dw-edma/dw-edma-core.h
+++ b/drivers/dma/dw-edma/dw-edma-core.h
@@ -103,6 +103,10 @@ struct dw_edma_irq {
 	struct dw_edma			*dw;
 };
 
+struct dw_edma_core_ops {
+	int	(*irq_vector)(struct device *dev, unsigned int nr);
+};
+
 struct dw_edma {
 	char				name[20];
 
diff --git a/drivers/dma/dw-edma/dw-edma-pcie.c b/drivers/dma/dw-edma/dw-edma-pcie.c
index dc85f55e1bb8ce..1eafc602e17ea5 100644
--- a/drivers/dma/dw-edma/dw-edma-pcie.c
+++ b/drivers/dma/dw-edma/dw-edma-pcie.c
@@ -54,6 +54,15 @@ static const struct dw_edma_pcie_data snps_edda_data = {
 	.irqs				= 1,
 };
 
+static int dw_edma_pcie_irq_vector(struct device *dev, unsigned int nr)
+{
+	return pci_irq_vector(to_pci_dev(dev), nr);
+}
+
+static const struct dw_edma_core_ops dw_edma_pcie_core_ops = {
+	.irq_vector = dw_edma_pcie_irq_vector,
+};
+
 static int dw_edma_pcie_probe(struct pci_dev *pdev,
 			      const struct pci_device_id *pid)
 {
@@ -151,6 +160,7 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 	dw->version = pdata->version;
 	dw->mode = pdata->mode;
 	dw->nr_irqs = nr_irqs;
+	dw->ops = &dw_edma_pcie_core_ops;
 
 	/* Debug info */
 	pci_dbg(pdev, "Version:\t%u\n", dw->version);
diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c
index 3999827970abae..052dae5d6dddbd 100644
--- a/drivers/dma/idxd/sysfs.c
+++ b/drivers/dma/idxd/sysfs.c
@@ -1092,6 +1092,16 @@ static const struct attribute_group *idxd_wq_attribute_groups[] = {
 };
 
 /* IDXD device attribs */
+static ssize_t version_show(struct device *dev, struct device_attribute *attr,
+			    char *buf)
+{
+	struct idxd_device *idxd =
+		container_of(dev, struct idxd_device, conf_dev);
+
+	return sprintf(buf, "%#x\n", idxd->hw.version);
+}
+static DEVICE_ATTR_RO(version);
+
 static ssize_t max_work_queues_size_show(struct device *dev,
 					 struct device_attribute *attr,
 					 char *buf)
@@ -1313,6 +1323,7 @@ static ssize_t cdev_major_show(struct device *dev,
 static DEVICE_ATTR_RO(cdev_major);
 
 static struct attribute *idxd_device_attributes[] = {
+	&dev_attr_version.attr,
 	&dev_attr_max_groups.attr,
 	&dev_attr_max_work_queues.attr,
 	&dev_attr_max_work_queues_size.attr,
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index 4d4477df4ede75..91774039ae5d63 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -2063,7 +2063,7 @@ static int sdma_probe(struct platform_device *pdev)
 
 	/* initially no scripts available */
 	saddr_arr = (s32 *)sdma->script_addrs;
-	for (i = 0; i < SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V1; i++)
+	for (i = 0; i < sizeof(*sdma->script_addrs) / sizeof(s32); i++)
 		saddr_arr[i] = -EINVAL;
 
 	dma_cap_set(DMA_SLAVE, sdma->dma_device.cap_mask);
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index 18c011e57592eb..8ad0ad861c8611 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -332,8 +332,8 @@ ioat_alloc_ring_ent(struct dma_chan *chan, int idx, gfp_t flags)
 	u8 *pos;
 	off_t offs;
 
-	chunk = idx / IOAT_DESCS_PER_2M;
-	idx &= (IOAT_DESCS_PER_2M - 1);
+	chunk = idx / IOAT_DESCS_PER_CHUNK;
+	idx &= (IOAT_DESCS_PER_CHUNK - 1);
 	offs = idx * IOAT_DESC_SZ;
 	pos = (u8 *)ioat_chan->descs[chunk].virt + offs;
 	phys = ioat_chan->descs[chunk].hw + offs;
@@ -370,7 +370,8 @@ ioat_alloc_ring(struct dma_chan *c, int order, gfp_t flags)
 	if (!ring)
 		return NULL;
 
-	ioat_chan->desc_chunks = chunks = (total_descs * IOAT_DESC_SZ) / SZ_2M;
+	chunks = (total_descs * IOAT_DESC_SZ) / IOAT_CHUNK_SIZE;
+	ioat_chan->desc_chunks = chunks;
 
 	for (i = 0; i < chunks; i++) {
 		struct ioat_descs *descs = &ioat_chan->descs[i];
@@ -382,8 +383,9 @@ ioat_alloc_ring(struct dma_chan *c, int order, gfp_t flags)
 
 			for (idx = 0; idx < i; idx++) {
 				descs = &ioat_chan->descs[idx];
-				dma_free_coherent(to_dev(ioat_chan), SZ_2M,
-						  descs->virt, descs->hw);
+				dma_free_coherent(to_dev(ioat_chan),
+						IOAT_CHUNK_SIZE,
+						descs->virt, descs->hw);
 				descs->virt = NULL;
 				descs->hw = 0;
 			}
@@ -404,7 +406,7 @@ ioat_alloc_ring(struct dma_chan *c, int order, gfp_t flags)
 
 			for (idx = 0; idx < ioat_chan->desc_chunks; idx++) {
 				dma_free_coherent(to_dev(ioat_chan),
-						  SZ_2M,
+						  IOAT_CHUNK_SIZE,
 						  ioat_chan->descs[idx].virt,
 						  ioat_chan->descs[idx].hw);
 				ioat_chan->descs[idx].virt = NULL;
@@ -867,6 +869,23 @@ static void check_active(struct ioatdma_chan *ioat_chan)
 		mod_timer(&ioat_chan->timer, jiffies + IDLE_TIMEOUT);
 }
 
+static void ioat_reboot_chan(struct ioatdma_chan *ioat_chan)
+{
+	spin_lock_bh(&ioat_chan->prep_lock);
+	set_bit(IOAT_CHAN_DOWN, &ioat_chan->state);
+	spin_unlock_bh(&ioat_chan->prep_lock);
+
+	ioat_abort_descs(ioat_chan);
+	dev_warn(to_dev(ioat_chan), "Reset channel...\n");
+	ioat_reset_hw(ioat_chan);
+	dev_warn(to_dev(ioat_chan), "Restart channel...\n");
+	ioat_restart_channel(ioat_chan);
+
+	spin_lock_bh(&ioat_chan->prep_lock);
+	clear_bit(IOAT_CHAN_DOWN, &ioat_chan->state);
+	spin_unlock_bh(&ioat_chan->prep_lock);
+}
+
 void ioat_timer_event(struct timer_list *t)
 {
 	struct ioatdma_chan *ioat_chan = from_timer(ioat_chan, t, timer);
@@ -889,19 +908,7 @@ void ioat_timer_event(struct timer_list *t)
 
 		if (test_bit(IOAT_RUN, &ioat_chan->state)) {
 			spin_lock_bh(&ioat_chan->cleanup_lock);
-			spin_lock_bh(&ioat_chan->prep_lock);
-			set_bit(IOAT_CHAN_DOWN, &ioat_chan->state);
-			spin_unlock_bh(&ioat_chan->prep_lock);
-
-			ioat_abort_descs(ioat_chan);
-			dev_warn(to_dev(ioat_chan), "Reset channel...\n");
-			ioat_reset_hw(ioat_chan);
-			dev_warn(to_dev(ioat_chan), "Restart channel...\n");
-			ioat_restart_channel(ioat_chan);
-
-			spin_lock_bh(&ioat_chan->prep_lock);
-			clear_bit(IOAT_CHAN_DOWN, &ioat_chan->state);
-			spin_unlock_bh(&ioat_chan->prep_lock);
+			ioat_reboot_chan(ioat_chan);
 			spin_unlock_bh(&ioat_chan->cleanup_lock);
 		}
 
@@ -915,17 +922,23 @@ void ioat_timer_event(struct timer_list *t)
 		spin_lock_bh(&ioat_chan->prep_lock);
 		check_active(ioat_chan);
 		spin_unlock_bh(&ioat_chan->prep_lock);
-		spin_unlock_bh(&ioat_chan->cleanup_lock);
-		return;
+		goto unlock_out;
+	}
+
+	/* handle the missed cleanup case */
+	if (ioat_cleanup_preamble(ioat_chan, &phys_complete)) {
+		/* timer restarted in ioat_cleanup_preamble
+		 * and IOAT_COMPLETION_ACK cleared
+		 */
+		__cleanup(ioat_chan, phys_complete);
+		goto unlock_out;
 	}
 
 	/* if we haven't made progress and we have already
 	 * acknowledged a pending completion once, then be more
 	 * forceful with a restart
 	 */
-	if (ioat_cleanup_preamble(ioat_chan, &phys_complete))
-		__cleanup(ioat_chan, phys_complete);
-	else if (test_bit(IOAT_COMPLETION_ACK, &ioat_chan->state)) {
+	if (test_bit(IOAT_COMPLETION_ACK, &ioat_chan->state)) {
 		u32 chanerr;
 
 		chanerr = readl(ioat_chan->reg_base + IOAT_CHANERR_OFFSET);
@@ -937,25 +950,23 @@ void ioat_timer_event(struct timer_list *t)
 		dev_dbg(to_dev(ioat_chan), "Active descriptors: %d\n",
 			ioat_ring_active(ioat_chan));
 
-		spin_lock_bh(&ioat_chan->prep_lock);
-		set_bit(IOAT_CHAN_DOWN, &ioat_chan->state);
-		spin_unlock_bh(&ioat_chan->prep_lock);
+		ioat_reboot_chan(ioat_chan);
 
-		ioat_abort_descs(ioat_chan);
-		dev_warn(to_dev(ioat_chan), "Resetting channel...\n");
-		ioat_reset_hw(ioat_chan);
-		dev_warn(to_dev(ioat_chan), "Restarting channel...\n");
-		ioat_restart_channel(ioat_chan);
+		goto unlock_out;
+	}
 
+	/* handle missed issue pending case */
+	if (ioat_ring_pending(ioat_chan)) {
+		dev_warn(to_dev(ioat_chan),
+			"Completion timeout with pending descriptors\n");
 		spin_lock_bh(&ioat_chan->prep_lock);
-		clear_bit(IOAT_CHAN_DOWN, &ioat_chan->state);
+		__ioat_issue_pending(ioat_chan);
 		spin_unlock_bh(&ioat_chan->prep_lock);
-		spin_unlock_bh(&ioat_chan->cleanup_lock);
-		return;
-	} else
-		set_bit(IOAT_COMPLETION_ACK, &ioat_chan->state);
+	}
 
+	set_bit(IOAT_COMPLETION_ACK, &ioat_chan->state);
 	mod_timer(&ioat_chan->timer, jiffies + COMPLETION_TIMEOUT);
+unlock_out:
 	spin_unlock_bh(&ioat_chan->cleanup_lock);
 }
 
diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h
index b8e8e0b9693c7c..e6b622e1ba92ee 100644
--- a/drivers/dma/ioat/dma.h
+++ b/drivers/dma/ioat/dma.h
@@ -81,6 +81,11 @@ struct ioatdma_device {
 	u32 msixpba;
 };
 
+#define IOAT_MAX_ORDER 16
+#define IOAT_MAX_DESCS (1 << IOAT_MAX_ORDER)
+#define IOAT_CHUNK_SIZE (SZ_512K)
+#define IOAT_DESCS_PER_CHUNK (IOAT_CHUNK_SIZE / IOAT_DESC_SZ)
+
 struct ioat_descs {
 	void *virt;
 	dma_addr_t hw;
@@ -128,7 +133,7 @@ struct ioatdma_chan {
 	u16 produce;
 	struct ioat_ring_ent **ring;
 	spinlock_t prep_lock;
-	struct ioat_descs descs[2];
+	struct ioat_descs descs[IOAT_MAX_DESCS / IOAT_DESCS_PER_CHUNK];
 	int desc_chunks;
 	int intr_coalesce;
 	int prev_intr_coalesce;
@@ -301,9 +306,6 @@ static inline bool is_ioat_bug(unsigned long err)
 	return !!err;
 }
 
-#define IOAT_MAX_ORDER 16
-#define IOAT_MAX_DESCS 65536
-#define IOAT_DESCS_PER_2M 32768
 
 static inline u32 ioat_ring_size(struct ioatdma_chan *ioat_chan)
 {
diff --git a/drivers/dma/ioat/init.c b/drivers/dma/ioat/init.c
index 60e9afbb896c33..58d13564f88b4e 100644
--- a/drivers/dma/ioat/init.c
+++ b/drivers/dma/ioat/init.c
@@ -651,7 +651,7 @@ static void ioat_free_chan_resources(struct dma_chan *c)
 	}
 
 	for (i = 0; i < ioat_chan->desc_chunks; i++) {
-		dma_free_coherent(to_dev(ioat_chan), SZ_2M,
+		dma_free_coherent(to_dev(ioat_chan), IOAT_CHUNK_SIZE,
 				  ioat_chan->descs[i].virt,
 				  ioat_chan->descs[i].hw);
 		ioat_chan->descs[i].virt = NULL;
diff --git a/drivers/dma/mmp_tdma.c b/drivers/dma/mmp_tdma.c
index d683232d7fea07..dbc6a48424fa13 100644
--- a/drivers/dma/mmp_tdma.c
+++ b/drivers/dma/mmp_tdma.c
@@ -235,7 +235,7 @@ static int mmp_tdma_config_chan(struct dma_chan *chan)
 			tdcr |= TDCR_BURSTSZ_128B;
 			break;
 		default:
-			dev_err(tdmac->dev, "mmp_tdma: unknown burst size.\n");
+			dev_err(tdmac->dev, "unknown burst size.\n");
 			return -EINVAL;
 		}
 
@@ -250,7 +250,7 @@ static int mmp_tdma_config_chan(struct dma_chan *chan)
 			tdcr |= TDCR_SSZ_32_BITS;
 			break;
 		default:
-			dev_err(tdmac->dev, "mmp_tdma: unknown bus size.\n");
+			dev_err(tdmac->dev, "unknown bus size.\n");
 			return -EINVAL;
 		}
 	} else if (tdmac->type == PXA910_SQU) {
@@ -276,7 +276,7 @@ static int mmp_tdma_config_chan(struct dma_chan *chan)
 			tdcr |= TDCR_BURSTSZ_SQU_32B;
 			break;
 		default:
-			dev_err(tdmac->dev, "mmp_tdma: unknown burst size.\n");
+			dev_err(tdmac->dev, "unknown burst size.\n");
 			return -EINVAL;
 		}
 	}
@@ -429,8 +429,15 @@ static struct dma_async_tx_descriptor *mmp_tdma_prep_dma_cyclic(
 	int num_periods = buf_len / period_len;
 	int i = 0, buf = 0;
 
-	if (tdmac->status != DMA_COMPLETE)
+	if (!is_slave_direction(direction)) {
+		dev_err(tdmac->dev, "unsupported transfer direction\n");
 		return NULL;
+	}
+
+	if (tdmac->status != DMA_COMPLETE) {
+		dev_err(tdmac->dev, "controller busy");
+		return NULL;
+	}
 
 	if (period_len > TDMA_MAX_XFER_BYTES) {
 		dev_err(tdmac->dev,
@@ -704,6 +711,17 @@ static int mmp_tdma_probe(struct platform_device *pdev)
 	tdev->device.device_terminate_all = mmp_tdma_terminate_all;
 	tdev->device.copy_align = DMAENGINE_ALIGN_8_BYTES;
 
+	tdev->device.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
+	if (type == MMP_AUD_TDMA) {
+		tdev->device.max_burst = SZ_128;
+		tdev->device.src_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_4_BYTES);
+		tdev->device.dst_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_4_BYTES);
+	} else if (type == PXA910_SQU) {
+		tdev->device.max_burst = SZ_32;
+	}
+	tdev->device.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
+	tdev->device.descriptor_reuse = true;
+
 	dma_set_mask(&pdev->dev, DMA_BIT_MASK(64));
 	platform_set_drvdata(pdev, tdev);
 
diff --git a/drivers/dma/moxart-dma.c b/drivers/dma/moxart-dma.c
index e04499c1f27f4c..4ab493d463759a 100644
--- a/drivers/dma/moxart-dma.c
+++ b/drivers/dma/moxart-dma.c
@@ -568,7 +568,7 @@ static int moxart_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct device_node *node = dev->of_node;
 	struct resource *res;
-	static void __iomem *dma_base_addr;
+	void __iomem *dma_base_addr;
 	int ret, i;
 	unsigned int irq;
 	struct moxart_chan *ch;
diff --git a/drivers/dma/qcom/bam_dma.c b/drivers/dma/qcom/bam_dma.c
index ef73f65224b1b7..5a08dd0d338874 100644
--- a/drivers/dma/qcom/bam_dma.c
+++ b/drivers/dma/qcom/bam_dma.c
@@ -74,7 +74,7 @@ struct bam_async_desc {
 	struct list_head desc_node;
 	enum dma_transfer_direction dir;
 	size_t length;
-	struct bam_desc_hw desc[0];
+	struct bam_desc_hw desc[];
 };
 
 enum bam_reg {
diff --git a/drivers/dma/qcom/hidma.c b/drivers/dma/qcom/hidma.c
index 411f91fde73458..0a6d3ea08c782a 100644
--- a/drivers/dma/qcom/hidma.c
+++ b/drivers/dma/qcom/hidma.c
@@ -550,7 +550,7 @@ static void hidma_free_chan_resources(struct dma_chan *dmach)
 		kfree(mdesc);
 	}
 
-	mchan->allocated = 0;
+	mchan->allocated = false;
 	spin_unlock_irqrestore(&mchan->lock, irqflags);
 }
 
@@ -897,7 +897,6 @@ uninit:
 	if (msi)
 		hidma_free_msis(dmadev);
 
-	hidma_debug_uninit(dmadev);
 	hidma_ll_uninit(dmadev->lldev);
 dmafree:
 	if (dmadev)
diff --git a/drivers/dma/sf-pdma/sf-pdma.c b/drivers/dma/sf-pdma/sf-pdma.c
index 6d0bec94763655..5c118c7e02bdc2 100644
--- a/drivers/dma/sf-pdma/sf-pdma.c
+++ b/drivers/dma/sf-pdma/sf-pdma.c
@@ -506,11 +506,11 @@ static int sf_pdma_probe(struct platform_device *pdev)
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	pdma->membase = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(pdma->membase))
-		goto ERR_MEMBASE;
+		return PTR_ERR(pdma->membase);
 
 	ret = sf_pdma_irq_init(pdev, pdma);
 	if (ret)
-		goto ERR_INITIRQ;
+		return ret;
 
 	sf_pdma_setup_chans(pdma);
 
@@ -544,24 +544,13 @@ static int sf_pdma_probe(struct platform_device *pdev)
 			 "Failed to set DMA mask. Fall back to default.\n");
 
 	ret = dma_async_device_register(&pdma->dma_dev);
-	if (ret)
-		goto ERR_REG_DMADEVICE;
+	if (ret) {
+		dev_err(&pdev->dev,
+			"Can't register SiFive Platform DMA. (%d)\n", ret);
+		return ret;
+	}
 
 	return 0;
-
-ERR_MEMBASE:
-	devm_kfree(&pdev->dev, pdma);
-	return PTR_ERR(pdma->membase);
-
-ERR_INITIRQ:
-	devm_kfree(&pdev->dev, pdma);
-	return ret;
-
-ERR_REG_DMADEVICE:
-	devm_kfree(&pdev->dev, pdma);
-	dev_err(&pdev->dev,
-		"Can't register SiFive Platform DMA. (%d)\n", ret);
-	return ret;
 }
 
 static int sf_pdma_remove(struct platform_device *pdev)
diff --git a/drivers/dma/stm32-dma.c b/drivers/dma/stm32-dma.c
index 0ddbaa4b4f0b8f..96ad1b3d24c68c 100644
--- a/drivers/dma/stm32-dma.c
+++ b/drivers/dma/stm32-dma.c
@@ -117,6 +117,7 @@
 #define STM32_DMA_FIFO_THRESHOLD_HALFFULL		0x01
 #define STM32_DMA_FIFO_THRESHOLD_3QUARTERSFULL		0x02
 #define STM32_DMA_FIFO_THRESHOLD_FULL			0x03
+#define STM32_DMA_FIFO_THRESHOLD_NONE			0x04
 
 #define STM32_DMA_MAX_DATA_ITEMS	0xffff
 /*
@@ -136,6 +137,9 @@
 /* DMA Features */
 #define STM32_DMA_THRESHOLD_FTR_MASK	GENMASK(1, 0)
 #define STM32_DMA_THRESHOLD_FTR_GET(n)	((n) & STM32_DMA_THRESHOLD_FTR_MASK)
+#define STM32_DMA_DIRECT_MODE_MASK	BIT(2)
+#define STM32_DMA_DIRECT_MODE_GET(n)	(((n) & STM32_DMA_DIRECT_MODE_MASK) \
+					 >> 2)
 
 enum stm32_dma_width {
 	STM32_DMA_BYTE,
@@ -281,6 +285,9 @@ static bool stm32_dma_fifo_threshold_is_allowed(u32 burst, u32 threshold,
 {
 	u32 remaining;
 
+	if (threshold == STM32_DMA_FIFO_THRESHOLD_NONE)
+		return false;
+
 	if (width != DMA_SLAVE_BUSWIDTH_UNDEFINED) {
 		if (burst != 0) {
 			/*
@@ -302,6 +309,10 @@ static bool stm32_dma_fifo_threshold_is_allowed(u32 burst, u32 threshold,
 
 static bool stm32_dma_is_burst_possible(u32 buf_len, u32 threshold)
 {
+	/* If FIFO direct mode, burst is not possible */
+	if (threshold == STM32_DMA_FIFO_THRESHOLD_NONE)
+		return false;
+
 	/*
 	 * Buffer or period length has to be aligned on FIFO depth.
 	 * Otherwise bytes may be stuck within FIFO at buffer or period
@@ -657,6 +668,12 @@ static irqreturn_t stm32_dma_chan_irq(int irq, void *devid)
 				dev_dbg(chan2dev(chan), "FIFO over/underrun\n");
 		}
 	}
+	if (status & STM32_DMA_DMEI) {
+		stm32_dma_irq_clear(chan, STM32_DMA_DMEI);
+		status &= ~STM32_DMA_DMEI;
+		if (sfcr & STM32_DMA_SCR_DMEIE)
+			dev_dbg(chan2dev(chan), "Direct mode overrun\n");
+	}
 	if (status) {
 		stm32_dma_irq_clear(chan, status);
 		dev_err(chan2dev(chan), "DMA error: status=0x%08x\n", status);
@@ -692,13 +709,13 @@ static int stm32_dma_set_xfer_param(struct stm32_dma_chan *chan,
 	int src_bus_width, dst_bus_width;
 	int src_burst_size, dst_burst_size;
 	u32 src_maxburst, dst_maxburst, src_best_burst, dst_best_burst;
-	u32 dma_scr, threshold;
+	u32 dma_scr, fifoth;
 
 	src_addr_width = chan->dma_sconfig.src_addr_width;
 	dst_addr_width = chan->dma_sconfig.dst_addr_width;
 	src_maxburst = chan->dma_sconfig.src_maxburst;
 	dst_maxburst = chan->dma_sconfig.dst_maxburst;
-	threshold = chan->threshold;
+	fifoth = chan->threshold;
 
 	switch (direction) {
 	case DMA_MEM_TO_DEV:
@@ -710,7 +727,7 @@ static int stm32_dma_set_xfer_param(struct stm32_dma_chan *chan,
 		/* Set device burst size */
 		dst_best_burst = stm32_dma_get_best_burst(buf_len,
 							  dst_maxburst,
-							  threshold,
+							  fifoth,
 							  dst_addr_width);
 
 		dst_burst_size = stm32_dma_get_burst(chan, dst_best_burst);
@@ -718,7 +735,7 @@ static int stm32_dma_set_xfer_param(struct stm32_dma_chan *chan,
 			return dst_burst_size;
 
 		/* Set memory data size */
-		src_addr_width = stm32_dma_get_max_width(buf_len, threshold);
+		src_addr_width = stm32_dma_get_max_width(buf_len, fifoth);
 		chan->mem_width = src_addr_width;
 		src_bus_width = stm32_dma_get_width(chan, src_addr_width);
 		if (src_bus_width < 0)
@@ -728,7 +745,7 @@ static int stm32_dma_set_xfer_param(struct stm32_dma_chan *chan,
 		src_maxburst = STM32_DMA_MAX_BURST;
 		src_best_burst = stm32_dma_get_best_burst(buf_len,
 							  src_maxburst,
-							  threshold,
+							  fifoth,
 							  src_addr_width);
 		src_burst_size = stm32_dma_get_burst(chan, src_best_burst);
 		if (src_burst_size < 0)
@@ -742,7 +759,8 @@ static int stm32_dma_set_xfer_param(struct stm32_dma_chan *chan,
 
 		/* Set FIFO threshold */
 		chan->chan_reg.dma_sfcr &= ~STM32_DMA_SFCR_FTH_MASK;
-		chan->chan_reg.dma_sfcr |= STM32_DMA_SFCR_FTH(threshold);
+		if (fifoth != STM32_DMA_FIFO_THRESHOLD_NONE)
+			chan->chan_reg.dma_sfcr |= STM32_DMA_SFCR_FTH(fifoth);
 
 		/* Set peripheral address */
 		chan->chan_reg.dma_spar = chan->dma_sconfig.dst_addr;
@@ -758,7 +776,7 @@ static int stm32_dma_set_xfer_param(struct stm32_dma_chan *chan,
 		/* Set device burst size */
 		src_best_burst = stm32_dma_get_best_burst(buf_len,
 							  src_maxburst,
-							  threshold,
+							  fifoth,
 							  src_addr_width);
 		chan->mem_burst = src_best_burst;
 		src_burst_size = stm32_dma_get_burst(chan, src_best_burst);
@@ -766,7 +784,7 @@ static int stm32_dma_set_xfer_param(struct stm32_dma_chan *chan,
 			return src_burst_size;
 
 		/* Set memory data size */
-		dst_addr_width = stm32_dma_get_max_width(buf_len, threshold);
+		dst_addr_width = stm32_dma_get_max_width(buf_len, fifoth);
 		chan->mem_width = dst_addr_width;
 		dst_bus_width = stm32_dma_get_width(chan, dst_addr_width);
 		if (dst_bus_width < 0)
@@ -776,7 +794,7 @@ static int stm32_dma_set_xfer_param(struct stm32_dma_chan *chan,
 		dst_maxburst = STM32_DMA_MAX_BURST;
 		dst_best_burst = stm32_dma_get_best_burst(buf_len,
 							  dst_maxburst,
-							  threshold,
+							  fifoth,
 							  dst_addr_width);
 		chan->mem_burst = dst_best_burst;
 		dst_burst_size = stm32_dma_get_burst(chan, dst_best_burst);
@@ -791,7 +809,8 @@ static int stm32_dma_set_xfer_param(struct stm32_dma_chan *chan,
 
 		/* Set FIFO threshold */
 		chan->chan_reg.dma_sfcr &= ~STM32_DMA_SFCR_FTH_MASK;
-		chan->chan_reg.dma_sfcr |= STM32_DMA_SFCR_FTH(threshold);
+		if (fifoth != STM32_DMA_FIFO_THRESHOLD_NONE)
+			chan->chan_reg.dma_sfcr |= STM32_DMA_SFCR_FTH(fifoth);
 
 		/* Set peripheral address */
 		chan->chan_reg.dma_spar = chan->dma_sconfig.src_addr;
@@ -1216,6 +1235,8 @@ static void stm32_dma_set_config(struct stm32_dma_chan *chan,
 	chan->chan_reg.dma_scr |= STM32_DMA_SCR_TEIE | STM32_DMA_SCR_TCIE;
 
 	chan->threshold = STM32_DMA_THRESHOLD_FTR_GET(cfg->features);
+	if (STM32_DMA_DIRECT_MODE_GET(cfg->features))
+		chan->threshold = STM32_DMA_FIFO_THRESHOLD_NONE;
 }
 
 static struct dma_chan *stm32_dma_of_xlate(struct of_phandle_args *dma_spec,
diff --git a/drivers/dma/ti/Kconfig b/drivers/dma/ti/Kconfig
index f76e06651f804c..79618fac119a72 100644
--- a/drivers/dma/ti/Kconfig
+++ b/drivers/dma/ti/Kconfig
@@ -36,7 +36,7 @@ config DMA_OMAP
 
 config TI_K3_UDMA
 	bool "Texas Instruments UDMA support"
-	depends on ARCH_K3 || COMPILE_TEST
+	depends on ARCH_K3
 	depends on TI_SCI_PROTOCOL
 	depends on TI_SCI_INTA_IRQCHIP
 	select DMA_ENGINE
@@ -49,7 +49,7 @@ config TI_K3_UDMA
 
 config TI_K3_UDMA_GLUE_LAYER
 	bool "Texas Instruments UDMA Glue layer for non DMAengine users"
-	depends on ARCH_K3 || COMPILE_TEST
+	depends on ARCH_K3
 	depends on TI_K3_UDMA
 	help
 	  Say y here to support the K3 NAVSS DMA glue interface
diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c
index a90e154b0ae0df..945b7c604f9173 100644
--- a/drivers/dma/ti/k3-udma.c
+++ b/drivers/dma/ti/k3-udma.c
@@ -231,7 +231,6 @@ struct udma_chan {
 	struct udma_tx_drain tx_drain;
 
 	u32 bcnt; /* number of bytes completed since the start of the channel */
-	u32 in_ring_cnt; /* number of descriptors in flight */
 
 	/* Channel configuration parameters */
 	struct udma_chan_config config;
@@ -574,7 +573,6 @@ static int udma_push_to_ring(struct udma_chan *uc, int idx)
 	struct udma_desc *d = uc->desc;
 	struct k3_ring *ring = NULL;
 	dma_addr_t paddr;
-	int ret;
 
 	switch (uc->config.dir) {
 	case DMA_DEV_TO_MEM:
@@ -598,11 +596,7 @@ static int udma_push_to_ring(struct udma_chan *uc, int idx)
 		udma_sync_for_device(uc, idx);
 	}
 
-	ret = k3_ringacc_ring_push(ring, &paddr);
-	if (!ret)
-		uc->in_ring_cnt++;
-
-	return ret;
+	return k3_ringacc_ring_push(ring, &paddr);
 }
 
 static bool udma_desc_is_rx_flush(struct udma_chan *uc, dma_addr_t addr)
@@ -655,9 +649,6 @@ static int udma_pop_from_ring(struct udma_chan *uc, dma_addr_t *addr)
 						d->hwdesc[0].cppi5_desc_size,
 						DMA_FROM_DEVICE);
 		rmb(); /* Ensure that reads are not moved before this point */
-
-		if (!ret)
-			uc->in_ring_cnt--;
 	}
 
 	return ret;
@@ -697,8 +688,6 @@ static void udma_reset_rings(struct udma_chan *uc)
 		udma_desc_free(&uc->terminated_desc->vd);
 		uc->terminated_desc = NULL;
 	}
-
-	uc->in_ring_cnt = 0;
 }
 
 static void udma_reset_counters(struct udma_chan *uc)
@@ -1073,9 +1062,6 @@ static irqreturn_t udma_ring_irq_handler(int irq, void *data)
 
 	/* Teardown completion message */
 	if (cppi5_desc_is_tdcm(paddr)) {
-		/* Compensate our internal pop/push counter */
-		uc->in_ring_cnt++;
-
 		complete_all(&uc->teardown_completed);
 
 		if (uc->terminated_desc) {
@@ -1291,10 +1277,8 @@ static int udma_get_tchan(struct udma_chan *uc)
 	}
 
 	uc->tchan = __udma_reserve_tchan(ud, uc->config.channel_tpl, -1);
-	if (IS_ERR(uc->tchan))
-		return PTR_ERR(uc->tchan);
 
-	return 0;
+	return PTR_ERR_OR_ZERO(uc->tchan);
 }
 
 static int udma_get_rchan(struct udma_chan *uc)
@@ -1308,10 +1292,8 @@ static int udma_get_rchan(struct udma_chan *uc)
 	}
 
 	uc->rchan = __udma_reserve_rchan(ud, uc->config.channel_tpl, -1);
-	if (IS_ERR(uc->rchan))
-		return PTR_ERR(uc->rchan);
 
-	return 0;
+	return PTR_ERR_OR_ZERO(uc->rchan);
 }
 
 static int udma_get_chan_pair(struct udma_chan *uc)
@@ -1373,10 +1355,8 @@ static int udma_get_rflow(struct udma_chan *uc, int flow_id)
 	}
 
 	uc->rflow = __udma_get_rflow(ud, flow_id);
-	if (IS_ERR(uc->rflow))
-		return PTR_ERR(uc->rflow);
 
-	return 0;
+	return PTR_ERR_OR_ZERO(uc->rflow);
 }
 
 static void udma_put_rchan(struct udma_chan *uc)
@@ -1870,6 +1850,7 @@ static int udma_alloc_chan_resources(struct dma_chan *chan)
 		udma_stop(uc);
 		if (udma_is_chan_running(uc)) {
 			dev_err(ud->dev, "chan%d: won't stop!\n", uc->id);
+			ret = -EBUSY;
 			goto err_res_free;
 		}
 	}
@@ -3189,7 +3170,7 @@ static struct udma_match_data am654_main_data = {
 
 static struct udma_match_data am654_mcu_data = {
 	.psil_base = 0x6000,
-	.enable_memcpy_support = true, /* TEST: DMA domains */
+	.enable_memcpy_support = false,
 	.statictr_z_mask = GENMASK(11, 0),
 	.rchan_oes_offset = 0x2000,
 	.tpl_levels = 2,
@@ -3471,6 +3452,9 @@ static int udma_setup_rx_flush(struct udma_dev *ud)
 	tr_req->icnt0 = rx_flush->buffer_size;
 	tr_req->icnt1 = 1;
 
+	dma_sync_single_for_device(dev, hwdesc->cppi5_desc_paddr,
+				   hwdesc->cppi5_desc_size, DMA_TO_DEVICE);
+
 	/* Set up descriptor to be used for packet mode */
 	hwdesc = &rx_flush->hwdescs[1];
 	hwdesc->cppi5_desc_size = ALIGN(sizeof(struct cppi5_host_desc_t) +