Merge tag 'dmaengine-5.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine

Pull dmaengine updates from Vinod Koul:
 "Core:
   - Support out of order dma completion
   - Support for repeating transaction

  New controllers:
   - Support for Actions S700 DMA engine
   - Renesas R8A774E1, r8a7742 controller binding
   - New driver for Xilinx DPDMA controller

  Other:
   - Support of out of order dma completion in idxd driver
   - W=1 warning cleanup of subsystem
   - Updates to ti-k3-dma, dw, idxd drivers"

* tag 'dmaengine-5.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine: (68 commits)
  dmaengine: dw: Don't include unneeded header to platform data header
  dmaengine: Actions: Add support for S700 DMA engine
  dmaengine: Actions: get rid of bit fields from dma descriptor
  dt-bindings: dmaengine: convert Actions Semi Owl SoCs bindings to yaml
  dmaengine: idxd: add missing invalid flags field to completion
  dmaengine: dw: Initialize max_sg_burst capability
  dmaengine: dw: Introduce max burst length hw config
  dmaengine: dw: Initialize min and max burst DMA device capability
  dmaengine: dw: Set DMA device max segment size parameter
  dmaengine: dw: Take HC_LLP flag into account for noLLP auto-config
  dmaengine: Introduce DMA-device device_caps callback
  dmaengine: Introduce max SG burst capability
  dmaengine: Introduce min burst length capability
  dt-bindings: dma: dw: Add max burst transaction length property
  dt-bindings: dma: dw: Convert DW DMAC to DT binding
  dmaengine: ti: k3-udma: Query throughput level information from hardware
  dmaengine: ti: k3-udma: Use defines for capabilities register parsing
  dmaengine: xilinx: dpdma: Fix kerneldoc warning
  dmaengine: xilinx: dpdma: add missing kernel doc
  dmaengine: xilinx: dpdma: remove comparison of unsigned expression
  ...

43 files changed, 720 insertions, 648 deletions

diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 668e9636c547..518a1437862a 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -285,8 +285,9 @@ config INTEL_IDMA64
 config INTEL_IDXD
 	tristate "Intel Data Accelerators support"
 	depends on PCI && X86_64
+	depends on PCI_MSI
+	depends on SBITMAP
 	select DMA_ENGINE
-	select SBITMAP
 	help
 	  Enable support for the Intel(R) data accelerators present
 	  in Intel Xeon CPU.
diff --git a/drivers/dma/acpi-dma.c b/drivers/dma/acpi-dma.c
index 8a05db3343d3..35f4804ea4af 100644
--- a/drivers/dma/acpi-dma.c
+++ b/drivers/dma/acpi-dma.c
@@ -358,19 +358,12 @@ struct dma_chan *acpi_dma_request_slave_chan_by_index(struct device *dev,
 {
 	struct acpi_dma_parser_data pdata;
 	struct acpi_dma_spec *dma_spec = &pdata.dma_spec;
+	struct acpi_device *adev = ACPI_COMPANION(dev);
 	struct list_head resource_list;
-	struct acpi_device *adev;
 	struct acpi_dma *adma;
 	struct dma_chan *chan = NULL;
 	int found;
-
-	/* Check if the device was enumerated by ACPI */
-	if (!dev)
-		return ERR_PTR(-ENODEV);
-
-	adev = ACPI_COMPANION(dev);
-	if (!adev)
-		return ERR_PTR(-ENODEV);
+	int ret;
 
 	memset(&pdata, 0, sizeof(pdata));
 	pdata.index = index;
@@ -380,9 +373,11 @@ struct dma_chan *acpi_dma_request_slave_chan_by_index(struct device *dev,
 	dma_spec->slave_id = -1;
 
 	INIT_LIST_HEAD(&resource_list);
-	acpi_dev_get_resources(adev, &resource_list,
-			acpi_dma_parse_fixed_dma, &pdata);
+	ret = acpi_dev_get_resources(adev, &resource_list,
+				     acpi_dma_parse_fixed_dma, &pdata);
 	acpi_dev_free_resource_list(&resource_list);
+	if (ret < 0)
+		return ERR_PTR(ret);
 
 	if (dma_spec->slave_id < 0 || dma_spec->chan_id < 0)
 		return ERR_PTR(-ENODEV);
diff --git a/drivers/dma/altera-msgdma.c b/drivers/dma/altera-msgdma.c
index 539e785039ca..321ac3a7aa41 100644
--- a/drivers/dma/altera-msgdma.c
+++ b/drivers/dma/altera-msgdma.c
@@ -153,7 +153,8 @@ struct msgdma_extended_desc {
  * struct msgdma_sw_desc - implements a sw descriptor
  * @async_tx: support for the async_tx api
  * @hw_desc: assosiated HW descriptor
- * @free_list: node of the free SW descriprots list
+ * @node: node to move from the free list to the tx list
+ * @tx_list: transmit list node
  */
 struct msgdma_sw_desc {
 	struct dma_async_tx_descriptor async_tx;
@@ -162,7 +163,7 @@ struct msgdma_sw_desc {
 	struct list_head tx_list;
 };
 
-/**
+/*
  * struct msgdma_device - DMA device structure
  */
 struct msgdma_device {
@@ -258,6 +259,7 @@ static void msgdma_free_desc_list(struct msgdma_device *mdev,
  * @dst: Destination buffer address
  * @src: Source buffer address
  * @len: Transfer length
+ * @stride: Read/write stride value to set
  */
 static void msgdma_desc_config(struct msgdma_extended_desc *desc,
 			       dma_addr_t dst, dma_addr_t src, size_t len,
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index 73a20780744b..45bbcd6146fd 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -656,7 +656,7 @@ static irqreturn_t at_dma_interrupt(int irq, void *dev_id)
 
 /**
  * atc_tx_submit - set the prepared descriptor(s) to be executed by the engine
- * @desc: descriptor at the head of the transaction chain
+ * @tx: descriptor at the head of the transaction chain
  *
  * Queue chain if DMA engine is working already
  *
@@ -1196,7 +1196,7 @@ err:
 	return NULL;
 }
 
-/**
+/*
  * atc_dma_cyclic_check_values
  * Check for too big/unaligned periods and unaligned DMA buffer
  */
@@ -1217,7 +1217,7 @@ err_out:
 	return -EINVAL;
 }
 
-/**
+/*
  * atc_dma_cyclic_fill_desc - Fill one period descriptor
  */
 static int
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 2b06a7a8629d..a53e71d2bbd4 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -592,13 +592,25 @@ int dma_get_slave_caps(struct dma_chan *chan, struct dma_slave_caps *caps)
 	caps->src_addr_widths = device->src_addr_widths;
 	caps->dst_addr_widths = device->dst_addr_widths;
 	caps->directions = device->directions;
+	caps->min_burst = device->min_burst;
 	caps->max_burst = device->max_burst;
+	caps->max_sg_burst = device->max_sg_burst;
 	caps->residue_granularity = device->residue_granularity;
 	caps->descriptor_reuse = device->descriptor_reuse;
 	caps->cmd_pause = !!device->device_pause;
 	caps->cmd_resume = !!device->device_resume;
 	caps->cmd_terminate = !!device->device_terminate_all;
 
+	/*
+	 * DMA engine device might be configured with non-uniformly
+	 * distributed slave capabilities per device channels. In this
+	 * case the corresponding driver may provide the device_caps
+	 * callback to override the generic capabilities with
+	 * channel-specific ones.
+	 */
+	if (device->device_caps)
+		device->device_caps(chan, caps);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(dma_get_slave_caps);
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index 604f80357931..45d4d92e91db 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -829,7 +829,10 @@ static int dmatest_func(void *data)
 			result("test timed out", total_tests, src->off, dst->off,
 			       len, 0);
 			goto error_unmap_continue;
-		} else if (status != DMA_COMPLETE) {
+		} else if (status != DMA_COMPLETE &&
+			   !(dma_has_cap(DMA_COMPLETION_NO_ORDER,
+					 dev->cap_mask) &&
+			     status == DMA_OUT_OF_ORDER)) {
 			result(status == DMA_ERROR ?
 			       "completion error status" :
 			       "completion busy status", total_tests, src->off,
@@ -1007,6 +1010,12 @@ static int dmatest_add_channel(struct dmatest_info *info,
 	dtc->chan = chan;
 	INIT_LIST_HEAD(&dtc->threads);
 
+	if (dma_has_cap(DMA_COMPLETION_NO_ORDER, dma_dev->cap_mask) &&
+	    info->params.polled) {
+		info->params.polled = false;
+		pr_warn("DMA_COMPLETION_NO_ORDER, polled disabled\n");
+	}
+
 	if (dma_has_cap(DMA_MEMCPY, dma_dev->cap_mask)) {
 		if (dmatest == 0) {
 			cnt = dmatest_add_threads(info, dtc, DMA_MEMCPY);
diff --git a/drivers/dma/dw/Makefile b/drivers/dma/dw/Makefile
index b6f06699e91a..a6f358ad8591 100644
--- a/drivers/dma/dw/Makefile
+++ b/drivers/dma/dw/Makefile
@@ -1,11 +1,11 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_DW_DMAC_CORE)	+= dw_dmac_core.o
-dw_dmac_core-objs	:= core.o dw.o idma32.o
+dw_dmac_core-y			:= core.o dw.o idma32.o
+dw_dmac_core-$(CONFIG_ACPI)	+= acpi.o
 
 obj-$(CONFIG_DW_DMAC)		+= dw_dmac.o
 dw_dmac-y			:= platform.o
-dw_dmac-$(CONFIG_ACPI)		+= acpi.o
 dw_dmac-$(CONFIG_OF)		+= of.o
 
 obj-$(CONFIG_DW_DMAC_PCI)	+= dw_dmac_pci.o
-dw_dmac_pci-objs	:= pci.o
+dw_dmac_pci-y			:= pci.o
diff --git a/drivers/dma/dw/acpi.c b/drivers/dma/dw/acpi.c
index f6e8d55b4f6e..c510c109d2c3 100644
--- a/drivers/dma/dw/acpi.c
+++ b/drivers/dma/dw/acpi.c
@@ -41,6 +41,7 @@ void dw_dma_acpi_controller_register(struct dw_dma *dw)
 	if (ret)
 		dev_err(dev, "could not register acpi_dma_controller\n");
 }
+EXPORT_SYMBOL_GPL(dw_dma_acpi_controller_register);
 
 void dw_dma_acpi_controller_free(struct dw_dma *dw)
 {
@@ -51,3 +52,4 @@ void dw_dma_acpi_controller_free(struct dw_dma *dw)
 
 	acpi_dma_controller_free(dev);
 }
+EXPORT_SYMBOL_GPL(dw_dma_acpi_controller_free);
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index a1b56f52db2f..4700f2e87a62 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -786,6 +786,11 @@ static int dwc_config(struct dma_chan *chan, struct dma_slave_config *sconfig)
 
 	memcpy(&dwc->dma_sconfig, sconfig, sizeof(*sconfig));
 
+	dwc->dma_sconfig.src_maxburst =
+		clamp(dwc->dma_sconfig.src_maxburst, 0U, dwc->max_burst);
+	dwc->dma_sconfig.dst_maxburst =
+		clamp(dwc->dma_sconfig.dst_maxburst, 0U, dwc->max_burst);
+
 	dw->encode_maxburst(dwc, &dwc->dma_sconfig.src_maxburst);
 	dw->encode_maxburst(dwc, &dwc->dma_sconfig.dst_maxburst);
 
@@ -1037,6 +1042,25 @@ static void dwc_free_chan_resources(struct dma_chan *chan)
 	dev_vdbg(chan2dev(chan), "%s: done\n", __func__);
 }
 
+static void dwc_caps(struct dma_chan *chan, struct dma_slave_caps *caps)
+{
+	struct dw_dma_chan *dwc = to_dw_dma_chan(chan);
+
+	caps->max_burst = dwc->max_burst;
+
+	/*
+	 * It might be crucial for some devices to have the hardware
+	 * accelerated multi-block transfers supported, aka LLPs in DW DMAC
+	 * notation. So if LLPs are supported then max_sg_burst is set to
+	 * zero which means unlimited number of SG entries can be handled in a
+	 * single DMA transaction, otherwise it's just one SG entry.
+	 */
+	if (dwc->nollp)
+		caps->max_sg_burst = 1;
+	else
+		caps->max_sg_burst = 0;
+}
+
 int do_dma_probe(struct dw_dma_chip *chip)
 {
 	struct dw_dma *dw = chip->dw;
@@ -1166,11 +1190,23 @@ int do_dma_probe(struct dw_dma_chip *chip)
 			 */
 			dwc->block_size =
 				(4 << ((pdata->block_size >> 4 * i) & 0xf)) - 1;
+
+			/*
+			 * According to the DW DMA databook the true scatter-
+			 * gether LLPs aren't available if either multi-block
+			 * config is disabled (CHx_MULTI_BLK_EN == 0) or the
+			 * LLP register is hard-coded to zeros
+			 * (CHx_HC_LLP == 1).
+			 */
 			dwc->nollp =
-				(dwc_params >> DWC_PARAMS_MBLK_EN & 0x1) == 0;
+				(dwc_params >> DWC_PARAMS_MBLK_EN & 0x1) == 0 ||
+				(dwc_params >> DWC_PARAMS_HC_LLP & 0x1) == 1;
+			dwc->max_burst =
+				(0x4 << (dwc_params >> DWC_PARAMS_MSIZE & 0x7));
 		} else {
 			dwc->block_size = pdata->block_size;
 			dwc->nollp = !pdata->multi_block[i];
+			dwc->max_burst = pdata->max_burst[i] ?: DW_DMA_MAX_BURST;
 		}
 	}
 
@@ -1193,6 +1229,7 @@ int do_dma_probe(struct dw_dma_chip *chip)
 	dw->dma.device_prep_dma_memcpy = dwc_prep_dma_memcpy;
 	dw->dma.device_prep_slave_sg = dwc_prep_slave_sg;
 
+	dw->dma.device_caps = dwc_caps;
 	dw->dma.device_config = dwc_config;
 	dw->dma.device_pause = dwc_pause;
 	dw->dma.device_resume = dwc_resume;
@@ -1202,12 +1239,21 @@ int do_dma_probe(struct dw_dma_chip *chip)
 	dw->dma.device_issue_pending = dwc_issue_pending;
 
 	/* DMA capabilities */
+	dw->dma.min_burst = DW_DMA_MIN_BURST;
+	dw->dma.max_burst = DW_DMA_MAX_BURST;
 	dw->dma.src_addr_widths = DW_DMA_BUSWIDTHS;
 	dw->dma.dst_addr_widths = DW_DMA_BUSWIDTHS;
 	dw->dma.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV) |
 			     BIT(DMA_MEM_TO_MEM);
 	dw->dma.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
 
+	/*
+	 * For now there is no hardware with non uniform maximum block size
+	 * across all of the device channels, so we set the maximum segment
+	 * size as the block size found for the very first channel.
+	 */
+	dma_set_max_seg_size(dw->dma.dev, dw->chan[0].block_size);
+
 	err = dma_async_device_register(&dw->dma);
 	if (err)
 		goto err_dma_register;
diff --git a/drivers/dma/dw/of.c b/drivers/dma/dw/of.c
index 9e27831dee32..1474b3817ef4 100644
--- a/drivers/dma/dw/of.c
+++ b/drivers/dma/dw/of.c
@@ -98,6 +98,11 @@ struct dw_dma_platform_data *dw_dma_parse_dt(struct platform_device *pdev)
 			pdata->multi_block[tmp] = 1;
 	}
 
+	if (of_property_read_u32_array(np, "snps,max-burst-len", pdata->max_burst,
+				       nr_channels)) {
+		memset32(pdata->max_burst, DW_DMA_MAX_BURST, nr_channels);
+	}
+
 	if (!of_property_read_u32(np, "snps,dma-protection-control", &tmp)) {
 		if (tmp > CHAN_PROTCTL_MASK)
 			return NULL;
diff --git a/drivers/dma/dw/pci.c b/drivers/dma/dw/pci.c
index cf6e8ec4c0ff..1142aa6f8c4a 100644
--- a/drivers/dma/dw/pci.c
+++ b/drivers/dma/dw/pci.c
@@ -60,6 +60,8 @@ static int dw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *pid)
 	if (ret)
 		return ret;
 
+	dw_dma_acpi_controller_register(chip->dw);
+
 	pci_set_drvdata(pdev, data);
 
 	return 0;
@@ -71,6 +73,8 @@ static void dw_pci_remove(struct pci_dev *pdev)
 	struct dw_dma_chip *chip = data->chip;
 	int ret;
 
+	dw_dma_acpi_controller_free(chip->dw);
+
 	ret = data->remove(chip);
 	if (ret)
 		dev_warn(&pdev->dev, "can't remove device properly: %d\n", ret);
diff --git a/drivers/dma/dw/regs.h b/drivers/dma/dw/regs.h
index 3fce66ecee7a..76654bd13c1a 100644
--- a/drivers/dma/dw/regs.h
+++ b/drivers/dma/dw/regs.h
@@ -125,6 +125,8 @@ struct dw_dma_regs {
 
 /* Bitfields in DWC_PARAMS */
 #define DWC_PARAMS_MBLK_EN	11		/* multi block transfer */
+#define DWC_PARAMS_HC_LLP	13		/* set LLP register to zero */
+#define DWC_PARAMS_MSIZE	16		/* max group transaction size */
 
 /* bursts size */
 enum dw_dma_msize {
@@ -283,6 +285,7 @@ struct dw_dma_chan {
 	/* hardware configuration */
 	unsigned int		block_size;
 	bool			nollp;
+	u32			max_burst;
 
 	/* custom slave configuration */
 	struct dw_dma_slave	dws;
diff --git a/drivers/dma/ep93xx_dma.c b/drivers/dma/ep93xx_dma.c
index 9c8b4d35cf03..87a246012629 100644
--- a/drivers/dma/ep93xx_dma.c
+++ b/drivers/dma/ep93xx_dma.c
@@ -147,6 +147,7 @@ struct ep93xx_dma_desc {
  *                is set via .device_config before slave operation is
  *                prepared
  * @runtime_ctrl: M2M runtime values for the control register.
+ * @slave_config: slave configuration
  *
  * As EP93xx DMA controller doesn't support real chained DMA descriptors we
  * will have slightly different scheme here: @active points to a head of
@@ -187,6 +188,7 @@ struct ep93xx_dma_chan {
  * @dma_dev: holds the dmaengine device
  * @m2m: is this an M2M or M2P device
  * @hw_setup: method which sets the channel up for operation
+ * @hw_synchronize: synchronizes DMA channel termination to current context
  * @hw_shutdown: shuts the channel down and flushes whatever is left
  * @hw_submit: pushes active descriptor(s) to the hardware
  * @hw_interrupt: handle the interrupt
diff --git a/drivers/dma/fsl-qdma.c b/drivers/dma/fsl-qdma.c
index 95cc0256b387..ed2ab46b15e7 100644
--- a/drivers/dma/fsl-qdma.c
+++ b/drivers/dma/fsl-qdma.c
@@ -56,7 +56,7 @@
 
 /* Registers for bit and genmask */
 #define FSL_QDMA_CQIDR_SQT		BIT(15)
-#define QDMA_CCDF_FOTMAT		BIT(29)
+#define QDMA_CCDF_FORMAT		BIT(29)
 #define QDMA_CCDF_SER			BIT(30)
 #define QDMA_SG_FIN			BIT(30)
 #define QDMA_SG_LEN_MASK		GENMASK(29, 0)
@@ -110,8 +110,19 @@
 #define FSL_QDMA_CMD_DSEN_OFFSET	19
 #define FSL_QDMA_CMD_LWC_OFFSET		16
 
+/* Field definition for Descriptor status */
+#define QDMA_CCDF_STATUS_RTE		BIT(5)
+#define QDMA_CCDF_STATUS_WTE		BIT(4)
+#define QDMA_CCDF_STATUS_CDE		BIT(2)
+#define QDMA_CCDF_STATUS_SDE		BIT(1)
+#define QDMA_CCDF_STATUS_DDE		BIT(0)
+#define QDMA_CCDF_STATUS_MASK		(QDMA_CCDF_STATUS_RTE | \
+					QDMA_CCDF_STATUS_WTE | \
+					QDMA_CCDF_STATUS_CDE | \
+					QDMA_CCDF_STATUS_SDE | \
+					QDMA_CCDF_STATUS_DDE)
+
 /* Field definition for Descriptor offset */
-#define QDMA_CCDF_STATUS		20
 #define QDMA_CCDF_OFFSET		20
 #define QDMA_SDDF_CMD(x)		(((u64)(x)) << 32)
 
@@ -136,7 +147,7 @@
  * @__reserved1:	    Reserved field.
  * @cfg8b_w1:		    Compound descriptor command queue origin produced
  *			    by qDMA and dynamic debug field.
- * @data		    Pointer to the memory 40-bit address, describes DMA
+ * @data:		    Pointer to the memory 40-bit address, describes DMA
  *			    source information and DMA destination information.
  */
 struct fsl_qdma_format {
@@ -243,13 +254,14 @@ qdma_ccdf_get_offset(const struct fsl_qdma_format *ccdf)
 static inline void
 qdma_ccdf_set_format(struct fsl_qdma_format *ccdf, int offset)
 {
-	ccdf->cfg = cpu_to_le32(QDMA_CCDF_FOTMAT | offset);
+	ccdf->cfg = cpu_to_le32(QDMA_CCDF_FORMAT |
+				(offset << QDMA_CCDF_OFFSET));
 }
 
 static inline int
 qdma_ccdf_get_status(const struct fsl_qdma_format *ccdf)
 {
-	return (le32_to_cpu(ccdf->status) & QDMA_CCDF_MASK) >> QDMA_CCDF_STATUS;
+	return (le32_to_cpu(ccdf->status) & QDMA_CCDF_STATUS_MASK);
 }
 
 static inline void
@@ -618,6 +630,7 @@ fsl_qdma_queue_transfer_complete(struct fsl_qdma_engine *fsl_qdma,
 {
 	bool duplicate;
 	u32 reg, i, count;
+	u8 completion_status;
 	struct fsl_qdma_queue *temp_queue;
 	struct fsl_qdma_format *status_addr;
 	struct fsl_qdma_comp *fsl_comp = NULL;
@@ -677,6 +690,8 @@ fsl_qdma_queue_transfer_complete(struct fsl_qdma_engine *fsl_qdma,
 		}
 		list_del(&fsl_comp->list);
 
+		completion_status = qdma_ccdf_get_status(status_addr);
+
 		reg = qdma_readl(fsl_qdma, block + FSL_QDMA_BSQMR);
 		reg |= FSL_QDMA_BSQMR_DI;
 		qdma_desc_addr_set64(status_addr, 0x0);
@@ -686,6 +701,31 @@ fsl_qdma_queue_transfer_complete(struct fsl_qdma_engine *fsl_qdma,
 		qdma_writel(fsl_qdma, reg, block + FSL_QDMA_BSQMR);
 		spin_unlock(&temp_queue->queue_lock);
 
+		/* The completion_status is evaluated here
+		 * (outside of spin lock)
+		 */
+		if (completion_status) {
+			/* A completion error occurred! */
+			if (completion_status & QDMA_CCDF_STATUS_WTE) {
+				/* Write transaction error */
+				fsl_comp->vdesc.tx_result.result =
+					DMA_TRANS_WRITE_FAILED;
+			} else if (completion_status & QDMA_CCDF_STATUS_RTE) {
+				/* Read transaction error */
+				fsl_comp->vdesc.tx_result.result =
+					DMA_TRANS_READ_FAILED;
+			} else {
+				/* Command/source/destination
+				 * description error
+				 */
+				fsl_comp->vdesc.tx_result.result =
+					DMA_TRANS_ABORTED;
+				dev_err(fsl_qdma->dma_dev.dev,
+					"DMA status descriptor error %x\n",
+					completion_status);
+			}
+		}
+
 		spin_lock(&fsl_comp->qchan->vchan.lock);
 		vchan_cookie_complete(&fsl_comp->vdesc);
 		fsl_comp->qchan->status = DMA_COMPLETE;
@@ -700,11 +740,22 @@ static irqreturn_t fsl_qdma_error_handler(int irq, void *dev_id)
 	unsigned int intr;
 	struct fsl_qdma_engine *fsl_qdma = dev_id;
 	void __iomem *status = fsl_qdma->status_base;
+	unsigned int decfdw0r;
+	unsigned int decfdw1r;
+	unsigned int decfdw2r;
+	unsigned int decfdw3r;
 
 	intr = qdma_readl(fsl_qdma, status + FSL_QDMA_DEDR);
 
-	if (intr)
-		dev_err(fsl_qdma->dma_dev.dev, "DMA transaction error!\n");
+	if (intr) {
+		decfdw0r = qdma_readl(fsl_qdma, status + FSL_QDMA_DECFDW0R);
+		decfdw1r = qdma_readl(fsl_qdma, status + FSL_QDMA_DECFDW1R);
+		decfdw2r = qdma_readl(fsl_qdma, status + FSL_QDMA_DECFDW2R);
+		decfdw3r = qdma_readl(fsl_qdma, status + FSL_QDMA_DECFDW3R);
+		dev_err(fsl_qdma->dma_dev.dev,
+			"DMA transaction error! (%x: %x-%x-%x-%x)\n",
+			intr, decfdw0r, decfdw1r, decfdw2r, decfdw3r);
+	}
 
 	qdma_writel(fsl_qdma, FSL_QDMA_DEDR_CLEAR, status + FSL_QDMA_DEDR);
 	return IRQ_HANDLED;
diff --git a/drivers/dma/hisi_dma.c b/drivers/dma/hisi_dma.c
index ed3619266a48..e1a958ae7925 100644
--- a/drivers/dma/hisi_dma.c
+++ b/drivers/dma/hisi_dma.c
@@ -511,7 +511,6 @@ static int hisi_dma_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	struct device *dev = &pdev->dev;
 	struct hisi_dma_dev *hdma_dev;
 	struct dma_device *dma_dev;
-	size_t dev_size;
 	int ret;
 
 	ret = pcim_enable_device(pdev);
@@ -534,9 +533,7 @@ static int hisi_dma_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (ret)
 		return ret;
 
-	dev_size = sizeof(struct hisi_dma_chan) * HISI_DMA_CHAN_NUM +
-		   sizeof(*hdma_dev);
-	hdma_dev = devm_kzalloc(dev, dev_size, GFP_KERNEL);
+	hdma_dev = devm_kzalloc(dev, struct_size(hdma_dev, chan, HISI_DMA_CHAN_NUM), GFP_KERNEL);
 	if (!hdma_dev)
 		return -EINVAL;
 
diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c
index cb376cf6a2d2..c3976156db2f 100644
--- a/drivers/dma/idxd/cdev.c
+++ b/drivers/dma/idxd/cdev.c
@@ -115,6 +115,9 @@ static int idxd_cdev_release(struct inode *node, struct file *filep)
 	dev_dbg(dev, "%s called\n", __func__);
 	filep->private_data = NULL;
 
+	/* Wait for in-flight operations to complete. */
+	idxd_wq_drain(wq);
+
 	kfree(ctx);
 	mutex_lock(&wq->wq_lock);
 	idxd_wq_put(wq);
diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index 8d2718c585dc..14b45853aa5f 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -6,70 +6,39 @@
 #include <linux/pci.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include <linux/dmaengine.h>
+#include <linux/irq.h>
+#include <linux/msi.h>
 #include <uapi/linux/idxd.h>
 #include "../dmaengine.h"
 #include "idxd.h"
 #include "registers.h"
 
-static int idxd_cmd_wait(struct idxd_device *idxd, u32 *status, int timeout);
-static int idxd_cmd_send(struct idxd_device *idxd, int cmd_code, u32 operand);
+static void idxd_cmd_exec(struct idxd_device *idxd, int cmd_code, u32 operand,
+			  u32 *status);
 
 /* Interrupt control bits */
-int idxd_mask_msix_vector(struct idxd_device *idxd, int vec_id)
+void idxd_mask_msix_vector(struct idxd_device *idxd, int vec_id)
 {
-	struct pci_dev *pdev = idxd->pdev;
-	int msixcnt = pci_msix_vec_count(pdev);
-	union msix_perm perm;
-	u32 offset;
-
-	if (vec_id < 0 || vec_id >= msixcnt)
-		return -EINVAL;
+	struct irq_data *data = irq_get_irq_data(idxd->msix_entries[vec_id].vector);
 
-	offset = idxd->msix_perm_offset + vec_id * 8;
-	perm.bits = ioread32(idxd->reg_base + offset);
-	perm.ignore = 1;
-	iowrite32(perm.bits, idxd->reg_base + offset);
-
-	return 0;
+	pci_msi_mask_irq(data);
 }
 
 void idxd_mask_msix_vectors(struct idxd_device *idxd)
 {
 	struct pci_dev *pdev = idxd->pdev;
 	int msixcnt = pci_msix_vec_count(pdev);
-	int i, rc;
+	int i;
 
-	for (i = 0; i < msixcnt; i++) {
-		rc = idxd_mask_msix_vector(idxd, i);
-		if (rc < 0)
-			dev_warn(&pdev->dev,
-				 "Failed disabling msix vec %d\n", i);
-	}
+	for (i = 0; i < msixcnt; i++)
+		idxd_mask_msix_vector(idxd, i);
 }
 
-int idxd_unmask_msix_vector(struct idxd_device *idxd, int vec_id)
+void idxd_unmask_msix_vector(struct idxd_device *idxd, int vec_id)
 {
-	struct pci_dev *pdev = idxd->pdev;
-	int msixcnt = pci_msix_vec_count(pdev);
-	union msix_perm perm;
-	u32 offset;
-
-	if (vec_id < 0 || vec_id >= msixcnt)
-		return -EINVAL;
+	struct irq_data *data = irq_get_irq_data(idxd->msix_entries[vec_id].vector);
 
-	offset = idxd->msix_perm_offset + vec_id * 8;
-	perm.bits = ioread32(idxd->reg_base + offset);
-	perm.ignore = 0;
-	iowrite32(perm.bits, idxd->reg_base + offset);
-
-	/*
-	 * A readback from the device ensures that any previously generated
-	 * completion record writes are visible to software based on PCI
-	 * ordering rules.
-	 */
-	perm.bits = ioread32(idxd->reg_base + offset);
-
-	return 0;
+	pci_msi_unmask_irq(data);
 }
 
 void idxd_unmask_error_interrupts(struct idxd_device *idxd)
@@ -160,16 +129,14 @@ static int alloc_descs(struct idxd_wq *wq, int num)
 int idxd_wq_alloc_resources(struct idxd_wq *wq)
 {
 	struct idxd_device *idxd = wq->idxd;
-	struct idxd_group *group = wq->group;
 	struct device *dev = &idxd->pdev->dev;
 	int rc, num_descs, i;
 
 	if (wq->type != IDXD_WQT_KERNEL)
 		return 0;
 
-	num_descs = wq->size +
-		idxd->hw.gen_cap.max_descs_per_engine * group->num_engines;
-	wq->num_descs = num_descs;
+	wq->num_descs = wq->size;
+	num_descs = wq->size;
 
 	rc = alloc_hw_descs(wq, num_descs);
 	if (rc &