Merge tag 'dmaengine-5.17-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine

Pull dmaengine updates from Vinod Koul:
 "A bunch of new support and few updates to drivers:

  New support:
   - DMA_MEMCPY_SG support is bought back as we have a user in Xilinx
     driver
   - Support for TI J721S2 SoC in k3-udma driver
   - Support for Ingenic MDMA and BDMA in the JZ4760
   - Support for Renesas r8a779f0 dmac

  Updates:
   - We are finally getting rid of slave_id, so this brings in the
     changes across tree for that
   - updates for idxd driver
   - at_xdmac driver cleanup"

* tag 'dmaengine-5.17-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine: (60 commits)
  dt-bindings: dma-controller: Split interrupt fields in example
  dmaengine: pch_dma: Remove usage of the deprecated "pci-dma-compat.h" API
  dmaengine: at_xdmac: Fix race over irq_status
  dmaengine: at_xdmac: Remove a level of indentation in at_xdmac_tasklet()
  dmaengine: at_xdmac: Fix at_xdmac_lld struct definition
  dmaengine: at_xdmac: Fix lld view setting
  dmaengine: at_xdmac: Remove a level of indentation in at_xdmac_advance_work()
  dmaengine: at_xdmac: Fix concurrency over xfers_list
  dmaengine: at_xdmac: Move the free desc to the tail of the desc list
  dmaengine: at_xdmac: Fix race for the tx desc callback
  dmaengine: at_xdmac: Fix concurrency over chan's completed_cookie
  dmaengine: at_xdmac: Print debug message after realeasing the lock
  dmaengine: at_xdmac: Start transfer for cyclic channels in issue_pending
  dmaengine: at_xdmac: Don't start transactions at tx_submit level
  dmaengine: idxd: deprecate token sysfs attributes for read buffers
  dmaengine: idxd: change bandwidth token to read buffers
  dmaengine: idxd: fix wq settings post wq disable
  dmaengine: idxd: change MSIX allocation based on per wq activation
  dmaengine: idxd: fix descriptor flushing locking
  dmaengine: idxd: embed irq_entry in idxd_wq struct
  ...

Documentation/ABI/stable/sysfs-driver-dma-idxd

@@ -41,14 +41,14 @@ KernelVersion:  5.6.0
 Contact:        dmaengine@vger.kernel.org
 Description:    The maximum number of groups can be created under this device.
 
-What:           /sys/bus/dsa/devices/dsa<m>/max_tokens
-Date:           Oct 25, 2019
-KernelVersion:  5.6.0
+What:           /sys/bus/dsa/devices/dsa<m>/max_read_buffers
+Date:           Dec 10, 2021
+KernelVersion:  5.17.0
 Contact:        dmaengine@vger.kernel.org
-Description:    The total number of bandwidth tokens supported by this device.
-		The bandwidth tokens represent resources within the DSA
+Description:    The total number of read buffers supported by this device.
+		The read buffers represent resources within the DSA
 		implementation, and these resources are allocated by engines to
-		support operations.
+		support operations. See DSA spec v1.2 9.2.4 Total Read Buffers.
 
 What:           /sys/bus/dsa/devices/dsa<m>/max_transfer_size
 Date:           Oct 25, 2019
@@ -115,13 +115,13 @@ KernelVersion:  5.6.0
 Contact:        dmaengine@vger.kernel.org
 Description:    To indicate if this device is configurable or not.
 
-What:           /sys/bus/dsa/devices/dsa<m>/token_limit
-Date:           Oct 25, 2019
-KernelVersion:  5.6.0
+What:           /sys/bus/dsa/devices/dsa<m>/read_buffer_limit
+Date:           Dec 10, 2021
+KernelVersion:  5.17.0
 Contact:        dmaengine@vger.kernel.org
-Description:    The maximum number of bandwidth tokens that may be in use at
+Description:    The maximum number of read buffers that may be in use at
 		one time by operations that access low bandwidth memory in the
-		device.
+		device. See DSA spec v1.2 9.2.8 GENCFG on Global Read Buffer Limit.
 
 What:		/sys/bus/dsa/devices/dsa<m>/cmd_status
 Date:		Aug 28, 2020
@@ -220,8 +220,38 @@ Contact:	dmaengine@vger.kernel.org
 Description:	Show the current number of entries in this WQ if WQ Occupancy
 		Support bit WQ capabilities is 1.
 
+What:		/sys/bus/dsa/devices/wq<m>.<n>/enqcmds_retries
+Date		Oct 29, 2021
+KernelVersion:	5.17.0
+Contact:	dmaengine@vger.kernel.org
+Description:	Indicate the number of retires for an enqcmds submission on a sharedwq.
+		A max value to set attribute is capped at 64.
+
 What:           /sys/bus/dsa/devices/engine<m>.<n>/group_id
 Date:           Oct 25, 2019
 KernelVersion:  5.6.0
 Contact:        dmaengine@vger.kernel.org
 Description:    The group that this engine belongs to.
+
+What:		/sys/bus/dsa/devices/group<m>.<n>/use_read_buffer_limit
+Date:		Dec 10, 2021
+KernelVersion:	5.17.0
+Contact:	dmaengine@vger.kernel.org
+Description:	Enable the use of global read buffer limit for the group. See DSA
+		spec v1.2 9.2.18 GRPCFG Use Global Read Buffer Limit.
+
+What:		/sys/bus/dsa/devices/group<m>.<n>/read_buffers_allowed
+Date:		Dec 10, 2021
+KernelVersion:	5.17.0
+Contact:	dmaengine@vger.kernel.org
+Description:	Indicates max number of read buffers that may be in use at one time
+		by all engines in the group. See DSA spec v1.2 9.2.18 GRPCFG Read
+		Buffers Allowed.
+
+What:		/sys/bus/dsa/devices/group<m>.<n>/read_buffers_reserved
+Date:		Dec 10, 2021
+KernelVersion:	5.17.0
+Contact:	dmaengine@vger.kernel.org
+Description:	Indicates the number of Read Buffers reserved for the use of
+		engines in the group. See DSA spec v1.2 9.2.18 GRPCFG Read Buffers
+		Reserved.

Documentation/devicetree/bindings/dma/arm,pl330.yaml

+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/dma/arm,pl330.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: ARM PrimeCell PL330 DMA Controller
+
+maintainers:
+  - Vinod Koul <vkoul@kernel.org>
+
+description:
+  The ARM PrimeCell PL330 DMA controller can move blocks of memory contents
+  between memory and peripherals or memory to memory.
+
+# We need a select here so we don't match all nodes with 'arm,primecell'
+select:
+  properties:
+    compatible:
+      contains:
+        const: arm,pl330
+  required:
+    - compatible
+
+allOf:
+  - $ref: dma-controller.yaml#
+  - $ref: /schemas/arm/primecell.yaml#
+
+properties:
+  compatible:
+    items:
+      - enum:
+          - arm,pl330
+      - const: arm,primecell
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    minItems: 1
+    maxItems: 32
+    description: A single combined interrupt or an interrupt per event
+
+  '#dma-cells':
+    const: 1
+    description: Contains the DMA request number for the consumer
+
+  arm,pl330-broken-no-flushp:
+    type: boolean
+    description: quirk for avoiding to execute DMAFLUSHP
+
+  arm,pl330-periph-burst:
+    type: boolean
+    description: quirk for performing burst transfer only
+
+  dma-coherent: true
+
+  resets:
+    minItems: 1
+    maxItems: 2
+
+  reset-names:
+    minItems: 1
+    items:
+      - const: dma
+      - const: dma-ocp
+
+required:
+  - compatible
+  - reg
+  - interrupts
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    dma-controller@12680000 {
+        compatible = "arm,pl330", "arm,primecell";
+        reg = <0x12680000 0x1000>;
+        interrupts = <99>;
+        #dma-cells = <1>;
+    };
+...

Documentation/devicetree/bindings/dma/arm-pl08x.yaml

@@ -10,6 +10,7 @@ maintainers:
   - Vinod Koul <vkoul@kernel.org>
 
 allOf:
+  - $ref: /schemas/arm/primecell.yaml#
   - $ref: "dma-controller.yaml#"
 
 # We need a select here so we don't match all nodes with 'arm,primecell'
@@ -89,6 +90,9 @@ properties:
       - 64
     description: bus width used for memcpy in bits. FTDMAC020 also accept 64 bits
 
+  resets:
+    maxItems: 1
+
 required:
   - reg
   - interrupts

Documentation/devicetree/bindings/dma/arm-pl330.txt

-* ARM PrimeCell PL330 DMA Controller
-
-The ARM PrimeCell PL330 DMA controller can move blocks of memory contents
-between memory and peripherals or memory to memory.
-
-Required properties:
-  - compatible: should include both "arm,pl330" and "arm,primecell".
-  - reg: physical base address of the controller and length of memory mapped
-    region.
-  - interrupts: interrupt number to the cpu.
-
-Optional properties:
-  - dma-coherent      : Present if dma operations are coherent
-  - #dma-cells: must be <1>. used to represent the number of integer
-    cells in the dmas property of client device.
-  - dma-channels: contains the total number of DMA channels supported by the DMAC
-  - dma-requests: contains the total number of DMA requests supported by the DMAC
-  - arm,pl330-broken-no-flushp: quirk for avoiding to execute DMAFLUSHP
-  - arm,pl330-periph-burst: quirk for performing burst transfer only
-  - resets: contains an entry for each entry in reset-names.
-	    See ../reset/reset.txt for details.
-  - reset-names: must contain at least "dma", and optional is "dma-ocp".
-
-Example:
-
-	pdma0: pdma@12680000 {
-		compatible = "arm,pl330", "arm,primecell";
-		reg = <0x12680000 0x1000>;
-		interrupts = <99>;
-		#dma-cells = <1>;
-		#dma-channels = <8>;
-		#dma-requests = <32>;
-	};
-
-Client drivers (device nodes requiring dma transfers from dev-to-mem or
-mem-to-dev) should specify the DMA channel numbers and dma channel names
-as shown below.
-
-  [property name]  = <[phandle of the dma controller] [dma request id]>;
-  [property name]  = <[dma channel name]>
-
-      where 'dma request id' is the dma request number which is connected
-      to the client controller. The 'property name' 'dmas' and 'dma-names'
-      as required by the generic dma device tree binding helpers. The dma
-      names correspond 1:1 with the dma request ids in the dmas property.
-
-  Example:  dmas = <&pdma0 12
-		    &pdma1 11>;
-	    dma-names = "tx", "rx";

Documentation/devicetree/bindings/dma/dma-controller.yaml

@@ -24,10 +24,10 @@ examples:
     dma: dma-controller@48000000 {
         compatible = "ti,omap-sdma";
         reg = <0x48000000 0x1000>;
-        interrupts = <0 12 0x4
-                      0 13 0x4
-                      0 14 0x4
-                      0 15 0x4>;
+        interrupts = <0 12 0x4>,
+                     <0 13 0x4>,
+                     <0 14 0x4>,
+                     <0 15 0x4>;
         #dma-cells = <1>;
         dma-channels = <32>;
         dma-requests = <127>;

Documentation/devicetree/bindings/dma/ingenic,dma.yaml

@@ -14,15 +14,23 @@ allOf:
 
 properties:
   compatible:
-    enum:
+    oneOf:
+      - enum:
           - ingenic,jz4740-dma
           - ingenic,jz4725b-dma
           - ingenic,jz4760-dma
+          - ingenic,jz4760-bdma
+          - ingenic,jz4760-mdma
           - ingenic,jz4760b-dma
+          - ingenic,jz4760b-bdma
+          - ingenic,jz4760b-mdma
           - ingenic,jz4770-dma
           - ingenic,jz4780-dma
           - ingenic,x1000-dma
           - ingenic,x1830-dma
+      - items:
+          - const: ingenic,jz4770-bdma
+          - const: ingenic,jz4760b-bdma
 
   reg:
     items:
@@ -36,13 +44,19 @@ properties:
     maxItems: 1
 
   "#dma-cells":
-    const: 2
+    enum: [2, 3]
     description: >
       DMA clients must use the format described in dma.txt, giving a phandle
-      to the DMA controller plus the following 2 integer cells:
-
-      - Request type: The DMA request type for transfers to/from the
-        device on the allocated channel, as defined in the SoC documentation.
+      to the DMA controller plus the following integer cells:
+
+      - Request type: The DMA request type specifies the device endpoint that
+        will be the source or destination of the DMA transfer.
+        If "#dma-cells" is 2, the request type is a single cell, and the
+        direction will be unidirectional (either RX or TX but not both).
+        If "#dma-cells" is 3, the request type has two cells; the first
+        one corresponds to the host to device direction (TX), the second one
+        corresponds to the device to host direction (RX). The DMA channel is
+        then bidirectional.
 
       - Channel: If set to 0xffffffff, any available channel will be allocated
         for the client. Otherwise, the exact channel specified will be used.

Documentation/devicetree/bindings/dma/renesas,rcar-dmac.yaml

@@ -44,6 +44,10 @@ properties:
       - items:
           - const: renesas,dmac-r8a779a0 # R-Car V3U
 
+      - items:
+          - const: renesas,dmac-r8a779f0 # R-Car S4-8
+          - const: renesas,rcar-gen4-dmac
+
   reg: true
 
   interrupts:
@@ -118,6 +122,7 @@ if:
       contains:
         enum:
           - renesas,dmac-r8a779a0
+          - renesas,rcar-gen4-dmac
 then:
   properties:
     reg:

Documentation/devicetree/bindings/dma/snps,dw-axi-dmac.yaml

@@ -53,6 +53,9 @@ properties:
     minimum: 1
     maximum: 8
 
+  resets:
+    maxItems: 1
+
   snps,dma-masters:
     description: |
       Number of AXI masters supported by the hardware.

Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml

@@ -30,6 +30,7 @@ description: |
 
 allOf:
   - $ref: /schemas/dma/dma-controller.yaml#
+  - $ref: /schemas/arm/keystone/ti,k3-sci-common.yaml#
 
 properties:
   compatible:

Documentation/devicetree/bindings/dma/ti/k3-pktdma.yaml

@@ -25,6 +25,7 @@ description: |
 
 allOf:
   - $ref: /schemas/dma/dma-controller.yaml#
+  - $ref: /schemas/arm/keystone/ti,k3-sci-common.yaml#
 
 properties:
   compatible:

Documentation/driver-api/dmaengine/dmatest.rst

@@ -6,6 +6,16 @@ Andy Shevchenko <andriy.shevchenko@linux.intel.com>
 
 This small document introduces how to test DMA drivers using dmatest module.
 
+The dmatest module tests DMA memcpy, memset, XOR and RAID6 P+Q operations using
+various lengths and various offsets into the source and destination buffers. It
+will initialize both buffers with a repeatable pattern and verify that the DMA
+engine copies the requested region and nothing more. It will also verify that
+the bytes aren't swapped around, and that the source buffer isn't modified.
+
+The dmatest module can be configured to test a specific channel. It can also
+test multiple channels at the same time, and it can start multiple threads
+competing for the same channel.
+
 .. note::
   The test suite works only on the channels that have at least one
   capability of the following: DMA_MEMCPY (memory-to-memory), DMA_MEMSET
@@ -143,13 +153,14 @@ Part 5 - Handling channel allocation
 Allocating Channels
 -------------------
 
-Channels are required to be configured prior to starting the test run.
-Attempting to run the test without configuring the channels will fail.
+Channels do not need to be configured prior to starting a test run. Attempting
+to run the test without configuring the channels will result in testing any
+channels that are available.
 
 Example::
 
     % echo 1 > /sys/module/dmatest/parameters/run
-    dmatest: Could not start test, no channels configured
+    dmatest: No channels configured, continue with any
 
 Channels are registered using the "channel" parameter. Channels can be requested by their
 name, once requested, the channel is registered and a pending thread is added to the test list.

Documentation/driver-api/dmaengine/provider.rst

@@ -162,6 +162,29 @@ Currently, the types available are:
 
   - The device is able to do memory to memory copies
 
+- - DMA_MEMCPY_SG
+
+  - The device supports memory to memory scatter-gather transfers.
+
+  - Even though a plain memcpy can look like a particular case of a
+    scatter-gather transfer, with a single chunk to copy, it's a distinct
+    transaction type in the mem2mem transfer case. This is because some very
+    simple devices might be able to do contiguous single-chunk memory copies,
+    but have no support for more complex SG transfers.
+
+  - No matter what the overall size of the combined chunks for source and
+    destination is, only as many bytes as the smallest of the two will be
+    transmitted. That means the number and size of the scatter-gather buffers in
+    both lists need not be the same, and that the operation functionally is
+    equivalent to a ``strncpy`` where the ``count`` argument equals the smallest
+    total size of the two scatter-gather list buffers.
+
+  - It's usually used for copying pixel data between host memory and
+    memory-mapped GPU device memory, such as found on modern PCI video graphics
+    cards. The most immediate example is the OpenGL API function
+    ``glReadPielx()``, which might require a verbatim copy of a huge framebuffer
+    from local device memory onto host memory.
+
 - DMA_XOR
 
   - The device is able to perform XOR operations on memory areas

drivers/dma/dma-jz4780.c

@@ -104,10 +104,10 @@
  * descriptor base address in the upper 8 bits.
  */
 struct jz4780_dma_hwdesc {
-	uint32_t dcm;
-	uint32_t dsa;
-	uint32_t dta;
-	uint32_t dtc;
+	u32 dcm;
+	u32 dsa;
+	u32 dta;
+	u32 dtc;
 };
 
 /* Size of allocations for hardware descriptor blocks. */
@@ -122,7 +122,8 @@ struct jz4780_dma_desc {
 	dma_addr_t desc_phys;
 	unsigned int count;
 	enum dma_transaction_type type;
-	uint32_t status;
+	u32 transfer_type;
+	u32 status;
 };
 
 struct jz4780_dma_chan {
@@ -130,8 +131,8 @@ struct jz4780_dma_chan {
 	unsigned int id;
 	struct dma_pool *desc_pool;
 
-	uint32_t transfer_type;
-	uint32_t transfer_shift;
+	u32 transfer_type_tx, transfer_type_rx;
+	u32 transfer_shift;
 	struct dma_slave_config	config;
 
 	struct jz4780_dma_desc *desc;
@@ -152,12 +153,12 @@ struct jz4780_dma_dev {
 	unsigned int irq;
 	const struct jz4780_dma_soc_data *soc_data;
 
-	uint32_t chan_reserved;
+	u32 chan_reserved;
 	struct jz4780_dma_chan chan[];
 };
 
 struct jz4780_dma_filter_data {
-	uint32_t transfer_type;
+	u32 transfer_type_tx, transfer_type_rx;
 	int channel;
 };
 
@@ -179,26 +180,26 @@ static inline struct jz4780_dma_dev *jz4780_dma_chan_parent(
 			    dma_device);
 }
 
-static inline uint32_t jz4780_dma_chn_readl(struct jz4780_dma_dev *jzdma,
+static inline u32 jz4780_dma_chn_readl(struct jz4780_dma_dev *jzdma,
 	unsigned int chn, unsigned int reg)
 {
 	return readl(jzdma->chn_base + reg + JZ_DMA_REG_CHAN(chn));
 }
 
 static inline void jz4780_dma_chn_writel(struct jz4780_dma_dev *jzdma,
-	unsigned int chn, unsigned int reg, uint32_t val)
+	unsigned int chn, unsigned int reg, u32 val)
 {
 	writel(val, jzdma->chn_base + reg + JZ_DMA_REG_CHAN(chn));
 }
 
-static inline uint32_t jz4780_dma_ctrl_readl(struct jz4780_dma_dev *jzdma,
+static inline u32 jz4780_dma_ctrl_readl(struct jz4780_dma_dev *jzdma,
 	unsigned int reg)
 {
 	return readl(jzdma->ctrl_base + reg);
 }
 
 static inline void jz4780_dma_ctrl_writel(struct jz4780_dma_dev *jzdma,
-	unsigned int reg, uint32_t val)
+	unsigned int reg, u32 val)
 {
 	writel(val, jzdma->ctrl_base + reg);
 }
@@ -226,9 +227,10 @@ static inline void jz4780_dma_chan_disable(struct jz4780_dma_dev *jzdma,
 		jz4780_dma_ctrl_writel(jzdma, JZ_DMA_REG_DCKEC, BIT(chn));
 }
 
-static struct jz4780_dma_desc *jz4780_dma_desc_alloc(
-	struct jz4780_dma_chan *jzchan, unsigned int count,
-	enum dma_transaction_type type)
+static struct jz4780_dma_desc *
+jz4780_dma_desc_alloc(struct jz4780_dma_chan *jzchan, unsigned int count,
+		      enum dma_transaction_type type,
+		      enum dma_transfer_direction direction)
 {
 	struct jz4780_dma_desc *desc;
 
@@ -248,6 +250,12 @@ static struct jz4780_dma_desc *jz4780_dma_desc_alloc(
 
 	desc->count = count;
 	desc->type = type;
+
+	if (direction == DMA_DEV_TO_MEM)
+		desc->transfer_type = jzchan->transfer_type_rx;
+	else
+		desc->transfer_type = jzchan->transfer_type_tx;
+
 	return desc;
 }
 
@@ -260,8 +268,8 @@ static void jz4780_dma_desc_free(struct virt_dma_desc *vdesc)
 	kfree(desc);
 }
 
-static uint32_t jz4780_dma_transfer_size(struct jz4780_dma_chan *jzchan,
-	unsigned long val, uint32_t *shift)
+static u32 jz4780_dma_transfer_size(struct jz4780_dma_chan *jzchan,
+	unsigned long val, u32 *shift)
 {
 	struct jz4780_dma_dev *jzdma = jz4780_dma_chan_parent(jzchan);
 	int ord = ffs(val) - 1;
@@ -303,7 +311,7 @@ static int jz4780_dma_setup_hwdesc(struct jz4780_dma_chan *jzchan,
 	enum dma_transfer_direction direction)
 {
 	struct dma_slave_config *config = &jzchan->config;
-	uint32_t width, maxburst, tsz;
+	u32 width, maxburst, tsz;
 
 	if (direction == DMA_MEM_TO_DEV) {
 		desc->dcm = JZ_DMA_DCM_SAI;
@@ -361,7 +369,7 @@ static struct dma_async_tx_descriptor *jz4780_dma_prep_slave_sg(
 	unsigned int i;
 	int err;
 
-	desc = jz4780_dma_desc_alloc(jzchan, sg_len, DMA_SLAVE);
+	desc = jz4780_dma_desc_alloc(jzchan, sg_len, DMA_SLAVE, direction);
 	if (!desc)
 		return NULL;
 
@@ -410,7 +418,7 @@ static struct dma_async_tx_descriptor *jz4780_dma_prep_dma_cyclic(
 
 	periods = buf_len / period_len;
 
-	desc = jz4780_dma_desc_alloc(jzchan, periods, DMA_CYCLIC);
+	desc = jz4780_dma_desc_alloc(jzchan, periods, DMA_CYCLIC, direction);
 	if (!desc)
 		return NULL;
 
@@ -453,16 +461,16 @@ static struct dma_async_tx_descriptor *jz4780_dma_prep_dma_memcpy(
 {
 	struct jz4780_dma_chan *jzchan = to_jz4780_dma_chan(chan);
 	struct jz4780_dma_desc *desc;
-	uint32_t tsz;
+	u32 tsz;
 
-	desc = jz4780_dma_desc_alloc(jzchan, 1, DMA_MEMCPY);
+	desc = jz4780_dma_desc_alloc(jzchan, 1, DMA_MEMCPY, 0);
 	if (!desc)
 		return NULL;
 
 	tsz = jz4780_dma_transfer_size(jzchan, dest | src | len,
 				       &jzchan->transfer_shift);
 
-	jzchan->transfer_type = JZ_DMA_DRT_AUTO;
+	desc->transfer_type = JZ_DMA_DRT_AUTO;
 
 	desc->desc[0].dsa = src;
 	desc->desc[0].dta = dest;
@@ -528,7 +536,7 @@ static void jz4780_dma_begin(struct jz4780_dma_chan *jzchan)
 
 	/* Set transfer type. */
 	jz4780_dma_chn_writel(jzdma, jzchan->id, JZ_DMA_REG_DRT,
-			      jzchan->transfer_type);
+			      jzchan->desc->transfer_type);
 
 	/*
 	 * Set the transfer count. This is redundant for a descriptor-driven
@@ -670,7 +678,7 @@ static bool jz4780_dma_chan_irq(struct jz4780_dma_dev *jzdma,
 {
 	const unsigned int soc_flags = jzdma->soc_data->flags;
 	struct jz4780_dma_desc *desc = jzchan->desc;
-	uint32_t dcs;
+	u32 dcs;
 	bool ack = true;
 
 	spin_lock(&jzchan->vchan.lock);
@@ -727,7 +735,7 @@ static irqreturn_t jz4780_dma_irq_handler(int irq, void *data)
 	struct jz4780_dma_dev *jzdma = data;
 	unsigned int nb_channels = jzdma->soc_data->nb_channels;
 	unsigned long pending;
-	uint32_t dmac;
+	u32 dmac;
 	int i;
 
 	pending = jz4780_dma_ctrl_readl(jzdma, JZ_DMA_REG_DIRQP);
@@ -788,7 +796,8 @@ static bool jz4780_dma_filter_fn(struct dma_chan *chan, void *param)
 		return false;
 	}
 
-	jzchan->transfer_type = data->transfer_type;
+	jzchan->transfer_type_tx = data->transfer_type_tx;
+	jzchan->transfer_type_rx = data->transfer_type_rx;
 
 	return true;
 }
@@ -800,11 +809,17 @@ static struct dma_chan *jz4780_of_dma_xlate(struct of_phandle_args *dma_spec,
 	dma_cap_mask_t mask = jzdma->dma_device.cap_mask;
 	struct jz4780_dma_filter_data data;
 
-	if (dma_spec->args_count != 2)
-		return NULL;
-
-	data.transfer_type = dma_spec->args[0];
+	if (dma_spec->args_count == 2) {
+		data.transfer_type_tx = dma_spec->args[0];
+		data.transfer_type_rx = dma_spec->args[0];
 		data.channel = dma_spec->args[1];
+	} else if (dma_spec->args_count == 3) {
+		data.transfer_type_tx = dma_spec->args[0];
+		data.transfer_type_rx = dma_spec->args[1];
+		data.channel = dma_spec->args[2];
+	} else {
+		return NULL;
+	}
 
 	if (data.channel > -1) {
 		if (data.channel >= jzdma->soc_data->nb_channels) {
@@ -822,7 +837,8 @@ static struct dma_chan *jz4780_of_dma_xlate(struct of_phandle_args *dma_spec,
 			return NULL;
 		}
 
-		jzdma->chan[data.channel].transfer_type = data.transfer_type;
+		jzdma->chan[data.channel].transfer_type_tx = data.transfer_type_tx;
+		jzdma->chan[data.channel].transfer_type_rx = data.transfer_type_rx;
 
 		return dma_get_slave_channel(
 			&jzdma->chan[data.channel].vchan.chan);
@@ -938,6 +954,14 @@ static int jz4780_dma_probe(struct platform_device *pdev)
 		jzchan->vchan.desc_free = jz4780_dma_desc_free;
 	}
 
+	/*
+	 * On JZ4760, chan0 won't enable properly the first time.
+	 * Enabling then disabling chan1 will magically make chan0 work
+	 * correctly.
+	 */
+	jz4780_dma_chan_enable(jzdma, 1);
+	jz4780_dma_chan_disable(jzdma, 1);
+
 	ret = platform_get_irq(pdev, 0);
 	if (ret < 0)
 		goto err_disable_clk;
@@ -1011,12 +1035,36 @@ static const struct jz4780_dma_soc_data jz4760_dma_soc_data = {
 	.flags = JZ_SOC_DATA_PER_CHAN_PM | JZ_SOC_DATA_NO_DCKES_DCKEC,
 };
 
+static const struct jz4780_dma_soc_data jz4760_mdma_soc_data = {
+	.nb_channels = 2,
+	.transfer_ord_max = 6,
+	.flags = JZ_SOC_DATA_PER_CHAN_PM | JZ_SOC_DATA_NO_DCKES_DCKEC,
+};
+
+static const struct jz4780_dma_soc_data jz4760_bdma_soc_data = {
+	.nb_channels = 3,
+	.transfer_ord_max = 6,
+	.flags = JZ_SOC_DATA_PER_CHAN_PM | JZ_SOC_DATA_NO_DCKES_DCKEC,
+};
+
 static const struct jz4780_dma_soc_data jz4760b_dma_soc_data = {
 	.nb_channels = 5,
 	.transfer_ord_max = 6,
 	.flags = JZ_SOC_DATA_PER_CHAN_PM,
 };
 
+static const struct jz4780_dma_soc_data jz4760b_mdma_soc_data = {
+	.nb_channels = 2,
+	.transfer_ord_max = 6,
+	.flags = JZ_SOC_DATA_PER_CHAN_PM,
+};
+
+static const struct jz4780_dma_soc_data jz4760b_bdma_soc_data = {
+	.nb_channels = 3,
+	.transfer_ord_max = 6,
+	.flags = JZ_SOC_DATA_PER_CHAN_PM,
+};
+
 static const struct jz4780_dma_soc_data jz4770_dma_soc_data = {
 	.nb_channels = 6,
 	.transfer_ord_max = 6,
@@ -1045,7 +1093,11 @@ static const struct of_device_id jz4780_dma_dt_match[] = {
 	{ .compatible = "ingenic,jz4740-dma", .data = &jz4740_dma_soc_data },
 	{ .compatible = "ingenic,jz4725b-dma", .data = &jz4725b_dma_soc_data },
 	{ .compatible = "ingenic,jz4760-dma", .data = &jz4760_dma_soc_data },
+	{ .compatible = "ingenic,jz4760-mdma", .data = &jz4760_mdma_soc_data },
+	{ .compatible = "ingenic,jz4760-bdma", .data = &jz4760_bdma_soc_data },
 	{ .compatible = "ingenic,jz4760b-dma", .data = &jz4760b_dma_soc_data },
+	{ .compatible = "ingenic,jz4760b-mdma", .data = &jz4760b_mdma_soc_data },
+	{ .compatible = "ingenic,jz4760b-bdma", .data = &jz4760b_bdma_soc_data },
 	{ .compatible = "ingenic,jz4770-dma", .data = &jz4770_dma_soc_data },
 	{ .compatible = "ingenic,jz4780-dma", .data = &jz4780_dma_soc_data },
 	{ .compatible = "ingenic,x1000-dma", .data = &x1000_dma_soc_data },

drivers/dma/dmaengine.c

@@ -1159,6 +1159,13 @@ int dma_async_device_register(struct dma_device *device)
 		return -EIO;
 	}
 
+	if (dma_has_cap(DMA_MEMCPY_SG, device->cap_mask) && !device->device_prep_dma_memcpy_sg) {
+		dev_err(device->dev,
+			"Device claims capability %s, but op is not defined\n",
+			"DMA_MEMCPY_SG");
+		return -EIO;
+	}
+
 	if (dma_has_cap(DMA_XOR, device->cap_mask) && !device->device_prep_dma_xor) {
 		dev_err(device->dev,
 			"Device claims capability %s, but op is not defined\n",

drivers/dma/idxd/device.c

@@ -19,30 +19,6 @@ static void idxd_device_wqs_clear_state(struct idxd_device *idxd);
 static void idxd_wq_disable_cleanup(struct idxd_wq *wq);
 
 /* Interrupt control bits */
-void idxd_mask_msix_vector(struct idxd_device *idxd, int vec_id)
-{
-	struct irq_data *data = irq_get_irq_data(idxd->irq_entries[vec_id].vector);
-
-	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;
-
-	for (i = 0; i < msixcnt; i++)
-		idxd_mask_msix_vector(idxd, i);
-}
-
-void idxd_unmask_msix_vector(struct idxd_device *idxd, int vec_id)
-{
-	struct irq_data *data = irq_get_irq_data(idxd->irq_entries[vec_id].vector);
-
-	pci_msi_unmask_irq(data);
-}
-
 void idxd_unmask_error_interrupts(struct idxd_device *idxd)
 {
 	union genctrl_reg genctrl;
@@ -382,14 +358,24 @@ static void idxd_wq_disable_cleanup(struct idxd_wq *wq)
 	lockdep_assert_held(&wq->wq_lock);
 	memset(wq->wqcfg, 0, idxd->wqcfg_size);
 	wq->type = IDXD_WQT_NONE;
-	wq->size = 0;
-	wq->group = NULL;
 	wq->threshold = 0;
 	wq->priority = 0;
 	wq->ats_dis = 0;
+	wq->enqcmds_retries = IDXD_ENQCMDS_RETRIES;
 	clear_bit(WQ_FLAG_DEDICATED, &wq->flags);
 	clear_bit(WQ_FLAG_BLOCK_ON_FAULT, &wq->flags);
 	memset(wq->name, 0, WQ_NAME_SIZE);
+	wq->max_xfer_bytes = WQ_DEFAULT_MAX_XFER;
+	wq->max_batch_size = WQ_DEFAULT_MAX_BATCH;
+}
+
+static void idxd_wq_device_reset_cleanup(struct idxd_wq *wq)
+{
+	lockdep_assert_held(&wq->wq_lock);
+
+	idxd_wq_disable_cleanup(wq);
+	wq->size = 0;
+	wq->group = NULL;
 }
 
 static void idxd_wq_ref_release(struct percpu_ref *ref)
@@ -404,19 +390,31 @@ int idxd_wq_init_percpu_ref(struct idxd_wq *wq)
 	int rc;
 
 	memset(&wq->wq_active, 0, sizeof(wq->wq_active));
-	rc = percpu_ref_init(&wq->wq_active, idxd_wq_ref_release, 0, GFP_KERNEL);
+	rc = percpu_ref_init(&wq->wq_active, idxd_wq_ref_release,
+			     PERCPU_REF_ALLOW_REINIT, GFP_KERNEL);
 	if (rc < 0)
 		return rc;
 	reinit_completion(&wq->wq_dead);
+	reinit_completion(&wq->wq_resurrect);
 	return 0;
 }
 
-void idxd_wq_quiesce(struct idxd_wq *wq)
+void __idxd_wq_quiesce(struct idxd_wq *wq)
 {
+	lockdep_assert_held(&wq->wq_lock);
+	reinit_completion(&wq->wq_resurrect);
 	percpu_ref_kill(&wq->wq_active);
+	complete_all(&wq->wq_resurrect);
 	wait_for_completion(&wq->wq_dead);
 }
 
+void idxd_wq_quiesce(struct idxd_wq *wq)
+{
+	mutex_lock(&wq->wq_lock);
+	__idxd_wq_quiesce(wq);
+	mutex_unlock(&wq->wq_lock);
+}
+
 /* Device control bits */
 static inline bool idxd_is_enabled(struct idxd_device *idxd)
 {
@@ -572,7 +570,6 @@ void idxd_device_reset(struct idxd_device *idxd)
 	idxd_device_clear_state(idxd);
 	idxd->state = IDXD_DEV_DISABLED;
 	idxd_unmask_error_interrupts(idxd);
-	idxd_msix_perm_setup(idxd);
 	spin_unlock(&idxd->dev_lock);
 }
 
@@ -681,9 +678,9 @@ static void idxd_groups_clear_state(struct idxd_device *idxd)
 		memset(&group->grpcfg, 0, sizeof(group->grpcfg));
 		group->num_engines = 0;
 		group->num_wqs = 0;
-		group->use_token_limit = false;
-		group->tokens_allowed = 0;
-		group->tokens_reserved = 0;
+		group->use_rdbuf_limit = false;
+		group->rdbufs_allowed = 0;
+		group->rdbufs_reserved = 0;
 		group->tc_a = -1;
 		group->tc_b = -1;
 	}
@@ -699,6 +696,7 @@ static void idxd_device_wqs_clear_state(struct idxd_device *idxd)
 
 		if (wq->state == IDXD_WQ_ENABLED) {
 			idxd_wq_disable_cleanup(wq);
+			idxd_wq_device_reset_cleanup(wq);
 			wq->state = IDXD_WQ_DISABLED;
 		}
 	}
@@ -711,36 +709,6 @@ void idxd_device_clear_state(struct idxd_device *idxd)
 	idxd_device_wqs_clear_state(idxd);
 }
 
-void idxd_msix_perm_setup(struct idxd_device *idxd)
-{
-	union msix_perm mperm;
-	int i, msixcnt;
-
-	msixcnt = pci_msix_vec_count(idxd->pdev);
-	if (msixcnt < 0)
-		return;
-
-	mperm.bits = 0;
-	mperm.pasid = idxd->pasid;
-	mperm.pasid_en = device_pasid_enabled(idxd);
-	for (i = 1; i < msixcnt; i++)
-		iowrite32(mperm.bits, idxd->reg_base + idxd->msix_perm_offset + i * 8);
-}
-
-void idxd_msix_perm_clear(struct idxd_device *idxd)
-{
-	union msix_perm mperm;
-	int i, msixcnt;
-
-	msixcnt = pci_msix_vec_count(idxd->pdev);
-	if (msixcnt < 0)
-		return;
-
-	mperm.bits = 0;
-	for (i = 1; i < msixcnt; i++)
-		iowrite32(mperm.bits, idxd->reg_base + idxd->msix_perm_offset + i * 8);
-}
-
 static void idxd_group_config_write(struct idxd_group *group)
 {
 	struct idxd_device *idxd = group->idxd;
@@ -780,10 +748,10 @@ static int idxd_groups_config_write(struct idxd_device *idxd)
 	int i;
 	struct device *dev = &idxd->pdev->dev;
 
-	/* Setup bandwidth token limit */
-	if (idxd->hw.gen_cap.config_en && idxd->token_limit) {
+	/* Setup bandwidth rdbuf limit */
+	if (idxd->hw.gen_cap.config_en && idxd->rdbuf_limit) {
 		reg.bits = ioread32(idxd->reg_base + IDXD_GENCFG_OFFSET);
-		reg.token_limit = idxd->token_limit;
+		reg.rdbuf_limit = idxd->rdbuf_limit;
 		iowrite32(reg.bits, idxd->reg_base + IDXD_GENCFG_OFFSET);
 	}
 
@@ -827,15 +795,12 @@ static int idxd_wq_config_write(struct idxd_wq *wq)
 		wq->wqcfg->bits[i] = ioread32(idxd->reg_base + wq_offset);
 	}
 
+	if (wq->size == 0 && wq->type != IDXD_WQT_NONE)
+		wq->size = WQ_DEFAULT_QUEUE_DEPTH;
+
 	/* byte 0-3 */
 	wq->wqcfg->wq_size = wq->size;
 
-	if (wq->size == 0) {
-		idxd->cmd_status = IDXD_SCMD_WQ_NO_SIZE;
-		dev_warn(dev, "Incorrect work queue size: 0\n");
-		return -EINVAL;
-	}
-
 	/* bytes 4-7 */
 	wq->wqcfg->wq_thresh = wq->threshold;
 
@@ -924,13 +889,12 @@ static void idxd_group_flags_setup(struct idxd_device *idxd)
 			group->tc_b = group->grpcfg.flags.tc_b = 1;
 		else
 			group->grpcfg.flags.tc_b = group->tc_b;
-		group->grpcfg.flags.use_token_limit = group->use_token_limit;
-		group->grpcfg.flags.tokens_reserved = group->tokens_reserved;
-		if (group->tokens_allowed)
-			group->grpcfg.flags.tokens_allowed =
-				group->tokens_allowed;
+		group->grpcfg.flags.use_rdbuf_limit = group->use_rdbuf_limit;
+		group->grpcfg.flags.rdbufs_reserved = group->rdbufs_reserved;
+		if (group->rdbufs_allowed)
+			group->grpcfg.flags.rdbufs_allowed = group->rdbufs_allowed;
 		else
-			group->grpcfg.flags.tokens_allowed = idxd->max_tokens;
+			group->grpcfg.flags.rdbufs_allowed = idxd->max_rdbufs;
 	}
 }
 
@@ -981,8 +945,6 @@ static int idxd_wqs_setup(struct idxd_device *idxd)
 
 		if (!wq->group)
 			continue;
-		if (!wq->size)
-			continue;
 
 		if (wq_shared(wq) && !device_swq_supported(idxd)) {
 			idxd->cmd_status = IDXD_SCMD_WQ_NO_SWQ_SUPPORT;
@@ -1123,7 +1085,7 @@ int idxd_device_load_config(struct idxd_device *idxd)
 	int i, rc;
 
 	reg.bits = ioread32(idxd->reg_base + IDXD_GENCFG_OFFSET);
-	idxd->token_limit = reg.token_limit;
+	idxd->rdbuf_limit = reg.rdbuf_limit;
 
 	for (i = 0; i < idxd->max_groups; i++) {
 		struct idxd_group *group = idxd->groups[i];
@@ -1142,6 +1104,106 @@ int idxd_device_load_config(struct idxd_device *idxd)
 	return 0;
 }
 
+static void idxd_flush_pending_descs(struct idxd_irq_entry *ie)
+{
+	struct idxd_desc *desc, *itr;
+	struct llist_node *head;
+	LIST_HEAD(flist);
+	enum idxd_complete_type ctype;
+
+	spin_lock(&ie->list_lock);
+	head = llist_del_all(&ie->pending_llist);
+	if (head) {
+		llist_for_each_entry_safe(desc, itr, head, llnode)
+			list_add_tail(&desc->list, &ie->work_list);
+	}
+
+	list_for_each_entry_safe(desc, itr, &ie->work_list, list)
+		list_move_tail(&desc->list, &flist);
+	spin_unlock(&ie->list_lock);
+
+	list_for_each_entry_safe(desc, itr, &flist, list) {
+		list_del(&desc->list);
+		ctype = desc->completion->status ? IDXD_COMPLETE_NORMAL : IDXD_COMPLETE_ABORT;
+		idxd_dma_complete_txd(desc, ctype, true);
+	}
+}
+
+static void idxd_device_set_perm_entry(struct idxd_device *idxd,
+				       struct idxd_irq_entry *ie)
+{
+	union msix_perm mperm;
+
+	if (ie->pasid == INVALID_IOASID)
+		return;
+
+	mperm.bits = 0;
+	mperm.pasid = ie->pasid;
+	mperm.pasid_en = 1;
+	iowrite32(mperm.bits, idxd->reg_base + idxd->msix_perm_offset + ie->id * 8);
+}
+
+static void idxd_device_clear_perm_entry(struct idxd_device *idxd,
+					 struct idxd_irq_entry *ie)
+{
+	iowrite32(0, idxd->reg_base + idxd->msix_perm_offset + ie->id * 8);
+}
+
+void idxd_wq_free_irq(struct idxd_wq *wq)
+{
+	struct idxd_device *idxd = wq->idxd;
+	struct idxd_irq_entry *ie = &wq->ie;
+
+	synchronize_irq(ie->vector);
+	free_irq(ie->vector, ie);
+	idxd_flush_pending_descs(ie);
+	if (idxd->request_int_handles)
+		idxd_device_release_int_handle(idxd, ie->int_handle, IDXD_IRQ_MSIX);
+	idxd_device_clear_perm_entry(idxd, ie);
+	ie->vector = -1;
+	ie->int_handle = INVALID_INT_HANDLE;
+	ie->pasid = INVALID_IOASID;
+}
+
+int idxd_wq_request_irq(struct idxd_wq *wq)
+{
+	struct idxd_device *idxd = wq->idxd;
+	struct pci_dev *pdev = idxd->pdev;
+	struct device *dev = &pdev->dev;
+	struct idxd_irq_entry *ie;
+	int rc;
+
+	ie = &wq->ie;
+	ie->vector = pci_irq_vector(pdev, ie->id);
+	ie->pasid = device_pasid_enabled(idxd) ? idxd->pasid : INVALID_IOASID;
+	idxd_device_set_perm_entry(idxd, ie);
+
+	rc = request_threaded_irq(ie->vector, NULL, idxd_wq_thread, 0, "idxd-portal", ie);
+	if (rc < 0) {
+		dev_err(dev, "Failed to request irq %d.\n", ie->vector);
+		goto err_irq;
+	}
+
+	if (idxd->request_int_handles) {
+		rc = idxd_device_request_int_handle(idxd, ie->id, &ie->int_handle,
+						    IDXD_IRQ_MSIX);
+		if (rc < 0)
+			goto err_int_handle;
+	} else {
+		ie->int_handle = ie->id;
+	}
+
+	return 0;
+
+err_int_handle:
+	ie->int_handle = INVALID_INT_HANDLE;
+	free_irq(ie->vector, ie);
+err_irq:
+	idxd_device_clear_perm_entry(idxd, ie);
+	ie->pasid = INVALID_IOASID;
+	return rc;
+}
+
 int __drv_enable_wq(struct idxd_wq *wq)
 {
 	struct idxd_device *idxd = wq->idxd;

drivers/dma/idxd/dma.c

@@ -21,20 +21,27 @@ static inline struct idxd_wq *to_idxd_wq(struct dma_chan *c)
 }
 
 void idxd_dma_complete_txd(struct idxd_desc *desc,
-			   enum idxd_complete_type comp_type)
+			   enum idxd_complete_type comp_type,
+			   bool free_desc)
 {
+	struct idxd_device *idxd = desc->wq->idxd;
 	struct dma_async_tx_descriptor *tx;
 	struct dmaengine_result res;
 	int complete = 1;
 
-	if (desc->completion->status == DSA_COMP_SUCCESS)
+	if (desc->completion->status == DSA_COMP_SUCCESS) {
 		res.result = DMA_TRANS_NOERROR;
-	else if (desc->completion->status)
+	} else if (desc->completion->status) {
+		if (idxd->request_int_handles && comp_type != IDXD_COMPLETE_ABORT &&
+		    desc->completion->status == DSA_COMP_INT_HANDLE_INVAL &&
+		    idxd_queue_int_handle_resubmit(desc))
+			return;
 		res.result = DMA_TRANS_WRITE_FAILED;
-	else if (comp_type == IDXD_COMPLETE_ABORT)
+	} else if (comp_type == IDXD_COMPLETE_ABORT) {
 		res.result = DMA_TRANS_ABORTED;
-	else
+	} else {
 		complete = 0;
+	}
 
 	tx = &desc->txd;
 	if (complete && tx->cookie) {
@@ -44,6 +51,9 @@ void idxd_dma_complete_txd(struct idxd_desc *desc,
 		tx->callback = NULL;
 		tx->callback_result = NULL;
 	}
+
+	if (free_desc)
+		idxd_free_desc(desc->wq, desc);
 }
 
 static void op_flag_setup(unsigned long flags, u32 *desc_flags)
@@ -153,8 +163,10 @@ static dma_cookie_t idxd_dma_tx_submit(struct dma_async_tx_descriptor *tx)
 	cookie = dma_cookie_assign(tx);
 
 	rc = idxd_submit_desc(wq, desc);
-	if (rc < 0)
+	if (rc < 0) {
+		idxd_free_desc(wq, desc);
 		return rc;
+	}
 
 	return cookie;
 }
@@ -277,6 +289,14 @@ static int idxd_dmaengine_drv_probe(struct idxd_dev *idxd_dev)
 
 	mutex_lock(&wq->wq_lock);
 	wq->type = IDXD_WQT_KERNEL;
+
+	rc = idxd_wq_request_irq(wq);
+	if (rc < 0) {
+		idxd->cmd_status = IDXD_SCMD_WQ_IRQ_ERR;
+		dev_dbg(dev, "WQ %d irq setup failed: %d\n", wq->id, rc);
+		goto err_irq;
+	}
+
 	rc = __drv_enable_wq(wq);
 	if (rc < 0) {
 		dev_dbg(dev, "Enable wq %d failed: %d\n", wq->id, rc);
@@ -310,13 +330,15 @@ static int idxd_dmaengine_drv_probe(struct idxd_dev *idxd_dev)
 	return 0;
 
 err_dma:
-	idxd_wq_quiesce(wq);
+	__idxd_wq_quiesce(wq);
 	percpu_ref_exit(&wq->wq_active);
 err_ref:
 	idxd_wq_free_resources(wq);
 err_res_alloc:
 	__drv_disable_wq(wq);
 err:
+	idxd_wq_free_irq(wq);
+err_irq:
 	wq->type = IDXD_WQT_NONE;
 	mutex_unlock(&wq->wq_lock);
 	return rc;
@@ -327,11 +349,13 @@ static void idxd_dmaengine_drv_remove(struct idxd_dev *idxd_dev)
 	struct idxd_wq *wq = idxd_dev_to_wq(idxd_dev);
 
 	mutex_lock(&wq->wq_lock);
-	idxd_wq_quiesce(wq);
+	__idxd_wq_quiesce(wq);
 	idxd_unregister_dma_channel(wq);
 	idxd_wq_free_resources(wq);
 	__drv_disable_wq(wq);
 	percpu_ref_exit(&wq->wq_active);
+	idxd_wq_free_irq(wq);
+	wq->type = IDXD_WQT_NONE;
 	mutex_unlock(&wq->wq_lock);
 }
 

drivers/dma/idxd/idxd.h

@@ -10,6 +10,7 @@
 #include <linux/cdev.h>
 #include <linux/idr.h>
 #include <linux/pci.h>
+#include <linux/ioasid.h>
 #include <linux/perf_event.h>
 #include <uapi/linux/idxd.h>
 #include "registers.h"
@@ -51,6 +52,9 @@ enum idxd_type {
 #define IDXD_NAME_SIZE		128
 #define IDXD_PMU_EVENT_MAX	64
 
+#define IDXD_ENQCMDS_RETRIES		32
+#define IDXD_ENQCMDS_MAX_RETRIES	64
+
 struct idxd_device_driver {
 	const char *name;
 	enum idxd_dev_type *type;
@@ -64,8 +68,8 @@ extern struct idxd_device_driver idxd_drv;
 extern struct idxd_device_driver idxd_dmaengine_drv;
 extern struct idxd_device_driver idxd_user_drv;
 
+#define INVALID_INT_HANDLE	-1
 struct idxd_irq_entry {
-	struct idxd_device *idxd;
 	int id;
 	int vector;
 	struct llist_head pending_llist;
@@ -75,6 +79,8 @@ struct idxd_irq_entry {
 	 * and irq thread processing error descriptor.
 	 */
 	spinlock_t list_lock;
+	int int_handle;
+	ioasid_t pasid;
 };
 
 struct idxd_group {
@@ -84,9 +90,9 @@ struct idxd_group {
 	int id;
 	int num_engines;
 	int num_wqs;
-	bool use_token_limit;
-	u8 tokens_allowed;
-	u8 tokens_reserved;
+	bool use_rdbuf_limit;
+	u8 rdbufs_allowed;
+	u8 rdbufs_reserved;
 	int tc_a;
 	int tc_b;
 };
@@ -145,6 +151,10 @@ struct idxd_cdev {
 #define WQ_NAME_SIZE   1024
 #define WQ_TYPE_SIZE   10
 
+#define WQ_DEFAULT_QUEUE_DEPTH		16
+#define WQ_DEFAULT_MAX_XFER		SZ_2M
+#define WQ_DEFAULT_MAX_BATCH		32
+
 enum idxd_op_type {
 	IDXD_OP_BLOCK = 0,
 	IDXD_OP_NONBLOCK = 1,
@@ -164,13 +174,16 @@ struct idxd_dma_chan {
 struct idxd_wq {
 	void __iomem *portal;
 	u32 portal_offset;
+	unsigned int enqcmds_retries;
 	struct percpu_ref wq_active;
 	struct completion wq_dead;
+	struct completion wq_resurrect;
 	struct idxd_dev idxd_dev;
 	struct idxd_cdev *idxd_cdev;
 	struct wait_queue_head err_queue;
 	struct idxd_device *idxd;
 	int id;
+	struct idxd_irq_entry ie;
 	enum idxd_wq_type type;
 	struct idxd_group *group;
 	int client_count;
@@ -251,6 +264,7 @@ struct idxd_device {
 	int id;
 	int major;
 	u32 cmd_status;
+	struct idxd_irq_entry ie;	/* misc irq, msix 0 */
 
 	struct pci_dev *pdev;
 	void __iomem *reg_base;
@@ -266,6 +280,8 @@ struct idxd_device {
 	unsigned int pasid;
 
 	int num_groups;
+	int irq_cnt;
+	bool request_int_handles;
 
 	u32 msix_perm_offset;
 	u32 wqcfg_offset;
@@ -276,24 +292,20 @@ struct idxd_device {
 	u32 max_batch_size;
 	int max_groups;
 	int max_engines;
-	int max_tokens;
+	int max_rdbufs;
 	int max_wqs;
 	int max_wq_size;
-	int token_limit;
-	int nr_tokens;		/* non-reserved tokens */
+	int rdbuf_limit;
+	int nr_rdbufs;		/* non-reserved read buffers */
 	unsigned int wqcfg_size;
 
 	union sw_err_reg sw_err;
 	wait_queue_head_t cmd_waitq;
-	int num_wq_irqs;
-	struct idxd_irq_entry *irq_entries;
 
 	struct idxd_dma_dev *idxd_dma;
 	struct workqueue_struct *wq;
 	struct work_struct work;
 
-	int *int_handles;
-
 	struct idxd_pmu *idxd_pmu;
 };
 
@@ -380,6 +392,21 @@ static inline void idxd_dev_set_type(struct idxd_dev *idev, int type)
 	idev->type = type;
 }
 
+static inline struct idxd_irq_entry *idxd_get_ie(struct idxd_device *idxd, int idx)
+{
+	return (idx == 0) ? &idxd->ie : &idxd->wqs[idx - 1]->ie;
+}
+
+static inline struct idxd_wq *ie_to_wq(struct idxd_irq_entry *ie)
+{
+	return container_of(ie, struct idxd_wq, ie);
+}
+
+static inline struct idxd_device *ie_to_idxd(struct idxd_irq_entry *ie)
+{
+	return container_of(ie, struct idxd_device, ie);
+}
+
 extern struct bus_type dsa_bus_type;
 
 extern bool support_enqcmd;
@@ -518,17 +545,13 @@ void idxd_unregister_devices(struct idxd_device *idxd);
 int idxd_register_driver(void);
 void idxd_unregister_driver(void);
 void idxd_wqs_quiesce(struct idxd_device *idxd);
+bool idxd_queue_int_handle_resubmit(struct idxd_desc *desc);
 
 /* device interrupt control */
-void idxd_msix_perm_setup(struct idxd_device *idxd);
-void idxd_msix_perm_clear(struct idxd_device *idxd);
 irqreturn_t idxd_misc_thread(int vec, void *data);
 irqreturn_t idxd_wq_thread(int irq, void *data);
 void idxd_mask_error_interrupts(struct idxd_device *idxd);
 void idxd_unmask_error_interrupts(struct idxd_device *idxd);
-void idxd_mask_msix_vectors(struct idxd_device *idxd);
-void idxd_mask_msix_vector(struct idxd_device *idxd, int vec_id);
-void idxd_unmask_msix_vector(struct idxd_device *idxd, int vec_id);
 
 /* device control */
 int idxd_register_idxd_drv(void);
@@ -564,13 +587,17 @@ int idxd_wq_map_portal(struct idxd_wq *wq);
 void idxd_wq_unmap_portal(struct idxd_wq *wq);
 int idxd_wq_set_pasid(struct idxd_wq *wq, int pasid);
 int idxd_wq_disable_pasid(struct idxd_wq *wq);
+void __idxd_wq_quiesce(struct idxd_wq *wq);
 void idxd_wq_quiesce(struct idxd_wq *wq);
 int idxd_wq_init_percpu_ref(struct idxd_wq *wq);
+void idxd_wq_free_irq(struct idxd_wq *wq);
+int idxd_wq_request_irq(struct idxd_wq *wq);
 
 /* submission */
 int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc);
 struct idxd_desc *idxd_alloc_desc(struct idxd_wq *wq, enum idxd_op_type optype);
 void idxd_free_desc(struct idxd_wq *wq, struct idxd_desc *desc);
+int idxd_enqcmds(struct idxd_wq *wq, void __iomem *portal, const void *desc);
 
 /* dmaengine */
 int idxd_register_dma_device(struct idxd_device *idxd);
@@ -579,7 +606,7 @@ int idxd_register_dma_channel(struct idxd_wq *wq);
 void idxd_unregister_dma_channel(struct idxd_wq *wq);
 void idxd_parse_completion_status(u8 status, enum dmaengine_tx_result *res);
 void idxd_dma_complete_txd(struct idxd_desc *desc,
-			   enum idxd_complete_type comp_type);
+			   enum idxd_complete_type comp_type, bool free_desc);
 
 /* cdev */
 int idxd_cdev_register(void);
@@ -603,10 +630,4 @@ static inline void perfmon_init(void) {}
 static inline void perfmon_exit(void) {}
 #endif
 
-static inline void complete_desc(struct idxd_desc *desc, enum idxd_complete_type reason)
-{
-	idxd_dma_complete_txd(desc, reason);
-	idxd_free_desc(desc->wq, desc);
-}
-
 #endif

drivers/dma/idxd/init.c

@@ -72,7 +72,7 @@ static int idxd_setup_interrupts(struct idxd_device *idxd)
 {
 	struct pci_dev *pdev = idxd->pdev;
 	struct device *dev = &pdev->dev;
-	struct idxd_irq_entry *irq_entry;
+	struct idxd_irq_entry *ie;
 	int i, msixcnt;
 	int rc = 0;
 
@@ -81,6 +81,7 @@ static int idxd_setup_interrupts(struct idxd_device *idxd)
 		dev_err(dev, "Not MSI-X interrupt capable.\n");
 		return -ENOSPC;
 	}
+	idxd->irq_cnt = msixcnt;
 
 	rc = pci_alloc_irq_vectors(pdev, msixcnt, msixcnt, PCI_IRQ_MSIX);
 	if (rc != msixcnt) {
@@ -89,87 +90,34 @@ static int idxd_setup_interrupts(struct idxd_device *idxd)
 	}
 	dev_dbg(dev, "Enabled %d msix vectors\n", msixcnt);
 
-	/*
-	 * We implement 1 completion list per MSI-X entry except for
-	 * entry 0, which is for errors and others.
-	 */
-	idxd->irq_entries = kcalloc_node(msixcnt, sizeof(struct idxd_irq_entry),
-					 GFP_KERNEL, dev_to_node(dev));
-	if (!idxd->irq_entries) {
-		rc = -ENOMEM;
-		goto err_irq_entries;
-	}
-
-	for (i = 0; i < msixcnt; i++) {
-		idxd->irq_entries[i].id = i;
-		idxd->irq_entries[i].idxd = idxd;
-		idxd->irq_entries[i].vector = pci_irq_vector(pdev, i);
-		spin_lock_init(&idxd->irq_entries[i].list_lock);
-	}
-
-	idxd_msix_perm_setup(idxd);
 
-	irq_entry = &idxd->irq_entries[0];
-	rc = request_threaded_irq(irq_entry->vector, NULL, idxd_misc_thread,
-				  0, "idxd-misc", irq_entry);
+	ie = idxd_get_ie(idxd, 0);
+	ie->vector = pci_irq_vector(pdev, 0);
+	rc = request_threaded_irq(ie->vector, NULL, idxd_misc_thread, 0, "idxd-misc", ie);
 	if (rc < 0) {
 		dev_err(dev, "Failed to allocate misc interrupt.\n");
 		goto err_misc_irq;
 	}
+	dev_dbg(dev, "Requested idxd-misc handler on msix vector %d\n", ie->vector);
 
-	dev_dbg(dev, "Allocated idxd-misc handler on msix vector %d\n", irq_entry->vector);
-
-	/* first MSI-X entry is not for wq interrupts */
-	idxd->num_wq_irqs = msixcnt - 1;
+	for (i = 0; i < idxd->max_wqs; i++) {
+		int msix_idx = i + 1;
 
-	for (i = 1; i < msixcnt; i++) {
-		irq_entry = &idxd->irq_entries[i];
+		ie = idxd_get_ie(idxd, msix_idx);
+		ie->id = msix_idx;
+		ie->int_handle = INVALID_INT_HANDLE;
+		ie->pasid = INVALID_IOASID;
 
-		init_llist_head(&idxd->irq_entries[i].pending_llist);
-		INIT_LIST_HEAD(&idxd->irq_entries[i].work_list);
-		rc = request_threaded_irq(irq_entry->vector, NULL,
-					  idxd_wq_thread, 0, "idxd-portal", irq_entry);
-		if (rc < 0) {
-			dev_err(dev, "Failed to allocate irq %d.\n", irq_entry->vector);
-			goto err_wq_irqs;
-		}
-
-		dev_dbg(dev, "Allocated idxd-msix %d for vector %d\n", i, irq_entry->vector);
-		if (idxd->hw.cmd_cap & BIT(IDXD_CMD_REQUEST_INT_HANDLE)) {
-			/*
-			 * The MSIX vector enumeration starts at 1 with vector 0 being the
-			 * misc interrupt that handles non I/O completion events. The
-			 * interrupt handles are for IMS enumeration on guest. The misc
-			 * interrupt vector does not require a handle and therefore we start
-			 * the int_handles at index 0. Since 'i' starts at 1, the first
-			 * int_handles index will be 0.
-			 */
-			rc = idxd_device_request_int_handle(idxd, i, &idxd->int_handles[i - 1],
-							    IDXD_IRQ_MSIX);
-			if (rc < 0) {
-				free_irq(irq_entry->vector, irq_entry);
-				goto err_wq_irqs;
-			}
-			dev_dbg(dev, "int handle requested: %u\n", idxd->int_handles[i - 1]);
-		}
+		spin_lock_init(&ie->list_lock);
+		init_llist_head(&ie->pending_llist);
+		INIT_LIST_HEAD(&ie->work_list);
 	}
 
 	idxd_unmask_error_interrupts(idxd);
 	return 0;
 
- err_wq_irqs:
-	while (--i >= 0) {
-		irq_entry = &idxd->irq_entries[i];
-		free_irq(irq_entry->vector, irq_entry);
-		if (i != 0)
-			idxd_device_release_int_handle(idxd,
-						       idxd->int_handles[i], IDXD_IRQ_MSIX);
-	}
  err_misc_irq:
-	/* Disable error interrupt generation */
 	idxd_mask_error_interrupts(idxd);
-	idxd_msix_perm_clear(idxd);
- err_irq_entries:
 	pci_free_irq_vectors(pdev);
 	dev_err(dev, "No usable interrupts\n");
 	return rc;
@@ -178,26 +126,16 @@ static int idxd_setup_interrupts(struct idxd_device *idxd)
 static void idxd_cleanup_interrupts(struct idxd_device *idxd)
 {
 	struct pci_dev *pdev = idxd->pdev;
-	struct idxd_irq_entry *irq_entry;
-	int i, msixcnt;
+	struct idxd_irq_entry *ie;
+	int msixcnt;
 
 	msixcnt = pci_msix_vec_count(pdev);
 	if (msixcnt <= 0)
 		return;
 
-	irq_entry = &idxd->irq_entries[0];
-	free_irq(irq_entry->vector, irq_entry);
-
-	for (i = 1; i < msixcnt; i++) {
-
-		irq_entry = &idxd->irq_entries[i];
-		if (idxd->hw.cmd_cap & BIT(IDXD_CMD_RELEASE_INT_HANDLE))
-			idxd_device_release_int_handle(idxd, idxd->int_handles[i],
-						       IDXD_IRQ_MSIX);
-		free_irq(irq_entry->vector, irq_entry);
-	}
-
+	ie = idxd_get_ie(idxd, 0);
 	idxd_mask_error_interrupts(idxd);
+	free_irq(ie->vector, ie);
 	pci_free_irq_vectors(pdev);
 }
 
@@ -237,8 +175,10 @@ static int idxd_setup_wqs(struct idxd_device *idxd)
 		mutex_init(&wq->wq_lock);
 		init_waitqueue_head(&wq->err_queue);
 		init_completion(&wq->wq_dead);
-		wq->max_xfer_bytes = idxd->max_xfer_bytes;
-		wq->max_batch_size = idxd->max_batch_size;
+		init_completion(&wq->wq_resurrect);
+		wq->max_xfer_bytes = WQ_DEFAULT_MAX_XFER;
+		wq->max_batch_size = WQ_DEFAULT_MAX_BATCH;
+		wq->enqcmds_retries = IDXD_ENQCMDS_RETRIES;
 		wq->wqcfg = kzalloc_node(idxd->wqcfg_size, GFP_KERNEL, dev_to_node(dev));
 		if (!wq->wqcfg) {
 			put_device(conf_dev);
@@ -379,13 +319,6 @@ static int idxd_setup_internals(struct idxd_device *idxd)
 
 	init_waitqueue_head(&idxd->cmd_waitq);
 
-	if (idxd->hw.cmd_cap & BIT(IDXD_CMD_REQUEST_INT_HANDLE)) {
-		idxd->int_handles = kcalloc_node(idxd->max_wqs, sizeof(int), GFP_KERNEL,
-						 dev_to_node(dev));
-		if (!idxd->int_handles)
-			return -ENOMEM;
-	}
-
 	rc = idxd_setup_wqs(idxd);
 	if (rc < 0)
 		goto err_wqs;
@@ -416,7 +349,6 @@ static int idxd_setup_internals(struct idxd_device *idxd)
 	for (i = 0; i < idxd->max_wqs; i++)
 		put_device(wq_confdev(idxd->wqs[i]));
  err_wqs:
-	kfree(idxd->int_handles);
 	return rc;
 }
 
@@ -451,6 +383,10 @@ static void idxd_read_caps(struct idxd_device *idxd)
 		dev_dbg(dev, "cmd_cap: %#x\n", idxd->hw.cmd_cap);
 	}
 
+	/* reading command capabilities */
+	if (idxd->hw.cmd_cap & BIT(IDXD_CMD_REQUEST_INT_HANDLE))
+		idxd->request_int_handles = true;
+
 	idxd->max_xfer_bytes = 1ULL << idxd->hw.gen_cap.max_xfer_shift;
 	dev_dbg(dev, "max xfer size: %llu bytes\n", idxd->max_xfer_bytes);
 	idxd->max_batch_size = 1U << idxd->hw.gen_cap.max_batch_shift;
@@ -464,9 +400,9 @@ static void idxd_read_caps(struct idxd_device *idxd)
 	dev_dbg(dev, "group_cap: %#llx\n", idxd->hw.group_cap.bits);
 	idxd->max_groups = idxd->hw.group_cap.num_groups;
 	dev_dbg(dev, "max groups: %u\n", idxd->max_groups);
-	idxd->max_tokens = idxd->hw.group_cap.total_tokens;
-	dev_dbg(dev, "max tokens: %u\n", idxd->max_tokens);
-	idxd->nr_tokens = idxd->max_tokens;
+	idxd->max_rdbufs = idxd->hw.group_cap.total_rdbufs;
+	dev_dbg(dev, "max read buffers: %u\n", idxd->max_rdbufs);
+	idxd->nr_rdbufs = idxd->max_rdbufs;
 
 	/* read engine capabilities */
 	idxd->hw.engine_cap.bits =
@@ -611,8 +547,6 @@ static int idxd_probe(struct idxd_device *idxd)
 	if (rc)
 		goto err_config;
 
-	dev_dbg(dev, "IDXD interrupt setup complete.\n");
-
 	idxd->major = idxd_cdev_get_major(idxd);
 
 	rc = perfmon_pmu_init(idxd);
@@ -708,32 +642,6 @@ static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	return rc;
 }
 
-static void idxd_flush_pending_llist(struct idxd_irq_entry *ie)
-{
-	struct idxd_desc *desc, *itr;
-	struct llist_node *head;
-
-	head = llist_del_all(&ie->pending_llist);
-	if (!head)
-		return;
-
-	llist_for_each_entry_safe(desc, itr, head, llnode) {
-		idxd_dma_complete_txd(desc, IDXD_COMPLETE_ABORT);
-		idxd_free_desc(desc->wq, desc);
-	}
-}
-
-static void idxd_flush_work_list(struct idxd_irq_entry *ie)
-{
-	struct idxd_desc *desc, *iter;
-
-	list_for_each_entry_safe(desc, iter, &ie->work_list, list) {
-		list_del(&desc->list);
-		idxd_dma_complete_txd(desc, IDXD_COMPLETE_ABORT);
-		idxd_free_desc(desc->wq, desc);
-	}
-}
-
 void idxd_wqs_quiesce(struct idxd_device *idxd)
 {
 	struct idxd_wq *wq;
@@ -746,47 +654,19 @@ void idxd_wqs_quiesce(struct idxd_device *idxd)
 	}
 }
 
-static void idxd_release_int_handles(struct idxd_device *idxd)
-{
-	struct device *dev = &idxd->pdev->dev;
-	int i, rc;
-
-	for (i = 0; i < idxd->num_wq_irqs; i++) {
-		if (idxd->hw.cmd_cap & BIT(IDXD_CMD_RELEASE_INT_HANDLE)) {
-			rc = idxd_device_release_int_handle(idxd, idxd->int_handles[i],
-							    IDXD_IRQ_MSIX);
-			if (rc < 0)
-				dev_warn(dev, "irq handle %d release failed\n",
-					 idxd->int_handles[i]);
-			else
-				dev_dbg(dev, "int handle requested: %u\n", idxd->int_handles[i]);
-		}
-	}
-}
-
 static void idxd_shutdown(struct pci_dev *pdev)
 {
 	struct idxd_device *idxd = pci_get_drvdata(pdev);
-	int rc, i;
 	struct idxd_irq_entry *irq_entry;
-	int msixcnt = pci_msix_vec_count(pdev);
+	int rc;
 
 	rc = idxd_device_disable(idxd);
 	if (rc)
 		dev_err(&pdev->dev, "Disabling device failed\n");
 
-	dev_dbg(&pdev->dev, "%s called\n", __func__);
-	idxd_mask_msix_vectors(idxd);
-	idxd_mask_error_interrupts(idxd);
-
-	for (i = 0; i < msixcnt; i++) {
-		irq_entry = &idxd->irq_entries[i];
+	irq_entry = &idxd->ie;
 	synchronize_irq(irq_entry->vector);
-		if (i == 0)
-			continue;
-		idxd_flush_pending_llist(irq_entry);
-		idxd_flush_work_list(irq_entry);
-	}
+	idxd_mask_error_interrupts(idxd);
 	flush_workqueue(idxd->wq);
 }
 
@@ -794,8 +674,6 @@ static void idxd_remove(struct pci_dev *pdev)
 {
 	struct idxd_device *idxd = pci_get_drvdata(pdev);
 	struct idxd_irq_entry *irq_entry;
-	int msixcnt = pci_msix_vec_count(pdev);
-	int i;
 
 	idxd_unregister_devices(idxd);
 	/*
@@ -811,12 +689,8 @@ static void idxd_remove(struct pci_dev *pdev)
 	if (device_pasid_enabled(idxd))
 		idxd_disable_system_pasid(idxd);
 
-	for (i = 0; i < msixcnt; i++) {
-		irq_entry = &idxd->irq_entries[i];
+	irq_entry = idxd_get_ie(idxd, 0);
 	free_irq(irq_entry->vector, irq_entry);
-	}
-	idxd_msix_perm_clear(idxd);
-	idxd_release_int_handles(idxd);
 	pci_free_irq_vectors(pdev);
 	pci_iounmap(pdev, idxd->reg_base);
 	iommu_dev_disable_feature(&pdev->dev, IOMMU_DEV_FEAT_SVA);

drivers/dma/idxd/irq.c

@@ -6,6 +6,7 @@
 #include <linux/pci.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include <linux/dmaengine.h>
+#include <linux/delay.h>
 #include <uapi/linux/idxd.h>
 #include "../dmaengine.h"
 #include "idxd.h"
@@ -22,6 +23,16 @@ struct idxd_fault {
 	struct idxd_device *idxd;
 };
 
+struct idxd_resubmit {
+	struct work_struct work;
+	struct idxd_desc *desc;
+};
+
+struct idxd_int_handle_revoke {
+	struct work_struct work;
+	struct idxd_device *idxd;
+};
+
 static void idxd_device_reinit(struct work_struct *work)
 {
 	struct idxd_device *idxd = container_of(work, struct idxd_device, work);
@@ -55,6 +66,162 @@ static void idxd_device_reinit(struct work_struct *work)
 	idxd_device_clear_state(idxd);
 }
 
+/*
+ * The function sends a drain descriptor for the interrupt handle. The drain ensures
+ * all descriptors with this interrupt handle is flushed and the interrupt
+ * will allow the cleanup of the outstanding descriptors.
+ */
+static void idxd_int_handle_revoke_drain(struct idxd_irq_entry *ie)
+{
+	struct idxd_wq *wq = ie_to_wq(ie);
+	struct idxd_device *idxd = wq->idxd;
+	struct device *dev = &idxd->pdev->dev;
+	struct dsa_hw_desc desc = {};
+	void __iomem *portal;
+	int rc;
+
+	/* Issue a simple drain operation with interrupt but no completion record */
+	desc.flags = IDXD_OP_FLAG_RCI;
+	desc.opcode = DSA_OPCODE_DRAIN;
+	desc.priv = 1;
+
+	if (ie->pasid != INVALID_IOASID)
+		desc.pasid = ie->pasid;
+	desc.int_handle = ie->int_handle;
+	portal = idxd_wq_portal_addr(wq);
+
+	/*
+	 * The wmb() makes sure that the descriptor is all there before we
+	 * issue.
+	 */
+	wmb();
+	if (wq_dedicated(wq)) {
+		iosubmit_cmds512(portal, &desc, 1);
+	} else {
+		rc = idxd_enqcmds(wq, portal, &desc);
+		/* This should not fail unless hardware failed. */
+		if (rc < 0)
+			dev_warn(dev, "Failed to submit drain desc on wq %d\n", wq->id);
+	}
+}
+
+static void idxd_abort_invalid_int_handle_descs(struct idxd_irq_entry *ie)
+{
+	LIST_HEAD(flist);
+	struct idxd_desc *d, *t;
+	struct llist_node *head;
+
+	spin_lock(&ie->list_lock);
+	head = llist_del_all(&ie->pending_llist);
+	if (head) {
+		llist_for_each_entry_safe(d, t, head, llnode)
+			list_add_tail(&d->list, &ie->work_list);
+	}
+
+	list_for_each_entry_safe(d, t, &ie->work_list, list) {
+		if (d->completion->status == DSA_COMP_INT_HANDLE_INVAL)
+			list_move_tail(&d->list, &flist);
+	}
+	spin_unlock(&ie->list_lock);
+
+	list_for_each_entry_safe(d, t, &flist, list) {
+		list_del(&d->list);
+		idxd_dma_complete_txd(d, IDXD_COMPLETE_ABORT, true);
+	}
+}
+
+static void idxd_int_handle_revoke(struct work_struct *work)
+{
+	struct idxd_int_handle_revoke *revoke =
+		container_of(work, struct idxd_int_handle_revoke, work);
+	struct idxd_device *idxd = revoke->idxd;
+	struct pci_dev *pdev = idxd->pdev;
+	struct device *dev = &pdev->dev;
+	int i, new_handle, rc;
+
+	if (!idxd->request_int_handles) {
+		kfree(revoke);
+		dev_warn(dev, "Unexpected int handle refresh interrupt.\n");
+		return;
+	}
+
+	/*
+	 * The loop attempts to acquire new interrupt handle for all interrupt
+	 * vectors that supports a handle. If a new interrupt handle is acquired and the
+	 * wq is kernel type, the driver will kill the percpu_ref to pause all
+	 * ongoing descriptor submissions. The interrupt handle is then changed.
+	 * After change, the percpu_ref is revived and all the pending submissions
+	 * are woken to try again. A drain is sent to for the interrupt handle
+	 * at the end to make sure all invalid int handle descriptors are processed.
+	 */
+	for (i = 1; i < idxd->irq_cnt; i++) {
+		struct idxd_irq_entry *ie = idxd_get_ie(idxd, i);
+		struct idxd_wq *wq = ie_to_wq(ie);
+
+		if (ie->int_handle == INVALID_INT_HANDLE)
+			continue;
+
+		rc = idxd_device_request_int_handle(idxd, i, &new_handle, IDXD_IRQ_MSIX);
+		if (rc < 0) {
+			dev_warn(dev, "get int handle %d failed: %d\n", i, rc);
+			/*
+			 * Failed to acquire new interrupt handle. Kill the WQ
+			 * and release all the pending submitters. The submitters will
+			 * get error return code and handle appropriately.
+			 */
+			ie->int_handle = INVALID_INT_HANDLE;
+			idxd_wq_quiesce(wq);
+			idxd_abort_invalid_int_handle_descs(ie);
+			continue;
+		}
+
+		/* No change in interrupt handle, nothing needs to be done */
+		if (ie->int_handle == new_handle)
+			continue;
+
+		if (wq->state != IDXD_WQ_ENABLED || wq->type != IDXD_WQT_KERNEL) {
+			/*
+			 * All the MSIX interrupts are allocated at once during probe.
+			 * Therefore we need to update all interrupts even if the WQ
+			 * isn't supporting interrupt operations.
+			 */
+			ie->int_handle = new_handle;
+			continue;
+		}
+
+		mutex_lock(&wq->wq_lock);
+		reinit_completion(&wq->wq_resurrect);
+
+		/* Kill percpu_ref to pause additional descriptor submissions */
+		percpu_ref_kill(&wq->wq_active);
+
+		/* Wait for all submitters quiesce before we change interrupt handle */
+		wait_for_completion(&wq->wq_dead);
+
+		ie->int_handle = new_handle;
+
+		/* Revive percpu ref and wake up all the waiting submitters */
+		percpu_ref_reinit(&wq->wq_active);
+		complete_all(&wq->wq_resurrect);
+		mutex_unlock(&wq->wq_lock);
+
+		/*
+		 * The delay here is to wait for all possible MOVDIR64B that
+		 * are issued before percpu_ref_kill() has happened to have
+		 * reached the PCIe domain before the drain is issued. The driver
+		 * needs to ensure that the drain descriptor issued does not pass
+		 * all the other issued descriptors that contain the invalid
+		 * interrupt handle in order to ensure that the drain descriptor
+		 * interrupt will allow the cleanup of all the descriptors with
+		 * invalid interrupt handle.
+		 */
+		if (wq_dedicated(wq))
+			udelay(100);
+		idxd_int_handle_revoke_drain(ie);
+	}
+	kfree(revoke);
+}
+
 static int process_misc_interrupts(struct idxd_device *idxd, u32 cause)
 {
 	struct device *dev = &idxd->pdev->dev;
@@ -101,6 +268,23 @@ static int process_misc_interrupts(struct idxd_device *idxd, u32 cause)
 		err = true;
 	}
 
+	if (cause & IDXD_INTC_INT_HANDLE_REVOKED) {
+		struct idxd_int_handle_revoke *revoke;
+
+		val |= IDXD_INTC_INT_HANDLE_REVOKED;
+
+		revoke = kzalloc(sizeof(*revoke), GFP_ATOMIC);
+		if (revoke) {
+			revoke->idxd = idxd;
+			INIT_WORK(&revoke->work, idxd_int_handle_revoke);
+			queue_work(idxd->wq, &revoke->work);
+
+		} else {
+			dev_err(dev, "Failed to allocate work for int handle revoke\n");
+			idxd_wqs_quiesce(idxd);
+		}
+	}
+
 	if (cause & IDXD_INTC_CMD) {
 		val |= IDXD_INTC_CMD;
 		complete(idxd->cmd_done);
@@ -157,7 +341,7 @@ static int process_misc_interrupts(struct idxd_device *idxd, u32 cause)
 irqreturn_t idxd_misc_thread(int vec, void *data)
 {
 	struct idxd_irq_entry *irq_entry = data;
-	struct idxd_device *idxd = irq_entry->idxd;
+	struct idxd_device *idxd = ie_to_idxd(irq_entry);
 	int rc;
 	u32 cause;
 
@@ -177,6 +361,51 @@ irqreturn_t idxd_misc_thread(int vec, void *data)
 	return IRQ_HANDLED;
 }
 
+static void idxd_int_handle_resubmit_work(struct work_struct *work)
+{
+	struct idxd_resubmit *irw = container_of(work, struct idxd_resubmit, work);
+	struct idxd_desc *desc = irw->desc;
+	struct idxd_wq *wq = desc->wq;
+	int rc;
+
+	desc->completion->status = 0;
+	rc = idxd_submit_desc(wq, desc);
+	if (rc < 0) {
+		dev_dbg(&wq->idxd->pdev->dev, "Failed to resubmit desc %d to wq %d.\n",
+			desc->id, wq->id);
+		/*
+		 * If the error is not -EAGAIN, it means the submission failed due to wq
+		 * has been killed instead of ENQCMDS failure. Here the driver needs to
+		 * notify the submitter of the failure by reporting abort status.
+		 *
+		 * -EAGAIN comes from ENQCMDS failure. idxd_submit_desc() will handle the
+		 * abort.
+		 */
+		if (rc != -EAGAIN) {
+			desc->completion->status = IDXD_COMP_DESC_ABORT;
+			idxd_dma_complete_txd(desc, IDXD_COMPLETE_ABORT, false);
+		}
+		idxd_free_desc(wq, desc);
+	}
+	kfree(irw);
+}
+
+bool idxd_queue_int_handle_resubmit(struct idxd_desc *desc)
+{
+	struct idxd_wq *wq = desc->wq;
+	struct idxd_device *idxd = wq->idxd;
+	struct idxd_resubmit *irw;
+
+	irw = kzalloc(sizeof(*irw), GFP_KERNEL);
+	if (!irw)
+		return false;
+
+	irw->desc = desc;
+	INIT_WORK(&irw->work, idxd_int_handle_resubmit_work);
+	queue_work(idxd->wq, &irw->work);
+	return true;
+}
+
 static void irq_process_pending_llist(struct idxd_irq_entry *irq_entry)
 {
 	struct idxd_desc *desc, *t;
@@ -195,11 +424,11 @@ static void irq_process_pending_llist(struct idxd_irq_entry *irq_entry)
 			 * and 0xff, which DSA_COMP_STATUS_MASK can mask out.
 			 */
 			if (unlikely(desc->completion->status == IDXD_COMP_DESC_ABORT)) {
-				complete_desc(desc, IDXD_COMPLETE_ABORT);
+				idxd_dma_complete_txd(desc, IDXD_COMPLETE_ABORT, true);
 				continue;
 			}
 
-			complete_desc(desc, IDXD_COMPLETE_NORMAL);
+			idxd_dma_complete_txd(desc, IDXD_COMPLETE_NORMAL, true);
 		} else {
 			spin_lock(&irq_entry->list_lock);
 			list_add_tail(&desc->list,
@@ -238,11 +467,11 @@ static void irq_process_work_list(struct idxd_irq_entry *irq_entry)
 		 * and 0xff, which DSA_COMP_STATUS_MASK can mask out.
 		 */
 		if (unlikely(desc->completion->status == IDXD_COMP_DESC_ABORT)) {
-			complete_desc(desc, IDXD_COMPLETE_ABORT);
+			idxd_dma_complete_txd(desc, IDXD_COMPLETE_ABORT, true);
 			continue;
 		}
 
-		complete_desc(desc, IDXD_COMPLETE_NORMAL);
+		idxd_dma_complete_txd(desc, IDXD_COMPLETE_NORMAL, true);
 	}
 }
 

drivers/dma/idxd/registers.h

@@ -64,9 +64,9 @@ union wq_cap_reg {
 union group_cap_reg {
 	struct {
 		u64 num_groups:8;
-		u64 total_tokens:8;
-		u64 token_en:1;
-		u64 token_limit:1;
+		u64 total_rdbufs:8;	/* formerly total_tokens */
+		u64 rdbuf_ctrl:1;	/* formerly token_en */
+		u64 rdbuf_limit:1;	/* formerly token_limit */
 		u64 rsvd:46;
 	};
 	u64 bits;
@@ -110,7 +110,7 @@ union offsets_reg {
 #define IDXD_GENCFG_OFFSET		0x80
 union gencfg_reg {
 	struct {
-		u32 token_limit:8;
+		u32 rdbuf_limit:8;
 		u32 rsvd:4;
 		u32 user_int_en:1;
 		u32 rsvd2:19;
@@ -158,6 +158,7 @@ enum idxd_device_reset_type {
 #define IDXD_INTC_OCCUPY			0x04
 #define IDXD_INTC_PERFMON_OVFL		0x08
 #define IDXD_INTC_HALT_STATE		0x10
+#define IDXD_INTC_INT_HANDLE_REVOKED	0x80000000
 
 #define IDXD_CMD_OFFSET			0xa0
 union idxd_command_reg {
@@ -287,10 +288,10 @@ union group_flags {
 		u32 tc_a:3;
 		u32 tc_b:3;
 		u32 rsvd:1;
-		u32 use_token_limit:1;
-		u32 tokens_reserved:8;
+		u32 use_rdbuf_limit:1;
+		u32 rdbufs_reserved:8;
 		u32 rsvd2:4;
-		u32 tokens_allowed:8;
+		u32 rdbufs_allowed:8;
 		u32 rsvd3:4;
 	};
 	u32 bits;

drivers/dma/idxd/submit.c

@@ -21,15 +21,6 @@ static struct idxd_desc *__get_desc(struct idxd_wq *wq, int idx, int cpu)
 	if (device_pasid_enabled(idxd))
 		desc->hw->pasid = idxd->pasid;
 
-	/*
-	 * On host, MSIX vecotr 0 is used for misc interrupt. Therefore when we match
-	 * vector 1:1 to the WQ id, we need to add 1
-	 */
-	if (!idxd->int_handles)
-		desc->hw->int_handle = wq->id + 1;
-	else
-		desc->hw->int_handle = idxd->int_handles[wq->id];
-
 	return desc;
 }
 
@@ -134,34 +125,57 @@ static void llist_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie,
 	spin_unlock(&ie->list_lock);
 
 	if (found)
-		complete_desc(found, IDXD_COMPLETE_ABORT);
+		idxd_dma_complete_txd(found, IDXD_COMPLETE_ABORT, false);
 
 	/*
-	 * complete_desc() will return desc to allocator and the desc can be
-	 * acquired by a different process and the desc->list can be modified.
-	 * Delete desc from list so the list trasversing does not get corrupted
-	 * by the other process.
+	 * completing the descriptor will return desc to allocator and
+	 * the desc can be acquired by a different process and the
+	 * desc->list can be modified.  Delete desc from list so the
+	 * list trasversing does not get corrupted by the other process.
 	 */
 	list_for_each_entry_safe(d, t, &flist, list) {
 		list_del_init(&d->list);
-		complete_desc(d, IDXD_COMPLETE_NORMAL);
+		idxd_dma_complete_txd(found, IDXD_COMPLETE_ABORT, true);
 	}
 }
 
+/*
+ * ENQCMDS typically fail when the WQ is inactive or busy. On host submission, the driver
+ * has better control of number of descriptors being submitted to a shared wq by limiting
+ * the number of driver allocated descriptors to the wq size. However, when the swq is
+ * exported to a guest kernel, it may be shared with multiple guest kernels. This means
+ * the likelihood of getting busy returned on the swq when submitting goes significantly up.
+ * Having a tunable retry mechanism allows the driver to keep trying for a bit before giving
+ * up. The sysfs knob can be tuned by the system administrator.
+ */
+int idxd_enqcmds(struct idxd_wq *wq, void __iomem *portal, const void *desc)
+{
+	int rc, retries = 0;
+
+	do {
+		rc = enqcmds(portal, desc);
+		if (rc == 0)
+			break;
+		cpu_relax();
+	} while (retries++ < wq->enqcmds_retries);
+
+	return rc;
+}
+
 int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc)
 {
 	struct idxd_device *idxd = wq->idxd;
 	struct idxd_irq_entry *ie = NULL;
+	u32 desc_flags = desc->hw->flags;
 	void __iomem *portal;
 	int rc;
 
-	if (idxd->state != IDXD_DEV_ENABLED) {
-		idxd_free_desc(wq, desc);
+	if (idxd->state != IDXD_DEV_ENABLED)
 		return -EIO;
-	}
 
 	if (!percpu_ref_tryget_live(&wq->wq_active)) {
-		idxd_free_desc(wq, desc);
+		wait_for_completion(&wq->wq_resurrect);
+		if (!percpu_ref_tryget_live(&wq->wq_active))
 			return -ENXIO;
 	}
 
@@ -178,28 +192,21 @@ int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc)
 	 * Pending the descriptor to the lockless list for the irq_entry
 	 * that we designated the descriptor to.
 	 */
-	if (desc->hw->flags & IDXD_OP_FLAG_RCI) {
-		ie = &idxd->irq_entries[wq->id + 1];
+	if (desc_flags & IDXD_OP_FLAG_RCI) {
+		ie = &wq->ie;
+		desc->hw->int_handle = ie->int_handle;
 		llist_add(&desc->llnode, &ie->pending_llist);
 	}
 
 	if (wq_dedicated(wq)) {
 		iosubmit_cmds512(portal, desc->hw, 1);
 	} else {
-		/*
-		 * It's not likely that we would receive queue full rejection
-		 * since the descriptor allocation gates at wq size. If we
-		 * receive a -EAGAIN, that means something went wrong such as the
-		 * device is not accepting descriptor at all.
-		 */
-		rc = enqcmds(portal, desc->hw);
+		rc = idxd_enqcmds(wq, portal, desc->hw);
 		if (rc < 0) {
 			percpu_ref_put(&wq->wq_active);
 			/* abort operation frees the descriptor */
 			if (ie)
 				llist_abort_desc(wq, ie, desc);
-			else
-				idxd_free_desc(wq, desc);
 			return rc;
 		}
 	}

drivers/dma/ioat/sysfs.c

@@ -158,8 +158,9 @@ static struct attribute *ioat_attrs[] = {
 	&intr_coalesce_attr.attr,
 	NULL,
 };
+ATTRIBUTE_GROUPS(ioat);
 
 struct kobj_type ioat_ktype = {
 	.sysfs_ops = &ioat_sysfs_ops,
-	.default_attrs = ioat_attrs,
+	.default_groups = ioat_groups,
 };

drivers/dma/pch_dma.c

@@ -835,7 +835,7 @@ static int pch_dma_probe(struct pci_dev *pdev,
 		goto err_disable_pdev;
 	}
 
-	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+	err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
 	if (err) {
 		dev_err(&pdev->dev, "Cannot set proper DMA config\n");
 		goto err_free_res;

drivers/dma/ppc4xx/adma.c

@@ -3240,7 +3240,6 @@ static int ppc440spe_adma_dma2rxor_prep_src(
 		struct ppc440spe_rxor *cursor, int index,
 		int src_cnt, u32 addr)
 {
-	int rval = 0;
 	u32 sign;
 	struct ppc440spe_adma_desc_slot *desc = hdesc;
 	int i;
@@ -3348,7 +3347,7 @@ static int ppc440spe_adma_dma2rxor_prep_src(
 		break;
 	}
 
-	return rval;
+	return 0;
 }
 
 /**

drivers/dma/qcom/gpi.c

@@ -2206,10 +2206,8 @@ static int gpi_probe(struct platform_device *pdev)
 
 		/* set up irq */
 		ret = platform_get_irq(pdev, i);
-		if (ret < 0) {
-			dev_err(gpi_dev->dev, "platform_get_irq failed for %d:%d\n", i, ret);
+		if (ret < 0)
 			return ret;
-		}
 		gpii->irq = ret;
 
 		/* set up channel specific register info */

drivers/dma/sh/rcar-dmac.c

@@ -236,7 +236,7 @@ struct rcar_dmac_of_data {
 #define RCAR_DMAOR_PRI_ROUND_ROBIN	(3 << 8)
 #define RCAR_DMAOR_AE			(1 << 2)
 #define RCAR_DMAOR_DME			(1 << 0)
-#define RCAR_DMACHCLR			0x0080	/* Not on R-Car V3U */
+#define RCAR_DMACHCLR			0x0080	/* Not on R-Car Gen4 */
 #define RCAR_DMADPSEC			0x00a0
 
 #define RCAR_DMASAR			0x0000
@@ -299,8 +299,8 @@ struct rcar_dmac_of_data {
 #define RCAR_DMAFIXDAR			0x0014
 #define RCAR_DMAFIXDPBASE		0x0060
 
-/* For R-Car V3U */
-#define RCAR_V3U_DMACHCLR		0x0100
+/* For R-Car Gen4 */
+#define RCAR_GEN4_DMACHCLR		0x0100
 
 /* Hardcode the MEMCPY transfer size to 4 bytes. */
 #define RCAR_DMAC_MEMCPY_XFER_SIZE	4
@@ -345,7 +345,7 @@ static void rcar_dmac_chan_clear(struct rcar_dmac *dmac,
 				 struct rcar_dmac_chan *chan)
 {
 	if (dmac->chan_base)
-		rcar_dmac_chan_write(chan, RCAR_V3U_DMACHCLR, 1);
+		rcar_dmac_chan_write(chan, RCAR_GEN4_DMACHCLR, 1);
 	else
 		rcar_dmac_write(dmac, RCAR_DMACHCLR, BIT(chan->index));
 }
@@ -357,7 +357,7 @@ static void rcar_dmac_chan_clear_all(struct rcar_dmac *dmac)
 
 	if (dmac->chan_base) {
 		for_each_rcar_dmac_chan(i, dmac, chan)
-			rcar_dmac_chan_write(chan, RCAR_V3U_DMACHCLR, 1);
+			rcar_dmac_chan_write(chan, RCAR_GEN4_DMACHCLR, 1);
 	} else {
 		rcar_dmac_write(dmac, RCAR_DMACHCLR, dmac->channels_mask);
 	}
@@ -2009,7 +2009,7 @@ static const struct rcar_dmac_of_data rcar_dmac_data = {
 	.chan_offset_stride	= 0x80,
 };
 
-static const struct rcar_dmac_of_data rcar_v3u_dmac_data = {
+static const struct rcar_dmac_of_data rcar_gen4_dmac_data = {
 	.chan_offset_base	= 0x0,
 	.chan_offset_stride	= 0x1000,
 };
@@ -2018,9 +2018,12 @@ static const struct of_device_id rcar_dmac_of_ids[] = {
 	{
 		.compatible = "renesas,rcar-dmac",
 		.data = &rcar_dmac_data,
+	}, {
+		.compatible = "renesas,rcar-gen4-dmac",
+		.data = &rcar_gen4_dmac_data,
 	}, {
 		.compatible = "renesas,dmac-r8a779a0",
-		.data = &rcar_v3u_dmac_data,
+		.data = &rcar_gen4_dmac_data,
 	},
 	{ /* Sentinel */ }
 };

drivers/dma/sh/shdma-base.c

@@ -1034,9 +1034,7 @@ EXPORT_SYMBOL(shdma_cleanup);
 
 static int __init shdma_enter(void)
 {
-	shdma_slave_used = kcalloc(DIV_ROUND_UP(slave_num, BITS_PER_LONG),
-				   sizeof(long),
-				   GFP_KERNEL);
+	shdma_slave_used = bitmap_zalloc(slave_num, GFP_KERNEL);
 	if (!shdma_slave_used)
 		return -ENOMEM;
 	return 0;
@@ -1045,7 +1043,7 @@ module_init(shdma_enter);
 
 static void __exit shdma_exit(void)
 {
-	kfree(shdma_slave_used);
+	bitmap_free(shdma_slave_used);
 }
 module_exit(shdma_exit);
 

drivers/dma/stm32-mdma.c

@@ -10,6 +10,7 @@
  * Inspired by stm32-dma.c and dma-jz4780.c
  */
 
+#include <linux/bitfield.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/dmaengine.h>
@@ -32,13 +33,6 @@
 
 #include "virt-dma.h"
 
-/*  MDMA Generic getter/setter */
-#define STM32_MDMA_SHIFT(n)		(ffs(n) - 1)
-#define STM32_MDMA_SET(n, mask)		(((n) << STM32_MDMA_SHIFT(mask)) & \
-					 (mask))
-#define STM32_MDMA_GET(n, mask)		(((n) & (mask)) >> \
-					 STM32_MDMA_SHIFT(mask))
-
 #define STM32_MDMA_GISR0		0x0000 /* MDMA Int Status Reg 1 */
 #define STM32_MDMA_GISR1		0x0004 /* MDMA Int Status Reg 2 */
 
@@ -80,8 +74,7 @@
 #define STM32_MDMA_CCR_HEX		BIT(13)
 #define STM32_MDMA_CCR_BEX		BIT(12)
 #define STM32_MDMA_CCR_PL_MASK		GENMASK(7, 6)
-#define STM32_MDMA_CCR_PL(n)		STM32_MDMA_SET(n, \
-						       STM32_MDMA_CCR_PL_MASK)
+#define STM32_MDMA_CCR_PL(n)		FIELD_PREP(STM32_MDMA_CCR_PL_MASK, (n))
 #define STM32_MDMA_CCR_TCIE		BIT(5)
 #define STM32_MDMA_CCR_BTIE		BIT(4)
 #define STM32_MDMA_CCR_BRTIE		BIT(3)
@@ -99,48 +92,33 @@
 #define STM32_MDMA_CTCR_BWM		BIT(31)
 #define STM32_MDMA_CTCR_SWRM		BIT(30)
 #define STM32_MDMA_CTCR_TRGM_MSK	GENMASK(29, 28)
-#define STM32_MDMA_CTCR_TRGM(n)		STM32_MDMA_SET((n), \
-						       STM32_MDMA_CTCR_TRGM_MSK)
-#define STM32_MDMA_CTCR_TRGM_GET(n)	STM32_MDMA_GET((n), \
-						       STM32_MDMA_CTCR_TRGM_MSK)
+#define STM32_MDMA_CTCR_TRGM(n)		FIELD_PREP(STM32_MDMA_CTCR_TRGM_MSK, (n))
+#define STM32_MDMA_CTCR_TRGM_GET(n)	FIELD_GET(STM32_MDMA_CTCR_TRGM_MSK, (n))
 #define STM32_MDMA_CTCR_PAM_MASK	GENMASK(27, 26)
-#define STM32_MDMA_CTCR_PAM(n)		STM32_MDMA_SET(n, \
-						       STM32_MDMA_CTCR_PAM_MASK)
+#define STM32_MDMA_CTCR_PAM(n)		FIELD_PREP(STM32_MDMA_CTCR_PAM_MASK, (n))
 #define STM32_MDMA_CTCR_PKE		BIT(25)
 #define STM32_MDMA_CTCR_TLEN_MSK	GENMASK(24, 18)
-#define STM32_MDMA_CTCR_TLEN(n)		STM32_MDMA_SET((n), \
-						       STM32_MDMA_CTCR_TLEN_MSK)
-#define STM32_MDMA_CTCR_TLEN_GET(n)	STM32_MDMA_GET((n), \
-						       STM32_MDMA_CTCR_TLEN_MSK)
+#define STM32_MDMA_CTCR_TLEN(n)		FIELD_PREP(STM32_MDMA_CTCR_TLEN_MSK, (n))
+#define STM32_MDMA_CTCR_TLEN_GET(n)	FIELD_GET(STM32_MDMA_CTCR_TLEN_MSK, (n))
 #define STM32_MDMA_CTCR_LEN2_MSK	GENMASK(25, 18)
-#define STM32_MDMA_CTCR_LEN2(n)		STM32_MDMA_SET((n), \
-						       STM32_MDMA_CTCR_LEN2_MSK)
-#define STM32_MDMA_CTCR_LEN2_GET(n)	STM32_MDMA_GET((n), \
-						       STM32_MDMA_CTCR_LEN2_MSK)
+#define STM32_MDMA_CTCR_LEN2(n)		FIELD_PREP(STM32_MDMA_CTCR_LEN2_MSK, (n))
+#define STM32_MDMA_CTCR_LEN2_GET(n)	FIELD_GET(STM32_MDMA_CTCR_LEN2_MSK, (n))
 #define STM32_MDMA_CTCR_DBURST_MASK	GENMASK(17, 15)
-#define STM32_MDMA_CTCR_DBURST(n)	STM32_MDMA_SET(n, \
-						    STM32_MDMA_CTCR_DBURST_MASK)
+#define STM32_MDMA_CTCR_DBURST(n)	FIELD_PREP(STM32_MDMA_CTCR_DBURST_MASK, (n))
 #define STM32_MDMA_CTCR_SBURST_MASK	GENMASK(14, 12)
-#define STM32_MDMA_CTCR_SBURST(n)	STM32_MDMA_SET(n, \
-						    STM32_MDMA_CTCR_SBURST_MASK)
+#define STM32_MDMA_CTCR_SBURST(n)	FIELD_PREP(STM32_MDMA_CTCR_SBURST_MASK, (n))
 #define STM32_MDMA_CTCR_DINCOS_MASK	GENMASK(11, 10)
-#define STM32_MDMA_CTCR_DINCOS(n)	STM32_MDMA_SET((n), \
-						    STM32_MDMA_CTCR_DINCOS_MASK)
+#define STM32_MDMA_CTCR_DINCOS(n)	FIELD_PREP(STM32_MDMA_CTCR_DINCOS_MASK, (n))
 #define STM32_MDMA_CTCR_SINCOS_MASK	GENMASK(9, 8)
-#define STM32_MDMA_CTCR_SINCOS(n)	STM32_MDMA_SET((n), \
-						    STM32_MDMA_CTCR_SINCOS_MASK)
+#define STM32_MDMA_CTCR_SINCOS(n)	FIELD_PREP(STM32_MDMA_CTCR_SINCOS_MASK, (n))
 #define STM32_MDMA_CTCR_DSIZE_MASK	GENMASK(7, 6)
-#define STM32_MDMA_CTCR_DSIZE(n)	STM32_MDMA_SET(n, \
-						     STM32_MDMA_CTCR_DSIZE_MASK)
+#define STM32_MDMA_CTCR_DSIZE(n)	FIELD_PREP(STM32_MDMA_CTCR_DSIZE_MASK, (n))
 #define STM32_MDMA_CTCR_SSIZE_MASK	GENMASK(5, 4)
-#define STM32_MDMA_CTCR_SSIZE(n)	STM32_MDMA_SET(n, \
-						     STM32_MDMA_CTCR_SSIZE_MASK)
+#define STM32_MDMA_CTCR_SSIZE(n)	FIELD_PREP(STM32_MDMA_CTCR_SSIZE_MASK, (n))
 #define STM32_MDMA_CTCR_DINC_MASK	GENMASK(3, 2)
-#define STM32_MDMA_CTCR_DINC(n)		STM32_MDMA_SET((n), \
-						      STM32_MDMA_CTCR_DINC_MASK)
+#define STM32_MDMA_CTCR_DINC(n)		FIELD_PREP(STM32_MDMA_CTCR_DINC_MASK, (n))
 #define STM32_MDMA_CTCR_SINC_MASK	GENMASK(1, 0)
-#define STM32_MDMA_CTCR_SINC(n)		STM32_MDMA_SET((n), \
-						      STM32_MDMA_CTCR_SINC_MASK)
+#define STM32_MDMA_CTCR_SINC(n)		FIELD_PREP(STM32_MDMA_CTCR_SINC_MASK, (n))
 #define STM32_MDMA_CTCR_CFG_MASK	(STM32_MDMA_CTCR_SINC_MASK \
 					| STM32_MDMA_CTCR_DINC_MASK \
 					| STM32_MDMA_CTCR_SINCOS_MASK \
@@ -151,16 +129,13 @@
 /* MDMA Channel x block number of data register */
 #define STM32_MDMA_CBNDTR(x)		(0x54 + 0x40 * (x))
 #define STM32_MDMA_CBNDTR_BRC_MK	GENMASK(31, 20)
-#define STM32_MDMA_CBNDTR_BRC(n)	STM32_MDMA_SET(n, \
-						       STM32_MDMA_CBNDTR_BRC_MK)
-#define STM32_MDMA_CBNDTR_BRC_GET(n)	STM32_MDMA_GET((n), \
-						       STM32_MDMA_CBNDTR_BRC_MK)
+#define STM32_MDMA_CBNDTR_BRC(n)	FIELD_PREP(STM32_MDMA_CBNDTR_BRC_MK, (n))
+#define STM32_MDMA_CBNDTR_BRC_GET(n)	FIELD_GET(STM32_MDMA_CBNDTR_BRC_MK, (n))
 
 #define STM32_MDMA_CBNDTR_BRDUM		BIT(19)
 #define STM32_MDMA_CBNDTR_BRSUM		BIT(18)
 #define STM32_MDMA_CBNDTR_BNDT_MASK	GENMASK(16, 0)
-#define STM32_MDMA_CBNDTR_BNDT(n)	STM32_MDMA_SET(n, \
-						    STM32_MDMA_CBNDTR_BNDT_MASK)
+#define STM32_MDMA_CBNDTR_BNDT(n)	FIELD_PREP(STM32_MDMA_CBNDTR_BNDT_MASK, (n))
 
 /* MDMA Channel x source address register */
 #define STM32_MDMA_CSAR(x)		(0x58 + 0x40 * (x))
@@ -171,11 +146,9 @@
 /* MDMA Channel x block repeat address update register */
 #define STM32_MDMA_CBRUR(x)		(0x60 + 0x40 * (x))
 #define STM32_MDMA_CBRUR_DUV_MASK	GENMASK(31, 16)
-#define STM32_MDMA_CBRUR_DUV(n)		STM32_MDMA_SET(n, \
-						      STM32_MDMA_CBRUR_DUV_MASK)
+#define STM32_MDMA_CBRUR_DUV(n)		FIELD_PREP(STM32_MDMA_CBRUR_DUV_MASK, (n))
 #define STM32_MDMA_CBRUR_SUV_MASK	GENMASK(15, 0)
-#define STM32_MDMA_CBRUR_SUV(n)		STM32_MDMA_SET(n, \
-						      STM32_MDMA_CBRUR_SUV_MASK)
+#define STM32_MDMA_CBRUR_SUV(n)		FIELD_PREP(STM32_MDMA_CBRUR_SUV_MASK, (n))
 
 /* MDMA Channel x link address register */
 #define STM32_MDMA_CLAR(x)		(0x64 + 0x40 * (x))
@@ -184,9 +157,8 @@
 #define STM32_MDMA_CTBR(x)		(0x68 + 0x40 * (x))
 #define STM32_MDMA_CTBR_DBUS		BIT(17)
 #define STM32_MDMA_CTBR_SBUS		BIT(16)
-#define STM32_MDMA_CTBR_TSEL_MASK	GENMASK(7, 0)
-#define STM32_MDMA_CTBR_TSEL(n)		STM32_MDMA_SET(n, \
-						      STM32_MDMA_CTBR_TSEL_MASK)
+#define STM32_MDMA_CTBR_TSEL_MASK	GENMASK(5, 0)
+#define STM32_MDMA_CTBR_TSEL(n)		FIELD_PREP(STM32_MDMA_CTBR_TSEL_MASK, (n))
 
 /* MDMA Channel x mask address register */
 #define STM32_MDMA_CMAR(x)		(0x70 + 0x40 * (x))
@@ -1279,7 +1251,7 @@ static size_t stm32_mdma_desc_residue(struct stm32_mdma_chan *chan,
 				      u32 curr_hwdesc)
 {
 	struct stm32_mdma_device *dmadev = stm32_mdma_get_dev(chan);
-	struct stm32_mdma_hwdesc *hwdesc = desc->node[0].hwdesc;
+	struct stm32_mdma_hwdesc *hwdesc;
 	u32 cbndtr, residue, modulo, burst_size;
 	int i;
 

drivers/dma/ti/Makefile

@@ -8,5 +8,6 @@ obj-$(CONFIG_TI_K3_PSIL) += k3-psil.o \
 			    k3-psil-am654.o \
 			    k3-psil-j721e.o \
 			    k3-psil-j7200.o \
-			    k3-psil-am64.o
+			    k3-psil-am64.o \
+			    k3-psil-j721s2.o
 obj-$(CONFIG_TI_DMA_CROSSBAR) += dma-crossbar.o

drivers/dma/ti/edma.c

@@ -1681,8 +1681,7 @@ static irqreturn_t dma_ccerr_handler(int irq, void *data)
 
 			dev_dbg(ecc->dev, "EMR%d 0x%08x\n", j, val);
 			emr = val;
-			for (i = find_next_bit(&emr, 32, 0); i < 32;
-			     i = find_next_bit(&emr, 32, i + 1)) {
+			for_each_set_bit(i, &emr, 32) {
 				int k = (j << 5) + i;
 
 				/* Clear the corresponding EMR bits */

drivers/dma/ti/k3-psil-j721s2.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Copyright (C) 2021 Texas Instruments Incorporated - https://www.ti.com
+ */
+
+#include <linux/kernel.h>
+
+#include "k3-psil-priv.h"
+
+#define PSIL_PDMA_XY_TR(x)				\
+	{						\
+		.thread_id = x,				\
+		.ep_config = {				\
+			.ep_type = PSIL_EP_PDMA_XY,	\
+		},					\
+	}
+
+#define PSIL_PDMA_XY_PKT(x)				\
+	{						\
+		.thread_id = x,				\
+		.ep_config = {				\
+			.ep_type = PSIL_EP_PDMA_XY,	\
+			.pkt_mode = 1,			\
+		},					\
+	}
+
+#define PSIL_PDMA_MCASP(x)				\
+	{						\
+		.thread_id = x,				\
+		.ep_config = {				\
+			.ep_type = PSIL_EP_PDMA_XY,	\
+			.pdma_acc32 = 1,		\
+			.pdma_burst = 1,		\
+		},					\
+	}
+
+#define PSIL_ETHERNET(x)				\
+	{						\
+		.thread_id = x,				\
+		.ep_config = {				\
+			.ep_type = PSIL_EP_NATIVE,	\
+			.pkt_mode = 1,			\
+			.needs_epib = 1,		\
+			.psd_size = 16,			\
+		},					\
+	}
+
+#define PSIL_SA2UL(x, tx)				\
+	{						\
+		.thread_id = x,				\
+		.ep_config = {				\
+			.ep_type = PSIL_EP_NATIVE,	\
+			.pkt_mode = 1,			\
+			.needs_epib = 1,		\
+			.psd_size = 64,			\
+			.notdpkt = tx,			\
+		},					\
+	}
+
+/* PSI-L source thread IDs, used for RX (DMA_DEV_TO_MEM) */
+static struct psil_ep j721s2_src_ep_map[] = {
+	/* PDMA_MCASP - McASP0-4 */
+	PSIL_PDMA_MCASP(0x4400),
+	PSIL_PDMA_MCASP(0x4401),
+	PSIL_PDMA_MCASP(0x4402),
+	PSIL_PDMA_MCASP(0x4403),
+	PSIL_PDMA_MCASP(0x4404),
+	/* PDMA_SPI_G0 - SPI0-3 */
+	PSIL_PDMA_XY_PKT(0x4600),
+	PSIL_PDMA_XY_PKT(0x4601),
+	PSIL_PDMA_XY_PKT(0x4602),
+	PSIL_PDMA_XY_PKT(0x4603),
+	PSIL_PDMA_XY_PKT(0x4604),
+	PSIL_PDMA_XY_PKT(0x4605),
+	PSIL_PDMA_XY_PKT(0x4606),
+	PSIL_PDMA_XY_PKT(0x4607),
+	PSIL_PDMA_XY_PKT(0x4608),
+	PSIL_PDMA_XY_PKT(0x4609),
+	PSIL_PDMA_XY_PKT(0x460a),
+	PSIL_PDMA_XY_PKT(0x460b),
+	PSIL_PDMA_XY_PKT(0x460c),
+	PSIL_PDMA_XY_PKT(0x460d),
+	PSIL_PDMA_XY_PKT(0x460e),
+	PSIL_PDMA_XY_PKT(0x460f),
+	/* PDMA_SPI_G1 - SPI4-7 */
+	PSIL_PDMA_XY_PKT(0x4610),
+	PSIL_PDMA_XY_PKT(0x4611),
+	PSIL_PDMA_XY_PKT(0x4612),
+	PSIL_PDMA_XY_PKT(0x4613),
+	PSIL_PDMA_XY_PKT(0x4614),
+	PSIL_PDMA_XY_PKT(0x4615),
+	PSIL_PDMA_XY_PKT(0x4616),
+	PSIL_PDMA_XY_PKT(0x4617),
+	PSIL_PDMA_XY_PKT(0x4618),
+	PSIL_PDMA_XY_PKT(0x4619),
+	PSIL_PDMA_XY_PKT(0x461a),
+	PSIL_PDMA_XY_PKT(0x461b),
+	PSIL_PDMA_XY_PKT(0x461c),
+	PSIL_PDMA_XY_PKT(0x461d),
+	PSIL_PDMA_XY_PKT(0x461e),
+	PSIL_PDMA_XY_PKT(0x461f),
+	/* PDMA_USART_G0 - UART0-1 */
+	PSIL_PDMA_XY_PKT(0x4700),
+	PSIL_PDMA_XY_PKT(0x4701),
+	/* PDMA_USART_G1 - UART2-3 */
+	PSIL_PDMA_XY_PKT(0x4702),
+	PSIL_PDMA_XY_PKT(0x4703),
+	/* PDMA_USART_G2 - UART4-9 */
+	PSIL_PDMA_XY_PKT(0x4704),
+	PSIL_PDMA_XY_PKT(0x4705),
+	PSIL_PDMA_XY_PKT(0x4706),
+	PSIL_PDMA_XY_PKT(0x4707),
+	PSIL_PDMA_XY_PKT(0x4708),
+	PSIL_PDMA_XY_PKT(0x4709),
+	/* CPSW0 */
+	PSIL_ETHERNET(0x7000),
+	/* MCU_PDMA0 (MCU_PDMA_MISC_G0) - SPI0 */
+	PSIL_PDMA_XY_PKT(0x7100),
+	PSIL_PDMA_XY_PKT(0x7101),
+	PSIL_PDMA_XY_PKT(0x7102),
+	PSIL_PDMA_XY_PKT(0x7103),
+	/* MCU_PDMA1 (MCU_PDMA_MISC_G1) - SPI1-2 */
+	PSIL_PDMA_XY_PKT(0x7200),
+	PSIL_PDMA_XY_PKT(0x7201),
+	PSIL_PDMA_XY_PKT(0x7202),
+	PSIL_PDMA_XY_PKT(0x7203),
+	PSIL_PDMA_XY_PKT(0x7204),
+	PSIL_PDMA_XY_PKT(0x7205),
+	PSIL_PDMA_XY_PKT(0x7206),
+	PSIL_PDMA_XY_PKT(0x7207),
+	/* MCU_PDMA2 (MCU_PDMA_MISC_G2) - UART0 */
+	PSIL_PDMA_XY_PKT(0x7300),
+	/* MCU_PDMA_ADC - ADC0-1 */
+	PSIL_PDMA_XY_TR(0x7400),
+	PSIL_PDMA_XY_TR(0x7401),
+	PSIL_PDMA_XY_TR(0x7402),
+	PSIL_PDMA_XY_TR(0x7403),
+	/* SA2UL */
+	PSIL_SA2UL(0x7500, 0),
+	PSIL_SA2UL(0x7501, 0),
+	PSIL_SA2UL(0x7502, 0),
+	PSIL_SA2UL(0x7503, 0),
+};
+
+/* PSI-L destination thread IDs, used for TX (DMA_MEM_TO_DEV) */
+static struct psil_ep j721s2_dst_ep_map[] = {
+	/* CPSW0 */
+	PSIL_ETHERNET(0xf000),
+	PSIL_ETHERNET(0xf001),
+	PSIL_ETHERNET(0xf002),
+	PSIL_ETHERNET(0xf003),
+	PSIL_ETHERNET(0xf004),
+	PSIL_ETHERNET(0xf005),
+	PSIL_ETHERNET(0xf006),
+	PSIL_ETHERNET(0xf007),
+	/* SA2UL */
+	PSIL_SA2UL(0xf500, 1),
+	PSIL_SA2UL(0xf501, 1),
+};
+
+struct psil_ep_map j721s2_ep_map = {
+	.name = "j721s2",
+	.src = j721s2_src_ep_map,
+	.src_count = ARRAY_SIZE(j721s2_src_ep_map),
+	.dst = j721s2_dst_ep_map,
+	.dst_count = ARRAY_SIZE(j721s2_dst_ep_map),
+};

drivers/dma/ti/k3-psil-priv.h

@@ -41,5 +41,6 @@ extern struct psil_ep_map am654_ep_map;
 extern struct psil_ep_map j721e_ep_map;
 extern struct psil_ep_map j7200_ep_map;
 extern struct psil_ep_map am64_ep_map;
+extern struct psil_ep_map j721s2_ep_map;
 
 #endif /* K3_PSIL_PRIV_H_ */

drivers/dma/ti/k3-psil.c

@@ -21,6 +21,7 @@ static const struct soc_device_attribute k3_soc_devices[] = {
 	{ .family = "J721E", .data = &j721e_ep_map },
 	{ .family = "J7200", .data = &j7200_ep_map },
 	{ .family = "AM64X", .data = &am64_ep_map },
+	{ .family = "J721S2", .data = &j721s2_ep_map },
 	{ /* sentinel */ }
 };
 

drivers/dma/ti/k3-udma.c

@@ -4374,6 +4374,7 @@ static const struct soc_device_attribute k3_soc_devices[] = {
 	{ .family = "J721E", .data = &j721e_soc_data },
 	{ .family = "J7200", .data = &j7200_soc_data },
 	{ .family = "AM64X", .data = &am64_soc_data },
+	{ .family = "J721S2", .data = &j721e_soc_data},
 	{ /* sentinel */ }
 };
 

drivers/dma/uniphier-xdmac.c

@@ -131,8 +131,9 @@ uniphier_xdmac_next_desc(struct uniphier_xdmac_chan *xc)
 static void uniphier_xdmac_chan_start(struct uniphier_xdmac_chan *xc,
 				      struct uniphier_xdmac_desc *xd)
 {
-	u32 src_mode, src_addr, src_width;
-	u32 dst_mode, dst_addr, dst_width;
+	u32 src_mode, src_width;
+	u32 dst_mode, dst_width;
+	dma_addr_t src_addr, dst_addr;
 	u32 val, its, tnum;
 	enum dma_slave_buswidth buswidth;
 

drivers/dma/xilinx/xilinx_dma.c

@@ -2127,6 +2127,126 @@ xilinx_cdma_prep_memcpy(struct dma_chan *dchan, dma_addr_t dma_dst,
 	return NULL;
 }
 
+/**
+ * xilinx_cdma_prep_memcpy_sg - prepare descriptors for a memcpy_sg transaction
+ * @dchan: DMA channel
+ * @dst_sg: Destination scatter list
+ * @dst_sg_len: Number of entries in destination scatter list
+ * @src_sg: Source scatter list
+ * @src_sg_len: Number of entries in source scatter list
+ * @flags: transfer ack flags
+ *
+ * Return: Async transaction descriptor on success and NULL on failure
+ */
+static struct dma_async_tx_descriptor *xilinx_cdma_prep_memcpy_sg(
+			struct dma_chan *dchan, struct scatterlist *dst_sg,
+			unsigned int dst_sg_len, struct scatterlist *src_sg,
+			unsigned int src_sg_len, unsigned long flags)
+{
+	struct xilinx_dma_chan *chan = to_xilinx_chan(dchan);
+	struct xilinx_dma_tx_descriptor *desc;
+	struct xilinx_cdma_tx_segment *segment, *prev = NULL;
+	struct xilinx_cdma_desc_hw *hw;
+	size_t len, dst_avail, src_avail;
+	dma_addr_t dma_dst, dma_src;
+
+	if (unlikely(dst_sg_len == 0 || src_sg_len == 0))
+		return NULL;
+
+	if (unlikely(!dst_sg  || !src_sg))
+		return NULL;
+
+	desc = xilinx_dma_alloc_tx_descriptor(chan);
+	if (!desc)
+		return NULL;
+
+	dma_async_tx_descriptor_init(&desc->async_tx, &chan->common);
+	desc->async_tx.tx_submit = xilinx_dma_tx_submit;
+
+	dst_avail = sg_dma_len(dst_sg);
+	src_avail = sg_dma_len(src_sg);
+	/*
+	 * loop until there is either no more source or no more destination
+	 * scatterlist entry
+	 */
+	while (true) {
+		len = min_t(size_t, src_avail, dst_avail);
+		len = min_t(size_t, len, chan->xdev->max_buffer_len);
+		if (len == 0)
+			goto fetch;
+
+		/* Allocate the link descriptor from DMA pool */
+		segment = xilinx_cdma_alloc_tx_segment(chan);
+		if (!segment)
+			goto error;
+
+		dma_dst = sg_dma_address(dst_sg) + sg_dma_len(dst_sg) -
+			dst_avail;
+		dma_src = sg_dma_address(src_sg) + sg_dma_len(src_sg) -
+			src_avail;
+		hw = &segment->hw;
+		hw->control = len;
+		hw->src_addr = dma_src;
+		hw->dest_addr = dma_dst;
+		if (chan->ext_addr) {
+			hw->src_addr_msb = upper_32_bits(dma_src);
+			hw->dest_addr_msb = upper_32_bits(dma_dst);
+		}
+
+		if (prev) {
+			prev->hw.next_desc = segment->phys;
+			if (chan->ext_addr)
+				prev->hw.next_desc_msb =
+					upper_32_bits(segment->phys);
+		}
+
+		prev = segment;
+		dst_avail -= len;
+		src_avail -= len;
+		list_add_tail(&segment->node, &desc->segments);
+
+fetch:
+		/* Fetch the next dst scatterlist entry */
+		if (dst_avail == 0) {
+			if (dst_sg_len == 0)
+				break;
+			dst_sg = sg_next(dst_sg);
+			if (dst_sg == NULL)
+				break;
+			dst_sg_len--;
+			dst_avail = sg_dma_len(dst_sg);
+		}
+		/* Fetch the next src scatterlist entry */
+		if (src_avail == 0) {
+			if (src_sg_len == 0)
+				break;
+			src_sg = sg_next(src_sg);
+			if (src_sg == NULL)
+				break;
+			src_sg_len--;
+			src_avail = sg_dma_len(src_sg);
+		}
+	}
+
+	if (list_empty(&desc->segments)) {
+		dev_err(chan->xdev->dev,
+			"%s: Zero-size SG transfer requested\n", __func__);
+		goto error;
+	}
+
+	/* Link the last hardware descriptor with the first. */
+	segment = list_first_entry(&desc->segments,
+				struct xilinx_cdma_tx_segment, node);
+	desc->async_tx.phys = segment->phys;
+	prev->hw.next_desc = segment->phys;
+
+	return &desc->async_tx;
+
+error:
+	xilinx_dma_free_tx_descriptor(chan, desc);
+	return NULL;
+}
+
 /**
  * xilinx_dma_prep_slave_sg - prepare descriptors for a DMA_SLAVE transaction
  * @dchan: DMA channel
@@ -2860,7 +2980,9 @@ static int xilinx_dma_chan_probe(struct xilinx_dma_device *xdev,
 	}
 
 	/* Request the interrupt */
-	chan->irq = irq_of_parse_and_map(node, chan->tdest);
+	chan->irq = of_irq_get(node, chan->tdest);
+	if (chan->irq < 0)
+		return dev_err_probe(xdev->dev, chan->irq, "failed to get irq\n");
 	err = request_irq(chan->irq, xdev->dma_config->irq_handler,
 			  IRQF_SHARED, "xilinx-dma-controller", chan);
 	if (err) {
@@ -2934,8 +3056,11 @@ static int xilinx_dma_child_probe(struct xilinx_dma_device *xdev,
 	if (xdev->dma_config->dmatype == XDMA_TYPE_AXIMCDMA && ret < 0)
 		dev_warn(xdev->dev, "missing dma-channels property\n");
 
-	for (i = 0; i < nr_channels; i++)
-		xilinx_dma_chan_probe(xdev, node);
+	for (i = 0; i < nr_channels; i++) {
+		ret = xilinx_dma_chan_probe(xdev, node);
+		if (ret)
+			return ret;
+	}
 
 	return 0;
 }
@@ -3115,7 +3240,9 @@ static int xilinx_dma_probe(struct platform_device *pdev)
 					  DMA_RESIDUE_GRANULARITY_SEGMENT;
 	} else if (xdev->dma_config->dmatype == XDMA_TYPE_CDMA) {
 		dma_cap_set(DMA_MEMCPY, xdev->common.cap_mask);
+		dma_cap_set(DMA_MEMCPY_SG, xdev->common.cap_mask);
 		xdev->common.device_prep_dma_memcpy = xilinx_cdma_prep_memcpy;
+		xdev->common.device_prep_dma_memcpy_sg = xilinx_cdma_prep_memcpy_sg;
 		/* Residue calculation is supported by only AXI DMA and CDMA */
 		xdev->common.residue_granularity =
 					  DMA_RESIDUE_GRANULARITY_SEGMENT;

include/linux/dma/xilinx_dpdma.h

-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __LINUX_DMA_XILINX_DPDMA_H
 #define __LINUX_DMA_XILINX_DPDMA_H
 

include/linux/dmaengine.h

@@ -50,6 +50,7 @@ enum dma_status {
  */
 enum dma_transaction_type {
 	DMA_MEMCPY,
+	DMA_MEMCPY_SG,
 	DMA_XOR,
 	DMA_PQ,
 	DMA_XOR_VAL,
@@ -887,6 +888,11 @@ struct dma_device {
 	struct dma_async_tx_descriptor *(*device_prep_dma_memcpy)(
 		struct dma_chan *chan, dma_addr_t dst, dma_addr_t src,
 		size_t len, unsigned long flags);
+	struct dma_async_tx_descriptor *(*device_prep_dma_memcpy_sg)(
+		struct dma_chan *chan,
+		struct scatterlist *dst_sg, unsigned int dst_nents,
+		struct scatterlist *src_sg, unsigned int src_nents,
+		unsigned long flags);
 	struct dma_async_tx_descriptor *(*device_prep_dma_xor)(
 		struct dma_chan *chan, dma_addr_t dst, dma_addr_t *src,
 		unsigned int src_cnt, size_t len, unsigned long flags);
@@ -1047,6 +1053,20 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_memcpy(
 						    len, flags);
 }
 
+static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_memcpy_sg(
+		struct dma_chan *chan,
+		struct scatterlist *dst_sg, unsigned int dst_nents,
+		struct scatterlist *src_sg, unsigned int src_nents,
+		unsigned long flags)
+{
+	if (!chan || !chan->device || !chan->device->device_prep_dma_memcpy_sg)
+		return NULL;
+
+	return chan->device->device_prep_dma_memcpy_sg(chan, dst_sg, dst_nents,
+						       src_sg, src_nents,
+						       flags);
+}
+
 static inline bool dmaengine_is_metadata_mode_supported(struct dma_chan *chan,
 		enum dma_desc_metadata_mode mode)
 {

include/uapi/linux/idxd.h

@@ -28,6 +28,7 @@ enum idxd_scmd_stat {
 	IDXD_SCMD_WQ_NONE_CONFIGURED = 0x800d0000,
 	IDXD_SCMD_WQ_NO_SIZE = 0x800e0000,
 	IDXD_SCMD_WQ_NO_PRIV = 0x800f0000,
+	IDXD_SCMD_WQ_IRQ_ERR = 0x80100000,
 };
 
 #define IDXD_SCMD_SOFTERR_MASK	0x80000000