Merge tag 'dmaengine-4.19-rc1' of git://git.infradead.org/users/vkoul/slave-dma

Pull DMAengine updates from Vinod Koul:
 "This round brings couple of framework changes, a new driver and usual
  driver updates:

   - new managed helper for dmaengine framework registration

   - split dmaengine pause capability to pause and resume and allow
     drivers to report that individually

   - update dma_request_chan_by_mask() to handle deferred probing

   - move imx-sdma to use virt-dma

   - new driver for Actions Semi Owl family S900 controller

   - minor updates to intel, renesas, mv_xor, pl330 etc"

* tag 'dmaengine-4.19-rc1' of git://git.infradead.org/users/vkoul/slave-dma: (46 commits)
  dmaengine: Add Actions Semi Owl family S900 DMA driver
  dt-bindings: dmaengine: Add binding for Actions Semi Owl SoCs
  dmaengine: sh: rcar-dmac: Should not stop the DMAC by rcar_dmac_sync_tcr()
  dmaengine: mic_x100_dma: use the new helper to simplify the code
  dmaengine: add a new helper dmaenginem_async_device_register
  dmaengine: imx-sdma: add memcpy interface
  dmaengine: imx-sdma: add SDMA_BD_MAX_CNT to replace '0xffff'
  dmaengine: dma_request_chan_by_mask() to handle deferred probing
  dmaengine: pl330: fix irq race with terminate_all
  dmaengine: Revert "dmaengine: mv_xor_v2: enable COMPILE_TEST"
  dmaengine: mv_xor_v2: use {lower,upper}_32_bits to configure HW descriptor address
  dmaengine: mv_xor_v2: enable COMPILE_TEST
  dmaengine: mv_xor_v2: move unmap to before callback
  dmaengine: mv_xor_v2: convert callback to helper function
  dmaengine: mv_xor_v2: kill the tasklets upon exit
  dmaengine: mv_xor_v2: explicitly freeup irq
  dmaengine: sh: rcar-dmac: Add dma_pause operation
  dmaengine: sh: rcar-dmac: add a new function to clear CHCR.DE with barrier
  dmaengine: idma64: Support dmaengine_terminate_sync()
  dmaengine: hsu: Support dmaengine_terminate_sync()
  ...

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

+* Actions Semi Owl SoCs DMA controller
+
+This binding follows the generic DMA bindings defined in dma.txt.
+
+Required properties:
+- compatible: Should be "actions,s900-dma".
+- reg: Should contain DMA registers location and length.
+- interrupts: Should contain 4 interrupts shared by all channel.
+- #dma-cells: Must be <1>. Used to represent the number of integer
+              cells in the dmas property of client device.
+- dma-channels: Physical channels supported.
+- dma-requests: Number of DMA request signals supported by the controller.
+                Refer to Documentation/devicetree/bindings/dma/dma.txt
+- clocks: Phandle and Specifier of the clock feeding the DMA controller.
+
+Example:
+
+Controller:
+                dma: dma-controller@e0260000 {
+                        compatible = "actions,s900-dma";
+                        reg = <0x0 0xe0260000 0x0 0x1000>;
+                        interrupts = <GIC_SPI 57 IRQ_TYPE_LEVEL_HIGH>,
+                                     <GIC_SPI 58 IRQ_TYPE_LEVEL_HIGH>,
+                                     <GIC_SPI 59 IRQ_TYPE_LEVEL_HIGH>,
+                                     <GIC_SPI 60 IRQ_TYPE_LEVEL_HIGH>;
+                        #dma-cells = <1>;
+                        dma-channels = <12>;
+                        dma-requests = <46>;
+                        clocks = <&clock CLK_DMAC>;
+                };
+
+Client:
+
+DMA clients connected to the Actions Semi Owl SoCs DMA controller must
+use the format described in the dma.txt file, using a two-cell specifier
+for each channel.
+
+The two cells in order are:
+1. A phandle pointing to the DMA controller.
+2. The channel id.
+
+uart5: serial@e012a000 {
+        ...
+        dma-names = "tx", "rx";
+        dmas = <&dma 26>, <&dma 27>;
+        ...
+};

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

@@ -29,6 +29,7 @@ Required Properties:
 		- "renesas,dmac-r8a77965" (R-Car M3-N)
 		- "renesas,dmac-r8a77970" (R-Car V3M)
 		- "renesas,dmac-r8a77980" (R-Car V3H)
+		- "renesas,dmac-r8a77990" (R-Car E3)
 		- "renesas,dmac-r8a77995" (R-Car D3)
 
 - reg: base address and length of the registers block for the DMAC

Documentation/devicetree/bindings/dma/xilinx/xilinx_dma.txt

@@ -66,6 +66,8 @@ Optional child node properties:
 Optional child node properties for VDMA:
 - xlnx,genlock-mode: Tells Genlock synchronization is
 	enabled/disabled in hardware.
+- xlnx,enable-vert-flip: Tells vertical flip is
+	enabled/disabled in hardware(S2MM path).
 Optional child node properties for AXI DMA:
 -dma-channels: Number of dma channels in child node.
 

Documentation/driver-model/devres.txt

@@ -240,6 +240,7 @@ CLOCK
   devm_of_clk_add_hw_provider()
 
 DMA
+  dmaenginem_async_device_register()
   dmam_alloc_coherent()
   dmam_alloc_attrs()
   dmam_declare_coherent_memory()

crypto/async_tx/async_pq.c

@@ -42,6 +42,8 @@ static struct page *pq_scribble_page;
 #define P(b, d) (b[d-2])
 #define Q(b, d) (b[d-1])
 
+#define MAX_DISKS 255
+
 /**
  * do_async_gen_syndrome - asynchronously calculate P and/or Q
  */
@@ -184,7 +186,7 @@ async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
 	struct dma_device *device = chan ? chan->device : NULL;
 	struct dmaengine_unmap_data *unmap = NULL;
 
-	BUG_ON(disks > 255 || !(P(blocks, disks) || Q(blocks, disks)));
+	BUG_ON(disks > MAX_DISKS || !(P(blocks, disks) || Q(blocks, disks)));
 
 	if (device)
 		unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOWAIT);
@@ -196,7 +198,7 @@ async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
 	    is_dma_pq_aligned(device, offset, 0, len)) {
 		struct dma_async_tx_descriptor *tx;
 		enum dma_ctrl_flags dma_flags = 0;
-		unsigned char coefs[src_cnt];
+		unsigned char coefs[MAX_DISKS];
 		int i, j;
 
 		/* run the p+q asynchronously */
@@ -299,11 +301,11 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
 	struct dma_chan *chan = pq_val_chan(submit, blocks, disks, len);
 	struct dma_device *device = chan ? chan->device : NULL;
 	struct dma_async_tx_descriptor *tx;
-	unsigned char coefs[disks-2];
+	unsigned char coefs[MAX_DISKS];
 	enum dma_ctrl_flags dma_flags = submit->cb_fn ? DMA_PREP_INTERRUPT : 0;
 	struct dmaengine_unmap_data *unmap = NULL;
 
-	BUG_ON(disks < 4);
+	BUG_ON(disks < 4 || disks > MAX_DISKS);
 
 	if (device)
 		unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOWAIT);

crypto/async_tx/raid6test.c

@@ -81,11 +81,13 @@ static void raid6_dual_recov(int disks, size_t bytes, int faila, int failb, stru
 			init_async_submit(&submit, 0, NULL, NULL, NULL, addr_conv);
 			tx = async_gen_syndrome(ptrs, 0, disks, bytes, &submit);
 		} else {
-			struct page *blocks[disks];
+			struct page *blocks[NDISKS];
 			struct page *dest;
 			int count = 0;
 			int i;
 
+			BUG_ON(disks > NDISKS);
+
 			/* data+Q failure.  Reconstruct data from P,
 			 * then rebuild syndrome
 			 */

drivers/dma/Kconfig

@@ -250,6 +250,7 @@ config IMX_SDMA
 	tristate "i.MX SDMA support"
 	depends on ARCH_MXC
 	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
 	help
 	  Support the i.MX SDMA engine. This engine is integrated into
 	  Freescale i.MX25/31/35/51/53/6 chips.
@@ -413,6 +414,14 @@ config NBPFAXI_DMA
 	help
 	  Support for "Type-AXI" NBPF DMA IPs from Renesas
 
+config OWL_DMA
+	tristate "Actions Semi Owl SoCs DMA support"
+	depends on ARCH_ACTIONS
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Enable support for the Actions Semi Owl SoCs DMA controller.
+
 config PCH_DMA
 	tristate "Intel EG20T PCH / LAPIS Semicon IOH(ML7213/ML7223/ML7831) DMA"
 	depends on PCI && (X86_32 || COMPILE_TEST)

drivers/dma/Makefile

@@ -52,6 +52,7 @@ obj-$(CONFIG_MV_XOR_V2) += mv_xor_v2.o
 obj-$(CONFIG_MXS_DMA) += mxs-dma.o
 obj-$(CONFIG_MX3_IPU) += ipu/
 obj-$(CONFIG_NBPFAXI_DMA) += nbpfaxi.o
+obj-$(CONFIG_OWL_DMA) += owl-dma.o
 obj-$(CONFIG_PCH_DMA) += pch_dma.o
 obj-$(CONFIG_PL330_DMA) += pl330.o
 obj-$(CONFIG_PPC_BESTCOMM) += bestcomm/

drivers/dma/dmaengine.c

@@ -500,12 +500,8 @@ int dma_get_slave_caps(struct dma_chan *chan, struct dma_slave_caps *caps)
 	caps->max_burst = device->max_burst;
 	caps->residue_granularity = device->residue_granularity;
 	caps->descriptor_reuse = device->descriptor_reuse;
-
-	/*
-	 * Some devices implement only pause (e.g. to get residuum) but no
-	 * resume. However cmd_pause is advertised as pause AND resume.
-	 */
-	caps->cmd_pause = !!(device->device_pause && device->device_resume);
+	caps->cmd_pause = !!device->device_pause;
+	caps->cmd_resume = !!device->device_resume;
 	caps->cmd_terminate = !!device->device_terminate_all;
 
 	return 0;
@@ -774,8 +770,14 @@ struct dma_chan *dma_request_chan_by_mask(const dma_cap_mask_t *mask)
 		return ERR_PTR(-ENODEV);
 
 	chan = __dma_request_channel(mask, NULL, NULL);
-	if (!chan)
-		chan = ERR_PTR(-ENODEV);
+	if (!chan) {
+		mutex_lock(&dma_list_mutex);
+		if (list_empty(&dma_device_list))
+			chan = ERR_PTR(-EPROBE_DEFER);
+		else
+			chan = ERR_PTR(-ENODEV);
+		mutex_unlock(&dma_list_mutex);
+	}
 
 	return chan;
 }
@@ -1139,6 +1141,41 @@ void dma_async_device_unregister(struct dma_device *device)
 }
 EXPORT_SYMBOL(dma_async_device_unregister);
 
+static void dmam_device_release(struct device *dev, void *res)
+{
+	struct dma_device *device;
+
+	device = *(struct dma_device **)res;
+	dma_async_device_unregister(device);
+}
+
+/**
+ * dmaenginem_async_device_register - registers DMA devices found
+ * @device: &dma_device
+ *
+ * The operation is managed and will be undone on driver detach.
+ */
+int dmaenginem_async_device_register(struct dma_device *device)
+{
+	void *p;
+	int ret;
+
+	p = devres_alloc(dmam_device_release, sizeof(void *), GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	ret = dma_async_device_register(device);
+	if (!ret) {
+		*(struct dma_device **)p = device;
+		devres_add(device->dev, p);
+	} else {
+		devres_free(p);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(dmaenginem_async_device_register);
+
 struct dmaengine_unmap_pool {
 	struct kmem_cache *cache;
 	const char *name;

drivers/dma/hsu/hsu.c

@@ -413,6 +413,13 @@ static void hsu_dma_free_chan_resources(struct dma_chan *chan)
 	vchan_free_chan_resources(to_virt_chan(chan));
 }
 
+static void hsu_dma_synchronize(struct dma_chan *chan)
+{
+	struct hsu_dma_chan *hsuc = to_hsu_dma_chan(chan);
+
+	vchan_synchronize(&hsuc->vchan);
+}
+
 int hsu_dma_probe(struct hsu_dma_chip *chip)
 {
 	struct hsu_dma *hsu;
@@ -459,6 +466,7 @@ int hsu_dma_probe(struct hsu_dma_chip *chip)
 	hsu->dma.device_pause = hsu_dma_pause;
 	hsu->dma.device_resume = hsu_dma_resume;
 	hsu->dma.device_terminate_all = hsu_dma_terminate_all;
+	hsu->dma.device_synchronize = hsu_dma_synchronize;
 
 	hsu->dma.src_addr_widths = HSU_DMA_BUSWIDTHS;
 	hsu->dma.dst_addr_widths = HSU_DMA_BUSWIDTHS;

drivers/dma/idma64.c

@@ -496,6 +496,13 @@ static int idma64_terminate_all(struct dma_chan *chan)
 	return 0;
 }
 
+static void idma64_synchronize(struct dma_chan *chan)
+{
+	struct idma64_chan *idma64c = to_idma64_chan(chan);
+
+	vchan_synchronize(&idma64c->vchan);
+}
+
 static int idma64_alloc_chan_resources(struct dma_chan *chan)
 {
 	struct idma64_chan *idma64c = to_idma64_chan(chan);
@@ -583,6 +590,7 @@ static int idma64_probe(struct idma64_chip *chip)
 	idma64->dma.device_pause = idma64_pause;
 	idma64->dma.device_resume = idma64_resume;
 	idma64->dma.device_terminate_all = idma64_terminate_all;
+	idma64->dma.device_synchronize = idma64_synchronize;
 
 	idma64->dma.src_addr_widths = IDMA64_BUSWIDTHS;
 	idma64->dma.dst_addr_widths = IDMA64_BUSWIDTHS;

drivers/dma/ioat/dma.c

@@ -688,6 +688,12 @@ static void ioat_restart_channel(struct ioatdma_chan *ioat_chan)
 {
 	u64 phys_complete;
 
+	/* set the completion address register again */
+	writel(lower_32_bits(ioat_chan->completion_dma),
+	       ioat_chan->reg_base + IOAT_CHANCMP_OFFSET_LOW);
+	writel(upper_32_bits(ioat_chan->completion_dma),
+	       ioat_chan->reg_base + IOAT_CHANCMP_OFFSET_HIGH);
+
 	ioat_quiesce(ioat_chan, 0);
 	if (ioat_cleanup_preamble(ioat_chan, &phys_complete))
 		__cleanup(ioat_chan, phys_complete);

drivers/dma/mic_x100_dma.c

@@ -470,11 +470,6 @@ static void mic_dma_chan_destroy(struct mic_dma_chan *ch)
 	mic_dma_chan_mask_intr(ch);
 }
 
-static void mic_dma_unregister_dma_device(struct mic_dma_device *mic_dma_dev)
-{
-	dma_async_device_unregister(&mic_dma_dev->dma_dev);
-}
-
 static int mic_dma_setup_irq(struct mic_dma_chan *ch)
 {
 	ch->cookie =
@@ -630,7 +625,7 @@ static int mic_dma_register_dma_device(struct mic_dma_device *mic_dma_dev,
 		list_add_tail(&mic_dma_dev->mic_ch[i].api_ch.device_node,
 			      &mic_dma_dev->dma_dev.channels);
 	}
-	return dma_async_device_register(&mic_dma_dev->dma_dev);
+	return dmaenginem_async_device_register(&mic_dma_dev->dma_dev);
 }
 
 /*
@@ -678,7 +673,6 @@ static struct mic_dma_device *mic_dma_dev_reg(struct mbus_device *mbdev,
 
 static void mic_dma_dev_unreg(struct mic_dma_device *mic_dma_dev)
 {
-	mic_dma_unregister_dma_device(mic_dma_dev);
 	mic_dma_uninit(mic_dma_dev);
 	kfree(mic_dma_dev);
 }

drivers/dma/mv_xor_v2.c

@@ -174,6 +174,7 @@ struct mv_xor_v2_device {
 	int desc_size;
 	unsigned int npendings;
 	unsigned int hw_queue_idx;
+	struct msi_desc *msi_desc;
 };
 
 /**
@@ -588,11 +589,9 @@ static void mv_xor_v2_tasklet(unsigned long data)
 			 */
 			dma_cookie_complete(&next_pending_sw_desc->async_tx);
 
-			if (next_pending_sw_desc->async_tx.callback)
-				next_pending_sw_desc->async_tx.callback(
-				next_pending_sw_desc->async_tx.callback_param);
-
 			dma_descriptor_unmap(&next_pending_sw_desc->async_tx);
+			dmaengine_desc_get_callback_invoke(
+					&next_pending_sw_desc->async_tx, NULL);
 		}
 
 		dma_run_dependencies(&next_pending_sw_desc->async_tx);
@@ -643,9 +642,9 @@ static int mv_xor_v2_descq_init(struct mv_xor_v2_device *xor_dev)
 	       xor_dev->dma_base + MV_XOR_V2_DMA_DESQ_SIZE_OFF);
 
 	/* write the DESQ address to the DMA enngine*/
-	writel(xor_dev->hw_desq & 0xFFFFFFFF,
+	writel(lower_32_bits(xor_dev->hw_desq),
 	       xor_dev->dma_base + MV_XOR_V2_DMA_DESQ_BALR_OFF);
-	writel((xor_dev->hw_desq & 0xFFFF00000000) >> 32,
+	writel(upper_32_bits(xor_dev->hw_desq),
 	       xor_dev->dma_base + MV_XOR_V2_DMA_DESQ_BAHR_OFF);
 
 	/*
@@ -780,6 +779,7 @@ static int mv_xor_v2_probe(struct platform_device *pdev)
 	msi_desc = first_msi_entry(&pdev->dev);
 	if (!msi_desc)
 		goto free_msi_irqs;
+	xor_dev->msi_desc = msi_desc;
 
 	ret = devm_request_irq(&pdev->dev, msi_desc->irq,
 			       mv_xor_v2_interrupt_handler, 0,
@@ -897,8 +897,12 @@ static int mv_xor_v2_remove(struct platform_device *pdev)
 			  xor_dev->desc_size * MV_XOR_V2_DESC_NUM,
 			  xor_dev->hw_desq_virt, xor_dev->hw_desq);
 
+	devm_free_irq(&pdev->dev, xor_dev->msi_desc->irq, xor_dev);
+
 	platform_msi_domain_free_irqs(&pdev->dev);
 
+	tasklet_kill(&xor_dev->irq_tasklet);
+
 	clk_disable_unprepare(xor_dev->clk);
 
 	return 0;

drivers/dma/nbpfaxi.c

@@ -479,6 +479,7 @@ static size_t nbpf_xfer_size(struct nbpf_device *nbpf,
 
 	default:
 		pr_warn("%s(): invalid bus width %u\n", __func__, width);
+		/* fall through */
 	case DMA_SLAVE_BUSWIDTH_1_BYTE:
 		size = burst;
 	}

drivers/dma/pl330.c

@@ -1046,13 +1046,16 @@ static bool _start(struct pl330_thread *thrd)
 
 		if (_state(thrd) == PL330_STATE_KILLING)
 			UNTIL(thrd, PL330_STATE_STOPPED)
+		/* fall through */
 
 	case PL330_STATE_FAULTING:
 		_stop(thrd);
+		/* fall through */
 
 	case PL330_STATE_KILLING:
 	case PL330_STATE_COMPLETING:
 		UNTIL(thrd, PL330_STATE_STOPPED)
+		/* fall through */
 
 	case PL330_STATE_STOPPED:
 		return _trigger(thrd);
@@ -1779,8 +1782,6 @@ static inline void _free_event(struct pl330_thread *thrd, int ev)
 
 static void pl330_release_channel(struct pl330_thread *thrd)
 {
-	struct pl330_dmac *pl330;
-
 	if (!thrd || thrd->free)
 		return;
 
@@ -1789,8 +1790,6 @@ static void pl330_release_channel(struct pl330_thread *thrd)
 	dma_pl330_rqcb(thrd->req[1 - thrd->lstenq].desc, PL330_ERR_ABORT);
 	dma_pl330_rqcb(thrd->req[thrd->lstenq].desc, PL330_ERR_ABORT);
 
-	pl330 = thrd->dmac;
-
 	_free_event(thrd, thrd->ev);
 	thrd->free = true;
 }
@@ -2257,13 +2256,14 @@ static int pl330_terminate_all(struct dma_chan *chan)
 
 	pm_runtime_get_sync(pl330->ddma.dev);
 	spin_lock_irqsave(&pch->lock, flags);
+
 	spin_lock(&pl330->lock);
 	_stop(pch->thread);
-	spin_unlock(&pl330->lock);
-
 	pch->thread->req[0].desc = NULL;
 	pch->thread->req[1].desc = NULL;
 	pch->thread->req_running = -1;
+	spin_unlock(&pl330->lock);
+
 	power_down = pch->active;
 	pch->active = false;
 

drivers/dma/sh/rcar-dmac.c

+// SPDX-License-Identifier: GPL-2.0
 /*
  * Renesas R-Car Gen2 DMA Controller Driver
  *
  * Copyright (C) 2014 Renesas Electronics Inc.
  *
  * Author: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
- *
- * This is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
  */
 
 #include <linux/delay.h>
@@ -431,7 +428,8 @@ static void rcar_dmac_chan_start_xfer(struct rcar_dmac_chan *chan)
 		chcr |= RCAR_DMACHCR_DPM_DISABLED | RCAR_DMACHCR_IE;
 	}
 
-	rcar_dmac_chan_write(chan, RCAR_DMACHCR, chcr | RCAR_DMACHCR_DE);
+	rcar_dmac_chan_write(chan, RCAR_DMACHCR,
+			     chcr | RCAR_DMACHCR_DE | RCAR_DMACHCR_CAIE);
 }
 
 static int rcar_dmac_init(struct rcar_dmac *dmac)
@@ -761,21 +759,15 @@ static void rcar_dmac_chcr_de_barrier(struct rcar_dmac_chan *chan)
 	dev_err(chan->chan.device->dev, "CHCR DE check error\n");
 }
 
-static void rcar_dmac_sync_tcr(struct rcar_dmac_chan *chan)
+static void rcar_dmac_clear_chcr_de(struct rcar_dmac_chan *chan)
 {
 	u32 chcr = rcar_dmac_chan_read(chan, RCAR_DMACHCR);
 
-	if (!(chcr & RCAR_DMACHCR_DE))
-		return;
-
 	/* set DE=0 and flush remaining data */
 	rcar_dmac_chan_write(chan, RCAR_DMACHCR, (chcr & ~RCAR_DMACHCR_DE));
 
 	/* make sure all remaining data was flushed */
 	rcar_dmac_chcr_de_barrier(chan);
-
-	/* back DE */
-	rcar_dmac_chan_write(chan, RCAR_DMACHCR, chcr);
 }
 
 static void rcar_dmac_chan_halt(struct rcar_dmac_chan *chan)
@@ -783,7 +775,8 @@ static void rcar_dmac_chan_halt(struct rcar_dmac_chan *chan)
 	u32 chcr = rcar_dmac_chan_read(chan, RCAR_DMACHCR);
 
 	chcr &= ~(RCAR_DMACHCR_DSE | RCAR_DMACHCR_DSIE | RCAR_DMACHCR_IE |
-		  RCAR_DMACHCR_TE | RCAR_DMACHCR_DE);
+		  RCAR_DMACHCR_TE | RCAR_DMACHCR_DE |
+		  RCAR_DMACHCR_CAE | RCAR_DMACHCR_CAIE);
 	rcar_dmac_chan_write(chan, RCAR_DMACHCR, chcr);
 	rcar_dmac_chcr_de_barrier(chan);
 }
@@ -812,12 +805,7 @@ static void rcar_dmac_chan_reinit(struct rcar_dmac_chan *chan)
 	}
 }
 
-static void rcar_dmac_stop(struct rcar_dmac *dmac)
-{
-	rcar_dmac_write(dmac, RCAR_DMAOR, 0);
-}
-
-static void rcar_dmac_abort(struct rcar_dmac *dmac)
+static void rcar_dmac_stop_all_chan(struct rcar_dmac *dmac)
 {
 	unsigned int i;
 
@@ -826,14 +814,24 @@ static void rcar_dmac_abort(struct rcar_dmac *dmac)
 		struct rcar_dmac_chan *chan = &dmac->channels[i];
 
 		/* Stop and reinitialize the channel. */
-		spin_lock(&chan->lock);
+		spin_lock_irq(&chan->lock);
 		rcar_dmac_chan_halt(chan);
-		spin_unlock(&chan->lock);
-
-		rcar_dmac_chan_reinit(chan);
+		spin_unlock_irq(&chan->lock);
 	}
 }
 
+static int rcar_dmac_chan_pause(struct dma_chan *chan)
+{
+	unsigned long flags;
+	struct rcar_dmac_chan *rchan = to_rcar_dmac_chan(chan);
+
+	spin_lock_irqsave(&rchan->lock, flags);
+	rcar_dmac_clear_chcr_de(rchan);
+	spin_unlock_irqrestore(&rchan->lock, flags);
+
+	return 0;
+}
+
 /* -----------------------------------------------------------------------------
  * Descriptors preparation
  */
@@ -1355,9 +1353,6 @@ static unsigned int rcar_dmac_chan_get_residue(struct rcar_dmac_chan *chan,
 		residue += chunk->size;
 	}
 
-	if (desc->direction == DMA_DEV_TO_MEM)
-		rcar_dmac_sync_tcr(chan);
-
 	/* Add the residue for the current chunk. */
 	residue += rcar_dmac_chan_read(chan, RCAR_DMATCRB) << desc->xfer_shift;
 
@@ -1522,11 +1517,26 @@ static irqreturn_t rcar_dmac_isr_channel(int irq, void *dev)
 	u32 mask = RCAR_DMACHCR_DSE | RCAR_DMACHCR_TE;
 	struct rcar_dmac_chan *chan = dev;
 	irqreturn_t ret = IRQ_NONE;
+	bool reinit = false;
 	u32 chcr;
 
 	spin_lock(&chan->lock);
 
 	chcr = rcar_dmac_chan_read(chan, RCAR_DMACHCR);
+	if (chcr & RCAR_DMACHCR_CAE) {
+		struct rcar_dmac *dmac = to_rcar_dmac(chan->chan.device);
+
+		/*
+		 * We don't need to call rcar_dmac_chan_halt()
+		 * because channel is already stopped in error case.
+		 * We need to clear register and check DE bit as recovery.
+		 */
+		rcar_dmac_write(dmac, RCAR_DMACHCLR, 1 << chan->index);
+		rcar_dmac_chcr_de_barrier(chan);
+		reinit = true;
+		goto spin_lock_end;
+	}
+
 	if (chcr & RCAR_DMACHCR_TE)
 		mask |= RCAR_DMACHCR_DE;
 	rcar_dmac_chan_write(chan, RCAR_DMACHCR, chcr & ~mask);
@@ -1539,8 +1549,16 @@ static irqreturn_t rcar_dmac_isr_channel(int irq, void *dev)
 	if (chcr & RCAR_DMACHCR_TE)
 		ret |= rcar_dmac_isr_transfer_end(chan);
 
+spin_lock_end:
 	spin_unlock(&chan->lock);
 
+	if (reinit) {
+		dev_err(chan->chan.device->dev, "Channel Address Error\n");
+
+		rcar_dmac_chan_reinit(chan);
+		ret = IRQ_HANDLED;
+	}
+
 	return ret;
 }
 
@@ -1597,24 +1615,6 @@ static irqreturn_t rcar_dmac_isr_channel_thread(int irq, void *dev)
 	return IRQ_HANDLED;
 }
 
-static irqreturn_t rcar_dmac_isr_error(int irq, void *data)
-{
-	struct rcar_dmac *dmac = data;
-
-	if (!(rcar_dmac_read(dmac, RCAR_DMAOR) & RCAR_DMAOR_AE))
-		return IRQ_NONE;
-
-	/*
-	 * An unrecoverable error occurred on an unknown channel. Halt the DMAC,
-	 * abort transfers on all channels, and reinitialize the DMAC.
-	 */
-	rcar_dmac_stop(dmac);
-	rcar_dmac_abort(dmac);
-	rcar_dmac_init(dmac);
-
-	return IRQ_HANDLED;
-}
-
 /* -----------------------------------------------------------------------------
  * OF xlate and channel filter
  */
@@ -1784,8 +1784,6 @@ static int rcar_dmac_probe(struct platform_device *pdev)
 	struct rcar_dmac *dmac;
 	struct resource *mem;
 	unsigned int i;
-	char *irqname;
-	int irq;
 	int ret;
 
 	dmac = devm_kzalloc(&pdev->dev, sizeof(*dmac), GFP_KERNEL);
@@ -1824,17 +1822,6 @@ static int rcar_dmac_probe(struct platform_device *pdev)
 	if (IS_ERR(dmac->iomem))
 		return PTR_ERR(dmac->iomem);
 
-	irq = platform_get_irq_byname(pdev, "error");
-	if (irq < 0) {
-		dev_err(&pdev->dev, "no error IRQ specified\n");
-		return -ENODEV;
-	}
-
-	irqname = devm_kasprintf(dmac->dev, GFP_KERNEL, "%s:error",
-				 dev_name(dmac->dev));
-	if (!irqname)
-		return -ENOMEM;
-
 	/* Enable runtime PM and initialize the device. */
 	pm_runtime_enable(&pdev->dev);
 	ret = pm_runtime_get_sync(&pdev->dev);
@@ -1871,6 +1858,7 @@ static int rcar_dmac_probe(struct platform_device *pdev)
 	engine->device_prep_slave_sg		= rcar_dmac_prep_slave_sg;
 	engine->device_prep_dma_cyclic		= rcar_dmac_prep_dma_cyclic;
 	engine->device_config			= rcar_dmac_device_config;
+	engine->device_pause			= rcar_dmac_chan_pause;
 	engine->device_terminate_all		= rcar_dmac_chan_terminate_all;
 	engine->device_tx_status		= rcar_dmac_tx_status;
 	engine->device_issue_pending		= rcar_dmac_issue_pending;
@@ -1885,14 +1873,6 @@ static int rcar_dmac_probe(struct platform_device *pdev)
 			goto error;
 	}
 
-	ret = devm_request_irq(&pdev->dev, irq, rcar_dmac_isr_error, 0,
-			       irqname, dmac);
-	if (ret) {
-		dev_err(&pdev->dev, "failed to request IRQ %u (%d)\n",
-			irq, ret);
-		return ret;
-	}
-
 	/* Register the DMAC as a DMA provider for DT. */
 	ret = of_dma_controller_register(pdev->dev.of_node, rcar_dmac_of_xlate,
 					 NULL);
@@ -1932,7 +1912,7 @@ static void rcar_dmac_shutdown(struct platform_device *pdev)
 {
 	struct rcar_dmac *dmac = platform_get_drvdata(pdev);
 
-	rcar_dmac_stop(dmac);
+	rcar_dmac_stop_all_chan(dmac);
 }
 
 static const struct of_device_id rcar_dmac_of_ids[] = {

drivers/dma/ste_dma40.c

@@ -555,6 +555,7 @@ struct d40_gen_dmac {
  * @reg_val_backup_v4: Backup of registers that only exits on dma40 v3 and
  * later
  * @reg_val_backup_chan: Backup data for standard channel parameter registers.
+ * @regs_interrupt: Scratch space for registers during interrupt.
  * @gcc_pwr_off_mask: Mask to maintain the channels that can be turned off.
  * @gen_dmac: the struct for generic registers values to represent u8500/8540
  * DMA controller
@@ -592,6 +593,7 @@ struct d40_base {
 	u32				  reg_val_backup[BACKUP_REGS_SZ];
 	u32				  reg_val_backup_v4[BACKUP_REGS_SZ_MAX];
 	u32				 *reg_val_backup_chan;
+	u32				 *regs_interrupt;
 	u16				  gcc_pwr_off_mask;
 	struct d40_gen_dmac		  gen_dmac;
 };
@@ -1637,7 +1639,7 @@ static irqreturn_t d40_handle_interrupt(int irq, void *data)
 	struct d40_chan *d40c;
 	unsigned long flags;
 	struct d40_base *base = data;
-	u32 regs[base->gen_dmac.il_size];
+	u32 *regs = base->regs_interrupt;
 	struct d40_interrupt_lookup *il = base->gen_dmac.il;
 	u32 il_size = base->gen_dmac.il_size;
 
@@ -3258,13 +3260,22 @@ static struct d40_base * __init d40_hw_detect_init(struct platform_device *pdev)
 	if (!base->lcla_pool.alloc_map)
 		goto free_backup_chan;
 
+	base->regs_interrupt = kmalloc_array(base->gen_dmac.il_size,
+					     sizeof(*base->regs_interrupt),
+					     GFP_KERNEL);
+	if (!base->regs_interrupt)
+		goto free_map;
+
 	base->desc_slab = kmem_cache_create(D40_NAME, sizeof(struct d40_desc),
 					    0, SLAB_HWCACHE_ALIGN,
 					    NULL);
 	if (base->desc_slab == NULL)
-		goto free_map;
+		goto free_regs;
+
 
 	return base;
+ free_regs:
+	kfree(base->regs_interrupt);
  free_map:
 	kfree(base->lcla_pool.alloc_map);
  free_backup_chan:

drivers/dma/stm32-dma.c

@@ -594,7 +594,7 @@ static void stm32_dma_start_transfer(struct stm32_dma_chan *chan)
 
 	chan->busy = true;
 
-	dev_dbg(chan2dev(chan), "vchan %p: started\n", &chan->vchan);
+	dev_dbg(chan2dev(chan), "vchan %pK: started\n", &chan->vchan);
 }
 
 static void stm32_dma_configure_next_sg(struct stm32_dma_chan *chan)
@@ -693,7 +693,7 @@ static void stm32_dma_issue_pending(struct dma_chan *c)
 
 	spin_lock_irqsave(&chan->vchan.lock, flags);
 	if (vchan_issue_pending(&chan->vchan) && !chan->desc && !chan->busy) {
-		dev_dbg(chan2dev(chan), "vchan %p: issued\n", &chan->vchan);
+		dev_dbg(chan2dev(chan), "vchan %pK: issued\n", &chan->vchan);
 		stm32_dma_start_transfer(chan);
 
 	}

drivers/dma/stm32-mdma.c

@@ -1170,7 +1170,7 @@ static void stm32_mdma_start_transfer(struct stm32_mdma_chan *chan)
 
 	chan->busy = true;
 
-	dev_dbg(chan2dev(chan), "vchan %p: started\n", &chan->vchan);
+	dev_dbg(chan2dev(chan), "vchan %pK: started\n", &chan->vchan);
 }
 
 static void stm32_mdma_issue_pending(struct dma_chan *c)
@@ -1183,7 +1183,7 @@ static void stm32_mdma_issue_pending(struct dma_chan *c)
 	if (!vchan_issue_pending(&chan->vchan))
 		goto end;
 
-	dev_dbg(chan2dev(chan), "vchan %p: issued\n", &chan->vchan);
+	dev_dbg(chan2dev(chan), "vchan %pK: issued\n", &chan->vchan);
 
 	if (!chan->desc && !chan->busy)
 		stm32_mdma_start_transfer(chan);
@@ -1203,7 +1203,7 @@ static int stm32_mdma_pause(struct dma_chan *c)
 	spin_unlock_irqrestore(&chan->vchan.lock, flags);
 
 	if (!ret)
-		dev_dbg(chan2dev(chan), "vchan %p: pause\n", &chan->vchan);
+		dev_dbg(chan2dev(chan), "vchan %pK: pause\n", &chan->vchan);
 
 	return ret;
 }
@@ -1240,7 +1240,7 @@ static int stm32_mdma_resume(struct dma_chan *c)
 
 	spin_unlock_irqrestore(&chan->vchan.lock, flags);
 
-	dev_dbg(chan2dev(chan), "vchan %p: resume\n", &chan->vchan);
+	dev_dbg(chan2dev(chan), "vchan %pK: resume\n", &chan->vchan);
 
 	return 0;
 }

drivers/dma/xilinx/xilinx_dma.c

@@ -115,6 +115,9 @@
 #define XILINX_VDMA_REG_START_ADDRESS(n)	(0x000c + 4 * (n))
 #define XILINX_VDMA_REG_START_ADDRESS_64(n)	(0x000c + 8 * (n))
 
+#define XILINX_VDMA_REG_ENABLE_VERTICAL_FLIP	0x00ec
+#define XILINX_VDMA_ENABLE_VERTICAL_FLIP	BIT(0)
+
 /* HW specific definitions */
 #define XILINX_DMA_MAX_CHANS_PER_DEVICE	0x20
 
@@ -340,6 +343,7 @@ struct xilinx_dma_tx_descriptor {
  * @start_transfer: Differentiate b/w DMA IP's transfer
  * @stop_transfer: Differentiate b/w DMA IP's quiesce
  * @tdest: TDEST value for mcdma
+ * @has_vflip: S2MM vertical flip
  */
 struct xilinx_dma_chan {
 	struct xilinx_dma_device *xdev;
@@ -376,6 +380,7 @@ struct xilinx_dma_chan {
 	void (*start_transfer)(struct xilinx_dma_chan *chan);
 	int (*stop_transfer)(struct xilinx_dma_chan *chan);
 	u16 tdest;
+	bool has_vflip;
 };
 
 /**
@@ -1092,6 +1097,14 @@ static void xilinx_vdma_start_transfer(struct xilinx_dma_chan *chan)
 				desc->async_tx.phys);
 
 	/* Configure the hardware using info in the config structure */
+	if (chan->has_vflip) {
+		reg = dma_read(chan, XILINX_VDMA_REG_ENABLE_VERTICAL_FLIP);
+		reg &= ~XILINX_VDMA_ENABLE_VERTICAL_FLIP;
+		reg |= config->vflip_en;
+		dma_write(chan, XILINX_VDMA_REG_ENABLE_VERTICAL_FLIP,
+			  reg);
+	}
+
 	reg = dma_ctrl_read(chan, XILINX_DMA_REG_DMACR);
 
 	if (config->frm_cnt_en)
@@ -2105,6 +2118,8 @@ int xilinx_vdma_channel_set_config(struct dma_chan *dchan,
 	}
 
 	chan->config.frm_cnt_en = cfg->frm_cnt_en;
+	chan->config.vflip_en = cfg->vflip_en;
+
 	if (cfg->park)
 		chan->config.park_frm = cfg->park_frm;
 	else
@@ -2428,6 +2443,13 @@ static int xilinx_dma_chan_probe(struct xilinx_dma_device *xdev,
 		chan->direction = DMA_DEV_TO_MEM;
 		chan->id = chan_id;
 		chan->tdest = chan_id - xdev->nr_channels;
+		chan->has_vflip = of_property_read_bool(node,
+					"xlnx,enable-vert-flip");
+		if (chan->has_vflip) {
+			chan->config.vflip_en = dma_read(chan,
+				XILINX_VDMA_REG_ENABLE_VERTICAL_FLIP) &
+				XILINX_VDMA_ENABLE_VERTICAL_FLIP;
+		}
 
 		chan->ctrl_offset = XILINX_DMA_S2MM_CTRL_OFFSET;
 		if (xdev->dma_config->dmatype == XDMA_TYPE_VDMA) {

include/linux/dma/xilinx_dma.h

@@ -27,6 +27,7 @@
  * @delay: Delay counter
  * @reset: Reset Channel
  * @ext_fsync: External Frame Sync source
+ * @vflip_en:  Vertical Flip enable
  */
 struct xilinx_vdma_config {
 	int frm_dly;
@@ -39,6 +40,7 @@ struct xilinx_vdma_config {
 	int delay;
 	int reset;
 	int ext_fsync;
+	bool vflip_en;
 };
 
 int xilinx_vdma_channel_set_config(struct dma_chan *dchan,

include/linux/dmaengine.h

@@ -415,7 +415,9 @@ enum dma_residue_granularity {
  *	each type, the dma controller should set BIT(<TYPE>) and same
  *	should be checked by controller as well
  * @max_burst: max burst capability per-transfer
- * @cmd_pause: true, if pause and thereby resume is supported
+ * @cmd_pause: true, if pause is supported (i.e. for reading residue or
+ *	       for resume later)
+ * @cmd_resume: true, if resume is supported
  * @cmd_terminate: true, if terminate cmd is supported
  * @residue_granularity: granularity of the reported transfer residue
  * @descriptor_reuse: if a descriptor can be reused by client and
@@ -427,6 +429,7 @@ struct dma_slave_caps {
 	u32 directions;
 	u32 max_burst;
 	bool cmd_pause;
+	bool cmd_resume;
 	bool cmd_terminate;
 	enum dma_residue_granularity residue_granularity;
 	bool descriptor_reuse;
@@ -1403,6 +1406,7 @@ static inline int dmaengine_desc_free(struct dma_async_tx_descriptor *desc)
 /* --- DMA device --- */
 
 int dma_async_device_register(struct dma_device *device);
+int dmaenginem_async_device_register(struct dma_device *device);
 void dma_async_device_unregister(struct dma_device *device);
 void dma_run_dependencies(struct dma_async_tx_descriptor *tx);
 struct dma_chan *dma_get_slave_channel(struct dma_chan *chan);

sound/soc/soc-generic-dmaengine-pcm.c

@@ -147,7 +147,7 @@ static int dmaengine_pcm_set_runtime_hwparams(struct snd_pcm_substream *substrea
 
 	ret = dma_get_slave_caps(chan, &dma_caps);
 	if (ret == 0) {
-		if (dma_caps.cmd_pause)
+		if (dma_caps.cmd_pause && dma_caps.cmd_resume)
 			hw.info |= SNDRV_PCM_INFO_PAUSE | SNDRV_PCM_INFO_RESUME;
 		if (dma_caps.residue_granularity <= DMA_RESIDUE_GRANULARITY_SEGMENT)
 			hw.info |= SNDRV_PCM_INFO_BATCH;