Merge tag 'dmaengine-4.13-rc1' of git://git.infradead.org/users/vkoul/slave-dma

Pull dmaengine updates from Vinod Koul:

 - removal of AVR32 support in dw driver as AVR32 is gone

 - new driver for Broadcom stream buffer accelerator (SBA) RAID driver

 - add support for Faraday Technology FTDMAC020 in amba-pl08x driver

 - IOMMU support in pl330 driver

 - updates to bunch of drivers

* tag 'dmaengine-4.13-rc1' of git://git.infradead.org/users/vkoul/slave-dma: (36 commits)
  dmaengine: qcom_hidma: correct API violation for submit
  dmaengine: zynqmp_dma: Remove max len check in zynqmp_dma_prep_memcpy
  dmaengine: tegra-apb: Really fix runtime-pm usage
  dmaengine: fsl_raid: make of_device_ids const.
  dmaengine: qcom_hidma: allow ACPI/DT parameters to be overridden
  dmaengine: fsldma: set BWC, DAHTS and SAHTS values correctly
  dmaengine: Kconfig: Simplify the help text for MXS_DMA
  dmaengine: pl330: Delete unused functions
  dmaengine: Replace WARN_TAINT_ONCE() with pr_warn_once()
  dmaengine: Kconfig: Extend the dependency for MXS_DMA
  dmaengine: mxs: Use %zu for printing a size_t variable
  dmaengine: ste_dma40: Cleanup scatterlist layering violations
  dmaengine: imx-dma: cleanup scatterlist layering violations
  dmaengine: use proper name for the R-Car SoC
  dmaengine: imx-sdma: Fix compilation warning.
  dmaengine: imx-sdma: Handle return value of clk_prepare_enable
  dmaengine: pl330: Add IOMMU support to slave tranfers
  dmaengine: DW DMAC: Handle return value of clk_prepare_enable
  dmaengine: pl08x: use GENMASK() to create bitmasks
  dmaengine: pl08x: Add support for Faraday Technology FTDMAC020
  ...

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

@@ -3,6 +3,11 @@
 Required properties:
 - compatible: "arm,pl080", "arm,primecell";
 	      "arm,pl081", "arm,primecell";
+	      "faraday,ftdmac020", "arm,primecell"
+- arm,primecell-periphid: on the FTDMAC020 the primecell ID is not hard-coded
+  in the hardware and must be specified here as <0x0003b080>. This number
+  follows the PrimeCell standard numbering using the JEP106 vendor code 0x38
+  for Faraday Technology.
 - reg: Address range of the PL08x registers
 - interrupt: The PL08x interrupt number
 - clocks: The clock running the IP core clock
@@ -20,8 +25,8 @@ Optional properties:
 - dma-requests: contains the total number of DMA requests supported by the DMAC
 - memcpy-burst-size: the size of the bursts for memcpy: 1, 4, 8, 16, 32
   64, 128 or 256 bytes are legal values
-- memcpy-bus-width: the bus width used for memcpy: 8, 16 or 32 are legal
-  values
+- memcpy-bus-width: the bus width used for memcpy in bits: 8, 16 or 32 are legal
+  values, the Faraday FTDMAC020 can also accept 64 bits
 
 Clients
 Required properties:

Documentation/devicetree/bindings/dma/brcm,iproc-sba.txt

@@ -0,0 +1,29 @@
+* Broadcom SBA RAID engine
+
+Required properties:
+- compatible: Should be one of the following
+	      "brcm,iproc-sba"
+	      "brcm,iproc-sba-v2"
+  The "brcm,iproc-sba" has support for only 6 PQ coefficients
+  The "brcm,iproc-sba-v2" has support for only 30 PQ coefficients
+- mboxes: List of phandle and mailbox channel specifiers
+
+Example:
+
+raid_mbox: mbox@67400000 {
+	...
+	#mbox-cells = <3>;
+	...
+};
+
+raid0 {
+	compatible = "brcm,iproc-sba-v2";
+	mboxes = <&raid_mbox 0 0x1 0xffff>,
+		 <&raid_mbox 1 0x1 0xffff>,
+		 <&raid_mbox 2 0x1 0xffff>,
+		 <&raid_mbox 3 0x1 0xffff>,
+		 <&raid_mbox 4 0x1 0xffff>,
+		 <&raid_mbox 5 0x1 0xffff>,
+		 <&raid_mbox 6 0x1 0xffff>,
+		 <&raid_mbox 7 0x1 0xffff>;
+};

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

@@ -30,8 +30,9 @@ Required Properties:
 
 - interrupts: interrupt specifiers for the DMAC, one for each entry in
   interrupt-names.
-- interrupt-names: one entry per channel, named "ch%u", where %u is the
-  channel number ranging from zero to the number of channels minus one.
+- interrupt-names: one entry for the error interrupt, named "error", plus one
+  entry per channel, named "ch%u", where %u is the channel number ranging from
+  zero to the number of channels minus one.
 
 - clock-names: "fck" for the functional clock
 - clocks: a list of phandle + clock-specifier pairs, one for each entry

Documentation/devicetree/bindings/dma/shdma.txt

@@ -1,6 +1,6 @@
 * SHDMA Device Tree bindings
 
-Sh-/r-mobile and r-car systems often have multiple identical DMA controller
+Sh-/r-mobile and R-Car systems often have multiple identical DMA controller
 instances, capable of serving any of a common set of DMA slave devices, using
 the same configuration. To describe this topology we require all compatible
 SHDMA DT nodes to be placed under a DMA multiplexer node. All such compatible

arch/arm/mach-lpc32xx/phy3250.c

@@ -137,6 +137,9 @@ static void pl08x_put_signal(const struct pl08x_channel_data *cd, int ch)
 }
 
 static struct pl08x_platform_data pl08x_pd = {
+	/* Some reasonable memcpy defaults */
+	.memcpy_burst_size = PL08X_BURST_SZ_256,
+	.memcpy_bus_width = PL08X_BUS_WIDTH_32_BITS,
 	.slave_channels = &pl08x_slave_channels[0],
 	.num_slave_channels = ARRAY_SIZE(pl08x_slave_channels),
 	.get_xfer_signal = pl08x_get_signal,

arch/arm/mach-s3c64xx/pl080.c

@@ -137,16 +137,10 @@ static const struct dma_slave_map s3c64xx_dma0_slave_map[] = {
 };
 
 struct pl08x_platform_data s3c64xx_dma0_plat_data = {
-	.memcpy_channel = {
-		.bus_id = "memcpy",
-		.cctl_memcpy =
-			(PL080_BSIZE_4 << PL080_CONTROL_SB_SIZE_SHIFT |
-			PL080_BSIZE_4 << PL080_CONTROL_DB_SIZE_SHIFT |
-			PL080_WIDTH_32BIT << PL080_CONTROL_SWIDTH_SHIFT |
-			PL080_WIDTH_32BIT << PL080_CONTROL_DWIDTH_SHIFT |
-			PL080_CONTROL_PROT_BUFF | PL080_CONTROL_PROT_CACHE |
-			PL080_CONTROL_PROT_SYS),
-	},
+	.memcpy_burst_size = PL08X_BURST_SZ_4,
+	.memcpy_bus_width = PL08X_BUS_WIDTH_32_BITS,
+	.memcpy_prot_buff = true,
+	.memcpy_prot_cache = true,
 	.lli_buses = PL08X_AHB1,
 	.mem_buses = PL08X_AHB1,
 	.get_xfer_signal = pl08x_get_xfer_signal,
@@ -238,16 +232,10 @@ static const struct dma_slave_map s3c64xx_dma1_slave_map[] = {
 };
 
 struct pl08x_platform_data s3c64xx_dma1_plat_data = {
-	.memcpy_channel = {
-		.bus_id = "memcpy",
-		.cctl_memcpy =
-			(PL080_BSIZE_4 << PL080_CONTROL_SB_SIZE_SHIFT |
-			PL080_BSIZE_4 << PL080_CONTROL_DB_SIZE_SHIFT |
-			PL080_WIDTH_32BIT << PL080_CONTROL_SWIDTH_SHIFT |
-			PL080_WIDTH_32BIT << PL080_CONTROL_DWIDTH_SHIFT |
-			PL080_CONTROL_PROT_BUFF | PL080_CONTROL_PROT_CACHE |
-			PL080_CONTROL_PROT_SYS),
-	},
+	.memcpy_burst_size = PL08X_BURST_SZ_4,
+	.memcpy_bus_width = PL08X_BUS_WIDTH_32_BITS,
+	.memcpy_prot_buff = true,
+	.memcpy_prot_cache = true,
 	.lli_buses = PL08X_AHB1,
 	.mem_buses = PL08X_AHB1,
 	.get_xfer_signal = pl08x_get_xfer_signal,

arch/arm/mach-spear/spear3xx.c

@@ -44,16 +44,10 @@ struct pl022_ssp_controller pl022_plat_data = {
 
 /* dmac device registration */
 struct pl08x_platform_data pl080_plat_data = {
-	.memcpy_channel = {
-		.bus_id = "memcpy",
-		.cctl_memcpy =
-			(PL080_BSIZE_16 << PL080_CONTROL_SB_SIZE_SHIFT | \
-			PL080_BSIZE_16 << PL080_CONTROL_DB_SIZE_SHIFT | \
-			PL080_WIDTH_32BIT << PL080_CONTROL_SWIDTH_SHIFT | \
-			PL080_WIDTH_32BIT << PL080_CONTROL_DWIDTH_SHIFT | \
-			PL080_CONTROL_PROT_BUFF | PL080_CONTROL_PROT_CACHE | \
-			PL080_CONTROL_PROT_SYS),
-	},
+	.memcpy_burst_size = PL08X_BURST_SZ_16,
+	.memcpy_bus_width = PL08X_BUS_WIDTH_32_BITS,
+	.memcpy_prot_buff = true,
+	.memcpy_prot_cache = true,
 	.lli_buses = PL08X_AHB1,
 	.mem_buses = PL08X_AHB1,
 	.get_xfer_signal = pl080_get_signal,

arch/arm/mach-spear/spear6xx.c

@@ -322,16 +322,10 @@ static struct pl08x_channel_data spear600_dma_info[] = {
 };
 
 static struct pl08x_platform_data spear6xx_pl080_plat_data = {
-	.memcpy_channel = {
-		.bus_id = "memcpy",
-		.cctl_memcpy =
-			(PL080_BSIZE_16 << PL080_CONTROL_SB_SIZE_SHIFT | \
-			PL080_BSIZE_16 << PL080_CONTROL_DB_SIZE_SHIFT | \
-			PL080_WIDTH_32BIT << PL080_CONTROL_SWIDTH_SHIFT | \
-			PL080_WIDTH_32BIT << PL080_CONTROL_DWIDTH_SHIFT | \
-			PL080_CONTROL_PROT_BUFF | PL080_CONTROL_PROT_CACHE | \
-			PL080_CONTROL_PROT_SYS),
-	},
+	.memcpy_burst_size = PL08X_BURST_SZ_16,
+	.memcpy_bus_width = PL08X_BUS_WIDTH_32_BITS,
+	.memcpy_prot_buff = true,
+	.memcpy_prot_cache = true,
 	.lli_buses = PL08X_AHB1,
 	.mem_buses = PL08X_AHB1,
 	.get_xfer_signal = pl080_get_signal,

crypto/async_tx/async_pq.c

@@ -62,9 +62,6 @@ do_async_gen_syndrome(struct dma_chan *chan,
 	dma_addr_t dma_dest[2];
 	int src_off = 0;
 
-	if (submit->flags & ASYNC_TX_FENCE)
-		dma_flags |= DMA_PREP_FENCE;
-
 	while (src_cnt > 0) {
 		submit->flags = flags_orig;
 		pq_src_cnt = min(src_cnt, dma_maxpq(dma, dma_flags));
@@ -83,6 +80,8 @@ do_async_gen_syndrome(struct dma_chan *chan,
 			if (cb_fn_orig)
 				dma_flags |= DMA_PREP_INTERRUPT;
 		}
+		if (submit->flags & ASYNC_TX_FENCE)
+			dma_flags |= DMA_PREP_FENCE;
 
 		/* Drivers force forward progress in case they can not provide
 		 * a descriptor

drivers/dma/Kconfig

@@ -62,8 +62,10 @@ config AMBA_PL08X
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
 	help
-	  Platform has a PL08x DMAC device
-	  which can provide DMA engine support
+	  Say yes if your platform has a PL08x DMAC device which can
+	  provide DMA engine support. This includes the original ARM
+	  PL080 and PL081, Samsungs PL080 derivative and Faraday
+	  Technology's FTDMAC020 PL080 derivative.
 
 config AMCC_PPC440SPE_ADMA
 	tristate "AMCC PPC440SPe ADMA support"
@@ -99,6 +101,21 @@ config AXI_DMAC
 	  controller is often used in Analog Device's reference designs for FPGA
 	  platforms.
 
+config BCM_SBA_RAID
+	tristate "Broadcom SBA RAID engine support"
+	depends on ARM64 || COMPILE_TEST
+	depends on MAILBOX && RAID6_PQ
+	select DMA_ENGINE
+	select DMA_ENGINE_RAID
+	select ASYNC_TX_DISABLE_XOR_VAL_DMA
+	select ASYNC_TX_DISABLE_PQ_VAL_DMA
+	default ARCH_BCM_IPROC
+	help
+	  Enable support for Broadcom SBA RAID Engine. The SBA RAID
+	  engine is available on most of the Broadcom iProc SoCs. It
+	  has the capability to offload memcpy, xor and pq computation
+	  for raid5/6.
+
 config COH901318
 	bool "ST-Ericsson COH901318 DMA support"
 	select DMA_ENGINE
@@ -354,13 +371,12 @@ config MV_XOR_V2
 
 config MXS_DMA
 	bool "MXS DMA support"
-	depends on SOC_IMX23 || SOC_IMX28 || SOC_IMX6Q || SOC_IMX6UL
+	depends on ARCH_MXS || ARCH_MXC || COMPILE_TEST
 	select STMP_DEVICE
 	select DMA_ENGINE
 	help
 	  Support the MXS DMA engine. This engine including APBH-DMA
-	  and APBX-DMA is integrated into Freescale
-	  i.MX23/28/MX6Q/MX6DL/MX6UL chips.
+	  and APBX-DMA is integrated into some Freescale chips.
 
 config MX3_IPU
 	bool "MX3x Image Processing Unit support"

drivers/dma/Makefile

@@ -17,6 +17,7 @@ obj-$(CONFIG_AMCC_PPC440SPE_ADMA) += ppc4xx/
 obj-$(CONFIG_AT_HDMAC) += at_hdmac.o
 obj-$(CONFIG_AT_XDMAC) += at_xdmac.o
 obj-$(CONFIG_AXI_DMAC) += dma-axi-dmac.o
+obj-$(CONFIG_BCM_SBA_RAID) += bcm-sba-raid.o
 obj-$(CONFIG_COH901318) += coh901318.o coh901318_lli.o
 obj-$(CONFIG_DMA_BCM2835) += bcm2835-dma.o
 obj-$(CONFIG_DMA_JZ4740) += dma-jz4740.o

drivers/dma/dw/platform.c

@@ -306,8 +306,12 @@ static int dw_resume_early(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct dw_dma_chip *chip = platform_get_drvdata(pdev);
+	int ret;
+
+	ret = clk_prepare_enable(chip->clk);
+	if (ret)
+		return ret;
 
-	clk_prepare_enable(chip->clk);
 	return dw_dma_enable(chip);
 }
 

drivers/dma/fsl_raid.c

@@ -877,7 +877,7 @@ static int fsl_re_remove(struct platform_device *ofdev)
 	return 0;
 }
 
-static struct of_device_id fsl_re_ids[] = {
+static const struct of_device_id fsl_re_ids[] = {
 	{ .compatible = "fsl,raideng-v1.0", },
 	{}
 };

drivers/dma/fsldma.c

@@ -269,6 +269,7 @@ static void fsl_chan_set_src_loop_size(struct fsldma_chan *chan, int size)
 	case 2:
 	case 4:
 	case 8:
+		mode &= ~FSL_DMA_MR_SAHTS_MASK;
 		mode |= FSL_DMA_MR_SAHE | (__ilog2(size) << 14);
 		break;
 	}
@@ -301,6 +302,7 @@ static void fsl_chan_set_dst_loop_size(struct fsldma_chan *chan, int size)
 	case 2:
 	case 4:
 	case 8:
+		mode &= ~FSL_DMA_MR_DAHTS_MASK;
 		mode |= FSL_DMA_MR_DAHE | (__ilog2(size) << 16);
 		break;
 	}
@@ -327,7 +329,8 @@ static void fsl_chan_set_request_count(struct fsldma_chan *chan, int size)
 	BUG_ON(size > 1024);
 
 	mode = get_mr(chan);
-	mode |= (__ilog2(size) << 24) & 0x0f000000;
+	mode &= ~FSL_DMA_MR_BWC_MASK;
+	mode |= (__ilog2(size) << 24) & FSL_DMA_MR_BWC_MASK;
 
 	set_mr(chan, mode);
 }

drivers/dma/fsldma.h

@@ -36,6 +36,10 @@
 #define FSL_DMA_MR_DAHE		0x00002000
 #define FSL_DMA_MR_SAHE		0x00001000
 
+#define FSL_DMA_MR_SAHTS_MASK	0x0000C000
+#define FSL_DMA_MR_DAHTS_MASK	0x00030000
+#define FSL_DMA_MR_BWC_MASK	0x0f000000
+
 /*
  * Bandwidth/pause control determines how many bytes a given
  * channel is allowed to transfer before the DMA engine pauses

drivers/dma/imx-dma.c

@@ -888,7 +888,7 @@ static struct dma_async_tx_descriptor *imxdma_prep_dma_cyclic(
 	sg_init_table(imxdmac->sg_list, periods);
 
 	for (i = 0; i < periods; i++) {
-		imxdmac->sg_list[i].page_link = 0;
+		sg_assign_page(&imxdmac->sg_list[i], NULL);
 		imxdmac->sg_list[i].offset = 0;
 		imxdmac->sg_list[i].dma_address = dma_addr;
 		sg_dma_len(&imxdmac->sg_list[i]) = period_len;
@@ -896,10 +896,7 @@ static struct dma_async_tx_descriptor *imxdma_prep_dma_cyclic(
 	}
 
 	/* close the loop */
-	imxdmac->sg_list[periods].offset = 0;
-	sg_dma_len(&imxdmac->sg_list[periods]) = 0;
-	imxdmac->sg_list[periods].page_link =
-		((unsigned long)imxdmac->sg_list | 0x01) & ~0x02;
+	sg_chain(imxdmac->sg_list, periods + 1, imxdmac->sg_list);
 
 	desc->type = IMXDMA_DESC_CYCLIC;
 	desc->sg = imxdmac->sg_list;

drivers/dma/imx-sdma.c

@@ -1323,7 +1323,7 @@ static struct dma_async_tx_descriptor *sdma_prep_dma_cyclic(
 	}
 
 	if (period_len > 0xffff) {
-		dev_err(sdma->dev, "SDMA channel %d: maximum period size exceeded: %d > %d\n",
+		dev_err(sdma->dev, "SDMA channel %d: maximum period size exceeded: %zu > %d\n",
 				channel, period_len, 0xffff);
 		goto err_out;
 	}
@@ -1347,7 +1347,7 @@ static struct dma_async_tx_descriptor *sdma_prep_dma_cyclic(
 		if (i + 1 == num_periods)
 			param |= BD_WRAP;
 
-		dev_dbg(sdma->dev, "entry %d: count: %d dma: %#llx %s%s\n",
+		dev_dbg(sdma->dev, "entry %d: count: %zu dma: %#llx %s%s\n",
 				i, period_len, (u64)dma_addr,
 				param & BD_WRAP ? "wrap" : "",
 				param & BD_INTR ? " intr" : "");
@@ -1755,19 +1755,26 @@ static int sdma_probe(struct platform_device *pdev)
 	if (IS_ERR(sdma->clk_ahb))
 		return PTR_ERR(sdma->clk_ahb);
 
-	clk_prepare(sdma->clk_ipg);
-	clk_prepare(sdma->clk_ahb);
+	ret = clk_prepare(sdma->clk_ipg);
+	if (ret)
+		return ret;
+
+	ret = clk_prepare(sdma->clk_ahb);
+	if (ret)
+		goto err_clk;
 
 	ret = devm_request_irq(&pdev->dev, irq, sdma_int_handler, 0, "sdma",
 			       sdma);
 	if (ret)
-		return ret;
+		goto err_irq;
 
 	sdma->irq = irq;
 
 	sdma->script_addrs = kzalloc(sizeof(*sdma->script_addrs), GFP_KERNEL);
-	if (!sdma->script_addrs)
-		return -ENOMEM;
+	if (!sdma->script_addrs) {
+		ret = -ENOMEM;
+		goto err_irq;
+	}
 
 	/* initially no scripts available */
 	saddr_arr = (s32 *)sdma->script_addrs;
@@ -1882,6 +1889,10 @@ err_register:
 	dma_async_device_unregister(&sdma->dma_device);
 err_init:
 	kfree(sdma->script_addrs);
+err_irq:
+	clk_unprepare(sdma->clk_ahb);
+err_clk:
+	clk_unprepare(sdma->clk_ipg);
 	return ret;
 }
 
@@ -1893,6 +1904,8 @@ static int sdma_remove(struct platform_device *pdev)
 	devm_free_irq(&pdev->dev, sdma->irq, sdma);
 	dma_async_device_unregister(&sdma->dma_device);
 	kfree(sdma->script_addrs);
+	clk_unprepare(sdma->clk_ahb);
+	clk_unprepare(sdma->clk_ipg);
 	/* Kill the tasklet */
 	for (i = 0; i < MAX_DMA_CHANNELS; i++) {
 		struct sdma_channel *sdmac = &sdma->channel[i];

drivers/dma/ioat/dca.c

@@ -336,10 +336,10 @@ struct dca_provider *ioat_dca_init(struct pci_dev *pdev, void __iomem *iobase)
 	}
 
 	if (dca3_tag_map_invalid(ioatdca->tag_map)) {
-		WARN_TAINT_ONCE(1, TAINT_FIRMWARE_WORKAROUND,
-				"%s %s: APICID_TAG_MAP set incorrectly by BIOS, disabling DCA\n",
-				dev_driver_string(&pdev->dev),
-				dev_name(&pdev->dev));
+		add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
+		pr_warn_once("%s %s: APICID_TAG_MAP set incorrectly by BIOS, disabling DCA\n",
+			     dev_driver_string(&pdev->dev),
+			     dev_name(&pdev->dev));
 		free_dca_provider(dca);
 		return NULL;
 	}