Merge remote-tracking branches 'spi/topic/octeon', 'spi/topic/omap2-mcspi',...

Merge remote-tracking branches 'spi/topic/octeon', 'spi/topic/omap2-mcspi', 'spi/topic/orion', 'spi/topic/pic32' and 'spi/topic/pic32-sqi' into spi-next

Documentation/devicetree/bindings/spi/spi-orion.txt

@@ -8,7 +8,15 @@ Required properties:
     - "marvell,armada-380-spi", for the Armada 38x SoCs
     - "marvell,armada-390-spi", for the Armada 39x SoCs
     - "marvell,armada-xp-spi", for the Armada XP SoCs
-- reg : offset and length of the register set for the device
+- reg : offset and length of the register set for the device.
+	This property can optionally have additional entries to configure
+	the SPI direct access mode that some of the Marvell SoCs support
+	additionally to the normal indirect access (PIO) mode. The values
+	for the MBus "target" and "attribute" are defined in the Marvell
+	SoC "Functional Specifications" Manual in the chapter "Marvell
+	Core Processor Address Decoding".
+	The eight register sets following the control registers refer to
+	chip-select lines 0 through 7 respectively.
 - cell-index : Which of multiple SPI controllers is this.
 Optional properties:
 - interrupts : Is currently not used.
@@ -23,3 +31,42 @@ Example:
 	       interrupts = <23>;
 	       status = "disabled";
        };
+
+Example with SPI direct mode support (optionally):
+	spi0: spi@10600 {
+		compatible = "marvell,orion-spi";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		cell-index = <0>;
+		reg = <MBUS_ID(0xf0, 0x01) 0x10600 0x28>, /* control */
+		      <MBUS_ID(0x01, 0x1e) 0 0xffffffff>, /* CS0 */
+		      <MBUS_ID(0x01, 0x5e) 0 0xffffffff>, /* CS1 */
+		      <MBUS_ID(0x01, 0x9e) 0 0xffffffff>, /* CS2 */
+		      <MBUS_ID(0x01, 0xde) 0 0xffffffff>, /* CS3 */
+		      <MBUS_ID(0x01, 0x1f) 0 0xffffffff>, /* CS4 */
+		      <MBUS_ID(0x01, 0x5f) 0 0xffffffff>, /* CS5 */
+		      <MBUS_ID(0x01, 0x9f) 0 0xffffffff>, /* CS6 */
+		      <MBUS_ID(0x01, 0xdf) 0 0xffffffff>; /* CS7 */
+		interrupts = <23>;
+		status = "disabled";
+	};
+
+To enable the direct mode, the board specific 'ranges' property in the
+'soc' node needs to add the entries for the desired SPI controllers
+and its chip-selects that are used in the direct mode instead of PIO
+mode. Here an example for this (SPI controller 0, device 1 and SPI
+controller 1, device 2 are used in direct mode. All other SPI device
+are used in the default indirect (PIO) mode):
+	soc {
+		/*
+		 * Enable the SPI direct access by configuring an entry
+		 * here in the board-specific ranges property
+		 */
+		ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xf1000000 0x100000>,	/* internal regs */
+			 <MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000>,	/* BootROM       */
+			 <MBUS_ID(0x01, 0x5e) 0 0 0xf1100000 0x10000>,	/* SPI0-DEV1 */
+			 <MBUS_ID(0x01, 0x9a) 0 0 0xf1110000 0x10000>;	/* SPI1-DEV2 */
+
+For further information on the MBus bindings, please see the MBus
+DT documentation:
+Documentation/devicetree/bindings/bus/mvebu-mbus.txt

drivers/spi/Kconfig

@@ -411,6 +411,7 @@ config SPI_OMAP24XX
 	tristate "McSPI driver for OMAP"
 	depends on HAS_DMA
 	depends on ARCH_OMAP2PLUS || COMPILE_TEST
+	select SG_SPLIT
 	help
 	  SPI master controller for OMAP24XX and later Multichannel SPI
 	  (McSPI) modules.

drivers/spi/Makefile

@@ -56,6 +56,7 @@ obj-$(CONFIG_SPI_MT65XX)                += spi-mt65xx.o
 obj-$(CONFIG_SPI_MXS)			+= spi-mxs.o
 obj-$(CONFIG_SPI_NUC900)		+= spi-nuc900.o
 obj-$(CONFIG_SPI_OC_TINY)		+= spi-oc-tiny.o
+spi-octeon-objs				:= spi-cavium.o spi-cavium-octeon.o
 obj-$(CONFIG_SPI_OCTEON)		+= spi-octeon.o
 obj-$(CONFIG_SPI_OMAP_UWIRE)		+= spi-omap-uwire.o
 obj-$(CONFIG_SPI_OMAP_100K)		+= spi-omap-100k.o

drivers/spi/spi-cavium-octeon.c

+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2011, 2012 Cavium, Inc.
+ */
+
+#include <linux/platform_device.h>
+#include <linux/spi/spi.h>
+#include <linux/module.h>
+#include <linux/io.h>
+#include <linux/of.h>
+
+#include <asm/octeon/octeon.h>
+
+#include "spi-cavium.h"
+
+static int octeon_spi_probe(struct platform_device *pdev)
+{
+	struct resource *res_mem;
+	void __iomem *reg_base;
+	struct spi_master *master;
+	struct octeon_spi *p;
+	int err = -ENOENT;
+
+	master = spi_alloc_master(&pdev->dev, sizeof(struct octeon_spi));
+	if (!master)
+		return -ENOMEM;
+	p = spi_master_get_devdata(master);
+	platform_set_drvdata(pdev, master);
+
+	res_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	reg_base = devm_ioremap_resource(&pdev->dev, res_mem);
+	if (IS_ERR(reg_base)) {
+		err = PTR_ERR(reg_base);
+		goto fail;
+	}
+
+	p->register_base = reg_base;
+	p->sys_freq = octeon_get_io_clock_rate();
+
+	p->regs.config = 0;
+	p->regs.status = 0x08;
+	p->regs.tx = 0x10;
+	p->regs.data = 0x80;
+
+	master->num_chipselect = 4;
+	master->mode_bits = SPI_CPHA |
+			    SPI_CPOL |
+			    SPI_CS_HIGH |
+			    SPI_LSB_FIRST |
+			    SPI_3WIRE;
+
+	master->transfer_one_message = octeon_spi_transfer_one_message;
+	master->bits_per_word_mask = SPI_BPW_MASK(8);
+	master->max_speed_hz = OCTEON_SPI_MAX_CLOCK_HZ;
+
+	master->dev.of_node = pdev->dev.of_node;
+	err = devm_spi_register_master(&pdev->dev, master);
+	if (err) {
+		dev_err(&pdev->dev, "register master failed: %d\n", err);
+		goto fail;
+	}
+
+	dev_info(&pdev->dev, "OCTEON SPI bus driver\n");
+
+	return 0;
+fail:
+	spi_master_put(master);
+	return err;
+}
+
+static int octeon_spi_remove(struct platform_device *pdev)
+{
+	struct spi_master *master = platform_get_drvdata(pdev);
+	struct octeon_spi *p = spi_master_get_devdata(master);
+
+	/* Clear the CSENA* and put everything in a known state. */
+	writeq(0, p->register_base + OCTEON_SPI_CFG(p));
+
+	return 0;
+}
+
+static const struct of_device_id octeon_spi_match[] = {
+	{ .compatible = "cavium,octeon-3010-spi", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, octeon_spi_match);
+
+static struct platform_driver octeon_spi_driver = {
+	.driver = {
+		.name		= "spi-octeon",
+		.of_match_table = octeon_spi_match,
+	},
+	.probe		= octeon_spi_probe,
+	.remove		= octeon_spi_remove,
+};
+
+module_platform_driver(octeon_spi_driver);
+
+MODULE_DESCRIPTION("Cavium, Inc. OCTEON SPI bus driver");
+MODULE_AUTHOR("David Daney");
+MODULE_LICENSE("GPL");

drivers/spi/spi-octeon.c → drivers/spi/spi-cavium.c

@@ -6,31 +6,12 @@
  * Copyright (C) 2011, 2012 Cavium, Inc.
  */
 
-#include <linux/platform_device.h>
-#include <linux/interrupt.h>
 #include <linux/spi/spi.h>
 #include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/io.h>
-#include <linux/of.h>
 
-#include <asm/octeon/octeon.h>
-#include <asm/octeon/cvmx-mpi-defs.h>
-
-#define OCTEON_SPI_CFG 0
-#define OCTEON_SPI_STS 0x08
-#define OCTEON_SPI_TX 0x10
-#define OCTEON_SPI_DAT0 0x80
-
-#define OCTEON_SPI_MAX_BYTES 9
-
-#define OCTEON_SPI_MAX_CLOCK_HZ 16000000
-
-struct octeon_spi {
-	u64 register_base;
-	u64 last_cfg;
-	u64 cs_enax;
-};
+#include "spi-cavium.h"
 
 static void octeon_spi_wait_ready(struct octeon_spi *p)
 {
@@ -40,7 +21,7 @@ static void octeon_spi_wait_ready(struct octeon_spi *p)
 	do {
 		if (loops++)
 			__delay(500);
-		mpi_sts.u64 = cvmx_read_csr(p->register_base + OCTEON_SPI_STS);
+		mpi_sts.u64 = readq(p->register_base + OCTEON_SPI_STS(p));
 	} while (mpi_sts.s.busy);
 }
 
@@ -53,7 +34,6 @@ static int octeon_spi_do_transfer(struct octeon_spi *p,
 	union cvmx_mpi_cfg mpi_cfg;
 	union cvmx_mpi_tx mpi_tx;
 	unsigned int clkdiv;
-	unsigned int speed_hz;
 	int mode;
 	bool cpha, cpol;
 	const u8 *tx_buf;
@@ -65,9 +45,7 @@ static int octeon_spi_do_transfer(struct octeon_spi *p,
 	cpha = mode & SPI_CPHA;
 	cpol = mode & SPI_CPOL;
 
-	speed_hz = xfer->speed_hz;
-
-	clkdiv = octeon_get_io_clock_rate() / (2 * speed_hz);
+	clkdiv = p->sys_freq / (2 * xfer->speed_hz);
 
 	mpi_cfg.u64 = 0;
 
@@ -85,7 +63,7 @@ static int octeon_spi_do_transfer(struct octeon_spi *p,
 
 	if (mpi_cfg.u64 != p->last_cfg) {
 		p->last_cfg = mpi_cfg.u64;
-		cvmx_write_csr(p->register_base + OCTEON_SPI_CFG, mpi_cfg.u64);
+		writeq(mpi_cfg.u64, p->register_base + OCTEON_SPI_CFG(p));
 	}
 	tx_buf = xfer->tx_buf;
 	rx_buf = xfer->rx_buf;
@@ -97,19 +75,19 @@ static int octeon_spi_do_transfer(struct octeon_spi *p,
 				d = *tx_buf++;
 			else
 				d = 0;
-			cvmx_write_csr(p->register_base + OCTEON_SPI_DAT0 + (8 * i), d);
+			writeq(d, p->register_base + OCTEON_SPI_DAT0(p) + (8 * i));
 		}
 		mpi_tx.u64 = 0;
 		mpi_tx.s.csid = spi->chip_select;
 		mpi_tx.s.leavecs = 1;
 		mpi_tx.s.txnum = tx_buf ? OCTEON_SPI_MAX_BYTES : 0;
 		mpi_tx.s.totnum = OCTEON_SPI_MAX_BYTES;
-		cvmx_write_csr(p->register_base + OCTEON_SPI_TX, mpi_tx.u64);
+		writeq(mpi_tx.u64, p->register_base + OCTEON_SPI_TX(p));
 
 		octeon_spi_wait_ready(p);
 		if (rx_buf)
 			for (i = 0; i < OCTEON_SPI_MAX_BYTES; i++) {
-				u64 v = cvmx_read_csr(p->register_base + OCTEON_SPI_DAT0 + (8 * i));
+				u64 v = readq(p->register_base + OCTEON_SPI_DAT0(p) + (8 * i));
 				*rx_buf++ = (u8)v;
 			}
 		len -= OCTEON_SPI_MAX_BYTES;
@@ -121,7 +99,7 @@ static int octeon_spi_do_transfer(struct octeon_spi *p,
 			d = *tx_buf++;
 		else
 			d = 0;
-		cvmx_write_csr(p->register_base + OCTEON_SPI_DAT0 + (8 * i), d);
+		writeq(d, p->register_base + OCTEON_SPI_DAT0(p) + (8 * i));
 	}
 
 	mpi_tx.u64 = 0;
@@ -132,12 +110,12 @@ static int octeon_spi_do_transfer(struct octeon_spi *p,
 		mpi_tx.s.leavecs = !xfer->cs_change;
 	mpi_tx.s.txnum = tx_buf ? len : 0;
 	mpi_tx.s.totnum = len;
-	cvmx_write_csr(p->register_base + OCTEON_SPI_TX, mpi_tx.u64);
+	writeq(mpi_tx.u64, p->register_base + OCTEON_SPI_TX(p));
 
 	octeon_spi_wait_ready(p);
 	if (rx_buf)
 		for (i = 0; i < len; i++) {
-			u64 v = cvmx_read_csr(p->register_base + OCTEON_SPI_DAT0 + (8 * i));
+			u64 v = readq(p->register_base + OCTEON_SPI_DAT0(p) + (8 * i));
 			*rx_buf++ = (u8)v;
 		}
 
@@ -147,8 +125,8 @@ static int octeon_spi_do_transfer(struct octeon_spi *p,
 	return xfer->len;
 }
 
-static int octeon_spi_transfer_one_message(struct spi_master *master,
-					   struct spi_message *msg)
+int octeon_spi_transfer_one_message(struct spi_master *master,
+				    struct spi_message *msg)
 {
 	struct octeon_spi *p = spi_master_get_devdata(master);
 	unsigned int total_len = 0;
@@ -171,85 +149,3 @@ static int octeon_spi_transfer_one_message(struct spi_master *master,
 	spi_finalize_current_message(master);
 	return status;
 }
-
-static int octeon_spi_probe(struct platform_device *pdev)
-{
-	struct resource *res_mem;
-	void __iomem *reg_base;
-	struct spi_master *master;
-	struct octeon_spi *p;
-	int err = -ENOENT;
-
-	master = spi_alloc_master(&pdev->dev, sizeof(struct octeon_spi));
-	if (!master)
-		return -ENOMEM;
-	p = spi_master_get_devdata(master);
-	platform_set_drvdata(pdev, master);
-
-	res_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	reg_base = devm_ioremap_resource(&pdev->dev, res_mem);
-	if (IS_ERR(reg_base)) {
-		err = PTR_ERR(reg_base);
-		goto fail;
-	}
-
-	p->register_base = (u64)reg_base;
-
-	master->num_chipselect = 4;
-	master->mode_bits = SPI_CPHA |
-			    SPI_CPOL |
-			    SPI_CS_HIGH |
-			    SPI_LSB_FIRST |
-			    SPI_3WIRE;
-
-	master->transfer_one_message = octeon_spi_transfer_one_message;
-	master->bits_per_word_mask = SPI_BPW_MASK(8);
-	master->max_speed_hz = OCTEON_SPI_MAX_CLOCK_HZ;
-
-	master->dev.of_node = pdev->dev.of_node;
-	err = devm_spi_register_master(&pdev->dev, master);
-	if (err) {
-		dev_err(&pdev->dev, "register master failed: %d\n", err);
-		goto fail;
-	}
-
-	dev_info(&pdev->dev, "OCTEON SPI bus driver\n");
-
-	return 0;
-fail:
-	spi_master_put(master);
-	return err;
-}
-
-static int octeon_spi_remove(struct platform_device *pdev)
-{
-	struct spi_master *master = platform_get_drvdata(pdev);
-	struct octeon_spi *p = spi_master_get_devdata(master);
-	u64 register_base = p->register_base;
-
-	/* Clear the CSENA* and put everything in a known state. */
-	cvmx_write_csr(register_base + OCTEON_SPI_CFG, 0);
-
-	return 0;
-}
-
-static const struct of_device_id octeon_spi_match[] = {
-	{ .compatible = "cavium,octeon-3010-spi", },
-	{},
-};
-MODULE_DEVICE_TABLE(of, octeon_spi_match);
-
-static struct platform_driver octeon_spi_driver = {
-	.driver = {
-		.name		= "spi-octeon",
-		.of_match_table = octeon_spi_match,
-	},
-	.probe		= octeon_spi_probe,
-	.remove		= octeon_spi_remove,
-};
-
-module_platform_driver(octeon_spi_driver);
-
-MODULE_DESCRIPTION("Cavium, Inc. OCTEON SPI bus driver");
-MODULE_AUTHOR("David Daney");
-MODULE_LICENSE("GPL");

arch/mips/include/asm/octeon/cvmx-mpi-defs.h → drivers/spi/spi-cavium.h

-/***********************license start***************
- * Author: Cavium Networks
- *
- * Contact: support@caviumnetworks.com
- * This file is part of the OCTEON SDK
- *
- * Copyright (c) 2003-2012 Cavium Networks
- *
- * This file is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, Version 2, as
- * published by the Free Software Foundation.
- *
- * This file is distributed in the hope that it will be useful, but
- * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
- * NONINFRINGEMENT.  See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this file; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- * or visit http://www.gnu.org/licenses/.
- *
- * This file may also be available under a different license from Cavium.
- * Contact Cavium Networks for more information
- ***********************license end**************************************/
+#ifndef __SPI_CAVIUM_H
+#define __SPI_CAVIUM_H
 
-#ifndef __CVMX_MPI_DEFS_H__
-#define __CVMX_MPI_DEFS_H__
+#define OCTEON_SPI_MAX_BYTES 9
+#define OCTEON_SPI_MAX_CLOCK_HZ 16000000
+
+struct octeon_spi_regs {
+	int config;
+	int status;
+	int tx;
+	int data;
+};
+
+struct octeon_spi {
+	void __iomem *register_base;
+	u64 last_cfg;
+	u64 cs_enax;
+	int sys_freq;
+	struct octeon_spi_regs regs;
+};
+
+#define OCTEON_SPI_CFG(x)	(x->regs.config)
+#define OCTEON_SPI_STS(x)	(x->regs.status)
+#define OCTEON_SPI_TX(x)	(x->regs.tx)
+#define OCTEON_SPI_DAT0(x)	(x->regs.data)
+
+int octeon_spi_transfer_one_message(struct spi_master *master,
+				    struct spi_message *msg);
+
+/* MPI register descriptions */
 
 #define CVMX_MPI_CFG (CVMX_ADD_IO_SEG(0x0001070000001000ull))
 #define CVMX_MPI_DATX(offset) (CVMX_ADD_IO_SEG(0x0001070000001080ull) + ((offset) & 15) * 8)
@@ -325,4 +326,4 @@ union cvmx_mpi_tx {
 	struct cvmx_mpi_tx_cn61xx cnf71xx;
 };
 
-#endif
+#endif /* __SPI_CAVIUM_H */

drivers/spi/spi-omap2-mcspi.c

@@ -419,16 +419,13 @@ static void omap2_mcspi_tx_dma(struct spi_device *spi,
 
 	if (mcspi_dma->dma_tx) {
 		struct dma_async_tx_descriptor *tx;
-		struct scatterlist sg;
 
 		dmaengine_slave_config(mcspi_dma->dma_tx, &cfg);
 
-		sg_init_table(&sg, 1);
-		sg_dma_address(&sg) = xfer->tx_dma;
-		sg_dma_len(&sg) = xfer->len;
-
-		tx = dmaengine_prep_slave_sg(mcspi_dma->dma_tx, &sg, 1,
-		DMA_MEM_TO_DEV, DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+		tx = dmaengine_prep_slave_sg(mcspi_dma->dma_tx, xfer->tx_sg.sgl,
+					     xfer->tx_sg.nents,
+					     DMA_MEM_TO_DEV,
+					     DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 		if (tx) {
 			tx->callback = omap2_mcspi_tx_callback;
 			tx->callback_param = spi;
@@ -449,7 +446,10 @@ omap2_mcspi_rx_dma(struct spi_device *spi, struct spi_transfer *xfer,
 {
 	struct omap2_mcspi	*mcspi;
 	struct omap2_mcspi_dma  *mcspi_dma;
-	unsigned int		count, dma_count;
+	unsigned int		count, transfer_reduction = 0;
+	struct scatterlist	*sg_out[2];
+	int			nb_sizes = 0, out_mapped_nents[2], ret, x;
+	size_t			sizes[2];
 	u32			l;
 	int			elements = 0;
 	int			word_len, element_count;
@@ -457,10 +457,14 @@ omap2_mcspi_rx_dma(struct spi_device *spi, struct spi_transfer *xfer,
 	mcspi = spi_master_get_devdata(spi->master);
 	mcspi_dma = &mcspi->dma_channels[spi->chip_select];
 	count = xfer->len;
-	dma_count = xfer->len;
 
+	/*
+	 *  In the "End-of-Transfer Procedure" section for DMA RX in OMAP35x TRM
+	 *  it mentions reducing DMA transfer length by one element in master
+	 *  normal mode.
+	 */
 	if (mcspi->fifo_depth == 0)
-		dma_count -= es;
+		transfer_reduction = es;
 
 	word_len = cs->word_len;
 	l = mcspi_cached_chconf0(spi);
@@ -474,20 +478,46 @@ omap2_mcspi_rx_dma(struct spi_device *spi, struct spi_transfer *xfer,
 
 	if (mcspi_dma->dma_rx) {
 		struct dma_async_tx_descriptor *tx;
-		struct scatterlist sg;
 
 		dmaengine_slave_config(mcspi_dma->dma_rx, &cfg);
 
+		/*
+		 *  Reduce DMA transfer length by one more if McSPI is
+		 *  configured in turbo mode.
+		 */
 		if ((l & OMAP2_MCSPI_CHCONF_TURBO) && mcspi->fifo_depth == 0)
-			dma_count -= es;
+			transfer_reduction += es;
+
+		if (transfer_reduction) {
+			/* Split sgl into two. The second sgl won't be used. */
+			sizes[0] = count - transfer_reduction;
+			sizes[1] = transfer_reduction;
+			nb_sizes = 2;
+		} else {
+			/*
+			 * Don't bother splitting the sgl. This essentially
+			 * clones the original sgl.
+			 */
+			sizes[0] = count;
+			nb_sizes = 1;
+		}
+
+		ret = sg_split(xfer->rx_sg.sgl, xfer->rx_sg.nents,
+			       0, nb_sizes,
+			       sizes,
+			       sg_out, out_mapped_nents,
+			       GFP_KERNEL);
 
-		sg_init_table(&sg, 1);
-		sg_dma_address(&sg) = xfer->rx_dma;
-		sg_dma_len(&sg) = dma_count;
+		if (ret < 0) {
+			dev_err(&spi->dev, "sg_split failed\n");
+			return 0;
+		}
 
-		tx = dmaengine_prep_slave_sg(mcspi_dma->dma_rx, &sg, 1,
-				DMA_DEV_TO_MEM, DMA_PREP_INTERRUPT |
-				DMA_CTRL_ACK);
+		tx = dmaengine_prep_slave_sg(mcspi_dma->dma_rx,
+					     sg_out[0],
+					     out_mapped_nents[0],
+					     DMA_DEV_TO_MEM,
+					     DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 		if (tx) {
 			tx->callback = omap2_mcspi_rx_callback;
 			tx->callback_param = spi;
@@ -501,12 +531,17 @@ omap2_mcspi_rx_dma(struct spi_device *spi, struct spi_transfer *xfer,
 	omap2_mcspi_set_dma_req(spi, 1, 1);
 
 	wait_for_completion(&mcspi_dma->dma_rx_completion);
-	dma_unmap_single(mcspi->dev, xfer->rx_dma, count,
-			 DMA_FROM_DEVICE);
+
+	for (x = 0; x < nb_sizes; x++)
+		kfree(sg_out[x]);
 
 	if (mcspi->fifo_depth > 0)
 		return count;
 
+	/*
+	 *  Due to the DMA transfer length reduction the missing bytes must
+	 *  be read manually to receive all of the expected data.
+	 */
 	omap2_mcspi_set_enable(spi, 0);
 
 	elements = element_count - 1;
@@ -615,8 +650,6 @@ omap2_mcspi_txrx_dma(struct spi_device *spi, struct spi_transfer *xfer)
 
 	if (tx != NULL) {
 		wait_for_completion(&mcspi_dma->dma_tx_completion);
-		dma_unmap_single(mcspi->dev, xfer->tx_dma, xfer->len,
-				 DMA_TO_DEVICE);
 
 		if (mcspi->fifo_depth > 0) {
 			irqstat_reg = mcspi->base + OMAP2_MCSPI_IRQSTATUS;
@@ -1074,8 +1107,9 @@ static void omap2_mcspi_cleanup(struct spi_device *spi)
 		gpio_free(spi->cs_gpio);
 }
 
-static int omap2_mcspi_work_one(struct omap2_mcspi *mcspi,
-		struct spi_device *spi, struct spi_transfer *t)
+static int omap2_mcspi_transfer_one(struct spi_master *master,
+				    struct spi_device *spi,
+				    struct spi_transfer *t)
 {
 
 	/* We only enable one channel at a time -- the one whose message is
@@ -1085,7 +1119,7 @@ static int omap2_mcspi_work_one(struct omap2_mcspi *mcspi,
 	 * chipselect with the FORCE bit ... CS != channel enable.
 	 */
 
-	struct spi_master		*master;
+	struct omap2_mcspi		*mcspi;
 	struct omap2_mcspi_dma		*mcspi_dma;
 	struct omap2_mcspi_cs		*cs;
 	struct omap2_mcspi_device_config *cd;
@@ -1093,7 +1127,7 @@ static int omap2_mcspi_work_one(struct omap2_mcspi *mcspi,
 	int				status = 0;
 	u32				chconf;
 
-	master = spi->master;
+	mcspi = spi_master_get_devdata(master);
 	mcspi_dma = mcspi->dma_channels + spi->chip_select;
 	cs = spi->controller_state;
 	cd = spi->controller_data;
@@ -1153,7 +1187,8 @@ static int omap2_mcspi_work_one(struct omap2_mcspi *mcspi,
 		unsigned	count;
 
 		if ((mcspi_dma->dma_rx && mcspi_dma->dma_tx) &&
-		    (t->len >= DMA_MIN_BYTES))
+		    master->cur_msg_mapped &&
+		    master->can_dma(master, spi, t))
 			omap2_mcspi_set_fifo(spi, t, 1);
 
 		omap2_mcspi_set_enable(spi, 1);
@@ -1164,7 +1199,8 @@ static int omap2_mcspi_work_one(struct omap2_mcspi *mcspi,
 					+ OMAP2_MCSPI_TX0);
 
 		if ((mcspi_dma->dma_rx && mcspi_dma->dma_tx) &&
-		    (t->len >= DMA_MIN_BYTES))
+		    master->cur_msg_mapped &&
+		    master->can_dma(master, spi, t))
 			count = omap2_mcspi_txrx_dma(spi, t);
 		else
 			count = omap2_mcspi_txrx_pio(spi, t);
@@ -1233,55 +1269,11 @@ static int omap2_mcspi_prepare_message(struct spi_master *master,
 	return 0;
 }
 
-static int omap2_mcspi_transfer_one(struct spi_master *master,
-		struct spi_device *spi, struct spi_transfer *t)
+static bool omap2_mcspi_can_dma(struct spi_master *master,
+				struct spi_device *spi,
+				struct spi_transfer *xfer)
 {
-	struct omap2_mcspi	*mcspi;
-	struct omap2_mcspi_dma	*mcspi_dma;
-	const void	*tx_buf = t->tx_buf;
-	void		*rx_buf = t->rx_buf;
-	unsigned	len = t->len;
-
-	mcspi = spi_master_get_devdata(master);
-	mcspi_dma = mcspi->dma_channels + spi->chip_select;
-
-	if ((len && !(rx_buf || tx_buf))) {
-		dev_dbg(mcspi->dev, "transfer: %d Hz, %d %s%s, %d bpw\n",
-				t->speed_hz,
-				len,
-				tx_buf ? "tx" : "",
-				rx_buf ? "rx" : "",
-				t->bits_per_word);
-		return -EINVAL;
-	}
-
-	if (len < DMA_MIN_BYTES)
-		goto skip_dma_map;
-
-	if (mcspi_dma->dma_tx && tx_buf != NULL) {
-		t->tx_dma = dma_map_single(mcspi->dev, (void *) tx_buf,
-				len, DMA_TO_DEVICE);
-		if (dma_mapping_error(mcspi->dev, t->tx_dma)) {
-			dev_dbg(mcspi->dev, "dma %cX %d bytes error\n",
-					'T', len);
-			return -EINVAL;
-		}
-	}
-	if (mcspi_dma->dma_rx && rx_buf != NULL) {
-		t->rx_dma = dma_map_single(mcspi->dev, rx_buf, t->len,
-				DMA_FROM_DEVICE);
-		if (dma_mapping_error(mcspi->dev, t->rx_dma)) {
-			dev_dbg(mcspi->dev, "dma %cX %d bytes error\n",
-					'R', len);
-			if (tx_buf != NULL)
-				dma_unmap_single(mcspi->dev, t->tx_dma,
-						len, DMA_TO_DEVICE);
-			return -EINVAL;
-		}
-	}
-
-skip_dma_map:
-	return omap2_mcspi_work_one(mcspi, spi, t);
+	return (xfer->len >= DMA_MIN_BYTES);
 }
 
 static int omap2_mcspi_master_setup(struct omap2_mcspi *mcspi)
@@ -1361,6 +1353,7 @@ static int omap2_mcspi_probe(struct platform_device *pdev)
 	master->setup = omap2_mcspi_setup;
 	master->auto_runtime_pm = true;
 	master->prepare_message = omap2_mcspi_prepare_message;
+	master->can_dma = omap2_mcspi_can_dma;
 	master->transfer_one = omap2_mcspi_transfer_one;
 	master->set_cs = omap2_mcspi_set_cs;
 	master->cleanup = omap2_mcspi_cleanup;

drivers/spi/spi-orion.c

@@ -18,6 +18,7 @@
 #include <linux/module.h>
 #include <linux/pm_runtime.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/of_device.h>
 #include <linux/clk.h>
 #include <linux/sizes.h>
@@ -43,6 +44,9 @@
 #define ORION_SPI_INT_CAUSE_REG		0x10
 #define ORION_SPI_TIMING_PARAMS_REG	0x18
 
+/* Register for the "Direct Mode" */
+#define SPI_DIRECT_WRITE_CONFIG_REG	0x20
+
 #define ORION_SPI_TMISO_SAMPLE_MASK	(0x3 << 6)
 #define ORION_SPI_TMISO_SAMPLE_1	(1 << 6)
 #define ORION_SPI_TMISO_SAMPLE_2	(2 << 6)
@@ -78,11 +82,18 @@ struct orion_spi_dev {
 	bool			is_errata_50mhz_ac;
 };
 
+struct orion_direct_acc {
+	void __iomem		*vaddr;
+	u32			size;
+};
+
 struct orion_spi {
 	struct spi_master	*master;
 	void __iomem		*base;
 	struct clk              *clk;
 	const struct orion_spi_dev *devdata;
+
+	struct orion_direct_acc	direct_access[ORION_NUM_CHIPSELECTS];
 };
 
 static inline void __iomem *spi_reg(struct orion_spi *orion_spi, u32 reg)
@@ -372,10 +383,39 @@ orion_spi_write_read(struct spi_device *spi, struct spi_transfer *xfer)
 {
 	unsigned int count;
 	int word_len;
+	struct orion_spi *orion_spi;
+	int cs = spi->chip_select;
 
 	word_len = spi->bits_per_word;
 	count = xfer->len;
 
+	orion_spi = spi_master_get_devdata(spi->master);
+
+	/*
+	 * Use SPI direct write mode if base address is available. Otherwise
+	 * fall back to PIO mode for this transfer.
+	 */
+	if ((orion_spi->direct_access[cs].vaddr) && (xfer->tx_buf) &&
+	    (word_len == 8)) {
+		unsigned int cnt = count / 4;
+		unsigned int rem = count % 4;
+
+		/*
+		 * Send the TX-data to the SPI device via the direct
+		 * mapped address window
+		 */
+		iowrite32_rep(orion_spi->direct_access[cs].vaddr,
+			      xfer->tx_buf, cnt);
+		if (rem) {
+			u32 *buf = (u32 *)xfer->tx_buf;
+
+			iowrite8_rep(orion_spi->direct_access[cs].vaddr,
+				     &buf[cnt], rem);
+		}
+
+		return count;
+	}
+
 	if (word_len == 8) {
 		const u8 *tx = xfer->tx_buf;
 		u8 *rx = xfer->rx_buf;
@@ -425,6 +465,10 @@ static int orion_spi_reset(struct orion_spi *orion_spi)
 {
 	/* Verify that the CS is deasserted */
 	orion_spi_clrbits(orion_spi, ORION_SPI_IF_CTRL_REG, 0x1);
+
+	/* Don't deassert CS between the direct mapped SPI transfers */
+	writel(0, spi_reg(orion_spi, SPI_DIRECT_WRITE_CONFIG_REG));
+
 	return 0;
 }
 
@@ -504,6 +548,7 @@ static int orion_spi_probe(struct platform_device *pdev)
 	struct resource *r;
 	unsigned long tclk_hz;
 	int status = 0;
+	struct device_node *np;
 
 	master = spi_alloc_master(&pdev->dev, sizeof(*spi));
 	if (master == NULL) {
@@ -576,6 +621,49 @@ static int orion_spi_probe(struct platform_device *pdev)
 		goto out_rel_clk;
 	}
 
+	/* Scan all SPI devices of this controller for direct mapped devices */
+	for_each_available_child_of_node(pdev->dev.of_node, np) {
+		u32 cs;
+
+		/* Get chip-select number from the "reg" property */
+		status = of_property_read_u32(np, "reg", &cs);
+		if (status) {
+			dev_err(&pdev->dev,
+				"%s has no valid 'reg' property (%d)\n",
+				np->full_name, status);
+			status = 0;
+			continue;
+		}
+
+		/*
+		 * Check if an address is configured for this SPI device. If
+		 * not, the MBus mapping via the 'ranges' property in the 'soc'
+		 * node is not configured and this device should not use the
+		 * direct mode. In this case, just continue with the next
+		 * device.
+		 */
+		status = of_address_to_resource(pdev->dev.of_node, cs + 1, r);
+		if (status)
+			continue;
+
+		/*
+		 * Only map one page for direct access. This is enough for the
+		 * simple TX transfer which only writes to the first word.
+		 * This needs to get extended for the direct SPI-NOR / SPI-NAND
+		 * support, once this gets implemented.
+		 */
+		spi->direct_access[cs].vaddr = devm_ioremap(&pdev->dev,
+							    r->start,
+							    PAGE_SIZE);
+		if (!spi->direct_access[cs].vaddr) {
+			status = -ENOMEM;
+			goto out_rel_clk;
+		}
+		spi->direct_access[cs].size = PAGE_SIZE;
+
+		dev_info(&pdev->dev, "CS%d configured for direct access\n", cs);
+	}
+
 	pm_runtime_set_active(&pdev->dev);
 	pm_runtime_use_autosuspend(&pdev->dev);
 	pm_runtime_set_autosuspend_delay(&pdev->dev, SPI_AUTOSUSPEND_TIMEOUT);

drivers/spi/spi-pic32-sqi.c

@@ -354,6 +354,7 @@ static int pic32_sqi_one_message(struct spi_master *master,
 	struct spi_transfer *xfer;
 	struct pic32_sqi *sqi;
 	int ret = 0, mode;
+	unsigned long timeout;
 	u32 val;
 
 	sqi = spi_master_get_devdata(master);
@@ -419,10 +420,10 @@ static int pic32_sqi_one_message(struct spi_master *master,
 	writel(val, sqi->regs + PESQI_BD_CTRL_REG);
 
 	/* wait for xfer completion */
-	ret = wait_for_completion_timeout(&sqi->xfer_done, 5 * HZ);
-	if (ret <= 0) {
+	timeout = wait_for_completion_timeout(&sqi->xfer_done, 5 * HZ);
+	if (timeout == 0) {
 		dev_err(&sqi->master->dev, "wait timedout/interrupted\n");
-		ret = -EIO;
+		ret = -ETIMEDOUT;
 		msg->status = ret;
 	} else {
 		/* success */

drivers/spi/spi-pic32.c

@@ -507,6 +507,7 @@ static int pic32_spi_one_transfer(struct spi_master *master,
 {
 	struct pic32_spi *pic32s;
 	bool dma_issued = false;
+	unsigned long timeout;
 	int ret;
 
 	pic32s = spi_master_get_devdata(master);
@@ -553,8 +554,8 @@ static int pic32_spi_one_transfer(struct spi_master *master,
 	}
 
 	/* wait for completion */
-	ret = wait_for_completion_timeout(&pic32s->xfer_done, 2 * HZ);
-	if (ret <= 0) {
+	timeout = wait_for_completion_timeout(&pic32s->xfer_done, 2 * HZ);
+	if (timeout == 0) {
 		dev_err(&spi->dev, "wait error/timedout\n");
 		if (dma_issued) {
 			dmaengine_terminate_all(master->dma_rx);