diff --git a/Documentation/devicetree/bindings/spi/qcom,spi-qup.txt b/Documentation/devicetree/bindings/spi/qcom,spi-qup.txt
index e2c88df2cc15..5c090771c016 100644
--- a/Documentation/devicetree/bindings/spi/qcom,spi-qup.txt
+++ b/Documentation/devicetree/bindings/spi/qcom,spi-qup.txt
@@ -33,6 +33,11 @@ Optional properties:
 		nodes.  If unspecified, a single SPI device without a chip
 		select can be used.
 
+- dmas:         Two DMA channel specifiers following the convention outlined
+                in bindings/dma/dma.txt
+- dma-names:    Names for the dma channels, if present. There must be at
+                least one channel named "tx" for transmit and named "rx" for
+                receive.
 
 SPI slave nodes must be children of the SPI master node and can contain
 properties described in Documentation/devicetree/bindings/spi/spi-bus.txt
@@ -51,6 +56,9 @@ Example:
 		clocks = <&gcc GCC_BLSP2_QUP2_SPI_APPS_CLK>, <&gcc GCC_BLSP2_AHB_CLK>;
 		clock-names = "core", "iface";
 
+		dmas = <&blsp1_bam 13>, <&blsp1_bam 12>;
+		dma-names = "rx", "tx";
+
 		pinctrl-names = "default";
 		pinctrl-0 = <&spi8_default>;
 
diff --git a/Documentation/devicetree/bindings/spi/spi-rockchip.txt b/Documentation/devicetree/bindings/spi/spi-rockchip.txt
index 467dec441c62..0c491bda4c65 100644
--- a/Documentation/devicetree/bindings/spi/spi-rockchip.txt
+++ b/Documentation/devicetree/bindings/spi/spi-rockchip.txt
@@ -24,6 +24,9 @@ Optional Properties:
 - dmas: DMA specifiers for tx and rx dma. See the DMA client binding,
 		Documentation/devicetree/bindings/dma/dma.txt
 - dma-names: DMA request names should include "tx" and "rx" if present.
+- rx-sample-delay-ns: nanoseconds to delay after the SCLK edge before sampling
+		Rx data (may need to be fine tuned for high capacitance lines).
+		No delay (0) by default.
 
 
 Example:
@@ -33,6 +36,7 @@ Example:
 		reg = <0xff110000 0x1000>;
 		dmas = <&pdma1 11>, <&pdma1 12>;
 		dma-names = "tx", "rx";
+		rx-sample-delay-ns = <10>;
 		#address-cells = <1>;
 		#size-cells = <0>;
 		interrupts = <GIC_SPI 44 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/drivers/spi/spi-qup.c b/drivers/spi/spi-qup.c
index 2b2c359f5a50..810a7fae3479 100644
--- a/drivers/spi/spi-qup.c
+++ b/drivers/spi/spi-qup.c
@@ -22,6 +22,8 @@
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/spi/spi.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
 
 #define QUP_CONFIG			0x0000
 #define QUP_STATE			0x0004
@@ -116,6 +118,8 @@
 
 #define SPI_NUM_CHIPSELECTS		4
 
+#define SPI_MAX_DMA_XFER		(SZ_64K - 64)
+
 /* high speed mode is when bus rate is greater then 26MHz */
 #define SPI_HS_MIN_RATE			26000000
 #define SPI_MAX_RATE			50000000
@@ -140,9 +144,14 @@ struct spi_qup {
 	struct completion	done;
 	int			error;
 	int			w_size;	/* bytes per SPI word */
+	int			n_words;
 	int			tx_bytes;
 	int			rx_bytes;
 	int			qup_v1;
+
+	int			use_dma;
+	struct dma_slave_config	rx_conf;
+	struct dma_slave_config	tx_conf;
 };
 
 
@@ -198,7 +207,6 @@ static int spi_qup_set_state(struct spi_qup *controller, u32 state)
 	return 0;
 }
 
-
 static void spi_qup_fifo_read(struct spi_qup *controller,
 			    struct spi_transfer *xfer)
 {
@@ -266,6 +274,107 @@ static void spi_qup_fifo_write(struct spi_qup *controller,
 	}
 }
 
+static void spi_qup_dma_done(void *data)
+{
+	struct spi_qup *qup = data;
+
+	complete(&qup->done);
+}
+
+static int spi_qup_prep_sg(struct spi_master *master, struct spi_transfer *xfer,
+			   enum dma_transfer_direction dir,
+			   dma_async_tx_callback callback)
+{
+	struct spi_qup *qup = spi_master_get_devdata(master);
+	unsigned long flags = DMA_PREP_INTERRUPT | DMA_PREP_FENCE;
+	struct dma_async_tx_descriptor *desc;
+	struct scatterlist *sgl;
+	struct dma_chan *chan;
+	dma_cookie_t cookie;
+	unsigned int nents;
+
+	if (dir == DMA_MEM_TO_DEV) {
+		chan = master->dma_tx;
+		nents = xfer->tx_sg.nents;
+		sgl = xfer->tx_sg.sgl;
+	} else {
+		chan = master->dma_rx;
+		nents = xfer->rx_sg.nents;
+		sgl = xfer->rx_sg.sgl;
+	}
+
+	desc = dmaengine_prep_slave_sg(chan, sgl, nents, dir, flags);
+	if (!desc)
+		return -EINVAL;
+
+	desc->callback = callback;
+	desc->callback_param = qup;
+
+	cookie = dmaengine_submit(desc);
+
+	return dma_submit_error(cookie);
+}
+
+static void spi_qup_dma_terminate(struct spi_master *master,
+				  struct spi_transfer *xfer)
+{
+	if (xfer->tx_buf)
+		dmaengine_terminate_all(master->dma_tx);
+	if (xfer->rx_buf)
+		dmaengine_terminate_all(master->dma_rx);
+}
+
+static int spi_qup_do_dma(struct spi_master *master, struct spi_transfer *xfer)
+{
+	dma_async_tx_callback rx_done = NULL, tx_done = NULL;
+	int ret;
+
+	if (xfer->rx_buf)
+		rx_done = spi_qup_dma_done;
+	else if (xfer->tx_buf)
+		tx_done = spi_qup_dma_done;
+
+	if (xfer->rx_buf) {
+		ret = spi_qup_prep_sg(master, xfer, DMA_DEV_TO_MEM, rx_done);
+		if (ret)
+			return ret;
+
+		dma_async_issue_pending(master->dma_rx);
+	}
+
+	if (xfer->tx_buf) {
+		ret = spi_qup_prep_sg(master, xfer, DMA_MEM_TO_DEV, tx_done);
+		if (ret)
+			return ret;
+
+		dma_async_issue_pending(master->dma_tx);
+	}
+
+	return 0;
+}
+
+static int spi_qup_do_pio(struct spi_master *master, struct spi_transfer *xfer)
+{
+	struct spi_qup *qup = spi_master_get_devdata(master);
+	int ret;
+
+	ret = spi_qup_set_state(qup, QUP_STATE_RUN);
+	if (ret) {
+		dev_warn(qup->dev, "cannot set RUN state\n");
+		return ret;
+	}
+
+	ret = spi_qup_set_state(qup, QUP_STATE_PAUSE);
+	if (ret) {
+		dev_warn(qup->dev, "cannot set PAUSE state\n");
+		return ret;
+	}
+
+	spi_qup_fifo_write(qup, xfer);
+
+	return 0;
+}
+
 static irqreturn_t spi_qup_qup_irq(int irq, void *dev_id)
 {
 	struct spi_qup *controller = dev_id;
@@ -315,11 +424,13 @@ static irqreturn_t spi_qup_qup_irq(int irq, void *dev_id)
 		error = -EIO;
 	}
 
-	if (opflags & QUP_OP_IN_SERVICE_FLAG)
-		spi_qup_fifo_read(controller, xfer);
+	if (!controller->use_dma) {
+		if (opflags & QUP_OP_IN_SERVICE_FLAG)
+			spi_qup_fifo_read(controller, xfer);
 
-	if (opflags & QUP_OP_OUT_SERVICE_FLAG)
-		spi_qup_fifo_write(controller, xfer);
+		if (opflags & QUP_OP_OUT_SERVICE_FLAG)
+			spi_qup_fifo_write(controller, xfer);
+	}
 
 	spin_lock_irqsave(&controller->lock, flags);
 	controller->error = error;
@@ -332,13 +443,35 @@ static irqreturn_t spi_qup_qup_irq(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+static u32
+spi_qup_get_mode(struct spi_master *master, struct spi_transfer *xfer)
+{
+	struct spi_qup *qup = spi_master_get_devdata(master);
+	u32 mode;
+
+	qup->w_size = 4;
+
+	if (xfer->bits_per_word <= 8)
+		qup->w_size = 1;
+	else if (xfer->bits_per_word <= 16)
+		qup->w_size = 2;
+
+	qup->n_words = xfer->len / qup->w_size;
+
+	if (qup->n_words <= (qup->in_fifo_sz / sizeof(u32)))
+		mode = QUP_IO_M_MODE_FIFO;
+	else
+		mode = QUP_IO_M_MODE_BLOCK;
+
+	return mode;
+}
 
 /* set clock freq ... bits per word */
 static int spi_qup_io_config(struct spi_device *spi, struct spi_transfer *xfer)
 {
 	struct spi_qup *controller = spi_master_get_devdata(spi->master);
 	u32 config, iomode, mode, control;
-	int ret, n_words, w_size;
+	int ret, n_words;
 
 	if (spi->mode & SPI_LOOP && xfer->len > controller->in_fifo_sz) {
 		dev_err(controller->dev, "too big size for loopback %d > %d\n",
@@ -358,35 +491,54 @@ static int spi_qup_io_config(struct spi_device *spi, struct spi_transfer *xfer)
 		return -EIO;
 	}
 
-	w_size = 4;
-	if (xfer->bits_per_word <= 8)
-		w_size = 1;
-	else if (xfer->bits_per_word <= 16)
-		w_size = 2;
+	mode = spi_qup_get_mode(spi->master, xfer);
+	n_words = controller->n_words;
 
-	n_words = xfer->len / w_size;
-	controller->w_size = w_size;
-
-	if (n_words <= (controller->in_fifo_sz / sizeof(u32))) {
-		mode = QUP_IO_M_MODE_FIFO;
+	if (mode == QUP_IO_M_MODE_FIFO) {
 		writel_relaxed(n_words, controller->base + QUP_MX_READ_CNT);
 		writel_relaxed(n_words, controller->base + QUP_MX_WRITE_CNT);
 		/* must be zero for FIFO */
 		writel_relaxed(0, controller->base + QUP_MX_INPUT_CNT);
 		writel_relaxed(0, controller->base + QUP_MX_OUTPUT_CNT);
-	} else {
-		mode = QUP_IO_M_MODE_BLOCK;
+	} else if (!controller->use_dma) {
 		writel_relaxed(n_words, controller->base + QUP_MX_INPUT_CNT);
 		writel_relaxed(n_words, controller->base + QUP_MX_OUTPUT_CNT);
 		/* must be zero for BLOCK and BAM */
 		writel_relaxed(0, controller->base + QUP_MX_READ_CNT);
 		writel_relaxed(0, controller->base + QUP_MX_WRITE_CNT);
+	} else {
+		mode = QUP_IO_M_MODE_BAM;
+		writel_relaxed(0, controller->base + QUP_MX_READ_CNT);
+		writel_relaxed(0, controller->base + QUP_MX_WRITE_CNT);
+
+		if (!controller->qup_v1) {
+			void __iomem *input_cnt;
+
+			input_cnt = controller->base + QUP_MX_INPUT_CNT;
+			/*
+			 * for DMA transfers, both QUP_MX_INPUT_CNT and
+			 * QUP_MX_OUTPUT_CNT must be zero to all cases but one.
+			 * That case is a non-balanced transfer when there is
+			 * only a rx_buf.
+			 */
+			if (xfer->tx_buf)
+				writel_relaxed(0, input_cnt);
+			else
+				writel_relaxed(n_words, input_cnt);
+
+			writel_relaxed(0, controller->base + QUP_MX_OUTPUT_CNT);
+		}
 	}
 
 	iomode = readl_relaxed(controller->base + QUP_IO_M_MODES);
 	/* Set input and output transfer mode */
 	iomode &= ~(QUP_IO_M_INPUT_MODE_MASK | QUP_IO_M_OUTPUT_MODE_MASK);
-	iomode &= ~(QUP_IO_M_PACK_EN | QUP_IO_M_UNPACK_EN);
+
+	if (!controller->use_dma)
+		iomode &= ~(QUP_IO_M_PACK_EN | QUP_IO_M_UNPACK_EN);
+	else
+		iomode |= QUP_IO_M_PACK_EN | QUP_IO_M_UNPACK_EN;
+
 	iomode |= (mode << QUP_IO_M_OUTPUT_MODE_MASK_SHIFT);
 	iomode |= (mode << QUP_IO_M_INPUT_MODE_MASK_SHIFT);
 
@@ -428,11 +580,31 @@ static int spi_qup_io_config(struct spi_device *spi, struct spi_transfer *xfer)
 	config &= ~(QUP_CONFIG_NO_INPUT | QUP_CONFIG_NO_OUTPUT | QUP_CONFIG_N);
 	config |= xfer->bits_per_word - 1;
 	config |= QUP_CONFIG_SPI_MODE;
+
+	if (controller->use_dma) {
+		if (!xfer->tx_buf)
+			config |= QUP_CONFIG_NO_OUTPUT;
+		if (!xfer->rx_buf)
+			config |= QUP_CONFIG_NO_INPUT;
+	}
+
 	writel_relaxed(config, controller->base + QUP_CONFIG);
 
 	/* only write to OPERATIONAL_MASK when register is present */
-	if (!controller->qup_v1)
-		writel_relaxed(0, controller->base + QUP_OPERATIONAL_MASK);
+	if (!controller->qup_v1) {
+		u32 mask = 0;
+
+		/*
+		 * mask INPUT and OUTPUT service flags to prevent IRQs on FIFO
+		 * status change in BAM mode
+		 */
+
+		if (mode == QUP_IO_M_MODE_BAM)
+			mask = QUP_OP_IN_SERVICE_FLAG | QUP_OP_OUT_SERVICE_FLAG;
+
+		writel_relaxed(mask, controller->base + QUP_OPERATIONAL_MASK);
+	}
+
 	return 0;
 }
 
@@ -461,17 +633,13 @@ static int spi_qup_transfer_one(struct spi_master *master,
 	controller->tx_bytes = 0;
 	spin_unlock_irqrestore(&controller->lock, flags);
 
-	if (spi_qup_set_state(controller, QUP_STATE_RUN)) {
-		dev_warn(controller->dev, "cannot set RUN state\n");
-		goto exit;
-	}
+	if (controller->use_dma)
+		ret = spi_qup_do_dma(master, xfer);
+	else
+		ret = spi_qup_do_pio(master, xfer);
 
-	if (spi_qup_set_state(controller, QUP_STATE_PAUSE)) {
-		dev_warn(controller->dev, "cannot set PAUSE state\n");
+	if (ret)
 		goto exit;
-	}
-
-	spi_qup_fifo_write(controller, xfer);
 
 	if (spi_qup_set_state(controller, QUP_STATE_RUN)) {
 		dev_warn(controller->dev, "cannot set EXECUTE state\n");
@@ -480,6 +648,7 @@ static int spi_qup_transfer_one(struct spi_master *master,
 
 	if (!wait_for_completion_timeout(&controller->done, timeout))
 		ret = -ETIMEDOUT;
+
 exit:
 	spi_qup_set_state(controller, QUP_STATE_RESET);
 	spin_lock_irqsave(&controller->lock, flags);
@@ -487,6 +656,97 @@ exit:
 	if (!ret)
 		ret = controller->error;
 	spin_unlock_irqrestore(&controller->lock, flags);
+
+	if (ret && controller->use_dma)
+		spi_qup_dma_terminate(master, xfer);
+
+	return ret;
+}
+
+static bool spi_qup_can_dma(struct spi_master *master, struct spi_device *spi,
+			    struct spi_transfer *xfer)
+{
+	struct spi_qup *qup = spi_master_get_devdata(master);
+	size_t dma_align = dma_get_cache_alignment();
+	u32 mode;
+
+	qup->use_dma = 0;
+
+	if (xfer->rx_buf && (xfer->len % qup->in_blk_sz ||
+	    IS_ERR_OR_NULL(master->dma_rx) ||
+	    !IS_ALIGNED((size_t)xfer->rx_buf, dma_align)))
+		return false;
+
+	if (xfer->tx_buf && (xfer->len % qup->out_blk_sz ||
+	    IS_ERR_OR_NULL(master->dma_tx) ||
+	    !IS_ALIGNED((size_t)xfer->tx_buf, dma_align)))
+		return false;
+
+	mode = spi_qup_get_mode(master, xfer);
+	if (mode == QUP_IO_M_MODE_FIFO)
+		return false;
+
+	qup->use_dma = 1;
+
+	return true;
+}
+
+static void spi_qup_release_dma(struct spi_master *master)
+{
+	if (!IS_ERR_OR_NULL(master->dma_rx))
+		dma_release_channel(master->dma_rx);
+	if (!IS_ERR_OR_NULL(master->dma_tx))
+		dma_release_channel(master->dma_tx);
+}
+
+static int spi_qup_init_dma(struct spi_master *master, resource_size_t base)
+{
+	struct spi_qup *spi = spi_master_get_devdata(master);
+	struct dma_slave_config *rx_conf = &spi->rx_conf,
+				*tx_conf = &spi->tx_conf;
+	struct device *dev = spi->dev;
+	int ret;
+
+	/* allocate dma resources, if available */
+	master->dma_rx = dma_request_slave_channel_reason(dev, "rx");
+	if (IS_ERR(master->dma_rx))
+		return PTR_ERR(master->dma_rx);
+
+	master->dma_tx = dma_request_slave_channel_reason(dev, "tx");
+	if (IS_ERR(master->dma_tx)) {
+		ret = PTR_ERR(master->dma_tx);
+		goto err_tx;
+	}
+
+	/* set DMA parameters */
+	rx_conf->direction = DMA_DEV_TO_MEM;
+	rx_conf->device_fc = 1;
+	rx_conf->src_addr = base + QUP_INPUT_FIFO;
+	rx_conf->src_maxburst = spi->in_blk_sz;
+
+	tx_conf->direction = DMA_MEM_TO_DEV;
+	tx_conf->device_fc = 1;
+	tx_conf->dst_addr = base + QUP_OUTPUT_FIFO;
+	tx_conf->dst_maxburst = spi->out_blk_sz;
+
+	ret = dmaengine_slave_config(master->dma_rx, rx_conf);
+	if (ret) {
+		dev_err(dev, "failed to configure RX channel\n");
+		goto err;
+	}
+
+	ret = dmaengine_slave_config(master->dma_tx, tx_conf);
+	if (ret) {
+		dev_err(dev, "failed to configure TX channel\n");
+		goto err;
+	}
+
+	return 0;
+
+err:
+	dma_release_channel(master->dma_tx);
+err_tx:
+	dma_release_channel(master->dma_rx);
 	return ret;
 }
 
@@ -563,6 +823,8 @@ static int spi_qup_probe(struct platform_device *pdev)
 	master->transfer_one = spi_qup_transfer_one;
 	master->dev.of_node = pdev->dev.of_node;
 	master->auto_runtime_pm = true;
+	master->dma_alignment = dma_get_cache_alignment();
+	master->max_dma_len = SPI_MAX_DMA_XFER;
 
 	platform_set_drvdata(pdev, master);
 
@@ -574,6 +836,12 @@ static int spi_qup_probe(struct platform_device *pdev)
 	controller->cclk = cclk;
 	controller->irq = irq;
 
+	ret = spi_qup_init_dma(master, res->start);
+	if (ret == -EPROBE_DEFER)
+		goto error;
+	else if (!ret)
+		master->can_dma = spi_qup_can_dma;
+
 	/* set v1 flag if device is version 1 */
 	if (of_device_is_compatible(dev->of_node, "qcom,spi-qup-v1.1.1"))
 		controller->qup_v1 = 1;
@@ -610,7 +878,7 @@ static int spi_qup_probe(struct platform_device *pdev)
 	ret = spi_qup_set_state(controller, QUP_STATE_RESET);
 	if (ret) {
 		dev_err(dev, "cannot set RESET state\n");
-		goto error;
+		goto error_dma;
 	}
 
 	writel_relaxed(0, base + QUP_OPERATIONAL);
@@ -634,7 +902,7 @@ static int spi_qup_probe(struct platform_device *pdev)
 	ret = devm_request_irq(dev, irq, spi_qup_qup_irq,
 			       IRQF_TRIGGER_HIGH, pdev->name, controller);
 	if (ret)
-		goto error;
+		goto error_dma;
 
 	pm_runtime_set_autosuspend_delay(dev, MSEC_PER_SEC);
 	pm_runtime_use_autosuspend(dev);
@@ -649,6 +917,8 @@ static int spi_qup_probe(struct platform_device *pdev)
 
 disable_pm:
 	pm_runtime_disable(&pdev->dev);
+error_dma:
+	spi_qup_release_dma(master);
 error:
 	clk_disable_unprepare(cclk);
 	clk_disable_unprepare(iclk);
@@ -740,6 +1010,8 @@ static int spi_qup_remove(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	spi_qup_release_dma(master);
+
 	clk_disable_unprepare(controller->cclk);
 	clk_disable_unprepare(controller->iclk);
 
diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c
index 5e4e52cbe053..68e7efeb9a27 100644
--- a/drivers/spi/spi-rockchip.c
+++ b/drivers/spi/spi-rockchip.c
@@ -179,6 +179,7 @@ struct rockchip_spi {
 	u8 tmode;
 	u8 bpw;
 	u8 n_bytes;
+	u8 rsd_nsecs;
 	unsigned len;
 	u32 speed;
 
@@ -302,8 +303,8 @@ static int rockchip_spi_prepare_message(struct spi_master *master,
 	return 0;
 }
 
-static int rockchip_spi_unprepare_message(struct spi_master *master,
-					  struct spi_message *msg)
+static void rockchip_spi_handle_err(struct spi_master *master,
+				    struct spi_message *msg)
 {
 	unsigned long flags;
 	struct rockchip_spi *rs = spi_master_get_devdata(master);
@@ -313,8 +314,8 @@ static int rockchip_spi_unprepare_message(struct spi_master *master,
 	/*
 	 * For DMA mode, we need terminate DMA channel and flush
 	 * fifo for the next transfer if DMA thansfer timeout.
-	 * unprepare_message() was called by core if transfer complete
-	 * or timeout. Maybe it is reasonable for error handling here.
+	 * handle_err() was called by core if transfer failed.
+	 * Maybe it is reasonable for error handling here.
 	 */
 	if (rs->use_dma) {
 		if (rs->state & RXBUSY) {
@@ -327,6 +328,12 @@ static int rockchip_spi_unprepare_message(struct spi_master *master,
 	}
 
 	spin_unlock_irqrestore(&rs->lock, flags);
+}
+
+static int rockchip_spi_unprepare_message(struct spi_master *master,
+					  struct spi_message *msg)
+{
+	struct rockchip_spi *rs = spi_master_get_devdata(master);
 
 	spi_enable_chip(rs, 0);
 
@@ -493,6 +500,7 @@ static void rockchip_spi_config(struct rockchip_spi *rs)
 {
 	u32 div = 0;
 	u32 dmacr = 0;
+	int rsd = 0;
 
 	u32 cr0 = (CR0_BHT_8BIT << CR0_BHT_OFFSET)
 		| (CR0_SSD_ONE << CR0_SSD_OFFSET);
@@ -522,6 +530,20 @@ static void rockchip_spi_config(struct rockchip_spi *rs)
 	div = DIV_ROUND_UP(rs->max_freq, rs->speed);
 	div = (div + 1) & 0xfffe;
 
+	/* Rx sample delay is expressed in parent clock cycles (max 3) */
+	rsd = DIV_ROUND_CLOSEST(rs->rsd_nsecs * (rs->max_freq >> 8),
+				1000000000 >> 8);
+	if (!rsd && rs->rsd_nsecs) {
+		pr_warn_once("rockchip-spi: %u Hz are too slow to express %u ns delay\n",
+			     rs->max_freq, rs->rsd_nsecs);
+	} else if (rsd > 3) {
+		rsd = 3;
+		pr_warn_once("rockchip-spi: %u Hz are too fast to express %u ns delay, clamping at %u ns\n",
+			     rs->max_freq, rs->rsd_nsecs,
+			     rsd * 1000000000U / rs->max_freq);
+	}
+	cr0 |= rsd << CR0_RSD_OFFSET;
+
 	writel_relaxed(cr0, rs->regs + ROCKCHIP_SPI_CTRLR0);
 
 	writel_relaxed(rs->len - 1, rs->regs + ROCKCHIP_SPI_CTRLR1);
@@ -614,6 +636,7 @@ static int rockchip_spi_probe(struct platform_device *pdev)
 	struct rockchip_spi *rs;
 	struct spi_master *master;
 	struct resource *mem;
+	u32 rsd_nsecs;
 
 	master = spi_alloc_master(&pdev->dev, sizeof(struct rockchip_spi));
 	if (!master)
@@ -665,6 +688,10 @@ static int rockchip_spi_probe(struct platform_device *pdev)
 	rs->dev = &pdev->dev;
 	rs->max_freq = clk_get_rate(rs->spiclk);
 
+	if (!of_property_read_u32(pdev->dev.of_node, "rx-sample-delay-ns",
+				  &rsd_nsecs))
+		rs->rsd_nsecs = rsd_nsecs;
+
 	rs->fifo_len = get_fifo_len(rs);
 	if (!rs->fifo_len) {
 		dev_err(&pdev->dev, "Failed to get fifo length\n");
@@ -688,6 +715,7 @@ static int rockchip_spi_probe(struct platform_device *pdev)
 	master->prepare_message = rockchip_spi_prepare_message;
 	master->unprepare_message = rockchip_spi_unprepare_message;
 	master->transfer_one = rockchip_spi_transfer_one;
+	master->handle_err = rockchip_spi_handle_err;
 
 	rs->dma_tx.ch = dma_request_slave_channel(rs->dev, "tx");
 	if (!rs->dma_tx.ch)
diff --git a/drivers/spi/spi-rspi.c b/drivers/spi/spi-rspi.c
index 46ce47076e63..186924aa4740 100644
--- a/drivers/spi/spi-rspi.c
+++ b/drivers/spi/spi-rspi.c
@@ -177,6 +177,13 @@
 #define SPBFCR_RXRST		0x40	/* Receive Buffer Data Reset */
 #define SPBFCR_TXTRG_MASK	0x30	/* Transmit Buffer Data Triggering Number */
 #define SPBFCR_RXTRG_MASK	0x07	/* Receive Buffer Data Triggering Number */
+/* QSPI on R-Car Gen2 */
+#define SPBFCR_TXTRG_1B		0x00	/* 31 bytes (1 byte available) */
+#define SPBFCR_TXTRG_32B	0x30	/* 0 byte (32 bytes available) */
+#define SPBFCR_RXTRG_1B		0x00	/* 1 byte (31 bytes available) */
+#define SPBFCR_RXTRG_32B	0x07	/* 32 bytes (0 byte available) */
+
+#define QSPI_BUFFER_SIZE        32u
 
 struct rspi_data {
 	void __iomem *addr;
@@ -366,6 +373,52 @@ static int qspi_set_config_register(struct rspi_data *rspi, int access_size)
 	return 0;
 }
 
+static void qspi_update(const struct rspi_data *rspi, u8 mask, u8 val, u8 reg)
+{
+	u8 data;
+
+	data = rspi_read8(rspi, reg);
+	data &= ~mask;
+	data |= (val & mask);
+	rspi_write8(rspi, data, reg);
+}
+
+static int qspi_set_send_trigger(struct rspi_data *rspi, unsigned int len)
+{
+	unsigned int n;
+
+	n = min(len, QSPI_BUFFER_SIZE);
+
+	if (len >= QSPI_BUFFER_SIZE) {
+		/* sets triggering number to 32 bytes */
+		qspi_update(rspi, SPBFCR_TXTRG_MASK,
+			     SPBFCR_TXTRG_32B, QSPI_SPBFCR);
+	} else {
+		/* sets triggering number to 1 byte */
+		qspi_update(rspi, SPBFCR_TXTRG_MASK,
+			     SPBFCR_TXTRG_1B, QSPI_SPBFCR);
+	}
+
+	return n;
+}
+
+static void qspi_set_receive_trigger(struct rspi_data *rspi, unsigned int len)
+{
+	unsigned int n;
+
+	n = min(len, QSPI_BUFFER_SIZE);
+
+	if (len >= QSPI_BUFFER_SIZE) {
+		/* sets triggering number to 32 bytes */
+		qspi_update(rspi, SPBFCR_RXTRG_MASK,
+			     SPBFCR_RXTRG_32B, QSPI_SPBFCR);
+	} else {
+		/* sets triggering number to 1 byte */
+		qspi_update(rspi, SPBFCR_RXTRG_MASK,
+			     SPBFCR_RXTRG_1B, QSPI_SPBFCR);
+	}
+}
+
 #define set_config_register(spi, n) spi->ops->set_config_register(spi, n)
 
 static void rspi_enable_irq(const struct rspi_data *rspi, u8 enable)
@@ -609,18 +662,28 @@ static bool rspi_can_dma(struct spi_master *master, struct spi_device *spi,
 	return __rspi_can_dma(rspi, xfer);
 }
 
+static int rspi_dma_check_then_transfer(struct rspi_data *rspi,
+					 struct spi_transfer *xfer)
+{
+	if (rspi->master->can_dma && __rspi_can_dma(rspi, xfer)) {
+		/* rx_buf can be NULL on RSPI on SH in TX-only Mode */
+		int ret = rspi_dma_transfer(rspi, &xfer->tx_sg,
+					xfer->rx_buf ? &xfer->rx_sg : NULL);
+		if (ret != -EAGAIN)
+			return 0;
+	}
+
+	return -EAGAIN;
+}
+
 static int rspi_common_transfer(struct rspi_data *rspi,
 				struct spi_transfer *xfer)
 {
 	int ret;
 
-	if (rspi->master->can_dma && __rspi_can_dma(rspi, xfer)) {
-		/* rx_buf can be NULL on RSPI on SH in TX-only Mode */
-		ret = rspi_dma_transfer(rspi, &xfer->tx_sg,
-					xfer->rx_buf ? &xfer->rx_sg : NULL);
-		if (ret != -EAGAIN)
-			return ret;
-	}
+	ret = rspi_dma_check_then_transfer(rspi, xfer);
+	if (ret != -EAGAIN)
+		return ret;
 
 	ret = rspi_pio_transfer(rspi, xfer->tx_buf, xfer->rx_buf, xfer->len);
 	if (ret < 0)
@@ -661,12 +724,59 @@ static int rspi_rz_transfer_one(struct spi_master *master,
 	return rspi_common_transfer(rspi, xfer);
 }
 
+static int qspi_trigger_transfer_out_int(struct rspi_data *rspi, const u8 *tx,
+					u8 *rx, unsigned int len)
+{
+	int i, n, ret;
+	int error;
+
+	while (len > 0) {
+		n = qspi_set_send_trigger(rspi, len);
+		qspi_set_receive_trigger(rspi, len);
+		if (n == QSPI_BUFFER_SIZE) {
+			error = rspi_wait_for_tx_empty(rspi);
+			if (error < 0) {
+				dev_err(&rspi->master->dev, "transmit timeout\n");
+				return error;
+			}
+			for (i = 0; i < n; i++)
+				rspi_write_data(rspi, *tx++);
+
+			error = rspi_wait_for_rx_full(rspi);
+			if (error < 0) {
+				dev_err(&rspi->master->dev, "receive timeout\n");
+				return error;
+			}
+			for (i = 0; i < n; i++)
+				*rx++ = rspi_read_data(rspi);
+		} else {
+			ret = rspi_pio_transfer(rspi, tx, rx, n);
+			if (ret < 0)
+				return ret;
+		}
+		len -= n;
+	}
+
+	return 0;
+}
+
 static int qspi_transfer_out_in(struct rspi_data *rspi,
 				struct spi_transfer *xfer)
 {
+	int ret;
+
 	qspi_receive_init(rspi);
 
-	return rspi_common_transfer(rspi, xfer);
+	ret = rspi_dma_check_then_transfer(rspi, xfer);
+	if (ret != -EAGAIN)
+		return ret;
+
+	ret = qspi_trigger_transfer_out_int(rspi, xfer->tx_buf,
+					    xfer->rx_buf, xfer->len);
+	if (ret < 0)
+		return ret;
+
+	return 0;
 }
 
 static int qspi_transfer_out(struct rspi_data *rspi, struct spi_transfer *xfer)
diff --git a/drivers/spi/spi-s3c64xx.c b/drivers/spi/spi-s3c64xx.c
index 9231c34b5a5c..b1c6731fbf27 100644
--- a/drivers/spi/spi-s3c64xx.c
+++ b/drivers/spi/spi-s3c64xx.c
@@ -324,7 +324,7 @@ static int s3c64xx_spi_prepare_transfer(struct spi_master *spi)
 
 		/* Acquire DMA channels */
 		sdd->rx_dma.ch = dma_request_slave_channel_compat(mask, filter,
-				   (void *)sdd->rx_dma.dmach, dev, "rx");
+				   (void *)(long)sdd->rx_dma.dmach, dev, "rx");
 		if (!sdd->rx_dma.ch) {
 			dev_err(dev, "Failed to get RX DMA channel\n");
 			ret = -EBUSY;
@@ -333,7 +333,7 @@ static int s3c64xx_spi_prepare_transfer(struct spi_master *spi)
 		spi->dma_rx = sdd->rx_dma.ch;
 
 		sdd->tx_dma.ch = dma_request_slave_channel_compat(mask, filter,
-				   (void *)sdd->tx_dma.dmach, dev, "tx");
+				   (void *)(long)sdd->tx_dma.dmach, dev, "tx");
 		if (!sdd->tx_dma.ch) {
 			dev_err(dev, "Failed to get TX DMA channel\n");
 			ret = -EBUSY;
diff --git a/drivers/spi/spi-sc18is602.c b/drivers/spi/spi-sc18is602.c
index 5a56acf8a43e..36af4d48a700 100644
--- a/drivers/spi/spi-sc18is602.c
+++ b/drivers/spi/spi-sc18is602.c
@@ -286,7 +286,7 @@ static int sc18is602_probe(struct i2c_client *client,
 			hw->freq = SC18IS602_CLOCK;
 		break;
 	}
-	master->bus_num = client->adapter->nr;
+	master->bus_num = np ? -1 : client->adapter->nr;
 	master->mode_bits = SPI_CPHA | SPI_CPOL | SPI_LSB_FIRST;
 	master->bits_per_word_mask = SPI_BPW_MASK(8);
 	master->setup = sc18is602_setup;