1 files changed, 246 insertions, 41 deletions

diff --git a/drivers/spi/spi-meson-spicc.c b/drivers/spi/spi-meson-spicc.c
index fc75492e50ff..6b9137307533 100644
--- a/drivers/spi/spi-meson-spicc.c
+++ b/drivers/spi/spi-meson-spicc.c
@@ -21,18 +21,26 @@
 #include <linux/interrupt.h>
 #include <linux/reset.h>
 #include <linux/pinctrl/consumer.h>
+#include <linux/dma-mapping.h>
 
 /*
- * The Meson SPICC controller could support DMA based transfers, but is not
- * implemented by the vendor code, and while having the registers documentation
- * it has never worked on the GXL Hardware.
- * The PIO mode is the only mode implemented, and due to badly designed HW :
- * - all transfers are cutted in 16 words burst because the FIFO hangs on
- *   TX underflow, and there is no TX "Half-Empty" interrupt, so we go by
- *   FIFO max size chunk only
- * - CS management is dumb, and goes UP between every burst, so is really a
- *   "Data Valid" signal than a Chip Select, GPIO link should be used instead
- *   to have a CS go down over the full transfer
+ * There are two modes for data transmission: PIO and DMA.
+ * When bits_per_word is 8, 16, 24, or 32, data is transferred using PIO mode.
+ * When bits_per_word is 64, DMA mode is used by default.
+ *
+ * DMA achieves a transfer with one or more SPI bursts, each SPI burst is made
+ * up of one or more DMA bursts. The DMA burst implementation mechanism is,
+ * For TX, when the number of words in TXFIFO is less than the preset
+ * reading threshold, SPICC starts a reading DMA burst, which reads the preset
+ * number of words from TX buffer, then writes them into TXFIFO.
+ * For RX, when the number of words in RXFIFO is greater than the preset
+ * writing threshold, SPICC starts a writing request burst, which reads the
+ * preset number of words from RXFIFO, then write them into RX buffer.
+ * DMA works if the transfer meets the following conditions,
+ * - 64 bits per word
+ * - The transfer length in word must be multiples of the dma_burst_len, and
+ *   the dma_burst_len should be one of 8,7...2, otherwise, it will be split
+ *   into several SPI bursts by this driver
  */
 
 #define SPICC_MAX_BURST	128
@@ -128,6 +136,23 @@
 
 #define SPICC_DWADDR	0x24	/* Write Address of DMA */
 
+#define SPICC_LD_CNTL0	0x28
+#define VSYNC_IRQ_SRC_SELECT		BIT(0)
+#define DMA_EN_SET_BY_VSYNC		BIT(2)
+#define XCH_EN_SET_BY_VSYNC		BIT(3)
+#define DMA_READ_COUNTER_EN		BIT(4)
+#define DMA_WRITE_COUNTER_EN		BIT(5)
+#define DMA_RADDR_LOAD_BY_VSYNC		BIT(6)
+#define DMA_WADDR_LOAD_BY_VSYNC		BIT(7)
+#define DMA_ADDR_LOAD_FROM_LD_ADDR	BIT(8)
+
+#define SPICC_LD_CNTL1	0x2c
+#define DMA_READ_COUNTER		GENMASK(15, 0)
+#define DMA_WRITE_COUNTER		GENMASK(31, 16)
+#define DMA_BURST_LEN_DEFAULT		8
+#define DMA_BURST_COUNT_MAX		0xffff
+#define SPI_BURST_LEN_MAX	(DMA_BURST_LEN_DEFAULT * DMA_BURST_COUNT_MAX)
+
 #define SPICC_ENH_CTL0	0x38	/* Enhanced Feature */
 #define SPICC_ENH_CLK_CS_DELAY_MASK	GENMASK(15, 0)
 #define SPICC_ENH_DATARATE_MASK		GENMASK(23, 16)
@@ -171,6 +196,9 @@ struct meson_spicc_device {
 	struct pinctrl			*pinctrl;
 	struct pinctrl_state		*pins_idle_high;
 	struct pinctrl_state		*pins_idle_low;
+	dma_addr_t			tx_dma;
+	dma_addr_t			rx_dma;
+	bool				using_dma;
 };
 
 #define pow2_clk_to_spicc(_div) container_of(_div, struct meson_spicc_device, pow2_div)
@@ -202,6 +230,148 @@ static void meson_spicc_oen_enable(struct meson_spicc_device *spicc)
 	writel_relaxed(conf, spicc->base + SPICC_ENH_CTL0);
 }
 
+static int meson_spicc_dma_map(struct meson_spicc_device *spicc,
+			       struct spi_transfer *t)
+{
+	struct device *dev = spicc->host->dev.parent;
+
+	if (!(t->tx_buf && t->rx_buf))
+		return -EINVAL;
+
+	t->tx_dma = dma_map_single(dev, (void *)t->tx_buf, t->len, DMA_TO_DEVICE);
+	if (dma_mapping_error(dev, t->tx_dma))
+		return -ENOMEM;
+
+	t->rx_dma = dma_map_single(dev, t->rx_buf, t->len, DMA_FROM_DEVICE);
+	if (dma_mapping_error(dev, t->rx_dma))
+		return -ENOMEM;
+
+	spicc->tx_dma = t->tx_dma;
+	spicc->rx_dma = t->rx_dma;
+
+	return 0;
+}
+
+static void meson_spicc_dma_unmap(struct meson_spicc_device *spicc,
+				  struct spi_transfer *t)
+{
+	struct device *dev = spicc->host->dev.parent;
+
+	if (t->tx_dma)
+		dma_unmap_single(dev, t->tx_dma, t->len, DMA_TO_DEVICE);
+	if (t->rx_dma)
+		dma_unmap_single(dev, t->rx_dma, t->len, DMA_FROM_DEVICE);
+}
+
+/*
+ * According to the remain words length, calculate a suitable spi burst length
+ * and a dma burst length for current spi burst
+ */
+static u32 meson_spicc_calc_dma_len(struct meson_spicc_device *spicc,
+				    u32 len, u32 *dma_burst_len)
+{
+	u32 i;
+
+	if (len <= spicc->data->fifo_size) {
+		*dma_burst_len = len;
+		return len;
+	}
+
+	*dma_burst_len = DMA_BURST_LEN_DEFAULT;
+
+	if (len == (SPI_BURST_LEN_MAX + 1))
+		return SPI_BURST_LEN_MAX - DMA_BURST_LEN_DEFAULT;
+
+	if (len >= SPI_BURST_LEN_MAX)
+		return SPI_BURST_LEN_MAX;
+
+	for (i = DMA_BURST_LEN_DEFAULT; i > 1; i--)
+		if ((len % i) == 0) {
+			*dma_burst_len = i;
+			return len;
+		}
+
+	i = len % DMA_BURST_LEN_DEFAULT;
+	len -= i;
+
+	if (i == 1)
+		len -= DMA_BURST_LEN_DEFAULT;
+
+	return len;
+}
+
+static void meson_spicc_setup_dma(struct meson_spicc_device *spicc)
+{
+	unsigned int len;
+	unsigned int dma_burst_len, dma_burst_count;
+	unsigned int count_en = 0;
+	unsigned int txfifo_thres = 0;
+	unsigned int read_req = 0;
+	unsigned int rxfifo_thres = 31;
+	unsigned int write_req = 0;
+	unsigned int ld_ctr1 = 0;
+
+	writel_relaxed(spicc->tx_dma, spicc->base + SPICC_DRADDR);
+	writel_relaxed(spicc->rx_dma, spicc->base + SPICC_DWADDR);
+
+	/* Set the max burst length to support a transmission with length of
+	 * no more than 1024 bytes(128 words), which must use the CS management
+	 * because of some strict timing requirements
+	 */
+	writel_bits_relaxed(SPICC_BURSTLENGTH_MASK, SPICC_BURSTLENGTH_MASK,
+			    spicc->base + SPICC_CONREG);
+
+	len = meson_spicc_calc_dma_len(spicc, spicc->xfer_remain,
+				       &dma_burst_len);
+	spicc->xfer_remain -= len;
+	dma_burst_count = DIV_ROUND_UP(len, dma_burst_len);
+	dma_burst_len--;
+
+	if (spicc->tx_dma) {
+		spicc->tx_dma += len;
+		count_en |= DMA_READ_COUNTER_EN;
+		txfifo_thres = spicc->data->fifo_size - dma_burst_len;
+		read_req = dma_burst_len;
+		ld_ctr1 |= FIELD_PREP(DMA_READ_COUNTER, dma_burst_count);
+	}
+
+	if (spicc->rx_dma) {
+		spicc->rx_dma += len;
+		count_en |= DMA_WRITE_COUNTER_EN;
+		rxfifo_thres = dma_burst_len;
+		write_req = dma_burst_len;
+		ld_ctr1 |= FIELD_PREP(DMA_WRITE_COUNTER, dma_burst_count);
+	}
+
+	writel_relaxed(count_en, spicc->base + SPICC_LD_CNTL0);
+	writel_relaxed(ld_ctr1, spicc->base + SPICC_LD_CNTL1);
+	writel_relaxed(SPICC_DMA_ENABLE
+		    | SPICC_DMA_URGENT
+		    | FIELD_PREP(SPICC_TXFIFO_THRESHOLD_MASK, txfifo_thres)
+		    | FIELD_PREP(SPICC_READ_BURST_MASK, read_req)
+		    | FIELD_PREP(SPICC_RXFIFO_THRESHOLD_MASK, rxfifo_thres)
+		    | FIELD_PREP(SPICC_WRITE_BURST_MASK, write_req),
+		    spicc->base + SPICC_DMAREG);
+}
+
+static irqreturn_t meson_spicc_dma_irq(struct meson_spicc_device *spicc)
+{
+	if (readl_relaxed(spicc->base + SPICC_DMAREG) & SPICC_DMA_ENABLE)
+		return IRQ_HANDLED;
+
+	if (spicc->xfer_remain) {
+		meson_spicc_setup_dma(spicc);
+	} else {
+		writel_bits_relaxed(SPICC_SMC, 0, spicc->base + SPICC_CONREG);
+		writel_relaxed(0, spicc->base + SPICC_INTREG);
+		writel_relaxed(0, spicc->base + SPICC_DMAREG);
+		meson_spicc_dma_unmap(spicc, spicc->xfer);
+		complete(&spicc->done);
+	}
+
+	return IRQ_HANDLED;
+}
+
 static inline bool meson_spicc_txfull(struct meson_spicc_device *spicc)
 {
 	return !!FIELD_GET(SPICC_TF,
@@ -293,6 +463,9 @@ static irqreturn_t meson_spicc_irq(int irq, void *data)
 
 	writel_bits_relaxed(SPICC_TC, SPICC_TC, spicc->base + SPICC_STATREG);
 
+	if (spicc->using_dma)
+		return meson_spicc_dma_irq(spicc);
+
 	/* Empty RX FIFO */
 	meson_spicc_rx(spicc);
 
@@ -426,9 +599,6 @@ static int meson_spicc_transfer_one(struct spi_controller *host,
 
 	meson_spicc_reset_fifo(spicc);
 
-	/* Setup burst */
-	meson_spicc_setup_burst(spicc);
-
 	/* Setup wait for completion */
 	reinit_completion(&spicc->done);
 
@@ -442,11 +612,36 @@ static int meson_spicc_transfer_one(struct spi_controller *host,
 	/* Increase it twice and add 200 ms tolerance */
 	timeout += timeout + 200;
 
-	/* Start burst */
-	writel_bits_relaxed(SPICC_XCH, SPICC_XCH, spicc->base + SPICC_CONREG);
+	if (xfer->bits_per_word == 64) {
+		int ret;
 
-	/* Enable interrupts */
-	writel_relaxed(SPICC_TC_EN, spicc->base + SPICC_INTREG);
+		/* dma_burst_len 1 can't trigger a dma burst */
+		if (xfer->len < 16)
+			return -EINVAL;
+
+		ret = meson_spicc_dma_map(spicc, xfer);
+		if (ret) {
+			meson_spicc_dma_unmap(spicc, xfer);
+			dev_err(host->dev.parent, "dma map failed\n");
+			return ret;
+		}
+
+		spicc->using_dma = true;
+		spicc->xfer_remain = DIV_ROUND_UP(xfer->len, spicc->bytes_per_word);
+		meson_spicc_setup_dma(spicc);
+		writel_relaxed(SPICC_TE_EN, spicc->base + SPICC_INTREG);
+		writel_bits_relaxed(SPICC_SMC, SPICC_SMC, spicc->base + SPICC_CONREG);
+	} else {
+		spicc->using_dma = false;
+		/* Setup burst */
+		meson_spicc_setup_burst(spicc);
+
+		/* Start burst */
+		writel_bits_relaxed(SPICC_XCH, SPICC_XCH, spicc->base + SPICC_CONREG);
+
+		/* Enable interrupts */
+		writel_relaxed(SPICC_TC_EN, spicc->base + SPICC_INTREG);
+	}
 
 	if (!wait_for_completion_timeout(&spicc->done, msecs_to_jiffies(timeout)))
 		return -ETIMEDOUT;
@@ -514,7 +709,9 @@ static int meson_spicc_prepare_message(struct spi_controller *host,
 	/* Setup no wait cycles by default */
 	writel_relaxed(0, spicc->base + SPICC_PERIODREG);
 
-	writel_bits_relaxed(SPICC_LBC_W1, 0, spicc->base + SPICC_TESTREG);
+	writel_bits_relaxed(SPICC_LBC_W1,
+			    spi->mode & SPI_LOOP ? SPICC_LBC_W1 : 0,
+			    spicc->base + SPICC_TESTREG);
 
 	return 0;
 }
@@ -543,6 +740,14 @@ static int meson_spicc_setup(struct spi_device *spi)
 	if (!spi->controller_state)
 		spi->controller_state = spi_controller_get_devdata(spi->controller);
 
+	/* DMA works at 64 bits, the rest works on PIO */
+	if (spi->bits_per_word != 8 &&
+	    spi->bits_per_word != 16 &&
+	    spi->bits_per_word != 24 &&
+	    spi->bits_per_word != 32 &&
+	    spi->bits_per_word != 64)
+		return -EINVAL;
+
 	return 0;
 }
 
@@ -644,15 +849,17 @@ static int meson_spicc_pow2_clk_init(struct meson_spicc_device *spicc)
 	snprintf(name, sizeof(name), "%s#pow2_fixed_div", dev_name(dev));
 	init.name = name;
 	init.ops = &clk_fixed_factor_ops;
-	init.flags = 0;
-	if (spicc->data->has_pclk)
+	if (spicc->data->has_pclk) {
+		init.flags = CLK_SET_RATE_PARENT;
 		parent_data[0].hw = __clk_get_hw(spicc->pclk);
-	else
+	} else {
+		init.flags = 0;
 		parent_data[0].hw = __clk_get_hw(spicc->core);
+	}
 	init.num_parents = 1;
 
-	pow2_fixed_div->mult = 1,
-	pow2_fixed_div->div = 4,
+	pow2_fixed_div->mult = 1;
+	pow2_fixed_div->div = 4;
 	pow2_fixed_div->hw.init = &init;
 
 	clk = devm_clk_register(dev, &pow2_fixed_div->hw);
@@ -670,9 +877,9 @@ static int meson_spicc_pow2_clk_init(struct meson_spicc_device *spicc)
 	parent_data[0].hw = &pow2_fixed_div->hw;
 	init.num_parents = 1;
 
-	spicc->pow2_div.shift = 16,
-	spicc->pow2_div.width = 3,
-	spicc->pow2_div.flags = CLK_DIVIDER_POWER_OF_TWO,
+	spicc->pow2_div.shift = 16;
+	spicc->pow2_div.width = 3;
+	spicc->pow2_div.flags = CLK_DIVIDER_POWER_OF_TWO;
 	spicc->pow2_div.reg = spicc->base + SPICC_CONREG;
 	spicc->pow2_div.hw.init = &init;
 
@@ -708,15 +915,17 @@ static int meson_spicc_enh_clk_init(struct meson_spicc_device *spicc)
 	snprintf(name, sizeof(name), "%s#enh_fixed_div", dev_name(dev));
 	init.name = name;
 	init.ops = &clk_fixed_factor_ops;
-	init.flags = 0;
-	if (spicc->data->has_pclk)
+	if (spicc->data->has_pclk) {
+		init.flags = CLK_SET_RATE_PARENT;
 		parent_data[0].hw = __clk_get_hw(spicc->pclk);
-	else
+	} else {
+		init.flags = 0;
 		parent_data[0].hw = __clk_get_hw(spicc->core);
+	}
 	init.num_parents = 1;
 
-	enh_fixed_div->mult = 1,
-	enh_fixed_div->div = 2,
+	enh_fixed_div->mult = 1;
+	enh_fixed_div->div = 2;
 	enh_fixed_div->hw.init = &init;
 
 	clk = devm_clk_register(dev, &enh_fixed_div->hw);
@@ -734,8 +943,8 @@ static int meson_spicc_enh_clk_init(struct meson_spicc_device *spicc)
 	parent_data[0].hw = &enh_fixed_div->hw;
 	init.num_parents = 1;
 
-	enh_div->shift	= 16,
-	enh_div->width	= 8,
+	enh_div->shift	= 16;
+	enh_div->width	= 8;
 	enh_div->reg = spicc->base + SPICC_ENH_CTL0;
 	enh_div->hw.init = &init;
 
@@ -755,8 +964,8 @@ static int meson_spicc_enh_clk_init(struct meson_spicc_device *spicc)
 	init.num_parents = 2;
 	init.flags = CLK_SET_RATE_PARENT;
 
-	mux->mask = 0x1,
-	mux->shift = 24,
+	mux->mask = 0x1;
+	mux->shift = 24;
 	mux->reg = spicc->base + SPICC_ENH_CTL0;
 	mux->hw.init = &init;
 
@@ -846,11 +1055,7 @@ static int meson_spicc_probe(struct platform_device *pdev)
 
 	host->num_chipselect = 4;
 	host->dev.of_node = pdev->dev.of_node;
-	host->mode_bits = SPI_CPHA | SPI_CPOL | SPI_CS_HIGH;
-	host->bits_per_word_mask = SPI_BPW_MASK(32) |
-				   SPI_BPW_MASK(24) |
-				   SPI_BPW_MASK(16) |
-				   SPI_BPW_MASK(8);
+	host->mode_bits = SPI_CPHA | SPI_CPOL | SPI_CS_HIGH | SPI_LOOP;
 	host->flags = (SPI_CONTROLLER_MUST_RX | SPI_CONTROLLER_MUST_TX);
 	host->min_speed_hz = spicc->data->min_speed_hz;
 	host->max_speed_hz = spicc->data->max_speed_hz;
@@ -943,7 +1148,7 @@ MODULE_DEVICE_TABLE(of, meson_spicc_of_match);
 
 static struct platform_driver meson_spicc_driver = {
 	.probe   = meson_spicc_probe,
-	.remove_new = meson_spicc_remove,
+	.remove = meson_spicc_remove,
 	.driver  = {
 		.name = "meson-spicc",
 		.of_match_table = of_match_ptr(meson_spicc_of_match),